linux/fs/file.c

904 lines
21 KiB
C
Raw Normal View History

/*
* linux/fs/file.c
*
* Copyright (C) 1998-1999, Stephen Tweedie and Bill Hawes
*
* Manage the dynamic fd arrays in the process files_struct.
*/
#include <linux/syscalls.h>
#include <linux/export.h>
#include <linux/fs.h>
#include <linux/mm.h>
#include <linux/mmzone.h>
#include <linux/time.h>
#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/vmalloc.h>
#include <linux/file.h>
#include <linux/fdtable.h>
#include <linux/bitops.h>
#include <linux/interrupt.h>
#include <linux/spinlock.h>
#include <linux/rcupdate.h>
#include <linux/workqueue.h>
int sysctl_nr_open __read_mostly = 1024*1024;
int sysctl_nr_open_min = BITS_PER_LONG;
int sysctl_nr_open_max = 1024 * 1024; /* raised later */
static void *alloc_fdmem(size_t size)
{
/*
* Very large allocations can stress page reclaim, so fall back to
* vmalloc() if the allocation size will be considered "large" by the VM.
*/
if (size <= (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) {
fs/file.c:fdtable: avoid triggering OOMs from alloc_fdmem Recently due to a spike in connections per second memcached on 3 separate boxes triggered the OOM killer from accept. At the time the OOM killer was triggered there was 4GB out of 36GB free in zone 1. The problem was that alloc_fdtable was allocating an order 3 page (32KiB) to hold a bitmap, and there was sufficient fragmentation that the largest page available was 8KiB. I find the logic that PAGE_ALLOC_COSTLY_ORDER can't fail pretty dubious but I do agree that order 3 allocations are very likely to succeed. There are always pathologies where order > 0 allocations can fail when there are copious amounts of free memory available. Using the pigeon hole principle it is easy to show that it requires 1 page more than 50% of the pages being free to guarantee an order 1 (8KiB) allocation will succeed, 1 page more than 75% of the pages being free to guarantee an order 2 (16KiB) allocation will succeed and 1 page more than 87.5% of the pages being free to guarantee an order 3 allocate will succeed. A server churning memory with a lot of small requests and replies like memcached is a common case that if anything can will skew the odds against large pages being available. Therefore let's not give external applications a practical way to kill linux server applications, and specify __GFP_NORETRY to the kmalloc in alloc_fdmem. Unless I am misreading the code and by the time the code reaches should_alloc_retry in __alloc_pages_slowpath (where __GFP_NORETRY becomes signification). We have already tried everything reasonable to allocate a page and the only thing left to do is wait. So not waiting and falling back to vmalloc immediately seems like the reasonable thing to do even if there wasn't a chance of triggering the OOM killer. Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Eric Dumazet <eric.dumazet@gmail.com> Acked-by: David Rientjes <rientjes@google.com> Cc: Cong Wang <cwang@twopensource.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-02-10 23:25:41 +01:00
void *data = kmalloc(size, GFP_KERNEL|__GFP_NOWARN|__GFP_NORETRY);
if (data != NULL)
return data;
}
return vmalloc(size);
}
static void free_fdmem(void *ptr)
{
is_vmalloc_addr(ptr) ? vfree(ptr) : kfree(ptr);
}
static void __free_fdtable(struct fdtable *fdt)
{
free_fdmem(fdt->fd);
free_fdmem(fdt->open_fds);
kfree(fdt);
}
static void free_fdtable_rcu(struct rcu_head *rcu)
{
__free_fdtable(container_of(rcu, struct fdtable, rcu));
}
/*
* Expand the fdset in the files_struct. Called with the files spinlock
* held for write.
*/
[PATCH] fdtable: Implement new pagesize-based fdtable allocator This patch provides an improved fdtable allocation scheme, useful for expanding fdtable file descriptor entries. The main focus is on the fdarray, as its memory usage grows 128 times faster than that of an fdset. The allocation algorithm sizes the fdarray in such a way that its memory usage increases in easy page-sized chunks. The overall algorithm expands the allowed size in powers of two, in order to amortize the cost of invoking vmalloc() for larger allocation sizes. Namely, the following sizes for the fdarray are considered, and the smallest that accommodates the requested fd count is chosen: pagesize / 4 pagesize / 2 pagesize <- memory allocator switch point pagesize * 2 pagesize * 4 ...etc... Unlike the current implementation, this allocation scheme does not require a loop to compute the optimal fdarray size, and can be done in efficient straightline code. Furthermore, since the fdarray overflows the pagesize boundary long before any of the fdsets do, it makes sense to optimize run-time by allocating both fdsets in a single swoop. Even together, they will still be, by far, smaller than the fdarray. The fdtable->open_fds is now used as the anchor for the fdset memory allocation. Signed-off-by: Vadim Lobanov <vlobanov@speakeasy.net> Cc: Christoph Hellwig <hch@lst.de> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Dipankar Sarma <dipankar@in.ibm.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-12-10 11:21:22 +01:00
static void copy_fdtable(struct fdtable *nfdt, struct fdtable *ofdt)
{
[PATCH] fdtable: Implement new pagesize-based fdtable allocator This patch provides an improved fdtable allocation scheme, useful for expanding fdtable file descriptor entries. The main focus is on the fdarray, as its memory usage grows 128 times faster than that of an fdset. The allocation algorithm sizes the fdarray in such a way that its memory usage increases in easy page-sized chunks. The overall algorithm expands the allowed size in powers of two, in order to amortize the cost of invoking vmalloc() for larger allocation sizes. Namely, the following sizes for the fdarray are considered, and the smallest that accommodates the requested fd count is chosen: pagesize / 4 pagesize / 2 pagesize <- memory allocator switch point pagesize * 2 pagesize * 4 ...etc... Unlike the current implementation, this allocation scheme does not require a loop to compute the optimal fdarray size, and can be done in efficient straightline code. Furthermore, since the fdarray overflows the pagesize boundary long before any of the fdsets do, it makes sense to optimize run-time by allocating both fdsets in a single swoop. Even together, they will still be, by far, smaller than the fdarray. The fdtable->open_fds is now used as the anchor for the fdset memory allocation. Signed-off-by: Vadim Lobanov <vlobanov@speakeasy.net> Cc: Christoph Hellwig <hch@lst.de> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Dipankar Sarma <dipankar@in.ibm.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-12-10 11:21:22 +01:00
unsigned int cpy, set;
[PATCH] fdtable: Implement new pagesize-based fdtable allocator This patch provides an improved fdtable allocation scheme, useful for expanding fdtable file descriptor entries. The main focus is on the fdarray, as its memory usage grows 128 times faster than that of an fdset. The allocation algorithm sizes the fdarray in such a way that its memory usage increases in easy page-sized chunks. The overall algorithm expands the allowed size in powers of two, in order to amortize the cost of invoking vmalloc() for larger allocation sizes. Namely, the following sizes for the fdarray are considered, and the smallest that accommodates the requested fd count is chosen: pagesize / 4 pagesize / 2 pagesize <- memory allocator switch point pagesize * 2 pagesize * 4 ...etc... Unlike the current implementation, this allocation scheme does not require a loop to compute the optimal fdarray size, and can be done in efficient straightline code. Furthermore, since the fdarray overflows the pagesize boundary long before any of the fdsets do, it makes sense to optimize run-time by allocating both fdsets in a single swoop. Even together, they will still be, by far, smaller than the fdarray. The fdtable->open_fds is now used as the anchor for the fdset memory allocation. Signed-off-by: Vadim Lobanov <vlobanov@speakeasy.net> Cc: Christoph Hellwig <hch@lst.de> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Dipankar Sarma <dipankar@in.ibm.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-12-10 11:21:22 +01:00
BUG_ON(nfdt->max_fds < ofdt->max_fds);
cpy = ofdt->max_fds * sizeof(struct file *);
set = (nfdt->max_fds - ofdt->max_fds) * sizeof(struct file *);
memcpy(nfdt->fd, ofdt->fd, cpy);
memset((char *)(nfdt->fd) + cpy, 0, set);
cpy = ofdt->max_fds / BITS_PER_BYTE;
set = (nfdt->max_fds - ofdt->max_fds) / BITS_PER_BYTE;
memcpy(nfdt->open_fds, ofdt->open_fds, cpy);
memset((char *)(nfdt->open_fds) + cpy, 0, set);
memcpy(nfdt->close_on_exec, ofdt->close_on_exec, cpy);
memset((char *)(nfdt->close_on_exec) + cpy, 0, set);
}
[PATCH] fdtable: Implement new pagesize-based fdtable allocator This patch provides an improved fdtable allocation scheme, useful for expanding fdtable file descriptor entries. The main focus is on the fdarray, as its memory usage grows 128 times faster than that of an fdset. The allocation algorithm sizes the fdarray in such a way that its memory usage increases in easy page-sized chunks. The overall algorithm expands the allowed size in powers of two, in order to amortize the cost of invoking vmalloc() for larger allocation sizes. Namely, the following sizes for the fdarray are considered, and the smallest that accommodates the requested fd count is chosen: pagesize / 4 pagesize / 2 pagesize <- memory allocator switch point pagesize * 2 pagesize * 4 ...etc... Unlike the current implementation, this allocation scheme does not require a loop to compute the optimal fdarray size, and can be done in efficient straightline code. Furthermore, since the fdarray overflows the pagesize boundary long before any of the fdsets do, it makes sense to optimize run-time by allocating both fdsets in a single swoop. Even together, they will still be, by far, smaller than the fdarray. The fdtable->open_fds is now used as the anchor for the fdset memory allocation. Signed-off-by: Vadim Lobanov <vlobanov@speakeasy.net> Cc: Christoph Hellwig <hch@lst.de> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Dipankar Sarma <dipankar@in.ibm.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-12-10 11:21:22 +01:00
static struct fdtable * alloc_fdtable(unsigned int nr)
{
[PATCH] fdtable: Implement new pagesize-based fdtable allocator This patch provides an improved fdtable allocation scheme, useful for expanding fdtable file descriptor entries. The main focus is on the fdarray, as its memory usage grows 128 times faster than that of an fdset. The allocation algorithm sizes the fdarray in such a way that its memory usage increases in easy page-sized chunks. The overall algorithm expands the allowed size in powers of two, in order to amortize the cost of invoking vmalloc() for larger allocation sizes. Namely, the following sizes for the fdarray are considered, and the smallest that accommodates the requested fd count is chosen: pagesize / 4 pagesize / 2 pagesize <- memory allocator switch point pagesize * 2 pagesize * 4 ...etc... Unlike the current implementation, this allocation scheme does not require a loop to compute the optimal fdarray size, and can be done in efficient straightline code. Furthermore, since the fdarray overflows the pagesize boundary long before any of the fdsets do, it makes sense to optimize run-time by allocating both fdsets in a single swoop. Even together, they will still be, by far, smaller than the fdarray. The fdtable->open_fds is now used as the anchor for the fdset memory allocation. Signed-off-by: Vadim Lobanov <vlobanov@speakeasy.net> Cc: Christoph Hellwig <hch@lst.de> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Dipankar Sarma <dipankar@in.ibm.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-12-10 11:21:22 +01:00
struct fdtable *fdt;
void *data;
/*
[PATCH] fdtable: Implement new pagesize-based fdtable allocator This patch provides an improved fdtable allocation scheme, useful for expanding fdtable file descriptor entries. The main focus is on the fdarray, as its memory usage grows 128 times faster than that of an fdset. The allocation algorithm sizes the fdarray in such a way that its memory usage increases in easy page-sized chunks. The overall algorithm expands the allowed size in powers of two, in order to amortize the cost of invoking vmalloc() for larger allocation sizes. Namely, the following sizes for the fdarray are considered, and the smallest that accommodates the requested fd count is chosen: pagesize / 4 pagesize / 2 pagesize <- memory allocator switch point pagesize * 2 pagesize * 4 ...etc... Unlike the current implementation, this allocation scheme does not require a loop to compute the optimal fdarray size, and can be done in efficient straightline code. Furthermore, since the fdarray overflows the pagesize boundary long before any of the fdsets do, it makes sense to optimize run-time by allocating both fdsets in a single swoop. Even together, they will still be, by far, smaller than the fdarray. The fdtable->open_fds is now used as the anchor for the fdset memory allocation. Signed-off-by: Vadim Lobanov <vlobanov@speakeasy.net> Cc: Christoph Hellwig <hch@lst.de> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Dipankar Sarma <dipankar@in.ibm.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-12-10 11:21:22 +01:00
* Figure out how many fds we actually want to support in this fdtable.
* Allocation steps are keyed to the size of the fdarray, since it
* grows far faster than any of the other dynamic data. We try to fit
* the fdarray into comfortable page-tuned chunks: starting at 1024B
* and growing in powers of two from there on.
*/
[PATCH] fdtable: Implement new pagesize-based fdtable allocator This patch provides an improved fdtable allocation scheme, useful for expanding fdtable file descriptor entries. The main focus is on the fdarray, as its memory usage grows 128 times faster than that of an fdset. The allocation algorithm sizes the fdarray in such a way that its memory usage increases in easy page-sized chunks. The overall algorithm expands the allowed size in powers of two, in order to amortize the cost of invoking vmalloc() for larger allocation sizes. Namely, the following sizes for the fdarray are considered, and the smallest that accommodates the requested fd count is chosen: pagesize / 4 pagesize / 2 pagesize <- memory allocator switch point pagesize * 2 pagesize * 4 ...etc... Unlike the current implementation, this allocation scheme does not require a loop to compute the optimal fdarray size, and can be done in efficient straightline code. Furthermore, since the fdarray overflows the pagesize boundary long before any of the fdsets do, it makes sense to optimize run-time by allocating both fdsets in a single swoop. Even together, they will still be, by far, smaller than the fdarray. The fdtable->open_fds is now used as the anchor for the fdset memory allocation. Signed-off-by: Vadim Lobanov <vlobanov@speakeasy.net> Cc: Christoph Hellwig <hch@lst.de> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Dipankar Sarma <dipankar@in.ibm.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-12-10 11:21:22 +01:00
nr /= (1024 / sizeof(struct file *));
nr = roundup_pow_of_two(nr + 1);
nr *= (1024 / sizeof(struct file *));
/*
* Note that this can drive nr *below* what we had passed if sysctl_nr_open
* had been set lower between the check in expand_files() and here. Deal
* with that in caller, it's cheaper that way.
*
* We make sure that nr remains a multiple of BITS_PER_LONG - otherwise
* bitmaps handling below becomes unpleasant, to put it mildly...
*/
if (unlikely(nr > sysctl_nr_open))
nr = ((sysctl_nr_open - 1) | (BITS_PER_LONG - 1)) + 1;
[PATCH] fdtable: Implement new pagesize-based fdtable allocator This patch provides an improved fdtable allocation scheme, useful for expanding fdtable file descriptor entries. The main focus is on the fdarray, as its memory usage grows 128 times faster than that of an fdset. The allocation algorithm sizes the fdarray in such a way that its memory usage increases in easy page-sized chunks. The overall algorithm expands the allowed size in powers of two, in order to amortize the cost of invoking vmalloc() for larger allocation sizes. Namely, the following sizes for the fdarray are considered, and the smallest that accommodates the requested fd count is chosen: pagesize / 4 pagesize / 2 pagesize <- memory allocator switch point pagesize * 2 pagesize * 4 ...etc... Unlike the current implementation, this allocation scheme does not require a loop to compute the optimal fdarray size, and can be done in efficient straightline code. Furthermore, since the fdarray overflows the pagesize boundary long before any of the fdsets do, it makes sense to optimize run-time by allocating both fdsets in a single swoop. Even together, they will still be, by far, smaller than the fdarray. The fdtable->open_fds is now used as the anchor for the fdset memory allocation. Signed-off-by: Vadim Lobanov <vlobanov@speakeasy.net> Cc: Christoph Hellwig <hch@lst.de> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Dipankar Sarma <dipankar@in.ibm.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-12-10 11:21:22 +01:00
fdt = kmalloc(sizeof(struct fdtable), GFP_KERNEL);
if (!fdt)
goto out;
[PATCH] fdtable: Implement new pagesize-based fdtable allocator This patch provides an improved fdtable allocation scheme, useful for expanding fdtable file descriptor entries. The main focus is on the fdarray, as its memory usage grows 128 times faster than that of an fdset. The allocation algorithm sizes the fdarray in such a way that its memory usage increases in easy page-sized chunks. The overall algorithm expands the allowed size in powers of two, in order to amortize the cost of invoking vmalloc() for larger allocation sizes. Namely, the following sizes for the fdarray are considered, and the smallest that accommodates the requested fd count is chosen: pagesize / 4 pagesize / 2 pagesize <- memory allocator switch point pagesize * 2 pagesize * 4 ...etc... Unlike the current implementation, this allocation scheme does not require a loop to compute the optimal fdarray size, and can be done in efficient straightline code. Furthermore, since the fdarray overflows the pagesize boundary long before any of the fdsets do, it makes sense to optimize run-time by allocating both fdsets in a single swoop. Even together, they will still be, by far, smaller than the fdarray. The fdtable->open_fds is now used as the anchor for the fdset memory allocation. Signed-off-by: Vadim Lobanov <vlobanov@speakeasy.net> Cc: Christoph Hellwig <hch@lst.de> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Dipankar Sarma <dipankar@in.ibm.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-12-10 11:21:22 +01:00
fdt->max_fds = nr;
data = alloc_fdmem(nr * sizeof(struct file *));
if (!data)
goto out_fdt;
fdt->fd = data;
data = alloc_fdmem(max_t(size_t,
[PATCH] fdtable: Implement new pagesize-based fdtable allocator This patch provides an improved fdtable allocation scheme, useful for expanding fdtable file descriptor entries. The main focus is on the fdarray, as its memory usage grows 128 times faster than that of an fdset. The allocation algorithm sizes the fdarray in such a way that its memory usage increases in easy page-sized chunks. The overall algorithm expands the allowed size in powers of two, in order to amortize the cost of invoking vmalloc() for larger allocation sizes. Namely, the following sizes for the fdarray are considered, and the smallest that accommodates the requested fd count is chosen: pagesize / 4 pagesize / 2 pagesize <- memory allocator switch point pagesize * 2 pagesize * 4 ...etc... Unlike the current implementation, this allocation scheme does not require a loop to compute the optimal fdarray size, and can be done in efficient straightline code. Furthermore, since the fdarray overflows the pagesize boundary long before any of the fdsets do, it makes sense to optimize run-time by allocating both fdsets in a single swoop. Even together, they will still be, by far, smaller than the fdarray. The fdtable->open_fds is now used as the anchor for the fdset memory allocation. Signed-off-by: Vadim Lobanov <vlobanov@speakeasy.net> Cc: Christoph Hellwig <hch@lst.de> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Dipankar Sarma <dipankar@in.ibm.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-12-10 11:21:22 +01:00
2 * nr / BITS_PER_BYTE, L1_CACHE_BYTES));
if (!data)
goto out_arr;
fdt->open_fds = data;
[PATCH] fdtable: Implement new pagesize-based fdtable allocator This patch provides an improved fdtable allocation scheme, useful for expanding fdtable file descriptor entries. The main focus is on the fdarray, as its memory usage grows 128 times faster than that of an fdset. The allocation algorithm sizes the fdarray in such a way that its memory usage increases in easy page-sized chunks. The overall algorithm expands the allowed size in powers of two, in order to amortize the cost of invoking vmalloc() for larger allocation sizes. Namely, the following sizes for the fdarray are considered, and the smallest that accommodates the requested fd count is chosen: pagesize / 4 pagesize / 2 pagesize <- memory allocator switch point pagesize * 2 pagesize * 4 ...etc... Unlike the current implementation, this allocation scheme does not require a loop to compute the optimal fdarray size, and can be done in efficient straightline code. Furthermore, since the fdarray overflows the pagesize boundary long before any of the fdsets do, it makes sense to optimize run-time by allocating both fdsets in a single swoop. Even together, they will still be, by far, smaller than the fdarray. The fdtable->open_fds is now used as the anchor for the fdset memory allocation. Signed-off-by: Vadim Lobanov <vlobanov@speakeasy.net> Cc: Christoph Hellwig <hch@lst.de> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Dipankar Sarma <dipankar@in.ibm.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-12-10 11:21:22 +01:00
data += nr / BITS_PER_BYTE;
fdt->close_on_exec = data;
[PATCH] fdtable: Implement new pagesize-based fdtable allocator This patch provides an improved fdtable allocation scheme, useful for expanding fdtable file descriptor entries. The main focus is on the fdarray, as its memory usage grows 128 times faster than that of an fdset. The allocation algorithm sizes the fdarray in such a way that its memory usage increases in easy page-sized chunks. The overall algorithm expands the allowed size in powers of two, in order to amortize the cost of invoking vmalloc() for larger allocation sizes. Namely, the following sizes for the fdarray are considered, and the smallest that accommodates the requested fd count is chosen: pagesize / 4 pagesize / 2 pagesize <- memory allocator switch point pagesize * 2 pagesize * 4 ...etc... Unlike the current implementation, this allocation scheme does not require a loop to compute the optimal fdarray size, and can be done in efficient straightline code. Furthermore, since the fdarray overflows the pagesize boundary long before any of the fdsets do, it makes sense to optimize run-time by allocating both fdsets in a single swoop. Even together, they will still be, by far, smaller than the fdarray. The fdtable->open_fds is now used as the anchor for the fdset memory allocation. Signed-off-by: Vadim Lobanov <vlobanov@speakeasy.net> Cc: Christoph Hellwig <hch@lst.de> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Dipankar Sarma <dipankar@in.ibm.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-12-10 11:21:22 +01:00
return fdt;
[PATCH] fdtable: Implement new pagesize-based fdtable allocator This patch provides an improved fdtable allocation scheme, useful for expanding fdtable file descriptor entries. The main focus is on the fdarray, as its memory usage grows 128 times faster than that of an fdset. The allocation algorithm sizes the fdarray in such a way that its memory usage increases in easy page-sized chunks. The overall algorithm expands the allowed size in powers of two, in order to amortize the cost of invoking vmalloc() for larger allocation sizes. Namely, the following sizes for the fdarray are considered, and the smallest that accommodates the requested fd count is chosen: pagesize / 4 pagesize / 2 pagesize <- memory allocator switch point pagesize * 2 pagesize * 4 ...etc... Unlike the current implementation, this allocation scheme does not require a loop to compute the optimal fdarray size, and can be done in efficient straightline code. Furthermore, since the fdarray overflows the pagesize boundary long before any of the fdsets do, it makes sense to optimize run-time by allocating both fdsets in a single swoop. Even together, they will still be, by far, smaller than the fdarray. The fdtable->open_fds is now used as the anchor for the fdset memory allocation. Signed-off-by: Vadim Lobanov <vlobanov@speakeasy.net> Cc: Christoph Hellwig <hch@lst.de> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Dipankar Sarma <dipankar@in.ibm.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-12-10 11:21:22 +01:00
out_arr:
free_fdmem(fdt->fd);
[PATCH] fdtable: Implement new pagesize-based fdtable allocator This patch provides an improved fdtable allocation scheme, useful for expanding fdtable file descriptor entries. The main focus is on the fdarray, as its memory usage grows 128 times faster than that of an fdset. The allocation algorithm sizes the fdarray in such a way that its memory usage increases in easy page-sized chunks. The overall algorithm expands the allowed size in powers of two, in order to amortize the cost of invoking vmalloc() for larger allocation sizes. Namely, the following sizes for the fdarray are considered, and the smallest that accommodates the requested fd count is chosen: pagesize / 4 pagesize / 2 pagesize <- memory allocator switch point pagesize * 2 pagesize * 4 ...etc... Unlike the current implementation, this allocation scheme does not require a loop to compute the optimal fdarray size, and can be done in efficient straightline code. Furthermore, since the fdarray overflows the pagesize boundary long before any of the fdsets do, it makes sense to optimize run-time by allocating both fdsets in a single swoop. Even together, they will still be, by far, smaller than the fdarray. The fdtable->open_fds is now used as the anchor for the fdset memory allocation. Signed-off-by: Vadim Lobanov <vlobanov@speakeasy.net> Cc: Christoph Hellwig <hch@lst.de> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Dipankar Sarma <dipankar@in.ibm.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-12-10 11:21:22 +01:00
out_fdt:
kfree(fdt);
[PATCH] fdtable: Implement new pagesize-based fdtable allocator This patch provides an improved fdtable allocation scheme, useful for expanding fdtable file descriptor entries. The main focus is on the fdarray, as its memory usage grows 128 times faster than that of an fdset. The allocation algorithm sizes the fdarray in such a way that its memory usage increases in easy page-sized chunks. The overall algorithm expands the allowed size in powers of two, in order to amortize the cost of invoking vmalloc() for larger allocation sizes. Namely, the following sizes for the fdarray are considered, and the smallest that accommodates the requested fd count is chosen: pagesize / 4 pagesize / 2 pagesize <- memory allocator switch point pagesize * 2 pagesize * 4 ...etc... Unlike the current implementation, this allocation scheme does not require a loop to compute the optimal fdarray size, and can be done in efficient straightline code. Furthermore, since the fdarray overflows the pagesize boundary long before any of the fdsets do, it makes sense to optimize run-time by allocating both fdsets in a single swoop. Even together, they will still be, by far, smaller than the fdarray. The fdtable->open_fds is now used as the anchor for the fdset memory allocation. Signed-off-by: Vadim Lobanov <vlobanov@speakeasy.net> Cc: Christoph Hellwig <hch@lst.de> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Dipankar Sarma <dipankar@in.ibm.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-12-10 11:21:22 +01:00
out:
return NULL;
}
/*
* Expand the file descriptor table.
* This function will allocate a new fdtable and both fd array and fdset, of
* the given size.
* Return <0 error code on error; 1 on successful completion.
* The files->file_lock should be held on entry, and will be held on exit.
*/
static int expand_fdtable(struct files_struct *files, int nr)
__releases(files->file_lock)
__acquires(files->file_lock)
{
struct fdtable *new_fdt, *cur_fdt;
spin_unlock(&files->file_lock);
new_fdt = alloc_fdtable(nr);
spin_lock(&files->file_lock);
if (!new_fdt)
return -ENOMEM;
/*
* extremely unlikely race - sysctl_nr_open decreased between the check in
* caller and alloc_fdtable(). Cheaper to catch it here...
*/
if (unlikely(new_fdt->max_fds <= nr)) {
__free_fdtable(new_fdt);
return -EMFILE;
}
/*
* Check again since another task may have expanded the fd table while
* we dropped the lock
*/
cur_fdt = files_fdtable(files);
if (nr >= cur_fdt->max_fds) {
/* Continue as planned */
copy_fdtable(new_fdt, cur_fdt);
rcu_assign_pointer(files->fdt, new_fdt);
if (cur_fdt != &files->fdtab)
call_rcu(&cur_fdt->rcu, free_fdtable_rcu);
} else {
/* Somebody else expanded, so undo our attempt */
__free_fdtable(new_fdt);
}
return 1;
}
/*
* Expand files.
* This function will expand the file structures, if the requested size exceeds
* the current capacity and there is room for expansion.
* Return <0 error code on error; 0 when nothing done; 1 when files were
* expanded and execution may have blocked.
* The files->file_lock should be held on entry, and will be held on exit.
*/
static int expand_files(struct files_struct *files, int nr)
{
struct fdtable *fdt;
fdt = files_fdtable(files);
/* Do we need to expand? */
if (nr < fdt->max_fds)
return 0;
/* Can we expand? */
if (nr >= sysctl_nr_open)
return -EMFILE;
/* All good, so we try */
return expand_fdtable(files, nr);
}
static inline void __set_close_on_exec(int fd, struct fdtable *fdt)
{
__set_bit(fd, fdt->close_on_exec);
}
static inline void __clear_close_on_exec(int fd, struct fdtable *fdt)
{
__clear_bit(fd, fdt->close_on_exec);
}
static inline void __set_open_fd(int fd, struct fdtable *fdt)
{
__set_bit(fd, fdt->open_fds);
}
static inline void __clear_open_fd(int fd, struct fdtable *fdt)
{
__clear_bit(fd, fdt->open_fds);
}
static int count_open_files(struct fdtable *fdt)
{
int size = fdt->max_fds;
int i;
/* Find the last open fd */
for (i = size / BITS_PER_LONG; i > 0; ) {
if (fdt->open_fds[--i])
break;
}
i = (i + 1) * BITS_PER_LONG;
return i;
}
/*
* Allocate a new files structure and copy contents from the
* passed in files structure.
* errorp will be valid only when the returned files_struct is NULL.
*/
struct files_struct *dup_fd(struct files_struct *oldf, int *errorp)
{
struct files_struct *newf;
struct file **old_fds, **new_fds;
int open_files, size, i;
struct fdtable *old_fdt, *new_fdt;
*errorp = -ENOMEM;
newf = kmem_cache_alloc(files_cachep, GFP_KERNEL);
if (!newf)
goto out;
atomic_set(&newf->count, 1);
spin_lock_init(&newf->file_lock);
newf->next_fd = 0;
new_fdt = &newf->fdtab;
new_fdt->max_fds = NR_OPEN_DEFAULT;
new_fdt->close_on_exec = newf->close_on_exec_init;
new_fdt->open_fds = newf->open_fds_init;
new_fdt->fd = &newf->fd_array[0];
spin_lock(&oldf->file_lock);
old_fdt = files_fdtable(oldf);
open_files = count_open_files(old_fdt);
/*
* Check whether we need to allocate a larger fd array and fd set.
*/
while (unlikely(open_files > new_fdt->max_fds)) {
spin_unlock(&oldf->file_lock);
if (new_fdt != &newf->fdtab)
__free_fdtable(new_fdt);
new_fdt = alloc_fdtable(open_files - 1);
if (!new_fdt) {
*errorp = -ENOMEM;
goto out_release;
}
/* beyond sysctl_nr_open; nothing to do */
if (unlikely(new_fdt->max_fds < open_files)) {
__free_fdtable(new_fdt);
*errorp = -EMFILE;
goto out_release;
}
/*
* Reacquire the oldf lock and a pointer to its fd table
* who knows it may have a new bigger fd table. We need
* the latest pointer.
*/
spin_lock(&oldf->file_lock);
old_fdt = files_fdtable(oldf);
open_files = count_open_files(old_fdt);
}
old_fds = old_fdt->fd;
new_fds = new_fdt->fd;
memcpy(new_fdt->open_fds, old_fdt->open_fds, open_files / 8);
memcpy(new_fdt->close_on_exec, old_fdt->close_on_exec, open_files / 8);
for (i = open_files; i != 0; i--) {
struct file *f = *old_fds++;
if (f) {
get_file(f);
} else {
/*
* The fd may be claimed in the fd bitmap but not yet
* instantiated in the files array if a sibling thread
* is partway through open(). So make sure that this
* fd is available to the new process.
*/
__clear_open_fd(open_files - i, new_fdt);
}
rcu_assign_pointer(*new_fds++, f);
}
spin_unlock(&oldf->file_lock);
/* compute the remainder to be cleared */
size = (new_fdt->max_fds - open_files) * sizeof(struct file *);
/* This is long word aligned thus could use a optimized version */
memset(new_fds, 0, size);
if (new_fdt->max_fds > open_files) {
int left = (new_fdt->max_fds - open_files) / 8;
int start = open_files / BITS_PER_LONG;
memset(&new_fdt->open_fds[start], 0, left);
memset(&new_fdt->close_on_exec[start], 0, left);
}
rcu_assign_pointer(newf->fdt, new_fdt);
return newf;
out_release:
kmem_cache_free(files_cachep, newf);
out:
return NULL;
}
static struct fdtable *close_files(struct files_struct * files)
{
/*
* It is safe to dereference the fd table without RCU or
* ->file_lock because this is the last reference to the
* files structure.
*/
struct fdtable *fdt = rcu_dereference_raw(files->fdt);
int i, j = 0;
for (;;) {
unsigned long set;
i = j * BITS_PER_LONG;
if (i >= fdt->max_fds)
break;
set = fdt->open_fds[j++];
while (set) {
if (set & 1) {
struct file * file = xchg(&fdt->fd[i], NULL);
if (file) {
filp_close(file, files);
cond_resched();
}
}
i++;
set >>= 1;
}
}
return fdt;
}
struct files_struct *get_files_struct(struct task_struct *task)
{
struct files_struct *files;
task_lock(task);
files = task->files;
if (files)
atomic_inc(&files->count);
task_unlock(task);
return files;
}
void put_files_struct(struct files_struct *files)
{
if (atomic_dec_and_test(&files->count)) {
struct fdtable *fdt = close_files(files);
/* free the arrays if they are not embedded */
if (fdt != &files->fdtab)
__free_fdtable(fdt);
kmem_cache_free(files_cachep, files);
}
}
void reset_files_struct(struct files_struct *files)
{
struct task_struct *tsk = current;
struct files_struct *old;
old = tsk->files;
task_lock(tsk);
tsk->files = files;
task_unlock(tsk);
put_files_struct(old);
}
void exit_files(struct task_struct *tsk)
{
struct files_struct * files = tsk->files;
if (files) {
task_lock(tsk);
tsk->files = NULL;
task_unlock(tsk);
put_files_struct(files);
}
}
void __init files_defer_init(void)
{
sysctl_nr_open_max = min((size_t)INT_MAX, ~(size_t)0/sizeof(void *)) &
-BITS_PER_LONG;
}
struct files_struct init_files = {
.count = ATOMIC_INIT(1),
.fdt = &init_files.fdtab,
.fdtab = {
.max_fds = NR_OPEN_DEFAULT,
.fd = &init_files.fd_array[0],
.close_on_exec = init_files.close_on_exec_init,
.open_fds = init_files.open_fds_init,
},
.file_lock = __SPIN_LOCK_UNLOCKED(init_files.file_lock),
};
/*
* allocate a file descriptor, mark it busy.
*/
int __alloc_fd(struct files_struct *files,
unsigned start, unsigned end, unsigned flags)
{
unsigned int fd;
int error;
struct fdtable *fdt;
spin_lock(&files->file_lock);
repeat:
fdt = files_fdtable(files);
fd = start;
if (fd < files->next_fd)
fd = files->next_fd;
if (fd < fdt->max_fds)
fd = find_next_zero_bit(fdt->open_fds, fdt->max_fds, fd);
/*
* N.B. For clone tasks sharing a files structure, this test
* will limit the total number of files that can be opened.
*/
error = -EMFILE;
if (fd >= end)
goto out;
error = expand_files(files, fd);
if (error < 0)
goto out;
/*
* If we needed to expand the fs array we
* might have blocked - try again.
*/
if (error)
goto repeat;
if (start <= files->next_fd)
files->next_fd = fd + 1;
__set_open_fd(fd, fdt);
if (flags & O_CLOEXEC)
__set_close_on_exec(fd, fdt);
else
__clear_close_on_exec(fd, fdt);
error = fd;
#if 1
/* Sanity check */
if (rcu_dereference_raw(fdt->fd[fd]) != NULL) {
printk(KERN_WARNING "alloc_fd: slot %d not NULL!\n", fd);
rcu_assign_pointer(fdt->fd[fd], NULL);
}
#endif
out:
spin_unlock(&files->file_lock);
return error;
}
static int alloc_fd(unsigned start, unsigned flags)
{
return __alloc_fd(current->files, start, rlimit(RLIMIT_NOFILE), flags);
}
int get_unused_fd_flags(unsigned flags)
{
return __alloc_fd(current->files, 0, rlimit(RLIMIT_NOFILE), flags);
}
EXPORT_SYMBOL(get_unused_fd_flags);
static void __put_unused_fd(struct files_struct *files, unsigned int fd)
{
struct fdtable *fdt = files_fdtable(files);
__clear_open_fd(fd, fdt);
if (fd < files->next_fd)
files->next_fd = fd;
}
void put_unused_fd(unsigned int fd)
{
struct files_struct *files = current->files;
spin_lock(&files->file_lock);
__put_unused_fd(files, fd);
spin_unlock(&files->file_lock);
}
EXPORT_SYMBOL(put_unused_fd);
/*
* Install a file pointer in the fd array.
*
* The VFS is full of places where we drop the files lock between
* setting the open_fds bitmap and installing the file in the file
* array. At any such point, we are vulnerable to a dup2() race
* installing a file in the array before us. We need to detect this and
* fput() the struct file we are about to overwrite in this case.
*
* It should never happen - if we allow dup2() do it, _really_ bad things
* will follow.
*
* NOTE: __fd_install() variant is really, really low-level; don't
* use it unless you are forced to by truly lousy API shoved down
* your throat. 'files' *MUST* be either current->files or obtained
* by get_files_struct(current) done by whoever had given it to you,
* or really bad things will happen. Normally you want to use
* fd_install() instead.
*/
void __fd_install(struct files_struct *files, unsigned int fd,
struct file *file)
{
struct fdtable *fdt;
spin_lock(&files->file_lock);
fdt = files_fdtable(files);
BUG_ON(fdt->fd[fd] != NULL);
rcu_assign_pointer(fdt->fd[fd], file);
spin_unlock(&files->file_lock);
}
void fd_install(unsigned int fd, struct file *file)
{
__fd_install(current->files, fd, file);
}
EXPORT_SYMBOL(fd_install);
/*
* The same warnings as for __alloc_fd()/__fd_install() apply here...
*/
int __close_fd(struct files_struct *files, unsigned fd)
{
struct file *file;
struct fdtable *fdt;
spin_lock(&files->file_lock);
fdt = files_fdtable(files);
if (fd >= fdt->max_fds)
goto out_unlock;
file = fdt->fd[fd];
if (!file)
goto out_unlock;
rcu_assign_pointer(fdt->fd[fd], NULL);
__clear_close_on_exec(fd, fdt);
__put_unused_fd(files, fd);
spin_unlock(&files->file_lock);
return filp_close(file, files);
out_unlock:
spin_unlock(&files->file_lock);
return -EBADF;
}
void do_close_on_exec(struct files_struct *files)
{
unsigned i;
struct fdtable *fdt;
/* exec unshares first */
spin_lock(&files->file_lock);
for (i = 0; ; i++) {
unsigned long set;
unsigned fd = i * BITS_PER_LONG;
fdt = files_fdtable(files);
if (fd >= fdt->max_fds)
break;
set = fdt->close_on_exec[i];
if (!set)
continue;
fdt->close_on_exec[i] = 0;
for ( ; set ; fd++, set >>= 1) {
struct file *file;
if (!(set & 1))
continue;
file = fdt->fd[fd];
if (!file)
continue;
rcu_assign_pointer(fdt->fd[fd], NULL);
__put_unused_fd(files, fd);
spin_unlock(&files->file_lock);
filp_close(file, files);
cond_resched();
spin_lock(&files->file_lock);
}
}
spin_unlock(&files->file_lock);
}
static struct file *__fget(unsigned int fd, fmode_t mask)
{
struct files_struct *files = current->files;
struct file *file;
rcu_read_lock();
file = fcheck_files(files, fd);
if (file) {
/* File object ref couldn't be taken */
if ((file->f_mode & mask) ||
!atomic_long_inc_not_zero(&file->f_count))
file = NULL;
}
rcu_read_unlock();
return file;
}
struct file *fget(unsigned int fd)
{
return __fget(fd, FMODE_PATH);
}
EXPORT_SYMBOL(fget);
struct file *fget_raw(unsigned int fd)
{
return __fget(fd, 0);
}
EXPORT_SYMBOL(fget_raw);
/*
* Lightweight file lookup - no refcnt increment if fd table isn't shared.
*
* You can use this instead of fget if you satisfy all of the following
* conditions:
* 1) You must call fput_light before exiting the syscall and returning control
* to userspace (i.e. you cannot remember the returned struct file * after
* returning to userspace).
* 2) You must not call filp_close on the returned struct file * in between
* calls to fget_light and fput_light.
* 3) You must not clone the current task in between the calls to fget_light
* and fput_light.
*
* The fput_needed flag returned by fget_light should be passed to the
* corresponding fput_light.
*/
struct file *__fget_light(unsigned int fd, fmode_t mask, int *fput_needed)
{
struct files_struct *files = current->files;
struct file *file;
*fput_needed = 0;
if (atomic_read(&files->count) == 1) {
file = __fcheck_files(files, fd);
if (file && (file->f_mode & mask))
file = NULL;
} else {
file = __fget(fd, mask);
if (file)
*fput_needed = 1;
}
return file;
}
struct file *fget_light(unsigned int fd, int *fput_needed)
{
return __fget_light(fd, FMODE_PATH, fput_needed);
}
EXPORT_SYMBOL(fget_light);
struct file *fget_raw_light(unsigned int fd, int *fput_needed)
{
return __fget_light(fd, 0, fput_needed);
}
void set_close_on_exec(unsigned int fd, int flag)
{
struct files_struct *files = current->files;
struct fdtable *fdt;
spin_lock(&files->file_lock);
fdt = files_fdtable(files);
if (flag)
__set_close_on_exec(fd, fdt);
else
__clear_close_on_exec(fd, fdt);
spin_unlock(&files->file_lock);
}
bool get_close_on_exec(unsigned int fd)
{
struct files_struct *files = current->files;
struct fdtable *fdt;
bool res;
rcu_read_lock();
fdt = files_fdtable(files);
res = close_on_exec(fd, fdt);
rcu_read_unlock();
return res;
}
static int do_dup2(struct files_struct *files,
struct file *file, unsigned fd, unsigned flags)
{
struct file *tofree;
struct fdtable *fdt;
/*
* We need to detect attempts to do dup2() over allocated but still
* not finished descriptor. NB: OpenBSD avoids that at the price of
* extra work in their equivalent of fget() - they insert struct
* file immediately after grabbing descriptor, mark it larval if
* more work (e.g. actual opening) is needed and make sure that
* fget() treats larval files as absent. Potentially interesting,
* but while extra work in fget() is trivial, locking implications
* and amount of surgery on open()-related paths in VFS are not.
* FreeBSD fails with -EBADF in the same situation, NetBSD "solution"
* deadlocks in rather amusing ways, AFAICS. All of that is out of
* scope of POSIX or SUS, since neither considers shared descriptor
* tables and this condition does not arise without those.
*/
fdt = files_fdtable(files);
tofree = fdt->fd[fd];
if (!tofree && fd_is_open(fd, fdt))
goto Ebusy;
get_file(file);
rcu_assign_pointer(fdt->fd[fd], file);
__set_open_fd(fd, fdt);
if (flags & O_CLOEXEC)
__set_close_on_exec(fd, fdt);
else
__clear_close_on_exec(fd, fdt);
spin_unlock(&files->file_lock);
if (tofree)
filp_close(tofree, files);
return fd;
Ebusy:
spin_unlock(&files->file_lock);
return -EBUSY;
}
int replace_fd(unsigned fd, struct file *file, unsigned flags)
{
int err;
struct files_struct *files = current->files;
if (!file)
return __close_fd(files, fd);
if (fd >= rlimit(RLIMIT_NOFILE))
return -EBADF;
spin_lock(&files->file_lock);
err = expand_files(files, fd);
if (unlikely(err < 0))
goto out_unlock;
return do_dup2(files, file, fd, flags);
out_unlock:
spin_unlock(&files->file_lock);
return err;
}
SYSCALL_DEFINE3(dup3, unsigned int, oldfd, unsigned int, newfd, int, flags)
{
int err = -EBADF;
struct file *file;
struct files_struct *files = current->files;
if ((flags & ~O_CLOEXEC) != 0)
return -EINVAL;
if (unlikely(oldfd == newfd))
return -EINVAL;
if (newfd >= rlimit(RLIMIT_NOFILE))
return -EBADF;
spin_lock(&files->file_lock);
err = expand_files(files, newfd);
file = fcheck(oldfd);
if (unlikely(!file))
goto Ebadf;
if (unlikely(err < 0)) {
if (err == -EMFILE)
goto Ebadf;
goto out_unlock;
}
return do_dup2(files, file, newfd, flags);
Ebadf:
err = -EBADF;
out_unlock:
spin_unlock(&files->file_lock);
return err;
}
SYSCALL_DEFINE2(dup2, unsigned int, oldfd, unsigned int, newfd)
{
if (unlikely(newfd == oldfd)) { /* corner case */
struct files_struct *files = current->files;
int retval = oldfd;
rcu_read_lock();
if (!fcheck_files(files, oldfd))
retval = -EBADF;
rcu_read_unlock();
return retval;
}
return sys_dup3(oldfd, newfd, 0);
}
SYSCALL_DEFINE1(dup, unsigned int, fildes)
{
int ret = -EBADF;
struct file *file = fget_raw(fildes);
if (file) {
ret = get_unused_fd();
if (ret >= 0)
fd_install(ret, file);
else
fput(file);
}
return ret;
}
int f_dupfd(unsigned int from, struct file *file, unsigned flags)
{
int err;
if (from >= rlimit(RLIMIT_NOFILE))
return -EINVAL;
err = alloc_fd(from, flags);
if (err >= 0) {
get_file(file);
fd_install(err, file);
}
return err;
}
int iterate_fd(struct files_struct *files, unsigned n,
int (*f)(const void *, struct file *, unsigned),
const void *p)
{
struct fdtable *fdt;
int res = 0;
if (!files)
return 0;
spin_lock(&files->file_lock);
for (fdt = files_fdtable(files); n < fdt->max_fds; n++) {
struct file *file;
file = rcu_dereference_check_fdtable(files, fdt->fd[n]);
if (!file)
continue;
res = f(p, file, n);
if (res)
break;
}
spin_unlock(&files->file_lock);
return res;
}
EXPORT_SYMBOL(iterate_fd);