Commit b330e6a4 authored by Kent Overstreet's avatar Kent Overstreet Committed by Linus Torvalds

md: convert to kvmalloc

The code really just wants a big flat buffer, so just do that.

Link: http://lkml.kernel.org/r/20181217131929.11727-3-kent.overstreet@gmail.comSigned-off-by: default avatarKent Overstreet <kent.overstreet@gmail.com>
Reviewed-by: default avatarMatthew Wilcox <willy@infradead.org>
Cc: Shaohua Li <shli@kernel.org>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Eric Paris <eparis@parisplace.org>
Cc: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Cc: Neil Horman <nhorman@tuxdriver.com>
Cc: Paul Moore <paul@paul-moore.com>
Cc: Pravin B Shelar <pshelar@ovn.org>
Cc: Stephen Smalley <sds@tycho.nsa.gov>
Cc: Vlad Yasevich <vyasevich@gmail.com>
Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
parent ee9c5e67
......@@ -16,7 +16,6 @@
#include <linux/blkdev.h>
#include <linux/slab.h>
#include <linux/crc32c.h>
#include <linux/flex_array.h>
#include <linux/async_tx.h>
#include <linux/raid/md_p.h>
#include "md.h"
......@@ -165,7 +164,7 @@ ops_run_partial_parity(struct stripe_head *sh, struct raid5_percpu *percpu,
struct dma_async_tx_descriptor *tx)
{
int disks = sh->disks;
struct page **srcs = flex_array_get(percpu->scribble, 0);
struct page **srcs = percpu->scribble;
int count = 0, pd_idx = sh->pd_idx, i;
struct async_submit_ctl submit;
......@@ -196,8 +195,7 @@ ops_run_partial_parity(struct stripe_head *sh, struct raid5_percpu *percpu,
}
init_async_submit(&submit, ASYNC_TX_FENCE|ASYNC_TX_XOR_ZERO_DST, tx,
NULL, sh, flex_array_get(percpu->scribble, 0)
+ sizeof(struct page *) * (sh->disks + 2));
NULL, sh, (void *) (srcs + sh->disks + 2));
if (count == 1)
tx = async_memcpy(sh->ppl_page, srcs[0], 0, 0, PAGE_SIZE,
......
......@@ -54,7 +54,6 @@
#include <linux/slab.h>
#include <linux/ratelimit.h>
#include <linux/nodemask.h>
#include <linux/flex_array.h>
#include <trace/events/block.h>
#include <linux/list_sort.h>
......@@ -1394,22 +1393,16 @@ static void ops_complete_compute(void *stripe_head_ref)
}
/* return a pointer to the address conversion region of the scribble buffer */
static addr_conv_t *to_addr_conv(struct stripe_head *sh,
struct raid5_percpu *percpu, int i)
static struct page **to_addr_page(struct raid5_percpu *percpu, int i)
{
void *addr;
addr = flex_array_get(percpu->scribble, i);
return addr + sizeof(struct page *) * (sh->disks + 2);
return percpu->scribble + i * percpu->scribble_obj_size;
}
/* return a pointer to the address conversion region of the scribble buffer */
static struct page **to_addr_page(struct raid5_percpu *percpu, int i)
static addr_conv_t *to_addr_conv(struct stripe_head *sh,
struct raid5_percpu *percpu, int i)
{
void *addr;
addr = flex_array_get(percpu->scribble, i);
return addr;
return (void *) (to_addr_page(percpu, i) + sh->disks + 2);
}
static struct dma_async_tx_descriptor *
......@@ -2238,21 +2231,23 @@ static int grow_stripes(struct r5conf *conf, int num)
* calculate over all devices (not just the data blocks), using zeros in place
* of the P and Q blocks.
*/
static struct flex_array *scribble_alloc(int num, int cnt, gfp_t flags)
static int scribble_alloc(struct raid5_percpu *percpu,
int num, int cnt, gfp_t flags)
{
struct flex_array *ret;
size_t len;
size_t obj_size =
sizeof(struct page *) * (num+2) +
sizeof(addr_conv_t) * (num+2);
void *scribble;
len = sizeof(struct page *) * (num+2) + sizeof(addr_conv_t) * (num+2);
ret = flex_array_alloc(len, cnt, flags);
if (!ret)
return NULL;
/* always prealloc all elements, so no locking is required */
if (flex_array_prealloc(ret, 0, cnt, flags)) {
flex_array_free(ret);
return NULL;
}
return ret;
scribble = kvmalloc_array(cnt, obj_size, flags);
if (!scribble)
return -ENOMEM;
kvfree(percpu->scribble);
percpu->scribble = scribble;
percpu->scribble_obj_size = obj_size;
return 0;
}
static int resize_chunks(struct r5conf *conf, int new_disks, int new_sectors)
......@@ -2270,23 +2265,18 @@ static int resize_chunks(struct r5conf *conf, int new_disks, int new_sectors)
return 0;
mddev_suspend(conf->mddev);
get_online_cpus();
for_each_present_cpu(cpu) {
struct raid5_percpu *percpu;
struct flex_array *scribble;
percpu = per_cpu_ptr(conf->percpu, cpu);
scribble = scribble_alloc(new_disks,
err = scribble_alloc(percpu, new_disks,
new_sectors / STRIPE_SECTORS,
GFP_NOIO);
if (scribble) {
flex_array_free(percpu->scribble);
percpu->scribble = scribble;
} else {
err = -ENOMEM;
if (err)
break;
}
}
put_online_cpus();
mddev_resume(conf->mddev);
if (!err) {
......@@ -6742,25 +6732,26 @@ raid5_size(struct mddev *mddev, sector_t sectors, int raid_disks)
static void free_scratch_buffer(struct r5conf *conf, struct raid5_percpu *percpu)
{
safe_put_page(percpu->spare_page);
if (percpu->scribble)
flex_array_free(percpu->scribble);
percpu->spare_page = NULL;
kvfree(percpu->scribble);
percpu->scribble = NULL;
}
static int alloc_scratch_buffer(struct r5conf *conf, struct raid5_percpu *percpu)
{
if (conf->level == 6 && !percpu->spare_page)
if (conf->level == 6 && !percpu->spare_page) {
percpu->spare_page = alloc_page(GFP_KERNEL);
if (!percpu->scribble)
percpu->scribble = scribble_alloc(max(conf->raid_disks,
if (!percpu->spare_page)
return -ENOMEM;
}
if (scribble_alloc(percpu,
max(conf->raid_disks,
conf->previous_raid_disks),
max(conf->chunk_sectors,
conf->prev_chunk_sectors)
/ STRIPE_SECTORS,
GFP_KERNEL);
if (!percpu->scribble || (conf->level == 6 && !percpu->spare_page)) {
GFP_KERNEL)) {
free_scratch_buffer(conf, percpu);
return -ENOMEM;
}
......
......@@ -638,10 +638,11 @@ struct r5conf {
/* per cpu variables */
struct raid5_percpu {
struct page *spare_page; /* Used when checking P/Q in raid6 */
struct flex_array *scribble; /* space for constructing buffer
void *scribble; /* space for constructing buffer
* lists and performing address
* conversions
*/
int scribble_obj_size;
} __percpu *percpu;
int scribble_disks;
int scribble_sectors;
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment