| Message ID | 20220315144521.3810298-1-aisheng.dong@nxp.com |
|---|---|
| Headers | show |
| Series | mm: fix cma allocation fail sometimes | expand |
On Wed, 16 Mar 2022 11:41:37 +0800 Dong Aisheng <dongas86@gmail.com> wrote: > On Wed, Mar 16, 2022 at 6:58 AM Andrew Morton <akpm@linux-foundation.org> wrote: > > > > On Tue, 15 Mar 2022 22:45:20 +0800 Dong Aisheng <aisheng.dong@nxp.com> wrote: > > > > > --- a/mm/cma.c > > > +++ b/mm/cma.c > > > > > > ... > > > > > > @@ -457,6 +458,16 @@ struct page *cma_alloc(struct cma *cma, unsigned long count, > > > offset); > > > if (bitmap_no >= bitmap_maxno) { > > > spin_unlock_irq(&cma->lock); > > > + pr_debug("%s(): alloc fail, retry loop %d\n", __func__, loop++); > > > + /* > > > + * rescan as others may finish the memory migration > > > + * and quit if no available CMA memory found finally > > > + */ > > > + if (start) { > > > + schedule(); > > > + start = 0; > > > + continue; > > > + } > > > break; > > > > The schedule() is problematic. For a start, we'd normally use > > cond_resched() here, so we avoid calling the more expensive schedule() > > if we know it won't perform any action. > > > > But cond_resched() is problematic if this thread has realtime > > scheduling policy and the process we're waiting on does not. One way > > to address that is to use an unconditional msleep(1), but that's still > > just a hack. > > > > I think we can simply drop schedule() here during the second round of retry > as the estimated delay may not be really needed. That will simply cause a tight loop, so I'm obviously not understanding the proposal.
On Thu, Mar 17, 2022 at 5:09 AM Andrew Morton <akpm@linux-foundation.org> wrote: > > On Wed, 16 Mar 2022 11:41:37 +0800 Dong Aisheng <dongas86@gmail.com> wrote: > > > On Wed, Mar 16, 2022 at 6:58 AM Andrew Morton <akpm@linux-foundation.org> wrote: > > > > > > On Tue, 15 Mar 2022 22:45:20 +0800 Dong Aisheng <aisheng.dong@nxp.com> wrote: > > > > > > > --- a/mm/cma.c > > > > +++ b/mm/cma.c > > > > > > > > ... > > > > > > > > @@ -457,6 +458,16 @@ struct page *cma_alloc(struct cma *cma, unsigned long count, > > > > offset); > > > > if (bitmap_no >= bitmap_maxno) { > > > > spin_unlock_irq(&cma->lock); > > > > + pr_debug("%s(): alloc fail, retry loop %d\n", __func__, loop++); > > > > + /* > > > > + * rescan as others may finish the memory migration > > > > + * and quit if no available CMA memory found finally > > > > + */ > > > > + if (start) { > > > > + schedule(); > > > > + start = 0; > > > > + continue; > > > > + } > > > > break; > > > > > > The schedule() is problematic. For a start, we'd normally use > > > cond_resched() here, so we avoid calling the more expensive schedule() > > > if we know it won't perform any action. > > > > > > But cond_resched() is problematic if this thread has realtime > > > scheduling policy and the process we're waiting on does not. One way > > > to address that is to use an unconditional msleep(1), but that's still > > > just a hack. > > > > > > > I think we can simply drop schedule() here during the second round of retry > > as the estimated delay may not be really needed. > > That will simply cause a tight loop, so I'm obviously not understanding > the proposal. > IIUC the original code is already a tight loop, isn't it? You could also see my observation, thousands of retries, in patch 2. The logic in this patch is just retry the original loop in case in case there's a false possive error return. Or you mean infinite loop? The loop will break out when meet an non EBUSY error in alloc_contig_range(). BTW, the tight loop situation could be improved a lot by my patch 2. And after Zi Yan's patchset [1] got merged, the situation could be further improved by retring in pageblock step. 1. [v7,0/5] Use pageblock_order for cma and alloc_contig_range alignment. - Patchwork (kernel.org) So generally i wonder it seems still better than simply revert. Please fix me if i still missed something. Regards Aisheng
On 15.03.22 15:45, Dong Aisheng wrote: > When there're multiple process allocing dma memory in parallel s/allocing/allocating/ > by calling dma_alloc_coherent(), it may fail sometimes as follows: > > Error log: > cma: cma_alloc: linux,cma: alloc failed, req-size: 148 pages, ret: -16 > cma: number of available pages: > 3@125+20@172+12@236+4@380+32@736+17@2287+23@2473+20@36076+99@40477+108@40852+44@41108+20@41196+108@41364+108@41620+ > 108@42900+108@43156+483@44061+1763@45341+1440@47712+20@49324+20@49388+5076@49452+2304@55040+35@58141+20@58220+20@58284+ > 7188@58348+84@66220+7276@66452+227@74525+6371@75549=> 33161 free of 81920 total pages > > When issue happened, we saw there were still 33161 pages (129M) free CMA > memory and a lot available free slots for 148 pages in CMA bitmap that we > want to allocate. > > If dumping memory info, we found that there was also ~342M normal memory, > but only 1352K CMA memory left in buddy system while a lot of pageblocks > were isolated. s/If/When/ > > Memory info log: > Normal free:351096kB min:30000kB low:37500kB high:45000kB reserved_highatomic:0KB > active_anon:98060kB inactive_anon:98948kB active_file:60864kB inactive_file:31776kB > unevictable:0kB writepending:0kB present:1048576kB managed:1018328kB mlocked:0kB > bounce:0kB free_pcp:220kB local_pcp:192kB free_cma:1352kB lowmem_reserve[]: 0 0 0 > Normal: 78*4kB (UECI) 1772*8kB (UMECI) 1335*16kB (UMECI) 360*32kB (UMECI) 65*64kB (UMCI) > 36*128kB (UMECI) 16*256kB (UMCI) 6*512kB (EI) 8*1024kB (UEI) 4*2048kB (MI) 8*4096kB (EI) > 8*8192kB (UI) 3*16384kB (EI) 8*32768kB (M) = 489288kB > > The root cause of this issue is that since commit a4efc174b382 > ("mm/cma.c: remove redundant cma_mutex lock"), CMA supports concurrent > memory allocation. It's possible that the memory range process A trying > to alloc has already been isolated by the allocation of process B during > memory migration. > > The problem here is that the memory range isolated during one allocation > by start_isolate_page_range() could be much bigger than the real size we > want to alloc due to the range is aligned to MAX_ORDER_NR_PAGES. > > Taking an ARMv7 platform with 1G memory as an example, when MAX_ORDER_NR_PAGES > is big (e.g. 32M with max_order 14) and CMA memory is relatively small > (e.g. 128M), there're only 4 MAX_ORDER slot, then it's very easy that > all CMA memory may have already been isolated by other processes when > one trying to allocate memory using dma_alloc_coherent(). > Since current CMA code will only scan one time of whole available CMA > memory, then dma_alloc_coherent() may easy fail due to contention with > other processes. > > This patch introduces a retry mechanism to rescan CMA bitmap for -EBUSY > error in case the target memory range may has been temporarily isolated > by others and released later. But you patch doesn't check for -EBUSY and instead might retry forever, on any allocation error, no? I'd really suggest letting alloc_contig_range() return -EAGAIN in case the isolation failed and handling -EAGAIN only in a special way instead. In addition, we might want to stop once we looped to often I assume.
On Thu, Mar 17, 2022 at 10:26:42PM +0800, Dong Aisheng wrote: > On Thu, Mar 17, 2022 at 6:55 PM David Hildenbrand <david@redhat.com> wrote: > > > > On 15.03.22 15:45, Dong Aisheng wrote: > > > When there're multiple process allocing dma memory in parallel > > > > s/allocing/allocating/ > > > > > by calling dma_alloc_coherent(), it may fail sometimes as follows: > > > > > > Error log: > > > cma: cma_alloc: linux,cma: alloc failed, req-size: 148 pages, ret: -16 > > > cma: number of available pages: > > > 3@125+20@172+12@236+4@380+32@736+17@2287+23@2473+20@36076+99@40477+108@40852+44@41108+20@41196+108@41364+108@41620+ > > > 108@42900+108@43156+483@44061+1763@45341+1440@47712+20@49324+20@49388+5076@49452+2304@55040+35@58141+20@58220+20@58284+ > > > 7188@58348+84@66220+7276@66452+227@74525+6371@75549=> 33161 free of 81920 total pages > > > > > > When issue happened, we saw there were still 33161 pages (129M) free CMA > > > memory and a lot available free slots for 148 pages in CMA bitmap that we > > > want to allocate. Yes, I also have met the problem especially when the multiple threads compete cma allocation. Thanks for bringing up the issue. > > > > > > If dumping memory info, we found that there was also ~342M normal memory, > > > but only 1352K CMA memory left in buddy system while a lot of pageblocks > > > were isolated. > > > > s/If/When/ > > > > Will fix them all, thanks. > > > > > > > Memory info log: > > > Normal free:351096kB min:30000kB low:37500kB high:45000kB reserved_highatomic:0KB > > > active_anon:98060kB inactive_anon:98948kB active_file:60864kB inactive_file:31776kB > > > unevictable:0kB writepending:0kB present:1048576kB managed:1018328kB mlocked:0kB > > > bounce:0kB free_pcp:220kB local_pcp:192kB free_cma:1352kB lowmem_reserve[]: 0 0 0 > > > Normal: 78*4kB (UECI) 1772*8kB (UMECI) 1335*16kB (UMECI) 360*32kB (UMECI) 65*64kB (UMCI) > > > 36*128kB (UMECI) 16*256kB (UMCI) 6*512kB (EI) 8*1024kB (UEI) 4*2048kB (MI) 8*4096kB (EI) > > > 8*8192kB (UI) 3*16384kB (EI) 8*32768kB (M) = 489288kB > > > > > > The root cause of this issue is that since commit a4efc174b382 > > > ("mm/cma.c: remove redundant cma_mutex lock"), CMA supports concurrent > > > memory allocation. It's possible that the memory range process A trying > > > to alloc has already been isolated by the allocation of process B during > > > memory migration. > > > > > > The problem here is that the memory range isolated during one allocation > > > by start_isolate_page_range() could be much bigger than the real size we > > > want to alloc due to the range is aligned to MAX_ORDER_NR_PAGES. > > > > > > Taking an ARMv7 platform with 1G memory as an example, when MAX_ORDER_NR_PAGES > > > is big (e.g. 32M with max_order 14) and CMA memory is relatively small > > > (e.g. 128M), there're only 4 MAX_ORDER slot, then it's very easy that > > > all CMA memory may have already been isolated by other processes when > > > one trying to allocate memory using dma_alloc_coherent(). > > > Since current CMA code will only scan one time of whole available CMA > > > memory, then dma_alloc_coherent() may easy fail due to contention with > > > other processes. > > > > > > This patch introduces a retry mechanism to rescan CMA bitmap for -EBUSY > > > error in case the target memory range may has been temporarily isolated > > > by others and released later. > > > > But you patch doesn't check for -EBUSY and instead might retry forever, > > on any allocation error, no? > > > > My patch seems not need check it because there's no chance to retry the loop > in case an non -EBUS error happened earlier. > > for (;;) { > if (bitmap_no >= bitmap_maxno) { > retry_the_whole_loop; > } > > pfn = cma->base_pfn + (bitmap_no << cma->order_per_bit); > ret = alloc_contig_range(pfn, pfn + count, MIGRATE_CMA, > GFP_KERNEL | (no_warn ? __GFP_NOWARN : 0)); > > if (ret != -EBUSY) > break; > } > > > I'd really suggest letting alloc_contig_range() return -EAGAIN in case > > the isolation failed and handling -EAGAIN only in a special way instead. > > > > Yes, i guess that's another improvement and is applicable. > > > In addition, we might want to stop once we looped to often I assume. > > > > I wonder if really retried un-reasonably too often, we probably may > need figure out > what's going on inside alloc_contig_range() and fix it rather than > return EBUSY error to > users in case there're still a lot of avaiable memories. > So currently i didn't add a maximum retry loop outside. > > Additionaly, for a small CMA system (128M with 32M max_order pages), > the retry would > be frequently when multiple process allocating memory, it also depends > on system running > state, so it's hard to define a reasonable and stable maxinum retry count. IMO, when the CMA see the -EAGAIN, it should put the task into cma->wait_queue and then be woken up by other thread which finish work of the cma. So it's similar with cma_mutex but we don't need to synchronize for !EAGAIN cases and make the cma allocatoin fair.
On Fri, Mar 18, 2022 at 11:43:41AM +0800, Dong Aisheng wrote: > On Fri, Mar 18, 2022 at 1:12 AM Minchan Kim <minchan@kernel.org> wrote: > > > > On Thu, Mar 17, 2022 at 10:26:42PM +0800, Dong Aisheng wrote: > > > On Thu, Mar 17, 2022 at 6:55 PM David Hildenbrand <david@redhat.com> wrote: > > > > > > > > On 15.03.22 15:45, Dong Aisheng wrote: > > > > > When there're multiple process allocing dma memory in parallel > > > > > > > > s/allocing/allocating/ > > > > > > > > > by calling dma_alloc_coherent(), it may fail sometimes as follows: > > > > > > > > > > Error log: > > > > > cma: cma_alloc: linux,cma: alloc failed, req-size: 148 pages, ret: -16 > > > > > cma: number of available pages: > > > > > 3@125+20@172+12@236+4@380+32@736+17@2287+23@2473+20@36076+99@40477+108@40852+44@41108+20@41196+108@41364+108@41620+ > > > > > 108@42900+108@43156+483@44061+1763@45341+1440@47712+20@49324+20@49388+5076@49452+2304@55040+35@58141+20@58220+20@58284+ > > > > > 7188@58348+84@66220+7276@66452+227@74525+6371@75549=> 33161 free of 81920 total pages > > > > > > > > > > When issue happened, we saw there were still 33161 pages (129M) free CMA > > > > > memory and a lot available free slots for 148 pages in CMA bitmap that we > > > > > want to allocate. > > > > Yes, I also have met the problem especially when the multiple threads > > compete cma allocation. Thanks for bringing up the issue. > > > > > > > > > > > > If dumping memory info, we found that there was also ~342M normal memory, > > > > > but only 1352K CMA memory left in buddy system while a lot of pageblocks > > > > > were isolated. > > > > > > > > s/If/When/ > > > > > > > > > > Will fix them all, thanks. > > > > > > > > > > > > > Memory info log: > > > > > Normal free:351096kB min:30000kB low:37500kB high:45000kB reserved_highatomic:0KB > > > > > active_anon:98060kB inactive_anon:98948kB active_file:60864kB inactive_file:31776kB > > > > > unevictable:0kB writepending:0kB present:1048576kB managed:1018328kB mlocked:0kB > > > > > bounce:0kB free_pcp:220kB local_pcp:192kB free_cma:1352kB lowmem_reserve[]: 0 0 0 > > > > > Normal: 78*4kB (UECI) 1772*8kB (UMECI) 1335*16kB (UMECI) 360*32kB (UMECI) 65*64kB (UMCI) > > > > > 36*128kB (UMECI) 16*256kB (UMCI) 6*512kB (EI) 8*1024kB (UEI) 4*2048kB (MI) 8*4096kB (EI) > > > > > 8*8192kB (UI) 3*16384kB (EI) 8*32768kB (M) = 489288kB > > > > > > > > > > The root cause of this issue is that since commit a4efc174b382 > > > > > ("mm/cma.c: remove redundant cma_mutex lock"), CMA supports concurrent > > > > > memory allocation. It's possible that the memory range process A trying > > > > > to alloc has already been isolated by the allocation of process B during > > > > > memory migration. > > > > > > > > > > The problem here is that the memory range isolated during one allocation > > > > > by start_isolate_page_range() could be much bigger than the real size we > > > > > want to alloc due to the range is aligned to MAX_ORDER_NR_PAGES. > > > > > > > > > > Taking an ARMv7 platform with 1G memory as an example, when MAX_ORDER_NR_PAGES > > > > > is big (e.g. 32M with max_order 14) and CMA memory is relatively small > > > > > (e.g. 128M), there're only 4 MAX_ORDER slot, then it's very easy that > > > > > all CMA memory may have already been isolated by other processes when > > > > > one trying to allocate memory using dma_alloc_coherent(). > > > > > Since current CMA code will only scan one time of whole available CMA > > > > > memory, then dma_alloc_coherent() may easy fail due to contention with > > > > > other processes. > > > > > > > > > > This patch introduces a retry mechanism to rescan CMA bitmap for -EBUSY > > > > > error in case the target memory range may has been temporarily isolated > > > > > by others and released later. > > > > > > > > But you patch doesn't check for -EBUSY and instead might retry forever, > > > > on any allocation error, no? > > > > > > > > > > My patch seems not need check it because there's no chance to retry the loop > > > in case an non -EBUS error happened earlier. > > > > > > for (;;) { > > > if (bitmap_no >= bitmap_maxno) { > > > retry_the_whole_loop; > > > } > > > > > > pfn = cma->base_pfn + (bitmap_no << cma->order_per_bit); > > > ret = alloc_contig_range(pfn, pfn + count, MIGRATE_CMA, > > > GFP_KERNEL | (no_warn ? __GFP_NOWARN : 0)); > > > > > > if (ret != -EBUSY) > > > break; > > > } > > > > > > > I'd really suggest letting alloc_contig_range() return -EAGAIN in case > > > > the isolation failed and handling -EAGAIN only in a special way instead. > > > > > > > > > > Yes, i guess that's another improvement and is applicable. > > > > > > > In addition, we might want to stop once we looped to often I assume. > > > > > > > > > > I wonder if really retried un-reasonably too often, we probably may > > > need figure out > > > what's going on inside alloc_contig_range() and fix it rather than > > > return EBUSY error to > > > users in case there're still a lot of avaiable memories. > > > So currently i didn't add a maximum retry loop outside. > > > > > > Additionaly, for a small CMA system (128M with 32M max_order pages), > > > the retry would > > > be frequently when multiple process allocating memory, it also depends > > > on system running > > > state, so it's hard to define a reasonable and stable maxinum retry count. > > > > IMO, when the CMA see the -EAGAIN, it should put the task into > > cma->wait_queue and then be woken up by other thread which finish > > work of the cma. So it's similar with cma_mutex but we don't need to > > synchronize for !EAGAIN cases and make the cma allocatoin fair. > > Okay, that's another approach which is completely different from the > existing one. > Instead of blocking on the CMA memory range which we want to allocate, > the existing code will try the next available memory ranges. > The question is whether we need to change this behavior? It could wait only if it scan the whole range but everyblock were taken and then one more trial after woken up. If the cma_alloc return -EAGAIN in the end, user could decide the policy. > It looks to me both ways have pros and cons. > > And for sleeping on -EAGAIN case, do we need an accurate wakeup? > IOW only wakes the sleeper when the exact memory range is released > which means we need create some more complicated code logic > to track different CMA memory range usage. > Otherwise, there will be possible false positive wakeups and the requester may > quickly sleep again. I even didn't consider such complicated model since we would have the race anyway.(Never tested but wanted to show the intention) diff --git a/mm/cma.c b/mm/cma.c index bc9ca8f3c487..cccf684da587 100644 --- a/mm/cma.c +++ b/mm/cma.c @@ -449,6 +449,7 @@ struct page *cma_alloc(struct cma *cma, unsigned long count, offset = cma_bitmap_aligned_offset(cma, align); bitmap_maxno = cma_bitmap_maxno(cma); bitmap_count = cma_bitmap_pages_to_bits(cma, count); + bool retried = false; if (bitmap_count > bitmap_maxno) goto out; @@ -460,6 +461,12 @@ struct page *cma_alloc(struct cma *cma, unsigned long count, offset); if (bitmap_no >= bitmap_maxno) { spin_unlock_irq(&cma->lock); + if (ret == -EAGAIN && !retried) { + wait_event_killable(cma->wq); + retried = true; + start = 0; + continue; + } break; } bitmap_set(cma->bitmap, bitmap_no, bitmap_count); @@ -471,6 +478,10 @@ struct page *cma_alloc(struct cma *cma, unsigned long count, spin_unlock_irq(&cma->lock); pfn = cma->base_pfn + (bitmap_no << cma->order_per_bit); + if (is_migrate_isolate_page(pfn_to_page(pfn))) { + ret = -EAGAIN; + goto next; + } ret = alloc_contig_range(pfn, pfn + count, MIGRATE_CMA, GFP_KERNEL | (no_warn ? __GFP_NOWARN : 0)); @@ -478,9 +489,9 @@ struct page *cma_alloc(struct cma *cma, unsigned long count, page = pfn_to_page(pfn); break; } - +next: cma_clear_bitmap(cma, pfn, count); - if (ret != -EBUSY) + if (ret != -EBUSY && ret != -EAGAIN) break; pr_debug("%s(): memory range at %p is busy, retrying\n", @@ -489,7 +500,10 @@ struct page *cma_alloc(struct cma *cma, unsigned long count, trace_cma_alloc_busy_retry(cma->name, pfn, pfn_to_page(pfn), count, align); /* try again with a bit different memory target */ - start = bitmap_no + mask + 1; + if (ret == -EAGAIN) + start = (pfn_max_align_up(pfn + 1) - cma->base_pfn) >> cma->order_per_bit; + else + start = bitmap_no + mask + 1; } trace_cma_alloc_finish(cma->name, pfn, page, count, align); diff --git a/mm/page_isolation.c b/mm/page_isolation.c index f67c4c70f17f..f5a16a82552a 100644 --- a/mm/page_isolation.c +++ b/mm/page_isolation.c @@ -182,7 +182,7 @@ __first_valid_page(unsigned long pfn, unsigned long nr_pages) * might be used to flush and disable pcplist before isolation and enable after * unisolation. * - * Return: 0 on success and -EBUSY if any part of range cannot be isolated. + * Return: 0 on success and -EAGAIN if any part of range cannot be isolated. */ int start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn, unsigned migratetype, int flags) @@ -199,7 +199,7 @@ int start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn, page = __first_valid_page(pfn, pageblock_nr_pages); if (page && set_migratetype_isolate(page, migratetype, flags)) { undo_isolate_page_range(start_pfn, pfn, migratetype); - return -EBUSY; + return -EAGAIN } } return 0;
On Wed, May 04, 2022 at 11:52:30PM +0800, Dong Aisheng wrote: > Hi Minchan & David, > > On Sat, Mar 19, 2022 at 12:20 AM Minchan Kim <minchan@kernel.org> wrote: > > > > On Fri, Mar 18, 2022 at 11:43:41AM +0800, Dong Aisheng wrote: > > > On Fri, Mar 18, 2022 at 1:12 AM Minchan Kim <minchan@kernel.org> wrote: > > > > > > > > On Thu, Mar 17, 2022 at 10:26:42PM +0800, Dong Aisheng wrote: > > > > > On Thu, Mar 17, 2022 at 6:55 PM David Hildenbrand <david@redhat.com> wrote: > > > > > > > > > > > > On 15.03.22 15:45, Dong Aisheng wrote: > > > > > > > When there're multiple process allocing dma memory in parallel > > > > > > > > > > > > s/allocing/allocating/ > > > > > > > > > > > > > by calling dma_alloc_coherent(), it may fail sometimes as follows: > > > > > > > > > > > > > > Error log: > > > > > > > cma: cma_alloc: linux,cma: alloc failed, req-size: 148 pages, ret: -16 > > > > > > > cma: number of available pages: > > > > > > > 3@125+20@172+12@236+4@380+32@736+17@2287+23@2473+20@36076+99@40477+108@40852+44@41108+20@41196+108@41364+108@41620+ > > > > > > > 108@42900+108@43156+483@44061+1763@45341+1440@47712+20@49324+20@49388+5076@49452+2304@55040+35@58141+20@58220+20@58284+ > > > > > > > 7188@58348+84@66220+7276@66452+227@74525+6371@75549=> 33161 free of 81920 total pages > > > > > > > > > > > > > > When issue happened, we saw there were still 33161 pages (129M) free CMA > > > > > > > memory and a lot available free slots for 148 pages in CMA bitmap that we > > > > > > > want to allocate. > > > > > > > > Yes, I also have met the problem especially when the multiple threads > > > > compete cma allocation. Thanks for bringing up the issue. > > > > > > > > > > > > > > > > > > If dumping memory info, we found that there was also ~342M normal memory, > > > > > > > but only 1352K CMA memory left in buddy system while a lot of pageblocks > > > > > > > were isolated. > > > > > > > > > > > > s/If/When/ > > > > > > > > > > > > > > > > Will fix them all, thanks. > > > > > > > > > > > > > > > > > > > Memory info log: > > > > > > > Normal free:351096kB min:30000kB low:37500kB high:45000kB reserved_highatomic:0KB > > > > > > > active_anon:98060kB inactive_anon:98948kB active_file:60864kB inactive_file:31776kB > > > > > > > unevictable:0kB writepending:0kB present:1048576kB managed:1018328kB mlocked:0kB > > > > > > > bounce:0kB free_pcp:220kB local_pcp:192kB free_cma:1352kB lowmem_reserve[]: 0 0 0 > > > > > > > Normal: 78*4kB (UECI) 1772*8kB (UMECI) 1335*16kB (UMECI) 360*32kB (UMECI) 65*64kB (UMCI) > > > > > > > 36*128kB (UMECI) 16*256kB (UMCI) 6*512kB (EI) 8*1024kB (UEI) 4*2048kB (MI) 8*4096kB (EI) > > > > > > > 8*8192kB (UI) 3*16384kB (EI) 8*32768kB (M) = 489288kB > > > > > > > > > > > > > > The root cause of this issue is that since commit a4efc174b382 > > > > > > > ("mm/cma.c: remove redundant cma_mutex lock"), CMA supports concurrent > > > > > > > memory allocation. It's possible that the memory range process A trying > > > > > > > to alloc has already been isolated by the allocation of process B during > > > > > > > memory migration. > > > > > > > > > > > > > > The problem here is that the memory range isolated during one allocation > > > > > > > by start_isolate_page_range() could be much bigger than the real size we > > > > > > > want to alloc due to the range is aligned to MAX_ORDER_NR_PAGES. > > > > > > > > > > > > > > Taking an ARMv7 platform with 1G memory as an example, when MAX_ORDER_NR_PAGES > > > > > > > is big (e.g. 32M with max_order 14) and CMA memory is relatively small > > > > > > > (e.g. 128M), there're only 4 MAX_ORDER slot, then it's very easy that > > > > > > > all CMA memory may have already been isolated by other processes when > > > > > > > one trying to allocate memory using dma_alloc_coherent(). > > > > > > > Since current CMA code will only scan one time of whole available CMA > > > > > > > memory, then dma_alloc_coherent() may easy fail due to contention with > > > > > > > other processes. > > > > > > > > > > > > > > This patch introduces a retry mechanism to rescan CMA bitmap for -EBUSY > > > > > > > error in case the target memory range may has been temporarily isolated > > > > > > > by others and released later. > > > > > > > > > > > > But you patch doesn't check for -EBUSY and instead might retry forever, > > > > > > on any allocation error, no? > > > > > > > > > > > > > > > > My patch seems not need check it because there's no chance to retry the loop > > > > > in case an non -EBUS error happened earlier. > > > > > > > > > > for (;;) { > > > > > if (bitmap_no >= bitmap_maxno) { > > > > > retry_the_whole_loop; > > > > > } > > > > > > > > > > pfn = cma->base_pfn + (bitmap_no << cma->order_per_bit); > > > > > ret = alloc_contig_range(pfn, pfn + count, MIGRATE_CMA, > > > > > GFP_KERNEL | (no_warn ? __GFP_NOWARN : 0)); > > > > > > > > > > if (ret != -EBUSY) > > > > > break; > > > > > } > > > > > > > > > > > I'd really suggest letting alloc_contig_range() return -EAGAIN in case > > > > > > the isolation failed and handling -EAGAIN only in a special way instead. > > > > > > > > > > > > > > > > Yes, i guess that's another improvement and is applicable. > > > > > > > > > > > In addition, we might want to stop once we looped to often I assume. > > > > > > > > > > > > > > > > I wonder if really retried un-reasonably too often, we probably may > > > > > need figure out > > > > > what's going on inside alloc_contig_range() and fix it rather than > > > > > return EBUSY error to > > > > > users in case there're still a lot of avaiable memories. > > > > > So currently i didn't add a maximum retry loop outside. > > > > > > > > > > Additionaly, for a small CMA system (128M with 32M max_order pages), > > > > > the retry would > > > > > be frequently when multiple process allocating memory, it also depends > > > > > on system running > > > > > state, so it's hard to define a reasonable and stable maxinum retry count. > > > > > > > > IMO, when the CMA see the -EAGAIN, it should put the task into > > > > cma->wait_queue and then be woken up by other thread which finish > > > > work of the cma. So it's similar with cma_mutex but we don't need to > > > > synchronize for !EAGAIN cases and make the cma allocatoin fair. > > > > > > Okay, that's another approach which is completely different from the > > > existing one. > > > Instead of blocking on the CMA memory range which we want to allocate, > > > the existing code will try the next available memory ranges. > > > The question is whether we need to change this behavior? > > > > It could wait only if it scan the whole range but everyblock were > > taken and then one more trial after woken up. If the cma_alloc return > > -EAGAIN in the end, user could decide the policy. > > > > > It looks to me both ways have pros and cons. > > > > > > And for sleeping on -EAGAIN case, do we need an accurate wakeup? > > > IOW only wakes the sleeper when the exact memory range is released > > > which means we need create some more complicated code logic > > > to track different CMA memory range usage. > > > Otherwise, there will be possible false positive wakeups and the requester may > > > quickly sleep again. > > > > I even didn't consider such complicated model since we would have > > the race anyway.(Never tested but wanted to show the intention) > > > > diff --git a/mm/cma.c b/mm/cma.c > > index bc9ca8f3c487..cccf684da587 100644 > > --- a/mm/cma.c > > +++ b/mm/cma.c > > @@ -449,6 +449,7 @@ struct page *cma_alloc(struct cma *cma, unsigned long count, > > offset = cma_bitmap_aligned_offset(cma, align); > > bitmap_maxno = cma_bitmap_maxno(cma); > > bitmap_count = cma_bitmap_pages_to_bits(cma, count); > > + bool retried = false; > > > > if (bitmap_count > bitmap_maxno) > > goto out; > > @@ -460,6 +461,12 @@ struct page *cma_alloc(struct cma *cma, unsigned long count, > > offset); > > if (bitmap_no >= bitmap_maxno) { > > spin_unlock_irq(&cma->lock); > > + if (ret == -EAGAIN && !retried) { > > + wait_event_killable(cma->wq); > > I spent a few days reading the code carefully and implementing your suggestions. > But I think the problem was still when to wake up multiple callers > properly who were sleeping > on isolation contention error. The issue I observed was that there's > a synchronization problem > between the sleeper and waker in current code logic due to: > 1) we only need to wake up the caller when detecting users sleeping on > the isolation contention. > A flag needs to be introduced to check dynamically. > 2) wakeup code may be finished before the flag was set which means the > last sleeper > may be missed to wake up. So a timeout mechanism needs to be introduced. > 3) the code can't avoid the wait_for_completion() and complete() run in parallel > without introducing extra complexity to do proper synchronization. > (during my test, &cma->pending can be < 0 sometimes) > > I wonder if it's worth introducing such complexity to support sleeping > on isolation contention. > Maybe the simple way was just as Andrew said that let's revert that > broken patch first. > > Do you have any suggestions? Thanks for the effort. On a second thought, I am also worry about the unfairness on my suggestion since new comer could steal the pageblock while former was waiting on the queue to be woken up. If it's complicated than the expectation, I don't think we should block your workload so I agree reverting the original patch to resolve regression first as Andrew suggested and then we need to think over better ideas. Thanks.
We observed an issue with NXP 5.15 LTS kernel that dma_alloc_coherent() may fail sometimes when there're multiple processes trying to allocate CMA memory. This issue can be very easily reproduced on MX6Q SDB board with latest linux-next kernel by writing a test module creating 16 or 32 threads allocating random size of CMA memory in parallel at the background. Or simply enabling CONFIG_CMA_DEBUG, you can see endless of CMA alloc retries during booting: [ 1.452124] cma: cma_alloc(): memory range at (ptrval) is busy,retrying .... (thousands of reties) The root cause of this issue is that since commit a4efc174b382 ("mm/cma.c: remove redundant cma_mutex lock"), CMA supports concurrent memory allocation. It's possible that the memory range process A try to alloc has already been isolated by the allocation of process B during memory migration. The problem here is that the memory range isolated during one allocation by start_isolate_page_range() could be much bigger than the real size we want to alloc due to the range is aligned to MAX_ORDER_NR_PAGES. Taking an ARMv7 platform with 1G memory as an example, when MAX_ORDER_NR_PAGES is big (e.g. 32M with max_order 14) and CMA memory is relatively small (e.g. 128M), there're only 4 MAX_ORDER slot, then it's very easy that all CMA memory may have already been isolated by other processes when one trying to allocate memory using dma_alloc_coherent(). Since current CMA code will only scan one time of whole available CMA memory, then dma_alloc_coherent() may easy fail due to contention with other processes. This patchset introduces a retry mechanism to rescan CMA bitmap for -EBUSY error in case the target pageblock may has been temporarily isolated by others and released later. It also improves the CMA allocation performance by trying the next MAX_ORDER_NR_PAGES range during reties rather than looping within the same isolated range in small steps which wasting CPU mips. The following test is based on linux-next: next-20211213. Without the fix, it's easily fail. # insmod cma_alloc.ko pnum=16 [ 274.322369] CMA alloc test enter: thread number: 16 [ 274.329948] cpu: 0, pid: 692, index 4 pages 144 [ 274.330143] cpu: 1, pid: 694, index 2 pages 44 [ 274.330359] cpu: 2, pid: 695, index 7 pages 757 [ 274.330760] cpu: 2, pid: 696, index 4 pages 144 [ 274.330974] cpu: 2, pid: 697, index 6 pages 512 [ 274.331223] cpu: 2, pid: 698, index 6 pages 512 [ 274.331499] cpu: 2, pid: 699, index 2 pages 44 [ 274.332228] cpu: 2, pid: 700, index 0 pages 7 [ 274.337421] cpu: 0, pid: 701, index 1 pages 38 [ 274.337618] cpu: 2, pid: 702, index 0 pages 7 [ 274.344669] cpu: 1, pid: 703, index 0 pages 7 [ 274.344807] cpu: 3, pid: 704, index 6 pages 512 [ 274.348269] cpu: 2, pid: 705, index 5 pages 148 [ 274.349490] cma: cma_alloc: reserved: alloc failed, req-size: 38 pages, ret: -16 [ 274.366292] cpu: 1, pid: 706, index 4 pages 144 [ 274.366562] cpu: 0, pid: 707, index 3 pages 128 [ 274.367356] cma: cma_alloc: reserved: alloc failed, req-size: 128 pages, ret: -16 [ 274.367370] cpu: 0, pid: 707, index 3 pages 128 failed [ 274.371148] cma: cma_alloc: reserved: alloc failed, req-size: 148 pages, ret: -16 [ 274.375348] cma: cma_alloc: reserved: alloc failed, req-size: 144 pages, ret: -16 [ 274.384256] cpu: 2, pid: 708, index 0 pages 7 .... With the fix, 32 threads allocating in parallel can pass overnight stress test. root@imx6qpdlsolox:~# insmod cma_alloc.ko pnum=32 [ 112.976809] cma_alloc: loading out-of-tree module taints kernel. [ 112.984128] CMA alloc test enter: thread number: 32 [ 112.989748] cpu: 2, pid: 707, index 6 pages 512 [ 112.994342] cpu: 1, pid: 708, index 6 pages 512 [ 112.995162] cpu: 0, pid: 709, index 3 pages 128 [ 112.995867] cpu: 2, pid: 710, index 0 pages 7 [ 112.995910] cpu: 3, pid: 711, index 2 pages 44 [ 112.996005] cpu: 3, pid: 712, index 7 pages 757 [ 112.996098] cpu: 3, pid: 713, index 7 pages 757 ... [41877.368163] cpu: 1, pid: 737, index 2 pages 44 [41877.369388] cpu: 1, pid: 736, index 3 pages 128 [41878.486516] cpu: 0, pid: 737, index 2 pages 44 [41878.486515] cpu: 2, pid: 739, index 4 pages 144 [41878.486622] cpu: 1, pid: 736, index 3 pages 128 [41878.486948] cpu: 2, pid: 735, index 7 pages 757 [41878.487279] cpu: 2, pid: 738, index 4 pages 144 [41879.526603] cpu: 1, pid: 739, index 3 pages 128 [41879.606491] cpu: 2, pid: 737, index 3 pages 128 [41879.606550] cpu: 0, pid: 736, index 0 pages 7 [41879.612271] cpu: 2, pid: 738, index 4 pages 144 ... v1: https://patchwork.kernel.org/project/linux-mm/cover/20211215080242.3034856-1-aisheng.dong@nxp.com/ v2: https://patchwork.kernel.org/project/linux-mm/cover/20220112131552.3329380-1-aisheng.dong@nxp.com/ Dong Aisheng (2): mm: cma: fix allocation may fail sometimes mm: cma: try next MAX_ORDER_NR_PAGES during retry mm/cma.c | 23 +++++++++++++++++++++-- 1 file changed, 21 insertions(+), 2 deletions(-)