v6.0.0 release #5
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
walk->can_swap might be invalid since it's not guaranteed to be initialized for the particular lruvec. Instead deduce it from the folio type (anon/file). Link: https://lkml.kernel.org/r/20230802025606.346758-3-kaleshsingh@google.com Fixes: 018ee47f1489 ("mm: multi-gen LRU: exploit locality in rmap") Change-Id: I1ae78011d4972d87bac9f2db8c56352cdb7a9be6 Signed-off-by: Kalesh Singh <kaleshsingh@google.com> Tested-by: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com> [mediatek] Tested-by: Charan Teja Kalla <quic_charante@quicinc.com> Cc: Yu Zhao <yuzhao@google.com> Cc: Aneesh Kumar K V <aneesh.kumar@linux.ibm.com> Cc: Barry Song <baohua@kernel.org> Cc: Brian Geffon <bgeffon@google.com> Cc: Jan Alexander Steffens (heftig) <heftig@archlinux.org> Cc: Lecopzer Chen <lecopzer.chen@mediatek.com> Cc: Matthias Brugger <matthias.bgg@gmail.com> Cc: Oleksandr Natalenko <oleksandr@natalenko.name> Cc: Qi Zheng <zhengqi.arch@bytedance.com> Cc: Steven Barrett <steven@liquorix.net> Cc: Suleiman Souhlal <suleiman@google.com> Cc: Suren Baghdasaryan <surenb@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> (cherry picked from commit fdf19e8c8f1cdcee4eccf4c98a875f44f39d8b9d https://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm.git mm-unstable) Bug: 288383787 Bug: 291719697 [ Kalesh Singh - Fix trivial conflict in lru_gen_look_around() ] Signed-off-by: Kalesh Singh <kaleshsingh@google.com> [ ghostrider-reborn - Backport to k5.4 ] Signed-off-by: Adithya R <gh0strider.2k18.reborn@gmail.com>
This patch fixes unproductive reclaiming of CMA pages by skipping them when they are not available for current context. It arises from the below OOM issue, which was caused by a large proportion of MIGRATE_CMA pages among free pages. [ 36.172486] [03-19 10:05:52.172] ActivityManager: page allocation failure: order:0, mode:0xc00(GFP_NOIO), nodemask=(null),cpuset=foreground,mems_allowed=0 [ 36.189447] [03-19 10:05:52.189] DMA32: 0*4kB 447*8kB (C) 217*16kB (C) 124*32kB (C) 136*64kB (C) 70*128kB (C) 22*256kB (C) 3*512kB (C) 0*1024kB 0*2048kB 0*4096kB = 35848kB [ 36.193125] [03-19 10:05:52.193] Normal: 231*4kB (UMEH) 49*8kB (MEH) 14*16kB (H) 13*32kB (H) 8*64kB (H) 2*128kB (H) 0*256kB 1*512kB (H) 0*1024kB 0*2048kB 0*4096kB = 3236kB ... [ 36.234447] [03-19 10:05:52.234] SLUB: Unable to allocate memory on node -1, gfp=0xa20(GFP_ATOMIC) [ 36.234455] [03-19 10:05:52.234] cache: ext4_io_end, object size: 64, buffer size: 64, default order: 0, min order: 0 [ 36.234459] [03-19 10:05:52.234] node 0: slabs: 53,objs: 3392, free: 0 This change further decreases the chance for wrong OOMs in the presence of a lot of CMA memory. [david@redhat.com: changelog addition] Link: https://lkml.kernel.org/r/1685501461-19290-1-git-send-email-zhaoyang.huang@unisoc.com Change-Id: I84f1145c38b5ff7b825f2122b33bc55997931bd7 Signed-off-by: Zhaoyang Huang <zhaoyang.huang@unisoc.com> Acked-by: David Hildenbrand <david@redhat.com> Cc: ke.wang <ke.wang@unisoc.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Minchan Kim <minchan@kernel.org> Cc: Suren Baghdasaryan <surenb@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> (cherry picked from commit 5da226dbfce3a2f44978c2c7cf88166e69a6788b) Bug: 288383787 Bug: 291719697 [ Rename folio to page - Kalesh Singh ] Signed-off-by: Kalesh Singh <kaleshsingh@google.com> [ ghostrider-reborn - Backport to k5.4 ] Signed-off-by: Adithya R <gh0strider.2k18.reborn@gmail.com>
This patch is based on the commit 5da226dbfce3("mm: skip CMA pages when
they are not available") which skips cma pages reclaim when they are not
eligible for the current allocation context. In mglru, such pages are
added to the tail of the immediate generation to maintain better LRU
order, which is unlike the case of conventional LRU where such pages are
directly added to the head of the LRU list(akin to adding to head of the
youngest generation in mglru).
No observable issue without this patch on MGLRU, but logically it make
sense to skip the CMA page reclaim when those pages can't be satisfied for
the current allocation context.
Link: https://lkml.kernel.org/r/1691568344-13475-1-git-send-email-quic_charante@quicinc.com
Change-Id: I586415b3e3a92da23f3e79b9d63802a2ced03432
Signed-off-by: Charan Teja Kalla <quic_charante@quicinc.com>
Reviewed-by: Kalesh Singh <kaleshsingh@google.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Yu Zhao <yuzhao@google.com>
Cc: Zhaoyang Huang <zhaoyang.huang@unisoc.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
(cherry picked from commit 75d52d9304ef5b268eb798b0c679815290a0fc83 https://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm.git mm-unstable)
Bug: 288383787
Bug: 291719697
Signed-off-by: Kalesh Singh <kaleshsingh@google.com>
DCE is not problematic on arm64 and works out of the box. Let it be used. Change-Id: I8a7574c3aeeeef27955796d7810ae86b70bad6fd
… v4l2-common The functions uvc_simplify_fraction and uvc_fraction_to_interval are generic helpers which are also useful for other v4l2 drivers. This patch moves them to v4l2-common. Tested-by: Daniel Scally <dan.scally@ideasonboard.com> Reviewed-by: Daniel Scally <dan.scally@ideasonboard.com> Signed-off-by: Michael Grzeschik <m.grzeschik@pengutronix.de> Link: https://lore.kernel.org/r/20220909221335.15033-2-m.grzeschik@pengutronix.de Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> (cherry picked from commit 6ba8b8d45335180523df8f1b6cd1c995a3dbf560) arakesh: resolved minor conflicts in include/media/v4l2-common.h and drivers/media/v4l2-core/v4l2-common.c Bug: 259171206 Change-Id: I17eea1ef6788ba98599b1d8a12499147ebef7d60 Signed-off-by: Avichal Rakesh <arakesh@google.com> Signed-off-by: Vishalcj17 <vishalcj@aospa.co>
The uvc_format_desc, GUID defines and the uvc_format_by_guid helper is also useful for the uvc gadget stack. This patch moves them to a common header. Tested-by: Daniel Scally <dan.scally@ideasonboard.com> Reviewed-by: Daniel Scally <dan.scally@ideasonboard.com> Signed-off-by: Michael Grzeschik <m.grzeschik@pengutronix.de> Link: https://lore.kernel.org/r/20220909221335.15033-3-m.grzeschik@pengutronix.de Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> (cherry picked from commit 6b028df7d466a5f7c0263a46256c9bdc42debd9f) arakesh: resolved minor conflicts in drivers/media/usb/uvc/uvc_driver.c and drivers/media/usb/uvc/uvcvideo.h Bug: 259171206 Change-Id: I37b839850896fff279159fca93a50f4788184354 Signed-off-by: Avichal Rakesh <arakesh@google.com> Signed-off-by: Vishalcj17 <vishalcj@aospa.co>
Add or improve documentation for function regarding creating and sending IO requests to the hardware. Change-Id: I4e2c4bfba4aef89bbc6c66d677f98d15ff4631cd Signed-off-by: André Almeida <andrealmeid@collabora.com> Signed-off-by: Jens Axboe <axboe@kernel.dk> Signed-off-by: ralph950412 <ralph950412@gmail.com>
We have: * blk_mq_run_hw_queue() * blk_mq_delay_run_hw_queue() * blk_mq_run_hw_queues() ...but not blk_mq_delay_run_hw_queues(), presumably because nobody needed it before now. Since we need it for a later patch in this series, add it. Change-Id: If6b8f67f554b967b9c3699c2a79052c2806164dc Signed-off-by: Douglas Anderson <dianders@chromium.org> Reviewed-by: Ming Lei <ming.lei@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk> Signed-off-by: ralph950412 <ralph950412@gmail.com>
…tiple HW queues
Currently when non-mq aware IO scheduler (BFQ, mq-deadline) is used for
a queue with multiple HW queues, the performance it rather bad. The
problem is that these IO schedulers use queue-wide locking and their
dispatch function does not respect the hctx it is passed in and returns
any request it finds appropriate. Thus locality of request access is
broken and dispatch from multiple CPUs just contends on IO scheduler
locks. For these IO schedulers there's little point in dispatching from
multiple CPUs. Instead dispatch always only from a single CPU to limit
contention.
Below is a comparison of dbench runs on XFS filesystem where the storage
is a raid card with 64 HW queues and to it attached a single rotating
disk. BFQ is used as IO scheduler:
clients MQ SQ MQ-Patched
Amean 1 39.12 (0.00%) 43.29 * -10.67%* 36.09 * 7.74%*
Amean 2 128.58 (0.00%) 101.30 * 21.22%* 96.14 * 25.23%*
Amean 4 577.42 (0.00%) 494.47 * 14.37%* 508.49 * 11.94%*
Amean 8 610.95 (0.00%) 363.86 * 40.44%* 362.12 * 40.73%*
Amean 16 391.78 (0.00%) 261.49 * 33.25%* 282.94 * 27.78%*
Amean 32 324.64 (0.00%) 267.71 * 17.54%* 233.00 * 28.23%*
Amean 64 295.04 (0.00%) 253.02 * 14.24%* 242.37 * 17.85%*
Amean 512 10281.61 (0.00%) 10211.16 * 0.69%* 10447.53 * -1.61%*
Numbers are times so lower is better. MQ is stock 5.10-rc6 kernel. SQ is
the same kernel with megaraid_sas.host_tagset_enable=0 so that the card
advertises just a single HW queue. MQ-Patched is a kernel with this
patch applied.
You can see multiple hardware queues heavily hurt performance in
combination with BFQ. The patch restores the performance.
Signed-off-by: Jan Kara <jack@suse.cz>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
BUG: 187357408
Change-Id: I53645eb48cb308cd3af81a1c5e718a6abec6a1f9
(cherry picked from commit fa56cac78af68bd93734c290a0ffd0716e871dba git://git.kernel.dk/linux-block/ for-5.14/block)
Signed-off-by: Bart Van Assche <bvanassche@google.com>
Since commit 01e99aeca39796003 'blk-mq: insert passthrough request into hctx->dispatch directly', passthrough request should not appear in IO-scheduler any more, so blk_rq_is_passthrough checking in addon IO schedulers is redundant. (Notes: this patch passes generic IO load test with hdds under SAS controller and hdds under AHCI controller but obviously not covers all. Not sure if passthrough request can still escape into IO scheduler from blk_mq_sched_insert_requests, which is used by blk_mq_flush_plug_list and has lots of indirect callers.) Signed-off-by: Lin Feng <linf@wangsu.com> Reviewed-by: Ming Lei <ming.lei@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk> BUG: 187357408 Change-Id: I97d85c38e584add44399295f3839994b694bc9ca (cherry picked from commit 0856faaa220759a4fe4334f5c57a8661c94c14ce git://git.kernel.dk/linux-block/ for-5.14/block) Signed-off-by: Bart Van Assche <bvanassche@google.com>
…cutive These entries were consecutive at the time of their introduction but are no longer consecutive. Make these again consecutive. Additionally, modify the help text since it refers to blk-mq and since the legacy block layer has been removed. Reviewed-by: Damien Le Moal <damien.lemoal@wdc.com> Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com> Reviewed-by: Hannes Reinecke <hare@suse.de> Cc: Christoph Hellwig <hch@lst.de> Cc: Ming Lei <ming.lei@redhat.com> Cc: Himanshu Madhani <himanshu.madhani@oracle.com> Signed-off-by: Bart Van Assche <bvanassche@acm.org> BUG: 187357408 Change-Id: I568383377a3244efba9748adf0a2e90bd7660bb2 (cherry picked from commit fdc250ea26e44066d690bbe65a03fab512af0699 git://git.kernel.dk/linux-block/ for-5.14/block) Signed-off-by: Bart Van Assche <bvanassche@google.com>
…cy_init() calls Before adding more calls in this function, simplify the error path. Reviewed-by: Damien Le Moal <damien.lemoal@wdc.com> Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com> Reviewed-by: Hannes Reinecke <hare@suse.de> Cc: Tejun Heo <tj@kernel.org> Cc: Christoph Hellwig <hch@lst.de> Cc: Ming Lei <ming.lei@redhat.com> Cc: Himanshu Madhani <himanshu.madhani@oracle.com> Signed-off-by: Bart Van Assche <bvanassche@acm.org> BUG: 187357408 Change-Id: I8568b87d1bebbd3841e42a79b7efe2d0a1bff2bc (cherry picked from commit f1a7f539c2720906fb10be0af3514b034e1a9fee git://git.kernel.dk/linux-block/ for-5.14/block) Signed-off-by: Bart Van Assche <bvanassche@google.com>
…C file rq_qos_id_to_name() is only used in blk-mq-debugfs.c so move that function into in blk-mq-debugfs.c. Cc: Damien Le Moal <damien.lemoal@wdc.com> Cc: Hannes Reinecke <hare@suse.de> Cc: Christoph Hellwig <hch@lst.de> Cc: Ming Lei <ming.lei@redhat.com> Cc: Johannes Thumshirn <johannes.thumshirn@wdc.com> Cc: Himanshu Madhani <himanshu.madhani@oracle.com> Signed-off-by: Bart Van Assche <bvanassche@acm.org> BUG: 187357408 Change-Id: If03083a13917bc2f88b6df7151e033a11ab1bc50 (cherry picked from commit f1a7f539c2720906fb10be0af3514b034e1a9fee git://git.kernel.dk/linux-block/ for-5.14/block) Signed-off-by: Bart Van Assche <bvanassche@google.com>
Introduce an rq-qos policy that assigns an I/O priority to requests based on blk-cgroup configuration settings. This policy has the following advantages over the ioprio_set() system call: - This policy is cgroup based so it has all the advantages of cgroups. - While ioprio_set() does not affect page cache writeback I/O, this rq-qos controller affects page cache writeback I/O for filesystems that support assiociating a cgroup with writeback I/O. See also Documentation/admin-guide/cgroup-v2.rst. Cc: Damien Le Moal <damien.lemoal@wdc.com> Cc: Hannes Reinecke <hare@suse.de> Cc: Christoph Hellwig <hch@lst.de> Cc: Ming Lei <ming.lei@redhat.com> Cc: Johannes Thumshirn <johannes.thumshirn@wdc.com> Cc: Himanshu Madhani <himanshu.madhani@oracle.com> Signed-off-by: Bart Van Assche <bvanassche@acm.org> BUG: 187357408 Change-Id: If51e608ad37ee7a3f57b507bb17900dcfcb263ed (cherry picked from commit ee9d2a55c960f152b5710078bbe399a4c51eb0a9 git://git.kernel.dk/linux-block/ for-5.14/block) Signed-off-by: Bart Van Assche <bvanassche@google.com>
Make the code easier to read by adding more comments. Reviewed-by: Damien Le Moal <damien.lemoal@wdc.com> Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com> Reviewed-by: Himanshu Madhani <himanshu.madhani@oracle.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Hannes Reinecke <hare@suse.de> Cc: Ming Lei <ming.lei@redhat.com> Signed-off-by: Bart Van Assche <bvanassche@acm.org> BUG: 187357408 Change-Id: If62eb600614d2883d72ee3bd7e7859ae66b24512 (cherry picked from commit 16c3afdb127bbff7d3552e076e568281765674b7 git://git.kernel.dk/linux-block/ for-5.14/block) Signed-off-by: Bart Van Assche <bvanassche@google.com>
Document the locking strategy by adding two lockdep_assert_held() statements. Reviewed-by: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com> Reviewed-by: Damien Le Moal <damien.lemoal@wdc.com> Reviewed-by: Hannes Reinecke <hare@suse.de> Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com> Reviewed-by: Himanshu Madhani <himanshu.madhani@oracle.com> Cc: Damien Le Moal <damien.lemoal@wdc.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Ming Lei <ming.lei@redhat.com> Signed-off-by: Bart Van Assche <bvanassche@acm.org> BUG: 187357408 Change-Id: Ie8cf0b0ae208c9cc87731a9c6d7df5e5e59332d5 (cherry picked from commit 91831ddfd7c6e3df9857526a76cfa88673ec0637 git://git.kernel.dk/linux-block/ for-5.14/block) Signed-off-by: Bart Van Assche <bvanassche@google.com>
Make __dd_dispatch_request() easier to read by removing two local variables. Reviewed-by: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com> Reviewed-by: Damien Le Moal <damien.lemoal@wdc.com> Reviewed-by: Hannes Reinecke <hare@suse.de> Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com> Reviewed-by: Himanshu Madhani <himanshu.madhani@oracle.com> Cc: Damien Le Moal <damien.lemoal@wdc.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Ming Lei <ming.lei@redhat.com> Signed-off-by: Bart Van Assche <bvanassche@acm.org> BUG: 187357408 Change-Id: I5567f7d02a2c628efb437058a1c103c7b123747a (cherry picked from commit f005b6ff19d2a961a2c3ae9c5f49d48fda143469 git://git.kernel.dk/linux-block/ for-5.14/block) Signed-off-by: Bart Van Assche <bvanassche@google.com>
Change "queue" into "sched" to make the function names reflect better the purpose of these functions. Reviewed-by: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com> Reviewed-by: Damien Le Moal <damien.lemoal@wdc.com> Reviewed-by: Hannes Reinecke <hare@suse.de> Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com> Reviewed-by: Himanshu Madhani <himanshu.madhani@oracle.com> Cc: Damien Le Moal <damien.lemoal@wdc.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Ming Lei <ming.lei@redhat.com> Signed-off-by: Bart Van Assche <bvanassche@acm.org> BUG: 187357408 Change-Id: I30825b379146dbaef4ff3f85148b2e788667a77c (cherry picked from commit a6e57fe5ab09c250fc741294e6321270a4364fec git://git.kernel.dk/linux-block/ for-5.14/block) Signed-off-by: Bart Van Assche <bvanassche@google.com>
Modern compilers complain if an out-of-range value is passed to a function argument that has an enumeration type. Let the compiler detect out-of-range data direction arguments instead of verifying the data_dir argument at runtime. Reviewed-by: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com> Reviewed-by: Hannes Reinecke <hare@suse.de> Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com> Reviewed-by: Himanshu Madhani <himanshu.madhani@oracle.com> Cc: Damien Le Moal <damien.lemoal@wdc.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Ming Lei <ming.lei@redhat.com> Signed-off-by: Bart Van Assche <bvanassche@acm.org> BUG: 187357408 Change-Id: I4ad8c106a86d17f3010e12e172702e77eca61e80 (cherry picked from commit d9baee13f8cf66a8fac9ec67fdb85ce419fcce3a git://git.kernel.dk/linux-block/ for-5.14/block) Signed-off-by: Bart Van Assche <bvanassche@google.com>
Define separate macros for integers and jiffies to improve readability. Use sysfs_emit() and kstrtoint() instead of sprintf() and simple_strtol(). The former functions are the recommended functions. Cc: Damien Le Moal <damien.lemoal@wdc.com> Cc: Hannes Reinecke <hare@suse.de> Cc: Christoph Hellwig <hch@lst.de> Cc: Ming Lei <ming.lei@redhat.com> Cc: Johannes Thumshirn <johannes.thumshirn@wdc.com> Cc: Himanshu Madhani <himanshu.madhani@oracle.com> Signed-off-by: Bart Van Assche <bvanassche@acm.org> BUG: 187357408 Change-Id: I4e0fd35124cd0319fcace0d1d5e3c113b60a213c (cherry picked from commit d9baee13f8cf66a8fac9ec67fdb85ce419fcce3a git://git.kernel.dk/linux-block/ for-5.14/block) Signed-off-by: Bart Van Assche <bvanassche@google.com>
…or synchronous requests For interactive workloads it is important that synchronous requests are not delayed. Hence reserve 25% of scheduler tags for synchronous requests. This patch still allows asynchronous requests to fill the hardware queues since blk_mq_init_sched() makes sure that the number of scheduler requests is the double of the hardware queue depth. From blk_mq_init_sched(): q->nr_requests = 2 * min_t(unsigned int, q->tag_set->queue_depth, BLKDEV_MAX_RQ); Cc: Damien Le Moal <damien.lemoal@wdc.com> Cc: Hannes Reinecke <hare@suse.de> Cc: Christoph Hellwig <hch@lst.de> Cc: Ming Lei <ming.lei@redhat.com> Cc: Johannes Thumshirn <johannes.thumshirn@wdc.com> Cc: Himanshu Madhani <himanshu.madhani@oracle.com> Signed-off-by: Bart Van Assche <bvanassche@acm.org> BUG: 187357408 Change-Id: Ib9cd753a39c8e5f5c45908001d69334130ef2067 (cherry picked from commit c970bc8292aaaf6f2d333d612e657df3a99f417c git://git.kernel.dk/linux-block/ for-5.14/block) Signed-off-by: Bart Van Assche <bvanassche@google.com> Signed-off-by: ralph950412 <ralph950412@gmail.com>
When dispatching the first request of a batch, the deadline_move_request() call clears .next_rq[] for the opposite data direction. .next_rq[] is not restored when changing data direction. Fix this by not clearing .next_rq[] and by keeping track of the data direction of a batch in a variable instead. This patch is a micro-optimization because: - The number of deadline_next_request() calls for the read direction is halved. - The number of times that deadline_next_request() returns NULL is reduced. Cc: Damien Le Moal <damien.lemoal@wdc.com> Cc: Hannes Reinecke <hare@suse.de> Cc: Christoph Hellwig <hch@lst.de> Cc: Ming Lei <ming.lei@redhat.com> Cc: Johannes Thumshirn <johannes.thumshirn@wdc.com> Cc: Himanshu Madhani <himanshu.madhani@oracle.com> Signed-off-by: Bart Van Assche <bvanassche@acm.org> BUG: 187357408 Change-Id: I582e99603a5443d75cf2b18a5daa2c93b5c66de3 (cherry picked from commit ea0fd2a525436ab5b9ada0f1953b0c0a29357311 git://git.kernel.dk/linux-block/ for-5.14/block) Signed-off-by: Bart Van Assche <bvanassche@google.com>
Maintain one dispatch list and one FIFO list per I/O priority class: RT, BE and IDLE. Maintain statistics for each priority level. Split the debugfs attributes per priority level as follows: $ ls /sys/kernel/debug/block/.../sched/ async_depth dispatch2 read_next_rq write2_fifo_list batching read0_fifo_list starved write_next_rq dispatch0 read1_fifo_list write0_fifo_list dispatch1 read2_fifo_list write1_fifo_list Cc: Damien Le Moal <damien.lemoal@wdc.com> Cc: Hannes Reinecke <hare@suse.de> Cc: Christoph Hellwig <hch@lst.de> Cc: Ming Lei <ming.lei@redhat.com> Cc: Johannes Thumshirn <johannes.thumshirn@wdc.com> Cc: Himanshu Madhani <himanshu.madhani@oracle.com> Signed-off-by: Bart Van Assche <bvanassche@acm.org> BUG: 187357408 Change-Id: I60451cfdb416ad27601dc3ffb4eb307fa6ff783f (cherry picked from commit 5b701a6e040ff8626ecf29ac06de9689efc00754 git://git.kernel.dk/linux-block/ for-5.14/block) Signed-off-by: Bart Van Assche <bvanassche@google.com>
Track I/O statistics per I/O priority and export these statistics to debugfs. These statistics help developers of the deadline scheduler. Cc: Damien Le Moal <damien.lemoal@wdc.com> Cc: Hannes Reinecke <hare@suse.de> Cc: Christoph Hellwig <hch@lst.de> Cc: Ming Lei <ming.lei@redhat.com> Cc: Johannes Thumshirn <johannes.thumshirn@wdc.com> Cc: Himanshu Madhani <himanshu.madhani@oracle.com> Signed-off-by: Bart Van Assche <bvanassche@acm.org> BUG: 187357408 Change-Id: I8e91693dc1d015060737fa2fc15f5f2ebee2530c (cherry picked from commit 9dc236caf2518c1e434be7a4f8fae60fb0be506a git://git.kernel.dk/linux-block/ for-5.14/block) Signed-off-by: Bart Van Assche <bvanassche@google.com>
Maintain statistics per cgroup and export these to user space. These statistics are essential for verifying whether the proper I/O priorities have been assigned to requests. An example of the statistics data with this patch applied: $ cat /sys/fs/cgroup/io.stat 11:2 rbytes=0 wbytes=0 rios=3 wios=0 dbytes=0 dios=0 [NONE] dispatched=0 inserted=0 merged=171 [RT] dispatched=0 inserted=0 merged=0 [BE] dispatched=0 inserted=0 merged=0 [IDLE] dispatched=0 inserted=0 merged=0 8:32 rbytes=2142720 wbytes=0 rios=105 wios=0 dbytes=0 dios=0 [NONE] dispatched=0 inserted=0 merged=171 [RT] dispatched=0 inserted=0 merged=0 [BE] dispatched=0 inserted=0 merged=0 [IDLE] dispatched=0 inserted=0 merged=0 Cc: Damien Le Moal <damien.lemoal@wdc.com> Cc: Hannes Reinecke <hare@suse.de> Cc: Christoph Hellwig <hch@lst.de> Cc: Ming Lei <ming.lei@redhat.com> Cc: Johannes Thumshirn <johannes.thumshirn@wdc.com> Cc: Himanshu Madhani <himanshu.madhani@oracle.com> Signed-off-by: Bart Van Assche <bvanassche@acm.org> BUG: 187357408 Change-Id: I8d976c62ba2c0397cbb18076f3e61d5ab246cbcf (cherry picked from commit f5dc926252cb31739809f7d27a8cbc9941b4d36d git://git.kernel.dk/linux-block/ for-5.14/block) Signed-off-by: Bart Van Assche <bvanassche@google.com> Signed-off-by: ralph950412 <ralph950412@gmail.com>
While one or more requests with a certain I/O priority are pending, do not
dispatch lower priority requests. Dispatch lower priority requests anyway
after the "aging" time has expired.
This patch has been tested as follows:
modprobe scsi_debug ndelay=1000000 max_queue=16 &&
sd='' &&
while [ -z "$sd" ]; do
sd=/dev/$(basename /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/*)
done &&
echo $((100*1000)) > /sys/block/$sd/queue/iosched/aging_expire &&
cd /sys/fs/cgroup/blkio/ &&
echo $$ >cgroup.procs &&
echo restrict-to-be >blkio.prio.class &&
mkdir -p hipri &&
cd hipri &&
echo none-to-rt >blkio.prio.class &&
{ max-iops -a1 -d32 -j1 -e mq-deadline $sd >& ~/low-pri.txt & } &&
echo $$ >cgroup.procs &&
max-iops -a1 -d32 -j1 -e mq-deadline $sd >& ~/hi-pri.txt
Result:
* 11000 IOPS for the high-priority job
* 40 IOPS for the low-priority job
If the aging expiry time is changed from 100s into 0, the IOPS results change
into 6712 and 6796 IOPS.
The max-iops script is a script that runs fio with the following arguments:
--bs=4K --gtod_reduce=1 --ioengine=libaio --ioscheduler=${arg_e} --runtime=60
--norandommap --rw=read --thread --buffered=0 --numjobs=${arg_j}
--iodepth=${arg_d} --iodepth_batch_submit=${arg_a}
--iodepth_batch_complete=$((arg_d / 2)) --name=${positional_argument_1}
--filename=${positional_argument_1}
Reviewed-by: Damien Le Moal <damien.lemoal@wdc.com>
Cc: Hannes Reinecke <hare@suse.de>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Ming Lei <ming.lei@redhat.com>
Cc: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Cc: Himanshu Madhani <himanshu.madhani@oracle.com>
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Change-Id: I99a0674b018d096ec96bbfa3008eedcfda5013da
BUG: 187357408
(cherry picked from commit 40d5d42992b0de3ae7961735ea15eef5bd385ebf git://git.kernel.dk/linux-block/ for-5.14/block)
Signed-off-by: Bart Van Assche <bvanassche@google.com>
Add ANDROID_OEM_DATA for implement of oem gki Bug: 188749221 Change-Id: Ide8378a898de01a34d8ca3c34472844cd4ffa71c Signed-off-by: Yang Yang <yang.yang@vivo.com>
Add ANDROID_OEM_DATA for implement of oem gki Bug: 188749221 Change-Id: I1feba2334aa34e3bc46eb9d0217118485405beb4 Signed-off-by: Yang Yang <yang.yang@vivo.com>
Enable CONFIG_BLK_CGROUP_IOCOST to help control IO resources. Bug: 188749221 Change-Id: I611b3ff5929d0a998fa6241967887803636b7588 Signed-off-by: Yang Yang <yang.yang@vivo.com>
Enable this controller such that it can be used in performance tests. Bug: 186902601 Change-Id: Icd863fec49e3f928b992834e07ae0660ba57ea65 Signed-off-by: Bart Van Assche <bvanassche@google.com>
commit dc5723b02e523b ("kbuild: add support for Clang LTO")
from upstream had included scripts/Makefile.lib, but in
android12-5.4 it seems missing and makes ld_flags always empty.
Bug: 215292602
Fixes: 2e39b40 ("ANDROID: kbuild: add support for Clang LTO")
Signed-off-by: Lecopzer Chen <lecopzer.chen@mediatek.com>
Change-Id: I4fcbf84e75df0dcd44b175d722fdf6869101e191
Signed-off-by: Pranav Vashi <neobuddy89@gmail.com>
Signed-off-by: mukesh22584 <mks22584@gmail.com>
(cherry picked from commit 42de9bd5104326cb6a83501b2a38de26d981422a) Signed-off-by: TogoFire <togofire@mailfence.com> Change-Id: I1f99534b44d32c1ac146745835d3f85619732cff Signed-off-by: mukesh22584 <mks22584@gmail.com>
(cherry picked from commit cc1c1302f40ec4f5649611ed5789b6904820dce0) Signed-off-by: TogoFire <togofire@mailfence.com> Change-Id: I291397bc438d8228daedf553e4b81ee6e91d206c Signed-off-by: mukesh22584 <mks22584@gmail.com>
(cherry picked from commit 207ec3f455077a403e5294ed094c4c456cee2e23) Signed-off-by: TogoFire <togofire@mailfence.com> Change-Id: Id1206a6fa701c593b0aecfe3dd525301f7c29d0d Signed-off-by: mukesh22584 <mks22584@gmail.com>
(cherry picked from commit 8d6328184896868667bbab93f835a6c6bd7e6af4) Signed-off-by: TogoFire <togofire@mailfence.com> Change-Id: Ieb6df4dfe03a28760c6747d204111430742d1f76 Signed-off-by: mukesh22584 <mks22584@gmail.com>
Log:
In file included from ../include/vdso/const.h:5,
from ../include/linux/const.h:4,
from ../include/linux/list.h:8,
from ../include/linux/wait.h:7,
from ../include/linux/wait_bit.h:8,
from ../include/linux/fs.h:6,
from ../fs/ntfs3/attrib.c:9:
../fs/ntfs3/ntfs_fs.h:948:41: error: expected ')' before 'bits'
948 | static inline size_t bitmap_size(size_t bits)
| ^~~~
../include/uapi/linux/const.h:32:44: note: in definition of macro '__ALIGN_KERNEL_MASK'
32 | #define __ALIGN_KERNEL_MASK(x, mask) (((x) + (mask)) & ~(mask))
| ^
../include/linux/kernel.h:33:33: note: in expansion of macro '__ALIGN_KERNEL'
33 | #define ALIGN(x, a) __ALIGN_KERNEL((x), (a))
| ^~~~~~~~~~~~~~
../include/linux/bitmap.h:219:35: note: in expansion of macro 'ALIGN'
219 | #define bitmap_size(nbits) ((ALIGN(nbits, BITS_PER_LONG) / BITS_PER_BYTE))
| ^~~~~
../fs/ntfs3/ntfs_fs.h:948:22: note: in expansion of macro 'bitmap_size'
948 | static inline size_t bitmap_size(size_t bits)
| ^~~~~~~~~~~
../include/uapi/linux/const.h:32:47: error: expected ')' before '+' token
32 | #define __ALIGN_KERNEL_MASK(x, mask) (((x) + (mask)) & ~(mask))
| ^
../include/uapi/linux/const.h:31:41: note: in expansion of macro '__ALIGN_KERNEL_MASK'
31 | #define __ALIGN_KERNEL(x, a) __ALIGN_KERNEL_MASK(x, (typeof(x))(a) - 1)
| ^~~~~~~~~~~~~~~~~~~
../include/linux/kernel.h:33:33: note: in expansion of macro '__ALIGN_KERNEL'
33 | #define ALIGN(x, a) __ALIGN_KERNEL((x), (a))
| ^~~~~~~~~~~~~~
../include/linux/bitmap.h:219:35: note: in expansion of macro 'ALIGN'
219 | #define bitmap_size(nbits) ((ALIGN(nbits, BITS_PER_LONG) / BITS_PER_BYTE))
| ^~~~~
../fs/ntfs3/ntfs_fs.h:948:22: note: in expansion of macro 'bitmap_size'
948 | static inline size_t bitmap_size(size_t bits)
| ^~~~~~~~~~~
../include/uapi/linux/const.h:32:57: error: expected ')' before '&' token
32 | #define __ALIGN_KERNEL_MASK(x, mask) (((x) + (mask)) & ~(mask))
| ^
../include/uapi/linux/const.h:31:41: note: in expansion of macro '__ALIGN_KERNEL_MASK'
31 | #define __ALIGN_KERNEL(x, a) __ALIGN_KERNEL_MASK(x, (typeof(x))(a) - 1)
| ^~~~~~~~~~~~~~~~~~~
../include/linux/kernel.h:33:33: note: in expansion of macro '__ALIGN_KERNEL'
33 | #define ALIGN(x, a) __ALIGN_KERNEL((x), (a))
| ^~~~~~~~~~~~~~
../include/linux/bitmap.h:219:35: note: in expansion of macro 'ALIGN'
219 | #define bitmap_size(nbits) ((ALIGN(nbits, BITS_PER_LONG) / BITS_PER_BYTE))
| ^~~~~
../fs/ntfs3/ntfs_fs.h:948:22: note: in expansion of macro 'bitmap_size'
948 | static inline size_t bitmap_size(size_t bits)
| ^~~~~~~~~~~
Fix: 463074c ("bitmap: introduce generic optimized bitmap_size()")
Change-Id: c7afd3d5c99ce5a3c7ec53afb3736fa2f073c665
Signed-off-by: TogoFire <togofire@mailfence.com>
Signed-off-by: mukesh22584 <mks22584@gmail.com>
Allow the compat vdso (32b) to be compiled as either THUMB2 (default) or
ARM.
For THUMB2, the register r7 is reserved for the frame pointer, but
code in arch/arm64/include/asm/vdso/compat_gettimeofday.h
uses r7. Explicitly set -fomit-frame-pointer, since unwinding through
interworked THUMB2 and ARM is unreliable anyways. See also how
CONFIG_UNWINDER_FRAME_POINTER cannot be selected for
CONFIG_THUMB2_KERNEL for ARCH=arm.
This also helps toolchains that differ in their implicit value if the
choice of -f{no-}omit-frame-pointer is left unspecified, to not error on
the use of r7.
2019 Q4 ARM AAPCS seeks to standardize the use of r11 as the reserved
frame pointer register, but no production compiler that can compile the
Linux kernel currently implements this. We're actively discussing such
a transition with ARM toolchain developers currently.
Reported-by: Luis Lozano <llozano@google.com>
Signed-off-by: Nick Desaulniers <ndesaulniers@google.com>
Change-Id: Iae24ca6ceed2815c3a51f7b61bd4d37d426f422d
Tested-by: Manoj Gupta <manojgupta@google.com>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Cc: Stephen Boyd <swboyd@google.com>
Cc: Robin Murphy <robin.murphy@arm.com>
Cc: Dave Martin <Dave.Martin@arm.com>
Link: https://static.docs.arm.com/ihi0042/i/aapcs32.pdf
Link: https://bugs.chromium.org/p/chromium/issues/detail?id=1084372
Link: https://lore.kernel.org/r/20200608205711.109418-1-ndesaulniers@google.com
Signed-off-by: Will Deacon <will@kernel.org>
(cherry picked from commit 66e83e9901a239fee5537e49738e82d2e2e3460c)
Signed-off-by: TogoFire <togofire@mailfence.com>
Signed-off-by: mukesh22584 <mks22584@gmail.com>
flush_dcache_page() ensures that the 'PG_dcache_clean' flag for its 'page' argument is clear so that cache maintenance will be performed if the page is mapped into userspace with execute permissions. Newly allocated pages have this flag clear, so there is no need to call flush_dcache_page() for the compat vdso or signal pages. Remove the redundant calls. Signed-off-by: Will Deacon <will@kernel.org> Change-Id: I7a121831c70e13e9ae2572bfd6d6bd029b5f57d2 Reviewed-by: Vincenzo Frascino <vincenzo.frascino@arm.com> Link: https://lore.kernel.org/r/20210318170738.7756-3-will@kernel.org Signed-off-by: Catalin Marinas <catalin.marinas@arm.com> (cherry picked from commit c0f145ad34f4e18a841871b97eea76002eb8abf9) Signed-off-by: TogoFire <togofire@mailfence.com> Signed-off-by: mukesh22584 <mks22584@gmail.com>
There's no need to allocate the compat vDSO and signal pages using GFP_ATOMIC allocations, so use GFP_KERNEL instead. Signed-off-by: Will Deacon <will@kernel.org> Change-Id: Ib4c289103c69f8e1c0f482a631dd2878d1e9e2ac Reviewed-by: Vincenzo Frascino <vincenzo.frascino@arm.com> Link: https://lore.kernel.org/r/20210318170738.7756-2-will@kernel.org Signed-off-by: Catalin Marinas <catalin.marinas@arm.com> (cherry picked from commit 70b8d8705e070a7bb29dd49e05c78ba41a903719) Signed-off-by: TogoFire <togofire@mailfence.com> Signed-off-by: mukesh22584 <mks22584@gmail.com>
Use the EOR3 instruction to implement xor_blocks() if the instruction is available, which is the case if the CPU implements the SHA-3 extension. This is about 20% faster on Apple M1 when using the 5-way version. Signed-off-by: Ard Biesheuvel <ardb@kernel.org> Change-Id: I5d8a0b59ab3ca6218d63d10deba26dd22b31c431 Link: https://lore.kernel.org/r/20211213140252.2856053-1-ardb@kernel.org Signed-off-by: Catalin Marinas <catalin.marinas@arm.com> (cherry picked from commit 640c3abd8e8d45470f4f4fe113c6579173215dcd) Signed-off-by: TogoFire <togofire@mailfence.com> Signed-off-by: mukesh22584 <mks22584@gmail.com>
should rebase this later Signed-off-by: FPSensor <gkartyt@gmail.com>
commit ab8f58a ("PM / devfreq: Set min/max_freq when adding the devfreq device") introduces a change where an error in finding the ceil or floor is returned as a zero frequency. This return of zero is treated as error condition from the callsites. It is perfectly valid for a device to have a zero frequency, usually it denotes a power collapse. This valid return of zero frequency ends up being treated as an error condition. Fix it. Change-Id: I5eb6fa622d6fe09207746b96dce05d0b58b233dc
It is perfectly valid for a device to have a zero frequency, usually it denotes a power collapse. To support this, fix the PM suspend callback to allow the suspend_freq to be zero. Change-Id: Id10f95b59b219e82e0695f80361aa6b35cdc5137
With commit commit 921884ca1498 ("devfreq: Fix PM
callbacks to support zero frequency"), suspend_freq
of zero is considered valid.
However, the devfreq_set_target is called with zero frequency.
To avoid this, do not call devfreq_set_target if the
suspend_freq is less than the minimun allowed frequency.
Change-Id: I506165d28395eb67138ae2dac53e842357809bbb
Recently a discussion about stability and performance of a system involving a high rate of kfree_rcu() calls surfaced on the list [1] which led to another discussion how to prepare for this situation. This patch adds basic batching support for kfree_rcu(). It is "basic" because we do none of the slab management, dynamic allocation, code moving or any of the other things, some of which previous attempts did [2]. These fancier improvements can be follow-up patches and there are different ideas being discussed in those regards. This is an effort to start simple, and build up from there. In the future, an extension to use kfree_bulk and possibly per-slab batching could be done to further improve performance due to cache-locality and slab-specific bulk free optimizations. By using an array of pointers, the worker thread processing the work would need to read lesser data since it does not need to deal with large rcu_head(s) any longer. Torture tests follow in the next patch and show improvements of around 5x reduction in number of grace periods on a 16 CPU system. More details and test data are in that patch. There is an implication with rcu_barrier() with this patch. Since the kfree_rcu() calls can be batched, and may not be handed yet to the RCU machinery in fact, the monitor may not have even run yet to do the queue_rcu_work(), there seems no easy way of implementing rcu_barrier() to wait for those kfree_rcu()s that are already made. So this means a kfree_rcu() followed by an rcu_barrier() does not imply that memory will be freed once rcu_barrier() returns. Another implication is higher active memory usage (although not run-away..) until the kfree_rcu() flooding ends, in comparison to without batching. More details about this are in the second patch which adds an rcuperf test. Finally, in the near future we will get rid of kfree_rcu() special casing within RCU such as in rcu_do_batch and switch everything to just batching. Currently we don't do that since timer subsystem is not yet up and we cannot schedule the kfree_rcu() monitor as the timer subsystem's lock are not initialized. That would also mean getting rid of kfree_call_rcu_nobatch() entirely. [1] http://lore.kernel.org/lkml/20190723035725-mutt-send-email-mst@kernel.org [2] https://lkml.org/lkml/2017/12/19/824 Cc: kernel-team@android.com Cc: kernel-team@lge.com Co-developed-by: Byungchul Park <byungchul.park@lge.com> Change-Id: I01d066a56330cbf0bfebc5d7aaf84db865d3fe3d [ paulmck: Applied 0day and Paul Walmsley feedback on ->monitor_todo. ] [ paulmck: Make it work during early boot. ] [ paulmck: Add a crude early boot self-test. ] [ paulmck: Style adjustments and experimental docbook structure header. ] Link: https://lore.kernel.org/lkml/alpine.DEB.2.21.9999.1908161931110.32497@viisi.sifive.com/T/#me9956f66cb611b95d26ae92700e1d901f46e8c59 (cherry picked from commit a35d16905efc6ad5523d864a5c6efcb1e657e386)
During testing, it was observed that amount of memory consumed due kfree_rcu() batching is 300-400MB. Previously we had only a single head_free pointer pointing to the list of rcu_head(s) that are to be freed after a grace period. Until this list is drained, we cannot queue any more objects on it since such objects may not be ready to be reclaimed when the worker thread eventually gets to drainin g the head_free list. We can do better by maintaining multiple lists as done by this patch. Testing shows that memory consumption came down by around 100-150MB with just adding another list. Adding more than 1 additional list did not show any improvement. Suggested-by: Paul E. McKenney <paulmck@linux.ibm.com> Change-Id: If85626c133abc7009fc7d0f0c365066796efadf6 [ paulmck: Code style and initialization handling. ] [ paulmck: Fix field name, reported by kbuild test robot <lkp@intel.com>. ] (cherry picked from commit 0392bebebf26f09434e6c7ca4c09c014efeef76a)
This commit applies RCU's debug_objects debugging to the new batched kfree_rcu() implementations. The object is queued at the kfree_rcu() call and dequeued during reclaim. Tested that enabling CONFIG_DEBUG_OBJECTS_RCU_HEAD successfully detects double kfree_rcu() calls. Change-Id: Ib3645d67fea285a8a836a6ba7bd5a3d9325cf94c [ paulmck: Fix IRQ per kbuild test robot <lkp@intel.com> feedback. ] (cherry picked from commit e99637becb2e684bee2b9117f817f4d1346b8353)
The kfree_rcu() logic can be improved further by using kfree_bulk() interface along with "basic batching support" introduced earlier. The are at least two advantages of using "bulk" interface: - in case of large number of kfree_rcu() requests kfree_bulk() reduces the per-object overhead caused by calling kfree() per-object. - reduces the number of cache-misses due to "pointer chasing" between objects which can be far spread between each other. This approach defines a new kfree_rcu_bulk_data structure that stores pointers in an array with a specific size. Number of entries in that array depends on PAGE_SIZE making kfree_rcu_bulk_data structure to be exactly one page. Since it deals with "block-chain" technique there is an extra need in dynamic allocation when a new block is required. Memory is allocated with GFP_NOWAIT | __GFP_NOWARN flags, i.e. that allows to skip direct reclaim under low memory condition to prevent stalling and fails silently under high memory pressure. The "emergency path" gets maintained when a system is run out of memory. In that case objects are linked into regular list. The "rcuperf" was run to analyze this change in terms of memory consumption and kfree_bulk() throughput. 1) Testing on the Intel(R) Xeon(R) W-2135 CPU @ 3.70GHz, 12xCPUs with following parameters: kfree_loops=200000 kfree_alloc_num=1000 kfree_rcu_test=1 kfree_vary_obj_size=1 dev.2020.01.10a branch Default / CONFIG_SLAB 53607352517 ns, loops: 200000, batches: 1885, memory footprint: 1248MB 53529637912 ns, loops: 200000, batches: 1921, memory footprint: 1193MB 53570175705 ns, loops: 200000, batches: 1929, memory footprint: 1250MB Patch / CONFIG_SLAB 23981587315 ns, loops: 200000, batches: 810, memory footprint: 1219MB 23879375281 ns, loops: 200000, batches: 822, memory footprint: 1190MB 24086841707 ns, loops: 200000, batches: 794, memory footprint: 1380MB Default / CONFIG_SLUB 51291025022 ns, loops: 200000, batches: 1713, memory footprint: 741MB 51278911477 ns, loops: 200000, batches: 1671, memory footprint: 719MB 51256183045 ns, loops: 200000, batches: 1719, memory footprint: 647MB Patch / CONFIG_SLUB 50709919132 ns, loops: 200000, batches: 1618, memory footprint: 456MB 50736297452 ns, loops: 200000, batches: 1633, memory footprint: 507MB 50660403893 ns, loops: 200000, batches: 1628, memory footprint: 429MB in case of CONFIG_SLAB there is double increase in performance and slightly higher memory usage. As for CONFIG_SLUB, the performance figures are better together with lower memory usage. 2) Testing on the HiKey-960, arm64, 8xCPUs with below parameters: CONFIG_SLAB=y kfree_loops=200000 kfree_alloc_num=1000 kfree_rcu_test=1 102898760401 ns, loops: 200000, batches: 5822, memory footprint: 158MB 89947009882 ns, loops: 200000, batches: 6715, memory footprint: 115MB rcuperf shows approximately ~12% better throughput in case of using "bulk" interface. The "drain logic" or its RCU callback does the work faster that leads to better throughput. Change-Id: Ic12855e52b2ef2da3377f120bd162c404460cede Tested-by: Joel Fernandes (Google) <joel@joelfernandes.org> (cherry picked from commit 34c881745549e78f31ec65f319457c82aacc53bd)
It is possible that one of the channels cannot be detached
because its free channel is busy and previously queued data
has not been processed yet. On the other hand, another
channel can be successfully detached causing the monitor
work to stop.
Prevent that by rescheduling the monitor work if there are
any channels in the pending state after a detach attempt.
Fixes: 34c881745549e ("rcu: Support kfree_bulk() interface in kfree_rcu()")
Acked-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Change-Id: Id41e32135bf66486f6dfd78fb52294e6ff3c651a
(cherry picked from commit 594aa5975b9b5cfe9edaec06170e43b8c0607377)
Because the ->monitor_todo field is always protected by krcp->lock, this commit downgrades from xchg() to non-atomic unmarked assignment statements. Change-Id: Ied5798b21f9b96bab64b193b2308248b9ec0ed46 [ paulmck: Update to include early-boot kick code. ] (cherry picked from commit 569d767087ef56a59bc2d1d5f25ee447eeae442a)
To reduce grace periods and improve kfree() performance, we have done batching recently dramatically bringing down the number of grace periods while giving us the ability to use kfree_bulk() for efficient kfree'ing. However, this has increased the likelihood of OOM condition under heavy kfree_rcu() flood on small memory systems. This patch introduces a shrinker which starts grace periods right away if the system is under memory pressure due to existence of objects that have still not started a grace period. With this patch, I do not observe an OOM anymore on a system with 512MB RAM and 8 CPUs, with the following rcuperf options: rcuperf.kfree_loops=20000 rcuperf.kfree_alloc_num=8000 rcuperf.kfree_rcu_test=1 rcuperf.kfree_mult=2 Otherwise it easily OOMs with the above parameters. NOTE: 1. On systems with no memory pressure, the patch has no effect as intended. 2. In the future, we can use this same mechanism to prevent grace periods from happening even more, by relying on shrinkers carefully. Cc: urezki@gmail.com Change-Id: Iafb6d5f174b4ea0a710f5309e98b1743a466f5ac (cherry picked from commit 9154244c1ab6c9db4f1f25ac8f73bd46dba64287)
We can relax the correctness of counting of number of queued objects in favor of not hurting performance, by locklessly sampling per-cpu counters. This should be Ok since under high memory pressure, it should not matter if we are off by a few objects while counting. The shrinker will still do the reclaim. Change-Id: Ia2c5c49f91e68543ae7a120e6d2b62735ddeb997 [ paulmck: Remove unused "flags" variable. ] (cherry picked from commit a6a82ce18ba443186545d3fefbee8b9419a859dc)
…com/kernel/common into v6.s * 'android11-5.4-lts' of https://android.googlesource.com/kernel/common: (184 commits) Linux 5.4.302 Input: pegasus-notetaker - fix potential out-of-bounds access Input: remove third argument of usb_maxpacket() usb: deprecate the third argument of usb_maxpacket() ata: libata-scsi: Fix system suspend for a security locked drive fs/proc: fix uaf in proc_readdir_de() pmdomain: imx: Fix reference count leak in imx_gpc_remove pmdomain: arm: scmi: Fix genpd leak on provider registration failure net: netpoll: fix incorrect refcount handling causing incorrect cleanup net: qede: Initialize qede_ll_ops with designated initializer uio_hv_generic: Set event for all channels on the device net: ethernet: ti: netcp: Standardize knav_dma_open_channel to return NULL on error ALSA: usb-audio: fix uac2 clock source at terminal parser mm/page_alloc: fix hash table order logging in alloc_large_system_hash() kconfig/nconf: Initialize the default locale at startup kconfig/mconf: Initialize the default locale at startup vsock: Ignore signal/timeout on connect() if already established s390/ctcm: Fix double-kfree net: openvswitch: remove never-working support for setting nsh fields mlxsw: spectrum: Fix memory leak in mlxsw_sp_flower_stats() ...
Signed-off-by: FPSensor <gkartyt@gmail.com>
Contributor
Author
|
@Flopster101 @elitetest1 after tests u can do a final check and we can merge it |
Member
|
anashe |
elitetest1
pushed a commit
that referenced
this pull request
Dec 19, 2025
…-bit long
Switch most of BPF helper definitions from returning int to long. These
definitions are coming from comments in BPF UAPI header and are used to
generate bpf_helper_defs.h (under libbpf) to be later included and used from
BPF programs.
In actual in-kernel implementation, all the helpers are defined as returning
u64, but due to some historical reasons, most of them are actually defined as
returning int in UAPI (usually, to return 0 on success, and negative value on
error).
This actually causes Clang to quite often generate sub-optimal code, because
compiler believes that return value is 32-bit, and in a lot of cases has to be
up-converted (usually with a pair of 32-bit bit shifts) to 64-bit values,
before they can be used further in BPF code.
Besides just "polluting" the code, these 32-bit shifts quite often cause
problems for cases in which return value matters. This is especially the case
for the family of bpf_probe_read_str() functions. There are few other similar
helpers (e.g., bpf_read_branch_records()), in which return value is used by
BPF program logic to record variable-length data and process it. For such
cases, BPF program logic carefully manages offsets within some array or map to
read variable-length data. For such uses, it's crucial for BPF verifier to
track possible range of register values to prove that all the accesses happen
within given memory bounds. Those extraneous zero-extending bit shifts,
inserted by Clang (and quite often interleaved with other code, which makes
the issues even more challenging and sometimes requires employing extra
per-variable compiler barriers), throws off verifier logic and makes it mark
registers as having unknown variable offset. We'll study this pattern a bit
later below.
Another common pattern is to check return of BPF helper for non-zero state to
detect error conditions and attempt alternative actions in such case. Even in
this simple and straightforward case, this 32-bit vs BPF's native 64-bit mode
quite often leads to sub-optimal and unnecessary extra code. We'll look at
this pattern as well.
Clang's BPF target supports two modes of code generation: ALU32, in which it
is capable of using lower 32-bit parts of registers, and no-ALU32, in which
only full 64-bit registers are being used. ALU32 mode somewhat mitigates the
above described problems, but not in all cases.
This patch switches all the cases in which BPF helpers return 0 or negative
error from returning int to returning long. It is shown below that such change
in definition leads to equivalent or better code. No-ALU32 mode benefits more,
but ALU32 mode doesn't degrade or still gets improved code generation.
Another class of cases switched from int to long are bpf_probe_read_str()-like
helpers, which encode successful case as non-negative values, while still
returning negative value for errors.
In all of such cases, correctness is preserved due to two's complement
encoding of negative values and the fact that all helpers return values with
32-bit absolute value. Two's complement ensures that for negative values
higher 32 bits are all ones and when truncated, leave valid negative 32-bit
value with the same value. Non-negative values have upper 32 bits set to zero
and similarly preserve value when high 32 bits are truncated. This means that
just casting to int/u32 is correct and efficient (and in ALU32 mode doesn't
require any extra shifts).
To minimize the chances of regressions, two code patterns were investigated,
as mentioned above. For both patterns, BPF assembly was analyzed in
ALU32/NO-ALU32 compiler modes, both with current 32-bit int return type and
new 64-bit long return type.
Case 1. Variable-length data reading and concatenation. This is quite
ubiquitous pattern in tracing/monitoring applications, reading data like
process's environment variables, file path, etc. In such case, many pieces of
string-like variable-length data are read into a single big buffer, and at the
end of the process, only a part of array containing actual data is sent to
user-space for further processing. This case is tested in test_varlen.c
selftest (in the next patch). Code flow is roughly as follows:
void *payload = &sample->payload;
u64 len;
len = bpf_probe_read_kernel_str(payload, MAX_SZ1, &source_data1);
if (len <= MAX_SZ1) {
payload += len;
sample->len1 = len;
}
len = bpf_probe_read_kernel_str(payload, MAX_SZ2, &source_data2);
if (len <= MAX_SZ2) {
payload += len;
sample->len2 = len;
}
/* and so on */
sample->total_len = payload - &sample->payload;
/* send over, e.g., perf buffer */
There could be two variations with slightly different code generated: when len
is 64-bit integer and when it is 32-bit integer. Both variations were analysed.
BPF assembly instructions between two successive invocations of
bpf_probe_read_kernel_str() were used to check code regressions. Results are
below, followed by short analysis. Left side is using helpers with int return
type, the right one is after the switch to long.
ALU32 + INT ALU32 + LONG
=========== ============
64-BIT (13 insns): 64-BIT (10 insns):
------------------------------------ ------------------------------------
17: call 115 17: call 115
18: if w0 > 256 goto +9 <LBB0_4> 18: if r0 > 256 goto +6 <LBB0_4>
19: w1 = w0 19: r1 = 0 ll
20: r1 <<= 32 21: *(u64 *)(r1 + 0) = r0
21: r1 s>>= 32 22: r6 = 0 ll
22: r2 = 0 ll 24: r6 += r0
24: *(u64 *)(r2 + 0) = r1 00000000000000c8 <LBB0_4>:
25: r6 = 0 ll 25: r1 = r6
27: r6 += r1 26: w2 = 256
00000000000000e0 <LBB0_4>: 27: r3 = 0 ll
28: r1 = r6 29: call 115
29: w2 = 256
30: r3 = 0 ll
32: call 115
32-BIT (11 insns): 32-BIT (12 insns):
------------------------------------ ------------------------------------
17: call 115 17: call 115
18: if w0 > 256 goto +7 <LBB1_4> 18: if w0 > 256 goto +8 <LBB1_4>
19: r1 = 0 ll 19: r1 = 0 ll
21: *(u32 *)(r1 + 0) = r0 21: *(u32 *)(r1 + 0) = r0
22: w1 = w0 22: r0 <<= 32
23: r6 = 0 ll 23: r0 >>= 32
25: r6 += r1 24: r6 = 0 ll
00000000000000d0 <LBB1_4>: 26: r6 += r0
26: r1 = r6 00000000000000d8 <LBB1_4>:
27: w2 = 256 27: r1 = r6
28: r3 = 0 ll 28: w2 = 256
30: call 115 29: r3 = 0 ll
31: call 115
In ALU32 mode, the variant using 64-bit length variable clearly wins and
avoids unnecessary zero-extension bit shifts. In practice, this is even more
important and good, because BPF code won't need to do extra checks to "prove"
that payload/len are within good bounds.
32-bit len is one instruction longer. Clang decided to do 64-to-32 casting
with two bit shifts, instead of equivalent `w1 = w0` assignment. The former
uses extra register. The latter might potentially lose some range information,
but not for 32-bit value. So in this case, verifier infers that r0 is [0, 256]
after check at 18:, and shifting 32 bits left/right keeps that range intact.
We should probably look into Clang's logic and see why it chooses bitshifts
over sub-register assignments for this.
NO-ALU32 + INT NO-ALU32 + LONG
============== ===============
64-BIT (14 insns): 64-BIT (10 insns):
------------------------------------ ------------------------------------
17: call 115 17: call 115
18: r0 <<= 32 18: if r0 > 256 goto +6 <LBB0_4>
19: r1 = r0 19: r1 = 0 ll
20: r1 >>= 32 21: *(u64 *)(r1 + 0) = r0
21: if r1 > 256 goto +7 <LBB0_4> 22: r6 = 0 ll
22: r0 s>>= 32 24: r6 += r0
23: r1 = 0 ll 00000000000000c8 <LBB0_4>:
25: *(u64 *)(r1 + 0) = r0 25: r1 = r6
26: r6 = 0 ll 26: r2 = 256
28: r6 += r0 27: r3 = 0 ll
00000000000000e8 <LBB0_4>: 29: call 115
29: r1 = r6
30: r2 = 256
31: r3 = 0 ll
33: call 115
32-BIT (13 insns): 32-BIT (13 insns):
------------------------------------ ------------------------------------
17: call 115 17: call 115
18: r1 = r0 18: r1 = r0
19: r1 <<= 32 19: r1 <<= 32
20: r1 >>= 32 20: r1 >>= 32
21: if r1 > 256 goto +6 <LBB1_4> 21: if r1 > 256 goto +6 <LBB1_4>
22: r2 = 0 ll 22: r2 = 0 ll
24: *(u32 *)(r2 + 0) = r0 24: *(u32 *)(r2 + 0) = r0
25: r6 = 0 ll 25: r6 = 0 ll
27: r6 += r1 27: r6 += r1
00000000000000e0 <LBB1_4>: 00000000000000e0 <LBB1_4>:
28: r1 = r6 28: r1 = r6
29: r2 = 256 29: r2 = 256
30: r3 = 0 ll 30: r3 = 0 ll
32: call 115 32: call 115
In NO-ALU32 mode, for the case of 64-bit len variable, Clang generates much
superior code, as expected, eliminating unnecessary bit shifts. For 32-bit
len, code is identical.
So overall, only ALU-32 32-bit len case is more-or-less equivalent and the
difference stems from internal Clang decision, rather than compiler lacking
enough information about types.
Case 2. Let's look at the simpler case of checking return result of BPF helper
for errors. The code is very simple:
long bla;
if (bpf_probe_read_kenerl(&bla, sizeof(bla), 0))
return 1;
else
return 0;
ALU32 + CHECK (9 insns) ALU32 + CHECK (9 insns)
==================================== ====================================
0: r1 = r10 0: r1 = r10
1: r1 += -8 1: r1 += -8
2: w2 = 8 2: w2 = 8
3: r3 = 0 3: r3 = 0
4: call 113 4: call 113
5: w1 = w0 5: r1 = r0
6: w0 = 1 6: w0 = 1
7: if w1 != 0 goto +1 <LBB2_2> 7: if r1 != 0 goto +1 <LBB2_2>
8: w0 = 0 8: w0 = 0
0000000000000048 <LBB2_2>: 0000000000000048 <LBB2_2>:
9: exit 9: exit
Almost identical code, the only difference is the use of full register
assignment (r1 = r0) vs half-registers (w1 = w0) in instruction #5. On 32-bit
architectures, new BPF assembly might be slightly less optimal, in theory. But
one can argue that's not a big issue, given that use of full registers is
still prevalent (e.g., for parameter passing).
NO-ALU32 + CHECK (11 insns) NO-ALU32 + CHECK (9 insns)
==================================== ====================================
0: r1 = r10 0: r1 = r10
1: r1 += -8 1: r1 += -8
2: r2 = 8 2: r2 = 8
3: r3 = 0 3: r3 = 0
4: call 113 4: call 113
5: r1 = r0 5: r1 = r0
6: r1 <<= 32 6: r0 = 1
7: r1 >>= 32 7: if r1 != 0 goto +1 <LBB2_2>
8: r0 = 1 8: r0 = 0
9: if r1 != 0 goto +1 <LBB2_2> 0000000000000048 <LBB2_2>:
10: r0 = 0 9: exit
0000000000000058 <LBB2_2>:
11: exit
NO-ALU32 is a clear improvement, getting rid of unnecessary zero-extension bit
shifts.
Change-Id: Ie4ba541847b25df0d89042e74ee18c7b3d99d091
Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20200623032224.4020118-1-andriin@fb.com
Flopster101
pushed a commit
that referenced
this pull request
Jan 15, 2026
…-bit long
Switch most of BPF helper definitions from returning int to long. These
definitions are coming from comments in BPF UAPI header and are used to
generate bpf_helper_defs.h (under libbpf) to be later included and used from
BPF programs.
In actual in-kernel implementation, all the helpers are defined as returning
u64, but due to some historical reasons, most of them are actually defined as
returning int in UAPI (usually, to return 0 on success, and negative value on
error).
This actually causes Clang to quite often generate sub-optimal code, because
compiler believes that return value is 32-bit, and in a lot of cases has to be
up-converted (usually with a pair of 32-bit bit shifts) to 64-bit values,
before they can be used further in BPF code.
Besides just "polluting" the code, these 32-bit shifts quite often cause
problems for cases in which return value matters. This is especially the case
for the family of bpf_probe_read_str() functions. There are few other similar
helpers (e.g., bpf_read_branch_records()), in which return value is used by
BPF program logic to record variable-length data and process it. For such
cases, BPF program logic carefully manages offsets within some array or map to
read variable-length data. For such uses, it's crucial for BPF verifier to
track possible range of register values to prove that all the accesses happen
within given memory bounds. Those extraneous zero-extending bit shifts,
inserted by Clang (and quite often interleaved with other code, which makes
the issues even more challenging and sometimes requires employing extra
per-variable compiler barriers), throws off verifier logic and makes it mark
registers as having unknown variable offset. We'll study this pattern a bit
later below.
Another common pattern is to check return of BPF helper for non-zero state to
detect error conditions and attempt alternative actions in such case. Even in
this simple and straightforward case, this 32-bit vs BPF's native 64-bit mode
quite often leads to sub-optimal and unnecessary extra code. We'll look at
this pattern as well.
Clang's BPF target supports two modes of code generation: ALU32, in which it
is capable of using lower 32-bit parts of registers, and no-ALU32, in which
only full 64-bit registers are being used. ALU32 mode somewhat mitigates the
above described problems, but not in all cases.
This patch switches all the cases in which BPF helpers return 0 or negative
error from returning int to returning long. It is shown below that such change
in definition leads to equivalent or better code. No-ALU32 mode benefits more,
but ALU32 mode doesn't degrade or still gets improved code generation.
Another class of cases switched from int to long are bpf_probe_read_str()-like
helpers, which encode successful case as non-negative values, while still
returning negative value for errors.
In all of such cases, correctness is preserved due to two's complement
encoding of negative values and the fact that all helpers return values with
32-bit absolute value. Two's complement ensures that for negative values
higher 32 bits are all ones and when truncated, leave valid negative 32-bit
value with the same value. Non-negative values have upper 32 bits set to zero
and similarly preserve value when high 32 bits are truncated. This means that
just casting to int/u32 is correct and efficient (and in ALU32 mode doesn't
require any extra shifts).
To minimize the chances of regressions, two code patterns were investigated,
as mentioned above. For both patterns, BPF assembly was analyzed in
ALU32/NO-ALU32 compiler modes, both with current 32-bit int return type and
new 64-bit long return type.
Case 1. Variable-length data reading and concatenation. This is quite
ubiquitous pattern in tracing/monitoring applications, reading data like
process's environment variables, file path, etc. In such case, many pieces of
string-like variable-length data are read into a single big buffer, and at the
end of the process, only a part of array containing actual data is sent to
user-space for further processing. This case is tested in test_varlen.c
selftest (in the next patch). Code flow is roughly as follows:
void *payload = &sample->payload;
u64 len;
len = bpf_probe_read_kernel_str(payload, MAX_SZ1, &source_data1);
if (len <= MAX_SZ1) {
payload += len;
sample->len1 = len;
}
len = bpf_probe_read_kernel_str(payload, MAX_SZ2, &source_data2);
if (len <= MAX_SZ2) {
payload += len;
sample->len2 = len;
}
/* and so on */
sample->total_len = payload - &sample->payload;
/* send over, e.g., perf buffer */
There could be two variations with slightly different code generated: when len
is 64-bit integer and when it is 32-bit integer. Both variations were analysed.
BPF assembly instructions between two successive invocations of
bpf_probe_read_kernel_str() were used to check code regressions. Results are
below, followed by short analysis. Left side is using helpers with int return
type, the right one is after the switch to long.
ALU32 + INT ALU32 + LONG
=========== ============
64-BIT (13 insns): 64-BIT (10 insns):
------------------------------------ ------------------------------------
17: call 115 17: call 115
18: if w0 > 256 goto +9 <LBB0_4> 18: if r0 > 256 goto +6 <LBB0_4>
19: w1 = w0 19: r1 = 0 ll
20: r1 <<= 32 21: *(u64 *)(r1 + 0) = r0
21: r1 s>>= 32 22: r6 = 0 ll
22: r2 = 0 ll 24: r6 += r0
24: *(u64 *)(r2 + 0) = r1 00000000000000c8 <LBB0_4>:
25: r6 = 0 ll 25: r1 = r6
27: r6 += r1 26: w2 = 256
00000000000000e0 <LBB0_4>: 27: r3 = 0 ll
28: r1 = r6 29: call 115
29: w2 = 256
30: r3 = 0 ll
32: call 115
32-BIT (11 insns): 32-BIT (12 insns):
------------------------------------ ------------------------------------
17: call 115 17: call 115
18: if w0 > 256 goto +7 <LBB1_4> 18: if w0 > 256 goto +8 <LBB1_4>
19: r1 = 0 ll 19: r1 = 0 ll
21: *(u32 *)(r1 + 0) = r0 21: *(u32 *)(r1 + 0) = r0
22: w1 = w0 22: r0 <<= 32
23: r6 = 0 ll 23: r0 >>= 32
25: r6 += r1 24: r6 = 0 ll
00000000000000d0 <LBB1_4>: 26: r6 += r0
26: r1 = r6 00000000000000d8 <LBB1_4>:
27: w2 = 256 27: r1 = r6
28: r3 = 0 ll 28: w2 = 256
30: call 115 29: r3 = 0 ll
31: call 115
In ALU32 mode, the variant using 64-bit length variable clearly wins and
avoids unnecessary zero-extension bit shifts. In practice, this is even more
important and good, because BPF code won't need to do extra checks to "prove"
that payload/len are within good bounds.
32-bit len is one instruction longer. Clang decided to do 64-to-32 casting
with two bit shifts, instead of equivalent `w1 = w0` assignment. The former
uses extra register. The latter might potentially lose some range information,
but not for 32-bit value. So in this case, verifier infers that r0 is [0, 256]
after check at 18:, and shifting 32 bits left/right keeps that range intact.
We should probably look into Clang's logic and see why it chooses bitshifts
over sub-register assignments for this.
NO-ALU32 + INT NO-ALU32 + LONG
============== ===============
64-BIT (14 insns): 64-BIT (10 insns):
------------------------------------ ------------------------------------
17: call 115 17: call 115
18: r0 <<= 32 18: if r0 > 256 goto +6 <LBB0_4>
19: r1 = r0 19: r1 = 0 ll
20: r1 >>= 32 21: *(u64 *)(r1 + 0) = r0
21: if r1 > 256 goto +7 <LBB0_4> 22: r6 = 0 ll
22: r0 s>>= 32 24: r6 += r0
23: r1 = 0 ll 00000000000000c8 <LBB0_4>:
25: *(u64 *)(r1 + 0) = r0 25: r1 = r6
26: r6 = 0 ll 26: r2 = 256
28: r6 += r0 27: r3 = 0 ll
00000000000000e8 <LBB0_4>: 29: call 115
29: r1 = r6
30: r2 = 256
31: r3 = 0 ll
33: call 115
32-BIT (13 insns): 32-BIT (13 insns):
------------------------------------ ------------------------------------
17: call 115 17: call 115
18: r1 = r0 18: r1 = r0
19: r1 <<= 32 19: r1 <<= 32
20: r1 >>= 32 20: r1 >>= 32
21: if r1 > 256 goto +6 <LBB1_4> 21: if r1 > 256 goto +6 <LBB1_4>
22: r2 = 0 ll 22: r2 = 0 ll
24: *(u32 *)(r2 + 0) = r0 24: *(u32 *)(r2 + 0) = r0
25: r6 = 0 ll 25: r6 = 0 ll
27: r6 += r1 27: r6 += r1
00000000000000e0 <LBB1_4>: 00000000000000e0 <LBB1_4>:
28: r1 = r6 28: r1 = r6
29: r2 = 256 29: r2 = 256
30: r3 = 0 ll 30: r3 = 0 ll
32: call 115 32: call 115
In NO-ALU32 mode, for the case of 64-bit len variable, Clang generates much
superior code, as expected, eliminating unnecessary bit shifts. For 32-bit
len, code is identical.
So overall, only ALU-32 32-bit len case is more-or-less equivalent and the
difference stems from internal Clang decision, rather than compiler lacking
enough information about types.
Case 2. Let's look at the simpler case of checking return result of BPF helper
for errors. The code is very simple:
long bla;
if (bpf_probe_read_kenerl(&bla, sizeof(bla), 0))
return 1;
else
return 0;
ALU32 + CHECK (9 insns) ALU32 + CHECK (9 insns)
==================================== ====================================
0: r1 = r10 0: r1 = r10
1: r1 += -8 1: r1 += -8
2: w2 = 8 2: w2 = 8
3: r3 = 0 3: r3 = 0
4: call 113 4: call 113
5: w1 = w0 5: r1 = r0
6: w0 = 1 6: w0 = 1
7: if w1 != 0 goto +1 <LBB2_2> 7: if r1 != 0 goto +1 <LBB2_2>
8: w0 = 0 8: w0 = 0
0000000000000048 <LBB2_2>: 0000000000000048 <LBB2_2>:
9: exit 9: exit
Almost identical code, the only difference is the use of full register
assignment (r1 = r0) vs half-registers (w1 = w0) in instruction #5. On 32-bit
architectures, new BPF assembly might be slightly less optimal, in theory. But
one can argue that's not a big issue, given that use of full registers is
still prevalent (e.g., for parameter passing).
NO-ALU32 + CHECK (11 insns) NO-ALU32 + CHECK (9 insns)
==================================== ====================================
0: r1 = r10 0: r1 = r10
1: r1 += -8 1: r1 += -8
2: r2 = 8 2: r2 = 8
3: r3 = 0 3: r3 = 0
4: call 113 4: call 113
5: r1 = r0 5: r1 = r0
6: r1 <<= 32 6: r0 = 1
7: r1 >>= 32 7: if r1 != 0 goto +1 <LBB2_2>
8: r0 = 1 8: r0 = 0
9: if r1 != 0 goto +1 <LBB2_2> 0000000000000048 <LBB2_2>:
10: r0 = 0 9: exit
0000000000000058 <LBB2_2>:
11: exit
NO-ALU32 is a clear improvement, getting rid of unnecessary zero-extension bit
shifts.
Change-Id: Ie4ba541847b25df0d89042e74ee18c7b3d99d091
Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20200623032224.4020118-1-andriin@fb.com
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
20 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
full changes betewen latest stable and v6.0.0 testing branch