From da61267fedac3d3e498b48b039c7ec9ccec7d446 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Sun, 18 Dec 2016 01:52:58 +0100 Subject: [PATCH] bpf: fix overflow in prog accounting commit 5ccb071e97fbd9ffe623a0d3977cc6d013bee93c upstream. Commit aaac3ba95e4c ("bpf: charge user for creation of BPF maps and programs") made a wrong assumption of charging against prog->pages. Unlike map->pages, prog->pages are still subject to change when we need to expand the program through bpf_prog_realloc(). This can for example happen during verification stage when we need to expand and rewrite parts of the program. Should the required space cross a page boundary, then prog->pages is not the same anymore as its original value that we used to bpf_prog_charge_memlock() on. Thus, we'll hit a wrap-around during bpf_prog_uncharge_memlock() when prog is freed eventually. I noticed this that despite having unlimited memlock, programs suddenly refused to load with EPERM error due to insufficient memlock. There are two ways to fix this issue. One would be to add a cached variable to struct bpf_prog that takes a snapshot of prog->pages at the time of charging. The other approach is to also account for resizes. I chose to go with the latter for a couple of reasons: i) We want accounting rather to be more accurate instead of further fooling limits, ii) adding yet another page counter on struct bpf_prog would also be a waste just for this purpose. We also do want to charge as early as possible to avoid going into the verifier just to find out later on that we crossed limits. The only place that needs to be fixed is bpf_prog_realloc(), since only here we expand the program, so we try to account for the needed delta and should we fail, call-sites check for outcome anyway. On cBPF to eBPF migrations, we don't grab a reference to the user as they are charged differently. With that in place, my test case worked fine. Fixes: aaac3ba95e4c ("bpf: charge user for creation of BPF maps and programs") Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller [Quentin: backport to 4.9: Adjust context in bpf.h ] Signed-off-by: Quentin Monnet Signed-off-by: Greg Kroah-Hartman Change-Id: Ia30ba68eb099c1f6c091b37a7c1af257b227dbef --- include/linux/bpf.h | 10 +++++----- kernel/bpf/core.c | 16 +++++++++++++--- kernel/bpf/syscall.c | 36 ++++++++++++++++++++++++++++-------- 3 files changed, 46 insertions(+), 16 deletions(-) diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 249aac97b99e..c0f33c4b2893 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -255,6 +255,8 @@ struct bpf_prog *bpf_prog_get_type(u32 ufd, enum bpf_prog_type type); struct bpf_prog *bpf_prog_add(struct bpf_prog *prog, int i); struct bpf_prog *bpf_prog_inc(struct bpf_prog *prog); void bpf_prog_put(struct bpf_prog *prog); +int __bpf_prog_charge(struct user_struct *user, u32 pages); +void __bpf_prog_uncharge(struct user_struct *user, u32 pages); struct bpf_map *bpf_map_get_with_uref(u32 ufd); struct bpf_map *__bpf_map_get(struct fd f); @@ -342,15 +344,13 @@ static inline struct bpf_prog *bpf_prog_inc(struct bpf_prog *prog) return ERR_PTR(-EOPNOTSUPP); } -static inline int bpf_obj_get_user(const char __user *pathname) +static inline int __bpf_prog_charge(struct user_struct *user, u32 pages) { - return -EOPNOTSUPP; + return 0; } -static inline struct bpf_prog *bpf_prog_get_type_path(const char *name, - enum bpf_prog_type type) +static inline void __bpf_prog_uncharge(struct user_struct *user, u32 pages) { - return ERR_PTR(-EOPNOTSUPP); } static inline bool unprivileged_ebpf_enabled(void) diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 96c972fbea28..fba88a6128bd 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -107,19 +107,29 @@ struct bpf_prog *bpf_prog_realloc(struct bpf_prog *fp_old, unsigned int size, gfp_t gfp_flags = GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO | gfp_extra_flags; struct bpf_prog *fp; + u32 pages, delta; + int ret; BUG_ON(fp_old == NULL); size = round_up(size, PAGE_SIZE); - if (size <= fp_old->pages * PAGE_SIZE) + pages = size / PAGE_SIZE; + if (pages <= fp_old->pages) return fp_old; + delta = pages - fp_old->pages; + ret = __bpf_prog_charge(fp_old->aux->user, delta); + if (ret) + return NULL; + fp = __vmalloc(size, gfp_flags, PAGE_KERNEL); - if (fp != NULL) { + if (fp == NULL) { + __bpf_prog_uncharge(fp_old->aux->user, delta); + } else { kmemcheck_annotate_bitfield(fp, meta); memcpy(fp, fp_old, fp_old->pages * PAGE_SIZE); - fp->pages = size / PAGE_SIZE; + fp->pages = pages; fp->aux->prog = fp; /* We keep fp->aux from fp_old around in the new diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 5b5ad0b22404..92fbf162b191 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -652,19 +652,39 @@ static void free_used_maps(struct bpf_prog_aux *aux) kfree(aux->used_maps); } +int __bpf_prog_charge(struct user_struct *user, u32 pages) +{ + unsigned long memlock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT; + unsigned long user_bufs; + + if (user) { + user_bufs = atomic_long_add_return(pages, &user->locked_vm); + if (user_bufs > memlock_limit) { + atomic_long_sub(pages, &user->locked_vm); + return -EPERM; + } + } + + return 0; +} + +void __bpf_prog_uncharge(struct user_struct *user, u32 pages) +{ + if (user) + atomic_long_sub(pages, &user->locked_vm); +} + static int bpf_prog_charge_memlock(struct bpf_prog *prog) { struct user_struct *user = get_current_user(); - unsigned long memlock_limit; + int ret; - memlock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT; - - atomic_long_add(prog->pages, &user->locked_vm); - if (atomic_long_read(&user->locked_vm) > memlock_limit) { - atomic_long_sub(prog->pages, &user->locked_vm); + ret = __bpf_prog_charge(user, prog->pages); + if (ret) { free_uid(user); - return -EPERM; + return ret; } + prog->aux->user = user; return 0; } @@ -673,7 +693,7 @@ static void bpf_prog_uncharge_memlock(struct bpf_prog *prog) { struct user_struct *user = prog->aux->user; - atomic_long_sub(prog->pages, &user->locked_vm); + __bpf_prog_uncharge(user, prog->pages); free_uid(user); }