linux-stable/mm/debug.c

149 lines
3.9 KiB
C
Raw Normal View History

/*
* mm/debug.c
*
* mm/ specific debug routines.
*
*/
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/trace_events.h>
#include <linux/memcontrol.h>
mm, tracing: unify mm flags handling in tracepoints and printk In tracepoints, it's possible to print gfp flags in a human-friendly format through a macro show_gfp_flags(), which defines a translation array and passes is to __print_flags(). Since the following patch will introduce support for gfp flags printing in printk(), it would be nice to reuse the array. This is not straightforward, since __print_flags() can't simply reference an array defined in a .c file such as mm/debug.c - it has to be a macro to allow the macro magic to communicate the format to userspace tools such as trace-cmd. The solution is to create a macro __def_gfpflag_names which is used both in show_gfp_flags(), and to define the gfpflag_names[] array in mm/debug.c. On the other hand, mm/debug.c also defines translation tables for page flags and vma flags, and desire was expressed (but not implemented in this series) to use these also from tracepoints. Thus, this patch also renames the events/gfpflags.h file to events/mmflags.h and moves the table definitions there, using the same macro approach as for gfpflags. This allows translating all three kinds of mm-specific flags both in tracepoints and printk. Signed-off-by: Vlastimil Babka <vbabka@suse.cz> Reviewed-by: Michal Hocko <mhocko@suse.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Sasha Levin <sasha.levin@oracle.com> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Cc: Mel Gorman <mgorman@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-03-15 21:55:52 +00:00
#include <trace/events/mmflags.h>
mm, printk: introduce new format string for flags In mm we use several kinds of flags bitfields that are sometimes printed for debugging purposes, or exported to userspace via sysfs. To make them easier to interpret independently on kernel version and config, we want to dump also the symbolic flag names. So far this has been done with repeated calls to pr_cont(), which is unreliable on SMP, and not usable for e.g. sysfs export. To get a more reliable and universal solution, this patch extends printk() format string for pointers to handle the page flags (%pGp), gfp_flags (%pGg) and vma flags (%pGv). Existing users of dump_flag_names() are converted and simplified. It would be possible to pass flags by value instead of pointer, but the %p format string for pointers already has extensions for various kernel structures, so it's a good fit, and the extra indirection in a non-critical path is negligible. [linux@rasmusvillemoes.dk: lots of good implementation suggestions] Signed-off-by: Vlastimil Babka <vbabka@suse.cz> Acked-by: Michal Hocko <mhocko@suse.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Sasha Levin <sasha.levin@oracle.com> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Cc: Mel Gorman <mgorman@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-03-15 21:55:56 +00:00
#include "internal.h"
const struct trace_print_flags pageflag_names[] = {
__def_pageflag_names,
{0, NULL}
};
const struct trace_print_flags gfpflag_names[] = {
__def_gfpflag_names,
{0, NULL}
mm, tracing: unify mm flags handling in tracepoints and printk In tracepoints, it's possible to print gfp flags in a human-friendly format through a macro show_gfp_flags(), which defines a translation array and passes is to __print_flags(). Since the following patch will introduce support for gfp flags printing in printk(), it would be nice to reuse the array. This is not straightforward, since __print_flags() can't simply reference an array defined in a .c file such as mm/debug.c - it has to be a macro to allow the macro magic to communicate the format to userspace tools such as trace-cmd. The solution is to create a macro __def_gfpflag_names which is used both in show_gfp_flags(), and to define the gfpflag_names[] array in mm/debug.c. On the other hand, mm/debug.c also defines translation tables for page flags and vma flags, and desire was expressed (but not implemented in this series) to use these also from tracepoints. Thus, this patch also renames the events/gfpflags.h file to events/mmflags.h and moves the table definitions there, using the same macro approach as for gfpflags. This allows translating all three kinds of mm-specific flags both in tracepoints and printk. Signed-off-by: Vlastimil Babka <vbabka@suse.cz> Reviewed-by: Michal Hocko <mhocko@suse.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Sasha Levin <sasha.levin@oracle.com> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Cc: Mel Gorman <mgorman@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-03-15 21:55:52 +00:00
};
mm, printk: introduce new format string for flags In mm we use several kinds of flags bitfields that are sometimes printed for debugging purposes, or exported to userspace via sysfs. To make them easier to interpret independently on kernel version and config, we want to dump also the symbolic flag names. So far this has been done with repeated calls to pr_cont(), which is unreliable on SMP, and not usable for e.g. sysfs export. To get a more reliable and universal solution, this patch extends printk() format string for pointers to handle the page flags (%pGp), gfp_flags (%pGg) and vma flags (%pGv). Existing users of dump_flag_names() are converted and simplified. It would be possible to pass flags by value instead of pointer, but the %p format string for pointers already has extensions for various kernel structures, so it's a good fit, and the extra indirection in a non-critical path is negligible. [linux@rasmusvillemoes.dk: lots of good implementation suggestions] Signed-off-by: Vlastimil Babka <vbabka@suse.cz> Acked-by: Michal Hocko <mhocko@suse.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Sasha Levin <sasha.levin@oracle.com> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Cc: Mel Gorman <mgorman@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-03-15 21:55:56 +00:00
const struct trace_print_flags vmaflag_names[] = {
__def_vmaflag_names,
{0, NULL}
};
void dump_page_badflags(struct page *page, const char *reason,
unsigned long badflags)
{
mm: rework mapcount accounting to enable 4k mapping of THPs We're going to allow mapping of individual 4k pages of THP compound. It means we need to track mapcount on per small page basis. Straight-forward approach is to use ->_mapcount in all subpages to track how many time this subpage is mapped with PMDs or PTEs combined. But this is rather expensive: mapping or unmapping of a THP page with PMD would require HPAGE_PMD_NR atomic operations instead of single we have now. The idea is to store separately how many times the page was mapped as whole -- compound_mapcount. This frees up ->_mapcount in subpages to track PTE mapcount. We use the same approach as with compound page destructor and compound order to store compound_mapcount: use space in first tail page, ->mapping this time. Any time we map/unmap whole compound page (THP or hugetlb) -- we increment/decrement compound_mapcount. When we map part of compound page with PTE we operate on ->_mapcount of the subpage. page_mapcount() counts both: PTE and PMD mappings of the page. Basically, we have mapcount for a subpage spread over two counters. It makes tricky to detect when last mapcount for a page goes away. We introduced PageDoubleMap() for this. When we split THP PMD for the first time and there's other PMD mapping left we offset up ->_mapcount in all subpages by one and set PG_double_map on the compound page. These additional references go away with last compound_mapcount. This approach provides a way to detect when last mapcount goes away on per small page basis without introducing new overhead for most common cases. [akpm@linux-foundation.org: fix typo in comment] [mhocko@suse.com: ignore partial THP when moving task] Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Tested-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> Acked-by: Jerome Marchand <jmarchan@redhat.com> Cc: Sasha Levin <sasha.levin@oracle.com> Cc: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> Cc: Jerome Marchand <jmarchan@redhat.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Hugh Dickins <hughd@google.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Rik van Riel <riel@redhat.com> Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Cc: Steve Capper <steve.capper@linaro.org> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Christoph Lameter <cl@linux.com> Cc: David Rientjes <rientjes@google.com> Signed-off-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-01-16 00:53:42 +00:00
pr_emerg("page:%p count:%d mapcount:%d mapping:%p index:%#lx",
page, atomic_read(&page->_count), page_mapcount(page),
page->mapping, page->index);
mm: rework mapcount accounting to enable 4k mapping of THPs We're going to allow mapping of individual 4k pages of THP compound. It means we need to track mapcount on per small page basis. Straight-forward approach is to use ->_mapcount in all subpages to track how many time this subpage is mapped with PMDs or PTEs combined. But this is rather expensive: mapping or unmapping of a THP page with PMD would require HPAGE_PMD_NR atomic operations instead of single we have now. The idea is to store separately how many times the page was mapped as whole -- compound_mapcount. This frees up ->_mapcount in subpages to track PTE mapcount. We use the same approach as with compound page destructor and compound order to store compound_mapcount: use space in first tail page, ->mapping this time. Any time we map/unmap whole compound page (THP or hugetlb) -- we increment/decrement compound_mapcount. When we map part of compound page with PTE we operate on ->_mapcount of the subpage. page_mapcount() counts both: PTE and PMD mappings of the page. Basically, we have mapcount for a subpage spread over two counters. It makes tricky to detect when last mapcount for a page goes away. We introduced PageDoubleMap() for this. When we split THP PMD for the first time and there's other PMD mapping left we offset up ->_mapcount in all subpages by one and set PG_double_map on the compound page. These additional references go away with last compound_mapcount. This approach provides a way to detect when last mapcount goes away on per small page basis without introducing new overhead for most common cases. [akpm@linux-foundation.org: fix typo in comment] [mhocko@suse.com: ignore partial THP when moving task] Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Tested-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> Acked-by: Jerome Marchand <jmarchan@redhat.com> Cc: Sasha Levin <sasha.levin@oracle.com> Cc: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> Cc: Jerome Marchand <jmarchan@redhat.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Hugh Dickins <hughd@google.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Rik van Riel <riel@redhat.com> Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Cc: Steve Capper <steve.capper@linaro.org> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Christoph Lameter <cl@linux.com> Cc: David Rientjes <rientjes@google.com> Signed-off-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-01-16 00:53:42 +00:00
if (PageCompound(page))
pr_cont(" compound_mapcount: %d", compound_mapcount(page));
pr_cont("\n");
mm, printk: introduce new format string for flags In mm we use several kinds of flags bitfields that are sometimes printed for debugging purposes, or exported to userspace via sysfs. To make them easier to interpret independently on kernel version and config, we want to dump also the symbolic flag names. So far this has been done with repeated calls to pr_cont(), which is unreliable on SMP, and not usable for e.g. sysfs export. To get a more reliable and universal solution, this patch extends printk() format string for pointers to handle the page flags (%pGp), gfp_flags (%pGg) and vma flags (%pGv). Existing users of dump_flag_names() are converted and simplified. It would be possible to pass flags by value instead of pointer, but the %p format string for pointers already has extensions for various kernel structures, so it's a good fit, and the extra indirection in a non-critical path is negligible. [linux@rasmusvillemoes.dk: lots of good implementation suggestions] Signed-off-by: Vlastimil Babka <vbabka@suse.cz> Acked-by: Michal Hocko <mhocko@suse.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Sasha Levin <sasha.levin@oracle.com> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Cc: Mel Gorman <mgorman@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-03-15 21:55:56 +00:00
BUILD_BUG_ON(ARRAY_SIZE(pageflag_names) != __NR_PAGEFLAGS + 1);
pr_emerg("flags: %#lx(%pGp)\n", page->flags, &page->flags);
if (reason)
pr_alert("page dumped because: %s\n", reason);
badflags &= page->flags;
if (badflags)
pr_alert("bad because of flags: %#lx(%pGp)\n", badflags,
&badflags);
#ifdef CONFIG_MEMCG
if (page->mem_cgroup)
pr_alert("page->mem_cgroup:%p\n", page->mem_cgroup);
#endif
}
void dump_page(struct page *page, const char *reason)
{
dump_page_badflags(page, reason, 0);
}
EXPORT_SYMBOL(dump_page);
#ifdef CONFIG_DEBUG_VM
void dump_vma(const struct vm_area_struct *vma)
{
pr_emerg("vma %p start %p end %p\n"
"next %p prev %p mm %p\n"
"prot %lx anon_vma %p vm_ops %p\n"
"pgoff %lx file %p private_data %p\n"
"flags: %#lx(%pGv)\n",
vma, (void *)vma->vm_start, (void *)vma->vm_end, vma->vm_next,
vma->vm_prev, vma->vm_mm,
(unsigned long)pgprot_val(vma->vm_page_prot),
vma->anon_vma, vma->vm_ops, vma->vm_pgoff,
vma->vm_file, vma->vm_private_data,
vma->vm_flags, &vma->vm_flags);
}
EXPORT_SYMBOL(dump_vma);
void dump_mm(const struct mm_struct *mm)
{
pr_emerg("mm %p mmap %p seqnum %d task_size %lu\n"
#ifdef CONFIG_MMU
"get_unmapped_area %p\n"
#endif
"mmap_base %lu mmap_legacy_base %lu highest_vm_end %lu\n"
mm: account pmd page tables to the process Dave noticed that unprivileged process can allocate significant amount of memory -- >500 MiB on x86_64 -- and stay unnoticed by oom-killer and memory cgroup. The trick is to allocate a lot of PMD page tables. Linux kernel doesn't account PMD tables to the process, only PTE. The use-cases below use few tricks to allocate a lot of PMD page tables while keeping VmRSS and VmPTE low. oom_score for the process will be 0. #include <errno.h> #include <stdio.h> #include <stdlib.h> #include <unistd.h> #include <sys/mman.h> #include <sys/prctl.h> #define PUD_SIZE (1UL << 30) #define PMD_SIZE (1UL << 21) #define NR_PUD 130000 int main(void) { char *addr = NULL; unsigned long i; prctl(PR_SET_THP_DISABLE); for (i = 0; i < NR_PUD ; i++) { addr = mmap(addr + PUD_SIZE, PUD_SIZE, PROT_WRITE|PROT_READ, MAP_ANONYMOUS|MAP_PRIVATE, -1, 0); if (addr == MAP_FAILED) { perror("mmap"); break; } *addr = 'x'; munmap(addr, PMD_SIZE); mmap(addr, PMD_SIZE, PROT_WRITE|PROT_READ, MAP_ANONYMOUS|MAP_PRIVATE|MAP_FIXED, -1, 0); if (addr == MAP_FAILED) perror("re-mmap"), exit(1); } printf("PID %d consumed %lu KiB in PMD page tables\n", getpid(), i * 4096 >> 10); return pause(); } The patch addresses the issue by account PMD tables to the process the same way we account PTE. The main place where PMD tables is accounted is __pmd_alloc() and free_pmd_range(). But there're few corner cases: - HugeTLB can share PMD page tables. The patch handles by accounting the table to all processes who share it. - x86 PAE pre-allocates few PMD tables on fork. - Architectures with FIRST_USER_ADDRESS > 0. We need to adjust sanity check on exit(2). Accounting only happens on configuration where PMD page table's level is present (PMD is not folded). As with nr_ptes we use per-mm counter. The counter value is used to calculate baseline for badness score by oom-killer. Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Reported-by: Dave Hansen <dave.hansen@linux.intel.com> Cc: Hugh Dickins <hughd@google.com> Reviewed-by: Cyrill Gorcunov <gorcunov@openvz.org> Cc: Pavel Emelyanov <xemul@openvz.org> Cc: David Rientjes <rientjes@google.com> Tested-by: Sedat Dilek <sedat.dilek@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-02-11 23:26:50 +00:00
"pgd %p mm_users %d mm_count %d nr_ptes %lu nr_pmds %lu map_count %d\n"
"hiwater_rss %lx hiwater_vm %lx total_vm %lx locked_vm %lx\n"
mm: rework virtual memory accounting When inspecting a vague code inside prctl(PR_SET_MM_MEM) call (which testing the RLIMIT_DATA value to figure out if we're allowed to assign new @start_brk, @brk, @start_data, @end_data from mm_struct) it's been commited that RLIMIT_DATA in a form it's implemented now doesn't do anything useful because most of user-space libraries use mmap() syscall for dynamic memory allocations. Linus suggested to convert RLIMIT_DATA rlimit into something suitable for anonymous memory accounting. But in this patch we go further, and the changes are bundled together as: * keep vma counting if CONFIG_PROC_FS=n, will be used for limits * replace mm->shared_vm with better defined mm->data_vm * account anonymous executable areas as executable * account file-backed growsdown/up areas as stack * drop struct file* argument from vm_stat_account * enforce RLIMIT_DATA for size of data areas This way code looks cleaner: now code/stack/data classification depends only on vm_flags state: VM_EXEC & ~VM_WRITE -> code (VmExe + VmLib in proc) VM_GROWSUP | VM_GROWSDOWN -> stack (VmStk) VM_WRITE & ~VM_SHARED & !stack -> data (VmData) The rest (VmSize - VmData - VmStk - VmExe - VmLib) could be called "shared", but that might be strange beast like readonly-private or VM_IO area. - RLIMIT_AS limits whole address space "VmSize" - RLIMIT_STACK limits stack "VmStk" (but each vma individually) - RLIMIT_DATA now limits "VmData" Signed-off-by: Konstantin Khlebnikov <koct9i@gmail.com> Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org> Cc: Quentin Casasnovas <quentin.casasnovas@oracle.com> Cc: Vegard Nossum <vegard.nossum@oracle.com> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Cc: Willy Tarreau <w@1wt.eu> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Kees Cook <keescook@google.com> Cc: Vladimir Davydov <vdavydov@virtuozzo.com> Cc: Pavel Emelyanov <xemul@virtuozzo.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-01-14 23:22:07 +00:00
"pinned_vm %lx data_vm %lx exec_vm %lx stack_vm %lx\n"
"start_code %lx end_code %lx start_data %lx end_data %lx\n"
"start_brk %lx brk %lx start_stack %lx\n"
"arg_start %lx arg_end %lx env_start %lx env_end %lx\n"
"binfmt %p flags %lx core_state %p\n"
#ifdef CONFIG_AIO
"ioctx_table %p\n"
#endif
#ifdef CONFIG_MEMCG
"owner %p "
#endif
"exe_file %p\n"
#ifdef CONFIG_MMU_NOTIFIER
"mmu_notifier_mm %p\n"
#endif
#ifdef CONFIG_NUMA_BALANCING
"numa_next_scan %lu numa_scan_offset %lu numa_scan_seq %d\n"
#endif
#if defined(CONFIG_NUMA_BALANCING) || defined(CONFIG_COMPACTION)
"tlb_flush_pending %d\n"
#endif
"def_flags: %#lx(%pGv)\n",
mm, mm->mmap, mm->vmacache_seqnum, mm->task_size,
#ifdef CONFIG_MMU
mm->get_unmapped_area,
#endif
mm->mmap_base, mm->mmap_legacy_base, mm->highest_vm_end,
mm->pgd, atomic_read(&mm->mm_users),
atomic_read(&mm->mm_count),
atomic_long_read((atomic_long_t *)&mm->nr_ptes),
mm: account pmd page tables to the process Dave noticed that unprivileged process can allocate significant amount of memory -- >500 MiB on x86_64 -- and stay unnoticed by oom-killer and memory cgroup. The trick is to allocate a lot of PMD page tables. Linux kernel doesn't account PMD tables to the process, only PTE. The use-cases below use few tricks to allocate a lot of PMD page tables while keeping VmRSS and VmPTE low. oom_score for the process will be 0. #include <errno.h> #include <stdio.h> #include <stdlib.h> #include <unistd.h> #include <sys/mman.h> #include <sys/prctl.h> #define PUD_SIZE (1UL << 30) #define PMD_SIZE (1UL << 21) #define NR_PUD 130000 int main(void) { char *addr = NULL; unsigned long i; prctl(PR_SET_THP_DISABLE); for (i = 0; i < NR_PUD ; i++) { addr = mmap(addr + PUD_SIZE, PUD_SIZE, PROT_WRITE|PROT_READ, MAP_ANONYMOUS|MAP_PRIVATE, -1, 0); if (addr == MAP_FAILED) { perror("mmap"); break; } *addr = 'x'; munmap(addr, PMD_SIZE); mmap(addr, PMD_SIZE, PROT_WRITE|PROT_READ, MAP_ANONYMOUS|MAP_PRIVATE|MAP_FIXED, -1, 0); if (addr == MAP_FAILED) perror("re-mmap"), exit(1); } printf("PID %d consumed %lu KiB in PMD page tables\n", getpid(), i * 4096 >> 10); return pause(); } The patch addresses the issue by account PMD tables to the process the same way we account PTE. The main place where PMD tables is accounted is __pmd_alloc() and free_pmd_range(). But there're few corner cases: - HugeTLB can share PMD page tables. The patch handles by accounting the table to all processes who share it. - x86 PAE pre-allocates few PMD tables on fork. - Architectures with FIRST_USER_ADDRESS > 0. We need to adjust sanity check on exit(2). Accounting only happens on configuration where PMD page table's level is present (PMD is not folded). As with nr_ptes we use per-mm counter. The counter value is used to calculate baseline for badness score by oom-killer. Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Reported-by: Dave Hansen <dave.hansen@linux.intel.com> Cc: Hugh Dickins <hughd@google.com> Reviewed-by: Cyrill Gorcunov <gorcunov@openvz.org> Cc: Pavel Emelyanov <xemul@openvz.org> Cc: David Rientjes <rientjes@google.com> Tested-by: Sedat Dilek <sedat.dilek@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-02-11 23:26:50 +00:00
mm_nr_pmds((struct mm_struct *)mm),
mm->map_count,
mm->hiwater_rss, mm->hiwater_vm, mm->total_vm, mm->locked_vm,
mm: rework virtual memory accounting When inspecting a vague code inside prctl(PR_SET_MM_MEM) call (which testing the RLIMIT_DATA value to figure out if we're allowed to assign new @start_brk, @brk, @start_data, @end_data from mm_struct) it's been commited that RLIMIT_DATA in a form it's implemented now doesn't do anything useful because most of user-space libraries use mmap() syscall for dynamic memory allocations. Linus suggested to convert RLIMIT_DATA rlimit into something suitable for anonymous memory accounting. But in this patch we go further, and the changes are bundled together as: * keep vma counting if CONFIG_PROC_FS=n, will be used for limits * replace mm->shared_vm with better defined mm->data_vm * account anonymous executable areas as executable * account file-backed growsdown/up areas as stack * drop struct file* argument from vm_stat_account * enforce RLIMIT_DATA for size of data areas This way code looks cleaner: now code/stack/data classification depends only on vm_flags state: VM_EXEC & ~VM_WRITE -> code (VmExe + VmLib in proc) VM_GROWSUP | VM_GROWSDOWN -> stack (VmStk) VM_WRITE & ~VM_SHARED & !stack -> data (VmData) The rest (VmSize - VmData - VmStk - VmExe - VmLib) could be called "shared", but that might be strange beast like readonly-private or VM_IO area. - RLIMIT_AS limits whole address space "VmSize" - RLIMIT_STACK limits stack "VmStk" (but each vma individually) - RLIMIT_DATA now limits "VmData" Signed-off-by: Konstantin Khlebnikov <koct9i@gmail.com> Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org> Cc: Quentin Casasnovas <quentin.casasnovas@oracle.com> Cc: Vegard Nossum <vegard.nossum@oracle.com> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Cc: Willy Tarreau <w@1wt.eu> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Kees Cook <keescook@google.com> Cc: Vladimir Davydov <vdavydov@virtuozzo.com> Cc: Pavel Emelyanov <xemul@virtuozzo.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-01-14 23:22:07 +00:00
mm->pinned_vm, mm->data_vm, mm->exec_vm, mm->stack_vm,
mm->start_code, mm->end_code, mm->start_data, mm->end_data,
mm->start_brk, mm->brk, mm->start_stack,
mm->arg_start, mm->arg_end, mm->env_start, mm->env_end,
mm->binfmt, mm->flags, mm->core_state,
#ifdef CONFIG_AIO
mm->ioctx_table,
#endif
#ifdef CONFIG_MEMCG
mm->owner,
#endif
mm->exe_file,
#ifdef CONFIG_MMU_NOTIFIER
mm->mmu_notifier_mm,
#endif
#ifdef CONFIG_NUMA_BALANCING
mm->numa_next_scan, mm->numa_scan_offset, mm->numa_scan_seq,
#endif
#if defined(CONFIG_NUMA_BALANCING) || defined(CONFIG_COMPACTION)
mm->tlb_flush_pending,
#endif
mm->def_flags, &mm->def_flags
);
}
#endif /* CONFIG_DEBUG_VM */