Linux-stable-mirror

linux-stable-mirror@lists.linaro.org

287 participants
124115 discussions

[PATCH 1/2] mm: page_alloc: speed up fallbacks in rmqueue_bulk()

by Johannes Weiner

The test robot identified c2f6ea38fc1b ("mm: page_alloc: don't steal single pages from biggest buddy") as the root cause of a 56.4% regression in vm-scalability::lru-file-mmap-read. Carlos reports an earlier patch, c0cd6f557b90 ("mm: page_alloc: fix freelist movement during block conversion"), as the root cause for a regression in worst-case zone->lock+irqoff hold times. Both of these patches modify the page allocator's fallback path to be less greedy in an effort to stave off fragmentation. The flip side of this is that fallbacks are also less productive each time around, which means the fallback search can run much more frequently. Carlos' traces point to rmqueue_bulk() specifically, which tries to refill the percpu cache by allocating a large batch of pages in a loop. It highlights how once the native freelists are exhausted, the fallback code first scans orders top-down for whole blocks to claim, then falls back to a bottom-up search for the smallest buddy to steal. For the next batch page, it goes through the same thing again. This can be made more efficient. Since rmqueue_bulk() holds the zone->lock over the entire batch, the freelists are not subject to outside changes; when the search for a block to claim has already failed, there is no point in trying again for the next page. Modify __rmqueue() to remember the last successful fallback mode, and restart directly from there on the next rmqueue_bulk() iteration. Oliver confirms that this improves beyond the regression that the test robot reported against c2f6ea38fc1b: commit: f3b92176f4 ("tools/selftests: add guard region test for /proc/$pid/pagemap") c2f6ea38fc ("mm: page_alloc: don't steal single pages from biggest buddy") acc4d5ff0b ("Merge tag 'net-6.15-rc0' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net") 2c847f27c3 ("mm: page_alloc: speed up fallbacks in rmqueue_bulk()") <--- your patch f3b92176f4f7100f c2f6ea38fc1b640aa7a2e155cc1 acc4d5ff0b61eb1715c498b6536 2c847f27c37da65a93d23c237c5 ---------------- --------------------------- --------------------------- --------------------------- %stddev %change %stddev %change %stddev %change %stddev \ | \ | \ | \ 25525364 ± 3% -56.4% 11135467 -57.8% 10779336 +31.6% 33581409 vm-scalability.throughput Carlos confirms that worst-case times are almost fully recovered compared to before the earlier culprit patch: 2dd482ba627d (before freelist hygiene): 1ms c0cd6f557b90 (after freelist hygiene): 90ms next-20250319 (steal smallest buddy): 280ms this patch : 8ms Reported-by: kernel test robot <oliver.sang(a)intel.com> Reported-by: Carlos Song <carlos.song(a)nxp.com> Tested-by: kernel test robot <oliver.sang(a)intel.com> Fixes: c0cd6f557b90 ("mm: page_alloc: fix freelist movement during block conversion") Fixes: c2f6ea38fc1b ("mm: page_alloc: don't steal single pages from biggest buddy") Closes: https://lore.kernel.org/oe-lkp/202503271547.fc08b188-lkp@intel.com Cc: stable(a)vger.kernel.org # 6.10+ Signed-off-by: Johannes Weiner <hannes(a)cmpxchg.org> --- mm/page_alloc.c | 100 +++++++++++++++++++++++++++++++++++------------- 1 file changed, 74 insertions(+), 26 deletions(-) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index f51aa6051a99..03b0d45ed45a 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -2194,11 +2194,11 @@ try_to_claim_block(struct zone *zone, struct page *page, * The use of signed ints for order and current_order is a deliberate * deviation from the rest of this file, to make the for loop * condition simpler. - * - * Return the stolen page, or NULL if none can be found. */ + +/* Try to claim a whole foreign block, take a page, expand the remainder */ static __always_inline struct page * -__rmqueue_fallback(struct zone *zone, int order, int start_migratetype, +__rmqueue_claim(struct zone *zone, int order, int start_migratetype, unsigned int alloc_flags) { struct free_area *area; @@ -2236,14 +2236,26 @@ __rmqueue_fallback(struct zone *zone, int order, int start_migratetype, page = try_to_claim_block(zone, page, current_order, order, start_migratetype, fallback_mt, alloc_flags); - if (page) - goto got_one; + if (page) { + trace_mm_page_alloc_extfrag(page, order, current_order, + start_migratetype, fallback_mt); + return page; + } } - if (alloc_flags & ALLOC_NOFRAGMENT) - return NULL; + return NULL; +} + +/* Try to steal a single page from a foreign block */ +static __always_inline struct page * +__rmqueue_steal(struct zone *zone, int order, int start_migratetype) +{ + struct free_area *area; + int current_order; + struct page *page; + int fallback_mt; + bool claim_block; - /* No luck claiming pageblock. Find the smallest fallback page */ for (current_order = order; current_order < NR_PAGE_ORDERS; current_order++) { area = &(zone->free_area[current_order]); fallback_mt = find_suitable_fallback(area, current_order, @@ -2253,25 +2265,28 @@ __rmqueue_fallback(struct zone *zone, int order, int start_migratetype, page = get_page_from_free_area(area, fallback_mt); page_del_and_expand(zone, page, order, current_order, fallback_mt); - goto got_one; + trace_mm_page_alloc_extfrag(page, order, current_order, + start_migratetype, fallback_mt); + return page; } return NULL; - -got_one: - trace_mm_page_alloc_extfrag(page, order, current_order, - start_migratetype, fallback_mt); - - return page; } +enum rmqueue_mode { + RMQUEUE_NORMAL, + RMQUEUE_CMA, + RMQUEUE_CLAIM, + RMQUEUE_STEAL, +}; + /* * Do the hard work of removing an element from the buddy allocator. * Call me with the zone->lock already held. */ static __always_inline struct page * __rmqueue(struct zone *zone, unsigned int order, int migratetype, - unsigned int alloc_flags) + unsigned int alloc_flags, enum rmqueue_mode *mode) { struct page *page; @@ -2290,16 +2305,47 @@ __rmqueue(struct zone *zone, unsigned int order, int migratetype, } } - page = __rmqueue_smallest(zone, order, migratetype); - if (unlikely(!page)) { - if (alloc_flags & ALLOC_CMA) + /* + * Try the different freelists, native then foreign. + * + * The fallback logic is expensive and rmqueue_bulk() calls in + * a loop with the zone->lock held, meaning the freelists are + * not subject to any outside changes. Remember in *mode where + * we found pay dirt, to save us the search on the next call. + */ + switch (*mode) { + case RMQUEUE_NORMAL: + page = __rmqueue_smallest(zone, order, migratetype); + if (page) + return page; + fallthrough; + case RMQUEUE_CMA: + if (alloc_flags & ALLOC_CMA) { page = __rmqueue_cma_fallback(zone, order); - - if (!page) - page = __rmqueue_fallback(zone, order, migratetype, - alloc_flags); + if (page) { + *mode = RMQUEUE_CMA; + return page; + } + } + fallthrough; + case RMQUEUE_CLAIM: + page = __rmqueue_claim(zone, order, migratetype, alloc_flags); + if (page) { + /* Replenished native freelist, back to normal mode */ + *mode = RMQUEUE_NORMAL; + return page; + } + fallthrough; + case RMQUEUE_STEAL: + if (!(alloc_flags & ALLOC_NOFRAGMENT)) { + page = __rmqueue_steal(zone, order, migratetype); + if (page) { + *mode = RMQUEUE_STEAL; + return page; + } + } } - return page; + return NULL; } /* @@ -2311,6 +2357,7 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order, unsigned long count, struct list_head *list, int migratetype, unsigned int alloc_flags) { + enum rmqueue_mode rmqm = RMQUEUE_NORMAL; unsigned long flags; int i; @@ -2321,7 +2368,7 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order, } for (i = 0; i < count; ++i) { struct page *page = __rmqueue(zone, order, migratetype, - alloc_flags); + alloc_flags, &rmqm); if (unlikely(page == NULL)) break; @@ -2934,6 +2981,7 @@ struct page *rmqueue_buddy(struct zone *preferred_zone, struct zone *zone, { struct page *page; unsigned long flags; + enum rmqueue_mode rmqm = RMQUEUE_NORMAL; do { page = NULL; @@ -2945,7 +2993,7 @@ struct page *rmqueue_buddy(struct zone *preferred_zone, struct zone *zone, if (alloc_flags & ALLOC_HIGHATOMIC) page = __rmqueue_smallest(zone, order, MIGRATE_HIGHATOMIC); if (!page) { - page = __rmqueue(zone, order, migratetype, alloc_flags); + page = __rmqueue(zone, order, migratetype, alloc_flags, &rmqm); /* * If the allocation fails, allow OOM handling and -- 2.49.0

9 months

[PATCH V4] mm/gup: Clear the LRU flag of a page before adding to LRU batch

by yangge1116＠126.com

From: yangge <yangge1116(a)126.com> If a large number of CMA memory are configured in system (for example, the CMA memory accounts for 50% of the system memory), starting a virtual virtual machine with device passthrough, it will call pin_user_pages_remote(..., FOLL_LONGTERM, ...) to pin memory. Normally if a page is present and in CMA area, pin_user_pages_remote() will migrate the page from CMA area to non-CMA area because of FOLL_LONGTERM flag. But the current code will cause the migration failure due to unexpected page refcounts, and eventually cause the virtual machine fail to start. If a page is added in LRU batch, its refcount increases one, remove the page from LRU batch decreases one. Page migration requires the page is not referenced by others except page mapping. Before migrating a page, we should try to drain the page from LRU batch in case the page is in it, however, folio_test_lru() is not sufficient to tell whether the page is in LRU batch or not, if the page is in LRU batch, the migration will fail. To solve the problem above, we modify the logic of adding to LRU batch. Before adding a page to LRU batch, we clear the LRU flag of the page so that we can check whether the page is in LRU batch by folio_test_lru(page). It's quite valuable, because likely we don't want to blindly drain the LRU batch simply because there is some unexpected reference on a page, as described above. This change makes the LRU flag of a page invisible for longer, which may impact some programs. For example, as long as a page is on a LRU batch, we cannot isolate it, and we cannot check if it's an LRU page. Further, a page can now only be on exactly one LRU batch. This doesn't seem to matter much, because a new page is allocated from buddy and added to the lru batch, or be isolated, it's LRU flag may also be invisible for a long time. Fixes: 9a4e9f3b2d73 ("mm: update get_user_pages_longterm to migrate pages allocated from CMA region") Cc: <stable(a)vger.kernel.org> Signed-off-by: yangge <yangge1116(a)126.com> --- mm/swap.c | 43 +++++++++++++++++++++++++++++++------------ 1 file changed, 31 insertions(+), 12 deletions(-) V4: Adjust commit message according to David's comments V3: Add fixes tag V2: Adjust code and commit message according to David's comments diff --git a/mm/swap.c b/mm/swap.c index dc205bd..9caf6b0 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -211,10 +211,6 @@ static void folio_batch_move_lru(struct folio_batch *fbatch, move_fn_t move_fn) for (i = 0; i < folio_batch_count(fbatch); i++) { struct folio *folio = fbatch->folios[i]; - /* block memcg migration while the folio moves between lru */ - if (move_fn != lru_add_fn && !folio_test_clear_lru(folio)) - continue; - folio_lruvec_relock_irqsave(folio, &lruvec, &flags); move_fn(lruvec, folio); @@ -255,11 +251,16 @@ static void lru_move_tail_fn(struct lruvec *lruvec, struct folio *folio) void folio_rotate_reclaimable(struct folio *folio) { if (!folio_test_locked(folio) && !folio_test_dirty(folio) && - !folio_test_unevictable(folio) && folio_test_lru(folio)) { + !folio_test_unevictable(folio)) { struct folio_batch *fbatch; unsigned long flags; folio_get(folio); + if (!folio_test_clear_lru(folio)) { + folio_put(folio); + return; + } + local_lock_irqsave(&lru_rotate.lock, flags); fbatch = this_cpu_ptr(&lru_rotate.fbatch); folio_batch_add_and_move(fbatch, folio, lru_move_tail_fn); @@ -352,11 +353,15 @@ static void folio_activate_drain(int cpu) void folio_activate(struct folio *folio) { - if (folio_test_lru(folio) && !folio_test_active(folio) && - !folio_test_unevictable(folio)) { + if (!folio_test_active(folio) && !folio_test_unevictable(folio)) { struct folio_batch *fbatch; folio_get(folio); + if (!folio_test_clear_lru(folio)) { + folio_put(folio); + return; + } + local_lock(&cpu_fbatches.lock); fbatch = this_cpu_ptr(&cpu_fbatches.activate); folio_batch_add_and_move(fbatch, folio, folio_activate_fn); @@ -700,6 +705,11 @@ void deactivate_file_folio(struct folio *folio) return; folio_get(folio); + if (!folio_test_clear_lru(folio)) { + folio_put(folio); + return; + } + local_lock(&cpu_fbatches.lock); fbatch = this_cpu_ptr(&cpu_fbatches.lru_deactivate_file); folio_batch_add_and_move(fbatch, folio, lru_deactivate_file_fn); @@ -716,11 +726,16 @@ void deactivate_file_folio(struct folio *folio) */ void folio_deactivate(struct folio *folio) { - if (folio_test_lru(folio) && !folio_test_unevictable(folio) && - (folio_test_active(folio) || lru_gen_enabled())) { + if (!folio_test_unevictable(folio) && (folio_test_active(folio) || + lru_gen_enabled())) { struct folio_batch *fbatch; folio_get(folio); + if (!folio_test_clear_lru(folio)) { + folio_put(folio); + return; + } + local_lock(&cpu_fbatches.lock); fbatch = this_cpu_ptr(&cpu_fbatches.lru_deactivate); folio_batch_add_and_move(fbatch, folio, lru_deactivate_fn); @@ -737,12 +752,16 @@ void folio_deactivate(struct folio *folio) */ void folio_mark_lazyfree(struct folio *folio) { - if (folio_test_lru(folio) && folio_test_anon(folio) && - folio_test_swapbacked(folio) && !folio_test_swapcache(folio) && - !folio_test_unevictable(folio)) { + if (folio_test_anon(folio) && folio_test_swapbacked(folio) && + !folio_test_swapcache(folio) && !folio_test_unevictable(folio)) { struct folio_batch *fbatch; folio_get(folio); + if (!folio_test_clear_lru(folio)) { + folio_put(folio); + return; + } + local_lock(&cpu_fbatches.lock); fbatch = this_cpu_ptr(&cpu_fbatches.lru_lazyfree); folio_batch_add_and_move(fbatch, folio, lru_lazyfree_fn); -- 2.7.4

9 months

RE: Re: [PATCH] pps: fix poll support

by Denis OSTERLAND-HEIM

Hi Rodolfo, Do you think that there is a chance that this patch make it in the current merge window? Regards Denis -----Original Message----- From: Rodolfo Giometti <giometti(a)enneenne.com> Sent: Monday, March 3, 2025 12:54 PM To: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>; Andrew Morton <akpm(a)linux-foundation.org> Cc: linux-kernel(a)vger.kernel.org; Denis OSTERLAND-HEIM <denis.osterland(a)diehl.com>; stable(a)vger.kernel.org Subject: [EXT] Re: [PATCH] pps: fix poll support [EXTERNAL EMAIL] On 03/03/25 09:02, Denis OSTERLAND-HEIM wrote: > [BUG] > A user space program that calls select/poll get always an immediate data > ready-to-read response. As a result the intended use to wait until next > data becomes ready does not work. > > User space snippet: > > struct pollfd pollfd = { > .fd = open("/dev/pps0", O_RDONLY), > .events = POLLIN|POLLERR, > .revents = 0 }; > while(1) { > poll(&pollfd, 1, 2000/*ms*/); // returns immediate, but should wait > if(revents & EPOLLIN) { // always true > struct pps_fdata fdata; > memset(&fdata, 0, sizeof(memdata)); > ioctl(PPS_FETCH, &fdata); // currently fetches data at max speed > } > } > > [CAUSE] > pps_cdev_poll() returns unconditionally EPOLLIN. > > [FIX] > Remember the last fetch event counter and compare this value in > pps_cdev_poll() with most recent event counter > and return 0 if they are equal. > > Signed-off-by: Denis OSTERLAND-HEIM <denis.osterland(a)diehl.com> > Co-developed-by: Rodolfo Giometti <giometti(a)enneenne.com> > Signed-off-by: Rodolfo Giometti <giometti(a)enneenne.com> Acked-by: Rodolfo Giometti <giometti(a)enneenne.com> If needed. :) > Fixes: eae9d2ba0cfc ("LinuxPPS: core support") > CC: stable(a)vger.linux.org # 5.4+ > --- > drivers/pps/pps.c | 11 +++++++++-- > include/linux/pps_kernel.h | 1 + > 2 files changed, 10 insertions(+), 2 deletions(-) > > diff --git a/drivers/pps/pps.c b/drivers/pps/pps.c > index 6a02245ea35f..9463232af8d2 100644 > --- a/drivers/pps/pps.c > +++ b/drivers/pps/pps.c > @@ -41,6 +41,9 @@ static __poll_t pps_cdev_poll(struct file *file, poll_table *wait) > > poll_wait(file, &pps->queue, wait); > > + if (pps->last_fetched_ev == pps->last_ev) > + return 0; > + > return EPOLLIN | EPOLLRDNORM; > } > > @@ -186,9 +189,11 @@ static long pps_cdev_ioctl(struct file *file, > if (err) > return err; > > - /* Return the fetched timestamp */ > + /* Return the fetched timestamp and save last fetched event */ > spin_lock_irq(&pps->lock); > > + pps->last_fetched_ev = pps->last_ev; > + > fdata.info.assert_sequence = pps->assert_sequence; > fdata.info.clear_sequence = pps->clear_sequence; > fdata.info.assert_tu = pps->assert_tu; > @@ -272,9 +277,11 @@ static long pps_cdev_compat_ioctl(struct file *file, > if (err) > return err; > > - /* Return the fetched timestamp */ > + /* Return the fetched timestamp and save last fetched event */ > spin_lock_irq(&pps->lock); > > + pps->last_fetched_ev = pps->last_ev; > + > compat.info.assert_sequence = pps->assert_sequence; > compat.info.clear_sequence = pps->clear_sequence; > compat.info.current_mode = pps->current_mode; > diff --git a/include/linux/pps_kernel.h b/include/linux/pps_kernel.h > index c7abce28ed29..aab0aebb529e 100644 > --- a/include/linux/pps_kernel.h > +++ b/include/linux/pps_kernel.h > @@ -52,6 +52,7 @@ struct pps_device { > int current_mode; /* PPS mode at event time */ > > unsigned int last_ev; /* last PPS event id */ > + unsigned int last_fetched_ev; /* last fetched PPS event id */ > wait_queue_head_t queue; /* PPS event queue */ > > unsigned int id; /* PPS source unique ID */ -- GNU/Linux Solutions e-mail: giometti(a)enneenne.com Linux Device Driver giometti(a)linux.it Embedded Systems phone: +39 349 2432127 UNIX programming

9 months

[PATCH 6.6 000/152] 6.6.79-rc1 review

by Greg Kroah-Hartman

This is the start of the stable review cycle for the 6.6.79 release. There are 152 patches in this series, all will be posted as a response to this one. If anyone has any issues with these being applied, please let me know. Responses should be made by Fri, 21 Feb 2025 08:25:11 +0000. Anything received after that time might be too late. The whole patch series can be found in one patch at: https://www.kernel.org/pub/linux/kernel/v6.x/stable-review/patch-6.6.79-rc1… or in the git tree and branch at: git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git linux-6.6.y and the diffstat can be found below. thanks, greg k-h ------------- Pseudo-Shortlog of commits: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Linux 6.6.79-rc1 Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Revert "vfio/platform: check the bounds of read/write syscalls" David Woodhouse <dwmw(a)amazon.co.uk> x86/i8253: Disable PIT timer 0 when not in use Michal Luczaj <mhal(a)rbox.co> vsock: Orphan socket after transport release Michal Luczaj <mhal(a)rbox.co> vsock: Keep the binding until socket destruction Pavel Begunkov <asml.silence(a)gmail.com> io_uring/kbuf: reallocate buf lists on upgrade Vicki Pfau <vi(a)endrift.com> HID: hid-steam: Don't use cancel_delayed_work_sync in IRQ context Ivan Kokshaysky <ink(a)unseen.parts> alpha: replace hardcoded stack offsets with autogenerated ones Zhaoyang Huang <zhaoyang.huang(a)unisoc.com> mm: gup: fix infinite loop within __get_longterm_locked Marc Zyngier <maz(a)kernel.org> arm64: Filter out SVE hwcaps when FEAT_SVE isn't implemented Yu Kuai <yukuai3(a)huawei.com> md/md-bitmap: move bitmap_{start, end}write to md upper layer Yu Kuai <yukuai3(a)huawei.com> md/raid5: implement pers->bitmap_sector() Yu Kuai <yukuai3(a)huawei.com> md: add a new callback pers->bitmap_sector() Yu Kuai <yukuai3(a)huawei.com> md/md-bitmap: remove the last parameter for bimtap_ops->endwrite() Yu Kuai <yukuai3(a)huawei.com> md/md-bitmap: factor behind write counters out from bitmap_{start/end}write() Benjamin Marzinski <bmarzins(a)redhat.com> md/raid5: recheck if reshape has finished with device_lock held Hangbin Liu <liuhangbin(a)gmail.com> selftests: rtnetlink: update netdevsim ipsec output format Hangbin Liu <liuhangbin(a)gmail.com> netdevsim: print human readable IP address Alex Hung <alex.hung(a)amd.com> drm/amd/display: Pass non-null to dcn20_validate_apply_pipe_split_flags Srinivasan Shanmugam <srinivasan.shanmugam(a)amd.com> drm/amd/display: Add null check for head_pipe in dcn201_acquire_free_pipe_for_layer Andrew Cooper <andrew.cooper3(a)citrix.com> x86/static-call: Remove early_boot_irqs_disabled check to fix Xen PVH dom0 Christian Gmeiner <cgmeiner(a)igalia.com> drm/v3d: Stop active perfmon if it is being destroyed Tomi Valkeinen <tomi.valkeinen+renesas(a)ideasonboard.com> drm/rcar-du: dsi: Fix PHY lock bit check Devarsh Thakkar <devarsht(a)ti.com> drm/tidss: Clear the interrupt status for interrupts being disabled Tomi Valkeinen <tomi.valkeinen(a)ideasonboard.com> drm/tidss: Fix issue in irq handling causing irq-flood issue Eric Dumazet <edumazet(a)google.com> ipv6: mcast: add RCU protection to mld_newpack() Eric Dumazet <edumazet(a)google.com> ipv6: mcast: extend RCU protection in igmp6_send() Eric Dumazet <edumazet(a)google.com> ndisc: extend RCU protection in ndisc_send_skb() Eric Dumazet <edumazet(a)google.com> openvswitch: use RCU protection in ovs_vport_cmd_fill_info() Eric Dumazet <edumazet(a)google.com> arp: use RCU protection in arp_xmit() Eric Dumazet <edumazet(a)google.com> neighbour: use RCU protection in __neigh_notify() Li Zetao <lizetao1(a)huawei.com> neighbour: delete redundant judgment statements Eric Dumazet <edumazet(a)google.com> ndisc: use RCU protection in ndisc_alloc_skb() Vicki Pfau <vi(a)endrift.com> HID: hid-steam: Move hidraw input (un)registering to work Vicki Pfau <vi(a)endrift.com> HID: hid-steam: Make sure rumble work is canceled on removal Max Maisel <mmm-1(a)posteo.net> HID: hid-steam: Add Deck IMU support Dan Carpenter <dan.carpenter(a)linaro.org> HID: hid-steam: Fix cleanup in probe() Dan Carpenter <dan.carpenter(a)linaro.org> HID: hid-steam: remove pointless error message Vicki Pfau <vi(a)endrift.com> HID: hid-steam: Add gamepad-only mode switched to by holding options Vicki Pfau <vi(a)endrift.com> HID: hid-steam: Update list of identifiers from SDL Vicki Pfau <vi(a)endrift.com> HID: hid-steam: Clean up locking Vicki Pfau <vi(a)endrift.com> HID: hid-steam: Disable watchdog instead of using a heartbeat Vicki Pfau <vi(a)endrift.com> HID: hid-steam: Avoid overwriting smoothing parameter Eric Dumazet <edumazet(a)google.com> ipv6: icmp: convert to dev_net_rcu() Eric Dumazet <edumazet(a)google.com> ipv6: use RCU protection in ip6_default_advmss() Eric Dumazet <edumazet(a)google.com> flow_dissector: use RCU protection to fetch dev_net() Eric Dumazet <edumazet(a)google.com> ipv4: icmp: convert to dev_net_rcu() Eric Dumazet <edumazet(a)google.com> ipv4: use RCU protection in __ip_rt_update_pmtu() Vladimir Vdovin <deliran(a)verdict.gg> net: ipv4: Cache pmtu for all packet paths if multipath enabled Eric Dumazet <edumazet(a)google.com> ipv4: use RCU protection in inet_select_addr() Eric Dumazet <edumazet(a)google.com> ipv4: use RCU protection in rt_is_expired() Eric Dumazet <edumazet(a)google.com> ipv4: use RCU protection in ipv4_default_advmss() Eric Dumazet <edumazet(a)google.com> net: add dev_net_rcu() helper Jiri Pirko <jiri(a)resnulli.us> net: treat possible_net_t net pointer as an RCU one and add read_pnet_rcu() Eric Dumazet <edumazet(a)google.com> ipv4: add RCU protection to ip4_dst_hoplimit() Waiman Long <longman(a)redhat.com> clocksource: Use migrate_disable() to avoid calling get_random_u32() in atomic context Waiman Long <longman(a)redhat.com> clocksource: Use pr_info() for "Checking clocksource synchronization" message Filipe Manana <fdmanana(a)suse.com> btrfs: fix hole expansion when writing at an offset beyond EOF Wentao Liang <vulab(a)iscas.ac.cn> mlxsw: Add return value check for mlxsw_sp_port_get_stats_raw() Song Yoong Siang <yoong.siang.song(a)intel.com> igc: Set buffer type for empty frames in igc_init_empty_frame Andy-ld Lu <andy-ld.lu(a)mediatek.com> mmc: mtk-sd: Fix register settings for hs400(es) mode Nathan Chancellor <nathan(a)kernel.org> arm64: Handle .ARM.attributes section in linker scripts Jiasheng Jiang <jiashengjiangcool(a)gmail.com> regmap-irq: Add missing kfree() Varadarajan Narayanan <quic_varada(a)quicinc.com> regulator: qcom_smd: Add l2, l5 sub-node to mp5496 regulator Jann Horn <jannh(a)google.com> partitions: mac: fix handling of bogus partition table Wentao Liang <vulab(a)iscas.ac.cn> gpio: stmpe: Check return value of stmpe_reg_read in stmpe_gpio_irq_sync_unlock Mario Limonciello <mario.limonciello(a)amd.com> gpiolib: acpi: Add a quirk for Acer Nitro ANV14 Ivan Kokshaysky <ink(a)unseen.parts> alpha: align stack for page fault and user unaligned trap handlers John Keeping <jkeeping(a)inmusicbrands.com> serial: 8250: Fix fifo underflow on flush Andy Shevchenko <andriy.shevchenko(a)linux.intel.com> serial: port: Always update ->iotype in __uart_read_properties() Andy Shevchenko <andriy.shevchenko(a)linux.intel.com> serial: port: Assign ->iotype correctly when ->iobase is set Shakeel Butt <shakeel.butt(a)linux.dev> cgroup: fix race between fork and cgroup.kill Ard Biesheuvel <ardb(a)kernel.org> efi: Avoid cold plugged memory for placing the kernel Thomas Weißschuh <thomas.weissschuh(a)linutronix.de> kbuild: userprogs: fix bitsize and target detection on clang Aditya Kumar Singh <aditya.kumar.singh(a)oss.qualcomm.com> wifi: ath12k: fix handling of 6 GHz rules Ivan Kokshaysky <ink(a)unseen.parts> alpha: make stack 16-byte aligned (most cases) Vincent Mailhol <mailhol.vincent(a)wanadoo.fr> can: etas_es58x: fix potential NULL pointer dereference on udev->serial Alexander Hölzl <alexander.hoelzl(a)gmx.net> can: j1939: j1939_sk_send_loop(): fix unable to send messages with data length zero Krzysztof Kozlowski <krzysztof.kozlowski(a)linaro.org> can: c_can: fix unbalanced runtime PM disable in error path Fedor Pchelkin <pchelkin(a)ispras.ru> can: ctucanfd: handle skb allocation failure Johan Hovold <johan(a)kernel.org> USB: serial: option: drop MeiG Smart defines Fabio Porcedda <fabio.porcedda(a)gmail.com> USB: serial: option: fix Telit Cinterion FN990A name Fabio Porcedda <fabio.porcedda(a)gmail.com> USB: serial: option: add Telit Cinterion FN990B compositions Chester A. Unal <chester.a.unal(a)arinc9.com> USB: serial: option: add MeiG Smart SLM828 Jann Horn <jannh(a)google.com> usb: cdc-acm: Fix handling of oversized fragments Jann Horn <jannh(a)google.com> usb: cdc-acm: Check control transfer buffer size before access Marek Vasut <marek.vasut+renesas(a)mailbox.org> USB: cdc-acm: Fill in Renesas R-Car D3 USB Download mode quirk Alan Stern <stern(a)rowland.harvard.edu> USB: hub: Ignore non-compliant devices with too many configs or interfaces John Keeping <jkeeping(a)inmusicbrands.com> usb: gadget: f_midi: fix MIDI Streaming descriptor lengths Mathias Nyman <mathias.nyman(a)linux.intel.com> USB: Add USB_QUIRK_NO_LPM quirk for sony xperia xz1 smartphone Lei Huang <huanglei(a)kylinos.cn> USB: quirks: add USB_QUIRK_NO_LPM quirk for Teclast dist Stefan Eichenberger <stefan.eichenberger(a)toradex.com> usb: core: fix pipe creation for get_bMaxPacketSize0 Huacai Chen <chenhuacai(a)kernel.org> USB: pci-quirks: Fix HCCPARAMS register error for LS7A EHCI Fabrice Gasnier <fabrice.gasnier(a)foss.st.com> usb: dwc2: gadget: remove of_node reference upon udc_stop Guo Ren <guoren(a)kernel.org> usb: gadget: udc: renesas_usb3: Fix compiler warning Elson Roy Serrao <quic_eserrao(a)quicinc.com> usb: roles: set switch registered flag early on Selvarasu Ganesan <selvarasu.g(a)samsung.com> usb: dwc3: Fix timeout issue during controller enter/exit from halt state Selvarasu Ganesan <selvarasu.g(a)samsung.com> usb: gadget: f_midi: Fixing wMaxPacketSize exceeded issue during MIDI bind retries Sean Christopherson <seanjc(a)google.com> perf/x86/intel: Ensure LBRs are disabled when a CPU is starting Sean Christopherson <seanjc(a)google.com> KVM: nSVM: Enter guest mode before initializing nested NPT MMU Sean Christopherson <seanjc(a)google.com> KVM: x86: Reject Hyper-V's SEND_IPI hypercalls if local APIC isn't in-kernel Jiang Liu <gerry(a)linux.alibaba.com> drm/amdgpu: avoid buffer overflow attach in smu_sys_set_pp_table() Sven Eckelmann <sven(a)narfation.org> batman-adv: Drop unmanaged ELP metric worker Sven Eckelmann <sven(a)narfation.org> batman-adv: Ignore neighbor throughput metrics in error case Andy Strohman <andrew(a)andrewstrohman.com> batman-adv: fix panic during interface removal Hans de Goede <hdegoede(a)redhat.com> ASoC: Intel: bytcr_rt5640: Add DMI quirk for Vexia Edu Atla 10 tablet 5V Mike Marshall <hubcap(a)omnibond.com> orangefs: fix a oob in orangefs_debug_write Rik van Riel <riel(a)fb.com> x86/mm/tlb: Only trim the mm_cpumask once a second Hans de Goede <hdegoede(a)redhat.com> ACPI: x86: Add skip i2c clients quirk for Vexia EDU ATLA 10 tablet 5V Koichiro Den <koichiro.den(a)canonical.com> selftests: gpio: gpio-sim: Fix missing chip disablements Maksym Planeta <maksym(a)exostellar.io> Grab mm lock before grabbing pt lock Zichen Xie <zichenxie0106(a)gmail.com> NFS: Fix potential buffer overflowin nfs_sysfs_link_rpc_client() Ramesh Thomas <ramesh.thomas(a)intel.com> vfio/pci: Enable iowrite64 and ioread64 for vfio pci Tomas Glozar <tglozar(a)redhat.com> rtla/timerlat_top: Abort event processing on second signal Tomas Glozar <tglozar(a)redhat.com> rtla/timerlat_hist: Abort event processing on second signal Guixin Liu <kanie(a)linux.alibaba.com> scsi: ufs: bsg: Set bsg_queue to NULL after removal Rakesh Babu Saladi <Saladi.Rakeshbabu(a)microchip.com> PCI: switchtec: Add Microchip PCI100X device IDs Takashi Iwai <tiwai(a)suse.de> PCI/DPC: Quirk PIO log size for Intel Raptor Lake-P Edward Adam Davis <eadavis(a)qq.com> media: vidtv: Fix a null-ptr-deref in vidtv_mux_stop_thread Isaac Scott <isaac.scott(a)ideasonboard.com> media: uvcvideo: Add Kurokesu C1 PRO camera Isaac Scott <isaac.scott(a)ideasonboard.com> media: uvcvideo: Add new quirk definition for the Sonix Technology Co. 292a camera Isaac Scott <isaac.scott(a)ideasonboard.com> media: uvcvideo: Implement dual stream quirk to fix loss of usb packets Tomi Valkeinen <tomi.valkeinen(a)ideasonboard.com> media: i2c: ds90ub953: Add error handling for i2c reads/writes Tomi Valkeinen <tomi.valkeinen(a)ideasonboard.com> media: i2c: ds90ub913: Add error handling to ub913_hw_init() Arnd Bergmann <arnd(a)arndb.de> media: cxd2841er: fix 64-bit division on gcc-9 Kartik Rajput <kkartik(a)nvidia.com> soc/tegra: fuse: Update Tegra234 nvmem keepout list Aaro Koskinen <aaro.koskinen(a)iki.fi> fbdev: omap: use threaded IRQ for LCD DMA Michael Margolin <mrgolin(a)amazon.com> RDMA/efa: Reset device on probe failure Masahiro Yamada <masahiroy(a)kernel.org> tools: fix annoying "mkdir -p ..." logs when building tools in parallel Andy Shevchenko <andriy.shevchenko(a)linux.intel.com> gpiolib: Fix crash on error in gpiochip_get_ngpios() Jens Axboe <axboe(a)kernel.dk> block: cleanup and fix batch completion adding conditions Juergen Gross <jgross(a)suse.com> x86/xen: allow larger contiguous memory regions in PV guests Juergen Gross <jgross(a)suse.com> xen/swiotlb: relax alignment requirements Jiang Liu <gerry(a)linux.alibaba.com> drm/amdgpu: bail out when failed to load fw in psp_init_cap_microcode() Artur Weber <aweber.kernel(a)gmail.com> gpio: bcm-kona: Add missing newline to dev_err format string Artur Weber <aweber.kernel(a)gmail.com> gpio: bcm-kona: Make sure GPIO bits are unlocked when requesting IRQ Artur Weber <aweber.kernel(a)gmail.com> gpio: bcm-kona: Fix GPIO lock/unlock for banks above bank 0 Krzysztof Karas <krzysztof.karas(a)intel.com> drm/i915/selftests: avoid using uninitialized context Muhammad Adeel <Muhammad.Adeel(a)ibm.com> cgroup: Remove steal time from usage_usec Radu Rendec <rrendec(a)redhat.com> arm64: cacheinfo: Avoid out-of-bounds write to cacheinfo array Eric Dumazet <edumazet(a)google.com> team: better TEAM_OPTION_TYPE_STRING validation Yuli Wang <wangyuli(a)uniontech.com> LoongArch: csum: Fix OoB access in IP checksum code for negative lengths Marco Crivellari <marco.crivellari(a)suse.com> LoongArch: Fix idle VS timer enqueue Eric Dumazet <edumazet(a)google.com> vxlan: check vxlan_vnigroup_init() return value Eric Dumazet <edumazet(a)google.com> vrf: use RCU protection in l3mdev_l3_out() Eric Dumazet <edumazet(a)google.com> ndisc: ndisc_send_redirect() must use dev_get_by_index_rcu() Murad Masimov <m.masimov(a)mt-integration.ru> ax25: Fix refcount leak caused by setting SO_BINDTODEVICE sockopt Kunihiko Hayashi <hayashi.kunihiko(a)socionext.com> spi: sn-f-ospi: Fix division by zero Tulio Fernandes <tuliomf09(a)gmail.com> HID: hid-thrustmaster: fix stack-out-of-bounds read in usb_check_int_endpoints() Charles Han <hanchunchao(a)inspur.com> HID: multitouch: Add NULL check in mt_input_configured Andy Shevchenko <andriy.shevchenko(a)linux.intel.com> pinctrl: cy8c95x0: Respect IRQ trigger settings from firmware Dai Ngo <dai.ngo(a)oracle.com> NFSD: fix hang in nfsd4_shutdown_callback Li Lingfeng <lilingfeng3(a)huawei.com> nfsd: clear acl_access/acl_default after releasing them ------------- Diffstat: Documentation/arch/arm64/elf_hwcaps.rst | 36 +- .../bindings/regulator/qcom,smd-rpm-regulator.yaml | 2 +- Makefile | 17 +- arch/alpha/include/uapi/asm/ptrace.h | 2 + arch/alpha/kernel/asm-offsets.c | 2 + arch/alpha/kernel/entry.S | 24 +- arch/alpha/kernel/traps.c | 2 +- arch/alpha/mm/fault.c | 4 +- arch/arm64/kernel/cacheinfo.c | 12 +- arch/arm64/kernel/cpufeature.c | 38 +- arch/arm64/kernel/vdso/vdso.lds.S | 1 + arch/arm64/kernel/vmlinux.lds.S | 1 + arch/loongarch/kernel/genex.S | 28 +- arch/loongarch/kernel/idle.c | 3 +- arch/loongarch/kernel/reset.c | 6 +- arch/loongarch/lib/csum.c | 2 +- arch/x86/events/intel/core.c | 5 +- arch/x86/include/asm/mmu.h | 2 + arch/x86/include/asm/mmu_context.h | 1 + arch/x86/include/asm/msr-index.h | 3 +- arch/x86/include/asm/tlbflush.h | 1 + arch/x86/kernel/i8253.c | 11 +- arch/x86/kernel/static_call.c | 1 - arch/x86/kvm/hyperv.c | 6 +- arch/x86/kvm/mmu/mmu.c | 2 +- arch/x86/kvm/svm/nested.c | 10 +- arch/x86/mm/tlb.c | 35 +- arch/x86/xen/mmu_pv.c | 75 ++- block/partitions/mac.c | 18 +- drivers/acpi/x86/utils.c | 13 + drivers/base/regmap/regmap-irq.c | 2 + drivers/clocksource/i8253.c | 13 +- drivers/firmware/efi/efi.c | 6 +- drivers/firmware/efi/libstub/randomalloc.c | 3 + drivers/firmware/efi/libstub/relocate.c | 3 + drivers/gpio/gpio-bcm-kona.c | 71 +- drivers/gpio/gpio-stmpe.c | 15 +- drivers/gpio/gpiolib-acpi.c | 14 + drivers/gpio/gpiolib.c | 6 +- drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c | 5 +- .../gpu/drm/amd/display/dc/dcn20/dcn20_resource.c | 3 +- .../drm/amd/display/dc/dcn201/dcn201_resource.c | 4 +- .../gpu/drm/amd/display/dc/dcn21/dcn21_resource.c | 3 +- drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c | 3 +- drivers/gpu/drm/i915/selftests/i915_gem_gtt.c | 4 +- drivers/gpu/drm/renesas/rcar-du/rcar_mipi_dsi.c | 2 +- .../gpu/drm/renesas/rcar-du/rcar_mipi_dsi_regs.h | 1 - drivers/gpu/drm/tidss/tidss_dispc.c | 22 +- drivers/gpu/drm/v3d/v3d_perfmon.c | 5 + drivers/hid/hid-multitouch.c | 5 +- drivers/hid/hid-steam.c | 738 ++++++++++++++++----- drivers/hid/hid-thrustmaster.c | 2 +- drivers/infiniband/hw/efa/efa_main.c | 9 +- drivers/md/md-bitmap.c | 75 ++- drivers/md/md-bitmap.h | 6 +- drivers/md/md.c | 26 + drivers/md/md.h | 5 + drivers/md/raid1.c | 35 +- drivers/md/raid1.h | 1 - drivers/md/raid10.c | 26 +- drivers/md/raid10.h | 1 - drivers/md/raid5-cache.c | 4 - drivers/md/raid5.c | 174 ++--- drivers/md/raid5.h | 4 - drivers/media/dvb-frontends/cxd2841er.c | 8 +- drivers/media/i2c/ds90ub913.c | 25 +- drivers/media/i2c/ds90ub953.c | 46 +- drivers/media/test-drivers/vidtv/vidtv_bridge.c | 8 +- drivers/media/usb/uvc/uvc_driver.c | 18 + drivers/media/usb/uvc/uvc_video.c | 27 +- drivers/media/usb/uvc/uvcvideo.h | 1 + drivers/mmc/host/mtk-sd.c | 31 +- drivers/net/can/c_can/c_can_platform.c | 5 +- drivers/net/can/ctucanfd/ctucanfd_base.c | 10 +- drivers/net/can/usb/etas_es58x/es58x_devlink.c | 6 +- drivers/net/ethernet/intel/igc/igc_main.c | 1 + .../net/ethernet/mellanox/mlxsw/spectrum_ethtool.c | 4 +- drivers/net/netdevsim/ipsec.c | 12 +- drivers/net/team/team.c | 4 +- drivers/net/vxlan/vxlan_core.c | 7 +- drivers/net/wireless/ath/ath12k/wmi.c | 61 +- drivers/net/wireless/ath/ath12k/wmi.h | 1 - drivers/pci/quirks.c | 12 + drivers/pci/switch/switchtec.c | 26 + drivers/pinctrl/pinctrl-cy8c95x0.c | 2 +- drivers/soc/tegra/fuse/fuse-tegra30.c | 17 +- drivers/spi/spi-sn-f-ospi.c | 3 + drivers/tty/serial/8250/8250.h | 2 + drivers/tty/serial/8250/8250_dma.c | 16 + drivers/tty/serial/8250/8250_port.c | 9 + drivers/tty/serial/serial_port.c | 5 +- drivers/ufs/core/ufs_bsg.c | 1 + drivers/usb/class/cdc-acm.c | 28 +- drivers/usb/core/hub.c | 14 +- drivers/usb/core/quirks.c | 6 + drivers/usb/dwc2/gadget.c | 1 + drivers/usb/dwc3/gadget.c | 34 + drivers/usb/gadget/function/f_midi.c | 17 +- drivers/usb/gadget/udc/renesas_usb3.c | 2 +- drivers/usb/host/pci-quirks.c | 9 + drivers/usb/roles/class.c | 5 +- drivers/usb/serial/option.c | 49 +- drivers/vfio/pci/vfio_pci_rdwr.c | 1 + drivers/vfio/platform/vfio_platform_common.c | 10 - drivers/video/fbdev/omap/lcd_dma.c | 4 +- drivers/xen/swiotlb-xen.c | 20 +- fs/btrfs/file.c | 4 +- fs/nfs/sysfs.c | 6 +- fs/nfsd/nfs2acl.c | 2 + fs/nfsd/nfs3acl.c | 2 + fs/nfsd/nfs4callback.c | 7 +- fs/orangefs/orangefs-debugfs.c | 4 +- include/linux/blk-mq.h | 18 +- include/linux/cgroup-defs.h | 6 +- include/linux/efi.h | 1 + include/linux/i8253.h | 1 + include/linux/netdevice.h | 6 + include/linux/sched/task.h | 1 + include/net/l3mdev.h | 2 + include/net/net_namespace.h | 15 +- include/net/route.h | 9 +- io_uring/kbuf.c | 15 +- kernel/cgroup/cgroup.c | 20 +- kernel/cgroup/rstat.c | 1 - kernel/time/clocksource.c | 9 +- mm/gup.c | 14 +- net/ax25/af_ax25.c | 11 + net/batman-adv/bat_v.c | 2 - net/batman-adv/bat_v_elp.c | 122 +++- net/batman-adv/bat_v_elp.h | 2 - net/batman-adv/types.h | 3 - net/can/j1939/socket.c | 4 +- net/can/j1939/transport.c | 5 +- net/core/flow_dissector.c | 21 +- net/core/neighbour.c | 11 +- net/ipv4/arp.c | 4 +- net/ipv4/devinet.c | 3 +- net/ipv4/icmp.c | 31 +- net/ipv4/route.c | 39 +- net/ipv6/icmp.c | 42 +- net/ipv6/mcast.c | 45 +- net/ipv6/ndisc.c | 28 +- net/ipv6/route.c | 7 +- net/openvswitch/datapath.c | 12 +- net/vmw_vsock/af_vsock.c | 12 +- sound/soc/intel/boards/bytcr_rt5640.c | 17 +- tools/testing/selftests/gpio/gpio-sim.sh | 31 +- tools/testing/selftests/net/pmtu.sh | 112 +++- tools/testing/selftests/net/rtnetlink.sh | 4 +- tools/tracing/rtla/src/timerlat_hist.c | 8 + tools/tracing/rtla/src/timerlat_top.c | 8 + 151 files changed, 2108 insertions(+), 846 deletions(-)

9 months

[PATCH v5 2/5] ASoC: q6apm: add q6apm_get_hw_pointer helper

by srinivas.kandagatla＠linaro.org

From: Srinivas Kandagatla <srinivas.kandagatla(a)linaro.org> Implement an helper function in q6apm to be able to read the current hardware pointer for both read and write buffers. This should help q6apm-dai to get the hardware pointer consistently without it doing manual calculation, which could go wrong in some race conditions. Fixes: 9b4fe0f1cd79 ("ASoC: qdsp6: audioreach: add q6apm-dai support") Cc: stable(a)vger.kernel.org Signed-off-by: Srinivas Kandagatla <srinivas.kandagatla(a)linaro.org> Tested-by: Krzysztof Kozlowski <krzysztof.kozlowski(a)linaro.org> Tested-by: Johan Hovold <johan+linaro(a)kernel.org> --- sound/soc/qcom/qdsp6/q6apm.c | 18 +++++++++++++++++- sound/soc/qcom/qdsp6/q6apm.h | 3 +++ 2 files changed, 20 insertions(+), 1 deletion(-) diff --git a/sound/soc/qcom/qdsp6/q6apm.c b/sound/soc/qcom/qdsp6/q6apm.c index 2a2a5bd98110..ca57413cb784 100644 --- a/sound/soc/qcom/qdsp6/q6apm.c +++ b/sound/soc/qcom/qdsp6/q6apm.c @@ -494,6 +494,19 @@ int q6apm_read(struct q6apm_graph *graph) } EXPORT_SYMBOL_GPL(q6apm_read); +int q6apm_get_hw_pointer(struct q6apm_graph *graph, int dir) +{ + struct audioreach_graph_data *data; + + if (dir == SNDRV_PCM_STREAM_PLAYBACK) + data = &graph->rx_data; + else + data = &graph->tx_data; + + return (int)atomic_read(&data->hw_ptr); +} +EXPORT_SYMBOL_GPL(q6apm_get_hw_pointer); + static int graph_callback(struct gpr_resp_pkt *data, void *priv, int op) { struct data_cmd_rsp_rd_sh_mem_ep_data_buffer_done_v2 *rd_done; @@ -520,7 +533,8 @@ static int graph_callback(struct gpr_resp_pkt *data, void *priv, int op) done = data->payload; phys = graph->rx_data.buf[token].phys; mutex_unlock(&graph->lock); - + /* token numbering starts at 0 */ + atomic_set(&graph->rx_data.hw_ptr, token + 1); if (lower_32_bits(phys) == done->buf_addr_lsw && upper_32_bits(phys) == done->buf_addr_msw) { graph->result.opcode = hdr->opcode; @@ -553,6 +567,8 @@ static int graph_callback(struct gpr_resp_pkt *data, void *priv, int op) rd_done = data->payload; phys = graph->tx_data.buf[hdr->token].phys; mutex_unlock(&graph->lock); + /* token numbering starts at 0 */ + atomic_set(&graph->tx_data.hw_ptr, hdr->token + 1); if (upper_32_bits(phys) == rd_done->buf_addr_msw && lower_32_bits(phys) == rd_done->buf_addr_lsw) { diff --git a/sound/soc/qcom/qdsp6/q6apm.h b/sound/soc/qcom/qdsp6/q6apm.h index c248c8d2b1ab..7ce08b401e31 100644 --- a/sound/soc/qcom/qdsp6/q6apm.h +++ b/sound/soc/qcom/qdsp6/q6apm.h @@ -2,6 +2,7 @@ #ifndef __Q6APM_H__ #define __Q6APM_H__ #include <linux/types.h> +#include <linux/atomic.h> #include <linux/slab.h> #include <linux/wait.h> #include <linux/kernel.h> @@ -77,6 +78,7 @@ struct audioreach_graph_data { uint32_t num_periods; uint32_t dsp_buf; uint32_t mem_map_handle; + atomic_t hw_ptr; }; struct audioreach_graph { @@ -150,4 +152,5 @@ int q6apm_enable_compress_module(struct device *dev, struct q6apm_graph *graph, int q6apm_remove_initial_silence(struct device *dev, struct q6apm_graph *graph, uint32_t samples); int q6apm_remove_trailing_silence(struct device *dev, struct q6apm_graph *graph, uint32_t samples); int q6apm_set_real_module_id(struct device *dev, struct q6apm_graph *graph, uint32_t codec_id); +int q6apm_get_hw_pointer(struct q6apm_graph *graph, int dir); #endif /* __APM_GRAPH_ */ -- 2.39.5

9 months

[PATCH 2/2] usb: typec: ucsi: displayport: Fix NULL pointer access

by Andrei Kuchynski

This patch ensures that the UCSI driver waits for all pending tasks in the ucsi_displayport_work workqueue to finish executing before proceeding with the partner removal. Cc: stable(a)vger.kernel.org Fixes: af8622f6a585 ("usb: typec: ucsi: Support for DisplayPort alt mode") Signed-off-by: Andrei Kuchynski <akuchynski(a)chromium.org> --- drivers/usb/typec/ucsi/displayport.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/usb/typec/ucsi/displayport.c b/drivers/usb/typec/ucsi/displayport.c index acd053d4e38c..8aae80b457d7 100644 --- a/drivers/usb/typec/ucsi/displayport.c +++ b/drivers/usb/typec/ucsi/displayport.c @@ -299,6 +299,8 @@ void ucsi_displayport_remove_partner(struct typec_altmode *alt) if (!dp) return; + cancel_work_sync(&dp->work); + dp->data.conf = 0; dp->data.status = 0; dp->initialized = false; -- 2.49.0.504.g3bcea36a83-goog

9 months

[PATCH 1/2] usb: typec: ucsi: displayport: Fix deadlock

by Andrei Kuchynski

This patch introduces the ucsi_con_mutex_lock / ucsi_con_mutex_unlock functions to the UCSI driver. ucsi_con_mutex_lock ensures the connector mutex is only locked if a connection is established and the partner pointer is valid. This resolves a deadlock scenario where ucsi_displayport_remove_partner holds con->mutex waiting for dp_altmode_work to complete while dp_altmode_work attempts to acquire it. Cc: stable(a)vger.kernel.org Fixes: af8622f6a585 ("usb: typec: ucsi: Support for DisplayPort alt mode") Signed-off-by: Andrei Kuchynski <akuchynski(a)chromium.org> --- drivers/usb/typec/ucsi/displayport.c | 19 ++++++++------- drivers/usb/typec/ucsi/ucsi.c | 36 ++++++++++++++++++++++++++++ drivers/usb/typec/ucsi/ucsi.h | 2 ++ 3 files changed, 49 insertions(+), 8 deletions(-) diff --git a/drivers/usb/typec/ucsi/displayport.c b/drivers/usb/typec/ucsi/displayport.c index 420af5139c70..acd053d4e38c 100644 --- a/drivers/usb/typec/ucsi/displayport.c +++ b/drivers/usb/typec/ucsi/displayport.c @@ -54,7 +54,8 @@ static int ucsi_displayport_enter(struct typec_altmode *alt, u32 *vdo) u8 cur = 0; int ret; - mutex_lock(&dp->con->lock); + if (!ucsi_con_mutex_lock(dp->con)) + return -ENOTCONN; if (!dp->override && dp->initialized) { const struct typec_altmode *p = typec_altmode_get_partner(alt); @@ -100,7 +101,7 @@ static int ucsi_displayport_enter(struct typec_altmode *alt, u32 *vdo) schedule_work(&dp->work); ret = 0; err_unlock: - mutex_unlock(&dp->con->lock); + ucsi_con_mutex_unlock(dp->con); return ret; } @@ -112,7 +113,8 @@ static int ucsi_displayport_exit(struct typec_altmode *alt) u64 command; int ret = 0; - mutex_lock(&dp->con->lock); + if (!ucsi_con_mutex_lock(dp->con)) + return -ENOTCONN; if (!dp->override) { const struct typec_altmode *p = typec_altmode_get_partner(alt); @@ -144,7 +146,7 @@ static int ucsi_displayport_exit(struct typec_altmode *alt) schedule_work(&dp->work); out_unlock: - mutex_unlock(&dp->con->lock); + ucsi_con_mutex_unlock(dp->con); return ret; } @@ -202,20 +204,21 @@ static int ucsi_displayport_vdm(struct typec_altmode *alt, int cmd = PD_VDO_CMD(header); int svdm_version; - mutex_lock(&dp->con->lock); + if (!ucsi_con_mutex_lock(dp->con)) + return -ENOTCONN; if (!dp->override && dp->initialized) { const struct typec_altmode *p = typec_altmode_get_partner(alt); dev_warn(&p->dev, "firmware doesn't support alternate mode overriding\n"); - mutex_unlock(&dp->con->lock); + ucsi_con_mutex_unlock(dp->con); return -EOPNOTSUPP; } svdm_version = typec_altmode_get_svdm_version(alt); if (svdm_version < 0) { - mutex_unlock(&dp->con->lock); + ucsi_con_mutex_unlock(dp->con); return svdm_version; } @@ -259,7 +262,7 @@ static int ucsi_displayport_vdm(struct typec_altmode *alt, break; } - mutex_unlock(&dp->con->lock); + ucsi_con_mutex_unlock(dp->con); return 0; } diff --git a/drivers/usb/typec/ucsi/ucsi.c b/drivers/usb/typec/ucsi/ucsi.c index e8c7e9dc4930..ef867136e51d 100644 --- a/drivers/usb/typec/ucsi/ucsi.c +++ b/drivers/usb/typec/ucsi/ucsi.c @@ -1922,6 +1922,42 @@ void ucsi_set_drvdata(struct ucsi *ucsi, void *data) } EXPORT_SYMBOL_GPL(ucsi_set_drvdata); +/** + * ucsi_con_mutex_lock - Acquire the connector mutex + * @con: The connector interface to lock + * + * Returns true on success, false if the connector is disconnected + */ +bool ucsi_con_mutex_lock(struct ucsi_connector *con) +{ + bool mutex_locked = false; + bool connected = true; + + while (connected && !mutex_locked) { + mutex_locked = mutex_trylock(&con->lock) != 0; + connected = UCSI_CONSTAT(con, CONNECTED); + if (connected && !mutex_locked) + msleep(20); + } + + connected = connected && con->partner; + if (!connected && mutex_locked) + mutex_unlock(&con->lock); + + return connected; +} +EXPORT_SYMBOL_GPL(ucsi_con_mutex_lock); + +/** + * ucsi_con_mutex_unlock - Release the connector mutex + * @con: The connector interface to unlock + */ +void ucsi_con_mutex_unlock(struct ucsi_connector *con) +{ + mutex_unlock(&con->lock); +} +EXPORT_SYMBOL_GPL(ucsi_con_mutex_unlock); + /** * ucsi_create - Allocate UCSI instance * @dev: Device interface to the PPM (Platform Policy Manager) diff --git a/drivers/usb/typec/ucsi/ucsi.h b/drivers/usb/typec/ucsi/ucsi.h index 3a2c1762bec1..9c5278a0c5d4 100644 --- a/drivers/usb/typec/ucsi/ucsi.h +++ b/drivers/usb/typec/ucsi/ucsi.h @@ -94,6 +94,8 @@ int ucsi_register(struct ucsi *ucsi); void ucsi_unregister(struct ucsi *ucsi); void *ucsi_get_drvdata(struct ucsi *ucsi); void ucsi_set_drvdata(struct ucsi *ucsi, void *data); +bool ucsi_con_mutex_lock(struct ucsi_connector *con); +void ucsi_con_mutex_unlock(struct ucsi_connector *con); void ucsi_connector_change(struct ucsi *ucsi, u8 num); -- 2.49.0.504.g3bcea36a83-goog

9 months

[PATCH] f2fs: fix to do sanity check on ino and xnid

by Chao Yu

syzbot reported a f2fs bug as below: INFO: task syz-executor140:5308 blocked for more than 143 seconds. Not tainted 6.14.0-rc7-syzkaller-00069-g81e4f8d68c66 #0 "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. task:syz-executor140 state:D stack:24016 pid:5308 tgid:5308 ppid:5306 task_flags:0x400140 flags:0x00000006 Call Trace: <TASK> context_switch kernel/sched/core.c:5378 [inline] __schedule+0x190e/0x4c90 kernel/sched/core.c:6765 __schedule_loop kernel/sched/core.c:6842 [inline] schedule+0x14b/0x320 kernel/sched/core.c:6857 io_schedule+0x8d/0x110 kernel/sched/core.c:7690 folio_wait_bit_common+0x839/0xee0 mm/filemap.c:1317 __folio_lock mm/filemap.c:1664 [inline] folio_lock include/linux/pagemap.h:1163 [inline] __filemap_get_folio+0x147/0xb40 mm/filemap.c:1917 pagecache_get_page+0x2c/0x130 mm/folio-compat.c:87 find_get_page_flags include/linux/pagemap.h:842 [inline] f2fs_grab_cache_page+0x2b/0x320 fs/f2fs/f2fs.h:2776 __get_node_page+0x131/0x11b0 fs/f2fs/node.c:1463 read_xattr_block+0xfb/0x190 fs/f2fs/xattr.c:306 lookup_all_xattrs fs/f2fs/xattr.c:355 [inline] f2fs_getxattr+0x676/0xf70 fs/f2fs/xattr.c:533 __f2fs_get_acl+0x52/0x870 fs/f2fs/acl.c:179 f2fs_acl_create fs/f2fs/acl.c:375 [inline] f2fs_init_acl+0xd7/0x9b0 fs/f2fs/acl.c:418 f2fs_init_inode_metadata+0xa0f/0x1050 fs/f2fs/dir.c:539 f2fs_add_inline_entry+0x448/0x860 fs/f2fs/inline.c:666 f2fs_add_dentry+0xba/0x1e0 fs/f2fs/dir.c:765 f2fs_do_add_link+0x28c/0x3a0 fs/f2fs/dir.c:808 f2fs_add_link fs/f2fs/f2fs.h:3616 [inline] f2fs_mknod+0x2e8/0x5b0 fs/f2fs/namei.c:766 vfs_mknod+0x36d/0x3b0 fs/namei.c:4191 unix_bind_bsd net/unix/af_unix.c:1286 [inline] unix_bind+0x563/0xe30 net/unix/af_unix.c:1379 __sys_bind_socket net/socket.c:1817 [inline] __sys_bind+0x1e4/0x290 net/socket.c:1848 __do_sys_bind net/socket.c:1853 [inline] __se_sys_bind net/socket.c:1851 [inline] __x64_sys_bind+0x7a/0x90 net/socket.c:1851 do_syscall_x64 arch/x86/entry/common.c:52 [inline] do_syscall_64+0xf3/0x230 arch/x86/entry/common.c:83 entry_SYSCALL_64_after_hwframe+0x77/0x7f Let's dump and check metadata of corrupted inode, it shows its xattr_nid is the same to its i_ino. dump.f2fs -i 3 chaseyu.img.raw i_xattr_nid [0x 3 : 3] So that, during mknod in the corrupted directory, it tries to get and lock inode page twice, result in deadlock. - f2fs_mknod - f2fs_add_inline_entry - f2fs_get_inode_page --- lock dir's inode page - f2fs_init_acl - f2fs_acl_create(dir,..) - __f2fs_get_acl - f2fs_getxattr - lookup_all_xattrs - __get_node_page --- try to lock dir's inode page In order to fix this, let's add sanity check on ino and xnid. Cc: stable(a)vger.kernel.org Reported-by: syzbot+cc448dcdc7ae0b4e4ffa(a)syzkaller.appspotmail.com Closes: https://lore.kernel.org/linux-f2fs-devel/67e06150.050a0220.21942d.0005.GAE@… Signed-off-by: Chao Yu <chao(a)kernel.org> --- fs/f2fs/inode.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c index 83f862578fc8..5c8634eaef7b 100644 --- a/fs/f2fs/inode.c +++ b/fs/f2fs/inode.c @@ -286,6 +286,12 @@ static bool sanity_check_inode(struct inode *inode, struct page *node_page) return false; } + if (ino_of_node(node_page) == fi->i_xattr_nid) { + f2fs_warn(sbi, "%s: corrupted inode i_ino=%lx, xnid=%x, run fsck to fix.", + __func__, inode->i_ino, fi->i_xattr_nid); + return false; + } + if (f2fs_has_extra_attr(inode)) { if (!f2fs_sb_has_extra_attr(sbi)) { f2fs_warn(sbi, "%s: inode (ino=%lx) is with extra_attr, but extra_attr feature is off", -- 2.48.1

9 months

WTS

by Winston Taylor

Hello , These are available for sale. If you’re interested in purchasing these, please email me brand new and original Brand New ST8000NM017B $70 EA Brand New ST20000NM007D $100 EACH Brand New ST4000NM000A $30 EA Brand New WD80EFPX $60 EA Brand New WD101PURZ $70 EA Brand New CISCO C9300-48UXM-E Available 5 $21800 EACH Intel Xeon Gold 5418Y Processors QTY28 $780 each Brand New C9200L-48T-4X-E $1000 EAC Brand New N9K-C93108TC-FX-24 Nexus 9300-FX w/ 24p 100M/1/10GT & 6p 40/100G Available 4 $3000 each Brand New NVIDIA GeForce RTX 4090 Founders Edition 24GB - QTY: 56 - $700 each Brand new Palit NVIDIA GeForce RTX 5080 GamingPro OC card with full manufacturer QTY 48 $750 EAC BRAND NEW - ASUS TUF Gaming GeForce RTX ™ 5080 16GB GDDR7 OC Edition Gaming Graphics Card SEALED QTY50 $700 EACH Condition: Grade A Used HP EliteBook 840 G7 i7-10610U 16GB RAM 512GB SSD Windows 11 Pro TOUCH Screen QTY 30 USD 100 each Condition: Grade A Used HP EliteBook 850 G8 15.6" FHD, INTEL I7, 256GB SSD, 8GB RAM Win11 QTY50 $240 EACH SK Hynix 48GB DDR5 4800 1Rx4 PC5-4800B- PF0-1010-XT 288pin Server EC4 RDIMM RAM QTY 239 $50 EACH ----------------------------------------------------------------- --------------- Best Regards, Winston Taylor 300 Laird St, Wilkes-Barre, PA 18702, USA Mobile: +1 (570) 890-5512 Email: winstontaylor(a)theleadingone.net www.theleadingone.net

9 months

[PATCH v3 net] net: Fix null-ptr-deref by sock_lock_init_class_and_name() and rmmod.

by Kuniyuki Iwashima

When I ran the repro [0] and waited a few seconds, I observed two LOCKDEP splats: a warning immediately followed by a null-ptr-deref. [1] Reproduction Steps: 1) Mount CIFS 2) Add an iptables rule to drop incoming FIN packets for CIFS 3) Unmount CIFS 4) Unload the CIFS module 5) Remove the iptables rule At step 3), the CIFS module calls sock_release() for the underlying TCP socket, and it returns quickly. However, the socket remains in FIN_WAIT_1 because incoming FIN packets are dropped. At this point, the module's refcnt is 0 while the socket is still alive, so the following rmmod command succeeds. # ss -tan State Recv-Q Send-Q Local Address:Port Peer Address:Port FIN-WAIT-1 0 477 10.0.2.15:51062 10.0.0.137:445 # lsmod | grep cifs cifs 1159168 0 This highlights a discrepancy between the lifetime of the CIFS module and the underlying TCP socket. Even after CIFS calls sock_release() and it returns, the TCP socket does not die immediately in order to close the connection gracefully. While this is generally fine, it causes an issue with LOCKDEP because CIFS assigns a different lock class to the TCP socket's sk->sk_lock using sock_lock_init_class_and_name(). Once an incoming packet is processed for the socket or a timer fires, sk->sk_lock is acquired. Then, LOCKDEP checks the lock context in check_wait_context(), where hlock_class() is called to retrieve the lock class. However, since the module has already been unloaded, hlock_class() logs a warning and returns NULL, triggering the null-ptr-deref. If LOCKDEP is enabled, we must ensure that a module calling sock_lock_init_class_and_name() (CIFS, NFS, etc) cannot be unloaded while such a socket is still alive to prevent this issue. Let's hold the module reference in sock_lock_init_class_and_name() and release it when the socket is freed in sk_prot_free(). Note that sock_lock_init() clears sk->sk_owner for svc_create_socket() that calls sock_lock_init_class_and_name() for a listening socket, which clones a socket by sk_clone_lock() without GFP_ZERO. [0]: CIFS_SERVER="10.0.0.137" CIFS_PATH="//${CIFS_SERVER}/Users/Administrator/Desktop/CIFS_TEST" DEV="enp0s3" CRED="/root/WindowsCredential.txt" MNT=$(mktemp -d /tmp/XXXXXX) mount -t cifs ${CIFS_PATH} ${MNT} -o vers=3.0,credentials=${CRED},cache=none,echo_interval=1 iptables -A INPUT -s ${CIFS_SERVER} -j DROP for i in $(seq 10); do umount ${MNT} rmmod cifs sleep 1 done rm -r ${MNT} iptables -D INPUT -s ${CIFS_SERVER} -j DROP [1]: DEBUG_LOCKS_WARN_ON(1) WARNING: CPU: 10 PID: 0 at kernel/locking/lockdep.c:234 hlock_class (kernel/locking/lockdep.c:234 kernel/locking/lockdep.c:223) Modules linked in: cifs_arc4 nls_ucs2_utils cifs_md4 [last unloaded: cifs] CPU: 10 UID: 0 PID: 0 Comm: swapper/10 Not tainted 6.14.0 #36 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.0-0-gd239552ce722-prebuilt.qemu.org 04/01/2014 RIP: 0010:hlock_class (kernel/locking/lockdep.c:234 kernel/locking/lockdep.c:223) ... Call Trace: <IRQ> __lock_acquire (kernel/locking/lockdep.c:4853 kernel/locking/lockdep.c:5178) lock_acquire (kernel/locking/lockdep.c:469 kernel/locking/lockdep.c:5853 kernel/locking/lockdep.c:5816) _raw_spin_lock_nested (kernel/locking/spinlock.c:379) tcp_v4_rcv (./include/linux/skbuff.h:1678 ./include/net/tcp.h:2547 net/ipv4/tcp_ipv4.c:2350) ... BUG: kernel NULL pointer dereference, address: 00000000000000c4 PF: supervisor read access in kernel mode PF: error_code(0x0000) - not-present page PGD 0 Oops: Oops: 0000 [#1] PREEMPT SMP NOPTI CPU: 10 UID: 0 PID: 0 Comm: swapper/10 Tainted: G W 6.14.0 #36 Tainted: [W]=WARN Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.0-0-gd239552ce722-prebuilt.qemu.org 04/01/2014 RIP: 0010:__lock_acquire (kernel/locking/lockdep.c:4852 kernel/locking/lockdep.c:5178) Code: 15 41 09 c7 41 8b 44 24 20 25 ff 1f 00 00 41 09 c7 8b 84 24 a0 00 00 00 45 89 7c 24 20 41 89 44 24 24 e8 e1 bc ff ff 4c 89 e7 <44> 0f b6 b8 c4 00 00 00 e8 d1 bc ff ff 0f b6 80 c5 00 00 00 88 44 RSP: 0018:ffa0000000468a10 EFLAGS: 00010046 RAX: 0000000000000000 RBX: ff1100010091cc38 RCX: 0000000000000027 RDX: ff1100081f09ca48 RSI: 0000000000000001 RDI: ff1100010091cc88 RBP: ff1100010091c200 R08: ff1100083fe6e228 R09: 00000000ffffbfff R10: ff1100081eca0000 R11: ff1100083fe10dc0 R12: ff1100010091cc88 R13: 0000000000000001 R14: 0000000000000000 R15: 00000000000424b1 FS: 0000000000000000(0000) GS:ff1100081f080000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00000000000000c4 CR3: 0000000002c4a003 CR4: 0000000000771ef0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe07f0 DR7: 0000000000000400 PKRU: 55555554 Call Trace: <IRQ> lock_acquire (kernel/locking/lockdep.c:469 kernel/locking/lockdep.c:5853 kernel/locking/lockdep.c:5816) _raw_spin_lock_nested (kernel/locking/spinlock.c:379) tcp_v4_rcv (./include/linux/skbuff.h:1678 ./include/net/tcp.h:2547 net/ipv4/tcp_ipv4.c:2350) ip_protocol_deliver_rcu (net/ipv4/ip_input.c:205 (discriminator 1)) ip_local_deliver_finish (./include/linux/rcupdate.h:878 net/ipv4/ip_input.c:234) ip_sublist_rcv_finish (net/ipv4/ip_input.c:576) ip_list_rcv_finish (net/ipv4/ip_input.c:628) ip_list_rcv (net/ipv4/ip_input.c:670) __netif_receive_skb_list_core (net/core/dev.c:5939 net/core/dev.c:5986) netif_receive_skb_list_internal (net/core/dev.c:6040 net/core/dev.c:6129) napi_complete_done (./include/linux/list.h:37 ./include/net/gro.h:519 ./include/net/gro.h:514 net/core/dev.c:6496) e1000_clean (drivers/net/ethernet/intel/e1000/e1000_main.c:3815) __napi_poll.constprop.0 (net/core/dev.c:7191) net_rx_action (net/core/dev.c:7262 net/core/dev.c:7382) handle_softirqs (kernel/softirq.c:561) __irq_exit_rcu (kernel/softirq.c:596 kernel/softirq.c:435 kernel/softirq.c:662) irq_exit_rcu (kernel/softirq.c:680) common_interrupt (arch/x86/kernel/irq.c:280 (discriminator 14)) </IRQ> <TASK> asm_common_interrupt (./arch/x86/include/asm/idtentry.h:693) RIP: 0010:default_idle (./arch/x86/include/asm/irqflags.h:37 ./arch/x86/include/asm/irqflags.h:92 arch/x86/kernel/process.c:744) Code: 4c 01 c7 4c 29 c2 e9 72 ff ff ff 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 f3 0f 1e fa eb 07 0f 00 2d c3 2b 15 00 fb f4 <fa> c3 cc cc cc cc 66 66 2e 0f 1f 84 00 00 00 00 00 90 90 90 90 90 RSP: 0018:ffa00000000ffee8 EFLAGS: 00000202 RAX: 000000000000640b RBX: ff1100010091c200 RCX: 0000000000061aa4 RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffffffff812f30c5 RBP: 000000000000000a R08: 0000000000000001 R09: 0000000000000000 R10: 0000000000000001 R11: 0000000000000002 R12: 0000000000000000 R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000 ? do_idle (kernel/sched/idle.c:186 kernel/sched/idle.c:325) default_idle_call (./include/linux/cpuidle.h:143 kernel/sched/idle.c:118) do_idle (kernel/sched/idle.c:186 kernel/sched/idle.c:325) cpu_startup_entry (kernel/sched/idle.c:422 (discriminator 1)) start_secondary (arch/x86/kernel/smpboot.c:315) common_startup_64 (arch/x86/kernel/head_64.S:421) </TASK> Modules linked in: cifs_arc4 nls_ucs2_utils cifs_md4 [last unloaded: cifs] CR2: 00000000000000c4 Fixes: ed07536ed673 ("[PATCH] lockdep: annotate nfs/nfsd in-kernel sockets") Signed-off-by: Kuniyuki Iwashima <kuniyu(a)amazon.com> Cc: stable(a)vger.kernel.org --- v3: * Add kdoc for sk_owner * Move sk_owner_put() to sk_prot_free() v2: https://lore.kernel.org/netdev/20250403203619.36648-1-kuniyu@amazon.com/ * Clear sk_owner in sock_lock_init() * Define helper under the same #if guard * Remove redundant null check before module_put() v1: https://lore.kernel.org/netdev/20250403020837.51664-1-kuniyu@amazon.com/ --- include/net/sock.h | 40 ++++++++++++++++++++++++++++++++++++++-- net/core/sock.c | 5 +++++ 2 files changed, 43 insertions(+), 2 deletions(-) diff --git a/include/net/sock.h b/include/net/sock.h index 8daf1b3b12c6..694f954258d4 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -339,6 +339,8 @@ struct sk_filter; * @sk_txtime_unused: unused txtime flags * @ns_tracker: tracker for netns reference * @sk_user_frags: xarray of pages the user is holding a reference on. + * @sk_owner: reference to the real owner of the socket that calls + * sock_lock_init_class_and_name(). */ struct sock { /* @@ -547,6 +549,10 @@ struct sock { struct rcu_head sk_rcu; netns_tracker ns_tracker; struct xarray sk_user_frags; + +#if IS_ENABLED(CONFIG_PROVE_LOCKING) && IS_ENABLED(CONFIG_MODULES) + struct module *sk_owner; +#endif }; struct sock_bh_locked { @@ -1583,6 +1589,35 @@ static inline void sk_mem_uncharge(struct sock *sk, int size) sk_mem_reclaim(sk); } +#if IS_ENABLED(CONFIG_PROVE_LOCKING) && IS_ENABLED(CONFIG_MODULES) +static inline void sk_owner_set(struct sock *sk, struct module *owner) +{ + __module_get(owner); + sk->sk_owner = owner; +} + +static inline void sk_owner_clear(struct sock *sk) +{ + sk->sk_owner = NULL; +} + +static inline void sk_owner_put(struct sock *sk) +{ + module_put(sk->sk_owner); +} +#else +static inline void sk_owner_set(struct sock *sk, struct module *owner) +{ +} + +static inline void sk_owner_clear(struct sock *sk) +{ +} + +static inline void sk_owner_put(struct sock *sk) +{ +} +#endif /* * Macro so as to not evaluate some arguments when * lockdep is not enabled. @@ -1592,13 +1627,14 @@ static inline void sk_mem_uncharge(struct sock *sk, int size) */ #define sock_lock_init_class_and_name(sk, sname, skey, name, key) \ do { \ + sk_owner_set(sk, THIS_MODULE); \ sk->sk_lock.owned = 0; \ init_waitqueue_head(&sk->sk_lock.wq); \ spin_lock_init(&(sk)->sk_lock.slock); \ debug_check_no_locks_freed((void *)&(sk)->sk_lock, \ - sizeof((sk)->sk_lock)); \ + sizeof((sk)->sk_lock)); \ lockdep_set_class_and_name(&(sk)->sk_lock.slock, \ - (skey), (sname)); \ + (skey), (sname)); \ lockdep_init_map(&(sk)->sk_lock.dep_map, (name), (key), 0); \ } while (0) diff --git a/net/core/sock.c b/net/core/sock.c index 323892066def..739a79859828 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2130,6 +2130,8 @@ int sk_getsockopt(struct sock *sk, int level, int optname, */ static inline void sock_lock_init(struct sock *sk) { + sk_owner_clear(sk); + if (sk->sk_kern_sock) sock_lock_init_class_and_name( sk, @@ -2226,6 +2228,9 @@ static void sk_prot_free(struct proto *prot, struct sock *sk) cgroup_sk_free(&sk->sk_cgrp_data); mem_cgroup_sk_free(sk); security_sk_free(sk); + + sk_owner_put(sk); + if (slab != NULL) kmem_cache_free(slab, sk); else -- 2.48.1

9 months

Jump to page:

2026

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror