kernel/linux.git/lib/scatterlist.c, branch v4.16.11

lib/scatterlist: Fix chaining support in sgl_alloc_order()

2018-01-19T19:31:03+00:00

This patch avoids that workloads with large block sizes (megabytes) can trigger the following call stack with the ib_srpt driver (that driver is the only driver that chains scatterlists allocated by sgl_alloc_order()): BUG: Bad page state in process kworker/0:1H pfn:2423a78 page:fffffb03d08e9e00 count:-3 mapcount:0 mapping: (null) index:0x0 flags: 0x57ffffc0000000() raw: 0057ffffc0000000 0000000000000000 0000000000000000 fffffffdffffffff raw: dead000000000100 dead000000000200 0000000000000000 0000000000000000 page dumped because: nonzero _count CPU: 0 PID: 733 Comm: kworker/0:1H Tainted: G I 4.15.0-rc7.bart+ #1 Hardware name: HP ProLiant DL380 G7, BIOS P67 08/16/2015 Workqueue: ib-comp-wq ib_cq_poll_work [ib_core] Call Trace: dump_stack+0x5c/0x83 bad_page+0xf5/0x10f get_page_from_freelist+0xa46/0x11b0 __alloc_pages_nodemask+0x103/0x290 sgl_alloc_order+0x101/0x180 target_alloc_sgl+0x2c/0x40 [target_core_mod] srpt_alloc_rw_ctxs+0x173/0x2d0 [ib_srpt] srpt_handle_new_iu+0x61e/0x7f0 [ib_srpt] __ib_process_cq+0x55/0xa0 [ib_core] ib_cq_poll_work+0x1b/0x60 [ib_core] process_one_work+0x141/0x340 worker_thread+0x47/0x3e0 kthread+0xf5/0x130 ret_from_fork+0x1f/0x30 Fixes: e80a0af4759a ("lib/scatterlist: Introduce sgl_alloc() and sgl_free()") Reported-by: Laurence Oberman Tested-by: Laurence Oberman Signed-off-by: Bart Van Assche Cc: Nicholas A. Bellinger Cc: Laurence Oberman Signed-off-by: Jens Axboe

lib/scatterlist: Introduce sgl_alloc() and sgl_free()

2018-01-06T16:18:00+00:00

Many kernel drivers contain code that allocates and frees both a scatterlist and the pages that populate that scatterlist. Introduce functions in lib/scatterlist.c that perform these tasks instead of duplicating this functionality in multiple drivers. Only include these functions in the build if CONFIG_SGL_ALLOC=y to avoid that the kernel size increases if this functionality is not used. Signed-off-by: Bart Van Assche Reviewed-by: Hannes Reinecke Reviewed-by: Johannes Thumshirn Signed-off-by: Jens Axboe

lib/scatterlist: Introduce and export __sg_alloc_table_from_pages

2017-09-07T09:48:29+00:00

Drivers like i915 benefit from being able to control the maxium size of the sg coalesced segment while building the scatter- gather list. Introduce and export the __sg_alloc_table_from_pages function which will allow it that control. v2: Reorder parameters. (Chris Wilson) v3: Fix incomplete reordering in v2. v4: max_segment needs to be page aligned. v5: Rebase. v6: Rebase. v7: Fix spelling in commit and mention max segment size in __sg_alloc_table_from_pages kerneldoc. (Andrew Morton) Signed-off-by: Tvrtko Ursulin Cc: Masahiro Yamada Cc: linux-kernel@vger.kernel.org Cc: Chris Wilson Reviewed-by: Chris Wilson Cc: Joonas Lahtinen Cc: Andrew Morton Link: https://patchwork.freedesktop.org/patch/msgid/20170803091351.23594-1-tvrtko.ursulin@linux.intel.com

lib/scatterlist: Avoid potential scatterlist entry overflow

2017-09-07T09:48:28+00:00

Since the scatterlist length field is an unsigned int, make sure that sg_alloc_table_from_pages does not overflow it while coalescing pages to a single entry. v2: Drop reference to future use. Use UINT_MAX. v3: max_segment must be page aligned. v4: Do not rely on compiler to optimise out the rounddown. (Joonas Lahtinen) v5: Simplified loops and use post-increments rather than pre-increments. Use PAGE_MASK and fix comment typo. (Andy Shevchenko) v6: Commit spelling fix. Signed-off-by: Tvrtko Ursulin Cc: Masahiro Yamada Cc: linux-kernel@vger.kernel.org Reviewed-by: Chris Wilson Cc: Joonas Lahtinen Cc: Andy Shevchenko Link: https://patchwork.freedesktop.org/patch/msgid/20170803091312.22875-1-tvrtko.ursulin@linux.intel.com

lib/scatterlist: Fix offset type in sg_alloc_table_from_pages

2017-09-07T09:48:27+00:00

Scatterlist entries have an unsigned int for the offset so correct the sg_alloc_table_from_pages function accordingly. Since these are offsets withing a page, unsigned int is wide enough. Also converts callers which were using unsigned long locally with the lower_32_bits annotation to make it explicitly clear what is happening. v2: Use offset_in_page. (Chris Wilson) Signed-off-by: Tvrtko Ursulin Cc: Masahiro Yamada Cc: Pawel Osciak Cc: Marek Szyprowski Cc: Kyungmin Park Cc: Tomasz Stanislawski Cc: Matt Porter Cc: Alexandre Bounine Cc: linux-media@vger.kernel.org Cc: linux-kernel@vger.kernel.org Acked-by: Marek Szyprowski (v1) Reviewed-by: Chris Wilson Reviewed-by: Mauro Carvalho Chehab Link: https://patchwork.freedesktop.org/patch/msgid/20170731185512.20010-1-tvrtko.ursulin@linux.intel.com

scatterlist: add sg_zero_buffer() helper

2017-06-15T12:30:14+00:00

The sg_zero_buffer() helper is used to zero fill an area in a SG list. Signed-off-by: Johannes Thumshirn Reviewed-by: Sagi Grimberg [hch: renamed to sg_zero_buffer] Signed-off-by: Christoph Hellwig

scatterlist: do not disable IRQs in sg_copy_buffer

2017-02-28T02:43:46+00:00

Commit 50bed2e2862a ("sg: disable interrupts inside sg_copy_buffer") introduced disabling interrupts in sg_copy_buffer() since atomic uses of miter required it due to use of kmap_atomic(). However, as commit 8290e2d2dcbf ("scatterlist: atomic sg_mapping_iter() no longer needs disabled IRQs") acknowledges disabling interrupts is no longer needed for calls to kmap_atomic() and therefore unneeded for miter ops either, so remove it from sg_copy_buffer(). Link: http://lkml.kernel.org/r/1486040150-14109-3-git-send-email-gilad@benyossef.com Signed-off-by: Gilad Ben-Yossef Cc: Jens Axboe Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds

scatterlist: reorder compound boolean expression

2017-02-28T02:43:46+00:00

Test the cheaper boolean expression with no side effects first. Link: http://lkml.kernel.org/r/1486040150-14109-2-git-send-email-gilad@benyossef.com Signed-off-by: Gilad Ben-Yossef Cc: Jens Axboe Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds

scatterlist: fix a typo in comment block of sg_miter_stop()

2016-02-08T18:15:17+00:00

Fix the doubled "started" and tidy up the following sentences. Signed-off-by: Masahiro Yamada Signed-off-by: Linus Torvalds

scatterlist: allow limited chaining without ARCH_HAS_SG_CHAIN

2015-08-17T14:12:51+00:00

There are a couple of uses of struct scatterlist that never go to the dma_map_sg() helper and thus don't care about ARCH_HAS_SG_CHAIN which indicates that we can map chained S/G list. The most important one is the crypto code, which currently has to open code a few helpers to always allow chaining. This patch removes a few #ifdef ARCH_HAS_SG_CHAIN statements so that we can switch the crypto code to these common helpers. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe