Patches contributed by Eötvös Lorand University
commit ea6bff368548d79529421a9dc0710fc5330eb504
Author: Ingo Molnar <mingo@elte.hu>
Date: Fri Aug 28 10:44:56 2009 +0200
modules: Fix build error in the !CONFIG_KALLSYMS case
> James Bottomley (1):
> module: workaround duplicate section names
-tip testing found that this patch breaks the build on x86 if
CONFIG_KALLSYMS is disabled:
kernel/module.c: In function ‘load_module’:
kernel/module.c:2367: error: ‘struct module’ has no member named ‘sect_attrs’
distcc[8269] ERROR: compile kernel/module.c on ph/32 failed
make[1]: *** [kernel/module.o] Error 1
make: *** [kernel] Error 2
make: *** Waiting for unfinished jobs....
Commit 1b364bf misses the fact that section attributes are only
built and dealt with if kallsyms is enabled. The patch below fixes
this.
( note, technically speaking this should depend on CONFIG_SYSFS as
well but this patch is correct too and keeps the #ifdef less
intrusive - in the KALLSYMS && !SYSFS case the code is a NOP. )
Signed-off-by: Ingo Molnar <mingo@elte.hu>
[ Replaced patch with a slightly cleaner variation by James Bottomley ]
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
diff --git a/kernel/module.c b/kernel/module.c
index eccb561dd8a3..2d537186191f 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -1274,6 +1274,10 @@ static void add_notes_attrs(struct module *mod, unsigned int nsect,
struct module_notes_attrs *notes_attrs;
struct bin_attribute *nattr;
+ /* failed to create section attributes, so can't create notes */
+ if (!mod->sect_attrs)
+ return;
+
/* Count notes sections and allocate structures. */
notes = 0;
for (i = 0; i < nsect; i++)
@@ -2355,8 +2359,7 @@ static noinline struct module *load_module(void __user *umod,
if (err < 0)
goto unlink;
add_sect_attrs(mod, hdr->e_shnum, secstrings, sechdrs);
- if (mod->sect_attrs)
- add_notes_attrs(mod, hdr->e_shnum, secstrings, sechdrs);
+ add_notes_attrs(mod, hdr->e_shnum, secstrings, sechdrs);
/* Get rid of temporary copy */
vfree(hdr);
commit 66c6e29f24a50173fc1e761c3e2483c8d64e3b1a
Merge: 6c347d43eea2 117226d15850
Author: Ingo Molnar <mingo@elte.hu>
Date: Fri Aug 28 13:53:07 2009 +0200
Merge branch 'tracing/core' of git://git.kernel.org/pub/scm/linux/kernel/git/frederic/random-tracing into tracing/core
commit 6bb56347f5162d1a7cb1dc461023360781ecd4c0
Author: Ingo Molnar <mingo@elte.hu>
Date: Fri Aug 28 13:44:53 2009 +0200
perf_counters: Increase paranoia level
Per-cpu counters are an ASLR information leak as they show
the execution other tasks do. Increase the paranoia level
to 1, which disallows per-cpu counters. (they still allow
counting/profiling of own tasks - and admin can profile
everything.)
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
diff --git a/kernel/perf_counter.c b/kernel/perf_counter.c
index f274e1959885..7d4bb83b78cf 100644
--- a/kernel/perf_counter.c
+++ b/kernel/perf_counter.c
@@ -50,7 +50,7 @@ static atomic_t nr_task_counters __read_mostly;
* 1 - disallow cpu counters to unpriv
* 2 - disallow kernel profiling to unpriv
*/
-int sysctl_perf_counter_paranoid __read_mostly;
+int sysctl_perf_counter_paranoid __read_mostly = 1;
static inline bool perf_paranoid_cpu(void)
{
commit 35dce1a99d010f3d738af4ce1b9b77302fdfe69c
Merge: 7cb2e3ee2aee 1c569f0264ea
Author: Ingo Molnar <mingo@elte.hu>
Date: Wed Aug 26 08:29:02 2009 +0200
Merge branch 'tracing/core' of git://git.kernel.org/pub/scm/linux/kernel/git/frederic/random-tracing into tracing/core
Conflicts:
include/linux/tracepoint.h
Signed-off-by: Ingo Molnar <mingo@elte.hu>
diff --cc include/linux/tracepoint.h
index 0341f2e2698a,846a4ae501eb..63a3f7a80580
--- a/include/linux/tracepoint.h
+++ b/include/linux/tracepoint.h
@@@ -295,5 -273,9 +282,8 @@@ static inline void tracepoint_synchroni
#define TRACE_EVENT(name, proto, args, struct, assign, print) \
DECLARE_TRACE(name, PARAMS(proto), PARAMS(args))
+ #define TRACE_EVENT_FN(name, proto, args, struct, \
+ assign, print, reg, unreg) \
+ DECLARE_TRACE(name, PARAMS(proto), PARAMS(args))
-#endif
-#endif
+#endif /* ifdef TRACE_EVENT (see note above) */
commit daedc71836e5a398fd0cc0e12c5cb43539478485
Merge: c36ba80ea01d 422bef879e84
Author: Ingo Molnar <mingo@elte.hu>
Date: Tue Aug 25 10:04:27 2009 +0200
Merge commit 'v2.6.31-rc7' into irq/core
Merge reason: move from an -rc2 base to -rc7.
Signed-off-by: Ingo Molnar <mingo@elte.hu>
commit 5f9ece02401116b29eb04396b99ea092acb75dd8
Merge: 9f51e24ee8b5 422bef879e84
Author: Ingo Molnar <mingo@elte.hu>
Date: Mon Aug 24 12:25:44 2009 +0200
Merge commit 'v2.6.31-rc7' into x86/cleanups
Merge reason: we were on -rc1 before - go up to -rc7
Signed-off-by: Ingo Molnar <mingo@elte.hu>
diff --cc arch/x86/kernel/cpu/amd.c
index c6eb02e69875,63fddcd082cd..83b217c7225f
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@@ -400,8 -398,15 +400,15 @@@ static void __cpuinit init_amd(struct c
u32 level;
level = cpuid_eax(1);
- if((level >= 0x0f48 && level < 0x0f50) || level >= 0x0f58)
+ if ((level >= 0x0f48 && level < 0x0f50) || level >= 0x0f58)
set_cpu_cap(c, X86_FEATURE_REP_GOOD);
+
+ /*
+ * Some BIOSes incorrectly force this feature, but only K8
+ * revision D (model = 0x14) and later actually support it.
+ */
+ if (c->x86_model < 0x14)
+ clear_cpu_cap(c, X86_FEATURE_LAHF_LM);
}
if (c->x86 == 0x10 || c->x86 == 0x11)
set_cpu_cap(c, X86_FEATURE_REP_GOOD);
commit 96d6e48bc6b38342a59ccd23e25907d12caaeaf8
Merge: 6e086437f35a 4464fcaa9cbf
Author: Ingo Molnar <mingo@elte.hu>
Date: Wed Aug 19 14:50:35 2009 +0200
Merge branch 'perfcounters/urgent' into perfcounters/core
Conflicts:
tools/perf/builtin-annotate.c
tools/perf/builtin-report.c
Merge reason: resolve these conflicts.
Signed-off-by: Ingo Molnar <mingo@elte.hu>
diff --cc tools/perf/builtin-annotate.c
index 96d421f7161d,5e17de984dc8..4ac618b34254
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@@ -629,8 -981,15 +630,15 @@@ process_fork_event(event_t *event, unsi
(void *)(long)(event->header.size),
event->fork.pid, event->fork.ppid);
+ /*
+ * A thread clone will have the same PID for both
+ * parent and child.
+ */
+ if (thread == parent)
+ return 0;
+
if (!thread || !parent || thread__fork(thread, parent)) {
- dprintf("problem processing PERF_EVENT_FORK, skipping event.\n");
+ dump_printf("problem processing PERF_EVENT_FORK, skipping event.\n");
return -1;
}
total_fork++;
@@@ -976,7 -1335,12 +984,12 @@@ static int __cmd_annotate(void
exit(-1);
}
- if (!force && (stat.st_uid != geteuid())) {
++ if (!force && (input_stat.st_uid != geteuid())) {
+ fprintf(stderr, "file: %s not owned by current user\n", input_name);
+ exit(-1);
+ }
+
- if (!stat.st_size) {
+ if (!input_stat.st_size) {
fprintf(stderr, "zero-sized file, nothing to do!\n");
exit(0);
}
diff --cc tools/perf/builtin-report.c
index 3fc0d471b90b,8b2ec882e6e0..d2e28820ee60
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@@ -1404,7 -1857,12 +1405,12 @@@ static int __cmd_report(void
exit(-1);
}
- if (!force && (stat.st_uid != geteuid())) {
++ if (!force && (input_stat.st_uid != geteuid())) {
+ fprintf(stderr, "file: %s not owned by current user\n", input_name);
+ exit(-1);
+ }
+
- if (!stat.st_size) {
+ if (!input_stat.st_size) {
fprintf(stderr, "zero-sized file, nothing to do!\n");
exit(0);
}
@@@ -1614,7 -2069,8 +1620,8 @@@ static const struct option options[] =
"be more verbose (show symbol address, etc)"),
OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace,
"dump raw trace in ASCII"),
- OPT_STRING('k', "vmlinux", &vmlinux, "file", "vmlinux pathname"),
+ OPT_STRING('k', "vmlinux", &vmlinux_name, "file", "vmlinux pathname"),
+ OPT_BOOLEAN('f', "force", &force, "don't complain, do it"),
OPT_BOOLEAN('m', "modules", &modules,
"load module symbols - WARNING: use only with -k and LIVE kernel"),
OPT_BOOLEAN('n', "show-nr-samples", &show_nr_samples,
commit 8a517c514d5893602cf85c1b4c47afbbc04d2198
Merge: c64b04fe6e0c 422bef879e84
Author: Ingo Molnar <mingo@elte.hu>
Date: Sun Aug 23 11:18:47 2009 +0200
Merge commit 'v2.6.31-rc7' into x86/cpu
commit 4a683bf94b8a10e2bb0da07aec3ac0a55e5de61f
Author: Ingo Molnar <mingo@elte.hu>
Date: Fri Aug 21 12:53:36 2009 +0200
tracing: Fix too large stack usage in do_one_initcall()
One of my testboxes triggered this nasty stack overflow crash
during SCSI probing:
[ 5.874004] sd 0:0:0:0: [sda] Write cache: enabled, read cache: enabled, doesn't support DPO or FUA
[ 5.875004] device: 'sda': device_add
[ 5.878004] BUG: unable to handle kernel NULL pointer dereference at 00000a0c
[ 5.878004] IP: [<b1008321>] print_context_stack+0x81/0x110
[ 5.878004] *pde = 00000000
[ 5.878004] Thread overran stack, or stack corrupted
[ 5.878004] Oops: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC
[ 5.878004] last sysfs file:
[ 5.878004]
[ 5.878004] Pid: 1, comm: swapper Not tainted (2.6.31-rc6-tip-01272-g9919e28-dirty #5685)
[ 5.878004] EIP: 0060:[<b1008321>] EFLAGS: 00010083 CPU: 0
[ 5.878004] EIP is at print_context_stack+0x81/0x110
[ 5.878004] EAX: cf8a3000 EBX: cf8a3fe4 ECX: 00000049 EDX: 00000000
[ 5.878004] ESI: b1cfce84 EDI: 00000000 EBP: cf8a3018 ESP: cf8a2ff4
[ 5.878004] DS: 007b ES: 007b FS: 00d8 GS: 0000 SS: 0068
[ 5.878004] Process swapper (pid: 1, ti=cf8a2000 task=cf8a8000 task.ti=cf8a3000)
[ 5.878004] Stack:
[ 5.878004] b1004867 fffff000 cf8a3ffc
[ 5.878004] Call Trace:
[ 5.878004] [<b1004867>] ? kernel_thread_helper+0x7/0x10
[ 5.878004] BUG: unable to handle kernel NULL pointer dereference at 00000a0c
[ 5.878004] IP: [<b1008321>] print_context_stack+0x81/0x110
[ 5.878004] *pde = 00000000
[ 5.878004] Thread overran stack, or stack corrupted
[ 5.878004] Oops: 0000 [#2] PREEMPT SMP DEBUG_PAGEALLOC
The oops did not reveal any more details about the real stack
that we have and the system got into an infinite loop of
recursive pagefaults.
So i booted with CONFIG_STACK_TRACER=y and the 'stacktrace' boot
parameter. The box did not crash (timings/conditions probably
changed a tiny bit to trigger the catastrophic crash), but the
/debug/tracing/stack_trace file was rather revealing:
Depth Size Location (72 entries)
----- ---- --------
0) 3704 52 __change_page_attr+0xb8/0x290
1) 3652 24 __change_page_attr_set_clr+0x43/0x90
2) 3628 60 kernel_map_pages+0x108/0x120
3) 3568 40 prep_new_page+0x7d/0x130
4) 3528 84 get_page_from_freelist+0x106/0x420
5) 3444 116 __alloc_pages_nodemask+0xd7/0x550
6) 3328 36 allocate_slab+0xb1/0x100
7) 3292 36 new_slab+0x1c/0x160
8) 3256 36 __slab_alloc+0x133/0x2b0
9) 3220 4 kmem_cache_alloc+0x1bb/0x1d0
10) 3216 108 create_object+0x28/0x250
11) 3108 40 kmemleak_alloc+0x81/0xc0
12) 3068 24 kmem_cache_alloc+0x162/0x1d0
13) 3044 52 scsi_pool_alloc_command+0x29/0x70
14) 2992 20 scsi_host_alloc_command+0x22/0x70
15) 2972 24 __scsi_get_command+0x1b/0x90
16) 2948 28 scsi_get_command+0x35/0x90
17) 2920 24 scsi_setup_blk_pc_cmnd+0xd4/0x100
18) 2896 128 sd_prep_fn+0x332/0xa70
19) 2768 36 blk_peek_request+0xe7/0x1d0
20) 2732 56 scsi_request_fn+0x54/0x520
21) 2676 12 __generic_unplug_device+0x2b/0x40
22) 2664 24 blk_execute_rq_nowait+0x59/0x80
23) 2640 172 blk_execute_rq+0x6b/0xb0
24) 2468 32 scsi_execute+0xe0/0x140
25) 2436 64 scsi_execute_req+0x152/0x160
26) 2372 60 scsi_vpd_inquiry+0x6c/0x90
27) 2312 44 scsi_get_vpd_page+0x112/0x160
28) 2268 52 sd_revalidate_disk+0x1df/0x320
29) 2216 92 rescan_partitions+0x98/0x330
30) 2124 52 __blkdev_get+0x309/0x350
31) 2072 8 blkdev_get+0xf/0x20
32) 2064 44 register_disk+0xff/0x120
33) 2020 36 add_disk+0x6e/0xb0
34) 1984 44 sd_probe_async+0xfb/0x1d0
35) 1940 44 __async_schedule+0xf4/0x1b0
36) 1896 8 async_schedule+0x12/0x20
37) 1888 60 sd_probe+0x305/0x360
38) 1828 44 really_probe+0x63/0x170
39) 1784 36 driver_probe_device+0x5d/0x60
40) 1748 16 __device_attach+0x49/0x50
41) 1732 32 bus_for_each_drv+0x5b/0x80
42) 1700 24 device_attach+0x6b/0x70
43) 1676 16 bus_attach_device+0x47/0x60
44) 1660 76 device_add+0x33d/0x400
45) 1584 52 scsi_sysfs_add_sdev+0x6a/0x2c0
46) 1532 108 scsi_add_lun+0x44b/0x460
47) 1424 116 scsi_probe_and_add_lun+0x182/0x4e0
48) 1308 36 __scsi_add_device+0xd9/0xe0
49) 1272 44 ata_scsi_scan_host+0x10b/0x190
50) 1228 24 async_port_probe+0x96/0xd0
51) 1204 44 __async_schedule+0xf4/0x1b0
52) 1160 8 async_schedule+0x12/0x20
53) 1152 48 ata_host_register+0x171/0x1d0
54) 1104 60 ata_pci_sff_activate_host+0xf3/0x230
55) 1044 44 ata_pci_sff_init_one+0xea/0x100
56) 1000 48 amd_init_one+0xb2/0x190
57) 952 8 local_pci_probe+0x13/0x20
58) 944 32 pci_device_probe+0x68/0x90
59) 912 44 really_probe+0x63/0x170
60) 868 36 driver_probe_device+0x5d/0x60
61) 832 20 __driver_attach+0x89/0xa0
62) 812 32 bus_for_each_dev+0x5b/0x80
63) 780 12 driver_attach+0x1e/0x20
64) 768 72 bus_add_driver+0x14b/0x2d0
65) 696 36 driver_register+0x6e/0x150
66) 660 20 __pci_register_driver+0x53/0xc0
67) 640 8 amd_init+0x14/0x16
68) 632 572 do_one_initcall+0x2b/0x1d0
69) 60 12 do_basic_setup+0x56/0x6a
70) 48 20 kernel_init+0x84/0xce
71) 28 28 kernel_thread_helper+0x7/0x10
There's a lot of fat functions on that stack trace, but
the largest of all is do_one_initcall(). This is due to
the boot trace entry variables being on the stack.
Fixing this is relatively easy, initcalls are fundamentally
serialized, so we can move the local variables to file scope.
Note that this large stack footprint was present for a
couple of months already - what pushed my system over
the edge was the addition of kmemleak to the call-chain:
6) 3328 36 allocate_slab+0xb1/0x100
7) 3292 36 new_slab+0x1c/0x160
8) 3256 36 __slab_alloc+0x133/0x2b0
9) 3220 4 kmem_cache_alloc+0x1bb/0x1d0
10) 3216 108 create_object+0x28/0x250
11) 3108 40 kmemleak_alloc+0x81/0xc0
12) 3068 24 kmem_cache_alloc+0x162/0x1d0
13) 3044 52 scsi_pool_alloc_command+0x29/0x70
This pushes the total to ~3800 bytes, only a tiny bit
more was needed to corrupt the on-kernel-stack thread_info.
The fix reduces the stack footprint from 572 bytes
to 28 bytes.
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Steven Rostedt <srostedt@redhat.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Jens Axboe <jens.axboe@oracle.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: <stable@kernel.org>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
diff --git a/init/main.c b/init/main.c
index 2c5ade79eb81..98e679e3494a 100644
--- a/init/main.c
+++ b/init/main.c
@@ -733,13 +733,14 @@ static void __init do_ctors(void)
int initcall_debug;
core_param(initcall_debug, initcall_debug, bool, 0644);
+static char msgbuf[64];
+static struct boot_trace_call call;
+static struct boot_trace_ret ret;
+
int do_one_initcall(initcall_t fn)
{
int count = preempt_count();
ktime_t calltime, delta, rettime;
- char msgbuf[64];
- struct boot_trace_call call;
- struct boot_trace_ret ret;
if (initcall_debug) {
call.caller = task_pid_nr(current);
commit cbcb340cb6a6f9f32724c90493f509dd41105e20
Merge: 78b89ecd7317 ce2eef33d35c
Author: Ingo Molnar <mingo@elte.hu>
Date: Thu Aug 20 12:05:24 2009 +0200
Merge branch 'bugfix' of git://git.kernel.org/pub/scm/linux/kernel/git/jeremy/xen into x86/urgent