Page reporting features were never supported by legacy hypervisors.
Supporting them poses a problem: should we use native endian-ness (like
current code assumes)? Or little endian-ness like the virtio spec says?
Rather than try to figure out, and since results of
incorrect endian-ness are dire, let's just block this configuration.
Cc: stable(a)vger.kernel.org
Signed-off-by: Michael S. Tsirkin <mst(a)redhat.com>
---
drivers/virtio/virtio_balloon.c | 9 +++++++++
1 file changed, 9 insertions(+)
diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c
index 5d4b891bf84f..b9bc03345157 100644
--- a/drivers/virtio/virtio_balloon.c
+++ b/drivers/virtio/virtio_balloon.c
@@ -1107,6 +1107,15 @@ static int virtballoon_restore(struct virtio_device *vdev)
static int virtballoon_validate(struct virtio_device *vdev)
{
+ /*
+ * Legacy devices never specified how modern features should behave.
+ * E.g. which endian-ness to use? Better not to assume anything.
+ */
+ if (!virtio_has_feature(vdev, VIRTIO_F_VERSION_1)) {
+ __virtio_clear_bit(vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT);
+ __virtio_clear_bit(vdev, VIRTIO_BALLOON_F_PAGE_POISON);
+ __virtio_clear_bit(vdev, VIRTIO_BALLOON_F_REPORTING);
+ }
/*
* Inform the hypervisor that our pages are poisoned or
* initialized. If we cannot do that then we should disable
--
MST
From: Bas Nieuwenhuizen <bas(a)basnieuwenhuizen.nl>
Calltree:
timeline_fence_release
drm_sched_entity_wakeup
dma_fence_signal_locked
sync_timeline_signal
sw_sync_ioctl
Releasing the reference to the fence in the fence signal callback
seems reasonable to me, so this patch avoids the locking issue in
sw_sync.
d3862e44daa7 ("dma-buf/sw-sync: Fix locking around sync_timeline lists")
fixed the recursive locking issue but caused an use-after-free. Later
d3c6dd1fb30d ("dma-buf/sw_sync: Synchronize signal vs syncpt free")
fixed the use-after-free but reintroduced the recursive locking issue.
In this attempt we avoid the use-after-free still because the release
function still always locks, and outside of the locking region in the
signal function we have properly refcounted references.
We furthermore also avoid the recurive lock by making sure that either:
1) We have a properly refcounted reference, preventing the signal from
triggering the release function inside the locked region.
2) The refcount was already zero, and hence nobody will be able to trigger
the release function from the signal function.
v2: Move dma_fence_signal() into second loop in preparation to moving
the callback out of the timeline obj->lock.
Fixes: d3c6dd1fb30d ("dma-buf/sw_sync: Synchronize signal vs syncpt free")
Cc: Sumit Semwal <sumit.semwal(a)linaro.org>
Cc: Chris Wilson <chris(a)chris-wilson.co.uk>
Cc: Gustavo Padovan <gustavo(a)padovan.org>
Cc: Christian König <christian.koenig(a)amd.com>
Cc: <stable(a)vger.kernel.org>
Signed-off-by: Bas Nieuwenhuizen <bas(a)basnieuwenhuizen.nl>
Signed-off-by: Chris Wilson <chris(a)chris-wilson.co.uk>
---
drivers/dma-buf/sw_sync.c | 32 ++++++++++++++++++++++----------
1 file changed, 22 insertions(+), 10 deletions(-)
diff --git a/drivers/dma-buf/sw_sync.c b/drivers/dma-buf/sw_sync.c
index 348b3a9170fa..807c82148062 100644
--- a/drivers/dma-buf/sw_sync.c
+++ b/drivers/dma-buf/sw_sync.c
@@ -192,6 +192,7 @@ static const struct dma_fence_ops timeline_fence_ops = {
static void sync_timeline_signal(struct sync_timeline *obj, unsigned int inc)
{
struct sync_pt *pt, *next;
+ LIST_HEAD(signal);
trace_sync_timeline(obj);
@@ -203,21 +204,32 @@ static void sync_timeline_signal(struct sync_timeline *obj, unsigned int inc)
if (!timeline_fence_signaled(&pt->base))
break;
- list_del_init(&pt->link);
- rb_erase(&pt->node, &obj->pt_tree);
-
/*
- * A signal callback may release the last reference to this
- * fence, causing it to be freed. That operation has to be
- * last to avoid a use after free inside this loop, and must
- * be after we remove the fence from the timeline in order to
- * prevent deadlocking on timeline->lock inside
- * timeline_fence_release().
+ * We need to take a reference to avoid a release during
+ * signalling (which can cause a recursive lock of obj->lock).
+ * If refcount was already zero, another thread is already
+ * taking care of destroying the fence.
*/
- dma_fence_signal_locked(&pt->base);
+ if (!dma_fence_get_rcu(&pt->base))
+ continue;
+
+ list_move_tail(&pt->link, &signal);
+ rb_erase(&pt->node, &obj->pt_tree);
}
spin_unlock_irq(&obj->lock);
+
+ list_for_each_entry_safe(pt, next, &signal, link) {
+ /*
+ * This needs to be cleared before release, otherwise the
+ * timeline_fence_release function gets confused about also
+ * removing the fence from the pt_tree.
+ */
+ list_del_init(&pt->link);
+
+ dma_fence_signal(&pt->base);
+ dma_fence_put(&pt->base);
+ }
}
/**
--
2.20.1
This was suggested in the syzkaller thread as a fix for a bunch of issues. It
seems in line with what other architectures are doing, and while I haven't
personally figured out how to reproduce the issues they seem believable enough
to just change it.
Fixes: 7db91e57a0ac ("RISC-V: Task implementation")
Cc: stable(a)vger.kernel.org
Signed-off-by: Palmer Dabbelt <palmerdabbelt(a)google.com>
---
I've put this on fixes as I don't see a patch from anyone on that thread, and
it seems straight-forward enough to just do it. If there's any issues I'm
happy to listen, otherwise this is going up later this week.
---
arch/riscv/include/asm/thread_info.h | 4 ++++
1 file changed, 4 insertions(+)
diff --git a/arch/riscv/include/asm/thread_info.h b/arch/riscv/include/asm/thread_info.h
index 1dd12a0cbb2b..2026076b1d30 100644
--- a/arch/riscv/include/asm/thread_info.h
+++ b/arch/riscv/include/asm/thread_info.h
@@ -12,7 +12,11 @@
#include <linux/const.h>
/* thread information allocation */
+#if defined(CONFIG_32BIT)
#define THREAD_SIZE_ORDER (1)
+#elif defined(CONFIG_64BIT)
+#define THREAD_SIZE_ORDER (2)
+#endif
#define THREAD_SIZE (PAGE_SIZE << THREAD_SIZE_ORDER)
#ifndef __ASSEMBLY__
--
2.27.0.389.gc38d7665816-goog
From: Bas Nieuwenhuizen <bas(a)basnieuwenhuizen.nl>
Calltree:
timeline_fence_release
drm_sched_entity_wakeup
dma_fence_signal_locked
sync_timeline_signal
sw_sync_ioctl
Releasing the reference to the fence in the fence signal callback
seems reasonable to me, so this patch avoids the locking issue in
sw_sync.
d3862e44daa7 ("dma-buf/sw-sync: Fix locking around sync_timeline lists")
fixed the recursive locking issue but caused an use-after-free. Later
d3c6dd1fb30d ("dma-buf/sw_sync: Synchronize signal vs syncpt free")
fixed the use-after-free but reintroduced the recursive locking issue.
In this attempt we avoid the use-after-free still because the release
function still always locks, and outside of the locking region in the
signal function we have properly refcounted references.
We furthermore also avoid the recurive lock by making sure that either:
1) We have a properly refcounted reference, preventing the signal from
triggering the release function inside the locked region.
2) The refcount was already zero, and hence nobody will be able to trigger
the release function from the signal function.
v2: Move dma_fence_signal() into second loop in preparation to moving
the callback out of the timeline obj->lock.
Fixes: d3c6dd1fb30d ("dma-buf/sw_sync: Synchronize signal vs syncpt free")
Cc: Sumit Semwal <sumit.semwal(a)linaro.org>
Cc: Chris Wilson <chris(a)chris-wilson.co.uk>
Cc: Gustavo Padovan <gustavo(a)padovan.org>
Cc: Christian König <christian.koenig(a)amd.com>
Cc: <stable(a)vger.kernel.org>
Signed-off-by: Bas Nieuwenhuizen <bas(a)basnieuwenhuizen.nl>
Signed-off-by: Chris Wilson <chris(a)chris-wilson.co.uk>
---
drivers/dma-buf/sw_sync.c | 32 ++++++++++++++++++++++----------
1 file changed, 22 insertions(+), 10 deletions(-)
diff --git a/drivers/dma-buf/sw_sync.c b/drivers/dma-buf/sw_sync.c
index 348b3a9170fa..807c82148062 100644
--- a/drivers/dma-buf/sw_sync.c
+++ b/drivers/dma-buf/sw_sync.c
@@ -192,6 +192,7 @@ static const struct dma_fence_ops timeline_fence_ops = {
static void sync_timeline_signal(struct sync_timeline *obj, unsigned int inc)
{
struct sync_pt *pt, *next;
+ LIST_HEAD(signal);
trace_sync_timeline(obj);
@@ -203,21 +204,32 @@ static void sync_timeline_signal(struct sync_timeline *obj, unsigned int inc)
if (!timeline_fence_signaled(&pt->base))
break;
- list_del_init(&pt->link);
- rb_erase(&pt->node, &obj->pt_tree);
-
/*
- * A signal callback may release the last reference to this
- * fence, causing it to be freed. That operation has to be
- * last to avoid a use after free inside this loop, and must
- * be after we remove the fence from the timeline in order to
- * prevent deadlocking on timeline->lock inside
- * timeline_fence_release().
+ * We need to take a reference to avoid a release during
+ * signalling (which can cause a recursive lock of obj->lock).
+ * If refcount was already zero, another thread is already
+ * taking care of destroying the fence.
*/
- dma_fence_signal_locked(&pt->base);
+ if (!dma_fence_get_rcu(&pt->base))
+ continue;
+
+ list_move_tail(&pt->link, &signal);
+ rb_erase(&pt->node, &obj->pt_tree);
}
spin_unlock_irq(&obj->lock);
+
+ list_for_each_entry_safe(pt, next, &signal, link) {
+ /*
+ * This needs to be cleared before release, otherwise the
+ * timeline_fence_release function gets confused about also
+ * removing the fence from the pt_tree.
+ */
+ list_del_init(&pt->link);
+
+ dma_fence_signal(&pt->base);
+ dma_fence_put(&pt->base);
+ }
}
/**
--
2.20.1
On Tue, Jul 14, 2020 at 6:26 PM Chris Wilson <chris(a)chris-wilson.co.uk> wrote:
>
> Quoting Bas Nieuwenhuizen (2020-07-14 16:41:02)
> > Calltree:
> > timeline_fence_release
> > drm_sched_entity_wakeup
> > dma_fence_signal_locked
> > sync_timeline_signal
> > sw_sync_ioctl
> >
> > Releasing the reference to the fence in the fence signal callback
> > seems reasonable to me, so this patch avoids the locking issue in
> > sw_sync.
> >
> > d3862e44daa7 ("dma-buf/sw-sync: Fix locking around sync_timeline lists")
> > fixed the recursive locking issue but caused an use-after-free. Later
> > d3c6dd1fb30d ("dma-buf/sw_sync: Synchronize signal vs syncpt free")
> > fixed the use-after-free but reintroduced the recursive locking issue.
> >
> > In this attempt we avoid the use-after-free still because the release
> > function still always locks, and outside of the locking region in the
> > signal function we have properly refcounted references.
> >
> > We furthermore also avoid the recurive lock by making sure that either:
> >
> > 1) We have a properly refcounted reference, preventing the signal from
> > triggering the release function inside the locked region.
> > 2) The refcount was already zero, and hence nobody will be able to trigger
> > the release function from the signal function.
> >
> > Fixes: d3c6dd1fb30d ("dma-buf/sw_sync: Synchronize signal vs syncpt free")
> > Cc: Sumit Semwal <sumit.semwal(a)linaro.org>
> > Cc: Chris Wilson <chris(a)chris-wilson.co.uk>
> > Cc: Gustavo Padovan <gustavo(a)padovan.org>
> > Cc: Christian König <christian.koenig(a)amd.com>
> > Cc: <stable(a)vger.kernel.org>
> > Signed-off-by: Bas Nieuwenhuizen <bas(a)basnieuwenhuizen.nl>
> > ---
> > drivers/dma-buf/sw_sync.c | 28 ++++++++++++++++++++--------
> > 1 file changed, 20 insertions(+), 8 deletions(-)
> >
> > diff --git a/drivers/dma-buf/sw_sync.c b/drivers/dma-buf/sw_sync.c
> > index 348b3a9170fa..30a482f75d56 100644
> > --- a/drivers/dma-buf/sw_sync.c
> > +++ b/drivers/dma-buf/sw_sync.c
> > @@ -192,9 +192,12 @@ static const struct dma_fence_ops timeline_fence_ops = {
> > static void sync_timeline_signal(struct sync_timeline *obj, unsigned int inc)
> > {
> > struct sync_pt *pt, *next;
> > + struct list_head ref_list;
> >
> > trace_sync_timeline(obj);
> >
> > + INIT_LIST_HEAD(&ref_list);
> > +
> > spin_lock_irq(&obj->lock);
> >
> > obj->value += inc;
> > @@ -206,18 +209,27 @@ static void sync_timeline_signal(struct sync_timeline *obj, unsigned int inc)
> > list_del_init(&pt->link);
> > rb_erase(&pt->node, &obj->pt_tree);
> >
> > - /*
> > - * A signal callback may release the last reference to this
> > - * fence, causing it to be freed. That operation has to be
> > - * last to avoid a use after free inside this loop, and must
> > - * be after we remove the fence from the timeline in order to
> > - * prevent deadlocking on timeline->lock inside
> > - * timeline_fence_release().
> > - */
> > + /* We need to take a reference to avoid a release during
> > + * signalling (which can cause a recursive lock of obj->lock).
> > + * If refcount was already zero, another thread is already taking
> > + * care of destructing the fence, so the signal cannot release
> > + * it again and we hence will not have the recursive lock. */
>
> /*
> * Block commentary style:
> * https://www.kernel.org/doc/html/latest/process/coding-style.html#commenting
> */
>
> > + if (dma_fence_get_rcu(&pt->base))
> > + list_add_tail(&pt->link, &ref_list);
>
> Ok.
>
> > +
> > dma_fence_signal_locked(&pt->base);
> > }
> >
> > spin_unlock_irq(&obj->lock);
> > +
> > + list_for_each_entry_safe(pt, next, &ref_list, link) {
> > + /* This needs to be cleared before release, otherwise the
> > + * timeline_fence_release function gets confused about also
> > + * removing the fence from the pt_tree. */
> > + list_del_init(&pt->link);
> > +
> > + dma_fence_put(&pt->base);
> > + }
>
> How serious is the problem of one fence callback freeing another pt?
>
> Following the pattern here
>
> spin_lock(&obj->lock);
> list_for_each_entry_safe(pt, next, &obj->pt_list, link) {
> if (!timeline_fence_signaled(&pt->base))
> break;
>
> if (!dma_fence_get_rcu(&pt->base))
> continue; /* too late! */
>
> rb_erase(&pt->node, &obj->pt_tree);
> list_move_tail(&pt->link, &ref_list);
> }
> spin_unlock(&obj->lock);
>
> list_for_each_entry_safe(pt, next, &ref_list, link) {
> list_del_init(&pt->link);
> dma_fence_signal(&pt->base);
Question is what the scope should be. Using this method we only take a
reference and avoid releasing the fences we're going to signal.
However the lock is on the timeline and dma_fence_signal already takes
the lock, so if the signal ends up releasing any of the other fences
in the timeline (e.g. the fences that are later than the new value),
then we are still going to have the recursive locking issue.
One solution to that would be splitting the lock into 2 locks: 1
protecting pt_list + pt_tree and 1 protecting value & serving as the
lock for the fences. Then we can only take the list lock in the
release function and dma_fence_signal takes the value lock. However,
then you still have issues like if a callback for fence A (when called
it holds the lock of A's timeline) adds a callback to fence B of the
same timeline (requires the fence lock) we still have a recursion
locking issue.
I'm not sure it is reasonable for the last use case to work, because I
only see it working with per-fence locks, but per-fence locks are
deadlock prone due to the order of taking links not really being
fixed.
> dma_fence_put(&pt->base);
> }
>
> Marginal extra cost for signaling along the debug sw_timeline for total
> peace of mind.
> -Chris
When commit 9017dc4fbd59 ("pwm: jz4740: Enhance precision in calculation
of duty cycle") from v5.8-rc1 was backported to v5.4.x its dependency on
commit ce1f9cece057 ("pwm: jz4740: Use clocks from TCU driver") was not
noticed which made the pwm-jz4740 driver fail to build.
As ce1f9cece057 depends on still more rework, just backport a small part
of this commit to make the driver build again. (There is no dependency
on the functionality introduced in ce1f9cece057, just the rate variable
is needed.)
Signed-off-by: Uwe Kleine-König <u.kleine-koenig(a)pengutronix.de>
---
Hello,
@Paul: Can you please check this is correct? I only build-tested this
change.
Best regards
Uwe
drivers/pwm/pwm-jz4740.c | 5 +++--
1 file changed, 3 insertions(+), 2 deletions(-)
diff --git a/drivers/pwm/pwm-jz4740.c b/drivers/pwm/pwm-jz4740.c
index d0f5c69930d0..77c28313e95f 100644
--- a/drivers/pwm/pwm-jz4740.c
+++ b/drivers/pwm/pwm-jz4740.c
@@ -92,11 +92,12 @@ static int jz4740_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm,
{
struct jz4740_pwm_chip *jz4740 = to_jz4740(pwm->chip);
unsigned long long tmp;
- unsigned long period, duty;
+ unsigned long rate, period, duty;
unsigned int prescaler = 0;
uint16_t ctrl;
- tmp = (unsigned long long)clk_get_rate(jz4740->clk) * state->period;
+ rate = clk_get_rate(jz4740->clk);
+ tmp = rate * state->period;
do_div(tmp, 1000000000);
period = tmp;
--
2.27.0
Commit 33ae787b74fc ("serial: tegra: add support to ignore read") added
support for dropping input in case CREAD isn't set, but for PIO the
ignore_status_mask wasn't checked until after the character had been
put in the receive buffer.
Note that the NULL tty-port test is bogus and will be removed by a
follow-on patch.
Fixes: 33ae787b74fc ("serial: tegra: add support to ignore read")
Cc: stable <stable(a)vger.kernel.org> # 5.4
Cc: Shardar Shariff Md <smohammed(a)nvidia.com>
Cc: Krishna Yarlagadda <kyarlagadda(a)nvidia.com>
Signed-off-by: Johan Hovold <johan(a)kernel.org>
---
drivers/tty/serial/serial-tegra.c | 7 +++++--
1 file changed, 5 insertions(+), 2 deletions(-)
diff --git a/drivers/tty/serial/serial-tegra.c b/drivers/tty/serial/serial-tegra.c
index 8de8bac9c6c7..b3bbee6b6702 100644
--- a/drivers/tty/serial/serial-tegra.c
+++ b/drivers/tty/serial/serial-tegra.c
@@ -653,11 +653,14 @@ static void tegra_uart_handle_rx_pio(struct tegra_uart_port *tup,
ch = (unsigned char) tegra_uart_read(tup, UART_RX);
tup->uport.icount.rx++;
- if (!uart_handle_sysrq_char(&tup->uport, ch) && tty)
- tty_insert_flip_char(tty, ch, flag);
+ if (uart_handle_sysrq_char(&tup->uport, ch))
+ continue;
if (tup->uport.ignore_status_mask & UART_LSR_DR)
continue;
+
+ if (tty)
+ tty_insert_flip_char(tty, ch, flag);
} while (1);
}
--
2.26.2
Calltree:
timeline_fence_release
drm_sched_entity_wakeup
dma_fence_signal_locked
sync_timeline_signal
sw_sync_ioctl
Releasing the reference to the fence in the fence signal callback
seems reasonable to me, so this patch avoids the locking issue in
sw_sync.
d3862e44daa7 ("dma-buf/sw-sync: Fix locking around sync_timeline lists")
fixed the recursive locking issue but caused an use-after-free. Later
d3c6dd1fb30d ("dma-buf/sw_sync: Synchronize signal vs syncpt free")
fixed the use-after-free but reintroduced the recursive locking issue.
In this attempt we avoid the use-after-free still because the release
function still always locks, and outside of the locking region in the
signal function we have properly refcounted references.
We furthermore also avoid the recurive lock by making sure that either:
1) We have a properly refcounted reference, preventing the signal from
triggering the release function inside the locked region.
2) The refcount was already zero, and hence nobody will be able to trigger
the release function from the signal function.
Fixes: d3c6dd1fb30d ("dma-buf/sw_sync: Synchronize signal vs syncpt free")
Cc: Sumit Semwal <sumit.semwal(a)linaro.org>
Cc: Chris Wilson <chris(a)chris-wilson.co.uk>
Cc: Gustavo Padovan <gustavo(a)padovan.org>
Cc: Christian König <christian.koenig(a)amd.com>
Cc: <stable(a)vger.kernel.org>
Signed-off-by: Bas Nieuwenhuizen <bas(a)basnieuwenhuizen.nl>
---
drivers/dma-buf/sw_sync.c | 28 ++++++++++++++++++++--------
1 file changed, 20 insertions(+), 8 deletions(-)
diff --git a/drivers/dma-buf/sw_sync.c b/drivers/dma-buf/sw_sync.c
index 348b3a9170fa..30a482f75d56 100644
--- a/drivers/dma-buf/sw_sync.c
+++ b/drivers/dma-buf/sw_sync.c
@@ -192,9 +192,12 @@ static const struct dma_fence_ops timeline_fence_ops = {
static void sync_timeline_signal(struct sync_timeline *obj, unsigned int inc)
{
struct sync_pt *pt, *next;
+ struct list_head ref_list;
trace_sync_timeline(obj);
+ INIT_LIST_HEAD(&ref_list);
+
spin_lock_irq(&obj->lock);
obj->value += inc;
@@ -206,18 +209,27 @@ static void sync_timeline_signal(struct sync_timeline *obj, unsigned int inc)
list_del_init(&pt->link);
rb_erase(&pt->node, &obj->pt_tree);
- /*
- * A signal callback may release the last reference to this
- * fence, causing it to be freed. That operation has to be
- * last to avoid a use after free inside this loop, and must
- * be after we remove the fence from the timeline in order to
- * prevent deadlocking on timeline->lock inside
- * timeline_fence_release().
- */
+ /* We need to take a reference to avoid a release during
+ * signalling (which can cause a recursive lock of obj->lock).
+ * If refcount was already zero, another thread is already taking
+ * care of destructing the fence, so the signal cannot release
+ * it again and we hence will not have the recursive lock. */
+ if (dma_fence_get_rcu(&pt->base))
+ list_add_tail(&pt->link, &ref_list);
+
dma_fence_signal_locked(&pt->base);
}
spin_unlock_irq(&obj->lock);
+
+ list_for_each_entry_safe(pt, next, &ref_list, link) {
+ /* This needs to be cleared before release, otherwise the
+ * timeline_fence_release function gets confused about also
+ * removing the fence from the pt_tree. */
+ list_del_init(&pt->link);
+
+ dma_fence_put(&pt->base);
+ }
}
/**
--
2.27.0
When "ovl_is_inuse" true case, trap inode reference not put.
plus adding the comment explaining sequence of
ovl_is_inuse after ovl_setup_trap.
Fixes: 0be0bfd2de9d ("ovl: fix regression caused by overlapping layers..")
Cc: <stable(a)vger.kernel.org> # v4.19+
Reviewed-by: Amir Goldstein <amir73il(a)gmail.com>
Signed-off-by: youngjun <her0gyugyu(a)gmail.com>
---
fs/overlayfs/super.c | 10 +++++++++-
1 file changed, 9 insertions(+), 1 deletion(-)
diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c
index 91476bc422f9..3097142b1e23 100644
--- a/fs/overlayfs/super.c
+++ b/fs/overlayfs/super.c
@@ -1493,14 +1493,22 @@ static int ovl_get_layers(struct super_block *sb, struct ovl_fs *ofs,
if (err < 0)
goto out;
+ /*
+ * Check if lower root conflicts with this overlay layers before checking
+ * if it is in-use as upperdir/workdir of "another" mount, because we do
+ * not bother to check in ovl_is_inuse() if the upperdir/workdir is in fact
+ * in-use by our upperdir/workdir.
+ */
err = ovl_setup_trap(sb, stack[i].dentry, &trap, "lowerdir");
if (err)
goto out;
if (ovl_is_inuse(stack[i].dentry)) {
err = ovl_report_in_use(ofs, "lowerdir");
- if (err)
+ if (err) {
+ iput(trap);
goto out;
+ }
}
mnt = clone_private_mount(&stack[i]);
--
2.17.1
Again, Great thanks Amir. I revise my patch through your kind guidance.
I hit this FTBFS earlier today while trying to build the LT 4.19.132
kernel from source:
https://lore.kernel.org/patchwork/patch/960281/
The "quick hack" patch mentioned at the bottom of the thread gets it
to compile. Is this the correct solution, or is there a better fix? As
it stands, tools/perf doesn't seem to compile on 4.19.132.
The patch below does not apply to the 5.7-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 ed710a6ed797430026aa5116dd0ab22378798b69 Mon Sep 17 00:00:00 2001
From: Ralph Campbell <rcampbell(a)nvidia.com>
Date: Fri, 26 Jun 2020 14:03:37 -0700
Subject: [PATCH] drm/nouveau/nouveau: fix page fault on device private memory
If system memory is migrated to device private memory and no GPU MMU
page table entry exists, the GPU will fault and call hmm_range_fault()
to get the PFN for the page. Since the .dev_private_owner pointer in
struct hmm_range is not set, hmm_range_fault returns an error which
results in the GPU program stopping with a fatal fault.
Fix this by setting .dev_private_owner appropriately.
Fixes: 08ddddda667b ("mm/hmm: check the device private page owner in hmm_range_fault()")
Cc: stable(a)vger.kernel.org
Signed-off-by: Ralph Campbell <rcampbell(a)nvidia.com>
Reviewed-by: Jason Gunthorpe <jgg(a)mellanox.com>
Signed-off-by: Ben Skeggs <bskeggs(a)redhat.com>
diff --git a/drivers/gpu/drm/nouveau/nouveau_svm.c b/drivers/gpu/drm/nouveau/nouveau_svm.c
index ba9f9359c30e..6586d9d39874 100644
--- a/drivers/gpu/drm/nouveau/nouveau_svm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_svm.c
@@ -562,6 +562,7 @@ static int nouveau_range_fault(struct nouveau_svmm *svmm,
.end = notifier->notifier.interval_tree.last + 1,
.pfn_flags_mask = HMM_PFN_REQ_FAULT | HMM_PFN_REQ_WRITE,
.hmm_pfns = hmm_pfns,
+ .dev_private_owner = drm->dev,
};
struct mm_struct *mm = notifier->notifier.mm;
int ret;
The patch below does not apply to the 5.4-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 3b2e973dff59d88bee1d814ddf8762a24fc02b60 Mon Sep 17 00:00:00 2001
From: Aaron Ma <aaron.ma(a)canonical.com>
Date: Wed, 8 Jul 2020 04:16:22 -0400
Subject: [PATCH] drm/amd/display: add dmcub check on RENOIR
RENOIR loads dmub fw not dmcu, check dmcu only will prevent loading iram,
it breaks backlight control.
Bug: https://bugzilla.kernel.org/show_bug.cgi?id=208277
Acked-by: Alex Deucher <alexander.deucher(a)amd.com>
Reviewed-by: Nicholas Kazlauskas <nicholas.kazlauskas(a)amd.com>
Signed-off-by: Aaron Ma <aaron.ma(a)canonical.com>
Signed-off-by: Alex Deucher <alexander.deucher(a)amd.com>
Cc: stable(a)vger.kernel.org
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index 10ac8076d4f2..db5e0bb0d935 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -1358,7 +1358,7 @@ static int dm_late_init(void *handle)
struct dmcu *dmcu = NULL;
bool ret;
- if (!adev->dm.fw_dmcu)
+ if (!adev->dm.fw_dmcu && !adev->dm.dmub_fw)
return detect_mst_link_for_all_connectors(adev->ddev);
dmcu = adev->dm.dc->res_pool->dmcu;
The patch below does not apply to the 5.7-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 3b2e973dff59d88bee1d814ddf8762a24fc02b60 Mon Sep 17 00:00:00 2001
From: Aaron Ma <aaron.ma(a)canonical.com>
Date: Wed, 8 Jul 2020 04:16:22 -0400
Subject: [PATCH] drm/amd/display: add dmcub check on RENOIR
RENOIR loads dmub fw not dmcu, check dmcu only will prevent loading iram,
it breaks backlight control.
Bug: https://bugzilla.kernel.org/show_bug.cgi?id=208277
Acked-by: Alex Deucher <alexander.deucher(a)amd.com>
Reviewed-by: Nicholas Kazlauskas <nicholas.kazlauskas(a)amd.com>
Signed-off-by: Aaron Ma <aaron.ma(a)canonical.com>
Signed-off-by: Alex Deucher <alexander.deucher(a)amd.com>
Cc: stable(a)vger.kernel.org
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index 10ac8076d4f2..db5e0bb0d935 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -1358,7 +1358,7 @@ static int dm_late_init(void *handle)
struct dmcu *dmcu = NULL;
bool ret;
- if (!adev->dm.fw_dmcu)
+ if (!adev->dm.fw_dmcu && !adev->dm.dmub_fw)
return detect_mst_link_for_all_connectors(adev->ddev);
dmcu = adev->dm.dc->res_pool->dmcu;
The patch below does not apply to the 5.4-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 85067747cf9888249fa11fa49ef75af5192d3988 Mon Sep 17 00:00:00 2001
From: Ming Lei <ming.lei(a)redhat.com>
Date: Wed, 24 Jun 2020 16:00:58 -0400
Subject: [PATCH] dm: do not use waitqueue for request-based DM
Given request-based DM now uses blk-mq's blk_mq_queue_inflight() to
determine if outstanding IO has completed (and DM has no control over
the blk-mq state machine used to track outstanding IO) it is unsafe to
wakeup waiter (dm_wait_for_completion) before blk-mq has cleared a
request's state bits (e.g. MQ_RQ_IN_FLIGHT or MQ_RQ_COMPLETE). As
such dm_wait_for_completion() could be left to wait indefinitely if no
other requests complete.
Fix this by eliminating request-based DM's use of waitqueue to wait
for blk-mq requests to complete in dm_wait_for_completion.
Signed-off-by: Ming Lei <ming.lei(a)redhat.com>
Depends-on: 3c94d83cb3526 ("blk-mq: change blk_mq_queue_busy() to blk_mq_queue_inflight()")
Cc: stable(a)vger.kernel.org
Signed-off-by: Mike Snitzer <snitzer(a)redhat.com>
diff --git a/drivers/md/dm-rq.c b/drivers/md/dm-rq.c
index f60c02512121..85e0daabad49 100644
--- a/drivers/md/dm-rq.c
+++ b/drivers/md/dm-rq.c
@@ -146,10 +146,6 @@ static void rq_end_stats(struct mapped_device *md, struct request *orig)
*/
static void rq_completed(struct mapped_device *md)
{
- /* nudge anyone waiting on suspend queue */
- if (unlikely(wq_has_sleeper(&md->wait)))
- wake_up(&md->wait);
-
/*
* dm_put() must be at the end of this function. See the comment above
*/
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index e6807792fec8..446aff589732 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -654,28 +654,6 @@ static void free_tio(struct dm_target_io *tio)
bio_put(&tio->clone);
}
-static bool md_in_flight_bios(struct mapped_device *md)
-{
- int cpu;
- struct hd_struct *part = &dm_disk(md)->part0;
- long sum = 0;
-
- for_each_possible_cpu(cpu) {
- sum += part_stat_local_read_cpu(part, in_flight[0], cpu);
- sum += part_stat_local_read_cpu(part, in_flight[1], cpu);
- }
-
- return sum != 0;
-}
-
-static bool md_in_flight(struct mapped_device *md)
-{
- if (queue_is_mq(md->queue))
- return blk_mq_queue_inflight(md->queue);
- else
- return md_in_flight_bios(md);
-}
-
u64 dm_start_time_ns_from_clone(struct bio *bio)
{
struct dm_target_io *tio = container_of(bio, struct dm_target_io, clone);
@@ -2470,15 +2448,29 @@ void dm_put(struct mapped_device *md)
}
EXPORT_SYMBOL_GPL(dm_put);
-static int dm_wait_for_completion(struct mapped_device *md, long task_state)
+static bool md_in_flight_bios(struct mapped_device *md)
+{
+ int cpu;
+ struct hd_struct *part = &dm_disk(md)->part0;
+ long sum = 0;
+
+ for_each_possible_cpu(cpu) {
+ sum += part_stat_local_read_cpu(part, in_flight[0], cpu);
+ sum += part_stat_local_read_cpu(part, in_flight[1], cpu);
+ }
+
+ return sum != 0;
+}
+
+static int dm_wait_for_bios_completion(struct mapped_device *md, long task_state)
{
int r = 0;
DEFINE_WAIT(wait);
- while (1) {
+ while (true) {
prepare_to_wait(&md->wait, &wait, task_state);
- if (!md_in_flight(md))
+ if (!md_in_flight_bios(md))
break;
if (signal_pending_state(task_state, current)) {
@@ -2493,6 +2485,28 @@ static int dm_wait_for_completion(struct mapped_device *md, long task_state)
return r;
}
+static int dm_wait_for_completion(struct mapped_device *md, long task_state)
+{
+ int r = 0;
+
+ if (!queue_is_mq(md->queue))
+ return dm_wait_for_bios_completion(md, task_state);
+
+ while (true) {
+ if (!blk_mq_queue_inflight(md->queue))
+ break;
+
+ if (signal_pending_state(task_state, current)) {
+ r = -EINTR;
+ break;
+ }
+
+ msleep(5);
+ }
+
+ return r;
+}
+
/*
* Process the deferred bios
*/
The patch below does not apply to the 5.7-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 85067747cf9888249fa11fa49ef75af5192d3988 Mon Sep 17 00:00:00 2001
From: Ming Lei <ming.lei(a)redhat.com>
Date: Wed, 24 Jun 2020 16:00:58 -0400
Subject: [PATCH] dm: do not use waitqueue for request-based DM
Given request-based DM now uses blk-mq's blk_mq_queue_inflight() to
determine if outstanding IO has completed (and DM has no control over
the blk-mq state machine used to track outstanding IO) it is unsafe to
wakeup waiter (dm_wait_for_completion) before blk-mq has cleared a
request's state bits (e.g. MQ_RQ_IN_FLIGHT or MQ_RQ_COMPLETE). As
such dm_wait_for_completion() could be left to wait indefinitely if no
other requests complete.
Fix this by eliminating request-based DM's use of waitqueue to wait
for blk-mq requests to complete in dm_wait_for_completion.
Signed-off-by: Ming Lei <ming.lei(a)redhat.com>
Depends-on: 3c94d83cb3526 ("blk-mq: change blk_mq_queue_busy() to blk_mq_queue_inflight()")
Cc: stable(a)vger.kernel.org
Signed-off-by: Mike Snitzer <snitzer(a)redhat.com>
diff --git a/drivers/md/dm-rq.c b/drivers/md/dm-rq.c
index f60c02512121..85e0daabad49 100644
--- a/drivers/md/dm-rq.c
+++ b/drivers/md/dm-rq.c
@@ -146,10 +146,6 @@ static void rq_end_stats(struct mapped_device *md, struct request *orig)
*/
static void rq_completed(struct mapped_device *md)
{
- /* nudge anyone waiting on suspend queue */
- if (unlikely(wq_has_sleeper(&md->wait)))
- wake_up(&md->wait);
-
/*
* dm_put() must be at the end of this function. See the comment above
*/
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index e6807792fec8..446aff589732 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -654,28 +654,6 @@ static void free_tio(struct dm_target_io *tio)
bio_put(&tio->clone);
}
-static bool md_in_flight_bios(struct mapped_device *md)
-{
- int cpu;
- struct hd_struct *part = &dm_disk(md)->part0;
- long sum = 0;
-
- for_each_possible_cpu(cpu) {
- sum += part_stat_local_read_cpu(part, in_flight[0], cpu);
- sum += part_stat_local_read_cpu(part, in_flight[1], cpu);
- }
-
- return sum != 0;
-}
-
-static bool md_in_flight(struct mapped_device *md)
-{
- if (queue_is_mq(md->queue))
- return blk_mq_queue_inflight(md->queue);
- else
- return md_in_flight_bios(md);
-}
-
u64 dm_start_time_ns_from_clone(struct bio *bio)
{
struct dm_target_io *tio = container_of(bio, struct dm_target_io, clone);
@@ -2470,15 +2448,29 @@ void dm_put(struct mapped_device *md)
}
EXPORT_SYMBOL_GPL(dm_put);
-static int dm_wait_for_completion(struct mapped_device *md, long task_state)
+static bool md_in_flight_bios(struct mapped_device *md)
+{
+ int cpu;
+ struct hd_struct *part = &dm_disk(md)->part0;
+ long sum = 0;
+
+ for_each_possible_cpu(cpu) {
+ sum += part_stat_local_read_cpu(part, in_flight[0], cpu);
+ sum += part_stat_local_read_cpu(part, in_flight[1], cpu);
+ }
+
+ return sum != 0;
+}
+
+static int dm_wait_for_bios_completion(struct mapped_device *md, long task_state)
{
int r = 0;
DEFINE_WAIT(wait);
- while (1) {
+ while (true) {
prepare_to_wait(&md->wait, &wait, task_state);
- if (!md_in_flight(md))
+ if (!md_in_flight_bios(md))
break;
if (signal_pending_state(task_state, current)) {
@@ -2493,6 +2485,28 @@ static int dm_wait_for_completion(struct mapped_device *md, long task_state)
return r;
}
+static int dm_wait_for_completion(struct mapped_device *md, long task_state)
+{
+ int r = 0;
+
+ if (!queue_is_mq(md->queue))
+ return dm_wait_for_bios_completion(md, task_state);
+
+ while (true) {
+ if (!blk_mq_queue_inflight(md->queue))
+ break;
+
+ if (signal_pending_state(task_state, current)) {
+ r = -EINTR;
+ break;
+ }
+
+ msleep(5);
+ }
+
+ return r;
+}
+
/*
* Process the deferred bios
*/
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 45c11a927606c612e4898a9484867b71318699f6 Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede(a)redhat.com>
Date: Sat, 6 Jun 2020 11:31:50 +0200
Subject: [PATCH] pinctrl: baytrail: Fix pin being driven low for a while on
gpiod_get(..., GPIOD_OUT_HIGH)
The pins on the Bay Trail SoC have separate input-buffer and output-buffer
enable bits and a read of the level bit of the value register will always
return the value from the input-buffer.
The BIOS of a device may configure a pin in output-only mode, only enabling
the output buffer, and write 1 to the level bit to drive the pin high.
This 1 written to the level bit will be stored inside the data-latch of the
output buffer.
But a subsequent read of the value register will return 0 for the level bit
because the input-buffer is disabled. This causes a read-modify-write as
done by byt_gpio_set_direction() to write 0 to the level bit, driving the
pin low!
Before this commit byt_gpio_direction_output() relied on
pinctrl_gpio_direction_output() to set the direction, followed by a call
to byt_gpio_set() to apply the selected value. This causes the pin to
go low between the pinctrl_gpio_direction_output() and byt_gpio_set()
calls.
Change byt_gpio_direction_output() to directly make the register
modifications itself instead. Replacing the 2 subsequent writes to the
value register with a single write.
Note that the pinctrl code does not keep track internally of the direction,
so not going through pinctrl_gpio_direction_output() is not an issue.
This issue was noticed on a Trekstor SurfTab Twin 10.1. When the panel is
already on at boot (no external monitor connected), then the i915 driver
does a gpiod_get(..., GPIOD_OUT_HIGH) for the panel-enable GPIO. The
temporarily going low of that GPIO was causing the panel to reset itself
after which it would not show an image until it was turned off and back on
again (until a full modeset was done on it). This commit fixes this.
This commit also updates the byt_gpio_direction_input() to use direct
register accesses instead of going through pinctrl_gpio_direction_input(),
to keep it consistent with byt_gpio_direction_output().
Note for backporting, this commit depends on:
commit e2b74419e5cc ("pinctrl: baytrail: Replace WARN with dev_info_once
when setting direct-irq pin to output")
Cc: stable(a)vger.kernel.org
Fixes: 86e3ef812fe3 ("pinctrl: baytrail: Update gpio chip operations")
Signed-off-by: Hans de Goede <hdegoede(a)redhat.com>
Acked-by: Mika Westerberg <mika.westerberg(a)linux.intel.com>
Signed-off-by: Andy Shevchenko <andriy.shevchenko(a)linux.intel.com>
diff --git a/drivers/pinctrl/intel/pinctrl-baytrail.c b/drivers/pinctrl/intel/pinctrl-baytrail.c
index 0ff7c55173da..615174a9d1e0 100644
--- a/drivers/pinctrl/intel/pinctrl-baytrail.c
+++ b/drivers/pinctrl/intel/pinctrl-baytrail.c
@@ -800,6 +800,21 @@ static void byt_gpio_disable_free(struct pinctrl_dev *pctl_dev,
pm_runtime_put(vg->dev);
}
+static void byt_gpio_direct_irq_check(struct intel_pinctrl *vg,
+ unsigned int offset)
+{
+ void __iomem *conf_reg = byt_gpio_reg(vg, offset, BYT_CONF0_REG);
+
+ /*
+ * Before making any direction modifications, do a check if gpio is set
+ * for direct IRQ. On Bay Trail, setting GPIO to output does not make
+ * sense, so let's at least inform the caller before they shoot
+ * themselves in the foot.
+ */
+ if (readl(conf_reg) & BYT_DIRECT_IRQ_EN)
+ dev_info_once(vg->dev, "Potential Error: Setting GPIO with direct_irq_en to output");
+}
+
static int byt_gpio_set_direction(struct pinctrl_dev *pctl_dev,
struct pinctrl_gpio_range *range,
unsigned int offset,
@@ -807,7 +822,6 @@ static int byt_gpio_set_direction(struct pinctrl_dev *pctl_dev,
{
struct intel_pinctrl *vg = pinctrl_dev_get_drvdata(pctl_dev);
void __iomem *val_reg = byt_gpio_reg(vg, offset, BYT_VAL_REG);
- void __iomem *conf_reg = byt_gpio_reg(vg, offset, BYT_CONF0_REG);
unsigned long flags;
u32 value;
@@ -817,14 +831,8 @@ static int byt_gpio_set_direction(struct pinctrl_dev *pctl_dev,
value &= ~BYT_DIR_MASK;
if (input)
value |= BYT_OUTPUT_EN;
- else if (readl(conf_reg) & BYT_DIRECT_IRQ_EN)
- /*
- * Before making any direction modifications, do a check if gpio
- * is set for direct IRQ. On baytrail, setting GPIO to output
- * does not make sense, so let's at least inform the caller before
- * they shoot themselves in the foot.
- */
- dev_info_once(vg->dev, "Potential Error: Setting GPIO with direct_irq_en to output");
+ else
+ byt_gpio_direct_irq_check(vg, offset);
writel(value, val_reg);
@@ -1165,19 +1173,50 @@ static int byt_gpio_get_direction(struct gpio_chip *chip, unsigned int offset)
static int byt_gpio_direction_input(struct gpio_chip *chip, unsigned int offset)
{
- return pinctrl_gpio_direction_input(chip->base + offset);
+ struct intel_pinctrl *vg = gpiochip_get_data(chip);
+ void __iomem *val_reg = byt_gpio_reg(vg, offset, BYT_VAL_REG);
+ unsigned long flags;
+ u32 reg;
+
+ raw_spin_lock_irqsave(&byt_lock, flags);
+
+ reg = readl(val_reg);
+ reg &= ~BYT_DIR_MASK;
+ reg |= BYT_OUTPUT_EN;
+ writel(reg, val_reg);
+
+ raw_spin_unlock_irqrestore(&byt_lock, flags);
+ return 0;
}
+/*
+ * Note despite the temptation this MUST NOT be converted into a call to
+ * pinctrl_gpio_direction_output() + byt_gpio_set() that does not work this
+ * MUST be done as a single BYT_VAL_REG register write.
+ * See the commit message of the commit adding this comment for details.
+ */
static int byt_gpio_direction_output(struct gpio_chip *chip,
unsigned int offset, int value)
{
- int ret = pinctrl_gpio_direction_output(chip->base + offset);
+ struct intel_pinctrl *vg = gpiochip_get_data(chip);
+ void __iomem *val_reg = byt_gpio_reg(vg, offset, BYT_VAL_REG);
+ unsigned long flags;
+ u32 reg;
- if (ret)
- return ret;
+ raw_spin_lock_irqsave(&byt_lock, flags);
+
+ byt_gpio_direct_irq_check(vg, offset);
- byt_gpio_set(chip, offset, value);
+ reg = readl(val_reg);
+ reg &= ~BYT_DIR_MASK;
+ if (value)
+ reg |= BYT_LEVEL;
+ else
+ reg &= ~BYT_LEVEL;
+ writel(reg, val_reg);
+
+ raw_spin_unlock_irqrestore(&byt_lock, flags);
return 0;
}
The patch below does not apply to the 4.14-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 45c11a927606c612e4898a9484867b71318699f6 Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede(a)redhat.com>
Date: Sat, 6 Jun 2020 11:31:50 +0200
Subject: [PATCH] pinctrl: baytrail: Fix pin being driven low for a while on
gpiod_get(..., GPIOD_OUT_HIGH)
The pins on the Bay Trail SoC have separate input-buffer and output-buffer
enable bits and a read of the level bit of the value register will always
return the value from the input-buffer.
The BIOS of a device may configure a pin in output-only mode, only enabling
the output buffer, and write 1 to the level bit to drive the pin high.
This 1 written to the level bit will be stored inside the data-latch of the
output buffer.
But a subsequent read of the value register will return 0 for the level bit
because the input-buffer is disabled. This causes a read-modify-write as
done by byt_gpio_set_direction() to write 0 to the level bit, driving the
pin low!
Before this commit byt_gpio_direction_output() relied on
pinctrl_gpio_direction_output() to set the direction, followed by a call
to byt_gpio_set() to apply the selected value. This causes the pin to
go low between the pinctrl_gpio_direction_output() and byt_gpio_set()
calls.
Change byt_gpio_direction_output() to directly make the register
modifications itself instead. Replacing the 2 subsequent writes to the
value register with a single write.
Note that the pinctrl code does not keep track internally of the direction,
so not going through pinctrl_gpio_direction_output() is not an issue.
This issue was noticed on a Trekstor SurfTab Twin 10.1. When the panel is
already on at boot (no external monitor connected), then the i915 driver
does a gpiod_get(..., GPIOD_OUT_HIGH) for the panel-enable GPIO. The
temporarily going low of that GPIO was causing the panel to reset itself
after which it would not show an image until it was turned off and back on
again (until a full modeset was done on it). This commit fixes this.
This commit also updates the byt_gpio_direction_input() to use direct
register accesses instead of going through pinctrl_gpio_direction_input(),
to keep it consistent with byt_gpio_direction_output().
Note for backporting, this commit depends on:
commit e2b74419e5cc ("pinctrl: baytrail: Replace WARN with dev_info_once
when setting direct-irq pin to output")
Cc: stable(a)vger.kernel.org
Fixes: 86e3ef812fe3 ("pinctrl: baytrail: Update gpio chip operations")
Signed-off-by: Hans de Goede <hdegoede(a)redhat.com>
Acked-by: Mika Westerberg <mika.westerberg(a)linux.intel.com>
Signed-off-by: Andy Shevchenko <andriy.shevchenko(a)linux.intel.com>
diff --git a/drivers/pinctrl/intel/pinctrl-baytrail.c b/drivers/pinctrl/intel/pinctrl-baytrail.c
index 0ff7c55173da..615174a9d1e0 100644
--- a/drivers/pinctrl/intel/pinctrl-baytrail.c
+++ b/drivers/pinctrl/intel/pinctrl-baytrail.c
@@ -800,6 +800,21 @@ static void byt_gpio_disable_free(struct pinctrl_dev *pctl_dev,
pm_runtime_put(vg->dev);
}
+static void byt_gpio_direct_irq_check(struct intel_pinctrl *vg,
+ unsigned int offset)
+{
+ void __iomem *conf_reg = byt_gpio_reg(vg, offset, BYT_CONF0_REG);
+
+ /*
+ * Before making any direction modifications, do a check if gpio is set
+ * for direct IRQ. On Bay Trail, setting GPIO to output does not make
+ * sense, so let's at least inform the caller before they shoot
+ * themselves in the foot.
+ */
+ if (readl(conf_reg) & BYT_DIRECT_IRQ_EN)
+ dev_info_once(vg->dev, "Potential Error: Setting GPIO with direct_irq_en to output");
+}
+
static int byt_gpio_set_direction(struct pinctrl_dev *pctl_dev,
struct pinctrl_gpio_range *range,
unsigned int offset,
@@ -807,7 +822,6 @@ static int byt_gpio_set_direction(struct pinctrl_dev *pctl_dev,
{
struct intel_pinctrl *vg = pinctrl_dev_get_drvdata(pctl_dev);
void __iomem *val_reg = byt_gpio_reg(vg, offset, BYT_VAL_REG);
- void __iomem *conf_reg = byt_gpio_reg(vg, offset, BYT_CONF0_REG);
unsigned long flags;
u32 value;
@@ -817,14 +831,8 @@ static int byt_gpio_set_direction(struct pinctrl_dev *pctl_dev,
value &= ~BYT_DIR_MASK;
if (input)
value |= BYT_OUTPUT_EN;
- else if (readl(conf_reg) & BYT_DIRECT_IRQ_EN)
- /*
- * Before making any direction modifications, do a check if gpio
- * is set for direct IRQ. On baytrail, setting GPIO to output
- * does not make sense, so let's at least inform the caller before
- * they shoot themselves in the foot.
- */
- dev_info_once(vg->dev, "Potential Error: Setting GPIO with direct_irq_en to output");
+ else
+ byt_gpio_direct_irq_check(vg, offset);
writel(value, val_reg);
@@ -1165,19 +1173,50 @@ static int byt_gpio_get_direction(struct gpio_chip *chip, unsigned int offset)
static int byt_gpio_direction_input(struct gpio_chip *chip, unsigned int offset)
{
- return pinctrl_gpio_direction_input(chip->base + offset);
+ struct intel_pinctrl *vg = gpiochip_get_data(chip);
+ void __iomem *val_reg = byt_gpio_reg(vg, offset, BYT_VAL_REG);
+ unsigned long flags;
+ u32 reg;
+
+ raw_spin_lock_irqsave(&byt_lock, flags);
+
+ reg = readl(val_reg);
+ reg &= ~BYT_DIR_MASK;
+ reg |= BYT_OUTPUT_EN;
+ writel(reg, val_reg);
+
+ raw_spin_unlock_irqrestore(&byt_lock, flags);
+ return 0;
}
+/*
+ * Note despite the temptation this MUST NOT be converted into a call to
+ * pinctrl_gpio_direction_output() + byt_gpio_set() that does not work this
+ * MUST be done as a single BYT_VAL_REG register write.
+ * See the commit message of the commit adding this comment for details.
+ */
static int byt_gpio_direction_output(struct gpio_chip *chip,
unsigned int offset, int value)
{
- int ret = pinctrl_gpio_direction_output(chip->base + offset);
+ struct intel_pinctrl *vg = gpiochip_get_data(chip);
+ void __iomem *val_reg = byt_gpio_reg(vg, offset, BYT_VAL_REG);
+ unsigned long flags;
+ u32 reg;
- if (ret)
- return ret;
+ raw_spin_lock_irqsave(&byt_lock, flags);
+
+ byt_gpio_direct_irq_check(vg, offset);
- byt_gpio_set(chip, offset, value);
+ reg = readl(val_reg);
+ reg &= ~BYT_DIR_MASK;
+ if (value)
+ reg |= BYT_LEVEL;
+ else
+ reg &= ~BYT_LEVEL;
+ writel(reg, val_reg);
+
+ raw_spin_unlock_irqrestore(&byt_lock, flags);
return 0;
}
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>.
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
>From 45c11a927606c612e4898a9484867b71318699f6 Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede(a)redhat.com>
Date: Sat, 6 Jun 2020 11:31:50 +0200
Subject: [PATCH] pinctrl: baytrail: Fix pin being driven low for a while on
gpiod_get(..., GPIOD_OUT_HIGH)
The pins on the Bay Trail SoC have separate input-buffer and output-buffer
enable bits and a read of the level bit of the value register will always
return the value from the input-buffer.
The BIOS of a device may configure a pin in output-only mode, only enabling
the output buffer, and write 1 to the level bit to drive the pin high.
This 1 written to the level bit will be stored inside the data-latch of the
output buffer.
But a subsequent read of the value register will return 0 for the level bit
because the input-buffer is disabled. This causes a read-modify-write as
done by byt_gpio_set_direction() to write 0 to the level bit, driving the
pin low!
Before this commit byt_gpio_direction_output() relied on
pinctrl_gpio_direction_output() to set the direction, followed by a call
to byt_gpio_set() to apply the selected value. This causes the pin to
go low between the pinctrl_gpio_direction_output() and byt_gpio_set()
calls.
Change byt_gpio_direction_output() to directly make the register
modifications itself instead. Replacing the 2 subsequent writes to the
value register with a single write.
Note that the pinctrl code does not keep track internally of the direction,
so not going through pinctrl_gpio_direction_output() is not an issue.
This issue was noticed on a Trekstor SurfTab Twin 10.1. When the panel is
already on at boot (no external monitor connected), then the i915 driver
does a gpiod_get(..., GPIOD_OUT_HIGH) for the panel-enable GPIO. The
temporarily going low of that GPIO was causing the panel to reset itself
after which it would not show an image until it was turned off and back on
again (until a full modeset was done on it). This commit fixes this.
This commit also updates the byt_gpio_direction_input() to use direct
register accesses instead of going through pinctrl_gpio_direction_input(),
to keep it consistent with byt_gpio_direction_output().
Note for backporting, this commit depends on:
commit e2b74419e5cc ("pinctrl: baytrail: Replace WARN with dev_info_once
when setting direct-irq pin to output")
Cc: stable(a)vger.kernel.org
Fixes: 86e3ef812fe3 ("pinctrl: baytrail: Update gpio chip operations")
Signed-off-by: Hans de Goede <hdegoede(a)redhat.com>
Acked-by: Mika Westerberg <mika.westerberg(a)linux.intel.com>
Signed-off-by: Andy Shevchenko <andriy.shevchenko(a)linux.intel.com>
diff --git a/drivers/pinctrl/intel/pinctrl-baytrail.c b/drivers/pinctrl/intel/pinctrl-baytrail.c
index 0ff7c55173da..615174a9d1e0 100644
--- a/drivers/pinctrl/intel/pinctrl-baytrail.c
+++ b/drivers/pinctrl/intel/pinctrl-baytrail.c
@@ -800,6 +800,21 @@ static void byt_gpio_disable_free(struct pinctrl_dev *pctl_dev,
pm_runtime_put(vg->dev);
}
+static void byt_gpio_direct_irq_check(struct intel_pinctrl *vg,
+ unsigned int offset)
+{
+ void __iomem *conf_reg = byt_gpio_reg(vg, offset, BYT_CONF0_REG);
+
+ /*
+ * Before making any direction modifications, do a check if gpio is set
+ * for direct IRQ. On Bay Trail, setting GPIO to output does not make
+ * sense, so let's at least inform the caller before they shoot
+ * themselves in the foot.
+ */
+ if (readl(conf_reg) & BYT_DIRECT_IRQ_EN)
+ dev_info_once(vg->dev, "Potential Error: Setting GPIO with direct_irq_en to output");
+}
+
static int byt_gpio_set_direction(struct pinctrl_dev *pctl_dev,
struct pinctrl_gpio_range *range,
unsigned int offset,
@@ -807,7 +822,6 @@ static int byt_gpio_set_direction(struct pinctrl_dev *pctl_dev,
{
struct intel_pinctrl *vg = pinctrl_dev_get_drvdata(pctl_dev);
void __iomem *val_reg = byt_gpio_reg(vg, offset, BYT_VAL_REG);
- void __iomem *conf_reg = byt_gpio_reg(vg, offset, BYT_CONF0_REG);
unsigned long flags;
u32 value;
@@ -817,14 +831,8 @@ static int byt_gpio_set_direction(struct pinctrl_dev *pctl_dev,
value &= ~BYT_DIR_MASK;
if (input)
value |= BYT_OUTPUT_EN;
- else if (readl(conf_reg) & BYT_DIRECT_IRQ_EN)
- /*
- * Before making any direction modifications, do a check if gpio
- * is set for direct IRQ. On baytrail, setting GPIO to output
- * does not make sense, so let's at least inform the caller before
- * they shoot themselves in the foot.
- */
- dev_info_once(vg->dev, "Potential Error: Setting GPIO with direct_irq_en to output");
+ else
+ byt_gpio_direct_irq_check(vg, offset);
writel(value, val_reg);
@@ -1165,19 +1173,50 @@ static int byt_gpio_get_direction(struct gpio_chip *chip, unsigned int offset)
static int byt_gpio_direction_input(struct gpio_chip *chip, unsigned int offset)
{
- return pinctrl_gpio_direction_input(chip->base + offset);
+ struct intel_pinctrl *vg = gpiochip_get_data(chip);
+ void __iomem *val_reg = byt_gpio_reg(vg, offset, BYT_VAL_REG);
+ unsigned long flags;
+ u32 reg;
+
+ raw_spin_lock_irqsave(&byt_lock, flags);
+
+ reg = readl(val_reg);
+ reg &= ~BYT_DIR_MASK;
+ reg |= BYT_OUTPUT_EN;
+ writel(reg, val_reg);
+
+ raw_spin_unlock_irqrestore(&byt_lock, flags);
+ return 0;
}
+/*
+ * Note despite the temptation this MUST NOT be converted into a call to
+ * pinctrl_gpio_direction_output() + byt_gpio_set() that does not work this
+ * MUST be done as a single BYT_VAL_REG register write.
+ * See the commit message of the commit adding this comment for details.
+ */
static int byt_gpio_direction_output(struct gpio_chip *chip,
unsigned int offset, int value)
{
- int ret = pinctrl_gpio_direction_output(chip->base + offset);
+ struct intel_pinctrl *vg = gpiochip_get_data(chip);
+ void __iomem *val_reg = byt_gpio_reg(vg, offset, BYT_VAL_REG);
+ unsigned long flags;
+ u32 reg;
- if (ret)
- return ret;
+ raw_spin_lock_irqsave(&byt_lock, flags);
+
+ byt_gpio_direct_irq_check(vg, offset);
- byt_gpio_set(chip, offset, value);
+ reg = readl(val_reg);
+ reg &= ~BYT_DIR_MASK;
+ if (value)
+ reg |= BYT_LEVEL;
+ else
+ reg &= ~BYT_LEVEL;
+ writel(reg, val_reg);
+
+ raw_spin_unlock_irqrestore(&byt_lock, flags);
return 0;
}
The patch below does not apply to the 5.4-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 45c11a927606c612e4898a9484867b71318699f6 Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede(a)redhat.com>
Date: Sat, 6 Jun 2020 11:31:50 +0200
Subject: [PATCH] pinctrl: baytrail: Fix pin being driven low for a while on
gpiod_get(..., GPIOD_OUT_HIGH)
The pins on the Bay Trail SoC have separate input-buffer and output-buffer
enable bits and a read of the level bit of the value register will always
return the value from the input-buffer.
The BIOS of a device may configure a pin in output-only mode, only enabling
the output buffer, and write 1 to the level bit to drive the pin high.
This 1 written to the level bit will be stored inside the data-latch of the
output buffer.
But a subsequent read of the value register will return 0 for the level bit
because the input-buffer is disabled. This causes a read-modify-write as
done by byt_gpio_set_direction() to write 0 to the level bit, driving the
pin low!
Before this commit byt_gpio_direction_output() relied on
pinctrl_gpio_direction_output() to set the direction, followed by a call
to byt_gpio_set() to apply the selected value. This causes the pin to
go low between the pinctrl_gpio_direction_output() and byt_gpio_set()
calls.
Change byt_gpio_direction_output() to directly make the register
modifications itself instead. Replacing the 2 subsequent writes to the
value register with a single write.
Note that the pinctrl code does not keep track internally of the direction,
so not going through pinctrl_gpio_direction_output() is not an issue.
This issue was noticed on a Trekstor SurfTab Twin 10.1. When the panel is
already on at boot (no external monitor connected), then the i915 driver
does a gpiod_get(..., GPIOD_OUT_HIGH) for the panel-enable GPIO. The
temporarily going low of that GPIO was causing the panel to reset itself
after which it would not show an image until it was turned off and back on
again (until a full modeset was done on it). This commit fixes this.
This commit also updates the byt_gpio_direction_input() to use direct
register accesses instead of going through pinctrl_gpio_direction_input(),
to keep it consistent with byt_gpio_direction_output().
Note for backporting, this commit depends on:
commit e2b74419e5cc ("pinctrl: baytrail: Replace WARN with dev_info_once
when setting direct-irq pin to output")
Cc: stable(a)vger.kernel.org
Fixes: 86e3ef812fe3 ("pinctrl: baytrail: Update gpio chip operations")
Signed-off-by: Hans de Goede <hdegoede(a)redhat.com>
Acked-by: Mika Westerberg <mika.westerberg(a)linux.intel.com>
Signed-off-by: Andy Shevchenko <andriy.shevchenko(a)linux.intel.com>
diff --git a/drivers/pinctrl/intel/pinctrl-baytrail.c b/drivers/pinctrl/intel/pinctrl-baytrail.c
index 0ff7c55173da..615174a9d1e0 100644
--- a/drivers/pinctrl/intel/pinctrl-baytrail.c
+++ b/drivers/pinctrl/intel/pinctrl-baytrail.c
@@ -800,6 +800,21 @@ static void byt_gpio_disable_free(struct pinctrl_dev *pctl_dev,
pm_runtime_put(vg->dev);
}
+static void byt_gpio_direct_irq_check(struct intel_pinctrl *vg,
+ unsigned int offset)
+{
+ void __iomem *conf_reg = byt_gpio_reg(vg, offset, BYT_CONF0_REG);
+
+ /*
+ * Before making any direction modifications, do a check if gpio is set
+ * for direct IRQ. On Bay Trail, setting GPIO to output does not make
+ * sense, so let's at least inform the caller before they shoot
+ * themselves in the foot.
+ */
+ if (readl(conf_reg) & BYT_DIRECT_IRQ_EN)
+ dev_info_once(vg->dev, "Potential Error: Setting GPIO with direct_irq_en to output");
+}
+
static int byt_gpio_set_direction(struct pinctrl_dev *pctl_dev,
struct pinctrl_gpio_range *range,
unsigned int offset,
@@ -807,7 +822,6 @@ static int byt_gpio_set_direction(struct pinctrl_dev *pctl_dev,
{
struct intel_pinctrl *vg = pinctrl_dev_get_drvdata(pctl_dev);
void __iomem *val_reg = byt_gpio_reg(vg, offset, BYT_VAL_REG);
- void __iomem *conf_reg = byt_gpio_reg(vg, offset, BYT_CONF0_REG);
unsigned long flags;
u32 value;
@@ -817,14 +831,8 @@ static int byt_gpio_set_direction(struct pinctrl_dev *pctl_dev,
value &= ~BYT_DIR_MASK;
if (input)
value |= BYT_OUTPUT_EN;
- else if (readl(conf_reg) & BYT_DIRECT_IRQ_EN)
- /*
- * Before making any direction modifications, do a check if gpio
- * is set for direct IRQ. On baytrail, setting GPIO to output
- * does not make sense, so let's at least inform the caller before
- * they shoot themselves in the foot.
- */
- dev_info_once(vg->dev, "Potential Error: Setting GPIO with direct_irq_en to output");
+ else
+ byt_gpio_direct_irq_check(vg, offset);
writel(value, val_reg);
@@ -1165,19 +1173,50 @@ static int byt_gpio_get_direction(struct gpio_chip *chip, unsigned int offset)
static int byt_gpio_direction_input(struct gpio_chip *chip, unsigned int offset)
{
- return pinctrl_gpio_direction_input(chip->base + offset);
+ struct intel_pinctrl *vg = gpiochip_get_data(chip);
+ void __iomem *val_reg = byt_gpio_reg(vg, offset, BYT_VAL_REG);
+ unsigned long flags;
+ u32 reg;
+
+ raw_spin_lock_irqsave(&byt_lock, flags);
+
+ reg = readl(val_reg);
+ reg &= ~BYT_DIR_MASK;
+ reg |= BYT_OUTPUT_EN;
+ writel(reg, val_reg);
+
+ raw_spin_unlock_irqrestore(&byt_lock, flags);
+ return 0;
}
+/*
+ * Note despite the temptation this MUST NOT be converted into a call to
+ * pinctrl_gpio_direction_output() + byt_gpio_set() that does not work this
+ * MUST be done as a single BYT_VAL_REG register write.
+ * See the commit message of the commit adding this comment for details.
+ */
static int byt_gpio_direction_output(struct gpio_chip *chip,
unsigned int offset, int value)
{
- int ret = pinctrl_gpio_direction_output(chip->base + offset);
+ struct intel_pinctrl *vg = gpiochip_get_data(chip);
+ void __iomem *val_reg = byt_gpio_reg(vg, offset, BYT_VAL_REG);
+ unsigned long flags;
+ u32 reg;
- if (ret)
- return ret;
+ raw_spin_lock_irqsave(&byt_lock, flags);
+
+ byt_gpio_direct_irq_check(vg, offset);
- byt_gpio_set(chip, offset, value);
+ reg = readl(val_reg);
+ reg &= ~BYT_DIR_MASK;
+ if (value)
+ reg |= BYT_LEVEL;
+ else
+ reg &= ~BYT_LEVEL;
+ writel(reg, val_reg);
+
+ raw_spin_unlock_irqrestore(&byt_lock, flags);
return 0;
}
Hi Greg (et all),
Note several people are already working on this, so you may already have a request for this.
The "ath9k: Fix general protection fault in ath9k_hif_usb_rx_cb" commit which has been
added to several stable kernels (at least to 5.4.y and 5.7.y, but likely also to others)
is breaking networking for people with an ath9k card.
A revert has been submitted upstream, but it does not seem to have found it way
upstream yet. It has been cherry-picked by the Arch people:
https://git.archlinux.org/linux.git/commit/?h=v5.7.8-arch1&id=1a32e7b57b0b3…
So if you want to credit some of the original people working on fixing this,
you can find the revert submitted upstream there.
Reverting this fixes / also see:
https://bugzilla.kernel.org/show_bug.cgi?id=208251https://bugzilla.redhat.com/show_bug.cgi?id=1848631
Regards,
Hans
The patch below does not apply to the 5.4-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 66b7e05dc0239c5817859f261098ba9cc2efbd2b Mon Sep 17 00:00:00 2001
From: Steven Price <steven.price(a)arm.com>
Date: Wed, 17 Jun 2020 11:54:56 +0100
Subject: [PATCH] KVM: arm64: Fix kvm_reset_vcpu() return code being incorrect
with SVE
If SVE is enabled then 'ret' can be assigned the return value of
kvm_vcpu_enable_sve() which may be 0 causing future "goto out" sites to
erroneously return 0 on failure rather than -EINVAL as expected.
Remove the initialisation of 'ret' and make setting the return value
explicit to avoid this situation in the future.
Fixes: 9a3cdf26e336 ("KVM: arm64/sve: Allow userspace to enable SVE for vcpus")
Cc: stable(a)vger.kernel.org
Reported-by: James Morse <james.morse(a)arm.com>
Signed-off-by: Steven Price <steven.price(a)arm.com>
Signed-off-by: Marc Zyngier <maz(a)kernel.org>
Link: https://lore.kernel.org/r/20200617105456.28245-1-steven.price@arm.com
diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c
index d3b209023727..6ed36be51b4b 100644
--- a/arch/arm64/kvm/reset.c
+++ b/arch/arm64/kvm/reset.c
@@ -245,7 +245,7 @@ static int kvm_vcpu_enable_ptrauth(struct kvm_vcpu *vcpu)
*/
int kvm_reset_vcpu(struct kvm_vcpu *vcpu)
{
- int ret = -EINVAL;
+ int ret;
bool loaded;
u32 pstate;
@@ -269,15 +269,19 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu)
if (test_bit(KVM_ARM_VCPU_PTRAUTH_ADDRESS, vcpu->arch.features) ||
test_bit(KVM_ARM_VCPU_PTRAUTH_GENERIC, vcpu->arch.features)) {
- if (kvm_vcpu_enable_ptrauth(vcpu))
+ if (kvm_vcpu_enable_ptrauth(vcpu)) {
+ ret = -EINVAL;
goto out;
+ }
}
switch (vcpu->arch.target) {
default:
if (test_bit(KVM_ARM_VCPU_EL1_32BIT, vcpu->arch.features)) {
- if (!cpus_have_const_cap(ARM64_HAS_32BIT_EL1))
+ if (!cpus_have_const_cap(ARM64_HAS_32BIT_EL1)) {
+ ret = -EINVAL;
goto out;
+ }
pstate = VCPU_RESET_PSTATE_SVC;
} else {
pstate = VCPU_RESET_PSTATE_EL1;
Hello,
We ran automated tests on a recent commit from this kernel tree:
Kernel repo: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git
Commit: 48479b55494e - ALSA: hda/realtek - Fix Lenovo Thinkpad X1 Carbon 7th quirk subdevice id
The results of these automated tests are provided below.
Overall result: PASSED
Merge: OK
Compile: OK
Tests: OK
All kernel binaries, config files, and logs are available for download here:
https://cki-artifacts.s3.us-east-2.amazonaws.com/index.html?prefix=dataware…
Please reply to this email if you have any questions about the tests that we
ran or if you have any suggestions on how to make future tests more effective.
,-. ,-.
( C ) ( K ) Continuous
`-',-.`-' Kernel
( I ) Integration
`-'
______________________________________________________________________________
Compile testing
---------------
We compiled the kernel for 4 architectures:
aarch64:
make options: -j30 INSTALL_MOD_STRIP=1 targz-pkg
ppc64le:
make options: -j30 INSTALL_MOD_STRIP=1 targz-pkg
s390x:
make options: -j30 INSTALL_MOD_STRIP=1 targz-pkg
x86_64:
make options: -j30 INSTALL_MOD_STRIP=1 targz-pkg
Hardware testing
----------------
We booted each kernel and ran the following tests:
aarch64:
Host 1:
✅ Boot test
✅ ACPI table test
✅ ACPI enabled test
✅ Podman system integration test - as root
✅ Podman system integration test - as user
✅ LTP
✅ Loopdev Sanity
✅ Memory function: memfd_create
✅ AMTU (Abstract Machine Test Utility)
✅ Networking bridge: sanity
✅ Ethernet drivers sanity
✅ Networking socket: fuzz
✅ Networking: igmp conformance test
✅ Networking route: pmtu
✅ Networking route_func - local
✅ Networking route_func - forward
✅ Networking TCP: keepalive test
✅ Networking UDP: socket
✅ Networking tunnel: geneve basic test
✅ Networking tunnel: gre basic
✅ L2TP basic test
✅ Networking tunnel: vxlan basic
✅ Networking ipsec: basic netns - transport
✅ Networking ipsec: basic netns - tunnel
✅ Libkcapi AF_ALG test
✅ pciutils: update pci ids test
✅ ALSA PCM loopback test
✅ ALSA Control (mixer) Userspace Element test
✅ storage: SCSI VPD
🚧 ✅ CIFS Connectathon
🚧 ✅ POSIX pjd-fstest suites
🚧 ✅ jvm - DaCapo Benchmark Suite
🚧 ✅ jvm - jcstress tests
🚧 ✅ Memory function: kaslr
🚧 ✅ Networking firewall: basic netfilter test
🚧 ✅ audit: audit testsuite test
🚧 ✅ trace: ftrace/tracer
🚧 ✅ kdump - kexec_boot
Host 2:
✅ Boot test
✅ xfstests - ext4
✅ xfstests - xfs
✅ selinux-policy: serge-testsuite
✅ storage: software RAID testing
🚧 ✅ IPMI driver test
🚧 ✅ IPMItool loop stress test
🚧 ✅ Storage blktests
ppc64le:
Host 1:
✅ Boot test
✅ xfstests - ext4
✅ xfstests - xfs
✅ selinux-policy: serge-testsuite
✅ storage: software RAID testing
🚧 ✅ IPMI driver test
🚧 ✅ IPMItool loop stress test
🚧 ✅ Storage blktests
Host 2:
✅ Boot test
✅ Podman system integration test - as root
✅ Podman system integration test - as user
✅ LTP
✅ Loopdev Sanity
✅ Memory function: memfd_create
✅ AMTU (Abstract Machine Test Utility)
✅ Networking bridge: sanity
✅ Ethernet drivers sanity
✅ Networking socket: fuzz
✅ Networking route: pmtu
✅ Networking route_func - local
✅ Networking route_func - forward
✅ Networking TCP: keepalive test
✅ Networking UDP: socket
✅ Networking tunnel: geneve basic test
✅ Networking tunnel: gre basic
✅ L2TP basic test
✅ Networking tunnel: vxlan basic
✅ Networking ipsec: basic netns - tunnel
✅ Libkcapi AF_ALG test
✅ pciutils: update pci ids test
✅ ALSA PCM loopback test
✅ ALSA Control (mixer) Userspace Element test
🚧 ✅ CIFS Connectathon
🚧 ✅ POSIX pjd-fstest suites
🚧 ✅ jvm - DaCapo Benchmark Suite
🚧 ✅ jvm - jcstress tests
🚧 ✅ Memory function: kaslr
🚧 ✅ Networking firewall: basic netfilter test
🚧 ✅ audit: audit testsuite test
🚧 ✅ trace: ftrace/tracer
Host 3:
✅ Boot test
🚧 ✅ kdump - sysrq-c
s390x:
Host 1:
⚡ Internal infrastructure issues prevented one or more tests (marked
with ⚡⚡⚡) from running on this architecture.
This is not the fault of the kernel that was tested.
✅ Boot test
🚧 ⚡⚡⚡ kdump - sysrq-c
🚧 ⚡⚡⚡ kdump - file-load
Host 2:
✅ Boot test
✅ selinux-policy: serge-testsuite
✅ stress: stress-ng
🚧 ✅ Storage blktests
Host 3:
✅ Boot test
✅ Podman system integration test - as root
✅ Podman system integration test - as user
✅ LTP
✅ Loopdev Sanity
✅ Memory function: memfd_create
✅ Networking bridge: sanity
✅ Ethernet drivers sanity
✅ Networking route: pmtu
✅ Networking route_func - local
✅ Networking route_func - forward
✅ Networking TCP: keepalive test
✅ Networking UDP: socket
✅ Networking tunnel: geneve basic test
✅ Networking tunnel: gre basic
✅ L2TP basic test
✅ Networking tunnel: vxlan basic
✅ Networking ipsec: basic netns - transport
✅ Networking ipsec: basic netns - tunnel
✅ Libkcapi AF_ALG test
🚧 ✅ CIFS Connectathon
🚧 ✅ POSIX pjd-fstest suites
🚧 ✅ jvm - DaCapo Benchmark Suite
🚧 ✅ jvm - jcstress tests
🚧 ✅ Memory function: kaslr
🚧 ✅ Networking firewall: basic netfilter test
🚧 ✅ audit: audit testsuite test
🚧 ✅ trace: ftrace/tracer
🚧 ✅ kdump - kexec_boot
x86_64:
Host 1:
✅ Boot test
🚧 ✅ kdump - sysrq-c
🚧 ✅ kdump - file-load
Host 2:
✅ Boot test
✅ ACPI table test
✅ Podman system integration test - as root
✅ Podman system integration test - as user
✅ LTP
✅ Loopdev Sanity
✅ Memory function: memfd_create
✅ AMTU (Abstract Machine Test Utility)
✅ Networking bridge: sanity
✅ Ethernet drivers sanity
✅ Networking socket: fuzz
✅ Networking: igmp conformance test
✅ Networking route: pmtu
✅ Networking route_func - local
✅ Networking route_func - forward
✅ Networking TCP: keepalive test
✅ Networking UDP: socket
✅ Networking tunnel: geneve basic test
✅ Networking tunnel: gre basic
✅ L2TP basic test
✅ Networking tunnel: vxlan basic
✅ Networking ipsec: basic netns - transport
✅ Networking ipsec: basic netns - tunnel
✅ Libkcapi AF_ALG test
✅ pciutils: sanity smoke test
✅ pciutils: update pci ids test
✅ ALSA PCM loopback test
✅ ALSA Control (mixer) Userspace Element test
✅ storage: SCSI VPD
🚧 ✅ CIFS Connectathon
🚧 ✅ POSIX pjd-fstest suites
🚧 ✅ jvm - DaCapo Benchmark Suite
🚧 ✅ jvm - jcstress tests
🚧 ✅ Memory function: kaslr
🚧 ✅ Networking firewall: basic netfilter test
🚧 ✅ audit: audit testsuite test
🚧 ✅ trace: ftrace/tracer
🚧 ✅ kdump - kexec_boot
Host 3:
✅ Boot test
✅ xfstests - ext4
✅ xfstests - xfs
✅ selinux-policy: serge-testsuite
✅ storage: software RAID testing
✅ stress: stress-ng
🚧 ❌ CPU: Frequency Driver Test
🚧 ✅ CPU: Idle Test
🚧 ✅ IOMMU boot test
🚧 ✅ IPMI driver test
🚧 ✅ IPMItool loop stress test
🚧 ✅ power-management: cpupower/sanity test
🚧 ✅ Storage blktests
Test sources: https://gitlab.com/cki-project/kernel-tests
💚 Pull requests are welcome for new tests or improvements to existing tests!
Aborted tests
-------------
Tests that didn't complete running successfully are marked with ⚡⚡⚡.
If this was caused by an infrastructure issue, we try to mark that
explicitly in the report.
Waived tests
------------
If the test run included waived tests, they are marked with 🚧. Such tests are
executed but their results are not taken into account. Tests are waived when
their results are not reliable enough, e.g. when they're just introduced or are
being fixed.
Testing timeout
---------------
We aim to provide a report within reasonable timeframe. Tests that haven't
finished running yet are marked with ⏱.
From: Roland Scheidegger <sroland(a)vmware.com>
The assignment of metadata overwrote the new display resolution values,
hence we'd miss the size actually changed and wouldn't redefine the
surface. This would then lead to command buffer error when trying to
update the screen target (due to the size mismatch), and result in a
VM with black screen.
Fixes: 504901dbb0b5 ("drm/vmwgfx: Refactor surface_define to use vmw_surface_metadata")
Reviewed-by: Charmaine Lee <charmainel(a)vmware.com>
Signed-off-by: Roland Scheidegger <sroland(a)vmware.com>
Cc: stable(a)vger.kernel.org
---
drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c | 8 ++++----
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c b/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c
index 9ffa9c75a5da..16b385629688 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c
@@ -1069,10 +1069,6 @@ vmw_stdu_primary_plane_prepare_fb(struct drm_plane *plane,
if (new_content_type != SAME_AS_DISPLAY) {
struct vmw_surface_metadata metadata = {0};
- metadata.base_size.width = hdisplay;
- metadata.base_size.height = vdisplay;
- metadata.base_size.depth = 1;
-
/*
* If content buffer is a buffer object, then we have to
* construct surface info
@@ -1104,6 +1100,10 @@ vmw_stdu_primary_plane_prepare_fb(struct drm_plane *plane,
metadata = new_vfbs->surface->metadata;
}
+ metadata.base_size.width = hdisplay;
+ metadata.base_size.height = vdisplay;
+ metadata.base_size.depth = 1;
+
if (vps->surf) {
struct drm_vmw_size cur_base_size =
vps->surf->metadata.base_size;
--
2.17.1
From: Ville Syrjälä <ville.syrjala(a)linux.intel.com>
Currently we're failing to recalculate the gen9 FBC w/a stride
unless something more drastic than just the modifier itself has
changed. This often leaves us with FBC enabled with the linear
fbdev framebuffer without the w/a stride enabled. That will cause
an immediate underrun and FBC will get promptly disabled.
Fix the problem by checking if the w/a stride is about to change,
and go through the full dance if so. This part of the FBC code
is still pretty much a disaster and will need lots more work.
But this should at least fix the immediate issue.
Cc: stable(a)vger.kernel.org
Signed-off-by: Ville Syrjälä <ville.syrjala(a)linux.intel.com>
---
drivers/gpu/drm/i915/display/intel_fbc.c | 29 ++++++++++++++++++------
1 file changed, 22 insertions(+), 7 deletions(-)
diff --git a/drivers/gpu/drm/i915/display/intel_fbc.c b/drivers/gpu/drm/i915/display/intel_fbc.c
index ef2eb14f6157..ff199374ed36 100644
--- a/drivers/gpu/drm/i915/display/intel_fbc.c
+++ b/drivers/gpu/drm/i915/display/intel_fbc.c
@@ -742,6 +742,25 @@ static bool intel_fbc_cfb_size_changed(struct drm_i915_private *dev_priv)
fbc->compressed_fb.size * fbc->threshold;
}
+static u16 intel_fbc_gen9_wa_cfb_stride(struct drm_i915_private *dev_priv)
+{
+ struct intel_fbc *fbc = &dev_priv->fbc;
+ struct intel_fbc_state_cache *cache = &fbc->state_cache;
+
+ if ((IS_GEN9_BC(dev_priv) || IS_BROXTON(dev_priv)) &&
+ cache->fb.modifier != I915_FORMAT_MOD_X_TILED)
+ return DIV_ROUND_UP(cache->plane.src_w, 32 * fbc->threshold) * 8;
+ else
+ return 0;
+}
+
+static bool intel_fbc_gen9_wa_cfb_stride_changed(struct drm_i915_private *dev_priv)
+{
+ struct intel_fbc *fbc = &dev_priv->fbc;
+
+ return fbc->params.gen9_wa_cfb_stride != intel_fbc_gen9_wa_cfb_stride(dev_priv);
+}
+
static bool intel_fbc_can_enable(struct drm_i915_private *dev_priv)
{
struct intel_fbc *fbc = &dev_priv->fbc;
@@ -1218,7 +1237,8 @@ void intel_fbc_enable(struct intel_atomic_state *state,
if (fbc->crtc) {
if (fbc->crtc != crtc ||
- !intel_fbc_cfb_size_changed(dev_priv))
+ (!intel_fbc_cfb_size_changed(dev_priv) &&
+ !intel_fbc_gen9_wa_cfb_stride_changed(dev_priv)))
goto out;
__intel_fbc_disable(dev_priv);
@@ -1240,12 +1260,7 @@ void intel_fbc_enable(struct intel_atomic_state *state,
goto out;
}
- if ((IS_GEN9_BC(dev_priv) || IS_BROXTON(dev_priv)) &&
- plane_state->hw.fb->modifier != I915_FORMAT_MOD_X_TILED)
- cache->gen9_wa_cfb_stride =
- DIV_ROUND_UP(cache->plane.src_w, 32 * fbc->threshold) * 8;
- else
- cache->gen9_wa_cfb_stride = 0;
+ cache->gen9_wa_cfb_stride = intel_fbc_gen9_wa_cfb_stride(dev_priv);
drm_dbg_kms(&dev_priv->drm, "Enabling FBC on pipe %c\n",
pipe_name(crtc->pipe));
--
2.26.2
The danger in switching at random upon intel_context_pin is that the
context may still actually be inflight, as it will not be scheduled out
until a context switch after it is complete -- that is after we do a
final intel_context_unpin.
Closes: https://gitlab.freedesktop.org/drm/intel/-/issues/2118
Fixes: 6d06779e8672 ("drm/i915: Load balancing across a virtual engine")
Signed-off-by: Chris Wilson <chris(a)chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin(a)intel.com>
Cc: <stable(a)vger.kernel.org> # v5.3+
---
drivers/gpu/drm/i915/gt/intel_lrc.c | 18 ++++--------------
1 file changed, 4 insertions(+), 14 deletions(-)
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index cd4262cc96e2..f4658849b08a 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -5435,13 +5435,8 @@ static void virtual_engine_initial_hint(struct virtual_engine *ve)
* typically be the first we inspect for submission.
*/
swp = prandom_u32_max(ve->num_siblings);
- if (!swp)
- return;
-
- swap(ve->siblings[swp], ve->siblings[0]);
- if (!intel_engine_has_relative_mmio(ve->siblings[0]))
- virtual_update_register_offsets(ve->context.lrc_reg_state,
- ve->siblings[0]);
+ if (swp)
+ swap(ve->siblings[swp], ve->siblings[0]);
}
static int virtual_context_alloc(struct intel_context *ce)
@@ -5454,15 +5449,9 @@ static int virtual_context_alloc(struct intel_context *ce)
static int virtual_context_pin(struct intel_context *ce)
{
struct virtual_engine *ve = container_of(ce, typeof(*ve), context);
- int err;
/* Note: we must use a real engine class for setting up reg state */
- err = __execlists_context_pin(ce, ve->siblings[0]);
- if (err)
- return err;
-
- virtual_engine_initial_hint(ve);
- return 0;
+ return __execlists_context_pin(ce, ve->siblings[0]);
}
static void virtual_context_enter(struct intel_context *ce)
@@ -5808,6 +5797,7 @@ intel_execlists_create_virtual(struct intel_engine_cs **siblings,
ve->base.flags |= I915_ENGINE_IS_VIRTUAL;
+ virtual_engine_initial_hint(ve);
return &ve->context;
err_put:
--
2.20.1
Preempt-to-busy introduces various fascinating complications in that the
requests may complete as we are unsubmitting them from HW. As they may
then signal after unsubmission, we may find ourselves having to cleanup
the signaling request from within the signaling callback. This causes us
to recurse onto the same i915_request.lock.
However, if the request is already signaled (as it will be before we
enter the signal callbacks), we know we can skip the signaling of that
request during submission, neatly evading the spinlock recursion.
unsubmit(ve.rq0) # timeslice expiration or other preemption
-> virtual_submit_request(ve.rq0)
dma_fence_signal(ve.rq0) # request completed before preemption ack
-> submit_notify(ve.rq1)
-> virtual_submit_request(ve.rq1) # sees that we have completed ve.rq0
-> __i915_request_submit(ve.rq0)
[ 264.210142] BUG: spinlock recursion on CPU#2, sample_multi_tr/2093
[ 264.210150] lock: 0xffff9efd6ac55080, .magic: dead4ead, .owner: sample_multi_tr/2093, .owner_cpu: 2
[ 264.210155] CPU: 2 PID: 2093 Comm: sample_multi_tr Tainted: G U 5.4.48-prod-dg1-vn-2660+ #3
[ 264.210158] Hardware name: Intel Corporation CoffeeLake Client Platform/CoffeeLake S UDIMM RVP, BIOS CNLSFWR1.R00.X212.B01.1909060036 09/06/2019
[ 264.210160] Call Trace:
[ 264.210167] dump_stack+0x98/0xda
[ 264.210174] spin_dump.cold+0x24/0x3c
[ 264.210178] do_raw_spin_lock+0x9a/0xd0
[ 264.210184] _raw_spin_lock_nested+0x6a/0x70
[ 264.210314] __i915_request_submit+0x10a/0x3c0 [i915]
[ 264.210415] virtual_submit_request+0x9b/0x380 [i915]
[ 264.210516] submit_notify+0xaf/0x14c [i915]
[ 264.210602] __i915_sw_fence_complete+0x8a/0x230 [i915]
[ 264.210692] i915_sw_fence_complete+0x2d/0x40 [i915]
[ 264.210762] __dma_i915_sw_fence_wake+0x19/0x30 [i915]
[ 264.210767] dma_fence_signal_locked+0xb1/0x1c0
[ 264.210772] dma_fence_signal+0x29/0x50
[ 264.210871] i915_request_wait+0x5cb/0x830 [i915]
[ 264.210876] ? dma_resv_get_fences_rcu+0x294/0x5d0
[ 264.210974] i915_gem_object_wait_fence+0x2f/0x40 [i915]
[ 264.211084] i915_gem_object_wait+0xce/0x400 [i915]
[ 264.211178] i915_gem_wait_ioctl+0xff/0x290 [i915]
Signed-off-by: Chris Wilson <chris(a)chris-wilson.co.uk>
Fixes: 22b7a426bbe1 ("drm/i915/execlists: Preempt-to-busy")
References: 6d06779e8672 ("drm/i915: Load balancing across a virtual engine")
Signed-off-by: Chris Wilson <chris(a)chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin(a)intel.com>
Cc: "Nayana, Venkata Ramana" <venkata.ramana.nayana(a)intel.com>
Cc: <stable(a)vger.kernel.org> # v5.4+
---
drivers/gpu/drm/i915/i915_request.c | 21 +++++++++++++--------
1 file changed, 13 insertions(+), 8 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index 3bb7320249ae..9b74a1bea5db 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -560,9 +560,7 @@ bool __i915_request_submit(struct i915_request *request)
engine->serial++;
result = true;
-xfer: /* We may be recursing from the signal callback of another i915 fence */
- spin_lock_nested(&request->lock, SINGLE_DEPTH_NESTING);
-
+xfer:
if (!test_and_set_bit(I915_FENCE_FLAG_ACTIVE, &request->fence.flags)) {
list_move_tail(&request->sched.link, &engine->active.requests);
clear_bit(I915_FENCE_FLAG_PQUEUE, &request->fence.flags);
@@ -570,12 +568,19 @@ bool __i915_request_submit(struct i915_request *request)
}
GEM_BUG_ON(!llist_empty(&request->execute_cb));
- if (test_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT, &request->fence.flags) &&
- !test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &request->fence.flags) &&
- !i915_request_enable_breadcrumb(request))
- intel_engine_signal_breadcrumbs(engine);
+ /* We may be recursing from the signal callback of another i915 fence */
+ if (!i915_request_signaled(request)) {
+ spin_lock_nested(&request->lock, SINGLE_DEPTH_NESTING);
+
+ if (test_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT,
+ &request->fence.flags) &&
+ !test_bit(DMA_FENCE_FLAG_SIGNALED_BIT,
+ &request->fence.flags) &&
+ !i915_request_enable_breadcrumb(request))
+ intel_engine_signal_breadcrumbs(engine);
- spin_unlock(&request->lock);
+ spin_unlock(&request->lock);
+ }
return result;
}
--
2.20.1
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 7c83d096aed055a7763a03384f92115363448b71 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <sean.j.christopherson(a)intel.com>
Date: Thu, 2 Jul 2020 21:04:21 -0700
Subject: [PATCH] KVM: x86: Mark CR4.TSD as being possibly owned by the guest
Mark CR4.TSD as being possibly owned by the guest as that is indeed the
case on VMX. Without TSD being tagged as possibly owned by the guest, a
targeted read of CR4 to get TSD could observe a stale value. This bug
is benign in the current code base as the sole consumer of TSD is the
emulator (for RDTSC) and the emulator always "reads" the entirety of CR4
when grabbing bits.
Add a build-time assertion in to ensure VMX doesn't hand over more CR4
bits without also updating x86.
Fixes: 52ce3c21aec3 ("x86,kvm,vmx: Don't trap writes to CR4.TSD")
Cc: stable(a)vger.kernel.org
Signed-off-by: Sean Christopherson <sean.j.christopherson(a)intel.com>
Message-Id: <20200703040422.31536-2-sean.j.christopherson(a)intel.com>
Signed-off-by: Paolo Bonzini <pbonzini(a)redhat.com>
diff --git a/arch/x86/kvm/kvm_cache_regs.h b/arch/x86/kvm/kvm_cache_regs.h
index ff2d0e9ca3bc..cfe83d4ae625 100644
--- a/arch/x86/kvm/kvm_cache_regs.h
+++ b/arch/x86/kvm/kvm_cache_regs.h
@@ -7,7 +7,7 @@
#define KVM_POSSIBLE_CR0_GUEST_BITS X86_CR0_TS
#define KVM_POSSIBLE_CR4_GUEST_BITS \
(X86_CR4_PVI | X86_CR4_DE | X86_CR4_PCE | X86_CR4_OSFXSR \
- | X86_CR4_OSXMMEXCPT | X86_CR4_LA57 | X86_CR4_PGE)
+ | X86_CR4_OSXMMEXCPT | X86_CR4_LA57 | X86_CR4_PGE | X86_CR4_TSD)
#define BUILD_KVM_GPR_ACCESSORS(lname, uname) \
static __always_inline unsigned long kvm_##lname##_read(struct kvm_vcpu *vcpu)\
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index cb22f33bf1d8..5c9bfc0b9ab9 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -4034,6 +4034,8 @@ void vmx_set_constant_host_state(struct vcpu_vmx *vmx)
void set_cr4_guest_host_mask(struct vcpu_vmx *vmx)
{
+ BUILD_BUG_ON(KVM_CR4_GUEST_OWNED_BITS & ~KVM_POSSIBLE_CR4_GUEST_BITS);
+
vmx->vcpu.arch.cr4_guest_owned_bits = KVM_CR4_GUEST_OWNED_BITS;
if (enable_ept)
vmx->vcpu.arch.cr4_guest_owned_bits |= X86_CR4_PGE;
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 7c83d096aed055a7763a03384f92115363448b71 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <sean.j.christopherson(a)intel.com>
Date: Thu, 2 Jul 2020 21:04:21 -0700
Subject: [PATCH] KVM: x86: Mark CR4.TSD as being possibly owned by the guest
Mark CR4.TSD as being possibly owned by the guest as that is indeed the
case on VMX. Without TSD being tagged as possibly owned by the guest, a
targeted read of CR4 to get TSD could observe a stale value. This bug
is benign in the current code base as the sole consumer of TSD is the
emulator (for RDTSC) and the emulator always "reads" the entirety of CR4
when grabbing bits.
Add a build-time assertion in to ensure VMX doesn't hand over more CR4
bits without also updating x86.
Fixes: 52ce3c21aec3 ("x86,kvm,vmx: Don't trap writes to CR4.TSD")
Cc: stable(a)vger.kernel.org
Signed-off-by: Sean Christopherson <sean.j.christopherson(a)intel.com>
Message-Id: <20200703040422.31536-2-sean.j.christopherson(a)intel.com>
Signed-off-by: Paolo Bonzini <pbonzini(a)redhat.com>
diff --git a/arch/x86/kvm/kvm_cache_regs.h b/arch/x86/kvm/kvm_cache_regs.h
index ff2d0e9ca3bc..cfe83d4ae625 100644
--- a/arch/x86/kvm/kvm_cache_regs.h
+++ b/arch/x86/kvm/kvm_cache_regs.h
@@ -7,7 +7,7 @@
#define KVM_POSSIBLE_CR0_GUEST_BITS X86_CR0_TS
#define KVM_POSSIBLE_CR4_GUEST_BITS \
(X86_CR4_PVI | X86_CR4_DE | X86_CR4_PCE | X86_CR4_OSFXSR \
- | X86_CR4_OSXMMEXCPT | X86_CR4_LA57 | X86_CR4_PGE)
+ | X86_CR4_OSXMMEXCPT | X86_CR4_LA57 | X86_CR4_PGE | X86_CR4_TSD)
#define BUILD_KVM_GPR_ACCESSORS(lname, uname) \
static __always_inline unsigned long kvm_##lname##_read(struct kvm_vcpu *vcpu)\
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index cb22f33bf1d8..5c9bfc0b9ab9 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -4034,6 +4034,8 @@ void vmx_set_constant_host_state(struct vcpu_vmx *vmx)
void set_cr4_guest_host_mask(struct vcpu_vmx *vmx)
{
+ BUILD_BUG_ON(KVM_CR4_GUEST_OWNED_BITS & ~KVM_POSSIBLE_CR4_GUEST_BITS);
+
vmx->vcpu.arch.cr4_guest_owned_bits = KVM_CR4_GUEST_OWNED_BITS;
if (enable_ept)
vmx->vcpu.arch.cr4_guest_owned_bits |= X86_CR4_PGE;
The patch below does not apply to the 5.7-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 66b7e05dc0239c5817859f261098ba9cc2efbd2b Mon Sep 17 00:00:00 2001
From: Steven Price <steven.price(a)arm.com>
Date: Wed, 17 Jun 2020 11:54:56 +0100
Subject: [PATCH] KVM: arm64: Fix kvm_reset_vcpu() return code being incorrect
with SVE
If SVE is enabled then 'ret' can be assigned the return value of
kvm_vcpu_enable_sve() which may be 0 causing future "goto out" sites to
erroneously return 0 on failure rather than -EINVAL as expected.
Remove the initialisation of 'ret' and make setting the return value
explicit to avoid this situation in the future.
Fixes: 9a3cdf26e336 ("KVM: arm64/sve: Allow userspace to enable SVE for vcpus")
Cc: stable(a)vger.kernel.org
Reported-by: James Morse <james.morse(a)arm.com>
Signed-off-by: Steven Price <steven.price(a)arm.com>
Signed-off-by: Marc Zyngier <maz(a)kernel.org>
Link: https://lore.kernel.org/r/20200617105456.28245-1-steven.price@arm.com
diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c
index d3b209023727..6ed36be51b4b 100644
--- a/arch/arm64/kvm/reset.c
+++ b/arch/arm64/kvm/reset.c
@@ -245,7 +245,7 @@ static int kvm_vcpu_enable_ptrauth(struct kvm_vcpu *vcpu)
*/
int kvm_reset_vcpu(struct kvm_vcpu *vcpu)
{
- int ret = -EINVAL;
+ int ret;
bool loaded;
u32 pstate;
@@ -269,15 +269,19 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu)
if (test_bit(KVM_ARM_VCPU_PTRAUTH_ADDRESS, vcpu->arch.features) ||
test_bit(KVM_ARM_VCPU_PTRAUTH_GENERIC, vcpu->arch.features)) {
- if (kvm_vcpu_enable_ptrauth(vcpu))
+ if (kvm_vcpu_enable_ptrauth(vcpu)) {
+ ret = -EINVAL;
goto out;
+ }
}
switch (vcpu->arch.target) {
default:
if (test_bit(KVM_ARM_VCPU_EL1_32BIT, vcpu->arch.features)) {
- if (!cpus_have_const_cap(ARM64_HAS_32BIT_EL1))
+ if (!cpus_have_const_cap(ARM64_HAS_32BIT_EL1)) {
+ ret = -EINVAL;
goto out;
+ }
pstate = VCPU_RESET_PSTATE_SVC;
} else {
pstate = VCPU_RESET_PSTATE_EL1;
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>.
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
>From 9774dc218bb628974dcbc76412f970e9258e5f27 Mon Sep 17 00:00:00 2001
From: Benjamin Poirier <benjamin.poirier(a)gmail.com>
Date: Fri, 3 Jul 2020 17:00:04 +0900
Subject: [PATCH] ALSA: hda/realtek - Fix Lenovo Thinkpad X1 Carbon 7th quirk
subdevice id
1)
In snd_hda_pick_fixup(), quirks are first matched by PCI SSID and then, if
there is no match, by codec SSID. The Lenovo "ThinkPad X1 Carbon 7th" has
an audio chip with PCI SSID 0x2292 and codec SSID 0x2293[1]. Therefore, fix
the quirk meant for that device to match on .subdevice == 0x2292.
2)
The "Thinkpad X1 Yoga 7th" does not exist. The companion product to the
Carbon 7th is the Yoga 4th. That device has an audio chip with PCI SSID
0x2292 and codec SSID 0x2292[2]. Given the behavior of
snd_hda_pick_fixup(), it is not possible to have a separate quirk for the
Yoga based on SSID. Therefore, merge the quirks meant for the Carbon and
Yoga. This preserves the current behavior for the Yoga.
[1] This is the case on my own machine and can also be checked here
https://github.com/linuxhw/LsPCI/tree/master/Notebook/Lenovo/ThinkPadhttps://gist.github.com/hamidzr/dd81e429dc86f4327ded7a2030e7d7d9#gistcommen…
[2]
https://github.com/linuxhw/LsPCI/tree/master/Convertible/Lenovo/ThinkPadhttps://gist.github.com/hamidzr/dd81e429dc86f4327ded7a2030e7d7d9#gistcommen…
Fixes: d2cd795c4ece ("ALSA: hda - fixup for the bass speaker on Lenovo Carbon X1 7th gen")
Fixes: 54a6a7dc107d ("ALSA: hda/realtek - Add quirk for the bass speaker on Lenovo Yoga X1 7th gen")
Cc: Jaroslav Kysela <perex(a)perex.cz>
Cc: Kailang Yang <kailang(a)realtek.com>
Tested-by: Vincent Bernat <vincent(a)bernat.ch>
Tested-by: Even Brenden <evenbrenden(a)gmail.com>
Signed-off-by: Benjamin Poirier <benjamin.poirier(a)gmail.com>
Cc: <stable(a)vger.kernel.org>
Link: https://lore.kernel.org/r/20200703080005.8942-2-benjamin.poirier@gmail.com
Signed-off-by: Takashi Iwai <tiwai(a)suse.de>
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 737ef82a75fd..d6dd2aea146d 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -7571,8 +7571,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
SND_PCI_QUIRK(0x17aa, 0x224c, "Thinkpad", ALC298_FIXUP_TPT470_DOCK),
SND_PCI_QUIRK(0x17aa, 0x224d, "Thinkpad", ALC298_FIXUP_TPT470_DOCK),
SND_PCI_QUIRK(0x17aa, 0x225d, "Thinkpad T480", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
- SND_PCI_QUIRK(0x17aa, 0x2292, "Thinkpad X1 Yoga 7th", ALC285_FIXUP_THINKPAD_HEADSET_JACK),
- SND_PCI_QUIRK(0x17aa, 0x2293, "Thinkpad X1 Carbon 7th", ALC285_FIXUP_THINKPAD_HEADSET_JACK),
+ SND_PCI_QUIRK(0x17aa, 0x2292, "Thinkpad X1 Carbon 7th", ALC285_FIXUP_THINKPAD_HEADSET_JACK),
SND_PCI_QUIRK(0x17aa, 0x22be, "Thinkpad X1 Carbon 8th", ALC285_FIXUP_THINKPAD_HEADSET_JACK),
SND_PCI_QUIRK(0x17aa, 0x30bb, "ThinkCentre AIO", ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY),
SND_PCI_QUIRK(0x17aa, 0x30e2, "ThinkCentre AIO", ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY),
APPRAISE_BOOTPARAM has been marked as dependent on !ARCH_POLICY in compile
time, enforcing the appraisal whenever the kernel had the arch policy option
enabled.
However it breaks systems where the option is set but the system didn't
boot in a "secure boot" platform. In this scenario, anytime an appraisal
policy (i.e. ima_policy=appraisal_tcb) is used it will be forced, without
giving the user the opportunity to label the filesystem, before enforcing
integrity.
Considering the ARCH_POLICY is only effective when secure boot is actually
enabled this patch remove the compile time dependency and move it to a
runtime decision, based on the secure boot state of that platform.
With this patch:
- x86-64 with secure boot enabled
[ 0.004305] Secure boot enabled
...
[ 0.015651] Kernel command line: <...> ima_policy=appraise_tcb ima_appraise=fix
[ 0.015682] ima: appraise boot param ignored: secure boot enabled
- powerpc with secure boot disabled
[ 0.000000] Kernel command line: <...> ima_policy=appraise_tcb ima_appraise=fix
[ 0.000000] Secure boot mode disabled
...
< nothing about boot param ignored >
System working fine without secure boot and with both options set:
CONFIG_IMA_APPRAISE_BOOTPARAM=y
CONFIG_IMA_ARCH_POLICY=y
Audit logs pointing to "missing-hash" but still being able to execute due to
ima_appraise=fix:
type=INTEGRITY_DATA msg=audit(07/09/2020 12:30:27.778:1691) : pid=4976
uid=root auid=root ses=2
subj=unconfined_u:unconfined_r:unconfined_t:s0-s0:c0.c1023 op=appraise_data
cause=missing-hash comm=bash name=/usr/bin/evmctl dev="dm-0" ino=493150
res=no
Cc: stable(a)vger.kernel.org
Fixes: d958083a8f64 ("x86/ima: define arch_get_ima_policy() for x86")
Signed-off-by: Bruno Meneguele <bmeneg(a)redhat.com>
---
Changelog:
v5:
- add pr_info() to inform user the ima_appraise= boot param is being
ignored due to secure boot enabled (Nayna)
- add some testing results to commit log
v4:
- instead of change arch_policy loading code, check secure boot state at
"ima_appraise=" parameter handler (Mimi)
v3:
- extend secure boot arch checker to also consider trusted boot
- enforce IMA appraisal when secure boot is effectively enabled (Nayna)
- fix ima_appraise flag assignment by or'ing it (Mimi)
v2:
- pr_info() message prefix correction
security/integrity/ima/Kconfig | 2 +-
security/integrity/ima/ima_appraise.c | 5 +++++
2 files changed, 6 insertions(+), 1 deletion(-)
diff --git a/security/integrity/ima/Kconfig b/security/integrity/ima/Kconfig
index edde88dbe576..62dc11a5af01 100644
--- a/security/integrity/ima/Kconfig
+++ b/security/integrity/ima/Kconfig
@@ -232,7 +232,7 @@ config IMA_APPRAISE_REQUIRE_POLICY_SIGS
config IMA_APPRAISE_BOOTPARAM
bool "ima_appraise boot parameter"
- depends on IMA_APPRAISE && !IMA_ARCH_POLICY
+ depends on IMA_APPRAISE
default y
help
This option enables the different "ima_appraise=" modes
diff --git a/security/integrity/ima/ima_appraise.c b/security/integrity/ima/ima_appraise.c
index a9649b04b9f1..884de471b38a 100644
--- a/security/integrity/ima/ima_appraise.c
+++ b/security/integrity/ima/ima_appraise.c
@@ -19,6 +19,11 @@
static int __init default_appraise_setup(char *str)
{
#ifdef CONFIG_IMA_APPRAISE_BOOTPARAM
+ if (arch_ima_get_secureboot()) {
+ pr_info("appraise boot param ignored: secure boot enabled");
+ return 1;
+ }
+
if (strncmp(str, "off", 3) == 0)
ima_appraise = 0;
else if (strncmp(str, "log", 3) == 0)
--
2.26.2
The patch below does not apply to the 4.14-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 2315ec12ee8e8257bb335654c62e0cae71dc278d Mon Sep 17 00:00:00 2001
From: Kaike Wan <kaike.wan(a)intel.com>
Date: Tue, 23 Jun 2020 16:40:53 -0400
Subject: [PATCH] IB/hfi1: Do not destroy link_wq when the device is shut down
The workqueue link_wq should only be destroyed when the hfi1 driver is
unloaded, not when the device is shut down.
Fixes: 71d47008ca1b ("IB/hfi1: Create workqueue for link events")
Link: https://lore.kernel.org/r/20200623204053.107638.70315.stgit@awfm-01.aw.inte…
Cc: <stable(a)vger.kernel.org>
Reviewed-by: Mike Marciniszyn <mike.marciniszyn(a)intel.com>
Signed-off-by: Kaike Wan <kaike.wan(a)intel.com>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro(a)intel.com>
Signed-off-by: Jason Gunthorpe <jgg(a)nvidia.com>
diff --git a/drivers/infiniband/hw/hfi1/init.c b/drivers/infiniband/hw/hfi1/init.c
index 16d6788075f3..cb7ad1288821 100644
--- a/drivers/infiniband/hw/hfi1/init.c
+++ b/drivers/infiniband/hw/hfi1/init.c
@@ -846,6 +846,10 @@ static void destroy_workqueues(struct hfi1_devdata *dd)
destroy_workqueue(ppd->hfi1_wq);
ppd->hfi1_wq = NULL;
}
+ if (ppd->link_wq) {
+ destroy_workqueue(ppd->link_wq);
+ ppd->link_wq = NULL;
+ }
}
}
@@ -1122,14 +1126,10 @@ static void shutdown_device(struct hfi1_devdata *dd)
* We can't count on interrupts since we are stopping.
*/
hfi1_quiet_serdes(ppd);
-
if (ppd->hfi1_wq)
flush_workqueue(ppd->hfi1_wq);
- if (ppd->link_wq) {
+ if (ppd->link_wq)
flush_workqueue(ppd->link_wq);
- destroy_workqueue(ppd->link_wq);
- ppd->link_wq = NULL;
- }
}
sdma_exit(dd);
}
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>.
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
>From 2315ec12ee8e8257bb335654c62e0cae71dc278d Mon Sep 17 00:00:00 2001
From: Kaike Wan <kaike.wan(a)intel.com>
Date: Tue, 23 Jun 2020 16:40:53 -0400
Subject: [PATCH] IB/hfi1: Do not destroy link_wq when the device is shut down
The workqueue link_wq should only be destroyed when the hfi1 driver is
unloaded, not when the device is shut down.
Fixes: 71d47008ca1b ("IB/hfi1: Create workqueue for link events")
Link: https://lore.kernel.org/r/20200623204053.107638.70315.stgit@awfm-01.aw.inte…
Cc: <stable(a)vger.kernel.org>
Reviewed-by: Mike Marciniszyn <mike.marciniszyn(a)intel.com>
Signed-off-by: Kaike Wan <kaike.wan(a)intel.com>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro(a)intel.com>
Signed-off-by: Jason Gunthorpe <jgg(a)nvidia.com>
diff --git a/drivers/infiniband/hw/hfi1/init.c b/drivers/infiniband/hw/hfi1/init.c
index 16d6788075f3..cb7ad1288821 100644
--- a/drivers/infiniband/hw/hfi1/init.c
+++ b/drivers/infiniband/hw/hfi1/init.c
@@ -846,6 +846,10 @@ static void destroy_workqueues(struct hfi1_devdata *dd)
destroy_workqueue(ppd->hfi1_wq);
ppd->hfi1_wq = NULL;
}
+ if (ppd->link_wq) {
+ destroy_workqueue(ppd->link_wq);
+ ppd->link_wq = NULL;
+ }
}
}
@@ -1122,14 +1126,10 @@ static void shutdown_device(struct hfi1_devdata *dd)
* We can't count on interrupts since we are stopping.
*/
hfi1_quiet_serdes(ppd);
-
if (ppd->hfi1_wq)
flush_workqueue(ppd->hfi1_wq);
- if (ppd->link_wq) {
+ if (ppd->link_wq)
flush_workqueue(ppd->link_wq);
- destroy_workqueue(ppd->link_wq);
- ppd->link_wq = NULL;
- }
}
sdma_exit(dd);
}
With the recent addition of filesystem checksum types other than CRC32c,
it is not anymore hard-coded which checksum type a btrfs filesystem uses.
Up to now there is no good way to read the filesystem checksum, apart from
reading the filesystem UUID and then query sysfs for the checksum type.
Add a new csum_type and csum_size fields to the BTRFS_IOC_FS_INFO ioctl
command which usually is used to query filesystem features. Also add a
flags member indicating that the kernel responded with a set csum_type and
csum_size field.
For compatibility reasons, only return the csum_type and csum_size if
the BTRFS_FS_INFO_FLAG_CSUM_INFO flag was passed to the kernel. Also
clear any unknown flags so we don't pass false positives to user-space
newer than the kernel.
To simplify further additions to the ioctl, also switch the padding to a
u8 array. Pahole was used to verify the result of this switch:
pahole -C btrfs_ioctl_fs_info_args fs/btrfs/btrfs.ko
struct btrfs_ioctl_fs_info_args {
__u64 max_id; /* 0 8 */
__u64 num_devices; /* 8 8 */
__u8 fsid[16]; /* 16 16 */
__u32 nodesize; /* 32 4 */
__u32 sectorsize; /* 36 4 */
__u32 clone_alignment; /* 40 4 */
__u16 csum_type; /* 44 2 */
__u16 csum_size; /* 46 2 */
__u64 flags; /* 48 8 */
__u8 reserved[968]; /* 56 968 */
/* size: 1024, cachelines: 16, members: 10 */
};
Fixes: 3951e7f050ac ("btrfs: add xxhash64 to checksumming algorithms")
Fixes: 3831bf0094ab ("btrfs: add sha256 to checksumming algorithm")
CC: stable(a)vger.kernel.org # 5.5+
Signed-off-by: Johannes Thumshirn <johannes.thumshirn(a)wdc.com>
---
fs/btrfs/ioctl.c | 16 +++++++++++++---
include/uapi/linux/btrfs.h | 15 +++++++++++++--
2 files changed, 26 insertions(+), 5 deletions(-)
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index ab34179d7cbc..3a566cf71fc6 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -3217,11 +3217,15 @@ static long btrfs_ioctl_fs_info(struct btrfs_fs_info *fs_info,
struct btrfs_ioctl_fs_info_args *fi_args;
struct btrfs_device *device;
struct btrfs_fs_devices *fs_devices = fs_info->fs_devices;
+ u32 flags_in;
int ret = 0;
- fi_args = kzalloc(sizeof(*fi_args), GFP_KERNEL);
- if (!fi_args)
- return -ENOMEM;
+ fi_args = memdup_user(arg, sizeof(*fi_args));
+ if (IS_ERR(fi_args))
+ return PTR_ERR(fi_args);
+
+ flags_in = fi_args->flags;
+ memset(fi_args, 0, sizeof(*fi_args));
rcu_read_lock();
fi_args->num_devices = fs_devices->num_devices;
@@ -3237,6 +3241,12 @@ static long btrfs_ioctl_fs_info(struct btrfs_fs_info *fs_info,
fi_args->sectorsize = fs_info->sectorsize;
fi_args->clone_alignment = fs_info->sectorsize;
+ if (flags_in & BTRFS_FS_INFO_FLAG_CSUM_INFO) {
+ fi_args->csum_type = btrfs_super_csum_type(fs_info->super_copy);
+ fi_args->csum_size = btrfs_super_csum_size(fs_info->super_copy);
+ fi_args->flags |= BTRFS_FS_INFO_FLAG_CSUM_INFO;
+ }
+
if (copy_to_user(arg, fi_args, sizeof(*fi_args)))
ret = -EFAULT;
diff --git a/include/uapi/linux/btrfs.h b/include/uapi/linux/btrfs.h
index e6b6cb0f8bc6..b3e0af77642f 100644
--- a/include/uapi/linux/btrfs.h
+++ b/include/uapi/linux/btrfs.h
@@ -243,6 +243,13 @@ struct btrfs_ioctl_dev_info_args {
__u8 path[BTRFS_DEVICE_PATH_NAME_MAX]; /* out */
};
+/*
+ * Retrieve information about the filesystem
+ */
+
+/* Request information about checksum type and size */
+#define BTRFS_FS_INFO_FLAG_CSUM_INFO (1 << 0)
+
struct btrfs_ioctl_fs_info_args {
__u64 max_id; /* out */
__u64 num_devices; /* out */
@@ -250,10 +257,14 @@ struct btrfs_ioctl_fs_info_args {
__u32 nodesize; /* out */
__u32 sectorsize; /* out */
__u32 clone_alignment; /* out */
- __u32 reserved32;
- __u64 reserved[122]; /* pad to 1k */
+ /* See BTRFS_FS_INFO_FLAG_* */
+ __u16 csum_type; /* out */
+ __u16 csum_size; /* out */
+ __u64 flags; /* in/out */
+ __u8 reserved[968]; /* pad to 1k */
};
+
/*
* feature flags
*
--
2.26.2
BO will disable USB input until the device opens. This will
avoid garbage chars waiting flood the TTY. This mimics a real UART
device better.
For initial termios to reach USB core, USB driver has to be
registered before TTY driver.
Signed-off-by: Joakim Tjernlund <joakim.tjernlund(a)infinera.com>
Cc: stable(a)vger.kernel.org
---
I hope this change makes sense to you, if so I belive
ttyUSB could do the same.
drivers/usb/class/cdc-acm.c | 8 ++++----
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c
index 751f00285ee6..5680f71200e5 100644
--- a/drivers/usb/class/cdc-acm.c
+++ b/drivers/usb/class/cdc-acm.c
@@ -1999,19 +1999,19 @@ static int __init acm_init(void)
acm_tty_driver->subtype = SERIAL_TYPE_NORMAL,
acm_tty_driver->flags = TTY_DRIVER_REAL_RAW | TTY_DRIVER_DYNAMIC_DEV;
acm_tty_driver->init_termios = tty_std_termios;
- acm_tty_driver->init_termios.c_cflag = B9600 | CS8 | CREAD |
+ acm_tty_driver->init_termios.c_cflag = B0 | CS8 | CREAD |
HUPCL | CLOCAL;
tty_set_operations(acm_tty_driver, &acm_ops);
- retval = tty_register_driver(acm_tty_driver);
+ retval = usb_register(&acm_driver);
if (retval) {
put_tty_driver(acm_tty_driver);
return retval;
}
- retval = usb_register(&acm_driver);
+ retval = tty_register_driver(acm_tty_driver);
if (retval) {
- tty_unregister_driver(acm_tty_driver);
+ usb_deregister(&acm_driver);
put_tty_driver(acm_tty_driver);
return retval;
}
--
2.26.2
Since preempt-to-busy, we may unsubmit a request while it is still on
the HW and completes asynchronously. That means it may be retired and in
the process destroy the virtual engine (as the user has closed their
context), but that engine may still be holding onto the unsubmitted
compelted request. Therefore we need to potentially cleanup the old
request on destroying the virtual engine. We also have to keep the
virtual_engine alive until after the sibling's execlists_dequeue() have
finished peeking into the virtual engines, for which we serialise with
RCU.
Closes: https://gitlab.freedesktop.org/drm/intel/-/issues/2118
Fixes: 22b7a426bbe1 ("drm/i915/execlists: Preempt-to-busy")
References: 6d06779e8672 ("drm/i915: Load balancing across a virtual engine")
Signed-off-by: Chris Wilson <chris(a)chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin(a)intel.com>
Cc: <stable(a)vger.kernel.org> # v5.4+
---
drivers/gpu/drm/i915/gt/intel_lrc.c | 22 +++++++++++++++++++---
1 file changed, 19 insertions(+), 3 deletions(-)
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index cd4262cc96e2..8425fd917d75 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -179,6 +179,7 @@
#define EXECLISTS_REQUEST_SIZE 64 /* bytes */
struct virtual_engine {
+ struct rcu_head rcu;
struct intel_engine_cs base;
struct intel_context context;
@@ -5385,10 +5386,25 @@ static void virtual_context_destroy(struct kref *kref)
container_of(kref, typeof(*ve), context.ref);
unsigned int n;
- GEM_BUG_ON(!list_empty(virtual_queue(ve)));
- GEM_BUG_ON(ve->request);
GEM_BUG_ON(ve->context.inflight);
+ if (unlikely(ve->request)) {
+ struct i915_request *old;
+ unsigned long flags;
+
+ spin_lock_irqsave(&ve->base.active.lock, flags);
+
+ old = fetch_and_zero(&ve->request);
+ if (old) {
+ GEM_BUG_ON(!i915_request_completed(old));
+ __i915_request_submit(old);
+ i915_request_put(old);
+ }
+
+ spin_unlock_irqrestore(&ve->base.active.lock, flags);
+ }
+ GEM_BUG_ON(!list_empty(virtual_queue(ve)));
+
for (n = 0; n < ve->num_siblings; n++) {
struct intel_engine_cs *sibling = ve->siblings[n];
struct rb_node *node = &ve->nodes[sibling->id].rb;
@@ -5414,7 +5430,7 @@ static void virtual_context_destroy(struct kref *kref)
intel_engine_free_request_pool(&ve->base);
kfree(ve->bonds);
- kfree(ve);
+ kfree_rcu(ve, rcu);
}
static void virtual_engine_initial_hint(struct virtual_engine *ve)
--
2.20.1
We do not use the virtual engines for interrupts (they have physical
components), but we do use them to decouple the fence signaling during
submission. Currently, when we submit a completed request, we try to
enable the interrupt handler for the virtual engine, but we never disarm
it. A quick fix is then to mark the irq as enabled, and it will then
remain enabled -- and this prevents us from waking the device and never
letting it sleep again.
Fixes: f8db4d051b5e ("drm/i915: Initialise breadcrumb lists on the virtual engine")
Signed-off-by: Chris Wilson <chris(a)chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala(a)linux.intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin(a)intel.com>
Cc: <stable(a)vger.kernel.org> # v5.5+
---
drivers/gpu/drm/i915/gt/intel_lrc.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index cd4262cc96e2..504e269bb166 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -5727,6 +5727,7 @@ intel_execlists_create_virtual(struct intel_engine_cs **siblings,
intel_engine_init_active(&ve->base, ENGINE_VIRTUAL);
intel_engine_init_breadcrumbs(&ve->base);
intel_engine_init_execlists(&ve->base);
+ ve->base.breadcrumbs.irq_armed = true;
ve->base.cops = &virtual_context_ops;
ve->base.request_alloc = execlists_request_alloc;
--
2.20.1
From: Tom Rix <trix(a)redhat.com>
clang static analysis flags this error
lib/decompress_bunzip2.c:671:13: warning: Result of 'malloc' is converted
to a pointer of type 'unsigned int', which is incompatible with sizeof
operand type 'int' [unix.MallocSizeof]
bd->dbuf = large_malloc(bd->dbufSize * sizeof(int));
^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Reviewing the bunzip_data structure, the element dbuf is type
/* Intermediate buffer and its size (in bytes) */
unsigned int *dbuf, dbufSize;
So change the type in sizeof to 'unsigned int'
Fixes: bc22c17e12c1 ("bzip2/lzma: library support for gzip, bzip2 and lzma decompression")
Signed-off-by: Tom Rix <trix(a)redhat.com>
---
lib/decompress_bunzip2.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/lib/decompress_bunzip2.c b/lib/decompress_bunzip2.c
index 7c4932eed748..59ab76bda7a7 100644
--- a/lib/decompress_bunzip2.c
+++ b/lib/decompress_bunzip2.c
@@ -668,7 +668,7 @@ static int INIT start_bunzip(struct bunzip_data **bdp, void *inbuf, long len,
uncompressed data. Allocate intermediate buffer for block. */
bd->dbufSize = 100000*(i-BZh0);
- bd->dbuf = large_malloc(bd->dbufSize * sizeof(int));
+ bd->dbuf = large_malloc(bd->dbufSize * sizeof(unsigned int));
if (!bd->dbuf)
return RETVAL_OUT_OF_MEMORY;
return RETVAL_OK;
--
2.18.1
The patch titled
Subject: mm/hugetlb: avoid hardcoding while checking if cma is enabled
has been added to the -mm tree. Its filename is
mm-hugetlb-avoid-hardcoding-while-checking-if-cma-is-enabled.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/mm-hugetlb-avoid-hardcoding-while-…
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/mm-hugetlb-avoid-hardcoding-while-…
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next and is updated
there every 3-4 working days
------------------------------------------------------
From: Barry Song <song.bao.hua(a)hisilicon.com>
Subject: mm/hugetlb: avoid hardcoding while checking if cma is enabled
hugetlb_cma[0] can be NULL due to various reasons, for example, node0 has
no memory. so NULL hugetlb_cma[0] doesn't necessarily mean cma is not
enabled. gigantic pages might have been reserved on other nodes. This
patch fixes possible double reservation and CMA leak.
Link: http://lkml.kernel.org/r/20200710005726.36068-1-song.bao.hua@hisilicon.com
Fixes: cf11e85fc08c ("mm: hugetlb: optionally allocate gigantic hugepages using cma")
Signed-off-by: Barry Song <song.bao.hua(a)hisilicon.com>
Acked-by: Roman Gushchin <guro(a)fb.com>
Reviewed-by: Mike Kravetz <mike.kravetz(a)oracle.com>
Cc: Jonathan Cameron <jonathan.cameron(a)huawei.com>
Cc: <stable(a)vger.kernel.org>
Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org>
---
mm/hugetlb.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
--- a/mm/hugetlb.c~mm-hugetlb-avoid-hardcoding-while-checking-if-cma-is-enabled
+++ a/mm/hugetlb.c
@@ -46,6 +46,7 @@ unsigned int default_hstate_idx;
struct hstate hstates[HUGE_MAX_HSTATE];
static struct cma *hugetlb_cma[MAX_NUMNODES];
+static unsigned long hugetlb_cma_size __initdata;
/*
* Minimum page order among possible hugepage sizes, set to a proper value
@@ -2571,7 +2572,7 @@ static void __init hugetlb_hstate_alloc_
for (i = 0; i < h->max_huge_pages; ++i) {
if (hstate_is_gigantic(h)) {
- if (IS_ENABLED(CONFIG_CMA) && hugetlb_cma[0]) {
+ if (hugetlb_cma_size) {
pr_warn_once("HugeTLB: hugetlb_cma is enabled, skip boot time allocation\n");
break;
}
@@ -5654,7 +5655,6 @@ void move_hugetlb_state(struct page *old
}
#ifdef CONFIG_CMA
-static unsigned long hugetlb_cma_size __initdata;
static bool cma_reserve_called __initdata;
static int __init cmdline_parse_hugetlb_cma(char *p)
_
Patches currently in -mm which might be from song.bao.hua(a)hisilicon.com are
mm-hugetlb-avoid-hardcoding-while-checking-if-cma-is-enabled.patch
mm-hugetlb-split-hugetlb_cma-in-nodes-with-memory.patch
mm-cma-fix-the-name-of-cma-areas.patch
mm-hugetlb-fix-the-name-of-hugetlb-cma.patch
The patch titled
Subject: mm/hugetlb: avoid hardcoding while checking if cma is enabled
has been removed from the -mm tree. Its filename was
mm-hugetlb-avoid-hardcoding-while-checking-if-cma-is-enable.patch
This patch was dropped because an updated version will be merged
------------------------------------------------------
From: Barry Song <song.bao.hua(a)hisilicon.com>
Subject: mm/hugetlb: avoid hardcoding while checking if cma is enabled
hugetlb_cma[0] can be NULL due to various reasons, for example, node0 has
no memory. so NULL hugetlb_cma[0] doesn't necessarily mean cma is not
enabled. gigantic pages might have been reserved on other nodes.
Mike Kravetz said:
: Based on the code changes, I believe the following could happen:
: - Someone uses 'hugetlb_cma=' kernel command line parameter to reserve
: CMA for gigantic pages.
: - The system topology is such that no memory is on node 0. Therefore,
: no CMA can be reserved for gigantic pages on node 0. CMA is reserved
: on other nodes.
: - The user also specifies a number of gigantic pages to pre-allocate on
: the command line with hugepagesz=<gigantic_page_size> hugepages=<N>
: - The routine which allocates gigantic pages from the bootmem allocator
: will not detect CMA has been reserved as there is no memory on node 0.
: Therefore, pages will be pre-allocated from bootmem allocator as well
: as reserved in CMA.
:
: This double allocation (bootmem and CMA) is the worst case scenario. Not
: sure if this is what Barry saw, and I suspect this would rarely happen.
Link: http://lkml.kernel.org/r/20200707040204.30132-1-song.bao.hua@hisilicon.com
Fixes: cf11e85fc08c ("mm: hugetlb: optionally allocate gigantic hugepages using cma")
Signed-off-by: Barry Song <song.bao.hua(a)hisilicon.com>
Acked-by: Roman Gushchin <guro(a)fb.com>
Acked-by: Mike Rapoport <rppt(a)linux.ibm.com>
Cc: Mike Kravetz <mike.kravetz(a)oracle.com>
Cc: Jonathan Cameron <jonathan.cameron(a)huawei.com>
Cc: <stable(a)vger.kernel.org>
Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org>
---
mm/hugetlb.c | 16 +++++++++++++++-
1 file changed, 15 insertions(+), 1 deletion(-)
--- a/mm/hugetlb.c~mm-hugetlb-avoid-hardcoding-while-checking-if-cma-is-enable
+++ a/mm/hugetlb.c
@@ -2546,6 +2546,20 @@ static void __init gather_bootmem_preall
}
}
+bool __init hugetlb_cma_enabled(void)
+{
+#ifdef CONFIG_CMA
+ int node;
+
+ for_each_online_node(node) {
+ if (hugetlb_cma[node])
+ return true;
+ }
+#endif
+
+ return false;
+}
+
static void __init hugetlb_hstate_alloc_pages(struct hstate *h)
{
unsigned long i;
@@ -2571,7 +2585,7 @@ static void __init hugetlb_hstate_alloc_
for (i = 0; i < h->max_huge_pages; ++i) {
if (hstate_is_gigantic(h)) {
- if (IS_ENABLED(CONFIG_CMA) && hugetlb_cma[0]) {
+ if (hugetlb_cma_enabled()) {
pr_warn_once("HugeTLB: hugetlb_cma is enabled, skip boot time allocation\n");
break;
}
_
Patches currently in -mm which might be from song.bao.hua(a)hisilicon.com are
mm-hugetlb-split-hugetlb_cma-in-nodes-with-memory.patch
mm-cma-fix-the-name-of-cma-areas.patch
mm-hugetlb-fix-the-name-of-hugetlb-cma.patch
mm-hugetlb-avoid-hardcoding-while-checking-if-cma-is-enabled.patch
The patch titled
Subject: mm/memory_hotplug: fix unpaired mem_hotplug_begin/done
has been added to the -mm tree. Its filename is
mm-memory_hotplug-fix-unpaired-mem_hotplug_begin-done.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/mm-memory_hotplug-fix-unpaired-mem…
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/mm-memory_hotplug-fix-unpaired-mem…
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next and is updated
there every 3-4 working days
------------------------------------------------------
From: Jia He <justin.he(a)arm.com>
Subject: mm/memory_hotplug: fix unpaired mem_hotplug_begin/done
When check_memblock_offlined_cb() returns failed rc(e.g. the memblock is
online at that time), mem_hotplug_begin/done is unpaired in such case.
Therefore a warning:
Call Trace:
percpu_up_write+0x33/0x40
try_remove_memory+0x66/0x120
? _cond_resched+0x19/0x30
remove_memory+0x2b/0x40
dev_dax_kmem_remove+0x36/0x72 [kmem]
device_release_driver_internal+0xf0/0x1c0
device_release_driver+0x12/0x20
bus_remove_device+0xe1/0x150
device_del+0x17b/0x3e0
unregister_dev_dax+0x29/0x60
devm_action_release+0x15/0x20
release_nodes+0x19a/0x1e0
devres_release_all+0x3f/0x50
device_release_driver_internal+0x100/0x1c0
driver_detach+0x4c/0x8f
bus_remove_driver+0x5c/0xd0
driver_unregister+0x31/0x50
dax_pmem_exit+0x10/0xfe0 [dax_pmem]
Link: http://lkml.kernel.org/r/20200710031619.18762-3-justin.he@arm.com
Fixes: f1037ec0cc8a ("mm/memory_hotplug: fix remove_memory() lockdep splat")
Signed-off-by: Jia He <justin.he(a)arm.com>
Reviewed-by: David Hildenbrand <david(a)redhat.com>
Acked-by: Michal Hocko <mhocko(a)suse.com>
Acked-by: Dan Williams <dan.j.williams(a)intel.com>
Cc: <stable(a)vger.kernel.org> [5.6+]
Cc: Andy Lutomirski <luto(a)kernel.org>
Cc: Baoquan He <bhe(a)redhat.com>
Cc: Borislav Petkov <bp(a)alien8.de>
Cc: Catalin Marinas <catalin.marinas(a)arm.com>
Cc: Chuhong Yuan <hslester96(a)gmail.com>
Cc: Dave Hansen <dave.hansen(a)linux.intel.com>
Cc: Dave Jiang <dave.jiang(a)intel.com>
Cc: Fenghua Yu <fenghua.yu(a)intel.com>
Cc: "H. Peter Anvin" <hpa(a)zytor.com>
Cc: Ingo Molnar <mingo(a)redhat.com>
Cc: Jonathan Cameron <Jonathan.Cameron(a)Huawei.com>
Cc: Kaly Xin <Kaly.Xin(a)arm.com>
Cc: Logan Gunthorpe <logang(a)deltatee.com>
Cc: Masahiro Yamada <masahiroy(a)kernel.org>
Cc: Mike Rapoport <rppt(a)linux.ibm.com>
Cc: Peter Zijlstra <peterz(a)infradead.org>
Cc: Rich Felker <dalias(a)libc.org>
Cc: Thomas Gleixner <tglx(a)linutronix.de>
Cc: Tony Luck <tony.luck(a)intel.com>
Cc: Vishal Verma <vishal.l.verma(a)intel.com>
Cc: Will Deacon <will(a)kernel.org>
Cc: Yoshinori Sato <ysato(a)users.sourceforge.jp>
Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org>
---
mm/memory_hotplug.c | 5 ++---
1 file changed, 2 insertions(+), 3 deletions(-)
--- a/mm/memory_hotplug.c~mm-memory_hotplug-fix-unpaired-mem_hotplug_begin-done
+++ a/mm/memory_hotplug.c
@@ -1756,7 +1756,7 @@ static int __ref try_remove_memory(int n
*/
rc = walk_memory_blocks(start, size, NULL, check_memblock_offlined_cb);
if (rc)
- goto done;
+ return rc;
/* remove memmap entry */
firmware_map_remove(start, start + size, "System RAM");
@@ -1780,9 +1780,8 @@ static int __ref try_remove_memory(int n
try_offline_node(nid);
-done:
mem_hotplug_done();
- return rc;
+ return 0;
}
/**
_
Patches currently in -mm which might be from justin.he(a)arm.com are
mm-memory_hotplug-introduce-default-dummy-memory_add_physaddr_to_nid.patch
mm-memory_hotplug-fix-unpaired-mem_hotplug_begin-done.patch
VMA with VM_GROWSDOWN or VM_GROWSUP flag set can change their size under
mmap_read_lock(). It can lead to race with __do_munmap():
Thread A Thread B
__do_munmap()
detach_vmas_to_be_unmapped()
mmap_write_downgrade()
expand_downwards()
vma->vm_start = address;
// The VMA now overlaps with
// VMAs detached by the Thread A
// page fault populates expanded part
// of the VMA
unmap_region()
// Zaps pagetables partly
// populated by Thread B
Similar race exists for expand_upwards().
The fix is to avoid downgrading mmap_lock in __do_munmap() if detached
VMAs are next to VM_GROWSDOWN or VM_GROWSUP VMA.
Signed-off-by: Kirill A. Shutemov <kirill.shutemov(a)linux.intel.com>
Reported-by: Jann Horn <jannh(a)google.com>
Fixes: dd2283f2605e ("mm: mmap: zap pages with read mmap_sem in munmap")
Cc: <stable(a)vger.kernel.org> # 4.20
Cc: Yang Shi <yang.shi(a)linux.alibaba.com>
Cc: Vlastimil Babka <vbabka(a)suse.cz>
Cc: Oleg Nesterov <oleg(a)redhat.com>
Cc: Matthew Wilcox <willy(a)infradead.org>
---
mm/mmap.c | 16 ++++++++++++++--
1 file changed, 14 insertions(+), 2 deletions(-)
diff --git a/mm/mmap.c b/mm/mmap.c
index 59a4682ebf3f..71df4b36b42a 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -2620,7 +2620,7 @@ static void unmap_region(struct mm_struct *mm,
* Create a list of vma's touched by the unmap, removing them from the mm's
* vma list as we go..
*/
-static void
+static bool
detach_vmas_to_be_unmapped(struct mm_struct *mm, struct vm_area_struct *vma,
struct vm_area_struct *prev, unsigned long end)
{
@@ -2645,6 +2645,17 @@ detach_vmas_to_be_unmapped(struct mm_struct *mm, struct vm_area_struct *vma,
/* Kill the cache */
vmacache_invalidate(mm);
+
+ /*
+ * Do not downgrade mmap_sem if we are next to VM_GROWSDOWN or
+ * VM_GROWSUP VMA. Such VMAs can change their size under
+ * down_read(mmap_sem) and collide with the VMA we are about to unmap.
+ */
+ if (vma && (vma->vm_flags & VM_GROWSDOWN))
+ return false;
+ if (prev && (prev->vm_flags & VM_GROWSUP))
+ return false;
+ return true;
}
/*
@@ -2825,7 +2836,8 @@ int __do_munmap(struct mm_struct *mm, unsigned long start, size_t len,
}
/* Detach vmas from rbtree */
- detach_vmas_to_be_unmapped(mm, vma, prev, end);
+ if (!detach_vmas_to_be_unmapped(mm, vma, prev, end))
+ downgrade = false;
if (downgrade)
mmap_write_downgrade(mm);
--
2.26.2
Since clang does not push pc and sp in function prologues, the current
implementation of unwind_frame does not work. By using the previous
frame's lr/fp instead of saved pc/sp we get valid unwinds on clang-built
kernels.
The bounds check on next frame pointer must be changed as well since
there are 8 less bytes between frames.
This fixes /proc/<pid>/stack.
Link: https://github.com/ClangBuiltLinux/linux/issues/912
Reported-by: Miles Chen <miles.chen(a)mediatek.com>
Tested-by: Miles Chen <miles.chen(a)mediatek.com>
Cc: stable(a)vger.kernel.org
Reviewed-by: Nick Desaulniers <ndesaulniers(a)google.com>
Signed-off-by: Nathan Huckleberry <nhuck(a)google.com>
---
arch/arm/kernel/stacktrace.c | 24 ++++++++++++++++++++++++
1 file changed, 24 insertions(+)
diff --git a/arch/arm/kernel/stacktrace.c b/arch/arm/kernel/stacktrace.c
index cc726afea023..76ea4178a55c 100644
--- a/arch/arm/kernel/stacktrace.c
+++ b/arch/arm/kernel/stacktrace.c
@@ -22,6 +22,19 @@
* A simple function epilogue looks like this:
* ldm sp, {fp, sp, pc}
*
+ * When compiled with clang, pc and sp are not pushed. A simple function
+ * prologue looks like this when built with clang:
+ *
+ * stmdb {..., fp, lr}
+ * add fp, sp, #x
+ * sub sp, sp, #y
+ *
+ * A simple function epilogue looks like this when built with clang:
+ *
+ * sub sp, fp, #x
+ * ldm {..., fp, pc}
+ *
+ *
* Note that with framepointer enabled, even the leaf functions have the same
* prologue and epilogue, therefore we can ignore the LR value in this case.
*/
@@ -34,6 +47,16 @@ int notrace unwind_frame(struct stackframe *frame)
low = frame->sp;
high = ALIGN(low, THREAD_SIZE);
+#ifdef CONFIG_CC_IS_CLANG
+ /* check current frame pointer is within bounds */
+ if (fp < low + 4 || fp > high - 4)
+ return -EINVAL;
+
+ frame->sp = frame->fp;
+ frame->fp = *(unsigned long *)(fp);
+ frame->pc = frame->lr;
+ frame->lr = *(unsigned long *)(fp + 4);
+#else
/* check current frame pointer is within bounds */
if (fp < low + 12 || fp > high - 4)
return -EINVAL;
@@ -42,6 +65,7 @@ int notrace unwind_frame(struct stackframe *frame)
frame->fp = *(unsigned long *)(fp - 12);
frame->sp = *(unsigned long *)(fp - 8);
frame->pc = *(unsigned long *)(fp - 4);
+#endif
return 0;
}
--
2.27.0.212.ge8ba1cc988-goog
The drm/omap driver was fixed to correct an issue where using a
divider of 32 breaks the DSS despite the TRM stating 32 is a valid
number. Through experimentation, it appears that 31 works, and
it is consistent with the value used by the drm/omap driver.
This patch fixes the divider for fbdev driver instead of the drm.
Fixes: f76ee892a99e ("omapfb: copy omapdss & displays for omapfb")
Cc: <stable(a)vger.kernel.org> #4.9+
Signed-off-by: Adam Ford <aford173(a)gmail.com>
---
Linux 4.4 will need a similar patch, but it doesn't apply cleanly.
The DRM version of this same fix is:
e2c4ed148cf3 ("drm/omap: fix max fclk divider for omap36xx")
diff --git a/drivers/video/fbdev/omap2/omapfb/dss/dss.c b/drivers/video/fbdev/omap2/omapfb/dss/dss.c
index 7252d22dd117..bfc5c4c5a26a 100644
--- a/drivers/video/fbdev/omap2/omapfb/dss/dss.c
+++ b/drivers/video/fbdev/omap2/omapfb/dss/dss.c
@@ -833,7 +833,7 @@ static const struct dss_features omap34xx_dss_feats = {
};
static const struct dss_features omap3630_dss_feats = {
- .fck_div_max = 32,
+ .fck_div_max = 31,
.dss_fck_multiplier = 1,
.parent_clk_name = "dpll4_ck",
.dpi_select_source = &dss_dpi_select_source_omap2_omap3,
--
2.25.1
The kprobe show() functions were using "current"'s creds instead
of the file opener's creds for kallsyms visibility. Fix to use
seq_file->file->f_cred.
Cc: stable(a)vger.kernel.org
Fixes: 81365a947de4 ("kprobes: Show address of kprobes if kallsyms does")
Fixes: ffb9bd68ebdb ("kprobes: Show blacklist addresses as same as kallsyms does")
Signed-off-by: Kees Cook <keescook(a)chromium.org>
---
kernel/kprobes.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index d4de217e4a91..2e97febeef77 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -2448,7 +2448,7 @@ static void report_probe(struct seq_file *pi, struct kprobe *p,
else
kprobe_type = "k";
- if (!kallsyms_show_value(current_cred()))
+ if (!kallsyms_show_value(pi->file->f_cred))
addr = NULL;
if (sym)
@@ -2540,7 +2540,7 @@ static int kprobe_blacklist_seq_show(struct seq_file *m, void *v)
* If /proc/kallsyms is not showing kernel address, we won't
* show them here either.
*/
- if (!kallsyms_show_value(current_cred()))
+ if (!kallsyms_show_value(m->file->f_cred))
seq_printf(m, "0x%px-0x%px\t%ps\n", NULL, NULL,
(void *)ent->start_addr);
else
--
2.25.1
Hi
[This is an automated email]
This commit has been processed because it contains a -stable tag.
The stable tag indicates that it's relevant for the following trees: all
The bot has tested the following trees: v5.7.6, v5.4.49, v4.19.130, v4.14.186, v4.9.228, v4.4.228.
v5.7.6: Build OK!
v5.4.49: Build OK!
v4.19.130: Build OK!
v4.14.186: Build OK!
v4.9.228: Build OK!
v4.4.228: Failed to apply! Possible dependencies:
5d6c31910bc07 ("xattr: Add __vfs_{get,set,remove}xattr helpers")
6b2553918d8b4 ("replace ->follow_link() with new method that could stay in RCU mode")
aa80deab33a8f ("namei: page_getlink() and page_follow_link_light() are the same thing")
cd3417c8fc950 ("kill free_page_put_link()")
ce23e64013348 ("->getxattr(): pass dentry and inode as separate arguments")
fceef393a5381 ("switch ->get_link() to delayed_call, kill ->put_link()")
NOTE: The patch will not be queued to stable trees until it is upstream.
How should we proceed with this patch?
--
Thanks
Sasha
A recent LLVM 11 commit [1] made LLD stop implicitly coalescing some
temporary LLVM sections, namely .{data,bss}..compoundliteral.XXX:
[30] .data..compoundli PROGBITS ffffffff9ac9a000 19e9a000
000000000000cea0 0000000000000000 WA 0 0 32
[31] .rela.data..compo RELA 0000000000000000 40965440
0000000000001d88 0000000000000018 I 2238 30 8
[32] .data..compoundli PROGBITS ffffffff9aca6ea0 19ea6ea0
00000000000033c0 0000000000000000 WA 0 0 32
[33] .rela.data..compo RELA 0000000000000000 409671c8
0000000000000948 0000000000000018 I 2238 32 8
[...]
[2213] .bss..compoundlit NOBITS ffffffffa3000000 1d85c000
00000000000000a0 0000000000000000 WA 0 0 32
[2214] .bss..compoundlit NOBITS ffffffffa30000a0 1d85c000
0000000000000040 0000000000000000 WA 0 0 32
[...]
While these extra sections don't typically cause any breakage, they do
inflate the vmlinux size due to the overhead of storing metadata for
thousands of extra sections.
It's also worth noting that for some reason, some downstream Android
kernels can't boot at all if these sections aren't coalesced.
This issue isn't limited to any specific architecture; it affects arm64
and x86 if CONFIG_LD_DEAD_CODE_DATA_ELIMINATION is forced on.
Example on x86 allyesconfig:
Before: 2241 sections, 1170972 KiB
After: 56 sections, 1171169 KiB
[1] https://github.com/llvm/llvm-project/commit/9e33c096476ab5e02ab1c8442cc3cb4…
Link: https://github.com/ClangBuiltLinux/linux/issues/958
Cc: stable(a)vger.kernel.org # v4.4+
Suggested-by: Fangrui Song <maskray(a)google.com>
Signed-off-by: Danny Lin <danny(a)kdrag0n.dev>
---
include/asm-generic/vmlinux.lds.h | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index db600ef218d7..18968cba87c7 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -94,10 +94,10 @@
*/
#ifdef CONFIG_LD_DEAD_CODE_DATA_ELIMINATION
#define TEXT_MAIN .text .text.[0-9a-zA-Z_]*
-#define DATA_MAIN .data .data.[0-9a-zA-Z_]* .data..LPBX*
+#define DATA_MAIN .data .data.[0-9a-zA-Z_]* .data..LPBX* .data..compoundliteral*
#define SDATA_MAIN .sdata .sdata.[0-9a-zA-Z_]*
#define RODATA_MAIN .rodata .rodata.[0-9a-zA-Z_]*
-#define BSS_MAIN .bss .bss.[0-9a-zA-Z_]*
+#define BSS_MAIN .bss .bss.[0-9a-zA-Z_]* .bss..compoundliteral*
#define SBSS_MAIN .sbss .sbss.[0-9a-zA-Z_]*
#else
#define TEXT_MAIN .text
--
2.27.0
Sparse reports:
drivers/mfd/altera-sysmgr.c:150:30: warning: incorrect type in assignment (different address spaces)
drivers/mfd/altera-sysmgr.c:150:30: expected unsigned int [usertype] *base
drivers/mfd/altera-sysmgr.c:150:30: got void [noderef] <asn:2> *
drivers/mfd/altera-sysmgr.c:156:26: warning: incorrect type in argument 3 (different address spaces)
drivers/mfd/altera-sysmgr.c:156:26: expected void [noderef] <asn:2> *regs
drivers/mfd/altera-sysmgr.c:156:26: got unsigned int [usertype] *base
It appears as though the driver data property 'resource_size_t *base'
was being used to store 2 different types of addresses (physical and
IO-mapped) under a single declared type.
Fortunately, no value is recalled from the driver data entry, so it
can be easily omitted. Instead we can use the value obtained directly
from the platform resource to pass through Regmap into the call-backs
to be used for the SMCC call and use a local dedicated __iomem
variable for IO-remapping.
Cc: <stable(a)vger.kernel.org>
Cc: Thor Thayer <thor.thayer(a)linux.intel.com>
Signed-off-by: Lee Jones <lee.jones(a)linaro.org>
---
drivers/mfd/altera-sysmgr.c | 16 ++++++----------
1 file changed, 6 insertions(+), 10 deletions(-)
diff --git a/drivers/mfd/altera-sysmgr.c b/drivers/mfd/altera-sysmgr.c
index d2a13a547a3ca..83f0765f819b0 100644
--- a/drivers/mfd/altera-sysmgr.c
+++ b/drivers/mfd/altera-sysmgr.c
@@ -22,11 +22,9 @@
/**
* struct altr_sysmgr - Altera SOCFPGA System Manager
* @regmap: the regmap used for System Manager accesses.
- * @base : the base address for the System Manager
*/
struct altr_sysmgr {
struct regmap *regmap;
- resource_size_t *base;
};
static struct platform_driver altr_sysmgr_driver;
@@ -127,6 +125,7 @@ static int sysmgr_probe(struct platform_device *pdev)
struct regmap_config sysmgr_config = altr_sysmgr_regmap_cfg;
struct device *dev = &pdev->dev;
struct device_node *np = dev->of_node;
+ void __iomem *base;
sysmgr = devm_kzalloc(dev, sizeof(*sysmgr), GFP_KERNEL);
if (!sysmgr)
@@ -139,22 +138,19 @@ static int sysmgr_probe(struct platform_device *pdev)
sysmgr_config.max_register = resource_size(res) -
sysmgr_config.reg_stride;
if (of_device_is_compatible(np, "altr,sys-mgr-s10")) {
- /* Need physical address for SMCC call */
- sysmgr->base = (resource_size_t *)res->start;
sysmgr_config.reg_read = s10_protected_reg_read;
sysmgr_config.reg_write = s10_protected_reg_write;
- regmap = devm_regmap_init(dev, NULL, sysmgr->base,
+ /* Need physical address for SMCC call */
+ regmap = devm_regmap_init(dev, NULL, (void *)res->start,
&sysmgr_config);
} else {
- sysmgr->base = devm_ioremap(dev, res->start,
- resource_size(res));
- if (!sysmgr->base)
+ base = devm_ioremap(dev, res->start, resource_size(res));
+ if (!base)
return -ENOMEM;
sysmgr_config.max_register = res->end - res->start - 3;
- regmap = devm_regmap_init_mmio(dev, sysmgr->base,
- &sysmgr_config);
+ regmap = devm_regmap_init_mmio(dev, base, &sysmgr_config);
}
if (IS_ERR(regmap)) {
--
2.25.1