# git rev-parse -q --verify 3840cbe24cf060ea05a585ca497814609f5d47d1^{commit} 3840cbe24cf060ea05a585ca497814609f5d47d1 already have revision, skipping fetch # git checkout -q -f -B kisskb 3840cbe24cf060ea05a585ca497814609f5d47d1 # git clean -qxdf # < git log -1 # commit 3840cbe24cf060ea05a585ca497814609f5d47d1 # Author: Johannes Weiner # Date: Thu Oct 3 07:29:05 2024 -0400 # # sched: psi: fix bogus pressure spikes from aggregation race # # Brandon reports sporadic, non-sensical spikes in cumulative pressure # time (total=) when reading cpu.pressure at a high rate. This is due to # a race condition between reader aggregation and tasks changing states. # # While it affects all states and all resources captured by PSI, in # practice it most likely triggers with CPU pressure, since scheduling # events are so frequent compared to other resource events. # # The race context is the live snooping of ongoing stalls during a # pressure read. The read aggregates per-cpu records for stalls that # have concluded, but will also incorporate ad-hoc the duration of any # active state that hasn't been recorded yet. This is important to get # timely measurements of ongoing stalls. Those ad-hoc samples are # calculated on-the-fly up to the current time on that CPU; since the # stall hasn't concluded, it's expected that this is the minimum amount # of stall time that will enter the per-cpu records once it does. # # The problem is that the path that concludes the state uses a CPU clock # read that is not synchronized against aggregators; the clock is read # outside of the seqlock protection. This allows aggregators to race and # snoop a stall with a longer duration than will actually be recorded. # # With the recorded stall time being less than the last snapshot # remembered by the aggregator, a subsequent sample will underflow and # observe a bogus delta value, resulting in an erratic jump in pressure. # # Fix this by moving the clock read of the state change into the seqlock # protection. This ensures no aggregation can snoop live stalls past the # time that's recorded when the state concludes. # # Reported-by: Brandon Duffany # Link: https://bugzilla.kernel.org/show_bug.cgi?id=219194 # Link: https://lore.kernel.org/lkml/20240827121851.GB438928@cmpxchg.org/ # Fixes: df77430639c9 ("psi: Reduce calls to sched_clock() in psi") # Cc: stable@vger.kernel.org # Signed-off-by: Johannes Weiner # Reviewed-by: Chengming Zhou # Signed-off-by: Linus Torvalds # < /opt/cross/kisskb/x86-64--glibc--bleeding-edge-2022.08-1/bin/x86_64-linux-gcc --version # < /opt/cross/kisskb/x86-64--glibc--bleeding-edge-2022.08-1/bin/x86_64-linux-ld --version # < git log --format=%s --max-count=1 3840cbe24cf060ea05a585ca497814609f5d47d1 # make -s -j 40 ARCH=um O=/kisskb/build/linus_allmodconfig_um-x86_64-gcc12 CROSS_COMPILE=/opt/cross/kisskb/x86-64--glibc--bleeding-edge-2022.08-1/bin/x86_64-linux- SUBARCH=x86_64 allmodconfig WARNING: unmet direct dependencies detected for MODVERSIONS Depends on [n]: MODULES [=y] && !COMPILE_TEST [=y] Selected by [y]: - RANDSTRUCT_FULL [=y] && (CC_HAS_RANDSTRUCT [=n] || GCC_PLUGINS [=y]) && MODULES [=y] WARNING: unmet direct dependencies detected for GET_FREE_REGION Depends on [n]: SPARSEMEM [=n] Selected by [m]: - RESOURCE_KUNIT_TEST [=m] && RUNTIME_TESTING_MENU [=y] && KUNIT [=m] # Added to kconfig CONFIG_STANDALONE=y # Added to kconfig CONFIG_KCOV=n # Added to kconfig CONFIG_GCC_PLUGINS=n # Added to kconfig CONFIG_GCC_PLUGIN_CYC_COMPLEXITY=n # Added to kconfig CONFIG_GCC_PLUGIN_SANCOV=n # Added to kconfig CONFIG_GCC_PLUGIN_LATENT_ENTROPY=n # Added to kconfig CONFIG_GCC_PLUGIN_STRUCTLEAK=n # Added to kconfig CONFIG_GCC_PLUGIN_RANDSTRUCT=n # Added to kconfig CONFIG_UML_NET=n # Added to kconfig CONFIG_UML_NET_ETHERTAP=n # Added to kconfig CONFIG_UML_NET_TUNTAP=n # Added to kconfig CONFIG_UML_NET_SLIP=n # Added to kconfig CONFIG_UML_NET_DAEMON=n # Added to kconfig CONFIG_UML_NET_VDE=n # Added to kconfig CONFIG_UML_NET_MCAST=n # Added to kconfig CONFIG_UML_NET_PCAP=n # Added to kconfig CONFIG_UML_NET_SLIRP=n # Added to kconfig CONFIG_GCOV_KERNEL=n # Added to kconfig CONFIG_DEBUG_INFO_BTF=n # Added to kconfig CONFIG_BPF_PRELOAD=n # Added to kconfig CONFIG_SPI_STM32_QSPI=n # < make -s -j 40 ARCH=um O=/kisskb/build/linus_allmodconfig_um-x86_64-gcc12 CROSS_COMPILE=/opt/cross/kisskb/x86-64--glibc--bleeding-edge-2022.08-1/bin/x86_64-linux- SUBARCH=x86_64 help # make -s -j 40 ARCH=um O=/kisskb/build/linus_allmodconfig_um-x86_64-gcc12 CROSS_COMPILE=/opt/cross/kisskb/x86-64--glibc--bleeding-edge-2022.08-1/bin/x86_64-linux- SUBARCH=x86_64 olddefconfig .config:14873:warning: override: reassigning to symbol GCC_PLUGIN_LATENT_ENTROPY .config:14877:warning: override: reassigning to symbol UML_NET_ETHERTAP .config:14879:warning: override: reassigning to symbol UML_NET_SLIP .config:14884:warning: override: reassigning to symbol UML_NET_SLIRP WARNING: unmet direct dependencies detected for GET_FREE_REGION Depends on [n]: SPARSEMEM [=n] Selected by [m]: - RESOURCE_KUNIT_TEST [=m] && RUNTIME_TESTING_MENU [=y] && KUNIT [=m] # make -s -j 40 ARCH=um O=/kisskb/build/linus_allmodconfig_um-x86_64-gcc12 CROSS_COMPILE=/opt/cross/kisskb/x86-64--glibc--bleeding-edge-2022.08-1/bin/x86_64-linux- SUBARCH=x86_64 WARNING: unmet direct dependencies detected for GET_FREE_REGION Depends on [n]: SPARSEMEM [=n] Selected by [m]: - RESOURCE_KUNIT_TEST [=m] && RUNTIME_TESTING_MENU [=y] && KUNIT [=m] WARNING: unmet direct dependencies detected for GET_FREE_REGION Depends on [n]: SPARSEMEM [=n] Selected by [m]: - RESOURCE_KUNIT_TEST [=m] && RUNTIME_TESTING_MENU [=y] && KUNIT [=m] WARNING: unmet direct dependencies detected for GET_FREE_REGION Depends on [n]: SPARSEMEM [=n] Selected by [m]: - RESOURCE_KUNIT_TEST [=m] && RUNTIME_TESTING_MENU [=y] && KUNIT [=m] /kisskb/src/lib/iomap.c:156:5: error: no previous prototype for ‘ioread64_lo_hi’ [-Werror=missing-prototypes] 156 | u64 ioread64_lo_hi(const void __iomem *addr) | ^~~~~~~~~~~~~~ /kisskb/src/lib/iomap.c:163:5: error: no previous prototype for ‘ioread64_hi_lo’ [-Werror=missing-prototypes] 163 | u64 ioread64_hi_lo(const void __iomem *addr) | ^~~~~~~~~~~~~~ /kisskb/src/lib/iomap.c:170:5: error: no previous prototype for ‘ioread64be_lo_hi’ [-Werror=missing-prototypes] 170 | u64 ioread64be_lo_hi(const void __iomem *addr) | ^~~~~~~~~~~~~~~~ /kisskb/src/lib/iomap.c:178:5: error: no previous prototype for ‘ioread64be_hi_lo’ [-Werror=missing-prototypes] 178 | u64 ioread64be_hi_lo(const void __iomem *addr) | ^~~~~~~~~~~~~~~~ /kisskb/src/lib/iomap.c:264:6: error: no previous prototype for ‘iowrite64_lo_hi’ [-Werror=missing-prototypes] 264 | void iowrite64_lo_hi(u64 val, void __iomem *addr) | ^~~~~~~~~~~~~~~ /kisskb/src/lib/iomap.c:272:6: error: no previous prototype for ‘iowrite64_hi_lo’ [-Werror=missing-prototypes] 272 | void iowrite64_hi_lo(u64 val, void __iomem *addr) | ^~~~~~~~~~~~~~~ /kisskb/src/lib/iomap.c:280:6: error: no previous prototype for ‘iowrite64be_lo_hi’ [-Werror=missing-prototypes] 280 | void iowrite64be_lo_hi(u64 val, void __iomem *addr) | ^~~~~~~~~~~~~~~~~ /kisskb/src/lib/iomap.c:288:6: error: no previous prototype for ‘iowrite64be_hi_lo’ [-Werror=missing-prototypes] 288 | void iowrite64be_hi_lo(u64 val, void __iomem *addr) | ^~~~~~~~~~~~~~~~~ cc1: all warnings being treated as errors make[4]: *** [/kisskb/src/scripts/Makefile.build:229: lib/iomap.o] Error 1 make[3]: *** [/kisskb/src/scripts/Makefile.build:478: lib] Error 2 make[3]: *** Waiting for unfinished jobs.... make[2]: *** [/kisskb/src/Makefile:1936: .] Error 2 make[1]: *** [/kisskb/src/Makefile:224: __sub-make] Error 2 make: *** [Makefile:224: __sub-make] Error 2 Command 'make -s -j 40 ARCH=um O=/kisskb/build/linus_allmodconfig_um-x86_64-gcc12 CROSS_COMPILE=/opt/cross/kisskb/x86-64--glibc--bleeding-edge-2022.08-1/bin/x86_64-linux- SUBARCH=x86_64 ' returned non-zero exit status 2. # rm -rf /kisskb/build/linus_allmodconfig_um-x86_64-gcc12 # Build took: 0:09:27.791566