From 92d23f703c608fcb2c8edd74a3fd0f4031e18606 Mon Sep 17 00:00:00 2001 From: Ron Date: Fri, 8 May 2009 22:54:49 +0930 Subject: sched: Fix fallback sched_clock()'s offset when using jiffies Account for the initial offset to the jiffy count. [ Impact: fix printk timestamps on architectures using fallback sched_clock() ] Signed-off-by: Ron Lee Cc: Andrew Morton Signed-off-by: Ingo Molnar --- kernel/sched_clock.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/sched_clock.c b/kernel/sched_clock.c index 819f17ac796..e1d16c9a768 100644 --- a/kernel/sched_clock.c +++ b/kernel/sched_clock.c @@ -38,7 +38,8 @@ */ unsigned long long __attribute__((weak)) sched_clock(void) { - return (unsigned long long)jiffies * (NSEC_PER_SEC / HZ); + return (unsigned long long)(jiffies - INITIAL_JIFFIES) + * (NSEC_PER_SEC / HZ); } static __read_mostly int sched_clock_running; -- cgit v1.2.3 From d80c19df5fcceb8c741e96f09f275c2da719efef Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Tue, 12 May 2009 16:29:13 +0200 Subject: lockdep: increase MAX_LOCKDEP_ENTRIES and MAX_LOCKDEP_CHAINS Now that lockdep coverage has increased it has become easier to run out of entries: [ 21.401387] BUG: MAX_LOCKDEP_ENTRIES too low! [ 21.402007] turning off the locking correctness validator. [ 21.402007] Pid: 1555, comm: S99local Not tainted 2.6.30-rc5-tip #2 [ 21.402007] Call Trace: [ 21.402007] [] add_lock_to_list+0x53/0xba [ 21.402007] [] ? lookup_mnt+0x19/0x53 [ 21.402007] [] check_prev_add+0x14b/0x1c7 [ 21.402007] [] validate_chain+0x474/0x52a [ 21.402007] [] __lock_acquire+0x342/0x3c7 [ 21.402007] [] lock_acquire+0xc1/0xe5 [ 21.402007] [] ? lookup_mnt+0x19/0x53 [ 21.402007] [] _spin_lock+0x31/0x66 Double the size - as we've done in the past. [ Impact: allow lockdep to cover more locks ] Acked-by: Peter Zijlstra LKML-Reference: Signed-off-by: Ingo Molnar --- kernel/lockdep_internals.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/lockdep_internals.h b/kernel/lockdep_internals.h index a2cc7e9a6e8..699a2ac3a0d 100644 --- a/kernel/lockdep_internals.h +++ b/kernel/lockdep_internals.h @@ -54,9 +54,9 @@ enum { * table (if it's not there yet), and we check it for lock order * conflicts and deadlocks. */ -#define MAX_LOCKDEP_ENTRIES 8192UL +#define MAX_LOCKDEP_ENTRIES 16384UL -#define MAX_LOCKDEP_CHAINS_BITS 14 +#define MAX_LOCKDEP_CHAINS_BITS 15 #define MAX_LOCKDEP_CHAINS (1UL << MAX_LOCKDEP_CHAINS_BITS) #define MAX_LOCKDEP_CHAIN_HLOCKS (MAX_LOCKDEP_CHAINS*5) -- cgit v1.2.3 From 88fc86c283d9c3854e67e4155808027bc2519eb6 Mon Sep 17 00:00:00 2001 From: GeunSik Lim Date: Thu, 14 May 2009 17:23:38 +0900 Subject: tracing: Append prompt in /debug/tracing/README file append prompt in /debug/tracing/README file. This is trivial issue. Fix typo Mini Howto file(README) for ftrace. [ Impact: cleanup ] Signed-off-by: GeunSik Lim Acked-by: Steven Rostedt Cc: williams LKML-Reference: <1242289418.31161.45.camel@centos51> Signed-off-by: Ingo Molnar --- kernel/trace/trace.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index a884c09006c..cda81ec58d9 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -2380,7 +2380,7 @@ static const char readme_msg[] = "# echo print-parent > /debug/tracing/trace_options\n" "# echo 1 > /debug/tracing/tracing_enabled\n" "# cat /debug/tracing/trace > /tmp/trace.txt\n" - "echo 0 > /debug/tracing/tracing_enabled\n" + "# echo 0 > /debug/tracing/tracing_enabled\n" ; static ssize_t -- cgit v1.2.3 From 64d1304a64477629cb16b75491a77bafe6f86963 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 18 May 2009 21:20:10 +0200 Subject: futex: setup writeable mapping for futex ops which modify user space data The futex code installs a read only mapping via get_user_pages_fast() even if the futex op function has to modify user space data. The eventual fault was fixed up by futex_handle_fault() which walked the VMA with mmap_sem held. After the cleanup patches which removed the mmap_sem dependency of the futex code commit 4dc5b7a36a49eff97050894cf1b3a9a02523717 (futex: clean up fault logic) removed the private VMA walk logic from the futex code. This change results in a stale RO mapping which is not fixed up. Instead of reintroducing the previous fault logic we set up the mapping in get_user_pages_fast() read/write for all operations which modify user space data. Also handle private futexes in the same way and make the current unconditional access_ok(VERIFY_WRITE) depend on the futex op. Reported-by: Andreas Schwab Signed-off-by: Thomas Gleixner CC: stable@kernel.org --- kernel/futex.c | 24 +++++++++++++----------- 1 file changed, 13 insertions(+), 11 deletions(-) (limited to 'kernel') diff --git a/kernel/futex.c b/kernel/futex.c index eef8cd26b5e..d546b2d53a6 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -193,6 +193,7 @@ static void drop_futex_key_refs(union futex_key *key) * @uaddr: virtual address of the futex * @fshared: 0 for a PROCESS_PRIVATE futex, 1 for PROCESS_SHARED * @key: address where result is stored. + * @rw: mapping needs to be read/write (values: VERIFY_READ, VERIFY_WRITE) * * Returns a negative error code or 0 * The key words are stored in *key on success. @@ -203,7 +204,8 @@ static void drop_futex_key_refs(union futex_key *key) * * lock_page() might sleep, the caller should not hold a spinlock. */ -static int get_futex_key(u32 __user *uaddr, int fshared, union futex_key *key) +static int +get_futex_key(u32 __user *uaddr, int fshared, union futex_key *key, int rw) { unsigned long address = (unsigned long)uaddr; struct mm_struct *mm = current->mm; @@ -226,7 +228,7 @@ static int get_futex_key(u32 __user *uaddr, int fshared, union futex_key *key) * but access_ok() should be faster than find_vma() */ if (!fshared) { - if (unlikely(!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))) + if (unlikely(!access_ok(rw, uaddr, sizeof(u32)))) return -EFAULT; key->private.mm = mm; key->private.address = address; @@ -235,7 +237,7 @@ static int get_futex_key(u32 __user *uaddr, int fshared, union futex_key *key) } again: - err = get_user_pages_fast(address, 1, 0, &page); + err = get_user_pages_fast(address, 1, rw == VERIFY_WRITE, &page); if (err < 0) return err; @@ -677,7 +679,7 @@ static int futex_wake(u32 __user *uaddr, int fshared, int nr_wake, u32 bitset) if (!bitset) return -EINVAL; - ret = get_futex_key(uaddr, fshared, &key); + ret = get_futex_key(uaddr, fshared, &key, VERIFY_READ); if (unlikely(ret != 0)) goto out; @@ -723,10 +725,10 @@ futex_wake_op(u32 __user *uaddr1, int fshared, u32 __user *uaddr2, int ret, op_ret; retry: - ret = get_futex_key(uaddr1, fshared, &key1); + ret = get_futex_key(uaddr1, fshared, &key1, VERIFY_READ); if (unlikely(ret != 0)) goto out; - ret = get_futex_key(uaddr2, fshared, &key2); + ret = get_futex_key(uaddr2, fshared, &key2, VERIFY_WRITE); if (unlikely(ret != 0)) goto out_put_key1; @@ -814,10 +816,10 @@ static int futex_requeue(u32 __user *uaddr1, int fshared, u32 __user *uaddr2, int ret, drop_count = 0; retry: - ret = get_futex_key(uaddr1, fshared, &key1); + ret = get_futex_key(uaddr1, fshared, &key1, VERIFY_READ); if (unlikely(ret != 0)) goto out; - ret = get_futex_key(uaddr2, fshared, &key2); + ret = get_futex_key(uaddr2, fshared, &key2, VERIFY_READ); if (unlikely(ret != 0)) goto out_put_key1; @@ -1140,7 +1142,7 @@ static int futex_wait(u32 __user *uaddr, int fshared, q.bitset = bitset; retry: q.key = FUTEX_KEY_INIT; - ret = get_futex_key(uaddr, fshared, &q.key); + ret = get_futex_key(uaddr, fshared, &q.key, VERIFY_READ); if (unlikely(ret != 0)) goto out; @@ -1330,7 +1332,7 @@ static int futex_lock_pi(u32 __user *uaddr, int fshared, q.pi_state = NULL; retry: q.key = FUTEX_KEY_INIT; - ret = get_futex_key(uaddr, fshared, &q.key); + ret = get_futex_key(uaddr, fshared, &q.key, VERIFY_WRITE); if (unlikely(ret != 0)) goto out; @@ -1594,7 +1596,7 @@ retry: if ((uval & FUTEX_TID_MASK) != task_pid_vnr(current)) return -EPERM; - ret = get_futex_key(uaddr, fshared, &key); + ret = get_futex_key(uaddr, fshared, &key, VERIFY_WRITE); if (unlikely(ret != 0)) goto out; -- cgit v1.2.3 From 32bdfac5462d777f35b00838893c4f87baf23efe Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Sun, 24 May 2009 21:15:07 +0200 Subject: PM: Do not hold dpm_list_mtx while disabling/enabling nonboot CPUs We shouldn't hold dpm_list_mtx while executing [disable|enable]_nonboot_cpus(), because theoretically this may lead to a deadlock as shown by the following example (provided by Johannes Berg): CPU 3 CPU 2 CPU 1 suspend/hibernate something: rtnl_lock() device_pm_lock() -> mutex_lock(&dpm_list_mtx) mutex_lock(&dpm_list_mtx) linkwatch_work -> rtnl_lock() disable_nonboot_cpus() -> flush CPU 3 workqueue Fortunately, device drivers are supposed to stop any activities that might lead to the registration of new device objects way before disable_nonboot_cpus() is called, so it shouldn't be necessary to hold dpm_list_mtx over the entire late part of device suspend and early part of device resume. Thus, during the late suspend and the early resume of devices acquire dpm_list_mtx only when dpm_list is going to be traversed and release it right after that. This patch is reported to fix the regressions tracked as http://bugzilla.kernel.org/show_bug.cgi?id=13245. Signed-off-by: Rafael J. Wysocki Acked-by: Alan Stern Reported-by: Miles Lane Tested-by: Ming Lei --- kernel/kexec.c | 2 -- kernel/power/disk.c | 21 +++------------------ kernel/power/main.c | 7 +------ 3 files changed, 4 insertions(+), 26 deletions(-) (limited to 'kernel') diff --git a/kernel/kexec.c b/kernel/kexec.c index 5a758c6e495..e4983770913 100644 --- a/kernel/kexec.c +++ b/kernel/kexec.c @@ -1451,7 +1451,6 @@ int kernel_kexec(void) error = device_suspend(PMSG_FREEZE); if (error) goto Resume_console; - device_pm_lock(); /* At this point, device_suspend() has been called, * but *not* device_power_down(). We *must* * device_power_down() now. Otherwise, drivers for @@ -1489,7 +1488,6 @@ int kernel_kexec(void) enable_nonboot_cpus(); device_power_up(PMSG_RESTORE); Resume_devices: - device_pm_unlock(); device_resume(PMSG_RESTORE); Resume_console: resume_console(); diff --git a/kernel/power/disk.c b/kernel/power/disk.c index b0dc9e7a0d1..5cb080e7eeb 100644 --- a/kernel/power/disk.c +++ b/kernel/power/disk.c @@ -215,8 +215,6 @@ static int create_image(int platform_mode) if (error) return error; - device_pm_lock(); - /* At this point, device_suspend() has been called, but *not* * device_power_down(). We *must* call device_power_down() now. * Otherwise, drivers for some devices (e.g. interrupt controllers) @@ -227,7 +225,7 @@ static int create_image(int platform_mode) if (error) { printk(KERN_ERR "PM: Some devices failed to power down, " "aborting hibernation\n"); - goto Unlock; + return error; } error = platform_pre_snapshot(platform_mode); @@ -280,9 +278,6 @@ static int create_image(int platform_mode) device_power_up(in_suspend ? (error ? PMSG_RECOVER : PMSG_THAW) : PMSG_RESTORE); - Unlock: - device_pm_unlock(); - return error; } @@ -344,13 +339,11 @@ static int resume_target_kernel(bool platform_mode) { int error; - device_pm_lock(); - error = device_power_down(PMSG_QUIESCE); if (error) { printk(KERN_ERR "PM: Some devices failed to power down, " "aborting resume\n"); - goto Unlock; + return error; } error = platform_pre_restore(platform_mode); @@ -403,9 +396,6 @@ static int resume_target_kernel(bool platform_mode) device_power_up(PMSG_RECOVER); - Unlock: - device_pm_unlock(); - return error; } @@ -464,11 +454,9 @@ int hibernation_platform_enter(void) goto Resume_devices; } - device_pm_lock(); - error = device_power_down(PMSG_HIBERNATE); if (error) - goto Unlock; + goto Resume_devices; error = hibernation_ops->prepare(); if (error) @@ -493,9 +481,6 @@ int hibernation_platform_enter(void) device_power_up(PMSG_RESTORE); - Unlock: - device_pm_unlock(); - Resume_devices: entering_platform_hibernation = false; device_resume(PMSG_RESTORE); diff --git a/kernel/power/main.c b/kernel/power/main.c index f99ed6a75ea..868028280d1 100644 --- a/kernel/power/main.c +++ b/kernel/power/main.c @@ -289,12 +289,10 @@ static int suspend_enter(suspend_state_t state) { int error; - device_pm_lock(); - if (suspend_ops->prepare) { error = suspend_ops->prepare(); if (error) - goto Done; + return error; } error = device_power_down(PMSG_SUSPEND); @@ -343,9 +341,6 @@ static int suspend_enter(suspend_state_t state) if (suspend_ops->finish) suspend_ops->finish(); - Done: - device_pm_unlock(); - return error; } -- cgit v1.2.3 From d5a877e8dd409d8c702986d06485c374b705d340 Mon Sep 17 00:00:00 2001 From: James Bottomley Date: Sun, 24 May 2009 13:03:43 -0700 Subject: async: make sure independent async domains can't accidentally entangle The problem occurs when async_synchronize_full_domain() is called when the async_pending list is not empty. This will cause lowest_running() to return the cookie of the first entry on the async_pending list, which might be nothing at all to do with the domain being asked for and thus cause the domain synchronization to wait for an unrelated domain. This can cause a deadlock if domain synchronization is used from one domain to wait for another. Fix by running over the async_pending list to see if any pending items actually belong to our domain (and return their cookies if they do). Signed-off-by: James Bottomley Signed-off-by: Arjan van de Ven Signed-off-by: Linus Torvalds --- kernel/async.c | 20 ++++++++++++-------- 1 file changed, 12 insertions(+), 8 deletions(-) (limited to 'kernel') diff --git a/kernel/async.c b/kernel/async.c index 968ef9457d4..50540301ed0 100644 --- a/kernel/async.c +++ b/kernel/async.c @@ -92,19 +92,23 @@ extern int initcall_debug; static async_cookie_t __lowest_in_progress(struct list_head *running) { struct async_entry *entry; + async_cookie_t ret = next_cookie; /* begin with "infinity" value */ + if (!list_empty(running)) { entry = list_first_entry(running, struct async_entry, list); - return entry->cookie; - } else if (!list_empty(&async_pending)) { - entry = list_first_entry(&async_pending, - struct async_entry, list); - return entry->cookie; - } else { - /* nothing in progress... next_cookie is "infinity" */ - return next_cookie; + ret = entry->cookie; } + if (!list_empty(&async_pending)) { + list_for_each_entry(entry, &async_pending, list) + if (entry->running == running) { + ret = entry->cookie; + break; + } + } + + return ret; } static async_cookie_t lowest_in_progress(struct list_head *running) -- cgit v1.2.3 From ab2b7ebaad16226c9a5e85c5f384d19fa58a7459 Mon Sep 17 00:00:00 2001 From: Tetsuo Handa Date: Tue, 26 May 2009 09:11:03 +0100 Subject: kmod: Release sub_info on cred allocation failure. call_usermodehelper_setup() forgot to kfree(sub_info) when prepare_usermodehelper_creds() failed. Signed-off-by: Tetsuo Handa Signed-off-by: David Howells Signed-off-by: Linus Torvalds --- kernel/kmod.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/kmod.c b/kernel/kmod.c index b750675251e..7e95bedb2bf 100644 --- a/kernel/kmod.c +++ b/kernel/kmod.c @@ -370,8 +370,10 @@ struct subprocess_info *call_usermodehelper_setup(char *path, char **argv, sub_info->argv = argv; sub_info->envp = envp; sub_info->cred = prepare_usermodehelper_creds(); - if (!sub_info->cred) + if (!sub_info->cred) { + kfree(sub_info); return NULL; + } out: return sub_info; -- cgit v1.2.3