Buildresult: powerpc-fixes/m68k-defconfig/m68k-gcc8 built on Sep 12, 22:26

kisskb

Revisions | Branches | Compilers | Configs | Build Results | Build Failures |

Status:	OK
Date/Time:	Sep 12, 22:26
Duration:	0:05:18.333440
Builder:	ka4
Revision:	powerpc/qspinlock: Fix deadlock in MCS queue (`734ad0af3609464f8f93e00b6c0de1e112f44559)`
Target:	powerpc-fixes/m68k-defconfig/m68k-gcc8
Branch:	powerpc-fixes
Compiler:	m68k-gcc8 (m68k-linux-gcc (GCC) 8.5.0 / GNU ld (GNU Binutils) 2.36.1)
Config:	defconfig (download)
Log:	Download original No warnings found in log. Full Log # git gc Expanding reachable commits in commit graph: 76091 Expanding reachable commits in commit graph: 163902 Expanding reachable commits in commit graph: 257937 Expanding reachable commits in commit graph: 349050 Expanding reachable commits in commit graph: 447038 Expanding reachable commits in commit graph: 533014 Expanding reachable commits in commit graph: 637018 Expanding reachable commits in commit graph: 742896 Expanding reachable commits in commit graph: 851286 Expanding reachable commits in commit graph: 901420, done. Writing out commit graph in 4 passes: 67% (2450760/3605680) Writing out commit graph in 4 passes: 68% (2451863/3605680) Writing out commit graph in 4 passes: 69% (2487920/3605680) Writing out commit graph in 4 passes: 70% (2523976/3605680) Writing out commit graph in 4 passes: 71% (2560033/3605680) Writing out commit graph in 4 passes: 72% (2596090/3605680) Writing out commit graph in 4 passes: 73% (2632147/3605680) Writing out commit graph in 4 passes: 74% (2668204/3605680) Writing out commit graph in 4 passes: 75% (2704260/3605680) Writing out commit graph in 4 passes: 76% (2740317/3605680) Writing out commit graph in 4 passes: 77% (2776374/3605680) Writing out commit graph in 4 passes: 78% (2812431/3605680) Writing out commit graph in 4 passes: 79% (2848488/3605680) Writing out commit graph in 4 passes: 80% (2884544/3605680) Writing out commit graph in 4 passes: 81% (2920601/3605680) Writing out commit graph in 4 passes: 82% (2956658/3605680) Writing out commit graph in 4 passes: 83% (2992715/3605680) Writing out commit graph in 4 passes: 84% (3028772/3605680) Writing out commit graph in 4 passes: 85% (3064828/3605680) Writing out commit graph in 4 passes: 86% (3100885/3605680) Writing out commit graph in 4 passes: 87% (3136942/3605680) Writing out commit graph in 4 passes: 88% (3172999/3605680) Writing out commit graph in 4 passes: 89% (3209056/3605680) Writing out commit graph in 4 passes: 90% (3245112/3605680) Writing out commit graph in 4 passes: 91% (3281169/3605680) Writing out commit graph in 4 passes: 92% (3317226/3605680) Writing out commit graph in 4 passes: 93% (3353283/3605680) Writing out commit graph in 4 passes: 94% (3389340/3605680) Writing out commit graph in 4 passes: 95% (3425396/3605680) Writing out commit graph in 4 passes: 96% (3461453/3605680) Writing out commit graph in 4 passes: 97% (3497510/3605680) Writing out commit graph in 4 passes: 98% (3533567/3605680) Writing out commit graph in 4 passes: 99% (3569624/3605680) Writing out commit graph in 4 passes: 100% (3605680/3605680) Writing out commit graph in 4 passes: 100% (3605680/3605680), done. # git rev-parse -q --verify 734ad0af3609464f8f93e00b6c0de1e112f44559^{commit} 734ad0af3609464f8f93e00b6c0de1e112f44559 already have revision, skipping fetch # git checkout -q -f -B kisskb 734ad0af3609464f8f93e00b6c0de1e112f44559 # git clean -qxdf # < git log -1 # commit 734ad0af3609464f8f93e00b6c0de1e112f44559 # Author: Nysal Jan K.A. <nysal@linux.ibm.com> # Date: Thu Aug 29 07:58:27 2024 +0530 # # powerpc/qspinlock: Fix deadlock in MCS queue # # If an interrupt occurs in queued_spin_lock_slowpath() after we increment # qnodesp->count and before node->lock is initialized, another CPU might # see stale lock values in get_tail_qnode(). If the stale lock value happens # to match the lock on that CPU, then we write to the "next" pointer of # the wrong qnode. This causes a deadlock as the former CPU, once it becomes # the head of the MCS queue, will spin indefinitely until it's "next" pointer # is set by its successor in the queue. # # Running stress-ng on a 16 core (16EC/16VP) shared LPAR, results in # occasional lockups similar to the following: # # $ stress-ng --all 128 --vm-bytes 80% --aggressive \ # --maximize --oomable --verify --syslog \ # --metrics --times --timeout 5m # # watchdog: CPU 15 Hard LOCKUP # ...... # NIP [c0000000000b78f4] queued_spin_lock_slowpath+0x1184/0x1490 # LR [c000000001037c5c] _raw_spin_lock+0x6c/0x90 # Call Trace: # 0xc000002cfffa3bf0 (unreliable) # _raw_spin_lock+0x6c/0x90 # raw_spin_rq_lock_nested.part.135+0x4c/0xd0 # sched_ttwu_pending+0x60/0x1f0 # __flush_smp_call_function_queue+0x1dc/0x670 # smp_ipi_demux_relaxed+0xa4/0x100 # xive_muxed_ipi_action+0x20/0x40 # __handle_irq_event_percpu+0x80/0x240 # handle_irq_event_percpu+0x2c/0x80 # handle_percpu_irq+0x84/0xd0 # generic_handle_irq+0x54/0x80 # __do_irq+0xac/0x210 # __do_IRQ+0x74/0xd0 # 0x0 # do_IRQ+0x8c/0x170 # hardware_interrupt_common_virt+0x29c/0x2a0 # --- interrupt: 500 at queued_spin_lock_slowpath+0x4b8/0x1490 # ...... # NIP [c0000000000b6c28] queued_spin_lock_slowpath+0x4b8/0x1490 # LR [c000000001037c5c] _raw_spin_lock+0x6c/0x90 # --- interrupt: 500 # 0xc0000029c1a41d00 (unreliable) # _raw_spin_lock+0x6c/0x90 # futex_wake+0x100/0x260 # do_futex+0x21c/0x2a0 # sys_futex+0x98/0x270 # system_call_exception+0x14c/0x2f0 # system_call_vectored_common+0x15c/0x2ec # # The following code flow illustrates how the deadlock occurs. # For the sake of brevity, assume that both locks (A and B) are # contended and we call the queued_spin_lock_slowpath() function. # # CPU0 CPU1 # ---- ---- # spin_lock_irqsave(A) \| # spin_unlock_irqrestore(A) \| # spin_lock(B) \| # \| \| # ▼ \| # id = qnodesp->count++; \| # (Note that nodes[0].lock == A) \| # \| \| # ▼ \| # Interrupt \| # (happens before "nodes[0].lock = B") \| # \| \| # ▼ \| # spin_lock_irqsave(A) \| # \| \| # ▼ \| # id = qnodesp->count++ \| # nodes[1].lock = A \| # \| \| # ▼ \| # Tail of MCS queue \| # \| spin_lock_irqsave(A) # ▼ \| # Head of MCS queue ▼ # \| CPU0 is previous tail # ▼ \| # Spin indefinitely ▼ # (until "nodes[1].next != NULL") prev = get_tail_qnode(A, CPU0) # \| # ▼ # prev == &qnodes[CPU0].nodes[0] # (as qnodes[CPU0].nodes[0].lock == A) # \| # ▼ # WRITE_ONCE(prev->next, node) # \| # ▼ # Spin indefinitely # (until nodes[0].locked == 1) # # Thanks to Saket Kumar Bhaskar for help with recreating the issue # # Fixes: 84990b169557 ("powerpc/qspinlock: add mcs queueing for contended waiters") # Cc: stable@vger.kernel.org # v6.2+ # Reported-by: Geetika Moolchandani <geetika@linux.ibm.com> # Reported-by: Vaishnavi Bhat <vaish123@in.ibm.com> # Reported-by: Jijo Varghese <vargjijo@in.ibm.com> # Signed-off-by: Nysal Jan K.A. <nysal@linux.ibm.com> # Reviewed-by: Nicholas Piggin <npiggin@gmail.com> # Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> # Link: https://msgid.link/20240829022830.1164355-1-nysal@linux.ibm.com # < /opt/cross/kisskb/korg/gcc-8.5.0-nolibc/m68k-linux/bin/m68k-linux-gcc --version # < /opt/cross/kisskb/korg/gcc-8.5.0-nolibc/m68k-linux/bin/m68k-linux-ld --version # < git log --format=%s --max-count=1 734ad0af3609464f8f93e00b6c0de1e112f44559 # make -s -j 40 ARCH=m68k O=/kisskb/build/powerpc-fixes_defconfig_m68k-gcc8 CROSS_COMPILE=/opt/cross/kisskb/korg/gcc-8.5.0-nolibc/m68k-linux/bin/m68k-linux- defconfig # < make -s -j 40 ARCH=m68k O=/kisskb/build/powerpc-fixes_defconfig_m68k-gcc8 CROSS_COMPILE=/opt/cross/kisskb/korg/gcc-8.5.0-nolibc/m68k-linux/bin/m68k-linux- help # make -s -j 40 ARCH=m68k O=/kisskb/build/powerpc-fixes_defconfig_m68k-gcc8 CROSS_COMPILE=/opt/cross/kisskb/korg/gcc-8.5.0-nolibc/m68k-linux/bin/m68k-linux- olddefconfig # make -s -j 40 ARCH=m68k O=/kisskb/build/powerpc-fixes_defconfig_m68k-gcc8 CROSS_COMPILE=/opt/cross/kisskb/korg/gcc-8.5.0-nolibc/m68k-linux/bin/m68k-linux- Completed OK # rm -rf /kisskb/build/powerpc-fixes_defconfig_m68k-gcc8 # Build took: 0:05:18.333440

© Michael Ellerman 2006-2018.