December 2024 - Linux-stable-mirror

[PATCH V3] mm, compaction: don't use ALLOC_CMA in long term GUP flow

by yangge1116＠126.com

From: yangge <yangge1116(a)126.com> Since commit 984fdba6a32e ("mm, compaction: use proper alloc_flags in __compaction_suitable()") allow compaction to proceed when free pages required for compaction reside in the CMA pageblocks, it's possible that __compaction_suitable() always returns true, and in some cases, it's not acceptable. There are 4 NUMA nodes on my machine, and each NUMA node has 32GB of memory. I have configured 16GB of CMA memory on each NUMA node, and starting a 32GB virtual machine with device passthrough is extremely slow, taking almost an hour. During the start-up of the virtual machine, it will call pin_user_pages_remote(..., FOLL_LONGTERM, ...) to allocate memory. Long term GUP cannot allocate memory from CMA area, so a maximum of 16 GB of no-CMA memory on a NUMA node can be used as virtual machine memory. Since there is 16G of free CMA memory on the NUMA node, watermark for order-0 always be met for compaction, so __compaction_suitable() always returns true, even if the node is unable to allocate non-CMA memory for the virtual machine. For costly allocations, because __compaction_suitable() always returns true, __alloc_pages_slowpath() can't exit at the appropriate place, resulting in excessively long virtual machine startup times. Call trace: __alloc_pages_slowpath if (compact_result == COMPACT_SKIPPED || compact_result == COMPACT_DEFERRED) goto nopage; // should exit __alloc_pages_slowpath() from here To sum up, during long term GUP flow, we should remove ALLOC_CMA both in __compaction_suitable() and __isolate_free_page(). Signed-off-by: yangge <yangge1116(a)126.com> --- V3: - fix build errors - add ALLOC_CMA both in should_continue_reclaim() and compaction_ready() V2: - using the 'cc->alloc_flags' to determin if 'ALLOC_CMA' is needed - rich the commit log description include/linux/compaction.h | 6 ++++-- mm/compaction.c | 18 +++++++++++------- mm/page_alloc.c | 4 +++- mm/vmscan.c | 4 ++-- 4 files changed, 20 insertions(+), 12 deletions(-) diff --git a/include/linux/compaction.h b/include/linux/compaction.h index e947764..b4c3ac3 100644 --- a/include/linux/compaction.h +++ b/include/linux/compaction.h @@ -90,7 +90,8 @@ extern enum compact_result try_to_compact_pages(gfp_t gfp_mask, struct page **page); extern void reset_isolation_suitable(pg_data_t *pgdat); extern bool compaction_suitable(struct zone *zone, int order, - int highest_zoneidx); + int highest_zoneidx, + unsigned int alloc_flags); extern void compaction_defer_reset(struct zone *zone, int order, bool alloc_success); @@ -108,7 +109,8 @@ static inline void reset_isolation_suitable(pg_data_t *pgdat) } static inline bool compaction_suitable(struct zone *zone, int order, - int highest_zoneidx) + int highest_zoneidx, + unsigned int alloc_flags) { return false; } diff --git a/mm/compaction.c b/mm/compaction.c index 07bd227..585f5ab 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -2381,9 +2381,11 @@ static enum compact_result compact_finished(struct compact_control *cc) static bool __compaction_suitable(struct zone *zone, int order, int highest_zoneidx, + unsigned int alloc_flags, unsigned long wmark_target) { unsigned long watermark; + bool use_cma; /* * Watermarks for order-0 must be met for compaction to be able to * isolate free pages for migration targets. This means that the @@ -2395,25 +2397,27 @@ static bool __compaction_suitable(struct zone *zone, int order, * even if compaction succeeds. * For costly orders, we require low watermark instead of min for * compaction to proceed to increase its chances. - * ALLOC_CMA is used, as pages in CMA pageblocks are considered - * suitable migration targets + * In addition to long term GUP flow, ALLOC_CMA is used, as pages in + * CMA pageblocks are considered suitable migration targets */ watermark = (order > PAGE_ALLOC_COSTLY_ORDER) ? low_wmark_pages(zone) : min_wmark_pages(zone); watermark += compact_gap(order); + use_cma = !!(alloc_flags & ALLOC_CMA); return __zone_watermark_ok(zone, 0, watermark, highest_zoneidx, - ALLOC_CMA, wmark_target); + use_cma ? ALLOC_CMA : 0, wmark_target); } /* * compaction_suitable: Is this suitable to run compaction on this zone now? */ -bool compaction_suitable(struct zone *zone, int order, int highest_zoneidx) +bool compaction_suitable(struct zone *zone, int order, int highest_zoneidx, + unsigned int alloc_flags) { enum compact_result compact_result; bool suitable; - suitable = __compaction_suitable(zone, order, highest_zoneidx, + suitable = __compaction_suitable(zone, order, highest_zoneidx, alloc_flags, zone_page_state(zone, NR_FREE_PAGES)); /* * fragmentation index determines if allocation failures are due to @@ -2474,7 +2478,7 @@ bool compaction_zonelist_suitable(struct alloc_context *ac, int order, available = zone_reclaimable_pages(zone) / order; available += zone_page_state_snapshot(zone, NR_FREE_PAGES); if (__compaction_suitable(zone, order, ac->highest_zoneidx, - available)) + alloc_flags, available)) return true; } @@ -2499,7 +2503,7 @@ compaction_suit_allocation_order(struct zone *zone, unsigned int order, alloc_flags)) return COMPACT_SUCCESS; - if (!compaction_suitable(zone, order, highest_zoneidx)) + if (!compaction_suitable(zone, order, highest_zoneidx, alloc_flags)) return COMPACT_SKIPPED; return COMPACT_CONTINUE; diff --git a/mm/page_alloc.c b/mm/page_alloc.c index dde19db..9a5dfda 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -2813,6 +2813,7 @@ int __isolate_free_page(struct page *page, unsigned int order) { struct zone *zone = page_zone(page); int mt = get_pageblock_migratetype(page); + bool pin; if (!is_migrate_isolate(mt)) { unsigned long watermark; @@ -2823,7 +2824,8 @@ int __isolate_free_page(struct page *page, unsigned int order) * exists. */ watermark = zone->_watermark[WMARK_MIN] + (1UL << order); - if (!zone_watermark_ok(zone, 0, watermark, 0, ALLOC_CMA)) + pin = !!(current->flags & PF_MEMALLOC_PIN); + if (!zone_watermark_ok(zone, 0, watermark, 0, pin ? 0 : ALLOC_CMA)) return 0; } diff --git a/mm/vmscan.c b/mm/vmscan.c index 5e03a61..33f5b46 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -5815,7 +5815,7 @@ static inline bool should_continue_reclaim(struct pglist_data *pgdat, sc->reclaim_idx, 0)) return false; - if (compaction_suitable(zone, sc->order, sc->reclaim_idx)) + if (compaction_suitable(zone, sc->order, sc->reclaim_idx, ALLOC_CMA)) return false; } @@ -6043,7 +6043,7 @@ static inline bool compaction_ready(struct zone *zone, struct scan_control *sc) return true; /* Compaction cannot yet proceed. Do reclaim. */ - if (!compaction_suitable(zone, sc->order, sc->reclaim_idx)) + if (!compaction_suitable(zone, sc->order, sc->reclaim_idx, ALLOC_CMA)) return false; /* -- 2.7.4

4 months, 2 weeks

2
1
0 0

RE: Patch "mmc: sd: SDUC Support Recognition" has been added to the 6.12-stable tree

by Avri Altman

This patch is part of the series - https://patchwork.kernel.org/project/linux-mmc/list/?series=895924 This is patch 1/10, looks like the other 9 patches are missing. Thanks, Avri > This is a note to let you know that I've just added the patch titled > > mmc: sd: SDUC Support Recognition > > to the 6.12-stable tree which can be found at: > http://www.kernel.org/git/?p=linux/kernel/git/stable/stable- > queue.git;a=summary > > The filename of the patch is: > mmc-sd-sduc-support-recognition.patch > and it can be found in the queue-6.12 subdirectory. > > If you, or anyone else, feels it should not be added to the stable tree, please > let <stable(a)vger.kernel.org> know about it. > > > > commit 67bc965d660760bd68981c067932c4bd807ebf95 > Author: Avri Altman <avri.altman(a)wdc.com> > Date: Sun Oct 6 08:11:39 2024 +0300 > > mmc: sd: SDUC Support Recognition > > [ Upstream commit fce2ce78af1e14dc1316aaddb5b3308be05cf452 ] > > Ultra Capacity SD cards (SDUC) was already introduced in SD7.0. Those > cards support capacity larger than 2TB and up to including 128TB. > > ACMD41 was extended to support the host-card handshake during > initialization. The card expects that the HCS & HO2T bits to be set in > the command argument, and sets the applicable bits in the R3 returned > response. On the contrary, if a SDUC card is inserted to a > non-supporting host, it will never respond to this ACMD41 until > eventually, the host will timed out and give up. > > Also, add SD CSD version 3.0 - designated for SDUC, and properly parse > the csd register as the c_size field got expanded to 28 bits. > > Do not enable SDUC for now - leave it to the last patch in the series. > > Tested-by: Ricky WU <ricky_wu(a)realtek.com> > Reviewed-by: Adrian Hunter <adrian.hunter(a)intel.com> > Signed-off-by: Avri Altman <avri.altman(a)wdc.com> > Link: https://lore.kernel.org/r/20241006051148.160278-2- > avri.altman(a)wdc.com > Signed-off-by: Ulf Hansson <ulf.hansson(a)linaro.org> > Stable-dep-of: 869d37475788 ("mmc: core: Use GFP_NOIO in ACMD22") > Signed-off-by: Sasha Levin <sashal(a)kernel.org> > > diff --git a/drivers/mmc/core/bus.c b/drivers/mmc/core/bus.c index > 0ddaee0eae54f..30763b342bd36 100644 > --- a/drivers/mmc/core/bus.c > +++ b/drivers/mmc/core/bus.c > @@ -321,7 +321,9 @@ int mmc_add_card(struct mmc_card *card) > case MMC_TYPE_SD: > type = "SD"; > if (mmc_card_blockaddr(card)) { > - if (mmc_card_ext_capacity(card)) > + if (mmc_card_ult_capacity(card)) > + type = "SDUC"; > + else if (mmc_card_ext_capacity(card)) > type = "SDXC"; > else > type = "SDHC"; diff --git a/drivers/mmc/core/card.h > b/drivers/mmc/core/card.h index b7754a1b8d978..64dcb463a4f49 100644 > --- a/drivers/mmc/core/card.h > +++ b/drivers/mmc/core/card.h > @@ -23,6 +23,7 @@ > #define MMC_CARD_SDXC (1<<3) /* card is SDXC */ > #define MMC_CARD_REMOVED (1<<4) /* card has been removed */ > #define MMC_STATE_SUSPENDED (1<<5) /* card is suspended */ > +#define MMC_CARD_SDUC (1<<6) /* card is SDUC */ > > #define mmc_card_present(c) ((c)->state & MMC_STATE_PRESENT) > #define mmc_card_readonly(c) ((c)->state & MMC_STATE_READONLY) > @@ -30,11 +31,13 @@ > #define mmc_card_ext_capacity(c) ((c)->state & MMC_CARD_SDXC) > #define mmc_card_removed(c) ((c) && ((c)->state & > MMC_CARD_REMOVED)) > #define mmc_card_suspended(c) ((c)->state & MMC_STATE_SUSPENDED) > +#define mmc_card_ult_capacity(c) ((c)->state & MMC_CARD_SDUC) > > #define mmc_card_set_present(c) ((c)->state |= MMC_STATE_PRESENT) > #define mmc_card_set_readonly(c) ((c)->state |= MMC_STATE_READONLY) > #define mmc_card_set_blockaddr(c) ((c)->state |= MMC_STATE_BLOCKADDR) > #define mmc_card_set_ext_capacity(c) ((c)->state |= MMC_CARD_SDXC) > +#define mmc_card_set_ult_capacity(c) ((c)->state |= MMC_CARD_SDUC) > #define mmc_card_set_removed(c) ((c)->state |= MMC_CARD_REMOVED) > #define mmc_card_set_suspended(c) ((c)->state |= MMC_STATE_SUSPENDED) > #define mmc_card_clr_suspended(c) ((c)->state &= > ~MMC_STATE_SUSPENDED) diff --git a/drivers/mmc/core/sd.c > b/drivers/mmc/core/sd.c index 12fe282bea77e..1d09f0f2e7697 100644 > --- a/drivers/mmc/core/sd.c > +++ b/drivers/mmc/core/sd.c > @@ -100,7 +100,7 @@ void mmc_decode_cid(struct mmc_card *card) > /* > * Given a 128-bit response, decode to our card CSD structure. > */ > -static int mmc_decode_csd(struct mmc_card *card) > +static int mmc_decode_csd(struct mmc_card *card, bool is_sduc) > { > struct mmc_csd *csd = &card->csd; > unsigned int e, m, csd_struct; > @@ -144,9 +144,10 @@ static int mmc_decode_csd(struct mmc_card *card) > mmc_card_set_readonly(card); > break; > case 1: > + case 2: > /* > - * This is a block-addressed SDHC or SDXC card. Most > - * interesting fields are unused and have fixed > + * This is a block-addressed SDHC, SDXC or SDUC card. > + * Most interesting fields are unused and have fixed > * values. To avoid getting tripped by buggy cards, > * we assume those fixed values ourselves. > */ > @@ -159,14 +160,19 @@ static int mmc_decode_csd(struct mmc_card *card) > e = unstuff_bits(resp, 96, 3); > csd->max_dtr = tran_exp[e] * tran_mant[m]; > csd->cmdclass = unstuff_bits(resp, 84, 12); > - csd->c_size = unstuff_bits(resp, 48, 22); > > - /* SDXC cards have a minimum C_SIZE of 0x00FFFF */ > - if (csd->c_size >= 0xFFFF) > + if (csd_struct == 1) > + m = unstuff_bits(resp, 48, 22); > + else > + m = unstuff_bits(resp, 48, 28); > + csd->c_size = m; > + > + if (csd->c_size >= 0x400000 && is_sduc) > + mmc_card_set_ult_capacity(card); > + else if (csd->c_size >= 0xFFFF) > mmc_card_set_ext_capacity(card); > > - m = unstuff_bits(resp, 48, 22); > - csd->capacity = (1 + m) << 10; > + csd->capacity = (1 + (typeof(sector_t))m) << 10; > > csd->read_blkbits = 9; > csd->read_partial = 0; > @@ -876,7 +882,7 @@ int mmc_sd_get_cid(struct mmc_host *host, u32 ocr, > u32 *cid, u32 *rocr) > return err; > } > > -int mmc_sd_get_csd(struct mmc_card *card) > +int mmc_sd_get_csd(struct mmc_card *card, bool is_sduc) > { > int err; > > @@ -887,7 +893,7 @@ int mmc_sd_get_csd(struct mmc_card *card) > if (err) > return err; > > - err = mmc_decode_csd(card); > + err = mmc_decode_csd(card, is_sduc); > if (err) > return err; > > @@ -1442,7 +1448,7 @@ static int mmc_sd_init_card(struct mmc_host > *host, u32 ocr, > } > > if (!oldcard) { > - err = mmc_sd_get_csd(card); > + err = mmc_sd_get_csd(card, false); > if (err) > goto free_card; > > diff --git a/drivers/mmc/core/sd.h b/drivers/mmc/core/sd.h index > fe6dd46927a42..7e8beface2ca6 100644 > --- a/drivers/mmc/core/sd.h > +++ b/drivers/mmc/core/sd.h > @@ -10,7 +10,7 @@ struct mmc_host; > struct mmc_card; > > int mmc_sd_get_cid(struct mmc_host *host, u32 ocr, u32 *cid, u32 *rocr); - > int mmc_sd_get_csd(struct mmc_card *card); > +int mmc_sd_get_csd(struct mmc_card *card, bool is_sduc); > void mmc_decode_cid(struct mmc_card *card); int > mmc_sd_setup_card(struct mmc_host *host, struct mmc_card *card, > bool reinit); > diff --git a/drivers/mmc/core/sdio.c b/drivers/mmc/core/sdio.c index > 4fb247fde5c08..9566837c9848e 100644 > --- a/drivers/mmc/core/sdio.c > +++ b/drivers/mmc/core/sdio.c > @@ -769,7 +769,7 @@ static int mmc_sdio_init_card(struct mmc_host *host, > u32 ocr, > * Read CSD, before selecting the card > */ > if (!oldcard && mmc_card_sd_combo(card)) { > - err = mmc_sd_get_csd(card); > + err = mmc_sd_get_csd(card, false); > if (err) > goto remove; > > diff --git a/include/linux/mmc/card.h b/include/linux/mmc/card.h index > f34407cc27888..f39bce3223654 100644 > --- a/include/linux/mmc/card.h > +++ b/include/linux/mmc/card.h > @@ -35,7 +35,7 @@ struct mmc_csd { > unsigned int wp_grp_size; > unsigned int read_blkbits; > unsigned int write_blkbits; > - unsigned int capacity; > + sector_t capacity; > unsigned int read_partial:1, > read_misalign:1, > write_partial:1, diff --git a/include/linux/mmc/sd.h > b/include/linux/mmc/sd.h index 6727576a87555..865cc0ca8543d 100644 > --- a/include/linux/mmc/sd.h > +++ b/include/linux/mmc/sd.h > @@ -36,6 +36,7 @@ > /* OCR bit definitions */ > #define SD_OCR_S18R (1 << 24) /* 1.8V switching request */ > #define SD_ROCR_S18A SD_OCR_S18R /* 1.8V switching accepted by > card */ > +#define SD_OCR_2T (1 << 27) /* HO2T/CO2T - SDUC support */ > #define SD_OCR_XPC (1 << 28) /* SDXC power control */ > #define SD_OCR_CCS (1 << 30) /* Card Capacity Status */

4 months, 2 weeks

1
0
0 0

FAILED: patch "[PATCH] blk-cgroup: Fix UAF in blkcg_unpin_online()" failed to apply to 5.10-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.10-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.10.y git checkout FETCH_HEAD git cherry-pick -x 86e6ca55b83c575ab0f2e105cf08f98e58d3d7af # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024121539-nutty-gangly-3dff@gregkh' --subject-prefix 'PATCH 5.10.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 86e6ca55b83c575ab0f2e105cf08f98e58d3d7af Mon Sep 17 00:00:00 2001 From: Tejun Heo <tj(a)kernel.org> Date: Fri, 6 Dec 2024 07:59:51 -1000 Subject: [PATCH] blk-cgroup: Fix UAF in blkcg_unpin_online() blkcg_unpin_online() walks up the blkcg hierarchy putting the online pin. To walk up, it uses blkcg_parent(blkcg) but it was calling that after blkcg_destroy_blkgs(blkcg) which could free the blkcg, leading to the following UAF: ================================================================== BUG: KASAN: slab-use-after-free in blkcg_unpin_online+0x15a/0x270 Read of size 8 at addr ffff8881057678c0 by task kworker/9:1/117 CPU: 9 UID: 0 PID: 117 Comm: kworker/9:1 Not tainted 6.13.0-rc1-work-00182-gb8f52214c61a-dirty #48 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS unknown 02/02/2022 Workqueue: cgwb_release cgwb_release_workfn Call Trace: <TASK> dump_stack_lvl+0x27/0x80 print_report+0x151/0x710 kasan_report+0xc0/0x100 blkcg_unpin_online+0x15a/0x270 cgwb_release_workfn+0x194/0x480 process_scheduled_works+0x71b/0xe20 worker_thread+0x82a/0xbd0 kthread+0x242/0x2c0 ret_from_fork+0x33/0x70 ret_from_fork_asm+0x1a/0x30 </TASK> ... Freed by task 1944: kasan_save_track+0x2b/0x70 kasan_save_free_info+0x3c/0x50 __kasan_slab_free+0x33/0x50 kfree+0x10c/0x330 css_free_rwork_fn+0xe6/0xb30 process_scheduled_works+0x71b/0xe20 worker_thread+0x82a/0xbd0 kthread+0x242/0x2c0 ret_from_fork+0x33/0x70 ret_from_fork_asm+0x1a/0x30 Note that the UAF is not easy to trigger as the free path is indirected behind a couple RCU grace periods and a work item execution. I could only trigger it with artifical msleep() injected in blkcg_unpin_online(). Fix it by reading the parent pointer before destroying the blkcg's blkg's. Signed-off-by: Tejun Heo <tj(a)kernel.org> Reported-by: Abagail ren <renzezhongucas(a)gmail.com> Suggested-by: Linus Torvalds <torvalds(a)linuxfoundation.org> Fixes: 4308a434e5e0 ("blkcg: don't offline parent blkcg first") Cc: stable(a)vger.kernel.org # v5.7+ Signed-off-by: Jens Axboe <axboe(a)kernel.dk> diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index e68c725cf8d9..45a395862fbc 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -1324,10 +1324,14 @@ void blkcg_unpin_online(struct cgroup_subsys_state *blkcg_css) struct blkcg *blkcg = css_to_blkcg(blkcg_css); do { + struct blkcg *parent; + if (!refcount_dec_and_test(&blkcg->online_pin)) break; + + parent = blkcg_parent(blkcg); blkcg_destroy_blkgs(blkcg); - blkcg = blkcg_parent(blkcg); + blkcg = parent; } while (blkcg); }

4 months, 2 weeks

1
0
0 0

FAILED: patch "[PATCH] blk-cgroup: Fix UAF in blkcg_unpin_online()" failed to apply to 5.15-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.15-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.15.y git checkout FETCH_HEAD git cherry-pick -x 86e6ca55b83c575ab0f2e105cf08f98e58d3d7af # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024121538-engorge-overplant-b846@gregkh' --subject-prefix 'PATCH 5.15.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 86e6ca55b83c575ab0f2e105cf08f98e58d3d7af Mon Sep 17 00:00:00 2001 From: Tejun Heo <tj(a)kernel.org> Date: Fri, 6 Dec 2024 07:59:51 -1000 Subject: [PATCH] blk-cgroup: Fix UAF in blkcg_unpin_online() blkcg_unpin_online() walks up the blkcg hierarchy putting the online pin. To walk up, it uses blkcg_parent(blkcg) but it was calling that after blkcg_destroy_blkgs(blkcg) which could free the blkcg, leading to the following UAF: ================================================================== BUG: KASAN: slab-use-after-free in blkcg_unpin_online+0x15a/0x270 Read of size 8 at addr ffff8881057678c0 by task kworker/9:1/117 CPU: 9 UID: 0 PID: 117 Comm: kworker/9:1 Not tainted 6.13.0-rc1-work-00182-gb8f52214c61a-dirty #48 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS unknown 02/02/2022 Workqueue: cgwb_release cgwb_release_workfn Call Trace: <TASK> dump_stack_lvl+0x27/0x80 print_report+0x151/0x710 kasan_report+0xc0/0x100 blkcg_unpin_online+0x15a/0x270 cgwb_release_workfn+0x194/0x480 process_scheduled_works+0x71b/0xe20 worker_thread+0x82a/0xbd0 kthread+0x242/0x2c0 ret_from_fork+0x33/0x70 ret_from_fork_asm+0x1a/0x30 </TASK> ... Freed by task 1944: kasan_save_track+0x2b/0x70 kasan_save_free_info+0x3c/0x50 __kasan_slab_free+0x33/0x50 kfree+0x10c/0x330 css_free_rwork_fn+0xe6/0xb30 process_scheduled_works+0x71b/0xe20 worker_thread+0x82a/0xbd0 kthread+0x242/0x2c0 ret_from_fork+0x33/0x70 ret_from_fork_asm+0x1a/0x30 Note that the UAF is not easy to trigger as the free path is indirected behind a couple RCU grace periods and a work item execution. I could only trigger it with artifical msleep() injected in blkcg_unpin_online(). Fix it by reading the parent pointer before destroying the blkcg's blkg's. Signed-off-by: Tejun Heo <tj(a)kernel.org> Reported-by: Abagail ren <renzezhongucas(a)gmail.com> Suggested-by: Linus Torvalds <torvalds(a)linuxfoundation.org> Fixes: 4308a434e5e0 ("blkcg: don't offline parent blkcg first") Cc: stable(a)vger.kernel.org # v5.7+ Signed-off-by: Jens Axboe <axboe(a)kernel.dk> diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index e68c725cf8d9..45a395862fbc 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -1324,10 +1324,14 @@ void blkcg_unpin_online(struct cgroup_subsys_state *blkcg_css) struct blkcg *blkcg = css_to_blkcg(blkcg_css); do { + struct blkcg *parent; + if (!refcount_dec_and_test(&blkcg->online_pin)) break; + + parent = blkcg_parent(blkcg); blkcg_destroy_blkgs(blkcg); - blkcg = blkcg_parent(blkcg); + blkcg = parent; } while (blkcg); }

4 months, 2 weeks

1
0
0 0

FAILED: patch "[PATCH] serial: sh-sci: Check if TX data was written to device in" failed to apply to 5.4-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.4-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.4.y git checkout FETCH_HEAD git cherry-pick -x 7cc0e0a43a91052477c2921f924a37d9c3891f0c # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024121535-obscurity-banking-b3af@gregkh' --subject-prefix 'PATCH 5.4.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 7cc0e0a43a91052477c2921f924a37d9c3891f0c Mon Sep 17 00:00:00 2001 From: Claudiu Beznea <claudiu.beznea.uj(a)bp.renesas.com> Date: Mon, 25 Nov 2024 13:58:56 +0200 Subject: [PATCH] serial: sh-sci: Check if TX data was written to device in .tx_empty() On the Renesas RZ/G3S, when doing suspend to RAM, the uart_suspend_port() is called. The uart_suspend_port() calls 3 times the struct uart_port::ops::tx_empty() before shutting down the port. According to the documentation, the struct uart_port::ops::tx_empty() API tests whether the transmitter FIFO and shifter for the port is empty. The Renesas RZ/G3S SCIFA IP reports the number of data units stored in the transmit FIFO through the FDR (FIFO Data Count Register). The data units in the FIFOs are written in the shift register and transmitted from there. The TEND bit in the Serial Status Register reports if the data was transmitted from the shift register. In the previous code, in the tx_empty() API implemented by the sh-sci driver, it is considered that the TX is empty if the hardware reports the TEND bit set and the number of data units in the FIFO is zero. According to the HW manual, the TEND bit has the following meaning: 0: Transmission is in the waiting state or in progress. 1: Transmission is completed. It has been noticed that when opening the serial device w/o using it and then switch to a power saving mode, the tx_empty() call in the uart_port_suspend() function fails, leading to the "Unable to drain transmitter" message being printed on the console. This is because the TEND=0 if nothing has been transmitted and the FIFOs are empty. As the TEND=0 has double meaning (waiting state, in progress) we can't determined the scenario described above. Add a software workaround for this. This sets a variable if any data has been sent on the serial console (when using PIO) or if the DMA callback has been called (meaning something has been transmitted). In the tx_empty() API the status of the DMA transaction is also checked and if it is completed or in progress the code falls back in checking the hardware registers instead of relying on the software variable. Fixes: 73a19e4c0301 ("serial: sh-sci: Add DMA support.") Cc: stable(a)vger.kernel.org Signed-off-by: Claudiu Beznea <claudiu.beznea.uj(a)bp.renesas.com> Link: https://lore.kernel.org/r/20241125115856.513642-1-claudiu.beznea.uj@bp.rene… Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> diff --git a/drivers/tty/serial/sh-sci.c b/drivers/tty/serial/sh-sci.c index df523c744423..924b803af440 100644 --- a/drivers/tty/serial/sh-sci.c +++ b/drivers/tty/serial/sh-sci.c @@ -157,6 +157,7 @@ struct sci_port { bool has_rtscts; bool autorts; + bool tx_occurred; }; #define SCI_NPORTS CONFIG_SERIAL_SH_SCI_NR_UARTS @@ -850,6 +851,7 @@ static void sci_transmit_chars(struct uart_port *port) { struct tty_port *tport = &port->state->port; unsigned int stopped = uart_tx_stopped(port); + struct sci_port *s = to_sci_port(port); unsigned short status; unsigned short ctrl; int count; @@ -885,6 +887,7 @@ static void sci_transmit_chars(struct uart_port *port) } sci_serial_out(port, SCxTDR, c); + s->tx_occurred = true; port->icount.tx++; } while (--count > 0); @@ -1241,6 +1244,8 @@ static void sci_dma_tx_complete(void *arg) if (kfifo_len(&tport->xmit_fifo) < WAKEUP_CHARS) uart_write_wakeup(port); + s->tx_occurred = true; + if (!kfifo_is_empty(&tport->xmit_fifo)) { s->cookie_tx = 0; schedule_work(&s->work_tx); @@ -1731,6 +1736,19 @@ static void sci_flush_buffer(struct uart_port *port) s->cookie_tx = -EINVAL; } } + +static void sci_dma_check_tx_occurred(struct sci_port *s) +{ + struct dma_tx_state state; + enum dma_status status; + + if (!s->chan_tx) + return; + + status = dmaengine_tx_status(s->chan_tx, s->cookie_tx, &state); + if (status == DMA_COMPLETE || status == DMA_IN_PROGRESS) + s->tx_occurred = true; +} #else /* !CONFIG_SERIAL_SH_SCI_DMA */ static inline void sci_request_dma(struct uart_port *port) { @@ -1740,6 +1758,10 @@ static inline void sci_free_dma(struct uart_port *port) { } +static void sci_dma_check_tx_occurred(struct sci_port *s) +{ +} + #define sci_flush_buffer NULL #endif /* !CONFIG_SERIAL_SH_SCI_DMA */ @@ -2076,6 +2098,12 @@ static unsigned int sci_tx_empty(struct uart_port *port) { unsigned short status = sci_serial_in(port, SCxSR); unsigned short in_tx_fifo = sci_txfill(port); + struct sci_port *s = to_sci_port(port); + + sci_dma_check_tx_occurred(s); + + if (!s->tx_occurred) + return TIOCSER_TEMT; return (status & SCxSR_TEND(port)) && !in_tx_fifo ? TIOCSER_TEMT : 0; } @@ -2247,6 +2275,7 @@ static int sci_startup(struct uart_port *port) dev_dbg(port->dev, "%s(%d)\n", __func__, port->line); + s->tx_occurred = false; sci_request_dma(port); ret = sci_request_irq(s);

4 months, 2 weeks

1
0
0 0

FAILED: patch "[PATCH] serial: sh-sci: Check if TX data was written to device in" failed to apply to 5.10-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.10-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.10.y git checkout FETCH_HEAD git cherry-pick -x 7cc0e0a43a91052477c2921f924a37d9c3891f0c # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024121534-getaway-geometric-0284@gregkh' --subject-prefix 'PATCH 5.10.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 7cc0e0a43a91052477c2921f924a37d9c3891f0c Mon Sep 17 00:00:00 2001 From: Claudiu Beznea <claudiu.beznea.uj(a)bp.renesas.com> Date: Mon, 25 Nov 2024 13:58:56 +0200 Subject: [PATCH] serial: sh-sci: Check if TX data was written to device in .tx_empty() On the Renesas RZ/G3S, when doing suspend to RAM, the uart_suspend_port() is called. The uart_suspend_port() calls 3 times the struct uart_port::ops::tx_empty() before shutting down the port. According to the documentation, the struct uart_port::ops::tx_empty() API tests whether the transmitter FIFO and shifter for the port is empty. The Renesas RZ/G3S SCIFA IP reports the number of data units stored in the transmit FIFO through the FDR (FIFO Data Count Register). The data units in the FIFOs are written in the shift register and transmitted from there. The TEND bit in the Serial Status Register reports if the data was transmitted from the shift register. In the previous code, in the tx_empty() API implemented by the sh-sci driver, it is considered that the TX is empty if the hardware reports the TEND bit set and the number of data units in the FIFO is zero. According to the HW manual, the TEND bit has the following meaning: 0: Transmission is in the waiting state or in progress. 1: Transmission is completed. It has been noticed that when opening the serial device w/o using it and then switch to a power saving mode, the tx_empty() call in the uart_port_suspend() function fails, leading to the "Unable to drain transmitter" message being printed on the console. This is because the TEND=0 if nothing has been transmitted and the FIFOs are empty. As the TEND=0 has double meaning (waiting state, in progress) we can't determined the scenario described above. Add a software workaround for this. This sets a variable if any data has been sent on the serial console (when using PIO) or if the DMA callback has been called (meaning something has been transmitted). In the tx_empty() API the status of the DMA transaction is also checked and if it is completed or in progress the code falls back in checking the hardware registers instead of relying on the software variable. Fixes: 73a19e4c0301 ("serial: sh-sci: Add DMA support.") Cc: stable(a)vger.kernel.org Signed-off-by: Claudiu Beznea <claudiu.beznea.uj(a)bp.renesas.com> Link: https://lore.kernel.org/r/20241125115856.513642-1-claudiu.beznea.uj@bp.rene… Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> diff --git a/drivers/tty/serial/sh-sci.c b/drivers/tty/serial/sh-sci.c index df523c744423..924b803af440 100644 --- a/drivers/tty/serial/sh-sci.c +++ b/drivers/tty/serial/sh-sci.c @@ -157,6 +157,7 @@ struct sci_port { bool has_rtscts; bool autorts; + bool tx_occurred; }; #define SCI_NPORTS CONFIG_SERIAL_SH_SCI_NR_UARTS @@ -850,6 +851,7 @@ static void sci_transmit_chars(struct uart_port *port) { struct tty_port *tport = &port->state->port; unsigned int stopped = uart_tx_stopped(port); + struct sci_port *s = to_sci_port(port); unsigned short status; unsigned short ctrl; int count; @@ -885,6 +887,7 @@ static void sci_transmit_chars(struct uart_port *port) } sci_serial_out(port, SCxTDR, c); + s->tx_occurred = true; port->icount.tx++; } while (--count > 0); @@ -1241,6 +1244,8 @@ static void sci_dma_tx_complete(void *arg) if (kfifo_len(&tport->xmit_fifo) < WAKEUP_CHARS) uart_write_wakeup(port); + s->tx_occurred = true; + if (!kfifo_is_empty(&tport->xmit_fifo)) { s->cookie_tx = 0; schedule_work(&s->work_tx); @@ -1731,6 +1736,19 @@ static void sci_flush_buffer(struct uart_port *port) s->cookie_tx = -EINVAL; } } + +static void sci_dma_check_tx_occurred(struct sci_port *s) +{ + struct dma_tx_state state; + enum dma_status status; + + if (!s->chan_tx) + return; + + status = dmaengine_tx_status(s->chan_tx, s->cookie_tx, &state); + if (status == DMA_COMPLETE || status == DMA_IN_PROGRESS) + s->tx_occurred = true; +} #else /* !CONFIG_SERIAL_SH_SCI_DMA */ static inline void sci_request_dma(struct uart_port *port) { @@ -1740,6 +1758,10 @@ static inline void sci_free_dma(struct uart_port *port) { } +static void sci_dma_check_tx_occurred(struct sci_port *s) +{ +} + #define sci_flush_buffer NULL #endif /* !CONFIG_SERIAL_SH_SCI_DMA */ @@ -2076,6 +2098,12 @@ static unsigned int sci_tx_empty(struct uart_port *port) { unsigned short status = sci_serial_in(port, SCxSR); unsigned short in_tx_fifo = sci_txfill(port); + struct sci_port *s = to_sci_port(port); + + sci_dma_check_tx_occurred(s); + + if (!s->tx_occurred) + return TIOCSER_TEMT; return (status & SCxSR_TEND(port)) && !in_tx_fifo ? TIOCSER_TEMT : 0; } @@ -2247,6 +2275,7 @@ static int sci_startup(struct uart_port *port) dev_dbg(port->dev, "%s(%d)\n", __func__, port->line); + s->tx_occurred = false; sci_request_dma(port); ret = sci_request_irq(s);

4 months, 2 weeks

1
0
0 0

FAILED: patch "[PATCH] serial: sh-sci: Check if TX data was written to device in" failed to apply to 5.15-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.15-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.15.y git checkout FETCH_HEAD git cherry-pick -x 7cc0e0a43a91052477c2921f924a37d9c3891f0c # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024121532-brunch-radiation-be3a@gregkh' --subject-prefix 'PATCH 5.15.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 7cc0e0a43a91052477c2921f924a37d9c3891f0c Mon Sep 17 00:00:00 2001 From: Claudiu Beznea <claudiu.beznea.uj(a)bp.renesas.com> Date: Mon, 25 Nov 2024 13:58:56 +0200 Subject: [PATCH] serial: sh-sci: Check if TX data was written to device in .tx_empty() On the Renesas RZ/G3S, when doing suspend to RAM, the uart_suspend_port() is called. The uart_suspend_port() calls 3 times the struct uart_port::ops::tx_empty() before shutting down the port. According to the documentation, the struct uart_port::ops::tx_empty() API tests whether the transmitter FIFO and shifter for the port is empty. The Renesas RZ/G3S SCIFA IP reports the number of data units stored in the transmit FIFO through the FDR (FIFO Data Count Register). The data units in the FIFOs are written in the shift register and transmitted from there. The TEND bit in the Serial Status Register reports if the data was transmitted from the shift register. In the previous code, in the tx_empty() API implemented by the sh-sci driver, it is considered that the TX is empty if the hardware reports the TEND bit set and the number of data units in the FIFO is zero. According to the HW manual, the TEND bit has the following meaning: 0: Transmission is in the waiting state or in progress. 1: Transmission is completed. It has been noticed that when opening the serial device w/o using it and then switch to a power saving mode, the tx_empty() call in the uart_port_suspend() function fails, leading to the "Unable to drain transmitter" message being printed on the console. This is because the TEND=0 if nothing has been transmitted and the FIFOs are empty. As the TEND=0 has double meaning (waiting state, in progress) we can't determined the scenario described above. Add a software workaround for this. This sets a variable if any data has been sent on the serial console (when using PIO) or if the DMA callback has been called (meaning something has been transmitted). In the tx_empty() API the status of the DMA transaction is also checked and if it is completed or in progress the code falls back in checking the hardware registers instead of relying on the software variable. Fixes: 73a19e4c0301 ("serial: sh-sci: Add DMA support.") Cc: stable(a)vger.kernel.org Signed-off-by: Claudiu Beznea <claudiu.beznea.uj(a)bp.renesas.com> Link: https://lore.kernel.org/r/20241125115856.513642-1-claudiu.beznea.uj@bp.rene… Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> diff --git a/drivers/tty/serial/sh-sci.c b/drivers/tty/serial/sh-sci.c index df523c744423..924b803af440 100644 --- a/drivers/tty/serial/sh-sci.c +++ b/drivers/tty/serial/sh-sci.c @@ -157,6 +157,7 @@ struct sci_port { bool has_rtscts; bool autorts; + bool tx_occurred; }; #define SCI_NPORTS CONFIG_SERIAL_SH_SCI_NR_UARTS @@ -850,6 +851,7 @@ static void sci_transmit_chars(struct uart_port *port) { struct tty_port *tport = &port->state->port; unsigned int stopped = uart_tx_stopped(port); + struct sci_port *s = to_sci_port(port); unsigned short status; unsigned short ctrl; int count; @@ -885,6 +887,7 @@ static void sci_transmit_chars(struct uart_port *port) } sci_serial_out(port, SCxTDR, c); + s->tx_occurred = true; port->icount.tx++; } while (--count > 0); @@ -1241,6 +1244,8 @@ static void sci_dma_tx_complete(void *arg) if (kfifo_len(&tport->xmit_fifo) < WAKEUP_CHARS) uart_write_wakeup(port); + s->tx_occurred = true; + if (!kfifo_is_empty(&tport->xmit_fifo)) { s->cookie_tx = 0; schedule_work(&s->work_tx); @@ -1731,6 +1736,19 @@ static void sci_flush_buffer(struct uart_port *port) s->cookie_tx = -EINVAL; } } + +static void sci_dma_check_tx_occurred(struct sci_port *s) +{ + struct dma_tx_state state; + enum dma_status status; + + if (!s->chan_tx) + return; + + status = dmaengine_tx_status(s->chan_tx, s->cookie_tx, &state); + if (status == DMA_COMPLETE || status == DMA_IN_PROGRESS) + s->tx_occurred = true; +} #else /* !CONFIG_SERIAL_SH_SCI_DMA */ static inline void sci_request_dma(struct uart_port *port) { @@ -1740,6 +1758,10 @@ static inline void sci_free_dma(struct uart_port *port) { } +static void sci_dma_check_tx_occurred(struct sci_port *s) +{ +} + #define sci_flush_buffer NULL #endif /* !CONFIG_SERIAL_SH_SCI_DMA */ @@ -2076,6 +2098,12 @@ static unsigned int sci_tx_empty(struct uart_port *port) { unsigned short status = sci_serial_in(port, SCxSR); unsigned short in_tx_fifo = sci_txfill(port); + struct sci_port *s = to_sci_port(port); + + sci_dma_check_tx_occurred(s); + + if (!s->tx_occurred) + return TIOCSER_TEMT; return (status & SCxSR_TEND(port)) && !in_tx_fifo ? TIOCSER_TEMT : 0; } @@ -2247,6 +2275,7 @@ static int sci_startup(struct uart_port *port) dev_dbg(port->dev, "%s(%d)\n", __func__, port->line); + s->tx_occurred = false; sci_request_dma(port); ret = sci_request_irq(s);

4 months, 2 weeks

1
0
0 0

FAILED: patch "[PATCH] serial: sh-sci: Check if TX data was written to device in" failed to apply to 6.1-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.1-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.1.y git checkout FETCH_HEAD git cherry-pick -x 7cc0e0a43a91052477c2921f924a37d9c3891f0c # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024121531-unlearned-fondue-04e3@gregkh' --subject-prefix 'PATCH 6.1.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 7cc0e0a43a91052477c2921f924a37d9c3891f0c Mon Sep 17 00:00:00 2001 From: Claudiu Beznea <claudiu.beznea.uj(a)bp.renesas.com> Date: Mon, 25 Nov 2024 13:58:56 +0200 Subject: [PATCH] serial: sh-sci: Check if TX data was written to device in .tx_empty() On the Renesas RZ/G3S, when doing suspend to RAM, the uart_suspend_port() is called. The uart_suspend_port() calls 3 times the struct uart_port::ops::tx_empty() before shutting down the port. According to the documentation, the struct uart_port::ops::tx_empty() API tests whether the transmitter FIFO and shifter for the port is empty. The Renesas RZ/G3S SCIFA IP reports the number of data units stored in the transmit FIFO through the FDR (FIFO Data Count Register). The data units in the FIFOs are written in the shift register and transmitted from there. The TEND bit in the Serial Status Register reports if the data was transmitted from the shift register. In the previous code, in the tx_empty() API implemented by the sh-sci driver, it is considered that the TX is empty if the hardware reports the TEND bit set and the number of data units in the FIFO is zero. According to the HW manual, the TEND bit has the following meaning: 0: Transmission is in the waiting state or in progress. 1: Transmission is completed. It has been noticed that when opening the serial device w/o using it and then switch to a power saving mode, the tx_empty() call in the uart_port_suspend() function fails, leading to the "Unable to drain transmitter" message being printed on the console. This is because the TEND=0 if nothing has been transmitted and the FIFOs are empty. As the TEND=0 has double meaning (waiting state, in progress) we can't determined the scenario described above. Add a software workaround for this. This sets a variable if any data has been sent on the serial console (when using PIO) or if the DMA callback has been called (meaning something has been transmitted). In the tx_empty() API the status of the DMA transaction is also checked and if it is completed or in progress the code falls back in checking the hardware registers instead of relying on the software variable. Fixes: 73a19e4c0301 ("serial: sh-sci: Add DMA support.") Cc: stable(a)vger.kernel.org Signed-off-by: Claudiu Beznea <claudiu.beznea.uj(a)bp.renesas.com> Link: https://lore.kernel.org/r/20241125115856.513642-1-claudiu.beznea.uj@bp.rene… Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> diff --git a/drivers/tty/serial/sh-sci.c b/drivers/tty/serial/sh-sci.c index df523c744423..924b803af440 100644 --- a/drivers/tty/serial/sh-sci.c +++ b/drivers/tty/serial/sh-sci.c @@ -157,6 +157,7 @@ struct sci_port { bool has_rtscts; bool autorts; + bool tx_occurred; }; #define SCI_NPORTS CONFIG_SERIAL_SH_SCI_NR_UARTS @@ -850,6 +851,7 @@ static void sci_transmit_chars(struct uart_port *port) { struct tty_port *tport = &port->state->port; unsigned int stopped = uart_tx_stopped(port); + struct sci_port *s = to_sci_port(port); unsigned short status; unsigned short ctrl; int count; @@ -885,6 +887,7 @@ static void sci_transmit_chars(struct uart_port *port) } sci_serial_out(port, SCxTDR, c); + s->tx_occurred = true; port->icount.tx++; } while (--count > 0); @@ -1241,6 +1244,8 @@ static void sci_dma_tx_complete(void *arg) if (kfifo_len(&tport->xmit_fifo) < WAKEUP_CHARS) uart_write_wakeup(port); + s->tx_occurred = true; + if (!kfifo_is_empty(&tport->xmit_fifo)) { s->cookie_tx = 0; schedule_work(&s->work_tx); @@ -1731,6 +1736,19 @@ static void sci_flush_buffer(struct uart_port *port) s->cookie_tx = -EINVAL; } } + +static void sci_dma_check_tx_occurred(struct sci_port *s) +{ + struct dma_tx_state state; + enum dma_status status; + + if (!s->chan_tx) + return; + + status = dmaengine_tx_status(s->chan_tx, s->cookie_tx, &state); + if (status == DMA_COMPLETE || status == DMA_IN_PROGRESS) + s->tx_occurred = true; +} #else /* !CONFIG_SERIAL_SH_SCI_DMA */ static inline void sci_request_dma(struct uart_port *port) { @@ -1740,6 +1758,10 @@ static inline void sci_free_dma(struct uart_port *port) { } +static void sci_dma_check_tx_occurred(struct sci_port *s) +{ +} + #define sci_flush_buffer NULL #endif /* !CONFIG_SERIAL_SH_SCI_DMA */ @@ -2076,6 +2098,12 @@ static unsigned int sci_tx_empty(struct uart_port *port) { unsigned short status = sci_serial_in(port, SCxSR); unsigned short in_tx_fifo = sci_txfill(port); + struct sci_port *s = to_sci_port(port); + + sci_dma_check_tx_occurred(s); + + if (!s->tx_occurred) + return TIOCSER_TEMT; return (status & SCxSR_TEND(port)) && !in_tx_fifo ? TIOCSER_TEMT : 0; } @@ -2247,6 +2275,7 @@ static int sci_startup(struct uart_port *port) dev_dbg(port->dev, "%s(%d)\n", __func__, port->line); + s->tx_occurred = false; sci_request_dma(port); ret = sci_request_irq(s);

4 months, 2 weeks

1
0
0 0

FAILED: patch "[PATCH] serial: sh-sci: Check if TX data was written to device in" failed to apply to 6.6-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.6-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.6.y git checkout FETCH_HEAD git cherry-pick -x 7cc0e0a43a91052477c2921f924a37d9c3891f0c # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024121530-womanlike-motocross-3283@gregkh' --subject-prefix 'PATCH 6.6.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 7cc0e0a43a91052477c2921f924a37d9c3891f0c Mon Sep 17 00:00:00 2001 From: Claudiu Beznea <claudiu.beznea.uj(a)bp.renesas.com> Date: Mon, 25 Nov 2024 13:58:56 +0200 Subject: [PATCH] serial: sh-sci: Check if TX data was written to device in .tx_empty() On the Renesas RZ/G3S, when doing suspend to RAM, the uart_suspend_port() is called. The uart_suspend_port() calls 3 times the struct uart_port::ops::tx_empty() before shutting down the port. According to the documentation, the struct uart_port::ops::tx_empty() API tests whether the transmitter FIFO and shifter for the port is empty. The Renesas RZ/G3S SCIFA IP reports the number of data units stored in the transmit FIFO through the FDR (FIFO Data Count Register). The data units in the FIFOs are written in the shift register and transmitted from there. The TEND bit in the Serial Status Register reports if the data was transmitted from the shift register. In the previous code, in the tx_empty() API implemented by the sh-sci driver, it is considered that the TX is empty if the hardware reports the TEND bit set and the number of data units in the FIFO is zero. According to the HW manual, the TEND bit has the following meaning: 0: Transmission is in the waiting state or in progress. 1: Transmission is completed. It has been noticed that when opening the serial device w/o using it and then switch to a power saving mode, the tx_empty() call in the uart_port_suspend() function fails, leading to the "Unable to drain transmitter" message being printed on the console. This is because the TEND=0 if nothing has been transmitted and the FIFOs are empty. As the TEND=0 has double meaning (waiting state, in progress) we can't determined the scenario described above. Add a software workaround for this. This sets a variable if any data has been sent on the serial console (when using PIO) or if the DMA callback has been called (meaning something has been transmitted). In the tx_empty() API the status of the DMA transaction is also checked and if it is completed or in progress the code falls back in checking the hardware registers instead of relying on the software variable. Fixes: 73a19e4c0301 ("serial: sh-sci: Add DMA support.") Cc: stable(a)vger.kernel.org Signed-off-by: Claudiu Beznea <claudiu.beznea.uj(a)bp.renesas.com> Link: https://lore.kernel.org/r/20241125115856.513642-1-claudiu.beznea.uj@bp.rene… Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> diff --git a/drivers/tty/serial/sh-sci.c b/drivers/tty/serial/sh-sci.c index df523c744423..924b803af440 100644 --- a/drivers/tty/serial/sh-sci.c +++ b/drivers/tty/serial/sh-sci.c @@ -157,6 +157,7 @@ struct sci_port { bool has_rtscts; bool autorts; + bool tx_occurred; }; #define SCI_NPORTS CONFIG_SERIAL_SH_SCI_NR_UARTS @@ -850,6 +851,7 @@ static void sci_transmit_chars(struct uart_port *port) { struct tty_port *tport = &port->state->port; unsigned int stopped = uart_tx_stopped(port); + struct sci_port *s = to_sci_port(port); unsigned short status; unsigned short ctrl; int count; @@ -885,6 +887,7 @@ static void sci_transmit_chars(struct uart_port *port) } sci_serial_out(port, SCxTDR, c); + s->tx_occurred = true; port->icount.tx++; } while (--count > 0); @@ -1241,6 +1244,8 @@ static void sci_dma_tx_complete(void *arg) if (kfifo_len(&tport->xmit_fifo) < WAKEUP_CHARS) uart_write_wakeup(port); + s->tx_occurred = true; + if (!kfifo_is_empty(&tport->xmit_fifo)) { s->cookie_tx = 0; schedule_work(&s->work_tx); @@ -1731,6 +1736,19 @@ static void sci_flush_buffer(struct uart_port *port) s->cookie_tx = -EINVAL; } } + +static void sci_dma_check_tx_occurred(struct sci_port *s) +{ + struct dma_tx_state state; + enum dma_status status; + + if (!s->chan_tx) + return; + + status = dmaengine_tx_status(s->chan_tx, s->cookie_tx, &state); + if (status == DMA_COMPLETE || status == DMA_IN_PROGRESS) + s->tx_occurred = true; +} #else /* !CONFIG_SERIAL_SH_SCI_DMA */ static inline void sci_request_dma(struct uart_port *port) { @@ -1740,6 +1758,10 @@ static inline void sci_free_dma(struct uart_port *port) { } +static void sci_dma_check_tx_occurred(struct sci_port *s) +{ +} + #define sci_flush_buffer NULL #endif /* !CONFIG_SERIAL_SH_SCI_DMA */ @@ -2076,6 +2098,12 @@ static unsigned int sci_tx_empty(struct uart_port *port) { unsigned short status = sci_serial_in(port, SCxSR); unsigned short in_tx_fifo = sci_txfill(port); + struct sci_port *s = to_sci_port(port); + + sci_dma_check_tx_occurred(s); + + if (!s->tx_occurred) + return TIOCSER_TEMT; return (status & SCxSR_TEND(port)) && !in_tx_fifo ? TIOCSER_TEMT : 0; } @@ -2247,6 +2275,7 @@ static int sci_startup(struct uart_port *port) dev_dbg(port->dev, "%s(%d)\n", __func__, port->line); + s->tx_occurred = false; sci_request_dma(port); ret = sci_request_irq(s);

4 months, 2 weeks

1
0
0 0

[PATCH V2] mm, compaction: don't use ALLOC_CMA in long term GUP flow

by yangge1116＠126.com

From: yangge <yangge1116(a)126.com> Since commit 984fdba6a32e ("mm, compaction: use proper alloc_flags in __compaction_suitable()") allow compaction to proceed when free pages required for compaction reside in the CMA pageblocks, it's possible that __compaction_suitable() always returns true, and in some cases, it's not acceptable. There are 4 NUMA nodes on my machine, and each NUMA node has 32GB of memory. I have configured 16GB of CMA memory on each NUMA node, and starting a 32GB virtual machine with device passthrough is extremely slow, taking almost an hour. During the start-up of the virtual machine, it will call pin_user_pages_remote(..., FOLL_LONGTERM, ...) to allocate memory. Long term GUP cannot allocate memory from CMA area, so a maximum of 16 GB of no-CMA memory on a NUMA node can be used as virtual machine memory. Since there is 16G of free CMA memory on the NUMA node, watermark for order-0 always be met for compaction, so __compaction_suitable() always returns true, even if the node is unable to allocate non-CMA memory for the virtual machine. For costly allocations, because __compaction_suitable() always returns true, __alloc_pages_slowpath() can't exit at the appropriate place, resulting in excessively long virtual machine startup times. Call trace: __alloc_pages_slowpath if (compact_result == COMPACT_SKIPPED || compact_result == COMPACT_DEFERRED) goto nopage; // should exit __alloc_pages_slowpath() from here In order to quickly fall back to remote node, we should remove ALLOC_CMA both in __compaction_suitable() and __isolate_free_page() in long term GUP flow. After this fix, starting a 32GB virtual machine with device passthrough takes only a few seconds. Fixes: 984fdba6a32e ("mm, compaction: use proper alloc_flags in __compaction_suitable()") Cc: <stable(a)vger.kernel.org> Signed-off-by: yangge <yangge1116(a)126.com> --- V2: - using the 'cc->alloc_flags' to determin if 'ALLOC_CMA' is needed - rich the commit log description include/linux/compaction.h | 3 ++- mm/compaction.c | 18 +++++++++++------- mm/page_alloc.c | 4 +++- mm/vmscan.c | 4 ++-- 4 files changed, 18 insertions(+), 11 deletions(-) diff --git a/include/linux/compaction.h b/include/linux/compaction.h index e947764..0c6f97a 100644 --- a/include/linux/compaction.h +++ b/include/linux/compaction.h @@ -90,7 +90,8 @@ extern enum compact_result try_to_compact_pages(gfp_t gfp_mask, struct page **page); extern void reset_isolation_suitable(pg_data_t *pgdat); extern bool compaction_suitable(struct zone *zone, int order, - int highest_zoneidx); + int highest_zoneidx, + unsigned int alloc_flags); extern void compaction_defer_reset(struct zone *zone, int order, bool alloc_success); diff --git a/mm/compaction.c b/mm/compaction.c index 07bd227..585f5ab 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -2381,9 +2381,11 @@ static enum compact_result compact_finished(struct compact_control *cc) static bool __compaction_suitable(struct zone *zone, int order, int highest_zoneidx, + unsigned int alloc_flags, unsigned long wmark_target) { unsigned long watermark; + bool use_cma; /* * Watermarks for order-0 must be met for compaction to be able to * isolate free pages for migration targets. This means that the @@ -2395,25 +2397,27 @@ static bool __compaction_suitable(struct zone *zone, int order, * even if compaction succeeds. * For costly orders, we require low watermark instead of min for * compaction to proceed to increase its chances. - * ALLOC_CMA is used, as pages in CMA pageblocks are considered - * suitable migration targets + * In addition to long term GUP flow, ALLOC_CMA is used, as pages in + * CMA pageblocks are considered suitable migration targets */ watermark = (order > PAGE_ALLOC_COSTLY_ORDER) ? low_wmark_pages(zone) : min_wmark_pages(zone); watermark += compact_gap(order); + use_cma = !!(alloc_flags & ALLOC_CMA); return __zone_watermark_ok(zone, 0, watermark, highest_zoneidx, - ALLOC_CMA, wmark_target); + use_cma ? ALLOC_CMA : 0, wmark_target); } /* * compaction_suitable: Is this suitable to run compaction on this zone now? */ -bool compaction_suitable(struct zone *zone, int order, int highest_zoneidx) +bool compaction_suitable(struct zone *zone, int order, int highest_zoneidx, + unsigned int alloc_flags) { enum compact_result compact_result; bool suitable; - suitable = __compaction_suitable(zone, order, highest_zoneidx, + suitable = __compaction_suitable(zone, order, highest_zoneidx, alloc_flags, zone_page_state(zone, NR_FREE_PAGES)); /* * fragmentation index determines if allocation failures are due to @@ -2474,7 +2478,7 @@ bool compaction_zonelist_suitable(struct alloc_context *ac, int order, available = zone_reclaimable_pages(zone) / order; available += zone_page_state_snapshot(zone, NR_FREE_PAGES); if (__compaction_suitable(zone, order, ac->highest_zoneidx, - available)) + alloc_flags, available)) return true; } @@ -2499,7 +2503,7 @@ compaction_suit_allocation_order(struct zone *zone, unsigned int order, alloc_flags)) return COMPACT_SUCCESS; - if (!compaction_suitable(zone, order, highest_zoneidx)) + if (!compaction_suitable(zone, order, highest_zoneidx, alloc_flags)) return COMPACT_SKIPPED; return COMPACT_CONTINUE; diff --git a/mm/page_alloc.c b/mm/page_alloc.c index dde19db..9a5dfda 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -2813,6 +2813,7 @@ int __isolate_free_page(struct page *page, unsigned int order) { struct zone *zone = page_zone(page); int mt = get_pageblock_migratetype(page); + bool pin; if (!is_migrate_isolate(mt)) { unsigned long watermark; @@ -2823,7 +2824,8 @@ int __isolate_free_page(struct page *page, unsigned int order) * exists. */ watermark = zone->_watermark[WMARK_MIN] + (1UL << order); - if (!zone_watermark_ok(zone, 0, watermark, 0, ALLOC_CMA)) + pin = !!(current->flags & PF_MEMALLOC_PIN); + if (!zone_watermark_ok(zone, 0, watermark, 0, pin ? 0 : ALLOC_CMA)) return 0; } diff --git a/mm/vmscan.c b/mm/vmscan.c index 5e03a61..806f031 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -5815,7 +5815,7 @@ static inline bool should_continue_reclaim(struct pglist_data *pgdat, sc->reclaim_idx, 0)) return false; - if (compaction_suitable(zone, sc->order, sc->reclaim_idx)) + if (compaction_suitable(zone, sc->order, sc->reclaim_idx, 0)) return false; } @@ -6043,7 +6043,7 @@ static inline bool compaction_ready(struct zone *zone, struct scan_control *sc) return true; /* Compaction cannot yet proceed. Do reclaim. */ - if (!compaction_suitable(zone, sc->order, sc->reclaim_idx)) + if (!compaction_suitable(zone, sc->order, sc->reclaim_idx, 0)) return false; /* -- 2.7.4

4 months, 2 weeks

2
2
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror December 2024