[PATCH AUTOSEL 4.9 01/20] perf/x86/intel/ds: Fix EVENT vs. UEVENT PEBS constraints

[PATCH AUTOSEL 4.9 01/20] perf/x86/intel/ds: Fix EVENT vs. UEVENT PEBS constraints

[Sasha Levin]

From: Stephane Eranian <eranian@google.com>

[ Upstream commit 23e3983a466cd540ffdd2bbc6e0c51e31934f941 ]

This patch fixes an bug revealed by the following commit:

  6b89d4c1ae85 ("perf/x86/intel: Fix INTEL_FLAGS_EVENT_CONSTRAINT* masking")

That patch modified INTEL_FLAGS_EVENT_CONSTRAINT() to only look at the event code
when matching a constraint. If code+umask were needed, then the
INTEL_FLAGS_UEVENT_CONSTRAINT() macro was needed instead.
This broke with some of the constraints for PEBS events.

Several of them, including the one used for cycles:p, cycles:pp, cycles:ppp
fell in that category and caused the event to be rejected in PEBS mode.
In other words, on some platforms a cmdline such as:

  $ perf top -e cycles:pp

would fail with -EINVAL.

This patch fixes this bug by properly using INTEL_FLAGS_UEVENT_CONSTRAINT()
when needed in the PEBS constraint tables.

Reported-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Stephane Eranian <eranian@google.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Cc: kan.liang@intel.com
Link: http://lkml.kernel.org/r/20190521005246.423-1-eranian@google.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/x86/events/intel/ds.c | 28 ++++++++++++++--------------
 1 file changed, 14 insertions(+), 14 deletions(-)

diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index f26e26e4d84f..ad31c01f810f 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -655,7 +655,7 @@ struct event_constraint intel_core2_pebs_event_constraints[] = {
 	INTEL_FLAGS_UEVENT_CONSTRAINT(0x1fc7, 0x1), /* SIMD_INST_RETURED.ANY */
 	INTEL_FLAGS_EVENT_CONSTRAINT(0xcb, 0x1),    /* MEM_LOAD_RETIRED.* */
 	/* INST_RETIRED.ANY_P, inv=1, cmask=16 (cycles:p). */
-	INTEL_FLAGS_EVENT_CONSTRAINT(0x108000c0, 0x01),
+	INTEL_FLAGS_UEVENT_CONSTRAINT(0x108000c0, 0x01),
 	EVENT_CONSTRAINT_END
 };
 
@@ -664,7 +664,7 @@ struct event_constraint intel_atom_pebs_event_constraints[] = {
 	INTEL_FLAGS_UEVENT_CONSTRAINT(0x00c5, 0x1), /* MISPREDICTED_BRANCH_RETIRED */
 	INTEL_FLAGS_EVENT_CONSTRAINT(0xcb, 0x1),    /* MEM_LOAD_RETIRED.* */
 	/* INST_RETIRED.ANY_P, inv=1, cmask=16 (cycles:p). */
-	INTEL_FLAGS_EVENT_CONSTRAINT(0x108000c0, 0x01),
+	INTEL_FLAGS_UEVENT_CONSTRAINT(0x108000c0, 0x01),
 	/* Allow all events as PEBS with no flags */
 	INTEL_ALL_EVENT_CONSTRAINT(0, 0x1),
 	EVENT_CONSTRAINT_END
@@ -672,7 +672,7 @@ struct event_constraint intel_atom_pebs_event_constraints[] = {
 
 struct event_constraint intel_slm_pebs_event_constraints[] = {
 	/* INST_RETIRED.ANY_P, inv=1, cmask=16 (cycles:p). */
-	INTEL_FLAGS_EVENT_CONSTRAINT(0x108000c0, 0x1),
+	INTEL_FLAGS_UEVENT_CONSTRAINT(0x108000c0, 0x1),
 	/* Allow all events as PEBS with no flags */
 	INTEL_ALL_EVENT_CONSTRAINT(0, 0x1),
 	EVENT_CONSTRAINT_END
@@ -697,7 +697,7 @@ struct event_constraint intel_nehalem_pebs_event_constraints[] = {
 	INTEL_FLAGS_EVENT_CONSTRAINT(0xcb, 0xf),    /* MEM_LOAD_RETIRED.* */
 	INTEL_FLAGS_EVENT_CONSTRAINT(0xf7, 0xf),    /* FP_ASSIST.* */
 	/* INST_RETIRED.ANY_P, inv=1, cmask=16 (cycles:p). */
-	INTEL_FLAGS_EVENT_CONSTRAINT(0x108000c0, 0x0f),
+	INTEL_FLAGS_UEVENT_CONSTRAINT(0x108000c0, 0x0f),
 	EVENT_CONSTRAINT_END
 };
 
@@ -714,7 +714,7 @@ struct event_constraint intel_westmere_pebs_event_constraints[] = {
 	INTEL_FLAGS_EVENT_CONSTRAINT(0xcb, 0xf),    /* MEM_LOAD_RETIRED.* */
 	INTEL_FLAGS_EVENT_CONSTRAINT(0xf7, 0xf),    /* FP_ASSIST.* */
 	/* INST_RETIRED.ANY_P, inv=1, cmask=16 (cycles:p). */
-	INTEL_FLAGS_EVENT_CONSTRAINT(0x108000c0, 0x0f),
+	INTEL_FLAGS_UEVENT_CONSTRAINT(0x108000c0, 0x0f),
 	EVENT_CONSTRAINT_END
 };
 
@@ -723,7 +723,7 @@ struct event_constraint intel_snb_pebs_event_constraints[] = {
 	INTEL_PLD_CONSTRAINT(0x01cd, 0x8),    /* MEM_TRANS_RETIRED.LAT_ABOVE_THR */
 	INTEL_PST_CONSTRAINT(0x02cd, 0x8),    /* MEM_TRANS_RETIRED.PRECISE_STORES */
 	/* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */
-	INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c2, 0xf),
+	INTEL_FLAGS_UEVENT_CONSTRAINT(0x108001c2, 0xf),
         INTEL_EXCLEVT_CONSTRAINT(0xd0, 0xf),    /* MEM_UOP_RETIRED.* */
         INTEL_EXCLEVT_CONSTRAINT(0xd1, 0xf),    /* MEM_LOAD_UOPS_RETIRED.* */
         INTEL_EXCLEVT_CONSTRAINT(0xd2, 0xf),    /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */
@@ -738,9 +738,9 @@ struct event_constraint intel_ivb_pebs_event_constraints[] = {
         INTEL_PLD_CONSTRAINT(0x01cd, 0x8),    /* MEM_TRANS_RETIRED.LAT_ABOVE_THR */
 	INTEL_PST_CONSTRAINT(0x02cd, 0x8),    /* MEM_TRANS_RETIRED.PRECISE_STORES */
 	/* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */
-	INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c2, 0xf),
+	INTEL_FLAGS_UEVENT_CONSTRAINT(0x108001c2, 0xf),
 	/* INST_RETIRED.PREC_DIST, inv=1, cmask=16 (cycles:ppp). */
-	INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c0, 0x2),
+	INTEL_FLAGS_UEVENT_CONSTRAINT(0x108001c0, 0x2),
 	INTEL_EXCLEVT_CONSTRAINT(0xd0, 0xf),    /* MEM_UOP_RETIRED.* */
 	INTEL_EXCLEVT_CONSTRAINT(0xd1, 0xf),    /* MEM_LOAD_UOPS_RETIRED.* */
 	INTEL_EXCLEVT_CONSTRAINT(0xd2, 0xf),    /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */
@@ -754,9 +754,9 @@ struct event_constraint intel_hsw_pebs_event_constraints[] = {
 	INTEL_FLAGS_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PRECDIST */
 	INTEL_PLD_CONSTRAINT(0x01cd, 0xf),    /* MEM_TRANS_RETIRED.* */
 	/* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */
-	INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c2, 0xf),
+	INTEL_FLAGS_UEVENT_CONSTRAINT(0x108001c2, 0xf),
 	/* INST_RETIRED.PREC_DIST, inv=1, cmask=16 (cycles:ppp). */
-	INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c0, 0x2),
+	INTEL_FLAGS_UEVENT_CONSTRAINT(0x108001c0, 0x2),
 	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_NA(0x01c2, 0xf), /* UOPS_RETIRED.ALL */
 	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_XLD(0x11d0, 0xf), /* MEM_UOPS_RETIRED.STLB_MISS_LOADS */
 	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_XLD(0x21d0, 0xf), /* MEM_UOPS_RETIRED.LOCK_LOADS */
@@ -777,9 +777,9 @@ struct event_constraint intel_bdw_pebs_event_constraints[] = {
 	INTEL_FLAGS_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PRECDIST */
 	INTEL_PLD_CONSTRAINT(0x01cd, 0xf),    /* MEM_TRANS_RETIRED.* */
 	/* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */
-	INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c2, 0xf),
+	INTEL_FLAGS_UEVENT_CONSTRAINT(0x108001c2, 0xf),
 	/* INST_RETIRED.PREC_DIST, inv=1, cmask=16 (cycles:ppp). */
-	INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c0, 0x2),
+	INTEL_FLAGS_UEVENT_CONSTRAINT(0x108001c0, 0x2),
 	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_NA(0x01c2, 0xf), /* UOPS_RETIRED.ALL */
 	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x11d0, 0xf), /* MEM_UOPS_RETIRED.STLB_MISS_LOADS */
 	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x21d0, 0xf), /* MEM_UOPS_RETIRED.LOCK_LOADS */
@@ -800,9 +800,9 @@ struct event_constraint intel_bdw_pebs_event_constraints[] = {
 struct event_constraint intel_skl_pebs_event_constraints[] = {
 	INTEL_FLAGS_UEVENT_CONSTRAINT(0x1c0, 0x2),	/* INST_RETIRED.PREC_DIST */
 	/* INST_RETIRED.PREC_DIST, inv=1, cmask=16 (cycles:ppp). */
-	INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c0, 0x2),
+	INTEL_FLAGS_UEVENT_CONSTRAINT(0x108001c0, 0x2),
 	/* INST_RETIRED.TOTAL_CYCLES_PS (inv=1, cmask=16) (cycles:p). */
-	INTEL_FLAGS_EVENT_CONSTRAINT(0x108000c0, 0x0f),
+	INTEL_FLAGS_UEVENT_CONSTRAINT(0x108000c0, 0x0f),
 	INTEL_PLD_CONSTRAINT(0x1cd, 0xf),		      /* MEM_TRANS_RETIRED.* */
 	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x11d0, 0xf), /* MEM_INST_RETIRED.STLB_MISS_LOADS */
 	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x12d0, 0xf), /* MEM_INST_RETIRED.STLB_MISS_STORES */
-- 
2.20.1

[PATCH AUTOSEL 4.9 02/20] selftests: netfilter: missing error check when setting up veth interface

[Sasha Levin]

From: Jeffrin Jose T <jeffrin@rajagiritech.edu.in>

[ Upstream commit 82ce6eb1dd13fd12e449b2ee2c2ec051e6f52c43 ]

A test for the basic NAT functionality uses ip command which needs veth
device. There is a condition where the kernel support for veth is not
compiled into the kernel and the test script breaks. This patch contains
code for reasonable error display and correct code exit.

Signed-off-by: Jeffrin Jose T <jeffrin@rajagiritech.edu.in>
Acked-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 tools/testing/selftests/netfilter/nft_nat.sh | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/netfilter/nft_nat.sh b/tools/testing/selftests/netfilter/nft_nat.sh
index 8ec76681605c..f25f72a75cf3 100755
--- a/tools/testing/selftests/netfilter/nft_nat.sh
+++ b/tools/testing/selftests/netfilter/nft_nat.sh
@@ -23,7 +23,11 @@ ip netns add ns0
 ip netns add ns1
 ip netns add ns2
 
-ip link add veth0 netns ns0 type veth peer name eth0 netns ns1
+ip link add veth0 netns ns0 type veth peer name eth0 netns ns1 > /dev/null 2>&1
+if [ $? -ne 0 ];then
+    echo "SKIP: No virtual ethernet pair device support in kernel"
+    exit $ksft_skip
+fi
 ip link add veth1 netns ns0 type veth peer name eth0 netns ns2
 
 ip -net ns0 link set lo up
-- 
2.20.1

[PATCH AUTOSEL 4.9 03/20] mISDN: make sure device name is NUL terminated

[Sasha Levin]

From: Dan Carpenter <dan.carpenter@oracle.com>

[ Upstream commit ccfb62f27beb295103e9392462b20a6ed807d0ea ]

The user can change the device_name with the IMSETDEVNAME ioctl, but we
need to ensure that the user's name is NUL terminated.  Otherwise it
could result in a buffer overflow when we copy the name back to the user
with IMGETDEVINFO ioctl.

I also changed two strcpy() calls which handle the name to strscpy().
Hopefully, there aren't any other ways to create a too long name, but
it's nice to do this as a kernel hardening measure.

Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/isdn/mISDN/socket.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/isdn/mISDN/socket.c b/drivers/isdn/mISDN/socket.c
index f96b8f2bdf74..d7c986fb0b3b 100644
--- a/drivers/isdn/mISDN/socket.c
+++ b/drivers/isdn/mISDN/socket.c
@@ -394,7 +394,7 @@ data_sock_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
 			memcpy(di.channelmap, dev->channelmap,
 			       sizeof(di.channelmap));
 			di.nrbchan = dev->nrbchan;
-			strcpy(di.name, dev_name(&dev->dev));
+			strscpy(di.name, dev_name(&dev->dev), sizeof(di.name));
 			if (copy_to_user((void __user *)arg, &di, sizeof(di)))
 				err = -EFAULT;
 		} else
@@ -678,7 +678,7 @@ base_sock_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
 			memcpy(di.channelmap, dev->channelmap,
 			       sizeof(di.channelmap));
 			di.nrbchan = dev->nrbchan;
-			strcpy(di.name, dev_name(&dev->dev));
+			strscpy(di.name, dev_name(&dev->dev), sizeof(di.name));
 			if (copy_to_user((void __user *)arg, &di, sizeof(di)))
 				err = -EFAULT;
 		} else
@@ -692,6 +692,7 @@ base_sock_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
 			err = -EFAULT;
 			break;
 		}
+		dn.name[sizeof(dn.name) - 1] = '\0';
 		dev = get_mdevice(dn.id);
 		if (dev)
 			err = device_rename(&dev->dev, dn.name);
-- 
2.20.1

[PATCH AUTOSEL 4.9 04/20] x86/CPU/AMD: Don't force the CPB cap when running under a hypervisor

[Sasha Levin]

From: Frank van der Linden <fllinden@amazon.com>

[ Upstream commit 2ac44ab608705948564791ce1d15d43ba81a1e38 ]

For F17h AMD CPUs, the CPB capability ('Core Performance Boost') is forcibly set,
because some versions of that chip incorrectly report that they do not have it.

However, a hypervisor may filter out the CPB capability, for good
reasons. For example, KVM currently does not emulate setting the CPB
bit in MSR_K7_HWCR, and unchecked MSR access errors will be thrown
when trying to set it as a guest:

	unchecked MSR access error: WRMSR to 0xc0010015 (tried to write 0x0000000001000011) at rIP: 0xffffffff890638f4 (native_write_msr+0x4/0x20)

	Call Trace:
	boost_set_msr+0x50/0x80 [acpi_cpufreq]
	cpuhp_invoke_callback+0x86/0x560
	sort_range+0x20/0x20
	cpuhp_thread_fun+0xb0/0x110
	smpboot_thread_fn+0xef/0x160
	kthread+0x113/0x130
	kthread_create_worker_on_cpu+0x70/0x70
	ret_from_fork+0x35/0x40

To avoid this issue, don't forcibly set the CPB capability for a CPU
when running under a hypervisor.

Signed-off-by: Frank van der Linden <fllinden@amazon.com>
Acked-by: Borislav Petkov <bp@suse.de>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: bp@alien8.de
Cc: jiaxun.yang@flygoat.com
Fixes: 0237199186e7 ("x86/CPU/AMD: Set the CPB bit unconditionally on F17h")
Link: http://lkml.kernel.org/r/20190522221745.GA15789@dev-dsk-fllinden-2c-c1893d73.us-west-2.amazon.com
[ Minor edits to the changelog. ]
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/x86/kernel/cpu/amd.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index be6d0543e626..52a65f14db06 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -766,8 +766,11 @@ static void init_amd_zn(struct cpuinfo_x86 *c)
 {
 	set_cpu_cap(c, X86_FEATURE_ZEN);
 
-	/* Fix erratum 1076: CPB feature bit not being set in CPUID. */
-	if (!cpu_has(c, X86_FEATURE_CPB))
+	/*
+	 * Fix erratum 1076: CPB feature bit not being set in CPUID.
+	 * Always set it, except when running under a hypervisor.
+	 */
+	if (!cpu_has(c, X86_FEATURE_HYPERVISOR) && !cpu_has(c, X86_FEATURE_CPB))
 		set_cpu_cap(c, X86_FEATURE_CPB);
 }
 
-- 
2.20.1

[PATCH AUTOSEL 4.9 05/20] perf/ring_buffer: Fix exposing a temporarily decreased data_head

[Sasha Levin]

From: Yabin Cui <yabinc@google.com>

[ Upstream commit 1b038c6e05ff70a1e66e3e571c2e6106bdb75f53 ]

In perf_output_put_handle(), an IRQ/NMI can happen in below location and
write records to the same ring buffer:

	...
	local_dec_and_test(&rb->nest)
	...                          <-- an IRQ/NMI can happen here
	rb->user_page->data_head = head;
	...

In this case, a value A is written to data_head in the IRQ, then a value
B is written to data_head after the IRQ. And A > B. As a result,
data_head is temporarily decreased from A to B. And a reader may see
data_head < data_tail if it read the buffer frequently enough, which
creates unexpected behaviors.

This can be fixed by moving dec(&rb->nest) to after updating data_head,
which prevents the IRQ/NMI above from updating data_head.

[ Split up by peterz. ]

Signed-off-by: Yabin Cui <yabinc@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Cc: mark.rutland@arm.com
Fixes: ef60777c9abd ("perf: Optimize the perf_output() path by removing IRQ-disables")
Link: http://lkml.kernel.org/r/20190517115418.224478157@infradead.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 kernel/events/ring_buffer.c | 24 ++++++++++++++++++++----
 1 file changed, 20 insertions(+), 4 deletions(-)

diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index 99becab2c1ce..524744a38d61 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -52,11 +52,18 @@ static void perf_output_put_handle(struct perf_output_handle *handle)
 	head = local_read(&rb->head);
 
 	/*
-	 * IRQ/NMI can happen here, which means we can miss a head update.
+	 * IRQ/NMI can happen here and advance @rb->head, causing our
+	 * load above to be stale.
 	 */
 
-	if (!local_dec_and_test(&rb->nest))
+	/*
+	 * If this isn't the outermost nesting, we don't have to update
+	 * @rb->user_page->data_head.
+	 */
+	if (local_read(&rb->nest) > 1) {
+		local_dec(&rb->nest);
 		goto out;
+	}
 
 	/*
 	 * Since the mmap() consumer (userspace) can run on a different CPU:
@@ -88,9 +95,18 @@ static void perf_output_put_handle(struct perf_output_handle *handle)
 	rb->user_page->data_head = head;
 
 	/*
-	 * Now check if we missed an update -- rely on previous implied
-	 * compiler barriers to force a re-read.
+	 * We must publish the head before decrementing the nest count,
+	 * otherwise an IRQ/NMI can publish a more recent head value and our
+	 * write will (temporarily) publish a stale value.
+	 */
+	barrier();
+	local_set(&rb->nest, 0);
+
+	/*
+	 * Ensure we decrement @rb->nest before we validate the @rb->head.
+	 * Otherwise we cannot be sure we caught the 'last' nested update.
 	 */
+	barrier();
 	if (unlikely(head != local_read(&rb->head))) {
 		local_inc(&rb->nest);
 		goto again;
-- 
2.20.1

[PATCH AUTOSEL 4.9 06/20] perf/ring_buffer: Add ordering to rb->nest increment

[Sasha Levin]

From: Peter Zijlstra <peterz@infradead.org>

[ Upstream commit 3f9fbe9bd86c534eba2faf5d840fd44c6049f50e ]

Similar to how decrementing rb->next too early can cause data_head to
(temporarily) be observed to go backward, so too can this happen when
we increment too late.

This barrier() ensures the rb->head load happens after the increment,
both the one in the 'goto again' path, as the one from
perf_output_get_handle() -- albeit very unlikely to matter for the
latter.

Suggested-by: Yabin Cui <yabinc@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Cc: acme@kernel.org
Cc: mark.rutland@arm.com
Cc: namhyung@kernel.org
Fixes: ef60777c9abd ("perf: Optimize the perf_output() path by removing IRQ-disables")
Link: http://lkml.kernel.org/r/20190517115418.309516009@infradead.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 kernel/events/ring_buffer.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index 524744a38d61..8e8b903b7613 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -49,6 +49,15 @@ static void perf_output_put_handle(struct perf_output_handle *handle)
 	unsigned long head;
 
 again:
+	/*
+	 * In order to avoid publishing a head value that goes backwards,
+	 * we must ensure the load of @rb->head happens after we've
+	 * incremented @rb->nest.
+	 *
+	 * Otherwise we can observe a @rb->head value before one published
+	 * by an IRQ/NMI happening between the load and the increment.
+	 */
+	barrier();
 	head = local_read(&rb->head);
 
 	/*
-- 
2.20.1

[PATCH AUTOSEL 4.9 07/20] gpio: fix gpio-adp5588 build errors

[Sasha Levin]

From: Randy Dunlap <rdunlap@infradead.org>

[ Upstream commit e9646f0f5bb62b7d43f0968f39d536cfe7123b53 ]

The gpio-adp5588 driver uses interfaces that are provided by
GPIOLIB_IRQCHIP, so select that symbol in its Kconfig entry.

Fixes these build errors:

../drivers/gpio/gpio-adp5588.c: In function ‘adp5588_irq_handler’:
../drivers/gpio/gpio-adp5588.c:266:26: error: ‘struct gpio_chip’ has no member named ‘irq’
            dev->gpio_chip.irq.domain, gpio));
                          ^
../drivers/gpio/gpio-adp5588.c: In function ‘adp5588_irq_setup’:
../drivers/gpio/gpio-adp5588.c:298:2: error: implicit declaration of function ‘gpiochip_irqchip_add_nested’ [-Werror=implicit-function-declaration]
  ret = gpiochip_irqchip_add_nested(&dev->gpio_chip,
  ^
../drivers/gpio/gpio-adp5588.c:307:2: error: implicit declaration of function ‘gpiochip_set_nested_irqchip’ [-Werror=implicit-function-declaration]
  gpiochip_set_nested_irqchip(&dev->gpio_chip,
  ^

Fixes: 459773ae8dbb ("gpio: adp5588-gpio: support interrupt controller")
Reported-by: kbuild test robot <lkp@intel.com>
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: linux-gpio@vger.kernel.org
Reviewed-by: Bartosz Golaszewski <bgolaszewski@baylibre.com>
Acked-by: Michael Hennerich <michael.hennerich@analog.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/gpio/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig
index 12d417a4d4a8..b992badb99dd 100644
--- a/drivers/gpio/Kconfig
+++ b/drivers/gpio/Kconfig
@@ -670,6 +670,7 @@ config GPIO_ADP5588
 config GPIO_ADP5588_IRQ
 	bool "Interrupt controller support for ADP5588"
 	depends on GPIO_ADP5588=y
+	select GPIOLIB_IRQCHIP
 	help
 	  Say yes here to enable the adp5588 to be used as an interrupt
 	  controller. It requires the driver to be built in the kernel.
-- 
2.20.1

[PATCH AUTOSEL 4.9 08/20] net: tulip: de4x5: Drop redundant MODULE_DEVICE_TABLE()

[Sasha Levin]

From: Kees Cook <keescook@chromium.org>

[ Upstream commit 3e66b7cc50ef921121babc91487e1fb98af1ba6e ]

Building with Clang reports the redundant use of MODULE_DEVICE_TABLE():

drivers/net/ethernet/dec/tulip/de4x5.c:2110:1: error: redefinition of '__mod_eisa__de4x5_eisa_ids_device_table'
MODULE_DEVICE_TABLE(eisa, de4x5_eisa_ids);
^
./include/linux/module.h:229:21: note: expanded from macro 'MODULE_DEVICE_TABLE'
extern typeof(name) __mod_##type##__##name##_device_table               \
                    ^
<scratch space>:90:1: note: expanded from here
__mod_eisa__de4x5_eisa_ids_device_table
^
drivers/net/ethernet/dec/tulip/de4x5.c:2100:1: note: previous definition is here
MODULE_DEVICE_TABLE(eisa, de4x5_eisa_ids);
^
./include/linux/module.h:229:21: note: expanded from macro 'MODULE_DEVICE_TABLE'
extern typeof(name) __mod_##type##__##name##_device_table               \
                    ^
<scratch space>:85:1: note: expanded from here
__mod_eisa__de4x5_eisa_ids_device_table
^

This drops the one further from the table definition to match the common
use of MODULE_DEVICE_TABLE().

Fixes: 07563c711fbc ("EISA bus MODALIAS attributes support")
Signed-off-by: Kees Cook <keescook@chromium.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/ethernet/dec/tulip/de4x5.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/net/ethernet/dec/tulip/de4x5.c b/drivers/net/ethernet/dec/tulip/de4x5.c
index 6620fc861c47..005c79b5b3f0 100644
--- a/drivers/net/ethernet/dec/tulip/de4x5.c
+++ b/drivers/net/ethernet/dec/tulip/de4x5.c
@@ -2109,7 +2109,6 @@ static struct eisa_driver de4x5_eisa_driver = {
 		.remove  = de4x5_eisa_remove,
         }
 };
-MODULE_DEVICE_TABLE(eisa, de4x5_eisa_ids);
 #endif
 
 #ifdef CONFIG_PCI
-- 
2.20.1

[PATCH AUTOSEL 4.9 09/20] i2c: dev: fix potential memory leak in i2cdev_ioctl_rdwr

[Sasha Levin]

From: Yingjoe Chen <yingjoe.chen@mediatek.com>

[ Upstream commit a0692f0eef91354b62c2b4c94954536536be5425 ]

If I2C_M_RECV_LEN check failed, msgs[i].buf allocated by memdup_user
will not be freed. Pump index up so it will be freed.

Fixes: 838bfa6049fb ("i2c-dev: Add support for I2C_M_RECV_LEN")
Signed-off-by: Yingjoe Chen <yingjoe.chen@mediatek.com>
Signed-off-by: Wolfram Sang <wsa@the-dreams.de>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/i2c/i2c-dev.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/i2c/i2c-dev.c b/drivers/i2c/i2c-dev.c
index 00e8e675cbeb..eaa312bc3a3c 100644
--- a/drivers/i2c/i2c-dev.c
+++ b/drivers/i2c/i2c-dev.c
@@ -297,6 +297,7 @@ static noinline int i2cdev_ioctl_rdwr(struct i2c_client *client,
 			    rdwr_pa[i].buf[0] < 1 ||
 			    rdwr_pa[i].len < rdwr_pa[i].buf[0] +
 					     I2C_SMBUS_BLOCK_MAX) {
+				i++;
 				res = -EINVAL;
 				break;
 			}
-- 
2.20.1

[PATCH AUTOSEL 4.9 10/20] configfs: Fix use-after-free when accessing sd->s_dentry

[Sasha Levin]

From: Sahitya Tummala <stummala@codeaurora.org>

[ Upstream commit f6122ed2a4f9c9c1c073ddf6308d1b2ac10e0781 ]

In the vfs_statx() context, during path lookup, the dentry gets
added to sd->s_dentry via configfs_attach_attr(). In the end,
vfs_statx() kills the dentry by calling path_put(), which invokes
configfs_d_iput(). Ideally, this dentry must be removed from
sd->s_dentry but it doesn't if the sd->s_count >= 3. As a result,
sd->s_dentry is holding reference to a stale dentry pointer whose
memory is already freed up. This results in use-after-free issue,
when this stale sd->s_dentry is accessed later in
configfs_readdir() path.

This issue can be easily reproduced, by running the LTP test case -
sh fs_racer_file_list.sh /config
(https://github.com/linux-test-project/ltp/blob/master/testcases/kernel/fs/racer/fs_racer_file_list.sh)

Fixes: 76ae281f6307 ('configfs: fix race between dentry put and lookup')
Signed-off-by: Sahitya Tummala <stummala@codeaurora.org>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 fs/configfs/dir.c | 14 ++++++--------
 1 file changed, 6 insertions(+), 8 deletions(-)

diff --git a/fs/configfs/dir.c b/fs/configfs/dir.c
index d2a1a79fa324..4930a3a211f3 100644
--- a/fs/configfs/dir.c
+++ b/fs/configfs/dir.c
@@ -58,15 +58,13 @@ static void configfs_d_iput(struct dentry * dentry,
 	if (sd) {
 		/* Coordinate with configfs_readdir */
 		spin_lock(&configfs_dirent_lock);
-		/* Coordinate with configfs_attach_attr where will increase
-		 * sd->s_count and update sd->s_dentry to new allocated one.
-		 * Only set sd->dentry to null when this dentry is the only
-		 * sd owner.
-		 * If not do so, configfs_d_iput may run just after
-		 * configfs_attach_attr and set sd->s_dentry to null
-		 * even it's still in use.
+		/*
+		 * Set sd->s_dentry to null only when this dentry is the one
+		 * that is going to be killed.  Otherwise configfs_d_iput may
+		 * run just after configfs_attach_attr and set sd->s_dentry to
+		 * NULL even it's still in use.
 		 */
-		if (atomic_read(&sd->s_count) <= 2)
+		if (sd->s_dentry == dentry)
 			sd->s_dentry = NULL;
 
 		spin_unlock(&configfs_dirent_lock);
-- 
2.20.1

[PATCH AUTOSEL 4.9 11/20] perf data: Fix 'strncat may truncate' build failure with recent gcc

[Sasha Levin]

From: Shawn Landden <shawn@git.icu>

[ Upstream commit 97acec7df172cd1e450f81f5e293c0aa145a2797 ]

This strncat() is safe because the buffer was allocated with zalloc(),
however gcc doesn't know that. Since the string always has 4 non-null
bytes, just use memcpy() here.

    CC       /home/shawn/linux/tools/perf/util/data-convert-bt.o
  In file included from /usr/include/string.h:494,
                   from /home/shawn/linux/tools/lib/traceevent/event-parse.h:27,
                   from util/data-convert-bt.c:22:
  In function ‘strncat’,
      inlined from ‘string_set_value’ at util/data-convert-bt.c:274:4:
  /usr/include/powerpc64le-linux-gnu/bits/string_fortified.h:136:10: error: ‘__builtin_strncat’ output may be truncated copying 4 bytes from a string of length 4 [-Werror=stringop-truncation]
    136 |   return __builtin___strncat_chk (__dest, __src, __len, __bos (__dest));
        |          ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

Signed-off-by: Shawn Landden <shawn@git.icu>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
LPU-Reference: 20190518183238.10954-1-shawn@git.icu
Link: https://lkml.kernel.org/n/tip-289f1jice17ta7tr3tstm9jm@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 tools/perf/util/data-convert-bt.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/util/data-convert-bt.c b/tools/perf/util/data-convert-bt.c
index 7123f4de32cc..226f4312b8f3 100644
--- a/tools/perf/util/data-convert-bt.c
+++ b/tools/perf/util/data-convert-bt.c
@@ -265,7 +265,7 @@ static int string_set_value(struct bt_ctf_field *field, const char *string)
 				if (i > 0)
 					strncpy(buffer, string, i);
 			}
-			strncat(buffer + p, numstr, 4);
+			memcpy(buffer + p, numstr, 4);
 			p += 3;
 		}
 	}
-- 
2.20.1

[PATCH AUTOSEL 4.9 12/20] perf record: Fix s390 missing module symbol and warning for non-root users

[Sasha Levin]

From: Thomas Richter <tmricht@linux.ibm.com>

[ Upstream commit 6738028dd57df064b969d8392c943ef3b3ae705d ]

Command 'perf record' and 'perf report' on a system without kernel
debuginfo packages uses /proc/kallsyms and /proc/modules to find
addresses for kernel and module symbols. On x86 this works for root and
non-root users.

On s390, when invoked as non-root user, many of the following warnings
are shown and module symbols are missing:

    proc/{kallsyms,modules} inconsistency while looking for
        "[sha1_s390]" module!

Command 'perf record' creates a list of module start addresses by
parsing the output of /proc/modules and creates a PERF_RECORD_MMAP
record for the kernel and each module. The following function call
sequence is executed:

  machine__create_kernel_maps
    machine__create_module
      modules__parse
        machine__create_module --> for each line in /proc/modules
          arch__fix_module_text_start

Function arch__fix_module_text_start() is s390 specific. It opens
file /sys/module/<name>/sections/.text to extract the module's .text
section start address. On s390 the module loader prepends a header
before the first section, whereas on x86 the module's text section
address is identical the the module's load address.

However module section files are root readable only. For non-root the
read operation fails and machine__create_module() returns an error.
Command perf record does not generate any PERF_RECORD_MMAP record
for loaded modules. Later command perf report complains about missing
module maps.

To fix this function arch__fix_module_text_start() always returns
success. For root users there is no change, for non-root users
the module's load address is used as module's text start address
(the prepended header then counts as part of the text section).

This enable non-root users to use module symbols and avoid the
warning when perf report is executed.

Output before:

  [tmricht@m83lp54 perf]$ ./perf report -D | fgrep MMAP
  0 0x168 [0x50]: PERF_RECORD_MMAP ... x [kernel.kallsyms]_text

Output after:

  [tmricht@m83lp54 perf]$ ./perf report -D | fgrep MMAP
  0 0x168 [0x50]: PERF_RECORD_MMAP ... x [kernel.kallsyms]_text
  0 0x1b8 [0x98]: PERF_RECORD_MMAP ... x /lib/modules/.../autofs4.ko.xz
  0 0x250 [0xa8]: PERF_RECORD_MMAP ... x /lib/modules/.../sha_common.ko.xz
  0 0x2f8 [0x98]: PERF_RECORD_MMAP ... x /lib/modules/.../des_generic.ko.xz

Signed-off-by: Thomas Richter <tmricht@linux.ibm.com>
Reviewed-by: Hendrik Brueckner <brueckner@linux.ibm.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Link: http://lkml.kernel.org/r/20190522144601.50763-4-tmricht@linux.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 tools/perf/arch/s390/util/machine.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/tools/perf/arch/s390/util/machine.c b/tools/perf/arch/s390/util/machine.c
index b9a95a1a8e69..d3d1452021d4 100644
--- a/tools/perf/arch/s390/util/machine.c
+++ b/tools/perf/arch/s390/util/machine.c
@@ -4,16 +4,19 @@
 #include "util.h"
 #include "machine.h"
 #include "api/fs/fs.h"
+#include "debug.h"
 
 int arch__fix_module_text_start(u64 *start, const char *name)
 {
+	u64 m_start = *start;
 	char path[PATH_MAX];
 
 	snprintf(path, PATH_MAX, "module/%.*s/sections/.text",
 				(int)strlen(name) - 2, name + 1);
-
-	if (sysfs__read_ull(path, (unsigned long long *)start) < 0)
-		return -1;
+	if (sysfs__read_ull(path, (unsigned long long *)start) < 0) {
+		pr_debug2("Using module %s start:%#lx\n", path, m_start);
+		*start = m_start;
+	}
 
 	return 0;
 }
-- 
2.20.1

[PATCH AUTOSEL 4.9 13/20] ia64: fix build errors by exporting paddr_to_nid()

[Sasha Levin]

From: Randy Dunlap <rdunlap@infradead.org>

[ Upstream commit 9a626c4a6326da4433a0d4d4a8a7d1571caf1ed3 ]

Fix build errors on ia64 when DISCONTIGMEM=y and NUMA=y by
exporting paddr_to_nid().

Fixes these build errors:

ERROR: "paddr_to_nid" [sound/core/snd-pcm.ko] undefined!
ERROR: "paddr_to_nid" [net/sunrpc/sunrpc.ko] undefined!
ERROR: "paddr_to_nid" [fs/cifs/cifs.ko] undefined!
ERROR: "paddr_to_nid" [drivers/video/fbdev/core/fb.ko] undefined!
ERROR: "paddr_to_nid" [drivers/usb/mon/usbmon.ko] undefined!
ERROR: "paddr_to_nid" [drivers/usb/core/usbcore.ko] undefined!
ERROR: "paddr_to_nid" [drivers/md/raid1.ko] undefined!
ERROR: "paddr_to_nid" [drivers/md/dm-mod.ko] undefined!
ERROR: "paddr_to_nid" [drivers/md/dm-crypt.ko] undefined!
ERROR: "paddr_to_nid" [drivers/md/dm-bufio.ko] undefined!
ERROR: "paddr_to_nid" [drivers/ide/ide-core.ko] undefined!
ERROR: "paddr_to_nid" [drivers/ide/ide-cd_mod.ko] undefined!
ERROR: "paddr_to_nid" [drivers/gpu/drm/drm.ko] undefined!
ERROR: "paddr_to_nid" [drivers/char/agp/agpgart.ko] undefined!
ERROR: "paddr_to_nid" [drivers/block/nbd.ko] undefined!
ERROR: "paddr_to_nid" [drivers/block/loop.ko] undefined!
ERROR: "paddr_to_nid" [drivers/block/brd.ko] undefined!
ERROR: "paddr_to_nid" [crypto/ccm.ko] undefined!

Reported-by: kbuild test robot <lkp@intel.com>
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Tony Luck <tony.luck@intel.com>
Cc: Fenghua Yu <fenghua.yu@intel.com>
Cc: linux-ia64@vger.kernel.org
Signed-off-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/ia64/mm/numa.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/ia64/mm/numa.c b/arch/ia64/mm/numa.c
index aa19b7ac8222..476c7b4be378 100644
--- a/arch/ia64/mm/numa.c
+++ b/arch/ia64/mm/numa.c
@@ -49,6 +49,7 @@ paddr_to_nid(unsigned long paddr)
 
 	return (i < num_node_memblks) ? node_memblk[i].nid : (num_node_memblks ? -1 : 0);
 }
+EXPORT_SYMBOL(paddr_to_nid);
 
 #if defined(CONFIG_SPARSEMEM) && defined(CONFIG_NUMA)
 /*
-- 
2.20.1

[PATCH AUTOSEL 4.9 14/20] KVM: PPC: Book3S: Use new mutex to synchronize access to rtas token list

[Sasha Levin]

From: Paul Mackerras <paulus@ozlabs.org>

[ Upstream commit 1659e27d2bc1ef47b6d031abe01b467f18cb72d9 ]

Currently the Book 3S KVM code uses kvm->lock to synchronize access
to the kvm->arch.rtas_tokens list.  Because this list is scanned
inside kvmppc_rtas_hcall(), which is called with the vcpu mutex held,
taking kvm->lock cause a lock inversion problem, which could lead to
a deadlock.

To fix this, we add a new mutex, kvm->arch.rtas_token_lock, which nests
inside the vcpu mutexes, and use that instead of kvm->lock when
accessing the rtas token list.

This removes the lockdep_assert_held() in kvmppc_rtas_tokens_free().
At this point we don't hold the new mutex, but that is OK because
kvmppc_rtas_tokens_free() is only called when the whole VM is being
destroyed, and at that point nothing can be looking up a token in
the list.

Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/powerpc/include/asm/kvm_host.h |  1 +
 arch/powerpc/kvm/book3s.c           |  1 +
 arch/powerpc/kvm/book3s_rtas.c      | 14 ++++++--------
 3 files changed, 8 insertions(+), 8 deletions(-)

diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 5e12e19940e2..defa553fe823 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -271,6 +271,7 @@ struct kvm_arch {
 #ifdef CONFIG_PPC_BOOK3S_64
 	struct list_head spapr_tce_tables;
 	struct list_head rtas_tokens;
+	struct mutex rtas_token_lock;
 	DECLARE_BITMAP(enabled_hcalls, MAX_HCALL_OPCODE/4 + 1);
 #endif
 #ifdef CONFIG_KVM_MPIC
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index b6952dd23152..73c3c127d858 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -811,6 +811,7 @@ int kvmppc_core_init_vm(struct kvm *kvm)
 #ifdef CONFIG_PPC64
 	INIT_LIST_HEAD_RCU(&kvm->arch.spapr_tce_tables);
 	INIT_LIST_HEAD(&kvm->arch.rtas_tokens);
+	mutex_init(&kvm->arch.rtas_token_lock);
 #endif
 
 	return kvm->arch.kvm_ops->init_vm(kvm);
diff --git a/arch/powerpc/kvm/book3s_rtas.c b/arch/powerpc/kvm/book3s_rtas.c
index ef27fbd5d9c5..b1b2273d1f6d 100644
--- a/arch/powerpc/kvm/book3s_rtas.c
+++ b/arch/powerpc/kvm/book3s_rtas.c
@@ -133,7 +133,7 @@ static int rtas_token_undefine(struct kvm *kvm, char *name)
 {
 	struct rtas_token_definition *d, *tmp;
 
-	lockdep_assert_held(&kvm->lock);
+	lockdep_assert_held(&kvm->arch.rtas_token_lock);
 
 	list_for_each_entry_safe(d, tmp, &kvm->arch.rtas_tokens, list) {
 		if (rtas_name_matches(d->handler->name, name)) {
@@ -154,7 +154,7 @@ static int rtas_token_define(struct kvm *kvm, char *name, u64 token)
 	bool found;
 	int i;
 
-	lockdep_assert_held(&kvm->lock);
+	lockdep_assert_held(&kvm->arch.rtas_token_lock);
 
 	list_for_each_entry(d, &kvm->arch.rtas_tokens, list) {
 		if (d->token == token)
@@ -193,14 +193,14 @@ int kvm_vm_ioctl_rtas_define_token(struct kvm *kvm, void __user *argp)
 	if (copy_from_user(&args, argp, sizeof(args)))
 		return -EFAULT;
 
-	mutex_lock(&kvm->lock);
+	mutex_lock(&kvm->arch.rtas_token_lock);
 
 	if (args.token)
 		rc = rtas_token_define(kvm, args.name, args.token);
 	else
 		rc = rtas_token_undefine(kvm, args.name);
 
-	mutex_unlock(&kvm->lock);
+	mutex_unlock(&kvm->arch.rtas_token_lock);
 
 	return rc;
 }
@@ -232,7 +232,7 @@ int kvmppc_rtas_hcall(struct kvm_vcpu *vcpu)
 	orig_rets = args.rets;
 	args.rets = &args.args[be32_to_cpu(args.nargs)];
 
-	mutex_lock(&vcpu->kvm->lock);
+	mutex_lock(&vcpu->kvm->arch.rtas_token_lock);
 
 	rc = -ENOENT;
 	list_for_each_entry(d, &vcpu->kvm->arch.rtas_tokens, list) {
@@ -243,7 +243,7 @@ int kvmppc_rtas_hcall(struct kvm_vcpu *vcpu)
 		}
 	}
 
-	mutex_unlock(&vcpu->kvm->lock);
+	mutex_unlock(&vcpu->kvm->arch.rtas_token_lock);
 
 	if (rc == 0) {
 		args.rets = orig_rets;
@@ -269,8 +269,6 @@ void kvmppc_rtas_tokens_free(struct kvm *kvm)
 {
 	struct rtas_token_definition *d, *tmp;
 
-	lockdep_assert_held(&kvm->lock);
-
 	list_for_each_entry_safe(d, tmp, &kvm->arch.rtas_tokens, list) {
 		list_del(&d->list);
 		kfree(d);
-- 
2.20.1

[PATCH AUTOSEL 4.9 15/20] KVM: PPC: Book3S HV: Don't take kvm->lock around kvm_for_each_vcpu

[Sasha Levin]

From: Paul Mackerras <paulus@ozlabs.org>

[ Upstream commit 5a3f49364c3ffa1107bd88f8292406e98c5d206c ]

Currently the HV KVM code takes the kvm->lock around calls to
kvm_for_each_vcpu() and kvm_get_vcpu_by_id() (which can call
kvm_for_each_vcpu() internally).  However, that leads to a lock
order inversion problem, because these are called in contexts where
the vcpu mutex is held, but the vcpu mutexes nest within kvm->lock
according to Documentation/virtual/kvm/locking.txt.  Hence there
is a possibility of deadlock.

To fix this, we simply don't take the kvm->lock mutex around these
calls.  This is safe because the implementations of kvm_for_each_vcpu()
and kvm_get_vcpu_by_id() have been designed to be able to be called
locklessly.

Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
Reviewed-by: Cédric Le Goater <clg@kaod.org>
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/powerpc/kvm/book3s_hv.c | 9 +--------
 1 file changed, 1 insertion(+), 8 deletions(-)

diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 0a2b247dbc6b..e840f943cd2c 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -374,12 +374,7 @@ static void kvmppc_dump_regs(struct kvm_vcpu *vcpu)
 
 static struct kvm_vcpu *kvmppc_find_vcpu(struct kvm *kvm, int id)
 {
-	struct kvm_vcpu *ret;
-
-	mutex_lock(&kvm->lock);
-	ret = kvm_get_vcpu_by_id(kvm, id);
-	mutex_unlock(&kvm->lock);
-	return ret;
+	return kvm_get_vcpu_by_id(kvm, id);
 }
 
 static void init_vpa(struct kvm_vcpu *vcpu, struct lppaca *vpa)
@@ -1098,7 +1093,6 @@ static void kvmppc_set_lpcr(struct kvm_vcpu *vcpu, u64 new_lpcr,
 	struct kvmppc_vcore *vc = vcpu->arch.vcore;
 	u64 mask;
 
-	mutex_lock(&kvm->lock);
 	spin_lock(&vc->lock);
 	/*
 	 * If ILE (interrupt little-endian) has changed, update the
@@ -1132,7 +1126,6 @@ static void kvmppc_set_lpcr(struct kvm_vcpu *vcpu, u64 new_lpcr,
 		mask &= 0xFFFFFFFF;
 	vc->lpcr = (vc->lpcr & ~mask) | (new_lpcr & mask);
 	spin_unlock(&vc->lock);
-	mutex_unlock(&kvm->lock);
 }
 
 static int kvmppc_get_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,
-- 
2.20.1

[PATCH AUTOSEL 4.9 16/20] net: sh_eth: fix mdio access in sh_eth_close() for R-Car Gen2 and RZ/A1 SoCs

[Sasha Levin]

From: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>

[ Upstream commit 315ca92dd863fecbffc0bb52ae0ac11e0398726a ]

The sh_eth_close() resets the MAC and then calls phy_stop()
so that mdio read access result is incorrect without any error
according to kernel trace like below:

ifconfig-216   [003] .n..   109.133124: mdio_access: ee700000.ethernet-ffffffff read  phy:0x01 reg:0x00 val:0xffff

According to the hardware manual, the RMII mode should be set to 1
before operation the Ethernet MAC. However, the previous code was not
set to 1 after the driver issued the soft_reset in sh_eth_dev_exit()
so that the mdio read access result seemed incorrect. To fix the issue,
this patch adds a condition and set the RMII mode register in
sh_eth_dev_exit() for R-Car Gen2 and RZ/A1 SoCs.

Note that when I have tried to move the sh_eth_dev_exit() calling
after phy_stop() on sh_eth_close(), but it gets worse (kernel panic
happened and it seems that a register is accessed while the clock is
off).

Signed-off-by: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/ethernet/renesas/sh_eth.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c
index c59e8fe37069..49300194d3f9 100644
--- a/drivers/net/ethernet/renesas/sh_eth.c
+++ b/drivers/net/ethernet/renesas/sh_eth.c
@@ -1388,6 +1388,10 @@ static void sh_eth_dev_exit(struct net_device *ndev)
 	sh_eth_get_stats(ndev);
 	sh_eth_reset(ndev);
 
+	/* Set the RMII mode again if required */
+	if (mdp->cd->rmiimode)
+		sh_eth_write(ndev, 0x1, RMIIMODE);
+
 	/* Set MAC address again */
 	update_mac_address(ndev);
 }
-- 
2.20.1

[PATCH AUTOSEL 4.9 17/20] scsi: libcxgbi: add a check for NULL pointer in cxgbi_check_route()

[Sasha Levin]

From: Varun Prakash <varun@chelsio.com>

[ Upstream commit cc555759117e8349088e0c5d19f2f2a500bafdbd ]

ip_dev_find() can return NULL so add a check for NULL pointer.

Signed-off-by: Varun Prakash <varun@chelsio.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/scsi/cxgbi/libcxgbi.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/scsi/cxgbi/libcxgbi.c b/drivers/scsi/cxgbi/libcxgbi.c
index 2ffe029ff2b6..e974106f2bb5 100644
--- a/drivers/scsi/cxgbi/libcxgbi.c
+++ b/drivers/scsi/cxgbi/libcxgbi.c
@@ -637,6 +637,10 @@ static struct cxgbi_sock *cxgbi_check_route(struct sockaddr *dst_addr)
 
 	if (ndev->flags & IFF_LOOPBACK) {
 		ndev = ip_dev_find(&init_net, daddr->sin_addr.s_addr);
+		if (!ndev) {
+			err = -ENETUNREACH;
+			goto rel_neigh;
+		}
 		mtu = ndev->mtu;
 		pr_info("rt dev %s, loopback -> %s, mtu %u.\n",
 			n->dev->name, ndev->name, mtu);
-- 
2.20.1

[PATCH AUTOSEL 4.9 18/20] scsi: smartpqi: properly set both the DMA mask and the coherent DMA mask

[Sasha Levin]

From: Lianbo Jiang <lijiang@redhat.com>

[ Upstream commit 1d94f06e7f5df4064ef336b7b710f50143b64a53 ]

When SME is enabled, the smartpqi driver won't work on the HP DL385 G10
machine, which causes the failure of kernel boot because it fails to
allocate pqi error buffer. Please refer to the kernel log:
....
[    9.431749] usbcore: registered new interface driver uas
[    9.441524] Microsemi PQI Driver (v1.1.4-130)
[    9.442956] i40e 0000:04:00.0: fw 6.70.48768 api 1.7 nvm 10.2.5
[    9.447237] smartpqi 0000:23:00.0: Microsemi Smart Family Controller found
         Starting dracut initqueue hook...
[  OK  ] Started Show Plymouth Boot Scre[    9.471654] Broadcom NetXtreme-C/E driver bnxt_en v1.9.1
en.
[  OK  ] Started Forward Password Requests to Plymouth Directory Watch.
[[0;[    9.487108] smartpqi 0000:23:00.0: failed to allocate PQI error buffer
....
[  139.050544] dracut-initqueue[949]: Warning: dracut-initqueue timeout - starting timeout scripts
[  139.589779] dracut-initqueue[949]: Warning: dracut-initqueue timeout - starting timeout scripts

Basically, the fact that the coherent DMA mask value wasn't set caused the
driver to fall back to SWIOTLB when SME is active.

For correct operation, lets call the dma_set_mask_and_coherent() to
properly set the mask for both streaming and coherent, in order to inform
the kernel about the devices DMA addressing capabilities.

Signed-off-by: Lianbo Jiang <lijiang@redhat.com>
Acked-by: Don Brace <don.brace@microsemi.com>
Tested-by: Don Brace <don.brace@microsemi.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/scsi/smartpqi/smartpqi_init.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/scsi/smartpqi/smartpqi_init.c b/drivers/scsi/smartpqi/smartpqi_init.c
index 06a062455404..b12f7f952b70 100644
--- a/drivers/scsi/smartpqi/smartpqi_init.c
+++ b/drivers/scsi/smartpqi/smartpqi_init.c
@@ -5478,7 +5478,7 @@ static int pqi_pci_init(struct pqi_ctrl_info *ctrl_info)
 	else
 		mask = DMA_BIT_MASK(32);
 
-	rc = dma_set_mask(&ctrl_info->pci_dev->dev, mask);
+	rc = dma_set_mask_and_coherent(&ctrl_info->pci_dev->dev, mask);
 	if (rc) {
 		dev_err(&ctrl_info->pci_dev->dev, "failed to set DMA mask\n");
 		goto disable_device;
-- 
2.20.1

[PATCH AUTOSEL 4.9 19/20] scsi: libsas: delete sas port if expander discover failed

[Sasha Levin]

From: Jason Yan <yanaijie@huawei.com>

[ Upstream commit 3b0541791453fbe7f42867e310e0c9eb6295364d ]

The sas_port(phy->port) allocated in sas_ex_discover_expander() will not be
deleted when the expander failed to discover. This will cause resource leak
and a further issue of kernel BUG like below:

[159785.843156]  port-2:17:29: trying to add phy phy-2:17:29 fails: it's
already part of another port
[159785.852144] ------------[ cut here  ]------------
[159785.856833] kernel BUG at drivers/scsi/scsi_transport_sas.c:1086!
[159785.863000] Internal error: Oops - BUG: 0 [#1] SMP
[159785.867866] CPU: 39 PID: 16993 Comm: kworker/u96:2 Tainted: G
W  OE     4.19.25-vhulk1901.1.0.h111.aarch64 #1
[159785.878458] Hardware name: Huawei Technologies Co., Ltd.
Hi1620EVBCS/Hi1620EVBCS, BIOS Hi1620 CS B070 1P TA 03/21/2019
[159785.889231] Workqueue: 0000:74:02.0_disco_q sas_discover_domain
[159785.895224] pstate: 40c00009 (nZcv daif +PAN +UAO)
[159785.900094] pc : sas_port_add_phy+0x188/0x1b8
[159785.904524] lr : sas_port_add_phy+0x188/0x1b8
[159785.908952] sp : ffff0001120e3b80
[159785.912341] x29: ffff0001120e3b80 x28: 0000000000000000
[159785.917727] x27: ffff802ade8f5400 x26: ffff0000681b7560
[159785.923111] x25: ffff802adf11a800 x24: ffff0000680e8000
[159785.928496] x23: ffff802ade8f5728 x22: ffff802ade8f5708
[159785.933880] x21: ffff802adea2db40 x20: ffff802ade8f5400
[159785.939264] x19: ffff802adea2d800 x18: 0000000000000010
[159785.944649] x17: 00000000821bf734 x16: ffff00006714faa0
[159785.950033] x15: ffff0000e8ab4ecf x14: 7261702079646165
[159785.955417] x13: 726c612073277469 x12: ffff00006887b830
[159785.960802] x11: ffff00006773eaa0 x10: 7968702079687020
[159785.966186] x9 : 0000000000002453 x8 : 726f702072656874
[159785.971570] x7 : 6f6e6120666f2074 x6 : ffff802bcfb21290
[159785.976955] x5 : ffff802bcfb21290 x4 : 0000000000000000
[159785.982339] x3 : ffff802bcfb298c8 x2 : 337752b234c2ab00
[159785.987723] x1 : 337752b234c2ab00 x0 : 0000000000000000
[159785.993108] Process kworker/u96:2 (pid: 16993, stack limit =
0x0000000072dae094)
[159786.000576] Call trace:
[159786.003097]  sas_port_add_phy+0x188/0x1b8
[159786.007179]  sas_ex_get_linkrate.isra.5+0x134/0x140
[159786.012130]  sas_ex_discover_expander+0x128/0x408
[159786.016906]  sas_ex_discover_dev+0x218/0x4c8
[159786.021249]  sas_ex_discover_devices+0x9c/0x1a8
[159786.025852]  sas_discover_root_expander+0x134/0x160
[159786.030802]  sas_discover_domain+0x1b8/0x1e8
[159786.035148]  process_one_work+0x1b4/0x3f8
[159786.039230]  worker_thread+0x54/0x470
[159786.042967]  kthread+0x134/0x138
[159786.046269]  ret_from_fork+0x10/0x18
[159786.049918] Code: 91322300 f0004402 91178042 97fe4c9b (d4210000)
[159786.056083] Modules linked in: hns3_enet_ut(OE) hclge(OE) hnae3(OE)
hisi_sas_test_hw(OE) hisi_sas_test_main(OE) serdes(OE)
[159786.067202] ---[ end trace 03622b9e2d99e196  ]---
[159786.071893] Kernel panic - not syncing: Fatal exception
[159786.077190] SMP: stopping secondary CPUs
[159786.081192] Kernel Offset: disabled
[159786.084753] CPU features: 0x2,a2a00a38

Fixes: 2908d778ab3e ("[SCSI] aic94xx: new driver")
Reported-by: Jian Luo <luojian5@huawei.com>
Signed-off-by: Jason Yan <yanaijie@huawei.com>
CC: John Garry <john.garry@huawei.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/scsi/libsas/sas_expander.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/scsi/libsas/sas_expander.c b/drivers/scsi/libsas/sas_expander.c
index ee1f9ee995e5..400eee9d7783 100644
--- a/drivers/scsi/libsas/sas_expander.c
+++ b/drivers/scsi/libsas/sas_expander.c
@@ -978,6 +978,8 @@ static struct domain_device *sas_ex_discover_expander(
 		list_del(&child->dev_list_node);
 		spin_unlock_irq(&parent->port->dev_list_lock);
 		sas_put_device(child);
+		sas_port_delete(phy->port);
+		phy->port = NULL;
 		return NULL;
 	}
 	list_add_tail(&child->siblings, &parent->ex_dev.children);
-- 
2.20.1

[PATCH AUTOSEL 4.9 20/20] mlxsw: spectrum: Prevent force of 56G

[Sasha Levin]

From: Amit Cohen <amitc@mellanox.com>

[ Upstream commit 275e928f19117d22f6d26dee94548baf4041b773 ]

Force of 56G is not supported by hardware in Ethernet devices. This
configuration fails with a bad parameter error from firmware.

Add check of this case. Instead of trying to set 56G with autoneg off,
return a meaningful error.

Fixes: 56ade8fe3fe1 ("mlxsw: spectrum: Add initial support for Spectrum ASIC")
Signed-off-by: Amit Cohen <amitc@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index e3ed70a24029..585a40cc6470 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -2044,6 +2044,10 @@ mlxsw_sp_port_set_link_ksettings(struct net_device *dev,
 	mlxsw_reg_ptys_unpack(ptys_pl, &eth_proto_cap, NULL, NULL);
 
 	autoneg = cmd->base.autoneg == AUTONEG_ENABLE;
+	if (!autoneg && cmd->base.speed == SPEED_56000) {
+		netdev_err(dev, "56G not supported with autoneg off\n");
+		return -EINVAL;
+	}
 	eth_proto_new = autoneg ?
 		mlxsw_sp_to_ptys_advert_link(cmd) :
 		mlxsw_sp_to_ptys_speed(cmd->base.speed);
-- 
2.20.1