Merge 4.19.91 into android-4.19

Changes in 4.19.91
	inet: protect against too small mtu values.
	mqprio: Fix out-of-bounds access in mqprio_dump
	net: bridge: deny dev_set_mac_address() when unregistering
	net: dsa: fix flow dissection on Tx path
	net: ethernet: ti: cpsw: fix extra rx interrupt
	net: sched: fix dump qlen for sch_mq/sch_mqprio with NOLOCK subqueues
	net: thunderx: start phy before starting autonegotiation
	openvswitch: support asymmetric conntrack
	tcp: md5: fix potential overestimation of TCP option space
	tipc: fix ordering of tipc module init and exit routine
	net/mlx5e: Query global pause state before setting prio2buffer
	tcp: fix rejected syncookies due to stale timestamps
	tcp: tighten acceptance of ACKs not matching a child socket
	tcp: Protect accesses to .ts_recent_stamp with {READ,WRITE}_ONCE()
	Revert "arm64: preempt: Fix big-endian when checking preempt count in assembly"
	mmc: block: Make card_busy_detect() a bit more generic
	mmc: block: Add CMD13 polling for MMC IOCTLS with R1B response
	PCI/PM: Always return devices to D0 when thawing
	PCI: pciehp: Avoid returning prematurely from sysfs requests
	PCI: Fix Intel ACS quirk UPDCR register address
	PCI/MSI: Fix incorrect MSI-X masking on resume
	PCI: Apply Cavium ACS quirk to ThunderX2 and ThunderX3
	xtensa: fix TLB sanity checker
	rpmsg: glink: Set tail pointer to 0 at end of FIFO
	rpmsg: glink: Fix reuse intents memory leak issue
	rpmsg: glink: Fix use after free in open_ack TIMEOUT case
	rpmsg: glink: Put an extra reference during cleanup
	rpmsg: glink: Fix rpmsg_register_device err handling
	rpmsg: glink: Don't send pending rx_done during remove
	rpmsg: glink: Free pending deferred work on remove
	cifs: smbd: Return -EAGAIN when transport is reconnecting
	cifs: smbd: Add messages on RDMA session destroy and reconnection
	cifs: smbd: Return -EINVAL when the number of iovs exceeds SMBDIRECT_MAX_SGE
	cifs: Don't display RDMA transport on reconnect
	CIFS: Respect O_SYNC and O_DIRECT flags during reconnect
	CIFS: Close open handle after interrupted close
	ARM: dts: s3c64xx: Fix init order of clock providers
	ARM: tegra: Fix FLOW_CTLR_HALT register clobbering by tegra_resume()
	vfio/pci: call irq_bypass_unregister_producer() before freeing irq
	dma-buf: Fix memory leak in sync_file_merge()
	drm: meson: venc: cvbs: fix CVBS mode matching
	dm mpath: remove harmful bio-based optimization
	dm btree: increase rebalance threshold in __rebalance2()
	scsi: iscsi: Fix a potential deadlock in the timeout handler
	scsi: qla2xxx: Change discovery state before PLOGI
	drm/radeon: fix r1xx/r2xx register checker for POT textures
	xhci: fix USB3 device initiated resume race with roothub autosuspend
	Linux 4.19.91

Signed-off-by: Greg Kroah-Hartman <gregkh@google.com>
Change-Id: I974d1578d54f93e1c442e09685ddc2fdf373c441

Makefile

@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 VERSION = 4
 PATCHLEVEL = 19
-SUBLEVEL = 90
+SUBLEVEL = 91
 EXTRAVERSION =
 NAME = "People's Front"
 

arch/arm/boot/dts/s3c6410-mini6410.dts

@@ -165,6 +165,10 @@
 	};
 };
 
+&clocks {
+	clocks = <&fin_pll>;
+};
+
 &sdhci0 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&sd0_clk>, <&sd0_cmd>, <&sd0_cd>, <&sd0_bus4>;

arch/arm/boot/dts/s3c6410-smdk6410.dts

@@ -69,6 +69,10 @@
 	};
 };
 
+&clocks {
+	clocks = <&fin_pll>;
+};
+
 &sdhci0 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&sd0_clk>, <&sd0_cmd>, <&sd0_cd>, <&sd0_bus4>;

arch/arm/mach-tegra/reset-handler.S

@@ -56,16 +56,16 @@ ENTRY(tegra_resume)
 	cmp	r6, #TEGRA20
 	beq	1f				@ Yes
 	/* Clear the flow controller flags for this CPU. */
-	cpu_to_csr_reg r1, r0
+	cpu_to_csr_reg r3, r0
 	mov32	r2, TEGRA_FLOW_CTRL_BASE
-	ldr	r1, [r2, r1]
+	ldr	r1, [r2, r3]
 	/* Clear event & intr flag */
 	orr	r1, r1, \
 		#FLOW_CTRL_CSR_INTR_FLAG | FLOW_CTRL_CSR_EVENT_FLAG
 	movw	r0, #0x3FFD	@ enable, cluster_switch, immed, bitmaps
 				@ & ext flags for CPU power mgnt
 	bic	r1, r1, r0
-	str	r1, [r2]
+	str	r1, [r2, r3]
 1:
 
 	mov32	r9, 0xc09

arch/arm64/include/asm/assembler.h

@@ -692,9 +692,11 @@ USER(\label, ic	ivau, \tmp2)			// invalidate I line PoU
 	.macro		if_will_cond_yield_neon
 #ifdef CONFIG_PREEMPT
 	get_thread_info	x0
-	ldr		x0, [x0, #TSK_TI_PREEMPT]
+	ldr		w1, [x0, #TSK_TI_PREEMPT]
-	sub		x0, x0, #PREEMPT_DISABLE_OFFSET
+	ldr		x0, [x0, #TSK_TI_FLAGS]
-	cbz		x0, .Lyield_\@
+	cmp		w1, #PREEMPT_DISABLE_OFFSET
+	csel		x0, x0, xzr, eq
+	tbnz		x0, #TIF_NEED_RESCHED, .Lyield_\@	// needs rescheduling?
 	/* fall through to endif_yield_neon */
 	.subsection	1
 .Lyield_\@ :

arch/arm64/kernel/entry.S

@@ -644,8 +644,10 @@ el1_irq:
 	irq_handler
 
 #ifdef CONFIG_PREEMPT
-	ldr	x24, [tsk, #TSK_TI_PREEMPT]	// get preempt count
+	ldr	w24, [tsk, #TSK_TI_PREEMPT]	// get preempt count
-	cbnz	x24, 1f				// preempt count != 0
+	cbnz	w24, 1f				// preempt count != 0
+	ldr	x0, [tsk, #TSK_TI_FLAGS]	// get flags
+	tbz	x0, #TIF_NEED_RESCHED, 1f	// needs rescheduling?
 	bl	el1_preempt
 1:
 #endif

arch/xtensa/mm/tlb.c

@@ -216,6 +216,8 @@ static int check_tlb_entry(unsigned w, unsigned e, bool dtlb)
 	unsigned tlbidx = w | (e << PAGE_SHIFT);
 	unsigned r0 = dtlb ?
 		read_dtlb_virtual(tlbidx) : read_itlb_virtual(tlbidx);
+	unsigned r1 = dtlb ?
+		read_dtlb_translation(tlbidx) : read_itlb_translation(tlbidx);
 	unsigned vpn = (r0 & PAGE_MASK) | (e << PAGE_SHIFT);
 	unsigned pte = get_pte_for_vaddr(vpn);
 	unsigned mm_asid = (get_rasid_register() >> 8) & ASID_MASK;
@@ -231,8 +233,6 @@ static int check_tlb_entry(unsigned w, unsigned e, bool dtlb)
 	}
 
 	if (tlb_asid == mm_asid) {
-		unsigned r1 = dtlb ? read_dtlb_translation(tlbidx) :
-			read_itlb_translation(tlbidx);
 		if ((pte ^ r1) & PAGE_MASK) {
 			pr_err("%cTLB: way: %u, entry: %u, mapping: %08x->%08x, PTE: %08x\n",
 					dtlb ? 'D' : 'I', w, e, r0, r1, pte);

drivers/dma-buf/sync_file.c

@@ -230,7 +230,7 @@ static struct sync_file *sync_file_merge(const char *name, struct sync_file *a,
 	a_fences = get_fences(a, &a_num_fences);
 	b_fences = get_fences(b, &b_num_fences);
 	if (a_num_fences > INT_MAX - b_num_fences)
-		return NULL;
+		goto err;
 
 	num_fences = a_num_fences + b_num_fences;
 

drivers/gpu/drm/meson/meson_venc_cvbs.c

@@ -75,6 +75,25 @@ struct meson_cvbs_mode meson_cvbs_modes[MESON_CVBS_MODES_COUNT] = {
 	},
 };
 
+static const struct meson_cvbs_mode *
+meson_cvbs_get_mode(const struct drm_display_mode *req_mode)
+{
+	int i;
+
+	for (i = 0; i < MESON_CVBS_MODES_COUNT; ++i) {
+		struct meson_cvbs_mode *meson_mode = &meson_cvbs_modes[i];
+
+		if (drm_mode_match(req_mode, &meson_mode->mode,
+				   DRM_MODE_MATCH_TIMINGS |
+				   DRM_MODE_MATCH_CLOCK |
+				   DRM_MODE_MATCH_FLAGS |
+				   DRM_MODE_MATCH_3D_FLAGS))
+			return meson_mode;
+	}
+
+	return NULL;
+}
+
 /* Connector */
 
 static void meson_cvbs_connector_destroy(struct drm_connector *connector)
@@ -147,14 +166,8 @@ static int meson_venc_cvbs_encoder_atomic_check(struct drm_encoder *encoder,
 					struct drm_crtc_state *crtc_state,
 					struct drm_connector_state *conn_state)
 {
-	int i;
+	if (meson_cvbs_get_mode(&crtc_state->mode))
-
+		return 0;
-	for (i = 0; i < MESON_CVBS_MODES_COUNT; ++i) {
-		struct meson_cvbs_mode *meson_mode = &meson_cvbs_modes[i];
-
-		if (drm_mode_equal(&crtc_state->mode, &meson_mode->mode))
-			return 0;
-	}
 
 	return -EINVAL;
 }
@@ -192,24 +205,17 @@ static void meson_venc_cvbs_encoder_mode_set(struct drm_encoder *encoder,
 				   struct drm_display_mode *mode,
 				   struct drm_display_mode *adjusted_mode)
 {
+	const struct meson_cvbs_mode *meson_mode = meson_cvbs_get_mode(mode);
 	struct meson_venc_cvbs *meson_venc_cvbs =
 					encoder_to_meson_venc_cvbs(encoder);
 	struct meson_drm *priv = meson_venc_cvbs->priv;
-	int i;
 
-	for (i = 0; i < MESON_CVBS_MODES_COUNT; ++i) {
+	if (meson_mode) {
-		struct meson_cvbs_mode *meson_mode = &meson_cvbs_modes[i];
+		meson_venci_cvbs_mode_set(priv, meson_mode->enci);
 
-		if (drm_mode_equal(mode, &meson_mode->mode)) {
+		/* Setup 27MHz vclk2 for ENCI and VDAC */
-			meson_venci_cvbs_mode_set(priv,
+		meson_vclk_setup(priv, MESON_VCLK_TARGET_CVBS, MESON_VCLK_CVBS,
-						  meson_mode->enci);
+				 MESON_VCLK_CVBS, MESON_VCLK_CVBS, true);
-
-			/* Setup 27MHz vclk2 for ENCI and VDAC */
-			meson_vclk_setup(priv, MESON_VCLK_TARGET_CVBS,
-					 MESON_VCLK_CVBS, MESON_VCLK_CVBS,
-					 MESON_VCLK_CVBS, true);
-			break;
-		}
 	}
 }
 

drivers/gpu/drm/radeon/r100.c

@@ -1820,8 +1820,8 @@ static int r100_packet0_check(struct radeon_cs_parser *p,
 			track->textures[i].use_pitch = 1;
 		} else {
 			track->textures[i].use_pitch = 0;
-			track->textures[i].width = 1 << ((idx_value >> RADEON_TXFORMAT_WIDTH_SHIFT) & RADEON_TXFORMAT_WIDTH_MASK);
+			track->textures[i].width = 1 << ((idx_value & RADEON_TXFORMAT_WIDTH_MASK) >> RADEON_TXFORMAT_WIDTH_SHIFT);
-			track->textures[i].height = 1 << ((idx_value >> RADEON_TXFORMAT_HEIGHT_SHIFT) & RADEON_TXFORMAT_HEIGHT_MASK);
+			track->textures[i].height = 1 << ((idx_value & RADEON_TXFORMAT_HEIGHT_MASK) >> RADEON_TXFORMAT_HEIGHT_SHIFT);
 		}
 		if (idx_value & RADEON_TXFORMAT_CUBIC_MAP_ENABLE)
 			track->textures[i].tex_coord_type = 2;

drivers/gpu/drm/radeon/r200.c

@@ -476,8 +476,8 @@ int r200_packet0_check(struct radeon_cs_parser *p,
 			track->textures[i].use_pitch = 1;
 		} else {
 			track->textures[i].use_pitch = 0;
-			track->textures[i].width = 1 << ((idx_value >> RADEON_TXFORMAT_WIDTH_SHIFT) & RADEON_TXFORMAT_WIDTH_MASK);
+			track->textures[i].width = 1 << ((idx_value & RADEON_TXFORMAT_WIDTH_MASK) >> RADEON_TXFORMAT_WIDTH_SHIFT);
-			track->textures[i].height = 1 << ((idx_value >> RADEON_TXFORMAT_HEIGHT_SHIFT) & RADEON_TXFORMAT_HEIGHT_MASK);
+			track->textures[i].height = 1 << ((idx_value & RADEON_TXFORMAT_HEIGHT_MASK) >> RADEON_TXFORMAT_HEIGHT_SHIFT);
 		}
 		if (idx_value & R200_TXFORMAT_LOOKUP_DISABLE)
 			track->textures[i].lookup_disable = true;

drivers/md/dm-mpath.c

@@ -609,45 +609,10 @@ static struct pgpath *__map_bio(struct multipath *m, struct bio *bio)
 	return pgpath;
 }
 
-static struct pgpath *__map_bio_fast(struct multipath *m, struct bio *bio)
-{
-	struct pgpath *pgpath;
-	unsigned long flags;
-
-	/* Do we need to select a new pgpath? */
-	/*
-	 * FIXME: currently only switching path if no path (due to failure, etc)
-	 * - which negates the point of using a path selector
-	 */
-	pgpath = READ_ONCE(m->current_pgpath);
-	if (!pgpath)
-		pgpath = choose_pgpath(m, bio->bi_iter.bi_size);
-
-	if (!pgpath) {
-		if (test_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags)) {
-			/* Queue for the daemon to resubmit */
-			spin_lock_irqsave(&m->lock, flags);
-			bio_list_add(&m->queued_bios, bio);
-			spin_unlock_irqrestore(&m->lock, flags);
-			queue_work(kmultipathd, &m->process_queued_bios);
-
-			return ERR_PTR(-EAGAIN);
-		}
-		return NULL;
-	}
-
-	return pgpath;
-}
-
 static int __multipath_map_bio(struct multipath *m, struct bio *bio,
 			       struct dm_mpath_io *mpio)
 {
-	struct pgpath *pgpath;
+	struct pgpath *pgpath = __map_bio(m, bio);
-
-	if (!m->hw_handler_name)
-		pgpath = __map_bio_fast(m, bio);
-	else
-		pgpath = __map_bio(m, bio);
 
 	if (IS_ERR(pgpath))
 		return DM_MAPIO_SUBMITTED;

drivers/md/persistent-data/dm-btree-remove.c

@@ -203,7 +203,13 @@ static void __rebalance2(struct dm_btree_info *info, struct btree_node *parent,
 	struct btree_node *right = r->n;
 	uint32_t nr_left = le32_to_cpu(left->header.nr_entries);
 	uint32_t nr_right = le32_to_cpu(right->header.nr_entries);
-	unsigned threshold = 2 * merge_threshold(left) + 1;
+	/*
+	 * Ensure the number of entries in each child will be greater
+	 * than or equal to (max_entries / 3 + 1), so no matter which
+	 * child is used for removal, the number will still be not
+	 * less than (max_entries / 3).
+	 */
+	unsigned int threshold = 2 * (merge_threshold(left) + 1);
 
 	if (nr_left + nr_right < threshold) {
 		/*

drivers/mmc/core/block.c

@@ -409,38 +409,6 @@ static int mmc_blk_ioctl_copy_to_user(struct mmc_ioc_cmd __user *ic_ptr,
 	return 0;
 }
 
-static int ioctl_rpmb_card_status_poll(struct mmc_card *card, u32 *status,
-				       u32 retries_max)
-{
-	int err;
-	u32 retry_count = 0;
-
-	if (!status || !retries_max)
-		return -EINVAL;
-
-	do {
-		err = __mmc_send_status(card, status, 5);
-		if (err)
-			break;
-
-		if (!R1_STATUS(*status) &&
-				(R1_CURRENT_STATE(*status) != R1_STATE_PRG))
-			break; /* RPMB programming operation complete */
-
-		/*
-		 * Rechedule to give the MMC device a chance to continue
-		 * processing the previous command without being polled too
-		 * frequently.
-		 */
-		usleep_range(1000, 5000);
-	} while (++retry_count < retries_max);
-
-	if (retry_count == retries_max)
-		err = -EPERM;
-
-	return err;
-}
-
 static int ioctl_do_sanitize(struct mmc_card *card)
 {
 	int err;
@@ -469,6 +437,58 @@ static int ioctl_do_sanitize(struct mmc_card *card)
 	return err;
 }
 
+static inline bool mmc_blk_in_tran_state(u32 status)
+{
+	/*
+	 * Some cards mishandle the status bits, so make sure to check both the
+	 * busy indication and the card state.
+	 */
+	return status & R1_READY_FOR_DATA &&
+	       (R1_CURRENT_STATE(status) == R1_STATE_TRAN);
+}
+
+static int card_busy_detect(struct mmc_card *card, unsigned int timeout_ms,
+			    u32 *resp_errs)
+{
+	unsigned long timeout = jiffies + msecs_to_jiffies(timeout_ms);
+	int err = 0;
+	u32 status;
+
+	do {
+		bool done = time_after(jiffies, timeout);
+
+		err = __mmc_send_status(card, &status, 5);
+		if (err) {
+			dev_err(mmc_dev(card->host),
+				"error %d requesting status\n", err);
+			return err;
+		}
+
+		/* Accumulate any response error bits seen */
+		if (resp_errs)
+			*resp_errs |= status;
+
+		/*
+		 * Timeout if the device never becomes ready for data and never
+		 * leaves the program state.
+		 */
+		if (done) {
+			dev_err(mmc_dev(card->host),
+				"Card stuck in wrong state! %s status: %#x\n",
+				 __func__, status);
+			return -ETIMEDOUT;
+		}
+
+		/*
+		 * Some cards mishandle the status bits,
+		 * so make sure to check both the busy
+		 * indication and the card state.
+		 */
+	} while (!mmc_blk_in_tran_state(status));
+
+	return err;
+}
+
 static int __mmc_blk_ioctl_cmd(struct mmc_card *card, struct mmc_blk_data *md,
 			       struct mmc_blk_ioc_data *idata)
 {
@@ -478,7 +498,6 @@ static int __mmc_blk_ioctl_cmd(struct mmc_card *card, struct mmc_blk_data *md,
 	struct scatterlist sg;
 	int err;
 	unsigned int target_part;
-	u32 status = 0;
 
 	if (!card || !md || !idata)
 		return -EINVAL;
@@ -612,16 +631,12 @@ static int __mmc_blk_ioctl_cmd(struct mmc_card *card, struct mmc_blk_data *md,
 
 	memcpy(&(idata->ic.response), cmd.resp, sizeof(cmd.resp));
 
-	if (idata->rpmb) {
+	if (idata->rpmb || (cmd.flags & MMC_RSP_R1B)) {
 		/*
-		 * Ensure RPMB command has completed by polling CMD13
+		 * Ensure RPMB/R1B command has completed by polling CMD13
 		 * "Send Status".
 		 */
-		err = ioctl_rpmb_card_status_poll(card, &status, 5);
+		err = card_busy_detect(card, MMC_BLK_TIMEOUT_MS, NULL);
-		if (err)
-			dev_err(mmc_dev(card->host),
-					"%s: Card Status=0x%08X, error %d\n",
-					__func__, status, err);
 	}
 
 	return err;
@@ -971,58 +986,6 @@ static unsigned int mmc_blk_data_timeout_ms(struct mmc_host *host,
 	return ms;
 }
 
-static inline bool mmc_blk_in_tran_state(u32 status)
-{
-	/*
-	 * Some cards mishandle the status bits, so make sure to check both the
-	 * busy indication and the card state.
-	 */
-	return status & R1_READY_FOR_DATA &&
-	       (R1_CURRENT_STATE(status) == R1_STATE_TRAN);
-}
-
-static int card_busy_detect(struct mmc_card *card, unsigned int timeout_ms,
-			    struct request *req, u32 *resp_errs)
-{
-	unsigned long timeout = jiffies + msecs_to_jiffies(timeout_ms);
-	int err = 0;
-	u32 status;
-
-	do {
-		bool done = time_after(jiffies, timeout);
-
-		err = __mmc_send_status(card, &status, 5);
-		if (err) {
-			pr_err("%s: error %d requesting status\n",
-			       req->rq_disk->disk_name, err);
-			return err;
-		}
-
-		/* Accumulate any response error bits seen */
-		if (resp_errs)
-			*resp_errs |= status;
-
-		/*
-		 * Timeout if the device never becomes ready for data and never
-		 * leaves the program state.
-		 */
-		if (done) {
-			pr_err("%s: Card stuck in wrong state! %s %s status: %#x\n",
-				mmc_hostname(card->host),
-				req->rq_disk->disk_name, __func__, status);
-			return -ETIMEDOUT;
-		}
-
-		/*
-		 * Some cards mishandle the status bits,
-		 * so make sure to check both the busy
-		 * indication and the card state.
-		 */
-	} while (!mmc_blk_in_tran_state(status));
-
-	return err;
-}
-
 static int mmc_blk_reset(struct mmc_blk_data *md, struct mmc_host *host,
 			 int type)
 {
@@ -1678,7 +1641,7 @@ static int mmc_blk_fix_state(struct mmc_card *card, struct request *req)
 
 	mmc_blk_send_stop(card, timeout);
 
-	err = card_busy_detect(card, timeout, req, NULL);
+	err = card_busy_detect(card, timeout, NULL);
 
 	mmc_retune_release(card->host);
 
@@ -1902,7 +1865,7 @@ static int mmc_blk_card_busy(struct mmc_card *card, struct request *req)
 	if (mmc_host_is_spi(card->host) || rq_data_dir(req) == READ)
 		return 0;
 
-	err = card_busy_detect(card, MMC_BLK_TIMEOUT_MS, req, &status);
+	err = card_busy_detect(card, MMC_BLK_TIMEOUT_MS, &status);
 
 	/*
 	 * Do not assume data transferred correctly if there are any error bits

drivers/net/ethernet/cavium/thunder/thunder_bgx.c

@@ -1118,7 +1118,7 @@ static int bgx_lmac_enable(struct bgx *bgx, u8 lmacid)
 				       phy_interface_mode(lmac->lmac_type)))
 			return -ENODEV;
 
-		phy_start_aneg(lmac->phydev);
+		phy_start(lmac->phydev);
 		return 0;
 	}
 

drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c

@@ -155,8 +155,11 @@ static int update_xoff_threshold(struct mlx5e_port_buffer *port_buffer,
 		}
 
 		if (port_buffer->buffer[i].size <
-		    (xoff + max_mtu + (1 << MLX5E_BUFFER_CELL_SHIFT)))
+		    (xoff + max_mtu + (1 << MLX5E_BUFFER_CELL_SHIFT))) {
+			pr_err("buffer_size[%d]=%d is not enough for lossless buffer\n",
+			       i, port_buffer->buffer[i].size);
 			return -ENOMEM;
+		}
 
 		port_buffer->buffer[i].xoff = port_buffer->buffer[i].size - xoff;
 		port_buffer->buffer[i].xon  =
@@ -232,6 +235,26 @@ static int update_buffer_lossy(unsigned int max_mtu,
 	return 0;
 }
 
+static int fill_pfc_en(struct mlx5_core_dev *mdev, u8 *pfc_en)
+{
+	u32 g_rx_pause, g_tx_pause;
+	int err;
+
+	err = mlx5_query_port_pause(mdev, &g_rx_pause, &g_tx_pause);
+	if (err)
+		return err;
+
+	/* If global pause enabled, set all active buffers to lossless.
+	 * Otherwise, check PFC setting.
+	 */
+	if (g_rx_pause || g_tx_pause)
+		*pfc_en = 0xff;
+	else
+		err = mlx5_query_port_pfc(mdev, pfc_en, NULL);
+
+	return err;
+}
+
 #define MINIMUM_MAX_MTU 9216
 int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv,
 				    u32 change, unsigned int mtu,
@@ -277,7 +300,7 @@ int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv,
 
 	if (change & MLX5E_PORT_BUFFER_PRIO2BUFFER) {
 		update_prio2buffer = true;
-		err = mlx5_query_port_pfc(priv->mdev, &curr_pfc_en, NULL);
+		err = fill_pfc_en(priv->mdev, &curr_pfc_en);
 		if (err)
 			return err;
 

drivers/net/ethernet/ti/cpsw.c

@@ -954,8 +954,8 @@ static irqreturn_t cpsw_rx_interrupt(int irq, void *dev_id)
 {
 	struct cpsw_common *cpsw = dev_id;
 
-	cpdma_ctlr_eoi(cpsw->dma, CPDMA_EOI_RX);
 	writel(0, &cpsw->wr_regs->rx_en);
+	cpdma_ctlr_eoi(cpsw->dma, CPDMA_EOI_RX);
 
 	if (cpsw->quirk_irq) {
 		disable_irq_nosync(cpsw->irqs_table[0]);

drivers/pci/hotplug/pciehp.h

@@ -106,6 +106,7 @@ struct slot {
  *	that has not yet been cleared by the user
  * @pending_events: used by the IRQ handler to save events retrieved from the
  *	Slot Status register for later consumption by the IRQ thread
+ * @ist_running: flag to keep user request waiting while IRQ thread is running
  * @request_result: result of last user request submitted to the IRQ thread
  * @requester: wait queue to wake up on completion of user request,
  *	used for synchronous slot enable/disable request via sysfs
@@ -125,6 +126,7 @@ struct controller {
 	unsigned int notification_enabled:1;
 	unsigned int power_fault_detected;
 	atomic_t pending_events;
+	unsigned int ist_running;
 	int request_result;
 	wait_queue_head_t requester;
 };

drivers/pci/hotplug/pciehp_ctrl.c

@@ -383,7 +383,8 @@ int pciehp_sysfs_enable_slot(struct slot *p_slot)
 		ctrl->request_result = -ENODEV;
 		pciehp_request(ctrl, PCI_EXP_SLTSTA_PDC);
 		wait_event(ctrl->requester,
-			   !atomic_read(&ctrl->pending_events));
+			   !atomic_read(&ctrl->pending_events) &&
+			   !ctrl->ist_running);
 		return ctrl->request_result;
 	case POWERON_STATE:
 		ctrl_info(ctrl, "Slot(%s): Already in powering on state\n",
@@ -416,7 +417,8 @@ int pciehp_sysfs_disable_slot(struct slot *p_slot)
 		mutex_unlock(&p_slot->lock);
 		pciehp_request(ctrl, DISABLE_SLOT);
 		wait_event(ctrl->requester,
-			   !atomic_read(&ctrl->pending_events));
+			   !atomic_read(&ctrl->pending_events) &&
+			   !ctrl->ist_running);
 		return ctrl->request_result;
 	case POWEROFF_STATE:
 		ctrl_info(ctrl, "Slot(%s): Already in powering off state\n",

drivers/pci/hotplug/pciehp_hpc.c

@@ -620,6 +620,7 @@ static irqreturn_t pciehp_ist(int irq, void *dev_id)
 	irqreturn_t ret;
 	u32 events;
 
+	ctrl->ist_running = true;
 	pci_config_pm_runtime_get(pdev);
 
 	/* rerun pciehp_isr() if the port was inaccessible on interrupt */
@@ -666,6 +667,7 @@ static irqreturn_t pciehp_ist(int irq, void *dev_id)
 	up_read(&ctrl->reset_lock);
 
 	pci_config_pm_runtime_put(pdev);
+	ctrl->ist_running = false;
 	wake_up(&ctrl->requester);
 	return IRQ_HANDLED;
 }

drivers/pci/msi.c

@@ -211,7 +211,7 @@ u32 __pci_msix_desc_mask_irq(struct msi_desc *desc, u32 flag)
 		return 0;
 
 	mask_bits &= ~PCI_MSIX_ENTRY_CTRL_MASKBIT;
-	if (flag)
+	if (flag & PCI_MSIX_ENTRY_CTRL_MASKBIT)
 		mask_bits |= PCI_MSIX_ENTRY_CTRL_MASKBIT;
 	writel(mask_bits, pci_msix_desc_addr(desc) + PCI_MSIX_ENTRY_VECTOR_CTRL);
 

drivers/pci/pci-driver.c

@@ -1042,17 +1042,22 @@ static int pci_pm_thaw_noirq(struct device *dev)
 			return error;
 	}
 
-	if (pci_has_legacy_pm_support(pci_dev))
-		return pci_legacy_resume_early(dev);
-
 	/*
-	 * pci_restore_state() requires the device to be in D0 (because of MSI
+	 * Both the legacy ->resume_early() and the new pm->thaw_noirq()
-	 * restoration among other things), so force it into D0 in case the
+	 * callbacks assume the device has been returned to D0 and its
-	 * driver's "freeze" callbacks put it into a low-power state directly.
+	 * config state has been restored.
+	 *
+	 * In addition, pci_restore_state() restores MSI-X state in MMIO
+	 * space, which requires the device to be in D0, so return it to D0
+	 * in case the driver's "freeze" callbacks put it into a low-power
+	 * state.
 	 */
 	pci_set_power_state(pci_dev, PCI_D0);
 	pci_restore_state(pci_dev);
 
+	if (pci_has_legacy_pm_support(pci_dev))
+		return pci_legacy_resume_early(dev);
+
 	if (drv && drv->pm && drv->pm->thaw_noirq)
 		error = drv->pm->thaw_noirq(dev);
 

drivers/pci/quirks.c

@@ -4219,15 +4219,21 @@ static int pci_quirk_amd_sb_acs(struct pci_dev *dev, u16 acs_flags)
 
 static bool pci_quirk_cavium_acs_match(struct pci_dev *dev)
 {
+	if (!pci_is_pcie(dev) || pci_pcie_type(dev) != PCI_EXP_TYPE_ROOT_PORT)
+		return false;
+
+	switch (dev->device) {
 	/*
-	 * Effectively selects all downstream ports for whole ThunderX 1
+	 * Effectively selects all downstream ports for whole ThunderX1
-	 * family by 0xf800 mask (which represents 8 SoCs), while the lower
+	 * (which represents 8 SoCs).
-	 * bits of device ID are used to indicate which subdevice is used
-	 * within the SoC.
 	 */
-	return (pci_is_pcie(dev) &&
+	case 0xa000 ... 0xa7ff: /* ThunderX1 */
-		(pci_pcie_type(dev) == PCI_EXP_TYPE_ROOT_PORT) &&
+	case 0xaf84:  /* ThunderX2 */
-		((dev->device & 0xf800) == 0xa000));
+	case 0xb884:  /* ThunderX3 */
+		return true;
+	default:
+		return false;
+	}
 }
 
 static int pci_quirk_cavium_acs(struct pci_dev *dev, u16 acs_flags)
@@ -4576,7 +4582,7 @@ int pci_dev_specific_acs_enabled(struct pci_dev *dev, u16 acs_flags)
 #define INTEL_BSPR_REG_BPPD  (1 << 9)
 
 /* Upstream Peer Decode Configuration Register */
-#define INTEL_UPDCR_REG 0x1114
+#define INTEL_UPDCR_REG 0x1014
 /* 5:0 Peer Decode Enable bits */
 #define INTEL_UPDCR_REG_MASK 0x3f
 

drivers/rpmsg/qcom_glink_native.c

@@ -241,10 +241,31 @@ static void qcom_glink_channel_release(struct kref *ref)
 {
 	struct glink_channel *channel = container_of(ref, struct glink_channel,
 						     refcount);
+	struct glink_core_rx_intent *intent;
+	struct glink_core_rx_intent *tmp;
 	unsigned long flags;
+	int iid;
+
+	/* cancel pending rx_done work */
+	cancel_work_sync(&channel->intent_work);
 
 	spin_lock_irqsave(&channel->intent_lock, flags);
+	/* Free all non-reuse intents pending rx_done work */
+	list_for_each_entry_safe(intent, tmp, &channel->done_intents, node) {
+		if (!intent->reuse) {
+			kfree(intent->data);
+			kfree(intent);
+		}
+	}
+
+	idr_for_each_entry(&channel->liids, tmp, iid) {
+		kfree(tmp->data);
+		kfree(tmp);
+	}
 	idr_destroy(&channel->liids);
+
+	idr_for_each_entry(&channel->riids, tmp, iid)
+		kfree(tmp);
 	idr_destroy(&channel->riids);
 	spin_unlock_irqrestore(&channel->intent_lock, flags);
 
@@ -1097,13 +1118,12 @@ static int qcom_glink_create_remote(struct qcom_glink *glink,
 close_link:
 	/*
 	 * Send a close request to "undo" our open-ack. The close-ack will
-	 * release the last reference.
+	 * release qcom_glink_send_open_req() reference and the last reference
+	 * will be relesed after receiving remote_close or transport unregister
+	 * by calling qcom_glink_native_remove().
 	 */
 	qcom_glink_send_close_req(glink, channel);
 
-	/* Release qcom_glink_send_open_req() reference */
-	kref_put(&channel->refcount, qcom_glink_channel_release);
-
 	return ret;
 }
 
@@ -1418,15 +1438,13 @@ static int qcom_glink_rx_open(struct qcom_glink *glink, unsigned int rcid,
 
 		ret = rpmsg_register_device(rpdev);
 		if (ret)
-			goto free_rpdev;
+			goto rcid_remove;
 
 		channel->rpdev = rpdev;
 	}
 
 	return 0;
 
-free_rpdev:
-	kfree(rpdev);
 rcid_remove:
 	spin_lock_irqsave(&glink->idr_lock, flags);
 	idr_remove(&glink->rcids, channel->rcid);
@@ -1547,6 +1565,18 @@ static void qcom_glink_work(struct work_struct *work)
 	}
 }
 
+static void qcom_glink_cancel_rx_work(struct qcom_glink *glink)
+{
+	struct glink_defer_cmd *dcmd;
+	struct glink_defer_cmd *tmp;
+
+	/* cancel any pending deferred rx_work */
+	cancel_work_sync(&glink->rx_work);
+
+	list_for_each_entry_safe(dcmd, tmp, &glink->rx_queue, node)
+		kfree(dcmd);
+}
+
 struct qcom_glink *qcom_glink_native_probe(struct device *dev,
 					   unsigned long features,
 					   struct qcom_glink_pipe *rx,
@@ -1622,23 +1652,24 @@ void qcom_glink_native_remove(struct qcom_glink *glink)
 	struct glink_channel *channel;
 	int cid;
 	int ret;
-	unsigned long flags;
 
 	disable_irq(glink->irq);
-	cancel_work_sync(&glink->rx_work);
+	qcom_glink_cancel_rx_work(glink);
 
 	ret = device_for_each_child(glink->dev, NULL, qcom_glink_remove_device);
 	if (ret)
 		dev_warn(glink->dev, "Can't remove GLINK devices: %d\n", ret);
 
-	spin_lock_irqsave(&glink->idr_lock, flags);
 	/* Release any defunct local channels, waiting for close-ack */
 	idr_for_each_entry(&glink->lcids, channel, cid)
 		kref_put(&channel->refcount, qcom_glink_channel_release);
 
+	/* Release any defunct local channels, waiting for close-req */
+	idr_for_each_entry(&glink->rcids, channel, cid)
+		kref_put(&channel->refcount, qcom_glink_channel_release);
+
 	idr_destroy(&glink->lcids);
 	idr_destroy(&glink->rcids);
-	spin_unlock_irqrestore(&glink->idr_lock, flags);
 	mbox_free_channel(glink->mbox_chan);
 }
 EXPORT_SYMBOL_GPL(qcom_glink_native_remove);

drivers/rpmsg/qcom_glink_smem.c

@@ -105,7 +105,7 @@ static void glink_smem_rx_advance(struct qcom_glink_pipe *np,
 	tail = le32_to_cpu(*pipe->tail);
 
 	tail += count;
-	if (tail > pipe->native.length)
+	if (tail >= pipe->native.length)
 		tail -= pipe->native.length;
 
 	*pipe->tail = cpu_to_le32(tail);

drivers/scsi/libiscsi.c

@@ -1983,7 +1983,7 @@ enum blk_eh_timer_return iscsi_eh_cmd_timed_out(struct scsi_cmnd *sc)
 
 	ISCSI_DBG_EH(session, "scsi cmd %p timedout\n", sc);
 
-	spin_lock(&session->frwd_lock);
+	spin_lock_bh(&session->frwd_lock);
 	task = (struct iscsi_task *)sc->SCp.ptr;
 	if (!task) {
 		/*
@@ -2110,7 +2110,7 @@ enum blk_eh_timer_return iscsi_eh_cmd_timed_out(struct scsi_cmnd *sc)
 done:
 	if (task)
 		task->last_timeout = jiffies;
-	spin_unlock(&session->frwd_lock);
+	spin_unlock_bh(&session->frwd_lock);
 	ISCSI_DBG_EH(session, "return %s\n", rc == BLK_EH_RESET_TIMER ?
 		     "timer reset" : "shutdown or nh");
 	return rc;

drivers/scsi/qla2xxx/qla_init.c

@@ -966,6 +966,7 @@ int qla24xx_post_gnl_work(struct scsi_qla_host *vha, fc_port_t *fcport)
 
 	e->u.fcport.fcport = fcport;
 	fcport->flags |= FCF_ASYNC_ACTIVE;
+	fcport->disc_state = DSC_LOGIN_PEND;
 	return qla2x00_post_work(vha, e);
 }
 

drivers/usb/host/xhci-hub.c

@@ -868,6 +868,14 @@ static u32 xhci_get_port_status(struct usb_hcd *hcd,
 			status |= USB_PORT_STAT_C_BH_RESET << 16;
 		if ((raw_port_status & PORT_CEC))
 			status |= USB_PORT_STAT_C_CONFIG_ERROR << 16;
+
+		/* USB3 remote wake resume signaling completed */
+		if (bus_state->port_remote_wakeup & (1 << wIndex) &&
+		    (raw_port_status & PORT_PLS_MASK) != XDEV_RESUME &&
+		    (raw_port_status & PORT_PLS_MASK) != XDEV_RECOVERY) {
+			bus_state->port_remote_wakeup &= ~(1 << wIndex);
+			usb_hcd_end_port_resume(&hcd->self, wIndex);
+		}
 	}
 
 	if (hcd->speed < HCD_USB3) {

drivers/usb/host/xhci-ring.c

@@ -1609,7 +1609,6 @@ static void handle_port_status(struct xhci_hcd *xhci,
 		slot_id = xhci_find_slot_id_by_port(hcd, xhci, hcd_portnum + 1);
 		if (slot_id && xhci->devs[slot_id])
 			xhci->devs[slot_id]->flags |= VDEV_PORT_ERROR;
-		bus_state->port_remote_wakeup &= ~(1 << hcd_portnum);
 	}
 
 	if ((portsc & PORT_PLC) && (portsc & PORT_PLS_MASK) == XDEV_RESUME) {
@@ -1630,6 +1629,7 @@ static void handle_port_status(struct xhci_hcd *xhci,
 			bus_state->port_remote_wakeup |= 1 << hcd_portnum;
 			xhci_test_and_clear_bit(xhci, port, PORT_PLC);
 			xhci_set_link_state(xhci, port, XDEV_U0);
+			usb_hcd_start_port_resume(&hcd->self, hcd_portnum);
 			/* Need to wait until the next link state change
 			 * indicates the device is actually in U0.
 			 */
@@ -1669,7 +1669,6 @@ static void handle_port_status(struct xhci_hcd *xhci,
 		if (slot_id && xhci->devs[slot_id])
 			xhci_ring_device(xhci, slot_id);
 		if (bus_state->port_remote_wakeup & (1 << hcd_portnum)) {
-			bus_state->port_remote_wakeup &= ~(1 << hcd_portnum);
 			xhci_test_and_clear_bit(xhci, port, PORT_PLC);
 			usb_wakeup_notification(hcd->self.root_hub,
 					hcd_portnum + 1);

drivers/vfio/pci/vfio_pci_intrs.c

@@ -297,8 +297,8 @@ static int vfio_msi_set_vector_signal(struct vfio_pci_device *vdev,
 	irq = pci_irq_vector(pdev, vector);
 
 	if (vdev->ctx[vector].trigger) {
-		free_irq(irq, vdev->ctx[vector].trigger);
 		irq_bypass_unregister_producer(&vdev->ctx[vector].producer);
+		free_irq(irq, vdev->ctx[vector].trigger);
 		kfree(vdev->ctx[vector].name);
 		eventfd_ctx_put(vdev->ctx[vector].trigger);
 		vdev->ctx[vector].trigger = NULL;

fs/cifs/cifs_debug.c

@@ -210,6 +210,11 @@ static int cifs_debug_data_proc_show(struct seq_file *m, void *v)
 		if (!server->rdma)
 			goto skip_rdma;
 
+		if (!server->smbd_conn) {
+			seq_printf(m, "\nSMBDirect transport not available");
+			goto skip_rdma;
+		}
+
 		seq_printf(m, "\nSMBDirect (in hex) protocol version: %x "
 			"transport status: %x",
 			server->smbd_conn->protocol,

fs/cifs/file.c

@@ -726,6 +726,13 @@ cifs_reopen_file(struct cifsFileInfo *cfile, bool can_flush)
 	if (backup_cred(cifs_sb))
 		create_options |= CREATE_OPEN_BACKUP_INTENT;
 
+	/* O_SYNC also has bit for O_DSYNC so following check picks up either */
+	if (cfile->f_flags & O_SYNC)
+		create_options |= CREATE_WRITE_THROUGH;
+
+	if (cfile->f_flags & O_DIRECT)
+		create_options |= CREATE_NO_BUFFER;
+
 	if (server->ops->get_lease_key)
 		server->ops->get_lease_key(inode, &cfile->fid);
 

fs/cifs/smb2misc.c

@@ -743,36 +743,67 @@ smb2_cancelled_close_fid(struct work_struct *work)
 	kfree(cancelled);
 }
 
+/* Caller should already has an extra reference to @tcon */
+static int
+__smb2_handle_cancelled_close(struct cifs_tcon *tcon, __u64 persistent_fid,
+			      __u64 volatile_fid)
+{
+	struct close_cancelled_open *cancelled;
+
+	cancelled = kzalloc(sizeof(*cancelled), GFP_KERNEL);
+	if (!cancelled)
+		return -ENOMEM;
+
+	cancelled->fid.persistent_fid = persistent_fid;
+	cancelled->fid.volatile_fid = volatile_fid;
+	cancelled->tcon = tcon;
+	INIT_WORK(&cancelled->work, smb2_cancelled_close_fid);
+	WARN_ON(queue_work(cifsiod_wq, &cancelled->work) == false);
+
+	return 0;
+}
+
+int
+smb2_handle_cancelled_close(struct cifs_tcon *tcon, __u64 persistent_fid,
+			    __u64 volatile_fid)
+{
+	int rc;
+
+	cifs_dbg(FYI, "%s: tc_count=%d\n", __func__, tcon->tc_count);
+	spin_lock(&cifs_tcp_ses_lock);
+	tcon->tc_count++;
+	spin_unlock(&cifs_tcp_ses_lock);
+
+	rc = __smb2_handle_cancelled_close(tcon, persistent_fid, volatile_fid);
+	if (rc)
+		cifs_put_tcon(tcon);
+
+	return rc;
+}
+
 int
 smb2_handle_cancelled_mid(char *buffer, struct TCP_Server_Info *server)
 {
 	struct smb2_sync_hdr *sync_hdr = (struct smb2_sync_hdr *)buffer;
 	struct smb2_create_rsp *rsp = (struct smb2_create_rsp *)buffer;
 	struct cifs_tcon *tcon;
-	struct close_cancelled_open *cancelled;
+	int rc;
 
 	if (sync_hdr->Command != SMB2_CREATE ||
 	    sync_hdr->Status != STATUS_SUCCESS)
 		return 0;
 
-	cancelled = kzalloc(sizeof(*cancelled), GFP_KERNEL);
-	if (!cancelled)
-		return -ENOMEM;
-
 	tcon = smb2_find_smb_tcon(server, sync_hdr->SessionId,
 				  sync_hdr->TreeId);
-	if (!tcon) {
+	if (!tcon)
-		kfree(cancelled);
 		return -ENOENT;
-	}
 
-	cancelled->fid.persistent_fid = rsp->PersistentFileId;
+	rc = __smb2_handle_cancelled_close(tcon, rsp->PersistentFileId,
-	cancelled->fid.volatile_fid = rsp->VolatileFileId;
+					   rsp->VolatileFileId);
-	cancelled->tcon = tcon;
+	if (rc)
-	INIT_WORK(&cancelled->work, smb2_cancelled_close_fid);
+		cifs_put_tcon(tcon);
-	queue_work(cifsiod_wq, &cancelled->work);
 
-	return 0;
+	return rc;
 }
 
 /**

fs/cifs/smb2pdu.c

@@ -2629,7 +2629,21 @@ int
 SMB2_close(const unsigned int xid, struct cifs_tcon *tcon,
 	   u64 persistent_fid, u64 volatile_fid)
 {
-	return SMB2_close_flags(xid, tcon, persistent_fid, volatile_fid, 0);
+	int rc;
+	int tmp_rc;
+
+	rc = SMB2_close_flags(xid, tcon, persistent_fid, volatile_fid, 0);
+
+	/* retry close in a worker thread if this one is interrupted */
+	if (rc == -EINTR) {
+		tmp_rc = smb2_handle_cancelled_close(tcon, persistent_fid,
+						     volatile_fid);
+		if (tmp_rc)
+			cifs_dbg(VFS, "handle cancelled close fid 0x%llx returned error %d\n",
+				 persistent_fid, tmp_rc);
+	}
+
+	return rc;
 }
 
 int

fs/cifs/smb2proto.h

@@ -204,6 +204,9 @@ extern int SMB2_set_compression(const unsigned int xid, struct cifs_tcon *tcon,
 extern int SMB2_oplock_break(const unsigned int xid, struct cifs_tcon *tcon,
 			     const u64 persistent_fid, const u64 volatile_fid,
 			     const __u8 oplock_level);
+extern int smb2_handle_cancelled_close(struct cifs_tcon *tcon,
+				       __u64 persistent_fid,
+				       __u64 volatile_fid);
 extern int smb2_handle_cancelled_mid(char *buffer,
 					struct TCP_Server_Info *server);
 void smb2_cancelled_close_fid(struct work_struct *work);

fs/cifs/smbdirect.c

@@ -1164,7 +1164,7 @@ static int smbd_post_send_data(
 
 	if (n_vec > SMBDIRECT_MAX_SGE) {
 		cifs_dbg(VFS, "Can't fit data to SGL, n_vec=%d\n", n_vec);
-		return -ENOMEM;
+		return -EINVAL;
 	}
 
 	sg_init_table(sgl, n_vec);
@@ -1491,6 +1491,7 @@ void smbd_destroy(struct smbd_connection *info)
 		info->transport_status == SMBD_DESTROYED);
 
 	destroy_workqueue(info->workqueue);
+	log_rdma_event(INFO,  "rdma session destroyed\n");
 	kfree(info);
 }
 
@@ -1528,8 +1529,9 @@ int smbd_reconnect(struct TCP_Server_Info *server)
 	log_rdma_event(INFO, "creating rdma session\n");
 	server->smbd_conn = smbd_get_connection(
 		server, (struct sockaddr *) &server->dstaddr);
-	log_rdma_event(INFO, "created rdma session info=%p\n",
+
-		server->smbd_conn);
+	if (server->smbd_conn)
+		cifs_dbg(VFS, "RDMA transport re-established\n");
 
 	return server->smbd_conn ? 0 : -ENOENT;
 }

fs/cifs/transport.c

@@ -286,8 +286,11 @@ __smb_send_rqst(struct TCP_Server_Info *server, int num_rqst,
 	int val = 1;
 	__be32 rfc1002_marker;
 
-	if (cifs_rdma_enabled(server) && server->smbd_conn) {
+	if (cifs_rdma_enabled(server)) {
-		rc = smbd_send(server, num_rqst, rqst);
+		/* return -EAGAIN when connecting or reconnecting */
+		rc = -EAGAIN;
+		if (server->smbd_conn)
+			rc = smbd_send(server, num_rqst, rqst);
 		goto smbd_done;
 	}
 	if (ssocket == NULL)

include/linux/netdevice.h

@@ -1834,6 +1834,11 @@ struct net_device {
 	unsigned char		if_port;
 	unsigned char		dma;
 
+	/* Note : dev->mtu is often read without holding a lock.
+	 * Writers usually hold RTNL.
+	 * It is recommended to use READ_ONCE() to annotate the reads,
+	 * and to use WRITE_ONCE() to annotate the writes.
+	 */
 	unsigned int		mtu;
 	unsigned int		min_mtu;
 	unsigned int		max_mtu;

include/linux/time.h

@@ -96,4 +96,17 @@ static inline bool itimerspec64_valid(const struct itimerspec64 *its)
  */
 #define time_after32(a, b)	((s32)((u32)(b) - (u32)(a)) < 0)
 #define time_before32(b, a)	time_after32(a, b)
+
+/**
+ * time_between32 - check if a 32-bit timestamp is within a given time range
+ * @t:	the time which may be within [l,h]
+ * @l:	the lower bound of the range
+ * @h:	the higher bound of the range
+ *
+ * time_before32(t, l, h) returns true if @l <= @t <= @h. All operands are
+ * treated as 32-bit integers.
+ *
+ * Equivalent to !(time_before32(@t, @l) || time_after32(@t, @h)).
+ */
+#define time_between32(t, l, h) ((u32)(h) - (u32)(l) >= (u32)(t) - (u32)(l))
 #endif

include/net/ip.h

@@ -692,4 +692,9 @@ int ip_misc_proc_init(void);
 int rtm_getroute_parse_ip_proto(struct nlattr *attr, u8 *ip_proto, u8 family,
 				struct netlink_ext_ack *extack);
 
+static inline bool inetdev_valid_mtu(unsigned int mtu)
+{
+	return likely(mtu >= IPV4_MIN_MTU);
+}
+
 #endif	/* _IP_H */

include/net/tcp.h

@@ -485,15 +485,16 @@ static inline void tcp_synq_overflow(const struct sock *sk)
 		reuse = rcu_dereference(sk->sk_reuseport_cb);
 		if (likely(reuse)) {
 			last_overflow = READ_ONCE(reuse->synq_overflow_ts);
-			if (time_after32(now, last_overflow + HZ))
+			if (!time_between32(now, last_overflow,
+					    last_overflow + HZ))
 				WRITE_ONCE(reuse->synq_overflow_ts, now);
 			return;
 		}
 	}
 
-	last_overflow = tcp_sk(sk)->rx_opt.ts_recent_stamp;
+	last_overflow = READ_ONCE(tcp_sk(sk)->rx_opt.ts_recent_stamp);
-	if (time_after32(now, last_overflow + HZ))
+	if (!time_between32(now, last_overflow, last_overflow + HZ))
-		tcp_sk(sk)->rx_opt.ts_recent_stamp = now;
+		WRITE_ONCE(tcp_sk(sk)->rx_opt.ts_recent_stamp, now);
 }
 
 /* syncookies: no recent synqueue overflow on this listening socket? */
@@ -508,13 +509,23 @@ static inline bool tcp_synq_no_recent_overflow(const struct sock *sk)
 		reuse = rcu_dereference(sk->sk_reuseport_cb);
 		if (likely(reuse)) {
 			last_overflow = READ_ONCE(reuse->synq_overflow_ts);
-			return time_after32(now, last_overflow +
+			return !time_between32(now, last_overflow - HZ,
-					    TCP_SYNCOOKIE_VALID);
+					       last_overflow +
+					       TCP_SYNCOOKIE_VALID);
 		}
 	}
 
-	last_overflow = tcp_sk(sk)->rx_opt.ts_recent_stamp;
+	last_overflow = READ_ONCE(tcp_sk(sk)->rx_opt.ts_recent_stamp);
-	return time_after32(now, last_overflow + TCP_SYNCOOKIE_VALID);
+
+	/* If last_overflow <= jiffies <= last_overflow + TCP_SYNCOOKIE_VALID,
+	 * then we're under synflood. However, we have to use
+	 * 'last_overflow - HZ' as lower bound. That's because a concurrent
+	 * tcp_synq_overflow() could update .ts_recent_stamp after we read
+	 * jiffies but before we store .ts_recent_stamp into last_overflow,
+	 * which could lead to rejecting a valid syncookie.
+	 */
+	return !time_between32(now, last_overflow - HZ,
+			       last_overflow + TCP_SYNCOOKIE_VALID);
 }
 
 static inline u32 tcp_cookie_time(void)

net/bridge/br_device.c

@@ -246,6 +246,12 @@ static int br_set_mac_address(struct net_device *dev, void *p)
 	if (!is_valid_ether_addr(addr->sa_data))
 		return -EADDRNOTAVAIL;
 
+	/* dev_set_mac_addr() can be called by a master device on bridge's
+	 * NETDEV_UNREGISTER, but since it's being destroyed do nothing
+	 */
+	if (dev->reg_state != NETREG_REGISTERED)
+		return -EBUSY;
+
 	spin_lock_bh(&br->lock);
 	if (!ether_addr_equal(dev->dev_addr, addr->sa_data)) {
 		/* Mac address will be changed in br_stp_change_bridge_id(). */

net/core/dev.c

@@ -7595,7 +7595,8 @@ int __dev_set_mtu(struct net_device *dev, int new_mtu)
 	if (ops->ndo_change_mtu)
 		return ops->ndo_change_mtu(dev, new_mtu);
 
-	dev->mtu = new_mtu;
+	/* Pairs with all the lockless reads of dev->mtu in the stack */
+	WRITE_ONCE(dev->mtu, new_mtu);
 	return 0;
 }
 EXPORT_SYMBOL(__dev_set_mtu);

net/core/flow_dissector.c

@@ -630,9 +630,10 @@ bool __skb_flow_dissect(const struct sk_buff *skb,
 		nhoff = skb_network_offset(skb);
 		hlen = skb_headlen(skb);
 #if IS_ENABLED(CONFIG_NET_DSA)
-		if (unlikely(skb->dev && netdev_uses_dsa(skb->dev))) {
+		if (unlikely(skb->dev && netdev_uses_dsa(skb->dev) &&
+			     proto == htons(ETH_P_XDSA))) {
 			const struct dsa_device_ops *ops;
-			int offset;
+			int offset = 0;
 
 			ops = skb->dev->dsa_ptr->tag_ops;
 			if (ops->flow_dissect &&

net/ipv4/devinet.c

@@ -1441,11 +1441,6 @@ static void inetdev_changename(struct net_device *dev, struct in_device *in_dev)
 	}
 }
 
-static bool inetdev_valid_mtu(unsigned int mtu)
-{
-	return mtu >= IPV4_MIN_MTU;
-}
-
 static void inetdev_send_gratuitous_arp(struct net_device *dev,
 					struct in_device *in_dev)
 

net/ipv4/ip_output.c

@@ -1142,15 +1142,18 @@ static int ip_setup_cork(struct sock *sk, struct inet_cork *cork,
 		cork->addr = ipc->addr;
 	}
 
-	/*
-	 * We steal reference to this route, caller should not release it
-	 */
-	*rtp = NULL;
 	cork->fragsize = ip_sk_use_pmtu(sk) ?
-			 dst_mtu(&rt->dst) : rt->dst.dev->mtu;
+			 dst_mtu(&rt->dst) : READ_ONCE(rt->dst.dev->mtu);
+
+	if (!inetdev_valid_mtu(cork->fragsize))
+		return -ENETUNREACH;
 
 	cork->gso_size = ipc->gso_size;
+
 	cork->dst = &rt->dst;
+	/* We stole this route, caller should not release it. */
+	*rtp = NULL;
+
 	cork->length = 0;
 	cork->ttl = ipc->ttl;
 	cork->tos = ipc->tos;

net/ipv4/tcp_output.c

@@ -740,8 +740,9 @@ static unsigned int tcp_established_options(struct sock *sk, struct sk_buff *skb
 			min_t(unsigned int, eff_sacks,
 			      (remaining - TCPOLEN_SACK_BASE_ALIGNED) /
 			      TCPOLEN_SACK_PERBLOCK);
-		size += TCPOLEN_SACK_BASE_ALIGNED +
+		if (likely(opts->num_sack_blocks))
-			opts->num_sack_blocks * TCPOLEN_SACK_PERBLOCK;
+			size += TCPOLEN_SACK_BASE_ALIGNED +
+				opts->num_sack_blocks * TCPOLEN_SACK_PERBLOCK;
 	}
 
 	return size;

net/openvswitch/conntrack.c

@@ -897,6 +897,17 @@ static int ovs_ct_nat(struct net *net, struct sw_flow_key *key,
 	}
 	err = ovs_ct_nat_execute(skb, ct, ctinfo, &info->range, maniptype);
 
+	if (err == NF_ACCEPT &&
+	    ct->status & IPS_SRC_NAT && ct->status & IPS_DST_NAT) {
+		if (maniptype == NF_NAT_MANIP_SRC)
+			maniptype = NF_NAT_MANIP_DST;
+		else
+			maniptype = NF_NAT_MANIP_SRC;
+
+		err = ovs_ct_nat_execute(skb, ct, ctinfo, &info->range,
+					 maniptype);
+	}
+
 	/* Mark NAT done if successful and update the flow key. */
 	if (err == NF_ACCEPT)
 		ovs_nat_update_key(key, skb, maniptype);

net/sched/sch_mq.c

@@ -158,6 +158,7 @@ static int mq_dump(struct Qdisc *sch, struct sk_buff *skb)
 			__gnet_stats_copy_queue(&sch->qstats,
 						qdisc->cpu_qstats,
 						&qdisc->qstats, qlen);
+			sch->q.qlen		+= qlen;
 		} else {
 			sch->q.qlen		+= qdisc->q.qlen;
 			sch->bstats.bytes	+= qdisc->bstats.bytes;

net/sched/sch_mqprio.c

@@ -413,6 +413,7 @@ static int mqprio_dump(struct Qdisc *sch, struct sk_buff *skb)
 			__gnet_stats_copy_queue(&sch->qstats,
 						qdisc->cpu_qstats,
 						&qdisc->qstats, qlen);
+			sch->q.qlen		+= qlen;
 		} else {
 			sch->q.qlen		+= qdisc->q.qlen;
 			sch->bstats.bytes	+= qdisc->bstats.bytes;
@@ -435,7 +436,7 @@ static int mqprio_dump(struct Qdisc *sch, struct sk_buff *skb)
 		opt.offset[tc] = dev->tc_to_txq[tc].offset;
 	}
 
-	if (nla_put(skb, TCA_OPTIONS, NLA_ALIGN(sizeof(opt)), &opt))
+	if (nla_put(skb, TCA_OPTIONS, sizeof(opt), &opt))
 		goto nla_put_failure;
 
 	if ((priv->flags & TC_MQPRIO_F_MODE) &&

net/tipc/core.c

@@ -120,14 +120,6 @@ static int __init tipc_init(void)
 	sysctl_tipc_rmem[1] = RCVBUF_DEF;
 	sysctl_tipc_rmem[2] = RCVBUF_MAX;
 
-	err = tipc_netlink_start();
-	if (err)
-		goto out_netlink;
-
-	err = tipc_netlink_compat_start();
-	if (err)
-		goto out_netlink_compat;
-
 	err = tipc_register_sysctl();
 	if (err)
 		goto out_sysctl;
@@ -148,8 +140,21 @@ static int __init tipc_init(void)
 	if (err)
 		goto out_bearer;
 
+	err = tipc_netlink_start();
+	if (err)
+		goto out_netlink;
+
+	err = tipc_netlink_compat_start();
+	if (err)
+		goto out_netlink_compat;
+
 	pr_info("Started in single node mode\n");
 	return 0;
+
+out_netlink_compat:
+	tipc_netlink_stop();
+out_netlink:
+	tipc_bearer_cleanup();
 out_bearer:
 	unregister_pernet_device(&tipc_topsrv_net_ops);
 out_pernet_topsrv:
@@ -159,22 +164,18 @@ static int __init tipc_init(void)
 out_pernet:
 	tipc_unregister_sysctl();
 out_sysctl:
-	tipc_netlink_compat_stop();
-out_netlink_compat:
-	tipc_netlink_stop();
-out_netlink:
 	pr_err("Unable to start in single node mode\n");
 	return err;
 }
 
 static void __exit tipc_exit(void)
 {
+	tipc_netlink_compat_stop();
+	tipc_netlink_stop();
 	tipc_bearer_cleanup();
 	unregister_pernet_device(&tipc_topsrv_net_ops);
 	tipc_socket_stop();
 	unregister_pernet_device(&tipc_net_ops);
-	tipc_netlink_stop();
-	tipc_netlink_compat_stop();
 	tipc_unregister_sysctl();
 
 	pr_info("Deactivated\n");