Revision 472e5b056f000a778abb41f1e443de58eb259783 authored by Linus Torvalds on 02 October 2020, 02:14:36 UTC, committed by Linus Torvalds on 02 October 2020, 02:14:36 UTC
The pipe splice code still used the old model of waiting for pipe IO by using a non-specific "pipe_wait()" that waited for any pipe event to happen, which depended on all pipe IO being entirely serialized by the pipe lock. So by checking the state you were waiting for, and then adding yourself to the wait queue before dropping the lock, you were guaranteed to see all the wakeups. Strictly speaking, the actual wakeups were not done under the lock, but the pipe_wait() model still worked, because since the waiter held the lock when checking whether it should sleep, it would always see the current state, and the wakeup was always done after updating the state. However, commit 0ddad21d3e99 ("pipe: use exclusive waits when reading or writing") split the single wait-queue into two, and in the process also made the "wait for event" code wait for _two_ wait queues, and that then showed a race with the wakers that were not serialized by the pipe lock. It's only splice that used that "pipe_wait()" model, so the problem wasn't obvious, but Josef Bacik reports: "I hit a hang with fstest btrfs/187, which does a btrfs send into /dev/null. This works by creating a pipe, the write side is given to the kernel to write into, and the read side is handed to a thread that splices into a file, in this case /dev/null. The box that was hung had the write side stuck here [pipe_write] and the read side stuck here [splice_from_pipe_next -> pipe_wait]. [ more details about pipe_wait() scenario ] The problem is we're doing the prepare_to_wait, which sets our state each time, however we can be woken up either with reads or writes. In the case above we race with the WRITER waking us up, and re-set our state to INTERRUPTIBLE, and thus never break out of schedule" Josef had a patch that avoided the issue in pipe_wait() by just making it set the state only once, but the deeper problem is that pipe_wait() depends on a level of synchonization by the pipe mutex that it really shouldn't. And the whole "wait for any pipe state change" model really isn't very good to begin with. So rather than trying to work around things in pipe_wait(), remove that legacy model of "wait for arbitrary pipe event" entirely, and actually create functions that wait for the pipe actually being readable or writable, and can do so without depending on the pipe lock serializing everything. Fixes: 0ddad21d3e99 ("pipe: use exclusive waits when reading or writing") Link: https://lore.kernel.org/linux-fsdevel/bfa88b5ad6f069b2b679316b9e495a970130416c.1601567868.git.josef@toxicpanda.com/ Reported-by: Josef Bacik <josef@toxicpanda.com> Reviewed-and-tested-by: Josef Bacik <josef@toxicpanda.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
1 parent 44b6e23
lzo-rle.c
// SPDX-License-Identifier: GPL-2.0-only
/*
* Cryptographic API.
*/
#include <linux/init.h>
#include <linux/module.h>
#include <linux/crypto.h>
#include <linux/vmalloc.h>
#include <linux/mm.h>
#include <linux/lzo.h>
#include <crypto/internal/scompress.h>
struct lzorle_ctx {
void *lzorle_comp_mem;
};
static void *lzorle_alloc_ctx(struct crypto_scomp *tfm)
{
void *ctx;
ctx = kvmalloc(LZO1X_MEM_COMPRESS, GFP_KERNEL);
if (!ctx)
return ERR_PTR(-ENOMEM);
return ctx;
}
static int lzorle_init(struct crypto_tfm *tfm)
{
struct lzorle_ctx *ctx = crypto_tfm_ctx(tfm);
ctx->lzorle_comp_mem = lzorle_alloc_ctx(NULL);
if (IS_ERR(ctx->lzorle_comp_mem))
return -ENOMEM;
return 0;
}
static void lzorle_free_ctx(struct crypto_scomp *tfm, void *ctx)
{
kvfree(ctx);
}
static void lzorle_exit(struct crypto_tfm *tfm)
{
struct lzorle_ctx *ctx = crypto_tfm_ctx(tfm);
lzorle_free_ctx(NULL, ctx->lzorle_comp_mem);
}
static int __lzorle_compress(const u8 *src, unsigned int slen,
u8 *dst, unsigned int *dlen, void *ctx)
{
size_t tmp_len = *dlen; /* size_t(ulong) <-> uint on 64 bit */
int err;
err = lzorle1x_1_compress(src, slen, dst, &tmp_len, ctx);
if (err != LZO_E_OK)
return -EINVAL;
*dlen = tmp_len;
return 0;
}
static int lzorle_compress(struct crypto_tfm *tfm, const u8 *src,
unsigned int slen, u8 *dst, unsigned int *dlen)
{
struct lzorle_ctx *ctx = crypto_tfm_ctx(tfm);
return __lzorle_compress(src, slen, dst, dlen, ctx->lzorle_comp_mem);
}
static int lzorle_scompress(struct crypto_scomp *tfm, const u8 *src,
unsigned int slen, u8 *dst, unsigned int *dlen,
void *ctx)
{
return __lzorle_compress(src, slen, dst, dlen, ctx);
}
static int __lzorle_decompress(const u8 *src, unsigned int slen,
u8 *dst, unsigned int *dlen)
{
int err;
size_t tmp_len = *dlen; /* size_t(ulong) <-> uint on 64 bit */
err = lzo1x_decompress_safe(src, slen, dst, &tmp_len);
if (err != LZO_E_OK)
return -EINVAL;
*dlen = tmp_len;
return 0;
}
static int lzorle_decompress(struct crypto_tfm *tfm, const u8 *src,
unsigned int slen, u8 *dst, unsigned int *dlen)
{
return __lzorle_decompress(src, slen, dst, dlen);
}
static int lzorle_sdecompress(struct crypto_scomp *tfm, const u8 *src,
unsigned int slen, u8 *dst, unsigned int *dlen,
void *ctx)
{
return __lzorle_decompress(src, slen, dst, dlen);
}
static struct crypto_alg alg = {
.cra_name = "lzo-rle",
.cra_driver_name = "lzo-rle-generic",
.cra_flags = CRYPTO_ALG_TYPE_COMPRESS,
.cra_ctxsize = sizeof(struct lzorle_ctx),
.cra_module = THIS_MODULE,
.cra_init = lzorle_init,
.cra_exit = lzorle_exit,
.cra_u = { .compress = {
.coa_compress = lzorle_compress,
.coa_decompress = lzorle_decompress } }
};
static struct scomp_alg scomp = {
.alloc_ctx = lzorle_alloc_ctx,
.free_ctx = lzorle_free_ctx,
.compress = lzorle_scompress,
.decompress = lzorle_sdecompress,
.base = {
.cra_name = "lzo-rle",
.cra_driver_name = "lzo-rle-scomp",
.cra_module = THIS_MODULE,
}
};
static int __init lzorle_mod_init(void)
{
int ret;
ret = crypto_register_alg(&alg);
if (ret)
return ret;
ret = crypto_register_scomp(&scomp);
if (ret) {
crypto_unregister_alg(&alg);
return ret;
}
return ret;
}
static void __exit lzorle_mod_fini(void)
{
crypto_unregister_alg(&alg);
crypto_unregister_scomp(&scomp);
}
subsys_initcall(lzorle_mod_init);
module_exit(lzorle_mod_fini);
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("LZO-RLE Compression Algorithm");
MODULE_ALIAS_CRYPTO("lzo-rle");
![swh spinner](/static/img/swh-spinner.gif)
Computing file changes ...