[Kernel-packages] [Bug 2053152] Re: performance: mm/percpu-internal.h: Re-layout pcpu_chunk to mitigate false sharing
This bug is awaiting verification that the linux-xilinx- zynqmp/5.15.0-1029.33 kernel in -proposed solves the problem. Please test the kernel and update this bug with the results. If the problem is solved, change the tag 'verification-needed-jammy-linux-xilinx-zynqmp' to 'verification-done-jammy-linux-xilinx-zynqmp'. If the problem still exists, change the tag 'verification-needed-jammy-linux-xilinx-zynqmp' to 'verification-failed-jammy-linux-xilinx-zynqmp'. If verification is not done by 5 working days from today, this fix will be dropped from the source code, and this bug will be closed. See https://wiki.ubuntu.com/Testing/EnableProposed for documentation how to enable and use -proposed. Thank you! ** Tags added: kernel-spammed-jammy-linux-xilinx-zynqmp-v2 verification-needed-jammy-linux-xilinx-zynqmp -- You received this bug notification because you are a member of Kernel Packages, which is subscribed to linux in Ubuntu. https://bugs.launchpad.net/bugs/2053152 Title: performance: mm/percpu-internal.h: Re-layout pcpu_chunk to mitigate false sharing Status in linux package in Ubuntu: Fix Released Status in linux source package in Jammy: Fix Released Bug description: This is a public version of https://bugs.launchpad.net/bugs/2034984 [Description] When running UnixBench/Execl throughput case, false sharing is observed due to frequent read on base_addr and write on free_bytes, chunk_md. UnixBench/Execl represents a class of workload where bash scripts are spawned frequently to do some short jobs. It will do system call on execl frequently, and execl will call mm_init to initialize mm_struct of the process. mm_init will call __percpu_counter_init for percpu_counters initialization. Then pcpu_alloc is called to read the base_addr of pcpu_chunk for memory allocation. Inside pcpu_alloc, it will call pcpu_alloc_area to allocate memory from a specified chunk. This function will update "free_bytes" and "chunk_md" to record the rest free bytes and other meta data for this chunk. Correspondingly, pcpu_free_area will also update these 2 members when free memory. In current pcpu_chunk layout, `base_addr' is in the same cache line with `free_bytes' and `chunk_md', and `base_addr' is at the last 8 bytes. This patch moves `bound_map' up to `base_addr', to let `base_addr' locate in a new cacheline. [Hardware Information] Architecture: Intel / AMD (x86_64) Platform(s): Platform-Independent Date HW is expected at Canonical: Component(s): Performance and Scalability [Software Information] Target Version: 23.10 Target Kernel: 6.5 Commit IDs: 3a6358c0dbe6 percpu-internal/pcpu_chunk: re-layout pcpu_chunk structure to reduce false sharing External Links: [Business Justification] [Testing guidance] [External ID] OSVE-5160 The following requested patch has been applied upstream for v6.5-rc1: - 3a6358c0dbe6 percpu-internal/pcpu_chunk: re-layout pcpu_chunk structure to reduce false sharing https://github.com/torvalds/linux/commit/3a6358c0dbe6a286a4f4504ba392a6039a9fbd12 To manage notifications about this bug go to: https://bugs.launchpad.net/ubuntu/+source/linux/+bug/2053152/+subscriptions -- Mailing list: https://launchpad.net/~kernel-packages Post to : kernel-packages@lists.launchpad.net Unsubscribe : https://launchpad.net/~kernel-packages More help : https://help.launchpad.net/ListHelp
[Kernel-packages] [Bug 2053152] Re: performance: mm/percpu-internal.h: Re-layout pcpu_chunk to mitigate false sharing
This bug is awaiting verification that the linux-nvidia-tegra- igx/5.15.0-1010.10 kernel in -proposed solves the problem. Please test the kernel and update this bug with the results. If the problem is solved, change the tag 'verification-needed-jammy-linux-nvidia-tegra- igx' to 'verification-done-jammy-linux-nvidia-tegra-igx'. If the problem still exists, change the tag 'verification-needed-jammy-linux-nvidia- tegra-igx' to 'verification-failed-jammy-linux-nvidia-tegra-igx'. If verification is not done by 5 working days from today, this fix will be dropped from the source code, and this bug will be closed. See https://wiki.ubuntu.com/Testing/EnableProposed for documentation how to enable and use -proposed. Thank you! ** Tags added: kernel-spammed-jammy-linux-nvidia-tegra-igx-v2 verification-needed-jammy-linux-nvidia-tegra-igx -- You received this bug notification because you are a member of Kernel Packages, which is subscribed to linux in Ubuntu. https://bugs.launchpad.net/bugs/2053152 Title: performance: mm/percpu-internal.h: Re-layout pcpu_chunk to mitigate false sharing Status in linux package in Ubuntu: Fix Released Status in linux source package in Jammy: Fix Released Bug description: This is a public version of https://bugs.launchpad.net/bugs/2034984 [Description] When running UnixBench/Execl throughput case, false sharing is observed due to frequent read on base_addr and write on free_bytes, chunk_md. UnixBench/Execl represents a class of workload where bash scripts are spawned frequently to do some short jobs. It will do system call on execl frequently, and execl will call mm_init to initialize mm_struct of the process. mm_init will call __percpu_counter_init for percpu_counters initialization. Then pcpu_alloc is called to read the base_addr of pcpu_chunk for memory allocation. Inside pcpu_alloc, it will call pcpu_alloc_area to allocate memory from a specified chunk. This function will update "free_bytes" and "chunk_md" to record the rest free bytes and other meta data for this chunk. Correspondingly, pcpu_free_area will also update these 2 members when free memory. In current pcpu_chunk layout, `base_addr' is in the same cache line with `free_bytes' and `chunk_md', and `base_addr' is at the last 8 bytes. This patch moves `bound_map' up to `base_addr', to let `base_addr' locate in a new cacheline. [Hardware Information] Architecture: Intel / AMD (x86_64) Platform(s): Platform-Independent Date HW is expected at Canonical: Component(s): Performance and Scalability [Software Information] Target Version: 23.10 Target Kernel: 6.5 Commit IDs: 3a6358c0dbe6 percpu-internal/pcpu_chunk: re-layout pcpu_chunk structure to reduce false sharing External Links: [Business Justification] [Testing guidance] [External ID] OSVE-5160 The following requested patch has been applied upstream for v6.5-rc1: - 3a6358c0dbe6 percpu-internal/pcpu_chunk: re-layout pcpu_chunk structure to reduce false sharing https://github.com/torvalds/linux/commit/3a6358c0dbe6a286a4f4504ba392a6039a9fbd12 To manage notifications about this bug go to: https://bugs.launchpad.net/ubuntu/+source/linux/+bug/2053152/+subscriptions -- Mailing list: https://launchpad.net/~kernel-packages Post to : kernel-packages@lists.launchpad.net Unsubscribe : https://launchpad.net/~kernel-packages More help : https://help.launchpad.net/ListHelp
[Kernel-packages] [Bug 2053152] Re: performance: mm/percpu-internal.h: Re-layout pcpu_chunk to mitigate false sharing
This bug is awaiting verification that the linux- bluefield/5.15.0-1040.42 kernel in -proposed solves the problem. Please test the kernel and update this bug with the results. If the problem is solved, change the tag 'verification-needed-jammy-linux-bluefield' to 'verification-done-jammy-linux-bluefield'. If the problem still exists, change the tag 'verification-needed-jammy-linux-bluefield' to 'verification-failed-jammy-linux-bluefield'. If verification is not done by 5 working days from today, this fix will be dropped from the source code, and this bug will be closed. See https://wiki.ubuntu.com/Testing/EnableProposed for documentation how to enable and use -proposed. Thank you! ** Tags added: kernel-spammed-jammy-linux-bluefield-v2 verification-needed-jammy-linux-bluefield -- You received this bug notification because you are a member of Kernel Packages, which is subscribed to linux in Ubuntu. https://bugs.launchpad.net/bugs/2053152 Title: performance: mm/percpu-internal.h: Re-layout pcpu_chunk to mitigate false sharing Status in linux package in Ubuntu: Fix Released Status in linux source package in Jammy: Fix Released Bug description: This is a public version of https://bugs.launchpad.net/bugs/2034984 [Description] When running UnixBench/Execl throughput case, false sharing is observed due to frequent read on base_addr and write on free_bytes, chunk_md. UnixBench/Execl represents a class of workload where bash scripts are spawned frequently to do some short jobs. It will do system call on execl frequently, and execl will call mm_init to initialize mm_struct of the process. mm_init will call __percpu_counter_init for percpu_counters initialization. Then pcpu_alloc is called to read the base_addr of pcpu_chunk for memory allocation. Inside pcpu_alloc, it will call pcpu_alloc_area to allocate memory from a specified chunk. This function will update "free_bytes" and "chunk_md" to record the rest free bytes and other meta data for this chunk. Correspondingly, pcpu_free_area will also update these 2 members when free memory. In current pcpu_chunk layout, `base_addr' is in the same cache line with `free_bytes' and `chunk_md', and `base_addr' is at the last 8 bytes. This patch moves `bound_map' up to `base_addr', to let `base_addr' locate in a new cacheline. [Hardware Information] Architecture: Intel / AMD (x86_64) Platform(s): Platform-Independent Date HW is expected at Canonical: Component(s): Performance and Scalability [Software Information] Target Version: 23.10 Target Kernel: 6.5 Commit IDs: 3a6358c0dbe6 percpu-internal/pcpu_chunk: re-layout pcpu_chunk structure to reduce false sharing External Links: [Business Justification] [Testing guidance] [External ID] OSVE-5160 The following requested patch has been applied upstream for v6.5-rc1: - 3a6358c0dbe6 percpu-internal/pcpu_chunk: re-layout pcpu_chunk structure to reduce false sharing https://github.com/torvalds/linux/commit/3a6358c0dbe6a286a4f4504ba392a6039a9fbd12 To manage notifications about this bug go to: https://bugs.launchpad.net/ubuntu/+source/linux/+bug/2053152/+subscriptions -- Mailing list: https://launchpad.net/~kernel-packages Post to : kernel-packages@lists.launchpad.net Unsubscribe : https://launchpad.net/~kernel-packages More help : https://help.launchpad.net/ListHelp
[Kernel-packages] [Bug 2053152] Re: performance: mm/percpu-internal.h: Re-layout pcpu_chunk to mitigate false sharing
This bug is awaiting verification that the linux- oracle-5.15/5.15.0-1055.61~20.04.1 kernel in -proposed solves the problem. Please test the kernel and update this bug with the results. If the problem is solved, change the tag 'verification-needed-focal-linux- oracle-5.15' to 'verification-done-focal-linux-oracle-5.15'. If the problem still exists, change the tag 'verification-needed-focal-linux- oracle-5.15' to 'verification-failed-focal-linux-oracle-5.15'. If verification is not done by 5 working days from today, this fix will be dropped from the source code, and this bug will be closed. See https://wiki.ubuntu.com/Testing/EnableProposed for documentation how to enable and use -proposed. Thank you! ** Tags added: kernel-spammed-focal-linux-oracle-5.15-v2 verification-needed-focal-linux-oracle-5.15 -- You received this bug notification because you are a member of Kernel Packages, which is subscribed to linux in Ubuntu. https://bugs.launchpad.net/bugs/2053152 Title: performance: mm/percpu-internal.h: Re-layout pcpu_chunk to mitigate false sharing Status in linux package in Ubuntu: Fix Released Status in linux source package in Jammy: Fix Released Bug description: This is a public version of https://bugs.launchpad.net/bugs/2034984 [Description] When running UnixBench/Execl throughput case, false sharing is observed due to frequent read on base_addr and write on free_bytes, chunk_md. UnixBench/Execl represents a class of workload where bash scripts are spawned frequently to do some short jobs. It will do system call on execl frequently, and execl will call mm_init to initialize mm_struct of the process. mm_init will call __percpu_counter_init for percpu_counters initialization. Then pcpu_alloc is called to read the base_addr of pcpu_chunk for memory allocation. Inside pcpu_alloc, it will call pcpu_alloc_area to allocate memory from a specified chunk. This function will update "free_bytes" and "chunk_md" to record the rest free bytes and other meta data for this chunk. Correspondingly, pcpu_free_area will also update these 2 members when free memory. In current pcpu_chunk layout, `base_addr' is in the same cache line with `free_bytes' and `chunk_md', and `base_addr' is at the last 8 bytes. This patch moves `bound_map' up to `base_addr', to let `base_addr' locate in a new cacheline. [Hardware Information] Architecture: Intel / AMD (x86_64) Platform(s): Platform-Independent Date HW is expected at Canonical: Component(s): Performance and Scalability [Software Information] Target Version: 23.10 Target Kernel: 6.5 Commit IDs: 3a6358c0dbe6 percpu-internal/pcpu_chunk: re-layout pcpu_chunk structure to reduce false sharing External Links: [Business Justification] [Testing guidance] [External ID] OSVE-5160 The following requested patch has been applied upstream for v6.5-rc1: - 3a6358c0dbe6 percpu-internal/pcpu_chunk: re-layout pcpu_chunk structure to reduce false sharing https://github.com/torvalds/linux/commit/3a6358c0dbe6a286a4f4504ba392a6039a9fbd12 To manage notifications about this bug go to: https://bugs.launchpad.net/ubuntu/+source/linux/+bug/2053152/+subscriptions -- Mailing list: https://launchpad.net/~kernel-packages Post to : kernel-packages@lists.launchpad.net Unsubscribe : https://launchpad.net/~kernel-packages More help : https://help.launchpad.net/ListHelp
[Kernel-packages] [Bug 2053152] Re: performance: mm/percpu-internal.h: Re-layout pcpu_chunk to mitigate false sharing
This bug is awaiting verification that the linux-intel- iotg/5.15.0-1052.58 kernel in -proposed solves the problem. Please test the kernel and update this bug with the results. If the problem is solved, change the tag 'verification-needed-jammy-linux-intel-iotg' to 'verification-done-jammy-linux-intel-iotg'. If the problem still exists, change the tag 'verification-needed-jammy-linux-intel-iotg' to 'verification-failed-jammy-linux-intel-iotg'. If verification is not done by 5 working days from today, this fix will be dropped from the source code, and this bug will be closed. See https://wiki.ubuntu.com/Testing/EnableProposed for documentation how to enable and use -proposed. Thank you! ** Tags added: kernel-spammed-jammy-linux-intel-iotg-v2 verification-needed-jammy-linux-intel-iotg -- You received this bug notification because you are a member of Kernel Packages, which is subscribed to linux in Ubuntu. https://bugs.launchpad.net/bugs/2053152 Title: performance: mm/percpu-internal.h: Re-layout pcpu_chunk to mitigate false sharing Status in linux package in Ubuntu: Fix Released Status in linux source package in Jammy: Fix Released Bug description: This is a public version of https://bugs.launchpad.net/bugs/2034984 [Description] When running UnixBench/Execl throughput case, false sharing is observed due to frequent read on base_addr and write on free_bytes, chunk_md. UnixBench/Execl represents a class of workload where bash scripts are spawned frequently to do some short jobs. It will do system call on execl frequently, and execl will call mm_init to initialize mm_struct of the process. mm_init will call __percpu_counter_init for percpu_counters initialization. Then pcpu_alloc is called to read the base_addr of pcpu_chunk for memory allocation. Inside pcpu_alloc, it will call pcpu_alloc_area to allocate memory from a specified chunk. This function will update "free_bytes" and "chunk_md" to record the rest free bytes and other meta data for this chunk. Correspondingly, pcpu_free_area will also update these 2 members when free memory. In current pcpu_chunk layout, `base_addr' is in the same cache line with `free_bytes' and `chunk_md', and `base_addr' is at the last 8 bytes. This patch moves `bound_map' up to `base_addr', to let `base_addr' locate in a new cacheline. [Hardware Information] Architecture: Intel / AMD (x86_64) Platform(s): Platform-Independent Date HW is expected at Canonical: Component(s): Performance and Scalability [Software Information] Target Version: 23.10 Target Kernel: 6.5 Commit IDs: 3a6358c0dbe6 percpu-internal/pcpu_chunk: re-layout pcpu_chunk structure to reduce false sharing External Links: [Business Justification] [Testing guidance] [External ID] OSVE-5160 The following requested patch has been applied upstream for v6.5-rc1: - 3a6358c0dbe6 percpu-internal/pcpu_chunk: re-layout pcpu_chunk structure to reduce false sharing https://github.com/torvalds/linux/commit/3a6358c0dbe6a286a4f4504ba392a6039a9fbd12 To manage notifications about this bug go to: https://bugs.launchpad.net/ubuntu/+source/linux/+bug/2053152/+subscriptions -- Mailing list: https://launchpad.net/~kernel-packages Post to : kernel-packages@lists.launchpad.net Unsubscribe : https://launchpad.net/~kernel-packages More help : https://help.launchpad.net/ListHelp
[Kernel-packages] [Bug 2053152] Re: performance: mm/percpu-internal.h: Re-layout pcpu_chunk to mitigate false sharing
This bug was fixed in the package linux - 5.15.0-102.112 --- linux (5.15.0-102.112) jammy; urgency=medium * jammy/linux: 5.15.0-102.112 -proposed tracker (LP: #2055632) * Drop ABI checks from kernel build (LP: #2055686) - [Packaging] Remove in-tree abi checks - [Packaging] Drop abi checks from final-checks * Packaging resync (LP: #1786013) - [Packaging] drop ABI data - [Packaging] update annotations scripts - debian.master/dkms-versions -- update from kernel-versions (main/2024.03.04) * block/loop: No longer allows to create partitions (LP: #2056143) - block, loop: support partitions without scanning * Cranky update-dkms-versions rollout (LP: #2055685) - [Packaging] remove update-dkms-versions - Move debian/dkms-versions to debian.master/dkms-versions - [Packaging] Replace debian/dkms-versions with $(DEBIAN)/dkms-versions - [Packaging] remove update-version-dkms * linux: please move erofs.ko (CONFIG_EROFS for EROFS support) from linux- modules-extra to linux-modules (LP: #2054809) - UBUNTU [Packaging]: Include erofs in linux-modules instead of linux-modules- extra * linux-tools-common: man page of usbip[d] is misplaced (LP: #2054094) - [Packaging] rules: Put usbip manpages in the correct directory * CVE-2024-23851 - dm ioctl: log an error if the ioctl structure is corrupted - dm: limit the number of targets and parameter size area * CVE-2024-23850 - btrfs: do not ASSERT() if the newly created subvolume already got read * x86: performance: tsc: Extend watchdog check exemption to 4-Sockets platform (LP: #2054699) - x86/tsc: Extend watchdog check exemption to 4-Sockets platform * linux: please move dmi-sysfs.ko (CONFIG_DMI_SYSFS for SMBIOS support) from linux-modules-extra to linux-modules (LP: #2045561) - [Packaging] Move dmi-sysfs.ko into linux-modules * Fix bpf selftests build failure after v5.15.139 update (LP: #2054567) - Revert "selftests/bpf: Test tail call counting with bpf2bpf and data on stack" * Jammy update: v5.15.148 upstream stable release (LP: #2055145) - f2fs: explicitly null-terminate the xattr list - pinctrl: lochnagar: Don't build on MIPS - ALSA: hda - Fix speaker and headset mic pin config for CHUWI CoreBook XPro - mptcp: fix uninit-value in mptcp_incoming_options - wifi: cfg80211: lock wiphy mutex for rfkill poll - debugfs: fix automount d_fsdata usage - drm/amdgpu: Fix cat debugfs amdgpu_regs_didt causes kernel null pointer - nvme-core: check for too small lba shift - ASoC: wm8974: Correct boost mixer inputs - ASoC: Intel: Skylake: Fix mem leak in few functions - ASoC: nau8822: Fix incorrect type in assignment and cast to restricted __be16 - ASoC: Intel: Skylake: mem leak in skl register function - ASoC: cs43130: Fix the position of const qualifier - ASoC: cs43130: Fix incorrect frame delay configuration - ASoC: rt5650: add mutex to avoid the jack detection failure - nouveau/tu102: flush all pdbs on vmm flush - net/tg3: fix race condition in tg3_reset_task() - ASoC: da7219: Support low DC impedance headset - ASoC: ops: add correct range check for limiting volume - nvme: introduce helper function to get ctrl state - drm/amdgpu: Add NULL checks for function pointers - drm/exynos: fix a potential error pointer dereference - drm/exynos: fix a wrong error checking - hwmon: (corsair-psu) Fix probe when built-in - clk: rockchip: rk3128: Fix HCLK_OTG gate register - jbd2: correct the printing of write_flags in jbd2_write_superblock() - drm/crtc: Fix uninit-value bug in drm_mode_setcrtc - neighbour: Don't let neigh_forced_gc() disable preemption for long - platform/x86: intel-vbtn: Fix missing tablet-mode-switch events - jbd2: fix soft lockup in journal_finish_inode_data_buffers() - tracing: Have large events show up as '[LINE TOO BIG]' instead of nothing - tracing: Add size check when printing trace_marker output - stmmac: dwmac-loongson: drop useless check for compatible fallback - MIPS: dts: loongson: drop incorrect dwmac fallback compatible - tracing: Fix uaf issue when open the hist or hist_debug file - ring-buffer: Do not record in NMI if the arch does not support cmpxchg in NMI - reset: hisilicon: hi6220: fix Wvoid-pointer-to-enum-cast warning - Input: atkbd - skip ATKBD_CMD_GETID in translated mode - Input: i8042 - add nomux quirk for Acer P459-G2-M - s390/scm: fix virtual vs physical address confusion - ARC: fix spare error - wifi: iwlwifi: pcie: avoid a NULL pointer dereference - Input: xpad - add Razer Wolverine V2 support - ASoC: Intel: bytcr_rt5640: Add quirk for the Medion Lifetab S10346 - i2c: rk3x: fix potential spinlock recursion on poll - net: qrtr: ns: Return 0 if server port is not present - ARM: sun9i: smp: fix return code check of
[Kernel-packages] [Bug 2053152] Re: performance: mm/percpu-internal.h: Re-layout pcpu_chunk to mitigate false sharing
This bug is awaiting verification that the linux-nvidia- tegra-5.15/5.15.0-1023.23~20.04.1 kernel in -proposed solves the problem. Please test the kernel and update this bug with the results. If the problem is solved, change the tag 'verification-needed-focal-linux- nvidia-tegra-5.15' to 'verification-done-focal-linux-nvidia-tegra-5.15'. If the problem still exists, change the tag 'verification-needed-focal- linux-nvidia-tegra-5.15' to 'verification-failed-focal-linux-nvidia- tegra-5.15'. If verification is not done by 5 working days from today, this fix will be dropped from the source code, and this bug will be closed. See https://wiki.ubuntu.com/Testing/EnableProposed for documentation how to enable and use -proposed. Thank you! ** Tags added: kernel-spammed-focal-linux-nvidia-tegra-5.15-v2 verification-needed-focal-linux-nvidia-tegra-5.15 -- You received this bug notification because you are a member of Kernel Packages, which is subscribed to linux in Ubuntu. https://bugs.launchpad.net/bugs/2053152 Title: performance: mm/percpu-internal.h: Re-layout pcpu_chunk to mitigate false sharing Status in linux package in Ubuntu: Fix Released Status in linux source package in Jammy: Fix Committed Bug description: This is a public version of https://bugs.launchpad.net/bugs/2034984 [Description] When running UnixBench/Execl throughput case, false sharing is observed due to frequent read on base_addr and write on free_bytes, chunk_md. UnixBench/Execl represents a class of workload where bash scripts are spawned frequently to do some short jobs. It will do system call on execl frequently, and execl will call mm_init to initialize mm_struct of the process. mm_init will call __percpu_counter_init for percpu_counters initialization. Then pcpu_alloc is called to read the base_addr of pcpu_chunk for memory allocation. Inside pcpu_alloc, it will call pcpu_alloc_area to allocate memory from a specified chunk. This function will update "free_bytes" and "chunk_md" to record the rest free bytes and other meta data for this chunk. Correspondingly, pcpu_free_area will also update these 2 members when free memory. In current pcpu_chunk layout, `base_addr' is in the same cache line with `free_bytes' and `chunk_md', and `base_addr' is at the last 8 bytes. This patch moves `bound_map' up to `base_addr', to let `base_addr' locate in a new cacheline. [Hardware Information] Architecture: Intel / AMD (x86_64) Platform(s): Platform-Independent Date HW is expected at Canonical: Component(s): Performance and Scalability [Software Information] Target Version: 23.10 Target Kernel: 6.5 Commit IDs: 3a6358c0dbe6 percpu-internal/pcpu_chunk: re-layout pcpu_chunk structure to reduce false sharing External Links: [Business Justification] [Testing guidance] [External ID] OSVE-5160 The following requested patch has been applied upstream for v6.5-rc1: - 3a6358c0dbe6 percpu-internal/pcpu_chunk: re-layout pcpu_chunk structure to reduce false sharing https://github.com/torvalds/linux/commit/3a6358c0dbe6a286a4f4504ba392a6039a9fbd12 To manage notifications about this bug go to: https://bugs.launchpad.net/ubuntu/+source/linux/+bug/2053152/+subscriptions -- Mailing list: https://launchpad.net/~kernel-packages Post to : kernel-packages@lists.launchpad.net Unsubscribe : https://launchpad.net/~kernel-packages More help : https://help.launchpad.net/ListHelp
[Kernel-packages] [Bug 2053152] Re: performance: mm/percpu-internal.h: Re-layout pcpu_chunk to mitigate false sharing
This bug is awaiting verification that the linux-nvidia- tegra/5.15.0-1023.23 kernel in -proposed solves the problem. Please test the kernel and update this bug with the results. If the problem is solved, change the tag 'verification-needed-jammy-linux-nvidia-tegra' to 'verification-done-jammy-linux-nvidia-tegra'. If the problem still exists, change the tag 'verification-needed-jammy-linux-nvidia-tegra' to 'verification-failed-jammy-linux-nvidia-tegra'. If verification is not done by 5 working days from today, this fix will be dropped from the source code, and this bug will be closed. See https://wiki.ubuntu.com/Testing/EnableProposed for documentation how to enable and use -proposed. Thank you! ** Tags added: kernel-spammed-jammy-linux-nvidia-tegra-v2 verification-needed-jammy-linux-nvidia-tegra -- You received this bug notification because you are a member of Kernel Packages, which is subscribed to linux in Ubuntu. https://bugs.launchpad.net/bugs/2053152 Title: performance: mm/percpu-internal.h: Re-layout pcpu_chunk to mitigate false sharing Status in linux package in Ubuntu: Fix Released Status in linux source package in Jammy: Fix Committed Bug description: This is a public version of https://bugs.launchpad.net/bugs/2034984 [Description] When running UnixBench/Execl throughput case, false sharing is observed due to frequent read on base_addr and write on free_bytes, chunk_md. UnixBench/Execl represents a class of workload where bash scripts are spawned frequently to do some short jobs. It will do system call on execl frequently, and execl will call mm_init to initialize mm_struct of the process. mm_init will call __percpu_counter_init for percpu_counters initialization. Then pcpu_alloc is called to read the base_addr of pcpu_chunk for memory allocation. Inside pcpu_alloc, it will call pcpu_alloc_area to allocate memory from a specified chunk. This function will update "free_bytes" and "chunk_md" to record the rest free bytes and other meta data for this chunk. Correspondingly, pcpu_free_area will also update these 2 members when free memory. In current pcpu_chunk layout, `base_addr' is in the same cache line with `free_bytes' and `chunk_md', and `base_addr' is at the last 8 bytes. This patch moves `bound_map' up to `base_addr', to let `base_addr' locate in a new cacheline. [Hardware Information] Architecture: Intel / AMD (x86_64) Platform(s): Platform-Independent Date HW is expected at Canonical: Component(s): Performance and Scalability [Software Information] Target Version: 23.10 Target Kernel: 6.5 Commit IDs: 3a6358c0dbe6 percpu-internal/pcpu_chunk: re-layout pcpu_chunk structure to reduce false sharing External Links: [Business Justification] [Testing guidance] [External ID] OSVE-5160 The following requested patch has been applied upstream for v6.5-rc1: - 3a6358c0dbe6 percpu-internal/pcpu_chunk: re-layout pcpu_chunk structure to reduce false sharing https://github.com/torvalds/linux/commit/3a6358c0dbe6a286a4f4504ba392a6039a9fbd12 To manage notifications about this bug go to: https://bugs.launchpad.net/ubuntu/+source/linux/+bug/2053152/+subscriptions -- Mailing list: https://launchpad.net/~kernel-packages Post to : kernel-packages@lists.launchpad.net Unsubscribe : https://launchpad.net/~kernel-packages More help : https://help.launchpad.net/ListHelp
[Kernel-packages] [Bug 2053152] Re: performance: mm/percpu-internal.h: Re-layout pcpu_chunk to mitigate false sharing
This bug is awaiting verification that the linux- aws-5.15/5.15.0-1057.63~20.04.1 kernel in -proposed solves the problem. Please test the kernel and update this bug with the results. If the problem is solved, change the tag 'verification-needed-focal-linux- aws-5.15' to 'verification-done-focal-linux-aws-5.15'. If the problem still exists, change the tag 'verification-needed-focal-linux-aws-5.15' to 'verification-failed-focal-linux-aws-5.15'. If verification is not done by 5 working days from today, this fix will be dropped from the source code, and this bug will be closed. See https://wiki.ubuntu.com/Testing/EnableProposed for documentation how to enable and use -proposed. Thank you! ** Tags added: kernel-spammed-focal-linux-aws-5.15-v2 verification-needed-focal-linux-aws-5.15 -- You received this bug notification because you are a member of Kernel Packages, which is subscribed to linux in Ubuntu. https://bugs.launchpad.net/bugs/2053152 Title: performance: mm/percpu-internal.h: Re-layout pcpu_chunk to mitigate false sharing Status in linux package in Ubuntu: Fix Released Status in linux source package in Jammy: Fix Committed Bug description: This is a public version of https://bugs.launchpad.net/bugs/2034984 [Description] When running UnixBench/Execl throughput case, false sharing is observed due to frequent read on base_addr and write on free_bytes, chunk_md. UnixBench/Execl represents a class of workload where bash scripts are spawned frequently to do some short jobs. It will do system call on execl frequently, and execl will call mm_init to initialize mm_struct of the process. mm_init will call __percpu_counter_init for percpu_counters initialization. Then pcpu_alloc is called to read the base_addr of pcpu_chunk for memory allocation. Inside pcpu_alloc, it will call pcpu_alloc_area to allocate memory from a specified chunk. This function will update "free_bytes" and "chunk_md" to record the rest free bytes and other meta data for this chunk. Correspondingly, pcpu_free_area will also update these 2 members when free memory. In current pcpu_chunk layout, `base_addr' is in the same cache line with `free_bytes' and `chunk_md', and `base_addr' is at the last 8 bytes. This patch moves `bound_map' up to `base_addr', to let `base_addr' locate in a new cacheline. [Hardware Information] Architecture: Intel / AMD (x86_64) Platform(s): Platform-Independent Date HW is expected at Canonical: Component(s): Performance and Scalability [Software Information] Target Version: 23.10 Target Kernel: 6.5 Commit IDs: 3a6358c0dbe6 percpu-internal/pcpu_chunk: re-layout pcpu_chunk structure to reduce false sharing External Links: [Business Justification] [Testing guidance] [External ID] OSVE-5160 The following requested patch has been applied upstream for v6.5-rc1: - 3a6358c0dbe6 percpu-internal/pcpu_chunk: re-layout pcpu_chunk structure to reduce false sharing https://github.com/torvalds/linux/commit/3a6358c0dbe6a286a4f4504ba392a6039a9fbd12 To manage notifications about this bug go to: https://bugs.launchpad.net/ubuntu/+source/linux/+bug/2053152/+subscriptions -- Mailing list: https://launchpad.net/~kernel-packages Post to : kernel-packages@lists.launchpad.net Unsubscribe : https://launchpad.net/~kernel-packages More help : https://help.launchpad.net/ListHelp
[Kernel-packages] [Bug 2053152] Re: performance: mm/percpu-internal.h: Re-layout pcpu_chunk to mitigate false sharing
This bug is awaiting verification that the linux-aws- fips/5.15.0-1057.63+fips1 kernel in -proposed solves the problem. Please test the kernel and update this bug with the results. If the problem is solved, change the tag 'verification-needed-jammy-linux-aws-fips' to 'verification-done-jammy-linux-aws-fips'. If the problem still exists, change the tag 'verification-needed-jammy-linux-aws-fips' to 'verification-failed-jammy-linux-aws-fips'. If verification is not done by 5 working days from today, this fix will be dropped from the source code, and this bug will be closed. See https://wiki.ubuntu.com/Testing/EnableProposed for documentation how to enable and use -proposed. Thank you! ** Tags added: kernel-spammed-jammy-linux-aws-fips-v2 verification-needed-jammy-linux-aws-fips -- You received this bug notification because you are a member of Kernel Packages, which is subscribed to linux in Ubuntu. https://bugs.launchpad.net/bugs/2053152 Title: performance: mm/percpu-internal.h: Re-layout pcpu_chunk to mitigate false sharing Status in linux package in Ubuntu: Fix Released Status in linux source package in Jammy: Fix Committed Bug description: This is a public version of https://bugs.launchpad.net/bugs/2034984 [Description] When running UnixBench/Execl throughput case, false sharing is observed due to frequent read on base_addr and write on free_bytes, chunk_md. UnixBench/Execl represents a class of workload where bash scripts are spawned frequently to do some short jobs. It will do system call on execl frequently, and execl will call mm_init to initialize mm_struct of the process. mm_init will call __percpu_counter_init for percpu_counters initialization. Then pcpu_alloc is called to read the base_addr of pcpu_chunk for memory allocation. Inside pcpu_alloc, it will call pcpu_alloc_area to allocate memory from a specified chunk. This function will update "free_bytes" and "chunk_md" to record the rest free bytes and other meta data for this chunk. Correspondingly, pcpu_free_area will also update these 2 members when free memory. In current pcpu_chunk layout, `base_addr' is in the same cache line with `free_bytes' and `chunk_md', and `base_addr' is at the last 8 bytes. This patch moves `bound_map' up to `base_addr', to let `base_addr' locate in a new cacheline. [Hardware Information] Architecture: Intel / AMD (x86_64) Platform(s): Platform-Independent Date HW is expected at Canonical: Component(s): Performance and Scalability [Software Information] Target Version: 23.10 Target Kernel: 6.5 Commit IDs: 3a6358c0dbe6 percpu-internal/pcpu_chunk: re-layout pcpu_chunk structure to reduce false sharing External Links: [Business Justification] [Testing guidance] [External ID] OSVE-5160 The following requested patch has been applied upstream for v6.5-rc1: - 3a6358c0dbe6 percpu-internal/pcpu_chunk: re-layout pcpu_chunk structure to reduce false sharing https://github.com/torvalds/linux/commit/3a6358c0dbe6a286a4f4504ba392a6039a9fbd12 To manage notifications about this bug go to: https://bugs.launchpad.net/ubuntu/+source/linux/+bug/2053152/+subscriptions -- Mailing list: https://launchpad.net/~kernel-packages Post to : kernel-packages@lists.launchpad.net Unsubscribe : https://launchpad.net/~kernel-packages More help : https://help.launchpad.net/ListHelp
[Kernel-packages] [Bug 2053152] Re: performance: mm/percpu-internal.h: Re-layout pcpu_chunk to mitigate false sharing
This bug is awaiting verification that the linux/5.15.0-102.112 kernel in -proposed solves the problem. Please test the kernel and update this bug with the results. If the problem is solved, change the tag 'verification-needed-jammy-linux' to 'verification-done-jammy-linux'. If the problem still exists, change the tag 'verification-needed-jammy- linux' to 'verification-failed-jammy-linux'. If verification is not done by 5 working days from today, this fix will be dropped from the source code, and this bug will be closed. See https://wiki.ubuntu.com/Testing/EnableProposed for documentation how to enable and use -proposed. Thank you! ** Tags added: kernel-spammed-jammy-linux-v2 verification-needed-jammy-linux -- You received this bug notification because you are a member of Kernel Packages, which is subscribed to linux in Ubuntu. https://bugs.launchpad.net/bugs/2053152 Title: performance: mm/percpu-internal.h: Re-layout pcpu_chunk to mitigate false sharing Status in linux package in Ubuntu: Fix Released Status in linux source package in Jammy: Fix Committed Bug description: This is a public version of https://bugs.launchpad.net/bugs/2034984 [Description] When running UnixBench/Execl throughput case, false sharing is observed due to frequent read on base_addr and write on free_bytes, chunk_md. UnixBench/Execl represents a class of workload where bash scripts are spawned frequently to do some short jobs. It will do system call on execl frequently, and execl will call mm_init to initialize mm_struct of the process. mm_init will call __percpu_counter_init for percpu_counters initialization. Then pcpu_alloc is called to read the base_addr of pcpu_chunk for memory allocation. Inside pcpu_alloc, it will call pcpu_alloc_area to allocate memory from a specified chunk. This function will update "free_bytes" and "chunk_md" to record the rest free bytes and other meta data for this chunk. Correspondingly, pcpu_free_area will also update these 2 members when free memory. In current pcpu_chunk layout, `base_addr' is in the same cache line with `free_bytes' and `chunk_md', and `base_addr' is at the last 8 bytes. This patch moves `bound_map' up to `base_addr', to let `base_addr' locate in a new cacheline. [Hardware Information] Architecture: Intel / AMD (x86_64) Platform(s): Platform-Independent Date HW is expected at Canonical: Component(s): Performance and Scalability [Software Information] Target Version: 23.10 Target Kernel: 6.5 Commit IDs: 3a6358c0dbe6 percpu-internal/pcpu_chunk: re-layout pcpu_chunk structure to reduce false sharing External Links: [Business Justification] [Testing guidance] [External ID] OSVE-5160 The following requested patch has been applied upstream for v6.5-rc1: - 3a6358c0dbe6 percpu-internal/pcpu_chunk: re-layout pcpu_chunk structure to reduce false sharing https://github.com/torvalds/linux/commit/3a6358c0dbe6a286a4f4504ba392a6039a9fbd12 To manage notifications about this bug go to: https://bugs.launchpad.net/ubuntu/+source/linux/+bug/2053152/+subscriptions -- Mailing list: https://launchpad.net/~kernel-packages Post to : kernel-packages@lists.launchpad.net Unsubscribe : https://launchpad.net/~kernel-packages More help : https://help.launchpad.net/ListHelp
[Kernel-packages] [Bug 2053152] Re: performance: mm/percpu-internal.h: Re-layout pcpu_chunk to mitigate false sharing
** Changed in: linux (Ubuntu Jammy) Status: In Progress => Fix Committed -- You received this bug notification because you are a member of Kernel Packages, which is subscribed to linux in Ubuntu. https://bugs.launchpad.net/bugs/2053152 Title: performance: mm/percpu-internal.h: Re-layout pcpu_chunk to mitigate false sharing Status in linux package in Ubuntu: Fix Released Status in linux source package in Jammy: Fix Committed Bug description: This is a public version of https://bugs.launchpad.net/bugs/2034984 [Description] When running UnixBench/Execl throughput case, false sharing is observed due to frequent read on base_addr and write on free_bytes, chunk_md. UnixBench/Execl represents a class of workload where bash scripts are spawned frequently to do some short jobs. It will do system call on execl frequently, and execl will call mm_init to initialize mm_struct of the process. mm_init will call __percpu_counter_init for percpu_counters initialization. Then pcpu_alloc is called to read the base_addr of pcpu_chunk for memory allocation. Inside pcpu_alloc, it will call pcpu_alloc_area to allocate memory from a specified chunk. This function will update "free_bytes" and "chunk_md" to record the rest free bytes and other meta data for this chunk. Correspondingly, pcpu_free_area will also update these 2 members when free memory. In current pcpu_chunk layout, `base_addr' is in the same cache line with `free_bytes' and `chunk_md', and `base_addr' is at the last 8 bytes. This patch moves `bound_map' up to `base_addr', to let `base_addr' locate in a new cacheline. [Hardware Information] Architecture: Intel / AMD (x86_64) Platform(s): Platform-Independent Date HW is expected at Canonical: Component(s): Performance and Scalability [Software Information] Target Version: 23.10 Target Kernel: 6.5 Commit IDs: 3a6358c0dbe6 percpu-internal/pcpu_chunk: re-layout pcpu_chunk structure to reduce false sharing External Links: [Business Justification] [Testing guidance] [External ID] OSVE-5160 The following requested patch has been applied upstream for v6.5-rc1: - 3a6358c0dbe6 percpu-internal/pcpu_chunk: re-layout pcpu_chunk structure to reduce false sharing https://github.com/torvalds/linux/commit/3a6358c0dbe6a286a4f4504ba392a6039a9fbd12 To manage notifications about this bug go to: https://bugs.launchpad.net/ubuntu/+source/linux/+bug/2053152/+subscriptions -- Mailing list: https://launchpad.net/~kernel-packages Post to : kernel-packages@lists.launchpad.net Unsubscribe : https://launchpad.net/~kernel-packages More help : https://help.launchpad.net/ListHelp
[Kernel-packages] [Bug 2053152] Re: performance: mm/percpu-internal.h: Re-layout pcpu_chunk to mitigate false sharing
Changed devel (main) task to fix-released since the proposed patch is upstream as of v6.5-rc1. ** Changed in: linux (Ubuntu) Status: In Progress => Fix Released ** Changed in: linux (Ubuntu Jammy) Importance: Undecided => Medium -- You received this bug notification because you are a member of Kernel Packages, which is subscribed to linux in Ubuntu. https://bugs.launchpad.net/bugs/2053152 Title: performance: mm/percpu-internal.h: Re-layout pcpu_chunk to mitigate false sharing Status in linux package in Ubuntu: Fix Released Status in linux source package in Jammy: In Progress Bug description: This is a public version of https://bugs.launchpad.net/bugs/2034984 [Description] When running UnixBench/Execl throughput case, false sharing is observed due to frequent read on base_addr and write on free_bytes, chunk_md. UnixBench/Execl represents a class of workload where bash scripts are spawned frequently to do some short jobs. It will do system call on execl frequently, and execl will call mm_init to initialize mm_struct of the process. mm_init will call __percpu_counter_init for percpu_counters initialization. Then pcpu_alloc is called to read the base_addr of pcpu_chunk for memory allocation. Inside pcpu_alloc, it will call pcpu_alloc_area to allocate memory from a specified chunk. This function will update "free_bytes" and "chunk_md" to record the rest free bytes and other meta data for this chunk. Correspondingly, pcpu_free_area will also update these 2 members when free memory. In current pcpu_chunk layout, `base_addr' is in the same cache line with `free_bytes' and `chunk_md', and `base_addr' is at the last 8 bytes. This patch moves `bound_map' up to `base_addr', to let `base_addr' locate in a new cacheline. [Hardware Information] Architecture: Intel / AMD (x86_64) Platform(s): Platform-Independent Date HW is expected at Canonical: Component(s): Performance and Scalability [Software Information] Target Version: 23.10 Target Kernel: 6.5 Commit IDs: 3a6358c0dbe6 percpu-internal/pcpu_chunk: re-layout pcpu_chunk structure to reduce false sharing External Links: [Business Justification] [Testing guidance] [External ID] OSVE-5160 The following requested patch has been applied upstream for v6.5-rc1: - 3a6358c0dbe6 percpu-internal/pcpu_chunk: re-layout pcpu_chunk structure to reduce false sharing https://github.com/torvalds/linux/commit/3a6358c0dbe6a286a4f4504ba392a6039a9fbd12 To manage notifications about this bug go to: https://bugs.launchpad.net/ubuntu/+source/linux/+bug/2053152/+subscriptions -- Mailing list: https://launchpad.net/~kernel-packages Post to : kernel-packages@lists.launchpad.net Unsubscribe : https://launchpad.net/~kernel-packages More help : https://help.launchpad.net/ListHelp
