[patch added to 3.12-stable] libceph: set 'exists' flag for newly up osd

[patch added to 3.12-stable] libceph: set 'exists' flag for newly up osd

[Jiri Slaby]

From: Yan Zheng <zyan@redhat.com>

This patch has been added to the 3.12 stable tree. If you have any
objections, please let us know.

===============

commit 6dd74e44dc1df85f125982a8d6591bc4a76c9f5d upstream.

Signed-off-by: Yan Zheng <zyan@redhat.com>
Reviewed-by: Sage Weil <sage@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Cc: Ilya Dryomov <idryomov@gmail.com>
Signed-off-by: Jiri Slaby <jslaby@suse.cz>
---
 net/ceph/osdmap.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c
index 7ec4e0522215..6317b5d669e6 100644
--- a/net/ceph/osdmap.c
+++ b/net/ceph/osdmap.c
@@ -923,7 +923,7 @@ struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end,
 		ceph_decode_addr(&addr);
 		pr_info("osd%d up\n", osd);
 		BUG_ON(osd >= map->max_osd);
-		map->osd_state[osd] |= CEPH_OSD_UP;
+		map->osd_state[osd] |= CEPH_OSD_UP | CEPH_OSD_EXISTS;
 		map->osd_addr[osd] = addr;
 	}
 
-- 
2.9.2

[patch added to 3.12-stable] libceph: apply new_state before new_up_client on incrementals

[Jiri Slaby]

From: Ilya Dryomov <idryomov@gmail.com>

This patch has been added to the 3.12 stable tree. If you have any
objections, please let us know.

===============

commit 930c532869774ebf8af9efe9484c597f896a7d46 upstream.

Currently, osd_weight and osd_state fields are updated in the encoding
order.  This is wrong, because an incremental map may look like e.g.

    new_up_client: { osd=6, addr=... } # set osd_state and addr
    new_state: { osd=6, xorstate=EXISTS } # clear osd_state

Suppose osd6's current osd_state is EXISTS (i.e. osd6 is down).  After
applying new_up_client, osd_state is changed to EXISTS | UP.  Carrying
on with the new_state update, we flip EXISTS and leave osd6 in a weird
"!EXISTS but UP" state.  A non-existent OSD is considered down by the
mapping code

2087    for (i = 0; i < pg->pg_temp.len; i++) {
2088            if (ceph_osd_is_down(osdmap, pg->pg_temp.osds[i])) {
2089                    if (ceph_can_shift_osds(pi))
2090                            continue;
2091
2092                    temp->osds[temp->size++] = CRUSH_ITEM_NONE;

and so requests get directed to the second OSD in the set instead of
the first, resulting in OSD-side errors like:

[WRN] : client.4239 192.168.122.21:0/2444980242 misdirected client.4239.1:2827 pg 2.5df899f2 to osd.4 not [1,4,6] in e680/680

and hung rbds on the client:

[  493.566367] rbd: rbd0: write 400000 at 11cc00000 (0)
[  493.566805] rbd: rbd0:   result -6 xferred 400000
[  493.567011] blk_update_request: I/O error, dev rbd0, sector 9330688

The fix is to decouple application from the decoding and:
- apply new_weight first
- apply new_state before new_up_client
- twiddle osd_state flags if marking in
- clear out some of the state if osd is destroyed

Fixes: http://tracker.ceph.com/issues/14901

Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Reviewed-by: Josh Durgin <jdurgin@redhat.com>
[idryomov@gmail.com: backport to 3.10-3.14: strip primary-affinity]
Signed-off-by: Jiri Slaby <jslaby@suse.cz>
---
 net/ceph/osdmap.c | 152 ++++++++++++++++++++++++++++++++++++++----------------
 1 file changed, 108 insertions(+), 44 deletions(-)

diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c
index 6317b5d669e6..c1de8d404c47 100644
--- a/net/ceph/osdmap.c
+++ b/net/ceph/osdmap.c
@@ -798,6 +798,110 @@ bad:
 }
 
 /*
+ * Encoding order is (new_up_client, new_state, new_weight).  Need to
+ * apply in the (new_weight, new_state, new_up_client) order, because
+ * an incremental map may look like e.g.
+ *
+ *     new_up_client: { osd=6, addr=... } # set osd_state and addr
+ *     new_state: { osd=6, xorstate=EXISTS } # clear osd_state
+ */
+static int decode_new_up_state_weight(void **p, void *end,
+				      struct ceph_osdmap *map)
+{
+	void *new_up_client;
+	void *new_state;
+	void *new_weight_end;
+	u32 len;
+
+	new_up_client = *p;
+	ceph_decode_32_safe(p, end, len, e_inval);
+	len *= sizeof(u32) + sizeof(struct ceph_entity_addr);
+	ceph_decode_need(p, end, len, e_inval);
+	*p += len;
+
+	new_state = *p;
+	ceph_decode_32_safe(p, end, len, e_inval);
+	len *= sizeof(u32) + sizeof(u8);
+	ceph_decode_need(p, end, len, e_inval);
+	*p += len;
+
+	/* new_weight */
+	ceph_decode_32_safe(p, end, len, e_inval);
+	while (len--) {
+		s32 osd;
+		u32 w;
+
+		ceph_decode_need(p, end, 2*sizeof(u32), e_inval);
+		osd = ceph_decode_32(p);
+		w = ceph_decode_32(p);
+		BUG_ON(osd >= map->max_osd);
+		pr_info("osd%d weight 0x%x %s\n", osd, w,
+		     w == CEPH_OSD_IN ? "(in)" :
+		     (w == CEPH_OSD_OUT ? "(out)" : ""));
+		map->osd_weight[osd] = w;
+
+		/*
+		 * If we are marking in, set the EXISTS, and clear the
+		 * AUTOOUT and NEW bits.
+		 */
+		if (w) {
+			map->osd_state[osd] |= CEPH_OSD_EXISTS;
+			map->osd_state[osd] &= ~(CEPH_OSD_AUTOOUT |
+						 CEPH_OSD_NEW);
+		}
+	}
+	new_weight_end = *p;
+
+	/* new_state (up/down) */
+	*p = new_state;
+	len = ceph_decode_32(p);
+	while (len--) {
+		s32 osd;
+		u8 xorstate;
+
+		osd = ceph_decode_32(p);
+		xorstate = ceph_decode_8(p);
+		if (xorstate == 0)
+			xorstate = CEPH_OSD_UP;
+		BUG_ON(osd >= map->max_osd);
+		if ((map->osd_state[osd] & CEPH_OSD_UP) &&
+		    (xorstate & CEPH_OSD_UP))
+			pr_info("osd%d down\n", osd);
+		if ((map->osd_state[osd] & CEPH_OSD_EXISTS) &&
+		    (xorstate & CEPH_OSD_EXISTS)) {
+			pr_info("osd%d does not exist\n", osd);
+			map->osd_weight[osd] = CEPH_OSD_IN;
+			memset(map->osd_addr + osd, 0, sizeof(*map->osd_addr));
+			map->osd_state[osd] = 0;
+		} else {
+			map->osd_state[osd] ^= xorstate;
+		}
+	}
+
+	/* new_up_client */
+	*p = new_up_client;
+	len = ceph_decode_32(p);
+	while (len--) {
+		s32 osd;
+		struct ceph_entity_addr addr;
+
+		osd = ceph_decode_32(p);
+		ceph_decode_copy(p, &addr, sizeof(addr));
+		ceph_decode_addr(&addr);
+		BUG_ON(osd >= map->max_osd);
+		pr_info("osd%d up\n", osd);
+		map->osd_state[osd] |= CEPH_OSD_EXISTS | CEPH_OSD_UP;
+		map->osd_addr[osd] = addr;
+	}
+
+	*p = new_weight_end;
+	return 0;
+
+e_inval:
+	return -EINVAL;
+}
+
+/*
  * decode and apply an incremental map update.
  */
 struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end,
@@ -912,50 +1016,10 @@ struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end,
 			__remove_pg_pool(&map->pg_pools, pi);
 	}
 
-	/* new_up */
-	err = -EINVAL;
-	ceph_decode_32_safe(p, end, len, bad);
-	while (len--) {
-		u32 osd;
-		struct ceph_entity_addr addr;
-		ceph_decode_32_safe(p, end, osd, bad);
-		ceph_decode_copy_safe(p, end, &addr, sizeof(addr), bad);
-		ceph_decode_addr(&addr);
-		pr_info("osd%d up\n", osd);
-		BUG_ON(osd >= map->max_osd);
-		map->osd_state[osd] |= CEPH_OSD_UP | CEPH_OSD_EXISTS;
-		map->osd_addr[osd] = addr;
-	}
-
-	/* new_state */
-	ceph_decode_32_safe(p, end, len, bad);
-	while (len--) {
-		u32 osd;
-		u8 xorstate;
-		ceph_decode_32_safe(p, end, osd, bad);
-		xorstate = **(u8 **)p;
-		(*p)++;  /* clean flag */
-		if (xorstate == 0)
-			xorstate = CEPH_OSD_UP;
-		if (xorstate & CEPH_OSD_UP)
-			pr_info("osd%d down\n", osd);
-		if (osd < map->max_osd)
-			map->osd_state[osd] ^= xorstate;
-	}
-
-	/* new_weight */
-	ceph_decode_32_safe(p, end, len, bad);
-	while (len--) {
-		u32 osd, off;
-		ceph_decode_need(p, end, sizeof(u32)*2, bad);
-		osd = ceph_decode_32(p);
-		off = ceph_decode_32(p);
-		pr_info("osd%d weight 0x%x %s\n", osd, off,
-		     off == CEPH_OSD_IN ? "(in)" :
-		     (off == CEPH_OSD_OUT ? "(out)" : ""));
-		if (osd < map->max_osd)
-			map->osd_weight[osd] = off;
-	}
+	/* new_up_client, new_state, new_weight */
+	err = decode_new_up_state_weight(p, end, map);
+	if (err)
+		goto bad;
 
 	/* new_pg_temp */
 	ceph_decode_32_safe(p, end, len, bad);
-- 
2.9.2

[patch added to 3.12-stable] kvm: Fix irq route entries exceeding KVM_MAX_IRQ_ROUTES

[Jiri Slaby]

From: Xiubo Li <lixiubo@cmss.chinamobile.com>

This patch has been added to the 3.12 stable tree. If you have any
objections, please let us know.

===============

commit caf1ff26e1aa178133df68ac3d40815fed2187d9 upstream.

These days, we experienced one guest crash with 8 cores and 3 disks,
with qemu error logs as bellow:

qemu-system-x86_64: /build/qemu-2.0.0/kvm-all.c:984:
kvm_irqchip_commit_routes: Assertion `ret == 0' failed.

And then we found one patch(bdf026317d) in qemu tree, which said
could fix this bug.

Execute the following script will reproduce the BUG quickly:

irq_affinity.sh
========================================================================

vda_irq_num=25
vdb_irq_num=27
while [ 1 ]
do
    for irq in {1,2,4,8,10,20,40,80}
        do
            echo $irq > /proc/irq/$vda_irq_num/smp_affinity
            echo $irq > /proc/irq/$vdb_irq_num/smp_affinity
            dd if=/dev/vda of=/dev/zero bs=4K count=100 iflag=direct
            dd if=/dev/vdb of=/dev/zero bs=4K count=100 iflag=direct
        done
done
========================================================================

The following qemu log is added in the qemu code and is displayed when
this bug reproduced:

kvm_irqchip_commit_routes: max gsi: 1008, nr_allocated_irq_routes: 1024,
irq_routes->nr: 1024, gsi_count: 1024.

That's to say when irq_routes->nr == 1024, there are 1024 routing entries,
but in the kernel code when routes->nr >= 1024, will just return -EINVAL;

The nr is the number of the routing entries which is in of
[1 ~ KVM_MAX_IRQ_ROUTES], not the index in [0 ~ KVM_MAX_IRQ_ROUTES - 1].

This patch fix the BUG above.

Signed-off-by: Xiubo Li <lixiubo@cmss.chinamobile.com>
Signed-off-by: Wei Tang <tangwei@cmss.chinamobile.com>
Signed-off-by: Zhang Zhuoyu <zhangzhuoyu@cmss.chinamobile.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Jiri Slaby <jslaby@suse.cz>
---
 virt/kvm/kvm_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index f8a3dd96a37a..3351605d2608 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -2438,7 +2438,7 @@ static long kvm_vm_ioctl(struct file *filp,
 		if (copy_from_user(&routing, argp, sizeof(routing)))
 			goto out;
 		r = -EINVAL;
-		if (routing.nr >= KVM_MAX_IRQ_ROUTES)
+		if (routing.nr > KVM_MAX_IRQ_ROUTES)
 			goto out;
 		if (routing.flags)
 			goto out;
-- 
2.9.2

[patch added to 3.12-stable] tracing: Handle NULL formats in hold_module_trace_bprintk_format()

[Jiri Slaby]

From: "Steven Rostedt (Red Hat)" <rostedt@goodmis.org>

This patch has been added to the 3.12 stable tree. If you have any
objections, please let us know.

===============

commit 70c8217acd4383e069fe1898bbad36ea4fcdbdcc upstream.

If a task uses a non constant string for the format parameter in
trace_printk(), then the trace_printk_fmt variable is set to NULL. This
variable is then saved in the __trace_printk_fmt section.

The function hold_module_trace_bprintk_format() checks to see if duplicate
formats are used by modules, and reuses them if so (saves them to the list
if it is new). But this function calls lookup_format() that does a strcmp()
to the value (which is now NULL) and can cause a kernel oops.

This wasn't an issue till 3debb0a9ddb ("tracing: Fix trace_printk() to print
when not using bprintk()") which added "__used" to the trace_printk_fmt
variable, and before that, the kernel simply optimized it out (no NULL value
was saved).

The fix is simply to handle the NULL pointer in lookup_format() and have the
caller ignore the value if it was NULL.

Link: http://lkml.kernel.org/r/1464769870-18344-1-git-send-email-zhengjun.xing@intel.com

Reported-by: xingzhen <zhengjun.xing@intel.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Fixes: 3debb0a9ddb ("tracing: Fix trace_printk() to print when not using bprintk()")
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Jiri Slaby <jslaby@suse.cz>
---
 kernel/trace/trace_printk.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/kernel/trace/trace_printk.c b/kernel/trace/trace_printk.c
index 7b900474209d..6973eeca7d99 100644
--- a/kernel/trace/trace_printk.c
+++ b/kernel/trace/trace_printk.c
@@ -38,6 +38,10 @@ struct trace_bprintk_fmt {
 static inline struct trace_bprintk_fmt *lookup_format(const char *fmt)
 {
 	struct trace_bprintk_fmt *pos;
+
+	if (!fmt)
+		return ERR_PTR(-EINVAL);
+
 	list_for_each_entry(pos, &trace_bprintk_fmt_list, list) {
 		if (!strcmp(pos->fmt, fmt))
 			return pos;
@@ -59,7 +63,8 @@ void hold_module_trace_bprintk_format(const char **start, const char **end)
 	for (iter = start; iter < end; iter++) {
 		struct trace_bprintk_fmt *tb_fmt = lookup_format(*iter);
 		if (tb_fmt) {
-			*iter = tb_fmt->fmt;
+			if (!IS_ERR(tb_fmt))
+				*iter = tb_fmt->fmt;
 			continue;
 		}
 
-- 
2.9.2

[patch added to 3.12-stable] drm/radeon: fix asic initialization for virtualized environments

[Jiri Slaby]

From: Alex Deucher <alexander.deucher@amd.com>

This patch has been added to the 3.12 stable tree. If you have any
objections, please let us know.

===============

commit 05082b8bbd1a0ffc74235449c4b8930a8c240f85 upstream.

When executing in a PCI passthrough based virtuzliation environment, the
hypervisor will usually attempt to send a PCIe bus reset signal to the
ASIC when the VM reboots. In this scenario, the card is not correctly
initialized, but we still consider it to be posted. Therefore, in a
passthrough based environemnt we should always post the card to guarantee
it is in a good state for driver initialization.

Ported from amdgpu commit:
amdgpu: fix asic initialization for virtualized environments

Cc: Andres Rodriguez <andres.rodriguez@amd.com>
Cc: Alex Williamson <alex.williamson@redhat.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Jiri Slaby <jslaby@suse.cz>
---
 drivers/gpu/drm/radeon/radeon_device.c | 21 +++++++++++++++++++++
 1 file changed, 21 insertions(+)

diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c
index 8ca31266aa4a..b05ce8ac9bf4 100644
--- a/drivers/gpu/drm/radeon/radeon_device.c
+++ b/drivers/gpu/drm/radeon/radeon_device.c
@@ -540,6 +540,23 @@ void radeon_gtt_location(struct radeon_device *rdev, struct radeon_mc *mc)
 /*
  * GPU helpers function.
  */
+
+/**
+ * radeon_device_is_virtual - check if we are running is a virtual environment
+ *
+ * Check if the asic has been passed through to a VM (all asics).
+ * Used at driver startup.
+ * Returns true if virtual or false if not.
+ */
+static bool radeon_device_is_virtual(void)
+{
+#ifdef CONFIG_X86
+	return boot_cpu_has(X86_FEATURE_HYPERVISOR);
+#else
+	return false;
+#endif
+}
+
 /**
  * radeon_card_posted - check if the hw has already been initialized
  *
@@ -553,6 +570,10 @@ bool radeon_card_posted(struct radeon_device *rdev)
 {
 	uint32_t reg;
 
+	/* for pass through, always force asic_init */
+	if (radeon_device_is_virtual())
+		return false;
+
 	/* required for EFI mode on macbook2,1 which uses an r5xx asic */
 	if (efi_enabled(EFI_BOOT) &&
 	    (rdev->pdev->subsystem_vendor == PCI_VENDOR_ID_APPLE) &&
-- 
2.9.2

[patch added to 3.12-stable] drm/i915/ilk: Don't disable SSC source if it's in use

[Jiri Slaby]

From: Lyude <cpaul@redhat.com>

This patch has been added to the 3.12 stable tree. If you have any
objections, please let us know.

===============

commit 476490a945e1f0f6bd58e303058d2d8ca93a974c upstream.

Thanks to Ville Syrjälä for pointing me towards the cause of this issue.

Unfortunately one of the sideaffects of having the refclk for a DPLL set
to SSC is that as long as it's set to SSC, the GPU will prevent us from
powering down any of the pipes or transcoders using it. A couple of
BIOSes enable SSC in both PCH_DREF_CONTROL and in the DPLL
configurations. This causes issues on the first modeset, since we don't
expect SSC to be left on and as a result, can't successfully power down
the pipes or the transcoders using it. Here's an example from this Dell
OptiPlex 990:

[drm:intel_modeset_init] SSC enabled by BIOS, overriding VBT which says disabled
[drm:intel_modeset_init] 2 display pipes available.
[drm:intel_update_cdclk] Current CD clock rate: 400000 kHz
[drm:intel_update_max_cdclk] Max CD clock rate: 400000 kHz
[drm:intel_update_max_cdclk] Max dotclock rate: 360000 kHz
vgaarb: device changed decodes: PCI:0000:00:02.0,olddecodes=io+mem,decodes=io+mem:owns=io+mem
[drm:intel_crt_reset] crt adpa set to 0xf40000
[drm:intel_dp_init_connector] Adding DP connector on port C
[drm:intel_dp_aux_init] registering DPDDC-C bus for card0-DP-1
[drm:ironlake_init_pch_refclk] has_panel 0 has_lvds 0 has_ck505 0
[drm:ironlake_init_pch_refclk] Disabling SSC entirely
… later we try committing the first modeset …
[drm:intel_dump_pipe_config] [CRTC:26][modeset] config ffff88041b02e800 for pipe A
[drm:intel_dump_pipe_config] cpu_transcoder: A
…
[drm:intel_dump_pipe_config] dpll_hw_state: dpll: 0xc4016001, dpll_md: 0x0, fp0: 0x20e08, fp1: 0x30d07
[drm:intel_dump_pipe_config] planes on this crtc
[drm:intel_dump_pipe_config] STANDARD PLANE:23 plane: 0.0 idx: 0 enabled
[drm:intel_dump_pipe_config]     FB:42, fb = 800x600 format = 0x34325258
[drm:intel_dump_pipe_config]     scaler:0 src (0, 0) 800x600 dst (0, 0) 800x600
[drm:intel_dump_pipe_config] CURSOR PLANE:25 plane: 0.1 idx: 1 disabled, scaler_id = 0
[drm:intel_dump_pipe_config] STANDARD PLANE:27 plane: 0.1 idx: 2 disabled, scaler_id = 0
[drm:intel_get_shared_dpll] CRTC:26 allocated PCH DPLL A
[drm:intel_get_shared_dpll] using PCH DPLL A for pipe A
[drm:ilk_audio_codec_disable] Disable audio codec on port C, pipe A
[drm:intel_disable_pipe] disabling pipe A
------------[ cut here ]------------
WARNING: CPU: 1 PID: 130 at drivers/gpu/drm/i915/intel_display.c:1146 intel_disable_pipe+0x297/0x2d0 [i915]
pipe_off wait timed out
…
---[ end trace 94fc8aa03ae139e8 ]---
[drm:intel_dp_link_down]
[drm:ironlake_crtc_disable [i915]] *ERROR* failed to disable transcoder A

Later modesets succeed since they reset the DPLL's configuration anyway,
but this is enough to get stuck with a big fat warning in dmesg.

A better solution would be to add refcounts for the SSC source, but for
now leaving the source clock on should suffice.

Changes since v4:
 - Fix calculation of final for systems with LVDS panels (fixes BUG() on
   CI test suite)
Changes since v3:
 - Move temp variable into loop
 - Move checks for using_ssc_source to after we've figured out has_ck505
 - Add using_ssc_source to debug output
Changes since v2:
 - Fix debug output for when we disable the CPU source
Changes since v1:
 - Leave the SSC source clock on instead of just shutting it off on all
   of the DPLL configurations.

Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Lyude <cpaul@redhat.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: http://patchwork.freedesktop.org/patch/msgid/1465916649-10228-1-git-send-email-cpaul@redhat.com
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Jiri Slaby <jslaby@suse.cz>
---
 drivers/gpu/drm/i915/intel_display.c | 48 +++++++++++++++++++++++++-----------
 1 file changed, 34 insertions(+), 14 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index af46a33d8715..05f8b51cd42a 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -5126,12 +5126,14 @@ static void ironlake_init_pch_refclk(struct drm_device *dev)
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct drm_mode_config *mode_config = &dev->mode_config;
 	struct intel_encoder *encoder;
+	int i;
 	u32 val, final;
 	bool has_lvds = false;
 	bool has_cpu_edp = false;
 	bool has_panel = false;
 	bool has_ck505 = false;
 	bool can_ssc = false;
+	bool using_ssc_source = false;
 
 	/* We need to take the global config into account */
 	list_for_each_entry(encoder, &mode_config->encoder_list,
@@ -5157,8 +5159,22 @@ static void ironlake_init_pch_refclk(struct drm_device *dev)
 		can_ssc = true;
 	}
 
-	DRM_DEBUG_KMS("has_panel %d has_lvds %d has_ck505 %d\n",
-		      has_panel, has_lvds, has_ck505);
+	/* Check if any DPLLs are using the SSC source */
+	for (i = 0; i < dev_priv->num_shared_dpll; i++) {
+		u32 temp = I915_READ(PCH_DPLL(i));
+
+		if (!(temp & DPLL_VCO_ENABLE))
+			continue;
+
+		if ((temp & PLL_REF_INPUT_MASK) ==
+		    PLLB_REF_INPUT_SPREADSPECTRUMIN) {
+			using_ssc_source = true;
+			break;
+		}
+	}
+
+	DRM_DEBUG_KMS("has_panel %d has_lvds %d has_ck505 %d using_ssc_source %d\n",
+		      has_panel, has_lvds, has_ck505, using_ssc_source);
 
 	/* Ironlake: try to setup display ref clock before DPLL
 	 * enabling. This is only under driver's control after
@@ -5195,9 +5211,9 @@ static void ironlake_init_pch_refclk(struct drm_device *dev)
 				final |= DREF_CPU_SOURCE_OUTPUT_NONSPREAD;
 		} else
 			final |= DREF_CPU_SOURCE_OUTPUT_DISABLE;
-	} else {
-		final |= DREF_SSC_SOURCE_DISABLE;
-		final |= DREF_CPU_SOURCE_OUTPUT_DISABLE;
+	} else if (using_ssc_source) {
+		final |= DREF_SSC_SOURCE_ENABLE;
+		final |= DREF_SSC1_ENABLE;
 	}
 
 	if (final == val)
@@ -5244,7 +5260,7 @@ static void ironlake_init_pch_refclk(struct drm_device *dev)
 		POSTING_READ(PCH_DREF_CONTROL);
 		udelay(200);
 	} else {
-		DRM_DEBUG_KMS("Disabling SSC entirely\n");
+		DRM_DEBUG_KMS("Disabling CPU source output\n");
 
 		val &= ~DREF_CPU_SOURCE_OUTPUT_MASK;
 
@@ -5255,16 +5271,20 @@ static void ironlake_init_pch_refclk(struct drm_device *dev)
 		POSTING_READ(PCH_DREF_CONTROL);
 		udelay(200);
 
-		/* Turn off the SSC source */
-		val &= ~DREF_SSC_SOURCE_MASK;
-		val |= DREF_SSC_SOURCE_DISABLE;
+		if (!using_ssc_source) {
+			DRM_DEBUG_KMS("Disabling SSC source\n");
 
-		/* Turn off SSC1 */
-		val &= ~DREF_SSC1_ENABLE;
+			/* Turn off the SSC source */
+			val &= ~DREF_SSC_SOURCE_MASK;
+			val |= DREF_SSC_SOURCE_DISABLE;
 
-		I915_WRITE(PCH_DREF_CONTROL, val);
-		POSTING_READ(PCH_DREF_CONTROL);
-		udelay(200);
+			/* Turn off SSC1 */
+			val &= ~DREF_SSC1_ENABLE;
+
+			I915_WRITE(PCH_DREF_CONTROL, val);
+			POSTING_READ(PCH_DREF_CONTROL);
+			udelay(200);
+		}
 	}
 
 	BUG_ON(val != final);
-- 
2.9.2

[patch added to 3.12-stable] iio: Fix error handling in iio_trigger_attach_poll_func

[Jiri Slaby]

From: Crestez Dan Leonard <leonard.crestez@intel.com>

This patch has been added to the 3.12 stable tree. If you have any
objections, please let us know.

===============

commit 99543823357966ac938d9a310947e731b67338e6 upstream.

When attaching a pollfunc iio_trigger_attach_poll_func will allocate a
virtual irq and call the driver's set_trigger_state function. Fix error
handling to undo previous steps if any fails.

In particular this fixes handling errors from a driver's
set_trigger_state function. When using triggered buffers a failure to
enable the trigger used to make the buffer unusable.

Signed-off-by: Crestez Dan Leonard <leonard.crestez@intel.com>
Signed-off-by: Jonathan Cameron <jic23@kernel.org>
Signed-off-by: Jiri Slaby <jslaby@suse.cz>
---
 drivers/iio/industrialio-trigger.c | 23 ++++++++++++++++++-----
 1 file changed, 18 insertions(+), 5 deletions(-)

diff --git a/drivers/iio/industrialio-trigger.c b/drivers/iio/industrialio-trigger.c
index bf5e70a32d3f..08fb267bf31e 100644
--- a/drivers/iio/industrialio-trigger.c
+++ b/drivers/iio/industrialio-trigger.c
@@ -213,22 +213,35 @@ static int iio_trigger_attach_poll_func(struct iio_trigger *trig,
 
 	/* Prevent the module from being removed whilst attached to a trigger */
 	__module_get(pf->indio_dev->info->driver_module);
+
+	/* Get irq number */
 	pf->irq = iio_trigger_get_irq(trig);
+	if (pf->irq < 0)
+		goto out_put_module;
+
+	/* Request irq */
 	ret = request_threaded_irq(pf->irq, pf->h, pf->thread,
 				   pf->type, pf->name,
 				   pf);
-	if (ret < 0) {
-		module_put(pf->indio_dev->info->driver_module);
-		return ret;
-	}
+	if (ret < 0)
+		goto out_put_irq;
 
+	/* Enable trigger in driver */
 	if (trig->ops && trig->ops->set_trigger_state && notinuse) {
 		ret = trig->ops->set_trigger_state(trig, true);
 		if (ret < 0)
-			module_put(pf->indio_dev->info->driver_module);
+			goto out_free_irq;
 	}
 
 	return ret;
+
+out_free_irq:
+	free_irq(pf->irq, pf);
+out_put_irq:
+	iio_trigger_put_irq(trig, pf->irq);
+out_put_module:
+	module_put(pf->indio_dev->info->driver_module);
+	return ret;
 }
 
 static int iio_trigger_detach_poll_func(struct iio_trigger *trig,
-- 
2.9.2

[patch added to 3.12-stable] staging: iio: accel: fix error check

[Jiri Slaby]

From: Luis de Bethencourt <luisbg@osg.samsung.com>

This patch has been added to the 3.12 stable tree. If you have any
objections, please let us know.

===============

commit ef3149eb3ddb7f9125e11c90f8330e371b55cffd upstream.

sca3000_read_ctrl_reg() returns a negative number on failure, check for
this instead of zero.

Signed-off-by: Luis de Bethencourt <luisbg@osg.samsung.com>
Signed-off-by: Jonathan Cameron <jic23@kernel.org>
Signed-off-by: Jiri Slaby <jslaby@suse.cz>
---
 drivers/staging/iio/accel/sca3000_core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/staging/iio/accel/sca3000_core.c b/drivers/staging/iio/accel/sca3000_core.c
index 48a25ba290f5..162333d2fd00 100644
--- a/drivers/staging/iio/accel/sca3000_core.c
+++ b/drivers/staging/iio/accel/sca3000_core.c
@@ -588,7 +588,7 @@ static ssize_t sca3000_read_frequency(struct device *dev,
 		goto error_ret_mut;
 	ret = sca3000_read_ctrl_reg(st, SCA3000_REG_CTRL_SEL_OUT_CTRL);
 	mutex_unlock(&st->lock);
-	if (ret)
+	if (ret < 0)
 		goto error_ret;
 	val = ret;
 	if (base_freq > 0)
-- 
2.9.2

[patch added to 3.12-stable] iio: accel: kxsd9: fix the usage of spi_w8r8()

[Jiri Slaby]

From: Linus Walleij <linus.walleij@linaro.org>

This patch has been added to the 3.12 stable tree. If you have any
objections, please let us know.

===============

commit 0c1f91b98552da49d9d8eed32b3132a58d2f4598 upstream.

These two spi_w8r8() calls return a value with is used by the code
following the error check. The dubious use was caused by a cleanup
patch.

Fixes: d34dbee8ac8e ("staging:iio:accel:kxsd9 cleanup and conversion to iio_chan_spec.")
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Jonathan Cameron <jic23@kernel.org>
Signed-off-by: Jiri Slaby <jslaby@suse.cz>
---
 drivers/iio/accel/kxsd9.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/iio/accel/kxsd9.c b/drivers/iio/accel/kxsd9.c
index 34277153c211..61dcbcf73c22 100644
--- a/drivers/iio/accel/kxsd9.c
+++ b/drivers/iio/accel/kxsd9.c
@@ -81,7 +81,7 @@ static int kxsd9_write_scale(struct iio_dev *indio_dev, int micro)
 
 	mutex_lock(&st->buf_lock);
 	ret = spi_w8r8(st->us, KXSD9_READ(KXSD9_REG_CTRL_C));
-	if (ret)
+	if (ret < 0)
 		goto error_ret;
 	st->tx[0] = KXSD9_WRITE(KXSD9_REG_CTRL_C);
 	st->tx[1] = (ret & ~KXSD9_FS_MASK) | i;
@@ -163,7 +163,7 @@ static int kxsd9_read_raw(struct iio_dev *indio_dev,
 		break;
 	case IIO_CHAN_INFO_SCALE:
 		ret = spi_w8r8(st->us, KXSD9_READ(KXSD9_REG_CTRL_C));
-		if (ret)
+		if (ret < 0)
 			goto error_ret;
 		*val2 = kxsd9_micro_scales[ret & KXSD9_FS_MASK];
 		ret = IIO_VAL_INT_PLUS_MICRO;
-- 
2.9.2

[patch added to 3.12-stable] iio:ad7266: Fix broken regulator error handling

[Jiri Slaby]

From: Mark Brown <broonie@kernel.org>

This patch has been added to the 3.12 stable tree. If you have any
objections, please let us know.

===============

commit 6b7f4e25f3309f106a5c7ff42c8231494cf285d3 upstream.

All regulator_get() variants return either a pointer to a regulator or an
ERR_PTR() so testing for NULL makes no sense and may lead to bugs if we
use NULL as a valid regulator. Fix this by using IS_ERR() as expected.

Signed-off-by: Mark Brown <broonie@kernel.org>
Signed-off-by: Jonathan Cameron <jic23@kernel.org>
Signed-off-by: Jiri Slaby <jslaby@suse.cz>
---
 drivers/iio/adc/ad7266.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/iio/adc/ad7266.c b/drivers/iio/adc/ad7266.c
index 371731df1634..c9b150d39166 100644
--- a/drivers/iio/adc/ad7266.c
+++ b/drivers/iio/adc/ad7266.c
@@ -406,7 +406,7 @@ static int ad7266_probe(struct spi_device *spi)
 	st = iio_priv(indio_dev);
 
 	st->reg = devm_regulator_get(&spi->dev, "vref");
-	if (!IS_ERR_OR_NULL(st->reg)) {
+	if (!IS_ERR(st->reg)) {
 		ret = regulator_enable(st->reg);
 		if (ret)
 			return ret;
-- 
2.9.2

[patch added to 3.12-stable] iio:ad7266: Fix support for optional regulators

[Jiri Slaby]

From: Mark Brown <broonie@kernel.org>

This patch has been added to the 3.12 stable tree. If you have any
objections, please let us know.

===============

commit e5511c816e5ac4909bdd38e85ac344e2b9b8e984 upstream.

The ad7266 driver attempts to support deciding between the use of internal
and external power supplies by checking to see if an error is returned when
requesting the regulator. This doesn't work with the current code since the
driver uses a normal regulator_get() which is for non-optional supplies
and so assumes that if a regulator is not provided by the platform then
this is a bug in the platform integration and so substitutes a dummy
regulator. Use regulator_get_optional() instead which indicates to the
framework that the regulator may be absent and provides a dummy regulator
instead.

Signed-off-by: Mark Brown <broonie@kernel.org>
Signed-off-by: Jonathan Cameron <jic23@kernel.org>
Signed-off-by: Jiri Slaby <jslaby@suse.cz>
---
 drivers/iio/adc/ad7266.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/iio/adc/ad7266.c b/drivers/iio/adc/ad7266.c
index c9b150d39166..5154041257c2 100644
--- a/drivers/iio/adc/ad7266.c
+++ b/drivers/iio/adc/ad7266.c
@@ -405,7 +405,7 @@ static int ad7266_probe(struct spi_device *spi)
 
 	st = iio_priv(indio_dev);
 
-	st->reg = devm_regulator_get(&spi->dev, "vref");
+	st->reg = devm_regulator_get_optional(&spi->dev, "vref");
 	if (!IS_ERR(st->reg)) {
 		ret = regulator_enable(st->reg);
 		if (ret)
-- 
2.9.2

[patch added to 3.12-stable] iio:ad7266: Fix probe deferral for vref

[Jiri Slaby]

From: Mark Brown <broonie@kernel.org>

This patch has been added to the 3.12 stable tree. If you have any
objections, please let us know.

===============

commit 68b356eb3d9f5e38910fb62e22a78e2a18d544ae upstream.

Currently the ad7266 driver treats any failure to get vref as though the
regulator were not present but this means that if probe deferral is
triggered the driver will act as though the regulator were not present.
Instead only use the internal reference if we explicitly got -ENODEV which
is what is returned for absent regulators.

Signed-off-by: Mark Brown <broonie@kernel.org>
Signed-off-by: Jonathan Cameron <jic23@kernel.org>
Signed-off-by: Jiri Slaby <jslaby@suse.cz>
---
 drivers/iio/adc/ad7266.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/iio/adc/ad7266.c b/drivers/iio/adc/ad7266.c
index 5154041257c2..1094bdfcfa6e 100644
--- a/drivers/iio/adc/ad7266.c
+++ b/drivers/iio/adc/ad7266.c
@@ -417,6 +417,9 @@ static int ad7266_probe(struct spi_device *spi)
 
 		st->vref_uv = ret;
 	} else {
+		/* Any other error indicates that the regulator does exist */
+		if (PTR_ERR(st->reg) != -ENODEV)
+			return PTR_ERR(st->reg);
 		/* Use internal reference */
 		st->vref_uv = 2500000;
 	}
-- 
2.9.2

[patch added to 3.12-stable] tty/vt/keyboard: fix OOB access in do_compute_shiftstate()

[Jiri Slaby]

From: Dmitry Torokhov <dmitry.torokhov@gmail.com>

This patch has been added to the 3.12 stable tree. If you have any
objections, please let us know.

===============

commit 510cccb5b0c8868a2b302a0ab524da7912da648b upstream.

The size of individual keymap in drivers/tty/vt/keyboard.c is NR_KEYS,
which is currently 256, whereas number of keys/buttons in input device (and
therefor in key_down) is much larger - KEY_CNT - 768, and that can cause
out-of-bound access when we do

	sym = U(key_maps[0][k]);

with large 'k'.

To fix it we should not attempt iterating beyond smaller of NR_KEYS and
KEY_CNT.

Also while at it let's switch to for_each_set_bit() instead of open-coding
it.

Reported-by: Sasha Levin <sasha.levin@oracle.com>
Reviewed-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Signed-off-by: Jiri Slaby <jslaby@suse.cz>
---
 drivers/tty/vt/keyboard.c | 30 +++++++++---------------------
 1 file changed, 9 insertions(+), 21 deletions(-)

diff --git a/drivers/tty/vt/keyboard.c b/drivers/tty/vt/keyboard.c
index d0e3a4497707..adf4d3124cc6 100644
--- a/drivers/tty/vt/keyboard.c
+++ b/drivers/tty/vt/keyboard.c
@@ -365,34 +365,22 @@ static void to_utf8(struct vc_data *vc, uint c)
 
 static void do_compute_shiftstate(void)
 {
-	unsigned int i, j, k, sym, val;
+	unsigned int k, sym, val;
 
 	shift_state = 0;
 	memset(shift_down, 0, sizeof(shift_down));
 
-	for (i = 0; i < ARRAY_SIZE(key_down); i++) {
-
-		if (!key_down[i])
+	for_each_set_bit(k, key_down, min(NR_KEYS, KEY_CNT)) {
+		sym = U(key_maps[0][k]);
+		if (KTYP(sym) != KT_SHIFT && KTYP(sym) != KT_SLOCK)
 			continue;
 
-		k = i * BITS_PER_LONG;
-
-		for (j = 0; j < BITS_PER_LONG; j++, k++) {
-
-			if (!test_bit(k, key_down))
-				continue;
+		val = KVAL(sym);
+		if (val == KVAL(K_CAPSSHIFT))
+			val = KVAL(K_SHIFT);
 
-			sym = U(key_maps[0][k]);
-			if (KTYP(sym) != KT_SHIFT && KTYP(sym) != KT_SLOCK)
-				continue;
-
-			val = KVAL(sym);
-			if (val == KVAL(K_CAPSSHIFT))
-				val = KVAL(K_SHIFT);
-
-			shift_down[val]++;
-			shift_state |= (1 << val);
-		}
+		shift_down[val]++;
+		shift_state |= BIT(val);
 	}
 }
 
-- 
2.9.2

[patch added to 3.12-stable] ALSA: dummy: Fix a use-after-free at closing

[Jiri Slaby]

From: Takashi Iwai <tiwai@suse.de>

This patch has been added to the 3.12 stable tree. If you have any
objections, please let us know.

===============

commit d5dbbe6569481bf12dcbe3e12cff72c5f78d272c upstream.

syzkaller fuzzer spotted a potential use-after-free case in snd-dummy
driver when hrtimer is used as backend:
> ==================================================================
> BUG: KASAN: use-after-free in rb_erase+0x1b17/0x2010 at addr ffff88005e5b6f68
>  Read of size 8 by task syz-executor/8984
> =============================================================================
> BUG kmalloc-192 (Not tainted): kasan: bad access detected
> -----------------------------------------------------------------------------
>
> Disabling lock debugging due to kernel taint
> INFO: Allocated in 0xbbbbbbbbbbbbbbbb age=18446705582212484632
> ....
> [<      none      >] dummy_hrtimer_create+0x49/0x1a0 sound/drivers/dummy.c:464
> ....
> INFO: Freed in 0xfffd8e09 age=18446705496313138713 cpu=2164287125 pid=-1
> [<      none      >] dummy_hrtimer_free+0x68/0x80 sound/drivers/dummy.c:481
> ....
> Call Trace:
>  [<ffffffff8179e59e>] __asan_report_load8_noabort+0x3e/0x40 mm/kasan/report.c:333
>  [<     inline     >] rb_set_parent include/linux/rbtree_augmented.h:111
>  [<     inline     >] __rb_erase_augmented include/linux/rbtree_augmented.h:218
>  [<ffffffff82ca5787>] rb_erase+0x1b17/0x2010 lib/rbtree.c:427
>  [<ffffffff82cb02e8>] timerqueue_del+0x78/0x170 lib/timerqueue.c:86
>  [<ffffffff814d0c80>] __remove_hrtimer+0x90/0x220 kernel/time/hrtimer.c:903
>  [<     inline     >] remove_hrtimer kernel/time/hrtimer.c:945
>  [<ffffffff814d23da>] hrtimer_try_to_cancel+0x22a/0x570 kernel/time/hrtimer.c:1046
>  [<ffffffff814d2742>] hrtimer_cancel+0x22/0x40 kernel/time/hrtimer.c:1066
>  [<ffffffff85420531>] dummy_hrtimer_stop+0x91/0xb0 sound/drivers/dummy.c:417
>  [<ffffffff854228bf>] dummy_pcm_trigger+0x17f/0x1e0 sound/drivers/dummy.c:507
>  [<ffffffff85392170>] snd_pcm_do_stop+0x160/0x1b0 sound/core/pcm_native.c:1106
>  [<ffffffff85391b26>] snd_pcm_action_single+0x76/0x120 sound/core/pcm_native.c:956
>  [<ffffffff85391e01>] snd_pcm_action+0x231/0x290 sound/core/pcm_native.c:974
>  [<     inline     >] snd_pcm_stop sound/core/pcm_native.c:1139
>  [<ffffffff8539754d>] snd_pcm_drop+0x12d/0x1d0 sound/core/pcm_native.c:1784
>  [<ffffffff8539d3be>] snd_pcm_common_ioctl1+0xfae/0x2150 sound/core/pcm_native.c:2805
>  [<ffffffff8539ee91>] snd_pcm_capture_ioctl1+0x2a1/0x5e0 sound/core/pcm_native.c:2976
>  [<ffffffff8539f2ec>] snd_pcm_kernel_ioctl+0x11c/0x160 sound/core/pcm_native.c:3020
>  [<ffffffff853d9a44>] snd_pcm_oss_sync+0x3a4/0xa30 sound/core/oss/pcm_oss.c:1693
>  [<ffffffff853da27d>] snd_pcm_oss_release+0x1ad/0x280 sound/core/oss/pcm_oss.c:2483
>  .....

A workaround is to call hrtimer_cancel() in dummy_hrtimer_sync() which
is called certainly before other blocking ops.

Reported-by: Dmitry Vyukov <dvyukov@google.com>
Tested-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Signed-off-by: Jiri Slaby <jslaby@suse.cz>
---
 sound/drivers/dummy.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/drivers/dummy.c b/sound/drivers/dummy.c
index 8946cef245fc..fe5750a05368 100644
--- a/sound/drivers/dummy.c
+++ b/sound/drivers/dummy.c
@@ -422,6 +422,7 @@ static int dummy_hrtimer_stop(struct snd_pcm_substream *substream)
 
 static inline void dummy_hrtimer_sync(struct dummy_hrtimer_pcm *dpcm)
 {
+	hrtimer_cancel(&dpcm->timer);
 	tasklet_kill(&dpcm->tasklet);
 }
 
-- 
2.9.2

[patch added to 3.12-stable] ALSA: au88x0: Fix calculation in vortex_wtdma_bufshift()

[Jiri Slaby]

From: Takashi Iwai <tiwai@suse.de>

This patch has been added to the 3.12 stable tree. If you have any
objections, please let us know.

===============

commit 62db7152c924e4c060e42b34a69cd39658e8a0dc upstream.

vortex_wtdma_bufshift() function does calculate the page index
wrongly, first masking then shift, which always results in zero.
The proper computation is to first shift, then mask.

Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Signed-off-by: Jiri Slaby <jslaby@suse.cz>
---
 sound/pci/au88x0/au88x0_core.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/sound/pci/au88x0/au88x0_core.c b/sound/pci/au88x0/au88x0_core.c
index ae59dbaa53d9..42d4b13f1fa7 100644
--- a/sound/pci/au88x0/au88x0_core.c
+++ b/sound/pci/au88x0/au88x0_core.c
@@ -1442,9 +1442,8 @@ static int vortex_wtdma_bufshift(vortex_t * vortex, int wtdma)
 	int page, p, pp, delta, i;
 
 	page =
-	    (hwread(vortex->mmio, VORTEX_WTDMA_STAT + (wtdma << 2)) &
-	     WT_SUBBUF_MASK)
-	    >> WT_SUBBUF_SHIFT;
+	    (hwread(vortex->mmio, VORTEX_WTDMA_STAT + (wtdma << 2))
+	     >> WT_SUBBUF_SHIFT) & WT_SUBBUF_MASK;
 	if (dma->nr_periods >= 4)
 		delta = (page - dma->period_real) & 3;
 	else {
-- 
2.9.2

[patch added to 3.12-stable] ALSA: ctl: Stop notification after disconnection

[Jiri Slaby]

From: Takashi Iwai <tiwai@suse.de>

This patch has been added to the 3.12 stable tree. If you have any
objections, please let us know.

===============

commit f388cdcdd160687c6650833f286b9c89c50960ff upstream.

snd_ctl_remove() has a notification for the removal event.  It's
superfluous when done during the device got disconnected.  Although
the notification itself is mostly harmless, it may potentially be
harmful, and should be suppressed.  Actually some components PCM may
free ctl elements during the disconnect or free callbacks, thus it's
no theoretical issue.

This patch adds the check of card->shutdown flag for avoiding
unnecessary notifications after (or during) the disconnect.

Signed-off-by: Takashi Iwai <tiwai@suse.de>
Signed-off-by: Jiri Slaby <jslaby@suse.cz>
---
 sound/core/control.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/sound/core/control.c b/sound/core/control.c
index 3fcead61f0ef..251bc575f5c3 100644
--- a/sound/core/control.c
+++ b/sound/core/control.c
@@ -150,6 +150,8 @@ void snd_ctl_notify(struct snd_card *card, unsigned int mask,
 	
 	if (snd_BUG_ON(!card || !id))
 		return;
+	if (card->shutdown)
+		return;
 	read_lock(&card->ctl_files_rwlock);
 #if defined(CONFIG_SND_MIXER_OSS) || defined(CONFIG_SND_MIXER_OSS_MODULE)
 	card->mixer_oss_change_count++;
-- 
2.9.2

[patch added to 3.12-stable] scsi: fix race between simultaneous decrements of ->host_failed

[Jiri Slaby]

From: Wei Fang <fangwei1@huawei.com>

This patch has been added to the 3.12 stable tree. If you have any
objections, please let us know.

===============

commit 72d8c36ec364c82bf1bf0c64dfa1041cfaf139f7 upstream.

sas_ata_strategy_handler() adds the works of the ata error handler to
system_unbound_wq. This workqueue asynchronously runs work items, so the
ata error handler will be performed concurrently on different CPUs. In
this case, ->host_failed will be decreased simultaneously in
scsi_eh_finish_cmd() on different CPUs, and become abnormal.

It will lead to permanently inequality between ->host_failed and
->host_busy, and scsi error handler thread won't start running. IO
errors after that won't be handled.

Since all scmds must have been handled in the strategy handler, just
remove the decrement in scsi_eh_finish_cmd() and zero ->host_busy after
the strategy handler to fix this race.

Fixes: 50824d6c5657 ("[SCSI] libsas: async ata-eh")
Signed-off-by: Wei Fang <fangwei1@huawei.com>
Reviewed-by: James Bottomley <jejb@linux.vnet.ibm.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Jiri Slaby <jslaby@suse.cz>
---
 Documentation/scsi/scsi_eh.txt | 8 ++++++--
 drivers/ata/libata-eh.c        | 2 +-
 drivers/scsi/scsi_error.c      | 4 +++-
 3 files changed, 10 insertions(+), 4 deletions(-)

diff --git a/Documentation/scsi/scsi_eh.txt b/Documentation/scsi/scsi_eh.txt
index 6ff16b620d84..c08b62d63afa 100644
--- a/Documentation/scsi/scsi_eh.txt
+++ b/Documentation/scsi/scsi_eh.txt
@@ -255,19 +255,23 @@ scmd->allowed.
 
  3. scmd recovered
     ACTION: scsi_eh_finish_cmd() is invoked to EH-finish scmd
-	- shost->host_failed--
 	- clear scmd->eh_eflags
 	- scsi_setup_cmd_retry()
 	- move from local eh_work_q to local eh_done_q
     LOCKING: none
+    CONCURRENCY: at most one thread per separate eh_work_q to
+		 keep queue manipulation lockless
 
  4. EH completes
     ACTION: scsi_eh_flush_done_q() retries scmds or notifies upper
-	    layer of failure.
+	    layer of failure. May be called concurrently but must have
+	    a no more than one thread per separate eh_work_q to
+	    manipulate the queue locklessly
 	- scmd is removed from eh_done_q and scmd->eh_entry is cleared
 	- if retry is necessary, scmd is requeued using
           scsi_queue_insert()
 	- otherwise, scsi_finish_command() is invoked for scmd
+	- zero shost->host_failed
     LOCKING: queue or finish function performs appropriate locking
 
 
diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c
index 063036d876b0..126eb86f239f 100644
--- a/drivers/ata/libata-eh.c
+++ b/drivers/ata/libata-eh.c
@@ -604,7 +604,7 @@ void ata_scsi_error(struct Scsi_Host *host)
 	ata_scsi_port_error_handler(host, ap);
 
 	/* finish or retry handled scmd's and clean up */
-	WARN_ON(host->host_failed || !list_empty(&eh_work_q));
+	WARN_ON(!list_empty(&eh_work_q));
 
 	DPRINTK("EXIT\n");
 }
diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c
index ff2689d01209..bb40359ba620 100644
--- a/drivers/scsi/scsi_error.c
+++ b/drivers/scsi/scsi_error.c
@@ -960,7 +960,6 @@ static int scsi_request_sense(struct scsi_cmnd *scmd)
  */
 void scsi_eh_finish_cmd(struct scsi_cmnd *scmd, struct list_head *done_q)
 {
-	scmd->device->host->host_failed--;
 	scmd->eh_eflags = 0;
 	list_move_tail(&scmd->eh_entry, done_q);
 }
@@ -1949,6 +1948,9 @@ int scsi_error_handler(void *data)
 		else
 			scsi_unjam_host(shost);
 
+		/* All scmds have been handled */
+		shost->host_failed = 0;
+
 		/*
 		 * Note - if the above fails completely, the action is to take
 		 * individual devices offline and flush the queue of any
-- 
2.9.2

[patch added to 3.12-stable] Fix reconnect to not defer smb3 session reconnect long after socket reconnect

[Jiri Slaby]

From: Steve French <smfrench@gmail.com>

This patch has been added to the 3.12 stable tree. If you have any
objections, please let us know.

===============

commit 4fcd1813e6404dd4420c7d12fb483f9320f0bf93 upstream.

Azure server blocks clients that open a socket and don't do anything on it.
In our reconnect scenarios, we can reconnect the tcp session and
detect the socket is available but we defer the negprot and SMB3 session
setup and tree connect reconnection until the next i/o is requested, but
this looks suspicous to some servers who expect SMB3 negprog and session
setup soon after a socket is created.

In the echo thread, reconnect SMB3 sessions and tree connections
that are disconnected.  A later patch will replay persistent (and
resilient) handle opens.

Signed-off-by: Steve French <steve.french@primarydata.com>
Acked-by: Pavel Shilovsky <pshilovsky@samba.org>
Signed-off-by: Jiri Slaby <jslaby@suse.cz>
---
 fs/cifs/connect.c |  4 +++-
 fs/cifs/smb2pdu.c | 27 +++++++++++++++++++++++++++
 2 files changed, 30 insertions(+), 1 deletion(-)

diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index ebad721656f3..7bdcf8fbc1ff 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -410,7 +410,9 @@ cifs_echo_request(struct work_struct *work)
 	 * server->ops->need_neg() == true. Also, no need to ping if
 	 * we got a response recently.
 	 */
-	if (!server->ops->need_neg || server->ops->need_neg(server) ||
+
+	if (server->tcpStatus == CifsNeedReconnect ||
+	    server->tcpStatus == CifsExiting || server->tcpStatus == CifsNew ||
 	    (server->ops->can_echo && !server->ops->can_echo(server)) ||
 	    time_before(jiffies, server->lstrp + SMB_ECHO_INTERVAL - HZ))
 		goto requeue_echo;
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index 439cb86ed488..609350a69680 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -1552,6 +1552,33 @@ SMB2_echo(struct TCP_Server_Info *server)
 
 	cifs_dbg(FYI, "In echo request\n");
 
+	if (server->tcpStatus == CifsNeedNegotiate) {
+		struct list_head *tmp, *tmp2;
+		struct cifs_ses *ses;
+		struct cifs_tcon *tcon;
+
+		cifs_dbg(FYI, "Need negotiate, reconnecting tcons\n");
+		spin_lock(&cifs_tcp_ses_lock);
+		list_for_each(tmp, &server->smb_ses_list) {
+			ses = list_entry(tmp, struct cifs_ses, smb_ses_list);
+			list_for_each(tmp2, &ses->tcon_list) {
+				tcon = list_entry(tmp2, struct cifs_tcon,
+						  tcon_list);
+				/* add check for persistent handle reconnect */
+				if (tcon && tcon->need_reconnect) {
+					spin_unlock(&cifs_tcp_ses_lock);
+					rc = smb2_reconnect(SMB2_ECHO, tcon);
+					spin_lock(&cifs_tcp_ses_lock);
+				}
+			}
+		}
+		spin_unlock(&cifs_tcp_ses_lock);
+	}
+
+	/* if no session, renegotiate failed above */
+	if (server->tcpStatus == CifsNeedNegotiate)
+		return -EIO;
+
 	rc = small_smb2_init(SMB2_ECHO, NULL, (void **)&req);
 	if (rc)
 		return rc;
-- 
2.9.2

[patch added to 3.12-stable] xen/acpi: allow xen-acpi-processor driver to load on Xen 4.7

[Jiri Slaby]

From: Jan Beulich <JBeulich@suse.com>

This patch has been added to the 3.12 stable tree. If you have any
objections, please let us know.

===============

commit 6f2d9d99213514360034c6d52d2c3919290b3504 upstream.

As of Xen 4.7 PV CPUID doesn't expose either of CPUID[1].ECX[7] and
CPUID[0x80000007].EDX[7] anymore, causing the driver to fail to load on
both Intel and AMD systems. Doing any kind of hardware capability
checks in the driver as a prerequisite was wrong anyway: With the
hypervisor being in charge, all such checking should be done by it. If
ACPI data gets uploaded despite some missing capability, the hypervisor
is free to ignore part or all of that data.

Ditch the entire check_prereq() function, and do the only valid check
(xen_initial_domain()) in the caller in its place.

Signed-off-by: Jan Beulich <jbeulich@suse.com>
Signed-off-by: David Vrabel <david.vrabel@citrix.com>
Signed-off-by: Jiri Slaby <jslaby@suse.cz>
---
 drivers/xen/xen-acpi-processor.c | 35 +++--------------------------------
 1 file changed, 3 insertions(+), 32 deletions(-)

diff --git a/drivers/xen/xen-acpi-processor.c b/drivers/xen/xen-acpi-processor.c
index 13bc6c31c060..77658030259e 100644
--- a/drivers/xen/xen-acpi-processor.c
+++ b/drivers/xen/xen-acpi-processor.c
@@ -425,36 +425,7 @@ upload:
 
 	return 0;
 }
-static int __init check_prereq(void)
-{
-	struct cpuinfo_x86 *c = &cpu_data(0);
-
-	if (!xen_initial_domain())
-		return -ENODEV;
-
-	if (!acpi_gbl_FADT.smi_command)
-		return -ENODEV;
-
-	if (c->x86_vendor == X86_VENDOR_INTEL) {
-		if (!cpu_has(c, X86_FEATURE_EST))
-			return -ENODEV;
 
-		return 0;
-	}
-	if (c->x86_vendor == X86_VENDOR_AMD) {
-		/* Copied from powernow-k8.h, can't include ../cpufreq/powernow
-		 * as we get compile warnings for the static functions.
-		 */
-#define CPUID_FREQ_VOLT_CAPABILITIES    0x80000007
-#define USE_HW_PSTATE                   0x00000080
-		u32 eax, ebx, ecx, edx;
-		cpuid(CPUID_FREQ_VOLT_CAPABILITIES, &eax, &ebx, &ecx, &edx);
-		if ((edx & USE_HW_PSTATE) != USE_HW_PSTATE)
-			return -ENODEV;
-		return 0;
-	}
-	return -ENODEV;
-}
 /* acpi_perf_data is a pointer to percpu data. */
 static struct acpi_processor_performance __percpu *acpi_perf_data;
 
@@ -510,10 +481,10 @@ static struct syscore_ops xap_syscore_ops = {
 static int __init xen_acpi_processor_init(void)
 {
 	unsigned int i;
-	int rc = check_prereq();
+	int rc;
 
-	if (rc)
-		return rc;
+	if (!xen_initial_domain())
+		return -ENODEV;
 
 	nr_acpi_bits = get_max_acpi_id() + 1;
 	acpi_ids_done = kcalloc(BITS_TO_LONGS(nr_acpi_bits), sizeof(unsigned long), GFP_KERNEL);
-- 
2.9.2