Merge android-4.4.129 (b1c4836) into msm-4.4

* refs/heads/tmp-b1c4836
  Linux 4.4.129
  writeback: safer lock nesting
  fanotify: fix logic of events on child
  ext4: bugfix for mmaped pages in mpage_release_unused_pages()
  mm/filemap.c: fix NULL pointer in page_cache_tree_insert()
  mm: allow GFP_{FS,IO} for page_cache_read page cache allocation
  autofs: mount point create should honour passed in mode
  Don't leak MNT_INTERNAL away from internal mounts
  rpc_pipefs: fix double-dput()
  hypfs_kill_super(): deal with failed allocations
  jffs2_kill_sb(): deal with failed allocations
  powerpc/lib: Fix off-by-one in alternate feature patching
  powerpc/eeh: Fix enabling bridge MMIO windows
  MIPS: memset.S: Fix clobber of v1 in last_fixup
  MIPS: memset.S: Fix return of __clear_user from Lpartial_fixup
  MIPS: memset.S: EVA & fault support for small_memset
  MIPS: uaccess: Add micromips clobbers to bzero invocation
  HID: hidraw: Fix crash on HIDIOCGFEATURE with a destroyed device
  ALSA: hda - New VIA controller suppor no-snoop path
  ALSA: rawmidi: Fix missing input substream checks in compat ioctls
  ALSA: line6: Use correct endpoint type for midi output
  ext4: fix deadlock between inline_data and ext4_expand_extra_isize_ea()
  ext4: fix crashes in dioread_nolock mode
  drm/radeon: Fix PCIe lane width calculation
  ext4: don't allow r/w mounts if metadata blocks overlap the superblock
  vfio/pci: Virtualize Maximum Read Request Size
  vfio/pci: Virtualize Maximum Payload Size
  vfio-pci: Virtualize PCIe & AF FLR
  ALSA: pcm: Fix endless loop for XRUN recovery in OSS emulation
  ALSA: pcm: Fix mutex unbalance in OSS emulation ioctls
  ALSA: pcm: Return -EBUSY for OSS ioctls changing busy streams
  ALSA: pcm: Avoid potential races between OSS ioctls and read/write
  ALSA: pcm: Use ERESTARTSYS instead of EINTR in OSS emulation
  ALSA: oss: consolidate kmalloc/memset 0 call to kzalloc
  watchdog: f71808e_wdt: Fix WD_EN register read
  thermal: imx: Fix race condition in imx_thermal_probe()
  clk: bcm2835: De-assert/assert PLL reset signal when appropriate
  clk: mvebu: armada-38x: add support for missing clocks
  clk: mvebu: armada-38x: add support for 1866MHz variants
  mmc: jz4740: Fix race condition in IRQ mask update
  iommu/vt-d: Fix a potential memory leak
  um: Use POSIX ucontext_t instead of struct ucontext
  dmaengine: at_xdmac: fix rare residue corruption
  IB/srp: Fix completion vector assignment algorithm
  IB/srp: Fix srp_abort()
  ALSA: pcm: Fix UAF at PCM release via PCM timer access
  RDMA/ucma: Don't allow setting RDMA_OPTION_IB_PATH without an RDMA device
  ext4: fail ext4_iget for root directory if unallocated
  ext4: don't update checksum of new initialized bitmaps
  jbd2: if the journal is aborted then don't allow update of the log tail
  random: use a tighter cap in credit_entropy_bits_safe()
  thunderbolt: Resume control channel after hibernation image is created
  ASoC: ssm2602: Replace reg_default_raw with reg_default
  HID: core: Fix size as type u32
  HID: Fix hid_report_len usage
  powerpc/powernv: Fix OPAL NVRAM driver OPAL_BUSY loops
  powerpc/powernv: define a standard delay for OPAL_BUSY type retry loops
  powerpc/64: Fix smp_wmb barrier definition use use lwsync consistently
  powerpc/powernv: Handle unknown OPAL errors in opal_nvram_write()
  HID: i2c-hid: fix size check and type usage
  usb: dwc3: pci: Properly cleanup resource
  USB:fix USB3 devices behind USB3 hubs not resuming at hibernate thaw
  ACPI / hotplug / PCI: Check presence of slot itself in get_slot_status()
  ACPI / video: Add quirk to force acpi-video backlight on Samsung 670Z5E
  regmap: Fix reversed bounds check in regmap_raw_write()
  xen-netfront: Fix hang on device removal
  ARM: dts: at91: sama5d4: fix pinctrl compatible string
  ARM: dts: at91: at91sam9g25: fix mux-mask pinctrl property
  usb: musb: gadget: misplaced out of bounds check
  mm, slab: reschedule cache_reap() on the same CPU
  ipc/shm: fix use-after-free of shm file via remap_file_pages()
  resource: fix integer overflow at reallocation
  fs/reiserfs/journal.c: add missing resierfs_warning() arg
  ubi: Reject MLC NAND
  ubi: Fix error for write access
  ubi: fastmap: Don't flush fastmap work on detach
  ubifs: Check ubifs_wbuf_sync() return code
  tty: make n_tty_read() always abort if hangup is in progress
  x86/hweight: Don't clobber %rdi
  x86/hweight: Get rid of the special calling convention
  lan78xx: Correctly indicate invalid OTP
  slip: Check if rstate is initialized before uncompressing
  cdc_ether: flag the Cinterion AHS8 modem by gemalto as WWAN
  hwmon: (ina2xx) Fix access to uninitialized mutex
  rtl8187: Fix NULL pointer dereference in priv->conf_mutex
  getname_kernel() needs to make sure that ->name != ->iname in long case
  s390/ipl: ensure loadparm valid flag is set
  s390/qdio: don't merge ERROR output buffers
  s390/qdio: don't retry EQBS after CCQ 96
  block/loop: fix deadlock after loop_set_status
  Revert "perf tests: Decompress kernel module before objdump"
  radeon: hide pointless #warning when compile testing
  perf intel-pt: Fix timestamp following overflow
  perf intel-pt: Fix error recovery from missing TIP packet
  perf intel-pt: Fix sync_switch
  perf intel-pt: Fix overlap detection to identify consecutive buffers correctly
  parisc: Fix out of array access in match_pci_device()
  media: v4l2-compat-ioctl32: don't oops on overlay
  f2fs: check cap_resource only for data blocks
  Revert "f2fs: introduce f2fs_set_page_dirty_nobuffer"
  f2fs: clear PageError on writepage
  UPSTREAM: timer: Export destroy_hrtimer_on_stack()
  BACKPORT: dm verity: add 'check_at_most_once' option to only validate hashes once
  f2fs: call unlock_new_inode() before d_instantiate()
  f2fs: refactor read path to allow multiple postprocessing steps
  fscrypt: allow synchronous bio decryption

Change-Id: I45f4ac10734d92023b53118d83dcd6c83974a283
Signed-off-by: Srinivasarao P <spathi@codeaurora.org>

4 files changed, 62 insertions, 61 deletions

diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c
index 6ea4fcfaab36..a767a6400c5c 100644
--- a/tools/perf/tests/code-reading.c
+++ b/tools/perf/tests/code-reading.c
@@ -182,8 +182,6 @@ static int read_object_code(u64 addr, size_t len, u8 cpumode,
 	unsigned char buf2[BUFSZ];
 	size_t ret_len;
 	u64 objdump_addr;
-	const char *objdump_name;
-	char decomp_name[KMOD_DECOMP_LEN];
 	int ret;
 
 	pr_debug("Reading object code for memory address: %#"PRIx64"\n", addr);
@@ -244,25 +242,9 @@ static int read_object_code(u64 addr, size_t len, u8 cpumode,
 		state->done[state->done_cnt++] = al.map->start;
 	}
 
-	objdump_name = al.map->dso->long_name;
-	if (dso__needs_decompress(al.map->dso)) {
-		if (dso__decompress_kmodule_path(al.map->dso, objdump_name,
-						 decomp_name,
-						 sizeof(decomp_name)) < 0) {
-			pr_debug("decompression failed\n");
-			return -1;
-		}
-
-		objdump_name = decomp_name;
-	}
-
 	/* Read the object code using objdump */
 	objdump_addr = map__rip_2objdump(al.map, al.addr);
-	ret = read_via_objdump(objdump_name, objdump_addr, buf2, len);
-
-	if (dso__needs_decompress(al.map->dso))
-		unlink(objdump_name);
-
+	ret = read_via_objdump(al.map->dso->long_name, objdump_addr, buf2, len);
 	if (ret > 0) {
 		/*
 		 * The kernel maps are inaccurate - assume objdump is right in
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
index eeeae0629ad3..0b540b84f8b7 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
@@ -1270,6 +1270,7 @@ static int intel_pt_overflow(struct intel_pt_decoder *decoder)
 	intel_pt_clear_tx_flags(decoder);
 	decoder->have_tma = false;
 	decoder->cbr = 0;
+	decoder->timestamp_insn_cnt = 0;
 	decoder->pkt_state = INTEL_PT_STATE_ERR_RESYNC;
 	decoder->overflow = true;
 	return -EOVERFLOW;
@@ -1492,6 +1493,7 @@ static int intel_pt_walk_fup_tip(struct intel_pt_decoder *decoder)
 		case INTEL_PT_PSBEND:
 			intel_pt_log("ERROR: Missing TIP after FUP\n");
 			decoder->pkt_state = INTEL_PT_STATE_ERR3;
+			decoder->pkt_step = 0;
 			return -ENOENT;
 
 		case INTEL_PT_OVF:
@@ -2152,14 +2154,6 @@ const struct intel_pt_state *intel_pt_decode(struct intel_pt_decoder *decoder)
 	return &decoder->state;
 }
 
-static bool intel_pt_at_psb(unsigned char *buf, size_t len)
-{
-	if (len < INTEL_PT_PSB_LEN)
-		return false;
-	return memmem(buf, INTEL_PT_PSB_LEN, INTEL_PT_PSB_STR,
-		      INTEL_PT_PSB_LEN);
-}
-
 /**
  * intel_pt_next_psb - move buffer pointer to the start of the next PSB packet.
  * @buf: pointer to buffer pointer
@@ -2248,6 +2242,7 @@ static unsigned char *intel_pt_last_psb(unsigned char *buf, size_t len)
  * @buf: buffer
  * @len: size of buffer
  * @tsc: TSC value returned
+ * @rem: returns remaining size when TSC is found
  *
  * Find a TSC packet in @buf and return the TSC value.  This function assumes
  * that @buf starts at a PSB and that PSB+ will contain TSC and so stops if a
@@ -2255,7 +2250,8 @@ static unsigned char *intel_pt_last_psb(unsigned char *buf, size_t len)
  *
  * Return: %true if TSC is found, false otherwise.
  */
-static bool intel_pt_next_tsc(unsigned char *buf, size_t len, uint64_t *tsc)
+static bool intel_pt_next_tsc(unsigned char *buf, size_t len, uint64_t *tsc,
+			      size_t *rem)
 {
 	struct intel_pt_pkt packet;
 	int ret;
@@ -2266,6 +2262,7 @@ static bool intel_pt_next_tsc(unsigned char *buf, size_t len, uint64_t *tsc)
 			return false;
 		if (packet.type == INTEL_PT_TSC) {
 			*tsc = packet.payload;
+			*rem = len;
 			return true;
 		}
 		if (packet.type == INTEL_PT_PSBEND)
@@ -2316,6 +2313,8 @@ static int intel_pt_tsc_cmp(uint64_t tsc1, uint64_t tsc2)
  * @len_a: size of first buffer
  * @buf_b: second buffer
  * @len_b: size of second buffer
+ * @consecutive: returns true if there is data in buf_b that is consecutive
+ *               to buf_a
  *
  * If the trace contains TSC we can look at the last TSC of @buf_a and the
  * first TSC of @buf_b in order to determine if the buffers overlap, and then
@@ -2328,33 +2327,41 @@ static int intel_pt_tsc_cmp(uint64_t tsc1, uint64_t tsc2)
 static unsigned char *intel_pt_find_overlap_tsc(unsigned char *buf_a,
 						size_t len_a,
 						unsigned char *buf_b,
-						size_t len_b)
+						size_t len_b, bool *consecutive)
 {
 	uint64_t tsc_a, tsc_b;
 	unsigned char *p;
-	size_t len;
+	size_t len, rem_a, rem_b;
 
 	p = intel_pt_last_psb(buf_a, len_a);
 	if (!p)
 		return buf_b; /* No PSB in buf_a => no overlap */
 
 	len = len_a - (p - buf_a);
-	if (!intel_pt_next_tsc(p, len, &tsc_a)) {
+	if (!intel_pt_next_tsc(p, len, &tsc_a, &rem_a)) {
 		/* The last PSB+ in buf_a is incomplete, so go back one more */
 		len_a -= len;
 		p = intel_pt_last_psb(buf_a, len_a);
 		if (!p)
 			return buf_b; /* No full PSB+ => assume no overlap */
 		len = len_a - (p - buf_a);
-		if (!intel_pt_next_tsc(p, len, &tsc_a))
+		if (!intel_pt_next_tsc(p, len, &tsc_a, &rem_a))
 			return buf_b; /* No TSC in buf_a => assume no overlap */
 	}
 
 	while (1) {
 		/* Ignore PSB+ with no TSC */
-		if (intel_pt_next_tsc(buf_b, len_b, &tsc_b) &&
-		    intel_pt_tsc_cmp(tsc_a, tsc_b) < 0)
-			return buf_b; /* tsc_a < tsc_b => no overlap */
+		if (intel_pt_next_tsc(buf_b, len_b, &tsc_b, &rem_b)) {
+			int cmp = intel_pt_tsc_cmp(tsc_a, tsc_b);
+
+			/* Same TSC, so buffers are consecutive */
+			if (!cmp && rem_b >= rem_a) {
+				*consecutive = true;
+				return buf_b + len_b - (rem_b - rem_a);
+			}
+			if (cmp < 0)
+				return buf_b; /* tsc_a < tsc_b => no overlap */
+		}
 
 		if (!intel_pt_step_psb(&buf_b, &len_b))
 			return buf_b + len_b; /* No PSB in buf_b => no data */
@@ -2368,6 +2375,8 @@ static unsigned char *intel_pt_find_overlap_tsc(unsigned char *buf_a,
  * @buf_b: second buffer
  * @len_b: size of second buffer
  * @have_tsc: can use TSC packets to detect overlap
+ * @consecutive: returns true if there is data in buf_b that is consecutive
+ *               to buf_a
  *
  * When trace samples or snapshots are recorded there is the possibility that
  * the data overlaps.  Note that, for the purposes of decoding, data is only
@@ -2378,7 +2387,7 @@ static unsigned char *intel_pt_find_overlap_tsc(unsigned char *buf_a,
  */
 unsigned char *intel_pt_find_overlap(unsigned char *buf_a, size_t len_a,
 				     unsigned char *buf_b, size_t len_b,
-				     bool have_tsc)
+				     bool have_tsc, bool *consecutive)
 {
 	unsigned char *found;
 
@@ -2390,7 +2399,8 @@ unsigned char *intel_pt_find_overlap(unsigned char *buf_a, size_t len_a,
 		return buf_b; /* No overlap */
 
 	if (have_tsc) {
-		found = intel_pt_find_overlap_tsc(buf_a, len_a, buf_b, len_b);
+		found = intel_pt_find_overlap_tsc(buf_a, len_a, buf_b, len_b,
+						  consecutive);
 		if (found)
 			return found;
 	}
@@ -2405,28 +2415,16 @@ unsigned char *intel_pt_find_overlap(unsigned char *buf_a, size_t len_a,
 	}
 
 	/* Now len_b >= len_a */
-	if (len_b > len_a) {
-		/* The leftover buffer 'b' must start at a PSB */
-		while (!intel_pt_at_psb(buf_b + len_a, len_b - len_a)) {
-			if (!intel_pt_step_psb(&buf_a, &len_a))
-				return buf_b; /* No overlap */
-		}
-	}
-
 	while (1) {
 		/* Potential overlap so check the bytes */
 		found = memmem(buf_a, len_a, buf_b, len_a);
-		if (found)
+		if (found) {
+			*consecutive = true;
 			return buf_b + len_a;
+		}
 
 		/* Try again at next PSB in buffer 'a' */
 		if (!intel_pt_step_psb(&buf_a, &len_a))
 			return buf_b; /* No overlap */
-
-		/* The leftover buffer 'b' must start at a PSB */
-		while (!intel_pt_at_psb(buf_b + len_a, len_b - len_a)) {
-			if (!intel_pt_step_psb(&buf_a, &len_a))
-				return buf_b; /* No overlap */
-		}
 	}
 }
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h
index 02c38fec1c37..89a3eda6a318 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h
@@ -102,7 +102,7 @@ const struct intel_pt_state *intel_pt_decode(struct intel_pt_decoder *decoder);
 
 unsigned char *intel_pt_find_overlap(unsigned char *buf_a, size_t len_a,
 				     unsigned char *buf_b, size_t len_b,
-				     bool have_tsc);
+				     bool have_tsc, bool *consecutive);
 
 int intel_pt__strerror(int code, char *buf, size_t buflen);
 
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index 89927b5beebf..3693cb26ec66 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -125,6 +125,7 @@ struct intel_pt_queue {
 	bool stop;
 	bool step_through_buffers;
 	bool use_buffer_pid_tid;
+	bool sync_switch;
 	pid_t pid, tid;
 	int cpu;
 	int switch_state;
@@ -188,14 +189,17 @@ static void intel_pt_dump_event(struct intel_pt *pt, unsigned char *buf,
 static int intel_pt_do_fix_overlap(struct intel_pt *pt, struct auxtrace_buffer *a,
 				   struct auxtrace_buffer *b)
 {
+	bool consecutive = false;
 	void *start;
 
 	start = intel_pt_find_overlap(a->data, a->size, b->data, b->size,
-				      pt->have_tsc);
+				      pt->have_tsc, &consecutive);
 	if (!start)
 		return -EINVAL;
 	b->use_size = b->data + b->size - start;
 	b->use_data = start;
+	if (b->use_size && consecutive)
+		b->consecutive = true;
 	return 0;
 }
 
@@ -849,10 +853,12 @@ static int intel_pt_setup_queue(struct intel_pt *pt,
 			if (pt->timeless_decoding || !pt->have_sched_switch)
 				ptq->use_buffer_pid_tid = true;
 		}
+
+		ptq->sync_switch = pt->sync_switch;
 	}
 
 	if (!ptq->on_heap &&
-	    (!pt->sync_switch ||
+	    (!ptq->sync_switch ||
 	     ptq->switch_state != INTEL_PT_SS_EXPECTING_SWITCH_EVENT)) {
 		const struct intel_pt_state *state;
 		int ret;
@@ -1235,7 +1241,7 @@ static int intel_pt_sample(struct intel_pt_queue *ptq)
 	if (pt->synth_opts.last_branch)
 		intel_pt_update_last_branch_rb(ptq);
 
-	if (!pt->sync_switch)
+	if (!ptq->sync_switch)
 		return 0;
 
 	if (intel_pt_is_switch_ip(ptq, state->to_ip)) {
@@ -1316,6 +1322,21 @@ static u64 intel_pt_switch_ip(struct intel_pt *pt, u64 *ptss_ip)
 	return switch_ip;
 }
 
+static void intel_pt_enable_sync_switch(struct intel_pt *pt)
+{
+	unsigned int i;
+
+	pt->sync_switch = true;
+
+	for (i = 0; i < pt->queues.nr_queues; i++) {
+		struct auxtrace_queue *queue = &pt->queues.queue_array[i];
+		struct intel_pt_queue *ptq = queue->priv;
+
+		if (ptq)
+			ptq->sync_switch = true;
+	}
+}
+
 static int intel_pt_run_decoder(struct intel_pt_queue *ptq, u64 *timestamp)
 {
 	const struct intel_pt_state *state = ptq->state;
@@ -1332,7 +1353,7 @@ static int intel_pt_run_decoder(struct intel_pt_queue *ptq, u64 *timestamp)
 			if (pt->switch_ip) {
 				intel_pt_log("switch_ip: %"PRIx64" ptss_ip: %"PRIx64"\n",
 					     pt->switch_ip, pt->ptss_ip);
-				pt->sync_switch = true;
+				intel_pt_enable_sync_switch(pt);
 			}
 		}
 	}
@@ -1348,9 +1369,9 @@ static int intel_pt_run_decoder(struct intel_pt_queue *ptq, u64 *timestamp)
 		if (state->err) {
 			if (state->err == INTEL_PT_ERR_NODATA)
 				return 1;
-			if (pt->sync_switch &&
+			if (ptq->sync_switch &&
 			    state->from_ip >= pt->kernel_start) {
-				pt->sync_switch = false;
+				ptq->sync_switch = false;
 				intel_pt_next_tid(pt, ptq);
 			}
 			if (pt->synth_opts.errors) {
@@ -1376,7 +1397,7 @@ static int intel_pt_run_decoder(struct intel_pt_queue *ptq, u64 *timestamp)
 				     state->timestamp, state->est_timestamp);
 			ptq->timestamp = state->est_timestamp;
 		/* Use estimated TSC in unknown switch state */
-		} else if (pt->sync_switch &&
+		} else if (ptq->sync_switch &&
 			   ptq->switch_state == INTEL_PT_SS_UNKNOWN &&
 			   intel_pt_is_switch_ip(ptq, state->to_ip) &&
 			   ptq->next_tid == -1) {
@@ -1523,7 +1544,7 @@ static int intel_pt_sync_switch(struct intel_pt *pt, int cpu, pid_t tid,
 		return 1;
 
 	ptq = intel_pt_cpu_to_ptq(pt, cpu);
-	if (!ptq)
+	if (!ptq || !ptq->sync_switch)
 		return 1;
 
 	switch (ptq->switch_state) {