linux/fs/hugetlbfs/inode.c

1056 lines
24 KiB
C
Raw Normal View History

/*
* hugetlbpage-backed filesystem. Based on ramfs.
*
* William Irwin, 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/quotaops.h>
#include <linux/slab.h>
#include <linux/dnotify.h>
#include <linux/statfs.h>
#include <linux/security.h>
#include <asm/uaccess.h>
/* some random number */
#define HUGETLBFS_MAGIC 0x958458f6
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;
static struct backing_dev_info hugetlbfs_backing_dev_info = {
.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->f_path.dentry->d_inode;
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 10:03:32 +00:00
/*
* 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 10:03:32 +00:00
*/
vma->vm_flags |= VM_HUGETLB | VM_RESERVED;
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>
2008-07-24 04:27:23 +00:00
if (hugetlb_reserve_pages(inode,
vma->vm_pgoff >> huge_page_order(h),
len >> huge_page_shift(h), vma))
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 08:08:55 +00:00
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;
unsigned long start_addr;
struct hstate *h = hstate_file(file);
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;
}
start_addr = mm->free_area_cache;
[PATCH] Avoiding mmap fragmentation Ingo recently introduced a great speedup for allocating new mmaps using the free_area_cache pointer which boosts the specweb SSL benchmark by 4-5% and causes huge performance increases in thread creation. The downside of this patch is that it does lead to fragmentation in the mmap-ed areas (visible via /proc/self/maps), such that some applications that work fine under 2.4 kernels quickly run out of memory on any 2.6 kernel. The problem is twofold: 1) the free_area_cache is used to continue a search for memory where the last search ended. Before the change new areas were always searched from the base address on. So now new small areas are cluttering holes of all sizes throughout the whole mmap-able region whereas before small holes tended to close holes near the base leaving holes far from the base large and available for larger requests. 2) the free_area_cache also is set to the location of the last munmap-ed area so in scenarios where we allocate e.g. five regions of 1K each, then free regions 4 2 3 in this order the next request for 1K will be placed in the position of the old region 3, whereas before we appended it to the still active region 1, placing it at the location of the old region 2. Before we had 1 free region of 2K, now we only get two free regions of 1K -> fragmentation. The patch addresses thes issues by introducing yet another cache descriptor cached_hole_size that contains the largest known hole size below the current free_area_cache. If a new request comes in the size is compared against the cached_hole_size and if the request can be filled with a hole below free_area_cache the search is started from the base instead. The results look promising: Whereas 2.6.12-rc4 fragments quickly and my (earlier posted) leakme.c test program terminates after 50000+ iterations with 96 distinct and fragmented maps in /proc/self/maps it performs nicely (as expected) with thread creation, Ingo's test_str02 with 20000 threads requires 0.7s system time. Taking out Ingo's patch (un-patch available per request) by basically deleting all mentions of free_area_cache from the kernel and starting the search for new memory always at the respective bases we observe: leakme terminates successfully with 11 distinctive hardly fragmented areas in /proc/self/maps but thread creating is gringdingly slow: 30+s(!) system time for Ingo's test_str02 with 20000 threads. Now - drumroll ;-) the appended patch works fine with leakme: it ends with only 7 distinct areas in /proc/self/maps and also thread creation seems sufficiently fast with 0.71s for 20000 threads. Signed-off-by: Wolfgang Wander <wwc@rentec.com> Credit-to: "Richard Purdie" <rpurdie@rpsys.net> Signed-off-by: Ken Chen <kenneth.w.chen@intel.com> Acked-by: Ingo Molnar <mingo@elte.hu> (partly) Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-06-22 00:14:49 +00:00
if (len <= mm->cached_hole_size)
start_addr = TASK_UNMAPPED_BASE;
full_search:
addr = ALIGN(start_addr, huge_page_size(h));
for (vma = find_vma(mm, addr); ; vma = vma->vm_next) {
/* At this point: (!vma || addr < vma->vm_end). */
if (TASK_SIZE - len < addr) {
/*
* Start a new search - just in case we missed
* some holes.
*/
if (start_addr != TASK_UNMAPPED_BASE) {
start_addr = TASK_UNMAPPED_BASE;
goto full_search;
}
return -ENOMEM;
}
if (!vma || addr + len <= vma->vm_start)
return addr;
addr = ALIGN(vma->vm_end, huge_page_size(h));
}
}
#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;
mutex_lock(&inode->i_mutex);
/* validate length */
if (len == 0)
goto out;
isize = i_size_read(inode);
if (!isize)
goto out;
end_index = (isize - 1) >> huge_page_shift(h);
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);
if (index >= end_index) {
if (index > end_index)
goto out;
nr = ((isize - 1) & ~huge_page_mask(h)) + 1;
if (nr <= offset) {
goto out;
}
}
nr = nr - offset;
/* Find the page */
page = find_get_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 {
/*
* We have the page, copy it to user space buffer.
*/
ra = hugetlbfs_read_actor(page, offset, buf, len, nr);
ret = ra;
}
if (ra < 0) {
if (retval == 0)
retval = ra;
if (page)
page_cache_release(page);
goto out;
}
offset += ret;
retval += ret;
len -= ret;
index += offset >> huge_page_shift(h);
offset &= ~huge_page_mask(h);
if (page)
page_cache_release(page);
/* short read or no more work */
if ((ret != nr) || (len == 0))
break;
}
out:
*ppos = ((loff_t)index << huge_page_shift(h)) + offset;
mutex_unlock(&inode->i_mutex);
return retval;
}
/*
* Read a page. Again trivial. If it didn't already exist
* in the page cache, it is zero-filled.
*/
static int hugetlbfs_readpage(struct file *file, struct page * page)
{
unlock_page(page);
return -EINVAL;
}
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 21:46:42 +00:00
cancel_dirty_page(page, /* No IO accounting for huge pages? */0);
ClearPageUptodate(page);
remove_from_page_cache(page);
put_page(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 08:08:55 +00:00
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 08:08:55 +00:00
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_delete_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 08:08:55 +00:00
truncate_hugepages(inode, 0);
clear_inode(inode);
}
static void hugetlbfs_forget_inode(struct inode *inode) __releases(inode_lock)
{
struct super_block *sb = inode->i_sb;
if (!hlist_unhashed(&inode->i_hash)) {
if (!(inode->i_state & (I_DIRTY|I_SYNC)))
list_move(&inode->i_list, &inode_unused);
inodes_stat.nr_unused++;
if (!sb || (sb->s_flags & MS_ACTIVE)) {
spin_unlock(&inode_lock);
return;
}
inode->i_state |= I_WILL_FREE;
spin_unlock(&inode_lock);
/*
* write_inode_now is a noop as we set BDI_CAP_NO_WRITEBACK
* in our backing_dev_info.
*/
write_inode_now(inode, 1);
spin_lock(&inode_lock);
inode->i_state &= ~I_WILL_FREE;
inodes_stat.nr_unused--;
hlist_del_init(&inode->i_hash);
}
list_del_init(&inode->i_list);
list_del_init(&inode->i_sb_list);
inode->i_state |= I_FREEING;
inodes_stat.nr_inodes--;
spin_unlock(&inode_lock);
[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 08:08:55 +00:00
truncate_hugepages(inode, 0);
clear_inode(inode);
destroy_inode(inode);
}
static void hugetlbfs_drop_inode(struct inode *inode)
{
if (!inode->i_nlink)
generic_delete_inode(inode);
else
hugetlbfs_forget_inode(inode);
}
static inline void
hugetlb_vmtruncate_list(struct prio_tree_root *root, pgoff_t pgoff)
{
struct vm_area_struct *vma;
struct prio_tree_iter iter;
vma_prio_tree_foreach(vma, &iter, root, pgoff, ULONG_MAX) {
unsigned long v_offset;
/*
* Can the expression below overflow on 32-bit arches?
* No, because the prio_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,
hugetlb: guarantee that COW faults for a process that called mmap(MAP_PRIVATE) on hugetlbfs will succeed After patch 2 in this series, a process that successfully calls mmap() for a MAP_PRIVATE mapping will be guaranteed to successfully fault until a process calls fork(). At that point, the next write fault from the parent could fail due to COW if the child still has a reference. We only reserve pages for the parent but a copy must be made to avoid leaking data from the parent to the child after fork(). Reserves could be taken for both parent and child at fork time to guarantee faults but if the mapping is large it is highly likely we will not have sufficient pages for the reservation, and it is common to fork only to exec() immediatly after. A failure here would be very undesirable. Note that the current behaviour of mainline with MAP_PRIVATE pages is pretty bad. The following situation is allowed to occur today. 1. Process calls mmap(MAP_PRIVATE) 2. Process calls mlock() to fault all pages and makes sure it succeeds 3. Process forks() 4. Process writes to MAP_PRIVATE mapping while child still exists 5. If the COW fails at this point, the process gets SIGKILLed even though it had taken care to ensure the pages existed This patch improves the situation by guaranteeing the reliability of the process that successfully calls mmap(). When the parent performs COW, it will try to satisfy the allocation without using reserves. If that fails the parent will steal the page leaving any children without a page. Faults from the child after that point will result in failure. If the child COW happens first, an attempt will be made to allocate the page without reserves and the child will get SIGKILLed on failure. To summarise the new behaviour: 1. If the original mapper performs COW on a private mapping with multiple references, it will attempt to allocate a hugepage from the pool or the buddy allocator without using the existing reserves. On fail, VMAs mapping the same area are traversed and the page being COW'd is unmapped where found. It will then steal the original page as the last mapper in the normal way. 2. The VMAs the pages were unmapped from are flagged to note that pages with data no longer exist. Future no-page faults on those VMAs will terminate the process as otherwise it would appear that data was corrupted. A warning is printed to the console that this situation occured. 2. If the child performs COW first, it will attempt to satisfy the COW from the pool if there are enough pages or via the buddy allocator if overcommit is allowed and the buddy allocator can satisfy the request. If it fails, the child will be killed. If the pool is large enough, existing applications will not notice that the reserves were a factor. Existing applications depending on the no-reserves been set are unlikely to exist as for much of the history of hugetlbfs, pages were prefaulted at mmap(), allocating the pages at that point or failing the mmap(). [npiggin@suse.de: fix CONFIG_HUGETLB=n build] 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> Cc: Nick Piggin <npiggin@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-24 04:27:25 +00:00
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);
spin_lock(&mapping->i_mmap_lock);
if (!prio_tree_empty(&mapping->i_mmap))
hugetlb_vmtruncate_list(&mapping->i_mmap, pgoff);
spin_unlock(&mapping->i_mmap_lock);
[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 08:08:55 +00:00
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)
goto out;
if (ia_valid & ATTR_SIZE) {
error = -EINVAL;
if (!(attr->ia_size & ~huge_page_mask(h)))
error = hugetlb_vmtruncate(inode, attr->ia_size);
if (error)
goto out;
attr->ia_valid &= ~ATTR_SIZE;
}
error = inode_setattr(inode, attr);
out:
return error;
}
static struct inode *hugetlbfs_get_inode(struct super_block *sb, uid_t uid,
gid_t gid, int mode, dev_t dev)
{
struct inode *inode;
inode = new_inode(sb);
if (inode) {
struct hugetlbfs_inode_info *info;
inode->i_mode = mode;
inode->i_uid = uid;
inode->i_gid = gid;
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);
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 09:13:26 +00:00
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;
}
}
return inode;
}
/*
* File creation. Allocate an inode, and we're done..
*/
static int hugetlbfs_mknod(struct inode *dir,
struct dentry *dentry, int mode, dev_t dev)
{
struct inode *inode;
int error = -ENOSPC;
gid_t gid;
if (dir->i_mode & S_ISGID) {
gid = dir->i_gid;
if (S_ISDIR(mode))
mode |= S_ISGID;
} else {
gid = current_fsgid();
}
inode = hugetlbfs_get_inode(dir->i_sb, current_fsuid(), gid, 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, int 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, int mode, struct nameidata *nd)
{
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;
gid_t gid;
if (dir->i_mode & S_ISGID)
gid = dir->i_gid;
else
gid = current_fsgid();
inode = hugetlbfs_get_inode(dir->i_sb, current_fsuid(),
gid, 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 21:49:39 +00:00
struct page *head = compound_head(page);
SetPageDirty(head);
return 0;
}
static int hugetlbfs_statfs(struct dentry *dentry, struct kstatfs *buf)
{
struct hugetlbfs_sb_info *sbinfo = HUGETLBFS_SB(dentry->d_sb);
struct hstate *h = hstate_inode(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() */
if (sbinfo->max_blocks >= 0) {
buf->f_blocks = sbinfo->max_blocks;
buf->f_bavail = buf->f_bfree = sbinfo->free_blocks;
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;
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;
}
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);
kmem_cache_free(hugetlbfs_inode_cachep, HUGETLBFS_I(inode));
}
static const struct address_space_operations hugetlbfs_aops = {
.readpage = hugetlbfs_readpage,
.write_begin = hugetlbfs_write_begin,
.write_end = hugetlbfs_write_end,
.set_page_dirty = hugetlbfs_set_page_dirty,
};
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 = simple_sync_file,
.get_unmapped_area = hugetlb_get_unmapped_area,
};
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,
.statfs = hugetlbfs_statfs,
.delete_inode = hugetlbfs_delete_inode,
.drop_inode = hugetlbfs_drop_inode,
.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 = option;
break;
case Opt_gid:
if (match_int(&args[0], &option))
goto bad_val;
pconfig->gid = option;
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 1;
}
static int
hugetlbfs_fill_super(struct super_block *sb, void *data, int silent)
{
struct inode * inode;
struct dentry * root;
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_blocks = config.nr_blocks;
sbinfo->free_blocks = config.nr_blocks;
sbinfo->max_inodes = config.nr_inodes;
sbinfo->free_inodes = config.nr_inodes;
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;
inode = hugetlbfs_get_inode(sb, config.uid, config.gid,
S_IFDIR | config.mode, 0);
if (!inode)
goto out_free;
root = d_alloc_root(inode);
if (!root) {
iput(inode);
goto out_free;
}
sb->s_root = root;
return 0;
out_free:
kfree(sbinfo);
return -ENOMEM;
}
int hugetlb_get_quota(struct address_space *mapping, long delta)
{
int ret = 0;
struct hugetlbfs_sb_info *sbinfo = HUGETLBFS_SB(mapping->host->i_sb);
if (sbinfo->free_blocks > -1) {
spin_lock(&sbinfo->stat_lock);
if (sbinfo->free_blocks - delta >= 0)
sbinfo->free_blocks -= delta;
else
ret = -ENOMEM;
spin_unlock(&sbinfo->stat_lock);
}
return ret;
}
void hugetlb_put_quota(struct address_space *mapping, long delta)
{
struct hugetlbfs_sb_info *sbinfo = HUGETLBFS_SB(mapping->host->i_sb);
if (sbinfo->free_blocks > -1) {
spin_lock(&sbinfo->stat_lock);
sbinfo->free_blocks += delta;
spin_unlock(&sbinfo->stat_lock);
}
}
[PATCH] VFS: Permit filesystem to override root dentry on mount Extend the get_sb() filesystem operation to take an extra argument that permits the VFS to pass in the target vfsmount that defines the mountpoint. The filesystem is then required to manually set the superblock and root dentry pointers. For most filesystems, this should be done with simple_set_mnt() which will set the superblock pointer and then set the root dentry to the superblock's s_root (as per the old default behaviour). The get_sb() op now returns an integer as there's now no need to return the superblock pointer. This patch permits a superblock to be implicitly shared amongst several mount points, such as can be done with NFS to avoid potential inode aliasing. In such a case, simple_set_mnt() would not be called, and instead the mnt_root and mnt_sb would be set directly. The patch also makes the following changes: (*) the get_sb_*() convenience functions in the core kernel now take a vfsmount pointer argument and return an integer, so most filesystems have to change very little. (*) If one of the convenience function is not used, then get_sb() should normally call simple_set_mnt() to instantiate the vfsmount. This will always return 0, and so can be tail-called from get_sb(). (*) generic_shutdown_super() now calls shrink_dcache_sb() to clean up the dcache upon superblock destruction rather than shrink_dcache_anon(). This is required because the superblock may now have multiple trees that aren't actually bound to s_root, but that still need to be cleaned up. The currently called functions assume that the whole tree is rooted at s_root, and that anonymous dentries are not the roots of trees which results in dentries being left unculled. However, with the way NFS superblock sharing are currently set to be implemented, these assumptions are violated: the root of the filesystem is simply a dummy dentry and inode (the real inode for '/' may well be inaccessible), and all the vfsmounts are rooted on anonymous[*] dentries with child trees. [*] Anonymous until discovered from another tree. (*) The documentation has been adjusted, including the additional bit of changing ext2_* into foo_* in the documentation. [akpm@osdl.org: convert ipath_fs, do other stuff] Signed-off-by: David Howells <dhowells@redhat.com> Acked-by: Al Viro <viro@zeniv.linux.org.uk> Cc: Nathan Scott <nathans@sgi.com> Cc: Roland Dreier <rolandd@cisco.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 09:02:57 +00:00
static int hugetlbfs_get_sb(struct file_system_type *fs_type,
int flags, const char *dev_name, void *data, struct vfsmount *mnt)
{
[PATCH] VFS: Permit filesystem to override root dentry on mount Extend the get_sb() filesystem operation to take an extra argument that permits the VFS to pass in the target vfsmount that defines the mountpoint. The filesystem is then required to manually set the superblock and root dentry pointers. For most filesystems, this should be done with simple_set_mnt() which will set the superblock pointer and then set the root dentry to the superblock's s_root (as per the old default behaviour). The get_sb() op now returns an integer as there's now no need to return the superblock pointer. This patch permits a superblock to be implicitly shared amongst several mount points, such as can be done with NFS to avoid potential inode aliasing. In such a case, simple_set_mnt() would not be called, and instead the mnt_root and mnt_sb would be set directly. The patch also makes the following changes: (*) the get_sb_*() convenience functions in the core kernel now take a vfsmount pointer argument and return an integer, so most filesystems have to change very little. (*) If one of the convenience function is not used, then get_sb() should normally call simple_set_mnt() to instantiate the vfsmount. This will always return 0, and so can be tail-called from get_sb(). (*) generic_shutdown_super() now calls shrink_dcache_sb() to clean up the dcache upon superblock destruction rather than shrink_dcache_anon(). This is required because the superblock may now have multiple trees that aren't actually bound to s_root, but that still need to be cleaned up. The currently called functions assume that the whole tree is rooted at s_root, and that anonymous dentries are not the roots of trees which results in dentries being left unculled. However, with the way NFS superblock sharing are currently set to be implemented, these assumptions are violated: the root of the filesystem is simply a dummy dentry and inode (the real inode for '/' may well be inaccessible), and all the vfsmounts are rooted on anonymous[*] dentries with child trees. [*] Anonymous until discovered from another tree. (*) The documentation has been adjusted, including the additional bit of changing ext2_* into foo_* in the documentation. [akpm@osdl.org: convert ipath_fs, do other stuff] Signed-off-by: David Howells <dhowells@redhat.com> Acked-by: Al Viro <viro@zeniv.linux.org.uk> Cc: Nathan Scott <nathans@sgi.com> Cc: Roland Dreier <rolandd@cisco.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 09:02:57 +00:00
return get_sb_nodev(fs_type, flags, data, hugetlbfs_fill_super, mnt);
}
static struct file_system_type hugetlbfs_fs_type = {
.name = "hugetlbfs",
.get_sb = hugetlbfs_get_sb,
.kill_sb = kill_litter_super,
};
static struct vfsmount *hugetlbfs_vfsmount;
static int can_do_hugetlb_shm(void)
{
return likely(capable(CAP_IPC_LOCK) ||
in_group_p(sysctl_hugetlb_shm_group) ||
can_do_mlock());
}
struct file *hugetlb_file_setup(const char *name, size_t size)
{
int error = -ENOMEM;
struct file *file;
struct inode *inode;
struct dentry *dentry, *root;
struct qstr quick_string;
struct user_struct *user = current_user();
if (!hugetlbfs_vfsmount)
return ERR_PTR(-ENOENT);
if (!can_do_hugetlb_shm())
return ERR_PTR(-EPERM);
if (!user_shm_lock(size, user))
return ERR_PTR(-ENOMEM);
root = hugetlbfs_vfsmount->mnt_root;
quick_string.name = name;
quick_string.len = strlen(quick_string.name);
quick_string.hash = 0;
dentry = d_alloc(root, &quick_string);
if (!dentry)
goto out_shm_unlock;
error = -ENOSPC;
inode = hugetlbfs_get_inode(root->d_sb, current_fsuid(),
current_fsgid(), S_IFREG | S_IRWXUGO, 0);
if (!inode)
r/o bind mounts: filesystem helpers for custom 'struct file's Why do we need r/o bind mounts? This feature allows a read-only view into a read-write filesystem. In the process of doing that, it also provides infrastructure for keeping track of the number of writers to any given mount. This has a number of uses. It allows chroots to have parts of filesystems writable. It will be useful for containers in the future because users may have root inside a container, but should not be allowed to write to somefilesystems. This also replaces patches that vserver has had out of the tree for several years. It allows security enhancement by making sure that parts of your filesystem read-only (such as when you don't trust your FTP server), when you don't want to have entire new filesystems mounted, or when you want atime selectively updated. I've been using the following script to test that the feature is working as desired. It takes a directory and makes a regular bind and a r/o bind mount of it. It then performs some normal filesystem operations on the three directories, including ones that are expected to fail, like creating a file on the r/o mount. This patch: Some filesystems forego the vfs and may_open() and create their own 'struct file's. This patch creates a couple of helper functions which can be used by these filesystems, and will provide a unified place which the r/o bind mount code may patch. Also, rename an existing, static-scope init_file() to a less generic name. Signed-off-by: Dave Hansen <haveblue@us.ibm.com> Cc: Christoph Hellwig <hch@lst.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-17 06:31:13 +00:00
goto out_dentry;
[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 08:08:55 +00:00
error = -ENOMEM;
if (hugetlb_reserve_pages(inode, 0,
size >> huge_page_shift(hstate_inode(inode)), NULL))
[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 08:08:55 +00:00
goto out_inode;
d_instantiate(dentry, inode);
inode->i_size = size;
inode->i_nlink = 0;
r/o bind mounts: filesystem helpers for custom 'struct file's Why do we need r/o bind mounts? This feature allows a read-only view into a read-write filesystem. In the process of doing that, it also provides infrastructure for keeping track of the number of writers to any given mount. This has a number of uses. It allows chroots to have parts of filesystems writable. It will be useful for containers in the future because users may have root inside a container, but should not be allowed to write to somefilesystems. This also replaces patches that vserver has had out of the tree for several years. It allows security enhancement by making sure that parts of your filesystem read-only (such as when you don't trust your FTP server), when you don't want to have entire new filesystems mounted, or when you want atime selectively updated. I've been using the following script to test that the feature is working as desired. It takes a directory and makes a regular bind and a r/o bind mount of it. It then performs some normal filesystem operations on the three directories, including ones that are expected to fail, like creating a file on the r/o mount. This patch: Some filesystems forego the vfs and may_open() and create their own 'struct file's. This patch creates a couple of helper functions which can be used by these filesystems, and will provide a unified place which the r/o bind mount code may patch. Also, rename an existing, static-scope init_file() to a less generic name. Signed-off-by: Dave Hansen <haveblue@us.ibm.com> Cc: Christoph Hellwig <hch@lst.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-17 06:31:13 +00:00
error = -ENFILE;
file = alloc_file(hugetlbfs_vfsmount, dentry,
FMODE_WRITE | FMODE_READ,
&hugetlbfs_file_operations);
if (!file)
goto out_dentry; /* inode is already attached */
r/o bind mounts: filesystem helpers for custom 'struct file's Why do we need r/o bind mounts? This feature allows a read-only view into a read-write filesystem. In the process of doing that, it also provides infrastructure for keeping track of the number of writers to any given mount. This has a number of uses. It allows chroots to have parts of filesystems writable. It will be useful for containers in the future because users may have root inside a container, but should not be allowed to write to somefilesystems. This also replaces patches that vserver has had out of the tree for several years. It allows security enhancement by making sure that parts of your filesystem read-only (such as when you don't trust your FTP server), when you don't want to have entire new filesystems mounted, or when you want atime selectively updated. I've been using the following script to test that the feature is working as desired. It takes a directory and makes a regular bind and a r/o bind mount of it. It then performs some normal filesystem operations on the three directories, including ones that are expected to fail, like creating a file on the r/o mount. This patch: Some filesystems forego the vfs and may_open() and create their own 'struct file's. This patch creates a couple of helper functions which can be used by these filesystems, and will provide a unified place which the r/o bind mount code may patch. Also, rename an existing, static-scope init_file() to a less generic name. Signed-off-by: Dave Hansen <haveblue@us.ibm.com> Cc: Christoph Hellwig <hch@lst.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-17 06:31:13 +00:00
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 08:08:55 +00:00
out_inode:
iput(inode);
out_dentry:
dput(dentry);
out_shm_unlock:
user_shm_unlock(size, user);
return ERR_PTR(error);
}
static int __init init_hugetlbfs_fs(void)
{
int error;
struct vfsmount *vfsmount;
error = bdi_init(&hugetlbfs_backing_dev_info);
if (error)
return error;
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;
vfsmount = kern_mount(&hugetlbfs_fs_type);
if (!IS_ERR(vfsmount)) {
hugetlbfs_vfsmount = vfsmount;
return 0;
}
error = PTR_ERR(vfsmount);
out:
if (error)
kmem_cache_destroy(hugetlbfs_inode_cachep);
out2:
bdi_destroy(&hugetlbfs_backing_dev_info);
return error;
}
static void __exit exit_hugetlbfs_fs(void)
{
kmem_cache_destroy(hugetlbfs_inode_cachep);
unregister_filesystem(&hugetlbfs_fs_type);
bdi_destroy(&hugetlbfs_backing_dev_info);
}
module_init(init_hugetlbfs_fs)
module_exit(exit_hugetlbfs_fs)
MODULE_LICENSE("GPL");