remarkable-linux/include/linux/hugetlb.h
Mel Gorman d833352a43 mm: hugetlbfs: close race during teardown of hugetlbfs shared page tables
If a process creates a large hugetlbfs mapping that is eligible for page
table sharing and forks heavily with children some of whom fault and
others which destroy the mapping then it is possible for page tables to
get corrupted.  Some teardowns of the mapping encounter a "bad pmd" and
output a message to the kernel log.  The final teardown will trigger a
BUG_ON in mm/filemap.c.

This was reproduced in 3.4 but is known to have existed for a long time
and goes back at least as far as 2.6.37.  It was probably was introduced
in 2.6.20 by [39dde65c: shared page table for hugetlb page].  The messages
look like this;

[  ..........] Lots of bad pmd messages followed by this
[  127.164256] mm/memory.c:391: bad pmd ffff880412e04fe8(80000003de4000e7).
[  127.164257] mm/memory.c:391: bad pmd ffff880412e04ff0(80000003de6000e7).
[  127.164258] mm/memory.c:391: bad pmd ffff880412e04ff8(80000003de0000e7).
[  127.186778] ------------[ cut here ]------------
[  127.186781] kernel BUG at mm/filemap.c:134!
[  127.186782] invalid opcode: 0000 [#1] SMP
[  127.186783] CPU 7
[  127.186784] Modules linked in: af_packet cpufreq_conservative cpufreq_userspace cpufreq_powersave acpi_cpufreq mperf ext3 jbd dm_mod coretemp crc32c_intel usb_storage ghash_clmulni_intel aesni_intel i2c_i801 r8169 mii uas sr_mod cdrom sg iTCO_wdt iTCO_vendor_support shpchp serio_raw cryptd aes_x86_64 e1000e pci_hotplug dcdbas aes_generic container microcode ext4 mbcache jbd2 crc16 sd_mod crc_t10dif i915 drm_kms_helper drm i2c_algo_bit ehci_hcd ahci libahci usbcore rtc_cmos usb_common button i2c_core intel_agp video intel_gtt fan processor thermal thermal_sys hwmon ata_generic pata_atiixp libata scsi_mod
[  127.186801]
[  127.186802] Pid: 9017, comm: hugetlbfs-test Not tainted 3.4.0-autobuild #53 Dell Inc. OptiPlex 990/06D7TR
[  127.186804] RIP: 0010:[<ffffffff810ed6ce>]  [<ffffffff810ed6ce>] __delete_from_page_cache+0x15e/0x160
[  127.186809] RSP: 0000:ffff8804144b5c08  EFLAGS: 00010002
[  127.186810] RAX: 0000000000000001 RBX: ffffea000a5c9000 RCX: 00000000ffffffc0
[  127.186811] RDX: 0000000000000000 RSI: 0000000000000009 RDI: ffff88042dfdad00
[  127.186812] RBP: ffff8804144b5c18 R08: 0000000000000009 R09: 0000000000000003
[  127.186813] R10: 0000000000000000 R11: 000000000000002d R12: ffff880412ff83d8
[  127.186814] R13: ffff880412ff83d8 R14: 0000000000000000 R15: ffff880412ff83d8
[  127.186815] FS:  00007fe18ed2c700(0000) GS:ffff88042dce0000(0000) knlGS:0000000000000000
[  127.186816] CS:  0010 DS: 0000 ES: 0000 CR0: 000000008005003b
[  127.186817] CR2: 00007fe340000503 CR3: 0000000417a14000 CR4: 00000000000407e0
[  127.186818] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[  127.186819] DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400
[  127.186820] Process hugetlbfs-test (pid: 9017, threadinfo ffff8804144b4000, task ffff880417f803c0)
[  127.186821] Stack:
[  127.186822]  ffffea000a5c9000 0000000000000000 ffff8804144b5c48 ffffffff810ed83b
[  127.186824]  ffff8804144b5c48 000000000000138a 0000000000001387 ffff8804144b5c98
[  127.186825]  ffff8804144b5d48 ffffffff811bc925 ffff8804144b5cb8 0000000000000000
[  127.186827] Call Trace:
[  127.186829]  [<ffffffff810ed83b>] delete_from_page_cache+0x3b/0x80
[  127.186832]  [<ffffffff811bc925>] truncate_hugepages+0x115/0x220
[  127.186834]  [<ffffffff811bca43>] hugetlbfs_evict_inode+0x13/0x30
[  127.186837]  [<ffffffff811655c7>] evict+0xa7/0x1b0
[  127.186839]  [<ffffffff811657a3>] iput_final+0xd3/0x1f0
[  127.186840]  [<ffffffff811658f9>] iput+0x39/0x50
[  127.186842]  [<ffffffff81162708>] d_kill+0xf8/0x130
[  127.186843]  [<ffffffff81162812>] dput+0xd2/0x1a0
[  127.186845]  [<ffffffff8114e2d0>] __fput+0x170/0x230
[  127.186848]  [<ffffffff81236e0e>] ? rb_erase+0xce/0x150
[  127.186849]  [<ffffffff8114e3ad>] fput+0x1d/0x30
[  127.186851]  [<ffffffff81117db7>] remove_vma+0x37/0x80
[  127.186853]  [<ffffffff81119182>] do_munmap+0x2d2/0x360
[  127.186855]  [<ffffffff811cc639>] sys_shmdt+0xc9/0x170
[  127.186857]  [<ffffffff81410a39>] system_call_fastpath+0x16/0x1b
[  127.186858] Code: 0f 1f 44 00 00 48 8b 43 08 48 8b 00 48 8b 40 28 8b b0 40 03 00 00 85 f6 0f 88 df fe ff ff 48 89 df e8 e7 cb 05 00 e9 d2 fe ff ff <0f> 0b 55 83 e2 fd 48 89 e5 48 83 ec 30 48 89 5d d8 4c 89 65 e0
[  127.186868] RIP  [<ffffffff810ed6ce>] __delete_from_page_cache+0x15e/0x160
[  127.186870]  RSP <ffff8804144b5c08>
[  127.186871] ---[ end trace 7cbac5d1db69f426 ]---

The bug is a race and not always easy to reproduce.  To reproduce it I was
doing the following on a single socket I7-based machine with 16G of RAM.

$ hugeadm --pool-pages-max DEFAULT:13G
$ echo $((18*1048576*1024)) > /proc/sys/kernel/shmmax
$ echo $((18*1048576*1024)) > /proc/sys/kernel/shmall
$ for i in `seq 1 9000`; do ./hugetlbfs-test; done

On my particular machine, it usually triggers within 10 minutes but
enabling debug options can change the timing such that it never hits.
Once the bug is triggered, the machine is in trouble and needs to be
rebooted.  The machine will respond but processes accessing proc like "ps
aux" will hang due to the BUG_ON.  shutdown will also hang and needs a
hard reset or a sysrq-b.

The basic problem is a race between page table sharing and teardown.  For
the most part page table sharing depends on i_mmap_mutex.  In some cases,
it is also taking the mm->page_table_lock for the PTE updates but with
shared page tables, it is the i_mmap_mutex that is more important.

Unfortunately it appears to be also insufficient. Consider the following
situation

Process A					Process B
---------					---------
hugetlb_fault					shmdt
  						LockWrite(mmap_sem)
    						  do_munmap
						    unmap_region
						      unmap_vmas
						        unmap_single_vma
						          unmap_hugepage_range
      						            Lock(i_mmap_mutex)
							    Lock(mm->page_table_lock)
							    huge_pmd_unshare/unmap tables <--- (1)
							    Unlock(mm->page_table_lock)
      						            Unlock(i_mmap_mutex)
  huge_pte_alloc				      ...
    Lock(i_mmap_mutex)				      ...
    vma_prio_walk, find svma, spte		      ...
    Lock(mm->page_table_lock)			      ...
    share spte					      ...
    Unlock(mm->page_table_lock)			      ...
    Unlock(i_mmap_mutex)			      ...
  hugetlb_no_page									  <--- (2)
						      free_pgtables
						        unlink_file_vma
							hugetlb_free_pgd_range
						    remove_vma_list

In this scenario, it is possible for Process A to share page tables with
Process B that is trying to tear them down.  The i_mmap_mutex on its own
does not prevent Process A walking Process B's page tables.  At (1) above,
the page tables are not shared yet so it unmaps the PMDs.  Process A sets
up page table sharing and at (2) faults a new entry.  Process B then trips
up on it in free_pgtables.

This patch fixes the problem by adding a new function
__unmap_hugepage_range_final that is only called when the VMA is about to
be destroyed.  This function clears VM_MAYSHARE during
unmap_hugepage_range() under the i_mmap_mutex.  This makes the VMA
ineligible for sharing and avoids the race.  Superficially this looks like
it would then be vunerable to truncate and madvise issues but hugetlbfs
has its own truncate handlers so does not use unmap_mapping_range() and
does not support madvise(DONTNEED).

This should be treated as a -stable candidate if it is merged.

Test program is as follows. The test case was mostly written by Michal
Hocko with a few minor changes to reproduce this bug.

==== CUT HERE ====

static size_t huge_page_size = (2UL << 20);
static size_t nr_huge_page_A = 512;
static size_t nr_huge_page_B = 5632;

unsigned int get_random(unsigned int max)
{
	struct timeval tv;

	gettimeofday(&tv, NULL);
	srandom(tv.tv_usec);
	return random() % max;
}

static void play(void *addr, size_t size)
{
	unsigned char *start = addr,
		      *end = start + size,
		      *a;
	start += get_random(size/2);

	/* we could itterate on huge pages but let's give it more time. */
	for (a = start; a < end; a += 4096)
		*a = 0;
}

int main(int argc, char **argv)
{
	key_t key = IPC_PRIVATE;
	size_t sizeA = nr_huge_page_A * huge_page_size;
	size_t sizeB = nr_huge_page_B * huge_page_size;
	int shmidA, shmidB;
	void *addrA = NULL, *addrB = NULL;
	int nr_children = 300, n = 0;

	if ((shmidA = shmget(key, sizeA, IPC_CREAT|SHM_HUGETLB|0660)) == -1) {
		perror("shmget:");
		return 1;
	}

	if ((addrA = shmat(shmidA, addrA, SHM_R|SHM_W)) == (void *)-1UL) {
		perror("shmat");
		return 1;
	}
	if ((shmidB = shmget(key, sizeB, IPC_CREAT|SHM_HUGETLB|0660)) == -1) {
		perror("shmget:");
		return 1;
	}

	if ((addrB = shmat(shmidB, addrB, SHM_R|SHM_W)) == (void *)-1UL) {
		perror("shmat");
		return 1;
	}

fork_child:
	switch(fork()) {
		case 0:
			switch (n%3) {
			case 0:
				play(addrA, sizeA);
				break;
			case 1:
				play(addrB, sizeB);
				break;
			case 2:
				break;
			}
			break;
		case -1:
			perror("fork:");
			break;
		default:
			if (++n < nr_children)
				goto fork_child;
			play(addrA, sizeA);
			break;
	}
	shmdt(addrA);
	shmdt(addrB);
	do {
		wait(NULL);
	} while (--n > 0);
	shmctl(shmidA, IPC_RMID, NULL);
	shmctl(shmidB, IPC_RMID, NULL);
	return 0;
}

[akpm@linux-foundation.org: name the declaration's args, fix CONFIG_HUGETLBFS=n build]
Signed-off-by: Hugh Dickins <hughd@google.com>
Reviewed-by: Michal Hocko <mhocko@suse.cz>
Signed-off-by: Mel Gorman <mgorman@suse.de>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-07-31 18:42:50 -07:00

366 lines
10 KiB
C

#ifndef _LINUX_HUGETLB_H
#define _LINUX_HUGETLB_H
#include <linux/mm_types.h>
#include <linux/fs.h>
#include <linux/hugetlb_inline.h>
#include <linux/cgroup.h>
struct ctl_table;
struct user_struct;
struct mmu_gather;
#ifdef CONFIG_HUGETLB_PAGE
#include <linux/mempolicy.h>
#include <linux/shm.h>
#include <asm/tlbflush.h>
struct hugepage_subpool {
spinlock_t lock;
long count;
long max_hpages, used_hpages;
};
extern spinlock_t hugetlb_lock;
extern int hugetlb_max_hstate __read_mostly;
#define for_each_hstate(h) \
for ((h) = hstates; (h) < &hstates[hugetlb_max_hstate]; (h)++)
struct hugepage_subpool *hugepage_new_subpool(long nr_blocks);
void hugepage_put_subpool(struct hugepage_subpool *spool);
int PageHuge(struct page *page);
void reset_vma_resv_huge_pages(struct vm_area_struct *vma);
int hugetlb_sysctl_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *);
int hugetlb_overcommit_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *);
int hugetlb_treat_movable_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *);
#ifdef CONFIG_NUMA
int hugetlb_mempolicy_sysctl_handler(struct ctl_table *, int,
void __user *, size_t *, loff_t *);
#endif
int copy_hugetlb_page_range(struct mm_struct *, struct mm_struct *, struct vm_area_struct *);
int follow_hugetlb_page(struct mm_struct *, struct vm_area_struct *,
struct page **, struct vm_area_struct **,
unsigned long *, int *, int, unsigned int flags);
void unmap_hugepage_range(struct vm_area_struct *,
unsigned long, unsigned long, struct page *);
void __unmap_hugepage_range_final(struct mmu_gather *tlb,
struct vm_area_struct *vma,
unsigned long start, unsigned long end,
struct page *ref_page);
void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma,
unsigned long start, unsigned long end,
struct page *ref_page);
int hugetlb_prefault(struct address_space *, struct vm_area_struct *);
void hugetlb_report_meminfo(struct seq_file *);
int hugetlb_report_node_meminfo(int, char *);
unsigned long hugetlb_total_pages(void);
int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
unsigned long address, unsigned int flags);
int hugetlb_reserve_pages(struct inode *inode, long from, long to,
struct vm_area_struct *vma,
vm_flags_t vm_flags);
void hugetlb_unreserve_pages(struct inode *inode, long offset, long freed);
int dequeue_hwpoisoned_huge_page(struct page *page);
void copy_huge_page(struct page *dst, struct page *src);
extern unsigned long hugepages_treat_as_movable;
extern const unsigned long hugetlb_zero, hugetlb_infinity;
extern int sysctl_hugetlb_shm_group;
extern struct list_head huge_boot_pages;
/* arch callbacks */
pte_t *huge_pte_alloc(struct mm_struct *mm,
unsigned long addr, unsigned long sz);
pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr);
int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep);
struct page *follow_huge_addr(struct mm_struct *mm, unsigned long address,
int write);
struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address,
pmd_t *pmd, int write);
struct page *follow_huge_pud(struct mm_struct *mm, unsigned long address,
pud_t *pud, int write);
int pmd_huge(pmd_t pmd);
int pud_huge(pud_t pmd);
void hugetlb_change_protection(struct vm_area_struct *vma,
unsigned long address, unsigned long end, pgprot_t newprot);
#else /* !CONFIG_HUGETLB_PAGE */
static inline int PageHuge(struct page *page)
{
return 0;
}
static inline void reset_vma_resv_huge_pages(struct vm_area_struct *vma)
{
}
static inline unsigned long hugetlb_total_pages(void)
{
return 0;
}
#define follow_hugetlb_page(m,v,p,vs,a,b,i,w) ({ BUG(); 0; })
#define follow_huge_addr(mm, addr, write) ERR_PTR(-EINVAL)
#define copy_hugetlb_page_range(src, dst, vma) ({ BUG(); 0; })
#define hugetlb_prefault(mapping, vma) ({ BUG(); 0; })
static inline void hugetlb_report_meminfo(struct seq_file *m)
{
}
#define hugetlb_report_node_meminfo(n, buf) 0
#define follow_huge_pmd(mm, addr, pmd, write) NULL
#define follow_huge_pud(mm, addr, pud, write) NULL
#define prepare_hugepage_range(file, addr, len) (-EINVAL)
#define pmd_huge(x) 0
#define pud_huge(x) 0
#define is_hugepage_only_range(mm, addr, len) 0
#define hugetlb_free_pgd_range(tlb, addr, end, floor, ceiling) ({BUG(); 0; })
#define hugetlb_fault(mm, vma, addr, flags) ({ BUG(); 0; })
#define huge_pte_offset(mm, address) 0
static inline int dequeue_hwpoisoned_huge_page(struct page *page)
{
return 0;
}
static inline void copy_huge_page(struct page *dst, struct page *src)
{
}
#define hugetlb_change_protection(vma, address, end, newprot)
static inline void __unmap_hugepage_range_final(struct mmu_gather *tlb,
struct vm_area_struct *vma, unsigned long start,
unsigned long end, struct page *ref_page)
{
BUG();
}
static inline void __unmap_hugepage_range(struct mmu_gather *tlb,
struct vm_area_struct *vma, unsigned long start,
unsigned long end, struct page *ref_page)
{
BUG();
}
#endif /* !CONFIG_HUGETLB_PAGE */
#define HUGETLB_ANON_FILE "anon_hugepage"
enum {
/*
* The file will be used as an shm file so shmfs accounting rules
* apply
*/
HUGETLB_SHMFS_INODE = 1,
/*
* The file is being created on the internal vfs mount and shmfs
* accounting rules do not apply
*/
HUGETLB_ANONHUGE_INODE = 2,
};
#ifdef CONFIG_HUGETLBFS
struct hugetlbfs_sb_info {
long max_inodes; /* inodes allowed */
long free_inodes; /* inodes free */
spinlock_t stat_lock;
struct hstate *hstate;
struct hugepage_subpool *spool;
};
static inline struct hugetlbfs_sb_info *HUGETLBFS_SB(struct super_block *sb)
{
return sb->s_fs_info;
}
extern const struct file_operations hugetlbfs_file_operations;
extern const struct vm_operations_struct hugetlb_vm_ops;
struct file *hugetlb_file_setup(const char *name, unsigned long addr,
size_t size, vm_flags_t acct,
struct user_struct **user, int creat_flags);
static inline int is_file_hugepages(struct file *file)
{
if (file->f_op == &hugetlbfs_file_operations)
return 1;
if (is_file_shm_hugepages(file))
return 1;
return 0;
}
#else /* !CONFIG_HUGETLBFS */
#define is_file_hugepages(file) 0
static inline struct file *
hugetlb_file_setup(const char *name, unsigned long addr, size_t size,
vm_flags_t acctflag, struct user_struct **user, int creat_flags)
{
return ERR_PTR(-ENOSYS);
}
#endif /* !CONFIG_HUGETLBFS */
#ifdef HAVE_ARCH_HUGETLB_UNMAPPED_AREA
unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
unsigned long len, unsigned long pgoff,
unsigned long flags);
#endif /* HAVE_ARCH_HUGETLB_UNMAPPED_AREA */
#ifdef CONFIG_HUGETLB_PAGE
#define HSTATE_NAME_LEN 32
/* Defines one hugetlb page size */
struct hstate {
int next_nid_to_alloc;
int next_nid_to_free;
unsigned int order;
unsigned long mask;
unsigned long max_huge_pages;
unsigned long nr_huge_pages;
unsigned long free_huge_pages;
unsigned long resv_huge_pages;
unsigned long surplus_huge_pages;
unsigned long nr_overcommit_huge_pages;
struct list_head hugepage_activelist;
struct list_head hugepage_freelists[MAX_NUMNODES];
unsigned int nr_huge_pages_node[MAX_NUMNODES];
unsigned int free_huge_pages_node[MAX_NUMNODES];
unsigned int surplus_huge_pages_node[MAX_NUMNODES];
#ifdef CONFIG_CGROUP_HUGETLB
/* cgroup control files */
struct cftype cgroup_files[5];
#endif
char name[HSTATE_NAME_LEN];
};
struct huge_bootmem_page {
struct list_head list;
struct hstate *hstate;
#ifdef CONFIG_HIGHMEM
phys_addr_t phys;
#endif
};
struct page *alloc_huge_page_node(struct hstate *h, int nid);
/* arch callback */
int __init alloc_bootmem_huge_page(struct hstate *h);
void __init hugetlb_add_hstate(unsigned order);
struct hstate *size_to_hstate(unsigned long size);
#ifndef HUGE_MAX_HSTATE
#define HUGE_MAX_HSTATE 1
#endif
extern struct hstate hstates[HUGE_MAX_HSTATE];
extern unsigned int default_hstate_idx;
#define default_hstate (hstates[default_hstate_idx])
static inline struct hstate *hstate_inode(struct inode *i)
{
struct hugetlbfs_sb_info *hsb;
hsb = HUGETLBFS_SB(i->i_sb);
return hsb->hstate;
}
static inline struct hstate *hstate_file(struct file *f)
{
return hstate_inode(f->f_dentry->d_inode);
}
static inline struct hstate *hstate_vma(struct vm_area_struct *vma)
{
return hstate_file(vma->vm_file);
}
static inline unsigned long huge_page_size(struct hstate *h)
{
return (unsigned long)PAGE_SIZE << h->order;
}
extern unsigned long vma_kernel_pagesize(struct vm_area_struct *vma);
extern unsigned long vma_mmu_pagesize(struct vm_area_struct *vma);
static inline unsigned long huge_page_mask(struct hstate *h)
{
return h->mask;
}
static inline unsigned int huge_page_order(struct hstate *h)
{
return h->order;
}
static inline unsigned huge_page_shift(struct hstate *h)
{
return h->order + PAGE_SHIFT;
}
static inline unsigned int pages_per_huge_page(struct hstate *h)
{
return 1 << h->order;
}
static inline unsigned int blocks_per_huge_page(struct hstate *h)
{
return huge_page_size(h) / 512;
}
#include <asm/hugetlb.h>
#ifndef arch_make_huge_pte
static inline pte_t arch_make_huge_pte(pte_t entry, struct vm_area_struct *vma,
struct page *page, int writable)
{
return entry;
}
#endif
static inline struct hstate *page_hstate(struct page *page)
{
return size_to_hstate(PAGE_SIZE << compound_order(page));
}
static inline unsigned hstate_index_to_shift(unsigned index)
{
return hstates[index].order + PAGE_SHIFT;
}
static inline int hstate_index(struct hstate *h)
{
return h - hstates;
}
#else
struct hstate {};
#define alloc_huge_page_node(h, nid) NULL
#define alloc_bootmem_huge_page(h) NULL
#define hstate_file(f) NULL
#define hstate_vma(v) NULL
#define hstate_inode(i) NULL
#define huge_page_size(h) PAGE_SIZE
#define huge_page_mask(h) PAGE_MASK
#define vma_kernel_pagesize(v) PAGE_SIZE
#define vma_mmu_pagesize(v) PAGE_SIZE
#define huge_page_order(h) 0
#define huge_page_shift(h) PAGE_SHIFT
static inline unsigned int pages_per_huge_page(struct hstate *h)
{
return 1;
}
#define hstate_index_to_shift(index) 0
#define hstate_index(h) 0
#endif
#endif /* _LINUX_HUGETLB_H */