commit 56406e017a883b54b339207b230f85599f4d70ae upstream.
The commit 3bc04e28a030 ("usb: dwc2: host: Get aligned DMA in a more
supported way") introduced a common way to align DMA allocations.
The code in the commit aligns the struct dma_aligned_buffer but the
actual DMA address pointed by data[0] gets aligned to an offset from
the allocated boundary by the kmalloc_ptr and the old_xfer_buffer
pointers.
This is against the recommendation in Documentation/DMA-API.txt which
states:
Therefore, it is recommended that driver writers who don't take
special care to determine the cache line size at run time only map
virtual regions that begin and end on page boundaries (which are
guaranteed also to be cache line boundaries).
The effect of this is that architectures with non-coherent DMA caches
may run into memory corruption or kernel crashes with Unhandled
kernel unaligned accesses exceptions.
Fix the alignment by positioning the DMA area in front of the allocation
and use memory at the end of the area for storing the orginal
transfer_buffer pointer. This may have the added benefit of increased
performance as the DMA area is now fully aligned on all architectures.
Tested with Lantiq xRX200 (MIPS) and RPi Model B Rev 2 (ARM).
Fixes: 3bc04e28a030 ("usb: dwc2: host: Get aligned DMA in a more supported way")
Cc: <stable(a)vger.kernel.org>
Reviewed-by: Douglas Anderson <dianders(a)chromium.org>
[ Antti: backported to 4.9: edited difference in whitespace ]
Signed-off-by: Antti Seppälä <a.seppala(a)gmail.com>
Signed-off-by: Felipe Balbi <felipe.balbi(a)linux.intel.com>
---
Notes:
This is the same patch already applied upstream and queued for stable kernels
4.14 and 4.17 but with a minor whitespace edit to make it apply also on 4.9.
drivers/usb/dwc2/hcd.c | 44 +++++++++++++++++++++++---------------------
1 file changed, 23 insertions(+), 21 deletions(-)
diff --git a/drivers/usb/dwc2/hcd.c b/drivers/usb/dwc2/hcd.c
index 0a0cf154814b..984d6aae7529 100644
--- a/drivers/usb/dwc2/hcd.c
+++ b/drivers/usb/dwc2/hcd.c
@@ -2544,34 +2544,29 @@ static void dwc2_hc_init_xfer(struct dwc2_hsotg *hsotg,
#define DWC2_USB_DMA_ALIGN 4
-struct dma_aligned_buffer {
- void *kmalloc_ptr;
- void *old_xfer_buffer;
- u8 data[0];
-};
-
static void dwc2_free_dma_aligned_buffer(struct urb *urb)
{
- struct dma_aligned_buffer *temp;
+ void *stored_xfer_buffer;
if (!(urb->transfer_flags & URB_ALIGNED_TEMP_BUFFER))
return;
- temp = container_of(urb->transfer_buffer,
- struct dma_aligned_buffer, data);
+ /* Restore urb->transfer_buffer from the end of the allocated area */
+ memcpy(&stored_xfer_buffer, urb->transfer_buffer +
+ urb->transfer_buffer_length, sizeof(urb->transfer_buffer));
if (usb_urb_dir_in(urb))
- memcpy(temp->old_xfer_buffer, temp->data,
+ memcpy(stored_xfer_buffer, urb->transfer_buffer,
urb->transfer_buffer_length);
- urb->transfer_buffer = temp->old_xfer_buffer;
- kfree(temp->kmalloc_ptr);
+ kfree(urb->transfer_buffer);
+ urb->transfer_buffer = stored_xfer_buffer;
urb->transfer_flags &= ~URB_ALIGNED_TEMP_BUFFER;
}
static int dwc2_alloc_dma_aligned_buffer(struct urb *urb, gfp_t mem_flags)
{
- struct dma_aligned_buffer *temp, *kmalloc_ptr;
+ void *kmalloc_ptr;
size_t kmalloc_size;
if (urb->num_sgs || urb->sg ||
@@ -2579,22 +2574,29 @@ static int dwc2_alloc_dma_aligned_buffer(struct urb *urb, gfp_t mem_flags)
!((uintptr_t)urb->transfer_buffer & (DWC2_USB_DMA_ALIGN - 1)))
return 0;
- /* Allocate a buffer with enough padding for alignment */
+ /*
+ * Allocate a buffer with enough padding for original transfer_buffer
+ * pointer. This allocation is guaranteed to be aligned properly for
+ * DMA
+ */
kmalloc_size = urb->transfer_buffer_length +
- sizeof(struct dma_aligned_buffer) + DWC2_USB_DMA_ALIGN - 1;
+ sizeof(urb->transfer_buffer);
kmalloc_ptr = kmalloc(kmalloc_size, mem_flags);
if (!kmalloc_ptr)
return -ENOMEM;
- /* Position our struct dma_aligned_buffer such that data is aligned */
- temp = PTR_ALIGN(kmalloc_ptr + 1, DWC2_USB_DMA_ALIGN) - 1;
- temp->kmalloc_ptr = kmalloc_ptr;
- temp->old_xfer_buffer = urb->transfer_buffer;
+ /*
+ * Position value of original urb->transfer_buffer pointer to the end
+ * of allocation for later referencing
+ */
+ memcpy(kmalloc_ptr + urb->transfer_buffer_length,
+ &urb->transfer_buffer, sizeof(urb->transfer_buffer));
+
if (usb_urb_dir_out(urb))
- memcpy(temp->data, urb->transfer_buffer,
+ memcpy(kmalloc_ptr, urb->transfer_buffer,
urb->transfer_buffer_length);
- urb->transfer_buffer = temp->data;
+ urb->transfer_buffer = kmalloc_ptr;
urb->transfer_flags |= URB_ALIGNED_TEMP_BUFFER;
--
2.13.6
The patch below does not apply to the 3.18-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>.
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
>From 73c8d8945505acdcbae137c2e00a1232e0be709f Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat(a)kernel.org>
Date: Sat, 14 Jul 2018 01:28:15 +0900
Subject: [PATCH] ring_buffer: tracing: Inherit the tracing setting to next
ring buffer
Maintain the tracing on/off setting of the ring_buffer when switching
to the trace buffer snapshot.
Taking a snapshot is done by swapping the backup ring buffer
(max_tr_buffer). But since the tracing on/off setting is defined
by the ring buffer, when swapping it, the tracing on/off setting
can also be changed. This causes a strange result like below:
/sys/kernel/debug/tracing # cat tracing_on
1
/sys/kernel/debug/tracing # echo 0 > tracing_on
/sys/kernel/debug/tracing # cat tracing_on
0
/sys/kernel/debug/tracing # echo 1 > snapshot
/sys/kernel/debug/tracing # cat tracing_on
1
/sys/kernel/debug/tracing # echo 1 > snapshot
/sys/kernel/debug/tracing # cat tracing_on
0
We don't touch tracing_on, but snapshot changes tracing_on
setting each time. This is an anomaly, because user doesn't know
that each "ring_buffer" stores its own tracing-enable state and
the snapshot is done by swapping ring buffers.
Link: http://lkml.kernel.org/r/153149929558.11274.11730609978254724394.stgit@devb…
Cc: Ingo Molnar <mingo(a)redhat.com>
Cc: Shuah Khan <shuah(a)kernel.org>
Cc: Tom Zanussi <tom.zanussi(a)linux.intel.com>
Cc: Hiraku Toyooka <hiraku.toyooka(a)cybertrust.co.jp>
Cc: stable(a)vger.kernel.org
Fixes: debdd57f5145 ("tracing: Make a snapshot feature available from userspace")
Signed-off-by: Masami Hiramatsu <mhiramat(a)kernel.org>
[ Updated commit log and comment in the code ]
Signed-off-by: Steven Rostedt (VMware) <rostedt(a)goodmis.org>
diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h
index b72ebdff0b77..003d09ab308d 100644
--- a/include/linux/ring_buffer.h
+++ b/include/linux/ring_buffer.h
@@ -165,6 +165,7 @@ void ring_buffer_record_enable(struct ring_buffer *buffer);
void ring_buffer_record_off(struct ring_buffer *buffer);
void ring_buffer_record_on(struct ring_buffer *buffer);
int ring_buffer_record_is_on(struct ring_buffer *buffer);
+int ring_buffer_record_is_set_on(struct ring_buffer *buffer);
void ring_buffer_record_disable_cpu(struct ring_buffer *buffer, int cpu);
void ring_buffer_record_enable_cpu(struct ring_buffer *buffer, int cpu);
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 6a46af21765c..0b0b688ea166 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -3226,6 +3226,22 @@ int ring_buffer_record_is_on(struct ring_buffer *buffer)
return !atomic_read(&buffer->record_disabled);
}
+/**
+ * ring_buffer_record_is_set_on - return true if the ring buffer is set writable
+ * @buffer: The ring buffer to see if write is set enabled
+ *
+ * Returns true if the ring buffer is set writable by ring_buffer_record_on().
+ * Note that this does NOT mean it is in a writable state.
+ *
+ * It may return true when the ring buffer has been disabled by
+ * ring_buffer_record_disable(), as that is a temporary disabling of
+ * the ring buffer.
+ */
+int ring_buffer_record_is_set_on(struct ring_buffer *buffer)
+{
+ return !(atomic_read(&buffer->record_disabled) & RB_BUFFER_OFF);
+}
+
/**
* ring_buffer_record_disable_cpu - stop all writes into the cpu_buffer
* @buffer: The ring buffer to stop writes to.
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 87cf25171fb8..823687997b01 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1373,6 +1373,12 @@ update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
arch_spin_lock(&tr->max_lock);
+ /* Inherit the recordable setting from trace_buffer */
+ if (ring_buffer_record_is_set_on(tr->trace_buffer.buffer))
+ ring_buffer_record_on(tr->max_buffer.buffer);
+ else
+ ring_buffer_record_off(tr->max_buffer.buffer);
+
swap(tr->trace_buffer.buffer, tr->max_buffer.buffer);
__update_max_tr(tr, tsk, cpu);
The patch below does not apply to the 4.4-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>.
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
>From 73c8d8945505acdcbae137c2e00a1232e0be709f Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat(a)kernel.org>
Date: Sat, 14 Jul 2018 01:28:15 +0900
Subject: [PATCH] ring_buffer: tracing: Inherit the tracing setting to next
ring buffer
Maintain the tracing on/off setting of the ring_buffer when switching
to the trace buffer snapshot.
Taking a snapshot is done by swapping the backup ring buffer
(max_tr_buffer). But since the tracing on/off setting is defined
by the ring buffer, when swapping it, the tracing on/off setting
can also be changed. This causes a strange result like below:
/sys/kernel/debug/tracing # cat tracing_on
1
/sys/kernel/debug/tracing # echo 0 > tracing_on
/sys/kernel/debug/tracing # cat tracing_on
0
/sys/kernel/debug/tracing # echo 1 > snapshot
/sys/kernel/debug/tracing # cat tracing_on
1
/sys/kernel/debug/tracing # echo 1 > snapshot
/sys/kernel/debug/tracing # cat tracing_on
0
We don't touch tracing_on, but snapshot changes tracing_on
setting each time. This is an anomaly, because user doesn't know
that each "ring_buffer" stores its own tracing-enable state and
the snapshot is done by swapping ring buffers.
Link: http://lkml.kernel.org/r/153149929558.11274.11730609978254724394.stgit@devb…
Cc: Ingo Molnar <mingo(a)redhat.com>
Cc: Shuah Khan <shuah(a)kernel.org>
Cc: Tom Zanussi <tom.zanussi(a)linux.intel.com>
Cc: Hiraku Toyooka <hiraku.toyooka(a)cybertrust.co.jp>
Cc: stable(a)vger.kernel.org
Fixes: debdd57f5145 ("tracing: Make a snapshot feature available from userspace")
Signed-off-by: Masami Hiramatsu <mhiramat(a)kernel.org>
[ Updated commit log and comment in the code ]
Signed-off-by: Steven Rostedt (VMware) <rostedt(a)goodmis.org>
diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h
index b72ebdff0b77..003d09ab308d 100644
--- a/include/linux/ring_buffer.h
+++ b/include/linux/ring_buffer.h
@@ -165,6 +165,7 @@ void ring_buffer_record_enable(struct ring_buffer *buffer);
void ring_buffer_record_off(struct ring_buffer *buffer);
void ring_buffer_record_on(struct ring_buffer *buffer);
int ring_buffer_record_is_on(struct ring_buffer *buffer);
+int ring_buffer_record_is_set_on(struct ring_buffer *buffer);
void ring_buffer_record_disable_cpu(struct ring_buffer *buffer, int cpu);
void ring_buffer_record_enable_cpu(struct ring_buffer *buffer, int cpu);
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 6a46af21765c..0b0b688ea166 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -3226,6 +3226,22 @@ int ring_buffer_record_is_on(struct ring_buffer *buffer)
return !atomic_read(&buffer->record_disabled);
}
+/**
+ * ring_buffer_record_is_set_on - return true if the ring buffer is set writable
+ * @buffer: The ring buffer to see if write is set enabled
+ *
+ * Returns true if the ring buffer is set writable by ring_buffer_record_on().
+ * Note that this does NOT mean it is in a writable state.
+ *
+ * It may return true when the ring buffer has been disabled by
+ * ring_buffer_record_disable(), as that is a temporary disabling of
+ * the ring buffer.
+ */
+int ring_buffer_record_is_set_on(struct ring_buffer *buffer)
+{
+ return !(atomic_read(&buffer->record_disabled) & RB_BUFFER_OFF);
+}
+
/**
* ring_buffer_record_disable_cpu - stop all writes into the cpu_buffer
* @buffer: The ring buffer to stop writes to.
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 87cf25171fb8..823687997b01 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1373,6 +1373,12 @@ update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
arch_spin_lock(&tr->max_lock);
+ /* Inherit the recordable setting from trace_buffer */
+ if (ring_buffer_record_is_set_on(tr->trace_buffer.buffer))
+ ring_buffer_record_on(tr->max_buffer.buffer);
+ else
+ ring_buffer_record_off(tr->max_buffer.buffer);
+
swap(tr->trace_buffer.buffer, tr->max_buffer.buffer);
__update_max_tr(tr, tsk, cpu);
The patch below does not apply to the 4.9-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>.
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
>From 73c8d8945505acdcbae137c2e00a1232e0be709f Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat(a)kernel.org>
Date: Sat, 14 Jul 2018 01:28:15 +0900
Subject: [PATCH] ring_buffer: tracing: Inherit the tracing setting to next
ring buffer
Maintain the tracing on/off setting of the ring_buffer when switching
to the trace buffer snapshot.
Taking a snapshot is done by swapping the backup ring buffer
(max_tr_buffer). But since the tracing on/off setting is defined
by the ring buffer, when swapping it, the tracing on/off setting
can also be changed. This causes a strange result like below:
/sys/kernel/debug/tracing # cat tracing_on
1
/sys/kernel/debug/tracing # echo 0 > tracing_on
/sys/kernel/debug/tracing # cat tracing_on
0
/sys/kernel/debug/tracing # echo 1 > snapshot
/sys/kernel/debug/tracing # cat tracing_on
1
/sys/kernel/debug/tracing # echo 1 > snapshot
/sys/kernel/debug/tracing # cat tracing_on
0
We don't touch tracing_on, but snapshot changes tracing_on
setting each time. This is an anomaly, because user doesn't know
that each "ring_buffer" stores its own tracing-enable state and
the snapshot is done by swapping ring buffers.
Link: http://lkml.kernel.org/r/153149929558.11274.11730609978254724394.stgit@devb…
Cc: Ingo Molnar <mingo(a)redhat.com>
Cc: Shuah Khan <shuah(a)kernel.org>
Cc: Tom Zanussi <tom.zanussi(a)linux.intel.com>
Cc: Hiraku Toyooka <hiraku.toyooka(a)cybertrust.co.jp>
Cc: stable(a)vger.kernel.org
Fixes: debdd57f5145 ("tracing: Make a snapshot feature available from userspace")
Signed-off-by: Masami Hiramatsu <mhiramat(a)kernel.org>
[ Updated commit log and comment in the code ]
Signed-off-by: Steven Rostedt (VMware) <rostedt(a)goodmis.org>
diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h
index b72ebdff0b77..003d09ab308d 100644
--- a/include/linux/ring_buffer.h
+++ b/include/linux/ring_buffer.h
@@ -165,6 +165,7 @@ void ring_buffer_record_enable(struct ring_buffer *buffer);
void ring_buffer_record_off(struct ring_buffer *buffer);
void ring_buffer_record_on(struct ring_buffer *buffer);
int ring_buffer_record_is_on(struct ring_buffer *buffer);
+int ring_buffer_record_is_set_on(struct ring_buffer *buffer);
void ring_buffer_record_disable_cpu(struct ring_buffer *buffer, int cpu);
void ring_buffer_record_enable_cpu(struct ring_buffer *buffer, int cpu);
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 6a46af21765c..0b0b688ea166 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -3226,6 +3226,22 @@ int ring_buffer_record_is_on(struct ring_buffer *buffer)
return !atomic_read(&buffer->record_disabled);
}
+/**
+ * ring_buffer_record_is_set_on - return true if the ring buffer is set writable
+ * @buffer: The ring buffer to see if write is set enabled
+ *
+ * Returns true if the ring buffer is set writable by ring_buffer_record_on().
+ * Note that this does NOT mean it is in a writable state.
+ *
+ * It may return true when the ring buffer has been disabled by
+ * ring_buffer_record_disable(), as that is a temporary disabling of
+ * the ring buffer.
+ */
+int ring_buffer_record_is_set_on(struct ring_buffer *buffer)
+{
+ return !(atomic_read(&buffer->record_disabled) & RB_BUFFER_OFF);
+}
+
/**
* ring_buffer_record_disable_cpu - stop all writes into the cpu_buffer
* @buffer: The ring buffer to stop writes to.
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 87cf25171fb8..823687997b01 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1373,6 +1373,12 @@ update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
arch_spin_lock(&tr->max_lock);
+ /* Inherit the recordable setting from trace_buffer */
+ if (ring_buffer_record_is_set_on(tr->trace_buffer.buffer))
+ ring_buffer_record_on(tr->max_buffer.buffer);
+ else
+ ring_buffer_record_off(tr->max_buffer.buffer);
+
swap(tr->trace_buffer.buffer, tr->max_buffer.buffer);
__update_max_tr(tr, tsk, cpu);
The patch below does not apply to the 4.17-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>.
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
>From 73c8d8945505acdcbae137c2e00a1232e0be709f Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat(a)kernel.org>
Date: Sat, 14 Jul 2018 01:28:15 +0900
Subject: [PATCH] ring_buffer: tracing: Inherit the tracing setting to next
ring buffer
Maintain the tracing on/off setting of the ring_buffer when switching
to the trace buffer snapshot.
Taking a snapshot is done by swapping the backup ring buffer
(max_tr_buffer). But since the tracing on/off setting is defined
by the ring buffer, when swapping it, the tracing on/off setting
can also be changed. This causes a strange result like below:
/sys/kernel/debug/tracing # cat tracing_on
1
/sys/kernel/debug/tracing # echo 0 > tracing_on
/sys/kernel/debug/tracing # cat tracing_on
0
/sys/kernel/debug/tracing # echo 1 > snapshot
/sys/kernel/debug/tracing # cat tracing_on
1
/sys/kernel/debug/tracing # echo 1 > snapshot
/sys/kernel/debug/tracing # cat tracing_on
0
We don't touch tracing_on, but snapshot changes tracing_on
setting each time. This is an anomaly, because user doesn't know
that each "ring_buffer" stores its own tracing-enable state and
the snapshot is done by swapping ring buffers.
Link: http://lkml.kernel.org/r/153149929558.11274.11730609978254724394.stgit@devb…
Cc: Ingo Molnar <mingo(a)redhat.com>
Cc: Shuah Khan <shuah(a)kernel.org>
Cc: Tom Zanussi <tom.zanussi(a)linux.intel.com>
Cc: Hiraku Toyooka <hiraku.toyooka(a)cybertrust.co.jp>
Cc: stable(a)vger.kernel.org
Fixes: debdd57f5145 ("tracing: Make a snapshot feature available from userspace")
Signed-off-by: Masami Hiramatsu <mhiramat(a)kernel.org>
[ Updated commit log and comment in the code ]
Signed-off-by: Steven Rostedt (VMware) <rostedt(a)goodmis.org>
diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h
index b72ebdff0b77..003d09ab308d 100644
--- a/include/linux/ring_buffer.h
+++ b/include/linux/ring_buffer.h
@@ -165,6 +165,7 @@ void ring_buffer_record_enable(struct ring_buffer *buffer);
void ring_buffer_record_off(struct ring_buffer *buffer);
void ring_buffer_record_on(struct ring_buffer *buffer);
int ring_buffer_record_is_on(struct ring_buffer *buffer);
+int ring_buffer_record_is_set_on(struct ring_buffer *buffer);
void ring_buffer_record_disable_cpu(struct ring_buffer *buffer, int cpu);
void ring_buffer_record_enable_cpu(struct ring_buffer *buffer, int cpu);
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 6a46af21765c..0b0b688ea166 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -3226,6 +3226,22 @@ int ring_buffer_record_is_on(struct ring_buffer *buffer)
return !atomic_read(&buffer->record_disabled);
}
+/**
+ * ring_buffer_record_is_set_on - return true if the ring buffer is set writable
+ * @buffer: The ring buffer to see if write is set enabled
+ *
+ * Returns true if the ring buffer is set writable by ring_buffer_record_on().
+ * Note that this does NOT mean it is in a writable state.
+ *
+ * It may return true when the ring buffer has been disabled by
+ * ring_buffer_record_disable(), as that is a temporary disabling of
+ * the ring buffer.
+ */
+int ring_buffer_record_is_set_on(struct ring_buffer *buffer)
+{
+ return !(atomic_read(&buffer->record_disabled) & RB_BUFFER_OFF);
+}
+
/**
* ring_buffer_record_disable_cpu - stop all writes into the cpu_buffer
* @buffer: The ring buffer to stop writes to.
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 87cf25171fb8..823687997b01 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1373,6 +1373,12 @@ update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
arch_spin_lock(&tr->max_lock);
+ /* Inherit the recordable setting from trace_buffer */
+ if (ring_buffer_record_is_set_on(tr->trace_buffer.buffer))
+ ring_buffer_record_on(tr->max_buffer.buffer);
+ else
+ ring_buffer_record_off(tr->max_buffer.buffer);
+
swap(tr->trace_buffer.buffer, tr->max_buffer.buffer);
__update_max_tr(tr, tsk, cpu);
The patch below does not apply to the 3.18-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>.
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
>From 3e536e222f2930534c252c1cc7ae799c725c5ff9 Mon Sep 17 00:00:00 2001
From: Snild Dolkow <snild(a)sony.com>
Date: Thu, 26 Jul 2018 09:15:39 +0200
Subject: [PATCH] kthread, tracing: Don't expose half-written comm when
creating kthreads
There is a window for racing when printing directly to task->comm,
allowing other threads to see a non-terminated string. The vsnprintf
function fills the buffer, counts the truncated chars, then finally
writes the \0 at the end.
creator other
vsnprintf:
fill (not terminated)
count the rest trace_sched_waking(p):
... memcpy(comm, p->comm, TASK_COMM_LEN)
write \0
The consequences depend on how 'other' uses the string. In our case,
it was copied into the tracing system's saved cmdlines, a buffer of
adjacent TASK_COMM_LEN-byte buffers (note the 'n' where 0 should be):
crash-arm64> x/1024s savedcmd->saved_cmdlines | grep 'evenk'
0xffffffd5b3818640: "irq/497-pwr_evenkworker/u16:12"
...and a strcpy out of there would cause stack corruption:
[224761.522292] Kernel panic - not syncing: stack-protector:
Kernel stack is corrupted in: ffffff9bf9783c78
crash-arm64> kbt | grep 'comm\|trace_print_context'
#6 0xffffff9bf9783c78 in trace_print_context+0x18c(+396)
comm (char [16]) = "irq/497-pwr_even"
crash-arm64> rd 0xffffffd4d0e17d14 8
ffffffd4d0e17d14: 2f71726900000000 5f7277702d373934 ....irq/497-pwr_
ffffffd4d0e17d24: 726f776b6e657665 3a3631752f72656b evenkworker/u16:
ffffffd4d0e17d34: f9780248ff003231 cede60e0ffffff9b 12..H.x......`..
ffffffd4d0e17d44: cede60c8ffffffd4 00000fffffffffd4 .....`..........
The workaround in e09e28671 (use strlcpy in __trace_find_cmdline) was
likely needed because of this same bug.
Solved by vsnprintf:ing to a local buffer, then using set_task_comm().
This way, there won't be a window where comm is not terminated.
Link: http://lkml.kernel.org/r/20180726071539.188015-1-snild@sony.com
Cc: stable(a)vger.kernel.org
Fixes: bc0c38d139ec7 ("ftrace: latency tracer infrastructure")
Reviewed-by: Steven Rostedt (VMware) <rostedt(a)goodmis.org>
Signed-off-by: Snild Dolkow <snild(a)sony.com>
Signed-off-by: Steven Rostedt (VMware) <rostedt(a)goodmis.org>
diff --git a/kernel/kthread.c b/kernel/kthread.c
index 750cb8082694..486dedbd9af5 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -325,8 +325,14 @@ struct task_struct *__kthread_create_on_node(int (*threadfn)(void *data),
task = create->result;
if (!IS_ERR(task)) {
static const struct sched_param param = { .sched_priority = 0 };
+ char name[TASK_COMM_LEN];
- vsnprintf(task->comm, sizeof(task->comm), namefmt, args);
+ /*
+ * task is already visible to other tasks, so updating
+ * COMM must be protected.
+ */
+ vsnprintf(name, sizeof(name), namefmt, args);
+ set_task_comm(task, name);
/*
* root may have changed our (kthreadd's) priority or CPU mask.
* The kernel thread should not inherit these properties.