From 582db7e0c4c2fc5bb4f932f268035883385e3692 Mon Sep 17 00:00:00 2001 From: Tobias Klauser Date: Mon, 18 Sep 2017 15:03:46 +0200 Subject: bpf: devmap: pass on return value of bpf_map_precharge_memlock If bpf_map_precharge_memlock in dev_map_alloc, -ENOMEM is returned regardless of the actual error produced by bpf_map_precharge_memlock. Fix it by passing on the error returned by bpf_map_precharge_memlock. Also return -EINVAL instead of -ENOMEM if the page count overflow check fails. This makes dev_map_alloc match the behavior of other bpf maps' alloc functions wrt. return values. Signed-off-by: Tobias Klauser Acked-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- kernel/bpf/devmap.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c index 959c9a07f318..e093d9a2c4dd 100644 --- a/kernel/bpf/devmap.c +++ b/kernel/bpf/devmap.c @@ -75,8 +75,8 @@ static u64 dev_map_bitmap_size(const union bpf_attr *attr) static struct bpf_map *dev_map_alloc(union bpf_attr *attr) { struct bpf_dtab *dtab; + int err = -EINVAL; u64 cost; - int err; /* check sanity of attributes */ if (attr->max_entries == 0 || attr->key_size != 4 || @@ -108,6 +108,8 @@ static struct bpf_map *dev_map_alloc(union bpf_attr *attr) if (err) goto free_dtab; + err = -ENOMEM; + /* A per cpu bitfield with a bit per possible net device */ dtab->flush_needed = __alloc_percpu(dev_map_bitmap_size(attr), __alignof__(unsigned long)); @@ -128,7 +130,7 @@ static struct bpf_map *dev_map_alloc(union bpf_attr *attr) free_dtab: free_percpu(dtab->flush_needed); kfree(dtab); - return ERR_PTR(-ENOMEM); + return ERR_PTR(err); } static void dev_map_free(struct bpf_map *map) -- cgit v1.2.3 From 930651a75bf1ba6893a8b8475270664ebdb6cf4a Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 19 Sep 2017 09:15:59 -0700 Subject: bpf: do not disable/enable BH in bpf_map_free_id() syzkaller reported following splat [1] Since hard irq are disabled by the caller, bpf_map_free_id() should not try to enable/disable BH. Another solution would be to change htab_map_delete_elem() to defer the free_htab_elem() call after raw_spin_unlock_irqrestore(&b->lock, flags), but this might be not enough to cover other code paths. [1] WARNING: CPU: 1 PID: 8052 at kernel/softirq.c:161 __local_bh_enable_ip +0x1e/0x160 kernel/softirq.c:161 Kernel panic - not syncing: panic_on_warn set ... CPU: 1 PID: 8052 Comm: syz-executor1 Not tainted 4.13.0-next-20170915+ #23 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:16 [inline] dump_stack+0x194/0x257 lib/dump_stack.c:52 panic+0x1e4/0x417 kernel/panic.c:181 __warn+0x1c4/0x1d9 kernel/panic.c:542 report_bug+0x211/0x2d0 lib/bug.c:183 fixup_bug+0x40/0x90 arch/x86/kernel/traps.c:178 do_trap_no_signal arch/x86/kernel/traps.c:212 [inline] do_trap+0x260/0x390 arch/x86/kernel/traps.c:261 do_error_trap+0x120/0x390 arch/x86/kernel/traps.c:298 do_invalid_op+0x1b/0x20 arch/x86/kernel/traps.c:311 invalid_op+0x18/0x20 arch/x86/entry/entry_64.S:905 RIP: 0010:__local_bh_enable_ip+0x1e/0x160 kernel/softirq.c:161 RSP: 0018:ffff8801cdcd7748 EFLAGS: 00010046 RAX: 0000000000000082 RBX: 0000000000000201 RCX: 0000000000000000 RDX: 1ffffffff0b5933c RSI: 0000000000000201 RDI: ffffffff85ac99e0 RBP: ffff8801cdcd7758 R08: ffffffff85b87158 R09: 1ffff10039b9aec6 R10: ffff8801c99f24c0 R11: 0000000000000002 R12: ffffffff817b0b47 R13: dffffc0000000000 R14: ffff8801cdcd77e8 R15: 0000000000000001 __raw_spin_unlock_bh include/linux/spinlock_api_smp.h:176 [inline] _raw_spin_unlock_bh+0x30/0x40 kernel/locking/spinlock.c:207 spin_unlock_bh include/linux/spinlock.h:361 [inline] bpf_map_free_id kernel/bpf/syscall.c:197 [inline] __bpf_map_put+0x267/0x320 kernel/bpf/syscall.c:227 bpf_map_put+0x1a/0x20 kernel/bpf/syscall.c:235 bpf_map_fd_put_ptr+0x15/0x20 kernel/bpf/map_in_map.c:96 free_htab_elem+0xc3/0x1b0 kernel/bpf/hashtab.c:658 htab_map_delete_elem+0x74d/0x970 kernel/bpf/hashtab.c:1063 map_delete_elem kernel/bpf/syscall.c:633 [inline] SYSC_bpf kernel/bpf/syscall.c:1479 [inline] SyS_bpf+0x2188/0x46a0 kernel/bpf/syscall.c:1451 entry_SYSCALL_64_fastpath+0x1f/0xbe Fixes: f3f1c054c288 ("bpf: Introduce bpf_map ID") Signed-off-by: Eric Dumazet Cc: Martin KaFai Lau Acked-by: Martin KaFai Lau Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- kernel/bpf/syscall.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index cb17e1cd1d43..25d074920a00 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -186,15 +186,17 @@ static int bpf_map_alloc_id(struct bpf_map *map) static void bpf_map_free_id(struct bpf_map *map, bool do_idr_lock) { + unsigned long flags; + if (do_idr_lock) - spin_lock_bh(&map_idr_lock); + spin_lock_irqsave(&map_idr_lock, flags); else __acquire(&map_idr_lock); idr_remove(&map_idr, map->id); if (do_idr_lock) - spin_unlock_bh(&map_idr_lock); + spin_unlock_irqrestore(&map_idr_lock, flags); else __release(&map_idr_lock); } -- cgit v1.2.3 From 7c30013133964aaa2f45c17d6e9782ac6cfd7f5f Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Wed, 20 Sep 2017 00:44:21 +0200 Subject: bpf: fix ri->map_owner pointer on bpf_prog_realloc Commit 109980b894e9 ("bpf: don't select potentially stale ri->map from buggy xdp progs") passed the pointer to the prog itself to be loaded into r4 prior on bpf_redirect_map() helper call, so that we can store the owner into ri->map_owner out of the helper. Issue with that is that the actual address of the prog is still subject to change when subsequent rewrites occur that require slow path in bpf_prog_realloc() to alloc more memory, e.g. from patching inlining helper functions or constant blinding. Thus, we really need to take prog->aux as the address we're holding, which also works with prog clones as they share the same aux object. Instead of then fetching aux->prog during runtime, which could potentially incur cache misses due to false sharing, we are going to just use aux for comparison on the map owner. This will also keep the patchlet of the same size, and later check in xdp_map_invalid() only accesses read-only aux pointer from the prog, it's also in the same cacheline already from prior access when calling bpf_func. Fixes: 109980b894e9 ("bpf: don't select potentially stale ri->map from buggy xdp progs") Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- kernel/bpf/verifier.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 799b2451ef2d..b914fbe1383e 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -4205,7 +4205,12 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env) } if (insn->imm == BPF_FUNC_redirect_map) { - u64 addr = (unsigned long)prog; + /* Note, we cannot use prog directly as imm as subsequent + * rewrites would still change the prog pointer. The only + * stable address we can use is aux, which also works with + * prog clones during blinding. + */ + u64 addr = (unsigned long)prog->aux; struct bpf_insn r4_ld[] = { BPF_LD_IMM64(BPF_REG_4, addr), *insn, -- cgit v1.2.3 From ec9dd352d591f0c90402ec67a317c1ed4fb2e638 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Mon, 18 Sep 2017 16:38:36 -0700 Subject: bpf: one perf event close won't free bpf program attached by another perf event This patch fixes a bug exhibited by the following scenario: 1. fd1 = perf_event_open with attr.config = ID1 2. attach bpf program prog1 to fd1 3. fd2 = perf_event_open with attr.config = ID1 4. user program closes fd2 and prog1 is detached from the tracepoint. 5. user program with fd1 does not work properly as tracepoint no output any more. The issue happens at step 4. Multiple perf_event_open can be called successfully, but only one bpf prog pointer in the tp_event. In the current logic, any fd release for the same tp_event will free the tp_event->prog. The fix is to free tp_event->prog only when the closing fd corresponds to the one which registered the program. Signed-off-by: Yonghong Song Signed-off-by: David S. Miller --- kernel/events/core.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/events/core.c b/kernel/events/core.c index 3e691b75b2db..6bc21e202ae4 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -8171,6 +8171,7 @@ static int perf_event_set_bpf_prog(struct perf_event *event, u32 prog_fd) } } event->tp_event->prog = prog; + event->tp_event->bpf_prog_owner = event; return 0; } @@ -8185,7 +8186,7 @@ static void perf_event_free_bpf_prog(struct perf_event *event) return; prog = event->tp_event->prog; - if (prog) { + if (prog && event->tp_event->bpf_prog_owner == event) { event->tp_event->prog = NULL; bpf_prog_put(prog); } -- cgit v1.2.3