October 2020 - Linux-stable-mirror

[PATCH AUTOSEL 4.14 1/2] epoll: do not insert into poll queues until all sanity checks are done

by Sasha Levin

From: Al Viro <viro(a)zeniv.linux.org.uk> [ Upstream commit f8d4f44df056c5b504b0d49683fb7279218fd207 ] Signed-off-by: Al Viro <viro(a)zeniv.linux.org.uk> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- fs/eventpoll.c | 37 ++++++++++++++++++------------------- 1 file changed, 18 insertions(+), 19 deletions(-) diff --git a/fs/eventpoll.c b/fs/eventpoll.c index af9dfa494b1fa..a32df9cad519f 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -1461,6 +1461,22 @@ static int ep_insert(struct eventpoll *ep, struct epoll_event *event, RCU_INIT_POINTER(epi->ws, NULL); } + /* Add the current item to the list of active epoll hook for this file */ + spin_lock(&tfile->f_lock); + list_add_tail_rcu(&epi->fllink, &tfile->f_ep_links); + spin_unlock(&tfile->f_lock); + + /* + * Add the current item to the RB tree. All RB tree operations are + * protected by "mtx", and ep_insert() is called with "mtx" held. + */ + ep_rbtree_insert(ep, epi); + + /* now check if we've created too many backpaths */ + error = -EINVAL; + if (full_check && reverse_path_check()) + goto error_remove_epi; + /* Initialize the poll table using the queue callback */ epq.epi = epi; init_poll_funcptr(&epq.pt, ep_ptable_queue_proc); @@ -1483,22 +1499,6 @@ static int ep_insert(struct eventpoll *ep, struct epoll_event *event, if (epi->nwait < 0) goto error_unregister; - /* Add the current item to the list of active epoll hook for this file */ - spin_lock(&tfile->f_lock); - list_add_tail_rcu(&epi->fllink, &tfile->f_ep_links); - spin_unlock(&tfile->f_lock); - - /* - * Add the current item to the RB tree. All RB tree operations are - * protected by "mtx", and ep_insert() is called with "mtx" held. - */ - ep_rbtree_insert(ep, epi); - - /* now check if we've created too many backpaths */ - error = -EINVAL; - if (full_check && reverse_path_check()) - goto error_remove_epi; - /* We have to drop the new item inside our item list to keep track of it */ spin_lock_irqsave(&ep->lock, flags); @@ -1527,6 +1527,8 @@ static int ep_insert(struct eventpoll *ep, struct epoll_event *event, return 0; +error_unregister: + ep_unregister_pollwait(ep, epi); error_remove_epi: spin_lock(&tfile->f_lock); list_del_rcu(&epi->fllink); @@ -1534,9 +1536,6 @@ static int ep_insert(struct eventpoll *ep, struct epoll_event *event, rb_erase_cached(&epi->rbn, &ep->rbr); -error_unregister: - ep_unregister_pollwait(ep, epi); - /* * We need to do this because an event could have been arrived on some * allocated wait queue. Note that we don't care about the ep->ovflist -- 2.25.1

5 years

1
1
0 0

[PATCH AUTOSEL 4.19 1/2] epoll: do not insert into poll queues until all sanity checks are done

by Sasha Levin

From: Al Viro <viro(a)zeniv.linux.org.uk> [ Upstream commit f8d4f44df056c5b504b0d49683fb7279218fd207 ] Signed-off-by: Al Viro <viro(a)zeniv.linux.org.uk> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- fs/eventpoll.c | 37 ++++++++++++++++++------------------- 1 file changed, 18 insertions(+), 19 deletions(-) diff --git a/fs/eventpoll.c b/fs/eventpoll.c index 61a52bb26d127..ed6c06dbb5369 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -1450,6 +1450,22 @@ static int ep_insert(struct eventpoll *ep, const struct epoll_event *event, RCU_INIT_POINTER(epi->ws, NULL); } + /* Add the current item to the list of active epoll hook for this file */ + spin_lock(&tfile->f_lock); + list_add_tail_rcu(&epi->fllink, &tfile->f_ep_links); + spin_unlock(&tfile->f_lock); + + /* + * Add the current item to the RB tree. All RB tree operations are + * protected by "mtx", and ep_insert() is called with "mtx" held. + */ + ep_rbtree_insert(ep, epi); + + /* now check if we've created too many backpaths */ + error = -EINVAL; + if (full_check && reverse_path_check()) + goto error_remove_epi; + /* Initialize the poll table using the queue callback */ epq.epi = epi; init_poll_funcptr(&epq.pt, ep_ptable_queue_proc); @@ -1472,22 +1488,6 @@ static int ep_insert(struct eventpoll *ep, const struct epoll_event *event, if (epi->nwait < 0) goto error_unregister; - /* Add the current item to the list of active epoll hook for this file */ - spin_lock(&tfile->f_lock); - list_add_tail_rcu(&epi->fllink, &tfile->f_ep_links); - spin_unlock(&tfile->f_lock); - - /* - * Add the current item to the RB tree. All RB tree operations are - * protected by "mtx", and ep_insert() is called with "mtx" held. - */ - ep_rbtree_insert(ep, epi); - - /* now check if we've created too many backpaths */ - error = -EINVAL; - if (full_check && reverse_path_check()) - goto error_remove_epi; - /* We have to drop the new item inside our item list to keep track of it */ spin_lock_irq(&ep->wq.lock); @@ -1516,6 +1516,8 @@ static int ep_insert(struct eventpoll *ep, const struct epoll_event *event, return 0; +error_unregister: + ep_unregister_pollwait(ep, epi); error_remove_epi: spin_lock(&tfile->f_lock); list_del_rcu(&epi->fllink); @@ -1523,9 +1525,6 @@ static int ep_insert(struct eventpoll *ep, const struct epoll_event *event, rb_erase_cached(&epi->rbn, &ep->rbr); -error_unregister: - ep_unregister_pollwait(ep, epi); - /* * We need to do this because an event could have been arrived on some * allocated wait queue. Note that we don't care about the ep->ovflist -- 2.25.1

5 years

1
1
0 0

[PATCH AUTOSEL 5.4 1/4] epoll: do not insert into poll queues until all sanity checks are done

by Sasha Levin

From: Al Viro <viro(a)zeniv.linux.org.uk> [ Upstream commit f8d4f44df056c5b504b0d49683fb7279218fd207 ] Signed-off-by: Al Viro <viro(a)zeniv.linux.org.uk> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- fs/eventpoll.c | 37 ++++++++++++++++++------------------- 1 file changed, 18 insertions(+), 19 deletions(-) diff --git a/fs/eventpoll.c b/fs/eventpoll.c index ae1d32344f7ac..f70df53666ed1 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -1527,6 +1527,22 @@ static int ep_insert(struct eventpoll *ep, const struct epoll_event *event, RCU_INIT_POINTER(epi->ws, NULL); } + /* Add the current item to the list of active epoll hook for this file */ + spin_lock(&tfile->f_lock); + list_add_tail_rcu(&epi->fllink, &tfile->f_ep_links); + spin_unlock(&tfile->f_lock); + + /* + * Add the current item to the RB tree. All RB tree operations are + * protected by "mtx", and ep_insert() is called with "mtx" held. + */ + ep_rbtree_insert(ep, epi); + + /* now check if we've created too many backpaths */ + error = -EINVAL; + if (full_check && reverse_path_check()) + goto error_remove_epi; + /* Initialize the poll table using the queue callback */ epq.epi = epi; init_poll_funcptr(&epq.pt, ep_ptable_queue_proc); @@ -1549,22 +1565,6 @@ static int ep_insert(struct eventpoll *ep, const struct epoll_event *event, if (epi->nwait < 0) goto error_unregister; - /* Add the current item to the list of active epoll hook for this file */ - spin_lock(&tfile->f_lock); - list_add_tail_rcu(&epi->fllink, &tfile->f_ep_links); - spin_unlock(&tfile->f_lock); - - /* - * Add the current item to the RB tree. All RB tree operations are - * protected by "mtx", and ep_insert() is called with "mtx" held. - */ - ep_rbtree_insert(ep, epi); - - /* now check if we've created too many backpaths */ - error = -EINVAL; - if (full_check && reverse_path_check()) - goto error_remove_epi; - /* We have to drop the new item inside our item list to keep track of it */ write_lock_irq(&ep->lock); @@ -1593,6 +1593,8 @@ static int ep_insert(struct eventpoll *ep, const struct epoll_event *event, return 0; +error_unregister: + ep_unregister_pollwait(ep, epi); error_remove_epi: spin_lock(&tfile->f_lock); list_del_rcu(&epi->fllink); @@ -1600,9 +1602,6 @@ static int ep_insert(struct eventpoll *ep, const struct epoll_event *event, rb_erase_cached(&epi->rbn, &ep->rbr); -error_unregister: - ep_unregister_pollwait(ep, epi); - /* * We need to do this because an event could have been arrived on some * allocated wait queue. Note that we don't care about the ep->ovflist -- 2.25.1

5 years

1
3
0 0

RFC: backport of commit a32c1c61212d

by Doug Berger

I recently tracked down a problem I observed when booting a v5.4 kernel on a sparsemem UMA arm platform which includes a no-map reserved-memory region in the middle of its HighMem zone. When memmap_init_zone() is invoked the pfn's that correspond to the no-map region fail the early_pfn_valid() check and the struct page structures are not initialized creating a "hole" in the memmap. Later in my boot sequence the sock_init() initcall leads to a bpf_prog_alloc() which ends up stealing a page from the block containing the no-map region which then leads to a call of move_freepages_block() to reclassify the migratetype of the entire block. The function move_freepages() includes a check of pfn_valid_within for each page in the range, but since the arm architecture doesn't include HOLES_IN_ZONE this check is optimized out and the uninitialized struct page is accessed. Specifically, PageLRU() calls compound_head() on the page and if the page->compound_head value is odd the value is used as a pointer to the head struct page. For uninitialized memory there is a high chance that a random value of compound head will be odd and contain an invalid pointer value that causes the kernel to abort and panic. As you might imagine specifying HOLES_IN_ZONE for the arm build allows pfn_valid_within to protect against accessing the uninitialized struct page. However, the performance penalty this incurs seems unnecessary. Commit 35fd1eb1e821 ("mm/sparse: abstract sparse buffer allocations") as part of the "sparse_init rewrite" series introduced in v4.19 changed the way sparsemem memmaps are initialized. Prior to this patch the sparsemem memmaps are initialized to all 0's. I observed that on older kernels the "uninitialized" struct page access also occurs, but the 0 page->compound_head indicates no compound head and the page pointer is therefore not corrupted. The other logic ends up causing the page to be skipped and everything "happens to work". While considering solutions to this issue I observed that the problem does not occur in the current upstream as a result of a combination of other commits. The following commits provided functionality to initialize struct page structures for pages that are unavailable like the no-map region in my system: commit a4a3ede2132a ("mm: zero reserved and unavailable struct pages") commit 907ec5fca3dc ("mm: zero remaining unavailable struct pages") commit ec393a0f014e ("mm: return zero_resv_unavail optimization") commit e822969cab48 ("mm/page_alloc.c: fix uninitialized memmaps on a partially populated last section") commit 4b094b7851bf ("mm/page_alloc.c: initialize memmap of unavailable memory directly") However, those commits added the functionality to the free_area_init() and free_area_init_nodes() functions and the non-NUMA arm architecture did not begin calling free_area_init() until the following commit in v5.8: commit a32c1c61212d ("arm: simplify detection of memory zone boundaries") Prior to that commit the non-NUMA arm architecture called free_area_init_node() directly at the end of zone_sizes_init(). So while the problem appears to be fixed upstream by commit a32c1c61212d ("arm: simplify detection of memory zone boundaries") it is still present in stable branches between v4.19.y and v5.7.y inclusive and probably for architectures other than arm as well that didn't call free_area_init(). This upstream commit is not easily/safely backportable to stable branches, but if we focus on the sliver of functionality that adds the initialization code from free_area_init() to the zones_sizes_init() function used by non-NUMA arm kernels I believe a simple patch could be developed for each relevant stable branch to resolve the issue I am observing. Similar patches could also be applied for other architectures that now call free_area_init() upstream but not in one of these stable branches, but I am not in a position to test those architectures. For the linux-5.4.y branch such a patch might look like this: >From 671c341b5cdb8360349c33ade43115e28ca56a8a Mon Sep 17 00:00:00 2001 From: Doug Berger <opendmb(a)gmail.com> Date: Tue, 25 Aug 2020 14:39:43 -0700 Subject: [PATCH] ARM: mm: sync zone_sizes_init with free_area_init The arm architecture does not invoke the common function free_area_init(). Instead for non-NUMA builds it invokes free_area_init_node() directly from zone_sizes_init(). As a result recent changes in free_area_init() are not picked up by arm architecture builds. This commit adds the updates to the zone_sizes_init() function to achieve parity with the free_area_init() functionality. Fixes: 35fd1eb1e821 ("mm/sparse: abstract sparse buffer allocations") Signed-off-by: Doug Berger <opendmb(a)gmail.com> Cc: stable(a)vger.kernel.org --- arch/arm/mm/init.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c index 6f19ba53fd1f..4f171d834c60 100644 --- a/arch/arm/mm/init.c +++ b/arch/arm/mm/init.c @@ -169,6 +169,7 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max_low, arm_dma_zone_size >> PAGE_SHIFT); #endif + zero_resv_unavail(); free_area_init_node(0, zone_size, min, zhole_size); } -- 2.7.4 I am unclear of the mechanics for submitting such a stable patch when it represents a perhaps less than obvious sliver of the upstream commit that fixes the issue, so I am soliciting guidance with this email. Thank you for taking the time to read this far, and please let me know how I can improve the situation, Doug

5 years

3
5
0 0

[stable 4.19] [PANIC]: tracing: Centralize preemptirq tracepoints and unify their usage

by Naresh Kamboju

>From stable rc 4.18.1 onwards to today's stable rc 4.19.147 There are two problems while running LTP tracing tests 1) kernel panic on i386, qemu_i386, x86_64 and qemu_x86_64 [1] 2) " segfault at 0 ip " and "Code: Bad RIP value" on x86_64 and qemu_x86_64 [2] Please refer to the full test logs from below links. The first bad commit found by git bisect. commit: c3bc8fd637a9623f5c507bd18f9677effbddf584 tracing: Centralize preemptirq tracepoints and unify their usage Reported-by: Naresh Kamboju <naresh.kamboju(a)linaro.org> easily reproducible on qemu steps to reproduce: # Boot qemu x86_64 with trace configs enabled. # cd /opt/ltp # ./runltp -f tracing metadata: git branch: linux-4.19.y git repo: https://gitlab.com/Linaro/lkft/mirrors/stable/linux-stable-rc make_kernelversion: 4.19.147 kernel-config: https://builds.tuxbuild.com/lOpUmeYR2e1pzvYdlLgGqw/kernel.config Crash log on qemu_i386 --------------------------------- ftrace-stress-test 1 TINFO: Start pid15=2414 /opt/ltp/testcases/bin/ftrace_stress/ftrace_buffer_size_kb.sh ftrace-stress-test 1 TINFO: Start pid16=2415 /opt/ltp/testcases/bin/ftrace_stress/ftrace_tracing_cpumask.sh ftrace-stress-test 1 TINFO: Start pid17=2416 /opt/ltp/testcases/bin/ftrace_stress/ftrace_set_ftrace_filter.sh [ 38.479869] Scheduler tracepoints stat_sleep, stat_iowait, stat_blocked and stat_runtime require the kernel parameter schedstats=enable or kernel.sched_schedstats=1 Sep 23 18:39:40 intel-core2-32 user.warn kernel: [ 38.479869] Scheduler tracepoints stat_sleep, stat_iowait, stat_blocked and stat_runtime require the kernel parameter schedstats=enable or kernel.sched_schedstats=1 [ 38.549712] cat[2583]: segfault at 0 ip b7f81767 sp bfbb3a20 error 4 in ld-2.27.so[b7f6c000+25000] [ 38.550427] sh[2582]: segfault at 467 ip b7fba0d8 sp bfacdb04 error 4 in ld-2.27.so[b7f9f000+25000] [ 38.551386] Code: 50 8d 86 84 62 ff ff 50 e8 86 a9 ff ff 83 c4 10 89 c2 83 f8 ff 0f 84 72 01 00 00 8b b6 e4 08 00 00 83 fe 10 0f 86 56 01 00 00 <81> 38 6c 64 2e 73 0f 85 1d 01 00 00 81 78 04 6f 2d 31 2e 0f 85 10 [ 38.552710] Code: 40 38 d5 74 ea 80 fd 00 74 12 c1 e9 10 40 38 d1 74 dd 80 f9 00 74 05 40 38 d5 74 d3 31 c0 eb cf 66 90 8b 4c 24 04 8b 54 24 08 <8a> 01 3a 02 75 09 41 42 84 c0 75 f4 31 c0 c3 b8 01 00 00 00 b9 ff [ 38.556010] systemd-journal[1327]: segfault at 5e ip b7c61e12 sp bff45044 error 6 in libc-2.27.so[b7b29000+1cc000] [ 38.558971] sh[2584]: segfault at 0 ip b7f30c15 sp bfbce710 error 14 [ 38.559387] audit: type=1701 audit(1600886380.372:3): auid=4294967295 uid=0 gid=0 ses=4294967295 subj=kernel pid=2582 comm=\"sh\" exe=\"/bin/bash.bash\" sig=11 res=1 [ 38.559411] audit: type=1701 audit(1600886380.372:4): auid=4294967295 uid=0 gid=0 ses=4294967295 subj=kernel pid=2583 comm=\"cat\" exe=\"/bin/cat.coreutils\" sig=11 res=1 [ 38.560079] Code: 66 0f 7f 5c 3a f0 72 30 66 0f 6f 54 38 10 83 e9 20 66 0f 6f 5c 38 20 66 0f 6f cb 66 0f 3a 0f da 08 66 0f 3a 0f d4 08 8d 7f 20 <66> 0f 7f 54 3a e0 66 0f 7f 5c 3a f0 73 a0 8d 49 20 01 cf 01 fa 8d [ 38.560811] audit: type=1701 audit(1600886380.373:5): auid=4294967295 uid=0 gid=0 ses=4294967295 subj=kernel pid=1327 comm=\"systemd-journal\" exe=\"/lib/systemd/systemd-journald\" sig=11 res=1 [ 38.561615] Code: Bad RIP value. [ 38.564712] Core dump to |/bin/false pipe failed [ 38.566144] Core dump to |/bin/false pipe failed [ 38.566213] Core dump to |/bin/false pipe failed Sep 23 18:39:40 intel-core2-32 user.info kernel: [ 38.549712] cat[2583]: segfault at 0 ip b7f81767 sp bfbb3a20 error 4 in ld-2.27.so[b7f6c000+25000] Sep 23 18:39:40 intel-core2-32 user.info kernel: [ 38.550427] sh[2582]: segfault at 467 ip b7fba0d8 sp bfacdb04 error 4 in ld-2.27.so[b7f9f000+25000] Sep 23 18:39:40 intel-core2-32 user.info kernel: [ 38.551386] Code: 50 8d 86 84 62 ff ff 50 e8 86 a9 ff ff 83 c4 10 89 c2 83 f8 ff 0f 84 72 01 00 00 8b b6 e4 08 00 00 83 fe 10 0f 86 56 01 00 00 <81> 38 6c 64 2e 73 0f 85 1d 01 00 00 81 78 04 6f 2d 31 2e 0f 85 10 Sep 23 18:39:40 intel-core2-32 user.info kernel: [ 38.552710] Code: 40 38 d5 74 ea 80 fd 00 74 12 c1 e9 10 40 38 d1 74 dd 80 f9 00 74 05 40 38 d5 74 d3 31 c0 eb cf 66 90 8b 4c 24 04 8b 54 24 08 <8a> 01 3a 02 75 09 41 42 84 c0 75[ 38.582519] systemd[1]: segfault at 1 ip b7de036e sp bfd888e0 error 7 in libsystemd-shared-237.so[b7cd4000+1e2000] f4 31 c0 c3 b8 [ 38.584227] Code: 46 18 83 e0 1f 83 c8 20 88 46 18 89 f0 e8 ba da ff ff 85 c0 89 c3 0f 88 e0 00 00 00 8b 44 24 24 31 db 85 c0 74 06 8b 44 24 24 <89> 30 83 c4 0c 89 d8 5b 5e 5f 5d c3 8d b6 00 00 00 00 8d 83 1c 1c 01 00 00 00 b9 ff Sep 23 18:39:40 intel-core2-32 user.info kernel: [ 38.556010] systemd-journal[1327]: segfau[ 38.587783] systemd[1]: segfault at 0 ip b7a9fbe3 sp bfd88000 error 7 in libc-2.27.so[b79e5000+1cc000] lt at 5e ip b7c6[ 38.589349] Code: 14 8b 4c 24 10 8b 5c 24 0c b8 72 00 00 00 65 ff 15 10 00 00 00 5b 5e 3d 01 f0 ff ff 0f 83 75 e3 f5 ff c3 66 90 66 90 55 57 56 <53> 83 ec 1c 8b 5c 24 30 8b 4c 24 34 8b 54 24 38 8b 74 24 3c 65 8b 1e12 sp bff45044 error 6 in libc-2.27.so[b7b29000+1cc000] Sep 23 18:39:40 intel-core2-32 user.info kernel: [ 38.558971] sh[2584]: segfault at 0 ip b7f30c15 sp bfbce710 error 14 Sep 23 18:39:40 intel-core2-32 user.notice kernel: [ 38.559387] audit: type=1701 audit(1600886380.372:3): auid=4294967295 uid=0 gid=0 ses=4294967295 subj=kernel pid=2582 comm=\"sh\" exe=\"/bin/bash.bash\" sig=11 res=1 Sep 23 18:39:40 intel-core2-32 user.notice kernel: [ 38.559411] audit: type=1701 audit(1600886380.372:4): auid=4294967295 uid=0 gid=0 ses=4294967295 subj=kernel pid=2583 comm=\"cat\" exe=\"/bin/cat.coreutils\" sig=11 res=1 Sep 23 18:39:40 intel-core2-32 user.info kernel: [ 38.560079] Code: 66 0f 7f 5c 3a f0 72 30 66 0f 6f 54 38 10 83 e9 20 66 0f 6f 5c 38 20 66 0f 6f [ 38.598779] Core dump to |/bin/false pipe failed cb 66 0f 3a 0f da 08 66 0f 3a 0f d4 08 8d 7f 20 <66> 0f 7f 54 3a e0 66 0f 7f 5c 3a f0 73 a0 8d 49 20 01 cf 01 fa[ 38.600281] Core dump to |/bin/false pipe failed 8d Sep 23 18:39:40 intel-core2-32 user.notice kernel: [ 38.560811] audit: type=1701 audit(1600886380.373:5): auid=4294967295 uid=0 gid=0 ses=4294967295 subj=kernel pid=1327 comm=\"systemd-j[ 38.602831] Core dump to |/bin/false pipe failed ournal\" exe=\"/li[ 38.603778] Kernel panic - not syncing: Attempted to kill init! exitcode=0x0000000b [ 38.603778] [ 38.604715] CPU: 3 PID: 1 Comm: systemd Not tainted 4.19.147 #1 [ 38.605408] Core dump to |/bin/false pipe failed b/[sy s t e3m8d./6s0y4s7t1e5m] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.12.0-1 04/01/2014 [ 38.604715] Call Trace: [ 38.604715] dump_stack+0x6e/0x9e [ 38.604715] panic+0x94/0x1d1 [ 38.608596] do_exit.cold+0x8d/0xa6 [ 38.608596] do_group_exit+0x36/0xa0 [ 38.608596] get_signal+0x131/0x6c0 [ 38.608596] do_signal+0x29/0x5a0 [ 38.608596] ? trace_buffer_unlock_commit_regs+0x54/0x80 d-[j o u rna3ld\"8. s60i8g5=96] ? trace_event_buffer_commit+0x5d/0x1c0 [ 38.608596] ? trace_event_buffer_reserve+0x50/0x80 1[1 r e3s8=1 Sep 23.608596] exit_to_usermode_loop+0x8f/0x100 [ 38.608596] ? __do_page_fault+0x470/0x470 [ 38.608596] prepare_exit_to_usermode+0x57/0x80 [ 38.608596] resume_userspace+0xd/0x12 [ 1 8 :3389.:604805 9i6n]t eElI-P: 0xb7a9fbe3 [ 38.608596] Code: 14 8b 4c 24 10 8b 5c 24 0c b8 72 00 00 00 65 ff 15 10 00 00 00 5b 5e 3d 01 f0 ff ff 0f 83 75 e3 f5 ff c3 66 90 66 90 55 57 56 <53> 83 ec 1c 8b 5c 24 30 8b 4c 24 34 8b 54 24 38 8b 74 24 3c 65 8b [ 38.617637] EAX: 00000000 EBX: b7efb2e4 ECX: 00000000 EDX: 00000a1d [ 38.617637] ESI: bfd88100 EDI: bfd88180 EBP: 00000000 ESP: bfd88000 [ 38.617637] DS: 007b ES: 007b FS: 0000 GS: 0033 SS: 007b EFLAGS: 00010246 core2-32 user.info kernel: [ 38.561615] Code: Bad RIP value. Sep 23 18:39:40 intel-core2-32 user.info kernel: [ 38.564712] Core dump to |/bin/false pipe failed Sep 23 18:39:40 intel-core2-32 user.info kernel: [ 38.566144] Core dump to |/bin/false pipe failed Sep 23 18:39:40 intel-core2-32 user.info kernel: [ 38.566213] Core dump to |/bin/false pipe failed Sep 23 18:39:40 intel-core2-32 user.emerg kernel: [ 38.582519] systemd[1]: segfault at 1 ip b7de036e sp bfd888e0 error 7 in libsystemd-shared-237.so[b7cd4000+1e2000] Sep 23 18:39:40 intel-core2-32 user.emerg kernel: [ 38.584227] Code: 46 18 83 e0 1f 83 c8 20 88 46 18 89 f0 e8 ba da ff ff 85 c0 89 c3 0f 88 e0 00 00 00 8b 44 24 24 31 db 85 c0 74 06 8b 44 24 24 <89> 30 83 c4 0c 89 d8 5b 5e 5f 5d c3 8d b6 00 00 00 00 8d 83 1c 1c Sep 23 18:39:40 intel-core2-32 user.emerg kernel: [ 38.587783] systemd[1]: segfault at 0 ip b7a9fbe3 sp bfd88000 error 7 in libc-2.27.so[b79e5000+1cc000] Sep 23 18:39:40 intel-core2-32 user.emerg kernel: [ 38.589349] Code: 14 8b 4c 24 10 8b 5c 24 0c b8 72 00 00 00 65 ff 15 10 00 00 00 5b 5e 3d 01 f0 ff ff 0f 83 75 e3 f5 ff c3 66 90 66 90 55 57 56 <53> 83 ec 1c 8b 5c 24 30 8b 4c 24 34 8b 54 24 38 8b 74 24 3c 65 8b Sep 23 18:39:40 intel-core2-32 user.info kernel: [ 38.598779] Core dump to |/bin/false pipe failed Sep 23 18:39:40 intel-core2-32 user.info kernel: [ 38.600281] Core dump to |/bin/false pipe failed [ 38.617637] Kernel Offset: 0x10c00000 from 0xc1000000 (relocation range: 0xc0000000-0xf77fdfff) [ 38.617637] ---[ end Kernel panic - not syncing: Attempted to kill init! exitcode=0x0000000b [ 38.617637] ]--- [ 38.622610] ------------[ cut here ]------------ [ 38.622610] sched: Unexpected reschedule of offline CPU#0! [ 38.622610] WARNING: CPU: 3 PID: 1 at arch/x86/kernel/smp.c:128 native_smp_send_reschedule+0x3b/0x50 [ 38.622610] Modules linked in: [ 38.622610] CPU: 3 PID: 1 Comm: systemd Not tainted 4.19.147 #1 [ 38.622610] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.12.0-1 04/01/2014 [ 38.622610] EIP: native_smp_send_reschedule+0x3b/0x50 [ 38.622610] Code: 8b 15 20 4a b8 d2 8b 4a 18 ba fd 00 00 00 e8 a4 02 b0 00 c9 c3 8d b4 26 00 00 00 00 8d 76 00 50 68 24 a7 a8 d2 e8 9f f3 01 00 <0f> 0b 58 5a c9 c3 8d b4 26 00 00 00 00 8d b4 26 00 00 00 00 90 0f [ 38.622610] EAX: 0000002e EBX: f456d800 ECX: f51eab88 EDX: 00000007 [ 38.622610] ESI: d2dfcf00 EDI: 00000000 EBP: f4d1dca4 ESP: f4d1dc9c [ 38.622610] DS: 007b ES: 007b FS: 00d8 GS: 00e0 SS: 0068 EFLAGS: 00010092 [ 38.622610] CR0: 80050033 CR2: 00000000 CR3: 33f02000 CR4: 003406d0 [ 38.622610] Call Trace: [ 38.622610] try_to_wake_up+0x38b/0x400 [ 38.622610] ? wait_woken+0x70/0x70 [ 38.622610] default_wake_function+0x10/0x20 [ 38.622610] autoremove_wake_function+0x14/0x40 [ 38.622610] __wake_up_common+0x6b/0x130 [ 38.622610] __wake_up_common_lock+0x77/0xb0 [ 38.622610] __wake_up+0x12/0x20 [ 38.622610] wake_up_klogd_work_func+0x66/0x70 [ 38.622610] irq_work_run_list+0x48/0x80 [ 38.622610] ? setup_data_read+0xd0/0xd0 [ 38.622610] irq_work_run+0x25/0x40 [ 38.622610] flush_smp_call_function_queue+0x66/0xe0 [ 38.622610] generic_smp_call_function_single_interrupt+0x12/0x2a [ 38.622610] smp_call_function_interrupt+0x3a/0xd0 [ 38.622610] call_function_interrupt+0xd7/0xdc [ 38.622610] EIP: panic+0x194/0x1d1 [ 38.622610] Code: 83 c3 64 eb b7 83 3d 4c d5 e1 d2 00 74 05 e8 e6 f7 01 00 68 80 d5 e1 d2 68 f8 04 a9 d2 e8 47 7c 05 00 e8 42 28 0d 00 fb 31 db <58> 5a 39 fb 7c 18 83 f6 01 8b 15 40 d5 e1 d2 89 f0 e8 31 0d ae 00 [ 38.622610] EAX: d1ccf04e EBX: 00000000 ECX: 40000000 EDX: 80000000 [ 38.622610] ESI: 00000000 EDI: 00000000 EBP: f4d1de20 ESP: f4d1de08 [ 38.622610] DS: 007b ES: 007b FS: 00d8 GS: 00e0 SS: 0068 EFLAGS: 00000246 [ 38.622610] ? panic+0x191/0x1d1 [ 38.622610] do_exit.cold+0x8d/0xa6 [ 38.622610] do_group_exit+0x36/0xa0 [ 38.622610] get_signal+0x131/0x6c0 [ 38.622610] do_signal+0x29/0x5a0 [ 38.622610] ? trace_buffer_unlock_commit_regs+0x54/0x80 [ 38.622610] ? trace_event_buffer_commit+0x5d/0x1c0 [ 38.622610] ? trace_event_buffer_reserve+0x50/0x80 [ 38.622610] exit_to_usermode_loop+0x8f/0x100 [ 38.622610] ? __do_page_fault+0x470/0x470 [ 38.622610] prepare_exit_to_usermode+0x57/0x80 [ 38.622610] resume_userspace+0xd/0x12 [ 38.622610] EIP: 0xb7a9fbe3 [ 38.622610] Code: 14 8b 4c 24 10 8b 5c 24 0c b8 72 00 00 00 65 ff 15 10 00 00 00 5b 5e 3d 01 f0 ff ff 0f 83 75 e3 f5 ff c3 66 90 66 90 55 57 56 <53> 83 ec 1c 8b 5c 24 30 8b 4c 24 34 8b 54 24 38 8b 74 24 3c 65 8b [ 38.622610] EAX: 00000000 EBX: b7efb2e4 ECX: 00000000 EDX: 00000a1d [ 38.622610] ESI: bfd88100 EDI: bfd88180 EBP: 00000000 ESP: bfd88000 [ 38.622610] DS: 007b ES: 007b FS: 0000 GS: 0033 SS: 007b EFLAGS: 00010246 [ 38.622610] ---[ end trace 16b4da0e9552fc5a ]--- Crash log on qemu_x86_64 ------------------------------------- ftrace-stress-test 1 TINFO: Start pid16=2519 /opt/ltp/testcases/bin/ftrace_stress/ftrace_tracing_cpumask.sh ftrace-stress-test 1 TINFO: Start pid17=2520 /opt/ltp/testcases/bin/ftrace_stress/ftrace_set_ftrace_filter.sh [ 37.455928] Scheduler tracepoints stat_sleep, stat_iowait, stat_blocked and stat_runtime require the kernel parameter schedstats=enable or kernel.sched_schedstats=1 Sep 23 18:30:46 intel-corei7-64 user.warn kernel: [ 37.455928] Scheduler tracepoints stat_sleep, stat_iowait, stat_blocked and stat_runtime require the kernel parameter schedstats=enable or kernel.sched_schedstats=1 Sep 23 18:30:46 intel-corei7-64 daemon.info avahi-daemon[2069]: Withdrawing address record for 10.66.17.129 on enp0s3. Sep 23 18:30:46 intel-corei7-64 daemon.warn avahi-daemon[2069]: Host name conflict, retrying with intel-corei7-74 Sep 23 18:30:46 intel-corei7-64 daemon.info avahi-daemon[2069]: Registering new address record for fe80::1b53:d658:9c7c:5b03 on enp0s3.*. Sep 23 18:30:46 intel-corei7-64 daemon.info avahi-daemon[2069]: Registering new address record for 10.66.17.129 on enp0s3.IPv4. [ 38.065573] cat[2507]: segfault at 0 ip 00007ff47cb93810 sp 00007fff74060ce8 error 14 [ 38.065833] sh[2519]: segfault at 0 ip 000000000042bc9e sp 00007fffeae3b3c0 error 7 [ 38.065894] in libc-2.27.so[7ff47cad2000+1aa000] [ 38.067380] cat[2532]: segfault at 0 ip 00007f5565234810 sp 00007fffcf0bb1b8 error 14 [ 38.067698] in bash.bash[400000+f3000] [ 38.068171] Code: 41 56 45 31 f6 41 55 41 54 41 bc c8 00 00 00 55 53 48 81 ec 68 0e 00 00 c7 05 8a 49 2d 00 00 00 00 00 48 8d ac 24 e0 01 00 00 <66> 89 74 24 50 48 8d 5c 24 50 48 89 6c 24 20 c7 05 99 49 2d 00 fe [ 38.069425] Code: Bad RIP value. [ 38.069821] klogd[2071]: segfault at 1ff ip 00007fc2806db17b sp 00007ffed1ee9f10 error 6 [ 38.070702] audit: type=1701 audit(1600885846.865:3): auid=4294967295 uid=0 gid=0 ses=4294967295 subj=kernel pid=2519 comm=\"sh\" exe=\"/bin/bash.bash\" sig=11 res=1 [ 38.071592] in libc-2.27.so[7f5565173000+1aa000] [ 38.072685] in libc-2.27.so[7fc28065c000+1aa000] [ 38.073082] Code: 48 29 d8 31 f6 48 8d 3c 19 49 39 d5 40 0f 95 c6 48 83 cb 01 48 83 c8 01 49 89 7d 60 48 c1 e6 02 48 89 da 48 09 f2 48 89 51 08 <48> 89 47 08 e9 95 fe ff ff 48 8d 3d 9d af 0f 00 e8 60 ca ff ff 48 [ 38.075649] audit: type=1701 audit(1600885846.868:4): auid=4294967295 uid=0 gid=0 ses=4294967295 subj=kernel pid=2071 comm=\"klogd\" exe=\"/bin/busybox.nosuid\" sig=11 res=1 [ 38.076574] Code: Bad RIP value. [ 38.079615] sh[2518]: segfault at ff ip 00007f580bee417b sp 00007ffce56b4180 error 6 in libc-2.27.so[7f580be65000+1aa000] [ 38.087568] Code: 48 29 d8 31 f6 48 8d 3c 19 49 39 d5 40 0f 95 c6 48 83 cb 01 48 83 c8 01 49 89 7d 60 48 c1 e6 02 48 89 da 48 09 f2 48 89 51 08 <48> 89 47 08 e9 95 fe ff ff 48 8d 3d 9d af 0f 00 e8 60 ca ff ff 48 [ 38.094737] cat[2699]: segfault at 0 ip 00007f1d6e9d6030 sp 00007ffdbad5e380 error 14 in ld-2.27.so[7f1d6e9d5000+25000] [ 38.097246] Code: Bad RIP value. [ 38.101982] audit: type=1701 audit(1600885846.898:6): auid=4294967295 uid=0 gid=0 ses=4294967295 subj=kernel pid=2532 comm=\"cat\" exe=\"/bin/cat.coreutils\" sig=11 res=1 [ 38.102536] Core dump to |/bin/false pipe failed [ 38.105603] Core dump to |/bin/false pipe failed ftrace_stack_max_size.sh: line 26: 2698 Segmentation fault cat \"$TRACING_PATH\"/stack_max_size > /dev/null ftrace_trace_pipe.sh: line 36: 2507 Segmentation fault (core dumped) cat \"$TRACING_PATH\"/trace_pipe > /dev/null ftrace_trace.sh: line 25: 2532 Segmentation fault (core dumped) cat \"$TRACING_PATH\"/trace > /dev/null ftrace_trace_stat.sh: line 44: 2699 Segmentation fault (core dumped) cat \"$TRACING_PATH\"/trace_stat/function${cpu} > /dev/null 2>&1 Sep 23 18:30:49 intel-corei7-64 daemon.info avahi-daemon[2069]: Server startup complete. Host name is intel-corei7-74.local. Local service cookie is 673226982. Sep 23 18:30:49 intel-corei7-64 daemon.info avahi-daemon[2069]: Service \"intel-corei7-74\" (/services/ssh.service) successfully established. Sep 23 18:30:49 intel-corei7-64 daemon.info avahi-daemon[2069]: Service \"intel-corei7-74\" (/services/sftp-ssh.service) successfully established. [ 48.755576] show_signal_msg: 4 callbacks suppressed [ 48.755753] sh[2912]: segfault at 1 ip 000000000047098f sp 00007ffe9f95d980 error 4 in bash.bash[400000+f3000] [ 48.760451] Code: 8b 41 20 8b 41 14 48 89 cf 4c 89 45 a8 44 8b 79 20 44 8b 71 08 89 43 14 e8 be 3b fc ff 4c 8b 45 a8 41 83 fc 13 77 34 44 89 e0 <ff> 24 c5 e0 fb 4b 00 66 2e 0f 1f 84 00 00 00 00 00 44 89 f7 e8 58 [ 48.769218] audit: type=1701 audit(1600885857.562:10): auid=4294967295 uid=0 gid=0 ses=4294967295 subj=kernel pid=2912 comm=\"sh\" exe=\"/bin/bash.bash\" sig=11 res=1 [ 48.774574] systemd[1]: segfault at 0 ip 00007fb40e076853 sp 00007ffeaa93ee50 error 7 in libsystemd-shared-237.so[7fb40df64000+1a3000] [ 48.779661] Code: 9b 63 05 00 e8 be b8 f2 ff 66 0f 1f 44 00 00 41 f6 44 24 28 1f 0f 85 84 04 00 00 41 8b 06 41 f6 44 24 29 01 0f 85 25 04 00 00 <41> 89 44 24 70 be 01 00 00 00 4c 89 e7 e8 0b b7 ff ff 85 c0 0f 88 [ 48.784452] ftrace_stress_t[2479]: segfault at 0 ip 0000000000446999 sp 00007ffeabb6ab00 error 7 in bash.bash[400000+f3000] [ 48.789662] Code: 90 48 8b 1b 48 85 db 0f 84 54 02 00 00 44 3b 6b 08 75 ee 8b 74 24 18 44 89 ef e8 42 eb fe ff 8b 44 24 18 31 d2 3d ff ff 00 00 <89> 43 0c 0f 94 c2 89 53 10 0f 84 68 02 00 00 8b 7c 24 1c 83 05 e5 [ 48.836666] Core dump to |/bin/false pipe failed [ 48.897839] systemd-journal[1442]: segfault at 24 ip 00007f2600e10913 sp 00007ffe69ebb798 error 6 in libc-2.27.so[7f2600cdf000+1aa000] [ 48.903524] Code: 47 d4 4c 89 4f dc 4c 89 57 e4 4c 89 5f ec 48 89 4f f4 89 57 fc c3 90 4c 8b 4e dc 4c 8b 56 e4 4c 8b 5e ec 48 8b 4e f4 8b 56 fc <4c> 89 4f dc 4c 89 57 e4 4c 89 5f ec 48 89 4f f4 89 57 fc c3 66 0f [ 48.918479] audit: type=1701 audit(1600885857.686:11): auid=4294967295 uid=0 gid=0 ses=4294967295 subj=kernel pid=2914 comm=\"systemd\" exe=\"/lib/systemd/systemd\" sig=11 res=1 [ 48.921093] audit: type=1701 audit(1600885857.705:12): auid=4294967295 uid=0 gid=0 ses=4294967295 subj=kernel pid=1442 comm=\"systemd-journal\" exe=\"/lib/systemd/systemd-journald\" sig=11 res=1 [ 48.927551] audit: type=1701 audit(1600885857.723:13): auid=4294967295 uid=0 gid=0 ses=4294967295 subj=kernel pid=2479 comm=\"ftrace_stress_t\" exe=\"/bin/bash.bash\" sig=11 res=1 ftrace_stack_trace.sh: line 35: 2912 Segmentation fault cat \"$TRACING_PATH\"/stack_trace > /dev/null [ 49.101773] (agetty): 41 output lines suppressed due to ratelimiting [ 49.382601] systemd[2806]: serial-getty(a)ttyS1.service: Failed to connect stdout to the journal socket, ignoring: Connection refused Sep 23 18:30:58 intel-corei7-64 authpriv.err agetty[2805]: /dev/ttyS2: not a tty Sep 23 18:30:58 intel-corei7-64 authpriv.err agetty[2806]: /dev/ttyS1: not a tty [ 49.707082] audit: type=1701 audit(1600885858.503:14): auid=4294967295 uid=0 gid=0 ses=4294967295 subj=kernel pid=2919 comm=\"dynamic_debug01\" exe=\"/bin/bash.bash\" sig=11 res=1 [ 49.707084] ltp-pan[2314]: segfault at 1 ip 00000000004037b0 sp 00007ffeb10df110 error 7 in ltp-pan[400000+7000] [ 49.711151] Code: e8 c5 e0 ff ff 48 85 c0 0f 85 9a 04 00 00 8b bc 24 d8 00 00 00 e8 80 e0 ff ff 83 7c 24 38 00 74 09 8b 7c 24 30 e8 70 e0 ff ff <44> 89 2b 48 8b 3d 5e 4b 20 00 44 89 ee c7 43 04 00 00 00 00 49 8b [ 49.715540] Core dump to |/bin/false pipe failed [ 49.718565] Core dump to |/bin/false pipe failed [ 49.722630] Core dump to |/bin/false pipe failed [ 49.805761] Core dump to |/bin/false pipe failed [ 49.807855] Core dump to |/bin/false pipe failed [ 49.810211] Core dump to |/bin/false pipe failed [ 49.812494] Core dump to |/bin/false pipe failed [ 49.815536] Core dump to |/bin/false pipe failed [ 49.818732] Core dump to |/bin/false pipe failed [ 49.822770] Core dump to |/bin/false pipe failed [ 49.826468] Core dump to |/bin/false pipe failed [ 49.830480] Core dump to |/bin/false pipe failed [ 50.651176] avahi-daemon (2069) used greatest stack depth: 12184 bytes left [ 74.858293] show_signal_msg: 22 callbacks suppressed [ 74.858310] dbus-daemon[2096]: segfault at 1ff ip 00007f86246c717b sp 00007ffc0e7b6b40 error 6 in libc-2.27.so[7f8624648000+1aa000] [ 74.859556] systemd-logind[2074]: Failed to abandon session scope, ignoring: Connection timed out [ 74.860273] Code: 48 29 d8 31 f6 48 8d 3c 19 49 39 d5 40 0f 95 c6 48 83 cb 01 48 83 c8 01 49 89 7d 60 48 c1 e6 02 48 89 da 48 09 f2 48 89 51 08 <48> 89 47 08 e9 95 fe ff ff 48 8d 3d 9d af 0f 00 e8 60 ca ff ff 48 [ 74.871558] audit: type=1701 audit(1600885883.668:28): auid=4294967295 uid=996 gid=994 ses=4294967295 subj=kernel pid=2096 comm=\"dbus-daemon\" exe=\"/usr/bin/dbus-daemon\" sig=11 res=1 Sep 23 18:31:23 intel-corei7-64 [ 74.877646] NetworkManager[2098]: segfault at 0 ip 00007fe5d0fb30d5 sp 00007fff3c9695e0 error 7 in libc-2.27.so[7fe5d0f36000+1aa000] authpriv.notice polkitd[2161]: Lost the name org[ 74.881756] Code: 4c 0f be 04 0e 4c 3b 05 29 02 33 00 4c 89 c7 73 34 48 83 f9 3f 0f 87 ea 03 00 00 48 8d 04 ce 49 83 c4 10 83 c7 01 48 8b 50 40 <49> 89 14 24 4c 89 60 40 40 88 3c 0e 48 83 c4 48 5b 5d 41 5c 41 5d .freedesktop.PolicyKit1 - exiting[ 74.887291] audit: type=1701 audit(1600885883.684:29): auid=4294967295 uid=0 gid=0 ses=4294967295 subj=kernel pid=2098 comm=\"NetworkManager\" exe=\"/usr/sbin/NetworkManager\" sig=11 res=1 [ 74.891439] Core dump to |/bin/false pipe failed [ 74.896814] NetworkManager (2098) used greatest stack depth: 11912 bytes left [ 258.966773] isc-worker0000[2169]: segfault at 4 ip 000000000043bc05 sp 00007f59aab33c78 error 7 in dhclient[400000+5b000] [ 258.969115] Code: 00 00 00 00 00 b8 03 00 06 00 48 85 ff 74 0b 48 85 f6 74 06 48 83 3f 00 74 0b c3 66 2e 0f 1f 84 00 00 00 00 00 48 89 37 31 c0 <83> 46 1c 01 c3 66 0f 1f 44 00 00 e9 cb 7d fc ff 90 66 2e 0f 1f 84 [ 258.972803] audit: type=1701 audit(1600886067.769:30): auid=4294967295 uid=0 gid=0 ses=4294967295 subj=kernel pid=2162 comm=\"isc-worker0000\" exe=\"/sbin/dhclient\" sig=11 res=1 [ 258.975070] Core dump to |/bin/false pipe failed [ 353.027171] kworker/dying (1398) used greatest stack depth: 11904 bytes left Full test log links, [1] https://lkft.validation.linaro.org/scheduler/job/1784423#L1656 [2] https://lkft.validation.linaro.org/scheduler/job/1784270#L1582 The git bisect confirms the first bad patch to cause these problems. --- commit c3bc8fd637a9623f5c507bd18f9677effbddf584 Author: Joel Fernandes (Google) <joel(a)joelfernandes.org> Date: Mon Jul 30 15:24:23 2018 -0700 tracing: Centralize preemptirq tracepoints and unify their usage This patch detaches the preemptirq tracepoints from the tracers and keeps it separate. Advantages: * Lockdep and irqsoff event can now run in parallel since they no longer have their own calls. * This unifies the usecase of adding hooks to an irqsoff and irqson event, and a preemptoff and preempton event. 3 users of the events exist: - Lockdep - irqsoff and preemptoff tracers - irqs and preempt trace events The unification cleans up several ifdefs and makes the code in preempt tracer and irqsoff tracers simpler. It gets rid of all the horrific ifdeferry around PROVE_LOCKING and makes configuration of the different users of the tracepoints more easy and understandable. It also gets rid of the time_* function calls from the lockdep hooks used to call into the preemptirq tracer which is not needed anymore. The negative delta in lines of code in this patch is quite large too. In the patch we introduce a new CONFIG option PREEMPTIRQ_TRACEPOINTS as a single point for registering probes onto the tracepoints. With this, the web of config options for preempt/irq toggle tracepoints and its users becomes: PREEMPT_TRACER PREEMPTIRQ_EVENTS IRQSOFF_TRACER PROVE_LOCKING | | \ | | \ (selects) / \ \ (selects) / TRACE_PREEMPT_TOGGLE ----> TRACE_IRQFLAGS \ / \ (depends on) / PREEMPTIRQ_TRACEPOINTS Other than the performance tests mentioned in the previous patch, I also ran the locking API test suite. I verified that all tests cases are passing. I also injected issues by not registering lockdep probes onto the tracepoints and I see failures to confirm that the probes are indeed working. This series + lockdep probes not registered (just to inject errors): [ 0.000000] hard-irqs-on + irq-safe-A/21: ok | ok | ok | [ 0.000000] soft-irqs-on + irq-safe-A/21: ok | ok | ok | [ 0.000000] sirq-safe-A => hirqs-on/12:FAILED|FAILED| ok | [ 0.000000] sirq-safe-A => hirqs-on/21:FAILED|FAILED| ok | [ 0.000000] hard-safe-A + irqs-on/12:FAILED|FAILED| ok | [ 0.000000] soft-safe-A + irqs-on/12:FAILED|FAILED| ok | [ 0.000000] hard-safe-A + irqs-on/21:FAILED|FAILED| ok | [ 0.000000] soft-safe-A + irqs-on/21:FAILED|FAILED| ok | [ 0.000000] hard-safe-A + unsafe-B #1/123: ok | ok | ok | [ 0.000000] soft-safe-A + unsafe-B #1/123: ok | ok | ok | With this series + lockdep probes registered, all locking tests pass: [ 0.000000] hard-irqs-on + irq-safe-A/21: ok | ok | ok | [ 0.000000] soft-irqs-on + irq-safe-A/21: ok | ok | ok | [ 0.000000] sirq-safe-A => hirqs-on/12: ok | ok | ok | [ 0.000000] sirq-safe-A => hirqs-on/21: ok | ok | ok | [ 0.000000] hard-safe-A + irqs-on/12: ok | ok | ok | [ 0.000000] soft-safe-A + irqs-on/12: ok | ok | ok | [ 0.000000] hard-safe-A + irqs-on/21: ok | ok | ok | [ 0.000000] soft-safe-A + irqs-on/21: ok | ok | ok | [ 0.000000] hard-safe-A + unsafe-B #1/123: ok | ok | ok | [ 0.000000] soft-safe-A + unsafe-B #1/123: ok | ok | ok | Link: http://lkml.kernel.org/r/20180730222423.196630-4-joel@joelfernandes.org Acked-by: Peter Zijlstra (Intel) <peterz(a)infradead.org> Reviewed-by: Namhyung Kim <namhyung(a)kernel.org> Signed-off-by: Joel Fernandes (Google) <joel(a)joelfernandes.org> Signed-off-by: Steven Rostedt (VMware) <rostedt(a)goodmis.org> include/linux/ftrace.h | 11 +- include/linux/irqflags.h | 11 +- include/linux/lockdep.h | 8 +- include/linux/preempt.h | 2 +- include/trace/events/preemptirq.h | 23 ++-- init/main.c | 5 +- kernel/locking/lockdep.c | 35 +++--- kernel/sched/core.c | 2 +- kernel/trace/Kconfig | 22 +++- kernel/trace/Makefile | 2 +- kernel/trace/trace_irqsoff.c | 231 ++++++++++---------------------------- kernel/trace/trace_preemptirq.c | 72 ++++++++++++ 12 files changed, 195 insertions(+), 229 deletions(-) create mode 100644 kernel/trace/trace_preemptirq.c -- Linaro LKFT https://lkft.linaro.org

5 years

3
8
0 0

[PATCH] btrfs: workaround the over-confident over-commit available space calculation

by Qu Wenruo

[BUG] There are quite some bug reports of btrfs falling into a ENOSPC trap, where btrfs can't even start a transaction to add new devices. [CAUSE] Most of the reports are utilize multi-device profiles, like RAID1/RAID10/RAID5/RAID6, and the involved disks have very unbalanced sizes. It turns out that, the overcommit calculation in btrfs_can_overcommit() is just a factor based calculation, which can't check if devices can really fulfill the requirement for the desired profile. This makes btrfs_can_overcommit() to be always over-confident about usable space, and when we can't allocate any new metadata chunk but still allow new metadata operations, we fall into the ENOSPC trap and have no way to exit it. [WORKAROUND] The root fix needs a device layout aware, chunk allocator like available space calculation. There used to be such patchset submitted to the mail list, but the extra failure mode is tricky to handle for chunk allocation, thus that patchset needs more time to mature. Meanwhile to prevent such problems reaching more users, workaround the problem by: - Half the over-commit available space reported So that we won't always be that over-confident. But this won't really help if we have extremely unbalanced disk size. - Don't over-commit if the space info is already full This may already be too late, but still better than doing nothing and believe the over-commit values. CC: stable(a)vger.kernel.org # 4.4+ Signed-off-by: Qu Wenruo <wqu(a)suse.com> --- fs/btrfs/space-info.c | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) diff --git a/fs/btrfs/space-info.c b/fs/btrfs/space-info.c index 475968ccbd1d..e8133ec7e34a 100644 --- a/fs/btrfs/space-info.c +++ b/fs/btrfs/space-info.c @@ -339,6 +339,18 @@ static u64 calc_available_free_space(struct btrfs_fs_info *fs_info, avail >>= 3; else avail >>= 1; + /* + * Since current over-commit calculation is doomed already for + * RAID0/RADI1/RAID10/RAID5/6, we half the availabe space to reduce + * over-commit amount. + * + * This is just a workaround before the device layout aware + * available space calculation arrives. + */ + if ((BTRFS_BLOCK_GROUP_RAID0 | BTRFS_BLOCK_GROUP_RAID1_MASK | + BTRFS_BLOCK_GROUP_RAID10 | BTRFS_BLOCK_GROUP_RAID56_MASK) & + profile) + avail >>= 1; return avail; } @@ -353,6 +365,14 @@ int btrfs_can_overcommit(struct btrfs_fs_info *fs_info, if (space_info->flags & BTRFS_BLOCK_GROUP_DATA) return 0; + /* + * If we can't allocate new space already, no overcommit is allowed. + * + * This check may be already late, but still better than nothing. + */ + if (space_info->full) + return 0; + used = btrfs_space_info_used(space_info, true); avail = calc_available_free_space(fs_info, space_info, flush); -- 2.28.0

5 years

3
3
0 0

[PATCH 1/2] mm: replace memmap_context by memplug_context

by Laurent Dufour

Backport version to the 4.19-stable tree of: [ Upstream commit c1d0da83358a2316d9be7f229f26126dbaa07468 ] Patch series "mm: fix memory to node bad links in sysfs", v3. Sometimes, firmware may expose interleaved memory layout like this: Early memory node ranges node 1: [mem 0x0000000000000000-0x000000011fffffff] node 2: [mem 0x0000000120000000-0x000000014fffffff] node 1: [mem 0x0000000150000000-0x00000001ffffffff] node 0: [mem 0x0000000200000000-0x000000048fffffff] node 2: [mem 0x0000000490000000-0x00000007ffffffff] In that case, we can see memory blocks assigned to multiple nodes in sysfs: $ ls -l /sys/devices/system/memory/memory21 total 0 lrwxrwxrwx 1 root root 0 Aug 24 05:27 node1 -> ../../node/node1 lrwxrwxrwx 1 root root 0 Aug 24 05:27 node2 -> ../../node/node2 -rw-r--r-- 1 root root 65536 Aug 24 05:27 online -r--r--r-- 1 root root 65536 Aug 24 05:27 phys_device -r--r--r-- 1 root root 65536 Aug 24 05:27 phys_index drwxr-xr-x 2 root root 0 Aug 24 05:27 power -r--r--r-- 1 root root 65536 Aug 24 05:27 removable -rw-r--r-- 1 root root 65536 Aug 24 05:27 state lrwxrwxrwx 1 root root 0 Aug 24 05:25 subsystem -> ../../../../bus/memory -rw-r--r-- 1 root root 65536 Aug 24 05:25 uevent -r--r--r-- 1 root root 65536 Aug 24 05:27 valid_zones The same applies in the node's directory with a memory21 link in both the node1 and node2's directory. This is wrong but doesn't prevent the system to run. However when later, one of these memory blocks is hot-unplugged and then hot-plugged, the system is detecting an inconsistency in the sysfs layout and a BUG_ON() is raised: kernel BUG at /Users/laurent/src/linux-ppc/mm/memory_hotplug.c:1084! LE PAGE_SIZE=64K MMU=Hash SMP NR_CPUS=2048 NUMA pSeries Modules linked in: rpadlpar_io rpaphp pseries_rng rng_core vmx_crypto gf128mul binfmt_misc ip_tables x_tables xfs libcrc32c crc32c_vpmsum autofs4 CPU: 8 PID: 10256 Comm: drmgr Not tainted 5.9.0-rc1+ #25 Call Trace: add_memory_resource+0x23c/0x340 (unreliable) __add_memory+0x5c/0xf0 dlpar_add_lmb+0x1b4/0x500 dlpar_memory+0x1f8/0xb80 handle_dlpar_errorlog+0xc0/0x190 dlpar_store+0x198/0x4a0 kobj_attr_store+0x30/0x50 sysfs_kf_write+0x64/0x90 kernfs_fop_write+0x1b0/0x290 vfs_write+0xe8/0x290 ksys_write+0xdc/0x130 system_call_exception+0x160/0x270 system_call_common+0xf0/0x27c This has been seen on PowerPC LPAR. The root cause of this issue is that when node's memory is registered, the range used can overlap another node's range, thus the memory block is registered to multiple nodes in sysfs. There are two issues here: (a) The sysfs memory and node's layouts are broken due to these multiple links (b) The link errors in link_mem_sections() should not lead to a system panic. To address (a) register_mem_sect_under_node should not rely on the system state to detect whether the link operation is triggered by a hot plug operation or not. This is addressed by the patches 1 and 2 of this series. Issue (b) will be addressed separately. This patch (of 2): The memmap_context enum is used to detect whether a memory operation is due to a hot-add operation or happening at boot time. Make it general to the hotplug operation and rename it as meminit_context. There is no functional change introduced by this patch Suggested-by: David Hildenbrand <david(a)redhat.com> Signed-off-by: Laurent Dufour <ldufour(a)linux.ibm.com> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> Reviewed-by: David Hildenbrand <david(a)redhat.com> Reviewed-by: Oscar Salvador <osalvador(a)suse.de> Acked-by: Michal Hocko <mhocko(a)suse.com> Cc: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Cc: "Rafael J . Wysocki" <rafael(a)kernel.org> Cc: Nathan Lynch <nathanl(a)linux.ibm.com> Cc: Scott Cheloha <cheloha(a)linux.ibm.com> Cc: Tony Luck <tony.luck(a)intel.com> Cc: Fenghua Yu <fenghua.yu(a)intel.com> Cc: <stable(a)vger.kernel.org> # 4.19.y Link: https://lkml.kernel.org/r/20200915094143.79181-1-ldufour@linux.ibm.com Link: https://lkml.kernel.org/r/20200915132624.9723-1-ldufour@linux.ibm.com Signed-off-by: Linus Torvalds <torvalds(a)linux-foundation.org> --- arch/ia64/mm/init.c | 6 +++--- include/linux/mm.h | 2 +- include/linux/mmzone.h | 11 ++++++++--- mm/memory_hotplug.c | 2 +- mm/page_alloc.c | 11 ++++++----- 5 files changed, 19 insertions(+), 13 deletions(-) diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c index 79e5cc70f1fd..561e2573bd34 100644 --- a/arch/ia64/mm/init.c +++ b/arch/ia64/mm/init.c @@ -499,7 +499,7 @@ virtual_memmap_init(u64 start, u64 end, void *arg) if (map_start < map_end) memmap_init_zone((unsigned long)(map_end - map_start), args->nid, args->zone, page_to_pfn(map_start), - MEMMAP_EARLY, NULL); + MEMINIT_EARLY, NULL); return 0; } @@ -508,8 +508,8 @@ memmap_init (unsigned long size, int nid, unsigned long zone, unsigned long start_pfn) { if (!vmem_map) { - memmap_init_zone(size, nid, zone, start_pfn, MEMMAP_EARLY, - NULL); + memmap_init_zone(size, nid, zone, start_pfn, + MEMINIT_EARLY, NULL); } else { struct page *start; struct memmap_init_callback_data args; diff --git a/include/linux/mm.h b/include/linux/mm.h index 05bc5f25ab85..83828c118b6b 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2179,7 +2179,7 @@ static inline void zero_resv_unavail(void) {} extern void set_dma_reserve(unsigned long new_dma_reserve); extern void memmap_init_zone(unsigned long, int, unsigned long, unsigned long, - enum memmap_context, struct vmem_altmap *); + enum meminit_context, struct vmem_altmap *); extern void setup_per_zone_wmarks(void); extern int __meminit init_per_zone_wmark_min(void); extern void mem_init(void); diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index fdd93a39f1fa..fa02014eba8e 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -759,10 +759,15 @@ bool zone_watermark_ok(struct zone *z, unsigned int order, unsigned int alloc_flags); bool zone_watermark_ok_safe(struct zone *z, unsigned int order, unsigned long mark, int classzone_idx); -enum memmap_context { - MEMMAP_EARLY, - MEMMAP_HOTPLUG, +/* + * Memory initialization context, use to differentiate memory added by + * the platform statically or via memory hotplug interface. + */ +enum meminit_context { + MEMINIT_EARLY, + MEMINIT_HOTPLUG, }; + extern void init_currently_empty_zone(struct zone *zone, unsigned long start_pfn, unsigned long size); diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index aae7ff485671..c839c4ad4871 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -733,7 +733,7 @@ void __ref move_pfn_range_to_zone(struct zone *zone, unsigned long start_pfn, * are reserved so nobody should be touching them so we should be safe */ memmap_init_zone(nr_pages, nid, zone_idx(zone), start_pfn, - MEMMAP_HOTPLUG, altmap); + MEMINIT_HOTPLUG, altmap); set_zone_contiguous(zone); } diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 5717ee66c8b3..545800433dfb 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -5480,7 +5480,7 @@ void __ref build_all_zonelists(pg_data_t *pgdat) * done. Non-atomic initialization, single-pass. */ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone, - unsigned long start_pfn, enum memmap_context context, + unsigned long start_pfn, enum meminit_context context, struct vmem_altmap *altmap) { unsigned long end_pfn = start_pfn + size; @@ -5507,7 +5507,7 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone, * There can be holes in boot-time mem_map[]s handed to this * function. They do not exist on hotplugged memory. */ - if (context != MEMMAP_EARLY) + if (context != MEMINIT_EARLY) goto not_early; if (!early_pfn_valid(pfn)) @@ -5542,7 +5542,7 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone, not_early: page = pfn_to_page(pfn); __init_single_page(page, pfn, zone, nid); - if (context == MEMMAP_HOTPLUG) + if (context == MEMINIT_HOTPLUG) SetPageReserved(page); /* @@ -5557,7 +5557,7 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone, * check here not to call set_pageblock_migratetype() against * pfn out of zone. * - * Please note that MEMMAP_HOTPLUG path doesn't clear memmap + * Please note that MEMINIT_HOTPLUG path doesn't clear memmap * because this is done early in sparse_add_one_section */ if (!(pfn & (pageblock_nr_pages - 1))) { @@ -5578,7 +5578,8 @@ static void __meminit zone_init_free_lists(struct zone *zone) #ifndef __HAVE_ARCH_MEMMAP_INIT #define memmap_init(size, nid, zone, start_pfn) \ - memmap_init_zone((size), (nid), (zone), (start_pfn), MEMMAP_EARLY, NULL) + memmap_init_zone((size), (nid), (zone), (start_pfn), \ + MEMINIT_EARLY, NULL) #endif static int zone_batchsize(struct zone *zone) -- 2.28.0

5 years

2
2
0 0

block/diskstats: more accurate approximation of io_ticks for slow disks

by Banerjee, Debabrata

commit: 2b8bd423614c595540eaadcfbc702afe8e155e50 Please apply to linux-5.4.y. Without this fix, disk utilization reporting is unusable, especially on spinning disks. Thanks, Deb

5 years

2
1
0 0

FAILED: patch "[PATCH] scsi: sd: sd_zbc: Fix handling of host-aware ZBC disks" failed to apply to 5.8-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.8-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>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 27ba3e8ff3ab86449e63d38a8d623053591e65fa Mon Sep 17 00:00:00 2001 From: Damien Le Moal <damien.lemoal(a)wdc.com> Date: Tue, 15 Sep 2020 16:33:46 +0900 Subject: [PATCH] scsi: sd: sd_zbc: Fix handling of host-aware ZBC disks When CONFIG_BLK_DEV_ZONED is disabled, allow using host-aware ZBC disks as regular disks. In this case, ensure that command completion is correctly executed by changing sd_zbc_complete() to return good_bytes instead of 0 and causing a hang during device probe (endless retries). When CONFIG_BLK_DEV_ZONED is enabled and a host-aware disk is detected to have partitions, it will be used as a regular disk. In this case, make sure to not do anything in sd_zbc_revalidate_zones() as that triggers warnings. Since all these different cases result in subtle settings of the disk queue zoned model, introduce the block layer helper function blk_queue_set_zoned() to generically implement setting up the effective zoned model according to the disk type, the presence of partitions on the disk and CONFIG_BLK_DEV_ZONED configuration. Link: https://lore.kernel.org/r/20200915073347.832424-2-damien.lemoal@wdc.com Fixes: b72053072c0b ("block: allow partitions on host aware zone devices") Cc: <stable(a)vger.kernel.org> Reported-by: Borislav Petkov <bp(a)alien8.de> Suggested-by: Christoph Hellwig <hch(a)infradead.org> Reviewed-by: Christoph Hellwig <hch(a)lst.de> Reviewed-by: Johannes Thumshirn <johannes.thumshirn(a)wdc.com> Signed-off-by: Damien Le Moal <damien.lemoal(a)wdc.com> Signed-off-by: Martin K. Petersen <martin.petersen(a)oracle.com> diff --git a/block/blk-settings.c b/block/blk-settings.c index 76a7e03bcd6c..34b721a2743a 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -801,6 +801,52 @@ bool blk_queue_can_use_dma_map_merging(struct request_queue *q, } EXPORT_SYMBOL_GPL(blk_queue_can_use_dma_map_merging); +/** + * blk_queue_set_zoned - configure a disk queue zoned model. + * @disk: the gendisk of the queue to configure + * @model: the zoned model to set + * + * Set the zoned model of the request queue of @disk according to @model. + * When @model is BLK_ZONED_HM (host managed), this should be called only + * if zoned block device support is enabled (CONFIG_BLK_DEV_ZONED option). + * If @model specifies BLK_ZONED_HA (host aware), the effective model used + * depends on CONFIG_BLK_DEV_ZONED settings and on the existence of partitions + * on the disk. + */ +void blk_queue_set_zoned(struct gendisk *disk, enum blk_zoned_model model) +{ + switch (model) { + case BLK_ZONED_HM: + /* + * Host managed devices are supported only if + * CONFIG_BLK_DEV_ZONED is enabled. + */ + WARN_ON_ONCE(!IS_ENABLED(CONFIG_BLK_DEV_ZONED)); + break; + case BLK_ZONED_HA: + /* + * Host aware devices can be treated either as regular block + * devices (similar to drive managed devices) or as zoned block + * devices to take advantage of the zone command set, similarly + * to host managed devices. We try the latter if there are no + * partitions and zoned block device support is enabled, else + * we do nothing special as far as the block layer is concerned. + */ + if (!IS_ENABLED(CONFIG_BLK_DEV_ZONED) || + disk_has_partitions(disk)) + model = BLK_ZONED_NONE; + break; + case BLK_ZONED_NONE: + default: + if (WARN_ON_ONCE(model != BLK_ZONED_NONE)) + model = BLK_ZONED_NONE; + break; + } + + disk->queue->limits.zoned = model; +} +EXPORT_SYMBOL_GPL(blk_queue_set_zoned); + static int __init blk_settings_init(void) { blk_max_low_pfn = max_low_pfn - 1; diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index 95018e650f2d..06286b6aeaec 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -2964,26 +2964,32 @@ static void sd_read_block_characteristics(struct scsi_disk *sdkp) if (sdkp->device->type == TYPE_ZBC) { /* Host-managed */ - q->limits.zoned = BLK_ZONED_HM; + blk_queue_set_zoned(sdkp->disk, BLK_ZONED_HM); } else { sdkp->zoned = (buffer[8] >> 4) & 3; - if (sdkp->zoned == 1 && !disk_has_partitions(sdkp->disk)) { + if (sdkp->zoned == 1) { /* Host-aware */ - q->limits.zoned = BLK_ZONED_HA; + blk_queue_set_zoned(sdkp->disk, BLK_ZONED_HA); } else { - /* - * Treat drive-managed devices and host-aware devices - * with partitions as regular block devices. - */ - q->limits.zoned = BLK_ZONED_NONE; - if (sdkp->zoned == 2 && sdkp->first_scan) - sd_printk(KERN_NOTICE, sdkp, - "Drive-managed SMR disk\n"); + /* Regular disk or drive managed disk */ + blk_queue_set_zoned(sdkp->disk, BLK_ZONED_NONE); } } - if (blk_queue_is_zoned(q) && sdkp->first_scan) + + if (!sdkp->first_scan) + goto out; + + if (blk_queue_is_zoned(q)) { sd_printk(KERN_NOTICE, sdkp, "Host-%s zoned block device\n", q->limits.zoned == BLK_ZONED_HM ? "managed" : "aware"); + } else { + if (sdkp->zoned == 1) + sd_printk(KERN_NOTICE, sdkp, + "Host-aware SMR disk used as regular disk\n"); + else if (sdkp->zoned == 2) + sd_printk(KERN_NOTICE, sdkp, + "Drive-managed SMR disk\n"); + } out: kfree(buffer); diff --git a/drivers/scsi/sd.h b/drivers/scsi/sd.h index 4933e7daf17d..7251434100e6 100644 --- a/drivers/scsi/sd.h +++ b/drivers/scsi/sd.h @@ -259,7 +259,7 @@ static inline blk_status_t sd_zbc_setup_zone_mgmt_cmnd(struct scsi_cmnd *cmd, static inline unsigned int sd_zbc_complete(struct scsi_cmnd *cmd, unsigned int good_bytes, struct scsi_sense_hdr *sshdr) { - return 0; + return good_bytes; } static inline blk_status_t sd_zbc_prepare_zone_append(struct scsi_cmnd *cmd, diff --git a/drivers/scsi/sd_zbc.c b/drivers/scsi/sd_zbc.c index 0e94ff056bff..a739456dea02 100644 --- a/drivers/scsi/sd_zbc.c +++ b/drivers/scsi/sd_zbc.c @@ -667,7 +667,11 @@ int sd_zbc_revalidate_zones(struct scsi_disk *sdkp) u32 max_append; int ret = 0; - if (!sd_is_zoned(sdkp)) + /* + * There is nothing to do for regular disks, including host-aware disks + * that have partitions. + */ + if (!blk_queue_is_zoned(q)) return 0; /* diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index bb5636cc17b9..868e11face00 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -352,6 +352,8 @@ struct queue_limits { typedef int (*report_zones_cb)(struct blk_zone *zone, unsigned int idx, void *data); +void blk_queue_set_zoned(struct gendisk *disk, enum blk_zoned_model model); + #ifdef CONFIG_BLK_DEV_ZONED #define BLK_ALL_ZONES ((unsigned int)-1)

5 years

3
2
0 0

patch "usb: cdc-acm: add quirk to blacklist ETAS ES58X devices" added to usb-testing

by gregkh＠linuxfoundation.org

This is a note to let you know that I've just added the patch titled usb: cdc-acm: add quirk to blacklist ETAS ES58X devices to my usb git tree which can be found at git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/usb.git in the usb-testing branch. The patch will show up in the next release of the linux-next tree (usually sometime within the next 24 hours during the week.) The patch will be merged to the usb-next branch sometime soon, after it passes testing, and the merge window is open. If you have any questions about this process, please let me know. >From a4f88430af896bf34ec25a7a5f0e053fb3d928e0 Mon Sep 17 00:00:00 2001 From: Vincent Mailhol <mailhol.vincent(a)wanadoo.fr> Date: Sat, 3 Oct 2020 00:41:51 +0900 Subject: usb: cdc-acm: add quirk to blacklist ETAS ES58X devices The ES58X devices has a CDC ACM interface (used for debug purpose). During probing, the device is thus recognized as USB Modem (CDC ACM), preventing the etas-es58x module to load: usbcore: registered new interface driver etas_es58x usb 1-1.1: new full-speed USB device number 14 using xhci_hcd usb 1-1.1: New USB device found, idVendor=108c, idProduct=0159, bcdDevice= 1.00 usb 1-1.1: New USB device strings: Mfr=1, Product=2, SerialNumber=3 usb 1-1.1: Product: ES581.4 usb 1-1.1: Manufacturer: ETAS GmbH usb 1-1.1: SerialNumber: 2204355 cdc_acm 1-1.1:1.0: No union descriptor, testing for castrated device cdc_acm 1-1.1:1.0: ttyACM0: USB ACM device Thus, these have been added to the ignore list in drivers/usb/class/cdc-acm.c N.B. Future firmware release of the ES58X will remove the CDC-ACM interface. `lsusb -v` of the three devices variant (ES581.4, ES582.1 and ES584.1): Bus 001 Device 011: ID 108c:0159 Robert Bosch GmbH ES581.4 Device Descriptor: bLength 18 bDescriptorType 1 bcdUSB 1.10 bDeviceClass 2 Communications bDeviceSubClass 0 bDeviceProtocol 0 bMaxPacketSize0 64 idVendor 0x108c Robert Bosch GmbH idProduct 0x0159 bcdDevice 1.00 iManufacturer 1 ETAS GmbH iProduct 2 ES581.4 iSerial 3 2204355 bNumConfigurations 1 Configuration Descriptor: bLength 9 bDescriptorType 2 wTotalLength 0x0035 bNumInterfaces 1 bConfigurationValue 1 iConfiguration 5 Bus Powered Configuration bmAttributes 0x80 (Bus Powered) MaxPower 100mA Interface Descriptor: bLength 9 bDescriptorType 4 bInterfaceNumber 0 bAlternateSetting 0 bNumEndpoints 3 bInterfaceClass 2 Communications bInterfaceSubClass 2 Abstract (modem) bInterfaceProtocol 0 iInterface 4 ACM Control Interface CDC Header: bcdCDC 1.10 CDC Call Management: bmCapabilities 0x01 call management bDataInterface 0 CDC ACM: bmCapabilities 0x06 sends break line coding and serial state Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x81 EP 1 IN bmAttributes 3 Transfer Type Interrupt Synch Type None Usage Type Data wMaxPacketSize 0x0010 1x 16 bytes bInterval 10 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x82 EP 2 IN bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0040 1x 64 bytes bInterval 0 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x03 EP 3 OUT bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0040 1x 64 bytes bInterval 0 Device Status: 0x0000 (Bus Powered) Bus 001 Device 012: ID 108c:0168 Robert Bosch GmbH ES582 Device Descriptor: bLength 18 bDescriptorType 1 bcdUSB 2.00 bDeviceClass 2 Communications bDeviceSubClass 0 bDeviceProtocol 0 bMaxPacketSize0 64 idVendor 0x108c Robert Bosch GmbH idProduct 0x0168 bcdDevice 1.00 iManufacturer 1 ETAS GmbH iProduct 2 ES582 iSerial 3 0108933 bNumConfigurations 1 Configuration Descriptor: bLength 9 bDescriptorType 2 wTotalLength 0x0043 bNumInterfaces 2 bConfigurationValue 1 iConfiguration 0 bmAttributes 0x80 (Bus Powered) MaxPower 500mA Interface Descriptor: bLength 9 bDescriptorType 4 bInterfaceNumber 0 bAlternateSetting 0 bNumEndpoints 1 bInterfaceClass 2 Communications bInterfaceSubClass 2 Abstract (modem) bInterfaceProtocol 1 AT-commands (v.25ter) iInterface 0 CDC Header: bcdCDC 1.10 CDC ACM: bmCapabilities 0x02 line coding and serial state CDC Union: bMasterInterface 0 bSlaveInterface 1 CDC Call Management: bmCapabilities 0x03 call management use DataInterface bDataInterface 1 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x83 EP 3 IN bmAttributes 3 Transfer Type Interrupt Synch Type None Usage Type Data wMaxPacketSize 0x0040 1x 64 bytes bInterval 16 Interface Descriptor: bLength 9 bDescriptorType 4 bInterfaceNumber 1 bAlternateSetting 0 bNumEndpoints 2 bInterfaceClass 10 CDC Data bInterfaceSubClass 0 bInterfaceProtocol 0 iInterface 0 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x81 EP 1 IN bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0200 1x 512 bytes bInterval 0 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x02 EP 2 OUT bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0200 1x 512 bytes bInterval 0 Device Qualifier (for other device speed): bLength 10 bDescriptorType 6 bcdUSB 2.00 bDeviceClass 2 Communications bDeviceSubClass 0 bDeviceProtocol 0 bMaxPacketSize0 64 bNumConfigurations 1 Device Status: 0x0000 (Bus Powered) Bus 001 Device 013: ID 108c:0169 Robert Bosch GmbH ES584.1 Device Descriptor: bLength 18 bDescriptorType 1 bcdUSB 2.00 bDeviceClass 2 Communications bDeviceSubClass 0 bDeviceProtocol 0 bMaxPacketSize0 64 idVendor 0x108c Robert Bosch GmbH idProduct 0x0169 bcdDevice 1.00 iManufacturer 1 ETAS GmbH iProduct 2 ES584.1 iSerial 3 0100320 bNumConfigurations 1 Configuration Descriptor: bLength 9 bDescriptorType 2 wTotalLength 0x0043 bNumInterfaces 2 bConfigurationValue 1 iConfiguration 0 bmAttributes 0x80 (Bus Powered) MaxPower 500mA Interface Descriptor: bLength 9 bDescriptorType 4 bInterfaceNumber 0 bAlternateSetting 0 bNumEndpoints 1 bInterfaceClass 2 Communications bInterfaceSubClass 2 Abstract (modem) bInterfaceProtocol 1 AT-commands (v.25ter) iInterface 0 CDC Header: bcdCDC 1.10 CDC ACM: bmCapabilities 0x02 line coding and serial state CDC Union: bMasterInterface 0 bSlaveInterface 1 CDC Call Management: bmCapabilities 0x03 call management use DataInterface bDataInterface 1 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x83 EP 3 IN bmAttributes 3 Transfer Type Interrupt Synch Type None Usage Type Data wMaxPacketSize 0x0040 1x 64 bytes bInterval 16 Interface Descriptor: bLength 9 bDescriptorType 4 bInterfaceNumber 1 bAlternateSetting 0 bNumEndpoints 2 bInterfaceClass 10 CDC Data bInterfaceSubClass 0 bInterfaceProtocol 0 iInterface 0 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x81 EP 1 IN bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0200 1x 512 bytes bInterval 0 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x02 EP 2 OUT bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0200 1x 512 bytes bInterval 0 Device Qualifier (for other device speed): bLength 10 bDescriptorType 6 bcdUSB 2.00 bDeviceClass 2 Communications bDeviceSubClass 0 bDeviceProtocol 0 bMaxPacketSize0 64 bNumConfigurations 1 Device Status: 0x0000 (Bus Powered) Signed-off-by: Vincent Mailhol <mailhol.vincent(a)wanadoo.fr> Cc: stable <stable(a)vger.kernel.org> Link: https://lore.kernel.org/r/20201002154219.4887-8-mailhol.vincent@wanadoo.fr Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- drivers/usb/class/cdc-acm.c | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c index 1d301b92de2d..30ef946a8e1a 100644 --- a/drivers/usb/class/cdc-acm.c +++ b/drivers/usb/class/cdc-acm.c @@ -1900,6 +1900,17 @@ static const struct usb_device_id acm_ids[] = { .driver_info = IGNORE_DEVICE, }, + /* Exclude ETAS ES58x */ + { USB_DEVICE(0x108c, 0x0159), /* ES581.4 */ + .driver_info = IGNORE_DEVICE, + }, + { USB_DEVICE(0x108c, 0x0168), /* ES582.1 */ + .driver_info = IGNORE_DEVICE, + }, + { USB_DEVICE(0x108c, 0x0169), /* ES584.1 */ + .driver_info = IGNORE_DEVICE, + }, + { USB_DEVICE(0x1bc7, 0x0021), /* Telit 3G ACM only composition */ .driver_info = SEND_ZERO_PACKET, }, -- 2.28.0

5 years

1
0
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror October 2020