From 519fabc7aaba3f0847cf37d5f9a5740c370eb777 Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Thu, 2 Mar 2023 17:13:46 -0800 Subject: [PATCH] psi: remove 500ms min window size limitation for triggers Current 500ms min window size for psi triggers limits polling interval to 50ms to prevent polling threads from using too much cpu bandwidth by polling too frequently. However the number of cgroups with triggers is unlimited, so this protection can be defeated by creating multiple cgroups with psi triggers (triggers in each cgroup are served by a single "psimon" kernel thread). Instead of limiting min polling period, which also limits the latency of psi events, it's better to limit psi trigger creation to authorized users only, like we do for system-wide psi triggers (/proc/pressure/* files can be written only by processes with CAP_SYS_RESOURCE capability). This also makes access rules for cgroup psi files consistent with system-wide ones. Add a CAP_SYS_RESOURCE capability check for cgroup psi file writers and remove the psi window min size limitation. Suggested-by: Sudarshan Rajagopalan Signed-off-by: Suren Baghdasaryan Signed-off-by: Peter Zijlstra (Intel) Acked-by: Michal Hocko Acked-by: Johannes Weiner Link: https://lore.kernel.org/all/cover.1676067791.git.quic_sudaraja@quicinc.com/ --- kernel/cgroup/cgroup.c | 12 ++++++++++++ kernel/sched/psi.c | 4 +--- 2 files changed, 13 insertions(+), 3 deletions(-) diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 625d7483951c..b26ae200abef 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -3877,6 +3877,14 @@ static __poll_t cgroup_pressure_poll(struct kernfs_open_file *of, return psi_trigger_poll(&ctx->psi.trigger, of->file, pt); } +static int cgroup_pressure_open(struct kernfs_open_file *of) +{ + if (of->file->f_mode & FMODE_WRITE && !capable(CAP_SYS_RESOURCE)) + return -EPERM; + + return 0; +} + static void cgroup_pressure_release(struct kernfs_open_file *of) { struct cgroup_file_ctx *ctx = of->priv; @@ -5276,6 +5284,7 @@ static struct cftype cgroup_psi_files[] = { { .name = "io.pressure", .file_offset = offsetof(struct cgroup, psi_files[PSI_IO]), + .open = cgroup_pressure_open, .seq_show = cgroup_io_pressure_show, .write = cgroup_io_pressure_write, .poll = cgroup_pressure_poll, @@ -5284,6 +5293,7 @@ static struct cftype cgroup_psi_files[] = { { .name = "memory.pressure", .file_offset = offsetof(struct cgroup, psi_files[PSI_MEM]), + .open = cgroup_pressure_open, .seq_show = cgroup_memory_pressure_show, .write = cgroup_memory_pressure_write, .poll = cgroup_pressure_poll, @@ -5292,6 +5302,7 @@ static struct cftype cgroup_psi_files[] = { { .name = "cpu.pressure", .file_offset = offsetof(struct cgroup, psi_files[PSI_CPU]), + .open = cgroup_pressure_open, .seq_show = cgroup_cpu_pressure_show, .write = cgroup_cpu_pressure_write, .poll = cgroup_pressure_poll, @@ -5301,6 +5312,7 @@ static struct cftype cgroup_psi_files[] = { { .name = "irq.pressure", .file_offset = offsetof(struct cgroup, psi_files[PSI_IRQ]), + .open = cgroup_pressure_open, .seq_show = cgroup_irq_pressure_show, .write = cgroup_irq_pressure_write, .poll = cgroup_pressure_poll, diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index e072f6b31bf3..b49af594ad28 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -160,7 +160,6 @@ __setup("psi=", setup_psi); #define EXP_300s 2034 /* 1/exp(2s/300s) */ /* PSI trigger definitions */ -#define WINDOW_MIN_US 500000 /* Min window size is 500ms */ #define WINDOW_MAX_US 10000000 /* Max window size is 10s */ #define UPDATES_PER_WINDOW 10 /* 10 updates per window */ @@ -1305,8 +1304,7 @@ struct psi_trigger *psi_trigger_create(struct psi_group *group, if (state >= PSI_NONIDLE) return ERR_PTR(-EINVAL); - if (window_us < WINDOW_MIN_US || - window_us > WINDOW_MAX_US) + if (window_us == 0 || window_us > WINDOW_MAX_US) return ERR_PTR(-EINVAL); /*