opnsense-src/sys/compat/linuxkpi/common/include/linux/slab.h
Vladimir Kondratyev ec25b6fa5f LinuxKPI: Reimplement irq_work queue on top of fast taskqueue
Summary:
Linux's irq_work queue was created for asynchronous execution of code from contexts where spin_lock's are not available like "hardware interrupt context". FreeBSD's fast taskqueues was created for the same purposes.

Drm-kmod 5.4 uses irq_work_queue() at least in one place to schedule execution of task/work from the critical section that triggers following INVARIANTS-induced panic:

```
panic: acquiring blockable sleep lock with spinlock or critical section held (sleep mutex) linuxkpi_short_wq @ /usr/src/sys/kern/subr_taskqueue.c:281
cpuid = 6
time = 1605048416
KDB: stack backtrace:
db_trace_self_wrapper() at db_trace_self_wrapper+0x2b/frame 0xfffffe006b538c90
vpanic() at vpanic+0x182/frame 0xfffffe006b538ce0
panic() at panic+0x43/frame 0xfffffe006b538d40
witness_checkorder() at witness_checkorder+0xf3e/frame 0xfffffe006b538f00
__mtx_lock_flags() at __mtx_lock_flags+0x94/frame 0xfffffe006b538f50
taskqueue_enqueue() at taskqueue_enqueue+0x42/frame 0xfffffe006b538f70
linux_queue_work_on() at linux_queue_work_on+0xe9/frame 0xfffffe006b538fb0
irq_work_queue() at irq_work_queue+0x21/frame 0xfffffe006b538fd0
semaphore_notify() at semaphore_notify+0xb2/frame 0xfffffe006b539020
__i915_sw_fence_notify() at __i915_sw_fence_notify+0x2e/frame 0xfffffe006b539050
__i915_sw_fence_complete() at __i915_sw_fence_complete+0x63/frame 0xfffffe006b539080
i915_sw_fence_complete() at i915_sw_fence_complete+0x8e/frame 0xfffffe006b5390c0
dma_i915_sw_fence_wake() at dma_i915_sw_fence_wake+0x4f/frame 0xfffffe006b539100
dma_fence_signal_locked() at dma_fence_signal_locked+0x105/frame 0xfffffe006b539180
dma_fence_signal() at dma_fence_signal+0x72/frame 0xfffffe006b5391c0
dma_fence_is_signaled() at dma_fence_is_signaled+0x80/frame 0xfffffe006b539200
dma_resv_add_shared_fence() at dma_resv_add_shared_fence+0xb3/frame 0xfffffe006b539270
i915_vma_move_to_active() at i915_vma_move_to_active+0x18a/frame 0xfffffe006b5392b0
eb_move_to_gpu() at eb_move_to_gpu+0x3ad/frame 0xfffffe006b539320
eb_submit() at eb_submit+0x15/frame 0xfffffe006b539350
i915_gem_do_execbuffer() at i915_gem_do_execbuffer+0x7d4/frame 0xfffffe006b539570
i915_gem_execbuffer2_ioctl() at i915_gem_execbuffer2_ioctl+0x1c1/frame 0xfffffe006b539600
drm_ioctl_kernel() at drm_ioctl_kernel+0xd9/frame 0xfffffe006b539670
drm_ioctl() at drm_ioctl+0x5cd/frame 0xfffffe006b539820
linux_file_ioctl() at linux_file_ioctl+0x323/frame 0xfffffe006b539880
kern_ioctl() at kern_ioctl+0x1f4/frame 0xfffffe006b5398f0
sys_ioctl() at sys_ioctl+0x12a/frame 0xfffffe006b5399c0
amd64_syscall() at amd64_syscall+0x121/frame 0xfffffe006b539af0
fast_syscall_common() at fast_syscall_common+0xf8/frame 0xfffffe006b539af0
--- syscall (54, FreeBSD ELF64, sys_ioctl), rip = 0x800a6f09a, rsp = 0x7fffffffe588, rbp = 0x7fffffffe640 ---
KDB: enter: panic
```
Here, the  dma_resv_add_shared_fence() performs a critical_enter() and following call of schedule_work() from semaphore_notify() triggers 'acquiring blockable sleep lock with spinlock or critical section held' panic.

Switching irq_work implementation to fast taskqueue fixes the panic for me.

Other report with the similar bug: https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=247166

Reviewed By: hselasky
Differential Revision: https://reviews.freebsd.org/D27171
2021-01-17 12:47:28 +01:00

209 lines
6.2 KiB
C

/*-
* Copyright (c) 2010 Isilon Systems, Inc.
* Copyright (c) 2010 iX Systems, Inc.
* Copyright (c) 2010 Panasas, Inc.
* Copyright (c) 2013-2017 Mellanox Technologies, Ltd.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
* 1. Redistributions of source code must retain the above copyright
* notice unmodified, this list of conditions, and the following
* disclaimer.
* 2. Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the distribution.
*
* THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS OR
* IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
* OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED.
* IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT,
* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT
* NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
* DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
* THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
* (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
* THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
*
* $FreeBSD$
*/
#ifndef _LINUX_SLAB_H_
#define _LINUX_SLAB_H_
#include <sys/param.h>
#include <sys/systm.h>
#include <sys/malloc.h>
#include <sys/limits.h>
#include <sys/proc.h>
#include <vm/uma.h>
#include <linux/types.h>
#include <linux/gfp.h>
#include <linux/llist.h>
MALLOC_DECLARE(M_KMALLOC);
#define kvmalloc(size, flags) kmalloc(size, flags)
#define kvzalloc(size, flags) kmalloc(size, (flags) | __GFP_ZERO)
#define kvcalloc(n, size, flags) kvmalloc_array(n, size, (flags) | __GFP_ZERO)
#define kzalloc(size, flags) kmalloc(size, (flags) | __GFP_ZERO)
#define kzalloc_node(size, flags, node) kmalloc(size, (flags) | __GFP_ZERO)
#define kfree_const(ptr) kfree(ptr)
#define vzalloc(size) __vmalloc(size, GFP_KERNEL | __GFP_NOWARN | __GFP_ZERO, 0)
#define vfree(arg) kfree(arg)
#define kvfree(arg) kfree(arg)
#define vmalloc_node(size, node) __vmalloc(size, GFP_KERNEL, 0)
#define vmalloc_user(size) __vmalloc(size, GFP_KERNEL | __GFP_ZERO, 0)
#define vmalloc(size) __vmalloc(size, GFP_KERNEL, 0)
#define __kmalloc(...) kmalloc(__VA_ARGS__)
#define kmalloc_node(chunk, flags, n) kmalloc(chunk, flags)
/*
* Prefix some functions with linux_ to avoid namespace conflict
* with the OpenSolaris code in the kernel.
*/
#define kmem_cache linux_kmem_cache
#define kmem_cache_create(...) linux_kmem_cache_create(__VA_ARGS__)
#define kmem_cache_alloc(...) linux_kmem_cache_alloc(__VA_ARGS__)
#define kmem_cache_free(...) linux_kmem_cache_free(__VA_ARGS__)
#define kmem_cache_destroy(...) linux_kmem_cache_destroy(__VA_ARGS__)
#define KMEM_CACHE(__struct, flags) \
linux_kmem_cache_create(#__struct, sizeof(struct __struct), \
__alignof(struct __struct), (flags), NULL)
typedef void linux_kmem_ctor_t (void *);
struct linux_kmem_cache {
uma_zone_t cache_zone;
linux_kmem_ctor_t *cache_ctor;
unsigned cache_flags;
unsigned cache_size;
};
#define SLAB_HWCACHE_ALIGN (1 << 0)
#define SLAB_TYPESAFE_BY_RCU (1 << 1)
#define SLAB_RECLAIM_ACCOUNT (1 << 2)
#define SLAB_DESTROY_BY_RCU \
SLAB_TYPESAFE_BY_RCU
#define ARCH_KMALLOC_MINALIGN \
__alignof(unsigned long long)
/*
* Critical section-friendly version of kfree().
* Requires knowledge of the allocation size at build time.
*/
#define kfree_async(ptr) do { \
_Static_assert(sizeof(*(ptr)) >= sizeof(struct llist_node), \
"Size of object to free is unknown or too small"); \
if (curthread->td_critnest != 0) \
linux_kfree_async(ptr); \
else \
kfree(ptr); \
} while (0)
static inline gfp_t
linux_check_m_flags(gfp_t flags)
{
const gfp_t m = M_NOWAIT | M_WAITOK;
/* make sure either M_NOWAIT or M_WAITOK is set */
if ((flags & m) == 0)
flags |= M_NOWAIT;
else if ((flags & m) == m)
flags &= ~M_WAITOK;
/* mask away LinuxKPI specific flags */
return (flags & GFP_NATIVE_MASK);
}
static inline void *
kmalloc(size_t size, gfp_t flags)
{
return (malloc(size, M_KMALLOC, linux_check_m_flags(flags)));
}
static inline void *
kcalloc(size_t n, size_t size, gfp_t flags)
{
flags |= __GFP_ZERO;
return (mallocarray(n, size, M_KMALLOC, linux_check_m_flags(flags)));
}
static inline void *
__vmalloc(size_t size, gfp_t flags, int other)
{
return (malloc(size, M_KMALLOC, linux_check_m_flags(flags)));
}
static inline void *
vmalloc_32(size_t size)
{
return (contigmalloc(size, M_KMALLOC, M_WAITOK, 0, UINT_MAX, 1, 1));
}
static inline void *
kmalloc_array(size_t n, size_t size, gfp_t flags)
{
return (mallocarray(n, size, M_KMALLOC, linux_check_m_flags(flags)));
}
static inline void *
kvmalloc_array(size_t n, size_t size, gfp_t flags)
{
return (mallocarray(n, size, M_KMALLOC, linux_check_m_flags(flags)));
}
static inline void *
krealloc(void *ptr, size_t size, gfp_t flags)
{
return (realloc(ptr, size, M_KMALLOC, linux_check_m_flags(flags)));
}
static inline void
kfree(const void *ptr)
{
free(__DECONST(void *, ptr), M_KMALLOC);
}
static inline size_t
ksize(const void *ptr)
{
return (malloc_usable_size(ptr));
}
extern struct linux_kmem_cache *linux_kmem_cache_create(const char *name,
size_t size, size_t align, unsigned flags, linux_kmem_ctor_t *ctor);
static inline void *
linux_kmem_cache_alloc(struct linux_kmem_cache *c, gfp_t flags)
{
return (uma_zalloc_arg(c->cache_zone, c,
linux_check_m_flags(flags)));
}
static inline void *
kmem_cache_zalloc(struct linux_kmem_cache *c, gfp_t flags)
{
return (uma_zalloc_arg(c->cache_zone, c,
linux_check_m_flags(flags | M_ZERO)));
}
extern void linux_kmem_cache_free_rcu(struct linux_kmem_cache *, void *);
static inline void
linux_kmem_cache_free(struct linux_kmem_cache *c, void *m)
{
if (unlikely(c->cache_flags & SLAB_TYPESAFE_BY_RCU))
linux_kmem_cache_free_rcu(c, m);
else
uma_zfree(c->cache_zone, m);
}
extern void linux_kmem_cache_destroy(struct linux_kmem_cache *);
void linux_kfree_async(void *);
#endif /* _LINUX_SLAB_H_ */