mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-12-28 16:56:26 +00:00
fs: add file_ref
As atomic_inc_not_zero() is implemented with a try_cmpxchg() loop it has
O(N^2) behaviour under contention with N concurrent operations and it is
in a hot path in __fget_files_rcu().
The rcuref infrastructures remedies this problem by using an
unconditional increment relying on safe- and dead zones to make this
work and requiring rcu protection for the data structure in question.
This not just scales better it also introduces overflow protection.
However, in contrast to generic rcuref, files require a memory barrier
and thus cannot rely on *_relaxed() atomic operations and also require
to be built on atomic_long_t as having massive amounts of reference
isn't unheard of even if it is just an attack.
As suggested by Linus, add a file specific variant instead of making
this a generic library.
Files are SLAB_TYPESAFE_BY_RCU and thus don't have "regular" rcu
protection. In short, freeing of files isn't delayed until a grace
period has elapsed. Instead, they are freed immediately and thus can be
reused (multiple times) within the same grace period.
So when picking a file from the file descriptor table via its file
descriptor number it is thus possible to see an elevated reference count
on file->f_count even though the file has already been recycled possibly
multiple times by another task.
To guard against this the vfs will pick the file from the file
descriptor table twice. Once before the refcount increment and once
after to compare the pointers (grossly simplified). If they match then
the file is still valid. If not the caller needs to fput() it.
The unconditional increment makes the following race possible as
illustrated by rcuref:
> Deconstruction race
> ===================
>
> The release operation must be protected by prohibiting a grace period in
> order to prevent a possible use after free:
>
> T1 T2
> put() get()
> // ref->refcnt = ONEREF
> if (!atomic_add_negative(-1, &ref->refcnt))
> return false; <- Not taken
>
> // ref->refcnt == NOREF
> --> preemption
> // Elevates ref->refcnt to ONEREF
> if (!atomic_add_negative(1, &ref->refcnt))
> return true; <- taken
>
> if (put(&p->ref)) { <-- Succeeds
> remove_pointer(p);
> kfree_rcu(p, rcu);
> }
>
> RCU grace period ends, object is freed
>
> atomic_cmpxchg(&ref->refcnt, NOREF, DEAD); <- UAF
>
> [...] it prevents the grace period which keeps the object alive until
> all put() operations complete.
Having files by SLAB_TYPESAFE_BY_RCU shouldn't cause any problems for
this deconstruction race. Afaict, the only interesting case would be
someone freeing the file and someone immediately recycling it within the
same grace period and reinitializing file->f_count to ONEREF while a
concurrent fput() is doing atomic_cmpxchg(&ref->refcnt, NOREF, DEAD) as
in the race above.
But this is safe from SLAB_TYPESAFE_BY_RCU's perspective and it should
be safe from rcuref's perspective.
T1 T2 T3
fput() fget()
// f_count->refcnt = ONEREF
if (!atomic_add_negative(-1, &f_count->refcnt))
return false; <- Not taken
// f_count->refcnt == NOREF
--> preemption
// Elevates f_count->refcnt to ONEREF
if (!atomic_add_negative(1, &f_count->refcnt))
return true; <- taken
if (put(&f_count)) { <-- Succeeds
remove_pointer(p);
/*
* Cache is SLAB_TYPESAFE_BY_RCU
* so this is freed without a grace period.
*/
kmem_cache_free(p);
}
kmem_cache_alloc()
init_file() {
// Sets f_count->refcnt to ONEREF
rcuref_long_init(&f->f_count, 1);
}
Object has been reused within the same grace period
via kmem_cache_alloc()'s SLAB_TYPESAFE_BY_RCU.
/*
* With SLAB_TYPESAFE_BY_RCU this would be a safe UAF access and
* it would work correctly because the atomic_cmpxchg()
* will fail because the refcount has been reset to ONEREF by T3.
*/
atomic_cmpxchg(&ref->refcnt, NOREF, DEAD); <- UAF
However, there are other cases to consider:
(1) Benign race due to multiple atomic_long_read()
CPU1 CPU2
file_ref_put()
// last reference
// => count goes negative/FILE_REF_NOREF
atomic_long_add_negative_release(-1, &ref->refcnt)
-> __file_ref_put()
file_ref_get()
// goes back from negative/FILE_REF_NOREF to 0
// and file_ref_get() succeeds
atomic_long_add_negative(1, &ref->refcnt)
// This is immediately followed by file_ref_put()
// managing to set FILE_REF_DEAD
file_ref_put()
// __file_ref_put() continues and sees
// cnt > FILE_REF_RELEASED // and splats with
// "imbalanced put on file reference count"
cnt = atomic_long_read(&ref->refcnt);
The race however is benign and the problem is the
atomic_long_read(). Instead of performing a separate read this uses
atomic_long_dec_return() and pass the value to __file_ref_put().
Thanks to Linus for pointing out that braino.
(2) SLAB_TYPESAFE_BY_RCU may cause recycled files to be marked dead
When a file is recycled the following race exists:
CPU1 CPU2
// @file is already dead and thus
// cnt >= FILE_REF_RELEASED.
file_ref_get(file)
atomic_long_add_negative(1, &ref->refcnt)
// We thus call into __file_ref_get()
-> __file_ref_get()
// which sees cnt >= FILE_REF_RELEASED
cnt = atomic_long_read(&ref->refcnt);
// In the meantime @file gets freed
kmem_cache_free()
// and is immediately recycled
file = kmem_cache_zalloc()
// and the reference count is reinitialized
// and the file alive again in someone
// else's file descriptor table
file_ref_init(&ref->refcnt, 1);
// the __file_ref_get() slowpath now continues
// and as it saw earlier that cnt >= FILE_REF_RELEASED
// it wants to ensure that we're staying in the middle
// of the deadzone and unconditionally sets
// FILE_REF_DEAD.
// This marks @file dead for CPU2...
atomic_long_set(&ref->refcnt, FILE_REF_DEAD);
// Caller issues a close() system call to close @file
close(fd)
file = file_close_fd_locked()
filp_flush()
// The caller sees that cnt >= FILE_REF_RELEASED
// and warns the first time...
CHECK_DATA_CORRUPTION(file_count(file) == 0)
// and then splats a second time because
// __file_ref_put() sees cnt >= FILE_REF_RELEASED
file_ref_put(&ref->refcnt);
-> __file_ref_put()
My initial inclination was to replace the unconditional
atomic_long_set() with an atomic_long_try_cmpxchg() but Linus
pointed out that:
> I think we should just make file_ref_get() do a simple
>
> return !atomic_long_add_negative(1, &ref->refcnt));
>
> and nothing else. Yes, multiple CPU's can race, and you can increment
> more than once, but the gap - even on 32-bit - between DEAD and
> becoming close to REF_RELEASED is so big that we simply don't care.
> That's the point of having a gap.
I've been testing this with will-it-scale using fstat() on a machine
that Jens gave me access (thank you very much!):
processor : 511
vendor_id : AuthenticAMD
cpu family : 25
model : 160
model name : AMD EPYC 9754 128-Core Processor
and I consistently get a 3-5% improvement on 256+ threads.
Reported-by: kernel test robot <oliver.sang@intel.com>
Closes: https://lore.kernel.org/oe-lkp/202410151043.5d224a27-oliver.sang@intel.com
Closes: https://lore.kernel.org/all/202410151611.f4cd71f2-oliver.sang@intel.com
Link: https://lore.kernel.org/r/20241007-brauner-file-rcuref-v2-2-387e24dc9163@kernel.org
Signed-off-by: Christian Brauner <brauner@kernel.org>
This commit is contained in:
Christian Brauner
parent
8b1bc2590a
commit
08ef26ea9a
63
fs/file.c
63
fs/file.c
@ -20,10 +20,73 @@
|
||||
#include <linux/spinlock.h>
|
||||
#include <linux/rcupdate.h>
|
||||
#include <linux/close_range.h>
|
||||
#include <linux/file_ref.h>
|
||||
#include <net/sock.h>
|
||||
|
||||
#include "internal.h"
|
||||
|
||||
/**
|
||||
* __file_ref_put - Slowpath of file_ref_put()
|
||||
* @ref: Pointer to the reference count
|
||||
* @cnt: Current reference count
|
||||
*
|
||||
* Invoked when the reference count is outside of the valid zone.
|
||||
*
|
||||
* Return:
|
||||
* True if this was the last reference with no future references
|
||||
* possible. This signals the caller that it can safely schedule the
|
||||
* object, which is protected by the reference counter, for
|
||||
* deconstruction.
|
||||
*
|
||||
* False if there are still active references or the put() raced
|
||||
* with a concurrent get()/put() pair. Caller is not allowed to
|
||||
* deconstruct the protected object.
|
||||
*/
|
||||
bool __file_ref_put(file_ref_t *ref, unsigned long cnt)
|
||||
{
|
||||
/* Did this drop the last reference? */
|
||||
if (likely(cnt == FILE_REF_NOREF)) {
|
||||
/*
|
||||
* Carefully try to set the reference count to FILE_REF_DEAD.
|
||||
*
|
||||
* This can fail if a concurrent get() operation has
|
||||
* elevated it again or the corresponding put() even marked
|
||||
* it dead already. Both are valid situations and do not
|
||||
* require a retry. If this fails the caller is not
|
||||
* allowed to deconstruct the object.
|
||||
*/
|
||||
if (!atomic_long_try_cmpxchg_release(&ref->refcnt, &cnt, FILE_REF_DEAD))
|
||||
return false;
|
||||
|
||||
/*
|
||||
* The caller can safely schedule the object for
|
||||
* deconstruction. Provide acquire ordering.
|
||||
*/
|
||||
smp_acquire__after_ctrl_dep();
|
||||
return true;
|
||||
}
|
||||
|
||||
/*
|
||||
* If the reference count was already in the dead zone, then this
|
||||
* put() operation is imbalanced. Warn, put the reference count back to
|
||||
* DEAD and tell the caller to not deconstruct the object.
|
||||
*/
|
||||
if (WARN_ONCE(cnt >= FILE_REF_RELEASED, "imbalanced put on file reference count")) {
|
||||
atomic_long_set(&ref->refcnt, FILE_REF_DEAD);
|
||||
return false;
|
||||
}
|
||||
|
||||
/*
|
||||
* This is a put() operation on a saturated refcount. Restore the
|
||||
* mean saturation value and tell the caller to not deconstruct the
|
||||
* object.
|
||||
*/
|
||||
if (cnt > FILE_REF_MAXREF)
|
||||
atomic_long_set(&ref->refcnt, FILE_REF_SATURATED);
|
||||
return false;
|
||||
}
|
||||
EXPORT_SYMBOL_GPL(__file_ref_put);
|
||||
|
||||
unsigned int sysctl_nr_open __read_mostly = 1024*1024;
|
||||
unsigned int sysctl_nr_open_min = BITS_PER_LONG;
|
||||
/* our min() is unusable in constant expressions ;-/ */
|
||||
|
||||
177
include/linux/file_ref.h
Normal file
177
include/linux/file_ref.h
Normal file
@ -0,0 +1,177 @@
|
||||
/* SPDX-License-Identifier: GPL-2.0-only */
|
||||
#ifndef _LINUX_FILE_REF_H
|
||||
#define _LINUX_FILE_REF_H
|
||||
|
||||
#include <linux/atomic.h>
|
||||
#include <linux/preempt.h>
|
||||
#include <linux/types.h>
|
||||
|
||||
/*
|
||||
* file_ref is a reference count implementation specifically for use by
|
||||
* files. It takes inspiration from rcuref but differs in key aspects
|
||||
* such as support for SLAB_TYPESAFE_BY_RCU type caches.
|
||||
*
|
||||
* FILE_REF_ONEREF FILE_REF_MAXREF
|
||||
* 0x0000000000000000UL 0x7FFFFFFFFFFFFFFFUL
|
||||
* <-------------------valid ------------------->
|
||||
*
|
||||
* FILE_REF_SATURATED
|
||||
* 0x8000000000000000UL 0xA000000000000000UL 0xBFFFFFFFFFFFFFFFUL
|
||||
* <-----------------------saturation zone---------------------->
|
||||
*
|
||||
* FILE_REF_RELEASED FILE_REF_DEAD
|
||||
* 0xC000000000000000UL 0xE000000000000000UL
|
||||
* <-------------------dead zone------------------->
|
||||
*
|
||||
* FILE_REF_NOREF
|
||||
* 0xFFFFFFFFFFFFFFFFUL
|
||||
*/
|
||||
|
||||
#ifdef CONFIG_64BIT
|
||||
#define FILE_REF_ONEREF 0x0000000000000000UL
|
||||
#define FILE_REF_MAXREF 0x7FFFFFFFFFFFFFFFUL
|
||||
#define FILE_REF_SATURATED 0xA000000000000000UL
|
||||
#define FILE_REF_RELEASED 0xC000000000000000UL
|
||||
#define FILE_REF_DEAD 0xE000000000000000UL
|
||||
#define FILE_REF_NOREF 0xFFFFFFFFFFFFFFFFUL
|
||||
#else
|
||||
#define FILE_REF_ONEREF 0x00000000U
|
||||
#define FILE_REF_MAXREF 0x7FFFFFFFU
|
||||
#define FILE_REF_SATURATED 0xA0000000U
|
||||
#define FILE_REF_RELEASED 0xC0000000U
|
||||
#define FILE_REF_DEAD 0xE0000000U
|
||||
#define FILE_REF_NOREF 0xFFFFFFFFU
|
||||
#endif
|
||||
|
||||
typedef struct {
|
||||
#ifdef CONFIG_64BIT
|
||||
atomic64_t refcnt;
|
||||
#else
|
||||
atomic_t refcnt;
|
||||
#endif
|
||||
} file_ref_t;
|
||||
|
||||
/**
|
||||
* file_ref_init - Initialize a file reference count
|
||||
* @ref: Pointer to the reference count
|
||||
* @cnt: The initial reference count typically '1'
|
||||
*/
|
||||
static inline void file_ref_init(file_ref_t *ref, unsigned long cnt)
|
||||
{
|
||||
atomic_long_set(&ref->refcnt, cnt - 1);
|
||||
}
|
||||
|
||||
bool __file_ref_put(file_ref_t *ref, unsigned long cnt);
|
||||
|
||||
/**
|
||||
* file_ref_get - Acquire one reference on a file
|
||||
* @ref: Pointer to the reference count
|
||||
*
|
||||
* Similar to atomic_inc_not_zero() but saturates at FILE_REF_MAXREF.
|
||||
*
|
||||
* Provides full memory ordering.
|
||||
*
|
||||
* Return: False if the attempt to acquire a reference failed. This happens
|
||||
* when the last reference has been put already. True if a reference
|
||||
* was successfully acquired
|
||||
*/
|
||||
static __always_inline __must_check bool file_ref_get(file_ref_t *ref)
|
||||
{
|
||||
/*
|
||||
* Unconditionally increase the reference count with full
|
||||
* ordering. The saturation and dead zones provide enough
|
||||
* tolerance for this.
|
||||
*
|
||||
* If this indicates negative the file in question the fail can
|
||||
* be freed and immediately reused due to SLAB_TYPSAFE_BY_RCU.
|
||||
* Hence, unconditionally altering the file reference count to
|
||||
* e.g., reset the file reference count back to the middle of
|
||||
* the deadzone risk end up marking someone else's file as dead
|
||||
* behind their back.
|
||||
*
|
||||
* It would be possible to do a careful:
|
||||
*
|
||||
* cnt = atomic_long_inc_return();
|
||||
* if (likely(cnt >= 0))
|
||||
* return true;
|
||||
*
|
||||
* and then something like:
|
||||
*
|
||||
* if (cnt >= FILE_REF_RELEASE)
|
||||
* atomic_long_try_cmpxchg(&ref->refcnt, &cnt, FILE_REF_DEAD),
|
||||
*
|
||||
* to set the value back to the middle of the deadzone. But it's
|
||||
* practically impossible to go from FILE_REF_DEAD to
|
||||
* FILE_REF_ONEREF. It would need 2305843009213693952/2^61
|
||||
* file_ref_get()s to resurrect such a dead file.
|
||||
*/
|
||||
return !atomic_long_add_negative(1, &ref->refcnt);
|
||||
}
|
||||
|
||||
/**
|
||||
* file_ref_inc - Acquire one reference on a file
|
||||
* @ref: Pointer to the reference count
|
||||
*
|
||||
* Acquire an additional reference on a file. Warns if the caller didn't
|
||||
* already hold a reference.
|
||||
*/
|
||||
static __always_inline void file_ref_inc(file_ref_t *ref)
|
||||
{
|
||||
long prior = atomic_long_fetch_inc_relaxed(&ref->refcnt);
|
||||
WARN_ONCE(prior < 0, "file_ref_inc() on a released file reference");
|
||||
}
|
||||
|
||||
/**
|
||||
* file_ref_put -- Release a file reference
|
||||
* @ref: Pointer to the reference count
|
||||
*
|
||||
* Provides release memory ordering, such that prior loads and stores
|
||||
* are done before, and provides an acquire ordering on success such
|
||||
* that free() must come after.
|
||||
*
|
||||
* Return: True if this was the last reference with no future references
|
||||
* possible. This signals the caller that it can safely release
|
||||
* the object which is protected by the reference counter.
|
||||
* False if there are still active references or the put() raced
|
||||
* with a concurrent get()/put() pair. Caller is not allowed to
|
||||
* release the protected object.
|
||||
*/
|
||||
static __always_inline __must_check bool file_ref_put(file_ref_t *ref)
|
||||
{
|
||||
long cnt;
|
||||
|
||||
/*
|
||||
* While files are SLAB_TYPESAFE_BY_RCU and thus file_ref_put()
|
||||
* calls don't risk UAFs when a file is recyclyed, it is still
|
||||
* vulnerable to UAFs caused by freeing the whole slab page once
|
||||
* it becomes unused. Prevent file_ref_put() from being
|
||||
* preempted protects against this.
|
||||
*/
|
||||
guard(preempt)();
|
||||
/*
|
||||
* Unconditionally decrease the reference count. The saturation
|
||||
* and dead zones provide enough tolerance for this. If this
|
||||
* fails then we need to handle the last reference drop and
|
||||
* cases inside the saturation and dead zones.
|
||||
*/
|
||||
cnt = atomic_long_dec_return(&ref->refcnt);
|
||||
if (cnt >= 0)
|
||||
return false;
|
||||
return __file_ref_put(ref, cnt);
|
||||
}
|
||||
|
||||
/**
|
||||
* file_ref_read - Read the number of file references
|
||||
* @ref: Pointer to the reference count
|
||||
*
|
||||
* Return: The number of held references (0 ... N)
|
||||
*/
|
||||
static inline unsigned long file_ref_read(file_ref_t *ref)
|
||||
{
|
||||
unsigned long c = atomic_long_read(&ref->refcnt);
|
||||
|
||||
/* Return 0 if within the DEAD zone. */
|
||||
return c >= FILE_REF_RELEASED ? 0 : c + 1;
|
||||
}
|
||||
|
||||
#endif
|
||||
Loading…
Reference in New Issue
Block a user