diff --git a/Makefile b/Makefile
index 0d4fd6427349..e94ce68ecf87 100644
--- a/Makefile
+++ b/Makefile
@@ -1,6 +1,6 @@
 VERSION = 3
 PATCHLEVEL = 10
-SUBLEVEL = 87
+SUBLEVEL = 88
 EXTRAVERSION =
 NAME = TOSSUG Baby Fish
 
diff --git a/arch/arm64/mm/mmap.c b/arch/arm64/mm/mmap.c
index 7c7be7855638..8aaf073ee078 100644
--- a/arch/arm64/mm/mmap.c
+++ b/arch/arm64/mm/mmap.c
@@ -47,22 +47,14 @@ static int mmap_is_legacy(void)
 	return sysctl_legacy_va_layout;
 }
 
-/*
- * Since get_random_int() returns the same value within a 1 jiffy window, we
- * will almost always get the same randomisation for the stack and mmap
- * region. This will mean the relative distance between stack and mmap will be
- * the same.
- *
- * To avoid this we can shift the randomness by 1 bit.
- */
 static unsigned long mmap_rnd(void)
 {
 	unsigned long rnd = 0;
 
 	if (current->flags & PF_RANDOMIZE)
-		rnd = (long)get_random_int() & (STACK_RND_MASK >> 1);
+		rnd = (long)get_random_int() & STACK_RND_MASK;
 
-	return rnd << (PAGE_SHIFT + 1);
+	return rnd << PAGE_SHIFT;
 }
 
 static unsigned long mmap_base(void)
diff --git a/drivers/crypto/caam/caamhash.c b/drivers/crypto/caam/caamhash.c
index 84573b4d6f92..dda43cc4b6cd 100644
--- a/drivers/crypto/caam/caamhash.c
+++ b/drivers/crypto/caam/caamhash.c
@@ -895,13 +895,14 @@ static int ahash_final_ctx(struct ahash_request *req)
 			  state->buflen_1;
 	u32 *sh_desc = ctx->sh_desc_fin, *desc;
 	dma_addr_t ptr = ctx->sh_desc_fin_dma;
-	int sec4_sg_bytes;
+	int sec4_sg_bytes, sec4_sg_src_index;
 	int digestsize = crypto_ahash_digestsize(ahash);
 	struct ahash_edesc *edesc;
 	int ret = 0;
 	int sh_len;
 
-	sec4_sg_bytes = (1 + (buflen ? 1 : 0)) * sizeof(struct sec4_sg_entry);
+	sec4_sg_src_index = 1 + (buflen ? 1 : 0);
+	sec4_sg_bytes = sec4_sg_src_index * sizeof(struct sec4_sg_entry);
 
 	/* allocate space for base edesc and hw desc commands, link tables */
 	edesc = kmalloc(sizeof(struct ahash_edesc) + DESC_JOB_IO_LEN +
@@ -928,7 +929,7 @@ static int ahash_final_ctx(struct ahash_request *req)
 	state->buf_dma = try_buf_map_to_sec4_sg(jrdev, edesc->sec4_sg + 1,
 						buf, state->buf_dma, buflen,
 						last_buflen);
-	(edesc->sec4_sg + sec4_sg_bytes - 1)->len |= SEC4_SG_LEN_FIN;
+	(edesc->sec4_sg + sec4_sg_src_index - 1)->len |= SEC4_SG_LEN_FIN;
 
 	append_seq_in_ptr(desc, edesc->sec4_sg_dma, ctx->ctx_len + buflen,
 			  LDST_SGF);
diff --git a/drivers/edac/ppc4xx_edac.c b/drivers/edac/ppc4xx_edac.c
index ef6b7e08f485..5c361f3c66aa 100644
--- a/drivers/edac/ppc4xx_edac.c
+++ b/drivers/edac/ppc4xx_edac.c
@@ -921,7 +921,7 @@ static int ppc4xx_edac_init_csrows(struct mem_ctl_info *mci, u32 mcopt1)
 	 */
 
 	for (row = 0; row < mci->nr_csrows; row++) {
-		struct csrow_info *csi = &mci->csrows[row];
+		struct csrow_info *csi = mci->csrows[row];
 
 		/*
 		 * Get the configuration settings for this
diff --git a/drivers/md/dm-thin-metadata.c b/drivers/md/dm-thin-metadata.c
index 3b1503dc1f13..43f6250baadd 100644
--- a/drivers/md/dm-thin-metadata.c
+++ b/drivers/md/dm-thin-metadata.c
@@ -1281,8 +1281,8 @@ static int __release_metadata_snap(struct dm_pool_metadata *pmd)
 		return r;
 
 	disk_super = dm_block_data(copy);
-	dm_sm_dec_block(pmd->metadata_sm, le64_to_cpu(disk_super->data_mapping_root));
-	dm_sm_dec_block(pmd->metadata_sm, le64_to_cpu(disk_super->device_details_root));
+	dm_btree_del(&pmd->info, le64_to_cpu(disk_super->data_mapping_root));
+	dm_btree_del(&pmd->details_info, le64_to_cpu(disk_super->device_details_root));
 	dm_sm_dec_block(pmd->metadata_sm, held_root);
 
 	return dm_tm_unlock(pmd->tm, copy);
diff --git a/drivers/scsi/libfc/fc_fcp.c b/drivers/scsi/libfc/fc_fcp.c
index 09c81b2f2169..42c46dc19537 100644
--- a/drivers/scsi/libfc/fc_fcp.c
+++ b/drivers/scsi/libfc/fc_fcp.c
@@ -1039,11 +1039,26 @@ restart:
 		fc_fcp_pkt_hold(fsp);
 		spin_unlock_irqrestore(&si->scsi_queue_lock, flags);
 
-		if (!fc_fcp_lock_pkt(fsp)) {
+		spin_lock_bh(&fsp->scsi_pkt_lock);
+		if (!(fsp->state & FC_SRB_COMPL)) {
+			fsp->state |= FC_SRB_COMPL;
+			/*
+			 * TODO: dropping scsi_pkt_lock and then reacquiring
+			 * again around fc_fcp_cleanup_cmd() is required,
+			 * since fc_fcp_cleanup_cmd() calls into
+			 * fc_seq_set_resp() and that func preempts cpu using
+			 * schedule. May be schedule and related code should be
+			 * removed instead of unlocking here to avoid scheduling
+			 * while atomic bug.
+			 */
+			spin_unlock_bh(&fsp->scsi_pkt_lock);
+
 			fc_fcp_cleanup_cmd(fsp, error);
+
+			spin_lock_bh(&fsp->scsi_pkt_lock);
 			fc_io_compl(fsp);
-			fc_fcp_unlock_pkt(fsp);
 		}
+		spin_unlock_bh(&fsp->scsi_pkt_lock);
 
 		fc_fcp_pkt_release(fsp);
 		spin_lock_irqsave(&si->scsi_queue_lock, flags);
diff --git a/include/drm/drm_pciids.h b/include/drm/drm_pciids.h
index d7b717090f2f..2b5c3bc3b081 100644
--- a/include/drm/drm_pciids.h
+++ b/include/drm/drm_pciids.h
@@ -150,6 +150,7 @@
 	{0x1002, 0x6610, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6611, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6613, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x6617, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6620, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6621, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6623, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
diff --git a/ipc/sem.c b/ipc/sem.c
index db9d241af133..47a15192b8b8 100644
--- a/ipc/sem.c
+++ b/ipc/sem.c
@@ -253,6 +253,16 @@ static void sem_rcu_free(struct rcu_head *head)
 }
 
 /*
+ * spin_unlock_wait() and !spin_is_locked() are not memory barriers, they
+ * are only control barriers.
+ * The code must pair with spin_unlock(&sem->lock) or
+ * spin_unlock(&sem_perm.lock), thus just the control barrier is insufficient.
+ *
+ * smp_rmb() is sufficient, as writes cannot pass the control barrier.
+ */
+#define ipc_smp_acquire__after_spin_is_unlocked()	smp_rmb()
+
+/*
  * Wait until all currently ongoing simple ops have completed.
  * Caller must own sem_perm.lock.
  * New simple ops cannot start, because simple ops first check
@@ -275,6 +285,7 @@ static void sem_wait_array(struct sem_array *sma)
 		sem = sma->sem_base + i;
 		spin_unlock_wait(&sem->lock);
 	}
+	ipc_smp_acquire__after_spin_is_unlocked();
 }
 
 /*
@@ -326,8 +337,13 @@ static inline int sem_lock(struct sem_array *sma, struct sembuf *sops,
 
 		/* Then check that the global lock is free */
 		if (!spin_is_locked(&sma->sem_perm.lock)) {
-			/* spin_is_locked() is not a memory barrier */
-			smp_mb();
+			/*
+			 * We need a memory barrier with acquire semantics,
+			 * otherwise we can race with another thread that does:
+			 *	complex_count++;
+			 *	spin_unlock(sem_perm.lock);
+			 */
+			ipc_smp_acquire__after_spin_is_unlocked();
 
 			/* Now repeat the test of complex_count:
 			 * It can't change anymore until we drop sem->lock.
@@ -2049,17 +2065,28 @@ void exit_sem(struct task_struct *tsk)
 		rcu_read_lock();
 		un = list_entry_rcu(ulp->list_proc.next,
 				    struct sem_undo, list_proc);
-		if (&un->list_proc == &ulp->list_proc)
-			semid = -1;
-		 else
-			semid = un->semid;
+		if (&un->list_proc == &ulp->list_proc) {
+			/*
+			 * We must wait for freeary() before freeing this ulp,
+			 * in case we raced with last sem_undo. There is a small
+			 * possibility where we exit while freeary() didn't
+			 * finish unlocking sem_undo_list.
+			 */
+			spin_unlock_wait(&ulp->lock);
+			rcu_read_unlock();
+			break;
+		}
+		spin_lock(&ulp->lock);
+		semid = un->semid;
+		spin_unlock(&ulp->lock);
 
+		/* exit_sem raced with IPC_RMID, nothing to do */
 		if (semid == -1) {
 			rcu_read_unlock();
-			break;
+			continue;
 		}
 
-		sma = sem_obtain_object_check(tsk->nsproxy->ipc_ns, un->semid);
+		sma = sem_obtain_object_check(tsk->nsproxy->ipc_ns, semid);
 		/* exit_sem raced with IPC_RMID, nothing to do */
 		if (IS_ERR(sma)) {
 			rcu_read_unlock();
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 7daf52c340cd..d9b0aad17dbf 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -3993,12 +3993,20 @@ static const struct file_operations perf_fops = {
  * to user-space before waking everybody up.
  */
 
+static inline struct fasync_struct **perf_event_fasync(struct perf_event *event)
+{
+	/* only the parent has fasync state */
+	if (event->parent)
+		event = event->parent;
+	return &event->fasync;
+}
+
 void perf_event_wakeup(struct perf_event *event)
 {
 	ring_buffer_wakeup(event);
 
 	if (event->pending_kill) {
-		kill_fasync(&event->fasync, SIGIO, event->pending_kill);
+		kill_fasync(perf_event_fasync(event), SIGIO, event->pending_kill);
 		event->pending_kill = 0;
 	}
 }
@@ -5153,7 +5161,7 @@ static int __perf_event_overflow(struct perf_event *event,
 	else
 		perf_event_output(event, data, regs);
 
-	if (event->fasync && event->pending_kill) {
+	if (*perf_event_fasync(event) && event->pending_kill) {
 		event->pending_wakeup = 1;
 		irq_work_queue(&event->pending);
 	}
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index ca96f411b034..f97d709594e6 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -1473,6 +1473,8 @@ static int get_any_page(struct page *page, unsigned long pfn, int flags)
 		 */
 		ret = __get_any_page(page, pfn, 0);
 		if (!PageLRU(page)) {
+			/* Drop page reference which is from __get_any_page() */
+			put_page(page);
 			pr_info("soft_offline: %#lx: unknown non LRU page type %lx\n",
 				pfn, page->flags);
 			return -EIO;
diff --git a/scripts/kconfig/streamline_config.pl b/scripts/kconfig/streamline_config.pl
index 4606cdfb859d..7dd7c391b4d8 100644
--- a/scripts/kconfig/streamline_config.pl
+++ b/scripts/kconfig/streamline_config.pl
@@ -137,7 +137,7 @@ my $ksource = ($ARGV[0] ? $ARGV[0] : '.');
 my $kconfig = $ARGV[1];
 my $lsmod_file = $ENV{'LSMOD'};
 
-my @makefiles = `find $ksource -name Makefile 2>/dev/null`;
+my @makefiles = `find $ksource -name Makefile -or -name Kbuild 2>/dev/null`;
 chomp @makefiles;
 
 my %depends;