diff --git a/Makefile b/Makefile
index 24182b476fd4..c64aee063096 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,7 @@
 VERSION = 5
 PATCHLEVEL = 12
 SUBLEVEL = 0
-EXTRAVERSION = -rc4
+EXTRAVERSION = -rc5
 NAME = Frozen Wasteland
 
 # *DOCUMENTATION*
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 2d6d5a28c3bf..9a85eae37b17 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -27,7 +27,7 @@ endif
 REALMODE_CFLAGS	:= -m16 -g -Os -DDISABLE_BRANCH_PROFILING \
 		   -Wall -Wstrict-prototypes -march=i386 -mregparm=3 \
 		   -fno-strict-aliasing -fomit-frame-pointer -fno-pic \
-		   -mno-mmx -mno-sse
+		   -mno-mmx -mno-sse $(call cc-option,-fcf-protection=none)
 
 REALMODE_CFLAGS += -ffreestanding
 REALMODE_CFLAGS += -fno-stack-protector
diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c
index 4b01f7dbaf30..ae78cef79980 100644
--- a/arch/x86/mm/mem_encrypt.c
+++ b/arch/x86/mm/mem_encrypt.c
@@ -262,7 +262,7 @@ static void __init __set_clr_pte_enc(pte_t *kpte, int level, bool enc)
 	if (pgprot_val(old_prot) == pgprot_val(new_prot))
 		return;
 
-	pa = pfn << page_level_shift(level);
+	pa = pfn << PAGE_SHIFT;
 	size = page_level_size(level);
 
 	/*
diff --git a/block/bio.c b/block/bio.c
index 26b7f721cda8..963d1d406b3a 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -949,7 +949,7 @@ void bio_release_pages(struct bio *bio, bool mark_dirty)
 }
 EXPORT_SYMBOL_GPL(bio_release_pages);
 
-static int bio_iov_bvec_set(struct bio *bio, struct iov_iter *iter)
+static void __bio_iov_bvec_set(struct bio *bio, struct iov_iter *iter)
 {
 	WARN_ON_ONCE(bio->bi_max_vecs);
 
@@ -959,11 +959,26 @@ static int bio_iov_bvec_set(struct bio *bio, struct iov_iter *iter)
 	bio->bi_iter.bi_size = iter->count;
 	bio_set_flag(bio, BIO_NO_PAGE_REF);
 	bio_set_flag(bio, BIO_CLONED);
+}
 
+static int bio_iov_bvec_set(struct bio *bio, struct iov_iter *iter)
+{
+	__bio_iov_bvec_set(bio, iter);
 	iov_iter_advance(iter, iter->count);
 	return 0;
 }
 
+static int bio_iov_bvec_set_append(struct bio *bio, struct iov_iter *iter)
+{
+	struct request_queue *q = bio->bi_bdev->bd_disk->queue;
+	struct iov_iter i = *iter;
+
+	iov_iter_truncate(&i, queue_max_zone_append_sectors(q) << 9);
+	__bio_iov_bvec_set(bio, &i);
+	iov_iter_advance(iter, i.count);
+	return 0;
+}
+
 #define PAGE_PTRS_PER_BVEC     (sizeof(struct bio_vec) / sizeof(struct page *))
 
 /**
@@ -1094,8 +1109,8 @@ int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
 	int ret = 0;
 
 	if (iov_iter_is_bvec(iter)) {
-		if (WARN_ON_ONCE(bio_op(bio) == REQ_OP_ZONE_APPEND))
-			return -EINVAL;
+		if (bio_op(bio) == REQ_OP_ZONE_APPEND)
+			return bio_iov_bvec_set_append(bio, iter);
 		return bio_iov_bvec_set(bio, iter);
 	}
 
diff --git a/block/blk-merge.c b/block/blk-merge.c
index ffb4aa0ea68b..4d97fb6dd226 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -382,6 +382,14 @@ unsigned int blk_recalc_rq_segments(struct request *rq)
 	switch (bio_op(rq->bio)) {
 	case REQ_OP_DISCARD:
 	case REQ_OP_SECURE_ERASE:
+		if (queue_max_discard_segments(rq->q) > 1) {
+			struct bio *bio = rq->bio;
+
+			for_each_bio(bio)
+				nr_phys_segs++;
+			return nr_phys_segs;
+		}
+		return 1;
 	case REQ_OP_WRITE_ZEROES:
 		return 0;
 	case REQ_OP_WRITE_SAME:
diff --git a/block/partitions/core.c b/block/partitions/core.c
index 1a7558917c47..46f055bc7ecb 100644
--- a/block/partitions/core.c
+++ b/block/partitions/core.c
@@ -322,6 +322,13 @@ static struct block_device *add_partition(struct gendisk *disk, int partno,
 	const char *dname;
 	int err;
 
+	/*
+	 * disk_max_parts() won't be zero, either GENHD_FL_EXT_DEVT is set
+	 * or 'minors' is passed to alloc_disk().
+	 */
+	if (partno >= disk_max_parts(disk))
+		return ERR_PTR(-EINVAL);
+
 	/*
 	 * Partitions are not supported on zoned block devices that are used as
 	 * such.
diff --git a/drivers/auxdisplay/charlcd.c b/drivers/auxdisplay/charlcd.c
index f43430e9dcee..24fd6f369ebe 100644
--- a/drivers/auxdisplay/charlcd.c
+++ b/drivers/auxdisplay/charlcd.c
@@ -470,12 +470,14 @@ static ssize_t charlcd_write(struct file *file, const char __user *buf,
 	char c;
 
 	for (; count-- > 0; (*ppos)++, tmp++) {
-		if (!in_interrupt() && (((count + 1) & 0x1f) == 0))
+		if (((count + 1) & 0x1f) == 0) {
 			/*
-			 * let's be a little nice with other processes
-			 * that need some CPU
+			 * charlcd_write() is invoked as a VFS->write() callback
+			 * and as such it is always invoked from preemptible
+			 * context and may sleep.
 			 */
-			schedule();
+			cond_resched();
+		}
 
 		if (get_user(c, tmp))
 			return -EFAULT;
@@ -537,12 +539,8 @@ static void charlcd_puts(struct charlcd *lcd, const char *s)
 	int count = strlen(s);
 
 	for (; count-- > 0; tmp++) {
-		if (!in_interrupt() && (((count + 1) & 0x1f) == 0))
-			/*
-			 * let's be a little nice with other processes
-			 * that need some CPU
-			 */
-			schedule();
+		if (((count + 1) & 0x1f) == 0)
+			cond_resched();
 
 		charlcd_write_char(lcd, *tmp);
 	}
diff --git a/drivers/scsi/ibmvscsi/ibmvfc.c b/drivers/scsi/ibmvscsi/ibmvfc.c
index f140eafc0d6a..61831f2fdb30 100644
--- a/drivers/scsi/ibmvscsi/ibmvfc.c
+++ b/drivers/scsi/ibmvscsi/ibmvfc.c
@@ -2371,6 +2371,24 @@ static int ibmvfc_match_lun(struct ibmvfc_event *evt, void *device)
 	return 0;
 }
 
+/**
+ * ibmvfc_event_is_free - Check if event is free or not
+ * @evt:	ibmvfc event struct
+ *
+ * Returns:
+ *	true / false
+ **/
+static bool ibmvfc_event_is_free(struct ibmvfc_event *evt)
+{
+	struct ibmvfc_event *loop_evt;
+
+	list_for_each_entry(loop_evt, &evt->queue->free, queue_list)
+		if (loop_evt == evt)
+			return true;
+
+	return false;
+}
+
 /**
  * ibmvfc_wait_for_ops - Wait for ops to complete
  * @vhost:	ibmvfc host struct
@@ -2385,35 +2403,58 @@ static int ibmvfc_wait_for_ops(struct ibmvfc_host *vhost, void *device,
 {
 	struct ibmvfc_event *evt;
 	DECLARE_COMPLETION_ONSTACK(comp);
-	int wait;
+	int wait, i, q_index, q_size;
 	unsigned long flags;
 	signed long timeout = IBMVFC_ABORT_WAIT_TIMEOUT * HZ;
+	struct ibmvfc_queue *queues;
 
 	ENTER;
+	if (vhost->mq_enabled && vhost->using_channels) {
+		queues = vhost->scsi_scrqs.scrqs;
+		q_size = vhost->scsi_scrqs.active_queues;
+	} else {
+		queues = &vhost->crq;
+		q_size = 1;
+	}
+
 	do {
 		wait = 0;
-		spin_lock_irqsave(&vhost->crq.l_lock, flags);
-		list_for_each_entry(evt, &vhost->crq.sent, queue_list) {
-			if (match(evt, device)) {
-				evt->eh_comp = &comp;
-				wait++;
+		spin_lock_irqsave(vhost->host->host_lock, flags);
+		for (q_index = 0; q_index < q_size; q_index++) {
+			spin_lock(&queues[q_index].l_lock);
+			for (i = 0; i < queues[q_index].evt_pool.size; i++) {
+				evt = &queues[q_index].evt_pool.events[i];
+				if (!ibmvfc_event_is_free(evt)) {
+					if (match(evt, device)) {
+						evt->eh_comp = &comp;
+						wait++;
+					}
+				}
 			}
+			spin_unlock(&queues[q_index].l_lock);
 		}
-		spin_unlock_irqrestore(&vhost->crq.l_lock, flags);
+		spin_unlock_irqrestore(vhost->host->host_lock, flags);
 
 		if (wait) {
 			timeout = wait_for_completion_timeout(&comp, timeout);
 
 			if (!timeout) {
 				wait = 0;
-				spin_lock_irqsave(&vhost->crq.l_lock, flags);
-				list_for_each_entry(evt, &vhost->crq.sent, queue_list) {
-					if (match(evt, device)) {
-						evt->eh_comp = NULL;
-						wait++;
+				spin_lock_irqsave(vhost->host->host_lock, flags);
+				for (q_index = 0; q_index < q_size; q_index++) {
+					spin_lock(&queues[q_index].l_lock);
+					for (i = 0; i < queues[q_index].evt_pool.size; i++) {
+						evt = &queues[q_index].evt_pool.events[i];
+						if (!ibmvfc_event_is_free(evt)) {
+							if (match(evt, device)) {
+								evt->eh_comp = NULL;
+								wait++;
+							}
+						}
 					}
+					spin_unlock(&queues[q_index].l_lock);
 				}
-				spin_unlock_irqrestore(&vhost->crq.l_lock, flags);
+				spin_unlock_irqrestore(vhost->host->host_lock, flags);
 				if (wait)
 					dev_err(vhost->dev, "Timed out waiting for aborted commands\n");
 				LEAVE;
diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c
index ac066f86bb14..ac0eef975f17 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_base.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_base.c
@@ -7806,14 +7806,18 @@ mpt3sas_base_attach(struct MPT3SAS_ADAPTER *ioc)
 		ioc->pend_os_device_add_sz++;
 	ioc->pend_os_device_add = kzalloc(ioc->pend_os_device_add_sz,
 	    GFP_KERNEL);
-	if (!ioc->pend_os_device_add)
+	if (!ioc->pend_os_device_add) {
+		r = -ENOMEM;
 		goto out_free_resources;
+	}
 
 	ioc->device_remove_in_progress_sz = ioc->pend_os_device_add_sz;
 	ioc->device_remove_in_progress =
 		kzalloc(ioc->device_remove_in_progress_sz, GFP_KERNEL);
-	if (!ioc->device_remove_in_progress)
+	if (!ioc->device_remove_in_progress) {
+		r = -ENOMEM;
 		goto out_free_resources;
+	}
 
 	ioc->fwfault_debug = mpt3sas_fwfault_debug;
 
diff --git a/drivers/scsi/qedi/qedi_main.c b/drivers/scsi/qedi/qedi_main.c
index 47ad64b06623..69c5b5ee2169 100644
--- a/drivers/scsi/qedi/qedi_main.c
+++ b/drivers/scsi/qedi/qedi_main.c
@@ -1675,6 +1675,7 @@ static int qedi_alloc_global_queues(struct qedi_ctx *qedi)
 		if (!qedi->global_queues[i]) {
 			QEDI_ERR(&qedi->dbg_ctx,
 				 "Unable to allocation global queue %d.\n", i);
+			status = -ENOMEM;
 			goto mem_alloc_failure;
 		}
 
diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c
index c48daf52725d..480e7d2dcf3e 100644
--- a/drivers/scsi/qla2xxx/qla_target.c
+++ b/drivers/scsi/qla2xxx/qla_target.c
@@ -3222,8 +3222,7 @@ int qlt_xmit_response(struct qla_tgt_cmd *cmd, int xmit_type,
 	if (!qpair->fw_started || (cmd->reset_count != qpair->chip_reset) ||
 	    (cmd->sess && cmd->sess->deleted)) {
 		cmd->state = QLA_TGT_STATE_PROCESSED;
-		res = 0;
-		goto free;
+		return 0;
 	}
 
 	ql_dbg_qp(ql_dbg_tgt, qpair, 0xe018,
@@ -3234,8 +3233,9 @@ int qlt_xmit_response(struct qla_tgt_cmd *cmd, int xmit_type,
 
 	res = qlt_pre_xmit_response(cmd, &prm, xmit_type, scsi_status,
 	    &full_req_cnt);
-	if (unlikely(res != 0))
-		goto free;
+	if (unlikely(res != 0)) {
+		return res;
+	}
 
 	spin_lock_irqsave(qpair->qp_lock_ptr, flags);
 
@@ -3255,8 +3255,7 @@ int qlt_xmit_response(struct qla_tgt_cmd *cmd, int xmit_type,
 			vha->flags.online, qla2x00_reset_active(vha),
 			cmd->reset_count, qpair->chip_reset);
 		spin_unlock_irqrestore(qpair->qp_lock_ptr, flags);
-		res = 0;
-		goto free;
+		return 0;
 	}
 
 	/* Does F/W have an IOCBs for this request */
@@ -3359,8 +3358,6 @@ int qlt_xmit_response(struct qla_tgt_cmd *cmd, int xmit_type,
 	qlt_unmap_sg(vha, cmd);
 	spin_unlock_irqrestore(qpair->qp_lock_ptr, flags);
 
-free:
-	vha->hw->tgt.tgt_ops->free_cmd(cmd);
 	return res;
 }
 EXPORT_SYMBOL(qlt_xmit_response);
diff --git a/drivers/scsi/qla2xxx/tcm_qla2xxx.c b/drivers/scsi/qla2xxx/tcm_qla2xxx.c
index b55fc768a2a7..8b4890cdd4ca 100644
--- a/drivers/scsi/qla2xxx/tcm_qla2xxx.c
+++ b/drivers/scsi/qla2xxx/tcm_qla2xxx.c
@@ -644,7 +644,6 @@ static int tcm_qla2xxx_queue_data_in(struct se_cmd *se_cmd)
 {
 	struct qla_tgt_cmd *cmd = container_of(se_cmd,
 				struct qla_tgt_cmd, se_cmd);
-	struct scsi_qla_host *vha = cmd->vha;
 
 	if (cmd->aborted) {
 		/* Cmd can loop during Q-full.  tcm_qla2xxx_aborted_task
@@ -657,7 +656,6 @@ static int tcm_qla2xxx_queue_data_in(struct se_cmd *se_cmd)
 			cmd->se_cmd.transport_state,
 			cmd->se_cmd.t_state,
 			cmd->se_cmd.se_cmd_flags);
-		vha->hw->tgt.tgt_ops->free_cmd(cmd);
 		return 0;
 	}
 
@@ -685,7 +683,6 @@ static int tcm_qla2xxx_queue_status(struct se_cmd *se_cmd)
 {
 	struct qla_tgt_cmd *cmd = container_of(se_cmd,
 				struct qla_tgt_cmd, se_cmd);
-	struct scsi_qla_host *vha = cmd->vha;
 	int xmit_type = QLA_TGT_XMIT_STATUS;
 
 	if (cmd->aborted) {
@@ -699,7 +696,6 @@ static int tcm_qla2xxx_queue_status(struct se_cmd *se_cmd)
 		    cmd, kref_read(&cmd->se_cmd.cmd_kref),
 		    cmd->se_cmd.transport_state, cmd->se_cmd.t_state,
 		    cmd->se_cmd.se_cmd_flags);
-		vha->hw->tgt.tgt_ops->free_cmd(cmd);
 		return 0;
 	}
 	cmd->bufflen = se_cmd->data_length;
diff --git a/drivers/target/target_core_pscsi.c b/drivers/target/target_core_pscsi.c
index 3cbc074992bc..9ee797b8cb7e 100644
--- a/drivers/target/target_core_pscsi.c
+++ b/drivers/target/target_core_pscsi.c
@@ -882,7 +882,6 @@ pscsi_map_sg(struct se_cmd *cmd, struct scatterlist *sgl, u32 sgl_nents,
 			if (!bio) {
 new_bio:
 				nr_vecs = bio_max_segs(nr_pages);
-				nr_pages -= nr_vecs;
 				/*
 				 * Calls bio_kmalloc() and sets bio->bi_end_io()
 				 */
@@ -939,6 +938,14 @@ pscsi_map_sg(struct se_cmd *cmd, struct scatterlist *sgl, u32 sgl_nents,
 
 	return 0;
 fail:
+	if (bio)
+		bio_put(bio);
+	while (req->bio) {
+		bio = req->bio;
+		req->bio = bio->bi_next;
+		bio_put(bio);
+	}
+	req->biotail = NULL;
 	return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
 }
 
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 92ed7d5df677..28d583fcdc2c 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -1240,13 +1240,13 @@ int bdev_disk_changed(struct block_device *bdev, bool invalidate)
 
 	lockdep_assert_held(&bdev->bd_mutex);
 
-	clear_bit(GD_NEED_PART_SCAN, &bdev->bd_disk->state);
-
 rescan:
 	ret = blk_drop_partitions(bdev);
 	if (ret)
 		return ret;
 
+	clear_bit(GD_NEED_PART_SCAN, &disk->state);
+
 	/*
 	 * Historically we only set the capacity to zero for devices that
 	 * support partitions (independ of actually having partitions created).
diff --git a/fs/cifs/cifsacl.c b/fs/cifs/cifsacl.c
index 2be22a5c690f..d178cf85e926 100644
--- a/fs/cifs/cifsacl.c
+++ b/fs/cifs/cifsacl.c
@@ -1130,8 +1130,7 @@ static int set_chmod_dacl(struct cifs_acl *pdacl, struct cifs_acl *pndacl,
 		}
 
 		/* If it's any one of the ACE we're replacing, skip! */
-		if (!mode_from_sid &&
-				((compare_sids(&pntace->sid, &sid_unix_NFS_mode) == 0) ||
+		if (((compare_sids(&pntace->sid, &sid_unix_NFS_mode) == 0) ||
 				(compare_sids(&pntace->sid, pownersid) == 0) ||
 				(compare_sids(&pntace->sid, pgrpsid) == 0) ||
 				(compare_sids(&pntace->sid, &sid_everyone) == 0) ||
diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index 31fc8695abd6..67c056a9a519 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -919,8 +919,8 @@ struct cifs_ses {
 	bool binding:1; /* are we binding the session? */
 	__u16 session_flags;
 	__u8 smb3signingkey[SMB3_SIGN_KEY_SIZE];
-	__u8 smb3encryptionkey[SMB3_SIGN_KEY_SIZE];
-	__u8 smb3decryptionkey[SMB3_SIGN_KEY_SIZE];
+	__u8 smb3encryptionkey[SMB3_ENC_DEC_KEY_SIZE];
+	__u8 smb3decryptionkey[SMB3_ENC_DEC_KEY_SIZE];
 	__u8 preauth_sha_hash[SMB2_PREAUTH_HASH_SIZE];
 
 	__u8 binding_preauth_sha_hash[SMB2_PREAUTH_HASH_SIZE];
diff --git a/fs/cifs/cifspdu.h b/fs/cifs/cifspdu.h
index 64fe5a47b5e8..9adc74bd9f8f 100644
--- a/fs/cifs/cifspdu.h
+++ b/fs/cifs/cifspdu.h
@@ -147,6 +147,11 @@
  */
 #define SMB3_SIGN_KEY_SIZE (16)
 
+/*
+ * Size of the smb3 encryption/decryption keys
+ */
+#define SMB3_ENC_DEC_KEY_SIZE (32)
+
 #define CIFS_CLIENT_CHALLENGE_SIZE (8)
 #define CIFS_SERVER_CHALLENGE_SIZE (8)
 #define CIFS_HMAC_MD5_HASH_SIZE (16)
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 26de4329d161..042e24aad410 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -165,6 +165,7 @@ int cifs_posix_open(char *full_path, struct inode **pinode,
 			goto posix_open_ret;
 		}
 	} else {
+		cifs_revalidate_mapping(*pinode);
 		cifs_fattr_to_inode(*pinode, &fattr);
 	}
 
diff --git a/fs/cifs/smb2glob.h b/fs/cifs/smb2glob.h
index 99a1951a01ec..d9a990c99121 100644
--- a/fs/cifs/smb2glob.h
+++ b/fs/cifs/smb2glob.h
@@ -58,6 +58,7 @@
 #define SMB2_HMACSHA256_SIZE (32)
 #define SMB2_CMACAES_SIZE (16)
 #define SMB3_SIGNKEY_SIZE (16)
+#define SMB3_GCM128_CRYPTKEY_SIZE (16)
 #define SMB3_GCM256_CRYPTKEY_SIZE (32)
 
 /* Maximum buffer size value we can send with 1 credit */
diff --git a/fs/cifs/smb2misc.c b/fs/cifs/smb2misc.c
index b50164e2c88d..aac384f69f74 100644
--- a/fs/cifs/smb2misc.c
+++ b/fs/cifs/smb2misc.c
@@ -754,8 +754,8 @@ smb2_is_valid_oplock_break(char *buffer, struct TCP_Server_Info *server)
 		}
 	}
 	spin_unlock(&cifs_tcp_ses_lock);
-	cifs_dbg(FYI, "Can not process oplock break for non-existent connection\n");
-	return false;
+	cifs_dbg(FYI, "No file id matched, oplock break ignored\n");
+	return true;
 }
 
 void
diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index 9bae7e8deb09..f703204fb185 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -2038,6 +2038,7 @@ smb2_duplicate_extents(const unsigned int xid,
 {
 	int rc;
 	unsigned int ret_data_len;
+	struct inode *inode;
 	struct duplicate_extents_to_file dup_ext_buf;
 	struct cifs_tcon *tcon = tlink_tcon(trgtfile->tlink);
 
@@ -2054,10 +2055,21 @@ smb2_duplicate_extents(const unsigned int xid,
 	cifs_dbg(FYI, "Duplicate extents: src off %lld dst off %lld len %lld\n",
 		src_off, dest_off, len);
 
-	rc = smb2_set_file_size(xid, tcon, trgtfile, dest_off + len, false);
-	if (rc)
-		goto duplicate_extents_out;
+	inode = d_inode(trgtfile->dentry);
+	if (inode->i_size < dest_off + len) {
+		rc = smb2_set_file_size(xid, tcon, trgtfile, dest_off + len, false);
+		if (rc)
+			goto duplicate_extents_out;
 
+		/*
+		 * Although also could set plausible allocation size (i_blocks)
+		 * here in addition to setting the file size, in reflink
+		 * it is likely that the target file is sparse. Its allocation
+		 * size will be queried on next revalidate, but it is important
+		 * to make sure that file's cached size is updated immediately
+		 */
+		cifs_setsize(inode, dest_off + len);
+	}
 	rc = SMB2_ioctl(xid, tcon, trgtfile->fid.persistent_fid,
 			trgtfile->fid.volatile_fid,
 			FSCTL_DUPLICATE_EXTENTS_TO_FILE,
@@ -4158,7 +4170,7 @@ smb2_get_enc_key(struct TCP_Server_Info *server, __u64 ses_id, int enc, u8 *key)
 			if (ses->Suid == ses_id) {
 				ses_enc_key = enc ? ses->smb3encryptionkey :
 					ses->smb3decryptionkey;
-				memcpy(key, ses_enc_key, SMB3_SIGN_KEY_SIZE);
+				memcpy(key, ses_enc_key, SMB3_ENC_DEC_KEY_SIZE);
 				spin_unlock(&cifs_tcp_ses_lock);
 				return 0;
 			}
@@ -4185,7 +4197,7 @@ crypt_message(struct TCP_Server_Info *server, int num_rqst,
 	int rc = 0;
 	struct scatterlist *sg;
 	u8 sign[SMB2_SIGNATURE_SIZE] = {};
-	u8 key[SMB3_SIGN_KEY_SIZE];
+	u8 key[SMB3_ENC_DEC_KEY_SIZE];
 	struct aead_request *req;
 	char *iv;
 	unsigned int iv_len;
@@ -4209,10 +4221,11 @@ crypt_message(struct TCP_Server_Info *server, int num_rqst,
 	tfm = enc ? server->secmech.ccmaesencrypt :
 						server->secmech.ccmaesdecrypt;
 
-	if (server->cipher_type == SMB2_ENCRYPTION_AES256_GCM)
+	if ((server->cipher_type == SMB2_ENCRYPTION_AES256_CCM) ||
+		(server->cipher_type == SMB2_ENCRYPTION_AES256_GCM))
 		rc = crypto_aead_setkey(tfm, key, SMB3_GCM256_CRYPTKEY_SIZE);
 	else
-		rc = crypto_aead_setkey(tfm, key, SMB3_SIGN_KEY_SIZE);
+		rc = crypto_aead_setkey(tfm, key, SMB3_GCM128_CRYPTKEY_SIZE);
 
 	if (rc) {
 		cifs_server_dbg(VFS, "%s: Failed to set aead key %d\n", __func__, rc);
diff --git a/fs/cifs/smb2transport.c b/fs/cifs/smb2transport.c
index ebccd71cc60a..e6fa76ab70be 100644
--- a/fs/cifs/smb2transport.c
+++ b/fs/cifs/smb2transport.c
@@ -298,7 +298,8 @@ static int generate_key(struct cifs_ses *ses, struct kvec label,
 {
 	unsigned char zero = 0x0;
 	__u8 i[4] = {0, 0, 0, 1};
-	__u8 L[4] = {0, 0, 0, 128};
+	__u8 L128[4] = {0, 0, 0, 128};
+	__u8 L256[4] = {0, 0, 1, 0};
 	int rc = 0;
 	unsigned char prfhash[SMB2_HMACSHA256_SIZE];
 	unsigned char *hashptr = prfhash;
@@ -354,8 +355,14 @@ static int generate_key(struct cifs_ses *ses, struct kvec label,
 		goto smb3signkey_ret;
 	}
 
-	rc = crypto_shash_update(&server->secmech.sdeschmacsha256->shash,
-				L, 4);
+	if ((server->cipher_type == SMB2_ENCRYPTION_AES256_CCM) ||
+		(server->cipher_type == SMB2_ENCRYPTION_AES256_GCM)) {
+		rc = crypto_shash_update(&server->secmech.sdeschmacsha256->shash,
+				L256, 4);
+	} else {
+		rc = crypto_shash_update(&server->secmech.sdeschmacsha256->shash,
+				L128, 4);
+	}
 	if (rc) {
 		cifs_server_dbg(VFS, "%s: Could not update with L\n", __func__);
 		goto smb3signkey_ret;
@@ -390,6 +397,9 @@ generate_smb3signingkey(struct cifs_ses *ses,
 			const struct derivation_triplet *ptriplet)
 {
 	int rc;
+#ifdef CONFIG_CIFS_DEBUG_DUMP_KEYS
+	struct TCP_Server_Info *server = ses->server;
+#endif
 
 	/*
 	 * All channels use the same encryption/decryption keys but
@@ -422,11 +432,11 @@ generate_smb3signingkey(struct cifs_ses *ses,
 		rc = generate_key(ses, ptriplet->encryption.label,
 				  ptriplet->encryption.context,
 				  ses->smb3encryptionkey,
-				  SMB3_SIGN_KEY_SIZE);
+				  SMB3_ENC_DEC_KEY_SIZE);
 		rc = generate_key(ses, ptriplet->decryption.label,
 				  ptriplet->decryption.context,
 				  ses->smb3decryptionkey,
-				  SMB3_SIGN_KEY_SIZE);
+				  SMB3_ENC_DEC_KEY_SIZE);
 		if (rc)
 			return rc;
 	}
@@ -442,14 +452,23 @@ generate_smb3signingkey(struct cifs_ses *ses,
 	 */
 	cifs_dbg(VFS, "Session Id    %*ph\n", (int)sizeof(ses->Suid),
 			&ses->Suid);
+	cifs_dbg(VFS, "Cipher type   %d\n", server->cipher_type);
 	cifs_dbg(VFS, "Session Key   %*ph\n",
 		 SMB2_NTLMV2_SESSKEY_SIZE, ses->auth_key.response);
 	cifs_dbg(VFS, "Signing Key   %*ph\n",
 		 SMB3_SIGN_KEY_SIZE, ses->smb3signingkey);
-	cifs_dbg(VFS, "ServerIn Key  %*ph\n",
-		 SMB3_SIGN_KEY_SIZE, ses->smb3encryptionkey);
-	cifs_dbg(VFS, "ServerOut Key %*ph\n",
-		 SMB3_SIGN_KEY_SIZE, ses->smb3decryptionkey);
+	if ((server->cipher_type == SMB2_ENCRYPTION_AES256_CCM) ||
+		(server->cipher_type == SMB2_ENCRYPTION_AES256_GCM)) {
+		cifs_dbg(VFS, "ServerIn Key  %*ph\n",
+				SMB3_GCM256_CRYPTKEY_SIZE, ses->smb3encryptionkey);
+		cifs_dbg(VFS, "ServerOut Key %*ph\n",
+				SMB3_GCM256_CRYPTKEY_SIZE, ses->smb3decryptionkey);
+	} else {
+		cifs_dbg(VFS, "ServerIn Key  %*ph\n",
+				SMB3_GCM128_CRYPTKEY_SIZE, ses->smb3encryptionkey);
+		cifs_dbg(VFS, "ServerOut Key %*ph\n",
+				SMB3_GCM128_CRYPTKEY_SIZE, ses->smb3decryptionkey);
+	}
 #endif
 	return rc;
 }
diff --git a/fs/io-wq.c b/fs/io-wq.c
index 3dc10bfd8c3b..7434eb40ca8c 100644
--- a/fs/io-wq.c
+++ b/fs/io-wq.c
@@ -16,7 +16,6 @@
 #include <linux/rculist_nulls.h>
 #include <linux/cpu.h>
 #include <linux/tracehook.h>
-#include <linux/freezer.h>
 
 #include "../kernel/sched/sched.h"
 #include "io-wq.h"
@@ -388,11 +387,9 @@ static struct io_wq_work *io_get_next_work(struct io_wqe *wqe)
 
 static bool io_flush_signals(void)
 {
-	if (unlikely(test_tsk_thread_flag(current, TIF_NOTIFY_SIGNAL))) {
+	if (unlikely(test_thread_flag(TIF_NOTIFY_SIGNAL))) {
 		__set_current_state(TASK_RUNNING);
-		if (current->task_works)
-			task_work_run();
-		clear_tsk_thread_flag(current, TIF_NOTIFY_SIGNAL);
+		tracehook_notify_signal();
 		return true;
 	}
 	return false;
@@ -505,10 +502,15 @@ static int io_wqe_worker(void *data)
 		if (io_flush_signals())
 			continue;
 		ret = schedule_timeout(WORKER_IDLE_TIMEOUT);
-		if (try_to_freeze() || ret)
-			continue;
-		if (fatal_signal_pending(current))
+		if (signal_pending(current)) {
+			struct ksignal ksig;
+
+			if (!get_signal(&ksig))
+				continue;
 			break;
+		}
+		if (ret)
+			continue;
 		/* timed out, exit unless we're the fixed worker */
 		if (test_bit(IO_WQ_BIT_EXIT, &wq->state) ||
 		    !(worker->flags & IO_WORKER_F_FIXED))
@@ -716,9 +718,13 @@ static int io_wq_manager(void *data)
 		set_current_state(TASK_INTERRUPTIBLE);
 		io_wq_check_workers(wq);
 		schedule_timeout(HZ);
-		try_to_freeze();
-		if (fatal_signal_pending(current))
+		if (signal_pending(current)) {
+			struct ksignal ksig;
+
+			if (!get_signal(&ksig))
+				continue;
 			set_bit(IO_WQ_BIT_EXIT, &wq->state);
+		}
 	} while (!test_bit(IO_WQ_BIT_EXIT, &wq->state));
 
 	io_wq_check_workers(wq);
@@ -1065,7 +1071,11 @@ static void io_wq_destroy(struct io_wq *wq)
 
 	for_each_node(node) {
 		struct io_wqe *wqe = wq->wqes[node];
-		WARN_ON_ONCE(!wq_list_empty(&wqe->work_list));
+		struct io_cb_cancel_data match = {
+			.fn		= io_wq_work_match_all,
+			.cancel_all	= true,
+		};
+		io_wqe_cancel_pending_work(wqe, &match);
 		kfree(wqe);
 	}
 	io_wq_put_hash(wq->hash);
diff --git a/fs/io_uring.c b/fs/io_uring.c
index 543551d70327..1949b80677e7 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -78,7 +78,6 @@
 #include <linux/task_work.h>
 #include <linux/pagemap.h>
 #include <linux/io_uring.h>
-#include <linux/freezer.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/io_uring.h>
@@ -1095,8 +1094,6 @@ static bool io_match_task(struct io_kiocb *head,
 	io_for_each_link(req, head) {
 		if (req->flags & REQ_F_INFLIGHT)
 			return true;
-		if (req->task->files == files)
-			return true;
 	}
 	return false;
 }
@@ -1239,16 +1236,16 @@ static void io_queue_async_work(struct io_kiocb *req)
 	BUG_ON(!tctx);
 	BUG_ON(!tctx->io_wq);
 
-	trace_io_uring_queue_async_work(ctx, io_wq_is_hashed(&req->work), req,
-					&req->work, req->flags);
 	/* init ->work of the whole link before punting */
 	io_prep_async_link(req);
+	trace_io_uring_queue_async_work(ctx, io_wq_is_hashed(&req->work), req,
+					&req->work, req->flags);
 	io_wq_enqueue(tctx->io_wq, &req->work);
 	if (link)
 		io_queue_linked_timeout(link);
 }
 
-static void io_kill_timeout(struct io_kiocb *req)
+static void io_kill_timeout(struct io_kiocb *req, int status)
 {
 	struct io_timeout_data *io = req->async_data;
 	int ret;
@@ -1258,31 +1255,11 @@ static void io_kill_timeout(struct io_kiocb *req)
 		atomic_set(&req->ctx->cq_timeouts,
 			atomic_read(&req->ctx->cq_timeouts) + 1);
 		list_del_init(&req->timeout.list);
-		io_cqring_fill_event(req, 0);
+		io_cqring_fill_event(req, status);
 		io_put_req_deferred(req, 1);
 	}
 }
 
-/*
- * Returns true if we found and killed one or more timeouts
- */
-static bool io_kill_timeouts(struct io_ring_ctx *ctx, struct task_struct *tsk,
-			     struct files_struct *files)
-{
-	struct io_kiocb *req, *tmp;
-	int canceled = 0;
-
-	spin_lock_irq(&ctx->completion_lock);
-	list_for_each_entry_safe(req, tmp, &ctx->timeout_list, timeout.list) {
-		if (io_match_task(req, tsk, files)) {
-			io_kill_timeout(req);
-			canceled++;
-		}
-	}
-	spin_unlock_irq(&ctx->completion_lock);
-	return canceled != 0;
-}
-
 static void __io_queue_deferred(struct io_ring_ctx *ctx)
 {
 	do {
@@ -1327,7 +1304,7 @@ static void io_flush_timeouts(struct io_ring_ctx *ctx)
 			break;
 
 		list_del_init(&req->timeout.list);
-		io_kill_timeout(req);
+		io_kill_timeout(req, 0);
 	} while (!list_empty(&ctx->timeout_list));
 
 	ctx->cq_last_tm_flush = seq;
@@ -2524,13 +2501,12 @@ static void __io_complete_rw(struct io_kiocb *req, long res, long res2,
 {
 	int cflags = 0;
 
+	if (req->rw.kiocb.ki_flags & IOCB_WRITE)
+		kiocb_end_write(req);
 	if ((res == -EAGAIN || res == -EOPNOTSUPP) && io_rw_reissue(req))
 		return;
 	if (res != req->result)
 		req_set_fail_links(req);
-
-	if (req->rw.kiocb.ki_flags & IOCB_WRITE)
-		kiocb_end_write(req);
 	if (req->flags & REQ_F_BUFFER_SELECTED)
 		cflags = io_put_rw_kbuf(req);
 	__io_req_complete(req, issue_flags, res, cflags);
@@ -3978,6 +3954,7 @@ static int io_remove_buffers(struct io_kiocb *req, unsigned int issue_flags)
 static int io_provide_buffers_prep(struct io_kiocb *req,
 				   const struct io_uring_sqe *sqe)
 {
+	unsigned long size;
 	struct io_provide_buf *p = &req->pbuf;
 	u64 tmp;
 
@@ -3991,7 +3968,8 @@ static int io_provide_buffers_prep(struct io_kiocb *req,
 	p->addr = READ_ONCE(sqe->addr);
 	p->len = READ_ONCE(sqe->len);
 
-	if (!access_ok(u64_to_user_ptr(p->addr), (p->len * p->nbufs)))
+	size = (unsigned long)p->len * p->nbufs;
+	if (!access_ok(u64_to_user_ptr(p->addr), size))
 		return -EFAULT;
 
 	p->bgid = READ_ONCE(sqe->buf_group);
@@ -4820,7 +4798,6 @@ static int io_connect(struct io_kiocb *req, unsigned int issue_flags)
 			ret = -ENOMEM;
 			goto out;
 		}
-		io = req->async_data;
 		memcpy(req->async_data, &__io, sizeof(__io));
 		return -EAGAIN;
 	}
@@ -5583,7 +5560,8 @@ static int io_timeout_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe,
 
 	data->mode = io_translate_timeout_mode(flags);
 	hrtimer_init(&data->timer, CLOCK_MONOTONIC, data->mode);
-	io_req_track_inflight(req);
+	if (is_timeout_link)
+		io_req_track_inflight(req);
 	return 0;
 }
 
@@ -6479,8 +6457,6 @@ static int io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req,
 	ret = io_init_req(ctx, req, sqe);
 	if (unlikely(ret)) {
 fail_req:
-		io_put_req(req);
-		io_req_complete(req, ret);
 		if (link->head) {
 			/* fail even hard links since we don't submit */
 			link->head->flags |= REQ_F_FAIL_LINK;
@@ -6488,6 +6464,8 @@ static int io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req,
 			io_req_complete(link->head, -ECANCELED);
 			link->head = NULL;
 		}
+		io_put_req(req);
+		io_req_complete(req, ret);
 		return ret;
 	}
 	ret = io_req_prep(req, sqe);
@@ -6764,8 +6742,13 @@ static int io_sq_thread(void *data)
 			timeout = jiffies + sqd->sq_thread_idle;
 			continue;
 		}
-		if (fatal_signal_pending(current))
+		if (signal_pending(current)) {
+			struct ksignal ksig;
+
+			if (!get_signal(&ksig))
+				continue;
 			break;
+		}
 		sqt_spin = false;
 		cap_entries = !list_is_singular(&sqd->ctx_list);
 		list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) {
@@ -6808,7 +6791,6 @@ static int io_sq_thread(void *data)
 
 			mutex_unlock(&sqd->lock);
 			schedule();
-			try_to_freeze();
 			mutex_lock(&sqd->lock);
 			list_for_each_entry(ctx, &sqd->ctx_list, sqd_list)
 				io_ring_clear_wakeup_flag(ctx);
@@ -6873,7 +6855,7 @@ static int io_run_task_work_sig(void)
 		return 1;
 	if (!signal_pending(current))
 		return 0;
-	if (test_tsk_thread_flag(current, TIF_NOTIFY_SIGNAL))
+	if (test_thread_flag(TIF_NOTIFY_SIGNAL))
 		return -ERESTARTSYS;
 	return -EINTR;
 }
@@ -8563,6 +8545,14 @@ static void io_ring_exit_work(struct work_struct *work)
 	struct io_tctx_node *node;
 	int ret;
 
+	/* prevent SQPOLL from submitting new requests */
+	if (ctx->sq_data) {
+		io_sq_thread_park(ctx->sq_data);
+		list_del_init(&ctx->sqd_list);
+		io_sqd_update_thread_idle(ctx->sq_data);
+		io_sq_thread_unpark(ctx->sq_data);
+	}
+
 	/*
 	 * If we're doing polled IO and end up having requests being
 	 * submitted async (out-of-line), then completions can come in while
@@ -8599,6 +8589,28 @@ static void io_ring_exit_work(struct work_struct *work)
 	io_ring_ctx_free(ctx);
 }
 
+/* Returns true if we found and killed one or more timeouts */
+static bool io_kill_timeouts(struct io_ring_ctx *ctx, struct task_struct *tsk,
+			     struct files_struct *files)
+{
+	struct io_kiocb *req, *tmp;
+	int canceled = 0;
+
+	spin_lock_irq(&ctx->completion_lock);
+	list_for_each_entry_safe(req, tmp, &ctx->timeout_list, timeout.list) {
+		if (io_match_task(req, tsk, files)) {
+			io_kill_timeout(req, -ECANCELED);
+			canceled++;
+		}
+	}
+	io_commit_cqring(ctx);
+	spin_unlock_irq(&ctx->completion_lock);
+
+	if (canceled != 0)
+		io_cqring_ev_posted(ctx);
+	return canceled != 0;
+}
+
 static void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx)
 {
 	unsigned long index;
@@ -8614,14 +8626,6 @@ static void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx)
 		io_unregister_personality(ctx, index);
 	mutex_unlock(&ctx->uring_lock);
 
-	/* prevent SQPOLL from submitting new requests */
-	if (ctx->sq_data) {
-		io_sq_thread_park(ctx->sq_data);
-		list_del_init(&ctx->sqd_list);
-		io_sqd_update_thread_idle(ctx->sq_data);
-		io_sq_thread_unpark(ctx->sq_data);
-	}
-
 	io_kill_timeouts(ctx, NULL, NULL);
 	io_poll_remove_all(ctx, NULL, NULL);
 
diff --git a/include/linux/mutex.h b/include/linux/mutex.h
index 0cd631a19727..515cff77a4f4 100644
--- a/include/linux/mutex.h
+++ b/include/linux/mutex.h
@@ -185,7 +185,7 @@ extern void mutex_lock_io(struct mutex *lock);
 # define mutex_lock_interruptible_nested(lock, subclass) mutex_lock_interruptible(lock)
 # define mutex_lock_killable_nested(lock, subclass) mutex_lock_killable(lock)
 # define mutex_lock_nest_lock(lock, nest_lock) mutex_lock(lock)
-# define mutex_lock_io_nested(lock, subclass) mutex_lock(lock)
+# define mutex_lock_io_nested(lock, subclass) mutex_lock_io(lock)
 #endif
 
 /*
diff --git a/kernel/fork.c b/kernel/fork.c
index 7c5966a51876..53427bf61c93 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1951,8 +1951,14 @@ static __latent_entropy struct task_struct *copy_process(
 	p = dup_task_struct(current, node);
 	if (!p)
 		goto fork_out;
-	if (args->io_thread)
+	if (args->io_thread) {
+		/*
+		 * Mark us an IO worker, and block any signal that isn't
+		 * fatal or STOP
+		 */
 		p->flags |= PF_IO_WORKER;
+		siginitsetinv(&p->blocked, sigmask(SIGKILL)|sigmask(SIGSTOP));
+	}
 
 	cpufreq_task_times_init(p);
 
@@ -2443,14 +2449,8 @@ struct task_struct *create_io_thread(int (*fn)(void *), void *arg, int node)
 		.stack_size	= (unsigned long)arg,
 		.io_thread	= 1,
 	};
-	struct task_struct *tsk;
 
-	tsk = copy_process(NULL, 0, node, &args);
-	if (!IS_ERR(tsk)) {
-		sigfillset(&tsk->blocked);
-		sigdelsetmask(&tsk->blocked, sigmask(SIGKILL));
-	}
-	return tsk;
+	return copy_process(NULL, 0, node, &args);
 }
 
 /*
diff --git a/kernel/freezer.c b/kernel/freezer.c
index 1a2d57d1327c..dc520f01f99d 100644
--- a/kernel/freezer.c
+++ b/kernel/freezer.c
@@ -134,7 +134,7 @@ bool freeze_task(struct task_struct *p)
 		return false;
 	}
 
-	if (!(p->flags & (PF_KTHREAD | PF_IO_WORKER)))
+	if (!(p->flags & PF_KTHREAD))
 		fake_signal_wake_up(p);
 	else
 		wake_up_state(p, TASK_INTERRUPTIBLE);
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 821cf1723814..61db50f7ca86 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -375,7 +375,7 @@ static int ptrace_attach(struct task_struct *task, long request,
 	audit_ptrace(task);
 
 	retval = -EPERM;
-	if (unlikely(task->flags & (PF_KTHREAD | PF_IO_WORKER)))
+	if (unlikely(task->flags & PF_KTHREAD))
 		goto out;
 	if (same_thread_group(task, current))
 		goto out;
diff --git a/kernel/signal.c b/kernel/signal.c
index 6000f184ab76..fdbfce8fb167 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -91,7 +91,7 @@ static bool sig_task_ignored(struct task_struct *t, int sig, bool force)
 		return true;
 
 	/* Only allow kernel generated signals to this kthread */
-	if (unlikely((t->flags & (PF_KTHREAD | PF_IO_WORKER)) &&
+	if (unlikely((t->flags & PF_KTHREAD) &&
 		     (handler == SIG_KTHREAD_KERNEL) && !force))
 		return true;
 
@@ -288,8 +288,7 @@ bool task_set_jobctl_pending(struct task_struct *task, unsigned long mask)
 			JOBCTL_STOP_SIGMASK | JOBCTL_TRAPPING));
 	BUG_ON((mask & JOBCTL_TRAPPING) && !(mask & JOBCTL_PENDING_MASK));
 
-	if (unlikely(fatal_signal_pending(task) ||
-		     (task->flags & (PF_EXITING | PF_IO_WORKER))))
+	if (unlikely(fatal_signal_pending(task) || (task->flags & PF_EXITING)))
 		return false;
 
 	if (mask & JOBCTL_STOP_SIGMASK)
@@ -834,9 +833,6 @@ static int check_kill_permission(int sig, struct kernel_siginfo *info,
 
 	if (!valid_signal(sig))
 		return -EINVAL;
-	/* PF_IO_WORKER threads don't take any signals */
-	if (t->flags & PF_IO_WORKER)
-		return -ESRCH;
 
 	if (!si_fromuser(info))
 		return 0;
@@ -1100,7 +1096,7 @@ static int __send_signal(int sig, struct kernel_siginfo *info, struct task_struc
 	/*
 	 * Skip useless siginfo allocation for SIGKILL and kernel threads.
 	 */
-	if ((sig == SIGKILL) || (t->flags & (PF_KTHREAD | PF_IO_WORKER)))
+	if ((sig == SIGKILL) || (t->flags & PF_KTHREAD))
 		goto out_set;
 
 	/*
@@ -2772,6 +2768,14 @@ bool get_signal(struct ksignal *ksig)
 			do_coredump(&ksig->info);
 		}
 
+		/*
+		 * PF_IO_WORKER threads will catch and exit on fatal signals
+		 * themselves. They have cleanup that must be performed, so
+		 * we cannot call do_exit() on their behalf.
+		 */
+		if (current->flags & PF_IO_WORKER)
+			goto out;
+
 		/*
 		 * Death signals, no core dump.
 		 */
@@ -2779,7 +2783,7 @@ bool get_signal(struct ksignal *ksig)
 		/* NOTREACHED */
 	}
 	spin_unlock_irq(&sighand->siglock);
-
+out:
 	ksig->sig = signr;
 
 	if (!(ksig->ka.sa.sa_flags & SA_EXPOSE_TAGBITS))
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index 8b281f722e5b..f6afee209620 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -1154,6 +1154,7 @@ struct kvm_x86_mce {
 #define KVM_XEN_HVM_CONFIG_HYPERCALL_MSR	(1 << 0)
 #define KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL	(1 << 1)
 #define KVM_XEN_HVM_CONFIG_SHARED_INFO		(1 << 2)
+#define KVM_XEN_HVM_CONFIG_RUNSTATE		(1 << 3)
 
 struct kvm_xen_hvm_config {
 	__u32 flags;
@@ -1621,12 +1622,24 @@ struct kvm_xen_vcpu_attr {
 	union {
 		__u64 gpa;
 		__u64 pad[8];
+		struct {
+			__u64 state;
+			__u64 state_entry_time;
+			__u64 time_running;
+			__u64 time_runnable;
+			__u64 time_blocked;
+			__u64 time_offline;
+		} runstate;
 	} u;
 };
 
 /* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO */
 #define KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO	0x0
 #define KVM_XEN_VCPU_ATTR_TYPE_VCPU_TIME_INFO	0x1
+#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADDR	0x2
+#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_CURRENT	0x3
+#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_DATA	0x4
+#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADJUST	0x5
 
 /* Secure Encrypted Virtualization command */
 enum sev_cmd_id {
diff --git a/tools/perf/builtin-daemon.c b/tools/perf/builtin-daemon.c
index ace8772a4f03..7c4a9d424a64 100644
--- a/tools/perf/builtin-daemon.c
+++ b/tools/perf/builtin-daemon.c
@@ -402,35 +402,42 @@ static pid_t handle_signalfd(struct daemon *daemon)
 	int status;
 	pid_t pid;
 
+	/*
+	 * Take signal fd data as pure signal notification and check all
+	 * the sessions state. The reason is that multiple signals can get
+	 * coalesced in kernel and we can receive only single signal even
+	 * if multiple SIGCHLD were generated.
+	 */
 	err = read(daemon->signal_fd, &si, sizeof(struct signalfd_siginfo));
-	if (err != sizeof(struct signalfd_siginfo))
+	if (err != sizeof(struct signalfd_siginfo)) {
+		pr_err("failed to read signal fd\n");
 		return -1;
+	}
 
 	list_for_each_entry(session, &daemon->sessions, list) {
-
-		if (session->pid != (int) si.ssi_pid)
+		if (session->pid == -1)
 			continue;
 
-		pid = waitpid(session->pid, &status, 0);
-		if (pid == session->pid) {
-			if (WIFEXITED(status)) {
-				pr_info("session '%s' exited, status=%d\n",
-					session->name, WEXITSTATUS(status));
-			} else if (WIFSIGNALED(status)) {
-				pr_info("session '%s' killed (signal %d)\n",
-					session->name, WTERMSIG(status));
-			} else if (WIFSTOPPED(status)) {
-				pr_info("session '%s' stopped (signal %d)\n",
-					session->name, WSTOPSIG(status));
-			} else {
-				pr_info("session '%s' Unexpected status (0x%x)\n",
-					session->name, status);
-			}
+		pid = waitpid(session->pid, &status, WNOHANG);
+		if (pid <= 0)
+			continue;
+
+		if (WIFEXITED(status)) {
+			pr_info("session '%s' exited, status=%d\n",
+				session->name, WEXITSTATUS(status));
+		} else if (WIFSIGNALED(status)) {
+			pr_info("session '%s' killed (signal %d)\n",
+				session->name, WTERMSIG(status));
+		} else if (WIFSTOPPED(status)) {
+			pr_info("session '%s' stopped (signal %d)\n",
+				session->name, WSTOPSIG(status));
+		} else {
+			pr_info("session '%s' Unexpected status (0x%x)\n",
+				session->name, status);
 		}
 
 		session->state = KILL;
 		session->pid = -1;
-		return pid;
 	}
 
 	return 0;
@@ -443,7 +450,6 @@ static int daemon_session__wait(struct daemon_session *session, struct daemon *d
 		.fd	= daemon->signal_fd,
 		.events	= POLLIN,
 	};
-	pid_t wpid = 0, pid = session->pid;
 	time_t start;
 
 	start = time(NULL);
@@ -452,7 +458,7 @@ static int daemon_session__wait(struct daemon_session *session, struct daemon *d
 		int err = poll(&pollfd, 1, 1000);
 
 		if (err > 0) {
-			wpid = handle_signalfd(daemon);
+			handle_signalfd(daemon);
 		} else if (err < 0) {
 			perror("failed: poll\n");
 			return -1;
@@ -460,7 +466,7 @@ static int daemon_session__wait(struct daemon_session *session, struct daemon *d
 
 		if (start + secs < time(NULL))
 			return -1;
-	} while (wpid != pid);
+	} while (session->pid != -1);
 
 	return 0;
 }
@@ -902,7 +908,9 @@ static void daemon_session__kill(struct daemon_session *session,
 			daemon_session__signal(session, SIGKILL);
 			break;
 		default:
-			break;
+			pr_err("failed to wait for session %s\n",
+			       session->name);
+			return;
 		}
 		how++;
 
@@ -955,7 +963,8 @@ static void daemon__kill(struct daemon *daemon)
 			daemon__signal(daemon, SIGKILL);
 			break;
 		default:
-			break;
+			pr_err("failed to wait for sessions\n");
+			return;
 		}
 		how++;
 
@@ -1344,7 +1353,7 @@ static int __cmd_start(struct daemon *daemon, struct option parent_options[],
 		close(sock_fd);
 	if (conf_fd != -1)
 		close(conf_fd);
-	if (conf_fd != -1)
+	if (signal_fd != -1)
 		close(signal_fd);
 
 	pr_info("daemon exited\n");
diff --git a/tools/perf/tests/bpf.c b/tools/perf/tests/bpf.c
index f57e075b0ed2..c72adbd67386 100644
--- a/tools/perf/tests/bpf.c
+++ b/tools/perf/tests/bpf.c
@@ -86,7 +86,7 @@ static struct {
 		.msg_load_fail	  = "check your vmlinux setting?",
 		.target_func	  = &epoll_pwait_loop,
 		.expect_result	  = (NR_ITERS + 1) / 2,
-		.pin 		  = true,
+		.pin		  = true,
 	},
 #ifdef HAVE_BPF_PROLOGUE
 	{
@@ -99,13 +99,6 @@ static struct {
 		.expect_result	  = (NR_ITERS + 1) / 4,
 	},
 #endif
-	{
-		.prog_id	  = LLVM_TESTCASE_BPF_RELOCATION,
-		.desc		  = "BPF relocation checker",
-		.name		  = "[bpf_relocation_test]",
-		.msg_compile_fail = "fix 'perf test LLVM' first",
-		.msg_load_fail	  = "libbpf error when dealing with relocation",
-	},
 };
 
 static int do_test(struct bpf_object *obj, int (*func)(void),
diff --git a/tools/perf/tests/shell/daemon.sh b/tools/perf/tests/shell/daemon.sh
index 5ad3ca8d681b..58984380b211 100755
--- a/tools/perf/tests/shell/daemon.sh
+++ b/tools/perf/tests/shell/daemon.sh
@@ -1,4 +1,4 @@
-#!/bin/sh
+#!/bin/bash
 # daemon operations
 # SPDX-License-Identifier: GPL-2.0
 
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index 953f4afacd3b..5b6ccb90b397 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -298,10 +298,6 @@ static int auxtrace_queues__queue_buffer(struct auxtrace_queues *queues,
 		queue->set = true;
 		queue->tid = buffer->tid;
 		queue->cpu = buffer->cpu;
-	} else if (buffer->cpu != queue->cpu || buffer->tid != queue->tid) {
-		pr_err("auxtrace queue conflict: cpu %d, tid %d vs cpu %d, tid %d\n",
-		       queue->cpu, queue->tid, buffer->cpu, buffer->tid);
-		return -EINVAL;
 	}
 
 	buffer->buffer_nr = queues->next_buffer_nr++;
diff --git a/tools/perf/util/bpf-event.c b/tools/perf/util/bpf-event.c
index 57d58c81a5f8..cdecda1ddd36 100644
--- a/tools/perf/util/bpf-event.c
+++ b/tools/perf/util/bpf-event.c
@@ -196,25 +196,32 @@ static int perf_event__synthesize_one_bpf_prog(struct perf_session *session,
 	}
 
 	if (info_linear->info_len < offsetof(struct bpf_prog_info, prog_tags)) {
+		free(info_linear);
 		pr_debug("%s: the kernel is too old, aborting\n", __func__);
 		return -2;
 	}
 
 	info = &info_linear->info;
+	if (!info->jited_ksyms) {
+		free(info_linear);
+		return -1;
+	}
 
 	/* number of ksyms, func_lengths, and tags should match */
 	sub_prog_cnt = info->nr_jited_ksyms;
 	if (sub_prog_cnt != info->nr_prog_tags ||
-	    sub_prog_cnt != info->nr_jited_func_lens)
+	    sub_prog_cnt != info->nr_jited_func_lens) {
+		free(info_linear);
 		return -1;
+	}
 
 	/* check BTF func info support */
 	if (info->btf_id && info->nr_func_info && info->func_info_rec_size) {
 		/* btf func info number should be same as sub_prog_cnt */
 		if (sub_prog_cnt != info->nr_func_info) {
 			pr_debug("%s: mismatch in BPF sub program count and BTF function info count, aborting\n", __func__);
-			err = -1;
-			goto out;
+			free(info_linear);
+			return -1;
 		}
 		if (btf__get_from_id(info->btf_id, &btf)) {
 			pr_debug("%s: failed to get BTF of id %u, aborting\n", __func__, info->btf_id);
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 42c84adeb2fb..c0c0fab22cb8 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -356,6 +356,9 @@ __add_event(struct list_head *list, int *idx,
 	struct perf_cpu_map *cpus = pmu ? perf_cpu_map__get(pmu->cpus) :
 			       cpu_list ? perf_cpu_map__new(cpu_list) : NULL;
 
+	if (pmu && attr->type == PERF_TYPE_RAW)
+		perf_pmu__warn_invalid_config(pmu, attr->config, name);
+
 	if (init_attr)
 		event_attr_init(attr);
 
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 44ef28302fc7..46fd0f998484 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -1812,3 +1812,36 @@ int perf_pmu__caps_parse(struct perf_pmu *pmu)
 
 	return nr_caps;
 }
+
+void perf_pmu__warn_invalid_config(struct perf_pmu *pmu, __u64 config,
+				   char *name)
+{
+	struct perf_pmu_format *format;
+	__u64 masks = 0, bits;
+	char buf[100];
+	unsigned int i;
+
+	list_for_each_entry(format, &pmu->format, list)	{
+		if (format->value != PERF_PMU_FORMAT_VALUE_CONFIG)
+			continue;
+
+		for_each_set_bit(i, format->bits, PERF_PMU_FORMAT_BITS)
+			masks |= 1ULL << i;
+	}
+
+	/*
+	 * Kernel doesn't export any valid format bits.
+	 */
+	if (masks == 0)
+		return;
+
+	bits = config & ~masks;
+	if (bits == 0)
+		return;
+
+	bitmap_scnprintf((unsigned long *)&bits, sizeof(bits) * 8, buf, sizeof(buf));
+
+	pr_warning("WARNING: event '%s' not valid (bits %s of config "
+		   "'%llx' not supported by kernel)!\n",
+		   name ?: "N/A", buf, config);
+}
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index 8164388478c6..160b0f561771 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -123,4 +123,7 @@ int perf_pmu__convert_scale(const char *scale, char **end, double *sval);
 
 int perf_pmu__caps_parse(struct perf_pmu *pmu);
 
+void perf_pmu__warn_invalid_config(struct perf_pmu *pmu, __u64 config,
+				   char *name);
+
 #endif /* __PMU_H */
diff --git a/tools/perf/util/synthetic-events.c b/tools/perf/util/synthetic-events.c
index b698046ec2db..dff178103ce5 100644
--- a/tools/perf/util/synthetic-events.c
+++ b/tools/perf/util/synthetic-events.c
@@ -424,7 +424,7 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 
 	while (!io.eof) {
 		static const char anonstr[] = "//anon";
-		size_t size;
+		size_t size, aligned_size;
 
 		/* ensure null termination since stack will be reused. */
 		event->mmap2.filename[0] = '\0';
@@ -484,11 +484,12 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 		}
 
 		size = strlen(event->mmap2.filename) + 1;
-		size = PERF_ALIGN(size, sizeof(u64));
+		aligned_size = PERF_ALIGN(size, sizeof(u64));
 		event->mmap2.len -= event->mmap.start;
 		event->mmap2.header.size = (sizeof(event->mmap2) -
-					(sizeof(event->mmap2.filename) - size));
-		memset(event->mmap2.filename + size, 0, machine->id_hdr_size);
+					(sizeof(event->mmap2.filename) - aligned_size));
+		memset(event->mmap2.filename + size, 0, machine->id_hdr_size +
+			(aligned_size - size));
 		event->mmap2.header.size += machine->id_hdr_size;
 		event->mmap2.pid = tgid;
 		event->mmap2.tid = pid;
@@ -758,7 +759,7 @@ static int __event__synthesize_thread(union perf_event *comm_event,
 	for (i = 0; i < n; i++) {
 		char *end;
 		pid_t _pid;
-		bool kernel_thread;
+		bool kernel_thread = false;
 
 		_pid = strtol(dirent[i]->d_name, &end, 10);
 		if (*end)
diff --git a/tools/perf/util/vdso.c b/tools/perf/util/vdso.c
index 3cc91ad048ea..43beb169631d 100644
--- a/tools/perf/util/vdso.c
+++ b/tools/perf/util/vdso.c
@@ -133,6 +133,8 @@ static struct dso *__machine__addnew_vdso(struct machine *machine, const char *s
 	if (dso != NULL) {
 		__dsos__add(&machine->dsos, dso);
 		dso__set_long_name(dso, long_name, false);
+		/* Put dso here because __dsos_add already got it */
+		dso__put(dso);
 	}
 
 	return dso;