mirror of
https://github.com/brain-hackers/linux-brain.git
synced 2024-06-09 15:26:21 +09:00
f8f9ee4794
Memory we use to submit for IO needs strict alignment to the underlying driver contraints. Worst case, this is 512 bytes. Given that all allocations for IO are always a power of 2 multiple of 512 bytes, the kernel heap provides natural alignment for objects of these sizes and that suffices. Until, of course, memory debugging of some kind is turned on (e.g. red zones, poisoning, KASAN) and then the alignment of the heap objects is thrown out the window. Then we get weird IO errors and data corruption problems because drivers don't validate alignment and do the wrong thing when passed unaligned memory buffers in bios. TO fix this, introduce kmem_alloc_io(), which will guaranteeat least 512 byte alignment of buffers for IO, even if memory debugging options are turned on. It is assumed that the minimum allocation size will be 512 bytes, and that sizes will be power of 2 mulitples of 512 bytes. Use this everywhere we allocate buffers for IO. This no longer fails with log recovery errors when KASAN is enabled due to the brd driver not handling unaligned memory buffers: # mkfs.xfs -f /dev/ram0 ; mount /dev/ram0 /mnt/test Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com> Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
139 lines
3.2 KiB
C
139 lines
3.2 KiB
C
// SPDX-License-Identifier: GPL-2.0
|
|
/*
|
|
* Copyright (c) 2000-2005 Silicon Graphics, Inc.
|
|
* All Rights Reserved.
|
|
*/
|
|
#include "xfs.h"
|
|
#include <linux/backing-dev.h>
|
|
#include "xfs_message.h"
|
|
#include "xfs_trace.h"
|
|
|
|
void *
|
|
kmem_alloc(size_t size, xfs_km_flags_t flags)
|
|
{
|
|
int retries = 0;
|
|
gfp_t lflags = kmem_flags_convert(flags);
|
|
void *ptr;
|
|
|
|
trace_kmem_alloc(size, flags, _RET_IP_);
|
|
|
|
do {
|
|
ptr = kmalloc(size, lflags);
|
|
if (ptr || (flags & KM_MAYFAIL))
|
|
return ptr;
|
|
if (!(++retries % 100))
|
|
xfs_err(NULL,
|
|
"%s(%u) possible memory allocation deadlock size %u in %s (mode:0x%x)",
|
|
current->comm, current->pid,
|
|
(unsigned int)size, __func__, lflags);
|
|
congestion_wait(BLK_RW_ASYNC, HZ/50);
|
|
} while (1);
|
|
}
|
|
|
|
|
|
/*
|
|
* __vmalloc() will allocate data pages and auxillary structures (e.g.
|
|
* pagetables) with GFP_KERNEL, yet we may be under GFP_NOFS context here. Hence
|
|
* we need to tell memory reclaim that we are in such a context via
|
|
* PF_MEMALLOC_NOFS to prevent memory reclaim re-entering the filesystem here
|
|
* and potentially deadlocking.
|
|
*/
|
|
static void *
|
|
__kmem_vmalloc(size_t size, xfs_km_flags_t flags)
|
|
{
|
|
unsigned nofs_flag = 0;
|
|
void *ptr;
|
|
gfp_t lflags = kmem_flags_convert(flags);
|
|
|
|
if (flags & KM_NOFS)
|
|
nofs_flag = memalloc_nofs_save();
|
|
|
|
ptr = __vmalloc(size, lflags, PAGE_KERNEL);
|
|
|
|
if (flags & KM_NOFS)
|
|
memalloc_nofs_restore(nofs_flag);
|
|
|
|
return ptr;
|
|
}
|
|
|
|
/*
|
|
* Same as kmem_alloc_large, except we guarantee the buffer returned is aligned
|
|
* to the @align_mask. We only guarantee alignment up to page size, we'll clamp
|
|
* alignment at page size if it is larger. vmalloc always returns a PAGE_SIZE
|
|
* aligned region.
|
|
*/
|
|
void *
|
|
kmem_alloc_io(size_t size, int align_mask, xfs_km_flags_t flags)
|
|
{
|
|
void *ptr;
|
|
|
|
trace_kmem_alloc_io(size, flags, _RET_IP_);
|
|
|
|
if (WARN_ON_ONCE(align_mask >= PAGE_SIZE))
|
|
align_mask = PAGE_SIZE - 1;
|
|
|
|
ptr = kmem_alloc(size, flags | KM_MAYFAIL);
|
|
if (ptr) {
|
|
if (!((uintptr_t)ptr & align_mask))
|
|
return ptr;
|
|
kfree(ptr);
|
|
}
|
|
return __kmem_vmalloc(size, flags);
|
|
}
|
|
|
|
void *
|
|
kmem_alloc_large(size_t size, xfs_km_flags_t flags)
|
|
{
|
|
void *ptr;
|
|
|
|
trace_kmem_alloc_large(size, flags, _RET_IP_);
|
|
|
|
ptr = kmem_alloc(size, flags | KM_MAYFAIL);
|
|
if (ptr)
|
|
return ptr;
|
|
return __kmem_vmalloc(size, flags);
|
|
}
|
|
|
|
void *
|
|
kmem_realloc(const void *old, size_t newsize, xfs_km_flags_t flags)
|
|
{
|
|
int retries = 0;
|
|
gfp_t lflags = kmem_flags_convert(flags);
|
|
void *ptr;
|
|
|
|
trace_kmem_realloc(newsize, flags, _RET_IP_);
|
|
|
|
do {
|
|
ptr = krealloc(old, newsize, lflags);
|
|
if (ptr || (flags & KM_MAYFAIL))
|
|
return ptr;
|
|
if (!(++retries % 100))
|
|
xfs_err(NULL,
|
|
"%s(%u) possible memory allocation deadlock size %zu in %s (mode:0x%x)",
|
|
current->comm, current->pid,
|
|
newsize, __func__, lflags);
|
|
congestion_wait(BLK_RW_ASYNC, HZ/50);
|
|
} while (1);
|
|
}
|
|
|
|
void *
|
|
kmem_zone_alloc(kmem_zone_t *zone, xfs_km_flags_t flags)
|
|
{
|
|
int retries = 0;
|
|
gfp_t lflags = kmem_flags_convert(flags);
|
|
void *ptr;
|
|
|
|
trace_kmem_zone_alloc(kmem_cache_size(zone), flags, _RET_IP_);
|
|
do {
|
|
ptr = kmem_cache_alloc(zone, lflags);
|
|
if (ptr || (flags & KM_MAYFAIL))
|
|
return ptr;
|
|
if (!(++retries % 100))
|
|
xfs_err(NULL,
|
|
"%s(%u) possible memory allocation deadlock in %s (mode:0x%x)",
|
|
current->comm, current->pid,
|
|
__func__, lflags);
|
|
congestion_wait(BLK_RW_ASYNC, HZ/50);
|
|
} while (1);
|
|
}
|