4.14.76-stable review

This is the start of the stable review cycle for the 4.14.76 release. There are 45 patches in this series, all will be posted as a response to this one. If anyone has any issues with these being applied, please let me know.

Responses should be made by Sat Oct 13 15:24:53 UTC 2018. Anything received after that time might be too late.

The whole patch series can be found in one patch at:

	https://www.kernel.org/pub/linux/kernel/v4.x/stable-review/patch-4.14.76-rc1.gz

or in the git tree and branch at:
git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git linux-4.14.y
and the diffstat can be found below.

thanks,

greg k-h

-------------
Pseudo-Shortlog of commits:

Greg Kroah-Hartman <[email protected]>

    Linux 4.14.76-rc1

Zhi Chen <[email protected]>
ath10k: fix scan crash due to incorrect length calculation

Jan Stancek <[email protected]>

    virtio_balloon: fix increment of vb->num_pfns in fill_balloon()

Michael S. Tsirkin <[email protected]>
virtio_balloon: fix deadlock on OOM

Ka-Cheong Poon <[email protected]>
rds: rds_ib_recv_alloc_cache() should call alloc_percpu_gfp() instead

Richard Weinberger <[email protected]>
ubifs: Check for name being NULL while mounting

Cong Wang <[email protected]>
ucma: fix a use-after-free in ucma_resolve_ip()

Chao Yu <[email protected]>
f2fs: fix invalid memory access

Jiri Olsa <[email protected]>
perf utils: Move is_directory() to path.h

Harsh Jain <[email protected]>
crypto: chelsio - Fix memory corruption in DMA Mapped buffers.

Vineet Gupta <[email protected]>
ARC: clone syscall to setp r25 as thread pointer

Christophe Leroy <[email protected]>
powerpc/lib: fix book3s/32 boot failure due to code patching

Michael Neuling <[email protected]>
powerpc: Avoid code patching freed init sections

Christophe Leroy <[email protected]>
powerpc/lib/code-patching: refactor patch_instruction()

James Smart <[email protected]>
nvme_fc: fix ctrl create failures racing with workq items

Yu Wang <[email protected]>
ath10k: fix kernel panic issue during pci probe

Carl Huang <[email protected]>
ath10k: fix use-after-free in ath10k_wmi_cmd_send_nowait

Prateek Sood <[email protected]>
cgroup/cpuset: remove circular dependency deadlock

Jiri Olsa <[email protected]>
perf tools: Fix python extension build for gcc 8

Arnaldo Carvalho de Melo <[email protected]>
perf annotate: Use asprintf when formatting objdump command line

Guenter Roeck <[email protected]>
of: unittest: Disable interrupt node tests for old world MAC systems

Dmitry Safonov <[email protected]>

    tty: Drop tty->count on tty_reopen() failure

Romain Izard <[email protected]>
usb: cdc_acm: Do not leak URB buffers

Johan Hovold <[email protected]>
USB: serial: simple: add Motorola Tetra MTP6550 id

Chunfeng Yun <[email protected]>
usb: xhci-mtk: resume USB3 roothub first

Mathias Nyman <[email protected]>
xhci: Add missing CAS workaround for Intel Sunrise Point xHCI

Mike Snitzer <[email protected]>
dm cache: fix resize crash if user doesn't reload cache table

Joe Thornber <[email protected]>
dm cache metadata: ignore hints array being too small during resize

Rafael J. Wysocki <[email protected]>
PM / core: Clear the direct_complete flag on errors

Felix Fietkau <[email protected]>
mac80211: fix setting IEEE80211_KEY_FLAG_RX_MGMT for AP mode keys

Daniel Drake <[email protected]>
PCI: Reprogram bridge prefetch registers on resume

Andy Lutomirski <[email protected]>
x86/vdso: Fix vDSO syscall fallback asm constraint regression

Andy Lutomirski <[email protected]>
x86/vdso: Only enable vDSO retpolines when enabled and supported

Andy Lutomirski <[email protected]>
selftests/x86: Add clock_gettime() tests to test_vdso

Andy Lutomirski <[email protected]>
x86/vdso: Fix asm constraints on vDSO syscall fallbacks

Jason Ekstrand <[email protected]>
drm/syncobj: Don't leak fences when WAIT_FOR_SUBMIT is set

Rex Zhu <[email protected]>
drm/amdgpu: Fix vce work queue was not cancelled when suspend

Jan Beulich <[email protected]>
xen-netback: fix input validation in xenvif_set_hash_mapping()

Tomi Valkeinen <[email protected]>
fbdev/omapfb: fix omapfb_memory_read infoleak

Alexandre Belloni <[email protected]>
clocksource/drivers/timer-atmel-pit: Properly handle error cases

Ilya Dryomov <[email protected]>
blk-mq: I/O and timer unplugs are inverted in blktrace

Sean Christopherson <[email protected]>
KVM: x86: fix L1TF's MMIO GFN calculation

Jann Horn <[email protected]>
mm/vmstat.c: skip NR_TLB_REMOTE_FLUSH* properly

Kirill A. Shutemov <[email protected]>
mm, thp: fix mlocking THP page with migration enabled

Mike Kravetz <[email protected]>
mm: migration: fix migration of huge PMD shared pages

Reinette Chatre <[email protected]>
perf/core: Add sanity check to deal with pinned event failure

-------------

Diffstat:

 Makefile                                        |   4 +-
 arch/arc/kernel/process.c                       |  20 +++
 arch/powerpc/include/asm/setup.h                |   1 +
 arch/powerpc/lib/code-patching.c                |  44 +++---
 arch/powerpc/mm/mem.c                           |   2 +
 arch/x86/entry/vdso/Makefile                    |  16 ++-
 arch/x86/entry/vdso/vclock_gettime.c            |  26 ++--
 arch/x86/kvm/mmu.c                              |  24 +++-
 block/blk-mq.c                                  |   4 +-
 drivers/base/power/main.c                       |   5 +-
 drivers/clocksource/timer-atmel-pit.c           |  20 ++-
 drivers/crypto/chelsio/chcr_algo.c              |  41 ++++--
 drivers/crypto/chelsio/chcr_crypto.h            |   2 +
 drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c         |   3 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c         |   4 +-
 drivers/gpu/drm/drm_syncobj.c                   |   5 +
 drivers/infiniband/core/ucma.c                  |   2 +
 drivers/md/dm-cache-metadata.c                  |   4 +-
 drivers/md/dm-cache-target.c                    |   9 +-
 drivers/net/wireless/ath/ath10k/debug.c         |  12 +-
 drivers/net/wireless/ath/ath10k/trace.h         |  12 +-
 drivers/net/wireless/ath/ath10k/wmi-tlv.c       |   8 +-
 drivers/net/wireless/ath/ath10k/wmi.c           |   2 +-
 drivers/net/xen-netback/hash.c                  |  12 +-
 drivers/nvme/host/fc.c                          |   4 +
 drivers/of/unittest.c                           |  26 ++--
 drivers/pci/pci.c                               |  27 ++--
 drivers/tty/tty_io.c                            |  11 +-
 drivers/usb/class/cdc-acm.c                     |   6 +
 drivers/usb/host/xhci-mtk.c                     |   4 +-
 drivers/usb/host/xhci-pci.c                     |   2 +
 drivers/usb/serial/usb-serial-simple.c          |   3 +-
 drivers/video/fbdev/omap2/omapfb/omapfb-ioctl.c |   5 +-
 drivers/virtio/virtio_balloon.c                 |  23 +++-
 fs/f2fs/checkpoint.c                            |   9 +-
 fs/ubifs/super.c                                |   3 +
 include/linux/balloon_compaction.h              |  35 ++++-
 include/linux/hugetlb.h                         |  14 ++
 include/linux/mm.h                              |   6 +
 kernel/cgroup/cpuset.c                          |  53 ++++----
 kernel/events/core.c                            |   6 +
 mm/balloon_compaction.c                         |  28 +++-
 mm/huge_memory.c                                |   2 +-
 mm/hugetlb.c                                    |  37 ++++-
 mm/migrate.c                                    |   3 +
 mm/rmap.c                                       |  42 +++++-
 mm/vmstat.c                                     |   3 +
 net/mac80211/cfg.c                              |   2 +-
 net/rds/ib.h                                    |   2 +-
 net/rds/ib_cm.c                                 |   2 +-
 net/rds/ib_recv.c                               |  10 +-
 tools/perf/builtin-script.c                     |  14 +-
 tools/perf/util/annotate.c                      |  17 ++-
 tools/perf/util/path.c                          |  14 ++
 tools/perf/util/path.h                          |   3 +
 tools/perf/util/setup.py                        |   2 +
 tools/testing/selftests/x86/test_vdso.c         | 172 ++++++++++++++++++++++++
 57 files changed, 690 insertions(+), 182 deletions(-)

4.14-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ilya Dryomov <[email protected]>

commit 587562d0c7cd6861f4f90a2eb811cccb1a376f5f upstream.

trace_block_unplug() takes true for explicit unplugs and false for implicit unplugs. schedule() unplugs are implicit and should be reported as timer unplugs. While correct in the legacy code, this has been inverted in blk-mq since 4.11.

---
 block/blk-mq.c |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

@@ -1512,7 +1512,7 @@ void blk_mq_flush_plug_list(struct blk_p
 		BUG_ON(!rq->q);
 		if (rq->mq_ctx != this_ctx) {
 			if (this_ctx) {
-				trace_block_unplug(this_q, depth, from_schedule);
+				trace_block_unplug(this_q, depth, !from_schedule);
 				blk_mq_sched_insert_requests(this_q, this_ctx,
 								&ctx_list,
 								from_schedule);

@@ -1532,7 +1532,7 @@ void blk_mq_flush_plug_list(struct blk_p
 	 * on 'ctx_list'. Do those.
 	 */
 	if (this_ctx) {
-		trace_block_unplug(this_q, depth, from_schedule);
+		trace_block_unplug(this_q, depth, !from_schedule);
 		blk_mq_sched_insert_requests(this_q, this_ctx, &ctx_list,
 						from_schedule);
 	}

4.14-stable review patch. If anyone has any objections, please let me know.

------------------

From: Andy Lutomirski <[email protected]>

commit 715bd9d12f84d8f5cc8ad21d888f9bc304a8eb0b upstream.

The syscall fallbacks in the vDSO have incorrect asm constraints. They are not marked as writing to their outputs -- instead, they are marked as clobbering "memory", which is useless. In particular, gcc is smart enough to know that the timespec parameter hasn't escaped, so a memory clobber doesn't clobber it. And passing a pointer as an asm *input* does not tell gcc that the pointed-to value is changed.

Add in the fact that the asm instructions weren't volatile, and gcc was free to omit them entirely unless their sole output (the return value) is used. Which it is (phew!), but that stops happening with some upcoming patches.

As a trivial example, the following code:

void test_fallback(struct timespec *ts)

{
	vdso_fallback_gettime(CLOCK_MONOTONIC, ts);
}

compiles to:

00000000000000c0 <test_fallback>:
c0: c3 retq

To add insult to injury, the RCX and R11 clobbers on 64-bit builds were missing.

The "memory" clobber is also unnecessary -- no ordering with respect to other memory operations is needed, but that's going to be fixed in a separate not-for-stable patch.

---
 arch/x86/entry/vdso/vclock_gettime.c |   18 ++++++++++--------
 1 file changed, 10 insertions(+), 8 deletions(-)

@@ -43,8 +43,9 @@ extern u8 hvclock_page
 notrace static long vdso_fallback_gettime(long clock, struct timespec *ts)
 {
 	long ret;
-	asm("syscall" : "=a" (ret) :
-	    "0" (__NR_clock_gettime), "D" (clock), "S" (ts) : "memory");
+	asm ("syscall" : "=a" (ret), "=m" (*ts) :
+	     "0" (__NR_clock_gettime), "D" (clock), "S" (ts) :
+	     "memory", "rcx", "r11");
 	return ret;
 }
 

@@ -52,8 +53,9 @@ notrace static long vdso_fallback_gtod(s
 {
 	long ret;
 
-	asm("syscall" : "=a" (ret) :
-	    "0" (__NR_gettimeofday), "D" (tv), "S" (tz) : "memory");
+	asm ("syscall" : "=a" (ret), "=m" (*tv), "=m" (*tz) :
+	     "0" (__NR_gettimeofday), "D" (tv), "S" (tz) :
+	     "memory", "rcx", "r11");
 	return ret;
 }
 

@@ -64,12 +66,12 @@ notrace static long vdso_fallback_gettim
 {
 	long ret;
 
-	asm(
+	asm (
 		"mov %%ebx, %%edx \n"
 		"mov %2, %%ebx \n"
 		"call __kernel_vsyscall \n"
 		"mov %%edx, %%ebx \n"
-		: "=a" (ret)
+		: "=a" (ret), "=m" (*ts)
 		: "0" (__NR_clock_gettime), "g" (clock), "c" (ts)
 		: "memory", "edx");
 	return ret;

@@ -79,12 +81,12 @@ notrace static long vdso_fallback_gtod(s
 {
 	long ret;
 
-	asm(
+	asm (
 		"mov %%ebx, %%edx \n"
 		"mov %2, %%ebx \n"
 		"call __kernel_vsyscall \n"
 		"mov %%edx, %%ebx \n"
-		: "=a" (ret)
+		: "=a" (ret), "=m" (*tv), "=m" (*tz)
 		: "0" (__NR_gettimeofday), "g" (tv), "c" (tz)
 		: "memory", "edx");
 	return ret;

4.14-stable review patch. If anyone has any objections, please let me know.

------------------

From: Reinette Chatre <[email protected]>

commit befb1b3c2703897c5b8ffb0044dc5d0e5f27c5d7 upstream.

It is possible that a failure can occur during the scheduling of a pinned event. The initial portion of perf_event_read_local() contains the various error checks an event should pass before it can be considered valid. Ensure that the potential scheduling failure of a pinned event is checked for and have a credible error.

---
 kernel/events/core.c |    6 ++++++
 1 file changed, 6 insertions(+)

@@ -3757,6 +3757,12 @@ int perf_event_read_local(struct perf_ev
 		goto out;
 	}
 
+	/* If this is a pinned event it must be running on this CPU */
+	if (event->attr.pinned && event->oncpu != smp_processor_id()) {
+		ret = -EBUSY;
+		goto out;
+	}
+
 	/*
 	 * If the event is currently on this CPU, its either a per-task event,
 	 * or local to this CPU. Furthermore it means its ACTIVE (otherwise

4.14-stable review patch. If anyone has any objections, please let me know.

------------------

From: Rex Zhu <[email protected]>

commit 61ea6f5831974ebd1a57baffd7cc30600a2e26fc upstream.

The vce cancel_delayed_work_sync never be called. driver call the function in error path.

This caused the A+A suspend hang when runtime pm enebled. As we will visit the smu in the idle queue. this will cause smu hang because the dgpu has been suspend, and the dgpu also will be waked up. As the smu has been hang, so the dgpu resume will failed.

---
 drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c |    3 ++-
 drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c |    4 ++--
 2 files changed, 4 insertions(+), 3 deletions(-)

@@ -231,6 +231,8 @@ int amdgpu_vce_suspend(struct amdgpu_dev
 {
 	int i;
 
+	cancel_delayed_work_sync(&adev->vce.idle_work);
+
 	if (adev->vce.vcpu_bo == NULL)
 		return 0;
 

@@ -241,7 +243,6 @@ int amdgpu_vce_suspend(struct amdgpu_dev
 	if (i == AMDGPU_MAX_VCE_HANDLES)
 		return 0;
 
-	cancel_delayed_work_sync(&adev->vce.idle_work);
 	/* TODO: suspending running encoding sessions isn't supported */
 	return -EINVAL;
 }

@@ -155,11 +155,11 @@ int amdgpu_vcn_suspend(struct amdgpu_dev
 	unsigned size;
 	void *ptr;
 
+	cancel_delayed_work_sync(&adev->vcn.idle_work);
+
 	if (adev->vcn.vcpu_bo == NULL)
 		return 0;
 
-	cancel_delayed_work_sync(&adev->vcn.idle_work);
-
 	size = amdgpu_bo_size(adev->vcn.vcpu_bo);
 	ptr = adev->vcn.cpu_addr;
 

4.14-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jason Ekstrand <[email protected]>

commit 337fe9f5c1e7de1f391c6a692531379d2aa2ee11 upstream.

We attempt to get fences earlier in the hopes that everything will already have fences and no callbacks will be needed. If we do succeed in getting a fence, getting one a second time will result in a duplicate ref with no unref. This is causing memory leaks in Vulkan applications that create a lot of fences; playing for a few hours can, apparently, bring down the system.

Cc: [email protected]
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=107899

---
 drivers/gpu/drm/drm_syncobj.c |    5 +++++
 1 file changed, 5 insertions(+)

@@ -96,6 +96,8 @@ static int drm_syncobj_fence_get_or_add_
 {
 	int ret;
 
+	WARN_ON(*fence);
+
 	*fence = drm_syncobj_fence_get(syncobj);
 	if (*fence)
 		return 1;

@@ -656,6 +658,9 @@ static signed long drm_syncobj_array_wai
 
 	if (flags & DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT) {
 		for (i = 0; i < count; ++i) {
+			if (entries[i].fence)
+				continue;
+
 			drm_syncobj_fence_get_or_add_callback(syncobjs[i],
 							      &entries[i].fence,
 							      &entries[i].syncobj_cb,

4.14-stable review patch. If anyone has any objections, please let me know.

------------------

From: Andy Lutomirski <[email protected]>

commit 7c03e7035ac1cf2a6165754e4f3a49c2f1977838 upstream.

Now that the vDSO implementation of clock_gettime() is getting reworked, add a selftest for it. This tests that its output is consistent with the syscall version.

This is marked for stable to serve as a test for commit

715bd9d12f84 ("x86/vdso: Fix asm constraints on vDSO syscall fallbacks")

---
 tools/testing/selftests/x86/test_vdso.c |   99 ++++++++++++++++++++++++++++++++
 1 file changed, 99 insertions(+)

@@ -17,6 +17,7 @@
 #include <errno.h>
 #include <sched.h>
 #include <stdbool.h>
+#include <limits.h>
 
 #ifndef SYS_getcpu
 # ifdef __x86_64__

@@ -31,6 +32,10 @@
 
 int nerrs = 0;
 
+typedef int (*vgettime_t)(clockid_t, struct timespec *);
+
+vgettime_t vdso_clock_gettime;
+
 typedef long (*getcpu_t)(unsigned *, unsigned *, void *);
 
 getcpu_t vgetcpu;

@@ -95,6 +100,10 @@ static void fill_function_pointers()
 		printf("Warning: failed to find getcpu in vDSO\n");
 
 	vgetcpu = (getcpu_t) vsyscall_getcpu();
+
+	vdso_clock_gettime = (vgettime_t)dlsym(vdso, "__vdso_clock_gettime");
+	if (!vdso_clock_gettime)
+		printf("Warning: failed to find clock_gettime in vDSO\n");
 }
 
 static long sys_getcpu(unsigned * cpu, unsigned * node,

@@ -103,6 +112,11 @@ static long sys_getcpu(unsigned * cpu, u
 	return syscall(__NR_getcpu, cpu, node, cache);
 }
 
+static inline int sys_clock_gettime(clockid_t id, struct timespec *ts)
+{
+	return syscall(__NR_clock_gettime, id, ts);
+}
+
 static void test_getcpu(void)
 {
 	printf("[RUN]\tTesting getcpu...\n");

@@ -155,10 +169,95 @@ static void test_getcpu(void)
 	}
 }
 
+static bool ts_leq(const struct timespec *a, const struct timespec *b)
+{
+	if (a->tv_sec != b->tv_sec)
+		return a->tv_sec < b->tv_sec;
+	else
+		return a->tv_nsec <= b->tv_nsec;
+}
+
+static char const * const clocknames[] = {
+	[0] = "CLOCK_REALTIME",
+	[1] = "CLOCK_MONOTONIC",
+	[2] = "CLOCK_PROCESS_CPUTIME_ID",
+	[3] = "CLOCK_THREAD_CPUTIME_ID",
+	[4] = "CLOCK_MONOTONIC_RAW",
+	[5] = "CLOCK_REALTIME_COARSE",
+	[6] = "CLOCK_MONOTONIC_COARSE",
+	[7] = "CLOCK_BOOTTIME",
+	[8] = "CLOCK_REALTIME_ALARM",
+	[9] = "CLOCK_BOOTTIME_ALARM",
+	[10] = "CLOCK_SGI_CYCLE",
+	[11] = "CLOCK_TAI",
+};
+
+static void test_one_clock_gettime(int clock, const char *name)
+{
+	struct timespec start, vdso, end;
+	int vdso_ret, end_ret;
+
+	printf("[RUN]\tTesting clock_gettime for clock %s (%d)...\n", name, clock);
+
+	if (sys_clock_gettime(clock, &start) < 0) {
+		if (errno == EINVAL) {
+			vdso_ret = vdso_clock_gettime(clock, &vdso);
+			if (vdso_ret == -EINVAL) {
+				printf("[OK]\tNo such clock.\n");
+			} else {
+				printf("[FAIL]\tNo such clock, but __vdso_clock_gettime returned %d\n", vdso_ret);
+				nerrs++;
+			}
+		} else {
+			printf("[WARN]\t clock_gettime(%d) syscall returned error %d\n", clock, errno);
+		}
+		return;
+	}
+
+	vdso_ret = vdso_clock_gettime(clock, &vdso);
+	end_ret = sys_clock_gettime(clock, &end);
+
+	if (vdso_ret != 0 || end_ret != 0) {
+		printf("[FAIL]\tvDSO returned %d, syscall errno=%d\n",
+		       vdso_ret, errno);
+		nerrs++;
+		return;
+	}
+
+	printf("\t%llu.%09ld %llu.%09ld %llu.%09ld\n",
+	       (unsigned long long)start.tv_sec, start.tv_nsec,
+	       (unsigned long long)vdso.tv_sec, vdso.tv_nsec,
+	       (unsigned long long)end.tv_sec, end.tv_nsec);
+
+	if (!ts_leq(&start, &vdso) || !ts_leq(&vdso, &end)) {
+		printf("[FAIL]\tTimes are out of sequence\n");
+		nerrs++;
+	}
+}
+
+static void test_clock_gettime(void)
+{
+	for (int clock = 0; clock < sizeof(clocknames) / sizeof(clocknames[0]);
+	     clock++) {
+		test_one_clock_gettime(clock, clocknames[clock]);
+	}
+
+	/* Also test some invalid clock ids */
+	test_one_clock_gettime(-1, "invalid");
+	test_one_clock_gettime(INT_MIN, "invalid");
+	test_one_clock_gettime(INT_MAX, "invalid");
+}
+
 int main(int argc, char **argv)
 {
 	fill_function_pointers();
 
+	test_clock_gettime();
+
+	/*
+	 * Test getcpu() last so that, if something goes wrong setting affinity,
+	 * we still run the other tests.
+	 */
 	test_getcpu();
 
 	return nerrs ? 1 : 0;

4.14-stable review patch. If anyone has any objections, please let me know.

------------------

From: Andy Lutomirski <[email protected]>

commit 4f166564014aba65ad6f15b612f6711fd0f117ee upstream.

When I fixed the vDSO build to use inline retpolines, I messed up the Makefile logic and made it unconditional. It should have depended on CONFIG_RETPOLINE and on the availability of compiler support. This broke the build on some older compilers.

---
 arch/x86/entry/vdso/Makefile |   16 ++++++++++++++--
 1 file changed, 14 insertions(+), 2 deletions(-)

@@ -74,7 +74,13 @@ $(obj)/vdso-image-%.c: $(obj)/vdso%.so.d
 CFL := $(PROFILING) -mcmodel=small -fPIC -O2 -fasynchronous-unwind-tables -m64 \
        $(filter -g%,$(KBUILD_CFLAGS)) $(call cc-option, -fno-stack-protector) \
        -fno-omit-frame-pointer -foptimize-sibling-calls \
-       -DDISABLE_BRANCH_PROFILING -DBUILD_VDSO $(RETPOLINE_VDSO_CFLAGS)
+       -DDISABLE_BRANCH_PROFILING -DBUILD_VDSO
+
+ifdef CONFIG_RETPOLINE
+ifneq ($(RETPOLINE_VDSO_CFLAGS),)
+  CFL += $(RETPOLINE_VDSO_CFLAGS)
+endif
+endif
 
 $(vobjs): KBUILD_CFLAGS := $(filter-out $(GCC_PLUGINS_CFLAGS) $(RETPOLINE_CFLAGS),$(KBUILD_CFLAGS)) $(CFL)
 

@@ -153,7 +159,13 @@ KBUILD_CFLAGS_32 += $(call cc-option, -f
 KBUILD_CFLAGS_32 += $(call cc-option, -foptimize-sibling-calls)
 KBUILD_CFLAGS_32 += -fno-omit-frame-pointer
 KBUILD_CFLAGS_32 += -DDISABLE_BRANCH_PROFILING
-KBUILD_CFLAGS_32 += $(RETPOLINE_VDSO_CFLAGS)
+
+ifdef CONFIG_RETPOLINE
+ifneq ($(RETPOLINE_VDSO_CFLAGS),)
+  KBUILD_CFLAGS_32 += $(RETPOLINE_VDSO_CFLAGS)
+endif
+endif
+
 $(obj)/vdso32.so.dbg: KBUILD_CFLAGS = $(KBUILD_CFLAGS_32)
 
 $(obj)/vdso32.so.dbg: FORCE \

4.14-stable review patch. If anyone has any objections, please let me know.

------------------

From: Andy Lutomirski <[email protected]>

commit 02e425668f5c9deb42787d10001a3b605993ad15 upstream.

When I added the missing memory outputs, I failed to update the index of the first argument (ebx) on 32-bit builds, which broke the fallbacks. Somehow I must have screwed up my testing or gotten lucky.

Add another test to cover gettimeofday() as well.

---
 arch/x86/entry/vdso/vclock_gettime.c    |    8 +--
 tools/testing/selftests/x86/test_vdso.c |   73 ++++++++++++++++++++++++++++++++
 2 files changed, 77 insertions(+), 4 deletions(-)

@@ -68,11 +68,11 @@ notrace static long vdso_fallback_gettim
 
 	asm (
 		"mov %%ebx, %%edx \n"
-		"mov %2, %%ebx \n"
+		"mov %[clock], %%ebx \n"
 		"call __kernel_vsyscall \n"
 		"mov %%edx, %%ebx \n"
 		: "=a" (ret), "=m" (*ts)
-		: "0" (__NR_clock_gettime), "g" (clock), "c" (ts)
+		: "0" (__NR_clock_gettime), [clock] "g" (clock), "c" (ts)
 		: "memory", "edx");
 	return ret;
 }

@@ -83,11 +83,11 @@ notrace static long vdso_fallback_gtod(s
 
 	asm (
 		"mov %%ebx, %%edx \n"
-		"mov %2, %%ebx \n"
+		"mov %[tv], %%ebx \n"
 		"call __kernel_vsyscall \n"
 		"mov %%edx, %%ebx \n"
 		: "=a" (ret), "=m" (*tv), "=m" (*tz)
-		: "0" (__NR_gettimeofday), "g" (tv), "c" (tz)
+		: "0" (__NR_gettimeofday), [tv] "g" (tv), "c" (tz)
 		: "memory", "edx");
 	return ret;
 }

4.14-stable review patch. If anyone has any objections, please let me know.

------------------

From: Daniel Drake <[email protected]>

commit 083874549fdfefa629dfa752785e20427dde1511 upstream.

On 38+ Intel-based ASUS products, the NVIDIA GPU becomes unusable after S3 suspend/resume. The affected products include multiple generations of NVIDIA GPUs and Intel SoCs. After resume, nouveau logs many errors such as:

fifo: fault 00 [READ] at 0000005555555000 engine 00 [GR] client 04

        [HUB/FE] reason 4a [] on channel -1 [007fa91000 unknown]

DRM: failed to idle channel 0 [DRM]

Similarly, the NVIDIA proprietary driver also fails after resume (black screen, 100% CPU usage in Xorg process). We shipped a sample to NVIDIA for diagnosis, and their response indicated that it's a problem with the parent PCI bridge (on the Intel SoC), not the GPU.

Runtime suspend/resume works fine, only S3 suspend is affected.

We found a workaround: on resume, rewrite the Intel PCI bridge 'Prefetchable Base Upper 32 Bits' register (PCI_PREF_BASE_UPPER32). In the cases that I checked, this register has value 0 and we just have to rewrite that value.

Linux already saves and restores PCI config space during suspend/resume, but this register was being skipped because upon resume, it already has value 0 (the correct, pre-suspend value).

Intel appear to have previously acknowledged this behaviour and the requirement to rewrite this register:
https://bugzilla.kernel.org/show_bug.cgi?id=116851#c23

Based on that, rewrite the prefetch register values even when that appears unnecessary.

We have confirmed this solution on all the affected models we have in-hands (X542UQ, UX533FD, X530UN, V272UN).

Additionally, this solves an issue where r8169 MSI-X interrupts were broken after S3 suspend/resume on ASUS X441UAR. This issue was recently worked around in commit 7bb05b85bc2d ("r8169: don't use MSI-X on RTL8106e"). It also fixes the same issue on RTL6186evl/8111evl on an Aimfor-tech laptop that we had not yet patched. I suspect it will also fix the issue that was worked around in commit 7c53a722459c ("r8169: don't use MSI-X on RTL8168g").

Thomas Martitz reports that this change also solves an issue where the AMD Radeon Polaris 10 GPU on the HP Zbook 14u G5 is unresponsive after S3 suspend/resume.

---
 drivers/pci/pci.c |   27 +++++++++++++++++++--------
 1 file changed, 19 insertions(+), 8 deletions(-)

@@ -1112,12 +1112,12 @@ int pci_save_state(struct pci_dev *dev)
 EXPORT_SYMBOL(pci_save_state);
 
 static void pci_restore_config_dword(struct pci_dev *pdev, int offset,
-				     u32 saved_val, int retry)
+				     u32 saved_val, int retry, bool force)
 {
 	u32 val;
 
 	pci_read_config_dword(pdev, offset, &val);
-	if (val == saved_val)
+	if (!force && val == saved_val)
 		return;
 
 	for (;;) {

@@ -1136,25 +1136,36 @@ static void pci_restore_config_dword(str
 }
 
 static void pci_restore_config_space_range(struct pci_dev *pdev,
-					   int start, int end, int retry)
+					   int start, int end, int retry,
+					   bool force)
 {
 	int index;
 
 	for (index = end; index >= start; index--)
 		pci_restore_config_dword(pdev, 4 * index,
 					 pdev->saved_config_space[index],
-					 retry);
+					 retry, force);
 }
 
 static void pci_restore_config_space(struct pci_dev *pdev)
 {
 	if (pdev->hdr_type == PCI_HEADER_TYPE_NORMAL) {
-		pci_restore_config_space_range(pdev, 10, 15, 0);
+		pci_restore_config_space_range(pdev, 10, 15, 0, false);
 		/* Restore BARs before the command register. */
-		pci_restore_config_space_range(pdev, 4, 9, 10);
-		pci_restore_config_space_range(pdev, 0, 3, 0);
+		pci_restore_config_space_range(pdev, 4, 9, 10, false);
+		pci_restore_config_space_range(pdev, 0, 3, 0, false);
+	} else if (pdev->hdr_type == PCI_HEADER_TYPE_BRIDGE) {
+		pci_restore_config_space_range(pdev, 12, 15, 0, false);
+
+		/*
+		 * Force rewriting of prefetch registers to avoid S3 resume
+		 * issues on Intel PCI bridges that occur when these
+		 * registers are not explicitly written.
+		 */
+		pci_restore_config_space_range(pdev, 9, 11, 0, true);
+		pci_restore_config_space_range(pdev, 0, 8, 0, false);
 	} else {
-		pci_restore_config_space_range(pdev, 0, 15, 0);
+		pci_restore_config_space_range(pdev, 0, 15, 0, false);
 	}
 }
 

4.14-stable review patch. If anyone has any objections, please let me know.

------------------

From: Felix Fietkau <[email protected]>

commit 211710ca74adf790b46ab3867fcce8047b573cd1 upstream.

key->sta is only valid after ieee80211_key_link, which is called later in this function. Because of that, the IEEE80211_KEY_FLAG_RX_MGMT is never set when management frame protection is enabled.

---
 net/mac80211/cfg.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -426,7 +426,7 @@ static int ieee80211_add_key(struct wiph
 	case NL80211_IFTYPE_AP:
 	case NL80211_IFTYPE_AP_VLAN:
 		/* Keys without a station are used for TX only */
-		if (key->sta && test_sta_flag(key->sta, WLAN_STA_MFP))
+		if (sta && test_sta_flag(sta, WLAN_STA_MFP))
 			key->conf.flags |= IEEE80211_KEY_FLAG_RX_MGMT;
 		break;
 	case NL80211_IFTYPE_ADHOC:

4.14-stable review patch. If anyone has any objections, please let me know.

------------------

From: Rafael J. Wysocki <[email protected]>

commit 69e445ab8b66a9f30519842ef18be555d3ee9b51 upstream.

If __device_suspend() runs asynchronously (in which case the device passed to it is in dpm_suspended_list at that point) and it returns early on an error or pending wakeup, and the power.direct_complete flag has been set for the device already, the subsequent device_resume() will be confused by that and it will call pm_runtime_enable() incorrectly, as runtime PM has not been disabled for the device by __device_suspend().

To avoid that, clear power.direct_complete if __device_suspend() is not going to disable runtime PM for the device before returning.

---
 drivers/base/power/main.c |    5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

@@ -1462,8 +1462,10 @@ static int __device_suspend(struct devic
 
 	dpm_wait_for_subordinate(dev, async);
 
-	if (async_error)
+	if (async_error) {
+		dev->power.direct_complete = false;
 		goto Complete;
+	}
 
 	/*
 	 * If a device configured to wake up the system from sleep states

@@ -1475,6 +1477,7 @@ static int __device_suspend(struct devic
 		pm_wakeup_event(dev, 0);
 
 	if (pm_wakeup_pending()) {
+		dev->power.direct_complete = false;
 		async_error = -EBUSY;
 		goto Complete;
 	}

4.14-stable review patch. If anyone has any objections, please let me know.

------------------

From: Joe Thornber <[email protected]>

commit 4561ffca88c546f96367f94b8f1e4715a9c62314 upstream.

Commit fd2fa9541 ("dm cache metadata: save in-core policy_hint_size to on-disk superblock") enabled previously written policy hints to be used after a cache is reactivated. But in doing so the cache metadata's hint array was left exposed to out of bounds access because on resize the metadata's on-disk hint array wasn't ever extended.

Fix this by ignoring that there are no on-disk hints associated with the newly added cache blocks. An expanded on-disk hint array is later rewritten upon the next clean shutdown of the cache.

---
 drivers/md/dm-cache-metadata.c |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

@@ -1454,8 +1454,8 @@ static int __load_mappings(struct dm_cac
 		if (hints_valid) {
 			r = dm_array_cursor_next(&cmd->hint_cursor);
 			if (r) {
-				DMERR("dm_array_cursor_next for hint failed");
-				goto out;
+				dm_array_cursor_end(&cmd->hint_cursor);
+				hints_valid = false;
 			}
 		}
 

4.14-stable review patch. If anyone has any objections, please let me know.

------------------

From: Mike Kravetz <[email protected]>

commit 017b1660df89f5fb4bfe66c34e35f7d2031100c7 upstream.

The page migration code employs try_to_unmap() to try and unmap the source page. This is accomplished by using rmap_walk to find all vmas where the page is mapped. This search stops when page mapcount is zero. For shared PMD huge pages, the page map count is always 1 no matter the number of mappings. Shared mappings are tracked via the reference count of the PMD page. Therefore, try_to_unmap stops prematurely and does not completely unmap all mappings of the source page.

This problem can result is data corruption as writes to the original source page can happen after contents of the page are copied to the target page. Hence, data is lost.

This problem was originally seen as DB corruption of shared global areas after a huge page was soft offlined due to ECC memory errors. DB developers noticed they could reproduce the issue by (hotplug) offlining memory used to back huge pages. A simple testcase can reproduce the problem by creating a shared PMD mapping (note that this must be at least PUD_SIZE in size and PUD_SIZE aligned (1GB on x86)), and using migrate_pages() to migrate process pages between nodes while continually writing to the huge pages being migrated.

To fix, have the try_to_unmap_one routine check for huge PMD sharing by calling huge_pmd_unshare for hugetlbfs huge pages. If it is a shared mapping it will be 'unshared' which removes the page table entry and drops the reference on the PMD page. After this, flush caches and TLB.

mmu notifiers are called before locking page tables, but we can not be sure of PMD sharing until page tables are locked. Therefore, check for the possibility of PMD sharing before locking so that notifiers can prepare for the worst possible case.

---
 include/linux/hugetlb.h |   14 ++++++++++++++
 include/linux/mm.h      |    6 ++++++
 mm/hugetlb.c            |   37 +++++++++++++++++++++++++++++++++++--
 mm/rmap.c               |   42 +++++++++++++++++++++++++++++++++++++++---
 4 files changed, 94 insertions(+), 5 deletions(-)

@@ -140,6 +140,8 @@ pte_t *huge_pte_alloc(struct mm_struct *
 pte_t *huge_pte_offset(struct mm_struct *mm,
 		       unsigned long addr, unsigned long sz);
 int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep);
+void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma,
+				unsigned long *start, unsigned long *end);
 struct page *follow_huge_addr(struct mm_struct *mm, unsigned long address,
 			      int write);
 struct page *follow_huge_pd(struct vm_area_struct *vma,

@@ -169,6 +171,18 @@ static inline unsigned long hugetlb_tota
 	return 0;
 }
 
+static inline int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr,
+					pte_t *ptep)
+{
+	return 0;
+}
+
+static inline void adjust_range_if_pmd_sharing_possible(
+				struct vm_area_struct *vma,
+				unsigned long *start, unsigned long *end)
+{
+}
+
 #define follow_hugetlb_page(m,v,p,vs,a,b,i,w,n)	({ BUG(); 0; })
 #define follow_huge_addr(mm, addr, write)	ERR_PTR(-EINVAL)
 #define copy_hugetlb_page_range(src, dst, vma)	({ BUG(); 0; })

@@ -2322,6 +2322,12 @@ static inline struct vm_area_struct *fin
 	return vma;
 }
 
+static inline bool range_in_vma(struct vm_area_struct *vma,
+				unsigned long start, unsigned long end)
+{
+	return (vma && vma->vm_start <= start && end <= vma->vm_end);
+}
+
 #ifdef CONFIG_MMU
 pgprot_t vm_get_page_prot(unsigned long vm_flags);
 void vma_set_page_prot(struct vm_area_struct *vma);

@@ -4517,13 +4517,41 @@ static bool vma_shareable(struct vm_area
 	/*
 	 * check on proper vm_flags and page table alignment
 	 */
-	if (vma->vm_flags & VM_MAYSHARE &&
-	    vma->vm_start <= base && end <= vma->vm_end)
+	if (vma->vm_flags & VM_MAYSHARE && range_in_vma(vma, base, end))
 		return true;
 	return false;
 }
 
 /*
+ * Determine if start,end range within vma could be mapped by shared pmd.
+ * If yes, adjust start and end to cover range associated with possible
+ * shared pmd mappings.
+ */
+void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma,
+				unsigned long *start, unsigned long *end)
+{
+	unsigned long check_addr = *start;
+
+	if (!(vma->vm_flags & VM_MAYSHARE))
+		return;
+
+	for (check_addr = *start; check_addr < *end; check_addr += PUD_SIZE) {
+		unsigned long a_start = check_addr & PUD_MASK;
+		unsigned long a_end = a_start + PUD_SIZE;
+
+		/*
+		 * If sharing is possible, adjust start/end if necessary.
+		 */
+		if (range_in_vma(vma, a_start, a_end)) {
+			if (a_start < *start)
+				*start = a_start;
+			if (a_end > *end)
+				*end = a_end;
+		}
+	}
+}
+
+/*
  * Search for a shareable pmd page for hugetlb. In any case calls pmd_alloc()
  * and returns the corresponding pte. While this is not necessary for the
  * !shared pmd case because we can allocate the pmd later as well, it makes the

@@ -4620,6 +4648,11 @@ int huge_pmd_unshare(struct mm_struct *m
 {
 	return 0;
 }
+
+void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma,
+				unsigned long *start, unsigned long *end)
+{
+}
 #define want_pmd_share()	(0)
 #endif /* CONFIG_ARCH_WANT_HUGE_PMD_SHARE */
 

4.14-stable review patch. If anyone has any objections, please let me know.

------------------

From: Mike Snitzer <[email protected]>

commit 5d07384a666d4b2f781dc056bfeec2c27fbdf383 upstream.

A reload of the cache's DM table is needed during resize because otherwise a crash will occur when attempting to access smq policy entries associated with the portion of the cache that was recently extended.

The reason is cache-size based data structures in the policy will not be resized, the only way to safely extend the cache is to allow for a proper cache policy initialization that occurs when the cache table is loaded. For example the smq policy's space_init(), init_allocator(), calc_hotspot_params() must be sized based on the extended cache size.

The fix for this is to disallow cache resizes of this pattern:
1) suspend "cache" target's device
2) resize the fast device used for the cache
3) resume "cache" target's device

Instead, the last step must be a full reload of the cache's DM table.

---
 drivers/md/dm-cache-target.c |    9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

@@ -3097,8 +3097,13 @@ static dm_cblock_t get_cache_dev_size(st
 
 static bool can_resize(struct cache *cache, dm_cblock_t new_size)
 {
-	if (from_cblock(new_size) > from_cblock(cache->cache_size))
-		return true;
+	if (from_cblock(new_size) > from_cblock(cache->cache_size)) {
+		if (cache->sized) {
+			DMERR("%s: unable to extend cache due to missing cache table reload",
+			      cache_device_name(cache));
+			return false;
+		}
+	}
 
 	/*
 	 * We can't drop a dirty block when shrinking the cache.

4.14-stable review patch. If anyone has any objections, please let me know.

------------------

From: Mathias Nyman <[email protected]>

commit ffe84e01bb1b38c7eb9c6b6da127a6c136d251df upstream.

The workaround for missing CAS bit is also needed for xHC on Intel sunrisepoint PCH. For more details see:

Intel 100/c230 series PCH specification update Doc #332692-006 Errata #8

---
 drivers/usb/host/xhci-pci.c |    2 ++
 1 file changed, 2 insertions(+)

@@ -196,6 +196,8 @@ static void xhci_pci_quirks(struct devic
 	}
 	if (pdev->vendor == PCI_VENDOR_ID_INTEL &&
 	    (pdev->device == PCI_DEVICE_ID_INTEL_CHERRYVIEW_XHCI ||
+	     pdev->device == PCI_DEVICE_ID_INTEL_SUNRISEPOINT_LP_XHCI ||
+	     pdev->device == PCI_DEVICE_ID_INTEL_SUNRISEPOINT_H_XHCI ||
 	     pdev->device == PCI_DEVICE_ID_INTEL_APL_XHCI ||
 	     pdev->device == PCI_DEVICE_ID_INTEL_DNV_XHCI))
 		xhci->quirks |= XHCI_MISSING_CAS;

4.14-stable review patch. If anyone has any objections, please let me know.

------------------

From: Chunfeng Yun <[email protected]>

commit 555df5820e733cded7eb8d0bf78b2a791be51d75 upstream.

Give USB3 devices a better chance to enumerate at USB3 speeds if they are connected to a suspended host.
Porting from "671ffdff5b13 xhci: resume USB 3 roothub first"

---
 drivers/usb/host/xhci-mtk.c |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

@@ -780,10 +780,10 @@ static int __maybe_unused xhci_mtk_resum
 	xhci_mtk_host_enable(mtk);
 
 	xhci_dbg(xhci, "%s: restart port polling\n", __func__);
-	set_bit(HCD_FLAG_POLL_RH, &hcd->flags);
-	usb_hcd_poll_rh_status(hcd);
 	set_bit(HCD_FLAG_POLL_RH, &xhci->shared_hcd->flags);
 	usb_hcd_poll_rh_status(xhci->shared_hcd);
+	set_bit(HCD_FLAG_POLL_RH, &hcd->flags);
+	usb_hcd_poll_rh_status(hcd);
 	return 0;
 }
 

4.14-stable review patch. If anyone has any objections, please let me know.

------------------

From: Johan Hovold <[email protected]>

commit f5fad711c06e652f90f581fc7c2caee327c33d31 upstream.

Add device-id for the Motorola Tetra radio MTP6550.

Bus 001 Device 004: ID 0cad:9012 Motorola CGISS
Device Descriptor:
bLength 18
bDescriptorType 1
bcdUSB 2.00

  bDeviceClass            0 (Defined at Interface level)
  bDeviceSubClass         0
  bDeviceProtocol         0
  bMaxPacketSize0        64
  idVendor           0x0cad Motorola CGISS
  idProduct          0x9012
  bcdDevice           24.16
  iManufacturer           1 Motorola Solutions, Inc.
  iProduct                2 TETRA PEI interface
  iSerial                 0
  bNumConfigurations      1

Configuration Descriptor:
bLength 9
bDescriptorType 2
wTotalLength 55
bNumInterfaces 2
bConfigurationValue 1
iConfiguration 3 Generic Serial config
bmAttributes 0x80
(Bus Powered)
MaxPower 500mA
Interface Descriptor:
bLength 9
bDescriptorType 4
bInterfaceNumber 0
bAlternateSetting 0
bNumEndpoints 2
bInterfaceClass 255 Vendor Specific Class
bInterfaceSubClass 0
bInterfaceProtocol 0
iInterface 0
Endpoint Descriptor:
bLength 7
bDescriptorType 5
bEndpointAddress 0x81 EP 1 IN
bmAttributes 2
Transfer Type Bulk
Synch Type None
Usage Type Data
wMaxPacketSize 0x0200 1x 512 bytes
bInterval 0
Endpoint Descriptor:
bLength 7
bDescriptorType 5
bEndpointAddress 0x01 EP 1 OUT
bmAttributes 2
Transfer Type Bulk
Synch Type None
Usage Type Data
wMaxPacketSize 0x0200 1x 512 bytes
Interface Descriptor:
bLength 9
bDescriptorType 4
bInterfaceNumber 1
bAlternateSetting 0
bNumEndpoints 2
bInterfaceClass 255 Vendor Specific Class
bInterfaceSubClass 0
bInterfaceProtocol 0
iInterface 0
Endpoint Descriptor:
bLength 7
bDescriptorType 5
bEndpointAddress 0x82 EP 2 IN
bmAttributes 2
Transfer Type Bulk
Synch Type None
Usage Type Data
wMaxPacketSize 0x0200 1x 512 bytes
bInterval 0
Endpoint Descriptor:
bLength 7
bDescriptorType 5
bEndpointAddress 0x02 EP 2 OUT
bmAttributes 2
Transfer Type Bulk
Synch Type None
Usage Type Data
wMaxPacketSize 0x0200 1x 512 bytes
bInterval 0
Device Qualifier (for other device speed):
bLength 10
bDescriptorType 6
bcdUSB 2.00

  bDeviceClass            0 (Defined at Interface level)
  bDeviceSubClass         0
  bDeviceProtocol         0

bMaxPacketSize0 64
bNumConfigurations 1
Device Status: 0x0000
(Bus Powered)

---
 drivers/usb/serial/usb-serial-simple.c |    3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

@@ -87,7 +87,8 @@ DEVICE(moto_modem, MOTO_IDS);
 
 /* Motorola Tetra driver */
 #define MOTOROLA_TETRA_IDS()			\
-	{ USB_DEVICE(0x0cad, 0x9011) }	/* Motorola Solutions TETRA PEI */
+	{ USB_DEVICE(0x0cad, 0x9011) },	/* Motorola Solutions TETRA PEI */ \
+	{ USB_DEVICE(0x0cad, 0x9012) }	/* MTP6550 */
 DEVICE(motorola_tetra, MOTOROLA_TETRA_IDS);
 
 /* Novatel Wireless GPS driver */

4.14-stable review patch. If anyone has any objections, please let me know.

------------------

From: Romain Izard <[email protected]>

commit f2924d4b16ae138c2de6a0e73f526fb638330858 upstream.

When the ACM TTY port is disconnected, the URBs it uses must be killed, and then the buffers must be freed. Unfortunately a previous refactor removed the code freeing the buffers because it looked extremely similar to the code killing the URBs.

As a result, there were many new leaks for each plug/unplug cycle of a CDC-ACM device, that were detected by kmemleak.

Restore the missing code, and the memory leak is removed.

---
 drivers/usb/class/cdc-acm.c |    6 ++++++
 1 file changed, 6 insertions(+)

@@ -1527,6 +1527,7 @@ static void acm_disconnect(struct usb_in
 {
 	struct acm *acm = usb_get_intfdata(intf);
 	struct tty_struct *tty;
+	int i;
 
 	/* sibling interface is already cleaning up */
 	if (!acm)

@@ -1557,6 +1558,11 @@ static void acm_disconnect(struct usb_in
 
 	tty_unregister_device(acm_tty_driver, acm->minor);
 
+	usb_free_urb(acm->ctrlurb);
+	for (i = 0; i < ACM_NW; i++)
+		usb_free_urb(acm->wb[i].urb);
+	for (i = 0; i < acm->rx_buflimit; i++)
+		usb_free_urb(acm->read_urbs[i]);
 	acm_write_buffers_free(acm);
 	usb_free_coherent(acm->dev, acm->ctrlsize, acm->ctrl_buffer, acm->ctrl_dma);
 	acm_read_buffers_free(acm);

4.14-stable review patch. If anyone has any objections, please let me know.

------------------

From: Dmitry Safonov <[email protected]>

commit fe32416790093b31364c08395727de17ec96ace1 upstream.

In case of tty_ldisc_reinit() failure, tty->count should be decremented back, otherwise we will never release_tty().
Tetsuo reported that it fixes noisy warnings on tty release like:
pts pts4033: tty_release: tty->count(10529) != (#fd's(7) + #kopen's(0))

---
 drivers/tty/tty_io.c |   11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

@@ -1254,6 +1254,7 @@ static void tty_driver_remove_tty(struct
 static int tty_reopen(struct tty_struct *tty)
 {
 	struct tty_driver *driver = tty->driver;
+	int retval;
 
 	if (driver->type == TTY_DRIVER_TYPE_PTY &&
 	    driver->subtype == PTY_TYPE_MASTER)

@@ -1267,10 +1268,14 @@ static int tty_reopen(struct tty_struct
 
 	tty->count++;
 
-	if (!tty->ldisc)
-		return tty_ldisc_reinit(tty, tty->termios.c_line);
+	if (tty->ldisc)
+		return 0;
 
-	return 0;
+	retval = tty_ldisc_reinit(tty, tty->termios.c_line);
+	if (retval)
+		tty->count--;
+
+	return retval;
 }
 
 /**

4.14-stable review patch. If anyone has any objections, please let me know.

------------------

From: Guenter Roeck <[email protected]>

commit 8894891446c9380709451b99ab45c5c53adfd2fc upstream.

On systems with OF_IMAP_OLDWORLD_MAC set in of_irq_workarounds, the devicetree interrupt parsing code is different, causing unit tests of devicetree interrupt nodes to fail. Due to a bug in unittest code, which tries to dereference an uninitialized pointer, this results in a crash.

OF: /testcase-data/phandle-tests/consumer-a: arguments longer than property

Unable to handle kernel paging request for data at address 0x00bc616e
Faulting instruction address: 0xc08e9468
Oops: Kernel access of bad area, sig: 11 [#1]
BE PREEMPT PowerMac
Modules linked in:
CPU: 0 PID: 1 Comm: swapper Not tainted 4.14.72-rc1-yocto-standard+ #1
task: cf8e0000 task.stack: cf8da000
NIP:  c08e9468 LR: c08ea5bc CTR: c08ea5ac
REGS: cf8dbb50 TRAP: 0300   Not tainted  (4.14.72-rc1-yocto-standard+)
MSR:  00001032 <ME,IR,DR,RI>  CR: 82004044  XER: 00000000
DAR: 00bc616e DSISR: 40000000
GPR00: c08ea5bc cf8dbc00 cf8e0000 c13ca517 c13ca517 c13ca8a0 00000066 00000002
GPR08: 00000063 00bc614e c0b05865 000affff 82004048 00000000 c00047f0 00000000
GPR16: c0a80000 c0a9cc34 c13ca517 c0ad1134 05ffffff 000affff c0b05860 c0abeef8
GPR24: cecec278 cecec278 c0a8c4d0 c0a885e0 c13ca8a0 05ffffff c13ca8a0 c13ca517

NIP [c08e9468] device_node_gen_full_name+0x30/0x15c LR [c08ea5bc] device_node_string+0x190/0x3c8

Call Trace:
[cf8dbc00] [c007f670] trace_hardirqs_on_caller+0x118/0x1fc (unreliable)
[cf8dbc40] [c08ea5bc] device_node_string+0x190/0x3c8
[cf8dbcb0] [c08eb794] pointer+0x25c/0x4d0
[cf8dbd00] [c08ebcbc] vsnprintf+0x2b4/0x5ec
[cf8dbd60] [c08ec00c] vscnprintf+0x18/0x48
[cf8dbd70] [c008e268] vprintk_store+0x4c/0x22c
[cf8dbda0] [c008ecac] vprintk_emit+0x94/0x130
[cf8dbdd0] [c008ff54] printk+0x5c/0x6c
[cf8dbe10] [c0b8ddd4] of_unittest+0x2220/0x26f8
[cf8dbea0] [c0004434] do_one_initcall+0x4c/0x184
[cf8dbf00] [c0b4534c] kernel_init_freeable+0x13c/0x1d8
[cf8dbf30] [c0004814] kernel_init+0x24/0x118
[cf8dbf40] [c0013398] ret_from_kernel_thread+0x5c/0x64

The problem was observed when running a qemu test for the g3beige machine with devicetree unittests enabled.

Disable interrupt node tests on affected systems to avoid both false unittest failures and the crash.

With this patch in place, unittest on the affected system passes with the following message.

dt-test ### end of unittest - 144 passed, 0 failed

---
 drivers/of/unittest.c |   28 +++++++++++++++++++---------
 1 file changed, 19 insertions(+), 9 deletions(-)

@@ -614,6 +614,9 @@ static void __init of_unittest_parse_int
 	struct of_phandle_args args;
 	int i, rc;
 
+	if (of_irq_workarounds & OF_IMAP_OLDWORLD_MAC)
+		return;
+
 	np = of_find_node_by_path("/testcase-data/interrupts/interrupts0");
 	if (!np) {
 		pr_err("missing testcase data\n");

@@ -688,6 +691,9 @@ static void __init of_unittest_parse_int
 	struct of_phandle_args args;
 	int i, rc;
 
+	if (of_irq_workarounds & OF_IMAP_OLDWORLD_MAC)
+		return;
+
 	np = of_find_node_by_path("/testcase-data/interrupts/interrupts-extended0");
 	if (!np) {
 		pr_err("missing testcase data\n");

@@ -844,15 +850,19 @@ static void __init of_unittest_platform_
 	pdev = of_find_device_by_node(np);
 	unittest(pdev, "device 1 creation failed\n");
 
-	irq = platform_get_irq(pdev, 0);
-	unittest(irq == -EPROBE_DEFER, "device deferred probe failed - %d\n", irq);
-
-	/* Test that a parsing failure does not return -EPROBE_DEFER */
-	np = of_find_node_by_path("/testcase-data/testcase-device2");
-	pdev = of_find_device_by_node(np);
-	unittest(pdev, "device 2 creation failed\n");
-	irq = platform_get_irq(pdev, 0);
-	unittest(irq < 0 && irq != -EPROBE_DEFER, "device parsing error failed - %d\n", irq);
+	if (!(of_irq_workarounds & OF_IMAP_OLDWORLD_MAC)) {
+		irq = platform_get_irq(pdev, 0);
+		unittest(irq == -EPROBE_DEFER,
+			 "device deferred probe failed - %d\n", irq);
+
+		/* Test that a parsing failure does not return -EPROBE_DEFER */
+		np = of_find_node_by_path("/testcase-data/testcase-device2");
+		pdev = of_find_device_by_node(np);
+		unittest(pdev, "device 2 creation failed\n");
+		irq = platform_get_irq(pdev, 0);
+		unittest(irq < 0 && irq != -EPROBE_DEFER,
+			 "device parsing error failed - %d\n", irq);
+	}
 
 	np = of_find_node_by_path("/testcase-data/platform-tests");
 	unittest(np, "No testcase data in device tree\n");

4.14-stable review patch. If anyone has any objections, please let me know.

------------------

From: Arnaldo Carvalho de Melo <[email protected]>

commit 6810158d526e483868e519befff407b91e76b3db upstream.

We were using a local buffer with an arbitrary size, that would have to get increased to avoid truncation as warned by gcc 8:

util/annotate.c: In function 'symbol__disassemble':
util/annotate.c:1488:4: error: '%s' directive output may be truncated writing up to 4095 bytes into a region of size between 3966 and 8086 [-Werror=format-truncation=]

      "%s %s%s --start-address=0x%016" PRIx64
      ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
  util/annotate.c:1498:20:
      symfs_filename, symfs_filename);
                      ~~~~~~~~~~~~~~
  util/annotate.c:1490:50: note: format string is defined here
      " -l -d %s %s -C \"%s\" 2>/dev/null|grep -v \"%s:\"|expand",
                                                  ^~
  In file included from /usr/include/stdio.h:861,
                   from util/color.h:5,
                   from util/sort.h:8,
                   from util/annotate.c:14:
  /usr/include/bits/stdio2.h:67:10: note: '__builtin___snprintf_chk' output 116 or more bytes (assuming 8331) into a destination of size 8192
     return __builtin___snprintf_chk (__s, __n, __USE_FORTIFY_LEVEL - 1,
            ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
          __bos (__s), __fmt, __va_arg_pack ());
          ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

So switch to asprintf, that will make sure enough space is available.

---
 tools/perf/util/annotate.c |   17 ++++++++++++-----
 1 file changed, 12 insertions(+), 5 deletions(-)

@@ -1432,7 +1432,7 @@ int symbol__disassemble(struct symbol *s
 			struct arch **parch, char *cpuid)
 {
 	struct dso *dso = map->dso;
-	char command[PATH_MAX * 2];
+	char *command;
 	struct arch *arch = NULL;
 	FILE *file;
 	char symfs_filename[PATH_MAX];

@@ -1496,7 +1496,7 @@ int symbol__disassemble(struct symbol *s
 		strcpy(symfs_filename, tmp);
 	}
 
-	snprintf(command, sizeof(command),
+	err = asprintf(&command,
 		 "%s %s%s --start-address=0x%016" PRIx64
 		 " --stop-address=0x%016" PRIx64
 		 " -l -d %s %s -C \"%s\" 2>/dev/null|grep -v \"%s:\"|expand",

@@ -1509,12 +1509,17 @@ int symbol__disassemble(struct symbol *s
 		 symbol_conf.annotate_src ? "-S" : "",
 		 symfs_filename, symfs_filename);
 
+	if (err < 0) {
+		pr_err("Failure allocating memory for the command to run\n");
+		goto out_remove_tmp;
+	}
+
 	pr_debug("Executing: %s\n", command);
 
 	err = -1;
 	if (pipe(stdout_fd) < 0) {
 		pr_err("Failure creating the pipe to run %s\n", command);
-		goto out_remove_tmp;
+		goto out_free_command;
 	}
 
 	pid = fork();

@@ -1541,7 +1546,7 @@ int symbol__disassemble(struct symbol *s
 		 * If we were using debug info should retry with
 		 * original binary.
 		 */
-		goto out_remove_tmp;
+		goto out_free_command;
 	}
 
 	nline = 0;

@@ -1570,6 +1575,8 @@ int symbol__disassemble(struct symbol *s
 
 	fclose(file);
 	err = 0;
+out_free_command:
+	free(command);
 out_remove_tmp:
 	close(stdout_fd[0]);
 

@@ -1583,7 +1590,7 @@ out:
 
 out_close_stdout:
 	close(stdout_fd[1]);
-	goto out_remove_tmp;
+	goto out_free_command;
 }
 
 static void insert_source_line(struct rb_root *root, struct source_line *src_line)

4.14-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jiri Olsa <[email protected]>

commit b7a313d84e853049062011d78cb04b6decd12f5c upstream.

The gcc 8 compiler won't compile the python extension code with the following errors (one example):

  python.c:830:15: error: cast between incompatible  function types from              \
  ‘PyObject * (*)(struct pyrf_evsel *, PyObject *, PyObject *)’                       \
  uct _object * (*)(struct pyrf_evsel *, struct _object *, struct _object *)’} to     \
  ‘PyObject * (*)(PyObject *, PyObject *)’ {aka ‘struct _object * (*)(struct _objeuct \
  _object *)’} [-Werror=cast-function-type]
     .ml_meth  = (PyCFunction)pyrf_evsel__open,

The problem with the PyMethodDef::ml_meth callback is that its type is determined based on the PyMethodDef::ml_flags value, which we set as METH_VARARGS | METH_KEYWORDS.

That indicates that the callback is expecting an extra PyObject* arg, and is actually PyCFunctionWithKeywords type, but the base PyMethodDef::ml_meth type stays PyCFunction.

Previous gccs did not find this, gcc8 now does. Fixing this by silencing this warning for python.c build.

Commiter notes:

Do not do that for CC=clang, as it breaks the build in some clang versions, like the ones in fedora up to fedora27:

fedora:25:error: unknown warning option '-Wno-cast-function-type'; did you mean '-Wno-bad-function-cast'? [-Werror,-Wunknown-warning-option] fedora:26:error: unknown warning option '-Wno-cast-function-type'; did you mean '-Wno-bad-function-cast'? [-Werror,-Wunknown-warning-option] fedora:27:error: unknown warning option '-Wno-cast-function-type'; did you mean '-Wno-bad-function-cast'? [-Werror,-Wunknown-warning-option] #

those have:

clang version 3.9.1 (tags/RELEASE_391/final)

The one in rawhide accepts that:

clang version 6.0.0 (tags/RELEASE_600/final)

---
 tools/perf/util/setup.py |    2 ++
 1 file changed, 2 insertions(+)

@@ -28,6 +28,8 @@ class install_lib(_install_lib):
 cflags = getenv('CFLAGS', '').split()
 # switch off several checks (need to be at the end of cflags list)
 cflags += ['-fno-strict-aliasing', '-Wno-write-strings', '-Wno-unused-parameter' ]
+if cc != "clang":
+    cflags += ['-Wno-cast-function-type' ]
 
 src_perf  = getenv('srctree') + '/tools/perf'
 build_lib = getenv('PYTHON_EXTBUILD_LIB')

4.14-stable review patch. If anyone has any objections, please let me know.

------------------

From: Prateek Sood <[email protected]>

commit aa24163b2ee5c92120e32e99b5a93143a0f4258e upstream.

Remove circular dependency deadlock in a scenario where hotplug of CPU is being done while there is updation in cgroup and cpuset triggered from userspace.

Process A => kthreadd => Process B => Process C => Process A

Process A
cpu_subsys_offline();

  cpu_down();
    _cpu_down();
      percpu_down_write(&cpu_hotplug_lock); //held
      cpuhp_invoke_callback();
	     workqueue_offline_cpu();
            queue_work_on(); // unbind_work on system_highpri_wq
               __queue_work();
                 insert_work();
                    wake_up_worker();
            flush_work();
               wait_for_completion();

worker_thread();

   manage_workers();
      create_worker();
	     kthread_create_on_node();
		    wake_up_process(kthreadd_task);

kthreadd
kthreadd();

  kernel_thread();
    do_fork();
      copy_process();
        percpu_down_read(&cgroup_threadgroup_rwsem);
          __rwsem_down_read_failed_common(); //waiting

Process B
kernfs_fop_write();

  cgroup_file_write();
    cgroup_procs_write();
      percpu_down_write(&cgroup_threadgroup_rwsem); //held
      cgroup_attach_task();
        cgroup_migrate();
          cgroup_migrate_execute();
            cpuset_can_attach();
              mutex_lock(&cpuset_mutex); //waiting

Process C
kernfs_fop_write();

  cgroup_file_write();
    cpuset_write_resmask();
      mutex_lock(&cpuset_mutex); //held
      update_cpumask();
        update_cpumasks_hier();
          rebuild_sched_domains_locked();
            get_online_cpus();
              percpu_down_read(&cpu_hotplug_lock); //waiting

Eliminating deadlock by reversing the locking order for cpuset_mutex and cpu_hotplug_lock.

---
 kernel/cgroup/cpuset.c |   53 +++++++++++++++++++++++++++----------------------
 1 file changed, 30 insertions(+), 23 deletions(-)

@@ -817,6 +817,18 @@ done:
 	return ndoms;
 }
 
+static void cpuset_sched_change_begin(void)
+{
+	cpus_read_lock();
+	mutex_lock(&cpuset_mutex);
+}
+
+static void cpuset_sched_change_end(void)
+{
+	mutex_unlock(&cpuset_mutex);
+	cpus_read_unlock();
+}
+
 /*
  * Rebuild scheduler domains.
  *

@@ -826,16 +838,14 @@ done:
  * 'cpus' is removed, then call this routine to rebuild the
  * scheduler's dynamic sched domains.
  *
- * Call with cpuset_mutex held.  Takes get_online_cpus().
  */
-static void rebuild_sched_domains_locked(void)
+static void rebuild_sched_domains_cpuslocked(void)
 {
 	struct sched_domain_attr *attr;
 	cpumask_var_t *doms;
 	int ndoms;
 
 	lockdep_assert_held(&cpuset_mutex);
-	get_online_cpus();
 
 	/*
 	 * We have raced with CPU hotplug. Don't do anything to avoid

@@ -843,27 +853,25 @@ static void rebuild_sched_domains_locked
 	 * Anyways, hotplug work item will rebuild sched domains.
 	 */
 	if (!cpumask_equal(top_cpuset.effective_cpus, cpu_active_mask))
-		goto out;
+		return;
 
 	/* Generate domain masks and attrs */
 	ndoms = generate_sched_domains(&doms, &attr);
 
 	/* Have scheduler rebuild the domains */
 	partition_sched_domains(ndoms, doms, attr);
-out:
-	put_online_cpus();
 }
 #else /* !CONFIG_SMP */
-static void rebuild_sched_domains_locked(void)
+static void rebuild_sched_domains_cpuslocked(void)
 {
 }
 #endif /* CONFIG_SMP */
 
 void rebuild_sched_domains(void)
 {
-	mutex_lock(&cpuset_mutex);
-	rebuild_sched_domains_locked();
-	mutex_unlock(&cpuset_mutex);
+	cpuset_sched_change_begin();
+	rebuild_sched_domains_cpuslocked();
+	cpuset_sched_change_end();
 }
 
 /**

@@ -949,7 +957,7 @@ static void update_cpumasks_hier(struct
 	rcu_read_unlock();
 
 	if (need_rebuild_sched_domains)
-		rebuild_sched_domains_locked();
+		rebuild_sched_domains_cpuslocked();
 }
 
 /**

@@ -1281,7 +1289,7 @@ static int update_relax_domain_level(str
 		cs->relax_domain_level = val;
 		if (!cpumask_empty(cs->cpus_allowed) &&
 		    is_sched_load_balance(cs))
-			rebuild_sched_domains_locked();
+			rebuild_sched_domains_cpuslocked();
 	}
 
 	return 0;

@@ -1314,7 +1322,6 @@ static void update_tasks_flags(struct cp
  *
  * Call with cpuset_mutex held.
  */
-
 static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs,
 		       int turning_on)
 {

@@ -1347,7 +1354,7 @@ static int update_flag(cpuset_flagbits_t
 	spin_unlock_irq(&callback_lock);
 
 	if (!cpumask_empty(trialcs->cpus_allowed) && balance_flag_changed)
-		rebuild_sched_domains_locked();
+		rebuild_sched_domains_cpuslocked();
 
 	if (spread_flag_changed)
 		update_tasks_flags(cs);

@@ -1615,7 +1622,7 @@ static int cpuset_write_u64(struct cgrou
 	cpuset_filetype_t type = cft->private;
 	int retval = 0;
 
-	mutex_lock(&cpuset_mutex);
+	cpuset_sched_change_begin();
 	if (!is_cpuset_online(cs)) {
 		retval = -ENODEV;
 		goto out_unlock;

@@ -1651,7 +1658,7 @@ static int cpuset_write_u64(struct cgrou
 		break;
 	}
 out_unlock:
-	mutex_unlock(&cpuset_mutex);
+	cpuset_sched_change_end();
 	return retval;
 }
 

@@ -1662,7 +1669,7 @@ static int cpuset_write_s64(struct cgrou
 	cpuset_filetype_t type = cft->private;
 	int retval = -ENODEV;
 
-	mutex_lock(&cpuset_mutex);
+	cpuset_sched_change_begin();
 	if (!is_cpuset_online(cs))
 		goto out_unlock;
 

@@ -1675,7 +1682,7 @@ static int cpuset_write_s64(struct cgrou
 		break;
 	}
 out_unlock:
-	mutex_unlock(&cpuset_mutex);
+	cpuset_sched_change_end();
 	return retval;
 }
 

@@ -1714,7 +1721,7 @@ static ssize_t cpuset_write_resmask(stru
 	kernfs_break_active_protection(of->kn);
 	flush_work(&cpuset_hotplug_work);
 
-	mutex_lock(&cpuset_mutex);
+	cpuset_sched_change_begin();
 	if (!is_cpuset_online(cs))
 		goto out_unlock;
 

@@ -1738,7 +1745,7 @@ static ssize_t cpuset_write_resmask(stru
 
 	free_trial_cpuset(trialcs);
 out_unlock:
-	mutex_unlock(&cpuset_mutex);
+	cpuset_sched_change_end();
 	kernfs_unbreak_active_protection(of->kn);
 	css_put(&cs->css);
 	flush_workqueue(cpuset_migrate_mm_wq);

@@ -2039,14 +2046,14 @@ out_unlock:
 /*
  * If the cpuset being removed has its flag 'sched_load_balance'
  * enabled, then simulate turning sched_load_balance off, which
- * will call rebuild_sched_domains_locked().
+ * will call rebuild_sched_domains_cpuslocked().
  */
 
 static void cpuset_css_offline(struct cgroup_subsys_state *css)
 {
 	struct cpuset *cs = css_cs(css);
 
-	mutex_lock(&cpuset_mutex);
+	cpuset_sched_change_begin();
 
 	if (is_sched_load_balance(cs))
 		update_flag(CS_SCHED_LOAD_BALANCE, cs, 0);

@@ -2054,7 +2061,7 @@ static void cpuset_css_offline(struct cg
 	cpuset_dec();
 	clear_bit(CS_ONLINE, &cs->flags);
 
-	mutex_unlock(&cpuset_mutex);
+	cpuset_sched_change_end();
 }
 
 static void cpuset_css_free(struct cgroup_subsys_state *css)

4.14-stable review patch. If anyone has any objections, please let me know.

------------------

From: Kirill A. Shutemov <[email protected]>

commit e125fe405abedc1dc8a5b2229b80ee91c1434015 upstream.

A transparent huge page is represented by a single entry on an LRU list. Therefore, we can only make unevictable an entire compound page, not individual subpages.

If a user tries to mlock() part of a huge page, we want the rest of the page to be reclaimable.

We handle this by keeping PTE-mapped huge pages on normal LRU lists: the PMD on border of VM_LOCKED VMA will be split into PTE table.

Introduction of THP migration breaks[1] the rules around mlocking THP pages. If we had a single PMD mapping of the page in mlocked VMA, the page will get mlocked, regardless of PTE mappings of the page.

For tmpfs/shmem it's easy to fix by checking PageDoubleMap() in remove_migration_pmd().

Anon THP pages can only be shared between processes via fork(). Mlocked page can only be shared if parent mlocked it before forking, otherwise CoW will be triggered on mlock().

For Anon-THP, we can fix the issue by munlocking the page on removing PTE migration entry for the page. PTEs for the page will always come after mlocked PMD: rmap walks VMAs from oldest to newest.

Test-case:

	#include <unistd.h>
	#include <sys/mman.h>
	#include <sys/wait.h>
	#include <linux/mempolicy.h>
	#include <numaif.h>

	int main(void)
	{
	        unsigned long nodemask = 4;
	        void *addr;

		addr = mmap((void *)0x20000000UL, 2UL << 20, PROT_READ | PROT_WRITE,
			MAP_PRIVATE | MAP_ANONYMOUS | MAP_LOCKED, -1, 0);

	        if (fork()) {
			wait(NULL);
			return 0;
	        }

	        mlock(addr, 4UL << 10);
	        mbind(addr, 2UL << 20, MPOL_PREFERRED | MPOL_F_RELATIVE_NODES,
	                &nodemask, 4, MPOL_MF_MOVE);

	        return 0;
	}

[1] https://lkml.kernel.org/r/CAOMGZ=G52R-30rZvhGxEbkTw7rLLwBGadVYeo--iizcD3upL3A@mail.gmail.com

---
 mm/huge_memory.c |    2 +-
 mm/migrate.c     |    3 +++
 2 files changed, 4 insertions(+), 1 deletion(-)

@@ -2886,7 +2886,7 @@ void remove_migration_pmd(struct page_vm
 	flush_cache_range(vma, mmun_start, mmun_start + HPAGE_PMD_SIZE);
 	page_add_anon_rmap(new, vma, mmun_start, true);
 	set_pmd_at(mm, mmun_start, pvmw->pmd, pmde);
-	if (vma->vm_flags & VM_LOCKED)
+	if ((vma->vm_flags & VM_LOCKED) && !PageDoubleMap(new))
 		mlock_vma_page(new);
 	update_mmu_cache_pmd(vma, address, pvmw->pmd);
 }

@@ -274,6 +274,9 @@ static bool remove_migration_pte(struct
 		if (vma->vm_flags & VM_LOCKED && !PageTransCompound(new))
 			mlock_vma_page(new);
 
+		if (PageTransHuge(page) && PageMlocked(page))
+			clear_page_mlock(page);
+
 		/* No need to invalidate - it was non-present before */
 		update_mmu_cache(vma, pvmw.address, pvmw.pte);
 	}

4.14-stable review patch. If anyone has any objections, please let me know.

------------------

From: Carl Huang <[email protected]>

commit 9ef0f58ed7b4a55da4a64641d538e0d9e46579ac upstream.

The skb may be freed in tx completion context before trace_ath10k_wmi_cmd is called. This can be easily captured when KASAN(Kernel Address Sanitizer) is enabled. The fix is to move trace_ath10k_wmi_cmd before the send operation. As the ret has no meaning in trace_ath10k_wmi_cmd then, so remove this parameter too.

---
 drivers/net/wireless/ath/ath10k/trace.h |   12 ++++--------
 drivers/net/wireless/ath/ath10k/wmi.c   |    2 +-
 2 files changed, 5 insertions(+), 9 deletions(-)

@@ -152,10 +152,9 @@ TRACE_EVENT(ath10k_log_dbg_dump,
 );
 
 TRACE_EVENT(ath10k_wmi_cmd,
-	TP_PROTO(struct ath10k *ar, int id, const void *buf, size_t buf_len,
-		 int ret),
+	TP_PROTO(struct ath10k *ar, int id, const void *buf, size_t buf_len),
 
-	TP_ARGS(ar, id, buf, buf_len, ret),
+	TP_ARGS(ar, id, buf, buf_len),
 
 	TP_STRUCT__entry(
 		__string(device, dev_name(ar->dev))

@@ -163,7 +162,6 @@ TRACE_EVENT(ath10k_wmi_cmd,
 		__field(unsigned int, id)
 		__field(size_t, buf_len)
 		__dynamic_array(u8, buf, buf_len)
-		__field(int, ret)
 	),
 
 	TP_fast_assign(

@@ -171,17 +169,15 @@ TRACE_EVENT(ath10k_wmi_cmd,
 		__assign_str(driver, dev_driver_string(ar->dev));
 		__entry->id = id;
 		__entry->buf_len = buf_len;
-		__entry->ret = ret;
 		memcpy(__get_dynamic_array(buf), buf, buf_len);
 	),
 
 	TP_printk(
-		"%s %s id %d len %zu ret %d",
+		"%s %s id %d len %zu",
 		__get_str(driver),
 		__get_str(device),
 		__entry->id,
-		__entry->buf_len,
-		__entry->ret
+		__entry->buf_len
 	)
 );
 

@@ -1741,8 +1741,8 @@ int ath10k_wmi_cmd_send_nowait(struct at
 	cmd_hdr->cmd_id = __cpu_to_le32(cmd);
 
 	memset(skb_cb, 0, sizeof(*skb_cb));
+	trace_ath10k_wmi_cmd(ar, cmd_id, skb->data, skb->len);
 	ret = ath10k_htc_send(&ar->htc, ar->wmi.eid, skb);
-	trace_ath10k_wmi_cmd(ar, cmd_id, skb->data, skb->len, ret);
 
 	if (ret)
 		goto err_pull;

4.14-stable review patch. If anyone has any objections, please let me know.

------------------

From: Yu Wang <[email protected]>

commit 50e79e25250bf928369996277e85b00536b380c7 upstream.

If device gone during chip reset, ar->normal_mode_fw.board is not initialized, but ath10k_debug_print_hwfw_info() will try to access its member, which will cause 'kernel NULL pointer' issue. This was found using a faulty device (pci link went down sometimes) in a random insmod/rmmod/other-op test.
To fix it, check ar->normal_mode_fw.board before accessing the member.

pci 0000:02:00.0: BAR 0: assigned [mem 0xf7400000-0xf75fffff 64bit] ath10k_pci 0000:02:00.0: enabling device (0000 -> 0002)
ath10k_pci 0000:02:00.0: pci irq msi oper_irq_mode 2 irq_mode 0 reset_mode 0 ath10k_pci 0000:02:00.0: failed to read device register, device is gone ath10k_pci 0000:02:00.0: failed to wait for target init: -5
ath10k_pci 0000:02:00.0: failed to warm reset: -5
ath10k_pci 0000:02:00.0: firmware crashed during chip reset
ath10k_pci 0000:02:00.0: firmware crashed! (uuid 5d018951-b8e1-404a-8fde-923078b4423a) ath10k_pci 0000:02:00.0: (null) target 0x00000000 chip_id 0x00340aff sub 0000:0000 ath10k_pci 0000:02:00.0: kconfig debug 1 debugfs 1 tracing 1 dfs 1 testmode 1 ath10k_pci 0000:02:00.0: firmware ver api 0 features crc32 00000000
...

BUG: unable to handle kernel NULL pointer dereference at 00000004
...
Call Trace:
 [<fb4e7882>] ath10k_print_driver_info+0x12/0x20 [ath10k_core]
 [<fb62b7dd>] ath10k_pci_fw_crashed_dump+0x6d/0x4d0 [ath10k_pci]
 [<fb629f07>] ? ath10k_pci_sleep.part.19+0x57/0xc0 [ath10k_pci]
 [<fb62c8ee>] ath10k_pci_hif_power_up+0x14e/0x1b0 [ath10k_pci]
 [<c10477fb>] ? do_page_fault+0xb/0x10
 [<fb4eb934>] ath10k_core_register_work+0x24/0x840 [ath10k_core]
 [<c18a00d8>] ? netlbl_unlhsh_remove+0x178/0x410
 [<c10477f0>] ? __do_page_fault+0x480/0x480
 [<c1068e44>] process_one_work+0x114/0x3e0
 [<c1069d07>] worker_thread+0x37/0x4a0
 [<c106e294>] kthread+0xa4/0xc0
 [<c1069cd0>] ? create_worker+0x180/0x180
 [<c106e1f0>] ? kthread_park+0x50/0x50
 [<c18ab4f7>] ret_from_fork+0x1b/0x28
 Code: 78 80 b8 50 09 00 00 00 75 5d 8d 75 94 c7 44 24 08 aa d7 52 fb c7 44 24 04 64 00 00 00
 89 34 24 e8 82 52 e2 c5 8b 83 dc 08 00 00 <8b> 50 04 8b 08 31 c0 e8 20 57 e3 c5 89 44 24 10 8b 83 58 09 00
 EIP: [<fb4e7754>]-
 ath10k_debug_print_board_info+0x34/0xb0 [ath10k_core]
 SS:ESP 0068:f4921d90
 CR2: 0000000000000004

---
 drivers/net/wireless/ath/ath10k/debug.c |   12 ++++++++++--
 1 file changed, 10 insertions(+), 2 deletions(-)

@@ -1,6 +1,7 @@
 /*
  * Copyright (c) 2005-2011 Atheros Communications Inc.
  * Copyright (c) 2011-2013 Qualcomm Atheros, Inc.
+ * Copyright (c) 2018, The Linux Foundation. All rights reserved.
  *
  * Permission to use, copy, modify, and/or distribute this software for any
  * purpose with or without fee is hereby granted, provided that the above

@@ -163,6 +164,8 @@ void ath10k_debug_print_hwfw_info(struct
 void ath10k_debug_print_board_info(struct ath10k *ar)
 {
 	char boardinfo[100];
+	const struct firmware *board;
+	u32 crc;
 
 	if (ar->id.bmi_ids_valid)
 		scnprintf(boardinfo, sizeof(boardinfo), "%d:%d",

@@ -170,11 +173,16 @@ void ath10k_debug_print_board_info(struc
 	else
 		scnprintf(boardinfo, sizeof(boardinfo), "N/A");
 
+	board = ar->normal_mode_fw.board;
+	if (!IS_ERR_OR_NULL(board))
+		crc = crc32_le(0, board->data, board->size);
+	else
+		crc = 0;
+
 	ath10k_info(ar, "board_file api %d bmi_id %s crc32 %08x",
 		    ar->bd_api,
 		    boardinfo,
-		    crc32_le(0, ar->normal_mode_fw.board->data,
-			     ar->normal_mode_fw.board->size));
+		    crc);
 }
 
 void ath10k_debug_print_boot_info(struct ath10k *ar)

4.14-stable review patch. If anyone has any objections, please let me know.

------------------

From: James Smart <[email protected]>

commit cf25809bec2c7df4b45df5b2196845d9a4a3c89b upstream.

If there are errors during initial controller create, the transport will teardown the partially initialized controller struct and free the ctlr memory. Trouble is - most of those errors can occur due to asynchronous events happening such io timeouts and subsystem connectivity failures. Those failures invoke async workq items to reset the controller and attempt reconnect. Those may be in progress as the main thread frees the ctrl memory, resulting in NULL ptr oops.

Prevent this from happening by having the main ctrl failure thread changing state to DELETING followed by synchronously cancelling any pending queued work item. The change of state will prevent the scheduling of resets or reconnect events.

---
 drivers/nvme/host/fc.c |    4 ++++
 1 file changed, 4 insertions(+)

@@ -2868,6 +2868,10 @@ nvme_fc_init_ctrl(struct device *dev, st
 	}
 
 	if (ret) {
+		nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_DELETING);
+		cancel_work_sync(&ctrl->ctrl.reset_work);
+		cancel_delayed_work_sync(&ctrl->connect_work);
+
 		/* couldn't schedule retry - fail out */
 		dev_err(ctrl->ctrl.device,
 			"NVME-FC{%d}: Connect retry failed\n", ctrl->cnum);

4.14-stable review patch. If anyone has any objections, please let me know.

------------------

From: Christophe Leroy <[email protected]>

commit 8cf4c05712f04a405f0dacebcca8f042b391694a upstream.

patch_instruction() uses almost the same sequence as __patch_instruction()

This patch refactor it so that patch_instruction() uses __patch_instruction() instead of duplicating code.

---
 arch/powerpc/lib/code-patching.c |   30 +++++++++++++++---------------
 1 file changed, 15 insertions(+), 15 deletions(-)

@@ -23,19 +23,26 @@
 #include <asm/code-patching.h>
 #include <asm/setup.h>
 
-static int __patch_instruction(unsigned int *addr, unsigned int instr)
+static int __patch_instruction(unsigned int *exec_addr, unsigned int instr,
+			       unsigned int *patch_addr)
 {
 	int err;
 
-	__put_user_size(instr, addr, 4, err);
+	__put_user_size(instr, patch_addr, 4, err);
 	if (err)
 		return err;
 
-	asm ("dcbst 0, %0; sync; icbi 0,%0; sync; isync" :: "r" (addr));
+	asm ("dcbst 0, %0; sync; icbi 0,%1; sync; isync" :: "r" (patch_addr),
+							    "r" (exec_addr));
 
 	return 0;
 }
 
+static int raw_patch_instruction(unsigned int *addr, unsigned int instr)
+{
+	return __patch_instruction(addr, instr, addr);
+}
+
 #ifdef CONFIG_STRICT_KERNEL_RWX
 static DEFINE_PER_CPU(struct vm_struct *, text_poke_area);
 

@@ -138,7 +145,7 @@ static inline int unmap_patch_area(unsig
 int patch_instruction(unsigned int *addr, unsigned int instr)
 {
 	int err;
-	unsigned int *dest = NULL;
+	unsigned int *patch_addr = NULL;
 	unsigned long flags;
 	unsigned long text_poke_addr;
 	unsigned long kaddr = (unsigned long)addr;

@@ -149,7 +156,7 @@ int patch_instruction(unsigned int *addr
 	 * to allow patching. We just do the plain old patching
 	 */
 	if (!this_cpu_read(*PTRRELOC(&text_poke_area)))
-		return __patch_instruction(addr, instr);
+		return raw_patch_instruction(addr, instr);
 
 	local_irq_save(flags);
 

@@ -159,17 +166,10 @@ int patch_instruction(unsigned int *addr
 		goto out;
 	}
 
-	dest = (unsigned int *)(text_poke_addr) +
+	patch_addr = (unsigned int *)(text_poke_addr) +
 			((kaddr & ~PAGE_MASK) / sizeof(unsigned int));
 
-	/*
-	 * We use __put_user_size so that we can handle faults while
-	 * writing to dest and return err to handle faults gracefully
-	 */
-	__put_user_size(instr, dest, 4, err);
-	if (!err)
-		asm ("dcbst 0, %0; sync; icbi 0,%0; icbi 0,%1; sync; isync"
-			::"r" (dest), "r"(addr));
+	__patch_instruction(addr, instr, patch_addr);
 
 	err = unmap_patch_area(text_poke_addr);
 	if (err)

@@ -184,7 +184,7 @@ out:
 
 int patch_instruction(unsigned int *addr, unsigned int instr)
 {
-	return __patch_instruction(addr, instr);
+	return raw_patch_instruction(addr, instr);
 }
 
 #endif /* CONFIG_STRICT_KERNEL_RWX */

4.14-stable review patch. If anyone has any objections, please let me know.

------------------

From: Michael Neuling <[email protected]>

commit 51c3c62b58b357e8d35e4cc32f7b4ec907426fe3 upstream.

This stops us from doing code patching in init sections after they've been freed.

In this chain:
kvm_guest_init() ->

    kvm_use_magic_page() ->
      fault_in_pages_readable() ->
	 __get_user() ->
	   __get_user_nocheck() ->
	     barrier_nospec();

We have a code patching location at barrier_nospec() and kvm_guest_init() is an init function. This whole chain gets inlined, so when we free the init section (hence kvm_guest_init()), this code goes away and hence should no longer be patched.

We seen this as userspace memory corruption when using a memory checker while doing partition migration testing on powervm (this starts the code patching post migration via /sys/kernel/mobility/migration). In theory, it could also happen when using /sys/kernel/debug/powerpc/barrier_nospec.

---
 arch/powerpc/include/asm/setup.h |    1 +
 arch/powerpc/lib/code-patching.c |    6 ++++++
 arch/powerpc/mm/mem.c            |    2 ++
 3 files changed, 9 insertions(+)

@@ -9,6 +9,7 @@ extern void ppc_printk_progress(char *s,
 
 extern unsigned int rtas_data;
 extern unsigned long long memory_limit;
+extern bool init_mem_is_free;
 extern unsigned long klimit;
 extern void *zalloc_maybe_bootmem(size_t size, gfp_t mask);
 

@@ -28,6 +28,12 @@ static int __patch_instruction(unsigned
 {
 	int err;
 
+	/* Make sure we aren't patching a freed init section */
+	if (init_mem_is_free && init_section_contains(exec_addr, 4)) {
+		pr_debug("Skipping init section patching addr: 0x%px\n", exec_addr);
+		return 0;
+	}
+
 	__put_user_size(instr, patch_addr, 4, err);
 	if (err)
 		return err;

@@ -63,6 +63,7 @@
 #endif
 
 unsigned long long memory_limit;
+bool init_mem_is_free;
 
 #ifdef CONFIG_HIGHMEM
 pte_t *kmap_pte;

@@ -405,6 +406,7 @@ void free_initmem(void)
 {
 	ppc_md.progress = ppc_printk_progress;
 	mark_initmem_nx();
+	init_mem_is_free = true;
 	free_initmem_default(POISON_FREE_INITMEM);
 }
 

4.14-stable review patch. If anyone has any objections, please let me know.

------------------

From: Christophe Leroy <[email protected]>

commit b45ba4a51cde29b2939365ef0c07ad34c8321789 upstream.

Commit 51c3c62b58b3 ("powerpc: Avoid code patching freed init sections") accesses 'init_mem_is_free' flag too early, before the kernel is relocated. This provokes early boot failure (before the console is active).

As it is not necessary to do this verification that early, this patch moves the test into patch_instruction() instead of __patch_instruction().

This modification also has the advantage of avoiding unnecessary remappings.

---
 arch/powerpc/lib/code-patching.c |   20 ++++++++++++--------
 1 file changed, 12 insertions(+), 8 deletions(-)

@@ -28,12 +28,6 @@ static int __patch_instruction(unsigned
 {
 	int err;
 
-	/* Make sure we aren't patching a freed init section */
-	if (init_mem_is_free && init_section_contains(exec_addr, 4)) {
-		pr_debug("Skipping init section patching addr: 0x%px\n", exec_addr);
-		return 0;
-	}
-
 	__put_user_size(instr, patch_addr, 4, err);
 	if (err)
 		return err;

@@ -148,7 +142,7 @@ static inline int unmap_patch_area(unsig
 	return 0;
 }
 
-int patch_instruction(unsigned int *addr, unsigned int instr)
+static int do_patch_instruction(unsigned int *addr, unsigned int instr)
 {
 	int err;
 	unsigned int *patch_addr = NULL;

@@ -188,12 +182,22 @@ out:
 }
 #else /* !CONFIG_STRICT_KERNEL_RWX */
 
-int patch_instruction(unsigned int *addr, unsigned int instr)
+static int do_patch_instruction(unsigned int *addr, unsigned int instr)
 {
 	return raw_patch_instruction(addr, instr);
 }
 
 #endif /* CONFIG_STRICT_KERNEL_RWX */
+
+int patch_instruction(unsigned int *addr, unsigned int instr)
+{
+	/* Make sure we aren't patching a freed init section */
+	if (init_mem_is_free && init_section_contains(addr, 4)) {
+		pr_debug("Skipping init section patching addr: 0x%px\n", addr);
+		return 0;
+	}
+	return do_patch_instruction(addr, instr);
+}
 NOKPROBE_SYMBOL(patch_instruction);
 
 int patch_branch(unsigned int *addr, unsigned long target, int flags)

4.14-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jann Horn <[email protected]>

commit 58bc4c34d249bf1bc50730a9a209139347cfacfe upstream.

5dd0b16cdaff ("mm/vmstat: Make NR_TLB_REMOTE_FLUSH_RECEIVED available even on UP") made the availability of the NR_TLB_REMOTE_FLUSH* counters inside the kernel unconditional to reduce #ifdef soup, but (either to avoid showing dummy zero counters to userspace, or because that code was missed) didn't update the vmstat_array, meaning that all following counters would be shown with incorrect values.

This only affects kernel builds with CONFIG_VM_EVENT_COUNTERS=y && CONFIG_DEBUG_TLBFLUSH=y && CONFIG_SMP=n.

---
 mm/vmstat.c |    3 +++
 1 file changed, 3 insertions(+)

@@ -1203,6 +1203,9 @@ const char * const vmstat_text[] = {
 #ifdef CONFIG_SMP
 	"nr_tlb_remote_flush",
 	"nr_tlb_remote_flush_received",
+#else
+	"", /* nr_tlb_remote_flush */
+	"", /* nr_tlb_remote_flush_received */
 #endif /* CONFIG_SMP */
 	"nr_tlb_local_flush_all",
 	"nr_tlb_local_flush_one",

4.14-stable review patch. If anyone has any objections, please let me know.

------------------

From: Sean Christopherson <[email protected]>

commit daa07cbc9ae3da2d61b7ce900c0b9107d134f2c1 upstream.

One defense against L1TF in KVM is to always set the upper five bits of the *legal* physical address in the SPTEs for non-present and reserved SPTEs, e.g. MMIO SPTEs. In the MMIO case, the GFN of the MMIO SPTE may overlap with the upper five bits that are being usurped to defend against L1TF. To preserve the GFN, the bits of the GFN that overlap with the repurposed bits are shifted left into the reserved bits, i.e. the GFN in the SPTE will be split into high and low parts. When retrieving the GFN from the MMIO SPTE, e.g. to check for an MMIO access, get_mmio_spte_gfn() unshifts the affected bits and restores the original GFN for comparison. Unfortunately, get_mmio_spte_gfn() neglects to mask off the reserved bits in the SPTE that were used to store the upper chunk of the GFN. As a result, KVM fails to detect MMIO accesses whose GPA overlaps the repurprosed bits, which in turn causes guest panics and hangs.

Fix the bug by generating a mask that covers the lower chunk of the GFN, i.e. the bits that aren't shifted by the L1TF mitigation. The alternative approach would be to explicitly zero the five reserved bits that are used to store the upper chunk of the GFN, but that requires additional run-time computation and makes an already-ugly bit of code even more inscrutable.

I considered adding a WARN_ON_ONCE(low_phys_bits-1 <= PAGE_SHIFT) to warn if GENMASK_ULL() generated a nonsensical value, but that seemed silly since that would mean a system that supports VMX has less than 18 bits of physical address space...

---
 arch/x86/kvm/mmu.c |   24 ++++++++++++++++++++----
 1 file changed, 20 insertions(+), 4 deletions(-)

@@ -231,6 +231,17 @@ static u64 __read_mostly shadow_nonprese
  */
 static const u64 shadow_nonpresent_or_rsvd_mask_len = 5;
 
+/*
+ * In some cases, we need to preserve the GFN of a non-present or reserved
+ * SPTE when we usurp the upper five bits of the physical address space to
+ * defend against L1TF, e.g. for MMIO SPTEs.  To preserve the GFN, we'll
+ * shift bits of the GFN that overlap with shadow_nonpresent_or_rsvd_mask
+ * left into the reserved bits, i.e. the GFN in the SPTE will be split into
+ * high and low parts.  This mask covers the lower bits of the GFN.
+ */
+static u64 __read_mostly shadow_nonpresent_or_rsvd_lower_gfn_mask;
+
+
 static void mmu_spte_set(u64 *sptep, u64 spte);
 static void mmu_free_roots(struct kvm_vcpu *vcpu);
 

@@ -338,9 +349,7 @@ static bool is_mmio_spte(u64 spte)
 
 static gfn_t get_mmio_spte_gfn(u64 spte)
 {
-	u64 mask = generation_mmio_spte_mask(MMIO_GEN_MASK) | shadow_mmio_mask |
-		   shadow_nonpresent_or_rsvd_mask;
-	u64 gpa = spte & ~mask;
+	u64 gpa = spte & shadow_nonpresent_or_rsvd_lower_gfn_mask;
 
 	gpa |= (spte >> shadow_nonpresent_or_rsvd_mask_len)
 	       & shadow_nonpresent_or_rsvd_mask;

@@ -404,6 +413,8 @@ EXPORT_SYMBOL_GPL(kvm_mmu_set_mask_ptes)
 
 static void kvm_mmu_reset_all_pte_masks(void)
 {
+	u8 low_phys_bits;
+
 	shadow_user_mask = 0;
 	shadow_accessed_mask = 0;
 	shadow_dirty_mask = 0;

@@ -418,12 +429,17 @@ static void kvm_mmu_reset_all_pte_masks(
 	 * appropriate mask to guard against L1TF attacks. Otherwise, it is
 	 * assumed that the CPU is not vulnerable to L1TF.
 	 */
+	low_phys_bits = boot_cpu_data.x86_phys_bits;
 	if (boot_cpu_data.x86_phys_bits <
-	    52 - shadow_nonpresent_or_rsvd_mask_len)
+	    52 - shadow_nonpresent_or_rsvd_mask_len) {
 		shadow_nonpresent_or_rsvd_mask =
 			rsvd_bits(boot_cpu_data.x86_phys_bits -
 				  shadow_nonpresent_or_rsvd_mask_len,
 				  boot_cpu_data.x86_phys_bits - 1);
+		low_phys_bits -= shadow_nonpresent_or_rsvd_mask_len;
+	}
+	shadow_nonpresent_or_rsvd_lower_gfn_mask =
+		GENMASK_ULL(low_phys_bits - 1, PAGE_SHIFT);
 }
 
 static int is_cpuid_PSE36(void)

4.14-stable review patch. If anyone has any objections, please let me know.

------------------

From: Alexandre Belloni <[email protected]>

commit 52bf4a900d9cede3eb14982d0f2c5e6db6d97cc3 upstream.

The smatch utility reports a possible leak:

smatch warnings:
drivers/clocksource/timer-atmel-pit.c:183 at91sam926x_pit_dt_init() warn: possible memory leak of 'data'

Ensure data is freed before exiting with an error.

---
 drivers/clocksource/timer-atmel-pit.c |   20 ++++++++++++++------
 1 file changed, 14 insertions(+), 6 deletions(-)

@@ -180,26 +180,29 @@ static int __init at91sam926x_pit_dt_ini
 	data->base = of_iomap(node, 0);
 	if (!data->base) {
 		pr_err("Could not map PIT address\n");
-		return -ENXIO;
+		ret = -ENXIO;
+		goto exit;
 	}
 
 	data->mck = of_clk_get(node, 0);
 	if (IS_ERR(data->mck)) {
 		pr_err("Unable to get mck clk\n");
-		return PTR_ERR(data->mck);
+		ret = PTR_ERR(data->mck);
+		goto exit;
 	}
 
 	ret = clk_prepare_enable(data->mck);
 	if (ret) {
 		pr_err("Unable to enable mck\n");
-		return ret;
+		goto exit;
 	}
 
 	/* Get the interrupts property */
 	data->irq = irq_of_parse_and_map(node, 0);
 	if (!data->irq) {
 		pr_err("Unable to get IRQ from DT\n");
-		return -EINVAL;
+		ret = -EINVAL;
+		goto exit;
 	}
 
 	/*

@@ -227,7 +230,7 @@ static int __init at91sam926x_pit_dt_ini
 	ret = clocksource_register_hz(&data->clksrc, pit_rate);
 	if (ret) {
 		pr_err("Failed to register clocksource\n");
-		return ret;
+		goto exit;
 	}
 
 	/* Set up irq handler */

@@ -236,7 +239,8 @@ static int __init at91sam926x_pit_dt_ini
 			  "at91_tick", data);
 	if (ret) {
 		pr_err("Unable to setup IRQ\n");
-		return ret;
+		clocksource_unregister(&data->clksrc);
+		goto exit;
 	}
 
 	/* Set up and register clockevents */

@@ -254,6 +258,10 @@ static int __init at91sam926x_pit_dt_ini
 	clockevents_register_device(&data->clkevt);
 
 	return 0;
+
+exit:
+	kfree(data);
+	return ret;
 }
 TIMER_OF_DECLARE(at91sam926x_pit, "atmel,at91sam9260-pit",
 		       at91sam926x_pit_dt_init);

4.14-stable review patch. If anyone has any objections, please let me know.

------------------

From: Tomi Valkeinen <[email protected]>

commit 1bafcbf59fed92af58955024452f45430d3898c5 upstream.

OMAPFB_MEMORY_READ ioctl reads pixels from the LCD's memory and copies them to a userspace buffer. The code has two issues:

- The user provided width and height could be large enough to overflow the calculations
- The copy_to_user() can copy uninitialized memory to the userspace, which might contain sensitive kernel information.

Fix these by limiting the width & height parameters, and only copying the amount of data that we actually received from the LCD.

---
 drivers/video/fbdev/omap2/omapfb/omapfb-ioctl.c |    5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

@@ -496,6 +496,9 @@ static int omapfb_memory_read(struct fb_
 	if (!access_ok(VERIFY_WRITE, mr->buffer, mr->buffer_size))
 		return -EFAULT;
 
+	if (mr->w > 4096 || mr->h > 4096)
+		return -EINVAL;
+
 	if (mr->w * mr->h * 3 > mr->buffer_size)
 		return -EINVAL;
 

@@ -509,7 +512,7 @@ static int omapfb_memory_read(struct fb_
 			mr->x, mr->y, mr->w, mr->h);
 
 	if (r > 0) {
-		if (copy_to_user(mr->buffer, buf, mr->buffer_size))
+		if (copy_to_user(mr->buffer, buf, r))
 			r = -EFAULT;
 	}
 

4.14-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jan Beulich <[email protected]>

commit 780e83c259fc33e8959fed8dfdad17e378d72b62 upstream.

Both len and off are frontend specified values, so we need to make sure there's no overflow when adding the two for the bounds check. We also want to avoid undefined behavior and hence use off to index into ->hash.mapping[] only after bounds checking. This at the same time allows to take care of not applying off twice for the bounds checking against vif->num_queues.

It is also insufficient to bounds check copy_op.len, as this is len truncated to 16 bits.

This is XSA-270 / CVE-2018-15471.

---
 drivers/net/xen-netback/hash.c |   12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

@@ -332,20 +332,22 @@ u32 xenvif_set_hash_mapping_size(struct
 u32 xenvif_set_hash_mapping(struct xenvif *vif, u32 gref, u32 len,
 			    u32 off)
 {
-	u32 *mapping = &vif->hash.mapping[off];
+	u32 *mapping = vif->hash.mapping;
 	struct gnttab_copy copy_op = {
 		.source.u.ref = gref,
 		.source.domid = vif->domid,
-		.dest.u.gmfn = virt_to_gfn(mapping),
 		.dest.domid = DOMID_SELF,
-		.dest.offset = xen_offset_in_page(mapping),
-		.len = len * sizeof(u32),
+		.len = len * sizeof(*mapping),
 		.flags = GNTCOPY_source_gref
 	};
 
-	if ((off + len > vif->hash.size) || copy_op.len > XEN_PAGE_SIZE)
+	if ((off + len < off) || (off + len > vif->hash.size) ||
+	    len > XEN_PAGE_SIZE / sizeof(*mapping))
 		return XEN_NETIF_CTRL_STATUS_INVALID_PARAMETER;
 
+	copy_op.dest.u.gmfn = virt_to_gfn(mapping + off);
+	copy_op.dest.offset = xen_offset_in_page(mapping + off);
+
 	while (len-- != 0)
 		if (mapping[off++] >= vif->num_queues)
 			return XEN_NETIF_CTRL_STATUS_INVALID_PARAMETER;

4.14-stable review patch. If anyone has any objections, please let me know.

------------------

From: Harsh Jain <[email protected]>

commit add92a817e60e308a419693413a38d9d1e663aff upstream.

Update PCI Id in "cpl_rx_phys_dsgl" header. In case pci_chan_id and tx_chan_id are not derived from same queue, H/W can send request completion indication before completing DMA Transfer.

Herbert, It would be good if fix can be merge to stable tree. For 4.14 kernel, It requires some update to avoid mege conficts.

---
 drivers/crypto/chelsio/chcr_algo.c   |   41 +++++++++++++++++++++++------------
 drivers/crypto/chelsio/chcr_crypto.h |    2 +
 2 files changed, 29 insertions(+), 14 deletions(-)

@@ -384,7 +384,8 @@ static inline int is_hmac(struct crypto_
 
 static void write_phys_cpl(struct cpl_rx_phys_dsgl *phys_cpl,
 			   struct scatterlist *sg,
-			   struct phys_sge_parm *sg_param)
+			   struct phys_sge_parm *sg_param,
+			   int pci_chan_id)
 {
 	struct phys_sge_pairs *to;
 	unsigned int len = 0, left_size = sg_param->obsize;

@@ -402,6 +403,7 @@ static void write_phys_cpl(struct cpl_rx
 	phys_cpl->rss_hdr_int.opcode = CPL_RX_PHYS_ADDR;
 	phys_cpl->rss_hdr_int.qid = htons(sg_param->qid);
 	phys_cpl->rss_hdr_int.hash_val = 0;
+	phys_cpl->rss_hdr_int.channel = pci_chan_id;
 	to = (struct phys_sge_pairs *)((unsigned char *)phys_cpl +
 				       sizeof(struct cpl_rx_phys_dsgl));
 	for (i = 0; nents && left_size; to++) {

@@ -418,7 +420,8 @@ static void write_phys_cpl(struct cpl_rx
 static inline int map_writesg_phys_cpl(struct device *dev,
 					struct cpl_rx_phys_dsgl *phys_cpl,
 					struct scatterlist *sg,
-					struct phys_sge_parm *sg_param)
+					struct phys_sge_parm *sg_param,
+					int pci_chan_id)
 {
 	if (!sg || !sg_param->nents)
 		return -EINVAL;

@@ -428,7 +431,7 @@ static inline int map_writesg_phys_cpl(s
 		pr_err("CHCR : DMA mapping failed\n");
 		return -EINVAL;
 	}
-	write_phys_cpl(phys_cpl, sg, sg_param);
+	write_phys_cpl(phys_cpl, sg, sg_param, pci_chan_id);
 	return 0;
 }
 

@@ -608,7 +611,7 @@ static inline void create_wreq(struct ch
 				is_iv ? iv_loc : IV_NOP, !!lcb,
 				ctx->tx_qidx);
 
-	chcr_req->ulptx.cmd_dest = FILL_ULPTX_CMD_DEST(ctx->dev->tx_channel_id,
+	chcr_req->ulptx.cmd_dest = FILL_ULPTX_CMD_DEST(ctx->tx_chan_id,
 						       qid);
 	chcr_req->ulptx.len = htonl((DIV_ROUND_UP((calc_tx_flits_ofld(skb) * 8),
 					16) - ((sizeof(chcr_req->wreq)) >> 4)));

@@ -698,7 +701,8 @@ static struct sk_buff *create_cipher_wr(
 	sg_param.obsize =  wrparam->bytes;
 	sg_param.qid = wrparam->qid;
 	error = map_writesg_phys_cpl(&u_ctx->lldi.pdev->dev, phys_cpl,
-				       reqctx->dst, &sg_param);
+				       reqctx->dst, &sg_param,
+				       ctx->pci_chan_id);
 	if (error)
 		goto map_fail1;
 

@@ -1228,16 +1232,23 @@ static int chcr_device_init(struct chcr_
 				    adap->vres.ncrypto_fc);
 		rxq_perchan = u_ctx->lldi.nrxq / u_ctx->lldi.nchan;
 		txq_perchan = ntxq / u_ctx->lldi.nchan;
-		rxq_idx = ctx->dev->tx_channel_id * rxq_perchan;
-		rxq_idx += id % rxq_perchan;
-		txq_idx = ctx->dev->tx_channel_id * txq_perchan;
-		txq_idx += id % txq_perchan;
 		spin_lock(&ctx->dev->lock_chcr_dev);
-		ctx->rx_qidx = rxq_idx;
-		ctx->tx_qidx = txq_idx;
+		ctx->tx_chan_id = ctx->dev->tx_channel_id;
 		ctx->dev->tx_channel_id = !ctx->dev->tx_channel_id;
 		ctx->dev->rx_channel_id = 0;
 		spin_unlock(&ctx->dev->lock_chcr_dev);
+		rxq_idx = ctx->tx_chan_id * rxq_perchan;
+		rxq_idx += id % rxq_perchan;
+		txq_idx = ctx->tx_chan_id * txq_perchan;
+		txq_idx += id % txq_perchan;
+		ctx->rx_qidx = rxq_idx;
+		ctx->tx_qidx = txq_idx;
+		/* Channel Id used by SGE to forward packet to Host.
+		 * Same value should be used in cpl_fw6_pld RSS_CH field
+		 * by FW. Driver programs PCI channel ID to be used in fw
+		 * at the time of queue allocation with value "pi->tx_chan"
+		 */
+		ctx->pci_chan_id = txq_idx / txq_perchan;
 	}
 out:
 	return err;

@@ -2066,7 +2077,8 @@ static struct sk_buff *create_authenc_wr
 	sg_param.obsize = req->cryptlen + (op_type ? -authsize : authsize);
 	sg_param.qid = qid;
 	error = map_writesg_phys_cpl(&u_ctx->lldi.pdev->dev, phys_cpl,
-					reqctx->dst, &sg_param);
+					reqctx->dst, &sg_param,
+					ctx->pci_chan_id);
 	if (error)
 		goto dstmap_fail;
 

@@ -2389,7 +2401,7 @@ static struct sk_buff *create_aead_ccm_w
 	sg_param.obsize = req->cryptlen + (op_type ? -authsize : authsize);
 	sg_param.qid = qid;
 	error = map_writesg_phys_cpl(&u_ctx->lldi.pdev->dev, phys_cpl,
-				 reqctx->dst, &sg_param);
+				 reqctx->dst, &sg_param, ctx->pci_chan_id);
 	if (error)
 		goto dstmap_fail;
 

@@ -2545,7 +2557,8 @@ static struct sk_buff *create_gcm_wr(str
 	sg_param.obsize = req->cryptlen + (op_type ? -authsize : authsize);
 	sg_param.qid = qid;
 	error = map_writesg_phys_cpl(&u_ctx->lldi.pdev->dev, phys_cpl,
-					  reqctx->dst, &sg_param);
+					  reqctx->dst, &sg_param,
+					  ctx->pci_chan_id);
 	if (error)
 		goto dstmap_fail;
 

@@ -222,6 +222,8 @@ struct chcr_context {
 	struct chcr_dev *dev;
 	unsigned char tx_qidx;
 	unsigned char rx_qidx;
+	unsigned char tx_chan_id;
+	unsigned char pci_chan_id;
 	struct __crypto_ctx crypto_ctx[0];
 };
 

4.14-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jiri Olsa <[email protected]>

commit 06c3f2aa9fc68e7f3fe3d83e7569d2a2801d9f99 upstream.

So that it can be used more widely, like in the next patch, when it will be used to fix a bug in 'perf test' handling of dirent.d_type == DT_UNKNOWN.

---
 tools/perf/builtin-script.c |   14 +-------------
 tools/perf/util/path.c      |   14 ++++++++++++++
 tools/perf/util/path.h      |    3 +++
 3 files changed, 18 insertions(+), 13 deletions(-)

@@ -25,6 +25,7 @@
 #include "util/string2.h"
 #include "util/thread-stack.h"
 #include "util/time-utils.h"
+#include "util/path.h"
 #include "print_binary.h"
 #include <linux/bitmap.h>
 #include <linux/kernel.h>

@@ -2129,19 +2130,6 @@ out:
 	return rc;
 }
 
-/* Helper function for filesystems that return a dent->d_type DT_UNKNOWN */
-static int is_directory(const char *base_path, const struct dirent *dent)
-{
-	char path[PATH_MAX];
-	struct stat st;
-
-	sprintf(path, "%s/%s", base_path, dent->d_name);
-	if (stat(path, &st))
-		return 0;
-
-	return S_ISDIR(st.st_mode);
-}
-
 #define for_each_lang(scripts_path, scripts_dir, lang_dirent)		\
 	while ((lang_dirent = readdir(scripts_dir)) != NULL)		\
 		if ((lang_dirent->d_type == DT_DIR ||			\

@@ -18,6 +18,7 @@
 #include <stdio.h>
 #include <sys/types.h>
 #include <sys/stat.h>
+#include <dirent.h>
 #include <unistd.h>
 
 static char bad_path[] = "/bad-path/";

@@ -77,3 +78,16 @@ bool is_regular_file(const char *file)
 
 	return S_ISREG(st.st_mode);
 }
+
+/* Helper function for filesystems that return a dent->d_type DT_UNKNOWN */
+bool is_directory(const char *base_path, const struct dirent *dent)
+{
+	char path[PATH_MAX];
+	struct stat st;
+
+	sprintf(path, "%s/%s", base_path, dent->d_name);
+	if (stat(path, &st))
+		return false;
+
+	return S_ISDIR(st.st_mode);
+}

@@ -2,9 +2,12 @@
 #ifndef _PERF_PATH_H
 #define _PERF_PATH_H
 
+struct dirent;
+
 int path__join(char *bf, size_t size, const char *path1, const char *path2);
 int path__join3(char *bf, size_t size, const char *path1, const char *path2, const char *path3);
 
 bool is_regular_file(const char *file);
+bool is_directory(const char *base_path, const struct dirent *dent);
 
 #endif /* _PERF_PATH_H */

4.14-stable review patch. If anyone has any objections, please let me know.

------------------

From: Chao Yu <[email protected]>

commit d3f07c049dab1a3f1740f476afd3d5e5b738c21c upstream.

syzbot found the following crash on:

HEAD commit:    d9bd94c0bcaa Add linux-next specific files for 20180801
git tree:       linux-next
console output: https://syzkaller.appspot.com/x/log.txt?x=1001189c400000
kernel config:  https://syzkaller.appspot.com/x/.config?x=cc8964ea4d04518c
dashboard link: https://syzkaller.appspot.com/bug?extid=c966a82db0b14aa37e81
compiler:       gcc (GCC) 8.0.1 20180413 (experimental)

Unfortunately, I don't have any reproducer for this crash yet.

IMPORTANT: if you fix the bug, please add the following tag to the commit:

loop7: rw=12288, want=8200, limit=20
netlink: 65342 bytes leftover after parsing attributes in process `syz-executor4'.
openvswitch: netlink: Message has 8 unknown bytes.
kasan: CONFIG_KASAN_INLINE enabled
kasan: GPF could be caused by NULL-ptr deref or user memory access

general protection fault: 0000 [#1] SMP KASAN
CPU: 1 PID: 7615 Comm: syz-executor7 Not tainted 4.18.0-rc7-next-20180801+ #29
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
RIP: 0010:__read_once_size include/linux/compiler.h:188 [inline]
RIP: 0010:compound_head include/linux/page-flags.h:142 [inline]
RIP: 0010:PageLocked include/linux/page-flags.h:272 [inline]
RIP: 0010:f2fs_put_page fs/f2fs/f2fs.h:2011 [inline]
RIP: 0010:validate_checkpoint+0x66d/0xec0 fs/f2fs/checkpoint.c:835
Code: e8 58 05 7f fe 4c 8d 6b 80 4d 8d 74 24 08 48 b8 00 00 00 00 00 fc ff df 4c 89 ea 48 c1 ea 03 c6 04 02 00 4c 89 f2 48 c1 ea 03 <80> 3c 02 00 0f 85 f4 06 00 00 4c 89 ea 4d 8b 7c 24 08 48 b8 00 00
RSP: 0018:ffff8801937cebe8 EFLAGS: 00010246
RAX: dffffc0000000000 RBX: ffff8801937cef30 RCX: ffffc90006035000
RDX: 0000000000000000 RSI: ffffffff82fd9658 RDI: 0000000000000005
RBP: ffff8801937cef58 R08: ffff8801ab254700 R09: fffff94000d9e026
R10: fffff94000d9e026 R11: ffffea0006cf0137 R12: fffffffffffffffb
R13: ffff8801937ceeb0 R14: 0000000000000003 R15: ffff880193419b40
FS:  00007f36a61d5700(0000) GS:ffff8801db100000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007fc04ff93000 CR3: 00000001d0562000 CR4: 00000000001426e0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
 f2fs_get_valid_checkpoint+0x436/0x1ec0 fs/f2fs/checkpoint.c:860
 f2fs_fill_super+0x2d42/0x8110 fs/f2fs/super.c:2883
 mount_bdev+0x314/0x3e0 fs/super.c:1344
 f2fs_mount+0x3c/0x50 fs/f2fs/super.c:3133
 legacy_get_tree+0x131/0x460 fs/fs_context.c:729
 vfs_get_tree+0x1cb/0x5c0 fs/super.c:1743
 do_new_mount fs/namespace.c:2603 [inline]
 do_mount+0x6f2/0x1e20 fs/namespace.c:2927
 ksys_mount+0x12d/0x140 fs/namespace.c:3143
 __do_sys_mount fs/namespace.c:3157 [inline]
 __se_sys_mount fs/namespace.c:3154 [inline]
 __x64_sys_mount+0xbe/0x150 fs/namespace.c:3154
 do_syscall_64+0x1b9/0x820 arch/x86/entry/common.c:290
 entry_SYSCALL_64_after_hwframe+0x49/0xbe
RIP: 0033:0x45943a
Code: b8 a6 00 00 00 0f 05 48 3d 01 f0 ff ff 0f 83 bd 8a fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 49 89 ca b8 a5 00 00 00 0f 05 <48> 3d 01 f0 ff ff 0f 83 9a 8a fb ff c3 66 0f 1f 84 00 00 00 00 00
RSP: 002b:00007f36a61d4a88 EFLAGS: 00000206 ORIG_RAX: 00000000000000a5
RAX: ffffffffffffffda RBX: 00007f36a61d4b30 RCX: 000000000045943a
RDX: 00007f36a61d4ad0 RSI: 0000000020000100 RDI: 00007f36a61d4af0
RBP: 0000000020000100 R08: 00007f36a61d4b30 R09: 00007f36a61d4ad0
R10: 0000000000000000 R11: 0000000000000206 R12: 0000000000000013
R13: 0000000000000000 R14: 00000000004c8ea0 R15: 0000000000000000
Modules linked in:
Dumping ftrace buffer:
   (ftrace buffer empty)
---[ end trace bd8550c129352286 ]---
RIP: 0010:__read_once_size include/linux/compiler.h:188 [inline]
RIP: 0010:compound_head include/linux/page-flags.h:142 [inline]
RIP: 0010:PageLocked include/linux/page-flags.h:272 [inline]
RIP: 0010:f2fs_put_page fs/f2fs/f2fs.h:2011 [inline]
RIP: 0010:validate_checkpoint+0x66d/0xec0 fs/f2fs/checkpoint.c:835
Code: e8 58 05 7f fe 4c 8d 6b 80 4d 8d 74 24 08 48 b8 00 00 00 00 00 fc ff df 4c 89 ea 48 c1 ea 03 c6 04 02 00 4c 89 f2 48 c1 ea 03 <80> 3c 02 00 0f 85 f4 06 00 00 4c 89 ea 4d 8b 7c 24 08 48 b8 00 00
RSP: 0018:ffff8801937cebe8 EFLAGS: 00010246
RAX: dffffc0000000000 RBX: ffff8801937cef30 RCX: ffffc90006035000
RDX: 0000000000000000 RSI: ffffffff82fd9658 RDI: 0000000000000005
netlink: 65342 bytes leftover after parsing attributes in process `syz-executor4'.
RBP: ffff8801937cef58 R08: ffff8801ab254700 R09: fffff94000d9e026
openvswitch: netlink: Message has 8 unknown bytes.
R10: fffff94000d9e026 R11: ffffea0006cf0137 R12: fffffffffffffffb
R13: ffff8801937ceeb0 R14: 0000000000000003 R15: ffff880193419b40
FS:  00007f36a61d5700(0000) GS:ffff8801db100000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007fc04ff93000 CR3: 00000001d0562000 CR4: 00000000001426e0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400

In validate_checkpoint(), if we failed to call get_checkpoint_version(), we will pass returned invalid page pointer into f2fs_put_page, cause accessing invalid memory, this patch tries to handle error path correctly to fix this issue.

---
 fs/f2fs/checkpoint.c |    9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

@@ -708,6 +708,7 @@ static int get_checkpoint_version(struct
 
 	crc_offset = le32_to_cpu((*cp_block)->checksum_offset);
 	if (crc_offset > (blk_size - sizeof(__le32))) {
+		f2fs_put_page(*cp_page, 1);
 		f2fs_msg(sbi->sb, KERN_WARNING,
 			"invalid crc_offset: %zu", crc_offset);
 		return -EINVAL;

@@ -715,6 +716,7 @@ static int get_checkpoint_version(struct
 
 	crc = cur_cp_crc(*cp_block);
 	if (!f2fs_crc_valid(sbi, crc, *cp_block, crc_offset)) {
+		f2fs_put_page(*cp_page, 1);
 		f2fs_msg(sbi->sb, KERN_WARNING, "invalid crc value");
 		return -EINVAL;
 	}

@@ -734,14 +736,14 @@ static struct page *validate_checkpoint(
 	err = get_checkpoint_version(sbi, cp_addr, &cp_block,
 					&cp_page_1, version);
 	if (err)
-		goto invalid_cp1;
+		return NULL;
 	pre_version = *version;
 
 	cp_addr += le32_to_cpu(cp_block->cp_pack_total_block_count) - 1;
 	err = get_checkpoint_version(sbi, cp_addr, &cp_block,
 					&cp_page_2, version);
 	if (err)
-		goto invalid_cp2;
+		goto invalid_cp;
 	cur_version = *version;
 
 	if (cur_version == pre_version) {

@@ -749,9 +751,8 @@ static struct page *validate_checkpoint(
 		f2fs_put_page(cp_page_2, 1);
 		return cp_page_1;
 	}
-invalid_cp2:
 	f2fs_put_page(cp_page_2, 1);
-invalid_cp1:
+invalid_cp:
 	f2fs_put_page(cp_page_1, 1);
 	return NULL;
 }

4.14-stable review patch. If anyone has any objections, please let me know.

------------------

From: Cong Wang <[email protected]>

commit 5fe23f262e0548ca7f19fb79f89059a60d087d22 upstream.

There is a race condition between ucma_close() and ucma_resolve_ip():

CPU0 CPU1
ucma_resolve_ip(): ucma_close():

ctx = ucma_get_ctx(file, cmd.id);

        list_for_each_entry_safe(ctx, tmp, &file->ctx_list, list) {
                mutex_lock(&mut);
                idr_remove(&ctx_idr, ctx->id);
                mutex_unlock(&mut);
		...
                mutex_lock(&mut);
                if (!ctx->closing) {
                        mutex_unlock(&mut);
                        rdma_destroy_id(ctx->cm_id);
		...
                ucma_free_ctx(ctx);

ret = rdma_resolve_addr();
ucma_put_ctx(ctx);

Before idr_remove(), ucma_get_ctx() could still find the ctx and after rdma_destroy_id(), rdma_resolve_addr() may still access id_priv pointer. Also, ucma_put_ctx() may use ctx after ucma_free_ctx() too.

ucma_close() should call ucma_put_ctx() too which tests the refcnt and waits for the last one releasing it. The similar pattern is already used by ucma_destroy_id().

---
 drivers/infiniband/core/ucma.c |    2 ++
 1 file changed, 2 insertions(+)

@@ -1742,6 +1742,8 @@ static int ucma_close(struct inode *inod
 		mutex_lock(&mut);
 		if (!ctx->closing) {
 			mutex_unlock(&mut);
+			ucma_put_ctx(ctx);
+			wait_for_completion(&ctx->comp);
 			/* rdma_destroy_id ensures that no event handlers are
 			 * inflight for that id before releasing it.
 			 */

4.14-stable review patch. If anyone has any objections, please let me know.

------------------

From: Richard Weinberger <[email protected]>

commit 37f31b6ca4311b94d985fb398a72e5399ad57925 upstream.

The requested device name can be NULL or an empty string. Check for that and refuse to continue. UBIFS has to do this manually since we cannot use mount_bdev(), which checks for this condition.

---
 fs/ubifs/super.c |    3 +++
 1 file changed, 3 insertions(+)

@@ -1930,6 +1930,9 @@ static struct ubi_volume_desc *open_ubi(
 	int dev, vol;
 	char *endptr;
 
+	if (!name || !*name)
+		return ERR_PTR(-EINVAL);
+
 	/* First, try to open using the device node path method */
 	ubi = ubi_open_volume_path(name, mode);
 	if (!IS_ERR(ubi))

4.14-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ka-Cheong Poon <[email protected]>

commit f394ad28feffbeebab77c8bf9a203bd49b957c9a upstream.

Currently, rds_ib_conn_alloc() calls rds_ib_recv_alloc_caches() without passing along the gfp_t flag. But rds_ib_recv_alloc_caches() and rds_ib_recv_alloc_cache() should take a gfp_t parameter so that rds_ib_recv_alloc_cache() can call alloc_percpu_gfp() using the correct flag instead of calling alloc_percpu().

---
 net/rds/ib.h      |    2 +-
 net/rds/ib_cm.c   |    2 +-
 net/rds/ib_recv.c |   10 +++++-----
 3 files changed, 7 insertions(+), 7 deletions(-)

@@ -373,7 +373,7 @@ void rds_ib_mr_cqe_handler(struct rds_ib
 int rds_ib_recv_init(void);
 void rds_ib_recv_exit(void);
 int rds_ib_recv_path(struct rds_conn_path *conn);
-int rds_ib_recv_alloc_caches(struct rds_ib_connection *ic);
+int rds_ib_recv_alloc_caches(struct rds_ib_connection *ic, gfp_t gfp);
 void rds_ib_recv_free_caches(struct rds_ib_connection *ic);
 void rds_ib_recv_refill(struct rds_connection *conn, int prefill, gfp_t gfp);
 void rds_ib_inc_free(struct rds_incoming *inc);

@@ -946,7 +946,7 @@ int rds_ib_conn_alloc(struct rds_connect
 	if (!ic)
 		return -ENOMEM;
 
-	ret = rds_ib_recv_alloc_caches(ic);
+	ret = rds_ib_recv_alloc_caches(ic, gfp);
 	if (ret) {
 		kfree(ic);
 		return ret;

@@ -98,12 +98,12 @@ static void rds_ib_cache_xfer_to_ready(s
 	}
 }
 
-static int rds_ib_recv_alloc_cache(struct rds_ib_refill_cache *cache)
+static int rds_ib_recv_alloc_cache(struct rds_ib_refill_cache *cache, gfp_t gfp)
 {
 	struct rds_ib_cache_head *head;
 	int cpu;
 
-	cache->percpu = alloc_percpu(struct rds_ib_cache_head);
+	cache->percpu = alloc_percpu_gfp(struct rds_ib_cache_head, gfp);
 	if (!cache->percpu)
 	       return -ENOMEM;
 

@@ -118,13 +118,13 @@ static int rds_ib_recv_alloc_cache(struc
 	return 0;
 }
 
-int rds_ib_recv_alloc_caches(struct rds_ib_connection *ic)
+int rds_ib_recv_alloc_caches(struct rds_ib_connection *ic, gfp_t gfp)
 {
 	int ret;
 
-	ret = rds_ib_recv_alloc_cache(&ic->i_cache_incs);
+	ret = rds_ib_recv_alloc_cache(&ic->i_cache_incs, gfp);
 	if (!ret) {
-		ret = rds_ib_recv_alloc_cache(&ic->i_cache_frags);
+		ret = rds_ib_recv_alloc_cache(&ic->i_cache_frags, gfp);
 		if (ret)
 			free_percpu(ic->i_cache_incs.percpu);
 	}

4.14-stable review patch. If anyone has any objections, please let me know.

------------------

From: Michael S. Tsirkin <[email protected]>

commit c7cdff0e864713a089d7cb3a2b1136ba9a54881a upstream.

fill_balloon doing memory allocations under balloon_lock can cause a deadlock when leak_balloon is called from virtballoon_oom_notify and tries to take same lock.

To fix, split page allocation and enqueue and do allocations outside the lock.

Here's a detailed analysis of the deadlock by Tetsuo Handa:

In leak_balloon(), mutex_lock(&vb->balloon_lock) is called in order to serialize against fill_balloon(). But in fill_balloon(), alloc_page(GFP_HIGHUSER[_MOVABLE] | __GFP_NOMEMALLOC | __GFP_NORETRY) is called with vb->balloon_lock mutex held. Since GFP_HIGHUSER[_MOVABLE] implies __GFP_DIRECT_RECLAIM | __GFP_IO | __GFP_FS, despite __GFP_NORETRY is specified, this allocation attempt might indirectly depend on somebody else's __GFP_DIRECT_RECLAIM memory allocation. And such indirect __GFP_DIRECT_RECLAIM memory allocation might call leak_balloon() via virtballoon_oom_notify() via blocking_notifier_call_chain() callback via out_of_memory() when it reached __alloc_pages_may_oom() and held oom_lock mutex. Since vb->balloon_lock mutex is already held by fill_balloon(), it will cause OOM lockup.

Thread1 Thread2
fill_balloon()
takes a balloon_lock
balloon_page_enqueue()
alloc_page(GFP_HIGHUSER_MOVABLE)
direct reclaim (__GFP_FS context) takes a fs lock
waits for that fs lock alloc_page(GFP_NOFS)
__alloc_pages_may_oom()
takes the oom_lock
out_of_memory()
blocking_notifier_call_chain()
leak_balloon()
tries to take that balloon_lock and deadlocks

---
 drivers/virtio/virtio_balloon.c    |   24 +++++++++++++++++++-----
 include/linux/balloon_compaction.h |   35 ++++++++++++++++++++++++++++++++++-
 mm/balloon_compaction.c            |   28 +++++++++++++++++++++-------
 3 files changed, 74 insertions(+), 13 deletions(-)

@@ -143,16 +143,17 @@ static void set_page_pfns(struct virtio_
 
 static unsigned fill_balloon(struct virtio_balloon *vb, size_t num)
 {
-	struct balloon_dev_info *vb_dev_info = &vb->vb_dev_info;
 	unsigned num_allocated_pages;
+	unsigned num_pfns;
+	struct page *page;
+	LIST_HEAD(pages);
 
 	/* We can only do one array worth at a time. */
 	num = min(num, ARRAY_SIZE(vb->pfns));
 
-	mutex_lock(&vb->balloon_lock);
-	for (vb->num_pfns = 0; vb->num_pfns < num;
-	     vb->num_pfns += VIRTIO_BALLOON_PAGES_PER_PAGE) {
-		struct page *page = balloon_page_enqueue(vb_dev_info);
+	for (num_pfns = 0; num_pfns < num;
+	     num_pfns += VIRTIO_BALLOON_PAGES_PER_PAGE) {
+		struct page *page = balloon_page_alloc();
 
 		if (!page) {
 			dev_info_ratelimited(&vb->vdev->dev,

@@ -162,6 +163,19 @@ static unsigned fill_balloon(struct virt
 			msleep(200);
 			break;
 		}
+
+		balloon_page_push(&pages, page);
+	}
+
+	mutex_lock(&vb->balloon_lock);
+
+	vb->num_pfns = 0;
+
+	while ((page = balloon_page_pop(&pages))) {
+		balloon_page_enqueue(&vb->vb_dev_info, page);
+
+		vb->num_pfns += VIRTIO_BALLOON_PAGES_PER_PAGE;
+
 		set_page_pfns(vb, vb->pfns + vb->num_pfns, page);
 		vb->num_pages += VIRTIO_BALLOON_PAGES_PER_PAGE;
 		if (!virtio_has_feature(vb->vdev,

@@ -50,6 +50,7 @@
 #include <linux/gfp.h>
 #include <linux/err.h>
 #include <linux/fs.h>
+#include <linux/list.h>
 
 /*
  * Balloon device information descriptor.

@@ -67,7 +68,9 @@ struct balloon_dev_info {
 	struct inode *inode;
 };
 
-extern struct page *balloon_page_enqueue(struct balloon_dev_info *b_dev_info);
+extern struct page *balloon_page_alloc(void);
+extern void balloon_page_enqueue(struct balloon_dev_info *b_dev_info,
+				 struct page *page);
 extern struct page *balloon_page_dequeue(struct balloon_dev_info *b_dev_info);
 
 static inline void balloon_devinfo_init(struct balloon_dev_info *balloon)

@@ -193,4 +196,34 @@ static inline gfp_t balloon_mapping_gfp_
 }
 
 #endif /* CONFIG_BALLOON_COMPACTION */
+
+/*
+ * balloon_page_push - insert a page into a page list.
+ * @head : pointer to list
+ * @page : page to be added
+ *
+ * Caller must ensure the page is private and protect the list.
+ */
+static inline void balloon_page_push(struct list_head *pages, struct page *page)
+{
+	list_add(&page->lru, pages);
+}
+
+/*
+ * balloon_page_pop - remove a page from a page list.
+ * @head : pointer to list
+ * @page : page to be added
+ *
+ * Caller must ensure the page is private and protect the list.
+ */
+static inline struct page *balloon_page_pop(struct list_head *pages)
+{
+	struct page *page = list_first_entry_or_null(pages, struct page, lru);
+
+	if (!page)
+		return NULL;
+
+	list_del(&page->lru);
+	return page;
+}
 #endif /* _LINUX_BALLOON_COMPACTION_H */

@@ -11,22 +11,37 @@
 #include <linux/balloon_compaction.h>
 
 /*
+ * balloon_page_alloc - allocates a new page for insertion into the balloon
+ *			  page list.
+ *
+ * Driver must call it to properly allocate a new enlisted balloon page.
+ * Driver must call balloon_page_enqueue before definitively removing it from
+ * the guest system.  This function returns the page address for the recently
+ * allocated page or NULL in the case we fail to allocate a new page this turn.
+ */
+struct page *balloon_page_alloc(void)
+{
+	struct page *page = alloc_page(balloon_mapping_gfp_mask() |
+				       __GFP_NOMEMALLOC | __GFP_NORETRY);
+	return page;
+}
+EXPORT_SYMBOL_GPL(balloon_page_alloc);
+
+/*
  * balloon_page_enqueue - allocates a new page and inserts it into the balloon
  *			  page list.
  * @b_dev_info: balloon device descriptor where we will insert a new page to
+ * @page: new page to enqueue - allocated using balloon_page_alloc.
  *
- * Driver must call it to properly allocate a new enlisted balloon page
+ * Driver must call it to properly enqueue a new allocated balloon page
  * before definitively removing it from the guest system.
  * This function returns the page address for the recently enqueued page or
  * NULL in the case we fail to allocate a new page this turn.
  */
-struct page *balloon_page_enqueue(struct balloon_dev_info *b_dev_info)
+void balloon_page_enqueue(struct balloon_dev_info *b_dev_info,
+			  struct page *page)
 {
 	unsigned long flags;
-	struct page *page = alloc_page(balloon_mapping_gfp_mask() |
-				       __GFP_NOMEMALLOC | __GFP_NORETRY);
-	if (!page)
-		return NULL;
 
 	/*
 	 * Block others from accessing the 'page' when we get around to

@@ -39,7 +54,6 @@ struct page *balloon_page_enqueue(struct
 	__count_vm_event(BALLOON_INFLATE);
 	spin_unlock_irqrestore(&b_dev_info->pages_lock, flags);
 	unlock_page(page);
-	return page;
 }
 EXPORT_SYMBOL_GPL(balloon_page_enqueue);
 

4.14-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jan Stancek <[email protected]>

commit d9e427f6ab8142d6868eb719e6a7851aafea56b6 upstream.

commit c7cdff0e8647 ("virtio_balloon: fix deadlock on OOM") changed code to increment vb->num_pfns before call to set_page_pfns(), which used to happen only after.

This patch fixes boot hang for me on ppc64le KVM guests.

---
 drivers/virtio/virtio_balloon.c |    3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

@@ -174,13 +174,12 @@ static unsigned fill_balloon(struct virt
 	while ((page = balloon_page_pop(&pages))) {
 		balloon_page_enqueue(&vb->vb_dev_info, page);
 
-		vb->num_pfns += VIRTIO_BALLOON_PAGES_PER_PAGE;
-
 		set_page_pfns(vb, vb->pfns + vb->num_pfns, page);
 		vb->num_pages += VIRTIO_BALLOON_PAGES_PER_PAGE;
 		if (!virtio_has_feature(vb->vdev,
 					VIRTIO_BALLOON_F_DEFLATE_ON_OOM))
 			adjust_managed_page_count(page, -1);
+		vb->num_pfns += VIRTIO_BALLOON_PAGES_PER_PAGE;
 	}
 
 	num_allocated_pages = vb->num_pfns;

4.14-stable review patch. If anyone has any objections, please let me know.

------------------

From: Zhi Chen <[email protected]>

commit c8291988806407e02a01b4b15b4504eafbcc04e0 upstream.

Length of WMI scan message was not calculated correctly. The allocated buffer was smaller than what we expected. So WMI message corrupted skb_info, which is at the end of skb->data. This fix takes TLV header into account even if the element is zero-length.

Crash log:

  [49.629986] Unhandled kernel unaligned access[#1]:
  [49.634932] CPU: 0 PID: 1176 Comm: logd Not tainted 4.4.60 #180
  [49.641040] task: 83051460 ti: 8329c000 task.ti: 8329c000
  [49.646608] $ 0   : 00000000 00000001 80984a80 00000000
  [49.652038] $ 4   : 45259e89 8046d484 8046df30 8024ba70
  [49.657468] $ 8   : 00000000 804cc4c0 00000001 20306320
  [49.662898] $12   : 33322037 000110f2 00000000 31203930
  [49.668327] $16   : 82792b40 80984a80 00000001 804207fc
  [49.673757] $20   : 00000000 0000012c 00000040 80470000
  [49.679186] $24   : 00000000 8024af7c
  [49.684617] $28   : 8329c000 8329db88 00000001 802c58d0
  [49.690046] Hi    : 00000000
  [49.693022] Lo    : 453c0000
  [49.696013] epc   : 800efae4 put_page+0x0/0x58
  [49.700615] ra    : 802c58d0 skb_release_data+0x148/0x1d4
  [49.706184] Status: 1000fc03 KERNEL EXL IE
  [49.710531] Cause : 00800010 (ExcCode 04)
  [49.714669] BadVA : 45259e89
  [49.717644] PrId  : 00019374 (MIPS 24Kc)

---
 drivers/net/wireless/ath/ath10k/wmi-tlv.c |    8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

@@ -1486,10 +1486,10 @@ ath10k_wmi_tlv_op_gen_start_scan(struct
 	bssid_len = arg->n_bssids * sizeof(struct wmi_mac_addr);
 	ie_len = roundup(arg->ie_len, 4);
 	len = (sizeof(*tlv) + sizeof(*cmd)) +
-	      (arg->n_channels ? sizeof(*tlv) + chan_len : 0) +
-	      (arg->n_ssids ? sizeof(*tlv) + ssid_len : 0) +
-	      (arg->n_bssids ? sizeof(*tlv) + bssid_len : 0) +
-	      (arg->ie_len ? sizeof(*tlv) + ie_len : 0);
+	      sizeof(*tlv) + chan_len +
+	      sizeof(*tlv) + ssid_len +
+	      sizeof(*tlv) + bssid_len +
+	      sizeof(*tlv) + ie_len;
 
 	skb = ath10k_wmi_alloc_skb(ar, len);
 	if (!skb)

4.14-stable review patch. If anyone has any objections, please let me know.

------------------

From: Vineet Gupta <[email protected]>

commit c58a584f05e35d1d4342923cd7aac07d9c3d3d16 upstream.

Per ARC TLS ABI, r25 is designated TP (thread pointer register). However so far kernel didn't do any special treatment, like setting up usermode r25, even for CLONE_SETTLS. We instead relied on libc runtime to do this, in say clone libc wrapper [1]. This was deliberate to keep kernel ABI agnostic (userspace could potentially change TP, specially for different ARC ISA say ARCompact vs. ARCv2 with different spare registers etc)

However userspace setting up r25, after clone syscall opens a race, if child is not scheduled and gets a signal instead. It starts off in userspace not in clone but in a signal handler and anything TP sepcific there such as pthread_self() fails which showed up with uClibc testsuite nptl/tst-kill6 [2]

Fix this by having kernel populate r25 to TP value. So this locks in ABI, but it was not going to change anyways, and fwiw is same for both ARCompact (arc700 core) and ARCvs (HS3x cores)

[1] https://cgit.uclibc-ng.org/cgi/cgit/uclibc-ng.git/tree/libc/sysdeps/linux/arc/clone.S
[2] https://github.com/wbx-github/uclibc-ng-test/blob/master/test/nptl/tst-kill6.c

---
 arch/arc/kernel/process.c |   20 ++++++++++++++++++++
 1 file changed, 20 insertions(+)

@@ -241,6 +241,26 @@ int copy_thread(unsigned long clone_flag
 		task_thread_info(current)->thr_ptr;
 	}
 
+
+	/*
+	 * setup usermode thread pointer #1:
+	 * when child is picked by scheduler, __switch_to() uses @c_callee to
+	 * populate usermode callee regs: this works (despite being in a kernel
+	 * function) since special return path for child @ret_from_fork()
+	 * ensures those regs are not clobbered all the way to RTIE to usermode
+	 */
+	c_callee->r25 = task_thread_info(p)->thr_ptr;
+
+#ifdef CONFIG_ARC_CURR_IN_REG
+	/*
+	 * setup usermode thread pointer #2:
+	 * however for this special use of r25 in kernel, __switch_to() sets
+	 * r25 for kernel needs and only in the final return path is usermode
+	 * r25 setup, from pt_regs->user_r25. So set that up as well
+	 */
+	c_regs->user_r25 = c_callee->r25;
+#endif
+
 	return 0;
 }
 

Hi Greg,

This has been already reverted in upstream.
bdfbbda90aeb ("Revert "cgroup/cpuset: remove circular dependency deadlock"")

Might be better to add e8b3f8db7aad ("workqueue/hotplug: simplify workqueue_offline_cpu()") instead which is mentioned in the revert commit.

Regards
Sudip

Compiled and booted on my test system. No dmesg regressions.

thanks,
-- Shuah

Results from Linaro’s test farm.
No regressions on arm64, arm, x86_64, and i386.

Summary
------------------------------------------------------------------------

kernel: 4.14.76-rc1
git repo: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git
git branch: linux-4.14.y
git commit: c0c2a4359275ed099acb465f0c929abd22647d64
git describe: v4.14.75-46-gc0c2a4359275
Test details: https://qa-reports.linaro.org/lkft/linux-stable-rc-4.14-oe/build/v4.14.75-46-gc0c2a4359275

No regressions (compared to build v4.14.75)

No fixes (compared to build v4.14.75)

Ran 18438 total tests in the following environments and test suites.

Environments
--------------
- dragonboard-410c - arm64
- hi6220-hikey - arm64
- i386
- juno-r2 - arm64
- qemu_arm
- qemu_arm64
- qemu_i386
- qemu_x86_64
- x15 - arm
- x86_64

Test Suites
-----------
* boot
* kselftest
* libhugetlbfs
* ltp-cap_bounds-tests
* ltp-containers-tests
* ltp-cve-tests
* ltp-fcntl-locktests-tests
* ltp-filecaps-tests
* ltp-fs-tests
* ltp-fs_bind-tests
* ltp-fs_perms_simple-tests
* ltp-fsx-tests
* ltp-hugetlb-tests
* ltp-io-tests
* ltp-ipc-tests
* ltp-math-tests
* ltp-nptl-tests
* ltp-pty-tests
* ltp-sched-tests
* ltp-securebits-tests
* ltp-syscalls-tests
* ltp-timers-tests
* ltp-open-posix-tests
* kselftest-vsyscall-mode-native
* kselftest-vsyscall-mode-none

Linaro LKFT
https://lkft.linaro.org

All tests are passing for Tegra ...

Test results for stable-v4.14:

    8 builds:	8 pass, 0 fail
    16 boots:	16 pass, 0 fail
    14 tests:	14 pass, 0 fail

Linux version: 4.14.76-rc1-gc0c2a43
Boards tested: tegra124-jetson-tk1, tegra20-ventana,

                tegra210-p2371-2180, tegra30-cardhu-a04

Cheers
Jon

nvpublic