Revision 6460495709aeb651896bc8e5c134b2e4ca7d34a8 authored by James Wang on 08 June 2017, 06:52:51 UTC, committed by Jens Axboe on 08 June 2017, 14:04:18 UTC
While installing SLES-12 (based on v4.4), I found that the installer will stall for 60+ seconds during LVM disk scan. The root cause was determined to be the removal of a bound device check in loop_flush() by commit b5dd2f6047ca ("block: loop: improve performance via blk-mq"). Restoring this check, examining ->lo_state as set by loop_set_fd() eliminates the bad behavior. Test method: modprobe loop max_loop=64 dd if=/dev/zero of=disk bs=512 count=200K for((i=0;i<4;i++))do losetup -f disk; done mkfs.ext4 -F /dev/loop0 for((i=0;i<4;i++))do mkdir t$i; mount /dev/loop$i t$i;done for f in `ls /dev/loop[0-9]*|sort`; do \ echo $f; dd if=$f of=/dev/null bs=512 count=1; \ done Test output: stock patched /dev/loop0 18.1217e-05 8.3842e-05 /dev/loop1 6.1114e-05 0.000147979 /dev/loop10 0.414701 0.000116564 /dev/loop11 0.7474 6.7942e-05 /dev/loop12 0.747986 8.9082e-05 /dev/loop13 0.746532 7.4799e-05 /dev/loop14 0.480041 9.3926e-05 /dev/loop15 1.26453 7.2522e-05 Note that from loop10 onward, the device is not mounted, yet the stock kernel consumes several orders of magnitude more wall time than it does for a mounted device. (Thanks for Mike Galbraith <efault@gmx.de>, give a changelog review.) Reviewed-by: Hannes Reinecke <hare@suse.com> Reviewed-by: Ming Lei <ming.lei@redhat.com> Signed-off-by: James Wang <jnwang@suse.com> Fixes: b5dd2f6047ca ("block: loop: improve performance via blk-mq") Signed-off-by: Jens Axboe <axboe@fb.com>
1 parent 6679a90
maccess.c
/*
* Access kernel memory without faulting.
*/
#include <linux/export.h>
#include <linux/mm.h>
#include <linux/uaccess.h>
/**
* probe_kernel_read(): safely attempt to read from a location
* @dst: pointer to the buffer that shall take the data
* @src: address to read from
* @size: size of the data chunk
*
* Safely read from address @src to the buffer at @dst. If a kernel fault
* happens, handle that and return -EFAULT.
*
* We ensure that the copy_from_user is executed in atomic context so that
* do_page_fault() doesn't attempt to take mmap_sem. This makes
* probe_kernel_read() suitable for use within regions where the caller
* already holds mmap_sem, or other locks which nest inside mmap_sem.
*/
long __weak probe_kernel_read(void *dst, const void *src, size_t size)
__attribute__((alias("__probe_kernel_read")));
long __probe_kernel_read(void *dst, const void *src, size_t size)
{
long ret;
mm_segment_t old_fs = get_fs();
set_fs(KERNEL_DS);
pagefault_disable();
ret = __copy_from_user_inatomic(dst,
(__force const void __user *)src, size);
pagefault_enable();
set_fs(old_fs);
return ret ? -EFAULT : 0;
}
EXPORT_SYMBOL_GPL(probe_kernel_read);
/**
* probe_kernel_write(): safely attempt to write to a location
* @dst: address to write to
* @src: pointer to the data that shall be written
* @size: size of the data chunk
*
* Safely write to address @dst from the buffer at @src. If a kernel fault
* happens, handle that and return -EFAULT.
*/
long __weak probe_kernel_write(void *dst, const void *src, size_t size)
__attribute__((alias("__probe_kernel_write")));
long __probe_kernel_write(void *dst, const void *src, size_t size)
{
long ret;
mm_segment_t old_fs = get_fs();
set_fs(KERNEL_DS);
pagefault_disable();
ret = __copy_to_user_inatomic((__force void __user *)dst, src, size);
pagefault_enable();
set_fs(old_fs);
return ret ? -EFAULT : 0;
}
EXPORT_SYMBOL_GPL(probe_kernel_write);
/**
* strncpy_from_unsafe: - Copy a NUL terminated string from unsafe address.
* @dst: Destination address, in kernel space. This buffer must be at
* least @count bytes long.
* @src: Unsafe address.
* @count: Maximum number of bytes to copy, including the trailing NUL.
*
* Copies a NUL-terminated string from unsafe address to kernel buffer.
*
* On success, returns the length of the string INCLUDING the trailing NUL.
*
* If access fails, returns -EFAULT (some data may have been copied
* and the trailing NUL added).
*
* If @count is smaller than the length of the string, copies @count-1 bytes,
* sets the last byte of @dst buffer to NUL and returns @count.
*/
long strncpy_from_unsafe(char *dst, const void *unsafe_addr, long count)
{
mm_segment_t old_fs = get_fs();
const void *src = unsafe_addr;
long ret;
if (unlikely(count <= 0))
return 0;
set_fs(KERNEL_DS);
pagefault_disable();
do {
ret = __get_user(*dst++, (const char __user __force *)src++);
} while (dst[-1] && ret == 0 && src - unsafe_addr < count);
dst[-1] = '\0';
pagefault_enable();
set_fs(old_fs);
return ret ? -EFAULT : src - unsafe_addr;
}
Computing file changes ...