diff options
Diffstat (limited to 'drivers/hv')
| -rw-r--r-- | drivers/hv/Kconfig | 1 | ||||
| -rw-r--r-- | drivers/hv/channel.c | 176 | ||||
| -rw-r--r-- | drivers/hv/hv.c | 36 | ||||
| -rw-r--r-- | drivers/hv/hv_common.c | 99 | ||||
| -rw-r--r-- | drivers/hv/hv_util.c | 31 | ||||
| -rw-r--r-- | drivers/hv/vmbus_drv.c | 7 |
6 files changed, 208 insertions, 142 deletions
diff --git a/drivers/hv/Kconfig b/drivers/hv/Kconfig index 00242107d62e..862c47b191af 100644 --- a/drivers/hv/Kconfig +++ b/drivers/hv/Kconfig @@ -16,6 +16,7 @@ config HYPERV config HYPERV_VTL_MODE bool "Enable Linux to boot in VTL context" depends on X86_64 && HYPERV + depends on SMP default n help Virtual Secure Mode (VSM) is a set of hypervisor capabilities and diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c index 56f7e06c673e..adbf674355b2 100644 --- a/drivers/hv/channel.c +++ b/drivers/hv/channel.c @@ -322,125 +322,89 @@ static int create_gpadl_header(enum hv_gpadl_type type, void *kbuffer, pagecount = hv_gpadl_size(type, size) >> HV_HYP_PAGE_SHIFT; - /* do we need a gpadl body msg */ pfnsize = MAX_SIZE_CHANNEL_MESSAGE - sizeof(struct vmbus_channel_gpadl_header) - sizeof(struct gpa_range); + pfncount = umin(pagecount, pfnsize / sizeof(u64)); + + msgsize = sizeof(struct vmbus_channel_msginfo) + + sizeof(struct vmbus_channel_gpadl_header) + + sizeof(struct gpa_range) + pfncount * sizeof(u64); + msgheader = kzalloc(msgsize, GFP_KERNEL); + if (!msgheader) + return -ENOMEM; + + INIT_LIST_HEAD(&msgheader->submsglist); + msgheader->msgsize = msgsize; + + gpadl_header = (struct vmbus_channel_gpadl_header *) + msgheader->msg; + gpadl_header->rangecount = 1; + gpadl_header->range_buflen = sizeof(struct gpa_range) + + pagecount * sizeof(u64); + gpadl_header->range[0].byte_offset = 0; + gpadl_header->range[0].byte_count = hv_gpadl_size(type, size); + for (i = 0; i < pfncount; i++) + gpadl_header->range[0].pfn_array[i] = hv_gpadl_hvpfn( + type, kbuffer, size, send_offset, i); + *msginfo = msgheader; + + pfnsum = pfncount; + pfnleft = pagecount - pfncount; + + /* how many pfns can we fit in a body message */ + pfnsize = MAX_SIZE_CHANNEL_MESSAGE - + sizeof(struct vmbus_channel_gpadl_body); pfncount = pfnsize / sizeof(u64); - if (pagecount > pfncount) { - /* we need a gpadl body */ - /* fill in the header */ + /* + * If pfnleft is zero, everything fits in the header and no body + * messages are needed + */ + while (pfnleft) { + pfncurr = umin(pfncount, pfnleft); msgsize = sizeof(struct vmbus_channel_msginfo) + - sizeof(struct vmbus_channel_gpadl_header) + - sizeof(struct gpa_range) + pfncount * sizeof(u64); - msgheader = kzalloc(msgsize, GFP_KERNEL); - if (!msgheader) - goto nomem; - - INIT_LIST_HEAD(&msgheader->submsglist); - msgheader->msgsize = msgsize; - - gpadl_header = (struct vmbus_channel_gpadl_header *) - msgheader->msg; - gpadl_header->rangecount = 1; - gpadl_header->range_buflen = sizeof(struct gpa_range) + - pagecount * sizeof(u64); - gpadl_header->range[0].byte_offset = 0; - gpadl_header->range[0].byte_count = hv_gpadl_size(type, size); - for (i = 0; i < pfncount; i++) - gpadl_header->range[0].pfn_array[i] = hv_gpadl_hvpfn( - type, kbuffer, size, send_offset, i); - *msginfo = msgheader; - - pfnsum = pfncount; - pfnleft = pagecount - pfncount; - - /* how many pfns can we fit */ - pfnsize = MAX_SIZE_CHANNEL_MESSAGE - - sizeof(struct vmbus_channel_gpadl_body); - pfncount = pfnsize / sizeof(u64); - - /* fill in the body */ - while (pfnleft) { - if (pfnleft > pfncount) - pfncurr = pfncount; - else - pfncurr = pfnleft; - - msgsize = sizeof(struct vmbus_channel_msginfo) + - sizeof(struct vmbus_channel_gpadl_body) + - pfncurr * sizeof(u64); - msgbody = kzalloc(msgsize, GFP_KERNEL); - - if (!msgbody) { - struct vmbus_channel_msginfo *pos = NULL; - struct vmbus_channel_msginfo *tmp = NULL; - /* - * Free up all the allocated messages. - */ - list_for_each_entry_safe(pos, tmp, - &msgheader->submsglist, - msglistentry) { - - list_del(&pos->msglistentry); - kfree(pos); - } - - goto nomem; - } - - msgbody->msgsize = msgsize; - gpadl_body = - (struct vmbus_channel_gpadl_body *)msgbody->msg; + sizeof(struct vmbus_channel_gpadl_body) + + pfncurr * sizeof(u64); + msgbody = kzalloc(msgsize, GFP_KERNEL); + if (!msgbody) { + struct vmbus_channel_msginfo *pos = NULL; + struct vmbus_channel_msginfo *tmp = NULL; /* - * Gpadl is u32 and we are using a pointer which could - * be 64-bit - * This is governed by the guest/host protocol and - * so the hypervisor guarantees that this is ok. + * Free up all the allocated messages. */ - for (i = 0; i < pfncurr; i++) - gpadl_body->pfn[i] = hv_gpadl_hvpfn(type, - kbuffer, size, send_offset, pfnsum + i); - - /* add to msg header */ - list_add_tail(&msgbody->msglistentry, - &msgheader->submsglist); - pfnsum += pfncurr; - pfnleft -= pfncurr; + list_for_each_entry_safe(pos, tmp, + &msgheader->submsglist, + msglistentry) { + + list_del(&pos->msglistentry); + kfree(pos); + } + kfree(msgheader); + return -ENOMEM; } - } else { - /* everything fits in a header */ - msgsize = sizeof(struct vmbus_channel_msginfo) + - sizeof(struct vmbus_channel_gpadl_header) + - sizeof(struct gpa_range) + pagecount * sizeof(u64); - msgheader = kzalloc(msgsize, GFP_KERNEL); - if (msgheader == NULL) - goto nomem; - - INIT_LIST_HEAD(&msgheader->submsglist); - msgheader->msgsize = msgsize; - - gpadl_header = (struct vmbus_channel_gpadl_header *) - msgheader->msg; - gpadl_header->rangecount = 1; - gpadl_header->range_buflen = sizeof(struct gpa_range) + - pagecount * sizeof(u64); - gpadl_header->range[0].byte_offset = 0; - gpadl_header->range[0].byte_count = hv_gpadl_size(type, size); - for (i = 0; i < pagecount; i++) - gpadl_header->range[0].pfn_array[i] = hv_gpadl_hvpfn( - type, kbuffer, size, send_offset, i); - - *msginfo = msgheader; + + msgbody->msgsize = msgsize; + gpadl_body = (struct vmbus_channel_gpadl_body *)msgbody->msg; + + /* + * Gpadl is u32 and we are using a pointer which could + * be 64-bit + * This is governed by the guest/host protocol and + * so the hypervisor guarantees that this is ok. + */ + for (i = 0; i < pfncurr; i++) + gpadl_body->pfn[i] = hv_gpadl_hvpfn(type, + kbuffer, size, send_offset, pfnsum + i); + + /* add to msg header */ + list_add_tail(&msgbody->msglistentry, &msgheader->submsglist); + pfnsum += pfncurr; + pfnleft -= pfncurr; } return 0; -nomem: - kfree(msgheader); - kfree(msgbody); - return -ENOMEM; } /* diff --git a/drivers/hv/hv.c b/drivers/hv/hv.c index 51e5018ac9b2..a8ad728354cb 100644 --- a/drivers/hv/hv.c +++ b/drivers/hv/hv.c @@ -270,7 +270,7 @@ void hv_synic_enable_regs(unsigned int cpu) union hv_synic_scontrol sctrl; /* Setup the Synic's message page */ - simp.as_uint64 = hv_get_register(HV_REGISTER_SIMP); + simp.as_uint64 = hv_get_msr(HV_MSR_SIMP); simp.simp_enabled = 1; if (ms_hyperv.paravisor_present || hv_root_partition) { @@ -286,10 +286,10 @@ void hv_synic_enable_regs(unsigned int cpu) >> HV_HYP_PAGE_SHIFT; } - hv_set_register(HV_REGISTER_SIMP, simp.as_uint64); + hv_set_msr(HV_MSR_SIMP, simp.as_uint64); /* Setup the Synic's event page */ - siefp.as_uint64 = hv_get_register(HV_REGISTER_SIEFP); + siefp.as_uint64 = hv_get_msr(HV_MSR_SIEFP); siefp.siefp_enabled = 1; if (ms_hyperv.paravisor_present || hv_root_partition) { @@ -305,13 +305,12 @@ void hv_synic_enable_regs(unsigned int cpu) >> HV_HYP_PAGE_SHIFT; } - hv_set_register(HV_REGISTER_SIEFP, siefp.as_uint64); + hv_set_msr(HV_MSR_SIEFP, siefp.as_uint64); /* Setup the shared SINT. */ if (vmbus_irq != -1) enable_percpu_irq(vmbus_irq, 0); - shared_sint.as_uint64 = hv_get_register(HV_REGISTER_SINT0 + - VMBUS_MESSAGE_SINT); + shared_sint.as_uint64 = hv_get_msr(HV_MSR_SINT0 + VMBUS_MESSAGE_SINT); shared_sint.vector = vmbus_interrupt; shared_sint.masked = false; @@ -326,14 +325,13 @@ void hv_synic_enable_regs(unsigned int cpu) #else shared_sint.auto_eoi = 0; #endif - hv_set_register(HV_REGISTER_SINT0 + VMBUS_MESSAGE_SINT, - shared_sint.as_uint64); + hv_set_msr(HV_MSR_SINT0 + VMBUS_MESSAGE_SINT, shared_sint.as_uint64); /* Enable the global synic bit */ - sctrl.as_uint64 = hv_get_register(HV_REGISTER_SCONTROL); + sctrl.as_uint64 = hv_get_msr(HV_MSR_SCONTROL); sctrl.enable = 1; - hv_set_register(HV_REGISTER_SCONTROL, sctrl.as_uint64); + hv_set_msr(HV_MSR_SCONTROL, sctrl.as_uint64); } int hv_synic_init(unsigned int cpu) @@ -357,17 +355,15 @@ void hv_synic_disable_regs(unsigned int cpu) union hv_synic_siefp siefp; union hv_synic_scontrol sctrl; - shared_sint.as_uint64 = hv_get_register(HV_REGISTER_SINT0 + - VMBUS_MESSAGE_SINT); + shared_sint.as_uint64 = hv_get_msr(HV_MSR_SINT0 + VMBUS_MESSAGE_SINT); shared_sint.masked = 1; /* Need to correctly cleanup in the case of SMP!!! */ /* Disable the interrupt */ - hv_set_register(HV_REGISTER_SINT0 + VMBUS_MESSAGE_SINT, - shared_sint.as_uint64); + hv_set_msr(HV_MSR_SINT0 + VMBUS_MESSAGE_SINT, shared_sint.as_uint64); - simp.as_uint64 = hv_get_register(HV_REGISTER_SIMP); + simp.as_uint64 = hv_get_msr(HV_MSR_SIMP); /* * In Isolation VM, sim and sief pages are allocated by * paravisor. These pages also will be used by kdump @@ -382,9 +378,9 @@ void hv_synic_disable_regs(unsigned int cpu) simp.base_simp_gpa = 0; } - hv_set_register(HV_REGISTER_SIMP, simp.as_uint64); + hv_set_msr(HV_MSR_SIMP, simp.as_uint64); - siefp.as_uint64 = hv_get_register(HV_REGISTER_SIEFP); + siefp.as_uint64 = hv_get_msr(HV_MSR_SIEFP); siefp.siefp_enabled = 0; if (ms_hyperv.paravisor_present || hv_root_partition) { @@ -394,12 +390,12 @@ void hv_synic_disable_regs(unsigned int cpu) siefp.base_siefp_gpa = 0; } - hv_set_register(HV_REGISTER_SIEFP, siefp.as_uint64); + hv_set_msr(HV_MSR_SIEFP, siefp.as_uint64); /* Disable the global synic bit */ - sctrl.as_uint64 = hv_get_register(HV_REGISTER_SCONTROL); + sctrl.as_uint64 = hv_get_msr(HV_MSR_SCONTROL); sctrl.enable = 0; - hv_set_register(HV_REGISTER_SCONTROL, sctrl.as_uint64); + hv_set_msr(HV_MSR_SCONTROL, sctrl.as_uint64); if (vmbus_irq != -1) disable_percpu_irq(vmbus_irq); diff --git a/drivers/hv/hv_common.c b/drivers/hv/hv_common.c index 0285a74363b3..dde3f9b6871a 100644 --- a/drivers/hv/hv_common.c +++ b/drivers/hv/hv_common.c @@ -20,8 +20,11 @@ #include <linux/sched/task_stack.h> #include <linux/panic_notifier.h> #include <linux/ptrace.h> +#include <linux/random.h> +#include <linux/efi.h> #include <linux/kdebug.h> #include <linux/kmsg_dump.h> +#include <linux/sizes.h> #include <linux/slab.h> #include <linux/dma-map-ops.h> #include <linux/set_memory.h> @@ -227,19 +230,19 @@ static void hv_kmsg_dump(struct kmsg_dumper *dumper, * contain the size of the panic data in that page. Rest of the * registers are no-op when the NOTIFY_MSG flag is set. */ - hv_set_register(HV_REGISTER_CRASH_P0, 0); - hv_set_register(HV_REGISTER_CRASH_P1, 0); - hv_set_register(HV_REGISTER_CRASH_P2, 0); - hv_set_register(HV_REGISTER_CRASH_P3, virt_to_phys(hv_panic_page)); - hv_set_register(HV_REGISTER_CRASH_P4, bytes_written); + hv_set_msr(HV_MSR_CRASH_P0, 0); + hv_set_msr(HV_MSR_CRASH_P1, 0); + hv_set_msr(HV_MSR_CRASH_P2, 0); + hv_set_msr(HV_MSR_CRASH_P3, virt_to_phys(hv_panic_page)); + hv_set_msr(HV_MSR_CRASH_P4, bytes_written); /* * Let Hyper-V know there is crash data available along with * the panic message. */ - hv_set_register(HV_REGISTER_CRASH_CTL, - (HV_CRASH_CTL_CRASH_NOTIFY | - HV_CRASH_CTL_CRASH_NOTIFY_MSG)); + hv_set_msr(HV_MSR_CRASH_CTL, + (HV_CRASH_CTL_CRASH_NOTIFY | + HV_CRASH_CTL_CRASH_NOTIFY_MSG)); } static struct kmsg_dumper hv_kmsg_dumper = { @@ -278,6 +281,14 @@ static void hv_kmsg_dump_register(void) int __init hv_common_init(void) { int i; + union hv_hypervisor_version_info version; + + /* Get information about the Hyper-V host version */ + if (!hv_get_hypervisor_version(&version)) + pr_info("Hyper-V: Host Build %d.%d.%d.%d-%d-%d\n", + version.major_version, version.minor_version, + version.build_number, version.service_number, + version.service_pack, version.service_branch); if (hv_is_isolation_supported()) sysctl_record_panic_msg = 0; @@ -310,7 +321,7 @@ int __init hv_common_init(void) * Register for panic kmsg callback only if the right * capability is supported by the hypervisor. */ - hyperv_crash_ctl = hv_get_register(HV_REGISTER_CRASH_CTL); + hyperv_crash_ctl = hv_get_msr(HV_MSR_CRASH_CTL); if (hyperv_crash_ctl & HV_CRASH_CTL_CRASH_NOTIFY_MSG) hv_kmsg_dump_register(); @@ -347,6 +358,72 @@ int __init hv_common_init(void) return 0; } +void __init ms_hyperv_late_init(void) +{ + struct acpi_table_header *header; + acpi_status status; + u8 *randomdata; + u32 length, i; + + /* + * Seed the Linux random number generator with entropy provided by + * the Hyper-V host in ACPI table OEM0. + */ + if (!IS_ENABLED(CONFIG_ACPI)) + return; + + status = acpi_get_table("OEM0", 0, &header); + if (ACPI_FAILURE(status) || !header) + return; + + /* + * Since the "OEM0" table name is for OEM specific usage, verify + * that what we're seeing purports to be from Microsoft. + */ + if (strncmp(header->oem_table_id, "MICROSFT", 8)) + goto error; + + /* + * Ensure the length is reasonable. Requiring at least 8 bytes and + * no more than 4K bytes is somewhat arbitrary and just protects + * against a malformed table. Hyper-V currently provides 64 bytes, + * but allow for a change in a later version. + */ + if (header->length < sizeof(*header) + 8 || + header->length > sizeof(*header) + SZ_4K) + goto error; + + length = header->length - sizeof(*header); + randomdata = (u8 *)(header + 1); + + pr_debug("Hyper-V: Seeding rng with %d random bytes from ACPI table OEM0\n", + length); + + add_bootloader_randomness(randomdata, length); + + /* + * To prevent the seed data from being visible in /sys/firmware/acpi, + * zero out the random data in the ACPI table and fixup the checksum. + * The zero'ing is done out of an abundance of caution in avoiding + * potential security risks to the rng. Similarly, reset the table + * length to just the header size so that a subsequent kexec doesn't + * try to use the zero'ed out random data. + */ + for (i = 0; i < length; i++) { + header->checksum += randomdata[i]; + randomdata[i] = 0; + } + + for (i = 0; i < sizeof(header->length); i++) + header->checksum += ((u8 *)&header->length)[i]; + header->length = sizeof(*header); + for (i = 0; i < sizeof(header->length); i++) + header->checksum -= ((u8 *)&header->length)[i]; + +error: + acpi_put_table(header); +} + /* * Hyper-V specific initialization and die code for * individual CPUs that is common across all architectures. @@ -409,7 +486,7 @@ int hv_common_cpu_init(unsigned int cpu) *inputarg = mem; } - msr_vp_index = hv_get_register(HV_REGISTER_VP_INDEX); + msr_vp_index = hv_get_msr(HV_MSR_VP_INDEX); hv_vp_index[cpu] = msr_vp_index; @@ -506,7 +583,7 @@ EXPORT_SYMBOL_GPL(hv_is_hibernation_supported); */ static u64 __hv_read_ref_counter(void) { - return hv_get_register(HV_REGISTER_TIME_REF_COUNT); + return hv_get_msr(HV_MSR_TIME_REF_COUNT); } u64 (*hv_read_reference_counter)(void) = __hv_read_ref_counter; diff --git a/drivers/hv/hv_util.c b/drivers/hv/hv_util.c index 42aec2c5606a..9c97c4065fe7 100644 --- a/drivers/hv/hv_util.c +++ b/drivers/hv/hv_util.c @@ -296,6 +296,11 @@ static struct { spinlock_t lock; } host_ts; +static bool timesync_implicit; + +module_param(timesync_implicit, bool, 0644); +MODULE_PARM_DESC(timesync_implicit, "If set treat SAMPLE as SYNC when clock is behind"); + static inline u64 reftime_to_ns(u64 reftime) { return (reftime - WLTIMEDELTA) * 100; @@ -345,6 +350,29 @@ static void hv_set_host_time(struct work_struct *work) } /* + * Due to a bug on Hyper-V hosts, the sync flag may not always be sent on resume. + * Force a sync if the guest is behind. + */ +static inline bool hv_implicit_sync(u64 host_time) +{ + struct timespec64 new_ts; + struct timespec64 threshold_ts; + + new_ts = ns_to_timespec64(reftime_to_ns(host_time)); + ktime_get_real_ts64(&threshold_ts); + + threshold_ts.tv_sec += 5; + + /* + * If guest behind the host by 5 or more seconds. + */ + if (timespec64_compare(&new_ts, &threshold_ts) >= 0) + return true; + + return false; +} + +/* * Synchronize time with host after reboot, restore, etc. * * ICTIMESYNCFLAG_SYNC flag bit indicates reboot, restore events of the VM. @@ -384,7 +412,8 @@ static inline void adj_guesttime(u64 hosttime, u64 reftime, u8 adj_flags) spin_unlock_irqrestore(&host_ts.lock, flags); /* Schedule work to do do_settimeofday64() */ - if (adj_flags & ICTIMESYNCFLAG_SYNC) + if ((adj_flags & ICTIMESYNCFLAG_SYNC) || + (timesync_implicit && hv_implicit_sync(host_ts.host_time))) schedule_work(&adj_time_work); } diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c index b33d5abd9beb..4cb17603a828 100644 --- a/drivers/hv/vmbus_drv.c +++ b/drivers/hv/vmbus_drv.c @@ -988,7 +988,7 @@ static const struct dev_pm_ops vmbus_pm = { }; /* The one and only one */ -static struct bus_type hv_bus = { +static const struct bus_type hv_bus = { .name = "vmbus", .match = vmbus_match, .shutdown = vmbus_shutdown, @@ -2359,10 +2359,9 @@ static int vmbus_platform_driver_probe(struct platform_device *pdev) return vmbus_acpi_add(pdev); } -static int vmbus_platform_driver_remove(struct platform_device *pdev) +static void vmbus_platform_driver_remove(struct platform_device *pdev) { vmbus_mmio_remove(); - return 0; } #ifdef CONFIG_PM_SLEEP @@ -2542,7 +2541,7 @@ static const struct dev_pm_ops vmbus_bus_pm = { static struct platform_driver vmbus_platform_driver = { .probe = vmbus_platform_driver_probe, - .remove = vmbus_platform_driver_remove, + .remove_new = vmbus_platform_driver_remove, .driver = { .name = "vmbus", .acpi_match_table = ACPI_PTR(vmbus_acpi_device_ids), |