Merge 5.15.64 into android14-5.15

Changes in 5.15.64
	wifi: rtlwifi: remove always-true condition pointed out by GCC 12
	eth: sun: cassini: remove dead code
	audit: fix potential double free on error path from fsnotify_add_inode_mark
	cgroup: Fix race condition at rebind_subsystems()
	parisc: Make CONFIG_64BIT available for ARCH=parisc64 only
	parisc: Fix exception handler for fldw and fstw instructions
	kernel/sys_ni: add compat entry for fadvise64_64
	x86/entry: Move CLD to the start of the idtentry macro
	block: add a bdev_max_zone_append_sectors helper
	block: add bdev_max_segments() helper
	btrfs: zoned: revive max_zone_append_bytes
	btrfs: replace BTRFS_MAX_EXTENT_SIZE with fs_info->max_extent_size
	btrfs: convert count_max_extents() to use fs_info->max_extent_size
	Input: i8042 - move __initconst to fix code styling warning
	Input: i8042 - merge quirk tables
	Input: i8042 - add TUXEDO devices to i8042 quirk tables
	Input: i8042 - add additional TUXEDO devices to i8042 quirk tables
	drivers/base: fix userspace break from using bin_attributes for cpumap and cpulist
	scsi: qla2xxx: Fix response queue handler reading stale packets
	scsi: qla2xxx: edif: Fix dropped IKE message
	btrfs: put initial index value of a directory in a constant
	btrfs: pass the dentry to btrfs_log_new_name() instead of the inode
	btrfs: remove unnecessary parameter delalloc_start for writepage_delalloc()
	riscv: lib: uaccess: fold fixups into body
	riscv: lib: uaccess: fix CSR_STATUS SR_SUM bit
	xfrm: fix refcount leak in __xfrm_policy_check()
	xfrm: clone missing x->lastused in xfrm_do_migrate
	af_key: Do not call xfrm_probe_algs in parallel
	xfrm: policy: fix metadata dst->dev xmit null pointer dereference
	fs: require CAP_SYS_ADMIN in target namespace for idmapped mounts
	net: use eth_hw_addr_set() instead of ether_addr_copy()
	Revert "net: macsec: update SCI upon MAC address change."
	NFS: Don't allocate nfs_fattr on the stack in __nfs42_ssc_open()
	NFSv4.2 fix problems with __nfs42_ssc_open
	SUNRPC: RPC level errors should set task->tk_rpc_status
	mm/smaps: don't access young/dirty bit if pte unpresent
	ntfs: fix acl handling
	rose: check NULL rose_loopback_neigh->loopback
	r8152: fix the units of some registers for RTL8156A
	r8152: fix the RX FIFO settings when suspending
	nfc: pn533: Fix use-after-free bugs caused by pn532_cmd_timeout
	ice: xsk: Force rings to be sized to power of 2
	ice: xsk: prohibit usage of non-balanced queue id
	net/mlx5e: Properly disable vlan strip on non-UL reps
	net/mlx5: Avoid false positive lockdep warning by adding lock_class_key
	net/mlx5e: Fix wrong application of the LRO state
	net/mlx5e: Fix wrong tc flag used when set hw-tc-offload off
	net: ipa: don't assume SMEM is page-aligned
	net: phy: Don't WARN for PHY_READY state in mdio_bus_phy_resume()
	net: moxa: get rid of asymmetry in DMA mapping/unmapping
	bonding: 802.3ad: fix no transmission of LACPDUs
	net: ipvtap - add __init/__exit annotations to module init/exit funcs
	netfilter: ebtables: reject blobs that don't provide all entry points
	bnxt_en: fix NQ resource accounting during vf creation on 57500 chips
	netfilter: nf_tables: disallow updates of implicit chain
	netfilter: nf_tables: make table handle allocation per-netns friendly
	netfilter: nft_payload: report ERANGE for too long offset and length
	netfilter: nft_payload: do not truncate csum_offset and csum_type
	netfilter: nf_tables: do not leave chain stats enabled on error
	netfilter: nft_osf: restrict osf to ipv4, ipv6 and inet families
	netfilter: nft_tunnel: restrict it to netdev family
	netfilter: nf_tables: consolidate rule verdict trace call
	netfilter: nft_cmp: optimize comparison for 16-bytes
	netfilter: bitwise: improve error goto labels
	netfilter: nf_tables: upfront validation of data via nft_data_init()
	netfilter: nf_tables: disallow jump to implicit chain from set element
	netfilter: nf_tables: disallow binding to already bound chain
	netfilter: flowtable: add function to invoke garbage collection immediately
	netfilter: flowtable: fix stuck flows on cleanup due to pending work
	net: Fix data-races around sysctl_[rw]mem_(max|default).
	net: Fix data-races around weight_p and dev_weight_[rt]x_bias.
	net: Fix data-races around netdev_max_backlog.
	net: Fix data-races around netdev_tstamp_prequeue.
	ratelimit: Fix data-races in ___ratelimit().
	net: Fix data-races around sysctl_optmem_max.
	net: Fix a data-race around sysctl_tstamp_allow_data.
	net: Fix a data-race around sysctl_net_busy_poll.
	net: Fix a data-race around sysctl_net_busy_read.
	net: Fix a data-race around netdev_budget.
	tcp: expose the tcp_mark_push() and tcp_skb_entail() helpers
	mptcp: stop relying on tcp_tx_skb_cache
	net: Fix data-races around sysctl_max_skb_frags.
	net: Fix a data-race around netdev_budget_usecs.
	net: Fix data-races around sysctl_fb_tunnels_only_for_init_net.
	net: Fix data-races around sysctl_devconf_inherit_init_net.
	net: Fix a data-race around sysctl_somaxconn.
	ixgbe: stop resetting SYSTIME in ixgbe_ptp_start_cyclecounter
	i40e: Fix incorrect address type for IPv6 flow rules
	rxrpc: Fix locking in rxrpc's sendmsg
	ionic: widen queue_lock use around lif init and deinit
	ionic: clear broken state on generation change
	ionic: fix up issues with handling EAGAIN on FW cmds
	ionic: VF initial random MAC address if no assigned mac
	net: stmmac: work around sporadic tx issue on link-up
	btrfs: fix silent failure when deleting root reference
	btrfs: replace: drop assert for suspended replace
	btrfs: add info when mount fails due to stale replace target
	btrfs: check if root is readonly while setting security xattr
	btrfs: fix possible memory leak in btrfs_get_dev_args_from_path()
	perf/x86/lbr: Enable the branch type for the Arch LBR by default
	x86/unwind/orc: Unwind ftrace trampolines with correct ORC entry
	x86/bugs: Add "unknown" reporting for MMIO Stale Data
	x86/nospec: Unwreck the RSB stuffing
	loop: Check for overflow while configuring loop
	writeback: avoid use-after-free after removing device
	asm-generic: sections: refactor memory_intersects
	mm/damon/dbgfs: avoid duplicate context directory creation
	s390/mm: do not trigger write fault when vma does not allow VM_WRITE
	bootmem: remove the vmemmap pages from kmemleak in put_page_bootmem
	s390: fix double free of GS and RI CBs on fork() failure
	fbdev: fbcon: Properly revert changes when vc_resize() failed
	Revert "memcg: cleanup racy sum avoidance code"
	ACPI: processor: Remove freq Qos request for all CPUs
	nouveau: explicitly wait on the fence in nouveau_bo_move_m2mf
	smb3: missing inode locks in punch hole
	xen/privcmd: fix error exit of privcmd_ioctl_dm_op()
	riscv: traps: add missing prototype
	io_uring: fix issue with io_write() not always undoing sb_start_write()
	Revert "usbnet: smsc95xx: Fix deadlock on runtime resume"
	Revert "usbnet: smsc95xx: Forward PHY interrupts to PHY driver to avoid polling"
	mm/hugetlb: fix hugetlb not supporting softdirty tracking
	Revert "md-raid: destroy the bitmap after destroying the thread"
	md: call __md_stop_writes in md_stop
	mptcp: Fix crash due to tcp_tsorted_anchor was initialized before release skb
	arm64: Fix match_list for erratum 1286807 on Arm Cortex-A76
	binder_alloc: add missing mmap_lock calls when using the VMA
	x86/nospec: Fix i386 RSB stuffing
	Documentation/ABI: Mention retbleed vulnerability info file for sysfs
	blk-mq: fix io hung due to missing commit_rqs
	perf python: Fix build when PYTHON_CONFIG is user supplied
	perf/x86/intel/uncore: Fix broken read_counter() for SNB IMC PMU
	perf/x86/intel/ds: Fix precise store latency handling
	perf stat: Clear evsel->reset_group for each stat run
	scsi: ufs: core: Enable link lost interrupt
	scsi: storvsc: Remove WQ_MEM_RECLAIM from storvsc_error_wq
	bpf: Don't use tnum_range on array range checking for poke descriptors
	Linux 5.15.64

Signed-off-by: Greg Kroah-Hartman <gregkh@google.com>
Change-Id: I8e4d8a8ed90e22487e249b9635b210935febda6e

Documentation/ABI/testing/sysfs-devices-system-cpu

@@ -521,6 +521,7 @@ What:		/sys/devices/system/cpu/vulnerabilities
 		/sys/devices/system/cpu/vulnerabilities/tsx_async_abort
 		/sys/devices/system/cpu/vulnerabilities/itlb_multihit
 		/sys/devices/system/cpu/vulnerabilities/mmio_stale_data
+		/sys/devices/system/cpu/vulnerabilities/retbleed
 Date:		January 2018
 Contact:	Linux kernel mailing list <linux-kernel@vger.kernel.org>
 Description:	Information about CPU vulnerabilities

Documentation/admin-guide/hw-vuln/processor_mmio_stale_data.rst

@@ -230,6 +230,20 @@ The possible values in this file are:
      * - 'Mitigation: Clear CPU buffers'
        - The processor is vulnerable and the CPU buffer clearing mitigation is
          enabled.
+     * - 'Unknown: No mitigations'
+       - The processor vulnerability status is unknown because it is
+	 out of Servicing period. Mitigation is not attempted.
+
+Definitions:
+------------
+
+Servicing period: The process of providing functional and security updates to
+Intel processors or platforms, utilizing the Intel Platform Update (IPU)
+process or other similar mechanisms.
+
+End of Servicing Updates (ESU): ESU is the date at which Intel will no
+longer provide Servicing, such as through IPU or other similar update
+processes. ESU dates will typically be aligned to end of quarter.
 
 If the processor is vulnerable then the following information is appended to
 the above information:

Documentation/admin-guide/sysctl/net.rst

@@ -271,7 +271,7 @@ poll cycle or the number of packets processed reaches netdev_budget.
 netdev_max_backlog
 ------------------
 
-Maximum number  of  packets,  queued  on  the  INPUT  side, when the interface
+Maximum number of packets, queued on the INPUT side, when the interface
 receives packets faster than kernel can process them.
 
 netdev_rss_key

Makefile

@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 VERSION = 5
 PATCHLEVEL = 15
-SUBLEVEL = 63
+SUBLEVEL = 64
 EXTRAVERSION =
 NAME = Trick or Treat
 

arch/arm64/kernel/cpu_errata.c

@@ -208,6 +208,8 @@ static const struct arm64_cpu_capabilities arm64_repeat_tlbi_list[] = {
 #ifdef CONFIG_ARM64_ERRATUM_1286807
 	{
 		ERRATA_MIDR_RANGE(MIDR_CORTEX_A76, 0, 0, 3, 0),
+	},
+	{
 		/* Kryo4xx Gold (rcpe to rfpe) => (r0p0 to r3p0) */
 		ERRATA_MIDR_RANGE(MIDR_QCOM_KRYO_4XX_GOLD, 0xc, 0xe, 0xf, 0xe),
 	},

arch/parisc/Kconfig

@@ -142,10 +142,10 @@ menu "Processor type and features"
 
 choice
 	prompt "Processor type"
-	default PA7000
+	default PA7000 if "$(ARCH)" = "parisc"
 
 config PA7000
-	bool "PA7000/PA7100"
+	bool "PA7000/PA7100" if "$(ARCH)" = "parisc"
 	help
 	  This is the processor type of your CPU.  This information is
 	  used for optimizing purposes.  In order to compile a kernel
@@ -156,21 +156,21 @@ config PA7000
 	  which is required on some machines.
 
 config PA7100LC
-	bool "PA7100LC"
+	bool "PA7100LC" if "$(ARCH)" = "parisc"
 	help
 	  Select this option for the PCX-L processor, as used in the
 	  712, 715/64, 715/80, 715/100, 715/100XC, 725/100, 743, 748,
 	  D200, D210, D300, D310 and E-class
 
 config PA7200
-	bool "PA7200"
+	bool "PA7200" if "$(ARCH)" = "parisc"
 	help
 	  Select this option for the PCX-T' processor, as used in the
 	  C100, C110, J100, J110, J210XC, D250, D260, D350, D360,
 	  K100, K200, K210, K220, K400, K410 and K420
 
 config PA7300LC
-	bool "PA7300LC"
+	bool "PA7300LC" if "$(ARCH)" = "parisc"
 	help
 	  Select this option for the PCX-L2 processor, as used in the
 	  744, A180, B132L, B160L, B180L, C132L, C160L, C180L,
@@ -220,17 +220,8 @@ config MLONGCALLS
 	  Enabling this option will probably slow down your kernel.
 
 config 64BIT
-	bool "64-bit kernel"
+	def_bool "$(ARCH)" = "parisc64"
 	depends on PA8X00
-	help
-	  Enable this if you want to support 64bit kernel on PA-RISC platform.
-
-	  At the moment, only people willing to use more than 2GB of RAM,
-	  or having a 64bit-only capable PA-RISC machine should say Y here.
-
-	  Since there is no 64bit userland on PA-RISC, there is no point to
-	  enable this option otherwise. The 64bit kernel is significantly bigger
-	  and slower than the 32bit one.
 
 choice
 	prompt "Kernel page size"

arch/parisc/kernel/unaligned.c

@@ -107,7 +107,7 @@
 #define R1(i) (((i)>>21)&0x1f)
 #define R2(i) (((i)>>16)&0x1f)
 #define R3(i) ((i)&0x1f)
-#define FR3(i) ((((i)<<1)&0x1f)|(((i)>>6)&1))
+#define FR3(i) ((((i)&0x1f)<<1)|(((i)>>6)&1))
 #define IM(i,n) (((i)>>1&((1<<(n-1))-1))|((i)&1?((0-1L)<<(n-1)):0))
 #define IM5_2(i) IM((i)>>16,5)
 #define IM5_3(i) IM((i),5)

arch/riscv/include/asm/thread_info.h

@@ -42,6 +42,8 @@
 
 #ifndef __ASSEMBLY__
 
+extern long shadow_stack[SHADOW_OVERFLOW_STACK_SIZE / sizeof(long)];
+
 #include <asm/processor.h>
 #include <asm/csr.h>
 

arch/riscv/kernel/traps.c

@@ -20,9 +20,10 @@
 
 #include <asm/asm-prototypes.h>
 #include <asm/bug.h>
+#include <asm/csr.h>
 #include <asm/processor.h>
 #include <asm/ptrace.h>
-#include <asm/csr.h>
+#include <asm/thread_info.h>
 
 int show_unhandled_signals = 1;
 

arch/riscv/lib/uaccess.S

@@ -173,6 +173,13 @@ ENTRY(__asm_copy_from_user)
 	csrc CSR_STATUS, t6
 	li	a0, 0
 	ret
+
+	/* Exception fixup code */
+10:
+	/* Disable access to user memory */
+	csrc CSR_STATUS, t6
+	mv a0, t5
+	ret
 ENDPROC(__asm_copy_to_user)
 ENDPROC(__asm_copy_from_user)
 EXPORT_SYMBOL(__asm_copy_to_user)
@@ -218,19 +225,12 @@ ENTRY(__clear_user)
 	addi a0, a0, 1
 	bltu a0, a3, 5b
 	j 3b
-ENDPROC(__clear_user)
-EXPORT_SYMBOL(__clear_user)
 
-	.section .fixup,"ax"
-	.balign 4
-	/* Fixup code for __copy_user(10) and __clear_user(11) */
-10:
-	/* Disable access to user memory */
-	csrs CSR_STATUS, t6
-	mv a0, t5
-	ret
+	/* Exception fixup code */
 11:
-	csrs CSR_STATUS, t6
+	/* Disable access to user memory */
+	csrc CSR_STATUS, t6
 	mv a0, a1
 	ret
-	.previous
+ENDPROC(__clear_user)
+EXPORT_SYMBOL(__clear_user)

arch/s390/kernel/process.c

@@ -91,6 +91,18 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 
 	memcpy(dst, src, arch_task_struct_size);
 	dst->thread.fpu.regs = dst->thread.fpu.fprs;
+
+	/*
+	 * Don't transfer over the runtime instrumentation or the guarded
+	 * storage control block pointers. These fields are cleared here instead
+	 * of in copy_thread() to avoid premature freeing of associated memory
+	 * on fork() failure. Wait to clear the RI flag because ->stack still
+	 * refers to the source thread.
+	 */
+	dst->thread.ri_cb = NULL;
+	dst->thread.gs_cb = NULL;
+	dst->thread.gs_bc_cb = NULL;
+
 	return 0;
 }
 
@@ -149,13 +161,11 @@ int copy_thread(unsigned long clone_flags, unsigned long new_stackp,
 	frame->childregs.flags = 0;
 	if (new_stackp)
 		frame->childregs.gprs[15] = new_stackp;
-
-	/* Don't copy runtime instrumentation info */
-	p->thread.ri_cb = NULL;
+	/*
+	 * Clear the runtime instrumentation flag after the above childregs
+	 * copy. The CB pointer was already cleared in arch_dup_task_struct().
+	 */
 	frame->childregs.psw.mask &= ~PSW_MASK_RI;
-	/* Don't copy guarded storage control block */
-	p->thread.gs_cb = NULL;
-	p->thread.gs_bc_cb = NULL;
 
 	/* Set a new TLS ?  */
 	if (clone_flags & CLONE_SETTLS) {

arch/s390/mm/fault.c

@@ -397,7 +397,9 @@ static inline vm_fault_t do_exception(struct pt_regs *regs, int access)
 	flags = FAULT_FLAG_DEFAULT;
 	if (user_mode(regs))
 		flags |= FAULT_FLAG_USER;
-	if (access == VM_WRITE || is_write)
+	if (is_write)
+		access = VM_WRITE;
+	if (access == VM_WRITE)
 		flags |= FAULT_FLAG_WRITE;
 	mmap_read_lock(mm);
 

arch/x86/entry/entry_64.S

@@ -373,6 +373,7 @@ SYM_CODE_END(xen_error_entry)
 SYM_CODE_START(\asmsym)
 	UNWIND_HINT_IRET_REGS offset=\has_error_code*8
 	ASM_CLAC
+	cld
 
 	.if \has_error_code == 0
 		pushq	$-1			/* ORIG_RAX: no syscall to restart */
@@ -440,6 +441,7 @@ SYM_CODE_END(\asmsym)
 SYM_CODE_START(\asmsym)
 	UNWIND_HINT_IRET_REGS
 	ASM_CLAC
+	cld
 
 	pushq	$-1			/* ORIG_RAX: no syscall to restart */
 
@@ -495,6 +497,7 @@ SYM_CODE_END(\asmsym)
 SYM_CODE_START(\asmsym)
 	UNWIND_HINT_IRET_REGS
 	ASM_CLAC
+	cld
 
 	/*
 	 * If the entry is from userspace, switch stacks and treat it as
@@ -557,6 +560,7 @@ SYM_CODE_END(\asmsym)
 SYM_CODE_START(\asmsym)
 	UNWIND_HINT_IRET_REGS offset=8
 	ASM_CLAC
+	cld
 
 	/* paranoid_entry returns GS information for paranoid_exit in EBX. */
 	call	paranoid_entry
@@ -876,7 +880,6 @@ SYM_CODE_END(xen_failsafe_callback)
  */
 SYM_CODE_START_LOCAL(paranoid_entry)
 	UNWIND_HINT_FUNC
-	cld
 	PUSH_AND_CLEAR_REGS save_ret=1
 	ENCODE_FRAME_POINTER 8
 
@@ -1012,7 +1015,6 @@ SYM_CODE_END(paranoid_exit)
  */
 SYM_CODE_START_LOCAL(error_entry)
 	UNWIND_HINT_FUNC
-	cld
 
 	PUSH_AND_CLEAR_REGS save_ret=1
 	ENCODE_FRAME_POINTER 8
@@ -1155,6 +1157,7 @@ SYM_CODE_START(asm_exc_nmi)
 	 */
 
 	ASM_CLAC
+	cld
 
 	/* Use %rdx as our temp variable throughout */
 	pushq	%rdx
@@ -1174,7 +1177,6 @@ SYM_CODE_START(asm_exc_nmi)
 	 */
 
 	swapgs
-	cld
 	FENCE_SWAPGS_USER_ENTRY
 	SWITCH_TO_KERNEL_CR3 scratch_reg=%rdx
 	movq	%rsp, %rdx

arch/x86/events/intel/ds.c

@@ -236,6 +236,7 @@ static u64 load_latency_data(u64 status)
 static u64 store_latency_data(u64 status)
 {
 	union intel_x86_pebs_dse dse;
+	union perf_mem_data_src src;
 	u64 val;
 
 	dse.val = status;
@@ -263,7 +264,14 @@ static u64 store_latency_data(u64 status)
 
 	val |= P(BLK, NA);
 
-	return val;
+	/*
+	 * the pebs_data_source table is only for loads
+	 * so override the mem_op to say STORE instead
+	 */
+	src.val = val;
+	src.mem_op = P(OP,STORE);
+
+	return src.val;
 }
 
 struct pebs_record_core {

arch/x86/events/intel/lbr.c

@@ -1114,6 +1114,14 @@ static int intel_pmu_setup_hw_lbr_filter(struct perf_event *event)
 
 	if (static_cpu_has(X86_FEATURE_ARCH_LBR)) {
 		reg->config = mask;
+
+		/*
+		 * The Arch LBR HW can retrieve the common branch types
+		 * from the LBR_INFO. It doesn't require the high overhead
+		 * SW disassemble.
+		 * Enable the branch type by default for the Arch LBR.
+		 */
+		reg->reg |= X86_BR_TYPE_SAVE;
 		return 0;
 	}
 

arch/x86/events/intel/uncore_snb.c

@@ -788,6 +788,22 @@ int snb_pci2phy_map_init(int devid)
 	return 0;
 }
 
+static u64 snb_uncore_imc_read_counter(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+
+	/*
+	 * SNB IMC counters are 32-bit and are laid out back to back
+	 * in MMIO space. Therefore we must use a 32-bit accessor function
+	 * using readq() from uncore_mmio_read_counter() causes problems
+	 * because it is reading 64-bit at a time. This is okay for the
+	 * uncore_perf_event_update() function because it drops the upper
+	 * 32-bits but not okay for plain uncore_read_counter() as invoked
+	 * in uncore_pmu_event_start().
+	 */
+	return (u64)readl(box->io_addr + hwc->event_base);
+}
+
 static struct pmu snb_uncore_imc_pmu = {
 	.task_ctx_nr	= perf_invalid_context,
 	.event_init	= snb_uncore_imc_event_init,
@@ -807,7 +823,7 @@ static struct intel_uncore_ops snb_uncore_imc_ops = {
 	.disable_event	= snb_uncore_imc_disable_event,
 	.enable_event	= snb_uncore_imc_enable_event,
 	.hw_config	= snb_uncore_imc_hw_config,
-	.read_counter	= uncore_mmio_read_counter,
+	.read_counter	= snb_uncore_imc_read_counter,
 };
 
 static struct intel_uncore_type snb_uncore_imc = {

arch/x86/include/asm/cpufeatures.h

@@ -446,7 +446,8 @@
 #define X86_BUG_ITLB_MULTIHIT		X86_BUG(23) /* CPU may incur MCE during certain page attribute changes */
 #define X86_BUG_SRBDS			X86_BUG(24) /* CPU may leak RNG bits if not mitigated */
 #define X86_BUG_MMIO_STALE_DATA		X86_BUG(25) /* CPU is affected by Processor MMIO Stale Data vulnerabilities */
-#define X86_BUG_RETBLEED		X86_BUG(26) /* CPU is affected by RETBleed */
-#define X86_BUG_EIBRS_PBRSB		X86_BUG(27) /* EIBRS is vulnerable to Post Barrier RSB Predictions */
+#define X86_BUG_MMIO_UNKNOWN		X86_BUG(26) /* CPU is too old and its MMIO Stale Data status is unknown */
+#define X86_BUG_RETBLEED		X86_BUG(27) /* CPU is affected by RETBleed */
+#define X86_BUG_EIBRS_PBRSB		X86_BUG(28) /* EIBRS is vulnerable to Post Barrier RSB Predictions */
 
 #endif /* _ASM_X86_CPUFEATURES_H */

arch/x86/include/asm/nospec-branch.h

@@ -35,33 +35,56 @@
 #define RSB_CLEAR_LOOPS		32	/* To forcibly overwrite all entries */
 
 /*
+ * Common helper for __FILL_RETURN_BUFFER and __FILL_ONE_RETURN.
+ */
+#define __FILL_RETURN_SLOT			\
+	ANNOTATE_INTRA_FUNCTION_CALL;		\
+	call	772f;				\
+	int3;					\
+772:
+
+/*
+ * Stuff the entire RSB.
+ *
  * Google experimented with loop-unrolling and this turned out to be
  * the optimal version - two calls, each with their own speculation
  * trap should their return address end up getting used, in a loop.
  */
-#define __FILL_RETURN_BUFFER(reg, nr, sp)	\
-	mov	$(nr/2), reg;			\
-771:						\
-	ANNOTATE_INTRA_FUNCTION_CALL;		\
-	call	772f;				\
-773:	/* speculation trap */			\
-	UNWIND_HINT_EMPTY;			\
-	pause;					\
-	lfence;					\
-	jmp	773b;				\
-772:						\
-	ANNOTATE_INTRA_FUNCTION_CALL;		\
-	call	774f;				\
-775:	/* speculation trap */			\
-	UNWIND_HINT_EMPTY;			\
-	pause;					\
-	lfence;					\
-	jmp	775b;				\
-774:						\
-	add	$(BITS_PER_LONG/8) * 2, sp;	\
-	dec	reg;				\
-	jnz	771b;				\
-	/* barrier for jnz misprediction */	\
+#ifdef CONFIG_X86_64
+#define __FILL_RETURN_BUFFER(reg, nr)			\
+	mov	$(nr/2), reg;				\
+771:							\
+	__FILL_RETURN_SLOT				\
+	__FILL_RETURN_SLOT				\
+	add	$(BITS_PER_LONG/8) * 2, %_ASM_SP;	\
+	dec	reg;					\
+	jnz	771b;					\
+	/* barrier for jnz misprediction */		\
+	lfence;
+#else
+/*
+ * i386 doesn't unconditionally have LFENCE, as such it can't
+ * do a loop.
+ */
+#define __FILL_RETURN_BUFFER(reg, nr)			\
+	.rept nr;					\
+	__FILL_RETURN_SLOT;				\
+	.endr;						\
+	add	$(BITS_PER_LONG/8) * nr, %_ASM_SP;
+#endif
+
+/*
+ * Stuff a single RSB slot.
+ *
+ * To mitigate Post-Barrier RSB speculation, one CALL instruction must be
+ * forced to retire before letting a RET instruction execute.
+ *
+ * On PBRSB-vulnerable CPUs, it is not safe for a RET to be executed
+ * before this point.
+ */
+#define __FILL_ONE_RETURN				\
+	__FILL_RETURN_SLOT				\
+	add	$(BITS_PER_LONG/8), %_ASM_SP;		\
 	lfence;
 
 #ifdef __ASSEMBLY__
@@ -120,28 +143,15 @@
 #endif
 .endm
 
-.macro ISSUE_UNBALANCED_RET_GUARD
-	ANNOTATE_INTRA_FUNCTION_CALL
-	call .Lunbalanced_ret_guard_\@
-	int3
-.Lunbalanced_ret_guard_\@:
-	add $(BITS_PER_LONG/8), %_ASM_SP
-	lfence
-.endm
-
  /*
   * A simpler FILL_RETURN_BUFFER macro. Don't make people use the CPP
   * monstrosity above, manually.
   */
-.macro FILL_RETURN_BUFFER reg:req nr:req ftr:req ftr2
-.ifb \ftr2
-	ALTERNATIVE "jmp .Lskip_rsb_\@", "", \ftr
-.else
-	ALTERNATIVE_2 "jmp .Lskip_rsb_\@", "", \ftr, "jmp .Lunbalanced_\@", \ftr2
-.endif
-	__FILL_RETURN_BUFFER(\reg,\nr,%_ASM_SP)
-.Lunbalanced_\@:
-	ISSUE_UNBALANCED_RET_GUARD
+.macro FILL_RETURN_BUFFER reg:req nr:req ftr:req ftr2=ALT_NOT(X86_FEATURE_ALWAYS)
+	ALTERNATIVE_2 "jmp .Lskip_rsb_\@", \
+		__stringify(__FILL_RETURN_BUFFER(\reg,\nr)), \ftr, \
+		__stringify(__FILL_ONE_RETURN), \ftr2
+
 .Lskip_rsb_\@:
 .endm
 

arch/x86/kernel/cpu/bugs.c

@@ -433,7 +433,8 @@ static void __init mmio_select_mitigation(void)
 	u64 ia32_cap;
 
 	if (!boot_cpu_has_bug(X86_BUG_MMIO_STALE_DATA) ||
-	    cpu_mitigations_off()) {
+	     boot_cpu_has_bug(X86_BUG_MMIO_UNKNOWN) ||
+	     cpu_mitigations_off()) {
 		mmio_mitigation = MMIO_MITIGATION_OFF;
 		return;
 	}
@@ -538,6 +539,8 @@ out:
 		pr_info("TAA: %s\n", taa_strings[taa_mitigation]);
 	if (boot_cpu_has_bug(X86_BUG_MMIO_STALE_DATA))
 		pr_info("MMIO Stale Data: %s\n", mmio_strings[mmio_mitigation]);
+	else if (boot_cpu_has_bug(X86_BUG_MMIO_UNKNOWN))
+		pr_info("MMIO Stale Data: Unknown: No mitigations\n");
 }
 
 static void __init md_clear_select_mitigation(void)
@@ -2268,6 +2271,9 @@ static ssize_t tsx_async_abort_show_state(char *buf)
 
 static ssize_t mmio_stale_data_show_state(char *buf)
 {
+	if (boot_cpu_has_bug(X86_BUG_MMIO_UNKNOWN))
+		return sysfs_emit(buf, "Unknown: No mitigations\n");
+
 	if (mmio_mitigation == MMIO_MITIGATION_OFF)
 		return sysfs_emit(buf, "%s\n", mmio_strings[mmio_mitigation]);
 
@@ -2414,6 +2420,7 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr
 		return srbds_show_state(buf);
 
 	case X86_BUG_MMIO_STALE_DATA:
+	case X86_BUG_MMIO_UNKNOWN:
 		return mmio_stale_data_show_state(buf);
 
 	case X86_BUG_RETBLEED:
@@ -2473,7 +2480,10 @@ ssize_t cpu_show_srbds(struct device *dev, struct device_attribute *attr, char *
 
 ssize_t cpu_show_mmio_stale_data(struct device *dev, struct device_attribute *attr, char *buf)
 {
-	return cpu_show_common(dev, attr, buf, X86_BUG_MMIO_STALE_DATA);
+	if (boot_cpu_has_bug(X86_BUG_MMIO_UNKNOWN))
+		return cpu_show_common(dev, attr, buf, X86_BUG_MMIO_UNKNOWN);
+	else
+		return cpu_show_common(dev, attr, buf, X86_BUG_MMIO_STALE_DATA);
 }
 
 ssize_t cpu_show_retbleed(struct device *dev, struct device_attribute *attr, char *buf)

arch/x86/kernel/cpu/common.c

@@ -1027,7 +1027,8 @@ static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c)
 #define NO_SWAPGS		BIT(6)
 #define NO_ITLB_MULTIHIT	BIT(7)
 #define NO_SPECTRE_V2		BIT(8)
-#define NO_EIBRS_PBRSB		BIT(9)
+#define NO_MMIO			BIT(9)
+#define NO_EIBRS_PBRSB		BIT(10)
 
 #define VULNWL(vendor, family, model, whitelist)	\
 	X86_MATCH_VENDOR_FAM_MODEL(vendor, family, model, whitelist)
@@ -1048,6 +1049,11 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = {
 	VULNWL(NSC,	5, X86_MODEL_ANY,	NO_SPECULATION),
 
 	/* Intel Family 6 */
+	VULNWL_INTEL(TIGERLAKE,			NO_MMIO),
+	VULNWL_INTEL(TIGERLAKE_L,		NO_MMIO),
+	VULNWL_INTEL(ALDERLAKE,			NO_MMIO),
+	VULNWL_INTEL(ALDERLAKE_L,		NO_MMIO),
+
 	VULNWL_INTEL(ATOM_SALTWELL,		NO_SPECULATION | NO_ITLB_MULTIHIT),
 	VULNWL_INTEL(ATOM_SALTWELL_TABLET,	NO_SPECULATION | NO_ITLB_MULTIHIT),
 	VULNWL_INTEL(ATOM_SALTWELL_MID,		NO_SPECULATION | NO_ITLB_MULTIHIT),
@@ -1066,9 +1072,9 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = {
 	VULNWL_INTEL(ATOM_AIRMONT_MID,		NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT),
 	VULNWL_INTEL(ATOM_AIRMONT_NP,		NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT),
 
-	VULNWL_INTEL(ATOM_GOLDMONT,		NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT),
-	VULNWL_INTEL(ATOM_GOLDMONT_D,		NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT),
-	VULNWL_INTEL(ATOM_GOLDMONT_PLUS,	NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_EIBRS_PBRSB),
+	VULNWL_INTEL(ATOM_GOLDMONT,		NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO),
+	VULNWL_INTEL(ATOM_GOLDMONT_D,		NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO),
+	VULNWL_INTEL(ATOM_GOLDMONT_PLUS,	NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_EIBRS_PBRSB),
 
 	/*
 	 * Technically, swapgs isn't serializing on AMD (despite it previously
@@ -1083,18 +1089,18 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = {
 	VULNWL_INTEL(ATOM_TREMONT_D,		NO_ITLB_MULTIHIT | NO_EIBRS_PBRSB),
 
 	/* AMD Family 0xf - 0x12 */
-	VULNWL_AMD(0x0f,	NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT),
-	VULNWL_AMD(0x10,	NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT),
-	VULNWL_AMD(0x11,	NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT),
-	VULNWL_AMD(0x12,	NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT),
+	VULNWL_AMD(0x0f,	NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO),
+	VULNWL_AMD(0x10,	NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO),
+	VULNWL_AMD(0x11,	NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO),
+	VULNWL_AMD(0x12,	NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO),
 
 	/* FAMILY_ANY must be last, otherwise 0x0f - 0x12 matches won't work */
-	VULNWL_AMD(X86_FAMILY_ANY,	NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT),
-	VULNWL_HYGON(X86_FAMILY_ANY,	NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT),
+	VULNWL_AMD(X86_FAMILY_ANY,	NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO),
+	VULNWL_HYGON(X86_FAMILY_ANY,	NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO),
 
 	/* Zhaoxin Family 7 */
-	VULNWL(CENTAUR,	7, X86_MODEL_ANY,	NO_SPECTRE_V2 | NO_SWAPGS),
-	VULNWL(ZHAOXIN,	7, X86_MODEL_ANY,	NO_SPECTRE_V2 | NO_SWAPGS),
+	VULNWL(CENTAUR,	7, X86_MODEL_ANY,	NO_SPECTRE_V2 | NO_SWAPGS | NO_MMIO),
+	VULNWL(ZHAOXIN,	7, X86_MODEL_ANY,	NO_SPECTRE_V2 | NO_SWAPGS | NO_MMIO),
 	{}
 };
 
@@ -1248,10 +1254,16 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
 	 * Affected CPU list is generally enough to enumerate the vulnerability,
 	 * but for virtualization case check for ARCH_CAP MSR bits also, VMM may
 	 * not want the guest to enumerate the bug.
+	 *
+	 * Set X86_BUG_MMIO_UNKNOWN for CPUs that are neither in the blacklist,
+	 * nor in the whitelist and also don't enumerate MSR ARCH_CAP MMIO bits.
 	 */
-	if (cpu_matches(cpu_vuln_blacklist, MMIO) &&
-	    !arch_cap_mmio_immune(ia32_cap))
-		setup_force_cpu_bug(X86_BUG_MMIO_STALE_DATA);
+	if (!arch_cap_mmio_immune(ia32_cap)) {
+		if (cpu_matches(cpu_vuln_blacklist, MMIO))
+			setup_force_cpu_bug(X86_BUG_MMIO_STALE_DATA);
+		else if (!cpu_matches(cpu_vuln_whitelist, NO_MMIO))
+			setup_force_cpu_bug(X86_BUG_MMIO_UNKNOWN);
+	}
 
 	if (!cpu_has(c, X86_FEATURE_BTC_NO)) {
 		if (cpu_matches(cpu_vuln_blacklist, RETBLEED) || (ia32_cap & ARCH_CAP_RSBA))

arch/x86/kernel/unwind_orc.c

@@ -93,22 +93,27 @@ static struct orc_entry *orc_find(unsigned long ip);
 static struct orc_entry *orc_ftrace_find(unsigned long ip)
 {
 	struct ftrace_ops *ops;
-	unsigned long caller;
+	unsigned long tramp_addr, offset;
 
 	ops = ftrace_ops_trampoline(ip);
 	if (!ops)
 		return NULL;
 
+	/* Set tramp_addr to the start of the code copied by the trampoline */
 	if (ops->flags & FTRACE_OPS_FL_SAVE_REGS)
-		caller = (unsigned long)ftrace_regs_call;
+		tramp_addr = (unsigned long)ftrace_regs_caller;
 	else
-		caller = (unsigned long)ftrace_call;
+		tramp_addr = (unsigned long)ftrace_caller;
+
+	/* Now place tramp_addr to the location within the trampoline ip is at */
+	offset = ip - ops->trampoline;
+	tramp_addr += offset;
 
 	/* Prevent unlikely recursion */
-	if (ip == caller)
+	if (ip == tramp_addr)
 		return NULL;
 
-	return orc_find(caller);
+	return orc_find(tramp_addr);
 }
 #else
 static struct orc_entry *orc_ftrace_find(unsigned long ip)

block/blk-mq.c

@@ -1403,7 +1403,8 @@ out:
 	/* If we didn't flush the entire list, we could have told the driver
 	 * there was more coming, but that turned out to be a lie.
 	 */
-	if ((!list_empty(list) || errors) && q->mq_ops->commit_rqs && queued)
+	if ((!list_empty(list) || errors || needs_resource ||
+	     ret == BLK_STS_DEV_RESOURCE) && q->mq_ops->commit_rqs && queued)
 		q->mq_ops->commit_rqs(hctx);
 	/*
 	 * Any items that need requeuing? Stuff them into hctx->dispatch,
@@ -2114,6 +2115,7 @@ void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx,
 		list_del_init(&rq->queuelist);
 		ret = blk_mq_request_issue_directly(rq, list_empty(list));
 		if (ret != BLK_STS_OK) {
+			errors++;
 			if (ret == BLK_STS_RESOURCE ||
 					ret == BLK_STS_DEV_RESOURCE) {
 				blk_mq_request_bypass_insert(rq, false,
@@ -2121,7 +2123,6 @@ void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx,
 				break;
 			}
 			blk_mq_end_request(rq, ret);
-			errors++;
 		} else
 			queued++;
 	}

drivers/acpi/processor_thermal.c

@@ -144,7 +144,7 @@ void acpi_thermal_cpufreq_exit(struct cpufreq_policy *policy)
 	unsigned int cpu;
 
 	for_each_cpu(cpu, policy->related_cpus) {
-		struct acpi_processor *pr = per_cpu(processors, policy->cpu);
+		struct acpi_processor *pr = per_cpu(processors, cpu);
 
 		if (pr)
 			freq_qos_remove_request(&pr->thermal_req);

drivers/android/binder_alloc.c

@@ -395,12 +395,15 @@ static struct binder_buffer *binder_alloc_new_buf_locked(
 	size_t size, data_offsets_size;
 	int ret;
 
+	mmap_read_lock(alloc->vma_vm_mm);
 	if (!binder_alloc_get_vma(alloc)) {
+		mmap_read_unlock(alloc->vma_vm_mm);
 		binder_alloc_debug(BINDER_DEBUG_USER_ERROR,
 				   "%d: binder_alloc_buf, no vma\n",
 				   alloc->pid);
 		return ERR_PTR(-ESRCH);
 	}
+	mmap_read_unlock(alloc->vma_vm_mm);
 
 	data_offsets_size = ALIGN(data_size, sizeof(void *)) +
 		ALIGN(offsets_size, sizeof(void *));
@@ -922,17 +925,25 @@ void binder_alloc_print_pages(struct seq_file *m,
 	 * Make sure the binder_alloc is fully initialized, otherwise we might
 	 * read inconsistent state.
 	 */
-	if (binder_alloc_get_vma(alloc) != NULL) {
-		for (i = 0; i < alloc->buffer_size / PAGE_SIZE; i++) {
-			page = &alloc->pages[i];
-			if (!page->page_ptr)
-				free++;
-			else if (list_empty(&page->lru))
-				active++;
-			else
-				lru++;
-		}
+
+	mmap_read_lock(alloc->vma_vm_mm);
+	if (binder_alloc_get_vma(alloc) == NULL) {
+		mmap_read_unlock(alloc->vma_vm_mm);
+		goto uninitialized;
 	}
+
+	mmap_read_unlock(alloc->vma_vm_mm);
+	for (i = 0; i < alloc->buffer_size / PAGE_SIZE; i++) {
+		page = &alloc->pages[i];
+		if (!page->page_ptr)
+			free++;
+		else if (list_empty(&page->lru))
+			active++;
+		else
+			lru++;
+	}
+
+uninitialized:
 	mutex_unlock(&alloc->mutex);
 	seq_printf(m, "  pages: %d:%d:%d\n", active, lru, free);
 	seq_printf(m, "  pages high watermark: %zu\n", alloc->pages_high);

drivers/base/node.c

@@ -45,7 +45,7 @@ static inline ssize_t cpumap_read(struct file *file, struct kobject *kobj,
 	return n;
 }
 
-static BIN_ATTR_RO(cpumap, 0);
+static BIN_ATTR_RO(cpumap, CPUMAP_FILE_MAX_BYTES);
 
 static inline ssize_t cpulist_read(struct file *file, struct kobject *kobj,
 				   struct bin_attribute *attr, char *buf,
@@ -66,7 +66,7 @@ static inline ssize_t cpulist_read(struct file *file, struct kobject *kobj,
 	return n;
 }
 
-static BIN_ATTR_RO(cpulist, 0);
+static BIN_ATTR_RO(cpulist, CPULIST_FILE_MAX_BYTES);
 
 /**
  * struct node_access_nodes - Access class device to hold user visible

drivers/base/topology.c

@@ -52,39 +52,39 @@ define_id_show_func(core_id);
 static DEVICE_ATTR_RO(core_id);
 
 define_siblings_read_func(thread_siblings, sibling_cpumask);
-static BIN_ATTR_RO(thread_siblings, 0);
-static BIN_ATTR_RO(thread_siblings_list, 0);
+static BIN_ATTR_RO(thread_siblings, CPUMAP_FILE_MAX_BYTES);
+static BIN_ATTR_RO(thread_siblings_list, CPULIST_FILE_MAX_BYTES);
 
 define_siblings_read_func(core_cpus, sibling_cpumask);
-static BIN_ATTR_RO(core_cpus, 0);
-static BIN_ATTR_RO(core_cpus_list, 0);
+static BIN_ATTR_RO(core_cpus, CPUMAP_FILE_MAX_BYTES);
+static BIN_ATTR_RO(core_cpus_list, CPULIST_FILE_MAX_BYTES);
 
 define_siblings_read_func(core_siblings, core_cpumask);
-static BIN_ATTR_RO(core_siblings, 0);
-static BIN_ATTR_RO(core_siblings_list, 0);
+static BIN_ATTR_RO(core_siblings, CPUMAP_FILE_MAX_BYTES);
+static BIN_ATTR_RO(core_siblings_list, CPULIST_FILE_MAX_BYTES);
 
 define_siblings_read_func(die_cpus, die_cpumask);
-static BIN_ATTR_RO(die_cpus, 0);
-static BIN_ATTR_RO(die_cpus_list, 0);
+static BIN_ATTR_RO(die_cpus, CPUMAP_FILE_MAX_BYTES);
+static BIN_ATTR_RO(die_cpus_list, CPULIST_FILE_MAX_BYTES);
 
 define_siblings_read_func(package_cpus, core_cpumask);
-static BIN_ATTR_RO(package_cpus, 0);
-static BIN_ATTR_RO(package_cpus_list, 0);
+static BIN_ATTR_RO(package_cpus, CPUMAP_FILE_MAX_BYTES);
+static BIN_ATTR_RO(package_cpus_list, CPULIST_FILE_MAX_BYTES);
 
 #ifdef CONFIG_SCHED_BOOK
 define_id_show_func(book_id);
 static DEVICE_ATTR_RO(book_id);
 define_siblings_read_func(book_siblings, book_cpumask);
-static BIN_ATTR_RO(book_siblings, 0);
-static BIN_ATTR_RO(book_siblings_list, 0);
+static BIN_ATTR_RO(book_siblings, CPUMAP_FILE_MAX_BYTES);
+static BIN_ATTR_RO(book_siblings_list, CPULIST_FILE_MAX_BYTES);
 #endif
 
 #ifdef CONFIG_SCHED_DRAWER
 define_id_show_func(drawer_id);
 static DEVICE_ATTR_RO(drawer_id);
 define_siblings_read_func(drawer_siblings, drawer_cpumask);
-static BIN_ATTR_RO(drawer_siblings, 0);
-static BIN_ATTR_RO(drawer_siblings_list, 0);
+static BIN_ATTR_RO(drawer_siblings, CPUMAP_FILE_MAX_BYTES);
+static BIN_ATTR_RO(drawer_siblings_list, CPULIST_FILE_MAX_BYTES);
 #endif
 
 static struct bin_attribute *bin_attrs[] = {

drivers/block/loop.c

@@ -1154,6 +1154,11 @@ loop_set_status_from_info(struct loop_device *lo,
 
 	lo->lo_offset = info->lo_offset;
 	lo->lo_sizelimit = info->lo_sizelimit;
+
+	/* loff_t vars have been assigned __u64 */
+	if (lo->lo_offset < 0 || lo->lo_sizelimit < 0)
+		return -EOVERFLOW;
+
 	memcpy(lo->lo_file_name, info->lo_file_name, LO_NAME_SIZE);
 	memcpy(lo->lo_crypt_name, info->lo_crypt_name, LO_NAME_SIZE);
 	lo->lo_file_name[LO_NAME_SIZE-1] = 0;

drivers/gpu/drm/nouveau/nouveau_bo.c

@@ -820,6 +820,15 @@ nouveau_bo_move_m2mf(struct ttm_buffer_object *bo, int evict,
 		if (ret == 0) {
 			ret = nouveau_fence_new(chan, false, &fence);
 			if (ret == 0) {
+				/* TODO: figure out a better solution here
+				 *
+				 * wait on the fence here explicitly as going through
+				 * ttm_bo_move_accel_cleanup somehow doesn't seem to do it.
+				 *
+				 * Without this the operation can timeout and we'll fallback to a
+				 * software copy, which might take several minutes to finish.
+				 */
+				nouveau_fence_wait(fence, false, false);
 				ret = ttm_bo_move_accel_cleanup(bo,
 								&fence->base,
 								evict, false,

drivers/md/md.c

@@ -6251,11 +6251,11 @@ static void mddev_detach(struct mddev *mddev)
 static void __md_stop(struct mddev *mddev)
 {
 	struct md_personality *pers = mddev->pers;
+	md_bitmap_destroy(mddev);
 	mddev_detach(mddev);
 	/* Ensure ->event_work is done */
 	if (mddev->event_work.func)
 		flush_workqueue(md_misc_wq);
-	md_bitmap_destroy(mddev);
 	spin_lock(&mddev->lock);
 	mddev->pers = NULL;
 	spin_unlock(&mddev->lock);
@@ -6272,6 +6272,7 @@ void md_stop(struct mddev *mddev)
 	/* stop the array and free an attached data structures.
 	 * This is called from dm-raid
 	 */
+	__md_stop_writes(mddev);
 	__md_stop(mddev);
 	bioset_exit(&mddev->bio_set);
 	bioset_exit(&mddev->sync_set);

drivers/net/bonding/bond_3ad.c

@@ -2007,30 +2007,24 @@ void bond_3ad_initiate_agg_selection(struct bonding *bond, int timeout)
  */
 void bond_3ad_initialize(struct bonding *bond, u16 tick_resolution)
 {
-	/* check that the bond is not initialized yet */
-	if (!MAC_ADDRESS_EQUAL(&(BOND_AD_INFO(bond).system.sys_mac_addr),
-				bond->dev->dev_addr)) {
+	BOND_AD_INFO(bond).aggregator_identifier = 0;
+	BOND_AD_INFO(bond).system.sys_priority =
+		bond->params.ad_actor_sys_prio;
+	if (is_zero_ether_addr(bond->params.ad_actor_system))
+		BOND_AD_INFO(bond).system.sys_mac_addr =
+		    *((struct mac_addr *)bond->dev->dev_addr);
+	else
+		BOND_AD_INFO(bond).system.sys_mac_addr =
+		    *((struct mac_addr *)bond->params.ad_actor_system);
 
-		BOND_AD_INFO(bond).aggregator_identifier = 0;
+	/* initialize how many times this module is called in one
+	 * second (should be about every 100ms)
+	 */
+	ad_ticks_per_sec = tick_resolution;
 
-		BOND_AD_INFO(bond).system.sys_priority =
-			bond->params.ad_actor_sys_prio;
-		if (is_zero_ether_addr(bond->params.ad_actor_system))
-			BOND_AD_INFO(bond).system.sys_mac_addr =
-			    *((struct mac_addr *)bond->dev->dev_addr);
-		else
-			BOND_AD_INFO(bond).system.sys_mac_addr =
-			    *((struct mac_addr *)bond->params.ad_actor_system);
-
-		/* initialize how many times this module is called in one
-		 * second (should be about every 100ms)
-		 */
-		ad_ticks_per_sec = tick_resolution;
-
-		bond_3ad_initiate_agg_selection(bond,
-						AD_AGGREGATOR_SELECTION_TIMER *
-						ad_ticks_per_sec);
-	}
+	bond_3ad_initiate_agg_selection(bond,
+					AD_AGGREGATOR_SELECTION_TIMER *
+					ad_ticks_per_sec);
 }
 
 /**

drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c

@@ -623,7 +623,7 @@ static int bnxt_hwrm_func_vf_resc_cfg(struct bnxt *bp, int num_vfs, bool reset)
 		hw_resc->max_stat_ctxs -= le16_to_cpu(req->min_stat_ctx) * n;
 		hw_resc->max_vnics -= le16_to_cpu(req->min_vnics) * n;
 		if (bp->flags & BNXT_FLAG_CHIP_P5)
-			hw_resc->max_irqs -= vf_msix * n;
+			hw_resc->max_nqs -= vf_msix;
 
 		rc = pf->active_vfs;
 	}

drivers/net/ethernet/intel/i40e/i40e_ethtool.c

@@ -4385,7 +4385,7 @@ static int i40e_check_fdir_input_set(struct i40e_vsi *vsi,
 				    (struct in6_addr *)&ipv6_full_mask))
 			new_mask |= I40E_L3_V6_DST_MASK;
 		else if (ipv6_addr_any((struct in6_addr *)
-				       &usr_ip6_spec->ip6src))
+				       &usr_ip6_spec->ip6dst))
 			new_mask &= ~I40E_L3_V6_DST_MASK;
 		else
 			return -EOPNOTSUPP;

drivers/net/ethernet/intel/ice/ice_xsk.c

@@ -321,6 +321,19 @@ int ice_xsk_pool_setup(struct ice_vsi *vsi, struct xsk_buff_pool *pool, u16 qid)
 	bool if_running, pool_present = !!pool;
 	int ret = 0, pool_failure = 0;
 
+	if (qid >= vsi->num_rxq || qid >= vsi->num_txq) {
+		netdev_err(vsi->netdev, "Please use queue id in scope of combined queues count\n");
+		pool_failure = -EINVAL;
+		goto failure;
+	}
+
+	if (!is_power_of_2(vsi->rx_rings[qid]->count) ||
+	    !is_power_of_2(vsi->tx_rings[qid]->count)) {
+		netdev_err(vsi->netdev, "Please align ring sizes to power of 2\n");
+		pool_failure = -EINVAL;
+		goto failure;
+	}
+
 	if_running = netif_running(vsi->netdev) && ice_is_xdp_ena_vsi(vsi);
 
 	if (if_running) {
@@ -343,6 +356,7 @@ xsk_pool_if_up:
 			netdev_err(vsi->netdev, "ice_qp_ena error = %d\n", ret);
 	}
 
+failure:
 	if (pool_failure) {
 		netdev_err(vsi->netdev, "Could not %sable buffer pool, error = %d\n",
 			   pool_present ? "en" : "dis", pool_failure);

drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c

@@ -1212,7 +1212,6 @@ void ixgbe_ptp_start_cyclecounter(struct ixgbe_adapter *adapter)
 	struct cyclecounter cc;
 	unsigned long flags;
 	u32 incval = 0;
-	u32 tsauxc = 0;
 	u32 fuse0 = 0;
 
 	/* For some of the boards below this mask is technically incorrect.
@@ -1247,18 +1246,6 @@ void ixgbe_ptp_start_cyclecounter(struct ixgbe_adapter *adapter)
 	case ixgbe_mac_x550em_a:
 	case ixgbe_mac_X550:
 		cc.read = ixgbe_ptp_read_X550;
-
-		/* enable SYSTIME counter */
-		IXGBE_WRITE_REG(hw, IXGBE_SYSTIMR, 0);
-		IXGBE_WRITE_REG(hw, IXGBE_SYSTIML, 0);
-		IXGBE_WRITE_REG(hw, IXGBE_SYSTIMH, 0);
-		tsauxc = IXGBE_READ_REG(hw, IXGBE_TSAUXC);
-		IXGBE_WRITE_REG(hw, IXGBE_TSAUXC,
-				tsauxc & ~IXGBE_TSAUXC_DISABLE_SYSTIME);
-		IXGBE_WRITE_REG(hw, IXGBE_TSIM, IXGBE_TSIM_TXTS);
-		IXGBE_WRITE_REG(hw, IXGBE_EIMS, IXGBE_EIMS_TIMESYNC);
-
-		IXGBE_WRITE_FLUSH(hw);
 		break;
 	case ixgbe_mac_X540:
 		cc.read = ixgbe_ptp_read_82599;
@@ -1290,6 +1277,50 @@ void ixgbe_ptp_start_cyclecounter(struct ixgbe_adapter *adapter)
 	spin_unlock_irqrestore(&adapter->tmreg_lock, flags);
 }
 
+/**
+ * ixgbe_ptp_init_systime - Initialize SYSTIME registers
+ * @adapter: the ixgbe private board structure
+ *
+ * Initialize and start the SYSTIME registers.
+ */
+static void ixgbe_ptp_init_systime(struct ixgbe_adapter *adapter)
+{
+	struct ixgbe_hw *hw = &adapter->hw;
+	u32 tsauxc;
+
+	switch (hw->mac.type) {
+	case ixgbe_mac_X550EM_x:
+	case ixgbe_mac_x550em_a:
+	case ixgbe_mac_X550:
+		tsauxc = IXGBE_READ_REG(hw, IXGBE_TSAUXC);
+
+		/* Reset SYSTIME registers to 0 */
+		IXGBE_WRITE_REG(hw, IXGBE_SYSTIMR, 0);
+		IXGBE_WRITE_REG(hw, IXGBE_SYSTIML, 0);
+		IXGBE_WRITE_REG(hw, IXGBE_SYSTIMH, 0);
+
+		/* Reset interrupt settings */
+		IXGBE_WRITE_REG(hw, IXGBE_TSIM, IXGBE_TSIM_TXTS);
+		IXGBE_WRITE_REG(hw, IXGBE_EIMS, IXGBE_EIMS_TIMESYNC);
+
+		/* Activate the SYSTIME counter */
+		IXGBE_WRITE_REG(hw, IXGBE_TSAUXC,
+				tsauxc & ~IXGBE_TSAUXC_DISABLE_SYSTIME);
+		break;
+	case ixgbe_mac_X540:
+	case ixgbe_mac_82599EB:
+		/* Reset SYSTIME registers to 0 */
+		IXGBE_WRITE_REG(hw, IXGBE_SYSTIML, 0);
+		IXGBE_WRITE_REG(hw, IXGBE_SYSTIMH, 0);
+		break;
+	default:
+		/* Other devices aren't supported */
+		return;
+	};
+
+	IXGBE_WRITE_FLUSH(hw);
+}
+
 /**
  * ixgbe_ptp_reset
  * @adapter: the ixgbe private board structure
@@ -1316,6 +1347,8 @@ void ixgbe_ptp_reset(struct ixgbe_adapter *adapter)
 
 	ixgbe_ptp_start_cyclecounter(adapter);
 
+	ixgbe_ptp_init_systime(adapter);
+
 	spin_lock_irqsave(&adapter->tmreg_lock, flags);
 	timecounter_init(&adapter->hw_tc, &adapter->hw_cc,
 			 ktime_to_ns(ktime_get_real()));

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

@@ -3325,7 +3325,9 @@ static int set_feature_hw_tc(struct net_device *netdev, bool enable)
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 
 #if IS_ENABLED(CONFIG_MLX5_CLS_ACT)
-	if (!enable && mlx5e_tc_num_filters(priv, MLX5_TC_FLAG(NIC_OFFLOAD))) {
+	int tc_flag = mlx5e_is_uplink_rep(priv) ? MLX5_TC_FLAG(ESW_OFFLOAD) :
+						  MLX5_TC_FLAG(NIC_OFFLOAD);
+	if (!enable && mlx5e_tc_num_filters(priv, tc_flag)) {
 		netdev_err(netdev,
 			   "Active offloaded tc filters, can't turn hw_tc_offload off\n");
 		return -EINVAL;
@@ -4350,14 +4352,6 @@ void mlx5e_build_nic_params(struct mlx5e_priv *priv, struct mlx5e_xsk *xsk, u16
 	/* RQ */
 	mlx5e_build_rq_params(mdev, params);
 
-	/* HW LRO */
-	if (MLX5_CAP_ETH(mdev, lro_cap) &&
-	    params->rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ) {
-		/* No XSK params: checking the availability of striding RQ in general. */
-		if (!mlx5e_rx_mpwqe_is_linear_skb(mdev, params, NULL))
-			params->packet_merge.type = slow_pci_heuristic(mdev) ?
-				MLX5E_PACKET_MERGE_NONE : MLX5E_PACKET_MERGE_LRO;
-	}
 	params->packet_merge.timeout = mlx5e_choose_lro_timeout(mdev, MLX5E_DEFAULT_LRO_TIMEOUT);
 
 	/* CQ moderation params */

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

@@ -618,6 +618,8 @@ static void mlx5e_build_rep_params(struct net_device *netdev)
 
 	params->mqprio.num_tc       = 1;
 	params->tunneled_offload_en = false;
+	if (rep->vport != MLX5_VPORT_UPLINK)
+		params->vlan_strip_disable = true;
 
 	/* Set an initial non-zero value, so that mlx5e_select_queue won't
 	 * divide by zero if called before first activating channels.

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

@@ -1427,7 +1427,9 @@ int mlx5_mdev_init(struct mlx5_core_dev *dev, int profile_idx)
 	memcpy(&dev->profile, &profile[profile_idx], sizeof(dev->profile));
 	INIT_LIST_HEAD(&priv->ctx_list);
 	spin_lock_init(&priv->ctx_lock);
+	lockdep_register_key(&dev->lock_key);
 	mutex_init(&dev->intf_state_mutex);
+	lockdep_set_class(&dev->intf_state_mutex, &dev->lock_key);
 
 	mutex_init(&priv->bfregs.reg_head.lock);
 	mutex_init(&priv->bfregs.wc_head.lock);
@@ -1474,6 +1476,7 @@ err_health_init:
 	mutex_destroy(&priv->bfregs.wc_head.lock);
 	mutex_destroy(&priv->bfregs.reg_head.lock);
 	mutex_destroy(&dev->intf_state_mutex);
+	lockdep_unregister_key(&dev->lock_key);
 	return err;
 }
 
@@ -1491,6 +1494,7 @@ void mlx5_mdev_uninit(struct mlx5_core_dev *dev)
 	mutex_destroy(&priv->bfregs.wc_head.lock);
 	mutex_destroy(&priv->bfregs.reg_head.lock);
 	mutex_destroy(&dev->intf_state_mutex);
+	lockdep_unregister_key(&dev->lock_key);
 }
 
 static int probe_one(struct pci_dev *pdev, const struct pci_device_id *id)

drivers/net/ethernet/moxa/moxart_ether.c

@@ -74,11 +74,6 @@ static int moxart_set_mac_address(struct net_device *ndev, void *addr)
 static void moxart_mac_free_memory(struct net_device *ndev)
 {
 	struct moxart_mac_priv_t *priv = netdev_priv(ndev);
-	int i;
-
-	for (i = 0; i < RX_DESC_NUM; i++)
-		dma_unmap_single(&priv->pdev->dev, priv->rx_mapping[i],
-				 priv->rx_buf_size, DMA_FROM_DEVICE);
 
 	if (priv->tx_desc_base)
 		dma_free_coherent(&priv->pdev->dev,
@@ -193,6 +188,7 @@ static int moxart_mac_open(struct net_device *ndev)
 static int moxart_mac_stop(struct net_device *ndev)
 {
 	struct moxart_mac_priv_t *priv = netdev_priv(ndev);
+	int i;
 
 	napi_disable(&priv->napi);
 
@@ -204,6 +200,11 @@ static int moxart_mac_stop(struct net_device *ndev)
 	/* disable all functions */
 	writel(0, priv->base + REG_MAC_CTRL);
 
+	/* unmap areas mapped in moxart_mac_setup_desc_ring() */
+	for (i = 0; i < RX_DESC_NUM; i++)
+		dma_unmap_single(&priv->pdev->dev, priv->rx_mapping[i],
+				 priv->rx_buf_size, DMA_FROM_DEVICE);
+
 	return 0;
 }
 

drivers/net/ethernet/pensando/ionic/ionic_lif.c

@@ -1692,8 +1692,67 @@ static int ionic_set_features(struct net_device *netdev,
 	return err;
 }
 
+static int ionic_set_attr_mac(struct ionic_lif *lif, u8 *mac)
+{
+	struct ionic_admin_ctx ctx = {
+		.work = COMPLETION_INITIALIZER_ONSTACK(ctx.work),
+		.cmd.lif_setattr = {
+			.opcode = IONIC_CMD_LIF_SETATTR,
+			.index = cpu_to_le16(lif->index),
+			.attr = IONIC_LIF_ATTR_MAC,
+		},
+	};
+
+	ether_addr_copy(ctx.cmd.lif_setattr.mac, mac);
+	return ionic_adminq_post_wait(lif, &ctx);
+}
+
+static int ionic_get_attr_mac(struct ionic_lif *lif, u8 *mac_addr)
+{
+	struct ionic_admin_ctx ctx = {
+		.work = COMPLETION_INITIALIZER_ONSTACK(ctx.work),
+		.cmd.lif_getattr = {
+			.opcode = IONIC_CMD_LIF_GETATTR,
+			.index = cpu_to_le16(lif->index),
+			.attr = IONIC_LIF_ATTR_MAC,
+		},
+	};
+	int err;
+
+	err = ionic_adminq_post_wait(lif, &ctx);
+	if (err)
+		return err;
+
+	ether_addr_copy(mac_addr, ctx.comp.lif_getattr.mac);
+	return 0;
+}
+
+static int ionic_program_mac(struct ionic_lif *lif, u8 *mac)
+{
+	u8  get_mac[ETH_ALEN];
+	int err;
+
+	err = ionic_set_attr_mac(lif, mac);
+	if (err)
+		return err;
+
+	err = ionic_get_attr_mac(lif, get_mac);
+	if (err)
+		return err;
+
+	/* To deal with older firmware that silently ignores the set attr mac:
+	 * doesn't actually change the mac and doesn't return an error, so we
+	 * do the get attr to verify whether or not the set actually happened
+	 */
+	if (!ether_addr_equal(get_mac, mac))
+		return 1;
+
+	return 0;
+}
+
 static int ionic_set_mac_address(struct net_device *netdev, void *sa)
 {
+	struct ionic_lif *lif = netdev_priv(netdev);
 	struct sockaddr *addr = sa;
 	u8 *mac;
 	int err;
@@ -1702,6 +1761,14 @@ static int ionic_set_mac_address(struct net_device *netdev, void *sa)
 	if (ether_addr_equal(netdev->dev_addr, mac))
 		return 0;
 
+	err = ionic_program_mac(lif, mac);
+	if (err < 0)
+		return err;
+
+	if (err > 0)
+		netdev_dbg(netdev, "%s: SET and GET ATTR Mac are not equal-due to old FW running\n",
+			   __func__);
+
 	err = eth_prepare_mac_addr_change(netdev, addr);
 	if (err)
 		return err;
@@ -2974,11 +3041,10 @@ static void ionic_lif_handle_fw_down(struct ionic_lif *lif)
 
 	netif_device_detach(lif->netdev);
 
+	mutex_lock(&lif->queue_lock);
 	if (test_bit(IONIC_LIF_F_UP, lif->state)) {
 		dev_info(ionic->dev, "Surprise FW stop, stopping queues\n");
-		mutex_lock(&lif->queue_lock);
 		ionic_stop_queues(lif);
-		mutex_unlock(&lif->queue_lock);
 	}
 
 	if (netif_running(lif->netdev)) {
@@ -2989,6 +3055,8 @@ static void ionic_lif_handle_fw_down(struct ionic_lif *lif)
 	ionic_reset(ionic);
 	ionic_qcqs_free(lif);
 
+	mutex_unlock(&lif->queue_lock);
+
 	dev_info(ionic->dev, "FW Down: LIFs stopped\n");
 }
 
@@ -3012,9 +3080,15 @@ static void ionic_lif_handle_fw_up(struct ionic_lif *lif)
 	err = ionic_port_init(ionic);
 	if (err)
 		goto err_out;
+
+	mutex_lock(&lif->queue_lock);
+
+	if (test_and_clear_bit(IONIC_LIF_F_BROKEN, lif->state))
+		dev_info(ionic->dev, "FW Up: clearing broken state\n");
+
 	err = ionic_qcqs_alloc(lif);
 	if (err)
-		goto err_out;
+		goto err_unlock;
 
 	err = ionic_lif_init(lif);
 	if (err)
@@ -3035,6 +3109,8 @@ static void ionic_lif_handle_fw_up(struct ionic_lif *lif)
 			goto err_txrx_free;
 	}
 
+	mutex_unlock(&lif->queue_lock);
+
 	clear_bit(IONIC_LIF_F_FW_RESET, lif->state);
 	ionic_link_status_check_request(lif, CAN_SLEEP);
 	netif_device_attach(lif->netdev);
@@ -3051,6 +3127,8 @@ err_lifs_deinit:
 	ionic_lif_deinit(lif);
 err_qcqs_free:
 	ionic_qcqs_free(lif);
+err_unlock:
+	mutex_unlock(&lif->queue_lock);
 err_out:
 	dev_err(ionic->dev, "FW Up: LIFs restart failed - err %d\n", err);
 }
@@ -3215,6 +3293,7 @@ static int ionic_station_set(struct ionic_lif *lif)
 			.attr = IONIC_LIF_ATTR_MAC,
 		},
 	};
+	u8 mac_address[ETH_ALEN];
 	struct sockaddr addr;
 	int err;
 
@@ -3223,8 +3302,23 @@ static int ionic_station_set(struct ionic_lif *lif)
 		return err;
 	netdev_dbg(lif->netdev, "found initial MAC addr %pM\n",
 		   ctx.comp.lif_getattr.mac);
-	if (is_zero_ether_addr(ctx.comp.lif_getattr.mac))
-		return 0;
+	ether_addr_copy(mac_address, ctx.comp.lif_getattr.mac);
+
+	if (is_zero_ether_addr(mac_address)) {
+		eth_hw_addr_random(netdev);
+		netdev_dbg(netdev, "Random Mac generated: %pM\n", netdev->dev_addr);
+		ether_addr_copy(mac_address, netdev->dev_addr);
+
+		err = ionic_program_mac(lif, mac_address);
+		if (err < 0)
+			return err;
+
+		if (err > 0) {
+			netdev_dbg(netdev, "%s:SET/GET ATTR Mac are not same-due to old FW running\n",
+				   __func__);
+			return 0;
+		}
+	}
 
 	if (!is_zero_ether_addr(netdev->dev_addr)) {
 		/* If the netdev mac is non-zero and doesn't match the default
@@ -3232,12 +3326,11 @@ static int ionic_station_set(struct ionic_lif *lif)
 		 * likely here again after a fw-upgrade reset.  We need to be
 		 * sure the netdev mac is in our filter list.
 		 */
-		if (!ether_addr_equal(ctx.comp.lif_getattr.mac,
-				      netdev->dev_addr))
+		if (!ether_addr_equal(mac_address, netdev->dev_addr))
 			ionic_lif_addr_add(lif, netdev->dev_addr);
 	} else {
 		/* Update the netdev mac with the device's mac */
-		memcpy(addr.sa_data, ctx.comp.lif_getattr.mac, netdev->addr_len);
+		ether_addr_copy(addr.sa_data, mac_address);
 		addr.sa_family = AF_INET;
 		err = eth_prepare_mac_addr_change(netdev, &addr);
 		if (err) {

drivers/net/ethernet/pensando/ionic/ionic_main.c

@@ -395,8 +395,8 @@ try_again:
 				ionic_opcode_to_str(opcode), opcode,
 				ionic_error_to_str(err), err);
 
-			msleep(1000);
 			iowrite32(0, &idev->dev_cmd_regs->done);
+			msleep(1000);
 			iowrite32(1, &idev->dev_cmd_regs->doorbell);
 			goto try_again;
 		}
@@ -409,6 +409,8 @@ try_again:
 		return ionic_error_to_errno(err);
 	}
 
+	ionic_dev_cmd_clean(ionic);
+
 	return 0;
 }
 

drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c

@@ -258,14 +258,18 @@ EXPORT_SYMBOL_GPL(stmmac_set_mac_addr);
 /* Enable disable MAC RX/TX */
 void stmmac_set_mac(void __iomem *ioaddr, bool enable)
 {
-	u32 value = readl(ioaddr + MAC_CTRL_REG);
+	u32 old_val, value;
+
+	old_val = readl(ioaddr + MAC_CTRL_REG);
+	value = old_val;
 
 	if (enable)
 		value |= MAC_ENABLE_RX | MAC_ENABLE_TX;
 	else
 		value &= ~(MAC_ENABLE_TX | MAC_ENABLE_RX);
 
-	writel(value, ioaddr + MAC_CTRL_REG);
+	if (value != old_val)
+		writel(value, ioaddr + MAC_CTRL_REG);
 }
 
 void stmmac_get_mac_addr(void __iomem *ioaddr, unsigned char *addr,

drivers/net/ethernet/stmicro/stmmac/stmmac_main.c

@@ -1083,10 +1083,10 @@ static void stmmac_mac_link_up(struct phylink_config *config,
 			       bool tx_pause, bool rx_pause)
 {
 	struct stmmac_priv *priv = netdev_priv(to_net_dev(config->dev));
-	u32 ctrl;
+	u32 old_ctrl, ctrl;
 
-	ctrl = readl(priv->ioaddr + MAC_CTRL_REG);
-	ctrl &= ~priv->hw->link.speed_mask;
+	old_ctrl = readl(priv->ioaddr + MAC_CTRL_REG);
+	ctrl = old_ctrl & ~priv->hw->link.speed_mask;
 
 	if (interface == PHY_INTERFACE_MODE_USXGMII) {
 		switch (speed) {
@@ -1161,7 +1161,8 @@ static void stmmac_mac_link_up(struct phylink_config *config,
 	if (tx_pause && rx_pause)
 		stmmac_mac_flow_ctrl(priv, duplex);
 
-	writel(ctrl, priv->ioaddr + MAC_CTRL_REG);
+	if (ctrl != old_ctrl)
+		writel(ctrl, priv->ioaddr + MAC_CTRL_REG);
 
 	stmmac_mac_set(priv, priv->ioaddr, true);
 	if (phy && priv->dma_cap.eee) {

drivers/net/ethernet/sun/cassini.c

@@ -1325,7 +1325,7 @@ static void cas_init_rx_dma(struct cas *cp)
 	writel(val, cp->regs + REG_RX_PAGE_SIZE);
 
 	/* enable the header parser if desired */
-	if (CAS_HP_FIRMWARE == cas_prog_null)
+	if (&CAS_HP_FIRMWARE[0] == &cas_prog_null[0])
 		return;
 
 	val = CAS_BASE(HP_CFG_NUM_CPU, CAS_NCPUS > 63 ? 0 : CAS_NCPUS);
@@ -3794,7 +3794,7 @@ static void cas_reset(struct cas *cp, int blkflag)
 
 	/* program header parser */
 	if ((cp->cas_flags & CAS_FLAG_TARGET_ABORT) ||
-	    (CAS_HP_ALT_FIRMWARE == cas_prog_null)) {
+	    (&CAS_HP_ALT_FIRMWARE[0] == &cas_prog_null[0])) {
 		cas_load_firmware(cp, CAS_HP_FIRMWARE);
 	} else {
 		cas_load_firmware(cp, CAS_HP_ALT_FIRMWARE);

drivers/net/ipa/ipa_mem.c

@@ -570,7 +570,7 @@ static int ipa_smem_init(struct ipa *ipa, u32 item, size_t size)
 	}
 
 	/* Align the address down and the size up to a page boundary */
-	addr = qcom_smem_virt_to_phys(virt) & PAGE_MASK;
+	addr = qcom_smem_virt_to_phys(virt);
 	phys = addr & PAGE_MASK;
 	size = PAGE_ALIGN(size + addr - phys);
 	iova = phys;	/* We just want a direct mapping */

drivers/net/ipvlan/ipvlan_main.c

@@ -787,7 +787,7 @@ static int ipvlan_device_event(struct notifier_block *unused,
 
 	case NETDEV_CHANGEADDR:
 		list_for_each_entry(ipvlan, &port->ipvlans, pnode) {
-			ether_addr_copy(ipvlan->dev->dev_addr, dev->dev_addr);
+			eth_hw_addr_set(ipvlan->dev, dev->dev_addr);
 			call_netdevice_notifiers(NETDEV_CHANGEADDR, ipvlan->dev);
 		}
 		break;

drivers/net/ipvlan/ipvtap.c

@@ -194,7 +194,7 @@ static struct notifier_block ipvtap_notifier_block __read_mostly = {
 	.notifier_call	= ipvtap_device_event,
 };
 
-static int ipvtap_init(void)
+static int __init ipvtap_init(void)
 {
 	int err;
 
@@ -228,7 +228,7 @@ out1:
 }
 module_init(ipvtap_init);
 
-static void ipvtap_exit(void)
+static void __exit ipvtap_exit(void)
 {
 	rtnl_link_unregister(&ipvtap_link_ops);
 	unregister_netdevice_notifier(&ipvtap_notifier_block);

drivers/net/macsec.c

@@ -447,11 +447,6 @@ static struct macsec_eth_header *macsec_ethhdr(struct sk_buff *skb)
 	return (struct macsec_eth_header *)skb_mac_header(skb);
 }
 
-static sci_t dev_to_sci(struct net_device *dev, __be16 port)
-{
-	return make_sci(dev->dev_addr, port);
-}
-
 static void __macsec_pn_wrapped(struct macsec_secy *secy,
 				struct macsec_tx_sa *tx_sa)
 {
@@ -3616,8 +3611,7 @@ static int macsec_set_mac_address(struct net_device *dev, void *p)
 	dev_uc_del(real_dev, dev->dev_addr);
 
 out:
-	ether_addr_copy(dev->dev_addr, addr->sa_data);
-	macsec->secy.sci = dev_to_sci(dev, MACSEC_PORT_ES);
+	eth_hw_addr_set(dev, addr->sa_data);
 
 	/* If h/w offloading is available, propagate to the device */
 	if (macsec_is_offloaded(macsec)) {
@@ -3953,6 +3947,11 @@ static bool sci_exists(struct net_device *dev, sci_t sci)
 	return false;
 }
 
+static sci_t dev_to_sci(struct net_device *dev, __be16 port)
+{
+	return make_sci(dev->dev_addr, port);
+}
+
 static int macsec_add_dev(struct net_device *dev, sci_t sci, u8 icv_len)
 {
 	struct macsec_dev *macsec = macsec_priv(dev);

drivers/net/macvlan.c

@@ -711,7 +711,7 @@ static int macvlan_sync_address(struct net_device *dev, unsigned char *addr)
 
 	if (!(dev->flags & IFF_UP)) {
 		/* Just copy in the new address */
-		ether_addr_copy(dev->dev_addr, addr);
+		eth_hw_addr_set(dev, addr);
 	} else {
 		/* Rehash and update the device filters */
 		if (macvlan_addr_busy(vlan->port, addr))

drivers/net/phy/phy_device.c

@@ -315,11 +315,11 @@ static __maybe_unused int mdio_bus_phy_resume(struct device *dev)
 
 	phydev->suspended_by_mdio_bus = 0;
 
-	/* If we managed to get here with the PHY state machine in a state other
-	 * than PHY_HALTED this is an indication that something went wrong and
-	 * we should most likely be using MAC managed PM and we are not.
+	/* If we manged to get here with the PHY state machine in a state neither
+	 * PHY_HALTED nor PHY_READY this is an indication that something went wrong
+	 * and we should most likely be using MAC managed PM and we are not.
 	 */
-	WARN_ON(phydev->state != PHY_HALTED && !phydev->mac_managed_pm);
+	WARN_ON(phydev->state != PHY_HALTED && phydev->state != PHY_READY);
 
 	ret = phy_init_hw(phydev);
 	if (ret < 0)

drivers/net/usb/r8152.c

@@ -5904,6 +5904,11 @@ static void r8153_enter_oob(struct r8152 *tp)
 	ocp_data &= ~NOW_IS_OOB;
 	ocp_write_byte(tp, MCU_TYPE_PLA, PLA_OOB_CTRL, ocp_data);
 
+	/* RX FIFO settings for OOB */
+	ocp_write_dword(tp, MCU_TYPE_PLA, PLA_RXFIFO_CTRL0, RXFIFO_THR1_OOB);
+	ocp_write_word(tp, MCU_TYPE_PLA, PLA_RXFIFO_CTRL1, RXFIFO_THR2_OOB);
+	ocp_write_word(tp, MCU_TYPE_PLA, PLA_RXFIFO_CTRL2, RXFIFO_THR3_OOB);
+
 	rtl_disable(tp);
 	rtl_reset_bmu(tp);
 
@@ -6429,21 +6434,8 @@ static void r8156_fc_parameter(struct r8152 *tp)
 	u32 pause_on = tp->fc_pause_on ? tp->fc_pause_on : fc_pause_on_auto(tp);
 	u32 pause_off = tp->fc_pause_off ? tp->fc_pause_off : fc_pause_off_auto(tp);
 
-	switch (tp->version) {
-	case RTL_VER_10:
-	case RTL_VER_11:
-		ocp_write_word(tp, MCU_TYPE_PLA, PLA_RX_FIFO_FULL, pause_on / 8);
-		ocp_write_word(tp, MCU_TYPE_PLA, PLA_RX_FIFO_EMPTY, pause_off / 8);
-		break;
-	case RTL_VER_12:
-	case RTL_VER_13:
-	case RTL_VER_15:
-		ocp_write_word(tp, MCU_TYPE_PLA, PLA_RX_FIFO_FULL, pause_on / 16);
-		ocp_write_word(tp, MCU_TYPE_PLA, PLA_RX_FIFO_EMPTY, pause_off / 16);
-		break;
-	default:
-		break;
-	}
+	ocp_write_word(tp, MCU_TYPE_PLA, PLA_RX_FIFO_FULL, pause_on / 16);
+	ocp_write_word(tp, MCU_TYPE_PLA, PLA_RX_FIFO_EMPTY, pause_off / 16);
 }
 
 static void rtl8156_change_mtu(struct r8152 *tp)
@@ -6555,6 +6547,11 @@ static void rtl8156_down(struct r8152 *tp)
 	ocp_data &= ~NOW_IS_OOB;
 	ocp_write_byte(tp, MCU_TYPE_PLA, PLA_OOB_CTRL, ocp_data);
 
+	/* RX FIFO settings for OOB */
+	ocp_write_word(tp, MCU_TYPE_PLA, PLA_RXFIFO_FULL, 64 / 16);
+	ocp_write_word(tp, MCU_TYPE_PLA, PLA_RX_FIFO_FULL, 1024 / 16);
+	ocp_write_word(tp, MCU_TYPE_PLA, PLA_RX_FIFO_EMPTY, 4096 / 16);
+
 	rtl_disable(tp);
 	rtl_reset_bmu(tp);
 

drivers/net/usb/smsc95xx.c

@@ -18,8 +18,6 @@
 #include <linux/usb/usbnet.h>
 #include <linux/slab.h>
 #include <linux/of_net.h>
-#include <linux/irq.h>
-#include <linux/irqdomain.h>
 #include <linux/mdio.h>
 #include <linux/phy.h>
 #include "smsc95xx.h"
@@ -53,9 +51,6 @@
 #define SUSPEND_ALLMODES		(SUSPEND_SUSPEND0 | SUSPEND_SUSPEND1 | \
 					 SUSPEND_SUSPEND2 | SUSPEND_SUSPEND3)
 
-#define SMSC95XX_NR_IRQS		(1) /* raise to 12 for GPIOs */
-#define PHY_HWIRQ			(SMSC95XX_NR_IRQS - 1)
-
 struct smsc95xx_priv {
 	u32 mac_cr;
 	u32 hash_hi;
@@ -64,12 +59,8 @@ struct smsc95xx_priv {
 	spinlock_t mac_cr_lock;
 	u8 features;
 	u8 suspend_flags;
-	struct irq_chip irqchip;
-	struct irq_domain *irqdomain;
-	struct fwnode_handle *irqfwnode;
 	struct mii_bus *mdiobus;
 	struct phy_device *phydev;
-	struct task_struct *pm_task;
 };
 
 static bool turbo_mode = true;
@@ -79,14 +70,13 @@ MODULE_PARM_DESC(turbo_mode, "Enable multiple frames per Rx transaction");
 static int __must_check __smsc95xx_read_reg(struct usbnet *dev, u32 index,
 					    u32 *data, int in_pm)
 {
-	struct smsc95xx_priv *pdata = dev->driver_priv;
 	u32 buf;
 	int ret;
 	int (*fn)(struct usbnet *, u8, u8, u16, u16, void *, u16);
 
 	BUG_ON(!dev);
 
-	if (current != pdata->pm_task)
+	if (!in_pm)
 		fn = usbnet_read_cmd;
 	else
 		fn = usbnet_read_cmd_nopm;
@@ -110,14 +100,13 @@ static int __must_check __smsc95xx_read_reg(struct usbnet *dev, u32 index,
 static int __must_check __smsc95xx_write_reg(struct usbnet *dev, u32 index,
 					     u32 data, int in_pm)
 {
-	struct smsc95xx_priv *pdata = dev->driver_priv;
 	u32 buf;
 	int ret;
 	int (*fn)(struct usbnet *, u8, u8, u16, u16, const void *, u16);
 
 	BUG_ON(!dev);
 
-	if (current != pdata->pm_task)
+	if (!in_pm)
 		fn = usbnet_write_cmd;
 	else
 		fn = usbnet_write_cmd_nopm;
@@ -606,8 +595,6 @@ static void smsc95xx_mac_update_fullduplex(struct usbnet *dev)
 
 static void smsc95xx_status(struct usbnet *dev, struct urb *urb)
 {
-	struct smsc95xx_priv *pdata = dev->driver_priv;
-	unsigned long flags;
 	u32 intdata;
 
 	if (urb->actual_length != 4) {
@@ -619,15 +606,11 @@ static void smsc95xx_status(struct usbnet *dev, struct urb *urb)
 	intdata = get_unaligned_le32(urb->transfer_buffer);
 	netif_dbg(dev, link, dev->net, "intdata: 0x%08X\n", intdata);
 
-	local_irq_save(flags);
-
 	if (intdata & INT_ENP_PHY_INT_)
-		generic_handle_domain_irq(pdata->irqdomain, PHY_HWIRQ);
+		;
 	else
 		netdev_warn(dev->net, "unexpected interrupt, intdata=0x%08X\n",
 			    intdata);
-
-	local_irq_restore(flags);
 }
 
 /* Enable or disable Tx & Rx checksum offload engines */
@@ -1089,9 +1072,8 @@ static int smsc95xx_bind(struct usbnet *dev, struct usb_interface *intf)
 {
 	struct smsc95xx_priv *pdata;
 	bool is_internal_phy;
-	char usb_path[64];
-	int ret, phy_irq;
 	u32 val;
+	int ret;
 
 	printk(KERN_INFO SMSC_CHIPNAME " v" SMSC_DRIVER_VERSION "\n");
 
@@ -1131,38 +1113,10 @@ static int smsc95xx_bind(struct usbnet *dev, struct usb_interface *intf)
 	if (ret)
 		goto free_pdata;
 
-	/* create irq domain for use by PHY driver and GPIO consumers */
-	usb_make_path(dev->udev, usb_path, sizeof(usb_path));
-	pdata->irqfwnode = irq_domain_alloc_named_fwnode(usb_path);
-	if (!pdata->irqfwnode) {
-		ret = -ENOMEM;
-		goto free_pdata;
-	}
-
-	pdata->irqdomain = irq_domain_create_linear(pdata->irqfwnode,
-						    SMSC95XX_NR_IRQS,
-						    &irq_domain_simple_ops,
-						    pdata);
-	if (!pdata->irqdomain) {
-		ret = -ENOMEM;
-		goto free_irqfwnode;
-	}
-
-	phy_irq = irq_create_mapping(pdata->irqdomain, PHY_HWIRQ);
-	if (!phy_irq) {
-		ret = -ENOENT;
-		goto remove_irqdomain;
-	}
-
-	pdata->irqchip = dummy_irq_chip;
-	pdata->irqchip.name = SMSC_CHIPNAME;
-	irq_set_chip_and_handler_name(phy_irq, &pdata->irqchip,
-				      handle_simple_irq, "phy");
-
 	pdata->mdiobus = mdiobus_alloc();
 	if (!pdata->mdiobus) {
 		ret = -ENOMEM;
-		goto dispose_irq;
+		goto free_pdata;
 	}
 
 	ret = smsc95xx_read_reg(dev, HW_CFG, &val);
@@ -1195,7 +1149,6 @@ static int smsc95xx_bind(struct usbnet *dev, struct usb_interface *intf)
 		goto unregister_mdio;
 	}
 
-	pdata->phydev->irq = phy_irq;
 	pdata->phydev->is_internal = is_internal_phy;
 
 	/* detect device revision as different features may be available */
@@ -1238,15 +1191,6 @@ unregister_mdio:
 free_mdio:
 	mdiobus_free(pdata->mdiobus);
 
-dispose_irq:
-	irq_dispose_mapping(phy_irq);
-
-remove_irqdomain:
-	irq_domain_remove(pdata->irqdomain);
-
-free_irqfwnode:
-	irq_domain_free_fwnode(pdata->irqfwnode);
-
 free_pdata:
 	kfree(pdata);
 	return ret;
@@ -1259,9 +1203,6 @@ static void smsc95xx_unbind(struct usbnet *dev, struct usb_interface *intf)
 	phy_disconnect(dev->net->phydev);
 	mdiobus_unregister(pdata->mdiobus);
 	mdiobus_free(pdata->mdiobus);
-	irq_dispose_mapping(irq_find_mapping(pdata->irqdomain, PHY_HWIRQ));
-	irq_domain_remove(pdata->irqdomain);
-	irq_domain_free_fwnode(pdata->irqfwnode);
 	netif_dbg(dev, ifdown, dev->net, "free pdata\n");
 	kfree(pdata);
 }
@@ -1286,6 +1227,29 @@ static u32 smsc_crc(const u8 *buffer, size_t len, int filter)
 	return crc << ((filter % 2) * 16);
 }
 
+static int smsc95xx_enable_phy_wakeup_interrupts(struct usbnet *dev, u16 mask)
+{
+	int ret;
+
+	netdev_dbg(dev->net, "enabling PHY wakeup interrupts\n");
+
+	/* read to clear */
+	ret = smsc95xx_mdio_read_nopm(dev, PHY_INT_SRC);
+	if (ret < 0)
+		return ret;
+
+	/* enable interrupt source */
+	ret = smsc95xx_mdio_read_nopm(dev, PHY_INT_MASK);
+	if (ret < 0)
+		return ret;
+
+	ret |= mask;
+
+	smsc95xx_mdio_write_nopm(dev, PHY_INT_MASK, ret);
+
+	return 0;
+}
+
 static int smsc95xx_link_ok_nopm(struct usbnet *dev)
 {
 	int ret;
@@ -1452,6 +1416,7 @@ static int smsc95xx_enter_suspend3(struct usbnet *dev)
 static int smsc95xx_autosuspend(struct usbnet *dev, u32 link_up)
 {
 	struct smsc95xx_priv *pdata = dev->driver_priv;
+	int ret;
 
 	if (!netif_running(dev->net)) {
 		/* interface is ifconfig down so fully power down hw */
@@ -1470,10 +1435,27 @@ static int smsc95xx_autosuspend(struct usbnet *dev, u32 link_up)
 		}
 
 		netdev_dbg(dev->net, "autosuspend entering SUSPEND1\n");
+
+		/* enable PHY wakeup events for if cable is attached */
+		ret = smsc95xx_enable_phy_wakeup_interrupts(dev,
+			PHY_INT_MASK_ANEG_COMP_);
+		if (ret < 0) {
+			netdev_warn(dev->net, "error enabling PHY wakeup ints\n");
+			return ret;
+		}
+
 		netdev_info(dev->net, "entering SUSPEND1 mode\n");
 		return smsc95xx_enter_suspend1(dev);
 	}
 
+	/* enable PHY wakeup events so we remote wakeup if cable is pulled */
+	ret = smsc95xx_enable_phy_wakeup_interrupts(dev,
+		PHY_INT_MASK_LINK_DOWN_);
+	if (ret < 0) {
+		netdev_warn(dev->net, "error enabling PHY wakeup ints\n");
+		return ret;
+	}
+
 	netdev_dbg(dev->net, "autosuspend entering SUSPEND3\n");
 	return smsc95xx_enter_suspend3(dev);
 }
@@ -1485,12 +1467,9 @@ static int smsc95xx_suspend(struct usb_interface *intf, pm_message_t message)
 	u32 val, link_up;
 	int ret;
 
-	pdata->pm_task = current;
-
 	ret = usbnet_suspend(intf, message);
 	if (ret < 0) {
 		netdev_warn(dev->net, "usbnet_suspend error\n");
-		pdata->pm_task = NULL;
 		return ret;
 	}
 
@@ -1542,6 +1521,13 @@ static int smsc95xx_suspend(struct usb_interface *intf, pm_message_t message)
 	}
 
 	if (pdata->wolopts & WAKE_PHY) {
+		ret = smsc95xx_enable_phy_wakeup_interrupts(dev,
+			(PHY_INT_MASK_ANEG_COMP_ | PHY_INT_MASK_LINK_DOWN_));
+		if (ret < 0) {
+			netdev_warn(dev->net, "error enabling PHY wakeup ints\n");
+			goto done;
+		}
+
 		/* if link is down then configure EDPD and enter SUSPEND1,
 		 * otherwise enter SUSPEND0 below
 		 */
@@ -1730,7 +1716,6 @@ done:
 	if (ret && PMSG_IS_AUTO(message))
 		usbnet_resume(intf);
 
-	pdata->pm_task = NULL;
 	return ret;
 }
 
@@ -1751,53 +1736,45 @@ static int smsc95xx_resume(struct usb_interface *intf)
 	/* do this first to ensure it's cleared even in error case */
 	pdata->suspend_flags = 0;
 
-	pdata->pm_task = current;
-
 	if (suspend_flags & SUSPEND_ALLMODES) {
 		/* clear wake-up sources */
 		ret = smsc95xx_read_reg_nopm(dev, WUCSR, &val);
 		if (ret < 0)
-			goto done;
+			return ret;
 
 		val &= ~(WUCSR_WAKE_EN_ | WUCSR_MPEN_);
 
 		ret = smsc95xx_write_reg_nopm(dev, WUCSR, val);
 		if (ret < 0)
-			goto done;
+			return ret;
 
 		/* clear wake-up status */
 		ret = smsc95xx_read_reg_nopm(dev, PM_CTRL, &val);
 		if (ret < 0)
-			goto done;
+			return ret;
 
 		val &= ~PM_CTL_WOL_EN_;
 		val |= PM_CTL_WUPS_;
 
 		ret = smsc95xx_write_reg_nopm(dev, PM_CTRL, val);
 		if (ret < 0)
-			goto done;
+			return ret;
 	}
 
-	phy_init_hw(pdata->phydev);
-
 	ret = usbnet_resume(intf);
 	if (ret < 0)
 		netdev_warn(dev->net, "usbnet_resume error\n");
 
-done:
-	pdata->pm_task = NULL;
+	phy_init_hw(pdata->phydev);
 	return ret;
 }
 
 static int smsc95xx_reset_resume(struct usb_interface *intf)
 {
 	struct usbnet *dev = usb_get_intfdata(intf);
-	struct smsc95xx_priv *pdata = dev->driver_priv;
 	int ret;
 
-	pdata->pm_task = current;
 	ret = smsc95xx_reset(dev);
-	pdata->pm_task = NULL;
 	if (ret < 0)
 		return ret;
 

drivers/net/wireless/realtek/rtlwifi/rtl8192de/phy.c

@@ -2386,10 +2386,7 @@ void rtl92d_phy_reload_iqk_setting(struct ieee80211_hw *hw, u8 channel)
 			rtl_dbg(rtlpriv, COMP_SCAN, DBG_LOUD,
 				"Just Read IQK Matrix reg for channel:%d....\n",
 				channel);
-			if ((rtlphy->iqk_matrix[indexforchannel].
-			     value[0] != NULL)
-				/*&&(regea4 != 0) */)
-				_rtl92d_phy_patha_fill_iqk_matrix(hw, true,
+			_rtl92d_phy_patha_fill_iqk_matrix(hw, true,
 					rtlphy->iqk_matrix[
 					indexforchannel].value,	0,
 					(rtlphy->iqk_matrix[

drivers/nfc/pn533/uart.c

@@ -310,6 +310,7 @@ static void pn532_uart_remove(struct serdev_device *serdev)
 	pn53x_unregister_nfc(pn532->priv);
 	serdev_device_close(serdev);
 	pn53x_common_clean(pn532->priv);
+	del_timer_sync(&pn532->cmd_timeout);
 	kfree_skb(pn532->recv_skb);
 	kfree(pn532);
 }

drivers/nvme/target/zns.c

@@ -34,8 +34,7 @@ static int validate_conv_zones_cb(struct blk_zone *z,
 
 bool nvmet_bdev_zns_enable(struct nvmet_ns *ns)
 {
-	struct request_queue *q = ns->bdev->bd_disk->queue;
-	u8 zasl = nvmet_zasl(queue_max_zone_append_sectors(q));
+	u8 zasl = nvmet_zasl(bdev_max_zone_append_sectors(ns->bdev));
 	struct gendisk *bd_disk = ns->bdev->bd_disk;
 	int ret;
 

drivers/scsi/qla2xxx/qla_gbl.h

@@ -192,6 +192,8 @@ extern int ql2xfulldump_on_mpifail;
 extern int ql2xsecenable;
 extern int ql2xenforce_iocb_limit;
 extern int ql2xabts_wait_nvme;
+extern int ql2xrspq_follow_inptr;
+extern int ql2xrspq_follow_inptr_legacy;
 
 extern int qla2x00_loop_reset(scsi_qla_host_t *);
 extern void qla2x00_abort_all_cmds(scsi_qla_host_t *, int);

drivers/scsi/qla2xxx/qla_isr.c

@@ -3707,12 +3707,11 @@ void qla24xx_nvme_ls4_iocb(struct scsi_qla_host *vha,
  * Return: 0 all iocbs has arrived, xx- all iocbs have not arrived.
  */
 static int qla_chk_cont_iocb_avail(struct scsi_qla_host *vha,
-	struct rsp_que *rsp, response_t *pkt)
+	struct rsp_que *rsp, response_t *pkt, u32 rsp_q_in)
 {
-	int start_pkt_ring_index, end_pkt_ring_index, n_ring_index;
-	response_t *end_pkt;
+	int start_pkt_ring_index;
+	u32 iocb_cnt = 0;
 	int rc = 0;
-	u32 rsp_q_in;
 
 	if (pkt->entry_count == 1)
 		return rc;
@@ -3723,34 +3722,18 @@ static int qla_chk_cont_iocb_avail(struct scsi_qla_host *vha,
 	else
 		start_pkt_ring_index = rsp->ring_index - 1;
 
-	if ((start_pkt_ring_index + pkt->entry_count) >= rsp->length)
-		end_pkt_ring_index = start_pkt_ring_index + pkt->entry_count -
-			rsp->length - 1;
+	if (rsp_q_in < start_pkt_ring_index)
+		/* q in ptr is wrapped */
+		iocb_cnt = rsp->length - start_pkt_ring_index + rsp_q_in;
 	else
-		end_pkt_ring_index = start_pkt_ring_index + pkt->entry_count - 1;
+		iocb_cnt = rsp_q_in - start_pkt_ring_index;
 
-	end_pkt = rsp->ring + end_pkt_ring_index;
-
-	/*  next pkt = end_pkt + 1 */
-	n_ring_index = end_pkt_ring_index + 1;
-	if (n_ring_index >= rsp->length)
-		n_ring_index = 0;
-
-	rsp_q_in = rsp->qpair->use_shadow_reg ? *rsp->in_ptr :
-		rd_reg_dword(rsp->rsp_q_in);
-
-	/* rsp_q_in is either wrapped or pointing beyond endpkt */
-	if ((rsp_q_in < start_pkt_ring_index && rsp_q_in < n_ring_index) ||
-			rsp_q_in >= n_ring_index)
-		/* all IOCBs arrived. */
-		rc = 0;
-	else
+	if (iocb_cnt < pkt->entry_count)
 		rc = -EIO;
 
-	ql_dbg(ql_dbg_init + ql_dbg_verbose, vha, 0x5091,
-	    "%s - ring %p pkt %p end pkt %p entry count %#x rsp_q_in %d rc %d\n",
-	    __func__, rsp->ring, pkt, end_pkt, pkt->entry_count,
-	    rsp_q_in, rc);
+	ql_dbg(ql_dbg_init, vha, 0x5091,
+	       "%s - ring %p pkt %p entry count %d iocb_cnt %d rsp_q_in %d rc %d\n",
+	       __func__, rsp->ring, pkt, pkt->entry_count, iocb_cnt, rsp_q_in, rc);
 
 	return rc;
 }
@@ -3767,6 +3750,8 @@ void qla24xx_process_response_queue(struct scsi_qla_host *vha,
 	struct qla_hw_data *ha = vha->hw;
 	struct purex_entry_24xx *purex_entry;
 	struct purex_item *pure_item;
+	u16 rsp_in = 0, cur_ring_index;
+	int follow_inptr, is_shadow_hba;
 
 	if (!ha->flags.fw_started)
 		return;
@@ -3776,8 +3761,27 @@ void qla24xx_process_response_queue(struct scsi_qla_host *vha,
 		qla_cpu_update(rsp->qpair, smp_processor_id());
 	}
 
-	while (rsp->ring_ptr->signature != RESPONSE_PROCESSED) {
+#define __update_rsp_in(_update, _is_shadow_hba, _rsp, _rsp_in)		\
+	do {								\
+		if (_update) {						\
+			_rsp_in = _is_shadow_hba ? *(_rsp)->in_ptr :	\
+				rd_reg_dword_relaxed((_rsp)->rsp_q_in);	\
+		}							\
+	} while (0)
+
+	is_shadow_hba = IS_SHADOW_REG_CAPABLE(ha);
+	follow_inptr = is_shadow_hba ? ql2xrspq_follow_inptr :
+				ql2xrspq_follow_inptr_legacy;
+
+	__update_rsp_in(follow_inptr, is_shadow_hba, rsp, rsp_in);
+
+	while ((likely(follow_inptr &&
+		       rsp->ring_index != rsp_in &&
+		       rsp->ring_ptr->signature != RESPONSE_PROCESSED)) ||
+		       (!follow_inptr &&
+			rsp->ring_ptr->signature != RESPONSE_PROCESSED)) {
 		pkt = (struct sts_entry_24xx *)rsp->ring_ptr;
+		cur_ring_index = rsp->ring_index;
 
 		rsp->ring_index++;
 		if (rsp->ring_index == rsp->length) {
@@ -3889,6 +3893,8 @@ process_err:
 				}
 				pure_item = qla27xx_copy_fpin_pkt(vha,
 							  (void **)&pkt, &rsp);
+				__update_rsp_in(follow_inptr, is_shadow_hba,
+						rsp, rsp_in);
 				if (!pure_item)
 					break;
 				qla24xx_queue_purex_item(vha, pure_item,
@@ -3896,7 +3902,17 @@ process_err:
 				break;
 
 			case ELS_AUTH_ELS:
-				if (qla_chk_cont_iocb_avail(vha, rsp, (response_t *)pkt)) {
+				if (qla_chk_cont_iocb_avail(vha, rsp, (response_t *)pkt, rsp_in)) {
+					/*
+					 * ring_ptr and ring_index were
+					 * pre-incremented above. Reset them
+					 * back to current. Wait for next
+					 * interrupt with all IOCBs to arrive
+					 * and re-process.
+					 */
+					rsp->ring_ptr = (response_t *)pkt;
+					rsp->ring_index = cur_ring_index;
+
 					ql_dbg(ql_dbg_init, vha, 0x5091,
 					    "Defer processing ELS opcode %#x...\n",
 					    purex_entry->els_frame_payload[3]);

drivers/scsi/qla2xxx/qla_os.c

@@ -338,6 +338,16 @@ module_param(ql2xdelay_before_pci_error_handling, uint, 0644);
 MODULE_PARM_DESC(ql2xdelay_before_pci_error_handling,
 	"Number of seconds delayed before qla begin PCI error self-handling (default: 5).\n");
 
+int ql2xrspq_follow_inptr = 1;
+module_param(ql2xrspq_follow_inptr, int, 0644);
+MODULE_PARM_DESC(ql2xrspq_follow_inptr,
+		 "Follow RSP IN pointer for RSP updates for HBAs 27xx and newer (default: 1).");
+
+int ql2xrspq_follow_inptr_legacy = 1;
+module_param(ql2xrspq_follow_inptr_legacy, int, 0644);
+MODULE_PARM_DESC(ql2xrspq_follow_inptr_legacy,
+		 "Follow RSP IN pointer for RSP updates for HBAs older than 27XX. (default: 1).");
+
 static void qla2x00_clear_drv_active(struct qla_hw_data *);
 static void qla2x00_free_device(scsi_qla_host_t *);
 static int qla2xxx_map_queues(struct Scsi_Host *shost);

drivers/scsi/storvsc_drv.c

@@ -2093,7 +2093,7 @@ static int storvsc_probe(struct hv_device *device,
 	 */
 	host_dev->handle_error_wq =
 			alloc_ordered_workqueue("storvsc_error_wq_%d",
-						WQ_MEM_RECLAIM,
+						0,
 						host->host_no);
 	if (!host_dev->handle_error_wq) {
 		ret = -ENOMEM;

drivers/video/fbdev/core/fbcon.c

@@ -2413,15 +2413,21 @@ static int fbcon_do_set_font(struct vc_data *vc, int w, int h, int charcount,
 	struct fb_info *info = registered_fb[con2fb_map[vc->vc_num]];
 	struct fbcon_ops *ops = info->fbcon_par;
 	struct fbcon_display *p = &fb_display[vc->vc_num];
-	int resize;
+	int resize, ret, old_userfont, old_width, old_height, old_charcount;
 	char *old_data = NULL;
 
 	resize = (w != vc->vc_font.width) || (h != vc->vc_font.height);
 	if (p->userfont)
 		old_data = vc->vc_font.data;
 	vc->vc_font.data = (void *)(p->fontdata = data);
+	old_userfont = p->userfont;
 	if ((p->userfont = userfont))
 		REFCOUNT(data)++;
+
+	old_width = vc->vc_font.width;
+	old_height = vc->vc_font.height;
+	old_charcount = vc->vc_font.charcount;
+
 	vc->vc_font.width = w;
 	vc->vc_font.height = h;
 	vc->vc_font.charcount = charcount;
@@ -2437,7 +2443,9 @@ static int fbcon_do_set_font(struct vc_data *vc, int w, int h, int charcount,
 		rows = FBCON_SWAP(ops->rotate, info->var.yres, info->var.xres);
 		cols /= w;
 		rows /= h;
-		vc_resize(vc, cols, rows);
+		ret = vc_resize(vc, cols, rows);
+		if (ret)
+			goto err_out;
 	} else if (con_is_visible(vc)
 		   && vc->vc_mode == KD_TEXT) {
 		fbcon_clear_margins(vc, 0);
@@ -2447,6 +2455,21 @@ static int fbcon_do_set_font(struct vc_data *vc, int w, int h, int charcount,
 	if (old_data && (--REFCOUNT(old_data) == 0))
 		kfree(old_data - FONT_EXTRA_WORDS * sizeof(int));
 	return 0;
+
+err_out:
+	p->fontdata = old_data;
+	vc->vc_font.data = (void *)old_data;
+
+	if (userfont) {
+		p->userfont = old_userfont;
+		REFCOUNT(data)--;
+	}
+
+	vc->vc_font.width = old_width;
+	vc->vc_font.height = old_height;
+	vc->vc_font.charcount = old_charcount;
+
+	return ret;
 }
 
 /*

drivers/xen/privcmd.c

@@ -581,27 +581,30 @@ static int lock_pages(
 	struct privcmd_dm_op_buf kbufs[], unsigned int num,
 	struct page *pages[], unsigned int nr_pages, unsigned int *pinned)
 {
-	unsigned int i;
+	unsigned int i, off = 0;
 
-	for (i = 0; i < num; i++) {
+	for (i = 0; i < num; ) {
 		unsigned int requested;
 		int page_count;
 
 		requested = DIV_ROUND_UP(
 			offset_in_page(kbufs[i].uptr) + kbufs[i].size,
-			PAGE_SIZE);
+			PAGE_SIZE) - off;
 		if (requested > nr_pages)
 			return -ENOSPC;
 
 		page_count = pin_user_pages_fast(
-			(unsigned long) kbufs[i].uptr,
+			(unsigned long)kbufs[i].uptr + off * PAGE_SIZE,
 			requested, FOLL_WRITE, pages);
-		if (page_count < 0)
-			return page_count;
+		if (page_count <= 0)
+			return page_count ? : -EFAULT;
 
 		*pinned += page_count;
 		nr_pages -= page_count;
 		pages += page_count;
+
+		off = (requested == page_count) ? 0 : off + page_count;
+		i += !off;
 	}
 
 	return 0;
@@ -677,10 +680,8 @@ static long privcmd_ioctl_dm_op(struct file *file, void __user *udata)
 	}
 
 	rc = lock_pages(kbufs, kdata.num, pages, nr_pages, &pinned);
-	if (rc < 0) {
-		nr_pages = pinned;
+	if (rc < 0)
 		goto out;
-	}
 
 	for (i = 0; i < kdata.num; i++) {
 		set_xen_guest_handle(xbufs[i].h, kbufs[i].uptr);
@@ -692,7 +693,7 @@ static long privcmd_ioctl_dm_op(struct file *file, void __user *udata)
 	xen_preemptible_hcall_end();
 
 out:
-	unlock_pages(pages, nr_pages);
+	unlock_pages(pages, pinned);
 	kfree(xbufs);
 	kfree(pages);
 	kfree(kbufs);

fs/btrfs/btrfs_inode.h

@@ -13,6 +13,13 @@
 #include "ordered-data.h"
 #include "delayed-inode.h"
 
+/*
+ * Since we search a directory based on f_pos (struct dir_context::pos) we have
+ * to start at 2 since '.' and '..' have f_pos of 0 and 1 respectively, so
+ * everybody else has to start at 2 (see btrfs_real_readdir() and dir_emit_dots()).
+ */
+#define BTRFS_DIR_START_INDEX 2
+
 /*
  * ordered_data_close is set by truncate when a file that used
  * to have good data has been truncated to zero.  When it is set
@@ -164,8 +171,9 @@ struct btrfs_inode {
 	u64 disk_i_size;
 
 	/*
-	 * if this is a directory then index_cnt is the counter for the index
-	 * number for new files that are created
+	 * If this is a directory then index_cnt is the counter for the index
+	 * number for new files that are created. For an empty directory, this
+	 * must be initialized to BTRFS_DIR_START_INDEX.
 	 */
 	u64 index_cnt;
 

fs/btrfs/ctree.h

@@ -105,14 +105,6 @@ struct btrfs_ref;
 #define BTRFS_STAT_CURR		0
 #define BTRFS_STAT_PREV		1
 
-/*
- * Count how many BTRFS_MAX_EXTENT_SIZE cover the @size
- */
-static inline u32 count_max_extents(u64 size)
-{
-	return div_u64(size + BTRFS_MAX_EXTENT_SIZE - 1, BTRFS_MAX_EXTENT_SIZE);
-}
-
 static inline unsigned long btrfs_chunk_item_size(int num_stripes)
 {
 	BUG_ON(num_stripes == 0);
@@ -999,6 +991,12 @@ struct btrfs_fs_info {
 	u32 csums_per_leaf;
 	u32 stripesize;
 
+	/*
+	 * Maximum size of an extent. BTRFS_MAX_EXTENT_SIZE on regular
+	 * filesystem, on zoned it depends on the device constraints.
+	 */
+	u64 max_extent_size;
+
 	/* Block groups and devices containing active swapfiles. */
 	spinlock_t swapfile_pins_lock;
 	struct rb_root swapfile_pins;
@@ -1017,6 +1015,8 @@ struct btrfs_fs_info {
 		u64 zoned;
 	};
 
+	/* Max size to emit ZONE_APPEND write command */
+	u64 max_zone_append_size;
 	struct mutex zoned_meta_io_lock;
 	spinlock_t treelog_bg_lock;
 	u64 treelog_bg;
@@ -3870,6 +3870,19 @@ static inline bool btrfs_is_zoned(const struct btrfs_fs_info *fs_info)
 	return fs_info->zoned != 0;
 }
 
+/*
+ * Count how many fs_info->max_extent_size cover the @size
+ */
+static inline u32 count_max_extents(struct btrfs_fs_info *fs_info, u64 size)
+{
+#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
+	if (!fs_info)
+		return div_u64(size + BTRFS_MAX_EXTENT_SIZE - 1, BTRFS_MAX_EXTENT_SIZE);
+#endif
+
+	return div_u64(size + fs_info->max_extent_size - 1, fs_info->max_extent_size);
+}
+
 static inline bool btrfs_is_data_reloc_root(const struct btrfs_root *root)
 {
 	return root->root_key.objectid == BTRFS_DATA_RELOC_TREE_OBJECTID;

fs/btrfs/delalloc-space.c

@@ -273,7 +273,7 @@ static void calc_inode_reservations(struct btrfs_fs_info *fs_info,
 				    u64 num_bytes, u64 *meta_reserve,
 				    u64 *qgroup_reserve)
 {
-	u64 nr_extents = count_max_extents(num_bytes);
+	u64 nr_extents = count_max_extents(fs_info, num_bytes);
 	u64 csum_leaves = btrfs_csum_bytes_to_leaves(fs_info, num_bytes);
 	u64 inode_update = btrfs_calc_metadata_size(fs_info, 1);
 
@@ -347,7 +347,7 @@ int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes)
 	 * needs to free the reservation we just made.
 	 */
 	spin_lock(&inode->lock);
-	nr_extents = count_max_extents(num_bytes);
+	nr_extents = count_max_extents(fs_info, num_bytes);
 	btrfs_mod_outstanding_extents(inode, nr_extents);
 	inode->csum_bytes += num_bytes;
 	btrfs_calculate_inode_block_rsv_size(fs_info, inode);
@@ -410,7 +410,7 @@ void btrfs_delalloc_release_extents(struct btrfs_inode *inode, u64 num_bytes)
 	unsigned num_extents;
 
 	spin_lock(&inode->lock);
-	num_extents = count_max_extents(num_bytes);
+	num_extents = count_max_extents(fs_info, num_bytes);
 	btrfs_mod_outstanding_extents(inode, -num_extents);
 	btrfs_calculate_inode_block_rsv_size(fs_info, inode);
 	spin_unlock(&inode->lock);

fs/btrfs/dev-replace.c

@@ -165,7 +165,7 @@ no_valid_dev_replace_entry_found:
 		 */
 		if (btrfs_find_device(fs_info->fs_devices, &args)) {
 			btrfs_err(fs_info,
-			"replace devid present without an active replace item");
+"replace without active item, run 'device scan --forget' on the target device");
 			ret = -EUCLEAN;
 		} else {
 			dev_replace->srcdev = NULL;
@@ -1151,8 +1151,7 @@ int btrfs_dev_replace_cancel(struct btrfs_fs_info *fs_info)
 		up_write(&dev_replace->rwsem);
 
 		/* Scrub for replace must not be running in suspended state */
-		ret = btrfs_scrub_cancel(fs_info);
-		ASSERT(ret != -ENOTCONN);
+		btrfs_scrub_cancel(fs_info);
 
 		trans = btrfs_start_transaction(root, 0);
 		if (IS_ERR(trans)) {

fs/btrfs/disk-io.c

@@ -3006,6 +3006,8 @@ void btrfs_init_fs_info(struct btrfs_fs_info *fs_info)
 	fs_info->sectorsize_bits = ilog2(4096);
 	fs_info->stripesize = 4096;
 
+	fs_info->max_extent_size = BTRFS_MAX_EXTENT_SIZE;
+
 	spin_lock_init(&fs_info->swapfile_pins_lock);
 	fs_info->swapfile_pins = RB_ROOT;
 

fs/btrfs/extent_io.c

@@ -1985,8 +1985,10 @@ noinline_for_stack bool find_lock_delalloc_range(struct inode *inode,
 				    struct page *locked_page, u64 *start,
 				    u64 *end)
 {
+	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	struct extent_io_tree *tree = &BTRFS_I(inode)->io_tree;
-	u64 max_bytes = BTRFS_MAX_EXTENT_SIZE;
+	/* The sanity tests may not set a valid fs_info. */
+	u64 max_bytes = fs_info ? fs_info->max_extent_size : BTRFS_MAX_EXTENT_SIZE;
 	u64 delalloc_start;
 	u64 delalloc_end;
 	bool found;
@@ -3778,10 +3780,11 @@ static void update_nr_written(struct writeback_control *wbc,
  */
 static noinline_for_stack int writepage_delalloc(struct btrfs_inode *inode,
 		struct page *page, struct writeback_control *wbc,
-		u64 delalloc_start, unsigned long *nr_written)
+		unsigned long *nr_written)
 {
-	u64 page_end = delalloc_start + PAGE_SIZE - 1;
+	u64 page_end = page_offset(page) + PAGE_SIZE - 1;
 	bool found;
+	u64 delalloc_start = page_offset(page);
 	u64 delalloc_to_write = 0;
 	u64 delalloc_end = 0;
 	int ret;
@@ -4066,8 +4069,8 @@ static int __extent_writepage(struct page *page, struct writeback_control *wbc,
 			      struct extent_page_data *epd)
 {
 	struct inode *inode = page->mapping->host;
-	u64 start = page_offset(page);
-	u64 page_end = start + PAGE_SIZE - 1;
+	const u64 page_start = page_offset(page);
+	const u64 page_end = page_start + PAGE_SIZE - 1;
 	int ret;
 	int nr = 0;
 	size_t pg_offset;
@@ -4102,8 +4105,7 @@ static int __extent_writepage(struct page *page, struct writeback_control *wbc,
 	}
 
 	if (!epd->extent_locked) {
-		ret = writepage_delalloc(BTRFS_I(inode), page, wbc, start,
-					 &nr_written);
+		ret = writepage_delalloc(BTRFS_I(inode), page, wbc, &nr_written);
 		if (ret == 1)
 			return 0;
 		if (ret)
@@ -4153,7 +4155,7 @@ done:
 	 * capable of that.
 	 */
 	if (PageError(page))
-		end_extent_writepage(page, ret, start, page_end);
+		end_extent_writepage(page, ret, page_start, page_end);
 	unlock_page(page);
 	ASSERT(ret <= 0);
 	return ret;

fs/btrfs/inode.c

@@ -2032,6 +2032,7 @@ int btrfs_run_delalloc_range(struct btrfs_inode *inode, struct page *locked_page
 void btrfs_split_delalloc_extent(struct inode *inode,
 				 struct extent_state *orig, u64 split)
 {
+	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	u64 size;
 
 	/* not delalloc, ignore it */
@@ -2039,7 +2040,7 @@ void btrfs_split_delalloc_extent(struct inode *inode,
 		return;
 
 	size = orig->end - orig->start + 1;
-	if (size > BTRFS_MAX_EXTENT_SIZE) {
+	if (size > fs_info->max_extent_size) {
 		u32 num_extents;
 		u64 new_size;
 
@@ -2048,10 +2049,10 @@ void btrfs_split_delalloc_extent(struct inode *inode,
 		 * applies here, just in reverse.
 		 */
 		new_size = orig->end - split + 1;
-		num_extents = count_max_extents(new_size);
+		num_extents = count_max_extents(fs_info, new_size);
 		new_size = split - orig->start;
-		num_extents += count_max_extents(new_size);
-		if (count_max_extents(size) >= num_extents)
+		num_extents += count_max_extents(fs_info, new_size);
+		if (count_max_extents(fs_info, size) >= num_extents)
 			return;
 	}
 
@@ -2068,6 +2069,7 @@ void btrfs_split_delalloc_extent(struct inode *inode,
 void btrfs_merge_delalloc_extent(struct inode *inode, struct extent_state *new,
 				 struct extent_state *other)
 {
+	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	u64 new_size, old_size;
 	u32 num_extents;
 
@@ -2081,7 +2083,7 @@ void btrfs_merge_delalloc_extent(struct inode *inode, struct extent_state *new,
 		new_size = other->end - new->start + 1;
 
 	/* we're not bigger than the max, unreserve the space and go */
-	if (new_size <= BTRFS_MAX_EXTENT_SIZE) {
+	if (new_size <= fs_info->max_extent_size) {
 		spin_lock(&BTRFS_I(inode)->lock);
 		btrfs_mod_outstanding_extents(BTRFS_I(inode), -1);
 		spin_unlock(&BTRFS_I(inode)->lock);
@@ -2107,10 +2109,10 @@ void btrfs_merge_delalloc_extent(struct inode *inode, struct extent_state *new,
 	 * this case.
 	 */
 	old_size = other->end - other->start + 1;
-	num_extents = count_max_extents(old_size);
+	num_extents = count_max_extents(fs_info, old_size);
 	old_size = new->end - new->start + 1;
-	num_extents += count_max_extents(old_size);
-	if (count_max_extents(new_size) >= num_extents)
+	num_extents += count_max_extents(fs_info, old_size);
+	if (count_max_extents(fs_info, new_size) >= num_extents)
 		return;
 
 	spin_lock(&BTRFS_I(inode)->lock);
@@ -2189,7 +2191,7 @@ void btrfs_set_delalloc_extent(struct inode *inode, struct extent_state *state,
 	if (!(state->state & EXTENT_DELALLOC) && (*bits & EXTENT_DELALLOC)) {
 		struct btrfs_root *root = BTRFS_I(inode)->root;
 		u64 len = state->end + 1 - state->start;
-		u32 num_extents = count_max_extents(len);
+		u32 num_extents = count_max_extents(fs_info, len);
 		bool do_list = !btrfs_is_free_space_inode(BTRFS_I(inode));
 
 		spin_lock(&BTRFS_I(inode)->lock);
@@ -2231,7 +2233,7 @@ void btrfs_clear_delalloc_extent(struct inode *vfs_inode,
 	struct btrfs_inode *inode = BTRFS_I(vfs_inode);
 	struct btrfs_fs_info *fs_info = btrfs_sb(vfs_inode->i_sb);
 	u64 len = state->end + 1 - state->start;
-	u32 num_extents = count_max_extents(len);
+	u32 num_extents = count_max_extents(fs_info, len);
 
 	if ((state->state & EXTENT_DEFRAG) && (*bits & EXTENT_DEFRAG)) {
 		spin_lock(&inode->lock);
@@ -6394,14 +6396,8 @@ static int btrfs_set_inode_index_count(struct btrfs_inode *inode)
 		goto out;
 	ret = 0;
 
-	/*
-	 * MAGIC NUMBER EXPLANATION:
-	 * since we search a directory based on f_pos we have to start at 2
-	 * since '.' and '..' have f_pos of 0 and 1 respectively, so everybody
-	 * else has to start at 2
-	 */
 	if (path->slots[0] == 0) {
-		inode->index_cnt = 2;
+		inode->index_cnt = BTRFS_DIR_START_INDEX;
 		goto out;
 	}
 
@@ -6412,7 +6408,7 @@ static int btrfs_set_inode_index_count(struct btrfs_inode *inode)
 
 	if (found_key.objectid != btrfs_ino(inode) ||
 	    found_key.type != BTRFS_DIR_INDEX_KEY) {
-		inode->index_cnt = 2;
+		inode->index_cnt = BTRFS_DIR_START_INDEX;
 		goto out;
 	}
 
@@ -6956,7 +6952,7 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir,
 				goto fail;
 		}
 		d_instantiate(dentry, inode);
-		btrfs_log_new_name(trans, BTRFS_I(inode), NULL, parent);
+		btrfs_log_new_name(trans, old_dentry, NULL, parent);
 	}
 
 fail:
@@ -9625,13 +9621,13 @@ static int btrfs_rename_exchange(struct inode *old_dir,
 		BTRFS_I(new_inode)->dir_index = new_idx;
 
 	if (root_log_pinned) {
-		btrfs_log_new_name(trans, BTRFS_I(old_inode), BTRFS_I(old_dir),
+		btrfs_log_new_name(trans, old_dentry, BTRFS_I(old_dir),
 				   new_dentry->d_parent);
 		btrfs_end_log_trans(root);
 		root_log_pinned = false;
 	}
 	if (dest_log_pinned) {
-		btrfs_log_new_name(trans, BTRFS_I(new_inode), BTRFS_I(new_dir),
+		btrfs_log_new_name(trans, new_dentry, BTRFS_I(new_dir),
 				   old_dentry->d_parent);
 		btrfs_end_log_trans(dest);
 		dest_log_pinned = false;
@@ -9912,7 +9908,7 @@ static int btrfs_rename(struct user_namespace *mnt_userns,
 		BTRFS_I(old_inode)->dir_index = index;
 
 	if (log_pinned) {
-		btrfs_log_new_name(trans, BTRFS_I(old_inode), BTRFS_I(old_dir),
+		btrfs_log_new_name(trans, old_dentry, BTRFS_I(old_dir),
 				   new_dentry->d_parent);
 		btrfs_end_log_trans(root);
 		log_pinned = false;

fs/btrfs/root-tree.c

@@ -351,9 +351,10 @@ int btrfs_del_root_ref(struct btrfs_trans_handle *trans, u64 root_id,
 	key.offset = ref_id;
 again:
 	ret = btrfs_search_slot(trans, tree_root, &key, path, -1, 1);
-	if (ret < 0)
+	if (ret < 0) {
+		err = ret;
 		goto out;
-	if (ret == 0) {
+	} else if (ret == 0) {
 		leaf = path->nodes[0];
 		ref = btrfs_item_ptr(leaf, path->slots[0],
 				     struct btrfs_root_ref);

fs/btrfs/tree-log.c

@@ -6628,14 +6628,25 @@ void btrfs_record_snapshot_destroy(struct btrfs_trans_handle *trans,
 	mutex_unlock(&dir->log_mutex);
 }
 
-/*
- * Call this after adding a new name for a file and it will properly
- * update the log to reflect the new name.
+/**
+ * Update the log after adding a new name for an inode.
+ *
+ * @trans:              Transaction handle.
+ * @old_dentry:         The dentry associated with the old name and the old
+ *                      parent directory.
+ * @old_dir:            The inode of the previous parent directory for the case
+ *                      of a rename. For a link operation, it must be NULL.
+ * @parent:             The dentry associated with the directory under which the
+ *                      new name is located.
+ *
+ * Call this after adding a new name for an inode, as a result of a link or
+ * rename operation, and it will properly update the log to reflect the new name.
  */
 void btrfs_log_new_name(struct btrfs_trans_handle *trans,
-			struct btrfs_inode *inode, struct btrfs_inode *old_dir,
+			struct dentry *old_dentry, struct btrfs_inode *old_dir,
 			struct dentry *parent)
 {
+	struct btrfs_inode *inode = BTRFS_I(d_inode(old_dentry));
 	struct btrfs_log_ctx ctx;
 
 	/*

fs/btrfs/tree-log.h

@@ -84,7 +84,7 @@ void btrfs_record_unlink_dir(struct btrfs_trans_handle *trans,
 void btrfs_record_snapshot_destroy(struct btrfs_trans_handle *trans,
 				   struct btrfs_inode *dir);
 void btrfs_log_new_name(struct btrfs_trans_handle *trans,
-			struct btrfs_inode *inode, struct btrfs_inode *old_dir,
+			struct dentry *old_dentry, struct btrfs_inode *old_dir,
 			struct dentry *parent);
 
 #endif

fs/btrfs/volumes.c

@@ -2392,8 +2392,11 @@ int btrfs_get_dev_args_from_path(struct btrfs_fs_info *fs_info,
 
 	ret = btrfs_get_bdev_and_sb(path, FMODE_READ, fs_info->bdev_holder, 0,
 				    &bdev, &disk_super);
-	if (ret)
+	if (ret) {
+		btrfs_put_dev_args_from_path(args);
 		return ret;
+	}
+
 	args->devid = btrfs_stack_device_id(&disk_super->dev_item);
 	memcpy(args->uuid, disk_super->dev_item.uuid, BTRFS_UUID_SIZE);
 	if (btrfs_fs_incompat(fs_info, METADATA_UUID))

fs/btrfs/xattr.c

@@ -391,6 +391,9 @@ static int btrfs_xattr_handler_set(const struct xattr_handler *handler,
 				   const char *name, const void *buffer,
 				   size_t size, int flags)
 {
+	if (btrfs_root_readonly(BTRFS_I(inode)->root))
+		return -EROFS;
+
 	name = xattr_full_name(handler, name);
 	return btrfs_setxattr_trans(inode, name, buffer, size, flags);
 }

fs/btrfs/zoned.c

@@ -386,6 +386,16 @@ int btrfs_get_dev_zone_info(struct btrfs_device *device, bool populate_cache)
 	nr_sectors = bdev_nr_sectors(bdev);
 	zone_info->zone_size_shift = ilog2(zone_info->zone_size);
 	zone_info->nr_zones = nr_sectors >> ilog2(zone_sectors);
+	/*
+	 * We limit max_zone_append_size also by max_segments *
+	 * PAGE_SIZE. Technically, we can have multiple pages per segment. But,
+	 * since btrfs adds the pages one by one to a bio, and btrfs cannot
+	 * increase the metadata reservation even if it increases the number of
+	 * extents, it is safe to stick with the limit.
+	 */
+	zone_info->max_zone_append_size =
+		min_t(u64, (u64)bdev_max_zone_append_sectors(bdev) << SECTOR_SHIFT,
+		      (u64)bdev_max_segments(bdev) << PAGE_SHIFT);
 	if (!IS_ALIGNED(nr_sectors, zone_sectors))
 		zone_info->nr_zones++;
 
@@ -570,6 +580,7 @@ int btrfs_check_zoned_mode(struct btrfs_fs_info *fs_info)
 	u64 zoned_devices = 0;
 	u64 nr_devices = 0;
 	u64 zone_size = 0;
+	u64 max_zone_append_size = 0;
 	const bool incompat_zoned = btrfs_fs_incompat(fs_info, ZONED);
 	int ret = 0;
 
@@ -605,6 +616,11 @@ int btrfs_check_zoned_mode(struct btrfs_fs_info *fs_info)
 				ret = -EINVAL;
 				goto out;
 			}
+			if (!max_zone_append_size ||
+			    (zone_info->max_zone_append_size &&
+			     zone_info->max_zone_append_size < max_zone_append_size))
+				max_zone_append_size =
+					zone_info->max_zone_append_size;
 		}
 		nr_devices++;
 	}
@@ -654,7 +670,11 @@ int btrfs_check_zoned_mode(struct btrfs_fs_info *fs_info)
 	}
 
 	fs_info->zone_size = zone_size;
+	fs_info->max_zone_append_size = ALIGN_DOWN(max_zone_append_size,
+						   fs_info->sectorsize);
 	fs_info->fs_devices->chunk_alloc_policy = BTRFS_CHUNK_ALLOC_ZONED;
+	if (fs_info->max_zone_append_size < fs_info->max_extent_size)
+		fs_info->max_extent_size = fs_info->max_zone_append_size;
 
 	/*
 	 * Check mount options here, because we might change fs_info->zoned

fs/btrfs/zoned.h

@@ -23,6 +23,7 @@ struct btrfs_zoned_device_info {
 	 */
 	u64 zone_size;
 	u8  zone_size_shift;
+	u64 max_zone_append_size;
 	u32 nr_zones;
 	unsigned long *seq_zones;
 	unsigned long *empty_zones;

fs/cifs/smb2ops.c

@@ -3599,7 +3599,7 @@ static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon,
 static long smb3_punch_hole(struct file *file, struct cifs_tcon *tcon,
 			    loff_t offset, loff_t len)
 {
-	struct inode *inode;
+	struct inode *inode = file_inode(file);
 	struct cifsFileInfo *cfile = file->private_data;
 	struct file_zero_data_information fsctl_buf;
 	long rc;
@@ -3608,14 +3608,12 @@ static long smb3_punch_hole(struct file *file, struct cifs_tcon *tcon,
 
 	xid = get_xid();
 
-	inode = d_inode(cfile->dentry);
-
+	inode_lock(inode);
 	/* Need to make file sparse, if not already, before freeing range. */
 	/* Consider adding equivalent for compressed since it could also work */
 	if (!smb2_set_sparse(xid, tcon, cfile, inode, set_sparse)) {
 		rc = -EOPNOTSUPP;
-		free_xid(xid);
-		return rc;
+		goto out;
 	}
 
 	filemap_invalidate_lock(inode->i_mapping);
@@ -3635,8 +3633,10 @@ static long smb3_punch_hole(struct file *file, struct cifs_tcon *tcon,
 			true /* is_fctl */, (char *)&fsctl_buf,
 			sizeof(struct file_zero_data_information),
 			CIFSMaxBufSize, NULL, NULL);
-	free_xid(xid);
 	filemap_invalidate_unlock(inode->i_mapping);
+out:
+	inode_unlock(inode);
+	free_xid(xid);
 	return rc;
 }
 

fs/fs-writeback.c

@@ -134,10 +134,10 @@ static bool inode_io_list_move_locked(struct inode *inode,
 
 static void wb_wakeup(struct bdi_writeback *wb)
 {
-	spin_lock_bh(&wb->work_lock);
+	spin_lock_irq(&wb->work_lock);
 	if (test_bit(WB_registered, &wb->state))
 		mod_delayed_work(bdi_wq, &wb->dwork, 0);
-	spin_unlock_bh(&wb->work_lock);
+	spin_unlock_irq(&wb->work_lock);
 }
 
 static void finish_writeback_work(struct bdi_writeback *wb,
@@ -164,7 +164,7 @@ static void wb_queue_work(struct bdi_writeback *wb,
 	if (work->done)
 		atomic_inc(&work->done->cnt);
 
-	spin_lock_bh(&wb->work_lock);
+	spin_lock_irq(&wb->work_lock);
 
 	if (test_bit(WB_registered, &wb->state)) {
 		list_add_tail(&work->list, &wb->work_list);
@@ -172,7 +172,7 @@ static void wb_queue_work(struct bdi_writeback *wb,
 	} else
 		finish_writeback_work(wb, work);
 
-	spin_unlock_bh(&wb->work_lock);
+	spin_unlock_irq(&wb->work_lock);
 }
 
 /**
@@ -2109,13 +2109,13 @@ static struct wb_writeback_work *get_next_work_item(struct bdi_writeback *wb)
 {
 	struct wb_writeback_work *work = NULL;
 
-	spin_lock_bh(&wb->work_lock);
+	spin_lock_irq(&wb->work_lock);
 	if (!list_empty(&wb->work_list)) {
 		work = list_entry(wb->work_list.next,
 				  struct wb_writeback_work, list);
 		list_del_init(&work->list);
 	}
-	spin_unlock_bh(&wb->work_lock);
+	spin_unlock_irq(&wb->work_lock);
 	return work;
 }
 

fs/io_uring.c

@@ -3720,7 +3720,12 @@ done:
 copy_iov:
 		iov_iter_restore(iter, state);
 		ret = io_setup_async_rw(req, iovec, inline_vecs, iter, false);
-		return ret ?: -EAGAIN;
+		if (!ret) {
+			if (kiocb->ki_flags & IOCB_WRITE)
+				kiocb_end_write(req);
+			return -EAGAIN;
+		}
+		return ret;
 	}
 out_free:
 	/* it's reportedly faster than delegating the null check to kfree() */

fs/namespace.c

@@ -4168,6 +4168,13 @@ static int build_mount_idmapped(const struct mount_attr *attr, size_t usize,
 		err = -EPERM;
 		goto out_fput;
 	}
+
+	/* We're not controlling the target namespace. */
+	if (!ns_capable(mnt_userns, CAP_SYS_ADMIN)) {
+		err = -EPERM;
+		goto out_fput;
+	}
+
 	kattr->mnt_userns = get_user_ns(mnt_userns);
 
 out_fput:

fs/nfs/nfs4file.c

@@ -319,7 +319,7 @@ static int read_name_gen = 1;
 static struct file *__nfs42_ssc_open(struct vfsmount *ss_mnt,
 		struct nfs_fh *src_fh, nfs4_stateid *stateid)
 {
-	struct nfs_fattr fattr;
+	struct nfs_fattr *fattr = nfs_alloc_fattr();
 	struct file *filep, *res;
 	struct nfs_server *server;
 	struct inode *r_ino = NULL;
@@ -330,14 +330,20 @@ static struct file *__nfs42_ssc_open(struct vfsmount *ss_mnt,
 
 	server = NFS_SERVER(ss_mnt->mnt_root->d_inode);
 
-	nfs_fattr_init(&fattr);
+	if (!fattr)
+		return ERR_PTR(-ENOMEM);
 
-	status = nfs4_proc_getattr(server, src_fh, &fattr, NULL, NULL);
+	status = nfs4_proc_getattr(server, src_fh, fattr, NULL, NULL);
 	if (status < 0) {
 		res = ERR_PTR(status);
 		goto out;
 	}
 
+	if (!S_ISREG(fattr->mode)) {
+		res = ERR_PTR(-EBADF);
+		goto out;
+	}
+
 	res = ERR_PTR(-ENOMEM);
 	len = strlen(SSC_READ_NAME_BODY) + 16;
 	read_name = kzalloc(len, GFP_NOFS);
@@ -345,7 +351,7 @@ static struct file *__nfs42_ssc_open(struct vfsmount *ss_mnt,
 		goto out;
 	snprintf(read_name, len, SSC_READ_NAME_BODY, read_name_gen++);
 
-	r_ino = nfs_fhget(ss_mnt->mnt_root->d_inode->i_sb, src_fh, &fattr,
+	r_ino = nfs_fhget(ss_mnt->mnt_root->d_inode->i_sb, src_fh, fattr,
 			NULL);
 	if (IS_ERR(r_ino)) {
 		res = ERR_CAST(r_ino);
@@ -356,6 +362,7 @@ static struct file *__nfs42_ssc_open(struct vfsmount *ss_mnt,
 				     r_ino->i_fop);
 	if (IS_ERR(filep)) {
 		res = ERR_CAST(filep);
+		iput(r_ino);
 		goto out_free_name;
 	}
 	filep->f_mode |= FMODE_READ;
@@ -390,6 +397,7 @@ static struct file *__nfs42_ssc_open(struct vfsmount *ss_mnt,
 out_free_name:
 	kfree(read_name);
 out:
+	nfs_free_fattr(fattr);
 	return res;
 out_stateowner:
 	nfs4_put_state_owner(sp);

fs/ntfs3/xattr.c

@@ -476,8 +476,7 @@ out:
 }
 
 #ifdef CONFIG_NTFS3_FS_POSIX_ACL
-static struct posix_acl *ntfs_get_acl_ex(struct user_namespace *mnt_userns,
-					 struct inode *inode, int type,
+static struct posix_acl *ntfs_get_acl_ex(struct inode *inode, int type,
 					 int locked)
 {
 	struct ntfs_inode *ni = ntfs_i(inode);
@@ -512,7 +511,7 @@ static struct posix_acl *ntfs_get_acl_ex(struct user_namespace *mnt_userns,
 
 	/* Translate extended attribute to acl. */
 	if (err >= 0) {
-		acl = posix_acl_from_xattr(mnt_userns, buf, err);
+		acl = posix_acl_from_xattr(&init_user_ns, buf, err);
 	} else if (err == -ENODATA) {
 		acl = NULL;
 	} else {
@@ -535,8 +534,7 @@ struct posix_acl *ntfs_get_acl(struct inode *inode, int type, bool rcu)
 	if (rcu)
 		return ERR_PTR(-ECHILD);
 
-	/* TODO: init_user_ns? */
-	return ntfs_get_acl_ex(&init_user_ns, inode, type, 0);
+	return ntfs_get_acl_ex(inode, type, 0);
 }
 
 static noinline int ntfs_set_acl_ex(struct user_namespace *mnt_userns,
@@ -588,7 +586,7 @@ static noinline int ntfs_set_acl_ex(struct user_namespace *mnt_userns,
 		value = kmalloc(size, GFP_NOFS);
 		if (!value)
 			return -ENOMEM;
-		err = posix_acl_to_xattr(mnt_userns, acl, value, size);
+		err = posix_acl_to_xattr(&init_user_ns, acl, value, size);
 		if (err < 0)
 			goto out;
 		flags = 0;
@@ -639,7 +637,7 @@ static int ntfs_xattr_get_acl(struct user_namespace *mnt_userns,
 	if (!acl)
 		return -ENODATA;
 
-	err = posix_acl_to_xattr(mnt_userns, acl, buffer, size);
+	err = posix_acl_to_xattr(&init_user_ns, acl, buffer, size);
 	posix_acl_release(acl);
 
 	return err;
@@ -663,12 +661,12 @@ static int ntfs_xattr_set_acl(struct user_namespace *mnt_userns,
 	if (!value) {
 		acl = NULL;
 	} else {
-		acl = posix_acl_from_xattr(mnt_userns, value, size);
+		acl = posix_acl_from_xattr(&init_user_ns, value, size);
 		if (IS_ERR(acl))
 			return PTR_ERR(acl);
 
 		if (acl) {
-			err = posix_acl_valid(mnt_userns, acl);
+			err = posix_acl_valid(&init_user_ns, acl);
 			if (err)
 				goto release_and_out;
 		}

fs/proc/task_mmu.c

@@ -514,10 +514,12 @@ static void smaps_pte_entry(pte_t *pte, unsigned long addr,
 	struct vm_area_struct *vma = walk->vma;
 	bool locked = !!(vma->vm_flags & VM_LOCKED);
 	struct page *page = NULL;
-	bool migration = false;
+	bool migration = false, young = false, dirty = false;
 
 	if (pte_present(*pte)) {
 		page = vm_normal_page(vma, addr, *pte);
+		young = pte_young(*pte);
+		dirty = pte_dirty(*pte);
 	} else if (is_swap_pte(*pte)) {
 		swp_entry_t swpent = pte_to_swp_entry(*pte);
 
@@ -551,8 +553,7 @@ static void smaps_pte_entry(pte_t *pte, unsigned long addr,
 	if (!page)
 		return;
 
-	smaps_account(mss, page, false, pte_young(*pte), pte_dirty(*pte),
-		      locked, migration);
+	smaps_account(mss, page, false, young, dirty, locked, migration);
 }
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE

fs/zonefs/super.c

@@ -723,13 +723,12 @@ static ssize_t zonefs_file_dio_append(struct kiocb *iocb, struct iov_iter *from)
 	struct inode *inode = file_inode(iocb->ki_filp);
 	struct zonefs_inode_info *zi = ZONEFS_I(inode);
 	struct block_device *bdev = inode->i_sb->s_bdev;
-	unsigned int max;
+	unsigned int max = bdev_max_zone_append_sectors(bdev);
 	struct bio *bio;
 	ssize_t size;
 	int nr_pages;
 	ssize_t ret;
 
-	max = queue_max_zone_append_sectors(bdev_get_queue(bdev));
 	max = ALIGN_DOWN(max << SECTOR_SHIFT, inode->i_sb->s_blocksize);
 	iov_iter_truncate(from, max);
 

include/asm-generic/sections.h

@@ -114,7 +114,7 @@ static inline bool memory_contains(void *begin, void *end, void *virt,
 /**
  * memory_intersects - checks if the region occupied by an object intersects
  *                     with another memory region
- * @begin: virtual address of the beginning of the memory regien
+ * @begin: virtual address of the beginning of the memory region
  * @end: virtual address of the end of the memory region
  * @virt: virtual address of the memory object
  * @size: size of the memory object
@@ -127,7 +127,10 @@ static inline bool memory_intersects(void *begin, void *end, void *virt,
 {
 	void *vend = virt + size;
 
-	return (virt >= begin && virt < end) || (vend >= begin && vend < end);
+	if (virt < end && vend > begin)
+		return true;
+
+	return false;
 }
 
 /**

include/linux/blkdev.h

@@ -1402,6 +1402,17 @@ static inline unsigned int queue_max_zone_append_sectors(const struct request_qu
 	return min(l->max_zone_append_sectors, l->max_sectors);
 }
 
+static inline unsigned int
+bdev_max_zone_append_sectors(struct block_device *bdev)
+{
+	return queue_max_zone_append_sectors(bdev_get_queue(bdev));
+}
+
+static inline unsigned int bdev_max_segments(struct block_device *bdev)
+{
+	return queue_max_segments(bdev_get_queue(bdev));
+}
+
 static inline unsigned queue_logical_block_size(const struct request_queue *q)
 {
 	int retval = 512;

include/linux/cpumask.h

@@ -1045,4 +1045,22 @@ cpumap_print_list_to_buf(char *buf, const struct cpumask *mask,
 	[0] =  1UL							\
 } }
 
+/*
+ * Provide a valid theoretical max size for cpumap and cpulist sysfs files
+ * to avoid breaking userspace which may allocate a buffer based on the size
+ * reported by e.g. fstat.
+ *
+ * for cpumap NR_CPUS * 9/32 - 1 should be an exact length.
+ *
+ * For cpulist 7 is (ceil(log10(NR_CPUS)) + 1) allowing for NR_CPUS to be up
+ * to 2 orders of magnitude larger than 8192. And then we divide by 2 to
+ * cover a worst-case of every other cpu being on one of two nodes for a
+ * very large NR_CPUS.
+ *
+ *  Use PAGE_SIZE as a minimum for smaller configurations.
+ */
+#define CPUMAP_FILE_MAX_BYTES  ((((NR_CPUS * 9)/32 - 1) > PAGE_SIZE) \
+					? (NR_CPUS * 9)/32 - 1 : PAGE_SIZE)
+#define CPULIST_FILE_MAX_BYTES  (((NR_CPUS * 7)/2 > PAGE_SIZE) ? (NR_CPUS * 7)/2 : PAGE_SIZE)
+
 #endif /* __LINUX_CPUMASK_H */

include/linux/memcontrol.h

@@ -995,19 +995,30 @@ static inline void mod_memcg_state(struct mem_cgroup *memcg,
 
 static inline unsigned long memcg_page_state(struct mem_cgroup *memcg, int idx)
 {
-	return READ_ONCE(memcg->vmstats.state[idx]);
+	long x = READ_ONCE(memcg->vmstats.state[idx]);
+#ifdef CONFIG_SMP
+	if (x < 0)
+		x = 0;
+#endif
+	return x;
 }
 
 static inline unsigned long lruvec_page_state(struct lruvec *lruvec,
 					      enum node_stat_item idx)
 {
 	struct mem_cgroup_per_node *pn;
+	long x;
 
 	if (mem_cgroup_disabled())
 		return node_page_state(lruvec_pgdat(lruvec), idx);
 
 	pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
-	return READ_ONCE(pn->lruvec_stats.state[idx]);
+	x = READ_ONCE(pn->lruvec_stats.state[idx]);
+#ifdef CONFIG_SMP
+	if (x < 0)
+		x = 0;
+#endif
+	return x;
 }
 
 static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec,

include/linux/mlx5/driver.h

@@ -759,6 +759,7 @@ struct mlx5_core_dev {
 	enum mlx5_device_state	state;
 	/* sync interface state */
 	struct mutex		intf_state_mutex;
+	struct lock_class_key	lock_key;
 	unsigned long		intf_state;
 	struct mlx5_priv	priv;
 	struct mlx5_profile	profile;

include/linux/netdevice.h

@@ -640,9 +640,23 @@ extern int sysctl_devconf_inherit_init_net;
  */
 static inline bool net_has_fallback_tunnels(const struct net *net)
 {
-	return !IS_ENABLED(CONFIG_SYSCTL) ||
-	       !sysctl_fb_tunnels_only_for_init_net ||
-	       (net == &init_net && sysctl_fb_tunnels_only_for_init_net == 1);
+#if IS_ENABLED(CONFIG_SYSCTL)
+	int fb_tunnels_only_for_init_net = READ_ONCE(sysctl_fb_tunnels_only_for_init_net);
+
+	return !fb_tunnels_only_for_init_net ||
+		(net_eq(net, &init_net) && fb_tunnels_only_for_init_net == 1);
+#else
+	return true;
+#endif
+}
+
+static inline int net_inherit_devconf(void)
+{
+#if IS_ENABLED(CONFIG_SYSCTL)
+	return READ_ONCE(sysctl_devconf_inherit_init_net);
+#else
+	return 0;
+#endif
 }
 
 static inline int netdev_queue_numa_node_read(const struct netdev_queue *q)

include/linux/netfilter_bridge/ebtables.h

@@ -94,10 +94,6 @@ struct ebt_table {
 	struct ebt_replace_kernel *table;
 	unsigned int valid_hooks;
 	rwlock_t lock;
-	/* e.g. could be the table explicitly only allows certain
-	 * matches, targets, ... 0 == let it in */
-	int (*check)(const struct ebt_table_info *info,
-	   unsigned int valid_hooks);
 	/* the data used by the kernel */
 	struct ebt_table_info *private;
 	struct nf_hook_ops *ops;

include/net/busy_poll.h

@@ -33,7 +33,7 @@ extern unsigned int sysctl_net_busy_poll __read_mostly;
 
 static inline bool net_busy_loop_on(void)
 {
-	return sysctl_net_busy_poll;
+	return READ_ONCE(sysctl_net_busy_poll);
 }
 
 static inline bool sk_can_busy_loop(const struct sock *sk)

include/net/netfilter/nf_flow_table.h

@@ -266,6 +266,7 @@ void flow_offload_refresh(struct nf_flowtable *flow_table,
 
 struct flow_offload_tuple_rhash *flow_offload_lookup(struct nf_flowtable *flow_table,
 						     struct flow_offload_tuple *tuple);
+void nf_flow_table_gc_run(struct nf_flowtable *flow_table);
 void nf_flow_table_gc_cleanup(struct nf_flowtable *flowtable,
 			      struct net_device *dev);
 void nf_flow_table_cleanup(struct net_device *dev);
@@ -302,6 +303,8 @@ void nf_flow_offload_stats(struct nf_flowtable *flowtable,
 			   struct flow_offload *flow);
 
 void nf_flow_table_offload_flush(struct nf_flowtable *flowtable);
+void nf_flow_table_offload_flush_cleanup(struct nf_flowtable *flowtable);
+
 int nf_flow_table_offload_setup(struct nf_flowtable *flowtable,
 				struct net_device *dev,
 				enum flow_block_command cmd);

include/net/netfilter/nf_tables.h

@@ -193,13 +193,18 @@ struct nft_ctx {
 	bool				report;
 };
 
-struct nft_data_desc {
-	enum nft_data_types		type;
-	unsigned int			len;
+enum nft_data_desc_flags {
+	NFT_DATA_DESC_SETELEM	= (1 << 0),
 };
 
-int nft_data_init(const struct nft_ctx *ctx,
-		  struct nft_data *data, unsigned int size,
+struct nft_data_desc {
+	enum nft_data_types		type;
+	unsigned int			size;
+	unsigned int			len;
+	unsigned int			flags;
+};
+
+int nft_data_init(const struct nft_ctx *ctx, struct nft_data *data,
 		  struct nft_data_desc *desc, const struct nlattr *nla);
 void nft_data_hold(const struct nft_data *data, enum nft_data_types type);
 void nft_data_release(const struct nft_data *data, enum nft_data_types type);
@@ -1595,6 +1600,7 @@ struct nftables_pernet {
 	struct list_head	module_list;
 	struct list_head	notify_list;
 	struct mutex		commit_mutex;
+	u64			table_handle;
 	unsigned int		base_seq;
 	u8			validate_state;
 };

include/net/netfilter/nf_tables_core.h

@@ -40,6 +40,14 @@ struct nft_cmp_fast_expr {
 	bool			inv;
 };
 
+struct nft_cmp16_fast_expr {
+	struct nft_data		data;
+	struct nft_data		mask;
+	u8			sreg;
+	u8			len;
+	bool			inv;
+};
+
 struct nft_immediate_expr {
 	struct nft_data		data;
 	u8			dreg;
@@ -57,6 +65,7 @@ static inline u32 nft_cmp_fast_mask(unsigned int len)
 }
 
 extern const struct nft_expr_ops nft_cmp_fast_ops;
+extern const struct nft_expr_ops nft_cmp16_fast_ops;
 
 struct nft_payload {
 	enum nft_payload_bases	base:8;

include/net/tcp.h

@@ -571,6 +571,8 @@ __u32 cookie_v6_init_sequence(const struct sk_buff *skb, __u16 *mss);
 #endif
 /* tcp_output.c */
 
+void tcp_skb_entail(struct sock *sk, struct sk_buff *skb);
+void tcp_mark_push(struct tcp_sock *tp, struct sk_buff *skb);
 void __tcp_push_pending_frames(struct sock *sk, unsigned int cur_mss,
 			       int nonagle);
 int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs);

include/ufs/ufshci.h

@@ -135,11 +135,7 @@ static inline u32 ufshci_version(u32 major, u32 minor)
 
 #define UFSHCD_UIC_MASK		(UIC_COMMAND_COMPL | UFSHCD_UIC_PWR_MASK)
 
-#define UFSHCD_ERROR_MASK	(UIC_ERROR |\
-				DEVICE_FATAL_ERROR |\
-				CONTROLLER_FATAL_ERROR |\
-				SYSTEM_BUS_FATAL_ERROR |\
-				CRYPTO_ENGINE_FATAL_ERROR)
+#define UFSHCD_ERROR_MASK	(UIC_ERROR | INT_FATAL_ERRORS)
 
 #define INT_FATAL_ERRORS	(DEVICE_FATAL_ERROR |\
 				CONTROLLER_FATAL_ERROR |\

kernel/audit_fsnotify.c

@@ -102,6 +102,7 @@ struct audit_fsnotify_mark *audit_alloc_mark(struct audit_krule *krule, char *pa
 
 	ret = fsnotify_add_inode_mark(&audit_mark->mark, inode, true);
 	if (ret < 0) {
+		audit_mark->path = NULL;
 		fsnotify_put_mark(&audit_mark->mark);
 		audit_mark = ERR_PTR(ret);
 	}

kernel/bpf/verifier.c

@@ -6096,8 +6096,7 @@ record_func_key(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta,
 	struct bpf_insn_aux_data *aux = &env->insn_aux_data[insn_idx];
 	struct bpf_reg_state *regs = cur_regs(env), *reg;
 	struct bpf_map *map = meta->map_ptr;
-	struct tnum range;
-	u64 val;
+	u64 val, max;
 	int err;
 
 	if (func_id != BPF_FUNC_tail_call)
@@ -6107,10 +6106,11 @@ record_func_key(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta,
 		return -EINVAL;
 	}
 
-	range = tnum_range(0, map->max_entries - 1);
 	reg = &regs[BPF_REG_3];
+	val = reg->var_off.value;
+	max = map->max_entries;
 
-	if (!register_is_const(reg) || !tnum_in(range, reg->var_off)) {
+	if (!(register_is_const(reg) && val < max)) {
 		bpf_map_key_store(aux, BPF_MAP_KEY_POISON);
 		return 0;
 	}
@@ -6118,8 +6118,6 @@ record_func_key(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta,
 	err = mark_chain_precision(env, BPF_REG_3);
 	if (err)
 		return err;
-
-	val = reg->var_off.value;
 	if (bpf_map_key_unseen(aux))
 		bpf_map_key_store(aux, val);
 	else if (!bpf_map_key_poisoned(aux) &&

kernel/cgroup/cgroup.c

@@ -1813,6 +1813,7 @@ int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask)
 
 		if (ss->css_rstat_flush) {
 			list_del_rcu(&css->rstat_css_node);
+			synchronize_rcu();
 			list_add_rcu(&css->rstat_css_node,
 				     &dcgrp->rstat_css_list);
 		}

kernel/sys_ni.c

@@ -276,6 +276,7 @@ COND_SYSCALL(landlock_restrict_self);
 
 /* mm/fadvise.c */
 COND_SYSCALL(fadvise64_64);
+COND_SYSCALL_COMPAT(fadvise64_64);
 
 /* mm/, CONFIG_MMU only */
 COND_SYSCALL(swapon);