[PATCH 64/91] oprofile, x86: Fix nmi-unsafe callgraph support

From: Willy Tarreau
Date: Sun Feb 05 2012 - 17:33:36 EST


2.6.27-longterm review patch. If anyone has any objections, please let us know.

------------------

commit a0e3e70243f5b270bc3eca718f0a9fa5e6b8262e upstream.

Backport for stable kernel v2.6.32.y to v2.6.36.y.

Current oprofile's x86 callgraph support may trigger page faults
throwing the BUG_ON(in_nmi()) message below. This patch fixes this by
using the same nmi-safe copy-from-user code as in perf.

------------[ cut here ]------------
kernel BUG at .../arch/x86/kernel/traps.c:436!
invalid opcode: 0000 [#1] SMP
last sysfs file: /sys/devices/pci0000:00/0000:00:0a.0/0000:07:00.0/0000:08:04.0/net/eth0/broadcast
CPU 5
Modules linked in:

Pid: 8611, comm: opcontrol Not tainted 2.6.39-00007-gfe47ae7 #1 Advanced Micro Device Anaheim/Anaheim
RIP: 0010:[<ffffffff813e8e35>] [<ffffffff813e8e35>] do_nmi+0x22/0x1ee
RSP: 0000:ffff88042fd47f28 EFLAGS: 00010002
RAX: ffff88042c0a7fd8 RBX: 0000000000000001 RCX: 00000000c0000101
RDX: 00000000ffff8804 RSI: ffffffffffffffff RDI: ffff88042fd47f58
RBP: ffff88042fd47f48 R08: 0000000000000004 R09: 0000000000001484
R10: 0000000000000001 R11: 0000000000000000 R12: ffff88042fd47f58
R13: 0000000000000000 R14: ffff88042fd47d98 R15: 0000000000000020
FS: 00007fca25e56700(0000) GS:ffff88042fd40000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000000000000074 CR3: 000000042d28b000 CR4: 00000000000006e0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400
Process opcontrol (pid: 8611, threadinfo ffff88042c0a6000, task ffff88042c532310)
Stack:
0000000000000000 0000000000000001 ffff88042c0a7fd8 0000000000000000
ffff88042fd47de8 ffffffff813e897a 0000000000000020 ffff88042fd47d98
0000000000000000 ffff88042c0a7fd8 ffff88042fd47de8 0000000000000074
Call Trace:
<NMI>
[<ffffffff813e897a>] nmi+0x1a/0x20
[<ffffffff813f08ab>] ? bad_to_user+0x25/0x771
<<EOE>>
Code: ff 59 5b 41 5c 41 5d c9 c3 55 65 48 8b 04 25 88 b5 00 00 48 89 e5 41 55 41 54 49 89 fc 53 48 83 ec 08 f6 80 47 e0 ff ff 04 74 04 <0f> 0b eb fe 81 80 44 e0 ff ff 00 00 01 04 65 ff 04 25 c4 0f 01
RIP [<ffffffff813e8e35>] do_nmi+0x22/0x1ee
RSP <ffff88042fd47f28>
---[ end trace ed6752185092104b ]---
Kernel panic - not syncing: Fatal exception in interrupt
Pid: 8611, comm: opcontrol Tainted: G D 2.6.39-00007-gfe47ae7 #1
Call Trace:
<NMI> [<ffffffff813e5e0a>] panic+0x8c/0x188
[<ffffffff813e915c>] oops_end+0x81/0x8e
[<ffffffff8100403d>] die+0x55/0x5e
[<ffffffff813e8c45>] do_trap+0x11c/0x12b
[<ffffffff810023c8>] do_invalid_op+0x91/0x9a
[<ffffffff813e8e35>] ? do_nmi+0x22/0x1ee
[<ffffffff8131e6fa>] ? oprofile_add_sample+0x83/0x95
[<ffffffff81321670>] ? op_amd_check_ctrs+0x4f/0x2cf
[<ffffffff813ee4d5>] invalid_op+0x15/0x20
[<ffffffff813e8e35>] ? do_nmi+0x22/0x1ee
[<ffffffff813e8e7a>] ? do_nmi+0x67/0x1ee
[<ffffffff813e897a>] nmi+0x1a/0x20
[<ffffffff813f08ab>] ? bad_to_user+0x25/0x771
<<EOE>>

Cc: John Lumby <johnlumby@xxxxxxxxxxx>
Cc: Maynard Johnson <maynardj@xxxxxxxxxx>
Signed-off-by: Robert Richter <robert.richter@xxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxx>
---
arch/x86/oprofile/backtrace.c | 46 +++++++++++++++++++++++++++++++++++++---
1 files changed, 42 insertions(+), 4 deletions(-)

Index: longterm-2.6.27/arch/x86/oprofile/backtrace.c
===================================================================
--- longterm-2.6.27.orig/arch/x86/oprofile/backtrace.c 2012-02-05 22:34:33.047915246 +0100
+++ longterm-2.6.27/arch/x86/oprofile/backtrace.c 2012-02-05 22:34:43.985914946 +0100
@@ -11,6 +11,8 @@
#include <linux/oprofile.h>
#include <linux/sched.h>
#include <linux/mm.h>
+#include <linux/highmem.h>
+
#include <asm/ptrace.h>
#include <asm/uaccess.h>
#include <asm/stacktrace.h>
@@ -47,6 +49,42 @@
.address = backtrace_address,
};

+/* from arch/x86/kernel/cpu/perf_event.c: */
+
+/*
+ * best effort, GUP based copy_from_user() that assumes IRQ or NMI context
+ */
+static unsigned long
+copy_from_user_nmi(void *to, const void __user *from, unsigned long n)
+{
+ unsigned long offset, addr = (unsigned long)from;
+ unsigned long size, len = 0;
+ struct page *page;
+ void *map;
+ int ret;
+
+ do {
+ ret = __get_user_pages_fast(addr, 1, 0, &page);
+ if (!ret)
+ break;
+
+ offset = addr & (PAGE_SIZE - 1);
+ size = min(PAGE_SIZE - offset, n - len);
+
+ map = kmap_atomic(page, KM_USER0);
+ memcpy(to, map+offset, size);
+ kunmap_atomic(map, KM_USER0);
+ put_page(page);
+
+ len += size;
+ to += size;
+ addr += size;
+
+ } while (len < n);
+
+ return len;
+}
+
struct frame_head {
struct frame_head *bp;
unsigned long ret;
@@ -55,12 +93,12 @@
static struct frame_head *
dump_user_backtrace(struct frame_head * head)
{
+ /* Also check accessibility of one struct frame_head beyond: */
struct frame_head bufhead[2];
+ unsigned long bytes;

- /* Also check accessibility of one struct frame_head beyond */
- if (!access_ok(VERIFY_READ, head, sizeof(bufhead)))
- return NULL;
- if (__copy_from_user_inatomic(bufhead, head, sizeof(bufhead)))
+ bytes = copy_from_user_nmi(bufhead, head, sizeof(bufhead));
+ if (bytes != sizeof(bufhead))
return NULL;

oprofile_add_trace(bufhead[0].ret);


--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/