Revision d99fbd9aab624fc030934e21655389ab1765dc94 authored by Thomas Hellström on 28 June 2024, 15:38:48 UTC, committed by Thomas Hellström on 04 July 2024, 07:22:04 UTC
Bos can be put with multiple unrelated dma-resv locks held. But
imported bos attempt to grab the bo dma-resv during dma-buf detach
that typically happens during cleanup. That leads to lockde splats
similar to the below and a potential ABBA deadlock.
Fix this by always taking the delayed workqueue cleanup path for
imported bos.
Requesting stable fixes from when the Xe driver was introduced,
since its usage of drm_exec and wide vm dma_resvs appear to be
the first reliable trigger of this.
[22982.116427] ============================================
[22982.116428] WARNING: possible recursive locking detected
[22982.116429] 6.10.0-rc2+ #10 Tainted: G U W
[22982.116430] --------------------------------------------
[22982.116430] glxgears:sh0/5785 is trying to acquire lock:
[22982.116431] ffff8c2bafa539a8 (reservation_ww_class_mutex){+.+.}-{3:3}, at: dma_buf_detach+0x3b/0xf0
[22982.116438]
but task is already holding lock:
[22982.116438] ffff8c2d9aba6da8 (reservation_ww_class_mutex){+.+.}-{3:3}, at: drm_exec_lock_obj+0x49/0x2b0 [drm_exec]
[22982.116442]
other info that might help us debug this:
[22982.116442] Possible unsafe locking scenario:
[22982.116443] CPU0
[22982.116444] ----
[22982.116444] lock(reservation_ww_class_mutex);
[22982.116445] lock(reservation_ww_class_mutex);
[22982.116447]
*** DEADLOCK ***
[22982.116447] May be due to missing lock nesting notation
[22982.116448] 5 locks held by glxgears:sh0/5785:
[22982.116449] #0: ffff8c2d9aba58c8 (&xef->vm.lock){+.+.}-{3:3}, at: xe_file_close+0xde/0x1c0 [xe]
[22982.116507] #1: ffff8c2e28cc8480 (&vm->lock){++++}-{3:3}, at: xe_vm_close_and_put+0x161/0x9b0 [xe]
[22982.116578] #2: ffff8c2e31982970 (&val->lock){.+.+}-{3:3}, at: xe_validation_ctx_init+0x6d/0x70 [xe]
[22982.116647] #3: ffffacdc469478a8 (reservation_ww_class_acquire){+.+.}-{0:0}, at: xe_vma_destroy_unlocked+0x7f/0xe0 [xe]
[22982.116716] #4: ffff8c2d9aba6da8 (reservation_ww_class_mutex){+.+.}-{3:3}, at: drm_exec_lock_obj+0x49/0x2b0 [drm_exec]
[22982.116719]
stack backtrace:
[22982.116720] CPU: 8 PID: 5785 Comm: glxgears:sh0 Tainted: G U W 6.10.0-rc2+ #10
[22982.116721] Hardware name: ASUS System Product Name/PRIME B560M-A AC, BIOS 2001 02/01/2023
[22982.116723] Call Trace:
[22982.116724] <TASK>
[22982.116725] dump_stack_lvl+0x77/0xb0
[22982.116727] __lock_acquire+0x1232/0x2160
[22982.116730] lock_acquire+0xcb/0x2d0
[22982.116732] ? dma_buf_detach+0x3b/0xf0
[22982.116734] ? __lock_acquire+0x417/0x2160
[22982.116736] __ww_mutex_lock.constprop.0+0xd0/0x13b0
[22982.116738] ? dma_buf_detach+0x3b/0xf0
[22982.116741] ? dma_buf_detach+0x3b/0xf0
[22982.116743] ? ww_mutex_lock+0x2b/0x90
[22982.116745] ww_mutex_lock+0x2b/0x90
[22982.116747] dma_buf_detach+0x3b/0xf0
[22982.116749] drm_prime_gem_destroy+0x2f/0x40 [drm]
[22982.116775] xe_ttm_bo_destroy+0x32/0x220 [xe]
[22982.116818] ? __mutex_unlock_slowpath+0x3a/0x290
[22982.116821] drm_exec_unlock_all+0xa1/0xd0 [drm_exec]
[22982.116823] drm_exec_fini+0x12/0xb0 [drm_exec]
[22982.116824] xe_validation_ctx_fini+0x15/0x40 [xe]
[22982.116892] xe_vma_destroy_unlocked+0xb1/0xe0 [xe]
[22982.116959] xe_vm_close_and_put+0x41a/0x9b0 [xe]
[22982.117025] ? xa_find+0xe3/0x1e0
[22982.117028] xe_file_close+0x10a/0x1c0 [xe]
[22982.117074] drm_file_free+0x22a/0x280 [drm]
[22982.117099] drm_release_noglobal+0x22/0x70 [drm]
[22982.117119] __fput+0xf1/0x2d0
[22982.117122] task_work_run+0x59/0x90
[22982.117125] do_exit+0x330/0xb40
[22982.117127] do_group_exit+0x36/0xa0
[22982.117129] get_signal+0xbd2/0xbe0
[22982.117131] arch_do_signal_or_restart+0x3e/0x240
[22982.117134] syscall_exit_to_user_mode+0x1e7/0x290
[22982.117137] do_syscall_64+0xa1/0x180
[22982.117139] ? lock_acquire+0xcb/0x2d0
[22982.117140] ? __set_task_comm+0x28/0x1e0
[22982.117141] ? find_held_lock+0x2b/0x80
[22982.117144] ? __set_task_comm+0xe1/0x1e0
[22982.117145] ? lock_release+0xca/0x290
[22982.117147] ? __do_sys_prctl+0x245/0xab0
[22982.117149] ? lockdep_hardirqs_on_prepare+0xde/0x190
[22982.117150] ? syscall_exit_to_user_mode+0xb0/0x290
[22982.117152] ? do_syscall_64+0xa1/0x180
[22982.117154] ? __lock_acquire+0x417/0x2160
[22982.117155] ? reacquire_held_locks+0xd1/0x1f0
[22982.117156] ? do_user_addr_fault+0x30c/0x790
[22982.117158] ? lock_acquire+0xcb/0x2d0
[22982.117160] ? find_held_lock+0x2b/0x80
[22982.117162] ? do_user_addr_fault+0x357/0x790
[22982.117163] ? lock_release+0xca/0x290
[22982.117164] ? do_user_addr_fault+0x361/0x790
[22982.117166] ? trace_hardirqs_off+0x4b/0xc0
[22982.117168] ? clear_bhb_loop+0x45/0xa0
[22982.117170] ? clear_bhb_loop+0x45/0xa0
[22982.117172] ? clear_bhb_loop+0x45/0xa0
[22982.117174] entry_SYSCALL_64_after_hwframe+0x76/0x7e
[22982.117176] RIP: 0033:0x7f943d267169
[22982.117192] Code: Unable to access opcode bytes at 0x7f943d26713f.
[22982.117193] RSP: 002b:00007f9430bffc80 EFLAGS: 00000246 ORIG_RAX: 00000000000000ca
[22982.117195] RAX: fffffffffffffe00 RBX: 0000000000000000 RCX: 00007f943d267169
[22982.117196] RDX: 0000000000000000 RSI: 0000000000000189 RDI: 00005622f89579d0
[22982.117197] RBP: 00007f9430bffcb0 R08: 0000000000000000 R09: 00000000ffffffff
[22982.117198] R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000
[22982.117199] R13: 0000000000000000 R14: 0000000000000000 R15: 00005622f89579d0
[22982.117202] </TASK>
Fixes: dd08ebf6c352 ("drm/xe: Introduce a new DRM driver for Intel GPUs")
Cc: Christian König <christian.koenig@amd.com>
Cc: Daniel Vetter <daniel@ffwll.ch>
Cc: dri-devel@lists.freedesktop.org
Cc: intel-xe@lists.freedesktop.org
Cc: <stable@vger.kernel.org> # v6.8+
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Reviewed-by: Christian König <christian.koenig@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240628153848.4989-1-thomas.hellstrom@linux.intel.com
1 parent 740b8da
842.c
// SPDX-License-Identifier: GPL-2.0-or-later
/*
* Cryptographic API for the 842 software compression algorithm.
*
* Copyright (C) IBM Corporation, 2011-2015
*
* Original Authors: Robert Jennings <rcj@linux.vnet.ibm.com>
* Seth Jennings <sjenning@linux.vnet.ibm.com>
*
* Rewrite: Dan Streetman <ddstreet@ieee.org>
*
* This is the software implementation of compression and decompression using
* the 842 format. This uses the software 842 library at lib/842/ which is
* only a reference implementation, and is very, very slow as compared to other
* software compressors. You probably do not want to use this software
* compression. If you have access to the PowerPC 842 compression hardware, you
* want to use the 842 hardware compression interface, which is at:
* drivers/crypto/nx/nx-842-crypto.c
*/
#include <linux/init.h>
#include <linux/module.h>
#include <linux/crypto.h>
#include <linux/sw842.h>
#include <crypto/internal/scompress.h>
struct crypto842_ctx {
void *wmem; /* working memory for compress */
};
static void *crypto842_alloc_ctx(struct crypto_scomp *tfm)
{
void *ctx;
ctx = kmalloc(SW842_MEM_COMPRESS, GFP_KERNEL);
if (!ctx)
return ERR_PTR(-ENOMEM);
return ctx;
}
static int crypto842_init(struct crypto_tfm *tfm)
{
struct crypto842_ctx *ctx = crypto_tfm_ctx(tfm);
ctx->wmem = crypto842_alloc_ctx(NULL);
if (IS_ERR(ctx->wmem))
return -ENOMEM;
return 0;
}
static void crypto842_free_ctx(struct crypto_scomp *tfm, void *ctx)
{
kfree(ctx);
}
static void crypto842_exit(struct crypto_tfm *tfm)
{
struct crypto842_ctx *ctx = crypto_tfm_ctx(tfm);
crypto842_free_ctx(NULL, ctx->wmem);
}
static int crypto842_compress(struct crypto_tfm *tfm,
const u8 *src, unsigned int slen,
u8 *dst, unsigned int *dlen)
{
struct crypto842_ctx *ctx = crypto_tfm_ctx(tfm);
return sw842_compress(src, slen, dst, dlen, ctx->wmem);
}
static int crypto842_scompress(struct crypto_scomp *tfm,
const u8 *src, unsigned int slen,
u8 *dst, unsigned int *dlen, void *ctx)
{
return sw842_compress(src, slen, dst, dlen, ctx);
}
static int crypto842_decompress(struct crypto_tfm *tfm,
const u8 *src, unsigned int slen,
u8 *dst, unsigned int *dlen)
{
return sw842_decompress(src, slen, dst, dlen);
}
static int crypto842_sdecompress(struct crypto_scomp *tfm,
const u8 *src, unsigned int slen,
u8 *dst, unsigned int *dlen, void *ctx)
{
return sw842_decompress(src, slen, dst, dlen);
}
static struct crypto_alg alg = {
.cra_name = "842",
.cra_driver_name = "842-generic",
.cra_priority = 100,
.cra_flags = CRYPTO_ALG_TYPE_COMPRESS,
.cra_ctxsize = sizeof(struct crypto842_ctx),
.cra_module = THIS_MODULE,
.cra_init = crypto842_init,
.cra_exit = crypto842_exit,
.cra_u = { .compress = {
.coa_compress = crypto842_compress,
.coa_decompress = crypto842_decompress } }
};
static struct scomp_alg scomp = {
.alloc_ctx = crypto842_alloc_ctx,
.free_ctx = crypto842_free_ctx,
.compress = crypto842_scompress,
.decompress = crypto842_sdecompress,
.base = {
.cra_name = "842",
.cra_driver_name = "842-scomp",
.cra_priority = 100,
.cra_module = THIS_MODULE,
}
};
static int __init crypto842_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;
}
subsys_initcall(crypto842_mod_init);
static void __exit crypto842_mod_exit(void)
{
crypto_unregister_alg(&alg);
crypto_unregister_scomp(&scomp);
}
module_exit(crypto842_mod_exit);
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("842 Software Compression Algorithm");
MODULE_ALIAS_CRYPTO("842");
MODULE_ALIAS_CRYPTO("842-generic");
MODULE_AUTHOR("Dan Streetman <ddstreet@ieee.org>");
Computing file changes ...
