ftrace/x86: Do not change stacks in DEBUG when calling lockdep

When both DYNAMIC_FTRACE and LOCKDEP are set, the TRACE_IRQS_ON/OFF
will call into the lockdep code. The lockdep code can call lots of
functions that may be traced by ftrace. When ftrace is updating its
code and hits a breakpoint, the breakpoint handler will call into
lockdep. If lockdep happens to call a function that also has a breakpoint
attached, it will jump back into the breakpoint handler resetting
the stack to the debug stack and corrupt the contents currently on
that stack.

The 'do_sym' call that calls do_int3() is protected by modifying the
IST table to point to a different location if another breakpoint is
hit. But the TRACE_IRQS_OFF/ON are outside that protection, and if
a breakpoint is hit from those, the stack will get corrupted, and
the kernel will crash:

[ 1013.243754] BUG: unable to handle kernel NULL pointer dereference at 0000000000000002
[ 1013.272665] IP: [<ffff880145cc0000>] 0xffff880145cbffff
[ 1013.285186] PGD 1401b2067 PUD 14324c067 PMD 0
[ 1013.298832] Oops: 0010 [#1] PREEMPT SMP
[ 1013.310600] CPU 2
[ 1013.317904] Modules linked in: ip6t_REJECT nf_conntrack_ipv6 nf_defrag_ipv6 xt_state nf_conntrack ip6table_filter ip6_tables crc32c_intel ghash_clmulni_intel microcode usb_debug serio_raw pcspkr iTCO_wdt i2c_i801 iTCO_vendor_support e1000e nfsd nfs_acl auth_rpcgss lockd sunrpc i915 video i2c_algo_bit drm_kms_helper drm i2c_core [last unloaded: scsi_wait_scan]
[ 1013.401848]
[ 1013.407399] Pid: 112, comm: kworker/2:1 Not tainted 3.4.0+ #30
[ 1013.437943] RIP: 8eb8:[<ffff88014630a000>]  [<ffff88014630a000>] 0xffff880146309fff
[ 1013.459871] RSP: ffffffff8165e919:ffff88014780f408  EFLAGS: 00010046
[ 1013.477909] RAX: 0000000000000001 RBX: ffffffff81104020 RCX: 0000000000000000
[ 1013.499458] RDX: ffff880148008ea8 RSI: ffffffff8131ef40 RDI: ffffffff82203b20
[ 1013.521612] RBP: ffffffff81005751 R08: 0000000000000000 R09: 0000000000000000
[ 1013.543121] R10: ffffffff82cdc318 R11: 0000000000000000 R12: ffff880145cc0000
[ 1013.564614] R13: ffff880148008eb8 R14: 0000000000000002 R15: ffff88014780cb40
[ 1013.586108] FS:  0000000000000000(0000) GS:ffff880148000000(0000) knlGS:0000000000000000
[ 1013.609458] CS:  0010 DS: 0000 ES: 0000 CR0: 000000008005003b
[ 1013.627420] CR2: 0000000000000002 CR3: 0000000141f10000 CR4: 00000000001407e0
[ 1013.649051] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[ 1013.670724] DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400
[ 1013.692376] Process kworker/2:1 (pid: 112, threadinfo ffff88013fe0e000, task ffff88014020a6a0)
[ 1013.717028] Stack:
[ 1013.724131]  ffff88014780f570 ffff880145cc0000 0000400000004000 0000000000000000
[ 1013.745918]  cccccccccccccccc ffff88014780cca8 ffffffff811072bb ffffffff81651627
[ 1013.767870]  ffffffff8118f8a7 ffffffff811072bb ffffffff81f2b6c5 ffffffff81f11bdb
[ 1013.790021] Call Trace:
[ 1013.800701] Code: 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a 5a <e7> d7 64 81 ff ff ff ff 01 00 00 00 00 00 00 00 65 d9 64 81 ff
[ 1013.861443] RIP  [<ffff88014630a000>] 0xffff880146309fff
[ 1013.884466]  RSP <ffff88014780f408>
[ 1013.901507] CR2: 0000000000000002

The solution was to reuse the NMI functions that change the IDT table to make the debug
stack keep its current stack (in kernel mode) when hitting a breakpoint:

  call debug_stack_set_zero
  TRACE_IRQS_ON
  call debug_stack_reset

If the TRACE_IRQS_ON happens to hit a breakpoint then it will keep the current stack
and not crash the box.

Reported-by: Dave Jones <davej@redhat.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>

diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index 320852d..7d65133 100644 (file)
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -191,6 +191,44 @@ ENDPROC(native_usergs_sysret64)
 .endm
 
 /*
+ * When dynamic function tracer is enabled it will add a breakpoint
+ * to all locations that it is about to modify, sync CPUs, update
+ * all the code, sync CPUs, then remove the breakpoints. In this time
+ * if lockdep is enabled, it might jump back into the debug handler
+ * outside the updating of the IST protection. (TRACE_IRQS_ON/OFF).
+ *
+ * We need to change the IDT table before calling TRACE_IRQS_ON/OFF to
+ * make sure the stack pointer does not get reset back to the top
+ * of the debug stack, and instead just reuses the current stack.
+ */
+#if defined(CONFIG_DYNAMIC_FTRACE) && defined(CONFIG_TRACE_IRQFLAGS)
+
+.macro TRACE_IRQS_OFF_DEBUG
+       call debug_stack_set_zero
+       TRACE_IRQS_OFF
+       call debug_stack_reset
+.endm
+
+.macro TRACE_IRQS_ON_DEBUG
+       call debug_stack_set_zero
+       TRACE_IRQS_ON
+       call debug_stack_reset
+.endm
+
+.macro TRACE_IRQS_IRETQ_DEBUG offset=ARGOFFSET
+       bt   $9,EFLAGS-\offset(%rsp)    /* interrupts off? */
+       jnc  1f
+       TRACE_IRQS_ON_DEBUG
+1:
+.endm
+
+#else
+# define TRACE_IRQS_OFF_DEBUG          TRACE_IRQS_OFF
+# define TRACE_IRQS_ON_DEBUG           TRACE_IRQS_ON
+# define TRACE_IRQS_IRETQ_DEBUG                TRACE_IRQS_IRETQ
+#endif
+
+/*
  * C code is not supposed to know about undefined top of stack. Every time
  * a C function with an pt_regs argument is called from the SYSCALL based
  * fast path FIXUP_TOP_OF_STACK is needed.
@@ -1098,7 +1136,7 @@ ENTRY(\sym)
        subq $ORIG_RAX-R15, %rsp
        CFI_ADJUST_CFA_OFFSET ORIG_RAX-R15
        call save_paranoid
-       TRACE_IRQS_OFF
+       TRACE_IRQS_OFF_DEBUG
        movq %rsp,%rdi          /* pt_regs pointer */
        xorl %esi,%esi          /* no error code */
        subq $EXCEPTION_STKSZ, INIT_TSS_IST(\ist)
@@ -1393,7 +1431,7 @@ paranoidzeroentry machine_check *machine_check_vector(%rip)
 ENTRY(paranoid_exit)
        DEFAULT_FRAME
        DISABLE_INTERRUPTS(CLBR_NONE)
-       TRACE_IRQS_OFF
+       TRACE_IRQS_OFF_DEBUG
        testl %ebx,%ebx                         /* swapgs needed? */
        jnz paranoid_restore
        testl $3,CS(%rsp)
@@ -1404,7 +1442,7 @@ paranoid_swapgs:
        RESTORE_ALL 8
        jmp irq_return
 paranoid_restore:
-       TRACE_IRQS_IRETQ 0
+       TRACE_IRQS_IRETQ_DEBUG 0
        RESTORE_ALL 8
        jmp irq_return
 paranoid_userspace: