linux_dsm_epyc7002/fs/hugetlbfs/inode.c

1416 lines
36 KiB
C
Raw Normal View History

/*
* hugetlbpage-backed filesystem. Based on ramfs.
*
* Nadia Yvette Chambers, 2002
*
* Copyright (C) 2002 Linus Torvalds.
hugetlb: make mm and fs code explicitly non-modular The Kconfig currently controlling compilation of this code is: config HUGETLBFS bool "HugeTLB file system support" ...meaning that it currently is not being built as a module by anyone. Lets remove the modular code that is essentially orphaned, so that when reading the driver there is no doubt it is builtin-only. Since module_init translates to device_initcall in the non-modular case, the init ordering gets moved to earlier levels when we use the more appropriate initcalls here. Originally I had the fs part and the mm part as separate commits, just by happenstance of the nature of how I detected these non-modular use cases. But that can possibly introduce regressions if the patch merge ordering puts the fs part 1st -- as the 0-day testing reported a splat at mount time. Investigating with "initcall_debug" showed that the delta was init_hugetlbfs_fs being called _before_ hugetlb_init instead of after. So both the fs change and the mm change are here together. In addition, it worked before due to luck of link order, since they were both in the same initcall category. So we now have the fs part using fs_initcall, and the mm part using subsys_initcall, which puts it one bucket earlier. It now passes the basic sanity test that failed in earlier 0-day testing. We delete the MODULE_LICENSE tag and capture that information at the top of the file alongside author comments, etc. We don't replace module.h with init.h since the file already has that. Also note that MODULE_ALIAS is a no-op for non-modular code. Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com> Reported-by: kernel test robot <ying.huang@linux.intel.com> Cc: Nadia Yvette Chambers <nyc@holomorphy.com> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com> Cc: David Rientjes <rientjes@google.com> Cc: Hillf Danton <hillf.zj@alibaba-inc.com> Acked-by: Davidlohr Bueso <dave@stgolabs.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-01-15 06:21:52 +07:00
* License: GPL
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/thread_info.h>
#include <asm/current.h>
#include <linux/sched/signal.h> /* remove ASAP */
#include <linux/falloc.h>
#include <linux/fs.h>
#include <linux/mount.h>
#include <linux/file.h>
#include <linux/kernel.h>
#include <linux/writeback.h>
#include <linux/pagemap.h>
#include <linux/highmem.h>
#include <linux/init.h>
#include <linux/string.h>
#include <linux/capability.h>
#include <linux/ctype.h>
#include <linux/backing-dev.h>
#include <linux/hugetlb.h>
#include <linux/pagevec.h>
#include <linux/parser.h>
#include <linux/mman.h>
#include <linux/slab.h>
#include <linux/dnotify.h>
#include <linux/statfs.h>
#include <linux/security.h>
#include <linux/magic.h>
#include <linux/migrate.h>
#include <linux/uio.h>
#include <linux/uaccess.h>
static const struct super_operations hugetlbfs_ops;
static const struct address_space_operations hugetlbfs_aops;
const struct file_operations hugetlbfs_file_operations;
static const struct inode_operations hugetlbfs_dir_inode_operations;
static const struct inode_operations hugetlbfs_inode_operations;
struct hugetlbfs_config {
struct hstate *hstate;
long max_hpages;
long nr_inodes;
long min_hpages;
kuid_t uid;
kgid_t gid;
umode_t mode;
};
struct hugetlbfs_inode_info {
struct shared_policy policy;
struct inode vfs_inode;
};
static inline struct hugetlbfs_inode_info *HUGETLBFS_I(struct inode *inode)
{
return container_of(inode, struct hugetlbfs_inode_info, vfs_inode);
}
int sysctl_hugetlb_shm_group;
enum {
Opt_size, Opt_nr_inodes,
Opt_mode, Opt_uid, Opt_gid,
Opt_pagesize, Opt_min_size,
Opt_err,
};
static const match_table_t tokens = {
{Opt_size, "size=%s"},
{Opt_nr_inodes, "nr_inodes=%s"},
{Opt_mode, "mode=%o"},
{Opt_uid, "uid=%u"},
{Opt_gid, "gid=%u"},
{Opt_pagesize, "pagesize=%s"},
{Opt_min_size, "min_size=%s"},
{Opt_err, NULL},
};
#ifdef CONFIG_NUMA
static inline void hugetlb_set_vma_policy(struct vm_area_struct *vma,
struct inode *inode, pgoff_t index)
{
vma->vm_policy = mpol_shared_policy_lookup(&HUGETLBFS_I(inode)->policy,
index);
}
static inline void hugetlb_drop_vma_policy(struct vm_area_struct *vma)
{
mpol_cond_put(vma->vm_policy);
}
#else
static inline void hugetlb_set_vma_policy(struct vm_area_struct *vma,
struct inode *inode, pgoff_t index)
{
}
static inline void hugetlb_drop_vma_policy(struct vm_area_struct *vma)
{
}
#endif
static void huge_pagevec_release(struct pagevec *pvec)
{
int i;
for (i = 0; i < pagevec_count(pvec); ++i)
put_page(pvec->pages[i]);
pagevec_reinit(pvec);
}
static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma)
{
struct inode *inode = file_inode(file);
loff_t len, vma_len;
int ret;
struct hstate *h = hstate_file(file);
[PATCH] hugetlb: prepare_hugepage_range check offset too (David:) If hugetlbfs_file_mmap() returns a failure to do_mmap_pgoff() - for example, because the given file offset is not hugepage aligned - then do_mmap_pgoff will go to the unmap_and_free_vma backout path. But at this stage the vma hasn't been marked as hugepage, and the backout path will call unmap_region() on it. That will eventually call down to the non-hugepage version of unmap_page_range(). On ppc64, at least, that will cause serious problems if there are any existing hugepage pagetable entries in the vicinity - for example if there are any other hugepage mappings under the same PUD. unmap_page_range() will trigger a bad_pud() on the hugepage pud entries. I suspect this will also cause bad problems on ia64, though I don't have a machine to test it on. (Hugh:) prepare_hugepage_range() should check file offset alignment when it checks virtual address and length, to stop MAP_FIXED with a bad huge offset from unmapping before it fails further down. PowerPC should apply the same prepare_hugepage_range alignment checks as ia64 and all the others do. Then none of the alignment checks in hugetlbfs_file_mmap are required (nor is the check for too small a mapping); but even so, move up setting of VM_HUGETLB and add a comment to warn of what David Gibson discovered - if hugetlbfs_file_mmap fails before setting it, do_mmap_pgoff's unmap_region when unwinding from error will go the non-huge way, which may cause bad behaviour on architectures (powerpc and ia64) which segregate their huge mappings into a separate region of the address space. Signed-off-by: Hugh Dickins <hugh@veritas.com> Cc: "Luck, Tony" <tony.luck@intel.com> Cc: "David S. Miller" <davem@davemloft.net> Acked-by: Adam Litke <agl@us.ibm.com> Acked-by: David Gibson <david@gibson.dropbear.id.au> Cc: Paul Mackerras <paulus@samba.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-11-14 17:03:32 +07:00
/*
* vma address alignment (but not the pgoff alignment) has
* already been checked by prepare_hugepage_range. If you add
* any error returns here, do so after setting VM_HUGETLB, so
* is_vm_hugetlb_page tests below unmap_region go the right
* way when do_mmap_pgoff unwinds (may be important on powerpc
* and ia64).
[PATCH] hugetlb: prepare_hugepage_range check offset too (David:) If hugetlbfs_file_mmap() returns a failure to do_mmap_pgoff() - for example, because the given file offset is not hugepage aligned - then do_mmap_pgoff will go to the unmap_and_free_vma backout path. But at this stage the vma hasn't been marked as hugepage, and the backout path will call unmap_region() on it. That will eventually call down to the non-hugepage version of unmap_page_range(). On ppc64, at least, that will cause serious problems if there are any existing hugepage pagetable entries in the vicinity - for example if there are any other hugepage mappings under the same PUD. unmap_page_range() will trigger a bad_pud() on the hugepage pud entries. I suspect this will also cause bad problems on ia64, though I don't have a machine to test it on. (Hugh:) prepare_hugepage_range() should check file offset alignment when it checks virtual address and length, to stop MAP_FIXED with a bad huge offset from unmapping before it fails further down. PowerPC should apply the same prepare_hugepage_range alignment checks as ia64 and all the others do. Then none of the alignment checks in hugetlbfs_file_mmap are required (nor is the check for too small a mapping); but even so, move up setting of VM_HUGETLB and add a comment to warn of what David Gibson discovered - if hugetlbfs_file_mmap fails before setting it, do_mmap_pgoff's unmap_region when unwinding from error will go the non-huge way, which may cause bad behaviour on architectures (powerpc and ia64) which segregate their huge mappings into a separate region of the address space. Signed-off-by: Hugh Dickins <hugh@veritas.com> Cc: "Luck, Tony" <tony.luck@intel.com> Cc: "David S. Miller" <davem@davemloft.net> Acked-by: Adam Litke <agl@us.ibm.com> Acked-by: David Gibson <david@gibson.dropbear.id.au> Cc: Paul Mackerras <paulus@samba.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-11-14 17:03:32 +07:00
*/
vma->vm_flags |= VM_HUGETLB | VM_DONTEXPAND;
[PATCH] hugetlb: prepare_hugepage_range check offset too (David:) If hugetlbfs_file_mmap() returns a failure to do_mmap_pgoff() - for example, because the given file offset is not hugepage aligned - then do_mmap_pgoff will go to the unmap_and_free_vma backout path. But at this stage the vma hasn't been marked as hugepage, and the backout path will call unmap_region() on it. That will eventually call down to the non-hugepage version of unmap_page_range(). On ppc64, at least, that will cause serious problems if there are any existing hugepage pagetable entries in the vicinity - for example if there are any other hugepage mappings under the same PUD. unmap_page_range() will trigger a bad_pud() on the hugepage pud entries. I suspect this will also cause bad problems on ia64, though I don't have a machine to test it on. (Hugh:) prepare_hugepage_range() should check file offset alignment when it checks virtual address and length, to stop MAP_FIXED with a bad huge offset from unmapping before it fails further down. PowerPC should apply the same prepare_hugepage_range alignment checks as ia64 and all the others do. Then none of the alignment checks in hugetlbfs_file_mmap are required (nor is the check for too small a mapping); but even so, move up setting of VM_HUGETLB and add a comment to warn of what David Gibson discovered - if hugetlbfs_file_mmap fails before setting it, do_mmap_pgoff's unmap_region when unwinding from error will go the non-huge way, which may cause bad behaviour on architectures (powerpc and ia64) which segregate their huge mappings into a separate region of the address space. Signed-off-by: Hugh Dickins <hugh@veritas.com> Cc: "Luck, Tony" <tony.luck@intel.com> Cc: "David S. Miller" <davem@davemloft.net> Acked-by: Adam Litke <agl@us.ibm.com> Acked-by: David Gibson <david@gibson.dropbear.id.au> Cc: Paul Mackerras <paulus@samba.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-11-14 17:03:32 +07:00
vma->vm_ops = &hugetlb_vm_ops;
hugetlbfs: fix offset overflow in hugetlbfs mmap If mmap() maps a file, it can be passed an offset into the file at which the mapping is to start. Offset could be a negative value when represented as a loff_t. The offset plus length will be used to update the file size (i_size) which is also a loff_t. Validate the value of offset and offset + length to make sure they do not overflow and appear as negative. Found by syzcaller with commit ff8c0c53c475 ("mm/hugetlb.c: don't call region_abort if region_chg fails") applied. Prior to this commit, the overflow would still occur but we would luckily return ENOMEM. To reproduce: mmap(0, 0x2000, 0, 0x40021, 0xffffffffffffffffULL, 0x8000000000000000ULL); Resulted in, kernel BUG at mm/hugetlb.c:742! Call Trace: hugetlbfs_evict_inode+0x80/0xa0 evict+0x24a/0x620 iput+0x48f/0x8c0 dentry_unlink_inode+0x31f/0x4d0 __dentry_kill+0x292/0x5e0 dput+0x730/0x830 __fput+0x438/0x720 ____fput+0x1a/0x20 task_work_run+0xfe/0x180 exit_to_usermode_loop+0x133/0x150 syscall_return_slowpath+0x184/0x1c0 entry_SYSCALL_64_fastpath+0xab/0xad Fixes: ff8c0c53c475 ("mm/hugetlb.c: don't call region_abort if region_chg fails") Link: http://lkml.kernel.org/r/1491951118-30678-1-git-send-email-mike.kravetz@oracle.com Reported-by: Vegard Nossum <vegard.nossum@oracle.com> Signed-off-by: Mike Kravetz <mike.kravetz@oracle.com> Acked-by: Hillf Danton <hillf.zj@alibaba-inc.com> Cc: Dmitry Vyukov <dvyukov@google.com> Cc: Michal Hocko <mhocko@suse.com> Cc: "Kirill A . Shutemov" <kirill.shutemov@linux.intel.com> Cc: Andrey Ryabinin <aryabinin@virtuozzo.com> Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-04-14 04:56:32 +07:00
/*
* Offset passed to mmap (before page shift) could have been
* negative when represented as a (l)off_t.
*/
if (((loff_t)vma->vm_pgoff << PAGE_SHIFT) < 0)
return -EINVAL;
if (vma->vm_pgoff & (~huge_page_mask(h) >> PAGE_SHIFT))
return -EINVAL;
vma_len = (loff_t)(vma->vm_end - vma->vm_start);
hugetlbfs: fix offset overflow in hugetlbfs mmap If mmap() maps a file, it can be passed an offset into the file at which the mapping is to start. Offset could be a negative value when represented as a loff_t. The offset plus length will be used to update the file size (i_size) which is also a loff_t. Validate the value of offset and offset + length to make sure they do not overflow and appear as negative. Found by syzcaller with commit ff8c0c53c475 ("mm/hugetlb.c: don't call region_abort if region_chg fails") applied. Prior to this commit, the overflow would still occur but we would luckily return ENOMEM. To reproduce: mmap(0, 0x2000, 0, 0x40021, 0xffffffffffffffffULL, 0x8000000000000000ULL); Resulted in, kernel BUG at mm/hugetlb.c:742! Call Trace: hugetlbfs_evict_inode+0x80/0xa0 evict+0x24a/0x620 iput+0x48f/0x8c0 dentry_unlink_inode+0x31f/0x4d0 __dentry_kill+0x292/0x5e0 dput+0x730/0x830 __fput+0x438/0x720 ____fput+0x1a/0x20 task_work_run+0xfe/0x180 exit_to_usermode_loop+0x133/0x150 syscall_return_slowpath+0x184/0x1c0 entry_SYSCALL_64_fastpath+0xab/0xad Fixes: ff8c0c53c475 ("mm/hugetlb.c: don't call region_abort if region_chg fails") Link: http://lkml.kernel.org/r/1491951118-30678-1-git-send-email-mike.kravetz@oracle.com Reported-by: Vegard Nossum <vegard.nossum@oracle.com> Signed-off-by: Mike Kravetz <mike.kravetz@oracle.com> Acked-by: Hillf Danton <hillf.zj@alibaba-inc.com> Cc: Dmitry Vyukov <dvyukov@google.com> Cc: Michal Hocko <mhocko@suse.com> Cc: "Kirill A . Shutemov" <kirill.shutemov@linux.intel.com> Cc: Andrey Ryabinin <aryabinin@virtuozzo.com> Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-04-14 04:56:32 +07:00
len = vma_len + ((loff_t)vma->vm_pgoff << PAGE_SHIFT);
/* check for overflow */
if (len < vma_len)
return -EINVAL;
inode_lock(inode);
file_accessed(file);
ret = -ENOMEM;
hugetlb: reserve huge pages for reliable MAP_PRIVATE hugetlbfs mappings until fork() This patch reserves huge pages at mmap() time for MAP_PRIVATE mappings in a similar manner to the reservations taken for MAP_SHARED mappings. The reserve count is accounted both globally and on a per-VMA basis for private mappings. This guarantees that a process that successfully calls mmap() will successfully fault all pages in the future unless fork() is called. The characteristics of private mappings of hugetlbfs files behaviour after this patch are; 1. The process calling mmap() is guaranteed to succeed all future faults until it forks(). 2. On fork(), the parent may die due to SIGKILL on writes to the private mapping if enough pages are not available for the COW. For reasonably reliable behaviour in the face of a small huge page pool, children of hugepage-aware processes should not reference the mappings; such as might occur when fork()ing to exec(). 3. On fork(), the child VMAs inherit no reserves. Reads on pages already faulted by the parent will succeed. Successful writes will depend on enough huge pages being free in the pool. 4. Quotas of the hugetlbfs mount are checked at reserve time for the mapper and at fault time otherwise. Before this patch, all reads or writes in the child potentially needs page allocations that can later lead to the death of the parent. This applies to reads and writes of uninstantiated pages as well as COW. After the patch it is only a write to an instantiated page that causes problems. Signed-off-by: Mel Gorman <mel@csn.ul.ie> Acked-by: Adam Litke <agl@us.ibm.com> Cc: Andy Whitcroft <apw@shadowen.org> Cc: William Lee Irwin III <wli@holomorphy.com> Cc: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-24 11:27:23 +07:00
if (hugetlb_reserve_pages(inode,
vma->vm_pgoff >> huge_page_order(h),
Do not account for the address space used by hugetlbfs using VM_ACCOUNT When overcommit is disabled, the core VM accounts for pages used by anonymous shared, private mappings and special mappings. It keeps track of VMAs that should be accounted for with VM_ACCOUNT and VMAs that never had a reserve with VM_NORESERVE. Overcommit for hugetlbfs is much riskier than overcommit for base pages due to contiguity requirements. It avoids overcommiting on both shared and private mappings using reservation counters that are checked and updated during mmap(). This ensures (within limits) that hugepages exist in the future when faults occurs or it is too easy to applications to be SIGKILLed. As hugetlbfs makes its own reservations of a different unit to the base page size, VM_ACCOUNT should never be set. Even if the units were correct, we would double account for the usage in the core VM and hugetlbfs. VM_NORESERVE may be set because an application can request no reserves be made for hugetlbfs at the risk of getting killed later. With commit fc8744adc870a8d4366908221508bb113d8b72ee, VM_NORESERVE and VM_ACCOUNT are getting unconditionally set for hugetlbfs-backed mappings. This breaks the accounting for both the core VM and hugetlbfs, can trigger an OOM storm when hugepage pools are too small lockups and corrupted counters otherwise are used. This patch brings hugetlbfs more in line with how the core VM treats VM_NORESERVE but prevents VM_ACCOUNT being set. Signed-off-by: Mel Gorman <mel@csn.ul.ie> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-02-10 21:02:27 +07:00
len >> huge_page_shift(h), vma,
vma->vm_flags))
goto out;
[PATCH] hugepage: Strict page reservation for hugepage inodes These days, hugepages are demand-allocated at first fault time. There's a somewhat dubious (and racy) heuristic when making a new mmap() to check if there are enough available hugepages to fully satisfy that mapping. A particularly obvious case where the heuristic breaks down is where a process maps its hugepages not as a single chunk, but as a bunch of individually mmap()ed (or shmat()ed) blocks without touching and instantiating the pages in between allocations. In this case the size of each block is compared against the total number of available hugepages. It's thus easy for the process to become overcommitted, because each block mapping will succeed, although the total number of hugepages required by all blocks exceeds the number available. In particular, this defeats such a program which will detect a mapping failure and adjust its hugepage usage downward accordingly. The patch below addresses this problem, by strictly reserving a number of physical hugepages for hugepage inodes which have been mapped, but not instatiated. MAP_SHARED mappings are thus "safe" - they will fail on mmap(), not later with an OOM SIGKILL. MAP_PRIVATE mappings can still trigger an OOM. (Actually SHARED mappings can technically still OOM, but only if the sysadmin explicitly reduces the hugepage pool between mapping and instantiation) This patch appears to address the problem at hand - it allows DB2 to start correctly, for instance, which previously suffered the failure described above. This patch causes no regressions on the libhugetblfs testsuite, and makes a test (designed to catch this problem) pass which previously failed (ppc64, POWER5). Signed-off-by: David Gibson <dwg@au1.ibm.com> Cc: William Lee Irwin III <wli@holomorphy.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-22 15:08:55 +07:00
ret = 0;
if (vma->vm_flags & VM_WRITE && inode->i_size < len)
hugetlbfs: fix offset overflow in hugetlbfs mmap If mmap() maps a file, it can be passed an offset into the file at which the mapping is to start. Offset could be a negative value when represented as a loff_t. The offset plus length will be used to update the file size (i_size) which is also a loff_t. Validate the value of offset and offset + length to make sure they do not overflow and appear as negative. Found by syzcaller with commit ff8c0c53c475 ("mm/hugetlb.c: don't call region_abort if region_chg fails") applied. Prior to this commit, the overflow would still occur but we would luckily return ENOMEM. To reproduce: mmap(0, 0x2000, 0, 0x40021, 0xffffffffffffffffULL, 0x8000000000000000ULL); Resulted in, kernel BUG at mm/hugetlb.c:742! Call Trace: hugetlbfs_evict_inode+0x80/0xa0 evict+0x24a/0x620 iput+0x48f/0x8c0 dentry_unlink_inode+0x31f/0x4d0 __dentry_kill+0x292/0x5e0 dput+0x730/0x830 __fput+0x438/0x720 ____fput+0x1a/0x20 task_work_run+0xfe/0x180 exit_to_usermode_loop+0x133/0x150 syscall_return_slowpath+0x184/0x1c0 entry_SYSCALL_64_fastpath+0xab/0xad Fixes: ff8c0c53c475 ("mm/hugetlb.c: don't call region_abort if region_chg fails") Link: http://lkml.kernel.org/r/1491951118-30678-1-git-send-email-mike.kravetz@oracle.com Reported-by: Vegard Nossum <vegard.nossum@oracle.com> Signed-off-by: Mike Kravetz <mike.kravetz@oracle.com> Acked-by: Hillf Danton <hillf.zj@alibaba-inc.com> Cc: Dmitry Vyukov <dvyukov@google.com> Cc: Michal Hocko <mhocko@suse.com> Cc: "Kirill A . Shutemov" <kirill.shutemov@linux.intel.com> Cc: Andrey Ryabinin <aryabinin@virtuozzo.com> Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-04-14 04:56:32 +07:00
i_size_write(inode, len);
out:
inode_unlock(inode);
return ret;
}
/*
* Called under down_write(mmap_sem).
*/
#ifndef HAVE_ARCH_HUGETLB_UNMAPPED_AREA
static unsigned long
hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
unsigned long len, unsigned long pgoff, unsigned long flags)
{
struct mm_struct *mm = current->mm;
struct vm_area_struct *vma;
struct hstate *h = hstate_file(file);
struct vm_unmapped_area_info info;
if (len & ~huge_page_mask(h))
return -EINVAL;
if (len > TASK_SIZE)
return -ENOMEM;
if (flags & MAP_FIXED) {
if (prepare_hugepage_range(file, addr, len))
return -EINVAL;
return addr;
}
if (addr) {
addr = ALIGN(addr, huge_page_size(h));
vma = find_vma(mm, addr);
if (TASK_SIZE - len >= addr &&
mm: larger stack guard gap, between vmas Stack guard page is a useful feature to reduce a risk of stack smashing into a different mapping. We have been using a single page gap which is sufficient to prevent having stack adjacent to a different mapping. But this seems to be insufficient in the light of the stack usage in userspace. E.g. glibc uses as large as 64kB alloca() in many commonly used functions. Others use constructs liks gid_t buffer[NGROUPS_MAX] which is 256kB or stack strings with MAX_ARG_STRLEN. This will become especially dangerous for suid binaries and the default no limit for the stack size limit because those applications can be tricked to consume a large portion of the stack and a single glibc call could jump over the guard page. These attacks are not theoretical, unfortunatelly. Make those attacks less probable by increasing the stack guard gap to 1MB (on systems with 4k pages; but make it depend on the page size because systems with larger base pages might cap stack allocations in the PAGE_SIZE units) which should cover larger alloca() and VLA stack allocations. It is obviously not a full fix because the problem is somehow inherent, but it should reduce attack space a lot. One could argue that the gap size should be configurable from userspace, but that can be done later when somebody finds that the new 1MB is wrong for some special case applications. For now, add a kernel command line option (stack_guard_gap) to specify the stack gap size (in page units). Implementation wise, first delete all the old code for stack guard page: because although we could get away with accounting one extra page in a stack vma, accounting a larger gap can break userspace - case in point, a program run with "ulimit -S -v 20000" failed when the 1MB gap was counted for RLIMIT_AS; similar problems could come with RLIMIT_MLOCK and strict non-overcommit mode. Instead of keeping gap inside the stack vma, maintain the stack guard gap as a gap between vmas: using vm_start_gap() in place of vm_start (or vm_end_gap() in place of vm_end if VM_GROWSUP) in just those few places which need to respect the gap - mainly arch_get_unmapped_area(), and and the vma tree's subtree_gap support for that. Original-patch-by: Oleg Nesterov <oleg@redhat.com> Original-patch-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Hugh Dickins <hughd@google.com> Acked-by: Michal Hocko <mhocko@suse.com> Tested-by: Helge Deller <deller@gmx.de> # parisc Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-06-19 18:03:24 +07:00
(!vma || addr + len <= vm_start_gap(vma)))
return addr;
}
info.flags = 0;
info.length = len;
info.low_limit = TASK_UNMAPPED_BASE;
info.high_limit = TASK_SIZE;
info.align_mask = PAGE_MASK & ~huge_page_mask(h);
info.align_offset = 0;
return vm_unmapped_area(&info);
}
#endif
static size_t
hugetlbfs_read_actor(struct page *page, unsigned long offset,
struct iov_iter *to, unsigned long size)
{
size_t copied = 0;
int i, chunksize;
/* Find which 4k chunk and offset with in that chunk */
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time ago with promise that one day it will be possible to implement page cache with bigger chunks than PAGE_SIZE. This promise never materialized. And unlikely will. We have many places where PAGE_CACHE_SIZE assumed to be equal to PAGE_SIZE. And it's constant source of confusion on whether PAGE_CACHE_* or PAGE_* constant should be used in a particular case, especially on the border between fs and mm. Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much breakage to be doable. Let's stop pretending that pages in page cache are special. They are not. The changes are pretty straight-forward: - <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN}; - page_cache_get() -> get_page(); - page_cache_release() -> put_page(); This patch contains automated changes generated with coccinelle using script below. For some reason, coccinelle doesn't patch header files. I've called spatch for them manually. The only adjustment after coccinelle is revert of changes to PAGE_CAHCE_ALIGN definition: we are going to drop it later. There are few places in the code where coccinelle didn't reach. I'll fix them manually in a separate patch. Comments and documentation also will be addressed with the separate patch. virtual patch @@ expression E; @@ - E << (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ expression E; @@ - E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ @@ - PAGE_CACHE_SHIFT + PAGE_SHIFT @@ @@ - PAGE_CACHE_SIZE + PAGE_SIZE @@ @@ - PAGE_CACHE_MASK + PAGE_MASK @@ expression E; @@ - PAGE_CACHE_ALIGN(E) + PAGE_ALIGN(E) @@ expression E; @@ - page_cache_get(E) + get_page(E) @@ expression E; @@ - page_cache_release(E) + put_page(E) Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 19:29:47 +07:00
i = offset >> PAGE_SHIFT;
offset = offset & ~PAGE_MASK;
while (size) {
size_t n;
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time ago with promise that one day it will be possible to implement page cache with bigger chunks than PAGE_SIZE. This promise never materialized. And unlikely will. We have many places where PAGE_CACHE_SIZE assumed to be equal to PAGE_SIZE. And it's constant source of confusion on whether PAGE_CACHE_* or PAGE_* constant should be used in a particular case, especially on the border between fs and mm. Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much breakage to be doable. Let's stop pretending that pages in page cache are special. They are not. The changes are pretty straight-forward: - <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN}; - page_cache_get() -> get_page(); - page_cache_release() -> put_page(); This patch contains automated changes generated with coccinelle using script below. For some reason, coccinelle doesn't patch header files. I've called spatch for them manually. The only adjustment after coccinelle is revert of changes to PAGE_CAHCE_ALIGN definition: we are going to drop it later. There are few places in the code where coccinelle didn't reach. I'll fix them manually in a separate patch. Comments and documentation also will be addressed with the separate patch. virtual patch @@ expression E; @@ - E << (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ expression E; @@ - E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ @@ - PAGE_CACHE_SHIFT + PAGE_SHIFT @@ @@ - PAGE_CACHE_SIZE + PAGE_SIZE @@ @@ - PAGE_CACHE_MASK + PAGE_MASK @@ expression E; @@ - PAGE_CACHE_ALIGN(E) + PAGE_ALIGN(E) @@ expression E; @@ - page_cache_get(E) + get_page(E) @@ expression E; @@ - page_cache_release(E) + put_page(E) Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 19:29:47 +07:00
chunksize = PAGE_SIZE;
if (offset)
chunksize -= offset;
if (chunksize > size)
chunksize = size;
n = copy_page_to_iter(&page[i], offset, chunksize, to);
copied += n;
if (n != chunksize)
return copied;
offset = 0;
size -= chunksize;
i++;
}
return copied;
}
/*
* Support for read() - Find the page attached to f_mapping and copy out the
* data. Its *very* similar to do_generic_mapping_read(), we can't use that
* since it has PAGE_SIZE assumptions.
*/
static ssize_t hugetlbfs_read_iter(struct kiocb *iocb, struct iov_iter *to)
{
struct file *file = iocb->ki_filp;
struct hstate *h = hstate_file(file);
struct address_space *mapping = file->f_mapping;
struct inode *inode = mapping->host;
unsigned long index = iocb->ki_pos >> huge_page_shift(h);
unsigned long offset = iocb->ki_pos & ~huge_page_mask(h);
unsigned long end_index;
loff_t isize;
ssize_t retval = 0;
while (iov_iter_count(to)) {
struct page *page;
size_t nr, copied;
/* nr is the maximum number of bytes to copy from this page */
nr = huge_page_size(h);
hugetlbfs: avoid taking i_mutex from hugetlbfs_read() Taking i_mutex in hugetlbfs_read() can result in deadlock with mmap as explained below Thread A: read() on hugetlbfs hugetlbfs_read() called i_mutex grabbed hugetlbfs_read_actor() called __copy_to_user() called page fault is triggered Thread B, sharing address space with A: mmap() the same file ->mmap_sem is grabbed on task_B->mm->mmap_sem hugetlbfs_file_mmap() is called attempt to grab ->i_mutex and block waiting for A to give it up Thread A: pagefault handled blocked on attempt to grab task_A->mm->mmap_sem, which happens to be the same thing as task_B->mm->mmap_sem. Block waiting for B to give it up. AFAIU the i_mutex locking was added to hugetlbfs_read() as per http://lkml.indiana.edu/hypermail/linux/kernel/0707.2/3066.html to take care of the race between truncate and read. This patch fixes this by looking at page->mapping under lock_page() (find_lock_page()) to ensure that the inode didn't get truncated in the range during a parallel read. Ideally we can extend the patch to make sure we don't increase i_size in mmap. But that will break userspace, because applications will now have to use truncate(2) to increase i_size in hugetlbfs. Based on the original patch from Hillf Danton. Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> Cc: Hillf Danton <dhillf@gmail.com> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Hugh Dickins <hughd@google.com> Cc: <stable@kernel.org> [everything after 2007 :)] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-03-22 06:34:08 +07:00
isize = i_size_read(inode);
if (!isize)
break;
hugetlbfs: avoid taking i_mutex from hugetlbfs_read() Taking i_mutex in hugetlbfs_read() can result in deadlock with mmap as explained below Thread A: read() on hugetlbfs hugetlbfs_read() called i_mutex grabbed hugetlbfs_read_actor() called __copy_to_user() called page fault is triggered Thread B, sharing address space with A: mmap() the same file ->mmap_sem is grabbed on task_B->mm->mmap_sem hugetlbfs_file_mmap() is called attempt to grab ->i_mutex and block waiting for A to give it up Thread A: pagefault handled blocked on attempt to grab task_A->mm->mmap_sem, which happens to be the same thing as task_B->mm->mmap_sem. Block waiting for B to give it up. AFAIU the i_mutex locking was added to hugetlbfs_read() as per http://lkml.indiana.edu/hypermail/linux/kernel/0707.2/3066.html to take care of the race between truncate and read. This patch fixes this by looking at page->mapping under lock_page() (find_lock_page()) to ensure that the inode didn't get truncated in the range during a parallel read. Ideally we can extend the patch to make sure we don't increase i_size in mmap. But that will break userspace, because applications will now have to use truncate(2) to increase i_size in hugetlbfs. Based on the original patch from Hillf Danton. Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> Cc: Hillf Danton <dhillf@gmail.com> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Hugh Dickins <hughd@google.com> Cc: <stable@kernel.org> [everything after 2007 :)] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-03-22 06:34:08 +07:00
end_index = (isize - 1) >> huge_page_shift(h);
if (index > end_index)
break;
if (index == end_index) {
nr = ((isize - 1) & ~huge_page_mask(h)) + 1;
hugetlbfs: avoid taking i_mutex from hugetlbfs_read() Taking i_mutex in hugetlbfs_read() can result in deadlock with mmap as explained below Thread A: read() on hugetlbfs hugetlbfs_read() called i_mutex grabbed hugetlbfs_read_actor() called __copy_to_user() called page fault is triggered Thread B, sharing address space with A: mmap() the same file ->mmap_sem is grabbed on task_B->mm->mmap_sem hugetlbfs_file_mmap() is called attempt to grab ->i_mutex and block waiting for A to give it up Thread A: pagefault handled blocked on attempt to grab task_A->mm->mmap_sem, which happens to be the same thing as task_B->mm->mmap_sem. Block waiting for B to give it up. AFAIU the i_mutex locking was added to hugetlbfs_read() as per http://lkml.indiana.edu/hypermail/linux/kernel/0707.2/3066.html to take care of the race between truncate and read. This patch fixes this by looking at page->mapping under lock_page() (find_lock_page()) to ensure that the inode didn't get truncated in the range during a parallel read. Ideally we can extend the patch to make sure we don't increase i_size in mmap. But that will break userspace, because applications will now have to use truncate(2) to increase i_size in hugetlbfs. Based on the original patch from Hillf Danton. Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> Cc: Hillf Danton <dhillf@gmail.com> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Hugh Dickins <hughd@google.com> Cc: <stable@kernel.org> [everything after 2007 :)] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-03-22 06:34:08 +07:00
if (nr <= offset)
break;
}
nr = nr - offset;
/* Find the page */
hugetlbfs: avoid taking i_mutex from hugetlbfs_read() Taking i_mutex in hugetlbfs_read() can result in deadlock with mmap as explained below Thread A: read() on hugetlbfs hugetlbfs_read() called i_mutex grabbed hugetlbfs_read_actor() called __copy_to_user() called page fault is triggered Thread B, sharing address space with A: mmap() the same file ->mmap_sem is grabbed on task_B->mm->mmap_sem hugetlbfs_file_mmap() is called attempt to grab ->i_mutex and block waiting for A to give it up Thread A: pagefault handled blocked on attempt to grab task_A->mm->mmap_sem, which happens to be the same thing as task_B->mm->mmap_sem. Block waiting for B to give it up. AFAIU the i_mutex locking was added to hugetlbfs_read() as per http://lkml.indiana.edu/hypermail/linux/kernel/0707.2/3066.html to take care of the race between truncate and read. This patch fixes this by looking at page->mapping under lock_page() (find_lock_page()) to ensure that the inode didn't get truncated in the range during a parallel read. Ideally we can extend the patch to make sure we don't increase i_size in mmap. But that will break userspace, because applications will now have to use truncate(2) to increase i_size in hugetlbfs. Based on the original patch from Hillf Danton. Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> Cc: Hillf Danton <dhillf@gmail.com> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Hugh Dickins <hughd@google.com> Cc: <stable@kernel.org> [everything after 2007 :)] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-03-22 06:34:08 +07:00
page = find_lock_page(mapping, index);
if (unlikely(page == NULL)) {
/*
* We have a HOLE, zero out the user-buffer for the
* length of the hole or request.
*/
copied = iov_iter_zero(nr, to);
} else {
hugetlbfs: avoid taking i_mutex from hugetlbfs_read() Taking i_mutex in hugetlbfs_read() can result in deadlock with mmap as explained below Thread A: read() on hugetlbfs hugetlbfs_read() called i_mutex grabbed hugetlbfs_read_actor() called __copy_to_user() called page fault is triggered Thread B, sharing address space with A: mmap() the same file ->mmap_sem is grabbed on task_B->mm->mmap_sem hugetlbfs_file_mmap() is called attempt to grab ->i_mutex and block waiting for A to give it up Thread A: pagefault handled blocked on attempt to grab task_A->mm->mmap_sem, which happens to be the same thing as task_B->mm->mmap_sem. Block waiting for B to give it up. AFAIU the i_mutex locking was added to hugetlbfs_read() as per http://lkml.indiana.edu/hypermail/linux/kernel/0707.2/3066.html to take care of the race between truncate and read. This patch fixes this by looking at page->mapping under lock_page() (find_lock_page()) to ensure that the inode didn't get truncated in the range during a parallel read. Ideally we can extend the patch to make sure we don't increase i_size in mmap. But that will break userspace, because applications will now have to use truncate(2) to increase i_size in hugetlbfs. Based on the original patch from Hillf Danton. Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> Cc: Hillf Danton <dhillf@gmail.com> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Hugh Dickins <hughd@google.com> Cc: <stable@kernel.org> [everything after 2007 :)] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-03-22 06:34:08 +07:00
unlock_page(page);
/*
* We have the page, copy it to user space buffer.
*/
copied = hugetlbfs_read_actor(page, offset, to, nr);
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time ago with promise that one day it will be possible to implement page cache with bigger chunks than PAGE_SIZE. This promise never materialized. And unlikely will. We have many places where PAGE_CACHE_SIZE assumed to be equal to PAGE_SIZE. And it's constant source of confusion on whether PAGE_CACHE_* or PAGE_* constant should be used in a particular case, especially on the border between fs and mm. Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much breakage to be doable. Let's stop pretending that pages in page cache are special. They are not. The changes are pretty straight-forward: - <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN}; - page_cache_get() -> get_page(); - page_cache_release() -> put_page(); This patch contains automated changes generated with coccinelle using script below. For some reason, coccinelle doesn't patch header files. I've called spatch for them manually. The only adjustment after coccinelle is revert of changes to PAGE_CAHCE_ALIGN definition: we are going to drop it later. There are few places in the code where coccinelle didn't reach. I'll fix them manually in a separate patch. Comments and documentation also will be addressed with the separate patch. virtual patch @@ expression E; @@ - E << (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ expression E; @@ - E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ @@ - PAGE_CACHE_SHIFT + PAGE_SHIFT @@ @@ - PAGE_CACHE_SIZE + PAGE_SIZE @@ @@ - PAGE_CACHE_MASK + PAGE_MASK @@ expression E; @@ - PAGE_CACHE_ALIGN(E) + PAGE_ALIGN(E) @@ expression E; @@ - page_cache_get(E) + get_page(E) @@ expression E; @@ - page_cache_release(E) + put_page(E) Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 19:29:47 +07:00
put_page(page);
}
offset += copied;
retval += copied;
if (copied != nr && iov_iter_count(to)) {
if (!retval)
retval = -EFAULT;
break;
}
index += offset >> huge_page_shift(h);
offset &= ~huge_page_mask(h);
}
iocb->ki_pos = ((loff_t)index << huge_page_shift(h)) + offset;
return retval;
}
static int hugetlbfs_write_begin(struct file *file,
struct address_space *mapping,
loff_t pos, unsigned len, unsigned flags,
struct page **pagep, void **fsdata)
{
return -EINVAL;
}
static int hugetlbfs_write_end(struct file *file, struct address_space *mapping,
loff_t pos, unsigned len, unsigned copied,
struct page *page, void *fsdata)
{
BUG();
return -EINVAL;
}
hugetlbfs: truncate_hugepages() takes a range of pages Modify truncate_hugepages() to take a range of pages (start, end) instead of simply start. If an end value of LLONG_MAX is passed, the current "truncate" functionality is maintained. Existing callers are modified to pass LLONG_MAX as end of range. By keying off end == LLONG_MAX, the routine behaves differently for truncate and hole punch. Page removal is now synchronized with page allocation via faults by using the fault mutex table. The hole punch case can experience the rare region_del error and must handle accordingly. Add the routine hugetlb_fix_reserve_counts to fix up reserve counts in the case where region_del returns an error. Since the routine handles more than just the truncate case, it is renamed to remove_inode_hugepages(). To be consistent, the routine truncate_huge_page() is renamed remove_huge_page(). Downstream of remove_inode_hugepages(), the routine hugetlb_unreserve_pages() is also modified to take a range of pages. hugetlb_unreserve_pages is modified to detect an error from region_del and pass it back to the caller. Signed-off-by: Mike Kravetz <mike.kravetz@oracle.com> Reviewed-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Acked-by: Hillf Danton <hillf.zj@alibaba-inc.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David Rientjes <rientjes@google.com> Cc: Hugh Dickins <hughd@google.com> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Aneesh Kumar <aneesh.kumar@linux.vnet.ibm.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Michal Hocko <mhocko@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-09-09 05:01:41 +07:00
static void remove_huge_page(struct page *page)
{
page_writeback: clean up mess around cancel_dirty_page() This patch replaces cancel_dirty_page() with a helper function account_page_cleaned() which only updates counters. It's called from truncate_complete_page() and from try_to_free_buffers() (hack for ext3). Page is locked in both cases, page-lock protects against concurrent dirtiers: see commit 2d6d7f982846 ("mm: protect set_page_dirty() from ongoing truncation"). Delete_from_page_cache() shouldn't be called for dirty pages, they must be handled by caller (either written or truncated). This patch treats final dirty accounting fixup at the end of __delete_from_page_cache() as a debug check and adds WARN_ON_ONCE() around it. If something removes dirty pages without proper handling that might be a bug and unwritten data might be lost. Hugetlbfs has no dirty pages accounting, ClearPageDirty() is enough here. cancel_dirty_page() in nfs_wb_page_cancel() is redundant. This is helper for nfs_invalidate_page() and it's called only in case complete invalidation. The mess was started in v2.6.20 after commits 46d2277c796f ("Clean up and make try_to_free_buffers() not race with dirty pages") and 3e67c0987d75 ("truncate: clear page dirtiness before running try_to_free_buffers()") first was reverted right in v2.6.20 in commit ecdfc9787fe5 ("Resurrect 'try_to_free_buffers()' VM hackery"), second in v2.6.25 commit a2b345642f53 ("Fix dirty page accounting leak with ext3 data=journal"). Custom fixes were introduced between these points. NFS in v2.6.23, commit 1b3b4a1a2deb ("NFS: Fix a write request leak in nfs_invalidate_page()"). Kludge in __delete_from_page_cache() in v2.6.24, commit 3a6927906f1b ("Do dirty page accounting when removing a page from the page cache"). Since v2.6.25 all of them are redundant. [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Konstantin Khlebnikov <khlebnikov@yandex-team.ru> Cc: Tejun Heo <tj@kernel.org> Cc: Jan Kara <jack@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-04-15 05:45:27 +07:00
ClearPageDirty(page);
ClearPageUptodate(page);
delete_from_page_cache(page);
}
static void
hugetlb_vmdelete_list(struct rb_root_cached *root, pgoff_t start, pgoff_t end)
{
struct vm_area_struct *vma;
/*
* end == 0 indicates that the entire range after
* start should be unmapped.
*/
vma_interval_tree_foreach(vma, root, start, end ? end : ULONG_MAX) {
unsigned long v_offset;
unsigned long v_end;
/*
* Can the expression below overflow on 32-bit arches?
* No, because the interval tree returns us only those vmas
* which overlap the truncated area starting at pgoff,
* and no vma on a 32-bit arch can span beyond the 4GB.
*/
if (vma->vm_pgoff < start)
v_offset = (start - vma->vm_pgoff) << PAGE_SHIFT;
else
v_offset = 0;
if (!end)
v_end = vma->vm_end;
else {
v_end = ((end - vma->vm_pgoff) << PAGE_SHIFT)
+ vma->vm_start;
if (v_end > vma->vm_end)
v_end = vma->vm_end;
}
unmap_hugepage_range(vma, vma->vm_start + v_offset, v_end,
NULL);
}
}
hugetlbfs: truncate_hugepages() takes a range of pages Modify truncate_hugepages() to take a range of pages (start, end) instead of simply start. If an end value of LLONG_MAX is passed, the current "truncate" functionality is maintained. Existing callers are modified to pass LLONG_MAX as end of range. By keying off end == LLONG_MAX, the routine behaves differently for truncate and hole punch. Page removal is now synchronized with page allocation via faults by using the fault mutex table. The hole punch case can experience the rare region_del error and must handle accordingly. Add the routine hugetlb_fix_reserve_counts to fix up reserve counts in the case where region_del returns an error. Since the routine handles more than just the truncate case, it is renamed to remove_inode_hugepages(). To be consistent, the routine truncate_huge_page() is renamed remove_huge_page(). Downstream of remove_inode_hugepages(), the routine hugetlb_unreserve_pages() is also modified to take a range of pages. hugetlb_unreserve_pages is modified to detect an error from region_del and pass it back to the caller. Signed-off-by: Mike Kravetz <mike.kravetz@oracle.com> Reviewed-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Acked-by: Hillf Danton <hillf.zj@alibaba-inc.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David Rientjes <rientjes@google.com> Cc: Hugh Dickins <hughd@google.com> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Aneesh Kumar <aneesh.kumar@linux.vnet.ibm.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Michal Hocko <mhocko@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-09-09 05:01:41 +07:00
/*
* remove_inode_hugepages handles two distinct cases: truncation and hole
* punch. There are subtle differences in operation for each case.
*
hugetlbfs: truncate_hugepages() takes a range of pages Modify truncate_hugepages() to take a range of pages (start, end) instead of simply start. If an end value of LLONG_MAX is passed, the current "truncate" functionality is maintained. Existing callers are modified to pass LLONG_MAX as end of range. By keying off end == LLONG_MAX, the routine behaves differently for truncate and hole punch. Page removal is now synchronized with page allocation via faults by using the fault mutex table. The hole punch case can experience the rare region_del error and must handle accordingly. Add the routine hugetlb_fix_reserve_counts to fix up reserve counts in the case where region_del returns an error. Since the routine handles more than just the truncate case, it is renamed to remove_inode_hugepages(). To be consistent, the routine truncate_huge_page() is renamed remove_huge_page(). Downstream of remove_inode_hugepages(), the routine hugetlb_unreserve_pages() is also modified to take a range of pages. hugetlb_unreserve_pages is modified to detect an error from region_del and pass it back to the caller. Signed-off-by: Mike Kravetz <mike.kravetz@oracle.com> Reviewed-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Acked-by: Hillf Danton <hillf.zj@alibaba-inc.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David Rientjes <rientjes@google.com> Cc: Hugh Dickins <hughd@google.com> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Aneesh Kumar <aneesh.kumar@linux.vnet.ibm.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Michal Hocko <mhocko@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-09-09 05:01:41 +07:00
* truncation is indicated by end of range being LLONG_MAX
* In this case, we first scan the range and release found pages.
* After releasing pages, hugetlb_unreserve_pages cleans up region/reserv
mm/hugetlbfs: fix bugs in fallocate hole punch of areas with holes Hugh Dickins pointed out problems with the new hugetlbfs fallocate hole punch code. These problems are in the routine remove_inode_hugepages and mostly occur in the case where there are holes in the range of pages to be removed. These holes could be the result of a previous hole punch or simply sparse allocation. The current code could access pages outside the specified range. remove_inode_hugepages handles both hole punch and truncate operations. Page index handling was fixed/cleaned up so that the loop index always matches the page being processed. The code now only makes a single pass through the range of pages as it was determined page faults could not race with truncate. A cond_resched() was added after removing up to PAGEVEC_SIZE pages. Some totally unnecessary code in hugetlbfs_fallocate() that remained from early development was also removed. Tested with fallocate tests submitted here: http://librelist.com/browser//libhugetlbfs/2015/6/25/patch-tests-add-tests-for-fallocate-system-call/ And, some ftruncate tests under development Fixes: b5cec28d36f5 ("hugetlbfs: truncate_hugepages() takes a range of pages") Signed-off-by: Mike Kravetz <mike.kravetz@oracle.com> Acked-by: Hugh Dickins <hughd@google.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: "Hillf Danton" <hillf.zj@alibaba-inc.com> Cc: <stable@vger.kernel.org> [4.3] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-11-21 06:57:13 +07:00
* maps and global counts. Page faults can not race with truncation
* in this routine. hugetlb_no_page() prevents page faults in the
* truncated range. It checks i_size before allocation, and again after
* with the page table lock for the page held. The same lock must be
* acquired to unmap a page.
hugetlbfs: truncate_hugepages() takes a range of pages Modify truncate_hugepages() to take a range of pages (start, end) instead of simply start. If an end value of LLONG_MAX is passed, the current "truncate" functionality is maintained. Existing callers are modified to pass LLONG_MAX as end of range. By keying off end == LLONG_MAX, the routine behaves differently for truncate and hole punch. Page removal is now synchronized with page allocation via faults by using the fault mutex table. The hole punch case can experience the rare region_del error and must handle accordingly. Add the routine hugetlb_fix_reserve_counts to fix up reserve counts in the case where region_del returns an error. Since the routine handles more than just the truncate case, it is renamed to remove_inode_hugepages(). To be consistent, the routine truncate_huge_page() is renamed remove_huge_page(). Downstream of remove_inode_hugepages(), the routine hugetlb_unreserve_pages() is also modified to take a range of pages. hugetlb_unreserve_pages is modified to detect an error from region_del and pass it back to the caller. Signed-off-by: Mike Kravetz <mike.kravetz@oracle.com> Reviewed-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Acked-by: Hillf Danton <hillf.zj@alibaba-inc.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David Rientjes <rientjes@google.com> Cc: Hugh Dickins <hughd@google.com> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Aneesh Kumar <aneesh.kumar@linux.vnet.ibm.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Michal Hocko <mhocko@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-09-09 05:01:41 +07:00
* hole punch is indicated if end is not LLONG_MAX
* In the hole punch case we scan the range and release found pages.
* Only when releasing a page is the associated region/reserv map
* deleted. The region/reserv map for ranges without associated
mm/hugetlbfs: fix bugs in fallocate hole punch of areas with holes Hugh Dickins pointed out problems with the new hugetlbfs fallocate hole punch code. These problems are in the routine remove_inode_hugepages and mostly occur in the case where there are holes in the range of pages to be removed. These holes could be the result of a previous hole punch or simply sparse allocation. The current code could access pages outside the specified range. remove_inode_hugepages handles both hole punch and truncate operations. Page index handling was fixed/cleaned up so that the loop index always matches the page being processed. The code now only makes a single pass through the range of pages as it was determined page faults could not race with truncate. A cond_resched() was added after removing up to PAGEVEC_SIZE pages. Some totally unnecessary code in hugetlbfs_fallocate() that remained from early development was also removed. Tested with fallocate tests submitted here: http://librelist.com/browser//libhugetlbfs/2015/6/25/patch-tests-add-tests-for-fallocate-system-call/ And, some ftruncate tests under development Fixes: b5cec28d36f5 ("hugetlbfs: truncate_hugepages() takes a range of pages") Signed-off-by: Mike Kravetz <mike.kravetz@oracle.com> Acked-by: Hugh Dickins <hughd@google.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: "Hillf Danton" <hillf.zj@alibaba-inc.com> Cc: <stable@vger.kernel.org> [4.3] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-11-21 06:57:13 +07:00
* pages are not modified. Page faults can race with hole punch.
* This is indicated if we find a mapped page.
hugetlbfs: truncate_hugepages() takes a range of pages Modify truncate_hugepages() to take a range of pages (start, end) instead of simply start. If an end value of LLONG_MAX is passed, the current "truncate" functionality is maintained. Existing callers are modified to pass LLONG_MAX as end of range. By keying off end == LLONG_MAX, the routine behaves differently for truncate and hole punch. Page removal is now synchronized with page allocation via faults by using the fault mutex table. The hole punch case can experience the rare region_del error and must handle accordingly. Add the routine hugetlb_fix_reserve_counts to fix up reserve counts in the case where region_del returns an error. Since the routine handles more than just the truncate case, it is renamed to remove_inode_hugepages(). To be consistent, the routine truncate_huge_page() is renamed remove_huge_page(). Downstream of remove_inode_hugepages(), the routine hugetlb_unreserve_pages() is also modified to take a range of pages. hugetlb_unreserve_pages is modified to detect an error from region_del and pass it back to the caller. Signed-off-by: Mike Kravetz <mike.kravetz@oracle.com> Reviewed-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Acked-by: Hillf Danton <hillf.zj@alibaba-inc.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David Rientjes <rientjes@google.com> Cc: Hugh Dickins <hughd@google.com> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Aneesh Kumar <aneesh.kumar@linux.vnet.ibm.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Michal Hocko <mhocko@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-09-09 05:01:41 +07:00
* Note: If the passed end of range value is beyond the end of file, but
* not LLONG_MAX this routine still performs a hole punch operation.
*/
static void remove_inode_hugepages(struct inode *inode, loff_t lstart,
loff_t lend)
{
struct hstate *h = hstate_inode(inode);
[PATCH] hugepage: Strict page reservation for hugepage inodes These days, hugepages are demand-allocated at first fault time. There's a somewhat dubious (and racy) heuristic when making a new mmap() to check if there are enough available hugepages to fully satisfy that mapping. A particularly obvious case where the heuristic breaks down is where a process maps its hugepages not as a single chunk, but as a bunch of individually mmap()ed (or shmat()ed) blocks without touching and instantiating the pages in between allocations. In this case the size of each block is compared against the total number of available hugepages. It's thus easy for the process to become overcommitted, because each block mapping will succeed, although the total number of hugepages required by all blocks exceeds the number available. In particular, this defeats such a program which will detect a mapping failure and adjust its hugepage usage downward accordingly. The patch below addresses this problem, by strictly reserving a number of physical hugepages for hugepage inodes which have been mapped, but not instatiated. MAP_SHARED mappings are thus "safe" - they will fail on mmap(), not later with an OOM SIGKILL. MAP_PRIVATE mappings can still trigger an OOM. (Actually SHARED mappings can technically still OOM, but only if the sysadmin explicitly reduces the hugepage pool between mapping and instantiation) This patch appears to address the problem at hand - it allows DB2 to start correctly, for instance, which previously suffered the failure described above. This patch causes no regressions on the libhugetblfs testsuite, and makes a test (designed to catch this problem) pass which previously failed (ppc64, POWER5). Signed-off-by: David Gibson <dwg@au1.ibm.com> Cc: William Lee Irwin III <wli@holomorphy.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-22 15:08:55 +07:00
struct address_space *mapping = &inode->i_data;
const pgoff_t start = lstart >> huge_page_shift(h);
hugetlbfs: truncate_hugepages() takes a range of pages Modify truncate_hugepages() to take a range of pages (start, end) instead of simply start. If an end value of LLONG_MAX is passed, the current "truncate" functionality is maintained. Existing callers are modified to pass LLONG_MAX as end of range. By keying off end == LLONG_MAX, the routine behaves differently for truncate and hole punch. Page removal is now synchronized with page allocation via faults by using the fault mutex table. The hole punch case can experience the rare region_del error and must handle accordingly. Add the routine hugetlb_fix_reserve_counts to fix up reserve counts in the case where region_del returns an error. Since the routine handles more than just the truncate case, it is renamed to remove_inode_hugepages(). To be consistent, the routine truncate_huge_page() is renamed remove_huge_page(). Downstream of remove_inode_hugepages(), the routine hugetlb_unreserve_pages() is also modified to take a range of pages. hugetlb_unreserve_pages is modified to detect an error from region_del and pass it back to the caller. Signed-off-by: Mike Kravetz <mike.kravetz@oracle.com> Reviewed-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Acked-by: Hillf Danton <hillf.zj@alibaba-inc.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David Rientjes <rientjes@google.com> Cc: Hugh Dickins <hughd@google.com> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Aneesh Kumar <aneesh.kumar@linux.vnet.ibm.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Michal Hocko <mhocko@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-09-09 05:01:41 +07:00
const pgoff_t end = lend >> huge_page_shift(h);
struct vm_area_struct pseudo_vma;
struct pagevec pvec;
pgoff_t next, index;
int i, freed = 0;
hugetlbfs: truncate_hugepages() takes a range of pages Modify truncate_hugepages() to take a range of pages (start, end) instead of simply start. If an end value of LLONG_MAX is passed, the current "truncate" functionality is maintained. Existing callers are modified to pass LLONG_MAX as end of range. By keying off end == LLONG_MAX, the routine behaves differently for truncate and hole punch. Page removal is now synchronized with page allocation via faults by using the fault mutex table. The hole punch case can experience the rare region_del error and must handle accordingly. Add the routine hugetlb_fix_reserve_counts to fix up reserve counts in the case where region_del returns an error. Since the routine handles more than just the truncate case, it is renamed to remove_inode_hugepages(). To be consistent, the routine truncate_huge_page() is renamed remove_huge_page(). Downstream of remove_inode_hugepages(), the routine hugetlb_unreserve_pages() is also modified to take a range of pages. hugetlb_unreserve_pages is modified to detect an error from region_del and pass it back to the caller. Signed-off-by: Mike Kravetz <mike.kravetz@oracle.com> Reviewed-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Acked-by: Hillf Danton <hillf.zj@alibaba-inc.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David Rientjes <rientjes@google.com> Cc: Hugh Dickins <hughd@google.com> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Aneesh Kumar <aneesh.kumar@linux.vnet.ibm.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Michal Hocko <mhocko@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-09-09 05:01:41 +07:00
bool truncate_op = (lend == LLONG_MAX);
hugetlbfs: truncate_hugepages() takes a range of pages Modify truncate_hugepages() to take a range of pages (start, end) instead of simply start. If an end value of LLONG_MAX is passed, the current "truncate" functionality is maintained. Existing callers are modified to pass LLONG_MAX as end of range. By keying off end == LLONG_MAX, the routine behaves differently for truncate and hole punch. Page removal is now synchronized with page allocation via faults by using the fault mutex table. The hole punch case can experience the rare region_del error and must handle accordingly. Add the routine hugetlb_fix_reserve_counts to fix up reserve counts in the case where region_del returns an error. Since the routine handles more than just the truncate case, it is renamed to remove_inode_hugepages(). To be consistent, the routine truncate_huge_page() is renamed remove_huge_page(). Downstream of remove_inode_hugepages(), the routine hugetlb_unreserve_pages() is also modified to take a range of pages. hugetlb_unreserve_pages is modified to detect an error from region_del and pass it back to the caller. Signed-off-by: Mike Kravetz <mike.kravetz@oracle.com> Reviewed-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Acked-by: Hillf Danton <hillf.zj@alibaba-inc.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David Rientjes <rientjes@google.com> Cc: Hugh Dickins <hughd@google.com> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Aneesh Kumar <aneesh.kumar@linux.vnet.ibm.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Michal Hocko <mhocko@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-09-09 05:01:41 +07:00
memset(&pseudo_vma, 0, sizeof(struct vm_area_struct));
pseudo_vma.vm_flags = (VM_HUGETLB | VM_MAYSHARE | VM_SHARED);
pagevec_init(&pvec);
next = start;
hugetlbfs: truncate_hugepages() takes a range of pages Modify truncate_hugepages() to take a range of pages (start, end) instead of simply start. If an end value of LLONG_MAX is passed, the current "truncate" functionality is maintained. Existing callers are modified to pass LLONG_MAX as end of range. By keying off end == LLONG_MAX, the routine behaves differently for truncate and hole punch. Page removal is now synchronized with page allocation via faults by using the fault mutex table. The hole punch case can experience the rare region_del error and must handle accordingly. Add the routine hugetlb_fix_reserve_counts to fix up reserve counts in the case where region_del returns an error. Since the routine handles more than just the truncate case, it is renamed to remove_inode_hugepages(). To be consistent, the routine truncate_huge_page() is renamed remove_huge_page(). Downstream of remove_inode_hugepages(), the routine hugetlb_unreserve_pages() is also modified to take a range of pages. hugetlb_unreserve_pages is modified to detect an error from region_del and pass it back to the caller. Signed-off-by: Mike Kravetz <mike.kravetz@oracle.com> Reviewed-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Acked-by: Hillf Danton <hillf.zj@alibaba-inc.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David Rientjes <rientjes@google.com> Cc: Hugh Dickins <hughd@google.com> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Aneesh Kumar <aneesh.kumar@linux.vnet.ibm.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Michal Hocko <mhocko@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-09-09 05:01:41 +07:00
while (next < end) {
/*
mm/hugetlbfs: fix bugs in fallocate hole punch of areas with holes Hugh Dickins pointed out problems with the new hugetlbfs fallocate hole punch code. These problems are in the routine remove_inode_hugepages and mostly occur in the case where there are holes in the range of pages to be removed. These holes could be the result of a previous hole punch or simply sparse allocation. The current code could access pages outside the specified range. remove_inode_hugepages handles both hole punch and truncate operations. Page index handling was fixed/cleaned up so that the loop index always matches the page being processed. The code now only makes a single pass through the range of pages as it was determined page faults could not race with truncate. A cond_resched() was added after removing up to PAGEVEC_SIZE pages. Some totally unnecessary code in hugetlbfs_fallocate() that remained from early development was also removed. Tested with fallocate tests submitted here: http://librelist.com/browser//libhugetlbfs/2015/6/25/patch-tests-add-tests-for-fallocate-system-call/ And, some ftruncate tests under development Fixes: b5cec28d36f5 ("hugetlbfs: truncate_hugepages() takes a range of pages") Signed-off-by: Mike Kravetz <mike.kravetz@oracle.com> Acked-by: Hugh Dickins <hughd@google.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: "Hillf Danton" <hillf.zj@alibaba-inc.com> Cc: <stable@vger.kernel.org> [4.3] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-11-21 06:57:13 +07:00
* When no more pages are found, we are done.
hugetlbfs: truncate_hugepages() takes a range of pages Modify truncate_hugepages() to take a range of pages (start, end) instead of simply start. If an end value of LLONG_MAX is passed, the current "truncate" functionality is maintained. Existing callers are modified to pass LLONG_MAX as end of range. By keying off end == LLONG_MAX, the routine behaves differently for truncate and hole punch. Page removal is now synchronized with page allocation via faults by using the fault mutex table. The hole punch case can experience the rare region_del error and must handle accordingly. Add the routine hugetlb_fix_reserve_counts to fix up reserve counts in the case where region_del returns an error. Since the routine handles more than just the truncate case, it is renamed to remove_inode_hugepages(). To be consistent, the routine truncate_huge_page() is renamed remove_huge_page(). Downstream of remove_inode_hugepages(), the routine hugetlb_unreserve_pages() is also modified to take a range of pages. hugetlb_unreserve_pages is modified to detect an error from region_del and pass it back to the caller. Signed-off-by: Mike Kravetz <mike.kravetz@oracle.com> Reviewed-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Acked-by: Hillf Danton <hillf.zj@alibaba-inc.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David Rientjes <rientjes@google.com> Cc: Hugh Dickins <hughd@google.com> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Aneesh Kumar <aneesh.kumar@linux.vnet.ibm.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Michal Hocko <mhocko@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-09-09 05:01:41 +07:00
*/
if (!pagevec_lookup_range(&pvec, mapping, &next, end - 1))
mm/hugetlbfs: fix bugs in fallocate hole punch of areas with holes Hugh Dickins pointed out problems with the new hugetlbfs fallocate hole punch code. These problems are in the routine remove_inode_hugepages and mostly occur in the case where there are holes in the range of pages to be removed. These holes could be the result of a previous hole punch or simply sparse allocation. The current code could access pages outside the specified range. remove_inode_hugepages handles both hole punch and truncate operations. Page index handling was fixed/cleaned up so that the loop index always matches the page being processed. The code now only makes a single pass through the range of pages as it was determined page faults could not race with truncate. A cond_resched() was added after removing up to PAGEVEC_SIZE pages. Some totally unnecessary code in hugetlbfs_fallocate() that remained from early development was also removed. Tested with fallocate tests submitted here: http://librelist.com/browser//libhugetlbfs/2015/6/25/patch-tests-add-tests-for-fallocate-system-call/ And, some ftruncate tests under development Fixes: b5cec28d36f5 ("hugetlbfs: truncate_hugepages() takes a range of pages") Signed-off-by: Mike Kravetz <mike.kravetz@oracle.com> Acked-by: Hugh Dickins <hughd@google.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: "Hillf Danton" <hillf.zj@alibaba-inc.com> Cc: <stable@vger.kernel.org> [4.3] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-11-21 06:57:13 +07:00
break;
for (i = 0; i < pagevec_count(&pvec); ++i) {
struct page *page = pvec.pages[i];
hugetlbfs: truncate_hugepages() takes a range of pages Modify truncate_hugepages() to take a range of pages (start, end) instead of simply start. If an end value of LLONG_MAX is passed, the current "truncate" functionality is maintained. Existing callers are modified to pass LLONG_MAX as end of range. By keying off end == LLONG_MAX, the routine behaves differently for truncate and hole punch. Page removal is now synchronized with page allocation via faults by using the fault mutex table. The hole punch case can experience the rare region_del error and must handle accordingly. Add the routine hugetlb_fix_reserve_counts to fix up reserve counts in the case where region_del returns an error. Since the routine handles more than just the truncate case, it is renamed to remove_inode_hugepages(). To be consistent, the routine truncate_huge_page() is renamed remove_huge_page(). Downstream of remove_inode_hugepages(), the routine hugetlb_unreserve_pages() is also modified to take a range of pages. hugetlb_unreserve_pages is modified to detect an error from region_del and pass it back to the caller. Signed-off-by: Mike Kravetz <mike.kravetz@oracle.com> Reviewed-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Acked-by: Hillf Danton <hillf.zj@alibaba-inc.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David Rientjes <rientjes@google.com> Cc: Hugh Dickins <hughd@google.com> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Aneesh Kumar <aneesh.kumar@linux.vnet.ibm.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Michal Hocko <mhocko@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-09-09 05:01:41 +07:00
u32 hash;
index = page->index;
hugetlbfs: truncate_hugepages() takes a range of pages Modify truncate_hugepages() to take a range of pages (start, end) instead of simply start. If an end value of LLONG_MAX is passed, the current "truncate" functionality is maintained. Existing callers are modified to pass LLONG_MAX as end of range. By keying off end == LLONG_MAX, the routine behaves differently for truncate and hole punch. Page removal is now synchronized with page allocation via faults by using the fault mutex table. The hole punch case can experience the rare region_del error and must handle accordingly. Add the routine hugetlb_fix_reserve_counts to fix up reserve counts in the case where region_del returns an error. Since the routine handles more than just the truncate case, it is renamed to remove_inode_hugepages(). To be consistent, the routine truncate_huge_page() is renamed remove_huge_page(). Downstream of remove_inode_hugepages(), the routine hugetlb_unreserve_pages() is also modified to take a range of pages. hugetlb_unreserve_pages is modified to detect an error from region_del and pass it back to the caller. Signed-off-by: Mike Kravetz <mike.kravetz@oracle.com> Reviewed-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Acked-by: Hillf Danton <hillf.zj@alibaba-inc.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David Rientjes <rientjes@google.com> Cc: Hugh Dickins <hughd@google.com> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Aneesh Kumar <aneesh.kumar@linux.vnet.ibm.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Michal Hocko <mhocko@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-09-09 05:01:41 +07:00
hash = hugetlb_fault_mutex_hash(h, current->mm,
&pseudo_vma,
mapping, index, 0);
hugetlbfs: truncate_hugepages() takes a range of pages Modify truncate_hugepages() to take a range of pages (start, end) instead of simply start. If an end value of LLONG_MAX is passed, the current "truncate" functionality is maintained. Existing callers are modified to pass LLONG_MAX as end of range. By keying off end == LLONG_MAX, the routine behaves differently for truncate and hole punch. Page removal is now synchronized with page allocation via faults by using the fault mutex table. The hole punch case can experience the rare region_del error and must handle accordingly. Add the routine hugetlb_fix_reserve_counts to fix up reserve counts in the case where region_del returns an error. Since the routine handles more than just the truncate case, it is renamed to remove_inode_hugepages(). To be consistent, the routine truncate_huge_page() is renamed remove_huge_page(). Downstream of remove_inode_hugepages(), the routine hugetlb_unreserve_pages() is also modified to take a range of pages. hugetlb_unreserve_pages is modified to detect an error from region_del and pass it back to the caller. Signed-off-by: Mike Kravetz <mike.kravetz@oracle.com> Reviewed-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Acked-by: Hillf Danton <hillf.zj@alibaba-inc.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David Rientjes <rientjes@google.com> Cc: Hugh Dickins <hughd@google.com> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Aneesh Kumar <aneesh.kumar@linux.vnet.ibm.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Michal Hocko <mhocko@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-09-09 05:01:41 +07:00
mutex_lock(&hugetlb_fault_mutex_table[hash]);
/*
* If page is mapped, it was faulted in after being
* unmapped in caller. Unmap (again) now after taking
* the fault mutex. The mutex will prevent faults
* until we finish removing the page.
*
* This race can only happen in the hole punch case.
* Getting here in a truncate operation is a bug.
*/
if (unlikely(page_mapped(page))) {
mm/hugetlbfs: fix bugs in fallocate hole punch of areas with holes Hugh Dickins pointed out problems with the new hugetlbfs fallocate hole punch code. These problems are in the routine remove_inode_hugepages and mostly occur in the case where there are holes in the range of pages to be removed. These holes could be the result of a previous hole punch or simply sparse allocation. The current code could access pages outside the specified range. remove_inode_hugepages handles both hole punch and truncate operations. Page index handling was fixed/cleaned up so that the loop index always matches the page being processed. The code now only makes a single pass through the range of pages as it was determined page faults could not race with truncate. A cond_resched() was added after removing up to PAGEVEC_SIZE pages. Some totally unnecessary code in hugetlbfs_fallocate() that remained from early development was also removed. Tested with fallocate tests submitted here: http://librelist.com/browser//libhugetlbfs/2015/6/25/patch-tests-add-tests-for-fallocate-system-call/ And, some ftruncate tests under development Fixes: b5cec28d36f5 ("hugetlbfs: truncate_hugepages() takes a range of pages") Signed-off-by: Mike Kravetz <mike.kravetz@oracle.com> Acked-by: Hugh Dickins <hughd@google.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: "Hillf Danton" <hillf.zj@alibaba-inc.com> Cc: <stable@vger.kernel.org> [4.3] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-11-21 06:57:13 +07:00
BUG_ON(truncate_op);
i_mmap_lock_write(mapping);
hugetlb_vmdelete_list(&mapping->i_mmap,
index * pages_per_huge_page(h),
(index + 1) * pages_per_huge_page(h));
i_mmap_unlock_write(mapping);
}
lock_page(page);
/*
* We must free the huge page and remove from page
* cache (remove_huge_page) BEFORE removing the
* region/reserve map (hugetlb_unreserve_pages). In
* rare out of memory conditions, removal of the
* region/reserve map could fail. Correspondingly,
* the subpool and global reserve usage count can need
* to be adjusted.
*/
VM_BUG_ON(PagePrivate(page));
remove_huge_page(page);
freed++;
if (!truncate_op) {
if (unlikely(hugetlb_unreserve_pages(inode,
index, index + 1, 1)))
hugetlb_fix_reserve_counts(inode);
hugetlbfs: truncate_hugepages() takes a range of pages Modify truncate_hugepages() to take a range of pages (start, end) instead of simply start. If an end value of LLONG_MAX is passed, the current "truncate" functionality is maintained. Existing callers are modified to pass LLONG_MAX as end of range. By keying off end == LLONG_MAX, the routine behaves differently for truncate and hole punch. Page removal is now synchronized with page allocation via faults by using the fault mutex table. The hole punch case can experience the rare region_del error and must handle accordingly. Add the routine hugetlb_fix_reserve_counts to fix up reserve counts in the case where region_del returns an error. Since the routine handles more than just the truncate case, it is renamed to remove_inode_hugepages(). To be consistent, the routine truncate_huge_page() is renamed remove_huge_page(). Downstream of remove_inode_hugepages(), the routine hugetlb_unreserve_pages() is also modified to take a range of pages. hugetlb_unreserve_pages is modified to detect an error from region_del and pass it back to the caller. Signed-off-by: Mike Kravetz <mike.kravetz@oracle.com> Reviewed-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Acked-by: Hillf Danton <hillf.zj@alibaba-inc.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David Rientjes <rientjes@google.com> Cc: Hugh Dickins <hughd@google.com> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Aneesh Kumar <aneesh.kumar@linux.vnet.ibm.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Michal Hocko <mhocko@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-09-09 05:01:41 +07:00
}
unlock_page(page);
hugetlbfs: truncate_hugepages() takes a range of pages Modify truncate_hugepages() to take a range of pages (start, end) instead of simply start. If an end value of LLONG_MAX is passed, the current "truncate" functionality is maintained. Existing callers are modified to pass LLONG_MAX as end of range. By keying off end == LLONG_MAX, the routine behaves differently for truncate and hole punch. Page removal is now synchronized with page allocation via faults by using the fault mutex table. The hole punch case can experience the rare region_del error and must handle accordingly. Add the routine hugetlb_fix_reserve_counts to fix up reserve counts in the case where region_del returns an error. Since the routine handles more than just the truncate case, it is renamed to remove_inode_hugepages(). To be consistent, the routine truncate_huge_page() is renamed remove_huge_page(). Downstream of remove_inode_hugepages(), the routine hugetlb_unreserve_pages() is also modified to take a range of pages. hugetlb_unreserve_pages is modified to detect an error from region_del and pass it back to the caller. Signed-off-by: Mike Kravetz <mike.kravetz@oracle.com> Reviewed-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Acked-by: Hillf Danton <hillf.zj@alibaba-inc.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David Rientjes <rientjes@google.com> Cc: Hugh Dickins <hughd@google.com> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Aneesh Kumar <aneesh.kumar@linux.vnet.ibm.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Michal Hocko <mhocko@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-09-09 05:01:41 +07:00
mutex_unlock(&hugetlb_fault_mutex_table[hash]);
}
huge_pagevec_release(&pvec);
mm/hugetlbfs: fix bugs in fallocate hole punch of areas with holes Hugh Dickins pointed out problems with the new hugetlbfs fallocate hole punch code. These problems are in the routine remove_inode_hugepages and mostly occur in the case where there are holes in the range of pages to be removed. These holes could be the result of a previous hole punch or simply sparse allocation. The current code could access pages outside the specified range. remove_inode_hugepages handles both hole punch and truncate operations. Page index handling was fixed/cleaned up so that the loop index always matches the page being processed. The code now only makes a single pass through the range of pages as it was determined page faults could not race with truncate. A cond_resched() was added after removing up to PAGEVEC_SIZE pages. Some totally unnecessary code in hugetlbfs_fallocate() that remained from early development was also removed. Tested with fallocate tests submitted here: http://librelist.com/browser//libhugetlbfs/2015/6/25/patch-tests-add-tests-for-fallocate-system-call/ And, some ftruncate tests under development Fixes: b5cec28d36f5 ("hugetlbfs: truncate_hugepages() takes a range of pages") Signed-off-by: Mike Kravetz <mike.kravetz@oracle.com> Acked-by: Hugh Dickins <hughd@google.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: "Hillf Danton" <hillf.zj@alibaba-inc.com> Cc: <stable@vger.kernel.org> [4.3] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-11-21 06:57:13 +07:00
cond_resched();
}
hugetlbfs: truncate_hugepages() takes a range of pages Modify truncate_hugepages() to take a range of pages (start, end) instead of simply start. If an end value of LLONG_MAX is passed, the current "truncate" functionality is maintained. Existing callers are modified to pass LLONG_MAX as end of range. By keying off end == LLONG_MAX, the routine behaves differently for truncate and hole punch. Page removal is now synchronized with page allocation via faults by using the fault mutex table. The hole punch case can experience the rare region_del error and must handle accordingly. Add the routine hugetlb_fix_reserve_counts to fix up reserve counts in the case where region_del returns an error. Since the routine handles more than just the truncate case, it is renamed to remove_inode_hugepages(). To be consistent, the routine truncate_huge_page() is renamed remove_huge_page(). Downstream of remove_inode_hugepages(), the routine hugetlb_unreserve_pages() is also modified to take a range of pages. hugetlb_unreserve_pages is modified to detect an error from region_del and pass it back to the caller. Signed-off-by: Mike Kravetz <mike.kravetz@oracle.com> Reviewed-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Acked-by: Hillf Danton <hillf.zj@alibaba-inc.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David Rientjes <rientjes@google.com> Cc: Hugh Dickins <hughd@google.com> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Aneesh Kumar <aneesh.kumar@linux.vnet.ibm.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Michal Hocko <mhocko@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-09-09 05:01:41 +07:00
if (truncate_op)
(void)hugetlb_unreserve_pages(inode, start, LONG_MAX, freed);
}
static void hugetlbfs_evict_inode(struct inode *inode)
{
struct resv_map *resv_map;
hugetlbfs: truncate_hugepages() takes a range of pages Modify truncate_hugepages() to take a range of pages (start, end) instead of simply start. If an end value of LLONG_MAX is passed, the current "truncate" functionality is maintained. Existing callers are modified to pass LLONG_MAX as end of range. By keying off end == LLONG_MAX, the routine behaves differently for truncate and hole punch. Page removal is now synchronized with page allocation via faults by using the fault mutex table. The hole punch case can experience the rare region_del error and must handle accordingly. Add the routine hugetlb_fix_reserve_counts to fix up reserve counts in the case where region_del returns an error. Since the routine handles more than just the truncate case, it is renamed to remove_inode_hugepages(). To be consistent, the routine truncate_huge_page() is renamed remove_huge_page(). Downstream of remove_inode_hugepages(), the routine hugetlb_unreserve_pages() is also modified to take a range of pages. hugetlb_unreserve_pages is modified to detect an error from region_del and pass it back to the caller. Signed-off-by: Mike Kravetz <mike.kravetz@oracle.com> Reviewed-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Acked-by: Hillf Danton <hillf.zj@alibaba-inc.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David Rientjes <rientjes@google.com> Cc: Hugh Dickins <hughd@google.com> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Aneesh Kumar <aneesh.kumar@linux.vnet.ibm.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Michal Hocko <mhocko@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-09-09 05:01:41 +07:00
remove_inode_hugepages(inode, 0, LLONG_MAX);
resv_map = (struct resv_map *)inode->i_mapping->private_data;
/* root inode doesn't have the resv_map, so we should check it */
if (resv_map)
resv_map_release(&resv_map->refs);
clear_inode(inode);
}
static int hugetlb_vmtruncate(struct inode *inode, loff_t offset)
{
pgoff_t pgoff;
struct address_space *mapping = inode->i_mapping;
struct hstate *h = hstate_inode(inode);
BUG_ON(offset & ~huge_page_mask(h));
pgoff = offset >> PAGE_SHIFT;
i_size_write(inode, offset);
i_mmap_lock_write(mapping);
if (!RB_EMPTY_ROOT(&mapping->i_mmap.rb_root))
hugetlb_vmdelete_list(&mapping->i_mmap, pgoff, 0);
i_mmap_unlock_write(mapping);
hugetlbfs: truncate_hugepages() takes a range of pages Modify truncate_hugepages() to take a range of pages (start, end) instead of simply start. If an end value of LLONG_MAX is passed, the current "truncate" functionality is maintained. Existing callers are modified to pass LLONG_MAX as end of range. By keying off end == LLONG_MAX, the routine behaves differently for truncate and hole punch. Page removal is now synchronized with page allocation via faults by using the fault mutex table. The hole punch case can experience the rare region_del error and must handle accordingly. Add the routine hugetlb_fix_reserve_counts to fix up reserve counts in the case where region_del returns an error. Since the routine handles more than just the truncate case, it is renamed to remove_inode_hugepages(). To be consistent, the routine truncate_huge_page() is renamed remove_huge_page(). Downstream of remove_inode_hugepages(), the routine hugetlb_unreserve_pages() is also modified to take a range of pages. hugetlb_unreserve_pages is modified to detect an error from region_del and pass it back to the caller. Signed-off-by: Mike Kravetz <mike.kravetz@oracle.com> Reviewed-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Acked-by: Hillf Danton <hillf.zj@alibaba-inc.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David Rientjes <rientjes@google.com> Cc: Hugh Dickins <hughd@google.com> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Aneesh Kumar <aneesh.kumar@linux.vnet.ibm.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Michal Hocko <mhocko@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-09-09 05:01:41 +07:00
remove_inode_hugepages(inode, offset, LLONG_MAX);
return 0;
}
static long hugetlbfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
{
struct hstate *h = hstate_inode(inode);
loff_t hpage_size = huge_page_size(h);
loff_t hole_start, hole_end;
/*
* For hole punch round up the beginning offset of the hole and
* round down the end.
*/
hole_start = round_up(offset, hpage_size);
hole_end = round_down(offset + len, hpage_size);
if (hole_end > hole_start) {
struct address_space *mapping = inode->i_mapping;
inode_lock(inode);
i_mmap_lock_write(mapping);
if (!RB_EMPTY_ROOT(&mapping->i_mmap.rb_root))
hugetlb_vmdelete_list(&mapping->i_mmap,
hole_start >> PAGE_SHIFT,
hole_end >> PAGE_SHIFT);
i_mmap_unlock_write(mapping);
remove_inode_hugepages(inode, hole_start, hole_end);
inode_unlock(inode);
}
return 0;
}
static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset,
loff_t len)
{
struct inode *inode = file_inode(file);
struct address_space *mapping = inode->i_mapping;
struct hstate *h = hstate_inode(inode);
struct vm_area_struct pseudo_vma;
struct mm_struct *mm = current->mm;
loff_t hpage_size = huge_page_size(h);
unsigned long hpage_shift = huge_page_shift(h);
pgoff_t start, index, end;
int error;
u32 hash;
if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE))
return -EOPNOTSUPP;
if (mode & FALLOC_FL_PUNCH_HOLE)
return hugetlbfs_punch_hole(inode, offset, len);
/*
* Default preallocate case.
* For this range, start is rounded down and end is rounded up
* as well as being converted to page offsets.
*/
start = offset >> hpage_shift;
end = (offset + len + hpage_size - 1) >> hpage_shift;
inode_lock(inode);
/* We need to check rlimit even when FALLOC_FL_KEEP_SIZE */
error = inode_newsize_ok(inode, offset + len);
if (error)
goto out;
/*
* Initialize a pseudo vma as this is required by the huge page
* allocation routines. If NUMA is configured, use page index
* as input to create an allocation policy.
*/
memset(&pseudo_vma, 0, sizeof(struct vm_area_struct));
pseudo_vma.vm_flags = (VM_HUGETLB | VM_MAYSHARE | VM_SHARED);
pseudo_vma.vm_file = file;
for (index = start; index < end; index++) {
/*
* This is supposed to be the vaddr where the page is being
* faulted in, but we have no vaddr here.
*/
struct page *page;
unsigned long addr;
int avoid_reserve = 0;
cond_resched();
/*
* fallocate(2) manpage permits EINTR; we may have been
* interrupted because we are using up too much memory.
*/
if (signal_pending(current)) {
error = -EINTR;
break;
}
/* Set numa allocation policy based on index */
hugetlb_set_vma_policy(&pseudo_vma, inode, index);
/* addr is the offset within the file (zero based) */
addr = index * hpage_size;
/* mutex taken here, fault path and hole punch */
hash = hugetlb_fault_mutex_hash(h, mm, &pseudo_vma, mapping,
index, addr);
mutex_lock(&hugetlb_fault_mutex_table[hash]);
/* See if already present in mapping to avoid alloc/free */
page = find_get_page(mapping, index);
if (page) {
put_page(page);
mutex_unlock(&hugetlb_fault_mutex_table[hash]);
hugetlb_drop_vma_policy(&pseudo_vma);
continue;
}
/* Allocate page and add to page cache */
page = alloc_huge_page(&pseudo_vma, addr, avoid_reserve);
hugetlb_drop_vma_policy(&pseudo_vma);
if (IS_ERR(page)) {
mutex_unlock(&hugetlb_fault_mutex_table[hash]);
error = PTR_ERR(page);
goto out;
}
clear_huge_page(page, addr, pages_per_huge_page(h));
__SetPageUptodate(page);
error = huge_add_to_page_cache(page, mapping, index);
if (unlikely(error)) {
put_page(page);
mutex_unlock(&hugetlb_fault_mutex_table[hash]);
goto out;
}
mutex_unlock(&hugetlb_fault_mutex_table[hash]);
/*
* page_put due to reference from alloc_huge_page()
* unlock_page because locked by add_to_page_cache()
*/
put_page(page);
unlock_page(page);
}
if (!(mode & FALLOC_FL_KEEP_SIZE) && offset + len > inode->i_size)
i_size_write(inode, offset + len);
inode->i_ctime = current_time(inode);
out:
inode_unlock(inode);
return error;
}
static int hugetlbfs_setattr(struct dentry *dentry, struct iattr *attr)
{
struct inode *inode = d_inode(dentry);
struct hstate *h = hstate_inode(inode);
int error;
unsigned int ia_valid = attr->ia_valid;
BUG_ON(!inode);
error = setattr_prepare(dentry, attr);
if (error)
return error;
if (ia_valid & ATTR_SIZE) {
if (attr->ia_size & ~huge_page_mask(h))
return -EINVAL;
error = hugetlb_vmtruncate(inode, attr->ia_size);
if (error)
return error;
}
setattr_copy(inode, attr);
mark_inode_dirty(inode);
return 0;
}
static struct inode *hugetlbfs_get_root(struct super_block *sb,
struct hugetlbfs_config *config)
{
struct inode *inode;
inode = new_inode(sb);
if (inode) {
inode->i_ino = get_next_ino();
inode->i_mode = S_IFDIR | config->mode;
inode->i_uid = config->uid;
inode->i_gid = config->gid;
inode->i_atime = inode->i_mtime = inode->i_ctime = current_time(inode);
inode->i_op = &hugetlbfs_dir_inode_operations;
inode->i_fop = &simple_dir_operations;
/* directory inodes start off with i_nlink == 2 (for "." entry) */
inc_nlink(inode);
hugetlbfs: lockdep annotate root inode properly This fixes the below reported false lockdep warning. e096d0c7e2e4 ("lockdep: Add helper function for dir vs file i_mutex annotation") added a similar annotation for every other inode in hugetlbfs but missed the root inode because it was allocated by a separate function. For HugeTLB fs we allow taking i_mutex in mmap. HugeTLB fs doesn't support file write and its file read callback is modified in a05b0855fd ("hugetlbfs: avoid taking i_mutex from hugetlbfs_read()") to not take i_mutex. Hence for HugeTLB fs with regular files we really don't take i_mutex with mmap_sem held. ====================================================== [ INFO: possible circular locking dependency detected ] 3.4.0-rc1+ #322 Not tainted ------------------------------------------------------- bash/1572 is trying to acquire lock: (&mm->mmap_sem){++++++}, at: [<ffffffff810f1618>] might_fault+0x40/0x90 but task is already holding lock: (&sb->s_type->i_mutex_key#12){+.+.+.}, at: [<ffffffff81125f88>] vfs_readdir+0x56/0xa8 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (&sb->s_type->i_mutex_key#12){+.+.+.}: [<ffffffff810a09e5>] lock_acquire+0xd5/0xfa [<ffffffff816a2f5e>] __mutex_lock_common+0x48/0x350 [<ffffffff816a3325>] mutex_lock_nested+0x2a/0x31 [<ffffffff811fb8e1>] hugetlbfs_file_mmap+0x7d/0x104 [<ffffffff810f859a>] mmap_region+0x272/0x47d [<ffffffff810f8a39>] do_mmap_pgoff+0x294/0x2ee [<ffffffff810f8b65>] sys_mmap_pgoff+0xd2/0x10e [<ffffffff8103d19e>] sys_mmap+0x1d/0x1f [<ffffffff816a5922>] system_call_fastpath+0x16/0x1b -> #0 (&mm->mmap_sem){++++++}: [<ffffffff810a0256>] __lock_acquire+0xa81/0xd75 [<ffffffff810a09e5>] lock_acquire+0xd5/0xfa [<ffffffff810f1645>] might_fault+0x6d/0x90 [<ffffffff81125d62>] filldir+0x6a/0xc2 [<ffffffff81133a83>] dcache_readdir+0x5c/0x222 [<ffffffff81125fa8>] vfs_readdir+0x76/0xa8 [<ffffffff811260b6>] sys_getdents+0x79/0xc9 [<ffffffff816a5922>] system_call_fastpath+0x16/0x1b other info that might help us debug this: Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(&sb->s_type->i_mutex_key#12); lock(&mm->mmap_sem); lock(&sb->s_type->i_mutex_key#12); lock(&mm->mmap_sem); *** DEADLOCK *** 1 lock held by bash/1572: #0: (&sb->s_type->i_mutex_key#12){+.+.+.}, at: [<ffffffff81125f88>] vfs_readdir+0x56/0xa8 stack backtrace: Pid: 1572, comm: bash Not tainted 3.4.0-rc1+ #322 Call Trace: [<ffffffff81699a3c>] print_circular_bug+0x1f8/0x209 [<ffffffff810a0256>] __lock_acquire+0xa81/0xd75 [<ffffffff810f38aa>] ? handle_pte_fault+0x5ff/0x614 [<ffffffff8109e622>] ? mark_lock+0x2d/0x258 [<ffffffff810f1618>] ? might_fault+0x40/0x90 [<ffffffff810a09e5>] lock_acquire+0xd5/0xfa [<ffffffff810f1618>] ? might_fault+0x40/0x90 [<ffffffff816a3249>] ? __mutex_lock_common+0x333/0x350 [<ffffffff810f1645>] might_fault+0x6d/0x90 [<ffffffff810f1618>] ? might_fault+0x40/0x90 [<ffffffff81125d62>] filldir+0x6a/0xc2 [<ffffffff81133a83>] dcache_readdir+0x5c/0x222 [<ffffffff81125cf8>] ? sys_ioctl+0x74/0x74 [<ffffffff81125cf8>] ? sys_ioctl+0x74/0x74 [<ffffffff81125cf8>] ? sys_ioctl+0x74/0x74 [<ffffffff81125fa8>] vfs_readdir+0x76/0xa8 [<ffffffff811260b6>] sys_getdents+0x79/0xc9 [<ffffffff816a5922>] system_call_fastpath+0x16/0x1b Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> Cc: Dave Jones <davej@redhat.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Josh Boyer <jwboyer@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mimi Zohar <zohar@linux.vnet.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-04-26 06:01:50 +07:00
lockdep_annotate_inode_mutex_key(inode);
}
return inode;
}
hugetlb: fix lockdep splat caused by pmd sharing Dave has reported the following lockdep splat: ================================= [ INFO: inconsistent lock state ] 3.11.0-rc1+ #9 Not tainted --------------------------------- inconsistent {RECLAIM_FS-ON-W} -> {IN-RECLAIM_FS-W} usage. kswapd0/49 [HC0[0]:SC0[0]:HE1:SE1] takes: (&mapping->i_mmap_mutex){+.+.?.}, at: [<c114971b>] page_referenced+0x87/0x5e3 {RECLAIM_FS-ON-W} state was registered at: mark_held_locks+0x81/0xe7 lockdep_trace_alloc+0x5e/0xbc __alloc_pages_nodemask+0x8b/0x9b6 __get_free_pages+0x20/0x31 get_zeroed_page+0x12/0x14 __pmd_alloc+0x1c/0x6b huge_pmd_share+0x265/0x283 huge_pte_alloc+0x5d/0x71 hugetlb_fault+0x7c/0x64a handle_mm_fault+0x255/0x299 __do_page_fault+0x142/0x55c do_page_fault+0xd/0x16 error_code+0x6c/0x74 irq event stamp: 3136917 hardirqs last enabled at (3136917): _raw_spin_unlock_irq+0x27/0x50 hardirqs last disabled at (3136916): _raw_spin_lock_irq+0x15/0x78 softirqs last enabled at (3136180): __do_softirq+0x137/0x30f softirqs last disabled at (3136175): irq_exit+0xa8/0xaa other info that might help us debug this: Possible unsafe locking scenario: CPU0 ---- lock(&mapping->i_mmap_mutex); <Interrupt> lock(&mapping->i_mmap_mutex); *** DEADLOCK *** no locks held by kswapd0/49. stack backtrace: CPU: 1 PID: 49 Comm: kswapd0 Not tainted 3.11.0-rc1+ #9 Hardware name: Dell Inc. Precision WorkStation 490 /0DT031, BIOS A08 04/25/2008 Call Trace: dump_stack+0x4b/0x79 print_usage_bug+0x1d9/0x1e3 mark_lock+0x1e0/0x261 __lock_acquire+0x623/0x17f2 lock_acquire+0x7d/0x195 mutex_lock_nested+0x6c/0x3a7 page_referenced+0x87/0x5e3 shrink_page_list+0x3d9/0x947 shrink_inactive_list+0x155/0x4cb shrink_lruvec+0x300/0x5ce shrink_zone+0x53/0x14e kswapd+0x517/0xa75 kthread+0xa8/0xaa ret_from_kernel_thread+0x1b/0x28 which is a false positive caused by hugetlb pmd sharing code which allocates a new pmd from withing mapping->i_mmap_mutex. If this allocation causes reclaim then the lockdep detector complains that we might self-deadlock. This is not correct though, because hugetlb pages are not reclaimable so their mapping will be never touched from the reclaim path. The patch tells lockup detector that hugetlb i_mmap_mutex is special by assigning it a separate lockdep class so it won't report possible deadlocks on unrelated mappings. [peterz@infradead.org: comment for annotation] Reported-by: Dave Jones <davej@redhat.com> Signed-off-by: Michal Hocko <mhocko@suse.cz> Cc: Peter Zijlstra <peterz@infradead.org> Reviewed-by: Minchan Kim <minchan@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-08-14 06:00:55 +07:00
/*
* Hugetlbfs is not reclaimable; therefore its i_mmap_rwsem will never
hugetlb: fix lockdep splat caused by pmd sharing Dave has reported the following lockdep splat: ================================= [ INFO: inconsistent lock state ] 3.11.0-rc1+ #9 Not tainted --------------------------------- inconsistent {RECLAIM_FS-ON-W} -> {IN-RECLAIM_FS-W} usage. kswapd0/49 [HC0[0]:SC0[0]:HE1:SE1] takes: (&mapping->i_mmap_mutex){+.+.?.}, at: [<c114971b>] page_referenced+0x87/0x5e3 {RECLAIM_FS-ON-W} state was registered at: mark_held_locks+0x81/0xe7 lockdep_trace_alloc+0x5e/0xbc __alloc_pages_nodemask+0x8b/0x9b6 __get_free_pages+0x20/0x31 get_zeroed_page+0x12/0x14 __pmd_alloc+0x1c/0x6b huge_pmd_share+0x265/0x283 huge_pte_alloc+0x5d/0x71 hugetlb_fault+0x7c/0x64a handle_mm_fault+0x255/0x299 __do_page_fault+0x142/0x55c do_page_fault+0xd/0x16 error_code+0x6c/0x74 irq event stamp: 3136917 hardirqs last enabled at (3136917): _raw_spin_unlock_irq+0x27/0x50 hardirqs last disabled at (3136916): _raw_spin_lock_irq+0x15/0x78 softirqs last enabled at (3136180): __do_softirq+0x137/0x30f softirqs last disabled at (3136175): irq_exit+0xa8/0xaa other info that might help us debug this: Possible unsafe locking scenario: CPU0 ---- lock(&mapping->i_mmap_mutex); <Interrupt> lock(&mapping->i_mmap_mutex); *** DEADLOCK *** no locks held by kswapd0/49. stack backtrace: CPU: 1 PID: 49 Comm: kswapd0 Not tainted 3.11.0-rc1+ #9 Hardware name: Dell Inc. Precision WorkStation 490 /0DT031, BIOS A08 04/25/2008 Call Trace: dump_stack+0x4b/0x79 print_usage_bug+0x1d9/0x1e3 mark_lock+0x1e0/0x261 __lock_acquire+0x623/0x17f2 lock_acquire+0x7d/0x195 mutex_lock_nested+0x6c/0x3a7 page_referenced+0x87/0x5e3 shrink_page_list+0x3d9/0x947 shrink_inactive_list+0x155/0x4cb shrink_lruvec+0x300/0x5ce shrink_zone+0x53/0x14e kswapd+0x517/0xa75 kthread+0xa8/0xaa ret_from_kernel_thread+0x1b/0x28 which is a false positive caused by hugetlb pmd sharing code which allocates a new pmd from withing mapping->i_mmap_mutex. If this allocation causes reclaim then the lockdep detector complains that we might self-deadlock. This is not correct though, because hugetlb pages are not reclaimable so their mapping will be never touched from the reclaim path. The patch tells lockup detector that hugetlb i_mmap_mutex is special by assigning it a separate lockdep class so it won't report possible deadlocks on unrelated mappings. [peterz@infradead.org: comment for annotation] Reported-by: Dave Jones <davej@redhat.com> Signed-off-by: Michal Hocko <mhocko@suse.cz> Cc: Peter Zijlstra <peterz@infradead.org> Reviewed-by: Minchan Kim <minchan@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-08-14 06:00:55 +07:00
* be taken from reclaim -- unlike regular filesystems. This needs an
* annotation because huge_pmd_share() does an allocation under hugetlb's
* i_mmap_rwsem.
hugetlb: fix lockdep splat caused by pmd sharing Dave has reported the following lockdep splat: ================================= [ INFO: inconsistent lock state ] 3.11.0-rc1+ #9 Not tainted --------------------------------- inconsistent {RECLAIM_FS-ON-W} -> {IN-RECLAIM_FS-W} usage. kswapd0/49 [HC0[0]:SC0[0]:HE1:SE1] takes: (&mapping->i_mmap_mutex){+.+.?.}, at: [<c114971b>] page_referenced+0x87/0x5e3 {RECLAIM_FS-ON-W} state was registered at: mark_held_locks+0x81/0xe7 lockdep_trace_alloc+0x5e/0xbc __alloc_pages_nodemask+0x8b/0x9b6 __get_free_pages+0x20/0x31 get_zeroed_page+0x12/0x14 __pmd_alloc+0x1c/0x6b huge_pmd_share+0x265/0x283 huge_pte_alloc+0x5d/0x71 hugetlb_fault+0x7c/0x64a handle_mm_fault+0x255/0x299 __do_page_fault+0x142/0x55c do_page_fault+0xd/0x16 error_code+0x6c/0x74 irq event stamp: 3136917 hardirqs last enabled at (3136917): _raw_spin_unlock_irq+0x27/0x50 hardirqs last disabled at (3136916): _raw_spin_lock_irq+0x15/0x78 softirqs last enabled at (3136180): __do_softirq+0x137/0x30f softirqs last disabled at (3136175): irq_exit+0xa8/0xaa other info that might help us debug this: Possible unsafe locking scenario: CPU0 ---- lock(&mapping->i_mmap_mutex); <Interrupt> lock(&mapping->i_mmap_mutex); *** DEADLOCK *** no locks held by kswapd0/49. stack backtrace: CPU: 1 PID: 49 Comm: kswapd0 Not tainted 3.11.0-rc1+ #9 Hardware name: Dell Inc. Precision WorkStation 490 /0DT031, BIOS A08 04/25/2008 Call Trace: dump_stack+0x4b/0x79 print_usage_bug+0x1d9/0x1e3 mark_lock+0x1e0/0x261 __lock_acquire+0x623/0x17f2 lock_acquire+0x7d/0x195 mutex_lock_nested+0x6c/0x3a7 page_referenced+0x87/0x5e3 shrink_page_list+0x3d9/0x947 shrink_inactive_list+0x155/0x4cb shrink_lruvec+0x300/0x5ce shrink_zone+0x53/0x14e kswapd+0x517/0xa75 kthread+0xa8/0xaa ret_from_kernel_thread+0x1b/0x28 which is a false positive caused by hugetlb pmd sharing code which allocates a new pmd from withing mapping->i_mmap_mutex. If this allocation causes reclaim then the lockdep detector complains that we might self-deadlock. This is not correct though, because hugetlb pages are not reclaimable so their mapping will be never touched from the reclaim path. The patch tells lockup detector that hugetlb i_mmap_mutex is special by assigning it a separate lockdep class so it won't report possible deadlocks on unrelated mappings. [peterz@infradead.org: comment for annotation] Reported-by: Dave Jones <davej@redhat.com> Signed-off-by: Michal Hocko <mhocko@suse.cz> Cc: Peter Zijlstra <peterz@infradead.org> Reviewed-by: Minchan Kim <minchan@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-08-14 06:00:55 +07:00
*/
static struct lock_class_key hugetlbfs_i_mmap_rwsem_key;
hugetlb: fix lockdep splat caused by pmd sharing Dave has reported the following lockdep splat: ================================= [ INFO: inconsistent lock state ] 3.11.0-rc1+ #9 Not tainted --------------------------------- inconsistent {RECLAIM_FS-ON-W} -> {IN-RECLAIM_FS-W} usage. kswapd0/49 [HC0[0]:SC0[0]:HE1:SE1] takes: (&mapping->i_mmap_mutex){+.+.?.}, at: [<c114971b>] page_referenced+0x87/0x5e3 {RECLAIM_FS-ON-W} state was registered at: mark_held_locks+0x81/0xe7 lockdep_trace_alloc+0x5e/0xbc __alloc_pages_nodemask+0x8b/0x9b6 __get_free_pages+0x20/0x31 get_zeroed_page+0x12/0x14 __pmd_alloc+0x1c/0x6b huge_pmd_share+0x265/0x283 huge_pte_alloc+0x5d/0x71 hugetlb_fault+0x7c/0x64a handle_mm_fault+0x255/0x299 __do_page_fault+0x142/0x55c do_page_fault+0xd/0x16 error_code+0x6c/0x74 irq event stamp: 3136917 hardirqs last enabled at (3136917): _raw_spin_unlock_irq+0x27/0x50 hardirqs last disabled at (3136916): _raw_spin_lock_irq+0x15/0x78 softirqs last enabled at (3136180): __do_softirq+0x137/0x30f softirqs last disabled at (3136175): irq_exit+0xa8/0xaa other info that might help us debug this: Possible unsafe locking scenario: CPU0 ---- lock(&mapping->i_mmap_mutex); <Interrupt> lock(&mapping->i_mmap_mutex); *** DEADLOCK *** no locks held by kswapd0/49. stack backtrace: CPU: 1 PID: 49 Comm: kswapd0 Not tainted 3.11.0-rc1+ #9 Hardware name: Dell Inc. Precision WorkStation 490 /0DT031, BIOS A08 04/25/2008 Call Trace: dump_stack+0x4b/0x79 print_usage_bug+0x1d9/0x1e3 mark_lock+0x1e0/0x261 __lock_acquire+0x623/0x17f2 lock_acquire+0x7d/0x195 mutex_lock_nested+0x6c/0x3a7 page_referenced+0x87/0x5e3 shrink_page_list+0x3d9/0x947 shrink_inactive_list+0x155/0x4cb shrink_lruvec+0x300/0x5ce shrink_zone+0x53/0x14e kswapd+0x517/0xa75 kthread+0xa8/0xaa ret_from_kernel_thread+0x1b/0x28 which is a false positive caused by hugetlb pmd sharing code which allocates a new pmd from withing mapping->i_mmap_mutex. If this allocation causes reclaim then the lockdep detector complains that we might self-deadlock. This is not correct though, because hugetlb pages are not reclaimable so their mapping will be never touched from the reclaim path. The patch tells lockup detector that hugetlb i_mmap_mutex is special by assigning it a separate lockdep class so it won't report possible deadlocks on unrelated mappings. [peterz@infradead.org: comment for annotation] Reported-by: Dave Jones <davej@redhat.com> Signed-off-by: Michal Hocko <mhocko@suse.cz> Cc: Peter Zijlstra <peterz@infradead.org> Reviewed-by: Minchan Kim <minchan@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-08-14 06:00:55 +07:00
static struct inode *hugetlbfs_get_inode(struct super_block *sb,
struct inode *dir,
umode_t mode, dev_t dev)
{
struct inode *inode;
struct resv_map *resv_map;
resv_map = resv_map_alloc();
if (!resv_map)
return NULL;
inode = new_inode(sb);
if (inode) {
inode->i_ino = get_next_ino();
inode_init_owner(inode, dir, mode);
lockdep_set_class(&inode->i_mapping->i_mmap_rwsem,
&hugetlbfs_i_mmap_rwsem_key);
inode->i_mapping->a_ops = &hugetlbfs_aops;
inode->i_atime = inode->i_mtime = inode->i_ctime = current_time(inode);
inode->i_mapping->private_data = resv_map;
switch (mode & S_IFMT) {
default:
init_special_inode(inode, mode, dev);
break;
case S_IFREG:
inode->i_op = &hugetlbfs_inode_operations;
inode->i_fop = &hugetlbfs_file_operations;
break;
case S_IFDIR:
inode->i_op = &hugetlbfs_dir_inode_operations;
inode->i_fop = &simple_dir_operations;
/* directory inodes start off with i_nlink == 2 (for "." entry) */
inc_nlink(inode);
break;
case S_IFLNK:
inode->i_op = &page_symlink_inode_operations;
inode_nohighmem(inode);
break;
}
lockdep: Add helper function for dir vs file i_mutex annotation Purely in-memory filesystems do not use the inode hash as the dcache tells us if an entry already exists. As a result, they do not call unlock_new_inode, and thus directory inodes do not get put into a different lockdep class for i_sem. We need the different lockdep classes, because the locking order for i_mutex is different for directory inodes and regular inodes. Directory inodes can do "readdir()", which takes i_mutex *before* possibly taking mm->mmap_sem (due to a page fault while copying the directory entry to user space). In contrast, regular inodes can be mmap'ed, which takes mm->mmap_sem before accessing i_mutex. The two cases can never happen for the same inode, so no real deadlock can occur, but without the different lockdep classes, lockdep cannot understand that. As a result, if CONFIG_DEBUG_LOCK_ALLOC is set, this can lead to false positives from lockdep like below: find/645 is trying to acquire lock: (&mm->mmap_sem){++++++}, at: [<ffffffff81109514>] might_fault+0x5c/0xac but task is already holding lock: (&sb->s_type->i_mutex_key#15){+.+.+.}, at: [<ffffffff81149f34>] vfs_readdir+0x5b/0xb4 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (&sb->s_type->i_mutex_key#15){+.+.+.}: [<ffffffff8108ac26>] lock_acquire+0xbf/0x103 [<ffffffff814db822>] __mutex_lock_common+0x4c/0x361 [<ffffffff814dbc46>] mutex_lock_nested+0x40/0x45 [<ffffffff811daa87>] hugetlbfs_file_mmap+0x82/0x110 [<ffffffff81111557>] mmap_region+0x258/0x432 [<ffffffff811119dd>] do_mmap_pgoff+0x2ac/0x306 [<ffffffff81111b4f>] sys_mmap_pgoff+0x118/0x16a [<ffffffff8100c858>] sys_mmap+0x22/0x24 [<ffffffff814e3ec2>] system_call_fastpath+0x16/0x1b -> #0 (&mm->mmap_sem){++++++}: [<ffffffff8108a4bc>] __lock_acquire+0xa1a/0xcf7 [<ffffffff8108ac26>] lock_acquire+0xbf/0x103 [<ffffffff81109541>] might_fault+0x89/0xac [<ffffffff81149cff>] filldir+0x6f/0xc7 [<ffffffff811586ea>] dcache_readdir+0x67/0x205 [<ffffffff81149f54>] vfs_readdir+0x7b/0xb4 [<ffffffff8114a073>] sys_getdents+0x7e/0xd1 [<ffffffff814e3ec2>] system_call_fastpath+0x16/0x1b This patch moves the directory vs file lockdep annotation into a helper function that can be called by in-memory filesystems and has hugetlbfs call it. Signed-off-by: Josh Boyer <jwboyer@redhat.com> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-08-25 18:48:12 +07:00
lockdep_annotate_inode_mutex_key(inode);
} else
kref_put(&resv_map->refs, resv_map_release);
return inode;
}
/*
* File creation. Allocate an inode, and we're done..
*/
static int hugetlbfs_mknod(struct inode *dir,
struct dentry *dentry, umode_t mode, dev_t dev)
{
struct inode *inode;
int error = -ENOSPC;
inode = hugetlbfs_get_inode(dir->i_sb, dir, mode, dev);
if (inode) {
dir->i_ctime = dir->i_mtime = current_time(dir);
d_instantiate(dentry, inode);
dget(dentry); /* Extra count - pin the dentry in core */
error = 0;
}
return error;
}
static int hugetlbfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
{
int retval = hugetlbfs_mknod(dir, dentry, mode | S_IFDIR, 0);
if (!retval)
inc_nlink(dir);
return retval;
}
static int hugetlbfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, bool excl)
{
return hugetlbfs_mknod(dir, dentry, mode | S_IFREG, 0);
}
static int hugetlbfs_symlink(struct inode *dir,
struct dentry *dentry, const char *symname)
{
struct inode *inode;
int error = -ENOSPC;
inode = hugetlbfs_get_inode(dir->i_sb, dir, S_IFLNK|S_IRWXUGO, 0);
if (inode) {
int l = strlen(symname)+1;
error = page_symlink(inode, symname, l);
if (!error) {
d_instantiate(dentry, inode);
dget(dentry);
} else
iput(inode);
}
dir->i_ctime = dir->i_mtime = current_time(dir);
return error;
}
/*
* mark the head page dirty
*/
static int hugetlbfs_set_page_dirty(struct page *page)
{
2007-05-07 04:49:39 +07:00
struct page *head = compound_head(page);
SetPageDirty(head);
return 0;
}
static int hugetlbfs_migrate_page(struct address_space *mapping,
struct page *newpage, struct page *page,
enum migrate_mode mode)
{
int rc;
rc = migrate_huge_page_move_mapping(mapping, newpage, page);
mm: adjust address_space_operations.migratepage() return code Memory fragmentation introduced by ballooning might reduce significantly the number of 2MB contiguous memory blocks that can be used within a guest, thus imposing performance penalties associated with the reduced number of transparent huge pages that could be used by the guest workload. This patch-set follows the main idea discussed at 2012 LSFMMS session: "Ballooning for transparent huge pages" -- http://lwn.net/Articles/490114/ to introduce the required changes to the virtio_balloon driver, as well as the changes to the core compaction & migration bits, in order to make those subsystems aware of ballooned pages and allow memory balloon pages become movable within a guest, thus avoiding the aforementioned fragmentation issue Following are numbers that prove this patch benefits on allowing compaction to be more effective at memory ballooned guests. Results for STRESS-HIGHALLOC benchmark, from Mel Gorman's mmtests suite, running on a 4gB RAM KVM guest which was ballooning 512mB RAM in 64mB chunks, at every minute (inflating/deflating), while test was running: ===BEGIN stress-highalloc STRESS-HIGHALLOC highalloc-3.7 highalloc-3.7 rc4-clean rc4-patch Pass 1 55.00 ( 0.00%) 62.00 ( 7.00%) Pass 2 54.00 ( 0.00%) 62.00 ( 8.00%) while Rested 75.00 ( 0.00%) 80.00 ( 5.00%) MMTests Statistics: duration 3.7 3.7 rc4-clean rc4-patch User 1207.59 1207.46 System 1300.55 1299.61 Elapsed 2273.72 2157.06 MMTests Statistics: vmstat 3.7 3.7 rc4-clean rc4-patch Page Ins 3581516 2374368 Page Outs 11148692 10410332 Swap Ins 80 47 Swap Outs 3641 476 Direct pages scanned 37978 33826 Kswapd pages scanned 1828245 1342869 Kswapd pages reclaimed 1710236 1304099 Direct pages reclaimed 32207 31005 Kswapd efficiency 93% 97% Kswapd velocity 804.077 622.546 Direct efficiency 84% 91% Direct velocity 16.703 15.682 Percentage direct scans 2% 2% Page writes by reclaim 79252 9704 Page writes file 75611 9228 Page writes anon 3641 476 Page reclaim immediate 16764 11014 Page rescued immediate 0 0 Slabs scanned 2171904 2152448 Direct inode steals 385 2261 Kswapd inode steals 659137 609670 Kswapd skipped wait 1 69 THP fault alloc 546 631 THP collapse alloc 361 339 THP splits 259 263 THP fault fallback 98 50 THP collapse fail 20 17 Compaction stalls 747 499 Compaction success 244 145 Compaction failures 503 354 Compaction pages moved 370888 474837 Compaction move failure 77378 65259 ===END stress-highalloc This patch: Introduce MIGRATEPAGE_SUCCESS as the default return code for address_space_operations.migratepage() method and documents the expected return code for the same method in failure cases. Signed-off-by: Rafael Aquini <aquini@redhat.com> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: "Michael S. Tsirkin" <mst@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Mel Gorman <mel@csn.ul.ie> Cc: Andi Kleen <andi@firstfloor.org> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Minchan Kim <minchan@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-12-12 07:02:31 +07:00
if (rc != MIGRATEPAGE_SUCCESS)
return rc;
mm/migrate: new migrate mode MIGRATE_SYNC_NO_COPY Introduce a new migration mode that allow to offload the copy to a device DMA engine. This changes the workflow of migration and not all address_space migratepage callback can support this. This is intended to be use by migrate_vma() which itself is use for thing like HMM (see include/linux/hmm.h). No additional per-filesystem migratepage testing is needed. I disables MIGRATE_SYNC_NO_COPY in all problematic migratepage() callback and i added comment in those to explain why (part of this patch). The commit message is unclear it should say that any callback that wish to support this new mode need to be aware of the difference in the migration flow from other mode. Some of these callbacks do extra locking while copying (aio, zsmalloc, balloon, ...) and for DMA to be effective you want to copy multiple pages in one DMA operations. But in the problematic case you can not easily hold the extra lock accross multiple call to this callback. Usual flow is: For each page { 1 - lock page 2 - call migratepage() callback 3 - (extra locking in some migratepage() callback) 4 - migrate page state (freeze refcount, update page cache, buffer head, ...) 5 - copy page 6 - (unlock any extra lock of migratepage() callback) 7 - return from migratepage() callback 8 - unlock page } The new mode MIGRATE_SYNC_NO_COPY: 1 - lock multiple pages For each page { 2 - call migratepage() callback 3 - abort in all problematic migratepage() callback 4 - migrate page state (freeze refcount, update page cache, buffer head, ...) } // finished all calls to migratepage() callback 5 - DMA copy multiple pages 6 - unlock all the pages To support MIGRATE_SYNC_NO_COPY in the problematic case we would need a new callback migratepages() (for instance) that deals with multiple pages in one transaction. Because the problematic cases are not important for current usage I did not wanted to complexify this patchset even more for no good reason. Link: http://lkml.kernel.org/r/20170817000548.32038-14-jglisse@redhat.com Signed-off-by: Jérôme Glisse <jglisse@redhat.com> Cc: Aneesh Kumar <aneesh.kumar@linux.vnet.ibm.com> Cc: Balbir Singh <bsingharora@gmail.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Dan Williams <dan.j.williams@intel.com> Cc: David Nellans <dnellans@nvidia.com> Cc: Evgeny Baskakov <ebaskakov@nvidia.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Mark Hairgrove <mhairgrove@nvidia.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Sherry Cheung <SCheung@nvidia.com> Cc: Subhash Gutti <sgutti@nvidia.com> Cc: Vladimir Davydov <vdavydov.dev@gmail.com> Cc: Bob Liu <liubo95@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-09-09 06:12:06 +07:00
if (mode != MIGRATE_SYNC_NO_COPY)
migrate_page_copy(newpage, page);
else
migrate_page_states(newpage, page);
mm: adjust address_space_operations.migratepage() return code Memory fragmentation introduced by ballooning might reduce significantly the number of 2MB contiguous memory blocks that can be used within a guest, thus imposing performance penalties associated with the reduced number of transparent huge pages that could be used by the guest workload. This patch-set follows the main idea discussed at 2012 LSFMMS session: "Ballooning for transparent huge pages" -- http://lwn.net/Articles/490114/ to introduce the required changes to the virtio_balloon driver, as well as the changes to the core compaction & migration bits, in order to make those subsystems aware of ballooned pages and allow memory balloon pages become movable within a guest, thus avoiding the aforementioned fragmentation issue Following are numbers that prove this patch benefits on allowing compaction to be more effective at memory ballooned guests. Results for STRESS-HIGHALLOC benchmark, from Mel Gorman's mmtests suite, running on a 4gB RAM KVM guest which was ballooning 512mB RAM in 64mB chunks, at every minute (inflating/deflating), while test was running: ===BEGIN stress-highalloc STRESS-HIGHALLOC highalloc-3.7 highalloc-3.7 rc4-clean rc4-patch Pass 1 55.00 ( 0.00%) 62.00 ( 7.00%) Pass 2 54.00 ( 0.00%) 62.00 ( 8.00%) while Rested 75.00 ( 0.00%) 80.00 ( 5.00%) MMTests Statistics: duration 3.7 3.7 rc4-clean rc4-patch User 1207.59 1207.46 System 1300.55 1299.61 Elapsed 2273.72 2157.06 MMTests Statistics: vmstat 3.7 3.7 rc4-clean rc4-patch Page Ins 3581516 2374368 Page Outs 11148692 10410332 Swap Ins 80 47 Swap Outs 3641 476 Direct pages scanned 37978 33826 Kswapd pages scanned 1828245 1342869 Kswapd pages reclaimed 1710236 1304099 Direct pages reclaimed 32207 31005 Kswapd efficiency 93% 97% Kswapd velocity 804.077 622.546 Direct efficiency 84% 91% Direct velocity 16.703 15.682 Percentage direct scans 2% 2% Page writes by reclaim 79252 9704 Page writes file 75611 9228 Page writes anon 3641 476 Page reclaim immediate 16764 11014 Page rescued immediate 0 0 Slabs scanned 2171904 2152448 Direct inode steals 385 2261 Kswapd inode steals 659137 609670 Kswapd skipped wait 1 69 THP fault alloc 546 631 THP collapse alloc 361 339 THP splits 259 263 THP fault fallback 98 50 THP collapse fail 20 17 Compaction stalls 747 499 Compaction success 244 145 Compaction failures 503 354 Compaction pages moved 370888 474837 Compaction move failure 77378 65259 ===END stress-highalloc This patch: Introduce MIGRATEPAGE_SUCCESS as the default return code for address_space_operations.migratepage() method and documents the expected return code for the same method in failure cases. Signed-off-by: Rafael Aquini <aquini@redhat.com> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: "Michael S. Tsirkin" <mst@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Mel Gorman <mel@csn.ul.ie> Cc: Andi Kleen <andi@firstfloor.org> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Minchan Kim <minchan@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-12-12 07:02:31 +07:00
return MIGRATEPAGE_SUCCESS;
}
mm: hwpoison: dissolve in-use hugepage in unrecoverable memory error Currently me_huge_page() relies on dequeue_hwpoisoned_huge_page() to keep the error hugepage away from the system, which is OK but not good enough because the hugepage still has a refcount and unpoison doesn't work on the error hugepage (PageHWPoison flags are cleared but pages are still leaked.) And there's "wasting health subpages" issue too. This patch reworks on me_huge_page() to solve these issues. For hugetlb file, recently we have truncating code so let's use it in hugetlbfs specific ->error_remove_page(). For anonymous hugepage, it's helpful to dissolve the error page after freeing it into free hugepage list. Migration entry and PageHWPoison in the head page prevent the access to it. TODO: dissolve_free_huge_page() can fail but we don't considered it yet. It's not critical (and at least no worse that now) because in such case the error hugepage just stays in free hugepage list without being dissolved. By virtue of PageHWPoison in head page, it's never allocated to processes. [akpm@linux-foundation.org: fix unused var warnings] Fixes: 23a003bfd23ea9ea0b7756b920e51f64b284b468 ("mm/madvise: pass return code of memory_failure() to userspace") Link: http://lkml.kernel.org/r/20170417055948.GM31394@yexl-desktop Link: http://lkml.kernel.org/r/1496305019-5493-8-git-send-email-n-horiguchi@ah.jp.nec.com Signed-off-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Reported-by: kernel test robot <lkp@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-07-11 05:47:50 +07:00
static int hugetlbfs_error_remove_page(struct address_space *mapping,
struct page *page)
{
struct inode *inode = mapping->host;
pgoff_t index = page->index;
mm: hwpoison: dissolve in-use hugepage in unrecoverable memory error Currently me_huge_page() relies on dequeue_hwpoisoned_huge_page() to keep the error hugepage away from the system, which is OK but not good enough because the hugepage still has a refcount and unpoison doesn't work on the error hugepage (PageHWPoison flags are cleared but pages are still leaked.) And there's "wasting health subpages" issue too. This patch reworks on me_huge_page() to solve these issues. For hugetlb file, recently we have truncating code so let's use it in hugetlbfs specific ->error_remove_page(). For anonymous hugepage, it's helpful to dissolve the error page after freeing it into free hugepage list. Migration entry and PageHWPoison in the head page prevent the access to it. TODO: dissolve_free_huge_page() can fail but we don't considered it yet. It's not critical (and at least no worse that now) because in such case the error hugepage just stays in free hugepage list without being dissolved. By virtue of PageHWPoison in head page, it's never allocated to processes. [akpm@linux-foundation.org: fix unused var warnings] Fixes: 23a003bfd23ea9ea0b7756b920e51f64b284b468 ("mm/madvise: pass return code of memory_failure() to userspace") Link: http://lkml.kernel.org/r/20170417055948.GM31394@yexl-desktop Link: http://lkml.kernel.org/r/1496305019-5493-8-git-send-email-n-horiguchi@ah.jp.nec.com Signed-off-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Reported-by: kernel test robot <lkp@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-07-11 05:47:50 +07:00
remove_huge_page(page);
if (unlikely(hugetlb_unreserve_pages(inode, index, index + 1, 1)))
hugetlb_fix_reserve_counts(inode);
mm: hwpoison: dissolve in-use hugepage in unrecoverable memory error Currently me_huge_page() relies on dequeue_hwpoisoned_huge_page() to keep the error hugepage away from the system, which is OK but not good enough because the hugepage still has a refcount and unpoison doesn't work on the error hugepage (PageHWPoison flags are cleared but pages are still leaked.) And there's "wasting health subpages" issue too. This patch reworks on me_huge_page() to solve these issues. For hugetlb file, recently we have truncating code so let's use it in hugetlbfs specific ->error_remove_page(). For anonymous hugepage, it's helpful to dissolve the error page after freeing it into free hugepage list. Migration entry and PageHWPoison in the head page prevent the access to it. TODO: dissolve_free_huge_page() can fail but we don't considered it yet. It's not critical (and at least no worse that now) because in such case the error hugepage just stays in free hugepage list without being dissolved. By virtue of PageHWPoison in head page, it's never allocated to processes. [akpm@linux-foundation.org: fix unused var warnings] Fixes: 23a003bfd23ea9ea0b7756b920e51f64b284b468 ("mm/madvise: pass return code of memory_failure() to userspace") Link: http://lkml.kernel.org/r/20170417055948.GM31394@yexl-desktop Link: http://lkml.kernel.org/r/1496305019-5493-8-git-send-email-n-horiguchi@ah.jp.nec.com Signed-off-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Reported-by: kernel test robot <lkp@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-07-11 05:47:50 +07:00
return 0;
}
/*
* Display the mount options in /proc/mounts.
*/
static int hugetlbfs_show_options(struct seq_file *m, struct dentry *root)
{
struct hugetlbfs_sb_info *sbinfo = HUGETLBFS_SB(root->d_sb);
struct hugepage_subpool *spool = sbinfo->spool;
unsigned long hpage_size = huge_page_size(sbinfo->hstate);
unsigned hpage_shift = huge_page_shift(sbinfo->hstate);
char mod;
if (!uid_eq(sbinfo->uid, GLOBAL_ROOT_UID))
seq_printf(m, ",uid=%u",
from_kuid_munged(&init_user_ns, sbinfo->uid));
if (!gid_eq(sbinfo->gid, GLOBAL_ROOT_GID))
seq_printf(m, ",gid=%u",
from_kgid_munged(&init_user_ns, sbinfo->gid));
if (sbinfo->mode != 0755)
seq_printf(m, ",mode=%o", sbinfo->mode);
if (sbinfo->max_inodes != -1)
seq_printf(m, ",nr_inodes=%lu", sbinfo->max_inodes);
hpage_size /= 1024;
mod = 'K';
if (hpage_size >= 1024) {
hpage_size /= 1024;
mod = 'M';
}
seq_printf(m, ",pagesize=%lu%c", hpage_size, mod);
if (spool) {
if (spool->max_hpages != -1)
seq_printf(m, ",size=%llu",
(unsigned long long)spool->max_hpages << hpage_shift);
if (spool->min_hpages != -1)
seq_printf(m, ",min_size=%llu",
(unsigned long long)spool->min_hpages << hpage_shift);
}
return 0;
}
static int hugetlbfs_statfs(struct dentry *dentry, struct kstatfs *buf)
{
struct hugetlbfs_sb_info *sbinfo = HUGETLBFS_SB(dentry->d_sb);
struct hstate *h = hstate_inode(d_inode(dentry));
buf->f_type = HUGETLBFS_MAGIC;
buf->f_bsize = huge_page_size(h);
if (sbinfo) {
spin_lock(&sbinfo->stat_lock);
/* If no limits set, just report 0 for max/free/used
* blocks, like simple_statfs() */
hugepages: fix use after free bug in "quota" handling hugetlbfs_{get,put}_quota() are badly named. They don't interact with the general quota handling code, and they don't much resemble its behaviour. Rather than being about maintaining limits on on-disk block usage by particular users, they are instead about maintaining limits on in-memory page usage (including anonymous MAP_PRIVATE copied-on-write pages) associated with a particular hugetlbfs filesystem instance. Worse, they work by having callbacks to the hugetlbfs filesystem code from the low-level page handling code, in particular from free_huge_page(). This is a layering violation of itself, but more importantly, if the kernel does a get_user_pages() on hugepages (which can happen from KVM amongst others), then the free_huge_page() can be delayed until after the associated inode has already been freed. If an unmount occurs at the wrong time, even the hugetlbfs superblock where the "quota" limits are stored may have been freed. Andrew Barry proposed a patch to fix this by having hugepages, instead of storing a pointer to their address_space and reaching the superblock from there, had the hugepages store pointers directly to the superblock, bumping the reference count as appropriate to avoid it being freed. Andrew Morton rejected that version, however, on the grounds that it made the existing layering violation worse. This is a reworked version of Andrew's patch, which removes the extra, and some of the existing, layering violation. It works by introducing the concept of a hugepage "subpool" at the lower hugepage mm layer - that is a finite logical pool of hugepages to allocate from. hugetlbfs now creates a subpool for each filesystem instance with a page limit set, and a pointer to the subpool gets added to each allocated hugepage, instead of the address_space pointer used now. The subpool has its own lifetime and is only freed once all pages in it _and_ all other references to it (i.e. superblocks) are gone. subpools are optional - a NULL subpool pointer is taken by the code to mean that no subpool limits are in effect. Previous discussion of this bug found in: "Fix refcounting in hugetlbfs quota handling.". See: https://lkml.org/lkml/2011/8/11/28 or http://marc.info/?l=linux-mm&m=126928970510627&w=1 v2: Fixed a bug spotted by Hillf Danton, and removed the extra parameter to alloc_huge_page() - since it already takes the vma, it is not necessary. Signed-off-by: Andrew Barry <abarry@cray.com> Signed-off-by: David Gibson <david@gibson.dropbear.id.au> Cc: Hugh Dickins <hughd@google.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Minchan Kim <minchan.kim@gmail.com> Cc: Hillf Danton <dhillf@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-03-22 06:34:12 +07:00
if (sbinfo->spool) {
long free_pages;
spin_lock(&sbinfo->spool->lock);
buf->f_blocks = sbinfo->spool->max_hpages;
free_pages = sbinfo->spool->max_hpages
- sbinfo->spool->used_hpages;
buf->f_bavail = buf->f_bfree = free_pages;
spin_unlock(&sbinfo->spool->lock);
buf->f_files = sbinfo->max_inodes;
buf->f_ffree = sbinfo->free_inodes;
}
spin_unlock(&sbinfo->stat_lock);
}
buf->f_namelen = NAME_MAX;
return 0;
}
static void hugetlbfs_put_super(struct super_block *sb)
{
struct hugetlbfs_sb_info *sbi = HUGETLBFS_SB(sb);
if (sbi) {
sb->s_fs_info = NULL;
hugepages: fix use after free bug in "quota" handling hugetlbfs_{get,put}_quota() are badly named. They don't interact with the general quota handling code, and they don't much resemble its behaviour. Rather than being about maintaining limits on on-disk block usage by particular users, they are instead about maintaining limits on in-memory page usage (including anonymous MAP_PRIVATE copied-on-write pages) associated with a particular hugetlbfs filesystem instance. Worse, they work by having callbacks to the hugetlbfs filesystem code from the low-level page handling code, in particular from free_huge_page(). This is a layering violation of itself, but more importantly, if the kernel does a get_user_pages() on hugepages (which can happen from KVM amongst others), then the free_huge_page() can be delayed until after the associated inode has already been freed. If an unmount occurs at the wrong time, even the hugetlbfs superblock where the "quota" limits are stored may have been freed. Andrew Barry proposed a patch to fix this by having hugepages, instead of storing a pointer to their address_space and reaching the superblock from there, had the hugepages store pointers directly to the superblock, bumping the reference count as appropriate to avoid it being freed. Andrew Morton rejected that version, however, on the grounds that it made the existing layering violation worse. This is a reworked version of Andrew's patch, which removes the extra, and some of the existing, layering violation. It works by introducing the concept of a hugepage "subpool" at the lower hugepage mm layer - that is a finite logical pool of hugepages to allocate from. hugetlbfs now creates a subpool for each filesystem instance with a page limit set, and a pointer to the subpool gets added to each allocated hugepage, instead of the address_space pointer used now. The subpool has its own lifetime and is only freed once all pages in it _and_ all other references to it (i.e. superblocks) are gone. subpools are optional - a NULL subpool pointer is taken by the code to mean that no subpool limits are in effect. Previous discussion of this bug found in: "Fix refcounting in hugetlbfs quota handling.". See: https://lkml.org/lkml/2011/8/11/28 or http://marc.info/?l=linux-mm&m=126928970510627&w=1 v2: Fixed a bug spotted by Hillf Danton, and removed the extra parameter to alloc_huge_page() - since it already takes the vma, it is not necessary. Signed-off-by: Andrew Barry <abarry@cray.com> Signed-off-by: David Gibson <david@gibson.dropbear.id.au> Cc: Hugh Dickins <hughd@google.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Minchan Kim <minchan.kim@gmail.com> Cc: Hillf Danton <dhillf@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-03-22 06:34:12 +07:00
if (sbi->spool)
hugepage_put_subpool(sbi->spool);
kfree(sbi);
}
}
static inline int hugetlbfs_dec_free_inodes(struct hugetlbfs_sb_info *sbinfo)
{
if (sbinfo->free_inodes >= 0) {
spin_lock(&sbinfo->stat_lock);
if (unlikely(!sbinfo->free_inodes)) {
spin_unlock(&sbinfo->stat_lock);
return 0;
}
sbinfo->free_inodes--;
spin_unlock(&sbinfo->stat_lock);
}
return 1;
}
static void hugetlbfs_inc_free_inodes(struct hugetlbfs_sb_info *sbinfo)
{
if (sbinfo->free_inodes >= 0) {
spin_lock(&sbinfo->stat_lock);
sbinfo->free_inodes++;
spin_unlock(&sbinfo->stat_lock);
}
}
static struct kmem_cache *hugetlbfs_inode_cachep;
static struct inode *hugetlbfs_alloc_inode(struct super_block *sb)
{
struct hugetlbfs_sb_info *sbinfo = HUGETLBFS_SB(sb);
struct hugetlbfs_inode_info *p;
if (unlikely(!hugetlbfs_dec_free_inodes(sbinfo)))
return NULL;
p = kmem_cache_alloc(hugetlbfs_inode_cachep, GFP_KERNEL);
if (unlikely(!p)) {
hugetlbfs_inc_free_inodes(sbinfo);
return NULL;
}
hugetlbfs: initialize shared policy as part of inode allocation Any time after inode allocation, destroy_inode can be called. The hugetlbfs inode contains a shared_policy structure, and mpol_free_shared_policy is unconditionally called as part of hugetlbfs_destroy_inode. Initialize the policy as part of inode allocation so that any quick (error path) calls to destroy_inode will be handed an initialized policy. syzkaller fuzzer found this bug, that resulted in the following: BUG: KASAN: user-memory-access in atomic_inc include/asm-generic/atomic-instrumented.h:87 [inline] at addr 000000131730bd7a BUG: KASAN: user-memory-access in __lock_acquire+0x21a/0x3a80 kernel/locking/lockdep.c:3239 at addr 000000131730bd7a Write of size 4 by task syz-executor6/14086 CPU: 3 PID: 14086 Comm: syz-executor6 Not tainted 4.11.0-rc3+ #364 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011 Call Trace: atomic_inc include/asm-generic/atomic-instrumented.h:87 [inline] __lock_acquire+0x21a/0x3a80 kernel/locking/lockdep.c:3239 lock_acquire+0x1ee/0x590 kernel/locking/lockdep.c:3762 __raw_write_lock include/linux/rwlock_api_smp.h:210 [inline] _raw_write_lock+0x33/0x50 kernel/locking/spinlock.c:295 mpol_free_shared_policy+0x43/0xb0 mm/mempolicy.c:2536 hugetlbfs_destroy_inode+0xca/0x120 fs/hugetlbfs/inode.c:952 alloc_inode+0x10d/0x180 fs/inode.c:216 new_inode_pseudo+0x69/0x190 fs/inode.c:889 new_inode+0x1c/0x40 fs/inode.c:918 hugetlbfs_get_inode+0x40/0x420 fs/hugetlbfs/inode.c:734 hugetlb_file_setup+0x329/0x9f0 fs/hugetlbfs/inode.c:1282 newseg+0x422/0xd30 ipc/shm.c:575 ipcget_new ipc/util.c:285 [inline] ipcget+0x21e/0x580 ipc/util.c:639 SYSC_shmget ipc/shm.c:673 [inline] SyS_shmget+0x158/0x230 ipc/shm.c:657 entry_SYSCALL_64_fastpath+0x1f/0xc2 Analysis provided by Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Link: http://lkml.kernel.org/r/1490477850-7944-1-git-send-email-mike.kravetz@oracle.com Signed-off-by: Mike Kravetz <mike.kravetz@oracle.com> Reported-by: Dmitry Vyukov <dvyukov@google.com> Acked-by: Hillf Danton <hillf.zj@alibaba-inc.com> Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Cc: Michal Hocko <mhocko@suse.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-04-01 05:12:01 +07:00
/*
* Any time after allocation, hugetlbfs_destroy_inode can be called
* for the inode. mpol_free_shared_policy is unconditionally called
* as part of hugetlbfs_destroy_inode. So, initialize policy here
* in case of a quick call to destroy.
*
* Note that the policy is initialized even if we are creating a
* private inode. This simplifies hugetlbfs_destroy_inode.
*/
mpol_shared_policy_init(&p->policy, NULL);
return &p->vfs_inode;
}
2011-01-07 13:49:49 +07:00
static void hugetlbfs_i_callback(struct rcu_head *head)
{
struct inode *inode = container_of(head, struct inode, i_rcu);
kmem_cache_free(hugetlbfs_inode_cachep, HUGETLBFS_I(inode));
}
static void hugetlbfs_destroy_inode(struct inode *inode)
{
hugetlbfs_inc_free_inodes(HUGETLBFS_SB(inode->i_sb));
mpol_free_shared_policy(&HUGETLBFS_I(inode)->policy);
2011-01-07 13:49:49 +07:00
call_rcu(&inode->i_rcu, hugetlbfs_i_callback);
}
static const struct address_space_operations hugetlbfs_aops = {
.write_begin = hugetlbfs_write_begin,
.write_end = hugetlbfs_write_end,
.set_page_dirty = hugetlbfs_set_page_dirty,
.migratepage = hugetlbfs_migrate_page,
mm: hwpoison: dissolve in-use hugepage in unrecoverable memory error Currently me_huge_page() relies on dequeue_hwpoisoned_huge_page() to keep the error hugepage away from the system, which is OK but not good enough because the hugepage still has a refcount and unpoison doesn't work on the error hugepage (PageHWPoison flags are cleared but pages are still leaked.) And there's "wasting health subpages" issue too. This patch reworks on me_huge_page() to solve these issues. For hugetlb file, recently we have truncating code so let's use it in hugetlbfs specific ->error_remove_page(). For anonymous hugepage, it's helpful to dissolve the error page after freeing it into free hugepage list. Migration entry and PageHWPoison in the head page prevent the access to it. TODO: dissolve_free_huge_page() can fail but we don't considered it yet. It's not critical (and at least no worse that now) because in such case the error hugepage just stays in free hugepage list without being dissolved. By virtue of PageHWPoison in head page, it's never allocated to processes. [akpm@linux-foundation.org: fix unused var warnings] Fixes: 23a003bfd23ea9ea0b7756b920e51f64b284b468 ("mm/madvise: pass return code of memory_failure() to userspace") Link: http://lkml.kernel.org/r/20170417055948.GM31394@yexl-desktop Link: http://lkml.kernel.org/r/1496305019-5493-8-git-send-email-n-horiguchi@ah.jp.nec.com Signed-off-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Reported-by: kernel test robot <lkp@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-07-11 05:47:50 +07:00
.error_remove_page = hugetlbfs_error_remove_page,
};
static void init_once(void *foo)
{
struct hugetlbfs_inode_info *ei = (struct hugetlbfs_inode_info *)foo;
inode_init_once(&ei->vfs_inode);
}
const struct file_operations hugetlbfs_file_operations = {
.read_iter = hugetlbfs_read_iter,
.mmap = hugetlbfs_file_mmap,
.fsync = noop_fsync,
.get_unmapped_area = hugetlb_get_unmapped_area,
.llseek = default_llseek,
.fallocate = hugetlbfs_fallocate,
};
static const struct inode_operations hugetlbfs_dir_inode_operations = {
.create = hugetlbfs_create,
.lookup = simple_lookup,
.link = simple_link,
.unlink = simple_unlink,
.symlink = hugetlbfs_symlink,
.mkdir = hugetlbfs_mkdir,
.rmdir = simple_rmdir,
.mknod = hugetlbfs_mknod,
.rename = simple_rename,
.setattr = hugetlbfs_setattr,
};
static const struct inode_operations hugetlbfs_inode_operations = {
.setattr = hugetlbfs_setattr,
};
static const struct super_operations hugetlbfs_ops = {
.alloc_inode = hugetlbfs_alloc_inode,
.destroy_inode = hugetlbfs_destroy_inode,
.evict_inode = hugetlbfs_evict_inode,
.statfs = hugetlbfs_statfs,
.put_super = hugetlbfs_put_super,
.show_options = hugetlbfs_show_options,
};
enum hugetlbfs_size_type { NO_SIZE, SIZE_STD, SIZE_PERCENT };
/*
* Convert size option passed from command line to number of huge pages
* in the pool specified by hstate. Size option could be in bytes
* (val_type == SIZE_STD) or percentage of the pool (val_type == SIZE_PERCENT).
*/
static long
hugetlbfs_size_to_hpages(struct hstate *h, unsigned long long size_opt,
enum hugetlbfs_size_type val_type)
{
if (val_type == NO_SIZE)
return -1;
if (val_type == SIZE_PERCENT) {
size_opt <<= huge_page_shift(h);
size_opt *= h->max_huge_pages;
do_div(size_opt, 100);
}
size_opt >>= huge_page_shift(h);
return size_opt;
}
static int
hugetlbfs_parse_options(char *options, struct hugetlbfs_config *pconfig)
{
char *p, *rest;
substring_t args[MAX_OPT_ARGS];
int option;
unsigned long long max_size_opt = 0, min_size_opt = 0;
enum hugetlbfs_size_type max_val_type = NO_SIZE, min_val_type = NO_SIZE;
if (!options)
return 0;
while ((p = strsep(&options, ",")) != NULL) {
int token;
if (!*p)
continue;
token = match_token(p, tokens, args);
switch (token) {
case Opt_uid:
if (match_int(&args[0], &option))
goto bad_val;
pconfig->uid = make_kuid(current_user_ns(), option);
if (!uid_valid(pconfig->uid))
goto bad_val;
break;
case Opt_gid:
if (match_int(&args[0], &option))
goto bad_val;
pconfig->gid = make_kgid(current_user_ns(), option);
if (!gid_valid(pconfig->gid))
goto bad_val;
break;
case Opt_mode:
if (match_octal(&args[0], &option))
goto bad_val;
pconfig->mode = option & 01777U;
break;
case Opt_size: {
/* memparse() will accept a K/M/G without a digit */
if (!isdigit(*args[0].from))
goto bad_val;
max_size_opt = memparse(args[0].from, &rest);
max_val_type = SIZE_STD;
if (*rest == '%')
max_val_type = SIZE_PERCENT;
break;
}
case Opt_nr_inodes:
/* memparse() will accept a K/M/G without a digit */
if (!isdigit(*args[0].from))
goto bad_val;
pconfig->nr_inodes = memparse(args[0].from, &rest);
break;
case Opt_pagesize: {
unsigned long ps;
ps = memparse(args[0].from, &rest);
pconfig->hstate = size_to_hstate(ps);
if (!pconfig->hstate) {
pr_err("Unsupported page size %lu MB\n",
ps >> 20);
return -EINVAL;
}
break;
}
case Opt_min_size: {
/* memparse() will accept a K/M/G without a digit */
if (!isdigit(*args[0].from))
goto bad_val;
min_size_opt = memparse(args[0].from, &rest);
min_val_type = SIZE_STD;
if (*rest == '%')
min_val_type = SIZE_PERCENT;
break;
}
default:
pr_err("Bad mount option: \"%s\"\n", p);
return -EINVAL;
break;
}
}
/*
* Use huge page pool size (in hstate) to convert the size
* options to number of huge pages. If NO_SIZE, -1 is returned.
*/
pconfig->max_hpages = hugetlbfs_size_to_hpages(pconfig->hstate,
max_size_opt, max_val_type);
pconfig->min_hpages = hugetlbfs_size_to_hpages(pconfig->hstate,
min_size_opt, min_val_type);
/*
* If max_size was specified, then min_size must be smaller
*/
if (max_val_type > NO_SIZE &&
pconfig->min_hpages > pconfig->max_hpages) {
pr_err("minimum size can not be greater than maximum size\n");
return -EINVAL;
}
return 0;
bad_val:
pr_err("Bad value '%s' for mount option '%s'\n", args[0].from, p);
return -EINVAL;
}
static int
hugetlbfs_fill_super(struct super_block *sb, void *data, int silent)
{
int ret;
struct hugetlbfs_config config;
struct hugetlbfs_sb_info *sbinfo;
config.max_hpages = -1; /* No limit on size by default */
config.nr_inodes = -1; /* No limit on number of inodes by default */
config.uid = current_fsuid();
config.gid = current_fsgid();
config.mode = 0755;
config.hstate = &default_hstate;
config.min_hpages = -1; /* No default minimum size */
ret = hugetlbfs_parse_options(data, &config);
if (ret)
return ret;
sbinfo = kmalloc(sizeof(struct hugetlbfs_sb_info), GFP_KERNEL);
if (!sbinfo)
return -ENOMEM;
sb->s_fs_info = sbinfo;
sbinfo->hstate = config.hstate;
spin_lock_init(&sbinfo->stat_lock);
sbinfo->max_inodes = config.nr_inodes;
sbinfo->free_inodes = config.nr_inodes;
hugepages: fix use after free bug in "quota" handling hugetlbfs_{get,put}_quota() are badly named. They don't interact with the general quota handling code, and they don't much resemble its behaviour. Rather than being about maintaining limits on on-disk block usage by particular users, they are instead about maintaining limits on in-memory page usage (including anonymous MAP_PRIVATE copied-on-write pages) associated with a particular hugetlbfs filesystem instance. Worse, they work by having callbacks to the hugetlbfs filesystem code from the low-level page handling code, in particular from free_huge_page(). This is a layering violation of itself, but more importantly, if the kernel does a get_user_pages() on hugepages (which can happen from KVM amongst others), then the free_huge_page() can be delayed until after the associated inode has already been freed. If an unmount occurs at the wrong time, even the hugetlbfs superblock where the "quota" limits are stored may have been freed. Andrew Barry proposed a patch to fix this by having hugepages, instead of storing a pointer to their address_space and reaching the superblock from there, had the hugepages store pointers directly to the superblock, bumping the reference count as appropriate to avoid it being freed. Andrew Morton rejected that version, however, on the grounds that it made the existing layering violation worse. This is a reworked version of Andrew's patch, which removes the extra, and some of the existing, layering violation. It works by introducing the concept of a hugepage "subpool" at the lower hugepage mm layer - that is a finite logical pool of hugepages to allocate from. hugetlbfs now creates a subpool for each filesystem instance with a page limit set, and a pointer to the subpool gets added to each allocated hugepage, instead of the address_space pointer used now. The subpool has its own lifetime and is only freed once all pages in it _and_ all other references to it (i.e. superblocks) are gone. subpools are optional - a NULL subpool pointer is taken by the code to mean that no subpool limits are in effect. Previous discussion of this bug found in: "Fix refcounting in hugetlbfs quota handling.". See: https://lkml.org/lkml/2011/8/11/28 or http://marc.info/?l=linux-mm&m=126928970510627&w=1 v2: Fixed a bug spotted by Hillf Danton, and removed the extra parameter to alloc_huge_page() - since it already takes the vma, it is not necessary. Signed-off-by: Andrew Barry <abarry@cray.com> Signed-off-by: David Gibson <david@gibson.dropbear.id.au> Cc: Hugh Dickins <hughd@google.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Minchan Kim <minchan.kim@gmail.com> Cc: Hillf Danton <dhillf@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-03-22 06:34:12 +07:00
sbinfo->spool = NULL;
sbinfo->uid = config.uid;
sbinfo->gid = config.gid;
sbinfo->mode = config.mode;
/*
* Allocate and initialize subpool if maximum or minimum size is
* specified. Any needed reservations (for minimim size) are taken
* taken when the subpool is created.
*/
if (config.max_hpages != -1 || config.min_hpages != -1) {
sbinfo->spool = hugepage_new_subpool(config.hstate,
config.max_hpages,
config.min_hpages);
hugepages: fix use after free bug in "quota" handling hugetlbfs_{get,put}_quota() are badly named. They don't interact with the general quota handling code, and they don't much resemble its behaviour. Rather than being about maintaining limits on on-disk block usage by particular users, they are instead about maintaining limits on in-memory page usage (including anonymous MAP_PRIVATE copied-on-write pages) associated with a particular hugetlbfs filesystem instance. Worse, they work by having callbacks to the hugetlbfs filesystem code from the low-level page handling code, in particular from free_huge_page(). This is a layering violation of itself, but more importantly, if the kernel does a get_user_pages() on hugepages (which can happen from KVM amongst others), then the free_huge_page() can be delayed until after the associated inode has already been freed. If an unmount occurs at the wrong time, even the hugetlbfs superblock where the "quota" limits are stored may have been freed. Andrew Barry proposed a patch to fix this by having hugepages, instead of storing a pointer to their address_space and reaching the superblock from there, had the hugepages store pointers directly to the superblock, bumping the reference count as appropriate to avoid it being freed. Andrew Morton rejected that version, however, on the grounds that it made the existing layering violation worse. This is a reworked version of Andrew's patch, which removes the extra, and some of the existing, layering violation. It works by introducing the concept of a hugepage "subpool" at the lower hugepage mm layer - that is a finite logical pool of hugepages to allocate from. hugetlbfs now creates a subpool for each filesystem instance with a page limit set, and a pointer to the subpool gets added to each allocated hugepage, instead of the address_space pointer used now. The subpool has its own lifetime and is only freed once all pages in it _and_ all other references to it (i.e. superblocks) are gone. subpools are optional - a NULL subpool pointer is taken by the code to mean that no subpool limits are in effect. Previous discussion of this bug found in: "Fix refcounting in hugetlbfs quota handling.". See: https://lkml.org/lkml/2011/8/11/28 or http://marc.info/?l=linux-mm&m=126928970510627&w=1 v2: Fixed a bug spotted by Hillf Danton, and removed the extra parameter to alloc_huge_page() - since it already takes the vma, it is not necessary. Signed-off-by: Andrew Barry <abarry@cray.com> Signed-off-by: David Gibson <david@gibson.dropbear.id.au> Cc: Hugh Dickins <hughd@google.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Minchan Kim <minchan.kim@gmail.com> Cc: Hillf Danton <dhillf@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-03-22 06:34:12 +07:00
if (!sbinfo->spool)
goto out_free;
}
sb->s_maxbytes = MAX_LFS_FILESIZE;
sb->s_blocksize = huge_page_size(config.hstate);
sb->s_blocksize_bits = huge_page_shift(config.hstate);
sb->s_magic = HUGETLBFS_MAGIC;
sb->s_op = &hugetlbfs_ops;
sb->s_time_gran = 1;
sb->s_root = d_make_root(hugetlbfs_get_root(sb, &config));
if (!sb->s_root)
goto out_free;
return 0;
out_free:
kfree(sbinfo->spool);
kfree(sbinfo);
return -ENOMEM;
}
static struct dentry *hugetlbfs_mount(struct file_system_type *fs_type,
int flags, const char *dev_name, void *data)
{
return mount_nodev(fs_type, flags, data, hugetlbfs_fill_super);
}
static struct file_system_type hugetlbfs_fs_type = {
.name = "hugetlbfs",
.mount = hugetlbfs_mount,
.kill_sb = kill_litter_super,
};
mm: support more pagesizes for MAP_HUGETLB/SHM_HUGETLB There was some desire in large applications using MAP_HUGETLB or SHM_HUGETLB to use 1GB huge pages on some mappings, and stay with 2MB on others. This is useful together with NUMA policy: use 2MB interleaving on some mappings, but 1GB on local mappings. This patch extends the IPC/SHM syscall interfaces slightly to allow specifying the page size. It borrows some upper bits in the existing flag arguments and allows encoding the log of the desired page size in addition to the *_HUGETLB flag. When 0 is specified the default size is used, this makes the change fully compatible. Extending the internal hugetlb code to handle this is straight forward. Instead of a single mount it just keeps an array of them and selects the right mount based on the specified page size. When no page size is specified it uses the mount of the default page size. The change is not visible in /proc/mounts because internal mounts don't appear there. It also has very little overhead: the additional mounts just consume a super block, but not more memory when not used. I also exported the new flags to the user headers (they were previously under __KERNEL__). Right now only symbols for x86 and some other architecture for 1GB and 2MB are defined. The interface should already work for all other architectures though. Only architectures that define multiple hugetlb sizes actually need it (that is currently x86, tile, powerpc). However tile and powerpc have user configurable hugetlb sizes, so it's not easy to add defines. A program on those architectures would need to query sysfs and use the appropiate log2. [akpm@linux-foundation.org: cleanups] [rientjes@google.com: fix build] [akpm@linux-foundation.org: checkpatch fixes] Signed-off-by: Andi Kleen <ak@linux.intel.com> Cc: Michael Kerrisk <mtk.manpages@gmail.com> Acked-by: Rik van Riel <riel@redhat.com> Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Hillf Danton <dhillf@gmail.com> Signed-off-by: David Rientjes <rientjes@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-12-12 07:01:34 +07:00
static struct vfsmount *hugetlbfs_vfsmount[HUGE_MAX_HSTATE];
static int can_do_hugetlb_shm(void)
{
kgid_t shm_group;
shm_group = make_kgid(&init_user_ns, sysctl_hugetlb_shm_group);
return capable(CAP_IPC_LOCK) || in_group_p(shm_group);
}
mm: support more pagesizes for MAP_HUGETLB/SHM_HUGETLB There was some desire in large applications using MAP_HUGETLB or SHM_HUGETLB to use 1GB huge pages on some mappings, and stay with 2MB on others. This is useful together with NUMA policy: use 2MB interleaving on some mappings, but 1GB on local mappings. This patch extends the IPC/SHM syscall interfaces slightly to allow specifying the page size. It borrows some upper bits in the existing flag arguments and allows encoding the log of the desired page size in addition to the *_HUGETLB flag. When 0 is specified the default size is used, this makes the change fully compatible. Extending the internal hugetlb code to handle this is straight forward. Instead of a single mount it just keeps an array of them and selects the right mount based on the specified page size. When no page size is specified it uses the mount of the default page size. The change is not visible in /proc/mounts because internal mounts don't appear there. It also has very little overhead: the additional mounts just consume a super block, but not more memory when not used. I also exported the new flags to the user headers (they were previously under __KERNEL__). Right now only symbols for x86 and some other architecture for 1GB and 2MB are defined. The interface should already work for all other architectures though. Only architectures that define multiple hugetlb sizes actually need it (that is currently x86, tile, powerpc). However tile and powerpc have user configurable hugetlb sizes, so it's not easy to add defines. A program on those architectures would need to query sysfs and use the appropiate log2. [akpm@linux-foundation.org: cleanups] [rientjes@google.com: fix build] [akpm@linux-foundation.org: checkpatch fixes] Signed-off-by: Andi Kleen <ak@linux.intel.com> Cc: Michael Kerrisk <mtk.manpages@gmail.com> Acked-by: Rik van Riel <riel@redhat.com> Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Hillf Danton <dhillf@gmail.com> Signed-off-by: David Rientjes <rientjes@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-12-12 07:01:34 +07:00
static int get_hstate_idx(int page_size_log)
{
struct hstate *h = hstate_sizelog(page_size_log);
mm: support more pagesizes for MAP_HUGETLB/SHM_HUGETLB There was some desire in large applications using MAP_HUGETLB or SHM_HUGETLB to use 1GB huge pages on some mappings, and stay with 2MB on others. This is useful together with NUMA policy: use 2MB interleaving on some mappings, but 1GB on local mappings. This patch extends the IPC/SHM syscall interfaces slightly to allow specifying the page size. It borrows some upper bits in the existing flag arguments and allows encoding the log of the desired page size in addition to the *_HUGETLB flag. When 0 is specified the default size is used, this makes the change fully compatible. Extending the internal hugetlb code to handle this is straight forward. Instead of a single mount it just keeps an array of them and selects the right mount based on the specified page size. When no page size is specified it uses the mount of the default page size. The change is not visible in /proc/mounts because internal mounts don't appear there. It also has very little overhead: the additional mounts just consume a super block, but not more memory when not used. I also exported the new flags to the user headers (they were previously under __KERNEL__). Right now only symbols for x86 and some other architecture for 1GB and 2MB are defined. The interface should already work for all other architectures though. Only architectures that define multiple hugetlb sizes actually need it (that is currently x86, tile, powerpc). However tile and powerpc have user configurable hugetlb sizes, so it's not easy to add defines. A program on those architectures would need to query sysfs and use the appropiate log2. [akpm@linux-foundation.org: cleanups] [rientjes@google.com: fix build] [akpm@linux-foundation.org: checkpatch fixes] Signed-off-by: Andi Kleen <ak@linux.intel.com> Cc: Michael Kerrisk <mtk.manpages@gmail.com> Acked-by: Rik van Riel <riel@redhat.com> Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Hillf Danton <dhillf@gmail.com> Signed-off-by: David Rientjes <rientjes@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-12-12 07:01:34 +07:00
if (!h)
return -1;
return h - hstates;
}
static const struct dentry_operations anon_ops = {
.d_dname = simple_dname
};
/*
* Note that size should be aligned to proper hugepage size in caller side,
* otherwise hugetlb_reserve_pages reserves one less hugepages than intended.
*/
struct file *hugetlb_file_setup(const char *name, size_t size,
vm_flags_t acctflag, struct user_struct **user,
mm: support more pagesizes for MAP_HUGETLB/SHM_HUGETLB There was some desire in large applications using MAP_HUGETLB or SHM_HUGETLB to use 1GB huge pages on some mappings, and stay with 2MB on others. This is useful together with NUMA policy: use 2MB interleaving on some mappings, but 1GB on local mappings. This patch extends the IPC/SHM syscall interfaces slightly to allow specifying the page size. It borrows some upper bits in the existing flag arguments and allows encoding the log of the desired page size in addition to the *_HUGETLB flag. When 0 is specified the default size is used, this makes the change fully compatible. Extending the internal hugetlb code to handle this is straight forward. Instead of a single mount it just keeps an array of them and selects the right mount based on the specified page size. When no page size is specified it uses the mount of the default page size. The change is not visible in /proc/mounts because internal mounts don't appear there. It also has very little overhead: the additional mounts just consume a super block, but not more memory when not used. I also exported the new flags to the user headers (they were previously under __KERNEL__). Right now only symbols for x86 and some other architecture for 1GB and 2MB are defined. The interface should already work for all other architectures though. Only architectures that define multiple hugetlb sizes actually need it (that is currently x86, tile, powerpc). However tile and powerpc have user configurable hugetlb sizes, so it's not easy to add defines. A program on those architectures would need to query sysfs and use the appropiate log2. [akpm@linux-foundation.org: cleanups] [rientjes@google.com: fix build] [akpm@linux-foundation.org: checkpatch fixes] Signed-off-by: Andi Kleen <ak@linux.intel.com> Cc: Michael Kerrisk <mtk.manpages@gmail.com> Acked-by: Rik van Riel <riel@redhat.com> Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Hillf Danton <dhillf@gmail.com> Signed-off-by: David Rientjes <rientjes@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-12-12 07:01:34 +07:00
int creat_flags, int page_size_log)
{
struct file *file = ERR_PTR(-ENOMEM);
struct inode *inode;
struct path path;
struct super_block *sb;
struct qstr quick_string;
mm: support more pagesizes for MAP_HUGETLB/SHM_HUGETLB There was some desire in large applications using MAP_HUGETLB or SHM_HUGETLB to use 1GB huge pages on some mappings, and stay with 2MB on others. This is useful together with NUMA policy: use 2MB interleaving on some mappings, but 1GB on local mappings. This patch extends the IPC/SHM syscall interfaces slightly to allow specifying the page size. It borrows some upper bits in the existing flag arguments and allows encoding the log of the desired page size in addition to the *_HUGETLB flag. When 0 is specified the default size is used, this makes the change fully compatible. Extending the internal hugetlb code to handle this is straight forward. Instead of a single mount it just keeps an array of them and selects the right mount based on the specified page size. When no page size is specified it uses the mount of the default page size. The change is not visible in /proc/mounts because internal mounts don't appear there. It also has very little overhead: the additional mounts just consume a super block, but not more memory when not used. I also exported the new flags to the user headers (they were previously under __KERNEL__). Right now only symbols for x86 and some other architecture for 1GB and 2MB are defined. The interface should already work for all other architectures though. Only architectures that define multiple hugetlb sizes actually need it (that is currently x86, tile, powerpc). However tile and powerpc have user configurable hugetlb sizes, so it's not easy to add defines. A program on those architectures would need to query sysfs and use the appropiate log2. [akpm@linux-foundation.org: cleanups] [rientjes@google.com: fix build] [akpm@linux-foundation.org: checkpatch fixes] Signed-off-by: Andi Kleen <ak@linux.intel.com> Cc: Michael Kerrisk <mtk.manpages@gmail.com> Acked-by: Rik van Riel <riel@redhat.com> Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Hillf Danton <dhillf@gmail.com> Signed-off-by: David Rientjes <rientjes@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-12-12 07:01:34 +07:00
int hstate_idx;
hstate_idx = get_hstate_idx(page_size_log);
if (hstate_idx < 0)
return ERR_PTR(-ENODEV);
*user = NULL;
mm: support more pagesizes for MAP_HUGETLB/SHM_HUGETLB There was some desire in large applications using MAP_HUGETLB or SHM_HUGETLB to use 1GB huge pages on some mappings, and stay with 2MB on others. This is useful together with NUMA policy: use 2MB interleaving on some mappings, but 1GB on local mappings. This patch extends the IPC/SHM syscall interfaces slightly to allow specifying the page size. It borrows some upper bits in the existing flag arguments and allows encoding the log of the desired page size in addition to the *_HUGETLB flag. When 0 is specified the default size is used, this makes the change fully compatible. Extending the internal hugetlb code to handle this is straight forward. Instead of a single mount it just keeps an array of them and selects the right mount based on the specified page size. When no page size is specified it uses the mount of the default page size. The change is not visible in /proc/mounts because internal mounts don't appear there. It also has very little overhead: the additional mounts just consume a super block, but not more memory when not used. I also exported the new flags to the user headers (they were previously under __KERNEL__). Right now only symbols for x86 and some other architecture for 1GB and 2MB are defined. The interface should already work for all other architectures though. Only architectures that define multiple hugetlb sizes actually need it (that is currently x86, tile, powerpc). However tile and powerpc have user configurable hugetlb sizes, so it's not easy to add defines. A program on those architectures would need to query sysfs and use the appropiate log2. [akpm@linux-foundation.org: cleanups] [rientjes@google.com: fix build] [akpm@linux-foundation.org: checkpatch fixes] Signed-off-by: Andi Kleen <ak@linux.intel.com> Cc: Michael Kerrisk <mtk.manpages@gmail.com> Acked-by: Rik van Riel <riel@redhat.com> Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Hillf Danton <dhillf@gmail.com> Signed-off-by: David Rientjes <rientjes@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-12-12 07:01:34 +07:00
if (!hugetlbfs_vfsmount[hstate_idx])
return ERR_PTR(-ENOENT);
if (creat_flags == HUGETLB_SHMFS_INODE && !can_do_hugetlb_shm()) {
*user = current_user();
if (user_shm_lock(size, *user)) {
task_lock(current);
pr_warn_once("%s (%d): Using mlock ulimits for SHM_HUGETLB is deprecated\n",
current->comm, current->pid);
task_unlock(current);
} else {
*user = NULL;
return ERR_PTR(-EPERM);
}
}
sb = hugetlbfs_vfsmount[hstate_idx]->mnt_sb;
quick_string.name = name;
quick_string.len = strlen(quick_string.name);
quick_string.hash = 0;
path.dentry = d_alloc_pseudo(sb, &quick_string);
if (!path.dentry)
goto out_shm_unlock;
d_set_d_op(path.dentry, &anon_ops);
mm: support more pagesizes for MAP_HUGETLB/SHM_HUGETLB There was some desire in large applications using MAP_HUGETLB or SHM_HUGETLB to use 1GB huge pages on some mappings, and stay with 2MB on others. This is useful together with NUMA policy: use 2MB interleaving on some mappings, but 1GB on local mappings. This patch extends the IPC/SHM syscall interfaces slightly to allow specifying the page size. It borrows some upper bits in the existing flag arguments and allows encoding the log of the desired page size in addition to the *_HUGETLB flag. When 0 is specified the default size is used, this makes the change fully compatible. Extending the internal hugetlb code to handle this is straight forward. Instead of a single mount it just keeps an array of them and selects the right mount based on the specified page size. When no page size is specified it uses the mount of the default page size. The change is not visible in /proc/mounts because internal mounts don't appear there. It also has very little overhead: the additional mounts just consume a super block, but not more memory when not used. I also exported the new flags to the user headers (they were previously under __KERNEL__). Right now only symbols for x86 and some other architecture for 1GB and 2MB are defined. The interface should already work for all other architectures though. Only architectures that define multiple hugetlb sizes actually need it (that is currently x86, tile, powerpc). However tile and powerpc have user configurable hugetlb sizes, so it's not easy to add defines. A program on those architectures would need to query sysfs and use the appropiate log2. [akpm@linux-foundation.org: cleanups] [rientjes@google.com: fix build] [akpm@linux-foundation.org: checkpatch fixes] Signed-off-by: Andi Kleen <ak@linux.intel.com> Cc: Michael Kerrisk <mtk.manpages@gmail.com> Acked-by: Rik van Riel <riel@redhat.com> Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Hillf Danton <dhillf@gmail.com> Signed-off-by: David Rientjes <rientjes@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-12-12 07:01:34 +07:00
path.mnt = mntget(hugetlbfs_vfsmount[hstate_idx]);
file = ERR_PTR(-ENOSPC);
inode = hugetlbfs_get_inode(sb, NULL, S_IFREG | S_IRWXUGO, 0);
if (!inode)
r/o bind mounts: filesystem helpers for custom 'struct file's Why do we need r/o bind mounts? This feature allows a read-only view into a read-write filesystem. In the process of doing that, it also provides infrastructure for keeping track of the number of writers to any given mount. This has a number of uses. It allows chroots to have parts of filesystems writable. It will be useful for containers in the future because users may have root inside a container, but should not be allowed to write to somefilesystems. This also replaces patches that vserver has had out of the tree for several years. It allows security enhancement by making sure that parts of your filesystem read-only (such as when you don't trust your FTP server), when you don't want to have entire new filesystems mounted, or when you want atime selectively updated. I've been using the following script to test that the feature is working as desired. It takes a directory and makes a regular bind and a r/o bind mount of it. It then performs some normal filesystem operations on the three directories, including ones that are expected to fail, like creating a file on the r/o mount. This patch: Some filesystems forego the vfs and may_open() and create their own 'struct file's. This patch creates a couple of helper functions which can be used by these filesystems, and will provide a unified place which the r/o bind mount code may patch. Also, rename an existing, static-scope init_file() to a less generic name. Signed-off-by: Dave Hansen <haveblue@us.ibm.com> Cc: Christoph Hellwig <hch@lst.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-17 13:31:13 +07:00
goto out_dentry;
ipc: use private shmem or hugetlbfs inodes for shm segments. The shm implementation internally uses shmem or hugetlbfs inodes for shm segments. As these inodes are never directly exposed to userspace and only accessed through the shm operations which are already hooked by security modules, mark the inodes with the S_PRIVATE flag so that inode security initialization and permission checking is skipped. This was motivated by the following lockdep warning: ====================================================== [ INFO: possible circular locking dependency detected ] 4.2.0-0.rc3.git0.1.fc24.x86_64+debug #1 Tainted: G W ------------------------------------------------------- httpd/1597 is trying to acquire lock: (&ids->rwsem){+++++.}, at: shm_close+0x34/0x130 but task is already holding lock: (&mm->mmap_sem){++++++}, at: SyS_shmdt+0x4b/0x180 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #3 (&mm->mmap_sem){++++++}: lock_acquire+0xc7/0x270 __might_fault+0x7a/0xa0 filldir+0x9e/0x130 xfs_dir2_block_getdents.isra.12+0x198/0x1c0 [xfs] xfs_readdir+0x1b4/0x330 [xfs] xfs_file_readdir+0x2b/0x30 [xfs] iterate_dir+0x97/0x130 SyS_getdents+0x91/0x120 entry_SYSCALL_64_fastpath+0x12/0x76 -> #2 (&xfs_dir_ilock_class){++++.+}: lock_acquire+0xc7/0x270 down_read_nested+0x57/0xa0 xfs_ilock+0x167/0x350 [xfs] xfs_ilock_attr_map_shared+0x38/0x50 [xfs] xfs_attr_get+0xbd/0x190 [xfs] xfs_xattr_get+0x3d/0x70 [xfs] generic_getxattr+0x4f/0x70 inode_doinit_with_dentry+0x162/0x670 sb_finish_set_opts+0xd9/0x230 selinux_set_mnt_opts+0x35c/0x660 superblock_doinit+0x77/0xf0 delayed_superblock_init+0x10/0x20 iterate_supers+0xb3/0x110 selinux_complete_init+0x2f/0x40 security_load_policy+0x103/0x600 sel_write_load+0xc1/0x750 __vfs_write+0x37/0x100 vfs_write+0xa9/0x1a0 SyS_write+0x58/0xd0 entry_SYSCALL_64_fastpath+0x12/0x76 ... Signed-off-by: Stephen Smalley <sds@tycho.nsa.gov> Reported-by: Morten Stevens <mstevens@fedoraproject.org> Acked-by: Hugh Dickins <hughd@google.com> Acked-by: Paul Moore <paul@paul-moore.com> Cc: Manfred Spraul <manfred@colorfullife.com> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Prarit Bhargava <prarit@redhat.com> Cc: Eric Paris <eparis@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-08-07 05:46:55 +07:00
if (creat_flags == HUGETLB_SHMFS_INODE)
inode->i_flags |= S_PRIVATE;
file = ERR_PTR(-ENOMEM);
if (hugetlb_reserve_pages(inode, 0,
size >> huge_page_shift(hstate_inode(inode)), NULL,
acctflag))
[PATCH] hugepage: Strict page reservation for hugepage inodes These days, hugepages are demand-allocated at first fault time. There's a somewhat dubious (and racy) heuristic when making a new mmap() to check if there are enough available hugepages to fully satisfy that mapping. A particularly obvious case where the heuristic breaks down is where a process maps its hugepages not as a single chunk, but as a bunch of individually mmap()ed (or shmat()ed) blocks without touching and instantiating the pages in between allocations. In this case the size of each block is compared against the total number of available hugepages. It's thus easy for the process to become overcommitted, because each block mapping will succeed, although the total number of hugepages required by all blocks exceeds the number available. In particular, this defeats such a program which will detect a mapping failure and adjust its hugepage usage downward accordingly. The patch below addresses this problem, by strictly reserving a number of physical hugepages for hugepage inodes which have been mapped, but not instatiated. MAP_SHARED mappings are thus "safe" - they will fail on mmap(), not later with an OOM SIGKILL. MAP_PRIVATE mappings can still trigger an OOM. (Actually SHARED mappings can technically still OOM, but only if the sysadmin explicitly reduces the hugepage pool between mapping and instantiation) This patch appears to address the problem at hand - it allows DB2 to start correctly, for instance, which previously suffered the failure described above. This patch causes no regressions on the libhugetblfs testsuite, and makes a test (designed to catch this problem) pass which previously failed (ppc64, POWER5). Signed-off-by: David Gibson <dwg@au1.ibm.com> Cc: William Lee Irwin III <wli@holomorphy.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-22 15:08:55 +07:00
goto out_inode;
d_instantiate(path.dentry, inode);
inode->i_size = size;
clear_nlink(inode);
r/o bind mounts: filesystem helpers for custom 'struct file's Why do we need r/o bind mounts? This feature allows a read-only view into a read-write filesystem. In the process of doing that, it also provides infrastructure for keeping track of the number of writers to any given mount. This has a number of uses. It allows chroots to have parts of filesystems writable. It will be useful for containers in the future because users may have root inside a container, but should not be allowed to write to somefilesystems. This also replaces patches that vserver has had out of the tree for several years. It allows security enhancement by making sure that parts of your filesystem read-only (such as when you don't trust your FTP server), when you don't want to have entire new filesystems mounted, or when you want atime selectively updated. I've been using the following script to test that the feature is working as desired. It takes a directory and makes a regular bind and a r/o bind mount of it. It then performs some normal filesystem operations on the three directories, including ones that are expected to fail, like creating a file on the r/o mount. This patch: Some filesystems forego the vfs and may_open() and create their own 'struct file's. This patch creates a couple of helper functions which can be used by these filesystems, and will provide a unified place which the r/o bind mount code may patch. Also, rename an existing, static-scope init_file() to a less generic name. Signed-off-by: Dave Hansen <haveblue@us.ibm.com> Cc: Christoph Hellwig <hch@lst.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-17 13:31:13 +07:00
file = alloc_file(&path, FMODE_WRITE | FMODE_READ,
r/o bind mounts: filesystem helpers for custom 'struct file's Why do we need r/o bind mounts? This feature allows a read-only view into a read-write filesystem. In the process of doing that, it also provides infrastructure for keeping track of the number of writers to any given mount. This has a number of uses. It allows chroots to have parts of filesystems writable. It will be useful for containers in the future because users may have root inside a container, but should not be allowed to write to somefilesystems. This also replaces patches that vserver has had out of the tree for several years. It allows security enhancement by making sure that parts of your filesystem read-only (such as when you don't trust your FTP server), when you don't want to have entire new filesystems mounted, or when you want atime selectively updated. I've been using the following script to test that the feature is working as desired. It takes a directory and makes a regular bind and a r/o bind mount of it. It then performs some normal filesystem operations on the three directories, including ones that are expected to fail, like creating a file on the r/o mount. This patch: Some filesystems forego the vfs and may_open() and create their own 'struct file's. This patch creates a couple of helper functions which can be used by these filesystems, and will provide a unified place which the r/o bind mount code may patch. Also, rename an existing, static-scope init_file() to a less generic name. Signed-off-by: Dave Hansen <haveblue@us.ibm.com> Cc: Christoph Hellwig <hch@lst.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-17 13:31:13 +07:00
&hugetlbfs_file_operations);
if (IS_ERR(file))
goto out_dentry; /* inode is already attached */
r/o bind mounts: filesystem helpers for custom 'struct file's Why do we need r/o bind mounts? This feature allows a read-only view into a read-write filesystem. In the process of doing that, it also provides infrastructure for keeping track of the number of writers to any given mount. This has a number of uses. It allows chroots to have parts of filesystems writable. It will be useful for containers in the future because users may have root inside a container, but should not be allowed to write to somefilesystems. This also replaces patches that vserver has had out of the tree for several years. It allows security enhancement by making sure that parts of your filesystem read-only (such as when you don't trust your FTP server), when you don't want to have entire new filesystems mounted, or when you want atime selectively updated. I've been using the following script to test that the feature is working as desired. It takes a directory and makes a regular bind and a r/o bind mount of it. It then performs some normal filesystem operations on the three directories, including ones that are expected to fail, like creating a file on the r/o mount. This patch: Some filesystems forego the vfs and may_open() and create their own 'struct file's. This patch creates a couple of helper functions which can be used by these filesystems, and will provide a unified place which the r/o bind mount code may patch. Also, rename an existing, static-scope init_file() to a less generic name. Signed-off-by: Dave Hansen <haveblue@us.ibm.com> Cc: Christoph Hellwig <hch@lst.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-17 13:31:13 +07:00
return file;
[PATCH] hugepage: Strict page reservation for hugepage inodes These days, hugepages are demand-allocated at first fault time. There's a somewhat dubious (and racy) heuristic when making a new mmap() to check if there are enough available hugepages to fully satisfy that mapping. A particularly obvious case where the heuristic breaks down is where a process maps its hugepages not as a single chunk, but as a bunch of individually mmap()ed (or shmat()ed) blocks without touching and instantiating the pages in between allocations. In this case the size of each block is compared against the total number of available hugepages. It's thus easy for the process to become overcommitted, because each block mapping will succeed, although the total number of hugepages required by all blocks exceeds the number available. In particular, this defeats such a program which will detect a mapping failure and adjust its hugepage usage downward accordingly. The patch below addresses this problem, by strictly reserving a number of physical hugepages for hugepage inodes which have been mapped, but not instatiated. MAP_SHARED mappings are thus "safe" - they will fail on mmap(), not later with an OOM SIGKILL. MAP_PRIVATE mappings can still trigger an OOM. (Actually SHARED mappings can technically still OOM, but only if the sysadmin explicitly reduces the hugepage pool between mapping and instantiation) This patch appears to address the problem at hand - it allows DB2 to start correctly, for instance, which previously suffered the failure described above. This patch causes no regressions on the libhugetblfs testsuite, and makes a test (designed to catch this problem) pass which previously failed (ppc64, POWER5). Signed-off-by: David Gibson <dwg@au1.ibm.com> Cc: William Lee Irwin III <wli@holomorphy.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-22 15:08:55 +07:00
out_inode:
iput(inode);
out_dentry:
path_put(&path);
out_shm_unlock:
if (*user) {
user_shm_unlock(size, *user);
*user = NULL;
}
return file;
}
static int __init init_hugetlbfs_fs(void)
{
mm: support more pagesizes for MAP_HUGETLB/SHM_HUGETLB There was some desire in large applications using MAP_HUGETLB or SHM_HUGETLB to use 1GB huge pages on some mappings, and stay with 2MB on others. This is useful together with NUMA policy: use 2MB interleaving on some mappings, but 1GB on local mappings. This patch extends the IPC/SHM syscall interfaces slightly to allow specifying the page size. It borrows some upper bits in the existing flag arguments and allows encoding the log of the desired page size in addition to the *_HUGETLB flag. When 0 is specified the default size is used, this makes the change fully compatible. Extending the internal hugetlb code to handle this is straight forward. Instead of a single mount it just keeps an array of them and selects the right mount based on the specified page size. When no page size is specified it uses the mount of the default page size. The change is not visible in /proc/mounts because internal mounts don't appear there. It also has very little overhead: the additional mounts just consume a super block, but not more memory when not used. I also exported the new flags to the user headers (they were previously under __KERNEL__). Right now only symbols for x86 and some other architecture for 1GB and 2MB are defined. The interface should already work for all other architectures though. Only architectures that define multiple hugetlb sizes actually need it (that is currently x86, tile, powerpc). However tile and powerpc have user configurable hugetlb sizes, so it's not easy to add defines. A program on those architectures would need to query sysfs and use the appropiate log2. [akpm@linux-foundation.org: cleanups] [rientjes@google.com: fix build] [akpm@linux-foundation.org: checkpatch fixes] Signed-off-by: Andi Kleen <ak@linux.intel.com> Cc: Michael Kerrisk <mtk.manpages@gmail.com> Acked-by: Rik van Riel <riel@redhat.com> Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Hillf Danton <dhillf@gmail.com> Signed-off-by: David Rientjes <rientjes@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-12-12 07:01:34 +07:00
struct hstate *h;
int error;
mm: support more pagesizes for MAP_HUGETLB/SHM_HUGETLB There was some desire in large applications using MAP_HUGETLB or SHM_HUGETLB to use 1GB huge pages on some mappings, and stay with 2MB on others. This is useful together with NUMA policy: use 2MB interleaving on some mappings, but 1GB on local mappings. This patch extends the IPC/SHM syscall interfaces slightly to allow specifying the page size. It borrows some upper bits in the existing flag arguments and allows encoding the log of the desired page size in addition to the *_HUGETLB flag. When 0 is specified the default size is used, this makes the change fully compatible. Extending the internal hugetlb code to handle this is straight forward. Instead of a single mount it just keeps an array of them and selects the right mount based on the specified page size. When no page size is specified it uses the mount of the default page size. The change is not visible in /proc/mounts because internal mounts don't appear there. It also has very little overhead: the additional mounts just consume a super block, but not more memory when not used. I also exported the new flags to the user headers (they were previously under __KERNEL__). Right now only symbols for x86 and some other architecture for 1GB and 2MB are defined. The interface should already work for all other architectures though. Only architectures that define multiple hugetlb sizes actually need it (that is currently x86, tile, powerpc). However tile and powerpc have user configurable hugetlb sizes, so it's not easy to add defines. A program on those architectures would need to query sysfs and use the appropiate log2. [akpm@linux-foundation.org: cleanups] [rientjes@google.com: fix build] [akpm@linux-foundation.org: checkpatch fixes] Signed-off-by: Andi Kleen <ak@linux.intel.com> Cc: Michael Kerrisk <mtk.manpages@gmail.com> Acked-by: Rik van Riel <riel@redhat.com> Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Hillf Danton <dhillf@gmail.com> Signed-off-by: David Rientjes <rientjes@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-12-12 07:01:34 +07:00
int i;
hugetlb: ensure hugepage access is denied if hugepages are not supported Currently, I am seeing the following when I `mount -t hugetlbfs /none /dev/hugetlbfs`, and then simply do a `ls /dev/hugetlbfs`. I think it's related to the fact that hugetlbfs is properly not correctly setting itself up in this state?: Unable to handle kernel paging request for data at address 0x00000031 Faulting instruction address: 0xc000000000245710 Oops: Kernel access of bad area, sig: 11 [#1] SMP NR_CPUS=2048 NUMA pSeries .... In KVM guests on Power, in a guest not backed by hugepages, we see the following: AnonHugePages: 0 kB HugePages_Total: 0 HugePages_Free: 0 HugePages_Rsvd: 0 HugePages_Surp: 0 Hugepagesize: 64 kB HPAGE_SHIFT == 0 in this configuration, which indicates that hugepages are not supported at boot-time, but this is only checked in hugetlb_init(). Extract the check to a helper function, and use it in a few relevant places. This does make hugetlbfs not supported (not registered at all) in this environment. I believe this is fine, as there are no valid hugepages and that won't change at runtime. [akpm@linux-foundation.org: use pr_info(), per Mel] [akpm@linux-foundation.org: fix build when HPAGE_SHIFT is undefined] Signed-off-by: Nishanth Aravamudan <nacc@linux.vnet.ibm.com> Reviewed-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> Acked-by: Mel Gorman <mgorman@suse.de> Cc: Randy Dunlap <rdunlap@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-05-07 02:50:00 +07:00
if (!hugepages_supported()) {
pr_info("disabling because there are no supported hugepage sizes\n");
hugetlb: ensure hugepage access is denied if hugepages are not supported Currently, I am seeing the following when I `mount -t hugetlbfs /none /dev/hugetlbfs`, and then simply do a `ls /dev/hugetlbfs`. I think it's related to the fact that hugetlbfs is properly not correctly setting itself up in this state?: Unable to handle kernel paging request for data at address 0x00000031 Faulting instruction address: 0xc000000000245710 Oops: Kernel access of bad area, sig: 11 [#1] SMP NR_CPUS=2048 NUMA pSeries .... In KVM guests on Power, in a guest not backed by hugepages, we see the following: AnonHugePages: 0 kB HugePages_Total: 0 HugePages_Free: 0 HugePages_Rsvd: 0 HugePages_Surp: 0 Hugepagesize: 64 kB HPAGE_SHIFT == 0 in this configuration, which indicates that hugepages are not supported at boot-time, but this is only checked in hugetlb_init(). Extract the check to a helper function, and use it in a few relevant places. This does make hugetlbfs not supported (not registered at all) in this environment. I believe this is fine, as there are no valid hugepages and that won't change at runtime. [akpm@linux-foundation.org: use pr_info(), per Mel] [akpm@linux-foundation.org: fix build when HPAGE_SHIFT is undefined] Signed-off-by: Nishanth Aravamudan <nacc@linux.vnet.ibm.com> Reviewed-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> Acked-by: Mel Gorman <mgorman@suse.de> Cc: Randy Dunlap <rdunlap@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-05-07 02:50:00 +07:00
return -ENOTSUPP;
}
error = -ENOMEM;
hugetlbfs_inode_cachep = kmem_cache_create("hugetlbfs_inode_cache",
sizeof(struct hugetlbfs_inode_info),
2016-01-15 06:18:21 +07:00
0, SLAB_ACCOUNT, init_once);
if (hugetlbfs_inode_cachep == NULL)
goto out2;
error = register_filesystem(&hugetlbfs_fs_type);
if (error)
goto out;
mm: support more pagesizes for MAP_HUGETLB/SHM_HUGETLB There was some desire in large applications using MAP_HUGETLB or SHM_HUGETLB to use 1GB huge pages on some mappings, and stay with 2MB on others. This is useful together with NUMA policy: use 2MB interleaving on some mappings, but 1GB on local mappings. This patch extends the IPC/SHM syscall interfaces slightly to allow specifying the page size. It borrows some upper bits in the existing flag arguments and allows encoding the log of the desired page size in addition to the *_HUGETLB flag. When 0 is specified the default size is used, this makes the change fully compatible. Extending the internal hugetlb code to handle this is straight forward. Instead of a single mount it just keeps an array of them and selects the right mount based on the specified page size. When no page size is specified it uses the mount of the default page size. The change is not visible in /proc/mounts because internal mounts don't appear there. It also has very little overhead: the additional mounts just consume a super block, but not more memory when not used. I also exported the new flags to the user headers (they were previously under __KERNEL__). Right now only symbols for x86 and some other architecture for 1GB and 2MB are defined. The interface should already work for all other architectures though. Only architectures that define multiple hugetlb sizes actually need it (that is currently x86, tile, powerpc). However tile and powerpc have user configurable hugetlb sizes, so it's not easy to add defines. A program on those architectures would need to query sysfs and use the appropiate log2. [akpm@linux-foundation.org: cleanups] [rientjes@google.com: fix build] [akpm@linux-foundation.org: checkpatch fixes] Signed-off-by: Andi Kleen <ak@linux.intel.com> Cc: Michael Kerrisk <mtk.manpages@gmail.com> Acked-by: Rik van Riel <riel@redhat.com> Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Hillf Danton <dhillf@gmail.com> Signed-off-by: David Rientjes <rientjes@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-12-12 07:01:34 +07:00
i = 0;
for_each_hstate(h) {
char buf[50];
unsigned ps_kb = 1U << (h->order + PAGE_SHIFT - 10);
mm: support more pagesizes for MAP_HUGETLB/SHM_HUGETLB There was some desire in large applications using MAP_HUGETLB or SHM_HUGETLB to use 1GB huge pages on some mappings, and stay with 2MB on others. This is useful together with NUMA policy: use 2MB interleaving on some mappings, but 1GB on local mappings. This patch extends the IPC/SHM syscall interfaces slightly to allow specifying the page size. It borrows some upper bits in the existing flag arguments and allows encoding the log of the desired page size in addition to the *_HUGETLB flag. When 0 is specified the default size is used, this makes the change fully compatible. Extending the internal hugetlb code to handle this is straight forward. Instead of a single mount it just keeps an array of them and selects the right mount based on the specified page size. When no page size is specified it uses the mount of the default page size. The change is not visible in /proc/mounts because internal mounts don't appear there. It also has very little overhead: the additional mounts just consume a super block, but not more memory when not used. I also exported the new flags to the user headers (they were previously under __KERNEL__). Right now only symbols for x86 and some other architecture for 1GB and 2MB are defined. The interface should already work for all other architectures though. Only architectures that define multiple hugetlb sizes actually need it (that is currently x86, tile, powerpc). However tile and powerpc have user configurable hugetlb sizes, so it's not easy to add defines. A program on those architectures would need to query sysfs and use the appropiate log2. [akpm@linux-foundation.org: cleanups] [rientjes@google.com: fix build] [akpm@linux-foundation.org: checkpatch fixes] Signed-off-by: Andi Kleen <ak@linux.intel.com> Cc: Michael Kerrisk <mtk.manpages@gmail.com> Acked-by: Rik van Riel <riel@redhat.com> Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Hillf Danton <dhillf@gmail.com> Signed-off-by: David Rientjes <rientjes@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-12-12 07:01:34 +07:00
snprintf(buf, sizeof(buf), "pagesize=%uK", ps_kb);
hugetlbfs_vfsmount[i] = kern_mount_data(&hugetlbfs_fs_type,
buf);
mm: support more pagesizes for MAP_HUGETLB/SHM_HUGETLB There was some desire in large applications using MAP_HUGETLB or SHM_HUGETLB to use 1GB huge pages on some mappings, and stay with 2MB on others. This is useful together with NUMA policy: use 2MB interleaving on some mappings, but 1GB on local mappings. This patch extends the IPC/SHM syscall interfaces slightly to allow specifying the page size. It borrows some upper bits in the existing flag arguments and allows encoding the log of the desired page size in addition to the *_HUGETLB flag. When 0 is specified the default size is used, this makes the change fully compatible. Extending the internal hugetlb code to handle this is straight forward. Instead of a single mount it just keeps an array of them and selects the right mount based on the specified page size. When no page size is specified it uses the mount of the default page size. The change is not visible in /proc/mounts because internal mounts don't appear there. It also has very little overhead: the additional mounts just consume a super block, but not more memory when not used. I also exported the new flags to the user headers (they were previously under __KERNEL__). Right now only symbols for x86 and some other architecture for 1GB and 2MB are defined. The interface should already work for all other architectures though. Only architectures that define multiple hugetlb sizes actually need it (that is currently x86, tile, powerpc). However tile and powerpc have user configurable hugetlb sizes, so it's not easy to add defines. A program on those architectures would need to query sysfs and use the appropiate log2. [akpm@linux-foundation.org: cleanups] [rientjes@google.com: fix build] [akpm@linux-foundation.org: checkpatch fixes] Signed-off-by: Andi Kleen <ak@linux.intel.com> Cc: Michael Kerrisk <mtk.manpages@gmail.com> Acked-by: Rik van Riel <riel@redhat.com> Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Hillf Danton <dhillf@gmail.com> Signed-off-by: David Rientjes <rientjes@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-12-12 07:01:34 +07:00
if (IS_ERR(hugetlbfs_vfsmount[i])) {
pr_err("Cannot mount internal hugetlbfs for "
mm: support more pagesizes for MAP_HUGETLB/SHM_HUGETLB There was some desire in large applications using MAP_HUGETLB or SHM_HUGETLB to use 1GB huge pages on some mappings, and stay with 2MB on others. This is useful together with NUMA policy: use 2MB interleaving on some mappings, but 1GB on local mappings. This patch extends the IPC/SHM syscall interfaces slightly to allow specifying the page size. It borrows some upper bits in the existing flag arguments and allows encoding the log of the desired page size in addition to the *_HUGETLB flag. When 0 is specified the default size is used, this makes the change fully compatible. Extending the internal hugetlb code to handle this is straight forward. Instead of a single mount it just keeps an array of them and selects the right mount based on the specified page size. When no page size is specified it uses the mount of the default page size. The change is not visible in /proc/mounts because internal mounts don't appear there. It also has very little overhead: the additional mounts just consume a super block, but not more memory when not used. I also exported the new flags to the user headers (they were previously under __KERNEL__). Right now only symbols for x86 and some other architecture for 1GB and 2MB are defined. The interface should already work for all other architectures though. Only architectures that define multiple hugetlb sizes actually need it (that is currently x86, tile, powerpc). However tile and powerpc have user configurable hugetlb sizes, so it's not easy to add defines. A program on those architectures would need to query sysfs and use the appropiate log2. [akpm@linux-foundation.org: cleanups] [rientjes@google.com: fix build] [akpm@linux-foundation.org: checkpatch fixes] Signed-off-by: Andi Kleen <ak@linux.intel.com> Cc: Michael Kerrisk <mtk.manpages@gmail.com> Acked-by: Rik van Riel <riel@redhat.com> Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Hillf Danton <dhillf@gmail.com> Signed-off-by: David Rientjes <rientjes@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-12-12 07:01:34 +07:00
"page size %uK", ps_kb);
error = PTR_ERR(hugetlbfs_vfsmount[i]);
hugetlbfs_vfsmount[i] = NULL;
}
i++;
}
/* Non default hstates are optional */
if (!IS_ERR_OR_NULL(hugetlbfs_vfsmount[default_hstate_idx]))
return 0;
out:
kmem_cache_destroy(hugetlbfs_inode_cachep);
out2:
return error;
}
hugetlb: make mm and fs code explicitly non-modular The Kconfig currently controlling compilation of this code is: config HUGETLBFS bool "HugeTLB file system support" ...meaning that it currently is not being built as a module by anyone. Lets remove the modular code that is essentially orphaned, so that when reading the driver there is no doubt it is builtin-only. Since module_init translates to device_initcall in the non-modular case, the init ordering gets moved to earlier levels when we use the more appropriate initcalls here. Originally I had the fs part and the mm part as separate commits, just by happenstance of the nature of how I detected these non-modular use cases. But that can possibly introduce regressions if the patch merge ordering puts the fs part 1st -- as the 0-day testing reported a splat at mount time. Investigating with "initcall_debug" showed that the delta was init_hugetlbfs_fs being called _before_ hugetlb_init instead of after. So both the fs change and the mm change are here together. In addition, it worked before due to luck of link order, since they were both in the same initcall category. So we now have the fs part using fs_initcall, and the mm part using subsys_initcall, which puts it one bucket earlier. It now passes the basic sanity test that failed in earlier 0-day testing. We delete the MODULE_LICENSE tag and capture that information at the top of the file alongside author comments, etc. We don't replace module.h with init.h since the file already has that. Also note that MODULE_ALIAS is a no-op for non-modular code. Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com> Reported-by: kernel test robot <ying.huang@linux.intel.com> Cc: Nadia Yvette Chambers <nyc@holomorphy.com> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com> Cc: David Rientjes <rientjes@google.com> Cc: Hillf Danton <hillf.zj@alibaba-inc.com> Acked-by: Davidlohr Bueso <dave@stgolabs.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-01-15 06:21:52 +07:00
fs_initcall(init_hugetlbfs_fs)