This reverts commit 673bdb4200c092692f83b5f7ba3df57021d52d29.
The origin mainline patch fix a buffer overflow issue in
amdgpu_debugfs_gprwave_read(), but it has not been introduced in kernel
6.1 and older kernels. This patch add a check in a wrong function in the
same file.
Signed-off-by: Zhang Zekun <zhangzekun11(a)huawei.com>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
index 4776196b2021..98bd8a23e5b0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
@@ -394,7 +394,7 @@ static ssize_t amdgpu_debugfs_regs_smc_read(struct file *f, char __user *buf,
if (!adev->smc_rreg)
return -EOPNOTSUPP;
- if (size > 4096 || size & 0x3 || *pos & 0x3)
+ if (size & 0x3 || *pos & 0x3)
return -EINVAL;
while (size) {
--
2.17.1
The patch below does not apply to the 4.19-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-4.19.y
git checkout FETCH_HEAD
git cherry-pick -x 5b590160d2cf776b304eb054afafea2bd55e3620
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024120221-raft-bully-e091@gregkh' --subject-prefix 'PATCH 4.19.y' HEAD^..
Possible dependencies:
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 5b590160d2cf776b304eb054afafea2bd55e3620 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter(a)intel.com>
Date: Tue, 22 Oct 2024 18:59:07 +0300
Subject: [PATCH] perf/x86/intel/pt: Fix buffer full but size is 0 case
If the trace data buffer becomes full, a truncated flag [T] is reported
in PERF_RECORD_AUX. In some cases, the size reported is 0, even though
data must have been added to make the buffer full.
That happens when the buffer fills up from empty to full before the
Intel PT driver has updated the buffer position. Then the driver
calculates the new buffer position before calculating the data size.
If the old and new positions are the same, the data size is reported
as 0, even though it is really the whole buffer size.
Fix by detecting when the buffer position is wrapped, and adjust the
data size calculation accordingly.
Example
Use a very small buffer size (8K) and observe the size of truncated [T]
data. Before the fix, it is possible to see records of 0 size.
Before:
$ perf record -m,8K -e intel_pt// uname
Linux
[ perf record: Woken up 2 times to write data ]
[ perf record: Captured and wrote 0.105 MB perf.data ]
$ perf script -D --no-itrace | grep AUX | grep -F '[T]'
Warning:
AUX data lost 2 times out of 3!
5 19462712368111 0x19710 [0x40]: PERF_RECORD_AUX offset: 0 size: 0 flags: 0x1 [T]
5 19462712700046 0x19ba8 [0x40]: PERF_RECORD_AUX offset: 0x170 size: 0xe90 flags: 0x1 [T]
After:
$ perf record -m,8K -e intel_pt// uname
Linux
[ perf record: Woken up 3 times to write data ]
[ perf record: Captured and wrote 0.040 MB perf.data ]
$ perf script -D --no-itrace | grep AUX | grep -F '[T]'
Warning:
AUX data lost 2 times out of 3!
1 113720802995 0x4948 [0x40]: PERF_RECORD_AUX offset: 0 size: 0x2000 flags: 0x1 [T]
1 113720979812 0x6b10 [0x40]: PERF_RECORD_AUX offset: 0x2000 size: 0x2000 flags: 0x1 [T]
Fixes: 52ca9ced3f70 ("perf/x86/intel/pt: Add Intel PT PMU driver")
Signed-off-by: Adrian Hunter <adrian.hunter(a)intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz(a)infradead.org>
Cc: stable(a)vger.kernel.org
Link: https://lkml.kernel.org/r/20241022155920.17511-2-adrian.hunter@intel.com
diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c
index fd4670a6694e..a087bc0c5498 100644
--- a/arch/x86/events/intel/pt.c
+++ b/arch/x86/events/intel/pt.c
@@ -828,11 +828,13 @@ static void pt_buffer_advance(struct pt_buffer *buf)
buf->cur_idx++;
if (buf->cur_idx == buf->cur->last) {
- if (buf->cur == buf->last)
+ if (buf->cur == buf->last) {
buf->cur = buf->first;
- else
+ buf->wrapped = true;
+ } else {
buf->cur = list_entry(buf->cur->list.next, struct topa,
list);
+ }
buf->cur_idx = 0;
}
}
@@ -846,8 +848,11 @@ static void pt_buffer_advance(struct pt_buffer *buf)
static void pt_update_head(struct pt *pt)
{
struct pt_buffer *buf = perf_get_aux(&pt->handle);
+ bool wrapped = buf->wrapped;
u64 topa_idx, base, old;
+ buf->wrapped = false;
+
if (buf->single) {
local_set(&buf->data_size, buf->output_off);
return;
@@ -865,7 +870,7 @@ static void pt_update_head(struct pt *pt)
} else {
old = (local64_xchg(&buf->head, base) &
((buf->nr_pages << PAGE_SHIFT) - 1));
- if (base < old)
+ if (base < old || (base == old && wrapped))
base += buf->nr_pages << PAGE_SHIFT;
local_add(base - old, &buf->data_size);
diff --git a/arch/x86/events/intel/pt.h b/arch/x86/events/intel/pt.h
index f5e46c04c145..a1b6c04b7f68 100644
--- a/arch/x86/events/intel/pt.h
+++ b/arch/x86/events/intel/pt.h
@@ -65,6 +65,7 @@ struct pt_pmu {
* @head: logical write offset inside the buffer
* @snapshot: if this is for a snapshot/overwrite counter
* @single: use Single Range Output instead of ToPA
+ * @wrapped: buffer advance wrapped back to the first topa table
* @stop_pos: STOP topa entry index
* @intr_pos: INT topa entry index
* @stop_te: STOP topa entry pointer
@@ -82,6 +83,7 @@ struct pt_buffer {
local64_t head;
bool snapshot;
bool single;
+ bool wrapped;
long stop_pos, intr_pos;
struct topa_entry *stop_te, *intr_te;
void **data_pages;
Commit efa7df3e3bb5 ("mm: align larger anonymous mappings on THP
boundaries") updated __get_unmapped_area() to align the start address
for the VMA to a PMD boundary if CONFIG_TRANSPARENT_HUGEPAGE=y.
It does this by effectively looking up a region that is of size,
request_size + PMD_SIZE, and aligning up the start to a PMD boundary.
Commit 4ef9ad19e176 ("mm: huge_memory: don't force huge page alignment
on 32 bit") opted out of this for 32bit due to regressions in mmap base
randomization.
Commit d4148aeab412 ("mm, mmap: limit THP alignment of anonymous
mappings to PMD-aligned sizes") restricted this to only mmap sizes that
are multiples of the PMD_SIZE due to reported regressions in some
performance benchmarks -- which seemed mostly due to the reduced spatial
locality of related mappings due to the forced PMD-alignment.
Another unintended side effect has emerged: When a user specifies an mmap
hint address, the THP alignment logic modifies the behavior, potentially
ignoring the hint even if a sufficiently large gap exists at the requested
hint location.
Example Scenario:
Consider the following simplified virtual address (VA) space:
...
0x200000-0x400000 --- VMA A
0x400000-0x600000 --- Hole
0x600000-0x800000 --- VMA B
...
A call to mmap() with hint=0x400000 and len=0x200000 behaves differently:
- Before THP alignment: The requested region (size 0x200000) fits into
the gap at 0x400000, so the hint is respected.
- After alignment: The logic searches for a region of size
0x400000 (len + PMD_SIZE) starting at 0x400000.
This search fails due to the mapping at 0x600000 (VMA B), and the hint
is ignored, falling back to arch_get_unmapped_area[_topdown]().
In general the hint is effectively ignored, if there is any
existing mapping in the below range:
[mmap_hint + mmap_size, mmap_hint + mmap_size + PMD_SIZE)
This changes the semantics of mmap hint; from ""Respect the hint if a
sufficiently large gap exists at the requested location" to "Respect the
hint only if an additional PMD-sized gap exists beyond the requested size".
This has performance implications for allocators that allocate their heap
using mmap but try to keep it "as contiguous as possible" by using the
end of the exisiting heap as the address hint. With the new behavior
it's more likely to get a much less contiguous heap, adding extra
fragmentation and performance overhead.
To restore the expected behavior; don't use thp_get_unmapped_area_vmflags()
when the user provided a hint address, for anonymous mappings.
Note: As, Yang Shi, pointed out: the issue still remains for filesystems
which are using thp_get_unmapped_area() for their get_unmapped_area() op.
It is unclear what worklaods will regress for if we ignore THP alignment
when the hint address is provided for such file backed mappings -- so this
fix will be handled separately.
Cc: Andrew Morton <akpm(a)linux-foundation.org>
Cc: Vlastimil Babka <vbabka(a)suse.cz>
Cc: Yang Shi <yang(a)os.amperecomputing.com>
Cc: Rik van Riel <riel(a)surriel.com>
Cc: Ryan Roberts <ryan.roberts(a)arm.com>
Cc: Suren Baghdasaryan <surenb(a)google.com>
Cc: Minchan Kim <minchan(a)kernel.org>
Cc: Hans Boehm <hboehm(a)google.com>
Cc: Lokesh Gidra <lokeshgidra(a)google.com>
Cc: <stable(a)vger.kernel.org>
Fixes: efa7df3e3bb5 ("mm: align larger anonymous mappings on THP boundaries")
Signed-off-by: Kalesh Singh <kaleshsingh(a)google.com>
Reviewed-by: Rik van Riel <riel(a)surriel.com>
Reviewed-by: Vlastimil Babka <vbabka(a)suse.cz>
---
Changes in v2:
- Clarify the handling of file backed mappings, as highlighted by Yang
- Collect Vlastimil's and Rik's Reviewed-by's
mm/mmap.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/mm/mmap.c b/mm/mmap.c
index 79d541f1502b..2f01f1a8e304 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -901,6 +901,7 @@ __get_unmapped_area(struct file *file, unsigned long addr, unsigned long len,
if (get_area) {
addr = get_area(file, addr, len, pgoff, flags);
} else if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)
+ && !addr /* no hint */
&& IS_ALIGNED(len, PMD_SIZE)) {
/* Ensures that larger anonymous mappings are THP aligned. */
addr = thp_get_unmapped_area_vmflags(file, addr, len,
base-commit: 2d5404caa8c7bb5c4e0435f94b28834ae5456623
--
2.47.0.338.g60cca15819-goog
There's USB error when tegra board is shutting down:
[ 180.919315] usb 2-3: Failed to set U1 timeout to 0x0,error code -113
[ 180.919995] usb 2-3: Failed to set U1 timeout to 0xa,error code -113
[ 180.920512] usb 2-3: Failed to set U2 timeout to 0x4,error code -113
[ 186.157172] tegra-xusb 3610000.usb: xHCI host controller not responding, assume dead
[ 186.157858] tegra-xusb 3610000.usb: HC died; cleaning up
[ 186.317280] tegra-xusb 3610000.usb: Timeout while waiting for evaluate context command
The issue is caused by disabling LPM on already suspended ports.
For USB2 LPM, the LPM is already disabled during port suspend. For USB3
LPM, port won't transit to U1/U2 when it's already suspended in U3,
hence disabling LPM is only needed for ports that are not suspended.
Cc: Wayne Chang <waynec(a)nvidia.com>
Cc: stable(a)vger.kernel.org
Fixes: d920a2ed8620 ("usb: Disable USB3 LPM at shutdown")
Signed-off-by: Kai-Heng Feng <kaihengf(a)nvidia.com>
---
v2:
Add "Cc: stable(a)vger.kernel.org"
drivers/usb/core/port.c | 7 ++++---
1 file changed, 4 insertions(+), 3 deletions(-)
diff --git a/drivers/usb/core/port.c b/drivers/usb/core/port.c
index e7da2fca11a4..d50b9e004e76 100644
--- a/drivers/usb/core/port.c
+++ b/drivers/usb/core/port.c
@@ -452,10 +452,11 @@ static int usb_port_runtime_suspend(struct device *dev)
static void usb_port_shutdown(struct device *dev)
{
struct usb_port *port_dev = to_usb_port(dev);
+ struct usb_device *udev = port_dev->child;
- if (port_dev->child) {
- usb_disable_usb2_hardware_lpm(port_dev->child);
- usb_unlocked_disable_lpm(port_dev->child);
+ if (udev && !pm_runtime_suspended(&udev->dev)) {
+ usb_disable_usb2_hardware_lpm(udev);
+ usb_unlocked_disable_lpm(udev);
}
}
--
2.47.0
From: Takashi Iwai <tiwai(a)suse.de>
Upstream commit a3dd4d63eeb452cfb064a13862fb376ab108f6a6
The current USB-audio driver code doesn't check bLength of each
descriptor at traversing for clock descriptors. That is, when a
device provides a bogus descriptor with a shorter bLength, the driver
might hit out-of-bounds reads.
For addressing it, this patch adds sanity checks to the validator
functions for the clock descriptor traversal. When the descriptor
length is shorter than expected, it's skipped in the loop.
For the clock source and clock multiplier descriptors, we can just
check bLength against the sizeof() of each descriptor type.
OTOH, the clock selector descriptor of UAC2 and UAC3 has an array
of bNrInPins elements and two more fields at its tail, hence those
have to be checked in addition to the sizeof() check.
This patch ports the upstream commit a3dd4d63eeb4 to trees that do not
include the refactoring commit 9ec730052fa2 ("ALSA: usb-audio:
Refactoring UAC2/3 clock setup code"). That commit provides union
objects for pointing both UAC2 and UAC3 objects and unifies the clock
source, selector and multiplier helper functions. This means we need to
perform the check in each version specific helper function, but on the
other hand do not need to do version specific union dereferencing in the
macros and helper functions.
Reported-by: Benoît Sevens <bsevens(a)google.com>
Cc: <stable(a)vger.kernel.org>
Link: https://lore.kernel.org/20241121140613.3651-1-bsevens@google.com
Link: https://patch.msgid.link/20241125144629.20757-1-tiwai@suse.de
Signed-off-by: Takashi Iwai <tiwai(a)suse.de>
(cherry picked from commit a3dd4d63eeb452cfb064a13862fb376ab108f6a6)
Signed-off-by: Benoît Sevens <bsevens(a)google.com>
---
sound/usb/clock.c | 32 ++++++++++++++++++++++++++++++--
1 file changed, 30 insertions(+), 2 deletions(-)
diff --git a/sound/usb/clock.c b/sound/usb/clock.c
index 3d1c0ec11753..58902275c815 100644
--- a/sound/usb/clock.c
+++ b/sound/usb/clock.c
@@ -21,6 +21,10 @@
#include "clock.h"
#include "quirks.h"
+/* check whether the descriptor bLength has the minimal length */
+#define DESC_LENGTH_CHECK(p) \
+ (p->bLength >= sizeof(*p))
+
static void *find_uac_clock_desc(struct usb_host_interface *iface, int id,
bool (*validator)(void *, int), u8 type)
{
@@ -38,36 +42,60 @@ static void *find_uac_clock_desc(struct usb_host_interface *iface, int id,
static bool validate_clock_source_v2(void *p, int id)
{
struct uac_clock_source_descriptor *cs = p;
+ if (!DESC_LENGTH_CHECK(cs))
+ return false;
return cs->bClockID == id;
}
static bool validate_clock_source_v3(void *p, int id)
{
struct uac3_clock_source_descriptor *cs = p;
+ if (!DESC_LENGTH_CHECK(cs))
+ return false;
return cs->bClockID == id;
}
static bool validate_clock_selector_v2(void *p, int id)
{
struct uac_clock_selector_descriptor *cs = p;
- return cs->bClockID == id;
+ if (!DESC_LENGTH_CHECK(cs))
+ return false;
+ if (cs->bClockID != id)
+ return false;
+ /* additional length check for baCSourceID array (in bNrInPins size)
+ * and two more fields (which sizes depend on the protocol)
+ */
+ return cs->bLength >= sizeof(*cs) + cs->bNrInPins +
+ 1 /* bmControls */ + 1 /* iClockSelector */;
}
static bool validate_clock_selector_v3(void *p, int id)
{
struct uac3_clock_selector_descriptor *cs = p;
- return cs->bClockID == id;
+ if (!DESC_LENGTH_CHECK(cs))
+ return false;
+ if (cs->bClockID != id)
+ return false;
+ /* additional length check for baCSourceID array (in bNrInPins size)
+ * and two more fields (which sizes depend on the protocol)
+ */
+ return cs->bLength >= sizeof(*cs) + cs->bNrInPins +
+ 4 /* bmControls */ + 2 /* wCSelectorDescrStr */;
}
static bool validate_clock_multiplier_v2(void *p, int id)
{
struct uac_clock_multiplier_descriptor *cs = p;
+ if (!DESC_LENGTH_CHECK(cs))
+ return false;
return cs->bClockID == id;
}
static bool validate_clock_multiplier_v3(void *p, int id)
{
struct uac3_clock_multiplier_descriptor *cs = p;
+ if (!DESC_LENGTH_CHECK(cs))
+ return false;
return cs->bClockID == id;
}
--
2.47.0.338.g60cca15819-goog
The quilt patch titled
Subject: sched/numa: fix memory leak due to the overwritten vma->numab_state
has been removed from the -mm tree. Its filename was
sched-numa-fix-memory-leak-due-to-the-overwritten-vma-numab_state.patch
This patch was dropped because it was merged into the mm-hotfixes-stable branch
of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
------------------------------------------------------
From: Adrian Huang <ahuang12(a)lenovo.com>
Subject: sched/numa: fix memory leak due to the overwritten vma->numab_state
Date: Wed, 13 Nov 2024 18:21:46 +0800
[Problem Description]
When running the hackbench program of LTP, the following memory leak is
reported by kmemleak.
# /opt/ltp/testcases/bin/hackbench 20 thread 1000
Running with 20*40 (== 800) tasks.
# dmesg | grep kmemleak
...
kmemleak: 480 new suspected memory leaks (see /sys/kernel/debug/kmemleak)
kmemleak: 665 new suspected memory leaks (see /sys/kernel/debug/kmemleak)
# cat /sys/kernel/debug/kmemleak
unreferenced object 0xffff888cd8ca2c40 (size 64):
comm "hackbench", pid 17142, jiffies 4299780315
hex dump (first 32 bytes):
ac 74 49 00 01 00 00 00 4c 84 49 00 01 00 00 00 .tI.....L.I.....
00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................
backtrace (crc bff18fd4):
[<ffffffff81419a89>] __kmalloc_cache_noprof+0x2f9/0x3f0
[<ffffffff8113f715>] task_numa_work+0x725/0xa00
[<ffffffff8110f878>] task_work_run+0x58/0x90
[<ffffffff81ddd9f8>] syscall_exit_to_user_mode+0x1c8/0x1e0
[<ffffffff81dd78d5>] do_syscall_64+0x85/0x150
[<ffffffff81e0012b>] entry_SYSCALL_64_after_hwframe+0x76/0x7e
...
This issue can be consistently reproduced on three different servers:
* a 448-core server
* a 256-core server
* a 192-core server
[Root Cause]
Since multiple threads are created by the hackbench program (along with
the command argument 'thread'), a shared vma might be accessed by two or
more cores simultaneously. When two or more cores observe that
vma->numab_state is NULL at the same time, vma->numab_state will be
overwritten.
Although current code ensures that only one thread scans the VMAs in a
single 'numa_scan_period', there might be a chance for another thread
to enter in the next 'numa_scan_period' while we have not gotten till
numab_state allocation [1].
Note that the command `/opt/ltp/testcases/bin/hackbench 50 process 1000`
cannot the reproduce the issue. It is verified with 200+ test runs.
[Solution]
Use the cmpxchg atomic operation to ensure that only one thread executes
the vma->numab_state assignment.
[1] https://lore.kernel.org/lkml/1794be3c-358c-4cdc-a43d-a1f841d91ef7@amd.com/
Link: https://lkml.kernel.org/r/20241113102146.2384-1-ahuang12@lenovo.com
Fixes: ef6a22b70f6d ("sched/numa: apply the scan delay to every new vma")
Signed-off-by: Adrian Huang <ahuang12(a)lenovo.com>
Reported-by: Jiwei Sun <sunjw10(a)lenovo.com>
Reviewed-by: Raghavendra K T <raghavendra.kt(a)amd.com>
Reviewed-by: Vlastimil Babka <vbabka(a)suse.cz>
Cc: Ben Segall <bsegall(a)google.com>
Cc: Dietmar Eggemann <dietmar.eggemann(a)arm.com>
Cc: Ingo Molnar <mingo(a)redhat.com>
Cc: Juri Lelli <juri.lelli(a)redhat.com>
Cc: Mel Gorman <mgorman(a)suse.de>
Cc: Peter Zijlstra <peterz(a)infradead.org>
Cc: Steven Rostedt <rostedt(a)goodmis.org>
Cc: Valentin Schneider <vschneid(a)redhat.com>
Cc: Vincent Guittot <vincent.guittot(a)linaro.org>
Cc: <stable(a)vger.kernel.org>
Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org>
---
kernel/sched/fair.c | 12 +++++++++---
1 file changed, 9 insertions(+), 3 deletions(-)
--- a/kernel/sched/fair.c~sched-numa-fix-memory-leak-due-to-the-overwritten-vma-numab_state
+++ a/kernel/sched/fair.c
@@ -3399,10 +3399,16 @@ retry_pids:
/* Initialise new per-VMA NUMAB state. */
if (!vma->numab_state) {
- vma->numab_state = kzalloc(sizeof(struct vma_numab_state),
- GFP_KERNEL);
- if (!vma->numab_state)
+ struct vma_numab_state *ptr;
+
+ ptr = kzalloc(sizeof(*ptr), GFP_KERNEL);
+ if (!ptr)
+ continue;
+
+ if (cmpxchg(&vma->numab_state, NULL, ptr)) {
+ kfree(ptr);
continue;
+ }
vma->numab_state->start_scan_seq = mm->numa_scan_seq;
_
Patches currently in -mm which might be from ahuang12(a)lenovo.com are