From 8282cb36d021835e6574c393df6a4aed1bf6ada3 Mon Sep 17 00:00:00 2001 From: Jianlin Shi Date: Thu, 6 Aug 2026 16:27:34 +0800 Subject: [PATCH] mm/page_alloc: only update lowmem_reserve_ratio on sysctl write lowmem_reserve_ratio_sysctl_handler() ignores the return value of proc_dointvec_minmax() and always calls setup_per_zone_lowmem_reserve(), even for read operations. Fix three issues: 1. Propagate errors from proc_dointvec_minmax() instead of always returning success. For example, writing non-integer garbage to the sysctl now returns an error instead of silently succeeding with unchanged values. 2. Only call setup_per_zone_lowmem_reserve() when the sysctl is actually written, matching the write-only refresh pattern of min_free_kbytes and watermark_scale_factor handlers. 3. On write, parse into a temporary ratio[] array and only copy into sysctl_lowmem_reserve_ratio[] and refresh derived state after the full vector is validated. This avoids leaving the ratio array partially updated while skipping setup when proc_dointvec_minmax() returns an error on a later element (suggested by Andrew Morton). Drop the manual "< 1 -> 0" sanitization loop and set .extra1 = SYSCTL_ZERO on the ctl_table entry so proc_dointvec_minmax() enforces the minimum on write; negative values now return -EINVAL instead of being silently coerced to 0 (suggested by Vlastimil Babka). [akpm@linux-foundation.org: add comment, per hannes] Link: https://lore.kernel.org/anSRGASe5FIrqwlg@cmpxchg.org Link: https://lore.kernel.org/linux-mm/tencent_FFD4F4D728AAE8A8AE0AF277A59854A29A06@qq.com/ Link: https://lore.kernel.org/tencent_A860C873956A52E26AD8D309A308A241BA08@qq.com Signed-off-by: Jianlin Shi Acked-by: Vlastimil Babka (SUSE) Cc: Brendan Jackman Cc: Johannes Weiner Cc: Michal Hocko Cc: Suren Baghdasaryan Cc: Zi Yan Cc: Joel Granados Signed-off-by: Andrew Morton --- mm/page_alloc.c | 28 ++++++++++++++++++++-------- 1 file changed, 20 insertions(+), 8 deletions(-) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 083cbcb5bdde..12fac9084c48 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -6853,8 +6853,8 @@ static int sysctl_min_slab_ratio_sysctl_handler(const struct ctl_table *table, i /* * lowmem_reserve_ratio_sysctl_handler - just a wrapper around - * proc_dointvec() so that we can call setup_per_zone_lowmem_reserve() - * whenever sysctl_lowmem_reserve_ratio changes. + * proc_dointvec_minmax() so that we can call + * setup_per_zone_lowmem_reserve() when the sysctl is written. * * The reserve ratio obviously has absolutely no relation with the * minimum watermarks. The lowmem reserve ratio can only make sense @@ -6863,16 +6863,27 @@ static int sysctl_min_slab_ratio_sysctl_handler(const struct ctl_table *table, i static int lowmem_reserve_ratio_sysctl_handler(const struct ctl_table *table, int write, void *buffer, size_t *length, loff_t *ppos) { - int i; + struct ctl_table tmp = *table; + int ratio[ARRAY_SIZE(sysctl_lowmem_reserve_ratio)]; + int rc; - proc_dointvec_minmax(table, write, buffer, length, ppos); + if (!write) + return proc_dointvec_minmax(table, write, buffer, length, ppos); - for (i = 0; i < MAX_NR_ZONES; i++) { - if (sysctl_lowmem_reserve_ratio[i] < 1) - sysctl_lowmem_reserve_ratio[i] = 0; - } + /* + * proc_dointvec_max() works incrementally. Use a buffer and only set + * the values if all of them parse cleanly. + */ + memcpy(ratio, sysctl_lowmem_reserve_ratio, sizeof(ratio)); + tmp.data = ratio; + rc = proc_dointvec_minmax(&tmp, write, buffer, length, ppos); + if (rc) + return rc; + + memcpy(sysctl_lowmem_reserve_ratio, ratio, sizeof(ratio)); setup_per_zone_lowmem_reserve(); + return 0; } @@ -6971,6 +6982,7 @@ static const struct ctl_table page_alloc_sysctl_table[] = { .maxlen = sizeof(sysctl_lowmem_reserve_ratio), .mode = 0644, .proc_handler = lowmem_reserve_ratio_sysctl_handler, + .extra1 = SYSCTL_ZERO, }, #ifdef CONFIG_NUMA {