| 文件 | 最后提交记录 | 最后更新时间 |
|---|---|---|
docs: admin-guide: sysctl: avoid using ReST :doc: foo markup The :doc:foo tag is auto-generated via automarkup.py. So, use the filename at the sources, instead of :doc:foo. Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org> Link: https://lore.kernel.org/r/12abd2290c7ebc05c89178d2556bea740bd70fac.1623824363.git.mchehab+huawei@kernel.org Signed-off-by: Jonathan Corbet <corbet@lwn.net> | 5 年前 | |
fuse: enable dynamic configuration of fuse max pages limit (FUSE_MAX_MAX_PAGES) mainline inclusion from mainline-v6.13-rc1 commit 2b3933b1e0a0a4b758fbc164bb31db0c113a7e2c category: feature bugzilla: https://gitee.com/src-openeuler/kernel/issues/IC6CFR Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=2b3933b1e0a0a4b758fbc164bb31db0c113a7e2c -------------------------------- Introduce the capability to dynamically configure the max pages limit (FUSE_MAX_MAX_PAGES) through a sysctl. This allows system administrators to dynamically set the maximum number of pages that can be used for servicing requests in fuse. Previously, this is gated by FUSE_MAX_MAX_PAGES which is statically set to 256 pages. One result of this is that the buffer size for a write request is limited to 1 MiB on a 4k-page system. The default value for this sysctl is the original limit (256 pages). $ sysctl -a | grep max_pages_limit fs.fuse.max_pages_limit = 256 $ sysctl -n fs.fuse.max_pages_limit 256 $ echo 1024 | sudo tee /proc/sys/fs/fuse/max_pages_limit 1024 $ sysctl -n fs.fuse.max_pages_limit 1024 $ echo 65536 | sudo tee /proc/sys/fs/fuse/max_pages_limit tee: /proc/sys/fs/fuse/max_pages_limit: Invalid argument $ echo 0 | sudo tee /proc/sys/fs/fuse/max_pages_limit tee: /proc/sys/fs/fuse/max_pages_limit: Invalid argument $ echo 65535 | sudo tee /proc/sys/fs/fuse/max_pages_limit 65535 $ sysctl -n fs.fuse.max_pages_limit 65535 Signed-off-by: Joanne Koong <joannelkoong@gmail.com> Reviewed-by: Josef Bacik <josef@toxicpanda.com> Reviewed-by: Sweet Tea Dorminy <sweettea-kernel@dorminy.me> Signed-off-by: Miklos Szeredi <mszeredi@redhat.com> Signed-off-by: Wang Zhaolong <wangzhaolong1@huawei.com> | 1 年前 | |
docs: admin-guide: move sysctl directory to it The stuff under sysctl describes /sys interface from userspace point of view. So, add it to the admin-guide and remove the :orphan: from its index file. Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org> | 6 年前 | |
arm64: Add runtime switch to control ESB for SEI synchronization hulk inclusion category: feature bugzilla: https://atomgit.com/openeuler/kernel/issues/9116 ------------------------------------------ Background: ESB (Error Synchronization Barrier) is used to synchronize SEI (SError Interrupt) at exception boundaries in firmware-first RAS model. However, ESB has performance impact and may not be needed on all platforms. Design: Add runtime sysctl (/proc/sys/kernel/arm64_sync_sei) that allows dynamic toggling of ESB (Error Synchronization Barrier) instruction patching at exception entry boundaries without rebooting. insertion: - Default is disabled (arm64_sync_sei = false) to minimize impact - When enabled via 'arm64_sync_sei', ESB is inserted at: - Exception entry from EL0 - Exception return to EL0 (before ERET) - Use linker section (.esb_patch_table) to collect ESB patch point addresses at link time, then aarch64_insn_patch_text() to atomically swap ESB/NOP instructions across all CPUs at runtime. - Simplify arm64_sync_sei_cb() (alternative_cb for sei_restore_sp_el0) to depend solely on ARM64_HAS_RAS_EXTN capability rather than the dynamic toggle, since SP_EL0 restoration in the el1h_64_error handler is a firmware-first correctness requirement independent of whether ESB is active at exception entry. Signed-off-by: Zheng Chuan <zhengchuan@huawei.com> Signed-off-by: Wupeng Ma <mawupeng1@huawei.com> Signed-off-by: Deng Guangxing <dengguangxing@huawei.com> | 2 个月前 | |
net: make SK_MEMORY_PCPU_RESERV tunable stable inclusion from stable-v6.6.30 commit fe1e83811c4f3eba1f202572a89e968d9d2a433d bugzilla: https://gitee.com/openeuler/kernel/issues/I9MPZ8 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=fe1e83811c4f3eba1f202572a89e968d9d2a433d -------------------------------- [ Upstream commit 12a686c2e761f1f1f6e6e2117a9ab9c6de2ac8a7 ] This patch adds /proc/sys/net/core/mem_pcpu_rsv sysctl file, to make SK_MEMORY_PCPU_RESERV tunable. Commit 3cd3399dd7a8 ("net: implement per-cpu reserves for memory_allocated") introduced per-cpu forward alloc cache: "Implement a per-cpu cache of +1/-1 MB, to reduce number of changes to sk->sk_prot->memory_allocated, which would otherwise be cause of false sharing." sk_prot->memory_allocated points to global atomic variable: atomic_long_t tcp_memory_allocated ____cacheline_aligned_in_smp; If increasing the per-cpu cache size from 1MB to e.g. 16MB, changes to sk->sk_prot->memory_allocated can be further reduced. Performance may be improved on system with many cores. Signed-off-by: Adam Li <adamli@os.amperecomputing.com> Reviewed-by: Christoph Lameter (Ampere) <cl@linux.com> Signed-off-by: David S. Miller <davem@davemloft.net> Stable-dep-of: 3584718cf2ec ("net: fix sk_memory_allocated_{add|sub} vs softirqs") Signed-off-by: Sasha Levin <sashal@kernel.org> Signed-off-by: ZhangPeng <zhangpeng362@huawei.com> | 2 年前 | |
docs: admin-guide: move sysctl directory to it The stuff under sysctl describes /sys interface from userspace point of view. So, add it to the admin-guide and remove the :orphan: from its index file. Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org> | 6 年前 | |
time/namespace: Add max_time_namespaces ucount Michael noticed that userns limit for number of time namespaces is missing. Furthermore, time namespace introduced UCOUNT_TIME_NAMESPACES, but didn't introduce an array member in user_table[]. It would make array's initialisation OOB write, but by luck the user_table array has an excessive empty member (all accesses to the array are limited with UCOUNT_COUNTS - so it silently reuses the last free member. Fixes user-visible regression: max_inotify_instances by reason of the missing UCOUNT_ENTRY() has limited max number of namespaces instead of the number of inotify instances. Fixes: 769071ac9f20 ("ns: Introduce Time Namespace") Reported-by: Michael Kerrisk (man-pages) <mtk.manpages@gmail.com> Signed-off-by: Dmitry Safonov <dima@arista.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Andrei Vagin <avagin@gmail.com> Acked-by: Vincenzo Frascino <vincenzo.frascino@arm.com> Cc: stable@kernel.org Link: https://lkml.kernel.org/r/20200406171342.128733-1-dima@arista.com | 6 年前 | |
docs: memcg: document memory.qos_level and memcg_qos_enable hulk inclusion category: docs bugzilla: https://atomgit.com/openeuler/kernel/issues/9471 -------------------------------- Add the missing interface documentation for the memcg OOM priority feature, covering the per-cgroup memory.qos_level knob on both cgroup-v1 and cgroup-v2, and the memcg_qos_enable sysctl that gates the feature. Signed-off-by: Jinjiang Tu <tujinjiang@huawei.com> | 28 天前 |