1
linux/fs/hugetlbfs/inode.c

1086 lines
26 KiB
C
Raw Normal View History

/*
* hugetlbpage-backed filesystem. Based on ramfs.
*
* Nadia Yvette Chambers, 2002
*
* Copyright (C) 2002 Linus Torvalds.
*/
#include <linux/module.h>
#include <linux/thread_info.h>
#include <asm/current.h>
#include <linux/sched.h> /* remove ASAP */
#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 <asm/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 {
kuid_t uid;
kgid_t gid;
umode_t mode;
long nr_blocks;
long nr_inodes;
struct hstate *hstate;
};
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);
}
static struct backing_dev_info hugetlbfs_backing_dev_info = {
.name = "hugetlbfs",
.ra_pages = 0, /* No readahead */
.capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK,
};
int sysctl_hugetlb_shm_group;
enum {
Opt_size, Opt_nr_inodes,
Opt_mode, Opt_uid, Opt_gid,
Opt_pagesize,
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_err, NULL},
};
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 03:03:32 -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 03:03:32 -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 03:03:32 -07:00
vma->vm_ops = &hugetlb_vm_ops;
if (vma->vm_pgoff & (~huge_page_mask(h) >> PAGE_SHIFT))
return -EINVAL;
vma_len = (loff_t)(vma->vm_end - vma->vm_start);
mutex_lock(&inode->i_mutex);
file_accessed(file);
ret = -ENOMEM;
len = vma_len + ((loff_t)vma->vm_pgoff << PAGE_SHIFT);
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>
2008-07-23 21:27:23 -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 07:02:27 -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 01:08:55 -07:00
ret = 0;
hugetlb_prefault_arch_hook(vma->vm_mm);
if (vma->vm_flags & VM_WRITE && inode->i_size < len)
inode->i_size = len;
out:
mutex_unlock(&inode->i_mutex);
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 &&
(!vma || addr + len <= vma->vm_start))
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 int
hugetlbfs_read_actor(struct page *page, unsigned long offset,
char __user *buf, unsigned long count,
unsigned long size)
{
char *kaddr;
unsigned long left, copied = 0;
int i, chunksize;
if (size > count)
size = count;
/* Find which 4k chunk and offset with in that chunk */
i = offset >> PAGE_CACHE_SHIFT;
offset = offset & ~PAGE_CACHE_MASK;
while (size) {
chunksize = PAGE_CACHE_SIZE;
if (offset)
chunksize -= offset;
if (chunksize > size)
chunksize = size;
kaddr = kmap(&page[i]);
left = __copy_to_user(buf, kaddr + offset, chunksize);
kunmap(&page[i]);
if (left) {
copied += (chunksize - left);
break;
}
offset = 0;
size -= chunksize;
buf += chunksize;
copied += chunksize;
i++;
}
return copied ? copied : -EFAULT;
}
/*
* 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_CACHE_SIZE assumptions.
*/
static ssize_t hugetlbfs_read(struct file *filp, char __user *buf,
size_t len, loff_t *ppos)
{
struct hstate *h = hstate_file(filp);
struct address_space *mapping = filp->f_mapping;
struct inode *inode = mapping->host;
unsigned long index = *ppos >> huge_page_shift(h);
unsigned long offset = *ppos & ~huge_page_mask(h);
unsigned long end_index;
loff_t isize;
ssize_t retval = 0;
/* validate length */
if (len == 0)
goto out;
for (;;) {
struct page *page;
unsigned long nr, ret;
int ra;
/* 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>
2012-03-21 16:34:08 -07:00
isize = i_size_read(inode);
if (!isize)
goto out;
end_index = (isize - 1) >> huge_page_shift(h);
if (index >= end_index) {
if (index > end_index)
goto out;
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>
2012-03-21 16:34:08 -07:00
if (nr <= offset)
goto out;
}
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>
2012-03-21 16:34:08 -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.
*/
ret = len < nr ? len : nr;
if (clear_user(buf, ret))
ra = -EFAULT;
else
ra = 0;
} 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>
2012-03-21 16:34:08 -07:00
unlock_page(page);
/*
* We have the page, copy it to user space buffer.
*/
ra = hugetlbfs_read_actor(page, offset, buf, len, nr);
ret = ra;
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>
2012-03-21 16:34:08 -07:00
page_cache_release(page);
}
if (ra < 0) {
if (retval == 0)
retval = ra;
goto out;
}
offset += ret;
retval += ret;
len -= ret;
index += offset >> huge_page_shift(h);
offset &= ~huge_page_mask(h);
/* short read or no more work */
if ((ret != nr) || (len == 0))
break;
}
out:
*ppos = ((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;
}
static void truncate_huge_page(struct page *page)
{
VM: Remove "clear_page_dirty()" and "test_clear_page_dirty()" functions They were horribly easy to mis-use because of their tempting naming, and they also did way more than any users of them generally wanted them to do. A dirty page can become clean under two circumstances: (a) when we write it out. We have "clear_page_dirty_for_io()" for this, and that function remains unchanged. In the "for IO" case it is not sufficient to just clear the dirty bit, you also have to mark the page as being under writeback etc. (b) when we actually remove a page due to it becoming inaccessible to users, notably because it was truncate()'d away or the file (or metadata) no longer exists, and we thus want to cancel any outstanding dirty state. For the (b) case, we now introduce "cancel_dirty_page()", which only touches the page state itself, and verifies that the page is not mapped (since cancelling writes on a mapped page would be actively wrong as it is still accessible to users). Some filesystems need to be fixed up for this: CIFS, FUSE, JFS, ReiserFS, XFS all use the old confusing functions, and will be fixed separately in subsequent commits (with some of them just removing the offending logic, and others using clear_page_dirty_for_io()). This was confirmed by Martin Michlmayr to fix the apt database corruption on ARM. Cc: Martin Michlmayr <tbm@cyrius.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Hugh Dickins <hugh@veritas.com> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: Arjan van de Ven <arjan@infradead.org> Cc: Andrei Popa <andrei.popa@i-neo.ro> Cc: Andrew Morton <akpm@osdl.org> Cc: Dave Kleikamp <shaggy@linux.vnet.ibm.com> Cc: Gordon Farquharson <gordonfarquharson@gmail.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Trond Myklebust <trond.myklebust@fys.uio.no> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-12-20 14:46:42 -07:00
cancel_dirty_page(page, /* No IO accounting for huge pages? */0);
ClearPageUptodate(page);
delete_from_page_cache(page);
}
[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 01:08:55 -07:00
static void truncate_hugepages(struct inode *inode, loff_t lstart)
{
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 01:08:55 -07:00
struct address_space *mapping = &inode->i_data;
const pgoff_t start = lstart >> huge_page_shift(h);
struct pagevec pvec;
pgoff_t next;
int i, freed = 0;
pagevec_init(&pvec, 0);
next = start;
while (1) {
if (!pagevec_lookup(&pvec, mapping, next, PAGEVEC_SIZE)) {
if (next == start)
break;
next = start;
continue;
}
for (i = 0; i < pagevec_count(&pvec); ++i) {
struct page *page = pvec.pages[i];
lock_page(page);
if (page->index > next)
next = page->index;
++next;
truncate_huge_page(page);
unlock_page(page);
freed++;
}
huge_pagevec_release(&pvec);
}
BUG_ON(!lstart && mapping->nrpages);
hugetlb_unreserve_pages(inode, start, freed);
}
static void hugetlbfs_evict_inode(struct 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 01:08:55 -07:00
truncate_hugepages(inode, 0);
clear_inode(inode);
}
static inline void
hugetlb_vmtruncate_list(struct rb_root *root, pgoff_t pgoff)
{
struct vm_area_struct *vma;
vma_interval_tree_foreach(vma, root, pgoff, ULONG_MAX) {
unsigned long v_offset;
/*
* 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 < pgoff)
v_offset = (pgoff - vma->vm_pgoff) << PAGE_SHIFT;
else
v_offset = 0;
unmap_hugepage_range(vma, vma->vm_start + v_offset,
vma->vm_end, NULL);
}
}
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);
mutex_lock(&mapping->i_mmap_mutex);
if (!RB_EMPTY_ROOT(&mapping->i_mmap))
hugetlb_vmtruncate_list(&mapping->i_mmap, pgoff);
mutex_unlock(&mapping->i_mmap_mutex);
[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 01:08:55 -07:00
truncate_hugepages(inode, offset);
return 0;
}
static int hugetlbfs_setattr(struct dentry *dentry, struct iattr *attr)
{
struct inode *inode = dentry->d_inode;
struct hstate *h = hstate_inode(inode);
int error;
unsigned int ia_valid = attr->ia_valid;
BUG_ON(!inode);
error = inode_change_ok(inode, attr);
if (error)
return error;
if (ia_valid & ATTR_SIZE) {
error = -EINVAL;
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) {
struct hugetlbfs_inode_info *info;
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;
info = HUGETLBFS_I(inode);
mpol_shared_policy_init(&info->policy, NULL);
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>
2012-04-25 16:01:50 -07:00
lockdep_annotate_inode_mutex_key(inode);
}
return inode;
}
static struct inode *hugetlbfs_get_inode(struct super_block *sb,
struct inode *dir,
umode_t mode, dev_t dev)
{
struct inode *inode;
inode = new_inode(sb);
if (inode) {
struct hugetlbfs_inode_info *info;
inode->i_ino = get_next_ino();
inode_init_owner(inode, dir, mode);
inode->i_mapping->a_ops = &hugetlbfs_aops;
inode->i_mapping->backing_dev_info =&hugetlbfs_backing_dev_info;
inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
INIT_LIST_HEAD(&inode->i_mapping->private_list);
info = HUGETLBFS_I(inode);
hugetlbfs: allow the creation of files suitable for MAP_PRIVATE on the vfs internal mount This patchset adds a flag to mmap that allows the user to request that an anonymous mapping be backed with huge pages. This mapping will borrow functionality from the huge page shm code to create a file on the kernel internal mount and use it to approximate an anonymous mapping. The MAP_HUGETLB flag is a modifier to MAP_ANONYMOUS and will not work without both flags being preset. A new flag is necessary because there is no other way to hook into huge pages without creating a file on a hugetlbfs mount which wouldn't be MAP_ANONYMOUS. To userspace, this mapping will behave just like an anonymous mapping because the file is not accessible outside of the kernel. This patchset is meant to simplify the programming model. Presently there is a large chunk of boiler platecode, contained in libhugetlbfs, required to create private, hugepage backed mappings. This patch set would allow use of hugepages without linking to libhugetlbfs or having hugetblfs mounted. Unification of the VM code would provide these same benefits, but it has been resisted each time that it has been suggested for several reasons: it would break PAGE_SIZE assumptions across the kernel, it makes page-table abstractions really expensive, and it does not provide any benefit on architectures that do not support huge pages, incurring fast path penalties without providing any benefit on these architectures. This patch: There are two means of creating mappings backed by huge pages: 1. mmap() a file created on hugetlbfs 2. Use shm which creates a file on an internal mount which essentially maps it MAP_SHARED The internal mount is only used for shared mappings but there is very little that stops it being used for private mappings. This patch extends hugetlbfs_file_setup() to deal with the creation of files that will be mapped MAP_PRIVATE on the internal hugetlbfs mount. This extended API is used in a subsequent patch to implement the MAP_HUGETLB mmap() flag. Signed-off-by: Eric Munson <ebmunson@us.ibm.com> Acked-by: David Rientjes <rientjes@google.com> Cc: Mel Gorman <mel@csn.ul.ie> Cc: Adam Litke <agl@us.ibm.com> Cc: David Gibson <david@gibson.dropbear.id.au> Cc: Lee Schermerhorn <lee.schermerhorn@hp.com> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: Hugh Dickins <hugh.dickins@tiscali.co.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-09-21 17:03:43 -07:00
/*
* The policy is initialized here even if we are creating a
* private inode because initialization simply creates an
* an empty rb tree and calls spin_lock_init(), later when we
* call mpol_free_shared_policy() it will just return because
* the rb tree will still be empty.
*/
mempolicy: use struct mempolicy pointer in shmem_sb_info This patch replaces the mempolicy mode, mode_flags, and nodemask in the shmem_sb_info struct with a struct mempolicy pointer, initialized to NULL. This removes dependency on the details of mempolicy from shmem.c and hugetlbfs inode.c and simplifies the interfaces. mpol_parse_str() in mempolicy.c is changed to return, via a pointer to a pointer arg, a struct mempolicy pointer on success. For MPOL_DEFAULT, the returned pointer is NULL. Further, mpol_parse_str() now takes a 'no_context' argument that causes the input nodemask to be stored in the w.user_nodemask of the created mempolicy for use when the mempolicy is installed in a tmpfs inode shared policy tree. At that time, any cpuset contextualization is applied to the original input nodemask. This preserves the previous behavior where the input nodemask was stored in the superblock. We can think of the returned mempolicy as "context free". Because mpol_parse_str() is now calling mpol_new(), we can remove from mpol_to_str() the semantic checks that mpol_new() already performs. Add 'no_context' parameter to mpol_to_str() to specify that it should format the nodemask in w.user_nodemask for 'bind' and 'interleave' policies. Change mpol_shared_policy_init() to take a pointer to a "context free" struct mempolicy and to create a new, "contextualized" mempolicy using the mode, mode_flags and user_nodemask from the input mempolicy. Note: we know that the mempolicy passed to mpol_to_str() or mpol_shared_policy_init() from a tmpfs superblock is "context free". This is currently the only instance thereof. However, if we found more uses for this concept, and introduced any ambiguity as to whether a mempolicy was context free or not, we could add another internal mode flag to identify context free mempolicies. Then, we could remove the 'no_context' argument from mpol_to_str(). Added shmem_get_sbmpol() to return a reference counted superblock mempolicy, if one exists, to pass to mpol_shared_policy_init(). We must add the reference under the sb stat_lock to prevent races with replacement of the mpol by remount. This reference is removed in mpol_shared_policy_init(). [akpm@linux-foundation.org: build fix] [akpm@linux-foundation.org: another build fix] [akpm@linux-foundation.org: yet another build fix] Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Cc: Christoph Lameter <clameter@sgi.com> Cc: David Rientjes <rientjes@google.com> Cc: Mel Gorman <mel@csn.ul.ie> Cc: Andi Kleen <ak@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 02:13:26 -07:00
mpol_shared_policy_init(&info->policy, NULL);
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;
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 04:48:12 -07:00
lockdep_annotate_inode_mutex_key(inode);
}
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;
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;
return error;
}
/*
* mark the head page dirty
*/
static int hugetlbfs_set_page_dirty(struct page *page)
{
2007-05-06 14:49:39 -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>
2012-12-11 17:02:31 -07:00
if (rc != MIGRATEPAGE_SUCCESS)
return rc;
migrate_page_copy(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>
2012-12-11 17:02:31 -07:00
return MIGRATEPAGE_SUCCESS;
}
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(dentry->d_inode);
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>
2012-03-21 16:34:12 -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>
2012-03-21 16:34:12 -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;
}
return &p->vfs_inode;
}
2011-01-06 23:49:49 -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);
2011-01-06 23:49:49 -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,
};
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 = hugetlbfs_read,
.mmap = hugetlbfs_file_mmap,
.fsync = noop_fsync,
.get_unmapped_area = hugetlb_get_unmapped_area,
llseek: automatically add .llseek fop All file_operations should get a .llseek operation so we can make nonseekable_open the default for future file operations without a .llseek pointer. The three cases that we can automatically detect are no_llseek, seq_lseek and default_llseek. For cases where we can we can automatically prove that the file offset is always ignored, we use noop_llseek, which maintains the current behavior of not returning an error from a seek. New drivers should normally not use noop_llseek but instead use no_llseek and call nonseekable_open at open time. Existing drivers can be converted to do the same when the maintainer knows for certain that no user code relies on calling seek on the device file. The generated code is often incorrectly indented and right now contains comments that clarify for each added line why a specific variant was chosen. In the version that gets submitted upstream, the comments will be gone and I will manually fix the indentation, because there does not seem to be a way to do that using coccinelle. Some amount of new code is currently sitting in linux-next that should get the same modifications, which I will do at the end of the merge window. Many thanks to Julia Lawall for helping me learn to write a semantic patch that does all this. ===== begin semantic patch ===== // This adds an llseek= method to all file operations, // as a preparation for making no_llseek the default. // // The rules are // - use no_llseek explicitly if we do nonseekable_open // - use seq_lseek for sequential files // - use default_llseek if we know we access f_pos // - use noop_llseek if we know we don't access f_pos, // but we still want to allow users to call lseek // @ open1 exists @ identifier nested_open; @@ nested_open(...) { <+... nonseekable_open(...) ...+> } @ open exists@ identifier open_f; identifier i, f; identifier open1.nested_open; @@ int open_f(struct inode *i, struct file *f) { <+... ( nonseekable_open(...) | nested_open(...) ) ...+> } @ read disable optional_qualifier exists @ identifier read_f; identifier f, p, s, off; type ssize_t, size_t, loff_t; expression E; identifier func; @@ ssize_t read_f(struct file *f, char *p, size_t s, loff_t *off) { <+... ( *off = E | *off += E | func(..., off, ...) | E = *off ) ...+> } @ read_no_fpos disable optional_qualifier exists @ identifier read_f; identifier f, p, s, off; type ssize_t, size_t, loff_t; @@ ssize_t read_f(struct file *f, char *p, size_t s, loff_t *off) { ... when != off } @ write @ identifier write_f; identifier f, p, s, off; type ssize_t, size_t, loff_t; expression E; identifier func; @@ ssize_t write_f(struct file *f, const char *p, size_t s, loff_t *off) { <+... ( *off = E | *off += E | func(..., off, ...) | E = *off ) ...+> } @ write_no_fpos @ identifier write_f; identifier f, p, s, off; type ssize_t, size_t, loff_t; @@ ssize_t write_f(struct file *f, const char *p, size_t s, loff_t *off) { ... when != off } @ fops0 @ identifier fops; @@ struct file_operations fops = { ... }; @ has_llseek depends on fops0 @ identifier fops0.fops; identifier llseek_f; @@ struct file_operations fops = { ... .llseek = llseek_f, ... }; @ has_read depends on fops0 @ identifier fops0.fops; identifier read_f; @@ struct file_operations fops = { ... .read = read_f, ... }; @ has_write depends on fops0 @ identifier fops0.fops; identifier write_f; @@ struct file_operations fops = { ... .write = write_f, ... }; @ has_open depends on fops0 @ identifier fops0.fops; identifier open_f; @@ struct file_operations fops = { ... .open = open_f, ... }; // use no_llseek if we call nonseekable_open //////////////////////////////////////////// @ nonseekable1 depends on !has_llseek && has_open @ identifier fops0.fops; identifier nso ~= "nonseekable_open"; @@ struct file_operations fops = { ... .open = nso, ... +.llseek = no_llseek, /* nonseekable */ }; @ nonseekable2 depends on !has_llseek @ identifier fops0.fops; identifier open.open_f; @@ struct file_operations fops = { ... .open = open_f, ... +.llseek = no_llseek, /* open uses nonseekable */ }; // use seq_lseek for sequential files ///////////////////////////////////// @ seq depends on !has_llseek @ identifier fops0.fops; identifier sr ~= "seq_read"; @@ struct file_operations fops = { ... .read = sr, ... +.llseek = seq_lseek, /* we have seq_read */ }; // use default_llseek if there is a readdir /////////////////////////////////////////// @ fops1 depends on !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier readdir_e; @@ // any other fop is used that changes pos struct file_operations fops = { ... .readdir = readdir_e, ... +.llseek = default_llseek, /* readdir is present */ }; // use default_llseek if at least one of read/write touches f_pos ///////////////////////////////////////////////////////////////// @ fops2 depends on !fops1 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier read.read_f; @@ // read fops use offset struct file_operations fops = { ... .read = read_f, ... +.llseek = default_llseek, /* read accesses f_pos */ }; @ fops3 depends on !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier write.write_f; @@ // write fops use offset struct file_operations fops = { ... .write = write_f, ... + .llseek = default_llseek, /* write accesses f_pos */ }; // Use noop_llseek if neither read nor write accesses f_pos /////////////////////////////////////////////////////////// @ fops4 depends on !fops1 && !fops2 && !fops3 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier read_no_fpos.read_f; identifier write_no_fpos.write_f; @@ // write fops use offset struct file_operations fops = { ... .write = write_f, .read = read_f, ... +.llseek = noop_llseek, /* read and write both use no f_pos */ }; @ depends on has_write && !has_read && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier write_no_fpos.write_f; @@ struct file_operations fops = { ... .write = write_f, ... +.llseek = noop_llseek, /* write uses no f_pos */ }; @ depends on has_read && !has_write && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier read_no_fpos.read_f; @@ struct file_operations fops = { ... .read = read_f, ... +.llseek = noop_llseek, /* read uses no f_pos */ }; @ depends on !has_read && !has_write && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; @@ struct file_operations fops = { ... +.llseek = noop_llseek, /* no read or write fn */ }; ===== End semantic patch ===== Signed-off-by: Arnd Bergmann <arnd@arndb.de> Cc: Julia Lawall <julia@diku.dk> Cc: Christoph Hellwig <hch@infradead.org>
2010-08-15 09:52:59 -07:00
.llseek = default_llseek,
};
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 = generic_show_options,
};
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 size = 0;
enum { NO_SIZE, SIZE_STD, SIZE_PERCENT } setsize = 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;
size = memparse(args[0].from, &rest);
setsize = SIZE_STD;
if (*rest == '%')
setsize = 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) {
printk(KERN_ERR
"hugetlbfs: Unsupported page size %lu MB\n",
ps >> 20);
return -EINVAL;
}
break;
}
default:
printk(KERN_ERR "hugetlbfs: Bad mount option: \"%s\"\n",
p);
return -EINVAL;
break;
}
}
/* Do size after hstate is set up */
if (setsize > NO_SIZE) {
struct hstate *h = pconfig->hstate;
if (setsize == SIZE_PERCENT) {
size <<= huge_page_shift(h);
size *= h->max_huge_pages;
do_div(size, 100);
}
pconfig->nr_blocks = (size >> huge_page_shift(h));
}
return 0;
bad_val:
printk(KERN_ERR "hugetlbfs: 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;
save_mount_options(sb, data);
config.nr_blocks = -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;
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>
2012-03-21 16:34:12 -07:00
sbinfo->spool = NULL;
if (config.nr_blocks != -1) {
sbinfo->spool = hugepage_new_subpool(config.nr_blocks);
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:
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>
2012-03-21 16:34:12 -07:00
if (sbinfo->spool)
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,
};
fs: Limit sys_mount to only request filesystem modules. Modify the request_module to prefix the file system type with "fs-" and add aliases to all of the filesystems that can be built as modules to match. A common practice is to build all of the kernel code and leave code that is not commonly needed as modules, with the result that many users are exposed to any bug anywhere in the kernel. Looking for filesystems with a fs- prefix limits the pool of possible modules that can be loaded by mount to just filesystems trivially making things safer with no real cost. Using aliases means user space can control the policy of which filesystem modules are auto-loaded by editing /etc/modprobe.d/*.conf with blacklist and alias directives. Allowing simple, safe, well understood work-arounds to known problematic software. This also addresses a rare but unfortunate problem where the filesystem name is not the same as it's module name and module auto-loading would not work. While writing this patch I saw a handful of such cases. The most significant being autofs that lives in the module autofs4. This is relevant to user namespaces because we can reach the request module in get_fs_type() without having any special permissions, and people get uncomfortable when a user specified string (in this case the filesystem type) goes all of the way to request_module. After having looked at this issue I don't think there is any particular reason to perform any filtering or permission checks beyond making it clear in the module request that we want a filesystem module. The common pattern in the kernel is to call request_module() without regards to the users permissions. In general all a filesystem module does once loaded is call register_filesystem() and go to sleep. Which means there is not much attack surface exposed by loading a filesytem module unless the filesystem is mounted. In a user namespace filesystems are not mounted unless .fs_flags = FS_USERNS_MOUNT, which most filesystems do not set today. Acked-by: Serge Hallyn <serge.hallyn@canonical.com> Acked-by: Kees Cook <keescook@chromium.org> Reported-by: Kees Cook <keescook@google.com> Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
2013-03-02 20:39:14 -07:00
MODULE_ALIAS_FS("hugetlbfs");
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>
2012-12-11 17:01:34 -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>
2012-12-11 17:01:34 -07:00
static int get_hstate_idx(int page_size_log)
{
struct hstate *h;
if (!page_size_log)
return default_hstate_idx;
h = size_to_hstate(1 << page_size_log);
if (!h)
return -1;
return h - hstates;
}
static char *hugetlb_dname(struct dentry *dentry, char *buffer, int buflen)
{
return dynamic_dname(dentry, buffer, buflen, "/%s (deleted)",
dentry->d_name.name);
}
static struct dentry_operations anon_ops = {
.d_dname = hugetlb_dname
};
struct file *hugetlb_file_setup(const char *name, unsigned long addr,
size_t size, vm_flags_t acctflag,
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>
2012-12-11 17:01:34 -07:00
struct user_struct **user,
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;
struct hstate *hstate;
unsigned long num_pages;
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>
2012-12-11 17:01:34 -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>
2012-12-11 17:01:34 -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);
printk_once(KERN_WARNING
"%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>
2012-12-11 17:01:34 -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>
2007-10-16 23:31:13 -07:00
goto out_dentry;
hstate = hstate_inode(inode);
size += addr & ~huge_page_mask(hstate);
num_pages = ALIGN(size, huge_page_size(hstate)) >>
huge_page_shift(hstate);
file = ERR_PTR(-ENOMEM);
if (hugetlb_reserve_pages(inode, 0, num_pages, 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 01:08:55 -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>
2007-10-16 23:31:13 -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>
2007-10-16 23:31:13 -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>
2007-10-16 23:31:13 -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 01:08:55 -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>
2012-12-11 17:01:34 -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>
2012-12-11 17:01:34 -07:00
int i;
error = bdi_init(&hugetlbfs_backing_dev_info);
if (error)
return error;
error = -ENOMEM;
hugetlbfs_inode_cachep = kmem_cache_create("hugetlbfs_inode_cache",
sizeof(struct hugetlbfs_inode_info),
0, 0, 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>
2012-12-11 17:01:34 -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>
2012-12-11 17:01:34 -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>
2012-12-11 17:01:34 -07:00
if (IS_ERR(hugetlbfs_vfsmount[i])) {
pr_err("hugetlb: Cannot mount internal hugetlbfs for "
"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:
bdi_destroy(&hugetlbfs_backing_dev_info);
return error;
}
static void __exit exit_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>
2012-12-11 17:01:34 -07:00
struct hstate *h;
int i;
/*
* Make sure all delayed rcu free inodes are flushed before we
* destroy cache.
*/
rcu_barrier();
kmem_cache_destroy(hugetlbfs_inode_cachep);
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>
2012-12-11 17:01:34 -07:00
i = 0;
for_each_hstate(h)
kern_unmount(hugetlbfs_vfsmount[i++]);
unregister_filesystem(&hugetlbfs_fs_type);
bdi_destroy(&hugetlbfs_backing_dev_info);
}
module_init(init_hugetlbfs_fs)
module_exit(exit_hugetlbfs_fs)
MODULE_LICENSE("GPL");