From 17f41571bb2c4a398785452ac2718a6c5d77180e Mon Sep 17 00:00:00 2001 From: Jiri Kosina Date: Tue, 23 Jul 2013 10:09:28 +0200 Subject: [PATCH] kprobes/x86: Call out into INT3 handler directly instead of using notifier In fd4363fff3d96 ("x86: Introduce int3 (breakpoint)-based instruction patching"), the mechanism that was introduced for notifying alternatives code from int3 exception handler that and exception occured was die_notifier. This is however problematic, as early code might be using jump labels even before the notifier registration has been performed, which will then lead to an oops due to unhandled exception. One of such occurences has been encountered by Fengguang: int3: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC Modules linked in: CPU: 1 PID: 0 Comm: swapper/1 Not tainted 3.11.0-rc1-01429-g04bf576 #8 task: ffff88000da1b040 ti: ffff88000da1c000 task.ti: ffff88000da1c000 RIP: 0010:[] [] ttwu_do_wakeup+0x28/0x225 RSP: 0000:ffff88000dd03f10 EFLAGS: 00000006 RAX: 0000000000000000 RBX: ffff88000dd12940 RCX: ffffffff81769c40 RDX: 0000000000000002 RSI: 0000000000000000 RDI: 0000000000000001 RBP: ffff88000dd03f28 R08: ffffffff8176a8c0 R09: 0000000000000002 R10: ffffffff810ff484 R11: ffff88000dd129e8 R12: ffff88000dbc90c0 R13: ffff88000dbc90c0 R14: ffff88000da1dfd8 R15: ffff88000da1dfd8 FS: 0000000000000000(0000) GS:ffff88000dd00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b CR2: 00000000ffffffff CR3: 0000000001c88000 CR4: 00000000000006e0 Stack: ffff88000dd12940 ffff88000dbc90c0 ffff88000da1dfd8 ffff88000dd03f48 ffffffff81109e2b ffff88000dd12940 0000000000000000 ffff88000dd03f68 ffffffff81109e9e 0000000000000000 0000000000012940 ffff88000dd03f98 Call Trace: [] ttwu_do_activate.constprop.56+0x6d/0x79 [] sched_ttwu_pending+0x67/0x84 [] scheduler_ipi+0x15a/0x2b0 [] smp_reschedule_interrupt+0x38/0x41 [] reschedule_interrupt+0x6d/0x80 [] ? __atomic_notifier_call_chain+0x5/0xc1 [] ? native_safe_halt+0xd/0x16 [] default_idle+0x147/0x282 [] arch_cpu_idle+0x3d/0x5d [] cpu_idle_loop+0x46d/0x5db [] cpu_startup_entry+0x84/0x84 [] start_secondary+0x3c8/0x3d5 [...] Fix this by directly calling poke_int3_handler() from the int3 exception handler (analogically to what ftrace has been doing already), instead of relying on notifier, registration of which might not have yet been finalized by the time of the first trap. Reported-and-tested-by: Fengguang Wu Signed-off-by: Jiri Kosina Acked-by: Masami Hiramatsu Cc: H. Peter Anvin Cc: Fengguang Wu Cc: Steven Rostedt Link: http://lkml.kernel.org/r/alpine.LNX.2.00.1307231007490.14024@pobox.suse.cz Signed-off-by: Ingo Molnar --- arch/x86/include/asm/alternative.h | 2 ++ arch/x86/kernel/alternative.c | 31 ++++++++---------------------- arch/x86/kernel/traps.c | 4 ++++ kernel/kprobes.c | 2 +- 4 files changed, 15 insertions(+), 24 deletions(-) diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h index 4daf8c501239..0a3f9c9f98d5 100644 --- a/arch/x86/include/asm/alternative.h +++ b/arch/x86/include/asm/alternative.h @@ -5,6 +5,7 @@ #include #include #include +#include /* * Alternative inline assembly for SMP. @@ -224,6 +225,7 @@ extern void *text_poke_early(void *addr, const void *opcode, size_t len); * inconsistent instruction while you patch. */ extern void *text_poke(void *addr, const void *opcode, size_t len); +extern int poke_int3_handler(struct pt_regs *regs); extern void *text_poke_bp(void *addr, const void *opcode, size_t len, void *handler); #endif /* _ASM_X86_ALTERNATIVE_H */ diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 5d8782ee3dd7..15e8563e5c24 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -605,26 +605,24 @@ static void do_sync_core(void *info) static bool bp_patching_in_progress; static void *bp_int3_handler, *bp_int3_addr; -static int int3_notify(struct notifier_block *self, unsigned long val, void *data) +int poke_int3_handler(struct pt_regs *regs) { - struct die_args *args = data; - /* bp_patching_in_progress */ smp_rmb(); if (likely(!bp_patching_in_progress)) - return NOTIFY_DONE; + return 0; - /* we are not interested in non-int3 faults and ring > 0 faults */ - if (val != DIE_INT3 || !args->regs || user_mode_vm(args->regs) - || args->regs->ip != (unsigned long)bp_int3_addr) - return NOTIFY_DONE; + if (user_mode_vm(regs) || regs->ip != (unsigned long)bp_int3_addr) + return 0; /* set up the specified breakpoint handler */ - args->regs->ip = (unsigned long) bp_int3_handler; + regs->ip = (unsigned long) bp_int3_handler; + + return 1; - return NOTIFY_STOP; } + /** * text_poke_bp() -- update instructions on live kernel on SMP * @addr: address to patch @@ -689,16 +687,3 @@ void *text_poke_bp(void *addr, const void *opcode, size_t len, void *handler) return addr; } -/* this one needs to run before anything else handles it as a - * regular exception */ -static struct notifier_block int3_nb = { - .priority = 0x7fffffff, - .notifier_call = int3_notify -}; - -static int __init int3_init(void) -{ - return register_die_notifier(&int3_nb); -} - -arch_initcall(int3_init); diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 1b23a1c92746..8c8093b146ca 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -58,6 +58,7 @@ #include #include #include +#include #ifdef CONFIG_X86_64 #include @@ -327,6 +328,9 @@ dotraplinkage void __kprobes notrace do_int3(struct pt_regs *regs, long error_co ftrace_int3_handler(regs)) return; #endif + if (poke_int3_handler(regs)) + return; + prev_state = exception_enter(); #ifdef CONFIG_KGDB_LOW_LEVEL_TRAP if (kgdb_ll_trap(DIE_INT3, "int3", regs, error_code, X86_TRAP_BP, diff --git a/kernel/kprobes.c b/kernel/kprobes.c index b58b490fa439..6e33498d665c 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -1709,7 +1709,7 @@ EXPORT_SYMBOL_GPL(unregister_kprobes); static struct notifier_block kprobe_exceptions_nb = { .notifier_call = kprobe_exceptions_notify, - .priority = 0x7ffffff0 /* High priority, but not first. */ + .priority = 0x7fffffff /* we need to be notified first */ }; unsigned long __weak arch_deref_entry_point(void *entry) -- 2.20.1