- 13 Dec, 2014 40 commits
-
-
Heinrich Schuchardt authored
The fanotify and the inotify API can be used to monitor changes of the file system. System call fallocate() modifies files. Hence it should trigger the corresponding fanotify (FAN_MODIFY) and inotify (IN_MODIFY) events. The most interesting case is FALLOC_FL_COLLAPSE_RANGE because this value allows to create arbitrary file content from random data. This patch adds the missing call to fsnotify_modify(). The FAN_MODIFY and IN_MODIFY event will be created when fallocate() succeeds. It will even be created if the file length remains unchanged, e.g. when calling fanotify with flag FALLOC_FL_KEEP_SIZE. This logic was primarily chosen to keep the coding simple. It resembles the logic of the write() system call. When we call write() we always create a FAN_MODIFY event, even in the case of overwriting with identical data. Events FAN_MODIFY and IN_MODIFY do not provide any guarantee that data was actually changed. Furthermore even if if the filesize remains unchanged, fallocate() may influence whether a subsequent write() will succeed and hence the fallocate() call may be considered a modification. The fallocate(2) man page teaches: After a successful call, subsequent writes into the range specified by offset and len are guaranteed not to fail because of lack of disk space. So calling fallocate(fd, FALLOC_FL_KEEP_SIZE, offset, len) may result in different outcomes of a subsequent write depending on the values of offset and len. Signed-off-by:
Heinrich Schuchardt <xypron.glpk@gmx.de> Reviewed-by:
Jan Kara <jack@suse.cz> Cc: Jan Kara <jack@suse.cz> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Eric Paris <eparis@parisplace.org> Cc: John McCutchan <john@johnmccutchan.com> Cc: Robert Love <rlove@rlove.org> Cc: Michael Kerrisk <mtk.manpages@gmail.com> Cc: Theodore Ts'o <tytso@mit.edu> Cc: Dave Chinner <david@fromorbit.com> Signed-off-by:
Andrew Morton <akpm@linux-foundation.org> Signed-off-by:
Linus Torvalds <torvalds@linux-foundation.org>
-
Thierry Reding authored
kmemleak will add allocations as objects to a pool. The memory allocated for each object in this pool is periodically searched for pointers to other allocated objects. This only works for memory that is mapped into the kernel's virtual address space, which happens not to be the case for most CMA regions. Furthermore, CMA regions are typically used to store data transferred to or from a device and therefore don't contain pointers to other objects. Without this, the kernel crashes on the first execution of the scan_gray_list() because it tries to access highmem. Perhaps a more appropriate fix would be to reject any object that can't map to a kernel virtual address? [akpm@linux-foundation.org: add comment] [akpm@linux-foundation.org: fix comment, per Catalin] [sfr@canb.auug.org.au: include linux/io.h for phys_to_virt()] Signed-off-by:
Thierry Reding <treding@nvidia.com> Cc: Michal Nazarewicz <mina86@mina86.com> Cc: Marek Szyprowski <m.szyprowski@samsung.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com> Cc: Catalin Marinas <catalin.marinas@arm.com> Signed-off-by:
Stephen Rothwell <sfr@canb.auug.org.au> Signed-off-by:
-
Vladimir Davydov authored
If we fail to allocate from the current node's stock, we look for free objects on other nodes before calling the page allocator (see get_any_partial). While checking other nodes we respect cpuset constraints by calling cpuset_zone_allowed. We enforce hardwall check. As a result, we will fallback to the page allocator even if there are some pages cached on other nodes, but the current cpuset doesn't have them set. However, the page allocator uses softwall check for kernel allocations, so it may allocate from one of the other nodes in this case. Therefore we should use softwall cpuset check in get_any_partial to conform with the cpuset check in the page allocator. Signed-off-by:
Vladimir Davydov <vdavydov@parallels.com> Acked-by:
Zefan Li <lizefan@huawei.com> Acked-by:
Christoph Lameter <cl@linux.com> Cc: Pekka Enberg <penberg@kernel.org> Cc: David Rientjes <rientjes@google.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Tejun Heo <tj@kernel.org> Signed-off-by:
-
Vladimir Davydov authored
fallback_alloc is called on kmalloc if the preferred node doesn't have free or partial slabs and there's no pages on the node's free list (GFP_THISNODE allocations fail). Before invoking the reclaimer it tries to locate a free or partial slab on other allowed nodes' lists. While iterating over the preferred node's zonelist it skips those zones which hardwall cpuset check returns false for. That means that for a task bound to a specific node using cpusets fallback_alloc will always ignore free slabs on other nodes and go directly to the reclaimer, which, however, may allocate from other nodes if cpuset.mem_hardwall is unset (default). As a result, we may get lists of free slabs grow without bounds on other nodes, which is bad, because inactive slabs are only evicted by cache_reap at a very slow rate and cannot be dropped forcefully. To reproduce the issue, run a process that will walk over a directory tree with lots of files inside a cpuset bound to a node that constantly experiences memory pressure. Look at num_slabs vs active_slabs growth as reported by /proc/slabinfo. To avoid this we should use softwall cpuset check in fallback_alloc. Signed-off-by:
-
Dave Hansen authored
Andrew Morton noted http://lkml.kernel.org/r/20141104142027.a7a0d010772d84560b445f59@linux-foundation.org that the shmdt uses inode->i_size outside of i_mutex being held. There is one more case in shm.c in shm_destroy(). This converts both users over to use i_size_read(). Signed-off-by:
Dave Hansen <dave.hansen@linux.intel.com> Cc: Manfred Spraul <manfred@colorfullife.com> Cc: Davidlohr Bueso <dave@stgolabs.net> Signed-off-by:
-
Dave Hansen authored
This is a highly-contrived scenario. But, a single shmdt() call can be induced in to unmapping memory from mulitple shm segments. Example code is here: http://www.sr71.net/~dave/intel/shmfun.c The fix is pretty simple: Record the 'struct file' for the first VMA we encounter and then stick to it. Decline to unmap anything not from the same file and thus the same segment. I found this by inspection and the odds of anyone hitting this in practice are pretty darn small. Lightly tested, but it's a pretty small patch. Signed-off-by:
Davidlohr Bueso <dave@stgolabs.net> Signed-off-by:
-
Manfred Spraul authored
SysV can be abused to allocate locked kernel memory. For most systems, a small limit doesn't make sense, see the discussion with regards to SHMMAX. Therefore: increase MSGMNI to the maximum supported. And: If we ignore the risk of locking too much memory, then an automatic scaling of MSGMNI doesn't make sense. Therefore the logic can be removed. The code preserves auto_msgmni to avoid breaking any user space applications that expect that the value exists. Notes: 1) If an administrator must limit the memory allocations, then he can set MSGMNI as necessary. Or he can disable sysv entirely (as e.g. done by Android). 2) MSGMAX and MSGMNB are intentionally not increased, as these values are used to control latency vs. throughput: If MSGMNB is large, then msgsnd() just returns and more messages can be queued before a task switch to a task that calls msgrcv() is forced. [akpm@linux-foundation.org: coding-style fixes] Signed-off-by:
Manfred Spraul <manfred@colorfullife.com> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Rafael Aquini <aquini@redhat.com> Signed-off-by:
-
Manfred Spraul authored
a) SysV can be abused to allocate locked kernel memory. For most systems, a small limit doesn't make sense, see the discussion with regards to SHMMAX. Therefore: Increase the sysv sem limits so that all known applications will work with these defaults. b) With regards to the maximum supported: Some of the specified hard limits are not correct anymore, therefore the patch updates the documentation. - SEMMNI must stay below IPCMNI, which is 32768. As for SHMMAX: Stay a bit below this limit. - SEMMSL was limited to 8k, to ensure that the kmalloc for the kernel array was limited to 16 kB (order=2) This doesn't apply anymore: - the allocation size isn't sizeof(short)*nsems anymore. - ipc_alloc falls back to vmalloc - SEMOPM should stay below 1000, to limit the kmalloc in semtimedop() to an order=1 allocation. Therefore: Leave it at 500 (order=0 allocation). Note: If an administrator must limit the memory allocations, then he can set the values as necessary. Or he can disable sysv entirely (as e.g. done by Android). Signed-off-by:
Rafael Aquini <aquini@redhat.com> Signed-off-by:
-
Manfred Spraul authored
When I fixed bugs in the sem_lock() logic, I was more conservative than necessary. Therefore it is safe to replace the smp_mb() with smp_rmb(). And: With smp_rmb(), semop() syscalls are up to 10% faster. The race we must protect against is: sem->lock is free sma->complex_count = 0 sma->sem_perm.lock held by thread B thread A: A: spin_lock(&sem->lock) B: sma->complex_count++; (now 1) B: spin_unlock(&sma->sem_perm.lock); A: spin_is_locked(&sma->sem_perm.lock); A: XXXXX memory barrier A: if (sma->complex_count == 0) Thread A must read the increased complex_count value, i.e. the read must not be reordered with the read of sem_perm.lock done by spin_is_locked(). Since it's about ordering of reads, smp_rmb() is sufficient. [akpm@linux-foundation.org: update sem_lock() comment, from Davidlohr] Signed-off-by:
-
Haesung Kim authored
Magic number of compress formats for kernel image is defined by two bytes. These numbers are written in hexadecimal number, nevertheless magic number for only gunzip is written in octal number. The formats should be consistent for readability. Therefore, magic numbers for gunzip are also defined by hexadecimal number. Signed-off-by:
Haesung Kim <matia.kim@lge.com> Signed-off-by:
-
Dan Carpenter authored
"origPtr" is used as an offset into the bd->dbuf[] array. That array is allocated in start_bunzip() and has "bd->dbufSize" number of elements so the test here should be >= instead of >. Later we check "origPtr" again before using it as an offset so I don't know if this bug can be triggered in real life. Fixes: bc22c17e ('bzip2/lzma: library support for gzip, bzip2 and lzma decompression') Signed-off-by:
Dan Carpenter <dan.carpenter@oracle.com> Cc: Alain Knaff <alain@knaff.lu> Cc: Yinghai Lu <yinghai@kernel.org> Cc: "H. Peter Anvin" <hpa@zytor.com> Signed-off-by:
-
Andi Kleen authored
The kernel has support for (nearly) every compression algorithm known to man, each to handle some particular microscopic niche. Unfortunately all of these always get compiled in if you want to support INITRDs, and can be only disabled when CONFIG_EXPERT is set. I don't see why I need to set EXPERT just to properly configure the initrd compression algorithms, and not always include every possible algorithm Usually the initrd is just compressed with gzip anyways, at least that's true on all distributions I use. Remove the dependencies for initrd compression on CONFIG_EXPERT. Make the various options just default y, which should be good enough to not break any previous configuration. Signed-off-by:
Andi Kleen <ak@linux.intel.com> Signed-off-by:
-
Dmitry Monakhov authored
Current debug levels are not optimal. Especially if one want to provoke big numbers of faults(broken device simulator) then any verbose level will produce giant numbers of identical logging messages. Let's add ratelimit parameter for that purpose. Signed-off-by:
Dmitry Monakhov <dmonakhov@openvz.org> Acked-by:
Akinobu Mita <akinobu.mita@gmail.com> Signed-off-by:
-
Dmitry Monakhov authored
Signed-off-by:
-
Fabian Frederick authored
linux kernel doesn't manage page sizes below 4kb. Signed-off-by:
Fabian Frederick <fabf@skynet.be> Signed-off-by:
-
Fabian Frederick authored
Based on ext2_direct_IO Tested with O_DIRECT file open and sysbench/mariadb with 1% written queries improvement (update_non_index test) on a volume created with mkaffs. Signed-off-by:
-
Fabian Frederick authored
-Remove ErrorBuffer and use %pV -Add __printf to enable argument mistmatch warnings Original patch by Joe Perches. Signed-off-by:
-
Fabian Frederick authored
-Move file_operations to avoid forward declarations. -Remove unused declarations. Signed-off-by:
-
Riku Voipio authored
Following the suggestions from Andrew Morton and Stephen Rothwell, Dont expand the ARCH list in kernel/gcov/Kconfig. Instead, define a ARCH_HAS_GCOV_PROFILE_ALL bool which architectures can enable. set ARCH_HAS_GCOV_PROFILE_ALL on Architectures where it was previously allowed + ARM64 which I tested. Signed-off-by:
Riku Voipio <riku.voipio@linaro.org> Cc: Peter Oberparleiter <oberpar@linux.vnet.ibm.com> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Signed-off-by:
-
Masanari Iida authored
Remove unnecessary KERN_ERR from pr_err() within kexec.c. Signed-off-by:
Masanari Iida <standby24x7@gmail.com> Acked-by:
Vivek Goyal <vgoyal@redhat.com> Signed-off-by:
-
David Drysdale authored
Signed-off-by:
David Drysdale <drysdale@google.com> Acked-by:
David S. Miller <davem@davemloft.net> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Signed-off-by:
-
David Drysdale authored
Signed-off-by:
-
David Drysdale authored
Hook up x86-64, i386 and x32 ABIs. Signed-off-by:
-
David Drysdale authored
This patchset adds execveat(2) for x86, and is derived from Meredydd Luff's patch from Sept 2012 (https://lkml.org/lkml/2012/9/11/528). The primary aim of adding an execveat syscall is to allow an implementation of fexecve(3) that does not rely on the /proc filesystem, at least for executables (rather than scripts). The current glibc version of fexecve(3) is implemented via /proc, which causes problems in sandboxed or otherwise restricted environments. Given the desire for a /proc-free fexecve() implementation, HPA suggested (https://lkml.org/lkml/2006/7/11/556) that an execveat(2) syscall would be an appropriate generalization. Also, having a new syscall means that it can take a flags argument without back-compatibility concerns. The current implementation just defines the AT_EMPTY_PATH and AT_SYMLINK_NOFOLLOW flags, but other flags could be added in future -- for example, flags for new namespaces (as suggested at https://lkml.org/lkml/2006/7/11/474). Related history: - https://lkml.org/lkml/2006/12/27/123 is an example of someone realizing that fexecve() is likely to fail in a chroot environment. - http://bugs.debian.org/cgi-bin/bugreport.cgi?bug=514043 covered documenting the /proc requirement of fexecve(3) in its manpage, to "prevent other people from wasting their time". - https://bugzilla.redhat.com/show_bug.cgi?id=241609 described a problem where a process that did setuid() could not fexecve() because it no longer had access to /proc/self/fd; this has since been fixed. This patch (of 4): Add a new execveat(2) system call. execveat() is to execve() as openat() is to open(): it takes a file descriptor that refers to a directory, and resolves the filename relative to that. In addition, if the filename is empty and AT_EMPTY_PATH is specified, execveat() executes the file to which the file descriptor refers. This replicates the functionality of fexecve(), which is a system call in other UNIXen, but in Linux glibc it depends on opening "/proc/self/fd/<fd>" (and so relies on /proc being mounted). The filename fed to the executed program as argv[0] (or the name of the script fed to a script interpreter) will be of the form "/dev/fd/<fd>" (for an empty filename) or "/dev/fd/<fd>/<filename>", effectively reflecting how the executable was found. This does however mean that execution of a script in a /proc-less environment won't work; also, script execution via an O_CLOEXEC file descriptor fails (as the file will not be accessible after exec). Based on patches by Meredydd Luff. Signed-off-by:
-
Namjae Jeon authored
When running FSX with direct I/O mode, fsx resulted in DATA past EOF issues. fsx ./file2 -Z -r 4096 -w 4096 ... .. truncating to largest ever: 0x907c fallocating to largest ever: 0x11137 truncating to largest ever: 0x2c6fe truncating to largest ever: 0x2cfdf fallocating to largest ever: 0x40000 Mapped Read: non-zero data past EOF (0x18628) page offset 0x629 is 0x2a4e ... .. The reason being, it is doing a truncate down, but the zeroing does not happen on the last block boundary when offset is not aligned. Even though it calls truncate_setsize()->truncate_inode_pages()-> truncate_inode_pages_range() and considers the partial zeroout but it retrieves the page using find_lock_page() - which only looks the page in the cache. So, zeroing out does not happen in case of direct IO. Make a truncate page based around block_truncate_page for FAT filesystem and invoke that helper to zerout in case the offset is not aligned with the blocksize. Signed-off-by:
Namjae Jeon <namjae.jeon@samsung.com> Signed-off-by:
Amit Sahrawat <a.sahrawat@samsung.com> Acked-by:
OGAWA Hirofumi <hirofumi@mail.parknet.co.jp> Signed-off-by:
-
Jan Kara authored
Coverity id: 1042674 Signed-off-by:
-
Heesub Shin authored
When zbud is initialized through the zpool wrapper, pool->ops which points to user-defined operations is always set regardless of whether it is specified from the upper layer. This causes zbud_reclaim_page() to iterate its loop for evicting pool pages out without any gain. This patch sets the user-defined ops only when it is needed, so that zbud_reclaim_page() can bail out the reclamation loop earlier if there is no user-defined operations specified. Signed-off-by:
Heesub Shin <heesub.shin@samsung.com> Acked-by:
Dan Streetman <ddstreet@ieee.org> Cc: Seth Jennings <sjennings@variantweb.net> Cc: Sunae Seo <sunae.seo@samsung.com> Signed-off-by:
-
Markus Elfring authored
free_percpu() tests whether its argument is NULL and then returns immediately. Thus the test around the call is not needed. This issue was detected by using the Coccinelle software. Signed-off-by:
Markus Elfring <elfring@users.sourceforge.net> Cc: Seth Jennings <sjennings@variantweb.net> Signed-off-by:
-
Mahendran Ganesh authored
zswap_cpu_init/zswap_comp_exit/zswap_entry_cache_create is only called by __init init_zswap() Signed-off-by:
Mahendran Ganesh <opensource.ganesh@gmail.com> Cc: Seth Jennings <sjennings@variantweb.net> Cc: Dan Streetman <ddstreet@ieee.org> Cc: Minchan Kim <minchan@kernel.org> Signed-off-by:
-
Ganesh Mahendran authored
In current zram, we use DEVICE_ATTR() to define sys device attributes. SO, we need to set (S_IRUGO | S_IWUSR) permission and other arguments manually. Linux already provids the macro DEVICE_ATTR_[RW|RO|WO] to define sys device attribute. It is simple and readable. This patch uses kernel defined macro DEVICE_ATTR_[RW|RO|WO] to define zram device attribute. Signed-off-by:
Jerome Marchand <jmarchan@redhat.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Nitin Gupta <ngupta@vflare.org> Signed-off-by:
-
Ganesh Mahendran authored
In zs_create_pool(), we allocate memory more then sizeof(struct zs_pool) ovhd_size = roundup(sizeof(*pool), PAGE_SIZE); This patch allocate memory of exactly needed size. Signed-off-by:
Minchan Kim <minchan@kernel.org> Cc: Nitin Gupta <ngupta@vflare.org> Cc: Dan Streetman <ddstreet@ieee.org> Signed-off-by:
-
Ganesh Mahendran authored
In zs_create_pool(), prev_class is assigned (ZS_SIZE_CLASSES - 1) times. And the prev_class only references to the previous size_class. So we do not need unnecessary assignement. This patch assigns *prev_class* when a new size_class structure is allocated and uses prev_class to check whether the first class has been allocated. [akpm@linux-foundation.org: remove now-unused ZS_SIZE_CLASSES] Signed-off-by:
-
Mahendran Ganesh authored
In struct zram_table_entry, the element *value* contains obj size and obj zram flags. Bit 0 to bit (ZRAM_FLAG_SHIFT - 1) represent obj size, and bit ZRAM_FLAG_SHIFT to the highest bit of unsigned long represent obj zram_flags. So the first zram flag(ZRAM_ZERO) should be from ZRAM_FLAG_SHIFT instead of (ZRAM_FLAG_SHIFT + 1). This patch fixes this cosmetic issue. Also fix a typo, "page in now accessed" -> "page is now accessed" Signed-off-by:
Weijie Yang <weijie.yang@samsung.com> Acked-by:
Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Cc: Nitin Gupta <ngupta@vflare.org> Signed-off-by:
-
Mahendran Ganesh authored
I sent a patch [1] for unnecessary check in zsmalloc. And Minchan Kim found zsmalloc even does not support allocating an obj with the size of ZS_MAX_ALLOC_SIZE in some situations. For example: In system with 64KB PAGE_SIZE and 32 bit of physical addr. Then: ZS_MIN_ALLOC_SIZE is 32 bytes which is calculated by: MAX(32, (ZS_MAX_PAGES_PER_ZSPAGE << PAGE_SHIFT >> OBJ_INDEX_BITS)) ZS_MAX_ALLOC_SIZE is 64KB(in current code, is PAGE_SIZE) ZS_SIZE_CLASS_DELTA is 256 bytes So, ZS_SIZE_CLASSES = (ZS_MAX_ALLOC_SIZE - ZS_MIN_ALLOC_SIZE) / ZS_SIZE_CLASS_DELTA + 1 = 256 In zs_create_pool(), the max size obj which can be allocated will be: ZS_MIN_ALLOC_SIZE + i * ZS_SIZE_CLASS_DELTA = 32 + 255*256 = 65312 We can see that 65312 < 65536 (ZS_MAX_ALLOC_SIZE). So we can NOT allocate objs with size ZS_MAX_ALLOC_SIZE(65536) which we promise upper users we can do. [1] http://lkml.iu.edu/hypermail/linux/kernel/1411.2/03835.html [2] http://lkml.iu.edu/hypermail/linux/kernel/1411.2/04534.html This patch fixes this issue by dynamiclly calculating zs_size_classes when module is loaded, allocates buffer with size ZS_MAX_ALLOC_SIZE. Then the max obj(size is ZS_MAX_ALLOC_SIZE) can be stored in it. [akpm@linux-foundation.org: restore ZS_SIZE_CLASSES to fix bisectability] Signed-off-by: -
Minchan Kim authored
The kunmap_atomic should use virtual address getting by kmap_atomic. However, some pieces of code in zsmalloc uses modified address, not the one got by kmap_atomic for kunmap_atomic. It's okay for working because zsmalloc modifies the address inner PAGE_SIZE bounday so it works with current kmap_atomic's implementation. But it's still fragile with potential changing of kmap_atomic so let's correct it. I got a subtle bug when I implemented a new feature of zsmalloc (compaction) due to a link's mishandling (the link was over page boundary). Although it was totally my mistake, it took a while to find the cause because an unpredictable kmapped address was unmapped causing an almost random crash. Signed-off-by:
-
Sergey Senozhatsky authored
Mahendran Ganesh reported that zpool-enabled zsmalloc should not call zpool_unregister_driver() from zs_init() if cpu notifier registration has failed, because error handling is performed before we register the driver via zpool_register_driver() call. Factor out cpu notifier registration and unregistration code and fix zs_init() error handling. link: http://lkml.iu.edu//hypermail/linux/kernel/1411.1/04156.html [akpm@linux-foundation.org: squash bogus gcc warning] [akpm@linux-foundation.org: use __init and __exit] Signed-off-by:
-
karam.lee authored
This patch implements rw_page operation for zram block device. I implemented the feature in zram and tested it. Test bed was the G2, LG electronic mobile device, whtich has msm8974 processor and 2GB memory. With a memory allocation test program consuming memory, the system generates swap. Operating time of swap_write_page() was measured. -------------------------------------------------- | | operating time | improvement | | | (20 runs average) | | -------------------------------------------------- |with patch | 1061.15 us | +2.4% | -------------------------------------------------- |without patch| 1087.35 us | | -------------------------------------------------- Each test(with paged_io,with BIO) result set shows normal distribution and has equal variance. I mean the two values are valid result to compare. I can say operation with paged I/O(without BIO) is faster 2.4% with confidence level 95%. [minchan@kernel.org: make rw_page opeartion return 0] [minchan@kernel.org: rely on the bi_end_io for zram_rw_page fails] [sergey.senozhatsky@gmail.com: code cleanup] [minchan@kernel.org: add comment] Signed-off-by:
karam.lee <karam.lee@lge.com> Acked-by:
-
karam.lee authored
This patch changes parameter of valid_io_request for common usage. The purpose of valid_io_request() is to determine if bio request is valid or not. This patch use I/O start address and size instead of a BIO parameter for common usage. Signed-off-by:
-
karam.lee authored
Recently rw_page block device operation has been added. This patchset implements rw_page operation for zram block device and does some clean-up. This patch (of 3): Remove an unnecessary parameter(bio) from zram_bvec_rw() and zram_bvec_read(). zram_bvec_read() doesn't use a bio parameter, so remove it. zram_bvec_rw() calls a read/write operation not using bio, so a rw parameter replaces a bio parameter. Signed-off-by:
-
Joonsoo Kim authored
zsmalloc has many size_classes to reduce fragmentation and they are in 16 bytes unit, for example, 16, 32, 48, etc., if PAGE_SIZE is 4096. And, zsmalloc has constraint that each zspage has 4 pages at maximum. In this situation, we can see interesting aspect. Let's think about size_class for 1488, 1472, ..., 1376. To prevent external fragmentation, they uses 4 pages per zspage and so all they can contain 11 objects at maximum. 16384 (4096 * 4) = 1488 * 11 + remains 16384 (4096 * 4) = 1472 * 11 + remains 16384 (4096 * 4) = ... 16384 (4096 * 4) = 1376 * 11 + remains It means that they have same characteristics and classification between them isn't needed. If we use one size_class for them, we can reduce fragementation and save some memory since both the 1488 and 1472 sized classes can only fit 11 objects into 4 pages, and an object that's 1472 bytes can fit into an object that's 1488 bytes, merging these classes to always use objects that are 1488 bytes will reduce the total number of size classes. And reducing the total number of size classes reduces overall fragmentation, because a wider range of compressed pages can fit into a single size class, leaving less unused objects in each size class. For this purpose, this patch implement size_class merging. If there is size_class that have same pages_per_zspage and same number of objects per zspage with previous size_class, we don't create new size_class. Instead, we use previous, same characteristic size_class. With this way, above example sizes (1488, 1472, ..., 1376) use just one size_class so we can get much more memory utilization. Below is result of my simple test. TEST ENV: EXT4 on zram, mount with discard option WORKLOAD: untar kernel source code, remove directory in descending order in size. (drivers arch fs sound include net Documentation firmware kernel tools) Each line represents orig_data_size, compr_data_size, mem_used_total, fragmentation overhead (mem_used - compr_data_size) and overhead ratio (overhead to compr_data_size), respectively, after untar and remove operation is executed. * untar-nomerge.out orig_size compr_size used_size overhead overhead_ratio 525.88MB 199.16MB 210.23MB 11.08MB 5.56% 288.32MB 97.43MB 105.63MB 8.20MB 8.41% 177.32MB 61.12MB 69.40MB 8.28MB 13.55% 146.47MB 47.32MB 56.10MB 8.78MB 18.55% 124.16MB 38.85MB 48.41MB 9.55MB 24.58% 103.93MB 31.68MB 40.93MB 9.25MB 29.21% 84.34MB 22.86MB 32.72MB 9.86MB 43.13% 66.87MB 14.83MB 23.83MB 9.00MB 60.70% 60.67MB 11.11MB 18.60MB 7.49MB 67.48% 55.86MB 8.83MB 16.61MB 7.77MB 88.03% 53.32MB 8.01MB 15.32MB 7.31MB 91.24% * untar-merge.out orig_size compr_size used_size overhead overhead_ratio 526.23MB 199.18MB 209.81MB 10.64MB 5.34% 288.68MB 97.45MB 104.08MB 6.63MB 6.80% 177.68MB 61.14MB 66.93MB 5.79MB 9.47% 146.83MB 47.34MB 52.79MB 5.45MB 11.51% 124.52MB 38.87MB 44.30MB 5.43MB 13.96% 104.29MB 31.70MB 36.83MB 5.13MB 16.19% 84.70MB 22.88MB 27.92MB 5.04MB 22.04% 67.11MB 14.83MB 19.26MB 4.43MB 29.86% 60.82MB 11.10MB 14.90MB 3.79MB 34.17% 55.90MB 8.82MB 12.61MB 3.79MB 42.97% 53.32MB 8.01MB 11.73MB 3.73MB 46.53% As you can see above result, merged one has better utilization (overhead ratio, 5th column) and uses less memory (mem_used_total, 3rd column). Signed-off-by:
Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Nitin Gupta <ngupta@vflare.org> Cc: Jerome Marchand <jmarchan@redhat.com> Cc: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Reviewed-by:
-
