OpenCloudOS-Kernel/drivers/block/zram/zram_drv.c

885 lines
20 KiB
C
Raw Normal View History

/*
* Compressed RAM block device
*
* Copyright (C) 2008, 2009, 2010 Nitin Gupta
* 2012, 2013 Minchan Kim
*
* This code is released using a dual license strategy: BSD/GPL
* You can choose the licence that better fits your requirements.
*
* Released under the terms of 3-clause BSD License
* Released under the terms of GNU General Public License Version 2.0
*
*/
#define KMSG_COMPONENT "zram"
#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
#ifdef CONFIG_ZRAM_DEBUG
#define DEBUG
#endif
#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/bio.h>
#include <linux/bitops.h>
#include <linux/blkdev.h>
#include <linux/buffer_head.h>
#include <linux/device.h>
#include <linux/genhd.h>
#include <linux/highmem.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 16:04:11 +08:00
#include <linux/slab.h>
#include <linux/string.h>
#include <linux/vmalloc.h>
#include "zram_drv.h"
/* Globals */
static int zram_major;
static struct zram *zram_devices;
static const char *default_compressor = "lzo";
/* Module params (documentation at end) */
static unsigned int num_devices = 1;
#define ZRAM_ATTR_RO(name) \
static ssize_t zram_attr_##name##_show(struct device *d, \
struct device_attribute *attr, char *b) \
{ \
struct zram *zram = dev_to_zram(d); \
return sprintf(b, "%llu\n", \
(u64)atomic64_read(&zram->stats.name)); \
} \
static struct device_attribute dev_attr_##name = \
__ATTR(name, S_IRUGO, zram_attr_##name##_show, NULL);
static inline int init_done(struct zram *zram)
{
return zram->meta != NULL;
}
static inline struct zram *dev_to_zram(struct device *dev)
{
return (struct zram *)dev_to_disk(dev)->private_data;
}
static ssize_t disksize_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct zram *zram = dev_to_zram(dev);
return sprintf(buf, "%llu\n", zram->disksize);
}
static ssize_t initstate_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
u32 val;
struct zram *zram = dev_to_zram(dev);
down_read(&zram->init_lock);
val = init_done(zram);
up_read(&zram->init_lock);
return sprintf(buf, "%u\n", val);
}
static ssize_t orig_data_size_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct zram *zram = dev_to_zram(dev);
return sprintf(buf, "%llu\n",
(u64)(atomic64_read(&zram->stats.pages_stored)) << PAGE_SHIFT);
}
static ssize_t mem_used_total_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
u64 val = 0;
struct zram *zram = dev_to_zram(dev);
struct zram_meta *meta = zram->meta;
down_read(&zram->init_lock);
if (init_done(zram))
val = zs_get_total_size_bytes(meta->mem_pool);
up_read(&zram->init_lock);
return sprintf(buf, "%llu\n", val);
}
/* flag operations needs meta->tb_lock */
static int zram_test_flag(struct zram_meta *meta, u32 index,
enum zram_pageflags flag)
{
return meta->table[index].flags & BIT(flag);
}
static void zram_set_flag(struct zram_meta *meta, u32 index,
enum zram_pageflags flag)
{
meta->table[index].flags |= BIT(flag);
}
static void zram_clear_flag(struct zram_meta *meta, u32 index,
enum zram_pageflags flag)
{
meta->table[index].flags &= ~BIT(flag);
}
static inline int is_partial_io(struct bio_vec *bvec)
{
return bvec->bv_len != PAGE_SIZE;
}
/*
* Check if request is within bounds and aligned on zram logical blocks.
*/
static inline int valid_io_request(struct zram *zram, struct bio *bio)
{
u64 start, end, bound;
/* unaligned request */
block: Abstract out bvec iterator Immutable biovecs are going to require an explicit iterator. To implement immutable bvecs, a later patch is going to add a bi_bvec_done member to this struct; for now, this patch effectively just renames things. Signed-off-by: Kent Overstreet <kmo@daterainc.com> Cc: Jens Axboe <axboe@kernel.dk> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: "Ed L. Cashin" <ecashin@coraid.com> Cc: Nick Piggin <npiggin@kernel.dk> Cc: Lars Ellenberg <drbd-dev@lists.linbit.com> Cc: Jiri Kosina <jkosina@suse.cz> Cc: Matthew Wilcox <willy@linux.intel.com> Cc: Geoff Levand <geoff@infradead.org> Cc: Yehuda Sadeh <yehuda@inktank.com> Cc: Sage Weil <sage@inktank.com> Cc: Alex Elder <elder@inktank.com> Cc: ceph-devel@vger.kernel.org Cc: Joshua Morris <josh.h.morris@us.ibm.com> Cc: Philip Kelleher <pjk1939@linux.vnet.ibm.com> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: "Michael S. Tsirkin" <mst@redhat.com> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Neil Brown <neilb@suse.de> Cc: Alasdair Kergon <agk@redhat.com> Cc: Mike Snitzer <snitzer@redhat.com> Cc: dm-devel@redhat.com Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: linux390@de.ibm.com Cc: Boaz Harrosh <bharrosh@panasas.com> Cc: Benny Halevy <bhalevy@tonian.com> Cc: "James E.J. Bottomley" <JBottomley@parallels.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: "Nicholas A. Bellinger" <nab@linux-iscsi.org> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Chris Mason <chris.mason@fusionio.com> Cc: "Theodore Ts'o" <tytso@mit.edu> Cc: Andreas Dilger <adilger.kernel@dilger.ca> Cc: Jaegeuk Kim <jaegeuk.kim@samsung.com> Cc: Steven Whitehouse <swhiteho@redhat.com> Cc: Dave Kleikamp <shaggy@kernel.org> Cc: Joern Engel <joern@logfs.org> Cc: Prasad Joshi <prasadjoshi.linux@gmail.com> Cc: Trond Myklebust <Trond.Myklebust@netapp.com> Cc: KONISHI Ryusuke <konishi.ryusuke@lab.ntt.co.jp> Cc: Mark Fasheh <mfasheh@suse.com> Cc: Joel Becker <jlbec@evilplan.org> Cc: Ben Myers <bpm@sgi.com> Cc: xfs@oss.sgi.com Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Len Brown <len.brown@intel.com> Cc: Pavel Machek <pavel@ucw.cz> Cc: "Rafael J. Wysocki" <rjw@sisk.pl> Cc: Herton Ronaldo Krzesinski <herton.krzesinski@canonical.com> Cc: Ben Hutchings <ben@decadent.org.uk> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Guo Chao <yan@linux.vnet.ibm.com> Cc: Tejun Heo <tj@kernel.org> Cc: Asai Thambi S P <asamymuthupa@micron.com> Cc: Selvan Mani <smani@micron.com> Cc: Sam Bradshaw <sbradshaw@micron.com> Cc: Wei Yongjun <yongjun_wei@trendmicro.com.cn> Cc: "Roger Pau Monné" <roger.pau@citrix.com> Cc: Jan Beulich <jbeulich@suse.com> Cc: Stefano Stabellini <stefano.stabellini@eu.citrix.com> Cc: Ian Campbell <Ian.Campbell@citrix.com> Cc: Sebastian Ott <sebott@linux.vnet.ibm.com> Cc: Christian Borntraeger <borntraeger@de.ibm.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Jiang Liu <jiang.liu@huawei.com> Cc: Nitin Gupta <ngupta@vflare.org> Cc: Jerome Marchand <jmarchand@redhat.com> Cc: Joe Perches <joe@perches.com> Cc: Peng Tao <tao.peng@emc.com> Cc: Andy Adamson <andros@netapp.com> Cc: fanchaoting <fanchaoting@cn.fujitsu.com> Cc: Jie Liu <jeff.liu@oracle.com> Cc: Sunil Mushran <sunil.mushran@gmail.com> Cc: "Martin K. Petersen" <martin.petersen@oracle.com> Cc: Namjae Jeon <namjae.jeon@samsung.com> Cc: Pankaj Kumar <pankaj.km@samsung.com> Cc: Dan Magenheimer <dan.magenheimer@oracle.com> Cc: Mel Gorman <mgorman@suse.de>6
2013-10-12 06:44:27 +08:00
if (unlikely(bio->bi_iter.bi_sector &
(ZRAM_SECTOR_PER_LOGICAL_BLOCK - 1)))
return 0;
block: Abstract out bvec iterator Immutable biovecs are going to require an explicit iterator. To implement immutable bvecs, a later patch is going to add a bi_bvec_done member to this struct; for now, this patch effectively just renames things. Signed-off-by: Kent Overstreet <kmo@daterainc.com> Cc: Jens Axboe <axboe@kernel.dk> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: "Ed L. Cashin" <ecashin@coraid.com> Cc: Nick Piggin <npiggin@kernel.dk> Cc: Lars Ellenberg <drbd-dev@lists.linbit.com> Cc: Jiri Kosina <jkosina@suse.cz> Cc: Matthew Wilcox <willy@linux.intel.com> Cc: Geoff Levand <geoff@infradead.org> Cc: Yehuda Sadeh <yehuda@inktank.com> Cc: Sage Weil <sage@inktank.com> Cc: Alex Elder <elder@inktank.com> Cc: ceph-devel@vger.kernel.org Cc: Joshua Morris <josh.h.morris@us.ibm.com> Cc: Philip Kelleher <pjk1939@linux.vnet.ibm.com> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: "Michael S. Tsirkin" <mst@redhat.com> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Neil Brown <neilb@suse.de> Cc: Alasdair Kergon <agk@redhat.com> Cc: Mike Snitzer <snitzer@redhat.com> Cc: dm-devel@redhat.com Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: linux390@de.ibm.com Cc: Boaz Harrosh <bharrosh@panasas.com> Cc: Benny Halevy <bhalevy@tonian.com> Cc: "James E.J. Bottomley" <JBottomley@parallels.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: "Nicholas A. Bellinger" <nab@linux-iscsi.org> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Chris Mason <chris.mason@fusionio.com> Cc: "Theodore Ts'o" <tytso@mit.edu> Cc: Andreas Dilger <adilger.kernel@dilger.ca> Cc: Jaegeuk Kim <jaegeuk.kim@samsung.com> Cc: Steven Whitehouse <swhiteho@redhat.com> Cc: Dave Kleikamp <shaggy@kernel.org> Cc: Joern Engel <joern@logfs.org> Cc: Prasad Joshi <prasadjoshi.linux@gmail.com> Cc: Trond Myklebust <Trond.Myklebust@netapp.com> Cc: KONISHI Ryusuke <konishi.ryusuke@lab.ntt.co.jp> Cc: Mark Fasheh <mfasheh@suse.com> Cc: Joel Becker <jlbec@evilplan.org> Cc: Ben Myers <bpm@sgi.com> Cc: xfs@oss.sgi.com Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Len Brown <len.brown@intel.com> Cc: Pavel Machek <pavel@ucw.cz> Cc: "Rafael J. Wysocki" <rjw@sisk.pl> Cc: Herton Ronaldo Krzesinski <herton.krzesinski@canonical.com> Cc: Ben Hutchings <ben@decadent.org.uk> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Guo Chao <yan@linux.vnet.ibm.com> Cc: Tejun Heo <tj@kernel.org> Cc: Asai Thambi S P <asamymuthupa@micron.com> Cc: Selvan Mani <smani@micron.com> Cc: Sam Bradshaw <sbradshaw@micron.com> Cc: Wei Yongjun <yongjun_wei@trendmicro.com.cn> Cc: "Roger Pau Monné" <roger.pau@citrix.com> Cc: Jan Beulich <jbeulich@suse.com> Cc: Stefano Stabellini <stefano.stabellini@eu.citrix.com> Cc: Ian Campbell <Ian.Campbell@citrix.com> Cc: Sebastian Ott <sebott@linux.vnet.ibm.com> Cc: Christian Borntraeger <borntraeger@de.ibm.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Jiang Liu <jiang.liu@huawei.com> Cc: Nitin Gupta <ngupta@vflare.org> Cc: Jerome Marchand <jmarchand@redhat.com> Cc: Joe Perches <joe@perches.com> Cc: Peng Tao <tao.peng@emc.com> Cc: Andy Adamson <andros@netapp.com> Cc: fanchaoting <fanchaoting@cn.fujitsu.com> Cc: Jie Liu <jeff.liu@oracle.com> Cc: Sunil Mushran <sunil.mushran@gmail.com> Cc: "Martin K. Petersen" <martin.petersen@oracle.com> Cc: Namjae Jeon <namjae.jeon@samsung.com> Cc: Pankaj Kumar <pankaj.km@samsung.com> Cc: Dan Magenheimer <dan.magenheimer@oracle.com> Cc: Mel Gorman <mgorman@suse.de>6
2013-10-12 06:44:27 +08:00
if (unlikely(bio->bi_iter.bi_size & (ZRAM_LOGICAL_BLOCK_SIZE - 1)))
return 0;
block: Abstract out bvec iterator Immutable biovecs are going to require an explicit iterator. To implement immutable bvecs, a later patch is going to add a bi_bvec_done member to this struct; for now, this patch effectively just renames things. Signed-off-by: Kent Overstreet <kmo@daterainc.com> Cc: Jens Axboe <axboe@kernel.dk> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: "Ed L. Cashin" <ecashin@coraid.com> Cc: Nick Piggin <npiggin@kernel.dk> Cc: Lars Ellenberg <drbd-dev@lists.linbit.com> Cc: Jiri Kosina <jkosina@suse.cz> Cc: Matthew Wilcox <willy@linux.intel.com> Cc: Geoff Levand <geoff@infradead.org> Cc: Yehuda Sadeh <yehuda@inktank.com> Cc: Sage Weil <sage@inktank.com> Cc: Alex Elder <elder@inktank.com> Cc: ceph-devel@vger.kernel.org Cc: Joshua Morris <josh.h.morris@us.ibm.com> Cc: Philip Kelleher <pjk1939@linux.vnet.ibm.com> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: "Michael S. Tsirkin" <mst@redhat.com> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Neil Brown <neilb@suse.de> Cc: Alasdair Kergon <agk@redhat.com> Cc: Mike Snitzer <snitzer@redhat.com> Cc: dm-devel@redhat.com Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: linux390@de.ibm.com Cc: Boaz Harrosh <bharrosh@panasas.com> Cc: Benny Halevy <bhalevy@tonian.com> Cc: "James E.J. Bottomley" <JBottomley@parallels.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: "Nicholas A. Bellinger" <nab@linux-iscsi.org> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Chris Mason <chris.mason@fusionio.com> Cc: "Theodore Ts'o" <tytso@mit.edu> Cc: Andreas Dilger <adilger.kernel@dilger.ca> Cc: Jaegeuk Kim <jaegeuk.kim@samsung.com> Cc: Steven Whitehouse <swhiteho@redhat.com> Cc: Dave Kleikamp <shaggy@kernel.org> Cc: Joern Engel <joern@logfs.org> Cc: Prasad Joshi <prasadjoshi.linux@gmail.com> Cc: Trond Myklebust <Trond.Myklebust@netapp.com> Cc: KONISHI Ryusuke <konishi.ryusuke@lab.ntt.co.jp> Cc: Mark Fasheh <mfasheh@suse.com> Cc: Joel Becker <jlbec@evilplan.org> Cc: Ben Myers <bpm@sgi.com> Cc: xfs@oss.sgi.com Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Len Brown <len.brown@intel.com> Cc: Pavel Machek <pavel@ucw.cz> Cc: "Rafael J. Wysocki" <rjw@sisk.pl> Cc: Herton Ronaldo Krzesinski <herton.krzesinski@canonical.com> Cc: Ben Hutchings <ben@decadent.org.uk> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Guo Chao <yan@linux.vnet.ibm.com> Cc: Tejun Heo <tj@kernel.org> Cc: Asai Thambi S P <asamymuthupa@micron.com> Cc: Selvan Mani <smani@micron.com> Cc: Sam Bradshaw <sbradshaw@micron.com> Cc: Wei Yongjun <yongjun_wei@trendmicro.com.cn> Cc: "Roger Pau Monné" <roger.pau@citrix.com> Cc: Jan Beulich <jbeulich@suse.com> Cc: Stefano Stabellini <stefano.stabellini@eu.citrix.com> Cc: Ian Campbell <Ian.Campbell@citrix.com> Cc: Sebastian Ott <sebott@linux.vnet.ibm.com> Cc: Christian Borntraeger <borntraeger@de.ibm.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Jiang Liu <jiang.liu@huawei.com> Cc: Nitin Gupta <ngupta@vflare.org> Cc: Jerome Marchand <jmarchand@redhat.com> Cc: Joe Perches <joe@perches.com> Cc: Peng Tao <tao.peng@emc.com> Cc: Andy Adamson <andros@netapp.com> Cc: fanchaoting <fanchaoting@cn.fujitsu.com> Cc: Jie Liu <jeff.liu@oracle.com> Cc: Sunil Mushran <sunil.mushran@gmail.com> Cc: "Martin K. Petersen" <martin.petersen@oracle.com> Cc: Namjae Jeon <namjae.jeon@samsung.com> Cc: Pankaj Kumar <pankaj.km@samsung.com> Cc: Dan Magenheimer <dan.magenheimer@oracle.com> Cc: Mel Gorman <mgorman@suse.de>6
2013-10-12 06:44:27 +08:00
start = bio->bi_iter.bi_sector;
end = start + (bio->bi_iter.bi_size >> SECTOR_SHIFT);
bound = zram->disksize >> SECTOR_SHIFT;
/* out of range range */
if (unlikely(start >= bound || end > bound || start > end))
return 0;
/* I/O request is valid */
return 1;
}
static void zram_meta_free(struct zram_meta *meta)
{
zs_destroy_pool(meta->mem_pool);
vfree(meta->table);
kfree(meta);
}
static struct zram_meta *zram_meta_alloc(u64 disksize)
{
size_t num_pages;
struct zram_meta *meta = kmalloc(sizeof(*meta), GFP_KERNEL);
if (!meta)
goto out;
num_pages = disksize >> PAGE_SHIFT;
meta->table = vzalloc(num_pages * sizeof(*meta->table));
if (!meta->table) {
pr_err("Error allocating zram address table\n");
goto free_meta;
}
meta->mem_pool = zs_create_pool(GFP_NOIO | __GFP_HIGHMEM);
if (!meta->mem_pool) {
pr_err("Error creating memory pool\n");
goto free_table;
}
rwlock_init(&meta->tb_lock);
return meta;
free_table:
vfree(meta->table);
free_meta:
kfree(meta);
meta = NULL;
out:
return meta;
}
static void update_position(u32 *index, int *offset, struct bio_vec *bvec)
{
if (*offset + bvec->bv_len >= PAGE_SIZE)
(*index)++;
*offset = (*offset + bvec->bv_len) % PAGE_SIZE;
}
static int page_zero_filled(void *ptr)
{
unsigned int pos;
unsigned long *page;
page = (unsigned long *)ptr;
for (pos = 0; pos != PAGE_SIZE / sizeof(*page); pos++) {
if (page[pos])
return 0;
}
return 1;
}
static void handle_zero_page(struct bio_vec *bvec)
{
struct page *page = bvec->bv_page;
void *user_mem;
user_mem = kmap_atomic(page);
if (is_partial_io(bvec))
memset(user_mem + bvec->bv_offset, 0, bvec->bv_len);
else
clear_page(user_mem);
kunmap_atomic(user_mem);
flush_dcache_page(page);
}
/* NOTE: caller should hold meta->tb_lock with write-side */
static void zram_free_page(struct zram *zram, size_t index)
{
struct zram_meta *meta = zram->meta;
unsigned long handle = meta->table[index].handle;
if (unlikely(!handle)) {
/*
* No memory is allocated for zero filled pages.
* Simply clear zero page flag.
*/
if (zram_test_flag(meta, index, ZRAM_ZERO)) {
zram_clear_flag(meta, index, ZRAM_ZERO);
atomic64_dec(&zram->stats.zero_pages);
}
return;
}
zs_free(meta->mem_pool, handle);
atomic64_sub(meta->table[index].size, &zram->stats.compr_data_size);
atomic64_dec(&zram->stats.pages_stored);
meta->table[index].handle = 0;
meta->table[index].size = 0;
}
static int zram_decompress_page(struct zram *zram, char *mem, u32 index)
{
int ret = 0;
unsigned char *cmem;
struct zram_meta *meta = zram->meta;
unsigned long handle;
u16 size;
read_lock(&meta->tb_lock);
handle = meta->table[index].handle;
size = meta->table[index].size;
if (!handle || zram_test_flag(meta, index, ZRAM_ZERO)) {
read_unlock(&meta->tb_lock);
clear_page(mem);
return 0;
}
cmem = zs_map_object(meta->mem_pool, handle, ZS_MM_RO);
if (size == PAGE_SIZE)
copy_page(mem, cmem);
else
ret = zcomp_decompress(zram->comp, cmem, size, mem);
zs_unmap_object(meta->mem_pool, handle);
read_unlock(&meta->tb_lock);
Staging: ramzswap: Support generic I/O requests Currently, ramzwap devices (/dev/ramzswapX) can only be used as swap disks since it was hard-coded to consider only the first request in bio vector. Now, we iterate over all the segments in an incoming bio which allows us to handle all kinds of I/O requests. ramzswap devices can still handle PAGE_SIZE aligned and multiple of PAGE_SIZE sized I/O requests only. To ensure that we get always get such requests only, we set following request_queue attributes to PAGE_SIZE: - physical_block_size - logical_block_size - io_min - io_opt Note: physical and logical block sizes were already set equal to PAGE_SIZE and that seems to be sufficient to get PAGE_SIZE aligned I/O. Since we are no longer limited to handling swap requests only, the next few patches rename ramzswap to zram. So, the devices will then be called /dev/zram{0, 1, 2, ...} Usage/Examples: 1) Use as /tmp storage - mkfs.ext4 /dev/zram0 - mount /dev/zram0 /tmp 2) Use as swap: - mkswap /dev/zram0 - swapon /dev/zram0 -p 10 # give highest priority to zram0 Performance: - I/O benchamark done with 'dd' command. Details can be found here: http://code.google.com/p/compcache/wiki/zramperf Summary: - Maximum read speed (approx): - ram disk: 1200 MB/sec - zram disk: 600 MB/sec - Maximum write speed (approx): - ram disk: 500 MB/sec - zram disk: 160 MB/sec Issues: - Double caching: We can potentially waste memory by having two copies of a page -- one in page cache (uncompress) and second in the device memory (compressed). However, during reclaim, clean page cache pages are quickly freed, so this does not seem to be a big problem. - Stale data: Not all filesystems support issuing 'discard' requests to underlying block devices. So, if such filesystems are used over zram devices, we can accumulate lot of stale data in memory. Even for filesystems to do support discard (example, ext4), we need to see how effective it is. - Scalability: There is only one (per-device) de/compression buffer stats. This can lead to significant contention, especially when used for generic (non-swap) purposes. Signed-off-by: Nitin Gupta <ngupta@vflare.org> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2010-06-01 16:01:23 +08:00
/* Should NEVER happen. Return bio error if it does. */
if (unlikely(ret)) {
pr_err("Decompression failed! err=%d, page=%u\n", ret, index);
atomic64_inc(&zram->stats.failed_reads);
return ret;
Staging: ramzswap: Support generic I/O requests Currently, ramzwap devices (/dev/ramzswapX) can only be used as swap disks since it was hard-coded to consider only the first request in bio vector. Now, we iterate over all the segments in an incoming bio which allows us to handle all kinds of I/O requests. ramzswap devices can still handle PAGE_SIZE aligned and multiple of PAGE_SIZE sized I/O requests only. To ensure that we get always get such requests only, we set following request_queue attributes to PAGE_SIZE: - physical_block_size - logical_block_size - io_min - io_opt Note: physical and logical block sizes were already set equal to PAGE_SIZE and that seems to be sufficient to get PAGE_SIZE aligned I/O. Since we are no longer limited to handling swap requests only, the next few patches rename ramzswap to zram. So, the devices will then be called /dev/zram{0, 1, 2, ...} Usage/Examples: 1) Use as /tmp storage - mkfs.ext4 /dev/zram0 - mount /dev/zram0 /tmp 2) Use as swap: - mkswap /dev/zram0 - swapon /dev/zram0 -p 10 # give highest priority to zram0 Performance: - I/O benchamark done with 'dd' command. Details can be found here: http://code.google.com/p/compcache/wiki/zramperf Summary: - Maximum read speed (approx): - ram disk: 1200 MB/sec - zram disk: 600 MB/sec - Maximum write speed (approx): - ram disk: 500 MB/sec - zram disk: 160 MB/sec Issues: - Double caching: We can potentially waste memory by having two copies of a page -- one in page cache (uncompress) and second in the device memory (compressed). However, during reclaim, clean page cache pages are quickly freed, so this does not seem to be a big problem. - Stale data: Not all filesystems support issuing 'discard' requests to underlying block devices. So, if such filesystems are used over zram devices, we can accumulate lot of stale data in memory. Even for filesystems to do support discard (example, ext4), we need to see how effective it is. - Scalability: There is only one (per-device) de/compression buffer stats. This can lead to significant contention, especially when used for generic (non-swap) purposes. Signed-off-by: Nitin Gupta <ngupta@vflare.org> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2010-06-01 16:01:23 +08:00
}
return 0;
}
static int zram_bvec_read(struct zram *zram, struct bio_vec *bvec,
u32 index, int offset, struct bio *bio)
{
int ret;
struct page *page;
unsigned char *user_mem, *uncmem = NULL;
struct zram_meta *meta = zram->meta;
page = bvec->bv_page;
read_lock(&meta->tb_lock);
if (unlikely(!meta->table[index].handle) ||
zram_test_flag(meta, index, ZRAM_ZERO)) {
read_unlock(&meta->tb_lock);
handle_zero_page(bvec);
return 0;
}
read_unlock(&meta->tb_lock);
if (is_partial_io(bvec))
/* Use a temporary buffer to decompress the page */
uncmem = kmalloc(PAGE_SIZE, GFP_NOIO);
user_mem = kmap_atomic(page);
if (!is_partial_io(bvec))
uncmem = user_mem;
if (!uncmem) {
pr_info("Unable to allocate temp memory\n");
ret = -ENOMEM;
goto out_cleanup;
}
ret = zram_decompress_page(zram, uncmem, index);
/* Should NEVER happen. Return bio error if it does. */
if (unlikely(ret))
goto out_cleanup;
if (is_partial_io(bvec))
memcpy(user_mem + bvec->bv_offset, uncmem + offset,
bvec->bv_len);
flush_dcache_page(page);
ret = 0;
out_cleanup:
kunmap_atomic(user_mem);
if (is_partial_io(bvec))
kfree(uncmem);
return ret;
}
static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, u32 index,
int offset)
{
int ret = 0;
size_t clen;
unsigned long handle;
struct page *page;
unsigned char *user_mem, *cmem, *src, *uncmem = NULL;
struct zram_meta *meta = zram->meta;
struct zcomp_strm *zstrm;
zram: remove zram->lock in read path and change it with mutex Finally, we separated zram->lock dependency from 32bit stat/ table handling so there is no reason to use rw_semaphore between read and write path so this patch removes the lock from read path totally and changes rw_semaphore with mutex. So, we could do old: read-read: OK read-write: NO write-write: NO Now: read-read: OK read-write: OK write-write: NO The below data proves mixed workload performs well 11 times and there is also enhance on write-write path because current rw-semaphore doesn't support SPIN_ON_OWNER. It's side effect but anyway good thing for us. Write-related tests perform better (from 61% to 1058%) but read path has good/bad(from -2.22% to 1.45%) but they are all marginal within stddev. CPU 12 iozone -t -T -l 12 -u 12 -r 16K -s 60M -I +Z -V 0 ==Initial write ==Initial write records: 10 records: 10 avg: 516189.16 avg: 839907.96 std: 22486.53 (4.36%) std: 47902.17 (5.70%) max: 546970.60 max: 909910.35 min: 481131.54 min: 751148.38 ==Rewrite ==Rewrite records: 10 records: 10 avg: 509527.98 avg: 1050156.37 std: 45799.94 (8.99%) std: 40695.44 (3.88%) max: 611574.27 max: 1111929.26 min: 443679.95 min: 980409.62 ==Read ==Read records: 10 records: 10 avg: 4408624.17 avg: 4472546.76 std: 281152.61 (6.38%) std: 163662.78 (3.66%) max: 4867888.66 max: 4727351.03 min: 4058347.69 min: 4126520.88 ==Re-read ==Re-read records: 10 records: 10 avg: 4462147.53 avg: 4363257.75 std: 283546.11 (6.35%) std: 247292.63 (5.67%) max: 4912894.44 max: 4677241.75 min: 4131386.50 min: 4035235.84 ==Reverse Read ==Reverse Read records: 10 records: 10 avg: 4565865.97 avg: 4485818.08 std: 313395.63 (6.86%) std: 248470.10 (5.54%) max: 5232749.16 max: 4789749.94 min: 4185809.62 min: 3963081.34 ==Stride read ==Stride read records: 10 records: 10 avg: 4515981.80 avg: 4418806.01 std: 211192.32 (4.68%) std: 212837.97 (4.82%) max: 4889287.28 max: 4686967.22 min: 4210362.00 min: 4083041.84 ==Random read ==Random read records: 10 records: 10 avg: 4410525.23 avg: 4387093.18 std: 236693.22 (5.37%) std: 235285.23 (5.36%) max: 4713698.47 max: 4669760.62 min: 4057163.62 min: 3952002.16 ==Mixed workload ==Mixed workload records: 10 records: 10 avg: 243234.25 avg: 2818677.27 std: 28505.07 (11.72%) std: 195569.70 (6.94%) max: 288905.23 max: 3126478.11 min: 212473.16 min: 2484150.69 ==Random write ==Random write records: 10 records: 10 avg: 555887.07 avg: 1053057.79 std: 70841.98 (12.74%) std: 35195.36 (3.34%) max: 683188.28 max: 1096125.73 min: 437299.57 min: 992481.93 ==Pwrite ==Pwrite records: 10 records: 10 avg: 501745.93 avg: 810363.09 std: 16373.54 (3.26%) std: 19245.01 (2.37%) max: 518724.52 max: 833359.70 min: 464208.73 min: 765501.87 ==Pread ==Pread records: 10 records: 10 avg: 4539894.60 avg: 4457680.58 std: 197094.66 (4.34%) std: 188965.60 (4.24%) max: 4877170.38 max: 4689905.53 min: 4226326.03 min: 4095739.72 Signed-off-by: Minchan Kim <minchan@kernel.org> Cc: Nitin Gupta <ngupta@vflare.org> Tested-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Cc: Jerome Marchand <jmarchan@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-01-31 07:46:06 +08:00
bool locked = false;
page = bvec->bv_page;
if (is_partial_io(bvec)) {
/*
* This is a partial IO. We need to read the full page
* before to write the changes.
*/
uncmem = kmalloc(PAGE_SIZE, GFP_NOIO);
if (!uncmem) {
ret = -ENOMEM;
goto out;
}
ret = zram_decompress_page(zram, uncmem, index);
if (ret)
goto out;
}
zstrm = zcomp_strm_find(zram->comp);
zram: remove zram->lock in read path and change it with mutex Finally, we separated zram->lock dependency from 32bit stat/ table handling so there is no reason to use rw_semaphore between read and write path so this patch removes the lock from read path totally and changes rw_semaphore with mutex. So, we could do old: read-read: OK read-write: NO write-write: NO Now: read-read: OK read-write: OK write-write: NO The below data proves mixed workload performs well 11 times and there is also enhance on write-write path because current rw-semaphore doesn't support SPIN_ON_OWNER. It's side effect but anyway good thing for us. Write-related tests perform better (from 61% to 1058%) but read path has good/bad(from -2.22% to 1.45%) but they are all marginal within stddev. CPU 12 iozone -t -T -l 12 -u 12 -r 16K -s 60M -I +Z -V 0 ==Initial write ==Initial write records: 10 records: 10 avg: 516189.16 avg: 839907.96 std: 22486.53 (4.36%) std: 47902.17 (5.70%) max: 546970.60 max: 909910.35 min: 481131.54 min: 751148.38 ==Rewrite ==Rewrite records: 10 records: 10 avg: 509527.98 avg: 1050156.37 std: 45799.94 (8.99%) std: 40695.44 (3.88%) max: 611574.27 max: 1111929.26 min: 443679.95 min: 980409.62 ==Read ==Read records: 10 records: 10 avg: 4408624.17 avg: 4472546.76 std: 281152.61 (6.38%) std: 163662.78 (3.66%) max: 4867888.66 max: 4727351.03 min: 4058347.69 min: 4126520.88 ==Re-read ==Re-read records: 10 records: 10 avg: 4462147.53 avg: 4363257.75 std: 283546.11 (6.35%) std: 247292.63 (5.67%) max: 4912894.44 max: 4677241.75 min: 4131386.50 min: 4035235.84 ==Reverse Read ==Reverse Read records: 10 records: 10 avg: 4565865.97 avg: 4485818.08 std: 313395.63 (6.86%) std: 248470.10 (5.54%) max: 5232749.16 max: 4789749.94 min: 4185809.62 min: 3963081.34 ==Stride read ==Stride read records: 10 records: 10 avg: 4515981.80 avg: 4418806.01 std: 211192.32 (4.68%) std: 212837.97 (4.82%) max: 4889287.28 max: 4686967.22 min: 4210362.00 min: 4083041.84 ==Random read ==Random read records: 10 records: 10 avg: 4410525.23 avg: 4387093.18 std: 236693.22 (5.37%) std: 235285.23 (5.36%) max: 4713698.47 max: 4669760.62 min: 4057163.62 min: 3952002.16 ==Mixed workload ==Mixed workload records: 10 records: 10 avg: 243234.25 avg: 2818677.27 std: 28505.07 (11.72%) std: 195569.70 (6.94%) max: 288905.23 max: 3126478.11 min: 212473.16 min: 2484150.69 ==Random write ==Random write records: 10 records: 10 avg: 555887.07 avg: 1053057.79 std: 70841.98 (12.74%) std: 35195.36 (3.34%) max: 683188.28 max: 1096125.73 min: 437299.57 min: 992481.93 ==Pwrite ==Pwrite records: 10 records: 10 avg: 501745.93 avg: 810363.09 std: 16373.54 (3.26%) std: 19245.01 (2.37%) max: 518724.52 max: 833359.70 min: 464208.73 min: 765501.87 ==Pread ==Pread records: 10 records: 10 avg: 4539894.60 avg: 4457680.58 std: 197094.66 (4.34%) std: 188965.60 (4.24%) max: 4877170.38 max: 4689905.53 min: 4226326.03 min: 4095739.72 Signed-off-by: Minchan Kim <minchan@kernel.org> Cc: Nitin Gupta <ngupta@vflare.org> Tested-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Cc: Jerome Marchand <jmarchan@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-01-31 07:46:06 +08:00
locked = true;
user_mem = kmap_atomic(page);
if (is_partial_io(bvec)) {
memcpy(uncmem + offset, user_mem + bvec->bv_offset,
bvec->bv_len);
kunmap_atomic(user_mem);
user_mem = NULL;
} else {
uncmem = user_mem;
}
if (page_zero_filled(uncmem)) {
kunmap_atomic(user_mem);
/* Free memory associated with this sector now. */
write_lock(&zram->meta->tb_lock);
zram_free_page(zram, index);
zram_set_flag(meta, index, ZRAM_ZERO);
write_unlock(&zram->meta->tb_lock);
atomic64_inc(&zram->stats.zero_pages);
ret = 0;
goto out;
}
ret = zcomp_compress(zram->comp, zstrm, uncmem, &clen);
if (!is_partial_io(bvec)) {
kunmap_atomic(user_mem);
user_mem = NULL;
uncmem = NULL;
}
if (unlikely(ret)) {
pr_err("Compression failed! err=%d\n", ret);
goto out;
}
src = zstrm->buffer;
if (unlikely(clen > max_zpage_size)) {
clen = PAGE_SIZE;
if (is_partial_io(bvec))
src = uncmem;
}
Staging: ramzswap: Support generic I/O requests Currently, ramzwap devices (/dev/ramzswapX) can only be used as swap disks since it was hard-coded to consider only the first request in bio vector. Now, we iterate over all the segments in an incoming bio which allows us to handle all kinds of I/O requests. ramzswap devices can still handle PAGE_SIZE aligned and multiple of PAGE_SIZE sized I/O requests only. To ensure that we get always get such requests only, we set following request_queue attributes to PAGE_SIZE: - physical_block_size - logical_block_size - io_min - io_opt Note: physical and logical block sizes were already set equal to PAGE_SIZE and that seems to be sufficient to get PAGE_SIZE aligned I/O. Since we are no longer limited to handling swap requests only, the next few patches rename ramzswap to zram. So, the devices will then be called /dev/zram{0, 1, 2, ...} Usage/Examples: 1) Use as /tmp storage - mkfs.ext4 /dev/zram0 - mount /dev/zram0 /tmp 2) Use as swap: - mkswap /dev/zram0 - swapon /dev/zram0 -p 10 # give highest priority to zram0 Performance: - I/O benchamark done with 'dd' command. Details can be found here: http://code.google.com/p/compcache/wiki/zramperf Summary: - Maximum read speed (approx): - ram disk: 1200 MB/sec - zram disk: 600 MB/sec - Maximum write speed (approx): - ram disk: 500 MB/sec - zram disk: 160 MB/sec Issues: - Double caching: We can potentially waste memory by having two copies of a page -- one in page cache (uncompress) and second in the device memory (compressed). However, during reclaim, clean page cache pages are quickly freed, so this does not seem to be a big problem. - Stale data: Not all filesystems support issuing 'discard' requests to underlying block devices. So, if such filesystems are used over zram devices, we can accumulate lot of stale data in memory. Even for filesystems to do support discard (example, ext4), we need to see how effective it is. - Scalability: There is only one (per-device) de/compression buffer stats. This can lead to significant contention, especially when used for generic (non-swap) purposes. Signed-off-by: Nitin Gupta <ngupta@vflare.org> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2010-06-01 16:01:23 +08:00
handle = zs_malloc(meta->mem_pool, clen);
if (!handle) {
pr_info("Error allocating memory for compressed page: %u, size=%zu\n",
index, clen);
ret = -ENOMEM;
goto out;
}
cmem = zs_map_object(meta->mem_pool, handle, ZS_MM_WO);
if ((clen == PAGE_SIZE) && !is_partial_io(bvec)) {
src = kmap_atomic(page);
copy_page(cmem, src);
kunmap_atomic(src);
} else {
memcpy(cmem, src, clen);
}
zcomp_strm_release(zram->comp, zstrm);
locked = false;
zs_unmap_object(meta->mem_pool, handle);
/*
* Free memory associated with this sector
* before overwriting unused sectors.
*/
write_lock(&zram->meta->tb_lock);
zram_free_page(zram, index);
meta->table[index].handle = handle;
meta->table[index].size = clen;
write_unlock(&zram->meta->tb_lock);
/* Update stats */
atomic64_add(clen, &zram->stats.compr_data_size);
atomic64_inc(&zram->stats.pages_stored);
out:
zram: remove zram->lock in read path and change it with mutex Finally, we separated zram->lock dependency from 32bit stat/ table handling so there is no reason to use rw_semaphore between read and write path so this patch removes the lock from read path totally and changes rw_semaphore with mutex. So, we could do old: read-read: OK read-write: NO write-write: NO Now: read-read: OK read-write: OK write-write: NO The below data proves mixed workload performs well 11 times and there is also enhance on write-write path because current rw-semaphore doesn't support SPIN_ON_OWNER. It's side effect but anyway good thing for us. Write-related tests perform better (from 61% to 1058%) but read path has good/bad(from -2.22% to 1.45%) but they are all marginal within stddev. CPU 12 iozone -t -T -l 12 -u 12 -r 16K -s 60M -I +Z -V 0 ==Initial write ==Initial write records: 10 records: 10 avg: 516189.16 avg: 839907.96 std: 22486.53 (4.36%) std: 47902.17 (5.70%) max: 546970.60 max: 909910.35 min: 481131.54 min: 751148.38 ==Rewrite ==Rewrite records: 10 records: 10 avg: 509527.98 avg: 1050156.37 std: 45799.94 (8.99%) std: 40695.44 (3.88%) max: 611574.27 max: 1111929.26 min: 443679.95 min: 980409.62 ==Read ==Read records: 10 records: 10 avg: 4408624.17 avg: 4472546.76 std: 281152.61 (6.38%) std: 163662.78 (3.66%) max: 4867888.66 max: 4727351.03 min: 4058347.69 min: 4126520.88 ==Re-read ==Re-read records: 10 records: 10 avg: 4462147.53 avg: 4363257.75 std: 283546.11 (6.35%) std: 247292.63 (5.67%) max: 4912894.44 max: 4677241.75 min: 4131386.50 min: 4035235.84 ==Reverse Read ==Reverse Read records: 10 records: 10 avg: 4565865.97 avg: 4485818.08 std: 313395.63 (6.86%) std: 248470.10 (5.54%) max: 5232749.16 max: 4789749.94 min: 4185809.62 min: 3963081.34 ==Stride read ==Stride read records: 10 records: 10 avg: 4515981.80 avg: 4418806.01 std: 211192.32 (4.68%) std: 212837.97 (4.82%) max: 4889287.28 max: 4686967.22 min: 4210362.00 min: 4083041.84 ==Random read ==Random read records: 10 records: 10 avg: 4410525.23 avg: 4387093.18 std: 236693.22 (5.37%) std: 235285.23 (5.36%) max: 4713698.47 max: 4669760.62 min: 4057163.62 min: 3952002.16 ==Mixed workload ==Mixed workload records: 10 records: 10 avg: 243234.25 avg: 2818677.27 std: 28505.07 (11.72%) std: 195569.70 (6.94%) max: 288905.23 max: 3126478.11 min: 212473.16 min: 2484150.69 ==Random write ==Random write records: 10 records: 10 avg: 555887.07 avg: 1053057.79 std: 70841.98 (12.74%) std: 35195.36 (3.34%) max: 683188.28 max: 1096125.73 min: 437299.57 min: 992481.93 ==Pwrite ==Pwrite records: 10 records: 10 avg: 501745.93 avg: 810363.09 std: 16373.54 (3.26%) std: 19245.01 (2.37%) max: 518724.52 max: 833359.70 min: 464208.73 min: 765501.87 ==Pread ==Pread records: 10 records: 10 avg: 4539894.60 avg: 4457680.58 std: 197094.66 (4.34%) std: 188965.60 (4.24%) max: 4877170.38 max: 4689905.53 min: 4226326.03 min: 4095739.72 Signed-off-by: Minchan Kim <minchan@kernel.org> Cc: Nitin Gupta <ngupta@vflare.org> Tested-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Cc: Jerome Marchand <jmarchan@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-01-31 07:46:06 +08:00
if (locked)
zcomp_strm_release(zram->comp, zstrm);
if (is_partial_io(bvec))
kfree(uncmem);
if (ret)
atomic64_inc(&zram->stats.failed_writes);
return ret;
}
static int zram_bvec_rw(struct zram *zram, struct bio_vec *bvec, u32 index,
int offset, struct bio *bio)
{
int ret;
int rw = bio_data_dir(bio);
if (rw == READ) {
atomic64_inc(&zram->stats.num_reads);
ret = zram_bvec_read(zram, bvec, index, offset, bio);
} else {
atomic64_inc(&zram->stats.num_writes);
ret = zram_bvec_write(zram, bvec, index, offset);
}
return ret;
}
static void zram_reset_device(struct zram *zram, bool reset_capacity)
{
size_t index;
struct zram_meta *meta;
down_write(&zram->init_lock);
if (!init_done(zram)) {
up_write(&zram->init_lock);
return;
}
meta = zram->meta;
/* Free all pages that are still in this zram device */
for (index = 0; index < zram->disksize >> PAGE_SHIFT; index++) {
unsigned long handle = meta->table[index].handle;
if (!handle)
continue;
zs_free(meta->mem_pool, handle);
}
zcomp_destroy(zram->comp);
zram_meta_free(zram->meta);
zram->meta = NULL;
/* Reset stats */
memset(&zram->stats, 0, sizeof(zram->stats));
zram->disksize = 0;
if (reset_capacity)
set_capacity(zram->disk, 0);
up_write(&zram->init_lock);
}
static ssize_t disksize_store(struct device *dev,
struct device_attribute *attr, const char *buf, size_t len)
{
u64 disksize;
struct zram_meta *meta;
struct zram *zram = dev_to_zram(dev);
int err;
disksize = memparse(buf, NULL);
if (!disksize)
return -EINVAL;
disksize = PAGE_ALIGN(disksize);
meta = zram_meta_alloc(disksize);
if (!meta)
return -ENOMEM;
down_write(&zram->init_lock);
if (init_done(zram)) {
pr_info("Cannot change disksize for initialized device\n");
err = -EBUSY;
goto out_free_meta;
}
zram->comp = zcomp_create(default_compressor);
if (!zram->comp) {
pr_info("Cannot initialise %s compressing backend\n",
default_compressor);
err = -EINVAL;
goto out_free_meta;
}
zram->meta = meta;
zram->disksize = disksize;
set_capacity(zram->disk, zram->disksize >> SECTOR_SHIFT);
up_write(&zram->init_lock);
return len;
out_free_meta:
up_write(&zram->init_lock);
zram_meta_free(meta);
return err;
}
static ssize_t reset_store(struct device *dev,
struct device_attribute *attr, const char *buf, size_t len)
{
int ret;
unsigned short do_reset;
struct zram *zram;
struct block_device *bdev;
zram = dev_to_zram(dev);
bdev = bdget_disk(zram->disk, 0);
if (!bdev)
return -ENOMEM;
/* Do not reset an active device! */
if (bdev->bd_holders) {
ret = -EBUSY;
goto out;
}
ret = kstrtou16(buf, 10, &do_reset);
if (ret)
goto out;
if (!do_reset) {
ret = -EINVAL;
goto out;
}
/* Make sure all pending I/O is finished */
fsync_bdev(bdev);
bdput(bdev);
zram_reset_device(zram, true);
return len;
out:
bdput(bdev);
return ret;
}
static void __zram_make_request(struct zram *zram, struct bio *bio)
{
block: Convert bio_for_each_segment() to bvec_iter More prep work for immutable biovecs - with immutable bvecs drivers won't be able to use the biovec directly, they'll need to use helpers that take into account bio->bi_iter.bi_bvec_done. This updates callers for the new usage without changing the implementation yet. Signed-off-by: Kent Overstreet <kmo@daterainc.com> Cc: Jens Axboe <axboe@kernel.dk> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: "Ed L. Cashin" <ecashin@coraid.com> Cc: Nick Piggin <npiggin@kernel.dk> Cc: Lars Ellenberg <drbd-dev@lists.linbit.com> Cc: Jiri Kosina <jkosina@suse.cz> Cc: Paul Clements <Paul.Clements@steeleye.com> Cc: Jim Paris <jim@jtan.com> Cc: Geoff Levand <geoff@infradead.org> Cc: Yehuda Sadeh <yehuda@inktank.com> Cc: Sage Weil <sage@inktank.com> Cc: Alex Elder <elder@inktank.com> Cc: ceph-devel@vger.kernel.org Cc: Joshua Morris <josh.h.morris@us.ibm.com> Cc: Philip Kelleher <pjk1939@linux.vnet.ibm.com> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Neil Brown <neilb@suse.de> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: linux390@de.ibm.com Cc: Nagalakshmi Nandigama <Nagalakshmi.Nandigama@lsi.com> Cc: Sreekanth Reddy <Sreekanth.Reddy@lsi.com> Cc: support@lsi.com Cc: "James E.J. Bottomley" <JBottomley@parallels.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Steven Whitehouse <swhiteho@redhat.com> Cc: Herton Ronaldo Krzesinski <herton.krzesinski@canonical.com> Cc: Tejun Heo <tj@kernel.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Guo Chao <yan@linux.vnet.ibm.com> Cc: Asai Thambi S P <asamymuthupa@micron.com> Cc: Selvan Mani <smani@micron.com> Cc: Sam Bradshaw <sbradshaw@micron.com> Cc: Matthew Wilcox <matthew.r.wilcox@intel.com> Cc: Keith Busch <keith.busch@intel.com> Cc: Stephen Hemminger <shemminger@vyatta.com> Cc: Quoc-Son Anh <quoc-sonx.anh@intel.com> Cc: Sebastian Ott <sebott@linux.vnet.ibm.com> Cc: Nitin Gupta <ngupta@vflare.org> Cc: Minchan Kim <minchan@kernel.org> Cc: Jerome Marchand <jmarchan@redhat.com> Cc: Seth Jennings <sjenning@linux.vnet.ibm.com> Cc: "Martin K. Petersen" <martin.petersen@oracle.com> Cc: Mike Snitzer <snitzer@redhat.com> Cc: Vivek Goyal <vgoyal@redhat.com> Cc: "Darrick J. Wong" <darrick.wong@oracle.com> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: Jan Kara <jack@suse.cz> Cc: linux-m68k@lists.linux-m68k.org Cc: linuxppc-dev@lists.ozlabs.org Cc: drbd-user@lists.linbit.com Cc: nbd-general@lists.sourceforge.net Cc: cbe-oss-dev@lists.ozlabs.org Cc: xen-devel@lists.xensource.com Cc: virtualization@lists.linux-foundation.org Cc: linux-raid@vger.kernel.org Cc: linux-s390@vger.kernel.org Cc: DL-MPTFusionLinux@lsi.com Cc: linux-scsi@vger.kernel.org Cc: devel@driverdev.osuosl.org Cc: linux-fsdevel@vger.kernel.org Cc: cluster-devel@redhat.com Cc: linux-mm@kvack.org Acked-by: Geoff Levand <geoff@infradead.org>
2013-11-24 09:19:00 +08:00
int offset;
u32 index;
block: Convert bio_for_each_segment() to bvec_iter More prep work for immutable biovecs - with immutable bvecs drivers won't be able to use the biovec directly, they'll need to use helpers that take into account bio->bi_iter.bi_bvec_done. This updates callers for the new usage without changing the implementation yet. Signed-off-by: Kent Overstreet <kmo@daterainc.com> Cc: Jens Axboe <axboe@kernel.dk> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: "Ed L. Cashin" <ecashin@coraid.com> Cc: Nick Piggin <npiggin@kernel.dk> Cc: Lars Ellenberg <drbd-dev@lists.linbit.com> Cc: Jiri Kosina <jkosina@suse.cz> Cc: Paul Clements <Paul.Clements@steeleye.com> Cc: Jim Paris <jim@jtan.com> Cc: Geoff Levand <geoff@infradead.org> Cc: Yehuda Sadeh <yehuda@inktank.com> Cc: Sage Weil <sage@inktank.com> Cc: Alex Elder <elder@inktank.com> Cc: ceph-devel@vger.kernel.org Cc: Joshua Morris <josh.h.morris@us.ibm.com> Cc: Philip Kelleher <pjk1939@linux.vnet.ibm.com> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Neil Brown <neilb@suse.de> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: linux390@de.ibm.com Cc: Nagalakshmi Nandigama <Nagalakshmi.Nandigama@lsi.com> Cc: Sreekanth Reddy <Sreekanth.Reddy@lsi.com> Cc: support@lsi.com Cc: "James E.J. Bottomley" <JBottomley@parallels.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Steven Whitehouse <swhiteho@redhat.com> Cc: Herton Ronaldo Krzesinski <herton.krzesinski@canonical.com> Cc: Tejun Heo <tj@kernel.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Guo Chao <yan@linux.vnet.ibm.com> Cc: Asai Thambi S P <asamymuthupa@micron.com> Cc: Selvan Mani <smani@micron.com> Cc: Sam Bradshaw <sbradshaw@micron.com> Cc: Matthew Wilcox <matthew.r.wilcox@intel.com> Cc: Keith Busch <keith.busch@intel.com> Cc: Stephen Hemminger <shemminger@vyatta.com> Cc: Quoc-Son Anh <quoc-sonx.anh@intel.com> Cc: Sebastian Ott <sebott@linux.vnet.ibm.com> Cc: Nitin Gupta <ngupta@vflare.org> Cc: Minchan Kim <minchan@kernel.org> Cc: Jerome Marchand <jmarchan@redhat.com> Cc: Seth Jennings <sjenning@linux.vnet.ibm.com> Cc: "Martin K. Petersen" <martin.petersen@oracle.com> Cc: Mike Snitzer <snitzer@redhat.com> Cc: Vivek Goyal <vgoyal@redhat.com> Cc: "Darrick J. Wong" <darrick.wong@oracle.com> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: Jan Kara <jack@suse.cz> Cc: linux-m68k@lists.linux-m68k.org Cc: linuxppc-dev@lists.ozlabs.org Cc: drbd-user@lists.linbit.com Cc: nbd-general@lists.sourceforge.net Cc: cbe-oss-dev@lists.ozlabs.org Cc: xen-devel@lists.xensource.com Cc: virtualization@lists.linux-foundation.org Cc: linux-raid@vger.kernel.org Cc: linux-s390@vger.kernel.org Cc: DL-MPTFusionLinux@lsi.com Cc: linux-scsi@vger.kernel.org Cc: devel@driverdev.osuosl.org Cc: linux-fsdevel@vger.kernel.org Cc: cluster-devel@redhat.com Cc: linux-mm@kvack.org Acked-by: Geoff Levand <geoff@infradead.org>
2013-11-24 09:19:00 +08:00
struct bio_vec bvec;
struct bvec_iter iter;
block: Abstract out bvec iterator Immutable biovecs are going to require an explicit iterator. To implement immutable bvecs, a later patch is going to add a bi_bvec_done member to this struct; for now, this patch effectively just renames things. Signed-off-by: Kent Overstreet <kmo@daterainc.com> Cc: Jens Axboe <axboe@kernel.dk> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: "Ed L. Cashin" <ecashin@coraid.com> Cc: Nick Piggin <npiggin@kernel.dk> Cc: Lars Ellenberg <drbd-dev@lists.linbit.com> Cc: Jiri Kosina <jkosina@suse.cz> Cc: Matthew Wilcox <willy@linux.intel.com> Cc: Geoff Levand <geoff@infradead.org> Cc: Yehuda Sadeh <yehuda@inktank.com> Cc: Sage Weil <sage@inktank.com> Cc: Alex Elder <elder@inktank.com> Cc: ceph-devel@vger.kernel.org Cc: Joshua Morris <josh.h.morris@us.ibm.com> Cc: Philip Kelleher <pjk1939@linux.vnet.ibm.com> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: "Michael S. Tsirkin" <mst@redhat.com> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Neil Brown <neilb@suse.de> Cc: Alasdair Kergon <agk@redhat.com> Cc: Mike Snitzer <snitzer@redhat.com> Cc: dm-devel@redhat.com Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: linux390@de.ibm.com Cc: Boaz Harrosh <bharrosh@panasas.com> Cc: Benny Halevy <bhalevy@tonian.com> Cc: "James E.J. Bottomley" <JBottomley@parallels.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: "Nicholas A. Bellinger" <nab@linux-iscsi.org> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Chris Mason <chris.mason@fusionio.com> Cc: "Theodore Ts'o" <tytso@mit.edu> Cc: Andreas Dilger <adilger.kernel@dilger.ca> Cc: Jaegeuk Kim <jaegeuk.kim@samsung.com> Cc: Steven Whitehouse <swhiteho@redhat.com> Cc: Dave Kleikamp <shaggy@kernel.org> Cc: Joern Engel <joern@logfs.org> Cc: Prasad Joshi <prasadjoshi.linux@gmail.com> Cc: Trond Myklebust <Trond.Myklebust@netapp.com> Cc: KONISHI Ryusuke <konishi.ryusuke@lab.ntt.co.jp> Cc: Mark Fasheh <mfasheh@suse.com> Cc: Joel Becker <jlbec@evilplan.org> Cc: Ben Myers <bpm@sgi.com> Cc: xfs@oss.sgi.com Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Len Brown <len.brown@intel.com> Cc: Pavel Machek <pavel@ucw.cz> Cc: "Rafael J. Wysocki" <rjw@sisk.pl> Cc: Herton Ronaldo Krzesinski <herton.krzesinski@canonical.com> Cc: Ben Hutchings <ben@decadent.org.uk> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Guo Chao <yan@linux.vnet.ibm.com> Cc: Tejun Heo <tj@kernel.org> Cc: Asai Thambi S P <asamymuthupa@micron.com> Cc: Selvan Mani <smani@micron.com> Cc: Sam Bradshaw <sbradshaw@micron.com> Cc: Wei Yongjun <yongjun_wei@trendmicro.com.cn> Cc: "Roger Pau Monné" <roger.pau@citrix.com> Cc: Jan Beulich <jbeulich@suse.com> Cc: Stefano Stabellini <stefano.stabellini@eu.citrix.com> Cc: Ian Campbell <Ian.Campbell@citrix.com> Cc: Sebastian Ott <sebott@linux.vnet.ibm.com> Cc: Christian Borntraeger <borntraeger@de.ibm.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Jiang Liu <jiang.liu@huawei.com> Cc: Nitin Gupta <ngupta@vflare.org> Cc: Jerome Marchand <jmarchand@redhat.com> Cc: Joe Perches <joe@perches.com> Cc: Peng Tao <tao.peng@emc.com> Cc: Andy Adamson <andros@netapp.com> Cc: fanchaoting <fanchaoting@cn.fujitsu.com> Cc: Jie Liu <jeff.liu@oracle.com> Cc: Sunil Mushran <sunil.mushran@gmail.com> Cc: "Martin K. Petersen" <martin.petersen@oracle.com> Cc: Namjae Jeon <namjae.jeon@samsung.com> Cc: Pankaj Kumar <pankaj.km@samsung.com> Cc: Dan Magenheimer <dan.magenheimer@oracle.com> Cc: Mel Gorman <mgorman@suse.de>6
2013-10-12 06:44:27 +08:00
index = bio->bi_iter.bi_sector >> SECTORS_PER_PAGE_SHIFT;
offset = (bio->bi_iter.bi_sector &
(SECTORS_PER_PAGE - 1)) << SECTOR_SHIFT;
block: Convert bio_for_each_segment() to bvec_iter More prep work for immutable biovecs - with immutable bvecs drivers won't be able to use the biovec directly, they'll need to use helpers that take into account bio->bi_iter.bi_bvec_done. This updates callers for the new usage without changing the implementation yet. Signed-off-by: Kent Overstreet <kmo@daterainc.com> Cc: Jens Axboe <axboe@kernel.dk> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: "Ed L. Cashin" <ecashin@coraid.com> Cc: Nick Piggin <npiggin@kernel.dk> Cc: Lars Ellenberg <drbd-dev@lists.linbit.com> Cc: Jiri Kosina <jkosina@suse.cz> Cc: Paul Clements <Paul.Clements@steeleye.com> Cc: Jim Paris <jim@jtan.com> Cc: Geoff Levand <geoff@infradead.org> Cc: Yehuda Sadeh <yehuda@inktank.com> Cc: Sage Weil <sage@inktank.com> Cc: Alex Elder <elder@inktank.com> Cc: ceph-devel@vger.kernel.org Cc: Joshua Morris <josh.h.morris@us.ibm.com> Cc: Philip Kelleher <pjk1939@linux.vnet.ibm.com> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Neil Brown <neilb@suse.de> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: linux390@de.ibm.com Cc: Nagalakshmi Nandigama <Nagalakshmi.Nandigama@lsi.com> Cc: Sreekanth Reddy <Sreekanth.Reddy@lsi.com> Cc: support@lsi.com Cc: "James E.J. Bottomley" <JBottomley@parallels.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Steven Whitehouse <swhiteho@redhat.com> Cc: Herton Ronaldo Krzesinski <herton.krzesinski@canonical.com> Cc: Tejun Heo <tj@kernel.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Guo Chao <yan@linux.vnet.ibm.com> Cc: Asai Thambi S P <asamymuthupa@micron.com> Cc: Selvan Mani <smani@micron.com> Cc: Sam Bradshaw <sbradshaw@micron.com> Cc: Matthew Wilcox <matthew.r.wilcox@intel.com> Cc: Keith Busch <keith.busch@intel.com> Cc: Stephen Hemminger <shemminger@vyatta.com> Cc: Quoc-Son Anh <quoc-sonx.anh@intel.com> Cc: Sebastian Ott <sebott@linux.vnet.ibm.com> Cc: Nitin Gupta <ngupta@vflare.org> Cc: Minchan Kim <minchan@kernel.org> Cc: Jerome Marchand <jmarchan@redhat.com> Cc: Seth Jennings <sjenning@linux.vnet.ibm.com> Cc: "Martin K. Petersen" <martin.petersen@oracle.com> Cc: Mike Snitzer <snitzer@redhat.com> Cc: Vivek Goyal <vgoyal@redhat.com> Cc: "Darrick J. Wong" <darrick.wong@oracle.com> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: Jan Kara <jack@suse.cz> Cc: linux-m68k@lists.linux-m68k.org Cc: linuxppc-dev@lists.ozlabs.org Cc: drbd-user@lists.linbit.com Cc: nbd-general@lists.sourceforge.net Cc: cbe-oss-dev@lists.ozlabs.org Cc: xen-devel@lists.xensource.com Cc: virtualization@lists.linux-foundation.org Cc: linux-raid@vger.kernel.org Cc: linux-s390@vger.kernel.org Cc: DL-MPTFusionLinux@lsi.com Cc: linux-scsi@vger.kernel.org Cc: devel@driverdev.osuosl.org Cc: linux-fsdevel@vger.kernel.org Cc: cluster-devel@redhat.com Cc: linux-mm@kvack.org Acked-by: Geoff Levand <geoff@infradead.org>
2013-11-24 09:19:00 +08:00
bio_for_each_segment(bvec, bio, iter) {
int max_transfer_size = PAGE_SIZE - offset;
block: Convert bio_for_each_segment() to bvec_iter More prep work for immutable biovecs - with immutable bvecs drivers won't be able to use the biovec directly, they'll need to use helpers that take into account bio->bi_iter.bi_bvec_done. This updates callers for the new usage without changing the implementation yet. Signed-off-by: Kent Overstreet <kmo@daterainc.com> Cc: Jens Axboe <axboe@kernel.dk> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: "Ed L. Cashin" <ecashin@coraid.com> Cc: Nick Piggin <npiggin@kernel.dk> Cc: Lars Ellenberg <drbd-dev@lists.linbit.com> Cc: Jiri Kosina <jkosina@suse.cz> Cc: Paul Clements <Paul.Clements@steeleye.com> Cc: Jim Paris <jim@jtan.com> Cc: Geoff Levand <geoff@infradead.org> Cc: Yehuda Sadeh <yehuda@inktank.com> Cc: Sage Weil <sage@inktank.com> Cc: Alex Elder <elder@inktank.com> Cc: ceph-devel@vger.kernel.org Cc: Joshua Morris <josh.h.morris@us.ibm.com> Cc: Philip Kelleher <pjk1939@linux.vnet.ibm.com> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Neil Brown <neilb@suse.de> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: linux390@de.ibm.com Cc: Nagalakshmi Nandigama <Nagalakshmi.Nandigama@lsi.com> Cc: Sreekanth Reddy <Sreekanth.Reddy@lsi.com> Cc: support@lsi.com Cc: "James E.J. Bottomley" <JBottomley@parallels.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Steven Whitehouse <swhiteho@redhat.com> Cc: Herton Ronaldo Krzesinski <herton.krzesinski@canonical.com> Cc: Tejun Heo <tj@kernel.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Guo Chao <yan@linux.vnet.ibm.com> Cc: Asai Thambi S P <asamymuthupa@micron.com> Cc: Selvan Mani <smani@micron.com> Cc: Sam Bradshaw <sbradshaw@micron.com> Cc: Matthew Wilcox <matthew.r.wilcox@intel.com> Cc: Keith Busch <keith.busch@intel.com> Cc: Stephen Hemminger <shemminger@vyatta.com> Cc: Quoc-Son Anh <quoc-sonx.anh@intel.com> Cc: Sebastian Ott <sebott@linux.vnet.ibm.com> Cc: Nitin Gupta <ngupta@vflare.org> Cc: Minchan Kim <minchan@kernel.org> Cc: Jerome Marchand <jmarchan@redhat.com> Cc: Seth Jennings <sjenning@linux.vnet.ibm.com> Cc: "Martin K. Petersen" <martin.petersen@oracle.com> Cc: Mike Snitzer <snitzer@redhat.com> Cc: Vivek Goyal <vgoyal@redhat.com> Cc: "Darrick J. Wong" <darrick.wong@oracle.com> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: Jan Kara <jack@suse.cz> Cc: linux-m68k@lists.linux-m68k.org Cc: linuxppc-dev@lists.ozlabs.org Cc: drbd-user@lists.linbit.com Cc: nbd-general@lists.sourceforge.net Cc: cbe-oss-dev@lists.ozlabs.org Cc: xen-devel@lists.xensource.com Cc: virtualization@lists.linux-foundation.org Cc: linux-raid@vger.kernel.org Cc: linux-s390@vger.kernel.org Cc: DL-MPTFusionLinux@lsi.com Cc: linux-scsi@vger.kernel.org Cc: devel@driverdev.osuosl.org Cc: linux-fsdevel@vger.kernel.org Cc: cluster-devel@redhat.com Cc: linux-mm@kvack.org Acked-by: Geoff Levand <geoff@infradead.org>
2013-11-24 09:19:00 +08:00
if (bvec.bv_len > max_transfer_size) {
/*
* zram_bvec_rw() can only make operation on a single
* zram page. Split the bio vector.
*/
struct bio_vec bv;
block: Convert bio_for_each_segment() to bvec_iter More prep work for immutable biovecs - with immutable bvecs drivers won't be able to use the biovec directly, they'll need to use helpers that take into account bio->bi_iter.bi_bvec_done. This updates callers for the new usage without changing the implementation yet. Signed-off-by: Kent Overstreet <kmo@daterainc.com> Cc: Jens Axboe <axboe@kernel.dk> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: "Ed L. Cashin" <ecashin@coraid.com> Cc: Nick Piggin <npiggin@kernel.dk> Cc: Lars Ellenberg <drbd-dev@lists.linbit.com> Cc: Jiri Kosina <jkosina@suse.cz> Cc: Paul Clements <Paul.Clements@steeleye.com> Cc: Jim Paris <jim@jtan.com> Cc: Geoff Levand <geoff@infradead.org> Cc: Yehuda Sadeh <yehuda@inktank.com> Cc: Sage Weil <sage@inktank.com> Cc: Alex Elder <elder@inktank.com> Cc: ceph-devel@vger.kernel.org Cc: Joshua Morris <josh.h.morris@us.ibm.com> Cc: Philip Kelleher <pjk1939@linux.vnet.ibm.com> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Neil Brown <neilb@suse.de> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: linux390@de.ibm.com Cc: Nagalakshmi Nandigama <Nagalakshmi.Nandigama@lsi.com> Cc: Sreekanth Reddy <Sreekanth.Reddy@lsi.com> Cc: support@lsi.com Cc: "James E.J. Bottomley" <JBottomley@parallels.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Steven Whitehouse <swhiteho@redhat.com> Cc: Herton Ronaldo Krzesinski <herton.krzesinski@canonical.com> Cc: Tejun Heo <tj@kernel.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Guo Chao <yan@linux.vnet.ibm.com> Cc: Asai Thambi S P <asamymuthupa@micron.com> Cc: Selvan Mani <smani@micron.com> Cc: Sam Bradshaw <sbradshaw@micron.com> Cc: Matthew Wilcox <matthew.r.wilcox@intel.com> Cc: Keith Busch <keith.busch@intel.com> Cc: Stephen Hemminger <shemminger@vyatta.com> Cc: Quoc-Son Anh <quoc-sonx.anh@intel.com> Cc: Sebastian Ott <sebott@linux.vnet.ibm.com> Cc: Nitin Gupta <ngupta@vflare.org> Cc: Minchan Kim <minchan@kernel.org> Cc: Jerome Marchand <jmarchan@redhat.com> Cc: Seth Jennings <sjenning@linux.vnet.ibm.com> Cc: "Martin K. Petersen" <martin.petersen@oracle.com> Cc: Mike Snitzer <snitzer@redhat.com> Cc: Vivek Goyal <vgoyal@redhat.com> Cc: "Darrick J. Wong" <darrick.wong@oracle.com> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: Jan Kara <jack@suse.cz> Cc: linux-m68k@lists.linux-m68k.org Cc: linuxppc-dev@lists.ozlabs.org Cc: drbd-user@lists.linbit.com Cc: nbd-general@lists.sourceforge.net Cc: cbe-oss-dev@lists.ozlabs.org Cc: xen-devel@lists.xensource.com Cc: virtualization@lists.linux-foundation.org Cc: linux-raid@vger.kernel.org Cc: linux-s390@vger.kernel.org Cc: DL-MPTFusionLinux@lsi.com Cc: linux-scsi@vger.kernel.org Cc: devel@driverdev.osuosl.org Cc: linux-fsdevel@vger.kernel.org Cc: cluster-devel@redhat.com Cc: linux-mm@kvack.org Acked-by: Geoff Levand <geoff@infradead.org>
2013-11-24 09:19:00 +08:00
bv.bv_page = bvec.bv_page;
bv.bv_len = max_transfer_size;
block: Convert bio_for_each_segment() to bvec_iter More prep work for immutable biovecs - with immutable bvecs drivers won't be able to use the biovec directly, they'll need to use helpers that take into account bio->bi_iter.bi_bvec_done. This updates callers for the new usage without changing the implementation yet. Signed-off-by: Kent Overstreet <kmo@daterainc.com> Cc: Jens Axboe <axboe@kernel.dk> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: "Ed L. Cashin" <ecashin@coraid.com> Cc: Nick Piggin <npiggin@kernel.dk> Cc: Lars Ellenberg <drbd-dev@lists.linbit.com> Cc: Jiri Kosina <jkosina@suse.cz> Cc: Paul Clements <Paul.Clements@steeleye.com> Cc: Jim Paris <jim@jtan.com> Cc: Geoff Levand <geoff@infradead.org> Cc: Yehuda Sadeh <yehuda@inktank.com> Cc: Sage Weil <sage@inktank.com> Cc: Alex Elder <elder@inktank.com> Cc: ceph-devel@vger.kernel.org Cc: Joshua Morris <josh.h.morris@us.ibm.com> Cc: Philip Kelleher <pjk1939@linux.vnet.ibm.com> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Neil Brown <neilb@suse.de> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: linux390@de.ibm.com Cc: Nagalakshmi Nandigama <Nagalakshmi.Nandigama@lsi.com> Cc: Sreekanth Reddy <Sreekanth.Reddy@lsi.com> Cc: support@lsi.com Cc: "James E.J. Bottomley" <JBottomley@parallels.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Steven Whitehouse <swhiteho@redhat.com> Cc: Herton Ronaldo Krzesinski <herton.krzesinski@canonical.com> Cc: Tejun Heo <tj@kernel.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Guo Chao <yan@linux.vnet.ibm.com> Cc: Asai Thambi S P <asamymuthupa@micron.com> Cc: Selvan Mani <smani@micron.com> Cc: Sam Bradshaw <sbradshaw@micron.com> Cc: Matthew Wilcox <matthew.r.wilcox@intel.com> Cc: Keith Busch <keith.busch@intel.com> Cc: Stephen Hemminger <shemminger@vyatta.com> Cc: Quoc-Son Anh <quoc-sonx.anh@intel.com> Cc: Sebastian Ott <sebott@linux.vnet.ibm.com> Cc: Nitin Gupta <ngupta@vflare.org> Cc: Minchan Kim <minchan@kernel.org> Cc: Jerome Marchand <jmarchan@redhat.com> Cc: Seth Jennings <sjenning@linux.vnet.ibm.com> Cc: "Martin K. Petersen" <martin.petersen@oracle.com> Cc: Mike Snitzer <snitzer@redhat.com> Cc: Vivek Goyal <vgoyal@redhat.com> Cc: "Darrick J. Wong" <darrick.wong@oracle.com> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: Jan Kara <jack@suse.cz> Cc: linux-m68k@lists.linux-m68k.org Cc: linuxppc-dev@lists.ozlabs.org Cc: drbd-user@lists.linbit.com Cc: nbd-general@lists.sourceforge.net Cc: cbe-oss-dev@lists.ozlabs.org Cc: xen-devel@lists.xensource.com Cc: virtualization@lists.linux-foundation.org Cc: linux-raid@vger.kernel.org Cc: linux-s390@vger.kernel.org Cc: DL-MPTFusionLinux@lsi.com Cc: linux-scsi@vger.kernel.org Cc: devel@driverdev.osuosl.org Cc: linux-fsdevel@vger.kernel.org Cc: cluster-devel@redhat.com Cc: linux-mm@kvack.org Acked-by: Geoff Levand <geoff@infradead.org>
2013-11-24 09:19:00 +08:00
bv.bv_offset = bvec.bv_offset;
if (zram_bvec_rw(zram, &bv, index, offset, bio) < 0)
goto out;
block: Convert bio_for_each_segment() to bvec_iter More prep work for immutable biovecs - with immutable bvecs drivers won't be able to use the biovec directly, they'll need to use helpers that take into account bio->bi_iter.bi_bvec_done. This updates callers for the new usage without changing the implementation yet. Signed-off-by: Kent Overstreet <kmo@daterainc.com> Cc: Jens Axboe <axboe@kernel.dk> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: "Ed L. Cashin" <ecashin@coraid.com> Cc: Nick Piggin <npiggin@kernel.dk> Cc: Lars Ellenberg <drbd-dev@lists.linbit.com> Cc: Jiri Kosina <jkosina@suse.cz> Cc: Paul Clements <Paul.Clements@steeleye.com> Cc: Jim Paris <jim@jtan.com> Cc: Geoff Levand <geoff@infradead.org> Cc: Yehuda Sadeh <yehuda@inktank.com> Cc: Sage Weil <sage@inktank.com> Cc: Alex Elder <elder@inktank.com> Cc: ceph-devel@vger.kernel.org Cc: Joshua Morris <josh.h.morris@us.ibm.com> Cc: Philip Kelleher <pjk1939@linux.vnet.ibm.com> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Neil Brown <neilb@suse.de> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: linux390@de.ibm.com Cc: Nagalakshmi Nandigama <Nagalakshmi.Nandigama@lsi.com> Cc: Sreekanth Reddy <Sreekanth.Reddy@lsi.com> Cc: support@lsi.com Cc: "James E.J. Bottomley" <JBottomley@parallels.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Steven Whitehouse <swhiteho@redhat.com> Cc: Herton Ronaldo Krzesinski <herton.krzesinski@canonical.com> Cc: Tejun Heo <tj@kernel.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Guo Chao <yan@linux.vnet.ibm.com> Cc: Asai Thambi S P <asamymuthupa@micron.com> Cc: Selvan Mani <smani@micron.com> Cc: Sam Bradshaw <sbradshaw@micron.com> Cc: Matthew Wilcox <matthew.r.wilcox@intel.com> Cc: Keith Busch <keith.busch@intel.com> Cc: Stephen Hemminger <shemminger@vyatta.com> Cc: Quoc-Son Anh <quoc-sonx.anh@intel.com> Cc: Sebastian Ott <sebott@linux.vnet.ibm.com> Cc: Nitin Gupta <ngupta@vflare.org> Cc: Minchan Kim <minchan@kernel.org> Cc: Jerome Marchand <jmarchan@redhat.com> Cc: Seth Jennings <sjenning@linux.vnet.ibm.com> Cc: "Martin K. Petersen" <martin.petersen@oracle.com> Cc: Mike Snitzer <snitzer@redhat.com> Cc: Vivek Goyal <vgoyal@redhat.com> Cc: "Darrick J. Wong" <darrick.wong@oracle.com> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: Jan Kara <jack@suse.cz> Cc: linux-m68k@lists.linux-m68k.org Cc: linuxppc-dev@lists.ozlabs.org Cc: drbd-user@lists.linbit.com Cc: nbd-general@lists.sourceforge.net Cc: cbe-oss-dev@lists.ozlabs.org Cc: xen-devel@lists.xensource.com Cc: virtualization@lists.linux-foundation.org Cc: linux-raid@vger.kernel.org Cc: linux-s390@vger.kernel.org Cc: DL-MPTFusionLinux@lsi.com Cc: linux-scsi@vger.kernel.org Cc: devel@driverdev.osuosl.org Cc: linux-fsdevel@vger.kernel.org Cc: cluster-devel@redhat.com Cc: linux-mm@kvack.org Acked-by: Geoff Levand <geoff@infradead.org>
2013-11-24 09:19:00 +08:00
bv.bv_len = bvec.bv_len - max_transfer_size;
bv.bv_offset += max_transfer_size;
if (zram_bvec_rw(zram, &bv, index + 1, 0, bio) < 0)
goto out;
} else
if (zram_bvec_rw(zram, &bvec, index, offset, bio) < 0)
goto out;
block: Convert bio_for_each_segment() to bvec_iter More prep work for immutable biovecs - with immutable bvecs drivers won't be able to use the biovec directly, they'll need to use helpers that take into account bio->bi_iter.bi_bvec_done. This updates callers for the new usage without changing the implementation yet. Signed-off-by: Kent Overstreet <kmo@daterainc.com> Cc: Jens Axboe <axboe@kernel.dk> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: "Ed L. Cashin" <ecashin@coraid.com> Cc: Nick Piggin <npiggin@kernel.dk> Cc: Lars Ellenberg <drbd-dev@lists.linbit.com> Cc: Jiri Kosina <jkosina@suse.cz> Cc: Paul Clements <Paul.Clements@steeleye.com> Cc: Jim Paris <jim@jtan.com> Cc: Geoff Levand <geoff@infradead.org> Cc: Yehuda Sadeh <yehuda@inktank.com> Cc: Sage Weil <sage@inktank.com> Cc: Alex Elder <elder@inktank.com> Cc: ceph-devel@vger.kernel.org Cc: Joshua Morris <josh.h.morris@us.ibm.com> Cc: Philip Kelleher <pjk1939@linux.vnet.ibm.com> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Neil Brown <neilb@suse.de> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: linux390@de.ibm.com Cc: Nagalakshmi Nandigama <Nagalakshmi.Nandigama@lsi.com> Cc: Sreekanth Reddy <Sreekanth.Reddy@lsi.com> Cc: support@lsi.com Cc: "James E.J. Bottomley" <JBottomley@parallels.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Steven Whitehouse <swhiteho@redhat.com> Cc: Herton Ronaldo Krzesinski <herton.krzesinski@canonical.com> Cc: Tejun Heo <tj@kernel.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Guo Chao <yan@linux.vnet.ibm.com> Cc: Asai Thambi S P <asamymuthupa@micron.com> Cc: Selvan Mani <smani@micron.com> Cc: Sam Bradshaw <sbradshaw@micron.com> Cc: Matthew Wilcox <matthew.r.wilcox@intel.com> Cc: Keith Busch <keith.busch@intel.com> Cc: Stephen Hemminger <shemminger@vyatta.com> Cc: Quoc-Son Anh <quoc-sonx.anh@intel.com> Cc: Sebastian Ott <sebott@linux.vnet.ibm.com> Cc: Nitin Gupta <ngupta@vflare.org> Cc: Minchan Kim <minchan@kernel.org> Cc: Jerome Marchand <jmarchan@redhat.com> Cc: Seth Jennings <sjenning@linux.vnet.ibm.com> Cc: "Martin K. Petersen" <martin.petersen@oracle.com> Cc: Mike Snitzer <snitzer@redhat.com> Cc: Vivek Goyal <vgoyal@redhat.com> Cc: "Darrick J. Wong" <darrick.wong@oracle.com> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: Jan Kara <jack@suse.cz> Cc: linux-m68k@lists.linux-m68k.org Cc: linuxppc-dev@lists.ozlabs.org Cc: drbd-user@lists.linbit.com Cc: nbd-general@lists.sourceforge.net Cc: cbe-oss-dev@lists.ozlabs.org Cc: xen-devel@lists.xensource.com Cc: virtualization@lists.linux-foundation.org Cc: linux-raid@vger.kernel.org Cc: linux-s390@vger.kernel.org Cc: DL-MPTFusionLinux@lsi.com Cc: linux-scsi@vger.kernel.org Cc: devel@driverdev.osuosl.org Cc: linux-fsdevel@vger.kernel.org Cc: cluster-devel@redhat.com Cc: linux-mm@kvack.org Acked-by: Geoff Levand <geoff@infradead.org>
2013-11-24 09:19:00 +08:00
update_position(&index, &offset, &bvec);
Staging: ramzswap: Support generic I/O requests Currently, ramzwap devices (/dev/ramzswapX) can only be used as swap disks since it was hard-coded to consider only the first request in bio vector. Now, we iterate over all the segments in an incoming bio which allows us to handle all kinds of I/O requests. ramzswap devices can still handle PAGE_SIZE aligned and multiple of PAGE_SIZE sized I/O requests only. To ensure that we get always get such requests only, we set following request_queue attributes to PAGE_SIZE: - physical_block_size - logical_block_size - io_min - io_opt Note: physical and logical block sizes were already set equal to PAGE_SIZE and that seems to be sufficient to get PAGE_SIZE aligned I/O. Since we are no longer limited to handling swap requests only, the next few patches rename ramzswap to zram. So, the devices will then be called /dev/zram{0, 1, 2, ...} Usage/Examples: 1) Use as /tmp storage - mkfs.ext4 /dev/zram0 - mount /dev/zram0 /tmp 2) Use as swap: - mkswap /dev/zram0 - swapon /dev/zram0 -p 10 # give highest priority to zram0 Performance: - I/O benchamark done with 'dd' command. Details can be found here: http://code.google.com/p/compcache/wiki/zramperf Summary: - Maximum read speed (approx): - ram disk: 1200 MB/sec - zram disk: 600 MB/sec - Maximum write speed (approx): - ram disk: 500 MB/sec - zram disk: 160 MB/sec Issues: - Double caching: We can potentially waste memory by having two copies of a page -- one in page cache (uncompress) and second in the device memory (compressed). However, during reclaim, clean page cache pages are quickly freed, so this does not seem to be a big problem. - Stale data: Not all filesystems support issuing 'discard' requests to underlying block devices. So, if such filesystems are used over zram devices, we can accumulate lot of stale data in memory. Even for filesystems to do support discard (example, ext4), we need to see how effective it is. - Scalability: There is only one (per-device) de/compression buffer stats. This can lead to significant contention, especially when used for generic (non-swap) purposes. Signed-off-by: Nitin Gupta <ngupta@vflare.org> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2010-06-01 16:01:23 +08:00
}
set_bit(BIO_UPTODATE, &bio->bi_flags);
bio_endio(bio, 0);
return;
out:
bio_io_error(bio);
}
/*
* Handler function for all zram I/O requests.
*/
static void zram_make_request(struct request_queue *queue, struct bio *bio)
{
struct zram *zram = queue->queuedata;
down_read(&zram->init_lock);
if (unlikely(!init_done(zram)))
goto error;
if (!valid_io_request(zram, bio)) {
atomic64_inc(&zram->stats.invalid_io);
goto error;
}
__zram_make_request(zram, bio);
up_read(&zram->init_lock);
Merge branch 'for-3.2/core' of git://git.kernel.dk/linux-block * 'for-3.2/core' of git://git.kernel.dk/linux-block: (29 commits) block: don't call blk_drain_queue() if elevator is not up blk-throttle: use queue_is_locked() instead of lockdep_is_held() blk-throttle: Take blkcg->lock while traversing blkcg->policy_list blk-throttle: Free up policy node associated with deleted rule block: warn if tag is greater than real_max_depth. block: make gendisk hold a reference to its queue blk-flush: move the queue kick into blk-flush: fix invalid BUG_ON in blk_insert_flush block: Remove the control of complete cpu from bio. block: fix a typo in the blk-cgroup.h file block: initialize the bounce pool if high memory may be added later block: fix request_queue lifetime handling by making blk_queue_cleanup() properly shutdown block: drop @tsk from attempt_plug_merge() and explain sync rules block: make get_request[_wait]() fail if queue is dead block: reorganize throtl_get_tg() and blk_throtl_bio() block: reorganize queue draining block: drop unnecessary blk_get/put_queue() in scsi_cmd_ioctl() and blk_get_tg() block: pass around REQ_* flags instead of broken down booleans during request alloc/free block: move blk_throtl prototypes to block/blk.h block: fix genhd refcounting in blkio_policy_parse_and_set() ... Fix up trivial conflicts due to "mddev_t" -> "struct mddev" conversion and making the request functions be of type "void" instead of "int" in - drivers/md/{faulty.c,linear.c,md.c,md.h,multipath.c,raid0.c,raid1.c,raid10.c,raid5.c} - drivers/staging/zram/zram_drv.c
2011-11-05 08:06:58 +08:00
return;
error:
up_read(&zram->init_lock);
bio_io_error(bio);
}
static void zram_slot_free_notify(struct block_device *bdev,
unsigned long index)
{
struct zram *zram;
struct zram_meta *meta;
zram = bdev->bd_disk->private_data;
meta = zram->meta;
zram: don't grab mutex in zram_slot_free_noity [1] introduced down_write in zram_slot_free_notify to prevent race between zram_slot_free_notify and zram_bvec_[read|write]. The race could happen if somebody who has right permission to open swap device is reading swap device while it is used by swap in parallel. However, zram_slot_free_notify is called with holding spin_lock of swap layer so we shouldn't avoid holing mutex. Otherwise, lockdep warns it. This patch adds new list to handle free slot and workqueue so zram_slot_free_notify just registers slot index to be freed and registers the request to workqueue. If workqueue is expired, it holds mutex_lock so there is no problem any more. If any I/O is issued, zram handles pending slot-free request caused by zram_slot_free_notify right before handling issued request because workqueue wouldn't be expired yet so zram I/O request handling function can miss it. Lastly, when zram is reset, flush_work could handle all of pending free request so we shouldn't have memory leak. NOTE: If zram_slot_free_notify's kmalloc with GFP_ATOMIC would be failed, the slot will be freed when next write I/O write the slot. [1] [57ab0485, zram: use zram->lock to protect zram_free_page() in swap free notify path] * from v2 * refactoring * from v1 * totally redesign Cc: Nitin Gupta <ngupta@vflare.org> Cc: Jiang Liu <jiang.liu@huawei.com> Cc: stable@vger.kernel.org Signed-off-by: Minchan Kim <minchan@kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2013-08-12 14:13:56 +08:00
write_lock(&meta->tb_lock);
zram_free_page(zram, index);
write_unlock(&meta->tb_lock);
atomic64_inc(&zram->stats.notify_free);
}
static const struct block_device_operations zram_devops = {
.swap_slot_free_notify = zram_slot_free_notify,
.owner = THIS_MODULE
};
static DEVICE_ATTR(disksize, S_IRUGO | S_IWUSR,
disksize_show, disksize_store);
static DEVICE_ATTR(initstate, S_IRUGO, initstate_show, NULL);
static DEVICE_ATTR(reset, S_IWUSR, NULL, reset_store);
static DEVICE_ATTR(orig_data_size, S_IRUGO, orig_data_size_show, NULL);
static DEVICE_ATTR(mem_used_total, S_IRUGO, mem_used_total_show, NULL);
ZRAM_ATTR_RO(num_reads);
ZRAM_ATTR_RO(num_writes);
ZRAM_ATTR_RO(failed_reads);
ZRAM_ATTR_RO(failed_writes);
ZRAM_ATTR_RO(invalid_io);
ZRAM_ATTR_RO(notify_free);
ZRAM_ATTR_RO(zero_pages);
ZRAM_ATTR_RO(compr_data_size);
static struct attribute *zram_disk_attrs[] = {
&dev_attr_disksize.attr,
&dev_attr_initstate.attr,
&dev_attr_reset.attr,
&dev_attr_num_reads.attr,
&dev_attr_num_writes.attr,
&dev_attr_failed_reads.attr,
&dev_attr_failed_writes.attr,
&dev_attr_invalid_io.attr,
&dev_attr_notify_free.attr,
&dev_attr_zero_pages.attr,
&dev_attr_orig_data_size.attr,
&dev_attr_compr_data_size.attr,
&dev_attr_mem_used_total.attr,
NULL,
};
static struct attribute_group zram_disk_attr_group = {
.attrs = zram_disk_attrs,
};
static int create_device(struct zram *zram, int device_id)
{
int ret = -ENOMEM;
init_rwsem(&zram->init_lock);
zram->queue = blk_alloc_queue(GFP_KERNEL);
if (!zram->queue) {
pr_err("Error allocating disk queue for device %d\n",
device_id);
goto out;
}
blk_queue_make_request(zram->queue, zram_make_request);
zram->queue->queuedata = zram;
/* gendisk structure */
zram->disk = alloc_disk(1);
if (!zram->disk) {
pr_warn("Error allocating disk structure for device %d\n",
device_id);
goto out_free_queue;
}
zram->disk->major = zram_major;
zram->disk->first_minor = device_id;
zram->disk->fops = &zram_devops;
zram->disk->queue = zram->queue;
zram->disk->private_data = zram;
snprintf(zram->disk->disk_name, 16, "zram%d", device_id);
/* Actual capacity set using syfs (/sys/block/zram<id>/disksize */
set_capacity(zram->disk, 0);
/* zram devices sort of resembles non-rotational disks */
queue_flag_set_unlocked(QUEUE_FLAG_NONROT, zram->disk->queue);
Staging: ramzswap: Support generic I/O requests Currently, ramzwap devices (/dev/ramzswapX) can only be used as swap disks since it was hard-coded to consider only the first request in bio vector. Now, we iterate over all the segments in an incoming bio which allows us to handle all kinds of I/O requests. ramzswap devices can still handle PAGE_SIZE aligned and multiple of PAGE_SIZE sized I/O requests only. To ensure that we get always get such requests only, we set following request_queue attributes to PAGE_SIZE: - physical_block_size - logical_block_size - io_min - io_opt Note: physical and logical block sizes were already set equal to PAGE_SIZE and that seems to be sufficient to get PAGE_SIZE aligned I/O. Since we are no longer limited to handling swap requests only, the next few patches rename ramzswap to zram. So, the devices will then be called /dev/zram{0, 1, 2, ...} Usage/Examples: 1) Use as /tmp storage - mkfs.ext4 /dev/zram0 - mount /dev/zram0 /tmp 2) Use as swap: - mkswap /dev/zram0 - swapon /dev/zram0 -p 10 # give highest priority to zram0 Performance: - I/O benchamark done with 'dd' command. Details can be found here: http://code.google.com/p/compcache/wiki/zramperf Summary: - Maximum read speed (approx): - ram disk: 1200 MB/sec - zram disk: 600 MB/sec - Maximum write speed (approx): - ram disk: 500 MB/sec - zram disk: 160 MB/sec Issues: - Double caching: We can potentially waste memory by having two copies of a page -- one in page cache (uncompress) and second in the device memory (compressed). However, during reclaim, clean page cache pages are quickly freed, so this does not seem to be a big problem. - Stale data: Not all filesystems support issuing 'discard' requests to underlying block devices. So, if such filesystems are used over zram devices, we can accumulate lot of stale data in memory. Even for filesystems to do support discard (example, ext4), we need to see how effective it is. - Scalability: There is only one (per-device) de/compression buffer stats. This can lead to significant contention, especially when used for generic (non-swap) purposes. Signed-off-by: Nitin Gupta <ngupta@vflare.org> Acked-by: Pekka Enberg <penberg@cs.helsinki.fi> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2010-06-01 16:01:23 +08:00
/*
* To ensure that we always get PAGE_SIZE aligned
* and n*PAGE_SIZED sized I/O requests.
*/
blk_queue_physical_block_size(zram->disk->queue, PAGE_SIZE);
blk_queue_logical_block_size(zram->disk->queue,
ZRAM_LOGICAL_BLOCK_SIZE);
blk_queue_io_min(zram->disk->queue, PAGE_SIZE);
blk_queue_io_opt(zram->disk->queue, PAGE_SIZE);
add_disk(zram->disk);
ret = sysfs_create_group(&disk_to_dev(zram->disk)->kobj,
&zram_disk_attr_group);
if (ret < 0) {
pr_warn("Error creating sysfs group");
goto out_free_disk;
}
zram->meta = NULL;
return 0;
out_free_disk:
del_gendisk(zram->disk);
put_disk(zram->disk);
out_free_queue:
blk_cleanup_queue(zram->queue);
out:
return ret;
}
static void destroy_device(struct zram *zram)
{
sysfs_remove_group(&disk_to_dev(zram->disk)->kobj,
&zram_disk_attr_group);
del_gendisk(zram->disk);
put_disk(zram->disk);
blk_cleanup_queue(zram->queue);
}
static int __init zram_init(void)
{
int ret, dev_id;
if (num_devices > max_num_devices) {
pr_warn("Invalid value for num_devices: %u\n",
num_devices);
ret = -EINVAL;
goto out;
}
zram_major = register_blkdev(0, "zram");
if (zram_major <= 0) {
pr_warn("Unable to get major number\n");
ret = -EBUSY;
goto out;
}
/* Allocate the device array and initialize each one */
zram_devices = kzalloc(num_devices * sizeof(struct zram), GFP_KERNEL);
if (!zram_devices) {
ret = -ENOMEM;
goto unregister;
}
for (dev_id = 0; dev_id < num_devices; dev_id++) {
ret = create_device(&zram_devices[dev_id], dev_id);
if (ret)
goto free_devices;
}
pr_info("Created %u device(s) ...\n", num_devices);
return 0;
free_devices:
while (dev_id)
destroy_device(&zram_devices[--dev_id]);
kfree(zram_devices);
unregister:
unregister_blkdev(zram_major, "zram");
out:
return ret;
}
static void __exit zram_exit(void)
{
int i;
struct zram *zram;
for (i = 0; i < num_devices; i++) {
zram = &zram_devices[i];
destroy_device(zram);
/*
* Shouldn't access zram->disk after destroy_device
* because destroy_device already released zram->disk.
*/
zram_reset_device(zram, false);
}
unregister_blkdev(zram_major, "zram");
kfree(zram_devices);
pr_debug("Cleanup done!\n");
}
module_init(zram_init);
module_exit(zram_exit);
module_param(num_devices, uint, 0);
MODULE_PARM_DESC(num_devices, "Number of zram devices");
MODULE_LICENSE("Dual BSD/GPL");
MODULE_AUTHOR("Nitin Gupta <ngupta@vflare.org>");
MODULE_DESCRIPTION("Compressed RAM Block Device");