From 6a40281ab5c1ed8ba2253857118a5d400a2d084b Mon Sep 17 00:00:00 2001 From: Chuck Ebbert Date: Sat, 20 Sep 2014 10:17:51 -0500 Subject: sched: Fix end_of_stack() and location of stack canary for architectures using CONFIG_STACK_GROWSUP Aaron Tomlin recently posted patches [1] to enable checking the stack canary on every task switch. Looking at the canary code, I realized that every arch (except ia64, which adds some space for register spill above the stack) shares a definition of end_of_stack() that makes it the first long after the threadinfo. For stacks that grow down, this low address is correct because the stack starts at the end of the thread area and grows toward lower addresses. However, for stacks that grow up, toward higher addresses, this is wrong. (The stack actually grows away from the canary.) On these archs end_of_stack() should return the address of the last long, at the highest possible address for the stack. [1] http://lkml.org/lkml/2014/9/12/293 Signed-off-by: Chuck Ebbert Link: http://lkml.kernel.org/r/20140920101751.6c5166b6@as Signed-off-by: Ingo Molnar Tested-by: James Hogan [metag] Acked-by: James Hogan Acked-by: Aaron Tomlin --- include/linux/sched.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include') diff --git a/include/linux/sched.h b/include/linux/sched.h index 5c2c885ee52b..1f07040d28e3 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2608,9 +2608,22 @@ static inline void setup_thread_stack(struct task_struct *p, struct task_struct task_thread_info(p)->task = p; } +/* + * Return the address of the last usable long on the stack. + * + * When the stack grows down, this is just above the thread + * info struct. Going any lower will corrupt the threadinfo. + * + * When the stack grows up, this is the highest address. + * Beyond that position, we corrupt data on the next page. + */ static inline unsigned long *end_of_stack(struct task_struct *p) { +#ifdef CONFIG_STACK_GROWSUP + return (unsigned long *)((unsigned long)task_thread_info(p) + THREAD_SIZE) - 1; +#else return (unsigned long *)(task_thread_info(p) + 1); +#endif } #endif -- cgit v1.2.3 From 8ab17fc92e49bc2b8fff9d220c19bf50ec9c1158 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Sun, 21 Sep 2014 02:58:18 +0200 Subject: ACPI / hotplug: Generate online uevents for ACPI containers Commit 46394fd01 (ACPI / hotplug: Move container-specific code out of the core) removed the generation of "online" uevents for containers, because "add" uevents are now generated for them automatically when container system devices are registered. However, there are user space tools that need to be notified when the container and all of its children have been enumerated, which doesn't happen any more. For this reason, add a mechanism allowing "online" uevents to be generated for ACPI containers after enumerating the container along with all of its children. Fixes: 46394fd01 (ACPI / hotplug: Move container-specific code out of the core) Reported-and-tested-by: Yasuaki Ishimatsu Cc: 3.14+ # 3.14+ Signed-off-by: Rafael J. Wysocki --- drivers/acpi/container.c | 8 ++++++++ drivers/acpi/scan.c | 3 +++ include/acpi/acpi_bus.h | 1 + 3 files changed, 12 insertions(+) (limited to 'include') diff --git a/drivers/acpi/container.c b/drivers/acpi/container.c index 76f7cff64594..c8ead9f97375 100644 --- a/drivers/acpi/container.c +++ b/drivers/acpi/container.c @@ -99,6 +99,13 @@ static void container_device_detach(struct acpi_device *adev) device_unregister(dev); } +static void container_device_online(struct acpi_device *adev) +{ + struct device *dev = acpi_driver_data(adev); + + kobject_uevent(&dev->kobj, KOBJ_ONLINE); +} + static struct acpi_scan_handler container_handler = { .ids = container_device_ids, .attach = container_device_attach, @@ -106,6 +113,7 @@ static struct acpi_scan_handler container_handler = { .hotplug = { .enabled = true, .demand_offline = true, + .notify_online = container_device_online, }, }; diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c index 3bf7764659a4..1c9a664c1705 100644 --- a/drivers/acpi/scan.c +++ b/drivers/acpi/scan.c @@ -2189,6 +2189,9 @@ static void acpi_bus_attach(struct acpi_device *device) ok: list_for_each_entry(child, &device->children, node) acpi_bus_attach(child); + + if (device->handler && device->handler->hotplug.notify_online) + device->handler->hotplug.notify_online(device); } /** diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h index c1c9de19edbe..2f98cf84368f 100644 --- a/include/acpi/acpi_bus.h +++ b/include/acpi/acpi_bus.h @@ -118,6 +118,7 @@ struct acpi_device; struct acpi_hotplug_profile { struct kobject kobj; int (*scan_dependent)(struct acpi_device *adev); + void (*notify_online)(struct acpi_device *adev); bool enabled:1; bool demand_offline:1; }; -- cgit v1.2.3 From a2b86f772227bcaf962c8b134f8d187046ac5f0e Mon Sep 17 00:00:00 2001 From: Zefan Li Date: Thu, 25 Sep 2014 09:40:17 +0800 Subject: sched: fix confusing PFA_NO_NEW_PRIVS constant Commit 1d4457f99928 ("sched: move no_new_privs into new atomic flags") defined PFA_NO_NEW_PRIVS as hexadecimal value, but it is confusing because it is used as bit number. Redefine it as decimal bit number. Note this changes the bit position of PFA_NOW_NEW_PRIVS from 1 to 0. Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Miao Xie Signed-off-by: Tetsuo Handa Acked-by: Kees Cook [ lizf: slightly modified subject and changelog ] Signed-off-by: Zefan Li Signed-off-by: Tejun Heo --- include/linux/sched.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/sched.h b/include/linux/sched.h index 5c2c885ee52b..45577650f629 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1957,7 +1957,7 @@ static inline void memalloc_noio_restore(unsigned int flags) } /* Per-process atomic flags. */ -#define PFA_NO_NEW_PRIVS 0x00000001 /* May not gain new privileges. */ +#define PFA_NO_NEW_PRIVS 0 /* May not gain new privileges. */ static inline bool task_no_new_privs(struct task_struct *p) { -- cgit v1.2.3 From e0e5070b20e01f0321f97db4e4e174f3f6b49e50 Mon Sep 17 00:00:00 2001 From: Zefan Li Date: Thu, 25 Sep 2014 09:40:40 +0800 Subject: sched: add macros to define bitops for task atomic flags This will simplify code when we add new flags. v3: - Kees pointed out that no_new_privs should never be cleared, so we shouldn't define task_clear_no_new_privs(). we define 3 macros instead of a single one. v2: - updated scripts/tags.sh, suggested by Peter Cc: Ingo Molnar Cc: Miao Xie Cc: Tetsuo Handa Acked-by: Peter Zijlstra (Intel) Acked-by: Kees Cook Signed-off-by: Zefan Li Signed-off-by: Tejun Heo --- include/linux/sched.h | 21 ++++++++++++--------- scripts/tags.sh | 6 ++++++ 2 files changed, 18 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/linux/sched.h b/include/linux/sched.h index 45577650f629..5630763956d9 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1959,15 +1959,18 @@ static inline void memalloc_noio_restore(unsigned int flags) /* Per-process atomic flags. */ #define PFA_NO_NEW_PRIVS 0 /* May not gain new privileges. */ -static inline bool task_no_new_privs(struct task_struct *p) -{ - return test_bit(PFA_NO_NEW_PRIVS, &p->atomic_flags); -} - -static inline void task_set_no_new_privs(struct task_struct *p) -{ - set_bit(PFA_NO_NEW_PRIVS, &p->atomic_flags); -} +#define TASK_PFA_TEST(name, func) \ + static inline bool task_##func(struct task_struct *p) \ + { return test_bit(PFA_##name, &p->atomic_flags); } +#define TASK_PFA_SET(name, func) \ + static inline void task_set_##func(struct task_struct *p) \ + { set_bit(PFA_##name, &p->atomic_flags); } +#define TASK_PFA_CLEAR(name, func) \ + static inline void task_clear_##func(struct task_struct *p) \ + { clear_bit(PFA_##name, &p->atomic_flags); } + +TASK_PFA_TEST(NO_NEW_PRIVS, no_new_privs) +TASK_PFA_SET(NO_NEW_PRIVS, no_new_privs) /* * task->jobctl flags diff --git a/scripts/tags.sh b/scripts/tags.sh index cbfd269a6011..293828bfd4ac 100755 --- a/scripts/tags.sh +++ b/scripts/tags.sh @@ -197,6 +197,9 @@ exuberant() --regex-c++='/SETPCGFLAG\(([^,)]*).*/SetPageCgroup\1/' \ --regex-c++='/CLEARPCGFLAG\(([^,)]*).*/ClearPageCgroup\1/' \ --regex-c++='/TESTCLEARPCGFLAG\(([^,)]*).*/TestClearPageCgroup\1/' \ + --regex-c++='/TASK_PFA_TEST\([^,]*,\s*([^)]*)\)/task_\1/' \ + --regex-c++='/TASK_PFA_SET\([^,]*,\s*([^)]*)\)/task_set_\1/' \ + --regex-c++='/TASK_PFA_CLEAR\([^,]*,\s*([^)]*)\)/task_clear_\1/'\ --regex-c='/PCI_OP_READ\((\w*).*[1-4]\)/pci_bus_read_config_\1/' \ --regex-c='/PCI_OP_WRITE\((\w*).*[1-4]\)/pci_bus_write_config_\1/' \ --regex-c='/DEFINE_(MUTEX|SEMAPHORE|SPINLOCK)\((\w*)/\2/v/' \ @@ -260,6 +263,9 @@ emacs() --regex='/SETPCGFLAG\(([^,)]*).*/SetPageCgroup\1/' \ --regex='/CLEARPCGFLAG\(([^,)]*).*/ClearPageCgroup\1/' \ --regex='/TESTCLEARPCGFLAG\(([^,)]*).*/TestClearPageCgroup\1/' \ + --regex='/TASK_PFA_TEST\([^,]*,\s*([^)]*)\)/task_\1/' \ + --regex='/TASK_PFA_SET\([^,]*,\s*([^)]*)\)/task_set_\1/' \ + --regex='/TASK_PFA_CLEAR\([^,]*,\s*([^)]*)\)/task_clear_\1/' \ --regex='/_PE(\([^,)]*\).*/PEVENT_ERRNO__\1/' \ --regex='/PCI_OP_READ(\([a-z]*[a-z]\).*[1-4])/pci_bus_read_config_\1/' \ --regex='/PCI_OP_WRITE(\([a-z]*[a-z]\).*[1-4])/pci_bus_write_config_\1/'\ -- cgit v1.2.3 From 2ad654bc5e2b211e92f66da1d819e47d79a866f0 Mon Sep 17 00:00:00 2001 From: Zefan Li Date: Thu, 25 Sep 2014 09:41:02 +0800 Subject: cpuset: PF_SPREAD_PAGE and PF_SPREAD_SLAB should be atomic flags When we change cpuset.memory_spread_{page,slab}, cpuset will flip PF_SPREAD_{PAGE,SLAB} bit of tsk->flags for each task in that cpuset. This should be done using atomic bitops, but currently we don't, which is broken. Tetsuo reported a hard-to-reproduce kernel crash on RHEL6, which happened when one thread tried to clear PF_USED_MATH while at the same time another thread tried to flip PF_SPREAD_PAGE/PF_SPREAD_SLAB. They both operate on the same task. Here's the full report: https://lkml.org/lkml/2014/9/19/230 To fix this, we make PF_SPREAD_PAGE and PF_SPREAD_SLAB atomic flags. v4: - updated mm/slab.c. (Fengguang Wu) - updated Documentation. Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Miao Xie Cc: Kees Cook Fixes: 950592f7b991 ("cpusets: update tasks' page/slab spread flags in time") Cc: # 2.6.31+ Reported-by: Tetsuo Handa Signed-off-by: Zefan Li Signed-off-by: Tejun Heo --- Documentation/cgroups/cpusets.txt | 6 +++--- include/linux/cpuset.h | 4 ++-- include/linux/sched.h | 13 +++++++++++-- kernel/cpuset.c | 9 +++++---- mm/slab.c | 4 ++-- 5 files changed, 23 insertions(+), 13 deletions(-) (limited to 'include') diff --git a/Documentation/cgroups/cpusets.txt b/Documentation/cgroups/cpusets.txt index 7740038d82bc..3c94ff3f9693 100644 --- a/Documentation/cgroups/cpusets.txt +++ b/Documentation/cgroups/cpusets.txt @@ -345,14 +345,14 @@ the named feature on. The implementation is simple. Setting the flag 'cpuset.memory_spread_page' turns on a per-process flag -PF_SPREAD_PAGE for each task that is in that cpuset or subsequently +PFA_SPREAD_PAGE for each task that is in that cpuset or subsequently joins that cpuset. The page allocation calls for the page cache -is modified to perform an inline check for this PF_SPREAD_PAGE task +is modified to perform an inline check for this PFA_SPREAD_PAGE task flag, and if set, a call to a new routine cpuset_mem_spread_node() returns the node to prefer for the allocation. Similarly, setting 'cpuset.memory_spread_slab' turns on the flag -PF_SPREAD_SLAB, and appropriately marked slab caches will allocate +PFA_SPREAD_SLAB, and appropriately marked slab caches will allocate pages from the node returned by cpuset_mem_spread_node(). The cpuset_mem_spread_node() routine is also simple. It uses the diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h index ade2390ffe92..6e39c9bb0dae 100644 --- a/include/linux/cpuset.h +++ b/include/linux/cpuset.h @@ -93,12 +93,12 @@ extern int cpuset_slab_spread_node(void); static inline int cpuset_do_page_mem_spread(void) { - return current->flags & PF_SPREAD_PAGE; + return task_spread_page(current); } static inline int cpuset_do_slab_mem_spread(void) { - return current->flags & PF_SPREAD_SLAB; + return task_spread_slab(current); } extern int current_cpuset_is_being_rebound(void); diff --git a/include/linux/sched.h b/include/linux/sched.h index 5630763956d9..7b1cafefb05e 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1903,8 +1903,6 @@ extern void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, #define PF_KTHREAD 0x00200000 /* I am a kernel thread */ #define PF_RANDOMIZE 0x00400000 /* randomize virtual address space */ #define PF_SWAPWRITE 0x00800000 /* Allowed to write to swap */ -#define PF_SPREAD_PAGE 0x01000000 /* Spread page cache over cpuset */ -#define PF_SPREAD_SLAB 0x02000000 /* Spread some slab caches over cpuset */ #define PF_NO_SETAFFINITY 0x04000000 /* Userland is not allowed to meddle with cpus_allowed */ #define PF_MCE_EARLY 0x08000000 /* Early kill for mce process policy */ #define PF_MUTEX_TESTER 0x20000000 /* Thread belongs to the rt mutex tester */ @@ -1958,6 +1956,9 @@ static inline void memalloc_noio_restore(unsigned int flags) /* Per-process atomic flags. */ #define PFA_NO_NEW_PRIVS 0 /* May not gain new privileges. */ +#define PFA_SPREAD_PAGE 1 /* Spread page cache over cpuset */ +#define PFA_SPREAD_SLAB 2 /* Spread some slab caches over cpuset */ + #define TASK_PFA_TEST(name, func) \ static inline bool task_##func(struct task_struct *p) \ @@ -1972,6 +1973,14 @@ static inline void memalloc_noio_restore(unsigned int flags) TASK_PFA_TEST(NO_NEW_PRIVS, no_new_privs) TASK_PFA_SET(NO_NEW_PRIVS, no_new_privs) +TASK_PFA_TEST(SPREAD_PAGE, spread_page) +TASK_PFA_SET(SPREAD_PAGE, spread_page) +TASK_PFA_CLEAR(SPREAD_PAGE, spread_page) + +TASK_PFA_TEST(SPREAD_SLAB, spread_slab) +TASK_PFA_SET(SPREAD_SLAB, spread_slab) +TASK_PFA_CLEAR(SPREAD_SLAB, spread_slab) + /* * task->jobctl flags */ diff --git a/kernel/cpuset.c b/kernel/cpuset.c index 22874d7cf2c0..52cb04c993b7 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -365,13 +365,14 @@ static void cpuset_update_task_spread_flag(struct cpuset *cs, struct task_struct *tsk) { if (is_spread_page(cs)) - tsk->flags |= PF_SPREAD_PAGE; + task_set_spread_page(tsk); else - tsk->flags &= ~PF_SPREAD_PAGE; + task_clear_spread_page(tsk); + if (is_spread_slab(cs)) - tsk->flags |= PF_SPREAD_SLAB; + task_set_spread_slab(tsk); else - tsk->flags &= ~PF_SPREAD_SLAB; + task_clear_spread_slab(tsk); } /* diff --git a/mm/slab.c b/mm/slab.c index a467b308c682..881951e67f12 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -2994,7 +2994,7 @@ out: #ifdef CONFIG_NUMA /* - * Try allocating on another node if PF_SPREAD_SLAB is a mempolicy is set. + * Try allocating on another node if PFA_SPREAD_SLAB is a mempolicy is set. * * If we are in_interrupt, then process context, including cpusets and * mempolicy, may not apply and should not be used for allocation policy. @@ -3226,7 +3226,7 @@ __do_cache_alloc(struct kmem_cache *cache, gfp_t flags) { void *objp; - if (current->mempolicy || unlikely(current->flags & PF_SPREAD_SLAB)) { + if (current->mempolicy || cpuset_do_slab_mem_spread()) { objp = alternate_node_alloc(cache, flags); if (objp) goto out; -- cgit v1.2.3 From 17f4a5c47f28de9ea59182f48d07f8c44ee5dcc9 Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Mon, 22 Sep 2014 19:41:00 +0200 Subject: i2c: move acpi code back into the core Commit 5d98e61d337c ("I2C/ACPI: Add i2c ACPI operation region support") renamed the i2c-core module. This may cause regressions for distributions, so put the ACPI code back into the core. Reported-by: Jean Delvare Signed-off-by: Wolfram Sang Tested-by: Lan Tianyu Tested-by: Mika Westerberg --- MAINTAINERS | 1 - drivers/i2c/Makefile | 5 +- drivers/i2c/i2c-acpi.c | 364 ------------------------------------------------- drivers/i2c/i2c-core.c | 354 +++++++++++++++++++++++++++++++++++++++++++++++ include/linux/i2c.h | 16 --- 5 files changed, 355 insertions(+), 385 deletions(-) delete mode 100644 drivers/i2c/i2c-acpi.c (limited to 'include') diff --git a/MAINTAINERS b/MAINTAINERS index 809ecd680d88..e3682d0dea1e 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -4477,7 +4477,6 @@ M: Mika Westerberg L: linux-i2c@vger.kernel.org L: linux-acpi@vger.kernel.org S: Maintained -F: drivers/i2c/i2c-acpi.c I2C-TAOS-EVM DRIVER M: Jean Delvare diff --git a/drivers/i2c/Makefile b/drivers/i2c/Makefile index e0228b228256..1722f50f2473 100644 --- a/drivers/i2c/Makefile +++ b/drivers/i2c/Makefile @@ -2,11 +2,8 @@ # Makefile for the i2c core. # -i2ccore-y := i2c-core.o -i2ccore-$(CONFIG_ACPI) += i2c-acpi.o - obj-$(CONFIG_I2C_BOARDINFO) += i2c-boardinfo.o -obj-$(CONFIG_I2C) += i2ccore.o +obj-$(CONFIG_I2C) += i2c-core.o obj-$(CONFIG_I2C_SMBUS) += i2c-smbus.o obj-$(CONFIG_I2C_CHARDEV) += i2c-dev.o obj-$(CONFIG_I2C_MUX) += i2c-mux.o diff --git a/drivers/i2c/i2c-acpi.c b/drivers/i2c/i2c-acpi.c deleted file mode 100644 index 0dbc18c15c43..000000000000 --- a/drivers/i2c/i2c-acpi.c +++ /dev/null @@ -1,364 +0,0 @@ -/* - * I2C ACPI code - * - * Copyright (C) 2014 Intel Corp - * - * Author: Lan Tianyu - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY - * or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License - * for more details. - */ -#define pr_fmt(fmt) "I2C/ACPI : " fmt - -#include -#include -#include -#include -#include - -struct acpi_i2c_handler_data { - struct acpi_connection_info info; - struct i2c_adapter *adapter; -}; - -struct gsb_buffer { - u8 status; - u8 len; - union { - u16 wdata; - u8 bdata; - u8 data[0]; - }; -} __packed; - -static int acpi_i2c_add_resource(struct acpi_resource *ares, void *data) -{ - struct i2c_board_info *info = data; - - if (ares->type == ACPI_RESOURCE_TYPE_SERIAL_BUS) { - struct acpi_resource_i2c_serialbus *sb; - - sb = &ares->data.i2c_serial_bus; - if (sb->type == ACPI_RESOURCE_SERIAL_TYPE_I2C) { - info->addr = sb->slave_address; - if (sb->access_mode == ACPI_I2C_10BIT_MODE) - info->flags |= I2C_CLIENT_TEN; - } - } else if (info->irq < 0) { - struct resource r; - - if (acpi_dev_resource_interrupt(ares, 0, &r)) - info->irq = r.start; - } - - /* Tell the ACPI core to skip this resource */ - return 1; -} - -static acpi_status acpi_i2c_add_device(acpi_handle handle, u32 level, - void *data, void **return_value) -{ - struct i2c_adapter *adapter = data; - struct list_head resource_list; - struct i2c_board_info info; - struct acpi_device *adev; - int ret; - - if (acpi_bus_get_device(handle, &adev)) - return AE_OK; - if (acpi_bus_get_status(adev) || !adev->status.present) - return AE_OK; - - memset(&info, 0, sizeof(info)); - info.acpi_node.companion = adev; - info.irq = -1; - - INIT_LIST_HEAD(&resource_list); - ret = acpi_dev_get_resources(adev, &resource_list, - acpi_i2c_add_resource, &info); - acpi_dev_free_resource_list(&resource_list); - - if (ret < 0 || !info.addr) - return AE_OK; - - adev->power.flags.ignore_parent = true; - strlcpy(info.type, dev_name(&adev->dev), sizeof(info.type)); - if (!i2c_new_device(adapter, &info)) { - adev->power.flags.ignore_parent = false; - dev_err(&adapter->dev, - "failed to add I2C device %s from ACPI\n", - dev_name(&adev->dev)); - } - - return AE_OK; -} - -/** - * acpi_i2c_register_devices - enumerate I2C slave devices behind adapter - * @adap: pointer to adapter - * - * Enumerate all I2C slave devices behind this adapter by walking the ACPI - * namespace. When a device is found it will be added to the Linux device - * model and bound to the corresponding ACPI handle. - */ -void acpi_i2c_register_devices(struct i2c_adapter *adap) -{ - acpi_handle handle; - acpi_status status; - - if (!adap->dev.parent) - return; - - handle = ACPI_HANDLE(adap->dev.parent); - if (!handle) - return; - - status = acpi_walk_namespace(ACPI_TYPE_DEVICE, handle, 1, - acpi_i2c_add_device, NULL, - adap, NULL); - if (ACPI_FAILURE(status)) - dev_warn(&adap->dev, "failed to enumerate I2C slaves\n"); -} - -#ifdef CONFIG_ACPI_I2C_OPREGION -static int acpi_gsb_i2c_read_bytes(struct i2c_client *client, - u8 cmd, u8 *data, u8 data_len) -{ - - struct i2c_msg msgs[2]; - int ret; - u8 *buffer; - - buffer = kzalloc(data_len, GFP_KERNEL); - if (!buffer) - return AE_NO_MEMORY; - - msgs[0].addr = client->addr; - msgs[0].flags = client->flags; - msgs[0].len = 1; - msgs[0].buf = &cmd; - - msgs[1].addr = client->addr; - msgs[1].flags = client->flags | I2C_M_RD; - msgs[1].len = data_len; - msgs[1].buf = buffer; - - ret = i2c_transfer(client->adapter, msgs, ARRAY_SIZE(msgs)); - if (ret < 0) - dev_err(&client->adapter->dev, "i2c read failed\n"); - else - memcpy(data, buffer, data_len); - - kfree(buffer); - return ret; -} - -static int acpi_gsb_i2c_write_bytes(struct i2c_client *client, - u8 cmd, u8 *data, u8 data_len) -{ - - struct i2c_msg msgs[1]; - u8 *buffer; - int ret = AE_OK; - - buffer = kzalloc(data_len + 1, GFP_KERNEL); - if (!buffer) - return AE_NO_MEMORY; - - buffer[0] = cmd; - memcpy(buffer + 1, data, data_len); - - msgs[0].addr = client->addr; - msgs[0].flags = client->flags; - msgs[0].len = data_len + 1; - msgs[0].buf = buffer; - - ret = i2c_transfer(client->adapter, msgs, ARRAY_SIZE(msgs)); - if (ret < 0) - dev_err(&client->adapter->dev, "i2c write failed\n"); - - kfree(buffer); - return ret; -} - -static acpi_status -acpi_i2c_space_handler(u32 function, acpi_physical_address command, - u32 bits, u64 *value64, - void *handler_context, void *region_context) -{ - struct gsb_buffer *gsb = (struct gsb_buffer *)value64; - struct acpi_i2c_handler_data *data = handler_context; - struct acpi_connection_info *info = &data->info; - struct acpi_resource_i2c_serialbus *sb; - struct i2c_adapter *adapter = data->adapter; - struct i2c_client client; - struct acpi_resource *ares; - u32 accessor_type = function >> 16; - u8 action = function & ACPI_IO_MASK; - acpi_status ret = AE_OK; - int status; - - ret = acpi_buffer_to_resource(info->connection, info->length, &ares); - if (ACPI_FAILURE(ret)) - return ret; - - if (!value64 || ares->type != ACPI_RESOURCE_TYPE_SERIAL_BUS) { - ret = AE_BAD_PARAMETER; - goto err; - } - - sb = &ares->data.i2c_serial_bus; - if (sb->type != ACPI_RESOURCE_SERIAL_TYPE_I2C) { - ret = AE_BAD_PARAMETER; - goto err; - } - - memset(&client, 0, sizeof(client)); - client.adapter = adapter; - client.addr = sb->slave_address; - client.flags = 0; - - if (sb->access_mode == ACPI_I2C_10BIT_MODE) - client.flags |= I2C_CLIENT_TEN; - - switch (accessor_type) { - case ACPI_GSB_ACCESS_ATTRIB_SEND_RCV: - if (action == ACPI_READ) { - status = i2c_smbus_read_byte(&client); - if (status >= 0) { - gsb->bdata = status; - status = 0; - } - } else { - status = i2c_smbus_write_byte(&client, gsb->bdata); - } - break; - - case ACPI_GSB_ACCESS_ATTRIB_BYTE: - if (action == ACPI_READ) { - status = i2c_smbus_read_byte_data(&client, command); - if (status >= 0) { - gsb->bdata = status; - status = 0; - } - } else { - status = i2c_smbus_write_byte_data(&client, command, - gsb->bdata); - } - break; - - case ACPI_GSB_ACCESS_ATTRIB_WORD: - if (action == ACPI_READ) { - status = i2c_smbus_read_word_data(&client, command); - if (status >= 0) { - gsb->wdata = status; - status = 0; - } - } else { - status = i2c_smbus_write_word_data(&client, command, - gsb->wdata); - } - break; - - case ACPI_GSB_ACCESS_ATTRIB_BLOCK: - if (action == ACPI_READ) { - status = i2c_smbus_read_block_data(&client, command, - gsb->data); - if (status >= 0) { - gsb->len = status; - status = 0; - } - } else { - status = i2c_smbus_write_block_data(&client, command, - gsb->len, gsb->data); - } - break; - - case ACPI_GSB_ACCESS_ATTRIB_MULTIBYTE: - if (action == ACPI_READ) { - status = acpi_gsb_i2c_read_bytes(&client, command, - gsb->data, info->access_length); - if (status > 0) - status = 0; - } else { - status = acpi_gsb_i2c_write_bytes(&client, command, - gsb->data, info->access_length); - } - break; - - default: - pr_info("protocol(0x%02x) is not supported.\n", accessor_type); - ret = AE_BAD_PARAMETER; - goto err; - } - - gsb->status = status; - - err: - ACPI_FREE(ares); - return ret; -} - - -int acpi_i2c_install_space_handler(struct i2c_adapter *adapter) -{ - acpi_handle handle = ACPI_HANDLE(adapter->dev.parent); - struct acpi_i2c_handler_data *data; - acpi_status status; - - if (!handle) - return -ENODEV; - - data = kzalloc(sizeof(struct acpi_i2c_handler_data), - GFP_KERNEL); - if (!data) - return -ENOMEM; - - data->adapter = adapter; - status = acpi_bus_attach_private_data(handle, (void *)data); - if (ACPI_FAILURE(status)) { - kfree(data); - return -ENOMEM; - } - - status = acpi_install_address_space_handler(handle, - ACPI_ADR_SPACE_GSBUS, - &acpi_i2c_space_handler, - NULL, - data); - if (ACPI_FAILURE(status)) { - dev_err(&adapter->dev, "Error installing i2c space handler\n"); - acpi_bus_detach_private_data(handle); - kfree(data); - return -ENOMEM; - } - - return 0; -} - -void acpi_i2c_remove_space_handler(struct i2c_adapter *adapter) -{ - acpi_handle handle = ACPI_HANDLE(adapter->dev.parent); - struct acpi_i2c_handler_data *data; - acpi_status status; - - if (!handle) - return; - - acpi_remove_address_space_handler(handle, - ACPI_ADR_SPACE_GSBUS, - &acpi_i2c_space_handler); - - status = acpi_bus_get_private_data(handle, (void **)&data); - if (ACPI_SUCCESS(status)) - kfree(data); - - acpi_bus_detach_private_data(handle); -} -#endif diff --git a/drivers/i2c/i2c-core.c b/drivers/i2c/i2c-core.c index 632057a44615..b696ac7e6d86 100644 --- a/drivers/i2c/i2c-core.c +++ b/drivers/i2c/i2c-core.c @@ -27,6 +27,8 @@ OF support is copyright (c) 2008 Jochen Friedrich (based on a previous patch from Jon Smirl ) and (c) 2013 Wolfram Sang + I2C ACPI code Copyright (C) 2014 Intel Corp + Author: Lan Tianyu */ #include @@ -78,6 +80,358 @@ void i2c_transfer_trace_unreg(void) static_key_slow_dec(&i2c_trace_msg); } +#if defined(CONFIG_ACPI) +struct acpi_i2c_handler_data { + struct acpi_connection_info info; + struct i2c_adapter *adapter; +}; + +struct gsb_buffer { + u8 status; + u8 len; + union { + u16 wdata; + u8 bdata; + u8 data[0]; + }; +} __packed; + +static int acpi_i2c_add_resource(struct acpi_resource *ares, void *data) +{ + struct i2c_board_info *info = data; + + if (ares->type == ACPI_RESOURCE_TYPE_SERIAL_BUS) { + struct acpi_resource_i2c_serialbus *sb; + + sb = &ares->data.i2c_serial_bus; + if (sb->type == ACPI_RESOURCE_SERIAL_TYPE_I2C) { + info->addr = sb->slave_address; + if (sb->access_mode == ACPI_I2C_10BIT_MODE) + info->flags |= I2C_CLIENT_TEN; + } + } else if (info->irq < 0) { + struct resource r; + + if (acpi_dev_resource_interrupt(ares, 0, &r)) + info->irq = r.start; + } + + /* Tell the ACPI core to skip this resource */ + return 1; +} + +static acpi_status acpi_i2c_add_device(acpi_handle handle, u32 level, + void *data, void **return_value) +{ + struct i2c_adapter *adapter = data; + struct list_head resource_list; + struct i2c_board_info info; + struct acpi_device *adev; + int ret; + + if (acpi_bus_get_device(handle, &adev)) + return AE_OK; + if (acpi_bus_get_status(adev) || !adev->status.present) + return AE_OK; + + memset(&info, 0, sizeof(info)); + info.acpi_node.companion = adev; + info.irq = -1; + + INIT_LIST_HEAD(&resource_list); + ret = acpi_dev_get_resources(adev, &resource_list, + acpi_i2c_add_resource, &info); + acpi_dev_free_resource_list(&resource_list); + + if (ret < 0 || !info.addr) + return AE_OK; + + adev->power.flags.ignore_parent = true; + strlcpy(info.type, dev_name(&adev->dev), sizeof(info.type)); + if (!i2c_new_device(adapter, &info)) { + adev->power.flags.ignore_parent = false; + dev_err(&adapter->dev, + "failed to add I2C device %s from ACPI\n", + dev_name(&adev->dev)); + } + + return AE_OK; +} + +/** + * acpi_i2c_register_devices - enumerate I2C slave devices behind adapter + * @adap: pointer to adapter + * + * Enumerate all I2C slave devices behind this adapter by walking the ACPI + * namespace. When a device is found it will be added to the Linux device + * model and bound to the corresponding ACPI handle. + */ +static void acpi_i2c_register_devices(struct i2c_adapter *adap) +{ + acpi_handle handle; + acpi_status status; + + if (!adap->dev.parent) + return; + + handle = ACPI_HANDLE(adap->dev.parent); + if (!handle) + return; + + status = acpi_walk_namespace(ACPI_TYPE_DEVICE, handle, 1, + acpi_i2c_add_device, NULL, + adap, NULL); + if (ACPI_FAILURE(status)) + dev_warn(&adap->dev, "failed to enumerate I2C slaves\n"); +} + +#else /* CONFIG_ACPI */ +static inline void acpi_i2c_register_devices(struct i2c_adapter *adap) { } +#endif /* CONFIG_ACPI */ + +#ifdef CONFIG_ACPI_I2C_OPREGION +static int acpi_gsb_i2c_read_bytes(struct i2c_client *client, + u8 cmd, u8 *data, u8 data_len) +{ + + struct i2c_msg msgs[2]; + int ret; + u8 *buffer; + + buffer = kzalloc(data_len, GFP_KERNEL); + if (!buffer) + return AE_NO_MEMORY; + + msgs[0].addr = client->addr; + msgs[0].flags = client->flags; + msgs[0].len = 1; + msgs[0].buf = &cmd; + + msgs[1].addr = client->addr; + msgs[1].flags = client->flags | I2C_M_RD; + msgs[1].len = data_len; + msgs[1].buf = buffer; + + ret = i2c_transfer(client->adapter, msgs, ARRAY_SIZE(msgs)); + if (ret < 0) + dev_err(&client->adapter->dev, "i2c read failed\n"); + else + memcpy(data, buffer, data_len); + + kfree(buffer); + return ret; +} + +static int acpi_gsb_i2c_write_bytes(struct i2c_client *client, + u8 cmd, u8 *data, u8 data_len) +{ + + struct i2c_msg msgs[1]; + u8 *buffer; + int ret = AE_OK; + + buffer = kzalloc(data_len + 1, GFP_KERNEL); + if (!buffer) + return AE_NO_MEMORY; + + buffer[0] = cmd; + memcpy(buffer + 1, data, data_len); + + msgs[0].addr = client->addr; + msgs[0].flags = client->flags; + msgs[0].len = data_len + 1; + msgs[0].buf = buffer; + + ret = i2c_transfer(client->adapter, msgs, ARRAY_SIZE(msgs)); + if (ret < 0) + dev_err(&client->adapter->dev, "i2c write failed\n"); + + kfree(buffer); + return ret; +} + +static acpi_status +acpi_i2c_space_handler(u32 function, acpi_physical_address command, + u32 bits, u64 *value64, + void *handler_context, void *region_context) +{ + struct gsb_buffer *gsb = (struct gsb_buffer *)value64; + struct acpi_i2c_handler_data *data = handler_context; + struct acpi_connection_info *info = &data->info; + struct acpi_resource_i2c_serialbus *sb; + struct i2c_adapter *adapter = data->adapter; + struct i2c_client client; + struct acpi_resource *ares; + u32 accessor_type = function >> 16; + u8 action = function & ACPI_IO_MASK; + acpi_status ret = AE_OK; + int status; + + ret = acpi_buffer_to_resource(info->connection, info->length, &ares); + if (ACPI_FAILURE(ret)) + return ret; + + if (!value64 || ares->type != ACPI_RESOURCE_TYPE_SERIAL_BUS) { + ret = AE_BAD_PARAMETER; + goto err; + } + + sb = &ares->data.i2c_serial_bus; + if (sb->type != ACPI_RESOURCE_SERIAL_TYPE_I2C) { + ret = AE_BAD_PARAMETER; + goto err; + } + + memset(&client, 0, sizeof(client)); + client.adapter = adapter; + client.addr = sb->slave_address; + client.flags = 0; + + if (sb->access_mode == ACPI_I2C_10BIT_MODE) + client.flags |= I2C_CLIENT_TEN; + + switch (accessor_type) { + case ACPI_GSB_ACCESS_ATTRIB_SEND_RCV: + if (action == ACPI_READ) { + status = i2c_smbus_read_byte(&client); + if (status >= 0) { + gsb->bdata = status; + status = 0; + } + } else { + status = i2c_smbus_write_byte(&client, gsb->bdata); + } + break; + + case ACPI_GSB_ACCESS_ATTRIB_BYTE: + if (action == ACPI_READ) { + status = i2c_smbus_read_byte_data(&client, command); + if (status >= 0) { + gsb->bdata = status; + status = 0; + } + } else { + status = i2c_smbus_write_byte_data(&client, command, + gsb->bdata); + } + break; + + case ACPI_GSB_ACCESS_ATTRIB_WORD: + if (action == ACPI_READ) { + status = i2c_smbus_read_word_data(&client, command); + if (status >= 0) { + gsb->wdata = status; + status = 0; + } + } else { + status = i2c_smbus_write_word_data(&client, command, + gsb->wdata); + } + break; + + case ACPI_GSB_ACCESS_ATTRIB_BLOCK: + if (action == ACPI_READ) { + status = i2c_smbus_read_block_data(&client, command, + gsb->data); + if (status >= 0) { + gsb->len = status; + status = 0; + } + } else { + status = i2c_smbus_write_block_data(&client, command, + gsb->len, gsb->data); + } + break; + + case ACPI_GSB_ACCESS_ATTRIB_MULTIBYTE: + if (action == ACPI_READ) { + status = acpi_gsb_i2c_read_bytes(&client, command, + gsb->data, info->access_length); + if (status > 0) + status = 0; + } else { + status = acpi_gsb_i2c_write_bytes(&client, command, + gsb->data, info->access_length); + } + break; + + default: + pr_info("protocol(0x%02x) is not supported.\n", accessor_type); + ret = AE_BAD_PARAMETER; + goto err; + } + + gsb->status = status; + + err: + ACPI_FREE(ares); + return ret; +} + + +static int acpi_i2c_install_space_handler(struct i2c_adapter *adapter) +{ + acpi_handle handle = ACPI_HANDLE(adapter->dev.parent); + struct acpi_i2c_handler_data *data; + acpi_status status; + + if (!handle) + return -ENODEV; + + data = kzalloc(sizeof(struct acpi_i2c_handler_data), + GFP_KERNEL); + if (!data) + return -ENOMEM; + + data->adapter = adapter; + status = acpi_bus_attach_private_data(handle, (void *)data); + if (ACPI_FAILURE(status)) { + kfree(data); + return -ENOMEM; + } + + status = acpi_install_address_space_handler(handle, + ACPI_ADR_SPACE_GSBUS, + &acpi_i2c_space_handler, + NULL, + data); + if (ACPI_FAILURE(status)) { + dev_err(&adapter->dev, "Error installing i2c space handler\n"); + acpi_bus_detach_private_data(handle); + kfree(data); + return -ENOMEM; + } + + return 0; +} + +static void acpi_i2c_remove_space_handler(struct i2c_adapter *adapter) +{ + acpi_handle handle = ACPI_HANDLE(adapter->dev.parent); + struct acpi_i2c_handler_data *data; + acpi_status status; + + if (!handle) + return; + + acpi_remove_address_space_handler(handle, + ACPI_ADR_SPACE_GSBUS, + &acpi_i2c_space_handler); + + status = acpi_bus_get_private_data(handle, (void **)&data); + if (ACPI_SUCCESS(status)) + kfree(data); + + acpi_bus_detach_private_data(handle); +} +#else /* CONFIG_ACPI_I2C_OPREGION */ +static inline void acpi_i2c_remove_space_handler(struct i2c_adapter *adapter) +{ } + +static inline int acpi_i2c_install_space_handler(struct i2c_adapter *adapter) +{ return 0; } +#endif /* CONFIG_ACPI_I2C_OPREGION */ + /* ------------------------------------------------------------------------- */ static const struct i2c_device_id *i2c_match_id(const struct i2c_device_id *id, diff --git a/include/linux/i2c.h b/include/linux/i2c.h index a95efeb53a8b..b556e0ab946f 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -577,20 +577,4 @@ static inline struct i2c_adapter *of_find_i2c_adapter_by_node(struct device_node } #endif /* CONFIG_OF */ -#ifdef CONFIG_ACPI -void acpi_i2c_register_devices(struct i2c_adapter *adap); -#else -static inline void acpi_i2c_register_devices(struct i2c_adapter *adap) { } -#endif /* CONFIG_ACPI */ - -#ifdef CONFIG_ACPI_I2C_OPREGION -int acpi_i2c_install_space_handler(struct i2c_adapter *adapter); -void acpi_i2c_remove_space_handler(struct i2c_adapter *adapter); -#else -static inline void acpi_i2c_remove_space_handler(struct i2c_adapter *adapter) -{ } -static inline int acpi_i2c_install_space_handler(struct i2c_adapter *adapter) -{ return 0; } -#endif /* CONFIG_ACPI_I2C_OPREGION */ - #endif /* _LINUX_I2C_H */ -- cgit v1.2.3 From 2c80929c4c4d54e568b07ab85877d5fd38f4b02f Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Wed, 24 Sep 2014 17:09:11 +0200 Subject: fuse: honour max_read and max_write in direct_io mode The third argument of fuse_get_user_pages() "nbytesp" refers to the number of bytes a caller asked to pack into fuse request. This value may be lesser than capacity of fuse request or iov_iter. So fuse_get_user_pages() must ensure that *nbytesp won't grow. Now, when helper iov_iter_get_pages() performs all hard work of extracting pages from iov_iter, it can be done by passing properly calculated "maxsize" to the helper. The other caller of iov_iter_get_pages() (dio_refill_pages()) doesn't need this capability, so pass LONG_MAX as the maxsize argument here. Fixes: c9c37e2e6378 ("fuse: switch to iov_iter_get_pages()") Reported-by: Werner Baumann Tested-by: Maxim Patlasov Signed-off-by: Miklos Szeredi Signed-off-by: Al Viro --- fs/direct-io.c | 2 +- fs/fuse/file.c | 1 + include/linux/uio.h | 2 +- mm/iov_iter.c | 14 +++++++++----- 4 files changed, 12 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/fs/direct-io.c b/fs/direct-io.c index c3116404ab49..e181b6b2e297 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -158,7 +158,7 @@ static inline int dio_refill_pages(struct dio *dio, struct dio_submit *sdio) { ssize_t ret; - ret = iov_iter_get_pages(sdio->iter, dio->pages, DIO_PAGES, + ret = iov_iter_get_pages(sdio->iter, dio->pages, LONG_MAX, DIO_PAGES, &sdio->from); if (ret < 0 && sdio->blocks_available && (dio->rw & WRITE)) { diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 912061ac4baf..caa8d95b24e8 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -1305,6 +1305,7 @@ static int fuse_get_user_pages(struct fuse_req *req, struct iov_iter *ii, size_t start; ssize_t ret = iov_iter_get_pages(ii, &req->pages[req->num_pages], + *nbytesp - nbytes, req->max_pages - req->num_pages, &start); if (ret < 0) diff --git a/include/linux/uio.h b/include/linux/uio.h index 48d64e6ab292..290fbf0b6b8a 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -84,7 +84,7 @@ unsigned long iov_iter_alignment(const struct iov_iter *i); void iov_iter_init(struct iov_iter *i, int direction, const struct iovec *iov, unsigned long nr_segs, size_t count); ssize_t iov_iter_get_pages(struct iov_iter *i, struct page **pages, - unsigned maxpages, size_t *start); + size_t maxsize, unsigned maxpages, size_t *start); ssize_t iov_iter_get_pages_alloc(struct iov_iter *i, struct page ***pages, size_t maxsize, size_t *start); int iov_iter_npages(const struct iov_iter *i, int maxpages); diff --git a/mm/iov_iter.c b/mm/iov_iter.c index ab88dc0ea1d3..9a09f2034fcc 100644 --- a/mm/iov_iter.c +++ b/mm/iov_iter.c @@ -310,7 +310,7 @@ void iov_iter_init(struct iov_iter *i, int direction, EXPORT_SYMBOL(iov_iter_init); static ssize_t get_pages_iovec(struct iov_iter *i, - struct page **pages, unsigned maxpages, + struct page **pages, size_t maxsize, unsigned maxpages, size_t *start) { size_t offset = i->iov_offset; @@ -323,6 +323,8 @@ static ssize_t get_pages_iovec(struct iov_iter *i, len = iov->iov_len - offset; if (len > i->count) len = i->count; + if (len > maxsize) + len = maxsize; addr = (unsigned long)iov->iov_base + offset; len += *start = addr & (PAGE_SIZE - 1); if (len > maxpages * PAGE_SIZE) @@ -588,13 +590,15 @@ static unsigned long alignment_bvec(const struct iov_iter *i) } static ssize_t get_pages_bvec(struct iov_iter *i, - struct page **pages, unsigned maxpages, + struct page **pages, size_t maxsize, unsigned maxpages, size_t *start) { const struct bio_vec *bvec = i->bvec; size_t len = bvec->bv_len - i->iov_offset; if (len > i->count) len = i->count; + if (len > maxsize) + len = maxsize; /* can't be more than PAGE_SIZE */ *start = bvec->bv_offset + i->iov_offset; @@ -711,13 +715,13 @@ unsigned long iov_iter_alignment(const struct iov_iter *i) EXPORT_SYMBOL(iov_iter_alignment); ssize_t iov_iter_get_pages(struct iov_iter *i, - struct page **pages, unsigned maxpages, + struct page **pages, size_t maxsize, unsigned maxpages, size_t *start) { if (i->type & ITER_BVEC) - return get_pages_bvec(i, pages, maxpages, start); + return get_pages_bvec(i, pages, maxsize, maxpages, start); else - return get_pages_iovec(i, pages, maxpages, start); + return get_pages_iovec(i, pages, maxsize, maxpages, start); } EXPORT_SYMBOL(iov_iter_get_pages); -- cgit v1.2.3 From 705f1c869d577c8055736dd02501f26a2507dd5b Mon Sep 17 00:00:00 2001 From: Hannes Frederic Sowa Date: Sun, 28 Sep 2014 00:46:06 +0200 Subject: ipv6: remove rt6i_genid Eric Dumazet noticed that all no-nonexthop or no-gateway routes which are already marked DST_HOST (e.g. input routes routes) will always be invalidated during sk_dst_check. Thus per-socket dst caching absolutely had no effect and early demuxing had no effect. Thus this patch removes rt6i_genid: fn_sernum already gets modified during add operations, so we only must ensure we mutate fn_sernum during ipv6 address remove operations. This is a fairly cost extensive operations, but address removal should not happen that often. Also our mtu update functions do the same and we heard no complains so far. xfrm policy changes also cause a call into fib6_flush_trees. Also plug a hole in rt6_info (no cacheline changes). I verified via tracing that this change has effect. Cc: Eric Dumazet Cc: YOSHIFUJI Hideaki Cc: Vlad Yasevich Cc: Nicolas Dichtel Cc: Martin Lau Signed-off-by: Hannes Frederic Sowa Signed-off-by: David S. Miller --- include/net/ip6_fib.h | 5 +---- include/net/net_namespace.h | 20 +++----------------- net/ipv6/addrconf.c | 3 ++- net/ipv6/addrconf_core.c | 7 +++++++ net/ipv6/ip6_fib.c | 20 ++++++++++++++++++++ net/ipv6/route.c | 4 ---- 6 files changed, 33 insertions(+), 26 deletions(-) (limited to 'include') diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index 9bcb220bd4ad..cf485f9aa563 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -114,16 +114,13 @@ struct rt6_info { u32 rt6i_flags; struct rt6key rt6i_src; struct rt6key rt6i_prefsrc; - u32 rt6i_metric; struct inet6_dev *rt6i_idev; unsigned long _rt6i_peer; - u32 rt6i_genid; - + u32 rt6i_metric; /* more non-fragment space at head required */ unsigned short rt6i_nfheader_len; - u8 rt6i_protocol; }; diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index 361d26077196..e0d64667a4b3 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -352,26 +352,12 @@ static inline void rt_genid_bump_ipv4(struct net *net) atomic_inc(&net->ipv4.rt_genid); } -#if IS_ENABLED(CONFIG_IPV6) -static inline int rt_genid_ipv6(struct net *net) -{ - return atomic_read(&net->ipv6.rt_genid); -} - -static inline void rt_genid_bump_ipv6(struct net *net) -{ - atomic_inc(&net->ipv6.rt_genid); -} -#else -static inline int rt_genid_ipv6(struct net *net) -{ - return 0; -} - +extern void (*__fib6_flush_trees)(struct net *net); static inline void rt_genid_bump_ipv6(struct net *net) { + if (__fib6_flush_trees) + __fib6_flush_trees(net); } -#endif #if IS_ENABLED(CONFIG_IEEE802154_6LOWPAN) static inline struct netns_ieee802154_lowpan * diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 3342ee64f2e3..3e118dfddd02 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -4780,10 +4780,11 @@ static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp) if (ip6_del_rt(ifp->rt)) dst_free(&ifp->rt->dst); + + rt_genid_bump_ipv6(net); break; } atomic_inc(&net->ipv6.dev_addr_genid); - rt_genid_bump_ipv6(net); } static void ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp) diff --git a/net/ipv6/addrconf_core.c b/net/ipv6/addrconf_core.c index e6960457f625..98cc4cd570e2 100644 --- a/net/ipv6/addrconf_core.c +++ b/net/ipv6/addrconf_core.c @@ -8,6 +8,13 @@ #include #include +/* if ipv6 module registers this function is used by xfrm to force all + * sockets to relookup their nodes - this is fairly expensive, be + * careful + */ +void (*__fib6_flush_trees)(struct net *); +EXPORT_SYMBOL(__fib6_flush_trees); + #define IPV6_ADDR_SCOPE_TYPE(scope) ((scope) << 16) static inline unsigned int ipv6_addr_scope2type(unsigned int scope) diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 76b7f5ee8f4c..97b9fa8de377 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -1605,6 +1605,24 @@ static void fib6_prune_clones(struct net *net, struct fib6_node *fn) fib6_clean_tree(net, fn, fib6_prune_clone, 1, NULL); } +static int fib6_update_sernum(struct rt6_info *rt, void *arg) +{ + __u32 sernum = *(__u32 *)arg; + + if (rt->rt6i_node && + rt->rt6i_node->fn_sernum != sernum) + rt->rt6i_node->fn_sernum = sernum; + + return 0; +} + +static void fib6_flush_trees(struct net *net) +{ + __u32 new_sernum = fib6_new_sernum(); + + fib6_clean_all(net, fib6_update_sernum, &new_sernum); +} + /* * Garbage collection */ @@ -1788,6 +1806,8 @@ int __init fib6_init(void) NULL); if (ret) goto out_unregister_subsys; + + __fib6_flush_trees = fib6_flush_trees; out: return ret; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index f23fbd28a501..bafde82324c5 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -314,7 +314,6 @@ static inline struct rt6_info *ip6_dst_alloc(struct net *net, memset(dst + 1, 0, sizeof(*rt) - sizeof(*dst)); rt6_init_peer(rt, table ? &table->tb6_peers : net->ipv6.peers); - rt->rt6i_genid = rt_genid_ipv6(net); INIT_LIST_HEAD(&rt->rt6i_siblings); } return rt; @@ -1098,9 +1097,6 @@ static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie) * DST_OBSOLETE_FORCE_CHK which forces validation calls down * into this function always. */ - if (rt->rt6i_genid != rt_genid_ipv6(dev_net(rt->dst.dev))) - return NULL; - if (!rt->rt6i_node || (rt->rt6i_node->fn_sernum != cookie)) return NULL; -- cgit v1.2.3