Merge 5.10.191 into android12-5.10-lts

Changes in 5.10.191
	wireguard: allowedips: expand maximum node depth
	mmc: moxart: read scr register without changing byte order
	ipv6: adjust ndisc_is_useropt() to also return true for PIO
	bpf: allow precision tracking for programs with subprogs
	bpf: stop setting precise in current state
	bpf: aggressively forget precise markings during state checkpointing
	selftests/bpf: make test_align selftest more robust
	selftests/bpf: Workaround verification failure for fexit_bpf2bpf/func_replace_return_code
	selftests/bpf: Fix sk_assign on s390x
	dmaengine: pl330: Return DMA_PAUSED when transaction is paused
	riscv,mmio: Fix readX()-to-delay() ordering
	drm/nouveau/gr: enable memory loads on helper invocation on all channels
	drm/shmem-helper: Reset vma->vm_ops before calling dma_buf_mmap()
	drm/amd/display: check attr flag before set cursor degamma on DCN3+
	hwmon: (pmbus/bel-pfe) Enable PMBUS_SKIP_STATUS_CHECK for pfe1100
	radix tree test suite: fix incorrect allocation size for pthreads
	x86/pkeys: Revert a5eff72597 ("x86/pkeys: Add PKRU value to init_fpstate")
	nilfs2: fix use-after-free of nilfs_root in dirtying inodes via iput
	io_uring: correct check for O_TMPFILE
	iio: cros_ec: Fix the allocation size for cros_ec_command
	binder: fix memory leak in binder_init()
	usb-storage: alauda: Fix uninit-value in alauda_check_media()
	usb: dwc3: Properly handle processing of pending events
	usb: common: usb-conn-gpio: Prevent bailing out if initial role is none
	x86/srso: Fix build breakage with the LLVM linker
	x86/cpu/amd: Enable Zenbleed fix for AMD Custom APU 0405
	x86/mm: Fix VDSO and VVAR placement on 5-level paging machines
	x86/speculation: Add cpu_show_gds() prototype
	x86: Move gds_ucode_mitigated() declaration to header
	drm/nouveau/disp: Revert a NULL check inside nouveau_connector_get_modes
	selftests/rseq: Fix build with undefined __weak
	selftests: forwarding: Add a helper to skip test when using veth pairs
	selftests: forwarding: ethtool: Skip when using veth pairs
	selftests: forwarding: ethtool_extended_state: Skip when using veth pairs
	selftests: forwarding: Skip test when no interfaces are specified
	selftests: forwarding: Switch off timeout
	selftests: forwarding: tc_flower: Relax success criterion
	mISDN: Update parameter type of dsp_cmx_send()
	net/packet: annotate data-races around tp->status
	tunnels: fix kasan splat when generating ipv4 pmtu error
	bonding: Fix incorrect deletion of ETH_P_8021AD protocol vid from slaves
	dccp: fix data-race around dp->dccps_mss_cache
	drivers: net: prevent tun_build_skb() to exceed the packet size limit
	IB/hfi1: Fix possible panic during hotplug remove
	wifi: cfg80211: fix sband iftype data lookup for AP_VLAN
	net: phy: at803x: remove set/get wol callbacks for AR8032
	net: hns3: refactor hclge_mac_link_status_wait for interface reuse
	net: hns3: add wait until mac link down
	dmaengine: mcf-edma: Fix a potential un-allocated memory access
	net/mlx5: Allow 0 for total host VFs
	ibmvnic: Enforce stronger sanity checks on login response
	ibmvnic: Unmap DMA login rsp buffer on send login fail
	ibmvnic: Handle DMA unmapping of login buffs in release functions
	btrfs: don't stop integrity writeback too early
	btrfs: set cache_block_group_error if we find an error
	nvme-tcp: fix potential unbalanced freeze & unfreeze
	nvme-rdma: fix potential unbalanced freeze & unfreeze
	netfilter: nf_tables: report use refcount overflow
	scsi: core: Fix legacy /proc parsing buffer overflow
	scsi: storvsc: Fix handling of virtual Fibre Channel timeouts
	scsi: 53c700: Check that command slot is not NULL
	scsi: snic: Fix possible memory leak if device_add() fails
	scsi: core: Fix possible memory leak if device_add() fails
	scsi: qedi: Fix firmware halt over suspend and resume
	scsi: qedf: Fix firmware halt over suspend and resume
	alpha: remove __init annotation from exported page_is_ram()
	sch_netem: fix issues in netem_change() vs get_dist_table()
	Linux 5.10.191

Change-Id: Ice1868f0a7b328bb0e56985ac0bb5af9434fd073
Signed-off-by: Greg Kroah-Hartman <gregkh@google.com>

Makefile

@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 VERSION = 5
 PATCHLEVEL = 10
-SUBLEVEL = 190
+SUBLEVEL = 191
 EXTRAVERSION =
 NAME = Dare mighty things
 

arch/alpha/kernel/setup.c

@@ -394,8 +394,7 @@ setup_memory(void *kernel_end)
 extern void setup_memory(void *);
 #endif /* !CONFIG_DISCONTIGMEM */
 
-int __init
+int page_is_ram(unsigned long pfn)
-page_is_ram(unsigned long pfn)
 {
 	struct memclust_struct * cluster;
 	struct memdesc_struct * memdesc;

arch/riscv/include/asm/mmio.h

@@ -101,9 +101,9 @@ static inline u64 __raw_readq(const volatile void __iomem *addr)
  * Relaxed I/O memory access primitives. These follow the Device memory
  * ordering rules but do not guarantee any ordering relative to Normal memory
  * accesses.  These are defined to order the indicated access (either a read or
- * write) with all other I/O memory accesses. Since the platform specification
+ * write) with all other I/O memory accesses to the same peripheral. Since the
- * defines that all I/O regions are strongly ordered on channel 2, no explicit
+ * platform specification defines that all I/O regions are strongly ordered on
- * fences are required to enforce this ordering.
+ * channel 0, no explicit fences are required to enforce this ordering.
  */
 /* FIXME: These are now the same as asm-generic */
 #define __io_rbr()		do {} while (0)
@@ -125,14 +125,14 @@ static inline u64 __raw_readq(const volatile void __iomem *addr)
 #endif
 
 /*
- * I/O memory access primitives. Reads are ordered relative to any
+ * I/O memory access primitives.  Reads are ordered relative to any following
- * following Normal memory access. Writes are ordered relative to any prior
+ * Normal memory read and delay() loop.  Writes are ordered relative to any
- * Normal memory access.  The memory barriers here are necessary as RISC-V
+ * prior Normal memory write.  The memory barriers here are necessary as RISC-V
  * doesn't define any ordering between the memory space and the I/O space.
  */
 #define __io_br()	do {} while (0)
-#define __io_ar(v)	__asm__ __volatile__ ("fence i,r" : : : "memory")
+#define __io_ar(v)	({ __asm__ __volatile__ ("fence i,ir" : : : "memory"); })
-#define __io_bw()	__asm__ __volatile__ ("fence w,o" : : : "memory")
+#define __io_bw()	({ __asm__ __volatile__ ("fence w,o" : : : "memory"); })
 #define __io_aw()	mmiowb_set_pending()
 
 #define readb(c)	({ u8  __v; __io_br(); __v = readb_cpu(c); __io_ar(__v); __v; })

arch/x86/entry/vdso/vma.c

@@ -339,8 +339,8 @@ static unsigned long vdso_addr(unsigned long start, unsigned len)
 
 	/* Round the lowest possible end address up to a PMD boundary. */
 	end = (start + len + PMD_SIZE - 1) & PMD_MASK;
-	if (end >= TASK_SIZE_MAX)
+	if (end >= DEFAULT_MAP_WINDOW)
-		end = TASK_SIZE_MAX;
+		end = DEFAULT_MAP_WINDOW;
 	end -= len;
 
 	if (end > start) {

arch/x86/include/asm/processor.h

@@ -864,4 +864,6 @@ enum mds_mitigations {
 	MDS_MITIGATION_VMWERV,
 };
 
+extern bool gds_ucode_mitigated(void);
+
 #endif /* _ASM_X86_PROCESSOR_H */

arch/x86/kernel/cpu/amd.c

@@ -74,6 +74,7 @@ static const int amd_erratum_1054[] =
 static const int amd_zenbleed[] =
 	AMD_LEGACY_ERRATUM(AMD_MODEL_RANGE(0x17, 0x30, 0x0, 0x4f, 0xf),
 			   AMD_MODEL_RANGE(0x17, 0x60, 0x0, 0x7f, 0xf),
+			   AMD_MODEL_RANGE(0x17, 0x90, 0x0, 0x91, 0xf),
 			   AMD_MODEL_RANGE(0x17, 0xa0, 0x0, 0xaf, 0xf));
 
 static const int amd_div0[] =

arch/x86/kernel/cpu/common.c

@@ -472,8 +472,6 @@ static bool pku_disabled;
 
 static __always_inline void setup_pku(struct cpuinfo_x86 *c)
 {
-	struct pkru_state *pk;
-
 	/* check the boot processor, plus compile options for PKU: */
 	if (!cpu_feature_enabled(X86_FEATURE_PKU))
 		return;
@@ -484,9 +482,6 @@ static __always_inline void setup_pku(struct cpuinfo_x86 *c)
 		return;
 
 	cr4_set_bits(X86_CR4_PKE);
-	pk = get_xsave_addr(&init_fpstate.xsave, XFEATURE_PKRU);
-	if (pk)
-		pk->pkru = init_pkru_value;
 	/*
 	 * Seting X86_CR4_PKE will cause the X86_FEATURE_OSPKE
 	 * cpuid bit to be set.  We need to ensure that we

arch/x86/kernel/vmlinux.lds.S

@@ -524,11 +524,17 @@ INIT_PER_CPU(irq_stack_backing_store);
 
 #ifdef CONFIG_CPU_SRSO
 /*
- * GNU ld cannot do XOR so do: (A | B) - (A & B) in order to compute the XOR
+ * GNU ld cannot do XOR until 2.41.
+ * https://sourceware.org/git/?p=binutils-gdb.git;a=commit;h=f6f78318fca803c4907fb8d7f6ded8295f1947b1
+ *
+ * LLVM lld cannot do XOR until lld-17.
+ * https://github.com/llvm/llvm-project/commit/fae96104d4378166cbe5c875ef8ed808a356f3fb
+ *
+ * Instead do: (A | B) - (A & B) in order to compute the XOR
  * of the two function addresses:
  */
-. = ASSERT(((srso_untrain_ret_alias | srso_safe_ret_alias) -
+. = ASSERT(((ABSOLUTE(srso_untrain_ret_alias) | srso_safe_ret_alias) -
-		(srso_untrain_ret_alias & srso_safe_ret_alias)) == ((1 << 2) | (1 << 8) | (1 << 14) | (1 << 20)),
+		(ABSOLUTE(srso_untrain_ret_alias) & srso_safe_ret_alias)) == ((1 << 2) | (1 << 8) | (1 << 14) | (1 << 20)),
 		"SRSO function pair won't alias");
 #endif
 

arch/x86/kvm/x86.c

@@ -255,8 +255,6 @@ static struct kmem_cache *x86_fpu_cache;
 
 static struct kmem_cache *x86_emulator_cache;
 
-extern bool gds_ucode_mitigated(void);
-
 /*
  * When called, it means the previous get/set msr reached an invalid msr.
  * Return true if we want to ignore/silent this failed msr access.

arch/x86/mm/pkeys.c

@@ -10,7 +10,6 @@
 
 #include <asm/cpufeature.h>             /* boot_cpu_has, ...            */
 #include <asm/mmu_context.h>            /* vma_pkey()                   */
-#include <asm/fpu/internal.h>		/* init_fpstate			*/
 
 int __execute_only_pkey(struct mm_struct *mm)
 {
@@ -154,7 +153,6 @@ static ssize_t init_pkru_read_file(struct file *file, char __user *user_buf,
 static ssize_t init_pkru_write_file(struct file *file,
 		 const char __user *user_buf, size_t count, loff_t *ppos)
 {
-	struct pkru_state *pk;
 	char buf[32];
 	ssize_t len;
 	u32 new_init_pkru;
@@ -177,10 +175,6 @@ static ssize_t init_pkru_write_file(struct file *file,
 		return -EINVAL;
 
 	WRITE_ONCE(init_pkru_value, new_init_pkru);
-	pk = get_xsave_addr(&init_fpstate.xsave, XFEATURE_PKRU);
-	if (!pk)
-		return -EINVAL;
-	pk->pkru = new_init_pkru;
 	return count;
 }
 

drivers/android/binder.c

@@ -6679,6 +6679,7 @@ static int __init binder_init(void)
 
 err_alloc_device_names_failed:
 	debugfs_remove_recursive(binder_debugfs_dir_entry_root);
+	binder_alloc_shrinker_exit();
 
 	return ret;
 }

drivers/android/binder_alloc.c

@@ -1097,6 +1097,12 @@ int binder_alloc_shrinker_init(void)
 	return ret;
 }
 
+void binder_alloc_shrinker_exit(void)
+{
+	unregister_shrinker(&binder_shrinker);
+	list_lru_destroy(&binder_alloc_lru);
+}
+
 /**
  * check_buffer() - verify that buffer/offset is safe to access
  * @alloc: binder_alloc for this proc

drivers/android/binder_alloc.h

@@ -131,6 +131,7 @@ extern struct binder_buffer *binder_alloc_new_buf(struct binder_alloc *alloc,
 						  int pid);
 extern void binder_alloc_init(struct binder_alloc *alloc);
 extern int binder_alloc_shrinker_init(void);
+extern void binder_alloc_shrinker_exit(void);
 extern void binder_alloc_vma_close(struct binder_alloc *alloc);
 extern struct binder_buffer *
 binder_alloc_prepare_to_free(struct binder_alloc *alloc,

drivers/dma/mcf-edma.c

@@ -191,7 +191,13 @@ static int mcf_edma_probe(struct platform_device *pdev)
 		return -EINVAL;
 	}
 
+	if (!pdata->dma_channels) {
+		dev_info(&pdev->dev, "setting default channel number to 64");
+		chans = 64;
+	} else {
 		chans = pdata->dma_channels;
+	}
+
 	len = sizeof(*mcf_edma) + sizeof(*mcf_chan) * chans;
 	mcf_edma = devm_kzalloc(&pdev->dev, len, GFP_KERNEL);
 	if (!mcf_edma)
@@ -203,11 +209,6 @@ static int mcf_edma_probe(struct platform_device *pdev)
 	mcf_edma->drvdata = &mcf_data;
 	mcf_edma->big_endian = 1;
 
-	if (!mcf_edma->n_chans) {
-		dev_info(&pdev->dev, "setting default channel number to 64");
-		mcf_edma->n_chans = 64;
-	}
-
 	mutex_init(&mcf_edma->fsl_edma_mutex);
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);

drivers/dma/pl330.c

@@ -403,6 +403,12 @@ enum desc_status {
 	 * of a channel can be BUSY at any time.
 	 */
 	BUSY,
+	/*
+	 * Pause was called while descriptor was BUSY. Due to hardware
+	 * limitations, only termination is possible for descriptors
+	 * that have been paused.
+	 */
+	PAUSED,
 	/*
 	 * Sitting on the channel work_list but xfer done
 	 * by PL330 core
@@ -2043,7 +2049,7 @@ static inline void fill_queue(struct dma_pl330_chan *pch)
 	list_for_each_entry(desc, &pch->work_list, node) {
 
 		/* If already submitted */
-		if (desc->status == BUSY)
+		if (desc->status == BUSY || desc->status == PAUSED)
 			continue;
 
 		ret = pl330_submit_req(pch->thread, desc);
@@ -2328,6 +2334,7 @@ static int pl330_pause(struct dma_chan *chan)
 {
 	struct dma_pl330_chan *pch = to_pchan(chan);
 	struct pl330_dmac *pl330 = pch->dmac;
+	struct dma_pl330_desc *desc;
 	unsigned long flags;
 
 	pm_runtime_get_sync(pl330->ddma.dev);
@@ -2337,6 +2344,10 @@ static int pl330_pause(struct dma_chan *chan)
 	_stop(pch->thread);
 	spin_unlock(&pl330->lock);
 
+	list_for_each_entry(desc, &pch->work_list, node) {
+		if (desc->status == BUSY)
+			desc->status = PAUSED;
+	}
 	spin_unlock_irqrestore(&pch->lock, flags);
 	pm_runtime_mark_last_busy(pl330->ddma.dev);
 	pm_runtime_put_autosuspend(pl330->ddma.dev);
@@ -2427,7 +2438,7 @@ pl330_tx_status(struct dma_chan *chan, dma_cookie_t cookie,
 		else if (running && desc == running)
 			transferred =
 				pl330_get_current_xferred_count(pch, desc);
-		else if (desc->status == BUSY)
+		else if (desc->status == BUSY || desc->status == PAUSED)
 			/*
 			 * Busy but not running means either just enqueued,
 			 * or finished and not yet marked done
@@ -2444,6 +2455,9 @@ pl330_tx_status(struct dma_chan *chan, dma_cookie_t cookie,
 			case DONE:
 				ret = DMA_COMPLETE;
 				break;
+			case PAUSED:
+				ret = DMA_PAUSED;
+				break;
 			case PREP:
 			case BUSY:
 				ret = DMA_IN_PROGRESS;

drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp.c

@@ -354,8 +354,11 @@ void dpp3_set_cursor_attributes(
 	int cur_rom_en = 0;
 
 	if (color_format == CURSOR_MODE_COLOR_PRE_MULTIPLIED_ALPHA ||
-		color_format == CURSOR_MODE_COLOR_UN_PRE_MULTIPLIED_ALPHA)
+		color_format == CURSOR_MODE_COLOR_UN_PRE_MULTIPLIED_ALPHA) {
+		if (cursor_attributes->attribute_flags.bits.ENABLE_CURSOR_DEGAMMA) {
 			cur_rom_en = 1;
+		}
+	}
 
 	REG_UPDATE_3(CURSOR0_CONTROL,
 			CUR0_MODE, color_format,

drivers/gpu/drm/drm_gem_shmem_helper.c

@@ -614,7 +614,13 @@ int drm_gem_shmem_mmap(struct drm_gem_object *obj, struct vm_area_struct *vma)
 	int ret;
 
 	if (obj->import_attach) {
+		/* Reset both vm_ops and vm_private_data, so we don't end up with
+		 * vm_ops pointing to our implementation if the dma-buf backend
+		 * doesn't set those fields.
+		 */
 		vma->vm_private_data = NULL;
+		vma->vm_ops = NULL;
+
 		ret = dma_buf_mmap(obj->dma_buf, vma, 0);
 
 		/* Drop the reference drm_gem_mmap_obj() acquired.*/

drivers/gpu/drm/nouveau/nouveau_connector.c

@@ -947,7 +947,7 @@ nouveau_connector_get_modes(struct drm_connector *connector)
 	/* Determine display colour depth for everything except LVDS now,
 	 * DP requires this before mode_valid() is called.
 	 */
-	if (connector->connector_type != DRM_MODE_CONNECTOR_LVDS && nv_connector->native_mode)
+	if (connector->connector_type != DRM_MODE_CONNECTOR_LVDS)
 		nouveau_connector_detect_depth(connector);
 
 	/* Find the native mode if this is a digital panel, if we didn't

drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf100.h

@@ -123,6 +123,7 @@ void gk104_grctx_generate_r418800(struct gf100_gr *);
 
 extern const struct gf100_grctx_func gk110_grctx;
 void gk110_grctx_generate_r419eb0(struct gf100_gr *);
+void gk110_grctx_generate_r419f78(struct gf100_gr *);
 
 extern const struct gf100_grctx_func gk110b_grctx;
 extern const struct gf100_grctx_func gk208_grctx;

drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk104.c

@@ -916,7 +916,9 @@ static void
 gk104_grctx_generate_r419f78(struct gf100_gr *gr)
 {
 	struct nvkm_device *device = gr->base.engine.subdev.device;
-	nvkm_mask(device, 0x419f78, 0x00000001, 0x00000000);
+
+	/* bit 3 set disables loads in fp helper invocations, we need it enabled */
+	nvkm_mask(device, 0x419f78, 0x00000009, 0x00000000);
 }
 
 void

drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk110.c

@@ -820,6 +820,15 @@ gk110_grctx_generate_r419eb0(struct gf100_gr *gr)
 	nvkm_mask(device, 0x419eb0, 0x00001000, 0x00001000);
 }
 
+void
+gk110_grctx_generate_r419f78(struct gf100_gr *gr)
+{
+	struct nvkm_device *device = gr->base.engine.subdev.device;
+
+	/* bit 3 set disables loads in fp helper invocations, we need it enabled */
+	nvkm_mask(device, 0x419f78, 0x00000008, 0x00000000);
+}
+
 const struct gf100_grctx_func
 gk110_grctx = {
 	.main  = gf100_grctx_generate_main,
@@ -852,4 +861,5 @@ gk110_grctx = {
 	.gpc_tpc_nr = gk104_grctx_generate_gpc_tpc_nr,
 	.r418800 = gk104_grctx_generate_r418800,
 	.r419eb0 = gk110_grctx_generate_r419eb0,
+	.r419f78 = gk110_grctx_generate_r419f78,
 };

drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk110b.c

@@ -101,4 +101,5 @@ gk110b_grctx = {
 	.gpc_tpc_nr = gk104_grctx_generate_gpc_tpc_nr,
 	.r418800 = gk104_grctx_generate_r418800,
 	.r419eb0 = gk110_grctx_generate_r419eb0,
+	.r419f78 = gk110_grctx_generate_r419f78,
 };

drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk208.c

@@ -566,4 +566,5 @@ gk208_grctx = {
 	.dist_skip_table = gf117_grctx_generate_dist_skip_table,
 	.gpc_tpc_nr = gk104_grctx_generate_gpc_tpc_nr,
 	.r418800 = gk104_grctx_generate_r418800,
+	.r419f78 = gk110_grctx_generate_r419f78,
 };

drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgm107.c

@@ -991,4 +991,5 @@ gm107_grctx = {
 	.r406500 = gm107_grctx_generate_r406500,
 	.gpc_tpc_nr = gk104_grctx_generate_gpc_tpc_nr,
 	.r419e00 = gm107_grctx_generate_r419e00,
+	.r419f78 = gk110_grctx_generate_r419f78,
 };

drivers/hwmon/pmbus/bel-pfe.c

@@ -17,12 +17,13 @@
 enum chips {pfe1100, pfe3000};
 
 /*
- * Disable status check for pfe3000 devices, because some devices report
+ * Disable status check because some devices report communication error
- * communication error (invalid command) for VOUT_MODE command (0x20)
+ * (invalid command) for VOUT_MODE command (0x20) although the correct
- * although correct VOUT_MODE (0x16) is returned: it leads to incorrect
+ * VOUT_MODE (0x16) is returned: it leads to incorrect exponent in linear
- * exponent in linear mode.
+ * mode.
+ * This affects both pfe3000 and pfe1100.
  */
-static struct pmbus_platform_data pfe3000_plat_data = {
+static struct pmbus_platform_data pfe_plat_data = {
 	.flags = PMBUS_SKIP_STATUS_CHECK,
 };
 
@@ -94,16 +95,15 @@ static int pfe_pmbus_probe(struct i2c_client *client)
 	int model;
 
 	model = (int)i2c_match_id(pfe_device_id, client)->driver_data;
+	client->dev.platform_data = &pfe_plat_data;
 
 	/*
 	 * PFE3000-12-069RA devices may not stay in page 0 during device
 	 * probe which leads to probe failure (read status word failed).
 	 * So let's set the device to page 0 at the beginning.
 	 */
-	if (model == pfe3000) {
+	if (model == pfe3000)
-		client->dev.platform_data = &pfe3000_plat_data;
 		i2c_smbus_write_byte_data(client, PMBUS_PAGE, 0);
-	}
 
 	return pmbus_do_probe(client, &pfe_driver_info[model]);
 }

drivers/iio/common/cros_ec_sensors/cros_ec_sensors_core.c

@@ -263,7 +263,7 @@ int cros_ec_sensors_core_init(struct platform_device *pdev,
 	platform_set_drvdata(pdev, indio_dev);
 
 	state->ec = ec->ec_dev;
-	state->msg = devm_kzalloc(&pdev->dev,
+	state->msg = devm_kzalloc(&pdev->dev, sizeof(*state->msg) +
 				max((u16)sizeof(struct ec_params_motion_sense),
 				state->ec->max_response), GFP_KERNEL);
 	if (!state->msg)

drivers/infiniband/hw/hfi1/chip.c

@@ -12348,6 +12348,7 @@ static void free_cntrs(struct hfi1_devdata *dd)
 
 	if (dd->synth_stats_timer.function)
 		del_timer_sync(&dd->synth_stats_timer);
+	cancel_work_sync(&dd->update_cntr_work);
 	ppd = (struct hfi1_pportdata *)(dd + 1);
 	for (i = 0; i < dd->num_pports; i++, ppd++) {
 		kfree(ppd->cntrs);

drivers/isdn/mISDN/dsp.h

@@ -247,7 +247,7 @@ extern void dsp_cmx_hardware(struct dsp_conf *conf, struct dsp *dsp);
 extern int dsp_cmx_conf(struct dsp *dsp, u32 conf_id);
 extern void dsp_cmx_receive(struct dsp *dsp, struct sk_buff *skb);
 extern void dsp_cmx_hdlc(struct dsp *dsp, struct sk_buff *skb);
-extern void dsp_cmx_send(void *arg);
+extern void dsp_cmx_send(struct timer_list *arg);
 extern void dsp_cmx_transmit(struct dsp *dsp, struct sk_buff *skb);
 extern int dsp_cmx_del_conf_member(struct dsp *dsp);
 extern int dsp_cmx_del_conf(struct dsp_conf *conf);

drivers/isdn/mISDN/dsp_cmx.c

@@ -1625,7 +1625,7 @@ static u16	dsp_count; /* last sample count */
 static int	dsp_count_valid; /* if we have last sample count */
 
 void
-dsp_cmx_send(void *arg)
+dsp_cmx_send(struct timer_list *arg)
 {
 	struct dsp_conf *conf;
 	struct dsp_conf_member *member;

drivers/isdn/mISDN/dsp_core.c

@@ -1200,7 +1200,7 @@ static int __init dsp_init(void)
 	}
 
 	/* set sample timer */
-	timer_setup(&dsp_spl_tl, (void *)dsp_cmx_send, 0);
+	timer_setup(&dsp_spl_tl, dsp_cmx_send, 0);
 	dsp_spl_tl.expires = jiffies + dsp_tics;
 	dsp_spl_jiffies = dsp_spl_tl.expires;
 	add_timer(&dsp_spl_tl);

drivers/mmc/host/moxart-mmc.c

@@ -339,13 +339,7 @@ static void moxart_transfer_pio(struct moxart_host *host)
 				return;
 			}
 			for (len = 0; len < remain && len < host->fifo_width;) {
-				/* SCR data must be read in big endian. */
+				*sgp = ioread32(host->base + REG_DATA_WINDOW);
-				if (data->mrq->cmd->opcode == SD_APP_SEND_SCR)
-					*sgp = ioread32be(host->base +
-							  REG_DATA_WINDOW);
-				else
-					*sgp = ioread32(host->base +
-							REG_DATA_WINDOW);
 				sgp++;
 				len += 4;
 			}

drivers/net/bonding/bond_main.c

@@ -4920,7 +4920,9 @@ void bond_setup(struct net_device *bond_dev)
 
 	bond_dev->hw_features = BOND_VLAN_FEATURES |
 				NETIF_F_HW_VLAN_CTAG_RX |
-				NETIF_F_HW_VLAN_CTAG_FILTER;
+				NETIF_F_HW_VLAN_CTAG_FILTER |
+				NETIF_F_HW_VLAN_STAG_RX |
+				NETIF_F_HW_VLAN_STAG_FILTER;
 
 	bond_dev->hw_features |= NETIF_F_GSO_ENCAP_ALL | NETIF_F_GSO_UDP_L4;
 #ifdef CONFIG_XFRM_OFFLOAD

drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c

@@ -71,6 +71,8 @@ static int hclge_set_default_loopback(struct hclge_dev *hdev);
 static void hclge_sync_mac_table(struct hclge_dev *hdev);
 static void hclge_restore_hw_table(struct hclge_dev *hdev);
 static void hclge_sync_promisc_mode(struct hclge_dev *hdev);
+static int hclge_mac_link_status_wait(struct hclge_dev *hdev, int link_ret,
+				      int wait_cnt);
 
 static struct hnae3_ae_algo ae_algo;
 
@@ -6558,6 +6560,8 @@ static void hclge_enable_fd(struct hnae3_handle *handle, bool enable)
 
 static void hclge_cfg_mac_mode(struct hclge_dev *hdev, bool enable)
 {
+#define HCLGE_LINK_STATUS_WAIT_CNT  3
+
 	struct hclge_desc desc;
 	struct hclge_config_mac_mode_cmd *req =
 		(struct hclge_config_mac_mode_cmd *)desc.data;
@@ -6582,9 +6586,15 @@ static void hclge_cfg_mac_mode(struct hclge_dev *hdev, bool enable)
 	req->txrx_pad_fcs_loop_en = cpu_to_le32(loop_en);
 
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
-	if (ret)
+	if (ret) {
 		dev_err(&hdev->pdev->dev,
 			"mac enable fail, ret =%d.\n", ret);
+		return;
+	}
+
+	if (!enable)
+		hclge_mac_link_status_wait(hdev, HCLGE_LINK_STATUS_DOWN,
+					   HCLGE_LINK_STATUS_WAIT_CNT);
 }
 
 static int hclge_config_switch_param(struct hclge_dev *hdev, int vfid,
@@ -6647,10 +6657,9 @@ static void hclge_phy_link_status_wait(struct hclge_dev *hdev,
 	} while (++i < HCLGE_PHY_LINK_STATUS_NUM);
 }
 
-static int hclge_mac_link_status_wait(struct hclge_dev *hdev, int link_ret)
+static int hclge_mac_link_status_wait(struct hclge_dev *hdev, int link_ret,
+				      int wait_cnt)
 {
-#define HCLGE_MAC_LINK_STATUS_NUM  100
-
 	int link_status;
 	int i = 0;
 	int ret;
@@ -6663,13 +6672,15 @@ static int hclge_mac_link_status_wait(struct hclge_dev *hdev, int link_ret)
 			return 0;
 
 		msleep(HCLGE_LINK_STATUS_MS);
-	} while (++i < HCLGE_MAC_LINK_STATUS_NUM);
+	} while (++i < wait_cnt);
 	return -EBUSY;
 }
 
 static int hclge_mac_phy_link_status_wait(struct hclge_dev *hdev, bool en,
 					  bool is_phy)
 {
+#define HCLGE_MAC_LINK_STATUS_NUM  100
+
 	int link_ret;
 
 	link_ret = en ? HCLGE_LINK_STATUS_UP : HCLGE_LINK_STATUS_DOWN;
@@ -6677,7 +6688,8 @@ static int hclge_mac_phy_link_status_wait(struct hclge_dev *hdev, bool en,
 	if (is_phy)
 		hclge_phy_link_status_wait(hdev, link_ret);
 
-	return hclge_mac_link_status_wait(hdev, link_ret);
+	return hclge_mac_link_status_wait(hdev, link_ret,
+					  HCLGE_MAC_LINK_STATUS_NUM);
 }
 
 static int hclge_set_app_loopback(struct hclge_dev *hdev, bool en)

drivers/net/ethernet/ibm/ibmvnic.c

@@ -929,12 +929,22 @@ static int ibmvnic_login(struct net_device *netdev)
 
 static void release_login_buffer(struct ibmvnic_adapter *adapter)
 {
+	if (!adapter->login_buf)
+		return;
+
+	dma_unmap_single(&adapter->vdev->dev, adapter->login_buf_token,
+			 adapter->login_buf_sz, DMA_TO_DEVICE);
 	kfree(adapter->login_buf);
 	adapter->login_buf = NULL;
 }
 
 static void release_login_rsp_buffer(struct ibmvnic_adapter *adapter)
 {
+	if (!adapter->login_rsp_buf)
+		return;
+
+	dma_unmap_single(&adapter->vdev->dev, adapter->login_rsp_buf_token,
+			 adapter->login_rsp_buf_sz, DMA_FROM_DEVICE);
 	kfree(adapter->login_rsp_buf);
 	adapter->login_rsp_buf = NULL;
 }
@@ -3861,11 +3871,14 @@ static int send_login(struct ibmvnic_adapter *adapter)
 	if (rc) {
 		adapter->login_pending = false;
 		netdev_err(adapter->netdev, "Failed to send login, rc=%d\n", rc);
-		goto buf_rsp_map_failed;
+		goto buf_send_failed;
 	}
 
 	return 0;
 
+buf_send_failed:
+	dma_unmap_single(dev, rsp_buffer_token, rsp_buffer_size,
+			 DMA_FROM_DEVICE);
 buf_rsp_map_failed:
 	kfree(login_rsp_buffer);
 	adapter->login_rsp_buf = NULL;
@@ -4430,6 +4443,7 @@ static int handle_login_rsp(union ibmvnic_crq *login_rsp_crq,
 	int num_tx_pools;
 	int num_rx_pools;
 	u64 *size_array;
+	u32 rsp_len;
 	int i;
 
 	/* CHECK: Test/set of login_pending does not need to be atomic
@@ -4441,11 +4455,6 @@ static int handle_login_rsp(union ibmvnic_crq *login_rsp_crq,
 	}
 	adapter->login_pending = false;
 
-	dma_unmap_single(dev, adapter->login_buf_token, adapter->login_buf_sz,
-			 DMA_TO_DEVICE);
-	dma_unmap_single(dev, adapter->login_rsp_buf_token,
-			 adapter->login_rsp_buf_sz, DMA_FROM_DEVICE);
-
 	/* If the number of queues requested can't be allocated by the
 	 * server, the login response will return with code 1. We will need
 	 * to resend the login buffer with fewer queues requested.
@@ -4481,6 +4490,23 @@ static int handle_login_rsp(union ibmvnic_crq *login_rsp_crq,
 		ibmvnic_reset(adapter, VNIC_RESET_FATAL);
 		return -EIO;
 	}
+
+	rsp_len = be32_to_cpu(login_rsp->len);
+	if (be32_to_cpu(login->login_rsp_len) < rsp_len ||
+	    rsp_len <= be32_to_cpu(login_rsp->off_txsubm_subcrqs) ||
+	    rsp_len <= be32_to_cpu(login_rsp->off_rxadd_subcrqs) ||
+	    rsp_len <= be32_to_cpu(login_rsp->off_rxadd_buff_size) ||
+	    rsp_len <= be32_to_cpu(login_rsp->off_supp_tx_desc)) {
+		/* This can happen if a login request times out and there are
+		 * 2 outstanding login requests sent, the LOGIN_RSP crq
+		 * could have been for the older login request. So we are
+		 * parsing the newer response buffer which may be incomplete
+		 */
+		dev_err(dev, "FATAL: Login rsp offsets/lengths invalid\n");
+		ibmvnic_reset(adapter, VNIC_RESET_FATAL);
+		return -EIO;
+	}
+
 	size_array = (u64 *)((u8 *)(adapter->login_rsp_buf) +
 		be32_to_cpu(adapter->login_rsp_buf->off_rxadd_buff_size));
 	/* variable buffer sizes are not supported, so just read the

drivers/net/ethernet/mellanox/mlx5/core/sriov.c

@@ -211,7 +211,6 @@ static u16 mlx5_get_max_vfs(struct mlx5_core_dev *dev)
 		host_total_vfs = MLX5_GET(query_esw_functions_out, out,
 					  host_params_context.host_total_vfs);
 		kvfree(out);
-		if (host_total_vfs)
 		return host_total_vfs;
 	}
 

drivers/net/phy/at803x.c

@@ -1115,8 +1115,6 @@ static struct phy_driver at803x_driver[] = {
 	.flags			= PHY_POLL_CABLE_TEST,
 	.config_init		= at803x_config_init,
 	.link_change_notify	= at803x_link_change_notify,
-	.set_wol		= at803x_set_wol,
-	.get_wol		= at803x_get_wol,
 	.suspend		= at803x_suspend,
 	.resume			= at803x_resume,
 	/* PHY_BASIC_FEATURES */

drivers/net/tun.c

@@ -1604,7 +1604,7 @@ static bool tun_can_build_skb(struct tun_struct *tun, struct tun_file *tfile,
 	if (zerocopy)
 		return false;
 
-	if (SKB_DATA_ALIGN(len + TUN_RX_PAD) +
+	if (SKB_DATA_ALIGN(len + TUN_RX_PAD + XDP_PACKET_HEADROOM) +
 	    SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) > PAGE_SIZE)
 		return false;
 

drivers/net/wireguard/allowedips.c

@@ -6,7 +6,7 @@
 #include "allowedips.h"
 #include "peer.h"
 
-enum { MAX_ALLOWEDIPS_BITS = 128 };
+enum { MAX_ALLOWEDIPS_DEPTH = 129 };
 
 static struct kmem_cache *node_cache;
 
@@ -42,7 +42,7 @@ static void push_rcu(struct allowedips_node **stack,
 		     struct allowedips_node __rcu *p, unsigned int *len)
 {
 	if (rcu_access_pointer(p)) {
-		if (WARN_ON(IS_ENABLED(DEBUG) && *len >= MAX_ALLOWEDIPS_BITS))
+		if (WARN_ON(IS_ENABLED(DEBUG) && *len >= MAX_ALLOWEDIPS_DEPTH))
 			return;
 		stack[(*len)++] = rcu_dereference_raw(p);
 	}
@@ -55,7 +55,7 @@ static void node_free_rcu(struct rcu_head *rcu)
 
 static void root_free_rcu(struct rcu_head *rcu)
 {
-	struct allowedips_node *node, *stack[MAX_ALLOWEDIPS_BITS] = {
+	struct allowedips_node *node, *stack[MAX_ALLOWEDIPS_DEPTH] = {
 		container_of(rcu, struct allowedips_node, rcu) };
 	unsigned int len = 1;
 
@@ -68,7 +68,7 @@ static void root_free_rcu(struct rcu_head *rcu)
 
 static void root_remove_peer_lists(struct allowedips_node *root)
 {
-	struct allowedips_node *node, *stack[MAX_ALLOWEDIPS_BITS] = { root };
+	struct allowedips_node *node, *stack[MAX_ALLOWEDIPS_DEPTH] = { root };
 	unsigned int len = 1;
 
 	while (len > 0 && (node = stack[--len])) {

drivers/net/wireguard/selftest/allowedips.c

@@ -593,16 +593,20 @@ bool __init wg_allowedips_selftest(void)
 	wg_allowedips_remove_by_peer(&t, a, &mutex);
 	test_negative(4, a, 192, 168, 0, 1);
 
-	/* These will hit the WARN_ON(len >= MAX_ALLOWEDIPS_BITS) in free_node
+	/* These will hit the WARN_ON(len >= MAX_ALLOWEDIPS_DEPTH) in free_node
 	 * if something goes wrong.
 	 */
-	for (i = 0; i < MAX_ALLOWEDIPS_BITS; ++i) {
+	for (i = 0; i < 64; ++i) {
-		part = cpu_to_be64(~(1LLU << (i % 64)));
+		part = cpu_to_be64(~0LLU << i);
-		memset(&ip, 0xff, 16);
+		memset(&ip, 0xff, 8);
-		memcpy((u8 *)&ip + (i < 64) * 8, &part, 8);
+		memcpy((u8 *)&ip + 8, &part, 8);
+		wg_allowedips_insert_v6(&t, &ip, 128, a, &mutex);
+		memcpy(&ip, &part, 8);
+		memset((u8 *)&ip + 8, 0, 8);
 		wg_allowedips_insert_v6(&t, &ip, 128, a, &mutex);
 	}
-
+	memset(&ip, 0, 16);
+	wg_allowedips_insert_v6(&t, &ip, 128, a, &mutex);
 	wg_allowedips_free(&t, &mutex);
 
 	wg_allowedips_init(&t);

drivers/nvme/host/rdma.c

@@ -989,6 +989,7 @@ static int nvme_rdma_configure_io_queues(struct nvme_rdma_ctrl *ctrl, bool new)
 		goto out_cleanup_connect_q;
 
 	if (!new) {
+		nvme_start_freeze(&ctrl->ctrl);
 		nvme_start_queues(&ctrl->ctrl);
 		if (!nvme_wait_freeze_timeout(&ctrl->ctrl, NVME_IO_TIMEOUT)) {
 			/*
@@ -997,6 +998,7 @@ static int nvme_rdma_configure_io_queues(struct nvme_rdma_ctrl *ctrl, bool new)
 			 * to be safe.
 			 */
 			ret = -ENODEV;
+			nvme_unfreeze(&ctrl->ctrl);
 			goto out_wait_freeze_timed_out;
 		}
 		blk_mq_update_nr_hw_queues(ctrl->ctrl.tagset,
@@ -1042,7 +1044,6 @@ static void nvme_rdma_teardown_io_queues(struct nvme_rdma_ctrl *ctrl,
 		bool remove)
 {
 	if (ctrl->ctrl.queue_count > 1) {
-		nvme_start_freeze(&ctrl->ctrl);
 		nvme_stop_queues(&ctrl->ctrl);
 		nvme_sync_io_queues(&ctrl->ctrl);
 		nvme_rdma_stop_io_queues(ctrl);

drivers/nvme/host/tcp.c

@@ -1859,6 +1859,7 @@ static int nvme_tcp_configure_io_queues(struct nvme_ctrl *ctrl, bool new)
 		goto out_cleanup_connect_q;
 
 	if (!new) {
+		nvme_start_freeze(ctrl);
 		nvme_start_queues(ctrl);
 		if (!nvme_wait_freeze_timeout(ctrl, NVME_IO_TIMEOUT)) {
 			/*
@@ -1867,6 +1868,7 @@ static int nvme_tcp_configure_io_queues(struct nvme_ctrl *ctrl, bool new)
 			 * to be safe.
 			 */
 			ret = -ENODEV;
+			nvme_unfreeze(ctrl);
 			goto out_wait_freeze_timed_out;
 		}
 		blk_mq_update_nr_hw_queues(ctrl->tagset,
@@ -1989,7 +1991,6 @@ static void nvme_tcp_teardown_io_queues(struct nvme_ctrl *ctrl,
 	if (ctrl->queue_count <= 1)
 		return;
 	blk_mq_quiesce_queue(ctrl->admin_q);
-	nvme_start_freeze(ctrl);
 	nvme_stop_queues(ctrl);
 	nvme_sync_io_queues(ctrl);
 	nvme_tcp_stop_io_queues(ctrl);

drivers/scsi/53c700.c

@@ -1600,7 +1600,7 @@ NCR_700_intr(int irq, void *dev_id)
 				printk("scsi%d (%d:%d) PHASE MISMATCH IN SEND MESSAGE %d remain, return %p[%04x], phase %s\n", host->host_no, pun, lun, count, (void *)temp, temp - hostdata->pScript, sbcl_to_string(NCR_700_readb(host, SBCL_REG)));
 #endif
 				resume_offset = hostdata->pScript + Ent_SendMessagePhaseMismatch;
-			} else if(dsp >= to32bit(&slot->pSG[0].ins) &&
+			} else if (slot && dsp >= to32bit(&slot->pSG[0].ins) &&
 				  dsp <= to32bit(&slot->pSG[NCR_700_SG_SEGMENTS].ins)) {
 				int data_transfer = NCR_700_readl(host, DBC_REG) & 0xffffff;
 				int SGcount = (dsp - to32bit(&slot->pSG[0].ins))/sizeof(struct NCR_700_SG_List);

drivers/scsi/qedf/qedf_main.c

@@ -31,6 +31,7 @@ static void qedf_remove(struct pci_dev *pdev);
 static void qedf_shutdown(struct pci_dev *pdev);
 static void qedf_schedule_recovery_handler(void *dev);
 static void qedf_recovery_handler(struct work_struct *work);
+static int qedf_suspend(struct pci_dev *pdev, pm_message_t state);
 
 /*
  * Driver module parameters.
@@ -3272,6 +3273,7 @@ static struct pci_driver qedf_pci_driver = {
 	.probe = qedf_probe,
 	.remove = qedf_remove,
 	.shutdown = qedf_shutdown,
+	.suspend = qedf_suspend,
 };
 
 static int __qedf_probe(struct pci_dev *pdev, int mode)
@@ -3986,6 +3988,22 @@ static void qedf_shutdown(struct pci_dev *pdev)
 	__qedf_remove(pdev, QEDF_MODE_NORMAL);
 }
 
+static int qedf_suspend(struct pci_dev *pdev, pm_message_t state)
+{
+	struct qedf_ctx *qedf;
+
+	if (!pdev) {
+		QEDF_ERR(NULL, "pdev is NULL.\n");
+		return -ENODEV;
+	}
+
+	qedf = pci_get_drvdata(pdev);
+
+	QEDF_ERR(&qedf->dbg_ctx, "%s: Device does not support suspend operation\n", __func__);
+
+	return -EPERM;
+}
+
 /*
  * Recovery handler code
  */

drivers/scsi/qedi/qedi_main.c

@@ -69,6 +69,7 @@ static struct nvm_iscsi_block *qedi_get_nvram_block(struct qedi_ctx *qedi);
 static void qedi_recovery_handler(struct work_struct *work);
 static void qedi_schedule_hw_err_handler(void *dev,
 					 enum qed_hw_err_type err_type);
+static int qedi_suspend(struct pci_dev *pdev, pm_message_t state);
 
 static int qedi_iscsi_event_cb(void *context, u8 fw_event_code, void *fw_handle)
 {
@@ -2517,6 +2518,22 @@ static void qedi_shutdown(struct pci_dev *pdev)
 	__qedi_remove(pdev, QEDI_MODE_SHUTDOWN);
 }
 
+static int qedi_suspend(struct pci_dev *pdev, pm_message_t state)
+{
+	struct qedi_ctx *qedi;
+
+	if (!pdev) {
+		QEDI_ERR(NULL, "pdev is NULL.\n");
+		return -ENODEV;
+	}
+
+	qedi = pci_get_drvdata(pdev);
+
+	QEDI_ERR(&qedi->dbg_ctx, "%s: Device does not support suspend operation\n", __func__);
+
+	return -EPERM;
+}
+
 static int __qedi_probe(struct pci_dev *pdev, int mode)
 {
 	struct qedi_ctx *qedi;
@@ -2875,6 +2892,7 @@ static struct pci_driver qedi_pci_driver = {
 	.remove = qedi_remove,
 	.shutdown = qedi_shutdown,
 	.err_handler = &qedi_err_handler,
+	.suspend = qedi_suspend,
 };
 
 static int __init qedi_init(void)

drivers/scsi/raid_class.c

@@ -248,6 +248,7 @@ int raid_component_add(struct raid_template *r,struct device *raid_dev,
 	return 0;
 
 err_out:
+	put_device(&rc->dev);
 	list_del(&rc->node);
 	rd->component_count--;
 	put_device(component_dev);

drivers/scsi/scsi_proc.c

@@ -311,7 +311,7 @@ static ssize_t proc_scsi_write(struct file *file, const char __user *buf,
 			       size_t length, loff_t *ppos)
 {
 	int host, channel, id, lun;
-	char *buffer, *p;
+	char *buffer, *end, *p;
 	int err;
 
 	if (!buf || length > PAGE_SIZE)
@@ -326,10 +326,14 @@ static ssize_t proc_scsi_write(struct file *file, const char __user *buf,
 		goto out;
 
 	err = -EINVAL;
-	if (length < PAGE_SIZE)
+	if (length < PAGE_SIZE) {
-		buffer[length] = '\0';
+		end = buffer + length;
-	else if (buffer[PAGE_SIZE-1])
+		*end = '\0';
+	} else {
+		end = buffer + PAGE_SIZE - 1;
+		if (*end)
 			goto out;
+	}
 
 	/*
 	 * Usage: echo "scsi add-single-device 0 1 2 3" >/proc/scsi/scsi
@@ -338,10 +342,10 @@ static ssize_t proc_scsi_write(struct file *file, const char __user *buf,
 	if (!strncmp("scsi add-single-device", buffer, 22)) {
 		p = buffer + 23;
 
-		host = simple_strtoul(p, &p, 0);
+		host    = (p     < end) ? simple_strtoul(p, &p, 0) : 0;
-		channel = simple_strtoul(p + 1, &p, 0);
+		channel = (p + 1 < end) ? simple_strtoul(p + 1, &p, 0) : 0;
-		id = simple_strtoul(p + 1, &p, 0);
+		id      = (p + 1 < end) ? simple_strtoul(p + 1, &p, 0) : 0;
-		lun = simple_strtoul(p + 1, &p, 0);
+		lun     = (p + 1 < end) ? simple_strtoul(p + 1, &p, 0) : 0;
 
 		err = scsi_add_single_device(host, channel, id, lun);
 
@@ -352,10 +356,10 @@ static ssize_t proc_scsi_write(struct file *file, const char __user *buf,
 	} else if (!strncmp("scsi remove-single-device", buffer, 25)) {
 		p = buffer + 26;
 
-		host = simple_strtoul(p, &p, 0);
+		host    = (p     < end) ? simple_strtoul(p, &p, 0) : 0;
-		channel = simple_strtoul(p + 1, &p, 0);
+		channel = (p + 1 < end) ? simple_strtoul(p + 1, &p, 0) : 0;
-		id = simple_strtoul(p + 1, &p, 0);
+		id      = (p + 1 < end) ? simple_strtoul(p + 1, &p, 0) : 0;
-		lun = simple_strtoul(p + 1, &p, 0);
+		lun     = (p + 1 < end) ? simple_strtoul(p + 1, &p, 0) : 0;
 
 		err = scsi_remove_single_device(host, channel, id, lun);
 	}

drivers/scsi/snic/snic_disc.c

@@ -317,6 +317,7 @@ snic_tgt_create(struct snic *snic, struct snic_tgt_id *tgtid)
 			      "Snic Tgt: device_add, with err = %d\n",
 			      ret);
 
+		put_device(&tgt->dev);
 		put_device(&snic->shost->shost_gendev);
 		spin_lock_irqsave(snic->shost->host_lock, flags);
 		list_del(&tgt->list);

drivers/scsi/storvsc_drv.c

@@ -1641,10 +1641,6 @@ static int storvsc_host_reset_handler(struct scsi_cmnd *scmnd)
  */
 static enum blk_eh_timer_return storvsc_eh_timed_out(struct scsi_cmnd *scmnd)
 {
-#if IS_ENABLED(CONFIG_SCSI_FC_ATTRS)
-	if (scmnd->device->host->transportt == fc_transport_template)
-		return fc_eh_timed_out(scmnd);
-#endif
 	return BLK_EH_RESET_TIMER;
 }
 

drivers/usb/common/usb-conn-gpio.c

@@ -42,6 +42,7 @@ struct usb_conn_info {
 
 	struct power_supply_desc desc;
 	struct power_supply *charger;
+	bool initial_detection;
 };
 
 /*
@@ -86,11 +87,13 @@ static void usb_conn_detect_cable(struct work_struct *work)
 	dev_dbg(info->dev, "role %d/%d, gpios: id %d, vbus %d\n",
 		info->last_role, role, id, vbus);
 
-	if (info->last_role == role) {
+	if (!info->initial_detection && info->last_role == role) {
 		dev_warn(info->dev, "repeated role: %d\n", role);
 		return;
 	}
 
+	info->initial_detection = false;
+
 	if (info->last_role == USB_ROLE_HOST && info->vbus)
 		regulator_disable(info->vbus);
 
@@ -278,6 +281,7 @@ static int usb_conn_probe(struct platform_device *pdev)
 	device_set_wakeup_capable(&pdev->dev, true);
 
 	/* Perform initial detection */
+	info->initial_detection = true;
 	usb_conn_queue_dwork(info, 0);
 
 	return 0;

drivers/usb/dwc3/gadget.c

@@ -4345,9 +4345,14 @@ static irqreturn_t dwc3_check_event_buf(struct dwc3_event_buffer *evt)
 	u32 count;
 
 	if (pm_runtime_suspended(dwc->dev)) {
+		dwc->pending_events = true;
+		/*
+		 * Trigger runtime resume. The get() function will be balanced
+		 * after processing the pending events in dwc3_process_pending
+		 * events().
+		 */
 		pm_runtime_get(dwc->dev);
 		disable_irq_nosync(dwc->irq_gadget);
-		dwc->pending_events = true;
 		return IRQ_HANDLED;
 	}
 
@@ -4616,6 +4621,8 @@ void dwc3_gadget_process_pending_events(struct dwc3 *dwc)
 {
 	if (dwc->pending_events) {
 		dwc3_interrupt(dwc->irq_gadget, dwc->ev_buf);
+		dwc3_thread_interrupt(dwc->irq_gadget, dwc->ev_buf);
+		pm_runtime_put(dwc->dev);
 		dwc->pending_events = false;
 		enable_irq(dwc->irq_gadget);
 	}

drivers/usb/storage/alauda.c

@@ -318,6 +318,7 @@ static int alauda_get_media_status(struct us_data *us, unsigned char *data)
 	rc = usb_stor_ctrl_transfer(us, us->recv_ctrl_pipe,
 		command, 0xc0, 0, 1, data, 2);
 
+	if (rc == USB_STOR_XFER_GOOD)
 		usb_stor_dbg(us, "Media status %02X %02X\n", data[0], data[1]);
 
 	return rc;
@@ -454,9 +455,14 @@ static int alauda_init_media(struct us_data *us)
 static int alauda_check_media(struct us_data *us)
 {
 	struct alauda_info *info = (struct alauda_info *) us->extra;
-	unsigned char status[2];
+	unsigned char *status = us->iobuf;
+	int rc;
 
-	alauda_get_media_status(us, status);
+	rc = alauda_get_media_status(us, status);
+	if (rc != USB_STOR_XFER_GOOD) {
+		status[0] = 0xF0;	/* Pretend there's no media */
+		status[1] = 0;
+	}
 
 	/* Check for no media or door open */
 	if ((status[0] & 0x80) || ((status[0] & 0x1F) == 0x10)

fs/btrfs/extent-tree.c

@@ -4138,8 +4138,11 @@ static noinline int find_free_extent(struct btrfs_root *root,
 			ret = 0;
 		}
 
-		if (unlikely(block_group->cached == BTRFS_CACHE_ERROR))
+		if (unlikely(block_group->cached == BTRFS_CACHE_ERROR)) {
+			if (!cache_block_group_error)
+				cache_block_group_error = -EIO;
 			goto loop;
+		}
 
 		bg_ret = NULL;
 		ret = do_allocation(block_group, &ffe_ctl, &bg_ret);

fs/btrfs/extent_io.c

@@ -4034,11 +4034,12 @@ int btree_write_cache_pages(struct address_space *mapping,
 			free_extent_buffer(eb);
 
 			/*
-			 * the filesystem may choose to bump up nr_to_write.
+			 * The filesystem may choose to bump up nr_to_write.
 			 * We have to make sure to honor the new nr_to_write
-			 * at any time
+			 * at any time.
 			 */
-			nr_to_write_done = wbc->nr_to_write <= 0;
+			nr_to_write_done = (wbc->sync_mode == WB_SYNC_NONE &&
+					    wbc->nr_to_write <= 0);
 		}
 		pagevec_release(&pvec);
 		cond_resched();

fs/nilfs2/inode.c

@@ -1103,9 +1103,17 @@ int nilfs_set_file_dirty(struct inode *inode, unsigned int nr_dirty)
 
 int __nilfs_mark_inode_dirty(struct inode *inode, int flags)
 {
+	struct the_nilfs *nilfs = inode->i_sb->s_fs_info;
 	struct buffer_head *ibh;
 	int err;
 
+	/*
+	 * Do not dirty inodes after the log writer has been detached
+	 * and its nilfs_root struct has been freed.
+	 */
+	if (unlikely(nilfs_purging(nilfs)))
+		return 0;
+
 	err = nilfs_load_inode_block(inode, &ibh);
 	if (unlikely(err)) {
 		nilfs_warn(inode->i_sb,

fs/nilfs2/segment.c

@@ -2850,6 +2850,7 @@ void nilfs_detach_log_writer(struct super_block *sb)
 		nilfs_segctor_destroy(nilfs->ns_writer);
 		nilfs->ns_writer = NULL;
 	}
+	set_nilfs_purging(nilfs);
 
 	/* Force to free the list of dirty files */
 	spin_lock(&nilfs->ns_inode_lock);
@@ -2862,4 +2863,5 @@ void nilfs_detach_log_writer(struct super_block *sb)
 	up_write(&nilfs->ns_segctor_sem);
 
 	nilfs_dispose_list(nilfs, &garbage_list, 1);
+	clear_nilfs_purging(nilfs);
 }

fs/nilfs2/the_nilfs.h

@@ -29,6 +29,7 @@ enum {
 	THE_NILFS_DISCONTINUED,	/* 'next' pointer chain has broken */
 	THE_NILFS_GC_RUNNING,	/* gc process is running */
 	THE_NILFS_SB_DIRTY,	/* super block is dirty */
+	THE_NILFS_PURGING,	/* disposing dirty files for cleanup */
 };
 
 /**
@@ -208,6 +209,7 @@ THE_NILFS_FNS(INIT, init)
 THE_NILFS_FNS(DISCONTINUED, discontinued)
 THE_NILFS_FNS(GC_RUNNING, gc_running)
 THE_NILFS_FNS(SB_DIRTY, sb_dirty)
+THE_NILFS_FNS(PURGING, purging)
 
 /*
  * Mount option operations

include/linux/cpu.h

@@ -72,6 +72,8 @@ extern ssize_t cpu_show_retbleed(struct device *dev,
 				 struct device_attribute *attr, char *buf);
 extern ssize_t cpu_show_spec_rstack_overflow(struct device *dev,
 					     struct device_attribute *attr, char *buf);
+extern ssize_t cpu_show_gds(struct device *dev,
+			    struct device_attribute *attr, char *buf);
 
 extern __printf(4, 5)
 struct device *cpu_device_create(struct device *parent, void *drvdata,

include/net/cfg80211.h

@@ -514,6 +514,9 @@ ieee80211_get_sband_iftype_data(const struct ieee80211_supported_band *sband,
 	if (WARN_ON(iftype >= NL80211_IFTYPE_MAX))
 		return NULL;
 
+	if (iftype == NL80211_IFTYPE_AP_VLAN)
+		iftype = NL80211_IFTYPE_AP;
+
 	for (i = 0; i < sband->n_iftype_data; i++)  {
 		const struct ieee80211_sband_iftype_data *data =
 			&sband->iftype_data[i];

include/net/netfilter/nf_tables.h

@@ -1073,6 +1073,29 @@ int __nft_release_basechain(struct nft_ctx *ctx);
 
 unsigned int nft_do_chain(struct nft_pktinfo *pkt, void *priv);
 
+static inline bool nft_use_inc(u32 *use)
+{
+	if (*use == UINT_MAX)
+		return false;
+
+	(*use)++;
+
+	return true;
+}
+
+static inline void nft_use_dec(u32 *use)
+{
+	WARN_ON_ONCE((*use)-- == 0);
+}
+
+/* For error and abort path: restore use counter to previous state. */
+static inline void nft_use_inc_restore(u32 *use)
+{
+	WARN_ON_ONCE(!nft_use_inc(use));
+}
+
+#define nft_use_dec_restore	nft_use_dec
+
 /**
  *	struct nft_table - nf_tables table
  *
@@ -1150,8 +1173,8 @@ struct nft_object {
 	struct list_head		list;
 	struct rhlist_head		rhlhead;
 	struct nft_object_hash_key	key;
-	u32				genmask:2,
+	u32				genmask:2;
-					use:30;
+	u32				use;
 	u64				handle;
 	u16				udlen;
 	u8				*udata;
@@ -1253,8 +1276,8 @@ struct nft_flowtable {
 	char				*name;
 	int				hooknum;
 	int				ops_len;
-	u32				genmask:2,
+	u32				genmask:2;
-					use:30;
+	u32				use;
 	u64				handle;
 	/* runtime data below here */
 	struct list_head		hook_list ____cacheline_aligned;

io_uring/io_uring.c

@@ -4239,9 +4239,11 @@ static int io_openat2(struct io_kiocb *req, unsigned int issue_flags)
 	if (issue_flags & IO_URING_F_NONBLOCK) {
 		/*
 		 * Don't bother trying for O_TRUNC, O_CREAT, or O_TMPFILE open,
-		 * it'll always -EAGAIN
+		 * it'll always -EAGAIN. Note that we test for __O_TMPFILE
+		 * because O_TMPFILE includes O_DIRECTORY, which isn't a flag
+		 * we need to force async for.
 		 */
-		if (req->open.how.flags & (O_TRUNC | O_CREAT | O_TMPFILE))
+		if (req->open.how.flags & (O_TRUNC | O_CREAT | __O_TMPFILE))
 			return -EAGAIN;
 		op.lookup_flags |= LOOKUP_CACHED;
 		op.open_flag |= O_NONBLOCK;

kernel/bpf/verifier.c

@@ -1359,7 +1359,7 @@ static void __mark_reg_unknown(const struct bpf_verifier_env *env,
 	reg->type = SCALAR_VALUE;
 	reg->var_off = tnum_unknown;
 	reg->frameno = 0;
-	reg->precise = env->subprog_cnt > 1 || !env->bpf_capable;
+	reg->precise = !env->bpf_capable;
 	__mark_reg_unbounded(reg);
 }
 
@@ -2023,8 +2023,11 @@ static void mark_all_scalars_precise(struct bpf_verifier_env *env,
 
 	/* big hammer: mark all scalars precise in this path.
 	 * pop_stack may still get !precise scalars.
+	 * We also skip current state and go straight to first parent state,
+	 * because precision markings in current non-checkpointed state are
+	 * not needed. See why in the comment in __mark_chain_precision below.
 	 */
-	for (; st; st = st->parent)
+	for (st = st->parent; st; st = st->parent) {
 		for (i = 0; i <= st->curframe; i++) {
 			func = st->frame[i];
 			for (j = 0; j < BPF_REG_FP; j++) {
@@ -2043,7 +2046,120 @@ static void mark_all_scalars_precise(struct bpf_verifier_env *env,
 			}
 		}
 	}
+}
 
+static void mark_all_scalars_imprecise(struct bpf_verifier_env *env, struct bpf_verifier_state *st)
+{
+	struct bpf_func_state *func;
+	struct bpf_reg_state *reg;
+	int i, j;
+
+	for (i = 0; i <= st->curframe; i++) {
+		func = st->frame[i];
+		for (j = 0; j < BPF_REG_FP; j++) {
+			reg = &func->regs[j];
+			if (reg->type != SCALAR_VALUE)
+				continue;
+			reg->precise = false;
+		}
+		for (j = 0; j < func->allocated_stack / BPF_REG_SIZE; j++) {
+			if (!is_spilled_reg(&func->stack[j]))
+				continue;
+			reg = &func->stack[j].spilled_ptr;
+			if (reg->type != SCALAR_VALUE)
+				continue;
+			reg->precise = false;
+		}
+	}
+}
+
+/*
+ * __mark_chain_precision() backtracks BPF program instruction sequence and
+ * chain of verifier states making sure that register *regno* (if regno >= 0)
+ * and/or stack slot *spi* (if spi >= 0) are marked as precisely tracked
+ * SCALARS, as well as any other registers and slots that contribute to
+ * a tracked state of given registers/stack slots, depending on specific BPF
+ * assembly instructions (see backtrack_insns() for exact instruction handling
+ * logic). This backtracking relies on recorded jmp_history and is able to
+ * traverse entire chain of parent states. This process ends only when all the
+ * necessary registers/slots and their transitive dependencies are marked as
+ * precise.
+ *
+ * One important and subtle aspect is that precise marks *do not matter* in
+ * the currently verified state (current state). It is important to understand
+ * why this is the case.
+ *
+ * First, note that current state is the state that is not yet "checkpointed",
+ * i.e., it is not yet put into env->explored_states, and it has no children
+ * states as well. It's ephemeral, and can end up either a) being discarded if
+ * compatible explored state is found at some point or BPF_EXIT instruction is
+ * reached or b) checkpointed and put into env->explored_states, branching out
+ * into one or more children states.
+ *
+ * In the former case, precise markings in current state are completely
+ * ignored by state comparison code (see regsafe() for details). Only
+ * checkpointed ("old") state precise markings are important, and if old
+ * state's register/slot is precise, regsafe() assumes current state's
+ * register/slot as precise and checks value ranges exactly and precisely. If
+ * states turn out to be compatible, current state's necessary precise
+ * markings and any required parent states' precise markings are enforced
+ * after the fact with propagate_precision() logic, after the fact. But it's
+ * important to realize that in this case, even after marking current state
+ * registers/slots as precise, we immediately discard current state. So what
+ * actually matters is any of the precise markings propagated into current
+ * state's parent states, which are always checkpointed (due to b) case above).
+ * As such, for scenario a) it doesn't matter if current state has precise
+ * markings set or not.
+ *
+ * Now, for the scenario b), checkpointing and forking into child(ren)
+ * state(s). Note that before current state gets to checkpointing step, any
+ * processed instruction always assumes precise SCALAR register/slot
+ * knowledge: if precise value or range is useful to prune jump branch, BPF
+ * verifier takes this opportunity enthusiastically. Similarly, when
+ * register's value is used to calculate offset or memory address, exact
+ * knowledge of SCALAR range is assumed, checked, and enforced. So, similar to
+ * what we mentioned above about state comparison ignoring precise markings
+ * during state comparison, BPF verifier ignores and also assumes precise
+ * markings *at will* during instruction verification process. But as verifier
+ * assumes precision, it also propagates any precision dependencies across
+ * parent states, which are not yet finalized, so can be further restricted
+ * based on new knowledge gained from restrictions enforced by their children
+ * states. This is so that once those parent states are finalized, i.e., when
+ * they have no more active children state, state comparison logic in
+ * is_state_visited() would enforce strict and precise SCALAR ranges, if
+ * required for correctness.
+ *
+ * To build a bit more intuition, note also that once a state is checkpointed,
+ * the path we took to get to that state is not important. This is crucial
+ * property for state pruning. When state is checkpointed and finalized at
+ * some instruction index, it can be correctly and safely used to "short
+ * circuit" any *compatible* state that reaches exactly the same instruction
+ * index. I.e., if we jumped to that instruction from a completely different
+ * code path than original finalized state was derived from, it doesn't
+ * matter, current state can be discarded because from that instruction
+ * forward having a compatible state will ensure we will safely reach the
+ * exit. States describe preconditions for further exploration, but completely
+ * forget the history of how we got here.
+ *
+ * This also means that even if we needed precise SCALAR range to get to
+ * finalized state, but from that point forward *that same* SCALAR register is
+ * never used in a precise context (i.e., it's precise value is not needed for
+ * correctness), it's correct and safe to mark such register as "imprecise"
+ * (i.e., precise marking set to false). This is what we rely on when we do
+ * not set precise marking in current state. If no child state requires
+ * precision for any given SCALAR register, it's safe to dictate that it can
+ * be imprecise. If any child state does require this register to be precise,
+ * we'll mark it precise later retroactively during precise markings
+ * propagation from child state to parent states.
+ *
+ * Skipping precise marking setting in current state is a mild version of
+ * relying on the above observation. But we can utilize this property even
+ * more aggressively by proactively forgetting any precise marking in the
+ * current state (which we inherited from the parent state), right before we
+ * checkpoint it and branch off into new child state. This is done by
+ * mark_all_scalars_imprecise() to hopefully get more permissive and generic
+ * finalized states which help in short circuiting more future states.
+ */
 static int __mark_chain_precision(struct bpf_verifier_env *env, int frame, int regno,
 				  int spi)
 {
@@ -2061,6 +2177,10 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int frame, int r
 	if (!env->bpf_capable)
 		return 0;
 
+	/* Do sanity checks against current state of register and/or stack
+	 * slot, but don't set precise flag in current state, as precision
+	 * tracking in the current state is unnecessary.
+	 */
 	func = st->frame[frame];
 	if (regno >= 0) {
 		reg = &func->regs[regno];
@@ -2068,11 +2188,7 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int frame, int r
 			WARN_ONCE(1, "backtracing misuse");
 			return -EFAULT;
 		}
-		if (!reg->precise)
 		new_marks = true;
-		else
-			reg_mask = 0;
-		reg->precise = true;
 	}
 
 	while (spi >= 0) {
@@ -2085,11 +2201,7 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int frame, int r
 			stack_mask = 0;
 			break;
 		}
-		if (!reg->precise)
 		new_marks = true;
-		else
-			stack_mask = 0;
-		reg->precise = true;
 		break;
 	}
 
@@ -2097,12 +2209,42 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int frame, int r
 		return 0;
 	if (!reg_mask && !stack_mask)
 		return 0;
+
 	for (;;) {
 		DECLARE_BITMAP(mask, 64);
 		u32 history = st->jmp_history_cnt;
 
 		if (env->log.level & BPF_LOG_LEVEL)
 			verbose(env, "last_idx %d first_idx %d\n", last_idx, first_idx);
+
+		if (last_idx < 0) {
+			/* we are at the entry into subprog, which
+			 * is expected for global funcs, but only if
+			 * requested precise registers are R1-R5
+			 * (which are global func's input arguments)
+			 */
+			if (st->curframe == 0 &&
+			    st->frame[0]->subprogno > 0 &&
+			    st->frame[0]->callsite == BPF_MAIN_FUNC &&
+			    stack_mask == 0 && (reg_mask & ~0x3e) == 0) {
+				bitmap_from_u64(mask, reg_mask);
+				for_each_set_bit(i, mask, 32) {
+					reg = &st->frame[0]->regs[i];
+					if (reg->type != SCALAR_VALUE) {
+						reg_mask &= ~(1u << i);
+						continue;
+					}
+					reg->precise = true;
+				}
+				return 0;
+			}
+
+			verbose(env, "BUG backtracing func entry subprog %d reg_mask %x stack_mask %llx\n",
+				st->frame[0]->subprogno, reg_mask, stack_mask);
+			WARN_ONCE(1, "verifier backtracking bug");
+			return -EFAULT;
+		}
+
 		for (i = last_idx;;) {
 			if (skip_first) {
 				err = 0;
@@ -9233,7 +9375,7 @@ static bool regsafe(struct bpf_verifier_env *env, struct bpf_reg_state *rold,
 		if (env->explore_alu_limits)
 			return false;
 		if (rcur->type == SCALAR_VALUE) {
-			if (!rold->precise && !rcur->precise)
+			if (!rold->precise)
 				return true;
 			/* new val must satisfy old val knowledge */
 			return range_within(rold, rcur) &&
@@ -9766,6 +9908,10 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx)
 	env->prev_jmps_processed = env->jmps_processed;
 	env->prev_insn_processed = env->insn_processed;
 
+	/* forget precise markings we inherited, see __mark_chain_precision */
+	if (env->bpf_capable)
+		mark_all_scalars_imprecise(env, cur);
+
 	/* add new state to the head of linked list */
 	new = &new_sl->state;
 	err = copy_verifier_state(new, cur);
@@ -11864,6 +12010,9 @@ static int do_check_common(struct bpf_verifier_env *env, int subprog)
 			0 /* frameno */,
 			subprog);
 
+	state->first_insn_idx = env->subprog_info[subprog].start;
+	state->last_insn_idx = -1;
+
 	regs = state->frame[state->curframe]->regs;
 	if (subprog || env->prog->type == BPF_PROG_TYPE_EXT) {
 		ret = btf_prepare_func_args(env, subprog, regs);

net/dccp/output.c

@@ -185,7 +185,7 @@ unsigned int dccp_sync_mss(struct sock *sk, u32 pmtu)
 
 	/* And store cached results */
 	icsk->icsk_pmtu_cookie = pmtu;
-	dp->dccps_mss_cache = cur_mps;
+	WRITE_ONCE(dp->dccps_mss_cache, cur_mps);
 
 	return cur_mps;
 }

net/dccp/proto.c

@@ -639,7 +639,7 @@ static int do_dccp_getsockopt(struct sock *sk, int level, int optname,
 		return dccp_getsockopt_service(sk, len,
 					       (__be32 __user *)optval, optlen);
 	case DCCP_SOCKOPT_GET_CUR_MPS:
-		val = dp->dccps_mss_cache;
+		val = READ_ONCE(dp->dccps_mss_cache);
 		break;
 	case DCCP_SOCKOPT_AVAILABLE_CCIDS:
 		return ccid_getsockopt_builtin_ccids(sk, len, optval, optlen);
@@ -748,7 +748,7 @@ int dccp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 
 	trace_dccp_probe(sk, len);
 
-	if (len > dp->dccps_mss_cache)
+	if (len > READ_ONCE(dp->dccps_mss_cache))
 		return -EMSGSIZE;
 
 	lock_sock(sk);
@@ -781,6 +781,12 @@ int dccp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 		goto out_discard;
 	}
 
+	/* We need to check dccps_mss_cache after socket is locked. */
+	if (len > dp->dccps_mss_cache) {
+		rc = -EMSGSIZE;
+		goto out_discard;
+	}
+
 	skb_reserve(skb, sk->sk_prot->max_header);
 	rc = memcpy_from_msg(skb_put(skb, len), msg, len);
 	if (rc != 0)

net/ipv4/ip_tunnel_core.c

@@ -224,7 +224,7 @@ static int iptunnel_pmtud_build_icmp(struct sk_buff *skb, int mtu)
 		.un.frag.__unused	= 0,
 		.un.frag.mtu		= ntohs(mtu),
 	};
-	icmph->checksum = ip_compute_csum(icmph, len);
+	icmph->checksum = csum_fold(skb_checksum(skb, 0, len, 0));
 	skb_reset_transport_header(skb);
 
 	niph = skb_push(skb, sizeof(*niph));

net/ipv6/ndisc.c

@@ -196,7 +196,8 @@ static struct nd_opt_hdr *ndisc_next_option(struct nd_opt_hdr *cur,
 static inline int ndisc_is_useropt(const struct net_device *dev,
 				   struct nd_opt_hdr *opt)
 {
-	return opt->nd_opt_type == ND_OPT_RDNSS ||
+	return opt->nd_opt_type == ND_OPT_PREFIX_INFO ||
+		opt->nd_opt_type == ND_OPT_RDNSS ||
 		opt->nd_opt_type == ND_OPT_DNSSL ||
 		opt->nd_opt_type == ND_OPT_CAPTIVE_PORTAL ||
 		opt->nd_opt_type == ND_OPT_PREF64 ||

net/netfilter/nf_tables_api.c

@@ -257,8 +257,10 @@ int nf_tables_bind_chain(const struct nft_ctx *ctx, struct nft_chain *chain)
 	if (chain->bound)
 		return -EBUSY;
 
+	if (!nft_use_inc(&chain->use))
+		return -EMFILE;
+
 	chain->bound = true;
-	chain->use++;
 	nft_chain_trans_bind(ctx, chain);
 
 	return 0;
@@ -427,7 +429,7 @@ static int nft_delchain(struct nft_ctx *ctx)
 	if (IS_ERR(trans))
 		return PTR_ERR(trans);
 
-	ctx->table->use--;
+	nft_use_dec(&ctx->table->use);
 	nft_deactivate_next(ctx->net, ctx->chain);
 
 	return 0;
@@ -466,7 +468,7 @@ nf_tables_delrule_deactivate(struct nft_ctx *ctx, struct nft_rule *rule)
 	/* You cannot delete the same rule twice */
 	if (nft_is_active_next(ctx->net, rule)) {
 		nft_deactivate_next(ctx->net, rule);
-		ctx->chain->use--;
+		nft_use_dec(&ctx->chain->use);
 		return 0;
 	}
 	return -ENOENT;
@@ -594,7 +596,7 @@ static int nft_delset(const struct nft_ctx *ctx, struct nft_set *set)
 		nft_map_deactivate(ctx, set);
 
 	nft_deactivate_next(ctx->net, set);
-	ctx->table->use--;
+	nft_use_dec(&ctx->table->use);
 
 	return err;
 }
@@ -626,7 +628,7 @@ static int nft_delobj(struct nft_ctx *ctx, struct nft_object *obj)
 		return err;
 
 	nft_deactivate_next(ctx->net, obj);
-	ctx->table->use--;
+	nft_use_dec(&ctx->table->use);
 
 	return err;
 }
@@ -661,7 +663,7 @@ static int nft_delflowtable(struct nft_ctx *ctx,
 		return err;
 
 	nft_deactivate_next(ctx->net, flowtable);
-	ctx->table->use--;
+	nft_use_dec(&ctx->table->use);
 
 	return err;
 }
@@ -2158,9 +2160,6 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask,
 	struct nft_rule **rules;
 	int err;
 
-	if (table->use == UINT_MAX)
-		return -EOVERFLOW;
-
 	if (nla[NFTA_CHAIN_HOOK]) {
 		struct nft_stats __percpu *stats = NULL;
 		struct nft_chain_hook hook;
@@ -2256,6 +2255,11 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask,
 	if (err < 0)
 		goto err_destroy_chain;
 
+	if (!nft_use_inc(&table->use)) {
+		err = -EMFILE;
+		goto err_use;
+	}
+
 	trans = nft_trans_chain_add(ctx, NFT_MSG_NEWCHAIN);
 	if (IS_ERR(trans)) {
 		err = PTR_ERR(trans);
@@ -2272,10 +2276,11 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask,
 		goto err_unregister_hook;
 	}
 
-	table->use++;
-
 	return 0;
+
 err_unregister_hook:
+	nft_use_dec_restore(&table->use);
+err_use:
 	nf_tables_unregister_hook(net, table, chain);
 err_destroy_chain:
 	nf_tables_chain_destroy(ctx);
@@ -3387,9 +3392,6 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk,
 			return -EINVAL;
 		handle = nf_tables_alloc_handle(table);
 
-		if (chain->use == UINT_MAX)
-			return -EOVERFLOW;
-
 		if (nla[NFTA_RULE_POSITION]) {
 			pos_handle = be64_to_cpu(nla_get_be64(nla[NFTA_RULE_POSITION]));
 			old_rule = __nft_rule_lookup(chain, pos_handle);
@@ -3475,16 +3477,21 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk,
 		expr = nft_expr_next(expr);
 	}
 
+	if (!nft_use_inc(&chain->use)) {
+		err = -EMFILE;
+		goto err2;
+	}
+
 	if (nlh->nlmsg_flags & NLM_F_REPLACE) {
 		trans = nft_trans_rule_add(&ctx, NFT_MSG_NEWRULE, rule);
 		if (trans == NULL) {
 			err = -ENOMEM;
-			goto err2;
+			goto err_destroy_flow_rule;
 		}
 		err = nft_delrule(&ctx, old_rule);
 		if (err < 0) {
 			nft_trans_destroy(trans);
-			goto err2;
+			goto err_destroy_flow_rule;
 		}
 
 		list_add_tail_rcu(&rule->list, &old_rule->list);
@@ -3492,7 +3499,7 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk,
 		trans = nft_trans_rule_add(&ctx, NFT_MSG_NEWRULE, rule);
 		if (!trans) {
 			err = -ENOMEM;
-			goto err2;
+			goto err_destroy_flow_rule;
 		}
 
 		if (nlh->nlmsg_flags & NLM_F_APPEND) {
@@ -3508,7 +3515,6 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk,
 		}
 	}
 	kvfree(info);
-	chain->use++;
 
 	if (nft_net->validate_state == NFT_VALIDATE_DO)
 		return nft_table_validate(net, table);
@@ -3522,6 +3528,9 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk,
 	}
 
 	return 0;
+
+err_destroy_flow_rule:
+	nft_use_dec_restore(&chain->use);
 err2:
 	nft_rule_expr_deactivate(&ctx, rule, NFT_TRANS_PREPARE_ERROR);
 	nf_tables_rule_destroy(&ctx, rule);
@@ -4437,9 +4446,15 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk,
 	alloc_size = sizeof(*set) + size + udlen;
 	if (alloc_size < size || alloc_size > INT_MAX)
 		return -ENOMEM;
+
+	if (!nft_use_inc(&table->use))
+		return -EMFILE;
+
 	set = kvzalloc(alloc_size, GFP_KERNEL);
-	if (!set)
+	if (!set) {
-		return -ENOMEM;
+		err = -ENOMEM;
+		goto err_alloc;
+	}
 
 	name = nla_strdup(nla[NFTA_SET_NAME], GFP_KERNEL);
 	if (!name) {
@@ -4500,7 +4515,7 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk,
 		goto err_set_expr_alloc;
 
 	list_add_tail_rcu(&set->list, &table->sets);
-	table->use++;
+
 	return 0;
 
 err_set_expr_alloc:
@@ -4512,6 +4527,9 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk,
 	kfree(set->name);
 err_set_name:
 	kvfree(set);
+err_alloc:
+	nft_use_dec_restore(&table->use);
+
 	return err;
 }
 
@@ -4605,9 +4623,6 @@ int nf_tables_bind_set(const struct nft_ctx *ctx, struct nft_set *set,
 	struct nft_set_binding *i;
 	struct nft_set_iter iter;
 
-	if (set->use == UINT_MAX)
-		return -EOVERFLOW;
-
 	if (!list_empty(&set->bindings) && nft_set_is_anonymous(set))
 		return -EBUSY;
 
@@ -4632,10 +4647,12 @@ int nf_tables_bind_set(const struct nft_ctx *ctx, struct nft_set *set,
 			return iter.err;
 	}
 bind:
+	if (!nft_use_inc(&set->use))
+		return -EMFILE;
+
 	binding->chain = ctx->chain;
 	list_add_tail_rcu(&binding->list, &set->bindings);
 	nft_set_trans_bind(ctx, set);
-	set->use++;
 
 	return 0;
 }
@@ -4688,7 +4705,7 @@ void nf_tables_activate_set(const struct nft_ctx *ctx, struct nft_set *set)
 		nft_clear(ctx->net, set);
 	}
 
-	set->use++;
+	nft_use_inc_restore(&set->use);
 }
 EXPORT_SYMBOL_GPL(nf_tables_activate_set);
 
@@ -4704,7 +4721,7 @@ void nf_tables_deactivate_set(const struct nft_ctx *ctx, struct nft_set *set,
 		else
 			list_del_rcu(&binding->list);
 
-		set->use--;
+		nft_use_dec(&set->use);
 		break;
 	case NFT_TRANS_PREPARE:
 		if (nft_set_is_anonymous(set)) {
@@ -4713,7 +4730,7 @@ void nf_tables_deactivate_set(const struct nft_ctx *ctx, struct nft_set *set,
 
 			nft_deactivate_next(ctx->net, set);
 		}
-		set->use--;
+		nft_use_dec(&set->use);
 		return;
 	case NFT_TRANS_ABORT:
 	case NFT_TRANS_RELEASE:
@@ -4721,7 +4738,7 @@ void nf_tables_deactivate_set(const struct nft_ctx *ctx, struct nft_set *set,
 		    set->flags & (NFT_SET_MAP | NFT_SET_OBJECT))
 			nft_map_deactivate(ctx, set);
 
-		set->use--;
+		nft_use_dec(&set->use);
 		fallthrough;
 	default:
 		nf_tables_unbind_set(ctx, set, binding,
@@ -5344,7 +5361,7 @@ void nft_set_elem_destroy(const struct nft_set *set, void *elem,
 		nft_set_elem_expr_destroy(&ctx, nft_set_ext_expr(ext));
 
 	if (nft_set_ext_exists(ext, NFT_SET_EXT_OBJREF))
-		(*nft_set_ext_obj(ext))->use--;
+		nft_use_dec(&(*nft_set_ext_obj(ext))->use);
 	kfree(elem);
 }
 EXPORT_SYMBOL_GPL(nft_set_elem_destroy);
@@ -5518,8 +5535,16 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
 				     set->objtype, genmask);
 		if (IS_ERR(obj)) {
 			err = PTR_ERR(obj);
+			obj = NULL;
 			goto err_parse_key_end;
 		}
+
+		if (!nft_use_inc(&obj->use)) {
+			err = -EMFILE;
+			obj = NULL;
+			goto err_parse_key_end;
+		}
+
 		nft_set_ext_add(&tmpl, NFT_SET_EXT_OBJREF);
 	}
 
@@ -5584,10 +5609,8 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
 		udata->len = ulen - 1;
 		nla_memcpy(&udata->data, nla[NFTA_SET_ELEM_USERDATA], ulen);
 	}
-	if (obj) {
+	if (obj)
 		*nft_set_ext_obj(ext) = obj;
-		obj->use++;
-	}
 
 	err = nft_set_elem_expr_setup(ctx, ext, expr);
 	if (err < 0)
@@ -5643,14 +5666,14 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
 err_element_clash:
 	kfree(trans);
 err_elem_expr:
-	if (obj)
-		obj->use--;
-
 	nf_tables_set_elem_destroy(ctx, set, elem.priv);
 err_parse_data:
 	if (nla[NFTA_SET_ELEM_DATA] != NULL)
 		nft_data_release(&elem.data.val, desc.type);
 err_parse_key_end:
+	if (obj)
+		nft_use_dec_restore(&obj->use);
+
 	nft_data_release(&elem.key_end.val, NFT_DATA_VALUE);
 err_parse_key:
 	nft_data_release(&elem.key.val, NFT_DATA_VALUE);
@@ -5722,7 +5745,7 @@ void nft_data_hold(const struct nft_data *data, enum nft_data_types type)
 		case NFT_JUMP:
 		case NFT_GOTO:
 			chain = data->verdict.chain;
-			chain->use++;
+			nft_use_inc_restore(&chain->use);
 			break;
 		}
 	}
@@ -5737,7 +5760,7 @@ static void nft_setelem_data_activate(const struct net *net,
 	if (nft_set_ext_exists(ext, NFT_SET_EXT_DATA))
 		nft_data_hold(nft_set_ext_data(ext), set->dtype);
 	if (nft_set_ext_exists(ext, NFT_SET_EXT_OBJREF))
-		(*nft_set_ext_obj(ext))->use++;
+		nft_use_inc_restore(&(*nft_set_ext_obj(ext))->use);
 }
 
 static void nft_setelem_data_deactivate(const struct net *net,
@@ -5749,7 +5772,7 @@ static void nft_setelem_data_deactivate(const struct net *net,
 	if (nft_set_ext_exists(ext, NFT_SET_EXT_DATA))
 		nft_data_release(nft_set_ext_data(ext), set->dtype);
 	if (nft_set_ext_exists(ext, NFT_SET_EXT_OBJREF))
-		(*nft_set_ext_obj(ext))->use--;
+		nft_use_dec(&(*nft_set_ext_obj(ext))->use);
 }
 
 static int nft_del_setelem(struct nft_ctx *ctx, struct nft_set *set,
@@ -6216,9 +6239,14 @@ static int nf_tables_newobj(struct net *net, struct sock *nlsk,
 
 	nft_ctx_init(&ctx, net, skb, nlh, family, table, NULL, nla);
 
+	if (!nft_use_inc(&table->use))
+		return -EMFILE;
+
 	type = nft_obj_type_get(net, objtype);
-	if (IS_ERR(type))
+	if (IS_ERR(type)) {
-		return PTR_ERR(type);
+		err = PTR_ERR(type);
+		goto err_type;
+	}
 
 	obj = nft_obj_init(&ctx, type, nla[NFTA_OBJ_DATA]);
 	if (IS_ERR(obj)) {
@@ -6252,7 +6280,7 @@ static int nf_tables_newobj(struct net *net, struct sock *nlsk,
 		goto err_obj_ht;
 
 	list_add_tail_rcu(&obj->list, &table->objects);
-	table->use++;
+
 	return 0;
 err_obj_ht:
 	/* queued in transaction log */
@@ -6268,6 +6296,9 @@ static int nf_tables_newobj(struct net *net, struct sock *nlsk,
 	kfree(obj);
 err_init:
 	module_put(type->owner);
+err_type:
+	nft_use_dec_restore(&table->use);
+
 	return err;
 }
 
@@ -6658,7 +6689,7 @@ void nf_tables_deactivate_flowtable(const struct nft_ctx *ctx,
 	case NFT_TRANS_PREPARE:
 	case NFT_TRANS_ABORT:
 	case NFT_TRANS_RELEASE:
-		flowtable->use--;
+		nft_use_dec(&flowtable->use);
 		fallthrough;
 	default:
 		return;
@@ -6995,9 +7026,14 @@ static int nf_tables_newflowtable(struct net *net, struct sock *nlsk,
 
 	nft_ctx_init(&ctx, net, skb, nlh, family, table, NULL, nla);
 
+	if (!nft_use_inc(&table->use))
+		return -EMFILE;
+
 	flowtable = kzalloc(sizeof(*flowtable), GFP_KERNEL);
-	if (!flowtable)
+	if (!flowtable) {
-		return -ENOMEM;
+		err = -ENOMEM;
+		goto flowtable_alloc;
+	}
 
 	flowtable->table = table;
 	flowtable->handle = nf_tables_alloc_handle(table);
@@ -7052,7 +7088,6 @@ static int nf_tables_newflowtable(struct net *net, struct sock *nlsk,
 		goto err5;
 
 	list_add_tail_rcu(&flowtable->list, &table->flowtables);
-	table->use++;
 
 	return 0;
 err5:
@@ -7069,6 +7104,9 @@ static int nf_tables_newflowtable(struct net *net, struct sock *nlsk,
 	kfree(flowtable->name);
 err1:
 	kfree(flowtable);
+flowtable_alloc:
+	nft_use_dec_restore(&table->use);
+
 	return err;
 }
 
@@ -8254,7 +8292,7 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb)
 			 */
 			if (nft_set_is_anonymous(nft_trans_set(trans)) &&
 			    !list_empty(&nft_trans_set(trans)->bindings))
-				trans->ctx.table->use--;
+				nft_use_dec(&trans->ctx.table->use);
 
 			nf_tables_set_notify(&trans->ctx, nft_trans_set(trans),
 					     NFT_MSG_NEWSET, GFP_KERNEL);
@@ -8438,7 +8476,7 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action)
 					nft_trans_destroy(trans);
 					break;
 				}
-				trans->ctx.table->use--;
+				nft_use_dec_restore(&trans->ctx.table->use);
 				nft_chain_del(trans->ctx.chain);
 				nf_tables_unregister_hook(trans->ctx.net,
 							  trans->ctx.table,
@@ -8446,7 +8484,7 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action)
 			}
 			break;
 		case NFT_MSG_DELCHAIN:
-			trans->ctx.table->use++;
+			nft_use_inc_restore(&trans->ctx.table->use);
 			nft_clear(trans->ctx.net, trans->ctx.chain);
 			nft_trans_destroy(trans);
 			break;
@@ -8455,20 +8493,20 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action)
 				nft_trans_destroy(trans);
 				break;
 			}
-			trans->ctx.chain->use--;
+			nft_use_dec_restore(&trans->ctx.chain->use);
 			list_del_rcu(&nft_trans_rule(trans)->list);
 			nft_rule_expr_deactivate(&trans->ctx,
 						 nft_trans_rule(trans),
 						 NFT_TRANS_ABORT);
 			break;
 		case NFT_MSG_DELRULE:
-			trans->ctx.chain->use++;
+			nft_use_inc_restore(&trans->ctx.chain->use);
 			nft_clear(trans->ctx.net, nft_trans_rule(trans));
 			nft_rule_expr_activate(&trans->ctx, nft_trans_rule(trans));
 			nft_trans_destroy(trans);
 			break;
 		case NFT_MSG_NEWSET:
-			trans->ctx.table->use--;
+			nft_use_dec_restore(&trans->ctx.table->use);
 			if (nft_trans_set_bound(trans)) {
 				nft_trans_destroy(trans);
 				break;
@@ -8476,7 +8514,7 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action)
 			list_del_rcu(&nft_trans_set(trans)->list);
 			break;
 		case NFT_MSG_DELSET:
-			trans->ctx.table->use++;
+			nft_use_inc_restore(&trans->ctx.table->use);
 			nft_clear(trans->ctx.net, nft_trans_set(trans));
 			if (nft_trans_set(trans)->flags & (NFT_SET_MAP | NFT_SET_OBJECT))
 				nft_map_activate(&trans->ctx, nft_trans_set(trans));
@@ -8506,12 +8544,12 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action)
 				nft_obj_destroy(&trans->ctx, nft_trans_obj_newobj(trans));
 				nft_trans_destroy(trans);
 			} else {
-				trans->ctx.table->use--;
+				nft_use_dec_restore(&trans->ctx.table->use);
 				nft_obj_del(nft_trans_obj(trans));
 			}
 			break;
 		case NFT_MSG_DELOBJ:
-			trans->ctx.table->use++;
+			nft_use_inc_restore(&trans->ctx.table->use);
 			nft_clear(trans->ctx.net, nft_trans_obj(trans));
 			nft_trans_destroy(trans);
 			break;
@@ -8520,7 +8558,7 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action)
 				nft_unregister_flowtable_net_hooks(net,
 						&nft_trans_flowtable_hooks(trans));
 			} else {
-				trans->ctx.table->use--;
+				nft_use_dec_restore(&trans->ctx.table->use);
 				list_del_rcu(&nft_trans_flowtable(trans)->list);
 				nft_unregister_flowtable_net_hooks(net,
 						&nft_trans_flowtable(trans)->hook_list);
@@ -8531,7 +8569,7 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action)
 				list_splice(&nft_trans_flowtable_hooks(trans),
 					    &nft_trans_flowtable(trans)->hook_list);
 			} else {
-				trans->ctx.table->use++;
+				nft_use_inc_restore(&trans->ctx.table->use);
 				nft_clear(trans->ctx.net, nft_trans_flowtable(trans));
 			}
 			nft_trans_destroy(trans);
@@ -8969,8 +9007,9 @@ static int nft_verdict_init(const struct nft_ctx *ctx, struct nft_data *data,
 		if (desc->flags & NFT_DATA_DESC_SETELEM &&
 		    chain->flags & NFT_CHAIN_BINDING)
 			return -EINVAL;
+		if (!nft_use_inc(&chain->use))
+			return -EMFILE;
 
-		chain->use++;
 		data->verdict.chain = chain;
 		break;
 	}
@@ -8988,7 +9027,7 @@ static void nft_verdict_uninit(const struct nft_data *data)
 	case NFT_JUMP:
 	case NFT_GOTO:
 		chain = data->verdict.chain;
-		chain->use--;
+		nft_use_dec(&chain->use);
 		break;
 	}
 }
@@ -9157,11 +9196,11 @@ int __nft_release_basechain(struct nft_ctx *ctx)
 	nf_tables_unregister_hook(ctx->net, ctx->chain->table, ctx->chain);
 	list_for_each_entry_safe(rule, nr, &ctx->chain->rules, list) {
 		list_del(&rule->list);
-		ctx->chain->use--;
+		nft_use_dec(&ctx->chain->use);
 		nf_tables_rule_release(ctx, rule);
 	}
 	nft_chain_del(ctx->chain);
-	ctx->table->use--;
+	nft_use_dec(&ctx->table->use);
 	nf_tables_chain_destroy(ctx);
 
 	return 0;
@@ -9201,18 +9240,18 @@ static void __nft_release_table(struct net *net, struct nft_table *table)
 		ctx.chain = chain;
 		list_for_each_entry_safe(rule, nr, &chain->rules, list) {
 			list_del(&rule->list);
-			chain->use--;
+			nft_use_dec(&chain->use);
 			nf_tables_rule_release(&ctx, rule);
 		}
 	}
 	list_for_each_entry_safe(flowtable, nf, &table->flowtables, list) {
 		list_del(&flowtable->list);
-		table->use--;
+		nft_use_dec(&table->use);
 		nf_tables_flowtable_destroy(flowtable);
 	}
 	list_for_each_entry_safe(set, ns, &table->sets, list) {
 		list_del(&set->list);
-		table->use--;
+		nft_use_dec(&table->use);
 		if (set->flags & (NFT_SET_MAP | NFT_SET_OBJECT))
 			nft_map_deactivate(&ctx, set);
 
@@ -9220,13 +9259,13 @@ static void __nft_release_table(struct net *net, struct nft_table *table)
 	}
 	list_for_each_entry_safe(obj, ne, &table->objects, list) {
 		nft_obj_del(obj);
-		table->use--;
+		nft_use_dec(&table->use);
 		nft_obj_destroy(&ctx, obj);
 	}
 	list_for_each_entry_safe(chain, nc, &table->chains, list) {
 		ctx.chain = chain;
 		nft_chain_del(chain);
-		table->use--;
+		nft_use_dec(&table->use);
 		nf_tables_chain_destroy(&ctx);
 	}
 	list_del(&table->list);

net/netfilter/nft_flow_offload.c

@@ -174,8 +174,10 @@ static int nft_flow_offload_init(const struct nft_ctx *ctx,
 	if (IS_ERR(flowtable))
 		return PTR_ERR(flowtable);
 
+	if (!nft_use_inc(&flowtable->use))
+		return -EMFILE;
+
 	priv->flowtable = flowtable;
-	flowtable->use++;
 
 	return nf_ct_netns_get(ctx->net, ctx->family);
 }
@@ -194,7 +196,7 @@ static void nft_flow_offload_activate(const struct nft_ctx *ctx,
 {
 	struct nft_flow_offload *priv = nft_expr_priv(expr);
 
-	priv->flowtable->use++;
+	nft_use_inc_restore(&priv->flowtable->use);
 }
 
 static void nft_flow_offload_destroy(const struct nft_ctx *ctx,

net/netfilter/nft_immediate.c

@@ -168,7 +168,7 @@ static void nft_immediate_deactivate(const struct nft_ctx *ctx,
 				nft_immediate_chain_deactivate(ctx, chain, phase);
 				nft_chain_del(chain);
 				chain->bound = false;
-				chain->table->use--;
+				nft_use_dec(&chain->table->use);
 				break;
 			}
 			break;
@@ -207,7 +207,7 @@ static void nft_immediate_destroy(const struct nft_ctx *ctx,
 		 * let the transaction records release this chain and its rules.
 		 */
 		if (chain->bound) {
-			chain->use--;
+			nft_use_dec(&chain->use);
 			break;
 		}
 
@@ -215,9 +215,9 @@ static void nft_immediate_destroy(const struct nft_ctx *ctx,
 		chain_ctx = *ctx;
 		chain_ctx.chain = chain;
 
-		chain->use--;
+		nft_use_dec(&chain->use);
 		list_for_each_entry_safe(rule, n, &chain->rules, list) {
-			chain->use--;
+			nft_use_dec(&chain->use);
 			list_del(&rule->list);
 			nf_tables_rule_destroy(&chain_ctx, rule);
 		}

net/netfilter/nft_objref.c

@@ -41,8 +41,10 @@ static int nft_objref_init(const struct nft_ctx *ctx,
 	if (IS_ERR(obj))
 		return -ENOENT;
 
+	if (!nft_use_inc(&obj->use))
+		return -EMFILE;
+
 	nft_objref_priv(expr) = obj;
-	obj->use++;
 
 	return 0;
 }
@@ -71,7 +73,7 @@ static void nft_objref_deactivate(const struct nft_ctx *ctx,
 	if (phase == NFT_TRANS_COMMIT)
 		return;
 
-	obj->use--;
+	nft_use_dec(&obj->use);
 }
 
 static void nft_objref_activate(const struct nft_ctx *ctx,
@@ -79,7 +81,7 @@ static void nft_objref_activate(const struct nft_ctx *ctx,
 {
 	struct nft_object *obj = nft_objref_priv(expr);
 
-	obj->use++;
+	nft_use_inc_restore(&obj->use);
 }
 
 static struct nft_expr_type nft_objref_type;

net/packet/af_packet.c

@@ -366,18 +366,20 @@ static void __packet_set_status(struct packet_sock *po, void *frame, int status)
 {
 	union tpacket_uhdr h;
 
+	/* WRITE_ONCE() are paired with READ_ONCE() in __packet_get_status */
+
 	h.raw = frame;
 	switch (po->tp_version) {
 	case TPACKET_V1:
-		h.h1->tp_status = status;
+		WRITE_ONCE(h.h1->tp_status, status);
 		flush_dcache_page(pgv_to_page(&h.h1->tp_status));
 		break;
 	case TPACKET_V2:
-		h.h2->tp_status = status;
+		WRITE_ONCE(h.h2->tp_status, status);
 		flush_dcache_page(pgv_to_page(&h.h2->tp_status));
 		break;
 	case TPACKET_V3:
-		h.h3->tp_status = status;
+		WRITE_ONCE(h.h3->tp_status, status);
 		flush_dcache_page(pgv_to_page(&h.h3->tp_status));
 		break;
 	default:
@@ -394,17 +396,19 @@ static int __packet_get_status(const struct packet_sock *po, void *frame)
 
 	smp_rmb();
 
+	/* READ_ONCE() are paired with WRITE_ONCE() in __packet_set_status */
+
 	h.raw = frame;
 	switch (po->tp_version) {
 	case TPACKET_V1:
 		flush_dcache_page(pgv_to_page(&h.h1->tp_status));
-		return h.h1->tp_status;
+		return READ_ONCE(h.h1->tp_status);
 	case TPACKET_V2:
 		flush_dcache_page(pgv_to_page(&h.h2->tp_status));
-		return h.h2->tp_status;
+		return READ_ONCE(h.h2->tp_status);
 	case TPACKET_V3:
 		flush_dcache_page(pgv_to_page(&h.h3->tp_status));
-		return h.h3->tp_status;
+		return READ_ONCE(h.h3->tp_status);
 	default:
 		WARN(1, "TPACKET version not supported.\n");
 		BUG();

net/sched/sch_netem.c

@@ -773,12 +773,10 @@ static void dist_free(struct disttable *d)
  * signed 16 bit values.
  */
 
-static int get_dist_table(struct Qdisc *sch, struct disttable **tbl,
+static int get_dist_table(struct disttable **tbl, const struct nlattr *attr)
-			  const struct nlattr *attr)
 {
 	size_t n = nla_len(attr)/sizeof(__s16);
 	const __s16 *data = nla_data(attr);
-	spinlock_t *root_lock;
 	struct disttable *d;
 	int i;
 
@@ -793,13 +791,7 @@ static int get_dist_table(struct Qdisc *sch, struct disttable **tbl,
 	for (i = 0; i < n; i++)
 		d->table[i] = data[i];
 
-	root_lock = qdisc_root_sleeping_lock(sch);
+	*tbl = d;
-
-	spin_lock_bh(root_lock);
-	swap(*tbl, d);
-	spin_unlock_bh(root_lock);
-
-	dist_free(d);
 	return 0;
 }
 
@@ -956,6 +948,8 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt,
 {
 	struct netem_sched_data *q = qdisc_priv(sch);
 	struct nlattr *tb[TCA_NETEM_MAX + 1];
+	struct disttable *delay_dist = NULL;
+	struct disttable *slot_dist = NULL;
 	struct tc_netem_qopt *qopt;
 	struct clgstate old_clg;
 	int old_loss_model = CLG_RANDOM;
@@ -969,6 +963,18 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt,
 	if (ret < 0)
 		return ret;
 
+	if (tb[TCA_NETEM_DELAY_DIST]) {
+		ret = get_dist_table(&delay_dist, tb[TCA_NETEM_DELAY_DIST]);
+		if (ret)
+			goto table_free;
+	}
+
+	if (tb[TCA_NETEM_SLOT_DIST]) {
+		ret = get_dist_table(&slot_dist, tb[TCA_NETEM_SLOT_DIST]);
+		if (ret)
+			goto table_free;
+	}
+
 	sch_tree_lock(sch);
 	/* backup q->clg and q->loss_model */
 	old_clg = q->clg;
@@ -978,26 +984,17 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt,
 		ret = get_loss_clg(q, tb[TCA_NETEM_LOSS]);
 		if (ret) {
 			q->loss_model = old_loss_model;
+			q->clg = old_clg;
 			goto unlock;
 		}
 	} else {
 		q->loss_model = CLG_RANDOM;
 	}
 
-	if (tb[TCA_NETEM_DELAY_DIST]) {
+	if (delay_dist)
-		ret = get_dist_table(sch, &q->delay_dist,
+		swap(q->delay_dist, delay_dist);
-				     tb[TCA_NETEM_DELAY_DIST]);
+	if (slot_dist)
-		if (ret)
+		swap(q->slot_dist, slot_dist);
-			goto get_table_failure;
-	}
-
-	if (tb[TCA_NETEM_SLOT_DIST]) {
-		ret = get_dist_table(sch, &q->slot_dist,
-				     tb[TCA_NETEM_SLOT_DIST]);
-		if (ret)
-			goto get_table_failure;
-	}
-
 	sch->limit = qopt->limit;
 
 	q->latency = PSCHED_TICKS2NS(qopt->latency);
@@ -1047,17 +1044,11 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt,
 
 unlock:
 	sch_tree_unlock(sch);
+
+table_free:
+	dist_free(delay_dist);
+	dist_free(slot_dist);
 	return ret;
-
-get_table_failure:
-	/* recover clg and loss_model, in case of
-	 * q->clg and q->loss_model were modified
-	 * in get_loss_clg()
-	 */
-	q->clg = old_clg;
-	q->loss_model = old_loss_model;
-
-	goto unlock;
 }
 
 static int netem_init(struct Qdisc *sch, struct nlattr *opt,

tools/testing/radix-tree/regression1.c

@@ -177,7 +177,7 @@ void regression1_test(void)
 	nr_threads = 2;
 	pthread_barrier_init(&worker_barrier, NULL, nr_threads);
 
-	threads = malloc(nr_threads * sizeof(pthread_t *));
+	threads = malloc(nr_threads * sizeof(*threads));
 
 	for (i = 0; i < nr_threads; i++) {
 		arg = i;

tools/testing/selftests/bpf/prog_tests/align.c

@@ -2,7 +2,7 @@
 #include <test_progs.h>
 
 #define MAX_INSNS	512
-#define MAX_MATCHES	16
+#define MAX_MATCHES	24
 
 struct bpf_reg_match {
 	unsigned int line;
@@ -267,6 +267,7 @@ static struct bpf_align_test tests[] = {
 			 */
 			BPF_MOV64_REG(BPF_REG_5, BPF_REG_2),
 			BPF_ALU64_REG(BPF_ADD, BPF_REG_5, BPF_REG_6),
+			BPF_MOV64_REG(BPF_REG_4, BPF_REG_5),
 			BPF_ALU64_IMM(BPF_ADD, BPF_REG_5, 14),
 			BPF_MOV64_REG(BPF_REG_4, BPF_REG_5),
 			BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 4),
@@ -280,6 +281,7 @@ static struct bpf_align_test tests[] = {
 			BPF_MOV64_REG(BPF_REG_5, BPF_REG_2),
 			BPF_ALU64_IMM(BPF_ADD, BPF_REG_5, 14),
 			BPF_ALU64_REG(BPF_ADD, BPF_REG_5, BPF_REG_6),
+			BPF_MOV64_REG(BPF_REG_4, BPF_REG_5),
 			BPF_ALU64_IMM(BPF_ADD, BPF_REG_5, 4),
 			BPF_ALU64_REG(BPF_ADD, BPF_REG_5, BPF_REG_6),
 			BPF_MOV64_REG(BPF_REG_4, BPF_REG_5),
@@ -311,44 +313,52 @@ static struct bpf_align_test tests[] = {
 			{15, "R4=pkt(id=1,off=18,r=18,umax_value=1020,var_off=(0x0; 0x3fc))"},
 			{15, "R5=pkt(id=1,off=14,r=18,umax_value=1020,var_off=(0x0; 0x3fc))"},
 			/* Variable offset is added to R5 packet pointer,
-			 * resulting in auxiliary alignment of 4.
+			 * resulting in auxiliary alignment of 4. To avoid BPF
+			 * verifier's precision backtracking logging
+			 * interfering we also have a no-op R4 = R5
+			 * instruction to validate R5 state. We also check
+			 * that R4 is what it should be in such case.
 			 */
-			{18, "R5_w=pkt(id=2,off=0,r=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
+			{19, "R4_w=pkt(id=2,off=0,r=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
+			{19, "R5_w=pkt(id=2,off=0,r=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
 			/* Constant offset is added to R5, resulting in
 			 * reg->off of 14.
 			 */
-			{19, "R5_w=pkt(id=2,off=14,r=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
+			{20, "R5_w=pkt(id=2,off=14,r=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
 			/* At the time the word size load is performed from R5,
 			 * its total fixed offset is NET_IP_ALIGN + reg->off
 			 * (14) which is 16.  Then the variable offset is 4-byte
 			 * aligned, so the total offset is 4-byte aligned and
 			 * meets the load's requirements.
 			 */
-			{23, "R4=pkt(id=2,off=18,r=18,umax_value=1020,var_off=(0x0; 0x3fc))"},
+			{24, "R4=pkt(id=2,off=18,r=18,umax_value=1020,var_off=(0x0; 0x3fc))"},
-			{23, "R5=pkt(id=2,off=14,r=18,umax_value=1020,var_off=(0x0; 0x3fc))"},
+			{24, "R5=pkt(id=2,off=14,r=18,umax_value=1020,var_off=(0x0; 0x3fc))"},
 			/* Constant offset is added to R5 packet pointer,
 			 * resulting in reg->off value of 14.
 			 */
-			{26, "R5_w=pkt(id=0,off=14,r=8"},
+			{27, "R5_w=pkt(id=0,off=14,r=8"},
 			/* Variable offset is added to R5, resulting in a
-			 * variable offset of (4n).
+			 * variable offset of (4n). See comment for insn #19
+			 * for R4 = R5 trick.
 			 */
-			{27, "R5_w=pkt(id=3,off=14,r=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
+			{29, "R4_w=pkt(id=3,off=14,r=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
+			{29, "R5_w=pkt(id=3,off=14,r=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
 			/* Constant is added to R5 again, setting reg->off to 18. */
-			{28, "R5_w=pkt(id=3,off=18,r=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
+			{30, "R5_w=pkt(id=3,off=18,r=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
 			/* And once more we add a variable; resulting var_off
 			 * is still (4n), fixed offset is not changed.
 			 * Also, we create a new reg->id.
 			 */
-			{29, "R5_w=pkt(id=4,off=18,r=0,umax_value=2040,var_off=(0x0; 0x7fc)"},
+			{32, "R4_w=pkt(id=4,off=18,r=0,umax_value=2040,var_off=(0x0; 0x7fc)"},
+			{32, "R5_w=pkt(id=4,off=18,r=0,umax_value=2040,var_off=(0x0; 0x7fc)"},
 			/* At the time the word size load is performed from R5,
 			 * its total fixed offset is NET_IP_ALIGN + reg->off (18)
 			 * which is 20.  Then the variable offset is (4n), so
 			 * the total offset is 4-byte aligned and meets the
 			 * load's requirements.
 			 */
-			{33, "R4=pkt(id=4,off=22,r=22,umax_value=2040,var_off=(0x0; 0x7fc)"},
+			{35, "R4=pkt(id=4,off=22,r=22,umax_value=2040,var_off=(0x0; 0x7fc)"},
-			{33, "R5=pkt(id=4,off=18,r=22,umax_value=2040,var_off=(0x0; 0x7fc)"},
+			{35, "R5=pkt(id=4,off=18,r=22,umax_value=2040,var_off=(0x0; 0x7fc)"},
 		},
 	},
 	{

tools/testing/selftests/bpf/prog_tests/sk_assign.c

@@ -29,7 +29,23 @@ static int stop, duration;
 static bool
 configure_stack(void)
 {
+	char tc_version[128];
 	char tc_cmd[BUFSIZ];
+	char *prog;
+	FILE *tc;
+
+	/* Check whether tc is built with libbpf. */
+	tc = popen("tc -V", "r");
+	if (CHECK_FAIL(!tc))
+		return false;
+	if (CHECK_FAIL(!fgets(tc_version, sizeof(tc_version), tc)))
+		return false;
+	if (strstr(tc_version, ", libbpf "))
+		prog = "test_sk_assign_libbpf.o";
+	else
+		prog = "test_sk_assign.o";
+	if (CHECK_FAIL(pclose(tc)))
+		return false;
 
 	/* Move to a new networking namespace */
 	if (CHECK_FAIL(unshare(CLONE_NEWNET)))
@@ -46,8 +62,8 @@ configure_stack(void)
 	/* Load qdisc, BPF program */
 	if (CHECK_FAIL(system("tc qdisc add dev lo clsact")))
 		return false;
-	sprintf(tc_cmd, "%s %s %s %s", "tc filter add dev lo ingress bpf",
+	sprintf(tc_cmd, "%s %s %s %s %s", "tc filter add dev lo ingress bpf",
-		       "direct-action object-file ./test_sk_assign.o",
+		       "direct-action object-file", prog,
 		       "section classifier/sk_assign_test",
 		       (env.verbosity < VERBOSE_VERY) ? " 2>/dev/null" : "verbose");
 	if (CHECK(system(tc_cmd), "BPF load failed;",
@@ -129,15 +145,12 @@ get_port(int fd)
 static ssize_t
 rcv_msg(int srv_client, int type)
 {
-	struct sockaddr_storage ss;
 	char buf[BUFSIZ];
-	socklen_t slen;
 
 	if (type == SOCK_STREAM)
 		return read(srv_client, &buf, sizeof(buf));
 	else
-		return recvfrom(srv_client, &buf, sizeof(buf), 0,
+		return recvfrom(srv_client, &buf, sizeof(buf), 0, NULL, NULL);
-				(struct sockaddr *)&ss, &slen);
 }
 
 static int

tools/testing/selftests/bpf/progs/connect4_prog.c

@@ -33,7 +33,7 @@
 
 int _version SEC("version") = 1;
 
-__attribute__ ((noinline))
+__attribute__ ((noinline)) __weak
 int do_bind(struct bpf_sock_addr *ctx)
 {
 	struct sockaddr_in sa = {};

tools/testing/selftests/bpf/progs/test_sk_assign.c

@@ -16,6 +16,16 @@
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_endian.h>
 
+#if defined(IPROUTE2_HAVE_LIBBPF)
+/* Use a new-style map definition. */
+struct {
+	__uint(type, BPF_MAP_TYPE_SOCKMAP);
+	__type(key, int);
+	__type(value, __u64);
+	__uint(pinning, LIBBPF_PIN_BY_NAME);
+	__uint(max_entries, 1);
+} server_map SEC(".maps");
+#else
 /* Pin map under /sys/fs/bpf/tc/globals/<map name> */
 #define PIN_GLOBAL_NS 2
 
@@ -35,6 +45,7 @@ struct {
 	.max_elem = 1,
 	.pinning = PIN_GLOBAL_NS,
 };
+#endif
 
 int _version SEC("version") = 1;
 char _license[] SEC("license") = "GPL";

tools/testing/selftests/bpf/progs/test_sk_assign_libbpf.c

@@ -0,0 +1,3 @@
+// SPDX-License-Identifier: GPL-2.0
+#define IPROUTE2_HAVE_LIBBPF
+#include "test_sk_assign.c"

tools/testing/selftests/net/forwarding/ethtool.sh

@@ -286,6 +286,8 @@ different_speeds_autoneg_on()
 	ethtool -s $h1 autoneg on
 }
 
+skip_on_veth
+
 trap cleanup EXIT
 
 setup_prepare

tools/testing/selftests/net/forwarding/ethtool_extended_state.sh

@@ -95,6 +95,8 @@ no_cable()
 	ip link set dev $swp3 down
 }
 
+skip_on_veth
+
 setup_prepare
 
 tests_run

tools/testing/selftests/net/forwarding/lib.sh

@@ -69,6 +69,17 @@ check_tc_action_hw_stats_support()
 	fi
 }
 
+skip_on_veth()
+{
+	local kind=$(ip -j -d link show dev ${NETIFS[p1]} |
+		jq -r '.[].linkinfo.info_kind')
+
+	if [[ $kind == veth ]]; then
+		echo "SKIP: Test cannot be run with veth pairs"
+		exit $ksft_skip
+	fi
+}
+
 if [[ "$(id -u)" -ne 0 ]]; then
 	echo "SKIP: need root privileges"
 	exit 0
@@ -121,6 +132,11 @@ create_netif_veth()
 	for ((i = 1; i <= NUM_NETIFS; ++i)); do
 		local j=$((i+1))
 
+		if [ -z ${NETIFS[p$i]} ]; then
+			echo "SKIP: Cannot create interface. Name not specified"
+			exit $ksft_skip
+		fi
+
 		ip link show dev ${NETIFS[p$i]} &> /dev/null
 		if [[ $? -ne 0 ]]; then
 			ip link add ${NETIFS[p$i]} type veth \

tools/testing/selftests/net/forwarding/settings

@@ -0,0 +1 @@
+timeout=0

tools/testing/selftests/net/forwarding/tc_flower.sh

@@ -49,8 +49,8 @@ match_dst_mac_test()
 	tc_check_packets "dev $h2 ingress" 101 1
 	check_fail $? "Matched on a wrong filter"
 
-	tc_check_packets "dev $h2 ingress" 102 1
+	tc_check_packets "dev $h2 ingress" 102 0
-	check_err $? "Did not match on correct filter"
+	check_fail $? "Did not match on correct filter"
 
 	tc filter del dev $h2 ingress protocol ip pref 1 handle 101 flower
 	tc filter del dev $h2 ingress protocol ip pref 2 handle 102 flower
@@ -75,8 +75,8 @@ match_src_mac_test()
 	tc_check_packets "dev $h2 ingress" 101 1
 	check_fail $? "Matched on a wrong filter"
 
-	tc_check_packets "dev $h2 ingress" 102 1
+	tc_check_packets "dev $h2 ingress" 102 0
-	check_err $? "Did not match on correct filter"
+	check_fail $? "Did not match on correct filter"
 
 	tc filter del dev $h2 ingress protocol ip pref 1 handle 101 flower
 	tc filter del dev $h2 ingress protocol ip pref 2 handle 102 flower

tools/testing/selftests/rseq/Makefile

@@ -4,8 +4,10 @@ ifneq ($(shell $(CC) --version 2>&1 | head -n 1 | grep clang),)
 CLANG_FLAGS += -no-integrated-as
 endif
 
+top_srcdir = ../../../..
+
 CFLAGS += -O2 -Wall -g -I./ -I../../../../usr/include/ -L$(OUTPUT) -Wl,-rpath=./ \
-	  $(CLANG_FLAGS)
+	  $(CLANG_FLAGS) -I$(top_srcdir)/tools/include
 LDLIBS += -lpthread -ldl
 
 # Own dependencies because we only want to build against 1st prerequisite, but

tools/testing/selftests/rseq/rseq.c

@@ -29,6 +29,8 @@
 #include <dlfcn.h>
 #include <stddef.h>
 
+#include <linux/compiler.h>
+
 #include "../kselftest.h"
 #include "rseq.h"