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 v1.2.3-70-g09d2 From 6f5bbff9a1b7d6864a495763448a363bbfa96324 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 6 May 2009 01:34:22 -0400 Subject: Convert obvious places to deactivate_locked_super() Signed-off-by: Al Viro --- drivers/mtd/mtdsuper.c | 3 +-- fs/9p/vfs_super.c | 5 +---- fs/afs/super.c | 3 +-- fs/btrfs/super.c | 12 ++++-------- fs/cifs/cifsfs.c | 3 +-- fs/devpts/inode.c | 5 ++--- fs/ecryptfs/main.c | 5 ++--- fs/libfs.c | 3 +-- fs/nfs/super.c | 15 +++++---------- fs/proc/root.c | 3 +-- fs/ubifs/super.c | 3 +-- kernel/cgroup.c | 3 +-- 12 files changed, 21 insertions(+), 42 deletions(-) (limited to 'kernel') diff --git a/drivers/mtd/mtdsuper.c b/drivers/mtd/mtdsuper.c index 92285d0089c..af8b42e0a55 100644 --- a/drivers/mtd/mtdsuper.c +++ b/drivers/mtd/mtdsuper.c @@ -74,8 +74,7 @@ static int get_sb_mtd_aux(struct file_system_type *fs_type, int flags, ret = fill_super(sb, data, flags & MS_SILENT ? 1 : 0); if (ret < 0) { - up_write(&sb->s_umount); - deactivate_super(sb); + deactivate_locked_super(sb); return ret; } diff --git a/fs/9p/vfs_super.c b/fs/9p/vfs_super.c index 7d23214e559..0d29a57c63e 100644 --- a/fs/9p/vfs_super.c +++ b/fs/9p/vfs_super.c @@ -174,10 +174,7 @@ P9_DPRINTK(P9_DEBUG_VFS, " simple set mount, return 0\n"); return 0; release_sb: - if (sb) { - up_write(&sb->s_umount); - deactivate_super(sb); - } + deactivate_locked_super(sb); free_stat: kfree(st); diff --git a/fs/afs/super.c b/fs/afs/super.c index aee239a048c..2753f16dd31 100644 --- a/fs/afs/super.c +++ b/fs/afs/super.c @@ -405,8 +405,7 @@ static int afs_get_sb(struct file_system_type *fs_type, sb->s_flags = flags; ret = afs_fill_super(sb, ¶ms); if (ret < 0) { - up_write(&sb->s_umount); - deactivate_super(sb); + deactivate_locked_super(sb); goto error; } sb->s_options = new_opts; diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 3536bdb2d7c..6dfae5b28f5 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -502,8 +502,7 @@ static int btrfs_get_sb(struct file_system_type *fs_type, int flags, if (s->s_root) { if ((flags ^ s->s_flags) & MS_RDONLY) { - up_write(&s->s_umount); - deactivate_super(s); + deactivate_locked_super(s); error = -EBUSY; goto error_close_devices; } @@ -517,8 +516,7 @@ static int btrfs_get_sb(struct file_system_type *fs_type, int flags, error = btrfs_fill_super(s, fs_devices, data, flags & MS_SILENT ? 1 : 0); if (error) { - up_write(&s->s_umount); - deactivate_super(s); + deactivate_locked_super(s); goto error_free_subvol_name; } @@ -535,15 +533,13 @@ static int btrfs_get_sb(struct file_system_type *fs_type, int flags, mutex_unlock(&s->s_root->d_inode->i_mutex); if (IS_ERR(root)) { - up_write(&s->s_umount); - deactivate_super(s); + deactivate_locked_super(s); error = PTR_ERR(root); goto error_free_subvol_name; } if (!root->d_inode) { dput(root); - up_write(&s->s_umount); - deactivate_super(s); + deactivate_locked_super(s); error = -ENXIO; goto error_free_subvol_name; } diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index 355e0efec0c..5e6d35804d7 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -602,8 +602,7 @@ cifs_get_sb(struct file_system_type *fs_type, rc = cifs_read_super(sb, data, dev_name, flags & MS_SILENT ? 1 : 0); if (rc) { - up_write(&sb->s_umount); - deactivate_super(sb); + deactivate_locked_super(sb); return rc; } sb->s_flags |= MS_ACTIVE; diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c index 63a4a59e414..21165cf934f 100644 --- a/fs/devpts/inode.c +++ b/fs/devpts/inode.c @@ -389,11 +389,10 @@ static int devpts_get_sb(struct file_system_type *fs_type, return 0; out_dput: - dput(s->s_root); + dput(s->s_root); /* undo dget() in simple_set_mnt() */ out_undo_sget: - up_write(&s->s_umount); - deactivate_super(s); + deactivate_locked_super(s); return error; } diff --git a/fs/ecryptfs/main.c b/fs/ecryptfs/main.c index ccabd5faa04..9f0aa9883c2 100644 --- a/fs/ecryptfs/main.c +++ b/fs/ecryptfs/main.c @@ -614,9 +614,8 @@ static int ecryptfs_get_sb(struct file_system_type *fs_type, int flags, } goto out; out_abort: - dput(sb->s_root); - up_write(&sb->s_umount); - deactivate_super(sb); + dput(sb->s_root); /* aka mnt->mnt_root, as set by get_sb_nodev() */ + deactivate_locked_super(sb); out: return rc; } diff --git a/fs/libfs.c b/fs/libfs.c index cd223190c4e..80046ddf506 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -246,8 +246,7 @@ int get_sb_pseudo(struct file_system_type *fs_type, char *name, return 0; Enomem: - up_write(&s->s_umount); - deactivate_super(s); + deactivate_locked_super(s); return -ENOMEM; } diff --git a/fs/nfs/super.c b/fs/nfs/super.c index 1679a164c8c..d2d67781c57 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -2111,8 +2111,7 @@ out_err_nosb: error_splat_root: dput(mntroot); error_splat_super: - up_write(&s->s_umount); - deactivate_super(s); + deactivate_locked_super(s); goto out; } @@ -2208,8 +2207,7 @@ out_err_noserver: return error; error_splat_super: - up_write(&s->s_umount); - deactivate_super(s); + deactivate_locked_super(s); dprintk("<-- nfs_xdev_get_sb() = %d [splat]\n", error); return error; } @@ -2469,8 +2467,7 @@ out_free: error_splat_root: dput(mntroot); error_splat_super: - up_write(&s->s_umount); - deactivate_super(s); + deactivate_locked_super(s); goto out; } @@ -2564,8 +2561,7 @@ out_err_noserver: return error; error_splat_super: - up_write(&s->s_umount); - deactivate_super(s); + deactivate_locked_super(s); dprintk("<-- nfs4_xdev_get_sb() = %d [splat]\n", error); return error; } @@ -2649,8 +2645,7 @@ out_err_noserver: return error; error_splat_super: - up_write(&s->s_umount); - deactivate_super(s); + deactivate_locked_super(s); dprintk("<-- nfs4_referral_get_sb() = %d [splat]\n", error); return error; } diff --git a/fs/proc/root.c b/fs/proc/root.c index 1e15a2b176e..b080b791d9e 100644 --- a/fs/proc/root.c +++ b/fs/proc/root.c @@ -67,8 +67,7 @@ static int proc_get_sb(struct file_system_type *fs_type, sb->s_flags = flags; err = proc_fill_super(sb); if (err) { - up_write(&sb->s_umount); - deactivate_super(sb); + deactivate_locked_super(sb); return err; } diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c index faa44f90608..e9f7a754c4f 100644 --- a/fs/ubifs/super.c +++ b/fs/ubifs/super.c @@ -2055,8 +2055,7 @@ static int ubifs_get_sb(struct file_system_type *fs_type, int flags, return 0; out_deact: - up_write(&sb->s_umount); - deactivate_super(sb); + deactivate_locked_super(sb); out_close: ubi_close_volume(ubi); return err; diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 382109b5bae..a7267bfd376 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -1133,8 +1133,7 @@ static int cgroup_get_sb(struct file_system_type *fs_type, free_cg_links: free_cg_links(&tmp_cg_links); drop_new_super: - up_write(&sb->s_umount); - deactivate_super(sb); + deactivate_locked_super(sb); return ret; } -- cgit v1.2.3-70-g09d2 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 v1.2.3-70-g09d2 From cd17cbfda004fe5f406c01b318c6378d9895896f Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 15 May 2009 11:32:24 +0200 Subject: Revert "mm: add /proc controls for pdflush threads" This reverts commit fafd688e4c0c34da0f3de909881117d374e4c7af. Work is progressing to switch away from pdflush as the process backing for flushing out dirty data. So it seems pointless to add more knobs to control pdflush threads. The original author of the patch did not have any specific use cases for adding the knobs, so we can easily revert this before 2.6.30 to avoid having to maintain this API forever. Signed-off-by: Jens Axboe --- Documentation/sysctl/vm.txt | 28 ---------------------------- include/linux/writeback.h | 2 -- kernel/sysctl.c | 23 ----------------------- mm/pdflush.c | 31 ++++++++++++------------------- 4 files changed, 12 insertions(+), 72 deletions(-) (limited to 'kernel') diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt index b716d33912d..c302ddf629a 100644 --- a/Documentation/sysctl/vm.txt +++ b/Documentation/sysctl/vm.txt @@ -39,8 +39,6 @@ Currently, these files are in /proc/sys/vm: - nr_hugepages - nr_overcommit_hugepages - nr_pdflush_threads -- nr_pdflush_threads_min -- nr_pdflush_threads_max - nr_trim_pages (only if CONFIG_MMU=n) - numa_zonelist_order - oom_dump_tasks @@ -469,32 +467,6 @@ The default value is 0. ============================================================== -nr_pdflush_threads_min - -This value controls the minimum number of pdflush threads. - -At boot time, the kernel will create and maintain 'nr_pdflush_threads_min' -threads for the kernel's lifetime. - -The default value is 2. The minimum value you can specify is 1, and -the maximum value is the current setting of 'nr_pdflush_threads_max'. - -See 'nr_pdflush_threads_max' below for more information. - -============================================================== - -nr_pdflush_threads_max - -This value controls the maximum number of pdflush threads that can be -created. The pdflush algorithm will create a new pdflush thread (up to -this maximum) if no pdflush threads have been available for >= 1 second. - -The default value is 8. The minimum value you can specify is the -current value of 'nr_pdflush_threads_min' and the -maximum is 1000. - -============================================================== - overcommit_memory: This value contains a flag that enables memory overcommitment. diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 9c1ed1fb6dd..93445477f86 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -168,8 +168,6 @@ void writeback_set_ratelimit(void); /* pdflush.c */ extern int nr_pdflush_threads; /* Global so it can be exported to sysctl read-only. */ -extern int nr_pdflush_threads_max; /* Global so it can be exported to sysctl */ -extern int nr_pdflush_threads_min; /* Global so it can be exported to sysctl */ #endif /* WRITEBACK_H */ diff --git a/kernel/sysctl.c b/kernel/sysctl.c index ea78fa101ad..b2970d56fb7 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -101,7 +101,6 @@ static int __maybe_unused one = 1; static int __maybe_unused two = 2; static unsigned long one_ul = 1; static int one_hundred = 100; -static int one_thousand = 1000; /* this is needed for the proc_doulongvec_minmax of vm_dirty_bytes */ static unsigned long dirty_bytes_min = 2 * PAGE_SIZE; @@ -1033,28 +1032,6 @@ static struct ctl_table vm_table[] = { .mode = 0444 /* read-only*/, .proc_handler = &proc_dointvec, }, - { - .ctl_name = CTL_UNNUMBERED, - .procname = "nr_pdflush_threads_min", - .data = &nr_pdflush_threads_min, - .maxlen = sizeof nr_pdflush_threads_min, - .mode = 0644 /* read-write */, - .proc_handler = &proc_dointvec_minmax, - .strategy = &sysctl_intvec, - .extra1 = &one, - .extra2 = &nr_pdflush_threads_max, - }, - { - .ctl_name = CTL_UNNUMBERED, - .procname = "nr_pdflush_threads_max", - .data = &nr_pdflush_threads_max, - .maxlen = sizeof nr_pdflush_threads_max, - .mode = 0644 /* read-write */, - .proc_handler = &proc_dointvec_minmax, - .strategy = &sysctl_intvec, - .extra1 = &nr_pdflush_threads_min, - .extra2 = &one_thousand, - }, { .ctl_name = VM_SWAPPINESS, .procname = "swappiness", diff --git a/mm/pdflush.c b/mm/pdflush.c index f2caf96993f..235ac440c44 100644 --- a/mm/pdflush.c +++ b/mm/pdflush.c @@ -57,14 +57,6 @@ static DEFINE_SPINLOCK(pdflush_lock); */ int nr_pdflush_threads = 0; -/* - * The max/min number of pdflush threads. R/W by sysctl at - * /proc/sys/vm/nr_pdflush_threads_max/min - */ -int nr_pdflush_threads_max __read_mostly = MAX_PDFLUSH_THREADS; -int nr_pdflush_threads_min __read_mostly = MIN_PDFLUSH_THREADS; - - /* * The time at which the pdflush thread pool last went empty */ @@ -76,7 +68,7 @@ static unsigned long last_empty_jifs; * Thread pool management algorithm: * * - The minimum and maximum number of pdflush instances are bound - * by nr_pdflush_threads_min and nr_pdflush_threads_max. + * by MIN_PDFLUSH_THREADS and MAX_PDFLUSH_THREADS. * * - If there have been no idle pdflush instances for 1 second, create * a new one. @@ -142,13 +134,14 @@ static int __pdflush(struct pdflush_work *my_work) * To throttle creation, we reset last_empty_jifs. */ if (time_after(jiffies, last_empty_jifs + 1 * HZ)) { - if (list_empty(&pdflush_list) && - nr_pdflush_threads < nr_pdflush_threads_max) { - last_empty_jifs = jiffies; - nr_pdflush_threads++; - spin_unlock_irq(&pdflush_lock); - start_one_pdflush_thread(); - spin_lock_irq(&pdflush_lock); + if (list_empty(&pdflush_list)) { + if (nr_pdflush_threads < MAX_PDFLUSH_THREADS) { + last_empty_jifs = jiffies; + nr_pdflush_threads++; + spin_unlock_irq(&pdflush_lock); + start_one_pdflush_thread(); + spin_lock_irq(&pdflush_lock); + } } } @@ -160,7 +153,7 @@ static int __pdflush(struct pdflush_work *my_work) */ if (list_empty(&pdflush_list)) continue; - if (nr_pdflush_threads <= nr_pdflush_threads_min) + if (nr_pdflush_threads <= MIN_PDFLUSH_THREADS) continue; pdf = list_entry(pdflush_list.prev, struct pdflush_work, list); if (time_after(jiffies, pdf->when_i_went_to_sleep + 1 * HZ)) { @@ -266,9 +259,9 @@ static int __init pdflush_init(void) * Pre-set nr_pdflush_threads... If we fail to create, * the count will be decremented. */ - nr_pdflush_threads = nr_pdflush_threads_min; + nr_pdflush_threads = MIN_PDFLUSH_THREADS; - for (i = 0; i < nr_pdflush_threads_min; i++) + for (i = 0; i < MIN_PDFLUSH_THREADS; i++) start_one_pdflush_thread(); return 0; } -- cgit v1.2.3-70-g09d2 From 364b5b7b1d793a7f98be55b6b154716dcae78dfc Mon Sep 17 00:00:00 2001 From: Jason Wessel Date: Wed, 13 May 2009 21:56:59 -0500 Subject: sysrq, intel_fb: fix sysrq g collision Commit 79e539453b34e35f39299a899d263b0a1f1670bd introduced a regression where you cannot use sysrq 'g' to enter kgdb. The solution is to move the intel fb sysrq over to V for video instead of G for graphics. The SMP VOYAGER code to register for the sysrq-v is not anywhere to be found in the mainline kernel, so the comments in the code were cleaned up as well. This patch also cleans up the sysrq definitions for kgdb to make it generic for the kernel debugger, such that the sysrq 'g' can be used in the future to enter a gdbstub or another kernel debugger. Signed-off-by: Jason Wessel Acked-by: Jesse Barnes Acked-by: Randy Dunlap Signed-off-by: Andrew Morton --- drivers/char/sysrq.c | 4 ++-- drivers/gpu/drm/i915/intel_fb.c | 4 ++-- kernel/kgdb.c | 4 ++-- 3 files changed, 6 insertions(+), 6 deletions(-) (limited to 'kernel') diff --git a/drivers/char/sysrq.c b/drivers/char/sysrq.c index b0a6a3e5192..d6a807f4077 100644 --- a/drivers/char/sysrq.c +++ b/drivers/char/sysrq.c @@ -406,7 +406,7 @@ static struct sysrq_key_op *sysrq_key_table[36] = { &sysrq_showlocks_op, /* d */ &sysrq_term_op, /* e */ &sysrq_moom_op, /* f */ - /* g: May be registered by ppc for kgdb */ + /* g: May be registered for the kernel debugger */ NULL, /* g */ NULL, /* h - reserved for help */ &sysrq_kill_op, /* i */ @@ -431,7 +431,7 @@ static struct sysrq_key_op *sysrq_key_table[36] = { &sysrq_sync_op, /* s */ &sysrq_showstate_op, /* t */ &sysrq_mountro_op, /* u */ - /* v: May be registered at init time by SMP VOYAGER */ + /* v: May be registered for frame buffer console restore */ NULL, /* v */ &sysrq_showstate_blocked_op, /* w */ /* x: May be registered on ppc/powerpc for xmon */ diff --git a/drivers/gpu/drm/i915/intel_fb.c b/drivers/gpu/drm/i915/intel_fb.c index 3e094beecb9..e4652dcdd9b 100644 --- a/drivers/gpu/drm/i915/intel_fb.c +++ b/drivers/gpu/drm/i915/intel_fb.c @@ -864,7 +864,7 @@ static void intelfb_sysrq(int dummy1, struct tty_struct *dummy3) static struct sysrq_key_op sysrq_intelfb_restore_op = { .handler = intelfb_sysrq, - .help_msg = "force-fb(G)", + .help_msg = "force-fb(V)", .action_msg = "Restore framebuffer console", }; @@ -898,7 +898,7 @@ int intelfb_probe(struct drm_device *dev) ret = intelfb_single_fb_probe(dev); } - register_sysrq_key('g', &sysrq_intelfb_restore_op); + register_sysrq_key('v', &sysrq_intelfb_restore_op); return ret; } diff --git a/kernel/kgdb.c b/kernel/kgdb.c index e4dcfb2272a..9147a3190c9 100644 --- a/kernel/kgdb.c +++ b/kernel/kgdb.c @@ -1583,8 +1583,8 @@ static void sysrq_handle_gdb(int key, struct tty_struct *tty) static struct sysrq_key_op sysrq_gdb_op = { .handler = sysrq_handle_gdb, - .help_msg = "Gdb", - .action_msg = "GDB", + .help_msg = "debug(G)", + .action_msg = "DEBUG", }; #endif -- cgit v1.2.3-70-g09d2 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 v1.2.3-70-g09d2 From 4484079d517c2b6521621be0b1ea246ccc55c7d7 Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Fri, 15 May 2009 23:30:50 +0200 Subject: PM: check sysdev_suspend(PMSG_FREEZE) return value Check the return value of sysdev_suspend(). I think this was a typo. Without this change, the following "if" check is always false. I also changed the error message so it's distinguishable from the similar message a few lines above. Signed-off-by: Bjorn Helgaas Acked-by: Pavel Machek Signed-off-by: Rafael J. Wysocki --- kernel/power/disk.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/power/disk.c b/kernel/power/disk.c index e71ca9cd81b..b0dc9e7a0d1 100644 --- a/kernel/power/disk.c +++ b/kernel/power/disk.c @@ -241,9 +241,9 @@ static int create_image(int platform_mode) local_irq_disable(); - sysdev_suspend(PMSG_FREEZE); + error = sysdev_suspend(PMSG_FREEZE); if (error) { - printk(KERN_ERR "PM: Some devices failed to power down, " + printk(KERN_ERR "PM: Some system devices failed to power down, " "aborting hibernation\n"); goto Enable_irqs; } -- cgit v1.2.3-70-g09d2 From 0f6f49a8cd0163fdb1723ed29f01fc65177108dc Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sat, 16 May 2009 13:41:28 -0700 Subject: Fix caller information for warn_slowpath_null Ian Campbell noticed that since "Eliminate thousands of warnings with gcc 3.2 build" (commit 57adc4d2dbf968fdbe516359688094eef4d46581) all WARN_ON()'s currently appear to come from warn_slowpath_null(), eg: WARNING: at kernel/softirq.c:143 warn_slowpath_null+0x1c/0x20() because now that warn_slowpath_null() is in the call path, the __builtin_return_address(0) returns that, rather than the place that caused the warning. Fix this by splitting up the warn_slowpath_null/fmt cases differently, using a common helper function, and getting the return address in the right place. This also happens to avoid the unnecessary stack usage for the non-stdargs case, and just generally cleans things up. Make the function name printout use %pS while at it. Cc: Ian Campbell Cc: Jesper Nilsson Cc: Johannes Weiner Cc: Arjan van de Ven Cc: Andi Kleen Cc: Hugh Dickins Cc: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/panic.c | 35 ++++++++++++++++++++--------------- 1 file changed, 20 insertions(+), 15 deletions(-) (limited to 'kernel') diff --git a/kernel/panic.c b/kernel/panic.c index 874ecf1307a..984b3ecbd72 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -340,39 +340,44 @@ void oops_exit(void) } #ifdef WANT_WARN_ON_SLOWPATH -void warn_slowpath_fmt(const char *file, int line, const char *fmt, ...) -{ +struct slowpath_args { + const char *fmt; va_list args; - char function[KSYM_SYMBOL_LEN]; - unsigned long caller = (unsigned long)__builtin_return_address(0); - const char *board; +}; - sprint_symbol(function, caller); +static void warn_slowpath_common(const char *file, int line, void *caller, struct slowpath_args *args) +{ + const char *board; printk(KERN_WARNING "------------[ cut here ]------------\n"); - printk(KERN_WARNING "WARNING: at %s:%d %s()\n", file, - line, function); + printk(KERN_WARNING "WARNING: at %s:%d %pS()\n", file, line, caller); board = dmi_get_system_info(DMI_PRODUCT_NAME); if (board) printk(KERN_WARNING "Hardware name: %s\n", board); - if (*fmt) { - va_start(args, fmt); - vprintk(fmt, args); - va_end(args); - } + if (args) + vprintk(args->fmt, args->args); print_modules(); dump_stack(); print_oops_end_marker(); add_taint(TAINT_WARN); } + +void warn_slowpath_fmt(const char *file, int line, const char *fmt, ...) +{ + struct slowpath_args args; + + args.fmt = fmt; + va_start(args.args, fmt); + warn_slowpath_common(file, line, __builtin_return_address(0), &args); + va_end(args.args); +} EXPORT_SYMBOL(warn_slowpath_fmt); void warn_slowpath_null(const char *file, int line) { - static const char *empty = ""; - warn_slowpath_fmt(file, line, empty); + warn_slowpath_common(file, line, __builtin_return_address(0), NULL); } EXPORT_SYMBOL(warn_slowpath_null); #endif -- cgit v1.2.3-70-g09d2 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 v1.2.3-70-g09d2 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 --- drivers/base/power/main.c | 4 ++++ kernel/kexec.c | 2 -- kernel/power/disk.c | 21 +++------------------ kernel/power/main.c | 7 +------ 4 files changed, 8 insertions(+), 26 deletions(-) (limited to 'kernel') diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c index 69b4ddb7de3..3e4bc699bc0 100644 --- a/drivers/base/power/main.c +++ b/drivers/base/power/main.c @@ -357,6 +357,7 @@ static void dpm_power_up(pm_message_t state) { struct device *dev; + mutex_lock(&dpm_list_mtx); list_for_each_entry(dev, &dpm_list, power.entry) if (dev->power.status > DPM_OFF) { int error; @@ -366,6 +367,7 @@ static void dpm_power_up(pm_message_t state) if (error) pm_dev_err(dev, state, " early", error); } + mutex_unlock(&dpm_list_mtx); } /** @@ -614,6 +616,7 @@ int device_power_down(pm_message_t state) int error = 0; suspend_device_irqs(); + mutex_lock(&dpm_list_mtx); list_for_each_entry_reverse(dev, &dpm_list, power.entry) { error = suspend_device_noirq(dev, state); if (error) { @@ -622,6 +625,7 @@ int device_power_down(pm_message_t state) } dev->power.status = DPM_OFF_IRQ; } + mutex_unlock(&dpm_list_mtx); if (error) device_power_up(resume_event(state)); return error; 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 v1.2.3-70-g09d2 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 v1.2.3-70-g09d2 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 v1.2.3-70-g09d2