diff options
Diffstat (limited to 'drivers')
834 files changed, 17561 insertions, 10321 deletions
diff --git a/drivers/acpi/acpica/nsaccess.c b/drivers/acpi/acpica/nsaccess.c index 3f045b5953b2..a0c1a665dfc1 100644 --- a/drivers/acpi/acpica/nsaccess.c +++ b/drivers/acpi/acpica/nsaccess.c @@ -99,13 +99,12 @@ acpi_status acpi_ns_root_initialize(void) * just create and link the new node(s) here. */ new_node = - ACPI_ALLOCATE_ZEROED(sizeof(struct acpi_namespace_node)); + acpi_ns_create_node(*ACPI_CAST_PTR(u32, init_val->name)); if (!new_node) { status = AE_NO_MEMORY; goto unlock_and_exit; } - ACPI_COPY_NAMESEG(new_node->name.ascii, init_val->name); new_node->descriptor_type = ACPI_DESC_TYPE_NAMED; new_node->type = init_val->type; diff --git a/drivers/acpi/internal.h b/drivers/acpi/internal.h index e6a5d997241c..cb8f70842249 100644 --- a/drivers/acpi/internal.h +++ b/drivers/acpi/internal.h @@ -9,6 +9,8 @@ #ifndef _ACPI_INTERNAL_H_ #define _ACPI_INTERNAL_H_ +#include <linux/idr.h> + #define PREFIX "ACPI: " int early_acpi_osi_init(void); @@ -96,9 +98,11 @@ void acpi_scan_table_handler(u32 event, void *table, void *context); extern struct list_head acpi_bus_id_list; +#define ACPI_MAX_DEVICE_INSTANCES 4096 + struct acpi_device_bus_id { const char *bus_id; - unsigned int instance_no; + struct ida instance_ida; struct list_head node; }; diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c index d93e400940a3..4e2d76b8b697 100644 --- a/drivers/acpi/processor_idle.c +++ b/drivers/acpi/processor_idle.c @@ -29,6 +29,7 @@ */ #ifdef CONFIG_X86 #include <asm/apic.h> +#include <asm/cpu.h> #endif #define _COMPONENT ACPI_PROCESSOR_COMPONENT @@ -541,6 +542,10 @@ static int acpi_idle_play_dead(struct cpuidle_device *dev, int index) wait_for_freeze(); } else return -ENODEV; + +#if defined(CONFIG_X86) && defined(CONFIG_HOTPLUG_CPU) + cond_wakeup_cpu0(); +#endif } /* Never reached */ diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c index a184529d8fa4..6efe7edd7b1e 100644 --- a/drivers/acpi/scan.c +++ b/drivers/acpi/scan.c @@ -479,9 +479,8 @@ static void acpi_device_del(struct acpi_device *device) list_for_each_entry(acpi_device_bus_id, &acpi_bus_id_list, node) if (!strcmp(acpi_device_bus_id->bus_id, acpi_device_hid(device))) { - if (acpi_device_bus_id->instance_no > 0) - acpi_device_bus_id->instance_no--; - else { + ida_simple_remove(&acpi_device_bus_id->instance_ida, device->pnp.instance_no); + if (ida_is_empty(&acpi_device_bus_id->instance_ida)) { list_del(&acpi_device_bus_id->node); kfree_const(acpi_device_bus_id->bus_id); kfree(acpi_device_bus_id); @@ -631,6 +630,21 @@ static struct acpi_device_bus_id *acpi_device_bus_id_match(const char *dev_id) return NULL; } +static int acpi_device_set_name(struct acpi_device *device, + struct acpi_device_bus_id *acpi_device_bus_id) +{ + struct ida *instance_ida = &acpi_device_bus_id->instance_ida; + int result; + + result = ida_simple_get(instance_ida, 0, ACPI_MAX_DEVICE_INSTANCES, GFP_KERNEL); + if (result < 0) + return result; + + device->pnp.instance_no = result; + dev_set_name(&device->dev, "%s:%02x", acpi_device_bus_id->bus_id, result); + return 0; +} + int acpi_device_add(struct acpi_device *device, void (*release)(struct device *)) { @@ -665,7 +679,9 @@ int acpi_device_add(struct acpi_device *device, acpi_device_bus_id = acpi_device_bus_id_match(acpi_device_hid(device)); if (acpi_device_bus_id) { - acpi_device_bus_id->instance_no++; + result = acpi_device_set_name(device, acpi_device_bus_id); + if (result) + goto err_unlock; } else { acpi_device_bus_id = kzalloc(sizeof(*acpi_device_bus_id), GFP_KERNEL); @@ -681,9 +697,16 @@ int acpi_device_add(struct acpi_device *device, goto err_unlock; } + ida_init(&acpi_device_bus_id->instance_ida); + + result = acpi_device_set_name(device, acpi_device_bus_id); + if (result) { + kfree(acpi_device_bus_id); + goto err_unlock; + } + list_add_tail(&acpi_device_bus_id->node, &acpi_bus_id_list); } - dev_set_name(&device->dev, "%s:%02x", acpi_device_bus_id->bus_id, acpi_device_bus_id->instance_no); if (device->parent) list_add_tail(&device->node, &device->parent->children); @@ -1647,6 +1670,8 @@ void acpi_init_device_object(struct acpi_device *device, acpi_handle handle, device_initialize(&device->dev); dev_set_uevent_suppress(&device->dev, true); acpi_init_coherency(device); + /* Assume there are unmet deps to start with. */ + device->dep_unmet = 1; } void acpi_device_add_finalize(struct acpi_device *device) @@ -1910,6 +1935,8 @@ static void acpi_scan_dep_init(struct acpi_device *adev) { struct acpi_dep_data *dep; + adev->dep_unmet = 0; + mutex_lock(&acpi_dep_list_lock); list_for_each_entry(dep, &acpi_dep_list, node) { @@ -1957,7 +1984,13 @@ static acpi_status acpi_bus_check_add(acpi_handle handle, bool check_dep, return AE_CTRL_DEPTH; acpi_scan_init_hotplug(device); - if (!check_dep) + /* + * If check_dep is true at this point, the device has no dependencies, + * or the creation of the device object would have been postponed above. + */ + if (check_dep) + device->dep_unmet = 0; + else acpi_scan_dep_init(device); out: diff --git a/drivers/acpi/tables.c b/drivers/acpi/tables.c index e48690a006a4..9d581045acff 100644 --- a/drivers/acpi/tables.c +++ b/drivers/acpi/tables.c @@ -780,7 +780,7 @@ acpi_status acpi_os_table_override(struct acpi_table_header *existing_table, } /* - * acpi_table_init() + * acpi_locate_initial_tables() * * find RSDP, find and checksum SDT/XSDT. * checksum all tables, print SDT/XSDT @@ -788,7 +788,7 @@ acpi_status acpi_os_table_override(struct acpi_table_header *existing_table, * result: sdt_entry[] is initialized */ -int __init acpi_table_init(void) +int __init acpi_locate_initial_tables(void) { acpi_status status; @@ -803,9 +803,45 @@ int __init acpi_table_init(void) status = acpi_initialize_tables(initial_tables, ACPI_MAX_TABLES, 0); if (ACPI_FAILURE(status)) return -EINVAL; - acpi_table_initrd_scan(); + return 0; +} + +void __init acpi_reserve_initial_tables(void) +{ + int i; + + for (i = 0; i < ACPI_MAX_TABLES; i++) { + struct acpi_table_desc *table_desc = &initial_tables[i]; + u64 start = table_desc->address; + u64 size = table_desc->length; + + if (!start || !size) + break; + + pr_info("Reserving %4s table memory at [mem 0x%llx-0x%llx]\n", + table_desc->signature.ascii, start, start + size - 1); + + memblock_reserve(start, size); + } +} + +void __init acpi_table_init_complete(void) +{ + acpi_table_initrd_scan(); check_multiple_madt(); +} + +int __init acpi_table_init(void) +{ + int ret; + + ret = acpi_locate_initial_tables(); + if (ret) + return ret; + + acpi_table_init_complete(); + return 0; } diff --git a/drivers/acpi/video_detect.c b/drivers/acpi/video_detect.c index 811d298637cb..83cd4c95faf0 100644 --- a/drivers/acpi/video_detect.c +++ b/drivers/acpi/video_detect.c @@ -147,6 +147,7 @@ static const struct dmi_system_id video_detect_dmi_table[] = { }, }, { + .callback = video_detect_force_vendor, .ident = "Sony VPCEH3U1E", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Sony Corporation"), diff --git a/drivers/atm/fore200e.c b/drivers/atm/fore200e.c index 9a70bee84125..495fd0a1f040 100644 --- a/drivers/atm/fore200e.c +++ b/drivers/atm/fore200e.c @@ -100,8 +100,6 @@ static LIST_HEAD(fore200e_boards); MODULE_AUTHOR("Christophe Lizzi - credits to Uwe Dannowski and Heikki Vatiainen"); MODULE_DESCRIPTION("FORE Systems 200E-series ATM driver - version " FORE200E_VERSION); -MODULE_SUPPORTED_DEVICE("PCA-200E, SBA-200E"); - static const int fore200e_rx_buf_nbr[ BUFFER_SCHEME_NBR ][ BUFFER_MAGN_NBR ] = { { BUFFER_S1_NBR, BUFFER_L1_NBR }, diff --git a/drivers/auxdisplay/charlcd.c b/drivers/auxdisplay/charlcd.c index f43430e9dcee..24fd6f369ebe 100644 --- a/drivers/auxdisplay/charlcd.c +++ b/drivers/auxdisplay/charlcd.c @@ -470,12 +470,14 @@ static ssize_t charlcd_write(struct file *file, const char __user *buf, char c; for (; count-- > 0; (*ppos)++, tmp++) { - if (!in_interrupt() && (((count + 1) & 0x1f) == 0)) + if (((count + 1) & 0x1f) == 0) { /* - * let's be a little nice with other processes - * that need some CPU + * charlcd_write() is invoked as a VFS->write() callback + * and as such it is always invoked from preemptible + * context and may sleep. */ - schedule(); + cond_resched(); + } if (get_user(c, tmp)) return -EFAULT; @@ -537,12 +539,8 @@ static void charlcd_puts(struct charlcd *lcd, const char *s) int count = strlen(s); for (; count-- > 0; tmp++) { - if (!in_interrupt() && (((count + 1) & 0x1f) == 0)) - /* - * let's be a little nice with other processes - * that need some CPU - */ - schedule(); + if (((count + 1) & 0x1f) == 0) + cond_resched(); charlcd_write_char(lcd, *tmp); } diff --git a/drivers/base/dd.c b/drivers/base/dd.c index 9179825ff646..37a5e5f8b221 100644 --- a/drivers/base/dd.c +++ b/drivers/base/dd.c @@ -97,6 +97,9 @@ static void deferred_probe_work_func(struct work_struct *work) get_device(dev); + kfree(dev->p->deferred_probe_reason); + dev->p->deferred_probe_reason = NULL; + /* * Drop the mutex while probing each device; the probe path may * manipulate the deferred list @@ -289,14 +292,16 @@ int driver_deferred_probe_check_state(struct device *dev) static void deferred_probe_timeout_work_func(struct work_struct *work) { - struct device_private *private, *p; + struct device_private *p; driver_deferred_probe_timeout = 0; driver_deferred_probe_trigger(); flush_work(&deferred_probe_work); - list_for_each_entry_safe(private, p, &deferred_probe_pending_list, deferred_probe) - dev_info(private->device, "deferred probe pending\n"); + mutex_lock(&deferred_probe_mutex); + list_for_each_entry(p, &deferred_probe_pending_list, deferred_probe) + dev_info(p->device, "deferred probe pending\n"); + mutex_unlock(&deferred_probe_mutex); wake_up_all(&probe_timeout_waitqueue); } static DECLARE_DELAYED_WORK(deferred_probe_timeout_work, deferred_probe_timeout_work_func); diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c index 18b82427d0cb..fe1dad68aee4 100644 --- a/drivers/base/power/runtime.c +++ b/drivers/base/power/runtime.c @@ -305,7 +305,7 @@ static int rpm_get_suppliers(struct device *dev) return 0; } -static void rpm_put_suppliers(struct device *dev) +static void __rpm_put_suppliers(struct device *dev, bool try_to_suspend) { struct device_link *link; @@ -313,10 +313,30 @@ static void rpm_put_suppliers(struct device *dev) device_links_read_lock_held()) { while (refcount_dec_not_one(&link->rpm_active)) - pm_runtime_put(link->supplier); + pm_runtime_put_noidle(link->supplier); + + if (try_to_suspend) + pm_request_idle(link->supplier); } } +static void rpm_put_suppliers(struct device *dev) +{ + __rpm_put_suppliers(dev, true); +} + +static void rpm_suspend_suppliers(struct device *dev) +{ + struct device_link *link; + int idx = device_links_read_lock(); + + list_for_each_entry_rcu(link, &dev->links.suppliers, c_node, + device_links_read_lock_held()) + pm_request_idle(link->supplier); + + device_links_read_unlock(idx); +} + /** * __rpm_callback - Run a given runtime PM callback for a given device. * @cb: Runtime PM callback to run. @@ -325,27 +345,29 @@ static void rpm_put_suppliers(struct device *dev) static int __rpm_callback(int (*cb)(struct device *), struct device *dev) __releases(&dev->power.lock) __acquires(&dev->power.lock) { - bool use_links = dev->power.links_count > 0; - bool get = false; int retval, idx; - bool put; + bool use_links = dev->power.links_count > 0; if (dev->power.irq_safe) { spin_unlock(&dev->power.lock); - } else if (!use_links) { - spin_unlock_irq(&dev->power.lock); } else { - get = dev->power.runtime_status == RPM_RESUMING; - spin_unlock_irq(&dev->power.lock); - /* Resume suppliers if necessary. */ - if (get) { + /* + * Resume suppliers if necessary. + * + * The device's runtime PM status cannot change until this + * routine returns, so it is safe to read the status outside of + * the lock. + */ + if (use_links && dev->power.runtime_status == RPM_RESUMING) { idx = device_links_read_lock(); retval = rpm_get_suppliers(dev); - if (retval) + if (retval) { + rpm_put_suppliers(dev); goto fail; + } device_links_read_unlock(idx); } @@ -355,36 +377,24 @@ static int __rpm_callback(int (*cb)(struct device *), struct device *dev) if (dev->power.irq_safe) { spin_lock(&dev->power.lock); - return retval; - } - - spin_lock_irq(&dev->power.lock); - - if (!use_links) - return retval; - - /* - * If the device is suspending and the callback has returned success, - * drop the usage counters of the suppliers that have been reference - * counted on its resume. - * - * Do that if the resume fails too. - */ - put = dev->power.runtime_status == RPM_SUSPENDING && !retval; - if (put) - __update_runtime_status(dev, RPM_SUSPENDED); - else - put = get && retval; - - if (put) { - spin_unlock_irq(&dev->power.lock); + } else { + /* + * If the device is suspending and the callback has returned + * success, drop the usage counters of the suppliers that have + * been reference counted on its resume. + * + * Do that if resume fails too. + */ + if (use_links + && ((dev->power.runtime_status == RPM_SUSPENDING && !retval) + || (dev->power.runtime_status == RPM_RESUMING && retval))) { + idx = device_links_read_lock(); - idx = device_links_read_lock(); + __rpm_put_suppliers(dev, false); fail: - rpm_put_suppliers(dev); - - device_links_read_unlock(idx); + device_links_read_unlock(idx); + } spin_lock_irq(&dev->power.lock); } @@ -654,8 +664,11 @@ static int rpm_suspend(struct device *dev, int rpmflags) goto out; } + if (dev->power.irq_safe) + goto out; + /* Maybe the parent is now able to suspend. */ - if (parent && !parent->power.ignore_children && !dev->power.irq_safe) { + if (parent && !parent->power.ignore_children) { spin_unlock(&dev->power.lock); spin_lock(&parent->power.lock); @@ -664,6 +677,14 @@ static int rpm_suspend(struct device *dev, int rpmflags) spin_lock(&dev->power.lock); } + /* Maybe the suppliers are now able to suspend. */ + if (dev->power.links_count > 0) { + spin_unlock_irq(&dev->power.lock); + + rpm_suspend_suppliers(dev); + + spin_lock_irq(&dev->power.lock); + } out: trace_rpm_return_int_rcuidle(dev, _THIS_IP_, retval); @@ -1669,8 +1690,8 @@ void pm_runtime_get_suppliers(struct device *dev) device_links_read_lock_held()) if (link->flags & DL_FLAG_PM_RUNTIME) { link->supplier_preactivated = true; - refcount_inc(&link->rpm_active); pm_runtime_get_sync(link->supplier); + refcount_inc(&link->rpm_active); } device_links_read_unlock(idx); @@ -1683,6 +1704,8 @@ void pm_runtime_get_suppliers(struct device *dev) void pm_runtime_put_suppliers(struct device *dev) { struct device_link *link; + unsigned long flags; + bool put; int idx; idx = device_links_read_lock(); @@ -1691,7 +1714,11 @@ void pm_runtime_put_suppliers(struct device *dev) device_links_read_lock_held()) if (link->supplier_preactivated) { link->supplier_preactivated = false; - if (refcount_dec_not_one(&link->rpm_active)) + spin_lock_irqsave(&dev->power.lock, flags); + put = pm_runtime_status_suspended(dev) && + refcount_dec_not_one(&link->rpm_active); + spin_unlock_irqrestore(&dev->power.lock, flags); + if (put) pm_runtime_put(link->supplier); } diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c index 0b71292d9d5a..4aa9683ee0c1 100644 --- a/drivers/block/floppy.c +++ b/drivers/block/floppy.c @@ -5091,7 +5091,6 @@ module_param(floppy, charp, 0); module_param(FLOPPY_IRQ, int, 0); module_param(FLOPPY_DMA, int, 0); MODULE_AUTHOR("Alain L. Knaff"); -MODULE_SUPPORTED_DEVICE("fd"); MODULE_LICENSE("GPL"); /* This doesn't actually get used other than for module information */ diff --git a/drivers/block/null_blk/main.c b/drivers/block/null_blk/main.c index d6c821d48090..51bfd7737552 100644 --- a/drivers/block/null_blk/main.c +++ b/drivers/block/null_blk/main.c @@ -1369,10 +1369,13 @@ static blk_status_t null_handle_cmd(struct nullb_cmd *cmd, sector_t sector, } if (dev->zoned) - cmd->error = null_process_zoned_cmd(cmd, op, - sector, nr_sectors); + sts = null_process_zoned_cmd(cmd, op, sector, nr_sectors); else - cmd->error = null_process_cmd(cmd, op, sector, nr_sectors); + sts = null_process_cmd(cmd, op, sector, nr_sectors); + + /* Do not overwrite errors (e.g. timeout errors) */ + if (cmd->error == BLK_STS_OK) + cmd->error = sts; out: nullb_complete_cmd(cmd); @@ -1451,8 +1454,20 @@ static bool should_requeue_request(struct request *rq) static enum blk_eh_timer_return null_timeout_rq(struct request *rq, bool res) { + struct nullb_cmd *cmd = blk_mq_rq_to_pdu(rq); + pr_info("rq %p timed out\n", rq); - blk_mq_complete_request(rq); + + /* + * If the device is marked as blocking (i.e. memory backed or zoned + * device), the submission path may be blocked waiting for resources + * and cause real timeouts. For these real timeouts, the submission + * path will complete the request using blk_mq_complete_request(). + * Only fake timeouts need to execute blk_mq_complete_request() here. + */ + cmd->error = BLK_STS_TIMEOUT; + if (cmd->fake_timeout) + blk_mq_complete_request(rq); return BLK_EH_DONE; } @@ -1473,6 +1488,7 @@ static blk_status_t null_queue_rq(struct blk_mq_hw_ctx *hctx, cmd->rq = bd->rq; cmd->error = BLK_STS_OK; cmd->nq = nq; + cmd->fake_timeout = should_timeout_request(bd->rq); blk_mq_start_request(bd->rq); @@ -1489,7 +1505,7 @@ static blk_status_t null_queue_rq(struct blk_mq_hw_ctx *hctx, return BLK_STS_OK; } } - if (should_timeout_request(bd->rq)) + if (cmd->fake_timeout) return BLK_STS_OK; return null_handle_cmd(cmd, sector, nr_sectors, req_op(bd->rq)); diff --git a/drivers/block/null_blk/null_blk.h b/drivers/block/null_blk/null_blk.h index 83504f3cc9d6..4876d5adb12d 100644 --- a/drivers/block/null_blk/null_blk.h +++ b/drivers/block/null_blk/null_blk.h @@ -22,6 +22,7 @@ struct nullb_cmd { blk_status_t error; struct nullb_queue *nq; struct hrtimer timer; + bool fake_timeout; }; struct nullb_queue { diff --git a/drivers/block/xen-blkback/blkback.c b/drivers/block/xen-blkback/blkback.c index 1cdf09ff67b6..14e452896d04 100644 --- a/drivers/block/xen-blkback/blkback.c +++ b/drivers/block/xen-blkback/blkback.c @@ -891,7 +891,7 @@ next: out: for (i = last_map; i < num; i++) { /* Don't zap current batch's valid persistent grants. */ - if(i >= last_map + segs_to_map) + if(i >= map_until) pages[i]->persistent_gnt = NULL; pages[i]->handle = BLKBACK_INVALID_HANDLE; } diff --git a/drivers/bluetooth/btrsi.c b/drivers/bluetooth/btrsi.c index 3951f7b23840..bea1595f6432 100644 --- a/drivers/bluetooth/btrsi.c +++ b/drivers/bluetooth/btrsi.c @@ -194,5 +194,4 @@ module_init(rsi_91x_bt_module_init); module_exit(rsi_91x_bt_module_exit); MODULE_AUTHOR("Redpine Signals Inc"); MODULE_DESCRIPTION("RSI BT driver"); -MODULE_SUPPORTED_DEVICE("RSI-BT"); MODULE_LICENSE("Dual BSD/GPL"); diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index 52683fd22e05..5cbfbd948f67 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -4849,8 +4849,8 @@ static int btusb_probe(struct usb_interface *intf, data->diag = NULL; } - if (!enable_autosuspend) - usb_disable_autosuspend(data->udev); + if (enable_autosuspend) + usb_enable_autosuspend(data->udev); err = hci_register_dev(hdev); if (err < 0) @@ -4910,9 +4910,6 @@ static void btusb_disconnect(struct usb_interface *intf) gpiod_put(data->reset_gpio); hci_free_dev(hdev); - - if (!enable_autosuspend) - usb_enable_autosuspend(data->udev); } #ifdef CONFIG_PM diff --git a/drivers/bus/moxtet.c b/drivers/bus/moxtet.c index b20fdcbd035b..fd87a59837fa 100644 --- a/drivers/bus/moxtet.c +++ b/drivers/bus/moxtet.c @@ -2,7 +2,7 @@ /* * Turris Mox module configuration bus driver * - * Copyright (C) 2019 Marek Behun <marek.behun@nic.cz> + * Copyright (C) 2019 Marek Behún <kabel@kernel.org> */ #include <dt-bindings/bus/moxtet.h> @@ -879,6 +879,6 @@ static void __exit moxtet_exit(void) } module_exit(moxtet_exit); -MODULE_AUTHOR("Marek Behun <marek.behun@nic.cz>"); +MODULE_AUTHOR("Marek Behun <kabel@kernel.org>"); MODULE_DESCRIPTION("CZ.NIC's Turris Mox module configuration bus"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/bus/mvebu-mbus.c b/drivers/bus/mvebu-mbus.c index dd9e7343a5e3..ea0424922de7 100644 --- a/drivers/bus/mvebu-mbus.c +++ b/drivers/bus/mvebu-mbus.c @@ -618,7 +618,7 @@ mvebu_mbus_find_bridge_hole(uint64_t *start, uint64_t *end) * This part of the memory is above 4 GB, so we don't * care for the MBus bridge hole. */ - if (reg_start >= 0x100000000ULL) + if ((u64)reg_start >= 0x100000000ULL) continue; /* diff --git a/drivers/bus/omap_l3_noc.c b/drivers/bus/omap_l3_noc.c index b040447575ad..dcfb32ee5cb6 100644 --- a/drivers/bus/omap_l3_noc.c +++ b/drivers/bus/omap_l3_noc.c @@ -285,7 +285,7 @@ static int omap_l3_probe(struct platform_device *pdev) */ l3->debug_irq = platform_get_irq(pdev, 0); ret = devm_request_irq(l3->dev, l3->debug_irq, l3_interrupt_handler, - 0x0, "l3-dbg-irq", l3); + IRQF_NO_THREAD, "l3-dbg-irq", l3); if (ret) { dev_err(l3->dev, "request_irq failed for %d\n", l3->debug_irq); @@ -294,7 +294,7 @@ static int omap_l3_probe(struct platform_device *pdev) l3->app_irq = platform_get_irq(pdev, 1); ret = devm_request_irq(l3->dev, l3->app_irq, l3_interrupt_handler, - 0x0, "l3-app-irq", l3); + IRQF_NO_THREAD, "l3-app-irq", l3); if (ret) dev_err(l3->dev, "request_irq failed for %d\n", l3->app_irq); diff --git a/drivers/bus/ti-sysc.c b/drivers/bus/ti-sysc.c index a27d751cf219..3d74f237f005 100644 --- a/drivers/bus/ti-sysc.c +++ b/drivers/bus/ti-sysc.c @@ -3053,7 +3053,9 @@ static int sysc_remove(struct platform_device *pdev) pm_runtime_put_sync(&pdev->dev); pm_runtime_disable(&pdev->dev); - reset_control_assert(ddata->rsts); + + if (!reset_control_status(ddata->rsts)) + reset_control_assert(ddata->rsts); unprepare: sysc_unprepare(ddata); diff --git a/drivers/char/agp/Kconfig b/drivers/char/agp/Kconfig index a086dd34f932..4f501e4842ab 100644 --- a/drivers/char/agp/Kconfig +++ b/drivers/char/agp/Kconfig @@ -125,7 +125,7 @@ config AGP_HP_ZX1 config AGP_PARISC tristate "HP Quicksilver AGP support" - depends on AGP && PARISC && 64BIT + depends on AGP && PARISC && 64BIT && IOMMU_SBA help This option gives you AGP GART support for the HP Quicksilver AGP bus adapter on HP PA-RISC machines (Ok, just on the C8000 diff --git a/drivers/char/applicom.c b/drivers/char/applicom.c index 14b2d8034c51..45ac7ab003ce 100644 --- a/drivers/char/applicom.c +++ b/drivers/char/applicom.c @@ -81,9 +81,6 @@ MODULE_DESCRIPTION("Driver for Applicom Profibus card"); MODULE_LICENSE("GPL"); MODULE_ALIAS_MISCDEV(AC_MINOR); -MODULE_SUPPORTED_DEVICE("ac"); - - static struct applicom_board { unsigned long PhysIO; void __iomem *RamIO; diff --git a/drivers/char/toshiba.c b/drivers/char/toshiba.c index aff0a8e44fff..776abbfd85d6 100644 --- a/drivers/char/toshiba.c +++ b/drivers/char/toshiba.c @@ -64,7 +64,6 @@ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Jonathan Buzzard <jonathan@buzzard.org.uk>"); MODULE_DESCRIPTION("Toshiba laptop SMM driver"); -MODULE_SUPPORTED_DEVICE("toshiba"); static DEFINE_MUTEX(tosh_mutex); static int tosh_fn; diff --git a/drivers/clk/clk-fixed-factor.c b/drivers/clk/clk-fixed-factor.c index 4f7bf3929d6d..4e4b6d367612 100644 --- a/drivers/clk/clk-fixed-factor.c +++ b/drivers/clk/clk-fixed-factor.c @@ -66,7 +66,14 @@ EXPORT_SYMBOL_GPL(clk_fixed_factor_ops); static void devm_clk_hw_register_fixed_factor_release(struct device *dev, void *res) { - clk_hw_unregister_fixed_factor(&((struct clk_fixed_factor *)res)->hw); + struct clk_fixed_factor *fix = res; + + /* + * We can not use clk_hw_unregister_fixed_factor, since it will kfree() + * the hw, resulting in double free. Just unregister the hw and let + * devres code kfree() it. + */ + clk_hw_unregister(&fix->hw); } static struct clk_hw * diff --git a/drivers/clk/clk-mux.c b/drivers/clk/clk-mux.c index e54e79714818..20582aae7a35 100644 --- a/drivers/clk/clk-mux.c +++ b/drivers/clk/clk-mux.c @@ -8,6 +8,7 @@ */ #include <linux/clk-provider.h> +#include <linux/device.h> #include <linux/module.h> #include <linux/slab.h> #include <linux/io.h> @@ -206,6 +207,40 @@ struct clk_hw *__clk_hw_register_mux(struct device *dev, struct device_node *np, } EXPORT_SYMBOL_GPL(__clk_hw_register_mux); +static void devm_clk_hw_release_mux(struct device *dev, void *res) +{ + clk_hw_unregister_mux(*(struct clk_hw **)res); +} + +struct clk_hw *__devm_clk_hw_register_mux(struct device *dev, struct device_node *np, + const char *name, u8 num_parents, + const char * const *parent_names, + const struct clk_hw **parent_hws, + const struct clk_parent_data *parent_data, + unsigned long flags, void __iomem *reg, u8 shift, u32 mask, + u8 clk_mux_flags, u32 *table, spinlock_t *lock) +{ + struct clk_hw **ptr, *hw; + + ptr = devres_alloc(devm_clk_hw_release_mux, sizeof(*ptr), GFP_KERNEL); + if (!ptr) + return ERR_PTR(-ENOMEM); + + hw = __clk_hw_register_mux(dev, np, name, num_parents, parent_names, parent_hws, + parent_data, flags, reg, shift, mask, + clk_mux_flags, table, lock); + + if (!IS_ERR(hw)) { + *ptr = hw; + devres_add(dev, ptr); + } else { + devres_free(ptr); + } + + return hw; +} +EXPORT_SYMBOL_GPL(__devm_clk_hw_register_mux); + struct clk *clk_register_mux_table(struct device *dev, const char *name, const char * const *parent_names, u8 num_parents, unsigned long flags, void __iomem *reg, u8 shift, u32 mask, diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c index 5052541a0986..39cfc6c6a8d2 100644 --- a/drivers/clk/clk.c +++ b/drivers/clk/clk.c @@ -4357,20 +4357,19 @@ int clk_notifier_register(struct clk *clk, struct notifier_block *nb) /* search the list of notifiers for this clk */ list_for_each_entry(cn, &clk_notifier_list, node) if (cn->clk == clk) - break; + goto found; /* if clk wasn't in the notifier list, allocate new clk_notifier */ - if (cn->clk != clk) { - cn = kzalloc(sizeof(*cn), GFP_KERNEL); - if (!cn) - goto out; + cn = kzalloc(sizeof(*cn), GFP_KERNEL); + if (!cn) + goto out; - cn->clk = clk; - srcu_init_notifier_head(&cn->notifier_head); + cn->clk = clk; + srcu_init_notifier_head(&cn->notifier_head); - list_add(&cn->node, &clk_notifier_list); - } + list_add(&cn->node, &clk_notifier_list); +found: ret = srcu_notifier_chain_register(&cn->notifier_head, nb); clk->core->notifier_count++; @@ -4395,32 +4394,28 @@ EXPORT_SYMBOL_GPL(clk_notifier_register); */ int clk_notifier_unregister(struct clk *clk, struct notifier_block *nb) { - struct clk_notifier *cn = NULL; - int ret = -EINVAL; + struct clk_notifier *cn; + int ret = -ENOENT; if (!clk || !nb) return -EINVAL; clk_prepare_lock(); - list_for_each_entry(cn, &clk_notifier_list, node) - if (cn->clk == clk) - break; - - if (cn->clk == clk) { - ret = srcu_notifier_chain_unregister(&cn->notifier_head, nb); + list_for_each_entry(cn, &clk_notifier_list, node) { + if (cn->clk == clk) { + ret = srcu_notifier_chain_unregister(&cn->notifier_head, nb); - clk->core->notifier_count--; + clk->core->notifier_count--; - /* XXX the notifier code should handle this better */ - if (!cn->notifier_head.head) { - srcu_cleanup_notifier_head(&cn->notifier_head); - list_del(&cn->node); - kfree(cn); + /* XXX the notifier code should handle this better */ + if (!cn->notifier_head.head) { + srcu_cleanup_notifier_head(&cn->notifier_head); + list_del(&cn->node); + kfree(cn); + } + break; } - - } else { - ret = -ENOENT; } clk_prepare_unlock(); diff --git a/drivers/clk/qcom/camcc-sc7180.c b/drivers/clk/qcom/camcc-sc7180.c index dbac5651ab85..9bcf2f8ed4de 100644 --- a/drivers/clk/qcom/camcc-sc7180.c +++ b/drivers/clk/qcom/camcc-sc7180.c @@ -304,7 +304,7 @@ static struct clk_rcg2 cam_cc_bps_clk_src = { .name = "cam_cc_bps_clk_src", .parent_data = cam_cc_parent_data_2, .num_parents = 5, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -325,7 +325,7 @@ static struct clk_rcg2 cam_cc_cci_0_clk_src = { .name = "cam_cc_cci_0_clk_src", .parent_data = cam_cc_parent_data_5, .num_parents = 3, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -339,7 +339,7 @@ static struct clk_rcg2 cam_cc_cci_1_clk_src = { .name = "cam_cc_cci_1_clk_src", .parent_data = cam_cc_parent_data_5, .num_parents = 3, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -360,7 +360,7 @@ static struct clk_rcg2 cam_cc_cphy_rx_clk_src = { .name = "cam_cc_cphy_rx_clk_src", .parent_data = cam_cc_parent_data_3, .num_parents = 6, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -379,7 +379,7 @@ static struct clk_rcg2 cam_cc_csi0phytimer_clk_src = { .name = "cam_cc_csi0phytimer_clk_src", .parent_data = cam_cc_parent_data_0, .num_parents = 4, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -393,7 +393,7 @@ static struct clk_rcg2 cam_cc_csi1phytimer_clk_src = { .name = "cam_cc_csi1phytimer_clk_src", .parent_data = cam_cc_parent_data_0, .num_parents = 4, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -407,7 +407,7 @@ static struct clk_rcg2 cam_cc_csi2phytimer_clk_src = { .name = "cam_cc_csi2phytimer_clk_src", .parent_data = cam_cc_parent_data_0, .num_parents = 4, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -421,7 +421,7 @@ static struct clk_rcg2 cam_cc_csi3phytimer_clk_src = { .name = "cam_cc_csi3phytimer_clk_src", .parent_data = cam_cc_parent_data_0, .num_parents = 4, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -443,7 +443,7 @@ static struct clk_rcg2 cam_cc_fast_ahb_clk_src = { .name = "cam_cc_fast_ahb_clk_src", .parent_data = cam_cc_parent_data_0, .num_parents = 4, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -466,7 +466,7 @@ static struct clk_rcg2 cam_cc_icp_clk_src = { .name = "cam_cc_icp_clk_src", .parent_data = cam_cc_parent_data_2, .num_parents = 5, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -488,7 +488,7 @@ static struct clk_rcg2 cam_cc_ife_0_clk_src = { .name = "cam_cc_ife_0_clk_src", .parent_data = cam_cc_parent_data_4, .num_parents = 4, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -510,7 +510,7 @@ static struct clk_rcg2 cam_cc_ife_0_csid_clk_src = { .name = "cam_cc_ife_0_csid_clk_src", .parent_data = cam_cc_parent_data_3, .num_parents = 6, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -524,7 +524,7 @@ static struct clk_rcg2 cam_cc_ife_1_clk_src = { .name = "cam_cc_ife_1_clk_src", .parent_data = cam_cc_parent_data_4, .num_parents = 4, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -538,7 +538,7 @@ static struct clk_rcg2 cam_cc_ife_1_csid_clk_src = { .name = "cam_cc_ife_1_csid_clk_src", .parent_data = cam_cc_parent_data_3, .num_parents = 6, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -553,7 +553,7 @@ static struct clk_rcg2 cam_cc_ife_lite_clk_src = { .parent_data = cam_cc_parent_data_4, .num_parents = 4, .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -567,7 +567,7 @@ static struct clk_rcg2 cam_cc_ife_lite_csid_clk_src = { .name = "cam_cc_ife_lite_csid_clk_src", .parent_data = cam_cc_parent_data_3, .num_parents = 6, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -590,7 +590,7 @@ static struct clk_rcg2 cam_cc_ipe_0_clk_src = { .name = "cam_cc_ipe_0_clk_src", .parent_data = cam_cc_parent_data_2, .num_parents = 5, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -613,7 +613,7 @@ static struct clk_rcg2 cam_cc_jpeg_clk_src = { .name = "cam_cc_jpeg_clk_src", .parent_data = cam_cc_parent_data_2, .num_parents = 5, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -635,7 +635,7 @@ static struct clk_rcg2 cam_cc_lrme_clk_src = { .name = "cam_cc_lrme_clk_src", .parent_data = cam_cc_parent_data_6, .num_parents = 5, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -656,7 +656,7 @@ static struct clk_rcg2 cam_cc_mclk0_clk_src = { .name = "cam_cc_mclk0_clk_src", .parent_data = cam_cc_parent_data_1, .num_parents = 3, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -670,7 +670,7 @@ static struct clk_rcg2 cam_cc_mclk1_clk_src = { .name = "cam_cc_mclk1_clk_src", .parent_data = cam_cc_parent_data_1, .num_parents = 3, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -684,7 +684,7 @@ static struct clk_rcg2 cam_cc_mclk2_clk_src = { .name = "cam_cc_mclk2_clk_src", .parent_data = cam_cc_parent_data_1, .num_parents = 3, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -698,7 +698,7 @@ static struct clk_rcg2 cam_cc_mclk3_clk_src = { .name = "cam_cc_mclk3_clk_src", .parent_data = cam_cc_parent_data_1, .num_parents = 3, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -712,7 +712,7 @@ static struct clk_rcg2 cam_cc_mclk4_clk_src = { .name = "cam_cc_mclk4_clk_src", .parent_data = cam_cc_parent_data_1, .num_parents = 3, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -732,7 +732,7 @@ static struct clk_rcg2 cam_cc_slow_ahb_clk_src = { .parent_data = cam_cc_parent_data_0, .num_parents = 4, .flags = CLK_SET_RATE_PARENT | CLK_OPS_PARENT_ENABLE, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; diff --git a/drivers/clk/qcom/clk-rcg2.c b/drivers/clk/qcom/clk-rcg2.c index 42f13a2d1cc1..05ff3b0d233e 100644 --- a/drivers/clk/qcom/clk-rcg2.c +++ b/drivers/clk/qcom/clk-rcg2.c @@ -730,7 +730,8 @@ static int clk_gfx3d_determine_rate(struct clk_hw *hw, struct clk_rate_request parent_req = { }; struct clk_rcg2_gfx3d *cgfx = to_clk_rcg2_gfx3d(hw); struct clk_hw *xo, *p0, *p1, *p2; - unsigned long request, p0_rate; + unsigned long p0_rate; + u8 mux_div = cgfx->div; int ret; p0 = cgfx->hws[0]; @@ -750,14 +751,15 @@ static int clk_gfx3d_determine_rate(struct clk_hw *hw, return 0; } - request = req->rate; - if (cgfx->div > 1) - parent_req.rate = request = request * cgfx->div; + if (mux_div == 0) + mux_div = 1; + + parent_req.rate = req->rate * mux_div; /* This has to be a fixed rate PLL */ p0_rate = clk_hw_get_rate(p0); - if (request == p0_rate) { + if (parent_req.rate == p0_rate) { req->rate = req->best_parent_rate = p0_rate; req->best_parent_hw = p0; return 0; @@ -765,7 +767,7 @@ static int clk_gfx3d_determine_rate(struct clk_hw *hw, if (req->best_parent_hw == p0) { /* Are we going back to a previously used rate? */ - if (clk_hw_get_rate(p2) == request) + if (clk_hw_get_rate(p2) == parent_req.rate) req->best_parent_hw = p2; else req->best_parent_hw = p1; @@ -780,8 +782,7 @@ static int clk_gfx3d_determine_rate(struct clk_hw *hw, return ret; req->rate = req->best_parent_rate = parent_req.rate; - if (cgfx->div > 1) - req->rate /= cgfx->div; + req->rate /= mux_div; return 0; } diff --git a/drivers/clk/qcom/clk-rpmh.c b/drivers/clk/qcom/clk-rpmh.c index 91dc390a583b..c623ce900406 100644 --- a/drivers/clk/qcom/clk-rpmh.c +++ b/drivers/clk/qcom/clk-rpmh.c @@ -510,9 +510,12 @@ static const struct clk_rpmh_desc clk_rpmh_sm8350 = { .num_clks = ARRAY_SIZE(sm8350_rpmh_clocks), }; +/* Resource name must match resource id present in cmd-db */ +DEFINE_CLK_RPMH_ARC(sc7280, bi_tcxo, bi_tcxo_ao, "xo.lvl", 0x3, 4); + static struct clk_hw *sc7280_rpmh_clocks[] = { - [RPMH_CXO_CLK] = &sdm845_bi_tcxo.hw, - [RPMH_CXO_CLK_A] = &sdm845_bi_tcxo_ao.hw, + [RPMH_CXO_CLK] = &sc7280_bi_tcxo.hw, + [RPMH_CXO_CLK_A] = &sc7280_bi_tcxo_ao.hw, [RPMH_LN_BB_CLK2] = &sdm845_ln_bb_clk2.hw, [RPMH_LN_BB_CLK2_A] = &sdm845_ln_bb_clk2_ao.hw, [RPMH_RF_CLK1] = &sdm845_rf_clk1.hw, diff --git a/drivers/clk/qcom/gcc-sc7180.c b/drivers/clk/qcom/gcc-sc7180.c index 88e896abb663..da8b627ca156 100644 --- a/drivers/clk/qcom/gcc-sc7180.c +++ b/drivers/clk/qcom/gcc-sc7180.c @@ -620,7 +620,7 @@ static struct clk_rcg2 gcc_sdcc1_apps_clk_src = { .name = "gcc_sdcc1_apps_clk_src", .parent_data = gcc_parent_data_1, .num_parents = 5, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_floor_ops, }, }; @@ -642,7 +642,7 @@ static struct clk_rcg2 gcc_sdcc1_ice_core_clk_src = { .name = "gcc_sdcc1_ice_core_clk_src", .parent_data = gcc_parent_data_0, .num_parents = 4, - .ops = &clk_rcg2_floor_ops, + .ops = &clk_rcg2_ops, }, }; diff --git a/drivers/clk/socfpga/clk-gate.c b/drivers/clk/socfpga/clk-gate.c index 43ecd507bf83..cf94a12459ea 100644 --- a/drivers/clk/socfpga/clk-gate.c +++ b/drivers/clk/socfpga/clk-gate.c @@ -99,7 +99,7 @@ static unsigned long socfpga_clk_recalc_rate(struct clk_hw *hwclk, val = readl(socfpgaclk->div_reg) >> socfpgaclk->shift; val &= GENMASK(socfpgaclk->width - 1, 0); /* Check for GPIO_DB_CLK by its offset */ - if ((int) socfpgaclk->div_reg & SOCFPGA_GPIO_DB_CLK_OFFSET) + if ((uintptr_t) socfpgaclk->div_reg & SOCFPGA_GPIO_DB_CLK_OFFSET) div = val + 1; else div = (1 << val); diff --git a/drivers/counter/stm32-timer-cnt.c b/drivers/counter/stm32-timer-cnt.c index ef2a974a2f10..75bc401fdd18 100644 --- a/drivers/counter/stm32-timer-cnt.c +++ b/drivers/counter/stm32-timer-cnt.c @@ -31,7 +31,7 @@ struct stm32_timer_cnt { struct counter_device counter; struct regmap *regmap; struct clk *clk; - u32 ceiling; + u32 max_arr; bool enabled; struct stm32_timer_regs bak; }; @@ -44,13 +44,14 @@ struct stm32_timer_cnt { * @STM32_COUNT_ENCODER_MODE_3: counts on both TI1FP1 and TI2FP2 edges */ enum stm32_count_function { - STM32_COUNT_SLAVE_MODE_DISABLED = -1, + STM32_COUNT_SLAVE_MODE_DISABLED, STM32_COUNT_ENCODER_MODE_1, STM32_COUNT_ENCODER_MODE_2, STM32_COUNT_ENCODER_MODE_3, }; static enum counter_count_function stm32_count_functions[] = { + [STM32_COUNT_SLAVE_MODE_DISABLED] = COUNTER_COUNT_FUNCTION_INCREASE, [STM32_COUNT_ENCODER_MODE_1] = COUNTER_COUNT_FUNCTION_QUADRATURE_X2_A, [STM32_COUNT_ENCODER_MODE_2] = COUNTER_COUNT_FUNCTION_QUADRATURE_X2_B, [STM32_COUNT_ENCODER_MODE_3] = COUNTER_COUNT_FUNCTION_QUADRATURE_X4, @@ -73,8 +74,10 @@ static int stm32_count_write(struct counter_device *counter, const unsigned long val) { struct stm32_timer_cnt *const priv = counter->priv; + u32 ceiling; - if (val > priv->ceiling) + regmap_read(priv->regmap, TIM_ARR, &ceiling); + if (val > ceiling) return -EINVAL; return regmap_write(priv->regmap, TIM_CNT, val); @@ -90,6 +93,9 @@ static int stm32_count_function_get(struct counter_device *counter, regmap_read(priv->regmap, TIM_SMCR, &smcr); switch (smcr & TIM_SMCR_SMS) { + case 0: + *function = STM32_COUNT_SLAVE_MODE_DISABLED; + return 0; case 1: *function = STM32_COUNT_ENCODER_MODE_1; return 0; @@ -99,9 +105,9 @@ static int stm32_count_function_get(struct counter_device *counter, case 3: *function = STM32_COUNT_ENCODER_MODE_3; return 0; + default: + return -EINVAL; } - - return -EINVAL; } static int stm32_count_function_set(struct counter_device *counter, @@ -112,6 +118,9 @@ static int stm32_count_function_set(struct counter_device *counter, u32 cr1, sms; switch (function) { + case STM32_COUNT_SLAVE_MODE_DISABLED: + sms = 0; + break; case STM32_COUNT_ENCODER_MODE_1: sms = 1; break; @@ -122,8 +131,7 @@ static int stm32_count_function_set(struct counter_device *counter, sms = 3; break; default: - sms = 0; - break; + return -EINVAL; } /* Store enable status */ @@ -131,10 +139,6 @@ static int stm32_count_function_set(struct counter_device *counter, regmap_update_bits(priv->regmap, TIM_CR1, TIM_CR1_CEN, 0); - /* TIMx_ARR register shouldn't be buffered (ARPE=0) */ - regmap_update_bits(priv->regmap, TIM_CR1, TIM_CR1_ARPE, 0); - regmap_write(priv->regmap, TIM_ARR, priv->ceiling); - regmap_update_bits(priv->regmap, TIM_SMCR, TIM_SMCR_SMS, sms); /* Make sure that registers are updated */ @@ -185,11 +189,13 @@ static ssize_t stm32_count_ceiling_write(struct counter_device *counter, if (ret) return ret; + if (ceiling > priv->max_arr) + return -ERANGE; + /* TIMx_ARR register shouldn't be buffered (ARPE=0) */ regmap_update_bits(priv->regmap, TIM_CR1, TIM_CR1_ARPE, 0); regmap_write(priv->regmap, TIM_ARR, ceiling); - priv->ceiling = ceiling; return len; } @@ -274,31 +280,36 @@ static int stm32_action_get(struct counter_device *counter, size_t function; int err; - /* Default action mode (e.g. STM32_COUNT_SLAVE_MODE_DISABLED) */ - *action = STM32_SYNAPSE_ACTION_NONE; - err = stm32_count_function_get(counter, count, &function); if (err) - return 0; + return err; switch (function) { + case STM32_COUNT_SLAVE_MODE_DISABLED: + /* counts on internal clock when CEN=1 */ + *action = STM32_SYNAPSE_ACTION_NONE; + return 0; case STM32_COUNT_ENCODER_MODE_1: /* counts up/down on TI1FP1 edge depending on TI2FP2 level */ if (synapse->signal->id == count->synapses[0].signal->id) *action = STM32_SYNAPSE_ACTION_BOTH_EDGES; - break; + else + *action = STM32_SYNAPSE_ACTION_NONE; + return 0; case STM32_COUNT_ENCODER_MODE_2: /* counts up/down on TI2FP2 edge depending on TI1FP1 level */ if (synapse->signal->id == count->synapses[1].signal->id) *action = STM32_SYNAPSE_ACTION_BOTH_EDGES; - break; + else + *action = STM32_SYNAPSE_ACTION_NONE; + return 0; case STM32_COUNT_ENCODER_MODE_3: /* counts up/down on both TI1FP1 and TI2FP2 edges */ *action = STM32_SYNAPSE_ACTION_BOTH_EDGES; - break; + return 0; + default: + return -EINVAL; } - - return 0; } static const struct counter_ops stm32_timer_cnt_ops = { @@ -359,7 +370,7 @@ static int stm32_timer_cnt_probe(struct platform_device *pdev) priv->regmap = ddata->regmap; priv->clk = ddata->clk; - priv->ceiling = ddata->max_arr; + priv->max_arr = ddata->max_arr; priv->counter.name = dev_name(dev); priv->counter.parent = dev; diff --git a/drivers/cpufreq/freq_table.c b/drivers/cpufreq/freq_table.c index d3f756f7b5a0..67e56cf638ef 100644 --- a/drivers/cpufreq/freq_table.c +++ b/drivers/cpufreq/freq_table.c @@ -267,7 +267,7 @@ struct freq_attr cpufreq_freq_attr_##_name##_freqs = \ __ATTR_RO(_name##_frequencies) /* - * show_scaling_available_frequencies - show available normal frequencies for + * scaling_available_frequencies_show - show available normal frequencies for * the specified CPU */ static ssize_t scaling_available_frequencies_show(struct cpufreq_policy *policy, @@ -279,7 +279,7 @@ cpufreq_attr_available_freq(scaling_available); EXPORT_SYMBOL_GPL(cpufreq_freq_attr_scaling_available_freqs); /* - * show_available_boost_freqs - show available boost frequencies for + * scaling_boost_frequencies_show - show available boost frequencies for * the specified CPU */ static ssize_t scaling_boost_frequencies_show(struct cpufreq_policy *policy, diff --git a/drivers/dma-buf/dma-fence.c b/drivers/dma-buf/dma-fence.c index d64fc03929be..ce0f5eff575d 100644 --- a/drivers/dma-buf/dma-fence.c +++ b/drivers/dma-buf/dma-fence.c @@ -123,7 +123,9 @@ static const struct dma_fence_ops dma_fence_stub_ops = { /** * dma_fence_get_stub - return a signaled fence * - * Return a stub fence which is already signaled. + * Return a stub fence which is already signaled. The fence's + * timestamp corresponds to the first time after boot this + * function is called. */ struct dma_fence *dma_fence_get_stub(void) { @@ -142,6 +144,29 @@ struct dma_fence *dma_fence_get_stub(void) EXPORT_SYMBOL(dma_fence_get_stub); /** + * dma_fence_allocate_private_stub - return a private, signaled fence + * + * Return a newly allocated and signaled stub fence. + */ +struct dma_fence *dma_fence_allocate_private_stub(void) +{ + struct dma_fence *fence; + + fence = kzalloc(sizeof(*fence), GFP_KERNEL); + if (fence == NULL) + return ERR_PTR(-ENOMEM); + + dma_fence_init(fence, + &dma_fence_stub_ops, + &dma_fence_stub_lock, + 0, 0); + dma_fence_signal(fence); + + return fence; +} +EXPORT_SYMBOL(dma_fence_allocate_private_stub); + +/** * dma_fence_context_alloc - allocate an array of fence contexts * @num: amount of contexts to allocate * diff --git a/drivers/extcon/extcon.c b/drivers/extcon/extcon.c index 0a6438cbb3f3..e7a9561a826d 100644 --- a/drivers/extcon/extcon.c +++ b/drivers/extcon/extcon.c @@ -1241,6 +1241,7 @@ int extcon_dev_register(struct extcon_dev *edev) sizeof(*edev->nh), GFP_KERNEL); if (!edev->nh) { ret = -ENOMEM; + device_unregister(&edev->dev); goto err_dev; } diff --git a/drivers/firewire/nosy.c b/drivers/firewire/nosy.c index 5fd6a60b6741..88ed971e32c0 100644 --- a/drivers/firewire/nosy.c +++ b/drivers/firewire/nosy.c @@ -346,6 +346,7 @@ nosy_ioctl(struct file *file, unsigned int cmd, unsigned long arg) struct client *client = file->private_data; spinlock_t *client_list_lock = &client->lynx->client_list_lock; struct nosy_stats stats; + int ret; switch (cmd) { case NOSY_IOC_GET_STATS: @@ -360,11 +361,15 @@ nosy_ioctl(struct file *file, unsigned int cmd, unsigned long arg) return 0; case NOSY_IOC_START: + ret = -EBUSY; spin_lock_irq(client_list_lock); - list_add_tail(&client->link, &client->lynx->client_list); + if (list_empty(&client->link)) { + list_add_tail(&client->link, &client->lynx->client_list); + ret = 0; + } spin_unlock_irq(client_list_lock); - return 0; + return ret; case NOSY_IOC_STOP: spin_lock_irq(client_list_lock); diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c index df3f9bcab581..4b7ee3fa9224 100644 --- a/drivers/firmware/efi/efi.c +++ b/drivers/firmware/efi/efi.c @@ -927,7 +927,7 @@ int __ref efi_mem_reserve_persistent(phys_addr_t addr, u64 size) } /* first try to find a slot in an existing linked list entry */ - for (prsv = efi_memreserve_root->next; prsv; prsv = rsv->next) { + for (prsv = efi_memreserve_root->next; prsv; ) { rsv = memremap(prsv, sizeof(*rsv), MEMREMAP_WB); index = atomic_fetch_add_unless(&rsv->count, 1, rsv->size); if (index < rsv->size) { @@ -937,6 +937,7 @@ int __ref efi_mem_reserve_persistent(phys_addr_t addr, u64 size) memunmap(rsv); return efi_mem_reserve_iomem(addr, size); } + prsv = rsv->next; memunmap(rsv); } diff --git a/drivers/firmware/efi/vars.c b/drivers/firmware/efi/vars.c index 41c1d00bf933..abdc8a6a3963 100644 --- a/drivers/firmware/efi/vars.c +++ b/drivers/firmware/efi/vars.c @@ -485,6 +485,10 @@ int efivar_init(int (*func)(efi_char16_t *, efi_guid_t, unsigned long, void *), } break; + case EFI_UNSUPPORTED: + err = -EOPNOTSUPP; + status = EFI_NOT_FOUND; + break; case EFI_NOT_FOUND: break; default: diff --git a/drivers/firmware/turris-mox-rwtm.c b/drivers/firmware/turris-mox-rwtm.c index 50bb2a6d6ccf..62f0d1a5dd32 100644 --- a/drivers/firmware/turris-mox-rwtm.c +++ b/drivers/firmware/turris-mox-rwtm.c @@ -2,7 +2,7 @@ /* * Turris Mox rWTM firmware driver * - * Copyright (C) 2019 Marek Behun <marek.behun@nic.cz> + * Copyright (C) 2019 Marek Behún <kabel@kernel.org> */ #include <linux/armada-37xx-rwtm-mailbox.h> @@ -547,4 +547,4 @@ module_platform_driver(turris_mox_rwtm_driver); MODULE_LICENSE("GPL v2"); MODULE_DESCRIPTION("Turris Mox rWTM firmware driver"); -MODULE_AUTHOR("Marek Behun <marek.behun@nic.cz>"); +MODULE_AUTHOR("Marek Behun <kabel@kernel.org>"); diff --git a/drivers/gpio/gpio-moxtet.c b/drivers/gpio/gpio-moxtet.c index 8299909318f4..61f9efd6c64f 100644 --- a/drivers/gpio/gpio-moxtet.c +++ b/drivers/gpio/gpio-moxtet.c @@ -2,7 +2,7 @@ /* * Turris Mox Moxtet GPIO expander * - * Copyright (C) 2018 Marek Behun <marek.behun@nic.cz> + * Copyright (C) 2018 Marek Behún <kabel@kernel.org> */ #include <linux/bitops.h> @@ -174,6 +174,6 @@ static struct moxtet_driver moxtet_gpio_driver = { }; module_moxtet_driver(moxtet_gpio_driver); -MODULE_AUTHOR("Marek Behun <marek.behun@nic.cz>"); +MODULE_AUTHOR("Marek Behun <kabel@kernel.org>"); MODULE_DESCRIPTION("Turris Mox Moxtet GPIO expander"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index 7ec0822c0505..6367646dce83 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -571,6 +571,7 @@ int gpiochip_add_data_with_key(struct gpio_chip *gc, void *data, struct lock_class_key *lock_key, struct lock_class_key *request_key) { + struct fwnode_handle *fwnode = gc->parent ? dev_fwnode(gc->parent) : NULL; unsigned long flags; int ret = 0; unsigned i; @@ -594,6 +595,12 @@ int gpiochip_add_data_with_key(struct gpio_chip *gc, void *data, of_gpio_dev_init(gc, gdev); + /* + * Assign fwnode depending on the result of the previous calls, + * if none of them succeed, assign it to the parent's one. + */ + gdev->dev.fwnode = dev_fwnode(&gdev->dev) ?: fwnode; + gdev->id = ida_alloc(&gpio_ida, GFP_KERNEL); if (gdev->id < 0) { ret = gdev->id; @@ -4256,7 +4263,8 @@ static int __init gpiolib_dev_init(void) return ret; } - if (driver_register(&gpio_stub_drv) < 0) { + ret = driver_register(&gpio_stub_drv); + if (ret < 0) { pr_err("gpiolib: could not register GPIO stub driver\n"); bus_unregister(&gpio_bus_type); return ret; diff --git a/drivers/gpu/drm/amd/amdgpu/Makefile b/drivers/gpu/drm/amd/amdgpu/Makefile index 741b68874e53..ee85e8aba636 100644 --- a/drivers/gpu/drm/amd/amdgpu/Makefile +++ b/drivers/gpu/drm/amd/amdgpu/Makefile @@ -71,7 +71,7 @@ amdgpu-y += \ vi.o mxgpu_vi.o nbio_v6_1.o soc15.o emu_soc.o mxgpu_ai.o nbio_v7_0.o vega10_reg_init.o \ vega20_reg_init.o nbio_v7_4.o nbio_v2_3.o nv.o navi10_reg_init.o navi14_reg_init.o \ arct_reg_init.o navi12_reg_init.o mxgpu_nv.o sienna_cichlid_reg_init.o vangogh_reg_init.o \ - nbio_v7_2.o dimgrey_cavefish_reg_init.o hdp_v4_0.o hdp_v5_0.o aldebaran_reg_init.o + nbio_v7_2.o dimgrey_cavefish_reg_init.o hdp_v4_0.o hdp_v5_0.o aldebaran_reg_init.o aldebaran.o # add DF block amdgpu-y += \ @@ -88,7 +88,7 @@ amdgpu-y += \ # add UMC block amdgpu-y += \ - umc_v6_1.o umc_v6_0.o umc_v8_7.o + umc_v6_0.o umc_v6_1.o umc_v6_7.o umc_v8_7.o # add IH block amdgpu-y += \ @@ -179,9 +179,14 @@ amdgpu-y += \ smuio_v11_0_6.o \ smuio_v13_0.o +# add reset block +amdgpu-y += \ + amdgpu_reset.o + # add amdkfd interfaces amdgpu-y += amdgpu_amdkfd.o + ifneq ($(CONFIG_HSA_AMD),) AMDKFD_PATH := ../amdkfd include $(FULL_AMD_PATH)/amdkfd/Makefile diff --git a/drivers/gpu/drm/amd/amdgpu/aldebaran.c b/drivers/gpu/drm/amd/amdgpu/aldebaran.c new file mode 100644 index 000000000000..65b1dca4b02e --- /dev/null +++ b/drivers/gpu/drm/amd/amdgpu/aldebaran.c @@ -0,0 +1,407 @@ +/* + * Copyright 2021 Advanced Micro Devices, Inc. + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR + * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, + * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR + * OTHER DEALINGS IN THE SOFTWARE. + * + */ + +#include "aldebaran.h" +#include "amdgpu_reset.h" +#include "amdgpu_amdkfd.h" +#include "amdgpu_dpm.h" +#include "amdgpu_job.h" +#include "amdgpu_ring.h" +#include "amdgpu_ras.h" +#include "amdgpu_psp.h" +#include "amdgpu_xgmi.h" + +static struct amdgpu_reset_handler * +aldebaran_get_reset_handler(struct amdgpu_reset_control *reset_ctl, + struct amdgpu_reset_context *reset_context) +{ + struct amdgpu_reset_handler *handler; + struct amdgpu_device *adev = (struct amdgpu_device *)reset_ctl->handle; + + if (reset_context->method != AMD_RESET_METHOD_NONE) { + dev_dbg(adev->dev, "Getting reset handler for method %d\n", + reset_context->method); + list_for_each_entry(handler, &reset_ctl->reset_handlers, + handler_list) { + if (handler->reset_method == reset_context->method) + return handler; + } + } + + if (adev->gmc.xgmi.connected_to_cpu) { + list_for_each_entry(handler, &reset_ctl->reset_handlers, + handler_list) { + if (handler->reset_method == AMD_RESET_METHOD_MODE2) { + reset_context->method = AMD_RESET_METHOD_MODE2; + return handler; + } + } + } + + dev_dbg(adev->dev, "Reset handler not found!\n"); + + return NULL; +} + +static int aldebaran_mode2_suspend_ip(struct amdgpu_device *adev) +{ + int r, i; + + amdgpu_device_set_pg_state(adev, AMD_PG_STATE_UNGATE); + amdgpu_device_set_cg_state(adev, AMD_CG_STATE_UNGATE); + + for (i = adev->num_ip_blocks - 1; i >= 0; i--) { + if (!(adev->ip_blocks[i].version->type == + AMD_IP_BLOCK_TYPE_GFX || + adev->ip_blocks[i].version->type == + AMD_IP_BLOCK_TYPE_SDMA)) + continue; + + r = adev->ip_blocks[i].version->funcs->suspend(adev); + + if (r) { + dev_err(adev->dev, + "suspend of IP block <%s> failed %d\n", + adev->ip_blocks[i].version->funcs->name, r); + return r; + } + + adev->ip_blocks[i].status.hw = false; + } + + return r; +} + +static int +aldebaran_mode2_prepare_hwcontext(struct amdgpu_reset_control *reset_ctl, + struct amdgpu_reset_context *reset_context) +{ + int r = 0; + struct amdgpu_device *adev = (struct amdgpu_device *)reset_ctl->handle; + + dev_dbg(adev->dev, "Aldebaran prepare hw context\n"); + /* Don't suspend on bare metal if we are not going to HW reset the ASIC */ + if (!amdgpu_sriov_vf(adev)) + r = aldebaran_mode2_suspend_ip(adev); + + return r; +} + +static void aldebaran_async_reset(struct work_struct *work) +{ + struct amdgpu_reset_handler *handler; + struct amdgpu_reset_control *reset_ctl = + container_of(work, struct amdgpu_reset_control, reset_work); + struct amdgpu_device *adev = (struct amdgpu_device *)reset_ctl->handle; + + list_for_each_entry(handler, &reset_ctl->reset_handlers, + handler_list) { + if (handler->reset_method == reset_ctl->active_reset) { + dev_dbg(adev->dev, "Resetting device\n"); + handler->do_reset(adev); + break; + } + } +} + +static int aldebaran_mode2_reset(struct amdgpu_device *adev) +{ + /* disable BM */ + pci_clear_master(adev->pdev); + adev->asic_reset_res = amdgpu_dpm_mode2_reset(adev); + return adev->asic_reset_res; +} + +static int +aldebaran_mode2_perform_reset(struct amdgpu_reset_control *reset_ctl, + struct amdgpu_reset_context *reset_context) +{ + struct amdgpu_device *tmp_adev = NULL; + struct amdgpu_device *adev = (struct amdgpu_device *)reset_ctl->handle; + int r = 0; + + dev_dbg(adev->dev, "aldebaran perform hw reset\n"); + if (reset_context->hive == NULL) { + /* Wrong context, return error */ + return -EINVAL; + } + + list_for_each_entry(tmp_adev, &reset_context->hive->device_list, + gmc.xgmi.head) { + mutex_lock(&tmp_adev->reset_cntl->reset_lock); + tmp_adev->reset_cntl->active_reset = AMD_RESET_METHOD_MODE2; + } + /* + * Mode2 reset doesn't need any sync between nodes in XGMI hive, instead launch + * them together so that they can be completed asynchronously on multiple nodes + */ + list_for_each_entry(tmp_adev, &reset_context->hive->device_list, + gmc.xgmi.head) { + /* For XGMI run all resets in parallel to speed up the process */ + if (tmp_adev->gmc.xgmi.num_physical_nodes > 1) { + if (!queue_work(system_unbound_wq, + &tmp_adev->reset_cntl->reset_work)) + r = -EALREADY; + } else + r = aldebaran_mode2_reset(tmp_adev); + if (r) { + dev_err(tmp_adev->dev, + "ASIC reset failed with error, %d for drm dev, %s", + r, adev_to_drm(tmp_adev)->unique); + break; + } + } + + /* For XGMI wait for all resets to complete before proceed */ + if (!r) { + list_for_each_entry(tmp_adev, + &reset_context->hive->device_list, + gmc.xgmi.head) { + if (tmp_adev->gmc.xgmi.num_physical_nodes > 1) { + flush_work(&tmp_adev->reset_cntl->reset_work); + r = tmp_adev->asic_reset_res; + if (r) + break; + } + } + } + + list_for_each_entry(tmp_adev, &reset_context->hive->device_list, + gmc.xgmi.head) { + mutex_unlock(&tmp_adev->reset_cntl->reset_lock); + tmp_adev->reset_cntl->active_reset = AMD_RESET_METHOD_NONE; + } + + return r; +} + +static int aldebaran_mode2_restore_ip(struct amdgpu_device *adev) +{ + struct amdgpu_firmware_info *ucode_list[AMDGPU_UCODE_ID_MAXIMUM]; + struct amdgpu_firmware_info *ucode; + struct amdgpu_ip_block *cmn_block; + int ucode_count = 0; + int i, r; + + dev_dbg(adev->dev, "Reloading ucodes after reset\n"); + for (i = 0; i < adev->firmware.max_ucodes; i++) { + ucode = &adev->firmware.ucode[i]; + if (!ucode->fw) + continue; + switch (ucode->ucode_id) { + case AMDGPU_UCODE_ID_SDMA0: + case AMDGPU_UCODE_ID_SDMA1: + case AMDGPU_UCODE_ID_SDMA2: + case AMDGPU_UCODE_ID_SDMA3: + case AMDGPU_UCODE_ID_SDMA4: + case AMDGPU_UCODE_ID_SDMA5: + case AMDGPU_UCODE_ID_SDMA6: + case AMDGPU_UCODE_ID_SDMA7: + case AMDGPU_UCODE_ID_CP_MEC1: + case AMDGPU_UCODE_ID_CP_MEC1_JT: + case AMDGPU_UCODE_ID_RLC_RESTORE_LIST_CNTL: + case AMDGPU_UCODE_ID_RLC_RESTORE_LIST_GPM_MEM: + case AMDGPU_UCODE_ID_RLC_RESTORE_LIST_SRM_MEM: + case AMDGPU_UCODE_ID_RLC_G: + ucode_list[ucode_count++] = ucode; + break; + default: + break; + }; + } + + /* Reinit NBIF block */ + cmn_block = + amdgpu_device_ip_get_ip_block(adev, AMD_IP_BLOCK_TYPE_COMMON); + if (unlikely(!cmn_block)) { + dev_err(adev->dev, "Failed to get BIF handle\n"); + return -EINVAL; + } + r = cmn_block->version->funcs->resume(adev); + if (r) + return r; + + /* Reinit GFXHUB */ + adev->gfxhub.funcs->init(adev); + r = adev->gfxhub.funcs->gart_enable(adev); + if (r) { + dev_err(adev->dev, "GFXHUB gart reenable failed after reset\n"); + return r; + } + + /* Reload GFX firmware */ + r = psp_load_fw_list(&adev->psp, ucode_list, ucode_count); + if (r) { + dev_err(adev->dev, "GFX ucode load failed after reset\n"); + return r; + } + + /* Resume RLC, FW needs RLC alive to complete reset process */ + adev->gfx.rlc.funcs->resume(adev); + + /* Wait for FW reset event complete */ + r = smu_wait_for_event(adev, SMU_EVENT_RESET_COMPLETE, 0); + if (r) { + dev_err(adev->dev, + "Failed to get response from firmware after reset\n"); + return r; + } + + for (i = 0; i < adev->num_ip_blocks; i++) { + if (!(adev->ip_blocks[i].version->type == + AMD_IP_BLOCK_TYPE_GFX || + adev->ip_blocks[i].version->type == + AMD_IP_BLOCK_TYPE_SDMA)) + continue; + r = adev->ip_blocks[i].version->funcs->resume(adev); + if (r) { + dev_err(adev->dev, + "resume of IP block <%s> failed %d\n", + adev->ip_blocks[i].version->funcs->name, r); + return r; + } + + adev->ip_blocks[i].status.hw = true; + } + + for (i = 0; i < adev->num_ip_blocks; i++) { + if (!(adev->ip_blocks[i].version->type == + AMD_IP_BLOCK_TYPE_GFX || + adev->ip_blocks[i].version->type == + AMD_IP_BLOCK_TYPE_SDMA || + adev->ip_blocks[i].version->type == + AMD_IP_BLOCK_TYPE_COMMON)) + continue; + + if (adev->ip_blocks[i].version->funcs->late_init) { + r = adev->ip_blocks[i].version->funcs->late_init( + (void *)adev); + if (r) { + dev_err(adev->dev, + "late_init of IP block <%s> failed %d after reset\n", + adev->ip_blocks[i].version->funcs->name, + r); + return r; + } + } + adev->ip_blocks[i].status.late_initialized = true; + } + + amdgpu_device_set_cg_state(adev, AMD_CG_STATE_GATE); + amdgpu_device_set_pg_state(adev, AMD_PG_STATE_GATE); + + return r; +} + +static int +aldebaran_mode2_restore_hwcontext(struct amdgpu_reset_control *reset_ctl, + struct amdgpu_reset_context *reset_context) +{ + int r; + struct amdgpu_device *tmp_adev = NULL; + + if (reset_context->hive == NULL) { + /* Wrong context, return error */ + return -EINVAL; + } + + list_for_each_entry(tmp_adev, &reset_context->hive->device_list, + gmc.xgmi.head) { + dev_info(tmp_adev->dev, + "GPU reset succeeded, trying to resume\n"); + r = aldebaran_mode2_restore_ip(tmp_adev); + if (r) + goto end; + + /* + * Add this ASIC as tracked as reset was already + * complete successfully. + */ + amdgpu_register_gpu_instance(tmp_adev); + + /* Resume RAS */ + amdgpu_ras_resume(tmp_adev); + + /* Update PSP FW topology after reset */ + if (reset_context->hive && + tmp_adev->gmc.xgmi.num_physical_nodes > 1) + r = amdgpu_xgmi_update_topology(reset_context->hive, + tmp_adev); + + if (!r) { + amdgpu_irq_gpu_reset_resume_helper(tmp_adev); + + r = amdgpu_ib_ring_tests(tmp_adev); + if (r) { + dev_err(tmp_adev->dev, + "ib ring test failed (%d).\n", r); + r = -EAGAIN; + tmp_adev->asic_reset_res = r; + goto end; + } + } + } + +end: + return r; +} + +static struct amdgpu_reset_handler aldebaran_mode2_handler = { + .reset_method = AMD_RESET_METHOD_MODE2, + .prepare_env = NULL, + .prepare_hwcontext = aldebaran_mode2_prepare_hwcontext, + .perform_reset = aldebaran_mode2_perform_reset, + .restore_hwcontext = aldebaran_mode2_restore_hwcontext, + .restore_env = NULL, + .do_reset = aldebaran_mode2_reset, +}; + +int aldebaran_reset_init(struct amdgpu_device *adev) +{ + struct amdgpu_reset_control *reset_ctl; + + reset_ctl = kzalloc(sizeof(*reset_ctl), GFP_KERNEL); + if (!reset_ctl) + return -ENOMEM; + + reset_ctl->handle = adev; + reset_ctl->async_reset = aldebaran_async_reset; + reset_ctl->active_reset = AMD_RESET_METHOD_NONE; + reset_ctl->get_reset_handler = aldebaran_get_reset_handler; + + INIT_LIST_HEAD(&reset_ctl->reset_handlers); + INIT_WORK(&reset_ctl->reset_work, reset_ctl->async_reset); + /* Only mode2 is handled through reset control now */ + amdgpu_reset_add_handler(reset_ctl, &aldebaran_mode2_handler); + + adev->reset_cntl = reset_ctl; + + return 0; +} + +int aldebaran_reset_fini(struct amdgpu_device *adev) +{ + kfree(adev->reset_cntl); + adev->reset_cntl = NULL; + return 0; +} diff --git a/drivers/gpu/drm/amd/amdgpu/aldebaran.h b/drivers/gpu/drm/amd/amdgpu/aldebaran.h new file mode 100644 index 000000000000..a07db5454d49 --- /dev/null +++ b/drivers/gpu/drm/amd/amdgpu/aldebaran.h @@ -0,0 +1,32 @@ +/* + * Copyright 2021 Advanced Micro Devices, Inc. + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR + * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, + * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR + * OTHER DEALINGS IN THE SOFTWARE. + * + */ + +#ifndef __ALDEBARAN_H__ +#define __ALDEBARAN_H__ + +#include "amdgpu.h" + +int aldebaran_reset_init(struct amdgpu_device *adev); +int aldebaran_reset_fini(struct amdgpu_device *adev); + +#endif diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index a037c223c251..dc3a69296321 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -107,7 +107,6 @@ #include "amdgpu_gfxhub.h" #include "amdgpu_df.h" #include "amdgpu_smuio.h" -#include "amdgpu_hdp.h" #define MAX_GPU_INSTANCE 16 @@ -271,6 +270,8 @@ struct amdgpu_bo_va_mapping; struct amdgpu_atif; struct kfd_vm_fault_info; struct amdgpu_hive_info; +struct amdgpu_reset_context; +struct amdgpu_reset_control; enum amdgpu_cp_irq { AMDGPU_CP_IRQ_GFX_ME0_PIPE0_EOP = 0, @@ -589,6 +590,7 @@ struct amdgpu_allowed_register_entry { }; enum amd_reset_method { + AMD_RESET_METHOD_NONE = -1, AMD_RESET_METHOD_LEGACY = 0, AMD_RESET_METHOD_MODE0, AMD_RESET_METHOD_MODE1, @@ -920,6 +922,7 @@ struct amdgpu_device { struct amdgpu_irq_src pageflip_irq; struct amdgpu_irq_src hpd_irq; struct amdgpu_irq_src dmub_trace_irq; + struct amdgpu_irq_src dmub_outbox_irq; /* rings */ u64 fence_context; @@ -1030,13 +1033,9 @@ struct amdgpu_device { /* s3/s4 mask */ bool in_suspend; - bool in_hibernate; - - /* - * The combination flag in_poweroff_reboot_com used to identify the poweroff - * and reboot opt in the s0i3 system-wide suspend. - */ - bool in_poweroff_reboot_com; + bool in_s3; + bool in_s4; + bool in_s0ix; atomic_t in_gpu_reset; enum pp_mp1_state mp1_state; @@ -1078,6 +1077,8 @@ struct amdgpu_device { bool in_pci_err_recovery; struct pci_saved_state *pci_state; + + struct amdgpu_reset_control *reset_cntl; }; static inline struct amdgpu_device *drm_to_adev(struct drm_device *ddev) @@ -1129,13 +1130,10 @@ bool amdgpu_device_asic_has_dc_support(enum amd_asic_type asic_type); bool amdgpu_device_has_dc_support(struct amdgpu_device *adev); int amdgpu_device_pre_asic_reset(struct amdgpu_device *adev, - struct amdgpu_job *job, - bool *need_full_reset_arg); + struct amdgpu_reset_context *reset_context); -int amdgpu_do_asic_reset(struct amdgpu_hive_info *hive, - struct list_head *device_list_handle, - bool *need_full_reset_arg, - bool skip_hw_reset); +int amdgpu_do_asic_reset(struct list_head *device_list_handle, + struct amdgpu_reset_context *reset_context); int emu_soc_asic_init(struct amdgpu_device *adev); @@ -1275,8 +1273,9 @@ void amdgpu_device_program_register_sequence(struct amdgpu_device *adev, const u32 *registers, const u32 array_size); -bool amdgpu_device_supports_atpx(struct drm_device *dev); int amdgpu_device_mode1_reset(struct amdgpu_device *adev); +bool amdgpu_device_supports_atpx(struct drm_device *dev); +bool amdgpu_device_supports_px(struct drm_device *dev); bool amdgpu_device_supports_boco(struct drm_device *dev); bool amdgpu_device_supports_baco(struct drm_device *dev); bool amdgpu_device_is_peer_accessible(struct amdgpu_device *adev, @@ -1390,6 +1389,13 @@ void amdgpu_pci_resume(struct pci_dev *pdev); bool amdgpu_device_cache_pci_state(struct pci_dev *pdev); bool amdgpu_device_load_pci_state(struct pci_dev *pdev); +bool amdgpu_device_skip_hw_access(struct amdgpu_device *adev); + +int amdgpu_device_set_cg_state(struct amdgpu_device *adev, + enum amd_clockgating_state state); +int amdgpu_device_set_pg_state(struct amdgpu_device *adev, + enum amd_powergating_state state); + #include "amdgpu_object.h" static inline bool amdgpu_is_tmz(struct amdgpu_device *adev) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c index 1c6be53313a8..5f6696a3c778 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c @@ -246,6 +246,7 @@ int amdgpu_amdkfd_alloc_gtt_mem(struct kgd_dev *kgd, size_t size, bp.flags = AMDGPU_GEM_CREATE_CPU_GTT_USWC; bp.type = ttm_bo_type_kernel; bp.resv = NULL; + bp.bo_ptr_size = sizeof(struct amdgpu_bo); if (cp_mqd_gfx9) bp.flags |= AMDGPU_GEM_CREATE_CP_MQD_GFX9; @@ -317,6 +318,7 @@ int amdgpu_amdkfd_alloc_gws(struct kgd_dev *kgd, size_t size, { struct amdgpu_device *adev = (struct amdgpu_device *)kgd; struct amdgpu_bo *bo = NULL; + struct amdgpu_bo_user *ubo; struct amdgpu_bo_param bp; int r; @@ -327,14 +329,16 @@ int amdgpu_amdkfd_alloc_gws(struct kgd_dev *kgd, size_t size, bp.flags = AMDGPU_GEM_CREATE_NO_CPU_ACCESS; bp.type = ttm_bo_type_device; bp.resv = NULL; + bp.bo_ptr_size = sizeof(struct amdgpu_bo); - r = amdgpu_bo_create(adev, &bp, &bo); + r = amdgpu_bo_create_user(adev, &bp, &ubo); if (r) { dev_err(adev->dev, "failed to allocate gws BO for amdkfd (%d)\n", r); return r; } + bo = &ubo->bo; *mem_obj = bo; return 0; } @@ -495,8 +499,6 @@ int amdgpu_amdkfd_get_dmabuf_info(struct kgd_dev *kgd, int dma_buf_fd, *dma_buf_kgd = (struct kgd_dev *)adev; if (bo_size) *bo_size = amdgpu_bo_size(bo); - if (metadata_size) - *metadata_size = bo->metadata_size; if (metadata_buffer) r = amdgpu_bo_get_metadata(bo, metadata_buffer, buffer_size, metadata_size, &metadata_flags); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h index 14f68c028126..5ffb07b02810 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h @@ -234,14 +234,10 @@ uint8_t amdgpu_amdkfd_get_xgmi_hops_count(struct kgd_dev *dst, struct kgd_dev *s }) /* GPUVM API */ -int amdgpu_amdkfd_gpuvm_create_process_vm(struct kgd_dev *kgd, u32 pasid, - void **vm, void **process_info, - struct dma_fence **ef); int amdgpu_amdkfd_gpuvm_acquire_process_vm(struct kgd_dev *kgd, struct file *filp, u32 pasid, void **vm, void **process_info, struct dma_fence **ef); -void amdgpu_amdkfd_gpuvm_destroy_process_vm(struct kgd_dev *kgd, void *vm); void amdgpu_amdkfd_gpuvm_release_process_vm(struct kgd_dev *kgd, void *vm); uint64_t amdgpu_amdkfd_gpuvm_get_process_page_dir(void *vm); int amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu( diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c index e93850f2f3b1..7d4118c8128a 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c @@ -445,22 +445,19 @@ static uint64_t get_pte_flags(struct amdgpu_device *adev, struct kgd_mem *mem) mapping_flags |= AMDGPU_VM_MTYPE_UC; } else if (mem->alloc_flags & KFD_IOC_ALLOC_MEM_FLAGS_VRAM) { if (bo_adev == adev) { - mapping_flags |= AMDGPU_VM_MTYPE_RW; + mapping_flags |= coherent ? + AMDGPU_VM_MTYPE_CC : AMDGPU_VM_MTYPE_RW; if (adev->gmc.xgmi.connected_to_cpu) snoop = true; } else { - mapping_flags |= AMDGPU_VM_MTYPE_NC; + mapping_flags |= AMDGPU_VM_MTYPE_UC; if (amdgpu_xgmi_same_hive(adev, bo_adev)) snoop = true; } } else { snoop = true; - if (adev->gmc.xgmi.connected_to_cpu) - /* system memory uses NC on A+A */ - mapping_flags |= AMDGPU_VM_MTYPE_NC; - else - mapping_flags |= coherent ? - AMDGPU_VM_MTYPE_UC : AMDGPU_VM_MTYPE_NC; + mapping_flags |= coherent ? + AMDGPU_VM_MTYPE_UC : AMDGPU_VM_MTYPE_NC; } break; default: @@ -1037,41 +1034,6 @@ create_evict_fence_fail: return ret; } -int amdgpu_amdkfd_gpuvm_create_process_vm(struct kgd_dev *kgd, u32 pasid, - void **vm, void **process_info, - struct dma_fence **ef) -{ - struct amdgpu_device *adev = get_amdgpu_device(kgd); - struct amdgpu_vm *new_vm; - int ret; - - new_vm = kzalloc(sizeof(*new_vm), GFP_KERNEL); - if (!new_vm) - return -ENOMEM; - - /* Initialize AMDGPU part of the VM */ - ret = amdgpu_vm_init(adev, new_vm, AMDGPU_VM_CONTEXT_COMPUTE, pasid); - if (ret) { - pr_err("Failed init vm ret %d\n", ret); - goto amdgpu_vm_init_fail; - } - - /* Initialize KFD part of the VM and process info */ - ret = init_kfd_vm(new_vm, process_info, ef); - if (ret) - goto init_kfd_vm_fail; - - *vm = (void *) new_vm; - - return 0; - -init_kfd_vm_fail: - amdgpu_vm_fini(adev, new_vm); -amdgpu_vm_init_fail: - kfree(new_vm); - return ret; -} - int amdgpu_amdkfd_gpuvm_acquire_process_vm(struct kgd_dev *kgd, struct file *filp, u32 pasid, void **vm, void **process_info, @@ -1138,21 +1100,6 @@ void amdgpu_amdkfd_gpuvm_destroy_cb(struct amdgpu_device *adev, } } -void amdgpu_amdkfd_gpuvm_destroy_process_vm(struct kgd_dev *kgd, void *vm) -{ - struct amdgpu_device *adev = get_amdgpu_device(kgd); - struct amdgpu_vm *avm = (struct amdgpu_vm *)vm; - - if (WARN_ON(!kgd || !vm)) - return; - - pr_debug("Destroying process vm %p\n", vm); - - /* Release the VM context */ - amdgpu_vm_fini(adev, avm); - kfree(vm); -} - void amdgpu_amdkfd_gpuvm_release_process_vm(struct kgd_dev *kgd, void *vm) { struct amdgpu_device *adev = get_amdgpu_device(kgd); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c index e05648a8a145..494b2e1717d5 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c @@ -1232,157 +1232,6 @@ int amdgpu_atombios_get_leakage_vddc_based_on_leakage_idx(struct amdgpu_device * return amdgpu_atombios_get_max_vddc(adev, VOLTAGE_TYPE_VDDC, leakage_idx, voltage); } -int amdgpu_atombios_get_leakage_id_from_vbios(struct amdgpu_device *adev, - u16 *leakage_id) -{ - union set_voltage args; - int index = GetIndexIntoMasterTable(COMMAND, SetVoltage); - u8 frev, crev; - - if (!amdgpu_atom_parse_cmd_header(adev->mode_info.atom_context, index, &frev, &crev)) - return -EINVAL; - - switch (crev) { - case 3: - case 4: - args.v3.ucVoltageType = 0; - args.v3.ucVoltageMode = ATOM_GET_LEAKAGE_ID; - args.v3.usVoltageLevel = 0; - - amdgpu_atom_execute_table(adev->mode_info.atom_context, index, (uint32_t *)&args); - - *leakage_id = le16_to_cpu(args.v3.usVoltageLevel); - break; - default: - DRM_ERROR("Unknown table version %d, %d\n", frev, crev); - return -EINVAL; - } - - return 0; -} - -int amdgpu_atombios_get_leakage_vddc_based_on_leakage_params(struct amdgpu_device *adev, - u16 *vddc, u16 *vddci, - u16 virtual_voltage_id, - u16 vbios_voltage_id) -{ - int index = GetIndexIntoMasterTable(DATA, ASIC_ProfilingInfo); - u8 frev, crev; - u16 data_offset, size; - int i, j; - ATOM_ASIC_PROFILING_INFO_V2_1 *profile; - u16 *leakage_bin, *vddc_id_buf, *vddc_buf, *vddci_id_buf, *vddci_buf; - - *vddc = 0; - *vddci = 0; - - if (!amdgpu_atom_parse_data_header(adev->mode_info.atom_context, index, &size, - &frev, &crev, &data_offset)) - return -EINVAL; - - profile = (ATOM_ASIC_PROFILING_INFO_V2_1 *) - (adev->mode_info.atom_context->bios + data_offset); - - switch (frev) { - case 1: - return -EINVAL; - case 2: - switch (crev) { - case 1: - if (size < sizeof(ATOM_ASIC_PROFILING_INFO_V2_1)) - return -EINVAL; - leakage_bin = (u16 *) - (adev->mode_info.atom_context->bios + data_offset + - le16_to_cpu(profile->usLeakageBinArrayOffset)); - vddc_id_buf = (u16 *) - (adev->mode_info.atom_context->bios + data_offset + - le16_to_cpu(profile->usElbVDDC_IdArrayOffset)); - vddc_buf = (u16 *) - (adev->mode_info.atom_context->bios + data_offset + - le16_to_cpu(profile->usElbVDDC_LevelArrayOffset)); - vddci_id_buf = (u16 *) - (adev->mode_info.atom_context->bios + data_offset + - le16_to_cpu(profile->usElbVDDCI_IdArrayOffset)); - vddci_buf = (u16 *) - (adev->mode_info.atom_context->bios + data_offset + - le16_to_cpu(profile->usElbVDDCI_LevelArrayOffset)); - - if (profile->ucElbVDDC_Num > 0) { - for (i = 0; i < profile->ucElbVDDC_Num; i++) { - if (vddc_id_buf[i] == virtual_voltage_id) { - for (j = 0; j < profile->ucLeakageBinNum; j++) { - if (vbios_voltage_id <= leakage_bin[j]) { - *vddc = vddc_buf[j * profile->ucElbVDDC_Num + i]; - break; - } - } - break; - } - } - } - if (profile->ucElbVDDCI_Num > 0) { - for (i = 0; i < profile->ucElbVDDCI_Num; i++) { - if (vddci_id_buf[i] == virtual_voltage_id) { - for (j = 0; j < profile->ucLeakageBinNum; j++) { - if (vbios_voltage_id <= leakage_bin[j]) { - *vddci = vddci_buf[j * profile->ucElbVDDCI_Num + i]; - break; - } - } - break; - } - } - } - break; - default: - DRM_ERROR("Unknown table version %d, %d\n", frev, crev); - return -EINVAL; - } - break; - default: - DRM_ERROR("Unknown table version %d, %d\n", frev, crev); - return -EINVAL; - } - - return 0; -} - -union get_voltage_info { - struct _GET_VOLTAGE_INFO_INPUT_PARAMETER_V1_2 in; - struct _GET_EVV_VOLTAGE_INFO_OUTPUT_PARAMETER_V1_2 evv_out; -}; - -int amdgpu_atombios_get_voltage_evv(struct amdgpu_device *adev, - u16 virtual_voltage_id, - u16 *voltage) -{ - int index = GetIndexIntoMasterTable(COMMAND, GetVoltageInfo); - u32 entry_id; - u32 count = adev->pm.dpm.dyn_state.vddc_dependency_on_sclk.count; - union get_voltage_info args; - - for (entry_id = 0; entry_id < count; entry_id++) { - if (adev->pm.dpm.dyn_state.vddc_dependency_on_sclk.entries[entry_id].v == - virtual_voltage_id) - break; - } - - if (entry_id >= count) - return -EINVAL; - - args.in.ucVoltageType = VOLTAGE_TYPE_VDDC; - args.in.ucVoltageMode = ATOM_GET_VOLTAGE_EVV_VOLTAGE; - args.in.usVoltageLevel = cpu_to_le16(virtual_voltage_id); - args.in.ulSCLKFreq = - cpu_to_le32(adev->pm.dpm.dyn_state.vddc_dependency_on_sclk.entries[entry_id].clk); - - amdgpu_atom_execute_table(adev->mode_info.atom_context, index, (uint32_t *)&args); - - *voltage = le16_to_cpu(args.evv_out.usVoltageLevel); - - return 0; -} - union voltage_object_info { struct _ATOM_VOLTAGE_OBJECT_INFO v1; struct _ATOM_VOLTAGE_OBJECT_INFO_V2 v2; @@ -1913,7 +1762,7 @@ static ssize_t amdgpu_atombios_get_vbios_version(struct device *dev, struct amdgpu_device *adev = drm_to_adev(ddev); struct atom_context *ctx = adev->mode_info.atom_context; - return snprintf(buf, PAGE_SIZE, "%s\n", ctx->vbios_version); + return sysfs_emit(buf, "%s\n", ctx->vbios_version); } static DEVICE_ATTR(vbios_version, 0444, amdgpu_atombios_get_vbios_version, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.h index 1321ec09c734..8cc0222dba19 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.h @@ -168,18 +168,6 @@ int amdgpu_atombios_get_memory_pll_dividers(struct amdgpu_device *adev, void amdgpu_atombios_set_engine_dram_timings(struct amdgpu_device *adev, u32 eng_clock, u32 mem_clock); -int amdgpu_atombios_get_leakage_id_from_vbios(struct amdgpu_device *adev, - u16 *leakage_id); - -int amdgpu_atombios_get_leakage_vddc_based_on_leakage_params(struct amdgpu_device *adev, - u16 *vddc, u16 *vddci, - u16 virtual_voltage_id, - u16 vbios_voltage_id); - -int amdgpu_atombios_get_voltage_evv(struct amdgpu_device *adev, - u16 virtual_voltage_id, - u16 *voltage); - bool amdgpu_atombios_is_voltage_gpio(struct amdgpu_device *adev, u8 voltage_type, u8 voltage_mode); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_benchmark.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_benchmark.c index d9b35df33806..313517f7cf10 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_benchmark.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_benchmark.c @@ -85,6 +85,8 @@ static void amdgpu_benchmark_move(struct amdgpu_device *adev, unsigned size, bp.flags = 0; bp.type = ttm_bo_type_kernel; bp.resv = NULL; + bp.bo_ptr_size = sizeof(struct amdgpu_bo); + n = AMDGPU_BENCHMARK_ITERATIONS; r = amdgpu_bo_create(adev, &bp, &sobj); if (r) { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 0f82c5d21237..b4ad1c055c70 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -65,6 +65,7 @@ #include "amdgpu_ras.h" #include "amdgpu_pmu.h" #include "amdgpu_fru_eeprom.h" +#include "amdgpu_reset.h" #include <linux/suspend.h> #include <drm/task_barrier.h> @@ -137,7 +138,7 @@ static ssize_t amdgpu_device_get_pcie_replay_count(struct device *dev, struct amdgpu_device *adev = drm_to_adev(ddev); uint64_t cnt = amdgpu_asic_get_pcie_replay_count(adev); - return snprintf(buf, PAGE_SIZE, "%llu\n", cnt); + return sysfs_emit(buf, "%llu\n", cnt); } static DEVICE_ATTR(pcie_replay_count, S_IRUGO, @@ -161,7 +162,7 @@ static ssize_t amdgpu_device_get_product_name(struct device *dev, struct drm_device *ddev = dev_get_drvdata(dev); struct amdgpu_device *adev = drm_to_adev(ddev); - return snprintf(buf, PAGE_SIZE, "%s\n", adev->product_name); + return sysfs_emit(buf, "%s\n", adev->product_name); } static DEVICE_ATTR(product_name, S_IRUGO, @@ -183,7 +184,7 @@ static ssize_t amdgpu_device_get_product_number(struct device *dev, struct drm_device *ddev = dev_get_drvdata(dev); struct amdgpu_device *adev = drm_to_adev(ddev); - return snprintf(buf, PAGE_SIZE, "%s\n", adev->product_number); + return sysfs_emit(buf, "%s\n", adev->product_number); } static DEVICE_ATTR(product_number, S_IRUGO, @@ -205,25 +206,25 @@ static ssize_t amdgpu_device_get_serial_number(struct device *dev, struct drm_device *ddev = dev_get_drvdata(dev); struct amdgpu_device *adev = drm_to_adev(ddev); - return snprintf(buf, PAGE_SIZE, "%s\n", adev->serial); + return sysfs_emit(buf, "%s\n", adev->serial); } static DEVICE_ATTR(serial_number, S_IRUGO, amdgpu_device_get_serial_number, NULL); /** - * amdgpu_device_supports_atpx - Is the device a dGPU with HG/PX power control + * amdgpu_device_supports_px - Is the device a dGPU with ATPX power control * * @dev: drm_device pointer * - * Returns true if the device is a dGPU with HG/PX power control, + * Returns true if the device is a dGPU with ATPX power control, * otherwise return false. */ -bool amdgpu_device_supports_atpx(struct drm_device *dev) +bool amdgpu_device_supports_px(struct drm_device *dev) { struct amdgpu_device *adev = drm_to_adev(dev); - if (adev->flags & AMD_IS_PX) + if ((adev->flags & AMD_IS_PX) && !amdgpu_is_atpx_hybrid()) return true; return false; } @@ -233,14 +234,15 @@ bool amdgpu_device_supports_atpx(struct drm_device *dev) * * @dev: drm_device pointer * - * Returns true if the device is a dGPU with HG/PX power control, + * Returns true if the device is a dGPU with ACPI power control, * otherwise return false. */ bool amdgpu_device_supports_boco(struct drm_device *dev) { struct amdgpu_device *adev = drm_to_adev(dev); - if (adev->has_pr3) + if (adev->has_pr3 || + ((adev->flags & AMD_IS_PX) && amdgpu_is_atpx_hybrid())) return true; return false; } @@ -326,6 +328,35 @@ void amdgpu_device_vram_access(struct amdgpu_device *adev, loff_t pos, /* * register access helper functions. */ + +/* Check if hw access should be skipped because of hotplug or device error */ +bool amdgpu_device_skip_hw_access(struct amdgpu_device *adev) +{ + if (adev->in_pci_err_recovery) + return true; + +#ifdef CONFIG_LOCKDEP + /* + * This is a bit complicated to understand, so worth a comment. What we assert + * here is that the GPU reset is not running on another thread in parallel. + * + * For this we trylock the read side of the reset semaphore, if that succeeds + * we know that the reset is not running in paralell. + * + * If the trylock fails we assert that we are either already holding the read + * side of the lock or are the reset thread itself and hold the write side of + * the lock. + */ + if (in_task()) { + if (down_read_trylock(&adev->reset_sem)) + up_read(&adev->reset_sem); + else + lockdep_assert_held(&adev->reset_sem); + } +#endif + return false; +} + /** * amdgpu_device_rreg - read a memory mapped IO or indirect register * @@ -340,7 +371,7 @@ uint32_t amdgpu_device_rreg(struct amdgpu_device *adev, { uint32_t ret; - if (adev->in_pci_err_recovery) + if (amdgpu_device_skip_hw_access(adev)) return 0; if ((reg * 4) < adev->rmmio_size) { @@ -377,7 +408,7 @@ uint32_t amdgpu_device_rreg(struct amdgpu_device *adev, */ uint8_t amdgpu_mm_rreg8(struct amdgpu_device *adev, uint32_t offset) { - if (adev->in_pci_err_recovery) + if (amdgpu_device_skip_hw_access(adev)) return 0; if (offset < adev->rmmio_size) @@ -402,7 +433,7 @@ uint8_t amdgpu_mm_rreg8(struct amdgpu_device *adev, uint32_t offset) */ void amdgpu_mm_wreg8(struct amdgpu_device *adev, uint32_t offset, uint8_t value) { - if (adev->in_pci_err_recovery) + if (amdgpu_device_skip_hw_access(adev)) return; if (offset < adev->rmmio_size) @@ -425,7 +456,7 @@ void amdgpu_device_wreg(struct amdgpu_device *adev, uint32_t reg, uint32_t v, uint32_t acc_flags) { - if (adev->in_pci_err_recovery) + if (amdgpu_device_skip_hw_access(adev)) return; if ((reg * 4) < adev->rmmio_size) { @@ -452,14 +483,14 @@ void amdgpu_device_wreg(struct amdgpu_device *adev, void amdgpu_mm_wreg_mmio_rlc(struct amdgpu_device *adev, uint32_t reg, uint32_t v) { - if (adev->in_pci_err_recovery) + if (amdgpu_device_skip_hw_access(adev)) return; if (amdgpu_sriov_fullaccess(adev) && adev->gfx.rlc.funcs && adev->gfx.rlc.funcs->is_rlcg_access_range) { if (adev->gfx.rlc.funcs->is_rlcg_access_range(adev, reg)) - return adev->gfx.rlc.funcs->rlcg_wreg(adev, reg, v); + return adev->gfx.rlc.funcs->rlcg_wreg(adev, reg, v, 0); } else { writel(v, ((void __iomem *)adev->rmmio) + (reg * 4)); } @@ -476,7 +507,7 @@ void amdgpu_mm_wreg_mmio_rlc(struct amdgpu_device *adev, */ u32 amdgpu_mm_rdoorbell(struct amdgpu_device *adev, u32 index) { - if (adev->in_pci_err_recovery) + if (amdgpu_device_skip_hw_access(adev)) return 0; if (index < adev->doorbell.num_doorbells) { @@ -499,7 +530,7 @@ u32 amdgpu_mm_rdoorbell(struct amdgpu_device *adev, u32 index) */ void amdgpu_mm_wdoorbell(struct amdgpu_device *adev, u32 index, u32 v) { - if (adev->in_pci_err_recovery) + if (amdgpu_device_skip_hw_access(adev)) return; if (index < adev->doorbell.num_doorbells) { @@ -520,7 +551,7 @@ void amdgpu_mm_wdoorbell(struct amdgpu_device *adev, u32 index, u32 v) */ u64 amdgpu_mm_rdoorbell64(struct amdgpu_device *adev, u32 index) { - if (adev->in_pci_err_recovery) + if (amdgpu_device_skip_hw_access(adev)) return 0; if (index < adev->doorbell.num_doorbells) { @@ -543,7 +574,7 @@ u64 amdgpu_mm_rdoorbell64(struct amdgpu_device *adev, u32 index) */ void amdgpu_mm_wdoorbell64(struct amdgpu_device *adev, u32 index, u64 v) { - if (adev->in_pci_err_recovery) + if (amdgpu_device_skip_hw_access(adev)) return; if (index < adev->doorbell.num_doorbells) { @@ -1391,7 +1422,7 @@ static void amdgpu_switcheroo_set_state(struct pci_dev *pdev, struct drm_device *dev = pci_get_drvdata(pdev); int r; - if (amdgpu_device_supports_atpx(dev) && state == VGA_SWITCHEROO_OFF) + if (amdgpu_device_supports_px(dev) && state == VGA_SWITCHEROO_OFF) return; if (state == VGA_SWITCHEROO_ON) { @@ -2049,6 +2080,11 @@ static int amdgpu_device_ip_early_init(struct amdgpu_device *adev) amdgpu_vf_error_put(adev, AMDGIM_ERROR_VF_ATOMBIOS_INIT_FAIL, 0, 0); return r; } + + /*get pf2vf msg info at it's earliest time*/ + if (amdgpu_sriov_vf(adev)) + amdgpu_virt_init_data_exchange(adev); + } } @@ -2331,8 +2367,8 @@ static bool amdgpu_device_check_vram_lost(struct amdgpu_device *adev) * Returns 0 on success, negative error code on failure. */ -static int amdgpu_device_set_cg_state(struct amdgpu_device *adev, - enum amd_clockgating_state state) +int amdgpu_device_set_cg_state(struct amdgpu_device *adev, + enum amd_clockgating_state state) { int i, j, r; @@ -2343,6 +2379,10 @@ static int amdgpu_device_set_cg_state(struct amdgpu_device *adev, i = state == AMD_CG_STATE_GATE ? j : adev->num_ip_blocks - j - 1; if (!adev->ip_blocks[i].status.late_initialized) continue; + /* skip CG for GFX on S0ix */ + if (adev->in_s0ix && + adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_GFX) + continue; /* skip CG for VCE/UVD, it's handled specially */ if (adev->ip_blocks[i].version->type != AMD_IP_BLOCK_TYPE_UVD && adev->ip_blocks[i].version->type != AMD_IP_BLOCK_TYPE_VCE && @@ -2363,7 +2403,8 @@ static int amdgpu_device_set_cg_state(struct amdgpu_device *adev, return 0; } -static int amdgpu_device_set_pg_state(struct amdgpu_device *adev, enum amd_powergating_state state) +int amdgpu_device_set_pg_state(struct amdgpu_device *adev, + enum amd_powergating_state state) { int i, j, r; @@ -2374,6 +2415,10 @@ static int amdgpu_device_set_pg_state(struct amdgpu_device *adev, enum amd_power i = state == AMD_PG_STATE_GATE ? j : adev->num_ip_blocks - j - 1; if (!adev->ip_blocks[i].status.late_initialized) continue; + /* skip PG for GFX on S0ix */ + if (adev->in_s0ix && + adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_GFX) + continue; /* skip CG for VCE/UVD, it's handled specially */ if (adev->ip_blocks[i].version->type != AMD_IP_BLOCK_TYPE_UVD && adev->ip_blocks[i].version->type != AMD_IP_BLOCK_TYPE_VCE && @@ -2655,11 +2700,8 @@ static int amdgpu_device_ip_suspend_phase1(struct amdgpu_device *adev) { int i, r; - if (adev->in_poweroff_reboot_com || - !amdgpu_acpi_is_s0ix_supported(adev) || amdgpu_in_reset(adev)) { - amdgpu_device_set_pg_state(adev, AMD_PG_STATE_UNGATE); - amdgpu_device_set_cg_state(adev, AMD_CG_STATE_UNGATE); - } + amdgpu_device_set_pg_state(adev, AMD_PG_STATE_UNGATE); + amdgpu_device_set_cg_state(adev, AMD_CG_STATE_UNGATE); for (i = adev->num_ip_blocks - 1; i >= 0; i--) { if (!adev->ip_blocks[i].status.valid) @@ -2699,6 +2741,9 @@ static int amdgpu_device_ip_suspend_phase2(struct amdgpu_device *adev) { int i, r; + if (adev->in_s0ix) + amdgpu_gfx_state_change_set(adev, sGpuChangeState_D3Entry); + for (i = adev->num_ip_blocks - 1; i >= 0; i--) { if (!adev->ip_blocks[i].status.valid) continue; @@ -2721,6 +2766,17 @@ static int amdgpu_device_ip_suspend_phase2(struct amdgpu_device *adev) adev->ip_blocks[i].status.hw = false; continue; } + + /* skip suspend of gfx and psp for S0ix + * gfx is in gfxoff state, so on resume it will exit gfxoff just + * like at runtime. PSP is also part of the always on hardware + * so no need to suspend it. + */ + if (adev->in_s0ix && + (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_PSP || + adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_GFX)) + continue; + /* XXX handle errors */ r = adev->ip_blocks[i].version->funcs->suspend(adev); /* XXX handle errors */ @@ -3086,8 +3142,9 @@ static void amdgpu_device_xgmi_reset_func(struct work_struct *__work) if (adev->asic_reset_res) goto fail; - if (adev->mmhub.funcs && adev->mmhub.funcs->reset_ras_error_count) - adev->mmhub.funcs->reset_ras_error_count(adev); + if (adev->mmhub.ras_funcs && + adev->mmhub.ras_funcs->reset_ras_error_count) + adev->mmhub.ras_funcs->reset_ras_error_count(adev); } else { task_barrier_full(&hive->tb); @@ -3197,7 +3254,7 @@ int amdgpu_device_init(struct amdgpu_device *adev, struct drm_device *ddev = adev_to_drm(adev); struct pci_dev *pdev = adev->pdev; int r, i; - bool atpx = false; + bool px = false; u32 max_MBps; adev->shutdown = false; @@ -3359,16 +3416,12 @@ int amdgpu_device_init(struct amdgpu_device *adev, if ((adev->pdev->class >> 8) == PCI_CLASS_DISPLAY_VGA) vga_client_register(adev->pdev, adev, NULL, amdgpu_device_vga_set_decode); - if (amdgpu_device_supports_atpx(ddev)) - atpx = true; - if (amdgpu_has_atpx() && - (amdgpu_is_atpx_hybrid() || - amdgpu_has_atpx_dgpu_power_cntl()) && - !pci_is_thunderbolt_attached(adev->pdev)) + if (amdgpu_device_supports_px(ddev)) { + px = true; vga_switcheroo_register_client(adev->pdev, - &amdgpu_switcheroo_ops, atpx); - if (atpx) + &amdgpu_switcheroo_ops, px); vga_switcheroo_init_domain_pm_ops(adev->dev, &adev->vga_pm_domain); + } if (amdgpu_emu_mode == 1) { /* post the asic on emulation mode */ @@ -3376,6 +3429,8 @@ int amdgpu_device_init(struct amdgpu_device *adev, goto fence_driver_init; } + amdgpu_reset_init(adev); + /* detect if we are with an SRIOV vbios */ amdgpu_device_detect_sriov_bios(adev); @@ -3575,7 +3630,7 @@ release_ras_con: failed: amdgpu_vf_error_trans_all(adev); - if (atpx) + if (px) vga_switcheroo_fini_domain_pm_ops(adev->dev); failed_unmap: @@ -3626,6 +3681,9 @@ void amdgpu_device_fini(struct amdgpu_device *adev) release_firmware(adev->firmware.gpu_info_fw); adev->firmware.gpu_info_fw = NULL; adev->accel_working = false; + + amdgpu_reset_fini(adev); + /* free i2c buses */ if (!amdgpu_device_has_dc_support(adev)) amdgpu_i2c_fini(adev); @@ -3635,13 +3693,10 @@ void amdgpu_device_fini(struct amdgpu_device *adev) kfree(adev->bios); adev->bios = NULL; - if (amdgpu_has_atpx() && - (amdgpu_is_atpx_hybrid() || - amdgpu_has_atpx_dgpu_power_cntl()) && - !pci_is_thunderbolt_attached(adev->pdev)) + if (amdgpu_device_supports_px(adev_to_drm(adev))) { vga_switcheroo_unregister_client(adev->pdev); - if (amdgpu_device_supports_atpx(adev_to_drm(adev))) vga_switcheroo_fini_domain_pm_ops(adev->dev); + } if ((adev->pdev->class >> 8) == PCI_CLASS_DISPLAY_VGA) vga_client_register(adev->pdev, NULL, NULL, NULL); iounmap(adev->rmmio); @@ -3674,14 +3729,9 @@ void amdgpu_device_fini(struct amdgpu_device *adev) */ int amdgpu_device_suspend(struct drm_device *dev, bool fbcon) { - struct amdgpu_device *adev; - struct drm_crtc *crtc; - struct drm_connector *connector; - struct drm_connector_list_iter iter; + struct amdgpu_device *adev = drm_to_adev(dev); int r; - adev = drm_to_adev(dev); - if (dev->switch_power_state == DRM_SWITCH_POWER_OFF) return 0; @@ -3693,61 +3743,19 @@ int amdgpu_device_suspend(struct drm_device *dev, bool fbcon) cancel_delayed_work_sync(&adev->delayed_init_work); - if (!amdgpu_device_has_dc_support(adev)) { - /* turn off display hw */ - drm_modeset_lock_all(dev); - drm_connector_list_iter_begin(dev, &iter); - drm_for_each_connector_iter(connector, &iter) - drm_helper_connector_dpms(connector, - DRM_MODE_DPMS_OFF); - drm_connector_list_iter_end(&iter); - drm_modeset_unlock_all(dev); - /* unpin the front buffers and cursors */ - list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) { - struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc); - struct drm_framebuffer *fb = crtc->primary->fb; - struct amdgpu_bo *robj; - - if (amdgpu_crtc->cursor_bo && !adev->enable_virtual_display) { - struct amdgpu_bo *aobj = gem_to_amdgpu_bo(amdgpu_crtc->cursor_bo); - r = amdgpu_bo_reserve(aobj, true); - if (r == 0) { - amdgpu_bo_unpin(aobj); - amdgpu_bo_unreserve(aobj); - } - } - - if (fb == NULL || fb->obj[0] == NULL) { - continue; - } - robj = gem_to_amdgpu_bo(fb->obj[0]); - /* don't unpin kernel fb objects */ - if (!amdgpu_fbdev_robj_is_fb(adev, robj)) { - r = amdgpu_bo_reserve(robj, true); - if (r == 0) { - amdgpu_bo_unpin(robj); - amdgpu_bo_unreserve(robj); - } - } - } - } - amdgpu_ras_suspend(adev); r = amdgpu_device_ip_suspend_phase1(adev); - amdgpu_amdkfd_suspend(adev, adev->in_runpm); + if (!adev->in_s0ix) + amdgpu_amdkfd_suspend(adev, adev->in_runpm); /* evict vram memory */ amdgpu_bo_evict_vram(adev); amdgpu_fence_driver_suspend(adev); - if (adev->in_poweroff_reboot_com || - !amdgpu_acpi_is_s0ix_supported(adev) || amdgpu_in_reset(adev)) - r = amdgpu_device_ip_suspend_phase2(adev); - else - amdgpu_gfx_state_change_set(adev, sGpuChangeState_D3Entry); + r = amdgpu_device_ip_suspend_phase2(adev); /* evict remaining vram memory * This second call to evict vram is to evict the gart page table * using the CPU. @@ -3769,16 +3777,13 @@ int amdgpu_device_suspend(struct drm_device *dev, bool fbcon) */ int amdgpu_device_resume(struct drm_device *dev, bool fbcon) { - struct drm_connector *connector; - struct drm_connector_list_iter iter; struct amdgpu_device *adev = drm_to_adev(dev); - struct drm_crtc *crtc; int r = 0; if (dev->switch_power_state == DRM_SWITCH_POWER_OFF) return 0; - if (amdgpu_acpi_is_s0ix_supported(adev)) + if (adev->in_s0ix) amdgpu_gfx_state_change_set(adev, sGpuChangeState_D0Entry); /* post card */ @@ -3803,50 +3808,17 @@ int amdgpu_device_resume(struct drm_device *dev, bool fbcon) queue_delayed_work(system_wq, &adev->delayed_init_work, msecs_to_jiffies(AMDGPU_RESUME_MS)); - if (!amdgpu_device_has_dc_support(adev)) { - /* pin cursors */ - list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) { - struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc); - - if (amdgpu_crtc->cursor_bo && !adev->enable_virtual_display) { - struct amdgpu_bo *aobj = gem_to_amdgpu_bo(amdgpu_crtc->cursor_bo); - r = amdgpu_bo_reserve(aobj, true); - if (r == 0) { - r = amdgpu_bo_pin(aobj, AMDGPU_GEM_DOMAIN_VRAM); - if (r != 0) - dev_err(adev->dev, "Failed to pin cursor BO (%d)\n", r); - amdgpu_crtc->cursor_addr = amdgpu_bo_gpu_offset(aobj); - amdgpu_bo_unreserve(aobj); - } - } - } + if (!adev->in_s0ix) { + r = amdgpu_amdkfd_resume(adev, adev->in_runpm); + if (r) + return r; } - r = amdgpu_amdkfd_resume(adev, adev->in_runpm); - if (r) - return r; /* Make sure IB tests flushed */ flush_delayed_work(&adev->delayed_init_work); - /* blat the mode back in */ - if (fbcon) { - if (!amdgpu_device_has_dc_support(adev)) { - /* pre DCE11 */ - drm_helper_resume_force_mode(dev); - - /* turn on display hw */ - drm_modeset_lock_all(dev); - - drm_connector_list_iter_begin(dev, &iter); - drm_for_each_connector_iter(connector, &iter) - drm_helper_connector_dpms(connector, - DRM_MODE_DPMS_ON); - drm_connector_list_iter_end(&iter); - - drm_modeset_unlock_all(dev); - } + if (fbcon) amdgpu_fbdev_set_suspend(adev, 0); - } drm_kms_helper_poll_enable(dev); @@ -4144,11 +4116,11 @@ static int amdgpu_device_reset_sriov(struct amdgpu_device *adev, amdgpu_amdkfd_post_reset(adev); error: - amdgpu_virt_release_full_gpu(adev, true); if (!r && adev->virt.gim_feature & AMDGIM_FEATURE_GIM_FLR_VRAMLOST) { amdgpu_inc_vram_lost(adev); r = amdgpu_device_recover_vram(adev); } + amdgpu_virt_release_full_gpu(adev, true); return r; } @@ -4225,6 +4197,8 @@ bool amdgpu_device_should_recover_gpu(struct amdgpu_device *adev) case CHIP_SIENNA_CICHLID: case CHIP_NAVY_FLOUNDER: case CHIP_DIMGREY_CAVEFISH: + case CHIP_VANGOGH: + case CHIP_ALDEBARAN: break; default: goto disabled; @@ -4279,11 +4253,15 @@ int amdgpu_device_mode1_reset(struct amdgpu_device *adev) } int amdgpu_device_pre_asic_reset(struct amdgpu_device *adev, - struct amdgpu_job *job, - bool *need_full_reset_arg) + struct amdgpu_reset_context *reset_context) { int i, r = 0; - bool need_full_reset = *need_full_reset_arg; + struct amdgpu_job *job = NULL; + bool need_full_reset = + test_bit(AMDGPU_NEED_FULL_RESET, &reset_context->flags); + + if (reset_context->reset_req_dev == adev) + job = reset_context->job; /* no need to dump if device is not in good state during probe period */ if (!adev->gmc.xgmi.pending_reset) @@ -4308,6 +4286,13 @@ int amdgpu_device_pre_asic_reset(struct amdgpu_device *adev, if(job) drm_sched_increase_karma(&job->base); + r = amdgpu_reset_prepare_hwcontext(adev, reset_context); + /* If reset handler not implemented, continue; otherwise return */ + if (r == -ENOSYS) + r = 0; + else + return r; + /* Don't suspend on bare metal if we are not going to HW reset the ASIC */ if (!amdgpu_sriov_vf(adev)) { @@ -4326,22 +4311,38 @@ int amdgpu_device_pre_asic_reset(struct amdgpu_device *adev, if (need_full_reset) r = amdgpu_device_ip_suspend(adev); - - *need_full_reset_arg = need_full_reset; + if (need_full_reset) + set_bit(AMDGPU_NEED_FULL_RESET, &reset_context->flags); + else + clear_bit(AMDGPU_NEED_FULL_RESET, + &reset_context->flags); } return r; } -int amdgpu_do_asic_reset(struct amdgpu_hive_info *hive, - struct list_head *device_list_handle, - bool *need_full_reset_arg, - bool skip_hw_reset) +int amdgpu_do_asic_reset(struct list_head *device_list_handle, + struct amdgpu_reset_context *reset_context) { struct amdgpu_device *tmp_adev = NULL; - bool need_full_reset = *need_full_reset_arg, vram_lost = false; + bool need_full_reset, skip_hw_reset, vram_lost = false; int r = 0; + /* Try reset handler method first */ + tmp_adev = list_first_entry(device_list_handle, struct amdgpu_device, + reset_list); + r = amdgpu_reset_perform_reset(tmp_adev, reset_context); + /* If reset handler not implemented, continue; otherwise return */ + if (r == -ENOSYS) + r = 0; + else + return r; + + /* Reset handler not implemented, use the default method */ + need_full_reset = + test_bit(AMDGPU_NEED_FULL_RESET, &reset_context->flags); + skip_hw_reset = test_bit(AMDGPU_SKIP_HW_RESET, &reset_context->flags); + /* * ASIC reset has to be done on all XGMI hive nodes ASAP * to allow proper links negotiation in FW (within 1 sec) @@ -4378,9 +4379,9 @@ int amdgpu_do_asic_reset(struct amdgpu_hive_info *hive, if (!r && amdgpu_ras_intr_triggered()) { list_for_each_entry(tmp_adev, device_list_handle, reset_list) { - if (tmp_adev->mmhub.funcs && - tmp_adev->mmhub.funcs->reset_ras_error_count) - tmp_adev->mmhub.funcs->reset_ras_error_count(tmp_adev); + if (tmp_adev->mmhub.ras_funcs && + tmp_adev->mmhub.ras_funcs->reset_ras_error_count) + tmp_adev->mmhub.ras_funcs->reset_ras_error_count(tmp_adev); } amdgpu_ras_intr_cleared(); @@ -4425,7 +4426,8 @@ int amdgpu_do_asic_reset(struct amdgpu_hive_info *hive, */ amdgpu_register_gpu_instance(tmp_adev); - if (!hive && tmp_adev->gmc.xgmi.num_physical_nodes > 1) + if (!reset_context->hive && + tmp_adev->gmc.xgmi.num_physical_nodes > 1) amdgpu_xgmi_add_device(tmp_adev); r = amdgpu_device_ip_late_init(tmp_adev); @@ -4453,8 +4455,10 @@ int amdgpu_do_asic_reset(struct amdgpu_hive_info *hive, } /* Update PSP FW topology after reset */ - if (hive && tmp_adev->gmc.xgmi.num_physical_nodes > 1) - r = amdgpu_xgmi_update_topology(hive, tmp_adev); + if (reset_context->hive && + tmp_adev->gmc.xgmi.num_physical_nodes > 1) + r = amdgpu_xgmi_update_topology( + reset_context->hive, tmp_adev); } } @@ -4478,7 +4482,10 @@ out: } end: - *need_full_reset_arg = need_full_reset; + if (need_full_reset) + set_bit(AMDGPU_NEED_FULL_RESET, &reset_context->flags); + else + clear_bit(AMDGPU_NEED_FULL_RESET, &reset_context->flags); return r; } @@ -4615,6 +4622,74 @@ static int amdgpu_device_suspend_display_audio(struct amdgpu_device *adev) return 0; } +void amdgpu_device_recheck_guilty_jobs( + struct amdgpu_device *adev, struct list_head *device_list_handle, + struct amdgpu_reset_context *reset_context) +{ + int i, r = 0; + + for (i = 0; i < AMDGPU_MAX_RINGS; ++i) { + struct amdgpu_ring *ring = adev->rings[i]; + int ret = 0; + struct drm_sched_job *s_job; + + if (!ring || !ring->sched.thread) + continue; + + s_job = list_first_entry_or_null(&ring->sched.pending_list, + struct drm_sched_job, list); + if (s_job == NULL) + continue; + + /* clear job's guilty and depend the folowing step to decide the real one */ + drm_sched_reset_karma(s_job); + drm_sched_resubmit_jobs_ext(&ring->sched, 1); + + ret = dma_fence_wait_timeout(s_job->s_fence->parent, false, ring->sched.timeout); + if (ret == 0) { /* timeout */ + DRM_ERROR("Found the real bad job! ring:%s, job_id:%llx\n", + ring->sched.name, s_job->id); + + /* set guilty */ + drm_sched_increase_karma(s_job); +retry: + /* do hw reset */ + if (amdgpu_sriov_vf(adev)) { + amdgpu_virt_fini_data_exchange(adev); + r = amdgpu_device_reset_sriov(adev, false); + if (r) + adev->asic_reset_res = r; + } else { + clear_bit(AMDGPU_SKIP_HW_RESET, + &reset_context->flags); + r = amdgpu_do_asic_reset(device_list_handle, + reset_context); + if (r && r == -EAGAIN) + goto retry; + } + + /* + * add reset counter so that the following + * resubmitted job could flush vmid + */ + atomic_inc(&adev->gpu_reset_counter); + continue; + } + + /* got the hw fence, signal finished fence */ + atomic_dec(ring->sched.score); + dma_fence_get(&s_job->s_fence->finished); + dma_fence_signal(&s_job->s_fence->finished); + dma_fence_put(&s_job->s_fence->finished); + + /* remove node from list and free the job */ + spin_lock(&ring->sched.job_list_lock); + list_del_init(&s_job->list); + spin_unlock(&ring->sched.job_list_lock); + ring->sched.ops->free_job(s_job); + } +} + /** * amdgpu_device_gpu_recover - reset the asic and recover scheduler * @@ -4630,13 +4705,16 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev, struct amdgpu_job *job) { struct list_head device_list, *device_list_handle = NULL; - bool need_full_reset = false; bool job_signaled = false; struct amdgpu_hive_info *hive = NULL; struct amdgpu_device *tmp_adev = NULL; int i, r = 0; bool need_emergency_restart = false; bool audio_suspended = false; + int tmp_vram_lost_counter; + struct amdgpu_reset_context reset_context; + + memset(&reset_context, 0, sizeof(reset_context)); /* * Special case: RAS triggered and full reset isn't supported @@ -4677,6 +4755,12 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev, mutex_lock(&hive->hive_lock); } + reset_context.method = AMD_RESET_METHOD_NONE; + reset_context.reset_req_dev = adev; + reset_context.job = job; + reset_context.hive = hive; + clear_bit(AMDGPU_NEED_FULL_RESET, &reset_context.flags); + /* * lock the device before we try to operate the linked list * if didn't get the device lock, don't touch the linked list since @@ -4777,9 +4861,7 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev, retry: /* Rest of adevs pre asic reset from XGMI hive. */ list_for_each_entry(tmp_adev, device_list_handle, reset_list) { - r = amdgpu_device_pre_asic_reset(tmp_adev, - (tmp_adev == adev) ? job : NULL, - &need_full_reset); + r = amdgpu_device_pre_asic_reset(tmp_adev, &reset_context); /*TODO Should we stop ?*/ if (r) { dev_err(tmp_adev->dev, "GPU pre asic reset failed with err, %d for drm dev, %s ", @@ -4788,6 +4870,7 @@ retry: /* Rest of adevs pre asic reset from XGMI hive. */ } } + tmp_vram_lost_counter = atomic_read(&((adev)->vram_lost_counter)); /* Actual ASIC resets if needed.*/ /* TODO Implement XGMI hive reset logic for SRIOV */ if (amdgpu_sriov_vf(adev)) { @@ -4795,7 +4878,7 @@ retry: /* Rest of adevs pre asic reset from XGMI hive. */ if (r) adev->asic_reset_res = r; } else { - r = amdgpu_do_asic_reset(hive, device_list_handle, &need_full_reset, false); + r = amdgpu_do_asic_reset(device_list_handle, &reset_context); if (r && r == -EAGAIN) goto retry; } @@ -4805,6 +4888,18 @@ skip_hw_reset: /* Post ASIC reset for all devs .*/ list_for_each_entry(tmp_adev, device_list_handle, reset_list) { + /* + * Sometimes a later bad compute job can block a good gfx job as gfx + * and compute ring share internal GC HW mutually. We add an additional + * guilty jobs recheck step to find the real guilty job, it synchronously + * submits and pends for the first job being signaled. If it gets timeout, + * we identify it as a real guilty job. + */ + if (amdgpu_gpu_recovery == 2 && + !(tmp_vram_lost_counter < atomic_read(&adev->vram_lost_counter))) + amdgpu_device_recheck_guilty_jobs( + tmp_adev, device_list_handle, &reset_context); + for (i = 0; i < AMDGPU_MAX_RINGS; ++i) { struct amdgpu_ring *ring = tmp_adev->rings[i]; @@ -5148,12 +5243,14 @@ pci_ers_result_t amdgpu_pci_slot_reset(struct pci_dev *pdev) struct drm_device *dev = pci_get_drvdata(pdev); struct amdgpu_device *adev = drm_to_adev(dev); int r, i; - bool need_full_reset = true; + struct amdgpu_reset_context reset_context; u32 memsize; struct list_head device_list; DRM_INFO("PCI error: slot reset callback!!\n"); + memset(&reset_context, 0, sizeof(reset_context)); + INIT_LIST_HEAD(&device_list); list_add_tail(&adev->reset_list, &device_list); @@ -5176,13 +5273,18 @@ pci_ers_result_t amdgpu_pci_slot_reset(struct pci_dev *pdev) goto out; } + reset_context.method = AMD_RESET_METHOD_NONE; + reset_context.reset_req_dev = adev; + set_bit(AMDGPU_NEED_FULL_RESET, &reset_context.flags); + set_bit(AMDGPU_SKIP_HW_RESET, &reset_context.flags); + adev->in_pci_err_recovery = true; - r = amdgpu_device_pre_asic_reset(adev, NULL, &need_full_reset); + r = amdgpu_device_pre_asic_reset(adev, &reset_context); adev->in_pci_err_recovery = false; if (r) goto out; - r = amdgpu_do_asic_reset(NULL, &device_list, &need_full_reset, true); + r = amdgpu_do_asic_reset(&device_list, &reset_context); out: if (!r) { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c index b05301e1815c..2e622c1675d7 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c @@ -908,6 +908,19 @@ int amdgpu_display_gem_fb_verify_and_init( &amdgpu_fb_funcs); if (ret) goto err; + /* Verify that the modifier is supported. */ + if (!drm_any_plane_has_format(dev, mode_cmd->pixel_format, + mode_cmd->modifier[0])) { + struct drm_format_name_buf format_name; + drm_dbg_kms(dev, + "unsupported pixel format %s / modifier 0x%llx\n", + drm_get_format_name(mode_cmd->pixel_format, + &format_name), + mode_cmd->modifier[0]); + + ret = -EINVAL; + goto err; + } ret = amdgpu_display_framebuffer_init(dev, rfb, mode_cmd, obj); if (ret) @@ -1354,3 +1367,92 @@ bool amdgpu_crtc_get_scanout_position(struct drm_crtc *crtc, return amdgpu_display_get_crtc_scanoutpos(dev, pipe, 0, vpos, hpos, stime, etime, mode); } + +int amdgpu_display_suspend_helper(struct amdgpu_device *adev) +{ + struct drm_device *dev = adev_to_drm(adev); + struct drm_crtc *crtc; + struct drm_connector *connector; + struct drm_connector_list_iter iter; + int r; + + /* turn off display hw */ + drm_modeset_lock_all(dev); + drm_connector_list_iter_begin(dev, &iter); + drm_for_each_connector_iter(connector, &iter) + drm_helper_connector_dpms(connector, + DRM_MODE_DPMS_OFF); + drm_connector_list_iter_end(&iter); + drm_modeset_unlock_all(dev); + /* unpin the front buffers and cursors */ + list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) { + struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc); + struct drm_framebuffer *fb = crtc->primary->fb; + struct amdgpu_bo *robj; + + if (amdgpu_crtc->cursor_bo && !adev->enable_virtual_display) { + struct amdgpu_bo *aobj = gem_to_amdgpu_bo(amdgpu_crtc->cursor_bo); + r = amdgpu_bo_reserve(aobj, true); + if (r == 0) { + amdgpu_bo_unpin(aobj); + amdgpu_bo_unreserve(aobj); + } + } + + if (fb == NULL || fb->obj[0] == NULL) { + continue; + } + robj = gem_to_amdgpu_bo(fb->obj[0]); + /* don't unpin kernel fb objects */ + if (!amdgpu_fbdev_robj_is_fb(adev, robj)) { + r = amdgpu_bo_reserve(robj, true); + if (r == 0) { + amdgpu_bo_unpin(robj); + amdgpu_bo_unreserve(robj); + } + } + } + return r; +} + +int amdgpu_display_resume_helper(struct amdgpu_device *adev) +{ + struct drm_device *dev = adev_to_drm(adev); + struct drm_connector *connector; + struct drm_connector_list_iter iter; + struct drm_crtc *crtc; + int r; + + /* pin cursors */ + list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) { + struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc); + + if (amdgpu_crtc->cursor_bo && !adev->enable_virtual_display) { + struct amdgpu_bo *aobj = gem_to_amdgpu_bo(amdgpu_crtc->cursor_bo); + r = amdgpu_bo_reserve(aobj, true); + if (r == 0) { + r = amdgpu_bo_pin(aobj, AMDGPU_GEM_DOMAIN_VRAM); + if (r != 0) + dev_err(adev->dev, "Failed to pin cursor BO (%d)\n", r); + amdgpu_crtc->cursor_addr = amdgpu_bo_gpu_offset(aobj); + amdgpu_bo_unreserve(aobj); + } + } + } + + drm_helper_resume_force_mode(dev); + + /* turn on display hw */ + drm_modeset_lock_all(dev); + + drm_connector_list_iter_begin(dev, &iter); + drm_for_each_connector_iter(connector, &iter) + drm_helper_connector_dpms(connector, + DRM_MODE_DPMS_ON); + drm_connector_list_iter_end(&iter); + + drm_modeset_unlock_all(dev); + + return 0; +} + diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.h index dc7b7d116549..7b6d83e2b13c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.h @@ -47,4 +47,7 @@ amdgpu_display_user_framebuffer_create(struct drm_device *dev, const struct drm_format_info * amdgpu_lookup_format_info(u32 format, uint64_t modifier); +int amdgpu_display_suspend_helper(struct amdgpu_device *adev); +int amdgpu_display_resume_helper(struct amdgpu_device *adev); + #endif diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c index e0c4f7c7f1b9..baa980a477d9 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c @@ -291,8 +291,8 @@ static struct sg_table *amdgpu_dma_buf_map(struct dma_buf_attachment *attach, break; case TTM_PL_VRAM: - r = amdgpu_vram_mgr_alloc_sgt(adev, &bo->tbo.mem, attach->dev, - dir, &sgt); + r = amdgpu_vram_mgr_alloc_sgt(adev, &bo->tbo.mem, 0, + bo->tbo.base.size, attach->dev, dir, &sgt); if (r) return ERR_PTR(r); break; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 33991b4a5627..922938931e1a 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -36,6 +36,7 @@ #include <linux/vga_switcheroo.h> #include <drm/drm_probe_helper.h> #include <linux/mmu_notifier.h> +#include <linux/suspend.h> #include "amdgpu.h" #include "amdgpu_irq.h" @@ -46,6 +47,7 @@ #include "amdgpu_ras.h" #include "amdgpu_xgmi.h" +#include "amdgpu_reset.h" /* * KMS wrapper. @@ -183,7 +185,7 @@ uint amdgpu_ras_mask = 0xffffffff; int amdgpu_bad_page_threshold = -1; struct amdgpu_watchdog_timer amdgpu_watchdog_timer = { .timeout_fatal_disable = false, - .period = 0x23, /* default to max. timeout = 1 << 0x23 cycles */ + .period = 0x0, /* default to 0x0 (timeout disable) */ }; /** @@ -515,7 +517,7 @@ module_param_named(compute_multipipe, amdgpu_compute_multipipe, int, 0444); * DOC: gpu_recovery (int) * Set to enable GPU recovery mechanism (1 = enable, 0 = disable). The default is -1 (auto, disabled except SRIOV). */ -MODULE_PARM_DESC(gpu_recovery, "Enable GPU recovery mechanism, (1 = enable, 0 = disable, -1 = auto)"); +MODULE_PARM_DESC(gpu_recovery, "Enable GPU recovery mechanism, (2 = advanced tdr mode, 1 = enable, 0 = disable, -1 = auto)"); module_param_named(gpu_recovery, amdgpu_gpu_recovery, int, 0444); /** @@ -551,7 +553,7 @@ module_param_named(timeout_fatal_disable, amdgpu_watchdog_timer.timeout_fatal_di * DOC: timeout_period (uint) * Modify the watchdog timeout max_cycles as (1 << period) */ -MODULE_PARM_DESC(timeout_period, "watchdog timeout period (1 to 0x23(default), timeout maxCycles = (1 << period)"); +MODULE_PARM_DESC(timeout_period, "watchdog timeout period (0 = timeout disabled, 1 ~ 0x23 = timeout maxcycles = (1 << period)"); module_param_named(timeout_period, amdgpu_watchdog_timer.period, uint, 0644); /** @@ -1161,6 +1163,7 @@ static const struct pci_device_id pciidlist[] = { {0x1002, 0x73A3, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SIENNA_CICHLID}, {0x1002, 0x73AB, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SIENNA_CICHLID}, {0x1002, 0x73AE, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SIENNA_CICHLID}, + {0x1002, 0x73AF, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SIENNA_CICHLID}, {0x1002, 0x73BF, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SIENNA_CICHLID}, /* Van Gogh */ @@ -1333,9 +1336,7 @@ amdgpu_pci_shutdown(struct pci_dev *pdev) */ if (!amdgpu_passthrough(adev)) adev->mp1_state = PP_MP1_STATE_UNLOAD; - adev->in_poweroff_reboot_com = true; amdgpu_device_ip_suspend(adev); - adev->in_poweroff_reboot_com = false; adev->mp1_state = PP_MP1_STATE_NONE; } @@ -1349,7 +1350,9 @@ static void amdgpu_drv_delayed_reset_work_handler(struct work_struct *work) struct list_head device_list; struct amdgpu_device *adev; int i, r; - bool need_full_reset = true; + struct amdgpu_reset_context reset_context; + + memset(&reset_context, 0, sizeof(reset_context)); mutex_lock(&mgpu_info.mutex); if (mgpu_info.pending_reset == true) { @@ -1359,9 +1362,14 @@ static void amdgpu_drv_delayed_reset_work_handler(struct work_struct *work) mgpu_info.pending_reset = true; mutex_unlock(&mgpu_info.mutex); + /* Use a common context, just need to make sure full reset is done */ + reset_context.method = AMD_RESET_METHOD_NONE; + set_bit(AMDGPU_NEED_FULL_RESET, &reset_context.flags); + for (i = 0; i < mgpu_info.num_dgpu; i++) { adev = mgpu_info.gpu_ins[i].adev; - r = amdgpu_device_pre_asic_reset(adev, NULL, &need_full_reset); + reset_context.reset_req_dev = adev; + r = amdgpu_device_pre_asic_reset(adev, &reset_context); if (r) { dev_err(adev->dev, "GPU pre asic reset failed with err, %d for drm dev, %s ", r, adev_to_drm(adev)->unique); @@ -1388,7 +1396,10 @@ static void amdgpu_drv_delayed_reset_work_handler(struct work_struct *work) list_for_each_entry(adev, &device_list, reset_list) amdgpu_unregister_gpu_instance(adev); - r = amdgpu_do_asic_reset(NULL, &device_list, &need_full_reset, true); + /* Use a common context, just need to make sure full reset is done */ + set_bit(AMDGPU_SKIP_HW_RESET, &reset_context.flags); + r = amdgpu_do_asic_reset(&device_list, &reset_context); + if (r) { DRM_ERROR("reinit gpus failure"); return; @@ -1402,18 +1413,50 @@ static void amdgpu_drv_delayed_reset_work_handler(struct work_struct *work) return; } +static int amdgpu_pmops_prepare(struct device *dev) +{ + struct drm_device *drm_dev = dev_get_drvdata(dev); + + /* Return a positive number here so + * DPM_FLAG_SMART_SUSPEND works properly + */ + if (amdgpu_device_supports_boco(drm_dev)) + return pm_runtime_suspended(dev) && + pm_suspend_via_firmware(); + + return 0; +} + +static void amdgpu_pmops_complete(struct device *dev) +{ + /* nothing to do */ +} + static int amdgpu_pmops_suspend(struct device *dev) { struct drm_device *drm_dev = dev_get_drvdata(dev); + struct amdgpu_device *adev = drm_to_adev(drm_dev); + int r; - return amdgpu_device_suspend(drm_dev, true); + if (amdgpu_acpi_is_s0ix_supported(adev)) + adev->in_s0ix = true; + adev->in_s3 = true; + r = amdgpu_device_suspend(drm_dev, true); + adev->in_s3 = false; + + return r; } static int amdgpu_pmops_resume(struct device *dev) { struct drm_device *drm_dev = dev_get_drvdata(dev); + struct amdgpu_device *adev = drm_to_adev(drm_dev); + int r; - return amdgpu_device_resume(drm_dev, true); + r = amdgpu_device_resume(drm_dev, true); + if (amdgpu_acpi_is_s0ix_supported(adev)) + adev->in_s0ix = false; + return r; } static int amdgpu_pmops_freeze(struct device *dev) @@ -1422,9 +1465,9 @@ static int amdgpu_pmops_freeze(struct device *dev) struct amdgpu_device *adev = drm_to_adev(drm_dev); int r; - adev->in_hibernate = true; + adev->in_s4 = true; r = amdgpu_device_suspend(drm_dev, true); - adev->in_hibernate = false; + adev->in_s4 = false; if (r) return r; return amdgpu_asic_reset(adev); @@ -1440,13 +1483,8 @@ static int amdgpu_pmops_thaw(struct device *dev) static int amdgpu_pmops_poweroff(struct device *dev) { struct drm_device *drm_dev = dev_get_drvdata(dev); - struct amdgpu_device *adev = drm_to_adev(drm_dev); - int r; - adev->in_poweroff_reboot_com = true; - r = amdgpu_device_suspend(drm_dev, true); - adev->in_poweroff_reboot_com = false; - return r; + return amdgpu_device_suspend(drm_dev, true); } static int amdgpu_pmops_restore(struct device *dev) @@ -1479,7 +1517,7 @@ static int amdgpu_pmops_runtime_suspend(struct device *dev) } adev->in_runpm = true; - if (amdgpu_device_supports_atpx(drm_dev)) + if (amdgpu_device_supports_px(drm_dev)) drm_dev->switch_power_state = DRM_SWITCH_POWER_CHANGING; ret = amdgpu_device_suspend(drm_dev, false); @@ -1488,16 +1526,14 @@ static int amdgpu_pmops_runtime_suspend(struct device *dev) return ret; } - if (amdgpu_device_supports_atpx(drm_dev)) { + if (amdgpu_device_supports_px(drm_dev)) { /* Only need to handle PCI state in the driver for ATPX * PCI core handles it for _PR3. */ - if (!amdgpu_is_atpx_hybrid()) { - amdgpu_device_cache_pci_state(pdev); - pci_disable_device(pdev); - pci_ignore_hotplug(pdev); - pci_set_power_state(pdev, PCI_D3cold); - } + amdgpu_device_cache_pci_state(pdev); + pci_disable_device(pdev); + pci_ignore_hotplug(pdev); + pci_set_power_state(pdev, PCI_D3cold); drm_dev->switch_power_state = DRM_SWITCH_POWER_DYNAMIC_OFF; } else if (amdgpu_device_supports_baco(drm_dev)) { amdgpu_device_baco_enter(drm_dev); @@ -1516,19 +1552,17 @@ static int amdgpu_pmops_runtime_resume(struct device *dev) if (!adev->runpm) return -EINVAL; - if (amdgpu_device_supports_atpx(drm_dev)) { + if (amdgpu_device_supports_px(drm_dev)) { drm_dev->switch_power_state = DRM_SWITCH_POWER_CHANGING; /* Only need to handle PCI state in the driver for ATPX * PCI core handles it for _PR3. */ - if (!amdgpu_is_atpx_hybrid()) { - pci_set_power_state(pdev, PCI_D0); - amdgpu_device_load_pci_state(pdev); - ret = pci_enable_device(pdev); - if (ret) - return ret; - } + pci_set_power_state(pdev, PCI_D0); + amdgpu_device_load_pci_state(pdev); + ret = pci_enable_device(pdev); + if (ret) + return ret; pci_set_master(pdev); } else if (amdgpu_device_supports_boco(drm_dev)) { /* Only need to handle PCI state in the driver for ATPX @@ -1539,7 +1573,7 @@ static int amdgpu_pmops_runtime_resume(struct device *dev) amdgpu_device_baco_exit(drm_dev); } ret = amdgpu_device_resume(drm_dev, false); - if (amdgpu_device_supports_atpx(drm_dev)) + if (amdgpu_device_supports_px(drm_dev)) drm_dev->switch_power_state = DRM_SWITCH_POWER_ON; adev->in_runpm = false; return 0; @@ -1620,6 +1654,8 @@ out: } static const struct dev_pm_ops amdgpu_pm_ops = { + .prepare = amdgpu_pmops_prepare, + .complete = amdgpu_pmops_complete, .suspend = amdgpu_pmops_suspend, .resume = amdgpu_pmops_resume, .freeze = amdgpu_pmops_freeze, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c index 4c5c19820d37..4f10c4529840 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c @@ -205,7 +205,6 @@ static int amdgpufb_create(struct drm_fb_helper *helper, struct drm_gem_object *gobj = NULL; struct amdgpu_bo *abo = NULL; int ret; - unsigned long tmp; memset(&mode_cmd, 0, sizeof(mode_cmd)); mode_cmd.width = sizes->surface_width; @@ -246,8 +245,7 @@ static int amdgpufb_create(struct drm_fb_helper *helper, info->fbops = &amdgpufb_ops; - tmp = amdgpu_bo_gpu_offset(abo) - adev->gmc.vram_start; - info->fix.smem_start = adev->gmc.aper_base + tmp; + info->fix.smem_start = amdgpu_gmc_vram_cpu_pa(adev, abo); info->fix.smem_len = amdgpu_bo_size(abo); info->screen_base = amdgpu_bo_kptr(abo); info->screen_size = amdgpu_bo_size(abo); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c index 1a4809d9e850..47ea46859618 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c @@ -439,7 +439,8 @@ int amdgpu_fence_driver_start_ring(struct amdgpu_ring *ring, * Helper function for amdgpu_fence_driver_init(). */ int amdgpu_fence_driver_init_ring(struct amdgpu_ring *ring, - unsigned num_hw_submission) + unsigned num_hw_submission, + atomic_t *sched_score) { struct amdgpu_device *adev = ring->adev; long timeout; @@ -467,30 +468,31 @@ int amdgpu_fence_driver_init_ring(struct amdgpu_ring *ring, return -ENOMEM; /* No need to setup the GPU scheduler for rings that don't need it */ - if (!ring->no_scheduler) { - switch (ring->funcs->type) { - case AMDGPU_RING_TYPE_GFX: - timeout = adev->gfx_timeout; - break; - case AMDGPU_RING_TYPE_COMPUTE: - timeout = adev->compute_timeout; - break; - case AMDGPU_RING_TYPE_SDMA: - timeout = adev->sdma_timeout; - break; - default: - timeout = adev->video_timeout; - break; - } + if (ring->no_scheduler) + return 0; - r = drm_sched_init(&ring->sched, &amdgpu_sched_ops, - num_hw_submission, amdgpu_job_hang_limit, - timeout, NULL, ring->name); - if (r) { - DRM_ERROR("Failed to create scheduler on ring %s.\n", - ring->name); - return r; - } + switch (ring->funcs->type) { + case AMDGPU_RING_TYPE_GFX: + timeout = adev->gfx_timeout; + break; + case AMDGPU_RING_TYPE_COMPUTE: + timeout = adev->compute_timeout; + break; + case AMDGPU_RING_TYPE_SDMA: + timeout = adev->sdma_timeout; + break; + default: + timeout = adev->video_timeout; + break; + } + + r = drm_sched_init(&ring->sched, &amdgpu_sched_ops, + num_hw_submission, amdgpu_job_hang_limit, + timeout, sched_score, ring->name); + if (r) { + DRM_ERROR("Failed to create scheduler on ring %s.\n", + ring->name); + return r; } return 0; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c index 5807cad833d3..c5a9a4fb10d2 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c @@ -126,6 +126,8 @@ int amdgpu_gart_table_vram_alloc(struct amdgpu_device *adev) AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS; bp.type = ttm_bo_type_kernel; bp.resv = NULL; + bp.bo_ptr_size = sizeof(struct amdgpu_bo); + r = amdgpu_bo_create(adev, &bp, &adev->gart.bo); if (r) { return r; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c index fb7171e5507c..311bcdc59eda 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c @@ -58,6 +58,7 @@ int amdgpu_gem_object_create(struct amdgpu_device *adev, unsigned long size, struct drm_gem_object **obj) { struct amdgpu_bo *bo; + struct amdgpu_bo_user *ubo; struct amdgpu_bo_param bp; int r; @@ -71,10 +72,13 @@ int amdgpu_gem_object_create(struct amdgpu_device *adev, unsigned long size, bp.preferred_domain = initial_domain; bp.flags = flags; bp.domain = initial_domain; - r = amdgpu_bo_create(adev, &bp, &bo); + bp.bo_ptr_size = sizeof(struct amdgpu_bo); + + r = amdgpu_bo_create_user(adev, &bp, &ubo); if (r) return r; + bo = &ubo->bo; *obj = &bo->tbo.base; (*obj)->funcs = &amdgpu_gem_object_funcs; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c index 689addb1520d..95d4f43a03df 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c @@ -310,9 +310,8 @@ int amdgpu_gfx_kiq_init_ring(struct amdgpu_device *adev, ring->eop_gpu_addr = kiq->eop_gpu_addr; ring->no_scheduler = true; sprintf(ring->name, "kiq_%d.%d.%d", ring->me, ring->pipe, ring->queue); - r = amdgpu_ring_init(adev, ring, 1024, - irq, AMDGPU_CP_KIQ_IRQ_DRIVER0, - AMDGPU_RING_PRIO_DEFAULT); + r = amdgpu_ring_init(adev, ring, 1024, irq, AMDGPU_CP_KIQ_IRQ_DRIVER0, + AMDGPU_RING_PRIO_DEFAULT, NULL); if (r) dev_warn(adev->dev, "(%d) failed to init kiq ring\n", r); @@ -463,20 +462,25 @@ int amdgpu_gfx_disable_kcq(struct amdgpu_device *adev) { struct amdgpu_kiq *kiq = &adev->gfx.kiq; struct amdgpu_ring *kiq_ring = &kiq->ring; - int i; + int i, r; if (!kiq->pmf || !kiq->pmf->kiq_unmap_queues) return -EINVAL; + spin_lock(&adev->gfx.kiq.ring_lock); if (amdgpu_ring_alloc(kiq_ring, kiq->pmf->unmap_queues_size * - adev->gfx.num_compute_rings)) + adev->gfx.num_compute_rings)) { + spin_unlock(&adev->gfx.kiq.ring_lock); return -ENOMEM; + } for (i = 0; i < adev->gfx.num_compute_rings; i++) kiq->pmf->kiq_unmap_queues(kiq_ring, &adev->gfx.compute_ring[i], RESET_QUEUES, 0, 0); + r = amdgpu_ring_test_helper(kiq_ring); + spin_unlock(&adev->gfx.kiq.ring_lock); - return amdgpu_ring_test_helper(kiq_ring); + return r; } int amdgpu_queue_mask_bit_to_set_resource_bit(struct amdgpu_device *adev, @@ -519,12 +523,13 @@ int amdgpu_gfx_enable_kcq(struct amdgpu_device *adev) DRM_INFO("kiq ring mec %d pipe %d q %d\n", kiq_ring->me, kiq_ring->pipe, kiq_ring->queue); - + spin_lock(&adev->gfx.kiq.ring_lock); r = amdgpu_ring_alloc(kiq_ring, kiq->pmf->map_queues_size * adev->gfx.num_compute_rings + kiq->pmf->set_resources_size); if (r) { DRM_ERROR("Failed to lock KIQ (%d).\n", r); + spin_unlock(&adev->gfx.kiq.ring_lock); return r; } @@ -533,6 +538,7 @@ int amdgpu_gfx_enable_kcq(struct amdgpu_device *adev) kiq->pmf->kiq_map_queues(kiq_ring, &adev->gfx.compute_ring[i]); r = amdgpu_ring_test_helper(kiq_ring); + spin_unlock(&adev->gfx.kiq.ring_lock); if (r) DRM_ERROR("KCQ enable failed\n"); @@ -671,8 +677,9 @@ int amdgpu_gfx_process_ras_data_cb(struct amdgpu_device *adev, */ if (!amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__GFX)) { kgd2kfd_set_sram_ecc_flag(adev->kfd.dev); - if (adev->gfx.funcs->query_ras_error_count) - adev->gfx.funcs->query_ras_error_count(adev, err_data); + if (adev->gfx.ras_funcs && + adev->gfx.ras_funcs->query_ras_error_count) + adev->gfx.ras_funcs->query_ras_error_count(adev, err_data); amdgpu_ras_reset_gpu(adev); } return AMDGPU_RAS_SUCCESS; @@ -705,7 +712,7 @@ uint32_t amdgpu_kiq_rreg(struct amdgpu_device *adev, uint32_t reg) struct amdgpu_kiq *kiq = &adev->gfx.kiq; struct amdgpu_ring *ring = &kiq->ring; - if (adev->in_pci_err_recovery) + if (amdgpu_device_skip_hw_access(adev)) return 0; BUG_ON(!ring->funcs->emit_rreg); @@ -772,7 +779,7 @@ void amdgpu_kiq_wreg(struct amdgpu_device *adev, uint32_t reg, uint32_t v) BUG_ON(!ring->funcs->emit_wreg); - if (adev->in_pci_err_recovery) + if (amdgpu_device_skip_hw_access(adev)) return; spin_lock_irqsave(&kiq->ring_lock, flags); @@ -836,14 +843,10 @@ int amdgpu_gfx_get_num_kcq(struct amdgpu_device *adev) void amdgpu_gfx_state_change_set(struct amdgpu_device *adev, enum gfx_change_state state) { - if (is_support_sw_smu(adev)) { - smu_gfx_state_change_set(&adev->smu, state); - } else { - mutex_lock(&adev->pm.mutex); - if (adev->powerplay.pp_funcs && - adev->powerplay.pp_funcs->gfx_state_change_set) - ((adev)->powerplay.pp_funcs->gfx_state_change_set( - (adev)->powerplay.pp_handle, state)); - mutex_unlock(&adev->pm.mutex); - } + mutex_lock(&adev->pm.mutex); + if (adev->powerplay.pp_funcs && + adev->powerplay.pp_funcs->gfx_state_change_set) + ((adev)->powerplay.pp_funcs->gfx_state_change_set( + (adev)->powerplay.pp_handle, state)); + mutex_unlock(&adev->pm.mutex); } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h index 38af93f501e1..d43fe2ed8116 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h @@ -205,6 +205,19 @@ struct amdgpu_cu_info { uint32_t bitmap[4][4]; }; +struct amdgpu_gfx_ras_funcs { + int (*ras_late_init)(struct amdgpu_device *adev); + void (*ras_fini)(struct amdgpu_device *adev); + int (*ras_error_inject)(struct amdgpu_device *adev, + void *inject_if); + int (*query_ras_error_count)(struct amdgpu_device *adev, + void *ras_error_status); + void (*reset_ras_error_count)(struct amdgpu_device *adev); + void (*query_ras_error_status)(struct amdgpu_device *adev); + void (*reset_ras_error_status)(struct amdgpu_device *adev); + void (*enable_watchdog_timer)(struct amdgpu_device *adev); +}; + struct amdgpu_gfx_funcs { /* get the gpu clock counter */ uint64_t (*get_gpu_clock_counter)(struct amdgpu_device *adev); @@ -220,14 +233,8 @@ struct amdgpu_gfx_funcs { uint32_t *dst); void (*select_me_pipe_q)(struct amdgpu_device *adev, u32 me, u32 pipe, u32 queue, u32 vmid); - int (*ras_error_inject)(struct amdgpu_device *adev, void *inject_if); - int (*query_ras_error_count) (struct amdgpu_device *adev, void *ras_error_status); - void (*reset_ras_error_count) (struct amdgpu_device *adev); void (*init_spm_golden)(struct amdgpu_device *adev); - void (*query_ras_error_status) (struct amdgpu_device *adev); - void (*reset_ras_error_status) (struct amdgpu_device *adev); void (*update_perfmon_mgcg)(struct amdgpu_device *adev, bool enable); - void (*enable_watchdog_timer)(struct amdgpu_device *adev); }; struct sq_work { @@ -330,7 +337,8 @@ struct amdgpu_gfx { DECLARE_BITMAP (pipe_reserve_bitmap, AMDGPU_MAX_COMPUTE_QUEUES); /*ras */ - struct ras_common_if *ras_if; + struct ras_common_if *ras_if; + const struct amdgpu_gfx_ras_funcs *ras_funcs; }; #define amdgpu_gfx_get_gpu_clock_counter(adev) (adev)->gfx.funcs->get_gpu_clock_counter((adev)) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c index 6f7995293a1e..c39ed9eb0987 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c @@ -55,6 +55,8 @@ int amdgpu_gmc_pdb0_alloc(struct amdgpu_device *adev) AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS; bp.type = ttm_bo_type_kernel; bp.resv = NULL; + bp.bo_ptr_size = sizeof(struct amdgpu_bo); + r = amdgpu_bo_create(adev, &bp, &adev->gmc.pdb0_bo); if (r) return r; @@ -389,26 +391,46 @@ int amdgpu_gmc_ras_late_init(struct amdgpu_device *adev) { int r; - if (adev->umc.funcs && adev->umc.funcs->ras_late_init) { - r = adev->umc.funcs->ras_late_init(adev); + if (adev->umc.ras_funcs && + adev->umc.ras_funcs->ras_late_init) { + r = adev->umc.ras_funcs->ras_late_init(adev); + if (r) + return r; + } + + if (adev->mmhub.ras_funcs && + adev->mmhub.ras_funcs->ras_late_init) { + r = adev->mmhub.ras_funcs->ras_late_init(adev); if (r) return r; } - if (adev->mmhub.funcs && adev->mmhub.funcs->ras_late_init) { - r = adev->mmhub.funcs->ras_late_init(adev); + if (!adev->gmc.xgmi.connected_to_cpu) + adev->gmc.xgmi.ras_funcs = &xgmi_ras_funcs; + + if (adev->gmc.xgmi.ras_funcs && + adev->gmc.xgmi.ras_funcs->ras_late_init) { + r = adev->gmc.xgmi.ras_funcs->ras_late_init(adev); if (r) return r; } - return amdgpu_xgmi_ras_late_init(adev); + return 0; } void amdgpu_gmc_ras_fini(struct amdgpu_device *adev) { - amdgpu_umc_ras_fini(adev); - amdgpu_mmhub_ras_fini(adev); - amdgpu_xgmi_ras_fini(adev); + if (adev->umc.ras_funcs && + adev->umc.ras_funcs->ras_fini) + adev->umc.ras_funcs->ras_fini(adev); + + if (adev->mmhub.ras_funcs && + adev->mmhub.ras_funcs->ras_fini) + amdgpu_mmhub_ras_fini(adev); + + if (adev->gmc.xgmi.ras_funcs && + adev->gmc.xgmi.ras_funcs->ras_fini) + adev->gmc.xgmi.ras_funcs->ras_fini(adev); } /* @@ -465,6 +487,7 @@ void amdgpu_gmc_tmz_set(struct amdgpu_device *adev) { switch (adev->asic_type) { case CHIP_RAVEN: + case CHIP_RENOIR: if (amdgpu_tmz == 0) { adev->gmc.tmz_enabled = false; dev_info(adev->dev, @@ -475,7 +498,6 @@ void amdgpu_gmc_tmz_set(struct amdgpu_device *adev) "Trusted Memory Zone (TMZ) feature enabled\n"); } break; - case CHIP_RENOIR: case CHIP_NAVI10: case CHIP_NAVI14: case CHIP_NAVI12: @@ -514,6 +536,7 @@ void amdgpu_gmc_noretry_set(struct amdgpu_device *adev) switch (adev->asic_type) { case CHIP_VEGA10: case CHIP_VEGA20: + case CHIP_ARCTURUS: case CHIP_ALDEBARAN: /* * noretry = 0 will cause kfd page fault tests fail @@ -638,8 +661,7 @@ void amdgpu_gmc_init_pdb0(struct amdgpu_device *adev) u64 vram_addr = adev->vm_manager.vram_base_offset - adev->gmc.xgmi.physical_node_id * adev->gmc.xgmi.node_segment_size; u64 vram_end = vram_addr + vram_size; - u64 gart_ptb_gpu_pa = amdgpu_bo_gpu_offset(adev->gart.bo) + - adev->vm_manager.vram_base_offset - adev->gmc.vram_start; + u64 gart_ptb_gpu_pa = amdgpu_gmc_vram_pa(adev, adev->gart.bo); flags |= AMDGPU_PTE_VALID | AMDGPU_PTE_READABLE; flags |= AMDGPU_PTE_WRITEABLE; @@ -662,3 +684,39 @@ void amdgpu_gmc_init_pdb0(struct amdgpu_device *adev) /* Requires gart_ptb_gpu_pa to be 4K aligned */ amdgpu_gmc_set_pte_pde(adev, adev->gmc.ptr_pdb0, i, gart_ptb_gpu_pa, flags); } + +/** + * amdgpu_gmc_vram_mc2pa - calculate vram buffer's physical address from MC + * address + * + * @adev: amdgpu_device pointer + * @mc_addr: MC address of buffer + */ +uint64_t amdgpu_gmc_vram_mc2pa(struct amdgpu_device *adev, uint64_t mc_addr) +{ + return mc_addr - adev->gmc.vram_start + adev->vm_manager.vram_base_offset; +} + +/** + * amdgpu_gmc_vram_pa - calculate vram buffer object's physical address from + * GPU's view + * + * @adev: amdgpu_device pointer + * @bo: amdgpu buffer object + */ +uint64_t amdgpu_gmc_vram_pa(struct amdgpu_device *adev, struct amdgpu_bo *bo) +{ + return amdgpu_gmc_vram_mc2pa(adev, amdgpu_bo_gpu_offset(bo)); +} + +/** + * amdgpu_gmc_vram_cpu_pa - calculate vram buffer object's physical address + * from CPU's view + * + * @adev: amdgpu_device pointer + * @bo: amdgpu buffer object + */ +uint64_t amdgpu_gmc_vram_cpu_pa(struct amdgpu_device *adev, struct amdgpu_bo *bo) +{ + return amdgpu_bo_gpu_offset(bo) - adev->gmc.vram_start + adev->gmc.aper_base; +} diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h index 7e248a4e2fa3..9d11c02a3938 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h @@ -135,6 +135,14 @@ struct amdgpu_gmc_funcs { unsigned int (*get_vbios_fb_size)(struct amdgpu_device *adev); }; +struct amdgpu_xgmi_ras_funcs { + int (*ras_late_init)(struct amdgpu_device *adev); + void (*ras_fini)(struct amdgpu_device *adev); + int (*query_ras_error_count)(struct amdgpu_device *adev, + void *ras_error_status); + void (*reset_ras_error_count)(struct amdgpu_device *adev); +}; + struct amdgpu_xgmi { /* from psp */ u64 node_id; @@ -151,6 +159,7 @@ struct amdgpu_xgmi { struct ras_common_if *ras_if; bool connected_to_cpu; bool pending_reset; + const struct amdgpu_xgmi_ras_funcs *ras_funcs; }; struct amdgpu_gmc { @@ -209,15 +218,6 @@ struct amdgpu_gmc { */ u64 fb_start; u64 fb_end; - /* In the case of use GART table for vmid0 FB access, [fb_start, fb_end] - * will be squeezed to GART aperture. But we have a PSP FW issue to fix - * for now. To temporarily workaround the PSP FW issue, added below two - * variables to remember the original fb_start/end to re-enable FB - * aperture to workaround the PSP FW issue. Will delete it after we - * get a proper PSP FW fix. - */ - u64 fb_start_original; - u64 fb_end_original; unsigned vram_width; u64 real_vram_size; int vram_mtrr; @@ -332,4 +332,7 @@ amdgpu_gmc_set_vm_fault_masks(struct amdgpu_device *adev, int hub_type, void amdgpu_gmc_get_vbios_allocations(struct amdgpu_device *adev); void amdgpu_gmc_init_pdb0(struct amdgpu_device *adev); +uint64_t amdgpu_gmc_vram_mc2pa(struct amdgpu_device *adev, uint64_t mc_addr); +uint64_t amdgpu_gmc_vram_pa(struct amdgpu_device *adev, struct amdgpu_bo *bo); +uint64_t amdgpu_gmc_vram_cpu_pa(struct amdgpu_device *adev, struct amdgpu_bo *bo); #endif diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c index 8980329cded0..540c01052b21 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c @@ -49,8 +49,7 @@ static ssize_t amdgpu_mem_info_gtt_total_show(struct device *dev, struct amdgpu_device *adev = drm_to_adev(ddev); struct ttm_resource_manager *man = ttm_manager_type(&adev->mman.bdev, TTM_PL_TT); - return snprintf(buf, PAGE_SIZE, "%llu\n", - man->size * PAGE_SIZE); + return sysfs_emit(buf, "%llu\n", man->size * PAGE_SIZE); } /** @@ -68,8 +67,7 @@ static ssize_t amdgpu_mem_info_gtt_used_show(struct device *dev, struct amdgpu_device *adev = drm_to_adev(ddev); struct ttm_resource_manager *man = ttm_manager_type(&adev->mman.bdev, TTM_PL_TT); - return snprintf(buf, PAGE_SIZE, "%llu\n", - amdgpu_gtt_mgr_usage(man)); + return sysfs_emit(buf, "%llu\n", amdgpu_gtt_mgr_usage(man)); } static DEVICE_ATTR(mem_info_gtt_total, S_IRUGO, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c index 148a3b481b12..a2fe2dac32c1 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c @@ -76,6 +76,8 @@ int amdgpu_ib_get(struct amdgpu_device *adev, struct amdgpu_vm *vm, } ib->ptr = amdgpu_sa_bo_cpu_addr(ib->sa_bo); + /* flush the cache before commit the IB */ + ib->flags = AMDGPU_IB_FLAG_EMIT_MEM_SYNC; if (!vm) ib->gpu_addr = amdgpu_sa_bo_gpu_addr(ib->sa_bo); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c index af026109421a..90f50561b43a 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c @@ -199,13 +199,13 @@ irqreturn_t amdgpu_irq_handler(int irq, void *arg) * ack the interrupt if it is there */ if (amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__PCIE_BIF)) { - if (adev->nbio.funcs && - adev->nbio.funcs->handle_ras_controller_intr_no_bifring) - adev->nbio.funcs->handle_ras_controller_intr_no_bifring(adev); + if (adev->nbio.ras_funcs && + adev->nbio.ras_funcs->handle_ras_controller_intr_no_bifring) + adev->nbio.ras_funcs->handle_ras_controller_intr_no_bifring(adev); - if (adev->nbio.funcs && - adev->nbio.funcs->handle_ras_err_event_athub_intr_no_bifring) - adev->nbio.funcs->handle_ras_err_event_athub_intr_no_bifring(adev); + if (adev->nbio.ras_funcs && + adev->nbio.ras_funcs->handle_ras_err_event_athub_intr_no_bifring) + adev->nbio.ras_funcs->handle_ras_err_event_athub_intr_no_bifring(adev); } return ret; @@ -382,11 +382,6 @@ void amdgpu_irq_fini(struct amdgpu_device *adev) kfree(src->enabled_types); src->enabled_types = NULL; - if (src->data) { - kfree(src->data); - kfree(src); - adev->irq.client[i].sources[j] = NULL; - } } kfree(adev->irq.client[i].sources); adev->irq.client[i].sources = NULL; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.h index ac527e5deae6..cf6116648322 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.h @@ -62,7 +62,6 @@ struct amdgpu_irq_src { unsigned num_types; atomic_t *enabled_types; const struct amdgpu_irq_src_funcs *funcs; - void *data; }; struct amdgpu_irq_client { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c index ada807de978b..39ee88d29cca 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c @@ -159,7 +159,7 @@ int amdgpu_driver_load_kms(struct amdgpu_device *adev, unsigned long flags) goto out; } - if (amdgpu_device_supports_atpx(dev) && + if (amdgpu_device_supports_px(dev) && (amdgpu_runtime_pm != 0)) { /* enable runpm by default for atpx */ adev->runpm = true; dev_info(adev->dev, "Using ATPX for runtime pm\n"); @@ -200,9 +200,13 @@ int amdgpu_driver_load_kms(struct amdgpu_device *adev, unsigned long flags) if (adev->runpm) { /* only need to skip on ATPX */ - if (amdgpu_device_supports_atpx(dev) && - !amdgpu_is_atpx_hybrid()) + if (amdgpu_device_supports_px(dev)) dev_pm_set_driver_flags(dev->dev, DPM_FLAG_NO_DIRECT_COMPLETE); + /* we want direct complete for BOCO */ + if (amdgpu_device_supports_boco(dev)) + dev_pm_set_driver_flags(dev->dev, DPM_FLAG_SMART_PREPARE | + DPM_FLAG_SMART_SUSPEND | + DPM_FLAG_MAY_SKIP_RESUME); pm_runtime_use_autosuspend(dev->dev); pm_runtime_set_autosuspend_delay(dev->dev, 5000); pm_runtime_allow(dev->dev); @@ -785,9 +789,9 @@ int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) dev_info->high_va_offset = AMDGPU_GMC_HOLE_END; dev_info->high_va_max = AMDGPU_GMC_HOLE_END | vm_size; } - dev_info->virtual_address_alignment = max((int)PAGE_SIZE, AMDGPU_GPU_PAGE_SIZE); + dev_info->virtual_address_alignment = max_t(u32, PAGE_SIZE, AMDGPU_GPU_PAGE_SIZE); dev_info->pte_fragment_size = (1 << adev->vm_manager.fragment_size) * AMDGPU_GPU_PAGE_SIZE; - dev_info->gart_page_size = AMDGPU_GPU_PAGE_SIZE; + dev_info->gart_page_size = max_t(u32, PAGE_SIZE, AMDGPU_GPU_PAGE_SIZE); dev_info->cu_active_number = adev->gfx.cu_info.number; dev_info->cu_ao_mask = adev->gfx.cu_info.ao_cu_mask; dev_info->ce_ram_size = adev->gfx.ce_ram_size; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mmhub.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_mmhub.h index 1ae9bdae7311..11aa29933c1f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mmhub.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mmhub.h @@ -21,12 +21,16 @@ #ifndef __AMDGPU_MMHUB_H__ #define __AMDGPU_MMHUB_H__ -struct amdgpu_mmhub_funcs { - void (*ras_init)(struct amdgpu_device *adev); +struct amdgpu_mmhub_ras_funcs { int (*ras_late_init)(struct amdgpu_device *adev); + void (*ras_fini)(struct amdgpu_device *adev); void (*query_ras_error_count)(struct amdgpu_device *adev, - void *ras_error_status); + void *ras_error_status); + void (*query_ras_error_status)(struct amdgpu_device *adev); void (*reset_ras_error_count)(struct amdgpu_device *adev); +}; + +struct amdgpu_mmhub_funcs { u64 (*get_fb_location)(struct amdgpu_device *adev); void (*init)(struct amdgpu_device *adev); int (*gart_enable)(struct amdgpu_device *adev); @@ -40,12 +44,12 @@ struct amdgpu_mmhub_funcs { uint64_t page_table_base); void (*update_power_gating)(struct amdgpu_device *adev, bool enable); - void (*query_ras_error_status)(struct amdgpu_device *adev); }; struct amdgpu_mmhub { struct ras_common_if *ras_if; const struct amdgpu_mmhub_funcs *funcs; + const struct amdgpu_mmhub_ras_funcs *ras_funcs; }; int amdgpu_mmhub_ras_late_init(struct amdgpu_device *adev); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_nbio.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_nbio.h index 7c11bce4514b..25ee53545837 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_nbio.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_nbio.h @@ -47,6 +47,17 @@ struct nbio_hdp_flush_reg { u32 ref_and_mask_sdma7; }; +struct amdgpu_nbio_ras_funcs { + void (*handle_ras_controller_intr_no_bifring)(struct amdgpu_device *adev); + void (*handle_ras_err_event_athub_intr_no_bifring)(struct amdgpu_device *adev); + int (*init_ras_controller_interrupt)(struct amdgpu_device *adev); + int (*init_ras_err_event_athub_interrupt)(struct amdgpu_device *adev); + void (*query_ras_error_count)(struct amdgpu_device *adev, + void *ras_error_status); + int (*ras_late_init)(struct amdgpu_device *adev); + void (*ras_fini)(struct amdgpu_device *adev); +}; + struct amdgpu_nbio_funcs { const struct nbio_hdp_flush_reg *hdp_flush_reg; u32 (*get_hdp_flush_req_offset)(struct amdgpu_device *adev); @@ -79,13 +90,6 @@ struct amdgpu_nbio_funcs { void (*ih_control)(struct amdgpu_device *adev); void (*init_registers)(struct amdgpu_device *adev); void (*remap_hdp_registers)(struct amdgpu_device *adev); - void (*handle_ras_controller_intr_no_bifring)(struct amdgpu_device *adev); - void (*handle_ras_err_event_athub_intr_no_bifring)(struct amdgpu_device *adev); - int (*init_ras_controller_interrupt)(struct amdgpu_device *adev); - int (*init_ras_err_event_athub_interrupt)(struct amdgpu_device *adev); - void (*query_ras_error_count)(struct amdgpu_device *adev, - void *ras_error_status); - int (*ras_late_init)(struct amdgpu_device *adev); void (*enable_aspm)(struct amdgpu_device *adev, bool enable); void (*program_aspm)(struct amdgpu_device *adev); @@ -97,6 +101,7 @@ struct amdgpu_nbio { struct amdgpu_irq_src ras_err_event_athub_irq; struct ras_common_if *ras_if; const struct amdgpu_nbio_funcs *funcs; + const struct amdgpu_nbio_ras_funcs *ras_funcs; }; int amdgpu_nbio_ras_late_init(struct amdgpu_device *adev); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c index ac1bb5089260..1345f7eba011 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c @@ -77,6 +77,7 @@ static void amdgpu_bo_destroy(struct ttm_buffer_object *tbo) { struct amdgpu_device *adev = amdgpu_ttm_adev(tbo->bdev); struct amdgpu_bo *bo = ttm_to_amdgpu_bo(tbo); + struct amdgpu_bo_user *ubo; if (bo->tbo.pin_count > 0) amdgpu_bo_subtract_pin_size(bo); @@ -94,7 +95,11 @@ static void amdgpu_bo_destroy(struct ttm_buffer_object *tbo) } amdgpu_bo_unref(&bo->parent); - kfree(bo->metadata); + if (bo->tbo.type == ttm_bo_type_device) { + ubo = to_amdgpu_bo_user(bo); + kfree(ubo->metadata); + } + kfree(bo); } @@ -248,6 +253,7 @@ int amdgpu_bo_create_reserved(struct amdgpu_device *adev, bp.flags |= AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS; bp.type = ttm_bo_type_kernel; bp.resv = NULL; + bp.bo_ptr_size = sizeof(struct amdgpu_bo); if (!*bo_ptr) { r = amdgpu_bo_create(adev, &bp, bo_ptr); @@ -543,9 +549,10 @@ static int amdgpu_bo_do_create(struct amdgpu_device *adev, if (!amdgpu_bo_validate_size(adev, size, bp->domain)) return -ENOMEM; - *bo_ptr = NULL; + BUG_ON(bp->bo_ptr_size < sizeof(struct amdgpu_bo)); - bo = kzalloc(sizeof(struct amdgpu_bo), GFP_KERNEL); + *bo_ptr = NULL; + bo = kzalloc(bp->bo_ptr_size, GFP_KERNEL); if (bo == NULL) return -ENOMEM; drm_gem_private_object_init(adev_to_drm(adev), &bo->tbo.base, size); @@ -635,6 +642,7 @@ static int amdgpu_bo_create_shadow(struct amdgpu_device *adev, AMDGPU_GEM_CREATE_SHADOW; bp.type = ttm_bo_type_kernel; bp.resv = bo->tbo.base.resv; + bp.bo_ptr_size = sizeof(struct amdgpu_bo); r = amdgpu_bo_do_create(adev, &bp, &bo->shadow); if (!r) { @@ -669,6 +677,7 @@ int amdgpu_bo_create(struct amdgpu_device *adev, int r; bp->flags = bp->flags & ~AMDGPU_GEM_CREATE_SHADOW; + r = amdgpu_bo_do_create(adev, bp, bo_ptr); if (r) return r; @@ -691,6 +700,34 @@ int amdgpu_bo_create(struct amdgpu_device *adev, } /** + * amdgpu_bo_create_user - create an &amdgpu_bo_user buffer object + * @adev: amdgpu device object + * @bp: parameters to be used for the buffer object + * @ubo_ptr: pointer to the buffer object pointer + * + * Create a BO to be used by user application; + * + * Returns: + * 0 for success or a negative error code on failure. + */ + +int amdgpu_bo_create_user(struct amdgpu_device *adev, + struct amdgpu_bo_param *bp, + struct amdgpu_bo_user **ubo_ptr) +{ + struct amdgpu_bo *bo_ptr; + int r; + + bp->flags = bp->flags & ~AMDGPU_GEM_CREATE_SHADOW; + bp->bo_ptr_size = sizeof(struct amdgpu_bo_user); + r = amdgpu_bo_do_create(adev, bp, &bo_ptr); + if (r) + return r; + + *ubo_ptr = to_amdgpu_bo_user(bo_ptr); + return r; +} +/** * amdgpu_bo_validate - validate an &amdgpu_bo buffer object * @bo: pointer to the buffer object * @@ -1024,13 +1061,10 @@ int amdgpu_bo_evict_vram(struct amdgpu_device *adev) { struct ttm_resource_manager *man; - /* late 2.6.33 fix IGP hibernate - we need pm ops to do this correct */ -#ifndef CONFIG_HIBERNATION - if (adev->flags & AMD_IS_APU) { - /* Useless to evict on IGP chips */ + if (adev->in_s3 && (adev->flags & AMD_IS_APU)) { + /* No need to evict vram on APUs for suspend to ram */ return 0; } -#endif man = ttm_manager_type(&adev->mman.bdev, TTM_PL_VRAM); return ttm_resource_manager_evict_all(&adev->mman.bdev, man); @@ -1096,25 +1130,6 @@ void amdgpu_bo_fini(struct amdgpu_device *adev) } /** - * amdgpu_bo_fbdev_mmap - mmap fbdev memory - * @bo: &amdgpu_bo buffer object - * @vma: vma as input from the fbdev mmap method - * - * Calls ttm_fbdev_mmap() to mmap fbdev memory if it is backed by a bo. - * - * Returns: - * 0 for success or a negative error code on failure. - */ -int amdgpu_bo_fbdev_mmap(struct amdgpu_bo *bo, - struct vm_area_struct *vma) -{ - if (vma->vm_pgoff != 0) - return -EACCES; - - return ttm_bo_mmap_obj(vma, &bo->tbo); -} - -/** * amdgpu_bo_set_tiling_flags - set tiling flags * @bo: &amdgpu_bo buffer object * @tiling_flags: new flags @@ -1128,12 +1143,15 @@ int amdgpu_bo_fbdev_mmap(struct amdgpu_bo *bo, int amdgpu_bo_set_tiling_flags(struct amdgpu_bo *bo, u64 tiling_flags) { struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev); + struct amdgpu_bo_user *ubo; + BUG_ON(bo->tbo.type == ttm_bo_type_kernel); if (adev->family <= AMDGPU_FAMILY_CZ && AMDGPU_TILING_GET(tiling_flags, TILE_SPLIT) > 6) return -EINVAL; - bo->tiling_flags = tiling_flags; + ubo = to_amdgpu_bo_user(bo); + ubo->tiling_flags = tiling_flags; return 0; } @@ -1147,10 +1165,14 @@ int amdgpu_bo_set_tiling_flags(struct amdgpu_bo *bo, u64 tiling_flags) */ void amdgpu_bo_get_tiling_flags(struct amdgpu_bo *bo, u64 *tiling_flags) { + struct amdgpu_bo_user *ubo; + + BUG_ON(bo->tbo.type == ttm_bo_type_kernel); dma_resv_assert_held(bo->tbo.base.resv); + ubo = to_amdgpu_bo_user(bo); if (tiling_flags) - *tiling_flags = bo->tiling_flags; + *tiling_flags = ubo->tiling_flags; } /** @@ -1169,13 +1191,16 @@ void amdgpu_bo_get_tiling_flags(struct amdgpu_bo *bo, u64 *tiling_flags) int amdgpu_bo_set_metadata (struct amdgpu_bo *bo, void *metadata, uint32_t metadata_size, uint64_t flags) { + struct amdgpu_bo_user *ubo; void *buffer; + BUG_ON(bo->tbo.type == ttm_bo_type_kernel); + ubo = to_amdgpu_bo_user(bo); if (!metadata_size) { - if (bo->metadata_size) { - kfree(bo->metadata); - bo->metadata = NULL; - bo->metadata_size = 0; + if (ubo->metadata_size) { + kfree(ubo->metadata); + ubo->metadata = NULL; + ubo->metadata_size = 0; } return 0; } @@ -1187,10 +1212,10 @@ int amdgpu_bo_set_metadata (struct amdgpu_bo *bo, void *metadata, if (buffer == NULL) return -ENOMEM; - kfree(bo->metadata); - bo->metadata_flags = flags; - bo->metadata = buffer; - bo->metadata_size = metadata_size; + kfree(ubo->metadata); + ubo->metadata_flags = flags; + ubo->metadata = buffer; + ubo->metadata_size = metadata_size; return 0; } @@ -1214,21 +1239,25 @@ int amdgpu_bo_get_metadata(struct amdgpu_bo *bo, void *buffer, size_t buffer_size, uint32_t *metadata_size, uint64_t *flags) { + struct amdgpu_bo_user *ubo; + if (!buffer && !metadata_size) return -EINVAL; + BUG_ON(bo->tbo.type == ttm_bo_type_kernel); + ubo = to_amdgpu_bo_user(bo); if (buffer) { - if (buffer_size < bo->metadata_size) + if (buffer_size < ubo->metadata_size) return -EINVAL; - if (bo->metadata_size) - memcpy(buffer, bo->metadata, bo->metadata_size); + if (ubo->metadata_size) + memcpy(buffer, ubo->metadata, ubo->metadata_size); } if (metadata_size) - *metadata_size = bo->metadata_size; + *metadata_size = ubo->metadata_size; if (flags) - *flags = bo->metadata_flags; + *flags = ubo->metadata_flags; return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h index 54ceb065e546..2d1fefbe1e99 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h @@ -37,9 +37,12 @@ #define AMDGPU_BO_INVALID_OFFSET LONG_MAX #define AMDGPU_BO_MAX_PLACEMENTS 3 +#define to_amdgpu_bo_user(abo) container_of((abo), struct amdgpu_bo_user, bo) + struct amdgpu_bo_param { unsigned long size; int byte_align; + u32 bo_ptr_size; u32 domain; u32 preferred_domain; u64 flags; @@ -89,10 +92,6 @@ struct amdgpu_bo { struct ttm_buffer_object tbo; struct ttm_bo_kmap_obj kmap; u64 flags; - u64 tiling_flags; - u64 metadata_flags; - void *metadata; - u32 metadata_size; unsigned prime_shared_count; /* per VM structure for page tables and with virtual addresses */ struct amdgpu_vm_bo_base *vm_bo; @@ -111,6 +110,15 @@ struct amdgpu_bo { struct kgd_mem *kfd_bo; }; +struct amdgpu_bo_user { + struct amdgpu_bo bo; + u64 tiling_flags; + u64 metadata_flags; + void *metadata; + u32 metadata_size; + +}; + static inline struct amdgpu_bo *ttm_to_amdgpu_bo(struct ttm_buffer_object *tbo) { return container_of(tbo, struct amdgpu_bo, tbo); @@ -254,6 +262,9 @@ int amdgpu_bo_create_kernel(struct amdgpu_device *adev, int amdgpu_bo_create_kernel_at(struct amdgpu_device *adev, uint64_t offset, uint64_t size, uint32_t domain, struct amdgpu_bo **bo_ptr, void **cpu_addr); +int amdgpu_bo_create_user(struct amdgpu_device *adev, + struct amdgpu_bo_param *bp, + struct amdgpu_bo_user **ubo_ptr); void amdgpu_bo_free_kernel(struct amdgpu_bo **bo, u64 *gpu_addr, void **cpu_addr); int amdgpu_bo_kmap(struct amdgpu_bo *bo, void **ptr); @@ -268,8 +279,6 @@ void amdgpu_bo_unpin(struct amdgpu_bo *bo); int amdgpu_bo_evict_vram(struct amdgpu_device *adev); int amdgpu_bo_init(struct amdgpu_device *adev); void amdgpu_bo_fini(struct amdgpu_device *adev); -int amdgpu_bo_fbdev_mmap(struct amdgpu_bo *bo, - struct vm_area_struct *vma); int amdgpu_bo_set_tiling_flags(struct amdgpu_bo *bo, u64 tiling_flags); void amdgpu_bo_get_tiling_flags(struct amdgpu_bo *bo, u64 *tiling_flags); int amdgpu_bo_set_metadata (struct amdgpu_bo *bo, void *metadata, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_pmu.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_pmu.c index 19c0a3655228..82e9ecf84352 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_pmu.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_pmu.c @@ -519,8 +519,10 @@ static int init_pmu_entry_by_type_and_add(struct amdgpu_pmu_entry *pmu_entry, pmu_entry->pmu.attr_groups = kmemdup(attr_groups, sizeof(attr_groups), GFP_KERNEL); - if (!pmu_entry->pmu.attr_groups) + if (!pmu_entry->pmu.attr_groups) { + ret = -ENOMEM; goto err_attr_group; + } snprintf(pmu_name, PMU_NAME_SIZE, "%s_%d", pmu_entry->pmu_file_prefix, adev_to_drm(pmu_entry->adev)->primary->index); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c index bae304b0d67a..a09483beb968 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c @@ -328,8 +328,12 @@ psp_cmd_submit_buf(struct psp_context *psp, static void psp_prep_tmr_cmd_buf(struct psp_context *psp, struct psp_gfx_cmd_resp *cmd, - uint64_t tmr_mc, uint32_t size) + uint64_t tmr_mc, struct amdgpu_bo *tmr_bo) { + struct amdgpu_device *adev = psp->adev; + uint32_t size = amdgpu_bo_size(tmr_bo); + uint64_t tmr_pa = amdgpu_gmc_vram_pa(adev, tmr_bo); + if (amdgpu_sriov_vf(psp->adev)) cmd->cmd_id = GFX_CMD_ID_SETUP_VMR; else @@ -337,6 +341,9 @@ static void psp_prep_tmr_cmd_buf(struct psp_context *psp, cmd->cmd.cmd_setup_tmr.buf_phy_addr_lo = lower_32_bits(tmr_mc); cmd->cmd.cmd_setup_tmr.buf_phy_addr_hi = upper_32_bits(tmr_mc); cmd->cmd.cmd_setup_tmr.buf_size = size; + cmd->cmd.cmd_setup_tmr.bitfield.virt_phy_addr = 1; + cmd->cmd.cmd_setup_tmr.system_phy_addr_lo = lower_32_bits(tmr_pa); + cmd->cmd.cmd_setup_tmr.system_phy_addr_hi = upper_32_bits(tmr_pa); } static void psp_prep_load_toc_cmd_buf(struct psp_gfx_cmd_resp *cmd, @@ -407,16 +414,6 @@ static int psp_tmr_init(struct psp_context *psp) AMDGPU_GEM_DOMAIN_VRAM, &psp->tmr_bo, &psp->tmr_mc_addr, pptr); - /* workaround the tmr_mc_addr: - * PSP requires an address in FB aperture. Right now driver produce - * tmr_mc_addr in the GART aperture. Convert it back to FB aperture - * for PSP. Will revert it after we get a fix from PSP FW. - */ - if (psp->adev->asic_type == CHIP_ALDEBARAN) { - psp->tmr_mc_addr -= psp->adev->gmc.fb_start; - psp->tmr_mc_addr += psp->adev->gmc.fb_start_original; - } - return ret; } @@ -466,8 +463,7 @@ static int psp_tmr_load(struct psp_context *psp) if (!cmd) return -ENOMEM; - psp_prep_tmr_cmd_buf(psp, cmd, psp->tmr_mc_addr, - amdgpu_bo_size(psp->tmr_bo)); + psp_prep_tmr_cmd_buf(psp, cmd, psp->tmr_mc_addr, psp->tmr_bo); DRM_INFO("reserve 0x%lx from 0x%llx for PSP TMR\n", amdgpu_bo_size(psp->tmr_bo), psp->tmr_mc_addr); @@ -556,6 +552,24 @@ int psp_get_fw_attestation_records_addr(struct psp_context *psp, return ret; } +static int psp_boot_config_set(struct amdgpu_device *adev) +{ + struct psp_context *psp = &adev->psp; + struct psp_gfx_cmd_resp *cmd = psp->cmd; + + if (adev->asic_type != CHIP_SIENNA_CICHLID || amdgpu_sriov_vf(adev)) + return 0; + + memset(cmd, 0, sizeof(struct psp_gfx_cmd_resp)); + + cmd->cmd_id = GFX_CMD_ID_BOOT_CFG; + cmd->cmd.boot_cfg.sub_cmd = BOOTCFG_CMD_SET; + cmd->cmd.boot_cfg.boot_config = BOOT_CONFIG_GECC; + cmd->cmd.boot_cfg.boot_config_valid = BOOT_CONFIG_GECC; + + return psp_cmd_submit_buf(psp, NULL, cmd, psp->fence_buf_mc_addr); +} + static int psp_rl_load(struct amdgpu_device *adev) { struct psp_context *psp = &adev->psp; @@ -1912,6 +1926,11 @@ static int psp_hw_start(struct psp_context *psp) return ret; } + ret = psp_boot_config_set(adev); + if (ret) { + DRM_WARN("PSP set boot config@\n"); + } + ret = psp_tmr_init(psp); if (ret) { DRM_ERROR("PSP tmr init failed!\n"); @@ -2146,9 +2165,13 @@ static int psp_load_smu_fw(struct psp_context *psp) if (!ucode->fw || amdgpu_sriov_vf(psp->adev)) return 0; - - if (amdgpu_in_reset(adev) && ras && ras->supported && - adev->asic_type == CHIP_ARCTURUS) { + if ((amdgpu_in_reset(adev) && + ras && ras->supported && + (adev->asic_type == CHIP_ARCTURUS || + adev->asic_type == CHIP_VEGA20)) || + (adev->in_runpm && + adev->asic_type >= CHIP_NAVI10 && + adev->asic_type <= CHIP_NAVI12)) { ret = amdgpu_dpm_set_mp1_state(adev, PP_MP1_STATE_UNLOAD); if (ret) { DRM_WARN("Failed to set MP1 state prepare for reload\n"); @@ -2201,6 +2224,22 @@ static bool fw_load_skip_check(struct psp_context *psp, return false; } +int psp_load_fw_list(struct psp_context *psp, + struct amdgpu_firmware_info **ucode_list, int ucode_count) +{ + int ret = 0, i; + struct amdgpu_firmware_info *ucode; + + for (i = 0; i < ucode_count; ++i) { + ucode = ucode_list[i]; + psp_print_fw_hdr(psp, ucode); + ret = psp_execute_np_fw_load(psp, ucode); + if (ret) + return ret; + } + return ret; +} + static int psp_np_fw_load(struct psp_context *psp) { int i, ret; @@ -2967,7 +3006,7 @@ static ssize_t psp_usbc_pd_fw_sysfs_read(struct device *dev, return ret; } - return snprintf(buf, PAGE_SIZE, "%x\n", fw_ver); + return sysfs_emit(buf, "%x\n", fw_ver); } static ssize_t psp_usbc_pd_fw_sysfs_write(struct device *dev, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h index 64f143390835..46a5328e00e0 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h @@ -420,4 +420,7 @@ int psp_init_ta_microcode(struct psp_context *psp, const char *chip_name); int psp_get_fw_attestation_records_addr(struct psp_context *psp, uint64_t *output_ptr); + +int psp_load_fw_list(struct psp_context *psp, + struct amdgpu_firmware_info **ucode_list, int ucode_count); #endif diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c index 0e16683876aa..b0d2fc9454ca 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c @@ -99,6 +99,49 @@ static bool amdgpu_ras_get_error_query_ready(struct amdgpu_device *adev) return false; } +static int amdgpu_reserve_page_direct(struct amdgpu_device *adev, uint64_t address) +{ + struct ras_err_data err_data = {0, 0, 0, NULL}; + struct eeprom_table_record err_rec; + + if ((address >= adev->gmc.mc_vram_size) || + (address >= RAS_UMC_INJECT_ADDR_LIMIT)) { + dev_warn(adev->dev, + "RAS WARN: input address 0x%llx is invalid.\n", + address); + return -EINVAL; + } + + if (amdgpu_ras_check_bad_page(adev, address)) { + dev_warn(adev->dev, + "RAS WARN: 0x%llx has already been marked as bad page!\n", + address); + return 0; + } + + memset(&err_rec, 0x0, sizeof(struct eeprom_table_record)); + + err_rec.address = address; + err_rec.retired_page = address >> AMDGPU_GPU_PAGE_SHIFT; + err_rec.ts = (uint64_t)ktime_get_real_seconds(); + err_rec.err_type = AMDGPU_RAS_EEPROM_ERR_NON_RECOVERABLE; + + err_data.err_addr = &err_rec; + err_data.err_addr_cnt = 1; + + if (amdgpu_bad_page_threshold != 0) { + amdgpu_ras_add_bad_pages(adev, err_data.err_addr, + err_data.err_addr_cnt); + amdgpu_ras_save_bad_pages(adev); + } + + dev_warn(adev->dev, "WARNING: THIS IS ONLY FOR TEST PURPOSES AND WILL CORRUPT RAS EEPROM\n"); + dev_warn(adev->dev, "Clear EEPROM:\n"); + dev_warn(adev->dev, " echo 1 > /sys/kernel/debug/dri/0/ras/ras_eeprom_reset\n"); + + return 0; +} + static ssize_t amdgpu_ras_debugfs_read(struct file *f, char __user *buf, size_t size, loff_t *pos) { @@ -178,11 +221,24 @@ static int amdgpu_ras_debugfs_ctrl_parse_data(struct file *f, op = 1; else if (sscanf(str, "inject %32s %8s", block_name, err) == 2) op = 2; + else if (strstr(str, "retire_page") != NULL) + op = 3; else if (str[0] && str[1] && str[2] && str[3]) /* ascii string, but commands are not matched. */ return -EINVAL; if (op != -1) { + if (op == 3) { + if (sscanf(str, "%*s 0x%llx", &address) != 1 && + sscanf(str, "%*s %llu", &address) != 1) + return -EINVAL; + + data->op = op; + data->inject.address = address; + + return 0; + } + if (amdgpu_ras_find_block_id_by_name(block_name, &block_id)) return -EINVAL; @@ -198,11 +254,11 @@ static int amdgpu_ras_debugfs_ctrl_parse_data(struct file *f, data->op = op; if (op == 2) { - if (sscanf(str, "%*s %*s %*s %u %llu %llu", - &sub_block, &address, &value) != 3) - if (sscanf(str, "%*s %*s %*s 0x%x 0x%llx 0x%llx", - &sub_block, &address, &value) != 3) - return -EINVAL; + if (sscanf(str, "%*s %*s %*s 0x%x 0x%llx 0x%llx", + &sub_block, &address, &value) != 3 && + sscanf(str, "%*s %*s %*s %u %llu %llu", + &sub_block, &address, &value) != 3) + return -EINVAL; data->head.sub_block_index = sub_block; data->inject.address = address; data->inject.value = value; @@ -221,7 +277,7 @@ static int amdgpu_ras_debugfs_ctrl_parse_data(struct file *f, /** * DOC: AMDGPU RAS debugfs control interface * - * It accepts struct ras_debug_if who has two members. + * The control interface accepts struct ras_debug_if which has two members. * * First member: ras_debug_if::head or ras_debug_if::inject. * @@ -246,32 +302,33 @@ static int amdgpu_ras_debugfs_ctrl_parse_data(struct file *f, * * How to use the interface? * - * Programs + * In a program * - * Copy the struct ras_debug_if in your codes and initialize it. - * Write the struct to the control node. + * Copy the struct ras_debug_if in your code and initialize it. + * Write the struct to the control interface. * - * Shells + * From shell * * .. code-block:: bash * - * echo op block [error [sub_block address value]] > .../ras/ras_ctrl + * echo "disable <block>" > /sys/kernel/debug/dri/<N>/ras/ras_ctrl + * echo "enable <block> <error>" > /sys/kernel/debug/dri/<N>/ras/ras_ctrl + * echo "inject <block> <error> <sub-block> <address> <value> > /sys/kernel/debug/dri/<N>/ras/ras_ctrl * - * Parameters: + * Where N, is the card which you want to affect. * - * op: disable, enable, inject - * disable: only block is needed - * enable: block and error are needed - * inject: error, address, value are needed - * block: umc, sdma, gfx, ......... + * "disable" requires only the block. + * "enable" requires the block and error type. + * "inject" requires the block, error type, address, and value. + * The block is one of: umc, sdma, gfx, etc. * see ras_block_string[] for details - * error: ue, ce - * ue: multi_uncorrectable - * ce: single_correctable - * sub_block: - * sub block index, pass 0 if there is no sub block + * The error type is one of: ue, ce, where, + * ue is multi-uncorrectable + * ce is single-correctable + * The sub-block is a the sub-block index, pass 0 if there is no sub-block. + * The address and value are hexadecimal numbers, leading 0x is optional. * - * here are some examples for bash commands: + * For instance, * * .. code-block:: bash * @@ -279,17 +336,17 @@ static int amdgpu_ras_debugfs_ctrl_parse_data(struct file *f, * echo inject umc ce 0 0 0 > /sys/kernel/debug/dri/0/ras/ras_ctrl * echo disable umc > /sys/kernel/debug/dri/0/ras/ras_ctrl * - * How to check the result? + * How to check the result of the operation? * - * For disable/enable, please check ras features at + * To check disable/enable, see "ras" features at, * /sys/class/drm/card[0/1/2...]/device/ras/features * - * For inject, please check corresponding err count at - * /sys/class/drm/card[0/1/2...]/device/ras/[gfx/sdma/...]_err_count + * To check inject, see the corresponding error count at, + * /sys/class/drm/card[0/1/2...]/device/ras/[gfx|sdma|umc|...]_err_count * * .. note:: * Operations are only allowed on blocks which are supported. - * Please check ras mask at /sys/module/amdgpu/parameters/ras_mask + * Check the "ras" mask at /sys/module/amdgpu/parameters/ras_mask * to see which blocks support RAS on a particular asic. * */ @@ -310,6 +367,14 @@ static ssize_t amdgpu_ras_debugfs_ctrl_write(struct file *f, const char __user * if (ret) return -EINVAL; + if (data.op == 3) { + ret = amdgpu_reserve_page_direct(adev, data.inject.address); + if (!ret) + return size; + else + return ret; + } + if (!amdgpu_ras_is_supported(adev, data.head.block)) return -EINVAL; @@ -431,15 +496,19 @@ static ssize_t amdgpu_ras_sysfs_read(struct device *dev, }; if (!amdgpu_ras_get_error_query_ready(obj->adev)) - return snprintf(buf, PAGE_SIZE, - "Query currently inaccessible\n"); + return sysfs_emit(buf, "Query currently inaccessible\n"); if (amdgpu_ras_query_error_status(obj->adev, &info)) return -EINVAL; - return snprintf(buf, PAGE_SIZE, "%s: %lu\n%s: %lu\n", - "ue", info.ue_count, - "ce", info.ce_count); + + if (obj->adev->asic_type == CHIP_ALDEBARAN) { + if (amdgpu_ras_reset_error_status(obj->adev, info.head.block)) + DRM_WARN("Failed to reset error counter and error status"); + } + + return sysfs_emit(buf, "%s: %lu\n%s: %lu\n", "ue", info.ue_count, + "ce", info.ce_count); } /* obj begin */ @@ -449,11 +518,10 @@ static ssize_t amdgpu_ras_sysfs_read(struct device *dev, static inline void put_obj(struct ras_manager *obj) { - if (obj && --obj->use == 0) + if (obj && (--obj->use == 0)) list_del(&obj->node); - if (obj && obj->use < 0) { - DRM_ERROR("RAS ERROR: Unbalance obj(%s) use\n", obj->head.name); - } + if (obj && (obj->use < 0)) + DRM_ERROR("RAS ERROR: Unbalance obj(%s) use\n", obj->head.name); } /* make one obj and return it. */ @@ -777,13 +845,15 @@ int amdgpu_ras_query_error_status(struct amdgpu_device *adev, switch (info->head.block) { case AMDGPU_RAS_BLOCK__UMC: - if (adev->umc.funcs->query_ras_error_count) - adev->umc.funcs->query_ras_error_count(adev, &err_data); + if (adev->umc.ras_funcs && + adev->umc.ras_funcs->query_ras_error_count) + adev->umc.ras_funcs->query_ras_error_count(adev, &err_data); /* umc query_ras_error_address is also responsible for clearing * error status */ - if (adev->umc.funcs->query_ras_error_address) - adev->umc.funcs->query_ras_error_address(adev, &err_data); + if (adev->umc.ras_funcs && + adev->umc.ras_funcs->query_ras_error_address) + adev->umc.ras_funcs->query_ras_error_address(adev, &err_data); break; case AMDGPU_RAS_BLOCK__SDMA: if (adev->sdma.funcs->query_ras_error_count) { @@ -793,25 +863,32 @@ int amdgpu_ras_query_error_status(struct amdgpu_device *adev, } break; case AMDGPU_RAS_BLOCK__GFX: - if (adev->gfx.funcs->query_ras_error_count) - adev->gfx.funcs->query_ras_error_count(adev, &err_data); + if (adev->gfx.ras_funcs && + adev->gfx.ras_funcs->query_ras_error_count) + adev->gfx.ras_funcs->query_ras_error_count(adev, &err_data); - if (adev->gfx.funcs->query_ras_error_status) - adev->gfx.funcs->query_ras_error_status(adev); + if (adev->gfx.ras_funcs && + adev->gfx.ras_funcs->query_ras_error_status) + adev->gfx.ras_funcs->query_ras_error_status(adev); break; case AMDGPU_RAS_BLOCK__MMHUB: - if (adev->mmhub.funcs->query_ras_error_count) - adev->mmhub.funcs->query_ras_error_count(adev, &err_data); + if (adev->mmhub.ras_funcs && + adev->mmhub.ras_funcs->query_ras_error_count) + adev->mmhub.ras_funcs->query_ras_error_count(adev, &err_data); - if (adev->mmhub.funcs->query_ras_error_status) - adev->mmhub.funcs->query_ras_error_status(adev); + if (adev->mmhub.ras_funcs && + adev->mmhub.ras_funcs->query_ras_error_status) + adev->mmhub.ras_funcs->query_ras_error_status(adev); break; case AMDGPU_RAS_BLOCK__PCIE_BIF: - if (adev->nbio.funcs->query_ras_error_count) - adev->nbio.funcs->query_ras_error_count(adev, &err_data); + if (adev->nbio.ras_funcs && + adev->nbio.ras_funcs->query_ras_error_count) + adev->nbio.ras_funcs->query_ras_error_count(adev, &err_data); break; case AMDGPU_RAS_BLOCK__XGMI_WAFL: - amdgpu_xgmi_query_ras_error_count(adev, &err_data); + if (adev->gmc.xgmi.ras_funcs && + adev->gmc.xgmi.ras_funcs->query_ras_error_count) + adev->gmc.xgmi.ras_funcs->query_ras_error_count(adev, &err_data); break; default: break; @@ -848,15 +925,18 @@ int amdgpu_ras_reset_error_status(struct amdgpu_device *adev, switch (block) { case AMDGPU_RAS_BLOCK__GFX: - if (adev->gfx.funcs->reset_ras_error_count) - adev->gfx.funcs->reset_ras_error_count(adev); + if (adev->gfx.ras_funcs && + adev->gfx.ras_funcs->reset_ras_error_count) + adev->gfx.ras_funcs->reset_ras_error_count(adev); - if (adev->gfx.funcs->reset_ras_error_status) - adev->gfx.funcs->reset_ras_error_status(adev); + if (adev->gfx.ras_funcs && + adev->gfx.ras_funcs->reset_ras_error_status) + adev->gfx.ras_funcs->reset_ras_error_status(adev); break; case AMDGPU_RAS_BLOCK__MMHUB: - if (adev->mmhub.funcs->reset_ras_error_count) - adev->mmhub.funcs->reset_ras_error_count(adev); + if (adev->mmhub.ras_funcs && + adev->mmhub.ras_funcs->reset_ras_error_count) + adev->mmhub.ras_funcs->reset_ras_error_count(adev); break; case AMDGPU_RAS_BLOCK__SDMA: if (adev->sdma.funcs->reset_ras_error_count) @@ -921,12 +1001,14 @@ int amdgpu_ras_error_inject(struct amdgpu_device *adev, switch (info->head.block) { case AMDGPU_RAS_BLOCK__GFX: - if (adev->gfx.funcs->ras_error_inject) - ret = adev->gfx.funcs->ras_error_inject(adev, info); + if (adev->gfx.ras_funcs && + adev->gfx.ras_funcs->ras_error_inject) + ret = adev->gfx.ras_funcs->ras_error_inject(adev, info); else ret = -EINVAL; break; case AMDGPU_RAS_BLOCK__UMC: + case AMDGPU_RAS_BLOCK__SDMA: case AMDGPU_RAS_BLOCK__MMHUB: case AMDGPU_RAS_BLOCK__PCIE_BIF: ret = psp_ras_trigger_error(&adev->psp, &block_info); @@ -1191,6 +1273,8 @@ static struct dentry *amdgpu_ras_debugfs_create_ctrl_node(struct amdgpu_device * &amdgpu_ras_debugfs_ctrl_ops); debugfs_create_file("ras_eeprom_reset", S_IWUGO | S_IRUGO, dir, adev, &amdgpu_ras_debugfs_eeprom_ops); + debugfs_create_u32("bad_page_cnt_threshold", 0444, dir, + &con->bad_page_cnt_threshold); /* * After one uncorrectable error happens, usually GPU recovery will @@ -1508,12 +1592,14 @@ static void amdgpu_ras_error_status_query(struct amdgpu_device *adev, */ switch (info->head.block) { case AMDGPU_RAS_BLOCK__GFX: - if (adev->gfx.funcs->query_ras_error_status) - adev->gfx.funcs->query_ras_error_status(adev); + if (adev->gfx.ras_funcs && + adev->gfx.ras_funcs->query_ras_error_status) + adev->gfx.ras_funcs->query_ras_error_status(adev); break; case AMDGPU_RAS_BLOCK__MMHUB: - if (adev->mmhub.funcs->query_ras_error_status) - adev->mmhub.funcs->query_ras_error_status(adev); + if (adev->mmhub.ras_funcs && + adev->mmhub.ras_funcs->query_ras_error_status) + adev->mmhub.ras_funcs->query_ras_error_status(adev); break; default: break; @@ -1933,15 +2019,13 @@ int amdgpu_ras_request_reset_on_boot(struct amdgpu_device *adev, return 0; } -static int amdgpu_ras_check_asic_type(struct amdgpu_device *adev) +static bool amdgpu_ras_asic_supported(struct amdgpu_device *adev) { - if (adev->asic_type != CHIP_VEGA10 && - adev->asic_type != CHIP_VEGA20 && - adev->asic_type != CHIP_ARCTURUS && - adev->asic_type != CHIP_SIENNA_CICHLID) - return 1; - else - return 0; + return adev->asic_type == CHIP_VEGA10 || + adev->asic_type == CHIP_VEGA20 || + adev->asic_type == CHIP_ARCTURUS || + adev->asic_type == CHIP_ALDEBARAN || + adev->asic_type == CHIP_SIENNA_CICHLID; } /* @@ -1960,22 +2044,32 @@ static void amdgpu_ras_check_supported(struct amdgpu_device *adev, *supported = 0; if (amdgpu_sriov_vf(adev) || !adev->is_atom_fw || - amdgpu_ras_check_asic_type(adev)) + !amdgpu_ras_asic_supported(adev)) return; - if (amdgpu_atomfirmware_mem_ecc_supported(adev)) { - dev_info(adev->dev, "MEM ECC is active.\n"); - *hw_supported |= (1 << AMDGPU_RAS_BLOCK__UMC | - 1 << AMDGPU_RAS_BLOCK__DF); - } else - dev_info(adev->dev, "MEM ECC is not presented.\n"); + if (!adev->gmc.xgmi.connected_to_cpu) { + if (amdgpu_atomfirmware_mem_ecc_supported(adev)) { + dev_info(adev->dev, "MEM ECC is active.\n"); + *hw_supported |= (1 << AMDGPU_RAS_BLOCK__UMC | + 1 << AMDGPU_RAS_BLOCK__DF); + } else { + dev_info(adev->dev, "MEM ECC is not presented.\n"); + } - if (amdgpu_atomfirmware_sram_ecc_supported(adev)) { - dev_info(adev->dev, "SRAM ECC is active.\n"); - *hw_supported |= ~(1 << AMDGPU_RAS_BLOCK__UMC | - 1 << AMDGPU_RAS_BLOCK__DF); - } else - dev_info(adev->dev, "SRAM ECC is not presented.\n"); + if (amdgpu_atomfirmware_sram_ecc_supported(adev)) { + dev_info(adev->dev, "SRAM ECC is active.\n"); + *hw_supported |= ~(1 << AMDGPU_RAS_BLOCK__UMC | + 1 << AMDGPU_RAS_BLOCK__DF); + } else { + dev_info(adev->dev, "SRAM ECC is not presented.\n"); + } + } else { + /* driver only manages a few IP blocks RAS feature + * when GPU is connected cpu through XGMI */ + *hw_supported |= (1 << AMDGPU_RAS_BLOCK__GFX | + 1 << AMDGPU_RAS_BLOCK__SDMA | + 1 << AMDGPU_RAS_BLOCK__MMHUB); + } /* hw_supported needs to be aligned with RAS block mask. */ *hw_supported &= AMDGPU_RAS_BLOCK_MASK; @@ -2024,14 +2118,31 @@ int amdgpu_ras_init(struct amdgpu_device *adev) /* Might need get this flag from vbios. */ con->flags = RAS_DEFAULT_FLAGS; - if (adev->nbio.funcs->init_ras_controller_interrupt) { - r = adev->nbio.funcs->init_ras_controller_interrupt(adev); + /* initialize nbio ras function ahead of any other + * ras functions so hardware fatal error interrupt + * can be enabled as early as possible */ + switch (adev->asic_type) { + case CHIP_VEGA20: + case CHIP_ARCTURUS: + case CHIP_ALDEBARAN: + if (!adev->gmc.xgmi.connected_to_cpu) + adev->nbio.ras_funcs = &nbio_v7_4_ras_funcs; + break; + default: + /* nbio ras is not available */ + break; + } + + if (adev->nbio.ras_funcs && + adev->nbio.ras_funcs->init_ras_controller_interrupt) { + r = adev->nbio.ras_funcs->init_ras_controller_interrupt(adev); if (r) goto release_con; } - if (adev->nbio.funcs->init_ras_err_event_athub_interrupt) { - r = adev->nbio.funcs->init_ras_err_event_athub_interrupt(adev); + if (adev->nbio.ras_funcs && + adev->nbio.ras_funcs->init_ras_err_event_athub_interrupt) { + r = adev->nbio.ras_funcs->init_ras_err_event_athub_interrupt(adev); if (r) goto release_con; } @@ -2052,6 +2163,32 @@ release_con: return r; } +static int amdgpu_persistent_edc_harvesting_supported(struct amdgpu_device *adev) +{ + if (adev->gmc.xgmi.connected_to_cpu) + return 1; + return 0; +} + +static int amdgpu_persistent_edc_harvesting(struct amdgpu_device *adev, + struct ras_common_if *ras_block) +{ + struct ras_query_if info = { + .head = *ras_block, + }; + + if (!amdgpu_persistent_edc_harvesting_supported(adev)) + return 0; + + if (amdgpu_ras_query_error_status(adev, &info) != 0) + DRM_WARN("RAS init harvest failure"); + + if (amdgpu_ras_reset_error_status(adev, ras_block->block) != 0) + DRM_WARN("RAS init harvest reset failure"); + + return 0; +} + /* helper function to handle common stuff in ip late init phase */ int amdgpu_ras_late_init(struct amdgpu_device *adev, struct ras_common_if *ras_block, @@ -2081,6 +2218,9 @@ int amdgpu_ras_late_init(struct amdgpu_device *adev, return r; } + /* check for errors on warm reset edc persisant supported ASIC */ + amdgpu_persistent_edc_harvesting(adev, ras_block); + /* in resume phase, no need to create ras fs node */ if (adev->in_suspend || amdgpu_in_reset(adev)) return 0; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c index a05dbbbd9803..f40c871da0c6 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c @@ -31,6 +31,7 @@ #define EEPROM_I2C_TARGET_ADDR_ARCTURUS 0xA8 #define EEPROM_I2C_TARGET_ADDR_ARCTURUS_D342 0xA0 #define EEPROM_I2C_TARGET_ADDR_SIENNA_CICHLID 0xA0 +#define EEPROM_I2C_TARGET_ADDR_ALDEBARAN 0xA0 /* * The 2 macros bellow represent the actual size in bytes that @@ -64,7 +65,8 @@ static bool __is_ras_eeprom_supported(struct amdgpu_device *adev) { if ((adev->asic_type == CHIP_VEGA20) || (adev->asic_type == CHIP_ARCTURUS) || - (adev->asic_type == CHIP_SIENNA_CICHLID)) + (adev->asic_type == CHIP_SIENNA_CICHLID) || + (adev->asic_type == CHIP_ALDEBARAN)) return true; return false; @@ -106,6 +108,10 @@ static bool __get_eeprom_i2c_addr(struct amdgpu_device *adev, *i2c_addr = EEPROM_I2C_TARGET_ADDR_SIENNA_CICHLID; break; + case CHIP_ALDEBARAN: + *i2c_addr = EEPROM_I2C_TARGET_ADDR_ALDEBARAN; + break; + default: return false; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_res_cursor.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_res_cursor.h index b49a61d07d60..40f2adf305bc 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_res_cursor.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_res_cursor.h @@ -64,7 +64,7 @@ static inline void amdgpu_res_first(struct ttm_resource *res, BUG_ON(start + size > res->num_pages << PAGE_SHIFT); node = res->mm_node; - while (start > node->size << PAGE_SHIFT) + while (start >= node->size << PAGE_SHIFT) start -= node++->size << PAGE_SHIFT; cur->start = (node->start << PAGE_SHIFT) + start; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.c new file mode 100644 index 000000000000..02afd4115675 --- /dev/null +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.c @@ -0,0 +1,98 @@ +/* + * Copyright 2021 Advanced Micro Devices, Inc. + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR + * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, + * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR + * OTHER DEALINGS IN THE SOFTWARE. + * + */ + +#include "amdgpu_reset.h" +#include "aldebaran.h" + +int amdgpu_reset_add_handler(struct amdgpu_reset_control *reset_ctl, + struct amdgpu_reset_handler *handler) +{ + /* TODO: Check if handler exists? */ + list_add_tail(&handler->handler_list, &reset_ctl->reset_handlers); + return 0; +} + +int amdgpu_reset_init(struct amdgpu_device *adev) +{ + int ret = 0; + + switch (adev->asic_type) { + case CHIP_ALDEBARAN: + ret = aldebaran_reset_init(adev); + break; + default: + break; + } + + return ret; +} + +int amdgpu_reset_fini(struct amdgpu_device *adev) +{ + int ret = 0; + + switch (adev->asic_type) { + case CHIP_ALDEBARAN: + ret = aldebaran_reset_fini(adev); + break; + default: + break; + } + + return ret; +} + +int amdgpu_reset_prepare_hwcontext(struct amdgpu_device *adev, + struct amdgpu_reset_context *reset_context) +{ + struct amdgpu_reset_handler *reset_handler = NULL; + + if (adev->reset_cntl && adev->reset_cntl->get_reset_handler) + reset_handler = adev->reset_cntl->get_reset_handler( + adev->reset_cntl, reset_context); + if (!reset_handler) + return -ENOSYS; + + return reset_handler->prepare_hwcontext(adev->reset_cntl, + reset_context); +} + +int amdgpu_reset_perform_reset(struct amdgpu_device *adev, + struct amdgpu_reset_context *reset_context) +{ + int ret; + struct amdgpu_reset_handler *reset_handler = NULL; + + if (adev->reset_cntl) + reset_handler = adev->reset_cntl->get_reset_handler( + adev->reset_cntl, reset_context); + if (!reset_handler) + return -ENOSYS; + + ret = reset_handler->perform_reset(adev->reset_cntl, reset_context); + if (ret) + return ret; + + return reset_handler->restore_hwcontext(adev->reset_cntl, + reset_context); +} diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.h new file mode 100644 index 000000000000..e00d38d9160a --- /dev/null +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.h @@ -0,0 +1,85 @@ +/* + * Copyright 2021 Advanced Micro Devices, Inc. + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR + * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, + * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR + * OTHER DEALINGS IN THE SOFTWARE. + * + */ + +#ifndef __AMDGPU_RESET_H__ +#define __AMDGPU_RESET_H__ + +#include "amdgpu.h" + +enum AMDGPU_RESET_FLAGS { + + AMDGPU_NEED_FULL_RESET = 0, + AMDGPU_SKIP_HW_RESET = 1, +}; + +struct amdgpu_reset_context { + enum amd_reset_method method; + struct amdgpu_device *reset_req_dev; + struct amdgpu_job *job; + struct amdgpu_hive_info *hive; + unsigned long flags; +}; + +struct amdgpu_reset_handler { + enum amd_reset_method reset_method; + struct list_head handler_list; + int (*prepare_env)(struct amdgpu_reset_control *reset_ctl, + struct amdgpu_reset_context *context); + int (*prepare_hwcontext)(struct amdgpu_reset_control *reset_ctl, + struct amdgpu_reset_context *context); + int (*perform_reset)(struct amdgpu_reset_control *reset_ctl, + struct amdgpu_reset_context *context); + int (*restore_hwcontext)(struct amdgpu_reset_control *reset_ctl, + struct amdgpu_reset_context *context); + int (*restore_env)(struct amdgpu_reset_control *reset_ctl, + struct amdgpu_reset_context *context); + + int (*do_reset)(struct amdgpu_device *adev); +}; + +struct amdgpu_reset_control { + void *handle; + struct work_struct reset_work; + struct mutex reset_lock; + struct list_head reset_handlers; + atomic_t in_reset; + enum amd_reset_method active_reset; + struct amdgpu_reset_handler *(*get_reset_handler)( + struct amdgpu_reset_control *reset_ctl, + struct amdgpu_reset_context *context); + void (*async_reset)(struct work_struct *work); +}; + +int amdgpu_reset_init(struct amdgpu_device *adev); +int amdgpu_reset_fini(struct amdgpu_device *adev); + +int amdgpu_reset_prepare_hwcontext(struct amdgpu_device *adev, + struct amdgpu_reset_context *reset_context); + +int amdgpu_reset_perform_reset(struct amdgpu_device *adev, + struct amdgpu_reset_context *reset_context); + +int amdgpu_reset_add_handler(struct amdgpu_reset_control *reset_ctl, + struct amdgpu_reset_handler *handler); + +#endif diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c index b644c78475fd..688624ebe421 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c @@ -164,7 +164,8 @@ void amdgpu_ring_undo(struct amdgpu_ring *ring) */ int amdgpu_ring_init(struct amdgpu_device *adev, struct amdgpu_ring *ring, unsigned int max_dw, struct amdgpu_irq_src *irq_src, - unsigned int irq_type, unsigned int hw_prio) + unsigned int irq_type, unsigned int hw_prio, + atomic_t *sched_score) { int r; int sched_hw_submission = amdgpu_sched_hw_submission; @@ -189,7 +190,8 @@ int amdgpu_ring_init(struct amdgpu_device *adev, struct amdgpu_ring *ring, ring->adev = adev; ring->idx = adev->num_rings++; adev->rings[ring->idx] = ring; - r = amdgpu_fence_driver_init_ring(ring, sched_hw_submission); + r = amdgpu_fence_driver_init_ring(ring, sched_hw_submission, + sched_score); if (r) return r; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h index 56acec1075ac..ca1622835296 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h @@ -111,7 +111,8 @@ void amdgpu_fence_driver_fini(struct amdgpu_device *adev); void amdgpu_fence_driver_force_completion(struct amdgpu_ring *ring); int amdgpu_fence_driver_init_ring(struct amdgpu_ring *ring, - unsigned num_hw_submission); + unsigned num_hw_submission, + atomic_t *sched_score); int amdgpu_fence_driver_start_ring(struct amdgpu_ring *ring, struct amdgpu_irq_src *irq_src, unsigned irq_type); @@ -282,7 +283,8 @@ void amdgpu_ring_commit(struct amdgpu_ring *ring); void amdgpu_ring_undo(struct amdgpu_ring *ring); int amdgpu_ring_init(struct amdgpu_device *adev, struct amdgpu_ring *ring, unsigned int ring_size, struct amdgpu_irq_src *irq_src, - unsigned int irq_type, unsigned int prio); + unsigned int irq_type, unsigned int prio, + atomic_t *sched_score); void amdgpu_ring_fini(struct amdgpu_ring *ring); void amdgpu_ring_emit_reg_write_reg_wait_helper(struct amdgpu_ring *ring, uint32_t reg0, uint32_t val0, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.h index aeaaae713c59..4fc2ce8ce8ab 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.h @@ -127,7 +127,8 @@ struct amdgpu_rlc_funcs { void (*reset)(struct amdgpu_device *adev); void (*start)(struct amdgpu_device *adev); void (*update_spm_vmid)(struct amdgpu_device *adev, unsigned vmid); - void (*rlcg_wreg)(struct amdgpu_device *adev, u32 offset, u32 v); + void (*rlcg_wreg)(struct amdgpu_device *adev, u32 offset, u32 v, u32 flag); + u32 (*rlcg_rreg)(struct amdgpu_device *adev, u32 offset, u32 flag); bool (*is_rlcg_access_range)(struct amdgpu_device *adev, uint32_t reg); }; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_securedisplay.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_securedisplay.c index 9cf856c94f94..5369c8dd0764 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_securedisplay.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_securedisplay.c @@ -95,9 +95,7 @@ static ssize_t amdgpu_securedisplay_debugfs_write(struct file *f, const char __u struct drm_device *dev = adev_to_drm(adev); uint32_t phy_id; uint32_t op; - int i; char str[64]; - char i2c_output[256]; int ret; if (*pos || size > sizeof(str) - 1) @@ -139,11 +137,9 @@ static ssize_t amdgpu_securedisplay_debugfs_write(struct file *f, const char __u ret = psp_securedisplay_invoke(psp, TA_SECUREDISPLAY_COMMAND__SEND_ROI_CRC); if (!ret) { if (securedisplay_cmd->status == TA_SECUREDISPLAY_STATUS__SUCCESS) { - memset(i2c_output, 0, sizeof(i2c_output)); - for (i = 0; i < TA_SECUREDISPLAY_I2C_BUFFER_SIZE; i++) - sprintf(i2c_output, "%s 0x%X", i2c_output, - securedisplay_cmd->securedisplay_out_message.send_roi_crc.i2c_buf[i]); - dev_info(adev->dev, "SECUREDISPLAY: I2C buffer out put is :%s\n", i2c_output); + dev_info(adev->dev, "SECUREDISPLAY: I2C buffer out put is: %*ph\n", + TA_SECUREDISPLAY_I2C_BUFFER_SIZE, + securedisplay_cmd->securedisplay_out_message.send_roi_crc.i2c_buf); } else { psp_securedisplay_parse_resp_status(psp, securedisplay_cmd->status); } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_test.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_test.c index 7b230bcbf2c6..909d830b513e 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_test.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_test.c @@ -62,6 +62,7 @@ static void amdgpu_do_test_moves(struct amdgpu_device *adev) bp.flags = 0; bp.type = ttm_bo_type_kernel; bp.resv = NULL; + bp.bo_ptr_size = sizeof(struct amdgpu_bo); r = amdgpu_bo_create(adev, &bp, &vram_obj); if (r) { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index 1c6131489a85..3bef0432cac2 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -823,15 +823,14 @@ static int amdgpu_ttm_tt_pin_userptr(struct ttm_device *bdev, { struct amdgpu_device *adev = amdgpu_ttm_adev(bdev); struct amdgpu_ttm_tt *gtt = (void *)ttm; - int r; - int write = !(gtt->userflags & AMDGPU_GEM_USERPTR_READONLY); enum dma_data_direction direction = write ? DMA_BIDIRECTIONAL : DMA_TO_DEVICE; + int r; /* Allocate an SG array and squash pages into it */ r = sg_alloc_table_from_pages(ttm->sg, ttm->pages, ttm->num_pages, 0, - ttm->num_pages << PAGE_SHIFT, + (u64)ttm->num_pages << PAGE_SHIFT, GFP_KERNEL); if (r) goto release_sg; @@ -861,13 +860,12 @@ static void amdgpu_ttm_tt_unpin_userptr(struct ttm_device *bdev, { struct amdgpu_device *adev = amdgpu_ttm_adev(bdev); struct amdgpu_ttm_tt *gtt = (void *)ttm; - int write = !(gtt->userflags & AMDGPU_GEM_USERPTR_READONLY); enum dma_data_direction direction = write ? DMA_BIDIRECTIONAL : DMA_TO_DEVICE; /* double check that we don't free the table twice */ - if (!ttm->sg->sgl) + if (!ttm->sg || !ttm->sg->sgl) return; /* unmap the pages mapped to the device */ @@ -1087,13 +1085,13 @@ static void amdgpu_ttm_backend_unbind(struct ttm_device *bdev, struct amdgpu_ttm_tt *gtt = (void *)ttm; int r; - if (!gtt->bound) - return; - /* if the pages have userptr pinning then clear that first */ if (gtt->userptr) amdgpu_ttm_tt_unpin_userptr(bdev, ttm); + if (!gtt->bound) + return; + if (gtt->offset == AMDGPU_BO_INVALID_OFFSET) return; @@ -1503,7 +1501,7 @@ static int amdgpu_ttm_access_memory(struct ttm_buffer_object *bo, memcpy(buf, &value, bytes); } } else { - bytes = cursor.size & 0x3ull; + bytes = cursor.size & ~0x3ULL; amdgpu_device_vram_access(adev, cursor.start, (uint32_t *)buf, bytes, write); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h index dec0db8b0b13..9e38475e0f8d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h @@ -112,6 +112,7 @@ int amdgpu_gtt_mgr_recover(struct ttm_resource_manager *man); u64 amdgpu_vram_mgr_bo_visible_size(struct amdgpu_bo *bo); int amdgpu_vram_mgr_alloc_sgt(struct amdgpu_device *adev, struct ttm_resource *mem, + u64 offset, u64 size, struct device *dev, enum dma_data_direction dir, struct sg_table **sgt); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c index a2975c8092a9..ea6f99be070b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c @@ -60,8 +60,9 @@ int amdgpu_umc_ras_late_init(struct amdgpu_device *adev) } /* ras init of specific umc version */ - if (adev->umc.funcs && adev->umc.funcs->err_cnt_init) - adev->umc.funcs->err_cnt_init(adev); + if (adev->umc.ras_funcs && + adev->umc.ras_funcs->err_cnt_init) + adev->umc.ras_funcs->err_cnt_init(adev); return 0; @@ -95,12 +96,12 @@ int amdgpu_umc_process_ras_data_cb(struct amdgpu_device *adev, struct ras_err_data *err_data = (struct ras_err_data *)ras_error_status; kgd2kfd_set_sram_ecc_flag(adev->kfd.dev); - if (adev->umc.funcs && - adev->umc.funcs->query_ras_error_count) - adev->umc.funcs->query_ras_error_count(adev, ras_error_status); + if (adev->umc.ras_funcs && + adev->umc.ras_funcs->query_ras_error_count) + adev->umc.ras_funcs->query_ras_error_count(adev, ras_error_status); - if (adev->umc.funcs && - adev->umc.funcs->query_ras_error_address && + if (adev->umc.ras_funcs && + adev->umc.ras_funcs->query_ras_error_address && adev->umc.max_ras_err_cnt_per_query) { err_data->err_addr = kcalloc(adev->umc.max_ras_err_cnt_per_query, @@ -116,7 +117,7 @@ int amdgpu_umc_process_ras_data_cb(struct amdgpu_device *adev, /* umc query_ras_error_address is also responsible for clearing * error status */ - adev->umc.funcs->query_ras_error_address(adev, ras_error_status); + adev->umc.ras_funcs->query_ras_error_address(adev, ras_error_status); } /* only uncorrectable error needs gpu reset */ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.h index 183814493658..bbcccf53080d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.h @@ -35,13 +35,17 @@ #define LOOP_UMC_CH_INST(ch_inst) for ((ch_inst) = 0; (ch_inst) < adev->umc.channel_inst_num; (ch_inst)++) #define LOOP_UMC_INST_AND_CH(umc_inst, ch_inst) LOOP_UMC_INST((umc_inst)) LOOP_UMC_CH_INST((ch_inst)) -struct amdgpu_umc_funcs { +struct amdgpu_umc_ras_funcs { void (*err_cnt_init)(struct amdgpu_device *adev); int (*ras_late_init)(struct amdgpu_device *adev); + void (*ras_fini)(struct amdgpu_device *adev); void (*query_ras_error_count)(struct amdgpu_device *adev, - void *ras_error_status); + void *ras_error_status); void (*query_ras_error_address)(struct amdgpu_device *adev, void *ras_error_status); +}; + +struct amdgpu_umc_funcs { void (*init_registers)(struct amdgpu_device *adev); }; @@ -59,6 +63,7 @@ struct amdgpu_umc { struct ras_common_if *ras_if; const struct amdgpu_umc_funcs *funcs; + const struct amdgpu_umc_ras_funcs *ras_funcs; }; int amdgpu_umc_ras_late_init(struct amdgpu_device *adev); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c index e2ed4689118a..c6dbc0801604 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c @@ -259,7 +259,7 @@ int amdgpu_uvd_sw_init(struct amdgpu_device *adev) if ((adev->asic_type == CHIP_POLARIS10 || adev->asic_type == CHIP_POLARIS11) && (adev->uvd.fw_version < FW_1_66_16)) - DRM_ERROR("POLARIS10/11 UVD firmware version %hu.%hu is too old.\n", + DRM_ERROR("POLARIS10/11 UVD firmware version %u.%u is too old.\n", version_major, version_minor); } else { unsigned int enc_major, enc_minor, dec_minor; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h index 1843bf8de0cf..bc76cab67697 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h @@ -212,6 +212,7 @@ struct amdgpu_vcn_inst { void *saved_bo; struct amdgpu_ring ring_dec; struct amdgpu_ring ring_enc[AMDGPU_VCN_MAX_ENC_RINGS]; + atomic_t sched_score; struct amdgpu_irq_src irq; struct amdgpu_vcn_reg external; struct amdgpu_bo *dpg_sram_bo; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c index d9ffff8eb41d..0c9c5255aa42 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c @@ -466,6 +466,8 @@ static int amdgpu_virt_read_pf2vf_data(struct amdgpu_device *adev) ((struct amd_sriov_msg_pf2vf_info *)pf2vf_info)->vf2pf_update_interval_ms; adev->virt.gim_feature = ((struct amd_sriov_msg_pf2vf_info *)pf2vf_info)->feature_flags.all; + adev->virt.reg_access = + ((struct amd_sriov_msg_pf2vf_info *)pf2vf_info)->reg_access_flags.all; break; default: @@ -617,6 +619,14 @@ void amdgpu_virt_init_data_exchange(struct amdgpu_device *adev) if (adev->virt.ras_init_done) amdgpu_virt_add_bad_page(adev, bp_block_offset, bp_block_size); } + } else if (adev->bios != NULL) { + adev->virt.fw_reserve.p_pf2vf = + (struct amd_sriov_msg_pf2vf_info_header *) + (adev->bios + (AMD_SRIOV_MSG_PF2VF_OFFSET_KB << 10)); + + amdgpu_virt_read_pf2vf_data(adev); + + return; } if (adev->virt.vf2pf_update_interval_ms != 0) { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h index 8dd624c20f89..383d4bdc3fb5 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h @@ -104,6 +104,17 @@ enum AMDGIM_FEATURE_FLAG { AMDGIM_FEATURE_GIM_MM_BW_MGR = 0x8, /* PP ONE VF MODE in GIM */ AMDGIM_FEATURE_PP_ONE_VF = (1 << 4), + /* Indirect Reg Access enabled */ + AMDGIM_FEATURE_INDIRECT_REG_ACCESS = (1 << 5), +}; + +enum AMDGIM_REG_ACCESS_FLAG { + /* Use PSP to program IH_RB_CNTL */ + AMDGIM_FEATURE_IH_REG_PSP_EN = (1 << 0), + /* Use RLC to program MMHUB regs */ + AMDGIM_FEATURE_MMHUB_REG_RLC_EN = (1 << 1), + /* Use RLC to program GC regs */ + AMDGIM_FEATURE_GC_REG_RLC_EN = (1 << 2), }; struct amdgim_pf2vf_info_v1 { @@ -217,6 +228,7 @@ struct amdgpu_virt { bool tdr_debug; struct amdgpu_virt_ras_err_handler_data *virt_eh_data; bool ras_init_done; + uint32_t reg_access; /* vf2pf message */ struct delayed_work vf2pf_work; @@ -238,6 +250,22 @@ struct amdgpu_virt { #define amdgpu_sriov_fullaccess(adev) \ (amdgpu_sriov_vf((adev)) && !amdgpu_sriov_runtime((adev))) +#define amdgpu_sriov_reg_indirect_en(adev) \ +(amdgpu_sriov_vf((adev)) && \ + ((adev)->virt.gim_feature & (AMDGIM_FEATURE_INDIRECT_REG_ACCESS))) + +#define amdgpu_sriov_reg_indirect_ih(adev) \ +(amdgpu_sriov_vf((adev)) && \ + ((adev)->virt.reg_access & (AMDGIM_FEATURE_IH_REG_PSP_EN))) + +#define amdgpu_sriov_reg_indirect_mmhub(adev) \ +(amdgpu_sriov_vf((adev)) && \ + ((adev)->virt.reg_access & (AMDGIM_FEATURE_MMHUB_REG_RLC_EN))) + +#define amdgpu_sriov_reg_indirect_gc(adev) \ +(amdgpu_sriov_vf((adev)) && \ + ((adev)->virt.reg_access & (AMDGIM_FEATURE_GC_REG_RLC_EN))) + #define amdgpu_passthrough(adev) \ ((adev)->virt.caps & AMDGPU_PASSTHROUGH_MODE) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index f314e1e269cd..0ffdf847cad0 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -869,6 +869,7 @@ static void amdgpu_vm_bo_param(struct amdgpu_device *adev, struct amdgpu_vm *vm, bp->domain = amdgpu_bo_get_preferred_pin_domain(adev, bp->domain); bp->flags = AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS | AMDGPU_GEM_CREATE_CPU_GTT_USWC; + bp->bo_ptr_size = sizeof(struct amdgpu_bo); if (vm->use_cpu_for_update) bp->flags |= AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED; else if (!vm->root.base.bo || vm->root.base.bo->shadow) @@ -2197,8 +2198,8 @@ int amdgpu_vm_bo_map(struct amdgpu_device *adev, uint64_t eaddr; /* validate the parameters */ - if (saddr & AMDGPU_GPU_PAGE_MASK || offset & AMDGPU_GPU_PAGE_MASK || - size == 0 || size & AMDGPU_GPU_PAGE_MASK) + if (saddr & ~PAGE_MASK || offset & ~PAGE_MASK || + size == 0 || size & ~PAGE_MASK) return -EINVAL; /* make sure object fit at this offset */ @@ -2263,8 +2264,8 @@ int amdgpu_vm_bo_replace_map(struct amdgpu_device *adev, int r; /* validate the parameters */ - if (saddr & AMDGPU_GPU_PAGE_MASK || offset & AMDGPU_GPU_PAGE_MASK || - size == 0 || size & AMDGPU_GPU_PAGE_MASK) + if (saddr & ~PAGE_MASK || offset & ~PAGE_MASK || + size == 0 || size & ~PAGE_MASK) return -EINVAL; /* make sure object fit at this offset */ @@ -2409,7 +2410,7 @@ int amdgpu_vm_bo_clear_mappings(struct amdgpu_device *adev, after->start = eaddr + 1; after->last = tmp->last; after->offset = tmp->offset; - after->offset += after->start - tmp->start; + after->offset += (after->start - tmp->start) << PAGE_SHIFT; after->flags = tmp->flags; after->bo_va = tmp->bo_va; list_add(&after->list, &tmp->bo_va->invalids); @@ -3300,7 +3301,7 @@ bool amdgpu_vm_handle_fault(struct amdgpu_device *adev, u32 pasid, struct amdgpu_bo *root; uint64_t value, flags; struct amdgpu_vm *vm; - long r; + int r; spin_lock(&adev->vm_manager.pasid_lock); vm = idr_find(&adev->vm_manager.pasid_idr, pasid); @@ -3349,6 +3350,12 @@ bool amdgpu_vm_handle_fault(struct amdgpu_device *adev, u32 pasid, value = 0; } + r = dma_resv_reserve_shared(root->tbo.base.resv, 1); + if (r) { + pr_debug("failed %d to reserve fence slot\n", r); + goto error_unlock; + } + r = amdgpu_vm_bo_update_mapping(adev, adev, vm, true, false, NULL, addr, addr, flags, value, NULL, NULL, NULL); @@ -3360,7 +3367,7 @@ bool amdgpu_vm_handle_fault(struct amdgpu_device *adev, u32 pasid, error_unlock: amdgpu_bo_unreserve(root); if (r < 0) - DRM_ERROR("Can't handle page fault (%ld)\n", r); + DRM_ERROR("Can't handle page fault (%d)\n", r); error_unref: amdgpu_bo_unref(&root); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c index b2fc475ce6f7..bce105e2973e 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c @@ -25,6 +25,7 @@ #include <linux/dma-mapping.h> #include "amdgpu.h" #include "amdgpu_vm.h" +#include "amdgpu_res_cursor.h" #include "amdgpu_atomfirmware.h" #include "atom.h" @@ -52,7 +53,7 @@ static ssize_t amdgpu_mem_info_vram_total_show(struct device *dev, struct drm_device *ddev = dev_get_drvdata(dev); struct amdgpu_device *adev = drm_to_adev(ddev); - return snprintf(buf, PAGE_SIZE, "%llu\n", adev->gmc.real_vram_size); + return sysfs_emit(buf, "%llu\n", adev->gmc.real_vram_size); } /** @@ -69,7 +70,7 @@ static ssize_t amdgpu_mem_info_vis_vram_total_show(struct device *dev, struct drm_device *ddev = dev_get_drvdata(dev); struct amdgpu_device *adev = drm_to_adev(ddev); - return snprintf(buf, PAGE_SIZE, "%llu\n", adev->gmc.visible_vram_size); + return sysfs_emit(buf, "%llu\n", adev->gmc.visible_vram_size); } /** @@ -87,8 +88,7 @@ static ssize_t amdgpu_mem_info_vram_used_show(struct device *dev, struct amdgpu_device *adev = drm_to_adev(ddev); struct ttm_resource_manager *man = ttm_manager_type(&adev->mman.bdev, TTM_PL_VRAM); - return snprintf(buf, PAGE_SIZE, "%llu\n", - amdgpu_vram_mgr_usage(man)); + return sysfs_emit(buf, "%llu\n", amdgpu_vram_mgr_usage(man)); } /** @@ -106,8 +106,7 @@ static ssize_t amdgpu_mem_info_vis_vram_used_show(struct device *dev, struct amdgpu_device *adev = drm_to_adev(ddev); struct ttm_resource_manager *man = ttm_manager_type(&adev->mman.bdev, TTM_PL_VRAM); - return snprintf(buf, PAGE_SIZE, "%llu\n", - amdgpu_vram_mgr_vis_usage(man)); + return sysfs_emit(buf, "%llu\n", amdgpu_vram_mgr_vis_usage(man)); } static ssize_t amdgpu_mem_info_vram_vendor(struct device *dev, @@ -119,27 +118,27 @@ static ssize_t amdgpu_mem_info_vram_vendor(struct device *dev, switch (adev->gmc.vram_vendor) { case SAMSUNG: - return snprintf(buf, PAGE_SIZE, "samsung\n"); + return sysfs_emit(buf, "samsung\n"); case INFINEON: - return snprintf(buf, PAGE_SIZE, "infineon\n"); + return sysfs_emit(buf, "infineon\n"); case ELPIDA: - return snprintf(buf, PAGE_SIZE, "elpida\n"); + return sysfs_emit(buf, "elpida\n"); case ETRON: - return snprintf(buf, PAGE_SIZE, "etron\n"); + return sysfs_emit(buf, "etron\n"); case NANYA: - return snprintf(buf, PAGE_SIZE, "nanya\n"); + return sysfs_emit(buf, "nanya\n"); case HYNIX: - return snprintf(buf, PAGE_SIZE, "hynix\n"); + return sysfs_emit(buf, "hynix\n"); case MOSEL: - return snprintf(buf, PAGE_SIZE, "mosel\n"); + return sysfs_emit(buf, "mosel\n"); case WINBOND: - return snprintf(buf, PAGE_SIZE, "winbond\n"); + return sysfs_emit(buf, "winbond\n"); case ESMT: - return snprintf(buf, PAGE_SIZE, "esmt\n"); + return sysfs_emit(buf, "esmt\n"); case MICRON: - return snprintf(buf, PAGE_SIZE, "micron\n"); + return sysfs_emit(buf, "micron\n"); default: - return snprintf(buf, PAGE_SIZE, "unknown\n"); + return sysfs_emit(buf, "unknown\n"); } } @@ -567,6 +566,8 @@ static void amdgpu_vram_mgr_del(struct ttm_resource_manager *man, * * @adev: amdgpu device pointer * @mem: TTM memory object + * @offset: byte offset from the base of VRAM BO + * @length: number of bytes to export in sg_table * @dev: the other device * @dir: dma direction * @sgt: resulting sg table @@ -575,39 +576,47 @@ static void amdgpu_vram_mgr_del(struct ttm_resource_manager *man, */ int amdgpu_vram_mgr_alloc_sgt(struct amdgpu_device *adev, struct ttm_resource *mem, + u64 offset, u64 length, struct device *dev, enum dma_data_direction dir, struct sg_table **sgt) { - struct drm_mm_node *node; + struct amdgpu_res_cursor cursor; struct scatterlist *sg; int num_entries = 0; - unsigned int pages; int i, r; *sgt = kmalloc(sizeof(**sgt), GFP_KERNEL); if (!*sgt) return -ENOMEM; - for (pages = mem->num_pages, node = mem->mm_node; - pages; pages -= node->size, ++node) - ++num_entries; + /* Determine the number of DRM_MM nodes to export */ + amdgpu_res_first(mem, offset, length, &cursor); + while (cursor.remaining) { + num_entries++; + amdgpu_res_next(&cursor, cursor.size); + } r = sg_alloc_table(*sgt, num_entries, GFP_KERNEL); if (r) goto error_free; + /* Initialize scatterlist nodes of sg_table */ for_each_sgtable_sg((*sgt), sg, i) sg->length = 0; - node = mem->mm_node; + /* + * Walk down DRM_MM nodes to populate scatterlist nodes + * @note: Use iterator api to get first the DRM_MM node + * and the number of bytes from it. Access the following + * DRM_MM node(s) if more buffer needs to exported + */ + amdgpu_res_first(mem, offset, length, &cursor); for_each_sgtable_sg((*sgt), sg, i) { - phys_addr_t phys = (node->start << PAGE_SHIFT) + - adev->gmc.aper_base; - size_t size = node->size << PAGE_SHIFT; + phys_addr_t phys = cursor.start + adev->gmc.aper_base; + size_t size = cursor.size; dma_addr_t addr; - ++node; addr = dma_map_resource(dev, phys, size, dir, DMA_ATTR_SKIP_CPU_SYNC); r = dma_mapping_error(dev, addr); @@ -617,7 +626,10 @@ int amdgpu_vram_mgr_alloc_sgt(struct amdgpu_device *adev, sg_set_page(sg, NULL, size, 0); sg_dma_address(sg) = addr; sg_dma_len(sg) = size; + + amdgpu_res_next(&cursor, cursor.size); } + return 0; error_unmap: diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c index 33f748e5bbfc..8567d5d77346 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c @@ -24,7 +24,6 @@ #include <linux/list.h> #include "amdgpu.h" #include "amdgpu_xgmi.h" -#include "amdgpu_smu.h" #include "amdgpu_ras.h" #include "soc15.h" #include "df/df_3_6_offset.h" @@ -217,7 +216,7 @@ static ssize_t amdgpu_xgmi_show_device_id(struct device *dev, struct drm_device *ddev = dev_get_drvdata(dev); struct amdgpu_device *adev = drm_to_adev(ddev); - return snprintf(buf, PAGE_SIZE, "%llu\n", adev->gmc.xgmi.node_id); + return sysfs_emit(buf, "%llu\n", adev->gmc.xgmi.node_id); } @@ -246,7 +245,7 @@ static ssize_t amdgpu_xgmi_show_error(struct device *dev, adev->df.funcs->set_fica(adev, ficaa_pie_status_in, 0, 0); - return snprintf(buf, PAGE_SIZE, "%u\n", error_count); + return sysfs_emit(buf, "%u\n", error_count); } @@ -629,7 +628,7 @@ int amdgpu_xgmi_remove_device(struct amdgpu_device *adev) return psp_xgmi_terminate(&adev->psp); } -int amdgpu_xgmi_ras_late_init(struct amdgpu_device *adev) +static int amdgpu_xgmi_ras_late_init(struct amdgpu_device *adev) { int r; struct ras_ih_if ih_info = { @@ -643,7 +642,7 @@ int amdgpu_xgmi_ras_late_init(struct amdgpu_device *adev) adev->gmc.xgmi.num_physical_nodes == 0) return 0; - amdgpu_xgmi_reset_ras_error_count(adev); + adev->gmc.xgmi.ras_funcs->reset_ras_error_count(adev); if (!adev->gmc.xgmi.ras_if) { adev->gmc.xgmi.ras_if = kmalloc(sizeof(struct ras_common_if), GFP_KERNEL); @@ -665,7 +664,7 @@ int amdgpu_xgmi_ras_late_init(struct amdgpu_device *adev) return r; } -void amdgpu_xgmi_ras_fini(struct amdgpu_device *adev) +static void amdgpu_xgmi_ras_fini(struct amdgpu_device *adev) { if (amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__XGMI_WAFL) && adev->gmc.xgmi.ras_if) { @@ -692,7 +691,7 @@ static void pcs_clear_status(struct amdgpu_device *adev, uint32_t pcs_status_reg WREG32_PCIE(pcs_status_reg, 0); } -void amdgpu_xgmi_reset_ras_error_count(struct amdgpu_device *adev) +static void amdgpu_xgmi_reset_ras_error_count(struct amdgpu_device *adev) { uint32_t i; @@ -752,8 +751,8 @@ static int amdgpu_xgmi_query_pcs_error_status(struct amdgpu_device *adev, return 0; } -int amdgpu_xgmi_query_ras_error_count(struct amdgpu_device *adev, - void *ras_error_status) +static int amdgpu_xgmi_query_ras_error_count(struct amdgpu_device *adev, + void *ras_error_status) { struct ras_err_data *err_data = (struct ras_err_data *)ras_error_status; int i; @@ -802,10 +801,17 @@ int amdgpu_xgmi_query_ras_error_count(struct amdgpu_device *adev, break; } - amdgpu_xgmi_reset_ras_error_count(adev); + adev->gmc.xgmi.ras_funcs->reset_ras_error_count(adev); err_data->ue_count += ue_cnt; err_data->ce_count += ce_cnt; return 0; } + +const struct amdgpu_xgmi_ras_funcs xgmi_ras_funcs = { + .ras_late_init = amdgpu_xgmi_ras_late_init, + .ras_fini = amdgpu_xgmi_ras_fini, + .query_ras_error_count = amdgpu_xgmi_query_ras_error_count, + .reset_ras_error_count = amdgpu_xgmi_reset_ras_error_count, +}; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h index 148560d63554..12969c0830d5 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h @@ -50,6 +50,7 @@ struct amdgpu_pcs_ras_field { uint32_t pcs_err_shift; }; +extern const struct amdgpu_xgmi_ras_funcs xgmi_ras_funcs; struct amdgpu_hive_info *amdgpu_get_xgmi_hive(struct amdgpu_device *adev); void amdgpu_put_xgmi_hive(struct amdgpu_hive_info *hive); int amdgpu_xgmi_update_topology(struct amdgpu_hive_info *hive, struct amdgpu_device *adev); @@ -58,14 +59,8 @@ int amdgpu_xgmi_remove_device(struct amdgpu_device *adev); int amdgpu_xgmi_set_pstate(struct amdgpu_device *adev, int pstate); int amdgpu_xgmi_get_hops_count(struct amdgpu_device *adev, struct amdgpu_device *peer_adev); -int amdgpu_xgmi_ras_late_init(struct amdgpu_device *adev); -void amdgpu_xgmi_ras_fini(struct amdgpu_device *adev); uint64_t amdgpu_xgmi_get_relative_phy_addr(struct amdgpu_device *adev, uint64_t addr); -int amdgpu_xgmi_query_ras_error_count(struct amdgpu_device *adev, - void *ras_error_status); -void amdgpu_xgmi_reset_ras_error_count(struct amdgpu_device *adev); - static inline bool amdgpu_xgmi_same_hive(struct amdgpu_device *adev, struct amdgpu_device *bo_adev) { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgv_sriovmsg.h b/drivers/gpu/drm/amd/amdgpu/amdgv_sriovmsg.h index 5355827ed0ae..1a8f6d4baab2 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgv_sriovmsg.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgv_sriovmsg.h @@ -90,11 +90,22 @@ union amd_sriov_msg_feature_flags { uint32_t host_flr_vramlost : 1; uint32_t mm_bw_management : 1; uint32_t pp_one_vf_mode : 1; - uint32_t reserved : 27; + uint32_t reg_indirect_acc : 1; + uint32_t reserved : 26; } flags; uint32_t all; }; +union amd_sriov_reg_access_flags { + struct { + uint32_t vf_reg_access_ih : 1; + uint32_t vf_reg_access_mmhub : 1; + uint32_t vf_reg_access_gc : 1; + uint32_t reserved : 29; + } flags; + uint32_t all; +}; + union amd_sriov_msg_os_info { struct { uint32_t windows : 1; @@ -149,8 +160,10 @@ struct amd_sriov_msg_pf2vf_info { /* identification in ROCm SMI */ uint64_t uuid; uint32_t fcn_idx; + /* flags which indicate the register access method VF should use */ + union amd_sriov_reg_access_flags reg_access_flags; /* reserved */ - uint32_t reserved[256-26]; + uint32_t reserved[256-27]; }; struct amd_sriov_msg_vf2pf_info_header { diff --git a/drivers/gpu/drm/amd/amdgpu/cik_sdma.c b/drivers/gpu/drm/amd/amdgpu/cik_sdma.c index 43b978144b79..c4bb8eed246d 100644 --- a/drivers/gpu/drm/amd/amdgpu/cik_sdma.c +++ b/drivers/gpu/drm/amd/amdgpu/cik_sdma.c @@ -984,10 +984,9 @@ static int cik_sdma_sw_init(void *handle) sprintf(ring->name, "sdma%d", i); r = amdgpu_ring_init(adev, ring, 1024, &adev->sdma.trap_irq, - (i == 0) ? - AMDGPU_SDMA_IRQ_INSTANCE0 : + (i == 0) ? AMDGPU_SDMA_IRQ_INSTANCE0 : AMDGPU_SDMA_IRQ_INSTANCE1, - AMDGPU_RING_PRIO_DEFAULT); + AMDGPU_RING_PRIO_DEFAULT, NULL); if (r) return r; } diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c index ea825b4f8ee8..d1570a462a51 100644 --- a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c @@ -2896,6 +2896,11 @@ static int dce_v10_0_hw_fini(void *handle) static int dce_v10_0_suspend(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; + int r; + + r = amdgpu_display_suspend_helper(adev); + if (r) + return r; adev->mode_info.bl_level = amdgpu_atombios_encoder_get_backlight_level_from_reg(adev); @@ -2920,8 +2925,10 @@ static int dce_v10_0_resume(void *handle) amdgpu_display_backlight_set_level(adev, adev->mode_info.bl_encoder, bl_level); } + if (ret) + return ret; - return ret; + return amdgpu_display_resume_helper(adev); } static bool dce_v10_0_is_idle(void *handle) diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c index a360a6dec198..18a7b3bd633b 100644 --- a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c @@ -3026,6 +3026,11 @@ static int dce_v11_0_hw_fini(void *handle) static int dce_v11_0_suspend(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; + int r; + + r = amdgpu_display_suspend_helper(adev); + if (r) + return r; adev->mode_info.bl_level = amdgpu_atombios_encoder_get_backlight_level_from_reg(adev); @@ -3050,8 +3055,10 @@ static int dce_v11_0_resume(void *handle) amdgpu_display_backlight_set_level(adev, adev->mode_info.bl_encoder, bl_level); } + if (ret) + return ret; - return ret; + return amdgpu_display_resume_helper(adev); } static bool dce_v11_0_is_idle(void *handle) diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c index ef124ac853b6..dbcb09cf83e6 100644 --- a/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c +++ b/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c @@ -2769,7 +2769,11 @@ static int dce_v6_0_hw_fini(void *handle) static int dce_v6_0_suspend(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; + int r; + r = amdgpu_display_suspend_helper(adev); + if (r) + return r; adev->mode_info.bl_level = amdgpu_atombios_encoder_get_backlight_level_from_reg(adev); @@ -2793,8 +2797,10 @@ static int dce_v6_0_resume(void *handle) amdgpu_display_backlight_set_level(adev, adev->mode_info.bl_encoder, bl_level); } + if (ret) + return ret; - return ret; + return amdgpu_display_resume_helper(adev); } static bool dce_v6_0_is_idle(void *handle) diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c index c98650183828..b200b9e722d9 100644 --- a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c @@ -2795,6 +2795,11 @@ static int dce_v8_0_hw_fini(void *handle) static int dce_v8_0_suspend(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; + int r; + + r = amdgpu_display_suspend_helper(adev); + if (r) + return r; adev->mode_info.bl_level = amdgpu_atombios_encoder_get_backlight_level_from_reg(adev); @@ -2819,8 +2824,10 @@ static int dce_v8_0_resume(void *handle) amdgpu_display_backlight_set_level(adev, adev->mode_info.bl_encoder, bl_level); } + if (ret) + return ret; - return ret; + return amdgpu_display_resume_helper(adev); } static bool dce_v8_0_is_idle(void *handle) diff --git a/drivers/gpu/drm/amd/amdgpu/dce_virtual.c b/drivers/gpu/drm/amd/amdgpu/dce_virtual.c index 9810af712cc0..5c11144da051 100644 --- a/drivers/gpu/drm/amd/amdgpu/dce_virtual.c +++ b/drivers/gpu/drm/amd/amdgpu/dce_virtual.c @@ -39,6 +39,7 @@ #include "dce_v11_0.h" #include "dce_virtual.h" #include "ivsrcid/ivsrcid_vislands30.h" +#include "amdgpu_display.h" #define DCE_VIRTUAL_VBLANK_PERIOD 16666666 @@ -491,12 +492,24 @@ static int dce_virtual_hw_fini(void *handle) static int dce_virtual_suspend(void *handle) { + struct amdgpu_device *adev = (struct amdgpu_device *)handle; + int r; + + r = amdgpu_display_suspend_helper(adev); + if (r) + return r; return dce_virtual_hw_fini(handle); } static int dce_virtual_resume(void *handle) { - return dce_virtual_hw_init(handle); + struct amdgpu_device *adev = (struct amdgpu_device *)handle; + int r; + + r = dce_virtual_hw_init(handle); + if (r) + return r; + return amdgpu_display_resume_helper(adev); } static bool dce_virtual_is_idle(void *handle) diff --git a/drivers/gpu/drm/amd/amdgpu/df_v3_6.c b/drivers/gpu/drm/amd/amdgpu/df_v3_6.c index 44109a6b8f44..0d8459d63bac 100644 --- a/drivers/gpu/drm/amd/amdgpu/df_v3_6.c +++ b/drivers/gpu/drm/amd/amdgpu/df_v3_6.c @@ -205,7 +205,7 @@ static ssize_t df_v3_6_get_df_cntr_avail(struct device *dev, count++; } - return snprintf(buf, PAGE_SIZE, "%i\n", count); + return sysfs_emit(buf, "%i\n", count); } /* device attr for available perfmon counters */ diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c index 45d1172b7bff..2408ed4c7d84 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c @@ -29,7 +29,6 @@ #include "amdgpu.h" #include "amdgpu_gfx.h" #include "amdgpu_psp.h" -#include "amdgpu_smu.h" #include "nv.h" #include "nvd.h" @@ -174,6 +173,11 @@ #define mmGC_THROTTLE_CTRL_Sienna_Cichlid 0x2030 #define mmGC_THROTTLE_CTRL_Sienna_Cichlid_BASE_IDX 0 +#define GFX_RLCG_GC_WRITE_OLD (0x8 << 28) +#define GFX_RLCG_GC_WRITE (0x0 << 28) +#define GFX_RLCG_GC_READ (0x1 << 28) +#define GFX_RLCG_MMHUB_WRITE (0x2 << 28) + MODULE_FIRMWARE("amdgpu/navi10_ce.bin"); MODULE_FIRMWARE("amdgpu/navi10_pfp.bin"); MODULE_FIRMWARE("amdgpu/navi10_me.bin"); @@ -1419,38 +1423,127 @@ static const struct soc15_reg_golden golden_settings_gc_10_1_2[] = SOC15_REG_GOLDEN_VALUE(GC, 0, mmUTCL1_CTRL, 0xffffffff, 0x00800000) }; -static void gfx_v10_rlcg_wreg(struct amdgpu_device *adev, u32 offset, u32 v) +static bool gfx_v10_is_rlcg_rw(struct amdgpu_device *adev, u32 offset, uint32_t *flag, bool write) +{ + /* always programed by rlcg, only for gc */ + if (offset == SOC15_REG_OFFSET(GC, 0, mmRLC_CSIB_ADDR_HI) || + offset == SOC15_REG_OFFSET(GC, 0, mmRLC_CSIB_ADDR_LO) || + offset == SOC15_REG_OFFSET(GC, 0, mmRLC_CSIB_LENGTH) || + offset == SOC15_REG_OFFSET(GC, 0, mmGRBM_GFX_CNTL) || + offset == SOC15_REG_OFFSET(GC, 0, mmGRBM_GFX_INDEX) || + offset == SOC15_REG_OFFSET(GC, 0, mmCP_ME_CNTL)) { + if (!amdgpu_sriov_reg_indirect_gc(adev)) + *flag = GFX_RLCG_GC_WRITE_OLD; + else + *flag = write ? GFX_RLCG_GC_WRITE : GFX_RLCG_GC_READ; + + return true; + } + + /* currently support gc read/write, mmhub write */ + if (offset >= SOC15_REG_OFFSET(GC, 0, mmSDMA0_DEC_START) && + offset <= SOC15_REG_OFFSET(GC, 0, mmRLC_GTS_OFFSET_MSB)) { + if (amdgpu_sriov_reg_indirect_gc(adev)) + *flag = write ? GFX_RLCG_GC_WRITE : GFX_RLCG_GC_READ; + else + return false; + } else { + if (amdgpu_sriov_reg_indirect_mmhub(adev)) + *flag = GFX_RLCG_MMHUB_WRITE; + else + return false; + } + + return true; +} + +static u32 gfx_v10_rlcg_rw(struct amdgpu_device *adev, u32 offset, u32 v, uint32_t flag) { static void *scratch_reg0; static void *scratch_reg1; + static void *scratch_reg2; + static void *scratch_reg3; static void *spare_int; + static uint32_t grbm_cntl; + static uint32_t grbm_idx; uint32_t i = 0; uint32_t retries = 50000; + u32 ret = 0; + + scratch_reg0 = adev->rmmio + + (adev->reg_offset[GC_HWIP][0][mmSCRATCH_REG0_BASE_IDX] + mmSCRATCH_REG0) * 4; + scratch_reg1 = adev->rmmio + + (adev->reg_offset[GC_HWIP][0][mmSCRATCH_REG1_BASE_IDX] + mmSCRATCH_REG1) * 4; + scratch_reg2 = adev->rmmio + + (adev->reg_offset[GC_HWIP][0][mmSCRATCH_REG0_BASE_IDX] + mmSCRATCH_REG2) * 4; + scratch_reg3 = adev->rmmio + + (adev->reg_offset[GC_HWIP][0][mmSCRATCH_REG1_BASE_IDX] + mmSCRATCH_REG3) * 4; + spare_int = adev->rmmio + + (adev->reg_offset[GC_HWIP][0][mmRLC_SPARE_INT_BASE_IDX] + mmRLC_SPARE_INT) * 4; + + grbm_cntl = adev->reg_offset[GC_HWIP][0][mmGRBM_GFX_CNTL_BASE_IDX] + mmGRBM_GFX_CNTL; + grbm_idx = adev->reg_offset[GC_HWIP][0][mmGRBM_GFX_INDEX_BASE_IDX] + mmGRBM_GFX_INDEX; + + if (offset == grbm_cntl || offset == grbm_idx) { + if (offset == grbm_cntl) + writel(v, scratch_reg2); + else if (offset == grbm_idx) + writel(v, scratch_reg3); + + writel(v, ((void __iomem *)adev->rmmio) + (offset * 4)); + } else { + writel(v, scratch_reg0); + writel(offset | flag, scratch_reg1); + writel(1, spare_int); + for (i = 0; i < retries; i++) { + u32 tmp; + + tmp = readl(scratch_reg1); + if (!(tmp & flag)) + break; - scratch_reg0 = adev->rmmio + (adev->reg_offset[GC_HWIP][0][mmSCRATCH_REG0_BASE_IDX] + mmSCRATCH_REG0)*4; - scratch_reg1 = adev->rmmio + (adev->reg_offset[GC_HWIP][0][mmSCRATCH_REG1_BASE_IDX] + mmSCRATCH_REG1)*4; - spare_int = adev->rmmio + (adev->reg_offset[GC_HWIP][0][mmRLC_SPARE_INT_BASE_IDX] + mmRLC_SPARE_INT)*4; + udelay(10); + } - if (amdgpu_sriov_runtime(adev)) { - pr_err("shouldn't call rlcg write register during runtime\n"); - return; + if (i >= retries) + pr_err("timeout: rlcg program reg:0x%05x failed !\n", offset); } - writel(v, scratch_reg0); - writel(offset | 0x80000000, scratch_reg1); - writel(1, spare_int); - for (i = 0; i < retries; i++) { - u32 tmp; + ret = readl(scratch_reg0); - tmp = readl(scratch_reg1); - if (!(tmp & 0x80000000)) - break; + return ret; +} + +static void gfx_v10_rlcg_wreg(struct amdgpu_device *adev, u32 offset, u32 value, u32 flag) +{ + uint32_t rlcg_flag; - udelay(10); + if (amdgpu_sriov_fullaccess(adev) && + gfx_v10_is_rlcg_rw(adev, offset, &rlcg_flag, 1)) { + gfx_v10_rlcg_rw(adev, offset, value, rlcg_flag); + + return; } + if (flag & AMDGPU_REGS_NO_KIQ) + WREG32_NO_KIQ(offset, value); + else + WREG32(offset, value); +} - if (i >= retries) - pr_err("timeout: rlcg program reg:0x%05x failed !\n", offset); +static u32 gfx_v10_rlcg_rreg(struct amdgpu_device *adev, u32 offset, u32 flag) +{ + uint32_t rlcg_flag; + + if (amdgpu_sriov_fullaccess(adev) && + gfx_v10_is_rlcg_rw(adev, offset, &rlcg_flag, 0)) + return gfx_v10_rlcg_rw(adev, offset, 0, rlcg_flag); + + if (flag & AMDGPU_REGS_NO_KIQ) + return RREG32_NO_KIQ(offset); + else + return RREG32(offset); + + return 0; } static const struct soc15_reg_golden golden_settings_gc_10_1_nv14[] = @@ -3280,7 +3373,7 @@ static const struct soc15_reg_golden golden_settings_gc_10_3_4[] = SOC15_REG_GOLDEN_VALUE(GC, 0, mmCPF_GCR_CNTL, 0x0007ffff, 0x0000c000), SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_DEBUG3, 0x00000280, 0x00000280), SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_DEBUG4, 0x07800000, 0x00800000), - SOC15_REG_GOLDEN_VALUE(GC, 0, mmGCR_GENERAL_CNTL, 0x00001d00, 0x00000500), + SOC15_REG_GOLDEN_VALUE(GC, 0, mmGCR_GENERAL_CNTL_Sienna_Cichlid, 0x00001d00, 0x00000500), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGE_PC_CNTL, 0x003c0000, 0x00280400), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL2A_ADDR_MATCH_MASK, 0xffffffff, 0xffffffcf), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL2C_ADDR_MATCH_MASK, 0xffffffff, 0xffffffcf), @@ -4459,9 +4552,8 @@ static int gfx_v10_0_gfx_ring_init(struct amdgpu_device *adev, int ring_id, sprintf(ring->name, "gfx_%d.%d.%d", ring->me, ring->pipe, ring->queue); irq_type = AMDGPU_CP_IRQ_GFX_ME0_PIPE0_EOP + ring->pipe; - r = amdgpu_ring_init(adev, ring, 1024, - &adev->gfx.eop_irq, irq_type, - AMDGPU_RING_PRIO_DEFAULT); + r = amdgpu_ring_init(adev, ring, 1024, &adev->gfx.eop_irq, irq_type, + AMDGPU_RING_PRIO_DEFAULT, NULL); if (r) return r; return 0; @@ -4495,8 +4587,8 @@ static int gfx_v10_0_compute_ring_init(struct amdgpu_device *adev, int ring_id, hw_prio = amdgpu_gfx_is_high_priority_compute_queue(adev, ring) ? AMDGPU_GFX_PIPE_PRIO_HIGH : AMDGPU_GFX_PIPE_PRIO_NORMAL; /* type-2 packets are deprecated on MEC, use type-3 instead */ - r = amdgpu_ring_init(adev, ring, 1024, - &adev->gfx.eop_irq, irq_type, hw_prio); + r = amdgpu_ring_init(adev, ring, 1024, &adev->gfx.eop_irq, irq_type, + hw_prio, NULL); if (r) return r; @@ -7172,16 +7264,10 @@ static int gfx_v10_0_hw_init(void *handle) * loaded firstly, so in direct type, it has to load smc ucode * here before rlc. */ - if (adev->smu.ppt_funcs != NULL && !(adev->flags & AMD_IS_APU)) { - r = smu_load_microcode(&adev->smu); + if (!(adev->flags & AMD_IS_APU)) { + r = amdgpu_pm_load_smu_firmware(adev, NULL); if (r) return r; - - r = smu_check_fw_status(&adev->smu); - if (r) { - pr_err("SMC firmware status is not correct\n"); - return r; - } } gfx_v10_0_disable_gpa_mode(adev); } @@ -7892,6 +7978,7 @@ static const struct amdgpu_rlc_funcs gfx_v10_0_rlc_funcs_sriov = { .start = gfx_v10_0_rlc_start, .update_spm_vmid = gfx_v10_0_update_spm_vmid, .rlcg_wreg = gfx_v10_rlcg_wreg, + .rlcg_rreg = gfx_v10_rlcg_rreg, .is_rlcg_access_range = gfx_v10_0_is_rlcg_access_range, }; diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c index ca74638dec9b..3a8d52a54873 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c @@ -3114,7 +3114,7 @@ static int gfx_v6_0_sw_init(void *handle) r = amdgpu_ring_init(adev, ring, 1024, &adev->gfx.eop_irq, AMDGPU_CP_IRQ_GFX_ME0_PIPE0_EOP, - AMDGPU_RING_PRIO_DEFAULT); + AMDGPU_RING_PRIO_DEFAULT, NULL); if (r) return r; } @@ -3137,7 +3137,7 @@ static int gfx_v6_0_sw_init(void *handle) irq_type = AMDGPU_CP_IRQ_COMPUTE_MEC1_PIPE0_EOP + ring->pipe; r = amdgpu_ring_init(adev, ring, 1024, &adev->gfx.eop_irq, irq_type, - AMDGPU_RING_PRIO_DEFAULT); + AMDGPU_RING_PRIO_DEFAULT, NULL); if (r) return r; } diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c index a368724c3dfc..c35fdd2ef2d4 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c @@ -1877,7 +1877,7 @@ static void gfx_v7_0_init_compute_vmid(struct amdgpu_device *adev) mutex_unlock(&adev->srbm_mutex); /* Initialize all compute VMIDs to have no GDS, GWS, or OA - acccess. These should be enabled by FW for target VMIDs. */ + access. These should be enabled by FW for target VMIDs. */ for (i = adev->vm_manager.first_kfd_vmid; i < AMDGPU_NUM_VMID; i++) { WREG32(amdgpu_gds_reg_offset[i].mem_base, 0); WREG32(amdgpu_gds_reg_offset[i].mem_size, 0); @@ -2058,7 +2058,7 @@ static void gfx_v7_0_constants_init(struct amdgpu_device *adev) * @adev: amdgpu_device pointer * * Set up the number and offset of the CP scratch registers. - * NOTE: use of CP scratch registers is a legacy inferface and + * NOTE: use of CP scratch registers is a legacy interface and * is not used by default on newer asics (r6xx+). On newer asics, * memory buffers are used for fences rather than scratch regs. */ @@ -2172,7 +2172,7 @@ static void gfx_v7_0_ring_emit_vgt_flush(struct amdgpu_ring *ring) * @seq: sequence number * @flags: fence related flags * - * Emits a fence sequnce number on the gfx ring and flushes + * Emits a fence sequence number on the gfx ring and flushes * GPU caches. */ static void gfx_v7_0_ring_emit_fence_gfx(struct amdgpu_ring *ring, u64 addr, @@ -2215,7 +2215,7 @@ static void gfx_v7_0_ring_emit_fence_gfx(struct amdgpu_ring *ring, u64 addr, * @seq: sequence number * @flags: fence related flags * - * Emits a fence sequnce number on the compute ring and flushes + * Emits a fence sequence number on the compute ring and flushes * GPU caches. */ static void gfx_v7_0_ring_emit_fence_compute(struct amdgpu_ring *ring, @@ -2245,14 +2245,14 @@ static void gfx_v7_0_ring_emit_fence_compute(struct amdgpu_ring *ring, * gfx_v7_0_ring_emit_ib - emit an IB (Indirect Buffer) on the ring * * @ring: amdgpu_ring structure holding ring information - * @job: job to retrive vmid from + * @job: job to retrieve vmid from * @ib: amdgpu indirect buffer object * @flags: options (AMDGPU_HAVE_CTX_SWITCH) * * Emits an DE (drawing engine) or CE (constant engine) IB * on the gfx ring. IBs are usually generated by userspace * acceleration drivers and submitted to the kernel for - * sheduling on the ring. This function schedules the IB + * scheduling on the ring. This function schedules the IB * on the gfx ring for execution by the GPU. */ static void gfx_v7_0_ring_emit_ib_gfx(struct amdgpu_ring *ring, @@ -2402,7 +2402,7 @@ err1: /* * CP. - * On CIK, gfx and compute now have independant command processors. + * On CIK, gfx and compute now have independent command processors. * * GFX * Gfx consists of a single ring and can process both gfx jobs and @@ -2630,7 +2630,7 @@ static int gfx_v7_0_cp_gfx_resume(struct amdgpu_device *adev) ring->wptr = 0; WREG32(mmCP_RB0_WPTR, lower_32_bits(ring->wptr)); - /* set the wb address wether it's enabled or not */ + /* set the wb address whether it's enabled or not */ rptr_addr = adev->wb.gpu_addr + (ring->rptr_offs * 4); WREG32(mmCP_RB0_RPTR_ADDR, lower_32_bits(rptr_addr)); WREG32(mmCP_RB0_RPTR_ADDR_HI, upper_32_bits(rptr_addr) & 0xFF); @@ -2985,7 +2985,7 @@ static void gfx_v7_0_mqd_init(struct amdgpu_device *adev, mqd->cp_hqd_pq_wptr_poll_addr_lo = wb_gpu_addr & 0xfffffffc; mqd->cp_hqd_pq_wptr_poll_addr_hi = upper_32_bits(wb_gpu_addr) & 0xffff; - /* set the wb address wether it's enabled or not */ + /* set the wb address whether it's enabled or not */ wb_gpu_addr = adev->wb.gpu_addr + (ring->rptr_offs * 4); mqd->cp_hqd_pq_rptr_report_addr_lo = wb_gpu_addr & 0xfffffffc; mqd->cp_hqd_pq_rptr_report_addr_hi = @@ -3198,7 +3198,7 @@ static int gfx_v7_0_cp_resume(struct amdgpu_device *adev) /** * gfx_v7_0_ring_emit_vm_flush - cik vm flush using the CP * - * @ring: the ring to emmit the commands to + * @ring: the ring to emit the commands to * * Sync the command pipeline with the PFP. E.g. wait for everything * to be completed. @@ -3220,7 +3220,7 @@ static void gfx_v7_0_ring_emit_pipeline_sync(struct amdgpu_ring *ring) amdgpu_ring_write(ring, 4); /* poll interval */ if (usepfp) { - /* synce CE with ME to prevent CE fetch CEIB before context switch done */ + /* sync CE with ME to prevent CE fetch CEIB before context switch done */ amdgpu_ring_write(ring, PACKET3(PACKET3_SWITCH_BUFFER, 0)); amdgpu_ring_write(ring, 0); amdgpu_ring_write(ring, PACKET3(PACKET3_SWITCH_BUFFER, 0)); @@ -4438,7 +4438,7 @@ static int gfx_v7_0_compute_ring_init(struct amdgpu_device *adev, int ring_id, /* type-2 packets are deprecated on MEC, use type-3 instead */ r = amdgpu_ring_init(adev, ring, 1024, &adev->gfx.eop_irq, irq_type, - AMDGPU_RING_PRIO_DEFAULT); + AMDGPU_RING_PRIO_DEFAULT, NULL); if (r) return r; @@ -4512,7 +4512,7 @@ static int gfx_v7_0_sw_init(void *handle) r = amdgpu_ring_init(adev, ring, 1024, &adev->gfx.eop_irq, AMDGPU_CP_IRQ_GFX_ME0_PIPE0_EOP, - AMDGPU_RING_PRIO_DEFAULT); + AMDGPU_RING_PRIO_DEFAULT, NULL); if (r) return r; } diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c index 4d45844a1d92..c26e06059466 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c @@ -1927,8 +1927,8 @@ static int gfx_v8_0_compute_ring_init(struct amdgpu_device *adev, int ring_id, hw_prio = amdgpu_gfx_is_high_priority_compute_queue(adev, ring) ? AMDGPU_GFX_PIPE_PRIO_HIGH : AMDGPU_RING_PRIO_DEFAULT; /* type-2 packets are deprecated on MEC, use type-3 instead */ - r = amdgpu_ring_init(adev, ring, 1024, - &adev->gfx.eop_irq, irq_type, hw_prio); + r = amdgpu_ring_init(adev, ring, 1024, &adev->gfx.eop_irq, irq_type, + hw_prio, NULL); if (r) return r; @@ -2033,7 +2033,7 @@ static int gfx_v8_0_sw_init(void *handle) r = amdgpu_ring_init(adev, ring, 1024, &adev->gfx.eop_irq, AMDGPU_CP_IRQ_GFX_ME0_PIPE0_EOP, - AMDGPU_RING_PRIO_DEFAULT); + AMDGPU_RING_PRIO_DEFAULT, NULL); if (r) return r; } diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c index 1393ccae7418..a078a38c2cee 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c @@ -734,7 +734,7 @@ static const u32 GFX_RLC_SRM_INDEX_CNTL_DATA_OFFSETS[] = mmRLC_SRM_INDEX_CNTL_DATA_7 - mmRLC_SRM_INDEX_CNTL_DATA_0, }; -static void gfx_v9_0_rlcg_wreg(struct amdgpu_device *adev, u32 offset, u32 v) +static void gfx_v9_0_rlcg_rw(struct amdgpu_device *adev, u32 offset, u32 v, u32 flag) { static void *scratch_reg0; static void *scratch_reg1; @@ -787,6 +787,20 @@ static void gfx_v9_0_rlcg_wreg(struct amdgpu_device *adev, u32 offset, u32 v) } +static void gfx_v9_0_rlcg_wreg(struct amdgpu_device *adev, u32 offset, u32 v, u32 flag) +{ + if (amdgpu_sriov_fullaccess(adev)) { + gfx_v9_0_rlcg_rw(adev, offset, v, flag); + + return; + } + + if (flag & AMDGPU_REGS_NO_KIQ) + WREG32_NO_KIQ(offset, v); + else + WREG32(offset, v); +} + #define VEGA10_GB_ADDR_CONFIG_GOLDEN 0x2a114042 #define VEGA12_GB_ADDR_CONFIG_GOLDEN 0x24104041 #define RAVEN_GB_ADDR_CONFIG_GOLDEN 0x24000042 @@ -1573,6 +1587,9 @@ static int gfx_v9_0_init_cp_compute_microcode(struct amdgpu_device *adev, err = 0; adev->gfx.mec2_fw = NULL; } + } else { + adev->gfx.mec2_fw_version = adev->gfx.mec_fw_version; + adev->gfx.mec2_feature_version = adev->gfx.mec_feature_version; } if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) { @@ -2089,45 +2106,22 @@ static void gfx_v9_0_select_me_pipe_q(struct amdgpu_device *adev, } static const struct amdgpu_gfx_funcs gfx_v9_0_gfx_funcs = { - .get_gpu_clock_counter = &gfx_v9_0_get_gpu_clock_counter, - .select_se_sh = &gfx_v9_0_select_se_sh, - .read_wave_data = &gfx_v9_0_read_wave_data, - .read_wave_sgprs = &gfx_v9_0_read_wave_sgprs, - .read_wave_vgprs = &gfx_v9_0_read_wave_vgprs, - .select_me_pipe_q = &gfx_v9_0_select_me_pipe_q, + .get_gpu_clock_counter = &gfx_v9_0_get_gpu_clock_counter, + .select_se_sh = &gfx_v9_0_select_se_sh, + .read_wave_data = &gfx_v9_0_read_wave_data, + .read_wave_sgprs = &gfx_v9_0_read_wave_sgprs, + .read_wave_vgprs = &gfx_v9_0_read_wave_vgprs, + .select_me_pipe_q = &gfx_v9_0_select_me_pipe_q, +}; + +static const struct amdgpu_gfx_ras_funcs gfx_v9_0_ras_funcs = { + .ras_late_init = amdgpu_gfx_ras_late_init, + .ras_fini = amdgpu_gfx_ras_fini, .ras_error_inject = &gfx_v9_0_ras_error_inject, .query_ras_error_count = &gfx_v9_0_query_ras_error_count, .reset_ras_error_count = &gfx_v9_0_reset_ras_error_count, }; -static const struct amdgpu_gfx_funcs gfx_v9_4_gfx_funcs = { - .get_gpu_clock_counter = &gfx_v9_0_get_gpu_clock_counter, - .select_se_sh = &gfx_v9_0_select_se_sh, - .read_wave_data = &gfx_v9_0_read_wave_data, - .read_wave_sgprs = &gfx_v9_0_read_wave_sgprs, - .read_wave_vgprs = &gfx_v9_0_read_wave_vgprs, - .select_me_pipe_q = &gfx_v9_0_select_me_pipe_q, - .ras_error_inject = &gfx_v9_4_ras_error_inject, - .query_ras_error_count = &gfx_v9_4_query_ras_error_count, - .reset_ras_error_count = &gfx_v9_4_reset_ras_error_count, - .query_ras_error_status = &gfx_v9_4_query_ras_error_status, -}; - -static const struct amdgpu_gfx_funcs gfx_v9_4_2_gfx_funcs = { - .get_gpu_clock_counter = &gfx_v9_0_get_gpu_clock_counter, - .select_se_sh = &gfx_v9_0_select_se_sh, - .read_wave_data = &gfx_v9_0_read_wave_data, - .read_wave_sgprs = &gfx_v9_0_read_wave_sgprs, - .read_wave_vgprs = &gfx_v9_0_read_wave_vgprs, - .select_me_pipe_q = &gfx_v9_0_select_me_pipe_q, - .ras_error_inject = &gfx_v9_4_2_ras_error_inject, - .query_ras_error_count = &gfx_v9_4_2_query_ras_error_count, - .reset_ras_error_count = &gfx_v9_4_2_reset_ras_error_count, - .query_ras_error_status = &gfx_v9_4_2_query_ras_error_status, - .reset_ras_error_status = &gfx_v9_4_2_reset_ras_error_status, - .enable_watchdog_timer = &gfx_v9_4_2_enable_watchdog_timer, -}; - static int gfx_v9_0_gpu_early_init(struct amdgpu_device *adev) { u32 gb_addr_config; @@ -2154,6 +2148,7 @@ static int gfx_v9_0_gpu_early_init(struct amdgpu_device *adev) DRM_INFO("fix gfx.config for vega12\n"); break; case CHIP_VEGA20: + adev->gfx.ras_funcs = &gfx_v9_0_ras_funcs; adev->gfx.config.max_hw_contexts = 8; adev->gfx.config.sc_prim_fifo_size_frontend = 0x20; adev->gfx.config.sc_prim_fifo_size_backend = 0x100; @@ -2179,7 +2174,7 @@ static int gfx_v9_0_gpu_early_init(struct amdgpu_device *adev) gb_addr_config = RAVEN_GB_ADDR_CONFIG_GOLDEN; break; case CHIP_ARCTURUS: - adev->gfx.funcs = &gfx_v9_4_gfx_funcs; + adev->gfx.ras_funcs = &gfx_v9_4_ras_funcs; adev->gfx.config.max_hw_contexts = 8; adev->gfx.config.sc_prim_fifo_size_frontend = 0x20; adev->gfx.config.sc_prim_fifo_size_backend = 0x100; @@ -2200,7 +2195,7 @@ static int gfx_v9_0_gpu_early_init(struct amdgpu_device *adev) gb_addr_config |= 0x22010042; break; case CHIP_ALDEBARAN: - adev->gfx.funcs = &gfx_v9_4_2_gfx_funcs; + adev->gfx.ras_funcs = &gfx_v9_4_2_ras_funcs; adev->gfx.config.max_hw_contexts = 8; adev->gfx.config.sc_prim_fifo_size_frontend = 0x20; adev->gfx.config.sc_prim_fifo_size_backend = 0x100; @@ -2286,8 +2281,8 @@ static int gfx_v9_0_compute_ring_init(struct amdgpu_device *adev, int ring_id, hw_prio = amdgpu_gfx_is_high_priority_compute_queue(adev, ring) ? AMDGPU_GFX_PIPE_PRIO_HIGH : AMDGPU_GFX_PIPE_PRIO_NORMAL; /* type-2 packets are deprecated on MEC, use type-3 instead */ - return amdgpu_ring_init(adev, ring, 1024, - &adev->gfx.eop_irq, irq_type, hw_prio); + return amdgpu_ring_init(adev, ring, 1024, &adev->gfx.eop_irq, irq_type, + hw_prio, NULL); } static int gfx_v9_0_sw_init(void *handle) @@ -2376,10 +2371,9 @@ static int gfx_v9_0_sw_init(void *handle) sprintf(ring->name, "gfx_%d", i); ring->use_doorbell = true; ring->doorbell_index = adev->doorbell_index.gfx_ring0 << 1; - r = amdgpu_ring_init(adev, ring, 1024, - &adev->gfx.eop_irq, + r = amdgpu_ring_init(adev, ring, 1024, &adev->gfx.eop_irq, AMDGPU_CP_IRQ_GFX_ME0_PIPE0_EOP, - AMDGPU_RING_PRIO_DEFAULT); + AMDGPU_RING_PRIO_DEFAULT, NULL); if (r) return r; } @@ -2434,7 +2428,9 @@ static int gfx_v9_0_sw_fini(void *handle) int i; struct amdgpu_device *adev = (struct amdgpu_device *)handle; - amdgpu_gfx_ras_fini(adev); + if (adev->gfx.ras_funcs && + adev->gfx.ras_funcs->ras_fini) + adev->gfx.ras_funcs->ras_fini(adev); for (i = 0; i < adev->gfx.num_gfx_rings; i++) amdgpu_ring_fini(&adev->gfx.gfx_ring[i]); @@ -4025,8 +4021,14 @@ static int gfx_v9_0_hw_fini(void *handle) } gfx_v9_0_cp_enable(adev, false); - adev->gfx.rlc.funcs->stop(adev); + /* Skip suspend with A+A reset */ + if (adev->gmc.xgmi.connected_to_cpu && amdgpu_in_reset(adev)) { + dev_dbg(adev->dev, "Device in reset. Skipping RLC halt\n"); + return 0; + } + + adev->gfx.rlc.funcs->stop(adev); return 0; } @@ -4747,12 +4749,16 @@ static int gfx_v9_0_ecc_late_init(void *handle) if (r) return r; - r = amdgpu_gfx_ras_late_init(adev); - if (r) - return r; + if (adev->gfx.ras_funcs && + adev->gfx.ras_funcs->ras_late_init) { + r = adev->gfx.ras_funcs->ras_late_init(adev); + if (r) + return r; + } - if (adev->gfx.funcs->enable_watchdog_timer) - adev->gfx.funcs->enable_watchdog_timer(adev); + if (adev->gfx.ras_funcs && + adev->gfx.ras_funcs->enable_watchdog_timer) + adev->gfx.ras_funcs->enable_watchdog_timer(adev); return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4.c index bc699d680ce8..b4789dfc2bb9 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4.c @@ -863,8 +863,8 @@ static int gfx_v9_4_ras_error_count(struct amdgpu_device *adev, return 0; } -int gfx_v9_4_query_ras_error_count(struct amdgpu_device *adev, - void *ras_error_status) +static int gfx_v9_4_query_ras_error_count(struct amdgpu_device *adev, + void *ras_error_status) { struct ras_err_data *err_data = (struct ras_err_data *)ras_error_status; uint32_t sec_count = 0, ded_count = 0; @@ -906,7 +906,7 @@ int gfx_v9_4_query_ras_error_count(struct amdgpu_device *adev, return 0; } -void gfx_v9_4_reset_ras_error_count(struct amdgpu_device *adev) +static void gfx_v9_4_reset_ras_error_count(struct amdgpu_device *adev) { int i, j, k; @@ -971,7 +971,8 @@ void gfx_v9_4_reset_ras_error_count(struct amdgpu_device *adev) WREG32_SOC15(GC, 0, mmATC_L2_CACHE_4K_DSM_INDEX, 255); } -int gfx_v9_4_ras_error_inject(struct amdgpu_device *adev, void *inject_if) +static int gfx_v9_4_ras_error_inject(struct amdgpu_device *adev, + void *inject_if) { struct ras_inject_if *info = (struct ras_inject_if *)inject_if; int ret; @@ -993,10 +994,10 @@ int gfx_v9_4_ras_error_inject(struct amdgpu_device *adev, void *inject_if) return ret; } -static const struct soc15_reg_entry gfx_v9_4_rdrsp_status_regs = +static const struct soc15_reg_entry gfx_v9_4_ea_err_status_regs = { SOC15_REG_ENTRY(GC, 0, mmGCEA_ERR_STATUS), 0, 1, 32 }; -void gfx_v9_4_query_ras_error_status(struct amdgpu_device *adev) +static void gfx_v9_4_query_ras_error_status(struct amdgpu_device *adev) { uint32_t i, j; uint32_t reg_value; @@ -1006,18 +1007,33 @@ void gfx_v9_4_query_ras_error_status(struct amdgpu_device *adev) mutex_lock(&adev->grbm_idx_mutex); - for (i = 0; i < gfx_v9_4_rdrsp_status_regs.se_num; i++) { - for (j = 0; j < gfx_v9_4_rdrsp_status_regs.instance; + for (i = 0; i < gfx_v9_4_ea_err_status_regs.se_num; i++) { + for (j = 0; j < gfx_v9_4_ea_err_status_regs.instance; j++) { gfx_v9_4_select_se_sh(adev, i, 0, j); reg_value = RREG32(SOC15_REG_ENTRY_OFFSET( - gfx_v9_4_rdrsp_status_regs)); - if (reg_value) + gfx_v9_4_ea_err_status_regs)); + if (REG_GET_FIELD(reg_value, GCEA_ERR_STATUS, SDP_RDRSP_STATUS) || + REG_GET_FIELD(reg_value, GCEA_ERR_STATUS, SDP_WRRSP_STATUS) || + REG_GET_FIELD(reg_value, GCEA_ERR_STATUS, SDP_RDRSP_DATAPARITY_ERROR)) { + /* SDP read/write error/parity error in FUE_IS_FATAL mode + * can cause system fatal error in arcturas. Harvest the error + * status before GPU reset */ dev_warn(adev->dev, "GCEA err detected at instance: %d, status: 0x%x!\n", j, reg_value); + } } } gfx_v9_4_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff); mutex_unlock(&adev->grbm_idx_mutex); } + +const struct amdgpu_gfx_ras_funcs gfx_v9_4_ras_funcs = { + .ras_late_init = amdgpu_gfx_ras_late_init, + .ras_fini = amdgpu_gfx_ras_fini, + .ras_error_inject = &gfx_v9_4_ras_error_inject, + .query_ras_error_count = &gfx_v9_4_query_ras_error_count, + .reset_ras_error_count = &gfx_v9_4_reset_ras_error_count, + .query_ras_error_status = &gfx_v9_4_query_ras_error_status, +}; diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4.h b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4.h index 875f18473a98..bdd16b568021 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4.h +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4.h @@ -24,16 +24,6 @@ #ifndef __GFX_V9_4_H__ #define __GFX_V9_4_H__ -void gfx_v9_4_clear_ras_edc_counter(struct amdgpu_device *adev); - -int gfx_v9_4_query_ras_error_count(struct amdgpu_device *adev, - void *ras_error_status); - -int gfx_v9_4_ras_error_inject(struct amdgpu_device *adev, - void *inject_if); - -void gfx_v9_4_reset_ras_error_count(struct amdgpu_device *adev); - -void gfx_v9_4_query_ras_error_status(struct amdgpu_device *adev); +extern const struct amdgpu_gfx_ras_funcs gfx_v9_4_ras_funcs; #endif /* __GFX_V9_4_H__ */ diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_2.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_2.c index 2e94998c9812..a30c7c10cd9a 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_2.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_2.c @@ -808,7 +808,7 @@ static struct gfx_v9_4_2_utc_block gfx_v9_4_2_utc_blocks[] = { REG_SET_FIELD(0, ATC_L2_CACHE_4K_DSM_CNTL, WRITE_COUNTERS, 1) }, }; -static const struct soc15_reg_entry gfx_v9_4_2_rdrsp_status_regs = +static const struct soc15_reg_entry gfx_v9_4_2_ea_err_status_regs = { SOC15_REG_ENTRY(GC, 0, regGCEA_ERR_STATUS), 0, 1, 16 }; static int gfx_v9_4_2_get_reg_error_count(struct amdgpu_device *adev, @@ -997,8 +997,9 @@ static int gfx_v9_4_2_query_utc_edc_count(struct amdgpu_device *adev, blk->clear); /* print the edc count */ - gfx_v9_4_2_log_utc_edc_count(adev, blk, j, sec_cnt, - ded_cnt); + if (sec_cnt || ded_cnt) + gfx_v9_4_2_log_utc_edc_count(adev, blk, j, sec_cnt, + ded_cnt); } } @@ -1040,11 +1041,11 @@ static void gfx_v9_4_2_reset_ea_err_status(struct amdgpu_device *adev) uint32_t i, j; mutex_lock(&adev->grbm_idx_mutex); - for (i = 0; i < gfx_v9_4_2_rdrsp_status_regs.se_num; i++) { - for (j = 0; j < gfx_v9_4_2_rdrsp_status_regs.instance; + for (i = 0; i < gfx_v9_4_2_ea_err_status_regs.se_num; i++) { + for (j = 0; j < gfx_v9_4_2_ea_err_status_regs.instance; j++) { gfx_v9_4_2_select_se_sh(adev, i, 0, j); - WREG32(SOC15_REG_ENTRY_OFFSET(gfx_v9_4_2_rdrsp_status_regs), 0x10); + WREG32(SOC15_REG_ENTRY_OFFSET(gfx_v9_4_2_ea_err_status_regs), 0x10); } } gfx_v9_4_2_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff); @@ -1089,17 +1090,20 @@ static void gfx_v9_4_2_query_ea_err_status(struct amdgpu_device *adev) mutex_lock(&adev->grbm_idx_mutex); - for (i = 0; i < gfx_v9_4_2_rdrsp_status_regs.se_num; i++) { - for (j = 0; j < gfx_v9_4_2_rdrsp_status_regs.instance; + for (i = 0; i < gfx_v9_4_2_ea_err_status_regs.se_num; i++) { + for (j = 0; j < gfx_v9_4_2_ea_err_status_regs.instance; j++) { gfx_v9_4_2_select_se_sh(adev, i, 0, j); reg_value = RREG32(SOC15_REG_ENTRY_OFFSET( - gfx_v9_4_2_rdrsp_status_regs)); - if (reg_value) + gfx_v9_4_2_ea_err_status_regs)); + if (REG_GET_FIELD(reg_value, GCEA_ERR_STATUS, SDP_RDRSP_STATUS) || + REG_GET_FIELD(reg_value, GCEA_ERR_STATUS, SDP_WRRSP_STATUS) || + REG_GET_FIELD(reg_value, GCEA_ERR_STATUS, SDP_RDRSP_DATAPARITY_ERROR)) { dev_warn(adev->dev, "GCEA err detected at instance: %d, status: 0x%x!\n", j, reg_value); + } /* clear after read */ - WREG32(SOC15_REG_ENTRY_OFFSET(gfx_v9_4_2_rdrsp_status_regs), 0x10); + WREG32(SOC15_REG_ENTRY_OFFSET(gfx_v9_4_2_ea_err_status_regs), 0x10); } } @@ -1112,19 +1116,19 @@ static void gfx_v9_4_2_query_utc_err_status(struct amdgpu_device *adev) uint32_t data; data = RREG32_SOC15(GC, 0, regUTCL2_MEM_ECC_STATUS); - if (!data) { + if (data) { dev_warn(adev->dev, "GFX UTCL2 Mem Ecc Status: 0x%x!\n", data); WREG32_SOC15(GC, 0, regUTCL2_MEM_ECC_STATUS, 0x3); } data = RREG32_SOC15(GC, 0, regVML2_MEM_ECC_STATUS); - if (!data) { + if (data) { dev_warn(adev->dev, "GFX VML2 Mem Ecc Status: 0x%x!\n", data); WREG32_SOC15(GC, 0, regVML2_MEM_ECC_STATUS, 0x3); } data = RREG32_SOC15(GC, 0, regVML2_WALKER_MEM_ECC_STATUS); - if (!data) { + if (data) { dev_warn(adev->dev, "GFX VML2 Walker Mem Ecc Status: 0x%x!\n", data); WREG32_SOC15(GC, 0, regVML2_WALKER_MEM_ECC_STATUS, 0x3); } @@ -1283,4 +1287,15 @@ static void gfx_v9_4_2_reset_sq_timeout_status(struct amdgpu_device *adev) } gfx_v9_4_2_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff); mutex_unlock(&adev->grbm_idx_mutex); -}
\ No newline at end of file +} + +const struct amdgpu_gfx_ras_funcs gfx_v9_4_2_ras_funcs = { + .ras_late_init = amdgpu_gfx_ras_late_init, + .ras_fini = amdgpu_gfx_ras_fini, + .ras_error_inject = &gfx_v9_4_2_ras_error_inject, + .query_ras_error_count = &gfx_v9_4_2_query_ras_error_count, + .reset_ras_error_count = &gfx_v9_4_2_reset_ras_error_count, + .query_ras_error_status = &gfx_v9_4_2_query_ras_error_status, + .reset_ras_error_status = &gfx_v9_4_2_reset_ras_error_status, + .enable_watchdog_timer = &gfx_v9_4_2_enable_watchdog_timer, +}; diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_2.h b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_2.h index c143d178ef98..81c5833b6b9f 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_2.h +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_2.h @@ -30,11 +30,6 @@ void gfx_v9_4_2_init_golden_registers(struct amdgpu_device *adev, uint32_t die_id); void gfx_v9_4_2_set_power_brake_sequence(struct amdgpu_device *adev); -void gfx_v9_4_2_reset_ras_error_count(struct amdgpu_device *adev); -int gfx_v9_4_2_ras_error_inject(struct amdgpu_device *adev, void *inject_if); -void gfx_v9_4_2_query_ras_error_status(struct amdgpu_device *adev); -int gfx_v9_4_2_query_ras_error_count(struct amdgpu_device *adev, - void *ras_error_status); -void gfx_v9_4_2_reset_ras_error_status(struct amdgpu_device *adev); -void gfx_v9_4_2_enable_watchdog_timer(struct amdgpu_device *adev); +extern const struct amdgpu_gfx_ras_funcs gfx_v9_4_2_ras_funcs; + #endif /* __GFX_V9_4_2_H__ */ diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c index d189507dcef0..1e4678cb98f0 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c @@ -120,8 +120,7 @@ static void gfxhub_v1_0_init_system_aperture_regs(struct amdgpu_device *adev) max(adev->gmc.fb_end, adev->gmc.agp_end) >> 18); /* Set default page address. */ - value = adev->vram_scratch.gpu_addr - adev->gmc.vram_start + - adev->vm_manager.vram_base_offset; + value = amdgpu_gmc_vram_mc2pa(adev, adev->vram_scratch.gpu_addr); WREG32_SOC15(GC, 0, mmMC_VM_SYSTEM_APERTURE_DEFAULT_ADDR_LSB, (u32)(value >> 12)); WREG32_SOC15(GC, 0, mmMC_VM_SYSTEM_APERTURE_DEFAULT_ADDR_MSB, @@ -141,21 +140,12 @@ static void gfxhub_v1_0_init_system_aperture_regs(struct amdgpu_device *adev) * FB aperture and AGP aperture. Disable them. */ if (adev->gmc.pdb0_bo) { - if (adev->asic_type == CHIP_ALDEBARAN) { - WREG32_SOC15(GC, 0, mmMC_VM_FB_LOCATION_TOP, adev->gmc.fb_end_original >> 24); - WREG32_SOC15(GC, 0, mmMC_VM_FB_LOCATION_BASE, adev->gmc.fb_start_original >> 24); - WREG32_SOC15(GC, 0, mmMC_VM_AGP_TOP, 0); - WREG32_SOC15(GC, 0, mmMC_VM_AGP_BOT, 0xFFFFFF); - WREG32_SOC15(GC, 0, mmMC_VM_SYSTEM_APERTURE_LOW_ADDR, adev->gmc.fb_start_original >> 18); - WREG32_SOC15(GC, 0, mmMC_VM_SYSTEM_APERTURE_HIGH_ADDR, adev->gmc.fb_end_original >> 18); - } else { - WREG32_SOC15(GC, 0, mmMC_VM_FB_LOCATION_TOP, 0); - WREG32_SOC15(GC, 0, mmMC_VM_FB_LOCATION_BASE, 0x00FFFFFF); - WREG32_SOC15(GC, 0, mmMC_VM_AGP_TOP, 0); - WREG32_SOC15(GC, 0, mmMC_VM_AGP_BOT, 0xFFFFFF); - WREG32_SOC15(GC, 0, mmMC_VM_SYSTEM_APERTURE_LOW_ADDR, 0x3FFFFFFF); - WREG32_SOC15(GC, 0, mmMC_VM_SYSTEM_APERTURE_HIGH_ADDR, 0); - } + WREG32_SOC15(GC, 0, mmMC_VM_FB_LOCATION_TOP, 0); + WREG32_SOC15(GC, 0, mmMC_VM_FB_LOCATION_BASE, 0x00FFFFFF); + WREG32_SOC15(GC, 0, mmMC_VM_AGP_TOP, 0); + WREG32_SOC15(GC, 0, mmMC_VM_AGP_BOT, 0xFFFFFF); + WREG32_SOC15(GC, 0, mmMC_VM_SYSTEM_APERTURE_LOW_ADDR, 0x3FFFFFFF); + WREG32_SOC15(GC, 0, mmMC_VM_SYSTEM_APERTURE_HIGH_ADDR, 0); } } diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.c b/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.c index 2aecc6a243e8..14c1c1a297dd 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.c @@ -165,8 +165,7 @@ static void gfxhub_v2_0_init_system_aperture_regs(struct amdgpu_device *adev) max(adev->gmc.fb_end, adev->gmc.agp_end) >> 18); /* Set default page address. */ - value = adev->vram_scratch.gpu_addr - adev->gmc.vram_start - + adev->vm_manager.vram_base_offset; + value = amdgpu_gmc_vram_mc2pa(adev, adev->vram_scratch.gpu_addr); WREG32_SOC15(GC, 0, mmGCMC_VM_SYSTEM_APERTURE_DEFAULT_ADDR_LSB, (u32)(value >> 12)); WREG32_SOC15(GC, 0, mmGCMC_VM_SYSTEM_APERTURE_DEFAULT_ADDR_MSB, diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_1.c b/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_1.c index 410fd3a1a388..41807817de7d 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_1.c +++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_1.c @@ -164,8 +164,7 @@ static void gfxhub_v2_1_init_system_aperture_regs(struct amdgpu_device *adev) max(adev->gmc.fb_end, adev->gmc.agp_end) >> 18); /* Set default page address. */ - value = adev->vram_scratch.gpu_addr - adev->gmc.vram_start - + adev->vm_manager.vram_base_offset; + value = amdgpu_gmc_vram_mc2pa(adev, adev->vram_scratch.gpu_addr); WREG32_SOC15(GC, 0, mmGCMC_VM_SYSTEM_APERTURE_DEFAULT_ADDR_LSB, (u32)(value >> 12)); WREG32_SOC15(GC, 0, mmGCMC_VM_SYSTEM_APERTURE_DEFAULT_ADDR_MSB, diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c index 33e54eed2eec..498b28a35f5b 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c @@ -568,8 +568,7 @@ static void gmc_v10_0_get_vm_pde(struct amdgpu_device *adev, int level, uint64_t *addr, uint64_t *flags) { if (!(*flags & AMDGPU_PDE_PTE) && !(*flags & AMDGPU_PTE_SYSTEM)) - *addr = adev->vm_manager.vram_base_offset + *addr - - adev->gmc.vram_start; + *addr = amdgpu_gmc_vram_mc2pa(adev, *addr); BUG_ON(*addr & 0xFFFF00000000003FULL); if (!adev->gmc.translate_further) @@ -655,7 +654,7 @@ static void gmc_v10_0_set_umc_funcs(struct amdgpu_device *adev) adev->umc.umc_inst_num = UMC_V8_7_UMC_INSTANCE_NUM; adev->umc.channel_offs = UMC_V8_7_PER_CHANNEL_OFFSET_SIENNA; adev->umc.channel_idx_tbl = &umc_v8_7_channel_idx_tbl[0][0]; - adev->umc.funcs = &umc_v8_7_funcs; + adev->umc.ras_funcs = &umc_v8_7_ras_funcs; break; default: break; diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c index 468acc06b681..455bb91060d0 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c @@ -574,7 +574,8 @@ static int gmc_v9_0_process_interrupt(struct amdgpu_device *adev, * be updated to avoid reading an incorrect value due to * the new fast GRBM interface. */ - if (entry->vmid_src == AMDGPU_GFXHUB_0) + if ((entry->vmid_src == AMDGPU_GFXHUB_0) && + (adev->asic_type < CHIP_ALDEBARAN)) RREG32(hub->vm_l2_pro_fault_status); status = RREG32(hub->vm_l2_pro_fault_status); @@ -653,7 +654,8 @@ static void gmc_v9_0_set_irq_funcs(struct amdgpu_device *adev) adev->gmc.vm_fault.num_types = 1; adev->gmc.vm_fault.funcs = &gmc_v9_0_irq_funcs; - if (!amdgpu_sriov_vf(adev)) { + if (!amdgpu_sriov_vf(adev) && + !adev->gmc.xgmi.connected_to_cpu) { adev->gmc.ecc_irq.num_types = 1; adev->gmc.ecc_irq.funcs = &gmc_v9_0_ecc_funcs; } @@ -801,7 +803,8 @@ static void gmc_v9_0_flush_gpu_tlb(struct amdgpu_device *adev, uint32_t vmid, * be cleared to avoid a false ACK due to the new fast * GRBM interface. */ - if (vmhub == AMDGPU_GFXHUB_0) + if ((vmhub == AMDGPU_GFXHUB_0) && + (adev->asic_type < CHIP_ALDEBARAN)) RREG32_NO_KIQ(hub->vm_inv_eng0_req + hub->eng_distance * eng); @@ -1047,8 +1050,7 @@ static void gmc_v9_0_get_vm_pde(struct amdgpu_device *adev, int level, uint64_t *addr, uint64_t *flags) { if (!(*flags & AMDGPU_PDE_PTE) && !(*flags & AMDGPU_PTE_SYSTEM)) - *addr = adev->vm_manager.vram_base_offset + *addr - - adev->gmc.vram_start; + *addr = amdgpu_gmc_vram_mc2pa(adev, *addr); BUG_ON(*addr & 0xFFFF00000000003FULL); if (!adev->gmc.translate_further) @@ -1155,7 +1157,7 @@ static void gmc_v9_0_set_umc_funcs(struct amdgpu_device *adev) adev->umc.umc_inst_num = UMC_V6_1_UMC_INSTANCE_NUM; adev->umc.channel_offs = UMC_V6_1_PER_CHANNEL_OFFSET_VG20; adev->umc.channel_idx_tbl = &umc_v6_1_channel_idx_tbl[0][0]; - adev->umc.funcs = &umc_v6_1_funcs; + adev->umc.ras_funcs = &umc_v6_1_ras_funcs; break; case CHIP_ARCTURUS: adev->umc.max_ras_err_cnt_per_query = UMC_V6_1_TOTAL_CHANNEL_NUM; @@ -1163,7 +1165,7 @@ static void gmc_v9_0_set_umc_funcs(struct amdgpu_device *adev) adev->umc.umc_inst_num = UMC_V6_1_UMC_INSTANCE_NUM; adev->umc.channel_offs = UMC_V6_1_PER_CHANNEL_OFFSET_ARCT; adev->umc.channel_idx_tbl = &umc_v6_1_channel_idx_tbl[0][0]; - adev->umc.funcs = &umc_v6_1_funcs; + adev->umc.ras_funcs = &umc_v6_1_ras_funcs; break; default: break; @@ -1185,6 +1187,24 @@ static void gmc_v9_0_set_mmhub_funcs(struct amdgpu_device *adev) } } +static void gmc_v9_0_set_mmhub_ras_funcs(struct amdgpu_device *adev) +{ + switch (adev->asic_type) { + case CHIP_VEGA20: + adev->mmhub.ras_funcs = &mmhub_v1_0_ras_funcs; + break; + case CHIP_ARCTURUS: + adev->mmhub.ras_funcs = &mmhub_v9_4_ras_funcs; + break; + case CHIP_ALDEBARAN: + adev->mmhub.ras_funcs = &mmhub_v1_7_ras_funcs; + break; + default: + /* mmhub ras is not available */ + break; + } +} + static void gmc_v9_0_set_gfxhub_funcs(struct amdgpu_device *adev) { adev->gfxhub.funcs = &gfxhub_v1_0_funcs; @@ -1194,12 +1214,6 @@ static int gmc_v9_0_early_init(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; - gmc_v9_0_set_gmc_funcs(adev); - gmc_v9_0_set_irq_funcs(adev); - gmc_v9_0_set_umc_funcs(adev); - gmc_v9_0_set_mmhub_funcs(adev); - gmc_v9_0_set_gfxhub_funcs(adev); - if (adev->asic_type == CHIP_VEGA20 || adev->asic_type == CHIP_ARCTURUS) adev->gmc.xgmi.supported = true; @@ -1208,7 +1222,14 @@ static int gmc_v9_0_early_init(void *handle) adev->gmc.xgmi.supported = true; adev->gmc.xgmi.connected_to_cpu = adev->smuio.funcs->is_host_gpu_xgmi_supported(adev); - } + } + + gmc_v9_0_set_gmc_funcs(adev); + gmc_v9_0_set_irq_funcs(adev); + gmc_v9_0_set_umc_funcs(adev); + gmc_v9_0_set_mmhub_funcs(adev); + gmc_v9_0_set_mmhub_ras_funcs(adev); + gmc_v9_0_set_gfxhub_funcs(adev); adev->gmc.shared_aperture_start = 0x2000000000000000ULL; adev->gmc.shared_aperture_end = @@ -1240,8 +1261,9 @@ static int gmc_v9_0_late_init(void *handle) } } - if (adev->mmhub.funcs && adev->mmhub.funcs->reset_ras_error_count) - adev->mmhub.funcs->reset_ras_error_count(adev); + if (adev->mmhub.ras_funcs && + adev->mmhub.ras_funcs->reset_ras_error_count) + adev->mmhub.ras_funcs->reset_ras_error_count(adev); r = amdgpu_gmc_ras_late_init(adev); if (r) @@ -1506,7 +1528,8 @@ static int gmc_v9_0_sw_init(void *handle) if (r) return r; - if (!amdgpu_sriov_vf(adev)) { + if (!amdgpu_sriov_vf(adev) && + !adev->gmc.xgmi.connected_to_cpu) { /* interrupt sent to DF. */ r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_DF, 0, &adev->gmc.ecc_irq); diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v1_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v1_0.c index 7332a320ede8..9360204da7fb 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v1_0.c +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v1_0.c @@ -487,7 +487,7 @@ int jpeg_v1_0_sw_init(void *handle) ring = &adev->jpeg.inst->ring_dec; sprintf(ring->name, "jpeg_dec"); r = amdgpu_ring_init(adev, ring, 512, &adev->jpeg.inst->irq, - 0, AMDGPU_RING_PRIO_DEFAULT); + 0, AMDGPU_RING_PRIO_DEFAULT, NULL); if (r) return r; diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c index 3b22953aa62e..de5abceced0d 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c @@ -108,7 +108,7 @@ static int jpeg_v2_0_sw_init(void *handle) ring->doorbell_index = (adev->doorbell_index.vcn.vcn_ring0_1 << 1) + 1; sprintf(ring->name, "jpeg_dec"); r = amdgpu_ring_init(adev, ring, 512, &adev->jpeg.inst->irq, - 0, AMDGPU_RING_PRIO_DEFAULT); + 0, AMDGPU_RING_PRIO_DEFAULT, NULL); if (r) return r; diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.c index 072774ae16bd..83531997aeba 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.c +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.c @@ -115,7 +115,7 @@ static int jpeg_v2_5_sw_init(void *handle) ring->doorbell_index = (adev->doorbell_index.vcn.vcn_ring0_1 << 1) + 1 + 8 * i; sprintf(ring->name, "jpeg_dec_%d", i); r = amdgpu_ring_init(adev, ring, 512, &adev->jpeg.inst[i].irq, - 0, AMDGPU_RING_PRIO_DEFAULT); + 0, AMDGPU_RING_PRIO_DEFAULT, NULL); if (r) return r; diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v3_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v3_0.c index e8fbb2a0de34..de5dfcfb3859 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v3_0.c +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v3_0.c @@ -94,7 +94,7 @@ static int jpeg_v3_0_sw_init(void *handle) ring->doorbell_index = (adev->doorbell_index.vcn.vcn_ring0_1 << 1) + 1; sprintf(ring->name, "jpeg_dec"); r = amdgpu_ring_init(adev, ring, 512, &adev->jpeg.inst->irq, 0, - AMDGPU_RING_PRIO_DEFAULT); + AMDGPU_RING_PRIO_DEFAULT, NULL); if (r) return r; diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v10_1.c b/drivers/gpu/drm/amd/amdgpu/mes_v10_1.c index 7f30629f21a2..a7ec4ac89da5 100644 --- a/drivers/gpu/drm/amd/amdgpu/mes_v10_1.c +++ b/drivers/gpu/drm/amd/amdgpu/mes_v10_1.c @@ -848,7 +848,8 @@ static int mes_v10_1_ring_init(struct amdgpu_device *adev) ring->no_scheduler = true; sprintf(ring->name, "mes_%d.%d.%d", ring->me, ring->pipe, ring->queue); - return amdgpu_ring_init(adev, ring, 1024, NULL, 0, AMDGPU_RING_PRIO_DEFAULT); + return amdgpu_ring_init(adev, ring, 1024, NULL, 0, + AMDGPU_RING_PRIO_DEFAULT, NULL); } static int mes_v10_1_mqd_sw_init(struct amdgpu_device *adev) diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c index d7b39c07de20..a99953833820 100644 --- a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c +++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c @@ -114,8 +114,7 @@ static void mmhub_v1_0_init_system_aperture_regs(struct amdgpu_device *adev) return; /* Set default page address. */ - value = adev->vram_scratch.gpu_addr - adev->gmc.vram_start + - adev->vm_manager.vram_base_offset; + value = amdgpu_gmc_vram_mc2pa(adev, adev->vram_scratch.gpu_addr); WREG32_SOC15(MMHUB, 0, mmMC_VM_SYSTEM_APERTURE_DEFAULT_ADDR_LSB, (u32)(value >> 12)); WREG32_SOC15(MMHUB, 0, mmMC_VM_SYSTEM_APERTURE_DEFAULT_ADDR_MSB, @@ -776,10 +775,14 @@ static void mmhub_v1_0_reset_ras_error_count(struct amdgpu_device *adev) } } -const struct amdgpu_mmhub_funcs mmhub_v1_0_funcs = { +const struct amdgpu_mmhub_ras_funcs mmhub_v1_0_ras_funcs = { .ras_late_init = amdgpu_mmhub_ras_late_init, + .ras_fini = amdgpu_mmhub_ras_fini, .query_ras_error_count = mmhub_v1_0_query_ras_error_count, .reset_ras_error_count = mmhub_v1_0_reset_ras_error_count, +}; + +const struct amdgpu_mmhub_funcs mmhub_v1_0_funcs = { .get_fb_location = mmhub_v1_0_get_fb_location, .init = mmhub_v1_0_init, .gart_enable = mmhub_v1_0_gart_enable, diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.h b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.h index d77f5b65a618..4661b094e007 100644 --- a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.h +++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.h @@ -24,5 +24,6 @@ #define __MMHUB_V1_0_H__ extern const struct amdgpu_mmhub_funcs mmhub_v1_0_funcs; +extern const struct amdgpu_mmhub_ras_funcs mmhub_v1_0_ras_funcs; #endif diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_7.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_7.c index ae7d8a1738a3..0103a5ab28e6 100644 --- a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_7.c +++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_7.c @@ -47,8 +47,6 @@ static u64 mmhub_v1_7_get_fb_location(struct amdgpu_device *adev) adev->gmc.fb_start = base; adev->gmc.fb_end = top; - adev->gmc.fb_start_original = base; - adev->gmc.fb_end_original = top; return base; } @@ -126,17 +124,16 @@ static void mmhub_v1_7_init_system_aperture_regs(struct amdgpu_device *adev) if (adev->gmc.pdb0_bo) { WREG32_SOC15(MMHUB, 0, regMC_VM_AGP_BOT, 0xFFFFFF); WREG32_SOC15(MMHUB, 0, regMC_VM_AGP_TOP, 0); - WREG32_SOC15(MMHUB, 0, regMC_VM_FB_LOCATION_TOP, adev->gmc.fb_end_original >> 24); - WREG32_SOC15(MMHUB, 0, regMC_VM_FB_LOCATION_BASE, adev->gmc.fb_start_original >> 24); - WREG32_SOC15(MMHUB, 0, regMC_VM_SYSTEM_APERTURE_LOW_ADDR, adev->gmc.fb_start_original >> 18); - WREG32_SOC15(MMHUB, 0, regMC_VM_SYSTEM_APERTURE_HIGH_ADDR, adev->gmc.fb_end_original >> 18); + WREG32_SOC15(MMHUB, 0, regMC_VM_FB_LOCATION_TOP, 0); + WREG32_SOC15(MMHUB, 0, regMC_VM_FB_LOCATION_BASE, 0x00FFFFFF); + WREG32_SOC15(MMHUB, 0, regMC_VM_SYSTEM_APERTURE_LOW_ADDR, 0x3FFFFFFF); + WREG32_SOC15(MMHUB, 0, regMC_VM_SYSTEM_APERTURE_HIGH_ADDR, 0); } if (amdgpu_sriov_vf(adev)) return; /* Set default page address. */ - value = adev->vram_scratch.gpu_addr - adev->gmc.vram_start + - adev->vm_manager.vram_base_offset; + value = amdgpu_gmc_vram_mc2pa(adev, adev->vram_scratch.gpu_addr); WREG32_SOC15(MMHUB, 0, regMC_VM_SYSTEM_APERTURE_DEFAULT_ADDR_LSB, (u32)(value >> 12)); WREG32_SOC15(MMHUB, 0, regMC_VM_SYSTEM_APERTURE_DEFAULT_ADDR_MSB, @@ -1287,7 +1284,7 @@ static void mmhub_v1_7_reset_ras_error_count(struct amdgpu_device *adev) } } -static const struct soc15_reg_entry mmhub_v1_7_err_status_regs[] = { +static const struct soc15_reg_entry mmhub_v1_7_ea_err_status_regs[] = { { SOC15_REG_ENTRY(MMHUB, 0, regMMEA0_ERR_STATUS), 0, 0, 0 }, { SOC15_REG_ENTRY(MMHUB, 0, regMMEA1_ERR_STATUS), 0, 0, 0 }, { SOC15_REG_ENTRY(MMHUB, 0, regMMEA2_ERR_STATUS), 0, 0, 0 }, @@ -1304,19 +1301,27 @@ static void mmhub_v1_7_query_ras_error_status(struct amdgpu_device *adev) if (!amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__MMHUB)) return; - for (i = 0; i < ARRAY_SIZE(mmhub_v1_7_err_status_regs); i++) { + for (i = 0; i < ARRAY_SIZE(mmhub_v1_7_ea_err_status_regs); i++) { reg_value = - RREG32(SOC15_REG_ENTRY_OFFSET(mmhub_v1_7_err_status_regs[i])); - if (reg_value) + RREG32(SOC15_REG_ENTRY_OFFSET(mmhub_v1_7_ea_err_status_regs[i])); + if (REG_GET_FIELD(reg_value, MMEA0_ERR_STATUS, SDP_RDRSP_STATUS) || + REG_GET_FIELD(reg_value, MMEA0_ERR_STATUS, SDP_WRRSP_STATUS) || + REG_GET_FIELD(reg_value, MMEA0_ERR_STATUS, SDP_RDRSP_DATAPARITY_ERROR)) { dev_warn(adev->dev, "MMHUB EA err detected at instance: %d, status: 0x%x!\n", i, reg_value); + } } } -const struct amdgpu_mmhub_funcs mmhub_v1_7_funcs = { +const struct amdgpu_mmhub_ras_funcs mmhub_v1_7_ras_funcs = { .ras_late_init = amdgpu_mmhub_ras_late_init, + .ras_fini = amdgpu_mmhub_ras_fini, .query_ras_error_count = mmhub_v1_7_query_ras_error_count, .reset_ras_error_count = mmhub_v1_7_reset_ras_error_count, + .query_ras_error_status = mmhub_v1_7_query_ras_error_status, +}; + +const struct amdgpu_mmhub_funcs mmhub_v1_7_funcs = { .get_fb_location = mmhub_v1_7_get_fb_location, .init = mmhub_v1_7_init, .gart_enable = mmhub_v1_7_gart_enable, @@ -1325,5 +1330,4 @@ const struct amdgpu_mmhub_funcs mmhub_v1_7_funcs = { .set_clockgating = mmhub_v1_7_set_clockgating, .get_clockgating = mmhub_v1_7_get_clockgating, .setup_vm_pt_regs = mmhub_v1_7_setup_vm_pt_regs, - .query_ras_error_status = mmhub_v1_7_query_ras_error_status, }; diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_7.h b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_7.h index bf2fbeb172d1..a7f9dfc24697 100644 --- a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_7.h +++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_7.h @@ -24,5 +24,6 @@ #define __MMHUB_V1_7_H__ extern const struct amdgpu_mmhub_funcs mmhub_v1_7_funcs; +extern const struct amdgpu_mmhub_ras_funcs mmhub_v1_7_ras_funcs; #endif diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c index f107385faba2..ac76081b91d5 100644 --- a/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c +++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c @@ -210,8 +210,7 @@ static void mmhub_v2_0_init_system_aperture_regs(struct amdgpu_device *adev) } /* Set default page address. */ - value = adev->vram_scratch.gpu_addr - adev->gmc.vram_start + - adev->vm_manager.vram_base_offset; + value = amdgpu_gmc_vram_mc2pa(adev, adev->vram_scratch.gpu_addr); WREG32_SOC15(MMHUB, 0, mmMMMC_VM_SYSTEM_APERTURE_DEFAULT_ADDR_LSB, (u32)(value >> 12)); WREG32_SOC15(MMHUB, 0, mmMMMC_VM_SYSTEM_APERTURE_DEFAULT_ADDR_MSB, @@ -689,7 +688,6 @@ static void mmhub_v2_0_get_clockgating(struct amdgpu_device *adev, u32 *flags) } const struct amdgpu_mmhub_funcs mmhub_v2_0_funcs = { - .ras_late_init = amdgpu_mmhub_ras_late_init, .init = mmhub_v2_0_init, .gart_enable = mmhub_v2_0_gart_enable, .set_fault_enable_default = mmhub_v2_0_set_fault_enable_default, diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v2_3.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_3.c index ab9be5ad5a5f..a9899335d0b1 100644 --- a/drivers/gpu/drm/amd/amdgpu/mmhub_v2_3.c +++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_3.c @@ -162,8 +162,7 @@ static void mmhub_v2_3_init_system_aperture_regs(struct amdgpu_device *adev) max(adev->gmc.fb_end, adev->gmc.agp_end) >> 18); /* Set default page address. */ - value = adev->vram_scratch.gpu_addr - adev->gmc.vram_start + - adev->vm_manager.vram_base_offset; + value = amdgpu_gmc_vram_mc2pa(adev, adev->vram_scratch.gpu_addr); WREG32_SOC15(MMHUB, 0, mmMMMC_VM_SYSTEM_APERTURE_DEFAULT_ADDR_LSB, (u32)(value >> 12)); WREG32_SOC15(MMHUB, 0, mmMMMC_VM_SYSTEM_APERTURE_DEFAULT_ADDR_MSB, @@ -616,7 +615,6 @@ static void mmhub_v2_3_get_clockgating(struct amdgpu_device *adev, u32 *flags) } const struct amdgpu_mmhub_funcs mmhub_v2_3_funcs = { - .ras_late_init = amdgpu_mmhub_ras_late_init, .init = mmhub_v2_3_init, .gart_enable = mmhub_v2_3_gart_enable, .set_fault_enable_default = mmhub_v2_3_set_fault_enable_default, diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c index 4a31737b6bb0..47c8dd9d1c78 100644 --- a/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c +++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c @@ -136,8 +136,7 @@ static void mmhub_v9_4_init_system_aperture_regs(struct amdgpu_device *adev, max(adev->gmc.fb_end, adev->gmc.agp_end) >> 18); /* Set default page address. */ - value = adev->vram_scratch.gpu_addr - adev->gmc.vram_start + - adev->vm_manager.vram_base_offset; + value = amdgpu_gmc_vram_mc2pa(adev, adev->vram_scratch.gpu_addr); WREG32_SOC15_OFFSET( MMHUB, 0, mmVMSHAREDPF0_MC_VM_SYSTEM_APERTURE_DEFAULT_ADDR_LSB, @@ -1646,16 +1645,27 @@ static void mmhub_v9_4_query_ras_error_status(struct amdgpu_device *adev) for (i = 0; i < ARRAY_SIZE(mmhub_v9_4_err_status_regs); i++) { reg_value = RREG32(SOC15_REG_ENTRY_OFFSET(mmhub_v9_4_err_status_regs[i])); - if (reg_value) + if (REG_GET_FIELD(reg_value, MMEA0_ERR_STATUS, SDP_RDRSP_STATUS) || + REG_GET_FIELD(reg_value, MMEA0_ERR_STATUS, SDP_WRRSP_STATUS) || + REG_GET_FIELD(reg_value, MMEA0_ERR_STATUS, SDP_RDRSP_DATAPARITY_ERROR)) { + /* SDP read/write error/parity error in FUE_IS_FATAL mode + * can cause system fatal error in arcturas. Harvest the error + * status before GPU reset */ dev_warn(adev->dev, "MMHUB EA err detected at instance: %d, status: 0x%x!\n", i, reg_value); + } } } -const struct amdgpu_mmhub_funcs mmhub_v9_4_funcs = { +const struct amdgpu_mmhub_ras_funcs mmhub_v9_4_ras_funcs = { .ras_late_init = amdgpu_mmhub_ras_late_init, + .ras_fini = amdgpu_mmhub_ras_fini, .query_ras_error_count = mmhub_v9_4_query_ras_error_count, .reset_ras_error_count = mmhub_v9_4_reset_ras_error_count, + .query_ras_error_status = mmhub_v9_4_query_ras_error_status, +}; + +const struct amdgpu_mmhub_funcs mmhub_v9_4_funcs = { .get_fb_location = mmhub_v9_4_get_fb_location, .init = mmhub_v9_4_init, .gart_enable = mmhub_v9_4_gart_enable, @@ -1664,5 +1674,4 @@ const struct amdgpu_mmhub_funcs mmhub_v9_4_funcs = { .set_clockgating = mmhub_v9_4_set_clockgating, .get_clockgating = mmhub_v9_4_get_clockgating, .setup_vm_pt_regs = mmhub_v9_4_setup_vm_pt_regs, - .query_ras_error_status = mmhub_v9_4_query_ras_error_status, }; diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.h b/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.h index 92404a8f66f3..90436efa92ef 100644 --- a/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.h +++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.h @@ -24,5 +24,6 @@ #define __MMHUB_V9_4_H__ extern const struct amdgpu_mmhub_funcs mmhub_v9_4_funcs; +extern const struct amdgpu_mmhub_ras_funcs mmhub_v9_4_ras_funcs; #endif diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v6_1.c b/drivers/gpu/drm/amd/amdgpu/nbio_v6_1.c index 83ea063388fd..0d2d629e2d6a 100644 --- a/drivers/gpu/drm/amd/amdgpu/nbio_v6_1.c +++ b/drivers/gpu/drm/amd/amdgpu/nbio_v6_1.c @@ -31,6 +31,28 @@ #include "vega10_enum.h" #include <uapi/linux/kfd_ioctl.h> +#define smnPCIE_LC_CNTL 0x11140280 +#define smnPCIE_LC_CNTL3 0x111402d4 +#define smnPCIE_LC_CNTL6 0x111402ec +#define smnPCIE_LC_CNTL7 0x111402f0 +#define smnNBIF_MGCG_CTRL_LCLK 0x1013a05c +#define NBIF_MGCG_CTRL_LCLK__NBIF_MGCG_REG_DIS_LCLK_MASK 0x00001000L +#define RCC_BIF_STRAP3__STRAP_VLINK_ASPM_IDLE_TIMER_MASK 0x0000FFFFL +#define RCC_BIF_STRAP3__STRAP_VLINK_PM_L1_ENTRY_TIMER_MASK 0xFFFF0000L +#define smnRCC_EP_DEV0_0_EP_PCIE_TX_LTR_CNTL 0x10123530 +#define smnBIF_CFG_DEV0_EPF0_DEVICE_CNTL2 0x1014008c +#define smnBIF_CFG_DEV0_EPF0_PCIE_LTR_CAP 0x10140324 +#define smnPSWUSP0_PCIE_LC_CNTL2 0x111402c4 +#define smnRCC_BIF_STRAP2 0x10123488 +#define smnRCC_BIF_STRAP3 0x1012348c +#define smnRCC_BIF_STRAP5 0x10123494 +#define BIF_CFG_DEV0_EPF0_DEVICE_CNTL2__LTR_EN_MASK 0x0400L +#define RCC_BIF_STRAP5__STRAP_VLINK_LDN_ENTRY_TIMER_MASK 0x0000FFFFL +#define RCC_BIF_STRAP2__STRAP_LTR_IN_ASPML1_DIS_MASK 0x00004000L +#define RCC_BIF_STRAP3__STRAP_VLINK_ASPM_IDLE_TIMER__SHIFT 0x0 +#define RCC_BIF_STRAP3__STRAP_VLINK_PM_L1_ENTRY_TIMER__SHIFT 0x10 +#define RCC_BIF_STRAP5__STRAP_VLINK_LDN_ENTRY_TIMER__SHIFT 0x0 + static void nbio_v6_1_remap_hdp_registers(struct amdgpu_device *adev) { WREG32_SOC15(NBIO, 0, mmREMAP_HDP_MEM_FLUSH_CNTL, @@ -256,6 +278,111 @@ static void nbio_v6_1_init_registers(struct amdgpu_device *adev) WREG32_PCIE(smnPCIE_CI_CNTL, data); } +static void nbio_v6_1_program_ltr(struct amdgpu_device *adev) +{ + uint32_t def, data; + + WREG32_PCIE(smnRCC_EP_DEV0_0_EP_PCIE_TX_LTR_CNTL, 0x75EB); + + def = data = RREG32_PCIE(smnRCC_BIF_STRAP2); + data &= ~RCC_BIF_STRAP2__STRAP_LTR_IN_ASPML1_DIS_MASK; + if (def != data) + WREG32_PCIE(smnRCC_BIF_STRAP2, data); + + def = data = RREG32_PCIE(smnRCC_EP_DEV0_0_EP_PCIE_TX_LTR_CNTL); + data &= ~EP_PCIE_TX_LTR_CNTL__LTR_PRIV_MSG_DIS_IN_PM_NON_D0_MASK; + if (def != data) + WREG32_PCIE(smnRCC_EP_DEV0_0_EP_PCIE_TX_LTR_CNTL, data); + + def = data = RREG32_PCIE(smnBIF_CFG_DEV0_EPF0_DEVICE_CNTL2); + data |= BIF_CFG_DEV0_EPF0_DEVICE_CNTL2__LTR_EN_MASK; + if (def != data) + WREG32_PCIE(smnBIF_CFG_DEV0_EPF0_DEVICE_CNTL2, data); +} + +static void nbio_v6_1_program_aspm(struct amdgpu_device *adev) +{ + uint32_t def, data; + + def = data = RREG32_PCIE(smnPCIE_LC_CNTL); + data &= ~PCIE_LC_CNTL__LC_L1_INACTIVITY_MASK; + data &= ~PCIE_LC_CNTL__LC_L0S_INACTIVITY_MASK; + data |= PCIE_LC_CNTL__LC_PMI_TO_L1_DIS_MASK; + if (def != data) + WREG32_PCIE(smnPCIE_LC_CNTL, data); + + def = data = RREG32_PCIE(smnPCIE_LC_CNTL7); + data |= PCIE_LC_CNTL7__LC_NBIF_ASPM_INPUT_EN_MASK; + if (def != data) + WREG32_PCIE(smnPCIE_LC_CNTL7, data); + + def = data = RREG32_PCIE(smnNBIF_MGCG_CTRL_LCLK); + data |= NBIF_MGCG_CTRL_LCLK__NBIF_MGCG_REG_DIS_LCLK_MASK; + if (def != data) + WREG32_PCIE(smnNBIF_MGCG_CTRL_LCLK, data); + + def = data = RREG32_PCIE(smnPCIE_LC_CNTL3); + data |= PCIE_LC_CNTL3__LC_DSC_DONT_ENTER_L23_AFTER_PME_ACK_MASK; + if (def != data) + WREG32_PCIE(smnPCIE_LC_CNTL3, data); + + def = data = RREG32_PCIE(smnRCC_BIF_STRAP3); + data &= ~RCC_BIF_STRAP3__STRAP_VLINK_ASPM_IDLE_TIMER_MASK; + data &= ~RCC_BIF_STRAP3__STRAP_VLINK_PM_L1_ENTRY_TIMER_MASK; + if (def != data) + WREG32_PCIE(smnRCC_BIF_STRAP3, data); + + def = data = RREG32_PCIE(smnRCC_BIF_STRAP5); + data &= ~RCC_BIF_STRAP5__STRAP_VLINK_LDN_ENTRY_TIMER_MASK; + if (def != data) + WREG32_PCIE(smnRCC_BIF_STRAP5, data); + + def = data = RREG32_PCIE(smnBIF_CFG_DEV0_EPF0_DEVICE_CNTL2); + data &= ~BIF_CFG_DEV0_EPF0_DEVICE_CNTL2__LTR_EN_MASK; + if (def != data) + WREG32_PCIE(smnBIF_CFG_DEV0_EPF0_DEVICE_CNTL2, data); + + WREG32_PCIE(smnBIF_CFG_DEV0_EPF0_PCIE_LTR_CAP, 0x10011001); + + def = data = RREG32_PCIE(smnPSWUSP0_PCIE_LC_CNTL2); + data |= PSWUSP0_PCIE_LC_CNTL2__LC_ALLOW_PDWN_IN_L1_MASK | + PSWUSP0_PCIE_LC_CNTL2__LC_ALLOW_PDWN_IN_L23_MASK; + data &= ~PSWUSP0_PCIE_LC_CNTL2__LC_RCV_L0_TO_RCV_L0S_DIS_MASK; + if (def != data) + WREG32_PCIE(smnPSWUSP0_PCIE_LC_CNTL2, data); + + def = data = RREG32_PCIE(smnPCIE_LC_CNTL6); + data |= PCIE_LC_CNTL6__LC_L1_POWERDOWN_MASK | + PCIE_LC_CNTL6__LC_RX_L0S_STANDBY_EN_MASK; + if (def != data) + WREG32_PCIE(smnPCIE_LC_CNTL6, data); + + nbio_v6_1_program_ltr(adev); + + def = data = RREG32_PCIE(smnRCC_BIF_STRAP3); + data |= 0x5DE0 << RCC_BIF_STRAP3__STRAP_VLINK_ASPM_IDLE_TIMER__SHIFT; + data |= 0x0010 << RCC_BIF_STRAP3__STRAP_VLINK_PM_L1_ENTRY_TIMER__SHIFT; + if (def != data) + WREG32_PCIE(smnRCC_BIF_STRAP3, data); + + def = data = RREG32_PCIE(smnRCC_BIF_STRAP5); + data |= 0x0010 << RCC_BIF_STRAP5__STRAP_VLINK_LDN_ENTRY_TIMER__SHIFT; + if (def != data) + WREG32_PCIE(smnRCC_BIF_STRAP5, data); + + def = data = RREG32_PCIE(smnPCIE_LC_CNTL); + data &= ~PCIE_LC_CNTL__LC_L0S_INACTIVITY_MASK; + data |= 0x9 << PCIE_LC_CNTL__LC_L1_INACTIVITY__SHIFT; + data |= 0x1 << PCIE_LC_CNTL__LC_PMI_TO_L1_DIS__SHIFT; + if (def != data) + WREG32_PCIE(smnPCIE_LC_CNTL, data); + + def = data = RREG32_PCIE(smnPCIE_LC_CNTL3); + data &= ~PCIE_LC_CNTL3__LC_DSC_DONT_ENTER_L23_AFTER_PME_ACK_MASK; + if (def != data) + WREG32_PCIE(smnPCIE_LC_CNTL3, data); +} + const struct amdgpu_nbio_funcs nbio_v6_1_funcs = { .get_hdp_flush_req_offset = nbio_v6_1_get_hdp_flush_req_offset, .get_hdp_flush_done_offset = nbio_v6_1_get_hdp_flush_done_offset, @@ -274,4 +401,5 @@ const struct amdgpu_nbio_funcs nbio_v6_1_funcs = { .ih_control = nbio_v6_1_ih_control, .init_registers = nbio_v6_1_init_registers, .remap_hdp_registers = nbio_v6_1_remap_hdp_registers, + .program_aspm = nbio_v6_1_program_aspm, }; diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c index c477f8972d5d..cef929746739 100644 --- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c +++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c @@ -31,7 +31,26 @@ #include "ivsrcid/nbio/irqsrcs_nbif_7_4.h" #include <uapi/linux/kfd_ioctl.h> +#define smnPCIE_LC_CNTL 0x11140280 +#define smnPCIE_LC_CNTL3 0x111402d4 +#define smnPCIE_LC_CNTL6 0x111402ec +#define smnPCIE_LC_CNTL7 0x111402f0 #define smnNBIF_MGCG_CTRL_LCLK 0x1013a21c +#define smnRCC_BIF_STRAP3 0x1012348c +#define RCC_BIF_STRAP3__STRAP_VLINK_ASPM_IDLE_TIMER_MASK 0x0000FFFFL +#define RCC_BIF_STRAP3__STRAP_VLINK_PM_L1_ENTRY_TIMER_MASK 0xFFFF0000L +#define smnRCC_BIF_STRAP5 0x10123494 +#define RCC_BIF_STRAP5__STRAP_VLINK_LDN_ENTRY_TIMER_MASK 0x0000FFFFL +#define smnBIF_CFG_DEV0_EPF0_DEVICE_CNTL2 0x1014008c +#define BIF_CFG_DEV0_EPF0_DEVICE_CNTL2__LTR_EN_MASK 0x0400L +#define smnBIF_CFG_DEV0_EPF0_PCIE_LTR_CAP 0x10140324 +#define smnPSWUSP0_PCIE_LC_CNTL2 0x111402c4 +#define smnRCC_EP_DEV0_0_EP_PCIE_TX_LTR_CNTL 0x10123538 +#define smnRCC_BIF_STRAP2 0x10123488 +#define RCC_BIF_STRAP2__STRAP_LTR_IN_ASPML1_DIS_MASK 0x00004000L +#define RCC_BIF_STRAP3__STRAP_VLINK_ASPM_IDLE_TIMER__SHIFT 0x0 +#define RCC_BIF_STRAP3__STRAP_VLINK_PM_L1_ENTRY_TIMER__SHIFT 0x10 +#define RCC_BIF_STRAP5__STRAP_VLINK_LDN_ENTRY_TIMER__SHIFT 0x0 /* * These are nbio v7_4_1 registers mask. Temporarily define these here since @@ -557,6 +576,121 @@ static void nbio_v7_4_enable_doorbell_interrupt(struct amdgpu_device *adev, DOORBELL_INTERRUPT_DISABLE, enable ? 0 : 1); } +const struct amdgpu_nbio_ras_funcs nbio_v7_4_ras_funcs = { + .handle_ras_controller_intr_no_bifring = nbio_v7_4_handle_ras_controller_intr_no_bifring, + .handle_ras_err_event_athub_intr_no_bifring = nbio_v7_4_handle_ras_err_event_athub_intr_no_bifring, + .init_ras_controller_interrupt = nbio_v7_4_init_ras_controller_interrupt, + .init_ras_err_event_athub_interrupt = nbio_v7_4_init_ras_err_event_athub_interrupt, + .query_ras_error_count = nbio_v7_4_query_ras_error_count, + .ras_late_init = amdgpu_nbio_ras_late_init, + .ras_fini = amdgpu_nbio_ras_fini, +}; + +static void nbio_v7_4_program_ltr(struct amdgpu_device *adev) +{ + uint32_t def, data; + + WREG32_PCIE(smnRCC_EP_DEV0_0_EP_PCIE_TX_LTR_CNTL, 0x75EB); + + def = data = RREG32_PCIE(smnRCC_BIF_STRAP2); + data &= ~RCC_BIF_STRAP2__STRAP_LTR_IN_ASPML1_DIS_MASK; + if (def != data) + WREG32_PCIE(smnRCC_BIF_STRAP2, data); + + def = data = RREG32_PCIE(smnRCC_EP_DEV0_0_EP_PCIE_TX_LTR_CNTL); + data &= ~EP_PCIE_TX_LTR_CNTL__LTR_PRIV_MSG_DIS_IN_PM_NON_D0_MASK; + if (def != data) + WREG32_PCIE(smnRCC_EP_DEV0_0_EP_PCIE_TX_LTR_CNTL, data); + + def = data = RREG32_PCIE(smnBIF_CFG_DEV0_EPF0_DEVICE_CNTL2); + data |= BIF_CFG_DEV0_EPF0_DEVICE_CNTL2__LTR_EN_MASK; + if (def != data) + WREG32_PCIE(smnBIF_CFG_DEV0_EPF0_DEVICE_CNTL2, data); +} + +static void nbio_v7_4_program_aspm(struct amdgpu_device *adev) +{ + uint32_t def, data; + + def = data = RREG32_PCIE(smnPCIE_LC_CNTL); + data &= ~PCIE_LC_CNTL__LC_L1_INACTIVITY_MASK; + data &= ~PCIE_LC_CNTL__LC_L0S_INACTIVITY_MASK; + data |= PCIE_LC_CNTL__LC_PMI_TO_L1_DIS_MASK; + if (def != data) + WREG32_PCIE(smnPCIE_LC_CNTL, data); + + def = data = RREG32_PCIE(smnPCIE_LC_CNTL7); + data |= PCIE_LC_CNTL7__LC_NBIF_ASPM_INPUT_EN_MASK; + if (def != data) + WREG32_PCIE(smnPCIE_LC_CNTL7, data); + + def = data = RREG32_PCIE(smnNBIF_MGCG_CTRL_LCLK); + data |= NBIF_MGCG_CTRL_LCLK__NBIF_MGCG_REG_DIS_LCLK_MASK; + if (def != data) + WREG32_PCIE(smnNBIF_MGCG_CTRL_LCLK, data); + + def = data = RREG32_PCIE(smnPCIE_LC_CNTL3); + data |= PCIE_LC_CNTL3__LC_DSC_DONT_ENTER_L23_AFTER_PME_ACK_MASK; + if (def != data) + WREG32_PCIE(smnPCIE_LC_CNTL3, data); + + def = data = RREG32_PCIE(smnRCC_BIF_STRAP3); + data &= ~RCC_BIF_STRAP3__STRAP_VLINK_ASPM_IDLE_TIMER_MASK; + data &= ~RCC_BIF_STRAP3__STRAP_VLINK_PM_L1_ENTRY_TIMER_MASK; + if (def != data) + WREG32_PCIE(smnRCC_BIF_STRAP3, data); + + def = data = RREG32_PCIE(smnRCC_BIF_STRAP5); + data &= ~RCC_BIF_STRAP5__STRAP_VLINK_LDN_ENTRY_TIMER_MASK; + if (def != data) + WREG32_PCIE(smnRCC_BIF_STRAP5, data); + + def = data = RREG32_PCIE(smnBIF_CFG_DEV0_EPF0_DEVICE_CNTL2); + data &= ~BIF_CFG_DEV0_EPF0_DEVICE_CNTL2__LTR_EN_MASK; + if (def != data) + WREG32_PCIE(smnBIF_CFG_DEV0_EPF0_DEVICE_CNTL2, data); + + WREG32_PCIE(smnBIF_CFG_DEV0_EPF0_PCIE_LTR_CAP, 0x10011001); + + def = data = RREG32_PCIE(smnPSWUSP0_PCIE_LC_CNTL2); + data |= PSWUSP0_PCIE_LC_CNTL2__LC_ALLOW_PDWN_IN_L1_MASK | + PSWUSP0_PCIE_LC_CNTL2__LC_ALLOW_PDWN_IN_L23_MASK; + data &= ~PSWUSP0_PCIE_LC_CNTL2__LC_RCV_L0_TO_RCV_L0S_DIS_MASK; + if (def != data) + WREG32_PCIE(smnPSWUSP0_PCIE_LC_CNTL2, data); + + def = data = RREG32_PCIE(smnPCIE_LC_CNTL6); + data |= PCIE_LC_CNTL6__LC_L1_POWERDOWN_MASK | + PCIE_LC_CNTL6__LC_RX_L0S_STANDBY_EN_MASK; + if (def != data) + WREG32_PCIE(smnPCIE_LC_CNTL6, data); + + nbio_v7_4_program_ltr(adev); + + def = data = RREG32_PCIE(smnRCC_BIF_STRAP3); + data |= 0x5DE0 << RCC_BIF_STRAP3__STRAP_VLINK_ASPM_IDLE_TIMER__SHIFT; + data |= 0x0010 << RCC_BIF_STRAP3__STRAP_VLINK_PM_L1_ENTRY_TIMER__SHIFT; + if (def != data) + WREG32_PCIE(smnRCC_BIF_STRAP3, data); + + def = data = RREG32_PCIE(smnRCC_BIF_STRAP5); + data |= 0x0010 << RCC_BIF_STRAP5__STRAP_VLINK_LDN_ENTRY_TIMER__SHIFT; + if (def != data) + WREG32_PCIE(smnRCC_BIF_STRAP5, data); + + def = data = RREG32_PCIE(smnPCIE_LC_CNTL); + data &= ~PCIE_LC_CNTL__LC_L0S_INACTIVITY_MASK; + data |= 0x9 << PCIE_LC_CNTL__LC_L1_INACTIVITY__SHIFT; + data |= 0x1 << PCIE_LC_CNTL__LC_PMI_TO_L1_DIS__SHIFT; + if (def != data) + WREG32_PCIE(smnPCIE_LC_CNTL, data); + + def = data = RREG32_PCIE(smnPCIE_LC_CNTL3); + data &= ~PCIE_LC_CNTL3__LC_DSC_DONT_ENTER_L23_AFTER_PME_ACK_MASK; + if (def != data) + WREG32_PCIE(smnPCIE_LC_CNTL3, data); +} + const struct amdgpu_nbio_funcs nbio_v7_4_funcs = { .get_hdp_flush_req_offset = nbio_v7_4_get_hdp_flush_req_offset, .get_hdp_flush_done_offset = nbio_v7_4_get_hdp_flush_done_offset, @@ -577,10 +711,5 @@ const struct amdgpu_nbio_funcs nbio_v7_4_funcs = { .ih_control = nbio_v7_4_ih_control, .init_registers = nbio_v7_4_init_registers, .remap_hdp_registers = nbio_v7_4_remap_hdp_registers, - .handle_ras_controller_intr_no_bifring = nbio_v7_4_handle_ras_controller_intr_no_bifring, - .handle_ras_err_event_athub_intr_no_bifring = nbio_v7_4_handle_ras_err_event_athub_intr_no_bifring, - .init_ras_controller_interrupt = nbio_v7_4_init_ras_controller_interrupt, - .init_ras_err_event_athub_interrupt = nbio_v7_4_init_ras_err_event_athub_interrupt, - .query_ras_error_count = nbio_v7_4_query_ras_error_count, - .ras_late_init = amdgpu_nbio_ras_late_init, + .program_aspm = nbio_v7_4_program_aspm, }; diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.h b/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.h index b1ac82872752..b8216581ec8d 100644 --- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.h +++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.h @@ -28,5 +28,6 @@ extern const struct nbio_hdp_flush_reg nbio_v7_4_hdp_flush_reg; extern const struct amdgpu_nbio_funcs nbio_v7_4_funcs; +extern const struct amdgpu_nbio_ras_funcs nbio_v7_4_ras_funcs; #endif diff --git a/drivers/gpu/drm/amd/amdgpu/nv.c b/drivers/gpu/drm/amd/amdgpu/nv.c index 5846eac292c3..d54af7f8801b 100644 --- a/drivers/gpu/drm/amd/amdgpu/nv.c +++ b/drivers/gpu/drm/amd/amdgpu/nv.c @@ -34,7 +34,6 @@ #include "amdgpu_vce.h" #include "amdgpu_ucode.h" #include "amdgpu_psp.h" -#include "amdgpu_smu.h" #include "atom.h" #include "amd_pcie.h" @@ -516,21 +515,9 @@ static int nv_asic_mode2_reset(struct amdgpu_device *adev) return ret; } -static bool nv_asic_supports_baco(struct amdgpu_device *adev) -{ - struct smu_context *smu = &adev->smu; - - if (smu_baco_is_support(smu)) - return true; - else - return false; -} - static enum amd_reset_method nv_asic_reset_method(struct amdgpu_device *adev) { - struct smu_context *smu = &adev->smu; - if (amdgpu_reset_method == AMD_RESET_METHOD_MODE1 || amdgpu_reset_method == AMD_RESET_METHOD_MODE2 || amdgpu_reset_method == AMD_RESET_METHOD_BACO || @@ -549,7 +536,7 @@ nv_asic_reset_method(struct amdgpu_device *adev) case CHIP_DIMGREY_CAVEFISH: return AMD_RESET_METHOD_MODE1; default: - if (smu_baco_is_support(smu)) + if (amdgpu_dpm_is_baco_supported(adev)) return AMD_RESET_METHOD_BACO; else return AMD_RESET_METHOD_MODE1; @@ -559,11 +546,6 @@ nv_asic_reset_method(struct amdgpu_device *adev) static int nv_asic_reset(struct amdgpu_device *adev) { int ret = 0; - struct smu_context *smu = &adev->smu; - - /* skip reset on vangogh for now */ - if (adev->asic_type == CHIP_VANGOGH) - return 0; switch (nv_asic_reset_method(adev)) { case AMD_RESET_METHOD_PCI: @@ -572,13 +554,7 @@ static int nv_asic_reset(struct amdgpu_device *adev) break; case AMD_RESET_METHOD_BACO: dev_info(adev->dev, "BACO reset\n"); - - ret = smu_baco_enter(smu); - if (ret) - return ret; - ret = smu_baco_exit(smu); - if (ret) - return ret; + ret = amdgpu_dpm_baco_reset(adev); break; case AMD_RESET_METHOD_MODE2: dev_info(adev->dev, "MODE2 reset\n"); @@ -625,8 +601,7 @@ static void nv_program_aspm(struct amdgpu_device *adev) if (amdgpu_aspm != 1) return; - if ((adev->asic_type >= CHIP_SIENNA_CICHLID) && - !(adev->flags & AMD_IS_APU) && + if (!(adev->flags & AMD_IS_APU) && (adev->nbio.funcs->program_aspm)) adev->nbio.funcs->program_aspm(adev); @@ -958,12 +933,7 @@ static int nv_update_umd_stable_pstate(struct amdgpu_device *adev, if (adev->gfx.funcs->update_perfmon_mgcg) adev->gfx.funcs->update_perfmon_mgcg(adev, !enter); - /* - * The ASPM function is not fully enabled and verified on - * Navi yet. Temporarily skip this until ASPM enabled. - */ - if ((adev->asic_type >= CHIP_SIENNA_CICHLID) && - !(adev->flags & AMD_IS_APU) && + if (!(adev->flags & AMD_IS_APU) && (adev->nbio.funcs->enable_aspm)) adev->nbio.funcs->enable_aspm(adev, !enter); @@ -986,7 +956,7 @@ static const struct amdgpu_asic_funcs nv_asic_funcs = .need_full_reset = &nv_need_full_reset, .need_reset_on_init = &nv_need_reset_on_init, .get_pcie_replay_count = &nv_get_pcie_replay_count, - .supports_baco = &nv_asic_supports_baco, + .supports_baco = &amdgpu_dpm_is_baco_supported, .pre_asic_init = &nv_pre_asic_init, .update_umd_stable_pstate = &nv_update_umd_stable_pstate, .query_video_codecs = &nv_query_video_codecs, diff --git a/drivers/gpu/drm/amd/amdgpu/psp_gfx_if.h b/drivers/gpu/drm/amd/amdgpu/psp_gfx_if.h index a41b054fe0ba..96064c343163 100644 --- a/drivers/gpu/drm/amd/amdgpu/psp_gfx_if.h +++ b/drivers/gpu/drm/amd/amdgpu/psp_gfx_if.h @@ -102,6 +102,21 @@ enum psp_gfx_cmd_id /* IDs upto 0x1F are reserved for older programs (Raven, Vega 10/12/20) */ GFX_CMD_ID_LOAD_TOC = 0x00000020, /* Load TOC and obtain TMR size */ GFX_CMD_ID_AUTOLOAD_RLC = 0x00000021, /* Indicates all graphics fw loaded, start RLC autoload */ + GFX_CMD_ID_BOOT_CFG = 0x00000022, /* Boot Config */ +}; + +/* PSP boot config sub-commands */ +enum psp_gfx_boot_config_cmd +{ + BOOTCFG_CMD_SET = 1, /* Set boot configuration settings */ + BOOTCFG_CMD_GET = 2, /* Get boot configuration settings */ + BOOTCFG_CMD_INVALIDATE = 3 /* Reset current boot configuration settings to VBIOS defaults */ +}; + +/* PSP boot config bitmask values */ +enum psp_gfx_boot_config +{ + BOOT_CONFIG_GECC = 0x1, }; /* Command to load Trusted Application binary into PSP OS. */ @@ -170,10 +185,19 @@ struct psp_gfx_cmd_setup_tmr uint32_t buf_phy_addr_lo; /* bits [31:0] of GPU Virtual address of TMR buffer (must be 4 KB aligned) */ uint32_t buf_phy_addr_hi; /* bits [63:32] of GPU Virtual address of TMR buffer */ uint32_t buf_size; /* buffer size in bytes (must be multiple of 4 KB) */ + union { + struct { + uint32_t sriov_enabled:1; /* whether the device runs under SR-IOV*/ + uint32_t virt_phy_addr:1; /* driver passes both virtual and physical address to PSP*/ + uint32_t reserved:30; + } bitfield; + uint32_t tmr_flags; + }; + uint32_t system_phy_addr_lo; /* bits [31:0] of system physical address of TMR buffer (must be 4 KB aligned) */ + uint32_t system_phy_addr_hi; /* bits [63:32] of system physical address of TMR buffer */ }; - /* FW types for GFX_CMD_ID_LOAD_IP_FW command. Limit 31. */ enum psp_gfx_fw_type { GFX_FW_TYPE_NONE = 0, /* */ @@ -273,6 +297,15 @@ struct psp_gfx_cmd_load_toc uint32_t toc_size; /* FW buffer size in bytes */ }; +/* Dynamic boot configuration */ +struct psp_gfx_cmd_boot_cfg +{ + uint32_t timestamp; /* calendar time as number of seconds */ + enum psp_gfx_boot_config_cmd sub_cmd; /* sub-command indicating how to process command data */ + uint32_t boot_config; /* dynamic boot configuration bitmask */ + uint32_t boot_config_valid; /* dynamic boot configuration valid bits bitmask */ +}; + /* All GFX ring buffer commands. */ union psp_gfx_commands { @@ -285,6 +318,7 @@ union psp_gfx_commands struct psp_gfx_cmd_reg_prog cmd_setup_reg_prog; struct psp_gfx_cmd_setup_tmr cmd_setup_vmr; struct psp_gfx_cmd_load_toc cmd_load_toc; + struct psp_gfx_cmd_boot_cfg boot_cfg; }; struct psp_gfx_uresp_reserved diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c index c325d6f53a71..589410c32d09 100644 --- a/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c @@ -598,7 +598,7 @@ static int psp_v11_0_memory_training_send_msg(struct psp_context *psp, int msg) } /* - * save and restore proces + * save and restore process */ static int psp_v11_0_memory_training(struct psp_context *psp, uint32_t ops) { @@ -661,9 +661,9 @@ static int psp_v11_0_memory_training(struct psp_context *psp, uint32_t ops) if (ops & PSP_MEM_TRAIN_SEND_LONG_MSG) { /* - * Long traing will encroach certain mount of bottom VRAM, - * saving the content of this bottom VRAM to system memory - * before training, and restoring it after training to avoid + * Long training will encroach a certain amount on the bottom of VRAM; + * save the content from the bottom of VRAM to system memory + * before training, and restore it after training to avoid * VRAM corruption. */ sz = GDDR6_MEM_TRAINING_ENCROACHED_SIZE; diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c index eb5dc6c5b46e..9f0dda040ec8 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c @@ -876,12 +876,10 @@ static int sdma_v2_4_sw_init(void *handle) ring->ring_obj = NULL; ring->use_doorbell = false; sprintf(ring->name, "sdma%d", i); - r = amdgpu_ring_init(adev, ring, 1024, - &adev->sdma.trap_irq, - (i == 0) ? - AMDGPU_SDMA_IRQ_INSTANCE0 : + r = amdgpu_ring_init(adev, ring, 1024, &adev->sdma.trap_irq, + (i == 0) ? AMDGPU_SDMA_IRQ_INSTANCE0 : AMDGPU_SDMA_IRQ_INSTANCE1, - AMDGPU_RING_PRIO_DEFAULT); + AMDGPU_RING_PRIO_DEFAULT, NULL); if (r) return r; } diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c index ad308d8c6d30..135727b59c41 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c @@ -1160,12 +1160,10 @@ static int sdma_v3_0_sw_init(void *handle) } sprintf(ring->name, "sdma%d", i); - r = amdgpu_ring_init(adev, ring, 1024, - &adev->sdma.trap_irq, - (i == 0) ? - AMDGPU_SDMA_IRQ_INSTANCE0 : + r = amdgpu_ring_init(adev, ring, 1024, &adev->sdma.trap_irq, + (i == 0) ? AMDGPU_SDMA_IRQ_INSTANCE0 : AMDGPU_SDMA_IRQ_INSTANCE1, - AMDGPU_RING_PRIO_DEFAULT); + AMDGPU_RING_PRIO_DEFAULT, NULL); if (r) return r; } diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c index 98b7db516438..5715be6770ec 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c @@ -1968,7 +1968,7 @@ static int sdma_v4_0_sw_init(void *handle) sprintf(ring->name, "sdma%d", i); r = amdgpu_ring_init(adev, ring, 1024, &adev->sdma.trap_irq, AMDGPU_SDMA_IRQ_INSTANCE0 + i, - AMDGPU_RING_PRIO_DEFAULT); + AMDGPU_RING_PRIO_DEFAULT, NULL); if (r) return r; @@ -1987,7 +1987,7 @@ static int sdma_v4_0_sw_init(void *handle) r = amdgpu_ring_init(adev, ring, 1024, &adev->sdma.trap_irq, AMDGPU_SDMA_IRQ_INSTANCE0 + i, - AMDGPU_RING_PRIO_DEFAULT); + AMDGPU_RING_PRIO_DEFAULT, NULL); if (r) return r; } diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_4.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_4.c index 6fcb95c89999..bf95007f0843 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_4.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_4.c @@ -160,6 +160,7 @@ static const struct soc15_ras_field_entry sdma_v4_4_ras_fields[] = { }; static void sdma_v4_4_get_ras_error_count(struct amdgpu_device *adev, + uint32_t reg_offset, uint32_t value, uint32_t instance, uint32_t *sec_count) @@ -169,6 +170,9 @@ static void sdma_v4_4_get_ras_error_count(struct amdgpu_device *adev, /* double bits error (multiple bits) error detection is not supported */ for (i = 0; i < ARRAY_SIZE(sdma_v4_4_ras_fields); i++) { + if (sdma_v4_4_ras_fields[i].reg_offset != reg_offset) + continue; + /* the SDMA_EDC_COUNTER register in each sdma instance * shares the same sed shift_mask * */ @@ -197,13 +201,30 @@ static int sdma_v4_4_query_ras_error_count(struct amdgpu_device *adev, reg_value = RREG32(reg_offset); /* double bit error is not supported */ if (reg_value) - sdma_v4_4_get_ras_error_count(adev, reg_value, instance, &sec_count); - /* err_data->ce_count should be initialized to 0 - * before calling into this function */ - err_data->ce_count += sec_count; - /* double bit error is not supported - * set ue count to 0 */ - err_data->ue_count = 0; + sdma_v4_4_get_ras_error_count(adev, regSDMA0_EDC_COUNTER, reg_value, + instance, &sec_count); + + reg_offset = sdma_v4_4_get_reg_offset(adev, instance, regSDMA0_EDC_COUNTER2); + reg_value = RREG32(reg_offset); + /* double bit error is not supported */ + if (reg_value) + sdma_v4_4_get_ras_error_count(adev, regSDMA0_EDC_COUNTER2, reg_value, + instance, &sec_count); + + /* + * err_data->ue_count should be initialized to 0 + * before calling into this function + * + * SDMA RAS supports single bit uncorrectable error detection. + * So, increment uncorrectable error count. + */ + err_data->ue_count += sec_count; + + /* + * SDMA RAS does not support correctable errors. + * Set ce count to 0. + */ + err_data->ce_count = 0; return 0; }; diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c index d345e324837d..920fc6d4a127 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c @@ -1273,12 +1273,10 @@ static int sdma_v5_0_sw_init(void *handle) : (adev->doorbell_index.sdma_engine[1] << 1); // get DWORD offset sprintf(ring->name, "sdma%d", i); - r = amdgpu_ring_init(adev, ring, 1024, - &adev->sdma.trap_irq, - (i == 0) ? - AMDGPU_SDMA_IRQ_INSTANCE0 : + r = amdgpu_ring_init(adev, ring, 1024, &adev->sdma.trap_irq, + (i == 0) ? AMDGPU_SDMA_IRQ_INSTANCE0 : AMDGPU_SDMA_IRQ_INSTANCE1, - AMDGPU_RING_PRIO_DEFAULT); + AMDGPU_RING_PRIO_DEFAULT, NULL); if (r) return r; } diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c index b39e7db0e299..b1ad9e52b234 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c @@ -370,6 +370,33 @@ static void sdma_v5_2_ring_emit_ib(struct amdgpu_ring *ring, } /** + * sdma_v5_2_ring_emit_mem_sync - flush the IB by graphics cache rinse + * + * @ring: amdgpu ring pointer + * @job: job to retrieve vmid from + * @ib: IB object to schedule + * + * flush the IB by graphics cache rinse. + */ +static void sdma_v5_2_ring_emit_mem_sync(struct amdgpu_ring *ring) +{ + uint32_t gcr_cntl = + SDMA_GCR_GL2_INV | SDMA_GCR_GL2_WB | SDMA_GCR_GLM_INV | + SDMA_GCR_GL1_INV | SDMA_GCR_GLV_INV | SDMA_GCR_GLK_INV | + SDMA_GCR_GLI_INV(1); + + /* flush entire cache L0/L1/L2, this can be optimized by performance requirement */ + amdgpu_ring_write(ring, SDMA_PKT_HEADER_OP(SDMA_OP_GCR_REQ)); + amdgpu_ring_write(ring, SDMA_PKT_GCR_REQ_PAYLOAD1_BASE_VA_31_7(0)); + amdgpu_ring_write(ring, SDMA_PKT_GCR_REQ_PAYLOAD2_GCR_CONTROL_15_0(gcr_cntl) | + SDMA_PKT_GCR_REQ_PAYLOAD2_BASE_VA_47_32(0)); + amdgpu_ring_write(ring, SDMA_PKT_GCR_REQ_PAYLOAD3_LIMIT_VA_31_7(0) | + SDMA_PKT_GCR_REQ_PAYLOAD3_GCR_CONTROL_18_16(gcr_cntl >> 16)); + amdgpu_ring_write(ring, SDMA_PKT_GCR_REQ_PAYLOAD4_LIMIT_VA_47_32(0) | + SDMA_PKT_GCR_REQ_PAYLOAD4_VMID(0)); +} + +/** * sdma_v5_2_ring_emit_hdp_flush - emit an hdp flush on the DMA ring * * @ring: amdgpu ring pointer @@ -1283,10 +1310,9 @@ static int sdma_v5_2_sw_init(void *handle) (adev->doorbell_index.sdma_engine[i] << 1); //get DWORD offset sprintf(ring->name, "sdma%d", i); - r = amdgpu_ring_init(adev, ring, 1024, - &adev->sdma.trap_irq, + r = amdgpu_ring_init(adev, ring, 1024, &adev->sdma.trap_irq, AMDGPU_SDMA_IRQ_INSTANCE0 + i, - AMDGPU_RING_PRIO_DEFAULT); + AMDGPU_RING_PRIO_DEFAULT, NULL); if (r) return r; } @@ -1664,6 +1690,7 @@ static const struct amdgpu_ring_funcs sdma_v5_2_ring_funcs = { 10 + 10 + 10, /* sdma_v5_2_ring_emit_fence x3 for user fence, vm fence */ .emit_ib_size = 7 + 6, /* sdma_v5_2_ring_emit_ib */ .emit_ib = sdma_v5_2_ring_emit_ib, + .emit_mem_sync = sdma_v5_2_ring_emit_mem_sync, .emit_fence = sdma_v5_2_ring_emit_fence, .emit_pipeline_sync = sdma_v5_2_ring_emit_pipeline_sync, .emit_vm_flush = sdma_v5_2_ring_emit_vm_flush, diff --git a/drivers/gpu/drm/amd/amdgpu/si_dma.c b/drivers/gpu/drm/amd/amdgpu/si_dma.c index 488497ad5e0c..cb703e307238 100644 --- a/drivers/gpu/drm/amd/amdgpu/si_dma.c +++ b/drivers/gpu/drm/amd/amdgpu/si_dma.c @@ -507,10 +507,9 @@ static int si_dma_sw_init(void *handle) sprintf(ring->name, "sdma%d", i); r = amdgpu_ring_init(adev, ring, 1024, &adev->sdma.trap_irq, - (i == 0) ? - AMDGPU_SDMA_IRQ_INSTANCE0 : + (i == 0) ? AMDGPU_SDMA_IRQ_INSTANCE0 : AMDGPU_SDMA_IRQ_INSTANCE1, - AMDGPU_RING_PRIO_DEFAULT); + AMDGPU_RING_PRIO_DEFAULT, NULL); if (r) return r; } diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c index 3808402cd964..d80e12b80c7e 100644 --- a/drivers/gpu/drm/amd/amdgpu/soc15.c +++ b/drivers/gpu/drm/amd/amdgpu/soc15.c @@ -76,7 +76,6 @@ #include "smuio_v13_0.h" #include "dce_virtual.h" #include "mxgpu_ai.h" -#include "amdgpu_smu.h" #include "amdgpu_ras.h" #include "amdgpu_xgmi.h" #include <uapi/linux/kfd_ioctl.h> @@ -817,11 +816,12 @@ static void soc15_pcie_gen3_enable(struct amdgpu_device *adev) static void soc15_program_aspm(struct amdgpu_device *adev) { - - if (amdgpu_aspm == 0) + if (amdgpu_aspm != 1) return; - /* todo */ + if (!(adev->flags & AMD_IS_APU) && + (adev->nbio.funcs->program_aspm)) + adev->nbio.funcs->program_aspm(adev); } static void soc15_enable_doorbell_aperture(struct amdgpu_device *adev, @@ -1495,8 +1495,8 @@ static int soc15_common_early_init(void *handle) AMD_CG_SUPPORT_HDP_LS | AMD_CG_SUPPORT_SDMA_MGCG | AMD_CG_SUPPORT_SDMA_LS | - AMD_CG_SUPPORT_IH_CG; - /*AMD_CG_SUPPORT_VCN_MGCG |AMD_CG_SUPPORT_JPEG_MGCG;*/ + AMD_CG_SUPPORT_IH_CG | + AMD_CG_SUPPORT_VCN_MGCG | AMD_CG_SUPPORT_JPEG_MGCG; adev->pg_flags = AMD_PG_SUPPORT_VCN_DPG; adev->external_rev_id = adev->rev_id + 0x3c; break; @@ -1524,8 +1524,9 @@ static int soc15_common_late_init(void *handle) if (adev->hdp.funcs->reset_ras_error_count) adev->hdp.funcs->reset_ras_error_count(adev); - if (adev->nbio.funcs->ras_late_init) - r = adev->nbio.funcs->ras_late_init(adev); + if (adev->nbio.ras_funcs && + adev->nbio.ras_funcs->ras_late_init) + r = adev->nbio.ras_funcs->ras_late_init(adev); return r; } @@ -1546,7 +1547,9 @@ static int soc15_common_sw_fini(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; - amdgpu_nbio_ras_fini(adev); + if (adev->nbio.ras_funcs && + adev->nbio.ras_funcs->ras_fini) + adev->nbio.ras_funcs->ras_fini(adev); adev->df.funcs->sw_fini(adev); return 0; } @@ -1610,9 +1613,11 @@ static int soc15_common_hw_fini(void *handle) if (adev->nbio.ras_if && amdgpu_ras_is_supported(adev, adev->nbio.ras_if->block)) { - if (adev->nbio.funcs->init_ras_controller_interrupt) + if (adev->nbio.ras_funcs && + adev->nbio.ras_funcs->init_ras_controller_interrupt) amdgpu_irq_put(adev, &adev->nbio.ras_controller_irq, 0); - if (adev->nbio.funcs->init_ras_err_event_athub_interrupt) + if (adev->nbio.ras_funcs && + adev->nbio.ras_funcs->init_ras_err_event_athub_interrupt) amdgpu_irq_put(adev, &adev->nbio.ras_err_event_athub_irq, 0); } diff --git a/drivers/gpu/drm/amd/amdgpu/soc15_common.h b/drivers/gpu/drm/amd/amdgpu/soc15_common.h index 8cdf5d1685cb..14bd794bbea6 100644 --- a/drivers/gpu/drm/amd/amdgpu/soc15_common.h +++ b/drivers/gpu/drm/amd/amdgpu/soc15_common.h @@ -77,27 +77,11 @@ }) #define WREG32_RLC(reg, value) \ - do { \ - if (amdgpu_sriov_fullaccess(adev)) { \ - uint32_t i = 0; \ - uint32_t retries = 50000; \ - uint32_t r0 = adev->reg_offset[GC_HWIP][0][mmSCRATCH_REG0_BASE_IDX] + mmSCRATCH_REG0; \ - uint32_t r1 = adev->reg_offset[GC_HWIP][0][mmSCRATCH_REG1_BASE_IDX] + mmSCRATCH_REG1; \ - uint32_t spare_int = adev->reg_offset[GC_HWIP][0][mmRLC_SPARE_INT_BASE_IDX] + mmRLC_SPARE_INT; \ - WREG32(r0, value); \ - WREG32(r1, (reg | 0x80000000)); \ - WREG32(spare_int, 0x1); \ - for (i = 0; i < retries; i++) { \ - u32 tmp = RREG32(r1); \ - if (!(tmp & 0x80000000)) \ - break; \ - udelay(10); \ - } \ - if (i >= retries) \ - pr_err("timeout: rlcg program reg:0x%05x failed !\n", reg); \ - } else { \ - WREG32(reg, value); \ - } \ + do { \ + if (adev->gfx.rlc.funcs->rlcg_wreg) \ + adev->gfx.rlc.funcs->rlcg_wreg(adev, reg, value, 0); \ + else \ + WREG32(reg, value); \ } while (0) #define WREG32_RLC_EX(prefix, reg, value) \ @@ -125,23 +109,24 @@ } while (0) #define WREG32_SOC15_RLC_SHADOW(ip, inst, reg, value) \ - do { \ - uint32_t target_reg = adev->reg_offset[ip##_HWIP][inst][reg##_BASE_IDX] + reg;\ - if (amdgpu_sriov_fullaccess(adev)) { \ - uint32_t r2 = adev->reg_offset[GC_HWIP][0][mmSCRATCH_REG1_BASE_IDX] + mmSCRATCH_REG2; \ - uint32_t r3 = adev->reg_offset[GC_HWIP][0][mmSCRATCH_REG1_BASE_IDX] + mmSCRATCH_REG3; \ - uint32_t grbm_cntl = adev->reg_offset[GC_HWIP][0][mmGRBM_GFX_CNTL_BASE_IDX] + mmGRBM_GFX_CNTL; \ - uint32_t grbm_idx = adev->reg_offset[GC_HWIP][0][mmGRBM_GFX_INDEX_BASE_IDX] + mmGRBM_GFX_INDEX; \ - if (target_reg == grbm_cntl) \ - WREG32(r2, value); \ - else if (target_reg == grbm_idx) \ - WREG32(r3, value); \ - WREG32(target_reg, value); \ - } else { \ - WREG32(target_reg, value); \ - } \ + WREG32_RLC((adev->reg_offset[ip##_HWIP][inst][reg##_BASE_IDX] + reg), value) + +#define RREG32_RLC(reg) \ + (adev->gfx.rlc.funcs->rlcg_rreg ? \ + adev->gfx.rlc.funcs->rlcg_rreg(adev, reg, 0) : RREG32(reg)) + +#define WREG32_RLC_NO_KIQ(reg, value) \ + do { \ + if (adev->gfx.rlc.funcs->rlcg_wreg) \ + adev->gfx.rlc.funcs->rlcg_wreg(adev, reg, value, AMDGPU_REGS_NO_KIQ); \ + else \ + WREG32_NO_KIQ(reg, value); \ } while (0) +#define RREG32_RLC_NO_KIQ(reg) \ + (adev->gfx.rlc.funcs->rlcg_rreg ? \ + adev->gfx.rlc.funcs->rlcg_rreg(adev, reg, AMDGPU_REGS_NO_KIQ) : RREG32_NO_KIQ(reg)) + #define WREG32_SOC15_RLC_SHADOW_EX(prefix, ip, inst, reg, value) \ do { \ uint32_t target_reg = adev->reg_offset[ip##_HWIP][inst][reg##_BASE_IDX] + reg;\ @@ -160,10 +145,13 @@ } \ } while (0) +#define RREG32_SOC15_RLC(ip, inst, reg) \ + RREG32_RLC(adev->reg_offset[ip##_HWIP][inst][reg##_BASE_IDX] + reg) + #define WREG32_SOC15_RLC(ip, inst, reg, value) \ do { \ - uint32_t target_reg = adev->reg_offset[GC_HWIP][0][reg##_BASE_IDX] + reg;\ - WREG32_RLC(target_reg, value); \ + uint32_t target_reg = adev->reg_offset[ip##_HWIP][0][reg##_BASE_IDX] + reg;\ + WREG32_RLC(target_reg, value); \ } while (0) #define WREG32_SOC15_RLC_EX(prefix, ip, inst, reg, value) \ @@ -173,11 +161,14 @@ } while (0) #define WREG32_FIELD15_RLC(ip, idx, reg, field, val) \ - WREG32_RLC((adev->reg_offset[ip##_HWIP][idx][mm##reg##_BASE_IDX] + mm##reg), \ - (RREG32(adev->reg_offset[ip##_HWIP][idx][mm##reg##_BASE_IDX] + mm##reg) \ - & ~REG_FIELD_MASK(reg, field)) | (val) << REG_FIELD_SHIFT(reg, field)) + WREG32_RLC((adev->reg_offset[ip##_HWIP][idx][mm##reg##_BASE_IDX] + mm##reg), \ + (RREG32_RLC(adev->reg_offset[ip##_HWIP][idx][mm##reg##_BASE_IDX] + mm##reg) \ + & ~REG_FIELD_MASK(reg, field)) | (val) << REG_FIELD_SHIFT(reg, field)) #define WREG32_SOC15_OFFSET_RLC(ip, inst, reg, offset, value) \ - WREG32_RLC(((adev->reg_offset[ip##_HWIP][inst][reg##_BASE_IDX] + reg) + offset), value) + WREG32_RLC(((adev->reg_offset[ip##_HWIP][inst][reg##_BASE_IDX] + reg) + offset), value) + +#define RREG32_SOC15_OFFSET_RLC(ip, inst, reg, offset) \ + RREG32_RLC(((adev->reg_offset[ip##_HWIP][inst][reg##_BASE_IDX] + reg) + offset)) #endif diff --git a/drivers/gpu/drm/amd/amdgpu/umc_v6_1.c b/drivers/gpu/drm/amd/amdgpu/umc_v6_1.c index 96d7769609f4..20b44983ac94 100644 --- a/drivers/gpu/drm/amd/amdgpu/umc_v6_1.c +++ b/drivers/gpu/drm/amd/amdgpu/umc_v6_1.c @@ -22,6 +22,7 @@ */ #include "umc_v6_1.h" #include "amdgpu_ras.h" +#include "amdgpu_umc.h" #include "amdgpu.h" #include "rsmu/rsmu_0_0_2_offset.h" @@ -464,9 +465,10 @@ static void umc_v6_1_err_cnt_init(struct amdgpu_device *adev) umc_v6_1_enable_umc_index_mode(adev); } -const struct amdgpu_umc_funcs umc_v6_1_funcs = { +const struct amdgpu_umc_ras_funcs umc_v6_1_ras_funcs = { .err_cnt_init = umc_v6_1_err_cnt_init, .ras_late_init = amdgpu_umc_ras_late_init, + .ras_fini = amdgpu_umc_ras_fini, .query_ras_error_count = umc_v6_1_query_ras_error_count, .query_ras_error_address = umc_v6_1_query_ras_error_address, }; diff --git a/drivers/gpu/drm/amd/amdgpu/umc_v6_1.h b/drivers/gpu/drm/amd/amdgpu/umc_v6_1.h index 0ce1d323cfdd..5dc36c730bb2 100644 --- a/drivers/gpu/drm/amd/amdgpu/umc_v6_1.h +++ b/drivers/gpu/drm/amd/amdgpu/umc_v6_1.h @@ -45,7 +45,7 @@ /* umc ce count initial value */ #define UMC_V6_1_CE_CNT_INIT (UMC_V6_1_CE_CNT_MAX - UMC_V6_1_CE_INT_THRESHOLD) -extern const struct amdgpu_umc_funcs umc_v6_1_funcs; +extern const struct amdgpu_umc_ras_funcs umc_v6_1_ras_funcs; extern const uint32_t umc_v6_1_channel_idx_tbl[UMC_V6_1_UMC_INSTANCE_NUM][UMC_V6_1_CHANNEL_INSTANCE_NUM]; diff --git a/drivers/gpu/drm/amd/amdgpu/umc_v6_7.c b/drivers/gpu/drm/amd/amdgpu/umc_v6_7.c new file mode 100644 index 000000000000..3a8f787374c0 --- /dev/null +++ b/drivers/gpu/drm/amd/amdgpu/umc_v6_7.c @@ -0,0 +1,281 @@ +/* + * Copyright 2021 Advanced Micro Devices, Inc. + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR + * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, + * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR + * OTHER DEALINGS IN THE SOFTWARE. + * + */ +#include "umc_v6_7.h" +#include "amdgpu_ras.h" +#include "amdgpu_umc.h" +#include "amdgpu.h" + +#include "umc/umc_6_7_0_offset.h" +#include "umc/umc_6_7_0_sh_mask.h" + +static inline uint32_t get_umc_v6_7_reg_offset(struct amdgpu_device *adev, + uint32_t umc_inst, + uint32_t ch_inst) +{ + return adev->umc.channel_offs * ch_inst + UMC_V6_7_INST_DIST * umc_inst; +} + +static void umc_v6_7_query_correctable_error_count(struct amdgpu_device *adev, + uint32_t umc_reg_offset, + unsigned long *error_count) +{ + uint32_t ecc_err_cnt_sel, ecc_err_cnt_sel_addr; + uint32_t ecc_err_cnt, ecc_err_cnt_addr; + uint64_t mc_umc_status; + uint32_t mc_umc_status_addr; + + /* UMC 6_1_1 registers */ + ecc_err_cnt_sel_addr = + SOC15_REG_OFFSET(UMC, 0, regUMCCH0_0_EccErrCntSel); + ecc_err_cnt_addr = + SOC15_REG_OFFSET(UMC, 0, regUMCCH0_0_EccErrCnt); + mc_umc_status_addr = + SOC15_REG_OFFSET(UMC, 0, regMCA_UMC_UMC0_MCUMC_STATUST0); + + /* select the lower chip and check the error count */ + ecc_err_cnt_sel = RREG32_PCIE((ecc_err_cnt_sel_addr + umc_reg_offset) * 4); + ecc_err_cnt_sel = REG_SET_FIELD(ecc_err_cnt_sel, UMCCH0_0_EccErrCntSel, + EccErrCntCsSel, 0); + WREG32_PCIE((ecc_err_cnt_sel_addr + umc_reg_offset) * 4, ecc_err_cnt_sel); + + ecc_err_cnt = RREG32_PCIE((ecc_err_cnt_addr + umc_reg_offset) * 4); + *error_count += + (REG_GET_FIELD(ecc_err_cnt, UMCCH0_0_EccErrCnt, EccErrCnt) - + UMC_V6_7_CE_CNT_INIT); + + /* select the higher chip and check the err counter */ + ecc_err_cnt_sel = REG_SET_FIELD(ecc_err_cnt_sel, UMCCH0_0_EccErrCntSel, + EccErrCntCsSel, 1); + WREG32_PCIE((ecc_err_cnt_sel_addr + umc_reg_offset) * 4, ecc_err_cnt_sel); + + ecc_err_cnt = RREG32_PCIE((ecc_err_cnt_addr + umc_reg_offset) * 4); + *error_count += + (REG_GET_FIELD(ecc_err_cnt, UMCCH0_0_EccErrCnt, EccErrCnt) - + UMC_V6_7_CE_CNT_INIT); + + /* check for SRAM correctable error + MCUMC_STATUS is a 64 bit register */ + mc_umc_status = RREG64_PCIE((mc_umc_status_addr + umc_reg_offset) * 4); + if (REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, Val) == 1 && + REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, CECC) == 1) + *error_count += 1; +} + +static void umc_v6_7_querry_uncorrectable_error_count(struct amdgpu_device *adev, + uint32_t umc_reg_offset, + unsigned long *error_count) +{ + uint64_t mc_umc_status; + uint32_t mc_umc_status_addr; + + mc_umc_status_addr = + SOC15_REG_OFFSET(UMC, 0, regMCA_UMC_UMC0_MCUMC_STATUST0); + + /* check the MCUMC_STATUS */ + mc_umc_status = RREG64_PCIE((mc_umc_status_addr + umc_reg_offset) * 4); + if ((REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, Val) == 1) && + (REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, Deferred) == 1 || + REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, UECC) == 1 || + REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, PCC) == 1 || + REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, UC) == 1 || + REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, TCC) == 1)) + *error_count += 1; +} + +static void umc_v6_7_reset_error_count_per_channel(struct amdgpu_device *adev, + uint32_t umc_reg_offset) +{ + uint32_t ecc_err_cnt_addr; + uint32_t ecc_err_cnt_sel, ecc_err_cnt_sel_addr; + + ecc_err_cnt_sel_addr = + SOC15_REG_OFFSET(UMC, 0, + regUMCCH0_0_EccErrCntSel); + ecc_err_cnt_addr = + SOC15_REG_OFFSET(UMC, 0, + regUMCCH0_0_EccErrCnt); + + /* select the lower chip */ + ecc_err_cnt_sel = RREG32_PCIE((ecc_err_cnt_sel_addr + + umc_reg_offset) * 4); + ecc_err_cnt_sel = REG_SET_FIELD(ecc_err_cnt_sel, + UMCCH0_0_EccErrCntSel, + EccErrCntCsSel, 0); + WREG32_PCIE((ecc_err_cnt_sel_addr + umc_reg_offset) * 4, + ecc_err_cnt_sel); + + /* clear lower chip error count */ + WREG32_PCIE((ecc_err_cnt_addr + umc_reg_offset) * 4, + UMC_V6_7_CE_CNT_INIT); + + /* select the higher chip */ + ecc_err_cnt_sel = RREG32_PCIE((ecc_err_cnt_sel_addr + + umc_reg_offset) * 4); + ecc_err_cnt_sel = REG_SET_FIELD(ecc_err_cnt_sel, + UMCCH0_0_EccErrCntSel, + EccErrCntCsSel, 1); + WREG32_PCIE((ecc_err_cnt_sel_addr + umc_reg_offset) * 4, + ecc_err_cnt_sel); + + /* clear higher chip error count */ + WREG32_PCIE((ecc_err_cnt_addr + umc_reg_offset) * 4, + UMC_V6_7_CE_CNT_INIT); +} + +static void umc_v6_7_reset_error_count(struct amdgpu_device *adev) +{ + uint32_t umc_inst = 0; + uint32_t ch_inst = 0; + uint32_t umc_reg_offset = 0; + + LOOP_UMC_INST_AND_CH(umc_inst, ch_inst) { + umc_reg_offset = get_umc_v6_7_reg_offset(adev, + umc_inst, + ch_inst); + + umc_v6_7_reset_error_count_per_channel(adev, + umc_reg_offset); + } +} + +static void umc_v6_7_query_ras_error_count(struct amdgpu_device *adev, + void *ras_error_status) +{ + struct ras_err_data *err_data = (struct ras_err_data *)ras_error_status; + + uint32_t umc_inst = 0; + uint32_t ch_inst = 0; + uint32_t umc_reg_offset = 0; + + /*TODO: driver needs to toggle DF Cstate to ensure + * safe access of UMC registers. Will add the protection */ + LOOP_UMC_INST_AND_CH(umc_inst, ch_inst) { + umc_reg_offset = get_umc_v6_7_reg_offset(adev, + umc_inst, + ch_inst); + umc_v6_7_query_correctable_error_count(adev, + umc_reg_offset, + &(err_data->ce_count)); + umc_v6_7_querry_uncorrectable_error_count(adev, + umc_reg_offset, + &(err_data->ue_count)); + } + + umc_v6_7_reset_error_count(adev); +} + +static void umc_v6_7_query_error_address(struct amdgpu_device *adev, + struct ras_err_data *err_data, + uint32_t umc_reg_offset, + uint32_t ch_inst, + uint32_t umc_inst) +{ + uint32_t mc_umc_status_addr; + uint64_t mc_umc_status, err_addr, retired_page, mc_umc_addrt0; + struct eeprom_table_record *err_rec; + uint32_t channel_index; + + mc_umc_status_addr = + SOC15_REG_OFFSET(UMC, 0, regMCA_UMC_UMC0_MCUMC_STATUST0); + mc_umc_addrt0 = + SOC15_REG_OFFSET(UMC, 0, regMCA_UMC_UMC0_MCUMC_ADDRT0); + + mc_umc_status = RREG64_PCIE((mc_umc_status_addr + umc_reg_offset) * 4); + + if (mc_umc_status == 0) + return; + + if (!err_data->err_addr) { + /* clear umc status */ + WREG64_PCIE((mc_umc_status_addr + umc_reg_offset) * 4, 0x0ULL); + return; + } + + err_rec = &err_data->err_addr[err_data->err_addr_cnt]; + + channel_index = + adev->umc.channel_idx_tbl[umc_inst * adev->umc.channel_inst_num + ch_inst]; + + /* calculate error address if ue/ce error is detected */ + if (REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, Val) == 1 && + (REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, UECC) == 1 || + REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, CECC) == 1)) { + + err_addr = RREG64_PCIE((mc_umc_addrt0 + umc_reg_offset) * 4); + err_addr = REG_GET_FIELD(err_addr, MCA_UMC_UMC0_MCUMC_ADDRT0, ErrorAddr); + + /* translate umc channel address to soc pa, 3 parts are included */ + retired_page = ADDR_OF_8KB_BLOCK(err_addr) | + ADDR_OF_256B_BLOCK(channel_index) | + OFFSET_IN_256B_BLOCK(err_addr); + + /* we only save ue error information currently, ce is skipped */ + if (REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, UECC) + == 1) { + err_rec->address = err_addr; + /* page frame address is saved */ + err_rec->retired_page = retired_page >> AMDGPU_GPU_PAGE_SHIFT; + err_rec->ts = (uint64_t)ktime_get_real_seconds(); + err_rec->err_type = AMDGPU_RAS_EEPROM_ERR_NON_RECOVERABLE; + err_rec->cu = 0; + err_rec->mem_channel = channel_index; + err_rec->mcumc_id = umc_inst; + + err_data->err_addr_cnt++; + } + } + + /* clear umc status */ + WREG64_PCIE((mc_umc_status_addr + umc_reg_offset) * 4, 0x0ULL); +} + +static void umc_v6_7_query_ras_error_address(struct amdgpu_device *adev, + void *ras_error_status) +{ + struct ras_err_data *err_data = (struct ras_err_data *)ras_error_status; + + uint32_t umc_inst = 0; + uint32_t ch_inst = 0; + uint32_t umc_reg_offset = 0; + + /*TODO: driver needs to toggle DF Cstate to ensure + * safe access of UMC resgisters. Will add the protection + * when firmware interface is ready */ + LOOP_UMC_INST_AND_CH(umc_inst, ch_inst) { + umc_reg_offset = get_umc_v6_7_reg_offset(adev, + umc_inst, + ch_inst); + umc_v6_7_query_error_address(adev, + err_data, + umc_reg_offset, + ch_inst, + umc_inst); + } +} + +const struct amdgpu_umc_ras_funcs umc_v6_7_ras_funcs = { + .ras_late_init = amdgpu_umc_ras_late_init, + .ras_fini = amdgpu_umc_ras_fini, + .query_ras_error_count = umc_v6_7_query_ras_error_count, + .query_ras_error_address = umc_v6_7_query_ras_error_address, +}; diff --git a/drivers/gpu/drm/amd/amdgpu/umc_v6_7.h b/drivers/gpu/drm/amd/amdgpu/umc_v6_7.h new file mode 100644 index 000000000000..4eb85f247e96 --- /dev/null +++ b/drivers/gpu/drm/amd/amdgpu/umc_v6_7.h @@ -0,0 +1,37 @@ +/* + * Copyright 2021 Advanced Micro Devices, Inc. + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR + * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, + * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR + * OTHER DEALINGS IN THE SOFTWARE. + * + */ +#ifndef __UMC_V6_7_H__ +#define __UMC_V6_7_H__ + +/* EccErrCnt max value */ +#define UMC_V6_7_CE_CNT_MAX 0xffff +/* umc ce interrupt threshold */ +#define UMC_V6_7_CE_INT_THRESHOLD 0xffff +/* umc ce count initial value */ +#define UMC_V6_7_CE_CNT_INIT (UMC_V6_7_CE_CNT_MAX - UMC_V6_7_CE_INT_THRESHOLD) + +#define UMC_V6_7_INST_DIST 0x40000 + +extern const struct amdgpu_umc_ras_funcs umc_v6_7_ras_funcs; + +#endif diff --git a/drivers/gpu/drm/amd/amdgpu/umc_v8_7.c b/drivers/gpu/drm/amd/amdgpu/umc_v8_7.c index a064c097690c..89d20adfa001 100644 --- a/drivers/gpu/drm/amd/amdgpu/umc_v8_7.c +++ b/drivers/gpu/drm/amd/amdgpu/umc_v8_7.c @@ -22,6 +22,7 @@ */ #include "umc_v8_7.h" #include "amdgpu_ras.h" +#include "amdgpu_umc.h" #include "amdgpu.h" #include "rsmu/rsmu_0_0_2_offset.h" @@ -323,9 +324,10 @@ static void umc_v8_7_err_cnt_init(struct amdgpu_device *adev) } } -const struct amdgpu_umc_funcs umc_v8_7_funcs = { +const struct amdgpu_umc_ras_funcs umc_v8_7_ras_funcs = { .err_cnt_init = umc_v8_7_err_cnt_init, .ras_late_init = amdgpu_umc_ras_late_init, + .ras_fini = amdgpu_umc_ras_fini, .query_ras_error_count = umc_v8_7_query_ras_error_count, .query_ras_error_address = umc_v8_7_query_ras_error_address, }; diff --git a/drivers/gpu/drm/amd/amdgpu/umc_v8_7.h b/drivers/gpu/drm/amd/amdgpu/umc_v8_7.h index d4d0468e3df5..37e6dc7c28e0 100644 --- a/drivers/gpu/drm/amd/amdgpu/umc_v8_7.h +++ b/drivers/gpu/drm/amd/amdgpu/umc_v8_7.h @@ -44,7 +44,7 @@ /* umc ce count initial value */ #define UMC_V8_7_CE_CNT_INIT (UMC_V8_7_CE_CNT_MAX - UMC_V8_7_CE_INT_THRESHOLD) -extern const struct amdgpu_umc_funcs umc_v8_7_funcs; +extern const struct amdgpu_umc_ras_funcs umc_v8_7_ras_funcs; extern const uint32_t umc_v8_7_channel_idx_tbl[UMC_V8_7_UMC_INSTANCE_NUM][UMC_V8_7_CHANNEL_INSTANCE_NUM]; diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v3_1.c b/drivers/gpu/drm/amd/amdgpu/uvd_v3_1.c index 10ecae257b18..284447d7a579 100644 --- a/drivers/gpu/drm/amd/amdgpu/uvd_v3_1.c +++ b/drivers/gpu/drm/amd/amdgpu/uvd_v3_1.c @@ -562,7 +562,7 @@ static int uvd_v3_1_sw_init(void *handle) ring = &adev->uvd.inst->ring; sprintf(ring->name, "uvd"); r = amdgpu_ring_init(adev, ring, 512, &adev->uvd.inst->irq, 0, - AMDGPU_RING_PRIO_DEFAULT); + AMDGPU_RING_PRIO_DEFAULT, NULL); if (r) return r; diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c b/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c index a70d2a0de316..a301518e4957 100644 --- a/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c +++ b/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c @@ -119,7 +119,7 @@ static int uvd_v4_2_sw_init(void *handle) ring = &adev->uvd.inst->ring; sprintf(ring->name, "uvd"); r = amdgpu_ring_init(adev, ring, 512, &adev->uvd.inst->irq, 0, - AMDGPU_RING_PRIO_DEFAULT); + AMDGPU_RING_PRIO_DEFAULT, NULL); if (r) return r; diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c index f3b0a927101b..a4d5bd21c83c 100644 --- a/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c +++ b/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c @@ -117,7 +117,7 @@ static int uvd_v5_0_sw_init(void *handle) ring = &adev->uvd.inst->ring; sprintf(ring->name, "uvd"); r = amdgpu_ring_init(adev, ring, 512, &adev->uvd.inst->irq, 0, - AMDGPU_RING_PRIO_DEFAULT); + AMDGPU_RING_PRIO_DEFAULT, NULL); if (r) return r; diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c index 760859880c1e..2bab9c77952f 100644 --- a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c +++ b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c @@ -420,7 +420,7 @@ static int uvd_v6_0_sw_init(void *handle) ring = &adev->uvd.inst->ring; sprintf(ring->name, "uvd"); r = amdgpu_ring_init(adev, ring, 512, &adev->uvd.inst->irq, 0, - AMDGPU_RING_PRIO_DEFAULT); + AMDGPU_RING_PRIO_DEFAULT, NULL); if (r) return r; @@ -434,7 +434,7 @@ static int uvd_v6_0_sw_init(void *handle) sprintf(ring->name, "uvd_enc%d", i); r = amdgpu_ring_init(adev, ring, 512, &adev->uvd.inst->irq, 0, - AMDGPU_RING_PRIO_DEFAULT); + AMDGPU_RING_PRIO_DEFAULT, NULL); if (r) return r; } diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c index 7cd67cb2ac5f..0cd98fcb1f9f 100644 --- a/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c +++ b/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c @@ -454,7 +454,7 @@ static int uvd_v7_0_sw_init(void *handle) sprintf(ring->name, "uvd_%d", ring->me); r = amdgpu_ring_init(adev, ring, 512, &adev->uvd.inst[j].irq, 0, - AMDGPU_RING_PRIO_DEFAULT); + AMDGPU_RING_PRIO_DEFAULT, NULL); if (r) return r; } @@ -475,7 +475,7 @@ static int uvd_v7_0_sw_init(void *handle) } r = amdgpu_ring_init(adev, ring, 512, &adev->uvd.inst[j].irq, 0, - AMDGPU_RING_PRIO_DEFAULT); + AMDGPU_RING_PRIO_DEFAULT, NULL); if (r) return r; } diff --git a/drivers/gpu/drm/amd/amdgpu/vce_v2_0.c b/drivers/gpu/drm/amd/amdgpu/vce_v2_0.c index 0e2945baf0f1..c7d28c169be5 100644 --- a/drivers/gpu/drm/amd/amdgpu/vce_v2_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vce_v2_0.c @@ -433,9 +433,8 @@ static int vce_v2_0_sw_init(void *handle) for (i = 0; i < adev->vce.num_rings; i++) { ring = &adev->vce.ring[i]; sprintf(ring->name, "vce%d", i); - r = amdgpu_ring_init(adev, ring, 512, - &adev->vce.irq, 0, - AMDGPU_RING_PRIO_DEFAULT); + r = amdgpu_ring_init(adev, ring, 512, &adev->vce.irq, 0, + AMDGPU_RING_PRIO_DEFAULT, NULL); if (r) return r; } diff --git a/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c index 6d9108fa22e0..3b82fb289ef6 100644 --- a/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c @@ -443,7 +443,7 @@ static int vce_v3_0_sw_init(void *handle) ring = &adev->vce.ring[i]; sprintf(ring->name, "vce%d", i); r = amdgpu_ring_init(adev, ring, 512, &adev->vce.irq, 0, - AMDGPU_RING_PRIO_DEFAULT); + AMDGPU_RING_PRIO_DEFAULT, NULL); if (r) return r; } diff --git a/drivers/gpu/drm/amd/amdgpu/vce_v4_0.c b/drivers/gpu/drm/amd/amdgpu/vce_v4_0.c index 37fa163393fd..8e238dea7bef 100644 --- a/drivers/gpu/drm/amd/amdgpu/vce_v4_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vce_v4_0.c @@ -477,7 +477,7 @@ static int vce_v4_0_sw_init(void *handle) ring->doorbell_index = adev->doorbell_index.uvd_vce.vce_ring2_3 * 2 + 1; } r = amdgpu_ring_init(adev, ring, 512, &adev->vce.irq, 0, - AMDGPU_RING_PRIO_DEFAULT); + AMDGPU_RING_PRIO_DEFAULT, NULL); if (r) return r; } diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c index 6117931fa8d7..51a773a37a35 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c @@ -129,7 +129,7 @@ static int vcn_v1_0_sw_init(void *handle) ring = &adev->vcn.inst->ring_dec; sprintf(ring->name, "vcn_dec"); r = amdgpu_ring_init(adev, ring, 512, &adev->vcn.inst->irq, 0, - AMDGPU_RING_PRIO_DEFAULT); + AMDGPU_RING_PRIO_DEFAULT, NULL); if (r) return r; @@ -148,7 +148,7 @@ static int vcn_v1_0_sw_init(void *handle) ring = &adev->vcn.inst->ring_enc[i]; sprintf(ring->name, "vcn_enc%d", i); r = amdgpu_ring_init(adev, ring, 512, &adev->vcn.inst->irq, 0, - AMDGPU_RING_PRIO_DEFAULT); + AMDGPU_RING_PRIO_DEFAULT, NULL); if (r) return r; } diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c index d63198c945bf..116b9643d5ba 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c @@ -136,7 +136,7 @@ static int vcn_v2_0_sw_init(void *handle) sprintf(ring->name, "vcn_dec"); r = amdgpu_ring_init(adev, ring, 512, &adev->vcn.inst->irq, 0, - AMDGPU_RING_PRIO_DEFAULT); + AMDGPU_RING_PRIO_DEFAULT, NULL); if (r) return r; @@ -167,7 +167,7 @@ static int vcn_v2_0_sw_init(void *handle) ring->doorbell_index = (adev->doorbell_index.vcn.vcn_ring0_1 << 1) + 1 + i; sprintf(ring->name, "vcn_enc%d", i); r = amdgpu_ring_init(adev, ring, 512, &adev->vcn.inst->irq, 0, - AMDGPU_RING_PRIO_DEFAULT); + AMDGPU_RING_PRIO_DEFAULT, NULL); if (r) return r; } diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c b/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c index 87ec883f7e06..948813d7caa0 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c @@ -189,7 +189,7 @@ static int vcn_v2_5_sw_init(void *handle) (amdgpu_sriov_vf(adev) ? 2*j : 8*j); sprintf(ring->name, "vcn_dec_%d", j); r = amdgpu_ring_init(adev, ring, 512, &adev->vcn.inst[j].irq, - 0, AMDGPU_RING_PRIO_DEFAULT); + 0, AMDGPU_RING_PRIO_DEFAULT, NULL); if (r) return r; @@ -203,7 +203,7 @@ static int vcn_v2_5_sw_init(void *handle) sprintf(ring->name, "vcn_enc_%d.%d", j, i); r = amdgpu_ring_init(adev, ring, 512, &adev->vcn.inst[j].irq, 0, - AMDGPU_RING_PRIO_DEFAULT); + AMDGPU_RING_PRIO_DEFAULT, NULL); if (r) return r; } diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c index b61d1ba1aa9d..3f15bf34123a 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c @@ -50,6 +50,9 @@ #define VCN_INSTANCES_SIENNA_CICHLID 2 #define DEC_SW_RING_ENABLED FALSE +#define RDECODE_MSG_CREATE 0x00000000 +#define RDECODE_MESSAGE_CREATE 0x00000001 + static int amdgpu_ih_clientid_vcns[] = { SOC15_IH_CLIENTID_VCN, SOC15_IH_CLIENTID_VCN1 @@ -171,6 +174,7 @@ static int vcn_v3_0_sw_init(void *handle) for (i = 0; i < adev->vcn.num_vcn_inst; i++) { volatile struct amdgpu_fw_shared *fw_shared; + if (adev->vcn.harvest_config & (1 << i)) continue; @@ -198,6 +202,8 @@ static int vcn_v3_0_sw_init(void *handle) if (r) return r; + atomic_set(&adev->vcn.inst[i].sched_score, 0); + ring = &adev->vcn.inst[i].ring_dec; ring->use_doorbell = true; if (amdgpu_sriov_vf(adev)) { @@ -205,11 +211,10 @@ static int vcn_v3_0_sw_init(void *handle) } else { ring->doorbell_index = (adev->doorbell_index.vcn.vcn_ring0_1 << 1) + 8 * i; } - if (adev->asic_type == CHIP_SIENNA_CICHLID && i != 0) - ring->no_scheduler = true; sprintf(ring->name, "vcn_dec_%d", i); r = amdgpu_ring_init(adev, ring, 512, &adev->vcn.inst[i].irq, 0, - AMDGPU_RING_PRIO_DEFAULT); + AMDGPU_RING_PRIO_DEFAULT, + &adev->vcn.inst[i].sched_score); if (r) return r; @@ -227,11 +232,10 @@ static int vcn_v3_0_sw_init(void *handle) } else { ring->doorbell_index = (adev->doorbell_index.vcn.vcn_ring0_1 << 1) + 2 + j + 8 * i; } - if (adev->asic_type == CHIP_SIENNA_CICHLID && i != 1) - ring->no_scheduler = true; sprintf(ring->name, "vcn_enc_%d.%d", i, j); r = amdgpu_ring_init(adev, ring, 512, &adev->vcn.inst[i].irq, 0, - AMDGPU_RING_PRIO_DEFAULT); + AMDGPU_RING_PRIO_DEFAULT, + &adev->vcn.inst[i].sched_score); if (r) return r; } @@ -1844,6 +1848,132 @@ static const struct amdgpu_ring_funcs vcn_v3_0_dec_sw_ring_vm_funcs = { .emit_reg_write_reg_wait = amdgpu_ring_emit_reg_write_reg_wait_helper, }; +static int vcn_v3_0_limit_sched(struct amdgpu_cs_parser *p) +{ + struct drm_gpu_scheduler **scheds; + + /* The create msg must be in the first IB submitted */ + if (atomic_read(&p->entity->fence_seq)) + return -EINVAL; + + scheds = p->adev->gpu_sched[AMDGPU_HW_IP_VCN_DEC] + [AMDGPU_RING_PRIO_DEFAULT].sched; + drm_sched_entity_modify_sched(p->entity, scheds, 1); + return 0; +} + +static int vcn_v3_0_dec_msg(struct amdgpu_cs_parser *p, uint64_t addr) +{ + struct ttm_operation_ctx ctx = { false, false }; + struct amdgpu_bo_va_mapping *map; + uint32_t *msg, num_buffers; + struct amdgpu_bo *bo; + uint64_t start, end; + unsigned int i; + void * ptr; + int r; + + addr &= AMDGPU_GMC_HOLE_MASK; + r = amdgpu_cs_find_mapping(p, addr, &bo, &map); + if (r) { + DRM_ERROR("Can't find BO for addr 0x%08Lx\n", addr); + return r; + } + + start = map->start * AMDGPU_GPU_PAGE_SIZE; + end = (map->last + 1) * AMDGPU_GPU_PAGE_SIZE; + if (addr & 0x7) { + DRM_ERROR("VCN messages must be 8 byte aligned!\n"); + return -EINVAL; + } + + bo->flags |= AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED; + amdgpu_bo_placement_from_domain(bo, bo->allowed_domains); + r = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx); + if (r) { + DRM_ERROR("Failed validating the VCN message BO (%d)!\n", r); + return r; + } + + r = amdgpu_bo_kmap(bo, &ptr); + if (r) { + DRM_ERROR("Failed mapping the VCN message (%d)!\n", r); + return r; + } + + msg = ptr + addr - start; + + /* Check length */ + if (msg[1] > end - addr) { + r = -EINVAL; + goto out; + } + + if (msg[3] != RDECODE_MSG_CREATE) + goto out; + + num_buffers = msg[2]; + for (i = 0, msg = &msg[6]; i < num_buffers; ++i, msg += 4) { + uint32_t offset, size, *create; + + if (msg[0] != RDECODE_MESSAGE_CREATE) + continue; + + offset = msg[1]; + size = msg[2]; + + if (offset + size > end) { + r = -EINVAL; + goto out; + } + + create = ptr + addr + offset - start; + + /* H246, HEVC and VP9 can run on any instance */ + if (create[0] == 0x7 || create[0] == 0x10 || create[0] == 0x11) + continue; + + r = vcn_v3_0_limit_sched(p); + if (r) + goto out; + } + +out: + amdgpu_bo_kunmap(bo); + return r; +} + +static int vcn_v3_0_ring_patch_cs_in_place(struct amdgpu_cs_parser *p, + uint32_t ib_idx) +{ + struct amdgpu_ring *ring = to_amdgpu_ring(p->entity->rq->sched); + struct amdgpu_ib *ib = &p->job->ibs[ib_idx]; + uint32_t msg_lo = 0, msg_hi = 0; + unsigned i; + int r; + + /* The first instance can decode anything */ + if (!ring->me) + return 0; + + for (i = 0; i < ib->length_dw; i += 2) { + uint32_t reg = amdgpu_get_ib_value(p, ib_idx, i); + uint32_t val = amdgpu_get_ib_value(p, ib_idx, i + 1); + + if (reg == PACKET0(p->adev->vcn.internal.data0, 0)) { + msg_lo = val; + } else if (reg == PACKET0(p->adev->vcn.internal.data1, 0)) { + msg_hi = val; + } else if (reg == PACKET0(p->adev->vcn.internal.cmd, 0) && + val == 0) { + r = vcn_v3_0_dec_msg(p, ((u64)msg_hi) << 32 | msg_lo); + if (r) + return r; + } + } + return 0; +} + static const struct amdgpu_ring_funcs vcn_v3_0_dec_ring_vm_funcs = { .type = AMDGPU_RING_TYPE_VCN_DEC, .align_mask = 0xf, @@ -1851,6 +1981,7 @@ static const struct amdgpu_ring_funcs vcn_v3_0_dec_ring_vm_funcs = { .get_rptr = vcn_v3_0_dec_ring_get_rptr, .get_wptr = vcn_v3_0_dec_ring_get_wptr, .set_wptr = vcn_v3_0_dec_ring_set_wptr, + .patch_cs_in_place = vcn_v3_0_ring_patch_cs_in_place, .emit_frame_size = SOC15_FLUSH_GPU_TLB_NUM_WREG * 6 + SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 8 + diff --git a/drivers/gpu/drm/amd/amdgpu/vega20_ih.c b/drivers/gpu/drm/amd/amdgpu/vega20_ih.c index 6c3cb3513b98..8a122b413bf5 100644 --- a/drivers/gpu/drm/amd/amdgpu/vega20_ih.c +++ b/drivers/gpu/drm/amd/amdgpu/vega20_ih.c @@ -264,10 +264,10 @@ static void vega20_ih_reroute_ih(struct amdgpu_device *adev) { uint32_t tmp; - /* vega20 ih reroute will go through psp - * this function is only used for arcturus + /* vega20 ih reroute will go through psp this + * function is used for newer asics starting arcturus */ - if (adev->asic_type == CHIP_ARCTURUS) { + if (adev->asic_type >= CHIP_ARCTURUS) { /* Reroute to IH ring 1 for VMC */ WREG32_SOC15(OSSSYS, 0, mmIH_CLIENT_CFG_INDEX, 0x12); tmp = RREG32_SOC15(OSSSYS, 0, mmIH_CLIENT_CFG_DATA); diff --git a/drivers/gpu/drm/amd/amdgpu/vi.c b/drivers/gpu/drm/amd/amdgpu/vi.c index ea338de5818a..735ebbd1148f 100644 --- a/drivers/gpu/drm/amd/amdgpu/vi.c +++ b/drivers/gpu/drm/amd/amdgpu/vi.c @@ -81,6 +81,30 @@ #include "mxgpu_vi.h" #include "amdgpu_dm.h" +#define ixPCIE_LC_L1_PM_SUBSTATE 0x100100C6 +#define PCIE_LC_L1_PM_SUBSTATE__LC_L1_SUBSTATES_OVERRIDE_EN_MASK 0x00000001L +#define PCIE_LC_L1_PM_SUBSTATE__LC_PCI_PM_L1_2_OVERRIDE_MASK 0x00000002L +#define PCIE_LC_L1_PM_SUBSTATE__LC_PCI_PM_L1_1_OVERRIDE_MASK 0x00000004L +#define PCIE_LC_L1_PM_SUBSTATE__LC_ASPM_L1_2_OVERRIDE_MASK 0x00000008L +#define PCIE_LC_L1_PM_SUBSTATE__LC_ASPM_L1_1_OVERRIDE_MASK 0x00000010L +#define ixPCIE_L1_PM_SUB_CNTL 0x378 +#define PCIE_L1_PM_SUB_CNTL__ASPM_L1_2_EN_MASK 0x00000004L +#define PCIE_L1_PM_SUB_CNTL__ASPM_L1_1_EN_MASK 0x00000008L +#define PCIE_L1_PM_SUB_CNTL__PCI_PM_L1_2_EN_MASK 0x00000001L +#define PCIE_L1_PM_SUB_CNTL__PCI_PM_L1_1_EN_MASK 0x00000002L +#define PCIE_LC_CNTL6__LC_L1_POWERDOWN_MASK 0x00200000L +#define LINK_CAP 0x64 +#define PCIE_LINK_CAP__CLOCK_POWER_MANAGEMENT_MASK 0x00040000L +#define ixCPM_CONTROL 0x1400118 +#define ixPCIE_LC_CNTL7 0x100100BC +#define PCIE_LC_CNTL7__LC_L1_SIDEBAND_CLKREQ_PDWN_EN_MASK 0x00000400L +#define PCIE_LC_CNTL__LC_L0S_INACTIVITY_DEFAULT 0x00000007 +#define PCIE_LC_CNTL__LC_L1_INACTIVITY_DEFAULT 0x00000009 +#define CPM_CONTROL__CLKREQb_UNGATE_TXCLK_ENABLE_MASK 0x01000000L +#define PCIE_L1_PM_SUB_CNTL 0x378 +#define ASIC_IS_P22(asic_type, rid) ((asic_type >= CHIP_POLARIS10) && \ + (asic_type <= CHIP_POLARIS12) && \ + (rid >= 0x6E)) /* Topaz */ static const struct amdgpu_video_codecs topaz_video_codecs_encode = { @@ -1091,13 +1115,178 @@ static void vi_pcie_gen3_enable(struct amdgpu_device *adev) /* todo */ } +static void vi_enable_aspm(struct amdgpu_device *adev) +{ + u32 data, orig; + + orig = data = RREG32_PCIE(ixPCIE_LC_CNTL); + data |= PCIE_LC_CNTL__LC_L0S_INACTIVITY_DEFAULT << + PCIE_LC_CNTL__LC_L0S_INACTIVITY__SHIFT; + data |= PCIE_LC_CNTL__LC_L1_INACTIVITY_DEFAULT << + PCIE_LC_CNTL__LC_L1_INACTIVITY__SHIFT; + data &= ~PCIE_LC_CNTL__LC_PMI_TO_L1_DIS_MASK; + data |= PCIE_LC_CNTL__LC_DELAY_L1_EXIT_MASK; + if (orig != data) + WREG32_PCIE(ixPCIE_LC_CNTL, data); +} + static void vi_program_aspm(struct amdgpu_device *adev) { + u32 data, data1, orig; + bool bL1SS = false; + bool bClkReqSupport = true; - if (amdgpu_aspm == 0) + if (amdgpu_aspm != 1) return; - /* todo */ + if (adev->flags & AMD_IS_APU || + adev->asic_type < CHIP_POLARIS10) + return; + + orig = data = RREG32_PCIE(ixPCIE_LC_CNTL); + data &= ~PCIE_LC_CNTL__LC_L1_INACTIVITY_MASK; + data &= ~PCIE_LC_CNTL__LC_L0S_INACTIVITY_MASK; + data |= PCIE_LC_CNTL__LC_PMI_TO_L1_DIS_MASK; + if (orig != data) + WREG32_PCIE(ixPCIE_LC_CNTL, data); + + orig = data = RREG32_PCIE(ixPCIE_LC_N_FTS_CNTL); + data &= ~PCIE_LC_N_FTS_CNTL__LC_XMIT_N_FTS_MASK; + data |= 0x0024 << PCIE_LC_N_FTS_CNTL__LC_XMIT_N_FTS__SHIFT; + data |= PCIE_LC_N_FTS_CNTL__LC_XMIT_N_FTS_OVERRIDE_EN_MASK; + if (orig != data) + WREG32_PCIE(ixPCIE_LC_N_FTS_CNTL, data); + + orig = data = RREG32_PCIE(ixPCIE_LC_CNTL3); + data |= PCIE_LC_CNTL3__LC_GO_TO_RECOVERY_MASK; + if (orig != data) + WREG32_PCIE(ixPCIE_LC_CNTL3, data); + + orig = data = RREG32_PCIE(ixPCIE_P_CNTL); + data |= PCIE_P_CNTL__P_IGNORE_EDB_ERR_MASK; + if (orig != data) + WREG32_PCIE(ixPCIE_P_CNTL, data); + + data = RREG32_PCIE(ixPCIE_LC_L1_PM_SUBSTATE); + pci_read_config_dword(adev->pdev, PCIE_L1_PM_SUB_CNTL, &data1); + if (data & PCIE_LC_L1_PM_SUBSTATE__LC_L1_SUBSTATES_OVERRIDE_EN_MASK && + (data & (PCIE_LC_L1_PM_SUBSTATE__LC_PCI_PM_L1_2_OVERRIDE_MASK | + PCIE_LC_L1_PM_SUBSTATE__LC_PCI_PM_L1_1_OVERRIDE_MASK | + PCIE_LC_L1_PM_SUBSTATE__LC_ASPM_L1_2_OVERRIDE_MASK | + PCIE_LC_L1_PM_SUBSTATE__LC_ASPM_L1_1_OVERRIDE_MASK))) { + bL1SS = true; + } else if (data1 & (PCIE_L1_PM_SUB_CNTL__ASPM_L1_2_EN_MASK | + PCIE_L1_PM_SUB_CNTL__ASPM_L1_1_EN_MASK | + PCIE_L1_PM_SUB_CNTL__PCI_PM_L1_2_EN_MASK | + PCIE_L1_PM_SUB_CNTL__PCI_PM_L1_1_EN_MASK)) { + bL1SS = true; + } + + orig = data = RREG32_PCIE(ixPCIE_LC_CNTL6); + data |= PCIE_LC_CNTL6__LC_L1_POWERDOWN_MASK; + if (orig != data) + WREG32_PCIE(ixPCIE_LC_CNTL6, data); + + orig = data = RREG32_PCIE(ixPCIE_LC_LINK_WIDTH_CNTL); + data |= PCIE_LC_LINK_WIDTH_CNTL__LC_DYN_LANES_PWR_STATE_MASK; + if (orig != data) + WREG32_PCIE(ixPCIE_LC_LINK_WIDTH_CNTL, data); + + pci_read_config_dword(adev->pdev, LINK_CAP, &data); + if (!(data & PCIE_LINK_CAP__CLOCK_POWER_MANAGEMENT_MASK)) + bClkReqSupport = false; + + if (bClkReqSupport) { + orig = data = RREG32_SMC(ixTHM_CLK_CNTL); + data &= ~(THM_CLK_CNTL__CMON_CLK_SEL_MASK | THM_CLK_CNTL__TMON_CLK_SEL_MASK); + data |= (1 << THM_CLK_CNTL__CMON_CLK_SEL__SHIFT) | + (1 << THM_CLK_CNTL__TMON_CLK_SEL__SHIFT); + if (orig != data) + WREG32_SMC(ixTHM_CLK_CNTL, data); + + orig = data = RREG32_SMC(ixMISC_CLK_CTRL); + data &= ~(MISC_CLK_CTRL__DEEP_SLEEP_CLK_SEL_MASK | + MISC_CLK_CTRL__ZCLK_SEL_MASK | MISC_CLK_CTRL__DFT_SMS_PG_CLK_SEL_MASK); + data |= (1 << MISC_CLK_CTRL__DEEP_SLEEP_CLK_SEL__SHIFT) | + (1 << MISC_CLK_CTRL__ZCLK_SEL__SHIFT); + data |= (0x20 << MISC_CLK_CTRL__DFT_SMS_PG_CLK_SEL__SHIFT); + if (orig != data) + WREG32_SMC(ixMISC_CLK_CTRL, data); + + orig = data = RREG32_SMC(ixCG_CLKPIN_CNTL); + data |= CG_CLKPIN_CNTL__XTALIN_DIVIDE_MASK; + if (orig != data) + WREG32_SMC(ixCG_CLKPIN_CNTL, data); + + orig = data = RREG32_SMC(ixCG_CLKPIN_CNTL_2); + data |= CG_CLKPIN_CNTL_2__ENABLE_XCLK_MASK; + if (orig != data) + WREG32_SMC(ixCG_CLKPIN_CNTL, data); + + orig = data = RREG32_SMC(ixMPLL_BYPASSCLK_SEL); + data &= ~MPLL_BYPASSCLK_SEL__MPLL_CLKOUT_SEL_MASK; + data |= (4 << MPLL_BYPASSCLK_SEL__MPLL_CLKOUT_SEL__SHIFT); + if (orig != data) + WREG32_SMC(ixMPLL_BYPASSCLK_SEL, data); + + orig = data = RREG32_PCIE(ixCPM_CONTROL); + data |= (CPM_CONTROL__REFCLK_XSTCLK_ENABLE_MASK | + CPM_CONTROL__CLKREQb_UNGATE_TXCLK_ENABLE_MASK); + if (orig != data) + WREG32_PCIE(ixCPM_CONTROL, data); + + orig = data = RREG32_PCIE(ixPCIE_CONFIG_CNTL); + data &= ~PCIE_CONFIG_CNTL__DYN_CLK_LATENCY_MASK; + data |= (0xE << PCIE_CONFIG_CNTL__DYN_CLK_LATENCY__SHIFT); + if (orig != data) + WREG32_PCIE(ixPCIE_CONFIG_CNTL, data); + + orig = data = RREG32(mmBIF_CLK_CTRL); + data |= BIF_CLK_CTRL__BIF_XSTCLK_READY_MASK; + if (orig != data) + WREG32(mmBIF_CLK_CTRL, data); + + orig = data = RREG32_PCIE(ixPCIE_LC_CNTL7); + data |= PCIE_LC_CNTL7__LC_L1_SIDEBAND_CLKREQ_PDWN_EN_MASK; + if (orig != data) + WREG32_PCIE(ixPCIE_LC_CNTL7, data); + + orig = data = RREG32_PCIE(ixPCIE_HW_DEBUG); + data |= PCIE_HW_DEBUG__HW_01_DEBUG_MASK; + if (orig != data) + WREG32_PCIE(ixPCIE_HW_DEBUG, data); + + orig = data = RREG32_PCIE(ixPCIE_LC_CNTL2); + data |= PCIE_LC_CNTL2__LC_ALLOW_PDWN_IN_L23_MASK; + data |= PCIE_LC_CNTL2__LC_ALLOW_PDWN_IN_L1_MASK; + if (bL1SS) + data &= ~PCIE_LC_CNTL2__LC_ALLOW_PDWN_IN_L1_MASK; + if (orig != data) + WREG32_PCIE(ixPCIE_LC_CNTL2, data); + + } + + vi_enable_aspm(adev); + + data = RREG32_PCIE(ixPCIE_LC_N_FTS_CNTL); + data1 = RREG32_PCIE(ixPCIE_LC_STATUS1); + if (((data & PCIE_LC_N_FTS_CNTL__LC_N_FTS_MASK) == PCIE_LC_N_FTS_CNTL__LC_N_FTS_MASK) && + data1 & PCIE_LC_STATUS1__LC_REVERSE_XMIT_MASK && + data1 & PCIE_LC_STATUS1__LC_REVERSE_RCVR_MASK) { + orig = data = RREG32_PCIE(ixPCIE_LC_CNTL); + data &= ~PCIE_LC_CNTL__LC_L0S_INACTIVITY_MASK; + if (orig != data) + WREG32_PCIE(ixPCIE_LC_CNTL, data); + } + + if ((adev->asic_type == CHIP_POLARIS12 && + !(ASICID_IS_P23(adev->pdev->device, adev->pdev->revision))) || + ASIC_IS_P22(adev->asic_type, adev->external_rev_id)) { + orig = data = RREG32_PCIE(ixPCIE_LC_TRAINING_CNTL); + data &= ~PCIE_LC_TRAINING_CNTL__LC_DISABLE_TRAINING_BIT_ARCH_MASK; + if (orig != data) + WREG32_PCIE(ixPCIE_LC_TRAINING_CNTL, data); + } } static void vi_enable_doorbell_aperture(struct amdgpu_device *adev, diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c index 6802c616e10e..43de260b2230 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c @@ -870,52 +870,47 @@ static int kfd_ioctl_get_process_apertures(struct file *filp, { struct kfd_ioctl_get_process_apertures_args *args = data; struct kfd_process_device_apertures *pAperture; - struct kfd_process_device *pdd; + int i; dev_dbg(kfd_device, "get apertures for PASID 0x%x", p->pasid); args->num_of_nodes = 0; mutex_lock(&p->mutex); + /* Run over all pdd of the process */ + for (i = 0; i < p->n_pdds; i++) { + struct kfd_process_device *pdd = p->pdds[i]; + + pAperture = + &args->process_apertures[args->num_of_nodes]; + pAperture->gpu_id = pdd->dev->id; + pAperture->lds_base = pdd->lds_base; + pAperture->lds_limit = pdd->lds_limit; + pAperture->gpuvm_base = pdd->gpuvm_base; + pAperture->gpuvm_limit = pdd->gpuvm_limit; + pAperture->scratch_base = pdd->scratch_base; + pAperture->scratch_limit = pdd->scratch_limit; - /*if the process-device list isn't empty*/ - if (kfd_has_process_device_data(p)) { - /* Run over all pdd of the process */ - pdd = kfd_get_first_process_device_data(p); - do { - pAperture = - &args->process_apertures[args->num_of_nodes]; - pAperture->gpu_id = pdd->dev->id; - pAperture->lds_base = pdd->lds_base; - pAperture->lds_limit = pdd->lds_limit; - pAperture->gpuvm_base = pdd->gpuvm_base; - pAperture->gpuvm_limit = pdd->gpuvm_limit; - pAperture->scratch_base = pdd->scratch_base; - pAperture->scratch_limit = pdd->scratch_limit; - - dev_dbg(kfd_device, - "node id %u\n", args->num_of_nodes); - dev_dbg(kfd_device, - "gpu id %u\n", pdd->dev->id); - dev_dbg(kfd_device, - "lds_base %llX\n", pdd->lds_base); - dev_dbg(kfd_device, - "lds_limit %llX\n", pdd->lds_limit); - dev_dbg(kfd_device, - "gpuvm_base %llX\n", pdd->gpuvm_base); - dev_dbg(kfd_device, - "gpuvm_limit %llX\n", pdd->gpuvm_limit); - dev_dbg(kfd_device, - "scratch_base %llX\n", pdd->scratch_base); - dev_dbg(kfd_device, - "scratch_limit %llX\n", pdd->scratch_limit); - - args->num_of_nodes++; - - pdd = kfd_get_next_process_device_data(p, pdd); - } while (pdd && (args->num_of_nodes < NUM_OF_SUPPORTED_GPUS)); - } + dev_dbg(kfd_device, + "node id %u\n", args->num_of_nodes); + dev_dbg(kfd_device, + "gpu id %u\n", pdd->dev->id); + dev_dbg(kfd_device, + "lds_base %llX\n", pdd->lds_base); + dev_dbg(kfd_device, + "lds_limit %llX\n", pdd->lds_limit); + dev_dbg(kfd_device, + "gpuvm_base %llX\n", pdd->gpuvm_base); + dev_dbg(kfd_device, + "gpuvm_limit %llX\n", pdd->gpuvm_limit); + dev_dbg(kfd_device, + "scratch_base %llX\n", pdd->scratch_base); + dev_dbg(kfd_device, + "scratch_limit %llX\n", pdd->scratch_limit); + if (++args->num_of_nodes >= NUM_OF_SUPPORTED_GPUS) + break; + } mutex_unlock(&p->mutex); return 0; @@ -926,9 +921,8 @@ static int kfd_ioctl_get_process_apertures_new(struct file *filp, { struct kfd_ioctl_get_process_apertures_new_args *args = data; struct kfd_process_device_apertures *pa; - struct kfd_process_device *pdd; - uint32_t nodes = 0; int ret; + int i; dev_dbg(kfd_device, "get apertures for PASID 0x%x", p->pasid); @@ -937,17 +931,7 @@ static int kfd_ioctl_get_process_apertures_new(struct file *filp, * sufficient memory */ mutex_lock(&p->mutex); - - if (!kfd_has_process_device_data(p)) - goto out_unlock; - - /* Run over all pdd of the process */ - pdd = kfd_get_first_process_device_data(p); - do { - args->num_of_nodes++; - pdd = kfd_get_next_process_device_data(p, pdd); - } while (pdd); - + args->num_of_nodes = p->n_pdds; goto out_unlock; } @@ -962,22 +946,23 @@ static int kfd_ioctl_get_process_apertures_new(struct file *filp, mutex_lock(&p->mutex); - if (!kfd_has_process_device_data(p)) { + if (!p->n_pdds) { args->num_of_nodes = 0; kfree(pa); goto out_unlock; } /* Run over all pdd of the process */ - pdd = kfd_get_first_process_device_data(p); - do { - pa[nodes].gpu_id = pdd->dev->id; - pa[nodes].lds_base = pdd->lds_base; - pa[nodes].lds_limit = pdd->lds_limit; - pa[nodes].gpuvm_base = pdd->gpuvm_base; - pa[nodes].gpuvm_limit = pdd->gpuvm_limit; - pa[nodes].scratch_base = pdd->scratch_base; - pa[nodes].scratch_limit = pdd->scratch_limit; + for (i = 0; i < min(p->n_pdds, args->num_of_nodes); i++) { + struct kfd_process_device *pdd = p->pdds[i]; + + pa[i].gpu_id = pdd->dev->id; + pa[i].lds_base = pdd->lds_base; + pa[i].lds_limit = pdd->lds_limit; + pa[i].gpuvm_base = pdd->gpuvm_base; + pa[i].gpuvm_limit = pdd->gpuvm_limit; + pa[i].scratch_base = pdd->scratch_base; + pa[i].scratch_limit = pdd->scratch_limit; dev_dbg(kfd_device, "gpu id %u\n", pdd->dev->id); @@ -993,17 +978,14 @@ static int kfd_ioctl_get_process_apertures_new(struct file *filp, "scratch_base %llX\n", pdd->scratch_base); dev_dbg(kfd_device, "scratch_limit %llX\n", pdd->scratch_limit); - nodes++; - - pdd = kfd_get_next_process_device_data(p, pdd); - } while (pdd && (nodes < args->num_of_nodes)); + } mutex_unlock(&p->mutex); - args->num_of_nodes = nodes; + args->num_of_nodes = i; ret = copy_to_user( (void __user *)args->kfd_process_device_apertures_ptr, pa, - (nodes * sizeof(struct kfd_process_device_apertures))); + (i * sizeof(struct kfd_process_device_apertures))); kfree(pa); return ret ? -EFAULT : 0; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c b/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c index b258a3dae767..159add0f5aaa 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c @@ -155,7 +155,7 @@ static int dbgdev_diq_submit_ib(struct kfd_dbgdev *dbgdev, /* Wait till CP writes sync code: */ status = amdkfd_fence_wait_timeout( - (unsigned int *) rm_state, + rm_state, QUEUESTATE__ACTIVE, 1500); kfd_gtt_sa_free(dbgdev->dev, mem_obj); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_debugfs.c b/drivers/gpu/drm/amd/amdkfd/kfd_debugfs.c index 511712c2e382..673d5e34f213 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_debugfs.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_debugfs.c @@ -33,6 +33,11 @@ static int kfd_debugfs_open(struct inode *inode, struct file *file) return single_open(file, show, NULL); } +static int kfd_debugfs_hang_hws_read(struct seq_file *m, void *data) +{ + seq_printf(m, "echo gpu_id > hang_hws\n"); + return 0; +} static ssize_t kfd_debugfs_hang_hws_write(struct file *file, const char __user *user_buf, size_t size, loff_t *ppos) @@ -94,7 +99,7 @@ void kfd_debugfs_init(void) debugfs_create_file("rls", S_IFREG | 0444, debugfs_root, kfd_debugfs_rls_by_device, &kfd_debugfs_fops); debugfs_create_file("hang_hws", S_IFREG | 0200, debugfs_root, - NULL, &kfd_debugfs_hang_hws_fops); + kfd_debugfs_hang_hws_read, &kfd_debugfs_hang_hws_fops); } void kfd_debugfs_fini(void) diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c index f860cd705961..357b9bf62a1c 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c @@ -1322,7 +1322,7 @@ void kfd_dec_compute_active(struct kfd_dev *kfd) void kgd2kfd_smi_event_throttle(struct kfd_dev *kfd, uint32_t throttle_bitmask) { - if (kfd) + if (kfd && kfd->init_complete) kfd_smi_event_update_thermal_throttling(kfd, throttle_bitmask); } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c index 965f9f230045..d3eaa1549bd7 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c @@ -1180,7 +1180,7 @@ static int start_cpsch(struct device_queue_manager *dqm) if (retval) goto fail_allocate_vidmem; - dqm->fence_addr = dqm->fence_mem->cpu_ptr; + dqm->fence_addr = (uint64_t *)dqm->fence_mem->cpu_ptr; dqm->fence_gpu_addr = dqm->fence_mem->gpu_addr; init_interrupts(dqm); @@ -1353,8 +1353,8 @@ out: return retval; } -int amdkfd_fence_wait_timeout(unsigned int *fence_addr, - unsigned int fence_value, +int amdkfd_fence_wait_timeout(uint64_t *fence_addr, + uint64_t fence_value, unsigned int timeout_ms) { unsigned long end_jiffies = msecs_to_jiffies(timeout_ms) + jiffies; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h index dd0d8834b432..71e2fde56b2b 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h @@ -187,7 +187,7 @@ struct device_queue_manager { uint16_t vmid_pasid[VMID_NUM]; uint64_t pipelines_addr; uint64_t fence_gpu_addr; - unsigned int *fence_addr; + uint64_t *fence_addr; struct kfd_mem_obj *fence_mem; bool active_runlist; int sched_policy; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c index 1c20458f3962..696944fa0177 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c @@ -25,6 +25,70 @@ #include "soc15_int.h" #include "kfd_device_queue_manager.h" #include "kfd_smi_events.h" +#include "amdgpu.h" + +enum SQ_INTERRUPT_WORD_ENCODING { + SQ_INTERRUPT_WORD_ENCODING_AUTO = 0x0, + SQ_INTERRUPT_WORD_ENCODING_INST, + SQ_INTERRUPT_WORD_ENCODING_ERROR, +}; + +enum SQ_INTERRUPT_ERROR_TYPE { + SQ_INTERRUPT_ERROR_TYPE_EDC_FUE = 0x0, + SQ_INTERRUPT_ERROR_TYPE_ILLEGAL_INST, + SQ_INTERRUPT_ERROR_TYPE_MEMVIOL, + SQ_INTERRUPT_ERROR_TYPE_EDC_FED, +}; + +/* SQ_INTERRUPT_WORD_AUTO_CTXID */ +#define SQ_INTERRUPT_WORD_AUTO_CTXID__THREAD_TRACE__SHIFT 0 +#define SQ_INTERRUPT_WORD_AUTO_CTXID__WLT__SHIFT 1 +#define SQ_INTERRUPT_WORD_AUTO_CTXID__THREAD_TRACE_BUF_FULL__SHIFT 2 +#define SQ_INTERRUPT_WORD_AUTO_CTXID__REG_TIMESTAMP__SHIFT 3 +#define SQ_INTERRUPT_WORD_AUTO_CTXID__CMD_TIMESTAMP__SHIFT 4 +#define SQ_INTERRUPT_WORD_AUTO_CTXID__HOST_CMD_OVERFLOW__SHIFT 5 +#define SQ_INTERRUPT_WORD_AUTO_CTXID__HOST_REG_OVERFLOW__SHIFT 6 +#define SQ_INTERRUPT_WORD_AUTO_CTXID__IMMED_OVERFLOW__SHIFT 7 +#define SQ_INTERRUPT_WORD_AUTO_CTXID__THREAD_TRACE_UTC_ERROR__SHIFT 8 +#define SQ_INTERRUPT_WORD_AUTO_CTXID__SE_ID__SHIFT 24 +#define SQ_INTERRUPT_WORD_AUTO_CTXID__ENCODING__SHIFT 26 + +#define SQ_INTERRUPT_WORD_AUTO_CTXID__THREAD_TRACE_MASK 0x00000001 +#define SQ_INTERRUPT_WORD_AUTO_CTXID__WLT_MASK 0x00000002 +#define SQ_INTERRUPT_WORD_AUTO_CTXID__THREAD_TRACE_BUF_FULL_MASK 0x00000004 +#define SQ_INTERRUPT_WORD_AUTO_CTXID__REG_TIMESTAMP_MASK 0x00000008 +#define SQ_INTERRUPT_WORD_AUTO_CTXID__CMD_TIMESTAMP_MASK 0x00000010 +#define SQ_INTERRUPT_WORD_AUTO_CTXID__HOST_CMD_OVERFLOW_MASK 0x00000020 +#define SQ_INTERRUPT_WORD_AUTO_CTXID__HOST_REG_OVERFLOW_MASK 0x00000040 +#define SQ_INTERRUPT_WORD_AUTO_CTXID__IMMED_OVERFLOW_MASK 0x00000080 +#define SQ_INTERRUPT_WORD_AUTO_CTXID__THREAD_TRACE_UTC_ERROR_MASK 0x00000100 +#define SQ_INTERRUPT_WORD_AUTO_CTXID__SE_ID_MASK 0x03000000 +#define SQ_INTERRUPT_WORD_AUTO_CTXID__ENCODING_MASK 0x0c000000 + +/* SQ_INTERRUPT_WORD_WAVE_CTXID */ +#define SQ_INTERRUPT_WORD_WAVE_CTXID__DATA__SHIFT 0 +#define SQ_INTERRUPT_WORD_WAVE_CTXID__SH_ID__SHIFT 12 +#define SQ_INTERRUPT_WORD_WAVE_CTXID__PRIV__SHIFT 13 +#define SQ_INTERRUPT_WORD_WAVE_CTXID__WAVE_ID__SHIFT 14 +#define SQ_INTERRUPT_WORD_WAVE_CTXID__SIMD_ID__SHIFT 18 +#define SQ_INTERRUPT_WORD_WAVE_CTXID__CU_ID__SHIFT 20 +#define SQ_INTERRUPT_WORD_WAVE_CTXID__SE_ID__SHIFT 24 +#define SQ_INTERRUPT_WORD_WAVE_CTXID__ENCODING__SHIFT 26 + +#define SQ_INTERRUPT_WORD_WAVE_CTXID__DATA_MASK 0x00000fff +#define SQ_INTERRUPT_WORD_WAVE_CTXID__SH_ID_MASK 0x00001000 +#define SQ_INTERRUPT_WORD_WAVE_CTXID__PRIV_MASK 0x00002000 +#define SQ_INTERRUPT_WORD_WAVE_CTXID__WAVE_ID_MASK 0x0003c000 +#define SQ_INTERRUPT_WORD_WAVE_CTXID__SIMD_ID_MASK 0x000c0000 +#define SQ_INTERRUPT_WORD_WAVE_CTXID__CU_ID_MASK 0x00f00000 +#define SQ_INTERRUPT_WORD_WAVE_CTXID__SE_ID_MASK 0x03000000 +#define SQ_INTERRUPT_WORD_WAVE_CTXID__ENCODING_MASK 0x0c000000 + +#define KFD_CONTEXT_ID_GET_SQ_INT_DATA(ctx0, ctx1) \ + ((ctx0 & 0xfff) | ((ctx0 >> 16) & 0xf000) | ((ctx1 << 16) & 0xff0000)) + +#define KFD_SQ_INT_DATA__ERR_TYPE_MASK 0xF00000 +#define KFD_SQ_INT_DATA__ERR_TYPE__SHIFT 20 static bool event_interrupt_isr_v9(struct kfd_dev *dev, const uint32_t *ih_ring_entry, @@ -108,13 +172,15 @@ static void event_interrupt_wq_v9(struct kfd_dev *dev, const uint32_t *ih_ring_entry) { uint16_t source_id, client_id, pasid, vmid; - uint32_t context_id; + uint32_t context_id0, context_id1; + uint32_t sq_intr_err, sq_int_data, encoding; source_id = SOC15_SOURCE_ID_FROM_IH_ENTRY(ih_ring_entry); client_id = SOC15_CLIENT_ID_FROM_IH_ENTRY(ih_ring_entry); pasid = SOC15_PASID_FROM_IH_ENTRY(ih_ring_entry); vmid = SOC15_VMID_FROM_IH_ENTRY(ih_ring_entry); - context_id = SOC15_CONTEXT_ID0_FROM_IH_ENTRY(ih_ring_entry); + context_id0 = SOC15_CONTEXT_ID0_FROM_IH_ENTRY(ih_ring_entry); + context_id1 = SOC15_CONTEXT_ID1_FROM_IH_ENTRY(ih_ring_entry); if (client_id == SOC15_IH_CLIENTID_GRBM_CP || client_id == SOC15_IH_CLIENTID_SE0SH || @@ -122,10 +188,59 @@ static void event_interrupt_wq_v9(struct kfd_dev *dev, client_id == SOC15_IH_CLIENTID_SE2SH || client_id == SOC15_IH_CLIENTID_SE3SH) { if (source_id == SOC15_INTSRC_CP_END_OF_PIPE) - kfd_signal_event_interrupt(pasid, context_id, 32); - else if (source_id == SOC15_INTSRC_SQ_INTERRUPT_MSG) - kfd_signal_event_interrupt(pasid, context_id & 0xffffff, 24); - else if (source_id == SOC15_INTSRC_CP_BAD_OPCODE) + kfd_signal_event_interrupt(pasid, context_id0, 32); + else if (source_id == SOC15_INTSRC_SQ_INTERRUPT_MSG) { + sq_int_data = KFD_CONTEXT_ID_GET_SQ_INT_DATA(context_id0, context_id1); + encoding = REG_GET_FIELD(context_id0, SQ_INTERRUPT_WORD_WAVE_CTXID, ENCODING); + switch (encoding) { + case SQ_INTERRUPT_WORD_ENCODING_AUTO: + pr_debug( + "sq_intr: auto, se %d, ttrace %d, wlt %d, ttrac_buf_full %d, reg_tms %d, cmd_tms %d, host_cmd_ovf %d, host_reg_ovf %d, immed_ovf %d, ttrace_utc_err %d\n", + REG_GET_FIELD(context_id0, SQ_INTERRUPT_WORD_AUTO_CTXID, SE_ID), + REG_GET_FIELD(context_id0, SQ_INTERRUPT_WORD_AUTO_CTXID, THREAD_TRACE), + REG_GET_FIELD(context_id0, SQ_INTERRUPT_WORD_AUTO_CTXID, WLT), + REG_GET_FIELD(context_id0, SQ_INTERRUPT_WORD_AUTO_CTXID, THREAD_TRACE_BUF_FULL), + REG_GET_FIELD(context_id0, SQ_INTERRUPT_WORD_AUTO_CTXID, REG_TIMESTAMP), + REG_GET_FIELD(context_id0, SQ_INTERRUPT_WORD_AUTO_CTXID, CMD_TIMESTAMP), + REG_GET_FIELD(context_id0, SQ_INTERRUPT_WORD_AUTO_CTXID, HOST_CMD_OVERFLOW), + REG_GET_FIELD(context_id0, SQ_INTERRUPT_WORD_AUTO_CTXID, HOST_REG_OVERFLOW), + REG_GET_FIELD(context_id0, SQ_INTERRUPT_WORD_AUTO_CTXID, IMMED_OVERFLOW), + REG_GET_FIELD(context_id0, SQ_INTERRUPT_WORD_AUTO_CTXID, THREAD_TRACE_UTC_ERROR)); + break; + case SQ_INTERRUPT_WORD_ENCODING_INST: + pr_debug("sq_intr: inst, se %d, data 0x%x, sh %d, priv %d, wave_id %d, simd_id %d, cu_id %d, intr_data 0x%x\n", + REG_GET_FIELD(context_id0, SQ_INTERRUPT_WORD_WAVE_CTXID, SE_ID), + REG_GET_FIELD(context_id0, SQ_INTERRUPT_WORD_WAVE_CTXID, DATA), + REG_GET_FIELD(context_id0, SQ_INTERRUPT_WORD_WAVE_CTXID, SH_ID), + REG_GET_FIELD(context_id0, SQ_INTERRUPT_WORD_WAVE_CTXID, PRIV), + REG_GET_FIELD(context_id0, SQ_INTERRUPT_WORD_WAVE_CTXID, WAVE_ID), + REG_GET_FIELD(context_id0, SQ_INTERRUPT_WORD_WAVE_CTXID, SIMD_ID), + REG_GET_FIELD(context_id0, SQ_INTERRUPT_WORD_WAVE_CTXID, CU_ID), + sq_int_data); + break; + case SQ_INTERRUPT_WORD_ENCODING_ERROR: + sq_intr_err = REG_GET_FIELD(sq_int_data, KFD_SQ_INT_DATA, ERR_TYPE); + pr_warn("sq_intr: error, se %d, data 0x%x, sh %d, priv %d, wave_id %d, simd_id %d, cu_id %d, err_type %d\n", + REG_GET_FIELD(context_id0, SQ_INTERRUPT_WORD_WAVE_CTXID, SE_ID), + REG_GET_FIELD(context_id0, SQ_INTERRUPT_WORD_WAVE_CTXID, DATA), + REG_GET_FIELD(context_id0, SQ_INTERRUPT_WORD_WAVE_CTXID, SH_ID), + REG_GET_FIELD(context_id0, SQ_INTERRUPT_WORD_WAVE_CTXID, PRIV), + REG_GET_FIELD(context_id0, SQ_INTERRUPT_WORD_WAVE_CTXID, WAVE_ID), + REG_GET_FIELD(context_id0, SQ_INTERRUPT_WORD_WAVE_CTXID, SIMD_ID), + REG_GET_FIELD(context_id0, SQ_INTERRUPT_WORD_WAVE_CTXID, CU_ID), + sq_intr_err); + if (sq_intr_err != SQ_INTERRUPT_ERROR_TYPE_ILLEGAL_INST && + sq_intr_err != SQ_INTERRUPT_ERROR_TYPE_MEMVIOL) { + kfd_signal_hw_exception_event(pasid); + amdgpu_amdkfd_gpu_reset(dev->kgd); + return; + } + break; + default: + break; + } + kfd_signal_event_interrupt(pasid, context_id0 & 0xffffff, 24); + } else if (source_id == SOC15_INTSRC_CP_BAD_OPCODE) kfd_signal_hw_exception_event(pasid); } else if (client_id == SOC15_IH_CLIENTID_SDMA0 || client_id == SOC15_IH_CLIENTID_SDMA1 || @@ -136,7 +251,7 @@ static void event_interrupt_wq_v9(struct kfd_dev *dev, client_id == SOC15_IH_CLIENTID_SDMA6 || client_id == SOC15_IH_CLIENTID_SDMA7) { if (source_id == SOC15_INTSRC_SDMA_TRAP) - kfd_signal_event_interrupt(pasid, context_id & 0xfffffff, 28); + kfd_signal_event_interrupt(pasid, context_id0 & 0xfffffff, 28); } else if (client_id == SOC15_IH_CLIENTID_VMC || client_id == SOC15_IH_CLIENTID_VMC1 || client_id == SOC15_IH_CLIENTID_UTCL2) { diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_iommu.c b/drivers/gpu/drm/amd/amdkfd/kfd_iommu.c index 9318936aa805..5a1f2433632b 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_iommu.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_iommu.c @@ -135,11 +135,11 @@ int kfd_iommu_bind_process_to_device(struct kfd_process_device *pdd) */ void kfd_iommu_unbind_process(struct kfd_process *p) { - struct kfd_process_device *pdd; + int i; - list_for_each_entry(pdd, &p->per_device_data, per_device_list) - if (pdd->bound == PDD_BOUND) - amd_iommu_unbind_pasid(pdd->dev->pdev, p->pasid); + for (i = 0; i < p->n_pdds; i++) + if (p->pdds[i]->bound == PDD_BOUND) + amd_iommu_unbind_pasid(p->pdds[i]->dev->pdev, p->pasid); } /* Callback for process shutdown invoked by the IOMMU driver */ diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c index d903f694acba..e840dd581719 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c @@ -348,7 +348,7 @@ fail_create_runlist_ib: } int pm_send_query_status(struct packet_manager *pm, uint64_t fence_address, - uint32_t fence_value) + uint64_t fence_value) { uint32_t *buffer, size; int retval = 0; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager_v9.c b/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager_v9.c index dfaf771a42e6..e3ba0cd3b6fa 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager_v9.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager_v9.c @@ -283,7 +283,7 @@ static int pm_unmap_queues_v9(struct packet_manager *pm, uint32_t *buffer, } static int pm_query_status_v9(struct packet_manager *pm, uint32_t *buffer, - uint64_t fence_address, uint32_t fence_value) + uint64_t fence_address, uint64_t fence_value) { struct pm4_mes_query_status *packet; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager_vi.c b/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager_vi.c index a852e0d7d804..08442e7d9944 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager_vi.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager_vi.c @@ -263,7 +263,7 @@ static int pm_unmap_queues_vi(struct packet_manager *pm, uint32_t *buffer, } static int pm_query_status_vi(struct packet_manager *pm, uint32_t *buffer, - uint64_t fence_address, uint32_t fence_value) + uint64_t fence_address, uint64_t fence_value) { struct pm4_mes_query_status *packet; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h index d8c8b5ff449a..0b6595f7acda 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h @@ -45,6 +45,7 @@ #include <linux/swap.h> #include "amd_shared.h" +#include "amdgpu.h" #define KFD_MAX_RING_ENTRY_SIZE 8 @@ -649,12 +650,6 @@ enum kfd_pdd_bound { /* Data that is per-process-per device. */ struct kfd_process_device { - /* - * List of all per-device data for a process. - * Starts from kfd_process.per_device_data. - */ - struct list_head per_device_list; - /* The device that owns this data. */ struct kfd_dev *dev; @@ -771,10 +766,11 @@ struct kfd_process { u32 pasid; /* - * List of kfd_process_device structures, + * Array of kfd_process_device pointers, * one for each device the process is using. */ - struct list_head per_device_data; + struct kfd_process_device *pdds[MAX_GPU_INSTANCE]; + uint32_t n_pdds; struct process_queue_manager pqm; @@ -872,14 +868,6 @@ void *kfd_process_device_translate_handle(struct kfd_process_device *p, void kfd_process_device_remove_obj_handle(struct kfd_process_device *pdd, int handle); -/* Process device data iterator */ -struct kfd_process_device *kfd_get_first_process_device_data( - struct kfd_process *p); -struct kfd_process_device *kfd_get_next_process_device_data( - struct kfd_process *p, - struct kfd_process_device *pdd); -bool kfd_has_process_device_data(struct kfd_process *p); - /* PASIDs */ int kfd_pasid_init(void); void kfd_pasid_exit(void); @@ -1012,8 +1000,8 @@ int pqm_get_wave_state(struct process_queue_manager *pqm, u32 *ctl_stack_used_size, u32 *save_area_used_size); -int amdkfd_fence_wait_timeout(unsigned int *fence_addr, - unsigned int fence_value, +int amdkfd_fence_wait_timeout(uint64_t *fence_addr, + uint64_t fence_value, unsigned int timeout_ms); /* Packet Manager */ @@ -1049,7 +1037,7 @@ struct packet_manager_funcs { uint32_t filter_param, bool reset, unsigned int sdma_engine); int (*query_status)(struct packet_manager *pm, uint32_t *buffer, - uint64_t fence_address, uint32_t fence_value); + uint64_t fence_address, uint64_t fence_value); int (*release_mem)(uint64_t gpu_addr, uint32_t *buffer); /* Packet sizes */ @@ -1071,7 +1059,7 @@ int pm_send_set_resources(struct packet_manager *pm, struct scheduling_resources *res); int pm_send_runlist(struct packet_manager *pm, struct list_head *dqm_queues); int pm_send_query_status(struct packet_manager *pm, uint64_t fence_address, - uint32_t fence_value); + uint64_t fence_value); int pm_send_unmap_queue(struct packet_manager *pm, enum kfd_queue_type type, enum kfd_unmap_queues_filter mode, diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c index f5237997fa18..d97e330a5022 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c @@ -505,7 +505,7 @@ static int kfd_sysfs_create_file(struct kfd_process *p, struct attribute *attr, static int kfd_procfs_add_sysfs_stats(struct kfd_process *p) { int ret = 0; - struct kfd_process_device *pdd; + int i; char stats_dir_filename[MAX_SYSFS_FILENAME_LEN]; if (!p) @@ -520,7 +520,8 @@ static int kfd_procfs_add_sysfs_stats(struct kfd_process *p) * - proc/<pid>/stats_<gpuid>/evicted_ms * - proc/<pid>/stats_<gpuid>/cu_occupancy */ - list_for_each_entry(pdd, &p->per_device_data, per_device_list) { + for (i = 0; i < p->n_pdds; i++) { + struct kfd_process_device *pdd = p->pdds[i]; struct kobject *kobj_stats; snprintf(stats_dir_filename, MAX_SYSFS_FILENAME_LEN, @@ -571,7 +572,7 @@ err: static int kfd_procfs_add_sysfs_files(struct kfd_process *p) { int ret = 0; - struct kfd_process_device *pdd; + int i; if (!p) return -EINVAL; @@ -584,7 +585,9 @@ static int kfd_procfs_add_sysfs_files(struct kfd_process *p) * - proc/<pid>/vram_<gpuid> * - proc/<pid>/sdma_<gpuid> */ - list_for_each_entry(pdd, &p->per_device_data, per_device_list) { + for (i = 0; i < p->n_pdds; i++) { + struct kfd_process_device *pdd = p->pdds[i]; + snprintf(pdd->vram_filename, MAX_SYSFS_FILENAME_LEN, "vram_%u", pdd->dev->id); ret = kfd_sysfs_create_file(p, &pdd->attr_vram, pdd->vram_filename); @@ -881,21 +884,23 @@ void kfd_unref_process(struct kfd_process *p) kref_put(&p->ref, kfd_process_ref_release); } + static void kfd_process_device_free_bos(struct kfd_process_device *pdd) { struct kfd_process *p = pdd->process; void *mem; int id; + int i; /* * Remove all handles from idr and release appropriate * local memory object */ idr_for_each_entry(&pdd->alloc_idr, mem, id) { - struct kfd_process_device *peer_pdd; - list_for_each_entry(peer_pdd, &p->per_device_data, - per_device_list) { + for (i = 0; i < p->n_pdds; i++) { + struct kfd_process_device *peer_pdd = p->pdds[i]; + if (!peer_pdd->vm) continue; amdgpu_amdkfd_gpuvm_unmap_memory_from_gpu( @@ -909,18 +914,19 @@ static void kfd_process_device_free_bos(struct kfd_process_device *pdd) static void kfd_process_free_outstanding_kfd_bos(struct kfd_process *p) { - struct kfd_process_device *pdd; + int i; - list_for_each_entry(pdd, &p->per_device_data, per_device_list) - kfd_process_device_free_bos(pdd); + for (i = 0; i < p->n_pdds; i++) + kfd_process_device_free_bos(p->pdds[i]); } static void kfd_process_destroy_pdds(struct kfd_process *p) { - struct kfd_process_device *pdd, *temp; + int i; + + for (i = 0; i < p->n_pdds; i++) { + struct kfd_process_device *pdd = p->pdds[i]; - list_for_each_entry_safe(pdd, temp, &p->per_device_data, - per_device_list) { pr_debug("Releasing pdd (topology id %d) for process (pasid 0x%x)\n", pdd->dev->id, p->pasid); @@ -929,11 +935,6 @@ static void kfd_process_destroy_pdds(struct kfd_process *p) pdd->dev->kgd, pdd->vm); fput(pdd->drm_file); } - else if (pdd->vm) - amdgpu_amdkfd_gpuvm_destroy_process_vm( - pdd->dev->kgd, pdd->vm); - - list_del(&pdd->per_device_list); if (pdd->qpd.cwsr_kaddr && !pdd->qpd.cwsr_base) free_pages((unsigned long)pdd->qpd.cwsr_kaddr, @@ -955,7 +956,9 @@ static void kfd_process_destroy_pdds(struct kfd_process *p) } kfree(pdd); + p->pdds[i] = NULL; } + p->n_pdds = 0; } /* No process locking is needed in this function, because the process @@ -967,7 +970,7 @@ static void kfd_process_wq_release(struct work_struct *work) { struct kfd_process *p = container_of(work, struct kfd_process, release_work); - struct kfd_process_device *pdd; + int i; /* Remove the procfs files */ if (p->kobj) { @@ -976,7 +979,9 @@ static void kfd_process_wq_release(struct work_struct *work) kobject_put(p->kobj_queues); p->kobj_queues = NULL; - list_for_each_entry(pdd, &p->per_device_data, per_device_list) { + for (i = 0; i < p->n_pdds; i++) { + struct kfd_process_device *pdd = p->pdds[i]; + sysfs_remove_file(p->kobj, &pdd->attr_vram); sysfs_remove_file(p->kobj, &pdd->attr_sdma); sysfs_remove_file(p->kobj, &pdd->attr_evict); @@ -1036,7 +1041,7 @@ static void kfd_process_notifier_release(struct mmu_notifier *mn, struct mm_struct *mm) { struct kfd_process *p; - struct kfd_process_device *pdd = NULL; + int i; /* * The kfd_process structure can not be free because the @@ -1060,8 +1065,8 @@ static void kfd_process_notifier_release(struct mmu_notifier *mn, * pdd is in debug mode, we should first force unregistration, * then we will be able to destroy the queues */ - list_for_each_entry(pdd, &p->per_device_data, per_device_list) { - struct kfd_dev *dev = pdd->dev; + for (i = 0; i < p->n_pdds; i++) { + struct kfd_dev *dev = p->pdds[i]->dev; mutex_lock(kfd_get_dbgmgr_mutex()); if (dev && dev->dbgmgr && dev->dbgmgr->pasid == p->pasid) { @@ -1098,11 +1103,11 @@ static const struct mmu_notifier_ops kfd_process_mmu_notifier_ops = { static int kfd_process_init_cwsr_apu(struct kfd_process *p, struct file *filep) { unsigned long offset; - struct kfd_process_device *pdd; + int i; - list_for_each_entry(pdd, &p->per_device_data, per_device_list) { - struct kfd_dev *dev = pdd->dev; - struct qcm_process_device *qpd = &pdd->qpd; + for (i = 0; i < p->n_pdds; i++) { + struct kfd_dev *dev = p->pdds[i]->dev; + struct qcm_process_device *qpd = &p->pdds[i]->qpd; if (!dev->cwsr_enabled || qpd->cwsr_kaddr || qpd->cwsr_base) continue; @@ -1199,7 +1204,7 @@ static struct kfd_process *create_process(const struct task_struct *thread) mutex_init(&process->mutex); process->mm = thread->mm; process->lead_thread = thread->group_leader; - INIT_LIST_HEAD(&process->per_device_data); + process->n_pdds = 0; INIT_DELAYED_WORK(&process->eviction_work, evict_process_worker); INIT_DELAYED_WORK(&process->restore_work, restore_process_worker); process->last_restore_timestamp = get_jiffies_64(); @@ -1290,11 +1295,11 @@ static int init_doorbell_bitmap(struct qcm_process_device *qpd, struct kfd_process_device *kfd_get_process_device_data(struct kfd_dev *dev, struct kfd_process *p) { - struct kfd_process_device *pdd = NULL; + int i; - list_for_each_entry(pdd, &p->per_device_data, per_device_list) - if (pdd->dev == dev) - return pdd; + for (i = 0; i < p->n_pdds; i++) + if (p->pdds[i]->dev == dev) + return p->pdds[i]; return NULL; } @@ -1304,6 +1309,8 @@ struct kfd_process_device *kfd_create_process_device_data(struct kfd_dev *dev, { struct kfd_process_device *pdd = NULL; + if (WARN_ON_ONCE(p->n_pdds >= MAX_GPU_INSTANCE)) + return NULL; pdd = kzalloc(sizeof(*pdd), GFP_KERNEL); if (!pdd) return NULL; @@ -1332,7 +1339,7 @@ struct kfd_process_device *kfd_create_process_device_data(struct kfd_dev *dev, pdd->vram_usage = 0; pdd->sdma_past_activity_counter = 0; atomic64_set(&pdd->evict_duration_counter, 0); - list_add(&pdd->per_device_list, &p->per_device_data); + p->pdds[p->n_pdds++] = pdd; /* Init idr used for memory handle translation */ idr_init(&pdd->alloc_idr); @@ -1365,19 +1372,18 @@ int kfd_process_device_init_vm(struct kfd_process_device *pdd, struct kfd_dev *dev; int ret; + if (!drm_file) + return -EINVAL; + if (pdd->vm) - return drm_file ? -EBUSY : 0; + return -EBUSY; p = pdd->process; dev = pdd->dev; - if (drm_file) - ret = amdgpu_amdkfd_gpuvm_acquire_process_vm( - dev->kgd, drm_file, p->pasid, - &pdd->vm, &p->kgd_process_info, &p->ef); - else - ret = amdgpu_amdkfd_gpuvm_create_process_vm(dev->kgd, p->pasid, - &pdd->vm, &p->kgd_process_info, &p->ef); + ret = amdgpu_amdkfd_gpuvm_acquire_process_vm( + dev->kgd, drm_file, p->pasid, + &pdd->vm, &p->kgd_process_info, &p->ef); if (ret) { pr_err("Failed to create process VM object\n"); return ret; @@ -1399,8 +1405,6 @@ int kfd_process_device_init_vm(struct kfd_process_device *pdd, err_init_cwsr: err_reserve_ib_mem: kfd_process_device_free_bos(pdd); - if (!drm_file) - amdgpu_amdkfd_gpuvm_destroy_process_vm(dev->kgd, pdd->vm); pdd->vm = NULL; return ret; @@ -1425,6 +1429,9 @@ struct kfd_process_device *kfd_bind_process_to_device(struct kfd_dev *dev, return ERR_PTR(-ENOMEM); } + if (!pdd->vm) + return ERR_PTR(-ENODEV); + /* * signal runtime-pm system to auto resume and prevent * further runtime suspend once device pdd is created until @@ -1442,10 +1449,6 @@ struct kfd_process_device *kfd_bind_process_to_device(struct kfd_dev *dev, if (err) goto out; - err = kfd_process_device_init_vm(pdd, NULL); - if (err) - goto out; - /* * make sure that runtime_usage counter is incremented just once * per pdd @@ -1464,28 +1467,6 @@ out: return ERR_PTR(err); } -struct kfd_process_device *kfd_get_first_process_device_data( - struct kfd_process *p) -{ - return list_first_entry(&p->per_device_data, - struct kfd_process_device, - per_device_list); -} - -struct kfd_process_device *kfd_get_next_process_device_data( - struct kfd_process *p, - struct kfd_process_device *pdd) -{ - if (list_is_last(&pdd->per_device_list, &p->per_device_data)) - return NULL; - return list_next_entry(pdd, per_device_list); -} - -bool kfd_has_process_device_data(struct kfd_process *p) -{ - return !(list_empty(&p->per_device_data)); -} - /* Create specific handle mapped to mem from process local memory idr * Assumes that the process lock is held. */ @@ -1561,11 +1542,13 @@ struct kfd_process *kfd_lookup_process_by_mm(const struct mm_struct *mm) */ int kfd_process_evict_queues(struct kfd_process *p) { - struct kfd_process_device *pdd; int r = 0; + int i; unsigned int n_evicted = 0; - list_for_each_entry(pdd, &p->per_device_data, per_device_list) { + for (i = 0; i < p->n_pdds; i++) { + struct kfd_process_device *pdd = p->pdds[i]; + r = pdd->dev->dqm->ops.evict_process_queues(pdd->dev->dqm, &pdd->qpd); if (r) { @@ -1581,7 +1564,9 @@ fail: /* To keep state consistent, roll back partial eviction by * restoring queues */ - list_for_each_entry(pdd, &p->per_device_data, per_device_list) { + for (i = 0; i < p->n_pdds; i++) { + struct kfd_process_device *pdd = p->pdds[i]; + if (n_evicted == 0) break; if (pdd->dev->dqm->ops.restore_process_queues(pdd->dev->dqm, @@ -1597,10 +1582,12 @@ fail: /* kfd_process_restore_queues - Restore all user queues of a process */ int kfd_process_restore_queues(struct kfd_process *p) { - struct kfd_process_device *pdd; int r, ret = 0; + int i; + + for (i = 0; i < p->n_pdds; i++) { + struct kfd_process_device *pdd = p->pdds[i]; - list_for_each_entry(pdd, &p->per_device_data, per_device_list) { r = pdd->dev->dqm->ops.restore_process_queues(pdd->dev->dqm, &pdd->qpd); if (r) { diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c index eb1635ac8988..95a6c36cea4c 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c @@ -126,10 +126,10 @@ int pqm_set_gws(struct process_queue_manager *pqm, unsigned int qid, void kfd_process_dequeue_from_all_devices(struct kfd_process *p) { - struct kfd_process_device *pdd; + int i; - list_for_each_entry(pdd, &p->per_device_data, per_device_list) - kfd_process_dequeue_from_device(pdd); + for (i = 0; i < p->n_pdds; i++) + kfd_process_dequeue_from_device(p->pdds[i]); } int pqm_init(struct process_queue_manager *pqm, struct kfd_process *p) diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c b/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c index 17d1736367ea..246522423559 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c @@ -81,7 +81,7 @@ static ssize_t kfd_smi_ev_read(struct file *filep, char __user *user, struct kfd_smi_client *client = filep->private_data; unsigned char *buf; - buf = kmalloc(MAX_KFIFO_SIZE * sizeof(*buf), GFP_KERNEL); + buf = kmalloc_array(MAX_KFIFO_SIZE, sizeof(*buf), GFP_KERNEL); if (!buf) return -ENOMEM; diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index 00edf78975b1..b34ab76c5f4c 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -121,7 +121,7 @@ MODULE_FIRMWARE(FIRMWARE_NAVI12_DMCU); * DOC: overview * * The AMDgpu display manager, **amdgpu_dm** (or even simpler, - * **dm**) sits between DRM and DC. It acts as a liason, converting DRM + * **dm**) sits between DRM and DC. It acts as a liaison, converting DRM * requests into DC requests, and DC responses into DRM responses. * * The root control structure is &struct amdgpu_display_manager. @@ -130,6 +130,7 @@ MODULE_FIRMWARE(FIRMWARE_NAVI12_DMCU); /* basic init/fini API */ static int amdgpu_dm_init(struct amdgpu_device *adev); static void amdgpu_dm_fini(struct amdgpu_device *adev); +static bool is_freesync_video_mode(const struct drm_display_mode *mode, struct amdgpu_dm_connector *aconnector); static enum drm_mode_subconnector get_subconnector_type(struct dc_link *link) { @@ -371,14 +372,14 @@ static void dm_pflip_high_irq(void *interrupt_params) /* IRQ could occur when in initial stage */ /* TODO work and BO cleanup */ if (amdgpu_crtc == NULL) { - DRM_DEBUG_DRIVER("CRTC is null, returning.\n"); + DC_LOG_PFLIP("CRTC is null, returning.\n"); return; } spin_lock_irqsave(&adev_to_drm(adev)->event_lock, flags); if (amdgpu_crtc->pflip_status != AMDGPU_FLIP_SUBMITTED){ - DRM_DEBUG_DRIVER("amdgpu_crtc->pflip_status = %d !=AMDGPU_FLIP_SUBMITTED(%d) on crtc:%d[%p] \n", + DC_LOG_PFLIP("amdgpu_crtc->pflip_status = %d !=AMDGPU_FLIP_SUBMITTED(%d) on crtc:%d[%p] \n", amdgpu_crtc->pflip_status, AMDGPU_FLIP_SUBMITTED, amdgpu_crtc->crtc_id, @@ -449,9 +450,9 @@ static void dm_pflip_high_irq(void *interrupt_params) amdgpu_crtc->pflip_status = AMDGPU_FLIP_NONE; spin_unlock_irqrestore(&adev_to_drm(adev)->event_lock, flags); - DRM_DEBUG_DRIVER("crtc:%d[%p], pflip_stat:AMDGPU_FLIP_NONE, vrr[%d]-fp %d\n", - amdgpu_crtc->crtc_id, amdgpu_crtc, - vrr_active, (int) !e); + DC_LOG_PFLIP("crtc:%d[%p], pflip_stat:AMDGPU_FLIP_NONE, vrr[%d]-fp %d\n", + amdgpu_crtc->crtc_id, amdgpu_crtc, + vrr_active, (int) !e); } static void dm_vupdate_high_irq(void *interrupt_params) @@ -459,6 +460,9 @@ static void dm_vupdate_high_irq(void *interrupt_params) struct common_irq_params *irq_params = interrupt_params; struct amdgpu_device *adev = irq_params->adev; struct amdgpu_crtc *acrtc; + struct drm_device *drm_dev; + struct drm_vblank_crtc *vblank; + ktime_t frame_duration_ns, previous_timestamp; unsigned long flags; int vrr_active; @@ -466,8 +470,19 @@ static void dm_vupdate_high_irq(void *interrupt_params) if (acrtc) { vrr_active = amdgpu_dm_vrr_active_irq(acrtc); + drm_dev = acrtc->base.dev; + vblank = &drm_dev->vblank[acrtc->base.index]; + previous_timestamp = atomic64_read(&irq_params->previous_timestamp); + frame_duration_ns = vblank->time - previous_timestamp; - DRM_DEBUG_VBL("crtc:%d, vupdate-vrr:%d\n", + if (frame_duration_ns > 0) { + trace_amdgpu_refresh_rate_track(acrtc->base.index, + frame_duration_ns, + ktime_divns(NSEC_PER_SEC, frame_duration_ns)); + atomic64_set(&irq_params->previous_timestamp, vblank->time); + } + + DC_LOG_VBLANK("crtc:%d, vupdate-vrr:%d\n", acrtc->crtc_id, vrr_active); @@ -520,7 +535,7 @@ static void dm_crtc_high_irq(void *interrupt_params) vrr_active = amdgpu_dm_vrr_active_irq(acrtc); - DRM_DEBUG_VBL("crtc:%d, vupdate-vrr:%d, planes:%d\n", acrtc->crtc_id, + DC_LOG_VBLANK("crtc:%d, vupdate-vrr:%d, planes:%d\n", acrtc->crtc_id, vrr_active, acrtc->dm_irq_params.active_planes); /** @@ -923,6 +938,32 @@ static int dm_dmub_hw_init(struct amdgpu_device *adev) } #if defined(CONFIG_DRM_AMD_DC_DCN) +#define DMUB_TRACE_MAX_READ 64 +static void dm_dmub_trace_high_irq(void *interrupt_params) +{ + struct common_irq_params *irq_params = interrupt_params; + struct amdgpu_device *adev = irq_params->adev; + struct amdgpu_display_manager *dm = &adev->dm; + struct dmcub_trace_buf_entry entry = { 0 }; + uint32_t count = 0; + + do { + if (dc_dmub_srv_get_dmub_outbox0_msg(dm->dc, &entry)) { + trace_amdgpu_dmub_trace_high_irq(entry.trace_code, entry.tick_count, + entry.param0, entry.param1); + + DRM_DEBUG_DRIVER("trace_code:%u, tick_count:%u, param0:%u, param1:%u\n", + entry.trace_code, entry.tick_count, entry.param0, entry.param1); + } else + break; + + count++; + + } while (count <= DMUB_TRACE_MAX_READ); + + ASSERT(count <= DMUB_TRACE_MAX_READ); +} + static void mmhub_read_system_context(struct amdgpu_device *adev, struct dc_phy_addr_space_config *pa_config) { uint64_t pt_base; @@ -987,13 +1028,12 @@ static void event_mall_stutter(struct work_struct *work) if (vblank_work->enable) dm->active_vblank_irq_count++; - else + else if(dm->active_vblank_irq_count) dm->active_vblank_irq_count--; dc_allow_idle_optimizations(dm->dc, dm->active_vblank_irq_count == 0); - DRM_DEBUG_DRIVER("Allow idle optimizations (MALL): %d\n", dm->active_vblank_irq_count == 0); - + DRM_DEBUG_KMS("Allow idle optimizations (MALL): %d\n", dm->active_vblank_irq_count == 0); mutex_unlock(&dm->dc_lock); } @@ -1809,8 +1849,8 @@ static void dm_gpureset_toggle_interrupts(struct amdgpu_device *adev, if (acrtc && state->stream_status[i].plane_count != 0) { irq_source = IRQ_TYPE_PFLIP + acrtc->otg_inst; rc = dc_interrupt_set(adev->dm.dc, irq_source, enable) ? 0 : -EBUSY; - DRM_DEBUG("crtc %d - vupdate irq %sabling: r=%d\n", - acrtc->crtc_id, enable ? "en" : "dis", rc); + DRM_DEBUG_VBL("crtc %d - vupdate irq %sabling: r=%d\n", + acrtc->crtc_id, enable ? "en" : "dis", rc); if (rc) DRM_WARN("Failed to %s pflip interrupts\n", enable ? "enable" : "disable"); @@ -2512,11 +2552,14 @@ static void handle_hpd_irq(void *param) struct drm_connector *connector = &aconnector->base; struct drm_device *dev = connector->dev; enum dc_connection_type new_connection_type = dc_connection_none; -#ifdef CONFIG_DRM_AMD_DC_HDCP struct amdgpu_device *adev = drm_to_adev(dev); +#ifdef CONFIG_DRM_AMD_DC_HDCP struct dm_connector_state *dm_con_state = to_dm_connector_state(connector->state); #endif + if (adev->dm.disable_hpd_irq) + return; + /* * In case of failure or MST no need to update connector status or notify the OS * since (for MST case) MST does this in its own context. @@ -2656,6 +2699,10 @@ static void handle_hpd_rx_irq(void *param) memset(&hpd_irq_data, 0, sizeof(hpd_irq_data)); + if (adev->dm.disable_hpd_irq) + return; + + /* * TODO:Temporary add mutex to protect hpd interrupt not have a gpio * conflict, after implement i2c helper, this mutex should be @@ -3104,6 +3151,28 @@ static int dcn10_register_irq_handlers(struct amdgpu_device *adev) } + if (dc->ctx->dmub_srv) { + i = DCN_1_0__SRCID__DMCUB_OUTBOX_HIGH_PRIORITY_READY_INT; + r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_DCE, i, &adev->dmub_trace_irq); + + if (r) { + DRM_ERROR("Failed to add dmub trace irq id!\n"); + return r; + } + + int_params.int_context = INTERRUPT_HIGH_IRQ_CONTEXT; + int_params.irq_source = + dc_interrupt_to_irq_source(dc, i, 0); + + c_irq_params = &adev->dm.dmub_trace_params[0]; + + c_irq_params->adev = adev; + c_irq_params->irq_src = int_params.irq_source; + + amdgpu_dm_irq_register_interrupt(adev, &int_params, + dm_dmub_trace_high_irq, c_irq_params); + } + /* HPD */ r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_DCE, DCN_1_0__SRCID__DC_HPD1_INT, &adev->hpd_irq); @@ -4163,6 +4232,7 @@ static bool dm_plane_format_mod_supported(struct drm_plane *plane, { struct amdgpu_device *adev = drm_to_adev(plane->dev); const struct drm_format_info *info = drm_format_info(format); + int i; enum dm_micro_swizzle microtile = modifier_gfx9_swizzle_mode(modifier) & 3; @@ -4170,17 +4240,21 @@ static bool dm_plane_format_mod_supported(struct drm_plane *plane, return false; /* - * We always have to allow this modifier, because core DRM still - * checks LINEAR support if userspace does not provide modifers. + * We always have to allow these modifiers: + * 1. Core DRM checks for LINEAR support if userspace does not provide modifiers. + * 2. Not passing any modifiers is the same as explicitly passing INVALID. */ - if (modifier == DRM_FORMAT_MOD_LINEAR) + if (modifier == DRM_FORMAT_MOD_LINEAR || + modifier == DRM_FORMAT_MOD_INVALID) { return true; + } - /* - * The arbitrary tiling support for multiplane formats has not been hooked - * up. - */ - if (info->num_planes > 1) + /* Check that the modifier is on the list of the plane's supported modifiers. */ + for (i = 0; i < plane->modifier_count; i++) { + if (modifier == plane->modifiers[i]) + break; + } + if (i == plane->modifier_count) return false; /* @@ -4201,6 +4275,10 @@ static bool dm_plane_format_mod_supported(struct drm_plane *plane, /* Per radeonsi comments 16/64 bpp are more complicated. */ if (info->cpp[0] != 4) return false; + /* We support multi-planar formats, but not when combined with + * additional DCC metadata planes. */ + if (info->num_planes > 1) + return false; } return true; @@ -4401,7 +4479,7 @@ add_gfx10_3_modifiers(const struct amdgpu_device *adev, AMD_FMT_MOD_SET(DCC_CONSTANT_ENCODE, 1) | AMD_FMT_MOD_SET(DCC_INDEPENDENT_64B, 1) | AMD_FMT_MOD_SET(DCC_INDEPENDENT_128B, 1) | - AMD_FMT_MOD_SET(DCC_MAX_COMPRESSED_BLOCK, AMD_FMT_MOD_DCC_BLOCK_128B)); + AMD_FMT_MOD_SET(DCC_MAX_COMPRESSED_BLOCK, AMD_FMT_MOD_DCC_BLOCK_64B)); add_modifier(mods, size, capacity, AMD_FMT_MOD | AMD_FMT_MOD_SET(TILE, AMD_FMT_MOD_TILE_GFX9_64K_R_X) | @@ -4413,7 +4491,7 @@ add_gfx10_3_modifiers(const struct amdgpu_device *adev, AMD_FMT_MOD_SET(DCC_CONSTANT_ENCODE, 1) | AMD_FMT_MOD_SET(DCC_INDEPENDENT_64B, 1) | AMD_FMT_MOD_SET(DCC_INDEPENDENT_128B, 1) | - AMD_FMT_MOD_SET(DCC_MAX_COMPRESSED_BLOCK, AMD_FMT_MOD_DCC_BLOCK_128B)); + AMD_FMT_MOD_SET(DCC_MAX_COMPRESSED_BLOCK, AMD_FMT_MOD_DCC_BLOCK_64B)); add_modifier(mods, size, capacity, AMD_FMT_MOD | AMD_FMT_MOD_SET(TILE, AMD_FMT_MOD_TILE_GFX9_64K_R_X) | @@ -4892,8 +4970,8 @@ static void update_stream_scaling_settings(const struct drm_display_mode *mode, stream->src = src; stream->dst = dst; - DRM_DEBUG_DRIVER("Destination Rectangle x:%d y:%d width:%d height:%d\n", - dst.x, dst.y, dst.width, dst.height); + DRM_DEBUG_KMS("Destination Rectangle x:%d y:%d width:%d height:%d\n", + dst.x, dst.y, dst.width, dst.height); } @@ -5106,15 +5184,27 @@ static void fill_stream_properties_from_drm_display_mode( timing_out->hdmi_vic = hv_frame.vic; } - timing_out->h_addressable = mode_in->hdisplay; - timing_out->h_total = mode_in->htotal; - timing_out->h_sync_width = mode_in->hsync_end - mode_in->hsync_start; - timing_out->h_front_porch = mode_in->hsync_start - mode_in->hdisplay; - timing_out->v_total = mode_in->vtotal; - timing_out->v_addressable = mode_in->vdisplay; - timing_out->v_front_porch = mode_in->vsync_start - mode_in->vdisplay; - timing_out->v_sync_width = mode_in->vsync_end - mode_in->vsync_start; - timing_out->pix_clk_100hz = mode_in->clock * 10; + if (is_freesync_video_mode(mode_in, aconnector)) { + timing_out->h_addressable = mode_in->hdisplay; + timing_out->h_total = mode_in->htotal; + timing_out->h_sync_width = mode_in->hsync_end - mode_in->hsync_start; + timing_out->h_front_porch = mode_in->hsync_start - mode_in->hdisplay; + timing_out->v_total = mode_in->vtotal; + timing_out->v_addressable = mode_in->vdisplay; + timing_out->v_front_porch = mode_in->vsync_start - mode_in->vdisplay; + timing_out->v_sync_width = mode_in->vsync_end - mode_in->vsync_start; + timing_out->pix_clk_100hz = mode_in->clock * 10; + } else { + timing_out->h_addressable = mode_in->crtc_hdisplay; + timing_out->h_total = mode_in->crtc_htotal; + timing_out->h_sync_width = mode_in->crtc_hsync_end - mode_in->crtc_hsync_start; + timing_out->h_front_porch = mode_in->crtc_hsync_start - mode_in->crtc_hdisplay; + timing_out->v_total = mode_in->crtc_vtotal; + timing_out->v_addressable = mode_in->crtc_vdisplay; + timing_out->v_front_porch = mode_in->crtc_vsync_start - mode_in->crtc_vdisplay; + timing_out->v_sync_width = mode_in->crtc_vsync_end - mode_in->crtc_vsync_start; + timing_out->pix_clk_100hz = mode_in->crtc_clock * 10; + } timing_out->aspect_ratio = get_aspect_ratio(mode_in); @@ -5234,9 +5324,14 @@ create_fake_sink(struct amdgpu_dm_connector *aconnector) static void set_multisync_trigger_params( struct dc_stream_state *stream) { + struct dc_stream_state *master = NULL; + if (stream->triggered_crtc_reset.enabled) { - stream->triggered_crtc_reset.event = CRTC_EVENT_VSYNC_RISING; - stream->triggered_crtc_reset.delay = TRIGGER_DELAY_NEXT_LINE; + master = stream->triggered_crtc_reset.event_source; + stream->triggered_crtc_reset.event = + master->timing.flags.VSYNC_POSITIVE_POLARITY ? + CRTC_EVENT_VSYNC_RISING : CRTC_EVENT_VSYNC_FALLING; + stream->triggered_crtc_reset.delay = TRIGGER_DELAY_NEXT_PIXEL; } } @@ -5266,6 +5361,7 @@ static void set_master_stream(struct dc_stream_state *stream_set[], static void dm_enable_per_frame_crtc_master_sync(struct dc_state *context) { int i = 0; + struct dc_stream_state *stream; if (context->stream_count < 2) return; @@ -5277,9 +5373,18 @@ static void dm_enable_per_frame_crtc_master_sync(struct dc_state *context) * crtc_sync_master.multi_sync_enabled flag * For now it's set to false */ - set_multisync_trigger_params(context->streams[i]); } + set_master_stream(context->streams, context->stream_count); + + for (i = 0; i < context->stream_count ; i++) { + stream = context->streams[i]; + + if (!stream) + continue; + + set_multisync_trigger_params(stream); + } } static struct drm_display_mode * @@ -5335,7 +5440,7 @@ get_highest_refresh_rate_mode(struct amdgpu_dm_connector *aconnector, return m_pref; } -static bool is_freesync_video_mode(struct drm_display_mode *mode, +static bool is_freesync_video_mode(const struct drm_display_mode *mode, struct amdgpu_dm_connector *aconnector) { struct drm_display_mode *high_mode; @@ -5458,7 +5563,7 @@ create_stream_for_sink(struct amdgpu_dm_connector *aconnector, if (recalculate_timing) drm_mode_set_crtcinfo(&saved_mode, 0); - else + else if (!dm_state) drm_mode_set_crtcinfo(&mode, 0); /* @@ -5636,8 +5741,8 @@ static inline int dm_set_vupdate_irq(struct drm_crtc *crtc, bool enable) rc = dc_interrupt_set(adev->dm.dc, irq_source, enable) ? 0 : -EBUSY; - DRM_DEBUG_DRIVER("crtc %d - vupdate irq %sabling: r=%d\n", - acrtc->crtc_id, enable ? "en" : "dis", rc); + DRM_DEBUG_VBL("crtc %d - vupdate irq %sabling: r=%d\n", + acrtc->crtc_id, enable ? "en" : "dis", rc); return rc; } @@ -6075,6 +6180,15 @@ create_validate_stream_for_sink(struct amdgpu_dm_connector *aconnector, } while (stream == NULL && requested_bpc >= 6); + if (dc_result == DC_FAIL_ENC_VALIDATE && !aconnector->force_yuv420_output) { + DRM_DEBUG_KMS("Retry forcing YCbCr420 encoding\n"); + + aconnector->force_yuv420_output = true; + stream = create_validate_stream_for_sink(aconnector, drm_mode, + dm_state, old_stream); + aconnector->force_yuv420_output = false; + } + return stream; } @@ -6577,7 +6691,7 @@ static int dm_plane_helper_prepare_fb(struct drm_plane *plane, int r; if (!new_state->fb) { - DRM_DEBUG_DRIVER("No FB bound\n"); + DRM_DEBUG_KMS("No FB bound\n"); return 0; } @@ -7295,7 +7409,7 @@ static void amdgpu_dm_connector_add_freesync_modes(struct drm_connector *connect if (!(amdgpu_freesync_vid_mode && edid)) return; - + if (amdgpu_dm_connector->max_vfreq - amdgpu_dm_connector->min_vfreq > 10) amdgpu_dm_connector->num_modes += add_fs_modes(amdgpu_dm_connector); @@ -7810,11 +7924,11 @@ static void handle_cursor_update(struct drm_plane *plane, if (!plane->state->fb && !old_plane_state->fb) return; - DRM_DEBUG_DRIVER("%s: crtc_id=%d with size %d to %d\n", - __func__, - amdgpu_crtc->crtc_id, - plane->state->crtc_w, - plane->state->crtc_h); + DC_LOG_CURSOR("%s: crtc_id=%d with size %d to %d\n", + __func__, + amdgpu_crtc->crtc_id, + plane->state->crtc_w, + plane->state->crtc_h); ret = get_cursor_position(plane, crtc, &position); if (ret) @@ -7872,8 +7986,8 @@ static void prepare_flip_isr(struct amdgpu_crtc *acrtc) /* Mark this event as consumed */ acrtc->base.state->event = NULL; - DRM_DEBUG_DRIVER("crtc:%d, pflip_stat:AMDGPU_FLIP_SUBMITTED\n", - acrtc->crtc_id); + DC_LOG_PFLIP("crtc:%d, pflip_stat:AMDGPU_FLIP_SUBMITTED\n", + acrtc->crtc_id); } static void update_freesync_state_on_stream( @@ -8179,7 +8293,7 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state, &bundle->flip_addrs[planes_count].address, afb->tmz_surface, false); - DRM_DEBUG_DRIVER("plane: id=%d dcc_en=%d\n", + DRM_DEBUG_ATOMIC("plane: id=%d dcc_en=%d\n", new_plane_state->plane->index, bundle->plane_infos[planes_count].dcc.enable); @@ -8213,7 +8327,7 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state, dc_plane, bundle->flip_addrs[planes_count].flip_timestamp_in_us); - DRM_DEBUG_DRIVER("%s Flipping to hi: 0x%x, low: 0x%x\n", + DRM_DEBUG_ATOMIC("%s Flipping to hi: 0x%x, low: 0x%x\n", __func__, bundle->flip_addrs[planes_count].address.grph.addr.high_part, bundle->flip_addrs[planes_count].address.grph.addr.low_part); @@ -8535,7 +8649,7 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state) dm_new_crtc_state = to_dm_crtc_state(new_crtc_state); dm_old_crtc_state = to_dm_crtc_state(old_crtc_state); - DRM_DEBUG_DRIVER( + DRM_DEBUG_ATOMIC( "amdgpu_crtc id:%d crtc_state_flags: enable:%d, active:%d, " "planes_changed:%d, mode_changed:%d,active_changed:%d," "connectors_changed:%d\n", @@ -8569,7 +8683,7 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state) if (modeset_required(new_crtc_state, dm_new_crtc_state->stream, dm_old_crtc_state->stream)) { - DRM_DEBUG_DRIVER("Atomic commit: SET crtc id %d: [%p]\n", acrtc->crtc_id, acrtc); + DRM_DEBUG_ATOMIC("Atomic commit: SET crtc id %d: [%p]\n", acrtc->crtc_id, acrtc); if (!dm_new_crtc_state->stream) { /* @@ -8602,7 +8716,7 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state) crtc->hwmode = new_crtc_state->mode; mode_set_reset_required = true; } else if (modereset_required(new_crtc_state)) { - DRM_DEBUG_DRIVER("Atomic commit: RESET. crtc id %d:[%p]\n", acrtc->crtc_id, acrtc); + DRM_DEBUG_ATOMIC("Atomic commit: RESET. crtc id %d:[%p]\n", acrtc->crtc_id, acrtc); /* i.e. reset mode */ if (dm_old_crtc_state->stream) remove_stream(adev, acrtc, dm_old_crtc_state->stream); @@ -8619,6 +8733,11 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state) dm_enable_per_frame_crtc_master_sync(dc_state); mutex_lock(&dm->dc_lock); WARN_ON(!dc_commit_state(dm->dc, dc_state)); +#if defined(CONFIG_DRM_AMD_DC_DCN) + /* Allow idle optimization when vblank count is 0 for display off */ + if (dm->active_vblank_irq_count == 0) + dc_allow_idle_optimizations(dm->dc,true); +#endif mutex_unlock(&dm->dc_lock); } @@ -9207,7 +9326,7 @@ static int dm_update_crtc_state(struct amdgpu_display_manager *dm, if (!drm_atomic_crtc_needs_modeset(new_crtc_state)) goto skip_modeset; - DRM_DEBUG_DRIVER( + DRM_DEBUG_ATOMIC( "amdgpu_crtc id:%d crtc_state_flags: enable:%d, active:%d, " "planes_changed:%d, mode_changed:%d,active_changed:%d," "connectors_changed:%d\n", @@ -9291,8 +9410,8 @@ static int dm_update_crtc_state(struct amdgpu_display_manager *dm, dc_stream_retain(new_stream); - DRM_DEBUG_DRIVER("Enabling DRM crtc: %d\n", - crtc->base.id); + DRM_DEBUG_ATOMIC("Enabling DRM crtc: %d\n", + crtc->base.id); if (dc_add_stream_to_ctx( dm->dc, @@ -9637,8 +9756,8 @@ static int dm_update_plane_state(struct dc *dc, if (!dc_new_plane_state) return -ENOMEM; - DRM_DEBUG_DRIVER("Enabling DRM plane: %d on DRM crtc %d\n", - plane->base.id, new_plane_crtc->base.id); + DRM_DEBUG_ATOMIC("Enabling DRM plane: %d on DRM crtc %d\n", + plane->base.id, new_plane_crtc->base.id); ret = fill_dc_plane_attributes( drm_to_adev(new_plane_crtc->dev), @@ -9701,7 +9820,8 @@ static int dm_check_crtc_cursor(struct drm_atomic_state *state, new_cursor_state = drm_atomic_get_new_plane_state(state, crtc->cursor); new_primary_state = drm_atomic_get_new_plane_state(state, crtc->primary); - if (!new_cursor_state || !new_primary_state || !new_cursor_state->fb) { + if (!new_cursor_state || !new_primary_state || + !new_cursor_state->fb || !new_primary_state->fb) { return 0; } diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h index 8f98d44490aa..b2f2ccfc20bb 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h @@ -1,5 +1,5 @@ /* - * Copyright 2015 Advanced Micro Devices, Inc. + * Copyright (C) 2015-2020 Advanced Micro Devices, Inc. All rights reserved. * * Permission is hereby granted, free of charge, to any person obtaining a * copy of this software and associated documentation files (the "Software"), @@ -66,6 +66,7 @@ struct dc_plane_state; struct common_irq_params { struct amdgpu_device *adev; enum dc_irq_source irq_src; + atomic64_t previous_timestamp; }; /** @@ -339,6 +340,15 @@ struct amdgpu_display_manager { struct common_irq_params vupdate_params[DC_IRQ_SOURCE_VUPDATE6 - DC_IRQ_SOURCE_VUPDATE1 + 1]; + /** + * @dmub_trace_params: + * + * DMUB trace event IRQ parameters, passed to registered handlers when + * triggered. + */ + struct common_irq_params + dmub_trace_params[1]; + spinlock_t irq_handler_list_table_lock; struct backlight_device *backlight_dev; @@ -385,6 +395,11 @@ struct amdgpu_display_manager { #endif #if defined(CONFIG_DRM_AMD_SECURE_DISPLAY) + /** + * @crc_rd_wrk: + * + * Work to be executed in a separate thread to communicate with PSP. + */ struct crc_rd_work *crc_rd_wrk; #endif @@ -395,6 +410,7 @@ struct amdgpu_display_manager { */ struct amdgpu_encoder mst_encoders[AMDGPU_DM_MAX_CRTC]; bool force_timing_sync; + bool disable_hpd_irq; bool dmcub_trace_event_en; /** * @da_list: diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crc.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crc.c index c6d6baab106e..5cd788b20c21 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crc.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crc.c @@ -307,7 +307,7 @@ int amdgpu_dm_crtc_set_crc_source(struct drm_crtc *crtc, const char *src_name) goto cleanup; } - aux = &aconn->dm_dp_aux.aux; + aux = (aconn->port) ? &aconn->port->aux : &aconn->dm_dp_aux.aux; if (!aux) { DRM_DEBUG_DRIVER("No dp aux for amd connector\n"); diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c index 927de7678a4f..529545045a3e 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c @@ -34,6 +34,7 @@ #include "resource.h" #include "dsc.h" #include "dc_link_dp.h" +#include "link_hwss.h" #include "dc/dc_dmub_srv.h" struct dmub_debugfs_trace_header { @@ -149,7 +150,7 @@ static int parse_write_buffer_into_params(char *wr_buf, uint32_t wr_buf_size, * * --- to get dp configuration * - * cat link_settings + * cat /sys/kernel/debug/dri/0/DP-x/link_settings * * It will list current, verified, reported, preferred dp configuration. * current -- for current video mode @@ -162,7 +163,7 @@ static int parse_write_buffer_into_params(char *wr_buf, uint32_t wr_buf_size, * echo <lane_count> <link_rate> > link_settings * * for example, to force to 2 lane, 2.7GHz, - * echo 4 0xa > link_settings + * echo 4 0xa > /sys/kernel/debug/dri/0/DP-x/link_settings * * spread_spectrum could not be changed dynamically. * @@ -170,7 +171,7 @@ static int parse_write_buffer_into_params(char *wr_buf, uint32_t wr_buf_size, * done. please check link settings after force operation to see if HW get * programming. * - * cat link_settings + * cat /sys/kernel/debug/dri/0/DP-x/link_settings * * check current and preferred settings. * @@ -246,7 +247,6 @@ static ssize_t dp_link_settings_write(struct file *f, const char __user *buf, { struct amdgpu_dm_connector *connector = file_inode(f)->i_private; struct dc_link *link = connector->dc_link; - struct dc *dc = (struct dc *)link->dc; struct dc_link_settings prefer_link_settings; char *wr_buf = NULL; const uint32_t wr_buf_size = 40; @@ -254,7 +254,7 @@ static ssize_t dp_link_settings_write(struct file *f, const char __user *buf, int max_param_num = 2; uint8_t param_nums = 0; long param[2]; - bool valid_input = false; + bool valid_input = true; if (size == 0) return -EINVAL; @@ -281,9 +281,9 @@ static ssize_t dp_link_settings_write(struct file *f, const char __user *buf, case LANE_COUNT_ONE: case LANE_COUNT_TWO: case LANE_COUNT_FOUR: - valid_input = true; break; default: + valid_input = false; break; } @@ -293,9 +293,9 @@ static ssize_t dp_link_settings_write(struct file *f, const char __user *buf, case LINK_RATE_RBR2: case LINK_RATE_HIGH2: case LINK_RATE_HIGH3: - valid_input = true; break; default: + valid_input = false; break; } @@ -309,10 +309,11 @@ static ssize_t dp_link_settings_write(struct file *f, const char __user *buf, * spread spectrum will not be changed */ prefer_link_settings.link_spread = link->cur_link_settings.link_spread; + prefer_link_settings.use_link_rate_set = false; prefer_link_settings.lane_count = param[0]; prefer_link_settings.link_rate = param[1]; - dc_link_set_preferred_link_settings(dc, &prefer_link_settings, link); + dp_retrain_link_dp_test(link, &prefer_link_settings, false); kfree(wr_buf); return size; @@ -399,6 +400,70 @@ static ssize_t dp_phy_settings_read(struct file *f, char __user *buf, return result; } +static int dp_lttpr_status_show(struct seq_file *m, void *d) +{ + char *data; + struct amdgpu_dm_connector *connector = file_inode(m->file)->i_private; + struct dc_link *link = connector->dc_link; + uint32_t read_size = 1; + uint8_t repeater_count = 0; + + data = kzalloc(read_size, GFP_KERNEL); + if (!data) + return 0; + + dm_helpers_dp_read_dpcd(link->ctx, link, 0xF0002, data, read_size); + + switch ((uint8_t)*data) { + case 0x80: + repeater_count = 1; + break; + case 0x40: + repeater_count = 2; + break; + case 0x20: + repeater_count = 3; + break; + case 0x10: + repeater_count = 4; + break; + case 0x8: + repeater_count = 5; + break; + case 0x4: + repeater_count = 6; + break; + case 0x2: + repeater_count = 7; + break; + case 0x1: + repeater_count = 8; + break; + case 0x0: + repeater_count = 0; + break; + default: + repeater_count = (uint8_t)*data; + break; + } + + seq_printf(m, "phy repeater count: %d\n", repeater_count); + + dm_helpers_dp_read_dpcd(link->ctx, link, 0xF0003, data, read_size); + + if ((uint8_t)*data == 0x55) + seq_printf(m, "phy repeater mode: transparent\n"); + else if ((uint8_t)*data == 0xAA) + seq_printf(m, "phy repeater mode: non-transparent\n"); + else if ((uint8_t)*data == 0x00) + seq_printf(m, "phy repeater mode: non lttpr\n"); + else + seq_printf(m, "phy repeater mode: read error\n"); + + kfree(data); + return 0; +} + static ssize_t dp_phy_settings_write(struct file *f, const char __user *buf, size_t size, loff_t *pos) { @@ -2300,6 +2365,7 @@ DEFINE_SHOW_ATTRIBUTE(dp_dsc_fec_support); DEFINE_SHOW_ATTRIBUTE(dmub_fw_state); DEFINE_SHOW_ATTRIBUTE(dmub_tracebuffer); DEFINE_SHOW_ATTRIBUTE(output_bpc); +DEFINE_SHOW_ATTRIBUTE(dp_lttpr_status); #ifdef CONFIG_DRM_AMD_DC_HDCP DEFINE_SHOW_ATTRIBUTE(hdcp_sink_capability); #endif @@ -2420,6 +2486,7 @@ static const struct { } dp_debugfs_entries[] = { {"link_settings", &dp_link_settings_debugfs_fops}, {"phy_settings", &dp_phy_settings_debugfs_fop}, + {"lttpr_status", &dp_lttpr_status_fops}, {"test_pattern", &dp_phy_test_pattern_fops}, #ifdef CONFIG_DRM_AMD_DC_HDCP {"hdcp_sink_capability", &hdcp_sink_capability_fops}, @@ -2900,6 +2967,10 @@ static int mst_topo_show(struct seq_file *m, void *unused) aconnector = to_amdgpu_dm_connector(connector); + /* Ensure we're only dumping the topology of a root mst node */ + if (!aconnector->mst_mgr.mst_state) + continue; + seq_printf(m, "\nMST topology for connector %d\n", aconnector->connector_id); drm_dp_mst_dump_topology(m, &aconnector->mst_mgr); } @@ -2909,7 +2980,73 @@ static int mst_topo_show(struct seq_file *m, void *unused) } /* - * Sets the force_timing_sync debug optino from the given string. + * Sets trigger hpd for MST topologies. + * All connected connectors will be rediscovered and re started as needed if val of 1 is sent. + * All topologies will be disconnected if val of 0 is set . + * Usage to enable topologies: echo 1 > /sys/kernel/debug/dri/0/amdgpu_dm_trigger_hpd_mst + * Usage to disable topologies: echo 0 > /sys/kernel/debug/dri/0/amdgpu_dm_trigger_hpd_mst + */ +static int trigger_hpd_mst_set(void *data, u64 val) +{ + struct amdgpu_device *adev = data; + struct drm_device *dev = adev_to_drm(adev); + struct drm_connector_list_iter iter; + struct amdgpu_dm_connector *aconnector; + struct drm_connector *connector; + struct dc_link *link = NULL; + + if (val == 1) { + drm_connector_list_iter_begin(dev, &iter); + drm_for_each_connector_iter(connector, &iter) { + aconnector = to_amdgpu_dm_connector(connector); + if (aconnector->dc_link->type == dc_connection_mst_branch && + aconnector->mst_mgr.aux) { + dc_link_detect(aconnector->dc_link, DETECT_REASON_HPD); + drm_dp_mst_topology_mgr_set_mst(&aconnector->mst_mgr, true); + } + } + } else if (val == 0) { + drm_connector_list_iter_begin(dev, &iter); + drm_for_each_connector_iter(connector, &iter) { + aconnector = to_amdgpu_dm_connector(connector); + if (!aconnector->dc_link) + continue; + + if (!(aconnector->port && &aconnector->mst_port->mst_mgr)) + continue; + + link = aconnector->dc_link; + dp_receiver_power_ctrl(link, false); + drm_dp_mst_topology_mgr_set_mst(&aconnector->mst_port->mst_mgr, false); + link->mst_stream_alloc_table.stream_count = 0; + memset(link->mst_stream_alloc_table.stream_allocations, 0, + sizeof(link->mst_stream_alloc_table.stream_allocations)); + } + } else { + return 0; + } + drm_kms_helper_hotplug_event(dev); + + return 0; +} + +/* + * The interface doesn't need get function, so it will return the + * value of zero + * Usage: cat /sys/kernel/debug/dri/0/amdgpu_dm_trigger_hpd_mst + */ +static int trigger_hpd_mst_get(void *data, u64 *val) +{ + *val = 0; + return 0; +} + +DEFINE_DEBUGFS_ATTRIBUTE(trigger_hpd_mst_ops, trigger_hpd_mst_get, + trigger_hpd_mst_set, "%llu\n"); + + +/* + * Sets the force_timing_sync debug option from the given string. * All connected displays will be force synchronized immediately. * Usage: echo 1 > /sys/kernel/debug/dri/0/amdgpu_dm_force_timing_sync */ @@ -2940,6 +3077,37 @@ static int force_timing_sync_get(void *data, u64 *val) DEFINE_DEBUGFS_ATTRIBUTE(force_timing_sync_ops, force_timing_sync_get, force_timing_sync_set, "%llu\n"); + +/* + * Disables all HPD and HPD RX interrupt handling in the + * driver when set to 1. Default is 0. + */ +static int disable_hpd_set(void *data, u64 val) +{ + struct amdgpu_device *adev = data; + + adev->dm.disable_hpd_irq = (bool)val; + + return 0; +} + + +/* + * Returns 1 if HPD and HPRX interrupt handling is disabled, + * 0 otherwise. + */ +static int disable_hpd_get(void *data, u64 *val) +{ + struct amdgpu_device *adev = data; + + *val = adev->dm.disable_hpd_irq; + + return 0; +} + +DEFINE_DEBUGFS_ATTRIBUTE(disable_hpd_ops, disable_hpd_get, + disable_hpd_set, "%llu\n"); + /* * Sets the DC visual confirm debug option from the given string. * Example usage: echo 1 > /sys/kernel/debug/dri/0/amdgpu_visual_confirm @@ -2972,6 +3140,64 @@ DEFINE_SHOW_ATTRIBUTE(mst_topo); DEFINE_DEBUGFS_ATTRIBUTE(visual_confirm_fops, visual_confirm_get, visual_confirm_set, "%llu\n"); +/* + * Dumps the DCC_EN bit for each pipe. + * Example usage: cat /sys/kernel/debug/dri/0/amdgpu_dm_dcc_en + */ +static ssize_t dcc_en_bits_read( + struct file *f, + char __user *buf, + size_t size, + loff_t *pos) +{ + struct amdgpu_device *adev = file_inode(f)->i_private; + struct dc *dc = adev->dm.dc; + char *rd_buf = NULL; + const uint32_t rd_buf_size = 32; + uint32_t result = 0; + int offset = 0; + int num_pipes = dc->res_pool->pipe_count; + int *dcc_en_bits; + int i, r; + + dcc_en_bits = kcalloc(num_pipes, sizeof(int), GFP_KERNEL); + if (!dcc_en_bits) + return -ENOMEM; + + if (!dc->hwss.get_dcc_en_bits) { + kfree(dcc_en_bits); + return 0; + } + + dc->hwss.get_dcc_en_bits(dc, dcc_en_bits); + + rd_buf = kcalloc(rd_buf_size, sizeof(char), GFP_KERNEL); + if (!rd_buf) + return -ENOMEM; + + for (i = 0; i < num_pipes; i++) + offset += snprintf(rd_buf + offset, rd_buf_size - offset, + "%d ", dcc_en_bits[i]); + rd_buf[strlen(rd_buf)] = '\n'; + + kfree(dcc_en_bits); + + while (size) { + if (*pos >= rd_buf_size) + break; + r = put_user(*(rd_buf + result), buf); + if (r) + return r; /* r = -EFAULT */ + buf += 1; + size -= 1; + *pos += 1; + result += 1; + } + + kfree(rd_buf); + return result; +} + void dtn_debugfs_init(struct amdgpu_device *adev) { static const struct file_operations dtn_log_fops = { @@ -2980,6 +3206,11 @@ void dtn_debugfs_init(struct amdgpu_device *adev) .write = dtn_log_write, .llseek = default_llseek }; + static const struct file_operations dcc_en_bits_fops = { + .owner = THIS_MODULE, + .read = dcc_en_bits_read, + .llseek = default_llseek + }; struct drm_minor *minor = adev_to_drm(adev)->primary; struct dentry *root = minor->debugfs_root; @@ -3007,4 +3238,14 @@ void dtn_debugfs_init(struct amdgpu_device *adev) debugfs_create_file_unsafe("amdgpu_dm_dmcub_trace_event_en", 0644, root, adev, &dmcub_trace_event_state_fops); + + debugfs_create_file_unsafe("amdgpu_dm_trigger_hpd_mst", 0644, root, + adev, &trigger_hpd_mst_ops); + + debugfs_create_file_unsafe("amdgpu_dm_dcc_en", 0644, root, adev, + &dcc_en_bits_fops); + + debugfs_create_file_unsafe("amdgpu_dm_disable_hpd", 0644, root, adev, + &disable_hpd_ops); + } diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c index 0cdbfcd475ec..616f5b1ea3a8 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c @@ -191,7 +191,7 @@ void hdcp_update_display(struct hdcp_workqueue *hdcp_work, psp_set_srm(hdcp_work->hdcp.config.psp.handle, hdcp_work->srm, hdcp_work->srm_size, &hdcp_work->srm_version); - display->adjust.disable = 0; + display->adjust.disable = MOD_HDCP_DISPLAY_NOT_DISABLE; if (content_type == DRM_MODE_HDCP_CONTENT_TYPE0) { hdcp_w->link.adjust.hdcp1.disable = 0; hdcp_w->link.adjust.hdcp2.force_type = MOD_HDCP_FORCE_TYPE_0; @@ -203,7 +203,7 @@ void hdcp_update_display(struct hdcp_workqueue *hdcp_work, schedule_delayed_work(&hdcp_w->property_validate_dwork, msecs_to_jiffies(DRM_HDCP_CHECK_PERIOD_MS)); } else { - display->adjust.disable = 1; + display->adjust.disable = MOD_HDCP_DISPLAY_DISABLE_AUTHENTICATION; hdcp_w->encryption_status = MOD_HDCP_ENCRYPTION_STATUS_HDCP_OFF; cancel_delayed_work(&hdcp_w->property_validate_dwork); } @@ -434,6 +434,7 @@ static void update_config(void *handle, struct cp_psp_stream_config *config) int link_index = aconnector->dc_link->link_index; struct mod_hdcp_display *display = &hdcp_work[link_index].display; struct mod_hdcp_link *link = &hdcp_work[link_index].link; + struct drm_connector_state *conn_state; if (config->dpms_off) { hdcp_remove_display(hdcp_work, link_index, aconnector); @@ -456,11 +457,16 @@ static void update_config(void *handle, struct cp_psp_stream_config *config) link->dp.rev = aconnector->dc_link->dpcd_caps.dpcd_rev.raw; link->dp.assr_enabled = config->assr_enabled; link->dp.mst_enabled = config->mst_enabled; - display->adjust.disable = 1; + display->adjust.disable = MOD_HDCP_DISPLAY_DISABLE_AUTHENTICATION; link->adjust.auth_delay = 3; link->adjust.hdcp1.disable = 0; + conn_state = aconnector->base.state; - hdcp_update_display(hdcp_work, link_index, aconnector, DRM_MODE_HDCP_CONTENT_TYPE0, false); + pr_debug("[HDCP_DM] display %d, CP %d, type %d\n", aconnector->base.index, + (!!aconnector->base.state) ? aconnector->base.state->content_protection : -1, + (!!aconnector->base.state) ? aconnector->base.state->hdcp_content_type : -1); + + hdcp_update_display(hdcp_work, link_index, aconnector, conn_state->hdcp_content_type, false); } diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c index 09bdffb3a09e..e8b325a828c1 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c @@ -700,6 +700,39 @@ void dm_helpers_free_gpu_mem( bool dm_helpers_dmub_outbox0_interrupt_control(struct dc_context *ctx, bool enable) { - // TODO - return true; + enum dc_irq_source irq_source; + bool ret; + + irq_source = DC_IRQ_SOURCE_DMCUB_OUTBOX0; + + ret = dc_interrupt_set(ctx->dc, irq_source, enable); + + DRM_DEBUG_DRIVER("Dmub trace irq %sabling: r=%d\n", + enable ? "en" : "dis", ret); + return ret; +} + +void dm_helpers_mst_enable_stream_features(const struct dc_stream_state *stream) +{ + /* TODO: virtual DPCD */ + struct dc_link *link = stream->link; + union down_spread_ctrl old_downspread; + union down_spread_ctrl new_downspread; + + if (link->aux_access_disabled) + return; + + if (!dm_helpers_dp_read_dpcd(link->ctx, link, DP_DOWNSPREAD_CTRL, + &old_downspread.raw, + sizeof(old_downspread))) + return; + + new_downspread.raw = old_downspread.raw; + new_downspread.bits.IGNORE_MSA_TIMING_PARAM = + (stream->ignore_msa_timing_param) ? 1 : 0; + + if (new_downspread.raw != old_downspread.raw) + dm_helpers_dp_write_dpcd(link->ctx, link, DP_DOWNSPREAD_CTRL, + &new_downspread.raw, + sizeof(new_downspread)); } diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c index d3c687d07ee6..b3ed7e777720 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c @@ -73,6 +73,7 @@ * @handler_arg: Argument passed to the handler when triggered * @dm: DM which this handler belongs to * @irq_source: DC interrupt source that this handler is registered for + * @work: work struct */ struct amdgpu_dm_irq_handler_data { struct list_head list; @@ -184,6 +185,55 @@ static struct list_head *remove_irq_handler(struct amdgpu_device *adev, return hnd_list; } +/** + * unregister_all_irq_handlers() - Cleans up handlers from the DM IRQ table + * @adev: The base driver device containing the DM device + * + * Go through low and high context IRQ tables and deallocate handlers. + */ +static void unregister_all_irq_handlers(struct amdgpu_device *adev) +{ + struct list_head *hnd_list_low; + struct list_head *hnd_list_high; + struct list_head *entry, *tmp; + struct amdgpu_dm_irq_handler_data *handler; + unsigned long irq_table_flags; + int i; + + DM_IRQ_TABLE_LOCK(adev, irq_table_flags); + + for (i = 0; i < DAL_IRQ_SOURCES_NUMBER; i++) { + hnd_list_low = &adev->dm.irq_handler_list_low_tab[i]; + hnd_list_high = &adev->dm.irq_handler_list_high_tab[i]; + + list_for_each_safe(entry, tmp, hnd_list_low) { + + handler = list_entry(entry, struct amdgpu_dm_irq_handler_data, + list); + + if (handler == NULL || handler->handler == NULL) + continue; + + list_del(&handler->list); + kfree(handler); + } + + list_for_each_safe(entry, tmp, hnd_list_high) { + + handler = list_entry(entry, struct amdgpu_dm_irq_handler_data, + list); + + if (handler == NULL || handler->handler == NULL) + continue; + + list_del(&handler->list); + kfree(handler); + } + } + + DM_IRQ_TABLE_UNLOCK(adev, irq_table_flags); +} + static bool validate_irq_registration_params(struct dc_interrupt_params *int_params, void (*ih)(void *)) @@ -414,6 +464,8 @@ void amdgpu_dm_irq_fini(struct amdgpu_device *adev) } } } + /* Deallocate handlers from the table. */ + unregister_all_irq_handlers(adev); } int amdgpu_dm_irq_suspend(struct amdgpu_device *adev) @@ -731,6 +783,18 @@ static int amdgpu_dm_set_vupdate_irq_state(struct amdgpu_device *adev, __func__); } +static int amdgpu_dm_set_dmub_trace_irq_state(struct amdgpu_device *adev, + struct amdgpu_irq_src *source, + unsigned int type, + enum amdgpu_interrupt_state state) +{ + enum dc_irq_source irq_source = DC_IRQ_SOURCE_DMCUB_OUTBOX0; + bool st = (state == AMDGPU_IRQ_STATE_ENABLE); + + dc_interrupt_set(adev->dm.dc, irq_source, st); + return 0; +} + static const struct amdgpu_irq_src_funcs dm_crtc_irq_funcs = { .set = amdgpu_dm_set_crtc_irq_state, .process = amdgpu_dm_irq_handler, @@ -746,6 +810,11 @@ static const struct amdgpu_irq_src_funcs dm_vupdate_irq_funcs = { .process = amdgpu_dm_irq_handler, }; +static const struct amdgpu_irq_src_funcs dm_dmub_trace_irq_funcs = { + .set = amdgpu_dm_set_dmub_trace_irq_state, + .process = amdgpu_dm_irq_handler, +}; + static const struct amdgpu_irq_src_funcs dm_pageflip_irq_funcs = { .set = amdgpu_dm_set_pflip_irq_state, .process = amdgpu_dm_irq_handler, @@ -768,6 +837,9 @@ void amdgpu_dm_set_irq_funcs(struct amdgpu_device *adev) adev->vupdate_irq.num_types = adev->mode_info.num_crtc; adev->vupdate_irq.funcs = &dm_vupdate_irq_funcs; + adev->dmub_trace_irq.num_types = 1; + adev->dmub_trace_irq.funcs = &dm_dmub_trace_irq_funcs; + adev->pageflip_irq.num_types = adev->mode_info.num_crtc; adev->pageflip_irq.funcs = &dm_pageflip_irq_funcs; diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c index 73cdb9fe981a..9b221db526dc 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c @@ -229,6 +229,11 @@ static int dm_dp_mst_get_modes(struct drm_connector *connector) (aconnector->edid->extensions + 1) * EDID_LENGTH, &init_params); + if (!dc_sink) { + DRM_ERROR("Unable to add a remote sink\n"); + return 0; + } + dc_sink->priv = aconnector; /* dc_link_add_remote_sink returns a new reference */ aconnector->dc_sink = dc_sink; @@ -745,8 +750,8 @@ static bool compute_mst_dsc_configs_for_link(struct drm_atomic_state *state, if (!dc_dsc_compute_bandwidth_range( stream->sink->ctx->dc->res_pool->dscs[0], stream->sink->ctx->dc->debug.dsc_min_slice_height_override, - dsc_policy.min_target_bpp, - dsc_policy.max_target_bpp, + dsc_policy.min_target_bpp * 16, + dsc_policy.max_target_bpp * 16, &stream->sink->dsc_caps.dsc_dec_caps, &stream->timing, ¶ms[count].bw_range)) params[count].bw_range.stream_kbps = dc_bandwidth_in_kbps_from_timing(&stream->timing); diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c index 607ec0999445..eba270121698 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c @@ -32,15 +32,12 @@ #include "amdgpu_dm_irq.h" #include "amdgpu_pm.h" #include "dm_pp_smu.h" -#include "amdgpu_smu.h" - bool dm_pp_apply_display_requirements( const struct dc_context *ctx, const struct dm_pp_display_configuration *pp_display_cfg) { struct amdgpu_device *adev = ctx->driver_context; - struct smu_context *smu = &adev->smu; int i; if (adev->pm.dpm_enabled) { @@ -106,9 +103,6 @@ bool dm_pp_apply_display_requirements( adev->powerplay.pp_funcs->display_configuration_change( adev->powerplay.pp_handle, &adev->pm.pm_display_cfg); - else if (adev->smu.ppt_funcs) - smu_display_configuration_change(smu, - &adev->pm.pm_display_cfg); amdgpu_pm_compute_clocks(adev); } @@ -148,36 +142,6 @@ static void get_default_clock_levels( } } -static enum smu_clk_type dc_to_smu_clock_type( - enum dm_pp_clock_type dm_pp_clk_type) -{ - enum smu_clk_type smu_clk_type = SMU_CLK_COUNT; - - switch (dm_pp_clk_type) { - case DM_PP_CLOCK_TYPE_DISPLAY_CLK: - smu_clk_type = SMU_DISPCLK; - break; - case DM_PP_CLOCK_TYPE_ENGINE_CLK: - smu_clk_type = SMU_GFXCLK; - break; - case DM_PP_CLOCK_TYPE_MEMORY_CLK: - smu_clk_type = SMU_MCLK; - break; - case DM_PP_CLOCK_TYPE_DCEFCLK: - smu_clk_type = SMU_DCEFCLK; - break; - case DM_PP_CLOCK_TYPE_SOCCLK: - smu_clk_type = SMU_SOCCLK; - break; - default: - DRM_ERROR("DM_PPLIB: invalid clock type: %d!\n", - dm_pp_clk_type); - break; - } - - return smu_clk_type; -} - static enum amd_pp_clock_type dc_to_pp_clock_type( enum dm_pp_clock_type dm_pp_clk_type) { @@ -417,14 +381,8 @@ bool dm_pp_get_clock_levels_by_type_with_latency( &pp_clks); if (ret) return false; - } else if (adev->smu.ppt_funcs && adev->smu.ppt_funcs->get_clock_by_type_with_latency) { - if (smu_get_clock_by_type_with_latency(&adev->smu, - dc_to_smu_clock_type(clk_type), - &pp_clks)) - return false; } - pp_to_dc_clock_levels_with_latency(&pp_clks, clk_level_info, clk_type); return true; @@ -502,10 +460,6 @@ bool dm_pp_apply_clock_for_voltage_request( ret = adev->powerplay.pp_funcs->display_clock_voltage_request( adev->powerplay.pp_handle, &pp_clock_request); - else if (adev->smu.ppt_funcs && - adev->smu.ppt_funcs->display_clock_voltage_request) - ret = smu_display_clock_voltage_request(&adev->smu, - &pp_clock_request); if (ret) return false; return true; @@ -655,8 +609,11 @@ static enum pp_smu_status pp_nv_set_wm_ranges(struct pp_smu *pp, { const struct dc_context *ctx = pp->dm; struct amdgpu_device *adev = ctx->driver_context; + void *pp_handle = adev->powerplay.pp_handle; + const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs; - smu_set_watermarks_for_clock_ranges(&adev->smu, ranges); + if (pp_funcs && pp_funcs->set_watermarks_for_clocks_ranges) + pp_funcs->set_watermarks_for_clocks_ranges(pp_handle, ranges); return PP_SMU_RESULT_OK; } @@ -665,13 +622,14 @@ static enum pp_smu_status pp_nv_set_display_count(struct pp_smu *pp, int count) { const struct dc_context *ctx = pp->dm; struct amdgpu_device *adev = ctx->driver_context; - struct smu_context *smu = &adev->smu; + void *pp_handle = adev->powerplay.pp_handle; + const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs; - if (!smu->ppt_funcs) + if (!pp_funcs || !pp_funcs->set_active_display_count) return PP_SMU_RESULT_UNSUPPORTED; /* 0: successful or smu.ppt_funcs->set_display_count = NULL; 1: fail */ - if (smu_set_display_count(smu, count)) + if (pp_funcs->set_active_display_count(pp_handle, count)) return PP_SMU_RESULT_FAIL; return PP_SMU_RESULT_OK; @@ -682,13 +640,14 @@ pp_nv_set_min_deep_sleep_dcfclk(struct pp_smu *pp, int mhz) { const struct dc_context *ctx = pp->dm; struct amdgpu_device *adev = ctx->driver_context; - struct smu_context *smu = &adev->smu; + void *pp_handle = adev->powerplay.pp_handle; + const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs; - if (!smu->ppt_funcs) + if (!pp_funcs || !pp_funcs->set_min_deep_sleep_dcefclk) return PP_SMU_RESULT_UNSUPPORTED; /* 0: successful or smu.ppt_funcs->set_deep_sleep_dcefclk = NULL;1: fail */ - if (smu_set_deep_sleep_dcefclk(smu, mhz)) + if (pp_funcs->set_min_deep_sleep_dcefclk(pp_handle, mhz)) return PP_SMU_RESULT_FAIL; return PP_SMU_RESULT_OK; @@ -699,10 +658,11 @@ static enum pp_smu_status pp_nv_set_hard_min_dcefclk_by_freq( { const struct dc_context *ctx = pp->dm; struct amdgpu_device *adev = ctx->driver_context; - struct smu_context *smu = &adev->smu; + void *pp_handle = adev->powerplay.pp_handle; + const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs; struct pp_display_clock_request clock_req; - if (!smu->ppt_funcs) + if (!pp_funcs || !pp_funcs->display_clock_voltage_request) return PP_SMU_RESULT_UNSUPPORTED; clock_req.clock_type = amd_pp_dcef_clock; @@ -711,7 +671,7 @@ static enum pp_smu_status pp_nv_set_hard_min_dcefclk_by_freq( /* 0: successful or smu.ppt_funcs->display_clock_voltage_request = NULL * 1: fail */ - if (smu_display_clock_voltage_request(smu, &clock_req)) + if (pp_funcs->display_clock_voltage_request(pp_handle, &clock_req)) return PP_SMU_RESULT_FAIL; return PP_SMU_RESULT_OK; @@ -722,10 +682,11 @@ pp_nv_set_hard_min_uclk_by_freq(struct pp_smu *pp, int mhz) { const struct dc_context *ctx = pp->dm; struct amdgpu_device *adev = ctx->driver_context; - struct smu_context *smu = &adev->smu; + void *pp_handle = adev->powerplay.pp_handle; + const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs; struct pp_display_clock_request clock_req; - if (!smu->ppt_funcs) + if (!pp_funcs || !pp_funcs->display_clock_voltage_request) return PP_SMU_RESULT_UNSUPPORTED; clock_req.clock_type = amd_pp_mem_clock; @@ -734,7 +695,7 @@ pp_nv_set_hard_min_uclk_by_freq(struct pp_smu *pp, int mhz) /* 0: successful or smu.ppt_funcs->display_clock_voltage_request = NULL * 1: fail */ - if (smu_display_clock_voltage_request(smu, &clock_req)) + if (pp_funcs->display_clock_voltage_request(pp_handle, &clock_req)) return PP_SMU_RESULT_FAIL; return PP_SMU_RESULT_OK; @@ -745,10 +706,14 @@ static enum pp_smu_status pp_nv_set_pstate_handshake_support( { const struct dc_context *ctx = pp->dm; struct amdgpu_device *adev = ctx->driver_context; - struct smu_context *smu = &adev->smu; + void *pp_handle = adev->powerplay.pp_handle; + const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs; - if (smu_display_disable_memory_clock_switch(smu, !pstate_handshake_supported)) - return PP_SMU_RESULT_FAIL; + if (pp_funcs && pp_funcs->display_disable_memory_clock_switch) { + if (pp_funcs->display_disable_memory_clock_switch(pp_handle, + !pstate_handshake_supported)) + return PP_SMU_RESULT_FAIL; + } return PP_SMU_RESULT_OK; } @@ -758,10 +723,11 @@ static enum pp_smu_status pp_nv_set_voltage_by_freq(struct pp_smu *pp, { const struct dc_context *ctx = pp->dm; struct amdgpu_device *adev = ctx->driver_context; - struct smu_context *smu = &adev->smu; + void *pp_handle = adev->powerplay.pp_handle; + const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs; struct pp_display_clock_request clock_req; - if (!smu->ppt_funcs) + if (!pp_funcs || !pp_funcs->display_clock_voltage_request) return PP_SMU_RESULT_UNSUPPORTED; switch (clock_id) { @@ -782,7 +748,7 @@ static enum pp_smu_status pp_nv_set_voltage_by_freq(struct pp_smu *pp, /* 0: successful or smu.ppt_funcs->display_clock_voltage_request = NULL * 1: fail */ - if (smu_display_clock_voltage_request(smu, &clock_req)) + if (pp_funcs->display_clock_voltage_request(pp_handle, &clock_req)) return PP_SMU_RESULT_FAIL; return PP_SMU_RESULT_OK; @@ -793,15 +759,13 @@ static enum pp_smu_status pp_nv_get_maximum_sustainable_clocks( { const struct dc_context *ctx = pp->dm; struct amdgpu_device *adev = ctx->driver_context; - struct smu_context *smu = &adev->smu; - - if (!smu->ppt_funcs) - return PP_SMU_RESULT_UNSUPPORTED; + void *pp_handle = adev->powerplay.pp_handle; + const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs; - if (!smu->ppt_funcs->get_max_sustainable_clocks_by_dc) + if (!pp_funcs || !pp_funcs->get_max_sustainable_clocks_by_dc) return PP_SMU_RESULT_UNSUPPORTED; - if (!smu_get_max_sustainable_clocks_by_dc(smu, max_clocks)) + if (!pp_funcs->get_max_sustainable_clocks_by_dc(pp_handle, max_clocks)) return PP_SMU_RESULT_OK; return PP_SMU_RESULT_FAIL; @@ -812,16 +776,15 @@ static enum pp_smu_status pp_nv_get_uclk_dpm_states(struct pp_smu *pp, { const struct dc_context *ctx = pp->dm; struct amdgpu_device *adev = ctx->driver_context; - struct smu_context *smu = &adev->smu; - - if (!smu->ppt_funcs) - return PP_SMU_RESULT_UNSUPPORTED; + void *pp_handle = adev->powerplay.pp_handle; + const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs; - if (!smu->ppt_funcs->get_uclk_dpm_states) + if (!pp_funcs || !pp_funcs->get_uclk_dpm_states) return PP_SMU_RESULT_UNSUPPORTED; - if (!smu_get_uclk_dpm_states(smu, - clock_values_in_khz, num_states)) + if (!pp_funcs->get_uclk_dpm_states(pp_handle, + clock_values_in_khz, + num_states)) return PP_SMU_RESULT_OK; return PP_SMU_RESULT_FAIL; @@ -832,15 +795,13 @@ static enum pp_smu_status pp_rn_get_dpm_clock_table( { const struct dc_context *ctx = pp->dm; struct amdgpu_device *adev = ctx->driver_context; - struct smu_context *smu = &adev->smu; - - if (!smu->ppt_funcs) - return PP_SMU_RESULT_UNSUPPORTED; + void *pp_handle = adev->powerplay.pp_handle; + const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs; - if (!smu->ppt_funcs->get_dpm_clock_table) + if (!pp_funcs || !pp_funcs->get_dpm_clock_table) return PP_SMU_RESULT_UNSUPPORTED; - if (!smu_get_dpm_clock_table(smu, clock_table)) + if (!pp_funcs->get_dpm_clock_table(pp_handle, clock_table)) return PP_SMU_RESULT_OK; return PP_SMU_RESULT_FAIL; @@ -851,8 +812,11 @@ static enum pp_smu_status pp_rn_set_wm_ranges(struct pp_smu *pp, { const struct dc_context *ctx = pp->dm; struct amdgpu_device *adev = ctx->driver_context; + void *pp_handle = adev->powerplay.pp_handle; + const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs; - smu_set_watermarks_for_clock_ranges(&adev->smu, ranges); + if (pp_funcs && pp_funcs->set_watermarks_for_clocks_ranges) + pp_funcs->set_watermarks_for_clocks_ranges(pp_handle, ranges); return PP_SMU_RESULT_OK; } diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_trace.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_trace.h index 86960476823c..46a33f64cf8e 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_trace.h +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_trace.h @@ -597,6 +597,46 @@ TRACE_EVENT(amdgpu_dm_dce_clocks_state, ) ); +TRACE_EVENT(amdgpu_dmub_trace_high_irq, + TP_PROTO(uint32_t trace_code, uint32_t tick_count, uint32_t param0, + uint32_t param1), + TP_ARGS(trace_code, tick_count, param0, param1), + TP_STRUCT__entry( + __field(uint32_t, trace_code) + __field(uint32_t, tick_count) + __field(uint32_t, param0) + __field(uint32_t, param1) + ), + TP_fast_assign( + __entry->trace_code = trace_code; + __entry->tick_count = tick_count; + __entry->param0 = param0; + __entry->param1 = param1; + ), + TP_printk("trace_code=%u tick_count=%u param0=%u param1=%u", + __entry->trace_code, __entry->tick_count, + __entry->param0, __entry->param1) +); + +TRACE_EVENT(amdgpu_refresh_rate_track, + TP_PROTO(int crtc_index, ktime_t refresh_rate_ns, uint32_t refresh_rate_hz), + TP_ARGS(crtc_index, refresh_rate_ns, refresh_rate_hz), + TP_STRUCT__entry( + __field(int, crtc_index) + __field(ktime_t, refresh_rate_ns) + __field(uint32_t, refresh_rate_hz) + ), + TP_fast_assign( + __entry->crtc_index = crtc_index; + __entry->refresh_rate_ns = refresh_rate_ns; + __entry->refresh_rate_hz = refresh_rate_hz; + ), + TP_printk("crtc_index=%d refresh_rate=%dHz (%lld)", + __entry->crtc_index, + __entry->refresh_rate_hz, + __entry->refresh_rate_ns) +); + #endif /* _AMDGPU_DM_TRACE_H_ */ #undef TRACE_INCLUDE_PATH diff --git a/drivers/gpu/drm/amd/display/dc/Makefile b/drivers/gpu/drm/amd/display/dc/Makefile index bbde6e6a4e43..f33847299bca 100644 --- a/drivers/gpu/drm/amd/display/dc/Makefile +++ b/drivers/gpu/drm/amd/display/dc/Makefile @@ -54,8 +54,9 @@ AMD_DC = $(addsuffix /Makefile, $(addprefix $(FULL_AMD_DISPLAY_PATH)/dc/,$(DC_LI include $(AMD_DC) -DISPLAY_CORE = dc.o dc_stat.o dc_link.o dc_resource.o dc_hw_sequencer.o dc_sink.o \ -dc_surface.o dc_link_hwss.o dc_link_dp.o dc_link_ddc.o dc_debug.o dc_stream.o +DISPLAY_CORE = dc.o dc_link.o dc_resource.o dc_hw_sequencer.o dc_sink.o \ +dc_surface.o dc_link_hwss.o dc_link_dp.o dc_link_ddc.o dc_debug.o dc_stream.o \ +dc_link_enc_cfg.o ifdef CONFIG_DRM_AMD_DC_DCN DISPLAY_CORE += dc_vm_helper.o diff --git a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c index b208f06ed514..d79f4fe06c47 100644 --- a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c +++ b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c @@ -916,6 +916,192 @@ static enum bp_result bios_parser_get_soc_bb_info( return result; } +static enum bp_result get_disp_caps_v4_1( + struct bios_parser *bp, + uint8_t *dce_caps) +{ + enum bp_result result = BP_RESULT_OK; + struct atom_display_controller_info_v4_1 *disp_cntl_tbl = NULL; + + if (!dce_caps) + return BP_RESULT_BADINPUT; + + if (!DATA_TABLES(dce_info)) + return BP_RESULT_BADBIOSTABLE; + + disp_cntl_tbl = GET_IMAGE(struct atom_display_controller_info_v4_1, + DATA_TABLES(dce_info)); + + if (!disp_cntl_tbl) + return BP_RESULT_BADBIOSTABLE; + + *dce_caps = disp_cntl_tbl->display_caps; + + return result; +} + +static enum bp_result get_disp_caps_v4_2( + struct bios_parser *bp, + uint8_t *dce_caps) +{ + enum bp_result result = BP_RESULT_OK; + struct atom_display_controller_info_v4_2 *disp_cntl_tbl = NULL; + + if (!dce_caps) + return BP_RESULT_BADINPUT; + + if (!DATA_TABLES(dce_info)) + return BP_RESULT_BADBIOSTABLE; + + disp_cntl_tbl = GET_IMAGE(struct atom_display_controller_info_v4_2, + DATA_TABLES(dce_info)); + + if (!disp_cntl_tbl) + return BP_RESULT_BADBIOSTABLE; + + *dce_caps = disp_cntl_tbl->display_caps; + + return result; +} + +static enum bp_result get_disp_caps_v4_3( + struct bios_parser *bp, + uint8_t *dce_caps) +{ + enum bp_result result = BP_RESULT_OK; + struct atom_display_controller_info_v4_3 *disp_cntl_tbl = NULL; + + if (!dce_caps) + return BP_RESULT_BADINPUT; + + if (!DATA_TABLES(dce_info)) + return BP_RESULT_BADBIOSTABLE; + + disp_cntl_tbl = GET_IMAGE(struct atom_display_controller_info_v4_3, + DATA_TABLES(dce_info)); + + if (!disp_cntl_tbl) + return BP_RESULT_BADBIOSTABLE; + + *dce_caps = disp_cntl_tbl->display_caps; + + return result; +} + +static enum bp_result get_disp_caps_v4_4( + struct bios_parser *bp, + uint8_t *dce_caps) +{ + enum bp_result result = BP_RESULT_OK; + struct atom_display_controller_info_v4_4 *disp_cntl_tbl = NULL; + + if (!dce_caps) + return BP_RESULT_BADINPUT; + + if (!DATA_TABLES(dce_info)) + return BP_RESULT_BADBIOSTABLE; + + disp_cntl_tbl = GET_IMAGE(struct atom_display_controller_info_v4_4, + DATA_TABLES(dce_info)); + + if (!disp_cntl_tbl) + return BP_RESULT_BADBIOSTABLE; + + *dce_caps = disp_cntl_tbl->display_caps; + + return result; +} + +static enum bp_result bios_parser_get_lttpr_interop( + struct dc_bios *dcb, + uint8_t *dce_caps) +{ + struct bios_parser *bp = BP_FROM_DCB(dcb); + enum bp_result result = BP_RESULT_UNSUPPORTED; + struct atom_common_table_header *header; + struct atom_data_revision tbl_revision; + + if (!DATA_TABLES(dce_info)) + return BP_RESULT_UNSUPPORTED; + + header = GET_IMAGE(struct atom_common_table_header, + DATA_TABLES(dce_info)); + get_atom_data_table_revision(header, &tbl_revision); + switch (tbl_revision.major) { + case 4: + switch (tbl_revision.minor) { + case 1: + result = get_disp_caps_v4_1(bp, dce_caps); + *dce_caps = !!(*dce_caps & DCE_INFO_CAPS_VBIOS_LTTPR_TRANSPARENT_ENABLE); + break; + case 2: + result = get_disp_caps_v4_2(bp, dce_caps); + *dce_caps = !!(*dce_caps & DCE_INFO_CAPS_VBIOS_LTTPR_TRANSPARENT_ENABLE); + break; + case 3: + result = get_disp_caps_v4_3(bp, dce_caps); + *dce_caps = !!(*dce_caps & DCE_INFO_CAPS_VBIOS_LTTPR_TRANSPARENT_ENABLE); + break; + case 4: + result = get_disp_caps_v4_4(bp, dce_caps); + *dce_caps = !!(*dce_caps & DCE_INFO_CAPS_VBIOS_LTTPR_TRANSPARENT_ENABLE); + break; + default: + break; + } + break; + default: + break; + } + + return result; +} + +static enum bp_result bios_parser_get_lttpr_caps( + struct dc_bios *dcb, + uint8_t *dce_caps) +{ + struct bios_parser *bp = BP_FROM_DCB(dcb); + enum bp_result result = BP_RESULT_UNSUPPORTED; + struct atom_common_table_header *header; + struct atom_data_revision tbl_revision; + + if (!DATA_TABLES(dce_info)) + return BP_RESULT_UNSUPPORTED; + + header = GET_IMAGE(struct atom_common_table_header, + DATA_TABLES(dce_info)); + get_atom_data_table_revision(header, &tbl_revision); + switch (tbl_revision.major) { + case 4: + switch (tbl_revision.minor) { + case 1: + result = get_disp_caps_v4_1(bp, dce_caps); + *dce_caps = !!(*dce_caps & DCE_INFO_CAPS_LTTPR_SUPPORT_ENABLE); + break; + case 2: + result = get_disp_caps_v4_2(bp, dce_caps); + *dce_caps = !!(*dce_caps & DCE_INFO_CAPS_LTTPR_SUPPORT_ENABLE); + break; + case 3: + result = get_disp_caps_v4_3(bp, dce_caps); + *dce_caps = !!(*dce_caps & DCE_INFO_CAPS_LTTPR_SUPPORT_ENABLE); + break; + case 4: + result = get_disp_caps_v4_4(bp, dce_caps); + *dce_caps = !!(*dce_caps & DCE_INFO_CAPS_LTTPR_SUPPORT_ENABLE); + break; + default: + break; + } + break; + default: + break; + } + + return result; +} + static enum bp_result get_embedded_panel_info_v2_1( struct bios_parser *bp, struct embedded_panel_info *info) @@ -2531,6 +2717,10 @@ static const struct dc_vbios_funcs vbios_funcs = { .get_soc_bb_info = bios_parser_get_soc_bb_info, .get_disp_connector_caps_info = bios_parser_get_disp_connector_caps_info, + + .get_lttpr_caps = bios_parser_get_lttpr_caps, + + .get_lttpr_interop = bios_parser_get_lttpr_interop, }; static bool bios_parser2_construct( diff --git a/drivers/gpu/drm/amd/display/dc/calcs/dce_calcs.c b/drivers/gpu/drm/amd/display/dc/calcs/dce_calcs.c index e633f8a51edb..1244fcb0f446 100644 --- a/drivers/gpu/drm/amd/display/dc/calcs/dce_calcs.c +++ b/drivers/gpu/drm/amd/display/dc/calcs/dce_calcs.c @@ -98,16 +98,16 @@ static void calculate_bandwidth( int32_t num_cursor_lines; int32_t i, j, k; - struct bw_fixed yclk[3]; - struct bw_fixed sclk[8]; + struct bw_fixed *yclk; + struct bw_fixed *sclk; bool d0_underlay_enable; bool d1_underlay_enable; bool fbc_enabled; bool lpt_enabled; enum bw_defines sclk_message; enum bw_defines yclk_message; - enum bw_defines tiling_mode[maximum_number_of_surfaces]; - enum bw_defines surface_type[maximum_number_of_surfaces]; + enum bw_defines *tiling_mode; + enum bw_defines *surface_type; enum bw_defines voltage; enum bw_defines pipe_check; enum bw_defines hsr_check; @@ -122,6 +122,22 @@ static void calculate_bandwidth( int32_t number_of_displays_enabled_with_margin = 0; int32_t number_of_aligned_displays_with_no_margin = 0; + yclk = kcalloc(3, sizeof(*yclk), GFP_KERNEL); + if (!yclk) + return; + + sclk = kcalloc(8, sizeof(*sclk), GFP_KERNEL); + if (!sclk) + goto free_yclk; + + tiling_mode = kcalloc(maximum_number_of_surfaces, sizeof(*tiling_mode), GFP_KERNEL); + if (!tiling_mode) + goto free_sclk; + + surface_type = kcalloc(maximum_number_of_surfaces, sizeof(*surface_type), GFP_KERNEL); + if (!surface_type) + goto free_tiling_mode; + yclk[low] = vbios->low_yclk; yclk[mid] = vbios->mid_yclk; yclk[high] = vbios->high_yclk; @@ -2013,6 +2029,14 @@ static void calculate_bandwidth( } } } + + kfree(surface_type); +free_tiling_mode: + kfree(tiling_mode); +free_yclk: + kfree(yclk); +free_sclk: + kfree(sclk); } /******************************************************************************* @@ -2022,707 +2046,719 @@ void bw_calcs_init(struct bw_calcs_dceip *bw_dceip, struct bw_calcs_vbios *bw_vbios, struct hw_asic_id asic_id) { - struct bw_calcs_dceip dceip = { 0 }; - struct bw_calcs_vbios vbios = { 0 }; + struct bw_calcs_dceip *dceip; + struct bw_calcs_vbios *vbios; enum bw_calcs_version version = bw_calcs_version_from_asic_id(asic_id); - dceip.version = version; + dceip = kzalloc(sizeof(*dceip), GFP_KERNEL); + if (!dceip) + return; + + vbios = kzalloc(sizeof(*vbios), GFP_KERNEL); + if (!vbios) { + kfree(dceip); + return; + } + + dceip->version = version; switch (version) { case BW_CALCS_VERSION_CARRIZO: - vbios.memory_type = bw_def_gddr5; - vbios.dram_channel_width_in_bits = 64; - vbios.number_of_dram_channels = asic_id.vram_width / vbios.dram_channel_width_in_bits; - vbios.number_of_dram_banks = 8; - vbios.high_yclk = bw_int_to_fixed(1600); - vbios.mid_yclk = bw_int_to_fixed(1600); - vbios.low_yclk = bw_frc_to_fixed(66666, 100); - vbios.low_sclk = bw_int_to_fixed(200); - vbios.mid1_sclk = bw_int_to_fixed(300); - vbios.mid2_sclk = bw_int_to_fixed(300); - vbios.mid3_sclk = bw_int_to_fixed(300); - vbios.mid4_sclk = bw_int_to_fixed(300); - vbios.mid5_sclk = bw_int_to_fixed(300); - vbios.mid6_sclk = bw_int_to_fixed(300); - vbios.high_sclk = bw_frc_to_fixed(62609, 100); - vbios.low_voltage_max_dispclk = bw_int_to_fixed(352); - vbios.mid_voltage_max_dispclk = bw_int_to_fixed(467); - vbios.high_voltage_max_dispclk = bw_int_to_fixed(643); - vbios.low_voltage_max_phyclk = bw_int_to_fixed(540); - vbios.mid_voltage_max_phyclk = bw_int_to_fixed(810); - vbios.high_voltage_max_phyclk = bw_int_to_fixed(810); - vbios.data_return_bus_width = bw_int_to_fixed(32); - vbios.trc = bw_int_to_fixed(50); - vbios.dmifmc_urgent_latency = bw_int_to_fixed(4); - vbios.stutter_self_refresh_exit_latency = bw_frc_to_fixed(153, 10); - vbios.stutter_self_refresh_entry_latency = bw_int_to_fixed(0); - vbios.nbp_state_change_latency = bw_frc_to_fixed(19649, 1000); - vbios.mcifwrmc_urgent_latency = bw_int_to_fixed(10); - vbios.scatter_gather_enable = true; - vbios.down_spread_percentage = bw_frc_to_fixed(5, 10); - vbios.cursor_width = 32; - vbios.average_compression_rate = 4; - vbios.number_of_request_slots_gmc_reserves_for_dmif_per_channel = 256; - vbios.blackout_duration = bw_int_to_fixed(0); /* us */ - vbios.maximum_blackout_recovery_time = bw_int_to_fixed(0); - - dceip.max_average_percent_of_ideal_port_bw_display_can_use_in_normal_system_operation = 100; - dceip.max_average_percent_of_ideal_drambw_display_can_use_in_normal_system_operation = 100; - dceip.percent_of_ideal_port_bw_received_after_urgent_latency = 100; - dceip.large_cursor = false; - dceip.dmif_request_buffer_size = bw_int_to_fixed(768); - dceip.dmif_pipe_en_fbc_chunk_tracker = false; - dceip.cursor_max_outstanding_group_num = 1; - dceip.lines_interleaved_into_lb = 2; - dceip.chunk_width = 256; - dceip.number_of_graphics_pipes = 3; - dceip.number_of_underlay_pipes = 1; - dceip.low_power_tiling_mode = 0; - dceip.display_write_back_supported = false; - dceip.argb_compression_support = false; - dceip.underlay_vscaler_efficiency6_bit_per_component = + vbios->memory_type = bw_def_gddr5; + vbios->dram_channel_width_in_bits = 64; + vbios->number_of_dram_channels = asic_id.vram_width / vbios->dram_channel_width_in_bits; + vbios->number_of_dram_banks = 8; + vbios->high_yclk = bw_int_to_fixed(1600); + vbios->mid_yclk = bw_int_to_fixed(1600); + vbios->low_yclk = bw_frc_to_fixed(66666, 100); + vbios->low_sclk = bw_int_to_fixed(200); + vbios->mid1_sclk = bw_int_to_fixed(300); + vbios->mid2_sclk = bw_int_to_fixed(300); + vbios->mid3_sclk = bw_int_to_fixed(300); + vbios->mid4_sclk = bw_int_to_fixed(300); + vbios->mid5_sclk = bw_int_to_fixed(300); + vbios->mid6_sclk = bw_int_to_fixed(300); + vbios->high_sclk = bw_frc_to_fixed(62609, 100); + vbios->low_voltage_max_dispclk = bw_int_to_fixed(352); + vbios->mid_voltage_max_dispclk = bw_int_to_fixed(467); + vbios->high_voltage_max_dispclk = bw_int_to_fixed(643); + vbios->low_voltage_max_phyclk = bw_int_to_fixed(540); + vbios->mid_voltage_max_phyclk = bw_int_to_fixed(810); + vbios->high_voltage_max_phyclk = bw_int_to_fixed(810); + vbios->data_return_bus_width = bw_int_to_fixed(32); + vbios->trc = bw_int_to_fixed(50); + vbios->dmifmc_urgent_latency = bw_int_to_fixed(4); + vbios->stutter_self_refresh_exit_latency = bw_frc_to_fixed(153, 10); + vbios->stutter_self_refresh_entry_latency = bw_int_to_fixed(0); + vbios->nbp_state_change_latency = bw_frc_to_fixed(19649, 1000); + vbios->mcifwrmc_urgent_latency = bw_int_to_fixed(10); + vbios->scatter_gather_enable = true; + vbios->down_spread_percentage = bw_frc_to_fixed(5, 10); + vbios->cursor_width = 32; + vbios->average_compression_rate = 4; + vbios->number_of_request_slots_gmc_reserves_for_dmif_per_channel = 256; + vbios->blackout_duration = bw_int_to_fixed(0); /* us */ + vbios->maximum_blackout_recovery_time = bw_int_to_fixed(0); + + dceip->max_average_percent_of_ideal_port_bw_display_can_use_in_normal_system_operation = 100; + dceip->max_average_percent_of_ideal_drambw_display_can_use_in_normal_system_operation = 100; + dceip->percent_of_ideal_port_bw_received_after_urgent_latency = 100; + dceip->large_cursor = false; + dceip->dmif_request_buffer_size = bw_int_to_fixed(768); + dceip->dmif_pipe_en_fbc_chunk_tracker = false; + dceip->cursor_max_outstanding_group_num = 1; + dceip->lines_interleaved_into_lb = 2; + dceip->chunk_width = 256; + dceip->number_of_graphics_pipes = 3; + dceip->number_of_underlay_pipes = 1; + dceip->low_power_tiling_mode = 0; + dceip->display_write_back_supported = false; + dceip->argb_compression_support = false; + dceip->underlay_vscaler_efficiency6_bit_per_component = bw_frc_to_fixed(35556, 10000); - dceip.underlay_vscaler_efficiency8_bit_per_component = + dceip->underlay_vscaler_efficiency8_bit_per_component = bw_frc_to_fixed(34286, 10000); - dceip.underlay_vscaler_efficiency10_bit_per_component = + dceip->underlay_vscaler_efficiency10_bit_per_component = bw_frc_to_fixed(32, 10); - dceip.underlay_vscaler_efficiency12_bit_per_component = + dceip->underlay_vscaler_efficiency12_bit_per_component = bw_int_to_fixed(3); - dceip.graphics_vscaler_efficiency6_bit_per_component = + dceip->graphics_vscaler_efficiency6_bit_per_component = bw_frc_to_fixed(35, 10); - dceip.graphics_vscaler_efficiency8_bit_per_component = + dceip->graphics_vscaler_efficiency8_bit_per_component = bw_frc_to_fixed(34286, 10000); - dceip.graphics_vscaler_efficiency10_bit_per_component = + dceip->graphics_vscaler_efficiency10_bit_per_component = bw_frc_to_fixed(32, 10); - dceip.graphics_vscaler_efficiency12_bit_per_component = + dceip->graphics_vscaler_efficiency12_bit_per_component = bw_int_to_fixed(3); - dceip.alpha_vscaler_efficiency = bw_int_to_fixed(3); - dceip.max_dmif_buffer_allocated = 2; - dceip.graphics_dmif_size = 12288; - dceip.underlay_luma_dmif_size = 19456; - dceip.underlay_chroma_dmif_size = 23552; - dceip.pre_downscaler_enabled = true; - dceip.underlay_downscale_prefetch_enabled = true; - dceip.lb_write_pixels_per_dispclk = bw_int_to_fixed(1); - dceip.lb_size_per_component444 = bw_int_to_fixed(82176); - dceip.graphics_lb_nodownscaling_multi_line_prefetching = false; - dceip.stutter_and_dram_clock_state_change_gated_before_cursor = + dceip->alpha_vscaler_efficiency = bw_int_to_fixed(3); + dceip->max_dmif_buffer_allocated = 2; + dceip->graphics_dmif_size = 12288; + dceip->underlay_luma_dmif_size = 19456; + dceip->underlay_chroma_dmif_size = 23552; + dceip->pre_downscaler_enabled = true; + dceip->underlay_downscale_prefetch_enabled = true; + dceip->lb_write_pixels_per_dispclk = bw_int_to_fixed(1); + dceip->lb_size_per_component444 = bw_int_to_fixed(82176); + dceip->graphics_lb_nodownscaling_multi_line_prefetching = false; + dceip->stutter_and_dram_clock_state_change_gated_before_cursor = bw_int_to_fixed(0); - dceip.underlay420_luma_lb_size_per_component = bw_int_to_fixed( + dceip->underlay420_luma_lb_size_per_component = bw_int_to_fixed( 82176); - dceip.underlay420_chroma_lb_size_per_component = + dceip->underlay420_chroma_lb_size_per_component = bw_int_to_fixed(164352); - dceip.underlay422_lb_size_per_component = bw_int_to_fixed( + dceip->underlay422_lb_size_per_component = bw_int_to_fixed( 82176); - dceip.cursor_chunk_width = bw_int_to_fixed(64); - dceip.cursor_dcp_buffer_lines = bw_int_to_fixed(4); - dceip.underlay_maximum_width_efficient_for_tiling = + dceip->cursor_chunk_width = bw_int_to_fixed(64); + dceip->cursor_dcp_buffer_lines = bw_int_to_fixed(4); + dceip->underlay_maximum_width_efficient_for_tiling = bw_int_to_fixed(1920); - dceip.underlay_maximum_height_efficient_for_tiling = + dceip->underlay_maximum_height_efficient_for_tiling = bw_int_to_fixed(1080); - dceip.peak_pte_request_to_eviction_ratio_limiting_multiple_displays_or_single_rotated_display = + dceip->peak_pte_request_to_eviction_ratio_limiting_multiple_displays_or_single_rotated_display = bw_frc_to_fixed(3, 10); - dceip.peak_pte_request_to_eviction_ratio_limiting_single_display_no_rotation = + dceip->peak_pte_request_to_eviction_ratio_limiting_single_display_no_rotation = bw_int_to_fixed(25); - dceip.minimum_outstanding_pte_request_limit = bw_int_to_fixed( + dceip->minimum_outstanding_pte_request_limit = bw_int_to_fixed( 2); - dceip.maximum_total_outstanding_pte_requests_allowed_by_saw = + dceip->maximum_total_outstanding_pte_requests_allowed_by_saw = bw_int_to_fixed(128); - dceip.limit_excessive_outstanding_dmif_requests = true; - dceip.linear_mode_line_request_alternation_slice = + dceip->limit_excessive_outstanding_dmif_requests = true; + dceip->linear_mode_line_request_alternation_slice = bw_int_to_fixed(64); - dceip.scatter_gather_lines_of_pte_prefetching_in_linear_mode = + dceip->scatter_gather_lines_of_pte_prefetching_in_linear_mode = 32; - dceip.display_write_back420_luma_mcifwr_buffer_size = 12288; - dceip.display_write_back420_chroma_mcifwr_buffer_size = 8192; - dceip.request_efficiency = bw_frc_to_fixed(8, 10); - dceip.dispclk_per_request = bw_int_to_fixed(2); - dceip.dispclk_ramping_factor = bw_frc_to_fixed(105, 100); - dceip.display_pipe_throughput_factor = bw_frc_to_fixed(105, 100); - dceip.scatter_gather_pte_request_rows_in_tiling_mode = 2; - dceip.mcifwr_all_surfaces_burst_time = bw_int_to_fixed(0); /* todo: this is a bug*/ + dceip->display_write_back420_luma_mcifwr_buffer_size = 12288; + dceip->display_write_back420_chroma_mcifwr_buffer_size = 8192; + dceip->request_efficiency = bw_frc_to_fixed(8, 10); + dceip->dispclk_per_request = bw_int_to_fixed(2); + dceip->dispclk_ramping_factor = bw_frc_to_fixed(105, 100); + dceip->display_pipe_throughput_factor = bw_frc_to_fixed(105, 100); + dceip->scatter_gather_pte_request_rows_in_tiling_mode = 2; + dceip->mcifwr_all_surfaces_burst_time = bw_int_to_fixed(0); /* todo: this is a bug*/ break; case BW_CALCS_VERSION_POLARIS10: /* TODO: Treat VEGAM the same as P10 for now * Need to tune the para for VEGAM if needed */ case BW_CALCS_VERSION_VEGAM: - vbios.memory_type = bw_def_gddr5; - vbios.dram_channel_width_in_bits = 32; - vbios.number_of_dram_channels = asic_id.vram_width / vbios.dram_channel_width_in_bits; - vbios.number_of_dram_banks = 8; - vbios.high_yclk = bw_int_to_fixed(6000); - vbios.mid_yclk = bw_int_to_fixed(3200); - vbios.low_yclk = bw_int_to_fixed(1000); - vbios.low_sclk = bw_int_to_fixed(300); - vbios.mid1_sclk = bw_int_to_fixed(400); - vbios.mid2_sclk = bw_int_to_fixed(500); - vbios.mid3_sclk = bw_int_to_fixed(600); - vbios.mid4_sclk = bw_int_to_fixed(700); - vbios.mid5_sclk = bw_int_to_fixed(800); - vbios.mid6_sclk = bw_int_to_fixed(974); - vbios.high_sclk = bw_int_to_fixed(1154); - vbios.low_voltage_max_dispclk = bw_int_to_fixed(459); - vbios.mid_voltage_max_dispclk = bw_int_to_fixed(654); - vbios.high_voltage_max_dispclk = bw_int_to_fixed(1108); - vbios.low_voltage_max_phyclk = bw_int_to_fixed(540); - vbios.mid_voltage_max_phyclk = bw_int_to_fixed(810); - vbios.high_voltage_max_phyclk = bw_int_to_fixed(810); - vbios.data_return_bus_width = bw_int_to_fixed(32); - vbios.trc = bw_int_to_fixed(48); - vbios.dmifmc_urgent_latency = bw_int_to_fixed(3); - vbios.stutter_self_refresh_exit_latency = bw_int_to_fixed(5); - vbios.stutter_self_refresh_entry_latency = bw_int_to_fixed(0); - vbios.nbp_state_change_latency = bw_int_to_fixed(45); - vbios.mcifwrmc_urgent_latency = bw_int_to_fixed(10); - vbios.scatter_gather_enable = true; - vbios.down_spread_percentage = bw_frc_to_fixed(5, 10); - vbios.cursor_width = 32; - vbios.average_compression_rate = 4; - vbios.number_of_request_slots_gmc_reserves_for_dmif_per_channel = 256; - vbios.blackout_duration = bw_int_to_fixed(0); /* us */ - vbios.maximum_blackout_recovery_time = bw_int_to_fixed(0); - - dceip.max_average_percent_of_ideal_port_bw_display_can_use_in_normal_system_operation = 100; - dceip.max_average_percent_of_ideal_drambw_display_can_use_in_normal_system_operation = 100; - dceip.percent_of_ideal_port_bw_received_after_urgent_latency = 100; - dceip.large_cursor = false; - dceip.dmif_request_buffer_size = bw_int_to_fixed(768); - dceip.dmif_pipe_en_fbc_chunk_tracker = false; - dceip.cursor_max_outstanding_group_num = 1; - dceip.lines_interleaved_into_lb = 2; - dceip.chunk_width = 256; - dceip.number_of_graphics_pipes = 6; - dceip.number_of_underlay_pipes = 0; - dceip.low_power_tiling_mode = 0; - dceip.display_write_back_supported = false; - dceip.argb_compression_support = true; - dceip.underlay_vscaler_efficiency6_bit_per_component = + vbios->memory_type = bw_def_gddr5; + vbios->dram_channel_width_in_bits = 32; + vbios->number_of_dram_channels = asic_id.vram_width / vbios->dram_channel_width_in_bits; + vbios->number_of_dram_banks = 8; + vbios->high_yclk = bw_int_to_fixed(6000); + vbios->mid_yclk = bw_int_to_fixed(3200); + vbios->low_yclk = bw_int_to_fixed(1000); + vbios->low_sclk = bw_int_to_fixed(300); + vbios->mid1_sclk = bw_int_to_fixed(400); + vbios->mid2_sclk = bw_int_to_fixed(500); + vbios->mid3_sclk = bw_int_to_fixed(600); + vbios->mid4_sclk = bw_int_to_fixed(700); + vbios->mid5_sclk = bw_int_to_fixed(800); + vbios->mid6_sclk = bw_int_to_fixed(974); + vbios->high_sclk = bw_int_to_fixed(1154); + vbios->low_voltage_max_dispclk = bw_int_to_fixed(459); + vbios->mid_voltage_max_dispclk = bw_int_to_fixed(654); + vbios->high_voltage_max_dispclk = bw_int_to_fixed(1108); + vbios->low_voltage_max_phyclk = bw_int_to_fixed(540); + vbios->mid_voltage_max_phyclk = bw_int_to_fixed(810); + vbios->high_voltage_max_phyclk = bw_int_to_fixed(810); + vbios->data_return_bus_width = bw_int_to_fixed(32); + vbios->trc = bw_int_to_fixed(48); + vbios->dmifmc_urgent_latency = bw_int_to_fixed(3); + vbios->stutter_self_refresh_exit_latency = bw_int_to_fixed(5); + vbios->stutter_self_refresh_entry_latency = bw_int_to_fixed(0); + vbios->nbp_state_change_latency = bw_int_to_fixed(45); + vbios->mcifwrmc_urgent_latency = bw_int_to_fixed(10); + vbios->scatter_gather_enable = true; + vbios->down_spread_percentage = bw_frc_to_fixed(5, 10); + vbios->cursor_width = 32; + vbios->average_compression_rate = 4; + vbios->number_of_request_slots_gmc_reserves_for_dmif_per_channel = 256; + vbios->blackout_duration = bw_int_to_fixed(0); /* us */ + vbios->maximum_blackout_recovery_time = bw_int_to_fixed(0); + + dceip->max_average_percent_of_ideal_port_bw_display_can_use_in_normal_system_operation = 100; + dceip->max_average_percent_of_ideal_drambw_display_can_use_in_normal_system_operation = 100; + dceip->percent_of_ideal_port_bw_received_after_urgent_latency = 100; + dceip->large_cursor = false; + dceip->dmif_request_buffer_size = bw_int_to_fixed(768); + dceip->dmif_pipe_en_fbc_chunk_tracker = false; + dceip->cursor_max_outstanding_group_num = 1; + dceip->lines_interleaved_into_lb = 2; + dceip->chunk_width = 256; + dceip->number_of_graphics_pipes = 6; + dceip->number_of_underlay_pipes = 0; + dceip->low_power_tiling_mode = 0; + dceip->display_write_back_supported = false; + dceip->argb_compression_support = true; + dceip->underlay_vscaler_efficiency6_bit_per_component = bw_frc_to_fixed(35556, 10000); - dceip.underlay_vscaler_efficiency8_bit_per_component = + dceip->underlay_vscaler_efficiency8_bit_per_component = bw_frc_to_fixed(34286, 10000); - dceip.underlay_vscaler_efficiency10_bit_per_component = + dceip->underlay_vscaler_efficiency10_bit_per_component = bw_frc_to_fixed(32, 10); - dceip.underlay_vscaler_efficiency12_bit_per_component = + dceip->underlay_vscaler_efficiency12_bit_per_component = bw_int_to_fixed(3); - dceip.graphics_vscaler_efficiency6_bit_per_component = + dceip->graphics_vscaler_efficiency6_bit_per_component = bw_frc_to_fixed(35, 10); - dceip.graphics_vscaler_efficiency8_bit_per_component = + dceip->graphics_vscaler_efficiency8_bit_per_component = bw_frc_to_fixed(34286, 10000); - dceip.graphics_vscaler_efficiency10_bit_per_component = + dceip->graphics_vscaler_efficiency10_bit_per_component = bw_frc_to_fixed(32, 10); - dceip.graphics_vscaler_efficiency12_bit_per_component = + dceip->graphics_vscaler_efficiency12_bit_per_component = bw_int_to_fixed(3); - dceip.alpha_vscaler_efficiency = bw_int_to_fixed(3); - dceip.max_dmif_buffer_allocated = 4; - dceip.graphics_dmif_size = 12288; - dceip.underlay_luma_dmif_size = 19456; - dceip.underlay_chroma_dmif_size = 23552; - dceip.pre_downscaler_enabled = true; - dceip.underlay_downscale_prefetch_enabled = true; - dceip.lb_write_pixels_per_dispclk = bw_int_to_fixed(1); - dceip.lb_size_per_component444 = bw_int_to_fixed(245952); - dceip.graphics_lb_nodownscaling_multi_line_prefetching = true; - dceip.stutter_and_dram_clock_state_change_gated_before_cursor = + dceip->alpha_vscaler_efficiency = bw_int_to_fixed(3); + dceip->max_dmif_buffer_allocated = 4; + dceip->graphics_dmif_size = 12288; + dceip->underlay_luma_dmif_size = 19456; + dceip->underlay_chroma_dmif_size = 23552; + dceip->pre_downscaler_enabled = true; + dceip->underlay_downscale_prefetch_enabled = true; + dceip->lb_write_pixels_per_dispclk = bw_int_to_fixed(1); + dceip->lb_size_per_component444 = bw_int_to_fixed(245952); + dceip->graphics_lb_nodownscaling_multi_line_prefetching = true; + dceip->stutter_and_dram_clock_state_change_gated_before_cursor = bw_int_to_fixed(1); - dceip.underlay420_luma_lb_size_per_component = bw_int_to_fixed( + dceip->underlay420_luma_lb_size_per_component = bw_int_to_fixed( 82176); - dceip.underlay420_chroma_lb_size_per_component = + dceip->underlay420_chroma_lb_size_per_component = bw_int_to_fixed(164352); - dceip.underlay422_lb_size_per_component = bw_int_to_fixed( + dceip->underlay422_lb_size_per_component = bw_int_to_fixed( 82176); - dceip.cursor_chunk_width = bw_int_to_fixed(64); - dceip.cursor_dcp_buffer_lines = bw_int_to_fixed(4); - dceip.underlay_maximum_width_efficient_for_tiling = + dceip->cursor_chunk_width = bw_int_to_fixed(64); + dceip->cursor_dcp_buffer_lines = bw_int_to_fixed(4); + dceip->underlay_maximum_width_efficient_for_tiling = bw_int_to_fixed(1920); - dceip.underlay_maximum_height_efficient_for_tiling = + dceip->underlay_maximum_height_efficient_for_tiling = bw_int_to_fixed(1080); - dceip.peak_pte_request_to_eviction_ratio_limiting_multiple_displays_or_single_rotated_display = + dceip->peak_pte_request_to_eviction_ratio_limiting_multiple_displays_or_single_rotated_display = bw_frc_to_fixed(3, 10); - dceip.peak_pte_request_to_eviction_ratio_limiting_single_display_no_rotation = + dceip->peak_pte_request_to_eviction_ratio_limiting_single_display_no_rotation = bw_int_to_fixed(25); - dceip.minimum_outstanding_pte_request_limit = bw_int_to_fixed( + dceip->minimum_outstanding_pte_request_limit = bw_int_to_fixed( 2); - dceip.maximum_total_outstanding_pte_requests_allowed_by_saw = + dceip->maximum_total_outstanding_pte_requests_allowed_by_saw = bw_int_to_fixed(128); - dceip.limit_excessive_outstanding_dmif_requests = true; - dceip.linear_mode_line_request_alternation_slice = + dceip->limit_excessive_outstanding_dmif_requests = true; + dceip->linear_mode_line_request_alternation_slice = bw_int_to_fixed(64); - dceip.scatter_gather_lines_of_pte_prefetching_in_linear_mode = + dceip->scatter_gather_lines_of_pte_prefetching_in_linear_mode = 32; - dceip.display_write_back420_luma_mcifwr_buffer_size = 12288; - dceip.display_write_back420_chroma_mcifwr_buffer_size = 8192; - dceip.request_efficiency = bw_frc_to_fixed(8, 10); - dceip.dispclk_per_request = bw_int_to_fixed(2); - dceip.dispclk_ramping_factor = bw_frc_to_fixed(105, 100); - dceip.display_pipe_throughput_factor = bw_frc_to_fixed(105, 100); - dceip.scatter_gather_pte_request_rows_in_tiling_mode = 2; - dceip.mcifwr_all_surfaces_burst_time = bw_int_to_fixed(0); + dceip->display_write_back420_luma_mcifwr_buffer_size = 12288; + dceip->display_write_back420_chroma_mcifwr_buffer_size = 8192; + dceip->request_efficiency = bw_frc_to_fixed(8, 10); + dceip->dispclk_per_request = bw_int_to_fixed(2); + dceip->dispclk_ramping_factor = bw_frc_to_fixed(105, 100); + dceip->display_pipe_throughput_factor = bw_frc_to_fixed(105, 100); + dceip->scatter_gather_pte_request_rows_in_tiling_mode = 2; + dceip->mcifwr_all_surfaces_burst_time = bw_int_to_fixed(0); break; case BW_CALCS_VERSION_POLARIS11: - vbios.memory_type = bw_def_gddr5; - vbios.dram_channel_width_in_bits = 32; - vbios.number_of_dram_channels = asic_id.vram_width / vbios.dram_channel_width_in_bits; - vbios.number_of_dram_banks = 8; - vbios.high_yclk = bw_int_to_fixed(6000); - vbios.mid_yclk = bw_int_to_fixed(3200); - vbios.low_yclk = bw_int_to_fixed(1000); - vbios.low_sclk = bw_int_to_fixed(300); - vbios.mid1_sclk = bw_int_to_fixed(400); - vbios.mid2_sclk = bw_int_to_fixed(500); - vbios.mid3_sclk = bw_int_to_fixed(600); - vbios.mid4_sclk = bw_int_to_fixed(700); - vbios.mid5_sclk = bw_int_to_fixed(800); - vbios.mid6_sclk = bw_int_to_fixed(974); - vbios.high_sclk = bw_int_to_fixed(1154); - vbios.low_voltage_max_dispclk = bw_int_to_fixed(459); - vbios.mid_voltage_max_dispclk = bw_int_to_fixed(654); - vbios.high_voltage_max_dispclk = bw_int_to_fixed(1108); - vbios.low_voltage_max_phyclk = bw_int_to_fixed(540); - vbios.mid_voltage_max_phyclk = bw_int_to_fixed(810); - vbios.high_voltage_max_phyclk = bw_int_to_fixed(810); - vbios.data_return_bus_width = bw_int_to_fixed(32); - vbios.trc = bw_int_to_fixed(48); - if (vbios.number_of_dram_channels == 2) // 64-bit - vbios.dmifmc_urgent_latency = bw_int_to_fixed(4); + vbios->memory_type = bw_def_gddr5; + vbios->dram_channel_width_in_bits = 32; + vbios->number_of_dram_channels = asic_id.vram_width / vbios->dram_channel_width_in_bits; + vbios->number_of_dram_banks = 8; + vbios->high_yclk = bw_int_to_fixed(6000); + vbios->mid_yclk = bw_int_to_fixed(3200); + vbios->low_yclk = bw_int_to_fixed(1000); + vbios->low_sclk = bw_int_to_fixed(300); + vbios->mid1_sclk = bw_int_to_fixed(400); + vbios->mid2_sclk = bw_int_to_fixed(500); + vbios->mid3_sclk = bw_int_to_fixed(600); + vbios->mid4_sclk = bw_int_to_fixed(700); + vbios->mid5_sclk = bw_int_to_fixed(800); + vbios->mid6_sclk = bw_int_to_fixed(974); + vbios->high_sclk = bw_int_to_fixed(1154); + vbios->low_voltage_max_dispclk = bw_int_to_fixed(459); + vbios->mid_voltage_max_dispclk = bw_int_to_fixed(654); + vbios->high_voltage_max_dispclk = bw_int_to_fixed(1108); + vbios->low_voltage_max_phyclk = bw_int_to_fixed(540); + vbios->mid_voltage_max_phyclk = bw_int_to_fixed(810); + vbios->high_voltage_max_phyclk = bw_int_to_fixed(810); + vbios->data_return_bus_width = bw_int_to_fixed(32); + vbios->trc = bw_int_to_fixed(48); + if (vbios->number_of_dram_channels == 2) // 64-bit + vbios->dmifmc_urgent_latency = bw_int_to_fixed(4); else - vbios.dmifmc_urgent_latency = bw_int_to_fixed(3); - vbios.stutter_self_refresh_exit_latency = bw_int_to_fixed(5); - vbios.stutter_self_refresh_entry_latency = bw_int_to_fixed(0); - vbios.nbp_state_change_latency = bw_int_to_fixed(45); - vbios.mcifwrmc_urgent_latency = bw_int_to_fixed(10); - vbios.scatter_gather_enable = true; - vbios.down_spread_percentage = bw_frc_to_fixed(5, 10); - vbios.cursor_width = 32; - vbios.average_compression_rate = 4; - vbios.number_of_request_slots_gmc_reserves_for_dmif_per_channel = 256; - vbios.blackout_duration = bw_int_to_fixed(0); /* us */ - vbios.maximum_blackout_recovery_time = bw_int_to_fixed(0); - - dceip.max_average_percent_of_ideal_port_bw_display_can_use_in_normal_system_operation = 100; - dceip.max_average_percent_of_ideal_drambw_display_can_use_in_normal_system_operation = 100; - dceip.percent_of_ideal_port_bw_received_after_urgent_latency = 100; - dceip.large_cursor = false; - dceip.dmif_request_buffer_size = bw_int_to_fixed(768); - dceip.dmif_pipe_en_fbc_chunk_tracker = false; - dceip.cursor_max_outstanding_group_num = 1; - dceip.lines_interleaved_into_lb = 2; - dceip.chunk_width = 256; - dceip.number_of_graphics_pipes = 5; - dceip.number_of_underlay_pipes = 0; - dceip.low_power_tiling_mode = 0; - dceip.display_write_back_supported = false; - dceip.argb_compression_support = true; - dceip.underlay_vscaler_efficiency6_bit_per_component = + vbios->dmifmc_urgent_latency = bw_int_to_fixed(3); + vbios->stutter_self_refresh_exit_latency = bw_int_to_fixed(5); + vbios->stutter_self_refresh_entry_latency = bw_int_to_fixed(0); + vbios->nbp_state_change_latency = bw_int_to_fixed(45); + vbios->mcifwrmc_urgent_latency = bw_int_to_fixed(10); + vbios->scatter_gather_enable = true; + vbios->down_spread_percentage = bw_frc_to_fixed(5, 10); + vbios->cursor_width = 32; + vbios->average_compression_rate = 4; + vbios->number_of_request_slots_gmc_reserves_for_dmif_per_channel = 256; + vbios->blackout_duration = bw_int_to_fixed(0); /* us */ + vbios->maximum_blackout_recovery_time = bw_int_to_fixed(0); + + dceip->max_average_percent_of_ideal_port_bw_display_can_use_in_normal_system_operation = 100; + dceip->max_average_percent_of_ideal_drambw_display_can_use_in_normal_system_operation = 100; + dceip->percent_of_ideal_port_bw_received_after_urgent_latency = 100; + dceip->large_cursor = false; + dceip->dmif_request_buffer_size = bw_int_to_fixed(768); + dceip->dmif_pipe_en_fbc_chunk_tracker = false; + dceip->cursor_max_outstanding_group_num = 1; + dceip->lines_interleaved_into_lb = 2; + dceip->chunk_width = 256; + dceip->number_of_graphics_pipes = 5; + dceip->number_of_underlay_pipes = 0; + dceip->low_power_tiling_mode = 0; + dceip->display_write_back_supported = false; + dceip->argb_compression_support = true; + dceip->underlay_vscaler_efficiency6_bit_per_component = bw_frc_to_fixed(35556, 10000); - dceip.underlay_vscaler_efficiency8_bit_per_component = + dceip->underlay_vscaler_efficiency8_bit_per_component = bw_frc_to_fixed(34286, 10000); - dceip.underlay_vscaler_efficiency10_bit_per_component = + dceip->underlay_vscaler_efficiency10_bit_per_component = bw_frc_to_fixed(32, 10); - dceip.underlay_vscaler_efficiency12_bit_per_component = + dceip->underlay_vscaler_efficiency12_bit_per_component = bw_int_to_fixed(3); - dceip.graphics_vscaler_efficiency6_bit_per_component = + dceip->graphics_vscaler_efficiency6_bit_per_component = bw_frc_to_fixed(35, 10); - dceip.graphics_vscaler_efficiency8_bit_per_component = + dceip->graphics_vscaler_efficiency8_bit_per_component = bw_frc_to_fixed(34286, 10000); - dceip.graphics_vscaler_efficiency10_bit_per_component = + dceip->graphics_vscaler_efficiency10_bit_per_component = bw_frc_to_fixed(32, 10); - dceip.graphics_vscaler_efficiency12_bit_per_component = + dceip->graphics_vscaler_efficiency12_bit_per_component = bw_int_to_fixed(3); - dceip.alpha_vscaler_efficiency = bw_int_to_fixed(3); - dceip.max_dmif_buffer_allocated = 4; - dceip.graphics_dmif_size = 12288; - dceip.underlay_luma_dmif_size = 19456; - dceip.underlay_chroma_dmif_size = 23552; - dceip.pre_downscaler_enabled = true; - dceip.underlay_downscale_prefetch_enabled = true; - dceip.lb_write_pixels_per_dispclk = bw_int_to_fixed(1); - dceip.lb_size_per_component444 = bw_int_to_fixed(245952); - dceip.graphics_lb_nodownscaling_multi_line_prefetching = true; - dceip.stutter_and_dram_clock_state_change_gated_before_cursor = + dceip->alpha_vscaler_efficiency = bw_int_to_fixed(3); + dceip->max_dmif_buffer_allocated = 4; + dceip->graphics_dmif_size = 12288; + dceip->underlay_luma_dmif_size = 19456; + dceip->underlay_chroma_dmif_size = 23552; + dceip->pre_downscaler_enabled = true; + dceip->underlay_downscale_prefetch_enabled = true; + dceip->lb_write_pixels_per_dispclk = bw_int_to_fixed(1); + dceip->lb_size_per_component444 = bw_int_to_fixed(245952); + dceip->graphics_lb_nodownscaling_multi_line_prefetching = true; + dceip->stutter_and_dram_clock_state_change_gated_before_cursor = bw_int_to_fixed(1); - dceip.underlay420_luma_lb_size_per_component = bw_int_to_fixed( + dceip->underlay420_luma_lb_size_per_component = bw_int_to_fixed( 82176); - dceip.underlay420_chroma_lb_size_per_component = + dceip->underlay420_chroma_lb_size_per_component = bw_int_to_fixed(164352); - dceip.underlay422_lb_size_per_component = bw_int_to_fixed( + dceip->underlay422_lb_size_per_component = bw_int_to_fixed( 82176); - dceip.cursor_chunk_width = bw_int_to_fixed(64); - dceip.cursor_dcp_buffer_lines = bw_int_to_fixed(4); - dceip.underlay_maximum_width_efficient_for_tiling = + dceip->cursor_chunk_width = bw_int_to_fixed(64); + dceip->cursor_dcp_buffer_lines = bw_int_to_fixed(4); + dceip->underlay_maximum_width_efficient_for_tiling = bw_int_to_fixed(1920); - dceip.underlay_maximum_height_efficient_for_tiling = + dceip->underlay_maximum_height_efficient_for_tiling = bw_int_to_fixed(1080); - dceip.peak_pte_request_to_eviction_ratio_limiting_multiple_displays_or_single_rotated_display = + dceip->peak_pte_request_to_eviction_ratio_limiting_multiple_displays_or_single_rotated_display = bw_frc_to_fixed(3, 10); - dceip.peak_pte_request_to_eviction_ratio_limiting_single_display_no_rotation = + dceip->peak_pte_request_to_eviction_ratio_limiting_single_display_no_rotation = bw_int_to_fixed(25); - dceip.minimum_outstanding_pte_request_limit = bw_int_to_fixed( + dceip->minimum_outstanding_pte_request_limit = bw_int_to_fixed( 2); - dceip.maximum_total_outstanding_pte_requests_allowed_by_saw = + dceip->maximum_total_outstanding_pte_requests_allowed_by_saw = bw_int_to_fixed(128); - dceip.limit_excessive_outstanding_dmif_requests = true; - dceip.linear_mode_line_request_alternation_slice = + dceip->limit_excessive_outstanding_dmif_requests = true; + dceip->linear_mode_line_request_alternation_slice = bw_int_to_fixed(64); - dceip.scatter_gather_lines_of_pte_prefetching_in_linear_mode = + dceip->scatter_gather_lines_of_pte_prefetching_in_linear_mode = 32; - dceip.display_write_back420_luma_mcifwr_buffer_size = 12288; - dceip.display_write_back420_chroma_mcifwr_buffer_size = 8192; - dceip.request_efficiency = bw_frc_to_fixed(8, 10); - dceip.dispclk_per_request = bw_int_to_fixed(2); - dceip.dispclk_ramping_factor = bw_frc_to_fixed(105, 100); - dceip.display_pipe_throughput_factor = bw_frc_to_fixed(105, 100); - dceip.scatter_gather_pte_request_rows_in_tiling_mode = 2; - dceip.mcifwr_all_surfaces_burst_time = bw_int_to_fixed(0); + dceip->display_write_back420_luma_mcifwr_buffer_size = 12288; + dceip->display_write_back420_chroma_mcifwr_buffer_size = 8192; + dceip->request_efficiency = bw_frc_to_fixed(8, 10); + dceip->dispclk_per_request = bw_int_to_fixed(2); + dceip->dispclk_ramping_factor = bw_frc_to_fixed(105, 100); + dceip->display_pipe_throughput_factor = bw_frc_to_fixed(105, 100); + dceip->scatter_gather_pte_request_rows_in_tiling_mode = 2; + dceip->mcifwr_all_surfaces_burst_time = bw_int_to_fixed(0); break; case BW_CALCS_VERSION_POLARIS12: - vbios.memory_type = bw_def_gddr5; - vbios.dram_channel_width_in_bits = 32; - vbios.number_of_dram_channels = asic_id.vram_width / vbios.dram_channel_width_in_bits; - vbios.number_of_dram_banks = 8; - vbios.high_yclk = bw_int_to_fixed(6000); - vbios.mid_yclk = bw_int_to_fixed(3200); - vbios.low_yclk = bw_int_to_fixed(1000); - vbios.low_sclk = bw_int_to_fixed(678); - vbios.mid1_sclk = bw_int_to_fixed(864); - vbios.mid2_sclk = bw_int_to_fixed(900); - vbios.mid3_sclk = bw_int_to_fixed(920); - vbios.mid4_sclk = bw_int_to_fixed(940); - vbios.mid5_sclk = bw_int_to_fixed(960); - vbios.mid6_sclk = bw_int_to_fixed(980); - vbios.high_sclk = bw_int_to_fixed(1049); - vbios.low_voltage_max_dispclk = bw_int_to_fixed(459); - vbios.mid_voltage_max_dispclk = bw_int_to_fixed(654); - vbios.high_voltage_max_dispclk = bw_int_to_fixed(1108); - vbios.low_voltage_max_phyclk = bw_int_to_fixed(540); - vbios.mid_voltage_max_phyclk = bw_int_to_fixed(810); - vbios.high_voltage_max_phyclk = bw_int_to_fixed(810); - vbios.data_return_bus_width = bw_int_to_fixed(32); - vbios.trc = bw_int_to_fixed(48); - if (vbios.number_of_dram_channels == 2) // 64-bit - vbios.dmifmc_urgent_latency = bw_int_to_fixed(4); + vbios->memory_type = bw_def_gddr5; + vbios->dram_channel_width_in_bits = 32; + vbios->number_of_dram_channels = asic_id.vram_width / vbios->dram_channel_width_in_bits; + vbios->number_of_dram_banks = 8; + vbios->high_yclk = bw_int_to_fixed(6000); + vbios->mid_yclk = bw_int_to_fixed(3200); + vbios->low_yclk = bw_int_to_fixed(1000); + vbios->low_sclk = bw_int_to_fixed(678); + vbios->mid1_sclk = bw_int_to_fixed(864); + vbios->mid2_sclk = bw_int_to_fixed(900); + vbios->mid3_sclk = bw_int_to_fixed(920); + vbios->mid4_sclk = bw_int_to_fixed(940); + vbios->mid5_sclk = bw_int_to_fixed(960); + vbios->mid6_sclk = bw_int_to_fixed(980); + vbios->high_sclk = bw_int_to_fixed(1049); + vbios->low_voltage_max_dispclk = bw_int_to_fixed(459); + vbios->mid_voltage_max_dispclk = bw_int_to_fixed(654); + vbios->high_voltage_max_dispclk = bw_int_to_fixed(1108); + vbios->low_voltage_max_phyclk = bw_int_to_fixed(540); + vbios->mid_voltage_max_phyclk = bw_int_to_fixed(810); + vbios->high_voltage_max_phyclk = bw_int_to_fixed(810); + vbios->data_return_bus_width = bw_int_to_fixed(32); + vbios->trc = bw_int_to_fixed(48); + if (vbios->number_of_dram_channels == 2) // 64-bit + vbios->dmifmc_urgent_latency = bw_int_to_fixed(4); else - vbios.dmifmc_urgent_latency = bw_int_to_fixed(3); - vbios.stutter_self_refresh_exit_latency = bw_int_to_fixed(5); - vbios.stutter_self_refresh_entry_latency = bw_int_to_fixed(0); - vbios.nbp_state_change_latency = bw_int_to_fixed(250); - vbios.mcifwrmc_urgent_latency = bw_int_to_fixed(10); - vbios.scatter_gather_enable = false; - vbios.down_spread_percentage = bw_frc_to_fixed(5, 10); - vbios.cursor_width = 32; - vbios.average_compression_rate = 4; - vbios.number_of_request_slots_gmc_reserves_for_dmif_per_channel = 256; - vbios.blackout_duration = bw_int_to_fixed(0); /* us */ - vbios.maximum_blackout_recovery_time = bw_int_to_fixed(0); - - dceip.max_average_percent_of_ideal_port_bw_display_can_use_in_normal_system_operation = 100; - dceip.max_average_percent_of_ideal_drambw_display_can_use_in_normal_system_operation = 100; - dceip.percent_of_ideal_port_bw_received_after_urgent_latency = 100; - dceip.large_cursor = false; - dceip.dmif_request_buffer_size = bw_int_to_fixed(768); - dceip.dmif_pipe_en_fbc_chunk_tracker = false; - dceip.cursor_max_outstanding_group_num = 1; - dceip.lines_interleaved_into_lb = 2; - dceip.chunk_width = 256; - dceip.number_of_graphics_pipes = 5; - dceip.number_of_underlay_pipes = 0; - dceip.low_power_tiling_mode = 0; - dceip.display_write_back_supported = true; - dceip.argb_compression_support = true; - dceip.underlay_vscaler_efficiency6_bit_per_component = + vbios->dmifmc_urgent_latency = bw_int_to_fixed(3); + vbios->stutter_self_refresh_exit_latency = bw_int_to_fixed(5); + vbios->stutter_self_refresh_entry_latency = bw_int_to_fixed(0); + vbios->nbp_state_change_latency = bw_int_to_fixed(250); + vbios->mcifwrmc_urgent_latency = bw_int_to_fixed(10); + vbios->scatter_gather_enable = false; + vbios->down_spread_percentage = bw_frc_to_fixed(5, 10); + vbios->cursor_width = 32; + vbios->average_compression_rate = 4; + vbios->number_of_request_slots_gmc_reserves_for_dmif_per_channel = 256; + vbios->blackout_duration = bw_int_to_fixed(0); /* us */ + vbios->maximum_blackout_recovery_time = bw_int_to_fixed(0); + + dceip->max_average_percent_of_ideal_port_bw_display_can_use_in_normal_system_operation = 100; + dceip->max_average_percent_of_ideal_drambw_display_can_use_in_normal_system_operation = 100; + dceip->percent_of_ideal_port_bw_received_after_urgent_latency = 100; + dceip->large_cursor = false; + dceip->dmif_request_buffer_size = bw_int_to_fixed(768); + dceip->dmif_pipe_en_fbc_chunk_tracker = false; + dceip->cursor_max_outstanding_group_num = 1; + dceip->lines_interleaved_into_lb = 2; + dceip->chunk_width = 256; + dceip->number_of_graphics_pipes = 5; + dceip->number_of_underlay_pipes = 0; + dceip->low_power_tiling_mode = 0; + dceip->display_write_back_supported = true; + dceip->argb_compression_support = true; + dceip->underlay_vscaler_efficiency6_bit_per_component = bw_frc_to_fixed(35556, 10000); - dceip.underlay_vscaler_efficiency8_bit_per_component = + dceip->underlay_vscaler_efficiency8_bit_per_component = bw_frc_to_fixed(34286, 10000); - dceip.underlay_vscaler_efficiency10_bit_per_component = + dceip->underlay_vscaler_efficiency10_bit_per_component = bw_frc_to_fixed(32, 10); - dceip.underlay_vscaler_efficiency12_bit_per_component = + dceip->underlay_vscaler_efficiency12_bit_per_component = bw_int_to_fixed(3); - dceip.graphics_vscaler_efficiency6_bit_per_component = + dceip->graphics_vscaler_efficiency6_bit_per_component = bw_frc_to_fixed(35, 10); - dceip.graphics_vscaler_efficiency8_bit_per_component = + dceip->graphics_vscaler_efficiency8_bit_per_component = bw_frc_to_fixed(34286, 10000); - dceip.graphics_vscaler_efficiency10_bit_per_component = + dceip->graphics_vscaler_efficiency10_bit_per_component = bw_frc_to_fixed(32, 10); - dceip.graphics_vscaler_efficiency12_bit_per_component = + dceip->graphics_vscaler_efficiency12_bit_per_component = bw_int_to_fixed(3); - dceip.alpha_vscaler_efficiency = bw_int_to_fixed(3); - dceip.max_dmif_buffer_allocated = 4; - dceip.graphics_dmif_size = 12288; - dceip.underlay_luma_dmif_size = 19456; - dceip.underlay_chroma_dmif_size = 23552; - dceip.pre_downscaler_enabled = true; - dceip.underlay_downscale_prefetch_enabled = true; - dceip.lb_write_pixels_per_dispclk = bw_int_to_fixed(1); - dceip.lb_size_per_component444 = bw_int_to_fixed(245952); - dceip.graphics_lb_nodownscaling_multi_line_prefetching = true; - dceip.stutter_and_dram_clock_state_change_gated_before_cursor = + dceip->alpha_vscaler_efficiency = bw_int_to_fixed(3); + dceip->max_dmif_buffer_allocated = 4; + dceip->graphics_dmif_size = 12288; + dceip->underlay_luma_dmif_size = 19456; + dceip->underlay_chroma_dmif_size = 23552; + dceip->pre_downscaler_enabled = true; + dceip->underlay_downscale_prefetch_enabled = true; + dceip->lb_write_pixels_per_dispclk = bw_int_to_fixed(1); + dceip->lb_size_per_component444 = bw_int_to_fixed(245952); + dceip->graphics_lb_nodownscaling_multi_line_prefetching = true; + dceip->stutter_and_dram_clock_state_change_gated_before_cursor = bw_int_to_fixed(1); - dceip.underlay420_luma_lb_size_per_component = bw_int_to_fixed( + dceip->underlay420_luma_lb_size_per_component = bw_int_to_fixed( 82176); - dceip.underlay420_chroma_lb_size_per_component = + dceip->underlay420_chroma_lb_size_per_component = bw_int_to_fixed(164352); - dceip.underlay422_lb_size_per_component = bw_int_to_fixed( + dceip->underlay422_lb_size_per_component = bw_int_to_fixed( 82176); - dceip.cursor_chunk_width = bw_int_to_fixed(64); - dceip.cursor_dcp_buffer_lines = bw_int_to_fixed(4); - dceip.underlay_maximum_width_efficient_for_tiling = + dceip->cursor_chunk_width = bw_int_to_fixed(64); + dceip->cursor_dcp_buffer_lines = bw_int_to_fixed(4); + dceip->underlay_maximum_width_efficient_for_tiling = bw_int_to_fixed(1920); - dceip.underlay_maximum_height_efficient_for_tiling = + dceip->underlay_maximum_height_efficient_for_tiling = bw_int_to_fixed(1080); - dceip.peak_pte_request_to_eviction_ratio_limiting_multiple_displays_or_single_rotated_display = + dceip->peak_pte_request_to_eviction_ratio_limiting_multiple_displays_or_single_rotated_display = bw_frc_to_fixed(3, 10); - dceip.peak_pte_request_to_eviction_ratio_limiting_single_display_no_rotation = + dceip->peak_pte_request_to_eviction_ratio_limiting_single_display_no_rotation = bw_int_to_fixed(25); - dceip.minimum_outstanding_pte_request_limit = bw_int_to_fixed( + dceip->minimum_outstanding_pte_request_limit = bw_int_to_fixed( 2); - dceip.maximum_total_outstanding_pte_requests_allowed_by_saw = + dceip->maximum_total_outstanding_pte_requests_allowed_by_saw = bw_int_to_fixed(128); - dceip.limit_excessive_outstanding_dmif_requests = true; - dceip.linear_mode_line_request_alternation_slice = + dceip->limit_excessive_outstanding_dmif_requests = true; + dceip->linear_mode_line_request_alternation_slice = bw_int_to_fixed(64); - dceip.scatter_gather_lines_of_pte_prefetching_in_linear_mode = + dceip->scatter_gather_lines_of_pte_prefetching_in_linear_mode = 32; - dceip.display_write_back420_luma_mcifwr_buffer_size = 12288; - dceip.display_write_back420_chroma_mcifwr_buffer_size = 8192; - dceip.request_efficiency = bw_frc_to_fixed(8, 10); - dceip.dispclk_per_request = bw_int_to_fixed(2); - dceip.dispclk_ramping_factor = bw_frc_to_fixed(105, 100); - dceip.display_pipe_throughput_factor = bw_frc_to_fixed(105, 100); - dceip.scatter_gather_pte_request_rows_in_tiling_mode = 2; - dceip.mcifwr_all_surfaces_burst_time = bw_int_to_fixed(0); + dceip->display_write_back420_luma_mcifwr_buffer_size = 12288; + dceip->display_write_back420_chroma_mcifwr_buffer_size = 8192; + dceip->request_efficiency = bw_frc_to_fixed(8, 10); + dceip->dispclk_per_request = bw_int_to_fixed(2); + dceip->dispclk_ramping_factor = bw_frc_to_fixed(105, 100); + dceip->display_pipe_throughput_factor = bw_frc_to_fixed(105, 100); + dceip->scatter_gather_pte_request_rows_in_tiling_mode = 2; + dceip->mcifwr_all_surfaces_burst_time = bw_int_to_fixed(0); break; case BW_CALCS_VERSION_STONEY: - vbios.memory_type = bw_def_gddr5; - vbios.dram_channel_width_in_bits = 64; - vbios.number_of_dram_channels = asic_id.vram_width / vbios.dram_channel_width_in_bits; - vbios.number_of_dram_banks = 8; - vbios.high_yclk = bw_int_to_fixed(1866); - vbios.mid_yclk = bw_int_to_fixed(1866); - vbios.low_yclk = bw_int_to_fixed(1333); - vbios.low_sclk = bw_int_to_fixed(200); - vbios.mid1_sclk = bw_int_to_fixed(600); - vbios.mid2_sclk = bw_int_to_fixed(600); - vbios.mid3_sclk = bw_int_to_fixed(600); - vbios.mid4_sclk = bw_int_to_fixed(600); - vbios.mid5_sclk = bw_int_to_fixed(600); - vbios.mid6_sclk = bw_int_to_fixed(600); - vbios.high_sclk = bw_int_to_fixed(800); - vbios.low_voltage_max_dispclk = bw_int_to_fixed(352); - vbios.mid_voltage_max_dispclk = bw_int_to_fixed(467); - vbios.high_voltage_max_dispclk = bw_int_to_fixed(643); - vbios.low_voltage_max_phyclk = bw_int_to_fixed(540); - vbios.mid_voltage_max_phyclk = bw_int_to_fixed(810); - vbios.high_voltage_max_phyclk = bw_int_to_fixed(810); - vbios.data_return_bus_width = bw_int_to_fixed(32); - vbios.trc = bw_int_to_fixed(50); - vbios.dmifmc_urgent_latency = bw_int_to_fixed(4); - vbios.stutter_self_refresh_exit_latency = bw_frc_to_fixed(158, 10); - vbios.stutter_self_refresh_entry_latency = bw_int_to_fixed(0); - vbios.nbp_state_change_latency = bw_frc_to_fixed(2008, 100); - vbios.mcifwrmc_urgent_latency = bw_int_to_fixed(10); - vbios.scatter_gather_enable = true; - vbios.down_spread_percentage = bw_frc_to_fixed(5, 10); - vbios.cursor_width = 32; - vbios.average_compression_rate = 4; - vbios.number_of_request_slots_gmc_reserves_for_dmif_per_channel = 256; - vbios.blackout_duration = bw_int_to_fixed(0); /* us */ - vbios.maximum_blackout_recovery_time = bw_int_to_fixed(0); - - dceip.max_average_percent_of_ideal_port_bw_display_can_use_in_normal_system_operation = 100; - dceip.max_average_percent_of_ideal_drambw_display_can_use_in_normal_system_operation = 100; - dceip.percent_of_ideal_port_bw_received_after_urgent_latency = 100; - dceip.large_cursor = false; - dceip.dmif_request_buffer_size = bw_int_to_fixed(768); - dceip.dmif_pipe_en_fbc_chunk_tracker = false; - dceip.cursor_max_outstanding_group_num = 1; - dceip.lines_interleaved_into_lb = 2; - dceip.chunk_width = 256; - dceip.number_of_graphics_pipes = 2; - dceip.number_of_underlay_pipes = 1; - dceip.low_power_tiling_mode = 0; - dceip.display_write_back_supported = false; - dceip.argb_compression_support = true; - dceip.underlay_vscaler_efficiency6_bit_per_component = + vbios->memory_type = bw_def_gddr5; + vbios->dram_channel_width_in_bits = 64; + vbios->number_of_dram_channels = asic_id.vram_width / vbios->dram_channel_width_in_bits; + vbios->number_of_dram_banks = 8; + vbios->high_yclk = bw_int_to_fixed(1866); + vbios->mid_yclk = bw_int_to_fixed(1866); + vbios->low_yclk = bw_int_to_fixed(1333); + vbios->low_sclk = bw_int_to_fixed(200); + vbios->mid1_sclk = bw_int_to_fixed(600); + vbios->mid2_sclk = bw_int_to_fixed(600); + vbios->mid3_sclk = bw_int_to_fixed(600); + vbios->mid4_sclk = bw_int_to_fixed(600); + vbios->mid5_sclk = bw_int_to_fixed(600); + vbios->mid6_sclk = bw_int_to_fixed(600); + vbios->high_sclk = bw_int_to_fixed(800); + vbios->low_voltage_max_dispclk = bw_int_to_fixed(352); + vbios->mid_voltage_max_dispclk = bw_int_to_fixed(467); + vbios->high_voltage_max_dispclk = bw_int_to_fixed(643); + vbios->low_voltage_max_phyclk = bw_int_to_fixed(540); + vbios->mid_voltage_max_phyclk = bw_int_to_fixed(810); + vbios->high_voltage_max_phyclk = bw_int_to_fixed(810); + vbios->data_return_bus_width = bw_int_to_fixed(32); + vbios->trc = bw_int_to_fixed(50); + vbios->dmifmc_urgent_latency = bw_int_to_fixed(4); + vbios->stutter_self_refresh_exit_latency = bw_frc_to_fixed(158, 10); + vbios->stutter_self_refresh_entry_latency = bw_int_to_fixed(0); + vbios->nbp_state_change_latency = bw_frc_to_fixed(2008, 100); + vbios->mcifwrmc_urgent_latency = bw_int_to_fixed(10); + vbios->scatter_gather_enable = true; + vbios->down_spread_percentage = bw_frc_to_fixed(5, 10); + vbios->cursor_width = 32; + vbios->average_compression_rate = 4; + vbios->number_of_request_slots_gmc_reserves_for_dmif_per_channel = 256; + vbios->blackout_duration = bw_int_to_fixed(0); /* us */ + vbios->maximum_blackout_recovery_time = bw_int_to_fixed(0); + + dceip->max_average_percent_of_ideal_port_bw_display_can_use_in_normal_system_operation = 100; + dceip->max_average_percent_of_ideal_drambw_display_can_use_in_normal_system_operation = 100; + dceip->percent_of_ideal_port_bw_received_after_urgent_latency = 100; + dceip->large_cursor = false; + dceip->dmif_request_buffer_size = bw_int_to_fixed(768); + dceip->dmif_pipe_en_fbc_chunk_tracker = false; + dceip->cursor_max_outstanding_group_num = 1; + dceip->lines_interleaved_into_lb = 2; + dceip->chunk_width = 256; + dceip->number_of_graphics_pipes = 2; + dceip->number_of_underlay_pipes = 1; + dceip->low_power_tiling_mode = 0; + dceip->display_write_back_supported = false; + dceip->argb_compression_support = true; + dceip->underlay_vscaler_efficiency6_bit_per_component = bw_frc_to_fixed(35556, 10000); - dceip.underlay_vscaler_efficiency8_bit_per_component = + dceip->underlay_vscaler_efficiency8_bit_per_component = bw_frc_to_fixed(34286, 10000); - dceip.underlay_vscaler_efficiency10_bit_per_component = + dceip->underlay_vscaler_efficiency10_bit_per_component = bw_frc_to_fixed(32, 10); - dceip.underlay_vscaler_efficiency12_bit_per_component = + dceip->underlay_vscaler_efficiency12_bit_per_component = bw_int_to_fixed(3); - dceip.graphics_vscaler_efficiency6_bit_per_component = + dceip->graphics_vscaler_efficiency6_bit_per_component = bw_frc_to_fixed(35, 10); - dceip.graphics_vscaler_efficiency8_bit_per_component = + dceip->graphics_vscaler_efficiency8_bit_per_component = bw_frc_to_fixed(34286, 10000); - dceip.graphics_vscaler_efficiency10_bit_per_component = + dceip->graphics_vscaler_efficiency10_bit_per_component = bw_frc_to_fixed(32, 10); - dceip.graphics_vscaler_efficiency12_bit_per_component = + dceip->graphics_vscaler_efficiency12_bit_per_component = bw_int_to_fixed(3); - dceip.alpha_vscaler_efficiency = bw_int_to_fixed(3); - dceip.max_dmif_buffer_allocated = 2; - dceip.graphics_dmif_size = 12288; - dceip.underlay_luma_dmif_size = 19456; - dceip.underlay_chroma_dmif_size = 23552; - dceip.pre_downscaler_enabled = true; - dceip.underlay_downscale_prefetch_enabled = true; - dceip.lb_write_pixels_per_dispclk = bw_int_to_fixed(1); - dceip.lb_size_per_component444 = bw_int_to_fixed(82176); - dceip.graphics_lb_nodownscaling_multi_line_prefetching = false; - dceip.stutter_and_dram_clock_state_change_gated_before_cursor = + dceip->alpha_vscaler_efficiency = bw_int_to_fixed(3); + dceip->max_dmif_buffer_allocated = 2; + dceip->graphics_dmif_size = 12288; + dceip->underlay_luma_dmif_size = 19456; + dceip->underlay_chroma_dmif_size = 23552; + dceip->pre_downscaler_enabled = true; + dceip->underlay_downscale_prefetch_enabled = true; + dceip->lb_write_pixels_per_dispclk = bw_int_to_fixed(1); + dceip->lb_size_per_component444 = bw_int_to_fixed(82176); + dceip->graphics_lb_nodownscaling_multi_line_prefetching = false; + dceip->stutter_and_dram_clock_state_change_gated_before_cursor = bw_int_to_fixed(0); - dceip.underlay420_luma_lb_size_per_component = bw_int_to_fixed( + dceip->underlay420_luma_lb_size_per_component = bw_int_to_fixed( 82176); - dceip.underlay420_chroma_lb_size_per_component = + dceip->underlay420_chroma_lb_size_per_component = bw_int_to_fixed(164352); - dceip.underlay422_lb_size_per_component = bw_int_to_fixed( + dceip->underlay422_lb_size_per_component = bw_int_to_fixed( 82176); - dceip.cursor_chunk_width = bw_int_to_fixed(64); - dceip.cursor_dcp_buffer_lines = bw_int_to_fixed(4); - dceip.underlay_maximum_width_efficient_for_tiling = + dceip->cursor_chunk_width = bw_int_to_fixed(64); + dceip->cursor_dcp_buffer_lines = bw_int_to_fixed(4); + dceip->underlay_maximum_width_efficient_for_tiling = bw_int_to_fixed(1920); - dceip.underlay_maximum_height_efficient_for_tiling = + dceip->underlay_maximum_height_efficient_for_tiling = bw_int_to_fixed(1080); - dceip.peak_pte_request_to_eviction_ratio_limiting_multiple_displays_or_single_rotated_display = + dceip->peak_pte_request_to_eviction_ratio_limiting_multiple_displays_or_single_rotated_display = bw_frc_to_fixed(3, 10); - dceip.peak_pte_request_to_eviction_ratio_limiting_single_display_no_rotation = + dceip->peak_pte_request_to_eviction_ratio_limiting_single_display_no_rotation = bw_int_to_fixed(25); - dceip.minimum_outstanding_pte_request_limit = bw_int_to_fixed( + dceip->minimum_outstanding_pte_request_limit = bw_int_to_fixed( 2); - dceip.maximum_total_outstanding_pte_requests_allowed_by_saw = + dceip->maximum_total_outstanding_pte_requests_allowed_by_saw = bw_int_to_fixed(128); - dceip.limit_excessive_outstanding_dmif_requests = true; - dceip.linear_mode_line_request_alternation_slice = + dceip->limit_excessive_outstanding_dmif_requests = true; + dceip->linear_mode_line_request_alternation_slice = bw_int_to_fixed(64); - dceip.scatter_gather_lines_of_pte_prefetching_in_linear_mode = + dceip->scatter_gather_lines_of_pte_prefetching_in_linear_mode = 32; - dceip.display_write_back420_luma_mcifwr_buffer_size = 12288; - dceip.display_write_back420_chroma_mcifwr_buffer_size = 8192; - dceip.request_efficiency = bw_frc_to_fixed(8, 10); - dceip.dispclk_per_request = bw_int_to_fixed(2); - dceip.dispclk_ramping_factor = bw_frc_to_fixed(105, 100); - dceip.display_pipe_throughput_factor = bw_frc_to_fixed(105, 100); - dceip.scatter_gather_pte_request_rows_in_tiling_mode = 2; - dceip.mcifwr_all_surfaces_burst_time = bw_int_to_fixed(0); + dceip->display_write_back420_luma_mcifwr_buffer_size = 12288; + dceip->display_write_back420_chroma_mcifwr_buffer_size = 8192; + dceip->request_efficiency = bw_frc_to_fixed(8, 10); + dceip->dispclk_per_request = bw_int_to_fixed(2); + dceip->dispclk_ramping_factor = bw_frc_to_fixed(105, 100); + dceip->display_pipe_throughput_factor = bw_frc_to_fixed(105, 100); + dceip->scatter_gather_pte_request_rows_in_tiling_mode = 2; + dceip->mcifwr_all_surfaces_burst_time = bw_int_to_fixed(0); break; case BW_CALCS_VERSION_VEGA10: - vbios.memory_type = bw_def_hbm; - vbios.dram_channel_width_in_bits = 128; - vbios.number_of_dram_channels = asic_id.vram_width / vbios.dram_channel_width_in_bits; - vbios.number_of_dram_banks = 16; - vbios.high_yclk = bw_int_to_fixed(2400); - vbios.mid_yclk = bw_int_to_fixed(1700); - vbios.low_yclk = bw_int_to_fixed(1000); - vbios.low_sclk = bw_int_to_fixed(300); - vbios.mid1_sclk = bw_int_to_fixed(350); - vbios.mid2_sclk = bw_int_to_fixed(400); - vbios.mid3_sclk = bw_int_to_fixed(500); - vbios.mid4_sclk = bw_int_to_fixed(600); - vbios.mid5_sclk = bw_int_to_fixed(700); - vbios.mid6_sclk = bw_int_to_fixed(760); - vbios.high_sclk = bw_int_to_fixed(776); - vbios.low_voltage_max_dispclk = bw_int_to_fixed(460); - vbios.mid_voltage_max_dispclk = bw_int_to_fixed(670); - vbios.high_voltage_max_dispclk = bw_int_to_fixed(1133); - vbios.low_voltage_max_phyclk = bw_int_to_fixed(540); - vbios.mid_voltage_max_phyclk = bw_int_to_fixed(810); - vbios.high_voltage_max_phyclk = bw_int_to_fixed(810); - vbios.data_return_bus_width = bw_int_to_fixed(32); - vbios.trc = bw_int_to_fixed(48); - vbios.dmifmc_urgent_latency = bw_int_to_fixed(3); - vbios.stutter_self_refresh_exit_latency = bw_frc_to_fixed(75, 10); - vbios.stutter_self_refresh_entry_latency = bw_frc_to_fixed(19, 10); - vbios.nbp_state_change_latency = bw_int_to_fixed(39); - vbios.mcifwrmc_urgent_latency = bw_int_to_fixed(10); - vbios.scatter_gather_enable = false; - vbios.down_spread_percentage = bw_frc_to_fixed(5, 10); - vbios.cursor_width = 32; - vbios.average_compression_rate = 4; - vbios.number_of_request_slots_gmc_reserves_for_dmif_per_channel = 8; - vbios.blackout_duration = bw_int_to_fixed(0); /* us */ - vbios.maximum_blackout_recovery_time = bw_int_to_fixed(0); - - dceip.max_average_percent_of_ideal_port_bw_display_can_use_in_normal_system_operation = 100; - dceip.max_average_percent_of_ideal_drambw_display_can_use_in_normal_system_operation = 100; - dceip.percent_of_ideal_port_bw_received_after_urgent_latency = 100; - dceip.large_cursor = false; - dceip.dmif_request_buffer_size = bw_int_to_fixed(2304); - dceip.dmif_pipe_en_fbc_chunk_tracker = true; - dceip.cursor_max_outstanding_group_num = 1; - dceip.lines_interleaved_into_lb = 2; - dceip.chunk_width = 256; - dceip.number_of_graphics_pipes = 6; - dceip.number_of_underlay_pipes = 0; - dceip.low_power_tiling_mode = 0; - dceip.display_write_back_supported = true; - dceip.argb_compression_support = true; - dceip.underlay_vscaler_efficiency6_bit_per_component = + vbios->memory_type = bw_def_hbm; + vbios->dram_channel_width_in_bits = 128; + vbios->number_of_dram_channels = asic_id.vram_width / vbios->dram_channel_width_in_bits; + vbios->number_of_dram_banks = 16; + vbios->high_yclk = bw_int_to_fixed(2400); + vbios->mid_yclk = bw_int_to_fixed(1700); + vbios->low_yclk = bw_int_to_fixed(1000); + vbios->low_sclk = bw_int_to_fixed(300); + vbios->mid1_sclk = bw_int_to_fixed(350); + vbios->mid2_sclk = bw_int_to_fixed(400); + vbios->mid3_sclk = bw_int_to_fixed(500); + vbios->mid4_sclk = bw_int_to_fixed(600); + vbios->mid5_sclk = bw_int_to_fixed(700); + vbios->mid6_sclk = bw_int_to_fixed(760); + vbios->high_sclk = bw_int_to_fixed(776); + vbios->low_voltage_max_dispclk = bw_int_to_fixed(460); + vbios->mid_voltage_max_dispclk = bw_int_to_fixed(670); + vbios->high_voltage_max_dispclk = bw_int_to_fixed(1133); + vbios->low_voltage_max_phyclk = bw_int_to_fixed(540); + vbios->mid_voltage_max_phyclk = bw_int_to_fixed(810); + vbios->high_voltage_max_phyclk = bw_int_to_fixed(810); + vbios->data_return_bus_width = bw_int_to_fixed(32); + vbios->trc = bw_int_to_fixed(48); + vbios->dmifmc_urgent_latency = bw_int_to_fixed(3); + vbios->stutter_self_refresh_exit_latency = bw_frc_to_fixed(75, 10); + vbios->stutter_self_refresh_entry_latency = bw_frc_to_fixed(19, 10); + vbios->nbp_state_change_latency = bw_int_to_fixed(39); + vbios->mcifwrmc_urgent_latency = bw_int_to_fixed(10); + vbios->scatter_gather_enable = false; + vbios->down_spread_percentage = bw_frc_to_fixed(5, 10); + vbios->cursor_width = 32; + vbios->average_compression_rate = 4; + vbios->number_of_request_slots_gmc_reserves_for_dmif_per_channel = 8; + vbios->blackout_duration = bw_int_to_fixed(0); /* us */ + vbios->maximum_blackout_recovery_time = bw_int_to_fixed(0); + + dceip->max_average_percent_of_ideal_port_bw_display_can_use_in_normal_system_operation = 100; + dceip->max_average_percent_of_ideal_drambw_display_can_use_in_normal_system_operation = 100; + dceip->percent_of_ideal_port_bw_received_after_urgent_latency = 100; + dceip->large_cursor = false; + dceip->dmif_request_buffer_size = bw_int_to_fixed(2304); + dceip->dmif_pipe_en_fbc_chunk_tracker = true; + dceip->cursor_max_outstanding_group_num = 1; + dceip->lines_interleaved_into_lb = 2; + dceip->chunk_width = 256; + dceip->number_of_graphics_pipes = 6; + dceip->number_of_underlay_pipes = 0; + dceip->low_power_tiling_mode = 0; + dceip->display_write_back_supported = true; + dceip->argb_compression_support = true; + dceip->underlay_vscaler_efficiency6_bit_per_component = bw_frc_to_fixed(35556, 10000); - dceip.underlay_vscaler_efficiency8_bit_per_component = + dceip->underlay_vscaler_efficiency8_bit_per_component = bw_frc_to_fixed(34286, 10000); - dceip.underlay_vscaler_efficiency10_bit_per_component = + dceip->underlay_vscaler_efficiency10_bit_per_component = bw_frc_to_fixed(32, 10); - dceip.underlay_vscaler_efficiency12_bit_per_component = + dceip->underlay_vscaler_efficiency12_bit_per_component = bw_int_to_fixed(3); - dceip.graphics_vscaler_efficiency6_bit_per_component = + dceip->graphics_vscaler_efficiency6_bit_per_component = bw_frc_to_fixed(35, 10); - dceip.graphics_vscaler_efficiency8_bit_per_component = + dceip->graphics_vscaler_efficiency8_bit_per_component = bw_frc_to_fixed(34286, 10000); - dceip.graphics_vscaler_efficiency10_bit_per_component = + dceip->graphics_vscaler_efficiency10_bit_per_component = bw_frc_to_fixed(32, 10); - dceip.graphics_vscaler_efficiency12_bit_per_component = + dceip->graphics_vscaler_efficiency12_bit_per_component = bw_int_to_fixed(3); - dceip.alpha_vscaler_efficiency = bw_int_to_fixed(3); - dceip.max_dmif_buffer_allocated = 4; - dceip.graphics_dmif_size = 24576; - dceip.underlay_luma_dmif_size = 19456; - dceip.underlay_chroma_dmif_size = 23552; - dceip.pre_downscaler_enabled = true; - dceip.underlay_downscale_prefetch_enabled = false; - dceip.lb_write_pixels_per_dispclk = bw_int_to_fixed(1); - dceip.lb_size_per_component444 = bw_int_to_fixed(245952); - dceip.graphics_lb_nodownscaling_multi_line_prefetching = true; - dceip.stutter_and_dram_clock_state_change_gated_before_cursor = + dceip->alpha_vscaler_efficiency = bw_int_to_fixed(3); + dceip->max_dmif_buffer_allocated = 4; + dceip->graphics_dmif_size = 24576; + dceip->underlay_luma_dmif_size = 19456; + dceip->underlay_chroma_dmif_size = 23552; + dceip->pre_downscaler_enabled = true; + dceip->underlay_downscale_prefetch_enabled = false; + dceip->lb_write_pixels_per_dispclk = bw_int_to_fixed(1); + dceip->lb_size_per_component444 = bw_int_to_fixed(245952); + dceip->graphics_lb_nodownscaling_multi_line_prefetching = true; + dceip->stutter_and_dram_clock_state_change_gated_before_cursor = bw_int_to_fixed(1); - dceip.underlay420_luma_lb_size_per_component = bw_int_to_fixed( + dceip->underlay420_luma_lb_size_per_component = bw_int_to_fixed( 82176); - dceip.underlay420_chroma_lb_size_per_component = + dceip->underlay420_chroma_lb_size_per_component = bw_int_to_fixed(164352); - dceip.underlay422_lb_size_per_component = bw_int_to_fixed( + dceip->underlay422_lb_size_per_component = bw_int_to_fixed( 82176); - dceip.cursor_chunk_width = bw_int_to_fixed(64); - dceip.cursor_dcp_buffer_lines = bw_int_to_fixed(4); - dceip.underlay_maximum_width_efficient_for_tiling = + dceip->cursor_chunk_width = bw_int_to_fixed(64); + dceip->cursor_dcp_buffer_lines = bw_int_to_fixed(4); + dceip->underlay_maximum_width_efficient_for_tiling = bw_int_to_fixed(1920); - dceip.underlay_maximum_height_efficient_for_tiling = + dceip->underlay_maximum_height_efficient_for_tiling = bw_int_to_fixed(1080); - dceip.peak_pte_request_to_eviction_ratio_limiting_multiple_displays_or_single_rotated_display = + dceip->peak_pte_request_to_eviction_ratio_limiting_multiple_displays_or_single_rotated_display = bw_frc_to_fixed(3, 10); - dceip.peak_pte_request_to_eviction_ratio_limiting_single_display_no_rotation = + dceip->peak_pte_request_to_eviction_ratio_limiting_single_display_no_rotation = bw_int_to_fixed(25); - dceip.minimum_outstanding_pte_request_limit = bw_int_to_fixed( + dceip->minimum_outstanding_pte_request_limit = bw_int_to_fixed( 2); - dceip.maximum_total_outstanding_pte_requests_allowed_by_saw = + dceip->maximum_total_outstanding_pte_requests_allowed_by_saw = bw_int_to_fixed(128); - dceip.limit_excessive_outstanding_dmif_requests = true; - dceip.linear_mode_line_request_alternation_slice = + dceip->limit_excessive_outstanding_dmif_requests = true; + dceip->linear_mode_line_request_alternation_slice = bw_int_to_fixed(64); - dceip.scatter_gather_lines_of_pte_prefetching_in_linear_mode = + dceip->scatter_gather_lines_of_pte_prefetching_in_linear_mode = 32; - dceip.display_write_back420_luma_mcifwr_buffer_size = 12288; - dceip.display_write_back420_chroma_mcifwr_buffer_size = 8192; - dceip.request_efficiency = bw_frc_to_fixed(8, 10); - dceip.dispclk_per_request = bw_int_to_fixed(2); - dceip.dispclk_ramping_factor = bw_frc_to_fixed(105, 100); - dceip.display_pipe_throughput_factor = bw_frc_to_fixed(105, 100); - dceip.scatter_gather_pte_request_rows_in_tiling_mode = 2; - dceip.mcifwr_all_surfaces_burst_time = bw_int_to_fixed(0); + dceip->display_write_back420_luma_mcifwr_buffer_size = 12288; + dceip->display_write_back420_chroma_mcifwr_buffer_size = 8192; + dceip->request_efficiency = bw_frc_to_fixed(8, 10); + dceip->dispclk_per_request = bw_int_to_fixed(2); + dceip->dispclk_ramping_factor = bw_frc_to_fixed(105, 100); + dceip->display_pipe_throughput_factor = bw_frc_to_fixed(105, 100); + dceip->scatter_gather_pte_request_rows_in_tiling_mode = 2; + dceip->mcifwr_all_surfaces_burst_time = bw_int_to_fixed(0); break; default: break; } - *bw_dceip = dceip; - *bw_vbios = vbios; + *bw_dceip = *dceip; + *bw_vbios = *vbios; + kfree(dceip); + kfree(vbios); } /* diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/clk_mgr.c index f7c728d4f50a..7d6c68c5dea9 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/clk_mgr.c @@ -125,87 +125,136 @@ struct clk_mgr *dc_clk_mgr_create(struct dc_context *ctx, struct pp_smu_funcs *p { struct hw_asic_id asic_id = ctx->asic_id; - struct clk_mgr_internal *clk_mgr = kzalloc(sizeof(*clk_mgr), GFP_KERNEL); - - if (clk_mgr == NULL) { - BREAK_TO_DEBUGGER(); - return NULL; - } - switch (asic_id.chip_family) { #if defined(CONFIG_DRM_AMD_DC_SI) - case FAMILY_SI: + case FAMILY_SI: { + struct clk_mgr_internal *clk_mgr = kzalloc(sizeof(*clk_mgr), GFP_KERNEL); + + if (clk_mgr == NULL) { + BREAK_TO_DEBUGGER(); + return NULL; + } dce60_clk_mgr_construct(ctx, clk_mgr); - break; + dce_clk_mgr_construct(ctx, clk_mgr); + return &clk_mgr->base; + } #endif case FAMILY_CI: - case FAMILY_KV: + case FAMILY_KV: { + struct clk_mgr_internal *clk_mgr = kzalloc(sizeof(*clk_mgr), GFP_KERNEL); + + if (clk_mgr == NULL) { + BREAK_TO_DEBUGGER(); + return NULL; + } dce_clk_mgr_construct(ctx, clk_mgr); - break; - case FAMILY_CZ: + return &clk_mgr->base; + } + case FAMILY_CZ: { + struct clk_mgr_internal *clk_mgr = kzalloc(sizeof(*clk_mgr), GFP_KERNEL); + + if (clk_mgr == NULL) { + BREAK_TO_DEBUGGER(); + return NULL; + } dce110_clk_mgr_construct(ctx, clk_mgr); - break; - case FAMILY_VI: + return &clk_mgr->base; + } + case FAMILY_VI: { + struct clk_mgr_internal *clk_mgr = kzalloc(sizeof(*clk_mgr), GFP_KERNEL); + + if (clk_mgr == NULL) { + BREAK_TO_DEBUGGER(); + return NULL; + } if (ASIC_REV_IS_TONGA_P(asic_id.hw_internal_rev) || ASIC_REV_IS_FIJI_P(asic_id.hw_internal_rev)) { dce_clk_mgr_construct(ctx, clk_mgr); - break; + return &clk_mgr->base; } if (ASIC_REV_IS_POLARIS10_P(asic_id.hw_internal_rev) || ASIC_REV_IS_POLARIS11_M(asic_id.hw_internal_rev) || ASIC_REV_IS_POLARIS12_V(asic_id.hw_internal_rev)) { dce112_clk_mgr_construct(ctx, clk_mgr); - break; + return &clk_mgr->base; } if (ASIC_REV_IS_VEGAM(asic_id.hw_internal_rev)) { dce112_clk_mgr_construct(ctx, clk_mgr); - break; + return &clk_mgr->base; + } + return &clk_mgr->base; + } + case FAMILY_AI: { + struct clk_mgr_internal *clk_mgr = kzalloc(sizeof(*clk_mgr), GFP_KERNEL); + + if (clk_mgr == NULL) { + BREAK_TO_DEBUGGER(); + return NULL; } - break; - case FAMILY_AI: if (ASICREV_IS_VEGA20_P(asic_id.hw_internal_rev)) dce121_clk_mgr_construct(ctx, clk_mgr); else dce120_clk_mgr_construct(ctx, clk_mgr); - break; - + return &clk_mgr->base; + } #if defined(CONFIG_DRM_AMD_DC_DCN) - case FAMILY_RV: + case FAMILY_RV: { + struct clk_mgr_internal *clk_mgr = kzalloc(sizeof(*clk_mgr), GFP_KERNEL); + + if (clk_mgr == NULL) { + BREAK_TO_DEBUGGER(); + return NULL; + } + if (ASICREV_IS_RENOIR(asic_id.hw_internal_rev)) { rn_clk_mgr_construct(ctx, clk_mgr, pp_smu, dccg); - break; + return &clk_mgr->base; } if (ASICREV_IS_GREEN_SARDINE(asic_id.hw_internal_rev)) { rn_clk_mgr_construct(ctx, clk_mgr, pp_smu, dccg); - break; + return &clk_mgr->base; } if (ASICREV_IS_RAVEN2(asic_id.hw_internal_rev)) { rv2_clk_mgr_construct(ctx, clk_mgr, pp_smu); - break; + return &clk_mgr->base; } if (ASICREV_IS_RAVEN(asic_id.hw_internal_rev) || ASICREV_IS_PICASSO(asic_id.hw_internal_rev)) { rv1_clk_mgr_construct(ctx, clk_mgr, pp_smu); - break; + return &clk_mgr->base; } - break; + return &clk_mgr->base; + } + case FAMILY_NV: { + struct clk_mgr_internal *clk_mgr = kzalloc(sizeof(*clk_mgr), GFP_KERNEL); - case FAMILY_NV: + if (clk_mgr == NULL) { + BREAK_TO_DEBUGGER(); + return NULL; + } if (ASICREV_IS_SIENNA_CICHLID_P(asic_id.hw_internal_rev)) { dcn3_clk_mgr_construct(ctx, clk_mgr, pp_smu, dccg); - break; + return &clk_mgr->base; } if (ASICREV_IS_DIMGREY_CAVEFISH_P(asic_id.hw_internal_rev)) { dcn3_clk_mgr_construct(ctx, clk_mgr, pp_smu, dccg); - break; + return &clk_mgr->base; } dcn20_clk_mgr_construct(ctx, clk_mgr, pp_smu, dccg); - break; - + return &clk_mgr->base; + } case FAMILY_VGH: - if (ASICREV_IS_VANGOGH(asic_id.hw_internal_rev)) + if (ASICREV_IS_VANGOGH(asic_id.hw_internal_rev)) { + struct clk_mgr_vgh *clk_mgr = kzalloc(sizeof(*clk_mgr), GFP_KERNEL); + + if (clk_mgr == NULL) { + BREAK_TO_DEBUGGER(); + return NULL; + } vg_clk_mgr_construct(ctx, clk_mgr, pp_smu, dccg); + return &clk_mgr->base.base; + } break; #endif default: @@ -213,7 +262,7 @@ struct clk_mgr *dc_clk_mgr_create(struct dc_context *ctx, struct pp_smu_funcs *p break; } - return &clk_mgr->base; + return NULL; } void dc_destroy_clk_mgr(struct clk_mgr *clk_mgr_base) @@ -226,6 +275,9 @@ void dc_destroy_clk_mgr(struct clk_mgr *clk_mgr_base) if (ASICREV_IS_SIENNA_CICHLID_P(clk_mgr_base->ctx->asic_id.hw_internal_rev)) { dcn3_clk_mgr_destroy(clk_mgr); } + if (ASICREV_IS_DIMGREY_CAVEFISH_P(clk_mgr_base->ctx->asic_id.hw_internal_rev)) { + dcn3_clk_mgr_destroy(clk_mgr); + } break; case FAMILY_VGH: diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c index 01b1853b7750..a06e86853bb9 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c @@ -128,7 +128,7 @@ void rn_update_clocks(struct clk_mgr *clk_mgr_base, struct clk_mgr_internal *clk_mgr = TO_CLK_MGR_INTERNAL(clk_mgr_base); struct dc_clocks *new_clocks = &context->bw_ctx.bw.dcn.clk; struct dc *dc = clk_mgr_base->ctx->dc; - int display_count; + int display_count, i; bool update_dppclk = false; bool update_dispclk = false; bool dpp_clock_lowered = false; @@ -210,6 +210,14 @@ void rn_update_clocks(struct clk_mgr *clk_mgr_base, clk_mgr_base->clks.dppclk_khz, safe_to_lower); + for (i = 0; i < context->stream_count; i++) { + if (context->streams[i]->signal == SIGNAL_TYPE_EDP && + context->streams[i]->apply_seamless_boot_optimization) { + dc_wait_for_vblank(dc, context->streams[i]); + break; + } + } + clk_mgr_base->clks.actual_dppclk_khz = rn_vbios_smu_set_dppclk(clk_mgr, clk_mgr_base->clks.dppclk_khz); @@ -761,6 +769,43 @@ static struct wm_table ddr4_wm_table_rn = { } }; +static struct wm_table ddr4_1R_wm_table_rn = { + .entries = { + { + .wm_inst = WM_A, + .wm_type = WM_TYPE_PSTATE_CHG, + .pstate_latency_us = 11.72, + .sr_exit_time_us = 13.90, + .sr_enter_plus_exit_time_us = 14.80, + .valid = true, + }, + { + .wm_inst = WM_B, + .wm_type = WM_TYPE_PSTATE_CHG, + .pstate_latency_us = 11.72, + .sr_exit_time_us = 13.90, + .sr_enter_plus_exit_time_us = 14.80, + .valid = true, + }, + { + .wm_inst = WM_C, + .wm_type = WM_TYPE_PSTATE_CHG, + .pstate_latency_us = 11.72, + .sr_exit_time_us = 13.90, + .sr_enter_plus_exit_time_us = 14.80, + .valid = true, + }, + { + .wm_inst = WM_D, + .wm_type = WM_TYPE_PSTATE_CHG, + .pstate_latency_us = 11.72, + .sr_exit_time_us = 13.90, + .sr_enter_plus_exit_time_us = 14.80, + .valid = true, + }, + } +}; + static struct wm_table lpddr4_wm_table_rn = { .entries = { { @@ -797,7 +842,18 @@ static struct wm_table lpddr4_wm_table_rn = { }, } }; +static unsigned int find_socclk_for_voltage(struct dpm_clocks *clock_table, unsigned int voltage) +{ + int i; + for (i = 0; i < PP_SMU_NUM_SOCCLK_DPM_LEVELS; i++) { + if (clock_table->SocClocks[i].Vol == voltage) + return clock_table->SocClocks[i].Freq; + } + + ASSERT(0); + return 0; +} static unsigned int find_dcfclk_for_voltage(struct dpm_clocks *clock_table, unsigned int voltage) { int i; @@ -841,6 +897,8 @@ static void rn_clk_mgr_helper_populate_bw_params(struct clk_bw_params *bw_params bw_params->clk_table.entries[i].memclk_mhz = clock_table->MemClocks[j].Freq; bw_params->clk_table.entries[i].voltage = clock_table->FClocks[j].Vol; bw_params->clk_table.entries[i].dcfclk_mhz = find_dcfclk_for_voltage(clock_table, clock_table->FClocks[j].Vol); + bw_params->clk_table.entries[i].socclk_mhz = find_socclk_for_voltage(clock_table, + bw_params->clk_table.entries[i].voltage); } bw_params->vram_type = bios_info->memory_type; @@ -932,8 +990,12 @@ void rn_clk_mgr_construct( } else { if (is_green_sardine) rn_bw_params.wm_table = ddr4_wm_table_gs; - else - rn_bw_params.wm_table = ddr4_wm_table_rn; + else { + if (ctx->dc->config.is_single_rank_dimm) + rn_bw_params.wm_table = ddr4_1R_wm_table_rn; + else + rn_bw_params.wm_table = ddr4_wm_table_rn; + } } /* Saved clocks configured at boot for debug purposes */ rn_dump_clk_registers(&clk_mgr->base.boot_snapshot, &clk_mgr->base, &log_info); @@ -951,6 +1013,9 @@ void rn_clk_mgr_construct( if (status == PP_SMU_RESULT_OK && ctx->dc_bios && ctx->dc_bios->integrated_info) { rn_clk_mgr_helper_populate_bw_params (clk_mgr->base.bw_params, &clock_table, ctx->dc_bios->integrated_info); + /* treat memory config as single channel if memory is asymmetrics. */ + if (ctx->dc->config.is_asymmetric_memory) + clk_mgr->base.bw_params->num_channels = 1; } } diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn30/dcn30_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn30/dcn30_clk_mgr.c index 81ea5d3a1947..652fa89fae5f 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn30/dcn30_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn30/dcn30_clk_mgr.c @@ -432,6 +432,12 @@ static void dcn3_get_memclk_states_from_smu(struct clk_mgr *clk_mgr_base) clk_mgr->base.ctx->dc, clk_mgr_base->bw_params); } +static bool dcn3_is_smu_present(struct clk_mgr *clk_mgr_base) +{ + struct clk_mgr_internal *clk_mgr = TO_CLK_MGR_INTERNAL(clk_mgr_base); + return clk_mgr->smu_present; +} + static bool dcn3_are_clock_states_equal(struct dc_clocks *a, struct dc_clocks *b) { @@ -494,6 +500,7 @@ static struct clk_mgr_funcs dcn3_funcs = { .are_clock_states_equal = dcn3_are_clock_states_equal, .enable_pme_wa = dcn3_enable_pme_wa, .notify_link_rate_change = dcn30_notify_link_rate_change, + .is_smu_present = dcn3_is_smu_present }; static void dcn3_init_clocks_fpga(struct clk_mgr *clk_mgr) diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn301/dcn301_smu.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn301/dcn301_smu.c index 68942bbc7472..07774fa2c2cf 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn301/dcn301_smu.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn301/dcn301_smu.c @@ -113,10 +113,13 @@ int dcn301_smu_send_msg_with_param( int dcn301_smu_get_smu_version(struct clk_mgr_internal *clk_mgr) { - return dcn301_smu_send_msg_with_param( - clk_mgr, - VBIOSSMC_MSG_GetSmuVersion, - 0); + int smu_version = dcn301_smu_send_msg_with_param(clk_mgr, + VBIOSSMC_MSG_GetSmuVersion, + 0); + + DC_LOG_DEBUG("%s %x\n", __func__, smu_version); + + return smu_version; } @@ -124,6 +127,8 @@ int dcn301_smu_set_dispclk(struct clk_mgr_internal *clk_mgr, int requested_dispc { int actual_dispclk_set_mhz = -1; + DC_LOG_DEBUG("%s(%d)\n", __func__, requested_dispclk_khz); + /* Unit of SMU msg parameter is Mhz */ actual_dispclk_set_mhz = dcn301_smu_send_msg_with_param( clk_mgr, @@ -137,6 +142,8 @@ int dcn301_smu_set_dprefclk(struct clk_mgr_internal *clk_mgr) { int actual_dprefclk_set_mhz = -1; + DC_LOG_DEBUG("%s %d\n", __func__, clk_mgr->base.dprefclk_khz / 1000); + actual_dprefclk_set_mhz = dcn301_smu_send_msg_with_param( clk_mgr, VBIOSSMC_MSG_SetDprefclkFreq, @@ -151,6 +158,8 @@ int dcn301_smu_set_hard_min_dcfclk(struct clk_mgr_internal *clk_mgr, int request { int actual_dcfclk_set_mhz = -1; + DC_LOG_DEBUG("%s(%d)\n", __func__, requested_dcfclk_khz); + actual_dcfclk_set_mhz = dcn301_smu_send_msg_with_param( clk_mgr, VBIOSSMC_MSG_SetHardMinDcfclkByFreq, @@ -163,6 +172,8 @@ int dcn301_smu_set_min_deep_sleep_dcfclk(struct clk_mgr_internal *clk_mgr, int r { int actual_min_ds_dcfclk_mhz = -1; + DC_LOG_DEBUG("%s(%d)\n", __func__, requested_min_ds_dcfclk_khz); + actual_min_ds_dcfclk_mhz = dcn301_smu_send_msg_with_param( clk_mgr, VBIOSSMC_MSG_SetMinDeepSleepDcfclk, @@ -175,6 +186,8 @@ int dcn301_smu_set_dppclk(struct clk_mgr_internal *clk_mgr, int requested_dpp_kh { int actual_dppclk_set_mhz = -1; + DC_LOG_DEBUG("%s(%d)\n", __func__, requested_dpp_khz); + actual_dppclk_set_mhz = dcn301_smu_send_msg_with_param( clk_mgr, VBIOSSMC_MSG_SetDppclkFreq, @@ -187,6 +200,8 @@ void dcn301_smu_set_display_idle_optimization(struct clk_mgr_internal *clk_mgr, { //TODO: Work with smu team to define optimization options. + DC_LOG_DEBUG("%s(%x)\n", __func__, idle_info); + dcn301_smu_send_msg_with_param( clk_mgr, VBIOSSMC_MSG_SetDisplayIdleOptimizations, @@ -202,6 +217,8 @@ void dcn301_smu_enable_phy_refclk_pwrdwn(struct clk_mgr_internal *clk_mgr, bool idle_info.idle_info.phy_ref_clk_off = 1; } + DC_LOG_DEBUG("%s(%d)\n", __func__, enable); + dcn301_smu_send_msg_with_param( clk_mgr, VBIOSSMC_MSG_SetDisplayIdleOptimizations, @@ -218,12 +235,16 @@ void dcn301_smu_enable_pme_wa(struct clk_mgr_internal *clk_mgr) void dcn301_smu_set_dram_addr_high(struct clk_mgr_internal *clk_mgr, uint32_t addr_high) { + DC_LOG_DEBUG("%s(%x)\n", __func__, addr_high); + dcn301_smu_send_msg_with_param(clk_mgr, VBIOSSMC_MSG_SetVbiosDramAddrHigh, addr_high); } void dcn301_smu_set_dram_addr_low(struct clk_mgr_internal *clk_mgr, uint32_t addr_low) { + DC_LOG_DEBUG("%s(%x)\n", __func__, addr_low); + dcn301_smu_send_msg_with_param(clk_mgr, VBIOSSMC_MSG_SetVbiosDramAddrLow, addr_low); } diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn301/vg_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn301/vg_clk_mgr.c index aadb801447a7..c636b589d69d 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn301/vg_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn301/vg_clk_mgr.c @@ -32,9 +32,8 @@ // For dcn20_update_clocks_update_dpp_dto #include "dcn20/dcn20_clk_mgr.h" - - #include "vg_clk_mgr.h" +#include "dcn301_smu.h" #include "reg_helper.h" #include "core_types.h" #include "dm_helpers.h" @@ -50,11 +49,14 @@ /* Macros */ +#define TO_CLK_MGR_VGH(clk_mgr)\ + container_of(clk_mgr, struct clk_mgr_vgh, base) + #define REG(reg_name) \ (CLK_BASE.instance[0].segment[mm ## reg_name ## _BASE_IDX] + mm ## reg_name) /* TODO: evaluate how to lower or disable all dcn clocks in screen off case */ -int vg_get_active_display_cnt_wa( +static int vg_get_active_display_cnt_wa( struct dc *dc, struct dc_state *context) { @@ -134,13 +136,13 @@ void vg_update_clocks(struct clk_mgr *clk_mgr_base, } } - if (should_set_clock(safe_to_lower, new_clocks->dcfclk_khz, clk_mgr_base->clks.dcfclk_khz)) { + if (should_set_clock(safe_to_lower, new_clocks->dcfclk_khz, clk_mgr_base->clks.dcfclk_khz) && !dc->debug.disable_min_fclk) { clk_mgr_base->clks.dcfclk_khz = new_clocks->dcfclk_khz; dcn301_smu_set_hard_min_dcfclk(clk_mgr, clk_mgr_base->clks.dcfclk_khz); } if (should_set_clock(safe_to_lower, - new_clocks->dcfclk_deep_sleep_khz, clk_mgr_base->clks.dcfclk_deep_sleep_khz)) { + new_clocks->dcfclk_deep_sleep_khz, clk_mgr_base->clks.dcfclk_deep_sleep_khz) && !dc->debug.disable_min_fclk) { clk_mgr_base->clks.dcfclk_deep_sleep_khz = new_clocks->dcfclk_deep_sleep_khz; dcn301_smu_set_min_deep_sleep_dcfclk(clk_mgr, clk_mgr_base->clks.dcfclk_deep_sleep_khz); } @@ -377,7 +379,7 @@ void vg_get_clk_states(struct clk_mgr *clk_mgr_base, struct clk_states *s) s->dprefclk_khz = sb.dprefclk * 1000; } -void vg_enable_pme_wa(struct clk_mgr *clk_mgr_base) +static void vg_enable_pme_wa(struct clk_mgr *clk_mgr_base) { struct clk_mgr_internal *clk_mgr = TO_CLK_MGR_INTERNAL(clk_mgr_base); @@ -449,15 +451,16 @@ static void vg_build_watermark_ranges(struct clk_bw_params *bw_params, struct wa } -void vg_notify_wm_ranges(struct clk_mgr *clk_mgr_base) +static void vg_notify_wm_ranges(struct clk_mgr *clk_mgr_base) { struct clk_mgr_internal *clk_mgr = TO_CLK_MGR_INTERNAL(clk_mgr_base); - struct watermarks *table = clk_mgr_base->smu_wm_set.wm_set; + struct clk_mgr_vgh *clk_mgr_vgh = TO_CLK_MGR_VGH(clk_mgr); + struct watermarks *table = clk_mgr_vgh->smu_wm_set.wm_set; if (!clk_mgr->smu_ver) return; - if (!table || clk_mgr_base->smu_wm_set.mc_address.quad_part == 0) + if (!table || clk_mgr_vgh->smu_wm_set.mc_address.quad_part == 0) return; memset(table, 0, sizeof(*table)); @@ -465,9 +468,9 @@ void vg_notify_wm_ranges(struct clk_mgr *clk_mgr_base) vg_build_watermark_ranges(clk_mgr_base->bw_params, table); dcn301_smu_set_dram_addr_high(clk_mgr, - clk_mgr_base->smu_wm_set.mc_address.high_part); + clk_mgr_vgh->smu_wm_set.mc_address.high_part); dcn301_smu_set_dram_addr_low(clk_mgr, - clk_mgr_base->smu_wm_set.mc_address.low_part); + clk_mgr_vgh->smu_wm_set.mc_address.low_part); dcn301_smu_transfer_wm_table_dram_2_smu(clk_mgr); } @@ -625,7 +628,7 @@ static unsigned int find_dcfclk_for_voltage(const struct vg_dpm_clocks *clock_ta return 0; } -void vg_clk_mgr_helper_populate_bw_params( +static void vg_clk_mgr_helper_populate_bw_params( struct clk_mgr_internal *clk_mgr, struct integrated_info *bios_info, const struct vg_dpm_clocks *clock_table) @@ -703,7 +706,7 @@ static struct vg_dpm_clocks dummy_clocks = { static struct watermarks dummy_wms = { 0 }; -void vg_get_dpm_table_from_smu(struct clk_mgr_internal *clk_mgr, +static void vg_get_dpm_table_from_smu(struct clk_mgr_internal *clk_mgr, struct smu_dpm_clks *smu_dpm_clks) { struct vg_dpm_clocks *table = smu_dpm_clks->dpm_clks; @@ -725,39 +728,39 @@ void vg_get_dpm_table_from_smu(struct clk_mgr_internal *clk_mgr, void vg_clk_mgr_construct( struct dc_context *ctx, - struct clk_mgr_internal *clk_mgr, + struct clk_mgr_vgh *clk_mgr, struct pp_smu_funcs *pp_smu, struct dccg *dccg) { struct smu_dpm_clks smu_dpm_clks = { 0 }; - clk_mgr->base.ctx = ctx; - clk_mgr->base.funcs = &vg_funcs; + clk_mgr->base.base.ctx = ctx; + clk_mgr->base.base.funcs = &vg_funcs; - clk_mgr->pp_smu = pp_smu; + clk_mgr->base.pp_smu = pp_smu; - clk_mgr->dccg = dccg; - clk_mgr->dfs_bypass_disp_clk = 0; + clk_mgr->base.dccg = dccg; + clk_mgr->base.dfs_bypass_disp_clk = 0; - clk_mgr->dprefclk_ss_percentage = 0; - clk_mgr->dprefclk_ss_divider = 1000; - clk_mgr->ss_on_dprefclk = false; - clk_mgr->dfs_ref_freq_khz = 48000; + clk_mgr->base.dprefclk_ss_percentage = 0; + clk_mgr->base.dprefclk_ss_divider = 1000; + clk_mgr->base.ss_on_dprefclk = false; + clk_mgr->base.dfs_ref_freq_khz = 48000; - clk_mgr->base.smu_wm_set.wm_set = (struct watermarks *)dm_helpers_allocate_gpu_mem( - clk_mgr->base.ctx, + clk_mgr->smu_wm_set.wm_set = (struct watermarks *)dm_helpers_allocate_gpu_mem( + clk_mgr->base.base.ctx, DC_MEM_ALLOC_TYPE_FRAME_BUFFER, sizeof(struct watermarks), - &clk_mgr->base.smu_wm_set.mc_address.quad_part); + &clk_mgr->smu_wm_set.mc_address.quad_part); - if (clk_mgr->base.smu_wm_set.wm_set == 0) { - clk_mgr->base.smu_wm_set.wm_set = &dummy_wms; - clk_mgr->base.smu_wm_set.mc_address.quad_part = 0; + if (clk_mgr->smu_wm_set.wm_set == 0) { + clk_mgr->smu_wm_set.wm_set = &dummy_wms; + clk_mgr->smu_wm_set.mc_address.quad_part = 0; } - ASSERT(clk_mgr->base.smu_wm_set.wm_set); + ASSERT(clk_mgr->smu_wm_set.wm_set); smu_dpm_clks.dpm_clks = (struct vg_dpm_clocks *)dm_helpers_allocate_gpu_mem( - clk_mgr->base.ctx, + clk_mgr->base.base.ctx, DC_MEM_ALLOC_TYPE_FRAME_BUFFER, sizeof(struct vg_dpm_clocks), &smu_dpm_clks.mc_address.quad_part); @@ -771,21 +774,21 @@ void vg_clk_mgr_construct( if (IS_FPGA_MAXIMUS_DC(ctx->dce_environment)) { vg_funcs.update_clocks = dcn2_update_clocks_fpga; - clk_mgr->base.dentist_vco_freq_khz = 3600000; + clk_mgr->base.base.dentist_vco_freq_khz = 3600000; } else { struct clk_log_info log_info = {0}; - clk_mgr->smu_ver = dcn301_smu_get_smu_version(clk_mgr); + clk_mgr->base.smu_ver = dcn301_smu_get_smu_version(&clk_mgr->base); - if (clk_mgr->smu_ver) - clk_mgr->smu_present = true; + if (clk_mgr->base.smu_ver) + clk_mgr->base.smu_present = true; /* TODO: Check we get what we expect during bringup */ - clk_mgr->base.dentist_vco_freq_khz = get_vco_frequency_from_reg(clk_mgr); + clk_mgr->base.base.dentist_vco_freq_khz = get_vco_frequency_from_reg(&clk_mgr->base); /* in case we don't get a value from the register, use default */ - if (clk_mgr->base.dentist_vco_freq_khz == 0) - clk_mgr->base.dentist_vco_freq_khz = 3600000; + if (clk_mgr->base.base.dentist_vco_freq_khz == 0) + clk_mgr->base.base.dentist_vco_freq_khz = 3600000; if (ctx->dc_bios->integrated_info->memory_type == LpDdr5MemType) { vg_bw_params.wm_table = lpddr5_wm_table; @@ -793,36 +796,38 @@ void vg_clk_mgr_construct( vg_bw_params.wm_table = ddr4_wm_table; } /* Saved clocks configured at boot for debug purposes */ - vg_dump_clk_registers(&clk_mgr->base.boot_snapshot, &clk_mgr->base, &log_info); + vg_dump_clk_registers(&clk_mgr->base.base.boot_snapshot, &clk_mgr->base.base, &log_info); } - clk_mgr->base.dprefclk_khz = 600000; - dce_clock_read_ss_info(clk_mgr); + clk_mgr->base.base.dprefclk_khz = 600000; + dce_clock_read_ss_info(&clk_mgr->base); - clk_mgr->base.bw_params = &vg_bw_params; + clk_mgr->base.base.bw_params = &vg_bw_params; - vg_get_dpm_table_from_smu(clk_mgr, &smu_dpm_clks); + vg_get_dpm_table_from_smu(&clk_mgr->base, &smu_dpm_clks); if (ctx->dc_bios && ctx->dc_bios->integrated_info) { vg_clk_mgr_helper_populate_bw_params( - clk_mgr, + &clk_mgr->base, ctx->dc_bios->integrated_info, smu_dpm_clks.dpm_clks); } if (smu_dpm_clks.dpm_clks && smu_dpm_clks.mc_address.quad_part != 0) - dm_helpers_free_gpu_mem(clk_mgr->base.ctx, DC_MEM_ALLOC_TYPE_FRAME_BUFFER, + dm_helpers_free_gpu_mem(clk_mgr->base.base.ctx, DC_MEM_ALLOC_TYPE_FRAME_BUFFER, smu_dpm_clks.dpm_clks); /* - if (!IS_FPGA_MAXIMUS_DC(ctx->dce_environment) && clk_mgr->smu_ver) { + if (!IS_FPGA_MAXIMUS_DC(ctx->dce_environment) && clk_mgr->base.smu_ver) { enable powerfeatures when displaycount goes to 0 dcn301_smu_enable_phy_refclk_pwrdwn(clk_mgr, !debug->disable_48mhz_pwrdwn); } */ } -void vg_clk_mgr_destroy(struct clk_mgr_internal *clk_mgr) +void vg_clk_mgr_destroy(struct clk_mgr_internal *clk_mgr_int) { - if (clk_mgr->base.smu_wm_set.wm_set && clk_mgr->base.smu_wm_set.mc_address.quad_part != 0) - dm_helpers_free_gpu_mem(clk_mgr->base.ctx, DC_MEM_ALLOC_TYPE_FRAME_BUFFER, - clk_mgr->base.smu_wm_set.wm_set); + struct clk_mgr_vgh *clk_mgr = TO_CLK_MGR_VGH(clk_mgr_int); + + if (clk_mgr->smu_wm_set.wm_set && clk_mgr->smu_wm_set.mc_address.quad_part != 0) + dm_helpers_free_gpu_mem(clk_mgr_int->base.ctx, DC_MEM_ALLOC_TYPE_FRAME_BUFFER, + clk_mgr->smu_wm_set.wm_set); } diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn301/vg_clk_mgr.h b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn301/vg_clk_mgr.h index b5115b3123a1..7255477307f1 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn301/vg_clk_mgr.h +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn301/vg_clk_mgr.h @@ -25,29 +25,25 @@ #ifndef __VG_CLK_MGR_H__ #define __VG_CLK_MGR_H__ +#include "clk_mgr_internal.h" -int vg_get_active_display_cnt_wa( - struct dc *dc, - struct dc_state *context); +struct watermarks; -void vg_enable_pme_wa(struct clk_mgr *clk_mgr_base); +struct smu_watermark_set { + struct watermarks *wm_set; + union large_integer mc_address; +}; + +struct clk_mgr_vgh { + struct clk_mgr_internal base; + struct smu_watermark_set smu_wm_set; +}; void vg_clk_mgr_construct(struct dc_context *ctx, - struct clk_mgr_internal *clk_mgr, + struct clk_mgr_vgh *clk_mgr, struct pp_smu_funcs *pp_smu, struct dccg *dccg); void vg_clk_mgr_destroy(struct clk_mgr_internal *clk_mgr); -#include "dcn301_smu.h" -void vg_notify_wm_ranges(struct clk_mgr *clk_mgr_base); - -void vg_get_dpm_table_from_smu(struct clk_mgr_internal *clk_mgr, - struct smu_dpm_clks *smu_dpm_clks); - -void vg_clk_mgr_helper_populate_bw_params( - struct clk_mgr_internal *clk_mgr, - struct integrated_info *bios_info, - const struct vg_dpm_clocks *clock_table); - #endif //__VG_CLK_MGR_H__ diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index 8e6c815b55d2..4713f09bcbf1 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -49,10 +49,13 @@ #include "timing_generator.h" #include "abm.h" #include "virtual/virtual_link_encoder.h" +#include "hubp.h" #include "link_hwss.h" #include "link_encoder.h" +#include "link_enc_cfg.h" +#include "dc_link.h" #include "dc_link_ddc.h" #include "dm_helpers.h" #include "mem_input.h" @@ -304,7 +307,10 @@ bool dc_stream_adjust_vmin_vmax(struct dc *dc, int i = 0; bool ret = false; - stream->adjust = *adjust; + stream->adjust.v_total_max = adjust->v_total_max; + stream->adjust.v_total_mid = adjust->v_total_mid; + stream->adjust.v_total_mid_frame_num = adjust->v_total_mid_frame_num; + stream->adjust.v_total_min = adjust->v_total_min; for (i = 0; i < MAX_PIPES; i++) { struct pipe_ctx *pipe = &dc->current_state->res_ctx.pipe_ctx[i]; @@ -312,10 +318,7 @@ bool dc_stream_adjust_vmin_vmax(struct dc *dc, if (pipe->stream == stream && pipe->stream_res.tg) { dc->hwss.set_drr(&pipe, 1, - adjust->v_total_min, - adjust->v_total_max, - adjust->v_total_mid, - adjust->v_total_mid_frame_num); + *adjust); ret = true; } @@ -870,6 +873,9 @@ static bool dc_construct(struct dc *dc, if (!create_links(dc, init_params->num_virtual_links)) goto fail; + /* Initialise DIG link encoder resource tracking variables. */ + link_enc_cfg_init(dc, dc->current_state); + return true; fail: @@ -1317,11 +1323,10 @@ bool dc_validate_seamless_boot_timing(const struct dc *dc, struct dc_link *link = sink->link; unsigned int i, enc_inst, tg_inst = 0; - // Seamless port only support single DP and EDP so far - if ((sink->sink_signal != SIGNAL_TYPE_DISPLAY_PORT && - sink->sink_signal != SIGNAL_TYPE_EDP) || - sink->sink_signal == SIGNAL_TYPE_DISPLAY_PORT_MST) + /* Support seamless boot on EDP displays only */ + if (sink->sink_signal != SIGNAL_TYPE_EDP) { return false; + } /* Check for enabled DIG to identify enabled display */ if (!link->link_enc->funcs->is_dig_enabled(link->link_enc)) @@ -1394,6 +1399,10 @@ bool dc_validate_seamless_boot_timing(const struct dc *dc, if (crtc_timing->v_sync_width != hw_crtc_timing.v_sync_width) return false; + /* block DSC for now, as VBIOS does not currently support DSC timings */ + if (crtc_timing->flags.DSC) + return false; + if (dc_is_dp_signal(link->connector_signal)) { unsigned int pix_clk_100hz; @@ -1424,6 +1433,11 @@ bool dc_validate_seamless_boot_timing(const struct dc *dc, return false; } + if (is_edp_ilr_optimization_required(link, crtc_timing)) { + DC_LOG_EVENT_LINK_TRAINING("Seamless boot disabled to optimize eDP link rate\n"); + return false; + } + return true; } @@ -2091,6 +2105,10 @@ static enum surface_update_type check_update_surfaces_for_stream( if (stream_status == NULL || stream_status->plane_count != surface_count) overall_type = UPDATE_TYPE_FULL; + if (stream_update && stream_update->pending_test_pattern) { + overall_type = UPDATE_TYPE_FULL; + } + /* some stream updates require passive update */ if (stream_update) { union stream_update_flags *su_flags = &stream_update->stream->update_flags; @@ -2390,6 +2408,8 @@ static void copy_stream_update_to_stream(struct dc *dc, if (update->dither_option) stream->dither_option = *update->dither_option; + if (update->pending_test_pattern) + stream->test_pattern = *update->pending_test_pattern; /* update current stream with writeback info */ if (update->wb_update) { int i; @@ -2485,6 +2505,7 @@ static void commit_planes_do_stream_update(struct dc *dc, } } + /* Full fe update*/ if (update_type == UPDATE_TYPE_FAST) continue; @@ -2492,6 +2513,15 @@ static void commit_planes_do_stream_update(struct dc *dc, if (stream_update->dsc_config) dp_update_dsc_config(pipe_ctx); + if (stream_update->pending_test_pattern) { + dc_link_dp_set_test_pattern(stream->link, + stream->test_pattern.type, + stream->test_pattern.color_space, + stream->test_pattern.p_link_settings, + stream->test_pattern.p_custom_pattern, + stream->test_pattern.cust_pattern_size); + } + if (stream_update->dpms_off) { if (*stream_update->dpms_off) { core_link_disable_stream(pipe_ctx); @@ -2578,6 +2608,17 @@ static void commit_planes_for_stream(struct dc *dc, } } +#ifdef CONFIG_DRM_AMD_DC_DCN + if (stream->test_pattern.type != DP_TEST_PATTERN_VIDEO_MODE) { + struct pipe_ctx *mpcc_pipe; + struct pipe_ctx *odm_pipe; + + for (mpcc_pipe = top_pipe_to_program; mpcc_pipe; mpcc_pipe = mpcc_pipe->bottom_pipe) + for (odm_pipe = mpcc_pipe; odm_pipe; odm_pipe = odm_pipe->next_odm_pipe) + odm_pipe->ttu_regs.min_ttu_vblank = MAX_TTU; + } +#endif + if ((update_type != UPDATE_TYPE_FAST) && stream->update_flags.bits.dsc_changed) if (top_pipe_to_program->stream_res.tg->funcs->lock_doublebuffer_enable) { if (should_use_dmub_lock(stream->link)) { @@ -2646,6 +2687,10 @@ static void commit_planes_for_stream(struct dc *dc, plane_state->triplebuffer_flips = true; } } + if (update_type == UPDATE_TYPE_FULL) { + /* force vsync flip when reconfiguring pipes to prevent underflow */ + plane_state->flip_immediate = false; + } } } @@ -2784,9 +2829,13 @@ static void commit_planes_for_stream(struct dc *dc, for (j = 0; j < dc->res_pool->pipe_count; j++) { struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[j]; + if (!pipe_ctx->plane_state) + continue; + if (pipe_ctx->bottom_pipe || pipe_ctx->next_odm_pipe || !pipe_ctx->stream || pipe_ctx->stream != stream || - !pipe_ctx->plane_state->update_flags.bits.addr_update) + !pipe_ctx->plane_state->update_flags.bits.addr_update || + pipe_ctx->plane_state->skip_manual_trigger) continue; if (pipe_ctx->stream_res.tg->funcs->program_manual_trigger) @@ -3170,6 +3219,19 @@ void dc_link_remove_remote_sink(struct dc_link *link, struct dc_sink *sink) } } +void dc_wait_for_vblank(struct dc *dc, struct dc_stream_state *stream) +{ + int i; + + for (i = 0; i < dc->res_pool->pipe_count; i++) + if (dc->current_state->res_ctx.pipe_ctx[i].stream == stream) { + struct timing_generator *tg = + dc->current_state->res_ctx.pipe_ctx[i].stream_res.tg; + tg->funcs->wait_for_state(tg, CRTC_STATE_VBLANK); + break; + } +} + void get_clock_requirements_for_state(struct dc_state *state, struct AsicStateEx *info) { info->displayClock = (unsigned int)state->bw_ctx.bw.dcn.clk.dispclk_khz; @@ -3225,6 +3287,10 @@ void dc_allow_idle_optimizations(struct dc *dc, bool allow) if (dc->debug.disable_idle_power_optimizations) return; + if (dc->clk_mgr->funcs->is_smu_present) + if (!dc->clk_mgr->funcs->is_smu_present(dc->clk_mgr)) + return; + if (allow == dc->idle_optimizations_allowed) return; diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link.c b/drivers/gpu/drm/amd/display/dc/core/dc_link.c index f9a33dc52c45..f4374d83662a 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c @@ -92,11 +92,14 @@ static void dc_link_destruct(struct dc_link *link) link->panel_cntl->funcs->destroy(&link->panel_cntl); if (link->link_enc) { - /* Update link encoder tracking variables. These are used for the dynamic - * assignment of link encoders to streams. + /* Update link encoder resource tracking variables. These are used for + * the dynamic assignment of link encoders to streams. Virtual links + * are not assigned encoder resources on creation. */ - link->dc->res_pool->link_encoders[link->link_enc->preferred_engine] = NULL; - link->dc->res_pool->dig_link_enc_count--; + if (link->link_id.id != CONNECTOR_ID_VIRTUAL) { + link->dc->res_pool->link_encoders[link->eng_id - ENGINE_ID_DIGA] = NULL; + link->dc->res_pool->dig_link_enc_count--; + } link->link_enc->funcs->destroy(&link->link_enc); } @@ -1407,6 +1410,8 @@ static bool dc_link_construct(struct dc_link *link, link->link_id = bios->funcs->get_connector_id(bios, init_params->connector_index); + link->ep_type = DISPLAY_ENDPOINT_PHY; + DC_LOG_DC("BIOS object table - link_id: %d", link->link_id.id); if (bios->funcs->get_disp_connector_caps_info) { @@ -1506,10 +1511,12 @@ static bool dc_link_construct(struct dc_link *link, (link->link_id.id == CONNECTOR_ID_EDP || link->link_id.id == CONNECTOR_ID_LVDS)) { panel_cntl_init_data.ctx = dc_ctx; - panel_cntl_init_data.inst = link->link_index; + panel_cntl_init_data.inst = + panel_cntl_init_data.ctx->dc_edp_id_count; link->panel_cntl = link->dc->res_pool->funcs->panel_cntl_create( &panel_cntl_init_data); + panel_cntl_init_data.ctx->dc_edp_id_count++; if (link->panel_cntl == NULL) { DC_ERROR("Failed to create link panel_cntl!\n"); @@ -1541,7 +1548,8 @@ static bool dc_link_construct(struct dc_link *link, /* Update link encoder tracking variables. These are used for the dynamic * assignment of link encoders to streams. */ - link->dc->res_pool->link_encoders[link->link_enc->preferred_engine] = link->link_enc; + link->eng_id = link->link_enc->preferred_engine; + link->dc->res_pool->link_encoders[link->eng_id - ENGINE_ID_DIGA] = link->link_enc; link->dc->res_pool->dig_link_enc_count++; link->link_enc_hw_inst = link->link_enc->transmitter; @@ -1671,21 +1679,27 @@ void link_destroy(struct dc_link **link) static void enable_stream_features(struct pipe_ctx *pipe_ctx) { struct dc_stream_state *stream = pipe_ctx->stream; - struct dc_link *link = stream->link; - union down_spread_ctrl old_downspread; - union down_spread_ctrl new_downspread; - core_link_read_dpcd(link, DP_DOWNSPREAD_CTRL, - &old_downspread.raw, sizeof(old_downspread)); + if (pipe_ctx->stream->signal != SIGNAL_TYPE_DISPLAY_PORT_MST) { + struct dc_link *link = stream->link; + union down_spread_ctrl old_downspread; + union down_spread_ctrl new_downspread; - new_downspread.raw = old_downspread.raw; + core_link_read_dpcd(link, DP_DOWNSPREAD_CTRL, + &old_downspread.raw, sizeof(old_downspread)); - new_downspread.bits.IGNORE_MSA_TIMING_PARAM = - (stream->ignore_msa_timing_param) ? 1 : 0; + new_downspread.raw = old_downspread.raw; - if (new_downspread.raw != old_downspread.raw) { - core_link_write_dpcd(link, DP_DOWNSPREAD_CTRL, - &new_downspread.raw, sizeof(new_downspread)); + new_downspread.bits.IGNORE_MSA_TIMING_PARAM = + (stream->ignore_msa_timing_param) ? 1 : 0; + + if (new_downspread.raw != old_downspread.raw) { + core_link_write_dpcd(link, DP_DOWNSPREAD_CTRL, + &new_downspread.raw, sizeof(new_downspread)); + } + + } else { + dm_helpers_mst_enable_stream_features(stream); } } @@ -2805,12 +2819,9 @@ bool dc_link_setup_psr(struct dc_link *link, psr_context->psr_level.u32all = 0; -#if defined(CONFIG_DRM_AMD_DC_DCN) /*skip power down the single pipe since it blocks the cstate*/ - if ((link->ctx->asic_id.chip_family == FAMILY_RV) && - ASICREV_IS_RAVEN(link->ctx->asic_id.hw_internal_rev)) + if (link->ctx->asic_id.chip_family >= FAMILY_RV) psr_context->psr_level.bits.SKIP_CRTC_DISABLE = true; -#endif /* SMU will perform additional powerdown sequence. * For unsupported ASICs, set psr_level flag to skip PSR @@ -2883,8 +2894,8 @@ static struct fixed31_32 get_pbn_per_slot(struct dc_stream_state *stream) static struct fixed31_32 get_pbn_from_bw_in_kbps(uint64_t kbps) { struct fixed31_32 peak_kbps; - uint32_t numerator; - uint32_t denominator; + uint32_t numerator = 0; + uint32_t denominator = 1; /* * margin 5300ppm + 300ppm ~ 0.6% as per spec, factor is 1.006 @@ -3131,50 +3142,6 @@ static enum dc_status deallocate_mst_payload(struct pipe_ctx *pipe_ctx) return DC_OK; } -enum dc_status dc_link_reallocate_mst_payload(struct dc_link *link) -{ - int i; - struct pipe_ctx *pipe_ctx; - - // Clear all of MST payload then reallocate - for (i = 0; i < MAX_PIPES; i++) { - pipe_ctx = &link->dc->current_state->res_ctx.pipe_ctx[i]; - - /* driver enable split pipe for external monitors - * we have to check pipe_ctx is split pipe or not - * If it's split pipe, driver using top pipe to - * reaallocate. - */ - if (!pipe_ctx || pipe_ctx->top_pipe) - continue; - - if (pipe_ctx->stream && pipe_ctx->stream->link == link && - pipe_ctx->stream->dpms_off == false && - pipe_ctx->stream->signal == SIGNAL_TYPE_DISPLAY_PORT_MST) { - deallocate_mst_payload(pipe_ctx); - } - } - - for (i = 0; i < MAX_PIPES; i++) { - pipe_ctx = &link->dc->current_state->res_ctx.pipe_ctx[i]; - - if (!pipe_ctx || pipe_ctx->top_pipe) - continue; - - if (pipe_ctx->stream && pipe_ctx->stream->link == link && - pipe_ctx->stream->dpms_off == false && - pipe_ctx->stream->signal == SIGNAL_TYPE_DISPLAY_PORT_MST) { - /* enable/disable PHY will clear connection between BE and FE - * need to restore it. - */ - link->link_enc->funcs->connect_dig_be_to_fe(link->link_enc, - pipe_ctx->stream_res.stream_enc->id, true); - dc_link_allocate_mst_payload(pipe_ctx); - } - } - - return DC_OK; -} #if defined(CONFIG_DRM_AMD_DC_HDCP) static void update_psp_stream_config(struct pipe_ctx *pipe_ctx, bool dpms_off) @@ -3288,7 +3255,8 @@ void core_link_enable_stream( /* eDP lit up by bios already, no need to enable again. */ if (pipe_ctx->stream->signal == SIGNAL_TYPE_EDP && - apply_edp_fast_boot_optimization) { + apply_edp_fast_boot_optimization && + !pipe_ctx->stream->timing.flags.DSC) { pipe_ctx->stream->dpms_off = false; #if defined(CONFIG_DRM_AMD_DC_HDCP) update_psp_stream_config(pipe_ctx, false); @@ -3350,8 +3318,10 @@ void core_link_enable_stream( /* Set DPS PPS SDP (AKA "info frames") */ if (pipe_ctx->stream->timing.flags.DSC) { if (dc_is_dp_signal(pipe_ctx->stream->signal) || - dc_is_virtual_signal(pipe_ctx->stream->signal)) + dc_is_virtual_signal(pipe_ctx->stream->signal)) { + dp_set_dsc_on_rx(pipe_ctx, true); dp_set_dsc_pps_sdp(pipe_ctx, true); + } } if (pipe_ctx->stream->signal == SIGNAL_TYPE_DISPLAY_PORT_MST) @@ -3746,7 +3716,8 @@ bool dc_link_should_enable_fec(const struct dc_link *link) if ((link->connector_signal != SIGNAL_TYPE_DISPLAY_PORT_MST && link->local_sink && link->local_sink->edid_caps.panel_patch.disable_fec) || - link->connector_signal == SIGNAL_TYPE_EDP) // Disable FEC for eDP + (link->connector_signal == SIGNAL_TYPE_EDP && + link->dc->debug.force_enable_edp_fec == false)) // Disable FEC for eDP is_fec_disable = true; if (dc_link_is_fec_supported(link) && !link->dc->debug.disable_fec && !is_fec_disable) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c index 47e6c33f73cb..3ff3d9e90983 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c @@ -284,7 +284,7 @@ static uint8_t dc_dp_initialize_scrambling_data_symbols( static inline bool is_repeater(struct dc_link *link, uint32_t offset) { - return (link->lttpr_non_transparent_mode && offset != 0); + return (link->lttpr_mode == LTTPR_MODE_NON_TRANSPARENT) && (offset != 0); } static void dpcd_set_lt_pattern_and_lane_settings( @@ -1072,7 +1072,7 @@ static enum link_training_result perform_clock_recovery_sequence( /* 3. wait receiver to lock-on*/ wait_time_microsec = lt_settings->cr_pattern_time; - if (link->lttpr_non_transparent_mode) + if (link->lttpr_mode == LTTPR_MODE_NON_TRANSPARENT) wait_time_microsec = TRAINING_AUX_RD_INTERVAL; wait_for_training_aux_rd_interval( @@ -1098,11 +1098,13 @@ static enum link_training_result perform_clock_recovery_sequence( if (is_max_vs_reached(lt_settings)) break; - /* 7. same voltage*/ - /* Note: VS same for all lanes, - * so comparing first lane is sufficient*/ - if (lt_settings->lane_settings[0].VOLTAGE_SWING == + /* 7. same lane settings*/ + /* Note: settings are the same for all lanes, + * so comparing first lane is sufficient*/ + if ((lt_settings->lane_settings[0].VOLTAGE_SWING == req_settings.lane_settings[0].VOLTAGE_SWING) + && (lt_settings->lane_settings[0].PRE_EMPHASIS == + req_settings.lane_settings[0].PRE_EMPHASIS)) retries_cr++; else retries_cr = 0; @@ -1130,11 +1132,6 @@ static inline enum link_training_result perform_link_training_int( enum link_training_result status) { union lane_count_set lane_count_set = { {0} }; - union dpcd_training_pattern dpcd_pattern = { {0} }; - - /* 3. set training not in progress*/ - dpcd_pattern.v1_4.TRAINING_PATTERN_SET = DPCD_TRAINING_PATTERN_VIDEOIDLE; - dpcd_set_training_pattern(link, dpcd_pattern); /* 4. mainlink output idle pattern*/ dp_set_hw_test_pattern(link, DP_TEST_PATTERN_VIDEO_MODE, NULL, 0); @@ -1324,7 +1321,17 @@ static uint8_t convert_to_count(uint8_t lttpr_repeater_count) return 0; // invalid value } -static void configure_lttpr_mode(struct dc_link *link) +static void configure_lttpr_mode_transparent(struct dc_link *link) +{ + uint8_t repeater_mode = DP_PHY_REPEATER_MODE_TRANSPARENT; + + core_link_write_dpcd(link, + DP_PHY_REPEATER_MODE, + (uint8_t *)&repeater_mode, + sizeof(repeater_mode)); +} + +static void configure_lttpr_mode_non_transparent(struct dc_link *link) { /* aux timeout is already set to extended */ /* RESET/SET lttpr mode to enable non transparent mode */ @@ -1344,7 +1351,7 @@ static void configure_lttpr_mode(struct dc_link *link) link->dpcd_caps.lttpr_caps.mode = repeater_mode; } - if (link->lttpr_non_transparent_mode) { + if (link->lttpr_mode == LTTPR_MODE_NON_TRANSPARENT) { DC_LOG_HW_LINK_TRAINING("%s\n Set LTTPR to Non Transparent Mode\n", __func__); @@ -1548,6 +1555,7 @@ enum link_training_result dc_link_dp_perform_link_training( { enum link_training_result status = LINK_TRAINING_SUCCESS; struct link_training_settings lt_settings; + union dpcd_training_pattern dpcd_pattern = { { 0 } }; bool fec_enable; uint8_t repeater_cnt; @@ -1560,8 +1568,10 @@ enum link_training_result dc_link_dp_perform_link_training( <_settings); /* Configure lttpr mode */ - if (link->lttpr_non_transparent_mode) - configure_lttpr_mode(link); + if (link->lttpr_mode == LTTPR_MODE_NON_TRANSPARENT) + configure_lttpr_mode_non_transparent(link); + else if (link->lttpr_mode == LTTPR_MODE_TRANSPARENT) + configure_lttpr_mode_transparent(link); if (link->ctx->dc->work_arounds.lt_early_cr_pattern) start_clock_recovery_pattern_early(link, <_settings, DPRX); @@ -1576,7 +1586,7 @@ enum link_training_result dc_link_dp_perform_link_training( dp_set_fec_ready(link, fec_enable); - if (link->lttpr_non_transparent_mode) { + if (link->lttpr_mode == LTTPR_MODE_NON_TRANSPARENT) { /* 2. perform link training (set link training done * to false is done as well) @@ -1610,6 +1620,9 @@ enum link_training_result dc_link_dp_perform_link_training( } } + /* 3. set training not in progress*/ + dpcd_pattern.v1_4.TRAINING_PATTERN_SET = DPCD_TRAINING_PATTERN_VIDEOIDLE; + dpcd_set_training_pattern(link, dpcd_pattern); if ((status == LINK_TRAINING_SUCCESS) || !skip_video_pattern) { status = perform_link_training_int(link, <_settings, @@ -1633,6 +1646,42 @@ enum link_training_result dc_link_dp_perform_link_training( return status; } +static enum dp_panel_mode try_enable_assr(struct dc_stream_state *stream) +{ + struct dc_link *link = stream->link; + enum dp_panel_mode panel_mode = dp_get_panel_mode(link); +#ifdef CONFIG_DRM_AMD_DC_HDCP + struct cp_psp *cp_psp = &stream->ctx->cp_psp; +#endif + + /* ASSR must be supported on the panel */ + if (panel_mode == DP_PANEL_MODE_DEFAULT) + return panel_mode; + + /* eDP or internal DP only */ + if (link->connector_signal != SIGNAL_TYPE_EDP && + !(link->connector_signal == SIGNAL_TYPE_DISPLAY_PORT && + link->is_internal_display)) + return DP_PANEL_MODE_DEFAULT; + +#ifdef CONFIG_DRM_AMD_DC_HDCP + if (cp_psp && cp_psp->funcs.enable_assr) { + if (!cp_psp->funcs.enable_assr(cp_psp->handle, link)) { + /* since eDP implies ASSR on, change panel + * mode to disable ASSR + */ + panel_mode = DP_PANEL_MODE_DEFAULT; + } + } else + panel_mode = DP_PANEL_MODE_DEFAULT; + +#else + /* turn off ASSR if the implementation is not compiled in */ + panel_mode = DP_PANEL_MODE_DEFAULT; +#endif + return panel_mode; +} + bool perform_link_training_with_retries( const struct dc_link_settings *link_setting, bool skip_video_pattern, @@ -1644,7 +1693,7 @@ bool perform_link_training_with_retries( uint8_t delay_between_attempts = LINK_TRAINING_RETRY_DELAY; struct dc_stream_state *stream = pipe_ctx->stream; struct dc_link *link = stream->link; - enum dp_panel_mode panel_mode = dp_get_panel_mode(link); + enum dp_panel_mode panel_mode; /* We need to do this before the link training to ensure the idle pattern in SST * mode will be sent right after the link training @@ -1669,32 +1718,25 @@ bool perform_link_training_with_retries( msleep(delay_dp_power_up_in_ms); } -#ifdef CONFIG_DRM_AMD_DC_HDCP - if (panel_mode == DP_PANEL_MODE_EDP) { - struct cp_psp *cp_psp = &stream->ctx->cp_psp; - - if (cp_psp && cp_psp->funcs.enable_assr) { - if (!cp_psp->funcs.enable_assr(cp_psp->handle, link)) { - /* since eDP implies ASSR on, change panel - * mode to disable ASSR - */ - panel_mode = DP_PANEL_MODE_DEFAULT; - } - } else - panel_mode = DP_PANEL_MODE_DEFAULT; - } -#endif - + panel_mode = try_enable_assr(stream); dp_set_panel_mode(link, panel_mode); + DC_LOG_DETECTION_DP_CAPS("Link: %d ASSR enabled: %d\n", + link->link_index, + panel_mode != DP_PANEL_MODE_DEFAULT); if (link->aux_access_disabled) { dc_link_dp_perform_link_training_skip_aux(link, link_setting); return true; - } else if (dc_link_dp_perform_link_training( - link, - link_setting, - skip_video_pattern) == LINK_TRAINING_SUCCESS) - return true; + } else { + enum link_training_result status = LINK_TRAINING_CR_FAIL_LANE0; + + status = dc_link_dp_perform_link_training( + link, + link_setting, + skip_video_pattern); + if (status == LINK_TRAINING_SUCCESS) + return true; + } /* latest link training still fail, skip delay and keep PHY on */ @@ -1873,7 +1915,7 @@ static struct dc_link_settings get_max_link_cap(struct dc_link *link) * account for lttpr repeaters cap * notes: repeaters do not snoop in the DPRX Capabilities addresses (3.6.3). */ - if (link->lttpr_non_transparent_mode) { + if (link->lttpr_mode == LTTPR_MODE_NON_TRANSPARENT) { if (link->dpcd_caps.lttpr_caps.max_lane_count < max_link_cap.lane_count) max_link_cap.lane_count = link->dpcd_caps.lttpr_caps.max_lane_count; @@ -2031,7 +2073,7 @@ bool dp_verify_link_cap( max_link_cap = get_max_link_cap(link); /* Grant extended timeout request */ - if (link->lttpr_non_transparent_mode && link->dpcd_caps.lttpr_caps.max_ext_timeout > 0) { + if ((link->lttpr_mode == LTTPR_MODE_NON_TRANSPARENT) && (link->dpcd_caps.lttpr_caps.max_ext_timeout > 0)) { uint8_t grant = link->dpcd_caps.lttpr_caps.max_ext_timeout & 0x80; core_link_write_dpcd(link, DP_PHY_REPEATER_EXTENDED_WAIT_TIMEOUT, &grant, sizeof(grant)); @@ -2447,7 +2489,7 @@ static bool decide_dp_link_settings(struct dc_link *link, struct dc_link_setting return false; } -static bool decide_edp_link_settings(struct dc_link *link, struct dc_link_settings *link_setting, uint32_t req_bw) +bool decide_edp_link_settings(struct dc_link *link, struct dc_link_settings *link_setting, uint32_t req_bw) { struct dc_link_settings initial_link_setting; struct dc_link_settings current_link_setting; @@ -2782,10 +2824,27 @@ static void dp_test_send_link_test_pattern(struct dc_link *link) enum dp_test_pattern test_pattern; enum dp_test_pattern_color_space test_pattern_color_space = DP_TEST_PATTERN_COLOR_SPACE_UNDEFINED; + enum dc_color_depth requestColorDepth = COLOR_DEPTH_UNDEFINED; + struct pipe_ctx *pipes = link->dc->current_state->res_ctx.pipe_ctx; + struct pipe_ctx *pipe_ctx = NULL; + int i; memset(&dpcd_test_pattern, 0, sizeof(dpcd_test_pattern)); memset(&dpcd_test_params, 0, sizeof(dpcd_test_params)); + for (i = 0; i < MAX_PIPES; i++) { + if (pipes[i].stream == NULL) + continue; + + if (pipes[i].stream->link == link && !pipes[i].top_pipe && !pipes[i].prev_odm_pipe) { + pipe_ctx = &pipes[i]; + break; + } + } + + if (pipe_ctx == NULL) + return; + /* get link test pattern and pattern parameters */ core_link_read_dpcd( link, @@ -2823,6 +2882,33 @@ static void dp_test_send_link_test_pattern(struct dc_link *link) DP_TEST_PATTERN_COLOR_SPACE_YCBCR709 : DP_TEST_PATTERN_COLOR_SPACE_YCBCR601; + switch (dpcd_test_params.bits.BPC) { + case 0: // 6 bits + requestColorDepth = COLOR_DEPTH_666; + break; + case 1: // 8 bits + requestColorDepth = COLOR_DEPTH_888; + break; + case 2: // 10 bits + requestColorDepth = COLOR_DEPTH_101010; + break; + case 3: // 12 bits + requestColorDepth = COLOR_DEPTH_121212; + break; + default: + break; + } + + if (requestColorDepth != COLOR_DEPTH_UNDEFINED + && pipe_ctx->stream->timing.display_color_depth != requestColorDepth) { + DC_LOG_DEBUG("%s: original bpc %d, changing to %d\n", + __func__, + pipe_ctx->stream->timing.display_color_depth, + requestColorDepth); + pipe_ctx->stream->timing.display_color_depth = requestColorDepth; + dp_update_dsc_config(pipe_ctx); + } + dc_link_dp_set_test_pattern( link, test_pattern, @@ -3369,6 +3455,9 @@ static bool retrieve_link_cap(struct dc_link *link) struct dp_sink_hw_fw_revision dp_hw_fw_revision; bool is_lttpr_present = false; const uint32_t post_oui_delay = 30; // 30ms + bool vbios_lttpr_enable = false; + bool vbios_lttpr_interop = false; + struct dc_bios *bios = link->dc->ctx->dc_bios; memset(dpcd_data, '\0', sizeof(dpcd_data)); memset(lttpr_dpcd_data, '\0', sizeof(lttpr_dpcd_data)); @@ -3416,13 +3505,45 @@ static bool retrieve_link_cap(struct dc_link *link) return false; } - if (link->dc->caps.extended_aux_timeout_support && - link->dc->config.allow_lttpr_non_transparent_mode) { + /* Query BIOS to determine if LTTPR functionality is forced on by system */ + if (bios->funcs->get_lttpr_caps) { + enum bp_result bp_query_result; + uint8_t is_vbios_lttpr_enable = 0; + + bp_query_result = bios->funcs->get_lttpr_caps(bios, &is_vbios_lttpr_enable); + vbios_lttpr_enable = (bp_query_result == BP_RESULT_OK) && !!is_vbios_lttpr_enable; + } + + if (bios->funcs->get_lttpr_interop) { + enum bp_result bp_query_result; + uint8_t is_vbios_interop_enabled = 0; + + bp_query_result = bios->funcs->get_lttpr_interop(bios, &is_vbios_interop_enabled); + vbios_lttpr_interop = (bp_query_result == BP_RESULT_OK) && !!is_vbios_interop_enabled; + } + + /* + * Logic to determine LTTPR mode + */ + link->lttpr_mode = LTTPR_MODE_NON_LTTPR; + if (vbios_lttpr_enable && vbios_lttpr_interop) + link->lttpr_mode = LTTPR_MODE_NON_TRANSPARENT; + else if (!vbios_lttpr_enable && vbios_lttpr_interop) { + if (link->dc->config.allow_lttpr_non_transparent_mode) + link->lttpr_mode = LTTPR_MODE_NON_TRANSPARENT; + else + link->lttpr_mode = LTTPR_MODE_TRANSPARENT; + } else if (!vbios_lttpr_enable && !vbios_lttpr_interop) { + if (!link->dc->config.allow_lttpr_non_transparent_mode + || !link->dc->caps.extended_aux_timeout_support) + link->lttpr_mode = LTTPR_MODE_NON_LTTPR; + else + link->lttpr_mode = LTTPR_MODE_NON_TRANSPARENT; + } + + if (link->lttpr_mode == LTTPR_MODE_NON_TRANSPARENT || link->lttpr_mode == LTTPR_MODE_TRANSPARENT) { /* By reading LTTPR capability, RX assumes that we will enable - * LTTPR non transparent if LTTPR is present. - * Therefore, only query LTTPR capability when both LTTPR - * extended aux timeout and - * non transparent mode is supported by hardware + * LTTPR extended aux timeout if LTTPR is present. */ status = core_link_read_dpcd( link, @@ -3460,11 +3581,10 @@ static bool retrieve_link_cap(struct dc_link *link) link->dpcd_caps.lttpr_caps.revision.raw >= 0x14); if (is_lttpr_present) CONN_DATA_DETECT(link, lttpr_dpcd_data, sizeof(lttpr_dpcd_data), "LTTPR Caps: "); + else + link->lttpr_mode = LTTPR_MODE_NON_LTTPR; } - /* decide lttpr non transparent mode */ - link->lttpr_non_transparent_mode = is_lttpr_present; - if (!is_lttpr_present) dc_link_aux_try_to_configure_timeout(link->ddc, LINK_AUX_DEFAULT_TIMEOUT_PERIOD); @@ -3773,7 +3893,7 @@ void detect_edp_sink_caps(struct dc_link *link) memset(supported_link_rates, 0, sizeof(supported_link_rates)); if (link->dpcd_caps.dpcd_rev.raw >= DPCD_REV_14 && - (link->dc->config.optimize_edp_link_rate || + (link->dc->debug.optimize_edp_link_rate || link->reported_link_cap.link_rate == LINK_RATE_UNKNOWN)) { // Read DPCD 00010h - 0001Fh 16 bytes at one shot core_link_read_dpcd(link, DP_SUPPORTED_LINK_RATES, @@ -4599,3 +4719,51 @@ bool dc_link_set_default_brightness_aux(struct dc_link *link) } return false; } + +bool is_edp_ilr_optimization_required(struct dc_link *link, struct dc_crtc_timing *crtc_timing) +{ + struct dc_link_settings link_setting; + uint8_t link_bw_set; + uint8_t link_rate_set; + uint32_t req_bw; + union lane_count_set lane_count_set = { {0} }; + + ASSERT(link || crtc_timing); // invalid input + + if (link->dpcd_caps.edp_supported_link_rates_count == 0 || + !link->dc->debug.optimize_edp_link_rate) + return false; + + + // Read DPCD 00100h to find if standard link rates are set + core_link_read_dpcd(link, DP_LINK_BW_SET, + &link_bw_set, sizeof(link_bw_set)); + + if (link_bw_set) { + DC_LOG_EVENT_LINK_TRAINING("eDP ILR: Optimization required, VBIOS used link_bw_set\n"); + return true; + } + + // Read DPCD 00115h to find the edp link rate set used + core_link_read_dpcd(link, DP_LINK_RATE_SET, + &link_rate_set, sizeof(link_rate_set)); + + // Read DPCD 00101h to find out the number of lanes currently set + core_link_read_dpcd(link, DP_LANE_COUNT_SET, + &lane_count_set.raw, sizeof(lane_count_set)); + + req_bw = dc_bandwidth_in_kbps_from_timing(crtc_timing); + + decide_edp_link_settings(link, &link_setting, req_bw); + + if (link->dpcd_caps.edp_supported_link_rates[link_rate_set] != link_setting.link_rate || + lane_count_set.bits.LANE_COUNT_SET != link_setting.lane_count) { + DC_LOG_EVENT_LINK_TRAINING("eDP ILR: Optimization required, VBIOS link_rate_set not optimal\n"); + return true; + } + + DC_LOG_EVENT_LINK_TRAINING("eDP ILR: No optimization required, VBIOS set optimal link_rate_set\n"); + return false; +} + + diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_enc_cfg.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_enc_cfg.c new file mode 100644 index 000000000000..1361b87d86d7 --- /dev/null +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_enc_cfg.c @@ -0,0 +1,303 @@ +/* + * Copyright 2021 Advanced Micro Devices, Inc. + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR + * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, + * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR + * OTHER DEALINGS IN THE SOFTWARE. + * + * Authors: AMD + * + */ + +#include "link_enc_cfg.h" +#include "resource.h" +#include "dc_link_dp.h" + +/* Check whether stream is supported by DIG link encoders. */ +static bool is_dig_link_enc_stream(struct dc_stream_state *stream) +{ + bool is_dig_stream = false; + struct link_encoder *link_enc = NULL; + int i; + + /* Loop over created link encoder objects. */ + for (i = 0; i < stream->ctx->dc->res_pool->res_cap->num_dig_link_enc; i++) { + link_enc = stream->ctx->dc->res_pool->link_encoders[i]; + + if (link_enc && + ((uint32_t)stream->signal & link_enc->output_signals)) { + if (dc_is_dp_signal(stream->signal)) { + /* DIGs do not support DP2.0 streams with 128b/132b encoding. */ + struct dc_link_settings link_settings = {0}; + + decide_link_settings(stream, &link_settings); + if ((link_settings.link_rate >= LINK_RATE_LOW) && + link_settings.link_rate <= LINK_RATE_HIGH3) { + is_dig_stream = true; + break; + } + } else { + is_dig_stream = true; + break; + } + } + } + + return is_dig_stream; +} + +/* Update DIG link encoder resource tracking variables in dc_state. */ +static void update_link_enc_assignment( + struct dc_state *state, + struct dc_stream_state *stream, + enum engine_id eng_id, + bool add_enc) +{ + int eng_idx; + int stream_idx; + int i; + + if (eng_id != ENGINE_ID_UNKNOWN) { + eng_idx = eng_id - ENGINE_ID_DIGA; + stream_idx = -1; + + /* Index of stream in dc_state used to update correct entry in + * link_enc_assignments table. + */ + for (i = 0; i < state->stream_count; i++) { + if (stream == state->streams[i]) { + stream_idx = i; + break; + } + } + + /* Update link encoder assignments table, link encoder availability + * pool and link encoder assigned to stream in state. + * Add/remove encoder resource to/from stream. + */ + if (stream_idx != -1) { + if (add_enc) { + state->res_ctx.link_enc_assignments[stream_idx] = (struct link_enc_assignment){ + .valid = true, + .ep_id = (struct display_endpoint_id) { + .link_id = stream->link->link_id, + .ep_type = stream->link->ep_type}, + .eng_id = eng_id}; + state->res_ctx.link_enc_avail[eng_idx] = ENGINE_ID_UNKNOWN; + stream->link_enc = stream->ctx->dc->res_pool->link_encoders[eng_idx]; + } else { + state->res_ctx.link_enc_assignments[stream_idx].valid = false; + state->res_ctx.link_enc_avail[eng_idx] = eng_id; + stream->link_enc = NULL; + } + } else { + dm_output_to_console("%s: Stream not found in dc_state.\n", __func__); + } + } +} + +/* Return first available DIG link encoder. */ +static enum engine_id find_first_avail_link_enc( + struct dc_context *ctx, + struct dc_state *state) +{ + enum engine_id eng_id = ENGINE_ID_UNKNOWN; + int i; + + for (i = 0; i < ctx->dc->res_pool->res_cap->num_dig_link_enc; i++) { + eng_id = state->res_ctx.link_enc_avail[i]; + if (eng_id != ENGINE_ID_UNKNOWN) + break; + } + + return eng_id; +} + +/* Return stream using DIG link encoder resource. NULL if unused. */ +static struct dc_stream_state *get_stream_using_link_enc( + struct dc_state *state, + enum engine_id eng_id) +{ + struct dc_stream_state *stream = NULL; + int stream_idx = -1; + int i; + + for (i = 0; i < state->stream_count; i++) { + struct link_enc_assignment assignment = state->res_ctx.link_enc_assignments[i]; + + if (assignment.valid && (assignment.eng_id == eng_id)) { + stream_idx = i; + break; + } + } + + if (stream_idx != -1) + stream = state->streams[stream_idx]; + else + dm_output_to_console("%s: No stream using DIG(%d).\n", __func__, eng_id); + + return stream; +} + +void link_enc_cfg_init( + struct dc *dc, + struct dc_state *state) +{ + int i; + + for (i = 0; i < dc->res_pool->res_cap->num_dig_link_enc; i++) { + if (dc->res_pool->link_encoders[i]) + state->res_ctx.link_enc_avail[i] = (enum engine_id) i; + else + state->res_ctx.link_enc_avail[i] = ENGINE_ID_UNKNOWN; + } +} + +void link_enc_cfg_link_encs_assign( + struct dc *dc, + struct dc_state *state, + struct dc_stream_state *streams[], + uint8_t stream_count) +{ + enum engine_id eng_id = ENGINE_ID_UNKNOWN; + int i; + + /* Release DIG link encoder resources before running assignment algorithm. */ + for (i = 0; i < stream_count; i++) + dc->res_pool->funcs->link_enc_unassign(state, streams[i]); + + /* (a) Assign DIG link encoders to physical (unmappable) endpoints first. */ + for (i = 0; i < stream_count; i++) { + struct dc_stream_state *stream = streams[i]; + + /* Skip stream if not supported by DIG link encoder. */ + if (!is_dig_link_enc_stream(stream)) + continue; + + /* Physical endpoints have a fixed mapping to DIG link encoders. */ + if (!stream->link->is_dig_mapping_flexible) { + eng_id = stream->link->eng_id; + update_link_enc_assignment(state, stream, eng_id, true); + } + } + + /* (b) Then assign encoders to mappable endpoints. */ + eng_id = ENGINE_ID_UNKNOWN; + + for (i = 0; i < stream_count; i++) { + struct dc_stream_state *stream = streams[i]; + + /* Skip stream if not supported by DIG link encoder. */ + if (!is_dig_link_enc_stream(stream)) + continue; + + /* Mappable endpoints have a flexible mapping to DIG link encoders. */ + if (stream->link->is_dig_mapping_flexible) { + eng_id = find_first_avail_link_enc(stream->ctx, state); + update_link_enc_assignment(state, stream, eng_id, true); + } + } +} + +void link_enc_cfg_link_enc_unassign( + struct dc_state *state, + struct dc_stream_state *stream) +{ + enum engine_id eng_id = ENGINE_ID_UNKNOWN; + + /* Only DIG link encoders. */ + if (!is_dig_link_enc_stream(stream)) + return; + + if (stream->link_enc) + eng_id = stream->link_enc->preferred_engine; + + update_link_enc_assignment(state, stream, eng_id, false); +} + +bool link_enc_cfg_is_transmitter_mappable( + struct dc_state *state, + struct link_encoder *link_enc) +{ + bool is_mappable = false; + enum engine_id eng_id = link_enc->preferred_engine; + struct dc_stream_state *stream = get_stream_using_link_enc(state, eng_id); + + if (stream) + is_mappable = stream->link->is_dig_mapping_flexible; + + return is_mappable; +} + +struct dc_link *link_enc_cfg_get_link_using_link_enc( + struct dc_state *state, + enum engine_id eng_id) +{ + struct dc_link *link = NULL; + int stream_idx = -1; + int i; + + for (i = 0; i < state->stream_count; i++) { + struct link_enc_assignment assignment = state->res_ctx.link_enc_assignments[i]; + + if (assignment.valid && (assignment.eng_id == eng_id)) { + stream_idx = i; + break; + } + } + + if (stream_idx != -1) + link = state->streams[stream_idx]->link; + else + dm_output_to_console("%s: No link using DIG(%d).\n", __func__, eng_id); + + return link; +} + +struct link_encoder *link_enc_cfg_get_link_enc_used_by_link( + struct dc_state *state, + struct dc_link *link) +{ + struct link_encoder *link_enc = NULL; + struct display_endpoint_id ep_id; + int stream_idx = -1; + int i; + + ep_id = (struct display_endpoint_id) { + .link_id = link->link_id, + .ep_type = link->ep_type}; + + for (i = 0; i < state->stream_count; i++) { + struct link_enc_assignment assignment = state->res_ctx.link_enc_assignments[i]; + + if (assignment.valid && + assignment.ep_id.link_id.id == ep_id.link_id.id && + assignment.ep_id.link_id.enum_id == ep_id.link_id.enum_id && + assignment.ep_id.link_id.type == ep_id.link_id.type && + assignment.ep_id.ep_type == ep_id.ep_type) { + stream_idx = i; + break; + } + } + + if (stream_idx != -1) + link_enc = state->streams[stream_idx]->link_enc; + else + dm_output_to_console("%s: No link encoder used by link(%d).\n", __func__, link->link_index); + + return link_enc; +} diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_hwss.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_hwss.c index 124ce215fca5..b426f878fb99 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link_hwss.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_hwss.c @@ -14,6 +14,7 @@ #include "dpcd_defs.h" #include "dsc.h" #include "resource.h" +#include "link_enc_cfg.h" #include "clk_mgr.h" static uint8_t convert_to_count(uint8_t lttpr_repeater_count) @@ -95,7 +96,7 @@ void dp_enable_link_phy( enum clock_source_id clock_source, const struct dc_link_settings *link_settings) { - struct link_encoder *link_enc = link->link_enc; + struct link_encoder *link_enc; struct dc *dc = link->ctx->dc; struct dmcu *dmcu = dc->res_pool->dmcu; @@ -105,6 +106,13 @@ void dp_enable_link_phy( link->dc->res_pool->dp_clock_source; unsigned int i; + /* Link should always be assigned encoder when en-/disabling. */ + if (link->is_dig_mapping_flexible && dc->res_pool->funcs->link_encs_assign) + link_enc = link_enc_cfg_get_link_enc_used_by_link(link->dc->current_state, link); + else + link_enc = link->link_enc; + ASSERT(link_enc); + if (link->connector_signal == SIGNAL_TYPE_EDP) { link->dc->hwss.edp_power_control(link, true); link->dc->hwss.edp_wait_for_hpd_ready(link, true); @@ -227,6 +235,14 @@ void dp_disable_link_phy(struct dc_link *link, enum signal_type signal) { struct dc *dc = link->ctx->dc; struct dmcu *dmcu = dc->res_pool->dmcu; + struct link_encoder *link_enc; + + /* Link should always be assigned encoder when en-/disabling. */ + if (link->is_dig_mapping_flexible && dc->res_pool->funcs->link_encs_assign) + link_enc = link_enc_cfg_get_link_enc_used_by_link(link->dc->current_state, link); + else + link_enc = link->link_enc; + ASSERT(link_enc); if (!link->wa_flags.dp_keep_receiver_powered) dp_receiver_power_ctrl(link, false); @@ -234,13 +250,13 @@ void dp_disable_link_phy(struct dc_link *link, enum signal_type signal) if (signal == SIGNAL_TYPE_EDP) { if (link->dc->hwss.edp_backlight_control) link->dc->hwss.edp_backlight_control(link, false); - link->link_enc->funcs->disable_output(link->link_enc, signal); + link_enc->funcs->disable_output(link_enc, signal); link->dc->hwss.edp_power_control(link, false); } else { if (dmcu != NULL && dmcu->funcs->lock_phy) dmcu->funcs->lock_phy(dmcu); - link->link_enc->funcs->disable_output(link->link_enc, signal); + link_enc->funcs->disable_output(link_enc, signal); if (dmcu != NULL && dmcu->funcs->unlock_phy) dmcu->funcs->unlock_phy(dmcu); @@ -302,7 +318,7 @@ void dp_set_hw_lane_settings( { struct link_encoder *encoder = link->link_enc; - if (link->lttpr_non_transparent_mode && !is_immediate_downstream(link, offset)) + if ((link->lttpr_mode == LTTPR_MODE_NON_TRANSPARENT) && !is_immediate_downstream(link, offset)) return; /* call Encoder to set lane settings */ @@ -415,7 +431,7 @@ static void dsc_optc_config_log(struct display_stream_compressor *dsc, DC_LOG_DSC("\tslice_width %d", config->slice_width); } -static bool dp_set_dsc_on_rx(struct pipe_ctx *pipe_ctx, bool enable) +bool dp_set_dsc_on_rx(struct pipe_ctx *pipe_ctx, bool enable) { struct dc *dc = pipe_ctx->stream->ctx->dc; struct dc_stream_state *stream = pipe_ctx->stream; @@ -525,7 +541,7 @@ bool dp_set_dsc_enable(struct pipe_ctx *pipe_ctx, bool enable) goto out; if (enable) { - if (dp_set_dsc_on_rx(pipe_ctx, true)) { + { dp_set_dsc_on_stream(pipe_ctx, true); result = true; } diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c index 3c91d16c2710..8cb937c046aa 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c @@ -1930,6 +1930,9 @@ enum dc_status dc_remove_stream_from_ctx( dc->res_pool, del_pipe->stream_res.stream_enc, false); + /* Release link encoder from stream in new dc_state. */ + if (dc->res_pool->funcs->link_enc_unassign) + dc->res_pool->funcs->link_enc_unassign(new_ctx, del_pipe->stream); if (del_pipe->stream_res.audio) update_audio_usage( @@ -2503,26 +2506,31 @@ static void set_avi_info_frame( hdmi_info.bits.ITC = itc_value; } + if (stream->qs_bit == 1) { + if (color_space == COLOR_SPACE_SRGB || + color_space == COLOR_SPACE_2020_RGB_FULLRANGE) + hdmi_info.bits.Q0_Q1 = RGB_QUANTIZATION_FULL_RANGE; + else if (color_space == COLOR_SPACE_SRGB_LIMITED || + color_space == COLOR_SPACE_2020_RGB_LIMITEDRANGE) + hdmi_info.bits.Q0_Q1 = RGB_QUANTIZATION_LIMITED_RANGE; + else + hdmi_info.bits.Q0_Q1 = RGB_QUANTIZATION_DEFAULT_RANGE; + } else + hdmi_info.bits.Q0_Q1 = RGB_QUANTIZATION_DEFAULT_RANGE; + /* TODO : We should handle YCC quantization */ /* but we do not have matrix calculation */ - if (stream->qs_bit == 1 && - stream->qy_bit == 1) { + if (stream->qy_bit == 1) { if (color_space == COLOR_SPACE_SRGB || - color_space == COLOR_SPACE_2020_RGB_FULLRANGE) { - hdmi_info.bits.Q0_Q1 = RGB_QUANTIZATION_FULL_RANGE; + color_space == COLOR_SPACE_2020_RGB_FULLRANGE) hdmi_info.bits.YQ0_YQ1 = YYC_QUANTIZATION_LIMITED_RANGE; - } else if (color_space == COLOR_SPACE_SRGB_LIMITED || - color_space == COLOR_SPACE_2020_RGB_LIMITEDRANGE) { - hdmi_info.bits.Q0_Q1 = RGB_QUANTIZATION_LIMITED_RANGE; + else if (color_space == COLOR_SPACE_SRGB_LIMITED || + color_space == COLOR_SPACE_2020_RGB_LIMITEDRANGE) hdmi_info.bits.YQ0_YQ1 = YYC_QUANTIZATION_LIMITED_RANGE; - } else { - hdmi_info.bits.Q0_Q1 = RGB_QUANTIZATION_DEFAULT_RANGE; + else hdmi_info.bits.YQ0_YQ1 = YYC_QUANTIZATION_LIMITED_RANGE; - } - } else { - hdmi_info.bits.Q0_Q1 = RGB_QUANTIZATION_DEFAULT_RANGE; - hdmi_info.bits.YQ0_YQ1 = YYC_QUANTIZATION_LIMITED_RANGE; - } + } else + hdmi_info.bits.YQ0_YQ1 = YYC_QUANTIZATION_LIMITED_RANGE; ///VIC format = stream->timing.timing_3d_format; @@ -2842,6 +2850,10 @@ bool pipe_need_reprogram( if (pipe_ctx_old->stream_res.dsc != pipe_ctx->stream_res.dsc) return true; + /* DIG link encoder resource assignment for stream changed. */ + if (pipe_ctx_old->stream->link_enc != pipe_ctx->stream->link_enc) + return true; + return false; } diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h index d163007e057c..100d434f7a03 100644 --- a/drivers/gpu/drm/amd/display/dc/dc.h +++ b/drivers/gpu/drm/amd/display/dc/dc.h @@ -45,7 +45,7 @@ /* forward declaration */ struct aux_payload; -#define DC_VER "3.2.127" +#define DC_VER "3.2.132" #define MAX_SURFACES 3 #define MAX_PLANES 6 @@ -293,7 +293,6 @@ struct dc_config { bool gpu_vm_support; bool disable_disp_pll_sharing; bool fbc_support; - bool optimize_edp_link_rate; bool disable_fractional_pwm; bool allow_seamless_boot_optimization; bool power_down_display_on_boot; @@ -309,6 +308,8 @@ struct dc_config { #endif uint64_t vblank_alignment_dto_params; uint8_t vblank_alignment_max_frame_time_diff; + bool is_asymmetric_memory; + bool is_single_rank_dimm; }; enum visual_confirm { @@ -460,6 +461,7 @@ struct dc_debug_options { enum pipe_split_policy pipe_split_policy; bool force_single_disp_pipe_split; bool voltage_align_fclk; + bool disable_min_fclk; bool disable_dfs_bypass; bool disable_dpp_power_gate; @@ -540,6 +542,11 @@ struct dc_debug_options { /* Enable dmub aux for legacy ddc */ bool enable_dmub_aux_for_legacy_ddc; + bool optimize_edp_link_rate; /* eDP ILR */ + /* force enable edp FEC */ + bool force_enable_edp_fec; + /* FEC/PSR1 sequence enable delay in 100us */ + uint8_t fec_enable_delay_in100us; }; struct dc_debug_data { @@ -712,6 +719,7 @@ void dc_init_callbacks(struct dc *dc, void dc_deinit_callbacks(struct dc *dc); void dc_destroy(struct dc **dc); +void dc_wait_for_vblank(struct dc *dc, struct dc_stream_state *stream); /******************************************************************************* * Surface Interfaces ******************************************************************************/ @@ -899,6 +907,8 @@ struct dc_plane_state { union surface_update_flags update_flags; bool flip_int_enabled; + bool skip_manual_trigger; + /* private to DC core */ struct dc_plane_status status; struct dc_context *ctx; diff --git a/drivers/gpu/drm/amd/display/dc/dc_bios_types.h b/drivers/gpu/drm/amd/display/dc/dc_bios_types.h index 86ab8f16f621..67abda44eb1f 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_bios_types.h +++ b/drivers/gpu/drm/amd/display/dc/dc_bios_types.h @@ -150,6 +150,12 @@ struct dc_vbios_funcs { struct dc_bios *dcb, struct graphics_object_id object_id, struct bp_disp_connector_caps_info *info); + enum bp_result (*get_lttpr_caps)( + struct dc_bios *dcb, + uint8_t *dce_caps); + enum bp_result (*get_lttpr_interop)( + struct dc_bios *dcb, + uint8_t *dce_caps); }; struct bios_registers { diff --git a/drivers/gpu/drm/amd/display/dc/dc_link.h b/drivers/gpu/drm/amd/display/dc/dc_link.h index c50ef5a909a6..054bab45ee17 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_link.h +++ b/drivers/gpu/drm/amd/display/dc/dc_link.h @@ -35,6 +35,13 @@ enum dc_link_fec_state { dc_link_fec_ready, dc_link_fec_enabled }; + +enum lttpr_mode { + LTTPR_MODE_NON_LTTPR, + LTTPR_MODE_TRANSPARENT, + LTTPR_MODE_NON_TRANSPARENT, +}; + struct dc_link_status { bool link_active; struct dpcd_caps *dpcd_caps; @@ -100,7 +107,7 @@ struct dc_link { bool link_state_valid; bool aux_access_disabled; bool sync_lt_in_progress; - bool lttpr_non_transparent_mode; + enum lttpr_mode lttpr_mode; bool is_internal_display; /* TODO: Rename. Flag an endpoint as having a programmable mapping to a @@ -125,6 +132,11 @@ struct dc_link { uint8_t hpd_src; uint8_t link_enc_hw_inst; + /* DIG link encoder ID. Used as index in link encoder resource pool. + * For links with fixed mapping to DIG, this is not changed after dc_link + * object creation. + */ + enum engine_id eng_id; bool test_pattern_enabled; union compliance_test_state compliance_test_state; @@ -144,6 +156,11 @@ struct dc_link { struct panel_cntl *panel_cntl; struct link_encoder *link_enc; struct graphics_object_id link_id; + /* Endpoint type distinguishes display endpoints which do not have entries + * in the BIOS connector table from those that do. Helps when tracking link + * encoder to display endpoint assignments. + */ + enum display_endpoint_type ep_type; union ddi_channel_mapping ddi_channel_mapping; struct connector_device_tag_info device_tag; struct dpcd_caps dpcd_caps; @@ -259,7 +276,6 @@ enum dc_detect_reason { bool dc_link_detect(struct dc_link *dc_link, enum dc_detect_reason reason); bool dc_link_get_hpd_state(struct dc_link *dc_link); enum dc_status dc_link_allocate_mst_payload(struct pipe_ctx *pipe_ctx); -enum dc_status dc_link_reallocate_mst_payload(struct dc_link *link); /* Notify DC about DP RX Interrupt (aka Short Pulse Interrupt). * Return: diff --git a/drivers/gpu/drm/amd/display/dc/dc_stream.h b/drivers/gpu/drm/amd/display/dc/dc_stream.h index e747370fc43b..13dae7238a58 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_stream.h +++ b/drivers/gpu/drm/amd/display/dc/dc_stream.h @@ -130,12 +130,24 @@ union stream_update_flags { uint32_t raw; }; +struct test_pattern { + enum dp_test_pattern type; + enum dp_test_pattern_color_space color_space; + struct link_training_settings const *p_link_settings; + unsigned char const *p_custom_pattern; + unsigned int cust_pattern_size; +}; + struct dc_stream_state { // sink is deprecated, new code should not reference // this pointer struct dc_sink *sink; struct dc_link *link; + /* For dynamic link encoder assignment, update the link encoder assigned to + * a stream via the volatile dc_state rather than the static dc_link. + */ + struct link_encoder *link_enc; struct dc_panel_patch sink_patches; union display_content_support content_support; struct dc_crtc_timing timing; @@ -226,7 +238,8 @@ struct dc_stream_state { bool apply_seamless_boot_optimization; uint32_t stream_id; - bool is_dsc_enabled; + + struct test_pattern test_pattern; union stream_update_flags update_flags; bool has_non_synchronizable_pclk; @@ -264,6 +277,8 @@ struct dc_stream_update { struct dc_dsc_config *dsc_config; struct dc_transfer_func *func_shaper; struct dc_3dlut *lut3d_func; + + struct test_pattern *pending_test_pattern; }; bool dc_is_stream_unchanged( diff --git a/drivers/gpu/drm/amd/display/dc/dc_types.h b/drivers/gpu/drm/amd/display/dc/dc_types.h index 80757a0ea7c6..432754eaf10b 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_types.h +++ b/drivers/gpu/drm/amd/display/dc/dc_types.h @@ -113,6 +113,7 @@ struct dc_context { struct gpio_service *gpio_service; uint32_t dc_sink_id_count; uint32_t dc_stream_id_count; + uint32_t dc_edp_id_count; uint64_t fbc_gpu_addr; struct dc_dmub_srv *dmub_srv; @@ -687,7 +688,8 @@ enum dc_psr_state { PSR_STATE5, PSR_STATE5a, PSR_STATE5b, - PSR_STATE5c + PSR_STATE5c, + PSR_STATE_INVALID = 0xFF }; struct psr_config { @@ -934,4 +936,19 @@ enum dc_psr_version { DC_PSR_VERSION_UNSUPPORTED = 0xFFFFFFFF, }; +/* Possible values of display_endpoint_id.endpoint */ +enum display_endpoint_type { + DISPLAY_ENDPOINT_PHY = 0, /* Physical connector. */ + DISPLAY_ENDPOINT_UNKNOWN = -1 +}; + +/* Extends graphics_object_id with an additional member 'ep_type' for + * distinguishing between physical endpoints (with entries in BIOS connector table) and + * logical endpoints. + */ +struct display_endpoint_id { + struct graphics_object_id link_id; + enum display_endpoint_type ep_type; +}; + #endif /* DC_TYPES_H_ */ diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_abm.c b/drivers/gpu/drm/amd/display/dc/dce/dce_abm.c index 4e87e70237e3..874b132fe1d7 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dce_abm.c +++ b/drivers/gpu/drm/amd/display/dc/dce/dce_abm.c @@ -283,7 +283,7 @@ struct abm *dce_abm_create( const struct dce_abm_shift *abm_shift, const struct dce_abm_mask *abm_mask) { - struct dce_abm *abm_dce = kzalloc(sizeof(*abm_dce), GFP_KERNEL); + struct dce_abm *abm_dce = kzalloc(sizeof(*abm_dce), GFP_ATOMIC); if (abm_dce == NULL) { BREAK_TO_DEBUGGER(); diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_dmcu.c b/drivers/gpu/drm/amd/display/dc/dce/dce_dmcu.c index 4f864501e046..8cd841320ded 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dce_dmcu.c +++ b/drivers/gpu/drm/amd/display/dc/dce/dce_dmcu.c @@ -1133,7 +1133,7 @@ struct dmcu *dcn10_dmcu_create( const struct dce_dmcu_shift *dmcu_shift, const struct dce_dmcu_mask *dmcu_mask) { - struct dce_dmcu *dmcu_dce = kzalloc(sizeof(*dmcu_dce), GFP_KERNEL); + struct dce_dmcu *dmcu_dce = kzalloc(sizeof(*dmcu_dce), GFP_ATOMIC); if (dmcu_dce == NULL) { BREAK_TO_DEBUGGER(); @@ -1154,7 +1154,7 @@ struct dmcu *dcn20_dmcu_create( const struct dce_dmcu_shift *dmcu_shift, const struct dce_dmcu_mask *dmcu_mask) { - struct dce_dmcu *dmcu_dce = kzalloc(sizeof(*dmcu_dce), GFP_KERNEL); + struct dce_dmcu *dmcu_dce = kzalloc(sizeof(*dmcu_dce), GFP_ATOMIC); if (dmcu_dce == NULL) { BREAK_TO_DEBUGGER(); @@ -1175,7 +1175,7 @@ struct dmcu *dcn21_dmcu_create( const struct dce_dmcu_shift *dmcu_shift, const struct dce_dmcu_mask *dmcu_mask) { - struct dce_dmcu *dmcu_dce = kzalloc(sizeof(*dmcu_dce), GFP_KERNEL); + struct dce_dmcu *dmcu_dce = kzalloc(sizeof(*dmcu_dce), GFP_ATOMIC); if (dmcu_dce == NULL) { BREAK_TO_DEBUGGER(); diff --git a/drivers/gpu/drm/amd/display/dc/dce/dmub_psr.c b/drivers/gpu/drm/amd/display/dc/dce/dmub_psr.c index 15ed09b7a452..5e99553fcdd4 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dmub_psr.c +++ b/drivers/gpu/drm/amd/display/dc/dce/dmub_psr.c @@ -80,19 +80,26 @@ static enum dc_psr_state convert_psr_state(uint32_t raw_state) static void dmub_psr_get_state(struct dmub_psr *dmub, enum dc_psr_state *state) { struct dmub_srv *srv = dmub->ctx->dmub_srv->dmub; - uint32_t raw_state; + uint32_t raw_state = 0; + uint32_t retry_count = 0; enum dmub_status status; - // Send gpint command and wait for ack - status = dmub_srv_send_gpint_command(srv, DMUB_GPINT__GET_PSR_STATE, 0, 30); - - if (status == DMUB_STATUS_OK) { - // GPINT was executed, get response - dmub_srv_get_gpint_response(srv, &raw_state); - *state = convert_psr_state(raw_state); - } else - // Return invalid state when GPINT times out - *state = 0xFF; + do { + // Send gpint command and wait for ack + status = dmub_srv_send_gpint_command(srv, DMUB_GPINT__GET_PSR_STATE, 0, 30); + + if (status == DMUB_STATUS_OK) { + // GPINT was executed, get response + dmub_srv_get_gpint_response(srv, &raw_state); + *state = convert_psr_state(raw_state); + } else + // Return invalid state when GPINT times out + *state = PSR_STATE_INVALID; + + // Assert if max retry hit + if (retry_count >= 1000) + ASSERT(0); + } while (++retry_count <= 1000 && *state == PSR_STATE_INVALID); } /* @@ -277,6 +284,8 @@ static bool dmub_psr_copy_settings(struct dmub_psr *dmub, copy_settings_data->debug.u32All = 0; copy_settings_data->debug.bitfields.visual_confirm = dc->dc->debug.visual_confirm == VISUAL_CONFIRM_PSR; copy_settings_data->debug.bitfields.use_hw_lock_mgr = 1; + copy_settings_data->fec_enable_status = (link->fec_state == dc_link_fec_enabled); + copy_settings_data->fec_enable_delay_in100us = link->dc->debug.fec_enable_delay_in100us; dc_dmub_srv_cmd_queue(dc->dmub_srv, &cmd); dc_dmub_srv_cmd_execute(dc->dmub_srv); diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c index 804092f81f85..5ddeee96bf23 100644 --- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c +++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c @@ -48,6 +48,7 @@ #include "stream_encoder.h" #include "link_encoder.h" #include "link_hwss.h" +#include "dc_link_dp.h" #include "clock_source.h" #include "clk_mgr.h" #include "abm.h" @@ -1694,6 +1695,8 @@ void dce110_enable_accelerated_mode(struct dc *dc, struct dc_state *context) bool can_apply_edp_fast_boot = false; bool can_apply_seamless_boot = false; bool keep_edp_vdd_on = false; + DC_LOGGER_INIT(); + get_edp_links_with_sink(dc, edp_links_with_sink, &edp_with_sink_num); get_edp_links(dc, edp_links, &edp_num); @@ -1714,8 +1717,11 @@ void dce110_enable_accelerated_mode(struct dc *dc, struct dc_state *context) /* Set optimization flag on eDP stream*/ if (edp_stream_num && edp_link->link_status.link_active) { edp_stream = edp_streams[0]; - edp_stream->apply_edp_fast_boot_optimization = true; - can_apply_edp_fast_boot = true; + can_apply_edp_fast_boot = !is_edp_ilr_optimization_required(edp_stream->link, &edp_stream->timing); + edp_stream->apply_edp_fast_boot_optimization = can_apply_edp_fast_boot; + if (can_apply_edp_fast_boot) + DC_LOG_EVENT_LINK_TRAINING("eDP fast boot disabled to optimize link rate\n"); + break; } } @@ -1846,8 +1852,7 @@ void dce110_set_safe_displaymarks( ******************************************************************************/ static void set_drr(struct pipe_ctx **pipe_ctx, - int num_pipes, unsigned int vmin, unsigned int vmax, - unsigned int vmid, unsigned int vmid_frame_number) + int num_pipes, struct dc_crtc_timing_adjust adjust) { int i = 0; struct drr_params params = {0}; @@ -1856,8 +1861,8 @@ static void set_drr(struct pipe_ctx **pipe_ctx, // Note DRR trigger events are generated regardless of whether num frames met. unsigned int num_frames = 2; - params.vertical_total_max = vmax; - params.vertical_total_min = vmin; + params.vertical_total_max = adjust.v_total_max; + params.vertical_total_min = adjust.v_total_min; /* TODO: If multiple pipes are to be supported, you need * some GSL stuff. Static screen triggers may be programmed differently @@ -1867,7 +1872,7 @@ static void set_drr(struct pipe_ctx **pipe_ctx, pipe_ctx[i]->stream_res.tg->funcs->set_drr( pipe_ctx[i]->stream_res.tg, ¶ms); - if (vmax != 0 && vmin != 0) + if (adjust.v_total_max != 0 && adjust.v_total_min != 0) pipe_ctx[i]->stream_res.tg->funcs->set_static_screen_control( pipe_ctx[i]->stream_res.tg, event_triggers, num_frames); diff --git a/drivers/gpu/drm/amd/display/dc/dce80/dce80_resource.c b/drivers/gpu/drm/amd/display/dc/dce80/dce80_resource.c index 612450f99278..725d92e40cd3 100644 --- a/drivers/gpu/drm/amd/display/dc/dce80/dce80_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dce80/dce80_resource.c @@ -526,7 +526,7 @@ static struct output_pixel_processor *dce80_opp_create( return &opp->base; } -struct dce_aux *dce80_aux_engine_create( +static struct dce_aux *dce80_aux_engine_create( struct dc_context *ctx, uint32_t inst) { @@ -564,7 +564,7 @@ static const struct dce_i2c_mask i2c_masks = { I2C_COMMON_MASK_SH_LIST_DCE_COMMON_BASE(_MASK) }; -struct dce_i2c_hw *dce80_i2c_hw_create( +static struct dce_i2c_hw *dce80_i2c_hw_create( struct dc_context *ctx, uint32_t inst) { @@ -580,7 +580,7 @@ struct dce_i2c_hw *dce80_i2c_hw_create( return dce_i2c_hw; } -struct dce_i2c_sw *dce80_i2c_sw_create( +static struct dce_i2c_sw *dce80_i2c_sw_create( struct dc_context *ctx) { struct dce_i2c_sw *dce_i2c_sw = @@ -714,7 +714,7 @@ static const struct encoder_feature_support link_enc_feature = { .flags.bits.IS_TPS3_CAPABLE = true }; -struct link_encoder *dce80_link_encoder_create( +static struct link_encoder *dce80_link_encoder_create( const struct encoder_init_data *enc_init_data) { struct dce110_link_encoder *enc110 = @@ -753,7 +753,7 @@ static struct panel_cntl *dce80_panel_cntl_create(const struct panel_cntl_init_d return &panel_cntl->base; } -struct clock_source *dce80_clock_source_create( +static struct clock_source *dce80_clock_source_create( struct dc_context *ctx, struct dc_bios *bios, enum clock_source_id id, @@ -777,7 +777,7 @@ struct clock_source *dce80_clock_source_create( return NULL; } -void dce80_clock_source_destroy(struct clock_source **clk_src) +static void dce80_clock_source_destroy(struct clock_source **clk_src) { kfree(TO_DCE110_CLK_SRC(*clk_src)); *clk_src = NULL; @@ -867,7 +867,7 @@ static void dce80_resource_destruct(struct dce110_resource_pool *pool) } } -bool dce80_validate_bandwidth( +static bool dce80_validate_bandwidth( struct dc *dc, struct dc_state *context, bool fast_validate) @@ -912,7 +912,7 @@ static bool dce80_validate_surface_sets( return true; } -enum dc_status dce80_validate_global( +static enum dc_status dce80_validate_global( struct dc *dc, struct dc_state *context) { diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c index 9eb33eae0e81..7c939c0a977b 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c @@ -1893,7 +1893,7 @@ uint64_t reduceSizeAndFraction( num = *numerator; denom = *denominator; for (i = 0; i < count; i++) { - uint32_t num_reminder, denom_reminder; + uint32_t num_remainder, denom_remainder; uint64_t num_result, denom_result; if (checkUint32Bounary && num <= max_int32 && denom <= max_int32) { @@ -1901,13 +1901,13 @@ uint64_t reduceSizeAndFraction( break; } do { - num_result = div_u64_rem(num, prime_numbers[i], &num_reminder); - denom_result = div_u64_rem(denom, prime_numbers[i], &denom_reminder); - if (num_reminder == 0 && denom_reminder == 0) { + num_result = div_u64_rem(num, prime_numbers[i], &num_remainder); + denom_result = div_u64_rem(denom, prime_numbers[i], &denom_remainder); + if (num_remainder == 0 && denom_remainder == 0) { num = num_result; denom = denom_result; } - } while (num_reminder == 0 && denom_reminder == 0); + } while (num_remainder == 0 && denom_remainder == 0); } *numerator = num; *denominator = denom; @@ -3271,8 +3271,7 @@ void dcn10_optimize_bandwidth( } void dcn10_set_drr(struct pipe_ctx **pipe_ctx, - int num_pipes, unsigned int vmin, unsigned int vmax, - unsigned int vmid, unsigned int vmid_frame_number) + int num_pipes, struct dc_crtc_timing_adjust adjust) { int i = 0; struct drr_params params = {0}; @@ -3281,11 +3280,10 @@ void dcn10_set_drr(struct pipe_ctx **pipe_ctx, // Note DRR trigger events are generated regardless of whether num frames met. unsigned int num_frames = 2; - params.vertical_total_max = vmax; - params.vertical_total_min = vmin; - params.vertical_total_mid = vmid; - params.vertical_total_mid_frame_num = vmid_frame_number; - + params.vertical_total_max = adjust.v_total_max; + params.vertical_total_min = adjust.v_total_min; + params.vertical_total_mid = adjust.v_total_mid; + params.vertical_total_mid_frame_num = adjust.v_total_mid_frame_num; /* TODO: If multiple pipes are to be supported, you need * some GSL stuff. Static screen triggers may be programmed differently * as well. @@ -3293,7 +3291,7 @@ void dcn10_set_drr(struct pipe_ctx **pipe_ctx, for (i = 0; i < num_pipes; i++) { pipe_ctx[i]->stream_res.tg->funcs->set_drr( pipe_ctx[i]->stream_res.tg, ¶ms); - if (vmax != 0 && vmin != 0) + if (adjust.v_total_max != 0 && adjust.v_total_min != 0) pipe_ctx[i]->stream_res.tg->funcs->set_static_screen_control( pipe_ctx[i]->stream_res.tg, event_triggers, num_frames); @@ -3981,3 +3979,19 @@ void dcn10_get_clock(struct dc *dc, dc->clk_mgr->funcs->get_clock(dc->clk_mgr, context, clock_type, clock_cfg); } + +void dcn10_get_dcc_en_bits(struct dc *dc, int *dcc_en_bits) +{ + struct resource_pool *pool = dc->res_pool; + int i; + + for (i = 0; i < pool->pipe_count; i++) { + struct hubp *hubp = pool->hubps[i]; + struct dcn_hubp_state *s = &(TO_DCN10_HUBP(hubp)->state); + + hubp->funcs->hubp_read_state(hubp); + + if (!s->blank_en) + dcc_en_bits[i] = s->dcc_en ? 1 : 0; + } +} diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.h index e0800cd1cc02..37bec421fde8 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.h +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.h @@ -1,5 +1,5 @@ /* -* Copyright 2016 Advanced Micro Devices, Inc. +* Copyright 2016-2020 Advanced Micro Devices, Inc. * * Permission is hereby granted, free of charge, to any person obtaining a * copy of this software and associated documentation files (the "Software"), @@ -145,8 +145,7 @@ bool dcn10_dummy_display_power_gating( struct dc_bios *dcb, enum pipe_gating_control power_gating); void dcn10_set_drr(struct pipe_ctx **pipe_ctx, - int num_pipes, unsigned int vmin, unsigned int vmax, - unsigned int vmid, unsigned int vmid_frame_number); + int num_pipes, struct dc_crtc_timing_adjust adjust); void dcn10_get_position(struct pipe_ctx **pipe_ctx, int num_pipes, struct crtc_position *position); @@ -210,4 +209,6 @@ void dcn10_wait_for_pending_cleared(struct dc *dc, void dcn10_set_hdr_multiplier(struct pipe_ctx *pipe_ctx); void dcn10_verify_allow_pstate_change_high(struct dc *dc); +void dcn10_get_dcc_en_bits(struct dc *dc, int *dcc_en_bits); + #endif /* __DC_HWSS_DCN10_H__ */ diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_init.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_init.c index 254300b06b43..d532c78ee764 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_init.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_init.c @@ -1,5 +1,5 @@ /* - * Copyright 2016 Advanced Micro Devices, Inc. + * Copyright 2016-2020 Advanced Micro Devices, Inc. * * Permission is hereby granted, free of charge, to any person obtaining a * copy of this software and associated documentation files (the "Software"), @@ -79,6 +79,7 @@ static const struct hw_sequencer_funcs dcn10_funcs = { .set_backlight_level = dce110_set_backlight_level, .set_abm_immediate_disable = dce110_set_abm_immediate_disable, .set_pipe = dce110_set_pipe, + .get_dcc_en_bits = dcn10_get_dcc_en_bits, }; static const struct hwseq_private_funcs dcn10_private_funcs = { diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.c index 6138f4887de7..677663cc7bff 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.c @@ -132,6 +132,22 @@ void optc1_setup_vertical_interrupt2( } /** + * Vupdate keepout can be set to a window to block the update lock for that pipe from changing. + * Start offset begins with vstartup and goes for x number of clocks, + * end offset starts from end of vupdate to x number of clocks. + */ +void optc1_set_vupdate_keepout(struct timing_generator *optc, + struct vupdate_keepout_params *params) +{ + struct optc *optc1 = DCN10TG_FROM_TG(optc); + + REG_SET_3(OTG_VUPDATE_KEEPOUT, 0, + MASTER_UPDATE_LOCK_VUPDATE_KEEPOUT_START_OFFSET, params->start_offset, + MASTER_UPDATE_LOCK_VUPDATE_KEEPOUT_END_OFFSET, params->end_offset, + OTG_MASTER_UPDATE_LOCK_VUPDATE_KEEPOUT_EN, params->enable); +} + +/** * program_timing_generator used by mode timing set * Program CRTC Timing Registers - OTG_H_*, OTG_V_*, Pixel repetition. * Including SYNC. Call BIOS command table to program Timings. diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.h index 2529723beeb1..cabfe83fd634 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.h +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.h @@ -194,6 +194,9 @@ struct dcn_optc_registers { SF(OTG0_OTG_DOUBLE_BUFFER_CONTROL, OTG_UPDATE_PENDING, mask_sh),\ SF(OTG0_OTG_DOUBLE_BUFFER_CONTROL, OTG_BLANK_DATA_DOUBLE_BUFFER_EN, mask_sh),\ SF(OTG0_OTG_DOUBLE_BUFFER_CONTROL, OTG_RANGE_TIMING_DBUF_UPDATE_MODE, mask_sh),\ + SF(OTG0_OTG_VUPDATE_KEEPOUT, OTG_MASTER_UPDATE_LOCK_VUPDATE_KEEPOUT_EN, mask_sh), \ + SF(OTG0_OTG_VUPDATE_KEEPOUT, MASTER_UPDATE_LOCK_VUPDATE_KEEPOUT_START_OFFSET, mask_sh), \ + SF(OTG0_OTG_VUPDATE_KEEPOUT, MASTER_UPDATE_LOCK_VUPDATE_KEEPOUT_END_OFFSET, mask_sh), \ SF(OTG0_OTG_H_TOTAL, OTG_H_TOTAL, mask_sh),\ SF(OTG0_OTG_H_BLANK_START_END, OTG_H_BLANK_START, mask_sh),\ SF(OTG0_OTG_H_BLANK_START_END, OTG_H_BLANK_END, mask_sh),\ diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c index d079f4e491e5..f962b905e79e 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c @@ -82,7 +82,7 @@ const struct _vcs_dpi_ip_params_st dcn1_0_ip = { .meta_chunk_size_kbytes = 2, .writeback_chunk_size_kbytes = 2, .line_buffer_size_bits = 589824, - .max_line_buffer_lines = 32, + .max_line_buffer_lines = 12, .IsLineBufferBppFixed = 0, .LineBufferFixedBpp = -1, .writeback_luma_buffer_size_kbytes = 12, @@ -619,7 +619,6 @@ static const struct dc_debug_options debug_defaults_drv = { .recovery_enabled = false, /*enable this by default after testing.*/ .max_downscale_src_width = 3840, .underflow_assert_delay_us = 0xFFFFFFFF, - .use_max_lb = true }; static const struct dc_debug_options debug_defaults_diags = { @@ -631,7 +630,6 @@ static const struct dc_debug_options debug_defaults_diags = { .disable_pplib_clock_request = true, .disable_pplib_wm_range = true, .underflow_assert_delay_us = 0xFFFFFFFF, - .use_max_lb = true }; static void dcn10_dpp_destroy(struct dpp **dpp) diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dccg.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dccg.c index 62cc2651e00c..8774406120fc 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dccg.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dccg.c @@ -112,7 +112,7 @@ struct dccg *dccg2_create( const struct dccg_shift *dccg_shift, const struct dccg_mask *dccg_mask) { - struct dcn_dccg *dccg_dcn = kzalloc(sizeof(*dccg_dcn), GFP_KERNEL); + struct dcn_dccg *dccg_dcn = kzalloc(sizeof(*dccg_dcn), GFP_ATOMIC); struct dccg *base; if (dccg_dcn == NULL) { diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c index bec7059f6d5d..a1318c31bcfa 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c @@ -1,5 +1,5 @@ /* - * Copyright 2012-17 Advanced Micro Devices, Inc. + * Copyright 2012-2021 Advanced Micro Devices, Inc. * * Permission is hereby granted, free of charge, to any person obtaining a * copy of this software and associated documentation files (the "Software"), @@ -181,11 +181,14 @@ void hubp2_vready_at_or_After_vsync(struct hubp *hubp, else Set HUBP_VREADY_AT_OR_AFTER_VSYNC = 0 */ - if ((pipe_dest->vstartup_start - (pipe_dest->vready_offset+pipe_dest->vupdate_width - + pipe_dest->vupdate_offset) / pipe_dest->htotal) <= pipe_dest->vblank_end) { - value = 1; - } else - value = 0; + if (pipe_dest->htotal != 0) { + if ((pipe_dest->vstartup_start - (pipe_dest->vready_offset+pipe_dest->vupdate_width + + pipe_dest->vupdate_offset) / pipe_dest->htotal) <= pipe_dest->vblank_end) { + value = 1; + } else + value = 0; + } + REG_UPDATE(DCHUBP_CNTL, HUBP_VREADY_AT_OR_AFTER_VSYNC, value); } diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_init.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_init.c index 7218ed9e43dc..b5bb613eed4d 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_init.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_init.c @@ -95,6 +95,7 @@ static const struct hw_sequencer_funcs dcn20_funcs = { .optimize_timing_for_fsft = dcn20_optimize_timing_for_fsft, #endif .set_disp_pattern_generator = dcn20_set_disp_pattern_generator, + .get_dcc_en_bits = dcn10_get_dcc_en_bits, }; static const struct hwseq_private_funcs dcn20_private_funcs = { diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_link_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_link_encoder.c index fa013496e26b..2f9bfaeaba8d 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_link_encoder.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_link_encoder.c @@ -341,8 +341,7 @@ void enc2_hw_init(struct link_encoder *enc) } else { AUX_REG_WRITE(AUX_DPHY_RX_CONTROL0, 0x103d1110); - AUX_REG_WRITE(AUX_DPHY_TX_CONTROL, 0x21c4d); - + AUX_REG_WRITE(AUX_DPHY_TX_CONTROL, 0x21c7a); } //AUX_DPHY_TX_REF_CONTROL'AUX_TX_REF_DIV HW default is 0x32; diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_optc.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_optc.c index ea7eaf7d755f..3139d90017ee 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_optc.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_optc.c @@ -134,22 +134,6 @@ void optc2_set_gsl_window(struct timing_generator *optc, OTG_GSL_WINDOW_END_Y, params->gsl_window_end_y); } -/** - * Vupdate keepout can be set to a window to block the update lock for that pipe from changing. - * Start offset begins with vstartup and goes for x number of clocks, - * end offset starts from end of vupdate to x number of clocks. - */ -void optc2_set_vupdate_keepout(struct timing_generator *optc, - const struct vupdate_keepout_params *params) -{ - struct optc *optc1 = DCN10TG_FROM_TG(optc); - - REG_SET_3(OTG_VUPDATE_KEEPOUT, 0, - MASTER_UPDATE_LOCK_VUPDATE_KEEPOUT_START_OFFSET, params->start_offset, - MASTER_UPDATE_LOCK_VUPDATE_KEEPOUT_END_OFFSET, params->end_offset, - OTG_MASTER_UPDATE_LOCK_VUPDATE_KEEPOUT_EN, params->enable); -} - void optc2_set_gsl_source_select( struct timing_generator *optc, int group_idx, diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_optc.h b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_optc.h index e0a0a8a8e2c6..3dee2ec2a1bb 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_optc.h +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_optc.h @@ -56,9 +56,6 @@ SF(OTG0_OTG_GSL_WINDOW_X, OTG_GSL_WINDOW_END_X, mask_sh), \ SF(OTG0_OTG_GSL_WINDOW_Y, OTG_GSL_WINDOW_START_Y, mask_sh),\ SF(OTG0_OTG_GSL_WINDOW_Y, OTG_GSL_WINDOW_END_Y, mask_sh),\ - SF(OTG0_OTG_VUPDATE_KEEPOUT, OTG_MASTER_UPDATE_LOCK_VUPDATE_KEEPOUT_EN, mask_sh), \ - SF(OTG0_OTG_VUPDATE_KEEPOUT, MASTER_UPDATE_LOCK_VUPDATE_KEEPOUT_START_OFFSET, mask_sh), \ - SF(OTG0_OTG_VUPDATE_KEEPOUT, MASTER_UPDATE_LOCK_VUPDATE_KEEPOUT_END_OFFSET, mask_sh), \ SF(OTG0_OTG_GSL_CONTROL, OTG_GSL_MASTER_MODE, mask_sh), \ SF(OTG0_OTG_GSL_CONTROL, OTG_MASTER_UPDATE_LOCK_GSL_EN, mask_sh), \ SF(OTG0_OTG_DSC_START_POSITION, OTG_DSC_START_POSITION_X, mask_sh), \ diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c index 2307b3517821..527e56c353cb 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c @@ -112,7 +112,7 @@ struct _vcs_dpi_ip_params_st dcn2_0_ip = { .is_line_buffer_bpp_fixed = 0, .line_buffer_fixed_bpp = 0, .dcc_supported = true, - .max_line_buffer_lines = 32, + .max_line_buffer_lines = 12, .writeback_luma_buffer_size_kbytes = 12, .writeback_chroma_buffer_size_kbytes = 8, .writeback_chroma_line_buffer_width_pixels = 4, @@ -180,7 +180,7 @@ static struct _vcs_dpi_ip_params_st dcn2_0_nv14_ip = { .is_line_buffer_bpp_fixed = 0, .line_buffer_fixed_bpp = 0, .dcc_supported = true, - .max_line_buffer_lines = 32, + .max_line_buffer_lines = 12, .writeback_luma_buffer_size_kbytes = 12, .writeback_chroma_buffer_size_kbytes = 8, .writeback_chroma_line_buffer_width_pixels = 4, @@ -1075,7 +1075,6 @@ static const struct dc_debug_options debug_defaults_drv = { .scl_reset_length10 = true, .sanity_checks = false, .underflow_assert_delay_us = 0xFFFFFFFF, - .use_max_lb = true }; static const struct dc_debug_options debug_defaults_diags = { @@ -1092,7 +1091,6 @@ static const struct dc_debug_options debug_defaults_diags = { .scl_reset_length10 = true, .underflow_assert_delay_us = 0xFFFFFFFF, .enable_tri_buf = true, - .use_max_lb = true }; void dcn20_dpp_destroy(struct dpp **dpp) @@ -1106,7 +1104,7 @@ struct dpp *dcn20_dpp_create( uint32_t inst) { struct dcn20_dpp *dpp = - kzalloc(sizeof(struct dcn20_dpp), GFP_KERNEL); + kzalloc(sizeof(struct dcn20_dpp), GFP_ATOMIC); if (!dpp) return NULL; @@ -1124,7 +1122,7 @@ struct input_pixel_processor *dcn20_ipp_create( struct dc_context *ctx, uint32_t inst) { struct dcn10_ipp *ipp = - kzalloc(sizeof(struct dcn10_ipp), GFP_KERNEL); + kzalloc(sizeof(struct dcn10_ipp), GFP_ATOMIC); if (!ipp) { BREAK_TO_DEBUGGER(); @@ -1141,7 +1139,7 @@ struct output_pixel_processor *dcn20_opp_create( struct dc_context *ctx, uint32_t inst) { struct dcn20_opp *opp = - kzalloc(sizeof(struct dcn20_opp), GFP_KERNEL); + kzalloc(sizeof(struct dcn20_opp), GFP_ATOMIC); if (!opp) { BREAK_TO_DEBUGGER(); @@ -1158,7 +1156,7 @@ struct dce_aux *dcn20_aux_engine_create( uint32_t inst) { struct aux_engine_dce110 *aux_engine = - kzalloc(sizeof(struct aux_engine_dce110), GFP_KERNEL); + kzalloc(sizeof(struct aux_engine_dce110), GFP_ATOMIC); if (!aux_engine) return NULL; @@ -1196,7 +1194,7 @@ struct dce_i2c_hw *dcn20_i2c_hw_create( uint32_t inst) { struct dce_i2c_hw *dce_i2c_hw = - kzalloc(sizeof(struct dce_i2c_hw), GFP_KERNEL); + kzalloc(sizeof(struct dce_i2c_hw), GFP_ATOMIC); if (!dce_i2c_hw) return NULL; @@ -1209,7 +1207,7 @@ struct dce_i2c_hw *dcn20_i2c_hw_create( struct mpc *dcn20_mpc_create(struct dc_context *ctx) { struct dcn20_mpc *mpc20 = kzalloc(sizeof(struct dcn20_mpc), - GFP_KERNEL); + GFP_ATOMIC); if (!mpc20) return NULL; @@ -1227,7 +1225,7 @@ struct hubbub *dcn20_hubbub_create(struct dc_context *ctx) { int i; struct dcn20_hubbub *hubbub = kzalloc(sizeof(struct dcn20_hubbub), - GFP_KERNEL); + GFP_ATOMIC); if (!hubbub) return NULL; @@ -1255,7 +1253,7 @@ struct timing_generator *dcn20_timing_generator_create( uint32_t instance) { struct optc *tgn10 = - kzalloc(sizeof(struct optc), GFP_KERNEL); + kzalloc(sizeof(struct optc), GFP_ATOMIC); if (!tgn10) return NULL; @@ -1334,7 +1332,7 @@ static struct clock_source *dcn20_clock_source_create( bool dp_clk_src) { struct dce110_clk_src *clk_src = - kzalloc(sizeof(struct dce110_clk_src), GFP_KERNEL); + kzalloc(sizeof(struct dce110_clk_src), GFP_ATOMIC); if (!clk_src) return NULL; @@ -1440,7 +1438,7 @@ struct display_stream_compressor *dcn20_dsc_create( struct dc_context *ctx, uint32_t inst) { struct dcn20_dsc *dsc = - kzalloc(sizeof(struct dcn20_dsc), GFP_KERNEL); + kzalloc(sizeof(struct dcn20_dsc), GFP_ATOMIC); if (!dsc) { BREAK_TO_DEBUGGER(); @@ -1574,7 +1572,7 @@ struct hubp *dcn20_hubp_create( uint32_t inst) { struct dcn20_hubp *hubp2 = - kzalloc(sizeof(struct dcn20_hubp), GFP_KERNEL); + kzalloc(sizeof(struct dcn20_hubp), GFP_ATOMIC); if (!hubp2) return NULL; @@ -2203,10 +2201,11 @@ int dcn20_populate_dml_pipes_from_context( pipes[pipe_cnt].dout.output_bpp = (output_bpc * 3.0) / 2; break; case PIXEL_ENCODING_YCBCR422: - if (true) /* todo */ - pipes[pipe_cnt].dout.output_format = dm_s422; - else + if (res_ctx->pipe_ctx[i].stream->timing.flags.DSC && + !res_ctx->pipe_ctx[i].stream->timing.dsc_cfg.ycbcr422_simple) pipes[pipe_cnt].dout.output_format = dm_n422; + else + pipes[pipe_cnt].dout.output_format = dm_s422; pipes[pipe_cnt].dout.output_bpp = output_bpc * 2; break; default: @@ -2218,7 +2217,7 @@ int dcn20_populate_dml_pipes_from_context( pipes[pipe_cnt].dout.output_bpp = res_ctx->pipe_ctx[i].stream->timing.dsc_cfg.bits_per_pixel / 16.0; /* todo: default max for now, until there is logic reflecting this in dc*/ - pipes[pipe_cnt].dout.output_bpc = 12; + pipes[pipe_cnt].dout.dsc_input_bpc = 12; /*fill up the audio sample rate (unit in kHz)*/ get_audio_check(&res_ctx->pipe_ctx[i].stream->audio_info, &aud_check); pipes[pipe_cnt].dout.max_audio_sample_rate = aud_check.max_audiosample_rate / 1000; @@ -3396,7 +3395,7 @@ bool dcn20_mmhubbub_create(struct dc_context *ctx, struct resource_pool *pool) static struct pp_smu_funcs *dcn20_pp_smu_create(struct dc_context *ctx) { - struct pp_smu_funcs *pp_smu = kzalloc(sizeof(*pp_smu), GFP_KERNEL); + struct pp_smu_funcs *pp_smu = kzalloc(sizeof(*pp_smu), GFP_ATOMIC); if (!pp_smu) return pp_smu; @@ -4042,7 +4041,7 @@ struct resource_pool *dcn20_create_resource_pool( struct dc *dc) { struct dcn20_resource_pool *pool = - kzalloc(sizeof(struct dcn20_resource_pool), GFP_KERNEL); + kzalloc(sizeof(struct dcn20_resource_pool), GFP_ATOMIC); if (!pool) return NULL; diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hwseq.c index d3b643089603..8fccee5a3036 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hwseq.c @@ -218,6 +218,8 @@ bool dcn21_set_backlight_level(struct pipe_ctx *pipe_ctx, cmd.abm_set_backlight.header.sub_type = DMUB_CMD__ABM_SET_BACKLIGHT; cmd.abm_set_backlight.abm_set_backlight_data.frame_ramp = frame_ramp; cmd.abm_set_backlight.abm_set_backlight_data.backlight_user_level = backlight_pwm_u16_16; + cmd.abm_set_backlight.abm_set_backlight_data.version = DMUB_CMD_ABM_SET_BACKLIGHT_VERSION_1; + cmd.abm_set_backlight.abm_set_backlight_data.panel_mask = (0x01 << panel_cntl->inst); cmd.abm_set_backlight.header.payload_bytes = sizeof(struct dmub_cmd_abm_set_backlight_data); dc_dmub_srv_cmd_queue(dc->dmub_srv, &cmd); diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_init.c b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_init.c index 074e2713257f..4f20a85ff396 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_init.c +++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_init.c @@ -1,5 +1,5 @@ /* - * Copyright 2016 Advanced Micro Devices, Inc. + * Copyright 2016-2020 Advanced Micro Devices, Inc. * * Permission is hereby granted, free of charge, to any person obtaining a * copy of this software and associated documentation files (the "Software"), @@ -99,6 +99,7 @@ static const struct hw_sequencer_funcs dcn21_funcs = { #endif .is_abm_supported = dcn21_is_abm_supported, .set_disp_pattern_generator = dcn20_set_disp_pattern_generator, + .get_dcc_en_bits = dcn10_get_dcc_en_bits, }; static const struct hwseq_private_funcs dcn21_private_funcs = { diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c index e62f931fc269..8e3f1d0b4cc3 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c @@ -55,7 +55,6 @@ #include "dce/dce_audio.h" #include "dce/dce_hwseq.h" #include "virtual/virtual_stream_encoder.h" -#include "dce110/dce110_resource.h" #include "dml/display_mode_vba.h" #include "dcn20/dcn20_dccg.h" #include "dcn21/dcn21_dccg.h" @@ -115,7 +114,7 @@ struct _vcs_dpi_ip_params_st dcn2_1_ip = { .is_line_buffer_bpp_fixed = 0, .line_buffer_fixed_bpp = 0, .dcc_supported = true, - .max_line_buffer_lines = 32, + .max_line_buffer_lines = 12, .writeback_luma_buffer_size_kbytes = 12, .writeback_chroma_buffer_size_kbytes = 8, .writeback_chroma_line_buffer_width_pixels = 4, diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hubp.h b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hubp.h index 705fbfc37502..8a32772d4e91 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hubp.h +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hubp.h @@ -134,6 +134,7 @@ HUBP_SF(HUBPREQ0_DCSURF_SURFACE_CONTROL, SECONDARY_SURFACE_DCC_EN, mask_sh),\ HUBP_SF(HUBPREQ0_DCSURF_SURFACE_CONTROL, SECONDARY_SURFACE_DCC_IND_BLK, mask_sh),\ HUBP_SF(HUBPREQ0_DCSURF_SURFACE_CONTROL, SECONDARY_SURFACE_DCC_IND_BLK_C, mask_sh),\ + HUBP_SF(HUBPREQ0_DCSURF_SURFACE_FLIP_INTERRUPT, SURFACE_FLIP_INT_MASK, mask_sh),\ HUBP_SF(HUBPRET0_HUBPRET_CONTROL, DET_BUF_PLANE1_BASE_ADDRESS, mask_sh),\ HUBP_SF(HUBPRET0_HUBPRET_CONTROL, CROSSBAR_SRC_CB_B, mask_sh),\ HUBP_SF(HUBPRET0_HUBPRET_CONTROL, CROSSBAR_SRC_CR_R, mask_sh),\ diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_init.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_init.c index c4c14e9c1309..bf7fa98b39eb 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_init.c +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_init.c @@ -1,5 +1,5 @@ /* - * Copyright 2020 Advanced Micro Devices, Inc. + * Copyright 2016-2020 Advanced Micro Devices, Inc. * * Permission is hereby granted, free of charge, to any person obtaining a * copy of this software and associated documentation files (the "Software"), @@ -98,6 +98,7 @@ static const struct hw_sequencer_funcs dcn30_funcs = { .hardware_release = dcn30_hardware_release, .set_pipe = dcn21_set_pipe, .set_disp_pattern_generator = dcn30_set_disp_pattern_generator, + .get_dcc_en_bits = dcn10_get_dcc_en_bits, }; static const struct hwseq_private_funcs dcn30_private_funcs = { diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c index 263c2986682d..4a5fa23d8e7b 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c @@ -120,7 +120,7 @@ struct _vcs_dpi_ip_params_st dcn3_0_ip = { .dcc_supported = true, .writeback_interface_buffer_size_kbytes = 90, .writeback_line_buffer_buffer_size = 0, - .max_line_buffer_lines = 32, + .max_line_buffer_lines = 12, .writeback_luma_buffer_size_kbytes = 12, // writeback_line_buffer_buffer_size = 656640 .writeback_chroma_buffer_size_kbytes = 8, .writeback_chroma_line_buffer_width_pixels = 4, diff --git a/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_init.c b/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_init.c index bdad72140cbc..70b053d9ba40 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_init.c +++ b/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_init.c @@ -1,5 +1,5 @@ /* - * Copyright 2020 Advanced Micro Devices, Inc. + * Copyright 2016-2020 Advanced Micro Devices, Inc. * * Permission is hereby granted, free of charge, to any person obtaining a * copy of this software and associated documentation files (the "Software"), @@ -98,6 +98,9 @@ static const struct hw_sequencer_funcs dcn301_funcs = { .set_abm_immediate_disable = dcn21_set_abm_immediate_disable, .set_pipe = dcn21_set_pipe, .set_disp_pattern_generator = dcn30_set_disp_pattern_generator, + .get_dcc_en_bits = dcn10_get_dcc_en_bits, + .optimize_pwr_state = dcn21_optimize_pwr_state, + .exit_optimized_pwr_state = dcn21_exit_optimized_pwr_state, }; static const struct hwseq_private_funcs dcn301_private_funcs = { diff --git a/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_resource.c b/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_resource.c index 622a5bf9737f..5b54b7fc5105 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_resource.c @@ -1,5 +1,5 @@ /* - * Copyright 2020 Advanced Micro Devices, Inc. + * Copyright 2019-2021 Advanced Micro Devices, Inc. * * Permission is hereby granted, free of charge, to any person obtaining a * copy of this software and associated documentation files (the "Software"), @@ -116,7 +116,7 @@ struct _vcs_dpi_ip_params_st dcn3_01_ip = { .dcc_supported = true, .writeback_interface_buffer_size_kbytes = 90, .writeback_line_buffer_buffer_size = 656640, - .max_line_buffer_lines = 32, + .max_line_buffer_lines = 12, .writeback_luma_buffer_size_kbytes = 12, // writeback_line_buffer_buffer_size = 656640 .writeback_chroma_buffer_size_kbytes = 8, .writeback_chroma_line_buffer_width_pixels = 4, diff --git a/drivers/gpu/drm/amd/display/dc/dcn302/dcn302_resource.c b/drivers/gpu/drm/amd/display/dc/dcn302/dcn302_resource.c index 0723e29fd42e..fc2dea243d1b 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn302/dcn302_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn302/dcn302_resource.c @@ -101,7 +101,7 @@ struct _vcs_dpi_ip_params_st dcn3_02_ip = { .dcc_supported = true, .writeback_interface_buffer_size_kbytes = 90, .writeback_line_buffer_buffer_size = 0, - .max_line_buffer_lines = 32, + .max_line_buffer_lines = 12, .writeback_luma_buffer_size_kbytes = 12, // writeback_line_buffer_buffer_size = 656640 .writeback_chroma_buffer_size_kbytes = 8, .writeback_chroma_line_buffer_width_pixels = 4, @@ -164,7 +164,7 @@ struct _vcs_dpi_soc_bounding_box_st dcn3_02_soc = { .min_dcfclk = 500.0, /* TODO: set this to actual min DCFCLK */ .num_states = 1, - .sr_exit_time_us = 12, + .sr_exit_time_us = 15.5, .sr_enter_plus_exit_time_us = 20, .urgent_latency_us = 4.0, .urgent_latency_pixel_data_only_us = 4.0, diff --git a/drivers/gpu/drm/amd/display/dc/dm_helpers.h b/drivers/gpu/drm/amd/display/dc/dm_helpers.h index f41db27c44de..7617fab9e1f9 100644 --- a/drivers/gpu/drm/amd/display/dc/dm_helpers.h +++ b/drivers/gpu/drm/amd/display/dc/dm_helpers.h @@ -147,6 +147,8 @@ bool dm_helpers_dp_write_dsc_enable( bool dm_helpers_is_dp_sink_present( struct dc_link *link); +void dm_helpers_mst_enable_stream_features(const struct dc_stream_state *stream); + enum dc_edid_status dm_helpers_read_local_edid( struct dc_context *ctx, struct dc_link *link, diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20.c b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20.c index 72423dc425dc..799bae229e67 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20.c @@ -293,13 +293,31 @@ static void handle_det_buf_split(struct display_mode_lib *mode_lib, if (surf_linear) { log2_swath_height_l = 0; log2_swath_height_c = 0; - } else if (!surf_vert) { - log2_swath_height_l = dml_log2(rq_param->misc.rq_l.blk256_height) - req128_l; - log2_swath_height_c = dml_log2(rq_param->misc.rq_c.blk256_height) - req128_c; } else { - log2_swath_height_l = dml_log2(rq_param->misc.rq_l.blk256_width) - req128_l; - log2_swath_height_c = dml_log2(rq_param->misc.rq_c.blk256_width) - req128_c; + unsigned int swath_height_l; + unsigned int swath_height_c; + + if (!surf_vert) { + swath_height_l = rq_param->misc.rq_l.blk256_height; + swath_height_c = rq_param->misc.rq_c.blk256_height; + } else { + swath_height_l = rq_param->misc.rq_l.blk256_width; + swath_height_c = rq_param->misc.rq_c.blk256_width; + } + + if (swath_height_l > 0) + log2_swath_height_l = dml_log2(swath_height_l); + + if (req128_l && log2_swath_height_l > 0) + log2_swath_height_l -= 1; + + if (swath_height_c > 0) + log2_swath_height_c = dml_log2(swath_height_c); + + if (req128_c && log2_swath_height_c > 0) + log2_swath_height_c -= 1; } + rq_param->dlg.rq_l.swath_height = 1 << log2_swath_height_l; rq_param->dlg.rq_c.swath_height = 1 << log2_swath_height_c; diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20v2.c b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20v2.c index 9c78446c3a9d..6a6d5970d1d5 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20v2.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20v2.c @@ -293,13 +293,31 @@ static void handle_det_buf_split(struct display_mode_lib *mode_lib, if (surf_linear) { log2_swath_height_l = 0; log2_swath_height_c = 0; - } else if (!surf_vert) { - log2_swath_height_l = dml_log2(rq_param->misc.rq_l.blk256_height) - req128_l; - log2_swath_height_c = dml_log2(rq_param->misc.rq_c.blk256_height) - req128_c; } else { - log2_swath_height_l = dml_log2(rq_param->misc.rq_l.blk256_width) - req128_l; - log2_swath_height_c = dml_log2(rq_param->misc.rq_c.blk256_width) - req128_c; + unsigned int swath_height_l; + unsigned int swath_height_c; + + if (!surf_vert) { + swath_height_l = rq_param->misc.rq_l.blk256_height; + swath_height_c = rq_param->misc.rq_c.blk256_height; + } else { + swath_height_l = rq_param->misc.rq_l.blk256_width; + swath_height_c = rq_param->misc.rq_c.blk256_width; + } + + if (swath_height_l > 0) + log2_swath_height_l = dml_log2(swath_height_l); + + if (req128_l && log2_swath_height_l > 0) + log2_swath_height_l -= 1; + + if (swath_height_c > 0) + log2_swath_height_c = dml_log2(swath_height_c); + + if (req128_c && log2_swath_height_c > 0) + log2_swath_height_c -= 1; } + rq_param->dlg.rq_l.swath_height = 1 << log2_swath_height_l; rq_param->dlg.rq_c.swath_height = 1 << log2_swath_height_c; diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_rq_dlg_calc_21.c b/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_rq_dlg_calc_21.c index edd41d358291..dc1c81a6e377 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_rq_dlg_calc_21.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_rq_dlg_calc_21.c @@ -277,13 +277,31 @@ static void handle_det_buf_split( if (surf_linear) { log2_swath_height_l = 0; log2_swath_height_c = 0; - } else if (!surf_vert) { - log2_swath_height_l = dml_log2(rq_param->misc.rq_l.blk256_height) - req128_l; - log2_swath_height_c = dml_log2(rq_param->misc.rq_c.blk256_height) - req128_c; } else { - log2_swath_height_l = dml_log2(rq_param->misc.rq_l.blk256_width) - req128_l; - log2_swath_height_c = dml_log2(rq_param->misc.rq_c.blk256_width) - req128_c; + unsigned int swath_height_l; + unsigned int swath_height_c; + + if (!surf_vert) { + swath_height_l = rq_param->misc.rq_l.blk256_height; + swath_height_c = rq_param->misc.rq_c.blk256_height; + } else { + swath_height_l = rq_param->misc.rq_l.blk256_width; + swath_height_c = rq_param->misc.rq_c.blk256_width; + } + + if (swath_height_l > 0) + log2_swath_height_l = dml_log2(swath_height_l); + + if (req128_l && log2_swath_height_l > 0) + log2_swath_height_l -= 1; + + if (swath_height_c > 0) + log2_swath_height_c = dml_log2(swath_height_c); + + if (req128_c && log2_swath_height_c > 0) + log2_swath_height_c -= 1; } + rq_param->dlg.rq_l.swath_height = 1 << log2_swath_height_l; rq_param->dlg.rq_c.swath_height = 1 << log2_swath_height_c; diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_rq_dlg_calc_30.c b/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_rq_dlg_calc_30.c index 0f14f205ebe5..04601a767a8f 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_rq_dlg_calc_30.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_rq_dlg_calc_30.c @@ -237,13 +237,31 @@ static void handle_det_buf_split(struct display_mode_lib *mode_lib, if (surf_linear) { log2_swath_height_l = 0; log2_swath_height_c = 0; - } else if (!surf_vert) { - log2_swath_height_l = dml_log2(rq_param->misc.rq_l.blk256_height) - req128_l; - log2_swath_height_c = dml_log2(rq_param->misc.rq_c.blk256_height) - req128_c; } else { - log2_swath_height_l = dml_log2(rq_param->misc.rq_l.blk256_width) - req128_l; - log2_swath_height_c = dml_log2(rq_param->misc.rq_c.blk256_width) - req128_c; + unsigned int swath_height_l; + unsigned int swath_height_c; + + if (!surf_vert) { + swath_height_l = rq_param->misc.rq_l.blk256_height; + swath_height_c = rq_param->misc.rq_c.blk256_height; + } else { + swath_height_l = rq_param->misc.rq_l.blk256_width; + swath_height_c = rq_param->misc.rq_c.blk256_width; + } + + if (swath_height_l > 0) + log2_swath_height_l = dml_log2(swath_height_l); + + if (req128_l && log2_swath_height_l > 0) + log2_swath_height_l -= 1; + + if (swath_height_c > 0) + log2_swath_height_c = dml_log2(swath_height_c); + + if (req128_c && log2_swath_height_c > 0) + log2_swath_height_c -= 1; } + rq_param->dlg.rq_l.swath_height = 1 << log2_swath_height_l; rq_param->dlg.rq_c.swath_height = 1 << log2_swath_height_c; diff --git a/drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.c b/drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.c index 098d6433f7f3..1f7b6ddf3020 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.c +++ b/drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.c @@ -226,7 +226,7 @@ void dml_log_pipe_params( dml_print("DML PARAMS: PIPE [%d] DISPLAY OUTPUT PARAMS:\n", i); dml_print("DML PARAMS: output_type = %d\n", dout->output_type); dml_print("DML PARAMS: output_format = %d\n", dout->output_format); - dml_print("DML PARAMS: output_bpc = %d\n", dout->output_bpc); + dml_print("DML PARAMS: dsc_input_bpc = %d\n", dout->dsc_input_bpc); dml_print("DML PARAMS: output_bpp = %3.4f\n", dout->output_bpp); dml_print("DML PARAMS: dp_lanes = %d\n", dout->dp_lanes); dml_print("DML PARAMS: dsc_enable = %d\n", dout->dsc_enable); diff --git a/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h b/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h index 0c5128187e08..2ece3690bfa3 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h +++ b/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h @@ -164,7 +164,7 @@ struct _vcs_dpi_ip_params_st { double writeback_max_vscl_ratio; double writeback_min_hscl_ratio; double writeback_min_vscl_ratio; - double maximum_dsc_bits_per_component; + unsigned int maximum_dsc_bits_per_component; unsigned int writeback_max_hscl_taps; unsigned int writeback_max_vscl_taps; unsigned int writeback_line_buffer_luma_buffer_size; @@ -292,10 +292,10 @@ struct writeback_st { struct _vcs_dpi_display_output_params_st { int dp_lanes; double output_bpp; + unsigned int dsc_input_bpc; int dsc_enable; int wb_enable; int num_active_wb; - int output_bpc; int output_type; int is_virtual; int output_format; diff --git a/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.c b/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.c index 94036a9612cf..2a967458065b 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.c +++ b/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.c @@ -471,7 +471,13 @@ static void fetch_pipe_params(struct display_mode_lib *mode_lib) mode_lib->vba.DSCEnable[mode_lib->vba.NumberOfActivePlanes] = dout->dsc_enable; mode_lib->vba.NumberOfDSCSlices[mode_lib->vba.NumberOfActivePlanes] = dout->dsc_slices; - mode_lib->vba.DSCInputBitPerComponent[mode_lib->vba.NumberOfActivePlanes] = dout->output_bpc; + if (!dout->dsc_input_bpc) { + mode_lib->vba.DSCInputBitPerComponent[mode_lib->vba.NumberOfActivePlanes] = + ip->maximum_dsc_bits_per_component; + } else { + mode_lib->vba.DSCInputBitPerComponent[mode_lib->vba.NumberOfActivePlanes] = + dout->dsc_input_bpc; + } mode_lib->vba.WritebackEnable[mode_lib->vba.NumberOfActivePlanes] = dout->wb_enable; mode_lib->vba.ActiveWritebacksPerPlane[mode_lib->vba.NumberOfActivePlanes] = dout->num_active_wb; diff --git a/drivers/gpu/drm/amd/display/dc/dml/dml1_display_rq_dlg_calc.c b/drivers/gpu/drm/amd/display/dc/dml/dml1_display_rq_dlg_calc.c index 4c3e9cc30167..414da64f5734 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dml1_display_rq_dlg_calc.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dml1_display_rq_dlg_calc.c @@ -344,13 +344,31 @@ static void handle_det_buf_split( if (surf_linear) { log2_swath_height_l = 0; log2_swath_height_c = 0; - } else if (!surf_vert) { - log2_swath_height_l = dml_log2(rq_param->misc.rq_l.blk256_height) - req128_l; - log2_swath_height_c = dml_log2(rq_param->misc.rq_c.blk256_height) - req128_c; } else { - log2_swath_height_l = dml_log2(rq_param->misc.rq_l.blk256_width) - req128_l; - log2_swath_height_c = dml_log2(rq_param->misc.rq_c.blk256_width) - req128_c; + unsigned int swath_height_l; + unsigned int swath_height_c; + + if (!surf_vert) { + swath_height_l = rq_param->misc.rq_l.blk256_height; + swath_height_c = rq_param->misc.rq_c.blk256_height; + } else { + swath_height_l = rq_param->misc.rq_l.blk256_width; + swath_height_c = rq_param->misc.rq_c.blk256_width; + } + + if (swath_height_l > 0) + log2_swath_height_l = dml_log2(swath_height_l); + + if (req128_l && log2_swath_height_l > 0) + log2_swath_height_l -= 1; + + if (swath_height_c > 0) + log2_swath_height_c = dml_log2(swath_height_c); + + if (req128_c && log2_swath_height_c > 0) + log2_swath_height_c -= 1; } + rq_param->dlg.rq_l.swath_height = 1 << log2_swath_height_l; rq_param->dlg.rq_c.swath_height = 1 << log2_swath_height_c; diff --git a/drivers/gpu/drm/amd/display/dc/inc/core_types.h b/drivers/gpu/drm/amd/display/dc/inc/core_types.h index eb1a19bf0d81..81b92f20d5b6 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/core_types.h +++ b/drivers/gpu/drm/amd/display/dc/inc/core_types.h @@ -118,6 +118,27 @@ struct resource_funcs { display_e2e_pipe_params_st *pipes, bool fast_validate); + /* + * Algorithm for assigning available link encoders to links. + * + * Update link_enc_assignments table and link_enc_avail list accordingly in + * struct resource_context. + */ + void (*link_encs_assign)( + struct dc *dc, + struct dc_state *state, + struct dc_stream_state *streams[], + uint8_t stream_count); + /* + * Unassign a link encoder from a stream. + * + * Update link_enc_assignments table and link_enc_avail list accordingly in + * struct resource_context. + */ + void (*link_enc_unassign)( + struct dc_state *state, + struct dc_stream_state *stream); + enum dc_status (*validate_global)( struct dc *dc, struct dc_state *context); @@ -358,6 +379,12 @@ struct resource_context { uint8_t clock_source_ref_count[MAX_CLOCK_SOURCES]; uint8_t dp_clock_source_ref_count; bool is_dsc_acquired[MAX_PIPES]; + /* A table/array of encoder-to-link assignments. One entry per stream. + * Indexed by stream index in dc_state. + */ + struct link_enc_assignment link_enc_assignments[MAX_PIPES]; + /* List of available link encoders. Uses engine ID as encoder identifier. */ + enum engine_id link_enc_avail[MAX_DIG_LINK_ENCODERS]; #if defined(CONFIG_DRM_AMD_DC_DCN) bool is_mpc_3dlut_acquired[MAX_PIPES]; #endif diff --git a/drivers/gpu/drm/amd/display/dc/inc/dc_link_dp.h b/drivers/gpu/drm/amd/display/dc/inc/dc_link_dp.h index b970a32177af..3ae05c96d557 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/dc_link_dp.h +++ b/drivers/gpu/drm/amd/display/dc/inc/dc_link_dp.h @@ -52,6 +52,10 @@ bool dp_validate_mode_timing( struct dc_link *link, const struct dc_crtc_timing *timing); +bool decide_edp_link_settings(struct dc_link *link, + struct dc_link_settings *link_setting, + uint32_t req_bw); + void decide_link_settings( struct dc_stream_state *stream, struct dc_link_settings *link_setting); @@ -71,6 +75,8 @@ void detect_edp_sink_caps(struct dc_link *link); bool is_dp_active_dongle(const struct dc_link *link); +bool is_edp_ilr_optimization_required(struct dc_link *link, struct dc_crtc_timing *crtc_timing); + void dp_enable_mst_on_sink(struct dc_link *link, bool enable); enum dp_panel_mode dp_get_panel_mode(struct dc_link *link); @@ -86,5 +92,7 @@ bool dp_set_dsc_enable(struct pipe_ctx *pipe_ctx, bool enable); bool dp_set_dsc_pps_sdp(struct pipe_ctx *pipe_ctx, bool enable); void dp_set_dsc_on_stream(struct pipe_ctx *pipe_ctx, bool enable); bool dp_update_dsc_config(struct pipe_ctx *pipe_ctx); +bool dp_set_dsc_on_rx(struct pipe_ctx *pipe_ctx, bool enable); + #endif /* __DC_LINK_DP_H__ */ diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr.h b/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr.h index 3a29f379d0c8..5dc8d02b40c3 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr.h @@ -262,14 +262,9 @@ struct clk_mgr_funcs { /* Get current memclk states from PMFW, update relevant structures */ void (*get_memclk_states_from_smu)(struct clk_mgr *clk_mgr); -}; - -struct dpm_clocks; -struct wartermarks; -struct smu_watermark_set { - struct watermarks *wm_set; - union large_integer mc_address; + /* Get SMU present */ + bool (*is_smu_present)(struct clk_mgr *clk_mgr); }; struct clk_mgr { @@ -283,7 +278,6 @@ struct clk_mgr { struct clk_state_registers_and_bypass boot_snapshot; struct clk_bw_params *bw_params; struct pp_smu_wm_range_sets ranges; - struct smu_watermark_set smu_wm_set; }; /* forward declarations */ diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h b/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h index 346dcd87dc10..80e1a32bc63d 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h @@ -29,6 +29,7 @@ #include "mem_input.h" #define OPP_ID_INVALID 0xf +#define MAX_TTU 0xffffff enum cursor_pitch { diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/link_encoder.h b/drivers/gpu/drm/amd/display/dc/inc/hw/link_encoder.h index 7f5acd8fb918..80bc99500645 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw/link_encoder.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw/link_encoder.h @@ -187,4 +187,17 @@ struct link_encoder_funcs { struct link_encoder *enc); }; +/* + * Used to track assignments of links (display endpoints) to link encoders. + * + * Entry in link_enc_assignments table in struct resource_context. + * Entries only marked valid once encoder assigned to a link and invalidated once unassigned. + * Uses engine ID as identifier since PHY ID not relevant for USB4 DPIA endpoint. + */ +struct link_enc_assignment { + bool valid; + struct display_endpoint_id ep_id; + enum engine_id eng_id; +}; + #endif /* LINK_ENCODER_H_ */ diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h b/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h index 2fedfcac6705..1d5853c95448 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h @@ -118,8 +118,7 @@ struct hw_sequencer_funcs { struct pipe_ctx *pipe_ctx, enum vline_select vline); void (*set_drr)(struct pipe_ctx **pipe_ctx, int num_pipes, - unsigned int vmin, unsigned int vmax, - unsigned int vmid, unsigned int vmid_frame_number); + struct dc_crtc_timing_adjust adjust); void (*set_static_screen_control)(struct pipe_ctx **pipe_ctx, int num_pipes, const struct dc_static_screen_params *events); @@ -218,6 +217,8 @@ struct hw_sequencer_funcs { void (*set_pipe)(struct pipe_ctx *pipe_ctx); + void (*get_dcc_en_bits)(struct dc *dc, int *dcc_en_bits); + /* Idle Optimization Related */ bool (*apply_idle_power_optimizations)(struct dc *dc, bool enable); diff --git a/drivers/gpu/drm/amd/display/dc/inc/link_enc_cfg.h b/drivers/gpu/drm/amd/display/dc/inc/link_enc_cfg.h new file mode 100644 index 000000000000..7d36e55f3097 --- /dev/null +++ b/drivers/gpu/drm/amd/display/dc/inc/link_enc_cfg.h @@ -0,0 +1,86 @@ +/* + * Copyright 2021 Advanced Micro Devices, Inc. + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR + * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, + * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR + * OTHER DEALINGS IN THE SOFTWARE. + * + * Authors: AMD + * + */ + +#ifndef DC_INC_LINK_ENC_CFG_H_ +#define DC_INC_LINK_ENC_CFG_H_ + +/* This module implements functionality for dynamically assigning DIG link + * encoder resources to display endpoints (links). + */ + +#include "core_types.h" + +/* + * Initialise link encoder resource tracking. + */ +void link_enc_cfg_init( + struct dc *dc, + struct dc_state *state); + +/* + * Algorithm for assigning available DIG link encoders to streams. + * + * Update link_enc_assignments table and link_enc_avail list accordingly in + * struct resource_context. + * + * Loop over all streams twice: + * a) First assign encoders to unmappable endpoints. + * b) Then assign encoders to mappable endpoints. + */ +void link_enc_cfg_link_encs_assign( + struct dc *dc, + struct dc_state *state, + struct dc_stream_state *streams[], + uint8_t stream_count); + +/* + * Unassign a link encoder from a stream. + * + * Update link_enc_assignments table and link_enc_avail list accordingly in + * struct resource_context. + */ +void link_enc_cfg_link_enc_unassign( + struct dc_state *state, + struct dc_stream_state *stream); + +/* + * Check whether the transmitter driven by a link encoder is a mappable + * endpoint. + */ +bool link_enc_cfg_is_transmitter_mappable( + struct dc_state *state, + struct link_encoder *link_enc); + +/* Return link using DIG link encoder resource. NULL if unused. */ +struct dc_link *link_enc_cfg_get_link_using_link_enc( + struct dc_state *state, + enum engine_id eng_id); + +/* Return DIG link encoder used by link. NULL if unused. */ +struct link_encoder *link_enc_cfg_get_link_enc_used_by_link( + struct dc_state *state, + struct dc_link *link); + +#endif /* DC_INC_LINK_ENC_CFG_H_ */ diff --git a/drivers/gpu/drm/amd/display/dc/irq/dcn21/irq_service_dcn21.c b/drivers/gpu/drm/amd/display/dc/irq/dcn21/irq_service_dcn21.c index 6ee9dd833b85..1a5be2792055 100644 --- a/drivers/gpu/drm/amd/display/dc/irq/dcn21/irq_service_dcn21.c +++ b/drivers/gpu/drm/amd/display/dc/irq/dcn21/irq_service_dcn21.c @@ -187,6 +187,10 @@ static const struct irq_source_info_funcs vupdate_no_lock_irq_info_funcs = { .ack = NULL }; +static const struct irq_source_info_funcs dmub_trace_irq_info_funcs = { + .set = NULL, + .ack = NULL +}; static const struct irq_source_info_funcs vline0_irq_info_funcs = { .set = NULL, @@ -205,6 +209,9 @@ static const struct irq_source_info_funcs vline0_irq_info_funcs = { BASE(mm ## block ## id ## _ ## reg_name ## _BASE_IDX) + \ mm ## block ## id ## _ ## reg_name +#define SRI_DMUB(reg_name)\ + BASE(mm ## reg_name ## _BASE_IDX) + \ + mm ## reg_name #define IRQ_REG_ENTRY(block, reg_num, reg1, mask1, reg2, mask2)\ .enable_reg = SRI(reg1, block, reg_num),\ @@ -220,7 +227,19 @@ static const struct irq_source_info_funcs vline0_irq_info_funcs = { .ack_value = \ block ## reg_num ## _ ## reg2 ## __ ## mask2 ## _MASK \ - +#define IRQ_REG_ENTRY_DMUB(reg1, mask1, reg2, mask2)\ + .enable_reg = SRI_DMUB(reg1),\ + .enable_mask = \ + reg1 ## __ ## mask1 ## _MASK,\ + .enable_value = {\ + reg1 ## __ ## mask1 ## _MASK,\ + ~reg1 ## __ ## mask1 ## _MASK \ + },\ + .ack_reg = SRI_DMUB(reg2),\ + .ack_mask = \ + reg2 ## __ ## mask2 ## _MASK,\ + .ack_value = \ + reg2 ## __ ## mask2 ## _MASK \ #define hpd_int_entry(reg_num)\ [DC_IRQ_SOURCE_HPD1 + reg_num] = {\ @@ -282,6 +301,13 @@ static const struct irq_source_info_funcs vline0_irq_info_funcs = { .funcs = &vline0_irq_info_funcs\ } +#define dmub_trace_int_entry()\ + [DC_IRQ_SOURCE_DMCUB_OUTBOX0] = {\ + IRQ_REG_ENTRY_DMUB(DMCUB_INTERRUPT_ENABLE, DMCUB_OUTBOX0_READY_INT_EN,\ + DMCUB_INTERRUPT_ACK, DMCUB_OUTBOX0_READY_INT_ACK),\ + .funcs = &dmub_trace_irq_info_funcs\ + } + #define dummy_irq_entry() \ {\ .funcs = &dummy_irq_info_funcs\ @@ -400,6 +426,7 @@ irq_source_info_dcn21[DAL_IRQ_SOURCES_NUMBER] = { vline0_int_entry(3), vline0_int_entry(4), vline0_int_entry(5), + dmub_trace_int_entry(), }; static const struct irq_service_funcs irq_service_funcs_dcn21 = { diff --git a/drivers/gpu/drm/amd/display/dc/irq/dcn30/irq_service_dcn30.c b/drivers/gpu/drm/amd/display/dc/irq/dcn30/irq_service_dcn30.c index 4ec6f6ad8c48..914ce2ce1c2f 100644 --- a/drivers/gpu/drm/amd/display/dc/irq/dcn30/irq_service_dcn30.c +++ b/drivers/gpu/drm/amd/display/dc/irq/dcn30/irq_service_dcn30.c @@ -215,6 +215,9 @@ static const struct irq_source_info_funcs vline0_irq_info_funcs = { BASE(mm ## block ## id ## _ ## reg_name ## _BASE_IDX) + \ mm ## block ## id ## _ ## reg_name +#define SRI_DMUB(reg_name)\ + BASE(mm ## reg_name ## _BASE_IDX) + \ + mm ## reg_name #define IRQ_REG_ENTRY(block, reg_num, reg1, mask1, reg2, mask2)\ .enable_reg = SRI(reg1, block, reg_num),\ @@ -230,7 +233,19 @@ static const struct irq_source_info_funcs vline0_irq_info_funcs = { .ack_value = \ block ## reg_num ## _ ## reg2 ## __ ## mask2 ## _MASK \ - +#define IRQ_REG_ENTRY_DMUB(reg1, mask1, reg2, mask2)\ + .enable_reg = SRI_DMUB(reg1),\ + .enable_mask = \ + reg1 ## __ ## mask1 ## _MASK,\ + .enable_value = {\ + reg1 ## __ ## mask1 ## _MASK,\ + ~reg1 ## __ ## mask1 ## _MASK \ + },\ + .ack_reg = SRI_DMUB(reg2),\ + .ack_mask = \ + reg2 ## __ ## mask2 ## _MASK,\ + .ack_value = \ + reg2 ## __ ## mask2 ## _MASK \ #define hpd_int_entry(reg_num)\ [DC_IRQ_SOURCE_HPD1 + reg_num] = {\ @@ -284,6 +299,13 @@ static const struct irq_source_info_funcs vline0_irq_info_funcs = { .funcs = &vline0_irq_info_funcs\ } +#define dmub_trace_int_entry()\ + [DC_IRQ_SOURCE_DMCUB_OUTBOX0] = {\ + IRQ_REG_ENTRY_DMUB(DMCUB_INTERRUPT_ENABLE, DMCUB_OUTBOX0_READY_INT_EN,\ + DMCUB_INTERRUPT_ACK, DMCUB_OUTBOX0_READY_INT_ACK),\ + .funcs = &dmub_trace_irq_info_funcs\ + } + #define dummy_irq_entry() \ {\ .funcs = &dummy_irq_info_funcs\ @@ -398,6 +420,7 @@ irq_source_info_dcn30[DAL_IRQ_SOURCES_NUMBER] = { vline0_int_entry(3), vline0_int_entry(4), vline0_int_entry(5), + dmub_trace_int_entry(), }; static const struct irq_service_funcs irq_service_funcs_dcn30 = { diff --git a/drivers/gpu/drm/amd/display/dc/irq/dcn302/irq_service_dcn302.c b/drivers/gpu/drm/amd/display/dc/irq/dcn302/irq_service_dcn302.c index 2313a5664f44..40fd34fb1d5e 100644 --- a/drivers/gpu/drm/amd/display/dc/irq/dcn302/irq_service_dcn302.c +++ b/drivers/gpu/drm/amd/display/dc/irq/dcn302/irq_service_dcn302.c @@ -50,6 +50,8 @@ static enum dc_irq_source to_dal_irq_source_dcn302(struct irq_service *irq_servi return DC_IRQ_SOURCE_VBLANK5; case DCN_1_0__SRCID__DC_D6_OTG_VSTARTUP: return DC_IRQ_SOURCE_VBLANK6; + case DCN_1_0__SRCID__DMCUB_OUTBOX_HIGH_PRIORITY_READY_INT: + return DC_IRQ_SOURCE_DMCUB_OUTBOX0; case DCN_1_0__SRCID__OTG1_VERTICAL_INTERRUPT0_CONTROL: return DC_IRQ_SOURCE_DC1_VLINE0; case DCN_1_0__SRCID__OTG2_VERTICAL_INTERRUPT0_CONTROL: @@ -166,6 +168,11 @@ static const struct irq_source_info_funcs vblank_irq_info_funcs = { .ack = NULL }; +static const struct irq_source_info_funcs dmub_trace_irq_info_funcs = { + .set = NULL, + .ack = NULL +}; + static const struct irq_source_info_funcs vline0_irq_info_funcs = { .set = NULL, .ack = NULL @@ -181,6 +188,9 @@ static const struct irq_source_info_funcs vline0_irq_info_funcs = { BASE(mm ## block ## id ## _ ## reg_name ## _BASE_IDX) + \ mm ## block ## id ## _ ## reg_name +#define SRI_DMUB(reg_name)\ + BASE(mm ## reg_name ## _BASE_IDX) + \ + mm ## reg_name #define IRQ_REG_ENTRY(block, reg_num, reg1, mask1, reg2, mask2)\ .enable_reg = SRI(reg1, block, reg_num),\ @@ -193,7 +203,26 @@ static const struct irq_source_info_funcs vline0_irq_info_funcs = { .ack_mask = block ## reg_num ## _ ## reg2 ## __ ## mask2 ## _MASK,\ .ack_value = block ## reg_num ## _ ## reg2 ## __ ## mask2 ## _MASK \ +#define dmub_trace_int_entry()\ + [DC_IRQ_SOURCE_DMCUB_OUTBOX0] = {\ + IRQ_REG_ENTRY_DMUB(DMCUB_INTERRUPT_ENABLE, DMCUB_OUTBOX0_READY_INT_EN,\ + DMCUB_INTERRUPT_ACK, DMCUB_OUTBOX0_READY_INT_ACK),\ + .funcs = &dmub_trace_irq_info_funcs\ + } +#define IRQ_REG_ENTRY_DMUB(reg1, mask1, reg2, mask2)\ + .enable_reg = SRI_DMUB(reg1),\ + .enable_mask = \ + reg1 ## __ ## mask1 ## _MASK,\ + .enable_value = {\ + reg1 ## __ ## mask1 ## _MASK,\ + ~reg1 ## __ ## mask1 ## _MASK \ + },\ + .ack_reg = SRI_DMUB(reg2),\ + .ack_mask = \ + reg2 ## __ ## mask2 ## _MASK,\ + .ack_value = \ + reg2 ## __ ## mask2 ## _MASK \ #define hpd_int_entry(reg_num)\ [DC_IRQ_SOURCE_HPD1 + reg_num] = {\ @@ -348,6 +377,7 @@ static const struct irq_source_info irq_source_info_dcn302[DAL_IRQ_SOURCES_NUMBE vline0_int_entry(2), vline0_int_entry(3), vline0_int_entry(4), + dmub_trace_int_entry(), }; static const struct irq_service_funcs irq_service_funcs_dcn302 = { diff --git a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h index f07b348f7c29..4195ff10c514 100644 --- a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h +++ b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h @@ -47,10 +47,10 @@ /* Firmware versioning. */ #ifdef DMUB_EXPOSE_VERSION -#define DMUB_FW_VERSION_GIT_HASH 0xc29b1734b +#define DMUB_FW_VERSION_GIT_HASH 0x23db9b126 #define DMUB_FW_VERSION_MAJOR 0 #define DMUB_FW_VERSION_MINOR 0 -#define DMUB_FW_VERSION_REVISION 56 +#define DMUB_FW_VERSION_REVISION 62 #define DMUB_FW_VERSION_TEST 0 #define DMUB_FW_VERSION_VBIOS 0 #define DMUB_FW_VERSION_HOTFIX 0 @@ -121,6 +121,16 @@ #define TRACE_BUFFER_ENTRY_OFFSET 16 /** + * ABM backlight control version legacy + */ +#define DMUB_CMD_ABM_SET_BACKLIGHT_VERSION_UNKNOWN 0x0 + +/** + * ABM backlight control version with multi edp support + */ +#define DMUB_CMD_ABM_SET_BACKLIGHT_VERSION_1 0x1 + +/** * Physical framebuffer address location, 64-bit. */ #ifndef PHYSICAL_ADDRESS_LOC @@ -202,12 +212,7 @@ struct dmub_feature_caps { * Max PSR version supported by FW. */ uint8_t psr; -#ifndef TRIM_FAMS - uint8_t fw_assisted_mclk_switch; - uint8_t reserved[6]; -#else uint8_t reserved[7]; -#endif }; #if defined(__cplusplus) @@ -532,10 +537,6 @@ enum dmub_cmd_type { * Command type used for OUTBOX1 notification enable */ DMUB_CMD__OUTBOX1_ENABLE = 71, -#ifndef TRIM_FAMS - DMUB_CMD__FW_ASSISTED_MCLK_SWITCH = 76, -#endif - /** * Command type used for all VBIOS interface commands. */ @@ -1115,13 +1116,6 @@ enum dmub_cmd_psr_type { DMUB_CMD__PSR_FORCE_STATIC = 5, }; -#ifndef TRIM_FAMS -enum dmub_cmd_fams_type { - DMUB_CMD__FAMS_SETUP_FW_CTRL = 0, - DMUB_CMD__FAMS_DRR_UPDATE = 1, -}; -#endif - /** * PSR versions. */ @@ -1245,6 +1239,19 @@ struct dmub_cmd_psr_copy_settings_data { * Length of each horizontal line in us. */ uint32_t line_time_in_us; + /** + * FEC enable status in driver + */ + uint8_t fec_enable_status; + /** + * FEC re-enable delay when PSR exit. + * unit is 100us, range form 0~255(0xFF). + */ + uint8_t fec_enable_delay_in100us; + /** + * Explicit padding to 4 byte boundary. + */ + uint8_t pad3[2]; }; /** @@ -1628,6 +1635,23 @@ struct dmub_cmd_abm_set_backlight_data { * Requested backlight level from user. */ uint32_t backlight_user_level; + + /** + * Backlight data version. + */ + uint8_t version; + + /** + * Panel Control HW instance mask. + * Bit 0 is Panel Control HW instance 0. + * Bit 1 is Panel Control HW instance 1. + */ + uint8_t panel_mask; + + /** + * Explicit padding to 4 byte boundary. + */ + uint8_t pad[2]; }; /** @@ -1791,24 +1815,6 @@ struct dmub_rb_cmd_drr_update { struct dmub_optc_state dmub_optc_state_req; }; -#ifndef TRIM_FAMS -struct dmub_cmd_fw_assisted_mclk_switch_pipe_data { - uint32_t pix_clk_100hz; - uint32_t min_refresh_in_uhz; - uint32_t max_ramp_step; -}; - -struct dmub_cmd_fw_assisted_mclk_switch_config { - uint32_t fams_enabled; - struct dmub_cmd_fw_assisted_mclk_switch_pipe_data pipe_data[DMUB_MAX_STREAMS]; -}; - -struct dmub_rb_cmd_fw_assisted_mclk_switch { - struct dmub_cmd_header header; - struct dmub_cmd_fw_assisted_mclk_switch_config config_data; -}; -#endif - /** * Data passed from driver to FW in a DMUB_CMD__VBIOS_LVTMA_CONTROL command. */ @@ -1951,9 +1957,6 @@ union dmub_rb_cmd { */ struct dmub_rb_cmd_query_feature_caps query_feature_caps; struct dmub_rb_cmd_drr_update drr_update; -#ifndef TRIM_FAMS - struct dmub_rb_cmd_fw_assisted_mclk_switch fw_assisted_mclk_switch; -#endif /** * Definition of a DMUB_CMD__VBIOS_LVTMA_CONTROL command. */ diff --git a/drivers/gpu/drm/amd/display/dmub/src/dmub_srv.c b/drivers/gpu/drm/amd/display/dmub/src/dmub_srv.c index 8ba0a9e2da54..1cbb125b4063 100644 --- a/drivers/gpu/drm/amd/display/dmub/src/dmub_srv.c +++ b/drivers/gpu/drm/amd/display/dmub/src/dmub_srv.c @@ -415,6 +415,12 @@ enum dmub_status dmub_srv_hw_init(struct dmub_srv *dmub, if (!dmub->sw_init) return DMUB_STATUS_INVALID; + if (!inst_fb || !stack_fb || !data_fb || !bios_fb || !mail_fb || + !tracebuff_fb || !fw_state_fb || !scratch_mem_fb) { + ASSERT(0); + return DMUB_STATUS_INVALID; + } + dmub->fb_base = params->fb_base; dmub->fb_offset = params->fb_offset; dmub->psp_version = params->psp_version; @@ -422,101 +428,89 @@ enum dmub_status dmub_srv_hw_init(struct dmub_srv *dmub, if (dmub->hw_funcs.reset) dmub->hw_funcs.reset(dmub); - if (inst_fb && data_fb) { - cw0.offset.quad_part = inst_fb->gpu_addr; - cw0.region.base = DMUB_CW0_BASE; - cw0.region.top = cw0.region.base + inst_fb->size - 1; - - cw1.offset.quad_part = stack_fb->gpu_addr; - cw1.region.base = DMUB_CW1_BASE; - cw1.region.top = cw1.region.base + stack_fb->size - 1; - - if (params->load_inst_const && dmub->hw_funcs.backdoor_load) { - /** - * Read back all the instruction memory so we don't hang the - * DMCUB when backdoor loading if the write from x86 hasn't been - * flushed yet. This only occurs in backdoor loading. - */ - dmub_flush_buffer_mem(inst_fb); - dmub->hw_funcs.backdoor_load(dmub, &cw0, &cw1); - } - - } - - if (inst_fb && data_fb && bios_fb && mail_fb && tracebuff_fb && - fw_state_fb && scratch_mem_fb) { - cw2.offset.quad_part = data_fb->gpu_addr; - cw2.region.base = DMUB_CW0_BASE + inst_fb->size; - cw2.region.top = cw2.region.base + data_fb->size; - - cw3.offset.quad_part = bios_fb->gpu_addr; - cw3.region.base = DMUB_CW3_BASE; - cw3.region.top = cw3.region.base + bios_fb->size; + cw0.offset.quad_part = inst_fb->gpu_addr; + cw0.region.base = DMUB_CW0_BASE; + cw0.region.top = cw0.region.base + inst_fb->size - 1; - cw4.offset.quad_part = mail_fb->gpu_addr; - cw4.region.base = DMUB_CW4_BASE; - cw4.region.top = cw4.region.base + mail_fb->size; + cw1.offset.quad_part = stack_fb->gpu_addr; + cw1.region.base = DMUB_CW1_BASE; + cw1.region.top = cw1.region.base + stack_fb->size - 1; + if (params->load_inst_const && dmub->hw_funcs.backdoor_load) { /** - * Doubled the mailbox region to accomodate inbox and outbox. - * Note: Currently, currently total mailbox size is 16KB. It is split - * equally into 8KB between inbox and outbox. If this config is - * changed, then uncached base address configuration of outbox1 - * has to be updated in funcs->setup_out_mailbox. + * Read back all the instruction memory so we don't hang the + * DMCUB when backdoor loading if the write from x86 hasn't been + * flushed yet. This only occurs in backdoor loading. */ - inbox1.base = cw4.region.base; - inbox1.top = cw4.region.base + DMUB_RB_SIZE; - outbox1.base = inbox1.top; - outbox1.top = cw4.region.top; + dmub_flush_buffer_mem(inst_fb); + dmub->hw_funcs.backdoor_load(dmub, &cw0, &cw1); + } - cw5.offset.quad_part = tracebuff_fb->gpu_addr; - cw5.region.base = DMUB_CW5_BASE; - cw5.region.top = cw5.region.base + tracebuff_fb->size; + cw2.offset.quad_part = data_fb->gpu_addr; + cw2.region.base = DMUB_CW0_BASE + inst_fb->size; + cw2.region.top = cw2.region.base + data_fb->size; - outbox0.base = DMUB_REGION5_BASE + TRACE_BUFFER_ENTRY_OFFSET; - outbox0.top = outbox0.base + tracebuff_fb->size - TRACE_BUFFER_ENTRY_OFFSET; + cw3.offset.quad_part = bios_fb->gpu_addr; + cw3.region.base = DMUB_CW3_BASE; + cw3.region.top = cw3.region.base + bios_fb->size; + cw4.offset.quad_part = mail_fb->gpu_addr; + cw4.region.base = DMUB_CW4_BASE; + cw4.region.top = cw4.region.base + mail_fb->size; - cw6.offset.quad_part = fw_state_fb->gpu_addr; - cw6.region.base = DMUB_CW6_BASE; - cw6.region.top = cw6.region.base + fw_state_fb->size; + /** + * Doubled the mailbox region to accomodate inbox and outbox. + * Note: Currently, currently total mailbox size is 16KB. It is split + * equally into 8KB between inbox and outbox. If this config is + * changed, then uncached base address configuration of outbox1 + * has to be updated in funcs->setup_out_mailbox. + */ + inbox1.base = cw4.region.base; + inbox1.top = cw4.region.base + DMUB_RB_SIZE; + outbox1.base = inbox1.top; + outbox1.top = cw4.region.top; - dmub->fw_state = fw_state_fb->cpu_addr; + cw5.offset.quad_part = tracebuff_fb->gpu_addr; + cw5.region.base = DMUB_CW5_BASE; + cw5.region.top = cw5.region.base + tracebuff_fb->size; - dmub->scratch_mem_fb = *scratch_mem_fb; + outbox0.base = DMUB_REGION5_BASE + TRACE_BUFFER_ENTRY_OFFSET; + outbox0.top = outbox0.base + tracebuff_fb->size - TRACE_BUFFER_ENTRY_OFFSET; - if (dmub->hw_funcs.setup_windows) - dmub->hw_funcs.setup_windows(dmub, &cw2, &cw3, &cw4, - &cw5, &cw6); + cw6.offset.quad_part = fw_state_fb->gpu_addr; + cw6.region.base = DMUB_CW6_BASE; + cw6.region.top = cw6.region.base + fw_state_fb->size; - if (dmub->hw_funcs.setup_outbox0) - dmub->hw_funcs.setup_outbox0(dmub, &outbox0); + dmub->fw_state = fw_state_fb->cpu_addr; - if (dmub->hw_funcs.setup_mailbox) - dmub->hw_funcs.setup_mailbox(dmub, &inbox1); - if (dmub->hw_funcs.setup_out_mailbox) - dmub->hw_funcs.setup_out_mailbox(dmub, &outbox1); - } + dmub->scratch_mem_fb = *scratch_mem_fb; - if (mail_fb) { - dmub_memset(&rb_params, 0, sizeof(rb_params)); - rb_params.ctx = dmub; - rb_params.base_address = mail_fb->cpu_addr; - rb_params.capacity = DMUB_RB_SIZE; + if (dmub->hw_funcs.setup_windows) + dmub->hw_funcs.setup_windows(dmub, &cw2, &cw3, &cw4, &cw5, &cw6); - dmub_rb_init(&dmub->inbox1_rb, &rb_params); + if (dmub->hw_funcs.setup_outbox0) + dmub->hw_funcs.setup_outbox0(dmub, &outbox0); - // Initialize outbox1 ring buffer - rb_params.ctx = dmub; - rb_params.base_address = (void *) ((uint8_t *) (mail_fb->cpu_addr) + DMUB_RB_SIZE); - rb_params.capacity = DMUB_RB_SIZE; - dmub_rb_init(&dmub->outbox1_rb, &rb_params); + if (dmub->hw_funcs.setup_mailbox) + dmub->hw_funcs.setup_mailbox(dmub, &inbox1); + if (dmub->hw_funcs.setup_out_mailbox) + dmub->hw_funcs.setup_out_mailbox(dmub, &outbox1); - } + dmub_memset(&rb_params, 0, sizeof(rb_params)); + rb_params.ctx = dmub; + rb_params.base_address = mail_fb->cpu_addr; + rb_params.capacity = DMUB_RB_SIZE; + dmub_rb_init(&dmub->inbox1_rb, &rb_params); + + // Initialize outbox1 ring buffer + rb_params.ctx = dmub; + rb_params.base_address = (void *) ((uint8_t *) (mail_fb->cpu_addr) + DMUB_RB_SIZE); + rb_params.capacity = DMUB_RB_SIZE; + dmub_rb_init(&dmub->outbox1_rb, &rb_params); dmub_memset(&outbox0_rb_params, 0, sizeof(outbox0_rb_params)); outbox0_rb_params.ctx = dmub; - outbox0_rb_params.base_address = (void *)((uint64_t)(tracebuff_fb->cpu_addr) + TRACE_BUFFER_ENTRY_OFFSET); + outbox0_rb_params.base_address = (void *)((uintptr_t)(tracebuff_fb->cpu_addr) + TRACE_BUFFER_ENTRY_OFFSET); outbox0_rb_params.capacity = tracebuff_fb->size - dmub_align(TRACE_BUFFER_ENTRY_OFFSET, 64); dmub_rb_init(&dmub->outbox0_rb, &outbox0_rb_params); @@ -653,6 +647,8 @@ dmub_srv_send_gpint_command(struct dmub_srv *dmub, dmub->hw_funcs.set_gpint(dmub, reg); for (i = 0; i < timeout_us; ++i) { + udelay(1); + if (dmub->hw_funcs.is_gpint_acked(dmub, reg)) return DMUB_STATUS_OK; } diff --git a/drivers/gpu/drm/amd/display/include/logger_types.h b/drivers/gpu/drm/amd/display/include/logger_types.h index 21bbee17c527..571fcf23cea9 100644 --- a/drivers/gpu/drm/amd/display/include/logger_types.h +++ b/drivers/gpu/drm/amd/display/include/logger_types.h @@ -36,6 +36,9 @@ #define DC_LOG_DC(...) DRM_DEBUG_KMS(__VA_ARGS__) #define DC_LOG_DTN(...) DRM_DEBUG_KMS(__VA_ARGS__) #define DC_LOG_SURFACE(...) pr_debug("[SURFACE]:"__VA_ARGS__) +#define DC_LOG_CURSOR(...) pr_debug("[CURSOR]:"__VA_ARGS__) +#define DC_LOG_PFLIP(...) pr_debug("[PFLIP]:"__VA_ARGS__) +#define DC_LOG_VBLANK(...) pr_debug("[VBLANK]:"__VA_ARGS__) #define DC_LOG_HW_HOTPLUG(...) DRM_DEBUG_KMS(__VA_ARGS__) #define DC_LOG_HW_LINK_TRAINING(...) pr_debug("[HW_LINK_TRAINING]:"__VA_ARGS__) #define DC_LOG_HW_SET_MODE(...) DRM_DEBUG_KMS(__VA_ARGS__) diff --git a/drivers/gpu/drm/amd/display/modules/color/color_gamma.c b/drivers/gpu/drm/amd/display/modules/color/color_gamma.c index 5c67e12b2e55..ef742d95ef05 100644 --- a/drivers/gpu/drm/amd/display/modules/color/color_gamma.c +++ b/drivers/gpu/drm/amd/display/modules/color/color_gamma.c @@ -942,7 +942,7 @@ static void hermite_spline_eetf(struct fixed31_32 input_x, static bool build_freesync_hdr(struct pwl_float_data_ex *rgb_regamma, uint32_t hw_points_num, const struct hw_x_point *coordinate_x, - const struct freesync_hdr_tf_params *fs_params, + const struct hdr_tm_params *fs_params, struct calculate_buffer *cal_buffer) { uint32_t i; @@ -2027,7 +2027,7 @@ rgb_user_alloc_fail: static bool calculate_curve(enum dc_transfer_func_predefined trans, struct dc_transfer_func_distributed_points *points, struct pwl_float_data_ex *rgb_regamma, - const struct freesync_hdr_tf_params *fs_params, + const struct hdr_tm_params *fs_params, uint32_t sdr_ref_white_level, struct calculate_buffer *cal_buffer) { @@ -2106,7 +2106,7 @@ static bool calculate_curve(enum dc_transfer_func_predefined trans, bool mod_color_calculate_regamma_params(struct dc_transfer_func *output_tf, const struct dc_gamma *ramp, bool mapUserRamp, bool canRomBeUsed, - const struct freesync_hdr_tf_params *fs_params, + const struct hdr_tm_params *fs_params, struct calculate_buffer *cal_buffer) { struct dc_transfer_func_distributed_points *tf_pts = &output_tf->tf_pts; diff --git a/drivers/gpu/drm/amd/display/modules/color/color_gamma.h b/drivers/gpu/drm/amd/display/modules/color/color_gamma.h index 7563457e2ff4..2893abf48208 100644 --- a/drivers/gpu/drm/amd/display/modules/color/color_gamma.h +++ b/drivers/gpu/drm/amd/display/modules/color/color_gamma.h @@ -76,7 +76,7 @@ struct regamma_lut { }; }; -struct freesync_hdr_tf_params { +struct hdr_tm_params { unsigned int sdr_white_level; unsigned int min_content; // luminance in 1/10000 nits unsigned int max_content; // luminance in nits @@ -108,7 +108,7 @@ void precompute_de_pq(void); bool mod_color_calculate_regamma_params(struct dc_transfer_func *output_tf, const struct dc_gamma *ramp, bool mapUserRamp, bool canRomBeUsed, - const struct freesync_hdr_tf_params *fs_params, + const struct hdr_tm_params *fs_params, struct calculate_buffer *cal_buffer); bool mod_color_calculate_degamma_params(struct dc_color_caps *dc_caps, diff --git a/drivers/gpu/drm/amd/display/modules/freesync/freesync.c b/drivers/gpu/drm/amd/display/modules/freesync/freesync.c index e5f9d7704a63..3f4f44b44e6a 100644 --- a/drivers/gpu/drm/amd/display/modules/freesync/freesync.c +++ b/drivers/gpu/drm/amd/display/modules/freesync/freesync.c @@ -118,7 +118,7 @@ static unsigned int calc_duration_in_us_from_v_total( return duration_in_us; } -static unsigned int calc_v_total_from_refresh( +unsigned int mod_freesync_calc_v_total_from_refresh( const struct dc_stream_state *stream, unsigned int refresh_in_uhz) { @@ -280,10 +280,10 @@ static void apply_below_the_range(struct core_freesync *core_freesync, /* Restore FreeSync */ in_out_vrr->adjust.v_total_min = - calc_v_total_from_refresh(stream, + mod_freesync_calc_v_total_from_refresh(stream, in_out_vrr->max_refresh_in_uhz); in_out_vrr->adjust.v_total_max = - calc_v_total_from_refresh(stream, + mod_freesync_calc_v_total_from_refresh(stream, in_out_vrr->min_refresh_in_uhz); /* BTR set to "active" so engage */ } else { @@ -442,16 +442,16 @@ static void apply_fixed_refresh(struct core_freesync *core_freesync, if (update) { if (in_out_vrr->fixed.fixed_active) { in_out_vrr->adjust.v_total_min = - calc_v_total_from_refresh( + mod_freesync_calc_v_total_from_refresh( stream, in_out_vrr->max_refresh_in_uhz); in_out_vrr->adjust.v_total_max = in_out_vrr->adjust.v_total_min; } else { in_out_vrr->adjust.v_total_min = - calc_v_total_from_refresh(stream, + mod_freesync_calc_v_total_from_refresh(stream, in_out_vrr->max_refresh_in_uhz); in_out_vrr->adjust.v_total_max = - calc_v_total_from_refresh(stream, + mod_freesync_calc_v_total_from_refresh(stream, in_out_vrr->min_refresh_in_uhz); } } @@ -543,8 +543,8 @@ static void build_vrr_infopacket_data_v1(const struct mod_vrr_params *vrr, infopacket->sb[6] |= 0x02; /* PB6 = [Bit 2 = FreeSync Active] */ - if (vrr->state == VRR_STATE_ACTIVE_VARIABLE || - vrr->state == VRR_STATE_ACTIVE_FIXED) + if (vrr->state != VRR_STATE_DISABLED && + vrr->state != VRR_STATE_UNSUPPORTED) infopacket->sb[6] |= 0x04; // For v1 & 2 infoframes program nominal if non-fs mode, otherwise full range @@ -1082,10 +1082,10 @@ void mod_freesync_build_vrr_params(struct mod_freesync *mod_freesync, refresh_range >= MIN_REFRESH_RANGE) { in_out_vrr->adjust.v_total_min = - calc_v_total_from_refresh(stream, + mod_freesync_calc_v_total_from_refresh(stream, in_out_vrr->max_refresh_in_uhz); in_out_vrr->adjust.v_total_max = - calc_v_total_from_refresh(stream, + mod_freesync_calc_v_total_from_refresh(stream, in_out_vrr->min_refresh_in_uhz); } else if (in_out_vrr->state == VRR_STATE_ACTIVE_FIXED) { in_out_vrr->fixed.target_refresh_in_uhz = @@ -1099,7 +1099,7 @@ void mod_freesync_build_vrr_params(struct mod_freesync *mod_freesync, } else { in_out_vrr->fixed.fixed_active = true; in_out_vrr->adjust.v_total_min = - calc_v_total_from_refresh(stream, + mod_freesync_calc_v_total_from_refresh(stream, in_out_vrr->fixed.target_refresh_in_uhz); in_out_vrr->adjust.v_total_max = in_out_vrr->adjust.v_total_min; @@ -1206,10 +1206,10 @@ void mod_freesync_handle_v_update(struct mod_freesync *mod_freesync, /* Restore FreeSync */ if (in_out_vrr->btr.frame_counter == 0) { in_out_vrr->adjust.v_total_min = - calc_v_total_from_refresh(stream, + mod_freesync_calc_v_total_from_refresh(stream, in_out_vrr->max_refresh_in_uhz); in_out_vrr->adjust.v_total_max = - calc_v_total_from_refresh(stream, + mod_freesync_calc_v_total_from_refresh(stream, in_out_vrr->min_refresh_in_uhz); } } @@ -1267,6 +1267,21 @@ unsigned long long mod_freesync_calc_nominal_field_rate( return nominal_field_rate_in_uhz; } +unsigned long long mod_freesync_calc_field_rate_from_timing( + unsigned int vtotal, unsigned int htotal, unsigned int pix_clk) +{ + unsigned long long field_rate_in_uhz = 0; + unsigned int total = htotal * vtotal; + + /* Calculate nominal field rate for stream, rounded up to nearest integer */ + field_rate_in_uhz = pix_clk; + field_rate_in_uhz *= 1000000ULL; + + field_rate_in_uhz = div_u64(field_rate_in_uhz, total); + + return field_rate_in_uhz; +} + bool mod_freesync_is_valid_range(uint32_t min_refresh_cap_in_uhz, uint32_t max_refresh_cap_in_uhz, uint32_t nominal_field_rate_in_uhz) diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp.c b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp.c index 20e554e771d1..68a6481d7f8f 100644 --- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp.c +++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp.c @@ -53,7 +53,7 @@ static uint8_t is_cp_desired_hdcp1(struct mod_hdcp *hdcp) */ for (i = 0; i < MAX_NUM_OF_DISPLAYS; i++) { if (hdcp->displays[i].state != MOD_HDCP_DISPLAY_INACTIVE && - !hdcp->displays[i].adjust.disable) { + hdcp->displays[i].adjust.disable != MOD_HDCP_DISPLAY_DISABLE_AUTHENTICATION) { is_auth_needed = 1; break; } @@ -74,7 +74,7 @@ static uint8_t is_cp_desired_hdcp2(struct mod_hdcp *hdcp) */ for (i = 0; i < MAX_NUM_OF_DISPLAYS; i++) { if (hdcp->displays[i].state != MOD_HDCP_DISPLAY_INACTIVE && - !hdcp->displays[i].adjust.disable) { + hdcp->displays[i].adjust.disable != MOD_HDCP_DISPLAY_DISABLE_AUTHENTICATION) { is_auth_needed = 1; break; } @@ -314,6 +314,9 @@ enum mod_hdcp_status mod_hdcp_add_display(struct mod_hdcp *hdcp, goto out; } + /* save current encryption states to restore after next authentication */ + mod_hdcp_save_current_encryption_states(hdcp); + /* reset existing authentication status */ status = reset_authentication(hdcp, output); if (status != MOD_HDCP_STATUS_SUCCESS) @@ -360,6 +363,9 @@ enum mod_hdcp_status mod_hdcp_remove_display(struct mod_hdcp *hdcp, goto out; } + /* save current encryption states to restore after next authentication */ + mod_hdcp_save_current_encryption_states(hdcp); + /* stop current authentication */ status = reset_authentication(hdcp, output); if (status != MOD_HDCP_STATUS_SUCCESS) diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp.h b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp.h index 5c22cf7e6118..3ce91db560d1 100644 --- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp.h +++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp.h @@ -331,6 +331,8 @@ enum mod_hdcp_status mod_hdcp_add_display_to_topology( struct mod_hdcp *hdcp, struct mod_hdcp_display *display); enum mod_hdcp_status mod_hdcp_remove_display_from_topology( struct mod_hdcp *hdcp, uint8_t index); +bool mod_hdcp_is_link_encryption_enabled(struct mod_hdcp *hdcp); +void mod_hdcp_save_current_encryption_states(struct mod_hdcp *hdcp); enum mod_hdcp_status mod_hdcp_hdcp1_create_session(struct mod_hdcp *hdcp); enum mod_hdcp_status mod_hdcp_hdcp1_destroy_session(struct mod_hdcp *hdcp); enum mod_hdcp_status mod_hdcp_hdcp1_validate_rx(struct mod_hdcp *hdcp); @@ -339,8 +341,6 @@ enum mod_hdcp_status mod_hdcp_hdcp1_validate_ksvlist_vp(struct mod_hdcp *hdcp); enum mod_hdcp_status mod_hdcp_hdcp1_enable_dp_stream_encryption( struct mod_hdcp *hdcp); enum mod_hdcp_status mod_hdcp_hdcp1_link_maintenance(struct mod_hdcp *hdcp); -enum mod_hdcp_status mod_hdcp_hdcp1_get_link_encryption_status(struct mod_hdcp *hdcp, - enum mod_hdcp_encryption_status *encryption_status); enum mod_hdcp_status mod_hdcp_hdcp2_create_session(struct mod_hdcp *hdcp); enum mod_hdcp_status mod_hdcp_hdcp2_destroy_session(struct mod_hdcp *hdcp); enum mod_hdcp_status mod_hdcp_hdcp2_prepare_ake_init(struct mod_hdcp *hdcp); diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp1_execution.c b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp1_execution.c index 73ca49f05bd3..2cbd931363bd 100644 --- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp1_execution.c +++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp1_execution.c @@ -256,10 +256,12 @@ static enum mod_hdcp_status authenticated(struct mod_hdcp *hdcp, goto out; } - if (!mod_hdcp_execute_and_set(mod_hdcp_hdcp1_link_maintenance, + mod_hdcp_execute_and_set(mod_hdcp_hdcp1_link_maintenance, &input->link_maintenance, &status, - hdcp, "link_maintenance")) - goto out; + hdcp, "link_maintenance"); + + if (status != MOD_HDCP_STATUS_SUCCESS) + mod_hdcp_save_current_encryption_states(hdcp); out: return status; } @@ -426,18 +428,21 @@ static enum mod_hdcp_status authenticated_dp(struct mod_hdcp *hdcp, goto out; } - if (!mod_hdcp_execute_and_set(mod_hdcp_read_bstatus, - &input->bstatus_read, &status, - hdcp, "bstatus_read")) - goto out; - if (!mod_hdcp_execute_and_set(check_link_integrity_dp, - &input->link_integrity_check, &status, - hdcp, "link_integrity_check")) - goto out; - if (!mod_hdcp_execute_and_set(check_no_reauthentication_request_dp, - &input->reauth_request_check, &status, - hdcp, "reauth_request_check")) - goto out; + if (status == MOD_HDCP_STATUS_SUCCESS) + mod_hdcp_execute_and_set(mod_hdcp_read_bstatus, + &input->bstatus_read, &status, + hdcp, "bstatus_read"); + if (status == MOD_HDCP_STATUS_SUCCESS) + mod_hdcp_execute_and_set(check_link_integrity_dp, + &input->link_integrity_check, &status, + hdcp, "link_integrity_check"); + if (status == MOD_HDCP_STATUS_SUCCESS) + mod_hdcp_execute_and_set(check_no_reauthentication_request_dp, + &input->reauth_request_check, &status, + hdcp, "reauth_request_check"); + + if (status != MOD_HDCP_STATUS_SUCCESS) + mod_hdcp_save_current_encryption_states(hdcp); out: return status; } diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp1_transition.c b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp1_transition.c index 24ab95b093f7..3dda8c1d83fc 100644 --- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp1_transition.c +++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp1_transition.c @@ -93,7 +93,7 @@ enum mod_hdcp_status mod_hdcp_hdcp1_transition(struct mod_hdcp *hdcp, } break; case H1_A45_AUTHENTICATED: - if (input->link_maintenance != PASS) { + if (input->link_maintenance == FAIL) { /* 1A-07: consider invalid ri' a failure */ /* 1A-07a: consider read ri' not returned a failure */ fail_and_restart_in_ms(0, &status, output); @@ -243,8 +243,8 @@ enum mod_hdcp_status mod_hdcp_hdcp1_dp_transition(struct mod_hdcp *hdcp, } break; case D1_A4_AUTHENTICATED: - if (input->link_integrity_check != PASS || - input->reauth_request_check != PASS) { + if (input->link_integrity_check == FAIL || + input->reauth_request_check == FAIL) { /* 1A-07: restart hdcp on a link integrity failure */ fail_and_restart_in_ms(0, &status, output); break; diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp2_execution.c b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp2_execution.c index a0895a7efda2..c1331facdcb4 100644 --- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp2_execution.c +++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp2_execution.c @@ -565,10 +565,10 @@ static enum mod_hdcp_status authenticated(struct mod_hdcp *hdcp, goto out; } - if (!process_rxstatus(hdcp, event_ctx, input, &status)) - goto out; - if (event_ctx->rx_id_list_ready) - goto out; + process_rxstatus(hdcp, event_ctx, input, &status); + + if (status != MOD_HDCP_STATUS_SUCCESS) + mod_hdcp_save_current_encryption_states(hdcp); out: return status; } diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp2_transition.c b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp2_transition.c index e738c7ae66ec..b0306ed6d6b4 100644 --- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp2_transition.c +++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp2_transition.c @@ -245,8 +245,8 @@ enum mod_hdcp_status mod_hdcp_hdcp2_transition(struct mod_hdcp *hdcp, HDCP_FULL_DDC_TRACE(hdcp); break; case H2_A5_AUTHENTICATED: - if (input->rxstatus_read != PASS || - input->reauth_request_check != PASS) { + if (input->rxstatus_read == FAIL || + input->reauth_request_check == FAIL) { fail_and_restart_in_ms(0, &status, output); break; } else if (event_ctx->rx_id_list_ready && conn->is_repeater) { @@ -562,11 +562,11 @@ enum mod_hdcp_status mod_hdcp_hdcp2_dp_transition(struct mod_hdcp *hdcp, HDCP_FULL_DDC_TRACE(hdcp); break; case D2_A5_AUTHENTICATED: - if (input->rxstatus_read != PASS || - input->reauth_request_check != PASS) { + if (input->rxstatus_read == FAIL || + input->reauth_request_check == FAIL) { fail_and_restart_in_ms(0, &status, output); break; - } else if (input->link_integrity_check_dp != PASS) { + } else if (input->link_integrity_check_dp == FAIL) { if (hdcp->connection.hdcp2_retry_count >= 1) adjust->hdcp2.force_type = MOD_HDCP_FORCE_TYPE_0; fail_and_restart_in_ms(0, &status, output); diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c index 904ce9b88088..26f96c05e0ec 100644 --- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c +++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c @@ -791,6 +791,8 @@ enum mod_hdcp_status mod_hdcp_hdcp2_validate_rx_id_list(struct mod_hdcp *hdcp) TA_HDCP2_MSG_AUTHENTICATION_STATUS__RECEIVERID_REVOKED) { hdcp->connection.is_hdcp2_revoked = 1; status = MOD_HDCP_STATUS_HDCP2_RX_ID_LIST_REVOKED; + } else { + status = MOD_HDCP_STATUS_HDCP2_VALIDATE_RX_ID_LIST_FAILURE; } } mutex_unlock(&psp->hdcp_context.mutex); @@ -914,3 +916,13 @@ enum mod_hdcp_status mod_hdcp_hdcp2_validate_stream_ready(struct mod_hdcp *hdcp) return status; } +bool mod_hdcp_is_link_encryption_enabled(struct mod_hdcp *hdcp) +{ + /* unsupported */ + return true; +} + +void mod_hdcp_save_current_encryption_states(struct mod_hdcp *hdcp) +{ + /* unsupported */ +} diff --git a/drivers/gpu/drm/amd/display/modules/inc/mod_freesync.h b/drivers/gpu/drm/amd/display/modules/inc/mod_freesync.h index b64cd5bdc7b5..75a158a2514c 100644 --- a/drivers/gpu/drm/amd/display/modules/inc/mod_freesync.h +++ b/drivers/gpu/drm/amd/display/modules/inc/mod_freesync.h @@ -171,10 +171,15 @@ void mod_freesync_handle_v_update(struct mod_freesync *mod_freesync, unsigned long long mod_freesync_calc_nominal_field_rate( const struct dc_stream_state *stream); +unsigned long long mod_freesync_calc_field_rate_from_timing( + unsigned int vtotal, unsigned int htotal, unsigned int pix_clk); + bool mod_freesync_is_valid_range(uint32_t min_refresh_cap_in_uhz, uint32_t max_refresh_cap_in_uhz, uint32_t nominal_field_rate_in_uhz); - +unsigned int mod_freesync_calc_v_total_from_refresh( + const struct dc_stream_state *stream, + unsigned int refresh_in_uhz); #endif diff --git a/drivers/gpu/drm/amd/display/modules/inc/mod_hdcp.h b/drivers/gpu/drm/amd/display/modules/inc/mod_hdcp.h index d223ed3be5d3..acbeada5215b 100644 --- a/drivers/gpu/drm/amd/display/modules/inc/mod_hdcp.h +++ b/drivers/gpu/drm/amd/display/modules/inc/mod_hdcp.h @@ -120,6 +120,12 @@ enum mod_hdcp_display_state { MOD_HDCP_DISPLAY_ENCRYPTION_ENABLED }; +enum mod_hdcp_display_disable_option { + MOD_HDCP_DISPLAY_NOT_DISABLE = 0, + MOD_HDCP_DISPLAY_DISABLE_AUTHENTICATION, + MOD_HDCP_DISPLAY_DISABLE_ENCRYPTION, +}; + struct mod_hdcp_ddc { void *handle; struct { @@ -149,8 +155,8 @@ struct mod_hdcp_psp { }; struct mod_hdcp_display_adjustment { - uint8_t disable : 1; - uint8_t reserved : 7; + uint8_t disable : 2; + uint8_t reserved : 6; }; struct mod_hdcp_link_adjustment_hdcp1 { @@ -255,8 +261,6 @@ struct mod_hdcp_config { uint8_t index; }; -struct mod_hdcp; - /* dm allocates memory of mod_hdcp per dc_link on dm init based on memory size*/ size_t mod_hdcp_get_memory_size(void); diff --git a/drivers/gpu/drm/amd/include/asic_reg/gc/gc_10_3_0_offset.h b/drivers/gpu/drm/amd/include/asic_reg/gc/gc_10_3_0_offset.h index 0102487a2c5f..f21554a1c86c 100644 --- a/drivers/gpu/drm/amd/include/asic_reg/gc/gc_10_3_0_offset.h +++ b/drivers/gpu/drm/amd/include/asic_reg/gc/gc_10_3_0_offset.h @@ -6955,6 +6955,12 @@ #define mmCP_CE_IB2_BASE_HI_BASE_IDX 1 #define mmCP_CE_IB2_BUFSZ 0x20cb #define mmCP_CE_IB2_BUFSZ_BASE_IDX 1 +#define mmCP_IB1_BASE_LO 0x20cc +#define mmCP_IB1_BASE_LO_BASE_IDX 1 +#define mmCP_IB1_BASE_HI 0x20cd +#define mmCP_IB1_BASE_HI_BASE_IDX 1 +#define mmCP_IB1_BUFSZ 0x20ce +#define mmCP_IB1_BUFSZ_BASE_IDX 1 #define mmCP_IB2_BASE_LO 0x20cf #define mmCP_IB2_BASE_LO_BASE_IDX 1 #define mmCP_IB2_BASE_HI 0x20d0 diff --git a/drivers/gpu/drm/amd/include/asic_reg/gc/gc_10_3_0_sh_mask.h b/drivers/gpu/drm/amd/include/asic_reg/gc/gc_10_3_0_sh_mask.h index 4d2a1432c121..a827b0ff8905 100644 --- a/drivers/gpu/drm/amd/include/asic_reg/gc/gc_10_3_0_sh_mask.h +++ b/drivers/gpu/drm/amd/include/asic_reg/gc/gc_10_3_0_sh_mask.h @@ -25818,6 +25818,15 @@ //CP_CE_IB2_BUFSZ #define CP_CE_IB2_BUFSZ__IB2_BUFSZ__SHIFT 0x0 #define CP_CE_IB2_BUFSZ__IB2_BUFSZ_MASK 0x000FFFFFL +//CP_IB1_BASE_LO +#define CP_IB1_BASE_LO__IB1_BASE_LO__SHIFT 0x2 +#define CP_IB1_BASE_LO__IB1_BASE_LO_MASK 0xFFFFFFFCL +//CP_IB1_BASE_HI +#define CP_IB1_BASE_HI__IB1_BASE_HI__SHIFT 0x0 +#define CP_IB1_BASE_HI__IB1_BASE_HI_MASK 0x0000FFFFL +//CP_IB1_BUFSZ +#define CP_IB1_BUFSZ__IB1_BUFSZ__SHIFT 0x0 +#define CP_IB1_BUFSZ__IB1_BUFSZ_MASK 0x000FFFFFL //CP_IB2_BASE_LO #define CP_IB2_BASE_LO__IB2_BASE_LO__SHIFT 0x2 #define CP_IB2_BASE_LO__IB2_BASE_LO_MASK 0xFFFFFFFCL diff --git a/drivers/gpu/drm/amd/include/asic_reg/gc/gc_9_4_1_sh_mask.h b/drivers/gpu/drm/amd/include/asic_reg/gc/gc_9_4_1_sh_mask.h index 4089cfa081f5..849450caca15 100644 --- a/drivers/gpu/drm/amd/include/asic_reg/gc/gc_9_4_1_sh_mask.h +++ b/drivers/gpu/drm/amd/include/asic_reg/gc/gc_9_4_1_sh_mask.h @@ -617,6 +617,22 @@ #define GCEA_EDC_CNT3__MAM_A3MEM_SEC_COUNT_MASK 0x30000000L #define GCEA_EDC_CNT3__MAM_A3MEM_DED_COUNT_MASK 0xC0000000L +//GCEA_ERR_STATUS +#define GCEA_ERR_STATUS__SDP_RDRSP_STATUS__SHIFT 0x0 +#define GCEA_ERR_STATUS__SDP_WRRSP_STATUS__SHIFT 0x4 +#define GCEA_ERR_STATUS__SDP_RDRSP_DATASTATUS__SHIFT 0x8 +#define GCEA_ERR_STATUS__SDP_RDRSP_DATAPARITY_ERROR__SHIFT 0xa +#define GCEA_ERR_STATUS__CLEAR_ERROR_STATUS__SHIFT 0xb +#define GCEA_ERR_STATUS__BUSY_ON_ERROR__SHIFT 0xc +#define GCEA_ERR_STATUS__FUE_FLAG__SHIFT 0xd +#define GCEA_ERR_STATUS__SDP_RDRSP_STATUS_MASK 0x0000000FL +#define GCEA_ERR_STATUS__SDP_WRRSP_STATUS_MASK 0x000000F0L +#define GCEA_ERR_STATUS__SDP_RDRSP_DATASTATUS_MASK 0x00000300L +#define GCEA_ERR_STATUS__SDP_RDRSP_DATAPARITY_ERROR_MASK 0x00000400L +#define GCEA_ERR_STATUS__CLEAR_ERROR_STATUS_MASK 0x00000800L +#define GCEA_ERR_STATUS__BUSY_ON_ERROR_MASK 0x00001000L +#define GCEA_ERR_STATUS__FUE_FLAG_MASK 0x00002000L + // addressBlock: gc_gfxudec //GRBM_GFX_INDEX #define GRBM_GFX_INDEX__INSTANCE_INDEX__SHIFT 0x0 diff --git a/drivers/gpu/drm/amd/include/atombios.h b/drivers/gpu/drm/amd/include/atombios.h index c1d7b1d0b952..47eb84598b96 100644 --- a/drivers/gpu/drm/amd/include/atombios.h +++ b/drivers/gpu/drm/amd/include/atombios.h @@ -1987,9 +1987,9 @@ typedef struct _PIXEL_CLOCK_PARAMETERS_V6 #define PIXEL_CLOCK_V6_MISC_HDMI_BPP_MASK 0x0c #define PIXEL_CLOCK_V6_MISC_HDMI_24BPP 0x00 #define PIXEL_CLOCK_V6_MISC_HDMI_36BPP 0x04 -#define PIXEL_CLOCK_V6_MISC_HDMI_36BPP_V6 0x08 //for V6, the correct defintion for 36bpp should be 2 for 36bpp(2:1) +#define PIXEL_CLOCK_V6_MISC_HDMI_36BPP_V6 0x08 //for V6, the correct definition for 36bpp should be 2 for 36bpp(2:1) #define PIXEL_CLOCK_V6_MISC_HDMI_30BPP 0x08 -#define PIXEL_CLOCK_V6_MISC_HDMI_30BPP_V6 0x04 //for V6, the correct defintion for 30bpp should be 1 for 36bpp(5:4) +#define PIXEL_CLOCK_V6_MISC_HDMI_30BPP_V6 0x04 //for V6, the correct definition for 30bpp should be 1 for 36bpp(5:4) #define PIXEL_CLOCK_V6_MISC_HDMI_48BPP 0x0c #define PIXEL_CLOCK_V6_MISC_REF_DIV_SRC 0x10 #define PIXEL_CLOCK_V6_MISC_GEN_DPREFCLK 0x40 diff --git a/drivers/gpu/drm/amd/include/atomfirmware.h b/drivers/gpu/drm/amd/include/atomfirmware.h index 58364a8eb1f3..f2564ba21c0b 100644 --- a/drivers/gpu/drm/amd/include/atomfirmware.h +++ b/drivers/gpu/drm/amd/include/atomfirmware.h @@ -981,6 +981,40 @@ struct atom_display_controller_info_v4_2 uint8_t reserved3[8]; }; +struct atom_display_controller_info_v4_3 +{ + struct atom_common_table_header table_header; + uint32_t display_caps; + uint32_t bootup_dispclk_10khz; + uint16_t dce_refclk_10khz; + uint16_t i2c_engine_refclk_10khz; + uint16_t dvi_ss_percentage; // in unit of 0.001% + uint16_t dvi_ss_rate_10hz; + uint16_t hdmi_ss_percentage; // in unit of 0.001% + uint16_t hdmi_ss_rate_10hz; + uint16_t dp_ss_percentage; // in unit of 0.001% + uint16_t dp_ss_rate_10hz; + uint8_t dvi_ss_mode; // enum of atom_spread_spectrum_mode + uint8_t hdmi_ss_mode; // enum of atom_spread_spectrum_mode + uint8_t dp_ss_mode; // enum of atom_spread_spectrum_mode + uint8_t ss_reserved; + uint8_t dfp_hardcode_mode_num; // DFP hardcode mode number defined in StandardVESA_TimingTable when EDID is not available + uint8_t dfp_hardcode_refreshrate;// DFP hardcode mode refreshrate defined in StandardVESA_TimingTable when EDID is not available + uint8_t vga_hardcode_mode_num; // VGA hardcode mode number defined in StandardVESA_TimingTable when EDID is not avablable + uint8_t vga_hardcode_refreshrate;// VGA hardcode mode number defined in StandardVESA_TimingTable when EDID is not avablable + uint16_t dpphy_refclk_10khz; + uint16_t reserved2; + uint8_t dcnip_min_ver; + uint8_t dcnip_max_ver; + uint8_t max_disp_pipe_num; + uint8_t max_vbios_active_disp_pipe_num; + uint8_t max_ppll_num; + uint8_t max_disp_phy_num; + uint8_t max_aux_pairs; + uint8_t remotedisplayconfig; + uint8_t reserved3[8]; +}; + struct atom_display_controller_info_v4_4 { struct atom_common_table_header table_header; uint32_t display_caps; @@ -1043,7 +1077,9 @@ enum dce_info_caps_def DCE_INFO_CAPS_DISABLE_DFP_DP_HBR2 =0x04, // only for VBIOS DCE_INFO_CAPS_ENABLE_INTERLAC_TIMING =0x08, - + // only for VBIOS + DCE_INFO_CAPS_LTTPR_SUPPORT_ENABLE =0x20, + DCE_INFO_CAPS_VBIOS_LTTPR_TRANSPARENT_ENABLE = 0x40, }; /* @@ -3300,6 +3336,47 @@ enum atom_smu11_syspll3_1_clock_id { SMU11_SYSPLL3_1_LCLK_ID = 2, // LCLK }; +enum atom_smu12_syspll_id { + SMU12_SYSPLL0_ID = 0, + SMU12_SYSPLL1_ID = 1, + SMU12_SYSPLL2_ID = 2, + SMU12_SYSPLL3_0_ID = 3, + SMU12_SYSPLL3_1_ID = 4, +}; + +enum atom_smu12_syspll0_clock_id { + SMU12_SYSPLL0_SMNCLK_ID = 0, // SOCCLK + SMU12_SYSPLL0_SOCCLK_ID = 1, // SOCCLK + SMU12_SYSPLL0_MP0CLK_ID = 2, // MP0CLK + SMU12_SYSPLL0_MP1CLK_ID = 3, // MP1CLK + SMU12_SYSPLL0_MP2CLK_ID = 4, // MP2CLK + SMU12_SYSPLL0_VCLK_ID = 5, // VCLK + SMU12_SYSPLL0_LCLK_ID = 6, // LCLK + SMU12_SYSPLL0_DCLK_ID = 7, // DCLK + SMU12_SYSPLL0_ACLK_ID = 8, // ACLK + SMU12_SYSPLL0_ISPCLK_ID = 9, // ISPCLK + SMU12_SYSPLL0_SHUBCLK_ID = 10, // SHUBCLK +}; + +enum atom_smu12_syspll1_clock_id { + SMU12_SYSPLL1_DISPCLK_ID = 0, // DISPCLK + SMU12_SYSPLL1_DPPCLK_ID = 1, // DPPCLK + SMU12_SYSPLL1_DPREFCLK_ID = 2, // DPREFCLK + SMU12_SYSPLL1_DCFCLK_ID = 3, // DCFCLK +}; + +enum atom_smu12_syspll2_clock_id { + SMU12_SYSPLL2_Pre_GFXCLK_ID = 0, // Pre_GFXCLK +}; + +enum atom_smu12_syspll3_0_clock_id { + SMU12_SYSPLL3_0_FCLK_ID = 0, // FCLK +}; + +enum atom_smu12_syspll3_1_clock_id { + SMU12_SYSPLL3_1_UMCCLK_ID = 0, // UMCCLK +}; + struct atom_get_smu_clock_info_output_parameters_v3_1 { union { diff --git a/drivers/gpu/drm/amd/include/ivsrcid/dcn/irqsrcs_dcn_1_0.h b/drivers/gpu/drm/amd/include/ivsrcid/dcn/irqsrcs_dcn_1_0.h index e2bffcae273a..754170a86ea4 100644 --- a/drivers/gpu/drm/amd/include/ivsrcid/dcn/irqsrcs_dcn_1_0.h +++ b/drivers/gpu/drm/amd/include/ivsrcid/dcn/irqsrcs_dcn_1_0.h @@ -1132,5 +1132,7 @@ #define DCN_1_0__SRCID__DMCUB_OUTBOX_HIGH_PRIORITY_READY_INT 0x68 #define DCN_1_0__CTXID__DMCUB_OUTBOX_HIGH_PRIORITY_READY_INT 6 +#define DCN_1_0__SRCID__DMCUB_OUTBOX_LOW_PRIORITY_READY_INT 0x68 // DMCUB_IHC_outbox1_ready_int IHC_DMCUB_outbox1_ready_int_ack DMCUB_OUTBOX_LOW_PRIORITY_READY_INTERRUPT DISP_INTERRUPT_STATUS_CONTINUE24 Level/Pulse +#define DCN_1_0__CTXID__DMCUB_OUTBOX_LOW_PRIORITY_READY_INT 8 #endif // __IRQSRCS_DCN_1_0_H__ diff --git a/drivers/gpu/drm/amd/include/kgd_pp_interface.h b/drivers/gpu/drm/amd/include/kgd_pp_interface.h index dd695817c481..353468667036 100644 --- a/drivers/gpu/drm/amd/include/kgd_pp_interface.h +++ b/drivers/gpu/drm/amd/include/kgd_pp_interface.h @@ -242,6 +242,9 @@ struct pp_display_clock_request; struct pp_clock_levels_with_voltage; struct pp_clock_levels_with_latency; struct amd_pp_clocks; +struct pp_smu_wm_range_sets; +struct pp_smu_nv_clock_table; +struct dpm_clocks; struct amd_pm_funcs { /* export for dpm on ci and si */ @@ -336,6 +339,17 @@ struct amd_pm_funcs { int (*set_df_cstate)(void *handle, enum pp_df_cstate state); int (*set_xgmi_pstate)(void *handle, uint32_t pstate); ssize_t (*get_gpu_metrics)(void *handle, void **table); + int (*set_watermarks_for_clock_ranges)(void *handle, + struct pp_smu_wm_range_sets *ranges); + int (*display_disable_memory_clock_switch)(void *handle, + bool disable_memory_clock_switch); + int (*get_max_sustainable_clocks_by_dc)(void *handle, + struct pp_smu_nv_clock_table *max_clocks); + int (*get_uclk_dpm_states)(void *handle, + unsigned int *clock_values_in_khz, + unsigned int *num_states); + int (*get_dpm_clock_table)(void *handle, + struct dpm_clocks *clock_table); }; struct metrics_table_header { diff --git a/drivers/gpu/drm/amd/pm/amdgpu_dpm.c b/drivers/gpu/drm/amd/pm/amdgpu_dpm.c index 0a6bb3311f0f..03581d5b1836 100644 --- a/drivers/gpu/drm/amd/pm/amdgpu_dpm.c +++ b/drivers/gpu/drm/amd/pm/amdgpu_dpm.c @@ -927,7 +927,6 @@ int amdgpu_dpm_set_powergating_by_smu(struct amdgpu_device *adev, uint32_t block { int ret = 0; const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs; - bool swsmu = is_support_sw_smu(adev); switch (block_type) { case AMD_IP_BLOCK_TYPE_UVD: @@ -968,15 +967,7 @@ int amdgpu_dpm_set_powergating_by_smu(struct amdgpu_device *adev, uint32_t block case AMD_IP_BLOCK_TYPE_GFX: case AMD_IP_BLOCK_TYPE_VCN: case AMD_IP_BLOCK_TYPE_SDMA: - if (pp_funcs && pp_funcs->set_powergating_by_smu) { - ret = (pp_funcs->set_powergating_by_smu( - (adev)->powerplay.pp_handle, block_type, gate)); - } - break; case AMD_IP_BLOCK_TYPE_JPEG: - if (swsmu) - ret = smu_dpm_set_power_gate(&adev->smu, block_type, gate); - break; case AMD_IP_BLOCK_TYPE_GMC: case AMD_IP_BLOCK_TYPE_ACP: if (pp_funcs && pp_funcs->set_powergating_by_smu) { @@ -1606,7 +1597,10 @@ int amdgpu_pm_load_smu_firmware(struct amdgpu_device *adev, uint32_t *smu_versio pr_err("smu firmware loading failed\n"); return r; } - *smu_version = adev->pm.fw_version; + + if (smu_version) + *smu_version = adev->pm.fw_version; } + return 0; } diff --git a/drivers/gpu/drm/amd/pm/amdgpu_pm.c b/drivers/gpu/drm/amd/pm/amdgpu_pm.c index 2627870a786e..8128603ef495 100644 --- a/drivers/gpu/drm/amd/pm/amdgpu_pm.c +++ b/drivers/gpu/drm/amd/pm/amdgpu_pm.c @@ -27,7 +27,6 @@ #include "amdgpu_drv.h" #include "amdgpu_pm.h" #include "amdgpu_dpm.h" -#include "amdgpu_smu.h" #include "atom.h" #include <linux/pci.h> #include <linux/hwmon.h> @@ -129,6 +128,8 @@ static ssize_t amdgpu_get_power_dpm_state(struct device *dev, if (amdgpu_in_reset(adev)) return -EPERM; + if (adev->in_suspend && !adev->in_runpm) + return -EPERM; ret = pm_runtime_get_sync(ddev->dev); if (ret < 0) { @@ -145,9 +146,9 @@ static ssize_t amdgpu_get_power_dpm_state(struct device *dev, pm_runtime_mark_last_busy(ddev->dev); pm_runtime_put_autosuspend(ddev->dev); - return snprintf(buf, PAGE_SIZE, "%s\n", - (pm == POWER_STATE_TYPE_BATTERY) ? "battery" : - (pm == POWER_STATE_TYPE_BALANCED) ? "balanced" : "performance"); + return sysfs_emit(buf, "%s\n", + (pm == POWER_STATE_TYPE_BATTERY) ? "battery" : + (pm == POWER_STATE_TYPE_BALANCED) ? "balanced" : "performance"); } static ssize_t amdgpu_set_power_dpm_state(struct device *dev, @@ -162,6 +163,8 @@ static ssize_t amdgpu_set_power_dpm_state(struct device *dev, if (amdgpu_in_reset(adev)) return -EPERM; + if (adev->in_suspend && !adev->in_runpm) + return -EPERM; if (strncmp("battery", buf, strlen("battery")) == 0) state = POWER_STATE_TYPE_BATTERY; @@ -268,6 +271,8 @@ static ssize_t amdgpu_get_power_dpm_force_performance_level(struct device *dev, if (amdgpu_in_reset(adev)) return -EPERM; + if (adev->in_suspend && !adev->in_runpm) + return -EPERM; ret = pm_runtime_get_sync(ddev->dev); if (ret < 0) { @@ -283,17 +288,17 @@ static ssize_t amdgpu_get_power_dpm_force_performance_level(struct device *dev, pm_runtime_mark_last_busy(ddev->dev); pm_runtime_put_autosuspend(ddev->dev); - return snprintf(buf, PAGE_SIZE, "%s\n", - (level == AMD_DPM_FORCED_LEVEL_AUTO) ? "auto" : - (level == AMD_DPM_FORCED_LEVEL_LOW) ? "low" : - (level == AMD_DPM_FORCED_LEVEL_HIGH) ? "high" : - (level == AMD_DPM_FORCED_LEVEL_MANUAL) ? "manual" : - (level == AMD_DPM_FORCED_LEVEL_PROFILE_STANDARD) ? "profile_standard" : - (level == AMD_DPM_FORCED_LEVEL_PROFILE_MIN_SCLK) ? "profile_min_sclk" : - (level == AMD_DPM_FORCED_LEVEL_PROFILE_MIN_MCLK) ? "profile_min_mclk" : - (level == AMD_DPM_FORCED_LEVEL_PROFILE_PEAK) ? "profile_peak" : - (level == AMD_DPM_FORCED_LEVEL_PERF_DETERMINISM) ? "perf_determinism" : - "unknown"); + return sysfs_emit(buf, "%s\n", + (level == AMD_DPM_FORCED_LEVEL_AUTO) ? "auto" : + (level == AMD_DPM_FORCED_LEVEL_LOW) ? "low" : + (level == AMD_DPM_FORCED_LEVEL_HIGH) ? "high" : + (level == AMD_DPM_FORCED_LEVEL_MANUAL) ? "manual" : + (level == AMD_DPM_FORCED_LEVEL_PROFILE_STANDARD) ? "profile_standard" : + (level == AMD_DPM_FORCED_LEVEL_PROFILE_MIN_SCLK) ? "profile_min_sclk" : + (level == AMD_DPM_FORCED_LEVEL_PROFILE_MIN_MCLK) ? "profile_min_mclk" : + (level == AMD_DPM_FORCED_LEVEL_PROFILE_PEAK) ? "profile_peak" : + (level == AMD_DPM_FORCED_LEVEL_PERF_DETERMINISM) ? "perf_determinism" : + "unknown"); } static ssize_t amdgpu_set_power_dpm_force_performance_level(struct device *dev, @@ -310,6 +315,8 @@ static ssize_t amdgpu_set_power_dpm_force_performance_level(struct device *dev, if (amdgpu_in_reset(adev)) return -EPERM; + if (adev->in_suspend && !adev->in_runpm) + return -EPERM; if (strncmp("low", buf, strlen("low")) == 0) { level = AMD_DPM_FORCED_LEVEL_LOW; @@ -408,6 +415,8 @@ static ssize_t amdgpu_get_pp_num_states(struct device *dev, if (amdgpu_in_reset(adev)) return -EPERM; + if (adev->in_suspend && !adev->in_runpm) + return -EPERM; ret = pm_runtime_get_sync(ddev->dev); if (ret < 0) { @@ -448,6 +457,8 @@ static ssize_t amdgpu_get_pp_cur_state(struct device *dev, if (amdgpu_in_reset(adev)) return -EPERM; + if (adev->in_suspend && !adev->in_runpm) + return -EPERM; ret = pm_runtime_get_sync(ddev->dev); if (ret < 0) { @@ -472,7 +483,7 @@ static ssize_t amdgpu_get_pp_cur_state(struct device *dev, if (i == data.nums) i = -EINVAL; - return snprintf(buf, PAGE_SIZE, "%d\n", i); + return sysfs_emit(buf, "%d\n", i); } static ssize_t amdgpu_get_pp_force_state(struct device *dev, @@ -484,11 +495,13 @@ static ssize_t amdgpu_get_pp_force_state(struct device *dev, if (amdgpu_in_reset(adev)) return -EPERM; + if (adev->in_suspend && !adev->in_runpm) + return -EPERM; if (adev->pp_force_state_enabled) return amdgpu_get_pp_cur_state(dev, attr, buf); else - return snprintf(buf, PAGE_SIZE, "\n"); + return sysfs_emit(buf, "\n"); } static ssize_t amdgpu_set_pp_force_state(struct device *dev, @@ -504,6 +517,8 @@ static ssize_t amdgpu_set_pp_force_state(struct device *dev, if (amdgpu_in_reset(adev)) return -EPERM; + if (adev->in_suspend && !adev->in_runpm) + return -EPERM; if (strlen(buf) == 1) adev->pp_force_state_enabled = false; @@ -564,6 +579,8 @@ static ssize_t amdgpu_get_pp_table(struct device *dev, if (amdgpu_in_reset(adev)) return -EPERM; + if (adev->in_suspend && !adev->in_runpm) + return -EPERM; ret = pm_runtime_get_sync(ddev->dev); if (ret < 0) { @@ -602,6 +619,8 @@ static ssize_t amdgpu_set_pp_table(struct device *dev, if (amdgpu_in_reset(adev)) return -EPERM; + if (adev->in_suspend && !adev->in_runpm) + return -EPERM; ret = pm_runtime_get_sync(ddev->dev); if (ret < 0) { @@ -764,6 +783,8 @@ static ssize_t amdgpu_set_pp_od_clk_voltage(struct device *dev, if (amdgpu_in_reset(adev)) return -EPERM; + if (adev->in_suspend && !adev->in_runpm) + return -EPERM; if (count > 127) return -EINVAL; @@ -865,6 +886,8 @@ static ssize_t amdgpu_get_pp_od_clk_voltage(struct device *dev, if (amdgpu_in_reset(adev)) return -EPERM; + if (adev->in_suspend && !adev->in_runpm) + return -EPERM; ret = pm_runtime_get_sync(ddev->dev); if (ret < 0) { @@ -916,6 +939,8 @@ static ssize_t amdgpu_set_pp_features(struct device *dev, if (amdgpu_in_reset(adev)) return -EPERM; + if (adev->in_suspend && !adev->in_runpm) + return -EPERM; ret = kstrtou64(buf, 0, &featuremask); if (ret) @@ -927,14 +952,7 @@ static ssize_t amdgpu_set_pp_features(struct device *dev, return ret; } - if (is_support_sw_smu(adev)) { - ret = smu_sys_set_pp_feature_mask(&adev->smu, featuremask); - if (ret) { - pm_runtime_mark_last_busy(ddev->dev); - pm_runtime_put_autosuspend(ddev->dev); - return -EINVAL; - } - } else if (adev->powerplay.pp_funcs->set_ppfeature_status) { + if (adev->powerplay.pp_funcs->set_ppfeature_status) { ret = amdgpu_dpm_set_ppfeature_status(adev, featuremask); if (ret) { pm_runtime_mark_last_busy(ddev->dev); @@ -959,6 +977,8 @@ static ssize_t amdgpu_get_pp_features(struct device *dev, if (amdgpu_in_reset(adev)) return -EPERM; + if (adev->in_suspend && !adev->in_runpm) + return -EPERM; ret = pm_runtime_get_sync(ddev->dev); if (ret < 0) { @@ -1018,6 +1038,8 @@ static ssize_t amdgpu_get_pp_dpm_clock(struct device *dev, if (amdgpu_in_reset(adev)) return -EPERM; + if (adev->in_suspend && !adev->in_runpm) + return -EPERM; ret = pm_runtime_get_sync(ddev->dev); if (ret < 0) { @@ -1083,6 +1105,8 @@ static ssize_t amdgpu_set_pp_dpm_clock(struct device *dev, if (amdgpu_in_reset(adev)) return -EPERM; + if (adev->in_suspend && !adev->in_runpm) + return -EPERM; ret = amdgpu_read_mask(buf, count, &mask); if (ret) @@ -1239,6 +1263,8 @@ static ssize_t amdgpu_get_pp_sclk_od(struct device *dev, if (amdgpu_in_reset(adev)) return -EPERM; + if (adev->in_suspend && !adev->in_runpm) + return -EPERM; ret = pm_runtime_get_sync(ddev->dev); if (ret < 0) { @@ -1254,7 +1280,7 @@ static ssize_t amdgpu_get_pp_sclk_od(struct device *dev, pm_runtime_mark_last_busy(ddev->dev); pm_runtime_put_autosuspend(ddev->dev); - return snprintf(buf, PAGE_SIZE, "%d\n", value); + return sysfs_emit(buf, "%d\n", value); } static ssize_t amdgpu_set_pp_sclk_od(struct device *dev, @@ -1269,6 +1295,8 @@ static ssize_t amdgpu_set_pp_sclk_od(struct device *dev, if (amdgpu_in_reset(adev)) return -EPERM; + if (adev->in_suspend && !adev->in_runpm) + return -EPERM; ret = kstrtol(buf, 0, &value); @@ -1312,6 +1340,8 @@ static ssize_t amdgpu_get_pp_mclk_od(struct device *dev, if (amdgpu_in_reset(adev)) return -EPERM; + if (adev->in_suspend && !adev->in_runpm) + return -EPERM; ret = pm_runtime_get_sync(ddev->dev); if (ret < 0) { @@ -1327,7 +1357,7 @@ static ssize_t amdgpu_get_pp_mclk_od(struct device *dev, pm_runtime_mark_last_busy(ddev->dev); pm_runtime_put_autosuspend(ddev->dev); - return snprintf(buf, PAGE_SIZE, "%d\n", value); + return sysfs_emit(buf, "%d\n", value); } static ssize_t amdgpu_set_pp_mclk_od(struct device *dev, @@ -1342,6 +1372,8 @@ static ssize_t amdgpu_set_pp_mclk_od(struct device *dev, if (amdgpu_in_reset(adev)) return -EPERM; + if (adev->in_suspend && !adev->in_runpm) + return -EPERM; ret = kstrtol(buf, 0, &value); @@ -1405,6 +1437,8 @@ static ssize_t amdgpu_get_pp_power_profile_mode(struct device *dev, if (amdgpu_in_reset(adev)) return -EPERM; + if (adev->in_suspend && !adev->in_runpm) + return -EPERM; ret = pm_runtime_get_sync(ddev->dev); if (ret < 0) { @@ -1443,6 +1477,8 @@ static ssize_t amdgpu_set_pp_power_profile_mode(struct device *dev, if (amdgpu_in_reset(adev)) return -EPERM; + if (adev->in_suspend && !adev->in_runpm) + return -EPERM; tmp[0] = *(buf); tmp[1] = '\0'; @@ -1506,6 +1542,8 @@ static ssize_t amdgpu_get_gpu_busy_percent(struct device *dev, if (amdgpu_in_reset(adev)) return -EPERM; + if (adev->in_suspend && !adev->in_runpm) + return -EPERM; r = pm_runtime_get_sync(ddev->dev); if (r < 0) { @@ -1523,7 +1561,7 @@ static ssize_t amdgpu_get_gpu_busy_percent(struct device *dev, if (r) return r; - return snprintf(buf, PAGE_SIZE, "%d\n", value); + return sysfs_emit(buf, "%d\n", value); } /** @@ -1544,6 +1582,8 @@ static ssize_t amdgpu_get_mem_busy_percent(struct device *dev, if (amdgpu_in_reset(adev)) return -EPERM; + if (adev->in_suspend && !adev->in_runpm) + return -EPERM; r = pm_runtime_get_sync(ddev->dev); if (r < 0) { @@ -1561,7 +1601,7 @@ static ssize_t amdgpu_get_mem_busy_percent(struct device *dev, if (r) return r; - return snprintf(buf, PAGE_SIZE, "%d\n", value); + return sysfs_emit(buf, "%d\n", value); } /** @@ -1587,6 +1627,8 @@ static ssize_t amdgpu_get_pcie_bw(struct device *dev, if (amdgpu_in_reset(adev)) return -EPERM; + if (adev->in_suspend && !adev->in_runpm) + return -EPERM; if (adev->flags & AMD_IS_APU) return -ENODATA; @@ -1605,8 +1647,8 @@ static ssize_t amdgpu_get_pcie_bw(struct device *dev, pm_runtime_mark_last_busy(ddev->dev); pm_runtime_put_autosuspend(ddev->dev); - return snprintf(buf, PAGE_SIZE, "%llu %llu %i\n", - count0, count1, pcie_get_mps(adev->pdev)); + return sysfs_emit(buf, "%llu %llu %i\n", + count0, count1, pcie_get_mps(adev->pdev)); } /** @@ -1628,9 +1670,11 @@ static ssize_t amdgpu_get_unique_id(struct device *dev, if (amdgpu_in_reset(adev)) return -EPERM; + if (adev->in_suspend && !adev->in_runpm) + return -EPERM; if (adev->unique_id) - return snprintf(buf, PAGE_SIZE, "%016llx\n", adev->unique_id); + return sysfs_emit(buf, "%016llx\n", adev->unique_id); return 0; } @@ -1657,10 +1701,10 @@ static ssize_t amdgpu_get_thermal_throttling_logging(struct device *dev, struct drm_device *ddev = dev_get_drvdata(dev); struct amdgpu_device *adev = drm_to_adev(ddev); - return snprintf(buf, PAGE_SIZE, "%s: thermal throttling logging %s, with interval %d seconds\n", - adev_to_drm(adev)->unique, - atomic_read(&adev->throttling_logging_enabled) ? "enabled" : "disabled", - adev->throttling_logging_rs.interval / HZ + 1); + return sysfs_emit(buf, "%s: thermal throttling logging %s, with interval %d seconds\n", + adev_to_drm(adev)->unique, + atomic_read(&adev->throttling_logging_enabled) ? "enabled" : "disabled", + adev->throttling_logging_rs.interval / HZ + 1); } static ssize_t amdgpu_set_thermal_throttling_logging(struct device *dev, @@ -1726,6 +1770,8 @@ static ssize_t amdgpu_get_gpu_metrics(struct device *dev, if (amdgpu_in_reset(adev)) return -EPERM; + if (adev->in_suspend && !adev->in_runpm) + return -EPERM; ret = pm_runtime_get_sync(ddev->dev); if (ret < 0) { @@ -1798,7 +1844,9 @@ static int default_attr_update(struct amdgpu_device *adev, struct amdgpu_device_ if (asic_type < CHIP_VEGA10) *states = ATTR_STATE_UNSUPPORTED; } else if (DEVICE_ATTR_IS(pp_dpm_dcefclk)) { - if (asic_type < CHIP_VEGA10 || asic_type == CHIP_ARCTURUS) + if (asic_type < CHIP_VEGA10 || + asic_type == CHIP_ARCTURUS || + asic_type == CHIP_ALDEBARAN) *states = ATTR_STATE_UNSUPPORTED; } else if (DEVICE_ATTR_IS(pp_dpm_fclk)) { if (asic_type < CHIP_VEGA20) @@ -1954,6 +2002,8 @@ static ssize_t amdgpu_hwmon_show_temp(struct device *dev, if (amdgpu_in_reset(adev)) return -EPERM; + if (adev->in_suspend && !adev->in_runpm) + return -EPERM; if (channel >= PP_TEMP_MAX) return -EINVAL; @@ -1991,7 +2041,7 @@ static ssize_t amdgpu_hwmon_show_temp(struct device *dev, if (r) return r; - return snprintf(buf, PAGE_SIZE, "%d\n", temp); + return sysfs_emit(buf, "%d\n", temp); } static ssize_t amdgpu_hwmon_show_temp_thresh(struct device *dev, @@ -2007,7 +2057,7 @@ static ssize_t amdgpu_hwmon_show_temp_thresh(struct device *dev, else temp = adev->pm.dpm.thermal.max_temp; - return snprintf(buf, PAGE_SIZE, "%d\n", temp); + return sysfs_emit(buf, "%d\n", temp); } static ssize_t amdgpu_hwmon_show_hotspot_temp_thresh(struct device *dev, @@ -2023,7 +2073,7 @@ static ssize_t amdgpu_hwmon_show_hotspot_temp_thresh(struct device *dev, else temp = adev->pm.dpm.thermal.max_hotspot_crit_temp; - return snprintf(buf, PAGE_SIZE, "%d\n", temp); + return sysfs_emit(buf, "%d\n", temp); } static ssize_t amdgpu_hwmon_show_mem_temp_thresh(struct device *dev, @@ -2039,7 +2089,7 @@ static ssize_t amdgpu_hwmon_show_mem_temp_thresh(struct device *dev, else temp = adev->pm.dpm.thermal.max_mem_crit_temp; - return snprintf(buf, PAGE_SIZE, "%d\n", temp); + return sysfs_emit(buf, "%d\n", temp); } static ssize_t amdgpu_hwmon_show_temp_label(struct device *dev, @@ -2051,7 +2101,7 @@ static ssize_t amdgpu_hwmon_show_temp_label(struct device *dev, if (channel >= PP_TEMP_MAX) return -EINVAL; - return snprintf(buf, PAGE_SIZE, "%s\n", temp_label[channel].label); + return sysfs_emit(buf, "%s\n", temp_label[channel].label); } static ssize_t amdgpu_hwmon_show_temp_emergency(struct device *dev, @@ -2077,7 +2127,7 @@ static ssize_t amdgpu_hwmon_show_temp_emergency(struct device *dev, break; } - return snprintf(buf, PAGE_SIZE, "%d\n", temp); + return sysfs_emit(buf, "%d\n", temp); } static ssize_t amdgpu_hwmon_get_pwm1_enable(struct device *dev, @@ -2090,6 +2140,8 @@ static ssize_t amdgpu_hwmon_get_pwm1_enable(struct device *dev, if (amdgpu_in_reset(adev)) return -EPERM; + if (adev->in_suspend && !adev->in_runpm) + return -EPERM; ret = pm_runtime_get_sync(adev_to_drm(adev)->dev); if (ret < 0) { @@ -2122,6 +2174,8 @@ static ssize_t amdgpu_hwmon_set_pwm1_enable(struct device *dev, if (amdgpu_in_reset(adev)) return -EPERM; + if (adev->in_suspend && !adev->in_runpm) + return -EPERM; err = kstrtoint(buf, 10, &value); if (err) @@ -2172,6 +2226,8 @@ static ssize_t amdgpu_hwmon_set_pwm1(struct device *dev, if (amdgpu_in_reset(adev)) return -EPERM; + if (adev->in_suspend && !adev->in_runpm) + return -EPERM; err = pm_runtime_get_sync(adev_to_drm(adev)->dev); if (err < 0) { @@ -2220,6 +2276,8 @@ static ssize_t amdgpu_hwmon_get_pwm1(struct device *dev, if (amdgpu_in_reset(adev)) return -EPERM; + if (adev->in_suspend && !adev->in_runpm) + return -EPERM; err = pm_runtime_get_sync(adev_to_drm(adev)->dev); if (err < 0) { @@ -2253,6 +2311,8 @@ static ssize_t amdgpu_hwmon_get_fan1_input(struct device *dev, if (amdgpu_in_reset(adev)) return -EPERM; + if (adev->in_suspend && !adev->in_runpm) + return -EPERM; err = pm_runtime_get_sync(adev_to_drm(adev)->dev); if (err < 0) { @@ -2285,6 +2345,8 @@ static ssize_t amdgpu_hwmon_get_fan1_min(struct device *dev, if (amdgpu_in_reset(adev)) return -EPERM; + if (adev->in_suspend && !adev->in_runpm) + return -EPERM; r = pm_runtime_get_sync(adev_to_drm(adev)->dev); if (r < 0) { @@ -2301,7 +2363,7 @@ static ssize_t amdgpu_hwmon_get_fan1_min(struct device *dev, if (r) return r; - return snprintf(buf, PAGE_SIZE, "%d\n", min_rpm); + return sysfs_emit(buf, "%d\n", min_rpm); } static ssize_t amdgpu_hwmon_get_fan1_max(struct device *dev, @@ -2315,6 +2377,8 @@ static ssize_t amdgpu_hwmon_get_fan1_max(struct device *dev, if (amdgpu_in_reset(adev)) return -EPERM; + if (adev->in_suspend && !adev->in_runpm) + return -EPERM; r = pm_runtime_get_sync(adev_to_drm(adev)->dev); if (r < 0) { @@ -2331,7 +2395,7 @@ static ssize_t amdgpu_hwmon_get_fan1_max(struct device *dev, if (r) return r; - return snprintf(buf, PAGE_SIZE, "%d\n", max_rpm); + return sysfs_emit(buf, "%d\n", max_rpm); } static ssize_t amdgpu_hwmon_get_fan1_target(struct device *dev, @@ -2344,6 +2408,8 @@ static ssize_t amdgpu_hwmon_get_fan1_target(struct device *dev, if (amdgpu_in_reset(adev)) return -EPERM; + if (adev->in_suspend && !adev->in_runpm) + return -EPERM; err = pm_runtime_get_sync(adev_to_drm(adev)->dev); if (err < 0) { @@ -2376,6 +2442,8 @@ static ssize_t amdgpu_hwmon_set_fan1_target(struct device *dev, if (amdgpu_in_reset(adev)) return -EPERM; + if (adev->in_suspend && !adev->in_runpm) + return -EPERM; err = pm_runtime_get_sync(adev_to_drm(adev)->dev); if (err < 0) { @@ -2422,6 +2490,8 @@ static ssize_t amdgpu_hwmon_get_fan1_enable(struct device *dev, if (amdgpu_in_reset(adev)) return -EPERM; + if (adev->in_suspend && !adev->in_runpm) + return -EPERM; ret = pm_runtime_get_sync(adev_to_drm(adev)->dev); if (ret < 0) { @@ -2455,6 +2525,8 @@ static ssize_t amdgpu_hwmon_set_fan1_enable(struct device *dev, if (amdgpu_in_reset(adev)) return -EPERM; + if (adev->in_suspend && !adev->in_runpm) + return -EPERM; err = kstrtoint(buf, 10, &value); if (err) @@ -2496,6 +2568,8 @@ static ssize_t amdgpu_hwmon_show_vddgfx(struct device *dev, if (amdgpu_in_reset(adev)) return -EPERM; + if (adev->in_suspend && !adev->in_runpm) + return -EPERM; r = pm_runtime_get_sync(adev_to_drm(adev)->dev); if (r < 0) { @@ -2513,14 +2587,14 @@ static ssize_t amdgpu_hwmon_show_vddgfx(struct device *dev, if (r) return r; - return snprintf(buf, PAGE_SIZE, "%d\n", vddgfx); + return sysfs_emit(buf, "%d\n", vddgfx); } static ssize_t amdgpu_hwmon_show_vddgfx_label(struct device *dev, struct device_attribute *attr, char *buf) { - return snprintf(buf, PAGE_SIZE, "vddgfx\n"); + return sysfs_emit(buf, "vddgfx\n"); } static ssize_t amdgpu_hwmon_show_vddnb(struct device *dev, @@ -2533,6 +2607,8 @@ static ssize_t amdgpu_hwmon_show_vddnb(struct device *dev, if (amdgpu_in_reset(adev)) return -EPERM; + if (adev->in_suspend && !adev->in_runpm) + return -EPERM; /* only APUs have vddnb */ if (!(adev->flags & AMD_IS_APU)) @@ -2554,14 +2630,14 @@ static ssize_t amdgpu_hwmon_show_vddnb(struct device *dev, if (r) return r; - return snprintf(buf, PAGE_SIZE, "%d\n", vddnb); + return sysfs_emit(buf, "%d\n", vddnb); } static ssize_t amdgpu_hwmon_show_vddnb_label(struct device *dev, struct device_attribute *attr, char *buf) { - return snprintf(buf, PAGE_SIZE, "vddnb\n"); + return sysfs_emit(buf, "vddnb\n"); } static ssize_t amdgpu_hwmon_show_power_avg(struct device *dev, @@ -2575,6 +2651,8 @@ static ssize_t amdgpu_hwmon_show_power_avg(struct device *dev, if (amdgpu_in_reset(adev)) return -EPERM; + if (adev->in_suspend && !adev->in_runpm) + return -EPERM; r = pm_runtime_get_sync(adev_to_drm(adev)->dev); if (r < 0) { @@ -2595,7 +2673,7 @@ static ssize_t amdgpu_hwmon_show_power_avg(struct device *dev, /* convert to microwatts */ uw = (query >> 8) * 1000000 + (query & 0xff) * 1000; - return snprintf(buf, PAGE_SIZE, "%u\n", uw); + return sysfs_emit(buf, "%u\n", uw); } static ssize_t amdgpu_hwmon_show_power_cap_min(struct device *dev, @@ -2619,6 +2697,8 @@ static ssize_t amdgpu_hwmon_show_power_cap_max(struct device *dev, if (amdgpu_in_reset(adev)) return -EPERM; + if (adev->in_suspend && !adev->in_runpm) + return -EPERM; r = pm_runtime_get_sync(adev_to_drm(adev)->dev); if (r < 0) { @@ -2656,6 +2736,8 @@ static ssize_t amdgpu_hwmon_show_power_cap(struct device *dev, if (amdgpu_in_reset(adev)) return -EPERM; + if (adev->in_suspend && !adev->in_runpm) + return -EPERM; r = pm_runtime_get_sync(adev_to_drm(adev)->dev); if (r < 0) { @@ -2693,6 +2775,8 @@ static ssize_t amdgpu_hwmon_show_power_cap_default(struct device *dev, if (amdgpu_in_reset(adev)) return -EPERM; + if (adev->in_suspend && !adev->in_runpm) + return -EPERM; r = pm_runtime_get_sync(adev_to_drm(adev)->dev); if (r < 0) { @@ -2722,7 +2806,7 @@ static ssize_t amdgpu_hwmon_show_power_label(struct device *dev, { int limit_type = to_sensor_dev_attr(attr)->index; - return snprintf(buf, PAGE_SIZE, "%s\n", + return sysfs_emit(buf, "%s\n", limit_type == SMU_FAST_PPT_LIMIT ? "fastPPT" : "slowPPT"); } @@ -2739,6 +2823,8 @@ static ssize_t amdgpu_hwmon_set_power_cap(struct device *dev, if (amdgpu_in_reset(adev)) return -EPERM; + if (adev->in_suspend && !adev->in_runpm) + return -EPERM; if (amdgpu_sriov_vf(adev)) return -EINVAL; @@ -2780,6 +2866,8 @@ static ssize_t amdgpu_hwmon_show_sclk(struct device *dev, if (amdgpu_in_reset(adev)) return -EPERM; + if (adev->in_suspend && !adev->in_runpm) + return -EPERM; r = pm_runtime_get_sync(adev_to_drm(adev)->dev); if (r < 0) { @@ -2797,14 +2885,14 @@ static ssize_t amdgpu_hwmon_show_sclk(struct device *dev, if (r) return r; - return snprintf(buf, PAGE_SIZE, "%u\n", sclk * 10 * 1000); + return sysfs_emit(buf, "%u\n", sclk * 10 * 1000); } static ssize_t amdgpu_hwmon_show_sclk_label(struct device *dev, struct device_attribute *attr, char *buf) { - return snprintf(buf, PAGE_SIZE, "sclk\n"); + return sysfs_emit(buf, "sclk\n"); } static ssize_t amdgpu_hwmon_show_mclk(struct device *dev, @@ -2817,6 +2905,8 @@ static ssize_t amdgpu_hwmon_show_mclk(struct device *dev, if (amdgpu_in_reset(adev)) return -EPERM; + if (adev->in_suspend && !adev->in_runpm) + return -EPERM; r = pm_runtime_get_sync(adev_to_drm(adev)->dev); if (r < 0) { @@ -2834,14 +2924,14 @@ static ssize_t amdgpu_hwmon_show_mclk(struct device *dev, if (r) return r; - return snprintf(buf, PAGE_SIZE, "%u\n", mclk * 10 * 1000); + return sysfs_emit(buf, "%u\n", mclk * 10 * 1000); } static ssize_t amdgpu_hwmon_show_mclk_label(struct device *dev, struct device_attribute *attr, char *buf) { - return snprintf(buf, PAGE_SIZE, "mclk\n"); + return sysfs_emit(buf, "mclk\n"); } /** @@ -3390,6 +3480,8 @@ static int amdgpu_debugfs_pm_info_show(struct seq_file *m, void *unused) if (amdgpu_in_reset(adev)) return -EPERM; + if (adev->in_suspend && !adev->in_runpm) + return -EPERM; r = pm_runtime_get_sync(dev->dev); if (r < 0) { diff --git a/drivers/gpu/drm/amd/pm/inc/aldebaran_ppsmc.h b/drivers/gpu/drm/amd/pm/inc/aldebaran_ppsmc.h index 433dd1e9ec4f..610266088ff1 100644 --- a/drivers/gpu/drm/amd/pm/inc/aldebaran_ppsmc.h +++ b/drivers/gpu/drm/amd/pm/inc/aldebaran_ppsmc.h @@ -100,7 +100,8 @@ #define PPSMC_MSG_SetSystemVirtualSTBtoDramAddrHigh 0x40 #define PPSMC_MSG_SetSystemVirtualSTBtoDramAddrLow 0x41 -#define PPSMC_Message_Count 0x42 +#define PPSMC_MSG_GfxDriverResetRecovery 0x42 +#define PPSMC_Message_Count 0x43 //PPSMC Reset Types #define PPSMC_RESET_TYPE_WARM_RESET 0x00 diff --git a/drivers/gpu/drm/amd/pm/inc/amdgpu_smu.h b/drivers/gpu/drm/amd/pm/inc/amdgpu_smu.h index 25d5f03aaa67..8bb224f6c762 100644 --- a/drivers/gpu/drm/amd/pm/inc/amdgpu_smu.h +++ b/drivers/gpu/drm/amd/pm/inc/amdgpu_smu.h @@ -195,6 +195,11 @@ struct smu_user_dpm_profile { uint32_t clk_dependency; }; +enum smu_event_type { + + SMU_EVENT_RESET_COMPLETE = 0, +}; + #define SMU_TABLE_INIT(tables, table_id, s, a, d) \ do { \ tables[table_id].size = s; \ @@ -338,7 +343,6 @@ struct smu_power_context { struct smu_power_gate power_gate; }; - #define SMU_FEATURE_MAX (64) struct smu_feature { @@ -807,6 +811,13 @@ struct pptable_funcs { int (*check_fw_status)(struct smu_context *smu); /** + * @set_mp1_state: put SMU into a correct state for comming + * resume from runpm or gpu reset. + */ + int (*set_mp1_state)(struct smu_context *smu, + enum pp_mp1_state mp1_state); + + /** * @setup_pptable: Initialize the power play table and populate it with * default values. */ @@ -1160,6 +1171,12 @@ struct pptable_funcs { * @set_light_sbr: Set light sbr mode for the SMU. */ int (*set_light_sbr)(struct smu_context *smu, bool enable); + + /** + * @wait_for_event: Wait for events from SMU. + */ + int (*wait_for_event)(struct smu_context *smu, + enum smu_event_type event, uint64_t event_arg); }; typedef enum { @@ -1235,64 +1252,13 @@ enum smu_cmn2asic_mapping_type { [profile] = {1, (workload)} #if !defined(SWSMU_CODE_LAYER_L2) && !defined(SWSMU_CODE_LAYER_L3) && !defined(SWSMU_CODE_LAYER_L4) -int smu_load_microcode(struct smu_context *smu); - -int smu_check_fw_status(struct smu_context *smu); - -int smu_set_gfx_cgpg(struct smu_context *smu, bool enabled); - -int smu_set_fan_speed_rpm(void *handle, uint32_t speed); - int smu_get_power_limit(struct smu_context *smu, uint32_t *limit, enum smu_ppt_limit_level limit_level); -int smu_set_power_limit(void *handle, uint32_t limit); -int smu_print_ppclk_levels(void *handle, enum pp_clock_type type, char *buf); - -int smu_od_edit_dpm_table(void *handle, - enum PP_OD_DPM_TABLE_COMMAND type, - long *input, uint32_t size); - -int smu_read_sensor(void *handle, int sensor, void *data, int *size); -int smu_get_power_profile_mode(void *handle, char *buf); -int smu_set_power_profile_mode(void *handle, long *param, uint32_t param_size); -u32 smu_get_fan_control_mode(void *handle); -int smu_set_fan_control_mode(struct smu_context *smu, int value); -void smu_pp_set_fan_control_mode(void *handle, u32 value); -int smu_get_fan_speed_percent(void *handle, u32 *speed); -int smu_set_fan_speed_percent(void *handle, u32 speed); -int smu_get_fan_speed_rpm(void *handle, uint32_t *speed); - -int smu_set_deep_sleep_dcefclk(struct smu_context *smu, int clk); - -int smu_get_clock_by_type_with_latency(struct smu_context *smu, - enum smu_clk_type clk_type, - struct pp_clock_levels_with_latency *clocks); - -int smu_display_clock_voltage_request(struct smu_context *smu, - struct pp_display_clock_request *clock_req); -int smu_display_disable_memory_clock_switch(struct smu_context *smu, bool disable_memory_clock_switch); - -int smu_set_xgmi_pstate(void *handle, - uint32_t pstate); - -int smu_set_azalia_d3_pme(struct smu_context *smu); - -bool smu_baco_is_support(struct smu_context *smu); -int smu_get_baco_capability(void *handle, bool *cap); - -int smu_baco_get_state(struct smu_context *smu, enum smu_baco_state *state); - -int smu_baco_enter(struct smu_context *smu); -int smu_baco_exit(struct smu_context *smu); -int smu_baco_set_state(void *handle, int state); - - bool smu_mode1_reset_is_support(struct smu_context *smu); bool smu_mode2_reset_is_support(struct smu_context *smu); int smu_mode1_reset(struct smu_context *smu); -int smu_mode2_reset(void *handle); extern const struct amd_ip_funcs smu_ip_funcs; @@ -1302,68 +1268,24 @@ extern const struct amdgpu_ip_block_version smu_v13_0_ip_block; bool is_support_sw_smu(struct amdgpu_device *adev); bool is_support_cclk_dpm(struct amdgpu_device *adev); -int smu_reset(struct smu_context *smu); -int smu_sys_get_pp_table(void *handle, char **table); -int smu_sys_set_pp_table(void *handle, const char *buf, size_t size); -int smu_get_power_num_states(void *handle, struct pp_states_info *state_info); -enum amd_pm_state_type smu_get_current_power_state(void *handle); int smu_write_watermarks_table(struct smu_context *smu); -int smu_set_watermarks_for_clock_ranges( - struct smu_context *smu, - struct pp_smu_wm_range_sets *clock_ranges); - -/* smu to display interface */ -extern int smu_display_configuration_change(struct smu_context *smu, const - struct amd_pp_display_configuration - *display_config); -extern int smu_dpm_set_power_gate(void *handle, uint32_t block_type, bool gate); -extern int smu_handle_task(struct smu_context *smu, - enum amd_dpm_forced_level level, - enum amd_pp_task task_id, - bool lock_needed); -extern int smu_handle_dpm_task(void *handle, - enum amd_pp_task task_id, - enum amd_pm_state_type *user_state); -int smu_switch_power_profile(void *handle, - enum PP_SMC_POWER_PROFILE type, - bool en); + int smu_get_dpm_freq_range(struct smu_context *smu, enum smu_clk_type clk_type, uint32_t *min, uint32_t *max); -u32 smu_get_mclk(void *handle, bool low); -u32 smu_get_sclk(void *handle, bool low); + int smu_set_soft_freq_range(struct smu_context *smu, enum smu_clk_type clk_type, uint32_t min, uint32_t max); -enum amd_dpm_forced_level smu_get_performance_level(void *handle); -int smu_force_performance_level(void *handle, enum amd_dpm_forced_level level); -int smu_set_display_count(struct smu_context *smu, uint32_t count); -int smu_set_ac_dc(struct smu_context *smu); -int smu_sys_get_pp_feature_mask(void *handle, char *buf); -int smu_sys_set_pp_feature_mask(void *handle, uint64_t new_mask); -int smu_force_ppclk_levels(void *handle, enum pp_clock_type type, uint32_t mask); -int smu_set_mp1_state(void *handle, - enum pp_mp1_state mp1_state); -int smu_set_df_cstate(void *handle, - enum pp_df_cstate state); -int smu_allow_xgmi_power_down(struct smu_context *smu, bool en); -int smu_get_max_sustainable_clocks_by_dc(struct smu_context *smu, - struct pp_smu_nv_clock_table *max_clocks); - -int smu_get_uclk_dpm_states(struct smu_context *smu, - unsigned int *clock_values_in_khz, - unsigned int *num_states); +int smu_set_ac_dc(struct smu_context *smu); -int smu_get_dpm_clock_table(struct smu_context *smu, - struct dpm_clocks *clock_table); +int smu_allow_xgmi_power_down(struct smu_context *smu, bool en); int smu_get_status_gfxoff(struct amdgpu_device *adev, uint32_t *value); -ssize_t smu_sys_get_gpu_metrics(void *handle, void **table); - -int smu_enable_mgpu_fan_boost(void *handle); -int smu_gfx_state_change_set(struct smu_context *smu, uint32_t state); - int smu_set_light_sbr(struct smu_context *smu, bool enable); +int smu_wait_for_event(struct amdgpu_device *adev, enum smu_event_type event, + uint64_t event_arg); + #endif #endif diff --git a/drivers/gpu/drm/amd/pm/inc/smu11_driver_if_vangogh.h b/drivers/gpu/drm/amd/pm/inc/smu11_driver_if_vangogh.h index 6e23a3f803a7..8361ebd8d876 100644 --- a/drivers/gpu/drm/amd/pm/inc/smu11_driver_if_vangogh.h +++ b/drivers/gpu/drm/amd/pm/inc/smu11_driver_if_vangogh.h @@ -26,7 +26,7 @@ // *** IMPORTANT *** // SMU TEAM: Always increment the interface version if // any structure is changed in this file -#define SMU13_DRIVER_IF_VERSION 2 +#define SMU13_DRIVER_IF_VERSION 3 typedef struct { int32_t value; @@ -191,6 +191,44 @@ typedef struct { uint16_t SocTemperature; //[centi-Celsius] uint16_t EdgeTemperature; uint16_t ThrottlerStatus; +} SmuMetrics_legacy_t; + +typedef struct { + uint16_t GfxclkFrequency; //[MHz] + uint16_t SocclkFrequency; //[MHz] + uint16_t VclkFrequency; //[MHz] + uint16_t DclkFrequency; //[MHz] + uint16_t MemclkFrequency; //[MHz] + uint16_t spare; + + uint16_t GfxActivity; //[centi] + uint16_t UvdActivity; //[centi] + uint16_t C0Residency[4]; //percentage + + uint16_t Voltage[3]; //[mV] indices: VDDCR_VDD, VDDCR_SOC, VDDCR_GFX + uint16_t Current[3]; //[mA] indices: VDDCR_VDD, VDDCR_SOC, VDDCR_GFX + uint16_t Power[3]; //[mW] indices: VDDCR_VDD, VDDCR_SOC, VDDCR_GFX + uint16_t CurrentSocketPower; //[mW] + + //3rd party tools in Windows need info in the case of APUs + uint16_t CoreFrequency[4]; //[MHz] + uint16_t CorePower[4]; //[mW] + uint16_t CoreTemperature[4]; //[centi-Celsius] + uint16_t L3Frequency[1]; //[MHz] + uint16_t L3Temperature[1]; //[centi-Celsius] + + uint16_t GfxTemperature; //[centi-Celsius] + uint16_t SocTemperature; //[centi-Celsius] + uint16_t EdgeTemperature; + uint16_t ThrottlerStatus; +} SmuMetricsTable_t; + +typedef struct { + SmuMetricsTable_t Current; + SmuMetricsTable_t Average; + //uint32_t AccCnt; + uint32_t SampleStartTime; + uint32_t SampleStopTime; } SmuMetrics_t; diff --git a/drivers/gpu/drm/amd/pm/inc/smu13_driver_if_aldebaran.h b/drivers/gpu/drm/amd/pm/inc/smu13_driver_if_aldebaran.h index df2ead254f37..d23533bda002 100644 --- a/drivers/gpu/drm/amd/pm/inc/smu13_driver_if_aldebaran.h +++ b/drivers/gpu/drm/amd/pm/inc/smu13_driver_if_aldebaran.h @@ -435,8 +435,12 @@ typedef struct { uint8_t GpioI2cSda; // Serial Data uint16_t spare5; + uint16_t XgmiMaxCurrent; // in Amps + int8_t XgmiOffset; // in Amps + uint8_t Padding_TelemetryXgmi; + //reserved - uint32_t reserved[16]; + uint32_t reserved[15]; } PPTable_t; @@ -481,7 +485,10 @@ typedef struct { uint16_t TemperatureAllHBM[4] ; uint32_t GfxBusyAcc ; uint32_t DramBusyAcc ; - uint32_t Spare[4]; + uint32_t EnergyAcc64bitLow ; //15.259uJ resolution + uint32_t EnergyAcc64bitHigh ; + uint32_t TimeStampLow ; //10ns resolution + uint32_t TimeStampHigh ; // Padding - ignore uint32_t MmHubPadding[8]; // SMU internal use diff --git a/drivers/gpu/drm/amd/pm/inc/smu_types.h b/drivers/gpu/drm/amd/pm/inc/smu_types.h index 5bfb60f41dd4..89a16dcd0fff 100644 --- a/drivers/gpu/drm/amd/pm/inc/smu_types.h +++ b/drivers/gpu/drm/amd/pm/inc/smu_types.h @@ -225,6 +225,7 @@ __SMU_DUMMY_MAP(DisableDeterminism), \ __SMU_DUMMY_MAP(SetUclkDpmMode), \ __SMU_DUMMY_MAP(LightSBR), \ + __SMU_DUMMY_MAP(GfxDriverResetRecovery), #undef __SMU_DUMMY_MAP #define __SMU_DUMMY_MAP(type) SMU_MSG_##type diff --git a/drivers/gpu/drm/amd/pm/inc/smu_v11_0.h b/drivers/gpu/drm/amd/pm/inc/smu_v11_0.h index ad4db2edf1fb..bb55a96f98e9 100644 --- a/drivers/gpu/drm/amd/pm/inc/smu_v11_0.h +++ b/drivers/gpu/drm/amd/pm/inc/smu_v11_0.h @@ -32,7 +32,7 @@ #define SMU11_DRIVER_IF_VERSION_NV14 0x38 #define SMU11_DRIVER_IF_VERSION_Sienna_Cichlid 0x3D #define SMU11_DRIVER_IF_VERSION_Navy_Flounder 0xE -#define SMU11_DRIVER_IF_VERSION_VANGOGH 0x02 +#define SMU11_DRIVER_IF_VERSION_VANGOGH 0x03 #define SMU11_DRIVER_IF_VERSION_Dimgrey_Cavefish 0xF /* MP Apertures */ @@ -61,8 +61,8 @@ #define LINK_WIDTH_MAX 6 #define LINK_SPEED_MAX 3 -static __maybe_unused uint16_t link_width[] = {0, 1, 2, 4, 8, 12, 16}; -static __maybe_unused uint16_t link_speed[] = {25, 50, 80, 160}; +static const __maybe_unused uint16_t link_width[] = {0, 1, 2, 4, 8, 12, 16}; +static const __maybe_unused uint16_t link_speed[] = {25, 50, 80, 160}; static const struct smu_temperature_range __maybe_unused smu11_thermal_policy[] = diff --git a/drivers/gpu/drm/amd/pm/inc/smu_v12_0.h b/drivers/gpu/drm/amd/pm/inc/smu_v12_0.h index 02de3b6199e5..1ad2dff71090 100644 --- a/drivers/gpu/drm/amd/pm/inc/smu_v12_0.h +++ b/drivers/gpu/drm/amd/pm/inc/smu_v12_0.h @@ -60,5 +60,7 @@ int smu_v12_0_set_soft_freq_limited_range(struct smu_context *smu, enum smu_clk_ int smu_v12_0_set_driver_table_location(struct smu_context *smu); +int smu_v12_0_get_vbios_bootup_values(struct smu_context *smu); + #endif #endif diff --git a/drivers/gpu/drm/amd/pm/inc/smu_v13_0.h b/drivers/gpu/drm/amd/pm/inc/smu_v13_0.h index 80208e1eefc9..8145e1cbf181 100644 --- a/drivers/gpu/drm/amd/pm/inc/smu_v13_0.h +++ b/drivers/gpu/drm/amd/pm/inc/smu_v13_0.h @@ -26,7 +26,7 @@ #include "amdgpu_smu.h" #define SMU13_DRIVER_IF_VERSION_INV 0xFFFFFFFF -#define SMU13_DRIVER_IF_VERSION_ALDE 0x5 +#define SMU13_DRIVER_IF_VERSION_ALDE 0x6 /* MP Apertures */ #define MP0_Public 0x03800000 @@ -268,5 +268,8 @@ int smu_v13_0_get_current_pcie_link_speed(struct smu_context *smu); int smu_v13_0_gfx_ulv_control(struct smu_context *smu, bool enablement); +int smu_v13_0_wait_for_event(struct smu_context *smu, enum smu_event_type event, + uint64_t event_arg); + #endif #endif diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c index f5d59fa3a030..f5fe540cd536 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c @@ -1297,19 +1297,18 @@ static int smu10_read_sensor(struct pp_hwmgr *hwmgr, int idx, *size = 4; break; case AMDGPU_PP_SENSOR_GPU_LOAD: - if (has_gfx_busy) { + if (!has_gfx_busy) + ret = -EOPNOTSUPP; + else { ret = smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetGfxBusy, &activity_percent); if (!ret) - activity_percent = activity_percent > 100 ? 100 : activity_percent; + *((uint32_t *)value) = min(activity_percent, (u32)100); else - return -EIO; - *((uint32_t *)value) = activity_percent; - return 0; - } else { - return -EOPNOTSUPP; + ret = -EIO; } + break; default: ret = -EOPNOTSUPP; break; diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c index 7edafef095a3..0541bfc81c1b 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c @@ -1224,7 +1224,8 @@ static int smu7_enable_sclk_mclk_dpm(struct pp_hwmgr *hwmgr) (hwmgr->chip_id == CHIP_POLARIS10) || (hwmgr->chip_id == CHIP_POLARIS11) || (hwmgr->chip_id == CHIP_POLARIS12) || - (hwmgr->chip_id == CHIP_TONGA)) + (hwmgr->chip_id == CHIP_TONGA) || + (hwmgr->chip_id == CHIP_TOPAZ)) PHM_WRITE_FIELD(hwmgr->device, MC_SEQ_CNTL_3, CAC_EN, 0x1); @@ -3330,7 +3331,8 @@ static int smu7_apply_state_adjust_rules(struct pp_hwmgr *hwmgr, disable_mclk_switching_for_display = ((1 < hwmgr->display_config->num_display) && !hwmgr->display_config->multi_monitor_in_sync) || - smu7_vblank_too_short(hwmgr, hwmgr->display_config->min_vblank_time); + (hwmgr->display_config->num_display && + smu7_vblank_too_short(hwmgr, hwmgr->display_config->min_vblank_time)); disable_mclk_switching = disable_mclk_switching_for_frame_lock || disable_mclk_switching_for_display; diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c index b6d7b7b224a9..1a097e608808 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c @@ -52,8 +52,8 @@ #define LINK_WIDTH_MAX 6 #define LINK_SPEED_MAX 3 -static int link_width[] = {0, 1, 2, 4, 8, 12, 16}; -static int link_speed[] = {25, 50, 80, 160}; +static const int link_width[] = {0, 1, 2, 4, 8, 12, 16}; +static const int link_speed[] = {25, 50, 80, 160}; static int vega12_force_clock_level(struct pp_hwmgr *hwmgr, enum pp_clock_type type, uint32_t mask); diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c index 213c9c6b4462..d3177a534fdf 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c @@ -57,8 +57,8 @@ #define LINK_WIDTH_MAX 6 #define LINK_SPEED_MAX 3 -static int link_width[] = {0, 1, 2, 4, 8, 12, 16}; -static int link_speed[] = {25, 50, 80, 160}; +static const int link_width[] = {0, 1, 2, 4, 8, 12, 16}; +static const int link_speed[] = {25, 50, 80, 160}; static void vega20_set_default_registry_data(struct pp_hwmgr *hwmgr) { diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c index e722adcf2f53..c29d8b3131b7 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c +++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c @@ -51,8 +51,19 @@ static const struct amd_pm_funcs swsmu_pm_funcs; static int smu_force_smuclk_levels(struct smu_context *smu, enum smu_clk_type clk_type, uint32_t mask); - -int smu_sys_get_pp_feature_mask(void *handle, char *buf) +static int smu_handle_task(struct smu_context *smu, + enum amd_dpm_forced_level level, + enum amd_pp_task task_id, + bool lock_needed); +static int smu_reset(struct smu_context *smu); +static int smu_set_fan_speed_percent(void *handle, u32 speed); +static int smu_set_fan_control_mode(struct smu_context *smu, int value); +static int smu_set_power_limit(void *handle, uint32_t limit); +static int smu_set_fan_speed_rpm(void *handle, uint32_t speed); +static int smu_set_gfx_cgpg(struct smu_context *smu, bool enabled); + +static int smu_sys_get_pp_feature_mask(void *handle, + char *buf) { struct smu_context *smu = handle; int size = 0; @@ -69,7 +80,8 @@ int smu_sys_get_pp_feature_mask(void *handle, char *buf) return size; } -int smu_sys_set_pp_feature_mask(void *handle, uint64_t new_mask) +static int smu_sys_set_pp_feature_mask(void *handle, + uint64_t new_mask) { struct smu_context *smu = handle; int ret = 0; @@ -142,7 +154,7 @@ int smu_get_dpm_freq_range(struct smu_context *smu, return ret; } -u32 smu_get_mclk(void *handle, bool low) +static u32 smu_get_mclk(void *handle, bool low) { struct smu_context *smu = handle; uint32_t clk_freq; @@ -156,7 +168,7 @@ u32 smu_get_mclk(void *handle, bool low) return clk_freq * 100; } -u32 smu_get_sclk(void *handle, bool low) +static u32 smu_get_sclk(void *handle, bool low) { struct smu_context *smu = handle; uint32_t clk_freq; @@ -256,8 +268,9 @@ static int smu_dpm_set_jpeg_enable(struct smu_context *smu, * Under this case, the smu->mutex lock protection is already enforced on * the parent API smu_force_performance_level of the call path. */ -int smu_dpm_set_power_gate(void *handle, uint32_t block_type, - bool gate) +static int smu_dpm_set_power_gate(void *handle, + uint32_t block_type, + bool gate) { struct smu_context *smu = handle; int ret = 0; @@ -406,8 +419,8 @@ static void smu_restore_dpm_user_profile(struct smu_context *smu) smu->user_dpm_profile.flags &= ~SMU_DPM_USER_PROFILE_RESTORE; } -int smu_get_power_num_states(void *handle, - struct pp_states_info *state_info) +static int smu_get_power_num_states(void *handle, + struct pp_states_info *state_info) { if (!state_info) return -EINVAL; @@ -442,7 +455,8 @@ bool is_support_cclk_dpm(struct amdgpu_device *adev) } -int smu_sys_get_pp_table(void *handle, char **table) +static int smu_sys_get_pp_table(void *handle, + char **table) { struct smu_context *smu = handle; struct smu_table_context *smu_table = &smu->smu_table; @@ -468,7 +482,9 @@ int smu_sys_get_pp_table(void *handle, char **table) return powerplay_table_size; } -int smu_sys_set_pp_table(void *handle, const char *buf, size_t size) +static int smu_sys_set_pp_table(void *handle, + const char *buf, + size_t size) { struct smu_context *smu = handle; struct smu_table_context *smu_table = &smu->smu_table; @@ -632,6 +648,7 @@ err0_out: return ret; } + static int smu_late_init(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; @@ -1337,7 +1354,7 @@ static int smu_disable_dpms(struct smu_context *smu) bool use_baco = !smu->is_apu && ((amdgpu_in_reset(adev) && (amdgpu_asic_reset_method(adev) == AMD_RESET_METHOD_BACO)) || - ((adev->in_runpm || adev->in_hibernate) && amdgpu_asic_supports_baco(adev))); + ((adev->in_runpm || adev->in_s4) && amdgpu_asic_supports_baco(adev))); /* * For custom pptable uploading, skip the DPM features @@ -1430,7 +1447,7 @@ static int smu_hw_fini(void *handle) return smu_smc_hw_cleanup(smu); } -int smu_reset(struct smu_context *smu) +static int smu_reset(struct smu_context *smu) { struct amdgpu_device *adev = smu->adev; int ret; @@ -1474,7 +1491,8 @@ static int smu_suspend(void *handle) smu->watermarks_bitmap &= ~(WATERMARKS_LOADED); - if (smu->is_apu) + /* skip CGPG when in S0ix */ + if (smu->is_apu && !adev->in_s0ix) smu_set_gfx_cgpg(&adev->smu, false); return 0; @@ -1518,9 +1536,10 @@ static int smu_resume(void *handle) return 0; } -int smu_display_configuration_change(struct smu_context *smu, - const struct amd_pp_display_configuration *display_config) +static int smu_display_configuration_change(void *handle, + const struct amd_pp_display_configuration *display_config) { + struct smu_context *smu = handle; int index = 0; int num_of_active_display = 0; @@ -1676,10 +1695,10 @@ static int smu_adjust_power_state_dynamic(struct smu_context *smu, return ret; } -int smu_handle_task(struct smu_context *smu, - enum amd_dpm_forced_level level, - enum amd_pp_task task_id, - bool lock_needed) +static int smu_handle_task(struct smu_context *smu, + enum amd_dpm_forced_level level, + enum amd_pp_task task_id, + bool lock_needed) { int ret = 0; @@ -1711,9 +1730,9 @@ out: return ret; } -int smu_handle_dpm_task(void *handle, - enum amd_pp_task task_id, - enum amd_pm_state_type *user_state) +static int smu_handle_dpm_task(void *handle, + enum amd_pp_task task_id, + enum amd_pm_state_type *user_state) { struct smu_context *smu = handle; struct smu_dpm_context *smu_dpm = &smu->smu_dpm; @@ -1722,10 +1741,9 @@ int smu_handle_dpm_task(void *handle, } - -int smu_switch_power_profile(void *handle, - enum PP_SMC_POWER_PROFILE type, - bool en) +static int smu_switch_power_profile(void *handle, + enum PP_SMC_POWER_PROFILE type, + bool en) { struct smu_context *smu = handle; struct smu_dpm_context *smu_dpm_ctx = &(smu->smu_dpm); @@ -1761,7 +1779,7 @@ int smu_switch_power_profile(void *handle, return 0; } -enum amd_dpm_forced_level smu_get_performance_level(void *handle) +static enum amd_dpm_forced_level smu_get_performance_level(void *handle) { struct smu_context *smu = handle; struct smu_dpm_context *smu_dpm_ctx = &(smu->smu_dpm); @@ -1780,7 +1798,8 @@ enum amd_dpm_forced_level smu_get_performance_level(void *handle) return level; } -int smu_force_performance_level(void *handle, enum amd_dpm_forced_level level) +static int smu_force_performance_level(void *handle, + enum amd_dpm_forced_level level) { struct smu_context *smu = handle; struct smu_dpm_context *smu_dpm_ctx = &(smu->smu_dpm); @@ -1815,8 +1834,9 @@ int smu_force_performance_level(void *handle, enum amd_dpm_forced_level level) return ret; } -int smu_set_display_count(struct smu_context *smu, uint32_t count) +static int smu_set_display_count(void *handle, uint32_t count) { + struct smu_context *smu = handle; int ret = 0; if (!smu->pm_enabled || !smu->adev->pm.dpm_enabled) @@ -1859,7 +1879,9 @@ static int smu_force_smuclk_levels(struct smu_context *smu, return ret; } -int smu_force_ppclk_levels(void *handle, enum pp_clock_type type, uint32_t mask) +static int smu_force_ppclk_levels(void *handle, + enum pp_clock_type type, + uint32_t mask) { struct smu_context *smu = handle; enum smu_clk_type clk_type; @@ -1903,48 +1925,28 @@ int smu_force_ppclk_levels(void *handle, enum pp_clock_type type, uint32_t mask) * However, the mp1 state setting should still be granted * even if the dpm_enabled cleared. */ -int smu_set_mp1_state(void *handle, - enum pp_mp1_state mp1_state) +static int smu_set_mp1_state(void *handle, + enum pp_mp1_state mp1_state) { struct smu_context *smu = handle; - uint16_t msg; - int ret; + int ret = 0; if (!smu->pm_enabled) return -EOPNOTSUPP; mutex_lock(&smu->mutex); - switch (mp1_state) { - case PP_MP1_STATE_SHUTDOWN: - msg = SMU_MSG_PrepareMp1ForShutdown; - break; - case PP_MP1_STATE_UNLOAD: - msg = SMU_MSG_PrepareMp1ForUnload; - break; - case PP_MP1_STATE_RESET: - msg = SMU_MSG_PrepareMp1ForReset; - break; - case PP_MP1_STATE_NONE: - default: - mutex_unlock(&smu->mutex); - return 0; - } - - ret = smu_send_smc_msg(smu, msg, NULL); - /* some asics may not support those messages */ - if (ret == -EINVAL) - ret = 0; - if (ret) - dev_err(smu->adev->dev, "[PrepareMp1] Failed!\n"); + if (smu->ppt_funcs && + smu->ppt_funcs->set_mp1_state) + ret = smu->ppt_funcs->set_mp1_state(smu, mp1_state); mutex_unlock(&smu->mutex); return ret; } -int smu_set_df_cstate(void *handle, - enum pp_df_cstate state) +static int smu_set_df_cstate(void *handle, + enum pp_df_cstate state) { struct smu_context *smu = handle; int ret = 0; @@ -2003,9 +2005,10 @@ int smu_write_watermarks_table(struct smu_context *smu) return ret; } -int smu_set_watermarks_for_clock_ranges(struct smu_context *smu, - struct pp_smu_wm_range_sets *clock_ranges) +static int smu_set_watermarks_for_clock_ranges(void *handle, + struct pp_smu_wm_range_sets *clock_ranges) { + struct smu_context *smu = handle; int ret = 0; if (!smu->pm_enabled || !smu->adev->pm.dpm_enabled) @@ -2092,41 +2095,39 @@ const struct amdgpu_ip_block_version smu_v13_0_ip_block = .funcs = &smu_ip_funcs, }; -int smu_load_microcode(struct smu_context *smu) +static int smu_load_microcode(void *handle) { + struct smu_context *smu = handle; + struct amdgpu_device *adev = smu->adev; int ret = 0; - if (!smu->pm_enabled || !smu->adev->pm.dpm_enabled) + if (!smu->pm_enabled) return -EOPNOTSUPP; - mutex_lock(&smu->mutex); + /* This should be used for non PSP loading */ + if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) + return 0; - if (smu->ppt_funcs->load_microcode) + if (smu->ppt_funcs->load_microcode) { ret = smu->ppt_funcs->load_microcode(smu); + if (ret) { + dev_err(adev->dev, "Load microcode failed\n"); + return ret; + } + } - mutex_unlock(&smu->mutex); - - return ret; -} - -int smu_check_fw_status(struct smu_context *smu) -{ - int ret = 0; - - if (!smu->pm_enabled || !smu->adev->pm.dpm_enabled) - return -EOPNOTSUPP; - - mutex_lock(&smu->mutex); - - if (smu->ppt_funcs->check_fw_status) + if (smu->ppt_funcs->check_fw_status) { ret = smu->ppt_funcs->check_fw_status(smu); - - mutex_unlock(&smu->mutex); + if (ret) { + dev_err(adev->dev, "SMC is not ready\n"); + return ret; + } + } return ret; } -int smu_set_gfx_cgpg(struct smu_context *smu, bool enabled) +static int smu_set_gfx_cgpg(struct smu_context *smu, bool enabled) { int ret = 0; @@ -2140,7 +2141,7 @@ int smu_set_gfx_cgpg(struct smu_context *smu, bool enabled) return ret; } -int smu_set_fan_speed_rpm(void *handle, uint32_t speed) +static int smu_set_fan_speed_rpm(void *handle, uint32_t speed) { struct smu_context *smu = handle; u32 percent; @@ -2199,7 +2200,7 @@ int smu_get_power_limit(struct smu_context *smu, return ret; } -int smu_set_power_limit(void *handle, uint32_t limit) +static int smu_set_power_limit(void *handle, uint32_t limit) { struct smu_context *smu = handle; uint32_t limit_type = limit >> 24; @@ -2220,6 +2221,7 @@ int smu_set_power_limit(void *handle, uint32_t limit) dev_err(smu->adev->dev, "New power limit (%d) is over the max allowed %d\n", limit, smu->max_power_limit); + ret = -EINVAL; goto out; } @@ -2255,7 +2257,9 @@ static int smu_print_smuclk_levels(struct smu_context *smu, enum smu_clk_type cl return ret; } -int smu_print_ppclk_levels(void *handle, enum pp_clock_type type, char *buf) +static int smu_print_ppclk_levels(void *handle, + enum pp_clock_type type, + char *buf) { struct smu_context *smu = handle; enum smu_clk_type clk_type; @@ -2296,9 +2300,9 @@ int smu_print_ppclk_levels(void *handle, enum pp_clock_type type, char *buf) return smu_print_smuclk_levels(smu, clk_type, buf); } -int smu_od_edit_dpm_table(void *handle, - enum PP_OD_DPM_TABLE_COMMAND type, - long *input, uint32_t size) +static int smu_od_edit_dpm_table(void *handle, + enum PP_OD_DPM_TABLE_COMMAND type, + long *input, uint32_t size) { struct smu_context *smu = handle; int ret = 0; @@ -2317,7 +2321,10 @@ int smu_od_edit_dpm_table(void *handle, return ret; } -int smu_read_sensor(void *handle, int sensor, void *data, int *size_arg) +static int smu_read_sensor(void *handle, + int sensor, + void *data, + int *size_arg) { struct smu_context *smu = handle; struct smu_umd_pstate_table *pstate_table = @@ -2384,7 +2391,7 @@ unlock: return ret; } -int smu_get_power_profile_mode(void *handle, char *buf) +static int smu_get_power_profile_mode(void *handle, char *buf) { struct smu_context *smu = handle; int ret = 0; @@ -2402,7 +2409,9 @@ int smu_get_power_profile_mode(void *handle, char *buf) return ret; } -int smu_set_power_profile_mode(void *handle, long *param, uint32_t param_size) +static int smu_set_power_profile_mode(void *handle, + long *param, + uint32_t param_size) { struct smu_context *smu = handle; int ret = 0; @@ -2420,7 +2429,7 @@ int smu_set_power_profile_mode(void *handle, long *param, uint32_t param_size) } -u32 smu_get_fan_control_mode(void *handle) +static u32 smu_get_fan_control_mode(void *handle) { struct smu_context *smu = handle; u32 ret = 0; @@ -2438,7 +2447,7 @@ u32 smu_get_fan_control_mode(void *handle) return ret; } -int smu_set_fan_control_mode(struct smu_context *smu, int value) +static int smu_set_fan_control_mode(struct smu_context *smu, int value) { int ret = 0; @@ -2463,14 +2472,15 @@ int smu_set_fan_control_mode(struct smu_context *smu, int value) return ret; } -void smu_pp_set_fan_control_mode(void *handle, u32 value) { +static void smu_pp_set_fan_control_mode(void *handle, u32 value) +{ struct smu_context *smu = handle; smu_set_fan_control_mode(smu, value); } -int smu_get_fan_speed_percent(void *handle, u32 *speed) +static int smu_get_fan_speed_percent(void *handle, u32 *speed) { struct smu_context *smu = handle; int ret = 0; @@ -2494,7 +2504,7 @@ int smu_get_fan_speed_percent(void *handle, u32 *speed) return ret; } -int smu_set_fan_speed_percent(void *handle, u32 speed) +static int smu_set_fan_speed_percent(void *handle, u32 speed) { struct smu_context *smu = handle; int ret = 0; @@ -2517,7 +2527,7 @@ int smu_set_fan_speed_percent(void *handle, u32 speed) return ret; } -int smu_get_fan_speed_rpm(void *handle, uint32_t *speed) +static int smu_get_fan_speed_rpm(void *handle, uint32_t *speed) { struct smu_context *smu = handle; int ret = 0; @@ -2538,8 +2548,9 @@ int smu_get_fan_speed_rpm(void *handle, uint32_t *speed) return ret; } -int smu_set_deep_sleep_dcefclk(struct smu_context *smu, int clk) +static int smu_set_deep_sleep_dcefclk(void *handle, uint32_t clk) { + struct smu_context *smu = handle; int ret = 0; if (!smu->pm_enabled || !smu->adev->pm.dpm_enabled) @@ -2554,10 +2565,12 @@ int smu_set_deep_sleep_dcefclk(struct smu_context *smu, int clk) return ret; } -int smu_get_clock_by_type_with_latency(struct smu_context *smu, - enum smu_clk_type clk_type, - struct pp_clock_levels_with_latency *clocks) +static int smu_get_clock_by_type_with_latency(void *handle, + enum amd_pp_clock_type type, + struct pp_clock_levels_with_latency *clocks) { + struct smu_context *smu = handle; + enum smu_clk_type clk_type; int ret = 0; if (!smu->pm_enabled || !smu->adev->pm.dpm_enabled) @@ -2565,17 +2578,38 @@ int smu_get_clock_by_type_with_latency(struct smu_context *smu, mutex_lock(&smu->mutex); - if (smu->ppt_funcs->get_clock_by_type_with_latency) + if (smu->ppt_funcs->get_clock_by_type_with_latency) { + switch (type) { + case amd_pp_sys_clock: + clk_type = SMU_GFXCLK; + break; + case amd_pp_mem_clock: + clk_type = SMU_MCLK; + break; + case amd_pp_dcef_clock: + clk_type = SMU_DCEFCLK; + break; + case amd_pp_disp_clock: + clk_type = SMU_DISPCLK; + break; + default: + dev_err(smu->adev->dev, "Invalid clock type!\n"); + mutex_unlock(&smu->mutex); + return -EINVAL; + } + ret = smu->ppt_funcs->get_clock_by_type_with_latency(smu, clk_type, clocks); + } mutex_unlock(&smu->mutex); return ret; } -int smu_display_clock_voltage_request(struct smu_context *smu, - struct pp_display_clock_request *clock_req) +static int smu_display_clock_voltage_request(void *handle, + struct pp_display_clock_request *clock_req) { + struct smu_context *smu = handle; int ret = 0; if (!smu->pm_enabled || !smu->adev->pm.dpm_enabled) @@ -2592,8 +2626,10 @@ int smu_display_clock_voltage_request(struct smu_context *smu, } -int smu_display_disable_memory_clock_switch(struct smu_context *smu, bool disable_memory_clock_switch) +static int smu_display_disable_memory_clock_switch(void *handle, + bool disable_memory_clock_switch) { + struct smu_context *smu = handle; int ret = -EINVAL; if (!smu->pm_enabled || !smu->adev->pm.dpm_enabled) @@ -2609,8 +2645,8 @@ int smu_display_disable_memory_clock_switch(struct smu_context *smu, bool disabl return ret; } -int smu_set_xgmi_pstate(void *handle, - uint32_t pstate) +static int smu_set_xgmi_pstate(void *handle, + uint32_t pstate) { struct smu_context *smu = handle; int ret = 0; @@ -2631,49 +2667,7 @@ int smu_set_xgmi_pstate(void *handle, return ret; } -int smu_set_azalia_d3_pme(struct smu_context *smu) -{ - int ret = 0; - - if (!smu->pm_enabled || !smu->adev->pm.dpm_enabled) - return -EOPNOTSUPP; - - mutex_lock(&smu->mutex); - - if (smu->ppt_funcs->set_azalia_d3_pme) - ret = smu->ppt_funcs->set_azalia_d3_pme(smu); - - mutex_unlock(&smu->mutex); - - return ret; -} - -/* - * On system suspending or resetting, the dpm_enabled - * flag will be cleared. So that those SMU services which - * are not supported will be gated. - * - * However, the baco/mode1 reset should still be granted - * as they are still supported and necessary. - */ -bool smu_baco_is_support(struct smu_context *smu) -{ - bool ret = false; - - if (!smu->pm_enabled) - return false; - - mutex_lock(&smu->mutex); - - if (smu->ppt_funcs && smu->ppt_funcs->baco_is_support) - ret = smu->ppt_funcs->baco_is_support(smu); - - mutex_unlock(&smu->mutex); - - return ret; -} - -int smu_get_baco_capability(void *handle, bool *cap) +static int smu_get_baco_capability(void *handle, bool *cap) { struct smu_context *smu = handle; int ret = 0; @@ -2693,60 +2687,7 @@ int smu_get_baco_capability(void *handle, bool *cap) return ret; } - -int smu_baco_get_state(struct smu_context *smu, enum smu_baco_state *state) -{ - if (smu->ppt_funcs->baco_get_state) - return -EINVAL; - - mutex_lock(&smu->mutex); - *state = smu->ppt_funcs->baco_get_state(smu); - mutex_unlock(&smu->mutex); - - return 0; -} - -int smu_baco_enter(struct smu_context *smu) -{ - int ret = 0; - - if (!smu->pm_enabled) - return -EOPNOTSUPP; - - mutex_lock(&smu->mutex); - - if (smu->ppt_funcs->baco_enter) - ret = smu->ppt_funcs->baco_enter(smu); - - mutex_unlock(&smu->mutex); - - if (ret) - dev_err(smu->adev->dev, "Failed to enter BACO state!\n"); - - return ret; -} - -int smu_baco_exit(struct smu_context *smu) -{ - int ret = 0; - - if (!smu->pm_enabled) - return -EOPNOTSUPP; - - mutex_lock(&smu->mutex); - - if (smu->ppt_funcs->baco_exit) - ret = smu->ppt_funcs->baco_exit(smu); - - mutex_unlock(&smu->mutex); - - if (ret) - dev_err(smu->adev->dev, "Failed to exit BACO state!\n"); - - return ret; -} - -int smu_baco_set_state(void *handle, int state) +static int smu_baco_set_state(void *handle, int state) { struct smu_context *smu = handle; int ret = 0; @@ -2831,7 +2772,7 @@ int smu_mode1_reset(struct smu_context *smu) return ret; } -int smu_mode2_reset(void *handle) +static int smu_mode2_reset(void *handle) { struct smu_context *smu = handle; int ret = 0; @@ -2852,9 +2793,10 @@ int smu_mode2_reset(void *handle) return ret; } -int smu_get_max_sustainable_clocks_by_dc(struct smu_context *smu, - struct pp_smu_nv_clock_table *max_clocks) +static int smu_get_max_sustainable_clocks_by_dc(void *handle, + struct pp_smu_nv_clock_table *max_clocks) { + struct smu_context *smu = handle; int ret = 0; if (!smu->pm_enabled || !smu->adev->pm.dpm_enabled) @@ -2870,10 +2812,11 @@ int smu_get_max_sustainable_clocks_by_dc(struct smu_context *smu, return ret; } -int smu_get_uclk_dpm_states(struct smu_context *smu, - unsigned int *clock_values_in_khz, - unsigned int *num_states) +static int smu_get_uclk_dpm_states(void *handle, + unsigned int *clock_values_in_khz, + unsigned int *num_states) { + struct smu_context *smu = handle; int ret = 0; if (!smu->pm_enabled || !smu->adev->pm.dpm_enabled) @@ -2889,7 +2832,7 @@ int smu_get_uclk_dpm_states(struct smu_context *smu, return ret; } -enum amd_pm_state_type smu_get_current_power_state(void *handle) +static enum amd_pm_state_type smu_get_current_power_state(void *handle) { struct smu_context *smu = handle; enum amd_pm_state_type pm_state = POWER_STATE_TYPE_DEFAULT; @@ -2907,9 +2850,10 @@ enum amd_pm_state_type smu_get_current_power_state(void *handle) return pm_state; } -int smu_get_dpm_clock_table(struct smu_context *smu, - struct dpm_clocks *clock_table) +static int smu_get_dpm_clock_table(void *handle, + struct dpm_clocks *clock_table) { + struct smu_context *smu = handle; int ret = 0; if (!smu->pm_enabled || !smu->adev->pm.dpm_enabled) @@ -2925,7 +2869,7 @@ int smu_get_dpm_clock_table(struct smu_context *smu, return ret; } -ssize_t smu_sys_get_gpu_metrics(void *handle, void **table) +static ssize_t smu_sys_get_gpu_metrics(void *handle, void **table) { struct smu_context *smu = handle; ssize_t size; @@ -2945,7 +2889,7 @@ ssize_t smu_sys_get_gpu_metrics(void *handle, void **table) return size; } -int smu_enable_mgpu_fan_boost(void *handle) +static int smu_enable_mgpu_fan_boost(void *handle) { struct smu_context *smu = handle; int ret = 0; @@ -2963,8 +2907,10 @@ int smu_enable_mgpu_fan_boost(void *handle) return ret; } -int smu_gfx_state_change_set(struct smu_context *smu, uint32_t state) +static int smu_gfx_state_change_set(void *handle, + uint32_t state) { + struct smu_context *smu = handle; int ret = 0; mutex_lock(&smu->mutex); @@ -3026,4 +2972,31 @@ static const struct amd_pm_funcs swsmu_pm_funcs = { .get_power_profile_mode = smu_get_power_profile_mode, .force_clock_level = smu_force_ppclk_levels, .print_clock_levels = smu_print_ppclk_levels, + .get_uclk_dpm_states = smu_get_uclk_dpm_states, + .get_dpm_clock_table = smu_get_dpm_clock_table, + .display_configuration_change = smu_display_configuration_change, + .get_clock_by_type_with_latency = smu_get_clock_by_type_with_latency, + .display_clock_voltage_request = smu_display_clock_voltage_request, + .set_active_display_count = smu_set_display_count, + .set_min_deep_sleep_dcefclk = smu_set_deep_sleep_dcefclk, + .set_watermarks_for_clock_ranges = smu_set_watermarks_for_clock_ranges, + .display_disable_memory_clock_switch = smu_display_disable_memory_clock_switch, + .get_max_sustainable_clocks_by_dc = smu_get_max_sustainable_clocks_by_dc, + .load_firmware = smu_load_microcode, + .gfx_state_change_set = smu_gfx_state_change_set, }; + +int smu_wait_for_event(struct amdgpu_device *adev, enum smu_event_type event, + uint64_t event_arg) +{ + int ret = -EINVAL; + struct smu_context *smu = &adev->smu; + + if (smu->ppt_funcs->wait_for_event) { + mutex_lock(&smu->mutex); + ret = smu->ppt_funcs->wait_for_event(smu, event, event_arg); + mutex_unlock(&smu->mutex); + } + + return ret; +} diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c index bbc03092b0a9..77693bf0840c 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c @@ -2365,6 +2365,7 @@ static const struct pptable_funcs arcturus_ppt_funcs = { .get_fan_parameters = arcturus_get_fan_parameters, .interrupt_work = smu_v11_0_interrupt_work, .set_light_sbr = smu_v11_0_set_light_sbr, + .set_mp1_state = smu_cmn_set_mp1_state, }; void arcturus_set_ppt_funcs(struct smu_context *smu) diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c index 3d0de2c958fa..f827096dc849 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c @@ -431,6 +431,30 @@ static int navi10_store_powerplay_table(struct smu_context *smu) return 0; } +static int navi10_set_mp1_state(struct smu_context *smu, + enum pp_mp1_state mp1_state) +{ + struct amdgpu_device *adev = smu->adev; + uint32_t mp1_fw_flags; + int ret = 0; + + ret = smu_cmn_set_mp1_state(smu, mp1_state); + if (ret) + return ret; + + if (mp1_state == PP_MP1_STATE_UNLOAD) { + mp1_fw_flags = RREG32_PCIE(MP1_Public | + (smnMP1_FIRMWARE_FLAGS & 0xffffffff)); + + mp1_fw_flags &= ~MP1_FIRMWARE_FLAGS__INTERRUPTS_ENABLED_MASK; + + WREG32_PCIE(MP1_Public | + (smnMP1_FIRMWARE_FLAGS & 0xffffffff), mp1_fw_flags); + } + + return 0; +} + static int navi10_setup_pptable(struct smu_context *smu) { int ret = 0; @@ -3031,6 +3055,7 @@ static const struct pptable_funcs navi10_ppt_funcs = { .get_fan_parameters = navi10_get_fan_parameters, .post_init = navi10_post_smu_init, .interrupt_work = smu_v11_0_interrupt_work, + .set_mp1_state = navi10_set_mp1_state, }; void navi10_set_ppt_funcs(struct smu_context *smu) diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c index 3621884c3293..72d9c1be1835 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c @@ -3110,6 +3110,23 @@ static int sienna_cichlid_system_features_control(struct smu_context *smu, return smu_v11_0_system_features_control(smu, en); } +static int sienna_cichlid_set_mp1_state(struct smu_context *smu, + enum pp_mp1_state mp1_state) +{ + int ret; + + switch (mp1_state) { + case PP_MP1_STATE_UNLOAD: + ret = smu_cmn_set_mp1_state(smu, mp1_state); + break; + default: + /* Ignore others */ + ret = 0; + } + + return ret; +} + static const struct pptable_funcs sienna_cichlid_ppt_funcs = { .get_allowed_feature_mask = sienna_cichlid_get_allowed_feature_mask, .set_default_dpm_table = sienna_cichlid_set_default_dpm_table, @@ -3195,6 +3212,7 @@ static const struct pptable_funcs sienna_cichlid_ppt_funcs = { .get_fan_parameters = sienna_cichlid_get_fan_parameters, .interrupt_work = smu_v11_0_interrupt_work, .gpo_control = sienna_cichlid_gpo_control, + .set_mp1_state = sienna_cichlid_set_mp1_state, }; void sienna_cichlid_set_ppt_funcs(struct smu_context *smu) diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c index 0d137af1a78a..6274cae4a065 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c @@ -561,6 +561,7 @@ int smu_v11_0_get_vbios_bootup_values(struct smu_context *smu) smu->smu_table.boot_values.firmware_caps = v_3_1->firmware_capability; break; case 3: + case 4: default: v_3_3 = (struct atom_firmware_info_v3_3 *)header; smu->smu_table.boot_values.revision = v_3_3->firmware_revision; diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c index c5b387360f01..77f532a49e37 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c @@ -194,18 +194,34 @@ static int vangogh_tables_init(struct smu_context *smu) { struct smu_table_context *smu_table = &smu->smu_table; struct smu_table *tables = smu_table->tables; + struct amdgpu_device *adev = smu->adev; + uint32_t if_version; + uint32_t ret = 0; + + ret = smu_cmn_get_smc_version(smu, &if_version, NULL); + if (ret) { + dev_err(adev->dev, "Failed to get smu if version!\n"); + goto err0_out; + } SMU_TABLE_INIT(tables, SMU_TABLE_WATERMARKS, sizeof(Watermarks_t), PAGE_SIZE, AMDGPU_GEM_DOMAIN_VRAM); - SMU_TABLE_INIT(tables, SMU_TABLE_SMU_METRICS, sizeof(SmuMetrics_t), - PAGE_SIZE, AMDGPU_GEM_DOMAIN_VRAM); SMU_TABLE_INIT(tables, SMU_TABLE_DPMCLOCKS, sizeof(DpmClocks_t), PAGE_SIZE, AMDGPU_GEM_DOMAIN_VRAM); SMU_TABLE_INIT(tables, SMU_TABLE_PMSTATUSLOG, SMU11_TOOL_SIZE, PAGE_SIZE, AMDGPU_GEM_DOMAIN_VRAM); SMU_TABLE_INIT(tables, SMU_TABLE_ACTIVITY_MONITOR_COEFF, sizeof(DpmActivityMonitorCoeffExt_t), PAGE_SIZE, AMDGPU_GEM_DOMAIN_VRAM); - smu_table->metrics_table = kzalloc(sizeof(SmuMetrics_t), GFP_KERNEL); + + if (if_version < 0x3) { + SMU_TABLE_INIT(tables, SMU_TABLE_SMU_METRICS, sizeof(SmuMetrics_legacy_t), + PAGE_SIZE, AMDGPU_GEM_DOMAIN_VRAM); + smu_table->metrics_table = kzalloc(sizeof(SmuMetrics_legacy_t), GFP_KERNEL); + } else { + SMU_TABLE_INIT(tables, SMU_TABLE_SMU_METRICS, sizeof(SmuMetrics_t), + PAGE_SIZE, AMDGPU_GEM_DOMAIN_VRAM); + smu_table->metrics_table = kzalloc(sizeof(SmuMetrics_t), GFP_KERNEL); + } if (!smu_table->metrics_table) goto err0_out; smu_table->metrics_time = 0; @@ -235,13 +251,12 @@ err0_out: return -ENOMEM; } -static int vangogh_get_smu_metrics_data(struct smu_context *smu, +static int vangogh_get_legacy_smu_metrics_data(struct smu_context *smu, MetricsMember_t member, uint32_t *value) { struct smu_table_context *smu_table = &smu->smu_table; - - SmuMetrics_t *metrics = (SmuMetrics_t *)smu_table->metrics_table; + SmuMetrics_legacy_t *metrics = (SmuMetrics_legacy_t *)smu_table->metrics_table; int ret = 0; mutex_lock(&smu->metrics_lock); @@ -255,7 +270,7 @@ static int vangogh_get_smu_metrics_data(struct smu_context *smu, } switch (member) { - case METRICS_AVERAGE_GFXCLK: + case METRICS_CURR_GFXCLK: *value = metrics->GfxclkFrequency; break; case METRICS_AVERAGE_SOCCLK: @@ -267,7 +282,7 @@ static int vangogh_get_smu_metrics_data(struct smu_context *smu, case METRICS_AVERAGE_DCLK: *value = metrics->DclkFrequency; break; - case METRICS_AVERAGE_UCLK: + case METRICS_CURR_UCLK: *value = metrics->MemclkFrequency; break; case METRICS_AVERAGE_GFXACTIVITY: @@ -311,6 +326,103 @@ static int vangogh_get_smu_metrics_data(struct smu_context *smu, return ret; } +static int vangogh_get_smu_metrics_data(struct smu_context *smu, + MetricsMember_t member, + uint32_t *value) +{ + struct smu_table_context *smu_table = &smu->smu_table; + SmuMetrics_t *metrics = (SmuMetrics_t *)smu_table->metrics_table; + int ret = 0; + + mutex_lock(&smu->metrics_lock); + + ret = smu_cmn_get_metrics_table_locked(smu, + NULL, + false); + if (ret) { + mutex_unlock(&smu->metrics_lock); + return ret; + } + + switch (member) { + case METRICS_CURR_GFXCLK: + *value = metrics->Current.GfxclkFrequency; + break; + case METRICS_AVERAGE_SOCCLK: + *value = metrics->Current.SocclkFrequency; + break; + case METRICS_AVERAGE_VCLK: + *value = metrics->Current.VclkFrequency; + break; + case METRICS_AVERAGE_DCLK: + *value = metrics->Current.DclkFrequency; + break; + case METRICS_CURR_UCLK: + *value = metrics->Current.MemclkFrequency; + break; + case METRICS_AVERAGE_GFXACTIVITY: + *value = metrics->Current.GfxActivity; + break; + case METRICS_AVERAGE_VCNACTIVITY: + *value = metrics->Current.UvdActivity; + break; + case METRICS_AVERAGE_SOCKETPOWER: + *value = (metrics->Current.CurrentSocketPower << 8) / + 1000; + break; + case METRICS_TEMPERATURE_EDGE: + *value = metrics->Current.GfxTemperature / 100 * + SMU_TEMPERATURE_UNITS_PER_CENTIGRADES; + break; + case METRICS_TEMPERATURE_HOTSPOT: + *value = metrics->Current.SocTemperature / 100 * + SMU_TEMPERATURE_UNITS_PER_CENTIGRADES; + break; + case METRICS_THROTTLER_STATUS: + *value = metrics->Current.ThrottlerStatus; + break; + case METRICS_VOLTAGE_VDDGFX: + *value = metrics->Current.Voltage[2]; + break; + case METRICS_VOLTAGE_VDDSOC: + *value = metrics->Current.Voltage[1]; + break; + case METRICS_AVERAGE_CPUCLK: + memcpy(value, &metrics->Current.CoreFrequency[0], + smu->cpu_core_num * sizeof(uint16_t)); + break; + default: + *value = UINT_MAX; + break; + } + + mutex_unlock(&smu->metrics_lock); + + return ret; +} + +static int vangogh_common_get_smu_metrics_data(struct smu_context *smu, + MetricsMember_t member, + uint32_t *value) +{ + struct amdgpu_device *adev = smu->adev; + uint32_t if_version; + int ret = 0; + + ret = smu_cmn_get_smc_version(smu, &if_version, NULL); + if (ret) { + dev_err(adev->dev, "Failed to get smu if version!\n"); + return ret; + } + + if (if_version < 0x3) + ret = vangogh_get_legacy_smu_metrics_data(smu, member, value); + else + ret = vangogh_get_smu_metrics_data(smu, member, value); + + return ret; +} + static int vangogh_allocate_dpm_context(struct smu_context *smu) { struct smu_dpm_context *smu_dpm = &smu->smu_dpm; @@ -384,10 +496,15 @@ static int vangogh_dpm_set_jpeg_enable(struct smu_context *smu, bool enable) static bool vangogh_is_dpm_running(struct smu_context *smu) { + struct amdgpu_device *adev = smu->adev; int ret = 0; uint32_t feature_mask[2]; uint64_t feature_enabled; + /* we need to re-init after suspend so return false */ + if (adev->in_suspend) + return false; + ret = smu_cmn_get_enabled_32_bits_mask(smu, feature_mask, 2); if (ret) @@ -442,11 +559,11 @@ static int vangogh_get_dpm_clk_limited(struct smu_context *smu, enum smu_clk_typ return 0; } -static int vangogh_print_clk_levels(struct smu_context *smu, +static int vangogh_print_legacy_clk_levels(struct smu_context *smu, enum smu_clk_type clk_type, char *buf) { DpmClocks_t *clk_table = smu->smu_table.clocks_table; - SmuMetrics_t metrics; + SmuMetrics_legacy_t metrics; struct smu_dpm_context *smu_dpm_ctx = &(smu->smu_dpm); int i, size = 0, ret = 0; uint32_t cur_value = 0, value = 0, count = 0; @@ -541,6 +658,126 @@ static int vangogh_print_clk_levels(struct smu_context *smu, return size; } +static int vangogh_print_clk_levels(struct smu_context *smu, + enum smu_clk_type clk_type, char *buf) +{ + DpmClocks_t *clk_table = smu->smu_table.clocks_table; + SmuMetrics_t metrics; + struct smu_dpm_context *smu_dpm_ctx = &(smu->smu_dpm); + int i, size = 0, ret = 0; + uint32_t cur_value = 0, value = 0, count = 0; + bool cur_value_match_level = false; + + memset(&metrics, 0, sizeof(metrics)); + + ret = smu_cmn_get_metrics_table(smu, &metrics, false); + if (ret) + return ret; + + switch (clk_type) { + case SMU_OD_SCLK: + if (smu_dpm_ctx->dpm_level == AMD_DPM_FORCED_LEVEL_MANUAL) { + size = sprintf(buf, "%s:\n", "OD_SCLK"); + size += sprintf(buf + size, "0: %10uMhz\n", + (smu->gfx_actual_hard_min_freq > 0) ? smu->gfx_actual_hard_min_freq : smu->gfx_default_hard_min_freq); + size += sprintf(buf + size, "1: %10uMhz\n", + (smu->gfx_actual_soft_max_freq > 0) ? smu->gfx_actual_soft_max_freq : smu->gfx_default_soft_max_freq); + } + break; + case SMU_OD_CCLK: + if (smu_dpm_ctx->dpm_level == AMD_DPM_FORCED_LEVEL_MANUAL) { + size = sprintf(buf, "CCLK_RANGE in Core%d:\n", smu->cpu_core_id_select); + size += sprintf(buf + size, "0: %10uMhz\n", + (smu->cpu_actual_soft_min_freq > 0) ? smu->cpu_actual_soft_min_freq : smu->cpu_default_soft_min_freq); + size += sprintf(buf + size, "1: %10uMhz\n", + (smu->cpu_actual_soft_max_freq > 0) ? smu->cpu_actual_soft_max_freq : smu->cpu_default_soft_max_freq); + } + break; + case SMU_OD_RANGE: + if (smu_dpm_ctx->dpm_level == AMD_DPM_FORCED_LEVEL_MANUAL) { + size = sprintf(buf, "%s:\n", "OD_RANGE"); + size += sprintf(buf + size, "SCLK: %7uMhz %10uMhz\n", + smu->gfx_default_hard_min_freq, smu->gfx_default_soft_max_freq); + size += sprintf(buf + size, "CCLK: %7uMhz %10uMhz\n", + smu->cpu_default_soft_min_freq, smu->cpu_default_soft_max_freq); + } + break; + case SMU_SOCCLK: + /* the level 3 ~ 6 of socclk use the same frequency for vangogh */ + count = clk_table->NumSocClkLevelsEnabled; + cur_value = metrics.Current.SocclkFrequency; + break; + case SMU_VCLK: + count = clk_table->VcnClkLevelsEnabled; + cur_value = metrics.Current.VclkFrequency; + break; + case SMU_DCLK: + count = clk_table->VcnClkLevelsEnabled; + cur_value = metrics.Current.DclkFrequency; + break; + case SMU_MCLK: + count = clk_table->NumDfPstatesEnabled; + cur_value = metrics.Current.MemclkFrequency; + break; + case SMU_FCLK: + count = clk_table->NumDfPstatesEnabled; + ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_GetFclkFrequency, 0, &cur_value); + if (ret) + return ret; + break; + default: + break; + } + + switch (clk_type) { + case SMU_SOCCLK: + case SMU_VCLK: + case SMU_DCLK: + case SMU_MCLK: + case SMU_FCLK: + for (i = 0; i < count; i++) { + ret = vangogh_get_dpm_clk_limited(smu, clk_type, i, &value); + if (ret) + return ret; + if (!value) + continue; + size += sprintf(buf + size, "%d: %uMhz %s\n", i, value, + cur_value == value ? "*" : ""); + if (cur_value == value) + cur_value_match_level = true; + } + + if (!cur_value_match_level) + size += sprintf(buf + size, " %uMhz *\n", cur_value); + break; + default: + break; + } + + return size; +} + +static int vangogh_common_print_clk_levels(struct smu_context *smu, + enum smu_clk_type clk_type, char *buf) +{ + struct amdgpu_device *adev = smu->adev; + uint32_t if_version; + int ret = 0; + + ret = smu_cmn_get_smc_version(smu, &if_version, NULL); + if (ret) { + dev_err(adev->dev, "Failed to get smu if version!\n"); + return ret; + } + + if (if_version < 0x3) + ret = vangogh_print_legacy_clk_levels(smu, clk_type, buf); + else + ret = vangogh_print_clk_levels(smu, clk_type, buf); + + return ret; +} + static int vangogh_get_profiling_clk_mask(struct smu_context *smu, enum amd_dpm_forced_level level, uint32_t *vclk_mask, @@ -855,7 +1092,6 @@ static int vangogh_set_soft_freq_limited_range(struct smu_context *smu, return ret; break; case SMU_FCLK: - case SMU_MCLK: ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_SetHardMinFclkByFreq, min, NULL); @@ -943,7 +1179,6 @@ static int vangogh_force_clk_levels(struct smu_context *smu, if (ret) return ret; break; - case SMU_MCLK: case SMU_FCLK: ret = vangogh_get_dpm_clk_limited(smu, clk_type, soft_min_level, &min_freq); @@ -1030,7 +1265,6 @@ static int vangogh_force_dpm_limit_value(struct smu_context *smu, bool highest) SMU_SOCCLK, SMU_VCLK, SMU_DCLK, - SMU_MCLK, SMU_FCLK, }; @@ -1059,7 +1293,6 @@ static int vangogh_unforce_dpm_levels(struct smu_context *smu) enum smu_clk_type clk_type; uint32_t feature; } clk_feature_map[] = { - {SMU_MCLK, SMU_FEATURE_DPM_FCLK_BIT}, {SMU_FCLK, SMU_FEATURE_DPM_FCLK_BIT}, {SMU_SOCCLK, SMU_FEATURE_DPM_SOCCLK_BIT}, {SMU_VCLK, SMU_FEATURE_VCN_DPM_BIT}, @@ -1191,7 +1424,6 @@ static int vangogh_set_performance_level(struct smu_context *smu, if (ret) return ret; - vangogh_force_clk_levels(smu, SMU_MCLK, 1 << mclk_mask); vangogh_force_clk_levels(smu, SMU_FCLK, 1 << fclk_mask); vangogh_force_clk_levels(smu, SMU_SOCCLK, 1 << soc_mask); vangogh_force_clk_levels(smu, SMU_VCLK, 1 << vclk_mask); @@ -1231,7 +1463,6 @@ static int vangogh_set_performance_level(struct smu_context *smu, if (ret) return ret; - vangogh_force_clk_levels(smu, SMU_MCLK, 1 << mclk_mask); vangogh_force_clk_levels(smu, SMU_FCLK, 1 << fclk_mask); break; case AMD_DPM_FORCED_LEVEL_PROFILE_PEAK: @@ -1273,57 +1504,57 @@ static int vangogh_read_sensor(struct smu_context *smu, mutex_lock(&smu->sensor_lock); switch (sensor) { case AMDGPU_PP_SENSOR_GPU_LOAD: - ret = vangogh_get_smu_metrics_data(smu, + ret = vangogh_common_get_smu_metrics_data(smu, METRICS_AVERAGE_GFXACTIVITY, (uint32_t *)data); *size = 4; break; case AMDGPU_PP_SENSOR_GPU_POWER: - ret = vangogh_get_smu_metrics_data(smu, + ret = vangogh_common_get_smu_metrics_data(smu, METRICS_AVERAGE_SOCKETPOWER, (uint32_t *)data); *size = 4; break; case AMDGPU_PP_SENSOR_EDGE_TEMP: - ret = vangogh_get_smu_metrics_data(smu, + ret = vangogh_common_get_smu_metrics_data(smu, METRICS_TEMPERATURE_EDGE, (uint32_t *)data); *size = 4; break; case AMDGPU_PP_SENSOR_HOTSPOT_TEMP: - ret = vangogh_get_smu_metrics_data(smu, + ret = vangogh_common_get_smu_metrics_data(smu, METRICS_TEMPERATURE_HOTSPOT, (uint32_t *)data); *size = 4; break; case AMDGPU_PP_SENSOR_GFX_MCLK: - ret = vangogh_get_smu_metrics_data(smu, - METRICS_AVERAGE_UCLK, + ret = vangogh_common_get_smu_metrics_data(smu, + METRICS_CURR_UCLK, (uint32_t *)data); *(uint32_t *)data *= 100; *size = 4; break; case AMDGPU_PP_SENSOR_GFX_SCLK: - ret = vangogh_get_smu_metrics_data(smu, - METRICS_AVERAGE_GFXCLK, + ret = vangogh_common_get_smu_metrics_data(smu, + METRICS_CURR_GFXCLK, (uint32_t *)data); *(uint32_t *)data *= 100; *size = 4; break; case AMDGPU_PP_SENSOR_VDDGFX: - ret = vangogh_get_smu_metrics_data(smu, + ret = vangogh_common_get_smu_metrics_data(smu, METRICS_VOLTAGE_VDDGFX, (uint32_t *)data); *size = 4; break; case AMDGPU_PP_SENSOR_VDDNB: - ret = vangogh_get_smu_metrics_data(smu, + ret = vangogh_common_get_smu_metrics_data(smu, METRICS_VOLTAGE_VDDSOC, (uint32_t *)data); *size = 4; break; case AMDGPU_PP_SENSOR_CPU_CLK: - ret = vangogh_get_smu_metrics_data(smu, + ret = vangogh_common_get_smu_metrics_data(smu, METRICS_AVERAGE_CPUCLK, (uint32_t *)data); *size = smu->cpu_core_num * sizeof(uint16_t); @@ -1397,13 +1628,13 @@ static int vangogh_set_watermarks_table(struct smu_context *smu, return 0; } -static ssize_t vangogh_get_gpu_metrics(struct smu_context *smu, +static ssize_t vangogh_get_legacy_gpu_metrics(struct smu_context *smu, void **table) { struct smu_table_context *smu_table = &smu->smu_table; struct gpu_metrics_v2_1 *gpu_metrics = (struct gpu_metrics_v2_1 *)smu_table->gpu_metrics_table; - SmuMetrics_t metrics; + SmuMetrics_legacy_t metrics; int ret = 0; ret = smu_cmn_get_metrics_table(smu, &metrics, true); @@ -1416,9 +1647,8 @@ static ssize_t vangogh_get_gpu_metrics(struct smu_context *smu, gpu_metrics->temperature_soc = metrics.SocTemperature; memcpy(&gpu_metrics->temperature_core[0], &metrics.CoreTemperature[0], - sizeof(uint16_t) * 8); + sizeof(uint16_t) * 4); gpu_metrics->temperature_l3[0] = metrics.L3Temperature[0]; - gpu_metrics->temperature_l3[1] = metrics.L3Temperature[1]; gpu_metrics->average_gfx_activity = metrics.GfxActivity; gpu_metrics->average_mm_activity = metrics.UvdActivity; @@ -1429,7 +1659,7 @@ static ssize_t vangogh_get_gpu_metrics(struct smu_context *smu, gpu_metrics->average_gfx_power = metrics.Power[2]; memcpy(&gpu_metrics->average_core_power[0], &metrics.CorePower[0], - sizeof(uint16_t) * 8); + sizeof(uint16_t) * 4); gpu_metrics->average_gfxclk_frequency = metrics.GfxclkFrequency; gpu_metrics->average_socclk_frequency = metrics.SocclkFrequency; @@ -1440,9 +1670,8 @@ static ssize_t vangogh_get_gpu_metrics(struct smu_context *smu, memcpy(&gpu_metrics->current_coreclk[0], &metrics.CoreFrequency[0], - sizeof(uint16_t) * 8); + sizeof(uint16_t) * 4); gpu_metrics->current_l3clk[0] = metrics.L3Frequency[0]; - gpu_metrics->current_l3clk[1] = metrics.L3Frequency[1]; gpu_metrics->throttle_status = metrics.ThrottlerStatus; @@ -1453,6 +1682,88 @@ static ssize_t vangogh_get_gpu_metrics(struct smu_context *smu, return sizeof(struct gpu_metrics_v2_1); } +static ssize_t vangogh_get_gpu_metrics(struct smu_context *smu, + void **table) +{ + struct smu_table_context *smu_table = &smu->smu_table; + struct gpu_metrics_v2_1 *gpu_metrics = + (struct gpu_metrics_v2_1 *)smu_table->gpu_metrics_table; + SmuMetrics_t metrics; + int ret = 0; + + ret = smu_cmn_get_metrics_table(smu, &metrics, true); + if (ret) + return ret; + + smu_cmn_init_soft_gpu_metrics(gpu_metrics, 2, 1); + + gpu_metrics->temperature_gfx = metrics.Current.GfxTemperature; + gpu_metrics->temperature_soc = metrics.Current.SocTemperature; + memcpy(&gpu_metrics->temperature_core[0], + &metrics.Current.CoreTemperature[0], + sizeof(uint16_t) * 4); + gpu_metrics->temperature_l3[0] = metrics.Current.L3Temperature[0]; + + gpu_metrics->average_gfx_activity = metrics.Current.GfxActivity; + gpu_metrics->average_mm_activity = metrics.Current.UvdActivity; + + gpu_metrics->average_socket_power = metrics.Current.CurrentSocketPower; + gpu_metrics->average_cpu_power = metrics.Current.Power[0]; + gpu_metrics->average_soc_power = metrics.Current.Power[1]; + gpu_metrics->average_gfx_power = metrics.Current.Power[2]; + memcpy(&gpu_metrics->average_core_power[0], + &metrics.Average.CorePower[0], + sizeof(uint16_t) * 4); + + gpu_metrics->average_gfxclk_frequency = metrics.Average.GfxclkFrequency; + gpu_metrics->average_socclk_frequency = metrics.Average.SocclkFrequency; + gpu_metrics->average_uclk_frequency = metrics.Average.MemclkFrequency; + gpu_metrics->average_fclk_frequency = metrics.Average.MemclkFrequency; + gpu_metrics->average_vclk_frequency = metrics.Average.VclkFrequency; + gpu_metrics->average_dclk_frequency = metrics.Average.DclkFrequency; + + gpu_metrics->current_gfxclk = metrics.Current.GfxclkFrequency; + gpu_metrics->current_socclk = metrics.Current.SocclkFrequency; + gpu_metrics->current_uclk = metrics.Current.MemclkFrequency; + gpu_metrics->current_fclk = metrics.Current.MemclkFrequency; + gpu_metrics->current_vclk = metrics.Current.VclkFrequency; + gpu_metrics->current_dclk = metrics.Current.DclkFrequency; + + memcpy(&gpu_metrics->current_coreclk[0], + &metrics.Current.CoreFrequency[0], + sizeof(uint16_t) * 4); + gpu_metrics->current_l3clk[0] = metrics.Current.L3Frequency[0]; + + gpu_metrics->throttle_status = metrics.Current.ThrottlerStatus; + + gpu_metrics->system_clock_counter = ktime_get_boottime_ns(); + + *table = (void *)gpu_metrics; + + return sizeof(struct gpu_metrics_v2_1); +} + +static ssize_t vangogh_common_get_gpu_metrics(struct smu_context *smu, + void **table) +{ + struct amdgpu_device *adev = smu->adev; + uint32_t if_version; + int ret = 0; + + ret = smu_cmn_get_smc_version(smu, &if_version, NULL); + if (ret) { + dev_err(adev->dev, "Failed to get smu if version!\n"); + return ret; + } + + if (if_version < 0x3) + ret = vangogh_get_legacy_gpu_metrics(smu, table); + else + ret = vangogh_get_gpu_metrics(smu, table); + + return ret; +} + static int vangogh_od_edit_dpm_table(struct smu_context *smu, enum PP_OD_DPM_TABLE_COMMAND type, long input[], uint32_t size) { @@ -1871,9 +2182,9 @@ static const struct pptable_funcs vangogh_ppt_funcs = { .set_watermarks_table = vangogh_set_watermarks_table, .set_driver_table_location = smu_v11_0_set_driver_table_location, .interrupt_work = smu_v11_0_interrupt_work, - .get_gpu_metrics = vangogh_get_gpu_metrics, + .get_gpu_metrics = vangogh_common_get_gpu_metrics, .od_edit_dpm_table = vangogh_od_edit_dpm_table, - .print_clk_levels = vangogh_print_clk_levels, + .print_clk_levels = vangogh_common_print_clk_levels, .set_default_dpm_table = vangogh_set_default_dpm_tables, .set_fine_grain_gfx_freq_parameters = vangogh_set_fine_grain_gfx_freq_parameters, .system_features_control = vangogh_system_features_control, @@ -1889,6 +2200,7 @@ static const struct pptable_funcs vangogh_ppt_funcs = { .get_ppt_limit = vangogh_get_ppt_limit, .get_power_limit = vangogh_get_power_limit, .set_power_limit = vangogh_set_power_limit, + .get_vbios_bootup_values = smu_v11_0_get_vbios_bootup_values, }; void vangogh_set_ppt_funcs(struct smu_context *smu) diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c index e3232295f2bf..f43b4c623685 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c @@ -1332,6 +1332,7 @@ static const struct pptable_funcs renoir_ppt_funcs = { .gfx_state_change_set = renoir_gfx_state_change_set, .set_fine_grain_gfx_freq_parameters = renoir_set_fine_grain_gfx_freq_parameters, .od_edit_dpm_table = renoir_od_edit_dpm_table, + .get_vbios_bootup_values = smu_v12_0_get_vbios_bootup_values, }; void renoir_set_ppt_funcs(struct smu_context *smu) diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu12/smu_v12_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu12/smu_v12_0.c index 6cc4855c8a37..d60b8c5e8715 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu12/smu_v12_0.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu12/smu_v12_0.c @@ -27,6 +27,7 @@ #include "amdgpu_smu.h" #include "atomfirmware.h" #include "amdgpu_atomfirmware.h" +#include "amdgpu_atombios.h" #include "smu_v12_0.h" #include "soc15_common.h" #include "atom.h" @@ -278,3 +279,125 @@ int smu_v12_0_set_driver_table_location(struct smu_context *smu) return ret; } + +static int smu_v12_0_atom_get_smu_clockinfo(struct amdgpu_device *adev, + uint8_t clk_id, + uint8_t syspll_id, + uint32_t *clk_freq) +{ + struct atom_get_smu_clock_info_parameters_v3_1 input = {0}; + struct atom_get_smu_clock_info_output_parameters_v3_1 *output; + int ret, index; + + input.clk_id = clk_id; + input.syspll_id = syspll_id; + input.command = GET_SMU_CLOCK_INFO_V3_1_GET_CLOCK_FREQ; + index = get_index_into_master_table(atom_master_list_of_command_functions_v2_1, + getsmuclockinfo); + + ret = amdgpu_atom_execute_table(adev->mode_info.atom_context, index, + (uint32_t *)&input); + if (ret) + return -EINVAL; + + output = (struct atom_get_smu_clock_info_output_parameters_v3_1 *)&input; + *clk_freq = le32_to_cpu(output->atom_smu_outputclkfreq.smu_clock_freq_hz) / 10000; + + return 0; +} + +int smu_v12_0_get_vbios_bootup_values(struct smu_context *smu) +{ + int ret, index; + uint16_t size; + uint8_t frev, crev; + struct atom_common_table_header *header; + struct atom_firmware_info_v3_1 *v_3_1; + struct atom_firmware_info_v3_3 *v_3_3; + + index = get_index_into_master_table(atom_master_list_of_data_tables_v2_1, + firmwareinfo); + + ret = amdgpu_atombios_get_data_table(smu->adev, index, &size, &frev, &crev, + (uint8_t **)&header); + if (ret) + return ret; + + if (header->format_revision != 3) { + dev_err(smu->adev->dev, "unknown atom_firmware_info version! for smu12\n"); + return -EINVAL; + } + + switch (header->content_revision) { + case 0: + case 1: + case 2: + v_3_1 = (struct atom_firmware_info_v3_1 *)header; + smu->smu_table.boot_values.revision = v_3_1->firmware_revision; + smu->smu_table.boot_values.gfxclk = v_3_1->bootup_sclk_in10khz; + smu->smu_table.boot_values.uclk = v_3_1->bootup_mclk_in10khz; + smu->smu_table.boot_values.socclk = 0; + smu->smu_table.boot_values.dcefclk = 0; + smu->smu_table.boot_values.vddc = v_3_1->bootup_vddc_mv; + smu->smu_table.boot_values.vddci = v_3_1->bootup_vddci_mv; + smu->smu_table.boot_values.mvddc = v_3_1->bootup_mvddc_mv; + smu->smu_table.boot_values.vdd_gfx = v_3_1->bootup_vddgfx_mv; + smu->smu_table.boot_values.cooling_id = v_3_1->coolingsolution_id; + smu->smu_table.boot_values.pp_table_id = 0; + smu->smu_table.boot_values.firmware_caps = v_3_1->firmware_capability; + break; + case 3: + case 4: + default: + v_3_3 = (struct atom_firmware_info_v3_3 *)header; + smu->smu_table.boot_values.revision = v_3_3->firmware_revision; + smu->smu_table.boot_values.gfxclk = v_3_3->bootup_sclk_in10khz; + smu->smu_table.boot_values.uclk = v_3_3->bootup_mclk_in10khz; + smu->smu_table.boot_values.socclk = 0; + smu->smu_table.boot_values.dcefclk = 0; + smu->smu_table.boot_values.vddc = v_3_3->bootup_vddc_mv; + smu->smu_table.boot_values.vddci = v_3_3->bootup_vddci_mv; + smu->smu_table.boot_values.mvddc = v_3_3->bootup_mvddc_mv; + smu->smu_table.boot_values.vdd_gfx = v_3_3->bootup_vddgfx_mv; + smu->smu_table.boot_values.cooling_id = v_3_3->coolingsolution_id; + smu->smu_table.boot_values.pp_table_id = v_3_3->pplib_pptable_id; + smu->smu_table.boot_values.firmware_caps = v_3_3->firmware_capability; + } + + smu->smu_table.boot_values.format_revision = header->format_revision; + smu->smu_table.boot_values.content_revision = header->content_revision; + + smu_v12_0_atom_get_smu_clockinfo(smu->adev, + (uint8_t)SMU12_SYSPLL0_SOCCLK_ID, + (uint8_t)SMU12_SYSPLL0_ID, + &smu->smu_table.boot_values.socclk); + + smu_v12_0_atom_get_smu_clockinfo(smu->adev, + (uint8_t)SMU12_SYSPLL1_DCFCLK_ID, + (uint8_t)SMU12_SYSPLL1_ID, + &smu->smu_table.boot_values.dcefclk); + + smu_v12_0_atom_get_smu_clockinfo(smu->adev, + (uint8_t)SMU12_SYSPLL0_VCLK_ID, + (uint8_t)SMU12_SYSPLL0_ID, + &smu->smu_table.boot_values.vclk); + + smu_v12_0_atom_get_smu_clockinfo(smu->adev, + (uint8_t)SMU12_SYSPLL0_DCLK_ID, + (uint8_t)SMU12_SYSPLL0_ID, + &smu->smu_table.boot_values.dclk); + + if ((smu->smu_table.boot_values.format_revision == 3) && + (smu->smu_table.boot_values.content_revision >= 2)) + smu_v12_0_atom_get_smu_clockinfo(smu->adev, + (uint8_t)SMU12_SYSPLL3_0_FCLK_ID, + (uint8_t)SMU12_SYSPLL3_0_ID, + &smu->smu_table.boot_values.fclk); + + smu_v12_0_atom_get_smu_clockinfo(smu->adev, + (uint8_t)SMU12_SYSPLL0_LCLK_ID, + (uint8_t)SMU12_SYSPLL0_ID, + &smu->smu_table.boot_values.lclk); + + return 0; +} diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c index 9813a86ca31a..dcbe3a72da09 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c @@ -78,6 +78,8 @@ #define smnPCIE_ESM_CTRL 0x111003D0 +#define CLOCK_VALID (1 << 31) + static const struct cmn2asic_msg_mapping aldebaran_message_map[SMU_MSG_MAX_COUNT] = { MSG_MAP(TestMessage, PPSMC_MSG_TestMessage, 0), MSG_MAP(GetSmuVersion, PPSMC_MSG_GetSmuVersion, 1), @@ -126,7 +128,8 @@ static const struct cmn2asic_msg_mapping aldebaran_message_map[SMU_MSG_MAX_COUNT MSG_MAP(SetExecuteDMATest, PPSMC_MSG_SetExecuteDMATest, 0), MSG_MAP(EnableDeterminism, PPSMC_MSG_EnableDeterminism, 0), MSG_MAP(DisableDeterminism, PPSMC_MSG_DisableDeterminism, 0), - MSG_MAP(SetUclkDpmMode, PPSMC_MSG_SetUclkDpmMode, 0), + MSG_MAP(SetUclkDpmMode, PPSMC_MSG_SetUclkDpmMode, 0), + MSG_MAP(GfxDriverResetRecovery, PPSMC_MSG_GfxDriverResetRecovery, 0), }; static const struct cmn2asic_mapping aldebaran_clk_map[SMU_CLK_COUNT] = { @@ -404,6 +407,9 @@ static int aldebaran_setup_pptable(struct smu_context *smu) { int ret = 0; + /* VBIOS pptable is the first choice */ + smu->smu_table.boot_values.pp_table_id = 0; + ret = smu_v13_0_setup_pptable(smu); if (ret) return ret; @@ -669,6 +675,7 @@ static int aldebaran_print_clk_levels(struct smu_context *smu, struct smu_13_0_dpm_context *dpm_context = NULL; uint32_t display_levels; uint32_t freq_values[3] = {0}; + uint32_t min_clk, max_clk; if (amdgpu_ras_intr_triggered()) return snprintf(buf, PAGE_SIZE, "unavailable\n"); @@ -696,12 +703,20 @@ static int aldebaran_print_clk_levels(struct smu_context *smu, display_levels = clocks.num_levels; + min_clk = smu->gfx_actual_hard_min_freq & CLOCK_VALID ? + smu->gfx_actual_hard_min_freq & ~CLOCK_VALID : + single_dpm_table->dpm_levels[0].value; + max_clk = smu->gfx_actual_soft_max_freq & CLOCK_VALID ? + smu->gfx_actual_soft_max_freq & ~CLOCK_VALID : + single_dpm_table->dpm_levels[1].value; + + freq_values[0] = min_clk; + freq_values[1] = max_clk; + /* fine-grained dpm has only 2 levels */ - if (now > single_dpm_table->dpm_levels[0].value && - now < single_dpm_table->dpm_levels[1].value) { + if (now > min_clk && now < max_clk) { display_levels = clocks.num_levels + 1; - freq_values[0] = single_dpm_table->dpm_levels[0].value; - freq_values[2] = single_dpm_table->dpm_levels[1].value; + freq_values[2] = max_clk; freq_values[1] = now; } @@ -711,12 +726,15 @@ static int aldebaran_print_clk_levels(struct smu_context *smu, */ if (display_levels == clocks.num_levels) { for (i = 0; i < clocks.num_levels; i++) - size += sprintf(buf + size, "%d: %uMhz %s\n", i, - clocks.data[i].clocks_in_khz / 1000, - (clocks.num_levels == 1) ? "*" : + size += sprintf( + buf + size, "%d: %uMhz %s\n", i, + freq_values[i], + (clocks.num_levels == 1) ? + "*" : (aldebaran_freqs_in_same_level( - clocks.data[i].clocks_in_khz / 1000, - now) ? "*" : "")); + freq_values[i], now) ? + "*" : + "")); } else { for (i = 0; i < display_levels; i++) size += sprintf(buf + size, "%d: %uMhz %s\n", i, @@ -1116,6 +1134,9 @@ static int aldebaran_set_performance_level(struct smu_context *smu, && (level != AMD_DPM_FORCED_LEVEL_PERF_DETERMINISM)) smu_cmn_send_smc_msg(smu, SMU_MSG_DisableDeterminism, NULL); + /* Reset user min/max gfx clock */ + smu->gfx_actual_hard_min_freq = 0; + smu->gfx_actual_soft_max_freq = 0; switch (level) { @@ -1157,7 +1178,14 @@ static int aldebaran_set_soft_freq_limited_range(struct smu_context *smu, if (smu_dpm->dpm_level == AMD_DPM_FORCED_LEVEL_MANUAL) { min_clk = max(min, dpm_context->dpm_tables.gfx_table.min); max_clk = min(max, dpm_context->dpm_tables.gfx_table.max); - return smu_v13_0_set_soft_freq_limited_range(smu, SMU_GFXCLK, min_clk, max_clk); + ret = smu_v13_0_set_soft_freq_limited_range(smu, SMU_GFXCLK, + min_clk, max_clk); + + if (!ret) { + smu->gfx_actual_hard_min_freq = min_clk | CLOCK_VALID; + smu->gfx_actual_soft_max_freq = max_clk | CLOCK_VALID; + } + return ret; } if (smu_dpm->dpm_level == AMD_DPM_FORCED_LEVEL_PERF_DETERMINISM) { @@ -1177,9 +1205,15 @@ static int aldebaran_set_soft_freq_limited_range(struct smu_context *smu, ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_EnableDeterminism, max, NULL); - if (ret) + if (ret) { dev_err(adev->dev, "Failed to enable determinism at GFX clock %d MHz\n", max); + } else { + smu->gfx_actual_hard_min_freq = + min_clk | CLOCK_VALID; + smu->gfx_actual_soft_max_freq = + max | CLOCK_VALID; + } } } @@ -1265,6 +1299,233 @@ static bool aldebaran_is_dpm_running(struct smu_context *smu) return !!(feature_enabled & SMC_DPM_FEATURE); } +static void aldebaran_fill_i2c_req(SwI2cRequest_t *req, bool write, + uint8_t address, uint32_t numbytes, + uint8_t *data) +{ + int i; + + req->I2CcontrollerPort = 0; + req->I2CSpeed = 2; + req->SlaveAddress = address; + req->NumCmds = numbytes; + + for (i = 0; i < numbytes; i++) { + SwI2cCmd_t *cmd = &req->SwI2cCmds[i]; + + /* First 2 bytes are always write for lower 2b EEPROM address */ + if (i < 2) + cmd->CmdConfig = CMDCONFIG_READWRITE_MASK; + else + cmd->CmdConfig = write ? CMDCONFIG_READWRITE_MASK : 0; + + + /* Add RESTART for read after address filled */ + cmd->CmdConfig |= (i == 2 && !write) ? CMDCONFIG_RESTART_MASK : 0; + + /* Add STOP in the end */ + cmd->CmdConfig |= (i == (numbytes - 1)) ? CMDCONFIG_STOP_MASK : 0; + + /* Fill with data regardless if read or write to simplify code */ + cmd->ReadWriteData = data[i]; + } +} + +static int aldebaran_i2c_read_data(struct i2c_adapter *control, + uint8_t address, + uint8_t *data, + uint32_t numbytes) +{ + uint32_t i, ret = 0; + SwI2cRequest_t req; + struct amdgpu_device *adev = to_amdgpu_device(control); + struct smu_table_context *smu_table = &adev->smu.smu_table; + struct smu_table *table = &smu_table->driver_table; + + if (numbytes > MAX_SW_I2C_COMMANDS) { + dev_err(adev->dev, "numbytes requested %d is over max allowed %d\n", + numbytes, MAX_SW_I2C_COMMANDS); + return -EINVAL; + } + + memset(&req, 0, sizeof(req)); + aldebaran_fill_i2c_req(&req, false, address, numbytes, data); + + mutex_lock(&adev->smu.mutex); + /* Now read data starting with that address */ + ret = smu_cmn_update_table(&adev->smu, SMU_TABLE_I2C_COMMANDS, 0, &req, + true); + mutex_unlock(&adev->smu.mutex); + + if (!ret) { + SwI2cRequest_t *res = (SwI2cRequest_t *)table->cpu_addr; + + /* Assume SMU fills res.SwI2cCmds[i].Data with read bytes */ + for (i = 0; i < numbytes; i++) + data[i] = res->SwI2cCmds[i].ReadWriteData; + + dev_dbg(adev->dev, "aldebaran_i2c_read_data, address = %x, bytes = %d, data :", + (uint16_t)address, numbytes); + + print_hex_dump(KERN_DEBUG, "data: ", DUMP_PREFIX_NONE, + 8, 1, data, numbytes, false); + } else + dev_err(adev->dev, "aldebaran_i2c_read_data - error occurred :%x", ret); + + return ret; +} + +static int aldebaran_i2c_write_data(struct i2c_adapter *control, + uint8_t address, + uint8_t *data, + uint32_t numbytes) +{ + uint32_t ret; + SwI2cRequest_t req; + struct amdgpu_device *adev = to_amdgpu_device(control); + + if (numbytes > MAX_SW_I2C_COMMANDS) { + dev_err(adev->dev, "numbytes requested %d is over max allowed %d\n", + numbytes, MAX_SW_I2C_COMMANDS); + return -EINVAL; + } + + memset(&req, 0, sizeof(req)); + aldebaran_fill_i2c_req(&req, true, address, numbytes, data); + + mutex_lock(&adev->smu.mutex); + ret = smu_cmn_update_table(&adev->smu, SMU_TABLE_I2C_COMMANDS, 0, &req, true); + mutex_unlock(&adev->smu.mutex); + + if (!ret) { + dev_dbg(adev->dev, "aldebaran_i2c_write(), address = %x, bytes = %d , data: ", + (uint16_t)address, numbytes); + + print_hex_dump(KERN_DEBUG, "data: ", DUMP_PREFIX_NONE, + 8, 1, data, numbytes, false); + /* + * According to EEPROM spec there is a MAX of 10 ms required for + * EEPROM to flush internal RX buffer after STOP was issued at the + * end of write transaction. During this time the EEPROM will not be + * responsive to any more commands - so wait a bit more. + */ + msleep(10); + + } else + dev_err(adev->dev, "aldebaran_i2c_write- error occurred :%x", ret); + + return ret; +} + +static int aldebaran_i2c_xfer(struct i2c_adapter *i2c_adap, + struct i2c_msg *msgs, int num) +{ + uint32_t i, j, ret, data_size, data_chunk_size, next_eeprom_addr = 0; + uint8_t *data_ptr, data_chunk[MAX_SW_I2C_COMMANDS] = { 0 }; + + for (i = 0; i < num; i++) { + /* + * SMU interface allows at most MAX_SW_I2C_COMMANDS bytes of data at + * once and hence the data needs to be spliced into chunks and sent each + * chunk separately + */ + data_size = msgs[i].len - 2; + data_chunk_size = MAX_SW_I2C_COMMANDS - 2; + next_eeprom_addr = (msgs[i].buf[0] << 8 & 0xff00) | (msgs[i].buf[1] & 0xff); + data_ptr = msgs[i].buf + 2; + + for (j = 0; j < data_size / data_chunk_size; j++) { + /* Insert the EEPROM dest addess, bits 0-15 */ + data_chunk[0] = ((next_eeprom_addr >> 8) & 0xff); + data_chunk[1] = (next_eeprom_addr & 0xff); + + if (msgs[i].flags & I2C_M_RD) { + ret = aldebaran_i2c_read_data(i2c_adap, + (uint8_t)msgs[i].addr, + data_chunk, MAX_SW_I2C_COMMANDS); + + memcpy(data_ptr, data_chunk + 2, data_chunk_size); + } else { + + memcpy(data_chunk + 2, data_ptr, data_chunk_size); + + ret = aldebaran_i2c_write_data(i2c_adap, + (uint8_t)msgs[i].addr, + data_chunk, MAX_SW_I2C_COMMANDS); + } + + if (ret) { + num = -EIO; + goto fail; + } + + next_eeprom_addr += data_chunk_size; + data_ptr += data_chunk_size; + } + + if (data_size % data_chunk_size) { + data_chunk[0] = ((next_eeprom_addr >> 8) & 0xff); + data_chunk[1] = (next_eeprom_addr & 0xff); + + if (msgs[i].flags & I2C_M_RD) { + ret = aldebaran_i2c_read_data(i2c_adap, + (uint8_t)msgs[i].addr, + data_chunk, (data_size % data_chunk_size) + 2); + + memcpy(data_ptr, data_chunk + 2, data_size % data_chunk_size); + } else { + memcpy(data_chunk + 2, data_ptr, data_size % data_chunk_size); + + ret = aldebaran_i2c_write_data(i2c_adap, + (uint8_t)msgs[i].addr, + data_chunk, (data_size % data_chunk_size) + 2); + } + + if (ret) { + num = -EIO; + goto fail; + } + } + } + +fail: + return num; +} + +static u32 aldebaran_i2c_func(struct i2c_adapter *adap) +{ + return I2C_FUNC_I2C | I2C_FUNC_SMBUS_EMUL; +} + + +static const struct i2c_algorithm aldebaran_i2c_algo = { + .master_xfer = aldebaran_i2c_xfer, + .functionality = aldebaran_i2c_func, +}; + +static int aldebaran_i2c_control_init(struct smu_context *smu, struct i2c_adapter *control) +{ + struct amdgpu_device *adev = to_amdgpu_device(control); + int res; + + control->owner = THIS_MODULE; + control->class = I2C_CLASS_SPD; + control->dev.parent = &adev->pdev->dev; + control->algo = &aldebaran_i2c_algo; + snprintf(control->name, sizeof(control->name), "AMDGPU SMU"); + + res = i2c_add_adapter(control); + if (res) + DRM_ERROR("Failed to register hw i2c, err: %d\n", res); + + return res; +} + +static void aldebaran_i2c_control_fini(struct smu_context *smu, struct i2c_adapter *control) +{ + i2c_del_adapter(control); +} + static void aldebaran_get_unique_id(struct smu_context *smu) { struct amdgpu_device *adev = smu->adev; @@ -1432,6 +1693,57 @@ static ssize_t aldebaran_get_gpu_metrics(struct smu_context *smu, return sizeof(struct gpu_metrics_v1_1); } +static int aldebaran_mode2_reset(struct smu_context *smu) +{ + u32 smu_version; + int ret = 0, index; + struct amdgpu_device *adev = smu->adev; + int timeout = 10; + + smu_cmn_get_smc_version(smu, NULL, &smu_version); + + index = smu_cmn_to_asic_specific_index(smu, CMN2ASIC_MAPPING_MSG, + SMU_MSG_GfxDeviceDriverReset); + + mutex_lock(&smu->message_lock); + if (smu_version >= 0x00441400) { + ret = smu_cmn_send_msg_without_waiting(smu, (uint16_t)index, SMU_RESET_MODE_2); + /* This is similar to FLR, wait till max FLR timeout */ + msleep(100); + dev_dbg(smu->adev->dev, "restore config space...\n"); + /* Restore the config space saved during init */ + amdgpu_device_load_pci_state(adev->pdev); + + dev_dbg(smu->adev->dev, "wait for reset ack\n"); + while (ret == -ETIME && timeout) { + ret = smu_cmn_wait_for_response(smu); + /* Wait a bit more time for getting ACK */ + if (ret == -ETIME) { + --timeout; + usleep_range(500, 1000); + continue; + } + + if (ret != 1) { + dev_err(adev->dev, "failed to send mode2 message \tparam: 0x%08x response %#x\n", + SMU_RESET_MODE_2, ret); + goto out; + } + } + + } else { + dev_err(adev->dev, "smu fw 0x%x does not support MSG_GfxDeviceDriverReset MSG\n", + smu_version); + } + + if (ret == 1) + ret = 0; +out: + mutex_unlock(&smu->message_lock); + + return ret; +} + static bool aldebaran_is_mode1_reset_supported(struct smu_context *smu) { #if 0 @@ -1460,6 +1772,19 @@ static bool aldebaran_is_mode2_reset_supported(struct smu_context *smu) return true; } +static int aldebaran_set_mp1_state(struct smu_context *smu, + enum pp_mp1_state mp1_state) +{ + switch (mp1_state) { + case PP_MP1_STATE_UNLOAD: + return smu_cmn_set_mp1_state(smu, mp1_state); + default: + return -EINVAL; + } + + return 0; +} + static const struct pptable_funcs aldebaran_ppt_funcs = { /* init dpm */ .get_allowed_feature_mask = aldebaran_get_allowed_feature_mask, @@ -1517,7 +1842,11 @@ static const struct pptable_funcs aldebaran_ppt_funcs = { .mode1_reset_is_support = aldebaran_is_mode1_reset_supported, .mode2_reset_is_support = aldebaran_is_mode2_reset_supported, .mode1_reset = smu_v13_0_mode1_reset, - .mode2_reset = smu_v13_0_mode2_reset, + .set_mp1_state = aldebaran_set_mp1_state, + .mode2_reset = aldebaran_mode2_reset, + .wait_for_event = smu_v13_0_wait_for_event, + .i2c_init = aldebaran_i2c_control_init, + .i2c_fini = aldebaran_i2c_control_fini, }; void aldebaran_set_ppt_funcs(struct smu_context *smu) diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c index bd3a9c89dc44..0864083e7435 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c @@ -72,8 +72,8 @@ MODULE_FIRMWARE("amdgpu/aldebaran_smc.bin"); #define PCIE_LC_SPEED_CNTL__LC_CURRENT_DATA_RATE_MASK 0xC000 #define PCIE_LC_SPEED_CNTL__LC_CURRENT_DATA_RATE__SHIFT 0xE -static int link_width[] = {0, 1, 2, 4, 8, 12, 16}; -static int link_speed[] = {25, 50, 80, 160}; +static const int link_width[] = {0, 1, 2, 4, 8, 12, 16}; +static const int link_speed[] = {25, 50, 80, 160}; int smu_v13_0_init_microcode(struct smu_context *smu) { @@ -276,8 +276,6 @@ int smu_v13_0_setup_pptable(struct smu_context *smu) void *table; uint16_t version_major, version_minor; - /* temporarily hardcode to use vbios pptable */ - smu->smu_table.boot_values.pp_table_id = 0; if (amdgpu_smu_pptable_id >= 0) { smu->smu_table.boot_values.pp_table_id = amdgpu_smu_pptable_id; @@ -1374,19 +1372,43 @@ int smu_v13_0_mode1_reset(struct smu_context *smu) return ret; } -int smu_v13_0_mode2_reset(struct smu_context *smu) +static int smu_v13_0_wait_for_reset_complete(struct smu_context *smu, + uint64_t event_arg) { - u32 smu_version; int ret = 0; - struct amdgpu_device *adev = smu->adev; - smu_cmn_get_smc_version(smu, NULL, &smu_version); - if (smu_version >= 0x00440700) - ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_GfxDeviceDriverReset, SMU_RESET_MODE_2, NULL); - else - dev_err(adev->dev, "smu fw 0x%x does not support MSG_GfxDeviceDriverReset MSG\n", smu_version); - /*TODO: mode2 reset wait time should be shorter, will modify it later*/ + + dev_dbg(smu->adev->dev, "waiting for smu reset complete\n"); + ret = smu_cmn_send_smc_msg(smu, SMU_MSG_GfxDriverResetRecovery, NULL); + + return ret; +} + +int smu_v13_0_wait_for_event(struct smu_context *smu, enum smu_event_type event, + uint64_t event_arg) +{ + int ret = -EINVAL; + + switch (event) { + case SMU_EVENT_RESET_COMPLETE: + ret = smu_v13_0_wait_for_reset_complete(smu, event_arg); + break; + default: + break; + } + + return ret; +} + +int smu_v13_0_mode2_reset(struct smu_context *smu) +{ + int ret; + + ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_GfxDeviceDriverReset, + SMU_RESET_MODE_2, NULL); + /*TODO: mode2 reset wait time should be shorter, add ASIC specific func if required */ if (!ret) msleep(SMU13_MODE1_RESET_WAIT_TIME_IN_MS); + return ret; } @@ -1686,10 +1708,14 @@ int smu_v13_0_get_dpm_level_count(struct smu_context *smu, enum smu_clk_type clk_type, uint32_t *value) { - return smu_v13_0_get_dpm_freq_by_index(smu, - clk_type, - 0xff, - value); + int ret; + + ret = smu_v13_0_get_dpm_freq_by_index(smu, clk_type, 0xff, value); + /* FW returns 0 based max level, increment by one */ + if (!ret && value) + ++(*value); + + return ret; } int smu_v13_0_set_single_dpm_table(struct smu_context *smu, diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c index 4b45953b36d8..dc7d2e71aa6f 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c @@ -76,10 +76,10 @@ static void smu_cmn_read_arg(struct smu_context *smu, *arg = RREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_82); } -static int smu_cmn_wait_for_response(struct smu_context *smu) +int smu_cmn_wait_for_response(struct smu_context *smu) { struct amdgpu_device *adev = smu->adev; - uint32_t cur_value, i, timeout = adev->usec_timeout * 10; + uint32_t cur_value, i, timeout = adev->usec_timeout * 20; for (i = 0; i < timeout; i++) { cur_value = RREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_90); @@ -780,3 +780,31 @@ void smu_cmn_init_soft_gpu_metrics(void *table, uint8_t frev, uint8_t crev) header->structure_size = structure_size; } + +int smu_cmn_set_mp1_state(struct smu_context *smu, + enum pp_mp1_state mp1_state) +{ + enum smu_message_type msg; + int ret; + + switch (mp1_state) { + case PP_MP1_STATE_SHUTDOWN: + msg = SMU_MSG_PrepareMp1ForShutdown; + break; + case PP_MP1_STATE_UNLOAD: + msg = SMU_MSG_PrepareMp1ForUnload; + break; + case PP_MP1_STATE_RESET: + msg = SMU_MSG_PrepareMp1ForReset; + break; + case PP_MP1_STATE_NONE: + default: + return 0; + } + + ret = smu_cmn_send_smc_msg(smu, msg, NULL); + if (ret) + dev_err(smu->adev->dev, "[PrepareMp1] Failed!\n"); + + return ret; +} diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.h b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.h index c69250185575..da6ff6f024f9 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.h +++ b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.h @@ -37,6 +37,8 @@ int smu_cmn_send_smc_msg(struct smu_context *smu, enum smu_message_type msg, uint32_t *read_arg); +int smu_cmn_wait_for_response(struct smu_context *smu); + int smu_cmn_to_asic_specific_index(struct smu_context *smu, enum smu_cmn2asic_mapping_type type, uint32_t index); @@ -99,5 +101,8 @@ int smu_cmn_get_metrics_table(struct smu_context *smu, void smu_cmn_init_soft_gpu_metrics(void *table, uint8_t frev, uint8_t crev); +int smu_cmn_set_mp1_state(struct smu_context *smu, + enum pp_mp1_state mp1_state); + #endif #endif diff --git a/drivers/gpu/drm/arm/display/include/malidp_utils.h b/drivers/gpu/drm/arm/display/include/malidp_utils.h index 3bc383d5bf73..49a1d7f3539c 100644 --- a/drivers/gpu/drm/arm/display/include/malidp_utils.h +++ b/drivers/gpu/drm/arm/display/include/malidp_utils.h @@ -13,9 +13,6 @@ #define has_bit(nr, mask) (BIT(nr) & (mask)) #define has_bits(bits, mask) (((bits) & (mask)) == (bits)) -#define dp_for_each_set_bit(bit, mask) \ - for_each_set_bit((bit), ((unsigned long *)&(mask)), sizeof(mask) * 8) - #define dp_wait_cond(__cond, __tries, __min_range, __max_range) \ ({ \ int num_tries = __tries; \ diff --git a/drivers/gpu/drm/arm/display/komeda/komeda_dev.c b/drivers/gpu/drm/arm/display/komeda/komeda_dev.c index ca891ae14d36..cc7664c95a54 100644 --- a/drivers/gpu/drm/arm/display/komeda/komeda_dev.c +++ b/drivers/gpu/drm/arm/display/komeda/komeda_dev.c @@ -62,7 +62,7 @@ core_id_show(struct device *dev, struct device_attribute *attr, char *buf) { struct komeda_dev *mdev = dev_to_mdev(dev); - return snprintf(buf, PAGE_SIZE, "0x%08x\n", mdev->chip.core_id); + return sysfs_emit(buf, "0x%08x\n", mdev->chip.core_id); } static DEVICE_ATTR_RO(core_id); @@ -85,7 +85,7 @@ config_id_show(struct device *dev, struct device_attribute *attr, char *buf) if (pipe->layers[i]->layer_type == KOMEDA_FMT_RICH_LAYER) config_id.n_richs++; } - return snprintf(buf, PAGE_SIZE, "0x%08x\n", config_id.value); + return sysfs_emit(buf, "0x%08x\n", config_id.value); } static DEVICE_ATTR_RO(config_id); @@ -94,7 +94,7 @@ aclk_hz_show(struct device *dev, struct device_attribute *attr, char *buf) { struct komeda_dev *mdev = dev_to_mdev(dev); - return snprintf(buf, PAGE_SIZE, "%lu\n", clk_get_rate(mdev->aclk)); + return sysfs_emit(buf, "%lu\n", clk_get_rate(mdev->aclk)); } static DEVICE_ATTR_RO(aclk_hz); diff --git a/drivers/gpu/drm/arm/display/komeda/komeda_pipeline.c b/drivers/gpu/drm/arm/display/komeda/komeda_pipeline.c index 719a79728e24..06c595378dda 100644 --- a/drivers/gpu/drm/arm/display/komeda/komeda_pipeline.c +++ b/drivers/gpu/drm/arm/display/komeda/komeda_pipeline.c @@ -46,8 +46,9 @@ void komeda_pipeline_destroy(struct komeda_dev *mdev, { struct komeda_component *c; int i; + unsigned long avail_comps = pipe->avail_comps; - dp_for_each_set_bit(i, pipe->avail_comps) { + for_each_set_bit(i, &avail_comps, 32) { c = komeda_pipeline_get_component(pipe, i); komeda_component_destroy(mdev, c); } @@ -247,6 +248,7 @@ static void komeda_pipeline_dump(struct komeda_pipeline *pipe) { struct komeda_component *c; int id; + unsigned long avail_comps = pipe->avail_comps; DRM_INFO("Pipeline-%d: n_layers: %d, n_scalers: %d, output: %s.\n", pipe->id, pipe->n_layers, pipe->n_scalers, @@ -258,7 +260,7 @@ static void komeda_pipeline_dump(struct komeda_pipeline *pipe) pipe->of_output_links[1] ? pipe->of_output_links[1]->full_name : "none"); - dp_for_each_set_bit(id, pipe->avail_comps) { + for_each_set_bit(id, &avail_comps, 32) { c = komeda_pipeline_get_component(pipe, id); komeda_component_dump(c); @@ -270,8 +272,9 @@ static void komeda_component_verify_inputs(struct komeda_component *c) struct komeda_pipeline *pipe = c->pipeline; struct komeda_component *input; int id; + unsigned long supported_inputs = c->supported_inputs; - dp_for_each_set_bit(id, c->supported_inputs) { + for_each_set_bit(id, &supported_inputs, 32) { input = komeda_pipeline_get_component(pipe, id); if (!input) { c->supported_inputs &= ~(BIT(id)); @@ -302,8 +305,9 @@ static void komeda_pipeline_assemble(struct komeda_pipeline *pipe) struct komeda_component *c; struct komeda_layer *layer; int i, id; + unsigned long avail_comps = pipe->avail_comps; - dp_for_each_set_bit(id, pipe->avail_comps) { + for_each_set_bit(id, &avail_comps, 32) { c = komeda_pipeline_get_component(pipe, id); komeda_component_verify_inputs(c); } @@ -355,13 +359,15 @@ void komeda_pipeline_dump_register(struct komeda_pipeline *pipe, { struct komeda_component *c; u32 id; + unsigned long avail_comps; seq_printf(sf, "\n======== Pipeline-%d ==========\n", pipe->id); if (pipe->funcs && pipe->funcs->dump_register) pipe->funcs->dump_register(pipe, sf); - dp_for_each_set_bit(id, pipe->avail_comps) { + avail_comps = pipe->avail_comps; + for_each_set_bit(id, &avail_comps, 32) { c = komeda_pipeline_get_component(pipe, id); seq_printf(sf, "\n------%s------\n", c->name); diff --git a/drivers/gpu/drm/arm/display/komeda/komeda_pipeline_state.c b/drivers/gpu/drm/arm/display/komeda/komeda_pipeline_state.c index 5c085116de3f..e672b9cffee3 100644 --- a/drivers/gpu/drm/arm/display/komeda/komeda_pipeline_state.c +++ b/drivers/gpu/drm/arm/display/komeda/komeda_pipeline_state.c @@ -1231,14 +1231,15 @@ komeda_pipeline_unbound_components(struct komeda_pipeline *pipe, struct komeda_pipeline_state *old = priv_to_pipe_st(pipe->obj.state); struct komeda_component_state *c_st; struct komeda_component *c; - u32 disabling_comps, id; + u32 id; + unsigned long disabling_comps; WARN_ON(!old); disabling_comps = (~new->active_comps) & old->active_comps; /* unbound all disabling component */ - dp_for_each_set_bit(id, disabling_comps) { + for_each_set_bit(id, &disabling_comps, 32) { c = komeda_pipeline_get_component(pipe, id); c_st = komeda_component_get_state_and_set_user(c, drm_st, NULL, new->crtc); @@ -1286,7 +1287,8 @@ bool komeda_pipeline_disable(struct komeda_pipeline *pipe, struct komeda_pipeline_state *old; struct komeda_component *c; struct komeda_component_state *c_st; - u32 id, disabling_comps = 0; + u32 id; + unsigned long disabling_comps; old = komeda_pipeline_get_old_state(pipe, old_state); @@ -1296,10 +1298,10 @@ bool komeda_pipeline_disable(struct komeda_pipeline *pipe, disabling_comps = old->active_comps & pipe->standalone_disabled_comps; - DRM_DEBUG_ATOMIC("PIPE%d: active_comps: 0x%x, disabling_comps: 0x%x.\n", + DRM_DEBUG_ATOMIC("PIPE%d: active_comps: 0x%x, disabling_comps: 0x%lx.\n", pipe->id, old->active_comps, disabling_comps); - dp_for_each_set_bit(id, disabling_comps) { + for_each_set_bit(id, &disabling_comps, 32) { c = komeda_pipeline_get_component(pipe, id); c_st = priv_to_comp_st(c->obj.state); @@ -1330,16 +1332,17 @@ void komeda_pipeline_update(struct komeda_pipeline *pipe, struct komeda_pipeline_state *new = priv_to_pipe_st(pipe->obj.state); struct komeda_pipeline_state *old; struct komeda_component *c; - u32 id, changed_comps = 0; + u32 id; + unsigned long changed_comps; old = komeda_pipeline_get_old_state(pipe, old_state); changed_comps = new->active_comps | old->active_comps; - DRM_DEBUG_ATOMIC("PIPE%d: active_comps: 0x%x, changed: 0x%x.\n", + DRM_DEBUG_ATOMIC("PIPE%d: active_comps: 0x%x, changed: 0x%lx.\n", pipe->id, new->active_comps, changed_comps); - dp_for_each_set_bit(id, changed_comps) { + for_each_set_bit(id, &changed_comps, 32) { c = komeda_pipeline_get_component(pipe, id); if (new->active_comps & BIT(c->id)) diff --git a/drivers/gpu/drm/bridge/Kconfig b/drivers/gpu/drm/bridge/Kconfig index 7de170e113d3..400193e38d29 100644 --- a/drivers/gpu/drm/bridge/Kconfig +++ b/drivers/gpu/drm/bridge/Kconfig @@ -55,7 +55,7 @@ config DRM_DISPLAY_CONNECTOR depends on OF help Driver for display connectors with support for DDC and hot-plug - detection. Most display controller handle display connectors + detection. Most display controllers handle display connectors internally and don't need this driver, but the DRM subsystem is moving towards separating connector handling from display controllers on ARM-based platforms. Saying Y here when this driver is not needed @@ -213,6 +213,7 @@ config DRM_TOSHIBA_TC358762 tristate "TC358762 DSI/DPI bridge" depends on OF select DRM_MIPI_DSI + select DRM_KMS_HELPER select DRM_PANEL_BRIDGE help Toshiba TC358762 DSI/DPI bridge driver. diff --git a/drivers/gpu/drm/bridge/lontium-lt8912b.c b/drivers/gpu/drm/bridge/lontium-lt8912b.c index 55d8aa22c882..443f1b47e031 100644 --- a/drivers/gpu/drm/bridge/lontium-lt8912b.c +++ b/drivers/gpu/drm/bridge/lontium-lt8912b.c @@ -5,6 +5,7 @@ #include <linux/device.h> #include <linux/delay.h> +#include <linux/gpio/consumer.h> #include <linux/i2c.h> #include <linux/gpio.h> #include <linux/of_gpio.h> diff --git a/drivers/gpu/drm/drm_atomic.c b/drivers/gpu/drm/drm_atomic.c index 5b4547e0f775..dd9ed000ad4c 100644 --- a/drivers/gpu/drm/drm_atomic.c +++ b/drivers/gpu/drm/drm_atomic.c @@ -1183,7 +1183,7 @@ EXPORT_SYMBOL(drm_atomic_add_encoder_bridges); * This function walks the current configuration and adds all connectors * currently using @crtc to the atomic configuration @state. Note that this * function must acquire the connection mutex. This can potentially cause - * unneeded seralization if the update is just for the planes on one CRTC. Hence + * unneeded serialization if the update is just for the planes on one CRTC. Hence * drivers and helpers should only call this when really needed (e.g. when a * full modeset needs to happen due to some change). * @@ -1248,7 +1248,7 @@ EXPORT_SYMBOL(drm_atomic_add_affected_connectors); * * Since acquiring a plane state will always also acquire the w/w mutex of the * current CRTC for that plane (if there is any) adding all the plane states for - * a CRTC will not reduce parallism of atomic updates. + * a CRTC will not reduce parallelism of atomic updates. * * Returns: * 0 on success or can fail with -EDEADLK or -ENOMEM. When the error is EDEADLK diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c index 01f47e59163f..159014455fab 100644 --- a/drivers/gpu/drm/drm_dp_mst_topology.c +++ b/drivers/gpu/drm/drm_dp_mst_topology.c @@ -4109,10 +4109,9 @@ static int drm_dp_mst_handle_up_req(struct drm_dp_mst_topology_mgr *mgr) return 0; up_req = kzalloc(sizeof(*up_req), GFP_KERNEL); - if (!up_req) { - DRM_ERROR("Not enough memory to process MST up req\n"); + if (!up_req) return -ENOMEM; - } + INIT_LIST_HEAD(&up_req->next); drm_dp_sideband_parse_req(&mgr->up_req_recv, &up_req->msg); diff --git a/drivers/gpu/drm/drm_internal.h b/drivers/gpu/drm/drm_internal.h index fad2249ee67b..1265de2b9d90 100644 --- a/drivers/gpu/drm/drm_internal.h +++ b/drivers/gpu/drm/drm_internal.h @@ -170,7 +170,6 @@ void drm_sysfs_connector_remove(struct drm_connector *connector); void drm_sysfs_lease_event(struct drm_device *dev); /* drm_gem.c */ -struct drm_gem_object; int drm_gem_init(struct drm_device *dev); int drm_gem_handle_create_tail(struct drm_file *file_priv, struct drm_gem_object *obj, diff --git a/drivers/gpu/drm/drm_modes.c b/drivers/gpu/drm/drm_modes.c index 1ac67d4505e0..33a93fa24eb1 100644 --- a/drivers/gpu/drm/drm_modes.c +++ b/drivers/gpu/drm/drm_modes.c @@ -1864,6 +1864,9 @@ drm_mode_create_from_cmdline_mode(struct drm_device *dev, { struct drm_display_mode *mode; + if (cmd->xres == 0 || cmd->yres == 0) + return NULL; + if (cmd->cvt) mode = drm_cvt_mode(dev, cmd->xres, cmd->yres, diff --git a/drivers/gpu/drm/drm_syncobj.c b/drivers/gpu/drm/drm_syncobj.c index 6231a8214c25..fdd2ec87cdd1 100644 --- a/drivers/gpu/drm/drm_syncobj.c +++ b/drivers/gpu/drm/drm_syncobj.c @@ -350,12 +350,16 @@ EXPORT_SYMBOL(drm_syncobj_replace_fence); * * Assign a already signaled stub fence to the sync object. */ -static void drm_syncobj_assign_null_handle(struct drm_syncobj *syncobj) +static int drm_syncobj_assign_null_handle(struct drm_syncobj *syncobj) { - struct dma_fence *fence = dma_fence_get_stub(); + struct dma_fence *fence = dma_fence_allocate_private_stub(); + + if (IS_ERR(fence)) + return PTR_ERR(fence); drm_syncobj_replace_fence(syncobj, fence); dma_fence_put(fence); + return 0; } /* 5s default for wait submission */ @@ -478,6 +482,7 @@ EXPORT_SYMBOL(drm_syncobj_free); int drm_syncobj_create(struct drm_syncobj **out_syncobj, uint32_t flags, struct dma_fence *fence) { + int ret; struct drm_syncobj *syncobj; syncobj = kzalloc(sizeof(struct drm_syncobj), GFP_KERNEL); @@ -488,8 +493,13 @@ int drm_syncobj_create(struct drm_syncobj **out_syncobj, uint32_t flags, INIT_LIST_HEAD(&syncobj->cb_list); spin_lock_init(&syncobj->lock); - if (flags & DRM_SYNCOBJ_CREATE_SIGNALED) - drm_syncobj_assign_null_handle(syncobj); + if (flags & DRM_SYNCOBJ_CREATE_SIGNALED) { + ret = drm_syncobj_assign_null_handle(syncobj); + if (ret < 0) { + drm_syncobj_put(syncobj); + return ret; + } + } if (fence) drm_syncobj_replace_fence(syncobj, fence); @@ -1334,8 +1344,11 @@ drm_syncobj_signal_ioctl(struct drm_device *dev, void *data, if (ret < 0) return ret; - for (i = 0; i < args->count_handles; i++) - drm_syncobj_assign_null_handle(syncobjs[i]); + for (i = 0; i < args->count_handles; i++) { + ret = drm_syncobj_assign_null_handle(syncobjs[i]); + if (ret < 0) + break; + } drm_syncobj_array_free(syncobjs, args->count_handles); diff --git a/drivers/gpu/drm/drm_vblank.c b/drivers/gpu/drm/drm_vblank.c index 2bd989688eae..3417e1ac7918 100644 --- a/drivers/gpu/drm/drm_vblank.c +++ b/drivers/gpu/drm/drm_vblank.c @@ -1478,6 +1478,7 @@ static void drm_vblank_restore(struct drm_device *dev, unsigned int pipe) u64 diff_ns; u32 cur_vblank, diff = 1; int count = DRM_TIMESTAMP_MAXRETRIES; + u32 max_vblank_count = drm_max_vblank_count(dev, pipe); if (drm_WARN_ON(dev, pipe >= dev->num_crtcs)) return; @@ -1504,7 +1505,7 @@ static void drm_vblank_restore(struct drm_device *dev, unsigned int pipe) drm_dbg_vbl(dev, "missed %d vblanks in %lld ns, frame duration=%d ns, hw_diff=%d\n", diff, diff_ns, framedur_ns, cur_vblank - vblank->last); - store_vblank(dev, pipe, diff, t_vblank, cur_vblank); + vblank->last = (cur_vblank - diff) & max_vblank_count; } /** diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem.c b/drivers/gpu/drm/etnaviv/etnaviv_gem.c index 6d38c5c17f23..db69f19ab5bc 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gem.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_gem.c @@ -689,7 +689,8 @@ static int etnaviv_gem_userptr_get_pages(struct etnaviv_gem_object *etnaviv_obj) struct page **pages = pvec + pinned; ret = pin_user_pages_fast(ptr, num_pages, - !userptr->ro ? FOLL_WRITE : 0, pages); + FOLL_WRITE | FOLL_FORCE | FOLL_LONGTERM, + pages); if (ret < 0) { unpin_user_pages(pvec, pinned); kvfree(pvec); diff --git a/drivers/gpu/drm/exynos/exynos5433_drm_decon.c b/drivers/gpu/drm/exynos/exynos5433_drm_decon.c index c277d2fc50c6..b9a4b7670a89 100644 --- a/drivers/gpu/drm/exynos/exynos5433_drm_decon.c +++ b/drivers/gpu/drm/exynos/exynos5433_drm_decon.c @@ -13,7 +13,6 @@ #include <linux/irq.h> #include <linux/mfd/syscon.h> #include <linux/of_device.h> -#include <linux/of_gpio.h> #include <linux/platform_device.h> #include <linux/pm_runtime.h> #include <linux/regmap.h> diff --git a/drivers/gpu/drm/gma500/power.c b/drivers/gpu/drm/gma500/power.c index 56ef88237ef6..f07641dfa5a4 100644 --- a/drivers/gpu/drm/gma500/power.c +++ b/drivers/gpu/drm/gma500/power.c @@ -36,7 +36,7 @@ #include <linux/pm_runtime.h> static struct mutex power_mutex; /* Serialize power ops */ -static spinlock_t power_ctrl_lock; /* Serialize power claim */ +static DEFINE_SPINLOCK(power_ctrl_lock); /* Serialize power claim */ /** * gma_power_init - initialise power manager @@ -55,7 +55,6 @@ void gma_power_init(struct drm_device *dev) dev_priv->display_power = true; /* We start active */ dev_priv->display_count = 0; /* Currently no users */ dev_priv->suspended = false; /* And not suspended */ - spin_lock_init(&power_ctrl_lock); mutex_init(&power_mutex); if (dev_priv->ops->init_pm) diff --git a/drivers/gpu/drm/i915/display/intel_acpi.c b/drivers/gpu/drm/i915/display/intel_acpi.c index e21fb14d5e07..833d0c1be4f1 100644 --- a/drivers/gpu/drm/i915/display/intel_acpi.c +++ b/drivers/gpu/drm/i915/display/intel_acpi.c @@ -84,13 +84,31 @@ static void intel_dsm_platform_mux_info(acpi_handle dhandle) return; } + if (!pkg->package.count) { + DRM_DEBUG_DRIVER("no connection in _DSM\n"); + return; + } + connector_count = &pkg->package.elements[0]; DRM_DEBUG_DRIVER("MUX info connectors: %lld\n", (unsigned long long)connector_count->integer.value); for (i = 1; i < pkg->package.count; i++) { union acpi_object *obj = &pkg->package.elements[i]; - union acpi_object *connector_id = &obj->package.elements[0]; - union acpi_object *info = &obj->package.elements[1]; + union acpi_object *connector_id; + union acpi_object *info; + + if (obj->type != ACPI_TYPE_PACKAGE || obj->package.count < 2) { + DRM_DEBUG_DRIVER("Invalid object for MUX #%d\n", i); + continue; + } + + connector_id = &obj->package.elements[0]; + info = &obj->package.elements[1]; + if (info->type != ACPI_TYPE_BUFFER || info->buffer.length < 4) { + DRM_DEBUG_DRIVER("Invalid info for MUX obj #%d\n", i); + continue; + } + DRM_DEBUG_DRIVER("Connector id: 0x%016llx\n", (unsigned long long)connector_id->integer.value); DRM_DEBUG_DRIVER(" port id: %s\n", diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c index d74b263c5f4e..64e9107d70f7 100644 --- a/drivers/gpu/drm/i915/display/intel_display.c +++ b/drivers/gpu/drm/i915/display/intel_display.c @@ -1403,7 +1403,8 @@ intel_fb_stride_alignment(const struct drm_framebuffer *fb, int color_plane) * require the entire fb to accommodate that to avoid * potential runtime errors at plane configuration time. */ - if (IS_DISPLAY_VER(dev_priv, 9) && color_plane == 0 && fb->width > 3840) + if ((IS_DISPLAY_VER(dev_priv, 9) || IS_GEMINILAKE(dev_priv)) && + color_plane == 0 && fb->width > 3840) tile_width *= 4; /* * The main surface pitch must be padded to a multiple of four diff --git a/drivers/gpu/drm/i915/display/intel_dp_link_training.c b/drivers/gpu/drm/i915/display/intel_dp_link_training.c index 5e9c3c74310c..597634e4f35f 100644 --- a/drivers/gpu/drm/i915/display/intel_dp_link_training.c +++ b/drivers/gpu/drm/i915/display/intel_dp_link_training.c @@ -96,7 +96,7 @@ static bool intel_dp_read_lttpr_common_caps(struct intel_dp *intel_dp) * Detecting LTTPRs must be avoided on platforms with an AUX timeout * period < 3.2ms. (see DP Standard v2.0, 2.11.2, 3.6.6.1). */ - if (DISPLAY_VER(i915) < 10) + if (DISPLAY_VER(i915) < 10 || IS_GEMINILAKE(i915)) return false; if (drm_dp_read_lttpr_common_caps(&intel_dp->aux, diff --git a/drivers/gpu/drm/i915/display/intel_fbc.c b/drivers/gpu/drm/i915/display/intel_fbc.c index 986bbbe3b12f..957252b695d7 100644 --- a/drivers/gpu/drm/i915/display/intel_fbc.c +++ b/drivers/gpu/drm/i915/display/intel_fbc.c @@ -597,7 +597,7 @@ static bool stride_is_valid(struct drm_i915_private *dev_priv, return false; /* Display WA #1105: skl,bxt,kbl,cfl,glk */ - if (IS_DISPLAY_VER(dev_priv, 9) && + if ((IS_DISPLAY_VER(dev_priv, 9) || IS_GEMINILAKE(dev_priv)) && modifier == DRM_FORMAT_MOD_LINEAR && stride & 511) return false; diff --git a/drivers/gpu/drm/i915/display/intel_overlay.c b/drivers/gpu/drm/i915/display/intel_overlay.c index e477b6114a60..e5dadde422f7 100644 --- a/drivers/gpu/drm/i915/display/intel_overlay.c +++ b/drivers/gpu/drm/i915/display/intel_overlay.c @@ -803,8 +803,10 @@ static int intel_overlay_do_put_image(struct intel_overlay *overlay, atomic_inc(&dev_priv->gpu_error.pending_fb_pin); vma = intel_overlay_pin_fb(new_bo); - if (IS_ERR(vma)) + if (IS_ERR(vma)) { + ret = PTR_ERR(vma); goto out_pin_section; + } i915_gem_object_flush_frontbuffer(new_bo, ORIGIN_DIRTYFB); diff --git a/drivers/gpu/drm/i915/display/intel_psr.c b/drivers/gpu/drm/i915/display/intel_psr.c index 1d561812fcad..8ada4f829cab 100644 --- a/drivers/gpu/drm/i915/display/intel_psr.c +++ b/drivers/gpu/drm/i915/display/intel_psr.c @@ -1519,8 +1519,7 @@ void intel_psr_wait_for_idle(const struct intel_crtc_state *new_crtc_state) u32 psr_status; mutex_lock(&intel_dp->psr.lock); - if (!intel_dp->psr.enabled || - (intel_dp->psr.enabled && intel_dp->psr.psr2_enabled)) { + if (!intel_dp->psr.enabled || intel_dp->psr.psr2_enabled) { mutex_unlock(&intel_dp->psr.lock); continue; } diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c b/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c index 3e248d3bd869..4f9c8d3021ab 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c @@ -70,6 +70,7 @@ static void try_to_writeback(struct drm_i915_gem_object *obj, /** * i915_gem_shrink - Shrink buffer object caches + * @ww: i915 gem ww acquire ctx, or NULL * @i915: i915 device * @target: amount of memory to make available, in pages * @nr_scanned: optional output for number of pages scanned (incremental) diff --git a/drivers/gpu/drm/i915/gvt/cmd_parser.c b/drivers/gpu/drm/i915/gvt/cmd_parser.c index fef1e857cefc..42c967dd8c60 100644 --- a/drivers/gpu/drm/i915/gvt/cmd_parser.c +++ b/drivers/gpu/drm/i915/gvt/cmd_parser.c @@ -941,11 +941,6 @@ static int cmd_reg_handler(struct parser_exec_state *s, /* below are all lri handlers */ vreg = &vgpu_vreg(s->vgpu, offset); - if (!intel_gvt_mmio_is_cmd_accessible(gvt, offset)) { - gvt_vgpu_err("%s access to non-render register (%x)\n", - cmd, offset); - return -EBADRQC; - } if (is_cmd_update_pdps(offset, s) && cmd_pdp_mmio_update_handler(s, offset, index)) diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c index 67a26923aa0e..9478c132d7b6 100644 --- a/drivers/gpu/drm/i915/gvt/gtt.c +++ b/drivers/gpu/drm/i915/gvt/gtt.c @@ -587,12 +587,6 @@ static void _ppgtt_set_root_entry(struct intel_vgpu_mm *mm, entry, index, false, 0, mm->vgpu); } -static inline void ppgtt_set_guest_root_entry(struct intel_vgpu_mm *mm, - struct intel_gvt_gtt_entry *entry, unsigned long index) -{ - _ppgtt_set_root_entry(mm, entry, index, true); -} - static inline void ppgtt_set_shadow_root_entry(struct intel_vgpu_mm *mm, struct intel_gvt_gtt_entry *entry, unsigned long index) { diff --git a/drivers/gpu/drm/i915/gvt/gvt.c b/drivers/gpu/drm/i915/gvt/gvt.c index 2ecb8534930b..1deb253ffe80 100644 --- a/drivers/gpu/drm/i915/gvt/gvt.c +++ b/drivers/gpu/drm/i915/gvt/gvt.c @@ -126,7 +126,7 @@ static bool intel_get_gvt_attrs(struct attribute_group ***intel_vgpu_type_groups return true; } -static bool intel_gvt_init_vgpu_type_groups(struct intel_gvt *gvt) +static int intel_gvt_init_vgpu_type_groups(struct intel_gvt *gvt) { int i, j; struct intel_vgpu_type *type; @@ -144,7 +144,7 @@ static bool intel_gvt_init_vgpu_type_groups(struct intel_gvt *gvt) gvt_vgpu_type_groups[i] = group; } - return true; + return 0; unwind: for (j = 0; j < i; j++) { @@ -152,7 +152,7 @@ unwind: kfree(group); } - return false; + return -ENOMEM; } static void intel_gvt_cleanup_vgpu_type_groups(struct intel_gvt *gvt) @@ -373,7 +373,7 @@ int intel_gvt_init_device(struct drm_i915_private *i915) goto out_clean_thread; ret = intel_gvt_init_vgpu_type_groups(gvt); - if (ret == false) { + if (ret) { gvt_err("failed to init vgpu type groups: %d\n", ret); goto out_clean_types; } diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c index 477badfcb258..dda320749c65 100644 --- a/drivers/gpu/drm/i915/gvt/handlers.c +++ b/drivers/gpu/drm/i915/gvt/handlers.c @@ -669,8 +669,8 @@ static void vgpu_update_refresh_rate(struct intel_vgpu *vgpu) link_n = vgpu_vreg_t(vgpu, PIPE_LINK_N1(TRANSCODER_A)); /* Get H/V total from transcoder timing */ - htotal = (vgpu_vreg_t(vgpu, HTOTAL(TRANSCODER_A)) >> TRANS_HTOTAL_SHIFT) + 1; - vtotal = (vgpu_vreg_t(vgpu, VTOTAL(TRANSCODER_A)) >> TRANS_VTOTAL_SHIFT) + 1; + htotal = (vgpu_vreg_t(vgpu, HTOTAL(TRANSCODER_A)) >> TRANS_HTOTAL_SHIFT); + vtotal = (vgpu_vreg_t(vgpu, VTOTAL(TRANSCODER_A)) >> TRANS_VTOTAL_SHIFT); if (dp_br && link_n && htotal && vtotal) { u64 pixel_clk = 0; @@ -682,7 +682,7 @@ static void vgpu_update_refresh_rate(struct intel_vgpu *vgpu) pixel_clk *= MSEC_PER_SEC; /* Calcuate refresh rate by (pixel_clk / (h_total * v_total)) */ - new_rate = DIV64_U64_ROUND_CLOSEST(pixel_clk, div64_u64(mul_u32_u32(htotal, vtotal), MSEC_PER_SEC)); + new_rate = DIV64_U64_ROUND_CLOSEST(mul_u64_u32_shr(pixel_clk, MSEC_PER_SEC, 0), mul_u32_u32(htotal + 1, vtotal + 1)); if (*old_rate != new_rate) *old_rate = new_rate; diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c index 9165971c3c47..bec9c3652188 100644 --- a/drivers/gpu/drm/i915/i915_request.c +++ b/drivers/gpu/drm/i915/i915_request.c @@ -350,6 +350,8 @@ static void __rq_arm_watchdog(struct i915_request *rq) if (!ce->watchdog.timeout_us) return; + i915_request_get(rq); + hrtimer_init(&wdg->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); wdg->timer.function = __rq_watchdog_expired; hrtimer_start_range_ns(&wdg->timer, @@ -357,7 +359,6 @@ static void __rq_arm_watchdog(struct i915_request *rq) NSEC_PER_USEC), NSEC_PER_MSEC, HRTIMER_MODE_REL); - i915_request_get(rq); } static void __rq_cancel_watchdog(struct i915_request *rq) diff --git a/drivers/gpu/drm/imx/imx-drm-core.c b/drivers/gpu/drm/imx/imx-drm-core.c index d1a9841adeed..e6a88c8cbd69 100644 --- a/drivers/gpu/drm/imx/imx-drm-core.c +++ b/drivers/gpu/drm/imx/imx-drm-core.c @@ -215,7 +215,7 @@ static int imx_drm_bind(struct device *dev) ret = drmm_mode_config_init(drm); if (ret) - return ret; + goto err_kms; ret = drm_vblank_init(drm, MAX_CRTC); if (ret) diff --git a/drivers/gpu/drm/imx/imx-ldb.c b/drivers/gpu/drm/imx/imx-ldb.c index dbfe39e2f7f6..ffdc492c5bc5 100644 --- a/drivers/gpu/drm/imx/imx-ldb.c +++ b/drivers/gpu/drm/imx/imx-ldb.c @@ -197,6 +197,11 @@ static void imx_ldb_encoder_enable(struct drm_encoder *encoder) int dual = ldb->ldb_ctrl & LDB_SPLIT_MODE_EN; int mux = drm_of_encoder_active_port_id(imx_ldb_ch->child, encoder); + if (mux < 0 || mux >= ARRAY_SIZE(ldb->clk_sel)) { + dev_warn(ldb->dev, "%s: invalid mux %d\n", __func__, mux); + return; + } + drm_panel_prepare(imx_ldb_ch->panel); if (dual) { @@ -255,6 +260,11 @@ imx_ldb_encoder_atomic_mode_set(struct drm_encoder *encoder, int mux = drm_of_encoder_active_port_id(imx_ldb_ch->child, encoder); u32 bus_format = imx_ldb_ch->bus_format; + if (mux < 0 || mux >= ARRAY_SIZE(ldb->clk_sel)) { + dev_warn(ldb->dev, "%s: invalid mux %d\n", __func__, mux); + return; + } + if (mode->clock > 170000) { dev_warn(ldb->dev, "%s: mode exceeds 170 MHz pixel clock\n", __func__); @@ -583,7 +593,7 @@ static int imx_ldb_bind(struct device *dev, struct device *master, void *data) struct imx_ldb_channel *channel = &imx_ldb->channel[i]; if (!channel->ldb) - break; + continue; ret = imx_ldb_register(drm, channel); if (ret) diff --git a/drivers/gpu/drm/msm/Kconfig b/drivers/gpu/drm/msm/Kconfig index dabb4a1ccdcf..10f693ea89d3 100644 --- a/drivers/gpu/drm/msm/Kconfig +++ b/drivers/gpu/drm/msm/Kconfig @@ -20,6 +20,7 @@ config DRM_MSM select SND_SOC_HDMI_CODEC if SND_SOC select SYNC_FILE select PM_OPP + select NVMEM help DRM/KMS driver for MSM/snapdragon. @@ -76,14 +77,6 @@ config DRM_MSM_DSI Choose this option if you have a need for MIPI DSI connector support. -config DRM_MSM_DSI_PLL - bool "Enable DSI PLL driver in MSM DRM" - depends on DRM_MSM_DSI && COMMON_CLK - default y - help - Choose this option to enable DSI PLL driver which provides DSI - source clocks under common clock framework. - config DRM_MSM_DSI_28NM_PHY bool "Enable DSI 28nm PHY driver in MSM DRM" depends on DRM_MSM_DSI diff --git a/drivers/gpu/drm/msm/Makefile b/drivers/gpu/drm/msm/Makefile index 3cc906121fb3..610d630326bb 100644 --- a/drivers/gpu/drm/msm/Makefile +++ b/drivers/gpu/drm/msm/Makefile @@ -136,13 +136,4 @@ msm-$(CONFIG_DRM_MSM_DSI_14NM_PHY) += dsi/phy/dsi_phy_14nm.o msm-$(CONFIG_DRM_MSM_DSI_10NM_PHY) += dsi/phy/dsi_phy_10nm.o msm-$(CONFIG_DRM_MSM_DSI_7NM_PHY) += dsi/phy/dsi_phy_7nm.o -ifeq ($(CONFIG_DRM_MSM_DSI_PLL),y) -msm-y += dsi/pll/dsi_pll.o -msm-$(CONFIG_DRM_MSM_DSI_28NM_PHY) += dsi/pll/dsi_pll_28nm.o -msm-$(CONFIG_DRM_MSM_DSI_28NM_8960_PHY) += dsi/pll/dsi_pll_28nm_8960.o -msm-$(CONFIG_DRM_MSM_DSI_14NM_PHY) += dsi/pll/dsi_pll_14nm.o -msm-$(CONFIG_DRM_MSM_DSI_10NM_PHY) += dsi/pll/dsi_pll_10nm.o -msm-$(CONFIG_DRM_MSM_DSI_7NM_PHY) += dsi/pll/dsi_pll_7nm.o -endif - obj-$(CONFIG_DRM_MSM) += msm.o diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c index 7e553d3efeb2..ce13d49e615b 100644 --- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c @@ -1386,8 +1386,8 @@ static int a5xx_pm_suspend(struct msm_gpu *gpu) static int a5xx_get_timestamp(struct msm_gpu *gpu, uint64_t *value) { - *value = gpu_read64(gpu, REG_A5XX_RBBM_PERFCTR_CP_0_LO, - REG_A5XX_RBBM_PERFCTR_CP_0_HI); + *value = gpu_read64(gpu, REG_A5XX_RBBM_ALWAYSON_COUNTER_LO, + REG_A5XX_RBBM_ALWAYSON_COUNTER_HI); return 0; } diff --git a/drivers/gpu/drm/msm/adreno/a5xx_power.c b/drivers/gpu/drm/msm/adreno/a5xx_power.c index 5ccc9da455a1..c35b06b46fcc 100644 --- a/drivers/gpu/drm/msm/adreno/a5xx_power.c +++ b/drivers/gpu/drm/msm/adreno/a5xx_power.c @@ -304,7 +304,7 @@ int a5xx_power_init(struct msm_gpu *gpu) /* Set up the limits management */ if (adreno_is_a530(adreno_gpu)) a530_lm_setup(gpu); - else + else if (adreno_is_a540(adreno_gpu)) a540_lm_setup(gpu); /* Set up SP/TP power collpase */ diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c index 71c917f909af..3d55e153fa9c 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c @@ -246,7 +246,7 @@ static int a6xx_gmu_hfi_start(struct a6xx_gmu *gmu) } struct a6xx_gmu_oob_bits { - int set, ack, set_new, ack_new; + int set, ack, set_new, ack_new, clear, clear_new; const char *name; }; @@ -260,6 +260,8 @@ static const struct a6xx_gmu_oob_bits a6xx_gmu_oob_bits[] = { .ack = 24, .set_new = 30, .ack_new = 31, + .clear = 24, + .clear_new = 31, }, [GMU_OOB_PERFCOUNTER_SET] = { @@ -268,18 +270,22 @@ static const struct a6xx_gmu_oob_bits a6xx_gmu_oob_bits[] = { .ack = 25, .set_new = 28, .ack_new = 30, + .clear = 25, + .clear_new = 29, }, [GMU_OOB_BOOT_SLUMBER] = { .name = "BOOT_SLUMBER", .set = 22, .ack = 30, + .clear = 30, }, [GMU_OOB_DCVS_SET] = { .name = "GPU_DCVS", .set = 23, .ack = 31, + .clear = 31, }, }; @@ -335,11 +341,11 @@ void a6xx_gmu_clear_oob(struct a6xx_gmu *gmu, enum a6xx_gmu_oob_state state) return; if (gmu->legacy) - bit = a6xx_gmu_oob_bits[state].ack; + bit = a6xx_gmu_oob_bits[state].clear; else - bit = a6xx_gmu_oob_bits[state].ack_new; + bit = a6xx_gmu_oob_bits[state].clear_new; - gmu_write(gmu, REG_A6XX_GMU_HOST2GMU_INTR_SET, bit); + gmu_write(gmu, REG_A6XX_GMU_HOST2GMU_INTR_SET, 1 << bit); } /* Enable CPU control of SPTP power power collapse */ diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c index ba8e9d3cf0fe..d553f62f4eeb 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c @@ -522,28 +522,73 @@ static int a6xx_cp_init(struct msm_gpu *gpu) return a6xx_idle(gpu, ring) ? 0 : -EINVAL; } -static void a6xx_ucode_check_version(struct a6xx_gpu *a6xx_gpu, +/* + * Check that the microcode version is new enough to include several key + * security fixes. Return true if the ucode is safe. + */ +static bool a6xx_ucode_check_version(struct a6xx_gpu *a6xx_gpu, struct drm_gem_object *obj) { + struct adreno_gpu *adreno_gpu = &a6xx_gpu->base; + struct msm_gpu *gpu = &adreno_gpu->base; u32 *buf = msm_gem_get_vaddr(obj); + bool ret = false; if (IS_ERR(buf)) - return; + return false; /* - * If the lowest nibble is 0xa that is an indication that this microcode - * has been patched. The actual version is in dword [3] but we only care - * about the patchlevel which is the lowest nibble of dword [3] - * - * Otherwise check that the firmware is greater than or equal to 1.90 - * which was the first version that had this fix built in + * Targets up to a640 (a618, a630 and a640) need to check for a + * microcode version that is patched to support the whereami opcode or + * one that is new enough to include it by default. */ - if (((buf[0] & 0xf) == 0xa) && (buf[2] & 0xf) >= 1) - a6xx_gpu->has_whereami = true; - else if ((buf[0] & 0xfff) > 0x190) - a6xx_gpu->has_whereami = true; + if (adreno_is_a618(adreno_gpu) || adreno_is_a630(adreno_gpu) || + adreno_is_a640(adreno_gpu)) { + /* + * If the lowest nibble is 0xa that is an indication that this + * microcode has been patched. The actual version is in dword + * [3] but we only care about the patchlevel which is the lowest + * nibble of dword [3] + * + * Otherwise check that the firmware is greater than or equal + * to 1.90 which was the first version that had this fix built + * in + */ + if ((((buf[0] & 0xf) == 0xa) && (buf[2] & 0xf) >= 1) || + (buf[0] & 0xfff) >= 0x190) { + a6xx_gpu->has_whereami = true; + ret = true; + goto out; + } + DRM_DEV_ERROR(&gpu->pdev->dev, + "a630 SQE ucode is too old. Have version %x need at least %x\n", + buf[0] & 0xfff, 0x190); + } else { + /* + * a650 tier targets don't need whereami but still need to be + * equal to or newer than 0.95 for other security fixes + */ + if (adreno_is_a650(adreno_gpu)) { + if ((buf[0] & 0xfff) >= 0x095) { + ret = true; + goto out; + } + + DRM_DEV_ERROR(&gpu->pdev->dev, + "a650 SQE ucode is too old. Have version %x need at least %x\n", + buf[0] & 0xfff, 0x095); + } + + /* + * When a660 is added those targets should return true here + * since those have all the critical security fixes built in + * from the start + */ + } +out: msm_gem_put_vaddr(obj); + return ret; } static int a6xx_ucode_init(struct msm_gpu *gpu) @@ -566,7 +611,13 @@ static int a6xx_ucode_init(struct msm_gpu *gpu) } msm_gem_object_set_name(a6xx_gpu->sqe_bo, "sqefw"); - a6xx_ucode_check_version(a6xx_gpu, a6xx_gpu->sqe_bo); + if (!a6xx_ucode_check_version(a6xx_gpu, a6xx_gpu->sqe_bo)) { + msm_gem_unpin_iova(a6xx_gpu->sqe_bo, gpu->aspace); + drm_gem_object_put(a6xx_gpu->sqe_bo); + + a6xx_gpu->sqe_bo = NULL; + return -EPERM; + } } gpu_write64(gpu, REG_A6XX_CP_SQE_INSTR_BASE_LO, @@ -1177,8 +1228,8 @@ static int a6xx_get_timestamp(struct msm_gpu *gpu, uint64_t *value) /* Force the GPU power on so we can read this register */ a6xx_gmu_set_oob(&a6xx_gpu->gmu, GMU_OOB_PERFCOUNTER_SET); - *value = gpu_read64(gpu, REG_A6XX_RBBM_PERFCTR_CP_0_LO, - REG_A6XX_RBBM_PERFCTR_CP_0_HI); + *value = gpu_read64(gpu, REG_A6XX_CP_ALWAYS_ON_COUNTER_LO, + REG_A6XX_CP_ALWAYS_ON_COUNTER_HI); a6xx_gmu_clear_oob(&a6xx_gpu->gmu, GMU_OOB_PERFCOUNTER_SET); mutex_unlock(&perfcounter_oob); @@ -1350,35 +1401,26 @@ static int a6xx_set_supported_hw(struct device *dev, struct a6xx_gpu *a6xx_gpu, u32 revn) { struct opp_table *opp_table; - struct nvmem_cell *cell; u32 supp_hw = UINT_MAX; - void *buf; + u16 speedbin; + int ret; - cell = nvmem_cell_get(dev, "speed_bin"); + ret = nvmem_cell_read_u16(dev, "speed_bin", &speedbin); /* * -ENOENT means that the platform doesn't support speedbin which is * fine */ - if (PTR_ERR(cell) == -ENOENT) + if (ret == -ENOENT) { return 0; - else if (IS_ERR(cell)) { - DRM_DEV_ERROR(dev, - "failed to read speed-bin. Some OPPs may not be supported by hardware"); - goto done; - } - - buf = nvmem_cell_read(cell, NULL); - if (IS_ERR(buf)) { - nvmem_cell_put(cell); + } else if (ret) { DRM_DEV_ERROR(dev, - "failed to read speed-bin. Some OPPs may not be supported by hardware"); + "failed to read speed-bin (%d). Some OPPs may not be supported by hardware", + ret); goto done; } + speedbin = le16_to_cpu(speedbin); - supp_hw = fuse_to_supp_hw(dev, revn, *((u32 *) buf)); - - kfree(buf); - nvmem_cell_put(cell); + supp_hw = fuse_to_supp_hw(dev, revn, speedbin); done: opp_table = dev_pm_opp_set_supported_hw(dev, &supp_hw, 1); diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c index 0f184c3dd9d9..6a35a30dd281 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c +++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c @@ -273,6 +273,9 @@ int adreno_get_param(struct msm_gpu *gpu, uint32_t param, uint64_t *value) case MSM_PARAM_FAULTS: *value = gpu->global_faults; return 0; + case MSM_PARAM_SUSPENDS: + *value = gpu->suspend_count; + return 0; default: DBG("%s: invalid param: %u", gpu->name, param); return -EINVAL; diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_irq.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_irq.c index 84ea09d9692f..cdec3fbe6ff4 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_irq.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_irq.c @@ -58,8 +58,8 @@ int dpu_core_irq_idx_lookup(struct dpu_kms *dpu_kms, if (!dpu_kms->hw_intr || !dpu_kms->hw_intr->ops.irq_idx_lookup) return -EINVAL; - return dpu_kms->hw_intr->ops.irq_idx_lookup(intr_type, - instance_idx); + return dpu_kms->hw_intr->ops.irq_idx_lookup(dpu_kms->hw_intr, + intr_type, instance_idx); } /** diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c index b6b3bbab0333..7cba5bbdf4b7 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c @@ -380,7 +380,6 @@ int dpu_core_perf_crtc_update(struct drm_crtc *crtc, } else { DPU_DEBUG("crtc=%d disable\n", crtc->base.id); memset(old, 0, sizeof(*old)); - memset(new, 0, sizeof(*new)); update_bus = true; update_clk = true; } diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c index e65ff8168269..18bc76b7f1a3 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c @@ -66,6 +66,83 @@ static void dpu_crtc_destroy(struct drm_crtc *crtc) kfree(dpu_crtc); } +static struct drm_encoder *get_encoder_from_crtc(struct drm_crtc *crtc) +{ + struct drm_device *dev = crtc->dev; + struct drm_encoder *encoder; + + drm_for_each_encoder(encoder, dev) + if (encoder->crtc == crtc) + return encoder; + + return NULL; +} + +static u32 dpu_crtc_get_vblank_counter(struct drm_crtc *crtc) +{ + struct drm_encoder *encoder; + + encoder = get_encoder_from_crtc(crtc); + if (!encoder) { + DRM_ERROR("no encoder found for crtc %d\n", crtc->index); + return false; + } + + return dpu_encoder_get_frame_count(encoder); +} + +static bool dpu_crtc_get_scanout_position(struct drm_crtc *crtc, + bool in_vblank_irq, + int *vpos, int *hpos, + ktime_t *stime, ktime_t *etime, + const struct drm_display_mode *mode) +{ + unsigned int pipe = crtc->index; + struct drm_encoder *encoder; + int line, vsw, vbp, vactive_start, vactive_end, vfp_end; + + encoder = get_encoder_from_crtc(crtc); + if (!encoder) { + DRM_ERROR("no encoder found for crtc %d\n", pipe); + return false; + } + + vsw = mode->crtc_vsync_end - mode->crtc_vsync_start; + vbp = mode->crtc_vtotal - mode->crtc_vsync_end; + + /* + * the line counter is 1 at the start of the VSYNC pulse and VTOTAL at + * the end of VFP. Translate the porch values relative to the line + * counter positions. + */ + + vactive_start = vsw + vbp + 1; + vactive_end = vactive_start + mode->crtc_vdisplay; + + /* last scan line before VSYNC */ + vfp_end = mode->crtc_vtotal; + + if (stime) + *stime = ktime_get(); + + line = dpu_encoder_get_linecount(encoder); + + if (line < vactive_start) + line -= vactive_start; + else if (line > vactive_end) + line = line - vfp_end - vactive_start; + else + line -= vactive_start; + + *vpos = line; + *hpos = 0; + + if (etime) + *etime = ktime_get(); + + return true; +} + static void _dpu_crtc_setup_blend_cfg(struct dpu_crtc_mixer *mixer, struct dpu_plane_state *pstate, struct dpu_format *format) { @@ -130,7 +207,9 @@ static void _dpu_crtc_blend_setup_mixer(struct drm_crtc *crtc, uint32_t stage_idx, lm_idx; int zpos_cnt[DPU_STAGE_MAX + 1] = { 0 }; bool bg_alpha_enable = false; + DECLARE_BITMAP(fetch_active, SSPP_MAX); + memset(fetch_active, 0, sizeof(fetch_active)); drm_atomic_crtc_for_each_plane(plane, crtc) { state = plane->state; if (!state) @@ -140,7 +219,7 @@ static void _dpu_crtc_blend_setup_mixer(struct drm_crtc *crtc, fb = state->fb; dpu_plane_get_ctl_flush(plane, ctl, &flush_mask); - + set_bit(dpu_plane_pipe(plane), fetch_active); DPU_DEBUG("crtc %d stage:%d - plane %d sspp %d fb %d\n", crtc->base.id, pstate->stage, @@ -180,6 +259,9 @@ static void _dpu_crtc_blend_setup_mixer(struct drm_crtc *crtc, } } + if (ctl->ops.set_active_pipes) + ctl->ops.set_active_pipes(ctl, fetch_active); + _dpu_crtc_program_lm_output_roi(crtc); } @@ -829,6 +911,7 @@ static int dpu_crtc_atomic_check(struct drm_crtc *crtc, DPU_DEBUG("crtc%d -> enable %d, active %d, skip atomic_check\n", crtc->base.id, crtc_state->enable, crtc_state->active); + memset(&cstate->new_perf, 0, sizeof(cstate->new_perf)); goto end; } @@ -1237,6 +1320,8 @@ static const struct drm_crtc_funcs dpu_crtc_funcs = { .early_unregister = dpu_crtc_early_unregister, .enable_vblank = msm_crtc_enable_vblank, .disable_vblank = msm_crtc_disable_vblank, + .get_vblank_timestamp = drm_crtc_vblank_helper_get_vblank_timestamp, + .get_vblank_counter = dpu_crtc_get_vblank_counter, }; static const struct drm_crtc_helper_funcs dpu_crtc_helper_funcs = { @@ -1245,6 +1330,7 @@ static const struct drm_crtc_helper_funcs dpu_crtc_helper_funcs = { .atomic_check = dpu_crtc_atomic_check, .atomic_begin = dpu_crtc_atomic_begin, .atomic_flush = dpu_crtc_atomic_flush, + .get_scanout_position = dpu_crtc_get_scanout_position, }; /* initialize crtc */ diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c index 288e95ee8e1d..8d942052db8a 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c @@ -426,6 +426,36 @@ int dpu_encoder_helper_unregister_irq(struct dpu_encoder_phys *phys_enc, return 0; } +int dpu_encoder_get_frame_count(struct drm_encoder *drm_enc) +{ + struct dpu_encoder_virt *dpu_enc; + struct dpu_encoder_phys *phys; + int framecount = 0; + + dpu_enc = to_dpu_encoder_virt(drm_enc); + phys = dpu_enc ? dpu_enc->cur_master : NULL; + + if (phys && phys->ops.get_frame_count) + framecount = phys->ops.get_frame_count(phys); + + return framecount; +} + +int dpu_encoder_get_linecount(struct drm_encoder *drm_enc) +{ + struct dpu_encoder_virt *dpu_enc; + struct dpu_encoder_phys *phys; + int linecount = 0; + + dpu_enc = to_dpu_encoder_virt(drm_enc); + phys = dpu_enc ? dpu_enc->cur_master : NULL; + + if (phys && phys->ops.get_line_count) + linecount = phys->ops.get_line_count(phys); + + return linecount; +} + void dpu_encoder_get_hw_resources(struct drm_encoder *drm_enc, struct dpu_encoder_hw_resources *hw_res) { diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.h index b4913465e602..99a5d73c9b88 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.h @@ -156,5 +156,16 @@ void dpu_encoder_prepare_commit(struct drm_encoder *drm_enc); */ void dpu_encoder_set_idle_timeout(struct drm_encoder *drm_enc, u32 idle_timeout); +/** + * dpu_encoder_get_linecount - get interface line count for the encoder. + * @drm_enc: Pointer to previously created drm encoder structure + */ +int dpu_encoder_get_linecount(struct drm_encoder *drm_enc); + +/** + * dpu_encoder_get_frame_count - get interface frame count for the encoder. + * @drm_enc: Pointer to previously created drm encoder structure + */ +int dpu_encoder_get_frame_count(struct drm_encoder *drm_enc); #endif /* __DPU_ENCODER_H__ */ diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys.h index f8f25157f635..ecbc4be98980 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys.h @@ -143,6 +143,7 @@ struct dpu_encoder_phys_ops { void (*prepare_idle_pc)(struct dpu_encoder_phys *phys_enc); void (*restore)(struct dpu_encoder_phys *phys); int (*get_line_count)(struct dpu_encoder_phys *phys); + int (*get_frame_count)(struct dpu_encoder_phys *phys); }; /** diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c index 9a69fad832cd..0e06b7e73c7a 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c @@ -658,6 +658,31 @@ static int dpu_encoder_phys_vid_get_line_count( return phys_enc->hw_intf->ops.get_line_count(phys_enc->hw_intf); } +static int dpu_encoder_phys_vid_get_frame_count( + struct dpu_encoder_phys *phys_enc) +{ + struct intf_status s = {0}; + u32 fetch_start = 0; + struct drm_display_mode mode = phys_enc->cached_mode; + + if (!dpu_encoder_phys_vid_is_master(phys_enc)) + return -EINVAL; + + if (!phys_enc->hw_intf || !phys_enc->hw_intf->ops.get_status) + return -EINVAL; + + phys_enc->hw_intf->ops.get_status(phys_enc->hw_intf, &s); + + if (s.is_prog_fetch_en && s.is_en) { + fetch_start = mode.vtotal - (mode.vsync_start - mode.vdisplay); + if ((s.line_count > fetch_start) && + (s.line_count <= mode.vtotal)) + return s.frame_count + 1; + } + + return s.frame_count; +} + static void dpu_encoder_phys_vid_init_ops(struct dpu_encoder_phys_ops *ops) { ops->is_master = dpu_encoder_phys_vid_is_master; @@ -676,6 +701,7 @@ static void dpu_encoder_phys_vid_init_ops(struct dpu_encoder_phys_ops *ops) ops->handle_post_kickoff = dpu_encoder_phys_vid_handle_post_kickoff; ops->needs_single_flush = dpu_encoder_phys_vid_needs_single_flush; ops->get_line_count = dpu_encoder_phys_vid_get_line_count; + ops->get_frame_count = dpu_encoder_phys_vid_get_frame_count; } struct dpu_encoder_phys *dpu_encoder_phys_vid_init( diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c index 189f3533525c..b569030a0847 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c @@ -22,7 +22,7 @@ (VIG_MASK | BIT(DPU_SSPP_QOS_8LVL) | BIT(DPU_SSPP_SCALER_QSEED4)) #define VIG_SM8250_MASK \ - (VIG_MASK | BIT(DPU_SSPP_SCALER_QSEED3LITE)) + (VIG_MASK | BIT(DPU_SSPP_QOS_8LVL) | BIT(DPU_SSPP_SCALER_QSEED3LITE)) #define DMA_SDM845_MASK \ (BIT(DPU_SSPP_SRC) | BIT(DPU_SSPP_QOS) | BIT(DPU_SSPP_QOS_8LVL) |\ @@ -43,6 +43,9 @@ #define PINGPONG_SDM845_SPLIT_MASK \ (PINGPONG_SDM845_MASK | BIT(DPU_PINGPONG_TE2)) +#define CTL_SC7280_MASK \ + (BIT(DPU_CTL_ACTIVE_CFG) | BIT(DPU_CTL_FETCH_ACTIVE)) + #define MERGE_3D_SM8150_MASK (0) #define DSPP_SC7180_MASK BIT(DPU_DSPP_PCC) @@ -51,6 +54,15 @@ #define INTF_SC7180_MASK BIT(DPU_INTF_INPUT_CTRL) | BIT(DPU_INTF_TE) +#define INTF_SC7280_MASK INTF_SC7180_MASK | BIT(DPU_DATA_HCTL_EN) + +#define INTR_SC7180_MASK \ + (BIT(DPU_IRQ_TYPE_PING_PONG_RD_PTR) |\ + BIT(DPU_IRQ_TYPE_PING_PONG_WR_PTR) |\ + BIT(DPU_IRQ_TYPE_PING_PONG_AUTO_REF) |\ + BIT(DPU_IRQ_TYPE_PING_PONG_TEAR_CHECK) |\ + BIT(DPU_IRQ_TYPE_PING_PONG_TE_CHECK)) + #define DEFAULT_PIXEL_RAM_SIZE (50 * 1024) #define DEFAULT_DPU_LINE_WIDTH 2048 #define DEFAULT_DPU_OUTPUT_LINE_WIDTH 2560 @@ -199,6 +211,18 @@ static const struct dpu_caps sm8250_dpu_caps = { .pixel_ram_size = DEFAULT_PIXEL_RAM_SIZE, }; +static const struct dpu_caps sc7280_dpu_caps = { + .max_mixer_width = DEFAULT_DPU_OUTPUT_LINE_WIDTH, + .max_mixer_blendstages = 0x7, + .qseed_type = DPU_SSPP_SCALER_QSEED4, + .smart_dma_rev = DPU_SSPP_SMART_DMA_V2, + .ubwc_version = DPU_HW_UBWC_VER_30, + .has_dim_layer = true, + .has_idle_pc = true, + .max_linewidth = 2400, + .pixel_ram_size = DEFAULT_PIXEL_RAM_SIZE, +}; + static const struct dpu_mdp_cfg sdm845_mdp[] = { { .name = "top_0", .id = MDP_TOP, @@ -268,6 +292,22 @@ static const struct dpu_mdp_cfg sm8250_mdp[] = { }, }; +static const struct dpu_mdp_cfg sc7280_mdp[] = { + { + .name = "top_0", .id = MDP_TOP, + .base = 0x0, .len = 0x2014, + .highest_bank_bit = 0x1, + .clk_ctrls[DPU_CLK_CTRL_VIG0] = { + .reg_off = 0x2AC, .bit_off = 0}, + .clk_ctrls[DPU_CLK_CTRL_DMA0] = { + .reg_off = 0x2AC, .bit_off = 8}, + .clk_ctrls[DPU_CLK_CTRL_CURSOR0] = { + .reg_off = 0x2B4, .bit_off = 8}, + .clk_ctrls[DPU_CLK_CTRL_CURSOR1] = { + .reg_off = 0x2C4, .bit_off = 8}, + }, +}; + /************************************************************* * CTL sub blocks config *************************************************************/ @@ -350,6 +390,29 @@ static const struct dpu_ctl_cfg sm8150_ctl[] = { }, }; +static const struct dpu_ctl_cfg sc7280_ctl[] = { + { + .name = "ctl_0", .id = CTL_0, + .base = 0x15000, .len = 0x1E8, + .features = CTL_SC7280_MASK + }, + { + .name = "ctl_1", .id = CTL_1, + .base = 0x16000, .len = 0x1E8, + .features = CTL_SC7280_MASK + }, + { + .name = "ctl_2", .id = CTL_2, + .base = 0x17000, .len = 0x1E8, + .features = CTL_SC7280_MASK + }, + { + .name = "ctl_3", .id = CTL_3, + .base = 0x18000, .len = 0x1E8, + .features = CTL_SC7280_MASK + }, +}; + /************************************************************* * SSPP sub blocks config *************************************************************/ @@ -475,6 +538,17 @@ static const struct dpu_sspp_cfg sm8250_sspp[] = { sdm845_dma_sblk_3, 13, SSPP_TYPE_DMA, DPU_CLK_CTRL_CURSOR1), }; +static const struct dpu_sspp_cfg sc7280_sspp[] = { + SSPP_BLK("sspp_0", SSPP_VIG0, 0x4000, VIG_SC7180_MASK, + sc7180_vig_sblk_0, 0, SSPP_TYPE_VIG, DPU_CLK_CTRL_VIG0), + SSPP_BLK("sspp_8", SSPP_DMA0, 0x24000, DMA_SDM845_MASK, + sdm845_dma_sblk_0, 1, SSPP_TYPE_DMA, DPU_CLK_CTRL_DMA0), + SSPP_BLK("sspp_9", SSPP_DMA1, 0x26000, DMA_CURSOR_SDM845_MASK, + sdm845_dma_sblk_1, 5, SSPP_TYPE_DMA, DPU_CLK_CTRL_CURSOR0), + SSPP_BLK("sspp_10", SSPP_DMA2, 0x28000, DMA_CURSOR_SDM845_MASK, + sdm845_dma_sblk_2, 9, SSPP_TYPE_DMA, DPU_CLK_CTRL_CURSOR1), +}; + /************************************************************* * MIXER sub blocks config *************************************************************/ @@ -550,6 +624,15 @@ static const struct dpu_lm_cfg sm8150_lm[] = { &sdm845_lm_sblk, PINGPONG_5, LM_4, 0), }; +static const struct dpu_lm_cfg sc7280_lm[] = { + LM_BLK("lm_0", LM_0, 0x44000, MIXER_SC7180_MASK, + &sc7180_lm_sblk, PINGPONG_0, 0, 0), + LM_BLK("lm_2", LM_2, 0x46000, MIXER_SC7180_MASK, + &sc7180_lm_sblk, PINGPONG_2, LM_3, 0), + LM_BLK("lm_3", LM_3, 0x47000, MIXER_SC7180_MASK, + &sc7180_lm_sblk, PINGPONG_3, LM_2, 0), +}; + /************************************************************* * DSPP sub blocks config *************************************************************/ @@ -602,42 +685,47 @@ static const struct dpu_pingpong_sub_blks sdm845_pp_sblk = { .len = 0x20, .version = 0x10000}, }; -#define PP_BLK_TE(_name, _id, _base, _merge_3d) \ +static const struct dpu_pingpong_sub_blks sc7280_pp_sblk = { + .dither = {.id = DPU_PINGPONG_DITHER, .base = 0xe0, + .len = 0x20, .version = 0x20000}, +}; + +#define PP_BLK_TE(_name, _id, _base, _merge_3d, _sblk) \ {\ .name = _name, .id = _id, \ .base = _base, .len = 0xd4, \ .features = PINGPONG_SDM845_SPLIT_MASK, \ .merge_3d = _merge_3d, \ - .sblk = &sdm845_pp_sblk_te \ + .sblk = &_sblk \ } -#define PP_BLK(_name, _id, _base, _merge_3d) \ +#define PP_BLK(_name, _id, _base, _merge_3d, _sblk) \ {\ .name = _name, .id = _id, \ .base = _base, .len = 0xd4, \ .features = PINGPONG_SDM845_MASK, \ .merge_3d = _merge_3d, \ - .sblk = &sdm845_pp_sblk \ + .sblk = &_sblk \ } static const struct dpu_pingpong_cfg sdm845_pp[] = { - PP_BLK_TE("pingpong_0", PINGPONG_0, 0x70000, 0), - PP_BLK_TE("pingpong_1", PINGPONG_1, 0x70800, 0), - PP_BLK("pingpong_2", PINGPONG_2, 0x71000, 0), - PP_BLK("pingpong_3", PINGPONG_3, 0x71800, 0), + PP_BLK_TE("pingpong_0", PINGPONG_0, 0x70000, 0, sdm845_pp_sblk_te), + PP_BLK_TE("pingpong_1", PINGPONG_1, 0x70800, 0, sdm845_pp_sblk_te), + PP_BLK("pingpong_2", PINGPONG_2, 0x71000, 0, sdm845_pp_sblk), + PP_BLK("pingpong_3", PINGPONG_3, 0x71800, 0, sdm845_pp_sblk), }; static struct dpu_pingpong_cfg sc7180_pp[] = { - PP_BLK_TE("pingpong_0", PINGPONG_0, 0x70000, 0), - PP_BLK_TE("pingpong_1", PINGPONG_1, 0x70800, 0), + PP_BLK_TE("pingpong_0", PINGPONG_0, 0x70000, 0, sdm845_pp_sblk_te), + PP_BLK_TE("pingpong_1", PINGPONG_1, 0x70800, 0, sdm845_pp_sblk_te), }; static const struct dpu_pingpong_cfg sm8150_pp[] = { - PP_BLK_TE("pingpong_0", PINGPONG_0, 0x70000, MERGE_3D_0), - PP_BLK_TE("pingpong_1", PINGPONG_1, 0x70800, MERGE_3D_0), - PP_BLK("pingpong_2", PINGPONG_2, 0x71000, MERGE_3D_1), - PP_BLK("pingpong_3", PINGPONG_3, 0x71800, MERGE_3D_1), - PP_BLK("pingpong_4", PINGPONG_4, 0x72000, MERGE_3D_2), - PP_BLK("pingpong_5", PINGPONG_5, 0x72800, MERGE_3D_2), + PP_BLK_TE("pingpong_0", PINGPONG_0, 0x70000, MERGE_3D_0, sdm845_pp_sblk_te), + PP_BLK_TE("pingpong_1", PINGPONG_1, 0x70800, MERGE_3D_0, sdm845_pp_sblk_te), + PP_BLK("pingpong_2", PINGPONG_2, 0x71000, MERGE_3D_1, sdm845_pp_sblk), + PP_BLK("pingpong_3", PINGPONG_3, 0x71800, MERGE_3D_1, sdm845_pp_sblk), + PP_BLK("pingpong_4", PINGPONG_4, 0x72000, MERGE_3D_2, sdm845_pp_sblk), + PP_BLK("pingpong_5", PINGPONG_5, 0x72800, MERGE_3D_2, sdm845_pp_sblk), }; /************************************************************* @@ -657,6 +745,12 @@ static const struct dpu_merge_3d_cfg sm8150_merge_3d[] = { MERGE_3D_BLK("merge_3d_2", MERGE_3D_2, 0x83200), }; +static const struct dpu_pingpong_cfg sc7280_pp[] = { + PP_BLK("pingpong_0", PINGPONG_0, 0x59000, 0, sc7280_pp_sblk), + PP_BLK("pingpong_1", PINGPONG_1, 0x6a000, 0, sc7280_pp_sblk), + PP_BLK("pingpong_2", PINGPONG_2, 0x6b000, 0, sc7280_pp_sblk), + PP_BLK("pingpong_3", PINGPONG_3, 0x6c000, 0, sc7280_pp_sblk), +}; /************************************************************* * INTF sub blocks config *************************************************************/ @@ -689,6 +783,12 @@ static const struct dpu_intf_cfg sm8150_intf[] = { INTF_BLK("intf_3", INTF_3, 0x6B800, INTF_DP, 1, 24, INTF_SC7180_MASK), }; +static const struct dpu_intf_cfg sc7280_intf[] = { + INTF_BLK("intf_0", INTF_0, 0x34000, INTF_DP, 0, 24, INTF_SC7280_MASK), + INTF_BLK("intf_1", INTF_1, 0x35000, INTF_DSI, 0, 24, INTF_SC7280_MASK), + INTF_BLK("intf_5", INTF_5, 0x39000, INTF_EDP, 0, 24, INTF_SC7280_MASK), +}; + /************************************************************* * VBIF sub blocks config *************************************************************/ @@ -817,6 +917,8 @@ static const struct dpu_perf_cfg sdm845_perf_data = { {.rd_enable = 1, .wr_enable = 1}, {.rd_enable = 1, .wr_enable = 0} }, + .clk_inefficiency_factor = 105, + .bw_inefficiency_factor = 120, }; static const struct dpu_perf_cfg sc7180_perf_data = { @@ -852,6 +954,7 @@ static const struct dpu_perf_cfg sm8150_perf_data = { .min_core_ib = 2400000, .min_llcc_ib = 800000, .min_dram_ib = 800000, + .min_prefill_lines = 24, .danger_lut_tbl = {0xf, 0xffff, 0x0}, .qos_lut_tbl = { {.nentry = ARRAY_SIZE(sm8150_qos_linear), @@ -869,6 +972,8 @@ static const struct dpu_perf_cfg sm8150_perf_data = { {.rd_enable = 1, .wr_enable = 1}, {.rd_enable = 1, .wr_enable = 0} }, + .clk_inefficiency_factor = 105, + .bw_inefficiency_factor = 120, }; static const struct dpu_perf_cfg sm8250_perf_data = { @@ -877,6 +982,7 @@ static const struct dpu_perf_cfg sm8250_perf_data = { .min_core_ib = 4800000, .min_llcc_ib = 0, .min_dram_ib = 800000, + .min_prefill_lines = 35, .danger_lut_tbl = {0xf, 0xffff, 0x0}, .qos_lut_tbl = { {.nentry = ARRAY_SIZE(sc7180_qos_linear), @@ -894,6 +1000,35 @@ static const struct dpu_perf_cfg sm8250_perf_data = { {.rd_enable = 1, .wr_enable = 1}, {.rd_enable = 1, .wr_enable = 0} }, + .clk_inefficiency_factor = 105, + .bw_inefficiency_factor = 120, +}; + +static const struct dpu_perf_cfg sc7280_perf_data = { + .max_bw_low = 4700000, + .max_bw_high = 8800000, + .min_core_ib = 2500000, + .min_llcc_ib = 0, + .min_dram_ib = 1600000, + .min_prefill_lines = 24, + .danger_lut_tbl = {0xffff, 0xffff, 0x0}, + .qos_lut_tbl = { + {.nentry = ARRAY_SIZE(sc7180_qos_macrotile), + .entries = sc7180_qos_macrotile + }, + {.nentry = ARRAY_SIZE(sc7180_qos_macrotile), + .entries = sc7180_qos_macrotile + }, + {.nentry = ARRAY_SIZE(sc7180_qos_nrt), + .entries = sc7180_qos_nrt + }, + }, + .cdp_cfg = { + {.rd_enable = 1, .wr_enable = 1}, + {.rd_enable = 1, .wr_enable = 0} + }, + .clk_inefficiency_factor = 105, + .bw_inefficiency_factor = 120, }; /************************************************************* @@ -957,6 +1092,7 @@ static void sc7180_cfg_init(struct dpu_mdss_cfg *dpu_cfg) .dma_cfg = sdm845_regdma, .perf = sc7180_perf_data, .mdss_irqs = 0x3f, + .obsolete_irq = INTR_SC7180_MASK, }; } @@ -1026,6 +1162,30 @@ static void sm8250_cfg_init(struct dpu_mdss_cfg *dpu_cfg) }; } +static void sc7280_cfg_init(struct dpu_mdss_cfg *dpu_cfg) +{ + *dpu_cfg = (struct dpu_mdss_cfg){ + .caps = &sc7280_dpu_caps, + .mdp_count = ARRAY_SIZE(sc7280_mdp), + .mdp = sc7280_mdp, + .ctl_count = ARRAY_SIZE(sc7280_ctl), + .ctl = sc7280_ctl, + .sspp_count = ARRAY_SIZE(sc7280_sspp), + .sspp = sc7280_sspp, + .mixer_count = ARRAY_SIZE(sc7280_lm), + .mixer = sc7280_lm, + .pingpong_count = ARRAY_SIZE(sc7280_pp), + .pingpong = sc7280_pp, + .intf_count = ARRAY_SIZE(sc7280_intf), + .intf = sc7280_intf, + .vbif_count = ARRAY_SIZE(sdm845_vbif), + .vbif = sdm845_vbif, + .perf = sc7280_perf_data, + .mdss_irqs = 0x1c07, + .obsolete_irq = INTR_SC7180_MASK, + }; +} + static const struct dpu_mdss_hw_cfg_handler cfg_handler[] = { { .hw_rev = DPU_HW_VER_400, .cfg_init = sdm845_cfg_init}, { .hw_rev = DPU_HW_VER_401, .cfg_init = sdm845_cfg_init}, @@ -1033,6 +1193,7 @@ static const struct dpu_mdss_hw_cfg_handler cfg_handler[] = { { .hw_rev = DPU_HW_VER_501, .cfg_init = sm8150_cfg_init}, { .hw_rev = DPU_HW_VER_600, .cfg_init = sm8250_cfg_init}, { .hw_rev = DPU_HW_VER_620, .cfg_init = sc7180_cfg_init}, + { .hw_rev = DPU_HW_VER_720, .cfg_init = sc7280_cfg_init}, }; void dpu_hw_catalog_deinit(struct dpu_mdss_cfg *dpu_cfg) diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.h index ea4647d21a20..4dfd8a20ad5c 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.h @@ -41,7 +41,7 @@ #define DPU_HW_VER_501 DPU_HW_VER(5, 0, 1) /* sm8150 v2.0 */ #define DPU_HW_VER_600 DPU_HW_VER(6, 0, 0) /* sm8250 */ #define DPU_HW_VER_620 DPU_HW_VER(6, 2, 0) /* sc7180 v1.0 */ - +#define DPU_HW_VER_720 DPU_HW_VER(7, 2, 0) /* sc7280 */ #define IS_MSM8996_TARGET(rev) IS_DPU_MAJOR_MINOR_SAME((rev), DPU_HW_VER_170) #define IS_MSM8998_TARGET(rev) IS_DPU_MAJOR_MINOR_SAME((rev), DPU_HW_VER_300) @@ -49,7 +49,7 @@ #define IS_SDM670_TARGET(rev) IS_DPU_MAJOR_MINOR_SAME((rev), DPU_HW_VER_410) #define IS_SDM855_TARGET(rev) IS_DPU_MAJOR_MINOR_SAME((rev), DPU_HW_VER_500) #define IS_SC7180_TARGET(rev) IS_DPU_MAJOR_MINOR_SAME((rev), DPU_HW_VER_620) - +#define IS_SC7280_TARGET(rev) IS_DPU_MAJOR_MINOR_SAME((rev), DPU_HW_VER_720) #define DPU_HW_BLK_NAME_LEN 16 @@ -185,6 +185,7 @@ enum { enum { DPU_CTL_SPLIT_DISPLAY = 0x1, DPU_CTL_ACTIVE_CFG, + DPU_CTL_FETCH_ACTIVE, DPU_CTL_MAX }; @@ -193,11 +194,14 @@ enum { * @DPU_INTF_INPUT_CTRL Supports the setting of pp block from which * pixel data arrives to this INTF * @DPU_INTF_TE INTF block has TE configuration support + * @DPU_DATA_HCTL_EN Allows data to be transferred at different rate + than video timing * @DPU_INTF_MAX */ enum { DPU_INTF_INPUT_CTRL = 0x1, DPU_INTF_TE, + DPU_DATA_HCTL_EN, DPU_INTF_MAX }; @@ -719,6 +723,7 @@ struct dpu_perf_cfg { * @cursor_formats Supported formats for cursor pipe * @vig_formats Supported formats for vig pipe * @mdss_irqs: Bitmap with the irqs supported by the target + * @obsolete_irq: Irq types that are obsolete for a particular target */ struct dpu_mdss_cfg { u32 hwversion; @@ -765,6 +770,7 @@ struct dpu_mdss_cfg { const struct dpu_format_extended *vig_formats; unsigned long mdss_irqs; + unsigned long obsolete_irq; }; struct dpu_mdss_hw_cfg_handler { diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.c index 8981cfa9dbc3..2d4645e01ebf 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.c @@ -27,6 +27,7 @@ #define CTL_MERGE_3D_FLUSH 0x100 #define CTL_INTF_FLUSH 0x110 #define CTL_INTF_MASTER 0x134 +#define CTL_FETCH_PIPE_ACTIVE 0x0FC #define CTL_MIXER_BORDER_OUT BIT(24) #define CTL_FLUSH_MASK_CTL BIT(17) @@ -34,6 +35,11 @@ #define DPU_REG_RESET_TIMEOUT_US 2000 #define MERGE_3D_IDX 23 #define INTF_IDX 31 +#define CTL_INVALID_BIT 0xffff + +static const u32 fetch_tbl[SSPP_MAX] = {CTL_INVALID_BIT, 16, 17, 18, 19, + CTL_INVALID_BIT, CTL_INVALID_BIT, CTL_INVALID_BIT, CTL_INVALID_BIT, 0, + 1, 2, 3, CTL_INVALID_BIT, CTL_INVALID_BIT}; static const struct dpu_ctl_cfg *_ctl_offset(enum dpu_ctl ctl, const struct dpu_mdss_cfg *m, @@ -344,6 +350,8 @@ static void dpu_hw_ctl_clear_all_blendstages(struct dpu_hw_ctl *ctx) DPU_REG_WRITE(c, CTL_LAYER_EXT2(LM_0 + i), 0); DPU_REG_WRITE(c, CTL_LAYER_EXT3(LM_0 + i), 0); } + + DPU_REG_WRITE(c, CTL_FETCH_PIPE_ACTIVE, 0); } static void dpu_hw_ctl_setup_blendstage(struct dpu_hw_ctl *ctx, @@ -496,7 +504,9 @@ static void dpu_hw_ctl_intf_cfg_v1(struct dpu_hw_ctl *ctx, DPU_REG_WRITE(c, CTL_TOP, mode_sel); DPU_REG_WRITE(c, CTL_INTF_ACTIVE, intf_active); - DPU_REG_WRITE(c, CTL_MERGE_3D_ACTIVE, BIT(cfg->merge_3d - MERGE_3D_0)); + if (cfg->merge_3d) + DPU_REG_WRITE(c, CTL_MERGE_3D_ACTIVE, + BIT(cfg->merge_3d - MERGE_3D_0)); } static void dpu_hw_ctl_intf_cfg(struct dpu_hw_ctl *ctx, @@ -529,6 +539,23 @@ static void dpu_hw_ctl_intf_cfg(struct dpu_hw_ctl *ctx, DPU_REG_WRITE(c, CTL_TOP, intf_cfg); } +static void dpu_hw_ctl_set_fetch_pipe_active(struct dpu_hw_ctl *ctx, + unsigned long *fetch_active) +{ + int i; + u32 val = 0; + + if (fetch_active) { + for (i = 0; i < SSPP_MAX; i++) { + if (test_bit(i, fetch_active) && + fetch_tbl[i] != CTL_INVALID_BIT) + val |= BIT(fetch_tbl[i]); + } + } + + DPU_REG_WRITE(&ctx->hw, CTL_FETCH_PIPE_ACTIVE, val); +} + static void _setup_ctl_ops(struct dpu_hw_ctl_ops *ops, unsigned long cap) { @@ -558,6 +585,8 @@ static void _setup_ctl_ops(struct dpu_hw_ctl_ops *ops, ops->get_bitmask_sspp = dpu_hw_ctl_get_bitmask_sspp; ops->get_bitmask_mixer = dpu_hw_ctl_get_bitmask_mixer; ops->get_bitmask_dspp = dpu_hw_ctl_get_bitmask_dspp; + if (cap & BIT(DPU_CTL_FETCH_ACTIVE)) + ops->set_active_pipes = dpu_hw_ctl_set_fetch_pipe_active; }; static struct dpu_hw_blk_ops dpu_hw_ops; diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.h index e93a42ab60b1..806c171e5df2 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.h @@ -167,6 +167,9 @@ struct dpu_hw_ctl_ops { */ void (*setup_blendstage)(struct dpu_hw_ctl *ctx, enum dpu_lm lm, struct dpu_hw_stage_cfg *cfg); + + void (*set_active_pipes)(struct dpu_hw_ctl *ctx, + unsigned long *fetch_active); }; /** diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.c index 5c521de71567..48c96b812126 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.c @@ -25,6 +25,9 @@ #define MDP_AD4_INTR_EN_OFF 0x41c #define MDP_AD4_INTR_CLEAR_OFF 0x424 #define MDP_AD4_INTR_STATUS_OFF 0x420 +#define MDP_INTF_0_OFF_REV_7xxx 0x34000 +#define MDP_INTF_1_OFF_REV_7xxx 0x35000 +#define MDP_INTF_5_OFF_REV_7xxx 0x39000 /** * WB interrupt status bit definitions @@ -69,10 +72,12 @@ #define DPU_INTR_INTF_1_UNDERRUN BIT(26) #define DPU_INTR_INTF_2_UNDERRUN BIT(28) #define DPU_INTR_INTF_3_UNDERRUN BIT(30) +#define DPU_INTR_INTF_5_UNDERRUN BIT(22) #define DPU_INTR_INTF_0_VSYNC BIT(25) #define DPU_INTR_INTF_1_VSYNC BIT(27) #define DPU_INTR_INTF_2_VSYNC BIT(29) #define DPU_INTR_INTF_3_VSYNC BIT(31) +#define DPU_INTR_INTF_5_VSYNC BIT(23) /** * Pingpong Secondary interrupt status bit definitions @@ -242,7 +247,22 @@ static const struct dpu_intr_reg dpu_intr_set[] = { MDP_AD4_1_OFF + MDP_AD4_INTR_CLEAR_OFF, MDP_AD4_1_OFF + MDP_AD4_INTR_EN_OFF, MDP_AD4_1_OFF + MDP_AD4_INTR_STATUS_OFF, - } + }, + { + MDP_INTF_0_OFF_REV_7xxx+INTF_INTR_CLEAR, + MDP_INTF_0_OFF_REV_7xxx+INTF_INTR_EN, + MDP_INTF_0_OFF_REV_7xxx+INTF_INTR_STATUS + }, + { + MDP_INTF_1_OFF_REV_7xxx+INTF_INTR_CLEAR, + MDP_INTF_1_OFF_REV_7xxx+INTF_INTR_EN, + MDP_INTF_1_OFF_REV_7xxx+INTF_INTR_STATUS + }, + { + MDP_INTF_5_OFF_REV_7xxx+INTF_INTR_CLEAR, + MDP_INTF_5_OFF_REV_7xxx+INTF_INTR_EN, + MDP_INTF_5_OFF_REV_7xxx+INTF_INTR_STATUS + }, }; /* @@ -308,24 +328,59 @@ static const struct dpu_irq_type dpu_irq_map[] = { { DPU_IRQ_TYPE_INTF_VSYNC, INTF_2, DPU_INTR_INTF_2_VSYNC, 0}, { DPU_IRQ_TYPE_INTF_UNDER_RUN, INTF_3, DPU_INTR_INTF_3_UNDERRUN, 0}, { DPU_IRQ_TYPE_INTF_VSYNC, INTF_3, DPU_INTR_INTF_3_VSYNC, 0}, - - /* BEGIN MAP_RANGE: 32-64, INTR2 */ - /* irq_idx: 32-35 */ + /* irq_idx:32-33 */ + { DPU_IRQ_TYPE_INTF_UNDER_RUN, INTF_5, DPU_INTR_INTF_5_UNDERRUN, 0}, + { DPU_IRQ_TYPE_INTF_VSYNC, INTF_5, DPU_INTR_INTF_5_VSYNC, 0}, + /* irq_idx:34-63 */ + { DPU_IRQ_TYPE_RESERVED, 0, 0, 0}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 0}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 0}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 0}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 0}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 0}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 0}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 0}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 0}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 0}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 0}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 0}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 0}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 0}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 0}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 0}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 0}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 0}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 0}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 0}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 0}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 0}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 0}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 0}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 0}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 0}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 0}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 0}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 0}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 0}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 0}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 0}, + /* BEGIN MAP_RANGE: 64-95, INTR2 */ + /* irq_idx: 64-67 */ { DPU_IRQ_TYPE_PING_PONG_AUTO_REF, PINGPONG_S0, DPU_INTR_PING_PONG_S0_AUTOREFRESH_DONE, 1}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 1}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 1}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 1}, - /* irq_idx: 36-39 */ + /* irq_idx: 68-71 */ { DPU_IRQ_TYPE_PING_PONG_WR_PTR, PINGPONG_S0, DPU_INTR_PING_PONG_S0_WR_PTR, 1}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 1}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 1}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 1}, - /* irq_idx: 40 */ + /* irq_idx: 72 */ { DPU_IRQ_TYPE_PING_PONG_RD_PTR, PINGPONG_S0, DPU_INTR_PING_PONG_S0_RD_PTR, 1}, - /* irq_idx: 41-45 */ + /* irq_idx: 73-77 */ { DPU_IRQ_TYPE_CTL_START, CTL_0, DPU_INTR_CTL_0_START, 1}, { DPU_IRQ_TYPE_CTL_START, CTL_1, @@ -336,10 +391,10 @@ static const struct dpu_irq_type dpu_irq_map[] = { DPU_INTR_CTL_3_START, 1}, { DPU_IRQ_TYPE_CTL_START, CTL_4, DPU_INTR_CTL_4_START, 1}, - /* irq_idx: 46-47 */ + /* irq_idx: 78-79 */ { DPU_IRQ_TYPE_CWB_OVERFLOW, CWB_2, DPU_INTR_CWB_2_OVERFLOW, 1}, { DPU_IRQ_TYPE_CWB_OVERFLOW, CWB_3, DPU_INTR_CWB_3_OVERFLOW, 1}, - /* irq_idx: 48-51 */ + /* irq_idx: 80-83 */ { DPU_IRQ_TYPE_PING_PONG_TEAR_CHECK, PINGPONG_0, DPU_INTR_PING_PONG_0_TEAR_DETECTED, 1}, { DPU_IRQ_TYPE_PING_PONG_TEAR_CHECK, PINGPONG_1, @@ -348,13 +403,13 @@ static const struct dpu_irq_type dpu_irq_map[] = { DPU_INTR_PING_PONG_2_TEAR_DETECTED, 1}, { DPU_IRQ_TYPE_PING_PONG_TEAR_CHECK, PINGPONG_3, DPU_INTR_PING_PONG_3_TEAR_DETECTED, 1}, - /* irq_idx: 52-55 */ + /* irq_idx: 84-87 */ { DPU_IRQ_TYPE_RESERVED, 0, 0, 1}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 1}, { DPU_IRQ_TYPE_PING_PONG_TEAR_CHECK, PINGPONG_S0, DPU_INTR_PING_PONG_S0_TEAR_DETECTED, 1}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 1}, - /* irq_idx: 56-59 */ + /* irq_idx: 88-91 */ { DPU_IRQ_TYPE_PING_PONG_TE_CHECK, PINGPONG_0, DPU_INTR_PING_PONG_0_TE_DETECTED, 1}, { DPU_IRQ_TYPE_PING_PONG_TE_CHECK, PINGPONG_1, @@ -363,65 +418,129 @@ static const struct dpu_irq_type dpu_irq_map[] = { DPU_INTR_PING_PONG_2_TE_DETECTED, 1}, { DPU_IRQ_TYPE_PING_PONG_TE_CHECK, PINGPONG_3, DPU_INTR_PING_PONG_3_TE_DETECTED, 1}, - /* irq_idx: 60-63 */ + /* irq_idx: 92-95 */ { DPU_IRQ_TYPE_PING_PONG_TE_CHECK, PINGPONG_S0, DPU_INTR_PING_PONG_S0_TE_DETECTED, 1}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 1}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 1}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 1}, - - /* BEGIN MAP_RANGE: 64-95 HIST */ - /* irq_idx: 64-67 */ + /* irq_idx: 96-127 */ + { DPU_IRQ_TYPE_RESERVED, 0, 0, 1}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 1}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 1}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 1}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 1}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 1}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 1}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 1}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 1}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 1}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 1}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 1}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 1}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 1}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 1}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 1}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 1}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 1}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 1}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 1}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 1}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 1}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 1}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 1}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 1}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 1}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 1}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 1}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 1}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 1}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 1}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 1}, + /* BEGIN MAP_RANGE: 128-159 HIST */ + /* irq_idx: 128-131 */ { DPU_IRQ_TYPE_HIST_VIG_DONE, SSPP_VIG0, DPU_INTR_HIST_VIG_0_DONE, 2}, { DPU_IRQ_TYPE_HIST_VIG_RSTSEQ, SSPP_VIG0, DPU_INTR_HIST_VIG_0_RSTSEQ_DONE, 2}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 2}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 2}, - /* irq_idx: 68-71 */ + /* irq_idx: 132-135 */ { DPU_IRQ_TYPE_HIST_VIG_DONE, SSPP_VIG1, DPU_INTR_HIST_VIG_1_DONE, 2}, { DPU_IRQ_TYPE_HIST_VIG_RSTSEQ, SSPP_VIG1, DPU_INTR_HIST_VIG_1_RSTSEQ_DONE, 2}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 2}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 2}, - /* irq_idx: 72-75 */ + /* irq_idx: 136-139 */ { DPU_IRQ_TYPE_HIST_VIG_DONE, SSPP_VIG2, DPU_INTR_HIST_VIG_2_DONE, 2}, { DPU_IRQ_TYPE_HIST_VIG_RSTSEQ, SSPP_VIG2, DPU_INTR_HIST_VIG_2_RSTSEQ_DONE, 2}, { DPU_IRQ_TYPE_HIST_VIG_DONE, SSPP_VIG3, DPU_INTR_HIST_VIG_3_DONE, 2}, { DPU_IRQ_TYPE_HIST_VIG_RSTSEQ, SSPP_VIG3, DPU_INTR_HIST_VIG_3_RSTSEQ_DONE, 2}, - /* irq_idx: 76-79 */ + /* irq_idx: 140-143 */ { DPU_IRQ_TYPE_HIST_DSPP_DONE, DSPP_0, DPU_INTR_HIST_DSPP_0_DONE, 2}, { DPU_IRQ_TYPE_HIST_DSPP_RSTSEQ, DSPP_0, DPU_INTR_HIST_DSPP_0_RSTSEQ_DONE, 2}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 2}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 2}, - /* irq_idx: 80-83 */ + /* irq_idx: 144-147 */ { DPU_IRQ_TYPE_HIST_DSPP_DONE, DSPP_1, DPU_INTR_HIST_DSPP_1_DONE, 2}, { DPU_IRQ_TYPE_HIST_DSPP_RSTSEQ, DSPP_1, DPU_INTR_HIST_DSPP_1_RSTSEQ_DONE, 2}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 2}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 2}, - /* irq_idx: 84-87 */ + /* irq_idx: 148-151 */ { DPU_IRQ_TYPE_HIST_DSPP_DONE, DSPP_2, DPU_INTR_HIST_DSPP_2_DONE, 2}, { DPU_IRQ_TYPE_HIST_DSPP_RSTSEQ, DSPP_2, DPU_INTR_HIST_DSPP_2_RSTSEQ_DONE, 2}, { DPU_IRQ_TYPE_HIST_DSPP_DONE, DSPP_3, DPU_INTR_HIST_DSPP_3_DONE, 2}, { DPU_IRQ_TYPE_HIST_DSPP_RSTSEQ, DSPP_3, DPU_INTR_HIST_DSPP_3_RSTSEQ_DONE, 2}, - /* irq_idx: 88-91 */ + /* irq_idx: 152-155 */ { DPU_IRQ_TYPE_RESERVED, 0, 0, 2}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 2}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 2}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 2}, - /* irq_idx: 92-95 */ + /* irq_idx: 156-159 */ { DPU_IRQ_TYPE_RESERVED, 0, 0, 2}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 2}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 2}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 2}, - - /* BEGIN MAP_RANGE: 96-127 INTF_0_INTR */ - /* irq_idx: 96-99 */ + /* irq_idx: 160-191 */ + { DPU_IRQ_TYPE_RESERVED, 0, 0, 2}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 2}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 2}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 2}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 2}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 2}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 2}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 2}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 2}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 2}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 2}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 2}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 2}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 2}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 2}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 2}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 2}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 2}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 2}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 2}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 2}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 2}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 2}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 2}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 2}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 2}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 2}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 2}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 2}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 2}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 2}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 2}, + /* BEGIN MAP_RANGE: 192-255 INTF_0_INTR */ + /* irq_idx: 192-195 */ { DPU_IRQ_TYPE_SFI_VIDEO_IN, INTF_0, DPU_INTR_VIDEO_INTO_STATIC, 3}, { DPU_IRQ_TYPE_SFI_VIDEO_OUT, INTF_0, @@ -430,7 +549,7 @@ static const struct dpu_irq_type dpu_irq_map[] = { DPU_INTR_DSICMD_0_INTO_STATIC, 3}, { DPU_IRQ_TYPE_SFI_CMD_0_OUT, INTF_0, DPU_INTR_DSICMD_0_OUTOF_STATIC, 3}, - /* irq_idx: 100-103 */ + /* irq_idx: 196-199 */ { DPU_IRQ_TYPE_SFI_CMD_1_IN, INTF_0, DPU_INTR_DSICMD_1_INTO_STATIC, 3}, { DPU_IRQ_TYPE_SFI_CMD_1_OUT, INTF_0, @@ -439,39 +558,71 @@ static const struct dpu_irq_type dpu_irq_map[] = { DPU_INTR_DSICMD_2_INTO_STATIC, 3}, { DPU_IRQ_TYPE_SFI_CMD_2_OUT, INTF_0, DPU_INTR_DSICMD_2_OUTOF_STATIC, 3}, - /* irq_idx: 104-107 */ + /* irq_idx: 200-203 */ { DPU_IRQ_TYPE_PROG_LINE, INTF_0, DPU_INTR_PROG_LINE, 3}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 3}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 3}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 3}, - /* irq_idx: 108-111 */ + /* irq_idx: 204-207 */ + { DPU_IRQ_TYPE_RESERVED, 0, 0, 3}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 3}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 3}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 3}, + /* irq_idx: 208-211 */ { DPU_IRQ_TYPE_RESERVED, 0, 0, 3}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 3}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 3}, - /* irq_idx: 112-115 */ { DPU_IRQ_TYPE_RESERVED, 0, 0, 3}, + /* irq_idx: 212-215 */ { DPU_IRQ_TYPE_RESERVED, 0, 0, 3}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 3}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 3}, - /* irq_idx: 116-119 */ { DPU_IRQ_TYPE_RESERVED, 0, 0, 3}, + /* irq_idx: 216-219 */ { DPU_IRQ_TYPE_RESERVED, 0, 0, 3}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 3}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 3}, - /* irq_idx: 120-123 */ { DPU_IRQ_TYPE_RESERVED, 0, 0, 3}, + /* irq_idx: 220-223 */ { DPU_IRQ_TYPE_RESERVED, 0, 0, 3}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 3}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 3}, - /* irq_idx: 124-127 */ { DPU_IRQ_TYPE_RESERVED, 0, 0, 3}, + /* irq_idx: 224-255 */ { DPU_IRQ_TYPE_RESERVED, 0, 0, 3}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 3}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 3}, - - /* BEGIN MAP_RANGE: 128-159 INTF_1_INTR */ - /* irq_idx: 128-131 */ + { DPU_IRQ_TYPE_RESERVED, 0, 0, 3}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 3}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 3}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 3}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 3}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 3}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 3}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 3}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 3}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 3}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 3}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 3}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 3}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 3}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 3}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 3}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 3}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 3}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 3}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 3}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 3}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 3}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 3}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 3}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 3}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 3}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 3}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 3}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 3}, + /* BEGIN MAP_RANGE: 256-319 INTF_1_INTR */ + /* irq_idx: 256-259 */ { DPU_IRQ_TYPE_SFI_VIDEO_IN, INTF_1, DPU_INTR_VIDEO_INTO_STATIC, 4}, { DPU_IRQ_TYPE_SFI_VIDEO_OUT, INTF_1, @@ -480,7 +631,7 @@ static const struct dpu_irq_type dpu_irq_map[] = { DPU_INTR_DSICMD_0_INTO_STATIC, 4}, { DPU_IRQ_TYPE_SFI_CMD_0_OUT, INTF_1, DPU_INTR_DSICMD_0_OUTOF_STATIC, 4}, - /* irq_idx: 132-135 */ + /* irq_idx: 260-263 */ { DPU_IRQ_TYPE_SFI_CMD_1_IN, INTF_1, DPU_INTR_DSICMD_1_INTO_STATIC, 4}, { DPU_IRQ_TYPE_SFI_CMD_1_OUT, INTF_1, @@ -489,39 +640,71 @@ static const struct dpu_irq_type dpu_irq_map[] = { DPU_INTR_DSICMD_2_INTO_STATIC, 4}, { DPU_IRQ_TYPE_SFI_CMD_2_OUT, INTF_1, DPU_INTR_DSICMD_2_OUTOF_STATIC, 4}, - /* irq_idx: 136-139 */ + /* irq_idx: 264-267 */ { DPU_IRQ_TYPE_PROG_LINE, INTF_1, DPU_INTR_PROG_LINE, 4}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 4}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 4}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 4}, - /* irq_idx: 140-143 */ + /* irq_idx: 268-271 */ { DPU_IRQ_TYPE_RESERVED, 0, 0, 4}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 4}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 4}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 4}, - /* irq_idx: 144-147 */ + /* irq_idx: 272-275 */ { DPU_IRQ_TYPE_RESERVED, 0, 0, 4}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 4}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 4}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 4}, - /* irq_idx: 148-151 */ + /* irq_idx: 276-279 */ { DPU_IRQ_TYPE_RESERVED, 0, 0, 4}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 4}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 4}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 4}, - /* irq_idx: 152-155 */ + /* irq_idx: 280-283 */ { DPU_IRQ_TYPE_RESERVED, 0, 0, 4}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 4}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 4}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 4}, - /* irq_idx: 156-159 */ + /* irq_idx: 284-287 */ { DPU_IRQ_TYPE_RESERVED, 0, 0, 4}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 4}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 4}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 4}, - - /* BEGIN MAP_RANGE: 160-191 INTF_2_INTR */ - /* irq_idx: 160-163 */ + /* irq_idx: 288-319 */ + { DPU_IRQ_TYPE_RESERVED, 0, 0, 4}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 4}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 4}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 4}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 4}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 4}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 4}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 4}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 4}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 4}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 4}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 4}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 4}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 4}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 4}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 4}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 4}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 4}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 4}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 4}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 4}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 4}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 4}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 4}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 4}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 4}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 4}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 4}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 4}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 4}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 4}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 4}, + /* BEGIN MAP_RANGE: 320-383 INTF_2_INTR */ + /* irq_idx: 320-323 */ { DPU_IRQ_TYPE_SFI_VIDEO_IN, INTF_2, DPU_INTR_VIDEO_INTO_STATIC, 5}, { DPU_IRQ_TYPE_SFI_VIDEO_OUT, INTF_2, @@ -530,7 +713,7 @@ static const struct dpu_irq_type dpu_irq_map[] = { DPU_INTR_DSICMD_0_INTO_STATIC, 5}, { DPU_IRQ_TYPE_SFI_CMD_0_OUT, INTF_2, DPU_INTR_DSICMD_0_OUTOF_STATIC, 5}, - /* irq_idx: 164-167 */ + /* irq_idx: 324-327 */ { DPU_IRQ_TYPE_SFI_CMD_1_IN, INTF_2, DPU_INTR_DSICMD_1_INTO_STATIC, 5}, { DPU_IRQ_TYPE_SFI_CMD_1_OUT, INTF_2, @@ -539,39 +722,71 @@ static const struct dpu_irq_type dpu_irq_map[] = { DPU_INTR_DSICMD_2_INTO_STATIC, 5}, { DPU_IRQ_TYPE_SFI_CMD_2_OUT, INTF_2, DPU_INTR_DSICMD_2_OUTOF_STATIC, 5}, - /* irq_idx: 168-171 */ + /* irq_idx: 328-331 */ { DPU_IRQ_TYPE_PROG_LINE, INTF_2, DPU_INTR_PROG_LINE, 5}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 5}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 5}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 5}, - /* irq_idx: 172-175 */ + /* irq_idx: 332-335 */ { DPU_IRQ_TYPE_RESERVED, 0, 0, 5}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 5}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 5}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 5}, - /* irq_idx: 176-179 */ + /* irq_idx: 336-339 */ { DPU_IRQ_TYPE_RESERVED, 0, 0, 5}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 5}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 5}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 5}, - /* irq_idx: 180-183 */ + /* irq_idx: 340-343 */ { DPU_IRQ_TYPE_RESERVED, 0, 0, 5}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 5}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 5}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 5}, - /* irq_idx: 184-187 */ + /* irq_idx: 344-347 */ { DPU_IRQ_TYPE_RESERVED, 0, 0, 5}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 5}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 5}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 5}, - /* irq_idx: 188-191 */ + /* irq_idx: 348-351 */ { DPU_IRQ_TYPE_RESERVED, 0, 0, 5}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 5}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 5}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 5}, - - /* BEGIN MAP_RANGE: 192-223 INTF_3_INTR */ - /* irq_idx: 192-195 */ + /* irq_idx: 352-383 */ + { DPU_IRQ_TYPE_RESERVED, 0, 0, 5}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 5}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 5}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 5}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 5}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 5}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 5}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 5}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 5}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 5}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 5}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 5}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 5}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 5}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 5}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 5}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 5}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 5}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 5}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 5}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 5}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 5}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 5}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 5}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 5}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 5}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 5}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 5}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 5}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 5}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 5}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 5}, + /* BEGIN MAP_RANGE: 384-447 INTF_3_INTR */ + /* irq_idx: 384-387 */ { DPU_IRQ_TYPE_SFI_VIDEO_IN, INTF_3, DPU_INTR_VIDEO_INTO_STATIC, 6}, { DPU_IRQ_TYPE_SFI_VIDEO_OUT, INTF_3, @@ -580,7 +795,7 @@ static const struct dpu_irq_type dpu_irq_map[] = { DPU_INTR_DSICMD_0_INTO_STATIC, 6}, { DPU_IRQ_TYPE_SFI_CMD_0_OUT, INTF_3, DPU_INTR_DSICMD_0_OUTOF_STATIC, 6}, - /* irq_idx: 196-199 */ + /* irq_idx: 388-391 */ { DPU_IRQ_TYPE_SFI_CMD_1_IN, INTF_3, DPU_INTR_DSICMD_1_INTO_STATIC, 6}, { DPU_IRQ_TYPE_SFI_CMD_1_OUT, INTF_3, @@ -589,39 +804,71 @@ static const struct dpu_irq_type dpu_irq_map[] = { DPU_INTR_DSICMD_2_INTO_STATIC, 6}, { DPU_IRQ_TYPE_SFI_CMD_2_OUT, INTF_3, DPU_INTR_DSICMD_2_OUTOF_STATIC, 6}, - /* irq_idx: 200-203 */ + /* irq_idx: 392-395 */ { DPU_IRQ_TYPE_PROG_LINE, INTF_3, DPU_INTR_PROG_LINE, 6}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 6}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 6}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 6}, - /* irq_idx: 204-207 */ + /* irq_idx: 396-399 */ { DPU_IRQ_TYPE_RESERVED, 0, 0, 6}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 6}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 6}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 6}, - /* irq_idx: 208-211 */ + /* irq_idx: 400-403 */ { DPU_IRQ_TYPE_RESERVED, 0, 0, 6}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 6}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 6}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 6}, - /* irq_idx: 212-215 */ + /* irq_idx: 404-407 */ { DPU_IRQ_TYPE_RESERVED, 0, 0, 6}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 6}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 6}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 6}, - /* irq_idx: 216-219 */ + /* irq_idx: 408-411 */ { DPU_IRQ_TYPE_RESERVED, 0, 0, 6}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 6}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 6}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 6}, - /* irq_idx: 220-223 */ + /* irq_idx: 412-415 */ { DPU_IRQ_TYPE_RESERVED, 0, 0, 6}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 6}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 6}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 6}, - - /* BEGIN MAP_RANGE: 224-255 INTF_4_INTR */ - /* irq_idx: 224-227 */ + /* irq_idx: 416-447*/ + { DPU_IRQ_TYPE_RESERVED, 0, 0, 6}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 6}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 6}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 6}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 6}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 6}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 6}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 6}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 6}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 6}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 6}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 6}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 6}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 6}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 6}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 6}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 6}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 6}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 6}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 6}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 6}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 6}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 6}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 6}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 6}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 6}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 6}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 6}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 6}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 6}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 6}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 6}, + /* BEGIN MAP_RANGE: 448-511 INTF_4_INTR */ + /* irq_idx: 448-451 */ { DPU_IRQ_TYPE_SFI_VIDEO_IN, INTF_4, DPU_INTR_VIDEO_INTO_STATIC, 7}, { DPU_IRQ_TYPE_SFI_VIDEO_OUT, INTF_4, @@ -630,7 +877,7 @@ static const struct dpu_irq_type dpu_irq_map[] = { DPU_INTR_DSICMD_0_INTO_STATIC, 7}, { DPU_IRQ_TYPE_SFI_CMD_0_OUT, INTF_4, DPU_INTR_DSICMD_0_OUTOF_STATIC, 7}, - /* irq_idx: 228-231 */ + /* irq_idx: 452-455 */ { DPU_IRQ_TYPE_SFI_CMD_1_IN, INTF_4, DPU_INTR_DSICMD_1_INTO_STATIC, 7}, { DPU_IRQ_TYPE_SFI_CMD_1_OUT, INTF_4, @@ -639,130 +886,474 @@ static const struct dpu_irq_type dpu_irq_map[] = { DPU_INTR_DSICMD_2_INTO_STATIC, 7}, { DPU_IRQ_TYPE_SFI_CMD_2_OUT, INTF_4, DPU_INTR_DSICMD_2_OUTOF_STATIC, 7}, - /* irq_idx: 232-235 */ + /* irq_idx: 456-459 */ { DPU_IRQ_TYPE_PROG_LINE, INTF_4, DPU_INTR_PROG_LINE, 7}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 7}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 7}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 7}, - /* irq_idx: 236-239 */ + /* irq_idx: 460-463 */ { DPU_IRQ_TYPE_RESERVED, 0, 0, 7}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 7}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 7}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 7}, - /* irq_idx: 240-243 */ + /* irq_idx: 464-467 */ { DPU_IRQ_TYPE_RESERVED, 0, 0, 7}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 7}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 7}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 7}, - /* irq_idx: 244-247 */ + /* irq_idx: 468-471 */ { DPU_IRQ_TYPE_RESERVED, 0, 0, 7}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 7}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 7}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 7}, - /* irq_idx: 248-251 */ + /* irq_idx: 472-475 */ { DPU_IRQ_TYPE_RESERVED, 0, 0, 7}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 7}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 7}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 7}, - /* irq_idx: 252-255 */ + /* irq_idx: 476-479 */ { DPU_IRQ_TYPE_RESERVED, 0, 0, 7}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 7}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 7}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 7}, - - /* BEGIN MAP_RANGE: 256-287 AD4_0_INTR */ - /* irq_idx: 256-259 */ + /* irq_idx: 480-511 */ + { DPU_IRQ_TYPE_RESERVED, 0, 0, 7}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 7}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 7}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 7}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 7}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 7}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 7}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 7}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 7}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 7}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 7}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 7}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 7}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 7}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 7}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 7}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 7}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 7}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 7}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 7}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 7}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 7}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 7}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 7}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 7}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 7}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 7}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 7}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 7}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 7}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 7}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 7}, + /* BEGIN MAP_RANGE: 512-575 AD4_0_INTR */ + /* irq_idx: 512-515 */ { DPU_IRQ_TYPE_AD4_BL_DONE, DSPP_0, DPU_INTR_BACKLIGHT_UPDATED, 8}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 8}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 8}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 8}, - /* irq_idx: 260-263 */ + /* irq_idx: 516-519 */ { DPU_IRQ_TYPE_RESERVED, 0, 0, 8}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 8}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 8}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 8}, - /* irq_idx: 264-267 */ + /* irq_idx: 520-523 */ { DPU_IRQ_TYPE_RESERVED, 0, 0, 8}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 8}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 8}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 8}, - /* irq_idx: 268-271 */ + /* irq_idx: 524-527 */ { DPU_IRQ_TYPE_RESERVED, 0, 0, 8}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 8}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 8}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 8}, - /* irq_idx: 272-275 */ + /* irq_idx: 528-531 */ { DPU_IRQ_TYPE_RESERVED, 0, 0, 8}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 8}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 8}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 8}, - /* irq_idx: 276-279 */ + /* irq_idx: 532-535 */ { DPU_IRQ_TYPE_RESERVED, 0, 0, 8}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 8}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 8}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 8}, - /* irq_idx: 280-283 */ + /* irq_idx: 536-539 */ { DPU_IRQ_TYPE_RESERVED, 0, 0, 8}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 8}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 8}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 8}, - /* irq_idx: 284-287 */ + /* irq_idx: 540-543 */ { DPU_IRQ_TYPE_RESERVED, 0, 0, 8}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 8}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 8}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 8}, - - /* BEGIN MAP_RANGE: 288-319 AD4_1_INTR */ - /* irq_idx: 288-291 */ + /* irq_idx: 544-575*/ + { DPU_IRQ_TYPE_RESERVED, 0, 0, 8}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 8}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 8}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 8}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 8}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 8}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 8}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 8}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 8}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 8}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 8}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 8}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 8}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 8}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 8}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 8}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 8}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 8}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 8}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 8}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 8}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 8}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 8}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 8}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 8}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 8}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 8}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 8}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 8}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 8}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 8}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 8}, + /* BEGIN MAP_RANGE: 576-639 AD4_1_INTR */ + /* irq_idx: 576-579 */ { DPU_IRQ_TYPE_AD4_BL_DONE, DSPP_1, DPU_INTR_BACKLIGHT_UPDATED, 9}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 9}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 9}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 9}, - /* irq_idx: 292-295 */ + /* irq_idx: 580-583 */ + { DPU_IRQ_TYPE_RESERVED, 0, 0, 9}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 9}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 9}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 9}, + /* irq_idx: 584-587 */ { DPU_IRQ_TYPE_RESERVED, 0, 0, 9}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 9}, - /* irq_idx: 296-299 */ { DPU_IRQ_TYPE_RESERVED, 0, 0, 9}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 9}, + /* irq_idx: 588-591 */ { DPU_IRQ_TYPE_RESERVED, 0, 0, 9}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 9}, - /* irq_idx: 300-303 */ { DPU_IRQ_TYPE_RESERVED, 0, 0, 9}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 9}, + /* irq_idx: 592-595 */ { DPU_IRQ_TYPE_RESERVED, 0, 0, 9}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 9}, - /* irq_idx: 304-307 */ { DPU_IRQ_TYPE_RESERVED, 0, 0, 9}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 9}, + /* irq_idx: 596-599 */ { DPU_IRQ_TYPE_RESERVED, 0, 0, 9}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 9}, - /* irq_idx: 308-311 */ { DPU_IRQ_TYPE_RESERVED, 0, 0, 9}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 9}, + /* irq_idx: 600-603 */ { DPU_IRQ_TYPE_RESERVED, 0, 0, 9}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 9}, - /* irq_idx: 312-315 */ { DPU_IRQ_TYPE_RESERVED, 0, 0, 9}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 9}, + /* irq_idx: 604-607 */ { DPU_IRQ_TYPE_RESERVED, 0, 0, 9}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 9}, - /* irq_idx: 315-319 */ { DPU_IRQ_TYPE_RESERVED, 0, 0, 9}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 9}, + /* irq_idx: 608-639 */ { DPU_IRQ_TYPE_RESERVED, 0, 0, 9}, { DPU_IRQ_TYPE_RESERVED, 0, 0, 9}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 9}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 9}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 9}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 9}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 9}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 9}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 9}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 9}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 9}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 9}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 9}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 9}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 9}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 9}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 9}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 9}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 9}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 9}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 9}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 9}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 9}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 9}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 9}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 9}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 9}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 9}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 9}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 9}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 9}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 9}, + /* BEGIN MAP_RANGE: 640-703 INTF_0_SC7280_INTR */ + /* irq_idx: 640-643 */ + { DPU_IRQ_TYPE_SFI_VIDEO_IN, INTF_0, + DPU_INTR_VIDEO_INTO_STATIC, 10}, + { DPU_IRQ_TYPE_SFI_VIDEO_OUT, INTF_0, + DPU_INTR_VIDEO_OUTOF_STATIC, 10}, + { DPU_IRQ_TYPE_SFI_CMD_0_IN, INTF_0, + DPU_INTR_DSICMD_0_INTO_STATIC, 10}, + { DPU_IRQ_TYPE_SFI_CMD_0_OUT, INTF_0, + DPU_INTR_DSICMD_0_OUTOF_STATIC, 10}, + /* irq_idx: 644-647 */ + { DPU_IRQ_TYPE_SFI_CMD_1_IN, INTF_0, + DPU_INTR_DSICMD_1_INTO_STATIC, 10}, + { DPU_IRQ_TYPE_SFI_CMD_1_OUT, INTF_0, + DPU_INTR_DSICMD_1_OUTOF_STATIC, 10}, + { DPU_IRQ_TYPE_SFI_CMD_2_IN, INTF_0, + DPU_INTR_DSICMD_2_INTO_STATIC, 10}, + { DPU_IRQ_TYPE_SFI_CMD_2_OUT, INTF_0, + DPU_INTR_DSICMD_2_OUTOF_STATIC, 10}, + /* irq_idx: 648-651 */ + { DPU_IRQ_TYPE_PROG_LINE, INTF_0, DPU_INTR_PROG_LINE, 10}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 10}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 10}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 10}, + /* irq_idx: 652-655 */ + { DPU_IRQ_TYPE_RESERVED, 0, 0, 10}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 10}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 10}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 10}, + /* irq_idx: 656-659 */ + { DPU_IRQ_TYPE_RESERVED, 0, 0, 10}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 10}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 10}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 10}, + /* irq_idx: 660-663 */ + { DPU_IRQ_TYPE_RESERVED, 0, 0, 10}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 10}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 10}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 10}, + /* irq_idx: 664-667 */ + { DPU_IRQ_TYPE_RESERVED, 0, 0, 10}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 10}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 10}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 10}, + /* irq_idx: 668-671 */ + { DPU_IRQ_TYPE_RESERVED, 0, 0, 10}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 10}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 10}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 10}, + /* irq_idx: 672-703 */ + { DPU_IRQ_TYPE_RESERVED, 0, 0, 10}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 10}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 10}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 10}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 10}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 10}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 10}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 10}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 10}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 10}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 10}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 10}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 10}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 10}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 10}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 10}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 10}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 10}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 10}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 10}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 10}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 10}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 10}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 10}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 10}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 10}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 10}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 10}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 10}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 10}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 10}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 10}, + /* BEGIN MAP_RANGE: 704-767 INTF_1_SC7280_INTR */ + /* irq_idx: 704-707 */ + { DPU_IRQ_TYPE_SFI_VIDEO_IN, INTF_1, + DPU_INTR_VIDEO_INTO_STATIC, 11}, + { DPU_IRQ_TYPE_SFI_VIDEO_OUT, INTF_1, + DPU_INTR_VIDEO_OUTOF_STATIC, 11}, + { DPU_IRQ_TYPE_SFI_CMD_0_IN, INTF_1, + DPU_INTR_DSICMD_0_INTO_STATIC, 11}, + { DPU_IRQ_TYPE_SFI_CMD_0_OUT, INTF_1, + DPU_INTR_DSICMD_0_OUTOF_STATIC, 11}, + /* irq_idx: 708-711 */ + { DPU_IRQ_TYPE_SFI_CMD_1_IN, INTF_1, + DPU_INTR_DSICMD_1_INTO_STATIC, 11}, + { DPU_IRQ_TYPE_SFI_CMD_1_OUT, INTF_1, + DPU_INTR_DSICMD_1_OUTOF_STATIC, 11}, + { DPU_IRQ_TYPE_SFI_CMD_2_IN, INTF_1, + DPU_INTR_DSICMD_2_INTO_STATIC, 11}, + { DPU_IRQ_TYPE_SFI_CMD_2_OUT, INTF_1, + DPU_INTR_DSICMD_2_OUTOF_STATIC, 11}, + /* irq_idx: 712-715 */ + { DPU_IRQ_TYPE_PROG_LINE, INTF_1, DPU_INTR_PROG_LINE, 11}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 11}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 11}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 11}, + /* irq_idx: 716-719 */ + { DPU_IRQ_TYPE_RESERVED, 0, 0, 11}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 11}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 11}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 11}, + /* irq_idx: 720-723 */ + { DPU_IRQ_TYPE_RESERVED, 0, 0, 11}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 11}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 11}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 11}, + /* irq_idx: 724-727 */ + { DPU_IRQ_TYPE_RESERVED, 0, 0, 11}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 11}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 11}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 11}, + /* irq_idx: 728-731 */ + { DPU_IRQ_TYPE_RESERVED, 0, 0, 11}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 11}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 11}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 11}, + /* irq_idx: 732-735 */ + { DPU_IRQ_TYPE_RESERVED, 0, 0, 11}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 11}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 11}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 11}, + /* irq_idx: 736-767 */ + { DPU_IRQ_TYPE_RESERVED, 0, 0, 11}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 11}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 11}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 11}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 11}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 11}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 11}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 11}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 11}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 11}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 11}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 11}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 11}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 11}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 11}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 11}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 11}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 11}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 11}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 11}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 11}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 11}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 11}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 11}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 11}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 11}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 11}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 11}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 11}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 11}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 11}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 11}, + /* BEGIN MAP_RANGE: 768-831 INTF_5_SC7280_INTR */ + /* irq_idx: 768-771 */ + { DPU_IRQ_TYPE_SFI_VIDEO_IN, INTF_5, + DPU_INTR_VIDEO_INTO_STATIC, 12}, + { DPU_IRQ_TYPE_SFI_VIDEO_OUT, INTF_5, + DPU_INTR_VIDEO_OUTOF_STATIC, 12}, + { DPU_IRQ_TYPE_SFI_CMD_0_IN, INTF_5, + DPU_INTR_DSICMD_0_INTO_STATIC, 12}, + { DPU_IRQ_TYPE_SFI_CMD_0_OUT, INTF_5, + DPU_INTR_DSICMD_0_OUTOF_STATIC, 12}, + /* irq_idx: 772-775 */ + { DPU_IRQ_TYPE_SFI_CMD_1_IN, INTF_5, + DPU_INTR_DSICMD_1_INTO_STATIC, 12}, + { DPU_IRQ_TYPE_SFI_CMD_1_OUT, INTF_5, + DPU_INTR_DSICMD_1_OUTOF_STATIC, 12}, + { DPU_IRQ_TYPE_SFI_CMD_2_IN, INTF_5, + DPU_INTR_DSICMD_2_INTO_STATIC, 12}, + { DPU_IRQ_TYPE_SFI_CMD_2_OUT, INTF_5, + DPU_INTR_DSICMD_2_OUTOF_STATIC, 12}, + /* irq_idx: 776-779 */ + { DPU_IRQ_TYPE_PROG_LINE, INTF_5, DPU_INTR_PROG_LINE, 12}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 12}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 12}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 12}, + /* irq_idx: 780-783 */ + { DPU_IRQ_TYPE_RESERVED, 0, 0, 12}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 12}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 12}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 12}, + /* irq_idx: 784-787 */ + { DPU_IRQ_TYPE_RESERVED, 0, 0, 12}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 12}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 12}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 12}, + /* irq_idx: 788-791 */ + { DPU_IRQ_TYPE_RESERVED, 0, 0, 12}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 12}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 12}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 12}, + /* irq_idx: 792-795 */ + { DPU_IRQ_TYPE_RESERVED, 0, 0, 12}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 12}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 12}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 12}, + /* irq_idx: 796-799 */ + { DPU_IRQ_TYPE_RESERVED, 0, 0, 12}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 12}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 12}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 12}, + /* irq_idx: 800-831 */ + { DPU_IRQ_TYPE_RESERVED, 0, 0, 12}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 12}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 12}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 12}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 12}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 12}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 12}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 12}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 12}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 12}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 12}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 12}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 12}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 12}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 12}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 12}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 12}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 12}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 12}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 12}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 12}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 12}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 12}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 12}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 12}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 12}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 12}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 12}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 12}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 12}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 12}, + { DPU_IRQ_TYPE_RESERVED, 0, 0, 12}, }; -static int dpu_hw_intr_irqidx_lookup(enum dpu_intr_type intr_type, - u32 instance_idx) +static int dpu_hw_intr_irqidx_lookup(struct dpu_hw_intr *intr, + enum dpu_intr_type intr_type, u32 instance_idx) { int i; for (i = 0; i < ARRAY_SIZE(dpu_irq_map); i++) { if (intr_type == dpu_irq_map[i].intr_type && - instance_idx == dpu_irq_map[i].instance_idx) + instance_idx == dpu_irq_map[i].instance_idx && + !(intr->obsolete_irq & BIT(dpu_irq_map[i].intr_type))) return i; } @@ -795,11 +1386,11 @@ static void dpu_hw_intr_dispatch_irq(struct dpu_hw_intr *intr, irq_status = intr->save_irq_status[reg_idx]; /* - * Each Interrupt register has a range of 32 indexes, and + * Each Interrupt register has a range of 64 indexes, and * that is static for dpu_irq_map. */ - start_idx = reg_idx * 32; - end_idx = start_idx + 32; + start_idx = reg_idx * 64; + end_idx = start_idx + 64; if (!test_bit(reg_idx, &intr->irq_mask) || start_idx >= ARRAY_SIZE(dpu_irq_map)) @@ -814,7 +1405,9 @@ static void dpu_hw_intr_dispatch_irq(struct dpu_hw_intr *intr, (irq_idx < end_idx) && irq_status; irq_idx++) if ((irq_status & dpu_irq_map[irq_idx].irq_mask) && - (dpu_irq_map[irq_idx].reg_idx == reg_idx)) { + (dpu_irq_map[irq_idx].reg_idx == reg_idx) && + !(intr->obsolete_irq & + BIT(dpu_irq_map[irq_idx].intr_type))) { /* * Once a match on irq mask, perform a callback * to the given cbfunc. cbfunc will take care @@ -1126,6 +1719,8 @@ struct dpu_hw_intr *dpu_hw_intr_init(void __iomem *addr, } intr->irq_mask = m->mdss_irqs; + intr->obsolete_irq = m->obsolete_irq; + spin_lock_init(&intr->irq_lock); return intr; diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.h index fc9c98617281..5d6f9a7a5195 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.h @@ -83,11 +83,12 @@ struct dpu_hw_intr_ops { /** * irq_idx_lookup - Lookup IRQ index on the HW interrupt type * Used for all irq related ops + * @intr: HW interrupt handle * @intr_type: Interrupt type defined in dpu_intr_type * @instance_idx: HW interrupt block instance * @return: irq_idx or -EINVAL for lookup fail */ - int (*irq_idx_lookup)( + int (*irq_idx_lookup)(struct dpu_hw_intr *intr, enum dpu_intr_type intr_type, u32 instance_idx); @@ -179,6 +180,7 @@ struct dpu_hw_intr_ops { * @save_irq_status: array of IRQ status reg storage created during init * @irq_idx_tbl_size: total number of irq_idx mapped in the hw_interrupts * @irq_lock: spinlock for accessing IRQ resources + * @obsolete_irq: irq types that are obsolete for a particular target */ struct dpu_hw_intr { struct dpu_hw_blk_reg_map hw; @@ -188,6 +190,7 @@ struct dpu_hw_intr { u32 irq_idx_tbl_size; spinlock_t irq_lock; unsigned long irq_mask; + unsigned long obsolete_irq; }; /** diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.c index 6f0f54588124..1599e3f49a4f 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.c @@ -31,6 +31,8 @@ #define INTF_TEST_CTL 0x054 #define INTF_TP_COLOR0 0x058 #define INTF_TP_COLOR1 0x05C +#define INTF_CONFIG2 0x060 +#define INTF_DISPLAY_DATA_HCTL 0x064 #define INTF_FRAME_LINE_COUNT_EN 0x0A8 #define INTF_FRAME_COUNT 0x0AC #define INTF_LINE_COUNT 0x0B0 @@ -93,7 +95,7 @@ static void dpu_hw_intf_setup_timing_engine(struct dpu_hw_intf *ctx, u32 active_hctl, display_hctl, hsync_ctl; u32 polarity_ctl, den_polarity, hsync_polarity, vsync_polarity; u32 panel_format; - u32 intf_cfg; + u32 intf_cfg, intf_cfg2 = 0, display_data_hctl = 0; /* read interface_cfg */ intf_cfg = DPU_REG_READ(c, INTF_CONFIG); @@ -178,6 +180,13 @@ static void dpu_hw_intf_setup_timing_engine(struct dpu_hw_intf *ctx, (COLOR_8BIT << 4) | (0x21 << 8)); + if (ctx->cap->features & BIT(DPU_DATA_HCTL_EN)) { + intf_cfg2 |= BIT(4); + display_data_hctl = display_hctl; + DPU_REG_WRITE(c, INTF_CONFIG2, intf_cfg2); + DPU_REG_WRITE(c, INTF_DISPLAY_DATA_HCTL, display_data_hctl); + } + DPU_REG_WRITE(c, INTF_HSYNC_CTL, hsync_ctl); DPU_REG_WRITE(c, INTF_VSYNC_PERIOD_F0, vsync_period * hsync_period); DPU_REG_WRITE(c, INTF_VSYNC_PULSE_WIDTH_F0, @@ -256,6 +265,7 @@ static void dpu_hw_intf_get_status( struct dpu_hw_blk_reg_map *c = &intf->hw; s->is_en = DPU_REG_READ(c, INTF_TIMING_ENGINE_EN); + s->is_prog_fetch_en = !!(DPU_REG_READ(c, INTF_CONFIG) & BIT(31)); if (s->is_en) { s->frame_count = DPU_REG_READ(c, INTF_FRAME_COUNT); s->line_count = DPU_REG_READ(c, INTF_LINE_COUNT); diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.h index 0ead64d3f63d..3568be80dab5 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.h @@ -40,6 +40,7 @@ struct intf_prog_fetch { struct intf_status { u8 is_en; /* interface timing engine is enabled or not */ + u8 is_prog_fetch_en; /* interface prog fetch counter is enabled or not */ u32 frame_count; /* frame count since timing engine enabled */ u32 line_count; /* current line count including blanking */ }; diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_top.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_top.h index 8018fff5667a..3aa10c89ca1b 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_top.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_top.h @@ -30,7 +30,7 @@ struct traffic_shaper_cfg { /** * struct split_pipe_cfg - pipe configuration for dual display panels - * @en : Enable/disable dual pipe confguration + * @en : Enable/disable dual pipe configuration * @mode : Panel interface mode * @intf : Interface id for main control path * @split_flush_en: Allows both the paths to be flushed when master path is @@ -76,7 +76,7 @@ struct dpu_vsync_source_cfg { * @setup_traffic_shaper : programs traffic shaper control */ struct dpu_hw_mdp_ops { - /** setup_split_pipe() : Regsiters are not double buffered, thisk + /** setup_split_pipe() : Registers are not double buffered, thisk * function should be called before timing control enable * @mdp : mdp top context driver * @cfg : upper and lower part of pipe configuration diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c index 5a8e3e1fc48c..88e9cc38c13b 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c @@ -14,6 +14,7 @@ #include <drm/drm_crtc.h> #include <drm/drm_file.h> +#include <drm/drm_vblank.h> #include "msm_drv.h" #include "msm_mmu.h" @@ -43,6 +44,8 @@ #define DPU_DEBUGFS_DIR "msm_dpu" #define DPU_DEBUGFS_HWMASKNAME "hw_log_mask" +#define MIN_IB_BW 400000000ULL /* Min ib vote 400MB */ + static int dpu_kms_hw_init(struct msm_kms *kms); static void _dpu_kms_mmu_destroy(struct dpu_kms *dpu_kms); @@ -931,6 +934,8 @@ static int dpu_kms_hw_init(struct msm_kms *kms) DPU_DEBUG("REG_DMA is not defined"); } + dpu_kms_parse_data_bus_icc_path(dpu_kms); + pm_runtime_get_sync(&dpu_kms->pdev->dev); dpu_kms->core_rev = readl_relaxed(dpu_kms->mmio + 0x0); @@ -1020,6 +1025,10 @@ static int dpu_kms_hw_init(struct msm_kms *kms) */ dev->mode_config.allow_fb_modifiers = true; + dev->max_vblank_count = 0xffffffff; + /* Disable vblank irqs aggressively for power-saving */ + dev->vblank_disable_immediate = true; + /* * _dpu_kms_drm_obj_init should create the DRM related objects * i.e. CRTCs, planes, encoders, connectors and so forth @@ -1032,9 +1041,6 @@ static int dpu_kms_hw_init(struct msm_kms *kms) dpu_vbif_init_memtypes(dpu_kms); - if (of_device_is_compatible(dev->dev->of_node, "qcom,sc7180-mdss")) - dpu_kms_parse_data_bus_icc_path(dpu_kms); - pm_runtime_put_sync(&dpu_kms->pdev->dev); return 0; @@ -1191,10 +1197,10 @@ static int __maybe_unused dpu_runtime_resume(struct device *dev) ddev = dpu_kms->dev; + WARN_ON(!(dpu_kms->num_paths)); /* Min vote of BW is required before turning on AXI clk */ for (i = 0; i < dpu_kms->num_paths; i++) - icc_set_bw(dpu_kms->path[i], 0, - dpu_kms->catalog->perf.min_dram_ib); + icc_set_bw(dpu_kms->path[i], 0, Bps_to_icc(MIN_IB_BW)); rc = msm_dss_enable_clk(mp->clk_config, mp->num_clk, true); if (rc) { @@ -1219,6 +1225,9 @@ static const struct dev_pm_ops dpu_pm_ops = { static const struct of_device_id dpu_dt_match[] = { { .compatible = "qcom,sdm845-dpu", }, { .compatible = "qcom,sc7180-dpu", }, + { .compatible = "qcom,sc7280-dpu", }, + { .compatible = "qcom,sm8150-dpu", }, + { .compatible = "qcom,sm8250-dpu", }, {} }; MODULE_DEVICE_TABLE(of, dpu_dt_match); diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_mdss.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_mdss.c index cd4078807db1..06b56fec04e0 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_mdss.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_mdss.c @@ -31,40 +31,8 @@ struct dpu_mdss { void __iomem *mmio; struct dss_module_power mp; struct dpu_irq_controller irq_controller; - struct icc_path *path[2]; - u32 num_paths; }; -static int dpu_mdss_parse_data_bus_icc_path(struct drm_device *dev, - struct dpu_mdss *dpu_mdss) -{ - struct icc_path *path0 = of_icc_get(dev->dev, "mdp0-mem"); - struct icc_path *path1 = of_icc_get(dev->dev, "mdp1-mem"); - - if (IS_ERR_OR_NULL(path0)) - return PTR_ERR_OR_ZERO(path0); - - dpu_mdss->path[0] = path0; - dpu_mdss->num_paths = 1; - - if (!IS_ERR_OR_NULL(path1)) { - dpu_mdss->path[1] = path1; - dpu_mdss->num_paths++; - } - - return 0; -} - -static void dpu_mdss_icc_request_bw(struct msm_mdss *mdss) -{ - struct dpu_mdss *dpu_mdss = to_dpu_mdss(mdss); - int i; - u64 avg_bw = dpu_mdss->num_paths ? MAX_BW / dpu_mdss->num_paths : 0; - - for (i = 0; i < dpu_mdss->num_paths; i++) - icc_set_bw(dpu_mdss->path[i], avg_bw, kBps_to_icc(MAX_BW)); -} - static void dpu_mdss_irq(struct irq_desc *desc) { struct dpu_mdss *dpu_mdss = irq_desc_get_handler_data(desc); @@ -178,8 +146,6 @@ static int dpu_mdss_enable(struct msm_mdss *mdss) struct dss_module_power *mp = &dpu_mdss->mp; int ret; - dpu_mdss_icc_request_bw(mdss); - ret = msm_dss_enable_clk(mp->clk_config, mp->num_clk, true); if (ret) { DPU_ERROR("clock enable failed, ret:%d\n", ret); @@ -204,6 +170,9 @@ static int dpu_mdss_enable(struct msm_mdss *mdss) case DPU_HW_VER_620: writel_relaxed(0x1e, dpu_mdss->mmio + UBWC_STATIC); break; + case DPU_HW_VER_720: + writel_relaxed(0x101e, dpu_mdss->mmio + UBWC_STATIC); + break; } return ret; @@ -213,15 +182,12 @@ static int dpu_mdss_disable(struct msm_mdss *mdss) { struct dpu_mdss *dpu_mdss = to_dpu_mdss(mdss); struct dss_module_power *mp = &dpu_mdss->mp; - int ret, i; + int ret; ret = msm_dss_enable_clk(mp->clk_config, mp->num_clk, false); if (ret) DPU_ERROR("clock disable failed, ret:%d\n", ret); - for (i = 0; i < dpu_mdss->num_paths; i++) - icc_set_bw(dpu_mdss->path[i], 0, 0); - return ret; } @@ -232,7 +198,6 @@ static void dpu_mdss_destroy(struct drm_device *dev) struct dpu_mdss *dpu_mdss = to_dpu_mdss(priv->mdss); struct dss_module_power *mp = &dpu_mdss->mp; int irq; - int i; pm_runtime_suspend(dev->dev); pm_runtime_disable(dev->dev); @@ -242,9 +207,6 @@ static void dpu_mdss_destroy(struct drm_device *dev) msm_dss_put_clk(mp->clk_config, mp->num_clk); devm_kfree(&pdev->dev, mp->clk_config); - for (i = 0; i < dpu_mdss->num_paths; i++) - icc_put(dpu_mdss->path[i]); - if (dpu_mdss->mmio) devm_iounmap(&pdev->dev, dpu_mdss->mmio); dpu_mdss->mmio = NULL; @@ -276,12 +238,6 @@ int dpu_mdss_init(struct drm_device *dev) DRM_DEBUG("mapped mdss address space @%pK\n", dpu_mdss->mmio); - if (!of_device_is_compatible(dev->dev->of_node, "qcom,sc7180-mdss")) { - ret = dpu_mdss_parse_data_bus_icc_path(dev, dpu_mdss); - if (ret) - return ret; - } - mp = &dpu_mdss->mp; ret = msm_dss_parse_clock(pdev, mp); if (ret) { @@ -307,8 +263,6 @@ int dpu_mdss_init(struct drm_device *dev) pm_runtime_enable(dev->dev); - dpu_mdss_icc_request_bw(priv->mdss); - return ret; irq_error: diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_cmd_encoder.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_cmd_encoder.c index ff2c1d583c79..ec6c7b09865e 100644 --- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_cmd_encoder.c +++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_cmd_encoder.c @@ -20,7 +20,7 @@ static int pingpong_tearcheck_setup(struct drm_encoder *encoder, { struct mdp5_kms *mdp5_kms = get_kms(encoder); struct device *dev = encoder->dev->dev; - u32 total_lines_x100, vclks_line, cfg; + u32 total_lines, vclks_line, cfg; long vsync_clk_speed; struct mdp5_hw_mixer *mixer = mdp5_crtc_get_mixer(encoder->crtc); int pp_id = mixer->pp; @@ -30,8 +30,8 @@ static int pingpong_tearcheck_setup(struct drm_encoder *encoder, return -EINVAL; } - total_lines_x100 = mode->vtotal * drm_mode_vrefresh(mode); - if (!total_lines_x100) { + total_lines = mode->vtotal * drm_mode_vrefresh(mode); + if (!total_lines) { DRM_DEV_ERROR(dev, "%s: vtotal(%d) or vrefresh(%d) is 0\n", __func__, mode->vtotal, drm_mode_vrefresh(mode)); return -EINVAL; @@ -43,15 +43,23 @@ static int pingpong_tearcheck_setup(struct drm_encoder *encoder, vsync_clk_speed); return -EINVAL; } - vclks_line = vsync_clk_speed * 100 / total_lines_x100; + vclks_line = vsync_clk_speed / total_lines; cfg = MDP5_PP_SYNC_CONFIG_VSYNC_COUNTER_EN | MDP5_PP_SYNC_CONFIG_VSYNC_IN_EN; cfg |= MDP5_PP_SYNC_CONFIG_VSYNC_COUNT(vclks_line); + /* + * Tearcheck emits a blanking signal every vclks_line * vtotal * 2 ticks on + * the vsync_clk equating to roughly half the desired panel refresh rate. + * This is only necessary as stability fallback if interrupts from the + * panel arrive too late or not at all, but is currently used by default + * because these panel interrupts are not wired up yet. + */ mdp5_write(mdp5_kms, REG_MDP5_PP_SYNC_CONFIG_VSYNC(pp_id), cfg); mdp5_write(mdp5_kms, - REG_MDP5_PP_SYNC_CONFIG_HEIGHT(pp_id), 0xfff0); + REG_MDP5_PP_SYNC_CONFIG_HEIGHT(pp_id), (2 * mode->vtotal)); + mdp5_write(mdp5_kms, REG_MDP5_PP_VSYNC_INIT_VAL(pp_id), mode->vdisplay); mdp5_write(mdp5_kms, REG_MDP5_PP_RD_PTR_IRQ(pp_id), mode->vdisplay + 1); @@ -59,6 +67,7 @@ static int pingpong_tearcheck_setup(struct drm_encoder *encoder, mdp5_write(mdp5_kms, REG_MDP5_PP_SYNC_THRESH(pp_id), MDP5_PP_SYNC_THRESH_START(4) | MDP5_PP_SYNC_THRESH_CONTINUE(4)); + mdp5_write(mdp5_kms, REG_MDP5_PP_AUTOREFRESH_CONFIG(pp_id), 0x0); return 0; } diff --git a/drivers/gpu/drm/msm/dp/dp_aux.c b/drivers/gpu/drm/msm/dp/dp_aux.c index 1c6e1d2b947c..7c22bfe0fc7d 100644 --- a/drivers/gpu/drm/msm/dp/dp_aux.c +++ b/drivers/gpu/drm/msm/dp/dp_aux.c @@ -32,6 +32,8 @@ struct dp_aux_private { struct drm_dp_aux dp_aux; }; +#define MAX_AUX_RETRIES 5 + static const char *dp_aux_get_error(u32 aux_error) { switch (aux_error) { @@ -377,6 +379,11 @@ static ssize_t dp_aux_transfer(struct drm_dp_aux *dp_aux, ret = dp_aux_cmd_fifo_tx(aux, msg); if (ret < 0) { + if (aux->native) { + aux->retry_cnt++; + if (!(aux->retry_cnt % MAX_AUX_RETRIES)) + dp_catalog_aux_update_cfg(aux->catalog); + } usleep_range(400, 500); /* at least 400us to next try */ goto unlock_exit; } diff --git a/drivers/gpu/drm/msm/dp/dp_debug.c b/drivers/gpu/drm/msm/dp/dp_debug.c index 84670bcdcfea..2f6247e80e9d 100644 --- a/drivers/gpu/drm/msm/dp/dp_debug.c +++ b/drivers/gpu/drm/msm/dp/dp_debug.c @@ -226,7 +226,7 @@ static int dp_test_data_show(struct seq_file *m, void *data) debug->link->test_video.test_h_width); seq_printf(m, "vdisplay: %d\n", debug->link->test_video.test_v_height); - seq_printf(m, "bpc: %u\n", + seq_printf(m, "bpc: %u\n", dp_link_bit_depth_to_bpc(bpc)); } else seq_puts(m, "0"); @@ -368,44 +368,21 @@ static int dp_debug_init(struct dp_debug *dp_debug, struct drm_minor *minor) int rc = 0; struct dp_debug_private *debug = container_of(dp_debug, struct dp_debug_private, dp_debug); - struct dentry *file; - struct dentry *test_active; - struct dentry *test_data, *test_type; - file = debugfs_create_file("dp_debug", 0444, minor->debugfs_root, + debugfs_create_file("dp_debug", 0444, minor->debugfs_root, debug, &dp_debug_fops); - if (IS_ERR_OR_NULL(file)) { - rc = PTR_ERR(file); - DRM_ERROR("[%s] debugfs create file failed, rc=%d\n", - DEBUG_NAME, rc); - } - test_active = debugfs_create_file("msm_dp_test_active", 0444, + debugfs_create_file("msm_dp_test_active", 0444, minor->debugfs_root, debug, &test_active_fops); - if (IS_ERR_OR_NULL(test_active)) { - rc = PTR_ERR(test_active); - DRM_ERROR("[%s] debugfs test_active failed, rc=%d\n", - DEBUG_NAME, rc); - } - test_data = debugfs_create_file("msm_dp_test_data", 0444, + debugfs_create_file("msm_dp_test_data", 0444, minor->debugfs_root, debug, &dp_test_data_fops); - if (IS_ERR_OR_NULL(test_data)) { - rc = PTR_ERR(test_data); - DRM_ERROR("[%s] debugfs test_data failed, rc=%d\n", - DEBUG_NAME, rc); - } - test_type = debugfs_create_file("msm_dp_test_type", 0444, + debugfs_create_file("msm_dp_test_type", 0444, minor->debugfs_root, debug, &dp_test_type_fops); - if (IS_ERR_OR_NULL(test_type)) { - rc = PTR_ERR(test_type); - DRM_ERROR("[%s] debugfs test_type failed, rc=%d\n", - DEBUG_NAME, rc); - } debug->root = minor->debugfs_root; diff --git a/drivers/gpu/drm/msm/dp/dp_hpd.c b/drivers/gpu/drm/msm/dp/dp_hpd.c index 5b8fe32022b5..e1c90fa47411 100644 --- a/drivers/gpu/drm/msm/dp/dp_hpd.c +++ b/drivers/gpu/drm/msm/dp/dp_hpd.c @@ -34,8 +34,8 @@ int dp_hpd_connect(struct dp_usbpd *dp_usbpd, bool hpd) dp_usbpd->hpd_high = hpd; - if (!hpd_priv->dp_cb && !hpd_priv->dp_cb->configure - && !hpd_priv->dp_cb->disconnect) { + if (!hpd_priv->dp_cb || !hpd_priv->dp_cb->configure + || !hpd_priv->dp_cb->disconnect) { pr_err("hpd dp_cb not initialized\n"); return -EINVAL; } diff --git a/drivers/gpu/drm/msm/dp/dp_power.c b/drivers/gpu/drm/msm/dp/dp_power.c index 9c4ea00a5f2a..3961ba4efc3c 100644 --- a/drivers/gpu/drm/msm/dp/dp_power.c +++ b/drivers/gpu/drm/msm/dp/dp_power.c @@ -269,7 +269,7 @@ int dp_power_clk_enable(struct dp_power *dp_power, DRM_ERROR("failed to '%s' clks for: %s. err=%d\n", enable ? "enable" : "disable", dp_parser_pm_name(pm_type), rc); - return rc; + return rc; } if (pm_type == DP_CORE_PM) diff --git a/drivers/gpu/drm/msm/dsi/dsi.h b/drivers/gpu/drm/msm/dsi/dsi.h index 78ef5d4ed922..7abfeab08165 100644 --- a/drivers/gpu/drm/msm/dsi/dsi.h +++ b/drivers/gpu/drm/msm/dsi/dsi.h @@ -23,18 +23,6 @@ struct msm_dsi_phy_shared_timings; struct msm_dsi_phy_clk_request; -enum msm_dsi_phy_type { - MSM_DSI_PHY_28NM_HPM, - MSM_DSI_PHY_28NM_LP, - MSM_DSI_PHY_20NM, - MSM_DSI_PHY_28NM_8960, - MSM_DSI_PHY_14NM, - MSM_DSI_PHY_10NM, - MSM_DSI_PHY_7NM, - MSM_DSI_PHY_7NM_V4_1, - MSM_DSI_PHY_MAX -}; - enum msm_dsi_phy_usecase { MSM_DSI_PHY_STANDALONE, MSM_DSI_PHY_MASTER, @@ -104,45 +92,6 @@ static inline bool msm_dsi_device_connected(struct msm_dsi *msm_dsi) struct drm_encoder *msm_dsi_get_encoder(struct msm_dsi *msm_dsi); -/* dsi pll */ -struct msm_dsi_pll; -#ifdef CONFIG_DRM_MSM_DSI_PLL -struct msm_dsi_pll *msm_dsi_pll_init(struct platform_device *pdev, - enum msm_dsi_phy_type type, int dsi_id); -void msm_dsi_pll_destroy(struct msm_dsi_pll *pll); -int msm_dsi_pll_get_clk_provider(struct msm_dsi_pll *pll, - struct clk **byte_clk_provider, struct clk **pixel_clk_provider); -void msm_dsi_pll_save_state(struct msm_dsi_pll *pll); -int msm_dsi_pll_restore_state(struct msm_dsi_pll *pll); -int msm_dsi_pll_set_usecase(struct msm_dsi_pll *pll, - enum msm_dsi_phy_usecase uc); -#else -static inline struct msm_dsi_pll *msm_dsi_pll_init(struct platform_device *pdev, - enum msm_dsi_phy_type type, int id) { - return ERR_PTR(-ENODEV); -} -static inline void msm_dsi_pll_destroy(struct msm_dsi_pll *pll) -{ -} -static inline int msm_dsi_pll_get_clk_provider(struct msm_dsi_pll *pll, - struct clk **byte_clk_provider, struct clk **pixel_clk_provider) -{ - return -ENODEV; -} -static inline void msm_dsi_pll_save_state(struct msm_dsi_pll *pll) -{ -} -static inline int msm_dsi_pll_restore_state(struct msm_dsi_pll *pll) -{ - return 0; -} -static inline int msm_dsi_pll_set_usecase(struct msm_dsi_pll *pll, - enum msm_dsi_phy_usecase uc) -{ - return -ENODEV; -} -#endif - /* dsi host */ struct msm_dsi_host; int msm_dsi_host_xfer_prepare(struct mipi_dsi_host *host, @@ -169,7 +118,7 @@ struct drm_bridge *msm_dsi_host_get_bridge(struct mipi_dsi_host *host); int msm_dsi_host_register(struct mipi_dsi_host *host, bool check_defer); void msm_dsi_host_unregister(struct mipi_dsi_host *host); int msm_dsi_host_set_src_pll(struct mipi_dsi_host *host, - struct msm_dsi_pll *src_pll); + struct msm_dsi_phy *src_phy); void msm_dsi_host_reset_phy(struct mipi_dsi_host *host); void msm_dsi_host_get_phy_clk_req(struct mipi_dsi_host *host, struct msm_dsi_phy_clk_request *clk_req, @@ -213,14 +162,17 @@ struct msm_dsi_phy_clk_request { void msm_dsi_phy_driver_register(void); void msm_dsi_phy_driver_unregister(void); -int msm_dsi_phy_enable(struct msm_dsi_phy *phy, int src_pll_id, +int msm_dsi_phy_enable(struct msm_dsi_phy *phy, struct msm_dsi_phy_clk_request *clk_req); void msm_dsi_phy_disable(struct msm_dsi_phy *phy); void msm_dsi_phy_get_shared_timings(struct msm_dsi_phy *phy, struct msm_dsi_phy_shared_timings *shared_timing); -struct msm_dsi_pll *msm_dsi_phy_get_pll(struct msm_dsi_phy *phy); void msm_dsi_phy_set_usecase(struct msm_dsi_phy *phy, enum msm_dsi_phy_usecase uc); +int msm_dsi_phy_get_clk_provider(struct msm_dsi_phy *phy, + struct clk **byte_clk_provider, struct clk **pixel_clk_provider); +void msm_dsi_phy_pll_save_state(struct msm_dsi_phy *phy); +int msm_dsi_phy_pll_restore_state(struct msm_dsi_phy *phy); #endif /* __DSI_CONNECTOR_H__ */ diff --git a/drivers/gpu/drm/msm/dsi/dsi_cfg.c b/drivers/gpu/drm/msm/dsi/dsi_cfg.c index b2ff68a15791..f3f1c03c7db9 100644 --- a/drivers/gpu/drm/msm/dsi/dsi_cfg.c +++ b/drivers/gpu/drm/msm/dsi/dsi_cfg.c @@ -106,12 +106,8 @@ static const struct msm_dsi_config msm8994_dsi_cfg = { .num_dsi = 2, }; -/* - * TODO: core_mmss_clk fails to enable for some reason, but things work fine - * without it too. Figure out why it doesn't enable and uncomment below - */ static const char * const dsi_8996_bus_clk_names[] = { - "mdp_core", "iface", "bus", /* "core_mmss", */ + "mdp_core", "iface", "bus", "core_mmss", }; static const struct msm_dsi_config msm8996_dsi_cfg = { diff --git a/drivers/gpu/drm/msm/dsi/dsi_host.c b/drivers/gpu/drm/msm/dsi/dsi_host.c index ab281cba0f08..8a10e4343281 100644 --- a/drivers/gpu/drm/msm/dsi/dsi_host.c +++ b/drivers/gpu/drm/msm/dsi/dsi_host.c @@ -1826,8 +1826,6 @@ int msm_dsi_host_init(struct msm_dsi *msm_dsi) msm_host = devm_kzalloc(&pdev->dev, sizeof(*msm_host), GFP_KERNEL); if (!msm_host) { - pr_err("%s: FAILED: cannot alloc dsi host\n", - __func__); ret = -ENOMEM; goto fail; } @@ -2226,13 +2224,13 @@ void msm_dsi_host_cmd_xfer_commit(struct mipi_dsi_host *host, u32 dma_base, } int msm_dsi_host_set_src_pll(struct mipi_dsi_host *host, - struct msm_dsi_pll *src_pll) + struct msm_dsi_phy *src_phy) { struct msm_dsi_host *msm_host = to_msm_dsi_host(host); struct clk *byte_clk_provider, *pixel_clk_provider; int ret; - ret = msm_dsi_pll_get_clk_provider(src_pll, + ret = msm_dsi_phy_get_clk_provider(src_phy, &byte_clk_provider, &pixel_clk_provider); if (ret) { pr_info("%s: can't get provider from pll, don't set parent\n", diff --git a/drivers/gpu/drm/msm/dsi/dsi_manager.c b/drivers/gpu/drm/msm/dsi/dsi_manager.c index 1d28dfba2c9b..cd016576e8c5 100644 --- a/drivers/gpu/drm/msm/dsi/dsi_manager.c +++ b/drivers/gpu/drm/msm/dsi/dsi_manager.c @@ -70,7 +70,6 @@ static int dsi_mgr_setup_components(int id) struct msm_dsi *other_dsi = dsi_mgr_get_other_dsi(id); struct msm_dsi *clk_master_dsi = dsi_mgr_get_dsi(DSI_CLOCK_MASTER); struct msm_dsi *clk_slave_dsi = dsi_mgr_get_dsi(DSI_CLOCK_SLAVE); - struct msm_dsi_pll *src_pll; int ret; if (!IS_DUAL_DSI()) { @@ -79,10 +78,7 @@ static int dsi_mgr_setup_components(int id) return ret; msm_dsi_phy_set_usecase(msm_dsi->phy, MSM_DSI_PHY_STANDALONE); - src_pll = msm_dsi_phy_get_pll(msm_dsi->phy); - if (IS_ERR(src_pll)) - return PTR_ERR(src_pll); - ret = msm_dsi_host_set_src_pll(msm_dsi->host, src_pll); + ret = msm_dsi_host_set_src_pll(msm_dsi->host, msm_dsi->phy); } else if (!other_dsi) { ret = 0; } else { @@ -109,19 +105,16 @@ static int dsi_mgr_setup_components(int id) MSM_DSI_PHY_MASTER); msm_dsi_phy_set_usecase(clk_slave_dsi->phy, MSM_DSI_PHY_SLAVE); - src_pll = msm_dsi_phy_get_pll(clk_master_dsi->phy); - if (IS_ERR(src_pll)) - return PTR_ERR(src_pll); - ret = msm_dsi_host_set_src_pll(msm_dsi->host, src_pll); + ret = msm_dsi_host_set_src_pll(msm_dsi->host, clk_master_dsi->phy); if (ret) return ret; - ret = msm_dsi_host_set_src_pll(other_dsi->host, src_pll); + ret = msm_dsi_host_set_src_pll(other_dsi->host, clk_master_dsi->phy); } return ret; } -static int enable_phy(struct msm_dsi *msm_dsi, int src_pll_id, +static int enable_phy(struct msm_dsi *msm_dsi, struct msm_dsi_phy_shared_timings *shared_timings) { struct msm_dsi_phy_clk_request clk_req; @@ -130,7 +123,7 @@ static int enable_phy(struct msm_dsi *msm_dsi, int src_pll_id, msm_dsi_host_get_phy_clk_req(msm_dsi->host, &clk_req, is_dual_dsi); - ret = msm_dsi_phy_enable(msm_dsi->phy, src_pll_id, &clk_req); + ret = msm_dsi_phy_enable(msm_dsi->phy, &clk_req); msm_dsi_phy_get_shared_timings(msm_dsi->phy, shared_timings); return ret; @@ -143,7 +136,6 @@ dsi_mgr_phy_enable(int id, struct msm_dsi *msm_dsi = dsi_mgr_get_dsi(id); struct msm_dsi *mdsi = dsi_mgr_get_dsi(DSI_CLOCK_MASTER); struct msm_dsi *sdsi = dsi_mgr_get_dsi(DSI_CLOCK_SLAVE); - int src_pll_id = IS_DUAL_DSI() ? DSI_CLOCK_MASTER : id; int ret; /* In case of dual DSI, some registers in PHY1 have been programmed @@ -156,11 +148,11 @@ dsi_mgr_phy_enable(int id, msm_dsi_host_reset_phy(mdsi->host); msm_dsi_host_reset_phy(sdsi->host); - ret = enable_phy(mdsi, src_pll_id, + ret = enable_phy(mdsi, &shared_timings[DSI_CLOCK_MASTER]); if (ret) return ret; - ret = enable_phy(sdsi, src_pll_id, + ret = enable_phy(sdsi, &shared_timings[DSI_CLOCK_SLAVE]); if (ret) { msm_dsi_phy_disable(mdsi->phy); @@ -169,7 +161,7 @@ dsi_mgr_phy_enable(int id, } } else { msm_dsi_host_reset_phy(msm_dsi->host); - ret = enable_phy(msm_dsi, src_pll_id, &shared_timings[id]); + ret = enable_phy(msm_dsi, &shared_timings[id]); if (ret) return ret; } @@ -505,7 +497,6 @@ static void dsi_mgr_bridge_post_disable(struct drm_bridge *bridge) struct msm_dsi *msm_dsi1 = dsi_mgr_get_dsi(DSI_1); struct mipi_dsi_host *host = msm_dsi->host; struct drm_panel *panel = msm_dsi->panel; - struct msm_dsi_pll *src_pll; bool is_dual_dsi = IS_DUAL_DSI(); int ret; @@ -539,9 +530,8 @@ static void dsi_mgr_bridge_post_disable(struct drm_bridge *bridge) id, ret); } - /* Save PLL status if it is a clock source */ - src_pll = msm_dsi_phy_get_pll(msm_dsi->phy); - msm_dsi_pll_save_state(src_pll); + /* Save PHY status if it is a clock source */ + msm_dsi_phy_pll_save_state(msm_dsi->phy); ret = msm_dsi_host_power_off(host); if (ret) diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c index e8c1a727179c..f0a2ddf96a4b 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c @@ -3,6 +3,7 @@ * Copyright (c) 2015, The Linux Foundation. All rights reserved. */ +#include <linux/clk-provider.h> #include <linux/platform_device.h> #include "dsi_phy.h" @@ -460,23 +461,6 @@ int msm_dsi_dphy_timing_calc_v4(struct msm_dsi_dphy_timing *timing, return 0; } -void msm_dsi_phy_set_src_pll(struct msm_dsi_phy *phy, int pll_id, u32 reg, - u32 bit_mask) -{ - int phy_id = phy->id; - u32 val; - - if ((phy_id >= DSI_MAX) || (pll_id >= DSI_MAX)) - return; - - val = dsi_phy_read(phy->base + reg); - - if (phy->cfg->src_pll_truthtable[phy_id][pll_id]) - dsi_phy_write(phy->base + reg, val | bit_mask); - else - dsi_phy_write(phy->base + reg, val & (~bit_mask)); -} - static int dsi_phy_regulator_init(struct msm_dsi_phy *phy) { struct regulator_bulk_data *s = phy->supplies; @@ -637,24 +621,6 @@ static int dsi_phy_get_id(struct msm_dsi_phy *phy) return -EINVAL; } -int msm_dsi_phy_init_common(struct msm_dsi_phy *phy) -{ - struct platform_device *pdev = phy->pdev; - int ret = 0; - - phy->reg_base = msm_ioremap(pdev, "dsi_phy_regulator", - "DSI_PHY_REG"); - if (IS_ERR(phy->reg_base)) { - DRM_DEV_ERROR(&pdev->dev, "%s: failed to map phy regulator base\n", - __func__); - ret = -ENOMEM; - goto fail; - } - -fail: - return ret; -} - static int dsi_phy_driver_probe(struct platform_device *pdev) { struct msm_dsi_phy *phy; @@ -670,6 +636,14 @@ static int dsi_phy_driver_probe(struct platform_device *pdev) if (!match) return -ENODEV; + phy->provided_clocks = devm_kzalloc(dev, + struct_size(phy->provided_clocks, hws, NUM_PROVIDED_CLKS), + GFP_KERNEL); + if (!phy->provided_clocks) + return -ENOMEM; + + phy->provided_clocks->num = NUM_PROVIDED_CLKS; + phy->cfg = match->data; phy->pdev = pdev; @@ -691,6 +665,31 @@ static int dsi_phy_driver_probe(struct platform_device *pdev) goto fail; } + phy->pll_base = msm_ioremap(pdev, "dsi_pll", "DSI_PLL"); + if (IS_ERR(phy->pll_base)) { + DRM_DEV_ERROR(&pdev->dev, "%s: failed to map pll base\n", __func__); + ret = -ENOMEM; + goto fail; + } + + if (phy->cfg->has_phy_lane) { + phy->lane_base = msm_ioremap(pdev, "dsi_phy_lane", "DSI_PHY_LANE"); + if (IS_ERR(phy->lane_base)) { + DRM_DEV_ERROR(&pdev->dev, "%s: failed to map phy lane base\n", __func__); + ret = -ENOMEM; + goto fail; + } + } + + if (phy->cfg->has_phy_regulator) { + phy->reg_base = msm_ioremap(pdev, "dsi_phy_regulator", "DSI_PHY_REG"); + if (IS_ERR(phy->reg_base)) { + DRM_DEV_ERROR(&pdev->dev, "%s: failed to map phy regulator base\n", __func__); + ret = -ENOMEM; + goto fail; + } + } + ret = dsi_phy_regulator_init(phy); if (ret) goto fail; @@ -702,12 +701,6 @@ static int dsi_phy_driver_probe(struct platform_device *pdev) goto fail; } - if (phy->cfg->ops.init) { - ret = phy->cfg->ops.init(phy); - if (ret) - goto fail; - } - /* PLL init will call into clk_register which requires * register access, so we need to enable power and ahb clock. */ @@ -715,12 +708,21 @@ static int dsi_phy_driver_probe(struct platform_device *pdev) if (ret) goto fail; - phy->pll = msm_dsi_pll_init(pdev, phy->cfg->type, phy->id); - if (IS_ERR_OR_NULL(phy->pll)) { - DRM_DEV_INFO(dev, - "%s: pll init failed: %ld, need separate pll clk driver\n", - __func__, PTR_ERR(phy->pll)); - phy->pll = NULL; + if (phy->cfg->ops.pll_init) { + ret = phy->cfg->ops.pll_init(phy); + if (ret) { + DRM_DEV_INFO(dev, + "%s: pll init failed: %d, need separate pll clk driver\n", + __func__, ret); + goto fail; + } + } + + ret = devm_of_clk_add_hw_provider(dev, of_clk_hw_onecell_get, + phy->provided_clocks); + if (ret) { + DRM_DEV_ERROR(dev, "%s: failed to register clk provider: %d\n", __func__, ret); + goto fail; } dsi_phy_disable_resource(phy); @@ -733,23 +735,8 @@ fail: return ret; } -static int dsi_phy_driver_remove(struct platform_device *pdev) -{ - struct msm_dsi_phy *phy = platform_get_drvdata(pdev); - - if (phy && phy->pll) { - msm_dsi_pll_destroy(phy->pll); - phy->pll = NULL; - } - - platform_set_drvdata(pdev, NULL); - - return 0; -} - static struct platform_driver dsi_phy_platform_driver = { .probe = dsi_phy_driver_probe, - .remove = dsi_phy_driver_remove, .driver = { .name = "msm_dsi_phy", .of_match_table = dsi_phy_dt_match, @@ -766,7 +753,7 @@ void __exit msm_dsi_phy_driver_unregister(void) platform_driver_unregister(&dsi_phy_platform_driver); } -int msm_dsi_phy_enable(struct msm_dsi_phy *phy, int src_pll_id, +int msm_dsi_phy_enable(struct msm_dsi_phy *phy, struct msm_dsi_phy_clk_request *clk_req) { struct device *dev = &phy->pdev->dev; @@ -789,7 +776,7 @@ int msm_dsi_phy_enable(struct msm_dsi_phy *phy, int src_pll_id, goto reg_en_fail; } - ret = phy->cfg->ops.enable(phy, src_pll_id, clk_req); + ret = phy->cfg->ops.enable(phy, clk_req); if (ret) { DRM_DEV_ERROR(dev, "%s: phy enable failed, %d\n", __func__, ret); goto phy_en_fail; @@ -802,9 +789,9 @@ int msm_dsi_phy_enable(struct msm_dsi_phy *phy, int src_pll_id, * source. */ if (phy->usecase != MSM_DSI_PHY_SLAVE) { - ret = msm_dsi_pll_restore_state(phy->pll); + ret = msm_dsi_phy_pll_restore_state(phy); if (ret) { - DRM_DEV_ERROR(dev, "%s: failed to restore pll state, %d\n", + DRM_DEV_ERROR(dev, "%s: failed to restore phy state, %d\n", __func__, ret); goto pll_restor_fail; } @@ -841,17 +828,43 @@ void msm_dsi_phy_get_shared_timings(struct msm_dsi_phy *phy, sizeof(*shared_timings)); } -struct msm_dsi_pll *msm_dsi_phy_get_pll(struct msm_dsi_phy *phy) -{ - if (!phy) - return NULL; - - return phy->pll; -} - void msm_dsi_phy_set_usecase(struct msm_dsi_phy *phy, enum msm_dsi_phy_usecase uc) { if (phy) phy->usecase = uc; } + +int msm_dsi_phy_get_clk_provider(struct msm_dsi_phy *phy, + struct clk **byte_clk_provider, struct clk **pixel_clk_provider) +{ + if (byte_clk_provider) + *byte_clk_provider = phy->provided_clocks->hws[DSI_BYTE_PLL_CLK]->clk; + if (pixel_clk_provider) + *pixel_clk_provider = phy->provided_clocks->hws[DSI_PIXEL_PLL_CLK]->clk; + + return -EINVAL; +} + +void msm_dsi_phy_pll_save_state(struct msm_dsi_phy *phy) +{ + if (phy->cfg->ops.save_pll_state) { + phy->cfg->ops.save_pll_state(phy); + phy->state_saved = true; + } +} + +int msm_dsi_phy_pll_restore_state(struct msm_dsi_phy *phy) +{ + int ret; + + if (phy->cfg->ops.restore_pll_state && phy->state_saved) { + ret = phy->cfg->ops.restore_pll_state(phy); + if (ret) + return ret; + + phy->state_saved = false; + } + + return 0; +} diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h index d2bd74b6f357..94a77ac364d3 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h @@ -6,37 +6,38 @@ #ifndef __DSI_PHY_H__ #define __DSI_PHY_H__ +#include <linux/clk-provider.h> +#include <linux/delay.h> #include <linux/regulator/consumer.h> #include "dsi.h" #define dsi_phy_read(offset) msm_readl((offset)) #define dsi_phy_write(offset, data) msm_writel((data), (offset)) - -/* v3.0.0 10nm implementation that requires the old timings settings */ -#define V3_0_0_10NM_OLD_TIMINGS_QUIRK BIT(0) +#define dsi_phy_write_udelay(offset, data, delay_us) { msm_writel((data), (offset)); udelay(delay_us); } +#define dsi_phy_write_ndelay(offset, data, delay_ns) { msm_writel((data), (offset)); ndelay(delay_ns); } struct msm_dsi_phy_ops { - int (*init) (struct msm_dsi_phy *phy); - int (*enable)(struct msm_dsi_phy *phy, int src_pll_id, + int (*pll_init)(struct msm_dsi_phy *phy); + int (*enable)(struct msm_dsi_phy *phy, struct msm_dsi_phy_clk_request *clk_req); void (*disable)(struct msm_dsi_phy *phy); + void (*save_pll_state)(struct msm_dsi_phy *phy); + int (*restore_pll_state)(struct msm_dsi_phy *phy); }; struct msm_dsi_phy_cfg { - enum msm_dsi_phy_type type; struct dsi_reg_config reg_cfg; struct msm_dsi_phy_ops ops; - /* - * Each cell {phy_id, pll_id} of the truth table indicates - * if the source PLL selection bit should be set for each PHY. - * Fill default H/W values in illegal cells, eg. cell {0, 1}. - */ - bool src_pll_truthtable[DSI_MAX][DSI_MAX]; + unsigned long min_pll_rate; + unsigned long max_pll_rate; + const resource_size_t io_start[DSI_MAX]; const int num_dsi_phy; const int quirks; + bool has_phy_regulator; + bool has_phy_lane; }; extern const struct msm_dsi_phy_cfg dsi_phy_28nm_hpm_cfgs; @@ -74,9 +75,14 @@ struct msm_dsi_dphy_timing { u8 hs_halfbyte_en_ckln; }; +#define DSI_BYTE_PLL_CLK 0 +#define DSI_PIXEL_PLL_CLK 1 +#define NUM_PROVIDED_CLKS 2 + struct msm_dsi_phy { struct platform_device *pdev; void __iomem *base; + void __iomem *pll_base; void __iomem *reg_base; void __iomem *lane_base; int id; @@ -90,7 +96,12 @@ struct msm_dsi_phy { enum msm_dsi_phy_usecase usecase; bool regulator_ldo_mode; - struct msm_dsi_pll *pll; + struct clk_hw *vco_hw; + bool pll_on; + + struct clk_hw_onecell_data *provided_clocks; + + bool state_saved; }; /* @@ -104,9 +115,5 @@ int msm_dsi_dphy_timing_calc_v3(struct msm_dsi_dphy_timing *timing, struct msm_dsi_phy_clk_request *clk_req); int msm_dsi_dphy_timing_calc_v4(struct msm_dsi_dphy_timing *timing, struct msm_dsi_phy_clk_request *clk_req); -void msm_dsi_phy_set_src_pll(struct msm_dsi_phy *phy, int pll_id, u32 reg, - u32 bit_mask); -int msm_dsi_phy_init_common(struct msm_dsi_phy *phy); #endif /* __DSI_PHY_H__ */ - diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_10nm.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_10nm.c index d1b92d4dc197..34bc93548fcf 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_10nm.c +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_10nm.c @@ -3,11 +3,715 @@ * Copyright (c) 2018, The Linux Foundation */ +#include <linux/clk.h> +#include <linux/clk-provider.h> #include <linux/iopoll.h> #include "dsi_phy.h" #include "dsi.xml.h" +/* + * DSI PLL 10nm - clock diagram (eg: DSI0): + * + * dsi0_pll_out_div_clk dsi0_pll_bit_clk + * | | + * | | + * +---------+ | +----------+ | +----+ + * dsi0vco_clk ---| out_div |--o--| divl_3_0 |--o--| /8 |-- dsi0_phy_pll_out_byteclk + * +---------+ | +----------+ | +----+ + * | | + * | | dsi0_pll_by_2_bit_clk + * | | | + * | | +----+ | |\ dsi0_pclk_mux + * | |--| /2 |--o--| \ | + * | | +----+ | \ | +---------+ + * | --------------| |--o--| div_7_4 |-- dsi0_phy_pll_out_dsiclk + * |------------------------------| / +---------+ + * | +-----+ | / + * -----------| /4? |--o----------|/ + * +-----+ | | + * | |dsiclk_sel + * | + * dsi0_pll_post_out_div_clk + */ + +#define VCO_REF_CLK_RATE 19200000 +#define FRAC_BITS 18 + +/* v3.0.0 10nm implementation that requires the old timings settings */ +#define DSI_PHY_10NM_QUIRK_OLD_TIMINGS BIT(0) + +struct dsi_pll_config { + bool enable_ssc; + bool ssc_center; + u32 ssc_freq; + u32 ssc_offset; + u32 ssc_adj_per; + + /* out */ + u32 pll_prop_gain_rate; + u32 decimal_div_start; + u32 frac_div_start; + u32 pll_clock_inverters; + u32 ssc_stepsize; + u32 ssc_div_per; +}; + +struct pll_10nm_cached_state { + unsigned long vco_rate; + u8 bit_clk_div; + u8 pix_clk_div; + u8 pll_out_div; + u8 pll_mux; +}; + +struct dsi_pll_10nm { + struct clk_hw clk_hw; + + struct msm_dsi_phy *phy; + + u64 vco_current_rate; + + /* protects REG_DSI_10nm_PHY_CMN_CLK_CFG0 register */ + spinlock_t postdiv_lock; + + struct pll_10nm_cached_state cached_state; + + struct dsi_pll_10nm *slave; +}; + +#define to_pll_10nm(x) container_of(x, struct dsi_pll_10nm, clk_hw) + +/* + * Global list of private DSI PLL struct pointers. We need this for Dual DSI + * mode, where the master PLL's clk_ops needs access the slave's private data + */ +static struct dsi_pll_10nm *pll_10nm_list[DSI_MAX]; + +static void dsi_pll_setup_config(struct dsi_pll_config *config) +{ + config->ssc_freq = 31500; + config->ssc_offset = 5000; + config->ssc_adj_per = 2; + + config->enable_ssc = false; + config->ssc_center = false; +} + +static void dsi_pll_calc_dec_frac(struct dsi_pll_10nm *pll, struct dsi_pll_config *config) +{ + u64 fref = VCO_REF_CLK_RATE; + u64 pll_freq; + u64 divider; + u64 dec, dec_multiple; + u32 frac; + u64 multiplier; + + pll_freq = pll->vco_current_rate; + + divider = fref * 2; + + multiplier = 1 << FRAC_BITS; + dec_multiple = div_u64(pll_freq * multiplier, divider); + dec = div_u64_rem(dec_multiple, multiplier, &frac); + + if (pll_freq <= 1900000000UL) + config->pll_prop_gain_rate = 8; + else if (pll_freq <= 3000000000UL) + config->pll_prop_gain_rate = 10; + else + config->pll_prop_gain_rate = 12; + if (pll_freq < 1100000000UL) + config->pll_clock_inverters = 8; + else + config->pll_clock_inverters = 0; + + config->decimal_div_start = dec; + config->frac_div_start = frac; +} + +#define SSC_CENTER BIT(0) +#define SSC_EN BIT(1) + +static void dsi_pll_calc_ssc(struct dsi_pll_10nm *pll, struct dsi_pll_config *config) +{ + u32 ssc_per; + u32 ssc_mod; + u64 ssc_step_size; + u64 frac; + + if (!config->enable_ssc) { + DBG("SSC not enabled\n"); + return; + } + + ssc_per = DIV_ROUND_CLOSEST(VCO_REF_CLK_RATE, config->ssc_freq) / 2 - 1; + ssc_mod = (ssc_per + 1) % (config->ssc_adj_per + 1); + ssc_per -= ssc_mod; + + frac = config->frac_div_start; + ssc_step_size = config->decimal_div_start; + ssc_step_size *= (1 << FRAC_BITS); + ssc_step_size += frac; + ssc_step_size *= config->ssc_offset; + ssc_step_size *= (config->ssc_adj_per + 1); + ssc_step_size = div_u64(ssc_step_size, (ssc_per + 1)); + ssc_step_size = DIV_ROUND_CLOSEST_ULL(ssc_step_size, 1000000); + + config->ssc_div_per = ssc_per; + config->ssc_stepsize = ssc_step_size; + + pr_debug("SCC: Dec:%d, frac:%llu, frac_bits:%d\n", + config->decimal_div_start, frac, FRAC_BITS); + pr_debug("SSC: div_per:0x%X, stepsize:0x%X, adjper:0x%X\n", + ssc_per, (u32)ssc_step_size, config->ssc_adj_per); +} + +static void dsi_pll_ssc_commit(struct dsi_pll_10nm *pll, struct dsi_pll_config *config) +{ + void __iomem *base = pll->phy->pll_base; + + if (config->enable_ssc) { + pr_debug("SSC is enabled\n"); + + dsi_phy_write(base + REG_DSI_10nm_PHY_PLL_SSC_STEPSIZE_LOW_1, + config->ssc_stepsize & 0xff); + dsi_phy_write(base + REG_DSI_10nm_PHY_PLL_SSC_STEPSIZE_HIGH_1, + config->ssc_stepsize >> 8); + dsi_phy_write(base + REG_DSI_10nm_PHY_PLL_SSC_DIV_PER_LOW_1, + config->ssc_div_per & 0xff); + dsi_phy_write(base + REG_DSI_10nm_PHY_PLL_SSC_DIV_PER_HIGH_1, + config->ssc_div_per >> 8); + dsi_phy_write(base + REG_DSI_10nm_PHY_PLL_SSC_DIV_ADJPER_LOW_1, + config->ssc_adj_per & 0xff); + dsi_phy_write(base + REG_DSI_10nm_PHY_PLL_SSC_DIV_ADJPER_HIGH_1, + config->ssc_adj_per >> 8); + dsi_phy_write(base + REG_DSI_10nm_PHY_PLL_SSC_CONTROL, + SSC_EN | (config->ssc_center ? SSC_CENTER : 0)); + } +} + +static void dsi_pll_config_hzindep_reg(struct dsi_pll_10nm *pll) +{ + void __iomem *base = pll->phy->pll_base; + + dsi_phy_write(base + REG_DSI_10nm_PHY_PLL_ANALOG_CONTROLS_ONE, 0x80); + dsi_phy_write(base + REG_DSI_10nm_PHY_PLL_ANALOG_CONTROLS_TWO, 0x03); + dsi_phy_write(base + REG_DSI_10nm_PHY_PLL_ANALOG_CONTROLS_THREE, 0x00); + dsi_phy_write(base + REG_DSI_10nm_PHY_PLL_DSM_DIVIDER, 0x00); + dsi_phy_write(base + REG_DSI_10nm_PHY_PLL_FEEDBACK_DIVIDER, 0x4e); + dsi_phy_write(base + REG_DSI_10nm_PHY_PLL_CALIBRATION_SETTINGS, 0x40); + dsi_phy_write(base + REG_DSI_10nm_PHY_PLL_BAND_SEL_CAL_SETTINGS_THREE, + 0xba); + dsi_phy_write(base + REG_DSI_10nm_PHY_PLL_FREQ_DETECT_SETTINGS_ONE, 0x0c); + dsi_phy_write(base + REG_DSI_10nm_PHY_PLL_OUTDIV, 0x00); + dsi_phy_write(base + REG_DSI_10nm_PHY_PLL_CORE_OVERRIDE, 0x00); + dsi_phy_write(base + REG_DSI_10nm_PHY_PLL_PLL_DIGITAL_TIMERS_TWO, 0x08); + dsi_phy_write(base + REG_DSI_10nm_PHY_PLL_PLL_PROP_GAIN_RATE_1, 0x08); + dsi_phy_write(base + REG_DSI_10nm_PHY_PLL_PLL_BAND_SET_RATE_1, 0xc0); + dsi_phy_write(base + REG_DSI_10nm_PHY_PLL_PLL_INT_GAIN_IFILT_BAND_1, 0xfa); + dsi_phy_write(base + REG_DSI_10nm_PHY_PLL_PLL_FL_INT_GAIN_PFILT_BAND_1, + 0x4c); + dsi_phy_write(base + REG_DSI_10nm_PHY_PLL_PLL_LOCK_OVERRIDE, 0x80); + dsi_phy_write(base + REG_DSI_10nm_PHY_PLL_PFILT, 0x29); + dsi_phy_write(base + REG_DSI_10nm_PHY_PLL_IFILT, 0x3f); +} + +static void dsi_pll_commit(struct dsi_pll_10nm *pll, struct dsi_pll_config *config) +{ + void __iomem *base = pll->phy->pll_base; + + dsi_phy_write(base + REG_DSI_10nm_PHY_PLL_CORE_INPUT_OVERRIDE, 0x12); + dsi_phy_write(base + REG_DSI_10nm_PHY_PLL_DECIMAL_DIV_START_1, + config->decimal_div_start); + dsi_phy_write(base + REG_DSI_10nm_PHY_PLL_FRAC_DIV_START_LOW_1, + config->frac_div_start & 0xff); + dsi_phy_write(base + REG_DSI_10nm_PHY_PLL_FRAC_DIV_START_MID_1, + (config->frac_div_start & 0xff00) >> 8); + dsi_phy_write(base + REG_DSI_10nm_PHY_PLL_FRAC_DIV_START_HIGH_1, + (config->frac_div_start & 0x30000) >> 16); + dsi_phy_write(base + REG_DSI_10nm_PHY_PLL_PLL_LOCKDET_RATE_1, 64); + dsi_phy_write(base + REG_DSI_10nm_PHY_PLL_PLL_LOCK_DELAY, 0x06); + dsi_phy_write(base + REG_DSI_10nm_PHY_PLL_CMODE, 0x10); + dsi_phy_write(base + REG_DSI_10nm_PHY_PLL_CLOCK_INVERTERS, + config->pll_clock_inverters); +} + +static int dsi_pll_10nm_vco_set_rate(struct clk_hw *hw, unsigned long rate, + unsigned long parent_rate) +{ + struct dsi_pll_10nm *pll_10nm = to_pll_10nm(hw); + struct dsi_pll_config config; + + DBG("DSI PLL%d rate=%lu, parent's=%lu", pll_10nm->phy->id, rate, + parent_rate); + + pll_10nm->vco_current_rate = rate; + + dsi_pll_setup_config(&config); + + dsi_pll_calc_dec_frac(pll_10nm, &config); + + dsi_pll_calc_ssc(pll_10nm, &config); + + dsi_pll_commit(pll_10nm, &config); + + dsi_pll_config_hzindep_reg(pll_10nm); + + dsi_pll_ssc_commit(pll_10nm, &config); + + /* flush, ensure all register writes are done*/ + wmb(); + + return 0; +} + +static int dsi_pll_10nm_lock_status(struct dsi_pll_10nm *pll) +{ + struct device *dev = &pll->phy->pdev->dev; + int rc; + u32 status = 0; + u32 const delay_us = 100; + u32 const timeout_us = 5000; + + rc = readl_poll_timeout_atomic(pll->phy->pll_base + + REG_DSI_10nm_PHY_PLL_COMMON_STATUS_ONE, + status, + ((status & BIT(0)) > 0), + delay_us, + timeout_us); + if (rc) + DRM_DEV_ERROR(dev, "DSI PLL(%d) lock failed, status=0x%08x\n", + pll->phy->id, status); + + return rc; +} + +static void dsi_pll_disable_pll_bias(struct dsi_pll_10nm *pll) +{ + u32 data = dsi_phy_read(pll->phy->base + REG_DSI_10nm_PHY_CMN_CTRL_0); + + dsi_phy_write(pll->phy->pll_base + REG_DSI_10nm_PHY_PLL_SYSTEM_MUXES, 0); + dsi_phy_write(pll->phy->base + REG_DSI_10nm_PHY_CMN_CTRL_0, + data & ~BIT(5)); + ndelay(250); +} + +static void dsi_pll_enable_pll_bias(struct dsi_pll_10nm *pll) +{ + u32 data = dsi_phy_read(pll->phy->base + REG_DSI_10nm_PHY_CMN_CTRL_0); + + dsi_phy_write(pll->phy->base + REG_DSI_10nm_PHY_CMN_CTRL_0, + data | BIT(5)); + dsi_phy_write(pll->phy->pll_base + REG_DSI_10nm_PHY_PLL_SYSTEM_MUXES, 0xc0); + ndelay(250); +} + +static void dsi_pll_disable_global_clk(struct dsi_pll_10nm *pll) +{ + u32 data; + + data = dsi_phy_read(pll->phy->base + REG_DSI_10nm_PHY_CMN_CLK_CFG1); + dsi_phy_write(pll->phy->base + REG_DSI_10nm_PHY_CMN_CLK_CFG1, + data & ~BIT(5)); +} + +static void dsi_pll_enable_global_clk(struct dsi_pll_10nm *pll) +{ + u32 data; + + data = dsi_phy_read(pll->phy->base + REG_DSI_10nm_PHY_CMN_CLK_CFG1); + dsi_phy_write(pll->phy->base + REG_DSI_10nm_PHY_CMN_CLK_CFG1, + data | BIT(5)); +} + +static int dsi_pll_10nm_vco_prepare(struct clk_hw *hw) +{ + struct dsi_pll_10nm *pll_10nm = to_pll_10nm(hw); + struct device *dev = &pll_10nm->phy->pdev->dev; + int rc; + + dsi_pll_enable_pll_bias(pll_10nm); + if (pll_10nm->slave) + dsi_pll_enable_pll_bias(pll_10nm->slave); + + rc = dsi_pll_10nm_vco_set_rate(hw,pll_10nm->vco_current_rate, 0); + if (rc) { + DRM_DEV_ERROR(dev, "vco_set_rate failed, rc=%d\n", rc); + return rc; + } + + /* Start PLL */ + dsi_phy_write(pll_10nm->phy->base + REG_DSI_10nm_PHY_CMN_PLL_CNTRL, + 0x01); + + /* + * ensure all PLL configurations are written prior to checking + * for PLL lock. + */ + wmb(); + + /* Check for PLL lock */ + rc = dsi_pll_10nm_lock_status(pll_10nm); + if (rc) { + DRM_DEV_ERROR(dev, "PLL(%d) lock failed\n", pll_10nm->phy->id); + goto error; + } + + pll_10nm->phy->pll_on = true; + + dsi_pll_enable_global_clk(pll_10nm); + if (pll_10nm->slave) + dsi_pll_enable_global_clk(pll_10nm->slave); + + dsi_phy_write(pll_10nm->phy->base + REG_DSI_10nm_PHY_CMN_RBUF_CTRL, + 0x01); + if (pll_10nm->slave) + dsi_phy_write(pll_10nm->slave->phy->base + + REG_DSI_10nm_PHY_CMN_RBUF_CTRL, 0x01); + +error: + return rc; +} + +static void dsi_pll_disable_sub(struct dsi_pll_10nm *pll) +{ + dsi_phy_write(pll->phy->base + REG_DSI_10nm_PHY_CMN_RBUF_CTRL, 0); + dsi_pll_disable_pll_bias(pll); +} + +static void dsi_pll_10nm_vco_unprepare(struct clk_hw *hw) +{ + struct dsi_pll_10nm *pll_10nm = to_pll_10nm(hw); + + /* + * To avoid any stray glitches while abruptly powering down the PLL + * make sure to gate the clock using the clock enable bit before + * powering down the PLL + */ + dsi_pll_disable_global_clk(pll_10nm); + dsi_phy_write(pll_10nm->phy->base + REG_DSI_10nm_PHY_CMN_PLL_CNTRL, 0); + dsi_pll_disable_sub(pll_10nm); + if (pll_10nm->slave) { + dsi_pll_disable_global_clk(pll_10nm->slave); + dsi_pll_disable_sub(pll_10nm->slave); + } + /* flush, ensure all register writes are done */ + wmb(); + pll_10nm->phy->pll_on = false; +} + +static unsigned long dsi_pll_10nm_vco_recalc_rate(struct clk_hw *hw, + unsigned long parent_rate) +{ + struct dsi_pll_10nm *pll_10nm = to_pll_10nm(hw); + void __iomem *base = pll_10nm->phy->pll_base; + u64 ref_clk = VCO_REF_CLK_RATE; + u64 vco_rate = 0x0; + u64 multiplier; + u32 frac; + u32 dec; + u64 pll_freq, tmp64; + + dec = dsi_phy_read(base + REG_DSI_10nm_PHY_PLL_DECIMAL_DIV_START_1); + dec &= 0xff; + + frac = dsi_phy_read(base + REG_DSI_10nm_PHY_PLL_FRAC_DIV_START_LOW_1); + frac |= ((dsi_phy_read(base + REG_DSI_10nm_PHY_PLL_FRAC_DIV_START_MID_1) & + 0xff) << 8); + frac |= ((dsi_phy_read(base + REG_DSI_10nm_PHY_PLL_FRAC_DIV_START_HIGH_1) & + 0x3) << 16); + + /* + * TODO: + * 1. Assumes prescaler is disabled + */ + multiplier = 1 << FRAC_BITS; + pll_freq = dec * (ref_clk * 2); + tmp64 = (ref_clk * 2 * frac); + pll_freq += div_u64(tmp64, multiplier); + + vco_rate = pll_freq; + + DBG("DSI PLL%d returning vco rate = %lu, dec = %x, frac = %x", + pll_10nm->phy->id, (unsigned long)vco_rate, dec, frac); + + return (unsigned long)vco_rate; +} + +static long dsi_pll_10nm_clk_round_rate(struct clk_hw *hw, + unsigned long rate, unsigned long *parent_rate) +{ + struct dsi_pll_10nm *pll_10nm = to_pll_10nm(hw); + + if (rate < pll_10nm->phy->cfg->min_pll_rate) + return pll_10nm->phy->cfg->min_pll_rate; + else if (rate > pll_10nm->phy->cfg->max_pll_rate) + return pll_10nm->phy->cfg->max_pll_rate; + else + return rate; +} + +static const struct clk_ops clk_ops_dsi_pll_10nm_vco = { + .round_rate = dsi_pll_10nm_clk_round_rate, + .set_rate = dsi_pll_10nm_vco_set_rate, + .recalc_rate = dsi_pll_10nm_vco_recalc_rate, + .prepare = dsi_pll_10nm_vco_prepare, + .unprepare = dsi_pll_10nm_vco_unprepare, +}; + +/* + * PLL Callbacks + */ + +static void dsi_10nm_pll_save_state(struct msm_dsi_phy *phy) +{ + struct dsi_pll_10nm *pll_10nm = to_pll_10nm(phy->vco_hw); + struct pll_10nm_cached_state *cached = &pll_10nm->cached_state; + void __iomem *phy_base = pll_10nm->phy->base; + u32 cmn_clk_cfg0, cmn_clk_cfg1; + + cached->pll_out_div = dsi_phy_read(pll_10nm->phy->pll_base + + REG_DSI_10nm_PHY_PLL_PLL_OUTDIV_RATE); + cached->pll_out_div &= 0x3; + + cmn_clk_cfg0 = dsi_phy_read(phy_base + REG_DSI_10nm_PHY_CMN_CLK_CFG0); + cached->bit_clk_div = cmn_clk_cfg0 & 0xf; + cached->pix_clk_div = (cmn_clk_cfg0 & 0xf0) >> 4; + + cmn_clk_cfg1 = dsi_phy_read(phy_base + REG_DSI_10nm_PHY_CMN_CLK_CFG1); + cached->pll_mux = cmn_clk_cfg1 & 0x3; + + DBG("DSI PLL%d outdiv %x bit_clk_div %x pix_clk_div %x pll_mux %x", + pll_10nm->phy->id, cached->pll_out_div, cached->bit_clk_div, + cached->pix_clk_div, cached->pll_mux); +} + +static int dsi_10nm_pll_restore_state(struct msm_dsi_phy *phy) +{ + struct dsi_pll_10nm *pll_10nm = to_pll_10nm(phy->vco_hw); + struct pll_10nm_cached_state *cached = &pll_10nm->cached_state; + void __iomem *phy_base = pll_10nm->phy->base; + u32 val; + int ret; + + val = dsi_phy_read(pll_10nm->phy->pll_base + REG_DSI_10nm_PHY_PLL_PLL_OUTDIV_RATE); + val &= ~0x3; + val |= cached->pll_out_div; + dsi_phy_write(pll_10nm->phy->pll_base + REG_DSI_10nm_PHY_PLL_PLL_OUTDIV_RATE, val); + + dsi_phy_write(phy_base + REG_DSI_10nm_PHY_CMN_CLK_CFG0, + cached->bit_clk_div | (cached->pix_clk_div << 4)); + + val = dsi_phy_read(phy_base + REG_DSI_10nm_PHY_CMN_CLK_CFG1); + val &= ~0x3; + val |= cached->pll_mux; + dsi_phy_write(phy_base + REG_DSI_10nm_PHY_CMN_CLK_CFG1, val); + + ret = dsi_pll_10nm_vco_set_rate(phy->vco_hw, + pll_10nm->vco_current_rate, + VCO_REF_CLK_RATE); + if (ret) { + DRM_DEV_ERROR(&pll_10nm->phy->pdev->dev, + "restore vco rate failed. ret=%d\n", ret); + return ret; + } + + DBG("DSI PLL%d", pll_10nm->phy->id); + + return 0; +} + +static int dsi_10nm_set_usecase(struct msm_dsi_phy *phy) +{ + struct dsi_pll_10nm *pll_10nm = to_pll_10nm(phy->vco_hw); + void __iomem *base = phy->base; + u32 data = 0x0; /* internal PLL */ + + DBG("DSI PLL%d", pll_10nm->phy->id); + + switch (phy->usecase) { + case MSM_DSI_PHY_STANDALONE: + break; + case MSM_DSI_PHY_MASTER: + pll_10nm->slave = pll_10nm_list[(pll_10nm->phy->id + 1) % DSI_MAX]; + break; + case MSM_DSI_PHY_SLAVE: + data = 0x1; /* external PLL */ + break; + default: + return -EINVAL; + } + + /* set PLL src */ + dsi_phy_write(base + REG_DSI_10nm_PHY_CMN_CLK_CFG1, (data << 2)); + + return 0; +} + +/* + * The post dividers and mux clocks are created using the standard divider and + * mux API. Unlike the 14nm PHY, the slave PLL doesn't need its dividers/mux + * state to follow the master PLL's divider/mux state. Therefore, we don't + * require special clock ops that also configure the slave PLL registers + */ +static int pll_10nm_register(struct dsi_pll_10nm *pll_10nm, struct clk_hw **provided_clocks) +{ + char clk_name[32], parent[32], vco_name[32]; + char parent2[32], parent3[32], parent4[32]; + struct clk_init_data vco_init = { + .parent_names = (const char *[]){ "xo" }, + .num_parents = 1, + .name = vco_name, + .flags = CLK_IGNORE_UNUSED, + .ops = &clk_ops_dsi_pll_10nm_vco, + }; + struct device *dev = &pll_10nm->phy->pdev->dev; + struct clk_hw *hw; + int ret; + + DBG("DSI%d", pll_10nm->phy->id); + + snprintf(vco_name, 32, "dsi%dvco_clk", pll_10nm->phy->id); + pll_10nm->clk_hw.init = &vco_init; + + ret = devm_clk_hw_register(dev, &pll_10nm->clk_hw); + if (ret) + return ret; + + snprintf(clk_name, 32, "dsi%d_pll_out_div_clk", pll_10nm->phy->id); + snprintf(parent, 32, "dsi%dvco_clk", pll_10nm->phy->id); + + hw = devm_clk_hw_register_divider(dev, clk_name, + parent, CLK_SET_RATE_PARENT, + pll_10nm->phy->pll_base + + REG_DSI_10nm_PHY_PLL_PLL_OUTDIV_RATE, + 0, 2, CLK_DIVIDER_POWER_OF_TWO, NULL); + if (IS_ERR(hw)) { + ret = PTR_ERR(hw); + goto fail; + } + + snprintf(clk_name, 32, "dsi%d_pll_bit_clk", pll_10nm->phy->id); + snprintf(parent, 32, "dsi%d_pll_out_div_clk", pll_10nm->phy->id); + + /* BIT CLK: DIV_CTRL_3_0 */ + hw = devm_clk_hw_register_divider(dev, clk_name, parent, + CLK_SET_RATE_PARENT, + pll_10nm->phy->base + + REG_DSI_10nm_PHY_CMN_CLK_CFG0, + 0, 4, CLK_DIVIDER_ONE_BASED, + &pll_10nm->postdiv_lock); + if (IS_ERR(hw)) { + ret = PTR_ERR(hw); + goto fail; + } + + snprintf(clk_name, 32, "dsi%d_phy_pll_out_byteclk", pll_10nm->phy->id); + snprintf(parent, 32, "dsi%d_pll_bit_clk", pll_10nm->phy->id); + + /* DSI Byte clock = VCO_CLK / OUT_DIV / BIT_DIV / 8 */ + hw = devm_clk_hw_register_fixed_factor(dev, clk_name, parent, + CLK_SET_RATE_PARENT, 1, 8); + if (IS_ERR(hw)) { + ret = PTR_ERR(hw); + goto fail; + } + + provided_clocks[DSI_BYTE_PLL_CLK] = hw; + + snprintf(clk_name, 32, "dsi%d_pll_by_2_bit_clk", pll_10nm->phy->id); + snprintf(parent, 32, "dsi%d_pll_bit_clk", pll_10nm->phy->id); + + hw = devm_clk_hw_register_fixed_factor(dev, clk_name, parent, + 0, 1, 2); + if (IS_ERR(hw)) { + ret = PTR_ERR(hw); + goto fail; + } + + snprintf(clk_name, 32, "dsi%d_pll_post_out_div_clk", pll_10nm->phy->id); + snprintf(parent, 32, "dsi%d_pll_out_div_clk", pll_10nm->phy->id); + + hw = devm_clk_hw_register_fixed_factor(dev, clk_name, parent, + 0, 1, 4); + if (IS_ERR(hw)) { + ret = PTR_ERR(hw); + goto fail; + } + + snprintf(clk_name, 32, "dsi%d_pclk_mux", pll_10nm->phy->id); + snprintf(parent, 32, "dsi%d_pll_bit_clk", pll_10nm->phy->id); + snprintf(parent2, 32, "dsi%d_pll_by_2_bit_clk", pll_10nm->phy->id); + snprintf(parent3, 32, "dsi%d_pll_out_div_clk", pll_10nm->phy->id); + snprintf(parent4, 32, "dsi%d_pll_post_out_div_clk", pll_10nm->phy->id); + + hw = devm_clk_hw_register_mux(dev, clk_name, + ((const char *[]){ + parent, parent2, parent3, parent4 + }), 4, 0, pll_10nm->phy->base + + REG_DSI_10nm_PHY_CMN_CLK_CFG1, + 0, 2, 0, NULL); + if (IS_ERR(hw)) { + ret = PTR_ERR(hw); + goto fail; + } + + snprintf(clk_name, 32, "dsi%d_phy_pll_out_dsiclk", pll_10nm->phy->id); + snprintf(parent, 32, "dsi%d_pclk_mux", pll_10nm->phy->id); + + /* PIX CLK DIV : DIV_CTRL_7_4*/ + hw = devm_clk_hw_register_divider(dev, clk_name, parent, + 0, pll_10nm->phy->base + + REG_DSI_10nm_PHY_CMN_CLK_CFG0, + 4, 4, CLK_DIVIDER_ONE_BASED, + &pll_10nm->postdiv_lock); + if (IS_ERR(hw)) { + ret = PTR_ERR(hw); + goto fail; + } + + provided_clocks[DSI_PIXEL_PLL_CLK] = hw; + + return 0; + +fail: + + return ret; +} + +static int dsi_pll_10nm_init(struct msm_dsi_phy *phy) +{ + struct platform_device *pdev = phy->pdev; + struct dsi_pll_10nm *pll_10nm; + int ret; + + pll_10nm = devm_kzalloc(&pdev->dev, sizeof(*pll_10nm), GFP_KERNEL); + if (!pll_10nm) + return -ENOMEM; + + DBG("DSI PLL%d", phy->id); + + pll_10nm_list[phy->id] = pll_10nm; + + spin_lock_init(&pll_10nm->postdiv_lock); + + pll_10nm->phy = phy; + + ret = pll_10nm_register(pll_10nm, phy->provided_clocks->hws); + if (ret) { + DRM_DEV_ERROR(&pdev->dev, "failed to register PLL: %d\n", ret); + return ret; + } + + phy->vco_hw = &pll_10nm->clk_hw; + + /* TODO: Remove this when we have proper display handover support */ + msm_dsi_phy_pll_save_state(phy); + + return 0; +} + static int dsi_phy_hw_v3_0_is_pll_on(struct msm_dsi_phy *phy) { void __iomem *base = phy->base; @@ -42,7 +746,7 @@ static void dsi_phy_hw_v3_0_lane_settings(struct msm_dsi_phy *phy) u8 tx_dctrl[] = { 0x00, 0x00, 0x00, 0x04, 0x01 }; void __iomem *lane_base = phy->lane_base; - if (phy->cfg->quirks & V3_0_0_10NM_OLD_TIMINGS_QUIRK) + if (phy->cfg->quirks & DSI_PHY_10NM_QUIRK_OLD_TIMINGS) tx_dctrl[3] = 0x02; /* Strength ctrl settings */ @@ -77,14 +781,14 @@ static void dsi_phy_hw_v3_0_lane_settings(struct msm_dsi_phy *phy) tx_dctrl[i]); } - if (!(phy->cfg->quirks & V3_0_0_10NM_OLD_TIMINGS_QUIRK)) { + if (!(phy->cfg->quirks & DSI_PHY_10NM_QUIRK_OLD_TIMINGS)) { /* Toggle BIT 0 to release freeze I/0 */ dsi_phy_write(lane_base + REG_DSI_10nm_PHY_LN_TX_DCTRL(3), 0x05); dsi_phy_write(lane_base + REG_DSI_10nm_PHY_LN_TX_DCTRL(3), 0x04); } } -static int dsi_10nm_phy_enable(struct msm_dsi_phy *phy, int src_pll_id, +static int dsi_10nm_phy_enable(struct msm_dsi_phy *phy, struct msm_dsi_phy_clk_request *clk_req) { int ret; @@ -175,7 +879,7 @@ static int dsi_10nm_phy_enable(struct msm_dsi_phy *phy, int src_pll_id, /* Select full-rate mode */ dsi_phy_write(base + REG_DSI_10nm_PHY_CMN_CTRL_2, 0x40); - ret = msm_dsi_pll_set_usecase(phy->pll, phy->usecase); + ret = dsi_10nm_set_usecase(phy); if (ret) { DRM_DEV_ERROR(&phy->pdev->dev, "%s: set pll usecase failed, %d\n", __func__, ret); @@ -216,24 +920,8 @@ static void dsi_10nm_phy_disable(struct msm_dsi_phy *phy) DBG("DSI%d PHY disabled", phy->id); } -static int dsi_10nm_phy_init(struct msm_dsi_phy *phy) -{ - struct platform_device *pdev = phy->pdev; - - phy->lane_base = msm_ioremap(pdev, "dsi_phy_lane", - "DSI_PHY_LANE"); - if (IS_ERR(phy->lane_base)) { - DRM_DEV_ERROR(&pdev->dev, "%s: failed to map phy lane base\n", - __func__); - return -ENOMEM; - } - - return 0; -} - const struct msm_dsi_phy_cfg dsi_phy_10nm_cfgs = { - .type = MSM_DSI_PHY_10NM, - .src_pll_truthtable = { {false, false}, {true, false} }, + .has_phy_lane = true, .reg_cfg = { .num = 1, .regs = { @@ -243,15 +931,18 @@ const struct msm_dsi_phy_cfg dsi_phy_10nm_cfgs = { .ops = { .enable = dsi_10nm_phy_enable, .disable = dsi_10nm_phy_disable, - .init = dsi_10nm_phy_init, + .pll_init = dsi_pll_10nm_init, + .save_pll_state = dsi_10nm_pll_save_state, + .restore_pll_state = dsi_10nm_pll_restore_state, }, + .min_pll_rate = 1000000000UL, + .max_pll_rate = 3500000000UL, .io_start = { 0xae94400, 0xae96400 }, .num_dsi_phy = 2, }; const struct msm_dsi_phy_cfg dsi_phy_10nm_8998_cfgs = { - .type = MSM_DSI_PHY_10NM, - .src_pll_truthtable = { {false, false}, {true, false} }, + .has_phy_lane = true, .reg_cfg = { .num = 1, .regs = { @@ -261,9 +952,13 @@ const struct msm_dsi_phy_cfg dsi_phy_10nm_8998_cfgs = { .ops = { .enable = dsi_10nm_phy_enable, .disable = dsi_10nm_phy_disable, - .init = dsi_10nm_phy_init, + .pll_init = dsi_pll_10nm_init, + .save_pll_state = dsi_10nm_pll_save_state, + .restore_pll_state = dsi_10nm_pll_restore_state, }, + .min_pll_rate = 1000000000UL, + .max_pll_rate = 3500000000UL, .io_start = { 0xc994400, 0xc996400 }, .num_dsi_phy = 2, - .quirks = V3_0_0_10NM_OLD_TIMINGS_QUIRK, + .quirks = DSI_PHY_10NM_QUIRK_OLD_TIMINGS, }; diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_14nm.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_14nm.c index 519400501bcd..65d68eb9e3cb 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_14nm.c +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_14nm.c @@ -3,6 +3,8 @@ * Copyright (c) 2016, The Linux Foundation. All rights reserved. */ +#include <linux/clk.h> +#include <linux/clk-provider.h> #include <linux/delay.h> #include "dsi_phy.h" @@ -10,6 +12,895 @@ #define PHY_14NM_CKLN_IDX 4 +/* + * DSI PLL 14nm - clock diagram (eg: DSI0): + * + * dsi0n1_postdiv_clk + * | + * | + * +----+ | +----+ + * dsi0vco_clk ---| n1 |--o--| /8 |-- dsi0pllbyte + * +----+ | +----+ + * | dsi0n1_postdivby2_clk + * | +----+ | + * o---| /2 |--o--|\ + * | +----+ | \ +----+ + * | | |--| n2 |-- dsi0pll + * o--------------| / +----+ + * |/ + */ + +#define POLL_MAX_READS 15 +#define POLL_TIMEOUT_US 1000 + +#define VCO_REF_CLK_RATE 19200000 +#define VCO_MIN_RATE 1300000000UL +#define VCO_MAX_RATE 2600000000UL + +struct dsi_pll_config { + u64 vco_current_rate; + + u32 ssc_en; /* SSC enable/disable */ + + /* fixed params */ + u32 plllock_cnt; + u32 ssc_center; + u32 ssc_adj_period; + u32 ssc_spread; + u32 ssc_freq; + + /* calculated */ + u32 dec_start; + u32 div_frac_start; + u32 ssc_period; + u32 ssc_step_size; + u32 plllock_cmp; + u32 pll_vco_div_ref; + u32 pll_vco_count; + u32 pll_kvco_div_ref; + u32 pll_kvco_count; +}; + +struct pll_14nm_cached_state { + unsigned long vco_rate; + u8 n2postdiv; + u8 n1postdiv; +}; + +struct dsi_pll_14nm { + struct clk_hw clk_hw; + + struct msm_dsi_phy *phy; + + /* protects REG_DSI_14nm_PHY_CMN_CLK_CFG0 register */ + spinlock_t postdiv_lock; + + struct pll_14nm_cached_state cached_state; + + struct dsi_pll_14nm *slave; +}; + +#define to_pll_14nm(x) container_of(x, struct dsi_pll_14nm, clk_hw) + +/* + * Private struct for N1/N2 post-divider clocks. These clocks are similar to + * the generic clk_divider class of clocks. The only difference is that it + * also sets the slave DSI PLL's post-dividers if in Dual DSI mode + */ +struct dsi_pll_14nm_postdiv { + struct clk_hw hw; + + /* divider params */ + u8 shift; + u8 width; + u8 flags; /* same flags as used by clk_divider struct */ + + struct dsi_pll_14nm *pll; +}; + +#define to_pll_14nm_postdiv(_hw) container_of(_hw, struct dsi_pll_14nm_postdiv, hw) + +/* + * Global list of private DSI PLL struct pointers. We need this for Dual DSI + * mode, where the master PLL's clk_ops needs access the slave's private data + */ +static struct dsi_pll_14nm *pll_14nm_list[DSI_MAX]; + +static bool pll_14nm_poll_for_ready(struct dsi_pll_14nm *pll_14nm, + u32 nb_tries, u32 timeout_us) +{ + bool pll_locked = false; + void __iomem *base = pll_14nm->phy->pll_base; + u32 tries, val; + + tries = nb_tries; + while (tries--) { + val = dsi_phy_read(base + + REG_DSI_14nm_PHY_PLL_RESET_SM_READY_STATUS); + pll_locked = !!(val & BIT(5)); + + if (pll_locked) + break; + + udelay(timeout_us); + } + + if (!pll_locked) { + tries = nb_tries; + while (tries--) { + val = dsi_phy_read(base + + REG_DSI_14nm_PHY_PLL_RESET_SM_READY_STATUS); + pll_locked = !!(val & BIT(0)); + + if (pll_locked) + break; + + udelay(timeout_us); + } + } + + DBG("DSI PLL is %slocked", pll_locked ? "" : "*not* "); + + return pll_locked; +} + +static void dsi_pll_14nm_config_init(struct dsi_pll_config *pconf) +{ + /* fixed input */ + pconf->plllock_cnt = 1; + + /* + * SSC is enabled by default. We might need DT props for configuring + * some SSC params like PPM and center/down spread etc. + */ + pconf->ssc_en = 1; + pconf->ssc_center = 0; /* down spread by default */ + pconf->ssc_spread = 5; /* PPM / 1000 */ + pconf->ssc_freq = 31500; /* default recommended */ + pconf->ssc_adj_period = 37; +} + +#define CEIL(x, y) (((x) + ((y) - 1)) / (y)) + +static void pll_14nm_ssc_calc(struct dsi_pll_14nm *pll, struct dsi_pll_config *pconf) +{ + u32 period, ssc_period; + u32 ref, rem; + u64 step_size; + + DBG("vco=%lld ref=%d", pconf->vco_current_rate, VCO_REF_CLK_RATE); + + ssc_period = pconf->ssc_freq / 500; + period = (u32)VCO_REF_CLK_RATE / 1000; + ssc_period = CEIL(period, ssc_period); + ssc_period -= 1; + pconf->ssc_period = ssc_period; + + DBG("ssc freq=%d spread=%d period=%d", pconf->ssc_freq, + pconf->ssc_spread, pconf->ssc_period); + + step_size = (u32)pconf->vco_current_rate; + ref = VCO_REF_CLK_RATE; + ref /= 1000; + step_size = div_u64(step_size, ref); + step_size <<= 20; + step_size = div_u64(step_size, 1000); + step_size *= pconf->ssc_spread; + step_size = div_u64(step_size, 1000); + step_size *= (pconf->ssc_adj_period + 1); + + rem = 0; + step_size = div_u64_rem(step_size, ssc_period + 1, &rem); + if (rem) + step_size++; + + DBG("step_size=%lld", step_size); + + step_size &= 0x0ffff; /* take lower 16 bits */ + + pconf->ssc_step_size = step_size; +} + +static void pll_14nm_dec_frac_calc(struct dsi_pll_14nm *pll, struct dsi_pll_config *pconf) +{ + u64 multiplier = BIT(20); + u64 dec_start_multiple, dec_start, pll_comp_val; + u32 duration, div_frac_start; + u64 vco_clk_rate = pconf->vco_current_rate; + u64 fref = VCO_REF_CLK_RATE; + + DBG("vco_clk_rate=%lld ref_clk_rate=%lld", vco_clk_rate, fref); + + dec_start_multiple = div_u64(vco_clk_rate * multiplier, fref); + div_u64_rem(dec_start_multiple, multiplier, &div_frac_start); + + dec_start = div_u64(dec_start_multiple, multiplier); + + pconf->dec_start = (u32)dec_start; + pconf->div_frac_start = div_frac_start; + + if (pconf->plllock_cnt == 0) + duration = 1024; + else if (pconf->plllock_cnt == 1) + duration = 256; + else if (pconf->plllock_cnt == 2) + duration = 128; + else + duration = 32; + + pll_comp_val = duration * dec_start_multiple; + pll_comp_val = div_u64(pll_comp_val, multiplier); + do_div(pll_comp_val, 10); + + pconf->plllock_cmp = (u32)pll_comp_val; +} + +static u32 pll_14nm_kvco_slop(u32 vrate) +{ + u32 slop = 0; + + if (vrate > VCO_MIN_RATE && vrate <= 1800000000UL) + slop = 600; + else if (vrate > 1800000000UL && vrate < 2300000000UL) + slop = 400; + else if (vrate > 2300000000UL && vrate < VCO_MAX_RATE) + slop = 280; + + return slop; +} + +static void pll_14nm_calc_vco_count(struct dsi_pll_14nm *pll, struct dsi_pll_config *pconf) +{ + u64 vco_clk_rate = pconf->vco_current_rate; + u64 fref = VCO_REF_CLK_RATE; + u32 vco_measure_time = 5; + u32 kvco_measure_time = 5; + u64 data; + u32 cnt; + + data = fref * vco_measure_time; + do_div(data, 1000000); + data &= 0x03ff; /* 10 bits */ + data -= 2; + pconf->pll_vco_div_ref = data; + + data = div_u64(vco_clk_rate, 1000000); /* unit is Mhz */ + data *= vco_measure_time; + do_div(data, 10); + pconf->pll_vco_count = data; + + data = fref * kvco_measure_time; + do_div(data, 1000000); + data &= 0x03ff; /* 10 bits */ + data -= 1; + pconf->pll_kvco_div_ref = data; + + cnt = pll_14nm_kvco_slop(vco_clk_rate); + cnt *= 2; + cnt /= 100; + cnt *= kvco_measure_time; + pconf->pll_kvco_count = cnt; +} + +static void pll_db_commit_ssc(struct dsi_pll_14nm *pll, struct dsi_pll_config *pconf) +{ + void __iomem *base = pll->phy->pll_base; + u8 data; + + data = pconf->ssc_adj_period; + data &= 0x0ff; + dsi_phy_write(base + REG_DSI_14nm_PHY_PLL_SSC_ADJ_PER1, data); + data = (pconf->ssc_adj_period >> 8); + data &= 0x03; + dsi_phy_write(base + REG_DSI_14nm_PHY_PLL_SSC_ADJ_PER2, data); + + data = pconf->ssc_period; + data &= 0x0ff; + dsi_phy_write(base + REG_DSI_14nm_PHY_PLL_SSC_PER1, data); + data = (pconf->ssc_period >> 8); + data &= 0x0ff; + dsi_phy_write(base + REG_DSI_14nm_PHY_PLL_SSC_PER2, data); + + data = pconf->ssc_step_size; + data &= 0x0ff; + dsi_phy_write(base + REG_DSI_14nm_PHY_PLL_SSC_STEP_SIZE1, data); + data = (pconf->ssc_step_size >> 8); + data &= 0x0ff; + dsi_phy_write(base + REG_DSI_14nm_PHY_PLL_SSC_STEP_SIZE2, data); + + data = (pconf->ssc_center & 0x01); + data <<= 1; + data |= 0x01; /* enable */ + dsi_phy_write(base + REG_DSI_14nm_PHY_PLL_SSC_EN_CENTER, data); + + wmb(); /* make sure register committed */ +} + +static void pll_db_commit_common(struct dsi_pll_14nm *pll, + struct dsi_pll_config *pconf) +{ + void __iomem *base = pll->phy->pll_base; + u8 data; + + /* confgiure the non frequency dependent pll registers */ + data = 0; + dsi_phy_write(base + REG_DSI_14nm_PHY_PLL_SYSCLK_EN_RESET, data); + + dsi_phy_write(base + REG_DSI_14nm_PHY_PLL_TXCLK_EN, 1); + + dsi_phy_write(base + REG_DSI_14nm_PHY_PLL_RESETSM_CNTRL, 48); + dsi_phy_write(base + REG_DSI_14nm_PHY_PLL_RESETSM_CNTRL2, 4 << 3); /* bandgap_timer */ + dsi_phy_write(base + REG_DSI_14nm_PHY_PLL_RESETSM_CNTRL5, 5); /* pll_wakeup_timer */ + + data = pconf->pll_vco_div_ref & 0xff; + dsi_phy_write(base + REG_DSI_14nm_PHY_PLL_VCO_DIV_REF1, data); + data = (pconf->pll_vco_div_ref >> 8) & 0x3; + dsi_phy_write(base + REG_DSI_14nm_PHY_PLL_VCO_DIV_REF2, data); + + data = pconf->pll_kvco_div_ref & 0xff; + dsi_phy_write(base + REG_DSI_14nm_PHY_PLL_KVCO_DIV_REF1, data); + data = (pconf->pll_kvco_div_ref >> 8) & 0x3; + dsi_phy_write(base + REG_DSI_14nm_PHY_PLL_KVCO_DIV_REF2, data); + + dsi_phy_write(base + REG_DSI_14nm_PHY_PLL_PLL_MISC1, 16); + + dsi_phy_write(base + REG_DSI_14nm_PHY_PLL_IE_TRIM, 4); + + dsi_phy_write(base + REG_DSI_14nm_PHY_PLL_IP_TRIM, 4); + + dsi_phy_write(base + REG_DSI_14nm_PHY_PLL_CP_SET_CUR, 1 << 3 | 1); + + dsi_phy_write(base + REG_DSI_14nm_PHY_PLL_PLL_ICPCSET, 0 << 3 | 0); + + dsi_phy_write(base + REG_DSI_14nm_PHY_PLL_PLL_ICPMSET, 0 << 3 | 0); + + dsi_phy_write(base + REG_DSI_14nm_PHY_PLL_PLL_ICP_SET, 4 << 3 | 4); + + dsi_phy_write(base + REG_DSI_14nm_PHY_PLL_PLL_LPF1, 1 << 4 | 11); + + dsi_phy_write(base + REG_DSI_14nm_PHY_PLL_IPTAT_TRIM, 7); + + dsi_phy_write(base + REG_DSI_14nm_PHY_PLL_PLL_CRCTRL, 1 << 4 | 2); +} + +static void pll_14nm_software_reset(struct dsi_pll_14nm *pll_14nm) +{ + void __iomem *cmn_base = pll_14nm->phy->base; + + /* de assert pll start and apply pll sw reset */ + + /* stop pll */ + dsi_phy_write(cmn_base + REG_DSI_14nm_PHY_CMN_PLL_CNTRL, 0); + + /* pll sw reset */ + dsi_phy_write_udelay(cmn_base + REG_DSI_14nm_PHY_CMN_CTRL_1, 0x20, 10); + wmb(); /* make sure register committed */ + + dsi_phy_write(cmn_base + REG_DSI_14nm_PHY_CMN_CTRL_1, 0); + wmb(); /* make sure register committed */ +} + +static void pll_db_commit_14nm(struct dsi_pll_14nm *pll, + struct dsi_pll_config *pconf) +{ + void __iomem *base = pll->phy->pll_base; + void __iomem *cmn_base = pll->phy->base; + u8 data; + + DBG("DSI%d PLL", pll->phy->id); + + dsi_phy_write(cmn_base + REG_DSI_14nm_PHY_CMN_LDO_CNTRL, 0x3c); + + pll_db_commit_common(pll, pconf); + + pll_14nm_software_reset(pll); + + /* Use the /2 path in Mux */ + dsi_phy_write(cmn_base + REG_DSI_14nm_PHY_CMN_CLK_CFG1, 1); + + data = 0xff; /* data, clk, pll normal operation */ + dsi_phy_write(cmn_base + REG_DSI_14nm_PHY_CMN_CTRL_0, data); + + /* configure the frequency dependent pll registers */ + data = pconf->dec_start; + dsi_phy_write(base + REG_DSI_14nm_PHY_PLL_DEC_START, data); + + data = pconf->div_frac_start & 0xff; + dsi_phy_write(base + REG_DSI_14nm_PHY_PLL_DIV_FRAC_START1, data); + data = (pconf->div_frac_start >> 8) & 0xff; + dsi_phy_write(base + REG_DSI_14nm_PHY_PLL_DIV_FRAC_START2, data); + data = (pconf->div_frac_start >> 16) & 0xf; + dsi_phy_write(base + REG_DSI_14nm_PHY_PLL_DIV_FRAC_START3, data); + + data = pconf->plllock_cmp & 0xff; + dsi_phy_write(base + REG_DSI_14nm_PHY_PLL_PLLLOCK_CMP1, data); + + data = (pconf->plllock_cmp >> 8) & 0xff; + dsi_phy_write(base + REG_DSI_14nm_PHY_PLL_PLLLOCK_CMP2, data); + + data = (pconf->plllock_cmp >> 16) & 0x3; + dsi_phy_write(base + REG_DSI_14nm_PHY_PLL_PLLLOCK_CMP3, data); + + data = pconf->plllock_cnt << 1 | 0 << 3; /* plllock_rng */ + dsi_phy_write(base + REG_DSI_14nm_PHY_PLL_PLLLOCK_CMP_EN, data); + + data = pconf->pll_vco_count & 0xff; + dsi_phy_write(base + REG_DSI_14nm_PHY_PLL_VCO_COUNT1, data); + data = (pconf->pll_vco_count >> 8) & 0xff; + dsi_phy_write(base + REG_DSI_14nm_PHY_PLL_VCO_COUNT2, data); + + data = pconf->pll_kvco_count & 0xff; + dsi_phy_write(base + REG_DSI_14nm_PHY_PLL_KVCO_COUNT1, data); + data = (pconf->pll_kvco_count >> 8) & 0x3; + dsi_phy_write(base + REG_DSI_14nm_PHY_PLL_KVCO_COUNT2, data); + + /* + * High nibble configures the post divider internal to the VCO. It's + * fixed to divide by 1 for now. + * + * 0: divided by 1 + * 1: divided by 2 + * 2: divided by 4 + * 3: divided by 8 + */ + dsi_phy_write(base + REG_DSI_14nm_PHY_PLL_PLL_LPF2_POSTDIV, 0 << 4 | 3); + + if (pconf->ssc_en) + pll_db_commit_ssc(pll, pconf); + + wmb(); /* make sure register committed */ +} + +/* + * VCO clock Callbacks + */ +static int dsi_pll_14nm_vco_set_rate(struct clk_hw *hw, unsigned long rate, + unsigned long parent_rate) +{ + struct dsi_pll_14nm *pll_14nm = to_pll_14nm(hw); + struct dsi_pll_config conf; + + DBG("DSI PLL%d rate=%lu, parent's=%lu", pll_14nm->phy->id, rate, + parent_rate); + + dsi_pll_14nm_config_init(&conf); + conf.vco_current_rate = rate; + + pll_14nm_dec_frac_calc(pll_14nm, &conf); + + if (conf.ssc_en) + pll_14nm_ssc_calc(pll_14nm, &conf); + + pll_14nm_calc_vco_count(pll_14nm, &conf); + + /* commit the slave DSI PLL registers if we're master. Note that we + * don't lock the slave PLL. We just ensure that the PLL/PHY registers + * of the master and slave are identical + */ + if (pll_14nm->phy->usecase == MSM_DSI_PHY_MASTER) { + struct dsi_pll_14nm *pll_14nm_slave = pll_14nm->slave; + + pll_db_commit_14nm(pll_14nm_slave, &conf); + } + + pll_db_commit_14nm(pll_14nm, &conf); + + return 0; +} + +static unsigned long dsi_pll_14nm_vco_recalc_rate(struct clk_hw *hw, + unsigned long parent_rate) +{ + struct dsi_pll_14nm *pll_14nm = to_pll_14nm(hw); + void __iomem *base = pll_14nm->phy->pll_base; + u64 vco_rate, multiplier = BIT(20); + u32 div_frac_start; + u32 dec_start; + u64 ref_clk = parent_rate; + + dec_start = dsi_phy_read(base + REG_DSI_14nm_PHY_PLL_DEC_START); + dec_start &= 0x0ff; + + DBG("dec_start = %x", dec_start); + + div_frac_start = (dsi_phy_read(base + REG_DSI_14nm_PHY_PLL_DIV_FRAC_START3) + & 0xf) << 16; + div_frac_start |= (dsi_phy_read(base + REG_DSI_14nm_PHY_PLL_DIV_FRAC_START2) + & 0xff) << 8; + div_frac_start |= dsi_phy_read(base + REG_DSI_14nm_PHY_PLL_DIV_FRAC_START1) + & 0xff; + + DBG("div_frac_start = %x", div_frac_start); + + vco_rate = ref_clk * dec_start; + + vco_rate += ((ref_clk * div_frac_start) / multiplier); + + /* + * Recalculating the rate from dec_start and frac_start doesn't end up + * the rate we originally set. Convert the freq to KHz, round it up and + * convert it back to MHz. + */ + vco_rate = DIV_ROUND_UP_ULL(vco_rate, 1000) * 1000; + + DBG("returning vco rate = %lu", (unsigned long)vco_rate); + + return (unsigned long)vco_rate; +} + +static int dsi_pll_14nm_vco_prepare(struct clk_hw *hw) +{ + struct dsi_pll_14nm *pll_14nm = to_pll_14nm(hw); + void __iomem *base = pll_14nm->phy->pll_base; + void __iomem *cmn_base = pll_14nm->phy->base; + bool locked; + + DBG(""); + + if (unlikely(pll_14nm->phy->pll_on)) + return 0; + + dsi_phy_write(base + REG_DSI_14nm_PHY_PLL_VREF_CFG1, 0x10); + dsi_phy_write(cmn_base + REG_DSI_14nm_PHY_CMN_PLL_CNTRL, 1); + + locked = pll_14nm_poll_for_ready(pll_14nm, POLL_MAX_READS, + POLL_TIMEOUT_US); + + if (unlikely(!locked)) { + DRM_DEV_ERROR(&pll_14nm->phy->pdev->dev, "DSI PLL lock failed\n"); + return -EINVAL; + } + + DBG("DSI PLL lock success"); + pll_14nm->phy->pll_on = true; + + return 0; +} + +static void dsi_pll_14nm_vco_unprepare(struct clk_hw *hw) +{ + struct dsi_pll_14nm *pll_14nm = to_pll_14nm(hw); + void __iomem *cmn_base = pll_14nm->phy->base; + + DBG(""); + + if (unlikely(!pll_14nm->phy->pll_on)) + return; + + dsi_phy_write(cmn_base + REG_DSI_14nm_PHY_CMN_PLL_CNTRL, 0); + + pll_14nm->phy->pll_on = false; +} + +static long dsi_pll_14nm_clk_round_rate(struct clk_hw *hw, + unsigned long rate, unsigned long *parent_rate) +{ + struct dsi_pll_14nm *pll_14nm = to_pll_14nm(hw); + + if (rate < pll_14nm->phy->cfg->min_pll_rate) + return pll_14nm->phy->cfg->min_pll_rate; + else if (rate > pll_14nm->phy->cfg->max_pll_rate) + return pll_14nm->phy->cfg->max_pll_rate; + else + return rate; +} + +static const struct clk_ops clk_ops_dsi_pll_14nm_vco = { + .round_rate = dsi_pll_14nm_clk_round_rate, + .set_rate = dsi_pll_14nm_vco_set_rate, + .recalc_rate = dsi_pll_14nm_vco_recalc_rate, + .prepare = dsi_pll_14nm_vco_prepare, + .unprepare = dsi_pll_14nm_vco_unprepare, +}; + +/* + * N1 and N2 post-divider clock callbacks + */ +#define div_mask(width) ((1 << (width)) - 1) +static unsigned long dsi_pll_14nm_postdiv_recalc_rate(struct clk_hw *hw, + unsigned long parent_rate) +{ + struct dsi_pll_14nm_postdiv *postdiv = to_pll_14nm_postdiv(hw); + struct dsi_pll_14nm *pll_14nm = postdiv->pll; + void __iomem *base = pll_14nm->phy->base; + u8 shift = postdiv->shift; + u8 width = postdiv->width; + u32 val; + + DBG("DSI%d PLL parent rate=%lu", pll_14nm->phy->id, parent_rate); + + val = dsi_phy_read(base + REG_DSI_14nm_PHY_CMN_CLK_CFG0) >> shift; + val &= div_mask(width); + + return divider_recalc_rate(hw, parent_rate, val, NULL, + postdiv->flags, width); +} + +static long dsi_pll_14nm_postdiv_round_rate(struct clk_hw *hw, + unsigned long rate, + unsigned long *prate) +{ + struct dsi_pll_14nm_postdiv *postdiv = to_pll_14nm_postdiv(hw); + struct dsi_pll_14nm *pll_14nm = postdiv->pll; + + DBG("DSI%d PLL parent rate=%lu", pll_14nm->phy->id, rate); + + return divider_round_rate(hw, rate, prate, NULL, + postdiv->width, + postdiv->flags); +} + +static int dsi_pll_14nm_postdiv_set_rate(struct clk_hw *hw, unsigned long rate, + unsigned long parent_rate) +{ + struct dsi_pll_14nm_postdiv *postdiv = to_pll_14nm_postdiv(hw); + struct dsi_pll_14nm *pll_14nm = postdiv->pll; + void __iomem *base = pll_14nm->phy->base; + spinlock_t *lock = &pll_14nm->postdiv_lock; + u8 shift = postdiv->shift; + u8 width = postdiv->width; + unsigned int value; + unsigned long flags = 0; + u32 val; + + DBG("DSI%d PLL parent rate=%lu parent rate %lu", pll_14nm->phy->id, rate, + parent_rate); + + value = divider_get_val(rate, parent_rate, NULL, postdiv->width, + postdiv->flags); + + spin_lock_irqsave(lock, flags); + + val = dsi_phy_read(base + REG_DSI_14nm_PHY_CMN_CLK_CFG0); + val &= ~(div_mask(width) << shift); + + val |= value << shift; + dsi_phy_write(base + REG_DSI_14nm_PHY_CMN_CLK_CFG0, val); + + /* If we're master in dual DSI mode, then the slave PLL's post-dividers + * follow the master's post dividers + */ + if (pll_14nm->phy->usecase == MSM_DSI_PHY_MASTER) { + struct dsi_pll_14nm *pll_14nm_slave = pll_14nm->slave; + void __iomem *slave_base = pll_14nm_slave->phy->base; + + dsi_phy_write(slave_base + REG_DSI_14nm_PHY_CMN_CLK_CFG0, val); + } + + spin_unlock_irqrestore(lock, flags); + + return 0; +} + +static const struct clk_ops clk_ops_dsi_pll_14nm_postdiv = { + .recalc_rate = dsi_pll_14nm_postdiv_recalc_rate, + .round_rate = dsi_pll_14nm_postdiv_round_rate, + .set_rate = dsi_pll_14nm_postdiv_set_rate, +}; + +/* + * PLL Callbacks + */ + +static void dsi_14nm_pll_save_state(struct msm_dsi_phy *phy) +{ + struct dsi_pll_14nm *pll_14nm = to_pll_14nm(phy->vco_hw); + struct pll_14nm_cached_state *cached_state = &pll_14nm->cached_state; + void __iomem *cmn_base = pll_14nm->phy->base; + u32 data; + + data = dsi_phy_read(cmn_base + REG_DSI_14nm_PHY_CMN_CLK_CFG0); + + cached_state->n1postdiv = data & 0xf; + cached_state->n2postdiv = (data >> 4) & 0xf; + + DBG("DSI%d PLL save state %x %x", pll_14nm->phy->id, + cached_state->n1postdiv, cached_state->n2postdiv); + + cached_state->vco_rate = clk_hw_get_rate(phy->vco_hw); +} + +static int dsi_14nm_pll_restore_state(struct msm_dsi_phy *phy) +{ + struct dsi_pll_14nm *pll_14nm = to_pll_14nm(phy->vco_hw); + struct pll_14nm_cached_state *cached_state = &pll_14nm->cached_state; + void __iomem *cmn_base = pll_14nm->phy->base; + u32 data; + int ret; + + ret = dsi_pll_14nm_vco_set_rate(phy->vco_hw, + cached_state->vco_rate, 0); + if (ret) { + DRM_DEV_ERROR(&pll_14nm->phy->pdev->dev, + "restore vco rate failed. ret=%d\n", ret); + return ret; + } + + data = cached_state->n1postdiv | (cached_state->n2postdiv << 4); + + DBG("DSI%d PLL restore state %x %x", pll_14nm->phy->id, + cached_state->n1postdiv, cached_state->n2postdiv); + + dsi_phy_write(cmn_base + REG_DSI_14nm_PHY_CMN_CLK_CFG0, data); + + /* also restore post-dividers for slave DSI PLL */ + if (phy->usecase == MSM_DSI_PHY_MASTER) { + struct dsi_pll_14nm *pll_14nm_slave = pll_14nm->slave; + void __iomem *slave_base = pll_14nm_slave->phy->base; + + dsi_phy_write(slave_base + REG_DSI_14nm_PHY_CMN_CLK_CFG0, data); + } + + return 0; +} + +static int dsi_14nm_set_usecase(struct msm_dsi_phy *phy) +{ + struct dsi_pll_14nm *pll_14nm = to_pll_14nm(phy->vco_hw); + void __iomem *base = phy->pll_base; + u32 clkbuflr_en, bandgap = 0; + + switch (phy->usecase) { + case MSM_DSI_PHY_STANDALONE: + clkbuflr_en = 0x1; + break; + case MSM_DSI_PHY_MASTER: + clkbuflr_en = 0x3; + pll_14nm->slave = pll_14nm_list[(pll_14nm->phy->id + 1) % DSI_MAX]; + break; + case MSM_DSI_PHY_SLAVE: + clkbuflr_en = 0x0; + bandgap = 0x3; + break; + default: + return -EINVAL; + } + + dsi_phy_write(base + REG_DSI_14nm_PHY_PLL_CLKBUFLR_EN, clkbuflr_en); + if (bandgap) + dsi_phy_write(base + REG_DSI_14nm_PHY_PLL_PLL_BANDGAP, bandgap); + + return 0; +} + +static struct clk_hw *pll_14nm_postdiv_register(struct dsi_pll_14nm *pll_14nm, + const char *name, + const char *parent_name, + unsigned long flags, + u8 shift) +{ + struct dsi_pll_14nm_postdiv *pll_postdiv; + struct device *dev = &pll_14nm->phy->pdev->dev; + struct clk_init_data postdiv_init = { + .parent_names = (const char *[]) { parent_name }, + .num_parents = 1, + .name = name, + .flags = flags, + .ops = &clk_ops_dsi_pll_14nm_postdiv, + }; + int ret; + + pll_postdiv = devm_kzalloc(dev, sizeof(*pll_postdiv), GFP_KERNEL); + if (!pll_postdiv) + return ERR_PTR(-ENOMEM); + + pll_postdiv->pll = pll_14nm; + pll_postdiv->shift = shift; + /* both N1 and N2 postdividers are 4 bits wide */ + pll_postdiv->width = 4; + /* range of each divider is from 1 to 15 */ + pll_postdiv->flags = CLK_DIVIDER_ONE_BASED; + pll_postdiv->hw.init = &postdiv_init; + + ret = devm_clk_hw_register(dev, &pll_postdiv->hw); + if (ret) + return ERR_PTR(ret); + + return &pll_postdiv->hw; +} + +static int pll_14nm_register(struct dsi_pll_14nm *pll_14nm, struct clk_hw **provided_clocks) +{ + char clk_name[32], parent[32], vco_name[32]; + struct clk_init_data vco_init = { + .parent_names = (const char *[]){ "xo" }, + .num_parents = 1, + .name = vco_name, + .flags = CLK_IGNORE_UNUSED, + .ops = &clk_ops_dsi_pll_14nm_vco, + }; + struct device *dev = &pll_14nm->phy->pdev->dev; + struct clk_hw *hw; + int ret; + + DBG("DSI%d", pll_14nm->phy->id); + + snprintf(vco_name, 32, "dsi%dvco_clk", pll_14nm->phy->id); + pll_14nm->clk_hw.init = &vco_init; + + ret = devm_clk_hw_register(dev, &pll_14nm->clk_hw); + if (ret) + return ret; + + snprintf(clk_name, 32, "dsi%dn1_postdiv_clk", pll_14nm->phy->id); + snprintf(parent, 32, "dsi%dvco_clk", pll_14nm->phy->id); + + /* N1 postdiv, bits 0-3 in REG_DSI_14nm_PHY_CMN_CLK_CFG0 */ + hw = pll_14nm_postdiv_register(pll_14nm, clk_name, parent, + CLK_SET_RATE_PARENT, 0); + if (IS_ERR(hw)) + return PTR_ERR(hw); + + snprintf(clk_name, 32, "dsi%dpllbyte", pll_14nm->phy->id); + snprintf(parent, 32, "dsi%dn1_postdiv_clk", pll_14nm->phy->id); + + /* DSI Byte clock = VCO_CLK / N1 / 8 */ + hw = devm_clk_hw_register_fixed_factor(dev, clk_name, parent, + CLK_SET_RATE_PARENT, 1, 8); + if (IS_ERR(hw)) + return PTR_ERR(hw); + + provided_clocks[DSI_BYTE_PLL_CLK] = hw; + + snprintf(clk_name, 32, "dsi%dn1_postdivby2_clk", pll_14nm->phy->id); + snprintf(parent, 32, "dsi%dn1_postdiv_clk", pll_14nm->phy->id); + + /* + * Skip the mux for now, force DSICLK_SEL to 1, Add a /2 divider + * on the way. Don't let it set parent. + */ + hw = devm_clk_hw_register_fixed_factor(dev, clk_name, parent, 0, 1, 2); + if (IS_ERR(hw)) + return PTR_ERR(hw); + + snprintf(clk_name, 32, "dsi%dpll", pll_14nm->phy->id); + snprintf(parent, 32, "dsi%dn1_postdivby2_clk", pll_14nm->phy->id); + + /* DSI pixel clock = VCO_CLK / N1 / 2 / N2 + * This is the output of N2 post-divider, bits 4-7 in + * REG_DSI_14nm_PHY_CMN_CLK_CFG0. Don't let it set parent. + */ + hw = pll_14nm_postdiv_register(pll_14nm, clk_name, parent, 0, 4); + if (IS_ERR(hw)) + return PTR_ERR(hw); + + provided_clocks[DSI_PIXEL_PLL_CLK] = hw; + + return 0; +} + +static int dsi_pll_14nm_init(struct msm_dsi_phy *phy) +{ + struct platform_device *pdev = phy->pdev; + struct dsi_pll_14nm *pll_14nm; + int ret; + + if (!pdev) + return -ENODEV; + + pll_14nm = devm_kzalloc(&pdev->dev, sizeof(*pll_14nm), GFP_KERNEL); + if (!pll_14nm) + return -ENOMEM; + + DBG("PLL%d", phy->id); + + pll_14nm_list[phy->id] = pll_14nm; + + spin_lock_init(&pll_14nm->postdiv_lock); + + pll_14nm->phy = phy; + + ret = pll_14nm_register(pll_14nm, phy->provided_clocks->hws); + if (ret) { + DRM_DEV_ERROR(&pdev->dev, "failed to register PLL: %d\n", ret); + return ret; + } + + phy->vco_hw = &pll_14nm->clk_hw; + + return 0; +} + static void dsi_14nm_dphy_set_timing(struct msm_dsi_phy *phy, struct msm_dsi_dphy_timing *timing, int lane_idx) @@ -47,7 +938,7 @@ static void dsi_14nm_dphy_set_timing(struct msm_dsi_phy *phy, DSI_14nm_PHY_LN_TIMING_CTRL_11_TRIG3_CMD(0xa0)); } -static int dsi_14nm_phy_enable(struct msm_dsi_phy *phy, int src_pll_id, +static int dsi_14nm_phy_enable(struct msm_dsi_phy *phy, struct msm_dsi_phy_clk_request *clk_req) { struct msm_dsi_dphy_timing *timing = &phy->timing; @@ -56,6 +947,7 @@ static int dsi_14nm_phy_enable(struct msm_dsi_phy *phy, int src_pll_id, int ret; void __iomem *base = phy->base; void __iomem *lane_base = phy->lane_base; + u32 glbl_test_ctrl; if (msm_dsi_dphy_timing_calc_v2(timing, clk_req)) { DRM_DEV_ERROR(&phy->pdev->dev, @@ -103,11 +995,13 @@ static int dsi_14nm_phy_enable(struct msm_dsi_phy *phy, int src_pll_id, udelay(100); dsi_phy_write(base + REG_DSI_14nm_PHY_CMN_CTRL_1, 0x00); - msm_dsi_phy_set_src_pll(phy, src_pll_id, - REG_DSI_14nm_PHY_CMN_GLBL_TEST_CTRL, - DSI_14nm_PHY_CMN_GLBL_TEST_CTRL_BITCLK_HS_SEL); - - ret = msm_dsi_pll_set_usecase(phy->pll, phy->usecase); + glbl_test_ctrl = dsi_phy_read(base + REG_DSI_14nm_PHY_CMN_GLBL_TEST_CTRL); + if (phy->id == DSI_1 && phy->usecase == MSM_DSI_PHY_SLAVE) + glbl_test_ctrl |= DSI_14nm_PHY_CMN_GLBL_TEST_CTRL_BITCLK_HS_SEL; + else + glbl_test_ctrl &= ~DSI_14nm_PHY_CMN_GLBL_TEST_CTRL_BITCLK_HS_SEL; + dsi_phy_write(base + REG_DSI_14nm_PHY_CMN_GLBL_TEST_CTRL, glbl_test_ctrl); + ret = dsi_14nm_set_usecase(phy); if (ret) { DRM_DEV_ERROR(&phy->pdev->dev, "%s: set pll usecase failed, %d\n", __func__, ret); @@ -129,24 +1023,8 @@ static void dsi_14nm_phy_disable(struct msm_dsi_phy *phy) wmb(); } -static int dsi_14nm_phy_init(struct msm_dsi_phy *phy) -{ - struct platform_device *pdev = phy->pdev; - - phy->lane_base = msm_ioremap(pdev, "dsi_phy_lane", - "DSI_PHY_LANE"); - if (IS_ERR(phy->lane_base)) { - DRM_DEV_ERROR(&pdev->dev, "%s: failed to map phy lane base\n", - __func__); - return -ENOMEM; - } - - return 0; -} - const struct msm_dsi_phy_cfg dsi_phy_14nm_cfgs = { - .type = MSM_DSI_PHY_14NM, - .src_pll_truthtable = { {false, false}, {true, false} }, + .has_phy_lane = true, .reg_cfg = { .num = 1, .regs = { @@ -156,15 +1034,18 @@ const struct msm_dsi_phy_cfg dsi_phy_14nm_cfgs = { .ops = { .enable = dsi_14nm_phy_enable, .disable = dsi_14nm_phy_disable, - .init = dsi_14nm_phy_init, + .pll_init = dsi_pll_14nm_init, + .save_pll_state = dsi_14nm_pll_save_state, + .restore_pll_state = dsi_14nm_pll_restore_state, }, + .min_pll_rate = VCO_MIN_RATE, + .max_pll_rate = VCO_MAX_RATE, .io_start = { 0x994400, 0x996400 }, .num_dsi_phy = 2, }; const struct msm_dsi_phy_cfg dsi_phy_14nm_660_cfgs = { - .type = MSM_DSI_PHY_14NM, - .src_pll_truthtable = { {false, false}, {true, false} }, + .has_phy_lane = true, .reg_cfg = { .num = 1, .regs = { @@ -174,8 +1055,12 @@ const struct msm_dsi_phy_cfg dsi_phy_14nm_660_cfgs = { .ops = { .enable = dsi_14nm_phy_enable, .disable = dsi_14nm_phy_disable, - .init = dsi_14nm_phy_init, + .pll_init = dsi_pll_14nm_init, + .save_pll_state = dsi_14nm_pll_save_state, + .restore_pll_state = dsi_14nm_pll_restore_state, }, + .min_pll_rate = VCO_MIN_RATE, + .max_pll_rate = VCO_MAX_RATE, .io_start = { 0xc994400, 0xc996000 }, .num_dsi_phy = 2, }; diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_20nm.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_20nm.c index eca86bf448f7..e96d789aea18 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_20nm.c +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_20nm.c @@ -63,13 +63,14 @@ static void dsi_20nm_phy_regulator_ctrl(struct msm_dsi_phy *phy, bool enable) dsi_phy_write(base + REG_DSI_20nm_PHY_REGULATOR_CTRL_0, 0x03); } -static int dsi_20nm_phy_enable(struct msm_dsi_phy *phy, int src_pll_id, +static int dsi_20nm_phy_enable(struct msm_dsi_phy *phy, struct msm_dsi_phy_clk_request *clk_req) { struct msm_dsi_dphy_timing *timing = &phy->timing; int i; void __iomem *base = phy->base; u32 cfg_4[4] = {0x20, 0x40, 0x20, 0x00}; + u32 val; DBG(""); @@ -83,9 +84,12 @@ static int dsi_20nm_phy_enable(struct msm_dsi_phy *phy, int src_pll_id, dsi_phy_write(base + REG_DSI_20nm_PHY_STRENGTH_0, 0xff); - msm_dsi_phy_set_src_pll(phy, src_pll_id, - REG_DSI_20nm_PHY_GLBL_TEST_CTRL, - DSI_20nm_PHY_GLBL_TEST_CTRL_BITCLK_HS_SEL); + val = dsi_phy_read(base + REG_DSI_20nm_PHY_GLBL_TEST_CTRL); + if (phy->id == DSI_1 && phy->usecase == MSM_DSI_PHY_STANDALONE) + val |= DSI_20nm_PHY_GLBL_TEST_CTRL_BITCLK_HS_SEL; + else + val &= ~DSI_20nm_PHY_GLBL_TEST_CTRL_BITCLK_HS_SEL; + dsi_phy_write(base + REG_DSI_20nm_PHY_GLBL_TEST_CTRL, val); for (i = 0; i < 4; i++) { dsi_phy_write(base + REG_DSI_20nm_PHY_LN_CFG_3(i), @@ -125,8 +129,7 @@ static void dsi_20nm_phy_disable(struct msm_dsi_phy *phy) } const struct msm_dsi_phy_cfg dsi_phy_20nm_cfgs = { - .type = MSM_DSI_PHY_20NM, - .src_pll_truthtable = { {false, true}, {false, true} }, + .has_phy_regulator = true, .reg_cfg = { .num = 2, .regs = { @@ -137,7 +140,6 @@ const struct msm_dsi_phy_cfg dsi_phy_20nm_cfgs = { .ops = { .enable = dsi_20nm_phy_enable, .disable = dsi_20nm_phy_disable, - .init = msm_dsi_phy_init_common, }, .io_start = { 0xfd998500, 0xfd9a0500 }, .num_dsi_phy = 2, diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm.c index c3c580cfd8b1..3304acda2165 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm.c +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm.c @@ -3,9 +3,621 @@ * Copyright (c) 2015, The Linux Foundation. All rights reserved. */ +#include <linux/clk.h> +#include <linux/clk-provider.h> + #include "dsi_phy.h" #include "dsi.xml.h" +/* + * DSI PLL 28nm - clock diagram (eg: DSI0): + * + * dsi0analog_postdiv_clk + * | dsi0indirect_path_div2_clk + * | | + * +------+ | +----+ | |\ dsi0byte_mux + * dsi0vco_clk --o--| DIV1 |--o--| /2 |--o--| \ | + * | +------+ +----+ | m| | +----+ + * | | u|--o--| /4 |-- dsi0pllbyte + * | | x| +----+ + * o--------------------------| / + * | |/ + * | +------+ + * o----------| DIV3 |------------------------- dsi0pll + * +------+ + */ + +#define POLL_MAX_READS 10 +#define POLL_TIMEOUT_US 50 + +#define VCO_REF_CLK_RATE 19200000 +#define VCO_MIN_RATE 350000000 +#define VCO_MAX_RATE 750000000 + +/* v2.0.0 28nm LP implementation */ +#define DSI_PHY_28NM_QUIRK_PHY_LP BIT(0) + +#define LPFR_LUT_SIZE 10 +struct lpfr_cfg { + unsigned long vco_rate; + u32 resistance; +}; + +/* Loop filter resistance: */ +static const struct lpfr_cfg lpfr_lut[LPFR_LUT_SIZE] = { + { 479500000, 8 }, + { 480000000, 11 }, + { 575500000, 8 }, + { 576000000, 12 }, + { 610500000, 8 }, + { 659500000, 9 }, + { 671500000, 10 }, + { 672000000, 14 }, + { 708500000, 10 }, + { 750000000, 11 }, +}; + +struct pll_28nm_cached_state { + unsigned long vco_rate; + u8 postdiv3; + u8 postdiv1; + u8 byte_mux; +}; + +struct dsi_pll_28nm { + struct clk_hw clk_hw; + + struct msm_dsi_phy *phy; + + struct pll_28nm_cached_state cached_state; +}; + +#define to_pll_28nm(x) container_of(x, struct dsi_pll_28nm, clk_hw) + +static bool pll_28nm_poll_for_ready(struct dsi_pll_28nm *pll_28nm, + u32 nb_tries, u32 timeout_us) +{ + bool pll_locked = false; + u32 val; + + while (nb_tries--) { + val = dsi_phy_read(pll_28nm->phy->pll_base + REG_DSI_28nm_PHY_PLL_STATUS); + pll_locked = !!(val & DSI_28nm_PHY_PLL_STATUS_PLL_RDY); + + if (pll_locked) + break; + + udelay(timeout_us); + } + DBG("DSI PLL is %slocked", pll_locked ? "" : "*not* "); + + return pll_locked; +} + +static void pll_28nm_software_reset(struct dsi_pll_28nm *pll_28nm) +{ + void __iomem *base = pll_28nm->phy->pll_base; + + /* + * Add HW recommended delays after toggling the software + * reset bit off and back on. + */ + dsi_phy_write_udelay(base + REG_DSI_28nm_PHY_PLL_TEST_CFG, + DSI_28nm_PHY_PLL_TEST_CFG_PLL_SW_RESET, 1); + dsi_phy_write_udelay(base + REG_DSI_28nm_PHY_PLL_TEST_CFG, 0x00, 1); +} + +/* + * Clock Callbacks + */ +static int dsi_pll_28nm_clk_set_rate(struct clk_hw *hw, unsigned long rate, + unsigned long parent_rate) +{ + struct dsi_pll_28nm *pll_28nm = to_pll_28nm(hw); + struct device *dev = &pll_28nm->phy->pdev->dev; + void __iomem *base = pll_28nm->phy->pll_base; + unsigned long div_fbx1000, gen_vco_clk; + u32 refclk_cfg, frac_n_mode, frac_n_value; + u32 sdm_cfg0, sdm_cfg1, sdm_cfg2, sdm_cfg3; + u32 cal_cfg10, cal_cfg11; + u32 rem; + int i; + + VERB("rate=%lu, parent's=%lu", rate, parent_rate); + + /* Force postdiv2 to be div-4 */ + dsi_phy_write(base + REG_DSI_28nm_PHY_PLL_POSTDIV2_CFG, 3); + + /* Configure the Loop filter resistance */ + for (i = 0; i < LPFR_LUT_SIZE; i++) + if (rate <= lpfr_lut[i].vco_rate) + break; + if (i == LPFR_LUT_SIZE) { + DRM_DEV_ERROR(dev, "unable to get loop filter resistance. vco=%lu\n", + rate); + return -EINVAL; + } + dsi_phy_write(base + REG_DSI_28nm_PHY_PLL_LPFR_CFG, lpfr_lut[i].resistance); + + /* Loop filter capacitance values : c1 and c2 */ + dsi_phy_write(base + REG_DSI_28nm_PHY_PLL_LPFC1_CFG, 0x70); + dsi_phy_write(base + REG_DSI_28nm_PHY_PLL_LPFC2_CFG, 0x15); + + rem = rate % VCO_REF_CLK_RATE; + if (rem) { + refclk_cfg = DSI_28nm_PHY_PLL_REFCLK_CFG_DBLR; + frac_n_mode = 1; + div_fbx1000 = rate / (VCO_REF_CLK_RATE / 500); + gen_vco_clk = div_fbx1000 * (VCO_REF_CLK_RATE / 500); + } else { + refclk_cfg = 0x0; + frac_n_mode = 0; + div_fbx1000 = rate / (VCO_REF_CLK_RATE / 1000); + gen_vco_clk = div_fbx1000 * (VCO_REF_CLK_RATE / 1000); + } + + DBG("refclk_cfg = %d", refclk_cfg); + + rem = div_fbx1000 % 1000; + frac_n_value = (rem << 16) / 1000; + + DBG("div_fb = %lu", div_fbx1000); + DBG("frac_n_value = %d", frac_n_value); + + DBG("Generated VCO Clock: %lu", gen_vco_clk); + rem = 0; + sdm_cfg1 = dsi_phy_read(base + REG_DSI_28nm_PHY_PLL_SDM_CFG1); + sdm_cfg1 &= ~DSI_28nm_PHY_PLL_SDM_CFG1_DC_OFFSET__MASK; + if (frac_n_mode) { + sdm_cfg0 = 0x0; + sdm_cfg0 |= DSI_28nm_PHY_PLL_SDM_CFG0_BYP_DIV(0); + sdm_cfg1 |= DSI_28nm_PHY_PLL_SDM_CFG1_DC_OFFSET( + (u32)(((div_fbx1000 / 1000) & 0x3f) - 1)); + sdm_cfg3 = frac_n_value >> 8; + sdm_cfg2 = frac_n_value & 0xff; + } else { + sdm_cfg0 = DSI_28nm_PHY_PLL_SDM_CFG0_BYP; + sdm_cfg0 |= DSI_28nm_PHY_PLL_SDM_CFG0_BYP_DIV( + (u32)(((div_fbx1000 / 1000) & 0x3f) - 1)); + sdm_cfg1 |= DSI_28nm_PHY_PLL_SDM_CFG1_DC_OFFSET(0); + sdm_cfg2 = 0; + sdm_cfg3 = 0; + } + + DBG("sdm_cfg0=%d", sdm_cfg0); + DBG("sdm_cfg1=%d", sdm_cfg1); + DBG("sdm_cfg2=%d", sdm_cfg2); + DBG("sdm_cfg3=%d", sdm_cfg3); + + cal_cfg11 = (u32)(gen_vco_clk / (256 * 1000000)); + cal_cfg10 = (u32)((gen_vco_clk % (256 * 1000000)) / 1000000); + DBG("cal_cfg10=%d, cal_cfg11=%d", cal_cfg10, cal_cfg11); + + dsi_phy_write(base + REG_DSI_28nm_PHY_PLL_CHGPUMP_CFG, 0x02); + dsi_phy_write(base + REG_DSI_28nm_PHY_PLL_CAL_CFG3, 0x2b); + dsi_phy_write(base + REG_DSI_28nm_PHY_PLL_CAL_CFG4, 0x06); + dsi_phy_write(base + REG_DSI_28nm_PHY_PLL_LKDET_CFG2, 0x0d); + + dsi_phy_write(base + REG_DSI_28nm_PHY_PLL_SDM_CFG1, sdm_cfg1); + dsi_phy_write(base + REG_DSI_28nm_PHY_PLL_SDM_CFG2, + DSI_28nm_PHY_PLL_SDM_CFG2_FREQ_SEED_7_0(sdm_cfg2)); + dsi_phy_write(base + REG_DSI_28nm_PHY_PLL_SDM_CFG3, + DSI_28nm_PHY_PLL_SDM_CFG3_FREQ_SEED_15_8(sdm_cfg3)); + dsi_phy_write(base + REG_DSI_28nm_PHY_PLL_SDM_CFG4, 0x00); + + /* Add hardware recommended delay for correct PLL configuration */ + if (pll_28nm->phy->cfg->quirks & DSI_PHY_28NM_QUIRK_PHY_LP) + udelay(1000); + else + udelay(1); + + dsi_phy_write(base + REG_DSI_28nm_PHY_PLL_REFCLK_CFG, refclk_cfg); + dsi_phy_write(base + REG_DSI_28nm_PHY_PLL_PWRGEN_CFG, 0x00); + dsi_phy_write(base + REG_DSI_28nm_PHY_PLL_VCOLPF_CFG, 0x31); + dsi_phy_write(base + REG_DSI_28nm_PHY_PLL_SDM_CFG0, sdm_cfg0); + dsi_phy_write(base + REG_DSI_28nm_PHY_PLL_CAL_CFG0, 0x12); + dsi_phy_write(base + REG_DSI_28nm_PHY_PLL_CAL_CFG6, 0x30); + dsi_phy_write(base + REG_DSI_28nm_PHY_PLL_CAL_CFG7, 0x00); + dsi_phy_write(base + REG_DSI_28nm_PHY_PLL_CAL_CFG8, 0x60); + dsi_phy_write(base + REG_DSI_28nm_PHY_PLL_CAL_CFG9, 0x00); + dsi_phy_write(base + REG_DSI_28nm_PHY_PLL_CAL_CFG10, cal_cfg10 & 0xff); + dsi_phy_write(base + REG_DSI_28nm_PHY_PLL_CAL_CFG11, cal_cfg11 & 0xff); + dsi_phy_write(base + REG_DSI_28nm_PHY_PLL_EFUSE_CFG, 0x20); + + return 0; +} + +static int dsi_pll_28nm_clk_is_enabled(struct clk_hw *hw) +{ + struct dsi_pll_28nm *pll_28nm = to_pll_28nm(hw); + + return pll_28nm_poll_for_ready(pll_28nm, POLL_MAX_READS, + POLL_TIMEOUT_US); +} + +static unsigned long dsi_pll_28nm_clk_recalc_rate(struct clk_hw *hw, + unsigned long parent_rate) +{ + struct dsi_pll_28nm *pll_28nm = to_pll_28nm(hw); + void __iomem *base = pll_28nm->phy->pll_base; + u32 sdm0, doubler, sdm_byp_div; + u32 sdm_dc_off, sdm_freq_seed, sdm2, sdm3; + u32 ref_clk = VCO_REF_CLK_RATE; + unsigned long vco_rate; + + VERB("parent_rate=%lu", parent_rate); + + /* Check to see if the ref clk doubler is enabled */ + doubler = dsi_phy_read(base + REG_DSI_28nm_PHY_PLL_REFCLK_CFG) & + DSI_28nm_PHY_PLL_REFCLK_CFG_DBLR; + ref_clk += (doubler * VCO_REF_CLK_RATE); + + /* see if it is integer mode or sdm mode */ + sdm0 = dsi_phy_read(base + REG_DSI_28nm_PHY_PLL_SDM_CFG0); + if (sdm0 & DSI_28nm_PHY_PLL_SDM_CFG0_BYP) { + /* integer mode */ + sdm_byp_div = FIELD( + dsi_phy_read(base + REG_DSI_28nm_PHY_PLL_SDM_CFG0), + DSI_28nm_PHY_PLL_SDM_CFG0_BYP_DIV) + 1; + vco_rate = ref_clk * sdm_byp_div; + } else { + /* sdm mode */ + sdm_dc_off = FIELD( + dsi_phy_read(base + REG_DSI_28nm_PHY_PLL_SDM_CFG1), + DSI_28nm_PHY_PLL_SDM_CFG1_DC_OFFSET); + DBG("sdm_dc_off = %d", sdm_dc_off); + sdm2 = FIELD(dsi_phy_read(base + REG_DSI_28nm_PHY_PLL_SDM_CFG2), + DSI_28nm_PHY_PLL_SDM_CFG2_FREQ_SEED_7_0); + sdm3 = FIELD(dsi_phy_read(base + REG_DSI_28nm_PHY_PLL_SDM_CFG3), + DSI_28nm_PHY_PLL_SDM_CFG3_FREQ_SEED_15_8); + sdm_freq_seed = (sdm3 << 8) | sdm2; + DBG("sdm_freq_seed = %d", sdm_freq_seed); + + vco_rate = (ref_clk * (sdm_dc_off + 1)) + + mult_frac(ref_clk, sdm_freq_seed, BIT(16)); + DBG("vco rate = %lu", vco_rate); + } + + DBG("returning vco rate = %lu", vco_rate); + + return vco_rate; +} + +static int _dsi_pll_28nm_vco_prepare_hpm(struct dsi_pll_28nm *pll_28nm) +{ + struct device *dev = &pll_28nm->phy->pdev->dev; + void __iomem *base = pll_28nm->phy->pll_base; + u32 max_reads = 5, timeout_us = 100; + bool locked; + u32 val; + int i; + + DBG("id=%d", pll_28nm->phy->id); + + pll_28nm_software_reset(pll_28nm); + + /* + * PLL power up sequence. + * Add necessary delays recommended by hardware. + */ + val = DSI_28nm_PHY_PLL_GLB_CFG_PLL_PWRDN_B; + dsi_phy_write_udelay(base + REG_DSI_28nm_PHY_PLL_GLB_CFG, val, 1); + + val |= DSI_28nm_PHY_PLL_GLB_CFG_PLL_PWRGEN_PWRDN_B; + dsi_phy_write_udelay(base + REG_DSI_28nm_PHY_PLL_GLB_CFG, val, 200); + + val |= DSI_28nm_PHY_PLL_GLB_CFG_PLL_LDO_PWRDN_B; + dsi_phy_write_udelay(base + REG_DSI_28nm_PHY_PLL_GLB_CFG, val, 500); + + val |= DSI_28nm_PHY_PLL_GLB_CFG_PLL_ENABLE; + dsi_phy_write_udelay(base + REG_DSI_28nm_PHY_PLL_GLB_CFG, val, 600); + + for (i = 0; i < 2; i++) { + /* DSI Uniphy lock detect setting */ + dsi_phy_write_udelay(base + REG_DSI_28nm_PHY_PLL_LKDET_CFG2, + 0x0c, 100); + dsi_phy_write(base + REG_DSI_28nm_PHY_PLL_LKDET_CFG2, 0x0d); + + /* poll for PLL ready status */ + locked = pll_28nm_poll_for_ready(pll_28nm, + max_reads, timeout_us); + if (locked) + break; + + pll_28nm_software_reset(pll_28nm); + + /* + * PLL power up sequence. + * Add necessary delays recommended by hardware. + */ + val = DSI_28nm_PHY_PLL_GLB_CFG_PLL_PWRDN_B; + dsi_phy_write_udelay(base + REG_DSI_28nm_PHY_PLL_GLB_CFG, val, 1); + + val |= DSI_28nm_PHY_PLL_GLB_CFG_PLL_PWRGEN_PWRDN_B; + dsi_phy_write_udelay(base + REG_DSI_28nm_PHY_PLL_GLB_CFG, val, 200); + + val |= DSI_28nm_PHY_PLL_GLB_CFG_PLL_LDO_PWRDN_B; + dsi_phy_write_udelay(base + REG_DSI_28nm_PHY_PLL_GLB_CFG, val, 250); + + val &= ~DSI_28nm_PHY_PLL_GLB_CFG_PLL_LDO_PWRDN_B; + dsi_phy_write_udelay(base + REG_DSI_28nm_PHY_PLL_GLB_CFG, val, 200); + + val |= DSI_28nm_PHY_PLL_GLB_CFG_PLL_LDO_PWRDN_B; + dsi_phy_write_udelay(base + REG_DSI_28nm_PHY_PLL_GLB_CFG, val, 500); + + val |= DSI_28nm_PHY_PLL_GLB_CFG_PLL_ENABLE; + dsi_phy_write_udelay(base + REG_DSI_28nm_PHY_PLL_GLB_CFG, val, 600); + } + + if (unlikely(!locked)) + DRM_DEV_ERROR(dev, "DSI PLL lock failed\n"); + else + DBG("DSI PLL Lock success"); + + return locked ? 0 : -EINVAL; +} + +static int dsi_pll_28nm_vco_prepare_hpm(struct clk_hw *hw) +{ + struct dsi_pll_28nm *pll_28nm = to_pll_28nm(hw); + int i, ret; + + if (unlikely(pll_28nm->phy->pll_on)) + return 0; + + for (i = 0; i < 3; i++) { + ret = _dsi_pll_28nm_vco_prepare_hpm(pll_28nm); + if (!ret) { + pll_28nm->phy->pll_on = true; + return 0; + } + } + + return ret; +} + +static int dsi_pll_28nm_vco_prepare_lp(struct clk_hw *hw) +{ + struct dsi_pll_28nm *pll_28nm = to_pll_28nm(hw); + struct device *dev = &pll_28nm->phy->pdev->dev; + void __iomem *base = pll_28nm->phy->pll_base; + bool locked; + u32 max_reads = 10, timeout_us = 50; + u32 val; + + DBG("id=%d", pll_28nm->phy->id); + + if (unlikely(pll_28nm->phy->pll_on)) + return 0; + + pll_28nm_software_reset(pll_28nm); + + /* + * PLL power up sequence. + * Add necessary delays recommended by hardware. + */ + dsi_phy_write_ndelay(base + REG_DSI_28nm_PHY_PLL_CAL_CFG1, 0x34, 500); + + val = DSI_28nm_PHY_PLL_GLB_CFG_PLL_PWRDN_B; + dsi_phy_write_ndelay(base + REG_DSI_28nm_PHY_PLL_GLB_CFG, val, 500); + + val |= DSI_28nm_PHY_PLL_GLB_CFG_PLL_PWRGEN_PWRDN_B; + dsi_phy_write_ndelay(base + REG_DSI_28nm_PHY_PLL_GLB_CFG, val, 500); + + val |= DSI_28nm_PHY_PLL_GLB_CFG_PLL_LDO_PWRDN_B | + DSI_28nm_PHY_PLL_GLB_CFG_PLL_ENABLE; + dsi_phy_write_ndelay(base + REG_DSI_28nm_PHY_PLL_GLB_CFG, val, 500); + + /* DSI PLL toggle lock detect setting */ + dsi_phy_write_ndelay(base + REG_DSI_28nm_PHY_PLL_LKDET_CFG2, 0x04, 500); + dsi_phy_write_udelay(base + REG_DSI_28nm_PHY_PLL_LKDET_CFG2, 0x05, 512); + + locked = pll_28nm_poll_for_ready(pll_28nm, max_reads, timeout_us); + + if (unlikely(!locked)) { + DRM_DEV_ERROR(dev, "DSI PLL lock failed\n"); + return -EINVAL; + } + + DBG("DSI PLL lock success"); + pll_28nm->phy->pll_on = true; + + return 0; +} + +static void dsi_pll_28nm_vco_unprepare(struct clk_hw *hw) +{ + struct dsi_pll_28nm *pll_28nm = to_pll_28nm(hw); + + DBG("id=%d", pll_28nm->phy->id); + + if (unlikely(!pll_28nm->phy->pll_on)) + return; + + dsi_phy_write(pll_28nm->phy->pll_base + REG_DSI_28nm_PHY_PLL_GLB_CFG, 0x00); + + pll_28nm->phy->pll_on = false; +} + +static long dsi_pll_28nm_clk_round_rate(struct clk_hw *hw, + unsigned long rate, unsigned long *parent_rate) +{ + struct dsi_pll_28nm *pll_28nm = to_pll_28nm(hw); + + if (rate < pll_28nm->phy->cfg->min_pll_rate) + return pll_28nm->phy->cfg->min_pll_rate; + else if (rate > pll_28nm->phy->cfg->max_pll_rate) + return pll_28nm->phy->cfg->max_pll_rate; + else + return rate; +} + +static const struct clk_ops clk_ops_dsi_pll_28nm_vco_hpm = { + .round_rate = dsi_pll_28nm_clk_round_rate, + .set_rate = dsi_pll_28nm_clk_set_rate, + .recalc_rate = dsi_pll_28nm_clk_recalc_rate, + .prepare = dsi_pll_28nm_vco_prepare_hpm, + .unprepare = dsi_pll_28nm_vco_unprepare, + .is_enabled = dsi_pll_28nm_clk_is_enabled, +}; + +static const struct clk_ops clk_ops_dsi_pll_28nm_vco_lp = { + .round_rate = dsi_pll_28nm_clk_round_rate, + .set_rate = dsi_pll_28nm_clk_set_rate, + .recalc_rate = dsi_pll_28nm_clk_recalc_rate, + .prepare = dsi_pll_28nm_vco_prepare_lp, + .unprepare = dsi_pll_28nm_vco_unprepare, + .is_enabled = dsi_pll_28nm_clk_is_enabled, +}; + +/* + * PLL Callbacks + */ + +static void dsi_28nm_pll_save_state(struct msm_dsi_phy *phy) +{ + struct dsi_pll_28nm *pll_28nm = to_pll_28nm(phy->vco_hw); + struct pll_28nm_cached_state *cached_state = &pll_28nm->cached_state; + void __iomem *base = pll_28nm->phy->pll_base; + + cached_state->postdiv3 = + dsi_phy_read(base + REG_DSI_28nm_PHY_PLL_POSTDIV3_CFG); + cached_state->postdiv1 = + dsi_phy_read(base + REG_DSI_28nm_PHY_PLL_POSTDIV1_CFG); + cached_state->byte_mux = dsi_phy_read(base + REG_DSI_28nm_PHY_PLL_VREG_CFG); + if (dsi_pll_28nm_clk_is_enabled(phy->vco_hw)) + cached_state->vco_rate = clk_hw_get_rate(phy->vco_hw); + else + cached_state->vco_rate = 0; +} + +static int dsi_28nm_pll_restore_state(struct msm_dsi_phy *phy) +{ + struct dsi_pll_28nm *pll_28nm = to_pll_28nm(phy->vco_hw); + struct pll_28nm_cached_state *cached_state = &pll_28nm->cached_state; + void __iomem *base = pll_28nm->phy->pll_base; + int ret; + + ret = dsi_pll_28nm_clk_set_rate(phy->vco_hw, + cached_state->vco_rate, 0); + if (ret) { + DRM_DEV_ERROR(&pll_28nm->phy->pdev->dev, + "restore vco rate failed. ret=%d\n", ret); + return ret; + } + + dsi_phy_write(base + REG_DSI_28nm_PHY_PLL_POSTDIV3_CFG, + cached_state->postdiv3); + dsi_phy_write(base + REG_DSI_28nm_PHY_PLL_POSTDIV1_CFG, + cached_state->postdiv1); + dsi_phy_write(base + REG_DSI_28nm_PHY_PLL_VREG_CFG, + cached_state->byte_mux); + + return 0; +} + +static int pll_28nm_register(struct dsi_pll_28nm *pll_28nm, struct clk_hw **provided_clocks) +{ + char clk_name[32], parent1[32], parent2[32], vco_name[32]; + struct clk_init_data vco_init = { + .parent_names = (const char *[]){ "xo" }, + .num_parents = 1, + .name = vco_name, + .flags = CLK_IGNORE_UNUSED, + }; + struct device *dev = &pll_28nm->phy->pdev->dev; + struct clk_hw *hw; + int ret; + + DBG("%d", pll_28nm->phy->id); + + if (pll_28nm->phy->cfg->quirks & DSI_PHY_28NM_QUIRK_PHY_LP) + vco_init.ops = &clk_ops_dsi_pll_28nm_vco_lp; + else + vco_init.ops = &clk_ops_dsi_pll_28nm_vco_hpm; + + snprintf(vco_name, 32, "dsi%dvco_clk", pll_28nm->phy->id); + pll_28nm->clk_hw.init = &vco_init; + ret = devm_clk_hw_register(dev, &pll_28nm->clk_hw); + if (ret) + return ret; + + snprintf(clk_name, 32, "dsi%danalog_postdiv_clk", pll_28nm->phy->id); + snprintf(parent1, 32, "dsi%dvco_clk", pll_28nm->phy->id); + hw = devm_clk_hw_register_divider(dev, clk_name, + parent1, CLK_SET_RATE_PARENT, + pll_28nm->phy->pll_base + + REG_DSI_28nm_PHY_PLL_POSTDIV1_CFG, + 0, 4, 0, NULL); + if (IS_ERR(hw)) + return PTR_ERR(hw); + + snprintf(clk_name, 32, "dsi%dindirect_path_div2_clk", pll_28nm->phy->id); + snprintf(parent1, 32, "dsi%danalog_postdiv_clk", pll_28nm->phy->id); + hw = devm_clk_hw_register_fixed_factor(dev, clk_name, + parent1, CLK_SET_RATE_PARENT, + 1, 2); + if (IS_ERR(hw)) + return PTR_ERR(hw); + + snprintf(clk_name, 32, "dsi%dpll", pll_28nm->phy->id); + snprintf(parent1, 32, "dsi%dvco_clk", pll_28nm->phy->id); + hw = devm_clk_hw_register_divider(dev, clk_name, + parent1, 0, pll_28nm->phy->pll_base + + REG_DSI_28nm_PHY_PLL_POSTDIV3_CFG, + 0, 8, 0, NULL); + if (IS_ERR(hw)) + return PTR_ERR(hw); + provided_clocks[DSI_PIXEL_PLL_CLK] = hw; + + snprintf(clk_name, 32, "dsi%dbyte_mux", pll_28nm->phy->id); + snprintf(parent1, 32, "dsi%dvco_clk", pll_28nm->phy->id); + snprintf(parent2, 32, "dsi%dindirect_path_div2_clk", pll_28nm->phy->id); + hw = devm_clk_hw_register_mux(dev, clk_name, + ((const char *[]){ + parent1, parent2 + }), 2, CLK_SET_RATE_PARENT, pll_28nm->phy->pll_base + + REG_DSI_28nm_PHY_PLL_VREG_CFG, 1, 1, 0, NULL); + if (IS_ERR(hw)) + return PTR_ERR(hw); + + snprintf(clk_name, 32, "dsi%dpllbyte", pll_28nm->phy->id); + snprintf(parent1, 32, "dsi%dbyte_mux", pll_28nm->phy->id); + hw = devm_clk_hw_register_fixed_factor(dev, clk_name, + parent1, CLK_SET_RATE_PARENT, 1, 4); + if (IS_ERR(hw)) + return PTR_ERR(hw); + provided_clocks[DSI_BYTE_PLL_CLK] = hw; + + return 0; +} + +static int dsi_pll_28nm_init(struct msm_dsi_phy *phy) +{ + struct platform_device *pdev = phy->pdev; + struct dsi_pll_28nm *pll_28nm; + int ret; + + if (!pdev) + return -ENODEV; + + pll_28nm = devm_kzalloc(&pdev->dev, sizeof(*pll_28nm), GFP_KERNEL); + if (!pll_28nm) + return -ENOMEM; + + pll_28nm->phy = phy; + + ret = pll_28nm_register(pll_28nm, phy->provided_clocks->hws); + if (ret) { + DRM_DEV_ERROR(&pdev->dev, "failed to register PLL: %d\n", ret); + return ret; + } + + phy->vco_hw = &pll_28nm->clk_hw; + + return 0; +} + static void dsi_28nm_dphy_set_timing(struct msm_dsi_phy *phy, struct msm_dsi_dphy_timing *timing) { @@ -66,7 +678,7 @@ static void dsi_28nm_phy_regulator_enable_ldo(struct msm_dsi_phy *phy) dsi_phy_write(base + REG_DSI_28nm_PHY_REGULATOR_CTRL_1, 0x1); dsi_phy_write(base + REG_DSI_28nm_PHY_REGULATOR_CTRL_4, 0x20); - if (phy->cfg->type == MSM_DSI_PHY_28NM_LP) + if (phy->cfg->quirks & DSI_PHY_28NM_QUIRK_PHY_LP) dsi_phy_write(phy->base + REG_DSI_28nm_PHY_LDO_CNTRL, 0x05); else dsi_phy_write(phy->base + REG_DSI_28nm_PHY_LDO_CNTRL, 0x0d); @@ -86,12 +698,13 @@ static void dsi_28nm_phy_regulator_ctrl(struct msm_dsi_phy *phy, bool enable) dsi_28nm_phy_regulator_enable_dcdc(phy); } -static int dsi_28nm_phy_enable(struct msm_dsi_phy *phy, int src_pll_id, +static int dsi_28nm_phy_enable(struct msm_dsi_phy *phy, struct msm_dsi_phy_clk_request *clk_req) { struct msm_dsi_dphy_timing *timing = &phy->timing; int i; void __iomem *base = phy->base; + u32 val; DBG(""); @@ -131,9 +744,12 @@ static int dsi_28nm_phy_enable(struct msm_dsi_phy *phy, int src_pll_id, dsi_phy_write(base + REG_DSI_28nm_PHY_CTRL_0, 0x5f); - msm_dsi_phy_set_src_pll(phy, src_pll_id, - REG_DSI_28nm_PHY_GLBL_TEST_CTRL, - DSI_28nm_PHY_GLBL_TEST_CTRL_BITCLK_HS_SEL); + val = dsi_phy_read(base + REG_DSI_28nm_PHY_GLBL_TEST_CTRL); + if (phy->id == DSI_1 && phy->usecase == MSM_DSI_PHY_SLAVE) + val &= ~DSI_28nm_PHY_GLBL_TEST_CTRL_BITCLK_HS_SEL; + else + val |= DSI_28nm_PHY_GLBL_TEST_CTRL_BITCLK_HS_SEL; + dsi_phy_write(base + REG_DSI_28nm_PHY_GLBL_TEST_CTRL, val); return 0; } @@ -151,8 +767,7 @@ static void dsi_28nm_phy_disable(struct msm_dsi_phy *phy) } const struct msm_dsi_phy_cfg dsi_phy_28nm_hpm_cfgs = { - .type = MSM_DSI_PHY_28NM_HPM, - .src_pll_truthtable = { {true, true}, {false, true} }, + .has_phy_regulator = true, .reg_cfg = { .num = 1, .regs = { @@ -162,15 +777,18 @@ const struct msm_dsi_phy_cfg dsi_phy_28nm_hpm_cfgs = { .ops = { .enable = dsi_28nm_phy_enable, .disable = dsi_28nm_phy_disable, - .init = msm_dsi_phy_init_common, + .pll_init = dsi_pll_28nm_init, + .save_pll_state = dsi_28nm_pll_save_state, + .restore_pll_state = dsi_28nm_pll_restore_state, }, + .min_pll_rate = VCO_MIN_RATE, + .max_pll_rate = VCO_MAX_RATE, .io_start = { 0xfd922b00, 0xfd923100 }, .num_dsi_phy = 2, }; const struct msm_dsi_phy_cfg dsi_phy_28nm_hpm_famb_cfgs = { - .type = MSM_DSI_PHY_28NM_HPM, - .src_pll_truthtable = { {true, true}, {false, true} }, + .has_phy_regulator = true, .reg_cfg = { .num = 1, .regs = { @@ -180,15 +798,18 @@ const struct msm_dsi_phy_cfg dsi_phy_28nm_hpm_famb_cfgs = { .ops = { .enable = dsi_28nm_phy_enable, .disable = dsi_28nm_phy_disable, - .init = msm_dsi_phy_init_common, + .pll_init = dsi_pll_28nm_init, + .save_pll_state = dsi_28nm_pll_save_state, + .restore_pll_state = dsi_28nm_pll_restore_state, }, + .min_pll_rate = VCO_MIN_RATE, + .max_pll_rate = VCO_MAX_RATE, .io_start = { 0x1a94400, 0x1a96400 }, .num_dsi_phy = 2, }; const struct msm_dsi_phy_cfg dsi_phy_28nm_lp_cfgs = { - .type = MSM_DSI_PHY_28NM_LP, - .src_pll_truthtable = { {true, true}, {true, true} }, + .has_phy_regulator = true, .reg_cfg = { .num = 1, .regs = { @@ -198,9 +819,14 @@ const struct msm_dsi_phy_cfg dsi_phy_28nm_lp_cfgs = { .ops = { .enable = dsi_28nm_phy_enable, .disable = dsi_28nm_phy_disable, - .init = msm_dsi_phy_init_common, + .pll_init = dsi_pll_28nm_init, + .save_pll_state = dsi_28nm_pll_save_state, + .restore_pll_state = dsi_28nm_pll_restore_state, }, + .min_pll_rate = VCO_MIN_RATE, + .max_pll_rate = VCO_MAX_RATE, .io_start = { 0x1a98500 }, .num_dsi_phy = 1, + .quirks = DSI_PHY_28NM_QUIRK_PHY_LP, }; diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm_8960.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm_8960.c index f22583353957..582b1428f971 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm_8960.c +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm_8960.c @@ -3,11 +3,479 @@ * Copyright (c) 2012-2015, The Linux Foundation. All rights reserved. */ +#include <linux/clk-provider.h> #include <linux/delay.h> #include "dsi_phy.h" #include "dsi.xml.h" +/* + * DSI PLL 28nm (8960/A family) - clock diagram (eg: DSI1): + * + * + * +------+ + * dsi1vco_clk ----o-----| DIV1 |---dsi1pllbit (not exposed as clock) + * F * byte_clk | +------+ + * | bit clock divider (F / 8) + * | + * | +------+ + * o-----| DIV2 |---dsi0pllbyte---o---> To byte RCG + * | +------+ | (sets parent rate) + * | byte clock divider (F) | + * | | + * | o---> To esc RCG + * | (doesn't set parent rate) + * | + * | +------+ + * o-----| DIV3 |----dsi0pll------o---> To dsi RCG + * +------+ | (sets parent rate) + * dsi clock divider (F * magic) | + * | + * o---> To pixel rcg + * (doesn't set parent rate) + */ + +#define POLL_MAX_READS 8000 +#define POLL_TIMEOUT_US 1 + +#define VCO_REF_CLK_RATE 27000000 +#define VCO_MIN_RATE 600000000 +#define VCO_MAX_RATE 1200000000 + +#define VCO_PREF_DIV_RATIO 27 + +struct pll_28nm_cached_state { + unsigned long vco_rate; + u8 postdiv3; + u8 postdiv2; + u8 postdiv1; +}; + +struct clk_bytediv { + struct clk_hw hw; + void __iomem *reg; +}; + +struct dsi_pll_28nm { + struct clk_hw clk_hw; + + struct msm_dsi_phy *phy; + + struct pll_28nm_cached_state cached_state; +}; + +#define to_pll_28nm(x) container_of(x, struct dsi_pll_28nm, clk_hw) + +static bool pll_28nm_poll_for_ready(struct dsi_pll_28nm *pll_28nm, + int nb_tries, int timeout_us) +{ + bool pll_locked = false; + u32 val; + + while (nb_tries--) { + val = dsi_phy_read(pll_28nm->phy->pll_base + REG_DSI_28nm_8960_PHY_PLL_RDY); + pll_locked = !!(val & DSI_28nm_8960_PHY_PLL_RDY_PLL_RDY); + + if (pll_locked) + break; + + udelay(timeout_us); + } + DBG("DSI PLL is %slocked", pll_locked ? "" : "*not* "); + + return pll_locked; +} + +/* + * Clock Callbacks + */ +static int dsi_pll_28nm_clk_set_rate(struct clk_hw *hw, unsigned long rate, + unsigned long parent_rate) +{ + struct dsi_pll_28nm *pll_28nm = to_pll_28nm(hw); + void __iomem *base = pll_28nm->phy->pll_base; + u32 val, temp, fb_divider; + + DBG("rate=%lu, parent's=%lu", rate, parent_rate); + + temp = rate / 10; + val = VCO_REF_CLK_RATE / 10; + fb_divider = (temp * VCO_PREF_DIV_RATIO) / val; + fb_divider = fb_divider / 2 - 1; + dsi_phy_write(base + REG_DSI_28nm_8960_PHY_PLL_CTRL_1, + fb_divider & 0xff); + + val = dsi_phy_read(base + REG_DSI_28nm_8960_PHY_PLL_CTRL_2); + + val |= (fb_divider >> 8) & 0x07; + + dsi_phy_write(base + REG_DSI_28nm_8960_PHY_PLL_CTRL_2, + val); + + val = dsi_phy_read(base + REG_DSI_28nm_8960_PHY_PLL_CTRL_3); + + val |= (VCO_PREF_DIV_RATIO - 1) & 0x3f; + + dsi_phy_write(base + REG_DSI_28nm_8960_PHY_PLL_CTRL_3, + val); + + dsi_phy_write(base + REG_DSI_28nm_8960_PHY_PLL_CTRL_6, + 0xf); + + val = dsi_phy_read(base + REG_DSI_28nm_8960_PHY_PLL_CTRL_8); + val |= 0x7 << 4; + dsi_phy_write(base + REG_DSI_28nm_8960_PHY_PLL_CTRL_8, + val); + + return 0; +} + +static int dsi_pll_28nm_clk_is_enabled(struct clk_hw *hw) +{ + struct dsi_pll_28nm *pll_28nm = to_pll_28nm(hw); + + return pll_28nm_poll_for_ready(pll_28nm, POLL_MAX_READS, + POLL_TIMEOUT_US); +} + +static unsigned long dsi_pll_28nm_clk_recalc_rate(struct clk_hw *hw, + unsigned long parent_rate) +{ + struct dsi_pll_28nm *pll_28nm = to_pll_28nm(hw); + void __iomem *base = pll_28nm->phy->pll_base; + unsigned long vco_rate; + u32 status, fb_divider, temp, ref_divider; + + VERB("parent_rate=%lu", parent_rate); + + status = dsi_phy_read(base + REG_DSI_28nm_8960_PHY_PLL_CTRL_0); + + if (status & DSI_28nm_8960_PHY_PLL_CTRL_0_ENABLE) { + fb_divider = dsi_phy_read(base + REG_DSI_28nm_8960_PHY_PLL_CTRL_1); + fb_divider &= 0xff; + temp = dsi_phy_read(base + REG_DSI_28nm_8960_PHY_PLL_CTRL_2) & 0x07; + fb_divider = (temp << 8) | fb_divider; + fb_divider += 1; + + ref_divider = dsi_phy_read(base + REG_DSI_28nm_8960_PHY_PLL_CTRL_3); + ref_divider &= 0x3f; + ref_divider += 1; + + /* multiply by 2 */ + vco_rate = (parent_rate / ref_divider) * fb_divider * 2; + } else { + vco_rate = 0; + } + + DBG("returning vco rate = %lu", vco_rate); + + return vco_rate; +} + +static int dsi_pll_28nm_vco_prepare(struct clk_hw *hw) +{ + struct dsi_pll_28nm *pll_28nm = to_pll_28nm(hw); + struct device *dev = &pll_28nm->phy->pdev->dev; + void __iomem *base = pll_28nm->phy->pll_base; + bool locked; + unsigned int bit_div, byte_div; + int max_reads = 1000, timeout_us = 100; + u32 val; + + DBG("id=%d", pll_28nm->phy->id); + + if (unlikely(pll_28nm->phy->pll_on)) + return 0; + + /* + * before enabling the PLL, configure the bit clock divider since we + * don't expose it as a clock to the outside world + * 1: read back the byte clock divider that should already be set + * 2: divide by 8 to get bit clock divider + * 3: write it to POSTDIV1 + */ + val = dsi_phy_read(base + REG_DSI_28nm_8960_PHY_PLL_CTRL_9); + byte_div = val + 1; + bit_div = byte_div / 8; + + val = dsi_phy_read(base + REG_DSI_28nm_8960_PHY_PLL_CTRL_8); + val &= ~0xf; + val |= (bit_div - 1); + dsi_phy_write(base + REG_DSI_28nm_8960_PHY_PLL_CTRL_8, val); + + /* enable the PLL */ + dsi_phy_write(base + REG_DSI_28nm_8960_PHY_PLL_CTRL_0, + DSI_28nm_8960_PHY_PLL_CTRL_0_ENABLE); + + locked = pll_28nm_poll_for_ready(pll_28nm, max_reads, timeout_us); + + if (unlikely(!locked)) { + DRM_DEV_ERROR(dev, "DSI PLL lock failed\n"); + return -EINVAL; + } + + DBG("DSI PLL lock success"); + pll_28nm->phy->pll_on = true; + + return 0; +} + +static void dsi_pll_28nm_vco_unprepare(struct clk_hw *hw) +{ + struct dsi_pll_28nm *pll_28nm = to_pll_28nm(hw); + + DBG("id=%d", pll_28nm->phy->id); + + if (unlikely(!pll_28nm->phy->pll_on)) + return; + + dsi_phy_write(pll_28nm->phy->pll_base + REG_DSI_28nm_8960_PHY_PLL_CTRL_0, 0x00); + + pll_28nm->phy->pll_on = false; +} + +static long dsi_pll_28nm_clk_round_rate(struct clk_hw *hw, + unsigned long rate, unsigned long *parent_rate) +{ + struct dsi_pll_28nm *pll_28nm = to_pll_28nm(hw); + + if (rate < pll_28nm->phy->cfg->min_pll_rate) + return pll_28nm->phy->cfg->min_pll_rate; + else if (rate > pll_28nm->phy->cfg->max_pll_rate) + return pll_28nm->phy->cfg->max_pll_rate; + else + return rate; +} + +static const struct clk_ops clk_ops_dsi_pll_28nm_vco = { + .round_rate = dsi_pll_28nm_clk_round_rate, + .set_rate = dsi_pll_28nm_clk_set_rate, + .recalc_rate = dsi_pll_28nm_clk_recalc_rate, + .prepare = dsi_pll_28nm_vco_prepare, + .unprepare = dsi_pll_28nm_vco_unprepare, + .is_enabled = dsi_pll_28nm_clk_is_enabled, +}; + +/* + * Custom byte clock divier clk_ops + * + * This clock is the entry point to configuring the PLL. The user (dsi host) + * will set this clock's rate to the desired byte clock rate. The VCO lock + * frequency is a multiple of the byte clock rate. The multiplication factor + * (shown as F in the diagram above) is a function of the byte clock rate. + * + * This custom divider clock ensures that its parent (VCO) is set to the + * desired rate, and that the byte clock postdivider (POSTDIV2) is configured + * accordingly + */ +#define to_clk_bytediv(_hw) container_of(_hw, struct clk_bytediv, hw) + +static unsigned long clk_bytediv_recalc_rate(struct clk_hw *hw, + unsigned long parent_rate) +{ + struct clk_bytediv *bytediv = to_clk_bytediv(hw); + unsigned int div; + + div = dsi_phy_read(bytediv->reg) & 0xff; + + return parent_rate / (div + 1); +} + +/* find multiplication factor(wrt byte clock) at which the VCO should be set */ +static unsigned int get_vco_mul_factor(unsigned long byte_clk_rate) +{ + unsigned long bit_mhz; + + /* convert to bit clock in Mhz */ + bit_mhz = (byte_clk_rate * 8) / 1000000; + + if (bit_mhz < 125) + return 64; + else if (bit_mhz < 250) + return 32; + else if (bit_mhz < 600) + return 16; + else + return 8; +} + +static long clk_bytediv_round_rate(struct clk_hw *hw, unsigned long rate, + unsigned long *prate) +{ + unsigned long best_parent; + unsigned int factor; + + factor = get_vco_mul_factor(rate); + + best_parent = rate * factor; + *prate = clk_hw_round_rate(clk_hw_get_parent(hw), best_parent); + + return *prate / factor; +} + +static int clk_bytediv_set_rate(struct clk_hw *hw, unsigned long rate, + unsigned long parent_rate) +{ + struct clk_bytediv *bytediv = to_clk_bytediv(hw); + u32 val; + unsigned int factor; + + factor = get_vco_mul_factor(rate); + + val = dsi_phy_read(bytediv->reg); + val |= (factor - 1) & 0xff; + dsi_phy_write(bytediv->reg, val); + + return 0; +} + +/* Our special byte clock divider ops */ +static const struct clk_ops clk_bytediv_ops = { + .round_rate = clk_bytediv_round_rate, + .set_rate = clk_bytediv_set_rate, + .recalc_rate = clk_bytediv_recalc_rate, +}; + +/* + * PLL Callbacks + */ +static void dsi_28nm_pll_save_state(struct msm_dsi_phy *phy) +{ + struct dsi_pll_28nm *pll_28nm = to_pll_28nm(phy->vco_hw); + struct pll_28nm_cached_state *cached_state = &pll_28nm->cached_state; + void __iomem *base = pll_28nm->phy->pll_base; + + cached_state->postdiv3 = + dsi_phy_read(base + REG_DSI_28nm_8960_PHY_PLL_CTRL_10); + cached_state->postdiv2 = + dsi_phy_read(base + REG_DSI_28nm_8960_PHY_PLL_CTRL_9); + cached_state->postdiv1 = + dsi_phy_read(base + REG_DSI_28nm_8960_PHY_PLL_CTRL_8); + + cached_state->vco_rate = clk_hw_get_rate(phy->vco_hw); +} + +static int dsi_28nm_pll_restore_state(struct msm_dsi_phy *phy) +{ + struct dsi_pll_28nm *pll_28nm = to_pll_28nm(phy->vco_hw); + struct pll_28nm_cached_state *cached_state = &pll_28nm->cached_state; + void __iomem *base = pll_28nm->phy->pll_base; + int ret; + + ret = dsi_pll_28nm_clk_set_rate(phy->vco_hw, + cached_state->vco_rate, 0); + if (ret) { + DRM_DEV_ERROR(&pll_28nm->phy->pdev->dev, + "restore vco rate failed. ret=%d\n", ret); + return ret; + } + + dsi_phy_write(base + REG_DSI_28nm_8960_PHY_PLL_CTRL_10, + cached_state->postdiv3); + dsi_phy_write(base + REG_DSI_28nm_8960_PHY_PLL_CTRL_9, + cached_state->postdiv2); + dsi_phy_write(base + REG_DSI_28nm_8960_PHY_PLL_CTRL_8, + cached_state->postdiv1); + + return 0; +} + +static int pll_28nm_register(struct dsi_pll_28nm *pll_28nm, struct clk_hw **provided_clocks) +{ + char *clk_name, *parent_name, *vco_name; + struct clk_init_data vco_init = { + .parent_names = (const char *[]){ "pxo" }, + .num_parents = 1, + .flags = CLK_IGNORE_UNUSED, + .ops = &clk_ops_dsi_pll_28nm_vco, + }; + struct device *dev = &pll_28nm->phy->pdev->dev; + struct clk_hw *hw; + struct clk_bytediv *bytediv; + struct clk_init_data bytediv_init = { }; + int ret; + + DBG("%d", pll_28nm->phy->id); + + bytediv = devm_kzalloc(dev, sizeof(*bytediv), GFP_KERNEL); + if (!bytediv) + return -ENOMEM; + + vco_name = devm_kzalloc(dev, 32, GFP_KERNEL); + if (!vco_name) + return -ENOMEM; + + clk_name = devm_kzalloc(dev, 32, GFP_KERNEL); + if (!clk_name) + return -ENOMEM; + + snprintf(vco_name, 32, "dsi%dvco_clk", pll_28nm->phy->id); + vco_init.name = vco_name; + + pll_28nm->clk_hw.init = &vco_init; + + ret = devm_clk_hw_register(dev, &pll_28nm->clk_hw); + if (ret) + return ret; + + /* prepare and register bytediv */ + bytediv->hw.init = &bytediv_init; + bytediv->reg = pll_28nm->phy->pll_base + REG_DSI_28nm_8960_PHY_PLL_CTRL_9; + + snprintf(parent_name, 32, "dsi%dvco_clk", pll_28nm->phy->id); + snprintf(clk_name, 32, "dsi%dpllbyte", pll_28nm->phy->id); + + bytediv_init.name = clk_name; + bytediv_init.ops = &clk_bytediv_ops; + bytediv_init.flags = CLK_SET_RATE_PARENT; + bytediv_init.parent_names = (const char * const *) &parent_name; + bytediv_init.num_parents = 1; + + /* DIV2 */ + ret = devm_clk_hw_register(dev, &bytediv->hw); + if (ret) + return ret; + provided_clocks[DSI_BYTE_PLL_CLK] = &bytediv->hw; + + snprintf(clk_name, 32, "dsi%dpll", pll_28nm->phy->id); + /* DIV3 */ + hw = devm_clk_hw_register_divider(dev, clk_name, + parent_name, 0, pll_28nm->phy->pll_base + + REG_DSI_28nm_8960_PHY_PLL_CTRL_10, + 0, 8, 0, NULL); + if (IS_ERR(hw)) + return PTR_ERR(hw); + provided_clocks[DSI_PIXEL_PLL_CLK] = hw; + + return 0; +} + +static int dsi_pll_28nm_8960_init(struct msm_dsi_phy *phy) +{ + struct platform_device *pdev = phy->pdev; + struct dsi_pll_28nm *pll_28nm; + int ret; + + if (!pdev) + return -ENODEV; + + pll_28nm = devm_kzalloc(&pdev->dev, sizeof(*pll_28nm), GFP_KERNEL); + if (!pll_28nm) + return -ENOMEM; + + pll_28nm->phy = phy; + + ret = pll_28nm_register(pll_28nm, phy->provided_clocks->hws); + if (ret) { + DRM_DEV_ERROR(&pdev->dev, "failed to register PLL: %d\n", ret); + return ret; + } + + phy->vco_hw = &pll_28nm->clk_hw; + + return 0; +} + static void dsi_28nm_dphy_set_timing(struct msm_dsi_phy *phy, struct msm_dsi_dphy_timing *timing) { @@ -117,7 +585,7 @@ static void dsi_28nm_phy_lane_config(struct msm_dsi_phy *phy) dsi_phy_write(base + REG_DSI_28nm_8960_PHY_LNCK_TEST_STR1, 0x88); } -static int dsi_28nm_phy_enable(struct msm_dsi_phy *phy, int src_pll_id, +static int dsi_28nm_phy_enable(struct msm_dsi_phy *phy, struct msm_dsi_phy_clk_request *clk_req) { struct msm_dsi_dphy_timing *timing = &phy->timing; @@ -174,8 +642,7 @@ static void dsi_28nm_phy_disable(struct msm_dsi_phy *phy) } const struct msm_dsi_phy_cfg dsi_phy_28nm_8960_cfgs = { - .type = MSM_DSI_PHY_28NM_8960, - .src_pll_truthtable = { {true, true}, {false, true} }, + .has_phy_regulator = true, .reg_cfg = { .num = 1, .regs = { @@ -185,8 +652,12 @@ const struct msm_dsi_phy_cfg dsi_phy_28nm_8960_cfgs = { .ops = { .enable = dsi_28nm_phy_enable, .disable = dsi_28nm_phy_disable, - .init = msm_dsi_phy_init_common, + .pll_init = dsi_pll_28nm_8960_init, + .save_pll_state = dsi_28nm_pll_save_state, + .restore_pll_state = dsi_28nm_pll_restore_state, }, + .min_pll_rate = VCO_MIN_RATE, + .max_pll_rate = VCO_MAX_RATE, .io_start = { 0x4700300, 0x5800300 }, .num_dsi_phy = 2, }; diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c index 79c034ae075d..e76ce40a12ab 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c @@ -3,11 +3,743 @@ * Copyright (c) 2018, The Linux Foundation */ +#include <linux/clk.h> +#include <linux/clk-provider.h> #include <linux/iopoll.h> #include "dsi_phy.h" #include "dsi.xml.h" +/* + * DSI PLL 7nm - clock diagram (eg: DSI0): TODO: updated CPHY diagram + * + * dsi0_pll_out_div_clk dsi0_pll_bit_clk + * | | + * | | + * +---------+ | +----------+ | +----+ + * dsi0vco_clk ---| out_div |--o--| divl_3_0 |--o--| /8 |-- dsi0_phy_pll_out_byteclk + * +---------+ | +----------+ | +----+ + * | | + * | | dsi0_pll_by_2_bit_clk + * | | | + * | | +----+ | |\ dsi0_pclk_mux + * | |--| /2 |--o--| \ | + * | | +----+ | \ | +---------+ + * | --------------| |--o--| div_7_4 |-- dsi0_phy_pll_out_dsiclk + * |------------------------------| / +---------+ + * | +-----+ | / + * -----------| /4? |--o----------|/ + * +-----+ | | + * | |dsiclk_sel + * | + * dsi0_pll_post_out_div_clk + */ + +#define VCO_REF_CLK_RATE 19200000 +#define FRAC_BITS 18 + +/* Hardware is V4.1 */ +#define DSI_PHY_7NM_QUIRK_V4_1 BIT(0) + +struct dsi_pll_config { + bool enable_ssc; + bool ssc_center; + u32 ssc_freq; + u32 ssc_offset; + u32 ssc_adj_per; + + /* out */ + u32 decimal_div_start; + u32 frac_div_start; + u32 pll_clock_inverters; + u32 ssc_stepsize; + u32 ssc_div_per; +}; + +struct pll_7nm_cached_state { + unsigned long vco_rate; + u8 bit_clk_div; + u8 pix_clk_div; + u8 pll_out_div; + u8 pll_mux; +}; + +struct dsi_pll_7nm { + struct clk_hw clk_hw; + + struct msm_dsi_phy *phy; + + u64 vco_current_rate; + + /* protects REG_DSI_7nm_PHY_CMN_CLK_CFG0 register */ + spinlock_t postdiv_lock; + + struct pll_7nm_cached_state cached_state; + + struct dsi_pll_7nm *slave; +}; + +#define to_pll_7nm(x) container_of(x, struct dsi_pll_7nm, clk_hw) + +/* + * Global list of private DSI PLL struct pointers. We need this for Dual DSI + * mode, where the master PLL's clk_ops needs access the slave's private data + */ +static struct dsi_pll_7nm *pll_7nm_list[DSI_MAX]; + +static void dsi_pll_setup_config(struct dsi_pll_config *config) +{ + config->ssc_freq = 31500; + config->ssc_offset = 4800; + config->ssc_adj_per = 2; + + /* TODO: ssc enable */ + config->enable_ssc = false; + config->ssc_center = 0; +} + +static void dsi_pll_calc_dec_frac(struct dsi_pll_7nm *pll, struct dsi_pll_config *config) +{ + u64 fref = VCO_REF_CLK_RATE; + u64 pll_freq; + u64 divider; + u64 dec, dec_multiple; + u32 frac; + u64 multiplier; + + pll_freq = pll->vco_current_rate; + + divider = fref * 2; + + multiplier = 1 << FRAC_BITS; + dec_multiple = div_u64(pll_freq * multiplier, divider); + div_u64_rem(dec_multiple, multiplier, &frac); + + dec = div_u64(dec_multiple, multiplier); + + if (!(pll->phy->cfg->quirks & DSI_PHY_7NM_QUIRK_V4_1)) + config->pll_clock_inverters = 0x28; + else if (pll_freq <= 1000000000ULL) + config->pll_clock_inverters = 0xa0; + else if (pll_freq <= 2500000000ULL) + config->pll_clock_inverters = 0x20; + else if (pll_freq <= 3020000000ULL) + config->pll_clock_inverters = 0x00; + else + config->pll_clock_inverters = 0x40; + + config->decimal_div_start = dec; + config->frac_div_start = frac; +} + +#define SSC_CENTER BIT(0) +#define SSC_EN BIT(1) + +static void dsi_pll_calc_ssc(struct dsi_pll_7nm *pll, struct dsi_pll_config *config) +{ + u32 ssc_per; + u32 ssc_mod; + u64 ssc_step_size; + u64 frac; + + if (!config->enable_ssc) { + DBG("SSC not enabled\n"); + return; + } + + ssc_per = DIV_ROUND_CLOSEST(VCO_REF_CLK_RATE, config->ssc_freq) / 2 - 1; + ssc_mod = (ssc_per + 1) % (config->ssc_adj_per + 1); + ssc_per -= ssc_mod; + + frac = config->frac_div_start; + ssc_step_size = config->decimal_div_start; + ssc_step_size *= (1 << FRAC_BITS); + ssc_step_size += frac; + ssc_step_size *= config->ssc_offset; + ssc_step_size *= (config->ssc_adj_per + 1); + ssc_step_size = div_u64(ssc_step_size, (ssc_per + 1)); + ssc_step_size = DIV_ROUND_CLOSEST_ULL(ssc_step_size, 1000000); + + config->ssc_div_per = ssc_per; + config->ssc_stepsize = ssc_step_size; + + pr_debug("SCC: Dec:%d, frac:%llu, frac_bits:%d\n", + config->decimal_div_start, frac, FRAC_BITS); + pr_debug("SSC: div_per:0x%X, stepsize:0x%X, adjper:0x%X\n", + ssc_per, (u32)ssc_step_size, config->ssc_adj_per); +} + +static void dsi_pll_ssc_commit(struct dsi_pll_7nm *pll, struct dsi_pll_config *config) +{ + void __iomem *base = pll->phy->pll_base; + + if (config->enable_ssc) { + pr_debug("SSC is enabled\n"); + + dsi_phy_write(base + REG_DSI_7nm_PHY_PLL_SSC_STEPSIZE_LOW_1, + config->ssc_stepsize & 0xff); + dsi_phy_write(base + REG_DSI_7nm_PHY_PLL_SSC_STEPSIZE_HIGH_1, + config->ssc_stepsize >> 8); + dsi_phy_write(base + REG_DSI_7nm_PHY_PLL_SSC_DIV_PER_LOW_1, + config->ssc_div_per & 0xff); + dsi_phy_write(base + REG_DSI_7nm_PHY_PLL_SSC_DIV_PER_HIGH_1, + config->ssc_div_per >> 8); + dsi_phy_write(base + REG_DSI_7nm_PHY_PLL_SSC_ADJPER_LOW_1, + config->ssc_adj_per & 0xff); + dsi_phy_write(base + REG_DSI_7nm_PHY_PLL_SSC_ADJPER_HIGH_1, + config->ssc_adj_per >> 8); + dsi_phy_write(base + REG_DSI_7nm_PHY_PLL_SSC_CONTROL, + SSC_EN | (config->ssc_center ? SSC_CENTER : 0)); + } +} + +static void dsi_pll_config_hzindep_reg(struct dsi_pll_7nm *pll) +{ + void __iomem *base = pll->phy->pll_base; + u8 analog_controls_five_1 = 0x01, vco_config_1 = 0x00; + + if (pll->phy->cfg->quirks & DSI_PHY_7NM_QUIRK_V4_1) { + if (pll->vco_current_rate >= 3100000000ULL) + analog_controls_five_1 = 0x03; + + if (pll->vco_current_rate < 1520000000ULL) + vco_config_1 = 0x08; + else if (pll->vco_current_rate < 2990000000ULL) + vco_config_1 = 0x01; + } + + dsi_phy_write(base + REG_DSI_7nm_PHY_PLL_ANALOG_CONTROLS_FIVE_1, + analog_controls_five_1); + dsi_phy_write(base + REG_DSI_7nm_PHY_PLL_VCO_CONFIG_1, vco_config_1); + dsi_phy_write(base + REG_DSI_7nm_PHY_PLL_ANALOG_CONTROLS_FIVE, 0x01); + dsi_phy_write(base + REG_DSI_7nm_PHY_PLL_ANALOG_CONTROLS_TWO, 0x03); + dsi_phy_write(base + REG_DSI_7nm_PHY_PLL_ANALOG_CONTROLS_THREE, 0x00); + dsi_phy_write(base + REG_DSI_7nm_PHY_PLL_DSM_DIVIDER, 0x00); + dsi_phy_write(base + REG_DSI_7nm_PHY_PLL_FEEDBACK_DIVIDER, 0x4e); + dsi_phy_write(base + REG_DSI_7nm_PHY_PLL_CALIBRATION_SETTINGS, 0x40); + dsi_phy_write(base + REG_DSI_7nm_PHY_PLL_BAND_SEL_CAL_SETTINGS_THREE, 0xba); + dsi_phy_write(base + REG_DSI_7nm_PHY_PLL_FREQ_DETECT_SETTINGS_ONE, 0x0c); + dsi_phy_write(base + REG_DSI_7nm_PHY_PLL_OUTDIV, 0x00); + dsi_phy_write(base + REG_DSI_7nm_PHY_PLL_CORE_OVERRIDE, 0x00); + dsi_phy_write(base + REG_DSI_7nm_PHY_PLL_PLL_DIGITAL_TIMERS_TWO, 0x08); + dsi_phy_write(base + REG_DSI_7nm_PHY_PLL_PLL_PROP_GAIN_RATE_1, 0x0a); + dsi_phy_write(base + REG_DSI_7nm_PHY_PLL_PLL_BAND_SEL_RATE_1, 0xc0); + dsi_phy_write(base + REG_DSI_7nm_PHY_PLL_PLL_INT_GAIN_IFILT_BAND_1, 0x84); + dsi_phy_write(base + REG_DSI_7nm_PHY_PLL_PLL_INT_GAIN_IFILT_BAND_1, 0x82); + dsi_phy_write(base + REG_DSI_7nm_PHY_PLL_PLL_FL_INT_GAIN_PFILT_BAND_1, 0x4c); + dsi_phy_write(base + REG_DSI_7nm_PHY_PLL_PLL_LOCK_OVERRIDE, 0x80); + dsi_phy_write(base + REG_DSI_7nm_PHY_PLL_PFILT, 0x29); + dsi_phy_write(base + REG_DSI_7nm_PHY_PLL_PFILT, 0x2f); + dsi_phy_write(base + REG_DSI_7nm_PHY_PLL_IFILT, 0x2a); + dsi_phy_write(base + REG_DSI_7nm_PHY_PLL_IFILT, + pll->phy->cfg->quirks & DSI_PHY_7NM_QUIRK_V4_1 ? 0x3f : 0x22); + + if (pll->phy->cfg->quirks & DSI_PHY_7NM_QUIRK_V4_1) { + dsi_phy_write(base + REG_DSI_7nm_PHY_PLL_PERF_OPTIMIZE, 0x22); + if (pll->slave) + dsi_phy_write(pll->slave->phy->pll_base + REG_DSI_7nm_PHY_PLL_PERF_OPTIMIZE, 0x22); + } +} + +static void dsi_pll_commit(struct dsi_pll_7nm *pll, struct dsi_pll_config *config) +{ + void __iomem *base = pll->phy->pll_base; + + dsi_phy_write(base + REG_DSI_7nm_PHY_PLL_CORE_INPUT_OVERRIDE, 0x12); + dsi_phy_write(base + REG_DSI_7nm_PHY_PLL_DECIMAL_DIV_START_1, config->decimal_div_start); + dsi_phy_write(base + REG_DSI_7nm_PHY_PLL_FRAC_DIV_START_LOW_1, + config->frac_div_start & 0xff); + dsi_phy_write(base + REG_DSI_7nm_PHY_PLL_FRAC_DIV_START_MID_1, + (config->frac_div_start & 0xff00) >> 8); + dsi_phy_write(base + REG_DSI_7nm_PHY_PLL_FRAC_DIV_START_HIGH_1, + (config->frac_div_start & 0x30000) >> 16); + dsi_phy_write(base + REG_DSI_7nm_PHY_PLL_PLL_LOCKDET_RATE_1, 0x40); + dsi_phy_write(base + REG_DSI_7nm_PHY_PLL_PLL_LOCK_DELAY, 0x06); + dsi_phy_write(base + REG_DSI_7nm_PHY_PLL_CMODE_1, 0x10); /* TODO: 0x00 for CPHY */ + dsi_phy_write(base + REG_DSI_7nm_PHY_PLL_CLOCK_INVERTERS, config->pll_clock_inverters); +} + +static int dsi_pll_7nm_vco_set_rate(struct clk_hw *hw, unsigned long rate, + unsigned long parent_rate) +{ + struct dsi_pll_7nm *pll_7nm = to_pll_7nm(hw); + struct dsi_pll_config config; + + DBG("DSI PLL%d rate=%lu, parent's=%lu", pll_7nm->phy->id, rate, + parent_rate); + + pll_7nm->vco_current_rate = rate; + + dsi_pll_setup_config(&config); + + dsi_pll_calc_dec_frac(pll_7nm, &config); + + dsi_pll_calc_ssc(pll_7nm, &config); + + dsi_pll_commit(pll_7nm, &config); + + dsi_pll_config_hzindep_reg(pll_7nm); + + dsi_pll_ssc_commit(pll_7nm, &config); + + /* flush, ensure all register writes are done*/ + wmb(); + + return 0; +} + +static int dsi_pll_7nm_lock_status(struct dsi_pll_7nm *pll) +{ + int rc; + u32 status = 0; + u32 const delay_us = 100; + u32 const timeout_us = 5000; + + rc = readl_poll_timeout_atomic(pll->phy->pll_base + + REG_DSI_7nm_PHY_PLL_COMMON_STATUS_ONE, + status, + ((status & BIT(0)) > 0), + delay_us, + timeout_us); + if (rc) + pr_err("DSI PLL(%d) lock failed, status=0x%08x\n", + pll->phy->id, status); + + return rc; +} + +static void dsi_pll_disable_pll_bias(struct dsi_pll_7nm *pll) +{ + u32 data = dsi_phy_read(pll->phy->base + REG_DSI_7nm_PHY_CMN_CTRL_0); + + dsi_phy_write(pll->phy->pll_base + REG_DSI_7nm_PHY_PLL_SYSTEM_MUXES, 0); + dsi_phy_write(pll->phy->base + REG_DSI_7nm_PHY_CMN_CTRL_0, data & ~BIT(5)); + ndelay(250); +} + +static void dsi_pll_enable_pll_bias(struct dsi_pll_7nm *pll) +{ + u32 data = dsi_phy_read(pll->phy->base + REG_DSI_7nm_PHY_CMN_CTRL_0); + + dsi_phy_write(pll->phy->base + REG_DSI_7nm_PHY_CMN_CTRL_0, data | BIT(5)); + dsi_phy_write(pll->phy->pll_base + REG_DSI_7nm_PHY_PLL_SYSTEM_MUXES, 0xc0); + ndelay(250); +} + +static void dsi_pll_disable_global_clk(struct dsi_pll_7nm *pll) +{ + u32 data; + + data = dsi_phy_read(pll->phy->base + REG_DSI_7nm_PHY_CMN_CLK_CFG1); + dsi_phy_write(pll->phy->base + REG_DSI_7nm_PHY_CMN_CLK_CFG1, data & ~BIT(5)); +} + +static void dsi_pll_enable_global_clk(struct dsi_pll_7nm *pll) +{ + u32 data; + + dsi_phy_write(pll->phy->base + REG_DSI_7nm_PHY_CMN_CTRL_3, 0x04); + + data = dsi_phy_read(pll->phy->base + REG_DSI_7nm_PHY_CMN_CLK_CFG1); + dsi_phy_write(pll->phy->base + REG_DSI_7nm_PHY_CMN_CLK_CFG1, + data | BIT(5) | BIT(4)); +} + +static void dsi_pll_phy_dig_reset(struct dsi_pll_7nm *pll) +{ + /* + * Reset the PHY digital domain. This would be needed when + * coming out of a CX or analog rail power collapse while + * ensuring that the pads maintain LP00 or LP11 state + */ + dsi_phy_write(pll->phy->base + REG_DSI_7nm_PHY_CMN_GLBL_DIGTOP_SPARE4, BIT(0)); + wmb(); /* Ensure that the reset is deasserted */ + dsi_phy_write(pll->phy->base + REG_DSI_7nm_PHY_CMN_GLBL_DIGTOP_SPARE4, 0x0); + wmb(); /* Ensure that the reset is deasserted */ +} + +static int dsi_pll_7nm_vco_prepare(struct clk_hw *hw) +{ + struct dsi_pll_7nm *pll_7nm = to_pll_7nm(hw); + int rc; + + dsi_pll_enable_pll_bias(pll_7nm); + if (pll_7nm->slave) + dsi_pll_enable_pll_bias(pll_7nm->slave); + + /* Start PLL */ + dsi_phy_write(pll_7nm->phy->base + REG_DSI_7nm_PHY_CMN_PLL_CNTRL, 0x01); + + /* + * ensure all PLL configurations are written prior to checking + * for PLL lock. + */ + wmb(); + + /* Check for PLL lock */ + rc = dsi_pll_7nm_lock_status(pll_7nm); + if (rc) { + pr_err("PLL(%d) lock failed\n", pll_7nm->phy->id); + goto error; + } + + pll_7nm->phy->pll_on = true; + + /* + * assert power on reset for PHY digital in case the PLL is + * enabled after CX of analog domain power collapse. This needs + * to be done before enabling the global clk. + */ + dsi_pll_phy_dig_reset(pll_7nm); + if (pll_7nm->slave) + dsi_pll_phy_dig_reset(pll_7nm->slave); + + dsi_pll_enable_global_clk(pll_7nm); + if (pll_7nm->slave) + dsi_pll_enable_global_clk(pll_7nm->slave); + +error: + return rc; +} + +static void dsi_pll_disable_sub(struct dsi_pll_7nm *pll) +{ + dsi_phy_write(pll->phy->base + REG_DSI_7nm_PHY_CMN_RBUF_CTRL, 0); + dsi_pll_disable_pll_bias(pll); +} + +static void dsi_pll_7nm_vco_unprepare(struct clk_hw *hw) +{ + struct dsi_pll_7nm *pll_7nm = to_pll_7nm(hw); + + /* + * To avoid any stray glitches while abruptly powering down the PLL + * make sure to gate the clock using the clock enable bit before + * powering down the PLL + */ + dsi_pll_disable_global_clk(pll_7nm); + dsi_phy_write(pll_7nm->phy->base + REG_DSI_7nm_PHY_CMN_PLL_CNTRL, 0); + dsi_pll_disable_sub(pll_7nm); + if (pll_7nm->slave) { + dsi_pll_disable_global_clk(pll_7nm->slave); + dsi_pll_disable_sub(pll_7nm->slave); + } + /* flush, ensure all register writes are done */ + wmb(); + pll_7nm->phy->pll_on = false; +} + +static unsigned long dsi_pll_7nm_vco_recalc_rate(struct clk_hw *hw, + unsigned long parent_rate) +{ + struct dsi_pll_7nm *pll_7nm = to_pll_7nm(hw); + void __iomem *base = pll_7nm->phy->pll_base; + u64 ref_clk = VCO_REF_CLK_RATE; + u64 vco_rate = 0x0; + u64 multiplier; + u32 frac; + u32 dec; + u64 pll_freq, tmp64; + + dec = dsi_phy_read(base + REG_DSI_7nm_PHY_PLL_DECIMAL_DIV_START_1); + dec &= 0xff; + + frac = dsi_phy_read(base + REG_DSI_7nm_PHY_PLL_FRAC_DIV_START_LOW_1); + frac |= ((dsi_phy_read(base + REG_DSI_7nm_PHY_PLL_FRAC_DIV_START_MID_1) & + 0xff) << 8); + frac |= ((dsi_phy_read(base + REG_DSI_7nm_PHY_PLL_FRAC_DIV_START_HIGH_1) & + 0x3) << 16); + + /* + * TODO: + * 1. Assumes prescaler is disabled + */ + multiplier = 1 << FRAC_BITS; + pll_freq = dec * (ref_clk * 2); + tmp64 = (ref_clk * 2 * frac); + pll_freq += div_u64(tmp64, multiplier); + + vco_rate = pll_freq; + + DBG("DSI PLL%d returning vco rate = %lu, dec = %x, frac = %x", + pll_7nm->phy->id, (unsigned long)vco_rate, dec, frac); + + return (unsigned long)vco_rate; +} + +static long dsi_pll_7nm_clk_round_rate(struct clk_hw *hw, + unsigned long rate, unsigned long *parent_rate) +{ + struct dsi_pll_7nm *pll_7nm = to_pll_7nm(hw); + + if (rate < pll_7nm->phy->cfg->min_pll_rate) + return pll_7nm->phy->cfg->min_pll_rate; + else if (rate > pll_7nm->phy->cfg->max_pll_rate) + return pll_7nm->phy->cfg->max_pll_rate; + else + return rate; +} + +static const struct clk_ops clk_ops_dsi_pll_7nm_vco = { + .round_rate = dsi_pll_7nm_clk_round_rate, + .set_rate = dsi_pll_7nm_vco_set_rate, + .recalc_rate = dsi_pll_7nm_vco_recalc_rate, + .prepare = dsi_pll_7nm_vco_prepare, + .unprepare = dsi_pll_7nm_vco_unprepare, +}; + +/* + * PLL Callbacks + */ + +static void dsi_7nm_pll_save_state(struct msm_dsi_phy *phy) +{ + struct dsi_pll_7nm *pll_7nm = to_pll_7nm(phy->vco_hw); + struct pll_7nm_cached_state *cached = &pll_7nm->cached_state; + void __iomem *phy_base = pll_7nm->phy->base; + u32 cmn_clk_cfg0, cmn_clk_cfg1; + + cached->pll_out_div = dsi_phy_read(pll_7nm->phy->pll_base + + REG_DSI_7nm_PHY_PLL_PLL_OUTDIV_RATE); + cached->pll_out_div &= 0x3; + + cmn_clk_cfg0 = dsi_phy_read(phy_base + REG_DSI_7nm_PHY_CMN_CLK_CFG0); + cached->bit_clk_div = cmn_clk_cfg0 & 0xf; + cached->pix_clk_div = (cmn_clk_cfg0 & 0xf0) >> 4; + + cmn_clk_cfg1 = dsi_phy_read(phy_base + REG_DSI_7nm_PHY_CMN_CLK_CFG1); + cached->pll_mux = cmn_clk_cfg1 & 0x3; + + DBG("DSI PLL%d outdiv %x bit_clk_div %x pix_clk_div %x pll_mux %x", + pll_7nm->phy->id, cached->pll_out_div, cached->bit_clk_div, + cached->pix_clk_div, cached->pll_mux); +} + +static int dsi_7nm_pll_restore_state(struct msm_dsi_phy *phy) +{ + struct dsi_pll_7nm *pll_7nm = to_pll_7nm(phy->vco_hw); + struct pll_7nm_cached_state *cached = &pll_7nm->cached_state; + void __iomem *phy_base = pll_7nm->phy->base; + u32 val; + int ret; + + val = dsi_phy_read(pll_7nm->phy->pll_base + REG_DSI_7nm_PHY_PLL_PLL_OUTDIV_RATE); + val &= ~0x3; + val |= cached->pll_out_div; + dsi_phy_write(pll_7nm->phy->pll_base + REG_DSI_7nm_PHY_PLL_PLL_OUTDIV_RATE, val); + + dsi_phy_write(phy_base + REG_DSI_7nm_PHY_CMN_CLK_CFG0, + cached->bit_clk_div | (cached->pix_clk_div << 4)); + + val = dsi_phy_read(phy_base + REG_DSI_7nm_PHY_CMN_CLK_CFG1); + val &= ~0x3; + val |= cached->pll_mux; + dsi_phy_write(phy_base + REG_DSI_7nm_PHY_CMN_CLK_CFG1, val); + + ret = dsi_pll_7nm_vco_set_rate(phy->vco_hw, + pll_7nm->vco_current_rate, + VCO_REF_CLK_RATE); + if (ret) { + DRM_DEV_ERROR(&pll_7nm->phy->pdev->dev, + "restore vco rate failed. ret=%d\n", ret); + return ret; + } + + DBG("DSI PLL%d", pll_7nm->phy->id); + + return 0; +} + +static int dsi_7nm_set_usecase(struct msm_dsi_phy *phy) +{ + struct dsi_pll_7nm *pll_7nm = to_pll_7nm(phy->vco_hw); + void __iomem *base = phy->base; + u32 data = 0x0; /* internal PLL */ + + DBG("DSI PLL%d", pll_7nm->phy->id); + + switch (phy->usecase) { + case MSM_DSI_PHY_STANDALONE: + break; + case MSM_DSI_PHY_MASTER: + pll_7nm->slave = pll_7nm_list[(pll_7nm->phy->id + 1) % DSI_MAX]; + break; + case MSM_DSI_PHY_SLAVE: + data = 0x1; /* external PLL */ + break; + default: + return -EINVAL; + } + + /* set PLL src */ + dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_CLK_CFG1, (data << 2)); + + return 0; +} + +/* + * The post dividers and mux clocks are created using the standard divider and + * mux API. Unlike the 14nm PHY, the slave PLL doesn't need its dividers/mux + * state to follow the master PLL's divider/mux state. Therefore, we don't + * require special clock ops that also configure the slave PLL registers + */ +static int pll_7nm_register(struct dsi_pll_7nm *pll_7nm, struct clk_hw **provided_clocks) +{ + char clk_name[32], parent[32], vco_name[32]; + char parent2[32], parent3[32], parent4[32]; + struct clk_init_data vco_init = { + .parent_names = (const char *[]){ "bi_tcxo" }, + .num_parents = 1, + .name = vco_name, + .flags = CLK_IGNORE_UNUSED, + .ops = &clk_ops_dsi_pll_7nm_vco, + }; + struct device *dev = &pll_7nm->phy->pdev->dev; + struct clk_hw *hw; + int ret; + + DBG("DSI%d", pll_7nm->phy->id); + + snprintf(vco_name, 32, "dsi%dvco_clk", pll_7nm->phy->id); + pll_7nm->clk_hw.init = &vco_init; + + ret = devm_clk_hw_register(dev, &pll_7nm->clk_hw); + if (ret) + return ret; + + snprintf(clk_name, 32, "dsi%d_pll_out_div_clk", pll_7nm->phy->id); + snprintf(parent, 32, "dsi%dvco_clk", pll_7nm->phy->id); + + hw = devm_clk_hw_register_divider(dev, clk_name, + parent, CLK_SET_RATE_PARENT, + pll_7nm->phy->pll_base + + REG_DSI_7nm_PHY_PLL_PLL_OUTDIV_RATE, + 0, 2, CLK_DIVIDER_POWER_OF_TWO, NULL); + if (IS_ERR(hw)) { + ret = PTR_ERR(hw); + goto fail; + } + + snprintf(clk_name, 32, "dsi%d_pll_bit_clk", pll_7nm->phy->id); + snprintf(parent, 32, "dsi%d_pll_out_div_clk", pll_7nm->phy->id); + + /* BIT CLK: DIV_CTRL_3_0 */ + hw = devm_clk_hw_register_divider(dev, clk_name, parent, + CLK_SET_RATE_PARENT, + pll_7nm->phy->base + + REG_DSI_7nm_PHY_CMN_CLK_CFG0, + 0, 4, CLK_DIVIDER_ONE_BASED, + &pll_7nm->postdiv_lock); + if (IS_ERR(hw)) { + ret = PTR_ERR(hw); + goto fail; + } + + snprintf(clk_name, 32, "dsi%d_phy_pll_out_byteclk", pll_7nm->phy->id); + snprintf(parent, 32, "dsi%d_pll_bit_clk", pll_7nm->phy->id); + + /* DSI Byte clock = VCO_CLK / OUT_DIV / BIT_DIV / 8 */ + hw = devm_clk_hw_register_fixed_factor(dev, clk_name, parent, + CLK_SET_RATE_PARENT, 1, 8); + if (IS_ERR(hw)) { + ret = PTR_ERR(hw); + goto fail; + } + + provided_clocks[DSI_BYTE_PLL_CLK] = hw; + + snprintf(clk_name, 32, "dsi%d_pll_by_2_bit_clk", pll_7nm->phy->id); + snprintf(parent, 32, "dsi%d_pll_bit_clk", pll_7nm->phy->id); + + hw = devm_clk_hw_register_fixed_factor(dev, clk_name, parent, + 0, 1, 2); + if (IS_ERR(hw)) { + ret = PTR_ERR(hw); + goto fail; + } + + snprintf(clk_name, 32, "dsi%d_pll_post_out_div_clk", pll_7nm->phy->id); + snprintf(parent, 32, "dsi%d_pll_out_div_clk", pll_7nm->phy->id); + + hw = devm_clk_hw_register_fixed_factor(dev, clk_name, parent, + 0, 1, 4); + if (IS_ERR(hw)) { + ret = PTR_ERR(hw); + goto fail; + } + + snprintf(clk_name, 32, "dsi%d_pclk_mux", pll_7nm->phy->id); + snprintf(parent, 32, "dsi%d_pll_bit_clk", pll_7nm->phy->id); + snprintf(parent2, 32, "dsi%d_pll_by_2_bit_clk", pll_7nm->phy->id); + snprintf(parent3, 32, "dsi%d_pll_out_div_clk", pll_7nm->phy->id); + snprintf(parent4, 32, "dsi%d_pll_post_out_div_clk", pll_7nm->phy->id); + + hw = devm_clk_hw_register_mux(dev, clk_name, + ((const char *[]){ + parent, parent2, parent3, parent4 + }), 4, 0, pll_7nm->phy->base + + REG_DSI_7nm_PHY_CMN_CLK_CFG1, + 0, 2, 0, NULL); + if (IS_ERR(hw)) { + ret = PTR_ERR(hw); + goto fail; + } + + snprintf(clk_name, 32, "dsi%d_phy_pll_out_dsiclk", pll_7nm->phy->id); + snprintf(parent, 32, "dsi%d_pclk_mux", pll_7nm->phy->id); + + /* PIX CLK DIV : DIV_CTRL_7_4*/ + hw = devm_clk_hw_register_divider(dev, clk_name, parent, + 0, pll_7nm->phy->base + + REG_DSI_7nm_PHY_CMN_CLK_CFG0, + 4, 4, CLK_DIVIDER_ONE_BASED, + &pll_7nm->postdiv_lock); + if (IS_ERR(hw)) { + ret = PTR_ERR(hw); + goto fail; + } + + provided_clocks[DSI_PIXEL_PLL_CLK] = hw; + + return 0; + +fail: + + return ret; +} + +static int dsi_pll_7nm_init(struct msm_dsi_phy *phy) +{ + struct platform_device *pdev = phy->pdev; + struct dsi_pll_7nm *pll_7nm; + int ret; + + pll_7nm = devm_kzalloc(&pdev->dev, sizeof(*pll_7nm), GFP_KERNEL); + if (!pll_7nm) + return -ENOMEM; + + DBG("DSI PLL%d", phy->id); + + pll_7nm_list[phy->id] = pll_7nm; + + spin_lock_init(&pll_7nm->postdiv_lock); + + pll_7nm->phy = phy; + + ret = pll_7nm_register(pll_7nm, phy->provided_clocks->hws); + if (ret) { + DRM_DEV_ERROR(&pdev->dev, "failed to register PLL: %d\n", ret); + return ret; + } + + phy->vco_hw = &pll_7nm->clk_hw; + + /* TODO: Remove this when we have proper display handover support */ + msm_dsi_phy_pll_save_state(phy); + + return 0; +} + static int dsi_phy_hw_v4_0_is_pll_on(struct msm_dsi_phy *phy) { void __iomem *base = phy->base; @@ -44,7 +776,7 @@ static void dsi_phy_hw_v4_0_lane_settings(struct msm_dsi_phy *phy) const u8 *tx_dctrl = tx_dctrl_0; void __iomem *lane_base = phy->lane_base; - if (phy->cfg->type == MSM_DSI_PHY_7NM_V4_1) + if (phy->cfg->quirks & DSI_PHY_7NM_QUIRK_V4_1) tx_dctrl = tx_dctrl_1; /* Strength ctrl settings */ @@ -69,7 +801,7 @@ static void dsi_phy_hw_v4_0_lane_settings(struct msm_dsi_phy *phy) } } -static int dsi_7nm_phy_enable(struct msm_dsi_phy *phy, int src_pll_id, +static int dsi_7nm_phy_enable(struct msm_dsi_phy *phy, struct msm_dsi_phy_clk_request *clk_req) { int ret; @@ -108,7 +840,7 @@ static int dsi_7nm_phy_enable(struct msm_dsi_phy *phy, int src_pll_id, /* Alter PHY configurations if data rate less than 1.5GHZ*/ less_than_1500_mhz = (clk_req->bitclk_rate <= 1500000000); - if (phy->cfg->type == MSM_DSI_PHY_7NM_V4_1) { + if (phy->cfg->quirks & DSI_PHY_7NM_QUIRK_V4_1) { vreg_ctrl_0 = less_than_1500_mhz ? 0x53 : 0x52; glbl_rescode_top_ctrl = less_than_1500_mhz ? 0x3d : 0x00; glbl_rescode_bot_ctrl = less_than_1500_mhz ? 0x39 : 0x3c; @@ -165,7 +897,7 @@ static int dsi_7nm_phy_enable(struct msm_dsi_phy *phy, int src_pll_id, /* Select full-rate mode */ dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_CTRL_2, 0x40); - ret = msm_dsi_pll_set_usecase(phy->pll, phy->usecase); + ret = dsi_7nm_set_usecase(phy); if (ret) { DRM_DEV_ERROR(&phy->pdev->dev, "%s: set pll usecase failed, %d\n", __func__, ret); @@ -224,24 +956,8 @@ static void dsi_7nm_phy_disable(struct msm_dsi_phy *phy) DBG("DSI%d PHY disabled", phy->id); } -static int dsi_7nm_phy_init(struct msm_dsi_phy *phy) -{ - struct platform_device *pdev = phy->pdev; - - phy->lane_base = msm_ioremap(pdev, "dsi_phy_lane", - "DSI_PHY_LANE"); - if (IS_ERR(phy->lane_base)) { - DRM_DEV_ERROR(&pdev->dev, "%s: failed to map phy lane base\n", - __func__); - return -ENOMEM; - } - - return 0; -} - const struct msm_dsi_phy_cfg dsi_phy_7nm_cfgs = { - .type = MSM_DSI_PHY_7NM_V4_1, - .src_pll_truthtable = { {false, false}, {true, false} }, + .has_phy_lane = true, .reg_cfg = { .num = 1, .regs = { @@ -251,15 +967,19 @@ const struct msm_dsi_phy_cfg dsi_phy_7nm_cfgs = { .ops = { .enable = dsi_7nm_phy_enable, .disable = dsi_7nm_phy_disable, - .init = dsi_7nm_phy_init, + .pll_init = dsi_pll_7nm_init, + .save_pll_state = dsi_7nm_pll_save_state, + .restore_pll_state = dsi_7nm_pll_restore_state, }, + .min_pll_rate = 600000000UL, + .max_pll_rate = (5000000000ULL < ULONG_MAX) ? 5000000000ULL : ULONG_MAX, .io_start = { 0xae94400, 0xae96400 }, .num_dsi_phy = 2, + .quirks = DSI_PHY_7NM_QUIRK_V4_1, }; const struct msm_dsi_phy_cfg dsi_phy_7nm_8150_cfgs = { - .type = MSM_DSI_PHY_7NM, - .src_pll_truthtable = { {false, false}, {true, false} }, + .has_phy_lane = true, .reg_cfg = { .num = 1, .regs = { @@ -269,8 +989,12 @@ const struct msm_dsi_phy_cfg dsi_phy_7nm_8150_cfgs = { .ops = { .enable = dsi_7nm_phy_enable, .disable = dsi_7nm_phy_disable, - .init = dsi_7nm_phy_init, + .pll_init = dsi_pll_7nm_init, + .save_pll_state = dsi_7nm_pll_save_state, + .restore_pll_state = dsi_7nm_pll_restore_state, }, + .min_pll_rate = 1000000000UL, + .max_pll_rate = 3500000000UL, .io_start = { 0xae94400, 0xae96400 }, .num_dsi_phy = 2, }; diff --git a/drivers/gpu/drm/msm/dsi/pll/dsi_pll.c b/drivers/gpu/drm/msm/dsi/pll/dsi_pll.c deleted file mode 100644 index a45fe95aff49..000000000000 --- a/drivers/gpu/drm/msm/dsi/pll/dsi_pll.c +++ /dev/null @@ -1,184 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Copyright (c) 2012-2015, The Linux Foundation. All rights reserved. - */ - -#include "dsi_pll.h" - -static int dsi_pll_enable(struct msm_dsi_pll *pll) -{ - int i, ret = 0; - - /* - * Certain PLLs do not allow VCO rate update when it is on. - * Keep track of their status to turn on/off after set rate success. - */ - if (unlikely(pll->pll_on)) - return 0; - - /* Try all enable sequences until one succeeds */ - for (i = 0; i < pll->en_seq_cnt; i++) { - ret = pll->enable_seqs[i](pll); - DBG("DSI PLL %s after sequence #%d", - ret ? "unlocked" : "locked", i + 1); - if (!ret) - break; - } - - if (ret) { - DRM_ERROR("DSI PLL failed to lock\n"); - return ret; - } - - pll->pll_on = true; - - return 0; -} - -static void dsi_pll_disable(struct msm_dsi_pll *pll) -{ - if (unlikely(!pll->pll_on)) - return; - - pll->disable_seq(pll); - - pll->pll_on = false; -} - -/* - * DSI PLL Helper functions - */ -long msm_dsi_pll_helper_clk_round_rate(struct clk_hw *hw, - unsigned long rate, unsigned long *parent_rate) -{ - struct msm_dsi_pll *pll = hw_clk_to_pll(hw); - - if (rate < pll->min_rate) - return pll->min_rate; - else if (rate > pll->max_rate) - return pll->max_rate; - else - return rate; -} - -int msm_dsi_pll_helper_clk_prepare(struct clk_hw *hw) -{ - struct msm_dsi_pll *pll = hw_clk_to_pll(hw); - - return dsi_pll_enable(pll); -} - -void msm_dsi_pll_helper_clk_unprepare(struct clk_hw *hw) -{ - struct msm_dsi_pll *pll = hw_clk_to_pll(hw); - - dsi_pll_disable(pll); -} - -void msm_dsi_pll_helper_unregister_clks(struct platform_device *pdev, - struct clk **clks, u32 num_clks) -{ - of_clk_del_provider(pdev->dev.of_node); - - if (!num_clks || !clks) - return; - - do { - clk_unregister(clks[--num_clks]); - clks[num_clks] = NULL; - } while (num_clks); -} - -/* - * DSI PLL API - */ -int msm_dsi_pll_get_clk_provider(struct msm_dsi_pll *pll, - struct clk **byte_clk_provider, struct clk **pixel_clk_provider) -{ - if (pll->get_provider) - return pll->get_provider(pll, - byte_clk_provider, - pixel_clk_provider); - - return -EINVAL; -} - -void msm_dsi_pll_destroy(struct msm_dsi_pll *pll) -{ - if (pll->destroy) - pll->destroy(pll); -} - -void msm_dsi_pll_save_state(struct msm_dsi_pll *pll) -{ - if (pll->save_state) { - pll->save_state(pll); - pll->state_saved = true; - } -} - -int msm_dsi_pll_restore_state(struct msm_dsi_pll *pll) -{ - int ret; - - if (pll->restore_state && pll->state_saved) { - ret = pll->restore_state(pll); - if (ret) - return ret; - - pll->state_saved = false; - } - - return 0; -} - -int msm_dsi_pll_set_usecase(struct msm_dsi_pll *pll, - enum msm_dsi_phy_usecase uc) -{ - if (pll->set_usecase) - return pll->set_usecase(pll, uc); - - return 0; -} - -struct msm_dsi_pll *msm_dsi_pll_init(struct platform_device *pdev, - enum msm_dsi_phy_type type, int id) -{ - struct device *dev = &pdev->dev; - struct msm_dsi_pll *pll; - - switch (type) { - case MSM_DSI_PHY_28NM_HPM: - case MSM_DSI_PHY_28NM_LP: - pll = msm_dsi_pll_28nm_init(pdev, type, id); - break; - case MSM_DSI_PHY_28NM_8960: - pll = msm_dsi_pll_28nm_8960_init(pdev, id); - break; - case MSM_DSI_PHY_14NM: - pll = msm_dsi_pll_14nm_init(pdev, id); - break; - case MSM_DSI_PHY_10NM: - pll = msm_dsi_pll_10nm_init(pdev, id); - break; - case MSM_DSI_PHY_7NM: - case MSM_DSI_PHY_7NM_V4_1: - pll = msm_dsi_pll_7nm_init(pdev, id); - break; - default: - pll = ERR_PTR(-ENXIO); - break; - } - - if (IS_ERR(pll)) { - DRM_DEV_ERROR(dev, "%s: failed to init DSI PLL\n", __func__); - return pll; - } - - pll->type = type; - - DBG("DSI:%d PLL registered", id); - - return pll; -} - diff --git a/drivers/gpu/drm/msm/dsi/pll/dsi_pll.h b/drivers/gpu/drm/msm/dsi/pll/dsi_pll.h deleted file mode 100644 index 3405982a092c..000000000000 --- a/drivers/gpu/drm/msm/dsi/pll/dsi_pll.h +++ /dev/null @@ -1,130 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright (c) 2012-2015, The Linux Foundation. All rights reserved. - */ - -#ifndef __DSI_PLL_H__ -#define __DSI_PLL_H__ - -#include <linux/clk-provider.h> -#include <linux/delay.h> - -#include "dsi.h" - -#define NUM_DSI_CLOCKS_MAX 6 -#define MAX_DSI_PLL_EN_SEQS 10 - -struct msm_dsi_pll { - enum msm_dsi_phy_type type; - - struct clk_hw clk_hw; - bool pll_on; - bool state_saved; - - unsigned long min_rate; - unsigned long max_rate; - u32 en_seq_cnt; - - int (*enable_seqs[MAX_DSI_PLL_EN_SEQS])(struct msm_dsi_pll *pll); - void (*disable_seq)(struct msm_dsi_pll *pll); - int (*get_provider)(struct msm_dsi_pll *pll, - struct clk **byte_clk_provider, - struct clk **pixel_clk_provider); - void (*destroy)(struct msm_dsi_pll *pll); - void (*save_state)(struct msm_dsi_pll *pll); - int (*restore_state)(struct msm_dsi_pll *pll); - int (*set_usecase)(struct msm_dsi_pll *pll, - enum msm_dsi_phy_usecase uc); -}; - -#define hw_clk_to_pll(x) container_of(x, struct msm_dsi_pll, clk_hw) - -static inline void pll_write(void __iomem *reg, u32 data) -{ - msm_writel(data, reg); -} - -static inline u32 pll_read(const void __iomem *reg) -{ - return msm_readl(reg); -} - -static inline void pll_write_udelay(void __iomem *reg, u32 data, u32 delay_us) -{ - pll_write(reg, data); - udelay(delay_us); -} - -static inline void pll_write_ndelay(void __iomem *reg, u32 data, u32 delay_ns) -{ - pll_write((reg), data); - ndelay(delay_ns); -} - -/* - * DSI PLL Helper functions - */ - -/* clock callbacks */ -long msm_dsi_pll_helper_clk_round_rate(struct clk_hw *hw, - unsigned long rate, unsigned long *parent_rate); -int msm_dsi_pll_helper_clk_prepare(struct clk_hw *hw); -void msm_dsi_pll_helper_clk_unprepare(struct clk_hw *hw); -/* misc */ -void msm_dsi_pll_helper_unregister_clks(struct platform_device *pdev, - struct clk **clks, u32 num_clks); - -/* - * Initialization for Each PLL Type - */ -#ifdef CONFIG_DRM_MSM_DSI_28NM_PHY -struct msm_dsi_pll *msm_dsi_pll_28nm_init(struct platform_device *pdev, - enum msm_dsi_phy_type type, int id); -#else -static inline struct msm_dsi_pll *msm_dsi_pll_28nm_init( - struct platform_device *pdev, enum msm_dsi_phy_type type, int id) -{ - return ERR_PTR(-ENODEV); -} -#endif -#ifdef CONFIG_DRM_MSM_DSI_28NM_8960_PHY -struct msm_dsi_pll *msm_dsi_pll_28nm_8960_init(struct platform_device *pdev, - int id); -#else -static inline struct msm_dsi_pll *msm_dsi_pll_28nm_8960_init( - struct platform_device *pdev, int id) -{ - return ERR_PTR(-ENODEV); -} -#endif - -#ifdef CONFIG_DRM_MSM_DSI_14NM_PHY -struct msm_dsi_pll *msm_dsi_pll_14nm_init(struct platform_device *pdev, int id); -#else -static inline struct msm_dsi_pll * -msm_dsi_pll_14nm_init(struct platform_device *pdev, int id) -{ - return ERR_PTR(-ENODEV); -} -#endif -#ifdef CONFIG_DRM_MSM_DSI_10NM_PHY -struct msm_dsi_pll *msm_dsi_pll_10nm_init(struct platform_device *pdev, int id); -#else -static inline struct msm_dsi_pll * -msm_dsi_pll_10nm_init(struct platform_device *pdev, int id) -{ - return ERR_PTR(-ENODEV); -} -#endif -#ifdef CONFIG_DRM_MSM_DSI_7NM_PHY -struct msm_dsi_pll *msm_dsi_pll_7nm_init(struct platform_device *pdev, int id); -#else -static inline struct msm_dsi_pll * -msm_dsi_pll_7nm_init(struct platform_device *pdev, int id) -{ - return ERR_PTR(-ENODEV); -} -#endif - -#endif /* __DSI_PLL_H__ */ - diff --git a/drivers/gpu/drm/msm/dsi/pll/dsi_pll_10nm.c b/drivers/gpu/drm/msm/dsi/pll/dsi_pll_10nm.c deleted file mode 100644 index de3b802ccd3d..000000000000 --- a/drivers/gpu/drm/msm/dsi/pll/dsi_pll_10nm.c +++ /dev/null @@ -1,881 +0,0 @@ -/* - * SPDX-License-Identifier: GPL-2.0 - * Copyright (c) 2018, The Linux Foundation - */ - -#include <linux/clk.h> -#include <linux/clk-provider.h> -#include <linux/iopoll.h> - -#include "dsi_pll.h" -#include "dsi.xml.h" - -/* - * DSI PLL 10nm - clock diagram (eg: DSI0): - * - * dsi0_pll_out_div_clk dsi0_pll_bit_clk - * | | - * | | - * +---------+ | +----------+ | +----+ - * dsi0vco_clk ---| out_div |--o--| divl_3_0 |--o--| /8 |-- dsi0_phy_pll_out_byteclk - * +---------+ | +----------+ | +----+ - * | | - * | | dsi0_pll_by_2_bit_clk - * | | | - * | | +----+ | |\ dsi0_pclk_mux - * | |--| /2 |--o--| \ | - * | | +----+ | \ | +---------+ - * | --------------| |--o--| div_7_4 |-- dsi0_phy_pll_out_dsiclk - * |------------------------------| / +---------+ - * | +-----+ | / - * -----------| /4? |--o----------|/ - * +-----+ | | - * | |dsiclk_sel - * | - * dsi0_pll_post_out_div_clk - */ - -#define DSI_BYTE_PLL_CLK 0 -#define DSI_PIXEL_PLL_CLK 1 -#define NUM_PROVIDED_CLKS 2 - -#define VCO_REF_CLK_RATE 19200000 - -struct dsi_pll_regs { - u32 pll_prop_gain_rate; - u32 pll_lockdet_rate; - u32 decimal_div_start; - u32 frac_div_start_low; - u32 frac_div_start_mid; - u32 frac_div_start_high; - u32 pll_clock_inverters; - u32 ssc_stepsize_low; - u32 ssc_stepsize_high; - u32 ssc_div_per_low; - u32 ssc_div_per_high; - u32 ssc_adjper_low; - u32 ssc_adjper_high; - u32 ssc_control; -}; - -struct dsi_pll_config { - u32 ref_freq; - bool div_override; - u32 output_div; - bool ignore_frac; - bool disable_prescaler; - bool enable_ssc; - bool ssc_center; - u32 dec_bits; - u32 frac_bits; - u32 lock_timer; - u32 ssc_freq; - u32 ssc_offset; - u32 ssc_adj_per; - u32 thresh_cycles; - u32 refclk_cycles; -}; - -struct pll_10nm_cached_state { - unsigned long vco_rate; - u8 bit_clk_div; - u8 pix_clk_div; - u8 pll_out_div; - u8 pll_mux; -}; - -struct dsi_pll_10nm { - struct msm_dsi_pll base; - - int id; - struct platform_device *pdev; - - void __iomem *phy_cmn_mmio; - void __iomem *mmio; - - u64 vco_ref_clk_rate; - u64 vco_current_rate; - - /* protects REG_DSI_10nm_PHY_CMN_CLK_CFG0 register */ - spinlock_t postdiv_lock; - - int vco_delay; - struct dsi_pll_config pll_configuration; - struct dsi_pll_regs reg_setup; - - /* private clocks: */ - struct clk_hw *out_div_clk_hw; - struct clk_hw *bit_clk_hw; - struct clk_hw *byte_clk_hw; - struct clk_hw *by_2_bit_clk_hw; - struct clk_hw *post_out_div_clk_hw; - struct clk_hw *pclk_mux_hw; - struct clk_hw *out_dsiclk_hw; - - /* clock-provider: */ - struct clk_hw_onecell_data *hw_data; - - struct pll_10nm_cached_state cached_state; - - enum msm_dsi_phy_usecase uc; - struct dsi_pll_10nm *slave; -}; - -#define to_pll_10nm(x) container_of(x, struct dsi_pll_10nm, base) - -/* - * Global list of private DSI PLL struct pointers. We need this for Dual DSI - * mode, where the master PLL's clk_ops needs access the slave's private data - */ -static struct dsi_pll_10nm *pll_10nm_list[DSI_MAX]; - -static void dsi_pll_setup_config(struct dsi_pll_10nm *pll) -{ - struct dsi_pll_config *config = &pll->pll_configuration; - - config->ref_freq = pll->vco_ref_clk_rate; - config->output_div = 1; - config->dec_bits = 8; - config->frac_bits = 18; - config->lock_timer = 64; - config->ssc_freq = 31500; - config->ssc_offset = 5000; - config->ssc_adj_per = 2; - config->thresh_cycles = 32; - config->refclk_cycles = 256; - - config->div_override = false; - config->ignore_frac = false; - config->disable_prescaler = false; - - config->enable_ssc = false; - config->ssc_center = 0; -} - -static void dsi_pll_calc_dec_frac(struct dsi_pll_10nm *pll) -{ - struct dsi_pll_config *config = &pll->pll_configuration; - struct dsi_pll_regs *regs = &pll->reg_setup; - u64 fref = pll->vco_ref_clk_rate; - u64 pll_freq; - u64 divider; - u64 dec, dec_multiple; - u32 frac; - u64 multiplier; - - pll_freq = pll->vco_current_rate; - - if (config->disable_prescaler) - divider = fref; - else - divider = fref * 2; - - multiplier = 1 << config->frac_bits; - dec_multiple = div_u64(pll_freq * multiplier, divider); - dec = div_u64_rem(dec_multiple, multiplier, &frac); - - if (pll_freq <= 1900000000UL) - regs->pll_prop_gain_rate = 8; - else if (pll_freq <= 3000000000UL) - regs->pll_prop_gain_rate = 10; - else - regs->pll_prop_gain_rate = 12; - if (pll_freq < 1100000000UL) - regs->pll_clock_inverters = 8; - else - regs->pll_clock_inverters = 0; - - regs->pll_lockdet_rate = config->lock_timer; - regs->decimal_div_start = dec; - regs->frac_div_start_low = (frac & 0xff); - regs->frac_div_start_mid = (frac & 0xff00) >> 8; - regs->frac_div_start_high = (frac & 0x30000) >> 16; -} - -#define SSC_CENTER BIT(0) -#define SSC_EN BIT(1) - -static void dsi_pll_calc_ssc(struct dsi_pll_10nm *pll) -{ - struct dsi_pll_config *config = &pll->pll_configuration; - struct dsi_pll_regs *regs = &pll->reg_setup; - u32 ssc_per; - u32 ssc_mod; - u64 ssc_step_size; - u64 frac; - - if (!config->enable_ssc) { - DBG("SSC not enabled\n"); - return; - } - - ssc_per = DIV_ROUND_CLOSEST(config->ref_freq, config->ssc_freq) / 2 - 1; - ssc_mod = (ssc_per + 1) % (config->ssc_adj_per + 1); - ssc_per -= ssc_mod; - - frac = regs->frac_div_start_low | - (regs->frac_div_start_mid << 8) | - (regs->frac_div_start_high << 16); - ssc_step_size = regs->decimal_div_start; - ssc_step_size *= (1 << config->frac_bits); - ssc_step_size += frac; - ssc_step_size *= config->ssc_offset; - ssc_step_size *= (config->ssc_adj_per + 1); - ssc_step_size = div_u64(ssc_step_size, (ssc_per + 1)); - ssc_step_size = DIV_ROUND_CLOSEST_ULL(ssc_step_size, 1000000); - - regs->ssc_div_per_low = ssc_per & 0xFF; - regs->ssc_div_per_high = (ssc_per & 0xFF00) >> 8; - regs->ssc_stepsize_low = (u32)(ssc_step_size & 0xFF); - regs->ssc_stepsize_high = (u32)((ssc_step_size & 0xFF00) >> 8); - regs->ssc_adjper_low = config->ssc_adj_per & 0xFF; - regs->ssc_adjper_high = (config->ssc_adj_per & 0xFF00) >> 8; - - regs->ssc_control = config->ssc_center ? SSC_CENTER : 0; - - pr_debug("SCC: Dec:%d, frac:%llu, frac_bits:%d\n", - regs->decimal_div_start, frac, config->frac_bits); - pr_debug("SSC: div_per:0x%X, stepsize:0x%X, adjper:0x%X\n", - ssc_per, (u32)ssc_step_size, config->ssc_adj_per); -} - -static void dsi_pll_ssc_commit(struct dsi_pll_10nm *pll) -{ - void __iomem *base = pll->mmio; - struct dsi_pll_regs *regs = &pll->reg_setup; - - if (pll->pll_configuration.enable_ssc) { - pr_debug("SSC is enabled\n"); - - pll_write(base + REG_DSI_10nm_PHY_PLL_SSC_STEPSIZE_LOW_1, - regs->ssc_stepsize_low); - pll_write(base + REG_DSI_10nm_PHY_PLL_SSC_STEPSIZE_HIGH_1, - regs->ssc_stepsize_high); - pll_write(base + REG_DSI_10nm_PHY_PLL_SSC_DIV_PER_LOW_1, - regs->ssc_div_per_low); - pll_write(base + REG_DSI_10nm_PHY_PLL_SSC_DIV_PER_HIGH_1, - regs->ssc_div_per_high); - pll_write(base + REG_DSI_10nm_PHY_PLL_SSC_DIV_ADJPER_LOW_1, - regs->ssc_adjper_low); - pll_write(base + REG_DSI_10nm_PHY_PLL_SSC_DIV_ADJPER_HIGH_1, - regs->ssc_adjper_high); - pll_write(base + REG_DSI_10nm_PHY_PLL_SSC_CONTROL, - SSC_EN | regs->ssc_control); - } -} - -static void dsi_pll_config_hzindep_reg(struct dsi_pll_10nm *pll) -{ - void __iomem *base = pll->mmio; - - pll_write(base + REG_DSI_10nm_PHY_PLL_ANALOG_CONTROLS_ONE, 0x80); - pll_write(base + REG_DSI_10nm_PHY_PLL_ANALOG_CONTROLS_TWO, 0x03); - pll_write(base + REG_DSI_10nm_PHY_PLL_ANALOG_CONTROLS_THREE, 0x00); - pll_write(base + REG_DSI_10nm_PHY_PLL_DSM_DIVIDER, 0x00); - pll_write(base + REG_DSI_10nm_PHY_PLL_FEEDBACK_DIVIDER, 0x4e); - pll_write(base + REG_DSI_10nm_PHY_PLL_CALIBRATION_SETTINGS, 0x40); - pll_write(base + REG_DSI_10nm_PHY_PLL_BAND_SEL_CAL_SETTINGS_THREE, - 0xba); - pll_write(base + REG_DSI_10nm_PHY_PLL_FREQ_DETECT_SETTINGS_ONE, 0x0c); - pll_write(base + REG_DSI_10nm_PHY_PLL_OUTDIV, 0x00); - pll_write(base + REG_DSI_10nm_PHY_PLL_CORE_OVERRIDE, 0x00); - pll_write(base + REG_DSI_10nm_PHY_PLL_PLL_DIGITAL_TIMERS_TWO, 0x08); - pll_write(base + REG_DSI_10nm_PHY_PLL_PLL_PROP_GAIN_RATE_1, 0x08); - pll_write(base + REG_DSI_10nm_PHY_PLL_PLL_BAND_SET_RATE_1, 0xc0); - pll_write(base + REG_DSI_10nm_PHY_PLL_PLL_INT_GAIN_IFILT_BAND_1, 0xfa); - pll_write(base + REG_DSI_10nm_PHY_PLL_PLL_FL_INT_GAIN_PFILT_BAND_1, - 0x4c); - pll_write(base + REG_DSI_10nm_PHY_PLL_PLL_LOCK_OVERRIDE, 0x80); - pll_write(base + REG_DSI_10nm_PHY_PLL_PFILT, 0x29); - pll_write(base + REG_DSI_10nm_PHY_PLL_IFILT, 0x3f); -} - -static void dsi_pll_commit(struct dsi_pll_10nm *pll) -{ - void __iomem *base = pll->mmio; - struct dsi_pll_regs *reg = &pll->reg_setup; - - pll_write(base + REG_DSI_10nm_PHY_PLL_CORE_INPUT_OVERRIDE, 0x12); - pll_write(base + REG_DSI_10nm_PHY_PLL_DECIMAL_DIV_START_1, - reg->decimal_div_start); - pll_write(base + REG_DSI_10nm_PHY_PLL_FRAC_DIV_START_LOW_1, - reg->frac_div_start_low); - pll_write(base + REG_DSI_10nm_PHY_PLL_FRAC_DIV_START_MID_1, - reg->frac_div_start_mid); - pll_write(base + REG_DSI_10nm_PHY_PLL_FRAC_DIV_START_HIGH_1, - reg->frac_div_start_high); - pll_write(base + REG_DSI_10nm_PHY_PLL_PLL_LOCKDET_RATE_1, - reg->pll_lockdet_rate); - pll_write(base + REG_DSI_10nm_PHY_PLL_PLL_LOCK_DELAY, 0x06); - pll_write(base + REG_DSI_10nm_PHY_PLL_CMODE, 0x10); - pll_write(base + REG_DSI_10nm_PHY_PLL_CLOCK_INVERTERS, - reg->pll_clock_inverters); -} - -static int dsi_pll_10nm_vco_set_rate(struct clk_hw *hw, unsigned long rate, - unsigned long parent_rate) -{ - struct msm_dsi_pll *pll = hw_clk_to_pll(hw); - struct dsi_pll_10nm *pll_10nm = to_pll_10nm(pll); - - DBG("DSI PLL%d rate=%lu, parent's=%lu", pll_10nm->id, rate, - parent_rate); - - pll_10nm->vco_current_rate = rate; - pll_10nm->vco_ref_clk_rate = VCO_REF_CLK_RATE; - - dsi_pll_setup_config(pll_10nm); - - dsi_pll_calc_dec_frac(pll_10nm); - - dsi_pll_calc_ssc(pll_10nm); - - dsi_pll_commit(pll_10nm); - - dsi_pll_config_hzindep_reg(pll_10nm); - - dsi_pll_ssc_commit(pll_10nm); - - /* flush, ensure all register writes are done*/ - wmb(); - - return 0; -} - -static int dsi_pll_10nm_lock_status(struct dsi_pll_10nm *pll) -{ - struct device *dev = &pll->pdev->dev; - int rc; - u32 status = 0; - u32 const delay_us = 100; - u32 const timeout_us = 5000; - - rc = readl_poll_timeout_atomic(pll->mmio + - REG_DSI_10nm_PHY_PLL_COMMON_STATUS_ONE, - status, - ((status & BIT(0)) > 0), - delay_us, - timeout_us); - if (rc) - DRM_DEV_ERROR(dev, "DSI PLL(%d) lock failed, status=0x%08x\n", - pll->id, status); - - return rc; -} - -static void dsi_pll_disable_pll_bias(struct dsi_pll_10nm *pll) -{ - u32 data = pll_read(pll->phy_cmn_mmio + REG_DSI_10nm_PHY_CMN_CTRL_0); - - pll_write(pll->mmio + REG_DSI_10nm_PHY_PLL_SYSTEM_MUXES, 0); - pll_write(pll->phy_cmn_mmio + REG_DSI_10nm_PHY_CMN_CTRL_0, - data & ~BIT(5)); - ndelay(250); -} - -static void dsi_pll_enable_pll_bias(struct dsi_pll_10nm *pll) -{ - u32 data = pll_read(pll->phy_cmn_mmio + REG_DSI_10nm_PHY_CMN_CTRL_0); - - pll_write(pll->phy_cmn_mmio + REG_DSI_10nm_PHY_CMN_CTRL_0, - data | BIT(5)); - pll_write(pll->mmio + REG_DSI_10nm_PHY_PLL_SYSTEM_MUXES, 0xc0); - ndelay(250); -} - -static void dsi_pll_disable_global_clk(struct dsi_pll_10nm *pll) -{ - u32 data; - - data = pll_read(pll->phy_cmn_mmio + REG_DSI_10nm_PHY_CMN_CLK_CFG1); - pll_write(pll->phy_cmn_mmio + REG_DSI_10nm_PHY_CMN_CLK_CFG1, - data & ~BIT(5)); -} - -static void dsi_pll_enable_global_clk(struct dsi_pll_10nm *pll) -{ - u32 data; - - data = pll_read(pll->phy_cmn_mmio + REG_DSI_10nm_PHY_CMN_CLK_CFG1); - pll_write(pll->phy_cmn_mmio + REG_DSI_10nm_PHY_CMN_CLK_CFG1, - data | BIT(5)); -} - -static int dsi_pll_10nm_vco_prepare(struct clk_hw *hw) -{ - struct msm_dsi_pll *pll = hw_clk_to_pll(hw); - struct dsi_pll_10nm *pll_10nm = to_pll_10nm(pll); - struct device *dev = &pll_10nm->pdev->dev; - int rc; - - dsi_pll_enable_pll_bias(pll_10nm); - if (pll_10nm->slave) - dsi_pll_enable_pll_bias(pll_10nm->slave); - - rc = dsi_pll_10nm_vco_set_rate(hw,pll_10nm->vco_current_rate, 0); - if (rc) { - DRM_DEV_ERROR(dev, "vco_set_rate failed, rc=%d\n", rc); - return rc; - } - - /* Start PLL */ - pll_write(pll_10nm->phy_cmn_mmio + REG_DSI_10nm_PHY_CMN_PLL_CNTRL, - 0x01); - - /* - * ensure all PLL configurations are written prior to checking - * for PLL lock. - */ - wmb(); - - /* Check for PLL lock */ - rc = dsi_pll_10nm_lock_status(pll_10nm); - if (rc) { - DRM_DEV_ERROR(dev, "PLL(%d) lock failed\n", pll_10nm->id); - goto error; - } - - pll->pll_on = true; - - dsi_pll_enable_global_clk(pll_10nm); - if (pll_10nm->slave) - dsi_pll_enable_global_clk(pll_10nm->slave); - - pll_write(pll_10nm->phy_cmn_mmio + REG_DSI_10nm_PHY_CMN_RBUF_CTRL, - 0x01); - if (pll_10nm->slave) - pll_write(pll_10nm->slave->phy_cmn_mmio + - REG_DSI_10nm_PHY_CMN_RBUF_CTRL, 0x01); - -error: - return rc; -} - -static void dsi_pll_disable_sub(struct dsi_pll_10nm *pll) -{ - pll_write(pll->phy_cmn_mmio + REG_DSI_10nm_PHY_CMN_RBUF_CTRL, 0); - dsi_pll_disable_pll_bias(pll); -} - -static void dsi_pll_10nm_vco_unprepare(struct clk_hw *hw) -{ - struct msm_dsi_pll *pll = hw_clk_to_pll(hw); - struct dsi_pll_10nm *pll_10nm = to_pll_10nm(pll); - - /* - * To avoid any stray glitches while abruptly powering down the PLL - * make sure to gate the clock using the clock enable bit before - * powering down the PLL - */ - dsi_pll_disable_global_clk(pll_10nm); - pll_write(pll_10nm->phy_cmn_mmio + REG_DSI_10nm_PHY_CMN_PLL_CNTRL, 0); - dsi_pll_disable_sub(pll_10nm); - if (pll_10nm->slave) { - dsi_pll_disable_global_clk(pll_10nm->slave); - dsi_pll_disable_sub(pll_10nm->slave); - } - /* flush, ensure all register writes are done */ - wmb(); - pll->pll_on = false; -} - -static unsigned long dsi_pll_10nm_vco_recalc_rate(struct clk_hw *hw, - unsigned long parent_rate) -{ - struct msm_dsi_pll *pll = hw_clk_to_pll(hw); - struct dsi_pll_10nm *pll_10nm = to_pll_10nm(pll); - struct dsi_pll_config *config = &pll_10nm->pll_configuration; - void __iomem *base = pll_10nm->mmio; - u64 ref_clk = pll_10nm->vco_ref_clk_rate; - u64 vco_rate = 0x0; - u64 multiplier; - u32 frac; - u32 dec; - u64 pll_freq, tmp64; - - dec = pll_read(base + REG_DSI_10nm_PHY_PLL_DECIMAL_DIV_START_1); - dec &= 0xff; - - frac = pll_read(base + REG_DSI_10nm_PHY_PLL_FRAC_DIV_START_LOW_1); - frac |= ((pll_read(base + REG_DSI_10nm_PHY_PLL_FRAC_DIV_START_MID_1) & - 0xff) << 8); - frac |= ((pll_read(base + REG_DSI_10nm_PHY_PLL_FRAC_DIV_START_HIGH_1) & - 0x3) << 16); - - /* - * TODO: - * 1. Assumes prescaler is disabled - */ - multiplier = 1 << config->frac_bits; - pll_freq = dec * (ref_clk * 2); - tmp64 = (ref_clk * 2 * frac); - pll_freq += div_u64(tmp64, multiplier); - - vco_rate = pll_freq; - - DBG("DSI PLL%d returning vco rate = %lu, dec = %x, frac = %x", - pll_10nm->id, (unsigned long)vco_rate, dec, frac); - - return (unsigned long)vco_rate; -} - -static const struct clk_ops clk_ops_dsi_pll_10nm_vco = { - .round_rate = msm_dsi_pll_helper_clk_round_rate, - .set_rate = dsi_pll_10nm_vco_set_rate, - .recalc_rate = dsi_pll_10nm_vco_recalc_rate, - .prepare = dsi_pll_10nm_vco_prepare, - .unprepare = dsi_pll_10nm_vco_unprepare, -}; - -/* - * PLL Callbacks - */ - -static void dsi_pll_10nm_save_state(struct msm_dsi_pll *pll) -{ - struct dsi_pll_10nm *pll_10nm = to_pll_10nm(pll); - struct pll_10nm_cached_state *cached = &pll_10nm->cached_state; - void __iomem *phy_base = pll_10nm->phy_cmn_mmio; - u32 cmn_clk_cfg0, cmn_clk_cfg1; - - cached->pll_out_div = pll_read(pll_10nm->mmio + - REG_DSI_10nm_PHY_PLL_PLL_OUTDIV_RATE); - cached->pll_out_div &= 0x3; - - cmn_clk_cfg0 = pll_read(phy_base + REG_DSI_10nm_PHY_CMN_CLK_CFG0); - cached->bit_clk_div = cmn_clk_cfg0 & 0xf; - cached->pix_clk_div = (cmn_clk_cfg0 & 0xf0) >> 4; - - cmn_clk_cfg1 = pll_read(phy_base + REG_DSI_10nm_PHY_CMN_CLK_CFG1); - cached->pll_mux = cmn_clk_cfg1 & 0x3; - - DBG("DSI PLL%d outdiv %x bit_clk_div %x pix_clk_div %x pll_mux %x", - pll_10nm->id, cached->pll_out_div, cached->bit_clk_div, - cached->pix_clk_div, cached->pll_mux); -} - -static int dsi_pll_10nm_restore_state(struct msm_dsi_pll *pll) -{ - struct dsi_pll_10nm *pll_10nm = to_pll_10nm(pll); - struct pll_10nm_cached_state *cached = &pll_10nm->cached_state; - void __iomem *phy_base = pll_10nm->phy_cmn_mmio; - u32 val; - int ret; - - val = pll_read(pll_10nm->mmio + REG_DSI_10nm_PHY_PLL_PLL_OUTDIV_RATE); - val &= ~0x3; - val |= cached->pll_out_div; - pll_write(pll_10nm->mmio + REG_DSI_10nm_PHY_PLL_PLL_OUTDIV_RATE, val); - - pll_write(phy_base + REG_DSI_10nm_PHY_CMN_CLK_CFG0, - cached->bit_clk_div | (cached->pix_clk_div << 4)); - - val = pll_read(phy_base + REG_DSI_10nm_PHY_CMN_CLK_CFG1); - val &= ~0x3; - val |= cached->pll_mux; - pll_write(phy_base + REG_DSI_10nm_PHY_CMN_CLK_CFG1, val); - - ret = dsi_pll_10nm_vco_set_rate(&pll->clk_hw, pll_10nm->vco_current_rate, pll_10nm->vco_ref_clk_rate); - if (ret) { - DRM_DEV_ERROR(&pll_10nm->pdev->dev, - "restore vco rate failed. ret=%d\n", ret); - return ret; - } - - DBG("DSI PLL%d", pll_10nm->id); - - return 0; -} - -static int dsi_pll_10nm_set_usecase(struct msm_dsi_pll *pll, - enum msm_dsi_phy_usecase uc) -{ - struct dsi_pll_10nm *pll_10nm = to_pll_10nm(pll); - void __iomem *base = pll_10nm->phy_cmn_mmio; - u32 data = 0x0; /* internal PLL */ - - DBG("DSI PLL%d", pll_10nm->id); - - switch (uc) { - case MSM_DSI_PHY_STANDALONE: - break; - case MSM_DSI_PHY_MASTER: - pll_10nm->slave = pll_10nm_list[(pll_10nm->id + 1) % DSI_MAX]; - break; - case MSM_DSI_PHY_SLAVE: - data = 0x1; /* external PLL */ - break; - default: - return -EINVAL; - } - - /* set PLL src */ - pll_write(base + REG_DSI_10nm_PHY_CMN_CLK_CFG1, (data << 2)); - - pll_10nm->uc = uc; - - return 0; -} - -static int dsi_pll_10nm_get_provider(struct msm_dsi_pll *pll, - struct clk **byte_clk_provider, - struct clk **pixel_clk_provider) -{ - struct dsi_pll_10nm *pll_10nm = to_pll_10nm(pll); - struct clk_hw_onecell_data *hw_data = pll_10nm->hw_data; - - DBG("DSI PLL%d", pll_10nm->id); - - if (byte_clk_provider) - *byte_clk_provider = hw_data->hws[DSI_BYTE_PLL_CLK]->clk; - if (pixel_clk_provider) - *pixel_clk_provider = hw_data->hws[DSI_PIXEL_PLL_CLK]->clk; - - return 0; -} - -static void dsi_pll_10nm_destroy(struct msm_dsi_pll *pll) -{ - struct dsi_pll_10nm *pll_10nm = to_pll_10nm(pll); - struct device *dev = &pll_10nm->pdev->dev; - - DBG("DSI PLL%d", pll_10nm->id); - of_clk_del_provider(dev->of_node); - - clk_hw_unregister_divider(pll_10nm->out_dsiclk_hw); - clk_hw_unregister_mux(pll_10nm->pclk_mux_hw); - clk_hw_unregister_fixed_factor(pll_10nm->post_out_div_clk_hw); - clk_hw_unregister_fixed_factor(pll_10nm->by_2_bit_clk_hw); - clk_hw_unregister_fixed_factor(pll_10nm->byte_clk_hw); - clk_hw_unregister_divider(pll_10nm->bit_clk_hw); - clk_hw_unregister_divider(pll_10nm->out_div_clk_hw); - clk_hw_unregister(&pll_10nm->base.clk_hw); -} - -/* - * The post dividers and mux clocks are created using the standard divider and - * mux API. Unlike the 14nm PHY, the slave PLL doesn't need its dividers/mux - * state to follow the master PLL's divider/mux state. Therefore, we don't - * require special clock ops that also configure the slave PLL registers - */ -static int pll_10nm_register(struct dsi_pll_10nm *pll_10nm) -{ - char clk_name[32], parent[32], vco_name[32]; - char parent2[32], parent3[32], parent4[32]; - struct clk_init_data vco_init = { - .parent_names = (const char *[]){ "xo" }, - .num_parents = 1, - .name = vco_name, - .flags = CLK_IGNORE_UNUSED, - .ops = &clk_ops_dsi_pll_10nm_vco, - }; - struct device *dev = &pll_10nm->pdev->dev; - struct clk_hw_onecell_data *hw_data; - struct clk_hw *hw; - int ret; - - DBG("DSI%d", pll_10nm->id); - - hw_data = devm_kzalloc(dev, sizeof(*hw_data) + - NUM_PROVIDED_CLKS * sizeof(struct clk_hw *), - GFP_KERNEL); - if (!hw_data) - return -ENOMEM; - - snprintf(vco_name, 32, "dsi%dvco_clk", pll_10nm->id); - pll_10nm->base.clk_hw.init = &vco_init; - - ret = clk_hw_register(dev, &pll_10nm->base.clk_hw); - if (ret) - return ret; - - snprintf(clk_name, 32, "dsi%d_pll_out_div_clk", pll_10nm->id); - snprintf(parent, 32, "dsi%dvco_clk", pll_10nm->id); - - hw = clk_hw_register_divider(dev, clk_name, - parent, CLK_SET_RATE_PARENT, - pll_10nm->mmio + - REG_DSI_10nm_PHY_PLL_PLL_OUTDIV_RATE, - 0, 2, CLK_DIVIDER_POWER_OF_TWO, NULL); - if (IS_ERR(hw)) { - ret = PTR_ERR(hw); - goto err_base_clk_hw; - } - - pll_10nm->out_div_clk_hw = hw; - - snprintf(clk_name, 32, "dsi%d_pll_bit_clk", pll_10nm->id); - snprintf(parent, 32, "dsi%d_pll_out_div_clk", pll_10nm->id); - - /* BIT CLK: DIV_CTRL_3_0 */ - hw = clk_hw_register_divider(dev, clk_name, parent, - CLK_SET_RATE_PARENT, - pll_10nm->phy_cmn_mmio + - REG_DSI_10nm_PHY_CMN_CLK_CFG0, - 0, 4, CLK_DIVIDER_ONE_BASED, - &pll_10nm->postdiv_lock); - if (IS_ERR(hw)) { - ret = PTR_ERR(hw); - goto err_out_div_clk_hw; - } - - pll_10nm->bit_clk_hw = hw; - - snprintf(clk_name, 32, "dsi%d_phy_pll_out_byteclk", pll_10nm->id); - snprintf(parent, 32, "dsi%d_pll_bit_clk", pll_10nm->id); - - /* DSI Byte clock = VCO_CLK / OUT_DIV / BIT_DIV / 8 */ - hw = clk_hw_register_fixed_factor(dev, clk_name, parent, - CLK_SET_RATE_PARENT, 1, 8); - if (IS_ERR(hw)) { - ret = PTR_ERR(hw); - goto err_bit_clk_hw; - } - - pll_10nm->byte_clk_hw = hw; - hw_data->hws[DSI_BYTE_PLL_CLK] = hw; - - snprintf(clk_name, 32, "dsi%d_pll_by_2_bit_clk", pll_10nm->id); - snprintf(parent, 32, "dsi%d_pll_bit_clk", pll_10nm->id); - - hw = clk_hw_register_fixed_factor(dev, clk_name, parent, - 0, 1, 2); - if (IS_ERR(hw)) { - ret = PTR_ERR(hw); - goto err_byte_clk_hw; - } - - pll_10nm->by_2_bit_clk_hw = hw; - - snprintf(clk_name, 32, "dsi%d_pll_post_out_div_clk", pll_10nm->id); - snprintf(parent, 32, "dsi%d_pll_out_div_clk", pll_10nm->id); - - hw = clk_hw_register_fixed_factor(dev, clk_name, parent, - 0, 1, 4); - if (IS_ERR(hw)) { - ret = PTR_ERR(hw); - goto err_by_2_bit_clk_hw; - } - - pll_10nm->post_out_div_clk_hw = hw; - - snprintf(clk_name, 32, "dsi%d_pclk_mux", pll_10nm->id); - snprintf(parent, 32, "dsi%d_pll_bit_clk", pll_10nm->id); - snprintf(parent2, 32, "dsi%d_pll_by_2_bit_clk", pll_10nm->id); - snprintf(parent3, 32, "dsi%d_pll_out_div_clk", pll_10nm->id); - snprintf(parent4, 32, "dsi%d_pll_post_out_div_clk", pll_10nm->id); - - hw = clk_hw_register_mux(dev, clk_name, - ((const char *[]){ - parent, parent2, parent3, parent4 - }), 4, 0, pll_10nm->phy_cmn_mmio + - REG_DSI_10nm_PHY_CMN_CLK_CFG1, - 0, 2, 0, NULL); - if (IS_ERR(hw)) { - ret = PTR_ERR(hw); - goto err_post_out_div_clk_hw; - } - - pll_10nm->pclk_mux_hw = hw; - - snprintf(clk_name, 32, "dsi%d_phy_pll_out_dsiclk", pll_10nm->id); - snprintf(parent, 32, "dsi%d_pclk_mux", pll_10nm->id); - - /* PIX CLK DIV : DIV_CTRL_7_4*/ - hw = clk_hw_register_divider(dev, clk_name, parent, - 0, pll_10nm->phy_cmn_mmio + - REG_DSI_10nm_PHY_CMN_CLK_CFG0, - 4, 4, CLK_DIVIDER_ONE_BASED, - &pll_10nm->postdiv_lock); - if (IS_ERR(hw)) { - ret = PTR_ERR(hw); - goto err_pclk_mux_hw; - } - - pll_10nm->out_dsiclk_hw = hw; - hw_data->hws[DSI_PIXEL_PLL_CLK] = hw; - - hw_data->num = NUM_PROVIDED_CLKS; - pll_10nm->hw_data = hw_data; - - ret = of_clk_add_hw_provider(dev->of_node, of_clk_hw_onecell_get, - pll_10nm->hw_data); - if (ret) { - DRM_DEV_ERROR(dev, "failed to register clk provider: %d\n", ret); - goto err_dsiclk_hw; - } - - return 0; - -err_dsiclk_hw: - clk_hw_unregister_divider(pll_10nm->out_dsiclk_hw); -err_pclk_mux_hw: - clk_hw_unregister_mux(pll_10nm->pclk_mux_hw); -err_post_out_div_clk_hw: - clk_hw_unregister_fixed_factor(pll_10nm->post_out_div_clk_hw); -err_by_2_bit_clk_hw: - clk_hw_unregister_fixed_factor(pll_10nm->by_2_bit_clk_hw); -err_byte_clk_hw: - clk_hw_unregister_fixed_factor(pll_10nm->byte_clk_hw); -err_bit_clk_hw: - clk_hw_unregister_divider(pll_10nm->bit_clk_hw); -err_out_div_clk_hw: - clk_hw_unregister_divider(pll_10nm->out_div_clk_hw); -err_base_clk_hw: - clk_hw_unregister(&pll_10nm->base.clk_hw); - - return ret; -} - -struct msm_dsi_pll *msm_dsi_pll_10nm_init(struct platform_device *pdev, int id) -{ - struct dsi_pll_10nm *pll_10nm; - struct msm_dsi_pll *pll; - int ret; - - pll_10nm = devm_kzalloc(&pdev->dev, sizeof(*pll_10nm), GFP_KERNEL); - if (!pll_10nm) - return ERR_PTR(-ENOMEM); - - DBG("DSI PLL%d", id); - - pll_10nm->pdev = pdev; - pll_10nm->id = id; - pll_10nm_list[id] = pll_10nm; - - pll_10nm->phy_cmn_mmio = msm_ioremap(pdev, "dsi_phy", "DSI_PHY"); - if (IS_ERR_OR_NULL(pll_10nm->phy_cmn_mmio)) { - DRM_DEV_ERROR(&pdev->dev, "failed to map CMN PHY base\n"); - return ERR_PTR(-ENOMEM); - } - - pll_10nm->mmio = msm_ioremap(pdev, "dsi_pll", "DSI_PLL"); - if (IS_ERR_OR_NULL(pll_10nm->mmio)) { - DRM_DEV_ERROR(&pdev->dev, "failed to map PLL base\n"); - return ERR_PTR(-ENOMEM); - } - - spin_lock_init(&pll_10nm->postdiv_lock); - - pll = &pll_10nm->base; - pll->min_rate = 1000000000UL; - pll->max_rate = 3500000000UL; - pll->get_provider = dsi_pll_10nm_get_provider; - pll->destroy = dsi_pll_10nm_destroy; - pll->save_state = dsi_pll_10nm_save_state; - pll->restore_state = dsi_pll_10nm_restore_state; - pll->set_usecase = dsi_pll_10nm_set_usecase; - - pll_10nm->vco_delay = 1; - - ret = pll_10nm_register(pll_10nm); - if (ret) { - DRM_DEV_ERROR(&pdev->dev, "failed to register PLL: %d\n", ret); - return ERR_PTR(ret); - } - - /* TODO: Remove this when we have proper display handover support */ - msm_dsi_pll_save_state(pll); - - return pll; -} diff --git a/drivers/gpu/drm/msm/dsi/pll/dsi_pll_14nm.c b/drivers/gpu/drm/msm/dsi/pll/dsi_pll_14nm.c deleted file mode 100644 index f847376d501e..000000000000 --- a/drivers/gpu/drm/msm/dsi/pll/dsi_pll_14nm.c +++ /dev/null @@ -1,1096 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Copyright (c) 2016, The Linux Foundation. All rights reserved. - */ - -#include <linux/clk.h> -#include <linux/clk-provider.h> - -#include "dsi_pll.h" -#include "dsi.xml.h" - -/* - * DSI PLL 14nm - clock diagram (eg: DSI0): - * - * dsi0n1_postdiv_clk - * | - * | - * +----+ | +----+ - * dsi0vco_clk ---| n1 |--o--| /8 |-- dsi0pllbyte - * +----+ | +----+ - * | dsi0n1_postdivby2_clk - * | +----+ | - * o---| /2 |--o--|\ - * | +----+ | \ +----+ - * | | |--| n2 |-- dsi0pll - * o--------------| / +----+ - * |/ - */ - -#define POLL_MAX_READS 15 -#define POLL_TIMEOUT_US 1000 - -#define NUM_PROVIDED_CLKS 2 - -#define VCO_REF_CLK_RATE 19200000 -#define VCO_MIN_RATE 1300000000UL -#define VCO_MAX_RATE 2600000000UL - -#define DSI_BYTE_PLL_CLK 0 -#define DSI_PIXEL_PLL_CLK 1 - -#define DSI_PLL_DEFAULT_VCO_POSTDIV 1 - -struct dsi_pll_input { - u32 fref; /* reference clk */ - u32 fdata; /* bit clock rate */ - u32 dsiclk_sel; /* Mux configuration (see diagram) */ - u32 ssc_en; /* SSC enable/disable */ - u32 ldo_en; - - /* fixed params */ - u32 refclk_dbler_en; - u32 vco_measure_time; - u32 kvco_measure_time; - u32 bandgap_timer; - u32 pll_wakeup_timer; - u32 plllock_cnt; - u32 plllock_rng; - u32 ssc_center; - u32 ssc_adj_period; - u32 ssc_spread; - u32 ssc_freq; - u32 pll_ie_trim; - u32 pll_ip_trim; - u32 pll_iptat_trim; - u32 pll_cpcset_cur; - u32 pll_cpmset_cur; - - u32 pll_icpmset; - u32 pll_icpcset; - - u32 pll_icpmset_p; - u32 pll_icpmset_m; - - u32 pll_icpcset_p; - u32 pll_icpcset_m; - - u32 pll_lpf_res1; - u32 pll_lpf_cap1; - u32 pll_lpf_cap2; - u32 pll_c3ctrl; - u32 pll_r3ctrl; -}; - -struct dsi_pll_output { - u32 pll_txclk_en; - u32 dec_start; - u32 div_frac_start; - u32 ssc_period; - u32 ssc_step_size; - u32 plllock_cmp; - u32 pll_vco_div_ref; - u32 pll_vco_count; - u32 pll_kvco_div_ref; - u32 pll_kvco_count; - u32 pll_misc1; - u32 pll_lpf2_postdiv; - u32 pll_resetsm_cntrl; - u32 pll_resetsm_cntrl2; - u32 pll_resetsm_cntrl5; - u32 pll_kvco_code; - - u32 cmn_clk_cfg0; - u32 cmn_clk_cfg1; - u32 cmn_ldo_cntrl; - - u32 pll_postdiv; - u32 fcvo; -}; - -struct pll_14nm_cached_state { - unsigned long vco_rate; - u8 n2postdiv; - u8 n1postdiv; -}; - -struct dsi_pll_14nm { - struct msm_dsi_pll base; - - int id; - struct platform_device *pdev; - - void __iomem *phy_cmn_mmio; - void __iomem *mmio; - - int vco_delay; - - struct dsi_pll_input in; - struct dsi_pll_output out; - - /* protects REG_DSI_14nm_PHY_CMN_CLK_CFG0 register */ - spinlock_t postdiv_lock; - - u64 vco_current_rate; - u64 vco_ref_clk_rate; - - /* private clocks: */ - struct clk_hw *hws[NUM_DSI_CLOCKS_MAX]; - u32 num_hws; - - /* clock-provider: */ - struct clk_hw_onecell_data *hw_data; - - struct pll_14nm_cached_state cached_state; - - enum msm_dsi_phy_usecase uc; - struct dsi_pll_14nm *slave; -}; - -#define to_pll_14nm(x) container_of(x, struct dsi_pll_14nm, base) - -/* - * Private struct for N1/N2 post-divider clocks. These clocks are similar to - * the generic clk_divider class of clocks. The only difference is that it - * also sets the slave DSI PLL's post-dividers if in Dual DSI mode - */ -struct dsi_pll_14nm_postdiv { - struct clk_hw hw; - - /* divider params */ - u8 shift; - u8 width; - u8 flags; /* same flags as used by clk_divider struct */ - - struct dsi_pll_14nm *pll; -}; - -#define to_pll_14nm_postdiv(_hw) container_of(_hw, struct dsi_pll_14nm_postdiv, hw) - -/* - * Global list of private DSI PLL struct pointers. We need this for Dual DSI - * mode, where the master PLL's clk_ops needs access the slave's private data - */ -static struct dsi_pll_14nm *pll_14nm_list[DSI_MAX]; - -static bool pll_14nm_poll_for_ready(struct dsi_pll_14nm *pll_14nm, - u32 nb_tries, u32 timeout_us) -{ - bool pll_locked = false; - void __iomem *base = pll_14nm->mmio; - u32 tries, val; - - tries = nb_tries; - while (tries--) { - val = pll_read(base + - REG_DSI_14nm_PHY_PLL_RESET_SM_READY_STATUS); - pll_locked = !!(val & BIT(5)); - - if (pll_locked) - break; - - udelay(timeout_us); - } - - if (!pll_locked) { - tries = nb_tries; - while (tries--) { - val = pll_read(base + - REG_DSI_14nm_PHY_PLL_RESET_SM_READY_STATUS); - pll_locked = !!(val & BIT(0)); - - if (pll_locked) - break; - - udelay(timeout_us); - } - } - - DBG("DSI PLL is %slocked", pll_locked ? "" : "*not* "); - - return pll_locked; -} - -static void dsi_pll_14nm_input_init(struct dsi_pll_14nm *pll) -{ - pll->in.fref = pll->vco_ref_clk_rate; - pll->in.fdata = 0; - pll->in.dsiclk_sel = 1; /* Use the /2 path in Mux */ - pll->in.ldo_en = 0; /* disabled for now */ - - /* fixed input */ - pll->in.refclk_dbler_en = 0; - pll->in.vco_measure_time = 5; - pll->in.kvco_measure_time = 5; - pll->in.bandgap_timer = 4; - pll->in.pll_wakeup_timer = 5; - pll->in.plllock_cnt = 1; - pll->in.plllock_rng = 0; - - /* - * SSC is enabled by default. We might need DT props for configuring - * some SSC params like PPM and center/down spread etc. - */ - pll->in.ssc_en = 1; - pll->in.ssc_center = 0; /* down spread by default */ - pll->in.ssc_spread = 5; /* PPM / 1000 */ - pll->in.ssc_freq = 31500; /* default recommended */ - pll->in.ssc_adj_period = 37; - - pll->in.pll_ie_trim = 4; - pll->in.pll_ip_trim = 4; - pll->in.pll_cpcset_cur = 1; - pll->in.pll_cpmset_cur = 1; - pll->in.pll_icpmset = 4; - pll->in.pll_icpcset = 4; - pll->in.pll_icpmset_p = 0; - pll->in.pll_icpmset_m = 0; - pll->in.pll_icpcset_p = 0; - pll->in.pll_icpcset_m = 0; - pll->in.pll_lpf_res1 = 3; - pll->in.pll_lpf_cap1 = 11; - pll->in.pll_lpf_cap2 = 1; - pll->in.pll_iptat_trim = 7; - pll->in.pll_c3ctrl = 2; - pll->in.pll_r3ctrl = 1; -} - -#define CEIL(x, y) (((x) + ((y) - 1)) / (y)) - -static void pll_14nm_ssc_calc(struct dsi_pll_14nm *pll) -{ - u32 period, ssc_period; - u32 ref, rem; - u64 step_size; - - DBG("vco=%lld ref=%lld", pll->vco_current_rate, pll->vco_ref_clk_rate); - - ssc_period = pll->in.ssc_freq / 500; - period = (u32)pll->vco_ref_clk_rate / 1000; - ssc_period = CEIL(period, ssc_period); - ssc_period -= 1; - pll->out.ssc_period = ssc_period; - - DBG("ssc freq=%d spread=%d period=%d", pll->in.ssc_freq, - pll->in.ssc_spread, pll->out.ssc_period); - - step_size = (u32)pll->vco_current_rate; - ref = pll->vco_ref_clk_rate; - ref /= 1000; - step_size = div_u64(step_size, ref); - step_size <<= 20; - step_size = div_u64(step_size, 1000); - step_size *= pll->in.ssc_spread; - step_size = div_u64(step_size, 1000); - step_size *= (pll->in.ssc_adj_period + 1); - - rem = 0; - step_size = div_u64_rem(step_size, ssc_period + 1, &rem); - if (rem) - step_size++; - - DBG("step_size=%lld", step_size); - - step_size &= 0x0ffff; /* take lower 16 bits */ - - pll->out.ssc_step_size = step_size; -} - -static void pll_14nm_dec_frac_calc(struct dsi_pll_14nm *pll) -{ - struct dsi_pll_input *pin = &pll->in; - struct dsi_pll_output *pout = &pll->out; - u64 multiplier = BIT(20); - u64 dec_start_multiple, dec_start, pll_comp_val; - u32 duration, div_frac_start; - u64 vco_clk_rate = pll->vco_current_rate; - u64 fref = pll->vco_ref_clk_rate; - - DBG("vco_clk_rate=%lld ref_clk_rate=%lld", vco_clk_rate, fref); - - dec_start_multiple = div_u64(vco_clk_rate * multiplier, fref); - div_u64_rem(dec_start_multiple, multiplier, &div_frac_start); - - dec_start = div_u64(dec_start_multiple, multiplier); - - pout->dec_start = (u32)dec_start; - pout->div_frac_start = div_frac_start; - - if (pin->plllock_cnt == 0) - duration = 1024; - else if (pin->plllock_cnt == 1) - duration = 256; - else if (pin->plllock_cnt == 2) - duration = 128; - else - duration = 32; - - pll_comp_val = duration * dec_start_multiple; - pll_comp_val = div_u64(pll_comp_val, multiplier); - do_div(pll_comp_val, 10); - - pout->plllock_cmp = (u32)pll_comp_val; - - pout->pll_txclk_en = 1; - pout->cmn_ldo_cntrl = 0x3c; -} - -static u32 pll_14nm_kvco_slop(u32 vrate) -{ - u32 slop = 0; - - if (vrate > VCO_MIN_RATE && vrate <= 1800000000UL) - slop = 600; - else if (vrate > 1800000000UL && vrate < 2300000000UL) - slop = 400; - else if (vrate > 2300000000UL && vrate < VCO_MAX_RATE) - slop = 280; - - return slop; -} - -static void pll_14nm_calc_vco_count(struct dsi_pll_14nm *pll) -{ - struct dsi_pll_input *pin = &pll->in; - struct dsi_pll_output *pout = &pll->out; - u64 vco_clk_rate = pll->vco_current_rate; - u64 fref = pll->vco_ref_clk_rate; - u64 data; - u32 cnt; - - data = fref * pin->vco_measure_time; - do_div(data, 1000000); - data &= 0x03ff; /* 10 bits */ - data -= 2; - pout->pll_vco_div_ref = data; - - data = div_u64(vco_clk_rate, 1000000); /* unit is Mhz */ - data *= pin->vco_measure_time; - do_div(data, 10); - pout->pll_vco_count = data; - - data = fref * pin->kvco_measure_time; - do_div(data, 1000000); - data &= 0x03ff; /* 10 bits */ - data -= 1; - pout->pll_kvco_div_ref = data; - - cnt = pll_14nm_kvco_slop(vco_clk_rate); - cnt *= 2; - cnt /= 100; - cnt *= pin->kvco_measure_time; - pout->pll_kvco_count = cnt; - - pout->pll_misc1 = 16; - pout->pll_resetsm_cntrl = 48; - pout->pll_resetsm_cntrl2 = pin->bandgap_timer << 3; - pout->pll_resetsm_cntrl5 = pin->pll_wakeup_timer; - pout->pll_kvco_code = 0; -} - -static void pll_db_commit_ssc(struct dsi_pll_14nm *pll) -{ - void __iomem *base = pll->mmio; - struct dsi_pll_input *pin = &pll->in; - struct dsi_pll_output *pout = &pll->out; - u8 data; - - data = pin->ssc_adj_period; - data &= 0x0ff; - pll_write(base + REG_DSI_14nm_PHY_PLL_SSC_ADJ_PER1, data); - data = (pin->ssc_adj_period >> 8); - data &= 0x03; - pll_write(base + REG_DSI_14nm_PHY_PLL_SSC_ADJ_PER2, data); - - data = pout->ssc_period; - data &= 0x0ff; - pll_write(base + REG_DSI_14nm_PHY_PLL_SSC_PER1, data); - data = (pout->ssc_period >> 8); - data &= 0x0ff; - pll_write(base + REG_DSI_14nm_PHY_PLL_SSC_PER2, data); - - data = pout->ssc_step_size; - data &= 0x0ff; - pll_write(base + REG_DSI_14nm_PHY_PLL_SSC_STEP_SIZE1, data); - data = (pout->ssc_step_size >> 8); - data &= 0x0ff; - pll_write(base + REG_DSI_14nm_PHY_PLL_SSC_STEP_SIZE2, data); - - data = (pin->ssc_center & 0x01); - data <<= 1; - data |= 0x01; /* enable */ - pll_write(base + REG_DSI_14nm_PHY_PLL_SSC_EN_CENTER, data); - - wmb(); /* make sure register committed */ -} - -static void pll_db_commit_common(struct dsi_pll_14nm *pll, - struct dsi_pll_input *pin, - struct dsi_pll_output *pout) -{ - void __iomem *base = pll->mmio; - u8 data; - - /* confgiure the non frequency dependent pll registers */ - data = 0; - pll_write(base + REG_DSI_14nm_PHY_PLL_SYSCLK_EN_RESET, data); - - data = pout->pll_txclk_en; - pll_write(base + REG_DSI_14nm_PHY_PLL_TXCLK_EN, data); - - data = pout->pll_resetsm_cntrl; - pll_write(base + REG_DSI_14nm_PHY_PLL_RESETSM_CNTRL, data); - data = pout->pll_resetsm_cntrl2; - pll_write(base + REG_DSI_14nm_PHY_PLL_RESETSM_CNTRL2, data); - data = pout->pll_resetsm_cntrl5; - pll_write(base + REG_DSI_14nm_PHY_PLL_RESETSM_CNTRL5, data); - - data = pout->pll_vco_div_ref & 0xff; - pll_write(base + REG_DSI_14nm_PHY_PLL_VCO_DIV_REF1, data); - data = (pout->pll_vco_div_ref >> 8) & 0x3; - pll_write(base + REG_DSI_14nm_PHY_PLL_VCO_DIV_REF2, data); - - data = pout->pll_kvco_div_ref & 0xff; - pll_write(base + REG_DSI_14nm_PHY_PLL_KVCO_DIV_REF1, data); - data = (pout->pll_kvco_div_ref >> 8) & 0x3; - pll_write(base + REG_DSI_14nm_PHY_PLL_KVCO_DIV_REF2, data); - - data = pout->pll_misc1; - pll_write(base + REG_DSI_14nm_PHY_PLL_PLL_MISC1, data); - - data = pin->pll_ie_trim; - pll_write(base + REG_DSI_14nm_PHY_PLL_IE_TRIM, data); - - data = pin->pll_ip_trim; - pll_write(base + REG_DSI_14nm_PHY_PLL_IP_TRIM, data); - - data = pin->pll_cpmset_cur << 3 | pin->pll_cpcset_cur; - pll_write(base + REG_DSI_14nm_PHY_PLL_CP_SET_CUR, data); - - data = pin->pll_icpcset_p << 3 | pin->pll_icpcset_m; - pll_write(base + REG_DSI_14nm_PHY_PLL_PLL_ICPCSET, data); - - data = pin->pll_icpmset_p << 3 | pin->pll_icpcset_m; - pll_write(base + REG_DSI_14nm_PHY_PLL_PLL_ICPMSET, data); - - data = pin->pll_icpmset << 3 | pin->pll_icpcset; - pll_write(base + REG_DSI_14nm_PHY_PLL_PLL_ICP_SET, data); - - data = pin->pll_lpf_cap2 << 4 | pin->pll_lpf_cap1; - pll_write(base + REG_DSI_14nm_PHY_PLL_PLL_LPF1, data); - - data = pin->pll_iptat_trim; - pll_write(base + REG_DSI_14nm_PHY_PLL_IPTAT_TRIM, data); - - data = pin->pll_c3ctrl | pin->pll_r3ctrl << 4; - pll_write(base + REG_DSI_14nm_PHY_PLL_PLL_CRCTRL, data); -} - -static void pll_14nm_software_reset(struct dsi_pll_14nm *pll_14nm) -{ - void __iomem *cmn_base = pll_14nm->phy_cmn_mmio; - - /* de assert pll start and apply pll sw reset */ - - /* stop pll */ - pll_write(cmn_base + REG_DSI_14nm_PHY_CMN_PLL_CNTRL, 0); - - /* pll sw reset */ - pll_write_udelay(cmn_base + REG_DSI_14nm_PHY_CMN_CTRL_1, 0x20, 10); - wmb(); /* make sure register committed */ - - pll_write(cmn_base + REG_DSI_14nm_PHY_CMN_CTRL_1, 0); - wmb(); /* make sure register committed */ -} - -static void pll_db_commit_14nm(struct dsi_pll_14nm *pll, - struct dsi_pll_input *pin, - struct dsi_pll_output *pout) -{ - void __iomem *base = pll->mmio; - void __iomem *cmn_base = pll->phy_cmn_mmio; - u8 data; - - DBG("DSI%d PLL", pll->id); - - data = pout->cmn_ldo_cntrl; - pll_write(cmn_base + REG_DSI_14nm_PHY_CMN_LDO_CNTRL, data); - - pll_db_commit_common(pll, pin, pout); - - pll_14nm_software_reset(pll); - - data = pin->dsiclk_sel; /* set dsiclk_sel = 1 */ - pll_write(cmn_base + REG_DSI_14nm_PHY_CMN_CLK_CFG1, data); - - data = 0xff; /* data, clk, pll normal operation */ - pll_write(cmn_base + REG_DSI_14nm_PHY_CMN_CTRL_0, data); - - /* configure the frequency dependent pll registers */ - data = pout->dec_start; - pll_write(base + REG_DSI_14nm_PHY_PLL_DEC_START, data); - - data = pout->div_frac_start & 0xff; - pll_write(base + REG_DSI_14nm_PHY_PLL_DIV_FRAC_START1, data); - data = (pout->div_frac_start >> 8) & 0xff; - pll_write(base + REG_DSI_14nm_PHY_PLL_DIV_FRAC_START2, data); - data = (pout->div_frac_start >> 16) & 0xf; - pll_write(base + REG_DSI_14nm_PHY_PLL_DIV_FRAC_START3, data); - - data = pout->plllock_cmp & 0xff; - pll_write(base + REG_DSI_14nm_PHY_PLL_PLLLOCK_CMP1, data); - - data = (pout->plllock_cmp >> 8) & 0xff; - pll_write(base + REG_DSI_14nm_PHY_PLL_PLLLOCK_CMP2, data); - - data = (pout->plllock_cmp >> 16) & 0x3; - pll_write(base + REG_DSI_14nm_PHY_PLL_PLLLOCK_CMP3, data); - - data = pin->plllock_cnt << 1 | pin->plllock_rng << 3; - pll_write(base + REG_DSI_14nm_PHY_PLL_PLLLOCK_CMP_EN, data); - - data = pout->pll_vco_count & 0xff; - pll_write(base + REG_DSI_14nm_PHY_PLL_VCO_COUNT1, data); - data = (pout->pll_vco_count >> 8) & 0xff; - pll_write(base + REG_DSI_14nm_PHY_PLL_VCO_COUNT2, data); - - data = pout->pll_kvco_count & 0xff; - pll_write(base + REG_DSI_14nm_PHY_PLL_KVCO_COUNT1, data); - data = (pout->pll_kvco_count >> 8) & 0x3; - pll_write(base + REG_DSI_14nm_PHY_PLL_KVCO_COUNT2, data); - - data = (pout->pll_postdiv - 1) << 4 | pin->pll_lpf_res1; - pll_write(base + REG_DSI_14nm_PHY_PLL_PLL_LPF2_POSTDIV, data); - - if (pin->ssc_en) - pll_db_commit_ssc(pll); - - wmb(); /* make sure register committed */ -} - -/* - * VCO clock Callbacks - */ -static int dsi_pll_14nm_vco_set_rate(struct clk_hw *hw, unsigned long rate, - unsigned long parent_rate) -{ - struct msm_dsi_pll *pll = hw_clk_to_pll(hw); - struct dsi_pll_14nm *pll_14nm = to_pll_14nm(pll); - struct dsi_pll_input *pin = &pll_14nm->in; - struct dsi_pll_output *pout = &pll_14nm->out; - - DBG("DSI PLL%d rate=%lu, parent's=%lu", pll_14nm->id, rate, - parent_rate); - - pll_14nm->vco_current_rate = rate; - pll_14nm->vco_ref_clk_rate = VCO_REF_CLK_RATE; - - dsi_pll_14nm_input_init(pll_14nm); - - /* - * This configures the post divider internal to the VCO. It's - * fixed to divide by 1 for now. - * - * tx_band = pll_postdiv. - * 0: divided by 1 - * 1: divided by 2 - * 2: divided by 4 - * 3: divided by 8 - */ - pout->pll_postdiv = DSI_PLL_DEFAULT_VCO_POSTDIV; - - pll_14nm_dec_frac_calc(pll_14nm); - - if (pin->ssc_en) - pll_14nm_ssc_calc(pll_14nm); - - pll_14nm_calc_vco_count(pll_14nm); - - /* commit the slave DSI PLL registers if we're master. Note that we - * don't lock the slave PLL. We just ensure that the PLL/PHY registers - * of the master and slave are identical - */ - if (pll_14nm->uc == MSM_DSI_PHY_MASTER) { - struct dsi_pll_14nm *pll_14nm_slave = pll_14nm->slave; - - pll_db_commit_14nm(pll_14nm_slave, pin, pout); - } - - pll_db_commit_14nm(pll_14nm, pin, pout); - - return 0; -} - -static unsigned long dsi_pll_14nm_vco_recalc_rate(struct clk_hw *hw, - unsigned long parent_rate) -{ - struct msm_dsi_pll *pll = hw_clk_to_pll(hw); - struct dsi_pll_14nm *pll_14nm = to_pll_14nm(pll); - void __iomem *base = pll_14nm->mmio; - u64 vco_rate, multiplier = BIT(20); - u32 div_frac_start; - u32 dec_start; - u64 ref_clk = parent_rate; - - dec_start = pll_read(base + REG_DSI_14nm_PHY_PLL_DEC_START); - dec_start &= 0x0ff; - - DBG("dec_start = %x", dec_start); - - div_frac_start = (pll_read(base + REG_DSI_14nm_PHY_PLL_DIV_FRAC_START3) - & 0xf) << 16; - div_frac_start |= (pll_read(base + REG_DSI_14nm_PHY_PLL_DIV_FRAC_START2) - & 0xff) << 8; - div_frac_start |= pll_read(base + REG_DSI_14nm_PHY_PLL_DIV_FRAC_START1) - & 0xff; - - DBG("div_frac_start = %x", div_frac_start); - - vco_rate = ref_clk * dec_start; - - vco_rate += ((ref_clk * div_frac_start) / multiplier); - - /* - * Recalculating the rate from dec_start and frac_start doesn't end up - * the rate we originally set. Convert the freq to KHz, round it up and - * convert it back to MHz. - */ - vco_rate = DIV_ROUND_UP_ULL(vco_rate, 1000) * 1000; - - DBG("returning vco rate = %lu", (unsigned long)vco_rate); - - return (unsigned long)vco_rate; -} - -static const struct clk_ops clk_ops_dsi_pll_14nm_vco = { - .round_rate = msm_dsi_pll_helper_clk_round_rate, - .set_rate = dsi_pll_14nm_vco_set_rate, - .recalc_rate = dsi_pll_14nm_vco_recalc_rate, - .prepare = msm_dsi_pll_helper_clk_prepare, - .unprepare = msm_dsi_pll_helper_clk_unprepare, -}; - -/* - * N1 and N2 post-divider clock callbacks - */ -#define div_mask(width) ((1 << (width)) - 1) -static unsigned long dsi_pll_14nm_postdiv_recalc_rate(struct clk_hw *hw, - unsigned long parent_rate) -{ - struct dsi_pll_14nm_postdiv *postdiv = to_pll_14nm_postdiv(hw); - struct dsi_pll_14nm *pll_14nm = postdiv->pll; - void __iomem *base = pll_14nm->phy_cmn_mmio; - u8 shift = postdiv->shift; - u8 width = postdiv->width; - u32 val; - - DBG("DSI%d PLL parent rate=%lu", pll_14nm->id, parent_rate); - - val = pll_read(base + REG_DSI_14nm_PHY_CMN_CLK_CFG0) >> shift; - val &= div_mask(width); - - return divider_recalc_rate(hw, parent_rate, val, NULL, - postdiv->flags, width); -} - -static long dsi_pll_14nm_postdiv_round_rate(struct clk_hw *hw, - unsigned long rate, - unsigned long *prate) -{ - struct dsi_pll_14nm_postdiv *postdiv = to_pll_14nm_postdiv(hw); - struct dsi_pll_14nm *pll_14nm = postdiv->pll; - - DBG("DSI%d PLL parent rate=%lu", pll_14nm->id, rate); - - return divider_round_rate(hw, rate, prate, NULL, - postdiv->width, - postdiv->flags); -} - -static int dsi_pll_14nm_postdiv_set_rate(struct clk_hw *hw, unsigned long rate, - unsigned long parent_rate) -{ - struct dsi_pll_14nm_postdiv *postdiv = to_pll_14nm_postdiv(hw); - struct dsi_pll_14nm *pll_14nm = postdiv->pll; - void __iomem *base = pll_14nm->phy_cmn_mmio; - spinlock_t *lock = &pll_14nm->postdiv_lock; - u8 shift = postdiv->shift; - u8 width = postdiv->width; - unsigned int value; - unsigned long flags = 0; - u32 val; - - DBG("DSI%d PLL parent rate=%lu parent rate %lu", pll_14nm->id, rate, - parent_rate); - - value = divider_get_val(rate, parent_rate, NULL, postdiv->width, - postdiv->flags); - - spin_lock_irqsave(lock, flags); - - val = pll_read(base + REG_DSI_14nm_PHY_CMN_CLK_CFG0); - val &= ~(div_mask(width) << shift); - - val |= value << shift; - pll_write(base + REG_DSI_14nm_PHY_CMN_CLK_CFG0, val); - - /* If we're master in dual DSI mode, then the slave PLL's post-dividers - * follow the master's post dividers - */ - if (pll_14nm->uc == MSM_DSI_PHY_MASTER) { - struct dsi_pll_14nm *pll_14nm_slave = pll_14nm->slave; - void __iomem *slave_base = pll_14nm_slave->phy_cmn_mmio; - - pll_write(slave_base + REG_DSI_14nm_PHY_CMN_CLK_CFG0, val); - } - - spin_unlock_irqrestore(lock, flags); - - return 0; -} - -static const struct clk_ops clk_ops_dsi_pll_14nm_postdiv = { - .recalc_rate = dsi_pll_14nm_postdiv_recalc_rate, - .round_rate = dsi_pll_14nm_postdiv_round_rate, - .set_rate = dsi_pll_14nm_postdiv_set_rate, -}; - -/* - * PLL Callbacks - */ - -static int dsi_pll_14nm_enable_seq(struct msm_dsi_pll *pll) -{ - struct dsi_pll_14nm *pll_14nm = to_pll_14nm(pll); - void __iomem *base = pll_14nm->mmio; - void __iomem *cmn_base = pll_14nm->phy_cmn_mmio; - bool locked; - - DBG(""); - - pll_write(base + REG_DSI_14nm_PHY_PLL_VREF_CFG1, 0x10); - pll_write(cmn_base + REG_DSI_14nm_PHY_CMN_PLL_CNTRL, 1); - - locked = pll_14nm_poll_for_ready(pll_14nm, POLL_MAX_READS, - POLL_TIMEOUT_US); - - if (unlikely(!locked)) - DRM_DEV_ERROR(&pll_14nm->pdev->dev, "DSI PLL lock failed\n"); - else - DBG("DSI PLL lock success"); - - return locked ? 0 : -EINVAL; -} - -static void dsi_pll_14nm_disable_seq(struct msm_dsi_pll *pll) -{ - struct dsi_pll_14nm *pll_14nm = to_pll_14nm(pll); - void __iomem *cmn_base = pll_14nm->phy_cmn_mmio; - - DBG(""); - - pll_write(cmn_base + REG_DSI_14nm_PHY_CMN_PLL_CNTRL, 0); -} - -static void dsi_pll_14nm_save_state(struct msm_dsi_pll *pll) -{ - struct dsi_pll_14nm *pll_14nm = to_pll_14nm(pll); - struct pll_14nm_cached_state *cached_state = &pll_14nm->cached_state; - void __iomem *cmn_base = pll_14nm->phy_cmn_mmio; - u32 data; - - data = pll_read(cmn_base + REG_DSI_14nm_PHY_CMN_CLK_CFG0); - - cached_state->n1postdiv = data & 0xf; - cached_state->n2postdiv = (data >> 4) & 0xf; - - DBG("DSI%d PLL save state %x %x", pll_14nm->id, - cached_state->n1postdiv, cached_state->n2postdiv); - - cached_state->vco_rate = clk_hw_get_rate(&pll->clk_hw); -} - -static int dsi_pll_14nm_restore_state(struct msm_dsi_pll *pll) -{ - struct dsi_pll_14nm *pll_14nm = to_pll_14nm(pll); - struct pll_14nm_cached_state *cached_state = &pll_14nm->cached_state; - void __iomem *cmn_base = pll_14nm->phy_cmn_mmio; - u32 data; - int ret; - - ret = dsi_pll_14nm_vco_set_rate(&pll->clk_hw, - cached_state->vco_rate, 0); - if (ret) { - DRM_DEV_ERROR(&pll_14nm->pdev->dev, - "restore vco rate failed. ret=%d\n", ret); - return ret; - } - - data = cached_state->n1postdiv | (cached_state->n2postdiv << 4); - - DBG("DSI%d PLL restore state %x %x", pll_14nm->id, - cached_state->n1postdiv, cached_state->n2postdiv); - - pll_write(cmn_base + REG_DSI_14nm_PHY_CMN_CLK_CFG0, data); - - /* also restore post-dividers for slave DSI PLL */ - if (pll_14nm->uc == MSM_DSI_PHY_MASTER) { - struct dsi_pll_14nm *pll_14nm_slave = pll_14nm->slave; - void __iomem *slave_base = pll_14nm_slave->phy_cmn_mmio; - - pll_write(slave_base + REG_DSI_14nm_PHY_CMN_CLK_CFG0, data); - } - - return 0; -} - -static int dsi_pll_14nm_set_usecase(struct msm_dsi_pll *pll, - enum msm_dsi_phy_usecase uc) -{ - struct dsi_pll_14nm *pll_14nm = to_pll_14nm(pll); - void __iomem *base = pll_14nm->mmio; - u32 clkbuflr_en, bandgap = 0; - - switch (uc) { - case MSM_DSI_PHY_STANDALONE: - clkbuflr_en = 0x1; - break; - case MSM_DSI_PHY_MASTER: - clkbuflr_en = 0x3; - pll_14nm->slave = pll_14nm_list[(pll_14nm->id + 1) % DSI_MAX]; - break; - case MSM_DSI_PHY_SLAVE: - clkbuflr_en = 0x0; - bandgap = 0x3; - break; - default: - return -EINVAL; - } - - pll_write(base + REG_DSI_14nm_PHY_PLL_CLKBUFLR_EN, clkbuflr_en); - if (bandgap) - pll_write(base + REG_DSI_14nm_PHY_PLL_PLL_BANDGAP, bandgap); - - pll_14nm->uc = uc; - - return 0; -} - -static int dsi_pll_14nm_get_provider(struct msm_dsi_pll *pll, - struct clk **byte_clk_provider, - struct clk **pixel_clk_provider) -{ - struct dsi_pll_14nm *pll_14nm = to_pll_14nm(pll); - struct clk_hw_onecell_data *hw_data = pll_14nm->hw_data; - - if (byte_clk_provider) - *byte_clk_provider = hw_data->hws[DSI_BYTE_PLL_CLK]->clk; - if (pixel_clk_provider) - *pixel_clk_provider = hw_data->hws[DSI_PIXEL_PLL_CLK]->clk; - - return 0; -} - -static void dsi_pll_14nm_destroy(struct msm_dsi_pll *pll) -{ - struct dsi_pll_14nm *pll_14nm = to_pll_14nm(pll); - struct platform_device *pdev = pll_14nm->pdev; - int num_hws = pll_14nm->num_hws; - - of_clk_del_provider(pdev->dev.of_node); - - while (num_hws--) - clk_hw_unregister(pll_14nm->hws[num_hws]); -} - -static struct clk_hw *pll_14nm_postdiv_register(struct dsi_pll_14nm *pll_14nm, - const char *name, - const char *parent_name, - unsigned long flags, - u8 shift) -{ - struct dsi_pll_14nm_postdiv *pll_postdiv; - struct device *dev = &pll_14nm->pdev->dev; - struct clk_init_data postdiv_init = { - .parent_names = (const char *[]) { parent_name }, - .num_parents = 1, - .name = name, - .flags = flags, - .ops = &clk_ops_dsi_pll_14nm_postdiv, - }; - int ret; - - pll_postdiv = devm_kzalloc(dev, sizeof(*pll_postdiv), GFP_KERNEL); - if (!pll_postdiv) - return ERR_PTR(-ENOMEM); - - pll_postdiv->pll = pll_14nm; - pll_postdiv->shift = shift; - /* both N1 and N2 postdividers are 4 bits wide */ - pll_postdiv->width = 4; - /* range of each divider is from 1 to 15 */ - pll_postdiv->flags = CLK_DIVIDER_ONE_BASED; - pll_postdiv->hw.init = &postdiv_init; - - ret = clk_hw_register(dev, &pll_postdiv->hw); - if (ret) - return ERR_PTR(ret); - - return &pll_postdiv->hw; -} - -static int pll_14nm_register(struct dsi_pll_14nm *pll_14nm) -{ - char clk_name[32], parent[32], vco_name[32]; - struct clk_init_data vco_init = { - .parent_names = (const char *[]){ "xo" }, - .num_parents = 1, - .name = vco_name, - .flags = CLK_IGNORE_UNUSED, - .ops = &clk_ops_dsi_pll_14nm_vco, - }; - struct device *dev = &pll_14nm->pdev->dev; - struct clk_hw **hws = pll_14nm->hws; - struct clk_hw_onecell_data *hw_data; - struct clk_hw *hw; - int num = 0; - int ret; - - DBG("DSI%d", pll_14nm->id); - - hw_data = devm_kzalloc(dev, sizeof(*hw_data) + - NUM_PROVIDED_CLKS * sizeof(struct clk_hw *), - GFP_KERNEL); - if (!hw_data) - return -ENOMEM; - - snprintf(vco_name, 32, "dsi%dvco_clk", pll_14nm->id); - pll_14nm->base.clk_hw.init = &vco_init; - - ret = clk_hw_register(dev, &pll_14nm->base.clk_hw); - if (ret) - return ret; - - hws[num++] = &pll_14nm->base.clk_hw; - - snprintf(clk_name, 32, "dsi%dn1_postdiv_clk", pll_14nm->id); - snprintf(parent, 32, "dsi%dvco_clk", pll_14nm->id); - - /* N1 postdiv, bits 0-3 in REG_DSI_14nm_PHY_CMN_CLK_CFG0 */ - hw = pll_14nm_postdiv_register(pll_14nm, clk_name, parent, - CLK_SET_RATE_PARENT, 0); - if (IS_ERR(hw)) - return PTR_ERR(hw); - - hws[num++] = hw; - - snprintf(clk_name, 32, "dsi%dpllbyte", pll_14nm->id); - snprintf(parent, 32, "dsi%dn1_postdiv_clk", pll_14nm->id); - - /* DSI Byte clock = VCO_CLK / N1 / 8 */ - hw = clk_hw_register_fixed_factor(dev, clk_name, parent, - CLK_SET_RATE_PARENT, 1, 8); - if (IS_ERR(hw)) - return PTR_ERR(hw); - - hws[num++] = hw; - hw_data->hws[DSI_BYTE_PLL_CLK] = hw; - - snprintf(clk_name, 32, "dsi%dn1_postdivby2_clk", pll_14nm->id); - snprintf(parent, 32, "dsi%dn1_postdiv_clk", pll_14nm->id); - - /* - * Skip the mux for now, force DSICLK_SEL to 1, Add a /2 divider - * on the way. Don't let it set parent. - */ - hw = clk_hw_register_fixed_factor(dev, clk_name, parent, 0, 1, 2); - if (IS_ERR(hw)) - return PTR_ERR(hw); - - hws[num++] = hw; - - snprintf(clk_name, 32, "dsi%dpll", pll_14nm->id); - snprintf(parent, 32, "dsi%dn1_postdivby2_clk", pll_14nm->id); - - /* DSI pixel clock = VCO_CLK / N1 / 2 / N2 - * This is the output of N2 post-divider, bits 4-7 in - * REG_DSI_14nm_PHY_CMN_CLK_CFG0. Don't let it set parent. - */ - hw = pll_14nm_postdiv_register(pll_14nm, clk_name, parent, 0, 4); - if (IS_ERR(hw)) - return PTR_ERR(hw); - - hws[num++] = hw; - hw_data->hws[DSI_PIXEL_PLL_CLK] = hw; - - pll_14nm->num_hws = num; - - hw_data->num = NUM_PROVIDED_CLKS; - pll_14nm->hw_data = hw_data; - - ret = of_clk_add_hw_provider(dev->of_node, of_clk_hw_onecell_get, - pll_14nm->hw_data); - if (ret) { - DRM_DEV_ERROR(dev, "failed to register clk provider: %d\n", ret); - return ret; - } - - return 0; -} - -struct msm_dsi_pll *msm_dsi_pll_14nm_init(struct platform_device *pdev, int id) -{ - struct dsi_pll_14nm *pll_14nm; - struct msm_dsi_pll *pll; - int ret; - - if (!pdev) - return ERR_PTR(-ENODEV); - - pll_14nm = devm_kzalloc(&pdev->dev, sizeof(*pll_14nm), GFP_KERNEL); - if (!pll_14nm) - return ERR_PTR(-ENOMEM); - - DBG("PLL%d", id); - - pll_14nm->pdev = pdev; - pll_14nm->id = id; - pll_14nm_list[id] = pll_14nm; - - pll_14nm->phy_cmn_mmio = msm_ioremap(pdev, "dsi_phy", "DSI_PHY"); - if (IS_ERR_OR_NULL(pll_14nm->phy_cmn_mmio)) { - DRM_DEV_ERROR(&pdev->dev, "failed to map CMN PHY base\n"); - return ERR_PTR(-ENOMEM); - } - - pll_14nm->mmio = msm_ioremap(pdev, "dsi_pll", "DSI_PLL"); - if (IS_ERR_OR_NULL(pll_14nm->mmio)) { - DRM_DEV_ERROR(&pdev->dev, "failed to map PLL base\n"); - return ERR_PTR(-ENOMEM); - } - - spin_lock_init(&pll_14nm->postdiv_lock); - - pll = &pll_14nm->base; - pll->min_rate = VCO_MIN_RATE; - pll->max_rate = VCO_MAX_RATE; - pll->get_provider = dsi_pll_14nm_get_provider; - pll->destroy = dsi_pll_14nm_destroy; - pll->disable_seq = dsi_pll_14nm_disable_seq; - pll->save_state = dsi_pll_14nm_save_state; - pll->restore_state = dsi_pll_14nm_restore_state; - pll->set_usecase = dsi_pll_14nm_set_usecase; - - pll_14nm->vco_delay = 1; - - pll->en_seq_cnt = 1; - pll->enable_seqs[0] = dsi_pll_14nm_enable_seq; - - ret = pll_14nm_register(pll_14nm); - if (ret) { - DRM_DEV_ERROR(&pdev->dev, "failed to register PLL: %d\n", ret); - return ERR_PTR(ret); - } - - return pll; -} diff --git a/drivers/gpu/drm/msm/dsi/pll/dsi_pll_28nm.c b/drivers/gpu/drm/msm/dsi/pll/dsi_pll_28nm.c deleted file mode 100644 index 37a1f996a588..000000000000 --- a/drivers/gpu/drm/msm/dsi/pll/dsi_pll_28nm.c +++ /dev/null @@ -1,643 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Copyright (c) 2012-2015, The Linux Foundation. All rights reserved. - */ - -#include <linux/clk.h> -#include <linux/clk-provider.h> - -#include "dsi_pll.h" -#include "dsi.xml.h" - -/* - * DSI PLL 28nm - clock diagram (eg: DSI0): - * - * dsi0analog_postdiv_clk - * | dsi0indirect_path_div2_clk - * | | - * +------+ | +----+ | |\ dsi0byte_mux - * dsi0vco_clk --o--| DIV1 |--o--| /2 |--o--| \ | - * | +------+ +----+ | m| | +----+ - * | | u|--o--| /4 |-- dsi0pllbyte - * | | x| +----+ - * o--------------------------| / - * | |/ - * | +------+ - * o----------| DIV3 |------------------------- dsi0pll - * +------+ - */ - -#define POLL_MAX_READS 10 -#define POLL_TIMEOUT_US 50 - -#define NUM_PROVIDED_CLKS 2 - -#define VCO_REF_CLK_RATE 19200000 -#define VCO_MIN_RATE 350000000 -#define VCO_MAX_RATE 750000000 - -#define DSI_BYTE_PLL_CLK 0 -#define DSI_PIXEL_PLL_CLK 1 - -#define LPFR_LUT_SIZE 10 -struct lpfr_cfg { - unsigned long vco_rate; - u32 resistance; -}; - -/* Loop filter resistance: */ -static const struct lpfr_cfg lpfr_lut[LPFR_LUT_SIZE] = { - { 479500000, 8 }, - { 480000000, 11 }, - { 575500000, 8 }, - { 576000000, 12 }, - { 610500000, 8 }, - { 659500000, 9 }, - { 671500000, 10 }, - { 672000000, 14 }, - { 708500000, 10 }, - { 750000000, 11 }, -}; - -struct pll_28nm_cached_state { - unsigned long vco_rate; - u8 postdiv3; - u8 postdiv1; - u8 byte_mux; -}; - -struct dsi_pll_28nm { - struct msm_dsi_pll base; - - int id; - struct platform_device *pdev; - void __iomem *mmio; - - int vco_delay; - - /* private clocks: */ - struct clk *clks[NUM_DSI_CLOCKS_MAX]; - u32 num_clks; - - /* clock-provider: */ - struct clk *provided_clks[NUM_PROVIDED_CLKS]; - struct clk_onecell_data clk_data; - - struct pll_28nm_cached_state cached_state; -}; - -#define to_pll_28nm(x) container_of(x, struct dsi_pll_28nm, base) - -static bool pll_28nm_poll_for_ready(struct dsi_pll_28nm *pll_28nm, - u32 nb_tries, u32 timeout_us) -{ - bool pll_locked = false; - u32 val; - - while (nb_tries--) { - val = pll_read(pll_28nm->mmio + REG_DSI_28nm_PHY_PLL_STATUS); - pll_locked = !!(val & DSI_28nm_PHY_PLL_STATUS_PLL_RDY); - - if (pll_locked) - break; - - udelay(timeout_us); - } - DBG("DSI PLL is %slocked", pll_locked ? "" : "*not* "); - - return pll_locked; -} - -static void pll_28nm_software_reset(struct dsi_pll_28nm *pll_28nm) -{ - void __iomem *base = pll_28nm->mmio; - - /* - * Add HW recommended delays after toggling the software - * reset bit off and back on. - */ - pll_write_udelay(base + REG_DSI_28nm_PHY_PLL_TEST_CFG, - DSI_28nm_PHY_PLL_TEST_CFG_PLL_SW_RESET, 1); - pll_write_udelay(base + REG_DSI_28nm_PHY_PLL_TEST_CFG, 0x00, 1); -} - -/* - * Clock Callbacks - */ -static int dsi_pll_28nm_clk_set_rate(struct clk_hw *hw, unsigned long rate, - unsigned long parent_rate) -{ - struct msm_dsi_pll *pll = hw_clk_to_pll(hw); - struct dsi_pll_28nm *pll_28nm = to_pll_28nm(pll); - struct device *dev = &pll_28nm->pdev->dev; - void __iomem *base = pll_28nm->mmio; - unsigned long div_fbx1000, gen_vco_clk; - u32 refclk_cfg, frac_n_mode, frac_n_value; - u32 sdm_cfg0, sdm_cfg1, sdm_cfg2, sdm_cfg3; - u32 cal_cfg10, cal_cfg11; - u32 rem; - int i; - - VERB("rate=%lu, parent's=%lu", rate, parent_rate); - - /* Force postdiv2 to be div-4 */ - pll_write(base + REG_DSI_28nm_PHY_PLL_POSTDIV2_CFG, 3); - - /* Configure the Loop filter resistance */ - for (i = 0; i < LPFR_LUT_SIZE; i++) - if (rate <= lpfr_lut[i].vco_rate) - break; - if (i == LPFR_LUT_SIZE) { - DRM_DEV_ERROR(dev, "unable to get loop filter resistance. vco=%lu\n", - rate); - return -EINVAL; - } - pll_write(base + REG_DSI_28nm_PHY_PLL_LPFR_CFG, lpfr_lut[i].resistance); - - /* Loop filter capacitance values : c1 and c2 */ - pll_write(base + REG_DSI_28nm_PHY_PLL_LPFC1_CFG, 0x70); - pll_write(base + REG_DSI_28nm_PHY_PLL_LPFC2_CFG, 0x15); - - rem = rate % VCO_REF_CLK_RATE; - if (rem) { - refclk_cfg = DSI_28nm_PHY_PLL_REFCLK_CFG_DBLR; - frac_n_mode = 1; - div_fbx1000 = rate / (VCO_REF_CLK_RATE / 500); - gen_vco_clk = div_fbx1000 * (VCO_REF_CLK_RATE / 500); - } else { - refclk_cfg = 0x0; - frac_n_mode = 0; - div_fbx1000 = rate / (VCO_REF_CLK_RATE / 1000); - gen_vco_clk = div_fbx1000 * (VCO_REF_CLK_RATE / 1000); - } - - DBG("refclk_cfg = %d", refclk_cfg); - - rem = div_fbx1000 % 1000; - frac_n_value = (rem << 16) / 1000; - - DBG("div_fb = %lu", div_fbx1000); - DBG("frac_n_value = %d", frac_n_value); - - DBG("Generated VCO Clock: %lu", gen_vco_clk); - rem = 0; - sdm_cfg1 = pll_read(base + REG_DSI_28nm_PHY_PLL_SDM_CFG1); - sdm_cfg1 &= ~DSI_28nm_PHY_PLL_SDM_CFG1_DC_OFFSET__MASK; - if (frac_n_mode) { - sdm_cfg0 = 0x0; - sdm_cfg0 |= DSI_28nm_PHY_PLL_SDM_CFG0_BYP_DIV(0); - sdm_cfg1 |= DSI_28nm_PHY_PLL_SDM_CFG1_DC_OFFSET( - (u32)(((div_fbx1000 / 1000) & 0x3f) - 1)); - sdm_cfg3 = frac_n_value >> 8; - sdm_cfg2 = frac_n_value & 0xff; - } else { - sdm_cfg0 = DSI_28nm_PHY_PLL_SDM_CFG0_BYP; - sdm_cfg0 |= DSI_28nm_PHY_PLL_SDM_CFG0_BYP_DIV( - (u32)(((div_fbx1000 / 1000) & 0x3f) - 1)); - sdm_cfg1 |= DSI_28nm_PHY_PLL_SDM_CFG1_DC_OFFSET(0); - sdm_cfg2 = 0; - sdm_cfg3 = 0; - } - - DBG("sdm_cfg0=%d", sdm_cfg0); - DBG("sdm_cfg1=%d", sdm_cfg1); - DBG("sdm_cfg2=%d", sdm_cfg2); - DBG("sdm_cfg3=%d", sdm_cfg3); - - cal_cfg11 = (u32)(gen_vco_clk / (256 * 1000000)); - cal_cfg10 = (u32)((gen_vco_clk % (256 * 1000000)) / 1000000); - DBG("cal_cfg10=%d, cal_cfg11=%d", cal_cfg10, cal_cfg11); - - pll_write(base + REG_DSI_28nm_PHY_PLL_CHGPUMP_CFG, 0x02); - pll_write(base + REG_DSI_28nm_PHY_PLL_CAL_CFG3, 0x2b); - pll_write(base + REG_DSI_28nm_PHY_PLL_CAL_CFG4, 0x06); - pll_write(base + REG_DSI_28nm_PHY_PLL_LKDET_CFG2, 0x0d); - - pll_write(base + REG_DSI_28nm_PHY_PLL_SDM_CFG1, sdm_cfg1); - pll_write(base + REG_DSI_28nm_PHY_PLL_SDM_CFG2, - DSI_28nm_PHY_PLL_SDM_CFG2_FREQ_SEED_7_0(sdm_cfg2)); - pll_write(base + REG_DSI_28nm_PHY_PLL_SDM_CFG3, - DSI_28nm_PHY_PLL_SDM_CFG3_FREQ_SEED_15_8(sdm_cfg3)); - pll_write(base + REG_DSI_28nm_PHY_PLL_SDM_CFG4, 0x00); - - /* Add hardware recommended delay for correct PLL configuration */ - if (pll_28nm->vco_delay) - udelay(pll_28nm->vco_delay); - - pll_write(base + REG_DSI_28nm_PHY_PLL_REFCLK_CFG, refclk_cfg); - pll_write(base + REG_DSI_28nm_PHY_PLL_PWRGEN_CFG, 0x00); - pll_write(base + REG_DSI_28nm_PHY_PLL_VCOLPF_CFG, 0x31); - pll_write(base + REG_DSI_28nm_PHY_PLL_SDM_CFG0, sdm_cfg0); - pll_write(base + REG_DSI_28nm_PHY_PLL_CAL_CFG0, 0x12); - pll_write(base + REG_DSI_28nm_PHY_PLL_CAL_CFG6, 0x30); - pll_write(base + REG_DSI_28nm_PHY_PLL_CAL_CFG7, 0x00); - pll_write(base + REG_DSI_28nm_PHY_PLL_CAL_CFG8, 0x60); - pll_write(base + REG_DSI_28nm_PHY_PLL_CAL_CFG9, 0x00); - pll_write(base + REG_DSI_28nm_PHY_PLL_CAL_CFG10, cal_cfg10 & 0xff); - pll_write(base + REG_DSI_28nm_PHY_PLL_CAL_CFG11, cal_cfg11 & 0xff); - pll_write(base + REG_DSI_28nm_PHY_PLL_EFUSE_CFG, 0x20); - - return 0; -} - -static int dsi_pll_28nm_clk_is_enabled(struct clk_hw *hw) -{ - struct msm_dsi_pll *pll = hw_clk_to_pll(hw); - struct dsi_pll_28nm *pll_28nm = to_pll_28nm(pll); - - return pll_28nm_poll_for_ready(pll_28nm, POLL_MAX_READS, - POLL_TIMEOUT_US); -} - -static unsigned long dsi_pll_28nm_clk_recalc_rate(struct clk_hw *hw, - unsigned long parent_rate) -{ - struct msm_dsi_pll *pll = hw_clk_to_pll(hw); - struct dsi_pll_28nm *pll_28nm = to_pll_28nm(pll); - void __iomem *base = pll_28nm->mmio; - u32 sdm0, doubler, sdm_byp_div; - u32 sdm_dc_off, sdm_freq_seed, sdm2, sdm3; - u32 ref_clk = VCO_REF_CLK_RATE; - unsigned long vco_rate; - - VERB("parent_rate=%lu", parent_rate); - - /* Check to see if the ref clk doubler is enabled */ - doubler = pll_read(base + REG_DSI_28nm_PHY_PLL_REFCLK_CFG) & - DSI_28nm_PHY_PLL_REFCLK_CFG_DBLR; - ref_clk += (doubler * VCO_REF_CLK_RATE); - - /* see if it is integer mode or sdm mode */ - sdm0 = pll_read(base + REG_DSI_28nm_PHY_PLL_SDM_CFG0); - if (sdm0 & DSI_28nm_PHY_PLL_SDM_CFG0_BYP) { - /* integer mode */ - sdm_byp_div = FIELD( - pll_read(base + REG_DSI_28nm_PHY_PLL_SDM_CFG0), - DSI_28nm_PHY_PLL_SDM_CFG0_BYP_DIV) + 1; - vco_rate = ref_clk * sdm_byp_div; - } else { - /* sdm mode */ - sdm_dc_off = FIELD( - pll_read(base + REG_DSI_28nm_PHY_PLL_SDM_CFG1), - DSI_28nm_PHY_PLL_SDM_CFG1_DC_OFFSET); - DBG("sdm_dc_off = %d", sdm_dc_off); - sdm2 = FIELD(pll_read(base + REG_DSI_28nm_PHY_PLL_SDM_CFG2), - DSI_28nm_PHY_PLL_SDM_CFG2_FREQ_SEED_7_0); - sdm3 = FIELD(pll_read(base + REG_DSI_28nm_PHY_PLL_SDM_CFG3), - DSI_28nm_PHY_PLL_SDM_CFG3_FREQ_SEED_15_8); - sdm_freq_seed = (sdm3 << 8) | sdm2; - DBG("sdm_freq_seed = %d", sdm_freq_seed); - - vco_rate = (ref_clk * (sdm_dc_off + 1)) + - mult_frac(ref_clk, sdm_freq_seed, BIT(16)); - DBG("vco rate = %lu", vco_rate); - } - - DBG("returning vco rate = %lu", vco_rate); - - return vco_rate; -} - -static const struct clk_ops clk_ops_dsi_pll_28nm_vco = { - .round_rate = msm_dsi_pll_helper_clk_round_rate, - .set_rate = dsi_pll_28nm_clk_set_rate, - .recalc_rate = dsi_pll_28nm_clk_recalc_rate, - .prepare = msm_dsi_pll_helper_clk_prepare, - .unprepare = msm_dsi_pll_helper_clk_unprepare, - .is_enabled = dsi_pll_28nm_clk_is_enabled, -}; - -/* - * PLL Callbacks - */ -static int dsi_pll_28nm_enable_seq_hpm(struct msm_dsi_pll *pll) -{ - struct dsi_pll_28nm *pll_28nm = to_pll_28nm(pll); - struct device *dev = &pll_28nm->pdev->dev; - void __iomem *base = pll_28nm->mmio; - u32 max_reads = 5, timeout_us = 100; - bool locked; - u32 val; - int i; - - DBG("id=%d", pll_28nm->id); - - pll_28nm_software_reset(pll_28nm); - - /* - * PLL power up sequence. - * Add necessary delays recommended by hardware. - */ - val = DSI_28nm_PHY_PLL_GLB_CFG_PLL_PWRDN_B; - pll_write_udelay(base + REG_DSI_28nm_PHY_PLL_GLB_CFG, val, 1); - - val |= DSI_28nm_PHY_PLL_GLB_CFG_PLL_PWRGEN_PWRDN_B; - pll_write_udelay(base + REG_DSI_28nm_PHY_PLL_GLB_CFG, val, 200); - - val |= DSI_28nm_PHY_PLL_GLB_CFG_PLL_LDO_PWRDN_B; - pll_write_udelay(base + REG_DSI_28nm_PHY_PLL_GLB_CFG, val, 500); - - val |= DSI_28nm_PHY_PLL_GLB_CFG_PLL_ENABLE; - pll_write_udelay(base + REG_DSI_28nm_PHY_PLL_GLB_CFG, val, 600); - - for (i = 0; i < 2; i++) { - /* DSI Uniphy lock detect setting */ - pll_write_udelay(base + REG_DSI_28nm_PHY_PLL_LKDET_CFG2, - 0x0c, 100); - pll_write(base + REG_DSI_28nm_PHY_PLL_LKDET_CFG2, 0x0d); - - /* poll for PLL ready status */ - locked = pll_28nm_poll_for_ready(pll_28nm, - max_reads, timeout_us); - if (locked) - break; - - pll_28nm_software_reset(pll_28nm); - - /* - * PLL power up sequence. - * Add necessary delays recommended by hardware. - */ - val = DSI_28nm_PHY_PLL_GLB_CFG_PLL_PWRDN_B; - pll_write_udelay(base + REG_DSI_28nm_PHY_PLL_GLB_CFG, val, 1); - - val |= DSI_28nm_PHY_PLL_GLB_CFG_PLL_PWRGEN_PWRDN_B; - pll_write_udelay(base + REG_DSI_28nm_PHY_PLL_GLB_CFG, val, 200); - - val |= DSI_28nm_PHY_PLL_GLB_CFG_PLL_LDO_PWRDN_B; - pll_write_udelay(base + REG_DSI_28nm_PHY_PLL_GLB_CFG, val, 250); - - val &= ~DSI_28nm_PHY_PLL_GLB_CFG_PLL_LDO_PWRDN_B; - pll_write_udelay(base + REG_DSI_28nm_PHY_PLL_GLB_CFG, val, 200); - - val |= DSI_28nm_PHY_PLL_GLB_CFG_PLL_LDO_PWRDN_B; - pll_write_udelay(base + REG_DSI_28nm_PHY_PLL_GLB_CFG, val, 500); - - val |= DSI_28nm_PHY_PLL_GLB_CFG_PLL_ENABLE; - pll_write_udelay(base + REG_DSI_28nm_PHY_PLL_GLB_CFG, val, 600); - } - - if (unlikely(!locked)) - DRM_DEV_ERROR(dev, "DSI PLL lock failed\n"); - else - DBG("DSI PLL Lock success"); - - return locked ? 0 : -EINVAL; -} - -static int dsi_pll_28nm_enable_seq_lp(struct msm_dsi_pll *pll) -{ - struct dsi_pll_28nm *pll_28nm = to_pll_28nm(pll); - struct device *dev = &pll_28nm->pdev->dev; - void __iomem *base = pll_28nm->mmio; - bool locked; - u32 max_reads = 10, timeout_us = 50; - u32 val; - - DBG("id=%d", pll_28nm->id); - - pll_28nm_software_reset(pll_28nm); - - /* - * PLL power up sequence. - * Add necessary delays recommended by hardware. - */ - pll_write_ndelay(base + REG_DSI_28nm_PHY_PLL_CAL_CFG1, 0x34, 500); - - val = DSI_28nm_PHY_PLL_GLB_CFG_PLL_PWRDN_B; - pll_write_ndelay(base + REG_DSI_28nm_PHY_PLL_GLB_CFG, val, 500); - - val |= DSI_28nm_PHY_PLL_GLB_CFG_PLL_PWRGEN_PWRDN_B; - pll_write_ndelay(base + REG_DSI_28nm_PHY_PLL_GLB_CFG, val, 500); - - val |= DSI_28nm_PHY_PLL_GLB_CFG_PLL_LDO_PWRDN_B | - DSI_28nm_PHY_PLL_GLB_CFG_PLL_ENABLE; - pll_write_ndelay(base + REG_DSI_28nm_PHY_PLL_GLB_CFG, val, 500); - - /* DSI PLL toggle lock detect setting */ - pll_write_ndelay(base + REG_DSI_28nm_PHY_PLL_LKDET_CFG2, 0x04, 500); - pll_write_udelay(base + REG_DSI_28nm_PHY_PLL_LKDET_CFG2, 0x05, 512); - - locked = pll_28nm_poll_for_ready(pll_28nm, max_reads, timeout_us); - - if (unlikely(!locked)) - DRM_DEV_ERROR(dev, "DSI PLL lock failed\n"); - else - DBG("DSI PLL lock success"); - - return locked ? 0 : -EINVAL; -} - -static void dsi_pll_28nm_disable_seq(struct msm_dsi_pll *pll) -{ - struct dsi_pll_28nm *pll_28nm = to_pll_28nm(pll); - - DBG("id=%d", pll_28nm->id); - pll_write(pll_28nm->mmio + REG_DSI_28nm_PHY_PLL_GLB_CFG, 0x00); -} - -static void dsi_pll_28nm_save_state(struct msm_dsi_pll *pll) -{ - struct dsi_pll_28nm *pll_28nm = to_pll_28nm(pll); - struct pll_28nm_cached_state *cached_state = &pll_28nm->cached_state; - void __iomem *base = pll_28nm->mmio; - - cached_state->postdiv3 = - pll_read(base + REG_DSI_28nm_PHY_PLL_POSTDIV3_CFG); - cached_state->postdiv1 = - pll_read(base + REG_DSI_28nm_PHY_PLL_POSTDIV1_CFG); - cached_state->byte_mux = pll_read(base + REG_DSI_28nm_PHY_PLL_VREG_CFG); - if (dsi_pll_28nm_clk_is_enabled(&pll->clk_hw)) - cached_state->vco_rate = clk_hw_get_rate(&pll->clk_hw); - else - cached_state->vco_rate = 0; -} - -static int dsi_pll_28nm_restore_state(struct msm_dsi_pll *pll) -{ - struct dsi_pll_28nm *pll_28nm = to_pll_28nm(pll); - struct pll_28nm_cached_state *cached_state = &pll_28nm->cached_state; - void __iomem *base = pll_28nm->mmio; - int ret; - - ret = dsi_pll_28nm_clk_set_rate(&pll->clk_hw, - cached_state->vco_rate, 0); - if (ret) { - DRM_DEV_ERROR(&pll_28nm->pdev->dev, - "restore vco rate failed. ret=%d\n", ret); - return ret; - } - - pll_write(base + REG_DSI_28nm_PHY_PLL_POSTDIV3_CFG, - cached_state->postdiv3); - pll_write(base + REG_DSI_28nm_PHY_PLL_POSTDIV1_CFG, - cached_state->postdiv1); - pll_write(base + REG_DSI_28nm_PHY_PLL_VREG_CFG, - cached_state->byte_mux); - - return 0; -} - -static int dsi_pll_28nm_get_provider(struct msm_dsi_pll *pll, - struct clk **byte_clk_provider, - struct clk **pixel_clk_provider) -{ - struct dsi_pll_28nm *pll_28nm = to_pll_28nm(pll); - - if (byte_clk_provider) - *byte_clk_provider = pll_28nm->provided_clks[DSI_BYTE_PLL_CLK]; - if (pixel_clk_provider) - *pixel_clk_provider = - pll_28nm->provided_clks[DSI_PIXEL_PLL_CLK]; - - return 0; -} - -static void dsi_pll_28nm_destroy(struct msm_dsi_pll *pll) -{ - struct dsi_pll_28nm *pll_28nm = to_pll_28nm(pll); - int i; - - msm_dsi_pll_helper_unregister_clks(pll_28nm->pdev, - pll_28nm->clks, pll_28nm->num_clks); - - for (i = 0; i < NUM_PROVIDED_CLKS; i++) - pll_28nm->provided_clks[i] = NULL; - - pll_28nm->num_clks = 0; - pll_28nm->clk_data.clks = NULL; - pll_28nm->clk_data.clk_num = 0; -} - -static int pll_28nm_register(struct dsi_pll_28nm *pll_28nm) -{ - char clk_name[32], parent1[32], parent2[32], vco_name[32]; - struct clk_init_data vco_init = { - .parent_names = (const char *[]){ "xo" }, - .num_parents = 1, - .name = vco_name, - .flags = CLK_IGNORE_UNUSED, - .ops = &clk_ops_dsi_pll_28nm_vco, - }; - struct device *dev = &pll_28nm->pdev->dev; - struct clk **clks = pll_28nm->clks; - struct clk **provided_clks = pll_28nm->provided_clks; - int num = 0; - int ret; - - DBG("%d", pll_28nm->id); - - snprintf(vco_name, 32, "dsi%dvco_clk", pll_28nm->id); - pll_28nm->base.clk_hw.init = &vco_init; - clks[num++] = clk_register(dev, &pll_28nm->base.clk_hw); - - snprintf(clk_name, 32, "dsi%danalog_postdiv_clk", pll_28nm->id); - snprintf(parent1, 32, "dsi%dvco_clk", pll_28nm->id); - clks[num++] = clk_register_divider(dev, clk_name, - parent1, CLK_SET_RATE_PARENT, - pll_28nm->mmio + - REG_DSI_28nm_PHY_PLL_POSTDIV1_CFG, - 0, 4, 0, NULL); - - snprintf(clk_name, 32, "dsi%dindirect_path_div2_clk", pll_28nm->id); - snprintf(parent1, 32, "dsi%danalog_postdiv_clk", pll_28nm->id); - clks[num++] = clk_register_fixed_factor(dev, clk_name, - parent1, CLK_SET_RATE_PARENT, - 1, 2); - - snprintf(clk_name, 32, "dsi%dpll", pll_28nm->id); - snprintf(parent1, 32, "dsi%dvco_clk", pll_28nm->id); - clks[num++] = provided_clks[DSI_PIXEL_PLL_CLK] = - clk_register_divider(dev, clk_name, - parent1, 0, pll_28nm->mmio + - REG_DSI_28nm_PHY_PLL_POSTDIV3_CFG, - 0, 8, 0, NULL); - - snprintf(clk_name, 32, "dsi%dbyte_mux", pll_28nm->id); - snprintf(parent1, 32, "dsi%dvco_clk", pll_28nm->id); - snprintf(parent2, 32, "dsi%dindirect_path_div2_clk", pll_28nm->id); - clks[num++] = clk_register_mux(dev, clk_name, - ((const char *[]){ - parent1, parent2 - }), 2, CLK_SET_RATE_PARENT, pll_28nm->mmio + - REG_DSI_28nm_PHY_PLL_VREG_CFG, 1, 1, 0, NULL); - - snprintf(clk_name, 32, "dsi%dpllbyte", pll_28nm->id); - snprintf(parent1, 32, "dsi%dbyte_mux", pll_28nm->id); - clks[num++] = provided_clks[DSI_BYTE_PLL_CLK] = - clk_register_fixed_factor(dev, clk_name, - parent1, CLK_SET_RATE_PARENT, 1, 4); - - pll_28nm->num_clks = num; - - pll_28nm->clk_data.clk_num = NUM_PROVIDED_CLKS; - pll_28nm->clk_data.clks = provided_clks; - - ret = of_clk_add_provider(dev->of_node, - of_clk_src_onecell_get, &pll_28nm->clk_data); - if (ret) { - DRM_DEV_ERROR(dev, "failed to register clk provider: %d\n", ret); - return ret; - } - - return 0; -} - -struct msm_dsi_pll *msm_dsi_pll_28nm_init(struct platform_device *pdev, - enum msm_dsi_phy_type type, int id) -{ - struct dsi_pll_28nm *pll_28nm; - struct msm_dsi_pll *pll; - int ret; - - if (!pdev) - return ERR_PTR(-ENODEV); - - pll_28nm = devm_kzalloc(&pdev->dev, sizeof(*pll_28nm), GFP_KERNEL); - if (!pll_28nm) - return ERR_PTR(-ENOMEM); - - pll_28nm->pdev = pdev; - pll_28nm->id = id; - - pll_28nm->mmio = msm_ioremap(pdev, "dsi_pll", "DSI_PLL"); - if (IS_ERR_OR_NULL(pll_28nm->mmio)) { - DRM_DEV_ERROR(&pdev->dev, "%s: failed to map pll base\n", __func__); - return ERR_PTR(-ENOMEM); - } - - pll = &pll_28nm->base; - pll->min_rate = VCO_MIN_RATE; - pll->max_rate = VCO_MAX_RATE; - pll->get_provider = dsi_pll_28nm_get_provider; - pll->destroy = dsi_pll_28nm_destroy; - pll->disable_seq = dsi_pll_28nm_disable_seq; - pll->save_state = dsi_pll_28nm_save_state; - pll->restore_state = dsi_pll_28nm_restore_state; - - if (type == MSM_DSI_PHY_28NM_HPM) { - pll_28nm->vco_delay = 1; - - pll->en_seq_cnt = 3; - pll->enable_seqs[0] = dsi_pll_28nm_enable_seq_hpm; - pll->enable_seqs[1] = dsi_pll_28nm_enable_seq_hpm; - pll->enable_seqs[2] = dsi_pll_28nm_enable_seq_hpm; - } else if (type == MSM_DSI_PHY_28NM_LP) { - pll_28nm->vco_delay = 1000; - - pll->en_seq_cnt = 1; - pll->enable_seqs[0] = dsi_pll_28nm_enable_seq_lp; - } else { - DRM_DEV_ERROR(&pdev->dev, "phy type (%d) is not 28nm\n", type); - return ERR_PTR(-EINVAL); - } - - ret = pll_28nm_register(pll_28nm); - if (ret) { - DRM_DEV_ERROR(&pdev->dev, "failed to register PLL: %d\n", ret); - return ERR_PTR(ret); - } - - return pll; -} - diff --git a/drivers/gpu/drm/msm/dsi/pll/dsi_pll_28nm_8960.c b/drivers/gpu/drm/msm/dsi/pll/dsi_pll_28nm_8960.c deleted file mode 100644 index a6e7a2525fe0..000000000000 --- a/drivers/gpu/drm/msm/dsi/pll/dsi_pll_28nm_8960.c +++ /dev/null @@ -1,526 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Copyright (c) 2012-2015, The Linux Foundation. All rights reserved. - */ - -#include <linux/clk-provider.h> - -#include "dsi_pll.h" -#include "dsi.xml.h" - -/* - * DSI PLL 28nm (8960/A family) - clock diagram (eg: DSI1): - * - * - * +------+ - * dsi1vco_clk ----o-----| DIV1 |---dsi1pllbit (not exposed as clock) - * F * byte_clk | +------+ - * | bit clock divider (F / 8) - * | - * | +------+ - * o-----| DIV2 |---dsi0pllbyte---o---> To byte RCG - * | +------+ | (sets parent rate) - * | byte clock divider (F) | - * | | - * | o---> To esc RCG - * | (doesn't set parent rate) - * | - * | +------+ - * o-----| DIV3 |----dsi0pll------o---> To dsi RCG - * +------+ | (sets parent rate) - * dsi clock divider (F * magic) | - * | - * o---> To pixel rcg - * (doesn't set parent rate) - */ - -#define POLL_MAX_READS 8000 -#define POLL_TIMEOUT_US 1 - -#define NUM_PROVIDED_CLKS 2 - -#define VCO_REF_CLK_RATE 27000000 -#define VCO_MIN_RATE 600000000 -#define VCO_MAX_RATE 1200000000 - -#define DSI_BYTE_PLL_CLK 0 -#define DSI_PIXEL_PLL_CLK 1 - -#define VCO_PREF_DIV_RATIO 27 - -struct pll_28nm_cached_state { - unsigned long vco_rate; - u8 postdiv3; - u8 postdiv2; - u8 postdiv1; -}; - -struct clk_bytediv { - struct clk_hw hw; - void __iomem *reg; -}; - -struct dsi_pll_28nm { - struct msm_dsi_pll base; - - int id; - struct platform_device *pdev; - void __iomem *mmio; - - /* custom byte clock divider */ - struct clk_bytediv *bytediv; - - /* private clocks: */ - struct clk *clks[NUM_DSI_CLOCKS_MAX]; - u32 num_clks; - - /* clock-provider: */ - struct clk *provided_clks[NUM_PROVIDED_CLKS]; - struct clk_onecell_data clk_data; - - struct pll_28nm_cached_state cached_state; -}; - -#define to_pll_28nm(x) container_of(x, struct dsi_pll_28nm, base) - -static bool pll_28nm_poll_for_ready(struct dsi_pll_28nm *pll_28nm, - int nb_tries, int timeout_us) -{ - bool pll_locked = false; - u32 val; - - while (nb_tries--) { - val = pll_read(pll_28nm->mmio + REG_DSI_28nm_8960_PHY_PLL_RDY); - pll_locked = !!(val & DSI_28nm_8960_PHY_PLL_RDY_PLL_RDY); - - if (pll_locked) - break; - - udelay(timeout_us); - } - DBG("DSI PLL is %slocked", pll_locked ? "" : "*not* "); - - return pll_locked; -} - -/* - * Clock Callbacks - */ -static int dsi_pll_28nm_clk_set_rate(struct clk_hw *hw, unsigned long rate, - unsigned long parent_rate) -{ - struct msm_dsi_pll *pll = hw_clk_to_pll(hw); - struct dsi_pll_28nm *pll_28nm = to_pll_28nm(pll); - void __iomem *base = pll_28nm->mmio; - u32 val, temp, fb_divider; - - DBG("rate=%lu, parent's=%lu", rate, parent_rate); - - temp = rate / 10; - val = VCO_REF_CLK_RATE / 10; - fb_divider = (temp * VCO_PREF_DIV_RATIO) / val; - fb_divider = fb_divider / 2 - 1; - pll_write(base + REG_DSI_28nm_8960_PHY_PLL_CTRL_1, - fb_divider & 0xff); - - val = pll_read(base + REG_DSI_28nm_8960_PHY_PLL_CTRL_2); - - val |= (fb_divider >> 8) & 0x07; - - pll_write(base + REG_DSI_28nm_8960_PHY_PLL_CTRL_2, - val); - - val = pll_read(base + REG_DSI_28nm_8960_PHY_PLL_CTRL_3); - - val |= (VCO_PREF_DIV_RATIO - 1) & 0x3f; - - pll_write(base + REG_DSI_28nm_8960_PHY_PLL_CTRL_3, - val); - - pll_write(base + REG_DSI_28nm_8960_PHY_PLL_CTRL_6, - 0xf); - - val = pll_read(base + REG_DSI_28nm_8960_PHY_PLL_CTRL_8); - val |= 0x7 << 4; - pll_write(base + REG_DSI_28nm_8960_PHY_PLL_CTRL_8, - val); - - return 0; -} - -static int dsi_pll_28nm_clk_is_enabled(struct clk_hw *hw) -{ - struct msm_dsi_pll *pll = hw_clk_to_pll(hw); - struct dsi_pll_28nm *pll_28nm = to_pll_28nm(pll); - - return pll_28nm_poll_for_ready(pll_28nm, POLL_MAX_READS, - POLL_TIMEOUT_US); -} - -static unsigned long dsi_pll_28nm_clk_recalc_rate(struct clk_hw *hw, - unsigned long parent_rate) -{ - struct msm_dsi_pll *pll = hw_clk_to_pll(hw); - struct dsi_pll_28nm *pll_28nm = to_pll_28nm(pll); - void __iomem *base = pll_28nm->mmio; - unsigned long vco_rate; - u32 status, fb_divider, temp, ref_divider; - - VERB("parent_rate=%lu", parent_rate); - - status = pll_read(base + REG_DSI_28nm_8960_PHY_PLL_CTRL_0); - - if (status & DSI_28nm_8960_PHY_PLL_CTRL_0_ENABLE) { - fb_divider = pll_read(base + REG_DSI_28nm_8960_PHY_PLL_CTRL_1); - fb_divider &= 0xff; - temp = pll_read(base + REG_DSI_28nm_8960_PHY_PLL_CTRL_2) & 0x07; - fb_divider = (temp << 8) | fb_divider; - fb_divider += 1; - - ref_divider = pll_read(base + REG_DSI_28nm_8960_PHY_PLL_CTRL_3); - ref_divider &= 0x3f; - ref_divider += 1; - - /* multiply by 2 */ - vco_rate = (parent_rate / ref_divider) * fb_divider * 2; - } else { - vco_rate = 0; - } - - DBG("returning vco rate = %lu", vco_rate); - - return vco_rate; -} - -static const struct clk_ops clk_ops_dsi_pll_28nm_vco = { - .round_rate = msm_dsi_pll_helper_clk_round_rate, - .set_rate = dsi_pll_28nm_clk_set_rate, - .recalc_rate = dsi_pll_28nm_clk_recalc_rate, - .prepare = msm_dsi_pll_helper_clk_prepare, - .unprepare = msm_dsi_pll_helper_clk_unprepare, - .is_enabled = dsi_pll_28nm_clk_is_enabled, -}; - -/* - * Custom byte clock divier clk_ops - * - * This clock is the entry point to configuring the PLL. The user (dsi host) - * will set this clock's rate to the desired byte clock rate. The VCO lock - * frequency is a multiple of the byte clock rate. The multiplication factor - * (shown as F in the diagram above) is a function of the byte clock rate. - * - * This custom divider clock ensures that its parent (VCO) is set to the - * desired rate, and that the byte clock postdivider (POSTDIV2) is configured - * accordingly - */ -#define to_clk_bytediv(_hw) container_of(_hw, struct clk_bytediv, hw) - -static unsigned long clk_bytediv_recalc_rate(struct clk_hw *hw, - unsigned long parent_rate) -{ - struct clk_bytediv *bytediv = to_clk_bytediv(hw); - unsigned int div; - - div = pll_read(bytediv->reg) & 0xff; - - return parent_rate / (div + 1); -} - -/* find multiplication factor(wrt byte clock) at which the VCO should be set */ -static unsigned int get_vco_mul_factor(unsigned long byte_clk_rate) -{ - unsigned long bit_mhz; - - /* convert to bit clock in Mhz */ - bit_mhz = (byte_clk_rate * 8) / 1000000; - - if (bit_mhz < 125) - return 64; - else if (bit_mhz < 250) - return 32; - else if (bit_mhz < 600) - return 16; - else - return 8; -} - -static long clk_bytediv_round_rate(struct clk_hw *hw, unsigned long rate, - unsigned long *prate) -{ - unsigned long best_parent; - unsigned int factor; - - factor = get_vco_mul_factor(rate); - - best_parent = rate * factor; - *prate = clk_hw_round_rate(clk_hw_get_parent(hw), best_parent); - - return *prate / factor; -} - -static int clk_bytediv_set_rate(struct clk_hw *hw, unsigned long rate, - unsigned long parent_rate) -{ - struct clk_bytediv *bytediv = to_clk_bytediv(hw); - u32 val; - unsigned int factor; - - factor = get_vco_mul_factor(rate); - - val = pll_read(bytediv->reg); - val |= (factor - 1) & 0xff; - pll_write(bytediv->reg, val); - - return 0; -} - -/* Our special byte clock divider ops */ -static const struct clk_ops clk_bytediv_ops = { - .round_rate = clk_bytediv_round_rate, - .set_rate = clk_bytediv_set_rate, - .recalc_rate = clk_bytediv_recalc_rate, -}; - -/* - * PLL Callbacks - */ -static int dsi_pll_28nm_enable_seq(struct msm_dsi_pll *pll) -{ - struct dsi_pll_28nm *pll_28nm = to_pll_28nm(pll); - struct device *dev = &pll_28nm->pdev->dev; - void __iomem *base = pll_28nm->mmio; - bool locked; - unsigned int bit_div, byte_div; - int max_reads = 1000, timeout_us = 100; - u32 val; - - DBG("id=%d", pll_28nm->id); - - /* - * before enabling the PLL, configure the bit clock divider since we - * don't expose it as a clock to the outside world - * 1: read back the byte clock divider that should already be set - * 2: divide by 8 to get bit clock divider - * 3: write it to POSTDIV1 - */ - val = pll_read(base + REG_DSI_28nm_8960_PHY_PLL_CTRL_9); - byte_div = val + 1; - bit_div = byte_div / 8; - - val = pll_read(base + REG_DSI_28nm_8960_PHY_PLL_CTRL_8); - val &= ~0xf; - val |= (bit_div - 1); - pll_write(base + REG_DSI_28nm_8960_PHY_PLL_CTRL_8, val); - - /* enable the PLL */ - pll_write(base + REG_DSI_28nm_8960_PHY_PLL_CTRL_0, - DSI_28nm_8960_PHY_PLL_CTRL_0_ENABLE); - - locked = pll_28nm_poll_for_ready(pll_28nm, max_reads, timeout_us); - - if (unlikely(!locked)) - DRM_DEV_ERROR(dev, "DSI PLL lock failed\n"); - else - DBG("DSI PLL lock success"); - - return locked ? 0 : -EINVAL; -} - -static void dsi_pll_28nm_disable_seq(struct msm_dsi_pll *pll) -{ - struct dsi_pll_28nm *pll_28nm = to_pll_28nm(pll); - - DBG("id=%d", pll_28nm->id); - pll_write(pll_28nm->mmio + REG_DSI_28nm_8960_PHY_PLL_CTRL_0, 0x00); -} - -static void dsi_pll_28nm_save_state(struct msm_dsi_pll *pll) -{ - struct dsi_pll_28nm *pll_28nm = to_pll_28nm(pll); - struct pll_28nm_cached_state *cached_state = &pll_28nm->cached_state; - void __iomem *base = pll_28nm->mmio; - - cached_state->postdiv3 = - pll_read(base + REG_DSI_28nm_8960_PHY_PLL_CTRL_10); - cached_state->postdiv2 = - pll_read(base + REG_DSI_28nm_8960_PHY_PLL_CTRL_9); - cached_state->postdiv1 = - pll_read(base + REG_DSI_28nm_8960_PHY_PLL_CTRL_8); - - cached_state->vco_rate = clk_hw_get_rate(&pll->clk_hw); -} - -static int dsi_pll_28nm_restore_state(struct msm_dsi_pll *pll) -{ - struct dsi_pll_28nm *pll_28nm = to_pll_28nm(pll); - struct pll_28nm_cached_state *cached_state = &pll_28nm->cached_state; - void __iomem *base = pll_28nm->mmio; - int ret; - - ret = dsi_pll_28nm_clk_set_rate(&pll->clk_hw, - cached_state->vco_rate, 0); - if (ret) { - DRM_DEV_ERROR(&pll_28nm->pdev->dev, - "restore vco rate failed. ret=%d\n", ret); - return ret; - } - - pll_write(base + REG_DSI_28nm_8960_PHY_PLL_CTRL_10, - cached_state->postdiv3); - pll_write(base + REG_DSI_28nm_8960_PHY_PLL_CTRL_9, - cached_state->postdiv2); - pll_write(base + REG_DSI_28nm_8960_PHY_PLL_CTRL_8, - cached_state->postdiv1); - - return 0; -} - -static int dsi_pll_28nm_get_provider(struct msm_dsi_pll *pll, - struct clk **byte_clk_provider, - struct clk **pixel_clk_provider) -{ - struct dsi_pll_28nm *pll_28nm = to_pll_28nm(pll); - - if (byte_clk_provider) - *byte_clk_provider = pll_28nm->provided_clks[DSI_BYTE_PLL_CLK]; - if (pixel_clk_provider) - *pixel_clk_provider = - pll_28nm->provided_clks[DSI_PIXEL_PLL_CLK]; - - return 0; -} - -static void dsi_pll_28nm_destroy(struct msm_dsi_pll *pll) -{ - struct dsi_pll_28nm *pll_28nm = to_pll_28nm(pll); - - msm_dsi_pll_helper_unregister_clks(pll_28nm->pdev, - pll_28nm->clks, pll_28nm->num_clks); -} - -static int pll_28nm_register(struct dsi_pll_28nm *pll_28nm) -{ - char *clk_name, *parent_name, *vco_name; - struct clk_init_data vco_init = { - .parent_names = (const char *[]){ "pxo" }, - .num_parents = 1, - .flags = CLK_IGNORE_UNUSED, - .ops = &clk_ops_dsi_pll_28nm_vco, - }; - struct device *dev = &pll_28nm->pdev->dev; - struct clk **clks = pll_28nm->clks; - struct clk **provided_clks = pll_28nm->provided_clks; - struct clk_bytediv *bytediv; - struct clk_init_data bytediv_init = { }; - int ret, num = 0; - - DBG("%d", pll_28nm->id); - - bytediv = devm_kzalloc(dev, sizeof(*bytediv), GFP_KERNEL); - if (!bytediv) - return -ENOMEM; - - vco_name = devm_kzalloc(dev, 32, GFP_KERNEL); - if (!vco_name) - return -ENOMEM; - - parent_name = devm_kzalloc(dev, 32, GFP_KERNEL); - if (!parent_name) - return -ENOMEM; - - clk_name = devm_kzalloc(dev, 32, GFP_KERNEL); - if (!clk_name) - return -ENOMEM; - - pll_28nm->bytediv = bytediv; - - snprintf(vco_name, 32, "dsi%dvco_clk", pll_28nm->id); - vco_init.name = vco_name; - - pll_28nm->base.clk_hw.init = &vco_init; - - clks[num++] = clk_register(dev, &pll_28nm->base.clk_hw); - - /* prepare and register bytediv */ - bytediv->hw.init = &bytediv_init; - bytediv->reg = pll_28nm->mmio + REG_DSI_28nm_8960_PHY_PLL_CTRL_9; - - snprintf(parent_name, 32, "dsi%dvco_clk", pll_28nm->id); - snprintf(clk_name, 32, "dsi%dpllbyte", pll_28nm->id); - - bytediv_init.name = clk_name; - bytediv_init.ops = &clk_bytediv_ops; - bytediv_init.flags = CLK_SET_RATE_PARENT; - bytediv_init.parent_names = (const char * const *) &parent_name; - bytediv_init.num_parents = 1; - - /* DIV2 */ - clks[num++] = provided_clks[DSI_BYTE_PLL_CLK] = - clk_register(dev, &bytediv->hw); - - snprintf(clk_name, 32, "dsi%dpll", pll_28nm->id); - /* DIV3 */ - clks[num++] = provided_clks[DSI_PIXEL_PLL_CLK] = - clk_register_divider(dev, clk_name, - parent_name, 0, pll_28nm->mmio + - REG_DSI_28nm_8960_PHY_PLL_CTRL_10, - 0, 8, 0, NULL); - - pll_28nm->num_clks = num; - - pll_28nm->clk_data.clk_num = NUM_PROVIDED_CLKS; - pll_28nm->clk_data.clks = provided_clks; - - ret = of_clk_add_provider(dev->of_node, - of_clk_src_onecell_get, &pll_28nm->clk_data); - if (ret) { - DRM_DEV_ERROR(dev, "failed to register clk provider: %d\n", ret); - return ret; - } - - return 0; -} - -struct msm_dsi_pll *msm_dsi_pll_28nm_8960_init(struct platform_device *pdev, - int id) -{ - struct dsi_pll_28nm *pll_28nm; - struct msm_dsi_pll *pll; - int ret; - - if (!pdev) - return ERR_PTR(-ENODEV); - - pll_28nm = devm_kzalloc(&pdev->dev, sizeof(*pll_28nm), GFP_KERNEL); - if (!pll_28nm) - return ERR_PTR(-ENOMEM); - - pll_28nm->pdev = pdev; - pll_28nm->id = id + 1; - - pll_28nm->mmio = msm_ioremap(pdev, "dsi_pll", "DSI_PLL"); - if (IS_ERR_OR_NULL(pll_28nm->mmio)) { - DRM_DEV_ERROR(&pdev->dev, "%s: failed to map pll base\n", __func__); - return ERR_PTR(-ENOMEM); - } - - pll = &pll_28nm->base; - pll->min_rate = VCO_MIN_RATE; - pll->max_rate = VCO_MAX_RATE; - pll->get_provider = dsi_pll_28nm_get_provider; - pll->destroy = dsi_pll_28nm_destroy; - pll->disable_seq = dsi_pll_28nm_disable_seq; - pll->save_state = dsi_pll_28nm_save_state; - pll->restore_state = dsi_pll_28nm_restore_state; - - pll->en_seq_cnt = 1; - pll->enable_seqs[0] = dsi_pll_28nm_enable_seq; - - ret = pll_28nm_register(pll_28nm); - if (ret) { - DRM_DEV_ERROR(&pdev->dev, "failed to register PLL: %d\n", ret); - return ERR_PTR(ret); - } - - return pll; -} diff --git a/drivers/gpu/drm/msm/dsi/pll/dsi_pll_7nm.c b/drivers/gpu/drm/msm/dsi/pll/dsi_pll_7nm.c deleted file mode 100644 index 93bf142e4a4e..000000000000 --- a/drivers/gpu/drm/msm/dsi/pll/dsi_pll_7nm.c +++ /dev/null @@ -1,912 +0,0 @@ -/* - * SPDX-License-Identifier: GPL-2.0 - * Copyright (c) 2018, The Linux Foundation - */ - -#include <linux/clk.h> -#include <linux/clk-provider.h> -#include <linux/iopoll.h> - -#include "dsi_pll.h" -#include "dsi.xml.h" - -/* - * DSI PLL 7nm - clock diagram (eg: DSI0): TODO: updated CPHY diagram - * - * dsi0_pll_out_div_clk dsi0_pll_bit_clk - * | | - * | | - * +---------+ | +----------+ | +----+ - * dsi0vco_clk ---| out_div |--o--| divl_3_0 |--o--| /8 |-- dsi0_phy_pll_out_byteclk - * +---------+ | +----------+ | +----+ - * | | - * | | dsi0_pll_by_2_bit_clk - * | | | - * | | +----+ | |\ dsi0_pclk_mux - * | |--| /2 |--o--| \ | - * | | +----+ | \ | +---------+ - * | --------------| |--o--| div_7_4 |-- dsi0_phy_pll_out_dsiclk - * |------------------------------| / +---------+ - * | +-----+ | / - * -----------| /4? |--o----------|/ - * +-----+ | | - * | |dsiclk_sel - * | - * dsi0_pll_post_out_div_clk - */ - -#define DSI_BYTE_PLL_CLK 0 -#define DSI_PIXEL_PLL_CLK 1 -#define NUM_PROVIDED_CLKS 2 - -#define VCO_REF_CLK_RATE 19200000 - -struct dsi_pll_regs { - u32 pll_prop_gain_rate; - u32 pll_lockdet_rate; - u32 decimal_div_start; - u32 frac_div_start_low; - u32 frac_div_start_mid; - u32 frac_div_start_high; - u32 pll_clock_inverters; - u32 ssc_stepsize_low; - u32 ssc_stepsize_high; - u32 ssc_div_per_low; - u32 ssc_div_per_high; - u32 ssc_adjper_low; - u32 ssc_adjper_high; - u32 ssc_control; -}; - -struct dsi_pll_config { - u32 ref_freq; - bool div_override; - u32 output_div; - bool ignore_frac; - bool disable_prescaler; - bool enable_ssc; - bool ssc_center; - u32 dec_bits; - u32 frac_bits; - u32 lock_timer; - u32 ssc_freq; - u32 ssc_offset; - u32 ssc_adj_per; - u32 thresh_cycles; - u32 refclk_cycles; -}; - -struct pll_7nm_cached_state { - unsigned long vco_rate; - u8 bit_clk_div; - u8 pix_clk_div; - u8 pll_out_div; - u8 pll_mux; -}; - -struct dsi_pll_7nm { - struct msm_dsi_pll base; - - int id; - struct platform_device *pdev; - - void __iomem *phy_cmn_mmio; - void __iomem *mmio; - - u64 vco_ref_clk_rate; - u64 vco_current_rate; - - /* protects REG_DSI_7nm_PHY_CMN_CLK_CFG0 register */ - spinlock_t postdiv_lock; - - int vco_delay; - struct dsi_pll_config pll_configuration; - struct dsi_pll_regs reg_setup; - - /* private clocks: */ - struct clk_hw *out_div_clk_hw; - struct clk_hw *bit_clk_hw; - struct clk_hw *byte_clk_hw; - struct clk_hw *by_2_bit_clk_hw; - struct clk_hw *post_out_div_clk_hw; - struct clk_hw *pclk_mux_hw; - struct clk_hw *out_dsiclk_hw; - - /* clock-provider: */ - struct clk_hw_onecell_data *hw_data; - - struct pll_7nm_cached_state cached_state; - - enum msm_dsi_phy_usecase uc; - struct dsi_pll_7nm *slave; -}; - -#define to_pll_7nm(x) container_of(x, struct dsi_pll_7nm, base) - -/* - * Global list of private DSI PLL struct pointers. We need this for Dual DSI - * mode, where the master PLL's clk_ops needs access the slave's private data - */ -static struct dsi_pll_7nm *pll_7nm_list[DSI_MAX]; - -static void dsi_pll_setup_config(struct dsi_pll_7nm *pll) -{ - struct dsi_pll_config *config = &pll->pll_configuration; - - config->ref_freq = pll->vco_ref_clk_rate; - config->output_div = 1; - config->dec_bits = 8; - config->frac_bits = 18; - config->lock_timer = 64; - config->ssc_freq = 31500; - config->ssc_offset = 4800; - config->ssc_adj_per = 2; - config->thresh_cycles = 32; - config->refclk_cycles = 256; - - config->div_override = false; - config->ignore_frac = false; - config->disable_prescaler = false; - - /* TODO: ssc enable */ - config->enable_ssc = false; - config->ssc_center = 0; -} - -static void dsi_pll_calc_dec_frac(struct dsi_pll_7nm *pll) -{ - struct dsi_pll_config *config = &pll->pll_configuration; - struct dsi_pll_regs *regs = &pll->reg_setup; - u64 fref = pll->vco_ref_clk_rate; - u64 pll_freq; - u64 divider; - u64 dec, dec_multiple; - u32 frac; - u64 multiplier; - - pll_freq = pll->vco_current_rate; - - if (config->disable_prescaler) - divider = fref; - else - divider = fref * 2; - - multiplier = 1 << config->frac_bits; - dec_multiple = div_u64(pll_freq * multiplier, divider); - div_u64_rem(dec_multiple, multiplier, &frac); - - dec = div_u64(dec_multiple, multiplier); - - if (pll->base.type != MSM_DSI_PHY_7NM_V4_1) - regs->pll_clock_inverters = 0x28; - else if (pll_freq <= 1000000000ULL) - regs->pll_clock_inverters = 0xa0; - else if (pll_freq <= 2500000000ULL) - regs->pll_clock_inverters = 0x20; - else if (pll_freq <= 3020000000ULL) - regs->pll_clock_inverters = 0x00; - else - regs->pll_clock_inverters = 0x40; - - regs->pll_lockdet_rate = config->lock_timer; - regs->decimal_div_start = dec; - regs->frac_div_start_low = (frac & 0xff); - regs->frac_div_start_mid = (frac & 0xff00) >> 8; - regs->frac_div_start_high = (frac & 0x30000) >> 16; -} - -#define SSC_CENTER BIT(0) -#define SSC_EN BIT(1) - -static void dsi_pll_calc_ssc(struct dsi_pll_7nm *pll) -{ - struct dsi_pll_config *config = &pll->pll_configuration; - struct dsi_pll_regs *regs = &pll->reg_setup; - u32 ssc_per; - u32 ssc_mod; - u64 ssc_step_size; - u64 frac; - - if (!config->enable_ssc) { - DBG("SSC not enabled\n"); - return; - } - - ssc_per = DIV_ROUND_CLOSEST(config->ref_freq, config->ssc_freq) / 2 - 1; - ssc_mod = (ssc_per + 1) % (config->ssc_adj_per + 1); - ssc_per -= ssc_mod; - - frac = regs->frac_div_start_low | - (regs->frac_div_start_mid << 8) | - (regs->frac_div_start_high << 16); - ssc_step_size = regs->decimal_div_start; - ssc_step_size *= (1 << config->frac_bits); - ssc_step_size += frac; - ssc_step_size *= config->ssc_offset; - ssc_step_size *= (config->ssc_adj_per + 1); - ssc_step_size = div_u64(ssc_step_size, (ssc_per + 1)); - ssc_step_size = DIV_ROUND_CLOSEST_ULL(ssc_step_size, 1000000); - - regs->ssc_div_per_low = ssc_per & 0xFF; - regs->ssc_div_per_high = (ssc_per & 0xFF00) >> 8; - regs->ssc_stepsize_low = (u32)(ssc_step_size & 0xFF); - regs->ssc_stepsize_high = (u32)((ssc_step_size & 0xFF00) >> 8); - regs->ssc_adjper_low = config->ssc_adj_per & 0xFF; - regs->ssc_adjper_high = (config->ssc_adj_per & 0xFF00) >> 8; - - regs->ssc_control = config->ssc_center ? SSC_CENTER : 0; - - pr_debug("SCC: Dec:%d, frac:%llu, frac_bits:%d\n", - regs->decimal_div_start, frac, config->frac_bits); - pr_debug("SSC: div_per:0x%X, stepsize:0x%X, adjper:0x%X\n", - ssc_per, (u32)ssc_step_size, config->ssc_adj_per); -} - -static void dsi_pll_ssc_commit(struct dsi_pll_7nm *pll) -{ - void __iomem *base = pll->mmio; - struct dsi_pll_regs *regs = &pll->reg_setup; - - if (pll->pll_configuration.enable_ssc) { - pr_debug("SSC is enabled\n"); - - pll_write(base + REG_DSI_7nm_PHY_PLL_SSC_STEPSIZE_LOW_1, - regs->ssc_stepsize_low); - pll_write(base + REG_DSI_7nm_PHY_PLL_SSC_STEPSIZE_HIGH_1, - regs->ssc_stepsize_high); - pll_write(base + REG_DSI_7nm_PHY_PLL_SSC_DIV_PER_LOW_1, - regs->ssc_div_per_low); - pll_write(base + REG_DSI_7nm_PHY_PLL_SSC_DIV_PER_HIGH_1, - regs->ssc_div_per_high); - pll_write(base + REG_DSI_7nm_PHY_PLL_SSC_ADJPER_LOW_1, - regs->ssc_adjper_low); - pll_write(base + REG_DSI_7nm_PHY_PLL_SSC_ADJPER_HIGH_1, - regs->ssc_adjper_high); - pll_write(base + REG_DSI_7nm_PHY_PLL_SSC_CONTROL, - SSC_EN | regs->ssc_control); - } -} - -static void dsi_pll_config_hzindep_reg(struct dsi_pll_7nm *pll) -{ - void __iomem *base = pll->mmio; - u8 analog_controls_five_1 = 0x01, vco_config_1 = 0x00; - - if (pll->base.type == MSM_DSI_PHY_7NM_V4_1) { - if (pll->vco_current_rate >= 3100000000ULL) - analog_controls_five_1 = 0x03; - - if (pll->vco_current_rate < 1520000000ULL) - vco_config_1 = 0x08; - else if (pll->vco_current_rate < 2990000000ULL) - vco_config_1 = 0x01; - } - - pll_write(base + REG_DSI_7nm_PHY_PLL_ANALOG_CONTROLS_FIVE_1, - analog_controls_five_1); - pll_write(base + REG_DSI_7nm_PHY_PLL_VCO_CONFIG_1, vco_config_1); - pll_write(base + REG_DSI_7nm_PHY_PLL_ANALOG_CONTROLS_FIVE, 0x01); - pll_write(base + REG_DSI_7nm_PHY_PLL_ANALOG_CONTROLS_TWO, 0x03); - pll_write(base + REG_DSI_7nm_PHY_PLL_ANALOG_CONTROLS_THREE, 0x00); - pll_write(base + REG_DSI_7nm_PHY_PLL_DSM_DIVIDER, 0x00); - pll_write(base + REG_DSI_7nm_PHY_PLL_FEEDBACK_DIVIDER, 0x4e); - pll_write(base + REG_DSI_7nm_PHY_PLL_CALIBRATION_SETTINGS, 0x40); - pll_write(base + REG_DSI_7nm_PHY_PLL_BAND_SEL_CAL_SETTINGS_THREE, 0xba); - pll_write(base + REG_DSI_7nm_PHY_PLL_FREQ_DETECT_SETTINGS_ONE, 0x0c); - pll_write(base + REG_DSI_7nm_PHY_PLL_OUTDIV, 0x00); - pll_write(base + REG_DSI_7nm_PHY_PLL_CORE_OVERRIDE, 0x00); - pll_write(base + REG_DSI_7nm_PHY_PLL_PLL_DIGITAL_TIMERS_TWO, 0x08); - pll_write(base + REG_DSI_7nm_PHY_PLL_PLL_PROP_GAIN_RATE_1, 0x0a); - pll_write(base + REG_DSI_7nm_PHY_PLL_PLL_BAND_SEL_RATE_1, 0xc0); - pll_write(base + REG_DSI_7nm_PHY_PLL_PLL_INT_GAIN_IFILT_BAND_1, 0x84); - pll_write(base + REG_DSI_7nm_PHY_PLL_PLL_INT_GAIN_IFILT_BAND_1, 0x82); - pll_write(base + REG_DSI_7nm_PHY_PLL_PLL_FL_INT_GAIN_PFILT_BAND_1, 0x4c); - pll_write(base + REG_DSI_7nm_PHY_PLL_PLL_LOCK_OVERRIDE, 0x80); - pll_write(base + REG_DSI_7nm_PHY_PLL_PFILT, 0x29); - pll_write(base + REG_DSI_7nm_PHY_PLL_PFILT, 0x2f); - pll_write(base + REG_DSI_7nm_PHY_PLL_IFILT, 0x2a); - pll_write(base + REG_DSI_7nm_PHY_PLL_IFILT, - pll->base.type == MSM_DSI_PHY_7NM_V4_1 ? 0x3f : 0x22); - - if (pll->base.type == MSM_DSI_PHY_7NM_V4_1) { - pll_write(base + REG_DSI_7nm_PHY_PLL_PERF_OPTIMIZE, 0x22); - if (pll->slave) - pll_write(pll->slave->mmio + REG_DSI_7nm_PHY_PLL_PERF_OPTIMIZE, 0x22); - } -} - -static void dsi_pll_commit(struct dsi_pll_7nm *pll) -{ - void __iomem *base = pll->mmio; - struct dsi_pll_regs *reg = &pll->reg_setup; - - pll_write(base + REG_DSI_7nm_PHY_PLL_CORE_INPUT_OVERRIDE, 0x12); - pll_write(base + REG_DSI_7nm_PHY_PLL_DECIMAL_DIV_START_1, reg->decimal_div_start); - pll_write(base + REG_DSI_7nm_PHY_PLL_FRAC_DIV_START_LOW_1, reg->frac_div_start_low); - pll_write(base + REG_DSI_7nm_PHY_PLL_FRAC_DIV_START_MID_1, reg->frac_div_start_mid); - pll_write(base + REG_DSI_7nm_PHY_PLL_FRAC_DIV_START_HIGH_1, reg->frac_div_start_high); - pll_write(base + REG_DSI_7nm_PHY_PLL_PLL_LOCKDET_RATE_1, 0x40); - pll_write(base + REG_DSI_7nm_PHY_PLL_PLL_LOCK_DELAY, 0x06); - pll_write(base + REG_DSI_7nm_PHY_PLL_CMODE_1, 0x10); /* TODO: 0x00 for CPHY */ - pll_write(base + REG_DSI_7nm_PHY_PLL_CLOCK_INVERTERS, reg->pll_clock_inverters); -} - -static int dsi_pll_7nm_vco_set_rate(struct clk_hw *hw, unsigned long rate, - unsigned long parent_rate) -{ - struct msm_dsi_pll *pll = hw_clk_to_pll(hw); - struct dsi_pll_7nm *pll_7nm = to_pll_7nm(pll); - - DBG("DSI PLL%d rate=%lu, parent's=%lu", pll_7nm->id, rate, - parent_rate); - - pll_7nm->vco_current_rate = rate; - pll_7nm->vco_ref_clk_rate = VCO_REF_CLK_RATE; - - dsi_pll_setup_config(pll_7nm); - - dsi_pll_calc_dec_frac(pll_7nm); - - dsi_pll_calc_ssc(pll_7nm); - - dsi_pll_commit(pll_7nm); - - dsi_pll_config_hzindep_reg(pll_7nm); - - dsi_pll_ssc_commit(pll_7nm); - - /* flush, ensure all register writes are done*/ - wmb(); - - return 0; -} - -static int dsi_pll_7nm_lock_status(struct dsi_pll_7nm *pll) -{ - int rc; - u32 status = 0; - u32 const delay_us = 100; - u32 const timeout_us = 5000; - - rc = readl_poll_timeout_atomic(pll->mmio + - REG_DSI_7nm_PHY_PLL_COMMON_STATUS_ONE, - status, - ((status & BIT(0)) > 0), - delay_us, - timeout_us); - if (rc) - pr_err("DSI PLL(%d) lock failed, status=0x%08x\n", - pll->id, status); - - return rc; -} - -static void dsi_pll_disable_pll_bias(struct dsi_pll_7nm *pll) -{ - u32 data = pll_read(pll->phy_cmn_mmio + REG_DSI_7nm_PHY_CMN_CTRL_0); - - pll_write(pll->mmio + REG_DSI_7nm_PHY_PLL_SYSTEM_MUXES, 0); - pll_write(pll->phy_cmn_mmio + REG_DSI_7nm_PHY_CMN_CTRL_0, data & ~BIT(5)); - ndelay(250); -} - -static void dsi_pll_enable_pll_bias(struct dsi_pll_7nm *pll) -{ - u32 data = pll_read(pll->phy_cmn_mmio + REG_DSI_7nm_PHY_CMN_CTRL_0); - - pll_write(pll->phy_cmn_mmio + REG_DSI_7nm_PHY_CMN_CTRL_0, data | BIT(5)); - pll_write(pll->mmio + REG_DSI_7nm_PHY_PLL_SYSTEM_MUXES, 0xc0); - ndelay(250); -} - -static void dsi_pll_disable_global_clk(struct dsi_pll_7nm *pll) -{ - u32 data; - - data = pll_read(pll->phy_cmn_mmio + REG_DSI_7nm_PHY_CMN_CLK_CFG1); - pll_write(pll->phy_cmn_mmio + REG_DSI_7nm_PHY_CMN_CLK_CFG1, data & ~BIT(5)); -} - -static void dsi_pll_enable_global_clk(struct dsi_pll_7nm *pll) -{ - u32 data; - - pll_write(pll->phy_cmn_mmio + REG_DSI_7nm_PHY_CMN_CTRL_3, 0x04); - - data = pll_read(pll->phy_cmn_mmio + REG_DSI_7nm_PHY_CMN_CLK_CFG1); - pll_write(pll->phy_cmn_mmio + REG_DSI_7nm_PHY_CMN_CLK_CFG1, - data | BIT(5) | BIT(4)); -} - -static void dsi_pll_phy_dig_reset(struct dsi_pll_7nm *pll) -{ - /* - * Reset the PHY digital domain. This would be needed when - * coming out of a CX or analog rail power collapse while - * ensuring that the pads maintain LP00 or LP11 state - */ - pll_write(pll->phy_cmn_mmio + REG_DSI_7nm_PHY_CMN_GLBL_DIGTOP_SPARE4, BIT(0)); - wmb(); /* Ensure that the reset is deasserted */ - pll_write(pll->phy_cmn_mmio + REG_DSI_7nm_PHY_CMN_GLBL_DIGTOP_SPARE4, 0x0); - wmb(); /* Ensure that the reset is deasserted */ -} - -static int dsi_pll_7nm_vco_prepare(struct clk_hw *hw) -{ - struct msm_dsi_pll *pll = hw_clk_to_pll(hw); - struct dsi_pll_7nm *pll_7nm = to_pll_7nm(pll); - int rc; - - dsi_pll_enable_pll_bias(pll_7nm); - if (pll_7nm->slave) - dsi_pll_enable_pll_bias(pll_7nm->slave); - - /* Start PLL */ - pll_write(pll_7nm->phy_cmn_mmio + REG_DSI_7nm_PHY_CMN_PLL_CNTRL, 0x01); - - /* - * ensure all PLL configurations are written prior to checking - * for PLL lock. - */ - wmb(); - - /* Check for PLL lock */ - rc = dsi_pll_7nm_lock_status(pll_7nm); - if (rc) { - pr_err("PLL(%d) lock failed\n", pll_7nm->id); - goto error; - } - - pll->pll_on = true; - - /* - * assert power on reset for PHY digital in case the PLL is - * enabled after CX of analog domain power collapse. This needs - * to be done before enabling the global clk. - */ - dsi_pll_phy_dig_reset(pll_7nm); - if (pll_7nm->slave) - dsi_pll_phy_dig_reset(pll_7nm->slave); - - dsi_pll_enable_global_clk(pll_7nm); - if (pll_7nm->slave) - dsi_pll_enable_global_clk(pll_7nm->slave); - -error: - return rc; -} - -static void dsi_pll_disable_sub(struct dsi_pll_7nm *pll) -{ - pll_write(pll->phy_cmn_mmio + REG_DSI_7nm_PHY_CMN_RBUF_CTRL, 0); - dsi_pll_disable_pll_bias(pll); -} - -static void dsi_pll_7nm_vco_unprepare(struct clk_hw *hw) -{ - struct msm_dsi_pll *pll = hw_clk_to_pll(hw); - struct dsi_pll_7nm *pll_7nm = to_pll_7nm(pll); - - /* - * To avoid any stray glitches while abruptly powering down the PLL - * make sure to gate the clock using the clock enable bit before - * powering down the PLL - */ - dsi_pll_disable_global_clk(pll_7nm); - pll_write(pll_7nm->phy_cmn_mmio + REG_DSI_7nm_PHY_CMN_PLL_CNTRL, 0); - dsi_pll_disable_sub(pll_7nm); - if (pll_7nm->slave) { - dsi_pll_disable_global_clk(pll_7nm->slave); - dsi_pll_disable_sub(pll_7nm->slave); - } - /* flush, ensure all register writes are done */ - wmb(); - pll->pll_on = false; -} - -static unsigned long dsi_pll_7nm_vco_recalc_rate(struct clk_hw *hw, - unsigned long parent_rate) -{ - struct msm_dsi_pll *pll = hw_clk_to_pll(hw); - struct dsi_pll_7nm *pll_7nm = to_pll_7nm(pll); - void __iomem *base = pll_7nm->mmio; - u64 ref_clk = pll_7nm->vco_ref_clk_rate; - u64 vco_rate = 0x0; - u64 multiplier; - u32 frac; - u32 dec; - u64 pll_freq, tmp64; - - dec = pll_read(base + REG_DSI_7nm_PHY_PLL_DECIMAL_DIV_START_1); - dec &= 0xff; - - frac = pll_read(base + REG_DSI_7nm_PHY_PLL_FRAC_DIV_START_LOW_1); - frac |= ((pll_read(base + REG_DSI_7nm_PHY_PLL_FRAC_DIV_START_MID_1) & - 0xff) << 8); - frac |= ((pll_read(base + REG_DSI_7nm_PHY_PLL_FRAC_DIV_START_HIGH_1) & - 0x3) << 16); - - /* - * TODO: - * 1. Assumes prescaler is disabled - * 2. Multiplier is 2^18. it should be 2^(num_of_frac_bits) - */ - multiplier = 1 << 18; - pll_freq = dec * (ref_clk * 2); - tmp64 = (ref_clk * 2 * frac); - pll_freq += div_u64(tmp64, multiplier); - - vco_rate = pll_freq; - - DBG("DSI PLL%d returning vco rate = %lu, dec = %x, frac = %x", - pll_7nm->id, (unsigned long)vco_rate, dec, frac); - - return (unsigned long)vco_rate; -} - -static const struct clk_ops clk_ops_dsi_pll_7nm_vco = { - .round_rate = msm_dsi_pll_helper_clk_round_rate, - .set_rate = dsi_pll_7nm_vco_set_rate, - .recalc_rate = dsi_pll_7nm_vco_recalc_rate, - .prepare = dsi_pll_7nm_vco_prepare, - .unprepare = dsi_pll_7nm_vco_unprepare, -}; - -/* - * PLL Callbacks - */ - -static void dsi_pll_7nm_save_state(struct msm_dsi_pll *pll) -{ - struct dsi_pll_7nm *pll_7nm = to_pll_7nm(pll); - struct pll_7nm_cached_state *cached = &pll_7nm->cached_state; - void __iomem *phy_base = pll_7nm->phy_cmn_mmio; - u32 cmn_clk_cfg0, cmn_clk_cfg1; - - cached->pll_out_div = pll_read(pll_7nm->mmio + - REG_DSI_7nm_PHY_PLL_PLL_OUTDIV_RATE); - cached->pll_out_div &= 0x3; - - cmn_clk_cfg0 = pll_read(phy_base + REG_DSI_7nm_PHY_CMN_CLK_CFG0); - cached->bit_clk_div = cmn_clk_cfg0 & 0xf; - cached->pix_clk_div = (cmn_clk_cfg0 & 0xf0) >> 4; - - cmn_clk_cfg1 = pll_read(phy_base + REG_DSI_7nm_PHY_CMN_CLK_CFG1); - cached->pll_mux = cmn_clk_cfg1 & 0x3; - - DBG("DSI PLL%d outdiv %x bit_clk_div %x pix_clk_div %x pll_mux %x", - pll_7nm->id, cached->pll_out_div, cached->bit_clk_div, - cached->pix_clk_div, cached->pll_mux); -} - -static int dsi_pll_7nm_restore_state(struct msm_dsi_pll *pll) -{ - struct dsi_pll_7nm *pll_7nm = to_pll_7nm(pll); - struct pll_7nm_cached_state *cached = &pll_7nm->cached_state; - void __iomem *phy_base = pll_7nm->phy_cmn_mmio; - u32 val; - int ret; - - val = pll_read(pll_7nm->mmio + REG_DSI_7nm_PHY_PLL_PLL_OUTDIV_RATE); - val &= ~0x3; - val |= cached->pll_out_div; - pll_write(pll_7nm->mmio + REG_DSI_7nm_PHY_PLL_PLL_OUTDIV_RATE, val); - - pll_write(phy_base + REG_DSI_7nm_PHY_CMN_CLK_CFG0, - cached->bit_clk_div | (cached->pix_clk_div << 4)); - - val = pll_read(phy_base + REG_DSI_7nm_PHY_CMN_CLK_CFG1); - val &= ~0x3; - val |= cached->pll_mux; - pll_write(phy_base + REG_DSI_7nm_PHY_CMN_CLK_CFG1, val); - - ret = dsi_pll_7nm_vco_set_rate(&pll->clk_hw, pll_7nm->vco_current_rate, pll_7nm->vco_ref_clk_rate); - if (ret) { - DRM_DEV_ERROR(&pll_7nm->pdev->dev, - "restore vco rate failed. ret=%d\n", ret); - return ret; - } - - DBG("DSI PLL%d", pll_7nm->id); - - return 0; -} - -static int dsi_pll_7nm_set_usecase(struct msm_dsi_pll *pll, - enum msm_dsi_phy_usecase uc) -{ - struct dsi_pll_7nm *pll_7nm = to_pll_7nm(pll); - void __iomem *base = pll_7nm->phy_cmn_mmio; - u32 data = 0x0; /* internal PLL */ - - DBG("DSI PLL%d", pll_7nm->id); - - switch (uc) { - case MSM_DSI_PHY_STANDALONE: - break; - case MSM_DSI_PHY_MASTER: - pll_7nm->slave = pll_7nm_list[(pll_7nm->id + 1) % DSI_MAX]; - break; - case MSM_DSI_PHY_SLAVE: - data = 0x1; /* external PLL */ - break; - default: - return -EINVAL; - } - - /* set PLL src */ - pll_write(base + REG_DSI_7nm_PHY_CMN_CLK_CFG1, (data << 2)); - - pll_7nm->uc = uc; - - return 0; -} - -static int dsi_pll_7nm_get_provider(struct msm_dsi_pll *pll, - struct clk **byte_clk_provider, - struct clk **pixel_clk_provider) -{ - struct dsi_pll_7nm *pll_7nm = to_pll_7nm(pll); - struct clk_hw_onecell_data *hw_data = pll_7nm->hw_data; - - DBG("DSI PLL%d", pll_7nm->id); - - if (byte_clk_provider) - *byte_clk_provider = hw_data->hws[DSI_BYTE_PLL_CLK]->clk; - if (pixel_clk_provider) - *pixel_clk_provider = hw_data->hws[DSI_PIXEL_PLL_CLK]->clk; - - return 0; -} - -static void dsi_pll_7nm_destroy(struct msm_dsi_pll *pll) -{ - struct dsi_pll_7nm *pll_7nm = to_pll_7nm(pll); - struct device *dev = &pll_7nm->pdev->dev; - - DBG("DSI PLL%d", pll_7nm->id); - of_clk_del_provider(dev->of_node); - - clk_hw_unregister_divider(pll_7nm->out_dsiclk_hw); - clk_hw_unregister_mux(pll_7nm->pclk_mux_hw); - clk_hw_unregister_fixed_factor(pll_7nm->post_out_div_clk_hw); - clk_hw_unregister_fixed_factor(pll_7nm->by_2_bit_clk_hw); - clk_hw_unregister_fixed_factor(pll_7nm->byte_clk_hw); - clk_hw_unregister_divider(pll_7nm->bit_clk_hw); - clk_hw_unregister_divider(pll_7nm->out_div_clk_hw); - clk_hw_unregister(&pll_7nm->base.clk_hw); -} - -/* - * The post dividers and mux clocks are created using the standard divider and - * mux API. Unlike the 14nm PHY, the slave PLL doesn't need its dividers/mux - * state to follow the master PLL's divider/mux state. Therefore, we don't - * require special clock ops that also configure the slave PLL registers - */ -static int pll_7nm_register(struct dsi_pll_7nm *pll_7nm) -{ - char clk_name[32], parent[32], vco_name[32]; - char parent2[32], parent3[32], parent4[32]; - struct clk_init_data vco_init = { - .parent_names = (const char *[]){ "bi_tcxo" }, - .num_parents = 1, - .name = vco_name, - .flags = CLK_IGNORE_UNUSED, - .ops = &clk_ops_dsi_pll_7nm_vco, - }; - struct device *dev = &pll_7nm->pdev->dev; - struct clk_hw_onecell_data *hw_data; - struct clk_hw *hw; - int ret; - - DBG("DSI%d", pll_7nm->id); - - hw_data = devm_kzalloc(dev, sizeof(*hw_data) + - NUM_PROVIDED_CLKS * sizeof(struct clk_hw *), - GFP_KERNEL); - if (!hw_data) - return -ENOMEM; - - snprintf(vco_name, 32, "dsi%dvco_clk", pll_7nm->id); - pll_7nm->base.clk_hw.init = &vco_init; - - ret = clk_hw_register(dev, &pll_7nm->base.clk_hw); - if (ret) - return ret; - - snprintf(clk_name, 32, "dsi%d_pll_out_div_clk", pll_7nm->id); - snprintf(parent, 32, "dsi%dvco_clk", pll_7nm->id); - - hw = clk_hw_register_divider(dev, clk_name, - parent, CLK_SET_RATE_PARENT, - pll_7nm->mmio + - REG_DSI_7nm_PHY_PLL_PLL_OUTDIV_RATE, - 0, 2, CLK_DIVIDER_POWER_OF_TWO, NULL); - if (IS_ERR(hw)) { - ret = PTR_ERR(hw); - goto err_base_clk_hw; - } - - pll_7nm->out_div_clk_hw = hw; - - snprintf(clk_name, 32, "dsi%d_pll_bit_clk", pll_7nm->id); - snprintf(parent, 32, "dsi%d_pll_out_div_clk", pll_7nm->id); - - /* BIT CLK: DIV_CTRL_3_0 */ - hw = clk_hw_register_divider(dev, clk_name, parent, - CLK_SET_RATE_PARENT, - pll_7nm->phy_cmn_mmio + - REG_DSI_7nm_PHY_CMN_CLK_CFG0, - 0, 4, CLK_DIVIDER_ONE_BASED, - &pll_7nm->postdiv_lock); - if (IS_ERR(hw)) { - ret = PTR_ERR(hw); - goto err_out_div_clk_hw; - } - - pll_7nm->bit_clk_hw = hw; - - snprintf(clk_name, 32, "dsi%d_phy_pll_out_byteclk", pll_7nm->id); - snprintf(parent, 32, "dsi%d_pll_bit_clk", pll_7nm->id); - - /* DSI Byte clock = VCO_CLK / OUT_DIV / BIT_DIV / 8 */ - hw = clk_hw_register_fixed_factor(dev, clk_name, parent, - CLK_SET_RATE_PARENT, 1, 8); - if (IS_ERR(hw)) { - ret = PTR_ERR(hw); - goto err_bit_clk_hw; - } - - pll_7nm->byte_clk_hw = hw; - hw_data->hws[DSI_BYTE_PLL_CLK] = hw; - - snprintf(clk_name, 32, "dsi%d_pll_by_2_bit_clk", pll_7nm->id); - snprintf(parent, 32, "dsi%d_pll_bit_clk", pll_7nm->id); - - hw = clk_hw_register_fixed_factor(dev, clk_name, parent, - 0, 1, 2); - if (IS_ERR(hw)) { - ret = PTR_ERR(hw); - goto err_byte_clk_hw; - } - - pll_7nm->by_2_bit_clk_hw = hw; - - snprintf(clk_name, 32, "dsi%d_pll_post_out_div_clk", pll_7nm->id); - snprintf(parent, 32, "dsi%d_pll_out_div_clk", pll_7nm->id); - - hw = clk_hw_register_fixed_factor(dev, clk_name, parent, - 0, 1, 4); - if (IS_ERR(hw)) { - ret = PTR_ERR(hw); - goto err_by_2_bit_clk_hw; - } - - pll_7nm->post_out_div_clk_hw = hw; - - snprintf(clk_name, 32, "dsi%d_pclk_mux", pll_7nm->id); - snprintf(parent, 32, "dsi%d_pll_bit_clk", pll_7nm->id); - snprintf(parent2, 32, "dsi%d_pll_by_2_bit_clk", pll_7nm->id); - snprintf(parent3, 32, "dsi%d_pll_out_div_clk", pll_7nm->id); - snprintf(parent4, 32, "dsi%d_pll_post_out_div_clk", pll_7nm->id); - - hw = clk_hw_register_mux(dev, clk_name, - ((const char *[]){ - parent, parent2, parent3, parent4 - }), 4, 0, pll_7nm->phy_cmn_mmio + - REG_DSI_7nm_PHY_CMN_CLK_CFG1, - 0, 2, 0, NULL); - if (IS_ERR(hw)) { - ret = PTR_ERR(hw); - goto err_post_out_div_clk_hw; - } - - pll_7nm->pclk_mux_hw = hw; - - snprintf(clk_name, 32, "dsi%d_phy_pll_out_dsiclk", pll_7nm->id); - snprintf(parent, 32, "dsi%d_pclk_mux", pll_7nm->id); - - /* PIX CLK DIV : DIV_CTRL_7_4*/ - hw = clk_hw_register_divider(dev, clk_name, parent, - 0, pll_7nm->phy_cmn_mmio + - REG_DSI_7nm_PHY_CMN_CLK_CFG0, - 4, 4, CLK_DIVIDER_ONE_BASED, - &pll_7nm->postdiv_lock); - if (IS_ERR(hw)) { - ret = PTR_ERR(hw); - goto err_pclk_mux_hw; - } - - pll_7nm->out_dsiclk_hw = hw; - hw_data->hws[DSI_PIXEL_PLL_CLK] = hw; - - hw_data->num = NUM_PROVIDED_CLKS; - pll_7nm->hw_data = hw_data; - - ret = of_clk_add_hw_provider(dev->of_node, of_clk_hw_onecell_get, - pll_7nm->hw_data); - if (ret) { - DRM_DEV_ERROR(dev, "failed to register clk provider: %d\n", ret); - goto err_dsiclk_hw; - } - - return 0; - -err_dsiclk_hw: - clk_hw_unregister_divider(pll_7nm->out_dsiclk_hw); -err_pclk_mux_hw: - clk_hw_unregister_mux(pll_7nm->pclk_mux_hw); -err_post_out_div_clk_hw: - clk_hw_unregister_fixed_factor(pll_7nm->post_out_div_clk_hw); -err_by_2_bit_clk_hw: - clk_hw_unregister_fixed_factor(pll_7nm->by_2_bit_clk_hw); -err_byte_clk_hw: - clk_hw_unregister_fixed_factor(pll_7nm->byte_clk_hw); -err_bit_clk_hw: - clk_hw_unregister_divider(pll_7nm->bit_clk_hw); -err_out_div_clk_hw: - clk_hw_unregister_divider(pll_7nm->out_div_clk_hw); -err_base_clk_hw: - clk_hw_unregister(&pll_7nm->base.clk_hw); - - return ret; -} - -struct msm_dsi_pll *msm_dsi_pll_7nm_init(struct platform_device *pdev, int id) -{ - struct dsi_pll_7nm *pll_7nm; - struct msm_dsi_pll *pll; - int ret; - - pll_7nm = devm_kzalloc(&pdev->dev, sizeof(*pll_7nm), GFP_KERNEL); - if (!pll_7nm) - return ERR_PTR(-ENOMEM); - - DBG("DSI PLL%d", id); - - pll_7nm->pdev = pdev; - pll_7nm->id = id; - pll_7nm_list[id] = pll_7nm; - - pll_7nm->phy_cmn_mmio = msm_ioremap(pdev, "dsi_phy", "DSI_PHY"); - if (IS_ERR_OR_NULL(pll_7nm->phy_cmn_mmio)) { - DRM_DEV_ERROR(&pdev->dev, "failed to map CMN PHY base\n"); - return ERR_PTR(-ENOMEM); - } - - pll_7nm->mmio = msm_ioremap(pdev, "dsi_pll", "DSI_PLL"); - if (IS_ERR_OR_NULL(pll_7nm->mmio)) { - DRM_DEV_ERROR(&pdev->dev, "failed to map PLL base\n"); - return ERR_PTR(-ENOMEM); - } - - spin_lock_init(&pll_7nm->postdiv_lock); - - pll = &pll_7nm->base; - pll->min_rate = 1000000000UL; - pll->max_rate = 3500000000UL; - if (pll->type == MSM_DSI_PHY_7NM_V4_1) { - pll->min_rate = 600000000UL; - pll->max_rate = (unsigned long)5000000000ULL; - /* workaround for max rate overflowing on 32-bit builds: */ - pll->max_rate = max(pll->max_rate, 0xffffffffUL); - } - pll->get_provider = dsi_pll_7nm_get_provider; - pll->destroy = dsi_pll_7nm_destroy; - pll->save_state = dsi_pll_7nm_save_state; - pll->restore_state = dsi_pll_7nm_restore_state; - pll->set_usecase = dsi_pll_7nm_set_usecase; - - pll_7nm->vco_delay = 1; - - ret = pll_7nm_register(pll_7nm); - if (ret) { - DRM_DEV_ERROR(&pdev->dev, "failed to register PLL: %d\n", ret); - return ERR_PTR(ret); - } - - /* TODO: Remove this when we have proper display handover support */ - msm_dsi_pll_save_state(pll); - - return pll; -} diff --git a/drivers/gpu/drm/msm/msm_atomic.c b/drivers/gpu/drm/msm/msm_atomic.c index e9c6544b6a01..fab09e7c6efc 100644 --- a/drivers/gpu/drm/msm/msm_atomic.c +++ b/drivers/gpu/drm/msm/msm_atomic.c @@ -57,10 +57,13 @@ static void vblank_put(struct msm_kms *kms, unsigned crtc_mask) static void lock_crtcs(struct msm_kms *kms, unsigned int crtc_mask) { + int crtc_index; struct drm_crtc *crtc; - for_each_crtc_mask(kms->dev, crtc, crtc_mask) - mutex_lock(&kms->commit_lock[drm_crtc_index(crtc)]); + for_each_crtc_mask(kms->dev, crtc, crtc_mask) { + crtc_index = drm_crtc_index(crtc); + mutex_lock_nested(&kms->commit_lock[crtc_index], crtc_index); + } } static void unlock_crtcs(struct msm_kms *kms, unsigned int crtc_mask) diff --git a/drivers/gpu/drm/msm/msm_debugfs.c b/drivers/gpu/drm/msm/msm_debugfs.c index 85ad0babc326..d611cc8e54a4 100644 --- a/drivers/gpu/drm/msm/msm_debugfs.c +++ b/drivers/gpu/drm/msm/msm_debugfs.c @@ -111,23 +111,15 @@ static const struct file_operations msm_gpu_fops = { static int msm_gem_show(struct drm_device *dev, struct seq_file *m) { struct msm_drm_private *priv = dev->dev_private; - struct msm_gpu *gpu = priv->gpu; int ret; - ret = mutex_lock_interruptible(&priv->mm_lock); + ret = mutex_lock_interruptible(&priv->obj_lock); if (ret) return ret; - if (gpu) { - seq_printf(m, "Active Objects (%s):\n", gpu->name); - msm_gem_describe_objects(&gpu->active_list, m); - } - - seq_printf(m, "Inactive Objects:\n"); - msm_gem_describe_objects(&priv->inactive_dontneed, m); - msm_gem_describe_objects(&priv->inactive_willneed, m); + msm_gem_describe_objects(&priv->objects, m); - mutex_unlock(&priv->mm_lock); + mutex_unlock(&priv->obj_lock); return 0; } diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c index 94525ac76d4e..e1104d2454e2 100644 --- a/drivers/gpu/drm/msm/msm_drv.c +++ b/drivers/gpu/drm/msm/msm_drv.c @@ -39,6 +39,7 @@ * GEM object's debug name * - 1.5.0 - Add SUBMITQUERY_QUERY ioctl * - 1.6.0 - Syncobj support + * - 1.7.0 - Add MSM_PARAM_SUSPENDS to access suspend count */ #define MSM_VERSION_MAJOR 1 #define MSM_VERSION_MINOR 6 @@ -446,8 +447,12 @@ static int msm_drm_init(struct device *dev, const struct drm_driver *drv) priv->wq = alloc_ordered_workqueue("msm", 0); + INIT_LIST_HEAD(&priv->objects); + mutex_init(&priv->obj_lock); + INIT_LIST_HEAD(&priv->inactive_willneed); INIT_LIST_HEAD(&priv->inactive_dontneed); + INIT_LIST_HEAD(&priv->inactive_unpinned); mutex_init(&priv->mm_lock); /* Teach lockdep about lock ordering wrt. shrinker: */ @@ -570,6 +575,7 @@ err_free_priv: kfree(priv); err_put_drm_dev: drm_dev_put(ddev); + platform_set_drvdata(pdev, NULL); return ret; } @@ -1072,6 +1078,10 @@ static int __maybe_unused msm_pm_resume(struct device *dev) static int __maybe_unused msm_pm_prepare(struct device *dev) { struct drm_device *ddev = dev_get_drvdata(dev); + struct msm_drm_private *priv = ddev ? ddev->dev_private : NULL; + + if (!priv || !priv->kms) + return 0; return drm_mode_config_helper_suspend(ddev); } @@ -1079,6 +1089,10 @@ static int __maybe_unused msm_pm_prepare(struct device *dev) static void __maybe_unused msm_pm_complete(struct device *dev) { struct drm_device *ddev = dev_get_drvdata(dev); + struct msm_drm_private *priv = ddev ? ddev->dev_private : NULL; + + if (!priv || !priv->kms) + return; drm_mode_config_helper_resume(ddev); } @@ -1173,10 +1187,11 @@ static int compare_name_mdp(struct device *dev, void *data) return (strstr(dev_name(dev), "mdp") != NULL); } -static int add_display_components(struct device *dev, +static int add_display_components(struct platform_device *pdev, struct component_match **matchptr) { struct device *mdp_dev; + struct device *dev = &pdev->dev; int ret; /* @@ -1185,9 +1200,9 @@ static int add_display_components(struct device *dev, * Populate the children devices, find the MDP5/DPU node, and then add * the interfaces to our components list. */ - if (of_device_is_compatible(dev->of_node, "qcom,mdss") || - of_device_is_compatible(dev->of_node, "qcom,sdm845-mdss") || - of_device_is_compatible(dev->of_node, "qcom,sc7180-mdss")) { + switch (get_mdp_ver(pdev)) { + case KMS_MDP5: + case KMS_DPU: ret = of_platform_populate(dev->of_node, NULL, NULL, dev); if (ret) { DRM_DEV_ERROR(dev, "failed to populate children devices\n"); @@ -1206,9 +1221,11 @@ static int add_display_components(struct device *dev, /* add the MDP component itself */ drm_of_component_match_add(dev, matchptr, compare_of, mdp_dev->of_node); - } else { + break; + case KMS_MDP4: /* MDP4 */ mdp_dev = dev; + break; } ret = add_components_mdp(mdp_dev, matchptr); @@ -1273,7 +1290,7 @@ static int msm_pdev_probe(struct platform_device *pdev) int ret; if (get_mdp_ver(pdev)) { - ret = add_display_components(&pdev->dev, &match); + ret = add_display_components(pdev, &match); if (ret) return ret; } @@ -1311,6 +1328,10 @@ static int msm_pdev_remove(struct platform_device *pdev) static void msm_pdev_shutdown(struct platform_device *pdev) { struct drm_device *drm = platform_get_drvdata(pdev); + struct msm_drm_private *priv = drm ? drm->dev_private : NULL; + + if (!priv || !priv->kms) + return; drm_atomic_helper_shutdown(drm); } @@ -1320,6 +1341,9 @@ static const struct of_device_id dt_match[] = { { .compatible = "qcom,mdss", .data = (void *)KMS_MDP5 }, { .compatible = "qcom,sdm845-mdss", .data = (void *)KMS_DPU }, { .compatible = "qcom,sc7180-mdss", .data = (void *)KMS_DPU }, + { .compatible = "qcom,sc7280-mdss", .data = (void *)KMS_DPU }, + { .compatible = "qcom,sm8150-mdss", .data = (void *)KMS_DPU }, + { .compatible = "qcom,sm8250-mdss", .data = (void *)KMS_DPU }, {} }; MODULE_DEVICE_TABLE(of, dt_match); diff --git a/drivers/gpu/drm/msm/msm_drv.h b/drivers/gpu/drm/msm/msm_drv.h index 591c47a654e8..2668941df529 100644 --- a/drivers/gpu/drm/msm/msm_drv.h +++ b/drivers/gpu/drm/msm/msm_drv.h @@ -174,20 +174,35 @@ struct msm_drm_private { struct msm_rd_state *hangrd; /* debugfs to dump hanging submits */ struct msm_perf_state *perf; - /* - * Lists of inactive GEM objects. Every bo is either in one of the + /** + * List of all GEM objects (mainly for debugfs, protected by obj_lock + * (acquire before per GEM object lock) + */ + struct list_head objects; + struct mutex obj_lock; + + /** + * LRUs of inactive GEM objects. Every bo is either in one of the * inactive lists (depending on whether or not it is shrinkable) or - * gpu->active_list (for the gpu it is active on[1]) + * gpu->active_list (for the gpu it is active on[1]), or transiently + * on a temporary list as the shrinker is running. + * + * Note that inactive_willneed also contains pinned and vmap'd bos, + * but the number of pinned-but-not-active objects is small (scanout + * buffers, ringbuffer, etc). * - * These lists are protected by mm_lock. If struct_mutex is involved, it - * should be aquired prior to mm_lock. One should *not* hold mm_lock in + * These lists are protected by mm_lock (which should be acquired + * before per GEM object lock). One should *not* hold mm_lock in * get_pages()/vmap()/etc paths, as they can trigger the shrinker. * * [1] if someone ever added support for the old 2d cores, there could be * more than one gpu object */ - struct list_head inactive_willneed; /* inactive + !shrinkable */ - struct list_head inactive_dontneed; /* inactive + shrinkable */ + struct list_head inactive_willneed; /* inactive + potentially unpin/evictable */ + struct list_head inactive_dontneed; /* inactive + shrinkable */ + struct list_head inactive_unpinned; /* inactive + purged or unpinned */ + long shrinkable_count; /* write access under mm_lock */ + long evictable_count; /* write access under mm_lock */ struct mutex mm_lock; struct workqueue_struct *wq; diff --git a/drivers/gpu/drm/msm/msm_fb.c b/drivers/gpu/drm/msm/msm_fb.c index d42f0665359a..91c0e493aed5 100644 --- a/drivers/gpu/drm/msm/msm_fb.c +++ b/drivers/gpu/drm/msm/msm_fb.c @@ -33,6 +33,7 @@ static const struct drm_framebuffer_funcs msm_framebuffer_funcs = { #ifdef CONFIG_DEBUG_FS void msm_framebuffer_describe(struct drm_framebuffer *fb, struct seq_file *m) { + struct msm_gem_stats stats = {}; int i, n = fb->format->num_planes; seq_printf(m, "fb: %dx%d@%4.4s (%2d, ID:%d)\n", @@ -42,7 +43,7 @@ void msm_framebuffer_describe(struct drm_framebuffer *fb, struct seq_file *m) for (i = 0; i < n; i++) { seq_printf(m, " %d: offset=%d pitch=%d, obj: ", i, fb->offsets[i], fb->pitches[i]); - msm_gem_describe(fb->obj[i], m); + msm_gem_describe(fb->obj[i], m, &stats); } } #endif diff --git a/drivers/gpu/drm/msm/msm_fence.c b/drivers/gpu/drm/msm/msm_fence.c index ad2703698b05..cd59a5918038 100644 --- a/drivers/gpu/drm/msm/msm_fence.c +++ b/drivers/gpu/drm/msm/msm_fence.c @@ -45,7 +45,7 @@ int msm_wait_fence(struct msm_fence_context *fctx, uint32_t fence, int ret; if (fence > fctx->last_fence) { - DRM_ERROR("%s: waiting on invalid fence: %u (of %u)\n", + DRM_ERROR_RATELIMITED("%s: waiting on invalid fence: %u (of %u)\n", fctx->name, fence, fctx->last_fence); return -EINVAL; } diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c index f091c1e164fa..b199942266a2 100644 --- a/drivers/gpu/drm/msm/msm_gem.c +++ b/drivers/gpu/drm/msm/msm_gem.c @@ -96,7 +96,7 @@ static struct page **get_pages(struct drm_gem_object *obj) { struct msm_gem_object *msm_obj = to_msm_bo(obj); - WARN_ON(!msm_gem_is_locked(obj)); + GEM_WARN_ON(!msm_gem_is_locked(obj)); if (!msm_obj->pages) { struct drm_device *dev = obj->dev; @@ -130,6 +130,9 @@ static struct page **get_pages(struct drm_gem_object *obj) */ if (msm_obj->flags & (MSM_BO_WC|MSM_BO_UNCACHED)) sync_for_device(msm_obj); + + GEM_WARN_ON(msm_obj->active_count); + update_inactive(msm_obj); } return msm_obj->pages; @@ -162,6 +165,7 @@ static void put_pages(struct drm_gem_object *obj) sg_free_table(msm_obj->sgt); kfree(msm_obj->sgt); + msm_obj->sgt = NULL; } if (use_pages(obj)) @@ -180,7 +184,7 @@ struct page **msm_gem_get_pages(struct drm_gem_object *obj) msm_gem_lock(obj); - if (WARN_ON(msm_obj->madv != MSM_MADV_WILLNEED)) { + if (GEM_WARN_ON(msm_obj->madv != MSM_MADV_WILLNEED)) { msm_gem_unlock(obj); return ERR_PTR(-EBUSY); } @@ -256,7 +260,7 @@ static vm_fault_t msm_gem_fault(struct vm_fault *vmf) goto out; } - if (WARN_ON(msm_obj->madv != MSM_MADV_WILLNEED)) { + if (GEM_WARN_ON(msm_obj->madv != MSM_MADV_WILLNEED)) { msm_gem_unlock(obj); return VM_FAULT_SIGBUS; } @@ -289,7 +293,7 @@ static uint64_t mmap_offset(struct drm_gem_object *obj) struct drm_device *dev = obj->dev; int ret; - WARN_ON(!msm_gem_is_locked(obj)); + GEM_WARN_ON(!msm_gem_is_locked(obj)); /* Make it mmapable */ ret = drm_gem_create_mmap_offset(obj); @@ -318,7 +322,7 @@ static struct msm_gem_vma *add_vma(struct drm_gem_object *obj, struct msm_gem_object *msm_obj = to_msm_bo(obj); struct msm_gem_vma *vma; - WARN_ON(!msm_gem_is_locked(obj)); + GEM_WARN_ON(!msm_gem_is_locked(obj)); vma = kzalloc(sizeof(*vma), GFP_KERNEL); if (!vma) @@ -337,7 +341,7 @@ static struct msm_gem_vma *lookup_vma(struct drm_gem_object *obj, struct msm_gem_object *msm_obj = to_msm_bo(obj); struct msm_gem_vma *vma; - WARN_ON(!msm_gem_is_locked(obj)); + GEM_WARN_ON(!msm_gem_is_locked(obj)); list_for_each_entry(vma, &msm_obj->vmas, list) { if (vma->aspace == aspace) @@ -356,19 +360,25 @@ static void del_vma(struct msm_gem_vma *vma) kfree(vma); } -/* Called with msm_obj locked */ +/** + * If close is true, this also closes the VMA (releasing the allocated + * iova range) in addition to removing the iommu mapping. In the eviction + * case (!close), we keep the iova allocated, but only remove the iommu + * mapping. + */ static void -put_iova_spaces(struct drm_gem_object *obj) +put_iova_spaces(struct drm_gem_object *obj, bool close) { struct msm_gem_object *msm_obj = to_msm_bo(obj); struct msm_gem_vma *vma; - WARN_ON(!msm_gem_is_locked(obj)); + GEM_WARN_ON(!msm_gem_is_locked(obj)); list_for_each_entry(vma, &msm_obj->vmas, list) { if (vma->aspace) { msm_gem_purge_vma(vma->aspace, vma); - msm_gem_close_vma(vma->aspace, vma); + if (close) + msm_gem_close_vma(vma->aspace, vma); } } } @@ -380,7 +390,7 @@ put_iova_vmas(struct drm_gem_object *obj) struct msm_gem_object *msm_obj = to_msm_bo(obj); struct msm_gem_vma *vma, *tmp; - WARN_ON(!msm_gem_is_locked(obj)); + GEM_WARN_ON(!msm_gem_is_locked(obj)); list_for_each_entry_safe(vma, tmp, &msm_obj->vmas, list) { del_vma(vma); @@ -394,7 +404,7 @@ static int get_iova_locked(struct drm_gem_object *obj, struct msm_gem_vma *vma; int ret = 0; - WARN_ON(!msm_gem_is_locked(obj)); + GEM_WARN_ON(!msm_gem_is_locked(obj)); vma = lookup_vma(obj, aspace); @@ -421,7 +431,7 @@ static int msm_gem_pin_iova(struct drm_gem_object *obj, struct msm_gem_object *msm_obj = to_msm_bo(obj); struct msm_gem_vma *vma; struct page **pages; - int prot = IOMMU_READ; + int ret, prot = IOMMU_READ; if (!(msm_obj->flags & MSM_BO_GPU_READONLY)) prot |= IOMMU_WRITE; @@ -429,21 +439,26 @@ static int msm_gem_pin_iova(struct drm_gem_object *obj, if (msm_obj->flags & MSM_BO_MAP_PRIV) prot |= IOMMU_PRIV; - WARN_ON(!msm_gem_is_locked(obj)); + GEM_WARN_ON(!msm_gem_is_locked(obj)); - if (WARN_ON(msm_obj->madv != MSM_MADV_WILLNEED)) + if (GEM_WARN_ON(msm_obj->madv != MSM_MADV_WILLNEED)) return -EBUSY; vma = lookup_vma(obj, aspace); - if (WARN_ON(!vma)) + if (GEM_WARN_ON(!vma)) return -EINVAL; pages = get_pages(obj); if (IS_ERR(pages)) return PTR_ERR(pages); - return msm_gem_map_vma(aspace, vma, prot, + ret = msm_gem_map_vma(aspace, vma, prot, msm_obj->sgt, obj->size >> PAGE_SHIFT); + + if (!ret) + msm_obj->pin_count++; + + return ret; } static int get_and_pin_iova_range_locked(struct drm_gem_object *obj, @@ -453,7 +468,7 @@ static int get_and_pin_iova_range_locked(struct drm_gem_object *obj, u64 local; int ret; - WARN_ON(!msm_gem_is_locked(obj)); + GEM_WARN_ON(!msm_gem_is_locked(obj)); ret = get_iova_locked(obj, aspace, &local, range_start, range_end); @@ -524,7 +539,7 @@ uint64_t msm_gem_iova(struct drm_gem_object *obj, msm_gem_lock(obj); vma = lookup_vma(obj, aspace); msm_gem_unlock(obj); - WARN_ON(!vma); + GEM_WARN_ON(!vma); return vma ? vma->iova : 0; } @@ -535,14 +550,21 @@ uint64_t msm_gem_iova(struct drm_gem_object *obj, void msm_gem_unpin_iova_locked(struct drm_gem_object *obj, struct msm_gem_address_space *aspace) { + struct msm_gem_object *msm_obj = to_msm_bo(obj); struct msm_gem_vma *vma; - WARN_ON(!msm_gem_is_locked(obj)); + GEM_WARN_ON(!msm_gem_is_locked(obj)); vma = lookup_vma(obj, aspace); - if (!WARN_ON(!vma)) + if (!GEM_WARN_ON(!vma)) { msm_gem_unmap_vma(aspace, vma); + + msm_obj->pin_count--; + GEM_WARN_ON(msm_obj->pin_count < 0); + + update_inactive(msm_obj); + } } /* @@ -593,12 +615,12 @@ static void *get_vaddr(struct drm_gem_object *obj, unsigned madv) struct msm_gem_object *msm_obj = to_msm_bo(obj); int ret = 0; - WARN_ON(!msm_gem_is_locked(obj)); + GEM_WARN_ON(!msm_gem_is_locked(obj)); if (obj->import_attach) return ERR_PTR(-ENODEV); - if (WARN_ON(msm_obj->madv > madv)) { + if (GEM_WARN_ON(msm_obj->madv > madv)) { DRM_DEV_ERROR(obj->dev->dev, "Invalid madv state: %u vs %u\n", msm_obj->madv, madv); return ERR_PTR(-EBUSY); @@ -664,8 +686,8 @@ void msm_gem_put_vaddr_locked(struct drm_gem_object *obj) { struct msm_gem_object *msm_obj = to_msm_bo(obj); - WARN_ON(!msm_gem_is_locked(obj)); - WARN_ON(msm_obj->vmap_count < 1); + GEM_WARN_ON(!msm_gem_is_locked(obj)); + GEM_WARN_ON(msm_obj->vmap_count < 1); msm_obj->vmap_count--; } @@ -707,20 +729,23 @@ void msm_gem_purge(struct drm_gem_object *obj) struct drm_device *dev = obj->dev; struct msm_gem_object *msm_obj = to_msm_bo(obj); - WARN_ON(!is_purgeable(msm_obj)); - WARN_ON(obj->import_attach); + GEM_WARN_ON(!msm_gem_is_locked(obj)); + GEM_WARN_ON(!is_purgeable(msm_obj)); - put_iova_spaces(obj); + /* Get rid of any iommu mapping(s): */ + put_iova_spaces(obj, true); msm_gem_vunmap(obj); + drm_vma_node_unmap(&obj->vma_node, dev->anon_inode->i_mapping); + put_pages(obj); put_iova_vmas(obj); msm_obj->madv = __MSM_MADV_PURGED; + update_inactive(msm_obj); - drm_vma_node_unmap(&obj->vma_node, dev->anon_inode->i_mapping); drm_gem_free_mmap_offset(obj); /* Our goal here is to return as much of the memory as @@ -734,13 +759,36 @@ void msm_gem_purge(struct drm_gem_object *obj) 0, (loff_t)-1); } +/** + * Unpin the backing pages and make them available to be swapped out. + */ +void msm_gem_evict(struct drm_gem_object *obj) +{ + struct drm_device *dev = obj->dev; + struct msm_gem_object *msm_obj = to_msm_bo(obj); + + GEM_WARN_ON(!msm_gem_is_locked(obj)); + GEM_WARN_ON(is_unevictable(msm_obj)); + GEM_WARN_ON(!msm_obj->evictable); + GEM_WARN_ON(msm_obj->active_count); + + /* Get rid of any iommu mapping(s): */ + put_iova_spaces(obj, false); + + drm_vma_node_unmap(&obj->vma_node, dev->anon_inode->i_mapping); + + put_pages(obj); + + update_inactive(msm_obj); +} + void msm_gem_vunmap(struct drm_gem_object *obj) { struct msm_gem_object *msm_obj = to_msm_bo(obj); - WARN_ON(!msm_gem_is_locked(obj)); + GEM_WARN_ON(!msm_gem_is_locked(obj)); - if (!msm_obj->vaddr || WARN_ON(!is_vunmapable(msm_obj))) + if (!msm_obj->vaddr || GEM_WARN_ON(!is_vunmapable(msm_obj))) return; vunmap(msm_obj->vaddr); @@ -788,12 +836,16 @@ void msm_gem_active_get(struct drm_gem_object *obj, struct msm_gpu *gpu) struct msm_drm_private *priv = obj->dev->dev_private; might_sleep(); - WARN_ON(!msm_gem_is_locked(obj)); - WARN_ON(msm_obj->madv != MSM_MADV_WILLNEED); + GEM_WARN_ON(!msm_gem_is_locked(obj)); + GEM_WARN_ON(msm_obj->madv != MSM_MADV_WILLNEED); + GEM_WARN_ON(msm_obj->dontneed); + GEM_WARN_ON(!msm_obj->sgt); if (msm_obj->active_count++ == 0) { mutex_lock(&priv->mm_lock); - list_del_init(&msm_obj->mm_list); + if (msm_obj->evictable) + mark_unevictable(msm_obj); + list_del(&msm_obj->mm_list); list_add_tail(&msm_obj->mm_list, &gpu->active_list); mutex_unlock(&priv->mm_lock); } @@ -804,7 +856,7 @@ void msm_gem_active_put(struct drm_gem_object *obj) struct msm_gem_object *msm_obj = to_msm_bo(obj); might_sleep(); - WARN_ON(!msm_gem_is_locked(obj)); + GEM_WARN_ON(!msm_gem_is_locked(obj)); if (--msm_obj->active_count == 0) { update_inactive(msm_obj); @@ -815,14 +867,29 @@ static void update_inactive(struct msm_gem_object *msm_obj) { struct msm_drm_private *priv = msm_obj->base.dev->dev_private; + GEM_WARN_ON(!msm_gem_is_locked(&msm_obj->base)); + + if (msm_obj->active_count != 0) + return; + mutex_lock(&priv->mm_lock); - WARN_ON(msm_obj->active_count != 0); - list_del_init(&msm_obj->mm_list); - if (msm_obj->madv == MSM_MADV_WILLNEED) + if (msm_obj->dontneed) + mark_unpurgeable(msm_obj); + if (msm_obj->evictable) + mark_unevictable(msm_obj); + + list_del(&msm_obj->mm_list); + if ((msm_obj->madv == MSM_MADV_WILLNEED) && msm_obj->sgt) { list_add_tail(&msm_obj->mm_list, &priv->inactive_willneed); - else + mark_evictable(msm_obj); + } else if (msm_obj->madv == MSM_MADV_DONTNEED) { list_add_tail(&msm_obj->mm_list, &priv->inactive_dontneed); + mark_purgeable(msm_obj); + } else { + GEM_WARN_ON((msm_obj->madv != __MSM_MADV_PURGED) && msm_obj->sgt); + list_add_tail(&msm_obj->mm_list, &priv->inactive_unpinned); + } mutex_unlock(&priv->mm_lock); } @@ -863,7 +930,8 @@ static void describe_fence(struct dma_fence *fence, const char *type, fence->seqno); } -void msm_gem_describe(struct drm_gem_object *obj, struct seq_file *m) +void msm_gem_describe(struct drm_gem_object *obj, struct seq_file *m, + struct msm_gem_stats *stats) { struct msm_gem_object *msm_obj = to_msm_bo(obj); struct dma_resv *robj = obj->resv; @@ -875,11 +943,28 @@ void msm_gem_describe(struct drm_gem_object *obj, struct seq_file *m) msm_gem_lock(obj); + stats->all.count++; + stats->all.size += obj->size; + + if (is_active(msm_obj)) { + stats->active.count++; + stats->active.size += obj->size; + } + + if (msm_obj->pages) { + stats->resident.count++; + stats->resident.size += obj->size; + } + switch (msm_obj->madv) { case __MSM_MADV_PURGED: + stats->purged.count++; + stats->purged.size += obj->size; madv = " purged"; break; case MSM_MADV_DONTNEED: + stats->purgeable.count++; + stats->purgeable.size += obj->size; madv = " purgeable"; break; case MSM_MADV_WILLNEED: @@ -946,20 +1031,26 @@ void msm_gem_describe(struct drm_gem_object *obj, struct seq_file *m) void msm_gem_describe_objects(struct list_head *list, struct seq_file *m) { + struct msm_gem_stats stats = {}; struct msm_gem_object *msm_obj; - int count = 0; - size_t size = 0; seq_puts(m, " flags id ref offset kaddr size madv name\n"); - list_for_each_entry(msm_obj, list, mm_list) { + list_for_each_entry(msm_obj, list, node) { struct drm_gem_object *obj = &msm_obj->base; seq_puts(m, " "); - msm_gem_describe(obj, m); - count++; - size += obj->size; + msm_gem_describe(obj, m, &stats); } - seq_printf(m, "Total %d objects, %zu bytes\n", count, size); + seq_printf(m, "Total: %4d objects, %9zu bytes\n", + stats.all.count, stats.all.size); + seq_printf(m, "Active: %4d objects, %9zu bytes\n", + stats.active.count, stats.active.size); + seq_printf(m, "Resident: %4d objects, %9zu bytes\n", + stats.resident.count, stats.resident.size); + seq_printf(m, "Purgeable: %4d objects, %9zu bytes\n", + stats.purgeable.count, stats.purgeable.size); + seq_printf(m, "Purged: %4d objects, %9zu bytes\n", + stats.purged.count, stats.purged.size); } #endif @@ -970,19 +1061,25 @@ void msm_gem_free_object(struct drm_gem_object *obj) struct drm_device *dev = obj->dev; struct msm_drm_private *priv = dev->dev_private; + mutex_lock(&priv->obj_lock); + list_del(&msm_obj->node); + mutex_unlock(&priv->obj_lock); + mutex_lock(&priv->mm_lock); + if (msm_obj->dontneed) + mark_unpurgeable(msm_obj); list_del(&msm_obj->mm_list); mutex_unlock(&priv->mm_lock); msm_gem_lock(obj); /* object should not be on active list: */ - WARN_ON(is_active(msm_obj)); + GEM_WARN_ON(is_active(msm_obj)); - put_iova_spaces(obj); + put_iova_spaces(obj, true); if (obj->import_attach) { - WARN_ON(msm_obj->vaddr); + GEM_WARN_ON(msm_obj->vaddr); /* Don't drop the pages for imported dmabuf, as they are not * ours, just free the array we allocated: @@ -1098,7 +1195,7 @@ static struct drm_gem_object *_msm_gem_new(struct drm_device *dev, else if ((flags & (MSM_BO_STOLEN | MSM_BO_SCANOUT)) && priv->vram.size) use_vram = true; - if (WARN_ON(use_vram && !priv->vram.size)) + if (GEM_WARN_ON(use_vram && !priv->vram.size)) return ERR_PTR(-EINVAL); /* Disallow zero sized objects as they make the underlying @@ -1153,10 +1250,13 @@ static struct drm_gem_object *_msm_gem_new(struct drm_device *dev, } mutex_lock(&priv->mm_lock); - /* Initially obj is idle, obj->madv == WILLNEED: */ - list_add_tail(&msm_obj->mm_list, &priv->inactive_willneed); + list_add_tail(&msm_obj->mm_list, &priv->inactive_unpinned); mutex_unlock(&priv->mm_lock); + mutex_lock(&priv->obj_lock); + list_add_tail(&msm_obj->node, &priv->objects); + mutex_unlock(&priv->obj_lock); + return obj; fail: @@ -1224,9 +1324,13 @@ struct drm_gem_object *msm_gem_import(struct drm_device *dev, msm_gem_unlock(obj); mutex_lock(&priv->mm_lock); - list_add_tail(&msm_obj->mm_list, &priv->inactive_willneed); + list_add_tail(&msm_obj->mm_list, &priv->inactive_unpinned); mutex_unlock(&priv->mm_lock); + mutex_lock(&priv->obj_lock); + list_add_tail(&msm_obj->node, &priv->objects); + mutex_unlock(&priv->obj_lock); + return obj; fail: diff --git a/drivers/gpu/drm/msm/msm_gem.h b/drivers/gpu/drm/msm/msm_gem.h index b3a0a880cbab..a6480d2c81b2 100644 --- a/drivers/gpu/drm/msm/msm_gem.h +++ b/drivers/gpu/drm/msm/msm_gem.h @@ -11,6 +11,11 @@ #include <linux/dma-resv.h> #include "msm_drv.h" +/* Make all GEM related WARN_ON()s ratelimited.. when things go wrong they + * tend to go wrong 1000s of times in a short timespan. + */ +#define GEM_WARN_ON(x) WARN_RATELIMIT(x, "%s", __stringify(x)) + /* Additional internal-use only BO flags: */ #define MSM_BO_STOLEN 0x10000000 /* try to use stolen/splash memory */ #define MSM_BO_MAP_PRIV 0x20000000 /* use IOMMU_PRIV when mapping */ @@ -51,17 +56,34 @@ struct msm_gem_object { uint8_t madv; /** + * Is object on inactive_dontneed list (ie. counted in priv->shrinkable_count)? + */ + bool dontneed : 1; + + /** + * Is object evictable (ie. counted in priv->evictable_count)? + */ + bool evictable : 1; + + /** * count of active vmap'ing */ uint8_t vmap_count; - /* And object is either: - * inactive - on priv->inactive_list + /** + * Node in list of all objects (mainly for debugfs, protected by + * priv->obj_lock + */ + struct list_head node; + + /** + * An object is either: + * inactive - on priv->inactive_dontneed or priv->inactive_willneed + * (depending on purgeability status) * active - on one one of the gpu's active_list.. well, at * least for now we don't have (I don't think) hw sync between * 2d and 3d one devices which have both, meaning we need to * block on submit if a bo is already on other ring - * */ struct list_head mm_list; @@ -78,8 +100,6 @@ struct msm_gem_object { struct list_head vmas; /* list of msm_gem_vma */ - struct llist_node freed; - /* For physically contiguous buffers. Used when we don't have * an IOMMU. Also used for stolen/splashscreen buffer. */ @@ -88,6 +108,7 @@ struct msm_gem_object { char name[32]; /* Identifier to print for the debugfs files */ int active_count; + int pin_count; }; #define to_msm_bo(x) container_of(x, struct msm_gem_object, base) @@ -147,8 +168,17 @@ struct drm_gem_object *msm_gem_import(struct drm_device *dev, struct dma_buf *dmabuf, struct sg_table *sgt); __printf(2, 3) void msm_gem_object_set_name(struct drm_gem_object *bo, const char *fmt, ...); + #ifdef CONFIG_DEBUG_FS -void msm_gem_describe(struct drm_gem_object *obj, struct seq_file *m); +struct msm_gem_stats { + struct { + unsigned count; + size_t size; + } all, active, resident, purgeable, purged; +}; + +void msm_gem_describe(struct drm_gem_object *obj, struct seq_file *m, + struct msm_gem_stats *stats); void msm_gem_describe_objects(struct list_head *list, struct seq_file *m); #endif @@ -184,23 +214,101 @@ msm_gem_is_locked(struct drm_gem_object *obj) static inline bool is_active(struct msm_gem_object *msm_obj) { - WARN_ON(!msm_gem_is_locked(&msm_obj->base)); + GEM_WARN_ON(!msm_gem_is_locked(&msm_obj->base)); return msm_obj->active_count; } +/* imported/exported objects are not purgeable: */ +static inline bool is_unpurgeable(struct msm_gem_object *msm_obj) +{ + return msm_obj->base.dma_buf && msm_obj->base.import_attach; +} + static inline bool is_purgeable(struct msm_gem_object *msm_obj) { return (msm_obj->madv == MSM_MADV_DONTNEED) && msm_obj->sgt && - !msm_obj->base.dma_buf && !msm_obj->base.import_attach; + !is_unpurgeable(msm_obj); } static inline bool is_vunmapable(struct msm_gem_object *msm_obj) { - WARN_ON(!msm_gem_is_locked(&msm_obj->base)); + GEM_WARN_ON(!msm_gem_is_locked(&msm_obj->base)); return (msm_obj->vmap_count == 0) && msm_obj->vaddr; } +static inline void mark_purgeable(struct msm_gem_object *msm_obj) +{ + struct msm_drm_private *priv = msm_obj->base.dev->dev_private; + + GEM_WARN_ON(!mutex_is_locked(&priv->mm_lock)); + + if (is_unpurgeable(msm_obj)) + return; + + if (GEM_WARN_ON(msm_obj->dontneed)) + return; + + priv->shrinkable_count += msm_obj->base.size >> PAGE_SHIFT; + msm_obj->dontneed = true; +} + +static inline void mark_unpurgeable(struct msm_gem_object *msm_obj) +{ + struct msm_drm_private *priv = msm_obj->base.dev->dev_private; + + GEM_WARN_ON(!mutex_is_locked(&priv->mm_lock)); + + if (is_unpurgeable(msm_obj)) + return; + + if (GEM_WARN_ON(!msm_obj->dontneed)) + return; + + priv->shrinkable_count -= msm_obj->base.size >> PAGE_SHIFT; + GEM_WARN_ON(priv->shrinkable_count < 0); + msm_obj->dontneed = false; +} + +static inline bool is_unevictable(struct msm_gem_object *msm_obj) +{ + return is_unpurgeable(msm_obj) || msm_obj->pin_count || msm_obj->vaddr; +} + +static inline void mark_evictable(struct msm_gem_object *msm_obj) +{ + struct msm_drm_private *priv = msm_obj->base.dev->dev_private; + + WARN_ON(!mutex_is_locked(&priv->mm_lock)); + + if (is_unevictable(msm_obj)) + return; + + if (WARN_ON(msm_obj->evictable)) + return; + + priv->evictable_count += msm_obj->base.size >> PAGE_SHIFT; + msm_obj->evictable = true; +} + +static inline void mark_unevictable(struct msm_gem_object *msm_obj) +{ + struct msm_drm_private *priv = msm_obj->base.dev->dev_private; + + WARN_ON(!mutex_is_locked(&priv->mm_lock)); + + if (is_unevictable(msm_obj)) + return; + + if (WARN_ON(!msm_obj->evictable)) + return; + + priv->evictable_count -= msm_obj->base.size >> PAGE_SHIFT; + WARN_ON(priv->evictable_count < 0); + msm_obj->evictable = false; +} + void msm_gem_purge(struct drm_gem_object *obj); +void msm_gem_evict(struct drm_gem_object *obj); void msm_gem_vunmap(struct drm_gem_object *obj); /* Created per submit-ioctl, to track bo's and cmdstream bufs, etc, diff --git a/drivers/gpu/drm/msm/msm_gem_shrinker.c b/drivers/gpu/drm/msm/msm_gem_shrinker.c index 9d5248be746f..1187ecf9d647 100644 --- a/drivers/gpu/drm/msm/msm_gem_shrinker.c +++ b/drivers/gpu/drm/msm/msm_gem_shrinker.c @@ -9,57 +9,140 @@ #include "msm_gpu.h" #include "msm_gpu_trace.h" +/* Default disabled for now until it has some more testing on the different + * iommu combinations that can be paired with the driver: + */ +bool enable_eviction = false; +MODULE_PARM_DESC(enable_eviction, "Enable swappable GEM buffers"); +module_param(enable_eviction, bool, 0600); + +static bool can_swap(void) +{ + return enable_eviction && get_nr_swap_pages() > 0; +} + static unsigned long msm_gem_shrinker_count(struct shrinker *shrinker, struct shrink_control *sc) { struct msm_drm_private *priv = container_of(shrinker, struct msm_drm_private, shrinker); - struct msm_gem_object *msm_obj; - unsigned long count = 0; + unsigned count = priv->shrinkable_count; - mutex_lock(&priv->mm_lock); + if (can_swap()) + count += priv->evictable_count; - list_for_each_entry(msm_obj, &priv->inactive_dontneed, mm_list) { - if (!msm_gem_trylock(&msm_obj->base)) - continue; - if (is_purgeable(msm_obj)) - count += msm_obj->base.size >> PAGE_SHIFT; - msm_gem_unlock(&msm_obj->base); - } + return count; +} - mutex_unlock(&priv->mm_lock); +static bool +purge(struct msm_gem_object *msm_obj) +{ + if (!is_purgeable(msm_obj)) + return false; - return count; + /* + * This will move the obj out of still_in_list to + * the purged list + */ + msm_gem_purge(&msm_obj->base); + + return true; +} + +static bool +evict(struct msm_gem_object *msm_obj) +{ + if (is_unevictable(msm_obj)) + return false; + + msm_gem_evict(&msm_obj->base); + + return true; } static unsigned long -msm_gem_shrinker_scan(struct shrinker *shrinker, struct shrink_control *sc) +scan(struct msm_drm_private *priv, unsigned nr_to_scan, struct list_head *list, + bool (*shrink)(struct msm_gem_object *msm_obj)) { - struct msm_drm_private *priv = - container_of(shrinker, struct msm_drm_private, shrinker); - struct msm_gem_object *msm_obj; - unsigned long freed = 0; + unsigned freed = 0; + struct list_head still_in_list; + + INIT_LIST_HEAD(&still_in_list); mutex_lock(&priv->mm_lock); - list_for_each_entry(msm_obj, &priv->inactive_dontneed, mm_list) { - if (freed >= sc->nr_to_scan) + while (freed < nr_to_scan) { + struct msm_gem_object *msm_obj = list_first_entry_or_null( + list, typeof(*msm_obj), mm_list); + + if (!msm_obj) break; - if (!msm_gem_trylock(&msm_obj->base)) + + list_move_tail(&msm_obj->mm_list, &still_in_list); + + /* + * If it is in the process of being freed, msm_gem_free_object + * can be blocked on mm_lock waiting to remove it. So just + * skip it. + */ + if (!kref_get_unless_zero(&msm_obj->base.refcount)) continue; - if (is_purgeable(msm_obj)) { - msm_gem_purge(&msm_obj->base); + + /* + * Now that we own a reference, we can drop mm_lock for the + * rest of the loop body, to reduce contention with the + * retire_submit path (which could make more objects purgeable) + */ + + mutex_unlock(&priv->mm_lock); + + /* + * Note that this still needs to be trylock, since we can + * hit shrinker in response to trying to get backing pages + * for this obj (ie. while it's lock is already held) + */ + if (!msm_gem_trylock(&msm_obj->base)) + goto tail; + + if (shrink(msm_obj)) freed += msm_obj->base.size >> PAGE_SHIFT; - } + msm_gem_unlock(&msm_obj->base); + +tail: + drm_gem_object_put(&msm_obj->base); + mutex_lock(&priv->mm_lock); } + list_splice_tail(&still_in_list, list); mutex_unlock(&priv->mm_lock); + return freed; +} + +static unsigned long +msm_gem_shrinker_scan(struct shrinker *shrinker, struct shrink_control *sc) +{ + struct msm_drm_private *priv = + container_of(shrinker, struct msm_drm_private, shrinker); + unsigned long freed; + + freed = scan(priv, sc->nr_to_scan, &priv->inactive_dontneed, purge); + if (freed > 0) trace_msm_gem_purge(freed << PAGE_SHIFT); - return freed; + if (can_swap() && freed < sc->nr_to_scan) { + int evicted = scan(priv, sc->nr_to_scan - freed, + &priv->inactive_willneed, evict); + + if (evicted > 0) + trace_msm_gem_evict(evicted << PAGE_SHIFT); + + freed += evicted; + } + + return (freed > 0) ? freed : SHRINK_STOP; } /* since we don't know any better, lets bail after a few @@ -68,26 +151,15 @@ msm_gem_shrinker_scan(struct shrinker *shrinker, struct shrink_control *sc) */ static const int vmap_shrink_limit = 15; -static unsigned -vmap_shrink(struct list_head *mm_list) +static bool +vmap_shrink(struct msm_gem_object *msm_obj) { - struct msm_gem_object *msm_obj; - unsigned unmapped = 0; + if (!is_vunmapable(msm_obj)) + return false; - list_for_each_entry(msm_obj, mm_list, mm_list) { - if (!msm_gem_trylock(&msm_obj->base)) - continue; - if (is_vunmapable(msm_obj)) { - msm_gem_vunmap(&msm_obj->base); - unmapped++; - } - msm_gem_unlock(&msm_obj->base); + msm_gem_vunmap(&msm_obj->base); - if (++unmapped >= vmap_shrink_limit) - break; - } - - return unmapped; + return true; } static int @@ -103,17 +175,11 @@ msm_gem_shrinker_vmap(struct notifier_block *nb, unsigned long event, void *ptr) }; unsigned idx, unmapped = 0; - mutex_lock(&priv->mm_lock); - - for (idx = 0; mm_lists[idx]; idx++) { - unmapped += vmap_shrink(mm_lists[idx]); - - if (unmapped >= vmap_shrink_limit) - break; + for (idx = 0; mm_lists[idx] && unmapped < vmap_shrink_limit; idx++) { + unmapped += scan(priv, vmap_shrink_limit - unmapped, + mm_lists[idx], vmap_shrink); } - mutex_unlock(&priv->mm_lock); - *(unsigned long *)ptr += unmapped; if (unmapped > 0) diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c index ab7c167b0623..9dd1c58430ab 100644 --- a/drivers/gpu/drm/msm/msm_gpu.c +++ b/drivers/gpu/drm/msm/msm_gpu.c @@ -251,6 +251,8 @@ int msm_gpu_pm_suspend(struct msm_gpu *gpu) if (ret) return ret; + gpu->suspend_count++; + return 0; } diff --git a/drivers/gpu/drm/msm/msm_gpu.h b/drivers/gpu/drm/msm/msm_gpu.h index d7cd02cd2109..18baf935e143 100644 --- a/drivers/gpu/drm/msm/msm_gpu.h +++ b/drivers/gpu/drm/msm/msm_gpu.h @@ -152,6 +152,8 @@ struct msm_gpu { ktime_t time; } devfreq; + uint32_t suspend_count; + struct msm_gpu_state *crashstate; /* True if the hardware supports expanded apriv (a650 and newer) */ bool hw_apriv; diff --git a/drivers/gpu/drm/msm/msm_gpu_trace.h b/drivers/gpu/drm/msm/msm_gpu_trace.h index 03e0c2536b94..ca0b08d7875b 100644 --- a/drivers/gpu/drm/msm/msm_gpu_trace.h +++ b/drivers/gpu/drm/msm/msm_gpu_trace.h @@ -128,6 +128,19 @@ TRACE_EVENT(msm_gem_purge, ); +TRACE_EVENT(msm_gem_evict, + TP_PROTO(u32 bytes), + TP_ARGS(bytes), + TP_STRUCT__entry( + __field(u32, bytes) + ), + TP_fast_assign( + __entry->bytes = bytes; + ), + TP_printk("Evicting %u bytes", __entry->bytes) +); + + TRACE_EVENT(msm_gem_purge_vmaps, TP_PROTO(u32 unmapped), TP_ARGS(unmapped), diff --git a/drivers/gpu/drm/msm/msm_kms.h b/drivers/gpu/drm/msm/msm_kms.h index 4735251a394d..d8151a89e163 100644 --- a/drivers/gpu/drm/msm/msm_kms.h +++ b/drivers/gpu/drm/msm/msm_kms.h @@ -157,7 +157,6 @@ struct msm_kms { * from the crtc's pending_timer close to end of the frame: */ struct mutex commit_lock[MAX_CRTCS]; - struct lock_class_key commit_lock_keys[MAX_CRTCS]; unsigned pending_crtc_mask; struct msm_pending_timer pending_timers[MAX_CRTCS]; }; @@ -167,11 +166,8 @@ static inline int msm_kms_init(struct msm_kms *kms, { unsigned i, ret; - for (i = 0; i < ARRAY_SIZE(kms->commit_lock); i++) { - lockdep_register_key(&kms->commit_lock_keys[i]); - __mutex_init(&kms->commit_lock[i], "&kms->commit_lock[i]", - &kms->commit_lock_keys[i]); - } + for (i = 0; i < ARRAY_SIZE(kms->commit_lock); i++) + mutex_init(&kms->commit_lock[i]); kms->funcs = funcs; diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.c b/drivers/gpu/drm/nouveau/dispnv50/disp.c index 196612addfd6..1c9c0cdf85db 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/disp.c +++ b/drivers/gpu/drm/nouveau/dispnv50/disp.c @@ -2693,9 +2693,20 @@ nv50_display_create(struct drm_device *dev) else nouveau_display(dev)->format_modifiers = disp50xx_modifiers; - if (disp->disp->object.oclass >= GK104_DISP) { + /* FIXME: 256x256 cursors are supported on Kepler, however unlike Maxwell and later + * generations Kepler requires that we use small pages (4K) for cursor scanout surfaces. The + * proper fix for this is to teach nouveau to migrate fbs being used for the cursor plane to + * small page allocations in prepare_fb(). When this is implemented, we should also force + * large pages (128K) for ovly fbs in order to fix Kepler ovlys. + * But until then, just limit cursors to 128x128 - which is small enough to avoid ever using + * large pages. + */ + if (disp->disp->object.oclass >= GM107_DISP) { dev->mode_config.cursor_width = 256; dev->mode_config.cursor_height = 256; + } else if (disp->disp->object.oclass >= GK104_DISP) { + dev->mode_config.cursor_width = 128; + dev->mode_config.cursor_height = 128; } else { dev->mode_config.cursor_width = 64; dev->mode_config.cursor_height = 64; diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c index 2d5d68fc15c2..3e09df0472ce 100644 --- a/drivers/gpu/drm/nouveau/nouveau_bo.c +++ b/drivers/gpu/drm/nouveau/nouveau_bo.c @@ -548,6 +548,10 @@ nouveau_bo_sync_for_device(struct nouveau_bo *nvbo) if (!ttm_dma) return; + if (!ttm_dma->pages) { + NV_DEBUG(drm, "ttm_dma 0x%p: pages NULL\n", ttm_dma); + return; + } /* Don't waste time looping if the object is coherent */ if (nvbo->force_coherent) @@ -580,6 +584,10 @@ nouveau_bo_sync_for_cpu(struct nouveau_bo *nvbo) if (!ttm_dma) return; + if (!ttm_dma->pages) { + NV_DEBUG(drm, "ttm_dma 0x%p: pages NULL\n", ttm_dma); + return; + } /* Don't waste time looping if the object is coherent */ if (nvbo->force_coherent) diff --git a/drivers/gpu/drm/omapdrm/dss/dsi.c b/drivers/gpu/drm/omapdrm/dss/dsi.c index 022a8d58e83a..5f1722b040f4 100644 --- a/drivers/gpu/drm/omapdrm/dss/dsi.c +++ b/drivers/gpu/drm/omapdrm/dss/dsi.c @@ -2149,12 +2149,12 @@ static int dsi_vc_send_short(struct dsi_data *dsi, int vc, const struct mipi_dsi_msg *msg) { struct mipi_dsi_packet pkt; - int err; + int ret; u32 r; - err = mipi_dsi_create_packet(&pkt, msg); - if (err) - return err; + ret = mipi_dsi_create_packet(&pkt, msg); + if (ret < 0) + return ret; WARN_ON(!dsi_bus_is_locked(dsi)); diff --git a/drivers/gpu/drm/panel/panel-dsi-cm.c b/drivers/gpu/drm/panel/panel-dsi-cm.c index af381d756ac1..5fbfb71ca3d9 100644 --- a/drivers/gpu/drm/panel/panel-dsi-cm.c +++ b/drivers/gpu/drm/panel/panel-dsi-cm.c @@ -37,6 +37,7 @@ struct dsic_panel_data { u32 height_mm; u32 max_hs_rate; u32 max_lp_rate; + bool te_support; }; struct panel_drv_data { @@ -334,9 +335,11 @@ static int dsicm_power_on(struct panel_drv_data *ddata) if (r) goto err; - r = mipi_dsi_dcs_set_tear_on(ddata->dsi, MIPI_DSI_DCS_TEAR_MODE_VBLANK); - if (r) - goto err; + if (ddata->panel_data->te_support) { + r = mipi_dsi_dcs_set_tear_on(ddata->dsi, MIPI_DSI_DCS_TEAR_MODE_VBLANK); + if (r) + goto err; + } /* possible panel bug */ msleep(100); @@ -619,6 +622,7 @@ static const struct dsic_panel_data taal_data = { .height_mm = 0, .max_hs_rate = 300000000, .max_lp_rate = 10000000, + .te_support = true, }; static const struct dsic_panel_data himalaya_data = { @@ -629,6 +633,7 @@ static const struct dsic_panel_data himalaya_data = { .height_mm = 88, .max_hs_rate = 300000000, .max_lp_rate = 10000000, + .te_support = false, }; static const struct dsic_panel_data droid4_data = { @@ -639,6 +644,7 @@ static const struct dsic_panel_data droid4_data = { .height_mm = 89, .max_hs_rate = 300000000, .max_lp_rate = 10000000, + .te_support = false, }; static const struct of_device_id dsicm_of_match[] = { diff --git a/drivers/gpu/drm/panel/panel-tpo-td043mtea1.c b/drivers/gpu/drm/panel/panel-tpo-td043mtea1.c index 49e6c9386258..bacaf1b7fb70 100644 --- a/drivers/gpu/drm/panel/panel-tpo-td043mtea1.c +++ b/drivers/gpu/drm/panel/panel-tpo-td043mtea1.c @@ -186,7 +186,7 @@ static ssize_t vmirror_show(struct device *dev, struct device_attribute *attr, { struct td043mtea1_panel *lcd = dev_get_drvdata(dev); - return snprintf(buf, PAGE_SIZE, "%d\n", lcd->vmirror); + return sysfs_emit(buf, "%d\n", lcd->vmirror); } static ssize_t vmirror_store(struct device *dev, struct device_attribute *attr, @@ -214,7 +214,7 @@ static ssize_t mode_show(struct device *dev, struct device_attribute *attr, { struct td043mtea1_panel *lcd = dev_get_drvdata(dev); - return snprintf(buf, PAGE_SIZE, "%d\n", lcd->mode); + return sysfs_emit(buf, "%d\n", lcd->mode); } static ssize_t mode_store(struct device *dev, struct device_attribute *attr, diff --git a/drivers/gpu/drm/radeon/cik.c b/drivers/gpu/drm/radeon/cik.c index 8b7a4f7b7576..42a8afa839cb 100644 --- a/drivers/gpu/drm/radeon/cik.c +++ b/drivers/gpu/drm/radeon/cik.c @@ -7948,8 +7948,6 @@ restart_ih: DRM_ERROR("Illegal register access in command stream\n"); /* XXX check the bitfield order! */ me_id = (ring_id & 0x60) >> 5; - pipe_id = (ring_id & 0x18) >> 3; - queue_id = (ring_id & 0x7) >> 0; switch (me_id) { case 0: /* This results in a full GPU reset, but all we need to do is soft @@ -7971,8 +7969,6 @@ restart_ih: DRM_ERROR("Illegal instruction in command stream\n"); /* XXX check the bitfield order! */ me_id = (ring_id & 0x60) >> 5; - pipe_id = (ring_id & 0x18) >> 3; - queue_id = (ring_id & 0x7) >> 0; switch (me_id) { case 0: /* This results in a full GPU reset, but all we need to do is soft diff --git a/drivers/gpu/drm/radeon/r600.c b/drivers/gpu/drm/radeon/r600.c index a0459b168d53..7444dc0e0c0e 100644 --- a/drivers/gpu/drm/radeon/r600.c +++ b/drivers/gpu/drm/radeon/r600.c @@ -2569,6 +2569,7 @@ int r600_init_microcode(struct radeon_device *rdev) pr_err("r600_cp: Bogus length %zu in firmware \"%s\"\n", rdev->me_fw->size, fw_name); err = -EINVAL; + goto out; } snprintf(fw_name, sizeof(fw_name), "radeon/%s_rlc.bin", rlc_chip_name); @@ -2579,6 +2580,7 @@ int r600_init_microcode(struct radeon_device *rdev) pr_err("r600_rlc: Bogus length %zu in firmware \"%s\"\n", rdev->rlc_fw->size, fw_name); err = -EINVAL; + goto out; } if ((rdev->family >= CHIP_RV770) && (rdev->family <= CHIP_HEMLOCK)) { diff --git a/drivers/gpu/drm/radeon/r600_cs.c b/drivers/gpu/drm/radeon/r600_cs.c index 34b7c6f16479..8be4799a98ef 100644 --- a/drivers/gpu/drm/radeon/r600_cs.c +++ b/drivers/gpu/drm/radeon/r600_cs.c @@ -38,7 +38,7 @@ extern void r600_cs_legacy_get_tiling_conf(struct drm_device *dev, u32 *npipes, struct r600_cs_track { - /* configuration we miror so that we use same code btw kms/ums */ + /* configuration we mirror so that we use same code btw kms/ums */ u32 group_size; u32 nbanks; u32 npipes; @@ -963,7 +963,7 @@ static int r600_cs_parse_packet0(struct radeon_cs_parser *p, * * This function will test against r600_reg_safe_bm and return 0 * if register is safe. If register is not flag as safe this function - * will test it against a list of register needind special handling. + * will test it against a list of register needing special handling. */ static int r600_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx) { @@ -2336,7 +2336,7 @@ int r600_cs_parse(struct radeon_cs_parser *p) /** * r600_dma_cs_next_reloc() - parse next reloc * @p: parser structure holding parsing context. - * @cs_reloc: reloc informations + * @cs_reloc: reloc information * * Return the next reloc, do bo validation and compute * GPU offset using the provided start. diff --git a/drivers/gpu/drm/radeon/radeon_dp_mst.c b/drivers/gpu/drm/radeon/radeon_dp_mst.c index 66a0e736cc4d..59cf1d288465 100644 --- a/drivers/gpu/drm/radeon/radeon_dp_mst.c +++ b/drivers/gpu/drm/radeon/radeon_dp_mst.c @@ -241,6 +241,9 @@ radeon_dp_mst_detect(struct drm_connector *connector, to_radeon_connector(connector); struct radeon_connector *master = radeon_connector->mst_port; + if (drm_connector_is_unregistered(connector)) + return connector_status_disconnected; + return drm_dp_mst_detect_port(connector, ctx, &master->mst_mgr, radeon_connector->port); } diff --git a/drivers/gpu/drm/radeon/radeon_object.c b/drivers/gpu/drm/radeon/radeon_object.c index 804f7a427be7..cee11c55fd15 100644 --- a/drivers/gpu/drm/radeon/radeon_object.c +++ b/drivers/gpu/drm/radeon/radeon_object.c @@ -380,6 +380,8 @@ int radeon_bo_evict_vram(struct radeon_device *rdev) } #endif man = ttm_manager_type(bdev, TTM_PL_VRAM); + if (!man) + return 0; return ttm_resource_manager_evict_all(bdev, man); } diff --git a/drivers/gpu/drm/radeon/radeon_pm.c b/drivers/gpu/drm/radeon/radeon_pm.c index b6737be9165c..0c1950f4e146 100644 --- a/drivers/gpu/drm/radeon/radeon_pm.c +++ b/drivers/gpu/drm/radeon/radeon_pm.c @@ -360,11 +360,10 @@ static ssize_t radeon_get_pm_profile(struct device *dev, struct radeon_device *rdev = ddev->dev_private; int cp = rdev->pm.profile; - return snprintf(buf, PAGE_SIZE, "%s\n", - (cp == PM_PROFILE_AUTO) ? "auto" : - (cp == PM_PROFILE_LOW) ? "low" : - (cp == PM_PROFILE_MID) ? "mid" : - (cp == PM_PROFILE_HIGH) ? "high" : "default"); + return sysfs_emit(buf, "%s\n", (cp == PM_PROFILE_AUTO) ? "auto" : + (cp == PM_PROFILE_LOW) ? "low" : + (cp == PM_PROFILE_MID) ? "mid" : + (cp == PM_PROFILE_HIGH) ? "high" : "default"); } static ssize_t radeon_set_pm_profile(struct device *dev, @@ -415,9 +414,8 @@ static ssize_t radeon_get_pm_method(struct device *dev, struct radeon_device *rdev = ddev->dev_private; int pm = rdev->pm.pm_method; - return snprintf(buf, PAGE_SIZE, "%s\n", - (pm == PM_METHOD_DYNPM) ? "dynpm" : - (pm == PM_METHOD_PROFILE) ? "profile" : "dpm"); + return sysfs_emit(buf, "%s\n", (pm == PM_METHOD_DYNPM) ? "dynpm" : + (pm == PM_METHOD_PROFILE) ? "profile" : "dpm"); } static ssize_t radeon_set_pm_method(struct device *dev, @@ -472,9 +470,9 @@ static ssize_t radeon_get_dpm_state(struct device *dev, struct radeon_device *rdev = ddev->dev_private; enum radeon_pm_state_type pm = rdev->pm.dpm.user_state; - return snprintf(buf, PAGE_SIZE, "%s\n", - (pm == POWER_STATE_TYPE_BATTERY) ? "battery" : - (pm == POWER_STATE_TYPE_BALANCED) ? "balanced" : "performance"); + return sysfs_emit(buf, "%s\n", + (pm == POWER_STATE_TYPE_BATTERY) ? "battery" : + (pm == POWER_STATE_TYPE_BALANCED) ? "balanced" : "performance"); } static ssize_t radeon_set_dpm_state(struct device *dev, @@ -518,11 +516,11 @@ static ssize_t radeon_get_dpm_forced_performance_level(struct device *dev, if ((rdev->flags & RADEON_IS_PX) && (ddev->switch_power_state != DRM_SWITCH_POWER_ON)) - return snprintf(buf, PAGE_SIZE, "off\n"); + return sysfs_emit(buf, "off\n"); - return snprintf(buf, PAGE_SIZE, "%s\n", - (level == RADEON_DPM_FORCED_LEVEL_AUTO) ? "auto" : - (level == RADEON_DPM_FORCED_LEVEL_LOW) ? "low" : "high"); + return sysfs_emit(buf, "%s\n", + (level == RADEON_DPM_FORCED_LEVEL_AUTO) ? "auto" : + (level == RADEON_DPM_FORCED_LEVEL_LOW) ? "low" : "high"); } static ssize_t radeon_set_dpm_forced_performance_level(struct device *dev, @@ -685,7 +683,7 @@ static ssize_t radeon_hwmon_show_temp(struct device *dev, else temp = 0; - return snprintf(buf, PAGE_SIZE, "%d\n", temp); + return sysfs_emit(buf, "%d\n", temp); } static ssize_t radeon_hwmon_show_temp_thresh(struct device *dev, @@ -701,7 +699,7 @@ static ssize_t radeon_hwmon_show_temp_thresh(struct device *dev, else temp = rdev->pm.dpm.thermal.max_temp; - return snprintf(buf, PAGE_SIZE, "%d\n", temp); + return sysfs_emit(buf, "%d\n", temp); } static SENSOR_DEVICE_ATTR(temp1_input, S_IRUGO, radeon_hwmon_show_temp, NULL, 0); @@ -731,7 +729,7 @@ static ssize_t radeon_hwmon_show_sclk(struct device *dev, for hwmon */ sclk *= 10000; - return snprintf(buf, PAGE_SIZE, "%u\n", sclk); + return sysfs_emit(buf, "%u\n", sclk); } static SENSOR_DEVICE_ATTR(freq1_input, S_IRUGO, radeon_hwmon_show_sclk, NULL, @@ -752,7 +750,7 @@ static ssize_t radeon_hwmon_show_vddc(struct device *dev, if (rdev->asic->dpm.get_current_vddc) vddc = rdev->asic->dpm.get_current_vddc(rdev); - return snprintf(buf, PAGE_SIZE, "%u\n", vddc); + return sysfs_emit(buf, "%u\n", vddc); } static SENSOR_DEVICE_ATTR(in0_input, S_IRUGO, radeon_hwmon_show_vddc, NULL, diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c index 476ce9c24b9f..380b3007fd0b 100644 --- a/drivers/gpu/drm/radeon/radeon_ttm.c +++ b/drivers/gpu/drm/radeon/radeon_ttm.c @@ -360,7 +360,7 @@ static int radeon_ttm_tt_pin_userptr(struct ttm_device *bdev, struct ttm_tt *ttm if (gtt->userflags & RADEON_GEM_USERPTR_ANONONLY) { /* check that we only pin down anonymous memory to prevent problems with writeback */ - unsigned long end = gtt->userptr + ttm->num_pages * PAGE_SIZE; + unsigned long end = gtt->userptr + (u64)ttm->num_pages * PAGE_SIZE; struct vm_area_struct *vma; vma = find_vma(gtt->usermm, gtt->userptr); if (!vma || vma->vm_file || vma->vm_end < end) @@ -382,7 +382,7 @@ static int radeon_ttm_tt_pin_userptr(struct ttm_device *bdev, struct ttm_tt *ttm } while (pinned < ttm->num_pages); r = sg_alloc_table_from_pages(ttm->sg, ttm->pages, ttm->num_pages, 0, - ttm->num_pages << PAGE_SHIFT, + (u64)ttm->num_pages << PAGE_SHIFT, GFP_KERNEL); if (r) goto release_sg; @@ -415,7 +415,7 @@ static void radeon_ttm_tt_unpin_userptr(struct ttm_device *bdev, struct ttm_tt * DMA_BIDIRECTIONAL : DMA_TO_DEVICE; /* double check that we don't free the table twice */ - if (!ttm->sg->sgl) + if (!ttm->sg || !ttm->sg->sgl) return; /* free the sg table and pages again */ @@ -481,13 +481,14 @@ static void radeon_ttm_backend_unbind(struct ttm_device *bdev, struct ttm_tt *tt struct radeon_ttm_tt *gtt = (void *)ttm; struct radeon_device *rdev = radeon_get_rdev(bdev); + if (gtt->userptr) + radeon_ttm_tt_unpin_userptr(bdev, ttm); + if (!gtt->bound) return; radeon_gart_unbind(rdev, gtt->offset, ttm->num_pages); - if (gtt->userptr) - radeon_ttm_tt_unpin_userptr(bdev, ttm); gtt->bound = false; } diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c index 88731b79c8f5..d0e94b10e4c0 100644 --- a/drivers/gpu/drm/radeon/si.c +++ b/drivers/gpu/drm/radeon/si.c @@ -4511,7 +4511,7 @@ static int si_vm_packet3_cp_dma_check(u32 *ib, u32 idx) } else { for (i = 0; i < (command & 0x1fffff); i++) { reg = start_reg + (4 * i); - if (!si_vm_reg_valid(reg)) { + if (!si_vm_reg_valid(reg)) { DRM_ERROR("CP DMA Bad DST register\n"); return -EINVAL; } diff --git a/drivers/gpu/drm/rcar-du/rcar_du_encoder.c b/drivers/gpu/drm/rcar-du/rcar_du_encoder.c index ba8c6038cd63..ca3761772211 100644 --- a/drivers/gpu/drm/rcar-du/rcar_du_encoder.c +++ b/drivers/gpu/drm/rcar-du/rcar_du_encoder.c @@ -48,21 +48,12 @@ static unsigned int rcar_du_encoder_count_ports(struct device_node *node) static const struct drm_encoder_funcs rcar_du_encoder_funcs = { }; -static void rcar_du_encoder_release(struct drm_device *dev, void *res) -{ - struct rcar_du_encoder *renc = res; - - drm_encoder_cleanup(&renc->base); - kfree(renc); -} - int rcar_du_encoder_init(struct rcar_du_device *rcdu, enum rcar_du_output output, struct device_node *enc_node) { struct rcar_du_encoder *renc; struct drm_bridge *bridge; - int ret; /* * Locate the DRM bridge from the DT node. For the DPAD outputs, if the @@ -101,26 +92,16 @@ int rcar_du_encoder_init(struct rcar_du_device *rcdu, return -ENOLINK; } - renc = kzalloc(sizeof(*renc), GFP_KERNEL); - if (renc == NULL) - return -ENOMEM; - - renc->output = output; - dev_dbg(rcdu->dev, "initializing encoder %pOF for output %u\n", enc_node, output); - ret = drm_encoder_init(&rcdu->ddev, &renc->base, &rcar_du_encoder_funcs, - DRM_MODE_ENCODER_NONE, NULL); - if (ret < 0) { - kfree(renc); - return ret; - } + renc = drmm_encoder_alloc(&rcdu->ddev, struct rcar_du_encoder, base, + &rcar_du_encoder_funcs, DRM_MODE_ENCODER_NONE, + NULL); + if (!renc) + return -ENOMEM; - ret = drmm_add_action_or_reset(&rcdu->ddev, rcar_du_encoder_release, - renc); - if (ret) - return ret; + renc->output = output; /* * Attach the bridge to the encoder. The bridge will create the diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c index d82a7ebf6099..92d8de24d0a1 100644 --- a/drivers/gpu/drm/scheduler/sched_main.c +++ b/drivers/gpu/drm/scheduler/sched_main.c @@ -361,40 +361,16 @@ static void drm_sched_job_timedout(struct work_struct *work) */ void drm_sched_increase_karma(struct drm_sched_job *bad) { - int i; - struct drm_sched_entity *tmp; - struct drm_sched_entity *entity; - struct drm_gpu_scheduler *sched = bad->sched; - - /* don't increase @bad's karma if it's from KERNEL RQ, - * because sometimes GPU hang would cause kernel jobs (like VM updating jobs) - * corrupt but keep in mind that kernel jobs always considered good. - */ - if (bad->s_priority != DRM_SCHED_PRIORITY_KERNEL) { - atomic_inc(&bad->karma); - for (i = DRM_SCHED_PRIORITY_MIN; i < DRM_SCHED_PRIORITY_KERNEL; - i++) { - struct drm_sched_rq *rq = &sched->sched_rq[i]; - - spin_lock(&rq->lock); - list_for_each_entry_safe(entity, tmp, &rq->entities, list) { - if (bad->s_fence->scheduled.context == - entity->fence_context) { - if (atomic_read(&bad->karma) > - bad->sched->hang_limit) - if (entity->guilty) - atomic_set(entity->guilty, 1); - break; - } - } - spin_unlock(&rq->lock); - if (&entity->list != &rq->entities) - break; - } - } + drm_sched_increase_karma_ext(bad, 1); } EXPORT_SYMBOL(drm_sched_increase_karma); +void drm_sched_reset_karma(struct drm_sched_job *bad) +{ + drm_sched_increase_karma_ext(bad, 0); +} +EXPORT_SYMBOL(drm_sched_reset_karma); + /** * drm_sched_stop - stop the scheduler * @@ -534,14 +510,31 @@ EXPORT_SYMBOL(drm_sched_start); */ void drm_sched_resubmit_jobs(struct drm_gpu_scheduler *sched) { + drm_sched_resubmit_jobs_ext(sched, INT_MAX); +} +EXPORT_SYMBOL(drm_sched_resubmit_jobs); + +/** + * drm_sched_resubmit_jobs_ext - helper to relunch certain number of jobs from mirror ring list + * + * @sched: scheduler instance + * @max: job numbers to relaunch + * + */ +void drm_sched_resubmit_jobs_ext(struct drm_gpu_scheduler *sched, int max) +{ struct drm_sched_job *s_job, *tmp; uint64_t guilty_context; bool found_guilty = false; struct dma_fence *fence; + int i = 0; list_for_each_entry_safe(s_job, tmp, &sched->pending_list, list) { struct drm_sched_fence *s_fence = s_job->s_fence; + if (i >= max) + break; + if (!found_guilty && atomic_read(&s_job->karma) > sched->hang_limit) { found_guilty = true; guilty_context = s_job->s_fence->scheduled.context; @@ -552,6 +545,7 @@ void drm_sched_resubmit_jobs(struct drm_gpu_scheduler *sched) dma_fence_put(s_job->s_fence->parent); fence = sched->ops->run_job(s_job); + i++; if (IS_ERR_OR_NULL(fence)) { if (IS_ERR(fence)) @@ -563,7 +557,7 @@ void drm_sched_resubmit_jobs(struct drm_gpu_scheduler *sched) } } } -EXPORT_SYMBOL(drm_sched_resubmit_jobs); +EXPORT_SYMBOL(drm_sched_resubmit_jobs_ext); /** * drm_sched_job_init - init a scheduler job @@ -903,3 +897,48 @@ void drm_sched_fini(struct drm_gpu_scheduler *sched) sched->ready = false; } EXPORT_SYMBOL(drm_sched_fini); + +/** + * drm_sched_increase_karma_ext - Update sched_entity guilty flag + * + * @bad: The job guilty of time out + * @type: type for increase/reset karma + * + */ +void drm_sched_increase_karma_ext(struct drm_sched_job *bad, int type) +{ + int i; + struct drm_sched_entity *tmp; + struct drm_sched_entity *entity; + struct drm_gpu_scheduler *sched = bad->sched; + + /* don't change @bad's karma if it's from KERNEL RQ, + * because sometimes GPU hang would cause kernel jobs (like VM updating jobs) + * corrupt but keep in mind that kernel jobs always considered good. + */ + if (bad->s_priority != DRM_SCHED_PRIORITY_KERNEL) { + if (type == 0) + atomic_set(&bad->karma, 0); + else if (type == 1) + atomic_inc(&bad->karma); + + for (i = DRM_SCHED_PRIORITY_MIN; i < DRM_SCHED_PRIORITY_KERNEL; + i++) { + struct drm_sched_rq *rq = &sched->sched_rq[i]; + + spin_lock(&rq->lock); + list_for_each_entry_safe(entity, tmp, &rq->entities, list) { + if (bad->s_fence->scheduled.context == + entity->fence_context) { + if (entity->guilty) + atomic_set(entity->guilty, type); + break; + } + } + spin_unlock(&rq->lock); + if (&entity->list != &rq->entities) + break; + } + } +} +EXPORT_SYMBOL(drm_sched_increase_karma_ext); diff --git a/drivers/gpu/drm/tegra/dc.c b/drivers/gpu/drm/tegra/dc.c index da6afe7f0c7d..f9120dc24682 100644 --- a/drivers/gpu/drm/tegra/dc.c +++ b/drivers/gpu/drm/tegra/dc.c @@ -832,10 +832,14 @@ static struct drm_plane *tegra_primary_plane_create(struct drm_device *drm, return &plane->base; } -static const u32 tegra_cursor_plane_formats[] = { +static const u32 tegra_legacy_cursor_plane_formats[] = { DRM_FORMAT_RGBA8888, }; +static const u32 tegra_cursor_plane_formats[] = { + DRM_FORMAT_ARGB8888, +}; + static int tegra_cursor_atomic_check(struct drm_plane *plane, struct drm_atomic_state *state) { @@ -875,12 +879,24 @@ static void tegra_cursor_atomic_update(struct drm_plane *plane, plane); struct tegra_plane_state *tegra_plane_state = to_tegra_plane_state(new_state); struct tegra_dc *dc = to_tegra_dc(new_state->crtc); - u32 value = CURSOR_CLIP_DISPLAY; + struct tegra_drm *tegra = plane->dev->dev_private; +#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT + u64 dma_mask = *dc->dev->dma_mask; +#endif + unsigned int x, y; + u32 value = 0; /* rien ne va plus */ if (!new_state->crtc || !new_state->fb) return; + /* + * Legacy display supports hardware clipping of the cursor, but + * nvdisplay relies on software to clip the cursor to the screen. + */ + if (!dc->soc->has_nvdisplay) + value |= CURSOR_CLIP_DISPLAY; + switch (new_state->crtc_w) { case 32: value |= CURSOR_SIZE_32x32; @@ -908,7 +924,7 @@ static void tegra_cursor_atomic_update(struct drm_plane *plane, tegra_dc_writel(dc, value, DC_DISP_CURSOR_START_ADDR); #ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT - value = (tegra_plane_state->iova[0] >> 32) & 0x3; + value = (tegra_plane_state->iova[0] >> 32) & (dma_mask >> 32); tegra_dc_writel(dc, value, DC_DISP_CURSOR_START_ADDR_HI); #endif @@ -920,15 +936,39 @@ static void tegra_cursor_atomic_update(struct drm_plane *plane, value = tegra_dc_readl(dc, DC_DISP_BLEND_CURSOR_CONTROL); value &= ~CURSOR_DST_BLEND_MASK; value &= ~CURSOR_SRC_BLEND_MASK; - value |= CURSOR_MODE_NORMAL; + + if (dc->soc->has_nvdisplay) + value &= ~CURSOR_COMPOSITION_MODE_XOR; + else + value |= CURSOR_MODE_NORMAL; + value |= CURSOR_DST_BLEND_NEG_K1_TIMES_SRC; value |= CURSOR_SRC_BLEND_K1_TIMES_SRC; value |= CURSOR_ALPHA; tegra_dc_writel(dc, value, DC_DISP_BLEND_CURSOR_CONTROL); + /* nvdisplay relies on software for clipping */ + if (dc->soc->has_nvdisplay) { + struct drm_rect src; + + x = new_state->dst.x1; + y = new_state->dst.y1; + + drm_rect_fp_to_int(&src, &new_state->src); + + value = (src.y1 & tegra->vmask) << 16 | (src.x1 & tegra->hmask); + tegra_dc_writel(dc, value, DC_DISP_PCALC_HEAD_SET_CROPPED_POINT_IN_CURSOR); + + value = (drm_rect_height(&src) & tegra->vmask) << 16 | + (drm_rect_width(&src) & tegra->hmask); + tegra_dc_writel(dc, value, DC_DISP_PCALC_HEAD_SET_CROPPED_SIZE_IN_CURSOR); + } else { + x = new_state->crtc_x; + y = new_state->crtc_y; + } + /* position the cursor */ - value = (new_state->crtc_y & 0x3fff) << 16 | - (new_state->crtc_x & 0x3fff); + value = ((y & tegra->vmask) << 16) | (x & tegra->hmask); tegra_dc_writel(dc, value, DC_DISP_CURSOR_POSITION); } @@ -982,8 +1022,13 @@ static struct drm_plane *tegra_dc_cursor_plane_create(struct drm_device *drm, plane->index = 6; plane->dc = dc; - num_formats = ARRAY_SIZE(tegra_cursor_plane_formats); - formats = tegra_cursor_plane_formats; + if (!dc->soc->has_nvdisplay) { + num_formats = ARRAY_SIZE(tegra_legacy_cursor_plane_formats); + formats = tegra_legacy_cursor_plane_formats; + } else { + num_formats = ARRAY_SIZE(tegra_cursor_plane_formats); + formats = tegra_cursor_plane_formats; + } err = drm_universal_plane_init(drm, &plane->base, possible_crtcs, &tegra_plane_funcs, formats, @@ -1700,6 +1745,11 @@ static void tegra_dc_commit_state(struct tegra_dc *dc, dev_err(dc->dev, "failed to set clock rate to %lu Hz\n", state->pclk); + + err = clk_set_rate(dc->clk, state->pclk); + if (err < 0) + dev_err(dc->dev, "failed to set clock %pC to %lu Hz: %d\n", + dc->clk, state->pclk, err); } DRM_DEBUG_KMS("rate: %lu, div: %u\n", clk_get_rate(dc->clk), @@ -1710,11 +1760,6 @@ static void tegra_dc_commit_state(struct tegra_dc *dc, value = SHIFT_CLK_DIVIDER(state->div) | PIXEL_CLK_DIVIDER_PCD1; tegra_dc_writel(dc, value, DC_DISP_DISP_CLOCK_CONTROL); } - - err = clk_set_rate(dc->clk, state->pclk); - if (err < 0) - dev_err(dc->dev, "failed to set clock %pC to %lu Hz: %d\n", - dc->clk, state->pclk, err); } static void tegra_dc_stop(struct tegra_dc *dc) @@ -2035,6 +2080,16 @@ static bool tegra_dc_has_window_groups(struct tegra_dc *dc) return false; } +static int tegra_dc_early_init(struct host1x_client *client) +{ + struct drm_device *drm = dev_get_drvdata(client->host); + struct tegra_drm *tegra = drm->dev_private; + + tegra->num_crtcs++; + + return 0; +} + static int tegra_dc_init(struct host1x_client *client) { struct drm_device *drm = dev_get_drvdata(client->host); @@ -2046,6 +2101,12 @@ static int tegra_dc_init(struct host1x_client *client) int err; /* + * DC has been reset by now, so VBLANK syncpoint can be released + * for general use. + */ + host1x_syncpt_release_vblank_reservation(client, 26 + dc->pipe); + + /* * XXX do not register DCs with no window groups because we cannot * assign a primary plane to them, which in turn will cause KMS to * crash. @@ -2111,6 +2172,12 @@ static int tegra_dc_init(struct host1x_client *client) if (dc->soc->pitch_align > tegra->pitch_align) tegra->pitch_align = dc->soc->pitch_align; + /* track maximum resolution */ + if (dc->soc->has_nvdisplay) + drm->mode_config.max_width = drm->mode_config.max_height = 16384; + else + drm->mode_config.max_width = drm->mode_config.max_height = 4096; + err = tegra_dc_rgb_init(drm, dc); if (err < 0 && err != -ENODEV) { dev_err(dc->dev, "failed to initialize RGB output: %d\n", err); @@ -2141,7 +2208,7 @@ cleanup: drm_plane_cleanup(primary); host1x_client_iommu_detach(client); - host1x_syncpt_free(dc->syncpt); + host1x_syncpt_put(dc->syncpt); return err; } @@ -2166,7 +2233,17 @@ static int tegra_dc_exit(struct host1x_client *client) } host1x_client_iommu_detach(client); - host1x_syncpt_free(dc->syncpt); + host1x_syncpt_put(dc->syncpt); + + return 0; +} + +static int tegra_dc_late_exit(struct host1x_client *client) +{ + struct drm_device *drm = dev_get_drvdata(client->host); + struct tegra_drm *tegra = drm->dev_private; + + tegra->num_crtcs--; return 0; } @@ -2235,8 +2312,10 @@ put_rpm: } static const struct host1x_client_ops dc_client_ops = { + .early_init = tegra_dc_early_init, .init = tegra_dc_init, .exit = tegra_dc_exit, + .late_exit = tegra_dc_late_exit, .suspend = tegra_dc_runtime_suspend, .resume = tegra_dc_runtime_resume, }; @@ -2246,6 +2325,7 @@ static const struct tegra_dc_soc_info tegra20_dc_soc_info = { .supports_interlacing = false, .supports_cursor = false, .supports_block_linear = false, + .supports_sector_layout = false, .has_legacy_blending = true, .pitch_align = 8, .has_powergate = false, @@ -2265,6 +2345,7 @@ static const struct tegra_dc_soc_info tegra30_dc_soc_info = { .supports_interlacing = false, .supports_cursor = false, .supports_block_linear = false, + .supports_sector_layout = false, .has_legacy_blending = true, .pitch_align = 8, .has_powergate = false, @@ -2284,6 +2365,7 @@ static const struct tegra_dc_soc_info tegra114_dc_soc_info = { .supports_interlacing = false, .supports_cursor = false, .supports_block_linear = false, + .supports_sector_layout = false, .has_legacy_blending = true, .pitch_align = 64, .has_powergate = true, @@ -2303,6 +2385,7 @@ static const struct tegra_dc_soc_info tegra124_dc_soc_info = { .supports_interlacing = true, .supports_cursor = true, .supports_block_linear = true, + .supports_sector_layout = false, .has_legacy_blending = false, .pitch_align = 64, .has_powergate = true, @@ -2322,6 +2405,7 @@ static const struct tegra_dc_soc_info tegra210_dc_soc_info = { .supports_interlacing = true, .supports_cursor = true, .supports_block_linear = true, + .supports_sector_layout = false, .has_legacy_blending = false, .pitch_align = 64, .has_powergate = true, @@ -2375,6 +2459,7 @@ static const struct tegra_dc_soc_info tegra186_dc_soc_info = { .supports_interlacing = true, .supports_cursor = true, .supports_block_linear = true, + .supports_sector_layout = false, .has_legacy_blending = false, .pitch_align = 64, .has_powergate = false, @@ -2423,6 +2508,7 @@ static const struct tegra_dc_soc_info tegra194_dc_soc_info = { .supports_interlacing = true, .supports_cursor = true, .supports_block_linear = true, + .supports_sector_layout = true, .has_legacy_blending = false, .pitch_align = 64, .has_powergate = false, @@ -2513,22 +2599,18 @@ static int tegra_dc_couple(struct tegra_dc *dc) * POWER_CONTROL registers during CRTC enabling. */ if (dc->soc->coupled_pm && dc->pipe == 1) { - u32 flags = DL_FLAG_PM_RUNTIME | DL_FLAG_AUTOREMOVE_CONSUMER; - struct device_link *link; - struct device *partner; + struct device *companion; + struct tegra_dc *parent; - partner = driver_find_device(dc->dev->driver, NULL, NULL, - tegra_dc_match_by_pipe); - if (!partner) + companion = driver_find_device(dc->dev->driver, NULL, (const void *)0, + tegra_dc_match_by_pipe); + if (!companion) return -EPROBE_DEFER; - link = device_link_add(dc->dev, partner, flags); - if (!link) { - dev_err(dc->dev, "failed to link controllers\n"); - return -EINVAL; - } + parent = dev_get_drvdata(companion); + dc->client.parent = &parent->client; - dev_dbg(dc->dev, "coupled to %s\n", dev_name(partner)); + dev_dbg(dc->dev, "coupled to %s\n", dev_name(companion)); } return 0; @@ -2536,9 +2618,16 @@ static int tegra_dc_couple(struct tegra_dc *dc) static int tegra_dc_probe(struct platform_device *pdev) { + u64 dma_mask = dma_get_mask(pdev->dev.parent); struct tegra_dc *dc; int err; + err = dma_coerce_mask_and_coherent(&pdev->dev, dma_mask); + if (err < 0) { + dev_err(&pdev->dev, "failed to set DMA mask: %d\n", err); + return err; + } + dc = devm_kzalloc(&pdev->dev, sizeof(*dc), GFP_KERNEL); if (!dc) return -ENOMEM; diff --git a/drivers/gpu/drm/tegra/dc.h b/drivers/gpu/drm/tegra/dc.h index 051d03dcb9b0..29f19c3c6149 100644 --- a/drivers/gpu/drm/tegra/dc.h +++ b/drivers/gpu/drm/tegra/dc.h @@ -52,6 +52,7 @@ struct tegra_dc_soc_info { bool supports_interlacing; bool supports_cursor; bool supports_block_linear; + bool supports_sector_layout; bool has_legacy_blending; unsigned int pitch_align; bool has_powergate; @@ -511,6 +512,8 @@ int tegra_dc_rgb_exit(struct tegra_dc *dc); #define DC_DISP_CURSOR_START_ADDR_HI 0x4ec #define DC_DISP_BLEND_CURSOR_CONTROL 0x4f1 +#define CURSOR_COMPOSITION_MODE_BLEND (0 << 25) +#define CURSOR_COMPOSITION_MODE_XOR (1 << 25) #define CURSOR_MODE_LEGACY (0 << 24) #define CURSOR_MODE_NORMAL (1 << 24) #define CURSOR_DST_BLEND_ZERO (0 << 16) @@ -705,6 +708,9 @@ int tegra_dc_rgb_exit(struct tegra_dc *dc); #define PROTOCOL_MASK (0xf << 8) #define PROTOCOL_SINGLE_TMDS_A (0x1 << 8) +#define DC_DISP_PCALC_HEAD_SET_CROPPED_POINT_IN_CURSOR 0x442 +#define DC_DISP_PCALC_HEAD_SET_CROPPED_SIZE_IN_CURSOR 0x446 + #define DC_WIN_CORE_WINDOWGROUP_SET_CONTROL 0x702 #define OWNER_MASK (0xf << 0) #define OWNER(x) (((x) & 0xf) << 0) diff --git a/drivers/gpu/drm/tegra/dpaux.c b/drivers/gpu/drm/tegra/dpaux.c index 105fb9cdbb3b..ea56c6ec25e4 100644 --- a/drivers/gpu/drm/tegra/dpaux.c +++ b/drivers/gpu/drm/tegra/dpaux.c @@ -534,9 +534,7 @@ static int tegra_dpaux_probe(struct platform_device *pdev) dpaux->aux.transfer = tegra_dpaux_transfer; dpaux->aux.dev = &pdev->dev; - err = drm_dp_aux_register(&dpaux->aux); - if (err < 0) - return err; + drm_dp_aux_init(&dpaux->aux); /* * Assume that by default the DPAUX/I2C pads will be used for HDMI, @@ -589,8 +587,6 @@ static int tegra_dpaux_remove(struct platform_device *pdev) pm_runtime_put_sync(&pdev->dev); pm_runtime_disable(&pdev->dev); - drm_dp_aux_unregister(&dpaux->aux); - mutex_lock(&dpaux_lock); list_del(&dpaux->list); mutex_unlock(&dpaux_lock); @@ -723,6 +719,10 @@ int drm_dp_aux_attach(struct drm_dp_aux *aux, struct tegra_output *output) unsigned long timeout; int err; + err = drm_dp_aux_register(aux); + if (err < 0) + return err; + output->connector.polled = DRM_CONNECTOR_POLL_HPD; dpaux->output = output; @@ -760,6 +760,7 @@ int drm_dp_aux_detach(struct drm_dp_aux *aux) unsigned long timeout; int err; + drm_dp_aux_unregister(aux); disable_irq(dpaux->irq); if (dpaux->output->panel) { diff --git a/drivers/gpu/drm/tegra/drm.c b/drivers/gpu/drm/tegra/drm.c index 90709c38c993..0c350b0daab4 100644 --- a/drivers/gpu/drm/tegra/drm.c +++ b/drivers/gpu/drm/tegra/drm.c @@ -174,7 +174,7 @@ int tegra_drm_submit(struct tegra_drm_context *context, struct drm_tegra_syncpt syncpt; struct host1x *host1x = dev_get_drvdata(drm->dev->parent); struct drm_gem_object **refs; - struct host1x_syncpt *sp; + struct host1x_syncpt *sp = NULL; struct host1x_job *job; unsigned int num_refs; int err; @@ -301,8 +301,8 @@ int tegra_drm_submit(struct tegra_drm_context *context, goto fail; } - /* check whether syncpoint ID is valid */ - sp = host1x_syncpt_get(host1x, syncpt.id); + /* Syncpoint ref will be dropped on job release. */ + sp = host1x_syncpt_get_by_id(host1x, syncpt.id); if (!sp) { err = -ENOENT; goto fail; @@ -311,7 +311,7 @@ int tegra_drm_submit(struct tegra_drm_context *context, job->is_addr_reg = context->client->ops->is_addr_reg; job->is_valid_class = context->client->ops->is_valid_class; job->syncpt_incrs = syncpt.incrs; - job->syncpt_id = syncpt.id; + job->syncpt = sp; job->timeout = 10000; if (args->timeout && args->timeout < 10000) @@ -383,7 +383,7 @@ static int tegra_syncpt_read(struct drm_device *drm, void *data, struct drm_tegra_syncpt_read *args = data; struct host1x_syncpt *sp; - sp = host1x_syncpt_get(host, args->id); + sp = host1x_syncpt_get_by_id_noref(host, args->id); if (!sp) return -EINVAL; @@ -398,7 +398,7 @@ static int tegra_syncpt_incr(struct drm_device *drm, void *data, struct drm_tegra_syncpt_incr *args = data; struct host1x_syncpt *sp; - sp = host1x_syncpt_get(host1x, args->id); + sp = host1x_syncpt_get_by_id_noref(host1x, args->id); if (!sp) return -EINVAL; @@ -412,7 +412,7 @@ static int tegra_syncpt_wait(struct drm_device *drm, void *data, struct drm_tegra_syncpt_wait *args = data; struct host1x_syncpt *sp; - sp = host1x_syncpt_get(host1x, args->id); + sp = host1x_syncpt_get_by_id_noref(host1x, args->id); if (!sp) return -EINVAL; @@ -1121,9 +1121,8 @@ static int host1x_drm_probe(struct host1x_device *dev) drm->mode_config.min_width = 0; drm->mode_config.min_height = 0; - - drm->mode_config.max_width = 4096; - drm->mode_config.max_height = 4096; + drm->mode_config.max_width = 0; + drm->mode_config.max_height = 0; drm->mode_config.allow_fb_modifiers = true; @@ -1142,6 +1141,14 @@ static int host1x_drm_probe(struct host1x_device *dev) if (err < 0) goto fbdev; + /* + * Now that all display controller have been initialized, the maximum + * supported resolution is known and the bitmask for horizontal and + * vertical bitfields can be computed. + */ + tegra->hmask = drm->mode_config.max_width - 1; + tegra->vmask = drm->mode_config.max_height - 1; + if (tegra->use_explicit_iommu) { u64 carveout_start, carveout_end, gem_start, gem_end; u64 dma_mask = dma_get_mask(&dev->dev); diff --git a/drivers/gpu/drm/tegra/drm.h b/drivers/gpu/drm/tegra/drm.h index f38de08e0c95..87df251c1fcf 100644 --- a/drivers/gpu/drm/tegra/drm.h +++ b/drivers/gpu/drm/tegra/drm.h @@ -24,6 +24,9 @@ #include "hub.h" #include "trace.h" +/* XXX move to include/uapi/drm/drm_fourcc.h? */ +#define DRM_FORMAT_MOD_NVIDIA_SECTOR_LAYOUT BIT(22) + struct reset_control; #ifdef CONFIG_DRM_FBDEV_EMULATION @@ -54,7 +57,9 @@ struct tegra_drm { struct tegra_fbdev *fbdev; #endif + unsigned int hmask, vmask; unsigned int pitch_align; + unsigned int num_crtcs; struct tegra_display_hub *hub; }; diff --git a/drivers/gpu/drm/tegra/fb.c b/drivers/gpu/drm/tegra/fb.c index 01939c57fc74..cae8b8cbe9dd 100644 --- a/drivers/gpu/drm/tegra/fb.c +++ b/drivers/gpu/drm/tegra/fb.c @@ -44,6 +44,15 @@ int tegra_fb_get_tiling(struct drm_framebuffer *framebuffer, { uint64_t modifier = framebuffer->modifier; + if ((modifier >> 56) == DRM_FORMAT_MOD_VENDOR_NVIDIA) { + if ((modifier & DRM_FORMAT_MOD_NVIDIA_SECTOR_LAYOUT) == 0) + tiling->sector_layout = TEGRA_BO_SECTOR_LAYOUT_TEGRA; + else + tiling->sector_layout = TEGRA_BO_SECTOR_LAYOUT_GPU; + + modifier &= ~DRM_FORMAT_MOD_NVIDIA_SECTOR_LAYOUT; + } + switch (modifier) { case DRM_FORMAT_MOD_LINEAR: tiling->mode = TEGRA_BO_TILING_MODE_PITCH; @@ -86,6 +95,7 @@ int tegra_fb_get_tiling(struct drm_framebuffer *framebuffer, break; default: + DRM_DEBUG_KMS("unknown format modifier: %llx\n", modifier); return -EINVAL; } diff --git a/drivers/gpu/drm/tegra/gem.h b/drivers/gpu/drm/tegra/gem.h index fafb5724499b..c15fd99d6cb2 100644 --- a/drivers/gpu/drm/tegra/gem.h +++ b/drivers/gpu/drm/tegra/gem.h @@ -21,9 +21,15 @@ enum tegra_bo_tiling_mode { TEGRA_BO_TILING_MODE_BLOCK, }; +enum tegra_bo_sector_layout { + TEGRA_BO_SECTOR_LAYOUT_TEGRA, + TEGRA_BO_SECTOR_LAYOUT_GPU, +}; + struct tegra_bo_tiling { enum tegra_bo_tiling_mode mode; unsigned long value; + enum tegra_bo_sector_layout sector_layout; }; struct tegra_bo { diff --git a/drivers/gpu/drm/tegra/gr2d.c b/drivers/gpu/drm/tegra/gr2d.c index adbe2ddcda19..de288cba3905 100644 --- a/drivers/gpu/drm/tegra/gr2d.c +++ b/drivers/gpu/drm/tegra/gr2d.c @@ -67,7 +67,7 @@ static int gr2d_init(struct host1x_client *client) detach: host1x_client_iommu_detach(client); free: - host1x_syncpt_free(client->syncpts[0]); + host1x_syncpt_put(client->syncpts[0]); put: host1x_channel_put(gr2d->channel); return err; @@ -86,7 +86,7 @@ static int gr2d_exit(struct host1x_client *client) return err; host1x_client_iommu_detach(client); - host1x_syncpt_free(client->syncpts[0]); + host1x_syncpt_put(client->syncpts[0]); host1x_channel_put(gr2d->channel); return 0; diff --git a/drivers/gpu/drm/tegra/gr3d.c b/drivers/gpu/drm/tegra/gr3d.c index b0b8154e8104..24442ade0da3 100644 --- a/drivers/gpu/drm/tegra/gr3d.c +++ b/drivers/gpu/drm/tegra/gr3d.c @@ -76,7 +76,7 @@ static int gr3d_init(struct host1x_client *client) detach: host1x_client_iommu_detach(client); free: - host1x_syncpt_free(client->syncpts[0]); + host1x_syncpt_put(client->syncpts[0]); put: host1x_channel_put(gr3d->channel); return err; @@ -94,7 +94,7 @@ static int gr3d_exit(struct host1x_client *client) return err; host1x_client_iommu_detach(client); - host1x_syncpt_free(client->syncpts[0]); + host1x_syncpt_put(client->syncpts[0]); host1x_channel_put(gr3d->channel); return 0; diff --git a/drivers/gpu/drm/tegra/hub.c b/drivers/gpu/drm/tegra/hub.c index 8e6d329d062b..79bff8b48271 100644 --- a/drivers/gpu/drm/tegra/hub.c +++ b/drivers/gpu/drm/tegra/hub.c @@ -55,6 +55,18 @@ static const u64 tegra_shared_plane_modifiers[] = { DRM_FORMAT_MOD_NVIDIA_16BX2_BLOCK(3), DRM_FORMAT_MOD_NVIDIA_16BX2_BLOCK(4), DRM_FORMAT_MOD_NVIDIA_16BX2_BLOCK(5), + /* + * The GPU sector layout is only supported on Tegra194, but these will + * be filtered out later on by ->format_mod_supported() on SoCs where + * it isn't supported. + */ + DRM_FORMAT_MOD_NVIDIA_16BX2_BLOCK(0) | DRM_FORMAT_MOD_NVIDIA_SECTOR_LAYOUT, + DRM_FORMAT_MOD_NVIDIA_16BX2_BLOCK(1) | DRM_FORMAT_MOD_NVIDIA_SECTOR_LAYOUT, + DRM_FORMAT_MOD_NVIDIA_16BX2_BLOCK(2) | DRM_FORMAT_MOD_NVIDIA_SECTOR_LAYOUT, + DRM_FORMAT_MOD_NVIDIA_16BX2_BLOCK(3) | DRM_FORMAT_MOD_NVIDIA_SECTOR_LAYOUT, + DRM_FORMAT_MOD_NVIDIA_16BX2_BLOCK(4) | DRM_FORMAT_MOD_NVIDIA_SECTOR_LAYOUT, + DRM_FORMAT_MOD_NVIDIA_16BX2_BLOCK(5) | DRM_FORMAT_MOD_NVIDIA_SECTOR_LAYOUT, + /* sentinel */ DRM_FORMAT_MOD_INVALID }; @@ -366,6 +378,12 @@ static int tegra_shared_plane_atomic_check(struct drm_plane *plane, return -EINVAL; } + if (tiling->sector_layout == TEGRA_BO_SECTOR_LAYOUT_GPU && + !dc->soc->supports_sector_layout) { + DRM_ERROR("hardware doesn't support GPU sector layout\n"); + return -EINVAL; + } + /* * Tegra doesn't support different strides for U and V planes so we * error out if the user tries to display a framebuffer with such a @@ -485,6 +503,16 @@ static void tegra_shared_plane_atomic_update(struct drm_plane *plane, base = tegra_plane_state->iova[0] + fb->offsets[0]; +#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT + /* + * Physical address bit 39 in Tegra194 is used as a switch for special + * logic that swizzles the memory using either the legacy Tegra or the + * dGPU sector layout. + */ + if (tegra_plane_state->tiling.sector_layout == TEGRA_BO_SECTOR_LAYOUT_GPU) + base |= BIT(39); +#endif + tegra_plane_writel(p, tegra_plane_state->format, DC_WIN_COLOR_DEPTH); tegra_plane_writel(p, 0, DC_WIN_PRECOMP_WGRP_PARAMS); @@ -562,9 +590,8 @@ struct drm_plane *tegra_shared_plane_create(struct drm_device *drm, enum drm_plane_type type = DRM_PLANE_TYPE_OVERLAY; struct tegra_drm *tegra = drm->dev_private; struct tegra_display_hub *hub = tegra->hub; - /* planes can be assigned to arbitrary CRTCs */ - unsigned int possible_crtcs = 0x7; struct tegra_shared_plane *plane; + unsigned int possible_crtcs; unsigned int num_formats; const u64 *modifiers; struct drm_plane *p; @@ -583,6 +610,9 @@ struct drm_plane *tegra_shared_plane_create(struct drm_device *drm, p = &plane->base.base; + /* planes can be assigned to arbitrary CRTCs */ + possible_crtcs = BIT(tegra->num_crtcs) - 1; + num_formats = ARRAY_SIZE(tegra_shared_plane_formats); formats = tegra_shared_plane_formats; modifiers = tegra_shared_plane_modifiers; @@ -848,12 +878,19 @@ static const struct host1x_client_ops tegra_display_hub_ops = { static int tegra_display_hub_probe(struct platform_device *pdev) { + u64 dma_mask = dma_get_mask(pdev->dev.parent); struct device_node *child = NULL; struct tegra_display_hub *hub; struct clk *clk; unsigned int i; int err; + err = dma_coerce_mask_and_coherent(&pdev->dev, dma_mask); + if (err < 0) { + dev_err(&pdev->dev, "failed to set DMA mask: %d\n", err); + return err; + } + hub = devm_kzalloc(&pdev->dev, sizeof(*hub), GFP_KERNEL); if (!hub) return -ENOMEM; diff --git a/drivers/gpu/drm/tegra/plane.c b/drivers/gpu/drm/tegra/plane.c index 19e8847a164b..2e11b4b1f702 100644 --- a/drivers/gpu/drm/tegra/plane.c +++ b/drivers/gpu/drm/tegra/plane.c @@ -83,6 +83,22 @@ static void tegra_plane_atomic_destroy_state(struct drm_plane *plane, kfree(state); } +static bool tegra_plane_supports_sector_layout(struct drm_plane *plane) +{ + struct drm_crtc *crtc; + + drm_for_each_crtc(crtc, plane->dev) { + if (plane->possible_crtcs & drm_crtc_mask(crtc)) { + struct tegra_dc *dc = to_tegra_dc(crtc); + + if (!dc->soc->supports_sector_layout) + return false; + } + } + + return true; +} + static bool tegra_plane_format_mod_supported(struct drm_plane *plane, uint32_t format, uint64_t modifier) @@ -92,6 +108,14 @@ static bool tegra_plane_format_mod_supported(struct drm_plane *plane, if (modifier == DRM_FORMAT_MOD_LINEAR) return true; + /* check for the sector layout bit */ + if ((modifier >> 56) == DRM_FORMAT_MOD_VENDOR_NVIDIA) { + if (modifier & DRM_FORMAT_MOD_NVIDIA_SECTOR_LAYOUT) { + if (!tegra_plane_supports_sector_layout(plane)) + return false; + } + } + if (info->num_planes == 1) return true; @@ -119,6 +143,14 @@ static int tegra_dc_pin(struct tegra_dc *dc, struct tegra_plane_state *state) dma_addr_t phys_addr, *phys; struct sg_table *sgt; + /* + * If we're not attached to a domain, we already stored the + * physical address when the buffer was allocated. If we're + * part of a group that's shared between all display + * controllers, we've also already mapped the framebuffer + * through the SMMU. In both cases we can short-circuit the + * code below and retrieve the stored IOV address. + */ if (!domain || dc->client.group) phys = &phys_addr; else diff --git a/drivers/gpu/drm/tegra/sor.c b/drivers/gpu/drm/tegra/sor.c index f02a035dda45..7b88261f57bb 100644 --- a/drivers/gpu/drm/tegra/sor.c +++ b/drivers/gpu/drm/tegra/sor.c @@ -3115,6 +3115,12 @@ static int tegra_sor_init(struct host1x_client *client) * kernel is possible. */ if (sor->rst) { + err = pm_runtime_resume_and_get(sor->dev); + if (err < 0) { + dev_err(sor->dev, "failed to get runtime PM: %d\n", err); + return err; + } + err = reset_control_acquire(sor->rst); if (err < 0) { dev_err(sor->dev, "failed to acquire SOR reset: %d\n", @@ -3148,6 +3154,7 @@ static int tegra_sor_init(struct host1x_client *client) } reset_control_release(sor->rst); + pm_runtime_put(sor->dev); } err = clk_prepare_enable(sor->clk_safe); diff --git a/drivers/gpu/drm/tegra/vic.c b/drivers/gpu/drm/tegra/vic.c index 77e128832920..72aea1cc0cfa 100644 --- a/drivers/gpu/drm/tegra/vic.c +++ b/drivers/gpu/drm/tegra/vic.c @@ -214,7 +214,7 @@ static int vic_init(struct host1x_client *client) return 0; free_syncpt: - host1x_syncpt_free(client->syncpts[0]); + host1x_syncpt_put(client->syncpts[0]); free_channel: host1x_channel_put(vic->channel); detach: @@ -238,7 +238,7 @@ static int vic_exit(struct host1x_client *client) if (err < 0) return err; - host1x_syncpt_free(client->syncpts[0]); + host1x_syncpt_put(client->syncpts[0]); host1x_channel_put(vic->channel); host1x_client_iommu_detach(client); diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c index 6ab7b66ce36d..cfd0b9292397 100644 --- a/drivers/gpu/drm/ttm/ttm_bo.c +++ b/drivers/gpu/drm/ttm/ttm_bo.c @@ -705,8 +705,9 @@ static int ttm_bo_add_move_fence(struct ttm_buffer_object *bo, return 0; if (no_wait_gpu) { + ret = dma_fence_is_signaled(fence) ? 0 : -EBUSY; dma_fence_put(fence); - return -EBUSY; + return ret; } dma_resv_add_shared_fence(bo->base.resv, fence); diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c index a2a17c84ceb3..efb7e9c34ab4 100644 --- a/drivers/gpu/drm/ttm/ttm_bo_util.c +++ b/drivers/gpu/drm/ttm/ttm_bo_util.c @@ -91,6 +91,10 @@ static int ttm_resource_ioremap(struct ttm_device *bdev, if (mem->bus.caching == ttm_write_combined) addr = ioremap_wc(mem->bus.offset, bus_size); +#ifdef CONFIG_X86 + else if (mem->bus.caching == ttm_cached) + addr = ioremap_cache(mem->bus.offset, bus_size); +#endif else addr = ioremap(mem->bus.offset, bus_size); if (!addr) { @@ -371,6 +375,11 @@ static int ttm_bo_ioremap(struct ttm_buffer_object *bo, if (mem->bus.caching == ttm_write_combined) map->virtual = ioremap_wc(bo->mem.bus.offset + offset, size); +#ifdef CONFIG_X86 + else if (mem->bus.caching == ttm_cached) + map->virtual = ioremap_cache(bo->mem.bus.offset + offset, + size); +#endif else map->virtual = ioremap(bo->mem.bus.offset + offset, size); @@ -489,6 +498,11 @@ int ttm_bo_vmap(struct ttm_buffer_object *bo, struct dma_buf_map *map) else if (mem->bus.caching == ttm_write_combined) vaddr_iomem = ioremap_wc(mem->bus.offset, bo->base.size); +#ifdef CONFIG_X86 + else if (mem->bus.caching == ttm_cached) + vaddr_iomem = ioremap_cache(mem->bus.offset, + bo->base.size); +#endif else vaddr_iomem = ioremap(mem->bus.offset, bo->base.size); diff --git a/drivers/gpu/drm/vc4/vc4_crtc.c b/drivers/gpu/drm/vc4/vc4_crtc.c index 269390bc586e..76657dcdf9b0 100644 --- a/drivers/gpu/drm/vc4/vc4_crtc.c +++ b/drivers/gpu/drm/vc4/vc4_crtc.c @@ -210,6 +210,7 @@ static u32 vc4_get_fifo_full_level(struct vc4_crtc *vc4_crtc, u32 format) { const struct vc4_crtc_data *crtc_data = vc4_crtc_to_vc4_crtc_data(vc4_crtc); const struct vc4_pv_data *pv_data = vc4_crtc_to_vc4_pv_data(vc4_crtc); + struct vc4_dev *vc4 = to_vc4_dev(vc4_crtc->base.dev); u32 fifo_len_bytes = pv_data->fifo_depth; /* @@ -238,6 +239,22 @@ static u32 vc4_get_fifo_full_level(struct vc4_crtc *vc4_crtc, u32 format) if (crtc_data->hvs_output == 5) return 32; + /* + * It looks like in some situations, we will overflow + * the PixelValve FIFO (with the bit 10 of PV stat being + * set) and stall the HVS / PV, eventually resulting in + * a page flip timeout. + * + * Displaying the video overlay during a playback with + * Kodi on an RPi3 seems to be a great solution with a + * failure rate around 50%. + * + * Removing 1 from the FIFO full level however + * seems to completely remove that issue. + */ + if (!vc4->hvs->hvs5) + return fifo_len_bytes - 3 * HVS_FIFO_LATENCY_PIX - 1; + return fifo_len_bytes - 3 * HVS_FIFO_LATENCY_PIX; } } diff --git a/drivers/gpu/drm/vc4/vc4_plane.c b/drivers/gpu/drm/vc4/vc4_plane.c index c76e73a452e0..19161b6ab27f 100644 --- a/drivers/gpu/drm/vc4/vc4_plane.c +++ b/drivers/gpu/drm/vc4/vc4_plane.c @@ -1150,7 +1150,6 @@ static void vc4_plane_atomic_async_update(struct drm_plane *plane, plane->state->src_y = new_plane_state->src_y; plane->state->src_w = new_plane_state->src_w; plane->state->src_h = new_plane_state->src_h; - plane->state->src_h = new_plane_state->src_h; plane->state->alpha = new_plane_state->alpha; plane->state->pixel_blend_mode = new_plane_state->pixel_blend_mode; plane->state->rotation = new_plane_state->rotation; diff --git a/drivers/gpu/drm/xen/xen_drm_front.c b/drivers/gpu/drm/xen/xen_drm_front.c index 30d9adf31c84..9f14d99c763c 100644 --- a/drivers/gpu/drm/xen/xen_drm_front.c +++ b/drivers/gpu/drm/xen/xen_drm_front.c @@ -521,7 +521,7 @@ static int xen_drm_drv_init(struct xen_drm_front_info *front_info) drm_dev = drm_dev_alloc(&xen_drm_driver, dev); if (IS_ERR(drm_dev)) { ret = PTR_ERR(drm_dev); - goto fail; + goto fail_dev; } drm_info->drm_dev = drm_dev; @@ -551,8 +551,10 @@ fail_modeset: drm_kms_helper_poll_fini(drm_dev); drm_mode_config_cleanup(drm_dev); drm_dev_put(drm_dev); -fail: +fail_dev: kfree(drm_info); + front_info->drm_info = NULL; +fail: return ret; } diff --git a/drivers/gpu/drm/xen/xen_drm_front_conn.h b/drivers/gpu/drm/xen/xen_drm_front_conn.h index 3adacba9a23b..e5f4314899ee 100644 --- a/drivers/gpu/drm/xen/xen_drm_front_conn.h +++ b/drivers/gpu/drm/xen/xen_drm_front_conn.h @@ -16,7 +16,6 @@ struct drm_connector; struct xen_drm_front_drm_info; -struct xen_drm_front_drm_info; int xen_drm_front_conn_init(struct xen_drm_front_drm_info *drm_info, struct drm_connector *connector); diff --git a/drivers/gpu/drm/xlnx/zynqmp_dp.c b/drivers/gpu/drm/xlnx/zynqmp_dp.c index 99158ee67d02..59d1fb017da0 100644 --- a/drivers/gpu/drm/xlnx/zynqmp_dp.c +++ b/drivers/gpu/drm/xlnx/zynqmp_dp.c @@ -866,7 +866,7 @@ static int zynqmp_dp_train(struct zynqmp_dp *dp) return ret; zynqmp_dp_write(dp, ZYNQMP_DP_SCRAMBLING_DISABLE, 1); - memset(dp->train_set, 0, 4); + memset(dp->train_set, 0, sizeof(dp->train_set)); ret = zynqmp_dp_link_train_cr(dp); if (ret) return ret; diff --git a/drivers/gpu/host1x/bus.c b/drivers/gpu/host1x/bus.c index 347fb962b6c9..46f69c532b6b 100644 --- a/drivers/gpu/host1x/bus.c +++ b/drivers/gpu/host1x/bus.c @@ -197,6 +197,17 @@ int host1x_device_init(struct host1x_device *device) mutex_lock(&device->clients_lock); list_for_each_entry(client, &device->clients, list) { + if (client->ops && client->ops->early_init) { + err = client->ops->early_init(client); + if (err < 0) { + dev_err(&device->dev, "failed to early initialize %s: %d\n", + dev_name(client->dev), err); + goto teardown_late; + } + } + } + + list_for_each_entry(client, &device->clients, list) { if (client->ops && client->ops->init) { err = client->ops->init(client); if (err < 0) { @@ -217,6 +228,14 @@ teardown: if (client->ops->exit) client->ops->exit(client); + /* reset client to end of list for late teardown */ + client = list_entry(&device->clients, struct host1x_client, list); + +teardown_late: + list_for_each_entry_continue_reverse(client, &device->clients, list) + if (client->ops->late_exit) + client->ops->late_exit(client); + mutex_unlock(&device->clients_lock); return err; } @@ -251,6 +270,18 @@ int host1x_device_exit(struct host1x_device *device) } } + list_for_each_entry_reverse(client, &device->clients, list) { + if (client->ops && client->ops->late_exit) { + err = client->ops->late_exit(client); + if (err < 0) { + dev_err(&device->dev, "failed to late cleanup %s: %d\n", + dev_name(client->dev), err); + mutex_unlock(&device->clients_lock); + return err; + } + } + } + mutex_unlock(&device->clients_lock); return 0; @@ -705,8 +736,9 @@ void host1x_driver_unregister(struct host1x_driver *driver) EXPORT_SYMBOL(host1x_driver_unregister); /** - * host1x_client_register() - register a host1x client + * __host1x_client_register() - register a host1x client * @client: host1x client + * @key: lock class key for the client-specific mutex * * Registers a host1x client with each host1x controller instance. Note that * each client will only match their parent host1x controller and will only be @@ -715,13 +747,14 @@ EXPORT_SYMBOL(host1x_driver_unregister); * device and call host1x_device_init(), which will in turn call each client's * &host1x_client_ops.init implementation. */ -int host1x_client_register(struct host1x_client *client) +int __host1x_client_register(struct host1x_client *client, + struct lock_class_key *key) { struct host1x *host1x; int err; INIT_LIST_HEAD(&client->list); - mutex_init(&client->lock); + __mutex_init(&client->lock, "host1x client lock", key); client->usecount = 0; mutex_lock(&devices_lock); @@ -742,7 +775,7 @@ int host1x_client_register(struct host1x_client *client) return 0; } -EXPORT_SYMBOL(host1x_client_register); +EXPORT_SYMBOL(__host1x_client_register); /** * host1x_client_unregister() - unregister a host1x client diff --git a/drivers/gpu/host1x/cdma.c b/drivers/gpu/host1x/cdma.c index e8d3fda91d8a..6e6ca774f68d 100644 --- a/drivers/gpu/host1x/cdma.c +++ b/drivers/gpu/host1x/cdma.c @@ -273,15 +273,13 @@ static int host1x_cdma_wait_pushbuffer_space(struct host1x *host1x, static void cdma_start_timer_locked(struct host1x_cdma *cdma, struct host1x_job *job) { - struct host1x *host = cdma_to_host1x(cdma); - if (cdma->timeout.client) { /* timer already started */ return; } cdma->timeout.client = job->client; - cdma->timeout.syncpt = host1x_syncpt_get(host, job->syncpt_id); + cdma->timeout.syncpt = job->syncpt; cdma->timeout.syncpt_val = job->syncpt_end; cdma->timeout.start_ktime = ktime_get(); @@ -312,7 +310,6 @@ static void stop_cdma_timer_locked(struct host1x_cdma *cdma) static void update_cdma_locked(struct host1x_cdma *cdma) { bool signal = false; - struct host1x *host1x = cdma_to_host1x(cdma); struct host1x_job *job, *n; /* If CDMA is stopped, queue is cleared and we can return */ @@ -324,8 +321,7 @@ static void update_cdma_locked(struct host1x_cdma *cdma) * to consume as many sync queue entries as possible without blocking */ list_for_each_entry_safe(job, n, &cdma->sync_queue, list) { - struct host1x_syncpt *sp = - host1x_syncpt_get(host1x, job->syncpt_id); + struct host1x_syncpt *sp = job->syncpt; /* Check whether this syncpt has completed, and bail if not */ if (!host1x_syncpt_is_expired(sp, job->syncpt_end)) { @@ -499,8 +495,7 @@ int host1x_cdma_begin(struct host1x_cdma *cdma, struct host1x_job *job) if (!cdma->timeout.initialized) { int err; - err = host1x_hw_cdma_timeout_init(host1x, cdma, - job->syncpt_id); + err = host1x_hw_cdma_timeout_init(host1x, cdma); if (err) { mutex_unlock(&cdma->lock); return err; diff --git a/drivers/gpu/host1x/debug.c b/drivers/gpu/host1x/debug.c index 1b4997bda1c7..8a14880c61bb 100644 --- a/drivers/gpu/host1x/debug.c +++ b/drivers/gpu/host1x/debug.c @@ -69,6 +69,7 @@ static int show_channel(struct host1x_channel *ch, void *data, bool show_fifo) static void show_syncpts(struct host1x *m, struct output *o) { + struct list_head *pos; unsigned int i; host1x_debug_output(o, "---- syncpts ----\n"); @@ -76,12 +77,19 @@ static void show_syncpts(struct host1x *m, struct output *o) for (i = 0; i < host1x_syncpt_nb_pts(m); i++) { u32 max = host1x_syncpt_read_max(m->syncpt + i); u32 min = host1x_syncpt_load(m->syncpt + i); + unsigned int waiters = 0; - if (!min && !max) + spin_lock(&m->syncpt[i].intr.lock); + list_for_each(pos, &m->syncpt[i].intr.wait_head) + waiters++; + spin_unlock(&m->syncpt[i].intr.lock); + + if (!min && !max && !waiters) continue; - host1x_debug_output(o, "id %u (%s) min %d max %d\n", - i, m->syncpt[i].name, min, max); + host1x_debug_output(o, + "id %u (%s) min %d max %d (%d waiters)\n", + i, m->syncpt[i].name, min, max, waiters); } for (i = 0; i < host1x_syncpt_nb_bases(m); i++) { diff --git a/drivers/gpu/host1x/dev.c b/drivers/gpu/host1x/dev.c index d0ebb70e2fdd..fbb6447b8659 100644 --- a/drivers/gpu/host1x/dev.c +++ b/drivers/gpu/host1x/dev.c @@ -77,6 +77,7 @@ static const struct host1x_info host1x01_info = { .has_hypervisor = false, .num_sid_entries = 0, .sid_table = NULL, + .reserve_vblank_syncpts = true, }; static const struct host1x_info host1x02_info = { @@ -91,6 +92,7 @@ static const struct host1x_info host1x02_info = { .has_hypervisor = false, .num_sid_entries = 0, .sid_table = NULL, + .reserve_vblank_syncpts = true, }; static const struct host1x_info host1x04_info = { @@ -105,6 +107,7 @@ static const struct host1x_info host1x04_info = { .has_hypervisor = false, .num_sid_entries = 0, .sid_table = NULL, + .reserve_vblank_syncpts = false, }; static const struct host1x_info host1x05_info = { @@ -119,6 +122,7 @@ static const struct host1x_info host1x05_info = { .has_hypervisor = false, .num_sid_entries = 0, .sid_table = NULL, + .reserve_vblank_syncpts = false, }; static const struct host1x_sid_entry tegra186_sid_table[] = { @@ -142,6 +146,7 @@ static const struct host1x_info host1x06_info = { .has_hypervisor = true, .num_sid_entries = ARRAY_SIZE(tegra186_sid_table), .sid_table = tegra186_sid_table, + .reserve_vblank_syncpts = false, }; static const struct host1x_sid_entry tegra194_sid_table[] = { @@ -165,6 +170,7 @@ static const struct host1x_info host1x07_info = { .has_hypervisor = true, .num_sid_entries = ARRAY_SIZE(tegra194_sid_table), .sid_table = tegra194_sid_table, + .reserve_vblank_syncpts = false, }; static const struct of_device_id host1x_of_match[] = { diff --git a/drivers/gpu/host1x/dev.h b/drivers/gpu/host1x/dev.h index f781a9b0f39d..fa6d4bc46e98 100644 --- a/drivers/gpu/host1x/dev.h +++ b/drivers/gpu/host1x/dev.h @@ -37,7 +37,7 @@ struct host1x_cdma_ops { void (*start)(struct host1x_cdma *cdma); void (*stop)(struct host1x_cdma *cdma); void (*flush)(struct host1x_cdma *cdma); - int (*timeout_init)(struct host1x_cdma *cdma, unsigned int syncpt); + int (*timeout_init)(struct host1x_cdma *cdma); void (*timeout_destroy)(struct host1x_cdma *cdma); void (*freeze)(struct host1x_cdma *cdma); void (*resume)(struct host1x_cdma *cdma, u32 getptr); @@ -101,6 +101,12 @@ struct host1x_info { bool has_hypervisor; /* has hypervisor registers */ unsigned int num_sid_entries; const struct host1x_sid_entry *sid_table; + /* + * On T20-T148, the boot chain may setup DC to increment syncpoints + * 26/27 on VBLANK. As such we cannot use these syncpoints until + * the display driver disables VBLANK increments. + */ + bool reserve_vblank_syncpts; }; struct host1x { @@ -261,10 +267,9 @@ static inline void host1x_hw_cdma_flush(struct host1x *host, } static inline int host1x_hw_cdma_timeout_init(struct host1x *host, - struct host1x_cdma *cdma, - unsigned int syncpt) + struct host1x_cdma *cdma) { - return host->cdma_op->timeout_init(cdma, syncpt); + return host->cdma_op->timeout_init(cdma); } static inline void host1x_hw_cdma_timeout_destroy(struct host1x *host, diff --git a/drivers/gpu/host1x/hw/cdma_hw.c b/drivers/gpu/host1x/hw/cdma_hw.c index 2f3bf94cf365..e49cd5b8f735 100644 --- a/drivers/gpu/host1x/hw/cdma_hw.c +++ b/drivers/gpu/host1x/hw/cdma_hw.c @@ -295,7 +295,7 @@ static void cdma_timeout_handler(struct work_struct *work) /* * Init timeout resources */ -static int cdma_timeout_init(struct host1x_cdma *cdma, unsigned int syncpt) +static int cdma_timeout_init(struct host1x_cdma *cdma) { INIT_DELAYED_WORK(&cdma->timeout.wq, cdma_timeout_handler); cdma->timeout.initialized = true; diff --git a/drivers/gpu/host1x/hw/channel_hw.c b/drivers/gpu/host1x/hw/channel_hw.c index 5eaa29d171c9..d4c28faf27d1 100644 --- a/drivers/gpu/host1x/hw/channel_hw.c +++ b/drivers/gpu/host1x/hw/channel_hw.c @@ -86,8 +86,7 @@ static void submit_gathers(struct host1x_job *job) static inline void synchronize_syncpt_base(struct host1x_job *job) { - struct host1x *host = dev_get_drvdata(job->channel->dev->parent); - struct host1x_syncpt *sp = host->syncpt + job->syncpt_id; + struct host1x_syncpt *sp = job->syncpt; unsigned int id; u32 value; @@ -118,7 +117,7 @@ static void host1x_channel_set_streamid(struct host1x_channel *channel) static int channel_submit(struct host1x_job *job) { struct host1x_channel *ch = job->channel; - struct host1x_syncpt *sp; + struct host1x_syncpt *sp = job->syncpt; u32 user_syncpt_incrs = job->syncpt_incrs; u32 prev_max = 0; u32 syncval; @@ -126,10 +125,9 @@ static int channel_submit(struct host1x_job *job) struct host1x_waitlist *completed_waiter = NULL; struct host1x *host = dev_get_drvdata(ch->dev->parent); - sp = host->syncpt + job->syncpt_id; trace_host1x_channel_submit(dev_name(ch->dev), job->num_gathers, job->num_relocs, - job->syncpt_id, job->syncpt_incrs); + job->syncpt->id, job->syncpt_incrs); /* before error checks, return current max */ prev_max = job->syncpt_end = host1x_syncpt_read_max(sp); @@ -163,7 +161,7 @@ static int channel_submit(struct host1x_job *job) host1x_cdma_push(&ch->cdma, host1x_opcode_setclass(HOST1X_CLASS_HOST1X, host1x_uclass_wait_syncpt_r(), 1), - host1x_class_host_wait_syncpt(job->syncpt_id, + host1x_class_host_wait_syncpt(job->syncpt->id, host1x_syncpt_read_max(sp))); } diff --git a/drivers/gpu/host1x/hw/debug_hw.c b/drivers/gpu/host1x/hw/debug_hw.c index f31bcfa1b837..ceb48229d14b 100644 --- a/drivers/gpu/host1x/hw/debug_hw.c +++ b/drivers/gpu/host1x/hw/debug_hw.c @@ -204,7 +204,7 @@ static void show_channel_gathers(struct output *o, struct host1x_cdma *cdma) unsigned int i; host1x_debug_output(o, "\n%p: JOB, syncpt_id=%d, syncpt_val=%d, first_get=%08x, timeout=%d num_slots=%d, num_handles=%d\n", - job, job->syncpt_id, job->syncpt_end, + job, job->syncpt->id, job->syncpt_end, job->first_get, job->timeout, job->num_slots, job->num_unpins); diff --git a/drivers/gpu/host1x/hw/hw_host1x07_vm.h b/drivers/gpu/host1x/hw/hw_host1x07_vm.h index 3058b3c9a91d..b766851d5b83 100644 --- a/drivers/gpu/host1x/hw/hw_host1x07_vm.h +++ b/drivers/gpu/host1x/hw/hw_host1x07_vm.h @@ -29,6 +29,6 @@ #define HOST1X_SYNC_SYNCPT_THRESH_INT_ENABLE_CPU0(x) (0x652c + 4 * (x)) #define HOST1X_SYNC_SYNCPT_THRESH_INT_DISABLE(x) (0x6590 + 4 * (x)) #define HOST1X_SYNC_SYNCPT(x) (0x8080 + 4 * (x)) -#define HOST1X_SYNC_SYNCPT_INT_THRESH(x) (0x8d00 + 4 * (x)) +#define HOST1X_SYNC_SYNCPT_INT_THRESH(x) (0x9980 + 4 * (x)) #define HOST1X_SYNC_SYNCPT_CH_APP(x) (0xa604 + 4 * (x)) #define HOST1X_SYNC_SYNCPT_CH_APP_CH(v) (((v) & 0x3f) << 8) diff --git a/drivers/gpu/host1x/intr.c b/drivers/gpu/host1x/intr.c index 9245add23b5d..6d1f3c0fdbe7 100644 --- a/drivers/gpu/host1x/intr.c +++ b/drivers/gpu/host1x/intr.c @@ -235,25 +235,37 @@ int host1x_intr_add_action(struct host1x *host, struct host1x_syncpt *syncpt, host1x_hw_intr_enable_syncpt_intr(host, syncpt->id); } - spin_unlock(&syncpt->intr.lock); - if (ref) *ref = waiter; + + spin_unlock(&syncpt->intr.lock); + return 0; } -void host1x_intr_put_ref(struct host1x *host, unsigned int id, void *ref) +void host1x_intr_put_ref(struct host1x *host, unsigned int id, void *ref, + bool flush) { struct host1x_waitlist *waiter = ref; struct host1x_syncpt *syncpt; - while (atomic_cmpxchg(&waiter->state, WLS_PENDING, WLS_CANCELLED) == - WLS_REMOVED) - schedule(); + atomic_cmpxchg(&waiter->state, WLS_PENDING, WLS_CANCELLED); syncpt = host->syncpt + id; - (void)process_wait_list(host, syncpt, - host1x_syncpt_load(host->syncpt + id)); + + spin_lock(&syncpt->intr.lock); + if (atomic_cmpxchg(&waiter->state, WLS_CANCELLED, WLS_HANDLED) == + WLS_CANCELLED) { + list_del(&waiter->list); + kref_put(&waiter->refcount, waiter_release); + } + spin_unlock(&syncpt->intr.lock); + + if (flush) { + /* Wait until any concurrently executing handler has finished. */ + while (atomic_read(&waiter->state) != WLS_HANDLED) + schedule(); + } kref_put(&waiter->refcount, waiter_release); } diff --git a/drivers/gpu/host1x/intr.h b/drivers/gpu/host1x/intr.h index aac38194398f..6ea55e615e3a 100644 --- a/drivers/gpu/host1x/intr.h +++ b/drivers/gpu/host1x/intr.h @@ -74,8 +74,10 @@ int host1x_intr_add_action(struct host1x *host, struct host1x_syncpt *syncpt, * Unreference an action submitted to host1x_intr_add_action(). * You must call this if you passed non-NULL as ref. * @ref the ref returned from host1x_intr_add_action() + * @flush wait until any pending handlers have completed before returning. */ -void host1x_intr_put_ref(struct host1x *host, unsigned int id, void *ref); +void host1x_intr_put_ref(struct host1x *host, unsigned int id, void *ref, + bool flush); /* Initialize host1x sync point interrupt */ int host1x_intr_init(struct host1x *host, unsigned int irq_sync); diff --git a/drivers/gpu/host1x/job.c b/drivers/gpu/host1x/job.c index 82d0a60ba3f7..adbdc225de8d 100644 --- a/drivers/gpu/host1x/job.c +++ b/drivers/gpu/host1x/job.c @@ -79,6 +79,9 @@ static void job_free(struct kref *ref) { struct host1x_job *job = container_of(ref, struct host1x_job, ref); + if (job->syncpt) + host1x_syncpt_put(job->syncpt); + kfree(job); } @@ -674,7 +677,7 @@ EXPORT_SYMBOL(host1x_job_unpin); */ void host1x_job_dump(struct device *dev, struct host1x_job *job) { - dev_dbg(dev, " SYNCPT_ID %d\n", job->syncpt_id); + dev_dbg(dev, " SYNCPT_ID %d\n", job->syncpt->id); dev_dbg(dev, " SYNCPT_VAL %d\n", job->syncpt_end); dev_dbg(dev, " FIRST_GET 0x%x\n", job->first_get); dev_dbg(dev, " TIMEOUT %d\n", job->timeout); diff --git a/drivers/gpu/host1x/syncpt.c b/drivers/gpu/host1x/syncpt.c index fce7892d5137..e648ebbb2027 100644 --- a/drivers/gpu/host1x/syncpt.c +++ b/drivers/gpu/host1x/syncpt.c @@ -42,17 +42,32 @@ static void host1x_syncpt_base_free(struct host1x_syncpt_base *base) base->requested = false; } -static struct host1x_syncpt *host1x_syncpt_alloc(struct host1x *host, - struct host1x_client *client, - unsigned long flags) +/** + * host1x_syncpt_alloc() - allocate a syncpoint + * @host: host1x device data + * @flags: bitfield of HOST1X_SYNCPT_* flags + * @name: name for the syncpoint for use in debug prints + * + * Allocates a hardware syncpoint for the caller's use. The caller then has + * the sole authority to mutate the syncpoint's value until it is freed again. + * + * If no free syncpoints are available, or a NULL name was specified, returns + * NULL. + */ +struct host1x_syncpt *host1x_syncpt_alloc(struct host1x *host, + unsigned long flags, + const char *name) { struct host1x_syncpt *sp = host->syncpt; + char *full_name; unsigned int i; - char *name; + + if (!name) + return NULL; mutex_lock(&host->syncpt_mutex); - for (i = 0; i < host->info->nb_pts && sp->name; i++, sp++) + for (i = 0; i < host->info->nb_pts && kref_read(&sp->ref); i++, sp++) ; if (i >= host->info->nb_pts) @@ -64,19 +79,19 @@ static struct host1x_syncpt *host1x_syncpt_alloc(struct host1x *host, goto unlock; } - name = kasprintf(GFP_KERNEL, "%02u-%s", sp->id, - client ? dev_name(client->dev) : NULL); - if (!name) + full_name = kasprintf(GFP_KERNEL, "%u-%s", sp->id, name); + if (!full_name) goto free_base; - sp->client = client; - sp->name = name; + sp->name = full_name; if (flags & HOST1X_SYNCPT_CLIENT_MANAGED) sp->client_managed = true; else sp->client_managed = false; + kref_init(&sp->ref); + mutex_unlock(&host->syncpt_mutex); return sp; @@ -87,6 +102,7 @@ unlock: mutex_unlock(&host->syncpt_mutex); return NULL; } +EXPORT_SYMBOL(host1x_syncpt_alloc); /** * host1x_syncpt_id() - retrieve syncpoint ID @@ -294,7 +310,7 @@ int host1x_syncpt_wait(struct host1x_syncpt *sp, u32 thresh, long timeout, } } - host1x_intr_put_ref(sp->host, sp->id, ref); + host1x_intr_put_ref(sp->host, sp->id, ref, true); done: return err; @@ -307,59 +323,12 @@ EXPORT_SYMBOL(host1x_syncpt_wait); bool host1x_syncpt_is_expired(struct host1x_syncpt *sp, u32 thresh) { u32 current_val; - u32 future_val; smp_rmb(); current_val = (u32)atomic_read(&sp->min_val); - future_val = (u32)atomic_read(&sp->max_val); - - /* Note the use of unsigned arithmetic here (mod 1<<32). - * - * c = current_val = min_val = the current value of the syncpoint. - * t = thresh = the value we are checking - * f = future_val = max_val = the value c will reach when all - * outstanding increments have completed. - * - * Note that c always chases f until it reaches f. - * - * Dtf = (f - t) - * Dtc = (c - t) - * - * Consider all cases: - * - * A) .....c..t..f..... Dtf < Dtc need to wait - * B) .....c.....f..t.. Dtf > Dtc expired - * C) ..t..c.....f..... Dtf > Dtc expired (Dct very large) - * - * Any case where f==c: always expired (for any t). Dtf == Dcf - * Any case where t==c: always expired (for any f). Dtf >= Dtc (because Dtc==0) - * Any case where t==f!=c: always wait. Dtf < Dtc (because Dtf==0, - * Dtc!=0) - * - * Other cases: - * - * A) .....t..f..c..... Dtf < Dtc need to wait - * A) .....f..c..t..... Dtf < Dtc need to wait - * A) .....f..t..c..... Dtf > Dtc expired - * - * So: - * Dtf >= Dtc implies EXPIRED (return true) - * Dtf < Dtc implies WAIT (return false) - * - * Note: If t is expired then we *cannot* wait on it. We would wait - * forever (hang the system). - * - * Note: do NOT get clever and remove the -thresh from both sides. It - * is NOT the same. - * - * If future valueis zero, we have a client managed sync point. In that - * case we do a direct comparison. - */ - if (!host1x_syncpt_client_managed(sp)) - return future_val - thresh >= current_val - thresh; - else - return (s32)(current_val - thresh) >= 0; + + return ((current_val - thresh) & 0x80000000U) == 0U; } int host1x_syncpt_init(struct host1x *host) @@ -401,10 +370,15 @@ int host1x_syncpt_init(struct host1x *host) host1x_hw_syncpt_enable_protection(host); /* Allocate sync point to use for clearing waits for expired fences */ - host->nop_sp = host1x_syncpt_alloc(host, NULL, 0); + host->nop_sp = host1x_syncpt_alloc(host, 0, "reserved-nop"); if (!host->nop_sp) return -ENOMEM; + if (host->info->reserve_vblank_syncpts) { + kref_init(&host->syncpt[26].ref); + kref_init(&host->syncpt[27].ref); + } + return 0; } @@ -416,44 +390,50 @@ int host1x_syncpt_init(struct host1x *host) * host1x client drivers can use this function to allocate a syncpoint for * subsequent use. A syncpoint returned by this function will be reserved for * use by the client exclusively. When no longer using a syncpoint, a host1x - * client driver needs to release it using host1x_syncpt_free(). + * client driver needs to release it using host1x_syncpt_put(). */ struct host1x_syncpt *host1x_syncpt_request(struct host1x_client *client, unsigned long flags) { struct host1x *host = dev_get_drvdata(client->host->parent); - return host1x_syncpt_alloc(host, client, flags); + return host1x_syncpt_alloc(host, flags, dev_name(client->dev)); } EXPORT_SYMBOL(host1x_syncpt_request); -/** - * host1x_syncpt_free() - free a requested syncpoint - * @sp: host1x syncpoint - * - * Release a syncpoint previously allocated using host1x_syncpt_request(). A - * host1x client driver should call this when the syncpoint is no longer in - * use. Note that client drivers must ensure that the syncpoint doesn't remain - * under the control of hardware after calling this function, otherwise two - * clients may end up trying to access the same syncpoint concurrently. - */ -void host1x_syncpt_free(struct host1x_syncpt *sp) +static void syncpt_release(struct kref *ref) { - if (!sp) - return; + struct host1x_syncpt *sp = container_of(ref, struct host1x_syncpt, ref); + + atomic_set(&sp->max_val, host1x_syncpt_read(sp)); mutex_lock(&sp->host->syncpt_mutex); host1x_syncpt_base_free(sp->base); kfree(sp->name); sp->base = NULL; - sp->client = NULL; sp->name = NULL; sp->client_managed = false; mutex_unlock(&sp->host->syncpt_mutex); } -EXPORT_SYMBOL(host1x_syncpt_free); + +/** + * host1x_syncpt_put() - free a requested syncpoint + * @sp: host1x syncpoint + * + * Release a syncpoint previously allocated using host1x_syncpt_request(). A + * host1x client driver should call this when the syncpoint is no longer in + * use. + */ +void host1x_syncpt_put(struct host1x_syncpt *sp) +{ + if (!sp) + return; + + kref_put(&sp->ref, syncpt_release); +} +EXPORT_SYMBOL(host1x_syncpt_put); void host1x_syncpt_deinit(struct host1x *host) { @@ -520,16 +500,48 @@ unsigned int host1x_syncpt_nb_mlocks(struct host1x *host) } /** - * host1x_syncpt_get() - obtain a syncpoint by ID + * host1x_syncpt_get_by_id() - obtain a syncpoint by ID * @host: host1x controller * @id: syncpoint ID */ -struct host1x_syncpt *host1x_syncpt_get(struct host1x *host, unsigned int id) +struct host1x_syncpt *host1x_syncpt_get_by_id(struct host1x *host, + unsigned int id) { if (id >= host->info->nb_pts) return NULL; - return host->syncpt + id; + if (kref_get_unless_zero(&host->syncpt[id].ref)) + return &host->syncpt[id]; + else + return NULL; +} +EXPORT_SYMBOL(host1x_syncpt_get_by_id); + +/** + * host1x_syncpt_get_by_id_noref() - obtain a syncpoint by ID but don't + * increase the refcount. + * @host: host1x controller + * @id: syncpoint ID + */ +struct host1x_syncpt *host1x_syncpt_get_by_id_noref(struct host1x *host, + unsigned int id) +{ + if (id >= host->info->nb_pts) + return NULL; + + return &host->syncpt[id]; +} +EXPORT_SYMBOL(host1x_syncpt_get_by_id_noref); + +/** + * host1x_syncpt_get() - increment syncpoint refcount + * @sp: syncpoint + */ +struct host1x_syncpt *host1x_syncpt_get(struct host1x_syncpt *sp) +{ + kref_get(&sp->ref); + + return sp; } EXPORT_SYMBOL(host1x_syncpt_get); @@ -552,3 +564,31 @@ u32 host1x_syncpt_base_id(struct host1x_syncpt_base *base) return base->id; } EXPORT_SYMBOL(host1x_syncpt_base_id); + +static void do_nothing(struct kref *ref) +{ +} + +/** + * host1x_syncpt_release_vblank_reservation() - Make VBLANK syncpoint + * available for allocation + * + * @client: host1x bus client + * @syncpt_id: syncpoint ID to make available + * + * Makes VBLANK<i> syncpoint available for allocatation if it was + * reserved at initialization time. This should be called by the display + * driver after it has ensured that any VBLANK increment programming configured + * by the boot chain has been disabled. + */ +void host1x_syncpt_release_vblank_reservation(struct host1x_client *client, + u32 syncpt_id) +{ + struct host1x *host = dev_get_drvdata(client->host->parent); + + if (!host->info->reserve_vblank_syncpts) + return; + + kref_put(&host->syncpt[syncpt_id].ref, do_nothing); +} +EXPORT_SYMBOL(host1x_syncpt_release_vblank_reservation); diff --git a/drivers/gpu/host1x/syncpt.h b/drivers/gpu/host1x/syncpt.h index 8e1d04dacaa0..a6766f8d55ee 100644 --- a/drivers/gpu/host1x/syncpt.h +++ b/drivers/gpu/host1x/syncpt.h @@ -11,6 +11,7 @@ #include <linux/atomic.h> #include <linux/host1x.h> #include <linux/kernel.h> +#include <linux/kref.h> #include <linux/sched.h> #include "intr.h" @@ -26,6 +27,8 @@ struct host1x_syncpt_base { }; struct host1x_syncpt { + struct kref ref; + unsigned int id; atomic_t min_val; atomic_t max_val; @@ -33,7 +36,6 @@ struct host1x_syncpt { const char *name; bool client_managed; struct host1x *host; - struct host1x_client *client; struct host1x_syncpt_base *base; /* interrupt data */ diff --git a/drivers/i2c/busses/i2c-designware-master.c b/drivers/i2c/busses/i2c-designware-master.c index dd27b9dbe931..873ef38eb1c8 100644 --- a/drivers/i2c/busses/i2c-designware-master.c +++ b/drivers/i2c/busses/i2c-designware-master.c @@ -129,6 +129,7 @@ static int i2c_dw_set_timings_master(struct dw_i2c_dev *dev) if ((comp_param1 & DW_IC_COMP_PARAM_1_SPEED_MODE_MASK) != DW_IC_COMP_PARAM_1_SPEED_MODE_HIGH) { dev_err(dev->dev, "High Speed not supported!\n"); + t->bus_freq_hz = I2C_MAX_FAST_MODE_FREQ; dev->master_cfg &= ~DW_IC_CON_SPEED_MASK; dev->master_cfg |= DW_IC_CON_SPEED_FAST; dev->hs_hcnt = 0; diff --git a/drivers/i2c/busses/i2c-exynos5.c b/drivers/i2c/busses/i2c-exynos5.c index 5ac30d95650c..97d4f3ac0abd 100644 --- a/drivers/i2c/busses/i2c-exynos5.c +++ b/drivers/i2c/busses/i2c-exynos5.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-only -/** +/* * i2c-exynos5.c - Samsung Exynos5 I2C Controller Driver * * Copyright (C) 2013 Samsung Electronics Co., Ltd. diff --git a/drivers/i2c/busses/i2c-hix5hd2.c b/drivers/i2c/busses/i2c-hix5hd2.c index c45f226c2b85..aa00ba8bcb70 100644 --- a/drivers/i2c/busses/i2c-hix5hd2.c +++ b/drivers/i2c/busses/i2c-hix5hd2.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (c) 2014 Linaro Ltd. - * Copyright (c) 2014 Hisilicon Limited. + * Copyright (c) 2014 HiSilicon Limited. * * Now only support 7 bit address. */ diff --git a/drivers/i2c/busses/i2c-jz4780.c b/drivers/i2c/busses/i2c-jz4780.c index 8509c5f11356..55177eb21d7b 100644 --- a/drivers/i2c/busses/i2c-jz4780.c +++ b/drivers/i2c/busses/i2c-jz4780.c @@ -525,8 +525,8 @@ static irqreturn_t jz4780_i2c_irq(int irqno, void *dev_id) i2c_sta = jz4780_i2c_readw(i2c, JZ4780_I2C_STA); data = *i2c->wbuf; data &= ~JZ4780_I2C_DC_READ; - if ((!i2c->stop_hold) && (i2c->cdata->version >= - ID_X1000)) + if ((i2c->wt_len == 1) && (!i2c->stop_hold) && + (i2c->cdata->version >= ID_X1000)) data |= X1000_I2C_DC_STOP; jz4780_i2c_writew(i2c, JZ4780_I2C_DC, data); i2c->wbuf++; diff --git a/drivers/i2c/busses/i2c-stm32f4.c b/drivers/i2c/busses/i2c-stm32f4.c index 937c2c8fd349..4933fc8ce3fd 100644 --- a/drivers/i2c/busses/i2c-stm32f4.c +++ b/drivers/i2c/busses/i2c-stm32f4.c @@ -534,7 +534,7 @@ static void stm32f4_i2c_handle_rx_addr(struct stm32f4_i2c_dev *i2c_dev) default: /* * N-byte reception: - * Enable ACK, reset POS (ACK postion) and clear ADDR flag. + * Enable ACK, reset POS (ACK position) and clear ADDR flag. * In that way, ACK will be sent as soon as the current byte * will be received in the shift register */ diff --git a/drivers/i2c/i2c-core-base.c b/drivers/i2c/i2c-core-base.c index 63ebf722a424..f21362355973 100644 --- a/drivers/i2c/i2c-core-base.c +++ b/drivers/i2c/i2c-core-base.c @@ -378,7 +378,7 @@ static int i2c_gpio_init_recovery(struct i2c_adapter *adap) static int i2c_init_recovery(struct i2c_adapter *adap) { struct i2c_bus_recovery_info *bri = adap->bus_recovery_info; - char *err_str; + char *err_str, *err_level = KERN_ERR; if (!bri) return 0; @@ -387,7 +387,8 @@ static int i2c_init_recovery(struct i2c_adapter *adap) return -EPROBE_DEFER; if (!bri->recover_bus) { - err_str = "no recover_bus() found"; + err_str = "no suitable method provided"; + err_level = KERN_DEBUG; goto err; } @@ -414,7 +415,7 @@ static int i2c_init_recovery(struct i2c_adapter *adap) return 0; err: - dev_err(&adap->dev, "Not using recovery: %s\n", err_str); + dev_printk(err_level, &adap->dev, "Not using recovery: %s\n", err_str); adap->bus_recovery_info = NULL; return -EINVAL; diff --git a/drivers/iio/adc/Kconfig b/drivers/iio/adc/Kconfig index bf7d22fa4be2..e0667c4b3c08 100644 --- a/drivers/iio/adc/Kconfig +++ b/drivers/iio/adc/Kconfig @@ -266,6 +266,8 @@ config ADI_AXI_ADC select IIO_BUFFER select IIO_BUFFER_HW_CONSUMER select IIO_BUFFER_DMAENGINE + depends on HAS_IOMEM + depends on OF help Say yes here to build support for Analog Devices Generic AXI ADC IP core. The IP core is used for interfacing with @@ -923,6 +925,7 @@ config STM32_ADC_CORE depends on ARCH_STM32 || COMPILE_TEST depends on OF depends on REGULATOR + depends on HAS_IOMEM select IIO_BUFFER select MFD_STM32_TIMERS select IIO_STM32_TIMER_TRIGGER diff --git a/drivers/iio/adc/ab8500-gpadc.c b/drivers/iio/adc/ab8500-gpadc.c index 6f9a3e2d5533..7b5212ba5501 100644 --- a/drivers/iio/adc/ab8500-gpadc.c +++ b/drivers/iio/adc/ab8500-gpadc.c @@ -918,7 +918,7 @@ static int ab8500_gpadc_read_raw(struct iio_dev *indio_dev, return processed; /* Return millivolt or milliamps or millicentigrades */ - *val = processed * 1000; + *val = processed; return IIO_VAL_INT; } diff --git a/drivers/iio/adc/ad7949.c b/drivers/iio/adc/ad7949.c index 5d597e5050f6..1b4b3203e428 100644 --- a/drivers/iio/adc/ad7949.c +++ b/drivers/iio/adc/ad7949.c @@ -91,7 +91,7 @@ static int ad7949_spi_read_channel(struct ad7949_adc_chip *ad7949_adc, int *val, int ret; int i; int bits_per_word = ad7949_adc->resolution; - int mask = GENMASK(ad7949_adc->resolution, 0); + int mask = GENMASK(ad7949_adc->resolution - 1, 0); struct spi_message msg; struct spi_transfer tx[] = { { diff --git a/drivers/iio/adc/qcom-spmi-vadc.c b/drivers/iio/adc/qcom-spmi-vadc.c index 05ff948372b3..07b1a99381d9 100644 --- a/drivers/iio/adc/qcom-spmi-vadc.c +++ b/drivers/iio/adc/qcom-spmi-vadc.c @@ -597,7 +597,7 @@ static const struct vadc_channels vadc_chans[] = { VADC_CHAN_NO_SCALE(P_MUX16_1_3, 1) VADC_CHAN_NO_SCALE(LR_MUX1_BAT_THERM, 0) - VADC_CHAN_NO_SCALE(LR_MUX2_BAT_ID, 0) + VADC_CHAN_VOLT(LR_MUX2_BAT_ID, 0, SCALE_DEFAULT) VADC_CHAN_NO_SCALE(LR_MUX3_XO_THERM, 0) VADC_CHAN_NO_SCALE(LR_MUX4_AMUX_THM1, 0) VADC_CHAN_NO_SCALE(LR_MUX5_AMUX_THM2, 0) diff --git a/drivers/iio/gyro/mpu3050-core.c b/drivers/iio/gyro/mpu3050-core.c index dfa31a23500f..ac90be03332a 100644 --- a/drivers/iio/gyro/mpu3050-core.c +++ b/drivers/iio/gyro/mpu3050-core.c @@ -551,6 +551,8 @@ static irqreturn_t mpu3050_trigger_handler(int irq, void *p) MPU3050_FIFO_R, &fifo_values[offset], toread); + if (ret) + goto out_trigger_unlock; dev_dbg(mpu3050->dev, "%04x %04x %04x %04x %04x\n", diff --git a/drivers/iio/humidity/hid-sensor-humidity.c b/drivers/iio/humidity/hid-sensor-humidity.c index 52f605114ef7..d62705448ae2 100644 --- a/drivers/iio/humidity/hid-sensor-humidity.c +++ b/drivers/iio/humidity/hid-sensor-humidity.c @@ -15,7 +15,10 @@ struct hid_humidity_state { struct hid_sensor_common common_attributes; struct hid_sensor_hub_attribute_info humidity_attr; - s32 humidity_data; + struct { + s32 humidity_data; + u64 timestamp __aligned(8); + } scan; int scale_pre_decml; int scale_post_decml; int scale_precision; @@ -125,9 +128,8 @@ static int humidity_proc_event(struct hid_sensor_hub_device *hsdev, struct hid_humidity_state *humid_st = iio_priv(indio_dev); if (atomic_read(&humid_st->common_attributes.data_ready)) - iio_push_to_buffers_with_timestamp(indio_dev, - &humid_st->humidity_data, - iio_get_time_ns(indio_dev)); + iio_push_to_buffers_with_timestamp(indio_dev, &humid_st->scan, + iio_get_time_ns(indio_dev)); return 0; } @@ -142,7 +144,7 @@ static int humidity_capture_sample(struct hid_sensor_hub_device *hsdev, switch (usage_id) { case HID_USAGE_SENSOR_ATMOSPHERIC_HUMIDITY: - humid_st->humidity_data = *(s32 *)raw_data; + humid_st->scan.humidity_data = *(s32 *)raw_data; return 0; default: diff --git a/drivers/iio/imu/adis16400.c b/drivers/iio/imu/adis16400.c index 54af2ed664f6..785a4ce606d8 100644 --- a/drivers/iio/imu/adis16400.c +++ b/drivers/iio/imu/adis16400.c @@ -462,8 +462,7 @@ static int adis16400_initial_setup(struct iio_dev *indio_dev) if (ret) goto err_ret; - ret = sscanf(indio_dev->name, "adis%u\n", &device_id); - if (ret != 1) { + if (sscanf(indio_dev->name, "adis%u\n", &device_id) != 1) { ret = -EINVAL; goto err_ret; } diff --git a/drivers/iio/light/hid-sensor-prox.c b/drivers/iio/light/hid-sensor-prox.c index 330cf359e0b8..e9e00ce0c6d4 100644 --- a/drivers/iio/light/hid-sensor-prox.c +++ b/drivers/iio/light/hid-sensor-prox.c @@ -23,6 +23,9 @@ struct prox_state { struct hid_sensor_common common_attributes; struct hid_sensor_hub_attribute_info prox_attr; u32 human_presence; + int scale_pre_decml; + int scale_post_decml; + int scale_precision; }; /* Channel definitions */ @@ -93,8 +96,9 @@ static int prox_read_raw(struct iio_dev *indio_dev, ret_type = IIO_VAL_INT; break; case IIO_CHAN_INFO_SCALE: - *val = prox_state->prox_attr.units; - ret_type = IIO_VAL_INT; + *val = prox_state->scale_pre_decml; + *val2 = prox_state->scale_post_decml; + ret_type = prox_state->scale_precision; break; case IIO_CHAN_INFO_OFFSET: *val = hid_sensor_convert_exponent( @@ -234,6 +238,11 @@ static int prox_parse_report(struct platform_device *pdev, HID_USAGE_SENSOR_HUMAN_PRESENCE, &st->common_attributes.sensitivity); + st->scale_precision = hid_sensor_format_scale( + hsdev->usage, + &st->prox_attr, + &st->scale_pre_decml, &st->scale_post_decml); + return ret; } diff --git a/drivers/iio/temperature/hid-sensor-temperature.c b/drivers/iio/temperature/hid-sensor-temperature.c index 81688f1b932f..da9a247097fa 100644 --- a/drivers/iio/temperature/hid-sensor-temperature.c +++ b/drivers/iio/temperature/hid-sensor-temperature.c @@ -15,7 +15,10 @@ struct temperature_state { struct hid_sensor_common common_attributes; struct hid_sensor_hub_attribute_info temperature_attr; - s32 temperature_data; + struct { + s32 temperature_data; + u64 timestamp __aligned(8); + } scan; int scale_pre_decml; int scale_post_decml; int scale_precision; @@ -32,7 +35,7 @@ static const struct iio_chan_spec temperature_channels[] = { BIT(IIO_CHAN_INFO_SAMP_FREQ) | BIT(IIO_CHAN_INFO_HYSTERESIS), }, - IIO_CHAN_SOFT_TIMESTAMP(3), + IIO_CHAN_SOFT_TIMESTAMP(1), }; /* Adjust channel real bits based on report descriptor */ @@ -123,9 +126,8 @@ static int temperature_proc_event(struct hid_sensor_hub_device *hsdev, struct temperature_state *temp_st = iio_priv(indio_dev); if (atomic_read(&temp_st->common_attributes.data_ready)) - iio_push_to_buffers_with_timestamp(indio_dev, - &temp_st->temperature_data, - iio_get_time_ns(indio_dev)); + iio_push_to_buffers_with_timestamp(indio_dev, &temp_st->scan, + iio_get_time_ns(indio_dev)); return 0; } @@ -140,7 +142,7 @@ static int temperature_capture_sample(struct hid_sensor_hub_device *hsdev, switch (usage_id) { case HID_USAGE_SENSOR_DATA_ENVIRONMENTAL_TEMPERATURE: - temp_st->temperature_data = *(s32 *)raw_data; + temp_st->scan.temperature_data = *(s32 *)raw_data; return 0; default: return -EINVAL; diff --git a/drivers/infiniband/core/addr.c b/drivers/infiniband/core/addr.c index 0abce004a959..65e3e7df8a4b 100644 --- a/drivers/infiniband/core/addr.c +++ b/drivers/infiniband/core/addr.c @@ -76,7 +76,9 @@ static struct workqueue_struct *addr_wq; static const struct nla_policy ib_nl_addr_policy[LS_NLA_TYPE_MAX] = { [LS_NLA_TYPE_DGID] = {.type = NLA_BINARY, - .len = sizeof(struct rdma_nla_ls_gid)}, + .len = sizeof(struct rdma_nla_ls_gid), + .validation_type = NLA_VALIDATE_MIN, + .min = sizeof(struct rdma_nla_ls_gid)}, }; static inline bool ib_nl_is_good_ip_resp(const struct nlmsghdr *nlh) diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c index 8769e7aa097f..e42c812e74c3 100644 --- a/drivers/infiniband/hw/cxgb4/cm.c +++ b/drivers/infiniband/hw/cxgb4/cm.c @@ -3610,13 +3610,14 @@ int c4iw_destroy_listen(struct iw_cm_id *cm_id) ep->com.local_addr.ss_family == AF_INET) { err = cxgb4_remove_server_filter( ep->com.dev->rdev.lldi.ports[0], ep->stid, - ep->com.dev->rdev.lldi.rxq_ids[0], 0); + ep->com.dev->rdev.lldi.rxq_ids[0], false); } else { struct sockaddr_in6 *sin6; c4iw_init_wr_wait(ep->com.wr_waitp); err = cxgb4_remove_server( ep->com.dev->rdev.lldi.ports[0], ep->stid, - ep->com.dev->rdev.lldi.rxq_ids[0], 0); + ep->com.dev->rdev.lldi.rxq_ids[0], + ep->com.local_addr.ss_family == AF_INET6); if (err) goto done; err = c4iw_wait_for_reply(&ep->com.dev->rdev, ep->com.wr_waitp, diff --git a/drivers/infiniband/hw/hfi1/affinity.c b/drivers/infiniband/hw/hfi1/affinity.c index 2a91b8d95e12..04b1e8f021f6 100644 --- a/drivers/infiniband/hw/hfi1/affinity.c +++ b/drivers/infiniband/hw/hfi1/affinity.c @@ -632,22 +632,11 @@ static void _dev_comp_vect_cpu_mask_clean_up(struct hfi1_devdata *dd, */ int hfi1_dev_affinity_init(struct hfi1_devdata *dd) { - int node = pcibus_to_node(dd->pcidev->bus); struct hfi1_affinity_node *entry; const struct cpumask *local_mask; int curr_cpu, possible, i, ret; bool new_entry = false; - /* - * If the BIOS does not have the NUMA node information set, select - * NUMA 0 so we get consistent performance. - */ - if (node < 0) { - dd_dev_err(dd, "Invalid PCI NUMA node. Performance may be affected\n"); - node = 0; - } - dd->node = node; - local_mask = cpumask_of_node(dd->node); if (cpumask_first(local_mask) >= nr_cpu_ids) local_mask = topology_core_cpumask(0); @@ -660,7 +649,7 @@ int hfi1_dev_affinity_init(struct hfi1_devdata *dd) * create an entry in the global affinity structure and initialize it. */ if (!entry) { - entry = node_affinity_allocate(node); + entry = node_affinity_allocate(dd->node); if (!entry) { dd_dev_err(dd, "Unable to allocate global affinity node\n"); @@ -751,6 +740,7 @@ int hfi1_dev_affinity_init(struct hfi1_devdata *dd) if (new_entry) node_affinity_add_tail(entry); + dd->affinity_entry = entry; mutex_unlock(&node_affinity.lock); return 0; @@ -766,10 +756,9 @@ void hfi1_dev_affinity_clean_up(struct hfi1_devdata *dd) { struct hfi1_affinity_node *entry; - if (dd->node < 0) - return; - mutex_lock(&node_affinity.lock); + if (!dd->affinity_entry) + goto unlock; entry = node_affinity_lookup(dd->node); if (!entry) goto unlock; @@ -780,8 +769,8 @@ void hfi1_dev_affinity_clean_up(struct hfi1_devdata *dd) */ _dev_comp_vect_cpu_mask_clean_up(dd, entry); unlock: + dd->affinity_entry = NULL; mutex_unlock(&node_affinity.lock); - dd->node = NUMA_NO_NODE; } /* diff --git a/drivers/infiniband/hw/hfi1/hfi.h b/drivers/infiniband/hw/hfi1/hfi.h index e09e8244a94c..2a9a040569eb 100644 --- a/drivers/infiniband/hw/hfi1/hfi.h +++ b/drivers/infiniband/hw/hfi1/hfi.h @@ -1409,6 +1409,7 @@ struct hfi1_devdata { spinlock_t irq_src_lock; int vnic_num_vports; struct net_device *dummy_netdev; + struct hfi1_affinity_node *affinity_entry; /* Keeps track of IPoIB RSM rule users */ atomic_t ipoib_rsm_usr_num; diff --git a/drivers/infiniband/hw/hfi1/init.c b/drivers/infiniband/hw/hfi1/init.c index cb7ad1288821..786c6316273f 100644 --- a/drivers/infiniband/hw/hfi1/init.c +++ b/drivers/infiniband/hw/hfi1/init.c @@ -1277,7 +1277,6 @@ static struct hfi1_devdata *hfi1_alloc_devdata(struct pci_dev *pdev, dd->pport = (struct hfi1_pportdata *)(dd + 1); dd->pcidev = pdev; pci_set_drvdata(pdev, dd); - dd->node = NUMA_NO_NODE; ret = xa_alloc_irq(&hfi1_dev_table, &dd->unit, dd, xa_limit_32b, GFP_KERNEL); @@ -1287,6 +1286,15 @@ static struct hfi1_devdata *hfi1_alloc_devdata(struct pci_dev *pdev, goto bail; } rvt_set_ibdev_name(&dd->verbs_dev.rdi, "%s_%d", class_name(), dd->unit); + /* + * If the BIOS does not have the NUMA node information set, select + * NUMA 0 so we get consistent performance. + */ + dd->node = pcibus_to_node(pdev->bus); + if (dd->node == NUMA_NO_NODE) { + dd_dev_err(dd, "Invalid PCI NUMA node. Performance may be affected\n"); + dd->node = 0; + } /* * Initialize all locks for the device. This needs to be as early as diff --git a/drivers/infiniband/hw/hfi1/netdev_rx.c b/drivers/infiniband/hw/hfi1/netdev_rx.c index 1fb6e1a0e4e1..1bcab992ac26 100644 --- a/drivers/infiniband/hw/hfi1/netdev_rx.c +++ b/drivers/infiniband/hw/hfi1/netdev_rx.c @@ -173,8 +173,7 @@ u32 hfi1_num_netdev_contexts(struct hfi1_devdata *dd, u32 available_contexts, return 0; } - cpumask_and(node_cpu_mask, cpu_mask, - cpumask_of_node(pcibus_to_node(dd->pcidev->bus))); + cpumask_and(node_cpu_mask, cpu_mask, cpumask_of_node(dd->node)); available_cpus = cpumask_weight(node_cpu_mask); diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c index c3934abeb260..ce26f97b2ca2 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c @@ -1194,8 +1194,10 @@ static void hns_roce_cmq_init_regs(struct hns_roce_dev *hr_dev, bool ring_type) upper_32_bits(dma)); roce_write(hr_dev, ROCEE_TX_CMQ_DEPTH_REG, (u32)ring->desc_num >> HNS_ROCE_CMQ_DESC_NUM_S); - roce_write(hr_dev, ROCEE_TX_CMQ_HEAD_REG, 0); + + /* Make sure to write tail first and then head */ roce_write(hr_dev, ROCEE_TX_CMQ_TAIL_REG, 0); + roce_write(hr_dev, ROCEE_TX_CMQ_HEAD_REG, 0); } else { roce_write(hr_dev, ROCEE_RX_CMQ_BASEADDR_L_REG, (u32)dma); roce_write(hr_dev, ROCEE_RX_CMQ_BASEADDR_H_REG, diff --git a/drivers/infiniband/hw/mlx5/devx.c b/drivers/infiniband/hw/mlx5/devx.c index de3c2fc6f361..07b8350929cd 100644 --- a/drivers/infiniband/hw/mlx5/devx.c +++ b/drivers/infiniband/hw/mlx5/devx.c @@ -1116,7 +1116,7 @@ static void devx_obj_build_destroy_cmd(void *in, void *out, void *din, case MLX5_CMD_OP_CREATE_MKEY: MLX5_SET(destroy_mkey_in, din, opcode, MLX5_CMD_OP_DESTROY_MKEY); - MLX5_SET(destroy_mkey_in, in, mkey_index, *obj_id); + MLX5_SET(destroy_mkey_in, din, mkey_index, *obj_id); break; case MLX5_CMD_OP_CREATE_CQ: MLX5_SET(destroy_cq_in, din, opcode, MLX5_CMD_OP_DESTROY_CQ); diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c index ec4b3f6a8222..f5a52a6fae43 100644 --- a/drivers/infiniband/hw/mlx5/qp.c +++ b/drivers/infiniband/hw/mlx5/qp.c @@ -1078,7 +1078,7 @@ static int _create_kernel_qp(struct mlx5_ib_dev *dev, qpc = MLX5_ADDR_OF(create_qp_in, *in, qpc); MLX5_SET(qpc, qpc, uar_page, uar_index); - MLX5_SET(qpc, qpc, ts_format, MLX5_QPC_TIMESTAMP_FORMAT_DEFAULT); + MLX5_SET(qpc, qpc, ts_format, mlx5_get_qp_default_ts(dev->mdev)); MLX5_SET(qpc, qpc, log_page_size, qp->buf.page_shift - MLX5_ADAPTER_PAGE_SHIFT); /* Set "fast registration enabled" for all kernel QPs */ @@ -1188,7 +1188,8 @@ static int get_rq_ts_format(struct mlx5_ib_dev *dev, struct mlx5_ib_cq *send_cq) } return MLX5_RQC_TIMESTAMP_FORMAT_FREE_RUNNING; } - return MLX5_RQC_TIMESTAMP_FORMAT_DEFAULT; + return fr_supported ? MLX5_RQC_TIMESTAMP_FORMAT_FREE_RUNNING : + MLX5_RQC_TIMESTAMP_FORMAT_DEFAULT; } static int get_sq_ts_format(struct mlx5_ib_dev *dev, struct mlx5_ib_cq *send_cq) @@ -1206,7 +1207,8 @@ static int get_sq_ts_format(struct mlx5_ib_dev *dev, struct mlx5_ib_cq *send_cq) } return MLX5_SQC_TIMESTAMP_FORMAT_FREE_RUNNING; } - return MLX5_SQC_TIMESTAMP_FORMAT_DEFAULT; + return fr_supported ? MLX5_SQC_TIMESTAMP_FORMAT_FREE_RUNNING : + MLX5_SQC_TIMESTAMP_FORMAT_DEFAULT; } static int get_qp_ts_format(struct mlx5_ib_dev *dev, struct mlx5_ib_cq *send_cq, @@ -1217,7 +1219,8 @@ static int get_qp_ts_format(struct mlx5_ib_dev *dev, struct mlx5_ib_cq *send_cq, MLX5_QP_TIMESTAMP_FORMAT_CAP_FREE_RUNNING || MLX5_CAP_ROCE(dev->mdev, qp_ts_format) == MLX5_QP_TIMESTAMP_FORMAT_CAP_FREE_RUNNING_AND_REAL_TIME; - int ts_format = MLX5_QPC_TIMESTAMP_FORMAT_DEFAULT; + int ts_format = fr_supported ? MLX5_QPC_TIMESTAMP_FORMAT_FREE_RUNNING : + MLX5_QPC_TIMESTAMP_FORMAT_DEFAULT; if (recv_cq && recv_cq->create_flags & IB_UVERBS_CQ_FLAGS_TIMESTAMP_COMPLETION) @@ -1930,6 +1933,7 @@ static int create_xrc_tgt_qp(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp, if (qp->flags & IB_QP_CREATE_MANAGED_RECV) MLX5_SET(qpc, qpc, cd_slave_receive, 1); + MLX5_SET(qpc, qpc, ts_format, mlx5_get_qp_default_ts(dev->mdev)); MLX5_SET(qpc, qpc, rq_type, MLX5_SRQ_RQ); MLX5_SET(qpc, qpc, no_sq, 1); MLX5_SET(qpc, qpc, cqn_rcv, to_mcq(devr->c0)->mcq.cqn); @@ -4873,6 +4877,7 @@ static int create_rq(struct mlx5_ib_rwq *rwq, struct ib_pd *pd, struct mlx5_ib_dev *dev; int has_net_offloads; __be64 *rq_pas0; + int ts_format; void *in; void *rqc; void *wq; @@ -4881,6 +4886,10 @@ static int create_rq(struct mlx5_ib_rwq *rwq, struct ib_pd *pd, dev = to_mdev(pd->device); + ts_format = get_rq_ts_format(dev, to_mcq(init_attr->cq)); + if (ts_format < 0) + return ts_format; + inlen = MLX5_ST_SZ_BYTES(create_rq_in) + sizeof(u64) * rwq->rq_num_pas; in = kvzalloc(inlen, GFP_KERNEL); if (!in) @@ -4890,6 +4899,7 @@ static int create_rq(struct mlx5_ib_rwq *rwq, struct ib_pd *pd, rqc = MLX5_ADDR_OF(create_rq_in, in, ctx); MLX5_SET(rqc, rqc, mem_rq_type, MLX5_RQC_MEM_RQ_TYPE_MEMORY_RQ_INLINE); + MLX5_SET(rqc, rqc, ts_format, ts_format); MLX5_SET(rqc, rqc, user_index, rwq->user_index); MLX5_SET(rqc, rqc, cqn, to_mcq(init_attr->cq)->mcq.cqn); MLX5_SET(rqc, rqc, state, MLX5_RQC_STATE_RST); diff --git a/drivers/infiniband/hw/qedr/verbs.c b/drivers/infiniband/hw/qedr/verbs.c index 0eb6a7a618e0..9ea542270ed4 100644 --- a/drivers/infiniband/hw/qedr/verbs.c +++ b/drivers/infiniband/hw/qedr/verbs.c @@ -1244,7 +1244,8 @@ static int qedr_check_qp_attrs(struct ib_pd *ibpd, struct qedr_dev *dev, * TGT QP isn't associated with RQ/SQ */ if ((attrs->qp_type != IB_QPT_GSI) && (dev->gsi_qp_created) && - (attrs->qp_type != IB_QPT_XRC_TGT)) { + (attrs->qp_type != IB_QPT_XRC_TGT) && + (attrs->qp_type != IB_QPT_XRC_INI)) { struct qedr_cq *send_cq = get_qedr_cq(attrs->send_cq); struct qedr_cq *recv_cq = get_qedr_cq(attrs->recv_cq); diff --git a/drivers/infiniband/ulp/rtrs/rtrs-clt.c b/drivers/infiniband/ulp/rtrs/rtrs-clt.c index 0a08b4b742a3..6734329cca33 100644 --- a/drivers/infiniband/ulp/rtrs/rtrs-clt.c +++ b/drivers/infiniband/ulp/rtrs/rtrs-clt.c @@ -2720,8 +2720,8 @@ void rtrs_clt_close(struct rtrs_clt *clt) /* Now it is safe to iterate over all paths without locks */ list_for_each_entry_safe(sess, tmp, &clt->paths_list, s.entry) { - rtrs_clt_destroy_sess_files(sess, NULL); rtrs_clt_close_conns(sess, true); + rtrs_clt_destroy_sess_files(sess, NULL); kobject_put(&sess->kobj); } free_clt(clt); diff --git a/drivers/input/joydev.c b/drivers/input/joydev.c index 430dc6975004..da8963a9f044 100644 --- a/drivers/input/joydev.c +++ b/drivers/input/joydev.c @@ -26,7 +26,6 @@ MODULE_AUTHOR("Vojtech Pavlik <vojtech@ucw.cz>"); MODULE_DESCRIPTION("Joystick device interfaces"); -MODULE_SUPPORTED_DEVICE("input/js"); MODULE_LICENSE("GPL"); #define JOYDEV_MINOR_BASE 0 diff --git a/drivers/interconnect/bulk.c b/drivers/interconnect/bulk.c index 73e2c8d0a412..448cc536aa79 100644 --- a/drivers/interconnect/bulk.c +++ b/drivers/interconnect/bulk.c @@ -53,7 +53,7 @@ void icc_bulk_put(int num_paths, struct icc_bulk_data *paths) EXPORT_SYMBOL_GPL(icc_bulk_put); /** - * icc_bulk_set() - set bandwidth to a set of paths + * icc_bulk_set_bw() - set bandwidth to a set of paths * @num_paths: the number of icc_bulk_data * @paths: the icc_bulk_data table containing the paths and bandwidth * diff --git a/drivers/interconnect/core.c b/drivers/interconnect/core.c index 5ad519c9f239..8a1e70e00876 100644 --- a/drivers/interconnect/core.c +++ b/drivers/interconnect/core.c @@ -942,6 +942,8 @@ int icc_link_destroy(struct icc_node *src, struct icc_node *dst) GFP_KERNEL); if (new) src->links = new; + else + ret = -ENOMEM; out: mutex_unlock(&icc_lock); diff --git a/drivers/interconnect/qcom/msm8939.c b/drivers/interconnect/qcom/msm8939.c index dfbec30ed149..20f31a1b4192 100644 --- a/drivers/interconnect/qcom/msm8939.c +++ b/drivers/interconnect/qcom/msm8939.c @@ -131,7 +131,7 @@ DEFINE_QNODE(mas_pcnoc_sdcc_1, MSM8939_MASTER_SDCC_1, 8, -1, -1, MSM8939_PNOC_IN DEFINE_QNODE(mas_pcnoc_sdcc_2, MSM8939_MASTER_SDCC_2, 8, -1, -1, MSM8939_PNOC_INT_1); DEFINE_QNODE(mas_qdss_bam, MSM8939_MASTER_QDSS_BAM, 8, -1, -1, MSM8939_SNOC_QDSS_INT); DEFINE_QNODE(mas_qdss_etr, MSM8939_MASTER_QDSS_ETR, 8, -1, -1, MSM8939_SNOC_QDSS_INT); -DEFINE_QNODE(mas_snoc_cfg, MSM8939_MASTER_SNOC_CFG, 4, 20, -1, MSM8939_SLAVE_SRVC_SNOC); +DEFINE_QNODE(mas_snoc_cfg, MSM8939_MASTER_SNOC_CFG, 4, -1, -1, MSM8939_SLAVE_SRVC_SNOC); DEFINE_QNODE(mas_spdm, MSM8939_MASTER_SPDM, 4, -1, -1, MSM8939_PNOC_MAS_0); DEFINE_QNODE(mas_tcu0, MSM8939_MASTER_TCU0, 16, -1, -1, MSM8939_SLAVE_EBI_CH0, MSM8939_BIMC_SNOC_MAS, MSM8939_SLAVE_AMPSS_L2); DEFINE_QNODE(mas_usb_hs1, MSM8939_MASTER_USB_HS1, 4, -1, -1, MSM8939_PNOC_MAS_1); @@ -156,14 +156,14 @@ DEFINE_QNODE(pcnoc_snoc_mas, MSM8939_PNOC_SNOC_MAS, 8, 29, -1, MSM8939_PNOC_SNOC DEFINE_QNODE(pcnoc_snoc_slv, MSM8939_PNOC_SNOC_SLV, 8, -1, 45, MSM8939_SNOC_INT_0, MSM8939_SNOC_INT_BIMC, MSM8939_SNOC_INT_1); DEFINE_QNODE(qdss_int, MSM8939_SNOC_QDSS_INT, 8, -1, -1, MSM8939_SNOC_INT_0, MSM8939_SNOC_INT_BIMC); DEFINE_QNODE(slv_apps_l2, MSM8939_SLAVE_AMPSS_L2, 16, -1, -1, 0); -DEFINE_QNODE(slv_apss, MSM8939_SLAVE_APSS, 4, -1, 20, 0); +DEFINE_QNODE(slv_apss, MSM8939_SLAVE_APSS, 4, -1, -1, 0); DEFINE_QNODE(slv_audio, MSM8939_SLAVE_LPASS, 4, -1, -1, 0); DEFINE_QNODE(slv_bimc_cfg, MSM8939_SLAVE_BIMC_CFG, 4, -1, -1, 0); DEFINE_QNODE(slv_blsp_1, MSM8939_SLAVE_BLSP_1, 4, -1, -1, 0); DEFINE_QNODE(slv_boot_rom, MSM8939_SLAVE_BOOT_ROM, 4, -1, -1, 0); DEFINE_QNODE(slv_camera_cfg, MSM8939_SLAVE_CAMERA_CFG, 4, -1, -1, 0); -DEFINE_QNODE(slv_cats_0, MSM8939_SLAVE_CATS_128, 16, -1, 106, 0); -DEFINE_QNODE(slv_cats_1, MSM8939_SLAVE_OCMEM_64, 8, -1, 107, 0); +DEFINE_QNODE(slv_cats_0, MSM8939_SLAVE_CATS_128, 16, -1, -1, 0); +DEFINE_QNODE(slv_cats_1, MSM8939_SLAVE_OCMEM_64, 8, -1, -1, 0); DEFINE_QNODE(slv_clk_ctl, MSM8939_SLAVE_CLK_CTL, 4, -1, -1, 0); DEFINE_QNODE(slv_crypto_0_cfg, MSM8939_SLAVE_CRYPTO_0_CFG, 4, -1, -1, 0); DEFINE_QNODE(slv_dehr_cfg, MSM8939_SLAVE_DEHR_CFG, 4, -1, -1, 0); @@ -187,20 +187,20 @@ DEFINE_QNODE(slv_sdcc_2, MSM8939_SLAVE_SDCC_2, 4, -1, -1, 0); DEFINE_QNODE(slv_security, MSM8939_SLAVE_SECURITY, 4, -1, -1, 0); DEFINE_QNODE(slv_snoc_cfg, MSM8939_SLAVE_SNOC_CFG, 4, -1, -1, 0); DEFINE_QNODE(slv_spdm, MSM8939_SLAVE_SPDM, 4, -1, -1, 0); -DEFINE_QNODE(slv_srvc_snoc, MSM8939_SLAVE_SRVC_SNOC, 8, -1, 29, 0); +DEFINE_QNODE(slv_srvc_snoc, MSM8939_SLAVE_SRVC_SNOC, 8, -1, -1, 0); DEFINE_QNODE(slv_tcsr, MSM8939_SLAVE_TCSR, 4, -1, -1, 0); DEFINE_QNODE(slv_tlmm, MSM8939_SLAVE_TLMM, 4, -1, -1, 0); DEFINE_QNODE(slv_usb_hs1, MSM8939_SLAVE_USB_HS1, 4, -1, -1, 0); DEFINE_QNODE(slv_usb_hs2, MSM8939_SLAVE_USB_HS2, 4, -1, -1, 0); DEFINE_QNODE(slv_venus_cfg, MSM8939_SLAVE_VENUS_CFG, 4, -1, -1, 0); -DEFINE_QNODE(snoc_bimc_0_mas, MSM8939_SNOC_BIMC_0_MAS, 16, 3, -1, MSM8939_SNOC_BIMC_0_SLV); -DEFINE_QNODE(snoc_bimc_0_slv, MSM8939_SNOC_BIMC_0_SLV, 16, -1, 24, MSM8939_SLAVE_EBI_CH0); +DEFINE_QNODE(snoc_bimc_0_mas, MSM8939_SNOC_BIMC_0_MAS, 16, -1, -1, MSM8939_SNOC_BIMC_0_SLV); +DEFINE_QNODE(snoc_bimc_0_slv, MSM8939_SNOC_BIMC_0_SLV, 16, -1, -1, MSM8939_SLAVE_EBI_CH0); DEFINE_QNODE(snoc_bimc_1_mas, MSM8939_SNOC_BIMC_1_MAS, 16, 76, -1, MSM8939_SNOC_BIMC_1_SLV); DEFINE_QNODE(snoc_bimc_1_slv, MSM8939_SNOC_BIMC_1_SLV, 16, -1, 104, MSM8939_SLAVE_EBI_CH0); DEFINE_QNODE(snoc_bimc_2_mas, MSM8939_SNOC_BIMC_2_MAS, 16, -1, -1, MSM8939_SNOC_BIMC_2_SLV); DEFINE_QNODE(snoc_bimc_2_slv, MSM8939_SNOC_BIMC_2_SLV, 16, -1, -1, MSM8939_SLAVE_EBI_CH0); DEFINE_QNODE(snoc_int_0, MSM8939_SNOC_INT_0, 8, 99, 130, MSM8939_SLAVE_QDSS_STM, MSM8939_SLAVE_IMEM, MSM8939_SNOC_PNOC_MAS); -DEFINE_QNODE(snoc_int_1, MSM8939_SNOC_INT_1, 8, 100, 131, MSM8939_SLAVE_APSS, MSM8939_SLAVE_CATS_128, MSM8939_SLAVE_OCMEM_64); +DEFINE_QNODE(snoc_int_1, MSM8939_SNOC_INT_1, 8, -1, -1, MSM8939_SLAVE_APSS, MSM8939_SLAVE_CATS_128, MSM8939_SLAVE_OCMEM_64); DEFINE_QNODE(snoc_int_bimc, MSM8939_SNOC_INT_BIMC, 8, 101, 132, MSM8939_SNOC_BIMC_1_MAS); DEFINE_QNODE(snoc_pcnoc_mas, MSM8939_SNOC_PNOC_MAS, 8, -1, -1, MSM8939_SNOC_PNOC_SLV); DEFINE_QNODE(snoc_pcnoc_slv, MSM8939_SNOC_PNOC_SLV, 8, -1, -1, MSM8939_PNOC_INT_0); diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c index 9126efcbaf2c..321f5906e6ed 100644 --- a/drivers/iommu/amd/init.c +++ b/drivers/iommu/amd/init.c @@ -2714,7 +2714,6 @@ static int __init early_amd_iommu_init(void) struct acpi_table_header *ivrs_base; int i, remap_cache_sz, ret; acpi_status status; - u32 pci_id; if (!amd_iommu_detected) return -ENODEV; @@ -2804,16 +2803,6 @@ static int __init early_amd_iommu_init(void) if (ret) goto out; - /* Disable IOMMU if there's Stoney Ridge graphics */ - for (i = 0; i < 32; i++) { - pci_id = read_pci_config(0, i, 0, 0); - if ((pci_id & 0xffff) == 0x1002 && (pci_id >> 16) == 0x98e4) { - pr_info("Disable IOMMU on Stoney Ridge\n"); - amd_iommu_disabled = true; - break; - } - } - /* Disable any previously enabled IOMMUs */ if (!is_kdump_kernel() || amd_iommu_disabled) disable_iommus(); @@ -2880,6 +2869,7 @@ static bool detect_ivrs(void) { struct acpi_table_header *ivrs_base; acpi_status status; + int i; status = acpi_get_table("IVRS", 0, &ivrs_base); if (status == AE_NOT_FOUND) @@ -2892,6 +2882,17 @@ static bool detect_ivrs(void) acpi_put_table(ivrs_base); + /* Don't use IOMMU if there is Stoney Ridge graphics */ + for (i = 0; i < 32; i++) { + u32 pci_id; + + pci_id = read_pci_config(0, i, 0, 0); + if ((pci_id & 0xffff) == 0x1002 && (pci_id >> 16) == 0x98e4) { + pr_info("Disable IOMMU on Stoney Ridge\n"); + return false; + } + } + /* Make sure ACS will be enabled during PCI probe */ pci_request_acs(); @@ -2918,12 +2919,12 @@ static int __init state_next(void) } break; case IOMMU_IVRS_DETECTED: - ret = early_amd_iommu_init(); - init_state = ret ? IOMMU_INIT_ERROR : IOMMU_ACPI_FINISHED; - if (init_state == IOMMU_ACPI_FINISHED && amd_iommu_disabled) { - pr_info("AMD IOMMU disabled\n"); + if (amd_iommu_disabled) { init_state = IOMMU_CMDLINE_DISABLED; ret = -EINVAL; + } else { + ret = early_amd_iommu_init(); + init_state = ret ? IOMMU_INIT_ERROR : IOMMU_ACPI_FINISHED; } break; case IOMMU_ACPI_FINISHED: @@ -3001,8 +3002,11 @@ int __init amd_iommu_prepare(void) amd_iommu_irq_remap = true; ret = iommu_go_to_state(IOMMU_ACPI_FINISHED); - if (ret) + if (ret) { + amd_iommu_irq_remap = false; return ret; + } + return amd_iommu_irq_remap ? 0 : -ENODEV; } diff --git a/drivers/iommu/tegra-smmu.c b/drivers/iommu/tegra-smmu.c index 97eb62f667d2..602aab98c079 100644 --- a/drivers/iommu/tegra-smmu.c +++ b/drivers/iommu/tegra-smmu.c @@ -849,12 +849,11 @@ static struct iommu_device *tegra_smmu_probe_device(struct device *dev) smmu = tegra_smmu_find(args.np); if (smmu) { err = tegra_smmu_configure(smmu, dev, &args); - of_node_put(args.np); - if (err < 0) + if (err < 0) { + of_node_put(args.np); return ERR_PTR(err); - - break; + } } of_node_put(args.np); diff --git a/drivers/isdn/capi/kcapi.c b/drivers/isdn/capi/kcapi.c index 7168778fbbe1..cb0afe897162 100644 --- a/drivers/isdn/capi/kcapi.c +++ b/drivers/isdn/capi/kcapi.c @@ -721,7 +721,7 @@ u16 capi20_put_message(struct capi20_appl *ap, struct sk_buff *skb) * Return value: CAPI result code */ -u16 capi20_get_manufacturer(u32 contr, u8 *buf) +u16 capi20_get_manufacturer(u32 contr, u8 buf[CAPI_MANUFACTURER_LEN]) { struct capi_ctr *ctr; u16 ret; @@ -787,7 +787,7 @@ u16 capi20_get_version(u32 contr, struct capi_version *verp) * Return value: CAPI result code */ -u16 capi20_get_serial(u32 contr, u8 *serial) +u16 capi20_get_serial(u32 contr, u8 serial[CAPI_SERIAL_LEN]) { struct capi_ctr *ctr; u16 ret; diff --git a/drivers/isdn/hardware/mISDN/mISDNipac.c b/drivers/isdn/hardware/mISDN/mISDNipac.c index ec475087fbf9..39f841b42488 100644 --- a/drivers/isdn/hardware/mISDN/mISDNipac.c +++ b/drivers/isdn/hardware/mISDN/mISDNipac.c @@ -694,7 +694,7 @@ isac_release(struct isac_hw *isac) { if (isac->type & IPAC_TYPE_ISACX) WriteISAC(isac, ISACX_MASK, 0xff); - else + else if (isac->type != 0) WriteISAC(isac, ISAC_MASK, 0xff); if (isac->dch.timer.function != NULL) { del_timer(&isac->dch.timer); diff --git a/drivers/leds/leds-turris-omnia.c b/drivers/leds/leds-turris-omnia.c index 7b2f4d0ae3fe..2f9a289ab245 100644 --- a/drivers/leds/leds-turris-omnia.c +++ b/drivers/leds/leds-turris-omnia.c @@ -2,7 +2,7 @@ /* * CZ.NIC's Turris Omnia LEDs driver * - * 2020 by Marek Behun <marek.behun@nic.cz> + * 2020 by Marek Behún <kabel@kernel.org> */ #include <linux/i2c.h> @@ -287,6 +287,6 @@ static struct i2c_driver omnia_leds_driver = { module_i2c_driver(omnia_leds_driver); -MODULE_AUTHOR("Marek Behun <marek.behun@nic.cz>"); +MODULE_AUTHOR("Marek Behun <kabel@kernel.org>"); MODULE_DESCRIPTION("CZ.NIC's Turris Omnia LEDs"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/mailbox/armada-37xx-rwtm-mailbox.c b/drivers/mailbox/armada-37xx-rwtm-mailbox.c index 9f2ce7f03c67..456a117a65fd 100644 --- a/drivers/mailbox/armada-37xx-rwtm-mailbox.c +++ b/drivers/mailbox/armada-37xx-rwtm-mailbox.c @@ -2,7 +2,7 @@ /* * rWTM BIU Mailbox driver for Armada 37xx * - * Author: Marek Behun <marek.behun@nic.cz> + * Author: Marek Behún <kabel@kernel.org> */ #include <linux/device.h> @@ -203,4 +203,4 @@ module_platform_driver(armada_37xx_mbox_driver); MODULE_LICENSE("GPL v2"); MODULE_DESCRIPTION("rWTM BIU Mailbox driver for Armada 37xx"); -MODULE_AUTHOR("Marek Behun <marek.behun@nic.cz>"); +MODULE_AUTHOR("Marek Behun <kabel@kernel.org>"); diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c index 5e306bba4375..1ca65b434f1f 100644 --- a/drivers/md/dm-ioctl.c +++ b/drivers/md/dm-ioctl.c @@ -529,7 +529,7 @@ static int list_devices(struct file *filp, struct dm_ioctl *param, size_t param_ * Grab our output buffer. */ nl = orig_nl = get_result_buffer(param, param_size, &len); - if (len < needed) { + if (len < needed || len < sizeof(nl->dev)) { param->flags |= DM_BUFFER_FULL_FLAG; goto out; } diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index 95391f78b8d5..e5f0f1703c5d 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -1594,6 +1594,13 @@ static int device_not_zoned_model(struct dm_target *ti, struct dm_dev *dev, return blk_queue_zoned_model(q) != *zoned_model; } +/* + * Check the device zoned model based on the target feature flag. If the target + * has the DM_TARGET_ZONED_HM feature flag set, host-managed zoned devices are + * also accepted but all devices must have the same zoned model. If the target + * has the DM_TARGET_MIXED_ZONED_MODEL feature set, the devices can have any + * zoned model with all zoned devices having the same zone size. + */ static bool dm_table_supports_zoned_model(struct dm_table *t, enum blk_zoned_model zoned_model) { @@ -1603,13 +1610,15 @@ static bool dm_table_supports_zoned_model(struct dm_table *t, for (i = 0; i < dm_table_get_num_targets(t); i++) { ti = dm_table_get_target(t, i); - if (zoned_model == BLK_ZONED_HM && - !dm_target_supports_zoned_hm(ti->type)) - return false; - - if (!ti->type->iterate_devices || - ti->type->iterate_devices(ti, device_not_zoned_model, &zoned_model)) - return false; + if (dm_target_supports_zoned_hm(ti->type)) { + if (!ti->type->iterate_devices || + ti->type->iterate_devices(ti, device_not_zoned_model, + &zoned_model)) + return false; + } else if (!dm_target_supports_mixed_zoned_model(ti->type)) { + if (zoned_model == BLK_ZONED_HM) + return false; + } } return true; @@ -1621,9 +1630,17 @@ static int device_not_matches_zone_sectors(struct dm_target *ti, struct dm_dev * struct request_queue *q = bdev_get_queue(dev->bdev); unsigned int *zone_sectors = data; + if (!blk_queue_is_zoned(q)) + return 0; + return blk_queue_zone_sectors(q) != *zone_sectors; } +/* + * Check consistency of zoned model and zone sectors across all targets. For + * zone sectors, if the destination device is a zoned block device, it shall + * have the specified zone_sectors. + */ static int validate_hardware_zoned_model(struct dm_table *table, enum blk_zoned_model zoned_model, unsigned int zone_sectors) @@ -1642,7 +1659,7 @@ static int validate_hardware_zoned_model(struct dm_table *table, return -EINVAL; if (dm_table_any_dev_attr(table, device_not_matches_zone_sectors, &zone_sectors)) { - DMERR("%s: zone sectors is not consistent across all devices", + DMERR("%s: zone sectors is not consistent across all zoned devices", dm_device_name(table->md)); return -EINVAL; } diff --git a/drivers/md/dm-verity-target.c b/drivers/md/dm-verity-target.c index 6b8e5bdd8526..808a98ef624c 100644 --- a/drivers/md/dm-verity-target.c +++ b/drivers/md/dm-verity-target.c @@ -34,7 +34,7 @@ #define DM_VERITY_OPT_IGN_ZEROES "ignore_zero_blocks" #define DM_VERITY_OPT_AT_MOST_ONCE "check_at_most_once" -#define DM_VERITY_OPTS_MAX (2 + DM_VERITY_OPTS_FEC + \ +#define DM_VERITY_OPTS_MAX (3 + DM_VERITY_OPTS_FEC + \ DM_VERITY_ROOT_HASH_VERIFICATION_OPTS) static unsigned dm_verity_prefetch_cluster = DM_VERITY_DEFAULT_PREFETCH_SIZE; diff --git a/drivers/md/dm-zoned-target.c b/drivers/md/dm-zoned-target.c index 697f9de37355..7e88df64d197 100644 --- a/drivers/md/dm-zoned-target.c +++ b/drivers/md/dm-zoned-target.c @@ -1143,7 +1143,7 @@ static int dmz_message(struct dm_target *ti, unsigned int argc, char **argv, static struct target_type dmz_type = { .name = "zoned", .version = {2, 0, 0}, - .features = DM_TARGET_SINGLETON | DM_TARGET_ZONED_HM, + .features = DM_TARGET_SINGLETON | DM_TARGET_MIXED_ZONED_MODEL, .module = THIS_MODULE, .ctr = dmz_ctr, .dtr = dmz_dtr, diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 50b693d776d6..3f3be9408afa 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -2036,7 +2036,10 @@ static struct dm_table *__bind(struct mapped_device *md, struct dm_table *t, if (size != dm_get_size(md)) memset(&md->geometry, 0, sizeof(md->geometry)); - set_capacity_and_notify(md->disk, size); + if (!get_capacity(md->disk)) + set_capacity(md->disk, size); + else + set_capacity_and_notify(md->disk, size); dm_table_event_callback(t, event_callback, md); diff --git a/drivers/media/firewire/firedtv-fw.c b/drivers/media/firewire/firedtv-fw.c index 8a8585261bb8..5f6e97a8d1c0 100644 --- a/drivers/media/firewire/firedtv-fw.c +++ b/drivers/media/firewire/firedtv-fw.c @@ -430,4 +430,3 @@ MODULE_AUTHOR("Andreas Monitzer <andy@monitzer.com>"); MODULE_AUTHOR("Ben Backx <ben@bbackx.com>"); MODULE_DESCRIPTION("FireDTV DVB Driver"); MODULE_LICENSE("GPL"); -MODULE_SUPPORTED_DEVICE("FireDTV DVB"); diff --git a/drivers/media/pci/cx18/cx18-alsa-main.c b/drivers/media/pci/cx18/cx18-alsa-main.c index 692b95a685d1..9a82e68303b6 100644 --- a/drivers/media/pci/cx18/cx18-alsa-main.c +++ b/drivers/media/pci/cx18/cx18-alsa-main.c @@ -41,7 +41,6 @@ MODULE_PARM_DESC(debug, MODULE_AUTHOR("Andy Walls"); MODULE_DESCRIPTION("CX23418 ALSA Interface"); -MODULE_SUPPORTED_DEVICE("CX23418 MPEG2 encoder"); MODULE_LICENSE("GPL"); MODULE_VERSION(CX18_VERSION); diff --git a/drivers/media/pci/cx18/cx18-driver.c b/drivers/media/pci/cx18/cx18-driver.c index 95aed00f353b..f2440eb38820 100644 --- a/drivers/media/pci/cx18/cx18-driver.c +++ b/drivers/media/pci/cx18/cx18-driver.c @@ -232,7 +232,6 @@ MODULE_PARM_DESC(cx18_first_minor, MODULE_AUTHOR("Hans Verkuil"); MODULE_DESCRIPTION("CX23418 driver"); -MODULE_SUPPORTED_DEVICE("CX23418 MPEG2 encoder"); MODULE_LICENSE("GPL"); MODULE_VERSION(CX18_VERSION); diff --git a/drivers/media/pci/cx25821/cx25821-alsa.c b/drivers/media/pci/cx25821/cx25821-alsa.c index 608fbaf0f659..8797d85a6b0a 100644 --- a/drivers/media/pci/cx25821/cx25821-alsa.c +++ b/drivers/media/pci/cx25821/cx25821-alsa.c @@ -104,7 +104,6 @@ MODULE_PARM_DESC(index, "Index value for cx25821 capture interface(s)."); MODULE_DESCRIPTION("ALSA driver module for cx25821 based capture cards"); MODULE_AUTHOR("Hiep Huynh"); MODULE_LICENSE("GPL"); -MODULE_SUPPORTED_DEVICE("{{Conexant,25821}"); /* "{{Conexant,23881}," */ static unsigned int debug; module_param(debug, int, 0644); diff --git a/drivers/media/pci/cx88/cx88-alsa.c b/drivers/media/pci/cx88/cx88-alsa.c index 95e0cbb1277d..c83814c052d3 100644 --- a/drivers/media/pci/cx88/cx88-alsa.c +++ b/drivers/media/pci/cx88/cx88-alsa.c @@ -98,7 +98,6 @@ MODULE_AUTHOR("Mauro Carvalho Chehab <mchehab@kernel.org>"); MODULE_LICENSE("GPL v2"); MODULE_VERSION(CX88_VERSION); -MODULE_SUPPORTED_DEVICE("{{Conexant,23881},{{Conexant,23882},{{Conexant,23883}"); static unsigned int debug; module_param(debug, int, 0644); MODULE_PARM_DESC(debug, "enable debug messages"); diff --git a/drivers/media/pci/ivtv/ivtv-alsa-main.c b/drivers/media/pci/ivtv/ivtv-alsa-main.c index 39029b8e12c9..4cefdb2e4d40 100644 --- a/drivers/media/pci/ivtv/ivtv-alsa-main.c +++ b/drivers/media/pci/ivtv/ivtv-alsa-main.c @@ -38,7 +38,6 @@ MODULE_PARM_DESC(index, MODULE_AUTHOR("Andy Walls"); MODULE_DESCRIPTION("CX23415/CX23416 ALSA Interface"); -MODULE_SUPPORTED_DEVICE("CX23415/CX23416 MPEG2 encoder"); MODULE_LICENSE("GPL"); MODULE_VERSION(IVTV_VERSION); diff --git a/drivers/media/pci/ivtv/ivtv-driver.c b/drivers/media/pci/ivtv/ivtv-driver.c index 6e448cb3b51c..942b8c266f50 100644 --- a/drivers/media/pci/ivtv/ivtv-driver.c +++ b/drivers/media/pci/ivtv/ivtv-driver.c @@ -275,9 +275,6 @@ MODULE_PARM_DESC(ivtv_first_minor, "Set device node number assigned to first car MODULE_AUTHOR("Kevin Thayer, Chris Kennedy, Hans Verkuil"); MODULE_DESCRIPTION("CX23415/CX23416 driver"); -MODULE_SUPPORTED_DEVICE - ("CX23415/CX23416 MPEG2 encoder (WinTV PVR-150/250/350/500,\n" - "\t\t\tYuan MPG series and similar)"); MODULE_LICENSE("GPL"); MODULE_VERSION(IVTV_VERSION); diff --git a/drivers/media/pci/sta2x11/sta2x11_vip.c b/drivers/media/pci/sta2x11/sta2x11_vip.c index 336df65c8af1..524912f20d9f 100644 --- a/drivers/media/pci/sta2x11/sta2x11_vip.c +++ b/drivers/media/pci/sta2x11/sta2x11_vip.c @@ -1269,6 +1269,5 @@ late_initcall_sync(sta2x11_vip_init_module); MODULE_DESCRIPTION("STA2X11 Video Input Port driver"); MODULE_AUTHOR("Wind River"); MODULE_LICENSE("GPL v2"); -MODULE_SUPPORTED_DEVICE("sta2x11 video input"); MODULE_VERSION(DRV_VERSION); MODULE_DEVICE_TABLE(pci, sta2x11_vip_pci_tbl); diff --git a/drivers/media/platform/atmel/atmel-isi.c b/drivers/media/platform/atmel/atmel-isi.c index 0514be6153df..e392b3efe363 100644 --- a/drivers/media/platform/atmel/atmel-isi.c +++ b/drivers/media/platform/atmel/atmel-isi.c @@ -1363,4 +1363,3 @@ module_platform_driver(atmel_isi_driver); MODULE_AUTHOR("Josh Wu <josh.wu@atmel.com>"); MODULE_DESCRIPTION("The V4L2 driver for Atmel Linux"); MODULE_LICENSE("GPL"); -MODULE_SUPPORTED_DEVICE("video"); diff --git a/drivers/media/platform/atmel/atmel-sama5d2-isc.c b/drivers/media/platform/atmel/atmel-sama5d2-isc.c index 0b78fecfd2a8..61d9885765f4 100644 --- a/drivers/media/platform/atmel/atmel-sama5d2-isc.c +++ b/drivers/media/platform/atmel/atmel-sama5d2-isc.c @@ -330,4 +330,3 @@ module_platform_driver(atmel_isc_driver); MODULE_AUTHOR("Songjun Wu"); MODULE_DESCRIPTION("The V4L2 driver for Atmel-ISC"); MODULE_LICENSE("GPL v2"); -MODULE_SUPPORTED_DEVICE("video"); diff --git a/drivers/media/platform/marvell-ccic/cafe-driver.c b/drivers/media/platform/marvell-ccic/cafe-driver.c index 9c94a8b58b7c..baac86f3d153 100644 --- a/drivers/media/platform/marvell-ccic/cafe-driver.c +++ b/drivers/media/platform/marvell-ccic/cafe-driver.c @@ -44,10 +44,6 @@ MODULE_AUTHOR("Jonathan Corbet <corbet@lwn.net>"); MODULE_DESCRIPTION("Marvell 88ALP01 CMOS Camera Controller driver"); MODULE_LICENSE("GPL"); -MODULE_SUPPORTED_DEVICE("Video"); - - - struct cafe_camera { int registered; /* Fully initialized? */ diff --git a/drivers/media/platform/stm32/stm32-dcmi.c b/drivers/media/platform/stm32/stm32-dcmi.c index bbcc2254fa2e..d9b4ad0abf0c 100644 --- a/drivers/media/platform/stm32/stm32-dcmi.c +++ b/drivers/media/platform/stm32/stm32-dcmi.c @@ -2149,4 +2149,3 @@ MODULE_AUTHOR("Yannick Fertre <yannick.fertre@st.com>"); MODULE_AUTHOR("Hugues Fruchet <hugues.fruchet@st.com>"); MODULE_DESCRIPTION("STMicroelectronics STM32 Digital Camera Memory Interface driver"); MODULE_LICENSE("GPL"); -MODULE_SUPPORTED_DEVICE("video"); diff --git a/drivers/media/usb/cpia2/cpia2_v4l.c b/drivers/media/usb/cpia2/cpia2_v4l.c index e488e7870f42..69d5c628a797 100644 --- a/drivers/media/usb/cpia2/cpia2_v4l.c +++ b/drivers/media/usb/cpia2/cpia2_v4l.c @@ -56,7 +56,6 @@ MODULE_PARM_DESC(flicker_mode, "Flicker frequency (0 (disabled), " __stringify(5 MODULE_AUTHOR("Steve Miller (STMicroelectronics) <steve.miller@st.com>"); MODULE_DESCRIPTION("V4L-driver for STMicroelectronics CPiA2 based cameras"); -MODULE_SUPPORTED_DEVICE("video"); MODULE_LICENSE("GPL"); MODULE_VERSION(CPIA_VERSION); diff --git a/drivers/media/usb/tm6000/tm6000-alsa.c b/drivers/media/usb/tm6000/tm6000-alsa.c index 3a2df36ef1db..a19a46770c2b 100644 --- a/drivers/media/usb/tm6000/tm6000-alsa.c +++ b/drivers/media/usb/tm6000/tm6000-alsa.c @@ -51,7 +51,6 @@ MODULE_PARM_DESC(index, "Index value for tm6000x capture interface(s)."); MODULE_DESCRIPTION("ALSA driver module for tm5600/tm6000/tm6010 based TV cards"); MODULE_AUTHOR("Mauro Carvalho Chehab"); MODULE_LICENSE("GPL v2"); -MODULE_SUPPORTED_DEVICE("{{Trident,tm5600},{{Trident,tm6000},{{Trident,tm6010}"); static unsigned int debug; module_param(debug, int, 0644); MODULE_PARM_DESC(debug, "enable debug messages"); diff --git a/drivers/media/usb/tm6000/tm6000-dvb.c b/drivers/media/usb/tm6000/tm6000-dvb.c index 293a460f4616..4990fa886d7a 100644 --- a/drivers/media/usb/tm6000/tm6000-dvb.c +++ b/drivers/media/usb/tm6000/tm6000-dvb.c @@ -23,8 +23,6 @@ MODULE_DESCRIPTION("DVB driver extension module for tm5600/6000/6010 based TV ca MODULE_AUTHOR("Mauro Carvalho Chehab"); MODULE_LICENSE("GPL"); -MODULE_SUPPORTED_DEVICE("{{Trident, tm5600},{{Trident, tm6000},{{Trident, tm6010}"); - static int debug; module_param(debug, int, 0644); diff --git a/drivers/mfd/intel_quark_i2c_gpio.c b/drivers/mfd/intel_quark_i2c_gpio.c index fe8ca945f367..b67cb0a3ab05 100644 --- a/drivers/mfd/intel_quark_i2c_gpio.c +++ b/drivers/mfd/intel_quark_i2c_gpio.c @@ -72,7 +72,8 @@ static const struct dmi_system_id dmi_platform_info[] = { {} }; -static const struct resource intel_quark_i2c_res[] = { +/* This is used as a place holder and will be modified at run-time */ +static struct resource intel_quark_i2c_res[] = { [INTEL_QUARK_IORES_MEM] = { .flags = IORESOURCE_MEM, }, @@ -85,7 +86,8 @@ static struct mfd_cell_acpi_match intel_quark_acpi_match_i2c = { .adr = MFD_ACPI_MATCH_I2C, }; -static const struct resource intel_quark_gpio_res[] = { +/* This is used as a place holder and will be modified at run-time */ +static struct resource intel_quark_gpio_res[] = { [INTEL_QUARK_IORES_MEM] = { .flags = IORESOURCE_MEM, }, diff --git a/drivers/misc/mei/client.c b/drivers/misc/mei/client.c index 4378a9b25848..2cc370adb238 100644 --- a/drivers/misc/mei/client.c +++ b/drivers/misc/mei/client.c @@ -2286,8 +2286,8 @@ int mei_cl_dma_alloc_and_map(struct mei_cl *cl, const struct file *fp, if (buffer_id == 0) return -EINVAL; - if (!mei_cl_is_connected(cl)) - return -ENODEV; + if (mei_cl_is_connected(cl)) + return -EPROTO; if (cl->dma_mapped) return -EPROTO; @@ -2327,9 +2327,7 @@ int mei_cl_dma_alloc_and_map(struct mei_cl *cl, const struct file *fp, mutex_unlock(&dev->device_lock); wait_event_timeout(cl->wait, - cl->dma_mapped || - cl->status || - !mei_cl_is_connected(cl), + cl->dma_mapped || cl->status, mei_secs_to_jiffies(MEI_CL_CONNECT_TIMEOUT)); mutex_lock(&dev->device_lock); @@ -2376,8 +2374,9 @@ int mei_cl_dma_unmap(struct mei_cl *cl, const struct file *fp) return -EOPNOTSUPP; } - if (!mei_cl_is_connected(cl)) - return -ENODEV; + /* do not allow unmap for connected client */ + if (mei_cl_is_connected(cl)) + return -EPROTO; if (!cl->dma_mapped) return -EPROTO; @@ -2405,9 +2404,7 @@ int mei_cl_dma_unmap(struct mei_cl *cl, const struct file *fp) mutex_unlock(&dev->device_lock); wait_event_timeout(cl->wait, - !cl->dma_mapped || - cl->status || - !mei_cl_is_connected(cl), + !cl->dma_mapped || cl->status, mei_secs_to_jiffies(MEI_CL_CONNECT_TIMEOUT)); mutex_lock(&dev->device_lock); diff --git a/drivers/mtd/maps/sun_uflash.c b/drivers/mtd/maps/sun_uflash.c index eb7258293256..f9cfb084c029 100644 --- a/drivers/mtd/maps/sun_uflash.c +++ b/drivers/mtd/maps/sun_uflash.c @@ -32,7 +32,6 @@ MODULE_AUTHOR("Eric Brower <ebrower@usa.net>"); MODULE_DESCRIPTION("User-programmable flash device on Sun Microsystems boardsets"); -MODULE_SUPPORTED_DEVICE(DRIVER_NAME); MODULE_LICENSE("GPL"); MODULE_VERSION("2.1"); diff --git a/drivers/net/arcnet/com20020-pci.c b/drivers/net/arcnet/com20020-pci.c index 8bdc44b7e09a..3c8f665c1558 100644 --- a/drivers/net/arcnet/com20020-pci.c +++ b/drivers/net/arcnet/com20020-pci.c @@ -127,6 +127,8 @@ static int com20020pci_probe(struct pci_dev *pdev, int i, ioaddr, ret; struct resource *r; + ret = 0; + if (pci_enable_device(pdev)) return -EIO; @@ -139,6 +141,8 @@ static int com20020pci_probe(struct pci_dev *pdev, priv->ci = ci; mm = &ci->misc_map; + pci_set_drvdata(pdev, priv); + INIT_LIST_HEAD(&priv->list_dev); if (mm->size) { @@ -161,7 +165,7 @@ static int com20020pci_probe(struct pci_dev *pdev, dev = alloc_arcdev(device); if (!dev) { ret = -ENOMEM; - goto out_port; + break; } dev->dev_port = i; @@ -178,7 +182,7 @@ static int com20020pci_probe(struct pci_dev *pdev, pr_err("IO region %xh-%xh already allocated\n", ioaddr, ioaddr + cm->size - 1); ret = -EBUSY; - goto out_port; + goto err_free_arcdev; } /* Dummy access after Reset @@ -216,18 +220,18 @@ static int com20020pci_probe(struct pci_dev *pdev, if (arcnet_inb(ioaddr, COM20020_REG_R_STATUS) == 0xFF) { pr_err("IO address %Xh is empty!\n", ioaddr); ret = -EIO; - goto out_port; + goto err_free_arcdev; } if (com20020_check(dev)) { ret = -EIO; - goto out_port; + goto err_free_arcdev; } card = devm_kzalloc(&pdev->dev, sizeof(struct com20020_dev), GFP_KERNEL); if (!card) { ret = -ENOMEM; - goto out_port; + goto err_free_arcdev; } card->index = i; @@ -253,29 +257,29 @@ static int com20020pci_probe(struct pci_dev *pdev, ret = devm_led_classdev_register(&pdev->dev, &card->tx_led); if (ret) - goto out_port; + goto err_free_arcdev; ret = devm_led_classdev_register(&pdev->dev, &card->recon_led); if (ret) - goto out_port; + goto err_free_arcdev; dev_set_drvdata(&dev->dev, card); ret = com20020_found(dev, IRQF_SHARED); if (ret) - goto out_port; + goto err_free_arcdev; devm_arcnet_led_init(dev, dev->dev_id, i); list_add(&card->list, &priv->list_dev); - } + continue; - pci_set_drvdata(pdev, priv); - - return 0; - -out_port: - com20020pci_remove(pdev); +err_free_arcdev: + free_arcdev(dev); + break; + } + if (ret) + com20020pci_remove(pdev); return ret; } diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 456315bef3a8..74cbbb22470b 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -3978,15 +3978,11 @@ static int bond_neigh_init(struct neighbour *n) rcu_read_lock(); slave = bond_first_slave_rcu(bond); - if (!slave) { - ret = -EINVAL; + if (!slave) goto out; - } slave_ops = slave->dev->netdev_ops; - if (!slave_ops->ndo_neigh_setup) { - ret = -EINVAL; + if (!slave_ops->ndo_neigh_setup) goto out; - } /* TODO: find another way [1] to implement this. * Passing a zeroed structure is fragile, diff --git a/drivers/net/can/c_can/c_can.c b/drivers/net/can/c_can/c_can.c index ef474bae47a1..6958830cb983 100644 --- a/drivers/net/can/c_can/c_can.c +++ b/drivers/net/can/c_can/c_can.c @@ -212,18 +212,6 @@ static const struct can_bittiming_const c_can_bittiming_const = { .brp_inc = 1, }; -static inline void c_can_pm_runtime_enable(const struct c_can_priv *priv) -{ - if (priv->device) - pm_runtime_enable(priv->device); -} - -static inline void c_can_pm_runtime_disable(const struct c_can_priv *priv) -{ - if (priv->device) - pm_runtime_disable(priv->device); -} - static inline void c_can_pm_runtime_get_sync(const struct c_can_priv *priv) { if (priv->device) @@ -1335,7 +1323,6 @@ static const struct net_device_ops c_can_netdev_ops = { int register_c_can_dev(struct net_device *dev) { - struct c_can_priv *priv = netdev_priv(dev); int err; /* Deactivate pins to prevent DRA7 DCAN IP from being @@ -1345,28 +1332,19 @@ int register_c_can_dev(struct net_device *dev) */ pinctrl_pm_select_sleep_state(dev->dev.parent); - c_can_pm_runtime_enable(priv); - dev->flags |= IFF_ECHO; /* we support local echo */ dev->netdev_ops = &c_can_netdev_ops; err = register_candev(dev); - if (err) - c_can_pm_runtime_disable(priv); - else + if (!err) devm_can_led_init(dev); - return err; } EXPORT_SYMBOL_GPL(register_c_can_dev); void unregister_c_can_dev(struct net_device *dev) { - struct c_can_priv *priv = netdev_priv(dev); - unregister_candev(dev); - - c_can_pm_runtime_disable(priv); } EXPORT_SYMBOL_GPL(unregister_c_can_dev); diff --git a/drivers/net/can/c_can/c_can_pci.c b/drivers/net/can/c_can/c_can_pci.c index 406b4847e5dc..7efb60b50876 100644 --- a/drivers/net/can/c_can/c_can_pci.c +++ b/drivers/net/can/c_can/c_can_pci.c @@ -239,12 +239,13 @@ static void c_can_pci_remove(struct pci_dev *pdev) { struct net_device *dev = pci_get_drvdata(pdev); struct c_can_priv *priv = netdev_priv(dev); + void __iomem *addr = priv->base; unregister_c_can_dev(dev); free_c_can_dev(dev); - pci_iounmap(pdev, priv->base); + pci_iounmap(pdev, addr); pci_disable_msi(pdev); pci_clear_master(pdev); pci_release_regions(pdev); diff --git a/drivers/net/can/c_can/c_can_platform.c b/drivers/net/can/c_can/c_can_platform.c index 05f425ceb53a..47b251b1607c 100644 --- a/drivers/net/can/c_can/c_can_platform.c +++ b/drivers/net/can/c_can/c_can_platform.c @@ -29,6 +29,7 @@ #include <linux/list.h> #include <linux/io.h> #include <linux/platform_device.h> +#include <linux/pm_runtime.h> #include <linux/clk.h> #include <linux/of.h> #include <linux/of_device.h> @@ -386,6 +387,7 @@ static int c_can_plat_probe(struct platform_device *pdev) platform_set_drvdata(pdev, dev); SET_NETDEV_DEV(dev, &pdev->dev); + pm_runtime_enable(priv->device); ret = register_c_can_dev(dev); if (ret) { dev_err(&pdev->dev, "registering %s failed (err=%d)\n", @@ -398,6 +400,7 @@ static int c_can_plat_probe(struct platform_device *pdev) return 0; exit_free_device: + pm_runtime_disable(priv->device); free_c_can_dev(dev); exit: dev_err(&pdev->dev, "probe failed\n"); @@ -408,9 +411,10 @@ exit: static int c_can_plat_remove(struct platform_device *pdev) { struct net_device *dev = platform_get_drvdata(pdev); + struct c_can_priv *priv = netdev_priv(dev); unregister_c_can_dev(dev); - + pm_runtime_disable(priv->device); free_c_can_dev(dev); return 0; diff --git a/drivers/net/can/dev/netlink.c b/drivers/net/can/dev/netlink.c index 867f6be31230..f5d79e6e5483 100644 --- a/drivers/net/can/dev/netlink.c +++ b/drivers/net/can/dev/netlink.c @@ -355,6 +355,7 @@ static void can_dellink(struct net_device *dev, struct list_head *head) struct rtnl_link_ops can_link_ops __read_mostly = { .kind = "can", + .netns_refund = true, .maxtype = IFLA_CAN_MAX, .policy = can_policy, .setup = can_setup, diff --git a/drivers/net/can/flexcan.c b/drivers/net/can/flexcan.c index 134c05757a3b..57f3635ad8d7 100644 --- a/drivers/net/can/flexcan.c +++ b/drivers/net/can/flexcan.c @@ -697,9 +697,15 @@ static int flexcan_chip_disable(struct flexcan_priv *priv) static int flexcan_chip_freeze(struct flexcan_priv *priv) { struct flexcan_regs __iomem *regs = priv->regs; - unsigned int timeout = 1000 * 1000 * 10 / priv->can.bittiming.bitrate; + unsigned int timeout; + u32 bitrate = priv->can.bittiming.bitrate; u32 reg; + if (bitrate) + timeout = 1000 * 1000 * 10 / bitrate; + else + timeout = FLEXCAN_TIMEOUT_US / 10; + reg = priv->read(®s->mcr); reg |= FLEXCAN_MCR_FRZ | FLEXCAN_MCR_HALT; priv->write(reg, ®s->mcr); diff --git a/drivers/net/can/kvaser_pciefd.c b/drivers/net/can/kvaser_pciefd.c index 37e05010ca91..74d9899fc904 100644 --- a/drivers/net/can/kvaser_pciefd.c +++ b/drivers/net/can/kvaser_pciefd.c @@ -57,6 +57,7 @@ MODULE_DESCRIPTION("CAN driver for Kvaser CAN/PCIe devices"); #define KVASER_PCIEFD_KCAN_STAT_REG 0x418 #define KVASER_PCIEFD_KCAN_MODE_REG 0x41c #define KVASER_PCIEFD_KCAN_BTRN_REG 0x420 +#define KVASER_PCIEFD_KCAN_BUS_LOAD_REG 0x424 #define KVASER_PCIEFD_KCAN_BTRD_REG 0x428 #define KVASER_PCIEFD_KCAN_PWM_REG 0x430 /* Loopback control register */ @@ -949,6 +950,9 @@ static int kvaser_pciefd_setup_can_ctrls(struct kvaser_pciefd *pcie) timer_setup(&can->bec_poll_timer, kvaser_pciefd_bec_poll_timer, 0); + /* Disable Bus load reporting */ + iowrite32(0, can->reg_base + KVASER_PCIEFD_KCAN_BUS_LOAD_REG); + tx_npackets = ioread32(can->reg_base + KVASER_PCIEFD_KCAN_TX_NPACKETS_REG); if (((tx_npackets >> KVASER_PCIEFD_KCAN_TX_NPACKETS_MAX_SHIFT) & diff --git a/drivers/net/can/m_can/m_can.c b/drivers/net/can/m_can/m_can.c index 3752520a7d4b..0c8d36bc668c 100644 --- a/drivers/net/can/m_can/m_can.c +++ b/drivers/net/can/m_can/m_can.c @@ -501,9 +501,6 @@ static int m_can_do_rx_poll(struct net_device *dev, int quota) } while ((rxfs & RXFS_FFL_MASK) && (quota > 0)) { - if (rxfs & RXFS_RFL) - netdev_warn(dev, "Rx FIFO 0 Message Lost\n"); - m_can_read_fifo(dev, rxfs); quota--; @@ -876,7 +873,7 @@ static int m_can_rx_peripheral(struct net_device *dev) { struct m_can_classdev *cdev = netdev_priv(dev); - m_can_rx_handler(dev, 1); + m_can_rx_handler(dev, M_CAN_NAPI_WEIGHT); m_can_enable_all_interrupts(cdev); diff --git a/drivers/net/can/peak_canfd/peak_pciefd_main.c b/drivers/net/can/peak_canfd/peak_pciefd_main.c index 0df1cdfa6835..1df3c4b54f03 100644 --- a/drivers/net/can/peak_canfd/peak_pciefd_main.c +++ b/drivers/net/can/peak_canfd/peak_pciefd_main.c @@ -21,7 +21,6 @@ MODULE_AUTHOR("Stephane Grosjean <s.grosjean@peak-system.com>"); MODULE_DESCRIPTION("Socket-CAN driver for PEAK PCAN PCIe/M.2 FD family cards"); -MODULE_SUPPORTED_DEVICE("PEAK PCAN PCIe/M.2 FD CAN cards"); MODULE_LICENSE("GPL v2"); #define PCIEFD_DRV_NAME "peak_pciefd" diff --git a/drivers/net/can/sja1000/ems_pci.c b/drivers/net/can/sja1000/ems_pci.c index 6f88c9932920..4ab91759a5c6 100644 --- a/drivers/net/can/sja1000/ems_pci.c +++ b/drivers/net/can/sja1000/ems_pci.c @@ -21,7 +21,6 @@ MODULE_AUTHOR("Sebastian Haas <haas@ems-wuenche.com>"); MODULE_DESCRIPTION("Socket-CAN driver for EMS CPC-PCI/PCIe/104P CAN cards"); -MODULE_SUPPORTED_DEVICE("EMS CPC-PCI/PCIe/104P CAN card"); MODULE_LICENSE("GPL v2"); #define EMS_PCI_V1_MAX_CHAN 2 diff --git a/drivers/net/can/sja1000/ems_pcmcia.c b/drivers/net/can/sja1000/ems_pcmcia.c index 770304eaef95..e21b169c14c0 100644 --- a/drivers/net/can/sja1000/ems_pcmcia.c +++ b/drivers/net/can/sja1000/ems_pcmcia.c @@ -21,7 +21,6 @@ MODULE_AUTHOR("Markus Plessing <plessing@ems-wuensche.com>"); MODULE_DESCRIPTION("Socket-CAN driver for EMS CPC-CARD cards"); -MODULE_SUPPORTED_DEVICE("EMS CPC-CARD CAN card"); MODULE_LICENSE("GPL v2"); #define EMS_PCMCIA_MAX_CHAN 2 diff --git a/drivers/net/can/sja1000/kvaser_pci.c b/drivers/net/can/sja1000/kvaser_pci.c index 0ea6b711c07b..95fe9ee1ce32 100644 --- a/drivers/net/can/sja1000/kvaser_pci.c +++ b/drivers/net/can/sja1000/kvaser_pci.c @@ -33,7 +33,6 @@ MODULE_AUTHOR("Per Dalen <per.dalen@cnw.se>"); MODULE_DESCRIPTION("Socket-CAN driver for KVASER PCAN PCI cards"); -MODULE_SUPPORTED_DEVICE("KVASER PCAN PCI CAN card"); MODULE_LICENSE("GPL v2"); #define MAX_NO_OF_CHANNELS 4 /* max no of channels on a single card */ diff --git a/drivers/net/can/sja1000/peak_pci.c b/drivers/net/can/sja1000/peak_pci.c index 4713921bd511..84eac8cb8686 100644 --- a/drivers/net/can/sja1000/peak_pci.c +++ b/drivers/net/can/sja1000/peak_pci.c @@ -24,8 +24,6 @@ MODULE_AUTHOR("Stephane Grosjean <s.grosjean@peak-system.com>"); MODULE_DESCRIPTION("Socket-CAN driver for PEAK PCAN PCI family cards"); -MODULE_SUPPORTED_DEVICE("PEAK PCAN PCI/PCIe/PCIeC miniPCI CAN cards"); -MODULE_SUPPORTED_DEVICE("PEAK PCAN miniPCIe/cPCI PC/104+ PCI/104e CAN Cards"); MODULE_LICENSE("GPL v2"); #define DRV_NAME "peak_pci" diff --git a/drivers/net/can/sja1000/peak_pcmcia.c b/drivers/net/can/sja1000/peak_pcmcia.c index cf951a783078..131a084c3535 100644 --- a/drivers/net/can/sja1000/peak_pcmcia.c +++ b/drivers/net/can/sja1000/peak_pcmcia.c @@ -22,7 +22,6 @@ MODULE_AUTHOR("Stephane Grosjean <s.grosjean@peak-system.com>"); MODULE_DESCRIPTION("CAN driver for PEAK-System PCAN-PC Cards"); MODULE_LICENSE("GPL v2"); -MODULE_SUPPORTED_DEVICE("PEAK PCAN-PC Card"); /* PEAK-System PCMCIA driver name */ #define PCC_NAME "peak_pcmcia" diff --git a/drivers/net/can/sja1000/plx_pci.c b/drivers/net/can/sja1000/plx_pci.c index 85679588ef73..5de1ebb0c6f0 100644 --- a/drivers/net/can/sja1000/plx_pci.c +++ b/drivers/net/can/sja1000/plx_pci.c @@ -25,18 +25,6 @@ MODULE_AUTHOR("Pavel Cheblakov <P.B.Cheblakov@inp.nsk.su>"); MODULE_DESCRIPTION("Socket-CAN driver for PLX90xx PCI-bridge cards with " "the SJA1000 chips"); -MODULE_SUPPORTED_DEVICE("Adlink PCI-7841/cPCI-7841, " - "Adlink PCI-7841/cPCI-7841 SE, " - "Marathon CAN-bus-PCI, " - "Marathon CAN-bus-PCIe, " - "TEWS TECHNOLOGIES TPMC810, " - "esd CAN-PCI/CPCI/PCI104/200, " - "esd CAN-PCI/PMC/266, " - "esd CAN-PCIe/2000, " - "Connect Tech Inc. CANpro/104-Plus Opto (CRG001), " - "IXXAT PC-I 04/PCI, " - "ELCUS CAN-200-PCI, " - "ASEM DUAL CAN-RAW") MODULE_LICENSE("GPL v2"); #define PLX_PCI_MAX_CHAN 2 diff --git a/drivers/net/can/spi/mcp251x.c b/drivers/net/can/spi/mcp251x.c index f69fb4238a65..a57da43680d8 100644 --- a/drivers/net/can/spi/mcp251x.c +++ b/drivers/net/can/spi/mcp251x.c @@ -314,6 +314,18 @@ static int mcp251x_spi_trans(struct spi_device *spi, int len) return ret; } +static int mcp251x_spi_write(struct spi_device *spi, int len) +{ + struct mcp251x_priv *priv = spi_get_drvdata(spi); + int ret; + + ret = spi_write(spi, priv->spi_tx_buf, len); + if (ret) + dev_err(&spi->dev, "spi write failed: ret = %d\n", ret); + + return ret; +} + static u8 mcp251x_read_reg(struct spi_device *spi, u8 reg) { struct mcp251x_priv *priv = spi_get_drvdata(spi); @@ -361,7 +373,7 @@ static void mcp251x_write_reg(struct spi_device *spi, u8 reg, u8 val) priv->spi_tx_buf[1] = reg; priv->spi_tx_buf[2] = val; - mcp251x_spi_trans(spi, 3); + mcp251x_spi_write(spi, 3); } static void mcp251x_write_2regs(struct spi_device *spi, u8 reg, u8 v1, u8 v2) @@ -373,7 +385,7 @@ static void mcp251x_write_2regs(struct spi_device *spi, u8 reg, u8 v1, u8 v2) priv->spi_tx_buf[2] = v1; priv->spi_tx_buf[3] = v2; - mcp251x_spi_trans(spi, 4); + mcp251x_spi_write(spi, 4); } static void mcp251x_write_bits(struct spi_device *spi, u8 reg, @@ -386,7 +398,7 @@ static void mcp251x_write_bits(struct spi_device *spi, u8 reg, priv->spi_tx_buf[2] = mask; priv->spi_tx_buf[3] = val; - mcp251x_spi_trans(spi, 4); + mcp251x_spi_write(spi, 4); } static u8 mcp251x_read_stat(struct spi_device *spi) @@ -618,7 +630,7 @@ static void mcp251x_hw_tx_frame(struct spi_device *spi, u8 *buf, buf[i]); } else { memcpy(priv->spi_tx_buf, buf, TXBDAT_OFF + len); - mcp251x_spi_trans(spi, TXBDAT_OFF + len); + mcp251x_spi_write(spi, TXBDAT_OFF + len); } } @@ -650,7 +662,7 @@ static void mcp251x_hw_tx(struct spi_device *spi, struct can_frame *frame, /* use INSTRUCTION_RTS, to avoid "repeated frame problem" */ priv->spi_tx_buf[0] = INSTRUCTION_RTS(1 << tx_buf_idx); - mcp251x_spi_trans(priv->spi, 1); + mcp251x_spi_write(priv->spi, 1); } static void mcp251x_hw_rx_frame(struct spi_device *spi, u8 *buf, @@ -888,7 +900,7 @@ static int mcp251x_hw_reset(struct spi_device *spi) mdelay(MCP251X_OST_DELAY_MS); priv->spi_tx_buf[0] = INSTRUCTION_RESET; - ret = mcp251x_spi_trans(spi, 1); + ret = mcp251x_spi_write(spi, 1); if (ret) return ret; diff --git a/drivers/net/can/usb/Kconfig b/drivers/net/can/usb/Kconfig index c1e5d5b570b6..538f4d9adb91 100644 --- a/drivers/net/can/usb/Kconfig +++ b/drivers/net/can/usb/Kconfig @@ -73,6 +73,7 @@ config CAN_KVASER_USB - Kvaser Memorator Pro 5xHS - Kvaser USBcan Light 4xHS - Kvaser USBcan Pro 2xHS v2 + - Kvaser USBcan Pro 4xHS - Kvaser USBcan Pro 5xHS - Kvaser U100 - Kvaser U100P diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c index 2b7efd296758..4e97da8434ab 100644 --- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c +++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c @@ -86,8 +86,9 @@ #define USB_U100_PRODUCT_ID 273 #define USB_U100P_PRODUCT_ID 274 #define USB_U100S_PRODUCT_ID 275 +#define USB_USBCAN_PRO_4HS_PRODUCT_ID 276 #define USB_HYDRA_PRODUCT_ID_END \ - USB_U100S_PRODUCT_ID + USB_USBCAN_PRO_4HS_PRODUCT_ID static inline bool kvaser_is_leaf(const struct usb_device_id *id) { @@ -193,6 +194,7 @@ static const struct usb_device_id kvaser_usb_table[] = { { USB_DEVICE(KVASER_VENDOR_ID, USB_U100_PRODUCT_ID) }, { USB_DEVICE(KVASER_VENDOR_ID, USB_U100P_PRODUCT_ID) }, { USB_DEVICE(KVASER_VENDOR_ID, USB_U100S_PRODUCT_ID) }, + { USB_DEVICE(KVASER_VENDOR_ID, USB_USBCAN_PRO_4HS_PRODUCT_ID) }, { } }; MODULE_DEVICE_TABLE(usb, kvaser_usb_table); diff --git a/drivers/net/can/usb/peak_usb/pcan_usb.c b/drivers/net/can/usb/peak_usb/pcan_usb.c index e6c1e5d33924..e393e8457d77 100644 --- a/drivers/net/can/usb/peak_usb/pcan_usb.c +++ b/drivers/net/can/usb/peak_usb/pcan_usb.c @@ -18,8 +18,6 @@ #include "pcan_usb_core.h" -MODULE_SUPPORTED_DEVICE("PEAK-System PCAN-USB adapter"); - /* PCAN-USB Endpoints */ #define PCAN_USB_EP_CMDOUT 1 #define PCAN_USB_EP_CMDIN (PCAN_USB_EP_CMDOUT | USB_DIR_IN) diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_core.c b/drivers/net/can/usb/peak_usb/pcan_usb_core.c index 573b11559d73..28e916a04047 100644 --- a/drivers/net/can/usb/peak_usb/pcan_usb_core.c +++ b/drivers/net/can/usb/peak_usb/pcan_usb_core.c @@ -857,7 +857,7 @@ static int peak_usb_create_dev(const struct peak_usb_adapter *peak_usb_adapter, if (dev->adapter->dev_set_bus) { err = dev->adapter->dev_set_bus(dev, 0); if (err) - goto lbl_unregister_candev; + goto adap_dev_free; } /* get device number early */ @@ -869,6 +869,10 @@ static int peak_usb_create_dev(const struct peak_usb_adapter *peak_usb_adapter, return 0; +adap_dev_free: + if (dev->adapter->dev_free) + dev->adapter->dev_free(dev); + lbl_unregister_candev: unregister_candev(netdev); diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_fd.c b/drivers/net/can/usb/peak_usb/pcan_usb_fd.c index f347ecc79aef..bae078579c0d 100644 --- a/drivers/net/can/usb/peak_usb/pcan_usb_fd.c +++ b/drivers/net/can/usb/peak_usb/pcan_usb_fd.c @@ -16,9 +16,6 @@ #include "pcan_usb_core.h" #include "pcan_usb_pro.h" -MODULE_SUPPORTED_DEVICE("PEAK-System PCAN-USB FD adapter"); -MODULE_SUPPORTED_DEVICE("PEAK-System PCAN-USB Pro FD adapter"); - #define PCAN_USBPROFD_CHANNEL_COUNT 2 #define PCAN_USBFD_CHANNEL_COUNT 1 diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_pro.c b/drivers/net/can/usb/peak_usb/pcan_usb_pro.c index 275087c39602..18fa180ecc81 100644 --- a/drivers/net/can/usb/peak_usb/pcan_usb_pro.c +++ b/drivers/net/can/usb/peak_usb/pcan_usb_pro.c @@ -17,8 +17,6 @@ #include "pcan_usb_core.h" #include "pcan_usb_pro.h" -MODULE_SUPPORTED_DEVICE("PEAK-System PCAN-USB Pro adapter"); - #define PCAN_USBPRO_CHANNEL_COUNT 2 /* PCAN-USB Pro adapter internal clock (MHz) */ diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c index a162499bcafc..eb443721c58e 100644 --- a/drivers/net/dsa/b53/b53_common.c +++ b/drivers/net/dsa/b53/b53_common.c @@ -1105,13 +1105,6 @@ static int b53_setup(struct dsa_switch *ds) b53_disable_port(ds, port); } - /* Let DSA handle the case were multiple bridges span the same switch - * device and different VLAN awareness settings are requested, which - * would be breaking filtering semantics for any of the other bridge - * devices. (not hardware supported) - */ - ds->vlan_filtering_is_global = true; - return b53_setup_devlink_resources(ds); } @@ -2664,6 +2657,13 @@ struct b53_device *b53_switch_alloc(struct device *base, ds->ops = &b53_switch_ops; ds->untag_bridge_pvid = true; dev->vlan_enabled = true; + /* Let DSA handle the case were multiple bridges span the same switch + * device and different VLAN awareness settings are requested, which + * would be breaking filtering semantics for any of the other bridge + * devices. (not hardware supported) + */ + ds->vlan_filtering_is_global = true; + mutex_init(&dev->reg_mutex); mutex_init(&dev->stats_mutex); diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c index f277df922fcd..ba5d546d06aa 100644 --- a/drivers/net/dsa/bcm_sf2.c +++ b/drivers/net/dsa/bcm_sf2.c @@ -114,7 +114,10 @@ static void bcm_sf2_imp_setup(struct dsa_switch *ds, int port) /* Force link status for IMP port */ reg = core_readl(priv, offset); reg |= (MII_SW_OR | LINK_STS); - reg &= ~GMII_SPEED_UP_2G; + if (priv->type == BCM4908_DEVICE_ID) + reg |= GMII_SPEED_UP_2G; + else + reg &= ~GMII_SPEED_UP_2G; core_writel(priv, reg, offset); /* Enable Broadcast, Multicast, Unicast forwarding to IMP port */ @@ -585,8 +588,10 @@ static u32 bcm_sf2_sw_get_phy_flags(struct dsa_switch *ds, int port) * in bits 15:8 and the patch level in bits 7:0 which is exactly what * the REG_PHY_REVISION register layout is. */ - - return priv->hw_params.gphy_rev; + if (priv->int_phy_mask & BIT(port)) + return priv->hw_params.gphy_rev; + else + return 0; } static void bcm_sf2_sw_validate(struct dsa_switch *ds, int port, diff --git a/drivers/net/dsa/lantiq_gswip.c b/drivers/net/dsa/lantiq_gswip.c index 52e865a3912c..bf5c62e5c0b0 100644 --- a/drivers/net/dsa/lantiq_gswip.c +++ b/drivers/net/dsa/lantiq_gswip.c @@ -93,8 +93,12 @@ /* GSWIP MII Registers */ #define GSWIP_MII_CFGp(p) (0x2 * (p)) +#define GSWIP_MII_CFG_RESET BIT(15) #define GSWIP_MII_CFG_EN BIT(14) +#define GSWIP_MII_CFG_ISOLATE BIT(13) #define GSWIP_MII_CFG_LDCLKDIS BIT(12) +#define GSWIP_MII_CFG_RGMII_IBS BIT(8) +#define GSWIP_MII_CFG_RMII_CLK BIT(7) #define GSWIP_MII_CFG_MODE_MIIP 0x0 #define GSWIP_MII_CFG_MODE_MIIM 0x1 #define GSWIP_MII_CFG_MODE_RMIIP 0x2 @@ -190,6 +194,23 @@ #define GSWIP_PCE_DEFPVID(p) (0x486 + ((p) * 0xA)) #define GSWIP_MAC_FLEN 0x8C5 +#define GSWIP_MAC_CTRL_0p(p) (0x903 + ((p) * 0xC)) +#define GSWIP_MAC_CTRL_0_PADEN BIT(8) +#define GSWIP_MAC_CTRL_0_FCS_EN BIT(7) +#define GSWIP_MAC_CTRL_0_FCON_MASK 0x0070 +#define GSWIP_MAC_CTRL_0_FCON_AUTO 0x0000 +#define GSWIP_MAC_CTRL_0_FCON_RX 0x0010 +#define GSWIP_MAC_CTRL_0_FCON_TX 0x0020 +#define GSWIP_MAC_CTRL_0_FCON_RXTX 0x0030 +#define GSWIP_MAC_CTRL_0_FCON_NONE 0x0040 +#define GSWIP_MAC_CTRL_0_FDUP_MASK 0x000C +#define GSWIP_MAC_CTRL_0_FDUP_AUTO 0x0000 +#define GSWIP_MAC_CTRL_0_FDUP_EN 0x0004 +#define GSWIP_MAC_CTRL_0_FDUP_DIS 0x000C +#define GSWIP_MAC_CTRL_0_GMII_MASK 0x0003 +#define GSWIP_MAC_CTRL_0_GMII_AUTO 0x0000 +#define GSWIP_MAC_CTRL_0_GMII_MII 0x0001 +#define GSWIP_MAC_CTRL_0_GMII_RGMII 0x0002 #define GSWIP_MAC_CTRL_2p(p) (0x905 + ((p) * 0xC)) #define GSWIP_MAC_CTRL_2_MLEN BIT(3) /* Maximum Untagged Frame Lnegth */ @@ -653,16 +674,13 @@ static int gswip_port_enable(struct dsa_switch *ds, int port, GSWIP_SDMA_PCTRLp(port)); if (!dsa_is_cpu_port(ds, port)) { - u32 macconf = GSWIP_MDIO_PHY_LINK_AUTO | - GSWIP_MDIO_PHY_SPEED_AUTO | - GSWIP_MDIO_PHY_FDUP_AUTO | - GSWIP_MDIO_PHY_FCONTX_AUTO | - GSWIP_MDIO_PHY_FCONRX_AUTO | - (phydev->mdio.addr & GSWIP_MDIO_PHY_ADDR_MASK); - - gswip_mdio_w(priv, macconf, GSWIP_MDIO_PHYp(port)); - /* Activate MDIO auto polling */ - gswip_mdio_mask(priv, 0, BIT(port), GSWIP_MDIO_MDC_CFG0); + u32 mdio_phy = 0; + + if (phydev) + mdio_phy = phydev->mdio.addr & GSWIP_MDIO_PHY_ADDR_MASK; + + gswip_mdio_mask(priv, GSWIP_MDIO_PHY_ADDR_MASK, mdio_phy, + GSWIP_MDIO_PHYp(port)); } return 0; @@ -675,14 +693,6 @@ static void gswip_port_disable(struct dsa_switch *ds, int port) if (!dsa_is_user_port(ds, port)) return; - if (!dsa_is_cpu_port(ds, port)) { - gswip_mdio_mask(priv, GSWIP_MDIO_PHY_LINK_DOWN, - GSWIP_MDIO_PHY_LINK_MASK, - GSWIP_MDIO_PHYp(port)); - /* Deactivate MDIO auto polling */ - gswip_mdio_mask(priv, BIT(port), 0, GSWIP_MDIO_MDC_CFG0); - } - gswip_switch_mask(priv, GSWIP_FDMA_PCTRL_EN, 0, GSWIP_FDMA_PCTRLp(port)); gswip_switch_mask(priv, GSWIP_SDMA_PCTRL_EN, 0, @@ -794,14 +804,32 @@ static int gswip_setup(struct dsa_switch *ds) gswip_switch_w(priv, BIT(cpu_port), GSWIP_PCE_PMAP2); gswip_switch_w(priv, BIT(cpu_port), GSWIP_PCE_PMAP3); - /* disable PHY auto polling */ + /* Deactivate MDIO PHY auto polling. Some PHYs as the AR8030 have an + * interoperability problem with this auto polling mechanism because + * their status registers think that the link is in a different state + * than it actually is. For the AR8030 it has the BMSR_ESTATEN bit set + * as well as ESTATUS_1000_TFULL and ESTATUS_1000_XFULL. This makes the + * auto polling state machine consider the link being negotiated with + * 1Gbit/s. Since the PHY itself is a Fast Ethernet RMII PHY this leads + * to the switch port being completely dead (RX and TX are both not + * working). + * Also with various other PHY / port combinations (PHY11G GPHY, PHY22F + * GPHY, external RGMII PEF7071/7072) any traffic would stop. Sometimes + * it would work fine for a few minutes to hours and then stop, on + * other device it would no traffic could be sent or received at all. + * Testing shows that when PHY auto polling is disabled these problems + * go away. + */ gswip_mdio_w(priv, 0x0, GSWIP_MDIO_MDC_CFG0); + /* Configure the MDIO Clock 2.5 MHz */ gswip_mdio_mask(priv, 0xff, 0x09, GSWIP_MDIO_MDC_CFG1); - /* Disable the xMII link */ + /* Disable the xMII interface and clear it's isolation bit */ for (i = 0; i < priv->hw_info->max_ports; i++) - gswip_mii_mask_cfg(priv, GSWIP_MII_CFG_EN, 0, i); + gswip_mii_mask_cfg(priv, + GSWIP_MII_CFG_EN | GSWIP_MII_CFG_ISOLATE, + 0, i); /* enable special tag insertion on cpu port */ gswip_switch_mask(priv, 0, GSWIP_FDMA_PCTRL_STEN, @@ -1450,6 +1478,112 @@ unsupported: return; } +static void gswip_port_set_link(struct gswip_priv *priv, int port, bool link) +{ + u32 mdio_phy; + + if (link) + mdio_phy = GSWIP_MDIO_PHY_LINK_UP; + else + mdio_phy = GSWIP_MDIO_PHY_LINK_DOWN; + + gswip_mdio_mask(priv, GSWIP_MDIO_PHY_LINK_MASK, mdio_phy, + GSWIP_MDIO_PHYp(port)); +} + +static void gswip_port_set_speed(struct gswip_priv *priv, int port, int speed, + phy_interface_t interface) +{ + u32 mdio_phy = 0, mii_cfg = 0, mac_ctrl_0 = 0; + + switch (speed) { + case SPEED_10: + mdio_phy = GSWIP_MDIO_PHY_SPEED_M10; + + if (interface == PHY_INTERFACE_MODE_RMII) + mii_cfg = GSWIP_MII_CFG_RATE_M50; + else + mii_cfg = GSWIP_MII_CFG_RATE_M2P5; + + mac_ctrl_0 = GSWIP_MAC_CTRL_0_GMII_MII; + break; + + case SPEED_100: + mdio_phy = GSWIP_MDIO_PHY_SPEED_M100; + + if (interface == PHY_INTERFACE_MODE_RMII) + mii_cfg = GSWIP_MII_CFG_RATE_M50; + else + mii_cfg = GSWIP_MII_CFG_RATE_M25; + + mac_ctrl_0 = GSWIP_MAC_CTRL_0_GMII_MII; + break; + + case SPEED_1000: + mdio_phy = GSWIP_MDIO_PHY_SPEED_G1; + + mii_cfg = GSWIP_MII_CFG_RATE_M125; + + mac_ctrl_0 = GSWIP_MAC_CTRL_0_GMII_RGMII; + break; + } + + gswip_mdio_mask(priv, GSWIP_MDIO_PHY_SPEED_MASK, mdio_phy, + GSWIP_MDIO_PHYp(port)); + gswip_mii_mask_cfg(priv, GSWIP_MII_CFG_RATE_MASK, mii_cfg, port); + gswip_switch_mask(priv, GSWIP_MAC_CTRL_0_GMII_MASK, mac_ctrl_0, + GSWIP_MAC_CTRL_0p(port)); +} + +static void gswip_port_set_duplex(struct gswip_priv *priv, int port, int duplex) +{ + u32 mac_ctrl_0, mdio_phy; + + if (duplex == DUPLEX_FULL) { + mac_ctrl_0 = GSWIP_MAC_CTRL_0_FDUP_EN; + mdio_phy = GSWIP_MDIO_PHY_FDUP_EN; + } else { + mac_ctrl_0 = GSWIP_MAC_CTRL_0_FDUP_DIS; + mdio_phy = GSWIP_MDIO_PHY_FDUP_DIS; + } + + gswip_switch_mask(priv, GSWIP_MAC_CTRL_0_FDUP_MASK, mac_ctrl_0, + GSWIP_MAC_CTRL_0p(port)); + gswip_mdio_mask(priv, GSWIP_MDIO_PHY_FDUP_MASK, mdio_phy, + GSWIP_MDIO_PHYp(port)); +} + +static void gswip_port_set_pause(struct gswip_priv *priv, int port, + bool tx_pause, bool rx_pause) +{ + u32 mac_ctrl_0, mdio_phy; + + if (tx_pause && rx_pause) { + mac_ctrl_0 = GSWIP_MAC_CTRL_0_FCON_RXTX; + mdio_phy = GSWIP_MDIO_PHY_FCONTX_EN | + GSWIP_MDIO_PHY_FCONRX_EN; + } else if (tx_pause) { + mac_ctrl_0 = GSWIP_MAC_CTRL_0_FCON_TX; + mdio_phy = GSWIP_MDIO_PHY_FCONTX_EN | + GSWIP_MDIO_PHY_FCONRX_DIS; + } else if (rx_pause) { + mac_ctrl_0 = GSWIP_MAC_CTRL_0_FCON_RX; + mdio_phy = GSWIP_MDIO_PHY_FCONTX_DIS | + GSWIP_MDIO_PHY_FCONRX_EN; + } else { + mac_ctrl_0 = GSWIP_MAC_CTRL_0_FCON_NONE; + mdio_phy = GSWIP_MDIO_PHY_FCONTX_DIS | + GSWIP_MDIO_PHY_FCONRX_DIS; + } + + gswip_switch_mask(priv, GSWIP_MAC_CTRL_0_FCON_MASK, + mac_ctrl_0, GSWIP_MAC_CTRL_0p(port)); + gswip_mdio_mask(priv, + GSWIP_MDIO_PHY_FCONTX_MASK | + GSWIP_MDIO_PHY_FCONRX_MASK, + mdio_phy, GSWIP_MDIO_PHYp(port)); +} + static void gswip_phylink_mac_config(struct dsa_switch *ds, int port, unsigned int mode, const struct phylink_link_state *state) @@ -1469,6 +1603,9 @@ static void gswip_phylink_mac_config(struct dsa_switch *ds, int port, break; case PHY_INTERFACE_MODE_RMII: miicfg |= GSWIP_MII_CFG_MODE_RMIIM; + + /* Configure the RMII clock as output: */ + miicfg |= GSWIP_MII_CFG_RMII_CLK; break; case PHY_INTERFACE_MODE_RGMII: case PHY_INTERFACE_MODE_RGMII_ID: @@ -1481,7 +1618,11 @@ static void gswip_phylink_mac_config(struct dsa_switch *ds, int port, "Unsupported interface: %d\n", state->interface); return; } - gswip_mii_mask_cfg(priv, GSWIP_MII_CFG_MODE_MASK, miicfg, port); + + gswip_mii_mask_cfg(priv, + GSWIP_MII_CFG_MODE_MASK | GSWIP_MII_CFG_RMII_CLK | + GSWIP_MII_CFG_RGMII_IBS | GSWIP_MII_CFG_LDCLKDIS, + miicfg, port); switch (state->interface) { case PHY_INTERFACE_MODE_RGMII_ID: @@ -1506,6 +1647,9 @@ static void gswip_phylink_mac_link_down(struct dsa_switch *ds, int port, struct gswip_priv *priv = ds->priv; gswip_mii_mask_cfg(priv, GSWIP_MII_CFG_EN, 0, port); + + if (!dsa_is_cpu_port(ds, port)) + gswip_port_set_link(priv, port, false); } static void gswip_phylink_mac_link_up(struct dsa_switch *ds, int port, @@ -1517,6 +1661,13 @@ static void gswip_phylink_mac_link_up(struct dsa_switch *ds, int port, { struct gswip_priv *priv = ds->priv; + if (!dsa_is_cpu_port(ds, port)) { + gswip_port_set_link(priv, port, true); + gswip_port_set_speed(priv, port, speed, interface); + gswip_port_set_duplex(priv, port, duplex); + gswip_port_set_pause(priv, port, tx_pause, rx_pause); + } + gswip_mii_mask_cfg(priv, 0, GSWIP_MII_CFG_EN, port); } diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c index f06f5fa2f898..9871d7cff93a 100644 --- a/drivers/net/dsa/mt7530.c +++ b/drivers/net/dsa/mt7530.c @@ -436,34 +436,32 @@ mt7530_pad_clk_setup(struct dsa_switch *ds, phy_interface_t interface) TD_DM_DRVP(8) | TD_DM_DRVN(8)); /* Setup core clock for MT7530 */ - if (!trgint) { - /* Disable MT7530 core clock */ - core_clear(priv, CORE_TRGMII_GSW_CLK_CG, REG_GSWCK_EN); - - /* Disable PLL, since phy_device has not yet been created - * provided for phy_[read,write]_mmd_indirect is called, we - * provide our own core_write_mmd_indirect to complete this - * function. - */ - core_write_mmd_indirect(priv, - CORE_GSWPLL_GRP1, - MDIO_MMD_VEND2, - 0); - - /* Set core clock into 500Mhz */ - core_write(priv, CORE_GSWPLL_GRP2, - RG_GSWPLL_POSDIV_500M(1) | - RG_GSWPLL_FBKDIV_500M(25)); + /* Disable MT7530 core clock */ + core_clear(priv, CORE_TRGMII_GSW_CLK_CG, REG_GSWCK_EN); - /* Enable PLL */ - core_write(priv, CORE_GSWPLL_GRP1, - RG_GSWPLL_EN_PRE | - RG_GSWPLL_POSDIV_200M(2) | - RG_GSWPLL_FBKDIV_200M(32)); - - /* Enable MT7530 core clock */ - core_set(priv, CORE_TRGMII_GSW_CLK_CG, REG_GSWCK_EN); - } + /* Disable PLL, since phy_device has not yet been created + * provided for phy_[read,write]_mmd_indirect is called, we + * provide our own core_write_mmd_indirect to complete this + * function. + */ + core_write_mmd_indirect(priv, + CORE_GSWPLL_GRP1, + MDIO_MMD_VEND2, + 0); + + /* Set core clock into 500Mhz */ + core_write(priv, CORE_GSWPLL_GRP2, + RG_GSWPLL_POSDIV_500M(1) | + RG_GSWPLL_FBKDIV_500M(25)); + + /* Enable PLL */ + core_write(priv, CORE_GSWPLL_GRP1, + RG_GSWPLL_EN_PRE | + RG_GSWPLL_POSDIV_200M(2) | + RG_GSWPLL_FBKDIV_200M(32)); + + /* Enable MT7530 core clock */ + core_set(priv, CORE_TRGMII_GSW_CLK_CG, REG_GSWCK_EN); /* Setup the MT7530 TRGMII Tx Clock */ core_set(priv, CORE_TRGMII_GSW_CLK_CG, REG_GSWCK_EN); diff --git a/drivers/net/ethernet/amd/pcnet32.c b/drivers/net/ethernet/amd/pcnet32.c index 187b0b9a6e1d..f78daba60b35 100644 --- a/drivers/net/ethernet/amd/pcnet32.c +++ b/drivers/net/ethernet/amd/pcnet32.c @@ -1534,8 +1534,7 @@ pcnet32_probe_pci(struct pci_dev *pdev, const struct pci_device_id *ent) } pci_set_master(pdev); - ioaddr = pci_resource_start(pdev, 0); - if (!ioaddr) { + if (!pci_resource_len(pdev, 0)) { if (pcnet32_debug & NETIF_MSG_PROBE) pr_err("card has no PCI IO resources, aborting\n"); err = -ENODEV; @@ -1548,6 +1547,8 @@ pcnet32_probe_pci(struct pci_dev *pdev, const struct pci_device_id *ent) pr_err("architecture does not support 32bit PCI busmaster DMA\n"); goto err_disable_dev; } + + ioaddr = pci_resource_start(pdev, 0); if (!request_region(ioaddr, PCNET32_TOTAL_SIZE, "pcnet32_probe_pci")) { if (pcnet32_debug & NETIF_MSG_PROBE) pr_err("io address range already allocated\n"); diff --git a/drivers/net/ethernet/amd/xgbe/xgbe.h b/drivers/net/ethernet/amd/xgbe/xgbe.h index ba8321ec1ee7..3305979a9f7c 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe.h +++ b/drivers/net/ethernet/amd/xgbe/xgbe.h @@ -180,9 +180,9 @@ #define XGBE_DMA_SYS_AWCR 0x30303030 /* DMA cache settings - PCI device */ -#define XGBE_DMA_PCI_ARCR 0x00000003 -#define XGBE_DMA_PCI_AWCR 0x13131313 -#define XGBE_DMA_PCI_AWARCR 0x00000313 +#define XGBE_DMA_PCI_ARCR 0x000f0f0f +#define XGBE_DMA_PCI_AWCR 0x0f0f0f0f +#define XGBE_DMA_PCI_AWARCR 0x00000f0f /* DMA channel interrupt modes */ #define XGBE_IRQ_MODE_EDGE 0 diff --git a/drivers/net/ethernet/broadcom/Kconfig b/drivers/net/ethernet/broadcom/Kconfig index f8a168b73307..cb88ffb8f12f 100644 --- a/drivers/net/ethernet/broadcom/Kconfig +++ b/drivers/net/ethernet/broadcom/Kconfig @@ -54,7 +54,7 @@ config B44_PCI config BCM4908_ENET tristate "Broadcom BCM4908 internal mac support" depends on ARCH_BCM4908 || COMPILE_TEST - default y + default y if ARCH_BCM4908 help This driver supports Ethernet controller integrated into Broadcom BCM4908 family SoCs. diff --git a/drivers/net/ethernet/broadcom/bcm4908_enet.c b/drivers/net/ethernet/broadcom/bcm4908_enet.c index 98cf82dea3e4..65981931a798 100644 --- a/drivers/net/ethernet/broadcom/bcm4908_enet.c +++ b/drivers/net/ethernet/broadcom/bcm4908_enet.c @@ -172,6 +172,7 @@ static int bcm4908_dma_alloc_buf_descs(struct bcm4908_enet *enet, err_free_buf_descs: dma_free_coherent(dev, size, ring->cpu_addr, ring->dma_addr); + ring->cpu_addr = NULL; return -ENOMEM; } diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index 15362d016a87..6e5cf490c01d 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -3239,6 +3239,9 @@ static void gem_prog_cmp_regs(struct macb *bp, struct ethtool_rx_flow_spec *fs) bool cmp_b = false; bool cmp_c = false; + if (!macb_is_gem(bp)) + return; + tp4sp_v = &(fs->h_u.tcp_ip4_spec); tp4sp_m = &(fs->m_u.tcp_ip4_spec); @@ -3607,6 +3610,7 @@ static void macb_restore_features(struct macb *bp) { struct net_device *netdev = bp->dev; netdev_features_t features = netdev->features; + struct ethtool_rx_fs_item *item; /* TX checksum offload */ macb_set_txcsum_feature(bp, features); @@ -3615,6 +3619,9 @@ static void macb_restore_features(struct macb *bp) macb_set_rxcsum_feature(bp, features); /* RX Flow Filters */ + list_for_each_entry(item, &bp->rx_fs_list.list, list) + gem_prog_cmp_regs(bp, &item->fs); + macb_set_rxflow_feature(bp, features); } diff --git a/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c b/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c index 6c85a10f465c..23a2ebdfd503 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c @@ -1794,11 +1794,25 @@ int cudbg_collect_sge_indirect(struct cudbg_init *pdbg_init, struct cudbg_buffer temp_buff = { 0 }; struct sge_qbase_reg_field *sge_qbase; struct ireg_buf *ch_sge_dbg; + u8 padap_running = 0; int i, rc; + u32 size; - rc = cudbg_get_buff(pdbg_init, dbg_buff, - sizeof(*ch_sge_dbg) * 2 + sizeof(*sge_qbase), - &temp_buff); + /* Accessing SGE_QBASE_MAP[0-3] and SGE_QBASE_INDEX regs can + * lead to SGE missing doorbells under heavy traffic. So, only + * collect them when adapter is idle. + */ + for_each_port(padap, i) { + padap_running = netif_running(padap->port[i]); + if (padap_running) + break; + } + + size = sizeof(*ch_sge_dbg) * 2; + if (!padap_running) + size += sizeof(*sge_qbase); + + rc = cudbg_get_buff(pdbg_init, dbg_buff, size, &temp_buff); if (rc) return rc; @@ -1820,7 +1834,8 @@ int cudbg_collect_sge_indirect(struct cudbg_init *pdbg_init, ch_sge_dbg++; } - if (CHELSIO_CHIP_VERSION(padap->params.chip) > CHELSIO_T5) { + if (CHELSIO_CHIP_VERSION(padap->params.chip) > CHELSIO_T5 && + !padap_running) { sge_qbase = (struct sge_qbase_reg_field *)ch_sge_dbg; /* 1 addr reg SGE_QBASE_INDEX and 4 data reg * SGE_QBASE_MAP[0-3] diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c index 98829e482bfa..80882cfc370f 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c @@ -2090,7 +2090,8 @@ void t4_get_regs(struct adapter *adap, void *buf, size_t buf_size) 0x1190, 0x1194, 0x11a0, 0x11a4, 0x11b0, 0x11b4, - 0x11fc, 0x1274, + 0x11fc, 0x123c, + 0x1254, 0x1274, 0x1280, 0x133c, 0x1800, 0x18fc, 0x3000, 0x302c, diff --git a/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c b/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c index 169e10c91378..1115b8f9ea4e 100644 --- a/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c +++ b/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c @@ -722,7 +722,7 @@ static int chcr_ktls_cpl_set_tcb_rpl(struct adapter *adap, unsigned char *input) kvfree(tx_info); return 0; } - tx_info->open_state = false; + tx_info->open_state = CH_KTLS_OPEN_SUCCESS; spin_unlock(&tx_info->lock); complete(&tx_info->completion); diff --git a/drivers/net/ethernet/faraday/ftgmac100.c b/drivers/net/ethernet/faraday/ftgmac100.c index 88bfe2107938..04421aec2dfd 100644 --- a/drivers/net/ethernet/faraday/ftgmac100.c +++ b/drivers/net/ethernet/faraday/ftgmac100.c @@ -1337,6 +1337,7 @@ static int ftgmac100_poll(struct napi_struct *napi, int budget) */ if (unlikely(priv->need_mac_restart)) { ftgmac100_start_hw(priv); + priv->need_mac_restart = false; /* Re-enable "bad" interrupts */ iowrite32(FTGMAC100_INT_BAD, diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c index 1cf8ef717453..3ec4d9fddd52 100644 --- a/drivers/net/ethernet/freescale/gianfar.c +++ b/drivers/net/ethernet/freescale/gianfar.c @@ -363,7 +363,11 @@ static void gfar_set_mac_for_addr(struct net_device *dev, int num, static int gfar_set_mac_addr(struct net_device *dev, void *p) { - eth_mac_addr(dev, p); + int ret; + + ret = eth_mac_addr(dev, p); + if (ret) + return ret; gfar_set_mac_for_addr(dev, 0, dev->dev_addr); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index e3f81c7e0ce7..b0dbe6dcaa7b 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -3966,7 +3966,6 @@ static void hclge_reset_event(struct pci_dev *pdev, struct hnae3_handle *handle) * normalcy is to reset. * 2. A new reset request from the stack due to timeout * - * For the first case,error event might not have ae handle available. * check if this is a new reset request and we are not here just because * last reset attempt did not succeed and watchdog hit us again. We will * know this if last reset request did not occur very recently (watchdog @@ -3976,14 +3975,14 @@ static void hclge_reset_event(struct pci_dev *pdev, struct hnae3_handle *handle) * want to make sure we throttle the reset request. Therefore, we will * not allow it again before 3*HZ times. */ - if (!handle) - handle = &hdev->vport[0].nic; if (time_before(jiffies, (hdev->last_reset_time + HCLGE_RESET_INTERVAL))) { mod_timer(&hdev->reset_timer, jiffies + HCLGE_RESET_INTERVAL); return; - } else if (hdev->default_reset_request) { + } + + if (hdev->default_reset_request) { hdev->reset_level = hclge_get_reset_level(ae_dev, &hdev->default_reset_request); @@ -11211,7 +11210,7 @@ static int hclge_set_channels(struct hnae3_handle *handle, u32 new_tqps_num, if (ret) return ret; - /* RSS indirection table has been configuared by user */ + /* RSS indirection table has been configured by user */ if (rxfh_configured) goto out; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c index 700e068764c8..e295d359e912 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c @@ -2193,7 +2193,7 @@ static void hclgevf_reset_service_task(struct hclgevf_dev *hdev) if (test_and_clear_bit(HCLGEVF_RESET_PENDING, &hdev->reset_state)) { - /* PF has initmated that it is about to reset the hardware. + /* PF has intimated that it is about to reset the hardware. * We now have to poll & check if hardware has actually * completed the reset sequence. On hardware reset completion, * VF needs to reset the client and ae device. @@ -2624,14 +2624,14 @@ static int hclgevf_ae_start(struct hnae3_handle *handle) { struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle); + clear_bit(HCLGEVF_STATE_DOWN, &hdev->state); + hclgevf_reset_tqp_stats(handle); hclgevf_request_link_info(hdev); hclgevf_update_link_mode(hdev); - clear_bit(HCLGEVF_STATE_DOWN, &hdev->state); - return 0; } @@ -3497,7 +3497,7 @@ static int hclgevf_set_channels(struct hnae3_handle *handle, u32 new_tqps_num, if (ret) return ret; - /* RSS indirection table has been configuared by user */ + /* RSS indirection table has been configured by user */ if (rxfh_configured) goto out; diff --git a/drivers/net/ethernet/intel/e1000e/82571.c b/drivers/net/ethernet/intel/e1000e/82571.c index 88faf05e23ba..0b1e890dd583 100644 --- a/drivers/net/ethernet/intel/e1000e/82571.c +++ b/drivers/net/ethernet/intel/e1000e/82571.c @@ -899,6 +899,8 @@ static s32 e1000_set_d0_lplu_state_82571(struct e1000_hw *hw, bool active) } else { data &= ~IGP02E1000_PM_D0_LPLU; ret_val = e1e_wphy(hw, IGP02E1000_PHY_POWER_MGMT, data); + if (ret_val) + return ret_val; /* LPLU and SmartSpeed are mutually exclusive. LPLU is used * during Dx states where the power conservation is most * important. During driver activity we should enable diff --git a/drivers/net/ethernet/intel/e1000e/hw.h b/drivers/net/ethernet/intel/e1000e/hw.h index 69a2329ea463..db79c4e6413e 100644 --- a/drivers/net/ethernet/intel/e1000e/hw.h +++ b/drivers/net/ethernet/intel/e1000e/hw.h @@ -1,8 +1,8 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* Copyright(c) 1999 - 2018 Intel Corporation. */ -#ifndef _E1000_HW_H_ -#define _E1000_HW_H_ +#ifndef _E1000E_HW_H_ +#define _E1000E_HW_H_ #include "regs.h" #include "defines.h" @@ -714,4 +714,4 @@ struct e1000_hw { #include "80003es2lan.h" #include "ich8lan.h" -#endif +#endif /* _E1000E_HW_H_ */ diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index e9b82c209c2d..a0948002ddf8 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -5974,15 +5974,19 @@ static void e1000_reset_task(struct work_struct *work) struct e1000_adapter *adapter; adapter = container_of(work, struct e1000_adapter, reset_task); + rtnl_lock(); /* don't run the task if already down */ - if (test_bit(__E1000_DOWN, &adapter->state)) + if (test_bit(__E1000_DOWN, &adapter->state)) { + rtnl_unlock(); return; + } if (!(adapter->flags & FLAG_RESTART_NOW)) { e1000e_dump(adapter); e_err("Reset adapter unexpectedly\n"); } e1000e_reinit_locked(adapter); + rtnl_unlock(); } /** diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h index cd53981fa5e0..15f93b355099 100644 --- a/drivers/net/ethernet/intel/i40e/i40e.h +++ b/drivers/net/ethernet/intel/i40e/i40e.h @@ -142,6 +142,7 @@ enum i40e_state_t { __I40E_VIRTCHNL_OP_PENDING, __I40E_RECOVERY_MODE, __I40E_VF_RESETS_DISABLED, /* disable resets during i40e_remove */ + __I40E_VFS_RELEASING, /* This must be last as it determines the size of the BITMAP */ __I40E_STATE_SIZE__, }; diff --git a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c index d7c13ca9be7d..d627b59ad446 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c +++ b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c @@ -578,6 +578,9 @@ static void i40e_dbg_dump_desc(int cnt, int vsi_seid, int ring_id, int desc_n, case RING_TYPE_XDP: ring = kmemdup(vsi->xdp_rings[ring_id], sizeof(*ring), GFP_KERNEL); break; + default: + ring = NULL; + break; } if (!ring) return; diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c index c70dec65a572..0e92668012e3 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c @@ -232,6 +232,8 @@ static void __i40e_add_stat_strings(u8 **p, const struct i40e_stats stats[], I40E_STAT(struct i40e_vsi, _name, _stat) #define I40E_VEB_STAT(_name, _stat) \ I40E_STAT(struct i40e_veb, _name, _stat) +#define I40E_VEB_TC_STAT(_name, _stat) \ + I40E_STAT(struct i40e_cp_veb_tc_stats, _name, _stat) #define I40E_PFC_STAT(_name, _stat) \ I40E_STAT(struct i40e_pfc_stats, _name, _stat) #define I40E_QUEUE_STAT(_name, _stat) \ @@ -266,11 +268,18 @@ static const struct i40e_stats i40e_gstrings_veb_stats[] = { I40E_VEB_STAT("veb.rx_unknown_protocol", stats.rx_unknown_protocol), }; +struct i40e_cp_veb_tc_stats { + u64 tc_rx_packets; + u64 tc_rx_bytes; + u64 tc_tx_packets; + u64 tc_tx_bytes; +}; + static const struct i40e_stats i40e_gstrings_veb_tc_stats[] = { - I40E_VEB_STAT("veb.tc_%u_tx_packets", tc_stats.tc_tx_packets), - I40E_VEB_STAT("veb.tc_%u_tx_bytes", tc_stats.tc_tx_bytes), - I40E_VEB_STAT("veb.tc_%u_rx_packets", tc_stats.tc_rx_packets), - I40E_VEB_STAT("veb.tc_%u_rx_bytes", tc_stats.tc_rx_bytes), + I40E_VEB_TC_STAT("veb.tc_%u_tx_packets", tc_tx_packets), + I40E_VEB_TC_STAT("veb.tc_%u_tx_bytes", tc_tx_bytes), + I40E_VEB_TC_STAT("veb.tc_%u_rx_packets", tc_rx_packets), + I40E_VEB_TC_STAT("veb.tc_%u_rx_bytes", tc_rx_bytes), }; static const struct i40e_stats i40e_gstrings_misc_stats[] = { @@ -1101,6 +1110,7 @@ static int i40e_get_link_ksettings(struct net_device *netdev, /* Set flow control settings */ ethtool_link_ksettings_add_link_mode(ks, supported, Pause); + ethtool_link_ksettings_add_link_mode(ks, supported, Asym_Pause); switch (hw->fc.requested_mode) { case I40E_FC_FULL: @@ -2217,6 +2227,29 @@ static int i40e_get_sset_count(struct net_device *netdev, int sset) } /** + * i40e_get_veb_tc_stats - copy VEB TC statistics to formatted structure + * @tc: the TC statistics in VEB structure (veb->tc_stats) + * @i: the index of traffic class in (veb->tc_stats) structure to copy + * + * Copy VEB TC statistics from structure of arrays (veb->tc_stats) to + * one dimensional structure i40e_cp_veb_tc_stats. + * Produce formatted i40e_cp_veb_tc_stats structure of the VEB TC + * statistics for the given TC. + **/ +static struct i40e_cp_veb_tc_stats +i40e_get_veb_tc_stats(struct i40e_veb_tc_stats *tc, unsigned int i) +{ + struct i40e_cp_veb_tc_stats veb_tc = { + .tc_rx_packets = tc->tc_rx_packets[i], + .tc_rx_bytes = tc->tc_rx_bytes[i], + .tc_tx_packets = tc->tc_tx_packets[i], + .tc_tx_bytes = tc->tc_tx_bytes[i], + }; + + return veb_tc; +} + +/** * i40e_get_pfc_stats - copy HW PFC statistics to formatted structure * @pf: the PF device structure * @i: the priority value to copy @@ -2300,8 +2333,16 @@ static void i40e_get_ethtool_stats(struct net_device *netdev, i40e_gstrings_veb_stats); for (i = 0; i < I40E_MAX_TRAFFIC_CLASS; i++) - i40e_add_ethtool_stats(&data, veb_stats ? veb : NULL, - i40e_gstrings_veb_tc_stats); + if (veb_stats) { + struct i40e_cp_veb_tc_stats veb_tc = + i40e_get_veb_tc_stats(&veb->tc_stats, i); + + i40e_add_ethtool_stats(&data, &veb_tc, + i40e_gstrings_veb_tc_stats); + } else { + i40e_add_ethtool_stats(&data, NULL, + i40e_gstrings_veb_tc_stats); + } i40e_add_ethtool_stats(&data, pf, i40e_gstrings_stats); @@ -5439,7 +5480,7 @@ static int i40e_get_module_eeprom(struct net_device *netdev, status = i40e_aq_get_phy_register(hw, I40E_AQ_PHY_REG_ACCESS_EXTERNAL_MODULE, - true, addr, offset, &value, NULL); + addr, true, offset, &value, NULL); if (status) return -EIO; data[i] = value; diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 353deae139f9..30ad7c08d0fb 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -2560,8 +2560,7 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi) i40e_stat_str(hw, aq_ret), i40e_aq_str(hw, hw->aq.asq_last_status)); } else { - dev_info(&pf->pdev->dev, "%s is %s allmulti mode.\n", - vsi->netdev->name, + dev_info(&pf->pdev->dev, "%s allmulti mode.\n", cur_multipromisc ? "entering" : "leaving"); } } @@ -3259,6 +3258,17 @@ static int i40e_configure_tx_ring(struct i40e_ring *ring) } /** + * i40e_rx_offset - Return expected offset into page to access data + * @rx_ring: Ring we are requesting offset of + * + * Returns the offset value for ring into the data buffer. + */ +static unsigned int i40e_rx_offset(struct i40e_ring *rx_ring) +{ + return ring_uses_build_skb(rx_ring) ? I40E_SKB_PAD : 0; +} + +/** * i40e_configure_rx_ring - Configure a receive ring context * @ring: The Rx ring to configure * @@ -3369,6 +3379,8 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring) else set_ring_build_skb_enabled(ring); + ring->rx_offset = i40e_rx_offset(ring); + /* cache tail for quicker writes, and clear the reg before use */ ring->tail = hw->hw_addr + I40E_QRX_TAIL(pf_q); writel(0, ring->tail); @@ -6725,9 +6737,9 @@ out: set_bit(__I40E_CLIENT_SERVICE_REQUESTED, pf->state); set_bit(__I40E_CLIENT_L2_CHANGE, pf->state); } - /* registers are set, lets apply */ - if (pf->hw_features & I40E_HW_USE_SET_LLDP_MIB) - ret = i40e_hw_set_dcb_config(pf, new_cfg); + /* registers are set, lets apply */ + if (pf->hw_features & I40E_HW_USE_SET_LLDP_MIB) + ret = i40e_hw_set_dcb_config(pf, new_cfg); } err: @@ -10560,12 +10572,6 @@ static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired) goto end_core_reset; } - if (!lock_acquired) - rtnl_lock(); - ret = i40e_setup_pf_switch(pf, reinit); - if (ret) - goto end_unlock; - #ifdef CONFIG_I40E_DCB /* Enable FW to write a default DCB config on link-up * unless I40E_FLAG_TC_MQPRIO was enabled or DCB @@ -10580,7 +10586,7 @@ static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired) i40e_aq_set_dcb_parameters(hw, false, NULL); dev_warn(&pf->pdev->dev, "DCB is not supported for X710-T*L 2.5/5G speeds\n"); - pf->flags &= ~I40E_FLAG_DCB_CAPABLE; + pf->flags &= ~I40E_FLAG_DCB_CAPABLE; } else { i40e_aq_set_dcb_parameters(hw, true, NULL); ret = i40e_init_pf_dcb(pf); @@ -10594,6 +10600,11 @@ static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired) } #endif /* CONFIG_I40E_DCB */ + if (!lock_acquired) + rtnl_lock(); + ret = i40e_setup_pf_switch(pf, reinit); + if (ret) + goto end_unlock; /* The driver only wants link up/down and module qualification * reports from firmware. Note the negative logic. @@ -15127,12 +15138,16 @@ static int i40e_init_recovery_mode(struct i40e_pf *pf, struct i40e_hw *hw) * in order to register the netdev */ v_idx = i40e_vsi_mem_alloc(pf, I40E_VSI_MAIN); - if (v_idx < 0) + if (v_idx < 0) { + err = v_idx; goto err_switch_setup; + } pf->lan_vsi = v_idx; vsi = pf->vsi[v_idx]; - if (!vsi) + if (!vsi) { + err = -EFAULT; goto err_switch_setup; + } vsi->alloc_queue_pairs = 1; err = i40e_config_netdev(vsi); if (err) diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index 627794b31e33..06b4271219b1 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -1570,17 +1570,6 @@ void i40e_free_rx_resources(struct i40e_ring *rx_ring) } /** - * i40e_rx_offset - Return expected offset into page to access data - * @rx_ring: Ring we are requesting offset of - * - * Returns the offset value for ring into the data buffer. - */ -static unsigned int i40e_rx_offset(struct i40e_ring *rx_ring) -{ - return ring_uses_build_skb(rx_ring) ? I40E_SKB_PAD : 0; -} - -/** * i40e_setup_rx_descriptors - Allocate Rx descriptors * @rx_ring: Rx descriptor ring (for a specific queue) to setup * @@ -1608,7 +1597,6 @@ int i40e_setup_rx_descriptors(struct i40e_ring *rx_ring) rx_ring->next_to_alloc = 0; rx_ring->next_to_clean = 0; rx_ring->next_to_use = 0; - rx_ring->rx_offset = i40e_rx_offset(rx_ring); /* XDP RX-queue info only needed for RX rings exposed to XDP */ if (rx_ring->vsi->type == I40E_VSI_MAIN) { @@ -2307,8 +2295,7 @@ int i40e_xmit_xdp_tx_ring(struct xdp_buff *xdp, struct i40e_ring *xdp_ring) * @rx_ring: Rx ring being processed * @xdp: XDP buffer containing the frame **/ -static struct sk_buff *i40e_run_xdp(struct i40e_ring *rx_ring, - struct xdp_buff *xdp) +static int i40e_run_xdp(struct i40e_ring *rx_ring, struct xdp_buff *xdp) { int err, result = I40E_XDP_PASS; struct i40e_ring *xdp_ring; @@ -2347,7 +2334,7 @@ static struct sk_buff *i40e_run_xdp(struct i40e_ring *rx_ring, } xdp_out: rcu_read_unlock(); - return ERR_PTR(-result); + return result; } /** @@ -2460,6 +2447,7 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget) unsigned int xdp_xmit = 0; bool failure = false; struct xdp_buff xdp; + int xdp_res = 0; #if (PAGE_SIZE < 8192) frame_sz = i40e_rx_frame_truesize(rx_ring, 0); @@ -2525,12 +2513,10 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget) /* At larger PAGE_SIZE, frame_sz depend on len size */ xdp.frame_sz = i40e_rx_frame_truesize(rx_ring, size); #endif - skb = i40e_run_xdp(rx_ring, &xdp); + xdp_res = i40e_run_xdp(rx_ring, &xdp); } - if (IS_ERR(skb)) { - unsigned int xdp_res = -PTR_ERR(skb); - + if (xdp_res) { if (xdp_res & (I40E_XDP_TX | I40E_XDP_REDIR)) { xdp_xmit |= xdp_res; i40e_rx_buffer_flip(rx_ring, rx_buffer, size); diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index 1b6ec9be155a..5d301a466f5c 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -137,6 +137,7 @@ void i40e_vc_notify_vf_reset(struct i40e_vf *vf) **/ static inline void i40e_vc_disable_vf(struct i40e_vf *vf) { + struct i40e_pf *pf = vf->pf; int i; i40e_vc_notify_vf_reset(vf); @@ -147,6 +148,11 @@ static inline void i40e_vc_disable_vf(struct i40e_vf *vf) * ensure a reset. */ for (i = 0; i < 20; i++) { + /* If PF is in VFs releasing state reset VF is impossible, + * so leave it. + */ + if (test_bit(__I40E_VFS_RELEASING, pf->state)) + return; if (i40e_reset_vf(vf, false)) return; usleep_range(10000, 20000); @@ -1574,6 +1580,8 @@ void i40e_free_vfs(struct i40e_pf *pf) if (!pf->vf) return; + + set_bit(__I40E_VFS_RELEASING, pf->state); while (test_and_set_bit(__I40E_VF_DISABLE, pf->state)) usleep_range(1000, 2000); @@ -1631,6 +1639,7 @@ void i40e_free_vfs(struct i40e_pf *pf) } } clear_bit(__I40E_VF_DISABLE, pf->state); + clear_bit(__I40E_VFS_RELEASING, pf->state); } #ifdef CONFIG_PCI_IOV diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c index fc32c5019b0f..12ca84113587 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c +++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c @@ -471,7 +471,7 @@ static bool i40e_xmit_zc(struct i40e_ring *xdp_ring, unsigned int budget) nb_pkts = xsk_tx_peek_release_desc_batch(xdp_ring->xsk_pool, descs, budget); if (!nb_pkts) - return false; + return true; if (xdp_ring->next_to_use + nb_pkts >= xdp_ring->count) { nb_processed = xdp_ring->count - xdp_ring->next_to_use; @@ -488,7 +488,7 @@ static bool i40e_xmit_zc(struct i40e_ring *xdp_ring, unsigned int budget) i40e_update_tx_stats(xdp_ring, nb_pkts, total_bytes); - return true; + return nb_pkts < budget; } /** diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h index 357706444dd5..17101c45cbcd 100644 --- a/drivers/net/ethernet/intel/ice/ice.h +++ b/drivers/net/ethernet/intel/ice/ice.h @@ -196,7 +196,6 @@ enum ice_state { __ICE_NEEDS_RESTART, __ICE_PREPARED_FOR_RESET, /* set by driver when prepared */ __ICE_RESET_OICR_RECV, /* set by driver after rcv reset OICR */ - __ICE_DCBNL_DEVRESET, /* set by dcbnl devreset */ __ICE_PFR_REQ, /* set by driver and peers */ __ICE_CORER_REQ, /* set by driver and peers */ __ICE_GLOBR_REQ, /* set by driver and peers */ @@ -624,7 +623,7 @@ int ice_schedule_reset(struct ice_pf *pf, enum ice_reset_req reset); void ice_print_link_msg(struct ice_vsi *vsi, bool isup); const char *ice_stat_str(enum ice_status stat_err); const char *ice_aq_str(enum ice_aq_err aq_err); -bool ice_is_wol_supported(struct ice_pf *pf); +bool ice_is_wol_supported(struct ice_hw *hw); int ice_fdir_write_fltr(struct ice_pf *pf, struct ice_fdir_fltr *input, bool add, bool is_tun); @@ -642,6 +641,7 @@ int ice_fdir_create_dflt_rules(struct ice_pf *pf); int ice_aq_wait_for_event(struct ice_pf *pf, u16 opcode, unsigned long timeout, struct ice_rq_event_info *event); int ice_open(struct net_device *netdev); +int ice_open_internal(struct net_device *netdev); int ice_stop(struct net_device *netdev); void ice_service_task_schedule(struct ice_pf *pf); diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c index 3124a3bf519a..1148d768f8ed 100644 --- a/drivers/net/ethernet/intel/ice/ice_base.c +++ b/drivers/net/ethernet/intel/ice/ice_base.c @@ -275,6 +275,22 @@ ice_setup_tx_ctx(struct ice_ring *ring, struct ice_tlan_ctx *tlan_ctx, u16 pf_q) } /** + * ice_rx_offset - Return expected offset into page to access data + * @rx_ring: Ring we are requesting offset of + * + * Returns the offset value for ring into the data buffer. + */ +static unsigned int ice_rx_offset(struct ice_ring *rx_ring) +{ + if (ice_ring_uses_build_skb(rx_ring)) + return ICE_SKB_PAD; + else if (ice_is_xdp_ena_vsi(rx_ring->vsi)) + return XDP_PACKET_HEADROOM; + + return 0; +} + +/** * ice_setup_rx_ctx - Configure a receive ring context * @ring: The Rx ring to configure * @@ -413,11 +429,15 @@ int ice_setup_rx_ctx(struct ice_ring *ring) else ice_set_ring_build_skb_ena(ring); + ring->rx_offset = ice_rx_offset(ring); + /* init queue specific tail register */ ring->tail = hw->hw_addr + QRX_TAIL(pf_q); writel(0, ring->tail); if (ring->xsk_pool) { + bool ok; + if (!xsk_buff_can_alloc(ring->xsk_pool, num_bufs)) { dev_warn(dev, "XSK buffer pool does not provide enough addresses to fill %d buffers on Rx ring %d\n", num_bufs, ring->q_index); @@ -426,8 +446,8 @@ int ice_setup_rx_ctx(struct ice_ring *ring) return 0; } - err = ice_alloc_rx_bufs_zc(ring, num_bufs); - if (err) + ok = ice_alloc_rx_bufs_zc(ring, num_bufs); + if (!ok) dev_info(dev, "Failed to allocate some buffers on XSK buffer pool enabled Rx ring %d (pf_q %d)\n", ring->q_index, pf_q); return 0; diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c index 3d9475e222cd..a20edf1538a0 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.c +++ b/drivers/net/ethernet/intel/ice/ice_common.c @@ -717,8 +717,8 @@ static enum ice_status ice_cfg_fw_log(struct ice_hw *hw, bool enable) if (!data) { data = devm_kcalloc(ice_hw_to_dev(hw), - sizeof(*data), ICE_AQC_FW_LOG_ID_MAX, + sizeof(*data), GFP_KERNEL); if (!data) return ICE_ERR_NO_MEMORY; diff --git a/drivers/net/ethernet/intel/ice/ice_controlq.h b/drivers/net/ethernet/intel/ice/ice_controlq.h index faaa08e8171b..68866f4f0eb0 100644 --- a/drivers/net/ethernet/intel/ice/ice_controlq.h +++ b/drivers/net/ethernet/intel/ice/ice_controlq.h @@ -31,8 +31,8 @@ enum ice_ctl_q { ICE_CTL_Q_MAILBOX, }; -/* Control Queue timeout settings - max delay 250ms */ -#define ICE_CTL_Q_SQ_CMD_TIMEOUT 2500 /* Count 2500 times */ +/* Control Queue timeout settings - max delay 1s */ +#define ICE_CTL_Q_SQ_CMD_TIMEOUT 10000 /* Count 10000 times */ #define ICE_CTL_Q_SQ_CMD_USEC 100 /* Check every 100usec */ #define ICE_CTL_Q_ADMIN_INIT_TIMEOUT 10 /* Count 10 times */ #define ICE_CTL_Q_ADMIN_INIT_MSEC 100 /* Check every 100msec */ diff --git a/drivers/net/ethernet/intel/ice/ice_dcb.c b/drivers/net/ethernet/intel/ice/ice_dcb.c index e42727941ef5..211ac6f907ad 100644 --- a/drivers/net/ethernet/intel/ice/ice_dcb.c +++ b/drivers/net/ethernet/intel/ice/ice_dcb.c @@ -738,22 +738,27 @@ ice_aq_get_cee_dcb_cfg(struct ice_hw *hw, /** * ice_cee_to_dcb_cfg * @cee_cfg: pointer to CEE configuration struct - * @dcbcfg: DCB configuration struct + * @pi: port information structure * * Convert CEE configuration from firmware to DCB configuration */ static void ice_cee_to_dcb_cfg(struct ice_aqc_get_cee_dcb_cfg_resp *cee_cfg, - struct ice_dcbx_cfg *dcbcfg) + struct ice_port_info *pi) { u32 status, tlv_status = le32_to_cpu(cee_cfg->tlv_status); u32 ice_aqc_cee_status_mask, ice_aqc_cee_status_shift; + u8 i, j, err, sync, oper, app_index, ice_app_sel_type; u16 app_prio = le16_to_cpu(cee_cfg->oper_app_prio); - u8 i, err, sync, oper, app_index, ice_app_sel_type; u16 ice_aqc_cee_app_mask, ice_aqc_cee_app_shift; + struct ice_dcbx_cfg *cmp_dcbcfg, *dcbcfg; u16 ice_app_prot_id_type; - /* CEE PG data to ETS config */ + dcbcfg = &pi->qos_cfg.local_dcbx_cfg; + dcbcfg->dcbx_mode = ICE_DCBX_MODE_CEE; + dcbcfg->tlv_status = tlv_status; + + /* CEE PG data */ dcbcfg->etscfg.maxtcs = cee_cfg->oper_num_tc; /* Note that the FW creates the oper_prio_tc nibbles reversed @@ -780,10 +785,16 @@ ice_cee_to_dcb_cfg(struct ice_aqc_get_cee_dcb_cfg_resp *cee_cfg, } } - /* CEE PFC data to ETS config */ + /* CEE PFC data */ dcbcfg->pfc.pfcena = cee_cfg->oper_pfc_en; dcbcfg->pfc.pfccap = ICE_MAX_TRAFFIC_CLASS; + /* CEE APP TLV data */ + if (dcbcfg->app_mode == ICE_DCBX_APPS_NON_WILLING) + cmp_dcbcfg = &pi->qos_cfg.desired_dcbx_cfg; + else + cmp_dcbcfg = &pi->qos_cfg.remote_dcbx_cfg; + app_index = 0; for (i = 0; i < 3; i++) { if (i == 0) { @@ -802,6 +813,18 @@ ice_cee_to_dcb_cfg(struct ice_aqc_get_cee_dcb_cfg_resp *cee_cfg, ice_aqc_cee_app_shift = ICE_AQC_CEE_APP_ISCSI_S; ice_app_sel_type = ICE_APP_SEL_TCPIP; ice_app_prot_id_type = ICE_APP_PROT_ID_ISCSI; + + for (j = 0; j < cmp_dcbcfg->numapps; j++) { + u16 prot_id = cmp_dcbcfg->app[j].prot_id; + u8 sel = cmp_dcbcfg->app[j].selector; + + if (sel == ICE_APP_SEL_TCPIP && + (prot_id == ICE_APP_PROT_ID_ISCSI || + prot_id == ICE_APP_PROT_ID_ISCSI_860)) { + ice_app_prot_id_type = prot_id; + break; + } + } } else { /* FIP APP */ ice_aqc_cee_status_mask = ICE_AQC_CEE_FIP_STATUS_M; @@ -892,11 +915,8 @@ enum ice_status ice_get_dcb_cfg(struct ice_port_info *pi) ret = ice_aq_get_cee_dcb_cfg(pi->hw, &cee_cfg, NULL); if (!ret) { /* CEE mode */ - dcbx_cfg = &pi->qos_cfg.local_dcbx_cfg; - dcbx_cfg->dcbx_mode = ICE_DCBX_MODE_CEE; - dcbx_cfg->tlv_status = le32_to_cpu(cee_cfg.tlv_status); - ice_cee_to_dcb_cfg(&cee_cfg, dcbx_cfg); ret = ice_get_ieee_or_cee_dcb_cfg(pi, ICE_DCBX_MODE_CEE); + ice_cee_to_dcb_cfg(&cee_cfg, pi); } else if (pi->hw->adminq.sq_last_status == ICE_AQ_RC_ENOENT) { /* CEE mode not enabled try querying IEEE data */ dcbx_cfg = &pi->qos_cfg.local_dcbx_cfg; diff --git a/drivers/net/ethernet/intel/ice/ice_dcb_nl.c b/drivers/net/ethernet/intel/ice/ice_dcb_nl.c index 468a63f7eff9..4180f1f35fb8 100644 --- a/drivers/net/ethernet/intel/ice/ice_dcb_nl.c +++ b/drivers/net/ethernet/intel/ice/ice_dcb_nl.c @@ -18,12 +18,10 @@ static void ice_dcbnl_devreset(struct net_device *netdev) while (ice_is_reset_in_progress(pf->state)) usleep_range(1000, 2000); - set_bit(__ICE_DCBNL_DEVRESET, pf->state); dev_close(netdev); netdev_state_change(netdev); dev_open(netdev, NULL); netdev_state_change(netdev); - clear_bit(__ICE_DCBNL_DEVRESET, pf->state); } /** diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c index 2dcfa685b763..32ba71a16165 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c @@ -3472,7 +3472,7 @@ static void ice_get_wol(struct net_device *netdev, struct ethtool_wolinfo *wol) netdev_warn(netdev, "Wake on LAN is not supported on this interface!\n"); /* Get WoL settings based on the HW capability */ - if (ice_is_wol_supported(pf)) { + if (ice_is_wol_supported(&pf->hw)) { wol->supported = WAKE_MAGIC; wol->wolopts = pf->wol_ena ? WAKE_MAGIC : 0; } else { @@ -3492,7 +3492,7 @@ static int ice_set_wol(struct net_device *netdev, struct ethtool_wolinfo *wol) struct ice_vsi *vsi = np->vsi; struct ice_pf *pf = vsi->back; - if (vsi->type != ICE_VSI_PF || !ice_is_wol_supported(pf)) + if (vsi->type != ICE_VSI_PF || !ice_is_wol_supported(&pf->hw)) return -EOPNOTSUPP; /* only magic packet is supported */ diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index 8d4e2ad4328d..d13c7fc8fb0a 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -2620,7 +2620,7 @@ int ice_ena_vsi(struct ice_vsi *vsi, bool locked) if (!locked) rtnl_lock(); - err = ice_open(vsi->netdev); + err = ice_open_internal(vsi->netdev); if (!locked) rtnl_unlock(); @@ -2649,7 +2649,7 @@ void ice_dis_vsi(struct ice_vsi *vsi, bool locked) if (!locked) rtnl_lock(); - ice_stop(vsi->netdev); + ice_vsi_close(vsi); if (!locked) rtnl_unlock(); @@ -3078,7 +3078,6 @@ err_vsi: bool ice_is_reset_in_progress(unsigned long *state) { return test_bit(__ICE_RESET_OICR_RECV, state) || - test_bit(__ICE_DCBNL_DEVRESET, state) || test_bit(__ICE_PFR_REQ, state) || test_bit(__ICE_CORER_REQ, state) || test_bit(__ICE_GLOBR_REQ, state); diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 2c23c8f468a5..d821c687f239 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -3537,15 +3537,14 @@ static int ice_init_interrupt_scheme(struct ice_pf *pf) } /** - * ice_is_wol_supported - get NVM state of WoL - * @pf: board private structure + * ice_is_wol_supported - check if WoL is supported + * @hw: pointer to hardware info * * Check if WoL is supported based on the HW configuration. * Returns true if NVM supports and enables WoL for this port, false otherwise */ -bool ice_is_wol_supported(struct ice_pf *pf) +bool ice_is_wol_supported(struct ice_hw *hw) { - struct ice_hw *hw = &pf->hw; u16 wol_ctrl; /* A bit set to 1 in the NVM Software Reserved Word 2 (WoL control @@ -3554,7 +3553,7 @@ bool ice_is_wol_supported(struct ice_pf *pf) if (ice_read_sr_word(hw, ICE_SR_NVM_WOL_CFG, &wol_ctrl)) return false; - return !(BIT(hw->pf_id) & wol_ctrl); + return !(BIT(hw->port_info->lport) & wol_ctrl); } /** @@ -4192,28 +4191,25 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent) goto err_send_version_unroll; } + /* not a fatal error if this fails */ err = ice_init_nvm_phy_type(pf->hw.port_info); - if (err) { + if (err) dev_err(dev, "ice_init_nvm_phy_type failed: %d\n", err); - goto err_send_version_unroll; - } + /* not a fatal error if this fails */ err = ice_update_link_info(pf->hw.port_info); - if (err) { + if (err) dev_err(dev, "ice_update_link_info failed: %d\n", err); - goto err_send_version_unroll; - } ice_init_link_dflt_override(pf->hw.port_info); /* if media available, initialize PHY settings */ if (pf->hw.port_info->phy.link_info.link_info & ICE_AQ_MEDIA_AVAILABLE) { + /* not a fatal error if this fails */ err = ice_init_phy_user_cfg(pf->hw.port_info); - if (err) { + if (err) dev_err(dev, "ice_init_phy_user_cfg failed: %d\n", err); - goto err_send_version_unroll; - } if (!test_bit(ICE_FLAG_LINK_DOWN_ON_CLOSE_ENA, pf->flags)) { struct ice_vsi *vsi = ice_get_main_vsi(pf); @@ -4568,6 +4564,7 @@ static int __maybe_unused ice_suspend(struct device *dev) continue; ice_vsi_free_q_vectors(pf->vsi[v]); } + ice_free_cpu_rx_rmap(ice_get_main_vsi(pf)); ice_clear_interrupt_scheme(pf); pci_save_state(pdev); @@ -6637,6 +6634,28 @@ static void ice_tx_timeout(struct net_device *netdev, unsigned int txqueue) int ice_open(struct net_device *netdev) { struct ice_netdev_priv *np = netdev_priv(netdev); + struct ice_pf *pf = np->vsi->back; + + if (ice_is_reset_in_progress(pf->state)) { + netdev_err(netdev, "can't open net device while reset is in progress"); + return -EBUSY; + } + + return ice_open_internal(netdev); +} + +/** + * ice_open_internal - Called when a network interface becomes active + * @netdev: network interface device structure + * + * Internal ice_open implementation. Should not be used directly except for ice_open and reset + * handling routine + * + * Returns 0 on success, negative value on failure + */ +int ice_open_internal(struct net_device *netdev) +{ + struct ice_netdev_priv *np = netdev_priv(netdev); struct ice_vsi *vsi = np->vsi; struct ice_pf *pf = vsi->back; struct ice_port_info *pi; @@ -6715,6 +6734,12 @@ int ice_stop(struct net_device *netdev) { struct ice_netdev_priv *np = netdev_priv(netdev); struct ice_vsi *vsi = np->vsi; + struct ice_pf *pf = vsi->back; + + if (ice_is_reset_in_progress(pf->state)) { + netdev_err(netdev, "can't stop net device while reset is in progress"); + return -EBUSY; + } ice_vsi_close(vsi); diff --git a/drivers/net/ethernet/intel/ice/ice_switch.c b/drivers/net/ethernet/intel/ice/ice_switch.c index 67c965a3f5d2..834cbd3f7b31 100644 --- a/drivers/net/ethernet/intel/ice/ice_switch.c +++ b/drivers/net/ethernet/intel/ice/ice_switch.c @@ -1238,6 +1238,9 @@ ice_add_update_vsi_list(struct ice_hw *hw, ice_create_vsi_list_map(hw, &vsi_handle_arr[0], 2, vsi_list_id); + if (!m_entry->vsi_list_info) + return ICE_ERR_NO_MEMORY; + /* If this entry was large action then the large action needs * to be updated to point to FWD to VSI list */ @@ -2220,6 +2223,7 @@ ice_vsi_uses_fltr(struct ice_fltr_mgmt_list_entry *fm_entry, u16 vsi_handle) return ((fm_entry->fltr_info.fltr_act == ICE_FWD_TO_VSI && fm_entry->fltr_info.vsi_handle == vsi_handle) || (fm_entry->fltr_info.fltr_act == ICE_FWD_TO_VSI_LIST && + fm_entry->vsi_list_info && (test_bit(vsi_handle, fm_entry->vsi_list_info->vsi_map)))); } @@ -2292,14 +2296,12 @@ ice_add_to_vsi_fltr_list(struct ice_hw *hw, u16 vsi_handle, return ICE_ERR_PARAM; list_for_each_entry(fm_entry, lkup_list_head, list_entry) { - struct ice_fltr_info *fi; - - fi = &fm_entry->fltr_info; - if (!fi || !ice_vsi_uses_fltr(fm_entry, vsi_handle)) + if (!ice_vsi_uses_fltr(fm_entry, vsi_handle)) continue; status = ice_add_entry_to_vsi_fltr_list(hw, vsi_handle, - vsi_list_head, fi); + vsi_list_head, + &fm_entry->fltr_info); if (status) return status; } @@ -2622,7 +2624,7 @@ ice_remove_vsi_lkup_fltr(struct ice_hw *hw, u16 vsi_handle, &remove_list_head); mutex_unlock(rule_lock); if (status) - return; + goto free_fltr_list; switch (lkup) { case ICE_SW_LKUP_MAC: @@ -2645,6 +2647,7 @@ ice_remove_vsi_lkup_fltr(struct ice_hw *hw, u16 vsi_handle, break; } +free_fltr_list: list_for_each_entry_safe(fm_entry, tmp, &remove_list_head, list_entry) { list_del(&fm_entry->list_entry); devm_kfree(ice_hw_to_dev(hw), fm_entry); diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c index b7dc25da1202..b91dcfd12727 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx.c @@ -444,22 +444,6 @@ void ice_free_rx_ring(struct ice_ring *rx_ring) } /** - * ice_rx_offset - Return expected offset into page to access data - * @rx_ring: Ring we are requesting offset of - * - * Returns the offset value for ring into the data buffer. - */ -static unsigned int ice_rx_offset(struct ice_ring *rx_ring) -{ - if (ice_ring_uses_build_skb(rx_ring)) - return ICE_SKB_PAD; - else if (ice_is_xdp_ena_vsi(rx_ring->vsi)) - return XDP_PACKET_HEADROOM; - - return 0; -} - -/** * ice_setup_rx_ring - Allocate the Rx descriptors * @rx_ring: the Rx ring to set up * @@ -493,7 +477,6 @@ int ice_setup_rx_ring(struct ice_ring *rx_ring) rx_ring->next_to_use = 0; rx_ring->next_to_clean = 0; - rx_ring->rx_offset = ice_rx_offset(rx_ring); if (ice_is_xdp_ena_vsi(rx_ring->vsi)) WRITE_ONCE(rx_ring->xdp_prog, rx_ring->vsi->xdp_prog); diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h index a6cb0c35748c..266036b7a49a 100644 --- a/drivers/net/ethernet/intel/ice/ice_type.h +++ b/drivers/net/ethernet/intel/ice/ice_type.h @@ -535,6 +535,7 @@ struct ice_dcb_app_priority_table { #define ICE_TLV_STATUS_ERR 0x4 #define ICE_APP_PROT_ID_FCOE 0x8906 #define ICE_APP_PROT_ID_ISCSI 0x0cbc +#define ICE_APP_PROT_ID_ISCSI_860 0x035c #define ICE_APP_PROT_ID_FIP 0x8914 #define ICE_APP_SEL_ETHTYPE 0x1 #define ICE_APP_SEL_TCPIP 0x2 diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c index 83f3c9574ed1..9f94d9159acd 100644 --- a/drivers/net/ethernet/intel/ice/ice_xsk.c +++ b/drivers/net/ethernet/intel/ice/ice_xsk.c @@ -358,18 +358,18 @@ xsk_pool_if_up: * This function allocates a number of Rx buffers from the fill ring * or the internal recycle mechanism and places them on the Rx ring. * - * Returns false if all allocations were successful, true if any fail. + * Returns true if all allocations were successful, false if any fail. */ bool ice_alloc_rx_bufs_zc(struct ice_ring *rx_ring, u16 count) { union ice_32b_rx_flex_desc *rx_desc; u16 ntu = rx_ring->next_to_use; struct ice_rx_buf *rx_buf; - bool ret = false; + bool ok = true; dma_addr_t dma; if (!count) - return false; + return true; rx_desc = ICE_RX_DESC(rx_ring, ntu); rx_buf = &rx_ring->rx_buf[ntu]; @@ -377,7 +377,7 @@ bool ice_alloc_rx_bufs_zc(struct ice_ring *rx_ring, u16 count) do { rx_buf->xdp = xsk_buff_alloc(rx_ring->xsk_pool); if (!rx_buf->xdp) { - ret = true; + ok = false; break; } @@ -402,7 +402,7 @@ bool ice_alloc_rx_bufs_zc(struct ice_ring *rx_ring, u16 count) ice_release_rx_desc(rx_ring, ntu); } - return ret; + return ok; } /** diff --git a/drivers/net/ethernet/intel/igb/e1000_hw.h b/drivers/net/ethernet/intel/igb/e1000_hw.h index 5d87957b2627..44111f65afc7 100644 --- a/drivers/net/ethernet/intel/igb/e1000_hw.h +++ b/drivers/net/ethernet/intel/igb/e1000_hw.h @@ -1,8 +1,8 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* Copyright(c) 2007 - 2018 Intel Corporation. */ -#ifndef _E1000_HW_H_ -#define _E1000_HW_H_ +#ifndef _E1000_IGB_HW_H_ +#define _E1000_IGB_HW_H_ #include <linux/types.h> #include <linux/delay.h> @@ -551,4 +551,4 @@ s32 igb_write_pcie_cap_reg(struct e1000_hw *hw, u32 reg, u16 *value); void igb_read_pci_cfg(struct e1000_hw *hw, u32 reg, u16 *value); void igb_write_pci_cfg(struct e1000_hw *hw, u32 reg, u16 *value); -#endif /* _E1000_HW_H_ */ +#endif /* _E1000_IGB_HW_H_ */ diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h index aaa954aae574..7bda8c5edea5 100644 --- a/drivers/net/ethernet/intel/igb/igb.h +++ b/drivers/net/ethernet/intel/igb/igb.h @@ -748,8 +748,8 @@ void igb_ptp_suspend(struct igb_adapter *adapter); void igb_ptp_rx_hang(struct igb_adapter *adapter); void igb_ptp_tx_hang(struct igb_adapter *adapter); void igb_ptp_rx_rgtstamp(struct igb_q_vector *q_vector, struct sk_buff *skb); -void igb_ptp_rx_pktstamp(struct igb_q_vector *q_vector, void *va, - struct sk_buff *skb); +int igb_ptp_rx_pktstamp(struct igb_q_vector *q_vector, void *va, + struct sk_buff *skb); int igb_ptp_set_ts_config(struct net_device *netdev, struct ifreq *ifr); int igb_ptp_get_ts_config(struct net_device *netdev, struct ifreq *ifr); void igb_set_flag_queue_pairs(struct igb_adapter *, const u32); diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 878b31d534ec..a45cd2b416c8 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -8214,7 +8214,8 @@ static void igb_reuse_rx_page(struct igb_ring *rx_ring, new_buff->pagecnt_bias = old_buff->pagecnt_bias; } -static bool igb_can_reuse_rx_page(struct igb_rx_buffer *rx_buffer) +static bool igb_can_reuse_rx_page(struct igb_rx_buffer *rx_buffer, + int rx_buf_pgcnt) { unsigned int pagecnt_bias = rx_buffer->pagecnt_bias; struct page *page = rx_buffer->page; @@ -8225,7 +8226,7 @@ static bool igb_can_reuse_rx_page(struct igb_rx_buffer *rx_buffer) #if (PAGE_SIZE < 8192) /* if we are only owner of page we can reuse it */ - if (unlikely((page_ref_count(page) - pagecnt_bias) > 1)) + if (unlikely((rx_buf_pgcnt - pagecnt_bias) > 1)) return false; #else #define IGB_LAST_OFFSET \ @@ -8301,9 +8302,10 @@ static struct sk_buff *igb_construct_skb(struct igb_ring *rx_ring, return NULL; if (unlikely(igb_test_staterr(rx_desc, E1000_RXDADV_STAT_TSIP))) { - igb_ptp_rx_pktstamp(rx_ring->q_vector, xdp->data, skb); - xdp->data += IGB_TS_HDR_LEN; - size -= IGB_TS_HDR_LEN; + if (!igb_ptp_rx_pktstamp(rx_ring->q_vector, xdp->data, skb)) { + xdp->data += IGB_TS_HDR_LEN; + size -= IGB_TS_HDR_LEN; + } } /* Determine available headroom for copy */ @@ -8364,8 +8366,8 @@ static struct sk_buff *igb_build_skb(struct igb_ring *rx_ring, /* pull timestamp out of packet data */ if (igb_test_staterr(rx_desc, E1000_RXDADV_STAT_TSIP)) { - igb_ptp_rx_pktstamp(rx_ring->q_vector, skb->data, skb); - __skb_pull(skb, IGB_TS_HDR_LEN); + if (!igb_ptp_rx_pktstamp(rx_ring->q_vector, skb->data, skb)) + __skb_pull(skb, IGB_TS_HDR_LEN); } /* update buffer offset */ @@ -8614,11 +8616,17 @@ static unsigned int igb_rx_offset(struct igb_ring *rx_ring) } static struct igb_rx_buffer *igb_get_rx_buffer(struct igb_ring *rx_ring, - const unsigned int size) + const unsigned int size, int *rx_buf_pgcnt) { struct igb_rx_buffer *rx_buffer; rx_buffer = &rx_ring->rx_buffer_info[rx_ring->next_to_clean]; + *rx_buf_pgcnt = +#if (PAGE_SIZE < 8192) + page_count(rx_buffer->page); +#else + 0; +#endif prefetchw(rx_buffer->page); /* we are reusing so sync this buffer for CPU use */ @@ -8634,9 +8642,9 @@ static struct igb_rx_buffer *igb_get_rx_buffer(struct igb_ring *rx_ring, } static void igb_put_rx_buffer(struct igb_ring *rx_ring, - struct igb_rx_buffer *rx_buffer) + struct igb_rx_buffer *rx_buffer, int rx_buf_pgcnt) { - if (igb_can_reuse_rx_page(rx_buffer)) { + if (igb_can_reuse_rx_page(rx_buffer, rx_buf_pgcnt)) { /* hand second half of page back to the ring */ igb_reuse_rx_page(rx_ring, rx_buffer); } else { @@ -8664,6 +8672,7 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget) unsigned int xdp_xmit = 0; struct xdp_buff xdp; u32 frame_sz = 0; + int rx_buf_pgcnt; /* Frame size depend on rx_ring setup when PAGE_SIZE=4K */ #if (PAGE_SIZE < 8192) @@ -8693,7 +8702,7 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget) */ dma_rmb(); - rx_buffer = igb_get_rx_buffer(rx_ring, size); + rx_buffer = igb_get_rx_buffer(rx_ring, size, &rx_buf_pgcnt); /* retrieve a buffer from the ring */ if (!skb) { @@ -8736,7 +8745,7 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget) break; } - igb_put_rx_buffer(rx_ring, rx_buffer); + igb_put_rx_buffer(rx_ring, rx_buffer, rx_buf_pgcnt); cleaned_count++; /* fetch next buffer in frame if non-eop */ diff --git a/drivers/net/ethernet/intel/igb/igb_ptp.c b/drivers/net/ethernet/intel/igb/igb_ptp.c index 7cc5428c3b3d..86a576201f5f 100644 --- a/drivers/net/ethernet/intel/igb/igb_ptp.c +++ b/drivers/net/ethernet/intel/igb/igb_ptp.c @@ -856,6 +856,9 @@ static void igb_ptp_tx_hwtstamp(struct igb_adapter *adapter) dev_kfree_skb_any(skb); } +#define IGB_RET_PTP_DISABLED 1 +#define IGB_RET_PTP_INVALID 2 + /** * igb_ptp_rx_pktstamp - retrieve Rx per packet timestamp * @q_vector: Pointer to interrupt specific structure @@ -864,19 +867,29 @@ static void igb_ptp_tx_hwtstamp(struct igb_adapter *adapter) * * This function is meant to retrieve a timestamp from the first buffer of an * incoming frame. The value is stored in little endian format starting on - * byte 8. + * byte 8 + * + * Returns: 0 if success, nonzero if failure **/ -void igb_ptp_rx_pktstamp(struct igb_q_vector *q_vector, void *va, - struct sk_buff *skb) +int igb_ptp_rx_pktstamp(struct igb_q_vector *q_vector, void *va, + struct sk_buff *skb) { - __le64 *regval = (__le64 *)va; struct igb_adapter *adapter = q_vector->adapter; + __le64 *regval = (__le64 *)va; int adjust = 0; + if (!(adapter->ptp_flags & IGB_PTP_ENABLED)) + return IGB_RET_PTP_DISABLED; + /* The timestamp is recorded in little endian format. * DWORD: 0 1 2 3 * Field: Reserved Reserved SYSTIML SYSTIMH */ + + /* check reserved dwords are zero, be/le doesn't matter for zero */ + if (regval[0]) + return IGB_RET_PTP_INVALID; + igb_ptp_systim_to_hwtstamp(adapter, skb_hwtstamps(skb), le64_to_cpu(regval[1])); @@ -896,6 +909,8 @@ void igb_ptp_rx_pktstamp(struct igb_q_vector *q_vector, void *va, } skb_hwtstamps(skb)->hwtstamp = ktime_sub_ns(skb_hwtstamps(skb)->hwtstamp, adjust); + + return 0; } /** @@ -906,13 +921,15 @@ void igb_ptp_rx_pktstamp(struct igb_q_vector *q_vector, void *va, * This function is meant to retrieve a timestamp from the internal registers * of the adapter and store it in the skb. **/ -void igb_ptp_rx_rgtstamp(struct igb_q_vector *q_vector, - struct sk_buff *skb) +void igb_ptp_rx_rgtstamp(struct igb_q_vector *q_vector, struct sk_buff *skb) { struct igb_adapter *adapter = q_vector->adapter; struct e1000_hw *hw = &adapter->hw; - u64 regval; int adjust = 0; + u64 regval; + + if (!(adapter->ptp_flags & IGB_PTP_ENABLED)) + return; /* If this bit is set, then the RX registers contain the time stamp. No * other packet will be time stamped until we read these registers, so diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h index 5d2809dfd06a..1b08a7dc7bc4 100644 --- a/drivers/net/ethernet/intel/igc/igc.h +++ b/drivers/net/ethernet/intel/igc/igc.h @@ -547,7 +547,7 @@ void igc_ptp_init(struct igc_adapter *adapter); void igc_ptp_reset(struct igc_adapter *adapter); void igc_ptp_suspend(struct igc_adapter *adapter); void igc_ptp_stop(struct igc_adapter *adapter); -void igc_ptp_rx_pktstamp(struct igc_q_vector *q_vector, void *va, +void igc_ptp_rx_pktstamp(struct igc_q_vector *q_vector, __le32 *va, struct sk_buff *skb); int igc_ptp_set_ts_config(struct net_device *netdev, struct ifreq *ifr); int igc_ptp_get_ts_config(struct net_device *netdev, struct ifreq *ifr); diff --git a/drivers/net/ethernet/intel/igc/igc_ethtool.c b/drivers/net/ethernet/intel/igc/igc_ethtool.c index 824a6c454bca..8722294ab90c 100644 --- a/drivers/net/ethernet/intel/igc/igc_ethtool.c +++ b/drivers/net/ethernet/intel/igc/igc_ethtool.c @@ -1711,6 +1711,9 @@ static int igc_ethtool_get_link_ksettings(struct net_device *netdev, Autoneg); } + /* Set pause flow control settings */ + ethtool_link_ksettings_add_link_mode(cmd, supported, Pause); + switch (hw->fc.requested_mode) { case igc_fc_full: ethtool_link_ksettings_add_link_mode(cmd, advertising, Pause); @@ -1725,9 +1728,7 @@ static int igc_ethtool_get_link_ksettings(struct net_device *netdev, Asym_Pause); break; default: - ethtool_link_ksettings_add_link_mode(cmd, advertising, Pause); - ethtool_link_ksettings_add_link_mode(cmd, advertising, - Asym_Pause); + break; } status = pm_runtime_suspended(&adapter->pdev->dev) ? diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index 7ac9597ddb84..4d989ebc9713 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -3831,10 +3831,19 @@ static void igc_reset_task(struct work_struct *work) adapter = container_of(work, struct igc_adapter, reset_task); + rtnl_lock(); + /* If we're already down or resetting, just bail */ + if (test_bit(__IGC_DOWN, &adapter->state) || + test_bit(__IGC_RESETTING, &adapter->state)) { + rtnl_unlock(); + return; + } + igc_rings_dump(adapter); igc_regs_dump(adapter); netdev_err(adapter->netdev, "Reset adapter\n"); igc_reinit_locked(adapter); + rtnl_unlock(); } /** diff --git a/drivers/net/ethernet/intel/igc/igc_ptp.c b/drivers/net/ethernet/intel/igc/igc_ptp.c index ac0b9c85da7c..545f4d0e67cf 100644 --- a/drivers/net/ethernet/intel/igc/igc_ptp.c +++ b/drivers/net/ethernet/intel/igc/igc_ptp.c @@ -152,46 +152,54 @@ static void igc_ptp_systim_to_hwtstamp(struct igc_adapter *adapter, } /** - * igc_ptp_rx_pktstamp - retrieve Rx per packet timestamp + * igc_ptp_rx_pktstamp - Retrieve timestamp from Rx packet buffer * @q_vector: Pointer to interrupt specific structure * @va: Pointer to address containing Rx buffer * @skb: Buffer containing timestamp and packet * - * This function is meant to retrieve the first timestamp from the - * first buffer of an incoming frame. The value is stored in little - * endian format starting on byte 0. There's a second timestamp - * starting on byte 8. - **/ -void igc_ptp_rx_pktstamp(struct igc_q_vector *q_vector, void *va, + * This function retrieves the timestamp saved in the beginning of packet + * buffer. While two timestamps are available, one in timer0 reference and the + * other in timer1 reference, this function considers only the timestamp in + * timer0 reference. + */ +void igc_ptp_rx_pktstamp(struct igc_q_vector *q_vector, __le32 *va, struct sk_buff *skb) { struct igc_adapter *adapter = q_vector->adapter; - __le64 *regval = (__le64 *)va; - int adjust = 0; - - /* The timestamp is recorded in little endian format. - * DWORD: | 0 | 1 | 2 | 3 - * Field: | Timer0 Low | Timer0 High | Timer1 Low | Timer1 High + u64 regval; + int adjust; + + /* Timestamps are saved in little endian at the beginning of the packet + * buffer following the layout: + * + * DWORD: | 0 | 1 | 2 | 3 | + * Field: | Timer1 SYSTIML | Timer1 SYSTIMH | Timer0 SYSTIML | Timer0 SYSTIMH | + * + * SYSTIML holds the nanoseconds part while SYSTIMH holds the seconds + * part of the timestamp. */ - igc_ptp_systim_to_hwtstamp(adapter, skb_hwtstamps(skb), - le64_to_cpu(regval[0])); - - /* adjust timestamp for the RX latency based on link speed */ - if (adapter->hw.mac.type == igc_i225) { - switch (adapter->link_speed) { - case SPEED_10: - adjust = IGC_I225_RX_LATENCY_10; - break; - case SPEED_100: - adjust = IGC_I225_RX_LATENCY_100; - break; - case SPEED_1000: - adjust = IGC_I225_RX_LATENCY_1000; - break; - case SPEED_2500: - adjust = IGC_I225_RX_LATENCY_2500; - break; - } + regval = le32_to_cpu(va[2]); + regval |= (u64)le32_to_cpu(va[3]) << 32; + igc_ptp_systim_to_hwtstamp(adapter, skb_hwtstamps(skb), regval); + + /* Adjust timestamp for the RX latency based on link speed */ + switch (adapter->link_speed) { + case SPEED_10: + adjust = IGC_I225_RX_LATENCY_10; + break; + case SPEED_100: + adjust = IGC_I225_RX_LATENCY_100; + break; + case SPEED_1000: + adjust = IGC_I225_RX_LATENCY_1000; + break; + case SPEED_2500: + adjust = IGC_I225_RX_LATENCY_2500; + break; + default: + adjust = 0; + netdev_warn_once(adapter->netdev, "Imprecise timestamp\n"); + break; } skb_hwtstamps(skb)->hwtstamp = ktime_sub_ns(skb_hwtstamps(skb)->hwtstamp, adjust); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 9f3f12e2ccf2..03d9aad516d4 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -4118,6 +4118,8 @@ void ixgbe_configure_rx_ring(struct ixgbe_adapter *adapter, #endif } + ring->rx_offset = ixgbe_rx_offset(ring); + if (ring->xsk_pool && hw->mac.type != ixgbe_mac_82599EB) { u32 xsk_buf_len = xsk_pool_get_rx_frame_size(ring->xsk_pool); @@ -6578,7 +6580,6 @@ int ixgbe_setup_rx_resources(struct ixgbe_adapter *adapter, rx_ring->next_to_clean = 0; rx_ring->next_to_use = 0; - rx_ring->rx_offset = ixgbe_rx_offset(rx_ring); /* XDP RX-queue info */ if (xdp_rxq_info_reg(&rx_ring->xdp_rxq, adapter->netdev, diff --git a/drivers/net/ethernet/marvell/Kconfig b/drivers/net/ethernet/marvell/Kconfig index 7fe15a3286f4..fe0989c0fc25 100644 --- a/drivers/net/ethernet/marvell/Kconfig +++ b/drivers/net/ethernet/marvell/Kconfig @@ -6,7 +6,7 @@ config NET_VENDOR_MARVELL bool "Marvell devices" default y - depends on PCI || CPU_PXA168 || MV64X60 || PPC32 || PLAT_ORION || INET || COMPILE_TEST + depends on PCI || CPU_PXA168 || PPC32 || PLAT_ORION || INET || COMPILE_TEST help If you have a network (Ethernet) card belonging to this class, say Y. @@ -19,7 +19,7 @@ if NET_VENDOR_MARVELL config MV643XX_ETH tristate "Marvell Discovery (643XX) and Orion ethernet support" - depends on MV64X60 || PPC32 || PLAT_ORION || COMPILE_TEST + depends on PPC32 || PLAT_ORION || COMPILE_TEST depends on INET select PHYLIB select MVMDIO diff --git a/drivers/net/ethernet/marvell/mv643xx_eth.c b/drivers/net/ethernet/marvell/mv643xx_eth.c index 90e6111ce534..3bfb659b5c99 100644 --- a/drivers/net/ethernet/marvell/mv643xx_eth.c +++ b/drivers/net/ethernet/marvell/mv643xx_eth.c @@ -2684,7 +2684,7 @@ static const struct of_device_id mv643xx_eth_shared_ids[] = { MODULE_DEVICE_TABLE(of, mv643xx_eth_shared_ids); #endif -#if defined(CONFIG_OF_IRQ) && !defined(CONFIG_MV64X60) +#ifdef CONFIG_OF_IRQ #define mv643xx_eth_property(_np, _name, _v) \ do { \ u32 tmp; \ diff --git a/drivers/net/ethernet/marvell/octeontx2/af/npc_profile.h b/drivers/net/ethernet/marvell/octeontx2/af/npc_profile.h index b192692b4fc4..5c372d2c24a1 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/npc_profile.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/npc_profile.h @@ -13499,8 +13499,6 @@ static struct npc_mcam_kex npc_mkex_default = { [NPC_LT_LC_IP] = { /* SIP+DIP: 8 bytes, KW2[63:0] */ KEX_LD_CFG(0x07, 0xc, 0x1, 0x0, 0x10), - /* TOS: 1 byte, KW1[63:56] */ - KEX_LD_CFG(0x0, 0x1, 0x1, 0x0, 0xf), }, /* Layer C: IPv6 */ [NPC_LT_LC_IP6] = { diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c index d9a1a71c7ccc..ab24a5e8ee8a 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c @@ -2462,8 +2462,10 @@ static void rvu_unregister_interrupts(struct rvu *rvu) INTR_MASK(rvu->hw->total_pfs) & ~1ULL); for (irq = 0; irq < rvu->num_vec; irq++) { - if (rvu->irq_allocated[irq]) + if (rvu->irq_allocated[irq]) { free_irq(pci_irq_vector(rvu->pdev, irq), rvu); + rvu->irq_allocated[irq] = false; + } } pci_free_irq_vectors(rvu->pdev); @@ -2975,8 +2977,8 @@ static void rvu_remove(struct pci_dev *pdev) struct rvu *rvu = pci_get_drvdata(pdev); rvu_dbg_exit(rvu); - rvu_unregister_interrupts(rvu); rvu_unregister_dl(rvu); + rvu_unregister_interrupts(rvu); rvu_flr_wq_destroy(rvu); rvu_cgx_exit(rvu); rvu_fwdata_exit(rvu); diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h index fa6e46e36ae4..76f399229ddb 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h @@ -678,6 +678,7 @@ void npc_read_mcam_entry(struct rvu *rvu, struct npc_mcam *mcam, u8 *intf, u8 *ena); bool is_mac_feature_supported(struct rvu *rvu, int pf, int feature); u32 rvu_cgx_get_fifolen(struct rvu *rvu); +void *rvu_first_cgx_pdata(struct rvu *rvu); /* CPT APIs */ int rvu_cpt_lf_teardown(struct rvu *rvu, u16 pcifunc, int lf, int slot); diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c index e668e482383a..6e2bf4fcd29c 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c @@ -89,6 +89,21 @@ void *rvu_cgx_pdata(u8 cgx_id, struct rvu *rvu) return rvu->cgx_idmap[cgx_id]; } +/* Return first enabled CGX instance if none are enabled then return NULL */ +void *rvu_first_cgx_pdata(struct rvu *rvu) +{ + int first_enabled_cgx = 0; + void *cgxd = NULL; + + for (; first_enabled_cgx < rvu->cgx_cnt_max; first_enabled_cgx++) { + cgxd = rvu_cgx_pdata(first_enabled_cgx, rvu); + if (cgxd) + break; + } + + return cgxd; +} + /* Based on P2X connectivity find mapped NIX block for a PF */ static void rvu_map_cgx_nix_block(struct rvu *rvu, int pf, int cgx_id, int lmac_id) @@ -711,10 +726,9 @@ int rvu_mbox_handler_cgx_features_get(struct rvu *rvu, u32 rvu_cgx_get_fifolen(struct rvu *rvu) { struct mac_ops *mac_ops; - int rvu_def_cgx_id = 0; u32 fifo_len; - mac_ops = get_mac_ops(rvu_cgx_pdata(rvu_def_cgx_id, rvu)); + mac_ops = get_mac_ops(rvu_first_cgx_pdata(rvu)); fifo_len = mac_ops ? mac_ops->fifo_len : 0; return fifo_len; diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c index aa2ca8780b9c..de3968d2e5ce 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c @@ -234,12 +234,14 @@ static ssize_t rvu_dbg_rsrc_attach_status(struct file *filp, char __user *buffer, size_t count, loff_t *ppos) { - int index, off = 0, flag = 0, go_back = 0, off_prev; + int index, off = 0, flag = 0, go_back = 0, len = 0; struct rvu *rvu = filp->private_data; int lf, pf, vf, pcifunc; struct rvu_block block; int bytes_not_copied; + int lf_str_size = 12; int buf_size = 2048; + char *lfs; char *buf; /* don't allow partial reads */ @@ -249,12 +251,20 @@ static ssize_t rvu_dbg_rsrc_attach_status(struct file *filp, buf = kzalloc(buf_size, GFP_KERNEL); if (!buf) return -ENOSPC; - off += scnprintf(&buf[off], buf_size - 1 - off, "\npcifunc\t\t"); + + lfs = kzalloc(lf_str_size, GFP_KERNEL); + if (!lfs) { + kfree(buf); + return -ENOMEM; + } + off += scnprintf(&buf[off], buf_size - 1 - off, "%-*s", lf_str_size, + "pcifunc"); for (index = 0; index < BLK_COUNT; index++) - if (strlen(rvu->hw->block[index].name)) - off += scnprintf(&buf[off], buf_size - 1 - off, - "%*s\t", (index - 1) * 2, - rvu->hw->block[index].name); + if (strlen(rvu->hw->block[index].name)) { + off += scnprintf(&buf[off], buf_size - 1 - off, + "%-*s", lf_str_size, + rvu->hw->block[index].name); + } off += scnprintf(&buf[off], buf_size - 1 - off, "\n"); for (pf = 0; pf < rvu->hw->total_pfs; pf++) { for (vf = 0; vf <= rvu->hw->total_vfs; vf++) { @@ -263,14 +273,15 @@ static ssize_t rvu_dbg_rsrc_attach_status(struct file *filp, continue; if (vf) { + sprintf(lfs, "PF%d:VF%d", pf, vf - 1); go_back = scnprintf(&buf[off], buf_size - 1 - off, - "PF%d:VF%d\t\t", pf, - vf - 1); + "%-*s", lf_str_size, lfs); } else { + sprintf(lfs, "PF%d", pf); go_back = scnprintf(&buf[off], buf_size - 1 - off, - "PF%d\t\t", pf); + "%-*s", lf_str_size, lfs); } off += go_back; @@ -278,20 +289,22 @@ static ssize_t rvu_dbg_rsrc_attach_status(struct file *filp, block = rvu->hw->block[index]; if (!strlen(block.name)) continue; - off_prev = off; + len = 0; + lfs[len] = '\0'; for (lf = 0; lf < block.lf.max; lf++) { if (block.fn_map[lf] != pcifunc) continue; flag = 1; - off += scnprintf(&buf[off], buf_size - 1 - - off, "%3d,", lf); + len += sprintf(&lfs[len], "%d,", lf); } - if (flag && off_prev != off) - off--; - else - go_back++; + + if (flag) + len--; + lfs[len] = '\0'; off += scnprintf(&buf[off], buf_size - 1 - off, - "\t"); + "%-*s", lf_str_size, lfs); + if (!strlen(lfs)) + go_back += lf_str_size; } if (!flag) off -= go_back; @@ -303,6 +316,7 @@ static ssize_t rvu_dbg_rsrc_attach_status(struct file *filp, } bytes_not_copied = copy_to_user(buffer, buf, off); + kfree(lfs); kfree(buf); if (bytes_not_copied) @@ -319,7 +333,6 @@ static int rvu_dbg_rvu_pf_cgx_map_display(struct seq_file *filp, void *unused) struct rvu *rvu = filp->private; struct pci_dev *pdev = NULL; struct mac_ops *mac_ops; - int rvu_def_cgx_id = 0; char cgx[10], lmac[10]; struct rvu_pfvf *pfvf; int pf, domain, blkid; @@ -327,7 +340,10 @@ static int rvu_dbg_rvu_pf_cgx_map_display(struct seq_file *filp, void *unused) u16 pcifunc; domain = 2; - mac_ops = get_mac_ops(rvu_cgx_pdata(rvu_def_cgx_id, rvu)); + mac_ops = get_mac_ops(rvu_first_cgx_pdata(rvu)); + /* There can be no CGX devices at all */ + if (!mac_ops) + return 0; seq_printf(filp, "PCI dev\t\tRVU PF Func\tNIX block\t%s\tLMAC\n", mac_ops->name); for (pf = 0; pf < rvu->hw->total_pfs; pf++) { @@ -1818,7 +1834,6 @@ static void rvu_dbg_cgx_init(struct rvu *rvu) { struct mac_ops *mac_ops; unsigned long lmac_bmap; - int rvu_def_cgx_id = 0; int i, lmac_id; char dname[20]; void *cgx; @@ -1826,7 +1841,7 @@ static void rvu_dbg_cgx_init(struct rvu *rvu) if (!cgx_get_cgxcnt_max()) return; - mac_ops = get_mac_ops(rvu_cgx_pdata(rvu_def_cgx_id, rvu)); + mac_ops = get_mac_ops(rvu_first_cgx_pdata(rvu)); if (!mac_ops) return; diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c index d3000194e2d3..3d068b7d46bd 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c @@ -2629,7 +2629,7 @@ static int set_flowkey_fields(struct nix_rx_flowkey_alg *alg, u32 flow_cfg) struct nix_rx_flowkey_alg *field; struct nix_rx_flowkey_alg tmp; u32 key_type, valid_key; - int l4_key_offset; + int l4_key_offset = 0; if (!alg) return -EINVAL; diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c index 04bb0803a5c5..0bd49c7080a6 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c @@ -2490,10 +2490,10 @@ int rvu_mbox_handler_npc_mcam_free_counter(struct rvu *rvu, index = find_next_bit(mcam->bmap, mcam->bmap_entries, entry); if (index >= mcam->bmap_entries) break; + entry = index + 1; if (mcam->entry2cntr_map[index] != req->cntr) continue; - entry = index + 1; npc_unmap_mcam_entry_and_cntr(rvu, mcam, blkaddr, index, req->cntr); } diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c index 0dbbf38e0597..dc1778420978 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c @@ -257,17 +257,19 @@ int otx2_get_flow(struct otx2_nic *pfvf, struct ethtool_rxnfc *nfc, int otx2_get_all_flows(struct otx2_nic *pfvf, struct ethtool_rxnfc *nfc, u32 *rule_locs) { + u32 rule_cnt = nfc->rule_cnt; u32 location = 0; int idx = 0; int err = 0; nfc->data = pfvf->flow_cfg->ntuple_max_flows; - while ((!err || err == -ENOENT) && idx < nfc->rule_cnt) { + while ((!err || err == -ENOENT) && idx < rule_cnt) { err = otx2_get_flow(pfvf, nfc, location); if (!err) rule_locs[idx++] = location; location++; } + nfc->rule_cnt = rule_cnt; return err; } diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c index 53ab1814d74b..2fd3d235d292 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c @@ -1672,6 +1672,7 @@ int otx2_stop(struct net_device *netdev) struct otx2_nic *pf = netdev_priv(netdev); struct otx2_cq_poll *cq_poll = NULL; struct otx2_qset *qset = &pf->qset; + struct otx2_rss_info *rss; int qidx, vec, wrk; netif_carrier_off(netdev); @@ -1684,6 +1685,10 @@ int otx2_stop(struct net_device *netdev) /* First stop packet Rx/Tx */ otx2_rxtx_enable(pf, false); + /* Clear RSS enable flag */ + rss = &pf->hw.rss_info; + rss->enable = false; + /* Cleanup Queue IRQ */ vec = pci_irq_vector(pf->pdev, pf->hw.nix_msixoff + NIX_LF_QINT_VEC_START); diff --git a/drivers/net/ethernet/marvell/pxa168_eth.c b/drivers/net/ethernet/marvell/pxa168_eth.c index d1e4d42e497d..3712e1786091 100644 --- a/drivers/net/ethernet/marvell/pxa168_eth.c +++ b/drivers/net/ethernet/marvell/pxa168_eth.c @@ -1544,8 +1544,8 @@ static int pxa168_eth_remove(struct platform_device *pdev) clk_disable_unprepare(pep->clk); mdiobus_unregister(pep->smi_bus); mdiobus_free(pep->smi_bus); - unregister_netdev(dev); cancel_work_sync(&pep->tx_timeout_task); + unregister_netdev(dev); free_netdev(dev); return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/dev.c b/drivers/net/ethernet/mellanox/mlx5/core/dev.c index b051417ede67..9153c9bda96f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/dev.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/dev.c @@ -191,12 +191,12 @@ static bool is_ib_supported(struct mlx5_core_dev *dev) } enum { - MLX5_INTERFACE_PROTOCOL_ETH_REP, MLX5_INTERFACE_PROTOCOL_ETH, + MLX5_INTERFACE_PROTOCOL_ETH_REP, + MLX5_INTERFACE_PROTOCOL_IB, MLX5_INTERFACE_PROTOCOL_IB_REP, MLX5_INTERFACE_PROTOCOL_MPIB, - MLX5_INTERFACE_PROTOCOL_IB, MLX5_INTERFACE_PROTOCOL_VNET, }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 7435fe6829b6..bc6f77ea0a31 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -92,14 +92,15 @@ struct page_pool; MLX5_MPWRQ_LOG_WQE_SZ - PAGE_SHIFT : 0) #define MLX5_MPWRQ_PAGES_PER_WQE BIT(MLX5_MPWRQ_WQE_PAGE_ORDER) -#define MLX5_MTT_OCTW(npages) (ALIGN(npages, 8) / 2) +#define MLX5_ALIGN_MTTS(mtts) (ALIGN(mtts, 8)) +#define MLX5_ALIGNED_MTTS_OCTW(mtts) ((mtts) / 2) +#define MLX5_MTT_OCTW(mtts) (MLX5_ALIGNED_MTTS_OCTW(MLX5_ALIGN_MTTS(mtts))) /* Add another page to MLX5E_REQUIRED_WQE_MTTS as a buffer between * WQEs, This page will absorb write overflow by the hardware, when * receiving packets larger than MTU. These oversize packets are * dropped by the driver at a later stage. */ -#define MLX5E_REQUIRED_WQE_MTTS (ALIGN(MLX5_MPWRQ_PAGES_PER_WQE + 1, 8)) -#define MLX5E_LOG_ALIGNED_MPWQE_PPW (ilog2(MLX5E_REQUIRED_WQE_MTTS)) +#define MLX5E_REQUIRED_WQE_MTTS (MLX5_ALIGN_MTTS(MLX5_MPWRQ_PAGES_PER_WQE + 1)) #define MLX5E_REQUIRED_MTTS(wqes) (wqes * MLX5E_REQUIRED_WQE_MTTS) #define MLX5E_MAX_RQ_NUM_MTTS \ ((1 << 16) * 2) /* So that MLX5_MTT_OCTW(num_mtts) fits into u16 */ @@ -515,6 +516,7 @@ struct mlx5e_icosq { struct mlx5_wq_cyc wq; void __iomem *uar_map; u32 sqn; + u16 reserved_room; unsigned long state; /* control path */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c index f3f6eb081948..68e54cc1cd16 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c @@ -186,6 +186,28 @@ mlx5_tc_ct_entry_has_nat(struct mlx5_ct_entry *entry) } static int +mlx5_get_label_mapping(struct mlx5_tc_ct_priv *ct_priv, + u32 *labels, u32 *id) +{ + if (!memchr_inv(labels, 0, sizeof(u32) * 4)) { + *id = 0; + return 0; + } + + if (mapping_add(ct_priv->labels_mapping, labels, id)) + return -EOPNOTSUPP; + + return 0; +} + +static void +mlx5_put_label_mapping(struct mlx5_tc_ct_priv *ct_priv, u32 id) +{ + if (id) + mapping_remove(ct_priv->labels_mapping, id); +} + +static int mlx5_tc_ct_rule_to_tuple(struct mlx5_ct_tuple *tuple, struct flow_rule *rule) { struct flow_match_control control; @@ -436,7 +458,7 @@ mlx5_tc_ct_entry_del_rule(struct mlx5_tc_ct_priv *ct_priv, mlx5_tc_rule_delete(netdev_priv(ct_priv->netdev), zone_rule->rule, attr); mlx5e_mod_hdr_detach(ct_priv->dev, ct_priv->mod_hdr_tbl, zone_rule->mh); - mapping_remove(ct_priv->labels_mapping, attr->ct_attr.ct_labels_id); + mlx5_put_label_mapping(ct_priv, attr->ct_attr.ct_labels_id); kfree(attr); } @@ -639,8 +661,8 @@ mlx5_tc_ct_entry_create_mod_hdr(struct mlx5_tc_ct_priv *ct_priv, if (!meta) return -EOPNOTSUPP; - err = mapping_add(ct_priv->labels_mapping, meta->ct_metadata.labels, - &attr->ct_attr.ct_labels_id); + err = mlx5_get_label_mapping(ct_priv, meta->ct_metadata.labels, + &attr->ct_attr.ct_labels_id); if (err) return -EOPNOTSUPP; if (nat) { @@ -677,7 +699,7 @@ mlx5_tc_ct_entry_create_mod_hdr(struct mlx5_tc_ct_priv *ct_priv, err_mapping: dealloc_mod_hdr_actions(&mod_acts); - mapping_remove(ct_priv->labels_mapping, attr->ct_attr.ct_labels_id); + mlx5_put_label_mapping(ct_priv, attr->ct_attr.ct_labels_id); return err; } @@ -745,7 +767,7 @@ mlx5_tc_ct_entry_add_rule(struct mlx5_tc_ct_priv *ct_priv, err_rule: mlx5e_mod_hdr_detach(ct_priv->dev, ct_priv->mod_hdr_tbl, zone_rule->mh); - mapping_remove(ct_priv->labels_mapping, attr->ct_attr.ct_labels_id); + mlx5_put_label_mapping(ct_priv, attr->ct_attr.ct_labels_id); err_mod_hdr: kfree(attr); err_attr: @@ -1181,7 +1203,8 @@ int mlx5_tc_ct_add_no_trk_match(struct mlx5_flow_spec *spec) mlx5e_tc_match_to_reg_get_match(spec, CTSTATE_TO_REG, &ctstate, &ctstate_mask); - if (ctstate_mask) + + if ((ctstate & ctstate_mask) == MLX5_CT_STATE_TRK_BIT) return -EOPNOTSUPP; ctstate_mask |= MLX5_CT_STATE_TRK_BIT; @@ -1196,7 +1219,7 @@ void mlx5_tc_ct_match_del(struct mlx5_tc_ct_priv *priv, struct mlx5_ct_attr *ct_ if (!priv || !ct_attr->ct_labels_id) return; - mapping_remove(priv->labels_mapping, ct_attr->ct_labels_id); + mlx5_put_label_mapping(priv, ct_attr->ct_labels_id); } int @@ -1279,7 +1302,7 @@ mlx5_tc_ct_match_add(struct mlx5_tc_ct_priv *priv, ct_labels[1] = key->ct_labels[1] & mask->ct_labels[1]; ct_labels[2] = key->ct_labels[2] & mask->ct_labels[2]; ct_labels[3] = key->ct_labels[3] & mask->ct_labels[3]; - if (mapping_add(priv->labels_mapping, ct_labels, &ct_attr->ct_labels_id)) + if (mlx5_get_label_mapping(priv, ct_labels, &ct_attr->ct_labels_id)) return -EOPNOTSUPP; mlx5e_tc_match_to_reg_match(spec, LABELS_TO_REG, ct_attr->ct_labels_id, MLX5_CT_LABELS_MASK); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c index f8075a604605..172e0474f2e6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c @@ -685,14 +685,14 @@ int mlx5e_tc_tun_route_lookup(struct mlx5e_priv *priv, u16 vport_num; int err = 0; - if (flow_attr->ip_version == 4) { + if (flow_attr->tun_ip_version == 4) { /* Addresses are swapped for decap */ attr.fl.fl4.saddr = esw_attr->rx_tun_attr->dst_ip.v4; attr.fl.fl4.daddr = esw_attr->rx_tun_attr->src_ip.v4; err = mlx5e_route_lookup_ipv4_get(priv, priv->netdev, &attr); } #if IS_ENABLED(CONFIG_INET) && IS_ENABLED(CONFIG_IPV6) - else if (flow_attr->ip_version == 6) { + else if (flow_attr->tun_ip_version == 6) { /* Addresses are swapped for decap */ attr.fl.fl6.saddr = esw_attr->rx_tun_attr->dst_ip.v6; attr.fl.fl6.daddr = esw_attr->rx_tun_attr->src_ip.v6; @@ -718,10 +718,10 @@ int mlx5e_tc_tun_route_lookup(struct mlx5e_priv *priv, esw_attr->rx_tun_attr->decap_vport = vport_num; out: - if (flow_attr->ip_version == 4) + if (flow_attr->tun_ip_version == 4) mlx5e_route_lookup_ipv4_put(&attr); #if IS_ENABLED(CONFIG_INET) && IS_ENABLED(CONFIG_IPV6) - else if (flow_attr->ip_version == 6) + else if (flow_attr->tun_ip_version == 6) mlx5e_route_lookup_ipv6_put(&attr); #endif return err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.h index 67de2bf36861..e1271998b937 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.h @@ -21,6 +21,11 @@ enum { MLX5E_TC_TUNNEL_TYPE_MPLSOUDP, }; +struct mlx5e_encap_key { + const struct ip_tunnel_key *ip_tun_key; + struct mlx5e_tc_tunnel *tc_tunnel; +}; + struct mlx5e_tc_tunnel { int tunnel_type; enum mlx5_flow_match_level match_level; @@ -44,6 +49,8 @@ struct mlx5e_tc_tunnel { struct flow_cls_offload *f, void *headers_c, void *headers_v); + bool (*encap_info_equal)(struct mlx5e_encap_key *a, + struct mlx5e_encap_key *b); }; extern struct mlx5e_tc_tunnel vxlan_tunnel; @@ -101,6 +108,9 @@ int mlx5e_tc_tun_parse_udp_ports(struct mlx5e_priv *priv, void *headers_c, void *headers_v); +bool mlx5e_tc_tun_encap_info_equal_generic(struct mlx5e_encap_key *a, + struct mlx5e_encap_key *b); + #endif /* CONFIG_MLX5_ESWITCH */ #endif //__MLX5_EN_TC_TUNNEL_H__ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c index 6a116335bb21..9f16ad2c0710 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c @@ -89,6 +89,7 @@ int mlx5e_tc_set_attr_rx_tun(struct mlx5e_tc_flow *flow, * required to establish routing. */ flow_flag_set(flow, TUN_RX); + flow->attr->tun_ip_version = ip_version; return 0; } @@ -475,16 +476,11 @@ void mlx5e_detach_decap(struct mlx5e_priv *priv, mlx5e_decap_dealloc(priv, d); } -struct encap_key { - const struct ip_tunnel_key *ip_tun_key; - struct mlx5e_tc_tunnel *tc_tunnel; -}; - -static int cmp_encap_info(struct encap_key *a, - struct encap_key *b) +bool mlx5e_tc_tun_encap_info_equal_generic(struct mlx5e_encap_key *a, + struct mlx5e_encap_key *b) { - return memcmp(a->ip_tun_key, b->ip_tun_key, sizeof(*a->ip_tun_key)) || - a->tc_tunnel->tunnel_type != b->tc_tunnel->tunnel_type; + return memcmp(a->ip_tun_key, b->ip_tun_key, sizeof(*a->ip_tun_key)) == 0 && + a->tc_tunnel->tunnel_type == b->tc_tunnel->tunnel_type; } static int cmp_decap_info(struct mlx5e_decap_key *a, @@ -493,7 +489,7 @@ static int cmp_decap_info(struct mlx5e_decap_key *a, return memcmp(&a->key, &b->key, sizeof(b->key)); } -static int hash_encap_info(struct encap_key *key) +static int hash_encap_info(struct mlx5e_encap_key *key) { return jhash(key->ip_tun_key, sizeof(*key->ip_tun_key), key->tc_tunnel->tunnel_type); @@ -515,18 +511,18 @@ static bool mlx5e_decap_take(struct mlx5e_decap_entry *e) } static struct mlx5e_encap_entry * -mlx5e_encap_get(struct mlx5e_priv *priv, struct encap_key *key, +mlx5e_encap_get(struct mlx5e_priv *priv, struct mlx5e_encap_key *key, uintptr_t hash_key) { struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; + struct mlx5e_encap_key e_key; struct mlx5e_encap_entry *e; - struct encap_key e_key; hash_for_each_possible_rcu(esw->offloads.encap_tbl, e, encap_hlist, hash_key) { e_key.ip_tun_key = &e->tun_info->key; e_key.tc_tunnel = e->tunnel; - if (!cmp_encap_info(&e_key, key) && + if (e->tunnel->encap_info_equal(&e_key, key) && mlx5e_encap_take(e)) return e; } @@ -693,8 +689,8 @@ int mlx5e_attach_encap(struct mlx5e_priv *priv, struct mlx5_flow_attr *attr = flow->attr; const struct ip_tunnel_info *tun_info; unsigned long tbl_time_before = 0; - struct encap_key key; struct mlx5e_encap_entry *e; + struct mlx5e_encap_key key; bool entry_created = false; unsigned short family; uintptr_t hash_key; @@ -1091,7 +1087,7 @@ int mlx5e_attach_decap_route(struct mlx5e_priv *priv, if (err || !esw_attr->rx_tun_attr->decap_vport) goto out; - key.ip_version = attr->ip_version; + key.ip_version = attr->tun_ip_version; if (key.ip_version == 4) key.endpoint_ip.v4 = esw_attr->rx_tun_attr->dst_ip.v4; else diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_geneve.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_geneve.c index e472ed0eacfb..f5b26f5a7de4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_geneve.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_geneve.c @@ -227,6 +227,10 @@ static int mlx5e_tc_tun_parse_geneve_options(struct mlx5e_priv *priv, option_key = (struct geneve_opt *)&enc_opts.key->data[0]; option_mask = (struct geneve_opt *)&enc_opts.mask->data[0]; + if (option_mask->opt_class == 0 && option_mask->type == 0 && + !memchr_inv(option_mask->opt_data, 0, option_mask->length * 4)) + return 0; + if (option_key->length > max_tlv_option_data_len) { NL_SET_ERR_MSG_MOD(extack, "Matching on GENEVE options: unsupported option len"); @@ -325,6 +329,34 @@ static int mlx5e_tc_tun_parse_geneve(struct mlx5e_priv *priv, return mlx5e_tc_tun_parse_geneve_options(priv, spec, f); } +static bool mlx5e_tc_tun_encap_info_equal_geneve(struct mlx5e_encap_key *a, + struct mlx5e_encap_key *b) +{ + struct ip_tunnel_info *a_info; + struct ip_tunnel_info *b_info; + bool a_has_opts, b_has_opts; + + if (!mlx5e_tc_tun_encap_info_equal_generic(a, b)) + return false; + + a_has_opts = !!(a->ip_tun_key->tun_flags & TUNNEL_GENEVE_OPT); + b_has_opts = !!(b->ip_tun_key->tun_flags & TUNNEL_GENEVE_OPT); + + /* keys are equal when both don't have any options attached */ + if (!a_has_opts && !b_has_opts) + return true; + + if (a_has_opts != b_has_opts) + return false; + + /* geneve options stored in memory next to ip_tunnel_info struct */ + a_info = container_of(a->ip_tun_key, struct ip_tunnel_info, key); + b_info = container_of(b->ip_tun_key, struct ip_tunnel_info, key); + + return a_info->options_len == b_info->options_len && + memcmp(a_info + 1, b_info + 1, a_info->options_len) == 0; +} + struct mlx5e_tc_tunnel geneve_tunnel = { .tunnel_type = MLX5E_TC_TUNNEL_TYPE_GENEVE, .match_level = MLX5_MATCH_L4, @@ -334,4 +366,5 @@ struct mlx5e_tc_tunnel geneve_tunnel = { .generate_ip_tun_hdr = mlx5e_gen_ip_tunnel_header_geneve, .parse_udp_ports = mlx5e_tc_tun_parse_udp_ports_geneve, .parse_tunnel = mlx5e_tc_tun_parse_geneve, + .encap_info_equal = mlx5e_tc_tun_encap_info_equal_geneve, }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_gre.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_gre.c index 2805416c32a3..ada14f0574dc 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_gre.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_gre.c @@ -94,4 +94,5 @@ struct mlx5e_tc_tunnel gre_tunnel = { .generate_ip_tun_hdr = mlx5e_gen_ip_tunnel_header_gretap, .parse_udp_ports = NULL, .parse_tunnel = mlx5e_tc_tun_parse_gretap, + .encap_info_equal = mlx5e_tc_tun_encap_info_equal_generic, }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_mplsoudp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_mplsoudp.c index 3479672e84cf..60952b33b568 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_mplsoudp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_mplsoudp.c @@ -131,4 +131,5 @@ struct mlx5e_tc_tunnel mplsoudp_tunnel = { .generate_ip_tun_hdr = generate_ip_tun_hdr, .parse_udp_ports = parse_udp_ports, .parse_tunnel = parse_tunnel, + .encap_info_equal = mlx5e_tc_tun_encap_info_equal_generic, }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c index 038a0f1cecec..4267f3a1059e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c @@ -150,4 +150,5 @@ struct mlx5e_tc_tunnel vxlan_tunnel = { .generate_ip_tun_hdr = mlx5e_gen_ip_tunnel_header_vxlan, .parse_udp_ports = mlx5e_tc_tun_parse_udp_ports_vxlan, .parse_tunnel = mlx5e_tc_tun_parse_vxlan, + .encap_info_equal = mlx5e_tc_tun_encap_info_equal_generic, }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h index 2371b83dad9c..055c3bc23733 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h @@ -441,4 +441,10 @@ static inline u16 mlx5e_stop_room_for_wqe(u16 wqe_size) return wqe_size * 2 - 1; } +static inline bool mlx5e_icosq_can_post_wqe(struct mlx5e_icosq *sq, u16 wqe_size) +{ + u16 room = sq->reserved_room + mlx5e_stop_room_for_wqe(wqe_size); + + return mlx5e_wqc_has_room_for(&sq->wq, sq->cc, sq->pc, room); +} #endif diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c index d06532d0baa4..19d22a63313f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c @@ -46,7 +46,8 @@ struct mlx5e_ktls_offload_context_rx { struct tls12_crypto_info_aes_gcm_128 crypto_info; struct accel_rule rule; struct sock *sk; - struct mlx5e_rq_stats *stats; + struct mlx5e_rq_stats *rq_stats; + struct mlx5e_tls_sw_stats *sw_stats; struct completion add_ctx; u32 tirn; u32 key_id; @@ -137,11 +138,10 @@ post_static_params(struct mlx5e_icosq *sq, { struct mlx5e_set_tls_static_params_wqe *wqe; struct mlx5e_icosq_wqe_info wi; - u16 pi, num_wqebbs, room; + u16 pi, num_wqebbs; num_wqebbs = MLX5E_TLS_SET_STATIC_PARAMS_WQEBBS; - room = mlx5e_stop_room_for_wqe(num_wqebbs); - if (unlikely(!mlx5e_wqc_has_room_for(&sq->wq, sq->cc, sq->pc, room))) + if (unlikely(!mlx5e_icosq_can_post_wqe(sq, num_wqebbs))) return ERR_PTR(-ENOSPC); pi = mlx5e_icosq_get_next_pi(sq, num_wqebbs); @@ -168,11 +168,10 @@ post_progress_params(struct mlx5e_icosq *sq, { struct mlx5e_set_tls_progress_params_wqe *wqe; struct mlx5e_icosq_wqe_info wi; - u16 pi, num_wqebbs, room; + u16 pi, num_wqebbs; num_wqebbs = MLX5E_TLS_SET_PROGRESS_PARAMS_WQEBBS; - room = mlx5e_stop_room_for_wqe(num_wqebbs); - if (unlikely(!mlx5e_wqc_has_room_for(&sq->wq, sq->cc, sq->pc, room))) + if (unlikely(!mlx5e_icosq_can_post_wqe(sq, num_wqebbs))) return ERR_PTR(-ENOSPC); pi = mlx5e_icosq_get_next_pi(sq, num_wqebbs); @@ -218,7 +217,7 @@ unlock: return err; err_out: - priv_rx->stats->tls_resync_req_skip++; + priv_rx->rq_stats->tls_resync_req_skip++; err = PTR_ERR(cseg); complete(&priv_rx->add_ctx); goto unlock; @@ -277,17 +276,15 @@ resync_post_get_progress_params(struct mlx5e_icosq *sq, buf->priv_rx = priv_rx; - BUILD_BUG_ON(MLX5E_KTLS_GET_PROGRESS_WQEBBS != 1); - spin_lock_bh(&sq->channel->async_icosq_lock); - if (unlikely(!mlx5e_wqc_has_room_for(&sq->wq, sq->cc, sq->pc, 1))) { + if (unlikely(!mlx5e_icosq_can_post_wqe(sq, MLX5E_KTLS_GET_PROGRESS_WQEBBS))) { spin_unlock_bh(&sq->channel->async_icosq_lock); err = -ENOSPC; goto err_dma_unmap; } - pi = mlx5e_icosq_get_next_pi(sq, 1); + pi = mlx5e_icosq_get_next_pi(sq, MLX5E_KTLS_GET_PROGRESS_WQEBBS); wqe = MLX5E_TLS_FETCH_GET_PROGRESS_PARAMS_WQE(sq, pi); #define GET_PSV_DS_CNT (DIV_ROUND_UP(sizeof(*wqe), MLX5_SEND_WQE_DS)) @@ -307,7 +304,7 @@ resync_post_get_progress_params(struct mlx5e_icosq *sq, wi = (struct mlx5e_icosq_wqe_info) { .wqe_type = MLX5E_ICOSQ_WQE_GET_PSV_TLS, - .num_wqebbs = 1, + .num_wqebbs = MLX5E_KTLS_GET_PROGRESS_WQEBBS, .tls_get_params.buf = buf, }; icosq_fill_wi(sq, pi, &wi); @@ -322,7 +319,7 @@ err_dma_unmap: err_free: kfree(buf); err_out: - priv_rx->stats->tls_resync_req_skip++; + priv_rx->rq_stats->tls_resync_req_skip++; return err; } @@ -378,13 +375,13 @@ static int resync_handle_seq_match(struct mlx5e_ktls_offload_context_rx *priv_rx cseg = post_static_params(sq, priv_rx); if (IS_ERR(cseg)) { - priv_rx->stats->tls_resync_res_skip++; + priv_rx->rq_stats->tls_resync_res_skip++; err = PTR_ERR(cseg); goto unlock; } /* Do not increment priv_rx refcnt, CQE handling is empty */ mlx5e_notify_hw(&sq->wq, sq->pc, sq->uar_map, cseg); - priv_rx->stats->tls_resync_res_ok++; + priv_rx->rq_stats->tls_resync_res_ok++; unlock: spin_unlock_bh(&c->async_icosq_lock); @@ -420,13 +417,13 @@ void mlx5e_ktls_handle_get_psv_completion(struct mlx5e_icosq_wqe_info *wi, auth_state = MLX5_GET(tls_progress_params, ctx, auth_state); if (tracker_state != MLX5E_TLS_PROGRESS_PARAMS_RECORD_TRACKER_STATE_TRACKING || auth_state != MLX5E_TLS_PROGRESS_PARAMS_AUTH_STATE_NO_OFFLOAD) { - priv_rx->stats->tls_resync_req_skip++; + priv_rx->rq_stats->tls_resync_req_skip++; goto out; } hw_seq = MLX5_GET(tls_progress_params, ctx, hw_resync_tcp_sn); tls_offload_rx_resync_async_request_end(priv_rx->sk, cpu_to_be32(hw_seq)); - priv_rx->stats->tls_resync_req_end++; + priv_rx->rq_stats->tls_resync_req_end++; out: mlx5e_ktls_priv_rx_put(priv_rx); dma_unmap_single(dev, buf->dma_addr, PROGRESS_PARAMS_PADDED_SIZE, DMA_FROM_DEVICE); @@ -609,7 +606,8 @@ int mlx5e_ktls_add_rx(struct net_device *netdev, struct sock *sk, priv_rx->rxq = rxq; priv_rx->sk = sk; - priv_rx->stats = &priv->channel_stats[rxq].rq; + priv_rx->rq_stats = &priv->channel_stats[rxq].rq; + priv_rx->sw_stats = &priv->tls->sw_stats; mlx5e_set_ktls_rx_priv_ctx(tls_ctx, priv_rx); rqtn = priv->direct_tir[rxq].rqt.rqtn; @@ -630,7 +628,7 @@ int mlx5e_ktls_add_rx(struct net_device *netdev, struct sock *sk, if (err) goto err_post_wqes; - priv_rx->stats->tls_ctx++; + atomic64_inc(&priv_rx->sw_stats->rx_tls_ctx); return 0; @@ -666,7 +664,7 @@ void mlx5e_ktls_del_rx(struct net_device *netdev, struct tls_context *tls_ctx) if (cancel_work_sync(&resync->work)) mlx5e_ktls_priv_rx_put(priv_rx); - priv_rx->stats->tls_del++; + atomic64_inc(&priv_rx->sw_stats->rx_tls_del); if (priv_rx->rule.rule) mlx5e_accel_fs_del_sk(priv_rx->rule.rule); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c index d16def68ecff..51bdf71073f3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB // Copyright (c) 2019 Mellanox Technologies. +#include "en_accel/tls.h" #include "en_accel/ktls_txrx.h" #include "en_accel/ktls_utils.h" @@ -50,6 +51,7 @@ static int mlx5e_ktls_create_tis(struct mlx5_core_dev *mdev, u32 *tisn) struct mlx5e_ktls_offload_context_tx { struct tls_offload_context_tx *tx_ctx; struct tls12_crypto_info_aes_gcm_128 crypto_info; + struct mlx5e_tls_sw_stats *sw_stats; u32 expected_seq; u32 tisn; u32 key_id; @@ -99,6 +101,7 @@ int mlx5e_ktls_add_tx(struct net_device *netdev, struct sock *sk, if (err) goto err_create_key; + priv_tx->sw_stats = &priv->tls->sw_stats; priv_tx->expected_seq = start_offload_tcp_sn; priv_tx->crypto_info = *(struct tls12_crypto_info_aes_gcm_128 *)crypto_info; @@ -111,6 +114,7 @@ int mlx5e_ktls_add_tx(struct net_device *netdev, struct sock *sk, goto err_create_tis; priv_tx->ctx_post_pending = true; + atomic64_inc(&priv_tx->sw_stats->tx_tls_ctx); return 0; @@ -452,7 +456,6 @@ bool mlx5e_ktls_handle_tx_skb(struct tls_context *tls_ctx, struct mlx5e_txqsq *s if (unlikely(mlx5e_ktls_tx_offload_test_and_clear_pending(priv_tx))) { mlx5e_ktls_tx_post_param_wqes(sq, priv_tx, false, false); - stats->tls_ctx++; } seq = ntohl(tcp_hdr(skb)->seq); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.h index bd270a85c804..4c9274d390da 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.h @@ -41,10 +41,13 @@ #include "en.h" struct mlx5e_tls_sw_stats { + atomic64_t tx_tls_ctx; atomic64_t tx_tls_drop_metadata; atomic64_t tx_tls_drop_resync_alloc; atomic64_t tx_tls_drop_no_sync_data; atomic64_t tx_tls_drop_bypass_required; + atomic64_t rx_tls_ctx; + atomic64_t rx_tls_del; atomic64_t rx_tls_drop_resync_request; atomic64_t rx_tls_resync_request; atomic64_t rx_tls_resync_reply; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_stats.c index b949b9a7538b..29463bdb7715 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_stats.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_stats.c @@ -45,49 +45,60 @@ static const struct counter_desc mlx5e_tls_sw_stats_desc[] = { { MLX5E_DECLARE_STAT(struct mlx5e_tls_sw_stats, tx_tls_drop_bypass_required) }, }; +static const struct counter_desc mlx5e_ktls_sw_stats_desc[] = { + { MLX5E_DECLARE_STAT(struct mlx5e_tls_sw_stats, tx_tls_ctx) }, + { MLX5E_DECLARE_STAT(struct mlx5e_tls_sw_stats, rx_tls_ctx) }, + { MLX5E_DECLARE_STAT(struct mlx5e_tls_sw_stats, rx_tls_del) }, +}; + #define MLX5E_READ_CTR_ATOMIC64(ptr, dsc, i) \ atomic64_read((atomic64_t *)((char *)(ptr) + (dsc)[i].offset)) -#define NUM_TLS_SW_COUNTERS ARRAY_SIZE(mlx5e_tls_sw_stats_desc) - -static bool is_tls_atomic_stats(struct mlx5e_priv *priv) +static const struct counter_desc *get_tls_atomic_stats(struct mlx5e_priv *priv) { - return priv->tls && !mlx5_accel_is_ktls_device(priv->mdev); + if (!priv->tls) + return NULL; + if (mlx5_accel_is_ktls_device(priv->mdev)) + return mlx5e_ktls_sw_stats_desc; + return mlx5e_tls_sw_stats_desc; } int mlx5e_tls_get_count(struct mlx5e_priv *priv) { - if (!is_tls_atomic_stats(priv)) + if (!priv->tls) return 0; - - return NUM_TLS_SW_COUNTERS; + if (mlx5_accel_is_ktls_device(priv->mdev)) + return ARRAY_SIZE(mlx5e_ktls_sw_stats_desc); + return ARRAY_SIZE(mlx5e_tls_sw_stats_desc); } int mlx5e_tls_get_strings(struct mlx5e_priv *priv, uint8_t *data) { - unsigned int i, idx = 0; + const struct counter_desc *stats_desc; + unsigned int i, n, idx = 0; - if (!is_tls_atomic_stats(priv)) - return 0; + stats_desc = get_tls_atomic_stats(priv); + n = mlx5e_tls_get_count(priv); - for (i = 0; i < NUM_TLS_SW_COUNTERS; i++) + for (i = 0; i < n; i++) strcpy(data + (idx++) * ETH_GSTRING_LEN, - mlx5e_tls_sw_stats_desc[i].format); + stats_desc[i].format); - return NUM_TLS_SW_COUNTERS; + return n; } int mlx5e_tls_get_stats(struct mlx5e_priv *priv, u64 *data) { - int i, idx = 0; + const struct counter_desc *stats_desc; + unsigned int i, n, idx = 0; - if (!is_tls_atomic_stats(priv)) - return 0; + stats_desc = get_tls_atomic_stats(priv); + n = mlx5e_tls_get_count(priv); - for (i = 0; i < NUM_TLS_SW_COUNTERS; i++) + for (i = 0; i < n; i++) data[idx++] = MLX5E_READ_CTR_ATOMIC64(&priv->tls->sw_stats, - mlx5e_tls_sw_stats_desc, i); + stats_desc, i); - return NUM_TLS_SW_COUNTERS; + return n; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index abdf721bb264..53802e18af90 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -758,11 +758,11 @@ static int get_fec_supported_advertised(struct mlx5_core_dev *dev, return 0; } -static void ptys2ethtool_supported_advertised_port(struct ethtool_link_ksettings *link_ksettings, - u32 eth_proto_cap, - u8 connector_type, bool ext) +static void ptys2ethtool_supported_advertised_port(struct mlx5_core_dev *mdev, + struct ethtool_link_ksettings *link_ksettings, + u32 eth_proto_cap, u8 connector_type) { - if ((!connector_type && !ext) || connector_type >= MLX5E_CONNECTOR_TYPE_NUMBER) { + if (!MLX5_CAP_PCAM_FEATURE(mdev, ptys_connector_type)) { if (eth_proto_cap & (MLX5E_PROT_MASK(MLX5E_10GBASE_CR) | MLX5E_PROT_MASK(MLX5E_10GBASE_SR) | MLX5E_PROT_MASK(MLX5E_40GBASE_CR4) @@ -898,9 +898,9 @@ static int ptys2connector_type[MLX5E_CONNECTOR_TYPE_NUMBER] = { [MLX5E_PORT_OTHER] = PORT_OTHER, }; -static u8 get_connector_port(u32 eth_proto, u8 connector_type, bool ext) +static u8 get_connector_port(struct mlx5_core_dev *mdev, u32 eth_proto, u8 connector_type) { - if ((connector_type || ext) && connector_type < MLX5E_CONNECTOR_TYPE_NUMBER) + if (MLX5_CAP_PCAM_FEATURE(mdev, ptys_connector_type)) return ptys2connector_type[connector_type]; if (eth_proto & @@ -1001,11 +1001,11 @@ int mlx5e_ethtool_get_link_ksettings(struct mlx5e_priv *priv, data_rate_oper, link_ksettings); eth_proto_oper = eth_proto_oper ? eth_proto_oper : eth_proto_cap; - - link_ksettings->base.port = get_connector_port(eth_proto_oper, - connector_type, ext); - ptys2ethtool_supported_advertised_port(link_ksettings, eth_proto_admin, - connector_type, ext); + connector_type = connector_type < MLX5E_CONNECTOR_TYPE_NUMBER ? + connector_type : MLX5E_PORT_UNKNOWN; + link_ksettings->base.port = get_connector_port(mdev, eth_proto_oper, connector_type); + ptys2ethtool_supported_advertised_port(mdev, link_ksettings, eth_proto_admin, + connector_type); get_lp_advertising(mdev, eth_proto_lp, link_ksettings); if (an_status == MLX5_AN_COMPLETE) @@ -1887,6 +1887,7 @@ static int set_pflag_rx_cqe_compress(struct net_device *netdev, { struct mlx5e_priv *priv = netdev_priv(netdev); struct mlx5_core_dev *mdev = priv->mdev; + int err; if (!MLX5_CAP_GEN(mdev, cqe_compression)) return -EOPNOTSUPP; @@ -1896,7 +1897,10 @@ static int set_pflag_rx_cqe_compress(struct net_device *netdev, return -EINVAL; } - mlx5e_modify_rx_cqe_compression_locked(priv, enable); + err = mlx5e_modify_rx_cqe_compression_locked(priv, enable); + if (err) + return err; + priv->channels.params.rx_cqe_compress_def = enable; return 0; @@ -2014,8 +2018,13 @@ static int set_pflag_tx_port_ts(struct net_device *netdev, bool enable) */ if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) { + struct mlx5e_params old_params; + + old_params = priv->channels.params; priv->channels.params = new_channels.params; err = mlx5e_num_channels_changed(priv); + if (err) + priv->channels.params = old_params; goto out; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index ec2fcb2a2977..5db63b9f3b70 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -334,9 +334,9 @@ static int mlx5e_create_rq_umr_mkey(struct mlx5_core_dev *mdev, struct mlx5e_rq rq->wqe_overflow.addr); } -static inline u64 mlx5e_get_mpwqe_offset(struct mlx5e_rq *rq, u16 wqe_ix) +static u64 mlx5e_get_mpwqe_offset(u16 wqe_ix) { - return (wqe_ix << MLX5E_LOG_ALIGNED_MPWQE_PPW) << PAGE_SHIFT; + return MLX5E_REQUIRED_MTTS(wqe_ix) << PAGE_SHIFT; } static void mlx5e_init_frags_partition(struct mlx5e_rq *rq) @@ -577,7 +577,7 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c, mlx5_wq_ll_get_wqe(&rq->mpwqe.wq, i); u32 byte_count = rq->mpwqe.num_strides << rq->mpwqe.log_stride_sz; - u64 dma_offset = mlx5e_get_mpwqe_offset(rq, i); + u64 dma_offset = mlx5e_get_mpwqe_offset(i); wqe->data[0].addr = cpu_to_be64(dma_offset + rq->buff.headroom); wqe->data[0].byte_count = cpu_to_be32(byte_count); @@ -1091,6 +1091,7 @@ static int mlx5e_alloc_icosq(struct mlx5e_channel *c, sq->channel = c; sq->uar_map = mdev->mlx5e_res.bfreg.map; + sq->reserved_room = param->stop_room; param->wq.db_numa_node = cpu_to_node(c->cpu); err = mlx5_wq_cyc_create(mdev, ¶m->wq, sqc_wq, wq, &sq->wq_ctrl); @@ -2350,6 +2351,24 @@ void mlx5e_build_icosq_param(struct mlx5e_priv *priv, mlx5e_build_ico_cq_param(priv, log_wq_size, ¶m->cqp); } +static void mlx5e_build_async_icosq_param(struct mlx5e_priv *priv, + struct mlx5e_params *params, + u8 log_wq_size, + struct mlx5e_sq_param *param) +{ + void *sqc = param->sqc; + void *wq = MLX5_ADDR_OF(sqc, sqc, wq); + + mlx5e_build_sq_param_common(priv, param); + + /* async_icosq is used by XSK only if xdp_prog is active */ + if (params->xdp_prog) + param->stop_room = mlx5e_stop_room_for_wqe(1); /* for XSK NOP */ + MLX5_SET(sqc, sqc, reg_umr, MLX5_CAP_ETH(priv->mdev, reg_umr_sq)); + MLX5_SET(wq, wq, log_wq_sz, log_wq_size); + mlx5e_build_ico_cq_param(priv, log_wq_size, ¶m->cqp); +} + void mlx5e_build_xdpsq_param(struct mlx5e_priv *priv, struct mlx5e_params *params, struct mlx5e_sq_param *param) @@ -2368,8 +2387,9 @@ static u8 mlx5e_build_icosq_log_wq_sz(struct mlx5e_params *params, { switch (params->rq_wq_type) { case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ: - return order_base_2(MLX5E_UMR_WQEBBS) + - mlx5e_get_rq_log_wq_sz(rqp->rqc); + return max_t(u8, MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE, + order_base_2(MLX5E_UMR_WQEBBS) + + mlx5e_get_rq_log_wq_sz(rqp->rqc)); default: /* MLX5_WQ_TYPE_CYCLIC */ return MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE; } @@ -2397,7 +2417,7 @@ static void mlx5e_build_channel_param(struct mlx5e_priv *priv, mlx5e_build_sq_param(priv, params, &cparam->txq_sq); mlx5e_build_xdpsq_param(priv, params, &cparam->xdp_sq); mlx5e_build_icosq_param(priv, icosq_log_wq_sz, &cparam->icosq); - mlx5e_build_icosq_param(priv, async_icosq_log_wq_sz, &cparam->async_icosq); + mlx5e_build_async_icosq_param(priv, params, async_icosq_log_wq_sz, &cparam->async_icosq); } int mlx5e_open_channels(struct mlx5e_priv *priv, @@ -2502,8 +2522,10 @@ void mlx5e_close_channels(struct mlx5e_channels *chs) { int i; - if (chs->port_ptp) + if (chs->port_ptp) { mlx5e_port_ptp_close(chs->port_ptp); + chs->port_ptp = NULL; + } for (i = 0; i < chs->num; i++) mlx5e_close_channel(chs->c[i]); @@ -3815,6 +3837,15 @@ void mlx5e_fold_sw_stats64(struct mlx5e_priv *priv, struct rtnl_link_stats64 *s) s->tx_dropped += sq_stats->dropped; } } + if (priv->port_ptp_opened) { + for (i = 0; i < priv->max_opened_tc; i++) { + struct mlx5e_sq_stats *sq_stats = &priv->port_ptp_stats.sq[i]; + + s->tx_packets += sq_stats->packets; + s->tx_bytes += sq_stats->bytes; + s->tx_dropped += sq_stats->dropped; + } + } } void @@ -3834,10 +3865,17 @@ mlx5e_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats) } if (mlx5e_is_uplink_rep(priv)) { + struct mlx5e_vport_stats *vstats = &priv->stats.vport; + stats->rx_packets = PPORT_802_3_GET(pstats, a_frames_received_ok); stats->rx_bytes = PPORT_802_3_GET(pstats, a_octets_received_ok); stats->tx_packets = PPORT_802_3_GET(pstats, a_frames_transmitted_ok); stats->tx_bytes = PPORT_802_3_GET(pstats, a_octets_transmitted_ok); + + /* vport multicast also counts packets that are dropped due to steering + * or rx out of buffer + */ + stats->multicast = VPORT_COUNTER_GET(vstats, received_eth_multicast.packets); } else { mlx5e_fold_sw_stats64(priv, stats); } @@ -4683,8 +4721,10 @@ static int mlx5e_xdp_set(struct net_device *netdev, struct bpf_prog *prog) struct mlx5e_channel *c = priv->channels.c[i]; mlx5e_rq_replace_xdp_prog(&c->rq, prog); - if (test_bit(MLX5E_CHANNEL_STATE_XSK, c->state)) + if (test_bit(MLX5E_CHANNEL_STATE_XSK, c->state)) { + bpf_prog_inc(prog); mlx5e_rq_replace_xdp_prog(&c->xskrq, prog); + } } unlock: @@ -4958,6 +4998,11 @@ void mlx5e_build_nic_params(struct mlx5e_priv *priv, struct mlx5e_xsk *xsk, u16 priv->max_nch); params->num_tc = 1; + /* Set an initial non-zero value, so that mlx5e_select_queue won't + * divide by zero if called before first activating channels. + */ + priv->num_tc_x_num_ch = params->num_channels * params->num_tc; + /* SQ */ params->log_sq_size = is_kdump_kernel() ? MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE : @@ -5474,8 +5519,6 @@ int mlx5e_priv_init(struct mlx5e_priv *priv, struct net_device *netdev, struct mlx5_core_dev *mdev) { - memset(priv, 0, sizeof(*priv)); - /* priv init */ priv->mdev = mdev; priv->netdev = netdev; @@ -5508,12 +5551,18 @@ void mlx5e_priv_cleanup(struct mlx5e_priv *priv) { int i; + /* bail if change profile failed and also rollback failed */ + if (!priv->mdev) + return; + destroy_workqueue(priv->wq); free_cpumask_var(priv->scratchpad.cpumask); for (i = 0; i < priv->htb.max_qos_sqs; i++) kfree(priv->htb.qos_sq_stats[i]); kvfree(priv->htb.qos_sq_stats); + + memset(priv, 0, sizeof(*priv)); } struct net_device * @@ -5630,11 +5679,10 @@ void mlx5e_detach_netdev(struct mlx5e_priv *priv) } static int -mlx5e_netdev_attach_profile(struct mlx5e_priv *priv, +mlx5e_netdev_attach_profile(struct net_device *netdev, struct mlx5_core_dev *mdev, const struct mlx5e_profile *new_profile, void *new_ppriv) { - struct net_device *netdev = priv->netdev; - struct mlx5_core_dev *mdev = priv->mdev; + struct mlx5e_priv *priv = netdev_priv(netdev); int err; err = mlx5e_priv_init(priv, netdev, mdev); @@ -5647,10 +5695,16 @@ mlx5e_netdev_attach_profile(struct mlx5e_priv *priv, priv->ppriv = new_ppriv; err = new_profile->init(priv->mdev, priv->netdev); if (err) - return err; + goto priv_cleanup; err = mlx5e_attach_netdev(priv); if (err) - new_profile->cleanup(priv); + goto profile_cleanup; + return err; + +profile_cleanup: + new_profile->cleanup(priv); +priv_cleanup: + mlx5e_priv_cleanup(priv); return err; } @@ -5659,13 +5713,14 @@ int mlx5e_netdev_change_profile(struct mlx5e_priv *priv, { unsigned int new_max_nch = mlx5e_calc_max_nch(priv, new_profile); const struct mlx5e_profile *orig_profile = priv->profile; + struct net_device *netdev = priv->netdev; + struct mlx5_core_dev *mdev = priv->mdev; void *orig_ppriv = priv->ppriv; int err, rollback_err; /* sanity */ if (new_max_nch != priv->max_nch) { - netdev_warn(priv->netdev, - "%s: Replacing profile with different max channels\n", + netdev_warn(netdev, "%s: Replacing profile with different max channels\n", __func__); return -EINVAL; } @@ -5675,22 +5730,19 @@ int mlx5e_netdev_change_profile(struct mlx5e_priv *priv, priv->profile->cleanup(priv); mlx5e_priv_cleanup(priv); - err = mlx5e_netdev_attach_profile(priv, new_profile, new_ppriv); + err = mlx5e_netdev_attach_profile(netdev, mdev, new_profile, new_ppriv); if (err) { /* roll back to original profile */ - netdev_warn(priv->netdev, "%s: new profile init failed, %d\n", - __func__, err); + netdev_warn(netdev, "%s: new profile init failed, %d\n", __func__, err); goto rollback; } return 0; rollback: - rollback_err = mlx5e_netdev_attach_profile(priv, orig_profile, orig_ppriv); - if (rollback_err) { - netdev_err(priv->netdev, - "%s: failed to rollback to orig profile, %d\n", + rollback_err = mlx5e_netdev_attach_profile(netdev, mdev, orig_profile, orig_ppriv); + if (rollback_err) + netdev_err(netdev, "%s: failed to rollback to orig profile, %d\n", __func__, rollback_err); - } return err; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index a132fff7a980..8d39bfee84a9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -1107,8 +1107,9 @@ static void mlx5e_uplink_rep_enable(struct mlx5e_priv *priv) mlx5e_rep_tc_enable(priv); - mlx5_modify_vport_admin_state(mdev, MLX5_VPORT_STATE_OP_MOD_UPLINK, - 0, 0, MLX5_VPORT_ADMIN_STATE_AUTO); + if (MLX5_CAP_GEN(mdev, uplink_follow)) + mlx5_modify_vport_admin_state(mdev, MLX5_VPORT_STATE_OP_MOD_UPLINK, + 0, 0, MLX5_VPORT_ADMIN_STATE_AUTO); mlx5_lag_add(mdev, netdev); priv->events_nb.notifier_call = uplink_rep_async_event; mlx5_notifier_register(mdev, &priv->events_nb); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index 1b6ad94ebb10..249d8905e644 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -500,7 +500,6 @@ static int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix) struct mlx5e_icosq *sq = rq->icosq; struct mlx5_wq_cyc *wq = &sq->wq; struct mlx5e_umr_wqe *umr_wqe; - u16 xlt_offset = ix << (MLX5E_LOG_ALIGNED_MPWQE_PPW - 1); u16 pi; int err; int i; @@ -531,7 +530,8 @@ static int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix) umr_wqe->ctrl.opmod_idx_opcode = cpu_to_be32((sq->pc << MLX5_WQE_CTRL_WQE_INDEX_SHIFT) | MLX5_OPCODE_UMR); - umr_wqe->uctrl.xlt_offset = cpu_to_be16(xlt_offset); + umr_wqe->uctrl.xlt_offset = + cpu_to_be16(MLX5_ALIGNED_MTTS_OCTW(MLX5E_REQUIRED_MTTS(ix))); sq->db.wqe_info[pi] = (struct mlx5e_icosq_wqe_info) { .wqe_type = MLX5E_ICOSQ_WQE_UMR_RX, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c index 92c5b81427b9..88a01c59ce61 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c @@ -116,7 +116,6 @@ static const struct counter_desc sw_stats_desc[] = { #ifdef CONFIG_MLX5_EN_TLS { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tls_encrypted_packets) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tls_encrypted_bytes) }, - { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tls_ctx) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tls_ooo) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tls_dump_packets) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tls_dump_bytes) }, @@ -180,8 +179,6 @@ static const struct counter_desc sw_stats_desc[] = { #ifdef CONFIG_MLX5_EN_TLS { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_tls_decrypted_packets) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_tls_decrypted_bytes) }, - { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_tls_ctx) }, - { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_tls_del) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_tls_resync_req_pkt) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_tls_resync_req_start) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_tls_resync_req_end) }, @@ -342,8 +339,6 @@ static void mlx5e_stats_grp_sw_update_stats_rq_stats(struct mlx5e_sw_stats *s, #ifdef CONFIG_MLX5_EN_TLS s->rx_tls_decrypted_packets += rq_stats->tls_decrypted_packets; s->rx_tls_decrypted_bytes += rq_stats->tls_decrypted_bytes; - s->rx_tls_ctx += rq_stats->tls_ctx; - s->rx_tls_del += rq_stats->tls_del; s->rx_tls_resync_req_pkt += rq_stats->tls_resync_req_pkt; s->rx_tls_resync_req_start += rq_stats->tls_resync_req_start; s->rx_tls_resync_req_end += rq_stats->tls_resync_req_end; @@ -390,7 +385,6 @@ static void mlx5e_stats_grp_sw_update_stats_sq(struct mlx5e_sw_stats *s, #ifdef CONFIG_MLX5_EN_TLS s->tx_tls_encrypted_packets += sq_stats->tls_encrypted_packets; s->tx_tls_encrypted_bytes += sq_stats->tls_encrypted_bytes; - s->tx_tls_ctx += sq_stats->tls_ctx; s->tx_tls_ooo += sq_stats->tls_ooo; s->tx_tls_dump_bytes += sq_stats->tls_dump_bytes; s->tx_tls_dump_packets += sq_stats->tls_dump_packets; @@ -1622,8 +1616,6 @@ static const struct counter_desc rq_stats_desc[] = { #ifdef CONFIG_MLX5_EN_TLS { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, tls_decrypted_packets) }, { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, tls_decrypted_bytes) }, - { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, tls_ctx) }, - { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, tls_del) }, { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, tls_resync_req_pkt) }, { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, tls_resync_req_start) }, { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, tls_resync_req_end) }, @@ -1650,7 +1642,6 @@ static const struct counter_desc sq_stats_desc[] = { #ifdef CONFIG_MLX5_EN_TLS { MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tls_encrypted_packets) }, { MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tls_encrypted_bytes) }, - { MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tls_ctx) }, { MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tls_ooo) }, { MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tls_dump_packets) }, { MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tls_dump_bytes) }, @@ -1776,7 +1767,6 @@ static const struct counter_desc qos_sq_stats_desc[] = { #ifdef CONFIG_MLX5_EN_TLS { MLX5E_DECLARE_QOS_TX_STAT(struct mlx5e_sq_stats, tls_encrypted_packets) }, { MLX5E_DECLARE_QOS_TX_STAT(struct mlx5e_sq_stats, tls_encrypted_bytes) }, - { MLX5E_DECLARE_QOS_TX_STAT(struct mlx5e_sq_stats, tls_ctx) }, { MLX5E_DECLARE_QOS_TX_STAT(struct mlx5e_sq_stats, tls_ooo) }, { MLX5E_DECLARE_QOS_TX_STAT(struct mlx5e_sq_stats, tls_dump_packets) }, { MLX5E_DECLARE_QOS_TX_STAT(struct mlx5e_sq_stats, tls_dump_bytes) }, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h index 93c41312fb03..adf9b7b8b712 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h @@ -191,7 +191,6 @@ struct mlx5e_sw_stats { #ifdef CONFIG_MLX5_EN_TLS u64 tx_tls_encrypted_packets; u64 tx_tls_encrypted_bytes; - u64 tx_tls_ctx; u64 tx_tls_ooo; u64 tx_tls_dump_packets; u64 tx_tls_dump_bytes; @@ -202,8 +201,6 @@ struct mlx5e_sw_stats { u64 rx_tls_decrypted_packets; u64 rx_tls_decrypted_bytes; - u64 rx_tls_ctx; - u64 rx_tls_del; u64 rx_tls_resync_req_pkt; u64 rx_tls_resync_req_start; u64 rx_tls_resync_req_end; @@ -334,8 +331,6 @@ struct mlx5e_rq_stats { #ifdef CONFIG_MLX5_EN_TLS u64 tls_decrypted_packets; u64 tls_decrypted_bytes; - u64 tls_ctx; - u64 tls_del; u64 tls_resync_req_pkt; u64 tls_resync_req_start; u64 tls_resync_req_end; @@ -364,7 +359,6 @@ struct mlx5e_sq_stats { #ifdef CONFIG_MLX5_EN_TLS u64 tls_encrypted_packets; u64 tls_encrypted_bytes; - u64 tls_ctx; u64 tls_ooo; u64 tls_dump_packets; u64 tls_dump_bytes; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 0da69b98f38f..df2a0af854bb 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -2296,6 +2296,16 @@ static int __parse_cls_flower(struct mlx5e_priv *priv, *match_level = MLX5_MATCH_L4; } + /* Currenlty supported only for MPLS over UDP */ + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_MPLS) && + !netif_is_bareudp(filter_dev)) { + NL_SET_ERR_MSG_MOD(extack, + "Matching on MPLS is supported only for MPLS over UDP"); + netdev_err(priv->netdev, + "Matching on MPLS is supported only for MPLS over UDP\n"); + return -EOPNOTSUPP; + } + return 0; } @@ -2899,6 +2909,37 @@ static int is_action_keys_supported(const struct flow_action_entry *act, return 0; } +static bool modify_tuple_supported(bool modify_tuple, bool ct_clear, + bool ct_flow, struct netlink_ext_ack *extack, + struct mlx5e_priv *priv, + struct mlx5_flow_spec *spec) +{ + if (!modify_tuple || ct_clear) + return true; + + if (ct_flow) { + NL_SET_ERR_MSG_MOD(extack, + "can't offload tuple modification with non-clear ct()"); + netdev_info(priv->netdev, + "can't offload tuple modification with non-clear ct()"); + return false; + } + + /* Add ct_state=-trk match so it will be offloaded for non ct flows + * (or after clear action), as otherwise, since the tuple is changed, + * we can't restore ct state + */ + if (mlx5_tc_ct_add_no_trk_match(spec)) { + NL_SET_ERR_MSG_MOD(extack, + "can't offload tuple modification with ct matches and no ct(clear) action"); + netdev_info(priv->netdev, + "can't offload tuple modification with ct matches and no ct(clear) action"); + return false; + } + + return true; +} + static bool modify_header_match_supported(struct mlx5e_priv *priv, struct mlx5_flow_spec *spec, struct flow_action *flow_action, @@ -2937,18 +2978,9 @@ static bool modify_header_match_supported(struct mlx5e_priv *priv, return err; } - /* Add ct_state=-trk match so it will be offloaded for non ct flows - * (or after clear action), as otherwise, since the tuple is changed, - * we can't restore ct state - */ - if (!ct_clear && modify_tuple && - mlx5_tc_ct_add_no_trk_match(spec)) { - NL_SET_ERR_MSG_MOD(extack, - "can't offload tuple modify header with ct matches"); - netdev_info(priv->netdev, - "can't offload tuple modify header with ct matches"); + if (!modify_tuple_supported(modify_tuple, ct_clear, ct_flow, extack, + priv, spec)) return false; - } ip_proto = MLX5_GET(fte_match_set_lyr_2_4, headers_v, ip_protocol); if (modify_ip_header && ip_proto != IPPROTO_TCP && @@ -4445,7 +4477,8 @@ static int apply_police_params(struct mlx5e_priv *priv, u64 rate, */ if (rate) { rate = (rate * BITS_PER_BYTE) + 500000; - rate_mbps = max_t(u64, do_div(rate, 1000000), 1); + do_div(rate, 1000000); + rate_mbps = max_t(u32, rate, 1); } err = mlx5_esw_modify_vport_rate(esw, vport_num, rate_mbps); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h index 89003ae7775a..25c091795bcd 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h @@ -79,6 +79,7 @@ struct mlx5_flow_attr { u8 inner_match_level; u8 outer_match_level; u8 ip_version; + u8 tun_ip_version; u32 flags; union { struct mlx5_esw_flow_attr esw_attr[0]; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c index 174dfbc996c6..1fa9c18563da 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c @@ -931,13 +931,24 @@ void mlx5_core_eq_free_irqs(struct mlx5_core_dev *dev) mutex_unlock(&table->lock); } +#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING +#define MLX5_MAX_ASYNC_EQS 4 +#else +#define MLX5_MAX_ASYNC_EQS 3 +#endif + int mlx5_eq_table_create(struct mlx5_core_dev *dev) { struct mlx5_eq_table *eq_table = dev->priv.eq_table; + int num_eqs = MLX5_CAP_GEN(dev, max_num_eqs) ? + MLX5_CAP_GEN(dev, max_num_eqs) : + 1 << MLX5_CAP_GEN(dev, log_max_eq); int err; eq_table->num_comp_eqs = - mlx5_irq_get_num_comp(eq_table->irq_table); + min_t(int, + mlx5_irq_get_num_comp(eq_table->irq_table), + num_eqs - MLX5_MAX_ASYNC_EQS); err = create_async_eqs(dev); if (err) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/indir_table.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/indir_table.c index 6f6772bf61a2..3da7becc1069 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/indir_table.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/indir_table.c @@ -248,7 +248,7 @@ err_mod_hdr_regc0: err_ethertype: kfree(rule); out: - kfree(rule_spec); + kvfree(rule_spec); return err; } @@ -328,7 +328,7 @@ static int mlx5_create_indir_recirc_group(struct mlx5_eswitch *esw, e->recirc_cnt = 0; out: - kfree(in); + kvfree(in); return err; } @@ -347,7 +347,7 @@ static int mlx5_create_indir_fwd_group(struct mlx5_eswitch *esw, spec = kvzalloc(sizeof(*spec), GFP_KERNEL); if (!spec) { - kfree(in); + kvfree(in); return -ENOMEM; } @@ -371,8 +371,8 @@ static int mlx5_create_indir_fwd_group(struct mlx5_eswitch *esw, } err_out: - kfree(spec); - kfree(in); + kvfree(spec); + kvfree(in); return err; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 94cb0217b4f3..d4a2f8d1ee9f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -537,6 +537,14 @@ esw_setup_vport_dests(struct mlx5_flow_destination *dest, struct mlx5_flow_act * return i; } +static bool +esw_src_port_rewrite_supported(struct mlx5_eswitch *esw) +{ + return MLX5_CAP_GEN(esw->dev, reg_c_preserve) && + mlx5_eswitch_vport_match_metadata_enabled(esw) && + MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, ignore_flow_level); +} + static int esw_setup_dests(struct mlx5_flow_destination *dest, struct mlx5_flow_act *flow_act, @@ -550,8 +558,7 @@ esw_setup_dests(struct mlx5_flow_destination *dest, int err = 0; if (!mlx5_eswitch_termtbl_required(esw, attr, flow_act, spec) && - MLX5_CAP_GEN(esw_attr->in_mdev, reg_c_preserve) && - mlx5_eswitch_vport_match_metadata_enabled(esw)) + esw_src_port_rewrite_supported(esw)) attr->flags |= MLX5_ESW_ATTR_FLAG_SRC_REWRITE; if (attr->dest_ft) { @@ -1715,36 +1722,40 @@ static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw) } esw->fdb_table.offloads.send_to_vport_grp = g; - /* meta send to vport */ - memset(flow_group_in, 0, inlen); - MLX5_SET(create_flow_group_in, flow_group_in, match_criteria_enable, - MLX5_MATCH_MISC_PARAMETERS_2); - - match_criteria = MLX5_ADDR_OF(create_flow_group_in, flow_group_in, match_criteria); + if (esw_src_port_rewrite_supported(esw)) { + /* meta send to vport */ + memset(flow_group_in, 0, inlen); + MLX5_SET(create_flow_group_in, flow_group_in, match_criteria_enable, + MLX5_MATCH_MISC_PARAMETERS_2); - MLX5_SET(fte_match_param, match_criteria, - misc_parameters_2.metadata_reg_c_0, mlx5_eswitch_get_vport_metadata_mask()); - MLX5_SET(fte_match_param, match_criteria, - misc_parameters_2.metadata_reg_c_1, ESW_TUN_MASK); + match_criteria = MLX5_ADDR_OF(create_flow_group_in, flow_group_in, match_criteria); - num_vfs = esw->esw_funcs.num_vfs; - if (num_vfs) { - MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, ix); - MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, ix + num_vfs - 1); - ix += num_vfs; + MLX5_SET(fte_match_param, match_criteria, + misc_parameters_2.metadata_reg_c_0, + mlx5_eswitch_get_vport_metadata_mask()); + MLX5_SET(fte_match_param, match_criteria, + misc_parameters_2.metadata_reg_c_1, ESW_TUN_MASK); - g = mlx5_create_flow_group(fdb, flow_group_in); - if (IS_ERR(g)) { - err = PTR_ERR(g); - esw_warn(dev, "Failed to create send-to-vport meta flow group err(%d)\n", - err); - goto send_vport_meta_err; + num_vfs = esw->esw_funcs.num_vfs; + if (num_vfs) { + MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, ix); + MLX5_SET(create_flow_group_in, flow_group_in, + end_flow_index, ix + num_vfs - 1); + ix += num_vfs; + + g = mlx5_create_flow_group(fdb, flow_group_in); + if (IS_ERR(g)) { + err = PTR_ERR(g); + esw_warn(dev, "Failed to create send-to-vport meta flow group err(%d)\n", + err); + goto send_vport_meta_err; + } + esw->fdb_table.offloads.send_to_vport_meta_grp = g; + + err = mlx5_eswitch_add_send_to_vport_meta_rules(esw); + if (err) + goto meta_rule_err; } - esw->fdb_table.offloads.send_to_vport_meta_grp = g; - - err = mlx5_eswitch_add_send_to_vport_meta_rules(esw); - if (err) - goto meta_rule_err; } if (MLX5_CAP_ESW(esw->dev, merged_eswitch)) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c index 80da50e12915..bd66ab2af5b5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c @@ -575,6 +575,7 @@ static int mlx5_fpga_conn_create_qp(struct mlx5_fpga_conn *conn, MLX5_SET(qpc, qpc, log_sq_size, ilog2(conn->qp.sq.size)); MLX5_SET(qpc, qpc, cqn_snd, conn->cq.mcq.cqn); MLX5_SET(qpc, qpc, cqn_rcv, conn->cq.mcq.cqn); + MLX5_SET(qpc, qpc, ts_format, mlx5_get_qp_default_ts(mdev)); MLX5_SET64(qpc, qpc, dbr_addr, conn->qp.wq_ctrl.db.dma); if (MLX5_CAP_GEN(mdev, cqe_version) == 1) MLX5_SET(qpc, qpc, user_index, 0xFFFFFF); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c index 1eeca45cfcdf..6f7cef47e04c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c @@ -233,6 +233,7 @@ int mlx5i_create_underlay_qp(struct mlx5e_priv *priv) } qpc = MLX5_ADDR_OF(create_qp_in, in, qpc); + MLX5_SET(qpc, qpc, ts_format, mlx5_get_qp_default_ts(priv->mdev)); MLX5_SET(qpc, qpc, st, MLX5_QP_ST_UD); MLX5_SET(qpc, qpc, pm_state, MLX5_QP_PM_MIGRATED); MLX5_SET(qpc, qpc, ulp_stateless_offload_mode, @@ -694,6 +695,7 @@ static int mlx5i_check_required_hca_cap(struct mlx5_core_dev *mdev) static void mlx5_rdma_netdev_free(struct net_device *netdev) { struct mlx5e_priv *priv = mlx5i_epriv(netdev); + struct mlx5_core_dev *mdev = priv->mdev; struct mlx5i_priv *ipriv = priv->ppriv; const struct mlx5e_profile *profile = priv->profile; @@ -702,7 +704,7 @@ static void mlx5_rdma_netdev_free(struct net_device *netdev) if (!ipriv->sub_interface) { mlx5i_pkey_qpn_ht_cleanup(netdev); - mlx5e_destroy_mdev_resources(priv->mdev); + mlx5e_destroy_mdev_resources(mdev); } } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c index b0e129d0f6d8..1e7f26b240de 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c @@ -495,15 +495,15 @@ static int mlx5_perout_configure(struct ptp_clock_info *ptp, return -EINVAL; field_select = MLX5_MTPPS_FS_ENABLE; + pin = ptp_find_pin(clock->ptp, PTP_PF_PEROUT, rq->perout.index); + if (pin < 0) + return -EBUSY; + if (on) { bool rt_mode = mlx5_real_time_mode(mdev); u32 nsec; s64 sec; - pin = ptp_find_pin(clock->ptp, PTP_PF_PEROUT, rq->perout.index); - if (pin < 0) - return -EBUSY; - pin_mode = MLX5_PIN_MODE_OUT; pattern = MLX5_OUT_PATTERN_PERIODIC; ts.tv_sec = rq->perout.period.sec; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c index b265f27b2166..90b524c59f3c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c @@ -181,15 +181,13 @@ static int mlx5_sf_dev_vhca_arm_all(struct mlx5_sf_dev_table *table) u16 max_functions; u16 function_id; int err = 0; - bool ecpu; int i; max_functions = mlx5_sf_max_functions(dev); function_id = MLX5_CAP_GEN(dev, sf_base_id); - ecpu = mlx5_read_embedded_cpu(dev); /* Arm the vhca context as the vhca event notifier */ for (i = 0; i < max_functions; i++) { - err = mlx5_vhca_event_arm(dev, function_id, ecpu); + err = mlx5_vhca_event_arm(dev, function_id); if (err) return err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/hw_table.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/hw_table.c index 58b6be0b03d7..a5a0f60bef66 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sf/hw_table.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/hw_table.c @@ -6,7 +6,7 @@ #include "sf.h" #include "mlx5_ifc_vhca_event.h" #include "vhca_event.h" -#include "ecpf.h" +#include "mlx5_core.h" struct mlx5_sf_hw { u32 usr_sfnum; @@ -18,7 +18,6 @@ struct mlx5_sf_hw_table { struct mlx5_core_dev *dev; struct mlx5_sf_hw *sfs; int max_local_functions; - u8 ecpu: 1; struct mutex table_lock; /* Serializes sf deletion and vhca state change handler. */ struct notifier_block vhca_nb; }; @@ -64,7 +63,7 @@ int mlx5_sf_hw_table_sf_alloc(struct mlx5_core_dev *dev, u32 usr_sfnum) } if (sw_id == -ENOSPC) { err = -ENOSPC; - goto err; + goto exist_err; } hw_fn_id = mlx5_sf_sw_to_hw_id(table->dev, sw_id); @@ -72,7 +71,7 @@ int mlx5_sf_hw_table_sf_alloc(struct mlx5_core_dev *dev, u32 usr_sfnum) if (err) goto err; - err = mlx5_modify_vhca_sw_id(dev, hw_fn_id, table->ecpu, usr_sfnum); + err = mlx5_modify_vhca_sw_id(dev, hw_fn_id, usr_sfnum); if (err) goto vhca_err; @@ -118,7 +117,7 @@ void mlx5_sf_hw_table_sf_deferred_free(struct mlx5_core_dev *dev, u16 id) hw_fn_id = mlx5_sf_sw_to_hw_id(dev, id); mutex_lock(&table->table_lock); - err = mlx5_cmd_query_vhca_state(dev, hw_fn_id, table->ecpu, out, sizeof(out)); + err = mlx5_cmd_query_vhca_state(dev, hw_fn_id, out, sizeof(out)); if (err) goto err; state = MLX5_GET(query_vhca_state_out, out, vhca_state_context.vhca_state); @@ -164,7 +163,6 @@ int mlx5_sf_hw_table_init(struct mlx5_core_dev *dev) table->dev = dev; table->sfs = sfs; table->max_local_functions = max_functions; - table->ecpu = mlx5_read_embedded_cpu(dev); dev->priv.sf_hw_table = table; mlx5_core_dbg(dev, "SF HW table: max sfs = %d\n", max_functions); return 0; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/mlx5_ifc_vhca_event.h b/drivers/net/ethernet/mellanox/mlx5/core/sf/mlx5_ifc_vhca_event.h index 1daf5a122ba3..4fc870140d71 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sf/mlx5_ifc_vhca_event.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/mlx5_ifc_vhca_event.h @@ -20,7 +20,7 @@ struct mlx5_ifc_vhca_state_context_bits { u8 sw_function_id[0x20]; - u8 reserved_at_40[0x80]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_query_vhca_state_out_bits { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/vhca_event.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/vhca_event.c index af2f2dd9db25..28b14b05086f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sf/vhca_event.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/vhca_event.c @@ -19,52 +19,51 @@ struct mlx5_vhca_event_work { struct mlx5_vhca_state_event event; }; -int mlx5_cmd_query_vhca_state(struct mlx5_core_dev *dev, u16 function_id, - bool ecpu, u32 *out, u32 outlen) +int mlx5_cmd_query_vhca_state(struct mlx5_core_dev *dev, u16 function_id, u32 *out, u32 outlen) { u32 in[MLX5_ST_SZ_DW(query_vhca_state_in)] = {}; MLX5_SET(query_vhca_state_in, in, opcode, MLX5_CMD_OP_QUERY_VHCA_STATE); MLX5_SET(query_vhca_state_in, in, function_id, function_id); - MLX5_SET(query_vhca_state_in, in, embedded_cpu_function, ecpu); + MLX5_SET(query_vhca_state_in, in, embedded_cpu_function, 0); return mlx5_cmd_exec(dev, in, sizeof(in), out, outlen); } static int mlx5_cmd_modify_vhca_state(struct mlx5_core_dev *dev, u16 function_id, - bool ecpu, u32 *in, u32 inlen) + u32 *in, u32 inlen) { u32 out[MLX5_ST_SZ_DW(modify_vhca_state_out)] = {}; MLX5_SET(modify_vhca_state_in, in, opcode, MLX5_CMD_OP_MODIFY_VHCA_STATE); MLX5_SET(modify_vhca_state_in, in, function_id, function_id); - MLX5_SET(modify_vhca_state_in, in, embedded_cpu_function, ecpu); + MLX5_SET(modify_vhca_state_in, in, embedded_cpu_function, 0); return mlx5_cmd_exec(dev, in, inlen, out, sizeof(out)); } -int mlx5_modify_vhca_sw_id(struct mlx5_core_dev *dev, u16 function_id, bool ecpu, u32 sw_fn_id) +int mlx5_modify_vhca_sw_id(struct mlx5_core_dev *dev, u16 function_id, u32 sw_fn_id) { u32 out[MLX5_ST_SZ_DW(modify_vhca_state_out)] = {}; u32 in[MLX5_ST_SZ_DW(modify_vhca_state_in)] = {}; MLX5_SET(modify_vhca_state_in, in, opcode, MLX5_CMD_OP_MODIFY_VHCA_STATE); MLX5_SET(modify_vhca_state_in, in, function_id, function_id); - MLX5_SET(modify_vhca_state_in, in, embedded_cpu_function, ecpu); + MLX5_SET(modify_vhca_state_in, in, embedded_cpu_function, 0); MLX5_SET(modify_vhca_state_in, in, vhca_state_field_select.sw_function_id, 1); MLX5_SET(modify_vhca_state_in, in, vhca_state_context.sw_function_id, sw_fn_id); return mlx5_cmd_exec_inout(dev, modify_vhca_state, in, out); } -int mlx5_vhca_event_arm(struct mlx5_core_dev *dev, u16 function_id, bool ecpu) +int mlx5_vhca_event_arm(struct mlx5_core_dev *dev, u16 function_id) { u32 in[MLX5_ST_SZ_DW(modify_vhca_state_in)] = {}; MLX5_SET(modify_vhca_state_in, in, vhca_state_context.arm_change_event, 1); MLX5_SET(modify_vhca_state_in, in, vhca_state_field_select.arm_change_event, 1); - return mlx5_cmd_modify_vhca_state(dev, function_id, ecpu, in, sizeof(in)); + return mlx5_cmd_modify_vhca_state(dev, function_id, in, sizeof(in)); } static void @@ -73,7 +72,7 @@ mlx5_vhca_event_notify(struct mlx5_core_dev *dev, struct mlx5_vhca_state_event * u32 out[MLX5_ST_SZ_DW(query_vhca_state_out)] = {}; int err; - err = mlx5_cmd_query_vhca_state(dev, event->function_id, event->ecpu, out, sizeof(out)); + err = mlx5_cmd_query_vhca_state(dev, event->function_id, out, sizeof(out)); if (err) return; @@ -82,7 +81,7 @@ mlx5_vhca_event_notify(struct mlx5_core_dev *dev, struct mlx5_vhca_state_event * event->new_vhca_state = MLX5_GET(query_vhca_state_out, out, vhca_state_context.vhca_state); - mlx5_vhca_event_arm(dev, event->function_id, event->ecpu); + mlx5_vhca_event_arm(dev, event->function_id); blocking_notifier_call_chain(&dev->priv.vhca_state_notifier->n_head, 0, event); } @@ -94,6 +93,7 @@ static void mlx5_vhca_state_work_handler(struct work_struct *_work) struct mlx5_core_dev *dev = notifier->dev; mlx5_vhca_event_notify(dev, &work->event); + kfree(work); } static int @@ -110,7 +110,6 @@ mlx5_vhca_state_change_notifier(struct notifier_block *nb, unsigned long type, v INIT_WORK(&work->work, &mlx5_vhca_state_work_handler); work->notifier = notifier; work->event.function_id = be16_to_cpu(eqe->data.vhca_state.function_id); - work->event.ecpu = be16_to_cpu(eqe->data.vhca_state.ec_function); mlx5_events_work_enqueue(notifier->dev, &work->work); return NOTIFY_OK; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/vhca_event.h b/drivers/net/ethernet/mellanox/mlx5/core/sf/vhca_event.h index 1fe1ec6f4d4b..013cdfe90616 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sf/vhca_event.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/vhca_event.h @@ -10,7 +10,6 @@ struct mlx5_vhca_state_event { u16 function_id; u16 sw_function_id; u8 new_vhca_state; - bool ecpu; }; static inline bool mlx5_vhca_event_supported(const struct mlx5_core_dev *dev) @@ -25,10 +24,10 @@ void mlx5_vhca_event_start(struct mlx5_core_dev *dev); void mlx5_vhca_event_stop(struct mlx5_core_dev *dev); int mlx5_vhca_event_notifier_register(struct mlx5_core_dev *dev, struct notifier_block *nb); void mlx5_vhca_event_notifier_unregister(struct mlx5_core_dev *dev, struct notifier_block *nb); -int mlx5_modify_vhca_sw_id(struct mlx5_core_dev *dev, u16 function_id, bool ecpu, u32 sw_fn_id); -int mlx5_vhca_event_arm(struct mlx5_core_dev *dev, u16 function_id, bool ecpu); +int mlx5_modify_vhca_sw_id(struct mlx5_core_dev *dev, u16 function_id, u32 sw_fn_id); +int mlx5_vhca_event_arm(struct mlx5_core_dev *dev, u16 function_id); int mlx5_cmd_query_vhca_state(struct mlx5_core_dev *dev, u16 function_id, - bool ecpu, u32 *out, u32 outlen); + u32 *out, u32 outlen); #else static inline void mlx5_vhca_state_cap_handle(struct mlx5_core_dev *dev, void *set_hca_cap) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c index 83c4c877d558..8a6a56f9dc4e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c @@ -169,6 +169,7 @@ static struct mlx5dr_qp *dr_create_rc_qp(struct mlx5_core_dev *mdev, MLX5_SET(qpc, qpc, log_rq_size, ilog2(dr_qp->rq.wqe_cnt)); MLX5_SET(qpc, qpc, rq_type, MLX5_NON_ZERO_RQ); MLX5_SET(qpc, qpc, log_sq_size, ilog2(dr_qp->sq.wqe_cnt)); + MLX5_SET(qpc, qpc, ts_format, mlx5_get_qp_default_ts(mdev)); MLX5_SET64(qpc, qpc, dbr_addr, dr_qp->wq_ctrl.db.dma); if (MLX5_CAP_GEN(mdev, cqe_version) == 1) MLX5_SET(qpc, qpc, user_index, 0xFFFFFF); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.c index 4088d6e51508..9143ec326ebf 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.c @@ -264,8 +264,8 @@ static void dr_ste_v1_set_miss_addr(u8 *hw_ste_p, u64 miss_addr) static u64 dr_ste_v1_get_miss_addr(u8 *hw_ste_p) { u64 index = - (MLX5_GET(ste_match_bwc_v1, hw_ste_p, miss_address_31_6) | - MLX5_GET(ste_match_bwc_v1, hw_ste_p, miss_address_39_32) << 26); + ((u64)MLX5_GET(ste_match_bwc_v1, hw_ste_p, miss_address_31_6) | + ((u64)MLX5_GET(ste_match_bwc_v1, hw_ste_p, miss_address_39_32)) << 26); return index << 6; } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h index d9d9e1f488f9..ba28ac7e79bc 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h @@ -21,6 +21,7 @@ #include <net/red.h> #include <net/vxlan.h> #include <net/flow_offload.h> +#include <net/inet_ecn.h> #include "port.h" #include "core.h" @@ -347,6 +348,20 @@ struct mlxsw_sp_port_type_speed_ops { u32 (*ptys_proto_cap_masked_get)(u32 eth_proto_cap); }; +static inline u8 mlxsw_sp_tunnel_ecn_decap(u8 outer_ecn, u8 inner_ecn, + bool *trap_en) +{ + bool set_ce = false; + + *trap_en = !!__INET_ECN_decapsulate(outer_ecn, inner_ecn, &set_ce); + if (set_ce) + return INET_ECN_CE; + else if (outer_ecn == INET_ECN_ECT_1 && inner_ecn == INET_ECN_ECT_0) + return INET_ECN_ECT_1; + else + return inner_ecn; +} + static inline struct net_device * mlxsw_sp_bridge_vxlan_dev_find(struct net_device *br_dev) { diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ethtool.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ethtool.c index 0bd64169bf81..078601d31cde 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ethtool.c @@ -1230,16 +1230,22 @@ mlxsw_sp1_from_ptys_link_mode(struct mlxsw_sp *mlxsw_sp, bool carrier_ok, u32 ptys_eth_proto, struct ethtool_link_ksettings *cmd) { + struct mlxsw_sp1_port_link_mode link; int i; - cmd->link_mode = -1; + cmd->base.speed = SPEED_UNKNOWN; + cmd->base.duplex = DUPLEX_UNKNOWN; + cmd->lanes = 0; if (!carrier_ok) return; for (i = 0; i < MLXSW_SP1_PORT_LINK_MODE_LEN; i++) { - if (ptys_eth_proto & mlxsw_sp1_port_link_mode[i].mask) - cmd->link_mode = mlxsw_sp1_port_link_mode[i].mask_ethtool; + if (ptys_eth_proto & mlxsw_sp1_port_link_mode[i].mask) { + link = mlxsw_sp1_port_link_mode[i]; + ethtool_params_from_link_mode(cmd, + link.mask_ethtool); + } } } @@ -1672,7 +1678,9 @@ mlxsw_sp2_from_ptys_link_mode(struct mlxsw_sp *mlxsw_sp, bool carrier_ok, struct mlxsw_sp2_port_link_mode link; int i; - cmd->link_mode = -1; + cmd->base.speed = SPEED_UNKNOWN; + cmd->base.duplex = DUPLEX_UNKNOWN; + cmd->lanes = 0; if (!carrier_ok) return; @@ -1680,7 +1688,8 @@ mlxsw_sp2_from_ptys_link_mode(struct mlxsw_sp *mlxsw_sp, bool carrier_ok, for (i = 0; i < MLXSW_SP2_PORT_LINK_MODE_LEN; i++) { if (ptys_eth_proto & mlxsw_sp2_port_link_mode[i].mask) { link = mlxsw_sp2_port_link_mode[i]; - cmd->link_mode = link.mask_ethtool[1]; + ethtool_params_from_link_mode(cmd, + link.mask_ethtool[1]); } } } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c index 6ccca39bae84..64a8f838eb53 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c @@ -335,12 +335,11 @@ static int mlxsw_sp_ipip_ecn_decap_init_one(struct mlxsw_sp *mlxsw_sp, u8 inner_ecn, u8 outer_ecn) { char tidem_pl[MLXSW_REG_TIDEM_LEN]; - bool trap_en, set_ce = false; u8 new_inner_ecn; + bool trap_en; - trap_en = __INET_ECN_decapsulate(outer_ecn, inner_ecn, &set_ce); - new_inner_ecn = set_ce ? INET_ECN_CE : inner_ecn; - + new_inner_ecn = mlxsw_sp_tunnel_ecn_decap(outer_ecn, inner_ecn, + &trap_en); mlxsw_reg_tidem_pack(tidem_pl, outer_ecn, inner_ecn, new_inner_ecn, trap_en, trap_en ? MLXSW_TRAP_ID_DECAP_ECN0 : 0); return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(tidem), tidem_pl); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.c index e5ec595593f4..9eba8fa684ae 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.c @@ -909,12 +909,11 @@ static int __mlxsw_sp_nve_ecn_decap_init(struct mlxsw_sp *mlxsw_sp, u8 inner_ecn, u8 outer_ecn) { char tndem_pl[MLXSW_REG_TNDEM_LEN]; - bool trap_en, set_ce = false; u8 new_inner_ecn; + bool trap_en; - trap_en = !!__INET_ECN_decapsulate(outer_ecn, inner_ecn, &set_ce); - new_inner_ecn = set_ce ? INET_ECN_CE : inner_ecn; - + new_inner_ecn = mlxsw_sp_tunnel_ecn_decap(outer_ecn, inner_ecn, + &trap_en); mlxsw_reg_tndem_pack(tndem_pl, outer_ecn, inner_ecn, new_inner_ecn, trap_en, trap_en ? MLXSW_TRAP_ID_DECAP_ECN0 : 0); return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(tndem), tndem_pl); diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c index 1c3e204d727c..7b6794aa8ea9 100644 --- a/drivers/net/ethernet/microchip/lan743x_main.c +++ b/drivers/net/ethernet/microchip/lan743x_main.c @@ -885,8 +885,8 @@ static int lan743x_mac_set_mtu(struct lan743x_adapter *adapter, int new_mtu) } mac_rx &= ~(MAC_RX_MAX_SIZE_MASK_); - mac_rx |= (((new_mtu + ETH_HLEN + 4) << MAC_RX_MAX_SIZE_SHIFT_) & - MAC_RX_MAX_SIZE_MASK_); + mac_rx |= (((new_mtu + ETH_HLEN + ETH_FCS_LEN) + << MAC_RX_MAX_SIZE_SHIFT_) & MAC_RX_MAX_SIZE_MASK_); lan743x_csr_write(adapter, MAC_RX, mac_rx); if (enabled) { @@ -1944,7 +1944,7 @@ static int lan743x_rx_init_ring_element(struct lan743x_rx *rx, int index) struct sk_buff *skb; dma_addr_t dma_ptr; - buffer_length = netdev->mtu + ETH_HLEN + 4 + RX_HEAD_PADDING; + buffer_length = netdev->mtu + ETH_HLEN + ETH_FCS_LEN + RX_HEAD_PADDING; descriptor = &rx->ring_cpu_ptr[index]; buffer_info = &rx->buffer_info[index]; @@ -2040,7 +2040,7 @@ lan743x_rx_trim_skb(struct sk_buff *skb, int frame_length) dev_kfree_skb_irq(skb); return NULL; } - frame_length = max_t(int, 0, frame_length - RX_HEAD_PADDING - 4); + frame_length = max_t(int, 0, frame_length - ETH_FCS_LEN); if (skb->len > frame_length) { skb->tail -= skb->len - frame_length; skb->len = frame_length; diff --git a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c index 1634ca6d4a8f..c84c8bf2bc20 100644 --- a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c +++ b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c @@ -2897,7 +2897,7 @@ static netdev_tx_t myri10ge_sw_tso(struct sk_buff *skb, dev_kfree_skb_any(curr); if (segs != NULL) { curr = segs; - segs = segs->next; + segs = next; curr->next = NULL; dev_kfree_skb_any(segs); } diff --git a/drivers/net/ethernet/netronome/nfp/bpf/cmsg.c b/drivers/net/ethernet/netronome/nfp/bpf/cmsg.c index 0e2db6ea79e9..2ec62c8d86e1 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/cmsg.c +++ b/drivers/net/ethernet/netronome/nfp/bpf/cmsg.c @@ -454,6 +454,7 @@ void nfp_bpf_ctrl_msg_rx(struct nfp_app *app, struct sk_buff *skb) dev_consume_skb_any(skb); else dev_kfree_skb_any(skb); + return; } nfp_ccm_rx(&bpf->ccm, skb); diff --git a/drivers/net/ethernet/netronome/nfp/flower/main.h b/drivers/net/ethernet/netronome/nfp/flower/main.h index caf12eec9945..56833a41f3d2 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/main.h +++ b/drivers/net/ethernet/netronome/nfp/flower/main.h @@ -190,6 +190,7 @@ struct nfp_fl_internal_ports { * @qos_rate_limiters: Current active qos rate limiters * @qos_stats_lock: Lock on qos stats updates * @pre_tun_rule_cnt: Number of pre-tunnel rules offloaded + * @merge_table: Hash table to store merged flows */ struct nfp_flower_priv { struct nfp_app *app; @@ -223,6 +224,7 @@ struct nfp_flower_priv { unsigned int qos_rate_limiters; spinlock_t qos_stats_lock; /* Protect the qos stats */ int pre_tun_rule_cnt; + struct rhashtable merge_table; }; /** @@ -350,6 +352,12 @@ struct nfp_fl_payload_link { }; extern const struct rhashtable_params nfp_flower_table_params; +extern const struct rhashtable_params merge_table_params; + +struct nfp_merge_info { + u64 parent_ctx; + struct rhash_head ht_node; +}; struct nfp_fl_stats_frame { __be32 stats_con_id; diff --git a/drivers/net/ethernet/netronome/nfp/flower/metadata.c b/drivers/net/ethernet/netronome/nfp/flower/metadata.c index 5defd31d481c..327bb56b3ef5 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/metadata.c +++ b/drivers/net/ethernet/netronome/nfp/flower/metadata.c @@ -327,8 +327,14 @@ int nfp_compile_flow_metadata(struct nfp_app *app, goto err_free_ctx_entry; } + /* Do net allocate a mask-id for pre_tun_rules. These flows are used to + * configure the pre_tun table and are never actually send to the + * firmware as an add-flow message. This causes the mask-id allocation + * on the firmware to get out of sync if allocated here. + */ new_mask_id = 0; - if (!nfp_check_mask_add(app, nfp_flow->mask_data, + if (!nfp_flow->pre_tun_rule.dev && + !nfp_check_mask_add(app, nfp_flow->mask_data, nfp_flow->meta.mask_len, &nfp_flow->meta.flags, &new_mask_id)) { NL_SET_ERR_MSG_MOD(extack, "invalid entry: cannot allocate a new mask id"); @@ -359,7 +365,8 @@ int nfp_compile_flow_metadata(struct nfp_app *app, goto err_remove_mask; } - if (!nfp_check_mask_remove(app, nfp_flow->mask_data, + if (!nfp_flow->pre_tun_rule.dev && + !nfp_check_mask_remove(app, nfp_flow->mask_data, nfp_flow->meta.mask_len, NULL, &new_mask_id)) { NL_SET_ERR_MSG_MOD(extack, "invalid entry: cannot release mask id"); @@ -374,8 +381,10 @@ int nfp_compile_flow_metadata(struct nfp_app *app, return 0; err_remove_mask: - nfp_check_mask_remove(app, nfp_flow->mask_data, nfp_flow->meta.mask_len, - NULL, &new_mask_id); + if (!nfp_flow->pre_tun_rule.dev) + nfp_check_mask_remove(app, nfp_flow->mask_data, + nfp_flow->meta.mask_len, + NULL, &new_mask_id); err_remove_rhash: WARN_ON_ONCE(rhashtable_remove_fast(&priv->stats_ctx_table, &ctx_entry->ht_node, @@ -406,9 +415,10 @@ int nfp_modify_flow_metadata(struct nfp_app *app, __nfp_modify_flow_metadata(priv, nfp_flow); - nfp_check_mask_remove(app, nfp_flow->mask_data, - nfp_flow->meta.mask_len, &nfp_flow->meta.flags, - &new_mask_id); + if (!nfp_flow->pre_tun_rule.dev) + nfp_check_mask_remove(app, nfp_flow->mask_data, + nfp_flow->meta.mask_len, &nfp_flow->meta.flags, + &new_mask_id); /* Update flow payload with mask ids. */ nfp_flow->unmasked_data[NFP_FL_MASK_ID_LOCATION] = new_mask_id; @@ -480,6 +490,12 @@ const struct rhashtable_params nfp_flower_table_params = { .automatic_shrinking = true, }; +const struct rhashtable_params merge_table_params = { + .key_offset = offsetof(struct nfp_merge_info, parent_ctx), + .head_offset = offsetof(struct nfp_merge_info, ht_node), + .key_len = sizeof(u64), +}; + int nfp_flower_metadata_init(struct nfp_app *app, u64 host_ctx_count, unsigned int host_num_mems) { @@ -496,6 +512,10 @@ int nfp_flower_metadata_init(struct nfp_app *app, u64 host_ctx_count, if (err) goto err_free_flow_table; + err = rhashtable_init(&priv->merge_table, &merge_table_params); + if (err) + goto err_free_stats_ctx_table; + get_random_bytes(&priv->mask_id_seed, sizeof(priv->mask_id_seed)); /* Init ring buffer and unallocated mask_ids. */ @@ -503,7 +523,7 @@ int nfp_flower_metadata_init(struct nfp_app *app, u64 host_ctx_count, kmalloc_array(NFP_FLOWER_MASK_ENTRY_RS, NFP_FLOWER_MASK_ELEMENT_RS, GFP_KERNEL); if (!priv->mask_ids.mask_id_free_list.buf) - goto err_free_stats_ctx_table; + goto err_free_merge_table; priv->mask_ids.init_unallocated = NFP_FLOWER_MASK_ENTRY_RS - 1; @@ -540,6 +560,8 @@ err_free_last_used: kfree(priv->mask_ids.last_used); err_free_mask_id: kfree(priv->mask_ids.mask_id_free_list.buf); +err_free_merge_table: + rhashtable_destroy(&priv->merge_table); err_free_stats_ctx_table: rhashtable_destroy(&priv->stats_ctx_table); err_free_flow_table: @@ -558,6 +580,8 @@ void nfp_flower_metadata_cleanup(struct nfp_app *app) nfp_check_rhashtable_empty, NULL); rhashtable_free_and_destroy(&priv->stats_ctx_table, nfp_check_rhashtable_empty, NULL); + rhashtable_free_and_destroy(&priv->merge_table, + nfp_check_rhashtable_empty, NULL); kvfree(priv->stats); kfree(priv->mask_ids.mask_id_free_list.buf); kfree(priv->mask_ids.last_used); diff --git a/drivers/net/ethernet/netronome/nfp/flower/offload.c b/drivers/net/ethernet/netronome/nfp/flower/offload.c index 1c59aff2163c..e95969c462e4 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/offload.c +++ b/drivers/net/ethernet/netronome/nfp/flower/offload.c @@ -1009,6 +1009,8 @@ int nfp_flower_merge_offloaded_flows(struct nfp_app *app, struct netlink_ext_ack *extack = NULL; struct nfp_fl_payload *merge_flow; struct nfp_fl_key_ls merge_key_ls; + struct nfp_merge_info *merge_info; + u64 parent_ctx = 0; int err; ASSERT_RTNL(); @@ -1019,6 +1021,15 @@ int nfp_flower_merge_offloaded_flows(struct nfp_app *app, nfp_flower_is_merge_flow(sub_flow2)) return -EINVAL; + /* check if the two flows are already merged */ + parent_ctx = (u64)(be32_to_cpu(sub_flow1->meta.host_ctx_id)) << 32; + parent_ctx |= (u64)(be32_to_cpu(sub_flow2->meta.host_ctx_id)); + if (rhashtable_lookup_fast(&priv->merge_table, + &parent_ctx, merge_table_params)) { + nfp_flower_cmsg_warn(app, "The two flows are already merged.\n"); + return 0; + } + err = nfp_flower_can_merge(sub_flow1, sub_flow2); if (err) return err; @@ -1060,16 +1071,33 @@ int nfp_flower_merge_offloaded_flows(struct nfp_app *app, if (err) goto err_release_metadata; + merge_info = kmalloc(sizeof(*merge_info), GFP_KERNEL); + if (!merge_info) { + err = -ENOMEM; + goto err_remove_rhash; + } + merge_info->parent_ctx = parent_ctx; + err = rhashtable_insert_fast(&priv->merge_table, &merge_info->ht_node, + merge_table_params); + if (err) + goto err_destroy_merge_info; + err = nfp_flower_xmit_flow(app, merge_flow, NFP_FLOWER_CMSG_TYPE_FLOW_MOD); if (err) - goto err_remove_rhash; + goto err_remove_merge_info; merge_flow->in_hw = true; sub_flow1->in_hw = false; return 0; +err_remove_merge_info: + WARN_ON_ONCE(rhashtable_remove_fast(&priv->merge_table, + &merge_info->ht_node, + merge_table_params)); +err_destroy_merge_info: + kfree(merge_info); err_remove_rhash: WARN_ON_ONCE(rhashtable_remove_fast(&priv->flow_table, &merge_flow->fl_node, @@ -1142,6 +1170,12 @@ nfp_flower_validate_pre_tun_rule(struct nfp_app *app, return -EOPNOTSUPP; } + if (!(key_layer & NFP_FLOWER_LAYER_IPV4) && + !(key_layer & NFP_FLOWER_LAYER_IPV6)) { + NL_SET_ERR_MSG_MOD(extack, "unsupported pre-tunnel rule: match on ipv4/ipv6 eth_type must be present"); + return -EOPNOTSUPP; + } + /* Skip fields known to exist. */ mask += sizeof(struct nfp_flower_meta_tci); ext += sizeof(struct nfp_flower_meta_tci); @@ -1152,6 +1186,13 @@ nfp_flower_validate_pre_tun_rule(struct nfp_app *app, mask += sizeof(struct nfp_flower_in_port); ext += sizeof(struct nfp_flower_in_port); + /* Ensure destination MAC address matches pre_tun_dev. */ + mac = (struct nfp_flower_mac_mpls *)ext; + if (memcmp(&mac->mac_dst[0], flow->pre_tun_rule.dev->dev_addr, 6)) { + NL_SET_ERR_MSG_MOD(extack, "unsupported pre-tunnel rule: dest MAC must match output dev MAC"); + return -EOPNOTSUPP; + } + /* Ensure destination MAC address is fully matched. */ mac = (struct nfp_flower_mac_mpls *)mask; if (!is_broadcast_ether_addr(&mac->mac_dst[0])) { @@ -1159,6 +1200,11 @@ nfp_flower_validate_pre_tun_rule(struct nfp_app *app, return -EOPNOTSUPP; } + if (mac->mpls_lse) { + NL_SET_ERR_MSG_MOD(extack, "unsupported pre-tunnel rule: MPLS not supported"); + return -EOPNOTSUPP; + } + mask += sizeof(struct nfp_flower_mac_mpls); ext += sizeof(struct nfp_flower_mac_mpls); if (key_layer & NFP_FLOWER_LAYER_IPV4 || @@ -1341,7 +1387,9 @@ nfp_flower_remove_merge_flow(struct nfp_app *app, { struct nfp_flower_priv *priv = app->priv; struct nfp_fl_payload_link *link, *temp; + struct nfp_merge_info *merge_info; struct nfp_fl_payload *origin; + u64 parent_ctx = 0; bool mod = false; int err; @@ -1378,8 +1426,22 @@ nfp_flower_remove_merge_flow(struct nfp_app *app, err_free_links: /* Clean any links connected with the merged flow. */ list_for_each_entry_safe(link, temp, &merge_flow->linked_flows, - merge_flow.list) + merge_flow.list) { + u32 ctx_id = be32_to_cpu(link->sub_flow.flow->meta.host_ctx_id); + + parent_ctx = (parent_ctx << 32) | (u64)(ctx_id); nfp_flower_unlink_flow(link); + } + + merge_info = rhashtable_lookup_fast(&priv->merge_table, + &parent_ctx, + merge_table_params); + if (merge_info) { + WARN_ON_ONCE(rhashtable_remove_fast(&priv->merge_table, + &merge_info->ht_node, + merge_table_params)); + kfree(merge_info); + } kfree(merge_flow->action_data); kfree(merge_flow->mask_data); diff --git a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c index 7248d248f604..d19c02e99114 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c +++ b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c @@ -16,8 +16,9 @@ #define NFP_FL_MAX_ROUTES 32 #define NFP_TUN_PRE_TUN_RULE_LIMIT 32 -#define NFP_TUN_PRE_TUN_RULE_DEL 0x1 -#define NFP_TUN_PRE_TUN_IDX_BIT 0x8 +#define NFP_TUN_PRE_TUN_RULE_DEL BIT(0) +#define NFP_TUN_PRE_TUN_IDX_BIT BIT(3) +#define NFP_TUN_PRE_TUN_IPV6_BIT BIT(7) /** * struct nfp_tun_pre_run_rule - rule matched before decap @@ -1268,6 +1269,7 @@ int nfp_flower_xmit_pre_tun_flow(struct nfp_app *app, { struct nfp_flower_priv *app_priv = app->priv; struct nfp_tun_offloaded_mac *mac_entry; + struct nfp_flower_meta_tci *key_meta; struct nfp_tun_pre_tun_rule payload; struct net_device *internal_dev; int err; @@ -1290,6 +1292,15 @@ int nfp_flower_xmit_pre_tun_flow(struct nfp_app *app, if (!mac_entry) return -ENOENT; + /* Set/clear IPV6 bit. cpu_to_be16() swap will lead to MSB being + * set/clear for port_idx. + */ + key_meta = (struct nfp_flower_meta_tci *)flow->unmasked_data; + if (key_meta->nfp_flow_key_layer & NFP_FLOWER_LAYER_IPV6) + mac_entry->index |= NFP_TUN_PRE_TUN_IPV6_BIT; + else + mac_entry->index &= ~NFP_TUN_PRE_TUN_IPV6_BIT; + payload.port_idx = cpu_to_be16(mac_entry->index); /* Copy mac id and vlan to flow - dev may not exist at delete time. */ diff --git a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c index 162a1ff1e9d2..4087311f7082 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c @@ -1079,15 +1079,17 @@ static int ionic_tx_descs_needed(struct ionic_queue *q, struct sk_buff *skb) { int sg_elems = q->lif->qtype_info[IONIC_QTYPE_TXQ].max_sg_elems; struct ionic_tx_stats *stats = q_to_tx_stats(q); + int ndescs; int err; - /* If TSO, need roundup(skb->len/mss) descs */ + /* Each desc is mss long max, so a descriptor for each gso_seg */ if (skb_is_gso(skb)) - return (skb->len / skb_shinfo(skb)->gso_size) + 1; + ndescs = skb_shinfo(skb)->gso_segs; + else + ndescs = 1; - /* If non-TSO, just need 1 desc and nr_frags sg elems */ if (skb_shinfo(skb)->nr_frags <= sg_elems) - return 1; + return ndescs; /* Too many frags, so linearize */ err = skb_linearize(skb); @@ -1096,8 +1098,7 @@ static int ionic_tx_descs_needed(struct ionic_queue *q, struct sk_buff *skb) stats->linearize++; - /* Need 1 desc and zero sg elems */ - return 1; + return ndescs; } static int ionic_maybe_stop_tx(struct ionic_queue *q, int ndescs) diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_minidump.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_minidump.c index 7760a3394e93..7ecb3dfe30bd 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_minidump.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_minidump.c @@ -1425,6 +1425,7 @@ void qlcnic_83xx_get_minidump_template(struct qlcnic_adapter *adapter) if (fw_dump->tmpl_hdr == NULL || current_version > prev_version) { vfree(fw_dump->tmpl_hdr); + fw_dump->tmpl_hdr = NULL; if (qlcnic_83xx_md_check_extended_dump_capability(adapter)) extended = !qlcnic_83xx_extend_md_capab(adapter); @@ -1443,6 +1444,8 @@ void qlcnic_83xx_get_minidump_template(struct qlcnic_adapter *adapter) struct qlcnic_83xx_dump_template_hdr *hdr; hdr = fw_dump->tmpl_hdr; + if (!hdr) + return; hdr->drv_cap_mask = 0x1f; fw_dump->cap_mask = 0x1f; dev_info(&pdev->dev, diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index 7aad0ba53372..581a92fc3292 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -4646,6 +4646,9 @@ static void rtl8169_down(struct rtl8169_private *tp) rtl8169_update_counters(tp); + pci_clear_master(tp->pci_dev); + rtl_pci_commit(tp); + rtl8169_cleanup(tp, true); rtl_prepare_power_down(tp); @@ -4653,6 +4656,7 @@ static void rtl8169_down(struct rtl8169_private *tp) static void rtl8169_up(struct rtl8169_private *tp) { + pci_set_master(tp->pci_dev); phy_resume(tp->phydev); rtl8169_init_phy(tp); napi_enable(&tp->napi); @@ -5307,8 +5311,6 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) rtl_hw_reset(tp); - pci_set_master(pdev); - rc = rtl_alloc_irq(tp); if (rc < 0) { dev_err(&pdev->dev, "Can't allocate interrupt\n"); diff --git a/drivers/net/ethernet/socionext/netsec.c b/drivers/net/ethernet/socionext/netsec.c index 3c53051bdacf..200785e703c8 100644 --- a/drivers/net/ethernet/socionext/netsec.c +++ b/drivers/net/ethernet/socionext/netsec.c @@ -1715,14 +1715,17 @@ static int netsec_netdev_init(struct net_device *ndev) goto err1; /* set phy power down */ - data = netsec_phy_read(priv->mii_bus, priv->phy_addr, MII_BMCR) | - BMCR_PDOWN; - netsec_phy_write(priv->mii_bus, priv->phy_addr, MII_BMCR, data); + data = netsec_phy_read(priv->mii_bus, priv->phy_addr, MII_BMCR); + netsec_phy_write(priv->mii_bus, priv->phy_addr, MII_BMCR, + data | BMCR_PDOWN); ret = netsec_reset_hardware(priv, true); if (ret) goto err2; + /* Restore phy power state */ + netsec_phy_write(priv->mii_bus, priv->phy_addr, MII_BMCR, data); + spin_lock_init(&priv->desc_ring[NETSEC_RING_TX].lock); spin_lock_init(&priv->desc_ring[NETSEC_RING_RX].lock); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c index 6b75cf2603ff..e62efd166ec8 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c @@ -1214,6 +1214,8 @@ static int sun8i_dwmac_probe(struct platform_device *pdev) plat_dat->init = sun8i_dwmac_init; plat_dat->exit = sun8i_dwmac_exit; plat_dat->setup = sun8i_dwmac_setup; + plat_dat->tx_fifo_size = 4096; + plat_dat->rx_fifo_size = 16384; ret = sun8i_dwmac_set_syscon(&pdev->dev, plat_dat); if (ret) diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet.h b/drivers/net/ethernet/xilinx/xilinx_axienet.h index 1e966a39967e..aca7f82f6791 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet.h +++ b/drivers/net/ethernet/xilinx/xilinx_axienet.h @@ -504,6 +504,18 @@ static inline u32 axinet_ior_read_mcr(struct axienet_local *lp) return axienet_ior(lp, XAE_MDIO_MCR_OFFSET); } +static inline void axienet_lock_mii(struct axienet_local *lp) +{ + if (lp->mii_bus) + mutex_lock(&lp->mii_bus->mdio_lock); +} + +static inline void axienet_unlock_mii(struct axienet_local *lp) +{ + if (lp->mii_bus) + mutex_unlock(&lp->mii_bus->mdio_lock); +} + /** * axienet_iow - Memory mapped Axi Ethernet register write * @lp: Pointer to axienet local structure diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c index 3a8775e0ca55..f8f8654ea728 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c +++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c @@ -1053,9 +1053,9 @@ static int axienet_open(struct net_device *ndev) * including the MDIO. MDIO must be disabled before resetting. * Hold MDIO bus lock to avoid MDIO accesses during the reset. */ - mutex_lock(&lp->mii_bus->mdio_lock); + axienet_lock_mii(lp); ret = axienet_device_reset(ndev); - mutex_unlock(&lp->mii_bus->mdio_lock); + axienet_unlock_mii(lp); ret = phylink_of_phy_connect(lp->phylink, lp->dev->of_node, 0); if (ret) { @@ -1148,9 +1148,9 @@ static int axienet_stop(struct net_device *ndev) } /* Do a reset to ensure DMA is really stopped */ - mutex_lock(&lp->mii_bus->mdio_lock); + axienet_lock_mii(lp); __axienet_device_reset(lp); - mutex_unlock(&lp->mii_bus->mdio_lock); + axienet_unlock_mii(lp); cancel_work_sync(&lp->dma_err_task); @@ -1709,9 +1709,9 @@ static void axienet_dma_err_handler(struct work_struct *work) * including the MDIO. MDIO must be disabled before resetting. * Hold MDIO bus lock to avoid MDIO accesses during the reset. */ - mutex_lock(&lp->mii_bus->mdio_lock); + axienet_lock_mii(lp); __axienet_device_reset(lp); - mutex_unlock(&lp->mii_bus->mdio_lock); + axienet_unlock_mii(lp); for (i = 0; i < lp->tx_bd_num; i++) { cur_p = &lp->tx_bd_v[i]; @@ -1880,7 +1880,7 @@ static int axienet_probe(struct platform_device *pdev) if (IS_ERR(lp->regs)) { dev_err(&pdev->dev, "could not map Axi Ethernet regs.\n"); ret = PTR_ERR(lp->regs); - goto free_netdev; + goto cleanup_clk; } lp->regs_start = ethres->start; @@ -1958,18 +1958,18 @@ static int axienet_probe(struct platform_device *pdev) break; default: ret = -EINVAL; - goto free_netdev; + goto cleanup_clk; } } else { ret = of_get_phy_mode(pdev->dev.of_node, &lp->phy_mode); if (ret) - goto free_netdev; + goto cleanup_clk; } if (lp->switch_x_sgmii && lp->phy_mode != PHY_INTERFACE_MODE_SGMII && lp->phy_mode != PHY_INTERFACE_MODE_1000BASEX) { dev_err(&pdev->dev, "xlnx,switch-x-sgmii only supported with SGMII or 1000BaseX\n"); ret = -EINVAL; - goto free_netdev; + goto cleanup_clk; } /* Find the DMA node, map the DMA registers, and decode the DMA IRQs */ @@ -1982,7 +1982,7 @@ static int axienet_probe(struct platform_device *pdev) dev_err(&pdev->dev, "unable to get DMA resource\n"); of_node_put(np); - goto free_netdev; + goto cleanup_clk; } lp->dma_regs = devm_ioremap_resource(&pdev->dev, &dmares); @@ -2002,12 +2002,12 @@ static int axienet_probe(struct platform_device *pdev) if (IS_ERR(lp->dma_regs)) { dev_err(&pdev->dev, "could not map DMA regs\n"); ret = PTR_ERR(lp->dma_regs); - goto free_netdev; + goto cleanup_clk; } if ((lp->rx_irq <= 0) || (lp->tx_irq <= 0)) { dev_err(&pdev->dev, "could not determine irqs\n"); ret = -ENOMEM; - goto free_netdev; + goto cleanup_clk; } /* Autodetect the need for 64-bit DMA pointers. @@ -2037,7 +2037,7 @@ static int axienet_probe(struct platform_device *pdev) ret = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(addr_width)); if (ret) { dev_err(&pdev->dev, "No suitable DMA available\n"); - goto free_netdev; + goto cleanup_clk; } /* Check for Ethernet core IRQ (optional) */ @@ -2068,12 +2068,12 @@ static int axienet_probe(struct platform_device *pdev) if (!lp->phy_node) { dev_err(&pdev->dev, "phy-handle required for 1000BaseX/SGMII\n"); ret = -EINVAL; - goto free_netdev; + goto cleanup_mdio; } lp->pcs_phy = of_mdio_find_device(lp->phy_node); if (!lp->pcs_phy) { ret = -EPROBE_DEFER; - goto free_netdev; + goto cleanup_mdio; } lp->phylink_config.pcs_poll = true; } @@ -2087,17 +2087,30 @@ static int axienet_probe(struct platform_device *pdev) if (IS_ERR(lp->phylink)) { ret = PTR_ERR(lp->phylink); dev_err(&pdev->dev, "phylink_create error (%i)\n", ret); - goto free_netdev; + goto cleanup_mdio; } ret = register_netdev(lp->ndev); if (ret) { dev_err(lp->dev, "register_netdev() error (%i)\n", ret); - goto free_netdev; + goto cleanup_phylink; } return 0; +cleanup_phylink: + phylink_destroy(lp->phylink); + +cleanup_mdio: + if (lp->pcs_phy) + put_device(&lp->pcs_phy->dev); + if (lp->mii_bus) + axienet_mdio_teardown(lp); + of_node_put(lp->phy_node); + +cleanup_clk: + clk_disable_unprepare(lp->clk); + free_netdev: free_netdev(ndev); diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c index 4ac0373326ef..d5b1e48e0c09 100644 --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -908,8 +908,16 @@ static int geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev, info = skb_tunnel_info(skb); if (info) { - info->key.u.ipv4.dst = fl4.saddr; - info->key.u.ipv4.src = fl4.daddr; + struct ip_tunnel_info *unclone; + + unclone = skb_tunnel_info_unclone(skb); + if (unlikely(!unclone)) { + dst_release(&rt->dst); + return -ENOMEM; + } + + unclone->key.u.ipv4.dst = fl4.saddr; + unclone->key.u.ipv4.src = fl4.daddr; } if (!pskb_may_pull(skb, ETH_HLEN)) { @@ -993,8 +1001,16 @@ static int geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev, struct ip_tunnel_info *info = skb_tunnel_info(skb); if (info) { - info->key.u.ipv6.dst = fl6.saddr; - info->key.u.ipv6.src = fl6.daddr; + struct ip_tunnel_info *unclone; + + unclone = skb_tunnel_info_unclone(skb); + if (unlikely(!unclone)) { + dst_release(dst); + return -ENOMEM; + } + + unclone->key.u.ipv6.dst = fl6.saddr; + unclone->key.u.ipv6.src = fl6.daddr; } if (!pskb_may_pull(skb, ETH_HLEN)) { diff --git a/drivers/net/hamradio/scc.c b/drivers/net/hamradio/scc.c index 36eeb80406f2..4690c6a59054 100644 --- a/drivers/net/hamradio/scc.c +++ b/drivers/net/hamradio/scc.c @@ -2167,7 +2167,6 @@ static void __exit scc_cleanup_driver(void) MODULE_AUTHOR("Joerg Reuter <jreuter@yaina.de>"); MODULE_DESCRIPTION("AX.25 Device Driver for Z8530 based HDLC cards"); -MODULE_SUPPORTED_DEVICE("Z8530 based SCC cards for Amateur Radio"); MODULE_LICENSE("GPL"); module_init(scc_init_driver); module_exit(scc_cleanup_driver); diff --git a/drivers/net/ieee802154/atusb.c b/drivers/net/ieee802154/atusb.c index 0dd0ba915ab9..23ee0b14cbfa 100644 --- a/drivers/net/ieee802154/atusb.c +++ b/drivers/net/ieee802154/atusb.c @@ -365,6 +365,7 @@ static int atusb_alloc_urbs(struct atusb *atusb, int n) return -ENOMEM; } usb_anchor_urb(urb, &atusb->idle_urbs); + usb_free_urb(urb); n--; } return 0; diff --git a/drivers/net/ipa/ipa_cmd.c b/drivers/net/ipa/ipa_cmd.c index 35e35852c25c..d73b03a80ef8 100644 --- a/drivers/net/ipa/ipa_cmd.c +++ b/drivers/net/ipa/ipa_cmd.c @@ -175,21 +175,23 @@ bool ipa_cmd_table_valid(struct ipa *ipa, const struct ipa_mem *mem, : field_max(IP_FLTRT_FLAGS_NHASH_ADDR_FMASK); if (mem->offset > offset_max || ipa->mem_offset > offset_max - mem->offset) { - dev_err(dev, "IPv%c %s%s table region offset too large " - "(0x%04x + 0x%04x > 0x%04x)\n", - ipv6 ? '6' : '4', hashed ? "hashed " : "", - route ? "route" : "filter", - ipa->mem_offset, mem->offset, offset_max); + dev_err(dev, "IPv%c %s%s table region offset too large\n", + ipv6 ? '6' : '4', hashed ? "hashed " : "", + route ? "route" : "filter"); + dev_err(dev, " (0x%04x + 0x%04x > 0x%04x)\n", + ipa->mem_offset, mem->offset, offset_max); + return false; } if (mem->offset > ipa->mem_size || mem->size > ipa->mem_size - mem->offset) { - dev_err(dev, "IPv%c %s%s table region out of range " - "(0x%04x + 0x%04x > 0x%04x)\n", - ipv6 ? '6' : '4', hashed ? "hashed " : "", - route ? "route" : "filter", - mem->offset, mem->size, ipa->mem_size); + dev_err(dev, "IPv%c %s%s table region out of range\n", + ipv6 ? '6' : '4', hashed ? "hashed " : "", + route ? "route" : "filter"); + dev_err(dev, " (0x%04x + 0x%04x > 0x%04x)\n", + mem->offset, mem->size, ipa->mem_size); + return false; } @@ -205,22 +207,36 @@ static bool ipa_cmd_header_valid(struct ipa *ipa) u32 size_max; u32 size; + /* In ipa_cmd_hdr_init_local_add() we record the offset and size + * of the header table memory area. Make sure the offset and size + * fit in the fields that need to hold them, and that the entire + * range is within the overall IPA memory range. + */ offset_max = field_max(HDR_INIT_LOCAL_FLAGS_HDR_ADDR_FMASK); if (mem->offset > offset_max || ipa->mem_offset > offset_max - mem->offset) { - dev_err(dev, "header table region offset too large " - "(0x%04x + 0x%04x > 0x%04x)\n", - ipa->mem_offset + mem->offset, offset_max); + dev_err(dev, "header table region offset too large\n"); + dev_err(dev, " (0x%04x + 0x%04x > 0x%04x)\n", + ipa->mem_offset, mem->offset, offset_max); + return false; } size_max = field_max(HDR_INIT_LOCAL_FLAGS_TABLE_SIZE_FMASK); size = ipa->mem[IPA_MEM_MODEM_HEADER].size; size += ipa->mem[IPA_MEM_AP_HEADER].size; - if (mem->offset > ipa->mem_size || size > ipa->mem_size - mem->offset) { - dev_err(dev, "header table region out of range " - "(0x%04x + 0x%04x > 0x%04x)\n", - mem->offset, size, ipa->mem_size); + + if (size > size_max) { + dev_err(dev, "header table region size too large\n"); + dev_err(dev, " (0x%04x > 0x%08x)\n", size, size_max); + + return false; + } + if (size > ipa->mem_size || mem->offset > ipa->mem_size - size) { + dev_err(dev, "header table region out of range\n"); + dev_err(dev, " (0x%04x + 0x%04x > 0x%04x)\n", + mem->offset, size, ipa->mem_size); + return false; } diff --git a/drivers/net/ipa/ipa_qmi.c b/drivers/net/ipa/ipa_qmi.c index 2fc64483f275..e594bf3b600f 100644 --- a/drivers/net/ipa/ipa_qmi.c +++ b/drivers/net/ipa/ipa_qmi.c @@ -249,6 +249,7 @@ static const struct qmi_msg_handler ipa_server_msg_handlers[] = { .decoded_size = IPA_QMI_DRIVER_INIT_COMPLETE_REQ_SZ, .fn = ipa_server_driver_init_complete, }, + { }, }; /* Handle an INIT_DRIVER response message from the modem. */ @@ -269,6 +270,7 @@ static const struct qmi_msg_handler ipa_client_msg_handlers[] = { .decoded_size = IPA_QMI_INIT_DRIVER_RSP_SZ, .fn = ipa_client_init_driver, }, + { }, }; /* Return a pointer to an init modem driver request structure, which contains diff --git a/drivers/net/phy/bcm-phy-lib.c b/drivers/net/phy/bcm-phy-lib.c index 53282a6d5928..287cccf8f7f4 100644 --- a/drivers/net/phy/bcm-phy-lib.c +++ b/drivers/net/phy/bcm-phy-lib.c @@ -369,7 +369,7 @@ EXPORT_SYMBOL_GPL(bcm_phy_enable_apd); int bcm_phy_set_eee(struct phy_device *phydev, bool enable) { - int val; + int val, mask = 0; /* Enable EEE at PHY level */ val = phy_read_mmd(phydev, MDIO_MMD_AN, BRCM_CL45VEN_EEE_CONTROL); @@ -388,10 +388,17 @@ int bcm_phy_set_eee(struct phy_device *phydev, bool enable) if (val < 0) return val; + if (linkmode_test_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT, + phydev->supported)) + mask |= MDIO_EEE_1000T; + if (linkmode_test_bit(ETHTOOL_LINK_MODE_100baseT_Full_BIT, + phydev->supported)) + mask |= MDIO_EEE_100TX; + if (enable) - val |= (MDIO_EEE_100TX | MDIO_EEE_1000T); + val |= mask; else - val &= ~(MDIO_EEE_100TX | MDIO_EEE_1000T); + val &= ~mask; phy_write_mmd(phydev, MDIO_MMD_AN, BCM_CL45VEN_EEE_ADV, (u32)val); diff --git a/drivers/net/phy/broadcom.c b/drivers/net/phy/broadcom.c index fa0be591ae79..82fe5f43f0e9 100644 --- a/drivers/net/phy/broadcom.c +++ b/drivers/net/phy/broadcom.c @@ -342,6 +342,10 @@ static int bcm54xx_config_init(struct phy_device *phydev) bcm54xx_adjust_rxrefclk(phydev); switch (BRCM_PHY_MODEL(phydev)) { + case PHY_ID_BCM50610: + case PHY_ID_BCM50610M: + err = bcm54xx_config_clock_delay(phydev); + break; case PHY_ID_BCM54210E: err = bcm54210e_config_init(phydev); break; @@ -399,6 +403,11 @@ static int bcm54xx_resume(struct phy_device *phydev) if (ret < 0) return ret; + /* Upon exiting power down, the PHY remains in an internal reset state + * for 40us + */ + fsleep(40); + return bcm54xx_config_init(phydev); } diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index 053c92e02cd8..dc2800beacc3 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -476,7 +476,7 @@ static void phylink_major_config(struct phylink *pl, bool restart, err = pl->mac_ops->mac_finish(pl->config, pl->cur_link_an_mode, state->interface); if (err < 0) - phylink_err(pl, "mac_prepare failed: %pe\n", + phylink_err(pl, "mac_finish failed: %pe\n", ERR_PTR(err)); } } diff --git a/drivers/net/tun.c b/drivers/net/tun.c index fc86da7f1628..4cf38be26dc9 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -69,6 +69,14 @@ #include <linux/bpf.h> #include <linux/bpf_trace.h> #include <linux/mutex.h> +#include <linux/ieee802154.h> +#include <linux/if_ltalk.h> +#include <uapi/linux/if_fddi.h> +#include <uapi/linux/if_hippi.h> +#include <uapi/linux/if_fc.h> +#include <net/ax25.h> +#include <net/rose.h> +#include <net/6lowpan.h> #include <linux/uaccess.h> #include <linux/proc_fs.h> @@ -2919,6 +2927,45 @@ static int tun_set_ebpf(struct tun_struct *tun, struct tun_prog __rcu **prog_p, return __tun_set_ebpf(tun, prog_p, prog); } +/* Return correct value for tun->dev->addr_len based on tun->dev->type. */ +static unsigned char tun_get_addr_len(unsigned short type) +{ + switch (type) { + case ARPHRD_IP6GRE: + case ARPHRD_TUNNEL6: + return sizeof(struct in6_addr); + case ARPHRD_IPGRE: + case ARPHRD_TUNNEL: + case ARPHRD_SIT: + return 4; + case ARPHRD_ETHER: + return ETH_ALEN; + case ARPHRD_IEEE802154: + case ARPHRD_IEEE802154_MONITOR: + return IEEE802154_EXTENDED_ADDR_LEN; + case ARPHRD_PHONET_PIPE: + case ARPHRD_PPP: + case ARPHRD_NONE: + return 0; + case ARPHRD_6LOWPAN: + return EUI64_ADDR_LEN; + case ARPHRD_FDDI: + return FDDI_K_ALEN; + case ARPHRD_HIPPI: + return HIPPI_ALEN; + case ARPHRD_IEEE802: + return FC_ALEN; + case ARPHRD_ROSE: + return ROSE_ADDR_LEN; + case ARPHRD_NETROM: + return AX25_ADDR_LEN; + case ARPHRD_LOCALTLK: + return LTALK_ALEN; + default: + return 0; + } +} + static long __tun_chr_ioctl(struct file *file, unsigned int cmd, unsigned long arg, int ifreq_len) { @@ -3082,6 +3129,7 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd, break; } tun->dev->type = (int) arg; + tun->dev->addr_len = tun_get_addr_len(tun->dev->type); netif_info(tun, drv, tun->dev, "linktype set to %d\n", tun->dev->type); call_netdevice_notifiers(NETDEV_POST_TYPE_CHANGE, diff --git a/drivers/net/usb/cdc-phonet.c b/drivers/net/usb/cdc-phonet.c index 02e6bbb17b15..8d1f69dad603 100644 --- a/drivers/net/usb/cdc-phonet.c +++ b/drivers/net/usb/cdc-phonet.c @@ -387,6 +387,8 @@ static int usbpn_probe(struct usb_interface *intf, const struct usb_device_id *i err = register_netdev(dev); if (err) { + /* Set disconnected flag so that disconnect() returns early. */ + pnd->disconnected = 1; usb_driver_release_interface(&usbpn_driver, data_intf); goto out; } diff --git a/drivers/net/usb/hso.c b/drivers/net/usb/hso.c index 31d51346786a..9bc58e64b5b7 100644 --- a/drivers/net/usb/hso.c +++ b/drivers/net/usb/hso.c @@ -611,7 +611,7 @@ static struct hso_serial *get_serial_by_index(unsigned index) return serial; } -static int get_free_serial_index(void) +static int obtain_minor(struct hso_serial *serial) { int index; unsigned long flags; @@ -619,8 +619,10 @@ static int get_free_serial_index(void) spin_lock_irqsave(&serial_table_lock, flags); for (index = 0; index < HSO_SERIAL_TTY_MINORS; index++) { if (serial_table[index] == NULL) { + serial_table[index] = serial->parent; + serial->minor = index; spin_unlock_irqrestore(&serial_table_lock, flags); - return index; + return 0; } } spin_unlock_irqrestore(&serial_table_lock, flags); @@ -629,15 +631,12 @@ static int get_free_serial_index(void) return -1; } -static void set_serial_by_index(unsigned index, struct hso_serial *serial) +static void release_minor(struct hso_serial *serial) { unsigned long flags; spin_lock_irqsave(&serial_table_lock, flags); - if (serial) - serial_table[index] = serial->parent; - else - serial_table[index] = NULL; + serial_table[serial->minor] = NULL; spin_unlock_irqrestore(&serial_table_lock, flags); } @@ -2230,6 +2229,7 @@ static int hso_stop_serial_device(struct hso_device *hso_dev) static void hso_serial_tty_unregister(struct hso_serial *serial) { tty_unregister_device(tty_drv, serial->minor); + release_minor(serial); } static void hso_serial_common_free(struct hso_serial *serial) @@ -2253,24 +2253,22 @@ static void hso_serial_common_free(struct hso_serial *serial) static int hso_serial_common_create(struct hso_serial *serial, int num_urbs, int rx_size, int tx_size) { - int minor; int i; tty_port_init(&serial->port); - minor = get_free_serial_index(); - if (minor < 0) + if (obtain_minor(serial)) goto exit2; /* register our minor number */ serial->parent->dev = tty_port_register_device_attr(&serial->port, - tty_drv, minor, &serial->parent->interface->dev, + tty_drv, serial->minor, &serial->parent->interface->dev, serial->parent, hso_serial_dev_groups); - if (IS_ERR(serial->parent->dev)) + if (IS_ERR(serial->parent->dev)) { + release_minor(serial); goto exit2; + } - /* fill in specific data for later use */ - serial->minor = minor; serial->magic = HSO_SERIAL_MAGIC; spin_lock_init(&serial->serial_lock); serial->num_rx_urbs = num_urbs; @@ -2667,9 +2665,6 @@ static struct hso_device *hso_create_bulk_serial_device( serial->write_data = hso_std_serial_write_data; - /* and record this serial */ - set_serial_by_index(serial->minor, serial); - /* setup the proc dirs and files if needed */ hso_log_port(hso_dev); @@ -2726,9 +2721,6 @@ struct hso_device *hso_create_mux_serial_device(struct usb_interface *interface, serial->shared_int->ref_count++; mutex_unlock(&serial->shared_int->shared_int_lock); - /* and record this serial */ - set_serial_by_index(serial->minor, serial); - /* setup the proc dirs and files if needed */ hso_log_port(hso_dev); @@ -3113,7 +3105,6 @@ static void hso_free_interface(struct usb_interface *interface) cancel_work_sync(&serial_table[i]->async_get_intf); hso_serial_tty_unregister(serial); kref_put(&serial_table[i]->ref, hso_serial_ref_free); - set_serial_by_index(i, NULL); } } diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index 90f1c0200042..20fb5638ac65 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -6553,7 +6553,10 @@ static int rtl_ops_init(struct r8152 *tp) ops->in_nway = rtl8153_in_nway; ops->hw_phy_cfg = r8153_hw_phy_cfg; ops->autosuspend_en = rtl8153_runtime_enable; - tp->rx_buf_sz = 32 * 1024; + if (tp->udev->speed < USB_SPEED_SUPER) + tp->rx_buf_sz = 16 * 1024; + else + tp->rx_buf_sz = 32 * 1024; tp->eee_en = true; tp->eee_adv = MDIO_EEE_1000T | MDIO_EEE_100TX; break; diff --git a/drivers/net/veth.c b/drivers/net/veth.c index aa1a66ad2ce5..34e49c75db42 100644 --- a/drivers/net/veth.c +++ b/drivers/net/veth.c @@ -302,8 +302,7 @@ static netdev_tx_t veth_xmit(struct sk_buff *skb, struct net_device *dev) if (rxq < rcv->real_num_rx_queues) { rq = &rcv_priv->rq[rxq]; rcv_xdp = rcu_access_pointer(rq->xdp_prog); - if (rcv_xdp) - skb_record_rx_queue(skb, rxq); + skb_record_rx_queue(skb, rxq); } skb_tx_timestamp(skb); diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 82e520d2cb12..0824e6999e49 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -406,9 +406,13 @@ static struct sk_buff *page_to_skb(struct virtnet_info *vi, offset += hdr_padded_len; p += hdr_padded_len; - copy = len; - if (copy > skb_tailroom(skb)) - copy = skb_tailroom(skb); + /* Copy all frame if it fits skb->head, otherwise + * we let virtio_net_hdr_to_skb() and GRO pull headers as needed. + */ + if (len <= skb_tailroom(skb)) + copy = len; + else + copy = ETH_HLEN + metasize; skb_put_data(skb, p, copy); if (metasize) { diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 666dd201c3d5..53dbc67e8a34 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -2725,12 +2725,17 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, goto tx_error; } else if (err) { if (info) { + struct ip_tunnel_info *unclone; struct in_addr src, dst; + unclone = skb_tunnel_info_unclone(skb); + if (unlikely(!unclone)) + goto tx_error; + src = remote_ip.sin.sin_addr; dst = local_ip.sin.sin_addr; - info->key.u.ipv4.src = src.s_addr; - info->key.u.ipv4.dst = dst.s_addr; + unclone->key.u.ipv4.src = src.s_addr; + unclone->key.u.ipv4.dst = dst.s_addr; } vxlan_encap_bypass(skb, vxlan, vxlan, vni, false); dst_release(ndst); @@ -2781,12 +2786,17 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, goto tx_error; } else if (err) { if (info) { + struct ip_tunnel_info *unclone; struct in6_addr src, dst; + unclone = skb_tunnel_info_unclone(skb); + if (unlikely(!unclone)) + goto tx_error; + src = remote_ip.sin6.sin6_addr; dst = local_ip.sin6.sin6_addr; - info->key.u.ipv6.src = src; - info->key.u.ipv6.dst = dst; + unclone->key.u.ipv6.src = src; + unclone->key.u.ipv6.dst = dst; } vxlan_encap_bypass(skb, vxlan, vxlan, vni, false); diff --git a/drivers/net/wan/hdlc_fr.c b/drivers/net/wan/hdlc_fr.c index 0720f5f92caa..4d9dc7d15908 100644 --- a/drivers/net/wan/hdlc_fr.c +++ b/drivers/net/wan/hdlc_fr.c @@ -415,7 +415,7 @@ static netdev_tx_t pvc_xmit(struct sk_buff *skb, struct net_device *dev) if (pad > 0) { /* Pad the frame with zeros */ if (__skb_pad(skb, pad, false)) - goto drop; + goto out; skb_put(skb, pad); } } @@ -448,8 +448,9 @@ static netdev_tx_t pvc_xmit(struct sk_buff *skb, struct net_device *dev) return NETDEV_TX_OK; drop: - dev->stats.tx_dropped++; kfree_skb(skb); +out: + dev->stats.tx_dropped++; return NETDEV_TX_OK; } diff --git a/drivers/net/wan/hdlc_x25.c b/drivers/net/wan/hdlc_x25.c index 4aaa6388b9ee..5a6a945f6c81 100644 --- a/drivers/net/wan/hdlc_x25.c +++ b/drivers/net/wan/hdlc_x25.c @@ -23,6 +23,8 @@ struct x25_state { x25_hdlc_proto settings; + bool up; + spinlock_t up_lock; /* Protects "up" */ }; static int x25_ioctl(struct net_device *dev, struct ifreq *ifr); @@ -104,6 +106,8 @@ static void x25_data_transmit(struct net_device *dev, struct sk_buff *skb) static netdev_tx_t x25_xmit(struct sk_buff *skb, struct net_device *dev) { + hdlc_device *hdlc = dev_to_hdlc(dev); + struct x25_state *x25st = state(hdlc); int result; /* There should be a pseudo header of 1 byte added by upper layers. @@ -114,11 +118,19 @@ static netdev_tx_t x25_xmit(struct sk_buff *skb, struct net_device *dev) return NETDEV_TX_OK; } + spin_lock_bh(&x25st->up_lock); + if (!x25st->up) { + spin_unlock_bh(&x25st->up_lock); + kfree_skb(skb); + return NETDEV_TX_OK; + } + switch (skb->data[0]) { case X25_IFACE_DATA: /* Data to be transmitted */ skb_pull(skb, 1); if ((result = lapb_data_request(dev, skb)) != LAPB_OK) dev_kfree_skb(skb); + spin_unlock_bh(&x25st->up_lock); return NETDEV_TX_OK; case X25_IFACE_CONNECT: @@ -147,6 +159,7 @@ static netdev_tx_t x25_xmit(struct sk_buff *skb, struct net_device *dev) break; } + spin_unlock_bh(&x25st->up_lock); dev_kfree_skb(skb); return NETDEV_TX_OK; } @@ -164,6 +177,7 @@ static int x25_open(struct net_device *dev) .data_transmit = x25_data_transmit, }; hdlc_device *hdlc = dev_to_hdlc(dev); + struct x25_state *x25st = state(hdlc); struct lapb_parms_struct params; int result; @@ -190,6 +204,10 @@ static int x25_open(struct net_device *dev) if (result != LAPB_OK) return -EINVAL; + spin_lock_bh(&x25st->up_lock); + x25st->up = true; + spin_unlock_bh(&x25st->up_lock); + return 0; } @@ -197,6 +215,13 @@ static int x25_open(struct net_device *dev) static void x25_close(struct net_device *dev) { + hdlc_device *hdlc = dev_to_hdlc(dev); + struct x25_state *x25st = state(hdlc); + + spin_lock_bh(&x25st->up_lock); + x25st->up = false; + spin_unlock_bh(&x25st->up_lock); + lapb_unregister(dev); } @@ -205,15 +230,28 @@ static void x25_close(struct net_device *dev) static int x25_rx(struct sk_buff *skb) { struct net_device *dev = skb->dev; + hdlc_device *hdlc = dev_to_hdlc(dev); + struct x25_state *x25st = state(hdlc); if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL) { dev->stats.rx_dropped++; return NET_RX_DROP; } - if (lapb_data_received(dev, skb) == LAPB_OK) + spin_lock_bh(&x25st->up_lock); + if (!x25st->up) { + spin_unlock_bh(&x25st->up_lock); + kfree_skb(skb); + dev->stats.rx_dropped++; + return NET_RX_DROP; + } + + if (lapb_data_received(dev, skb) == LAPB_OK) { + spin_unlock_bh(&x25st->up_lock); return NET_RX_SUCCESS; + } + spin_unlock_bh(&x25st->up_lock); dev->stats.rx_errors++; dev_kfree_skb_any(skb); return NET_RX_DROP; @@ -298,6 +336,8 @@ static int x25_ioctl(struct net_device *dev, struct ifreq *ifr) return result; memcpy(&state(hdlc)->settings, &new_settings, size); + state(hdlc)->up = false; + spin_lock_init(&state(hdlc)->up_lock); /* There's no header_ops so hard_header_len should be 0. */ dev->hard_header_len = 0; diff --git a/drivers/net/wireless/admtek/adm8211.c b/drivers/net/wireless/admtek/adm8211.c index c41e72508d3d..2db9c948c0fc 100644 --- a/drivers/net/wireless/admtek/adm8211.c +++ b/drivers/net/wireless/admtek/adm8211.c @@ -28,7 +28,6 @@ MODULE_AUTHOR("Michael Wu <flamingice@sourmilk.net>"); MODULE_AUTHOR("Jouni Malinen <j@w1.fi>"); MODULE_DESCRIPTION("Driver for IEEE 802.11b wireless cards based on ADMtek ADM8211"); -MODULE_SUPPORTED_DEVICE("ADM8211"); MODULE_LICENSE("GPL"); static unsigned int tx_ring_size __read_mostly = 16; diff --git a/drivers/net/wireless/ath/ath5k/base.c b/drivers/net/wireless/ath/ath5k/base.c index 4c6e57f9976d..cef17f33c69e 100644 --- a/drivers/net/wireless/ath/ath5k/base.c +++ b/drivers/net/wireless/ath/ath5k/base.c @@ -90,7 +90,6 @@ MODULE_PARM_DESC(no_hw_rfkill_switch, "Ignore the GPIO RFKill switch state"); MODULE_AUTHOR("Jiri Slaby"); MODULE_AUTHOR("Nick Kossifidis"); MODULE_DESCRIPTION("Support for 5xxx series of Atheros 802.11 wireless LAN cards."); -MODULE_SUPPORTED_DEVICE("Atheros 5xxx WLAN cards"); MODULE_LICENSE("Dual BSD/GPL"); static int ath5k_init(struct ieee80211_hw *hw); diff --git a/drivers/net/wireless/ath/ath9k/hw.c b/drivers/net/wireless/ath/ath9k/hw.c index b66eeb577272..5abc2a5526ec 100644 --- a/drivers/net/wireless/ath/ath9k/hw.c +++ b/drivers/net/wireless/ath/ath9k/hw.c @@ -34,7 +34,6 @@ static bool ath9k_hw_set_reset_reg(struct ath_hw *ah, u32 type); MODULE_AUTHOR("Atheros Communications"); MODULE_DESCRIPTION("Support for Atheros 802.11n wireless LAN cards."); -MODULE_SUPPORTED_DEVICE("Atheros 802.11n WLAN cards"); MODULE_LICENSE("Dual BSD/GPL"); static void ath9k_hw_set_clockrate(struct ath_hw *ah) diff --git a/drivers/net/wireless/ath/ath9k/init.c b/drivers/net/wireless/ath/ath9k/init.c index 42a208787f5a..01f9c26f9bf3 100644 --- a/drivers/net/wireless/ath/ath9k/init.c +++ b/drivers/net/wireless/ath/ath9k/init.c @@ -37,7 +37,6 @@ static char *dev_info = "ath9k"; MODULE_AUTHOR("Atheros Communications"); MODULE_DESCRIPTION("Support for Atheros 802.11n wireless LAN cards."); -MODULE_SUPPORTED_DEVICE("Atheros 802.11n WLAN cards"); MODULE_LICENSE("Dual BSD/GPL"); static unsigned int ath9k_debug = ATH_DBG_DEFAULT; diff --git a/drivers/net/wireless/atmel/atmel.c b/drivers/net/wireless/atmel/atmel.c index 707fe66727f8..febce4e8b3dd 100644 --- a/drivers/net/wireless/atmel/atmel.c +++ b/drivers/net/wireless/atmel/atmel.c @@ -75,7 +75,6 @@ MODULE_AUTHOR("Simon Kelley"); MODULE_DESCRIPTION("Support for Atmel at76c50x 802.11 wireless ethernet cards."); MODULE_LICENSE("GPL"); -MODULE_SUPPORTED_DEVICE("Atmel at76c50x wireless cards"); /* The name of the firmware file to be loaded over-rides any automatic selection */ diff --git a/drivers/net/wireless/atmel/atmel_cs.c b/drivers/net/wireless/atmel/atmel_cs.c index 368eebefa741..453bb84cb338 100644 --- a/drivers/net/wireless/atmel/atmel_cs.c +++ b/drivers/net/wireless/atmel/atmel_cs.c @@ -57,7 +57,6 @@ MODULE_AUTHOR("Simon Kelley"); MODULE_DESCRIPTION("Support for Atmel at76c50x 802.11 wireless ethernet cards."); MODULE_LICENSE("GPL"); -MODULE_SUPPORTED_DEVICE("Atmel at76c50x PCMCIA cards"); /*====================================================================*/ diff --git a/drivers/net/wireless/atmel/atmel_pci.c b/drivers/net/wireless/atmel/atmel_pci.c index 47f7ccb32414..f428dc79d916 100644 --- a/drivers/net/wireless/atmel/atmel_pci.c +++ b/drivers/net/wireless/atmel/atmel_pci.c @@ -16,7 +16,6 @@ MODULE_AUTHOR("Simon Kelley"); MODULE_DESCRIPTION("Support for Atmel at76c50x 802.11 wireless ethernet cards."); MODULE_LICENSE("GPL"); -MODULE_SUPPORTED_DEVICE("Atmel at76c506 PCI wireless cards"); static const struct pci_device_id card_ids[] = { { 0x1114, 0x0506, PCI_ANY_ID, PCI_ANY_ID }, diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/p2p.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/p2p.c index 6d30a0fcecea..34cd8a7401fe 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/p2p.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/p2p.c @@ -2439,7 +2439,7 @@ void brcmf_p2p_ifp_removed(struct brcmf_if *ifp, bool locked) vif = ifp->vif; cfg = wdev_to_cfg(&vif->wdev); cfg->p2p.bss_idx[P2PAPI_BSSCFG_DEVICE].vif = NULL; - if (locked) { + if (!locked) { rtnl_lock(); wiphy_lock(cfg->wiphy); cfg80211_unregister_wdev(&vif->wdev); diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/mac80211_if.c b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/mac80211_if.c index 818e523f6025..39f3af2d0439 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/mac80211_if.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/mac80211_if.c @@ -87,7 +87,6 @@ static int n_adapters_found; MODULE_AUTHOR("Broadcom Corporation"); MODULE_DESCRIPTION("Broadcom 802.11n wireless LAN driver."); -MODULE_SUPPORTED_DEVICE("Broadcom 802.11n WLAN cards"); MODULE_LICENSE("Dual BSD/GPL"); /* This needs to be adjusted when brcms_firmwares changes */ MODULE_FIRMWARE("brcm/bcm43xx-0.fw"); diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmutil/utils.c b/drivers/net/wireless/broadcom/brcm80211/brcmutil/utils.c index 4c84c3001c3f..e87e68cc46e2 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmutil/utils.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmutil/utils.c @@ -12,7 +12,6 @@ MODULE_AUTHOR("Broadcom Corporation"); MODULE_DESCRIPTION("Broadcom 802.11n wireless LAN driver utilities."); -MODULE_SUPPORTED_DEVICE("Broadcom 802.11n WLAN cards"); MODULE_LICENSE("Dual BSD/GPL"); struct sk_buff *brcmu_pkt_buf_get_skb(uint len) diff --git a/drivers/net/wireless/cisco/airo.c b/drivers/net/wireless/cisco/airo.c index e35e1380ae43..60db38c38960 100644 --- a/drivers/net/wireless/cisco/airo.c +++ b/drivers/net/wireless/cisco/airo.c @@ -251,7 +251,6 @@ MODULE_AUTHOR("Benjamin Reed"); MODULE_DESCRIPTION("Support for Cisco/Aironet 802.11 wireless ethernet cards. " "Direct support for ISA/PCI/MPI cards and support for PCMCIA when used with airo_cs."); MODULE_LICENSE("Dual BSD/GPL"); -MODULE_SUPPORTED_DEVICE("Aironet 4500, 4800 and Cisco 340/350"); module_param_hw_array(io, int, ioport, NULL, 0); module_param_hw_array(irq, int, irq, NULL, 0); module_param_array(rates, int, NULL, 0); diff --git a/drivers/net/wireless/cisco/airo_cs.c b/drivers/net/wireless/cisco/airo_cs.c index 3718f958c0fc..fcfe4c6d62f0 100644 --- a/drivers/net/wireless/cisco/airo_cs.c +++ b/drivers/net/wireless/cisco/airo_cs.c @@ -47,7 +47,6 @@ MODULE_DESCRIPTION("Support for Cisco/Aironet 802.11 wireless ethernet " "cards. This is the module that links the PCMCIA card " "with the airo module."); MODULE_LICENSE("Dual BSD/GPL"); -MODULE_SUPPORTED_DEVICE("Aironet 4500, 4800 and Cisco 340 PCMCIA cards"); /*====================================================================*/ diff --git a/drivers/net/wireless/intel/iwlwifi/fw/notif-wait.c b/drivers/net/wireless/intel/iwlwifi/fw/notif-wait.c index 3dbc6f3f92cc..231d2517f398 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/notif-wait.c +++ b/drivers/net/wireless/intel/iwlwifi/fw/notif-wait.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause /* - * Copyright (C) 2005-2014 Intel Corporation + * Copyright (C) 2005-2014, 2021 Intel Corporation * Copyright (C) 2015-2017 Intel Deutschland GmbH */ #include <linux/sched.h> @@ -26,7 +26,7 @@ bool iwl_notification_wait(struct iwl_notif_wait_data *notif_wait, if (!list_empty(¬if_wait->notif_waits)) { struct iwl_notification_wait *w; - spin_lock(¬if_wait->notif_wait_lock); + spin_lock_bh(¬if_wait->notif_wait_lock); list_for_each_entry(w, ¬if_wait->notif_waits, list) { int i; bool found = false; @@ -59,7 +59,7 @@ bool iwl_notification_wait(struct iwl_notif_wait_data *notif_wait, triggered = true; } } - spin_unlock(¬if_wait->notif_wait_lock); + spin_unlock_bh(¬if_wait->notif_wait_lock); } return triggered; @@ -70,10 +70,10 @@ void iwl_abort_notification_waits(struct iwl_notif_wait_data *notif_wait) { struct iwl_notification_wait *wait_entry; - spin_lock(¬if_wait->notif_wait_lock); + spin_lock_bh(¬if_wait->notif_wait_lock); list_for_each_entry(wait_entry, ¬if_wait->notif_waits, list) wait_entry->aborted = true; - spin_unlock(¬if_wait->notif_wait_lock); + spin_unlock_bh(¬if_wait->notif_wait_lock); wake_up_all(¬if_wait->notif_waitq); } diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-config.h b/drivers/net/wireless/intel/iwlwifi/iwl-config.h index 75f99ff7f908..c4f5da76f1c0 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-config.h +++ b/drivers/net/wireless/intel/iwlwifi/iwl-config.h @@ -414,6 +414,7 @@ struct iwl_cfg { #define IWL_CFG_MAC_TYPE_QNJ 0x36 #define IWL_CFG_MAC_TYPE_SO 0x37 #define IWL_CFG_MAC_TYPE_SNJ 0x42 +#define IWL_CFG_MAC_TYPE_SOF 0x43 #define IWL_CFG_MAC_TYPE_MA 0x44 #define IWL_CFG_RF_TYPE_TH 0x105 diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c index af684f80b0cc..c5a1e84dc1ab 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c +++ b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c @@ -232,7 +232,7 @@ enum iwl_reg_capa_flags_v2 { REG_CAPA_V2_MCS_9_ALLOWED = BIT(6), REG_CAPA_V2_WEATHER_DISABLED = BIT(7), REG_CAPA_V2_40MHZ_ALLOWED = BIT(8), - REG_CAPA_V2_11AX_DISABLED = BIT(13), + REG_CAPA_V2_11AX_DISABLED = BIT(10), }; /* diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c b/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c index 130760572262..34ddef97b099 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c @@ -1786,10 +1786,13 @@ static ssize_t iwl_dbgfs_rfi_freq_table_write(struct iwl_mvm *mvm, char *buf, return -EINVAL; /* value zero triggers re-sending the default table to the device */ - if (!op_id) + if (!op_id) { + mutex_lock(&mvm->mutex); ret = iwl_rfi_send_config_cmd(mvm, NULL); - else + mutex_unlock(&mvm->mutex); + } else { ret = -EOPNOTSUPP; /* in the future a new table will be added */ + } return ret ?: count; } diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rfi.c b/drivers/net/wireless/intel/iwlwifi/mvm/rfi.c index 873919048143..0b818067067c 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/rfi.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/rfi.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause /* - * Copyright (C) 2020 Intel Corporation + * Copyright (C) 2020 - 2021 Intel Corporation */ #include "mvm.h" @@ -66,6 +66,8 @@ int iwl_rfi_send_config_cmd(struct iwl_mvm *mvm, struct iwl_rfi_lut_entry *rfi_t if (!fw_has_capa(&mvm->fw->ucode_capa, IWL_UCODE_TLV_CAPA_RFIM_SUPPORT)) return -EOPNOTSUPP; + lockdep_assert_held(&mvm->mutex); + /* in case no table is passed, use the default one */ if (!rfi_table) { memcpy(cmd.table, iwl_rfi_table, sizeof(cmd.table)); @@ -75,9 +77,7 @@ int iwl_rfi_send_config_cmd(struct iwl_mvm *mvm, struct iwl_rfi_lut_entry *rfi_t cmd.oem = 1; } - mutex_lock(&mvm->mutex); ret = iwl_mvm_send_cmd(mvm, &hcmd); - mutex_unlock(&mvm->mutex); if (ret) IWL_ERR(mvm, "Failed to send RFI config cmd %d\n", ret); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c index c21736f80c29..af5a6dd81c41 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c @@ -272,10 +272,10 @@ static void iwl_mvm_get_signal_strength(struct iwl_mvm *mvm, rx_status->chain_signal[2] = S8_MIN; } -static int iwl_mvm_rx_mgmt_crypto(struct ieee80211_sta *sta, - struct ieee80211_hdr *hdr, - struct iwl_rx_mpdu_desc *desc, - u32 status) +static int iwl_mvm_rx_mgmt_prot(struct ieee80211_sta *sta, + struct ieee80211_hdr *hdr, + struct iwl_rx_mpdu_desc *desc, + u32 status) { struct iwl_mvm_sta *mvmsta; struct iwl_mvm_vif *mvmvif; @@ -285,6 +285,9 @@ static int iwl_mvm_rx_mgmt_crypto(struct ieee80211_sta *sta, u32 len = le16_to_cpu(desc->mpdu_len); const u8 *frame = (void *)hdr; + if ((status & IWL_RX_MPDU_STATUS_SEC_MASK) == IWL_RX_MPDU_STATUS_SEC_NONE) + return 0; + /* * For non-beacon, we don't really care. But beacons may * be filtered out, and we thus need the firmware's replay @@ -356,6 +359,10 @@ static int iwl_mvm_rx_crypto(struct iwl_mvm *mvm, struct ieee80211_sta *sta, IWL_RX_MPDU_STATUS_SEC_UNKNOWN && !mvm->monitor_on) return -1; + if (unlikely(ieee80211_is_mgmt(hdr->frame_control) && + !ieee80211_has_protected(hdr->frame_control))) + return iwl_mvm_rx_mgmt_prot(sta, hdr, desc, status); + if (!ieee80211_has_protected(hdr->frame_control) || (status & IWL_RX_MPDU_STATUS_SEC_MASK) == IWL_RX_MPDU_STATUS_SEC_NONE) @@ -411,7 +418,7 @@ static int iwl_mvm_rx_crypto(struct iwl_mvm *mvm, struct ieee80211_sta *sta, stats->flag |= RX_FLAG_DECRYPTED; return 0; case RX_MPDU_RES_STATUS_SEC_CMAC_GMAC_ENC: - return iwl_mvm_rx_mgmt_crypto(sta, hdr, desc, status); + break; default: /* * Sometimes we can get frames that were not decrypted diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info-gen3.c b/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info-gen3.c index 8fba190e84cf..cecc32e7dbe8 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info-gen3.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info-gen3.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause /* - * Copyright (C) 2018-2020 Intel Corporation + * Copyright (C) 2018-2021 Intel Corporation */ #include "iwl-trans.h" #include "iwl-fh.h" @@ -75,15 +75,6 @@ int iwl_pcie_ctxt_info_gen3_init(struct iwl_trans *trans, const struct fw_img *fw) { struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans); - u32 ltr_val = CSR_LTR_LONG_VAL_AD_NO_SNOOP_REQ | - u32_encode_bits(CSR_LTR_LONG_VAL_AD_SCALE_USEC, - CSR_LTR_LONG_VAL_AD_NO_SNOOP_SCALE) | - u32_encode_bits(250, - CSR_LTR_LONG_VAL_AD_NO_SNOOP_VAL) | - CSR_LTR_LONG_VAL_AD_SNOOP_REQ | - u32_encode_bits(CSR_LTR_LONG_VAL_AD_SCALE_USEC, - CSR_LTR_LONG_VAL_AD_SNOOP_SCALE) | - u32_encode_bits(250, CSR_LTR_LONG_VAL_AD_SNOOP_VAL); struct iwl_context_info_gen3 *ctxt_info_gen3; struct iwl_prph_scratch *prph_scratch; struct iwl_prph_scratch_ctrl_cfg *prph_sc_ctrl; @@ -217,26 +208,6 @@ int iwl_pcie_ctxt_info_gen3_init(struct iwl_trans *trans, iwl_set_bit(trans, CSR_CTXT_INFO_BOOT_CTRL, CSR_AUTO_FUNC_BOOT_ENA); - /* - * To workaround hardware latency issues during the boot process, - * initialize the LTR to ~250 usec (see ltr_val above). - * The firmware initializes this again later (to a smaller value). - */ - if ((trans->trans_cfg->device_family == IWL_DEVICE_FAMILY_AX210 || - trans->trans_cfg->device_family == IWL_DEVICE_FAMILY_22000) && - !trans->trans_cfg->integrated) { - iwl_write32(trans, CSR_LTR_LONG_VAL_AD, ltr_val); - } else if (trans->trans_cfg->integrated && - trans->trans_cfg->device_family == IWL_DEVICE_FAMILY_22000) { - iwl_write_prph(trans, HPM_MAC_LTR_CSR, HPM_MAC_LRT_ENABLE_ALL); - iwl_write_prph(trans, HPM_UMAC_LTR, ltr_val); - } - - if (trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_AX210) - iwl_write_umac_prph(trans, UREG_CPU_INIT_RUN, 1); - else - iwl_set_bit(trans, CSR_GP_CNTRL, CSR_AUTO_FUNC_INIT); - return 0; err_free_ctxt_info: diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info.c b/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info.c index d1bb273d6b6d..74ce31fdf45e 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause /* * Copyright (C) 2017 Intel Deutschland GmbH - * Copyright (C) 2018-2020 Intel Corporation + * Copyright (C) 2018-2021 Intel Corporation */ #include "iwl-trans.h" #include "iwl-fh.h" @@ -240,7 +240,6 @@ int iwl_pcie_ctxt_info_init(struct iwl_trans *trans, /* kick FW self load */ iwl_write64(trans, CSR_CTXT_INFO_BA, trans_pcie->ctxt_info_dma_addr); - iwl_write_prph(trans, UREG_CPU_INIT_RUN, 1); /* Context info will be released upon alive or failure to get one */ diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c index ffaf973dae94..558a0b2ef0fc 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c @@ -592,6 +592,7 @@ static const struct iwl_dev_info iwl_dev_info_table[] = { IWL_DEV_INFO(0x4DF0, 0x1652, killer1650i_2ax_cfg_qu_b0_hr_b0, NULL), IWL_DEV_INFO(0x4DF0, 0x2074, iwl_ax201_cfg_qu_hr, NULL), IWL_DEV_INFO(0x4DF0, 0x4070, iwl_ax201_cfg_qu_hr, NULL), + IWL_DEV_INFO(0x4DF0, 0x6074, iwl_ax201_cfg_qu_hr, NULL), /* So with HR */ IWL_DEV_INFO(0x2725, 0x0090, iwlax211_2ax_cfg_so_gf_a0, NULL), @@ -1040,7 +1041,31 @@ static const struct iwl_dev_info iwl_dev_info_table[] = { IWL_CFG_MAC_TYPE_SO, IWL_CFG_ANY, IWL_CFG_RF_TYPE_HR2, IWL_CFG_ANY, IWL_CFG_160, IWL_CFG_ANY, IWL_CFG_NO_CDB, - iwl_cfg_so_a0_hr_a0, iwl_ax201_name) + iwl_cfg_so_a0_hr_a0, iwl_ax201_name), + +/* So-F with Hr */ + _IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY, + IWL_CFG_MAC_TYPE_SOF, IWL_CFG_ANY, + IWL_CFG_RF_TYPE_HR2, IWL_CFG_ANY, + IWL_CFG_NO_160, IWL_CFG_ANY, IWL_CFG_NO_CDB, + iwl_cfg_so_a0_hr_a0, iwl_ax203_name), + _IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY, + IWL_CFG_MAC_TYPE_SOF, IWL_CFG_ANY, + IWL_CFG_RF_TYPE_HR1, IWL_CFG_ANY, + IWL_CFG_160, IWL_CFG_ANY, IWL_CFG_NO_CDB, + iwl_cfg_so_a0_hr_a0, iwl_ax101_name), + _IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY, + IWL_CFG_MAC_TYPE_SOF, IWL_CFG_ANY, + IWL_CFG_RF_TYPE_HR2, IWL_CFG_ANY, + IWL_CFG_160, IWL_CFG_ANY, IWL_CFG_NO_CDB, + iwl_cfg_so_a0_hr_a0, iwl_ax201_name), + +/* So-F with Gf */ + _IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY, + IWL_CFG_MAC_TYPE_SOF, IWL_CFG_ANY, + IWL_CFG_RF_TYPE_GF, IWL_CFG_ANY, + IWL_CFG_160, IWL_CFG_ANY, IWL_CFG_NO_CDB, + iwlax211_2ax_cfg_so_gf_a0, iwl_ax211_name), #endif /* CONFIG_IWLMVM */ }; diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/trans-gen2.c b/drivers/net/wireless/intel/iwlwifi/pcie/trans-gen2.c index 497ef3405da3..94ffc1ae484d 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/trans-gen2.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/trans-gen2.c @@ -266,6 +266,34 @@ void iwl_trans_pcie_gen2_fw_alive(struct iwl_trans *trans, u32 scd_addr) mutex_unlock(&trans_pcie->mutex); } +static void iwl_pcie_set_ltr(struct iwl_trans *trans) +{ + u32 ltr_val = CSR_LTR_LONG_VAL_AD_NO_SNOOP_REQ | + u32_encode_bits(CSR_LTR_LONG_VAL_AD_SCALE_USEC, + CSR_LTR_LONG_VAL_AD_NO_SNOOP_SCALE) | + u32_encode_bits(250, + CSR_LTR_LONG_VAL_AD_NO_SNOOP_VAL) | + CSR_LTR_LONG_VAL_AD_SNOOP_REQ | + u32_encode_bits(CSR_LTR_LONG_VAL_AD_SCALE_USEC, + CSR_LTR_LONG_VAL_AD_SNOOP_SCALE) | + u32_encode_bits(250, CSR_LTR_LONG_VAL_AD_SNOOP_VAL); + + /* + * To workaround hardware latency issues during the boot process, + * initialize the LTR to ~250 usec (see ltr_val above). + * The firmware initializes this again later (to a smaller value). + */ + if ((trans->trans_cfg->device_family == IWL_DEVICE_FAMILY_AX210 || + trans->trans_cfg->device_family == IWL_DEVICE_FAMILY_22000) && + !trans->trans_cfg->integrated) { + iwl_write32(trans, CSR_LTR_LONG_VAL_AD, ltr_val); + } else if (trans->trans_cfg->integrated && + trans->trans_cfg->device_family == IWL_DEVICE_FAMILY_22000) { + iwl_write_prph(trans, HPM_MAC_LTR_CSR, HPM_MAC_LRT_ENABLE_ALL); + iwl_write_prph(trans, HPM_UMAC_LTR, ltr_val); + } +} + int iwl_trans_pcie_gen2_start_fw(struct iwl_trans *trans, const struct fw_img *fw, bool run_in_rfkill) { @@ -332,6 +360,13 @@ int iwl_trans_pcie_gen2_start_fw(struct iwl_trans *trans, if (ret) goto out; + iwl_pcie_set_ltr(trans); + + if (trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_AX210) + iwl_write_umac_prph(trans, UREG_CPU_INIT_RUN, 1); + else + iwl_write_prph(trans, UREG_CPU_INIT_RUN, 1); + /* re-check RF-Kill state since we may have missed the interrupt */ hw_rfkill = iwl_pcie_check_hw_rf_kill(trans); if (hw_rfkill && !run_in_rfkill) diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/tx.c b/drivers/net/wireless/intel/iwlwifi/pcie/tx.c index 381e8f90b6f2..7ae32491b5da 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/tx.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/tx.c @@ -928,6 +928,7 @@ int iwl_pcie_enqueue_hcmd(struct iwl_trans *trans, u32 cmd_pos; const u8 *cmddata[IWL_MAX_CMD_TBS_PER_TFD]; u16 cmdlen[IWL_MAX_CMD_TBS_PER_TFD]; + unsigned long flags; if (WARN(!trans->wide_cmd_header && group_id > IWL_ALWAYS_LONG_GROUP, @@ -1011,10 +1012,10 @@ int iwl_pcie_enqueue_hcmd(struct iwl_trans *trans, goto free_dup_buf; } - spin_lock_bh(&txq->lock); + spin_lock_irqsave(&txq->lock, flags); if (iwl_txq_space(trans, txq) < ((cmd->flags & CMD_ASYNC) ? 2 : 1)) { - spin_unlock_bh(&txq->lock); + spin_unlock_irqrestore(&txq->lock, flags); IWL_ERR(trans, "No space in command queue\n"); iwl_op_mode_cmd_queue_full(trans->op_mode); @@ -1174,7 +1175,7 @@ int iwl_pcie_enqueue_hcmd(struct iwl_trans *trans, unlock_reg: spin_unlock(&trans_pcie->reg_lock); out: - spin_unlock_bh(&txq->lock); + spin_unlock_irqrestore(&txq->lock, flags); free_dup_buf: if (idx < 0) kfree(dup_buf); diff --git a/drivers/net/wireless/intersil/hostap/hostap_cs.c b/drivers/net/wireless/intersil/hostap/hostap_cs.c index 1a748670835a..ec7db2badc40 100644 --- a/drivers/net/wireless/intersil/hostap/hostap_cs.c +++ b/drivers/net/wireless/intersil/hostap/hostap_cs.c @@ -26,7 +26,6 @@ static char *dev_info = "hostap_cs"; MODULE_AUTHOR("Jouni Malinen"); MODULE_DESCRIPTION("Support for Intersil Prism2-based 802.11 wireless LAN " "cards (PC Card)."); -MODULE_SUPPORTED_DEVICE("Intersil Prism2-based WLAN cards (PC Card)"); MODULE_LICENSE("GPL"); diff --git a/drivers/net/wireless/intersil/hostap/hostap_pci.c b/drivers/net/wireless/intersil/hostap/hostap_pci.c index 101887e6bd0f..52d77506effd 100644 --- a/drivers/net/wireless/intersil/hostap/hostap_pci.c +++ b/drivers/net/wireless/intersil/hostap/hostap_pci.c @@ -27,7 +27,6 @@ static char *dev_info = "hostap_pci"; MODULE_AUTHOR("Jouni Malinen"); MODULE_DESCRIPTION("Support for Intersil Prism2.5-based 802.11 wireless LAN " "PCI cards."); -MODULE_SUPPORTED_DEVICE("Intersil Prism2.5-based WLAN PCI cards"); MODULE_LICENSE("GPL"); diff --git a/drivers/net/wireless/intersil/hostap/hostap_plx.c b/drivers/net/wireless/intersil/hostap/hostap_plx.c index 841cfc68ce84..58247290fcbc 100644 --- a/drivers/net/wireless/intersil/hostap/hostap_plx.c +++ b/drivers/net/wireless/intersil/hostap/hostap_plx.c @@ -30,7 +30,6 @@ static char *dev_info = "hostap_plx"; MODULE_AUTHOR("Jouni Malinen"); MODULE_DESCRIPTION("Support for Intersil Prism2-based 802.11 wireless LAN " "cards (PLX)."); -MODULE_SUPPORTED_DEVICE("Intersil Prism2-based WLAN cards (PLX)"); MODULE_LICENSE("GPL"); diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/regs.h b/drivers/net/wireless/mediatek/mt76/mt7921/regs.h index 18980bb32dee..6dad7f6ab09d 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7921/regs.h +++ b/drivers/net/wireless/mediatek/mt76/mt7921/regs.h @@ -135,10 +135,10 @@ #define MT_WTBLON_TOP_BASE 0x34000 #define MT_WTBLON_TOP(ofs) (MT_WTBLON_TOP_BASE + (ofs)) -#define MT_WTBLON_TOP_WDUCR MT_WTBLON_TOP(0x0) +#define MT_WTBLON_TOP_WDUCR MT_WTBLON_TOP(0x200) #define MT_WTBLON_TOP_WDUCR_GROUP GENMASK(2, 0) -#define MT_WTBL_UPDATE MT_WTBLON_TOP(0x030) +#define MT_WTBL_UPDATE MT_WTBLON_TOP(0x230) #define MT_WTBL_UPDATE_WLAN_IDX GENMASK(9, 0) #define MT_WTBL_UPDATE_ADM_COUNT_CLEAR BIT(12) #define MT_WTBL_UPDATE_BUSY BIT(31) diff --git a/drivers/net/wireless/ralink/rt2x00/rt2400pci.c b/drivers/net/wireless/ralink/rt2x00/rt2400pci.c index 8f860c14da58..dec6ffdf07c4 100644 --- a/drivers/net/wireless/ralink/rt2x00/rt2400pci.c +++ b/drivers/net/wireless/ralink/rt2x00/rt2400pci.c @@ -1821,7 +1821,6 @@ static const struct pci_device_id rt2400pci_device_table[] = { MODULE_AUTHOR(DRV_PROJECT); MODULE_VERSION(DRV_VERSION); MODULE_DESCRIPTION("Ralink RT2400 PCI & PCMCIA Wireless LAN driver."); -MODULE_SUPPORTED_DEVICE("Ralink RT2460 PCI & PCMCIA chipset based cards"); MODULE_DEVICE_TABLE(pci, rt2400pci_device_table); MODULE_LICENSE("GPL"); diff --git a/drivers/net/wireless/ralink/rt2x00/rt2500pci.c b/drivers/net/wireless/ralink/rt2x00/rt2500pci.c index e940443c52ad..8faa0a80e73a 100644 --- a/drivers/net/wireless/ralink/rt2x00/rt2500pci.c +++ b/drivers/net/wireless/ralink/rt2x00/rt2500pci.c @@ -2119,7 +2119,6 @@ static const struct pci_device_id rt2500pci_device_table[] = { MODULE_AUTHOR(DRV_PROJECT); MODULE_VERSION(DRV_VERSION); MODULE_DESCRIPTION("Ralink RT2500 PCI & PCMCIA Wireless LAN driver."); -MODULE_SUPPORTED_DEVICE("Ralink RT2560 PCI & PCMCIA chipset based cards"); MODULE_DEVICE_TABLE(pci, rt2500pci_device_table); MODULE_LICENSE("GPL"); diff --git a/drivers/net/wireless/ralink/rt2x00/rt2500usb.c b/drivers/net/wireless/ralink/rt2x00/rt2500usb.c index fce05fc88aaf..bb5ed6630645 100644 --- a/drivers/net/wireless/ralink/rt2x00/rt2500usb.c +++ b/drivers/net/wireless/ralink/rt2x00/rt2500usb.c @@ -1956,7 +1956,6 @@ static const struct usb_device_id rt2500usb_device_table[] = { MODULE_AUTHOR(DRV_PROJECT); MODULE_VERSION(DRV_VERSION); MODULE_DESCRIPTION("Ralink RT2500 USB Wireless LAN driver."); -MODULE_SUPPORTED_DEVICE("Ralink RT2570 USB chipset based cards"); MODULE_DEVICE_TABLE(usb, rt2500usb_device_table); MODULE_LICENSE("GPL"); diff --git a/drivers/net/wireless/ralink/rt2x00/rt2800pci.c b/drivers/net/wireless/ralink/rt2x00/rt2800pci.c index 9a33baaa6184..1fde0e767ce3 100644 --- a/drivers/net/wireless/ralink/rt2x00/rt2800pci.c +++ b/drivers/net/wireless/ralink/rt2x00/rt2800pci.c @@ -439,7 +439,6 @@ static const struct pci_device_id rt2800pci_device_table[] = { MODULE_AUTHOR(DRV_PROJECT); MODULE_VERSION(DRV_VERSION); MODULE_DESCRIPTION("Ralink RT2800 PCI & PCMCIA Wireless LAN driver."); -MODULE_SUPPORTED_DEVICE("Ralink RT2860 PCI & PCMCIA chipset based cards"); MODULE_FIRMWARE(FIRMWARE_RT2860); MODULE_DEVICE_TABLE(pci, rt2800pci_device_table); MODULE_LICENSE("GPL"); diff --git a/drivers/net/wireless/ralink/rt2x00/rt2800usb.c b/drivers/net/wireless/ralink/rt2x00/rt2800usb.c index 36ac18ca8082..b5c67f656cfd 100644 --- a/drivers/net/wireless/ralink/rt2x00/rt2800usb.c +++ b/drivers/net/wireless/ralink/rt2x00/rt2800usb.c @@ -1248,7 +1248,6 @@ static const struct usb_device_id rt2800usb_device_table[] = { MODULE_AUTHOR(DRV_PROJECT); MODULE_VERSION(DRV_VERSION); MODULE_DESCRIPTION("Ralink RT2800 USB Wireless LAN driver."); -MODULE_SUPPORTED_DEVICE("Ralink RT2870 USB chipset based cards"); MODULE_DEVICE_TABLE(usb, rt2800usb_device_table); MODULE_FIRMWARE(FIRMWARE_RT2870); MODULE_LICENSE("GPL"); diff --git a/drivers/net/wireless/ralink/rt2x00/rt61pci.c b/drivers/net/wireless/ralink/rt2x00/rt61pci.c index 02da5dd37ddd..82cfc2aadc2b 100644 --- a/drivers/net/wireless/ralink/rt2x00/rt61pci.c +++ b/drivers/net/wireless/ralink/rt2x00/rt61pci.c @@ -2993,8 +2993,6 @@ static const struct pci_device_id rt61pci_device_table[] = { MODULE_AUTHOR(DRV_PROJECT); MODULE_VERSION(DRV_VERSION); MODULE_DESCRIPTION("Ralink RT61 PCI & PCMCIA Wireless LAN driver."); -MODULE_SUPPORTED_DEVICE("Ralink RT2561, RT2561s & RT2661 " - "PCI & PCMCIA chipset based cards"); MODULE_DEVICE_TABLE(pci, rt61pci_device_table); MODULE_FIRMWARE(FIRMWARE_RT2561); MODULE_FIRMWARE(FIRMWARE_RT2561s); diff --git a/drivers/net/wireless/ralink/rt2x00/rt73usb.c b/drivers/net/wireless/ralink/rt2x00/rt73usb.c index e69793773d87..5ff2c740c3ea 100644 --- a/drivers/net/wireless/ralink/rt2x00/rt73usb.c +++ b/drivers/net/wireless/ralink/rt2x00/rt73usb.c @@ -2513,7 +2513,6 @@ static const struct usb_device_id rt73usb_device_table[] = { MODULE_AUTHOR(DRV_PROJECT); MODULE_VERSION(DRV_VERSION); MODULE_DESCRIPTION("Ralink RT73 USB Wireless LAN driver."); -MODULE_SUPPORTED_DEVICE("Ralink RT2571W & RT2671 USB chipset based cards"); MODULE_DEVICE_TABLE(usb, rt73usb_device_table); MODULE_FIRMWARE(FIRMWARE_RT2571); MODULE_LICENSE("GPL"); diff --git a/drivers/net/wireless/rsi/rsi_91x_main.c b/drivers/net/wireless/rsi/rsi_91x_main.c index 9a3d2439a8e7..d98483298555 100644 --- a/drivers/net/wireless/rsi/rsi_91x_main.c +++ b/drivers/net/wireless/rsi/rsi_91x_main.c @@ -441,6 +441,5 @@ module_init(rsi_91x_hal_module_init); module_exit(rsi_91x_hal_module_exit); MODULE_AUTHOR("Redpine Signals Inc"); MODULE_DESCRIPTION("Station driver for RSI 91x devices"); -MODULE_SUPPORTED_DEVICE("RSI-91x"); MODULE_VERSION("0.1"); MODULE_LICENSE("Dual BSD/GPL"); diff --git a/drivers/net/wireless/rsi/rsi_91x_sdio.c b/drivers/net/wireless/rsi/rsi_91x_sdio.c index 592e9dadcb55..fe0287b22a25 100644 --- a/drivers/net/wireless/rsi/rsi_91x_sdio.c +++ b/drivers/net/wireless/rsi/rsi_91x_sdio.c @@ -1571,7 +1571,6 @@ module_exit(rsi_module_exit); MODULE_AUTHOR("Redpine Signals Inc"); MODULE_DESCRIPTION("Common SDIO layer for RSI drivers"); -MODULE_SUPPORTED_DEVICE("RSI-91x"); MODULE_DEVICE_TABLE(sdio, rsi_dev_table); MODULE_FIRMWARE(FIRMWARE_RSI9113); MODULE_VERSION("0.1"); diff --git a/drivers/net/wireless/rsi/rsi_91x_usb.c b/drivers/net/wireless/rsi/rsi_91x_usb.c index a4a533c2a783..3fbe2a3c1455 100644 --- a/drivers/net/wireless/rsi/rsi_91x_usb.c +++ b/drivers/net/wireless/rsi/rsi_91x_usb.c @@ -928,7 +928,6 @@ module_usb_driver(rsi_driver); MODULE_AUTHOR("Redpine Signals Inc"); MODULE_DESCRIPTION("Common USB layer for RSI drivers"); -MODULE_SUPPORTED_DEVICE("RSI-91x"); MODULE_DEVICE_TABLE(usb, rsi_dev_table); MODULE_FIRMWARE(FIRMWARE_RSI9113); MODULE_VERSION("0.1"); diff --git a/drivers/net/wireless/virt_wifi.c b/drivers/net/wireless/virt_wifi.c index c878097f0dda..1df959532c7d 100644 --- a/drivers/net/wireless/virt_wifi.c +++ b/drivers/net/wireless/virt_wifi.c @@ -12,6 +12,7 @@ #include <net/cfg80211.h> #include <net/rtnetlink.h> #include <linux/etherdevice.h> +#include <linux/math64.h> #include <linux/module.h> static struct wiphy *common_wiphy; @@ -168,11 +169,11 @@ static void virt_wifi_scan_result(struct work_struct *work) scan_result.work); struct wiphy *wiphy = priv_to_wiphy(priv); struct cfg80211_scan_info scan_info = { .aborted = false }; + u64 tsf = div_u64(ktime_get_boottime_ns(), 1000); informed_bss = cfg80211_inform_bss(wiphy, &channel_5ghz, CFG80211_BSS_FTYPE_PRESP, - fake_router_bssid, - ktime_get_boottime_ns(), + fake_router_bssid, tsf, WLAN_CAPABILITY_ESS, 0, (void *)&ssid, sizeof(ssid), DBM_TO_MBM(-50), GFP_KERNEL); diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index a5653892d773..0896e21642be 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -1226,28 +1226,12 @@ static void nvme_keep_alive_end_io(struct request *rq, blk_status_t status) queue_delayed_work(nvme_wq, &ctrl->ka_work, ctrl->kato * HZ); } -static int nvme_keep_alive(struct nvme_ctrl *ctrl) -{ - struct request *rq; - - rq = nvme_alloc_request(ctrl->admin_q, &ctrl->ka_cmd, - BLK_MQ_REQ_RESERVED); - if (IS_ERR(rq)) - return PTR_ERR(rq); - - rq->timeout = ctrl->kato * HZ; - rq->end_io_data = ctrl; - - blk_execute_rq_nowait(NULL, rq, 0, nvme_keep_alive_end_io); - - return 0; -} - static void nvme_keep_alive_work(struct work_struct *work) { struct nvme_ctrl *ctrl = container_of(to_delayed_work(work), struct nvme_ctrl, ka_work); bool comp_seen = ctrl->comp_seen; + struct request *rq; if ((ctrl->ctratt & NVME_CTRL_ATTR_TBKAS) && comp_seen) { dev_dbg(ctrl->device, @@ -1257,12 +1241,18 @@ static void nvme_keep_alive_work(struct work_struct *work) return; } - if (nvme_keep_alive(ctrl)) { + rq = nvme_alloc_request(ctrl->admin_q, &ctrl->ka_cmd, + BLK_MQ_REQ_RESERVED | BLK_MQ_REQ_NOWAIT); + if (IS_ERR(rq)) { /* allocation failure, reset the controller */ - dev_err(ctrl->device, "keep-alive failed\n"); + dev_err(ctrl->device, "keep-alive failed: %ld\n", PTR_ERR(rq)); nvme_reset_ctrl(ctrl); return; } + + rq->timeout = ctrl->kato * HZ; + rq->end_io_data = ctrl; + blk_execute_rq_nowait(NULL, rq, 0, nvme_keep_alive_end_io); } static void nvme_start_keep_alive(struct nvme_ctrl *ctrl) @@ -1964,30 +1954,18 @@ static void nvme_config_discard(struct gendisk *disk, struct nvme_ns *ns) blk_queue_max_write_zeroes_sectors(queue, UINT_MAX); } -static void nvme_config_write_zeroes(struct gendisk *disk, struct nvme_ns *ns) +/* + * Even though NVMe spec explicitly states that MDTS is not applicable to the + * write-zeroes, we are cautious and limit the size to the controllers + * max_hw_sectors value, which is based on the MDTS field and possibly other + * limiting factors. + */ +static void nvme_config_write_zeroes(struct request_queue *q, + struct nvme_ctrl *ctrl) { - u64 max_blocks; - - if (!(ns->ctrl->oncs & NVME_CTRL_ONCS_WRITE_ZEROES) || - (ns->ctrl->quirks & NVME_QUIRK_DISABLE_WRITE_ZEROES)) - return; - /* - * Even though NVMe spec explicitly states that MDTS is not - * applicable to the write-zeroes:- "The restriction does not apply to - * commands that do not transfer data between the host and the - * controller (e.g., Write Uncorrectable ro Write Zeroes command).". - * In order to be more cautious use controller's max_hw_sectors value - * to configure the maximum sectors for the write-zeroes which is - * configured based on the controller's MDTS field in the - * nvme_init_identify() if available. - */ - if (ns->ctrl->max_hw_sectors == UINT_MAX) - max_blocks = (u64)USHRT_MAX + 1; - else - max_blocks = ns->ctrl->max_hw_sectors + 1; - - blk_queue_max_write_zeroes_sectors(disk->queue, - nvme_lba_to_sect(ns, max_blocks)); + if ((ctrl->oncs & NVME_CTRL_ONCS_WRITE_ZEROES) && + !(ctrl->quirks & NVME_QUIRK_DISABLE_WRITE_ZEROES)) + blk_queue_max_write_zeroes_sectors(q, ctrl->max_hw_sectors); } static bool nvme_ns_ids_valid(struct nvme_ns_ids *ids) @@ -2159,7 +2137,7 @@ static void nvme_update_disk_info(struct gendisk *disk, set_capacity_and_notify(disk, capacity); nvme_config_discard(disk, ns); - nvme_config_write_zeroes(disk, ns); + nvme_config_write_zeroes(disk->queue, ns->ctrl); set_disk_ro(disk, (id->nsattr & NVME_NS_ATTR_RO) || test_bit(NVME_NS_FORCE_RO, &ns->flags)); diff --git a/drivers/nvme/host/fabrics.h b/drivers/nvme/host/fabrics.h index 733010d2eafd..888b108d87a4 100644 --- a/drivers/nvme/host/fabrics.h +++ b/drivers/nvme/host/fabrics.h @@ -19,6 +19,13 @@ #define NVMF_DEF_FAIL_FAST_TMO -1 /* + * Reserved one command for internal usage. This command is used for sending + * the connect command, as well as for the keep alive command on the admin + * queue once live. + */ +#define NVMF_RESERVED_TAGS 1 + +/* * Define a host as seen by the target. We allocate one at boot, but also * allow the override it when creating controllers. This is both to provide * persistence of the Host NQN over multiple boots, and to allow using diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index 73d073748389..6ffa8de2a0d7 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -2863,7 +2863,7 @@ nvme_fc_create_io_queues(struct nvme_fc_ctrl *ctrl) memset(&ctrl->tag_set, 0, sizeof(ctrl->tag_set)); ctrl->tag_set.ops = &nvme_fc_mq_ops; ctrl->tag_set.queue_depth = ctrl->ctrl.opts->queue_size; - ctrl->tag_set.reserved_tags = 1; /* fabric connect */ + ctrl->tag_set.reserved_tags = NVMF_RESERVED_TAGS; ctrl->tag_set.numa_node = ctrl->ctrl.numa_node; ctrl->tag_set.flags = BLK_MQ_F_SHOULD_MERGE; ctrl->tag_set.cmd_size = @@ -3485,7 +3485,7 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts, memset(&ctrl->admin_tag_set, 0, sizeof(ctrl->admin_tag_set)); ctrl->admin_tag_set.ops = &nvme_fc_admin_mq_ops; ctrl->admin_tag_set.queue_depth = NVME_AQ_MQ_TAG_DEPTH; - ctrl->admin_tag_set.reserved_tags = 2; /* fabric connect + Keep-Alive */ + ctrl->admin_tag_set.reserved_tags = NVMF_RESERVED_TAGS; ctrl->admin_tag_set.numa_node = ctrl->ctrl.numa_node; ctrl->admin_tag_set.cmd_size = struct_size((struct nvme_fcp_op_w_sgl *)NULL, priv, diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index 53ac4d7442ba..be905d4fdb47 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -736,8 +736,11 @@ static int nvme_rdma_alloc_io_queues(struct nvme_rdma_ctrl *ctrl) return ret; ctrl->ctrl.queue_count = nr_io_queues + 1; - if (ctrl->ctrl.queue_count < 2) - return 0; + if (ctrl->ctrl.queue_count < 2) { + dev_err(ctrl->ctrl.device, + "unable to set any I/O queues\n"); + return -ENOMEM; + } dev_info(ctrl->ctrl.device, "creating %d I/O queues.\n", nr_io_queues); @@ -798,7 +801,7 @@ static struct blk_mq_tag_set *nvme_rdma_alloc_tagset(struct nvme_ctrl *nctrl, memset(set, 0, sizeof(*set)); set->ops = &nvme_rdma_admin_mq_ops; set->queue_depth = NVME_AQ_MQ_TAG_DEPTH; - set->reserved_tags = 2; /* connect + keep-alive */ + set->reserved_tags = NVMF_RESERVED_TAGS; set->numa_node = nctrl->numa_node; set->cmd_size = sizeof(struct nvme_rdma_request) + NVME_RDMA_DATA_SGL_SIZE; @@ -811,7 +814,7 @@ static struct blk_mq_tag_set *nvme_rdma_alloc_tagset(struct nvme_ctrl *nctrl, memset(set, 0, sizeof(*set)); set->ops = &nvme_rdma_mq_ops; set->queue_depth = nctrl->sqsize + 1; - set->reserved_tags = 1; /* fabric connect */ + set->reserved_tags = NVMF_RESERVED_TAGS; set->numa_node = nctrl->numa_node; set->flags = BLK_MQ_F_SHOULD_MERGE; set->cmd_size = sizeof(struct nvme_rdma_request) + diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c index 69f59d2c5799..a0f00cb8f9f3 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -287,7 +287,7 @@ static inline void nvme_tcp_queue_request(struct nvme_tcp_request *req, * directly, otherwise queue io_work. Also, only do that if we * are on the same cpu, so we don't introduce contention. */ - if (queue->io_cpu == __smp_processor_id() && + if (queue->io_cpu == raw_smp_processor_id() && sync && empty && mutex_trylock(&queue->send_mutex)) { queue->more_requests = !last; nvme_tcp_send_all(queue); @@ -568,6 +568,13 @@ static int nvme_tcp_setup_h2c_data_pdu(struct nvme_tcp_request *req, req->pdu_len = le32_to_cpu(pdu->r2t_length); req->pdu_sent = 0; + if (unlikely(!req->pdu_len)) { + dev_err(queue->ctrl->ctrl.device, + "req %d r2t len is %u, probably a bug...\n", + rq->tag, req->pdu_len); + return -EPROTO; + } + if (unlikely(req->data_sent + req->pdu_len > req->data_len)) { dev_err(queue->ctrl->ctrl.device, "req %d r2t len %u exceeded data len %u (%zu sent)\n", @@ -1575,7 +1582,7 @@ static struct blk_mq_tag_set *nvme_tcp_alloc_tagset(struct nvme_ctrl *nctrl, memset(set, 0, sizeof(*set)); set->ops = &nvme_tcp_admin_mq_ops; set->queue_depth = NVME_AQ_MQ_TAG_DEPTH; - set->reserved_tags = 2; /* connect + keep-alive */ + set->reserved_tags = NVMF_RESERVED_TAGS; set->numa_node = nctrl->numa_node; set->flags = BLK_MQ_F_BLOCKING; set->cmd_size = sizeof(struct nvme_tcp_request); @@ -1587,7 +1594,7 @@ static struct blk_mq_tag_set *nvme_tcp_alloc_tagset(struct nvme_ctrl *nctrl, memset(set, 0, sizeof(*set)); set->ops = &nvme_tcp_mq_ops; set->queue_depth = nctrl->sqsize + 1; - set->reserved_tags = 1; /* fabric connect */ + set->reserved_tags = NVMF_RESERVED_TAGS; set->numa_node = nctrl->numa_node; set->flags = BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_BLOCKING; set->cmd_size = sizeof(struct nvme_tcp_request); @@ -1745,8 +1752,11 @@ static int nvme_tcp_alloc_io_queues(struct nvme_ctrl *ctrl) return ret; ctrl->queue_count = nr_io_queues + 1; - if (ctrl->queue_count < 2) - return 0; + if (ctrl->queue_count < 2) { + dev_err(ctrl->device, + "unable to set any I/O queues\n"); + return -ENOMEM; + } dev_info(ctrl->device, "creating %d I/O queues.\n", nr_io_queues); diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c index be6fcdaf51a7..a027433b8be8 100644 --- a/drivers/nvme/target/core.c +++ b/drivers/nvme/target/core.c @@ -1118,9 +1118,20 @@ static void nvmet_start_ctrl(struct nvmet_ctrl *ctrl) { lockdep_assert_held(&ctrl->lock); - if (nvmet_cc_iosqes(ctrl->cc) != NVME_NVM_IOSQES || - nvmet_cc_iocqes(ctrl->cc) != NVME_NVM_IOCQES || - nvmet_cc_mps(ctrl->cc) != 0 || + /* + * Only I/O controllers should verify iosqes,iocqes. + * Strictly speaking, the spec says a discovery controller + * should verify iosqes,iocqes are zeroed, however that + * would break backwards compatibility, so don't enforce it. + */ + if (ctrl->subsys->type != NVME_NQN_DISC && + (nvmet_cc_iosqes(ctrl->cc) != NVME_NVM_IOSQES || + nvmet_cc_iocqes(ctrl->cc) != NVME_NVM_IOCQES)) { + ctrl->csts = NVME_CSTS_CFS; + return; + } + + if (nvmet_cc_mps(ctrl->cc) != 0 || nvmet_cc_ams(ctrl->cc) != 0 || nvmet_cc_css(ctrl->cc) != 0) { ctrl->csts = NVME_CSTS_CFS; diff --git a/drivers/nvme/target/loop.c b/drivers/nvme/target/loop.c index cb6f86572b24..3e189e753bcf 100644 --- a/drivers/nvme/target/loop.c +++ b/drivers/nvme/target/loop.c @@ -349,7 +349,7 @@ static int nvme_loop_configure_admin_queue(struct nvme_loop_ctrl *ctrl) memset(&ctrl->admin_tag_set, 0, sizeof(ctrl->admin_tag_set)); ctrl->admin_tag_set.ops = &nvme_loop_admin_mq_ops; ctrl->admin_tag_set.queue_depth = NVME_AQ_MQ_TAG_DEPTH; - ctrl->admin_tag_set.reserved_tags = 2; /* connect + keep-alive */ + ctrl->admin_tag_set.reserved_tags = NVMF_RESERVED_TAGS; ctrl->admin_tag_set.numa_node = ctrl->ctrl.numa_node; ctrl->admin_tag_set.cmd_size = sizeof(struct nvme_loop_iod) + NVME_INLINE_SG_CNT * sizeof(struct scatterlist); @@ -520,7 +520,7 @@ static int nvme_loop_create_io_queues(struct nvme_loop_ctrl *ctrl) memset(&ctrl->tag_set, 0, sizeof(ctrl->tag_set)); ctrl->tag_set.ops = &nvme_loop_mq_ops; ctrl->tag_set.queue_depth = ctrl->ctrl.opts->queue_size; - ctrl->tag_set.reserved_tags = 1; /* fabric connect */ + ctrl->tag_set.reserved_tags = NVMF_RESERVED_TAGS; ctrl->tag_set.numa_node = ctrl->ctrl.numa_node; ctrl->tag_set.flags = BLK_MQ_F_SHOULD_MERGE; ctrl->tag_set.cmd_size = sizeof(struct nvme_loop_iod) + diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c index 8b0485ada315..d658c6e8263a 100644 --- a/drivers/nvme/target/tcp.c +++ b/drivers/nvme/target/tcp.c @@ -1098,11 +1098,11 @@ static int nvmet_tcp_try_recv_data(struct nvmet_tcp_queue *queue) cmd->rbytes_done += ret; } + nvmet_tcp_unmap_pdu_iovec(cmd); if (queue->data_digest) { nvmet_tcp_prep_recv_ddgst(cmd); return 0; } - nvmet_tcp_unmap_pdu_iovec(cmd); if (!(cmd->flags & NVMET_TCP_F_INIT_FAILED) && cmd->rbytes_done == cmd->req.transfer_len) { diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c index dcc1dd96911a..adb26aff481d 100644 --- a/drivers/of/fdt.c +++ b/drivers/of/fdt.c @@ -205,7 +205,7 @@ static void populate_properties(const void *blob, *pprev = NULL; } -static bool populate_node(const void *blob, +static int populate_node(const void *blob, int offset, void **mem, struct device_node *dad, @@ -214,24 +214,24 @@ static bool populate_node(const void *blob, { struct device_node *np; const char *pathp; - unsigned int l, allocl; + int len; - pathp = fdt_get_name(blob, offset, &l); + pathp = fdt_get_name(blob, offset, &len); if (!pathp) { *pnp = NULL; - return false; + return len; } - allocl = ++l; + len++; - np = unflatten_dt_alloc(mem, sizeof(struct device_node) + allocl, + np = unflatten_dt_alloc(mem, sizeof(struct device_node) + len, __alignof__(struct device_node)); if (!dryrun) { char *fn; of_node_init(np); np->full_name = fn = ((char *)np) + sizeof(*np); - memcpy(fn, pathp, l); + memcpy(fn, pathp, len); if (dad != NULL) { np->parent = dad; @@ -295,6 +295,7 @@ static int unflatten_dt_nodes(const void *blob, struct device_node *nps[FDT_MAX_DEPTH]; void *base = mem; bool dryrun = !base; + int ret; if (nodepp) *nodepp = NULL; @@ -322,9 +323,10 @@ static int unflatten_dt_nodes(const void *blob, !of_fdt_device_is_available(blob, offset)) continue; - if (!populate_node(blob, offset, &mem, nps[depth], - &nps[depth+1], dryrun)) - return mem - base; + ret = populate_node(blob, offset, &mem, nps[depth], + &nps[depth+1], dryrun); + if (ret < 0) + return ret; if (!dryrun && nodepp && !*nodepp) *nodepp = nps[depth+1]; @@ -372,6 +374,10 @@ void *__unflatten_device_tree(const void *blob, { int size; void *mem; + int ret; + + if (mynodes) + *mynodes = NULL; pr_debug(" -> unflatten_device_tree()\n"); @@ -392,7 +398,7 @@ void *__unflatten_device_tree(const void *blob, /* First pass, scan for size */ size = unflatten_dt_nodes(blob, NULL, dad, NULL); - if (size < 0) + if (size <= 0) return NULL; size = ALIGN(size, 4); @@ -410,12 +416,16 @@ void *__unflatten_device_tree(const void *blob, pr_debug(" unflattening %p...\n", mem); /* Second pass, do actual unflattening */ - unflatten_dt_nodes(blob, mem, dad, mynodes); + ret = unflatten_dt_nodes(blob, mem, dad, mynodes); + if (be32_to_cpup(mem + size) != 0xdeadbeef) pr_warn("End of tree marker overwritten: %08x\n", be32_to_cpup(mem + size)); - if (detached && mynodes) { + if (ret <= 0) + return NULL; + + if (detached && mynodes && *mynodes) { of_node_set_flag(*mynodes, OF_DETACHED); pr_debug("unflattened tree is detached\n"); } diff --git a/drivers/of/of_private.h b/drivers/of/of_private.h index d9e6a324de0a..d717efbd637d 100644 --- a/drivers/of/of_private.h +++ b/drivers/of/of_private.h @@ -8,6 +8,8 @@ * Copyright (C) 1996-2005 Paul Mackerras. */ +#define FDT_ALIGN_SIZE 8 + /** * struct alias_prop - Alias property in 'aliases' node * @link: List node to link the structure in aliases_lookup list diff --git a/drivers/of/overlay.c b/drivers/of/overlay.c index 50bbe0edf538..23effe5e50ec 100644 --- a/drivers/of/overlay.c +++ b/drivers/of/overlay.c @@ -57,7 +57,7 @@ struct fragment { * struct overlay_changeset * @id: changeset identifier * @ovcs_list: list on which we are located - * @fdt: FDT that was unflattened to create @overlay_tree + * @fdt: base of memory allocated to hold aligned FDT that was unflattened to create @overlay_tree * @overlay_tree: expanded device tree that contains the fragment nodes * @count: count of fragment structures * @fragments: fragment nodes in the overlay expanded device tree @@ -719,8 +719,8 @@ static struct device_node *find_target(struct device_node *info_node) /** * init_overlay_changeset() - initialize overlay changeset from overlay tree * @ovcs: Overlay changeset to build - * @fdt: the FDT that was unflattened to create @tree - * @tree: Contains all the overlay fragments and overlay fixup nodes + * @fdt: base of memory allocated to hold aligned FDT that was unflattened to create @tree + * @tree: Contains the overlay fragments and overlay fixup nodes * * Initialize @ovcs. Populate @ovcs->fragments with node information from * the top level of @tree. The relevant top level nodes are the fragment @@ -873,7 +873,7 @@ static void free_overlay_changeset(struct overlay_changeset *ovcs) * internal documentation * * of_overlay_apply() - Create and apply an overlay changeset - * @fdt: the FDT that was unflattened to create @tree + * @fdt: base of memory allocated to hold the aligned FDT * @tree: Expanded overlay device tree * @ovcs_id: Pointer to overlay changeset id * @@ -953,7 +953,9 @@ static int of_overlay_apply(const void *fdt, struct device_node *tree, /* * after overlay_notify(), ovcs->overlay_tree related pointers may have * leaked to drivers, so can not kfree() tree, aka ovcs->overlay_tree; - * and can not free fdt, aka ovcs->fdt + * and can not free memory containing aligned fdt. The aligned fdt + * is contained within the memory at ovcs->fdt, possibly at an offset + * from ovcs->fdt. */ ret = overlay_notify(ovcs, OF_OVERLAY_PRE_APPLY); if (ret) { @@ -1014,10 +1016,11 @@ out: int of_overlay_fdt_apply(const void *overlay_fdt, u32 overlay_fdt_size, int *ovcs_id) { - const void *new_fdt; + void *new_fdt; + void *new_fdt_align; int ret; u32 size; - struct device_node *overlay_root; + struct device_node *overlay_root = NULL; *ovcs_id = 0; ret = 0; @@ -1036,11 +1039,14 @@ int of_overlay_fdt_apply(const void *overlay_fdt, u32 overlay_fdt_size, * Must create permanent copy of FDT because of_fdt_unflatten_tree() * will create pointers to the passed in FDT in the unflattened tree. */ - new_fdt = kmemdup(overlay_fdt, size, GFP_KERNEL); + new_fdt = kmalloc(size + FDT_ALIGN_SIZE, GFP_KERNEL); if (!new_fdt) return -ENOMEM; - of_fdt_unflatten_tree(new_fdt, NULL, &overlay_root); + new_fdt_align = PTR_ALIGN(new_fdt, FDT_ALIGN_SIZE); + memcpy(new_fdt_align, overlay_fdt, size); + + of_fdt_unflatten_tree(new_fdt_align, NULL, &overlay_root); if (!overlay_root) { pr_err("unable to unflatten overlay_fdt\n"); ret = -EINVAL; diff --git a/drivers/of/property.c b/drivers/of/property.c index 5036a362f52e..78427c85bef3 100644 --- a/drivers/of/property.c +++ b/drivers/of/property.c @@ -1262,7 +1262,16 @@ DEFINE_SIMPLE_PROP(pinctrl7, "pinctrl-7", NULL) DEFINE_SIMPLE_PROP(pinctrl8, "pinctrl-8", NULL) DEFINE_SUFFIX_PROP(regulators, "-supply", NULL) DEFINE_SUFFIX_PROP(gpio, "-gpio", "#gpio-cells") -DEFINE_SUFFIX_PROP(gpios, "-gpios", "#gpio-cells") + +static struct device_node *parse_gpios(struct device_node *np, + const char *prop_name, int index) +{ + if (!strcmp_suffix(prop_name, ",nr-gpios")) + return NULL; + + return parse_suffix_prop_cells(np, prop_name, index, "-gpios", + "#gpio-cells"); +} static struct device_node *parse_iommu_maps(struct device_node *np, const char *prop_name, int index) diff --git a/drivers/of/unittest.c b/drivers/of/unittest.c index eb100627c186..819a20acaa93 100644 --- a/drivers/of/unittest.c +++ b/drivers/of/unittest.c @@ -22,6 +22,7 @@ #include <linux/slab.h> #include <linux/device.h> #include <linux/platform_device.h> +#include <linux/kernel.h> #include <linux/i2c.h> #include <linux/i2c-mux.h> @@ -1408,7 +1409,8 @@ static void attach_node_and_children(struct device_node *np) static int __init unittest_data_add(void) { void *unittest_data; - struct device_node *unittest_data_node, *np; + void *unittest_data_align; + struct device_node *unittest_data_node = NULL, *np; /* * __dtb_testcases_begin[] and __dtb_testcases_end[] are magically * created by cmd_dt_S_dtb in scripts/Makefile.lib @@ -1417,21 +1419,29 @@ static int __init unittest_data_add(void) extern uint8_t __dtb_testcases_end[]; const int size = __dtb_testcases_end - __dtb_testcases_begin; int rc; + void *ret; if (!size) { - pr_warn("%s: No testcase data to attach; not running tests\n", - __func__); + pr_warn("%s: testcases is empty\n", __func__); return -ENODATA; } /* creating copy */ - unittest_data = kmemdup(__dtb_testcases_begin, size, GFP_KERNEL); + unittest_data = kmalloc(size + FDT_ALIGN_SIZE, GFP_KERNEL); if (!unittest_data) return -ENOMEM; - of_fdt_unflatten_tree(unittest_data, NULL, &unittest_data_node); + unittest_data_align = PTR_ALIGN(unittest_data, FDT_ALIGN_SIZE); + memcpy(unittest_data_align, __dtb_testcases_begin, size); + + ret = of_fdt_unflatten_tree(unittest_data_align, NULL, &unittest_data_node); + if (!ret) { + pr_warn("%s: unflatten testcases tree failed\n", __func__); + kfree(unittest_data); + return -ENODATA; + } if (!unittest_data_node) { - pr_warn("%s: No tree to attach; not running tests\n", __func__); + pr_warn("%s: testcases tree is empty\n", __func__); kfree(unittest_data); return -ENODATA; } diff --git a/drivers/parport/parport_amiga.c b/drivers/parport/parport_amiga.c index 1e88bcfe0d7b..84d5701d606c 100644 --- a/drivers/parport/parport_amiga.c +++ b/drivers/parport/parport_amiga.c @@ -241,6 +241,5 @@ module_platform_driver_probe(amiga_parallel_driver, amiga_parallel_probe); MODULE_AUTHOR("Joerg Dorchain <joerg@dorchain.net>"); MODULE_DESCRIPTION("Parport Driver for Amiga builtin Port"); -MODULE_SUPPORTED_DEVICE("Amiga builtin Parallel Port"); MODULE_LICENSE("GPL"); MODULE_ALIAS("platform:amiga-parallel"); diff --git a/drivers/parport/parport_atari.c b/drivers/parport/parport_atari.c index 2ff0fe053e6e..1623f010cdcc 100644 --- a/drivers/parport/parport_atari.c +++ b/drivers/parport/parport_atari.c @@ -218,7 +218,6 @@ static void __exit parport_atari_exit(void) MODULE_AUTHOR("Andreas Schwab"); MODULE_DESCRIPTION("Parport Driver for Atari builtin Port"); -MODULE_SUPPORTED_DEVICE("Atari builtin Parallel Port"); MODULE_LICENSE("GPL"); module_init(parport_atari_init) diff --git a/drivers/parport/parport_gsc.c b/drivers/parport/parport_gsc.c index 9228e8f90309..1e43b3f399a8 100644 --- a/drivers/parport/parport_gsc.c +++ b/drivers/parport/parport_gsc.c @@ -41,7 +41,6 @@ MODULE_AUTHOR("Helge Deller <deller@gmx.de>"); MODULE_DESCRIPTION("HP-PARISC PC-style parallel port driver"); -MODULE_SUPPORTED_DEVICE("integrated PC-style parallel port"); MODULE_LICENSE("GPL"); diff --git a/drivers/parport/parport_mfc3.c b/drivers/parport/parport_mfc3.c index d6bbe8446301..f4d0da741e85 100644 --- a/drivers/parport/parport_mfc3.c +++ b/drivers/parport/parport_mfc3.c @@ -359,7 +359,6 @@ static void __exit parport_mfc3_exit(void) MODULE_AUTHOR("Joerg Dorchain <joerg@dorchain.net>"); MODULE_DESCRIPTION("Parport Driver for Multiface 3 expansion cards Parallel Port"); -MODULE_SUPPORTED_DEVICE("Multiface 3 Parallel Port"); MODULE_LICENSE("GPL"); module_init(parport_mfc3_init) diff --git a/drivers/parport/parport_sunbpp.c b/drivers/parport/parport_sunbpp.c index e840c1b5ab90..865fc41dbb6c 100644 --- a/drivers/parport/parport_sunbpp.c +++ b/drivers/parport/parport_sunbpp.c @@ -377,6 +377,5 @@ module_platform_driver(bpp_sbus_driver); MODULE_AUTHOR("Derrick J Brashear"); MODULE_DESCRIPTION("Parport Driver for Sparc bidirectional Port"); -MODULE_SUPPORTED_DEVICE("Sparc Bidirectional Parallel Port"); MODULE_VERSION("2.0"); MODULE_LICENSE("GPL"); diff --git a/drivers/pci/hotplug/rpadlpar_sysfs.c b/drivers/pci/hotplug/rpadlpar_sysfs.c index cdbfa5df3a51..dbfa0b55d31a 100644 --- a/drivers/pci/hotplug/rpadlpar_sysfs.c +++ b/drivers/pci/hotplug/rpadlpar_sysfs.c @@ -34,12 +34,11 @@ static ssize_t add_slot_store(struct kobject *kobj, struct kobj_attribute *attr, if (nbytes >= MAX_DRC_NAME_LEN) return 0; - memcpy(drc_name, buf, nbytes); + strscpy(drc_name, buf, nbytes + 1); end = strchr(drc_name, '\n'); - if (!end) - end = &drc_name[nbytes]; - *end = '\0'; + if (end) + *end = '\0'; rc = dlpar_add_slot(drc_name); if (rc) @@ -65,12 +64,11 @@ static ssize_t remove_slot_store(struct kobject *kobj, if (nbytes >= MAX_DRC_NAME_LEN) return 0; - memcpy(drc_name, buf, nbytes); + strscpy(drc_name, buf, nbytes + 1); end = strchr(drc_name, '\n'); - if (!end) - end = &drc_name[nbytes]; - *end = '\0'; + if (end) + *end = '\0'; rc = dlpar_remove_slot(drc_name); if (rc) diff --git a/drivers/pci/hotplug/s390_pci_hpc.c b/drivers/pci/hotplug/s390_pci_hpc.c index c9e790c74051..a047c421debe 100644 --- a/drivers/pci/hotplug/s390_pci_hpc.c +++ b/drivers/pci/hotplug/s390_pci_hpc.c @@ -93,8 +93,9 @@ static int disable_slot(struct hotplug_slot *hotplug_slot) pci_dev_put(pdev); return -EBUSY; } + pci_dev_put(pdev); - zpci_remove_device(zdev); + zpci_remove_device(zdev, false); rc = zpci_disable_device(zdev); if (rc) diff --git a/drivers/pinctrl/intel/pinctrl-intel.c b/drivers/pinctrl/intel/pinctrl-intel.c index 8085782cd8f9..9f3361c13ded 100644 --- a/drivers/pinctrl/intel/pinctrl-intel.c +++ b/drivers/pinctrl/intel/pinctrl-intel.c @@ -1357,6 +1357,7 @@ static int intel_pinctrl_add_padgroups_by_gpps(struct intel_pinctrl *pctrl, gpps[i].gpio_base = 0; break; case INTEL_GPIO_BASE_NOMAP: + break; default: break; } @@ -1393,6 +1394,7 @@ static int intel_pinctrl_add_padgroups_by_size(struct intel_pinctrl *pctrl, gpps[i].size = min(gpp_size, npins); npins -= gpps[i].size; + gpps[i].gpio_base = gpps[i].base; gpps[i].padown_num = padown_num; /* @@ -1491,8 +1493,13 @@ static int intel_pinctrl_probe(struct platform_device *pdev, if (IS_ERR(regs)) return PTR_ERR(regs); - /* Determine community features based on the revision */ + /* + * Determine community features based on the revision. + * A value of all ones means the device is not present. + */ value = readl(regs + REVID); + if (value == ~0u) + return -ENODEV; if (((value & REVID_MASK) >> REVID_SHIFT) >= 0x94) { community->features |= PINCTRL_FEATURE_DEBOUNCE; community->features |= PINCTRL_FEATURE_1K_PD; diff --git a/drivers/pinctrl/pinctrl-microchip-sgpio.c b/drivers/pinctrl/pinctrl-microchip-sgpio.c index f35edb0eac40..c12fa57ebd12 100644 --- a/drivers/pinctrl/pinctrl-microchip-sgpio.c +++ b/drivers/pinctrl/pinctrl-microchip-sgpio.c @@ -572,7 +572,7 @@ static void microchip_sgpio_irq_settype(struct irq_data *data, /* Type value spread over 2 registers sets: low, high bit */ sgpio_clrsetbits(bank->priv, REG_INT_TRIGGER, addr.bit, BIT(addr.port), (!!(type & 0x1)) << addr.port); - sgpio_clrsetbits(bank->priv, REG_INT_TRIGGER + SGPIO_MAX_BITS, addr.bit, + sgpio_clrsetbits(bank->priv, REG_INT_TRIGGER, SGPIO_MAX_BITS + addr.bit, BIT(addr.port), (!!(type & 0x2)) << addr.port); if (type == SGPIO_INT_TRG_LEVEL) diff --git a/drivers/pinctrl/pinctrl-rockchip.c b/drivers/pinctrl/pinctrl-rockchip.c index aa1a1c850d05..53a0badc6b03 100644 --- a/drivers/pinctrl/pinctrl-rockchip.c +++ b/drivers/pinctrl/pinctrl-rockchip.c @@ -3727,12 +3727,15 @@ static int __maybe_unused rockchip_pinctrl_suspend(struct device *dev) static int __maybe_unused rockchip_pinctrl_resume(struct device *dev) { struct rockchip_pinctrl *info = dev_get_drvdata(dev); - int ret = regmap_write(info->regmap_base, RK3288_GRF_GPIO6C_IOMUX, - rk3288_grf_gpio6c_iomux | - GPIO6C6_SEL_WRITE_ENABLE); + int ret; - if (ret) - return ret; + if (info->ctrl->type == RK3288) { + ret = regmap_write(info->regmap_base, RK3288_GRF_GPIO6C_IOMUX, + rk3288_grf_gpio6c_iomux | + GPIO6C6_SEL_WRITE_ENABLE); + if (ret) + return ret; + } return pinctrl_force_default(info->pctl_dev); } diff --git a/drivers/pinctrl/qcom/pinctrl-lpass-lpi.c b/drivers/pinctrl/qcom/pinctrl-lpass-lpi.c index 369ee20a7ea9..2f19ab4db720 100644 --- a/drivers/pinctrl/qcom/pinctrl-lpass-lpi.c +++ b/drivers/pinctrl/qcom/pinctrl-lpass-lpi.c @@ -392,7 +392,7 @@ static int lpi_config_set(struct pinctrl_dev *pctldev, unsigned int group, unsigned long *configs, unsigned int nconfs) { struct lpi_pinctrl *pctrl = dev_get_drvdata(pctldev->dev); - unsigned int param, arg, pullup, strength; + unsigned int param, arg, pullup = LPI_GPIO_BIAS_DISABLE, strength = 2; bool value, output_enabled = false; const struct lpi_pingroup *g; unsigned long sval; diff --git a/drivers/pinctrl/qcom/pinctrl-sc7280.c b/drivers/pinctrl/qcom/pinctrl-sc7280.c index 8daccd530285..9d41abfca37e 100644 --- a/drivers/pinctrl/qcom/pinctrl-sc7280.c +++ b/drivers/pinctrl/qcom/pinctrl-sc7280.c @@ -1439,14 +1439,14 @@ static const struct msm_pingroup sc7280_groups[] = { [172] = PINGROUP(172, qdss, _, _, _, _, _, _, _, _), [173] = PINGROUP(173, qdss, _, _, _, _, _, _, _, _), [174] = PINGROUP(174, qdss, _, _, _, _, _, _, _, _), - [175] = UFS_RESET(ufs_reset, 0x1be000), - [176] = SDC_QDSD_PINGROUP(sdc1_rclk, 0x1b3000, 15, 0), - [177] = SDC_QDSD_PINGROUP(sdc1_clk, 0x1b3000, 13, 6), - [178] = SDC_QDSD_PINGROUP(sdc1_cmd, 0x1b3000, 11, 3), - [179] = SDC_QDSD_PINGROUP(sdc1_data, 0x1b3000, 9, 0), - [180] = SDC_QDSD_PINGROUP(sdc2_clk, 0x1b4000, 14, 6), - [181] = SDC_QDSD_PINGROUP(sdc2_cmd, 0x1b4000, 11, 3), - [182] = SDC_QDSD_PINGROUP(sdc2_data, 0x1b4000, 9, 0), + [175] = UFS_RESET(ufs_reset, 0xbe000), + [176] = SDC_QDSD_PINGROUP(sdc1_rclk, 0xb3004, 0, 6), + [177] = SDC_QDSD_PINGROUP(sdc1_clk, 0xb3000, 13, 6), + [178] = SDC_QDSD_PINGROUP(sdc1_cmd, 0xb3000, 11, 3), + [179] = SDC_QDSD_PINGROUP(sdc1_data, 0xb3000, 9, 0), + [180] = SDC_QDSD_PINGROUP(sdc2_clk, 0xb4000, 14, 6), + [181] = SDC_QDSD_PINGROUP(sdc2_cmd, 0xb4000, 11, 3), + [182] = SDC_QDSD_PINGROUP(sdc2_data, 0xb4000, 9, 0), }; static const struct msm_pinctrl_soc_data sc7280_pinctrl = { diff --git a/drivers/pinctrl/qcom/pinctrl-sdx55.c b/drivers/pinctrl/qcom/pinctrl-sdx55.c index 2b5b0e2b03ad..5aaf57b40407 100644 --- a/drivers/pinctrl/qcom/pinctrl-sdx55.c +++ b/drivers/pinctrl/qcom/pinctrl-sdx55.c @@ -423,7 +423,7 @@ static const char * const gpio_groups[] = { static const char * const qdss_stm_groups[] = { "gpio0", "gpio1", "gpio2", "gpio3", "gpio4", "gpio5", "gpio6", "gpio7", "gpio12", "gpio13", - "gpio14", "gpio15", "gpio16", "gpio17", "gpio18", "gpio19" "gpio20", "gpio21", "gpio22", + "gpio14", "gpio15", "gpio16", "gpio17", "gpio18", "gpio19", "gpio20", "gpio21", "gpio22", "gpio23", "gpio44", "gpio45", "gpio52", "gpio53", "gpio56", "gpio57", "gpio61", "gpio62", "gpio63", "gpio64", "gpio65", "gpio66", }; diff --git a/drivers/platform/x86/Kconfig b/drivers/platform/x86/Kconfig index ad4e630e73e2..461ec61530eb 100644 --- a/drivers/platform/x86/Kconfig +++ b/drivers/platform/x86/Kconfig @@ -1173,15 +1173,20 @@ config INTEL_PMC_CORE depends on PCI help The Intel Platform Controller Hub for Intel Core SoCs provides access - to Power Management Controller registers via a PCI interface. This + to Power Management Controller registers via various interfaces. This driver can utilize debugging capabilities and supported features as - exposed by the Power Management Controller. + exposed by the Power Management Controller. It also may perform some + tasks in the PMC in order to enable transition into the SLPS0 state. + It should be selected on all Intel platforms supported by the driver. Supported features: - SLP_S0_RESIDENCY counter - PCH IP Power Gating status - - LTR Ignore + - LTR Ignore / LTR Show - MPHY/PLL gating status (Sunrisepoint PCH only) + - SLPS0 Debug registers (Cannonlake/Icelake PCH) + - Low Power Mode registers (Tigerlake and beyond) + - PMC quirks as needed to enable SLPS0/S0ix config INTEL_PMT_CLASS tristate diff --git a/drivers/platform/x86/dell/dell-wmi-sysman/enum-attributes.c b/drivers/platform/x86/dell/dell-wmi-sysman/enum-attributes.c index 80f4b7785c6c..091e48c217ed 100644 --- a/drivers/platform/x86/dell/dell-wmi-sysman/enum-attributes.c +++ b/drivers/platform/x86/dell/dell-wmi-sysman/enum-attributes.c @@ -185,5 +185,8 @@ void exit_enum_attributes(void) sysfs_remove_group(wmi_priv.enumeration_data[instance_id].attr_name_kobj, &enumeration_attr_group); } + wmi_priv.enumeration_instances_count = 0; + kfree(wmi_priv.enumeration_data); + wmi_priv.enumeration_data = NULL; } diff --git a/drivers/platform/x86/dell/dell-wmi-sysman/int-attributes.c b/drivers/platform/x86/dell/dell-wmi-sysman/int-attributes.c index 75aedbb733be..8a49ba6e44f9 100644 --- a/drivers/platform/x86/dell/dell-wmi-sysman/int-attributes.c +++ b/drivers/platform/x86/dell/dell-wmi-sysman/int-attributes.c @@ -175,5 +175,8 @@ void exit_int_attributes(void) sysfs_remove_group(wmi_priv.integer_data[instance_id].attr_name_kobj, &integer_attr_group); } + wmi_priv.integer_instances_count = 0; + kfree(wmi_priv.integer_data); + wmi_priv.integer_data = NULL; } diff --git a/drivers/platform/x86/dell/dell-wmi-sysman/passobj-attributes.c b/drivers/platform/x86/dell/dell-wmi-sysman/passobj-attributes.c index 3abcd95477c0..834b3e82ad9f 100644 --- a/drivers/platform/x86/dell/dell-wmi-sysman/passobj-attributes.c +++ b/drivers/platform/x86/dell/dell-wmi-sysman/passobj-attributes.c @@ -183,5 +183,8 @@ void exit_po_attributes(void) sysfs_remove_group(wmi_priv.po_data[instance_id].attr_name_kobj, &po_attr_group); } + wmi_priv.po_instances_count = 0; + kfree(wmi_priv.po_data); + wmi_priv.po_data = NULL; } diff --git a/drivers/platform/x86/dell/dell-wmi-sysman/string-attributes.c b/drivers/platform/x86/dell/dell-wmi-sysman/string-attributes.c index ac75dce88a4c..552537852459 100644 --- a/drivers/platform/x86/dell/dell-wmi-sysman/string-attributes.c +++ b/drivers/platform/x86/dell/dell-wmi-sysman/string-attributes.c @@ -155,5 +155,8 @@ void exit_str_attributes(void) sysfs_remove_group(wmi_priv.str_data[instance_id].attr_name_kobj, &str_attr_group); } + wmi_priv.str_instances_count = 0; + kfree(wmi_priv.str_data); + wmi_priv.str_data = NULL; } diff --git a/drivers/platform/x86/dell/dell-wmi-sysman/sysman.c b/drivers/platform/x86/dell/dell-wmi-sysman/sysman.c index cb81010ba1a2..7410ccae650c 100644 --- a/drivers/platform/x86/dell/dell-wmi-sysman/sysman.c +++ b/drivers/platform/x86/dell/dell-wmi-sysman/sysman.c @@ -210,25 +210,17 @@ static struct kobj_attribute pending_reboot = __ATTR_RO(pending_reboot); */ static int create_attributes_level_sysfs_files(void) { - int ret = sysfs_create_file(&wmi_priv.main_dir_kset->kobj, &reset_bios.attr); + int ret; - if (ret) { - pr_debug("could not create reset_bios file\n"); + ret = sysfs_create_file(&wmi_priv.main_dir_kset->kobj, &reset_bios.attr); + if (ret) return ret; - } ret = sysfs_create_file(&wmi_priv.main_dir_kset->kobj, &pending_reboot.attr); - if (ret) { - pr_debug("could not create changing_pending_reboot file\n"); - sysfs_remove_file(&wmi_priv.main_dir_kset->kobj, &reset_bios.attr); - } - return ret; -} + if (ret) + return ret; -static void release_reset_bios_data(void) -{ - sysfs_remove_file(&wmi_priv.main_dir_kset->kobj, &reset_bios.attr); - sysfs_remove_file(&wmi_priv.main_dir_kset->kobj, &pending_reboot.attr); + return 0; } static ssize_t wmi_sysman_attr_show(struct kobject *kobj, struct attribute *attr, @@ -373,8 +365,6 @@ static void destroy_attribute_objs(struct kset *kset) */ static void release_attributes_data(void) { - release_reset_bios_data(); - mutex_lock(&wmi_priv.mutex); exit_enum_attributes(); exit_int_attributes(); @@ -386,11 +376,13 @@ static void release_attributes_data(void) wmi_priv.authentication_dir_kset = NULL; } if (wmi_priv.main_dir_kset) { + sysfs_remove_file(&wmi_priv.main_dir_kset->kobj, &reset_bios.attr); + sysfs_remove_file(&wmi_priv.main_dir_kset->kobj, &pending_reboot.attr); destroy_attribute_objs(wmi_priv.main_dir_kset); kset_unregister(wmi_priv.main_dir_kset); + wmi_priv.main_dir_kset = NULL; } mutex_unlock(&wmi_priv.mutex); - } /** @@ -497,7 +489,6 @@ nextobj: err_attr_init: mutex_unlock(&wmi_priv.mutex); - release_attributes_data(); kfree(obj); return retval; } @@ -513,102 +504,91 @@ static int __init sysman_init(void) } ret = init_bios_attr_set_interface(); - if (ret || !wmi_priv.bios_attr_wdev) { - pr_debug("failed to initialize set interface\n"); - goto fail_set_interface; - } + if (ret) + return ret; ret = init_bios_attr_pass_interface(); - if (ret || !wmi_priv.password_attr_wdev) { - pr_debug("failed to initialize pass interface\n"); - goto fail_pass_interface; + if (ret) + goto err_exit_bios_attr_set_interface; + + if (!wmi_priv.bios_attr_wdev || !wmi_priv.password_attr_wdev) { + pr_debug("failed to find set or pass interface\n"); + ret = -ENODEV; + goto err_exit_bios_attr_pass_interface; } ret = class_register(&firmware_attributes_class); if (ret) - goto fail_class; + goto err_exit_bios_attr_pass_interface; wmi_priv.class_dev = device_create(&firmware_attributes_class, NULL, MKDEV(0, 0), NULL, "%s", DRIVER_NAME); if (IS_ERR(wmi_priv.class_dev)) { ret = PTR_ERR(wmi_priv.class_dev); - goto fail_classdev; + goto err_unregister_class; } wmi_priv.main_dir_kset = kset_create_and_add("attributes", NULL, &wmi_priv.class_dev->kobj); if (!wmi_priv.main_dir_kset) { ret = -ENOMEM; - goto fail_main_kset; + goto err_destroy_classdev; } wmi_priv.authentication_dir_kset = kset_create_and_add("authentication", NULL, &wmi_priv.class_dev->kobj); if (!wmi_priv.authentication_dir_kset) { ret = -ENOMEM; - goto fail_authentication_kset; + goto err_release_attributes_data; } ret = create_attributes_level_sysfs_files(); if (ret) { pr_debug("could not create reset BIOS attribute\n"); - goto fail_reset_bios; + goto err_release_attributes_data; } ret = init_bios_attributes(ENUM, DELL_WMI_BIOS_ENUMERATION_ATTRIBUTE_GUID); if (ret) { pr_debug("failed to populate enumeration type attributes\n"); - goto fail_create_group; + goto err_release_attributes_data; } ret = init_bios_attributes(INT, DELL_WMI_BIOS_INTEGER_ATTRIBUTE_GUID); if (ret) { pr_debug("failed to populate integer type attributes\n"); - goto fail_create_group; + goto err_release_attributes_data; } ret = init_bios_attributes(STR, DELL_WMI_BIOS_STRING_ATTRIBUTE_GUID); if (ret) { pr_debug("failed to populate string type attributes\n"); - goto fail_create_group; + goto err_release_attributes_data; } ret = init_bios_attributes(PO, DELL_WMI_BIOS_PASSOBJ_ATTRIBUTE_GUID); if (ret) { pr_debug("failed to populate pass object type attributes\n"); - goto fail_create_group; + goto err_release_attributes_data; } return 0; -fail_create_group: +err_release_attributes_data: release_attributes_data(); -fail_reset_bios: - if (wmi_priv.authentication_dir_kset) { - kset_unregister(wmi_priv.authentication_dir_kset); - wmi_priv.authentication_dir_kset = NULL; - } - -fail_authentication_kset: - if (wmi_priv.main_dir_kset) { - kset_unregister(wmi_priv.main_dir_kset); - wmi_priv.main_dir_kset = NULL; - } - -fail_main_kset: +err_destroy_classdev: device_destroy(&firmware_attributes_class, MKDEV(0, 0)); -fail_classdev: +err_unregister_class: class_unregister(&firmware_attributes_class); -fail_class: +err_exit_bios_attr_pass_interface: exit_bios_attr_pass_interface(); -fail_pass_interface: +err_exit_bios_attr_set_interface: exit_bios_attr_set_interface(); -fail_set_interface: return ret; } diff --git a/drivers/platform/x86/intel-hid.c b/drivers/platform/x86/intel-hid.c index 2f5b8d09143e..078648a9201b 100644 --- a/drivers/platform/x86/intel-hid.c +++ b/drivers/platform/x86/intel-hid.c @@ -90,6 +90,13 @@ static const struct dmi_system_id button_array_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "HP Spectre x2 Detachable"), }, }, + { + .ident = "Lenovo ThinkPad X1 Tablet Gen 2", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_FAMILY, "ThinkPad X1 Tablet Gen 2"), + }, + }, { } }; @@ -476,11 +483,16 @@ static void notify_handler(acpi_handle handle, u32 event, void *context) goto wakeup; /* - * Switch events will wake the device and report the new switch - * position to the input subsystem. + * Some devices send (duplicate) tablet-mode events when moved + * around even though the mode has not changed; and they do this + * even when suspended. + * Update the switch state in case it changed and then return + * without waking up to avoid spurious wakeups. */ - if (priv->switches && (event == 0xcc || event == 0xcd)) - goto wakeup; + if (event == 0xcc || event == 0xcd) { + report_tablet_mode_event(priv->switches, event); + return; + } /* Wake up on 5-button array events only. */ if (event == 0xc0 || !priv->array) @@ -494,9 +506,6 @@ static void notify_handler(acpi_handle handle, u32 event, void *context) wakeup: pm_wakeup_hard_event(&device->dev); - if (report_tablet_mode_event(priv->switches, event)) - return; - return; } diff --git a/drivers/platform/x86/intel-vbtn.c b/drivers/platform/x86/intel-vbtn.c index 8a8017f9ca91..3fdf4cbec9ad 100644 --- a/drivers/platform/x86/intel-vbtn.c +++ b/drivers/platform/x86/intel-vbtn.c @@ -48,8 +48,16 @@ static const struct key_entry intel_vbtn_keymap[] = { }; static const struct key_entry intel_vbtn_switchmap[] = { - { KE_SW, 0xCA, { .sw = { SW_DOCK, 1 } } }, /* Docked */ - { KE_SW, 0xCB, { .sw = { SW_DOCK, 0 } } }, /* Undocked */ + /* + * SW_DOCK should only be reported for docking stations, but DSDTs using the + * intel-vbtn code, always seem to use this for 2-in-1s / convertibles and set + * SW_DOCK=1 when in laptop-mode (in tandem with setting SW_TABLET_MODE=0). + * This causes userspace to think the laptop is docked to a port-replicator + * and to disable suspend-on-lid-close, which is undesirable. + * Map the dock events to KEY_IGNORE to avoid this broken SW_DOCK reporting. + */ + { KE_IGNORE, 0xCA, { .sw = { SW_DOCK, 1 } } }, /* Docked */ + { KE_IGNORE, 0xCB, { .sw = { SW_DOCK, 0 } } }, /* Undocked */ { KE_SW, 0xCC, { .sw = { SW_TABLET_MODE, 1 } } }, /* Tablet */ { KE_SW, 0xCD, { .sw = { SW_TABLET_MODE, 0 } } }, /* Laptop */ { KE_END } diff --git a/drivers/platform/x86/intel_pmc_core.c b/drivers/platform/x86/intel_pmc_core.c index ee2f757515b0..b5888aeb4bcf 100644 --- a/drivers/platform/x86/intel_pmc_core.c +++ b/drivers/platform/x86/intel_pmc_core.c @@ -863,34 +863,45 @@ out_unlock: } DEFINE_SHOW_ATTRIBUTE(pmc_core_pll); -static ssize_t pmc_core_ltr_ignore_write(struct file *file, - const char __user *userbuf, - size_t count, loff_t *ppos) +static int pmc_core_send_ltr_ignore(u32 value) { struct pmc_dev *pmcdev = &pmc; const struct pmc_reg_map *map = pmcdev->map; - u32 val, buf_size, fd; - int err; - - buf_size = count < 64 ? count : 64; - - err = kstrtou32_from_user(userbuf, buf_size, 10, &val); - if (err) - return err; + u32 reg; + int err = 0; mutex_lock(&pmcdev->lock); - if (val > map->ltr_ignore_max) { + if (value > map->ltr_ignore_max) { err = -EINVAL; goto out_unlock; } - fd = pmc_core_reg_read(pmcdev, map->ltr_ignore_offset); - fd |= (1U << val); - pmc_core_reg_write(pmcdev, map->ltr_ignore_offset, fd); + reg = pmc_core_reg_read(pmcdev, map->ltr_ignore_offset); + reg |= BIT(value); + pmc_core_reg_write(pmcdev, map->ltr_ignore_offset, reg); out_unlock: mutex_unlock(&pmcdev->lock); + + return err; +} + +static ssize_t pmc_core_ltr_ignore_write(struct file *file, + const char __user *userbuf, + size_t count, loff_t *ppos) +{ + u32 buf_size, value; + int err; + + buf_size = min_t(u32, count, 64); + + err = kstrtou32_from_user(userbuf, buf_size, 10, &value); + if (err) + return err; + + err = pmc_core_send_ltr_ignore(value); + return err == 0 ? count : err; } @@ -1244,6 +1255,15 @@ static int pmc_core_probe(struct platform_device *pdev) pmcdev->pmc_xram_read_bit = pmc_core_check_read_lock_bit(); dmi_check_system(pmc_core_dmi_table); + /* + * On TGL, due to a hardware limitation, the GBE LTR blocks PC10 when + * a cable is attached. Tell the PMC to ignore it. + */ + if (pmcdev->map == &tgl_reg_map) { + dev_dbg(&pdev->dev, "ignoring GBE LTR\n"); + pmc_core_send_ltr_ignore(3); + } + pmc_core_dbgfs_register(pmcdev); device_initialized = true; diff --git a/drivers/platform/x86/intel_pmt_class.c b/drivers/platform/x86/intel_pmt_class.c index c8939fba4509..ee2b3bbeb83d 100644 --- a/drivers/platform/x86/intel_pmt_class.c +++ b/drivers/platform/x86/intel_pmt_class.c @@ -173,7 +173,7 @@ static int intel_pmt_dev_register(struct intel_pmt_entry *entry, struct intel_pmt_namespace *ns, struct device *parent) { - struct resource res; + struct resource res = {0}; struct device *dev; int ret; diff --git a/drivers/platform/x86/intel_pmt_crashlog.c b/drivers/platform/x86/intel_pmt_crashlog.c index 97dd749c8290..92d315a16cfd 100644 --- a/drivers/platform/x86/intel_pmt_crashlog.c +++ b/drivers/platform/x86/intel_pmt_crashlog.c @@ -23,18 +23,17 @@ #define CRASH_TYPE_OOBMSM 1 /* Control Flags */ -#define CRASHLOG_FLAG_DISABLE BIT(27) +#define CRASHLOG_FLAG_DISABLE BIT(28) /* - * Bits 28 and 29 control the state of bit 31. + * Bits 29 and 30 control the state of bit 31. * - * Bit 28 will clear bit 31, if set, allowing a new crashlog to be captured. - * Bit 29 will immediately trigger a crashlog to be generated, setting bit 31. - * Bit 30 is read-only and reserved as 0. + * Bit 29 will clear bit 31, if set, allowing a new crashlog to be captured. + * Bit 30 will immediately trigger a crashlog to be generated, setting bit 31. * Bit 31 is the read-only status with a 1 indicating log is complete. */ -#define CRASHLOG_FLAG_TRIGGER_CLEAR BIT(28) -#define CRASHLOG_FLAG_TRIGGER_EXECUTE BIT(29) +#define CRASHLOG_FLAG_TRIGGER_CLEAR BIT(29) +#define CRASHLOG_FLAG_TRIGGER_EXECUTE BIT(30) #define CRASHLOG_FLAG_TRIGGER_COMPLETE BIT(31) #define CRASHLOG_FLAG_TRIGGER_MASK GENMASK(31, 28) diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c index b881044b31b0..0d9e2ddbf904 100644 --- a/drivers/platform/x86/thinkpad_acpi.c +++ b/drivers/platform/x86/thinkpad_acpi.c @@ -4081,13 +4081,19 @@ static bool hotkey_notify_6xxx(const u32 hkey, case TP_HKEY_EV_KEY_NUMLOCK: case TP_HKEY_EV_KEY_FN: - case TP_HKEY_EV_KEY_FN_ESC: /* key press events, we just ignore them as long as the EC * is still reporting them in the normal keyboard stream */ *send_acpi_ev = false; *ignore_acpi_ev = true; return true; + case TP_HKEY_EV_KEY_FN_ESC: + /* Get the media key status to foce the status LED to update */ + acpi_evalf(hkey_handle, NULL, "GMKS", "v"); + *send_acpi_ev = false; + *ignore_acpi_ev = true; + return true; + case TP_HKEY_EV_TABLET_CHANGED: tpacpi_input_send_tabletsw(); hotkey_tablet_mode_notify_change(); @@ -9845,6 +9851,11 @@ static struct ibm_struct lcdshadow_driver_data = { * Thinkpad sensor interfaces */ +#define DYTC_CMD_QUERY 0 /* To get DYTC status - enable/revision */ +#define DYTC_QUERY_ENABLE_BIT 8 /* Bit 8 - 0 = disabled, 1 = enabled */ +#define DYTC_QUERY_SUBREV_BIT 16 /* Bits 16 - 27 - sub revision */ +#define DYTC_QUERY_REV_BIT 28 /* Bits 28 - 31 - revision */ + #define DYTC_CMD_GET 2 /* To get current IC function and mode */ #define DYTC_GET_LAPMODE_BIT 17 /* Set when in lapmode */ @@ -9855,6 +9866,7 @@ static bool has_palmsensor; static bool has_lapsensor; static bool palm_state; static bool lap_state; +static int dytc_version; static int dytc_command(int command, int *output) { @@ -9869,6 +9881,33 @@ static int dytc_command(int command, int *output) return 0; } +static int dytc_get_version(void) +{ + int err, output; + + /* Check if we've been called before - and just return cached value */ + if (dytc_version) + return dytc_version; + + /* Otherwise query DYTC and extract version information */ + err = dytc_command(DYTC_CMD_QUERY, &output); + /* + * If support isn't available (ENODEV) then don't return an error + * and don't create the sysfs group + */ + if (err == -ENODEV) + return 0; + /* For all other errors we can flag the failure */ + if (err) + return err; + + /* Check DYTC is enabled and supports mode setting */ + if (output & BIT(DYTC_QUERY_ENABLE_BIT)) + dytc_version = (output >> DYTC_QUERY_REV_BIT) & 0xF; + + return 0; +} + static int lapsensor_get(bool *present, bool *state) { int output, err; @@ -9974,7 +10013,18 @@ static int tpacpi_proxsensor_init(struct ibm_init_struct *iibm) if (err) return err; } - if (has_lapsensor) { + + /* Check if we know the DYTC version, if we don't then get it */ + if (!dytc_version) { + err = dytc_get_version(); + if (err) + return err; + } + /* + * Platforms before DYTC version 5 claim to have a lap sensor, but it doesn't work, so we + * ignore them + */ + if (has_lapsensor && (dytc_version >= 5)) { err = sysfs_create_file(&tpacpi_pdev->dev.kobj, &dev_attr_dytc_lapmode.attr); if (err) return err; @@ -9999,14 +10049,9 @@ static struct ibm_struct proxsensor_driver_data = { * DYTC Platform Profile interface */ -#define DYTC_CMD_QUERY 0 /* To get DYTC status - enable/revision */ #define DYTC_CMD_SET 1 /* To enable/disable IC function mode */ #define DYTC_CMD_RESET 0x1ff /* To reset back to default */ -#define DYTC_QUERY_ENABLE_BIT 8 /* Bit 8 - 0 = disabled, 1 = enabled */ -#define DYTC_QUERY_SUBREV_BIT 16 /* Bits 16 - 27 - sub revision */ -#define DYTC_QUERY_REV_BIT 28 /* Bits 28 - 31 - revision */ - #define DYTC_GET_FUNCTION_BIT 8 /* Bits 8-11 - function setting */ #define DYTC_GET_MODE_BIT 12 /* Bits 12-15 - mode setting */ @@ -10142,8 +10187,13 @@ static int dytc_profile_set(struct platform_profile_handler *pprof, return err; if (profile == PLATFORM_PROFILE_BALANCED) { - /* To get back to balanced mode we just issue a reset command */ - err = dytc_command(DYTC_CMD_RESET, &output); + /* + * To get back to balanced mode we need to issue a reset command. + * Note we still need to disable CQL mode before hand and re-enable + * it afterwards, otherwise dytc_lapmode gets reset to 0 and stays + * stuck at 0 for aprox. 30 minutes. + */ + err = dytc_cql_command(DYTC_CMD_RESET, &output); if (err) goto unlock; } else { @@ -10211,28 +10261,28 @@ static int tpacpi_dytc_profile_init(struct ibm_init_struct *iibm) if (err) return err; + /* Check if we know the DYTC version, if we don't then get it */ + if (!dytc_version) { + err = dytc_get_version(); + if (err) + return err; + } /* Check DYTC is enabled and supports mode setting */ - if (output & BIT(DYTC_QUERY_ENABLE_BIT)) { - /* Only DYTC v5.0 and later has this feature. */ - int dytc_version; - - dytc_version = (output >> DYTC_QUERY_REV_BIT) & 0xF; - if (dytc_version >= 5) { - dbg_printk(TPACPI_DBG_INIT, - "DYTC version %d: thermal mode available\n", dytc_version); - /* Create platform_profile structure and register */ - err = platform_profile_register(&dytc_profile); - /* - * If for some reason platform_profiles aren't enabled - * don't quit terminally. - */ - if (err) - return 0; + if (dytc_version >= 5) { + dbg_printk(TPACPI_DBG_INIT, + "DYTC version %d: thermal mode available\n", dytc_version); + /* Create platform_profile structure and register */ + err = platform_profile_register(&dytc_profile); + /* + * If for some reason platform_profiles aren't enabled + * don't quit terminally. + */ + if (err) + return 0; - dytc_profile_available = true; - /* Ensure initial values are correct */ - dytc_profile_refresh(); - } + dytc_profile_available = true; + /* Ensure initial values are correct */ + dytc_profile_refresh(); } return 0; } diff --git a/drivers/ptp/ptp_qoriq.c b/drivers/ptp/ptp_qoriq.c index beb5f74944cd..08f4cf0ad9e3 100644 --- a/drivers/ptp/ptp_qoriq.c +++ b/drivers/ptp/ptp_qoriq.c @@ -189,15 +189,16 @@ int ptp_qoriq_adjfine(struct ptp_clock_info *ptp, long scaled_ppm) tmr_add = ptp_qoriq->tmr_add; adj = tmr_add; - /* calculate diff as adj*(scaled_ppm/65536)/1000000 - * and round() to the nearest integer + /* + * Calculate diff and round() to the nearest integer + * + * diff = adj * (ppb / 1000000000) + * = adj * scaled_ppm / 65536000000 */ - adj *= scaled_ppm; - diff = div_u64(adj, 8000000); - diff = (diff >> 13) + ((diff >> 12) & 1); + diff = mul_u64_u64_div_u64(adj, scaled_ppm, 32768000000); + diff = DIV64_U64_ROUND_UP(diff, 2); tmr_add = neg_adj ? tmr_add - diff : tmr_add + diff; - ptp_qoriq->write(®s->ctrl_regs->tmr_add, tmr_add); return 0; diff --git a/drivers/ras/cec.c b/drivers/ras/cec.c index ddecf25b5dd4..d7894f178bd4 100644 --- a/drivers/ras/cec.c +++ b/drivers/ras/cec.c @@ -309,11 +309,20 @@ static bool sanity_check(struct ce_array *ca) return ret; } +/** + * cec_add_elem - Add an element to the CEC array. + * @pfn: page frame number to insert + * + * Return values: + * - <0: on error + * - 0: on success + * - >0: when the inserted pfn was offlined + */ static int cec_add_elem(u64 pfn) { struct ce_array *ca = &ce_arr; + int count, err, ret = 0; unsigned int to = 0; - int count, ret = 0; /* * We can be called very early on the identify_cpu() path where we are @@ -330,8 +339,8 @@ static int cec_add_elem(u64 pfn) if (ca->n == MAX_ELEMS) WARN_ON(!del_lru_elem_unlocked(ca)); - ret = find_elem(ca, pfn, &to); - if (ret < 0) { + err = find_elem(ca, pfn, &to); + if (err < 0) { /* * Shift range [to-end] to make room for one more element. */ diff --git a/drivers/regulator/bd9571mwv-regulator.c b/drivers/regulator/bd9571mwv-regulator.c index 7b0cd08db446..ba020a45f238 100644 --- a/drivers/regulator/bd9571mwv-regulator.c +++ b/drivers/regulator/bd9571mwv-regulator.c @@ -125,7 +125,7 @@ static const struct regulator_ops vid_ops = { static const struct regulator_desc regulators[] = { BD9571MWV_REG("VD09", "vd09", VD09, avs_ops, 0, 0x7f, - 0x80, 600000, 10000, 0x3c), + 0x6f, 600000, 10000, 0x3c), BD9571MWV_REG("VD18", "vd18", VD18, vid_ops, BD9571MWV_VD18_VID, 0xf, 16, 1625000, 25000, 0), BD9571MWV_REG("VD25", "vd25", VD25, vid_ops, BD9571MWV_VD25_VID, 0xf, @@ -134,7 +134,7 @@ static const struct regulator_desc regulators[] = { 11, 2800000, 100000, 0), BD9571MWV_REG("DVFS", "dvfs", DVFS, reg_ops, BD9571MWV_DVFS_MONIVDAC, 0x7f, - 0x80, 600000, 10000, 0x3c), + 0x6f, 600000, 10000, 0x3c), }; #ifdef CONFIG_PM_SLEEP @@ -174,7 +174,7 @@ static ssize_t backup_mode_show(struct device *dev, { struct bd9571mwv_reg *bdreg = dev_get_drvdata(dev); - return sprintf(buf, "%s\n", bdreg->bkup_mode_enabled ? "on" : "off"); + return sysfs_emit(buf, "%s\n", bdreg->bkup_mode_enabled ? "on" : "off"); } static ssize_t backup_mode_store(struct device *dev, @@ -301,7 +301,7 @@ static int bd9571mwv_regulator_probe(struct platform_device *pdev) &config); if (IS_ERR(rdev)) { dev_err(&pdev->dev, "failed to register %s regulator\n", - pdev->name); + regulators[i].name); return PTR_ERR(rdev); } } diff --git a/drivers/remoteproc/pru_rproc.c b/drivers/remoteproc/pru_rproc.c index 2667919d76b3..dcb380e868df 100644 --- a/drivers/remoteproc/pru_rproc.c +++ b/drivers/remoteproc/pru_rproc.c @@ -450,6 +450,24 @@ static void *pru_i_da_to_va(struct pru_rproc *pru, u32 da, size_t len) if (len == 0) return NULL; + /* + * GNU binutils do not support multiple address spaces. The GNU + * linker's default linker script places IRAM at an arbitrary high + * offset, in order to differentiate it from DRAM. Hence we need to + * strip the artificial offset in the IRAM addresses coming from the + * ELF file. + * + * The TI proprietary linker would never set those higher IRAM address + * bits anyway. PRU architecture limits the program counter to 16-bit + * word-address range. This in turn corresponds to 18-bit IRAM + * byte-address range for ELF. + * + * Two more bits are added just in case to make the final 20-bit mask. + * Idea is to have a safeguard in case TI decides to add banking + * in future SoCs. + */ + da &= 0xfffff; + if (da >= PRU_IRAM_DA && da + len <= PRU_IRAM_DA + pru->mem_regions[PRU_IOMEM_IRAM].size) { offset = da - PRU_IRAM_DA; @@ -585,7 +603,7 @@ pru_rproc_load_elf_segments(struct rproc *rproc, const struct firmware *fw) break; } - if (pru->data->is_k3 && is_iram) { + if (pru->data->is_k3) { ret = pru_rproc_memcpy(ptr, elf_data + phdr->p_offset, filesz); if (ret) { diff --git a/drivers/remoteproc/qcom_pil_info.c b/drivers/remoteproc/qcom_pil_info.c index 5521c4437ffa..7c007dd7b200 100644 --- a/drivers/remoteproc/qcom_pil_info.c +++ b/drivers/remoteproc/qcom_pil_info.c @@ -56,7 +56,7 @@ static int qcom_pil_info_init(void) memset_io(base, 0, resource_size(&imem)); _reloc.base = base; - _reloc.num_entries = resource_size(&imem) / PIL_RELOC_ENTRY_SIZE; + _reloc.num_entries = (u32)resource_size(&imem) / PIL_RELOC_ENTRY_SIZE; return 0; } diff --git a/drivers/s390/block/dasd.c b/drivers/s390/block/dasd.c index ba9ce4e0d30a..3a945abf268c 100644 --- a/drivers/s390/block/dasd.c +++ b/drivers/s390/block/dasd.c @@ -63,7 +63,6 @@ void dasd_int_handler(struct ccw_device *, unsigned long, struct irb *); MODULE_AUTHOR("Holger Smolinski <Holger.Smolinski@de.ibm.com>"); MODULE_DESCRIPTION("Linux on S/390 DASD device driver," " Copyright IBM Corp. 2000"); -MODULE_SUPPORTED_DEVICE("dasd"); MODULE_LICENSE("GPL"); /* diff --git a/drivers/sbus/char/display7seg.c b/drivers/sbus/char/display7seg.c index 00e72b97d0b6..d93595b39afa 100644 --- a/drivers/sbus/char/display7seg.c +++ b/drivers/sbus/char/display7seg.c @@ -50,7 +50,6 @@ MODULE_PARM_DESC(sol_compat, MODULE_AUTHOR("Eric Brower <ebrower@usa.net>"); MODULE_DESCRIPTION("7-Segment Display driver for Sun Microsystems CP1400/1500"); MODULE_LICENSE("GPL"); -MODULE_SUPPORTED_DEVICE("d7s"); struct d7s { void __iomem *regs; diff --git a/drivers/scsi/hpsa.c b/drivers/scsi/hpsa.c index 38369766511c..f135a10f582b 100644 --- a/drivers/scsi/hpsa.c +++ b/drivers/scsi/hpsa.c @@ -80,7 +80,6 @@ MODULE_AUTHOR("Hewlett-Packard Company"); MODULE_DESCRIPTION("Driver for HP Smart Array Controller version " \ HPSA_DRIVER_VERSION); -MODULE_SUPPORTED_DEVICE("HP Smart Array Controllers"); MODULE_VERSION(HPSA_DRIVER_VERSION); MODULE_LICENSE("GPL"); MODULE_ALIAS("cciss"); diff --git a/drivers/scsi/hpsa_cmd.h b/drivers/scsi/hpsa_cmd.h index d126bb877250..ba6a3aa8d954 100644 --- a/drivers/scsi/hpsa_cmd.h +++ b/drivers/scsi/hpsa_cmd.h @@ -20,6 +20,11 @@ #ifndef HPSA_CMD_H #define HPSA_CMD_H +#include <linux/compiler.h> + +#include <linux/build_bug.h> /* static_assert */ +#include <linux/stddef.h> /* offsetof */ + /* general boundary defintions */ #define SENSEINFOBYTES 32 /* may vary between hbas */ #define SG_ENTRIES_IN_CMD 32 /* Max SG entries excluding chain blocks */ @@ -200,12 +205,10 @@ union u64bit { MAX_EXT_TARGETS + 1) /* + 1 is for the controller itself */ /* SCSI-3 Commands */ -#pragma pack(1) - #define HPSA_INQUIRY 0x12 struct InquiryData { u8 data_byte[36]; -}; +} __packed; #define HPSA_REPORT_LOG 0xc2 /* Report Logical LUNs */ #define HPSA_REPORT_PHYS 0xc3 /* Report Physical LUNs */ @@ -221,7 +224,7 @@ struct raid_map_disk_data { u8 xor_mult[2]; /**< XOR multipliers for this position, * valid for data disks only */ u8 reserved[2]; -}; +} __packed; struct raid_map_data { __le32 structure_size; /* Size of entire structure in bytes */ @@ -247,14 +250,14 @@ struct raid_map_data { __le16 dekindex; /* Data encryption key index. */ u8 reserved[16]; struct raid_map_disk_data data[RAID_MAP_MAX_ENTRIES]; -}; +} __packed; struct ReportLUNdata { u8 LUNListLength[4]; u8 extended_response_flag; u8 reserved[3]; u8 LUN[HPSA_MAX_LUN][8]; -}; +} __packed; struct ext_report_lun_entry { u8 lunid[8]; @@ -269,20 +272,20 @@ struct ext_report_lun_entry { u8 lun_count; /* multi-lun device, how many luns */ u8 redundant_paths; u32 ioaccel_handle; /* ioaccel1 only uses lower 16 bits */ -}; +} __packed; struct ReportExtendedLUNdata { u8 LUNListLength[4]; u8 extended_response_flag; u8 reserved[3]; struct ext_report_lun_entry LUN[HPSA_MAX_PHYS_LUN]; -}; +} __packed; struct SenseSubsystem_info { u8 reserved[36]; u8 portname[8]; u8 reserved1[1108]; -}; +} __packed; /* BMIC commands */ #define BMIC_READ 0x26 @@ -317,7 +320,7 @@ union SCSI3Addr { u8 Targ:6; u8 Mode:2; /* b10 */ } LogUnit; -}; +} __packed; struct PhysDevAddr { u32 TargetId:24; @@ -325,20 +328,20 @@ struct PhysDevAddr { u32 Mode:2; /* 2 level target device addr */ union SCSI3Addr Target[2]; -}; +} __packed; struct LogDevAddr { u32 VolId:30; u32 Mode:2; u8 reserved[4]; -}; +} __packed; union LUNAddr { u8 LunAddrBytes[8]; union SCSI3Addr SCSI3Lun[4]; struct PhysDevAddr PhysDev; struct LogDevAddr LogDev; -}; +} __packed; struct CommandListHeader { u8 ReplyQueue; @@ -346,7 +349,7 @@ struct CommandListHeader { __le16 SGTotal; __le64 tag; union LUNAddr LUN; -}; +} __packed; struct RequestBlock { u8 CDBLen; @@ -365,18 +368,18 @@ struct RequestBlock { #define GET_DIR(tad) (((tad) >> 6) & 0x03) u16 Timeout; u8 CDB[16]; -}; +} __packed; struct ErrDescriptor { __le64 Addr; __le32 Len; -}; +} __packed; struct SGDescriptor { __le64 Addr; __le32 Len; __le32 Ext; -}; +} __packed; union MoreErrInfo { struct { @@ -390,7 +393,8 @@ union MoreErrInfo { u8 offense_num; /* byte # of offense 0-base */ u32 offense_value; } Invalid_Cmd; -}; +} __packed; + struct ErrorInfo { u8 ScsiStatus; u8 SenseLen; @@ -398,7 +402,7 @@ struct ErrorInfo { u32 ResidualCnt; union MoreErrInfo MoreErrInfo; u8 SenseInfo[SENSEINFOBYTES]; -}; +} __packed; /* Command types */ #define CMD_IOCTL_PEND 0x01 #define CMD_SCSI 0x03 @@ -453,6 +457,15 @@ struct CommandList { atomic_t refcount; /* Must be last to avoid memset in hpsa_cmd_init() */ } __aligned(COMMANDLIST_ALIGNMENT); +/* + * Make sure our embedded atomic variable is aligned. Otherwise we break atomic + * operations on architectures that don't support unaligned atomics like IA64. + * + * The assert guards against reintroductin against unwanted __packed to + * the struct CommandList. + */ +static_assert(offsetof(struct CommandList, refcount) % __alignof__(atomic_t) == 0); + /* Max S/G elements in I/O accelerator command */ #define IOACCEL1_MAXSGENTRIES 24 #define IOACCEL2_MAXSGENTRIES 28 @@ -489,7 +502,7 @@ struct io_accel1_cmd { __le64 host_addr; /* 0x70 - 0x77 */ u8 CISS_LUN[8]; /* 0x78 - 0x7F */ struct SGDescriptor SG[IOACCEL1_MAXSGENTRIES]; -} __aligned(IOACCEL1_COMMANDLIST_ALIGNMENT); +} __packed __aligned(IOACCEL1_COMMANDLIST_ALIGNMENT); #define IOACCEL1_FUNCTION_SCSIIO 0x00 #define IOACCEL1_SGLOFFSET 32 @@ -519,7 +532,7 @@ struct ioaccel2_sg_element { u8 chain_indicator; #define IOACCEL2_CHAIN 0x80 #define IOACCEL2_LAST_SG 0x40 -}; +} __packed; /* * SCSI Response Format structure for IO Accelerator Mode 2 @@ -559,7 +572,7 @@ struct io_accel2_scsi_response { u8 sense_data_len; /* sense/response data length */ u8 resid_cnt[4]; /* residual count */ u8 sense_data_buff[32]; /* sense/response data buffer */ -}; +} __packed; /* * Structure for I/O accelerator (mode 2 or m2) commands. @@ -592,7 +605,7 @@ struct io_accel2_cmd { __le32 tweak_upper; /* Encryption tweak, upper 4 bytes */ struct ioaccel2_sg_element sg[IOACCEL2_MAXSGENTRIES]; struct io_accel2_scsi_response error_data; -} __aligned(IOACCEL2_COMMANDLIST_ALIGNMENT); +} __packed __aligned(IOACCEL2_COMMANDLIST_ALIGNMENT); /* * defines for Mode 2 command struct @@ -618,7 +631,7 @@ struct hpsa_tmf_struct { __le64 abort_tag; /* cciss tag of SCSI cmd or TMF to abort */ __le64 error_ptr; /* Error Pointer */ __le32 error_len; /* Error Length */ -} __aligned(IOACCEL2_COMMANDLIST_ALIGNMENT); +} __packed __aligned(IOACCEL2_COMMANDLIST_ALIGNMENT); /* Configuration Table Structure */ struct HostWrite { @@ -626,7 +639,7 @@ struct HostWrite { __le32 command_pool_addr_hi; __le32 CoalIntDelay; __le32 CoalIntCount; -}; +} __packed; #define SIMPLE_MODE 0x02 #define PERFORMANT_MODE 0x04 @@ -675,7 +688,7 @@ struct CfgTable { #define HPSA_EVENT_NOTIFY_ACCEL_IO_PATH_STATE_CHANGE (1 << 30) #define HPSA_EVENT_NOTIFY_ACCEL_IO_PATH_CONFIG_CHANGE (1 << 31) __le32 clear_event_notify; -}; +} __packed; #define NUM_BLOCKFETCH_ENTRIES 8 struct TransTable_struct { @@ -686,14 +699,14 @@ struct TransTable_struct { __le32 RepQCtrAddrHigh32; #define MAX_REPLY_QUEUES 64 struct vals32 RepQAddr[MAX_REPLY_QUEUES]; -}; +} __packed; struct hpsa_pci_info { unsigned char bus; unsigned char dev_fn; unsigned short domain; u32 board_id; -}; +} __packed; struct bmic_identify_controller { u8 configured_logical_drive_count; /* offset 0 */ @@ -702,7 +715,7 @@ struct bmic_identify_controller { u8 pad2[136]; u8 controller_mode; /* offset 292 */ u8 pad3[32]; -}; +} __packed; struct bmic_identify_physical_device { @@ -845,7 +858,7 @@ struct bmic_identify_physical_device { u8 max_link_rate[256]; u8 neg_phys_link_rate[256]; u8 box_conn_name[8]; -} __attribute((aligned(512))); +} __packed __attribute((aligned(512))); struct bmic_sense_subsystem_info { u8 primary_slot_number; @@ -858,7 +871,7 @@ struct bmic_sense_subsystem_info { u8 secondary_array_serial_number[32]; u8 secondary_cache_serial_number[32]; u8 pad[332]; -}; +} __packed; struct bmic_sense_storage_box_params { u8 reserved[36]; @@ -870,7 +883,6 @@ struct bmic_sense_storage_box_params { u8 reserver_3[84]; u8 phys_connector[2]; u8 reserved_4[296]; -}; +} __packed; -#pragma pack() #endif /* HPSA_CMD_H */ diff --git a/drivers/scsi/ibmvscsi/ibmvfc.c b/drivers/scsi/ibmvscsi/ibmvfc.c index 1b68734940b5..61831f2fdb30 100644 --- a/drivers/scsi/ibmvscsi/ibmvfc.c +++ b/drivers/scsi/ibmvscsi/ibmvfc.c @@ -2372,6 +2372,24 @@ static int ibmvfc_match_lun(struct ibmvfc_event *evt, void *device) } /** + * ibmvfc_event_is_free - Check if event is free or not + * @evt: ibmvfc event struct + * + * Returns: + * true / false + **/ +static bool ibmvfc_event_is_free(struct ibmvfc_event *evt) +{ + struct ibmvfc_event *loop_evt; + + list_for_each_entry(loop_evt, &evt->queue->free, queue_list) + if (loop_evt == evt) + return true; + + return false; +} + +/** * ibmvfc_wait_for_ops - Wait for ops to complete * @vhost: ibmvfc host struct * @device: device to match (starget or sdev) @@ -2385,35 +2403,58 @@ static int ibmvfc_wait_for_ops(struct ibmvfc_host *vhost, void *device, { struct ibmvfc_event *evt; DECLARE_COMPLETION_ONSTACK(comp); - int wait; + int wait, i, q_index, q_size; unsigned long flags; signed long timeout = IBMVFC_ABORT_WAIT_TIMEOUT * HZ; + struct ibmvfc_queue *queues; ENTER; + if (vhost->mq_enabled && vhost->using_channels) { + queues = vhost->scsi_scrqs.scrqs; + q_size = vhost->scsi_scrqs.active_queues; + } else { + queues = &vhost->crq; + q_size = 1; + } + do { wait = 0; - spin_lock_irqsave(&vhost->crq.l_lock, flags); - list_for_each_entry(evt, &vhost->crq.sent, queue_list) { - if (match(evt, device)) { - evt->eh_comp = ∁ - wait++; + spin_lock_irqsave(vhost->host->host_lock, flags); + for (q_index = 0; q_index < q_size; q_index++) { + spin_lock(&queues[q_index].l_lock); + for (i = 0; i < queues[q_index].evt_pool.size; i++) { + evt = &queues[q_index].evt_pool.events[i]; + if (!ibmvfc_event_is_free(evt)) { + if (match(evt, device)) { + evt->eh_comp = ∁ + wait++; + } + } } + spin_unlock(&queues[q_index].l_lock); } - spin_unlock_irqrestore(&vhost->crq.l_lock, flags); + spin_unlock_irqrestore(vhost->host->host_lock, flags); if (wait) { timeout = wait_for_completion_timeout(&comp, timeout); if (!timeout) { wait = 0; - spin_lock_irqsave(&vhost->crq.l_lock, flags); - list_for_each_entry(evt, &vhost->crq.sent, queue_list) { - if (match(evt, device)) { - evt->eh_comp = NULL; - wait++; + spin_lock_irqsave(vhost->host->host_lock, flags); + for (q_index = 0; q_index < q_size; q_index++) { + spin_lock(&queues[q_index].l_lock); + for (i = 0; i < queues[q_index].evt_pool.size; i++) { + evt = &queues[q_index].evt_pool.events[i]; + if (!ibmvfc_event_is_free(evt)) { + if (match(evt, device)) { + evt->eh_comp = NULL; + wait++; + } + } } + spin_unlock(&queues[q_index].l_lock); } - spin_unlock_irqrestore(&vhost->crq.l_lock, flags); + spin_unlock_irqrestore(vhost->host->host_lock, flags); if (wait) dev_err(vhost->dev, "Timed out waiting for aborted commands\n"); LEAVE; @@ -5784,6 +5825,8 @@ static void ibmvfc_free_mem(struct ibmvfc_host *vhost) vhost->disc_buf_dma); dma_free_coherent(vhost->dev, sizeof(*vhost->login_buf), vhost->login_buf, vhost->login_buf_dma); + dma_free_coherent(vhost->dev, sizeof(*vhost->channel_setup_buf), + vhost->channel_setup_buf, vhost->channel_setup_dma); dma_pool_destroy(vhost->sg_pool); ibmvfc_free_queue(vhost, async_q); LEAVE; diff --git a/drivers/scsi/lpfc/lpfc_debugfs.c b/drivers/scsi/lpfc/lpfc_debugfs.c index bc79a017e1a2..46a8f2d1d2b8 100644 --- a/drivers/scsi/lpfc/lpfc_debugfs.c +++ b/drivers/scsi/lpfc/lpfc_debugfs.c @@ -2421,7 +2421,7 @@ lpfc_debugfs_dif_err_write(struct file *file, const char __user *buf, memset(dstbuf, 0, 33); size = (nbytes < 32) ? nbytes : 32; if (copy_from_user(dstbuf, buf, size)) - return 0; + return -EFAULT; if (dent == phba->debug_InjErrLBA) { if ((dstbuf[0] == 'o') && (dstbuf[1] == 'f') && @@ -2430,7 +2430,7 @@ lpfc_debugfs_dif_err_write(struct file *file, const char __user *buf, } if ((tmp == 0) && (kstrtoull(dstbuf, 0, &tmp))) - return 0; + return -EINVAL; if (dent == phba->debug_writeGuard) phba->lpfc_injerr_wgrd_cnt = (uint32_t)tmp; diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c index ac066f86bb14..ac0eef975f17 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_base.c +++ b/drivers/scsi/mpt3sas/mpt3sas_base.c @@ -7806,14 +7806,18 @@ mpt3sas_base_attach(struct MPT3SAS_ADAPTER *ioc) ioc->pend_os_device_add_sz++; ioc->pend_os_device_add = kzalloc(ioc->pend_os_device_add_sz, GFP_KERNEL); - if (!ioc->pend_os_device_add) + if (!ioc->pend_os_device_add) { + r = -ENOMEM; goto out_free_resources; + } ioc->device_remove_in_progress_sz = ioc->pend_os_device_add_sz; ioc->device_remove_in_progress = kzalloc(ioc->device_remove_in_progress_sz, GFP_KERNEL); - if (!ioc->device_remove_in_progress) + if (!ioc->device_remove_in_progress) { + r = -ENOMEM; goto out_free_resources; + } ioc->fwfault_debug = mpt3sas_fwfault_debug; diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c index ffca03064797..6aa6de729187 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c +++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c @@ -413,7 +413,7 @@ mpt3sas_get_port_by_id(struct MPT3SAS_ADAPTER *ioc, * And add this object to port_table_list. */ if (!ioc->multipath_on_hba) { - port = kzalloc(sizeof(struct hba_port), GFP_KERNEL); + port = kzalloc(sizeof(struct hba_port), GFP_ATOMIC); if (!port) return NULL; diff --git a/drivers/scsi/myrs.c b/drivers/scsi/myrs.c index 4adf9ded296a..329fd025c718 100644 --- a/drivers/scsi/myrs.c +++ b/drivers/scsi/myrs.c @@ -2273,12 +2273,12 @@ static void myrs_cleanup(struct myrs_hba *cs) if (cs->mmio_base) { cs->disable_intr(cs); iounmap(cs->mmio_base); + cs->mmio_base = NULL; } if (cs->irq) free_irq(cs->irq, cs); if (cs->io_addr) release_region(cs->io_addr, 0x80); - iounmap(cs->mmio_base); pci_set_drvdata(pdev, NULL); pci_disable_device(pdev); scsi_host_put(cs->host); diff --git a/drivers/scsi/pcmcia/nsp_cs.c b/drivers/scsi/pcmcia/nsp_cs.c index 5d5f50d6a02d..ac89002646a3 100644 --- a/drivers/scsi/pcmcia/nsp_cs.c +++ b/drivers/scsi/pcmcia/nsp_cs.c @@ -55,7 +55,6 @@ MODULE_AUTHOR("YOKOTA Hiroshi <yokota@netlab.is.tsukuba.ac.jp>"); MODULE_DESCRIPTION("WorkBit NinjaSCSI-3 / NinjaSCSI-32Bi(16bit) PCMCIA SCSI host adapter module"); -MODULE_SUPPORTED_DEVICE("sd,sr,sg,st"); MODULE_LICENSE("GPL"); #include "nsp_io.h" diff --git a/drivers/scsi/pm8001/pm8001_hwi.c b/drivers/scsi/pm8001/pm8001_hwi.c index 49bf2f70a470..31e5455d280c 100644 --- a/drivers/scsi/pm8001/pm8001_hwi.c +++ b/drivers/scsi/pm8001/pm8001_hwi.c @@ -223,7 +223,7 @@ static void init_default_table_values(struct pm8001_hba_info *pm8001_ha) PM8001_EVENT_LOG_SIZE; pm8001_ha->main_cfg_tbl.pm8001_tbl.iop_event_log_option = 0x01; pm8001_ha->main_cfg_tbl.pm8001_tbl.fatal_err_interrupt = 0x01; - for (i = 0; i < PM8001_MAX_INB_NUM; i++) { + for (i = 0; i < pm8001_ha->max_q_num; i++) { pm8001_ha->inbnd_q_tbl[i].element_pri_size_cnt = PM8001_MPI_QUEUE | (pm8001_ha->iomb_size << 16) | (0x00<<30); pm8001_ha->inbnd_q_tbl[i].upper_base_addr = @@ -249,7 +249,7 @@ static void init_default_table_values(struct pm8001_hba_info *pm8001_ha) pm8001_ha->inbnd_q_tbl[i].producer_idx = 0; pm8001_ha->inbnd_q_tbl[i].consumer_index = 0; } - for (i = 0; i < PM8001_MAX_OUTB_NUM; i++) { + for (i = 0; i < pm8001_ha->max_q_num; i++) { pm8001_ha->outbnd_q_tbl[i].element_size_cnt = PM8001_MPI_QUEUE | (pm8001_ha->iomb_size << 16) | (0x01<<30); pm8001_ha->outbnd_q_tbl[i].upper_base_addr = @@ -671,9 +671,9 @@ static int pm8001_chip_init(struct pm8001_hba_info *pm8001_ha) read_outbnd_queue_table(pm8001_ha); /* update main config table ,inbound table and outbound table */ update_main_config_table(pm8001_ha); - for (i = 0; i < PM8001_MAX_INB_NUM; i++) + for (i = 0; i < pm8001_ha->max_q_num; i++) update_inbnd_queue_table(pm8001_ha, i); - for (i = 0; i < PM8001_MAX_OUTB_NUM; i++) + for (i = 0; i < pm8001_ha->max_q_num; i++) update_outbnd_queue_table(pm8001_ha, i); /* 8081 controller donot require these operations */ if (deviceid != 0x8081 && deviceid != 0x0042) { diff --git a/drivers/scsi/qedi/qedi_main.c b/drivers/scsi/qedi/qedi_main.c index 47ad64b06623..69c5b5ee2169 100644 --- a/drivers/scsi/qedi/qedi_main.c +++ b/drivers/scsi/qedi/qedi_main.c @@ -1675,6 +1675,7 @@ static int qedi_alloc_global_queues(struct qedi_ctx *qedi) if (!qedi->global_queues[i]) { QEDI_ERR(&qedi->dbg_ctx, "Unable to allocation global queue %d.\n", i); + status = -ENOMEM; goto mem_alloc_failure; } diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c index c48daf52725d..480e7d2dcf3e 100644 --- a/drivers/scsi/qla2xxx/qla_target.c +++ b/drivers/scsi/qla2xxx/qla_target.c @@ -3222,8 +3222,7 @@ int qlt_xmit_response(struct qla_tgt_cmd *cmd, int xmit_type, if (!qpair->fw_started || (cmd->reset_count != qpair->chip_reset) || (cmd->sess && cmd->sess->deleted)) { cmd->state = QLA_TGT_STATE_PROCESSED; - res = 0; - goto free; + return 0; } ql_dbg_qp(ql_dbg_tgt, qpair, 0xe018, @@ -3234,8 +3233,9 @@ int qlt_xmit_response(struct qla_tgt_cmd *cmd, int xmit_type, res = qlt_pre_xmit_response(cmd, &prm, xmit_type, scsi_status, &full_req_cnt); - if (unlikely(res != 0)) - goto free; + if (unlikely(res != 0)) { + return res; + } spin_lock_irqsave(qpair->qp_lock_ptr, flags); @@ -3255,8 +3255,7 @@ int qlt_xmit_response(struct qla_tgt_cmd *cmd, int xmit_type, vha->flags.online, qla2x00_reset_active(vha), cmd->reset_count, qpair->chip_reset); spin_unlock_irqrestore(qpair->qp_lock_ptr, flags); - res = 0; - goto free; + return 0; } /* Does F/W have an IOCBs for this request */ @@ -3359,8 +3358,6 @@ out_unmap_unlock: qlt_unmap_sg(vha, cmd); spin_unlock_irqrestore(qpair->qp_lock_ptr, flags); -free: - vha->hw->tgt.tgt_ops->free_cmd(cmd); return res; } EXPORT_SYMBOL(qlt_xmit_response); diff --git a/drivers/scsi/qla2xxx/qla_target.h b/drivers/scsi/qla2xxx/qla_target.h index 10e5e6c8087d..01620f3eab39 100644 --- a/drivers/scsi/qla2xxx/qla_target.h +++ b/drivers/scsi/qla2xxx/qla_target.h @@ -116,7 +116,6 @@ (min(1270, ((ql) > 0) ? (QLA_TGT_DATASEGS_PER_CMD_24XX + \ QLA_TGT_DATASEGS_PER_CONT_24XX*((ql) - 1)) : 0)) #endif -#endif #define GET_TARGET_ID(ha, iocb) ((HAS_EXTENDED_IDS(ha)) \ ? le16_to_cpu((iocb)->u.isp2x.target.extended) \ @@ -244,6 +243,7 @@ struct ctio_to_2xxx { #ifndef CTIO_RET_TYPE #define CTIO_RET_TYPE 0x17 /* CTIO return entry */ #define ATIO_TYPE7 0x06 /* Accept target I/O entry for 24xx */ +#endif struct fcp_hdr { uint8_t r_ctl; diff --git a/drivers/scsi/qla2xxx/tcm_qla2xxx.c b/drivers/scsi/qla2xxx/tcm_qla2xxx.c index b55fc768a2a7..8b4890cdd4ca 100644 --- a/drivers/scsi/qla2xxx/tcm_qla2xxx.c +++ b/drivers/scsi/qla2xxx/tcm_qla2xxx.c @@ -644,7 +644,6 @@ static int tcm_qla2xxx_queue_data_in(struct se_cmd *se_cmd) { struct qla_tgt_cmd *cmd = container_of(se_cmd, struct qla_tgt_cmd, se_cmd); - struct scsi_qla_host *vha = cmd->vha; if (cmd->aborted) { /* Cmd can loop during Q-full. tcm_qla2xxx_aborted_task @@ -657,7 +656,6 @@ static int tcm_qla2xxx_queue_data_in(struct se_cmd *se_cmd) cmd->se_cmd.transport_state, cmd->se_cmd.t_state, cmd->se_cmd.se_cmd_flags); - vha->hw->tgt.tgt_ops->free_cmd(cmd); return 0; } @@ -685,7 +683,6 @@ static int tcm_qla2xxx_queue_status(struct se_cmd *se_cmd) { struct qla_tgt_cmd *cmd = container_of(se_cmd, struct qla_tgt_cmd, se_cmd); - struct scsi_qla_host *vha = cmd->vha; int xmit_type = QLA_TGT_XMIT_STATUS; if (cmd->aborted) { @@ -699,7 +696,6 @@ static int tcm_qla2xxx_queue_status(struct se_cmd *se_cmd) cmd, kref_read(&cmd->se_cmd.cmd_kref), cmd->se_cmd.transport_state, cmd->se_cmd.t_state, cmd->se_cmd.se_cmd_flags); - vha->hw->tgt.tgt_ops->free_cmd(cmd); return 0; } cmd->bufflen = se_cmd->data_length; diff --git a/drivers/scsi/scsi_transport_iscsi.c b/drivers/scsi/scsi_transport_iscsi.c index 91074fd97f64..f4bf62b007a0 100644 --- a/drivers/scsi/scsi_transport_iscsi.c +++ b/drivers/scsi/scsi_transport_iscsi.c @@ -2475,6 +2475,7 @@ static void iscsi_if_stop_conn(struct iscsi_cls_conn *conn, int flag) */ mutex_lock(&conn_mutex); conn->transport->stop_conn(conn, flag); + conn->state = ISCSI_CONN_DOWN; mutex_unlock(&conn_mutex); } @@ -2901,6 +2902,13 @@ iscsi_set_param(struct iscsi_transport *transport, struct iscsi_uevent *ev) default: err = transport->set_param(conn, ev->u.set_param.param, data, ev->u.set_param.len); + if ((conn->state == ISCSI_CONN_BOUND) || + (conn->state == ISCSI_CONN_UP)) { + err = transport->set_param(conn, ev->u.set_param.param, + data, ev->u.set_param.len); + } else { + return -ENOTCONN; + } } return err; @@ -2960,6 +2968,7 @@ static int iscsi_if_ep_disconnect(struct iscsi_transport *transport, mutex_lock(&conn->ep_mutex); conn->ep = NULL; mutex_unlock(&conn->ep_mutex); + conn->state = ISCSI_CONN_DOWN; } transport->ep_disconnect(ep); @@ -3727,6 +3736,8 @@ iscsi_if_recv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, uint32_t *group) ev->r.retcode = transport->bind_conn(session, conn, ev->u.b_conn.transport_eph, ev->u.b_conn.is_leading); + if (!ev->r.retcode) + conn->state = ISCSI_CONN_BOUND; mutex_unlock(&conn_mutex); if (ev->r.retcode || !transport->ep_connect) @@ -3966,7 +3977,8 @@ iscsi_conn_attr(local_ipaddr, ISCSI_PARAM_LOCAL_IPADDR); static const char *const connection_state_names[] = { [ISCSI_CONN_UP] = "up", [ISCSI_CONN_DOWN] = "down", - [ISCSI_CONN_FAILED] = "failed" + [ISCSI_CONN_FAILED] = "failed", + [ISCSI_CONN_BOUND] = "bound" }; static ssize_t show_conn_state(struct device *dev, diff --git a/drivers/scsi/scsi_transport_srp.c b/drivers/scsi/scsi_transport_srp.c index 1e939a2a387f..98a34ed10f1a 100644 --- a/drivers/scsi/scsi_transport_srp.c +++ b/drivers/scsi/scsi_transport_srp.c @@ -541,7 +541,7 @@ int srp_reconnect_rport(struct srp_rport *rport) res = mutex_lock_interruptible(&rport->mutex); if (res) goto out; - if (rport->state != SRP_RPORT_FAIL_FAST) + if (rport->state != SRP_RPORT_FAIL_FAST && rport->state != SRP_RPORT_LOST) /* * sdev state must be SDEV_TRANSPORT_OFFLINE, transition * to SDEV_BLOCK is illegal. Calling scsi_target_unblock() diff --git a/drivers/scsi/sd_zbc.c b/drivers/scsi/sd_zbc.c index ee558675eab4..994f1b8e3504 100644 --- a/drivers/scsi/sd_zbc.c +++ b/drivers/scsi/sd_zbc.c @@ -280,27 +280,28 @@ static int sd_zbc_update_wp_offset_cb(struct blk_zone *zone, unsigned int idx, static void sd_zbc_update_wp_offset_workfn(struct work_struct *work) { struct scsi_disk *sdkp; + unsigned long flags; unsigned int zno; int ret; sdkp = container_of(work, struct scsi_disk, zone_wp_offset_work); - spin_lock_bh(&sdkp->zones_wp_offset_lock); + spin_lock_irqsave(&sdkp->zones_wp_offset_lock, flags); for (zno = 0; zno < sdkp->nr_zones; zno++) { if (sdkp->zones_wp_offset[zno] != SD_ZBC_UPDATING_WP_OFST) continue; - spin_unlock_bh(&sdkp->zones_wp_offset_lock); + spin_unlock_irqrestore(&sdkp->zones_wp_offset_lock, flags); ret = sd_zbc_do_report_zones(sdkp, sdkp->zone_wp_update_buf, SD_BUF_SIZE, zno * sdkp->zone_blocks, true); - spin_lock_bh(&sdkp->zones_wp_offset_lock); + spin_lock_irqsave(&sdkp->zones_wp_offset_lock, flags); if (!ret) sd_zbc_parse_report(sdkp, sdkp->zone_wp_update_buf + 64, zno, sd_zbc_update_wp_offset_cb, sdkp); } - spin_unlock_bh(&sdkp->zones_wp_offset_lock); + spin_unlock_irqrestore(&sdkp->zones_wp_offset_lock, flags); scsi_device_put(sdkp->device); } @@ -324,6 +325,7 @@ blk_status_t sd_zbc_prepare_zone_append(struct scsi_cmnd *cmd, sector_t *lba, struct request *rq = cmd->request; struct scsi_disk *sdkp = scsi_disk(rq->rq_disk); unsigned int wp_offset, zno = blk_rq_zone_no(rq); + unsigned long flags; blk_status_t ret; ret = sd_zbc_cmnd_checks(cmd); @@ -337,7 +339,7 @@ blk_status_t sd_zbc_prepare_zone_append(struct scsi_cmnd *cmd, sector_t *lba, if (!blk_req_zone_write_trylock(rq)) return BLK_STS_ZONE_RESOURCE; - spin_lock_bh(&sdkp->zones_wp_offset_lock); + spin_lock_irqsave(&sdkp->zones_wp_offset_lock, flags); wp_offset = sdkp->zones_wp_offset[zno]; switch (wp_offset) { case SD_ZBC_INVALID_WP_OFST: @@ -366,7 +368,7 @@ blk_status_t sd_zbc_prepare_zone_append(struct scsi_cmnd *cmd, sector_t *lba, *lba += wp_offset; } - spin_unlock_bh(&sdkp->zones_wp_offset_lock); + spin_unlock_irqrestore(&sdkp->zones_wp_offset_lock, flags); if (ret) blk_req_zone_write_unlock(rq); return ret; @@ -445,6 +447,7 @@ static unsigned int sd_zbc_zone_wp_update(struct scsi_cmnd *cmd, struct scsi_disk *sdkp = scsi_disk(rq->rq_disk); unsigned int zno = blk_rq_zone_no(rq); enum req_opf op = req_op(rq); + unsigned long flags; /* * If we got an error for a command that needs updating the write @@ -452,7 +455,7 @@ static unsigned int sd_zbc_zone_wp_update(struct scsi_cmnd *cmd, * invalid to force an update from disk the next time a zone append * command is issued. */ - spin_lock_bh(&sdkp->zones_wp_offset_lock); + spin_lock_irqsave(&sdkp->zones_wp_offset_lock, flags); if (result && op != REQ_OP_ZONE_RESET_ALL) { if (op == REQ_OP_ZONE_APPEND) { @@ -496,7 +499,7 @@ static unsigned int sd_zbc_zone_wp_update(struct scsi_cmnd *cmd, } unlock_wp_offset: - spin_unlock_bh(&sdkp->zones_wp_offset_lock); + spin_unlock_irqrestore(&sdkp->zones_wp_offset_lock, flags); return good_bytes; } diff --git a/drivers/scsi/smartpqi/smartpqi_init.c b/drivers/scsi/smartpqi/smartpqi_init.c index c53f456fbd09..a1dacb6e993e 100644 --- a/drivers/scsi/smartpqi/smartpqi_init.c +++ b/drivers/scsi/smartpqi/smartpqi_init.c @@ -48,7 +48,6 @@ MODULE_AUTHOR("Microsemi"); MODULE_DESCRIPTION("Driver for Microsemi Smart Family Controller version " DRIVER_VERSION); -MODULE_SUPPORTED_DEVICE("Microsemi Smart Family Controllers"); MODULE_VERSION(DRIVER_VERSION); MODULE_LICENSE("GPL"); diff --git a/drivers/scsi/st.c b/drivers/scsi/st.c index 841ad2fc369a..9ca536aae784 100644 --- a/drivers/scsi/st.c +++ b/drivers/scsi/st.c @@ -1269,8 +1269,8 @@ static int st_open(struct inode *inode, struct file *filp) spin_lock(&st_use_lock); if (STp->in_use) { spin_unlock(&st_use_lock); - scsi_tape_put(STp); DEBC_printk(STp, "Device already in use.\n"); + scsi_tape_put(STp); return (-EBUSY); } diff --git a/drivers/scsi/ufs/ufs-mediatek.c b/drivers/scsi/ufs/ufs-mediatek.c index c55202b92a43..a981f261b304 100644 --- a/drivers/scsi/ufs/ufs-mediatek.c +++ b/drivers/scsi/ufs/ufs-mediatek.c @@ -911,7 +911,7 @@ static void ufs_mtk_vreg_set_lpm(struct ufs_hba *hba, bool lpm) if (!hba->vreg_info.vccq2 || !hba->vreg_info.vcc) return; - if (lpm & !hba->vreg_info.vcc->enabled) + if (lpm && !hba->vreg_info.vcc->enabled) regulator_set_mode(hba->vreg_info.vccq2->reg, REGULATOR_MODE_IDLE); else if (!lpm) diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c index c86760788c72..d3d05e997c13 100644 --- a/drivers/scsi/ufs/ufshcd.c +++ b/drivers/scsi/ufs/ufshcd.c @@ -6386,37 +6386,34 @@ static int __ufshcd_issue_tm_cmd(struct ufs_hba *hba, DECLARE_COMPLETION_ONSTACK(wait); struct request *req; unsigned long flags; - int free_slot, task_tag, err; + int task_tag, err; /* - * Get free slot, sleep if slots are unavailable. - * Even though we use wait_event() which sleeps indefinitely, - * the maximum wait time is bounded by %TM_CMD_TIMEOUT. + * blk_get_request() is used here only to get a free tag. */ req = blk_get_request(q, REQ_OP_DRV_OUT, 0); if (IS_ERR(req)) return PTR_ERR(req); req->end_io_data = &wait; - free_slot = req->tag; - WARN_ON_ONCE(free_slot < 0 || free_slot >= hba->nutmrs); ufshcd_hold(hba, false); spin_lock_irqsave(host->host_lock, flags); - task_tag = hba->nutrs + free_slot; + blk_mq_start_request(req); + task_tag = req->tag; treq->req_header.dword_0 |= cpu_to_be32(task_tag); - memcpy(hba->utmrdl_base_addr + free_slot, treq, sizeof(*treq)); - ufshcd_vops_setup_task_mgmt(hba, free_slot, tm_function); + memcpy(hba->utmrdl_base_addr + task_tag, treq, sizeof(*treq)); + ufshcd_vops_setup_task_mgmt(hba, task_tag, tm_function); /* send command to the controller */ - __set_bit(free_slot, &hba->outstanding_tasks); + __set_bit(task_tag, &hba->outstanding_tasks); /* Make sure descriptors are ready before ringing the task doorbell */ wmb(); - ufshcd_writel(hba, 1 << free_slot, REG_UTP_TASK_REQ_DOOR_BELL); + ufshcd_writel(hba, 1 << task_tag, REG_UTP_TASK_REQ_DOOR_BELL); /* Make sure that doorbell is committed immediately */ wmb(); @@ -6436,24 +6433,24 @@ static int __ufshcd_issue_tm_cmd(struct ufs_hba *hba, ufshcd_add_tm_upiu_trace(hba, task_tag, UFS_TM_ERR); dev_err(hba->dev, "%s: task management cmd 0x%.2x timed-out\n", __func__, tm_function); - if (ufshcd_clear_tm_cmd(hba, free_slot)) - dev_WARN(hba->dev, "%s: unable clear tm cmd (slot %d) after timeout\n", - __func__, free_slot); + if (ufshcd_clear_tm_cmd(hba, task_tag)) + dev_WARN(hba->dev, "%s: unable to clear tm cmd (slot %d) after timeout\n", + __func__, task_tag); err = -ETIMEDOUT; } else { err = 0; - memcpy(treq, hba->utmrdl_base_addr + free_slot, sizeof(*treq)); + memcpy(treq, hba->utmrdl_base_addr + task_tag, sizeof(*treq)); ufshcd_add_tm_upiu_trace(hba, task_tag, UFS_TM_COMP); } spin_lock_irqsave(hba->host->host_lock, flags); - __clear_bit(free_slot, &hba->outstanding_tasks); + __clear_bit(task_tag, &hba->outstanding_tasks); spin_unlock_irqrestore(hba->host->host_lock, flags); + ufshcd_release(hba); blk_put_request(req); - ufshcd_release(hba); return err; } diff --git a/drivers/sh/maple/maple.c b/drivers/sh/maple/maple.c index e5d7fb81ad66..bd0fbcdbdefe 100644 --- a/drivers/sh/maple/maple.c +++ b/drivers/sh/maple/maple.c @@ -30,7 +30,6 @@ MODULE_AUTHOR("Adrian McMenamin <adrian@mcmen.demon.co.uk>"); MODULE_DESCRIPTION("Maple bus driver for Dreamcast"); MODULE_LICENSE("GPL v2"); -MODULE_SUPPORTED_DEVICE("{{SEGA, Dreamcast/Maple}}"); static void maple_dma_handler(struct work_struct *work); static void maple_vblank_handler(struct work_struct *work); diff --git a/drivers/soc/fsl/qbman/qman.c b/drivers/soc/fsl/qbman/qman.c index a1b9be1d105a..fde4edd83c14 100644 --- a/drivers/soc/fsl/qbman/qman.c +++ b/drivers/soc/fsl/qbman/qman.c @@ -186,7 +186,7 @@ struct qm_eqcr_entry { __be32 tag; struct qm_fd fd; u8 __reserved3[32]; -} __packed; +} __packed __aligned(8); #define QM_EQCR_VERB_VBIT 0x80 #define QM_EQCR_VERB_CMD_MASK 0x61 /* but only one value; */ #define QM_EQCR_VERB_CMD_ENQUEUE 0x01 diff --git a/drivers/soc/litex/litex_soc_ctrl.c b/drivers/soc/litex/litex_soc_ctrl.c index 6268bfa7f0d6..c3e379a990f2 100644 --- a/drivers/soc/litex/litex_soc_ctrl.c +++ b/drivers/soc/litex/litex_soc_ctrl.c @@ -13,7 +13,6 @@ #include <linux/platform_device.h> #include <linux/printk.h> #include <linux/module.h> -#include <linux/errno.h> #include <linux/io.h> #include <linux/reboot.h> diff --git a/drivers/soc/qcom/qcom-geni-se.c b/drivers/soc/qcom/qcom-geni-se.c index f42954e2c98e..1fd29f93ff6d 100644 --- a/drivers/soc/qcom/qcom-geni-se.c +++ b/drivers/soc/qcom/qcom-geni-se.c @@ -3,7 +3,6 @@ #include <linux/acpi.h> #include <linux/clk.h> -#include <linux/console.h> #include <linux/slab.h> #include <linux/dma-mapping.h> #include <linux/io.h> @@ -92,14 +91,11 @@ struct geni_wrapper { struct device *dev; void __iomem *base; struct clk_bulk_data ahb_clks[NUM_AHB_CLKS]; - struct geni_icc_path to_core; }; static const char * const icc_path_names[] = {"qup-core", "qup-config", "qup-memory"}; -static struct geni_wrapper *earlycon_wrapper; - #define QUP_HW_VER_REG 0x4 /* Common SE registers */ @@ -843,44 +839,11 @@ int geni_icc_disable(struct geni_se *se) } EXPORT_SYMBOL(geni_icc_disable); -void geni_remove_earlycon_icc_vote(void) -{ - struct platform_device *pdev; - struct geni_wrapper *wrapper; - struct device_node *parent; - struct device_node *child; - - if (!earlycon_wrapper) - return; - - wrapper = earlycon_wrapper; - parent = of_get_next_parent(wrapper->dev->of_node); - for_each_child_of_node(parent, child) { - if (!of_device_is_compatible(child, "qcom,geni-se-qup")) - continue; - - pdev = of_find_device_by_node(child); - if (!pdev) - continue; - - wrapper = platform_get_drvdata(pdev); - icc_put(wrapper->to_core.path); - wrapper->to_core.path = NULL; - - } - of_node_put(parent); - - earlycon_wrapper = NULL; -} -EXPORT_SYMBOL(geni_remove_earlycon_icc_vote); - static int geni_se_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; struct resource *res; struct geni_wrapper *wrapper; - struct console __maybe_unused *bcon; - bool __maybe_unused has_earlycon = false; int ret; wrapper = devm_kzalloc(dev, sizeof(*wrapper), GFP_KERNEL); @@ -903,43 +866,6 @@ static int geni_se_probe(struct platform_device *pdev) } } -#ifdef CONFIG_SERIAL_EARLYCON - for_each_console(bcon) { - if (!strcmp(bcon->name, "qcom_geni")) { - has_earlycon = true; - break; - } - } - if (!has_earlycon) - goto exit; - - wrapper->to_core.path = devm_of_icc_get(dev, "qup-core"); - if (IS_ERR(wrapper->to_core.path)) - return PTR_ERR(wrapper->to_core.path); - /* - * Put minmal BW request on core clocks on behalf of early console. - * The vote will be removed earlycon exit function. - * - * Note: We are putting vote on each QUP wrapper instead only to which - * earlycon is connected because QUP core clock of different wrapper - * share same voltage domain. If core1 is put to 0, then core2 will - * also run at 0, if not voted. Default ICC vote will be removed ASA - * we touch any of the core clock. - * core1 = core2 = max(core1, core2) - */ - ret = icc_set_bw(wrapper->to_core.path, GENI_DEFAULT_BW, - GENI_DEFAULT_BW); - if (ret) { - dev_err(&pdev->dev, "%s: ICC BW voting failed for core: %d\n", - __func__, ret); - return ret; - } - - if (of_get_compatible_child(pdev->dev.of_node, "qcom,geni-debug-uart")) - earlycon_wrapper = wrapper; - of_node_put(pdev->dev.of_node); -exit: -#endif dev_set_drvdata(dev, wrapper); dev_dbg(dev, "GENI SE Driver probed\n"); return devm_of_platform_populate(dev); diff --git a/drivers/soc/ti/omap_prm.c b/drivers/soc/ti/omap_prm.c index bf1468e5bccb..51143a68a889 100644 --- a/drivers/soc/ti/omap_prm.c +++ b/drivers/soc/ti/omap_prm.c @@ -332,7 +332,7 @@ static const struct omap_prm_data dra7_prm_data[] = { { .name = "l3init", .base = 0x4ae07300, .pwrstctrl = 0x0, .pwrstst = 0x4, .dmap = &omap_prm_alwon, - .rstctrl = 0x10, .rstst = 0x14, .rstmap = rst_map_012, + .rstctrl = 0x10, .rstst = 0x14, .rstmap = rst_map_01, .clkdm_name = "pcie" }, { @@ -830,8 +830,12 @@ static int omap_reset_deassert(struct reset_controller_dev *rcdev, reset->prm->data->name, id); exit: - if (reset->clkdm) + if (reset->clkdm) { + /* At least dra7 iva needs a delay before clkdm idle */ + if (has_rstst) + udelay(1); pdata->clkdm_allow_idle(reset->clkdm); + } return ret; } diff --git a/drivers/spi/spi-cadence-quadspi.c b/drivers/spi/spi-cadence-quadspi.c index 442cc7c53a47..52ddb3255d88 100644 --- a/drivers/spi/spi-cadence-quadspi.c +++ b/drivers/spi/spi-cadence-quadspi.c @@ -1433,6 +1433,7 @@ static int cqspi_probe(struct platform_device *pdev) cqspi = spi_master_get_devdata(master); cqspi->pdev = pdev; + platform_set_drvdata(pdev, cqspi); /* Obtain configuration from OF. */ ret = cqspi_of_get_pdata(cqspi); diff --git a/drivers/staging/comedi/drivers/cb_pcidas.c b/drivers/staging/comedi/drivers/cb_pcidas.c index d740c4782775..2f20bd56ec6c 100644 --- a/drivers/staging/comedi/drivers/cb_pcidas.c +++ b/drivers/staging/comedi/drivers/cb_pcidas.c @@ -1281,7 +1281,7 @@ static int cb_pcidas_auto_attach(struct comedi_device *dev, devpriv->amcc + AMCC_OP_REG_INTCSR); ret = request_irq(pcidev->irq, cb_pcidas_interrupt, IRQF_SHARED, - dev->board_name, dev); + "cb_pcidas", dev); if (ret) { dev_dbg(dev->class_dev, "unable to allocate irq %d\n", pcidev->irq); diff --git a/drivers/staging/comedi/drivers/cb_pcidas64.c b/drivers/staging/comedi/drivers/cb_pcidas64.c index fa987bb0e7cd..6d3ba399a7f0 100644 --- a/drivers/staging/comedi/drivers/cb_pcidas64.c +++ b/drivers/staging/comedi/drivers/cb_pcidas64.c @@ -4035,7 +4035,7 @@ static int auto_attach(struct comedi_device *dev, init_stc_registers(dev); retval = request_irq(pcidev->irq, handle_interrupt, IRQF_SHARED, - dev->board_name, dev); + "cb_pcidas64", dev); if (retval) { dev_dbg(dev->class_dev, "unable to allocate irq %u\n", pcidev->irq); diff --git a/drivers/staging/comedi/drivers/vmk80xx.c b/drivers/staging/comedi/drivers/vmk80xx.c index 7956abcbae22..9f920819cd74 100644 --- a/drivers/staging/comedi/drivers/vmk80xx.c +++ b/drivers/staging/comedi/drivers/vmk80xx.c @@ -877,5 +877,4 @@ module_comedi_usb_driver(vmk80xx_driver, vmk80xx_usb_driver); MODULE_AUTHOR("Manuel Gebele <forensixs@gmx.de>"); MODULE_DESCRIPTION("Velleman USB Board Low-Level Driver"); -MODULE_SUPPORTED_DEVICE("K8055/K8061 aka VM110/VM140"); MODULE_LICENSE("GPL"); diff --git a/drivers/staging/media/tegra-video/vi.c b/drivers/staging/media/tegra-video/vi.c index 7a09061cda57..df5ca3596470 100644 --- a/drivers/staging/media/tegra-video/vi.c +++ b/drivers/staging/media/tegra-video/vi.c @@ -1131,8 +1131,8 @@ static void tegra_channel_host1x_syncpts_free(struct tegra_vi_channel *chan) int i; for (i = 0; i < chan->numgangports; i++) { - host1x_syncpt_free(chan->mw_ack_sp[i]); - host1x_syncpt_free(chan->frame_start_sp[i]); + host1x_syncpt_put(chan->mw_ack_sp[i]); + host1x_syncpt_put(chan->frame_start_sp[i]); } } @@ -1177,7 +1177,7 @@ static int tegra_channel_host1x_syncpt_init(struct tegra_vi_channel *chan) mw_sp = host1x_syncpt_request(&vi->client, flags); if (!mw_sp) { dev_err(vi->dev, "failed to request memory ack syncpoint\n"); - host1x_syncpt_free(fs_sp); + host1x_syncpt_put(fs_sp); ret = -ENOMEM; goto free_syncpts; } diff --git a/drivers/staging/rtl8192e/rtllib.h b/drivers/staging/rtl8192e/rtllib.h index b84f00b8d18b..4cabaf21c1ca 100644 --- a/drivers/staging/rtl8192e/rtllib.h +++ b/drivers/staging/rtl8192e/rtllib.h @@ -1105,7 +1105,7 @@ struct rtllib_network { bool bWithAironetIE; bool bCkipSupported; bool bCcxRmEnable; - u16 CcxRmState[2]; + u8 CcxRmState[2]; bool bMBssidValid; u8 MBssidMask; u8 MBssid[ETH_ALEN]; diff --git a/drivers/staging/rtl8192e/rtllib_rx.c b/drivers/staging/rtl8192e/rtllib_rx.c index 66c135321da4..15bbb63ca130 100644 --- a/drivers/staging/rtl8192e/rtllib_rx.c +++ b/drivers/staging/rtl8192e/rtllib_rx.c @@ -1967,7 +1967,7 @@ static void rtllib_parse_mife_generic(struct rtllib_device *ieee, info_element->data[2] == 0x96 && info_element->data[3] == 0x01) { if (info_element->len == 6) { - memcpy(network->CcxRmState, &info_element[4], 2); + memcpy(network->CcxRmState, &info_element->data[4], 2); if (network->CcxRmState[0] != 0) network->bCcxRmEnable = true; else diff --git a/drivers/staging/vt6655/rxtx.h b/drivers/staging/vt6655/rxtx.h index e7061d383306..c3c2c1566882 100644 --- a/drivers/staging/vt6655/rxtx.h +++ b/drivers/staging/vt6655/rxtx.h @@ -150,7 +150,7 @@ struct vnt_cts { u16 reserved; struct ieee80211_cts data; u16 reserved2; -} __packed; +} __packed __aligned(2); struct vnt_cts_fb { struct vnt_phy_field b; @@ -160,7 +160,7 @@ struct vnt_cts_fb { __le16 cts_duration_ba_f1; struct ieee80211_cts data; u16 reserved2; -} __packed; +} __packed __aligned(2); struct vnt_tx_fifo_head { u8 tx_key[WLAN_KEY_LEN_CCMP]; diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c index d0e7ed8f28cc..e5c443bfbdf9 100644 --- a/drivers/target/iscsi/iscsi_target.c +++ b/drivers/target/iscsi/iscsi_target.c @@ -1166,6 +1166,7 @@ int iscsit_setup_scsi_cmd(struct iscsi_conn *conn, struct iscsi_cmd *cmd, target_get_sess_cmd(&cmd->se_cmd, true); + cmd->se_cmd.tag = (__force u32)cmd->init_task_tag; cmd->sense_reason = target_cmd_init_cdb(&cmd->se_cmd, hdr->cdb); if (cmd->sense_reason) { if (cmd->sense_reason == TCM_OUT_OF_RESOURCES) { @@ -1180,8 +1181,6 @@ int iscsit_setup_scsi_cmd(struct iscsi_conn *conn, struct iscsi_cmd *cmd, if (cmd->sense_reason) goto attach_cmd; - /* only used for printks or comparing with ->ref_task_tag */ - cmd->se_cmd.tag = (__force u32)cmd->init_task_tag; cmd->sense_reason = target_cmd_parse_cdb(&cmd->se_cmd); if (cmd->sense_reason) goto attach_cmd; diff --git a/drivers/target/target_core_pscsi.c b/drivers/target/target_core_pscsi.c index 3cbc074992bc..9ee797b8cb7e 100644 --- a/drivers/target/target_core_pscsi.c +++ b/drivers/target/target_core_pscsi.c @@ -882,7 +882,6 @@ pscsi_map_sg(struct se_cmd *cmd, struct scatterlist *sgl, u32 sgl_nents, if (!bio) { new_bio: nr_vecs = bio_max_segs(nr_pages); - nr_pages -= nr_vecs; /* * Calls bio_kmalloc() and sets bio->bi_end_io() */ @@ -939,6 +938,14 @@ new_bio: return 0; fail: + if (bio) + bio_put(bio); + while (req->bio) { + bio = req->bio; + req->bio = bio->bi_next; + bio_put(bio); + } + req->biotail = NULL; return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE; } diff --git a/drivers/tee/optee/core.c b/drivers/tee/optee/core.c index cf4718c6d35d..319a1e701163 100644 --- a/drivers/tee/optee/core.c +++ b/drivers/tee/optee/core.c @@ -747,7 +747,6 @@ module_platform_driver(optee_driver); MODULE_AUTHOR("Linaro"); MODULE_DESCRIPTION("OP-TEE driver"); -MODULE_SUPPORTED_DEVICE(""); MODULE_VERSION("1.0"); MODULE_LICENSE("GPL v2"); MODULE_ALIAS("platform:optee"); diff --git a/drivers/thermal/thermal_sysfs.c b/drivers/thermal/thermal_sysfs.c index 345917a58f2f..1c4aac8464a7 100644 --- a/drivers/thermal/thermal_sysfs.c +++ b/drivers/thermal/thermal_sysfs.c @@ -674,6 +674,9 @@ void thermal_cooling_device_stats_update(struct thermal_cooling_device *cdev, { struct cooling_dev_stats *stats = cdev->stats; + if (!stats) + return; + spin_lock(&stats->lock); if (stats->state == new_state) diff --git a/drivers/thunderbolt/retimer.c b/drivers/thunderbolt/retimer.c index 620bcf586ee2..c44fad2b9fbb 100644 --- a/drivers/thunderbolt/retimer.c +++ b/drivers/thunderbolt/retimer.c @@ -347,7 +347,7 @@ static int tb_retimer_add(struct tb_port *port, u8 index, u32 auth_status) ret = tb_retimer_nvm_add(rt); if (ret) { dev_err(&rt->dev, "failed to add NVM devices: %d\n", ret); - device_del(&rt->dev); + device_unregister(&rt->dev); return ret; } @@ -406,7 +406,7 @@ static struct tb_retimer *tb_port_find_retimer(struct tb_port *port, u8 index) */ int tb_retimer_scan(struct tb_port *port) { - u32 status[TB_MAX_RETIMER_INDEX] = {}; + u32 status[TB_MAX_RETIMER_INDEX + 1] = {}; int ret, i, last_idx = 0; if (!port->cap_usb4) diff --git a/drivers/thunderbolt/switch.c b/drivers/thunderbolt/switch.c index b63fecca6c2a..2a95b4ce06c0 100644 --- a/drivers/thunderbolt/switch.c +++ b/drivers/thunderbolt/switch.c @@ -768,12 +768,6 @@ static int tb_init_port(struct tb_port *port) tb_dump_port(port->sw->tb, &port->config); - /* Control port does not need HopID allocation */ - if (port->port) { - ida_init(&port->in_hopids); - ida_init(&port->out_hopids); - } - INIT_LIST_HEAD(&port->list); return 0; @@ -1842,10 +1836,8 @@ static void tb_switch_release(struct device *dev) dma_port_free(sw->dma_port); tb_switch_for_each_port(sw, port) { - if (!port->disabled) { - ida_destroy(&port->in_hopids); - ida_destroy(&port->out_hopids); - } + ida_destroy(&port->in_hopids); + ida_destroy(&port->out_hopids); } kfree(sw->uuid); @@ -2025,6 +2017,12 @@ struct tb_switch *tb_switch_alloc(struct tb *tb, struct device *parent, /* minimum setup for tb_find_cap and tb_drom_read to work */ sw->ports[i].sw = sw; sw->ports[i].port = i; + + /* Control port does not need HopID allocation */ + if (i) { + ida_init(&sw->ports[i].in_hopids); + ida_init(&sw->ports[i].out_hopids); + } } ret = tb_switch_find_vse_cap(sw, TB_VSE_CAP_PLUG_EVENTS); diff --git a/drivers/thunderbolt/tb.c b/drivers/thunderbolt/tb.c index 1f000ac1728b..c348b1fc0efc 100644 --- a/drivers/thunderbolt/tb.c +++ b/drivers/thunderbolt/tb.c @@ -138,6 +138,10 @@ static void tb_discover_tunnels(struct tb_switch *sw) parent->boot = true; parent = tb_switch_parent(parent); } + } else if (tb_tunnel_is_dp(tunnel)) { + /* Keep the domain from powering down */ + pm_runtime_get_sync(&tunnel->src_port->sw->dev); + pm_runtime_get_sync(&tunnel->dst_port->sw->dev); } list_add_tail(&tunnel->list, &tcm->tunnel_list); diff --git a/drivers/tty/serial/icom.c b/drivers/tty/serial/icom.c index 9a872750581c..94af7a5ea497 100644 --- a/drivers/tty/serial/icom.c +++ b/drivers/tty/serial/icom.c @@ -1639,8 +1639,6 @@ module_exit(icom_exit); MODULE_AUTHOR("Michael Anderson <mjanders@us.ibm.com>"); MODULE_DESCRIPTION("IBM iSeries Serial IOA driver"); -MODULE_SUPPORTED_DEVICE - ("IBM iSeries 2745, 2771, 2772, 2742, 2793 and 2805 Communications adapters"); MODULE_LICENSE("GPL"); MODULE_FIRMWARE("icom_call_setup.bin"); MODULE_FIRMWARE("icom_res_dce.bin"); diff --git a/drivers/tty/serial/jsm/jsm_driver.c b/drivers/tty/serial/jsm/jsm_driver.c index cd30da0ef083..0ea799bf8dbb 100644 --- a/drivers/tty/serial/jsm/jsm_driver.c +++ b/drivers/tty/serial/jsm/jsm_driver.c @@ -19,7 +19,6 @@ MODULE_AUTHOR("Digi International, https://www.digi.com"); MODULE_DESCRIPTION("Driver for the Digi International Neo and Classic PCI based product line"); MODULE_LICENSE("GPL"); -MODULE_SUPPORTED_DEVICE("jsm"); #define JSM_DRIVER_NAME "jsm" #define NR_PORTS 32 diff --git a/drivers/tty/serial/qcom_geni_serial.c b/drivers/tty/serial/qcom_geni_serial.c index 291649f02821..0d85b55ea823 100644 --- a/drivers/tty/serial/qcom_geni_serial.c +++ b/drivers/tty/serial/qcom_geni_serial.c @@ -1177,12 +1177,6 @@ static inline void qcom_geni_serial_enable_early_read(struct geni_se *se, struct console *con) { } #endif -static int qcom_geni_serial_earlycon_exit(struct console *con) -{ - geni_remove_earlycon_icc_vote(); - return 0; -} - static struct qcom_geni_private_data earlycon_private_data; static int __init qcom_geni_serial_earlycon_setup(struct earlycon_device *dev, @@ -1233,7 +1227,6 @@ static int __init qcom_geni_serial_earlycon_setup(struct earlycon_device *dev, writel(stop_bit_len, uport->membase + SE_UART_TX_STOP_BIT_LEN); dev->con->write = qcom_geni_serial_earlycon_write; - dev->con->exit = qcom_geni_serial_earlycon_exit; dev->con->setup = NULL; qcom_geni_serial_enable_early_read(&se, dev->con); diff --git a/drivers/usb/cdns3/cdnsp-gadget.c b/drivers/usb/cdns3/cdnsp-gadget.c index f2ebbacd932e..d7d4bdd57f46 100644 --- a/drivers/usb/cdns3/cdnsp-gadget.c +++ b/drivers/usb/cdns3/cdnsp-gadget.c @@ -1128,6 +1128,10 @@ static int cdnsp_gadget_ep_dequeue(struct usb_ep *ep, return -ESHUTDOWN; } + /* Requests has been dequeued during disabling endpoint. */ + if (!(pep->ep_state & EP_ENABLED)) + return 0; + spin_lock_irqsave(&pdev->lock, flags); ret = cdnsp_ep_dequeue(pep, to_cdnsp_request(request)); spin_unlock_irqrestore(&pdev->lock, flags); diff --git a/drivers/usb/cdns3/cdnsp-ring.c b/drivers/usb/cdns3/cdnsp-ring.c index f9170d177a89..5f0513c96c04 100644 --- a/drivers/usb/cdns3/cdnsp-ring.c +++ b/drivers/usb/cdns3/cdnsp-ring.c @@ -2197,7 +2197,10 @@ static int cdnsp_queue_isoc_tx(struct cdnsp_device *pdev, * inverted in the first TDs isoc TRB. */ field = TRB_TYPE(TRB_ISOC) | TRB_TLBPC(last_burst_pkt) | - start_cycle ? 0 : 1 | TRB_SIA | TRB_TBC(burst_count); + TRB_SIA | TRB_TBC(burst_count); + + if (!start_cycle) + field |= TRB_CYCLE; /* Fill the rest of the TRB fields, and remaining normal TRBs. */ for (i = 0; i < trbs_per_td; i++) { diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c index 39ddb5585ded..3fda1ec961d7 100644 --- a/drivers/usb/class/cdc-acm.c +++ b/drivers/usb/class/cdc-acm.c @@ -147,17 +147,29 @@ static inline int acm_set_control(struct acm *acm, int control) #define acm_send_break(acm, ms) \ acm_ctrl_msg(acm, USB_CDC_REQ_SEND_BREAK, ms, NULL, 0) -static void acm_kill_urbs(struct acm *acm) +static void acm_poison_urbs(struct acm *acm) { int i; - usb_kill_urb(acm->ctrlurb); + usb_poison_urb(acm->ctrlurb); for (i = 0; i < ACM_NW; i++) - usb_kill_urb(acm->wb[i].urb); + usb_poison_urb(acm->wb[i].urb); for (i = 0; i < acm->rx_buflimit; i++) - usb_kill_urb(acm->read_urbs[i]); + usb_poison_urb(acm->read_urbs[i]); +} + +static void acm_unpoison_urbs(struct acm *acm) +{ + int i; + + for (i = 0; i < acm->rx_buflimit; i++) + usb_unpoison_urb(acm->read_urbs[i]); + for (i = 0; i < ACM_NW; i++) + usb_unpoison_urb(acm->wb[i].urb); + usb_unpoison_urb(acm->ctrlurb); } + /* * Write buffer management. * All of these assume proper locks taken by the caller. @@ -226,9 +238,10 @@ static int acm_start_wb(struct acm *acm, struct acm_wb *wb) rc = usb_submit_urb(wb->urb, GFP_ATOMIC); if (rc < 0) { - dev_err(&acm->data->dev, - "%s - usb_submit_urb(write bulk) failed: %d\n", - __func__, rc); + if (rc != -EPERM) + dev_err(&acm->data->dev, + "%s - usb_submit_urb(write bulk) failed: %d\n", + __func__, rc); acm_write_done(acm, wb); } return rc; @@ -313,8 +326,10 @@ static void acm_process_notification(struct acm *acm, unsigned char *buf) acm->iocount.dsr++; if (difference & ACM_CTRL_DCD) acm->iocount.dcd++; - if (newctrl & ACM_CTRL_BRK) + if (newctrl & ACM_CTRL_BRK) { acm->iocount.brk++; + tty_insert_flip_char(&acm->port, 0, TTY_BREAK); + } if (newctrl & ACM_CTRL_RI) acm->iocount.rng++; if (newctrl & ACM_CTRL_FRAMING) @@ -480,11 +495,6 @@ static void acm_read_bulk_callback(struct urb *urb) dev_vdbg(&acm->data->dev, "got urb %d, len %d, status %d\n", rb->index, urb->actual_length, status); - if (!acm->dev) { - dev_dbg(&acm->data->dev, "%s - disconnected\n", __func__); - return; - } - switch (status) { case 0: usb_mark_last_busy(acm->dev); @@ -649,7 +659,8 @@ static void acm_port_dtr_rts(struct tty_port *port, int raise) res = acm_set_control(acm, val); if (res && (acm->ctrl_caps & USB_CDC_CAP_LINE)) - dev_err(&acm->control->dev, "failed to set dtr/rts\n"); + /* This is broken in too many devices to spam the logs */ + dev_dbg(&acm->control->dev, "failed to set dtr/rts\n"); } static int acm_port_activate(struct tty_port *port, struct tty_struct *tty) @@ -731,6 +742,7 @@ static void acm_port_shutdown(struct tty_port *port) * Need to grab write_lock to prevent race with resume, but no need to * hold it due to the tty-port initialised flag. */ + acm_poison_urbs(acm); spin_lock_irq(&acm->write_lock); spin_unlock_irq(&acm->write_lock); @@ -747,7 +759,8 @@ static void acm_port_shutdown(struct tty_port *port) usb_autopm_put_interface_async(acm->control); } - acm_kill_urbs(acm); + acm_unpoison_urbs(acm); + } static void acm_tty_cleanup(struct tty_struct *tty) @@ -1296,13 +1309,6 @@ skip_normal_probe: if (!combined_interfaces && intf != control_interface) return -ENODEV; - if (!combined_interfaces && usb_interface_claimed(data_interface)) { - /* valid in this context */ - dev_dbg(&intf->dev, "The data interface isn't available\n"); - return -EBUSY; - } - - if (data_interface->cur_altsetting->desc.bNumEndpoints < 2 || control_interface->cur_altsetting->desc.bNumEndpoints == 0) return -EINVAL; @@ -1323,8 +1329,8 @@ made_compressed_probe: dev_dbg(&intf->dev, "interfaces are valid\n"); acm = kzalloc(sizeof(struct acm), GFP_KERNEL); - if (acm == NULL) - goto alloc_fail; + if (!acm) + return -ENOMEM; tty_port_init(&acm->port); acm->port.ops = &acm_port_ops; @@ -1341,7 +1347,7 @@ made_compressed_probe: minor = acm_alloc_minor(acm); if (minor < 0) - goto alloc_fail1; + goto err_put_port; acm->minor = minor; acm->dev = usb_dev; @@ -1372,15 +1378,15 @@ made_compressed_probe: buf = usb_alloc_coherent(usb_dev, ctrlsize, GFP_KERNEL, &acm->ctrl_dma); if (!buf) - goto alloc_fail1; + goto err_put_port; acm->ctrl_buffer = buf; if (acm_write_buffers_alloc(acm) < 0) - goto alloc_fail2; + goto err_free_ctrl_buffer; acm->ctrlurb = usb_alloc_urb(0, GFP_KERNEL); if (!acm->ctrlurb) - goto alloc_fail3; + goto err_free_write_buffers; for (i = 0; i < num_rx_buf; i++) { struct acm_rb *rb = &(acm->read_buffers[i]); @@ -1389,13 +1395,13 @@ made_compressed_probe: rb->base = usb_alloc_coherent(acm->dev, readsize, GFP_KERNEL, &rb->dma); if (!rb->base) - goto alloc_fail4; + goto err_free_read_urbs; rb->index = i; rb->instance = acm; urb = usb_alloc_urb(0, GFP_KERNEL); if (!urb) - goto alloc_fail4; + goto err_free_read_urbs; urb->transfer_flags |= URB_NO_TRANSFER_DMA_MAP; urb->transfer_dma = rb->dma; @@ -1416,8 +1422,8 @@ made_compressed_probe: struct acm_wb *snd = &(acm->wb[i]); snd->urb = usb_alloc_urb(0, GFP_KERNEL); - if (snd->urb == NULL) - goto alloc_fail5; + if (!snd->urb) + goto err_free_write_urbs; if (usb_endpoint_xfer_int(epwrite)) usb_fill_int_urb(snd->urb, usb_dev, acm->out, @@ -1435,7 +1441,7 @@ made_compressed_probe: i = device_create_file(&intf->dev, &dev_attr_bmCapabilities); if (i < 0) - goto alloc_fail5; + goto err_free_write_urbs; if (h.usb_cdc_country_functional_desc) { /* export the country data */ struct usb_cdc_country_functional_desc * cfd = @@ -1480,20 +1486,21 @@ skip_countries: acm->nb_index = 0; acm->nb_size = 0; - dev_info(&intf->dev, "ttyACM%d: USB ACM device\n", minor); - acm->line.dwDTERate = cpu_to_le32(9600); acm->line.bDataBits = 8; acm_set_line(acm, &acm->line); - usb_driver_claim_interface(&acm_driver, data_interface, acm); - usb_set_intfdata(data_interface, acm); + if (!acm->combined_interfaces) { + rv = usb_driver_claim_interface(&acm_driver, data_interface, acm); + if (rv) + goto err_remove_files; + } tty_dev = tty_port_register_device(&acm->port, acm_tty_driver, minor, &control_interface->dev); if (IS_ERR(tty_dev)) { rv = PTR_ERR(tty_dev); - goto alloc_fail6; + goto err_release_data_interface; } if (quirks & CLEAR_HALT_CONDITIONS) { @@ -1501,32 +1508,39 @@ skip_countries: usb_clear_halt(usb_dev, acm->out); } + dev_info(&intf->dev, "ttyACM%d: USB ACM device\n", minor); + return 0; -alloc_fail6: + +err_release_data_interface: + if (!acm->combined_interfaces) { + /* Clear driver data so that disconnect() returns early. */ + usb_set_intfdata(data_interface, NULL); + usb_driver_release_interface(&acm_driver, data_interface); + } +err_remove_files: if (acm->country_codes) { device_remove_file(&acm->control->dev, &dev_attr_wCountryCodes); device_remove_file(&acm->control->dev, &dev_attr_iCountryCodeRelDate); - kfree(acm->country_codes); } device_remove_file(&acm->control->dev, &dev_attr_bmCapabilities); -alloc_fail5: - usb_set_intfdata(intf, NULL); +err_free_write_urbs: for (i = 0; i < ACM_NW; i++) usb_free_urb(acm->wb[i].urb); -alloc_fail4: +err_free_read_urbs: for (i = 0; i < num_rx_buf; i++) usb_free_urb(acm->read_urbs[i]); acm_read_buffers_free(acm); usb_free_urb(acm->ctrlurb); -alloc_fail3: +err_free_write_buffers: acm_write_buffers_free(acm); -alloc_fail2: +err_free_ctrl_buffer: usb_free_coherent(usb_dev, ctrlsize, acm->ctrl_buffer, acm->ctrl_dma); -alloc_fail1: +err_put_port: tty_port_put(&acm->port); -alloc_fail: + return rv; } @@ -1540,8 +1554,14 @@ static void acm_disconnect(struct usb_interface *intf) if (!acm) return; - mutex_lock(&acm->mutex); acm->disconnected = true; + /* + * there is a circular dependency. acm_softint() can resubmit + * the URBs in error handling so we need to block any + * submission right away + */ + acm_poison_urbs(acm); + mutex_lock(&acm->mutex); if (acm->country_codes) { device_remove_file(&acm->control->dev, &dev_attr_wCountryCodes); @@ -1560,7 +1580,6 @@ static void acm_disconnect(struct usb_interface *intf) tty_kref_put(tty); } - acm_kill_urbs(acm); cancel_delayed_work_sync(&acm->dwork); tty_unregister_device(acm_tty_driver, acm->minor); @@ -1602,7 +1621,7 @@ static int acm_suspend(struct usb_interface *intf, pm_message_t message) if (cnt) return 0; - acm_kill_urbs(acm); + acm_poison_urbs(acm); cancel_delayed_work_sync(&acm->dwork); acm->urbs_in_error_delay = 0; @@ -1615,6 +1634,7 @@ static int acm_resume(struct usb_interface *intf) struct urb *urb; int rv = 0; + acm_unpoison_urbs(acm); spin_lock_irq(&acm->write_lock); if (--acm->susp_count) diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c index 6ade3daf7858..76ac5d6555ae 100644 --- a/drivers/usb/core/quirks.c +++ b/drivers/usb/core/quirks.c @@ -498,6 +498,10 @@ static const struct usb_device_id usb_quirk_list[] = { /* DJI CineSSD */ { USB_DEVICE(0x2ca3, 0x0031), .driver_info = USB_QUIRK_NO_LPM }, + /* Fibocom L850-GL LTE Modem */ + { USB_DEVICE(0x2cb7, 0x0007), .driver_info = + USB_QUIRK_IGNORE_REMOTE_WAKEUP }, + /* INTEL VALUE SSD */ { USB_DEVICE(0x8086, 0xf1a5), .driver_info = USB_QUIRK_RESET_RESUME }, diff --git a/drivers/usb/dwc2/hcd.c b/drivers/usb/dwc2/hcd.c index fc3269f5faf1..1a9789ec5847 100644 --- a/drivers/usb/dwc2/hcd.c +++ b/drivers/usb/dwc2/hcd.c @@ -4322,7 +4322,8 @@ static int _dwc2_hcd_suspend(struct usb_hcd *hcd) if (hsotg->op_state == OTG_STATE_B_PERIPHERAL) goto unlock; - if (hsotg->params.power_down > DWC2_POWER_DOWN_PARAM_PARTIAL) + if (hsotg->params.power_down != DWC2_POWER_DOWN_PARAM_PARTIAL || + hsotg->flags.b.port_connect_status == 0) goto skip_power_saving; /* @@ -5398,7 +5399,7 @@ int dwc2_host_enter_hibernation(struct dwc2_hsotg *hsotg) dwc2_writel(hsotg, hprt0, HPRT0); /* Wait for the HPRT0.PrtSusp register field to be set */ - if (dwc2_hsotg_wait_bit_set(hsotg, HPRT0, HPRT0_SUSP, 3000)) + if (dwc2_hsotg_wait_bit_set(hsotg, HPRT0, HPRT0_SUSP, 5000)) dev_warn(hsotg->dev, "Suspend wasn't generated\n"); /* diff --git a/drivers/usb/dwc3/dwc3-pci.c b/drivers/usb/dwc3/dwc3-pci.c index 3d3918a8d5fb..4c5c6972124a 100644 --- a/drivers/usb/dwc3/dwc3-pci.c +++ b/drivers/usb/dwc3/dwc3-pci.c @@ -120,6 +120,8 @@ static const struct property_entry dwc3_pci_intel_properties[] = { static const struct property_entry dwc3_pci_mrfld_properties[] = { PROPERTY_ENTRY_STRING("dr_mode", "otg"), PROPERTY_ENTRY_STRING("linux,extcon-name", "mrfld_bcove_pwrsrc"), + PROPERTY_ENTRY_BOOL("snps,dis_u3_susphy_quirk"), + PROPERTY_ENTRY_BOOL("snps,dis_u2_susphy_quirk"), PROPERTY_ENTRY_BOOL("linux,sysdev_is_parent"), {} }; diff --git a/drivers/usb/dwc3/dwc3-qcom.c b/drivers/usb/dwc3/dwc3-qcom.c index fcaf04483ad0..3de291ab951a 100644 --- a/drivers/usb/dwc3/dwc3-qcom.c +++ b/drivers/usb/dwc3/dwc3-qcom.c @@ -244,6 +244,9 @@ static int dwc3_qcom_interconnect_init(struct dwc3_qcom *qcom) struct device *dev = qcom->dev; int ret; + if (has_acpi_companion(dev)) + return 0; + qcom->icc_path_ddr = of_icc_get(dev, "usb-ddr"); if (IS_ERR(qcom->icc_path_ddr)) { dev_err(dev, "failed to get usb-ddr path: %ld\n", diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index aebcf8ec0716..c7ef218e7a8c 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -783,8 +783,6 @@ static int __dwc3_gadget_ep_disable(struct dwc3_ep *dep) trace_dwc3_gadget_ep_disable(dep); - dwc3_remove_requests(dwc, dep); - /* make sure HW endpoint isn't stalled */ if (dep->flags & DWC3_EP_STALL) __dwc3_gadget_ep_set_halt(dep, 0, false); @@ -793,16 +791,18 @@ static int __dwc3_gadget_ep_disable(struct dwc3_ep *dep) reg &= ~DWC3_DALEPENA_EP(dep->number); dwc3_writel(dwc->regs, DWC3_DALEPENA, reg); - dep->stream_capable = false; - dep->type = 0; - dep->flags = 0; - /* Clear out the ep descriptors for non-ep0 */ if (dep->number > 1) { dep->endpoint.comp_desc = NULL; dep->endpoint.desc = NULL; } + dwc3_remove_requests(dwc, dep); + + dep->stream_capable = false; + dep->type = 0; + dep->flags = 0; + return 0; } @@ -1617,7 +1617,7 @@ static int __dwc3_gadget_ep_queue(struct dwc3_ep *dep, struct dwc3_request *req) { struct dwc3 *dwc = dep->dwc; - if (!dep->endpoint.desc || !dwc->pullups_connected) { + if (!dep->endpoint.desc || !dwc->pullups_connected || !dwc->connected) { dev_err(dwc->dev, "%s: can't queue to disabled endpoint\n", dep->name); return -ESHUTDOWN; @@ -2083,7 +2083,7 @@ static void __dwc3_gadget_set_speed(struct dwc3 *dwc) u32 reg; speed = dwc->gadget_max_speed; - if (speed > dwc->maximum_speed) + if (speed == USB_SPEED_UNKNOWN || speed > dwc->maximum_speed) speed = dwc->maximum_speed; if (speed == USB_SPEED_SUPER_PLUS && @@ -2247,6 +2247,7 @@ static int dwc3_gadget_pullup(struct usb_gadget *g, int is_on) if (!is_on) { u32 count; + dwc->connected = false; /* * In the Synopsis DesignWare Cores USB3 Databook Rev. 3.30a * Section 4.1.8 Table 4-7, it states that for a device-initiated @@ -2271,7 +2272,6 @@ static int dwc3_gadget_pullup(struct usb_gadget *g, int is_on) dwc->ev_buf->lpos = (dwc->ev_buf->lpos + count) % dwc->ev_buf->length; } - dwc->connected = false; } else { __dwc3_gadget_start(dwc); } @@ -2523,6 +2523,7 @@ static void dwc3_gadget_set_ssp_rate(struct usb_gadget *g, unsigned long flags; spin_lock_irqsave(&dwc->lock, flags); + dwc->gadget_max_speed = USB_SPEED_SUPER_PLUS; dwc->gadget_ssp_rate = rate; spin_unlock_irqrestore(&dwc->lock, flags); } @@ -3321,8 +3322,6 @@ static void dwc3_gadget_reset_interrupt(struct dwc3 *dwc) { u32 reg; - dwc->connected = true; - /* * WORKAROUND: DWC3 revisions <1.88a have an issue which * would cause a missing Disconnect Event if there's a @@ -3362,6 +3361,7 @@ static void dwc3_gadget_reset_interrupt(struct dwc3 *dwc) * transfers." */ dwc3_stop_active_transfers(dwc); + dwc->connected = true; reg = dwc3_readl(dwc->regs, DWC3_DCTL); reg &= ~DWC3_DCTL_TSTCTRL_MASK; diff --git a/drivers/usb/gadget/configfs.c b/drivers/usb/gadget/configfs.c index 0d56f33d63c2..15a607ccef8a 100644 --- a/drivers/usb/gadget/configfs.c +++ b/drivers/usb/gadget/configfs.c @@ -97,6 +97,8 @@ struct gadget_config_name { struct list_head list; }; +#define USB_MAX_STRING_WITH_NULL_LEN (USB_MAX_STRING_LEN+1) + static int usb_string_copy(const char *s, char **s_copy) { int ret; @@ -106,12 +108,16 @@ static int usb_string_copy(const char *s, char **s_copy) if (ret > USB_MAX_STRING_LEN) return -EOVERFLOW; - str = kstrdup(s, GFP_KERNEL); - if (!str) - return -ENOMEM; + if (copy) { + str = copy; + } else { + str = kmalloc(USB_MAX_STRING_WITH_NULL_LEN, GFP_KERNEL); + if (!str) + return -ENOMEM; + } + strcpy(str, s); if (str[ret - 1] == '\n') str[ret - 1] = '\0'; - kfree(copy); *s_copy = str; return 0; } diff --git a/drivers/usb/gadget/udc/amd5536udc_pci.c b/drivers/usb/gadget/udc/amd5536udc_pci.c index 8d387e0e4d91..c80f9bd51b75 100644 --- a/drivers/usb/gadget/udc/amd5536udc_pci.c +++ b/drivers/usb/gadget/udc/amd5536udc_pci.c @@ -153,6 +153,11 @@ static int udc_pci_probe( pci_set_master(pdev); pci_try_set_mwi(pdev); + dev->phys_addr = resource; + dev->irq = pdev->irq; + dev->pdev = pdev; + dev->dev = &pdev->dev; + /* init dma pools */ if (use_dma) { retval = init_dma_pools(dev); @@ -160,11 +165,6 @@ static int udc_pci_probe( goto err_dma; } - dev->phys_addr = resource; - dev->irq = pdev->irq; - dev->pdev = pdev; - dev->dev = &pdev->dev; - /* general probing */ if (udc_probe(dev)) { retval = -ENODEV; diff --git a/drivers/usb/host/xhci-mtk.c b/drivers/usb/host/xhci-mtk.c index fe010cc61f19..2f27dc0d9c6b 100644 --- a/drivers/usb/host/xhci-mtk.c +++ b/drivers/usb/host/xhci-mtk.c @@ -397,6 +397,13 @@ static void xhci_mtk_quirks(struct device *dev, struct xhci_hcd *xhci) xhci->quirks |= XHCI_SPURIOUS_SUCCESS; if (mtk->lpm_support) xhci->quirks |= XHCI_LPM_SUPPORT; + + /* + * MTK xHCI 0.96: PSA is 1 by default even if doesn't support stream, + * and it's 3 when support it. + */ + if (xhci->hci_version < 0x100 && HCC_MAX_PSA(xhci->hcc_params) == 4) + xhci->quirks |= XHCI_BROKEN_STREAMS; } /* called during probe() after chip reset completes */ @@ -548,7 +555,8 @@ static int xhci_mtk_probe(struct platform_device *pdev) if (ret) goto put_usb3_hcd; - if (HCC_MAX_PSA(xhci->hcc_params) >= 4) + if (HCC_MAX_PSA(xhci->hcc_params) >= 4 && + !(xhci->quirks & XHCI_BROKEN_STREAMS)) xhci->shared_hcd->can_do_streams = 1; ret = usb_add_hcd(xhci->shared_hcd, irq, IRQF_SHARED); diff --git a/drivers/usb/misc/ldusb.c b/drivers/usb/misc/ldusb.c index 670e4d91e9ca..dcc88df72df4 100644 --- a/drivers/usb/misc/ldusb.c +++ b/drivers/usb/misc/ldusb.c @@ -117,7 +117,6 @@ MODULE_DEVICE_TABLE(usb, ld_usb_table); MODULE_AUTHOR("Michael Hund <mhund@ld-didactic.de>"); MODULE_DESCRIPTION("LD USB Driver"); MODULE_LICENSE("GPL"); -MODULE_SUPPORTED_DEVICE("LD USB Devices"); /* All interrupt in transfers are collected in a ring buffer to * avoid racing conditions and get better performance of the driver. diff --git a/drivers/usb/musb/musb_core.c b/drivers/usb/musb/musb_core.c index 1cd87729ba60..fc0457db62e1 100644 --- a/drivers/usb/musb/musb_core.c +++ b/drivers/usb/musb/musb_core.c @@ -2004,10 +2004,14 @@ static void musb_pm_runtime_check_session(struct musb *musb) MUSB_DEVCTL_HR; switch (devctl & ~s) { case MUSB_QUIRK_B_DISCONNECT_99: - musb_dbg(musb, "Poll devctl in case of suspend after disconnect\n"); - schedule_delayed_work(&musb->irq_work, - msecs_to_jiffies(1000)); - break; + if (musb->quirk_retries && !musb->flush_irq_work) { + musb_dbg(musb, "Poll devctl in case of suspend after disconnect\n"); + schedule_delayed_work(&musb->irq_work, + msecs_to_jiffies(1000)); + musb->quirk_retries--; + break; + } + fallthrough; case MUSB_QUIRK_B_INVALID_VBUS_91: if (musb->quirk_retries && !musb->flush_irq_work) { musb_dbg(musb, diff --git a/drivers/usb/storage/transport.c b/drivers/usb/storage/transport.c index 5eb895b19c55..f4304ce69350 100644 --- a/drivers/usb/storage/transport.c +++ b/drivers/usb/storage/transport.c @@ -656,6 +656,13 @@ void usb_stor_invoke_transport(struct scsi_cmnd *srb, struct us_data *us) need_auto_sense = 1; } + /* Some devices (Kindle) require another command after SYNC CACHE */ + if ((us->fflags & US_FL_SENSE_AFTER_SYNC) && + srb->cmnd[0] == SYNCHRONIZE_CACHE) { + usb_stor_dbg(us, "-- sense after SYNC CACHE\n"); + need_auto_sense = 1; + } + /* * If we have a failure, we're going to do a REQUEST_SENSE * automatically. Note that we differentiate between a command diff --git a/drivers/usb/storage/unusual_devs.h b/drivers/usb/storage/unusual_devs.h index 5732e9691f08..efa972be2ee3 100644 --- a/drivers/usb/storage/unusual_devs.h +++ b/drivers/usb/storage/unusual_devs.h @@ -2212,6 +2212,18 @@ UNUSUAL_DEV( 0x1908, 0x3335, 0x0200, 0x0200, US_FL_NO_READ_DISC_INFO ), /* + * Reported by Matthias Schwarzott <zzam@gentoo.org> + * The Amazon Kindle treats SYNCHRONIZE CACHE as an indication that + * the host may be finished with it, and automatically ejects its + * emulated media unless it receives another command within one second. + */ +UNUSUAL_DEV( 0x1949, 0x0004, 0x0000, 0x9999, + "Amazon", + "Kindle", + USB_SC_DEVICE, USB_PR_DEVICE, NULL, + US_FL_SENSE_AFTER_SYNC ), + +/* * Reported by Oliver Neukum <oneukum@suse.com> * This device morphes spontaneously into another device if the access * pattern of Windows isn't followed. Thus writable media would be dirty diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c index be0b6469dd3d..ce7af398c7c1 100644 --- a/drivers/usb/typec/tcpm/tcpm.c +++ b/drivers/usb/typec/tcpm/tcpm.c @@ -942,6 +942,7 @@ static int tcpm_set_current_limit(struct tcpm_port *port, u32 max_ma, u32 mv) port->supply_voltage = mv; port->current_limit = max_ma; + power_supply_changed(port->psy); if (port->tcpc->set_current_limit) ret = port->tcpc->set_current_limit(port->tcpc, max_ma, mv); @@ -2928,6 +2929,7 @@ static int tcpm_pd_select_pdo(struct tcpm_port *port, int *sink_pdo, port->pps_data.supported = false; port->usb_type = POWER_SUPPLY_USB_TYPE_PD; + power_supply_changed(port->psy); /* * Select the source PDO providing the most power which has a @@ -2952,6 +2954,7 @@ static int tcpm_pd_select_pdo(struct tcpm_port *port, int *sink_pdo, port->pps_data.supported = true; port->usb_type = POWER_SUPPLY_USB_TYPE_PD_PPS; + power_supply_changed(port->psy); } continue; default: @@ -3109,6 +3112,7 @@ static unsigned int tcpm_pd_select_pps_apdo(struct tcpm_port *port) port->pps_data.out_volt)); port->pps_data.op_curr = min(port->pps_data.max_curr, port->pps_data.op_curr); + power_supply_changed(port->psy); } return src_pdo; @@ -3344,6 +3348,7 @@ static int tcpm_set_charge(struct tcpm_port *port, bool charge) return ret; } port->vbus_charge = charge; + power_supply_changed(port->psy); return 0; } @@ -3523,6 +3528,7 @@ static void tcpm_reset_port(struct tcpm_port *port) port->try_src_count = 0; port->try_snk_count = 0; port->usb_type = POWER_SUPPLY_USB_TYPE_C; + power_supply_changed(port->psy); port->nr_sink_caps = 0; port->sink_cap_done = false; if (port->tcpc->enable_frs) @@ -5167,7 +5173,7 @@ static void tcpm_enable_frs_work(struct kthread_work *work) goto unlock; /* Send when the state machine is idle */ - if (port->state != SNK_READY || port->vdm_state != VDM_STATE_DONE || port->send_discover) + if (port->state != SNK_READY || port->vdm_sm_running || port->send_discover) goto resched; port->upcoming_state = GET_SINK_CAP; @@ -5905,7 +5911,7 @@ static int tcpm_psy_set_prop(struct power_supply *psy, ret = -EINVAL; break; } - + power_supply_changed(port->psy); return ret; } @@ -6058,6 +6064,7 @@ struct tcpm_port *tcpm_register_port(struct device *dev, struct tcpc_dev *tcpc) err = devm_tcpm_psy_register(port); if (err) goto out_role_sw_put; + power_supply_changed(port->psy); port->typec_port = typec_register_port(port->dev, &port->typec_caps); if (IS_ERR(port->typec_port)) { diff --git a/drivers/usb/typec/tps6598x.c b/drivers/usb/typec/tps6598x.c index 6e6ef6317523..29bd1c5a283c 100644 --- a/drivers/usb/typec/tps6598x.c +++ b/drivers/usb/typec/tps6598x.c @@ -64,7 +64,6 @@ enum { struct tps6598x_rx_identity_reg { u8 status; struct usb_pd_identity identity; - u32 vdo[3]; } __packed; /* Standard Task return codes */ diff --git a/drivers/usb/usbip/stub_dev.c b/drivers/usb/usbip/stub_dev.c index 8f1de1fbbeed..d8d3892e5a69 100644 --- a/drivers/usb/usbip/stub_dev.c +++ b/drivers/usb/usbip/stub_dev.c @@ -63,6 +63,7 @@ static ssize_t usbip_sockfd_store(struct device *dev, struct device_attribute *a dev_info(dev, "stub up\n"); + mutex_lock(&sdev->ud.sysfs_lock); spin_lock_irq(&sdev->ud.lock); if (sdev->ud.status != SDEV_ST_AVAILABLE) { @@ -87,13 +88,13 @@ static ssize_t usbip_sockfd_store(struct device *dev, struct device_attribute *a tcp_rx = kthread_create(stub_rx_loop, &sdev->ud, "stub_rx"); if (IS_ERR(tcp_rx)) { sockfd_put(socket); - return -EINVAL; + goto unlock_mutex; } tcp_tx = kthread_create(stub_tx_loop, &sdev->ud, "stub_tx"); if (IS_ERR(tcp_tx)) { kthread_stop(tcp_rx); sockfd_put(socket); - return -EINVAL; + goto unlock_mutex; } /* get task structs now */ @@ -112,6 +113,8 @@ static ssize_t usbip_sockfd_store(struct device *dev, struct device_attribute *a wake_up_process(sdev->ud.tcp_rx); wake_up_process(sdev->ud.tcp_tx); + mutex_unlock(&sdev->ud.sysfs_lock); + } else { dev_info(dev, "stub down\n"); @@ -122,6 +125,7 @@ static ssize_t usbip_sockfd_store(struct device *dev, struct device_attribute *a spin_unlock_irq(&sdev->ud.lock); usbip_event_add(&sdev->ud, SDEV_EVENT_DOWN); + mutex_unlock(&sdev->ud.sysfs_lock); } return count; @@ -130,6 +134,8 @@ sock_err: sockfd_put(socket); err: spin_unlock_irq(&sdev->ud.lock); +unlock_mutex: + mutex_unlock(&sdev->ud.sysfs_lock); return -EINVAL; } static DEVICE_ATTR_WO(usbip_sockfd); @@ -270,6 +276,7 @@ static struct stub_device *stub_device_alloc(struct usb_device *udev) sdev->ud.side = USBIP_STUB; sdev->ud.status = SDEV_ST_AVAILABLE; spin_lock_init(&sdev->ud.lock); + mutex_init(&sdev->ud.sysfs_lock); sdev->ud.tcp_socket = NULL; sdev->ud.sockfd = -1; diff --git a/drivers/usb/usbip/usbip_common.h b/drivers/usb/usbip/usbip_common.h index d60ce17d3dd2..ea2a20e6d27d 100644 --- a/drivers/usb/usbip/usbip_common.h +++ b/drivers/usb/usbip/usbip_common.h @@ -263,6 +263,9 @@ struct usbip_device { /* lock for status */ spinlock_t lock; + /* mutex for synchronizing sysfs store paths */ + struct mutex sysfs_lock; + int sockfd; struct socket *tcp_socket; diff --git a/drivers/usb/usbip/usbip_event.c b/drivers/usb/usbip/usbip_event.c index 5d88917c9631..086ca76dd053 100644 --- a/drivers/usb/usbip/usbip_event.c +++ b/drivers/usb/usbip/usbip_event.c @@ -70,6 +70,7 @@ static void event_handler(struct work_struct *work) while ((ud = get_event()) != NULL) { usbip_dbg_eh("pending event %lx\n", ud->event); + mutex_lock(&ud->sysfs_lock); /* * NOTE: shutdown must come first. * Shutdown the device. @@ -90,6 +91,7 @@ static void event_handler(struct work_struct *work) ud->eh_ops.unusable(ud); unset_event(ud, USBIP_EH_UNUSABLE); } + mutex_unlock(&ud->sysfs_lock); wake_up(&ud->eh_waitq); } diff --git a/drivers/usb/usbip/vhci_hcd.c b/drivers/usb/usbip/vhci_hcd.c index 3209b5ddd30c..4ba6bcdaa8e9 100644 --- a/drivers/usb/usbip/vhci_hcd.c +++ b/drivers/usb/usbip/vhci_hcd.c @@ -594,6 +594,8 @@ static int vhci_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue, pr_err("invalid port number %d\n", wIndex); goto error; } + if (wValue >= 32) + goto error; if (hcd->speed == HCD_USB3) { if ((vhci_hcd->port_status[rhport] & USB_SS_PORT_STAT_POWER) != 0) { @@ -1099,6 +1101,7 @@ static void vhci_device_init(struct vhci_device *vdev) vdev->ud.side = USBIP_VHCI; vdev->ud.status = VDEV_ST_NULL; spin_lock_init(&vdev->ud.lock); + mutex_init(&vdev->ud.sysfs_lock); INIT_LIST_HEAD(&vdev->priv_rx); INIT_LIST_HEAD(&vdev->priv_tx); diff --git a/drivers/usb/usbip/vhci_sysfs.c b/drivers/usb/usbip/vhci_sysfs.c index c4b4256e5dad..e2847cd3e6e3 100644 --- a/drivers/usb/usbip/vhci_sysfs.c +++ b/drivers/usb/usbip/vhci_sysfs.c @@ -185,6 +185,8 @@ static int vhci_port_disconnect(struct vhci_hcd *vhci_hcd, __u32 rhport) usbip_dbg_vhci_sysfs("enter\n"); + mutex_lock(&vdev->ud.sysfs_lock); + /* lock */ spin_lock_irqsave(&vhci->lock, flags); spin_lock(&vdev->ud.lock); @@ -195,6 +197,7 @@ static int vhci_port_disconnect(struct vhci_hcd *vhci_hcd, __u32 rhport) /* unlock */ spin_unlock(&vdev->ud.lock); spin_unlock_irqrestore(&vhci->lock, flags); + mutex_unlock(&vdev->ud.sysfs_lock); return -EINVAL; } @@ -205,6 +208,8 @@ static int vhci_port_disconnect(struct vhci_hcd *vhci_hcd, __u32 rhport) usbip_event_add(&vdev->ud, VDEV_EVENT_DOWN); + mutex_unlock(&vdev->ud.sysfs_lock); + return 0; } @@ -349,30 +354,36 @@ static ssize_t attach_store(struct device *dev, struct device_attribute *attr, else vdev = &vhci->vhci_hcd_hs->vdev[rhport]; + mutex_lock(&vdev->ud.sysfs_lock); + /* Extract socket from fd. */ socket = sockfd_lookup(sockfd, &err); if (!socket) { dev_err(dev, "failed to lookup sock"); - return -EINVAL; + err = -EINVAL; + goto unlock_mutex; } if (socket->type != SOCK_STREAM) { dev_err(dev, "Expecting SOCK_STREAM - found %d", socket->type); sockfd_put(socket); - return -EINVAL; + err = -EINVAL; + goto unlock_mutex; } /* create threads before locking */ tcp_rx = kthread_create(vhci_rx_loop, &vdev->ud, "vhci_rx"); if (IS_ERR(tcp_rx)) { sockfd_put(socket); - return -EINVAL; + err = -EINVAL; + goto unlock_mutex; } tcp_tx = kthread_create(vhci_tx_loop, &vdev->ud, "vhci_tx"); if (IS_ERR(tcp_tx)) { kthread_stop(tcp_rx); sockfd_put(socket); - return -EINVAL; + err = -EINVAL; + goto unlock_mutex; } /* get task structs now */ @@ -397,7 +408,8 @@ static ssize_t attach_store(struct device *dev, struct device_attribute *attr, * Will be retried from userspace * if there's another free port. */ - return -EBUSY; + err = -EBUSY; + goto unlock_mutex; } dev_info(dev, "pdev(%u) rhport(%u) sockfd(%d)\n", @@ -423,7 +435,15 @@ static ssize_t attach_store(struct device *dev, struct device_attribute *attr, rh_port_connect(vdev, speed); + dev_info(dev, "Device attached\n"); + + mutex_unlock(&vdev->ud.sysfs_lock); + return count; + +unlock_mutex: + mutex_unlock(&vdev->ud.sysfs_lock); + return err; } static DEVICE_ATTR_WO(attach); diff --git a/drivers/usb/usbip/vudc_dev.c b/drivers/usb/usbip/vudc_dev.c index c8eeabdd9b56..2bc428f2e261 100644 --- a/drivers/usb/usbip/vudc_dev.c +++ b/drivers/usb/usbip/vudc_dev.c @@ -572,6 +572,7 @@ static int init_vudc_hw(struct vudc *udc) init_waitqueue_head(&udc->tx_waitq); spin_lock_init(&ud->lock); + mutex_init(&ud->sysfs_lock); ud->status = SDEV_ST_AVAILABLE; ud->side = USBIP_VUDC; diff --git a/drivers/usb/usbip/vudc_sysfs.c b/drivers/usb/usbip/vudc_sysfs.c index a3ec39fc6177..f7633ee655a1 100644 --- a/drivers/usb/usbip/vudc_sysfs.c +++ b/drivers/usb/usbip/vudc_sysfs.c @@ -112,6 +112,7 @@ static ssize_t usbip_sockfd_store(struct device *dev, dev_err(dev, "no device"); return -ENODEV; } + mutex_lock(&udc->ud.sysfs_lock); spin_lock_irqsave(&udc->lock, flags); /* Don't export what we don't have */ if (!udc->driver || !udc->pullup) { @@ -174,7 +175,7 @@ static ssize_t usbip_sockfd_store(struct device *dev, udc->ud.tcp_socket = socket; udc->ud.tcp_rx = tcp_rx; - udc->ud.tcp_rx = tcp_tx; + udc->ud.tcp_tx = tcp_tx; udc->ud.status = SDEV_ST_USED; spin_unlock_irq(&udc->ud.lock); @@ -187,6 +188,8 @@ static ssize_t usbip_sockfd_store(struct device *dev, wake_up_process(udc->ud.tcp_rx); wake_up_process(udc->ud.tcp_tx); + + mutex_unlock(&udc->ud.sysfs_lock); return count; } else { @@ -207,6 +210,7 @@ static ssize_t usbip_sockfd_store(struct device *dev, } spin_unlock_irqrestore(&udc->lock, flags); + mutex_unlock(&udc->ud.sysfs_lock); return count; @@ -216,6 +220,7 @@ unlock_ud: spin_unlock_irq(&udc->ud.lock); unlock: spin_unlock_irqrestore(&udc->lock, flags); + mutex_unlock(&udc->ud.sysfs_lock); return ret; } diff --git a/drivers/vdpa/ifcvf/ifcvf_main.c b/drivers/vdpa/ifcvf/ifcvf_main.c index 7c8bbfcf6c3e..d555a6a5d1ba 100644 --- a/drivers/vdpa/ifcvf/ifcvf_main.c +++ b/drivers/vdpa/ifcvf/ifcvf_main.c @@ -431,8 +431,7 @@ static int ifcvf_probe(struct pci_dev *pdev, const struct pci_device_id *id) } adapter = vdpa_alloc_device(struct ifcvf_adapter, vdpa, - dev, &ifc_vdpa_ops, - IFCVF_MAX_QUEUE_PAIRS * 2, NULL); + dev, &ifc_vdpa_ops, NULL); if (adapter == NULL) { IFCVF_ERR(pdev, "Failed to allocate vDPA structure"); return -ENOMEM; @@ -456,7 +455,7 @@ static int ifcvf_probe(struct pci_dev *pdev, const struct pci_device_id *id) for (i = 0; i < IFCVF_MAX_QUEUE_PAIRS * 2; i++) vf->vring[i].irq = -EINVAL; - ret = vdpa_register_device(&adapter->vdpa); + ret = vdpa_register_device(&adapter->vdpa, IFCVF_MAX_QUEUE_PAIRS * 2); if (ret) { IFCVF_ERR(pdev, "Failed to register ifcvf to vdpa bus"); goto err; diff --git a/drivers/vdpa/mlx5/core/mlx5_vdpa.h b/drivers/vdpa/mlx5/core/mlx5_vdpa.h index 08f742fd2409..b6cc53ba980c 100644 --- a/drivers/vdpa/mlx5/core/mlx5_vdpa.h +++ b/drivers/vdpa/mlx5/core/mlx5_vdpa.h @@ -4,9 +4,13 @@ #ifndef __MLX5_VDPA_H__ #define __MLX5_VDPA_H__ +#include <linux/etherdevice.h> +#include <linux/if_vlan.h> #include <linux/vdpa.h> #include <linux/mlx5/driver.h> +#define MLX5V_ETH_HARD_MTU (ETH_HLEN + VLAN_HLEN + ETH_FCS_LEN) + struct mlx5_vdpa_direct_mr { u64 start; u64 end; diff --git a/drivers/vdpa/mlx5/core/mr.c b/drivers/vdpa/mlx5/core/mr.c index d300f799efcd..3908ff28eec0 100644 --- a/drivers/vdpa/mlx5/core/mr.c +++ b/drivers/vdpa/mlx5/core/mr.c @@ -219,6 +219,11 @@ static void destroy_indirect_key(struct mlx5_vdpa_dev *mvdev, struct mlx5_vdpa_m mlx5_vdpa_destroy_mkey(mvdev, &mkey->mkey); } +static struct device *get_dma_device(struct mlx5_vdpa_dev *mvdev) +{ + return &mvdev->mdev->pdev->dev; +} + static int map_direct_mr(struct mlx5_vdpa_dev *mvdev, struct mlx5_vdpa_direct_mr *mr, struct vhost_iotlb *iotlb) { @@ -234,7 +239,7 @@ static int map_direct_mr(struct mlx5_vdpa_dev *mvdev, struct mlx5_vdpa_direct_mr u64 pa; u64 paend; struct scatterlist *sg; - struct device *dma = mvdev->mdev->device; + struct device *dma = get_dma_device(mvdev); for (map = vhost_iotlb_itree_first(iotlb, mr->start, mr->end - 1); map; map = vhost_iotlb_itree_next(map, start, mr->end - 1)) { @@ -291,7 +296,7 @@ err_map: static void unmap_direct_mr(struct mlx5_vdpa_dev *mvdev, struct mlx5_vdpa_direct_mr *mr) { - struct device *dma = mvdev->mdev->device; + struct device *dma = get_dma_device(mvdev); destroy_direct_mr(mvdev, mr); dma_unmap_sg_attrs(dma, mr->sg_head.sgl, mr->nsg, DMA_BIDIRECTIONAL, 0); diff --git a/drivers/vdpa/mlx5/core/resources.c b/drivers/vdpa/mlx5/core/resources.c index 96e6421c5d1c..6521cbd0f5c2 100644 --- a/drivers/vdpa/mlx5/core/resources.c +++ b/drivers/vdpa/mlx5/core/resources.c @@ -246,7 +246,8 @@ int mlx5_vdpa_alloc_resources(struct mlx5_vdpa_dev *mvdev) if (err) goto err_key; - kick_addr = pci_resource_start(mdev->pdev, 0) + offset; + kick_addr = mdev->bar_addr + offset; + res->kick_addr = ioremap(kick_addr, PAGE_SIZE); if (!res->kick_addr) { err = -ENOMEM; diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c index 10e9b09932eb..4d2809c7d4e3 100644 --- a/drivers/vdpa/mlx5/net/mlx5_vnet.c +++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c @@ -820,7 +820,7 @@ static int create_virtqueue(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtque MLX5_SET(virtio_q, vq_ctx, event_qpn_or_msix, mvq->fwqp.mqp.qpn); MLX5_SET(virtio_q, vq_ctx, queue_size, mvq->num_ent); MLX5_SET(virtio_q, vq_ctx, virtio_version_1_0, - !!(ndev->mvdev.actual_features & VIRTIO_F_VERSION_1)); + !!(ndev->mvdev.actual_features & BIT_ULL(VIRTIO_F_VERSION_1))); MLX5_SET64(virtio_q, vq_ctx, desc_addr, mvq->desc_addr); MLX5_SET64(virtio_q, vq_ctx, used_addr, mvq->device_addr); MLX5_SET64(virtio_q, vq_ctx, available_addr, mvq->driver_addr); @@ -1169,6 +1169,7 @@ static void suspend_vq(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtqueue *m return; } mvq->avail_idx = attr.available_index; + mvq->used_idx = attr.used_index; } static void suspend_vqs(struct mlx5_vdpa_net *ndev) @@ -1426,6 +1427,7 @@ static int mlx5_vdpa_set_vq_state(struct vdpa_device *vdev, u16 idx, return -EINVAL; } + mvq->used_idx = state->avail_index; mvq->avail_idx = state->avail_index; return 0; } @@ -1443,7 +1445,11 @@ static int mlx5_vdpa_get_vq_state(struct vdpa_device *vdev, u16 idx, struct vdpa * that cares about emulating the index after vq is stopped. */ if (!mvq->initialized) { - state->avail_index = mvq->avail_idx; + /* Firmware returns a wrong value for the available index. + * Since both values should be identical, we take the value of + * used_idx which is reported correctly. + */ + state->avail_index = mvq->used_idx; return 0; } @@ -1452,7 +1458,7 @@ static int mlx5_vdpa_get_vq_state(struct vdpa_device *vdev, u16 idx, struct vdpa mlx5_vdpa_warn(mvdev, "failed to query virtqueue\n"); return err; } - state->avail_index = attr.available_index; + state->avail_index = attr.used_index; return 0; } @@ -1540,21 +1546,11 @@ static void teardown_virtqueues(struct mlx5_vdpa_net *ndev) } } -static void clear_virtqueues(struct mlx5_vdpa_net *ndev) -{ - int i; - - for (i = ndev->mvdev.max_vqs - 1; i >= 0; i--) { - ndev->vqs[i].avail_idx = 0; - ndev->vqs[i].used_idx = 0; - } -} - /* TODO: cross-endian support */ static inline bool mlx5_vdpa_is_little_endian(struct mlx5_vdpa_dev *mvdev) { return virtio_legacy_is_little_endian() || - (mvdev->actual_features & (1ULL << VIRTIO_F_VERSION_1)); + (mvdev->actual_features & BIT_ULL(VIRTIO_F_VERSION_1)); } static __virtio16 cpu_to_mlx5vdpa16(struct mlx5_vdpa_dev *mvdev, u16 val) @@ -1785,7 +1781,6 @@ static void mlx5_vdpa_set_status(struct vdpa_device *vdev, u8 status) if (!status) { mlx5_vdpa_info(mvdev, "performing device reset\n"); teardown_driver(ndev); - clear_virtqueues(ndev); mlx5_vdpa_destroy_mr(&ndev->mvdev); ndev->mvdev.status = 0; ndev->mvdev.mlx_features = 0; @@ -1907,6 +1902,19 @@ static const struct vdpa_config_ops mlx5_vdpa_ops = { .free = mlx5_vdpa_free, }; +static int query_mtu(struct mlx5_core_dev *mdev, u16 *mtu) +{ + u16 hw_mtu; + int err; + + err = mlx5_query_nic_vport_mtu(mdev, &hw_mtu); + if (err) + return err; + + *mtu = hw_mtu - MLX5V_ETH_HARD_MTU; + return 0; +} + static int alloc_resources(struct mlx5_vdpa_net *ndev) { struct mlx5_vdpa_net_resources *res = &ndev->res; @@ -1982,7 +1990,7 @@ static int mlx5v_probe(struct auxiliary_device *adev, max_vqs = min_t(u32, max_vqs, MLX5_MAX_SUPPORTED_VQS); ndev = vdpa_alloc_device(struct mlx5_vdpa_net, mvdev.vdev, mdev->device, &mlx5_vdpa_ops, - 2 * mlx5_vdpa_max_qps(max_vqs), NULL); + NULL); if (IS_ERR(ndev)) return PTR_ERR(ndev); @@ -1992,7 +2000,7 @@ static int mlx5v_probe(struct auxiliary_device *adev, init_mvqs(ndev); mutex_init(&ndev->reslock); config = &ndev->config; - err = mlx5_query_nic_vport_mtu(mdev, &ndev->mtu); + err = query_mtu(mdev, &ndev->mtu); if (err) goto err_mtu; @@ -2009,7 +2017,7 @@ static int mlx5v_probe(struct auxiliary_device *adev, if (err) goto err_res; - err = vdpa_register_device(&mvdev->vdev); + err = vdpa_register_device(&mvdev->vdev, 2 * mlx5_vdpa_max_qps(max_vqs)); if (err) goto err_reg; diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c index da67f07e24fd..5cffce67cab0 100644 --- a/drivers/vdpa/vdpa.c +++ b/drivers/vdpa/vdpa.c @@ -69,7 +69,6 @@ static void vdpa_release_dev(struct device *d) * initialized but before registered. * @parent: the parent device * @config: the bus operations that is supported by this device - * @nvqs: number of virtqueues supported by this device * @size: size of the parent structure that contains private data * @name: name of the vdpa device; optional. * @@ -81,7 +80,7 @@ static void vdpa_release_dev(struct device *d) */ struct vdpa_device *__vdpa_alloc_device(struct device *parent, const struct vdpa_config_ops *config, - int nvqs, size_t size, const char *name) + size_t size, const char *name) { struct vdpa_device *vdev; int err = -EINVAL; @@ -107,7 +106,6 @@ struct vdpa_device *__vdpa_alloc_device(struct device *parent, vdev->index = err; vdev->config = config; vdev->features_valid = false; - vdev->nvqs = nvqs; if (name) err = dev_set_name(&vdev->dev, "%s", name); @@ -136,10 +134,12 @@ static int vdpa_name_match(struct device *dev, const void *data) return (strcmp(dev_name(&vdev->dev), data) == 0); } -static int __vdpa_register_device(struct vdpa_device *vdev) +static int __vdpa_register_device(struct vdpa_device *vdev, int nvqs) { struct device *dev; + vdev->nvqs = nvqs; + lockdep_assert_held(&vdpa_dev_mutex); dev = bus_find_device(&vdpa_bus, NULL, dev_name(&vdev->dev), vdpa_name_match); if (dev) { @@ -155,15 +155,16 @@ static int __vdpa_register_device(struct vdpa_device *vdev) * Caller must invoke this routine in the management device dev_add() * callback after setting up valid mgmtdev for this vdpa device. * @vdev: the vdpa device to be registered to vDPA bus + * @nvqs: number of virtqueues supported by this device * * Returns an error when fail to add device to vDPA bus */ -int _vdpa_register_device(struct vdpa_device *vdev) +int _vdpa_register_device(struct vdpa_device *vdev, int nvqs) { if (!vdev->mdev) return -EINVAL; - return __vdpa_register_device(vdev); + return __vdpa_register_device(vdev, nvqs); } EXPORT_SYMBOL_GPL(_vdpa_register_device); @@ -171,15 +172,16 @@ EXPORT_SYMBOL_GPL(_vdpa_register_device); * vdpa_register_device - register a vDPA device * Callers must have a succeed call of vdpa_alloc_device() before. * @vdev: the vdpa device to be registered to vDPA bus + * @nvqs: number of virtqueues supported by this device * * Returns an error when fail to add to vDPA bus */ -int vdpa_register_device(struct vdpa_device *vdev) +int vdpa_register_device(struct vdpa_device *vdev, int nvqs) { int err; mutex_lock(&vdpa_dev_mutex); - err = __vdpa_register_device(vdev); + err = __vdpa_register_device(vdev, nvqs); mutex_unlock(&vdpa_dev_mutex); return err; } diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim.c b/drivers/vdpa/vdpa_sim/vdpa_sim.c index d5942842432d..5b6b2f87d40c 100644 --- a/drivers/vdpa/vdpa_sim/vdpa_sim.c +++ b/drivers/vdpa/vdpa_sim/vdpa_sim.c @@ -235,7 +235,7 @@ struct vdpasim *vdpasim_create(struct vdpasim_dev_attr *dev_attr) ops = &vdpasim_config_ops; vdpasim = vdpa_alloc_device(struct vdpasim, vdpa, NULL, ops, - dev_attr->nvqs, dev_attr->name); + dev_attr->name); if (!vdpasim) goto err_alloc; diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim_net.c b/drivers/vdpa/vdpa_sim/vdpa_sim_net.c index d344c5b7c914..a1ab6163f7d1 100644 --- a/drivers/vdpa/vdpa_sim/vdpa_sim_net.c +++ b/drivers/vdpa/vdpa_sim/vdpa_sim_net.c @@ -110,8 +110,7 @@ out: static void vdpasim_net_get_config(struct vdpasim *vdpasim, void *config) { - struct virtio_net_config *net_config = - (struct virtio_net_config *)config; + struct virtio_net_config *net_config = config; net_config->mtu = cpu_to_vdpasim16(vdpasim, 1500); net_config->status = cpu_to_vdpasim16(vdpasim, VIRTIO_NET_S_LINK_UP); @@ -147,7 +146,7 @@ static int vdpasim_net_dev_add(struct vdpa_mgmt_dev *mdev, const char *name) if (IS_ERR(simdev)) return PTR_ERR(simdev); - ret = _vdpa_register_device(&simdev->vdpa); + ret = _vdpa_register_device(&simdev->vdpa, VDPASIM_NET_VQ_NUM); if (ret) goto reg_err; diff --git a/drivers/vfio/Kconfig b/drivers/vfio/Kconfig index 5533df91b257..67d0bf4efa16 100644 --- a/drivers/vfio/Kconfig +++ b/drivers/vfio/Kconfig @@ -21,8 +21,8 @@ config VFIO_VIRQFD menuconfig VFIO tristate "VFIO Non-Privileged userspace driver framework" - depends on IOMMU_API - select VFIO_IOMMU_TYPE1 if (X86 || S390 || ARM || ARM64) + select IOMMU_API + select VFIO_IOMMU_TYPE1 if MMU && (X86 || S390 || ARM || ARM64) help VFIO provides a framework for secure userspace device drivers. See Documentation/driver-api/vfio.rst for more details. diff --git a/drivers/vfio/pci/Kconfig b/drivers/vfio/pci/Kconfig index ac3c1dd3edef..4abddbebd4b2 100644 --- a/drivers/vfio/pci/Kconfig +++ b/drivers/vfio/pci/Kconfig @@ -42,6 +42,6 @@ config VFIO_PCI_IGD config VFIO_PCI_NVLINK2 def_bool y - depends on VFIO_PCI && PPC_POWERNV + depends on VFIO_PCI && PPC_POWERNV && SPAPR_TCE_IOMMU help VFIO PCI support for P9 Witherspoon machine with NVIDIA V100 GPUs diff --git a/drivers/vfio/platform/Kconfig b/drivers/vfio/platform/Kconfig index dc1a3c44f2c6..ab341108a0be 100644 --- a/drivers/vfio/platform/Kconfig +++ b/drivers/vfio/platform/Kconfig @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0-only config VFIO_PLATFORM tristate "VFIO support for platform devices" - depends on VFIO && EVENTFD && (ARM || ARM64) + depends on VFIO && EVENTFD && (ARM || ARM64 || COMPILE_TEST) select VFIO_VIRQFD help Support for platform devices with VFIO. This is required to make @@ -12,7 +12,7 @@ config VFIO_PLATFORM config VFIO_AMBA tristate "VFIO support for AMBA devices" - depends on VFIO_PLATFORM && ARM_AMBA + depends on VFIO_PLATFORM && (ARM_AMBA || COMPILE_TEST) help Support for ARM AMBA devices with VFIO. This is required to make use of ARM AMBA devices present on the system using the VFIO diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c index 4bb162c1d649..45cbfd4879a5 100644 --- a/drivers/vfio/vfio_iommu_type1.c +++ b/drivers/vfio/vfio_iommu_type1.c @@ -189,7 +189,7 @@ static struct vfio_dma *vfio_find_dma(struct vfio_iommu *iommu, } static struct rb_node *vfio_find_dma_first_node(struct vfio_iommu *iommu, - dma_addr_t start, size_t size) + dma_addr_t start, u64 size) { struct rb_node *res = NULL; struct rb_node *node = iommu->dma_list.rb_node; @@ -739,6 +739,12 @@ out: ret = vfio_lock_acct(dma, lock_acct, false); unpin_out: + if (batch->size == 1 && !batch->offset) { + /* May be a VM_PFNMAP pfn, which the batch can't remember. */ + put_pfn(pfn, dma->prot); + batch->size = 0; + } + if (ret < 0) { if (pinned && !rsvd) { for (pfn = *pfn_base ; pinned ; pfn++, pinned--) @@ -785,7 +791,12 @@ static int vfio_pin_page_external(struct vfio_dma *dma, unsigned long vaddr, return -ENODEV; ret = vaddr_get_pfns(mm, vaddr, 1, dma->prot, pfn_base, pages); - if (ret == 1 && do_accounting && !is_invalid_reserved_pfn(*pfn_base)) { + if (ret != 1) + goto out; + + ret = 0; + + if (do_accounting && !is_invalid_reserved_pfn(*pfn_base)) { ret = vfio_lock_acct(dma, 1, true); if (ret) { put_pfn(*pfn_base, dma->prot); @@ -797,6 +808,7 @@ static int vfio_pin_page_external(struct vfio_dma *dma, unsigned long vaddr, } } +out: mmput(mm); return ret; } @@ -1288,7 +1300,7 @@ static int vfio_dma_do_unmap(struct vfio_iommu *iommu, int ret = -EINVAL, retries = 0; unsigned long pgshift; dma_addr_t iova = unmap->iova; - unsigned long size = unmap->size; + u64 size = unmap->size; bool unmap_all = unmap->flags & VFIO_DMA_UNMAP_FLAG_ALL; bool invalidate_vaddr = unmap->flags & VFIO_DMA_UNMAP_FLAG_VADDR; struct rb_node *n, *first_n; @@ -1304,14 +1316,12 @@ static int vfio_dma_do_unmap(struct vfio_iommu *iommu, if (unmap_all) { if (iova || size) goto unlock; - size = SIZE_MAX; - } else if (!size || size & (pgsize - 1)) { + size = U64_MAX; + } else if (!size || size & (pgsize - 1) || + iova + size - 1 < iova || size > SIZE_MAX) { goto unlock; } - if (iova + size - 1 < iova || size > SIZE_MAX) - goto unlock; - /* When dirty tracking is enabled, allow only min supported pgsize */ if ((unmap->flags & VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP) && (!iommu->dirty_page_tracking || (bitmap->pgsize != pgsize))) { diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c index ef688c8c0e0e..e0a27e336293 100644 --- a/drivers/vhost/vdpa.c +++ b/drivers/vhost/vdpa.c @@ -308,8 +308,10 @@ static long vhost_vdpa_get_vring_num(struct vhost_vdpa *v, u16 __user *argp) static void vhost_vdpa_config_put(struct vhost_vdpa *v) { - if (v->config_ctx) + if (v->config_ctx) { eventfd_ctx_put(v->config_ctx); + v->config_ctx = NULL; + } } static long vhost_vdpa_set_config_call(struct vhost_vdpa *v, u32 __user *argp) @@ -329,8 +331,12 @@ static long vhost_vdpa_set_config_call(struct vhost_vdpa *v, u32 __user *argp) if (!IS_ERR_OR_NULL(ctx)) eventfd_ctx_put(ctx); - if (IS_ERR(v->config_ctx)) - return PTR_ERR(v->config_ctx); + if (IS_ERR(v->config_ctx)) { + long ret = PTR_ERR(v->config_ctx); + + v->config_ctx = NULL; + return ret; + } v->vdpa->config->set_config_cb(v->vdpa, &cb); @@ -900,14 +906,10 @@ err: static void vhost_vdpa_clean_irq(struct vhost_vdpa *v) { - struct vhost_virtqueue *vq; int i; - for (i = 0; i < v->nvqs; i++) { - vq = &v->vqs[i]; - if (vq->call_ctx.producer.irq) - irq_bypass_unregister_producer(&vq->call_ctx.producer); - } + for (i = 0; i < v->nvqs; i++) + vhost_vdpa_unsetup_vq_irq(v, i); } static int vhost_vdpa_release(struct inode *inode, struct file *filep) diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index a262e12c6dc2..5ccb0705beae 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -332,8 +332,8 @@ static void vhost_vq_reset(struct vhost_dev *dev, vq->error_ctx = NULL; vq->kick = NULL; vq->log_ctx = NULL; - vhost_reset_is_le(vq); vhost_disable_cross_endian(vq); + vhost_reset_is_le(vq); vq->busyloop_timeout = 0; vq->umem = NULL; vq->iotlb = NULL; diff --git a/drivers/video/fbdev/core/fbcon.c b/drivers/video/fbdev/core/fbcon.c index 44a5cd2f54cc..3406067985b1 100644 --- a/drivers/video/fbdev/core/fbcon.c +++ b/drivers/video/fbdev/core/fbcon.c @@ -1333,6 +1333,9 @@ static void fbcon_cursor(struct vc_data *vc, int mode) ops->cursor_flash = (mode == CM_ERASE) ? 0 : 1; + if (!ops->cursor) + return; + ops->cursor(vc, info, mode, get_color(vc, info, c, 1), get_color(vc, info, c, 0)); } diff --git a/drivers/video/fbdev/hyperv_fb.c b/drivers/video/fbdev/hyperv_fb.c index c8b0ae676809..4dc9077dd2ac 100644 --- a/drivers/video/fbdev/hyperv_fb.c +++ b/drivers/video/fbdev/hyperv_fb.c @@ -1031,7 +1031,6 @@ static int hvfb_getmem(struct hv_device *hdev, struct fb_info *info) PCI_DEVICE_ID_HYPERV_VIDEO, NULL); if (!pdev) { pr_err("Unable to find PCI Hyper-V video\n"); - kfree(info->apertures); return -ENODEV; } @@ -1129,7 +1128,6 @@ getmem_done: } else { pci_dev_put(pdev); } - kfree(info->apertures); return 0; @@ -1141,7 +1139,6 @@ err2: err1: if (!gen2vm) pci_dev_put(pdev); - kfree(info->apertures); return -ENOMEM; } diff --git a/drivers/virtio/virtio.c b/drivers/virtio/virtio.c index 42e09cc1b8ac..4b15c00c0a0a 100644 --- a/drivers/virtio/virtio.c +++ b/drivers/virtio/virtio.c @@ -141,15 +141,14 @@ void virtio_config_changed(struct virtio_device *dev) } EXPORT_SYMBOL_GPL(virtio_config_changed); -void virtio_config_disable(struct virtio_device *dev) +static void virtio_config_disable(struct virtio_device *dev) { spin_lock_irq(&dev->config_lock); dev->config_enabled = false; spin_unlock_irq(&dev->config_lock); } -EXPORT_SYMBOL_GPL(virtio_config_disable); -void virtio_config_enable(struct virtio_device *dev) +static void virtio_config_enable(struct virtio_device *dev) { spin_lock_irq(&dev->config_lock); dev->config_enabled = true; @@ -158,7 +157,6 @@ void virtio_config_enable(struct virtio_device *dev) dev->config_change_pending = false; spin_unlock_irq(&dev->config_lock); } -EXPORT_SYMBOL_GPL(virtio_config_enable); void virtio_add_status(struct virtio_device *dev, unsigned int status) { diff --git a/drivers/virtio/virtio_mmio.c b/drivers/virtio/virtio_mmio.c index a286d22b6551..56128b9c46eb 100644 --- a/drivers/virtio/virtio_mmio.c +++ b/drivers/virtio/virtio_mmio.c @@ -548,8 +548,7 @@ static void virtio_mmio_release_dev(struct device *_d) { struct virtio_device *vdev = container_of(_d, struct virtio_device, dev); - struct virtio_mmio_device *vm_dev = - container_of(vdev, struct virtio_mmio_device, vdev); + struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev); struct platform_device *pdev = vm_dev->pdev; devm_kfree(&pdev->dev, vm_dev); diff --git a/drivers/watchdog/armada_37xx_wdt.c b/drivers/watchdog/armada_37xx_wdt.c index e5dcb26d85f0..1635f421ef2c 100644 --- a/drivers/watchdog/armada_37xx_wdt.c +++ b/drivers/watchdog/armada_37xx_wdt.c @@ -2,7 +2,7 @@ /* * Watchdog driver for Marvell Armada 37xx SoCs * - * Author: Marek Behun <marek.behun@nic.cz> + * Author: Marek Behún <kabel@kernel.org> */ #include <linux/clk.h> @@ -366,7 +366,7 @@ static struct platform_driver armada_37xx_wdt_driver = { module_platform_driver(armada_37xx_wdt_driver); -MODULE_AUTHOR("Marek Behun <marek.behun@nic.cz>"); +MODULE_AUTHOR("Marek Behun <kabel@kernel.org>"); MODULE_DESCRIPTION("Armada 37xx CPU Watchdog"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/watchdog/cpu5wdt.c b/drivers/watchdog/cpu5wdt.c index 9867a3a936df..688b112e712b 100644 --- a/drivers/watchdog/cpu5wdt.c +++ b/drivers/watchdog/cpu5wdt.c @@ -273,7 +273,6 @@ module_exit(cpu5wdt_exit_module); MODULE_AUTHOR("Heiko Ronsdorf <hero@ihg.uni-duisburg.de>"); MODULE_DESCRIPTION("sma cpu5 watchdog driver"); -MODULE_SUPPORTED_DEVICE("sma cpu5 watchdog"); MODULE_LICENSE("GPL"); module_param_hw(port, int, ioport, 0); diff --git a/drivers/watchdog/cpwd.c b/drivers/watchdog/cpwd.c index 808eeb4779e4..1eafe0b4d71c 100644 --- a/drivers/watchdog/cpwd.c +++ b/drivers/watchdog/cpwd.c @@ -172,7 +172,6 @@ MODULE_PARM_DESC(wd2_timeout, "Default watchdog2 timeout in 1/10secs"); MODULE_AUTHOR("Eric Brower <ebrower@usa.net>"); MODULE_DESCRIPTION("Hardware watchdog driver for Sun Microsystems CP1400/1500"); MODULE_LICENSE("GPL"); -MODULE_SUPPORTED_DEVICE("watchdog"); static void cpwd_writew(u16 val, void __iomem *addr) { diff --git a/drivers/watchdog/riowd.c b/drivers/watchdog/riowd.c index 7008596a575f..747e346ed06c 100644 --- a/drivers/watchdog/riowd.c +++ b/drivers/watchdog/riowd.c @@ -46,7 +46,6 @@ MODULE_AUTHOR("David S. Miller <davem@davemloft.net>"); MODULE_DESCRIPTION("Hardware watchdog driver for Sun RIO"); -MODULE_SUPPORTED_DEVICE("watchdog"); MODULE_LICENSE("GPL"); #define DRIVER_NAME "riowd" diff --git a/drivers/xen/Kconfig b/drivers/xen/Kconfig index 41645fe6ad48..ea0efd290c37 100644 --- a/drivers/xen/Kconfig +++ b/drivers/xen/Kconfig @@ -50,11 +50,11 @@ config XEN_BALLOON_MEMORY_HOTPLUG SUBSYSTEM=="memory", ACTION=="add", RUN+="/bin/sh -c '[ -f /sys$devpath/state ] && echo online > /sys$devpath/state'" -config XEN_BALLOON_MEMORY_HOTPLUG_LIMIT +config XEN_MEMORY_HOTPLUG_LIMIT int "Hotplugged memory limit (in GiB) for a PV guest" default 512 depends on XEN_HAVE_PVMMU - depends on XEN_BALLOON_MEMORY_HOTPLUG + depends on MEMORY_HOTPLUG help Maxmium amount of memory (in GiB) that a PV guest can be expanded to when using memory hotplug. diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c index 8236e2364eeb..7bbfd58958bc 100644 --- a/drivers/xen/events/events_base.c +++ b/drivers/xen/events/events_base.c @@ -110,7 +110,7 @@ struct irq_info { unsigned short eoi_cpu; /* EOI must happen on this cpu-1 */ unsigned int irq_epoch; /* If eoi_cpu valid: irq_epoch of event */ u64 eoi_time; /* Time in jiffies when to EOI. */ - spinlock_t lock; + raw_spinlock_t lock; union { unsigned short virq; @@ -312,7 +312,7 @@ static int xen_irq_info_common_setup(struct irq_info *info, info->evtchn = evtchn; info->cpu = cpu; info->mask_reason = EVT_MASK_REASON_EXPLICIT; - spin_lock_init(&info->lock); + raw_spin_lock_init(&info->lock); ret = set_evtchn_to_irq(evtchn, irq); if (ret < 0) @@ -472,28 +472,28 @@ static void do_mask(struct irq_info *info, u8 reason) { unsigned long flags; - spin_lock_irqsave(&info->lock, flags); + raw_spin_lock_irqsave(&info->lock, flags); if (!info->mask_reason) mask_evtchn(info->evtchn); info->mask_reason |= reason; - spin_unlock_irqrestore(&info->lock, flags); + raw_spin_unlock_irqrestore(&info->lock, flags); } static void do_unmask(struct irq_info *info, u8 reason) { unsigned long flags; - spin_lock_irqsave(&info->lock, flags); + raw_spin_lock_irqsave(&info->lock, flags); info->mask_reason &= ~reason; if (!info->mask_reason) unmask_evtchn(info->evtchn); - spin_unlock_irqrestore(&info->lock, flags); + raw_spin_unlock_irqrestore(&info->lock, flags); } #ifdef CONFIG_X86 |