From d45ed4a4e33ae103053c0a53d280014e7101bb5c Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Fri, 4 Oct 2013 00:14:06 -0700 Subject: net: fix unsafe set_memory_rw from softirq on x86 system with net.core.bpf_jit_enable = 1 sudo tcpdump -i eth1 'tcp port 22' causes the warning: [ 56.766097] Possible unsafe locking scenario: [ 56.766097] [ 56.780146] CPU0 [ 56.786807] ---- [ 56.793188] lock(&(&vb->lock)->rlock); [ 56.799593] [ 56.805889] lock(&(&vb->lock)->rlock); [ 56.812266] [ 56.812266] *** DEADLOCK *** [ 56.812266] [ 56.830670] 1 lock held by ksoftirqd/1/13: [ 56.836838] #0: (rcu_read_lock){.+.+..}, at: [] vm_unmap_aliases+0x8c/0x380 [ 56.849757] [ 56.849757] stack backtrace: [ 56.862194] CPU: 1 PID: 13 Comm: ksoftirqd/1 Not tainted 3.12.0-rc3+ #45 [ 56.868721] Hardware name: System manufacturer System Product Name/P8Z77 WS, BIOS 3007 07/26/2012 [ 56.882004] ffffffff821944c0 ffff88080bbdb8c8 ffffffff8175a145 0000000000000007 [ 56.895630] ffff88080bbd5f40 ffff88080bbdb928 ffffffff81755b14 0000000000000001 [ 56.909313] ffff880800000001 ffff880800000000 ffffffff8101178f 0000000000000001 [ 56.923006] Call Trace: [ 56.929532] [] dump_stack+0x55/0x76 [ 56.936067] [] print_usage_bug+0x1f7/0x208 [ 56.942445] [] ? save_stack_trace+0x2f/0x50 [ 56.948932] [] ? check_usage_backwards+0x150/0x150 [ 56.955470] [] mark_lock+0x282/0x2c0 [ 56.961945] [] __lock_acquire+0x45d/0x1d50 [ 56.968474] [] ? __lock_acquire+0x2de/0x1d50 [ 56.975140] [] ? cpumask_next_and+0x55/0x90 [ 56.981942] [] lock_acquire+0x92/0x1d0 [ 56.988745] [] ? vm_unmap_aliases+0x16a/0x380 [ 56.995619] [] _raw_spin_lock+0x41/0x50 [ 57.002493] [] ? vm_unmap_aliases+0x16a/0x380 [ 57.009447] [] vm_unmap_aliases+0x16a/0x380 [ 57.016477] [] ? vm_unmap_aliases+0x8c/0x380 [ 57.023607] [] change_page_attr_set_clr+0xc0/0x460 [ 57.030818] [] ? trace_hardirqs_on+0xd/0x10 [ 57.037896] [] ? kmem_cache_free+0xb0/0x2b0 [ 57.044789] [] ? free_object_rcu+0x93/0xa0 [ 57.051720] [] set_memory_rw+0x2f/0x40 [ 57.058727] [] bpf_jit_free+0x2c/0x40 [ 57.065577] [] sk_filter_release_rcu+0x1a/0x30 [ 57.072338] [] rcu_process_callbacks+0x202/0x7c0 [ 57.078962] [] __do_softirq+0xf7/0x3f0 [ 57.085373] [] run_ksoftirqd+0x35/0x70 cannot reuse jited filter memory, since it's readonly, so use original bpf insns memory to hold work_struct defer kfree of sk_filter until jit completed freeing tested on x86_64 and i386 Signed-off-by: Alexei Starovoitov Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- arch/x86/net/bpf_jit_comp.c | 18 +++++++++++++----- 1 file changed, 13 insertions(+), 5 deletions(-) (limited to 'arch/x86/net') diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 79c216aa0e2b..516593e1ce33 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -772,13 +772,21 @@ out: return; } +static void bpf_jit_free_deferred(struct work_struct *work) +{ + struct sk_filter *fp = container_of(work, struct sk_filter, work); + unsigned long addr = (unsigned long)fp->bpf_func & PAGE_MASK; + struct bpf_binary_header *header = (void *)addr; + + set_memory_rw(addr, header->pages); + module_free(NULL, header); + kfree(fp); +} + void bpf_jit_free(struct sk_filter *fp) { if (fp->bpf_func != sk_run_filter) { - unsigned long addr = (unsigned long)fp->bpf_func & PAGE_MASK; - struct bpf_binary_header *header = (void *)addr; - - set_memory_rw(addr, header->pages); - module_free(NULL, header); + INIT_WORK(&fp->work, bpf_jit_free_deferred); + schedule_work(&fp->work); } } -- cgit v1.2.1