From aff1871bfc81e9dffa7d2a77e67cc5441cc37f81 Mon Sep 17 00:00:00 2001 From: Viktor Malik Date: Mon, 26 Aug 2024 08:07:18 +0200 Subject: objpool: fix choosing allocation for percpu slots objpool intends to use vmalloc for default (non-atomic) allocations of percpu slots and objects. However, the condition checking if GFP flags set any bit of GFP_ATOMIC is wrong b/c GFP_ATOMIC is a combination of bits (__GFP_HIGH|__GFP_KSWAPD_RECLAIM) and so `pool->gfp & GFP_ATOMIC` will be true if either bit is set. Since GFP_ATOMIC and GFP_KERNEL share the ___GFP_KSWAPD_RECLAIM bit, kmalloc will be used in cases when GFP_KERNEL is specified, i.e. in all current usages of objpool. This may lead to unexpected OOM errors since kmalloc cannot allocate large amounts of memory. For instance, objpool is used by fprobe rethook which in turn is used by BPF kretprobe.multi and kprobe.session probe types. Trying to attach these to all kernel functions with libbpf using SEC("kprobe.session/*") int kprobe(struct pt_regs *ctx) { [...] } fails on objpool slot allocation with ENOMEM. Fix the condition to truly use vmalloc by default. Link: https://lore.kernel.org/all/20240826060718.267261-1-vmalik@redhat.com/ Fixes: b4edb8d2d464 ("lib: objpool added: ring-array based lockless MPMC") Signed-off-by: Viktor Malik Acked-by: Andrii Nakryiko Reviewed-by: Matt Wu Signed-off-by: Masami Hiramatsu (Google) --- lib/objpool.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'lib/objpool.c') diff --git a/lib/objpool.c b/lib/objpool.c index 234f9d0bd081..fd108fe0d095 100644 --- a/lib/objpool.c +++ b/lib/objpool.c @@ -76,7 +76,7 @@ objpool_init_percpu_slots(struct objpool_head *pool, int nr_objs, * mimimal size of vmalloc is one page since vmalloc would * always align the requested size to page size */ - if (pool->gfp & GFP_ATOMIC) + if ((pool->gfp & GFP_ATOMIC) == GFP_ATOMIC) slot = kmalloc_node(size, pool->gfp, cpu_to_node(i)); else slot = __vmalloc_node(size, sizeof(void *), pool->gfp, -- cgit From cb6fcef8b4b6c655b6a25cc3a415cd9eb81b3da8 Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Mon, 28 Oct 2024 12:26:27 +0900 Subject: objpool: fix to make percpu slot allocation more robust Since gfp & GFP_ATOMIC == GFP_ATOMIC is true for GFP_KERNEL | GFP_HIGH, it will use kmalloc if user specifies that combination. Here the reason why combining the __vmalloc_node() and kmalloc_node() is that the vmalloc does not support all GFP flag, especially GFP_ATOMIC. So we should check if gfp & (GFP_ATOMIC | GFP_KERNEL) != GFP_ATOMIC for vmalloc first. This ensures caller can sleep. And for the robustness, even if vmalloc fails, it should retry with kmalloc to allocate it. Link: https://lkml.kernel.org/r/173008598713.1262174.2959179484209897252.stgit@mhiramat.roam.corp.google.com Fixes: aff1871bfc81 ("objpool: fix choosing allocation for percpu slots") Signed-off-by: Masami Hiramatsu (Google) Reported-by: Linus Torvalds Closes: https://lore.kernel.org/all/CAHk-=whO+vSH+XVRio8byJU8idAWES0SPGVZ7KAVdc4qrV0VUA@mail.gmail.com/ Cc: Leo Yan Cc: Linus Torvalds Cc: Matt Wu Cc: Mikel Rychliski Cc: Steven Rostedt (Google) Cc: Viktor Malik Signed-off-by: Andrew Morton --- lib/objpool.c | 18 ++++++++++++------ 1 file changed, 12 insertions(+), 6 deletions(-) (limited to 'lib/objpool.c') diff --git a/lib/objpool.c b/lib/objpool.c index fd108fe0d095..b998b720c732 100644 --- a/lib/objpool.c +++ b/lib/objpool.c @@ -74,15 +74,21 @@ objpool_init_percpu_slots(struct objpool_head *pool, int nr_objs, * warm caches and TLB hits. in default vmalloc is used to * reduce the pressure of kernel slab system. as we know, * mimimal size of vmalloc is one page since vmalloc would - * always align the requested size to page size + * always align the requested size to page size. + * but if vmalloc fails or it is not available (e.g. GFP_ATOMIC) + * allocate percpu slot with kmalloc. */ - if ((pool->gfp & GFP_ATOMIC) == GFP_ATOMIC) - slot = kmalloc_node(size, pool->gfp, cpu_to_node(i)); - else + slot = NULL; + + if ((pool->gfp & (GFP_ATOMIC | GFP_KERNEL)) != GFP_ATOMIC) slot = __vmalloc_node(size, sizeof(void *), pool->gfp, cpu_to_node(i), __builtin_return_address(0)); - if (!slot) - return -ENOMEM; + + if (!slot) { + slot = kmalloc_node(size, pool->gfp, cpu_to_node(i)); + if (!slot) + return -ENOMEM; + } memset(slot, 0, size); pool->cpu_slots[i] = slot; -- cgit