linux/mm/debug.c

241 lines
6.6 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>
static const struct trace_print_flags pageflag_names[] = {
{1UL << PG_locked, "locked" },
{1UL << PG_error, "error" },
{1UL << PG_referenced, "referenced" },
{1UL << PG_uptodate, "uptodate" },
{1UL << PG_dirty, "dirty" },
{1UL << PG_lru, "lru" },
{1UL << PG_active, "active" },
{1UL << PG_slab, "slab" },
{1UL << PG_owner_priv_1, "owner_priv_1" },
{1UL << PG_arch_1, "arch_1" },
{1UL << PG_reserved, "reserved" },
{1UL << PG_private, "private" },
{1UL << PG_private_2, "private_2" },
{1UL << PG_writeback, "writeback" },
{1UL << PG_head, "head" },
{1UL << PG_swapcache, "swapcache" },
{1UL << PG_mappedtodisk, "mappedtodisk" },
{1UL << PG_reclaim, "reclaim" },
{1UL << PG_swapbacked, "swapbacked" },
{1UL << PG_unevictable, "unevictable" },
#ifdef CONFIG_MMU
{1UL << PG_mlocked, "mlocked" },
#endif
#ifdef CONFIG_ARCH_USES_PG_UNCACHED
{1UL << PG_uncached, "uncached" },
#endif
#ifdef CONFIG_MEMORY_FAILURE
{1UL << PG_hwpoison, "hwpoison" },
#endif
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
{1UL << PG_compound_lock, "compound_lock" },
#endif
mm: introduce idle page tracking Knowing the portion of memory that is not used by a certain application or memory cgroup (idle memory) can be useful for partitioning the system efficiently, e.g. by setting memory cgroup limits appropriately. Currently, the only means to estimate the amount of idle memory provided by the kernel is /proc/PID/{clear_refs,smaps}: the user can clear the access bit for all pages mapped to a particular process by writing 1 to clear_refs, wait for some time, and then count smaps:Referenced. However, this method has two serious shortcomings: - it does not count unmapped file pages - it affects the reclaimer logic To overcome these drawbacks, this patch introduces two new page flags, Idle and Young, and a new sysfs file, /sys/kernel/mm/page_idle/bitmap. A page's Idle flag can only be set from userspace by setting bit in /sys/kernel/mm/page_idle/bitmap at the offset corresponding to the page, and it is cleared whenever the page is accessed either through page tables (it is cleared in page_referenced() in this case) or using the read(2) system call (mark_page_accessed()). Thus by setting the Idle flag for pages of a particular workload, which can be found e.g. by reading /proc/PID/pagemap, waiting for some time to let the workload access its working set, and then reading the bitmap file, one can estimate the amount of pages that are not used by the workload. The Young page flag is used to avoid interference with the memory reclaimer. A page's Young flag is set whenever the Access bit of a page table entry pointing to the page is cleared by writing to the bitmap file. If page_referenced() is called on a Young page, it will add 1 to its return value, therefore concealing the fact that the Access bit was cleared. Note, since there is no room for extra page flags on 32 bit, this feature uses extended page flags when compiled on 32 bit. [akpm@linux-foundation.org: fix build] [akpm@linux-foundation.org: kpageidle requires an MMU] [akpm@linux-foundation.org: decouple from page-flags rework] Signed-off-by: Vladimir Davydov <vdavydov@parallels.com> Reviewed-by: Andres Lagar-Cavilla <andreslc@google.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Raghavendra K T <raghavendra.kt@linux.vnet.ibm.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Michal Hocko <mhocko@suse.cz> Cc: Greg Thelen <gthelen@google.com> Cc: Michel Lespinasse <walken@google.com> Cc: David Rientjes <rientjes@google.com> Cc: Pavel Emelyanov <xemul@parallels.com> Cc: Cyrill Gorcunov <gorcunov@openvz.org> Cc: Jonathan Corbet <corbet@lwn.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-09-10 06:35:45 +08:00
#if defined(CONFIG_IDLE_PAGE_TRACKING) && defined(CONFIG_64BIT)
{1UL << PG_young, "young" },
{1UL << PG_idle, "idle" },
#endif
};
static void dump_flags(unsigned long flags,
const struct trace_print_flags *names, int count)
{
const char *delim = "";
unsigned long mask;
int i;
pr_emerg("flags: %#lx(", flags);
/* remove zone id */
flags &= (1UL << NR_PAGEFLAGS) - 1;
for (i = 0; i < count && flags; i++) {
mask = names[i].mask;
if ((flags & mask) != mask)
continue;
flags &= ~mask;
pr_cont("%s%s", delim, names[i].name);
delim = "|";
}
/* check for left over flags */
if (flags)
pr_cont("%s%#lx", delim, flags);
pr_cont(")\n");
}
void dump_page_badflags(struct page *page, const char *reason,
unsigned long badflags)
{
pr_emerg("page:%p count:%d mapcount:%d mapping:%p index:%#lx\n",
page, atomic_read(&page->_count), page_mapcount(page),
page->mapping, page->index);
BUILD_BUG_ON(ARRAY_SIZE(pageflag_names) != __NR_PAGEFLAGS);
dump_flags(page->flags, pageflag_names, ARRAY_SIZE(pageflag_names));
if (reason)
pr_alert("page dumped because: %s\n", reason);
if (page->flags & badflags) {
pr_alert("bad because of flags:\n");
dump_flags(page->flags & badflags,
pageflag_names, ARRAY_SIZE(pageflag_names));
}
#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
static const struct trace_print_flags vmaflags_names[] = {
{VM_READ, "read" },
{VM_WRITE, "write" },
{VM_EXEC, "exec" },
{VM_SHARED, "shared" },
{VM_MAYREAD, "mayread" },
{VM_MAYWRITE, "maywrite" },
{VM_MAYEXEC, "mayexec" },
{VM_MAYSHARE, "mayshare" },
{VM_GROWSDOWN, "growsdown" },
{VM_PFNMAP, "pfnmap" },
{VM_DENYWRITE, "denywrite" },
mm: introduce VM_LOCKONFAULT The cost of faulting in all memory to be locked can be very high when working with large mappings. If only portions of the mapping will be used this can incur a high penalty for locking. For the example of a large file, this is the usage pattern for a large statical language model (probably applies to other statical or graphical models as well). For the security example, any application transacting in data that cannot be swapped out (credit card data, medical records, etc). This patch introduces the ability to request that pages are not pre-faulted, but are placed on the unevictable LRU when they are finally faulted in. The VM_LOCKONFAULT flag will be used together with VM_LOCKED and has no effect when set without VM_LOCKED. Setting the VM_LOCKONFAULT flag for a VMA will cause pages faulted into that VMA to be added to the unevictable LRU when they are faulted or if they are already present, but will not cause any missing pages to be faulted in. Exposing this new lock state means that we cannot overload the meaning of the FOLL_POPULATE flag any longer. Prior to this patch it was used to mean that the VMA for a fault was locked. This means we need the new FOLL_MLOCK flag to communicate the locked state of a VMA. FOLL_POPULATE will now only control if the VMA should be populated and in the case of VM_LOCKONFAULT, it will not be set. Signed-off-by: Eric B Munson <emunson@akamai.com> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Vlastimil Babka <vbabka@suse.cz> Cc: Michal Hocko <mhocko@suse.cz> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Guenter Roeck <linux@roeck-us.net> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Michael Kerrisk <mtk.manpages@gmail.com> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Shuah Khan <shuahkh@osg.samsung.com> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-11-06 10:51:36 +08:00
{VM_LOCKONFAULT, "lockonfault" },
{VM_LOCKED, "locked" },
{VM_IO, "io" },
{VM_SEQ_READ, "seqread" },
{VM_RAND_READ, "randread" },
{VM_DONTCOPY, "dontcopy" },
{VM_DONTEXPAND, "dontexpand" },
{VM_ACCOUNT, "account" },
{VM_NORESERVE, "noreserve" },
{VM_HUGETLB, "hugetlb" },
#if defined(CONFIG_X86)
{VM_PAT, "pat" },
#elif defined(CONFIG_PPC)
{VM_SAO, "sao" },
#elif defined(CONFIG_PARISC) || defined(CONFIG_METAG) || defined(CONFIG_IA64)
{VM_GROWSUP, "growsup" },
#elif !defined(CONFIG_MMU)
{VM_MAPPED_COPY, "mappedcopy" },
#else
{VM_ARCH_1, "arch_1" },
#endif
{VM_DONTDUMP, "dontdump" },
#ifdef CONFIG_MEM_SOFT_DIRTY
{VM_SOFTDIRTY, "softdirty" },
#endif
{VM_MIXEDMAP, "mixedmap" },
{VM_HUGEPAGE, "hugepage" },
{VM_NOHUGEPAGE, "nohugepage" },
{VM_MERGEABLE, "mergeable" },
};
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",
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);
dump_flags(vma->vm_flags, vmaflags_names, ARRAY_SIZE(vmaflags_names));
}
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>
2015-02-12 07:26:50 +08:00
"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"
"pinned_vm %lx shared_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
"%s", /* This is here to hold the comma */
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>
2015-02-12 07:26:50 +08:00
mm_nr_pmds((struct mm_struct *)mm),
mm->map_count,
mm->hiwater_rss, mm->hiwater_vm, mm->total_vm, mm->locked_vm,
mm->pinned_vm, mm->shared_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
"" /* This is here to not have a comma! */
);
dump_flags(mm->def_flags, vmaflags_names,
ARRAY_SIZE(vmaflags_names));
}
#endif /* CONFIG_DEBUG_VM */