From 1306d603fcf1f6682f8575d1ff23631a24184b21 Mon Sep 17 00:00:00 2001 From: KOSAKI Motohiro Date: Fri, 8 Jan 2010 14:42:56 -0800 Subject: proc: partially revert "procfs: provide stack information for threads" Commit d899bf7b (procfs: provide stack information for threads) introduced to show stack information in /proc/{pid}/status. But it cause large performance regression. Unfortunately /proc/{pid}/status is used ps command too and ps is one of most important component. Because both to take mmap_sem and page table walk are heavily operation. If many process run, the ps performance is, [before d899bf7b] % perf stat ps >/dev/null Performance counter stats for 'ps': 4090.435806 task-clock-msecs # 0.032 CPUs 229 context-switches # 0.000 M/sec 0 CPU-migrations # 0.000 M/sec 234 page-faults # 0.000 M/sec 8587565207 cycles # 2099.425 M/sec 9866662403 instructions # 1.149 IPC 3789415411 cache-references # 926.409 M/sec 30419509 cache-misses # 7.437 M/sec 128.859521955 seconds time elapsed [after d899bf7b] % perf stat ps > /dev/null Performance counter stats for 'ps': 4305.081146 task-clock-msecs # 0.028 CPUs 480 context-switches # 0.000 M/sec 2 CPU-migrations # 0.000 M/sec 237 page-faults # 0.000 M/sec 9021211334 cycles # 2095.480 M/sec 10605887536 instructions # 1.176 IPC 3612650999 cache-references # 839.160 M/sec 23917502 cache-misses # 5.556 M/sec 152.277819582 seconds time elapsed Thus, this patch revert it. Fortunately /proc/{pid}/task/{tid}/smaps provide almost same information. we can use it. Commit d899bf7b introduced two features: 1) Add the annotattion of [thread stack: xxxx] mark to /proc/{pid}/task/{tid}/maps. 2) Add StackUsage field to /proc/{pid}/status. I only revert (2), because I haven't seen (1) cause regression. Signed-off-by: KOSAKI Motohiro Cc: Stefani Seibold Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Alexey Dobriyan Cc: "Eric W. Biederman" Cc: Randy Dunlap Cc: Andrew Morton Cc: Andi Kleen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/proc/array.c | 89 --------------------------------------------------------- 1 file changed, 89 deletions(-) (limited to 'fs/proc/array.c') diff --git a/fs/proc/array.c b/fs/proc/array.c index f560325c444f..13b5d0708175 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -327,94 +327,6 @@ static inline void task_context_switch_counts(struct seq_file *m, p->nivcsw); } -#ifdef CONFIG_MMU - -struct stack_stats { - struct vm_area_struct *vma; - unsigned long startpage; - unsigned long usage; -}; - -static int stack_usage_pte_range(pmd_t *pmd, unsigned long addr, - unsigned long end, struct mm_walk *walk) -{ - struct stack_stats *ss = walk->private; - struct vm_area_struct *vma = ss->vma; - pte_t *pte, ptent; - spinlock_t *ptl; - int ret = 0; - - pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl); - for (; addr != end; pte++, addr += PAGE_SIZE) { - ptent = *pte; - -#ifdef CONFIG_STACK_GROWSUP - if (pte_present(ptent) || is_swap_pte(ptent)) - ss->usage = addr - ss->startpage + PAGE_SIZE; -#else - if (pte_present(ptent) || is_swap_pte(ptent)) { - ss->usage = ss->startpage - addr + PAGE_SIZE; - pte++; - ret = 1; - break; - } -#endif - } - pte_unmap_unlock(pte - 1, ptl); - cond_resched(); - return ret; -} - -static inline unsigned long get_stack_usage_in_bytes(struct vm_area_struct *vma, - struct task_struct *task) -{ - struct stack_stats ss; - struct mm_walk stack_walk = { - .pmd_entry = stack_usage_pte_range, - .mm = vma->vm_mm, - .private = &ss, - }; - - if (!vma->vm_mm || is_vm_hugetlb_page(vma)) - return 0; - - ss.vma = vma; - ss.startpage = task->stack_start & PAGE_MASK; - ss.usage = 0; - -#ifdef CONFIG_STACK_GROWSUP - walk_page_range(KSTK_ESP(task) & PAGE_MASK, vma->vm_end, - &stack_walk); -#else - walk_page_range(vma->vm_start, (KSTK_ESP(task) & PAGE_MASK) + PAGE_SIZE, - &stack_walk); -#endif - return ss.usage; -} - -static inline void task_show_stack_usage(struct seq_file *m, - struct task_struct *task) -{ - struct vm_area_struct *vma; - struct mm_struct *mm = get_task_mm(task); - - if (mm) { - down_read(&mm->mmap_sem); - vma = find_vma(mm, task->stack_start); - if (vma) - seq_printf(m, "Stack usage:\t%lu kB\n", - get_stack_usage_in_bytes(vma, task) >> 10); - - up_read(&mm->mmap_sem); - mmput(mm); - } -} -#else -static void task_show_stack_usage(struct seq_file *m, struct task_struct *task) -{ -} -#endif /* CONFIG_MMU */ - static void task_cpus_allowed(struct seq_file *m, struct task_struct *task) { seq_printf(m, "Cpus_allowed:\t"); @@ -445,7 +357,6 @@ int proc_pid_status(struct seq_file *m, struct pid_namespace *ns, task_show_regs(m, task); #endif task_context_switch_counts(m, task); - task_show_stack_usage(m, task); return 0; } -- cgit v1.2.3 From 7dc52157982ab771f40e3c0b7dc55b954c3c2d19 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 22 Feb 2010 17:04:52 -0800 Subject: vfs: Apply lockdep-based checking to rcu_dereference() uses Add lockdep-ified RCU primitives to alloc_fd(), files_fdtable() and fcheck_files(). Cc: Alexander Viro Signed-off-by: Paul E. McKenney Cc: laijs@cn.fujitsu.com Cc: dipankar@in.ibm.com Cc: mathieu.desnoyers@polymtl.ca Cc: josh@joshtriplett.org Cc: dvhltc@us.ibm.com Cc: niv@us.ibm.com Cc: peterz@infradead.org Cc: rostedt@goodmis.org Cc: Valdis.Kletnieks@vt.edu Cc: dhowells@redhat.com Cc: Alexander Viro LKML-Reference: <1266887105-1528-8-git-send-email-paulmck@linux.vnet.ibm.com> Signed-off-by: Ingo Molnar --- fs/proc/array.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'fs/proc/array.c') diff --git a/fs/proc/array.c b/fs/proc/array.c index 13b5d0708175..18e20feee251 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -270,7 +270,9 @@ static inline void task_sig(struct seq_file *m, struct task_struct *p) blocked = p->blocked; collect_sigign_sigcatch(p, &ignored, &caught); num_threads = atomic_read(&p->signal->count); + rcu_read_lock(); /* FIXME: is this correct? */ qsize = atomic_read(&__task_cred(p)->user->sigpending); + rcu_read_unlock(); qlim = p->signal->rlim[RLIMIT_SIGPENDING].rlim_cur; unlock_task_sighand(p, &flags); } -- cgit v1.2.3 From d554ed895dc8f293cc712c71f14b101ace82579a Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Fri, 5 Mar 2010 13:42:42 -0800 Subject: fs: use rlimit helpers Make sure compiler won't do weird things with limits. E.g. fetching them twice may return 2 different values after writable limits are implemented. I.e. either use rlimit helpers added in commit 3e10e716abf3 ("resource: add helpers for fetching rlimits") or ACCESS_ONCE if not applicable. Signed-off-by: Jiri Slaby Cc: Alexander Viro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/proc/array.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'fs/proc/array.c') diff --git a/fs/proc/array.c b/fs/proc/array.c index 18e20feee251..aa8637b81028 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -273,7 +273,7 @@ static inline void task_sig(struct seq_file *m, struct task_struct *p) rcu_read_lock(); /* FIXME: is this correct? */ qsize = atomic_read(&__task_cred(p)->user->sigpending); rcu_read_unlock(); - qlim = p->signal->rlim[RLIMIT_SIGPENDING].rlim_cur; + qlim = task_rlimit(p, RLIMIT_SIGPENDING); unlock_task_sighand(p, &flags); } @@ -420,7 +420,7 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, cutime = sig->cutime; cstime = sig->cstime; cgtime = sig->cgtime; - rsslim = sig->rlim[RLIMIT_RSS].rlim_cur; + rsslim = ACCESS_ONCE(sig->rlim[RLIMIT_RSS].rlim_cur); /* add up live thread stats at the group level */ if (whole) { -- cgit v1.2.3 From 5a0e3ad6af8660be21ca98a971cd00f331318c05 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 24 Mar 2010 17:04:11 +0900 Subject: include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo Guess-its-ok-by: Christoph Lameter Cc: Ingo Molnar Cc: Lee Schermerhorn --- fs/proc/array.c | 1 - 1 file changed, 1 deletion(-) (limited to 'fs/proc/array.c') diff --git a/fs/proc/array.c b/fs/proc/array.c index aa8637b81028..e51f2ec2c5e5 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -68,7 +68,6 @@ #include #include #include -#include #include #include #include -- cgit v1.2.3