Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Cross-merge networking fixes after downstream PR (net-7.0-rc7).

Conflicts:

net/vmw_vsock/af_vsock.c
b18c83388874 ("vsock: initialize child_ns_mode_locked in vsock_net_init()")
0de607dc4fd8 ("vsock: add G2H fallback for CIDs not owned by H2G transport")

Adjacent changes:

drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
ceee35e5674a ("bnxt_en: Refactor some basic ring setup and adjustment logic")
57cdfe0dc70b ("bnxt_en: Resize RSS contexts on channel count change")

drivers/net/wireless/intel/iwlwifi/mld/mac80211.c
4d56037a02bd ("wifi: iwlwifi: mld: block EMLSR during TDLS connections")
687a95d204e7 ("wifi: iwlwifi: mld: correctly set wifi generation data")

drivers/net/wireless/intel/iwlwifi/mld/scan.h
b6045c899e37 ("wifi: iwlwifi: mld: Refactor scan command handling")
ec66ec6a5a8f ("wifi: iwlwifi: mld: Fix MLO scan timing")

drivers/net/wireless/intel/iwlwifi/mvm/fw.c
078df640ef05 ("wifi: iwlwifi: mld: add support for iwl_mcc_allowed_ap_type_cmd v
2")
323156c3541e ("wifi: iwlwifi: mvm: don't send a 6E related command when not supported")

Signed-off-by: Jakub Kicinski <[e-mail]>

.mailmap

···
 Hans Verkuil <[e-mail]> <[e-mail]>
 Hao Ge <[e-mail]> <[e-mail]>
 Harry Yoo <[e-mail]> <[e-mail]>
+Harry Yoo <[e-mail]> <[e-mail]>
 Heiko Carstens <[e-mail]> <[e-mail]>
 Heiko Carstens <[e-mail]> <[e-mail]>
 Heiko Stuebner <[e-mail]> <[e-mail]>

Documentation/PCI/pcieaer-howto.rst

···
 the error message to the Root Port. Please refer to PCIe specs for other
 fields.
 
+The 'TLP Header' is the prefix/header of the TLP that caused the error
+in raw hex format. To decode the TLP Header into human-readable form
+one may use tlp-tool:
+
+https://github.com/mmpg-x86/tlp-tool
+
+Example usage::
+
+  curl -L https://git.kernel.org/linus/2ca1c94ce0b6 | rtlp-tool --aer
+
 AER Ratelimits
 --------------
 

Documentation/devicetree/bindings/auxdisplay/holtek,ht16k33.yaml

···
   required:
     - refresh-rate-hz
 
-additionalProperties: false
+unevaluatedProperties: false
 
 examples:
   - |

Documentation/devicetree/bindings/sound/rockchip-spdif.yaml

···
           - const: rockchip,rk3066-spdif
       - items:
           - enum:
+              - rockchip,rk3576-spdif
               - rockchip,rk3588-spdif
           - const: rockchip,rk3568-spdif
 

Documentation/devicetree/bindings/sound/st,stm32-sai.yaml

···
       properties:
         compatible:
           contains:
-            const: st,stm32mph7-sai
+            const: st,stm32h7-sai
     then:
       properties:
         clocks:

Documentation/filesystems/overlayfs.rst

···
     mounted with "uuid=on".
 
 
+Durability and copy up
+----------------------
+
+The fsync(2) system call ensures that the data and metadata of a file
+are safely written to the backing storage, which is expected to
+guarantee the existence of the information post system crash.
+
+Without an fsync(2) call, there is no guarantee that the observed
+data after a system crash will be either the old or the new data, but
+in practice, the observed data after crash is often the old or new data
+or a mix of both.
+
+When an overlayfs file is modified for the first time, copy up will
+create a copy of the lower file and its parent directories in the upper
+layer.  Since the Linux filesystem API does not enforce any particular
+ordering on storing changes without explicit fsync(2) calls, in case
+of a system crash, the upper file could end up with no data at all
+(i.e. zeros), which would be an unusual outcome.  To avoid this
+experience, overlayfs calls fsync(2) on the upper file before completing
+data copy up with rename(2) or link(2) to make the copy up "atomic".
+
+By default, overlayfs does not explicitly call fsync(2) on copied up
+directories or on metadata-only copy up, so it provides no guarantee to
+persist the user's modification unless the user calls fsync(2).
+The fsync during copy up only guarantees that if a copy up is observed
+after a crash, the observed data is not zeroes or intermediate values
+from the copy up staging area.
+
+On traditional local filesystems with a single journal (e.g. ext4, xfs),
+fsync on a file also persists the parent directory changes, because they
+are usually modified in the same transaction, so metadata durability during
+data copy up effectively comes for free.  Overlayfs further limits risk by
+disallowing network filesystems as upper layer.
+
+Overlayfs can be tuned to prefer performance or durability when storing
+to the underlying upper layer.  This is controlled by the "fsync" mount
+option, which supports these values:
+
+- "auto": (default)
+    Call fsync(2) on upper file before completion of data copy up.
+    No explicit fsync(2) on directory or metadata-only copy up.
+- "strict":
+    Call fsync(2) on upper file and directories before completion of any
+    copy up.
+- "volatile": [*]
+    Prefer performance over durability (see `Volatile mount`_)
+
+[*] The mount option "volatile" is an alias to "fsync=volatile".
+
+
 Volatile mount
 --------------
 

Documentation/hwmon/adm1177.rst

···
 Sysfs entries
 -------------
 
-The following attributes are supported. Current maxim attribute
+The following attributes are supported. Current maximum attribute
 is read-write, all other attributes are read-only.
 
-in0_input		Measured voltage in microvolts.
+in0_input		Measured voltage in millivolts.
 
-curr1_input		Measured current in microamperes.
-curr1_max_alarm		Overcurrent alarm in microamperes.
+curr1_input		Measured current in milliamperes.
+curr1_max		Overcurrent shutdown threshold in milliamperes.

Documentation/hwmon/peci-cputemp.rst

···
 temp1_crit		Provides shutdown temperature of the CPU package which
 			is also known as the maximum processor junction
 			temperature, Tjmax or Tprochot.
-temp1_crit_hyst		Provides the hysteresis value from Tcontrol to Tjmax of
-			the CPU package.
+temp1_crit_hyst		Provides the hysteresis temperature of the CPU
+			package. Returns Tcontrol, the temperature at which
+			the critical condition clears.
 
 temp2_label		"DTS"
 temp2_input		Provides current temperature of the CPU package scaled
···
 temp2_crit		Provides shutdown temperature of the CPU package which
 			is also known as the maximum processor junction
 			temperature, Tjmax or Tprochot.
-temp2_crit_hyst		Provides the hysteresis value from Tcontrol to Tjmax of
-			the CPU package.
+temp2_crit_hyst		Provides the hysteresis temperature of the CPU
+			package. Returns Tcontrol, the temperature at which
+			the critical condition clears.
 
 temp3_label		"Tcontrol"
 temp3_input		Provides current Tcontrol temperature of the CPU

Documentation/userspace-api/landlock.rst

···
 =====================================
 
 :Author: Mickaël Salaün
-:Date: January 2026
+:Date: March 2026
 
 The goal of Landlock is to enable restriction of ambient rights (e.g. global
 filesystem or network access) for a set of processes.  Because Landlock
···
 
 .. code-block:: c
 
-    __u32 restrict_flags = LANDLOCK_RESTRICT_SELF_LOG_NEW_EXEC_ON;
-    if (abi < 7) {
-        /* Clear logging flags unsupported before ABI 7. */
+    __u32 restrict_flags =
+        LANDLOCK_RESTRICT_SELF_LOG_NEW_EXEC_ON |
+        LANDLOCK_RESTRICT_SELF_TSYNC;
+    switch (abi) {
+    case 1 ... 6:
+        /* Removes logging flags for ABI < 7 */
         restrict_flags &= ~(LANDLOCK_RESTRICT_SELF_LOG_SAME_EXEC_OFF |
                             LANDLOCK_RESTRICT_SELF_LOG_NEW_EXEC_ON |
                             LANDLOCK_RESTRICT_SELF_LOG_SUBDOMAINS_OFF);
+        __attribute__((fallthrough));
+    case 7:
+        /*
+         * Removes multithreaded enforcement flag for ABI < 8
+         *
+         * WARNING: Without this flag, calling landlock_restrict_self(2) is
+         * only equivalent if the calling process is single-threaded. Below
+         * ABI v8 (and as of ABI v8, when not using this flag), a Landlock
+         * policy would only be enforced for the calling thread and its
+         * children (and not for all threads, including parents and siblings).
+         */
+        restrict_flags &= ~LANDLOCK_RESTRICT_SELF_TSYNC;
     }
 
 The next step is to restrict the current thread from gaining more privileges

MAINTAINERS

···
 F:	include/uapi/drm/lima_drm.h
 
 DRM DRIVERS FOR LOONGSON
+M:	Jianmin Lv <[e-mail]>
+M:	Qianhai Wu <[e-mail]>
+R:	Huacai Chen <[e-mail]>
+R:	Mingcong Bai <[e-mail]>
+R:	Xi Ruoyao <[e-mail]>
+R:	Icenowy Zheng <[e-mail]>
 L:	[e-mail]
-S:	Orphan
+S:	Maintained
 T:	git https://gitlab.freedesktop.org/drm/misc/kernel.git
 F:	drivers/gpu/drm/loongson/
 
···
 
 EXT4 FILE SYSTEM
 M:	"Theodore Ts'o" <[e-mail]>
-M:	Andreas Dilger <[e-mail]>
+R:	Andreas Dilger <[e-mail]>
+R:	Baokun Li <[e-mail]>
+R:	Jan Kara <[e-mail]>
+R:	Ojaswin Mujoo <[e-mail]>
+R:	Ritesh Harjani (IBM) <[e-mail]>
+R:	Zhang Yi <[e-mail]>
 L:	[e-mail]
 S:	Maintained
 W:	http://ext4.wiki.kernel.org
···
 M:	Wolfram Sang <[e-mail]>
 L:	[e-mail]
 S:	Maintained
-W:	https://i2c.wiki.kernel.org/
 Q:	https://patchwork.ozlabs.org/project/linux-i2c/list/
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/wsa/linux.git
 F:	Documentation/i2c/
···
 M:	Andi Shyti <[e-mail]>
 L:	[e-mail]
 S:	Maintained
-W:	https://i2c.wiki.kernel.org/
 Q:	https://patchwork.ozlabs.org/project/linux-i2c/list/
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/andi.shyti/linux.git
 F:	Documentation/devicetree/bindings/i2c/
···
 R:	Rik van Riel <[e-mail]>
 R:	Liam R. Howlett <[e-mail]>
 R:	Vlastimil Babka <[e-mail]>
-R:	Harry Yoo <[e-mail]>
+R:	Harry Yoo <[e-mail]>
 R:	Jann Horn <[e-mail]>
 L:	[e-mail]
 S:	Maintained
···
 
 SLAB ALLOCATOR
 M:	Vlastimil Babka <[e-mail]>
-M:	Harry Yoo <[e-mail]>
+M:	Harry Yoo <[e-mail]>
 M:	Andrew Morton <[e-mail]>
 R:	Hao Li <[e-mail]>
 R:	Christoph Lameter <[e-mail]>

Makefile

···
 VERSION = 7
 PATCHLEVEL = 0
 SUBLEVEL = 0
-EXTRAVERSION = -rc5
+EXTRAVERSION = -rc6
 NAME = Baby Opossum Posse
 
 # *DOCUMENTATION*

arch/loongarch/include/asm/linkage.h

···
 	.cfi_endproc;					\
 	SYM_END(name, SYM_T_NONE)
 
+/*
+ * This is for the signal handler trampoline, which is used as the return
+ * address of the signal handlers in userspace instead of called normally.
+ * The long standing libgcc bug https://gcc.gnu.org/PR124050 requires a
+ * nop between .cfi_startproc and the actual address of the trampoline, so
+ * we cannot simply use SYM_FUNC_START.
+ *
+ * This wrapper also contains all the .cfi_* directives for recovering
+ * the content of the GPRs and the "return address" (where the rt_sigreturn
+ * syscall will jump to), assuming there is a struct rt_sigframe (where
+ * a struct sigcontext containing those information we need to recover) at
+ * $sp.  The "DWARF for the LoongArch(TM) Architecture" manual states
+ * column 0 is for $zero, but it does not make too much sense to
+ * save/restore the hardware zero register.  Repurpose this column here
+ * for the return address (here it's not the content of $ra we cannot use
+ * the default column 3).
+ */
+#define SYM_SIGFUNC_START(name)				\
+	.cfi_startproc;					\
+	.cfi_signal_frame;				\
+	.cfi_def_cfa 3, RT_SIGFRAME_SC;			\
+	.cfi_return_column 0;				\
+	.cfi_offset 0, SC_PC;				\
+							\
+	.irp num, 1,  2,  3,  4,  5,  6,  7,  8, 	\
+		  9,  10, 11, 12, 13, 14, 15, 16,	\
+		  17, 18, 19, 20, 21, 22, 23, 24,	\
+		  25, 26, 27, 28, 29, 30, 31;		\
+	.cfi_offset \num, SC_REGS + \num * SZREG;	\
+	.endr;						\
+							\
+	nop;						\
+	SYM_START(name, SYM_L_GLOBAL, SYM_A_ALIGN)
+
+#define SYM_SIGFUNC_END(name) SYM_FUNC_END(name)
+
 #endif

arch/loongarch/include/asm/sigframe.h

···
+/* SPDX-License-Identifier: GPL-2.0+ */
+
+#include <asm/siginfo.h>
+#include <asm/ucontext.h>
+
+struct rt_sigframe {
+	struct siginfo rs_info;
+	struct ucontext rs_uctx;
+};

arch/loongarch/kernel/asm-offsets.c

···
 #include <asm/ptrace.h>
 #include <asm/processor.h>
 #include <asm/ftrace.h>
+#include <asm/sigframe.h>
 #include <vdso/datapage.h>
 
 static void __used output_ptreg_defines(void)
···
 	COMMENT("Linux sigcontext offsets.");
 	OFFSET(SC_REGS, sigcontext, sc_regs);
 	OFFSET(SC_PC, sigcontext, sc_pc);
+	OFFSET(RT_SIGFRAME_SC, rt_sigframe, rs_uctx.uc_mcontext);
 	BLANK();
 }
 

arch/loongarch/kernel/env.c

···
 	int cpu, ret;
 	char *cpuname;
 	const char *model;
-	struct device_node *root;
 
 	/* Parsing cpuname from DTS model property */
-	root = of_find_node_by_path("/");
-	ret = of_property_read_string(root, "model", &model);
+	ret = of_property_read_string(of_root, "model", &model);
 	if (ret == 0) {
 		cpuname = kstrdup(model, GFP_KERNEL);
+		if (!cpuname)
+			return -ENOMEM;
 		loongson_sysconf.cpuname = strsep(&cpuname, " ");
 	}
-	of_node_put(root);
 
 	if (loongson_sysconf.cpuname && !strncmp(loongson_sysconf.cpuname, "Loongson", 8)) {
 		for (cpu = 0; cpu < NR_CPUS; cpu++)

arch/loongarch/kernel/signal.c

···
 #include <asm/cpu-features.h>
 #include <asm/fpu.h>
 #include <asm/lbt.h>
+#include <asm/sigframe.h>
 #include <asm/ucontext.h>
 #include <asm/vdso.h>
 
···
 /* Make sure we will not lose LBT ownership */
 #define lock_lbt_owner()	({ preempt_disable(); pagefault_disable(); })
 #define unlock_lbt_owner()	({ pagefault_enable(); preempt_enable(); })
-
-struct rt_sigframe {
-	struct siginfo rs_info;
-	struct ucontext rs_uctx;
-};
 
 struct _ctx_layout {
 	struct sctx_info *addr;

arch/loongarch/kvm/intc/eiointc.c

···
 
 		if (!(s->status & BIT(EIOINTC_ENABLE_CPU_ENCODE))) {
 			cpuid = ffs(cpuid) - 1;
-			cpuid = (cpuid >= 4) ? 0 : cpuid;
+			cpuid = ((cpuid < 0) || (cpuid >= 4)) ? 0 : cpuid;
 		}
 
 		vcpu = kvm_get_vcpu_by_cpuid(s->kvm, cpuid);
···
 	switch (addr) {
 	case EIOINTC_NODETYPE_START ... EIOINTC_NODETYPE_END:
 		offset = (addr - EIOINTC_NODETYPE_START) / 4;
-		p = s->nodetype + offset * 4;
+		p = (void *)s->nodetype + offset * 4;
 		break;
 	case EIOINTC_IPMAP_START ... EIOINTC_IPMAP_END:
 		offset = (addr - EIOINTC_IPMAP_START) / 4;
-		p = &s->ipmap + offset * 4;
+		p = (void *)&s->ipmap + offset * 4;
 		break;
 	case EIOINTC_ENABLE_START ... EIOINTC_ENABLE_END:
 		offset = (addr - EIOINTC_ENABLE_START) / 4;
-		p = s->enable + offset * 4;
+		p = (void *)s->enable + offset * 4;
 		break;
 	case EIOINTC_BOUNCE_START ... EIOINTC_BOUNCE_END:
 		offset = (addr - EIOINTC_BOUNCE_START) / 4;
-		p = s->bounce + offset * 4;
+		p = (void *)s->bounce + offset * 4;
 		break;
 	case EIOINTC_ISR_START ... EIOINTC_ISR_END:
 		offset = (addr - EIOINTC_ISR_START) / 4;
-		p = s->isr + offset * 4;
+		p = (void *)s->isr + offset * 4;
 		break;
 	case EIOINTC_COREISR_START ... EIOINTC_COREISR_END:
 		if (cpu >= s->num_cpu)
 			return -EINVAL;
 
 		offset = (addr - EIOINTC_COREISR_START) / 4;
-		p = s->coreisr[cpu] + offset * 4;
+		p = (void *)s->coreisr[cpu] + offset * 4;
 		break;
 	case EIOINTC_COREMAP_START ... EIOINTC_COREMAP_END:
 		offset = (addr - EIOINTC_COREMAP_START) / 4;
-		p = s->coremap + offset * 4;
+		p = (void *)s->coremap + offset * 4;
 		break;
 	default:
 		kvm_err("%s: unknown eiointc register, addr = %d\n", __func__, addr);

arch/loongarch/kvm/vcpu.c

···
 {
 	struct kvm_phyid_map *map;
 
+	if (cpuid < 0)
+		return NULL;
+
 	if (cpuid >= KVM_MAX_PHYID)
 		return NULL;
 

arch/loongarch/pci/pci.c

···
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/acpi.h>
+#include <linux/delay.h>
 #include <linux/types.h>
 #include <linux/pci.h>
 #include <linux/vgaarb.h>
+#include <linux/io-64-nonatomic-lo-hi.h>
 #include <asm/cacheflush.h>
 #include <asm/loongson.h>
 
···
 #define PCI_DEVICE_ID_LOONGSON_DC1      0x7a06
 #define PCI_DEVICE_ID_LOONGSON_DC2      0x7a36
 #define PCI_DEVICE_ID_LOONGSON_DC3      0x7a46
+#define PCI_DEVICE_ID_LOONGSON_GPU1     0x7a15
+#define PCI_DEVICE_ID_LOONGSON_GPU2     0x7a25
+#define PCI_DEVICE_ID_LOONGSON_GPU3     0x7a35
 
 int raw_pci_read(unsigned int domain, unsigned int bus, unsigned int devfn,
 						int reg, int len, u32 *val)
···
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_LOONGSON, PCI_DEVICE_ID_LOONGSON_DC1, pci_fixup_vgadev);
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_LOONGSON, PCI_DEVICE_ID_LOONGSON_DC2, pci_fixup_vgadev);
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_LOONGSON, PCI_DEVICE_ID_LOONGSON_DC3, pci_fixup_vgadev);
+
+#define CRTC_NUM_MAX		2
+#define CRTC_OUTPUT_ENABLE	0x100
+
+static void loongson_gpu_fixup_dma_hang(struct pci_dev *pdev, bool on)
+{
+	u32 i, val, count, crtc_offset, device;
+	void __iomem *crtc_reg, *base, *regbase;
+	static u32 crtc_status[CRTC_NUM_MAX] = { 0 };
+
+	base = pdev->bus->ops->map_bus(pdev->bus, pdev->devfn + 1, 0);
+	device = readw(base + PCI_DEVICE_ID);
+
+	regbase = ioremap(readq(base + PCI_BASE_ADDRESS_0) & ~0xffull, SZ_64K);
+	if (!regbase) {
+		pci_err(pdev, "Failed to ioremap()\n");
+		return;
+	}
+
+	switch (device) {
+	case PCI_DEVICE_ID_LOONGSON_DC2:
+		crtc_reg = regbase + 0x1240;
+		crtc_offset = 0x10;
+		break;
+	case PCI_DEVICE_ID_LOONGSON_DC3:
+		crtc_reg = regbase;
+		crtc_offset = 0x400;
+		break;
+	}
+
+	for (i = 0; i < CRTC_NUM_MAX; i++, crtc_reg += crtc_offset) {
+		val = readl(crtc_reg);
+
+		if (!on)
+			crtc_status[i] = val;
+
+		/* No need to fixup if the status is off at startup. */
+		if (!(crtc_status[i] & CRTC_OUTPUT_ENABLE))
+			continue;
+
+		if (on)
+			val |= CRTC_OUTPUT_ENABLE;
+		else
+			val &= ~CRTC_OUTPUT_ENABLE;
+
+		mb();
+		writel(val, crtc_reg);
+
+		for (count = 0; count < 40; count++) {
+			val = readl(crtc_reg) & CRTC_OUTPUT_ENABLE;
+			if ((on && val) || (!on && !val))
+				break;
+			udelay(1000);
+		}
+
+		pci_info(pdev, "DMA hang fixup at reg[0x%lx]: 0x%x\n",
+				(unsigned long)crtc_reg & 0xffff, readl(crtc_reg));
+	}
+
+	iounmap(regbase);
+}
+
+static void pci_fixup_dma_hang_early(struct pci_dev *pdev)
+{
+	loongson_gpu_fixup_dma_hang(pdev, false);
+}
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_LOONGSON, PCI_DEVICE_ID_LOONGSON_GPU2, pci_fixup_dma_hang_early);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_LOONGSON, PCI_DEVICE_ID_LOONGSON_GPU3, pci_fixup_dma_hang_early);
+
+static void pci_fixup_dma_hang_final(struct pci_dev *pdev)
+{
+	loongson_gpu_fixup_dma_hang(pdev, true);
+}
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_LOONGSON, PCI_DEVICE_ID_LOONGSON_GPU2, pci_fixup_dma_hang_final);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_LOONGSON, PCI_DEVICE_ID_LOONGSON_GPU3, pci_fixup_dma_hang_final);

arch/loongarch/vdso/Makefile

···
 	$(filter -W%,$(filter-out -Wa$(comma)%,$(KBUILD_CFLAGS))) \
 	-std=gnu11 -fms-extensions -O2 -g -fno-strict-aliasing -fno-common -fno-builtin \
 	-fno-stack-protector -fno-jump-tables -DDISABLE_BRANCH_PROFILING \
-	$(call cc-option, -fno-asynchronous-unwind-tables) \
+	$(call cc-option, -fasynchronous-unwind-tables) \
 	$(call cc-option, -fno-stack-protector)
 aflags-vdso := $(ccflags-vdso) \
 	-D__ASSEMBLY__ -Wa,-gdwarf-2
···
 
 # VDSO linker flags.
 ldflags-y := -Bsymbolic --no-undefined -soname=linux-vdso.so.1 \
-	$(filter -E%,$(KBUILD_CFLAGS)) -shared --build-id -T
+	$(filter -E%,$(KBUILD_CFLAGS)) -shared --build-id --eh-frame-hdr -T
 
 #
 # Shared build commands.

arch/loongarch/vdso/sigreturn.S

···
 
 #include <asm/regdef.h>
 #include <asm/asm.h>
+#include <asm/asm-offsets.h>
 
 	.section	.text
-	.cfi_sections	.debug_frame
 
-SYM_FUNC_START(__vdso_rt_sigreturn)
+SYM_SIGFUNC_START(__vdso_rt_sigreturn)
 
 	li.w	a7, __NR_rt_sigreturn
 	syscall	0
 
-SYM_FUNC_END(__vdso_rt_sigreturn)
+SYM_SIGFUNC_END(__vdso_rt_sigreturn)

arch/s390/include/asm/barrier.h

···
  * @size: number of elements in array
  */
 #define array_index_mask_nospec array_index_mask_nospec
-static inline unsigned long array_index_mask_nospec(unsigned long index,
-						    unsigned long size)
+static __always_inline unsigned long array_index_mask_nospec(unsigned long index,
+							     unsigned long size)
 {
 	unsigned long mask;
 

arch/s390/kernel/entry.S

···
 	xgr	%r9,%r9
 	xgr	%r10,%r10
 	xgr	%r11,%r11
+	xgr	%r12,%r12
 	la	%r2,STACK_FRAME_OVERHEAD(%r15)	# pointer to pt_regs
 	mvc	__PT_R8(64,%r2),__LC_SAVE_AREA(%r13)
 	MBEAR	%r2,%r13
···
 	xgr	%r6,%r6
 	xgr	%r7,%r7
 	xgr	%r10,%r10
+	xgr	%r12,%r12
 	xc	__PT_FLAGS(8,%r11),__PT_FLAGS(%r11)
 	mvc	__PT_R8(64,%r11),__LC_SAVE_AREA(%r13)
 	MBEAR	%r11,%r13
···
 	xgr	%r6,%r6
 	xgr	%r7,%r7
 	xgr	%r10,%r10
+	xgr	%r12,%r12
 	stmg	%r8,%r9,__PT_PSW(%r11)
 	xc	__PT_FLAGS(8,%r11),__PT_FLAGS(%r11)
 	xc	__SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15)

arch/s390/kernel/syscall.c

···
  */
 
 #include <linux/cpufeature.h>
+#include <linux/nospec.h>
 #include <linux/errno.h>
 #include <linux/sched.h>
 #include <linux/mm.h>
···
 	if (unlikely(test_and_clear_pt_regs_flag(regs, PIF_SYSCALL_RET_SET)))
 		goto out;
 	regs->gprs[2] = -ENOSYS;
-	if (likely(nr < NR_syscalls))
+	if (likely(nr < NR_syscalls)) {
+		nr = array_index_nospec(nr, NR_syscalls);
 		regs->gprs[2] = sys_call_table[nr](regs);
+	}
 out:
 	syscall_exit_to_user_mode(regs);
 }

arch/s390/kvm/dat.c

···
 }
 
 /**
- * dat_crstep_xchg() - Exchange a gmap CRSTE with another.
- * @crstep: Pointer to the CRST entry
- * @new: Replacement entry.
- * @gfn: The affected guest address.
- * @asce: The ASCE of the address space.
- *
- * Context: This function is assumed to be called with kvm->mmu_lock held.
- */
-void dat_crstep_xchg(union crste *crstep, union crste new, gfn_t gfn, union asce asce)
-{
-	if (crstep->h.i) {
-		WRITE_ONCE(*crstep, new);
-		return;
-	} else if (cpu_has_edat2()) {
-		crdte_crste(crstep, *crstep, new, gfn, asce);
-		return;
-	}
-
-	if (machine_has_tlb_guest())
-		idte_crste(crstep, gfn, IDTE_GUEST_ASCE, asce, IDTE_GLOBAL);
-	else
-		idte_crste(crstep, gfn, 0, NULL_ASCE, IDTE_GLOBAL);
-	WRITE_ONCE(*crstep, new);
-}
-
-/**
  * dat_crstep_xchg_atomic() - Atomically exchange a gmap CRSTE with another.
  * @crstep: Pointer to the CRST entry.
  * @old: Expected old value.
···
  *
  * Return: %true if the exchange was successful.
  */
-bool dat_crstep_xchg_atomic(union crste *crstep, union crste old, union crste new, gfn_t gfn,
-			    union asce asce)
+bool __must_check dat_crstep_xchg_atomic(union crste *crstep, union crste old, union crste new,
+					 gfn_t gfn, union asce asce)
 {
 	if (old.h.i)
 		return arch_try_cmpxchg((long *)crstep, &old.val, new.val);
···
 				pt->ptes[i].val = init.val | i * PAGE_SIZE;
 			/* No need to take locks as the page table is not installed yet. */
 			pgste_init.prefix_notif = old.s.fc1.prefix_notif;
+			pgste_init.vsie_notif = old.s.fc1.vsie_notif;
 			pgste_init.pcl = uses_skeys && init.h.i;
 			dat_init_pgstes(pt, pgste_init.val);
 		} else {
···
 
 	/* This table entry needs to be updated. */
 	if (walk->start <= gfn && walk->end >= next) {
-		dat_crstep_xchg_atomic(crstep, crste, new_crste, gfn, walk->asce);
+		if (!dat_crstep_xchg_atomic(crstep, crste, new_crste, gfn, walk->asce))
+			return -EINVAL;
 		/* A lower level table was present, needs to be freed. */
 		if (!crste.h.fc && !crste.h.i) {
 			if (is_pmd(crste))
···
 	return _dat_walk_gfn_range(start, end, asce, &test_age_ops, 0, NULL) > 0;
 }
 
-int dat_link(struct kvm_s390_mmu_cache *mc, union asce asce, int level,
-	     bool uses_skeys, struct guest_fault *f)
-{
-	union crste oldval, newval;
-	union pte newpte, oldpte;
-	union pgste pgste;
-	int rc = 0;
-
-	rc = dat_entry_walk(mc, f->gfn, asce, DAT_WALK_ALLOC_CONTINUE, level, &f->crstep, &f->ptep);
-	if (rc == -EINVAL || rc == -ENOMEM)
-		return rc;
-	if (rc)
-		return -EAGAIN;
-
-	if (WARN_ON_ONCE(unlikely(get_level(f->crstep, f->ptep) > level)))
-		return -EINVAL;
-
-	if (f->ptep) {
-		pgste = pgste_get_lock(f->ptep);
-		oldpte = *f->ptep;
-		newpte = _pte(f->pfn, f->writable, f->write_attempt | oldpte.s.d, !f->page);
-		newpte.s.sd = oldpte.s.sd;
-		oldpte.s.sd = 0;
-		if (oldpte.val == _PTE_EMPTY.val || oldpte.h.pfra == f->pfn) {
-			pgste = __dat_ptep_xchg(f->ptep, pgste, newpte, f->gfn, asce, uses_skeys);
-			if (f->callback)
-				f->callback(f);
-		} else {
-			rc = -EAGAIN;
-		}
-		pgste_set_unlock(f->ptep, pgste);
-	} else {
-		oldval = READ_ONCE(*f->crstep);
-		newval = _crste_fc1(f->pfn, oldval.h.tt, f->writable,
-				    f->write_attempt | oldval.s.fc1.d);
-		newval.s.fc1.sd = oldval.s.fc1.sd;
-		if (oldval.val != _CRSTE_EMPTY(oldval.h.tt).val &&
-		    crste_origin_large(oldval) != crste_origin_large(newval))
-			return -EAGAIN;
-		if (!dat_crstep_xchg_atomic(f->crstep, oldval, newval, f->gfn, asce))
-			return -EAGAIN;
-		if (f->callback)
-			f->callback(f);
-	}
-
-	return rc;
-}
-
 static long dat_set_pn_crste(union crste *crstep, gfn_t gfn, gfn_t next, struct dat_walk *walk)
 {
-	union crste crste = READ_ONCE(*crstep);
+	union crste newcrste, oldcrste;
 	int *n = walk->priv;
 
-	if (!crste.h.fc || crste.h.i || crste.h.p)
-		return 0;
-
+	do {
+		oldcrste = READ_ONCE(*crstep);
+		if (!oldcrste.h.fc || oldcrste.h.i || oldcrste.h.p)
+			return 0;
+		if (oldcrste.s.fc1.prefix_notif)
+			break;
+		newcrste = oldcrste;
+		newcrste.s.fc1.prefix_notif = 1;
+	} while (!dat_crstep_xchg_atomic(crstep, oldcrste, newcrste, gfn, walk->asce));
 	*n = 2;
-	if (crste.s.fc1.prefix_notif)
-		return 0;
-	crste.s.fc1.prefix_notif = 1;
-	dat_crstep_xchg(crstep, crste, gfn, walk->asce);
 	return 0;
 }
 

arch/s390/kvm/dat.h

···
 			unsigned long              :44; /* HW */
 			unsigned long              : 3; /* Unused */
 			unsigned long              : 1; /* HW */
+			unsigned long s            : 1; /* Special */
 			unsigned long w            : 1; /* Writable soft-bit */
 			unsigned long r            : 1; /* Readable soft-bit */
 			unsigned long d            : 1; /* Dirty */
 			unsigned long y            : 1; /* Young */
-			unsigned long prefix_notif : 1; /* Guest prefix invalidation notification */
 			unsigned long              : 3; /* HW */
+			unsigned long prefix_notif : 1; /* Guest prefix invalidation notification */
 			unsigned long vsie_notif   : 1; /* Referenced in a shadow table */
-			unsigned long              : 1; /* Unused */
 			unsigned long              : 4; /* HW */
 			unsigned long sd           : 1; /* Soft-Dirty */
 			unsigned long pr           : 1; /* Present */
···
 			unsigned long              :33; /* HW */
 			unsigned long              :14; /* Unused */
 			unsigned long              : 1; /* HW */
+			unsigned long s            : 1; /* Special */
 			unsigned long w            : 1; /* Writable soft-bit */
 			unsigned long r            : 1; /* Readable soft-bit */
 			unsigned long d            : 1; /* Dirty */
 			unsigned long y            : 1; /* Young */
-			unsigned long prefix_notif : 1; /* Guest prefix invalidation notification */
 			unsigned long              : 3; /* HW */
+			unsigned long prefix_notif : 1; /* Guest prefix invalidation notification */
 			unsigned long vsie_notif   : 1; /* Referenced in a shadow table */
-			unsigned long              : 1; /* Unused */
 			unsigned long              : 4; /* HW */
 			unsigned long sd           : 1; /* Soft-Dirty */
 			unsigned long pr           : 1; /* Present */
···
 		struct {
 			unsigned long              :47;
 			unsigned long              : 1; /* HW (should be 0) */
+			unsigned long s            : 1; /* Special */
 			unsigned long w            : 1; /* Writable */
 			unsigned long r            : 1; /* Readable */
 			unsigned long d            : 1; /* Dirty */
 			unsigned long y            : 1; /* Young */
-			unsigned long prefix_notif : 1; /* Guest prefix invalidation notification */
 			unsigned long              : 3; /* HW */
+			unsigned long prefix_notif : 1; /* Guest prefix invalidation notification */
 			unsigned long vsie_notif   : 1; /* Referenced in a shadow table */
-			unsigned long              : 1;
 			unsigned long              : 4; /* HW */
 			unsigned long sd           : 1; /* Soft-Dirty */
 			unsigned long pr           : 1; /* Present */
···
 		 u16 type, u16 param);
 int dat_set_prefix_notif_bit(union asce asce, gfn_t gfn);
 bool dat_test_age_gfn(union asce asce, gfn_t start, gfn_t end);
-int dat_link(struct kvm_s390_mmu_cache *mc, union asce asce, int level,
-	     bool uses_skeys, struct guest_fault *f);
 
 int dat_perform_essa(union asce asce, gfn_t gfn, int orc, union essa_state *state, bool *dirty);
 long dat_reset_cmma(union asce asce, gfn_t start_gfn);
···
 	return dat_crstep_xchg_atomic(_CRSTEP(pudp), _CRSTE(old), _CRSTE(new), gfn, asce);
 }
 
-static inline void dat_crstep_clear(union crste *crstep, gfn_t gfn, union asce asce)
+static inline union crste dat_crstep_clear_atomic(union crste *crstep, gfn_t gfn, union asce asce)
 {
-	union crste newcrste = _CRSTE_EMPTY(crstep->h.tt);
+	union crste oldcrste, empty = _CRSTE_EMPTY(crstep->h.tt);
 
-	dat_crstep_xchg(crstep, newcrste, gfn, asce);
+	do {
+		oldcrste = READ_ONCE(*crstep);
+	} while (!dat_crstep_xchg_atomic(crstep, oldcrste, empty, gfn, asce));
+	return oldcrste;
 }
 
 static inline int get_level(union crste *crstep, union pte *ptep)

arch/s390/kvm/gaccess.c

···
 
 	if (!pgste_get_trylock(ptep_h, &pgste))
 		return -EAGAIN;
-	newpte = _pte(f->pfn, f->writable, !p, 0);
-	newpte.s.d |= ptep->s.d;
-	newpte.s.sd |= ptep->s.sd;
-	newpte.h.p &= ptep->h.p;
-	pgste = _gmap_ptep_xchg(sg->parent, ptep_h, newpte, pgste, f->gfn, false);
-	pgste.vsie_notif = 1;
+	newpte = _pte(f->pfn, f->writable, !p, ptep_h->s.s);
+	newpte.s.d |= ptep_h->s.d;
+	newpte.s.sd |= ptep_h->s.sd;
+	newpte.h.p &= ptep_h->h.p;
+	if (!newpte.h.p && !f->writable) {
+		rc = -EOPNOTSUPP;
+	} else {
+		pgste = _gmap_ptep_xchg(sg->parent, ptep_h, newpte, pgste, f->gfn, false);
+		pgste.vsie_notif = 1;
+	}
 	pgste_set_unlock(ptep_h, pgste);
+	if (rc)
+		return rc;
+	if (!sg->parent)
+		return -EAGAIN;
 
 	newpte = _pte(f->pfn, 0, !p, 0);
 	if (!pgste_get_trylock(ptep, &pgste))
···
 static int _do_shadow_crste(struct gmap *sg, gpa_t raddr, union crste *host, union crste *table,
 			    struct guest_fault *f, bool p)
 {
-	union crste newcrste;
+	union crste newcrste, oldcrste;
 	gfn_t gfn;
 	int rc;
 
···
 	if (rc)
 		return rc;
 
-	newcrste = _crste_fc1(f->pfn, host->h.tt, f->writable, !p);
-	newcrste.s.fc1.d |= host->s.fc1.d;
-	newcrste.s.fc1.sd |= host->s.fc1.sd;
-	newcrste.h.p &= host->h.p;
-	newcrste.s.fc1.vsie_notif = 1;
-	newcrste.s.fc1.prefix_notif = host->s.fc1.prefix_notif;
-	_gmap_crstep_xchg(sg->parent, host, newcrste, f->gfn, false);
+	do {
+		/* _gmap_crstep_xchg_atomic() could have unshadowed this shadow gmap */
+		if (!sg->parent)
+			return -EAGAIN;
+		oldcrste = READ_ONCE(*host);
+		newcrste = _crste_fc1(f->pfn, oldcrste.h.tt, f->writable, !p);
+		newcrste.s.fc1.d |= oldcrste.s.fc1.d;
+		newcrste.s.fc1.sd |= oldcrste.s.fc1.sd;
+		newcrste.h.p &= oldcrste.h.p;
+		newcrste.s.fc1.vsie_notif = 1;
+		newcrste.s.fc1.prefix_notif = oldcrste.s.fc1.prefix_notif;
+		newcrste.s.fc1.s = oldcrste.s.fc1.s;
+		if (!newcrste.h.p && !f->writable)
+			return -EOPNOTSUPP;
+	} while (!_gmap_crstep_xchg_atomic(sg->parent, host, oldcrste, newcrste, f->gfn, false));
+	if (!sg->parent)
+		return -EAGAIN;
 
-	newcrste = _crste_fc1(f->pfn, host->h.tt, 0, !p);
-	dat_crstep_xchg(table, newcrste, gpa_to_gfn(raddr), sg->asce);
+	newcrste = _crste_fc1(f->pfn, oldcrste.h.tt, 0, !p);
+	gfn = gpa_to_gfn(raddr);
+	while (!dat_crstep_xchg_atomic(table, READ_ONCE(*table), newcrste, gfn, sg->asce))
+		;
 	return 0;
 }
 
···
 	if (rc)
 		return rc;
 
-	/* A race occourred. The shadow mapping is already valid, nothing to do */
-	if ((ptep && !ptep->h.i) || (!ptep && crste_leaf(*table)))
+	/* A race occurred. The shadow mapping is already valid, nothing to do */
+	if ((ptep && !ptep->h.i && ptep->h.p == w->p) ||
+	    (!ptep && crste_leaf(*table) && !table->h.i && table->h.p == w->p))
 		return 0;
 
 	gl = get_level(table, ptep);
+
+	/* In case of a real address space */
+	if (w->level <= LEVEL_MEM) {
+		l = TABLE_TYPE_PAGE_TABLE;
+		hl = TABLE_TYPE_REGION1;
+		goto real_address_space;
+	}
 
 	/*
 	 * Skip levels that are already protected. For each level, protect
 	 * only the page containing the entry, not the whole table.
 	 */
 	for (i = gl ; i >= w->level; i--) {
-		rc = gmap_protect_rmap(mc, sg, entries[i - 1].gfn, gpa_to_gfn(saddr),
-				       entries[i - 1].pfn, i, entries[i - 1].writable);
+		rc = gmap_protect_rmap(mc, sg, entries[i].gfn, gpa_to_gfn(saddr),
+				       entries[i].pfn, i + 1, entries[i].writable);
 		if (rc)
 			return rc;
+		if (!sg->parent)
+			return -EAGAIN;
 	}
 
 	rc = dat_entry_walk(NULL, entries[LEVEL_MEM].gfn, sg->parent->asce, DAT_WALK_LEAF,
···
 	/* Get the smallest granularity */
 	l = min3(gl, hl, w->level);
 
+real_address_space:
 	flags = DAT_WALK_SPLIT_ALLOC | (uses_skeys(sg->parent) ? DAT_WALK_USES_SKEYS : 0);
 	/* If necessary, create the shadow mapping */
 	if (l < gl) {

arch/s390/kvm/gmap.c

···
 	struct clear_young_pte_priv *priv = walk->priv;
 	union crste crste, new;
 
-	crste = READ_ONCE(*crstep);
+	do {
+		crste = READ_ONCE(*crstep);
 
-	if (!crste.h.fc)
-		return 0;
-	if (!crste.s.fc1.y && crste.h.i)
-		return 0;
-	if (!crste_prefix(crste) || gmap_mkold_prefix(priv->gmap, gfn, end)) {
+		if (!crste.h.fc)
+			return 0;
+		if (!crste.s.fc1.y && crste.h.i)
+			return 0;
+		if (crste_prefix(crste) && !gmap_mkold_prefix(priv->gmap, gfn, end))
+			break;
+
 		new = crste;
 		new.h.i = 1;
 		new.s.fc1.y = 0;
···
 			folio_set_dirty(phys_to_folio(crste_origin_large(crste)));
 		new.s.fc1.d = 0;
 		new.h.p = 1;
-		dat_crstep_xchg(crstep, new, gfn, walk->asce);
-	}
+	} while (!dat_crstep_xchg_atomic(crstep, crste, new, gfn, walk->asce));
+
 	priv->young = 1;
 	return 0;
 }
···
 {
 	struct gmap_unmap_priv *priv = walk->priv;
 	struct folio *folio = NULL;
+	union crste old = *crstep;
 
-	if (crstep->h.fc) {
-		if (crstep->s.fc1.pr && test_bit(GMAP_FLAG_EXPORT_ON_UNMAP, &priv->gmap->flags))
-			folio = phys_to_folio(crste_origin_large(*crstep));
-		gmap_crstep_xchg(priv->gmap, crstep, _CRSTE_EMPTY(crstep->h.tt), gfn);
-		if (folio)
-			uv_convert_from_secure_folio(folio);
-	}
+	if (!old.h.fc)
+		return 0;
+
+	if (old.s.fc1.pr && test_bit(GMAP_FLAG_EXPORT_ON_UNMAP, &priv->gmap->flags))
+		folio = phys_to_folio(crste_origin_large(old));
+	/* No races should happen because kvm->mmu_lock is held in write mode */
+	KVM_BUG_ON(!gmap_crstep_xchg_atomic(priv->gmap, crstep, old, _CRSTE_EMPTY(old.h.tt), gfn),
+		   priv->gmap->kvm);
+	if (folio)
+		uv_convert_from_secure_folio(folio);
 
 	return 0;
 }
···
 
 	if (fatal_signal_pending(current))
 		return 1;
-	crste = READ_ONCE(*table);
-	if (!crste.h.fc)
-		return 0;
-	if (crste.h.p && !crste.s.fc1.sd)
-		return 0;
+	do {
+		crste = READ_ONCE(*table);
+		if (!crste.h.fc)
+			return 0;
+		if (crste.h.p && !crste.s.fc1.sd)
+			return 0;
 
-	/*
-	 * If this large page contains one or more prefixes of vCPUs that are
-	 * currently running, do not reset the protection, leave it marked as
-	 * dirty.
-	 */
-	if (!crste.s.fc1.prefix_notif || gmap_mkold_prefix(gmap, gfn, end)) {
+		/*
+		 * If this large page contains one or more prefixes of vCPUs that are
+		 * currently running, do not reset the protection, leave it marked as
+		 * dirty.
+		 */
+		if (crste.s.fc1.prefix_notif && !gmap_mkold_prefix(gmap, gfn, end))
+			break;
 		new = crste;
 		new.h.p = 1;
 		new.s.fc1.sd = 0;
-		gmap_crstep_xchg(gmap, table, new, gfn);
-	}
+	} while (!gmap_crstep_xchg_atomic(gmap, table, crste, new, gfn));
 
 	for ( ; gfn < end; gfn++)
 		mark_page_dirty(gmap->kvm, gfn);
···
 	_dat_walk_gfn_range(start, end, gmap->asce, &walk_ops, 0, gmap);
 }
 
-static int gmap_handle_minor_crste_fault(union asce asce, struct guest_fault *f)
+static int gmap_handle_minor_crste_fault(struct gmap *gmap, struct guest_fault *f)
 {
 	union crste newcrste, oldcrste = READ_ONCE(*f->crstep);
 
···
 			newcrste.s.fc1.d = 1;
 			newcrste.s.fc1.sd = 1;
 		}
-		if (!oldcrste.s.fc1.d && newcrste.s.fc1.d)
-			SetPageDirty(phys_to_page(crste_origin_large(newcrste)));
 		/* In case of races, let the slow path deal with it. */
-		return !dat_crstep_xchg_atomic(f->crstep, oldcrste, newcrste, f->gfn, asce);
+		return !gmap_crstep_xchg_atomic(gmap, f->crstep, oldcrste, newcrste, f->gfn);
 	}
 	/* Trying to write on a read-only page, let the slow path deal with it. */
 	return 1;
···
 		newpte.s.d = 1;
 		newpte.s.sd = 1;
 	}
-	if (!oldpte.s.d && newpte.s.d)
-		SetPageDirty(pfn_to_page(newpte.h.pfra));
 	*pgste = gmap_ptep_xchg(gmap, f->ptep, newpte, *pgste, f->gfn);
 
 	return 0;
···
 			fault->callback(fault);
 		pgste_set_unlock(fault->ptep, pgste);
 	} else {
-		rc = gmap_handle_minor_crste_fault(gmap->asce, fault);
+		rc = gmap_handle_minor_crste_fault(gmap, fault);
 		if (!rc && fault->callback)
 			fault->callback(fault);
 	}
···
 	return test_bit(GMAP_FLAG_ALLOW_HPAGE_1M, &gmap->flags);
 }
 
+static int _gmap_link(struct kvm_s390_mmu_cache *mc, struct gmap *gmap, int level,
+		      struct guest_fault *f)
+{
+	union crste oldval, newval;
+	union pte newpte, oldpte;
+	union pgste pgste;
+	int rc = 0;
+
+	rc = dat_entry_walk(mc, f->gfn, gmap->asce, DAT_WALK_ALLOC_CONTINUE, level,
+			    &f->crstep, &f->ptep);
+	if (rc == -ENOMEM)
+		return rc;
+	if (KVM_BUG_ON(rc == -EINVAL, gmap->kvm))
+		return rc;
+	if (rc)
+		return -EAGAIN;
+	if (KVM_BUG_ON(get_level(f->crstep, f->ptep) > level, gmap->kvm))
+		return -EINVAL;
+
+	if (f->ptep) {
+		pgste = pgste_get_lock(f->ptep);
+		oldpte = *f->ptep;
+		newpte = _pte(f->pfn, f->writable, f->write_attempt | oldpte.s.d, !f->page);
+		newpte.s.sd = oldpte.s.sd;
+		oldpte.s.sd = 0;
+		if (oldpte.val == _PTE_EMPTY.val || oldpte.h.pfra == f->pfn) {
+			pgste = gmap_ptep_xchg(gmap, f->ptep, newpte, pgste, f->gfn);
+			if (f->callback)
+				f->callback(f);
+		} else {
+			rc = -EAGAIN;
+		}
+		pgste_set_unlock(f->ptep, pgste);
+	} else {
+		do {
+			oldval = READ_ONCE(*f->crstep);
+			newval = _crste_fc1(f->pfn, oldval.h.tt, f->writable,
+					    f->write_attempt | oldval.s.fc1.d);
+			newval.s.fc1.s = !f->page;
+			newval.s.fc1.sd = oldval.s.fc1.sd;
+			if (oldval.val != _CRSTE_EMPTY(oldval.h.tt).val &&
+			    crste_origin_large(oldval) != crste_origin_large(newval))
+				return -EAGAIN;
+		} while (!gmap_crstep_xchg_atomic(gmap, f->crstep, oldval, newval, f->gfn));
+		if (f->callback)
+			f->callback(f);
+	}
+
+	return rc;
+}
+
 int gmap_link(struct kvm_s390_mmu_cache *mc, struct gmap *gmap, struct guest_fault *f)
 {
 	unsigned int order;
-	int rc, level;
+	int level;
 
 	lockdep_assert_held(&gmap->kvm->mmu_lock);
 
···
 		else if (order >= get_order(_SEGMENT_SIZE) && gmap_1m_allowed(gmap, f->gfn))
 			level = TABLE_TYPE_SEGMENT;
 	}
-	rc = dat_link(mc, gmap->asce, level, uses_skeys(gmap), f);
-	KVM_BUG_ON(rc == -EINVAL, gmap->kvm);
-	return rc;
+	return _gmap_link(mc, gmap, level, f);
 }
 
 static int gmap_ucas_map_one(struct kvm_s390_mmu_cache *mc, struct gmap *gmap,
 			     gfn_t p_gfn, gfn_t c_gfn, bool force_alloc)
 {
+	union crste newcrste, oldcrste;
 	struct page_table *pt;
-	union crste newcrste;
 	union crste *crstep;
 	union pte *ptep;
 	int rc;
···
 			    &crstep, &ptep);
 	if (rc)
 		return rc;
-	dat_crstep_xchg(crstep, newcrste, c_gfn, gmap->asce);
+	do {
+		oldcrste = READ_ONCE(*crstep);
+		if (oldcrste.val == newcrste.val)
+			break;
+	} while (!dat_crstep_xchg_atomic(crstep, oldcrste, newcrste, c_gfn, gmap->asce));
 	return 0;
 }
 
···
 	int rc;
 
 	rc = dat_entry_walk(NULL, c_gfn, gmap->asce, 0, TABLE_TYPE_SEGMENT, &crstep, &ptep);
-	if (!rc)
-		dat_crstep_xchg(crstep, _PMD_EMPTY, c_gfn, gmap->asce);
+	if (rc)
+		return;
+	while (!dat_crstep_xchg_atomic(crstep, READ_ONCE(*crstep), _PMD_EMPTY, c_gfn, gmap->asce))
+		;
 }
 
 void gmap_ucas_unmap(struct gmap *gmap, gfn_t c_gfn, unsigned long count)
···
 			dat_ptep_xchg(ptep, _PTE_EMPTY, r_gfn, sg->asce, uses_skeys(sg));
 		return;
 	}
-	crste = READ_ONCE(*crstep);
-	dat_crstep_clear(crstep, r_gfn, sg->asce);
+
+	crste = dat_crstep_clear_atomic(crstep, r_gfn, sg->asce);
 	if (crste_leaf(crste) || crste.h.i)
 		return;
 	if (is_pmd(crste))
···
 static inline int __gmap_protect_asce_top_level(struct kvm_s390_mmu_cache *mc, struct gmap *sg,
 						struct gmap_protect_asce_top_level *context)
 {
+	struct gmap *parent;
 	int rc, i;
 
 	guard(write_lock)(&sg->kvm->mmu_lock);
···
 	if (kvm_s390_array_needs_retry_safe(sg->kvm, context->seq, context->f))
 		return -EAGAIN;
 
-	scoped_guard(spinlock, &sg->parent->children_lock) {
+	parent = READ_ONCE(sg->parent);
+	if (!parent)
+		return -EAGAIN;
+	scoped_guard(spinlock, &parent->children_lock) {
+		if (READ_ONCE(sg->parent) != parent)
+			return -EAGAIN;
 		for (i = 0; i < CRST_TABLE_PAGES; i++) {
 			if (!context->f[i].valid)
 				continue;
···
 {
 	struct gmap *sg, *new;
 	int rc;
+
+	if (WARN_ON(!parent))
+		return ERR_PTR(-EINVAL);
 
 	scoped_guard(spinlock, &parent->children_lock) {
 		sg = gmap_find_shadow(parent, asce, edat_level);

arch/s390/kvm/gmap.h

···
 		else
 			_gmap_handle_vsie_unshadow_event(gmap, gfn);
 	}
+	if (!ptep->s.d && newpte.s.d && !newpte.s.s)
+		SetPageDirty(pfn_to_page(newpte.h.pfra));
 	return __dat_ptep_xchg(ptep, pgste, newpte, gfn, gmap->asce, uses_skeys(gmap));
 }
 
···
 	return _gmap_ptep_xchg(gmap, ptep, newpte, pgste, gfn, true);
 }
 
-static inline void _gmap_crstep_xchg(struct gmap *gmap, union crste *crstep, union crste ne,
-				     gfn_t gfn, bool needs_lock)
+static inline bool __must_check _gmap_crstep_xchg_atomic(struct gmap *gmap, union crste *crstep,
+							 union crste oldcrste, union crste newcrste,
+							 gfn_t gfn, bool needs_lock)
 {
-	unsigned long align = 8 + (is_pmd(*crstep) ? 0 : 11);
+	unsigned long align = is_pmd(newcrste) ? _PAGE_ENTRIES : _PAGE_ENTRIES * _CRST_ENTRIES;
+
+	if (KVM_BUG_ON(crstep->h.tt != oldcrste.h.tt || newcrste.h.tt != oldcrste.h.tt, gmap->kvm))
+		return true;
 
 	lockdep_assert_held(&gmap->kvm->mmu_lock);
 	if (!needs_lock)
 		lockdep_assert_held(&gmap->children_lock);
 
 	gfn = ALIGN_DOWN(gfn, align);
-	if (crste_prefix(*crstep) && (ne.h.p || ne.h.i || !crste_prefix(ne))) {
-		ne.s.fc1.prefix_notif = 0;
+	if (crste_prefix(oldcrste) && (newcrste.h.p || newcrste.h.i || !crste_prefix(newcrste))) {
+		newcrste.s.fc1.prefix_notif = 0;
 		gmap_unmap_prefix(gmap, gfn, gfn + align);
 	}
-	if (crste_leaf(*crstep) && crstep->s.fc1.vsie_notif &&
-	    (ne.h.p || ne.h.i || !ne.s.fc1.vsie_notif)) {
-		ne.s.fc1.vsie_notif = 0;
+	if (crste_leaf(oldcrste) && oldcrste.s.fc1.vsie_notif &&
+	    (newcrste.h.p || newcrste.h.i || !newcrste.s.fc1.vsie_notif)) {
+		newcrste.s.fc1.vsie_notif = 0;
 		if (needs_lock)
 			gmap_handle_vsie_unshadow_event(gmap, gfn);
 		else
 			_gmap_handle_vsie_unshadow_event(gmap, gfn);
 	}
-	dat_crstep_xchg(crstep, ne, gfn, gmap->asce);
+	if (!oldcrste.s.fc1.d && newcrste.s.fc1.d && !newcrste.s.fc1.s)
+		SetPageDirty(phys_to_page(crste_origin_large(newcrste)));
+	return dat_crstep_xchg_atomic(crstep, oldcrste, newcrste, gfn, gmap->asce);
 }
 
-static inline void gmap_crstep_xchg(struct gmap *gmap, union crste *crstep, union crste ne,
-				    gfn_t gfn)
+static inline bool __must_check gmap_crstep_xchg_atomic(struct gmap *gmap, union crste *crstep,
+							union crste oldcrste, union crste newcrste,
+							gfn_t gfn)
 {
-	return _gmap_crstep_xchg(gmap, crstep, ne, gfn, true);
+	return _gmap_crstep_xchg_atomic(gmap, crstep, oldcrste, newcrste, gfn, true);
 }
 
 /**

arch/s390/kvm/kvm-s390.c

···
 	}
 #endif
 	case KVM_S390_VCPU_FAULT: {
-		idx = srcu_read_lock(&vcpu->kvm->srcu);
-		r = vcpu_dat_fault_handler(vcpu, arg, 0);
-		srcu_read_unlock(&vcpu->kvm->srcu, idx);
+		gpa_t gaddr = arg;
+
+		scoped_guard(srcu, &vcpu->kvm->srcu) {
+			r = vcpu_ucontrol_translate(vcpu, &gaddr);
+			if (r)
+				break;
+
+			r = kvm_s390_faultin_gfn_simple(vcpu, NULL, gpa_to_gfn(gaddr), false);
+			if (r == PGM_ADDRESSING)
+				r = -EFAULT;
+			if (r <= 0)
+				break;
+			r = -EIO;
+			KVM_BUG_ON(r, vcpu->kvm);
+		}
 		break;
 	}
 	case KVM_ENABLE_CAP:

arch/s390/kvm/vsie.c

···
 static int vsie_run(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
 {
 	struct kvm_s390_sie_block *scb_s = &vsie_page->scb_s;
-	struct gmap *sg;
+	struct gmap *sg = NULL;
 	int rc = 0;
 
 	while (1) {
···
 			sg = gmap_put(sg);
 		cond_resched();
 	}
+	if (sg)
+		sg = gmap_put(sg);
 
 	if (rc == -EFAULT) {
 		/*

arch/x86/coco/sev/noinstr.c

···
 
 	WARN_ON(!irqs_disabled());
 
+	if (!sev_cfg.ghcbs_initialized)
+		return boot_ghcb;
+
 	data = this_cpu_read(runtime_data);
 	ghcb = &data->ghcb_page;
 
···
 	struct ghcb *ghcb;
 
 	WARN_ON(!irqs_disabled());
+
+	if (!sev_cfg.ghcbs_initialized)
+		return;
 
 	data = this_cpu_read(runtime_data);
 	ghcb = &data->ghcb_page;

arch/x86/entry/entry_fred.c

···
 	}
 }
 
+#ifdef CONFIG_AMD_MEM_ENCRYPT
+noinstr void exc_vmm_communication(struct pt_regs *regs, unsigned long error_code)
+{
+	if (user_mode(regs))
+		return user_exc_vmm_communication(regs, error_code);
+	else
+		return kernel_exc_vmm_communication(regs, error_code);
+}
+#endif
+
 static noinstr void fred_hwexc(struct pt_regs *regs, unsigned long error_code)
 {
 	/* Optimize for #PF. That's the only exception which matters performance wise */
···
 #ifdef CONFIG_X86_CET
 	case X86_TRAP_CP: return exc_control_protection(regs, error_code);
 #endif
+#ifdef CONFIG_AMD_MEM_ENCRYPT
+	case X86_TRAP_VC: return exc_vmm_communication(regs, error_code);
+#endif
+
 	default: return fred_bad_type(regs, error_code);
 	}
 

arch/x86/kernel/cpu/common.c

···
 
 /* These bits should not change their value after CPU init is finished. */
 static const unsigned long cr4_pinned_mask = X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_UMIP |
-					     X86_CR4_FSGSBASE | X86_CR4_CET | X86_CR4_FRED;
+					     X86_CR4_FSGSBASE | X86_CR4_CET;
+
+/*
+ * The CR pinning protects against ROP on the 'mov %reg, %CRn' instruction(s).
+ * Since you can ROP directly to these instructions (barring shadow stack),
+ * any protection must follow immediately and unconditionally after that.
+ *
+ * Specifically, the CR[04] write functions below will have the value
+ * validation controlled by the @cr_pinning static_branch which is
+ * __ro_after_init, just like the cr4_pinned_bits value.
+ *
+ * Once set, an attacker will have to defeat page-tables to get around these
+ * restrictions. Which is a much bigger ask than 'simple' ROP.
+ */
 static DEFINE_STATIC_KEY_FALSE_RO(cr_pinning);
 static unsigned long cr4_pinned_bits __ro_after_init;
 
···
 	setup_umip(c);
 	setup_lass(c);
 
-	/* Enable FSGSBASE instructions if available. */
-	if (cpu_has(c, X86_FEATURE_FSGSBASE)) {
-		cr4_set_bits(X86_CR4_FSGSBASE);
-		elf_hwcap2 |= HWCAP2_FSGSBASE;
-	}
-
 	/*
 	 * The vendor-specific functions might have changed features.
 	 * Now we do "generic changes."
···
 
 	/* GHCB needs to be setup to handle #VC. */
 	setup_ghcb();
+
+	/*
+	 * On CPUs with FSGSBASE support, paranoid_entry() uses
+	 * ALTERNATIVE-patched RDGSBASE/WRGSBASE instructions. Secondary CPUs
+	 * boot after alternatives are patched globally, so early exceptions
+	 * execute patched code that depends on FSGSBASE. Enable the feature
+	 * before any exceptions occur.
+	 */
+	if (cpu_feature_enabled(X86_FEATURE_FSGSBASE)) {
+		cr4_set_bits(X86_CR4_FSGSBASE);
+		elf_hwcap2 |= HWCAP2_FSGSBASE;
+	}
 
 	if (cpu_feature_enabled(X86_FEATURE_FRED)) {
 		/* The boot CPU has enabled FRED during early boot */

arch/x86/kvm/mmu/mmu.c

···
 	bool prefetch = !fault || fault->prefetch;
 	bool write_fault = fault && fault->write;
 
-	if (unlikely(is_noslot_pfn(pfn))) {
-		vcpu->stat.pf_mmio_spte_created++;
-		mark_mmio_spte(vcpu, sptep, gfn, pte_access);
-		return RET_PF_EMULATE;
-	}
-
 	if (is_shadow_present_pte(*sptep)) {
 		if (prefetch && is_last_spte(*sptep, level) &&
 		    pfn == spte_to_pfn(*sptep))
···
 			child = spte_to_child_sp(pte);
 			drop_parent_pte(vcpu->kvm, child, sptep);
 			flush = true;
-		} else if (WARN_ON_ONCE(pfn != spte_to_pfn(*sptep))) {
+		} else if (pfn != spte_to_pfn(*sptep)) {
+			WARN_ON_ONCE(vcpu->arch.mmu->root_role.direct);
 			drop_spte(vcpu->kvm, sptep);
 			flush = true;
 		} else
 			was_rmapped = 1;
+	}
+
+	if (unlikely(is_noslot_pfn(pfn))) {
+		vcpu->stat.pf_mmio_spte_created++;
+		mark_mmio_spte(vcpu, sptep, gfn, pte_access);
+		if (flush)
+			kvm_flush_remote_tlbs_gfn(vcpu->kvm, gfn, level);
+		return RET_PF_EMULATE;
 	}
 
 	wrprot = make_spte(vcpu, sp, slot, pte_access, gfn, pfn, *sptep, prefetch,

arch/x86/platform/efi/quirks.c

···
 	if (efi_enabled(EFI_DBG))
 		return;
 
-	sz = sizeof(*ranges_to_free) * efi.memmap.nr_map + 1;
+	sz = sizeof(*ranges_to_free) * (efi.memmap.nr_map + 1);
 	ranges_to_free = kzalloc(sz, GFP_KERNEL);
 	if (!ranges_to_free) {
 		pr_err("Failed to allocate storage for freeable EFI regions\n");

drivers/accel/ivpu/ivpu_drv.h

···
 #define IVPU_HW_IP_60XX 60
 
 #define IVPU_HW_IP_REV_LNL_B0 4
+#define IVPU_HW_IP_REV_NVL_A0 0
 
 #define IVPU_HW_BTRS_MTL 1
 #define IVPU_HW_BTRS_LNL 2

drivers/accel/ivpu/ivpu_hw.c

···
 	if (ivpu_hw_btrs_gen(vdev) == IVPU_HW_BTRS_MTL)
 		vdev->wa.interrupt_clear_with_0 = ivpu_hw_btrs_irqs_clear_with_0_mtl(vdev);
 
-	if (ivpu_device_id(vdev) == PCI_DEVICE_ID_LNL &&
-	    ivpu_revision(vdev) < IVPU_HW_IP_REV_LNL_B0)
+	if ((ivpu_device_id(vdev) == PCI_DEVICE_ID_LNL &&
+	     ivpu_revision(vdev) < IVPU_HW_IP_REV_LNL_B0) ||
+	    (ivpu_device_id(vdev) == PCI_DEVICE_ID_NVL &&
+	     ivpu_revision(vdev) == IVPU_HW_IP_REV_NVL_A0))
 		vdev->wa.disable_clock_relinquish = true;
 
 	if (ivpu_test_mode & IVPU_TEST_MODE_CLK_RELINQ_ENABLE)

drivers/acpi/ec.c

···
 
 	ret = ec_install_handlers(ec, device, call_reg);
 	if (ret) {
+		ec_remove_handlers(ec);
+
 		if (ec == first_ec)
 			first_ec = NULL;
 

drivers/auxdisplay/lcd2s.c

···
 {
 	struct lcd2s_data *lcd2s = lcd->drvdata;
 	u8 buf[2] = { LCD2S_CMD_WRITE, c };
+	int ret;
 
-	lcd2s_i2c_master_send(lcd2s->i2c, buf, sizeof(buf));
+	ret = lcd2s_i2c_master_send(lcd2s->i2c, buf, sizeof(buf));
+	if (ret < 0)
+		return ret;
+	if (ret != sizeof(buf))
+		return -EIO;
 	return 0;
 }
 
···
 {
 	struct lcd2s_data *lcd2s = lcd->drvdata;
 	u8 buf[3] = { LCD2S_CMD_CUR_POS, y + 1, x + 1 };
+	int ret;
 
-	lcd2s_i2c_master_send(lcd2s->i2c, buf, sizeof(buf));
-
+	ret = lcd2s_i2c_master_send(lcd2s->i2c, buf, sizeof(buf));
+	if (ret < 0)
+		return ret;
+	if (ret != sizeof(buf))
+		return -EIO;
 	return 0;
 }
 

drivers/auxdisplay/line-display.c

···
 
 static void linedisp_release(struct device *dev)
 {
-	struct linedisp *linedisp = to_linedisp(dev);
+	struct linedisp *linedisp = container_of(dev, struct linedisp, dev);
 
 	kfree(linedisp->map);
 	kfree(linedisp->message);

drivers/base/regmap/regmap.c

···
 			       unsigned int val_num)
 {
 	void *orig_work_buf;
+	unsigned int selector_reg;
 	unsigned int win_offset;
 	unsigned int win_page;
 	bool page_chg;
···
 			return -EINVAL;
 	}
 
-	/* It is possible to have selector register inside data window.
-	   In that case, selector register is located on every page and
-	   it needs no page switching, when accessed alone. */
+	/*
+	 * Calculate the address of the selector register in the corresponding
+	 * data window if it is located on every page.
+	 */
+	page_chg = in_range(range->selector_reg, range->window_start, range->window_len);
+	if (page_chg)
+		selector_reg = range->range_min + win_page * range->window_len +
+			       range->selector_reg - range->window_start;
+
+	/*
+	 * It is possible to have selector register inside data window.
+	 * In that case, selector register is located on every page and it
+	 * needs no page switching, when accessed alone.
+	 *
+	 * Nevertheless we should synchronize the cache values for it.
+	 * This can't be properly achieved if the selector register is
+	 * the first and the only one to be read inside the data window.
+	 * That's why we update it in that case as well.
+	 *
+	 * However, we specifically avoid updating it for the default page,
+	 * when it's overlapped with the real data window, to prevent from
+	 * infinite looping.
+	 */
 	if (val_num > 1 ||
+	    (page_chg && selector_reg != range->selector_reg) ||
 	    range->window_start + win_offset != range->selector_reg) {
 		/* Use separate work_buf during page switching */
 		orig_work_buf = map->work_buf;
···
 		ret = _regmap_update_bits(map, range->selector_reg,
 					  range->selector_mask,
 					  win_page << range->selector_shift,
-					  &page_chg, false);
+					  NULL, false);
 
 		map->work_buf = orig_work_buf;
 

drivers/bluetooth/hci_h4.c

···
 {
 	struct h4_struct *h4 = hu->priv;
 
-	if (!test_bit(HCI_UART_REGISTERED, &hu->flags))
-		return -EUNATCH;
-
 	h4->rx_skb = h4_recv_buf(hu, h4->rx_skb, data, count,
 				 h4_recv_pkts, ARRAY_SIZE(h4_recv_pkts));
 	if (IS_ERR(h4->rx_skb)) {

drivers/cpufreq/cpufreq.c

···
 		 * If there is a problem with its frequency table, take it
 		 * offline and drop it.
 		 */
-		if (policy->freq_table_sorted != CPUFREQ_TABLE_SORTED_ASCENDING &&
-		    policy->freq_table_sorted != CPUFREQ_TABLE_SORTED_DESCENDING) {
-			ret = cpufreq_table_validate_and_sort(policy);
-			if (ret)
-				goto out_offline_policy;
-		}
+		ret = cpufreq_table_validate_and_sort(policy);
+		if (ret)
+			goto out_offline_policy;
 
 		/* related_cpus should at least include policy->cpus. */
 		cpumask_copy(policy->related_cpus, policy->cpus);

drivers/cpufreq/cpufreq_conservative.c

···
 	dbs_info->requested_freq = policy->cur;
 }
 
+static void cs_limits(struct cpufreq_policy *policy)
+{
+	struct cs_policy_dbs_info *dbs_info = to_dbs_info(policy->governor_data);
+
+	/*
+	 * The limits have changed, so may have the current frequency. Reset
+	 * requested_freq to avoid any unintended outcomes due to the mismatch.
+	 */
+	dbs_info->requested_freq = policy->cur;
+}
+
 static struct dbs_governor cs_governor = {
 	.gov = CPUFREQ_DBS_GOVERNOR_INITIALIZER("conservative"),
 	.kobj_type = { .default_groups = cs_groups },
···
 	.init = cs_init,
 	.exit = cs_exit,
 	.start = cs_start,
+	.limits = cs_limits,
 };
 
 #define CPU_FREQ_GOV_CONSERVATIVE	(cs_governor.gov)

drivers/cpufreq/cpufreq_governor.c

···
 
 void cpufreq_dbs_governor_limits(struct cpufreq_policy *policy)
 {
+	struct dbs_governor *gov = dbs_governor_of(policy);
 	struct policy_dbs_info *policy_dbs;
 
 	/* Protect gov->gdbs_data against cpufreq_dbs_governor_exit() */
···
 	mutex_lock(&policy_dbs->update_mutex);
 	cpufreq_policy_apply_limits(policy);
 	gov_update_sample_delay(policy_dbs, 0);
+	if (gov->limits)
+		gov->limits(policy);
 	mutex_unlock(&policy_dbs->update_mutex);
 
 out:

drivers/cpufreq/cpufreq_governor.h

···
 	int (*init)(struct dbs_data *dbs_data);
 	void (*exit)(struct dbs_data *dbs_data);
 	void (*start)(struct cpufreq_policy *policy);
+	void (*limits)(struct cpufreq_policy *policy);
 };
 
 static inline struct dbs_governor *dbs_governor_of(struct cpufreq_policy *policy)

drivers/cpufreq/freq_table.c

···
 	if (policy_has_boost_freq(policy))
 		policy->boost_supported = true;
 
+	if (policy->freq_table_sorted == CPUFREQ_TABLE_SORTED_ASCENDING ||
+	    policy->freq_table_sorted == CPUFREQ_TABLE_SORTED_DESCENDING)
+		return 0;
+
 	return set_freq_table_sorted(policy);
 }
 

drivers/dma/dw-edma/dw-edma-core.c

···
 {
 	struct dw_edma_chip *chip = dw->chip;
 	struct device *dev = dw->chip->dev;
+	struct msi_desc *msi_desc;
 	u32 wr_mask = 1;
 	u32 rd_mask = 1;
 	int i, err = 0;
···
 					  &dw->irq[i]);
 			if (err)
 				goto err_irq_free;
-
-			if (irq_get_msi_desc(irq))
+			msi_desc = irq_get_msi_desc(irq);
+			if (msi_desc) {
 				get_cached_msi_msg(irq, &dw->irq[i].msi);
+				if (!msi_desc->pci.msi_attrib.is_msix)
+					dw->irq[i].msi.data = dw->irq[0].msi.data + i;
+			}
 		}
 
 		dw->nr_irqs = i;

drivers/dma/dw-edma/dw-hdma-v0-core.c

···
 			  lower_32_bits(chunk->ll_region.paddr));
 		SET_CH_32(dw, chan->dir, chan->id, llp.msb,
 			  upper_32_bits(chunk->ll_region.paddr));
+		/* Set consumer cycle */
+		SET_CH_32(dw, chan->dir, chan->id, cycle_sync,
+			HDMA_V0_CONSUMER_CYCLE_STAT | HDMA_V0_CONSUMER_CYCLE_BIT);
 	}
-	/* Set consumer cycle */
-	SET_CH_32(dw, chan->dir, chan->id, cycle_sync,
-		  HDMA_V0_CONSUMER_CYCLE_STAT | HDMA_V0_CONSUMER_CYCLE_BIT);
 
 	dw_hdma_v0_sync_ll_data(chunk);
 

drivers/dma/fsl-edma-main.c

···
 			return NULL;
 		i = fsl_chan - fsl_edma->chans;
 
-		fsl_chan->priority = dma_spec->args[1];
-		fsl_chan->is_rxchan = dma_spec->args[2] & FSL_EDMA_RX;
-		fsl_chan->is_remote = dma_spec->args[2] & FSL_EDMA_REMOTE;
-		fsl_chan->is_multi_fifo = dma_spec->args[2] & FSL_EDMA_MULTI_FIFO;
+		if (!b_chmux && i != dma_spec->args[0])
+			continue;
 
 		if ((dma_spec->args[2] & FSL_EDMA_EVEN_CH) && (i & 0x1))
 			continue;
···
 		if ((dma_spec->args[2] & FSL_EDMA_ODD_CH) && !(i & 0x1))
 			continue;
 
-		if (!b_chmux && i == dma_spec->args[0]) {
-			chan = dma_get_slave_channel(chan);
-			chan->device->privatecnt++;
-			return chan;
-		} else if (b_chmux && !fsl_chan->srcid) {
-			/* if controller support channel mux, choose a free channel */
-			chan = dma_get_slave_channel(chan);
-			chan->device->privatecnt++;
-			fsl_chan->srcid = dma_spec->args[0];
-			return chan;
-		}
+		fsl_chan->srcid = dma_spec->args[0];
+		fsl_chan->priority = dma_spec->args[1];
+		fsl_chan->is_rxchan = dma_spec->args[2] & FSL_EDMA_RX;
+		fsl_chan->is_remote = dma_spec->args[2] & FSL_EDMA_REMOTE;
+		fsl_chan->is_multi_fifo = dma_spec->args[2] & FSL_EDMA_MULTI_FIFO;
+
+		chan = dma_get_slave_channel(chan);
+		chan->device->privatecnt++;
+		return chan;
 	}
 	return NULL;
 }

drivers/dma/idxd/cdev.c

···
 static void idxd_cdev_dev_release(struct device *dev)
 {
 	struct idxd_cdev *idxd_cdev = dev_to_cdev(dev);
-	struct idxd_cdev_context *cdev_ctx;
-	struct idxd_wq *wq = idxd_cdev->wq;
 
-	cdev_ctx = &ictx[wq->idxd->data->type];
-	ida_free(&cdev_ctx->minor_ida, idxd_cdev->minor);
 	kfree(idxd_cdev);
 }
 
···
 
 void idxd_wq_del_cdev(struct idxd_wq *wq)
 {
+	struct idxd_cdev_context *cdev_ctx;
 	struct idxd_cdev *idxd_cdev;
 
 	idxd_cdev = wq->idxd_cdev;
 	wq->idxd_cdev = NULL;
 	cdev_device_del(&idxd_cdev->cdev, cdev_dev(idxd_cdev));
+
+	cdev_ctx = &ictx[wq->idxd->data->type];
+	ida_free(&cdev_ctx->minor_ida, idxd_cdev->minor);
 	put_device(cdev_dev(idxd_cdev));
 }
 

drivers/dma/idxd/device.c

···
 	free_descs(wq);
 	dma_free_coherent(dev, wq->compls_size, wq->compls, wq->compls_addr);
 	sbitmap_queue_free(&wq->sbq);
+	wq->type = IDXD_WQT_NONE;
 }
 EXPORT_SYMBOL_NS_GPL(idxd_wq_free_resources, "IDXD");
 
···
 	lockdep_assert_held(&wq->wq_lock);
 	wq->state = IDXD_WQ_DISABLED;
 	memset(wq->wqcfg, 0, idxd->wqcfg_size);
-	wq->type = IDXD_WQT_NONE;
 	wq->threshold = 0;
 	wq->priority = 0;
 	wq->enqcmds_retries = IDXD_ENQCMDS_RETRIES;
···
 	struct device *dev = &idxd->pdev->dev;
 	struct idxd_evl *evl = idxd->evl;
 
-	gencfg.bits = ioread32(idxd->reg_base + IDXD_GENCFG_OFFSET);
-	if (!gencfg.evl_en)
+	if (!evl)
 		return;
 
 	mutex_lock(&evl->lock);
···
 {
 	int rc;
 
-	lockdep_assert_held(&idxd->dev_lock);
+	guard(spinlock)(&idxd->dev_lock);
+
+	if (!test_bit(IDXD_FLAG_CONFIGURABLE, &idxd->flags))
+		return 0;
+
 	rc = idxd_wqs_setup(idxd);
 	if (rc < 0)
 		return rc;
···
 
 	free_irq(ie->vector, ie);
 	idxd_flush_pending_descs(ie);
+
+	/* The interrupt might have been already released by FLR */
+	if (ie->int_handle == INVALID_INT_HANDLE)
+		return;
+
 	if (idxd->request_int_handles)
 		idxd_device_release_int_handle(idxd, ie->int_handle, IDXD_IRQ_MSIX);
 	idxd_device_clear_perm_entry(idxd, ie);
 	ie->vector = -1;
 	ie->int_handle = INVALID_INT_HANDLE;
 	ie->pasid = IOMMU_PASID_INVALID;
+}
+
+void idxd_wq_flush_descs(struct idxd_wq *wq)
+{
+	struct idxd_irq_entry *ie = &wq->ie;
+	struct idxd_device *idxd = wq->idxd;
+
+	guard(mutex)(&wq->wq_lock);
+
+	if (wq->state != IDXD_WQ_ENABLED || wq->type != IDXD_WQT_KERNEL)
+		return;
+
+	idxd_flush_pending_descs(ie);
+	if (idxd->request_int_handles)
+		idxd_device_release_int_handle(idxd, ie->int_handle, IDXD_IRQ_MSIX);
+	idxd_device_clear_perm_entry(idxd, ie);
+	ie->int_handle = INVALID_INT_HANDLE;
 }
 
 int idxd_wq_request_irq(struct idxd_wq *wq)
···
 		}
 	}
 
-	rc = 0;
-	spin_lock(&idxd->dev_lock);
-	if (test_bit(IDXD_FLAG_CONFIGURABLE, &idxd->flags))
-		rc = idxd_device_config(idxd);
-	spin_unlock(&idxd->dev_lock);
+	rc = idxd_device_config(idxd);
 	if (rc < 0) {
 		dev_dbg(dev, "Writing wq %d config failed: %d\n", wq->id, rc);
 		goto err;
···
 	idxd_wq_reset(wq);
 	idxd_wq_free_resources(wq);
 	percpu_ref_exit(&wq->wq_active);
-	wq->type = IDXD_WQT_NONE;
 	wq->client_count = 0;
 }
 EXPORT_SYMBOL_NS_GPL(idxd_drv_disable_wq, "IDXD");
···
 	}
 
 	/* Device configuration */
-	spin_lock(&idxd->dev_lock);
-	if (test_bit(IDXD_FLAG_CONFIGURABLE, &idxd->flags))
-		rc = idxd_device_config(idxd);
-	spin_unlock(&idxd->dev_lock);
+	rc = idxd_device_config(idxd);
 	if (rc < 0)
 		return -ENXIO;
 

drivers/dma/idxd/dma.c

···
 	kfree(idxd_dma);
 }
 
+static int idxd_dma_terminate_all(struct dma_chan *c)
+{
+	struct idxd_wq *wq = to_idxd_wq(c);
+
+	idxd_wq_flush_descs(wq);
+
+	return 0;
+}
+
+static void idxd_dma_synchronize(struct dma_chan *c)
+{
+	struct idxd_wq *wq = to_idxd_wq(c);
+
+	idxd_wq_drain(wq);
+}
+
 int idxd_register_dma_device(struct idxd_device *idxd)
 {
 	struct idxd_dma_dev *idxd_dma;
···
 	dma->device_issue_pending = idxd_dma_issue_pending;
 	dma->device_alloc_chan_resources = idxd_dma_alloc_chan_resources;
 	dma->device_free_chan_resources = idxd_dma_free_chan_resources;
+	dma->device_terminate_all = idxd_dma_terminate_all;
+	dma->device_synchronize = idxd_dma_synchronize;
 
 	rc = dma_async_device_register(dma);
 	if (rc < 0) {

drivers/dma/idxd/idxd.h

···
 int idxd_wq_init_percpu_ref(struct idxd_wq *wq);
 void idxd_wq_free_irq(struct idxd_wq *wq);
 int idxd_wq_request_irq(struct idxd_wq *wq);
+void idxd_wq_flush_descs(struct idxd_wq *wq);
 
 /* submission */
 int idxd_submit_desc(struct idxd_wq *wq, struct idxd_desc *desc);

drivers/dma/idxd/init.c

···
 
 	idxd->rdbuf_limit = idxd_saved->saved_idxd.rdbuf_limit;
 
-	idxd->evl->size = saved_evl->size;
+	if (idxd->evl)
+		idxd->evl->size = saved_evl->size;
 
 	for (i = 0; i < idxd->max_groups; i++) {
 		struct idxd_group *saved_group, *group;
···
 	idxd_device_config_restore(idxd, idxd->idxd_saved);
 
 	/* Re-configure IDXD device if allowed. */
-	if (test_bit(IDXD_FLAG_CONFIGURABLE, &idxd->flags)) {
-		rc = idxd_device_config(idxd);
-		if (rc < 0) {
-			dev_err(dev, "HALT: %s config fails\n", idxd_name);
-			goto out;
-		}
+	rc = idxd_device_config(idxd);
+	if (rc < 0) {
+		dev_err(dev, "HALT: %s config fails\n", idxd_name);
+		goto out;
 	}
 
 	/* Bind IDXD device to driver. */
···
 	}
 out:
 	kfree(idxd->idxd_saved);
+	idxd->idxd_saved = NULL;
 }
 
 static const struct pci_error_handlers idxd_error_handler = {

drivers/dma/idxd/irq.c

···
 		dev_err(&idxd->pdev->dev, "FLR failed\n");
 }
 
+static void idxd_wqs_flush_descs(struct idxd_device *idxd)
+{
+	int i;
+
+	for (i = 0; i < idxd->max_wqs; i++) {
+		struct idxd_wq *wq = idxd->wqs[i];
+
+		idxd_wq_flush_descs(wq);
+	}
+}
+
 static irqreturn_t idxd_halt(struct idxd_device *idxd)
 {
 	union gensts_reg gensts;
···
 		} else if (gensts.reset_type == IDXD_DEVICE_RESET_FLR) {
 			idxd->state = IDXD_DEV_HALTED;
 			idxd_mask_error_interrupts(idxd);
+			/* Flush all pending descriptors, and disable
+			 * interrupts, they will be re-enabled when FLR
+			 * concludes.
+			 */
+			idxd_wqs_flush_descs(idxd);
 			dev_dbg(&idxd->pdev->dev,
 				"idxd halted, doing FLR. After FLR, configs are restored\n");
 			INIT_WORK(&idxd->work, idxd_device_flr);

drivers/dma/idxd/submit.c

···
 	 */
 	list_for_each_entry_safe(d, t, &flist, list) {
 		list_del_init(&d->list);
-		idxd_dma_complete_txd(found, IDXD_COMPLETE_ABORT, true,
+		idxd_dma_complete_txd(d, IDXD_COMPLETE_ABORT, true,
 				      NULL, NULL);
 	}
 }

drivers/dma/idxd/sysfs.c

···
 {
 	struct idxd_device *idxd = confdev_to_idxd(dev);
 
+	destroy_workqueue(idxd->wq);
 	kfree(idxd->groups);
 	bitmap_free(idxd->wq_enable_map);
 	kfree(idxd->wqs);

drivers/dma/sh/rz-dmac.c

···
  */
 
 #include <linux/bitfield.h>
+#include <linux/cleanup.h>
 #include <linux/dma-mapping.h>
 #include <linux/dmaengine.h>
 #include <linux/interrupt.h>
···
 {
 	struct dma_chan *chan = &channel->vc.chan;
 	struct rz_dmac *dmac = to_rz_dmac(chan->device);
-	unsigned long flags;
 
 	dev_dbg(dmac->dev, "%s channel %d\n", __func__, channel->index);
 
-	local_irq_save(flags);
 	rz_dmac_ch_writel(channel, CHCTRL_DEFAULT, CHCTRL, 1);
-	local_irq_restore(flags);
 }
 
 static void rz_dmac_set_dmars_register(struct rz_dmac *dmac, int nr, u32 dmars)
···
 		if (!desc)
 			break;
 
+		/* No need to lock. This is called only for the 1st client. */
 		list_add_tail(&desc->node, &channel->ld_free);
 		channel->descs_allocated++;
 	}
···
 	dev_dbg(dmac->dev, "%s channel: %d src=0x%pad dst=0x%pad len=%zu\n",
 		__func__, channel->index, &src, &dest, len);
 
-	if (list_empty(&channel->ld_free))
-		return NULL;
+	scoped_guard(spinlock_irqsave, &channel->vc.lock) {
+		if (list_empty(&channel->ld_free))
+			return NULL;
 
-	desc = list_first_entry(&channel->ld_free, struct rz_dmac_desc, node);
+		desc = list_first_entry(&channel->ld_free, struct rz_dmac_desc, node);
 
-	desc->type = RZ_DMAC_DESC_MEMCPY;
-	desc->src = src;
-	desc->dest = dest;
-	desc->len = len;
-	desc->direction = DMA_MEM_TO_MEM;
+		desc->type = RZ_DMAC_DESC_MEMCPY;
+		desc->src = src;
+		desc->dest = dest;
+		desc->len = len;
+		desc->direction = DMA_MEM_TO_MEM;
 
-	list_move_tail(channel->ld_free.next, &channel->ld_queue);
+		list_move_tail(channel->ld_free.next, &channel->ld_queue);
+	}
+
 	return vchan_tx_prep(&channel->vc, &desc->vd, flags);
 }
 
···
 	int dma_length = 0;
 	int i = 0;
 
-	if (list_empty(&channel->ld_free))
-		return NULL;
+	scoped_guard(spinlock_irqsave, &channel->vc.lock) {
+		if (list_empty(&channel->ld_free))
+			return NULL;
 
-	desc = list_first_entry(&channel->ld_free, struct rz_dmac_desc, node);
+		desc = list_first_entry(&channel->ld_free, struct rz_dmac_desc, node);
 
-	for_each_sg(sgl, sg, sg_len, i) {
-		dma_length += sg_dma_len(sg);
+		for_each_sg(sgl, sg, sg_len, i)
+			dma_length += sg_dma_len(sg);
+
+		desc->type = RZ_DMAC_DESC_SLAVE_SG;
+		desc->sg = sgl;
+		desc->sgcount = sg_len;
+		desc->len = dma_length;
+		desc->direction = direction;
+
+		if (direction == DMA_DEV_TO_MEM)
+			desc->src = channel->src_per_address;
+		else
+			desc->dest = channel->dst_per_address;
+
+		list_move_tail(channel->ld_free.next, &channel->ld_queue);
 	}
 
-	desc->type = RZ_DMAC_DESC_SLAVE_SG;
-	desc->sg = sgl;
-	desc->sgcount = sg_len;
-	desc->len = dma_length;
-	desc->direction = direction;
-
-	if (direction == DMA_DEV_TO_MEM)
-		desc->src = channel->src_per_address;
-	else
-		desc->dest = channel->dst_per_address;
-
-	list_move_tail(channel->ld_free.next, &channel->ld_queue);
 	return vchan_tx_prep(&channel->vc, &desc->vd, flags);
 }
 
···
 	unsigned int i;
 	LIST_HEAD(head);
 
-	rz_dmac_disable_hw(channel);
 	spin_lock_irqsave(&channel->vc.lock, flags);
+	rz_dmac_disable_hw(channel);
 	for (i = 0; i < DMAC_NR_LMDESC; i++)
 		lmdesc[i].header = 0;
 
···
 	if (chstat & CHSTAT_ER) {
 		dev_err(dmac->dev, "DMAC err CHSTAT_%d = %08X\n",
 			channel->index, chstat);
-		rz_dmac_ch_writel(channel, CHCTRL_DEFAULT, CHCTRL, 1);
+
+		scoped_guard(spinlock_irqsave, &channel->vc.lock)
+			rz_dmac_ch_writel(channel, CHCTRL_DEFAULT, CHCTRL, 1);
 		goto done;
 	}
 

drivers/dma/xilinx/xdma.c

···
 
 	xdev->rmap = devm_regmap_init_mmio(&pdev->dev, reg_base,
 					   &xdma_regmap_config);
-	if (!xdev->rmap) {
-		xdma_err(xdev, "config regmap failed: %d", ret);
+	if (IS_ERR(xdev->rmap)) {
+		xdma_err(xdev, "config regmap failed: %pe", xdev->rmap);
 		goto failed;
 	}
 	INIT_LIST_HEAD(&xdev->dma_dev.channels);

drivers/dma/xilinx/xilinx_dma.c

···
 					      struct xilinx_cdma_tx_segment,
 					      node);
 			cdma_hw = &cdma_seg->hw;
-			residue += (cdma_hw->control - cdma_hw->status) &
-				   chan->xdev->max_buffer_len;
+			residue += (cdma_hw->control & chan->xdev->max_buffer_len) -
+			           (cdma_hw->status & chan->xdev->max_buffer_len);
 		} else if (chan->xdev->dma_config->dmatype ==
 			   XDMA_TYPE_AXIDMA) {
 			axidma_seg = list_entry(entry,
 						struct xilinx_axidma_tx_segment,
 						node);
 			axidma_hw = &axidma_seg->hw;
-			residue += (axidma_hw->control - axidma_hw->status) &
-				   chan->xdev->max_buffer_len;
+			residue += (axidma_hw->control & chan->xdev->max_buffer_len) -
+			           (axidma_hw->status & chan->xdev->max_buffer_len);
 		} else {
 			aximcdma_seg =
 				list_entry(entry,
···
 					   node);
 			aximcdma_hw = &aximcdma_seg->hw;
 			residue +=
-				(aximcdma_hw->control - aximcdma_hw->status) &
-				chan->xdev->max_buffer_len;
+				(aximcdma_hw->control & chan->xdev->max_buffer_len) -
+				(aximcdma_hw->status & chan->xdev->max_buffer_len);
 		}
 	}
 
···
 	}
 
 	dma_cookie_init(dchan);
-
-	if (chan->xdev->dma_config->dmatype == XDMA_TYPE_AXIDMA) {
-		/* For AXI DMA resetting once channel will reset the
-		 * other channel as well so enable the interrupts here.
-		 */
-		dma_ctrl_set(chan, XILINX_DMA_REG_DMACR,
-			      XILINX_DMA_DMAXR_ALL_IRQ_MASK);
-	}
 
 	if ((chan->xdev->dma_config->dmatype == XDMA_TYPE_CDMA) && chan->has_sg)
 		dma_ctrl_set(chan, XILINX_DMA_REG_DMACR,
···
 	if (chan->err)
 		return;
 
-	if (list_empty(&chan->pending_list))
+	if (list_empty(&chan->pending_list)) {
+		if (chan->cyclic) {
+			struct xilinx_dma_tx_descriptor *desc;
+			struct list_head *entry;
+
+			desc = list_last_entry(&chan->done_list,
+					       struct xilinx_dma_tx_descriptor, node);
+			list_for_each(entry, &desc->segments) {
+				struct xilinx_axidma_tx_segment *axidma_seg;
+				struct xilinx_axidma_desc_hw *axidma_hw;
+				axidma_seg = list_entry(entry,
+							struct xilinx_axidma_tx_segment,
+							node);
+				axidma_hw = &axidma_seg->hw;
+				axidma_hw->status = 0;
+			}
+
+			list_splice_tail_init(&chan->done_list, &chan->active_list);
+			chan->desc_pendingcount = 0;
+			chan->idle = false;
+		}
 		return;
+	}
 
 	if (!chan->idle)
 		return;
···
 			     head_desc->async_tx.phys);
 	reg  &= ~XILINX_DMA_CR_DELAY_MAX;
 	reg  |= chan->irq_delay << XILINX_DMA_CR_DELAY_SHIFT;
+	reg |= XILINX_DMA_DMAXR_ALL_IRQ_MASK;
 	dma_ctrl_write(chan, XILINX_DMA_REG_DMACR, reg);
 
 	xilinx_dma_start(chan);
···
 		return -EINVAL;
 	}
 
-	xdev->common.directions |= chan->direction;
+	xdev->common.directions |= BIT(chan->direction);
 
 	/* Request the interrupt */
 	chan->irq = of_irq_get(node, chan->tdest);

drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c

···
 		goto err_ib_sched;
 	}
 
-	/* Drop the initial kref_init count (see drm_sched_main as example) */
-	dma_fence_put(f);
 	ret = dma_fence_wait(f, false);
+	/* Drop the returned fence reference after the wait completes */
+	dma_fence_put(f);
 
 err_ib_sched:
 	amdgpu_job_free(job);

drivers/gpu/drm/amd/amdgpu/amdgpu_device.c

···
 
 static int amdgpu_device_get_job_timeout_settings(struct amdgpu_device *adev)
 {
-	char *input = amdgpu_lockup_timeout;
+	char buf[AMDGPU_MAX_TIMEOUT_PARAM_LENGTH];
+	char *input = buf;
 	char *timeout_setting = NULL;
 	int index = 0;
 	long timeout;
···
 	adev->gfx_timeout = adev->compute_timeout = adev->sdma_timeout =
 		adev->video_timeout = msecs_to_jiffies(2000);
 
-	if (!strnlen(input, AMDGPU_MAX_TIMEOUT_PARAM_LENGTH))
+	if (!strnlen(amdgpu_lockup_timeout, AMDGPU_MAX_TIMEOUT_PARAM_LENGTH))
 		return 0;
+
+	/*
+	 * strsep() destructively modifies its input by replacing delimiters
+	 * with '\0'. Use a stack copy so the global module parameter buffer
+	 * remains intact for multi-GPU systems where this function is called
+	 * once per device.
+	 */
+	strscpy(buf, amdgpu_lockup_timeout, sizeof(buf));
 
 	while ((timeout_setting = strsep(&input, ",")) &&
 	       strnlen(timeout_setting, AMDGPU_MAX_TIMEOUT_PARAM_LENGTH)) {

drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c

···
  * PASIDs are global address space identifiers that can be shared
  * between the GPU, an IOMMU and the driver. VMs on different devices
  * may use the same PASID if they share the same address
- * space. Therefore PASIDs are allocated using a global IDA. VMs are
- * looked up from the PASID per amdgpu_device.
+ * space. Therefore PASIDs are allocated using IDR cyclic allocator
+ * (similar to kernel PID allocation) which naturally delays reuse.
+ * VMs are looked up from the PASID per amdgpu_device.
  */
-static DEFINE_IDA(amdgpu_pasid_ida);
+
+static DEFINE_IDR(amdgpu_pasid_idr);
+static DEFINE_SPINLOCK(amdgpu_pasid_idr_lock);
 
 /* Helper to free pasid from a fence callback */
 struct amdgpu_pasid_cb {
···
  * amdgpu_pasid_alloc - Allocate a PASID
  * @bits: Maximum width of the PASID in bits, must be at least 1
  *
- * Allocates a PASID of the given width while keeping smaller PASIDs
- * available if possible.
+ * Uses kernel's IDR cyclic allocator (same as PID allocation).
+ * Allocates sequentially with automatic wrap-around.
  *
  * Returns a positive integer on success. Returns %-EINVAL if bits==0.
  * Returns %-ENOSPC if no PASID was available. Returns %-ENOMEM on
···
  */
 int amdgpu_pasid_alloc(unsigned int bits)
 {
-	int pasid = -EINVAL;
+	int pasid;
 
-	for (bits = min(bits, 31U); bits > 0; bits--) {
-		pasid = ida_alloc_range(&amdgpu_pasid_ida, 1U << (bits - 1),
-					(1U << bits) - 1, GFP_KERNEL);
-		if (pasid != -ENOSPC)
-			break;
-	}
+	if (bits == 0)
+		return -EINVAL;
+
+	spin_lock(&amdgpu_pasid_idr_lock);
+	pasid = idr_alloc_cyclic(&amdgpu_pasid_idr, NULL, 1,
+				 1U << bits, GFP_KERNEL);
+	spin_unlock(&amdgpu_pasid_idr_lock);
 
 	if (pasid >= 0)
 		trace_amdgpu_pasid_allocated(pasid);
···
 void amdgpu_pasid_free(u32 pasid)
 {
 	trace_amdgpu_pasid_freed(pasid);
-	ida_free(&amdgpu_pasid_ida, pasid);
+
+	spin_lock(&amdgpu_pasid_idr_lock);
+	idr_remove(&amdgpu_pasid_idr, pasid);
+	spin_unlock(&amdgpu_pasid_idr_lock);
 }
 
 static void amdgpu_pasid_free_cb(struct dma_fence *fence,
···
 			dma_fence_put(id->pasid_mapping);
 		}
 	}
+}
+
+/**
+ * amdgpu_pasid_mgr_cleanup - cleanup PASID manager
+ *
+ * Cleanup the IDR allocator.
+ */
+void amdgpu_pasid_mgr_cleanup(void)
+{
+	spin_lock(&amdgpu_pasid_idr_lock);
+	idr_destroy(&amdgpu_pasid_idr);
+	spin_unlock(&amdgpu_pasid_idr_lock);
 }

drivers/gpu/drm/amd/amdgpu/amdgpu_ids.h

···
 void amdgpu_pasid_free(u32 pasid);
 void amdgpu_pasid_free_delayed(struct dma_resv *resv,
 			       u32 pasid);
+void amdgpu_pasid_mgr_cleanup(void);
 
 bool amdgpu_vmid_had_gpu_reset(struct amdgpu_device *adev,
 			       struct amdgpu_vmid *id);

drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c

···
 	xa_destroy(&adev->vm_manager.pasids);
 
 	amdgpu_vmid_mgr_fini(adev);
+	amdgpu_pasid_mgr_cleanup();
 }
 
 /**
···
 	if (!root)
 		return false;
 
-	addr /= AMDGPU_GPU_PAGE_SIZE;
-
 	if (is_compute_context && !svm_range_restore_pages(adev, pasid, vmid,
-	    node_id, addr, ts, write_fault)) {
+	    node_id, addr >> PAGE_SHIFT, ts, write_fault)) {
 		amdgpu_bo_unref(&root);
 		return true;
 	}
+
+	addr /= AMDGPU_GPU_PAGE_SIZE;
 
 	r = amdgpu_bo_reserve(root, true);
 	if (r)

drivers/gpu/drm/amd/amdkfd/kfd_chardev.c

···
 	struct kfd_process *process;
 	int ret;
 
-	/* Each FD owns only one kfd_process */
-	if (p->context_id != KFD_CONTEXT_ID_PRIMARY)
+	if (!filep->private_data || !p)
 		return -EINVAL;
 
-	if (!filep->private_data || !p)
+	/* Each FD owns only one kfd_process */
+	if (p->context_id != KFD_CONTEXT_ID_PRIMARY)
 		return -EINVAL;
 
 	mutex_lock(&kfd_processes_mutex);

drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c

···
 
 		aconnector->dc_sink = sink;
 		dc_sink_retain(aconnector->dc_sink);
+		drm_edid_free(aconnector->drm_edid);
+		aconnector->drm_edid = NULL;
 		if (sink->dc_edid.length == 0) {
-			aconnector->drm_edid = NULL;
 			hdmi_cec_unset_edid(aconnector);
 			if (aconnector->dc_link->aux_mode) {
 				drm_dp_cec_unset_edid(&aconnector->dm_dp_aux.aux);
···
 	caps = &dm->backlight_caps[aconnector->bl_idx];
 
 	/* Only offer ABM property when non-OLED and user didn't turn off by module parameter */
-	if (!caps->ext_caps->bits.oled && amdgpu_dm_abm_level < 0)
+	if (caps->ext_caps && !caps->ext_caps->bits.oled && amdgpu_dm_abm_level < 0)
 		drm_object_attach_property(&aconnector->base.base,
 					   dm->adev->mode_info.abm_level_property,
 					   ABM_SYSFS_CONTROL);
···
 	}
 
 	if (dc_resource_is_dsc_encoding_supported(dc)) {
+		for_each_oldnew_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) {
+			dm_new_crtc_state = to_dm_crtc_state(new_crtc_state);
+			dm_new_crtc_state->mode_changed_independent_from_dsc = new_crtc_state->mode_changed;
+		}
+
 		for_each_oldnew_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) {
 			if (drm_atomic_crtc_needs_modeset(new_crtc_state)) {
 				ret = add_affected_mst_dsc_crtcs(state, crtc);

drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h

···
 
 	bool freesync_vrr_info_changed;
 
+	bool mode_changed_independent_from_dsc;
 	bool dsc_force_changed;
 	bool vrr_supported;
 	struct mod_freesync_config freesync_config;

drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c

···
 			int ind = find_crtc_index_in_state_by_stream(state, stream);
 
 			if (ind >= 0) {
+				struct dm_crtc_state *dm_new_crtc_state = to_dm_crtc_state(state->crtcs[ind].new_state);
+
 				DRM_INFO_ONCE("%s:%d MST_DSC no mode changed for stream 0x%p\n",
 						__func__, __LINE__, stream);
-				state->crtcs[ind].new_state->mode_changed = 0;
+				dm_new_crtc_state->base.mode_changed = dm_new_crtc_state->mode_changed_independent_from_dsc;
 			}
 		}
 	}

drivers/gpu/drm/amd/display/dc/resource/dce100/dce100_resource.c

···
 		return &enc110->base;
 	}
 
-	if (enc_init_data->hpd_source >= ARRAY_SIZE(link_enc_hpd_regs))
-		return NULL;
-
 	link_regs_id =
 		map_transmitter_id_to_phy_instance(enc_init_data->transmitter);
 
···
 				      &link_enc_feature,
 				      &link_enc_regs[link_regs_id],
 				      &link_enc_aux_regs[enc_init_data->channel - 1],
-				      &link_enc_hpd_regs[enc_init_data->hpd_source]);
+				      enc_init_data->hpd_source >= ARRAY_SIZE(link_enc_hpd_regs) ?
+				      NULL : &link_enc_hpd_regs[enc_init_data->hpd_source]);
 	return &enc110->base;
 }
 

drivers/gpu/drm/amd/display/dc/resource/dce110/dce110_resource.c

···
 		kzalloc_obj(struct dce110_link_encoder);
 	int link_regs_id;
 
-	if (!enc110 || enc_init_data->hpd_source >= ARRAY_SIZE(link_enc_hpd_regs))
+	if (!enc110)
 		return NULL;
 
 	link_regs_id =
···
 				      &link_enc_feature,
 				      &link_enc_regs[link_regs_id],
 				      &link_enc_aux_regs[enc_init_data->channel - 1],
-				      &link_enc_hpd_regs[enc_init_data->hpd_source]);
+				      enc_init_data->hpd_source >= ARRAY_SIZE(link_enc_hpd_regs) ?
+				      NULL : &link_enc_hpd_regs[enc_init_data->hpd_source]);
 	return &enc110->base;
 }
 

drivers/gpu/drm/amd/display/dc/resource/dce112/dce112_resource.c

···
 		kzalloc_obj(struct dce110_link_encoder);
 	int link_regs_id;
 
-	if (!enc110 || enc_init_data->hpd_source >= ARRAY_SIZE(link_enc_hpd_regs))
+	if (!enc110)
 		return NULL;
 
 	link_regs_id =
···
 				      &link_enc_feature,
 				      &link_enc_regs[link_regs_id],
 				      &link_enc_aux_regs[enc_init_data->channel - 1],
-				      &link_enc_hpd_regs[enc_init_data->hpd_source]);
+				      enc_init_data->hpd_source >= ARRAY_SIZE(link_enc_hpd_regs) ?
+				      NULL : &link_enc_hpd_regs[enc_init_data->hpd_source]);
 	return &enc110->base;
 }
 

drivers/gpu/drm/amd/display/dc/resource/dce120/dce120_resource.c

···
 		kzalloc_obj(struct dce110_link_encoder);
 	int link_regs_id;
 
-	if (!enc110 || enc_init_data->hpd_source >= ARRAY_SIZE(link_enc_hpd_regs))
+	if (!enc110)
 		return NULL;
 
 	link_regs_id =
···
 				      &link_enc_feature,
 				      &link_enc_regs[link_regs_id],
 				      &link_enc_aux_regs[enc_init_data->channel - 1],
-				      &link_enc_hpd_regs[enc_init_data->hpd_source]);
+				      enc_init_data->hpd_source >= ARRAY_SIZE(link_enc_hpd_regs) ?
+				      NULL : &link_enc_hpd_regs[enc_init_data->hpd_source]);
 
 	return &enc110->base;
 }

drivers/gpu/drm/amd/display/dc/resource/dce60/dce60_resource.c

···
 		return &enc110->base;
 	}
 
-	if (enc_init_data->hpd_source >= ARRAY_SIZE(link_enc_hpd_regs))
-		return NULL;
-
 	link_regs_id =
 		map_transmitter_id_to_phy_instance(enc_init_data->transmitter);
 
 	dce60_link_encoder_construct(enc110,
-				      enc_init_data,
-				      &link_enc_feature,
-				      &link_enc_regs[link_regs_id],
-				      &link_enc_aux_regs[enc_init_data->channel - 1],
-				      &link_enc_hpd_regs[enc_init_data->hpd_source]);
+				     enc_init_data,
+				     &link_enc_feature,
+				     &link_enc_regs[link_regs_id],
+				     &link_enc_aux_regs[enc_init_data->channel - 1],
+				     enc_init_data->hpd_source >= ARRAY_SIZE(link_enc_hpd_regs) ?
+				     NULL : &link_enc_hpd_regs[enc_init_data->hpd_source]);
 	return &enc110->base;
 }
 

drivers/gpu/drm/amd/display/dc/resource/dce80/dce80_resource.c

···
 		return &enc110->base;
 	}
 
-	if (enc_init_data->hpd_source >= ARRAY_SIZE(link_enc_hpd_regs))
-		return NULL;
-
 	link_regs_id =
 		map_transmitter_id_to_phy_instance(enc_init_data->transmitter);
 
···
 				      &link_enc_feature,
 				      &link_enc_regs[link_regs_id],
 				      &link_enc_aux_regs[enc_init_data->channel - 1],
-				      &link_enc_hpd_regs[enc_init_data->hpd_source]);
+				      enc_init_data->hpd_source >= ARRAY_SIZE(link_enc_hpd_regs) ?
+				      NULL : &link_enc_hpd_regs[enc_init_data->hpd_source]);
 	return &enc110->base;
 }
 

drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c

···
 
 #define to_amdgpu_device(x) (container_of(x, struct amdgpu_device, pm.smu_i2c))
 
+static void smu_v13_0_0_get_od_setting_limits(struct smu_context *smu,
+					      int od_feature_bit,
+					      int32_t *min, int32_t *max);
+
 static const struct smu_feature_bits smu_v13_0_0_dpm_features = {
 	.bits = {
 		SMU_FEATURE_BIT_INIT(FEATURE_DPM_GFXCLK_BIT),
···
 	PPTable_t *pptable = smu->smu_table.driver_pptable;
 	const OverDriveLimits_t * const overdrive_upperlimits =
 				&pptable->SkuTable.OverDriveLimitsBasicMax;
+	int32_t min_value, max_value;
+	bool feature_enabled;
 
-	return overdrive_upperlimits->FeatureCtrlMask & (1U << od_feature_bit);
+	switch (od_feature_bit) {
+	case PP_OD_FEATURE_FAN_CURVE_BIT:
+		feature_enabled = !!(overdrive_upperlimits->FeatureCtrlMask & (1U << od_feature_bit));
+		if (feature_enabled) {
+			smu_v13_0_0_get_od_setting_limits(smu, PP_OD_FEATURE_FAN_CURVE_TEMP,
+							  &min_value, &max_value);
+			if (!min_value && !max_value) {
+				feature_enabled = false;
+				goto out;
+			}
+
+			smu_v13_0_0_get_od_setting_limits(smu, PP_OD_FEATURE_FAN_CURVE_PWM,
+							  &min_value, &max_value);
+			if (!min_value && !max_value) {
+				feature_enabled = false;
+				goto out;
+			}
+		}
+		break;
+	default:
+		feature_enabled = !!(overdrive_upperlimits->FeatureCtrlMask & (1U << od_feature_bit));
+		break;
+	}
+
+out:
+	return feature_enabled;
 }
 
 static void smu_v13_0_0_get_od_setting_limits(struct smu_context *smu,

drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c

···
 		break;
 	case SMU_OD_MCLK:
 		if (!smu_v13_0_6_cap_supported(smu, SMU_CAP(SET_UCLK_MAX)))
-			return 0;
+			return -EOPNOTSUPP;
 
 		size += sysfs_emit_at(buf, size, "%s:\n", "OD_MCLK");
 		size += sysfs_emit_at(buf, size, "0: %uMhz\n1: %uMhz\n",
···
 {
 	struct smu_dpm_context *smu_dpm = &(smu->smu_dpm);
 	struct smu_13_0_dpm_context *dpm_context = smu_dpm->dpm_context;
+	struct smu_dpm_table *uclk_table = &dpm_context->dpm_tables.uclk_table;
 	struct smu_umd_pstate_table *pstate_table = &smu->pstate_table;
 	uint32_t min_clk;
 	uint32_t max_clk;
···
 			if (ret)
 				return ret;
 
-			min_clk = SMU_DPM_TABLE_MIN(
-				&dpm_context->dpm_tables.uclk_table);
-			max_clk = SMU_DPM_TABLE_MAX(
-				&dpm_context->dpm_tables.uclk_table);
-			ret = smu_v13_0_6_set_soft_freq_limited_range(
-				smu, SMU_UCLK, min_clk, max_clk, false);
-			if (ret)
-				return ret;
+			if (SMU_DPM_TABLE_MAX(uclk_table) !=
+			    pstate_table->uclk_pstate.curr.max) {
+				min_clk = SMU_DPM_TABLE_MIN(&dpm_context->dpm_tables.uclk_table);
+				max_clk = SMU_DPM_TABLE_MAX(&dpm_context->dpm_tables.uclk_table);
+				ret = smu_v13_0_6_set_soft_freq_limited_range(smu,
+									      SMU_UCLK, min_clk,
+									      max_clk, false);
+				if (ret)
+					return ret;
+			}
 			smu_v13_0_reset_custom_level(smu);
 		}
 		break;

drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c

···
 
 #define to_amdgpu_device(x) (container_of(x, struct amdgpu_device, pm.smu_i2c))
 
+static void smu_v13_0_7_get_od_setting_limits(struct smu_context *smu,
+					      int od_feature_bit,
+					      int32_t *min, int32_t *max);
+
 static const struct smu_feature_bits smu_v13_0_7_dpm_features = {
 	.bits = {
 		SMU_FEATURE_BIT_INIT(FEATURE_DPM_GFXCLK_BIT),
···
 	PPTable_t *pptable = smu->smu_table.driver_pptable;
 	const OverDriveLimits_t * const overdrive_upperlimits =
 				&pptable->SkuTable.OverDriveLimitsBasicMax;
+	int32_t min_value, max_value;
+	bool feature_enabled;
 
-	return overdrive_upperlimits->FeatureCtrlMask & (1U << od_feature_bit);
+	switch (od_feature_bit) {
+	case PP_OD_FEATURE_FAN_CURVE_BIT:
+		feature_enabled = !!(overdrive_upperlimits->FeatureCtrlMask & (1U << od_feature_bit));
+		if (feature_enabled) {
+			smu_v13_0_7_get_od_setting_limits(smu, PP_OD_FEATURE_FAN_CURVE_TEMP,
+							  &min_value, &max_value);
+			if (!min_value && !max_value) {
+				feature_enabled = false;
+				goto out;
+			}
+
+			smu_v13_0_7_get_od_setting_limits(smu, PP_OD_FEATURE_FAN_CURVE_PWM,
+							  &min_value, &max_value);
+			if (!min_value && !max_value) {
+				feature_enabled = false;
+				goto out;
+			}
+		}
+		break;
+	default:
+		feature_enabled = !!(overdrive_upperlimits->FeatureCtrlMask & (1U << od_feature_bit));
+		break;
+	}
+
+out:
+	return feature_enabled;
 }
 
 static void smu_v13_0_7_get_od_setting_limits(struct smu_context *smu,

drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c

···
 
 #define to_amdgpu_device(x) (container_of(x, struct amdgpu_device, pm.smu_i2c))
 
+static void smu_v14_0_2_get_od_setting_limits(struct smu_context *smu,
+					      int od_feature_bit,
+					      int32_t *min, int32_t *max);
+
 static const struct smu_feature_bits smu_v14_0_2_dpm_features = {
 	.bits = { SMU_FEATURE_BIT_INIT(FEATURE_DPM_GFXCLK_BIT),
 		  SMU_FEATURE_BIT_INIT(FEATURE_DPM_UCLK_BIT),
···
 	PPTable_t *pptable = smu->smu_table.driver_pptable;
 	const OverDriveLimits_t * const overdrive_upperlimits =
 				&pptable->SkuTable.OverDriveLimitsBasicMax;
+	int32_t min_value, max_value;
+	bool feature_enabled;
 
-	return overdrive_upperlimits->FeatureCtrlMask & (1U << od_feature_bit);
+	switch (od_feature_bit) {
+	case PP_OD_FEATURE_FAN_CURVE_BIT:
+		feature_enabled = !!(overdrive_upperlimits->FeatureCtrlMask & (1U << od_feature_bit));
+		if (feature_enabled) {
+			smu_v14_0_2_get_od_setting_limits(smu, PP_OD_FEATURE_FAN_CURVE_TEMP,
+							  &min_value, &max_value);
+			if (!min_value && !max_value) {
+				feature_enabled = false;
+				goto out;
+			}
+
+			smu_v14_0_2_get_od_setting_limits(smu, PP_OD_FEATURE_FAN_CURVE_PWM,
+							  &min_value, &max_value);
+			if (!min_value && !max_value) {
+				feature_enabled = false;
+				goto out;
+			}
+		}
+		break;
+	default:
+		feature_enabled = !!(overdrive_upperlimits->FeatureCtrlMask & (1U << od_feature_bit));
+		break;
+	}
+
+out:
+	return feature_enabled;
 }
 
 static void smu_v14_0_2_get_od_setting_limits(struct smu_context *smu,

drivers/gpu/drm/drm_gem_shmem_helper.c

···
 }
 EXPORT_SYMBOL_GPL(drm_gem_shmem_dumb_create);
 
-static bool drm_gem_shmem_try_map_pmd(struct vm_fault *vmf, unsigned long addr,
-				      struct page *page)
+static vm_fault_t try_insert_pfn(struct vm_fault *vmf, unsigned int order,
+				 unsigned long pfn)
 {
+	if (!order) {
+		return vmf_insert_pfn(vmf->vma, vmf->address, pfn);
 #ifdef CONFIG_ARCH_SUPPORTS_PMD_PFNMAP
-	unsigned long pfn = page_to_pfn(page);
-	unsigned long paddr = pfn << PAGE_SHIFT;
-	bool aligned = (addr & ~PMD_MASK) == (paddr & ~PMD_MASK);
+	} else if (order == PMD_ORDER) {
+		unsigned long paddr = pfn << PAGE_SHIFT;
+		bool aligned = (vmf->address & ~PMD_MASK) == (paddr & ~PMD_MASK);
 
-	if (aligned &&
-	    pmd_none(*vmf->pmd) &&
-	    folio_test_pmd_mappable(page_folio(page))) {
-		pfn &= PMD_MASK >> PAGE_SHIFT;
-		if (vmf_insert_pfn_pmd(vmf, pfn, false) == VM_FAULT_NOPAGE)
-			return true;
-	}
+		if (aligned &&
+		    folio_test_pmd_mappable(page_folio(pfn_to_page(pfn)))) {
+			pfn &= PMD_MASK >> PAGE_SHIFT;
+			return vmf_insert_pfn_pmd(vmf, pfn, false);
+		}
 #endif
-
-	return false;
+	}
+	return VM_FAULT_FALLBACK;
 }
 
-static vm_fault_t drm_gem_shmem_fault(struct vm_fault *vmf)
+static vm_fault_t drm_gem_shmem_any_fault(struct vm_fault *vmf, unsigned int order)
 {
 	struct vm_area_struct *vma = vmf->vma;
 	struct drm_gem_object *obj = vma->vm_private_data;
···
 	struct page **pages = shmem->pages;
 	pgoff_t page_offset;
 	unsigned long pfn;
+
+	if (order && order != PMD_ORDER)
+		return VM_FAULT_FALLBACK;
 
 	/* Offset to faulty address in the VMA. */
 	page_offset = vmf->pgoff - vma->vm_pgoff;
···
 		goto out;
 	}
 
-	if (drm_gem_shmem_try_map_pmd(vmf, vmf->address, pages[page_offset])) {
-		ret = VM_FAULT_NOPAGE;
-		goto out;
-	}
-
 	pfn = page_to_pfn(pages[page_offset]);
-	ret = vmf_insert_pfn(vma, vmf->address, pfn);
+	ret = try_insert_pfn(vmf, order, pfn);
 
  out:
 	dma_resv_unlock(shmem->base.resv);
 
 	return ret;
+}
+
+static vm_fault_t drm_gem_shmem_fault(struct vm_fault *vmf)
+{
+	return drm_gem_shmem_any_fault(vmf, 0);
 }
 
 static void drm_gem_shmem_vm_open(struct vm_area_struct *vma)
···
 
 const struct vm_operations_struct drm_gem_shmem_vm_ops = {
 	.fault = drm_gem_shmem_fault,
+#ifdef CONFIG_ARCH_SUPPORTS_PMD_PFNMAP
+	.huge_fault = drm_gem_shmem_any_fault,
+#endif
 	.open = drm_gem_shmem_vm_open,
 	.close = drm_gem_shmem_vm_close,
 };

drivers/gpu/drm/drm_syncobj.c

···
 	drm_syncobj_get(syncobj);
 
 	ret = xa_alloc(&file_private->syncobj_xa, handle, syncobj, xa_limit_32b,
-		       GFP_NOWAIT);
+		       GFP_KERNEL);
 	if (ret)
 		drm_syncobj_put(syncobj);
 
···
 	drm_syncobj_get(syncobj);
 
 	ret = xa_alloc(&file_private->syncobj_xa, handle, syncobj, xa_limit_32b,
-		       GFP_NOWAIT);
+		       GFP_KERNEL);
 	if (ret)
 		drm_syncobj_put(syncobj);
 

drivers/gpu/drm/i915/display/intel_display.c

···
 	struct intel_crtc_state *crtc_state =
 		intel_atomic_get_new_crtc_state(state, crtc);
 	struct intel_crtc_state *saved_state;
+	int err;
 
 	saved_state = intel_crtc_state_alloc(crtc);
 	if (!saved_state)
···
 	/* free the old crtc_state->hw members */
 	intel_crtc_free_hw_state(crtc_state);
 
-	intel_dp_tunnel_atomic_clear_stream_bw(state, crtc_state);
+	err = intel_dp_tunnel_atomic_clear_stream_bw(state, crtc_state);
+	if (err) {
+		kfree(saved_state);
+
+		return err;
+	}
 
 	/* FIXME: before the switch to atomic started, a new pipe_config was
 	 * kzalloc'd. Code that depends on any field being zero should be

drivers/gpu/drm/i915/display/intel_dp_tunnel.c

···
  *
  * Clear any DP tunnel stream BW requirement set by
  * intel_dp_tunnel_atomic_compute_stream_bw().
+ *
+ * Returns 0 in case of success, a negative error code otherwise.
  */
-void intel_dp_tunnel_atomic_clear_stream_bw(struct intel_atomic_state *state,
-					    struct intel_crtc_state *crtc_state)
+int intel_dp_tunnel_atomic_clear_stream_bw(struct intel_atomic_state *state,
+					   struct intel_crtc_state *crtc_state)
 {
 	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
+	int err;
 
 	if (!crtc_state->dp_tunnel_ref.tunnel)
-		return;
+		return 0;
 
-	drm_dp_tunnel_atomic_set_stream_bw(&state->base,
-					   crtc_state->dp_tunnel_ref.tunnel,
-					   crtc->pipe, 0);
+	err = drm_dp_tunnel_atomic_set_stream_bw(&state->base,
+						 crtc_state->dp_tunnel_ref.tunnel,
+						 crtc->pipe, 0);
+	if (err)
+		return err;
+
 	drm_dp_tunnel_ref_put(&crtc_state->dp_tunnel_ref);
+
+	return 0;
 }
 
 /**

drivers/gpu/drm/i915/display/intel_dp_tunnel.h

···
 					     struct intel_dp *intel_dp,
 					     const struct intel_connector *connector,
 					     struct intel_crtc_state *crtc_state);
-void intel_dp_tunnel_atomic_clear_stream_bw(struct intel_atomic_state *state,
-					    struct intel_crtc_state *crtc_state);
+int intel_dp_tunnel_atomic_clear_stream_bw(struct intel_atomic_state *state,
+					   struct intel_crtc_state *crtc_state);
 
 int intel_dp_tunnel_atomic_add_state_for_crtc(struct intel_atomic_state *state,
 					      struct intel_crtc *crtc);
···
 	return 0;
 }
 
-static inline void
+static inline int
 intel_dp_tunnel_atomic_clear_stream_bw(struct intel_atomic_state *state,
-				       struct intel_crtc_state *crtc_state) {}
+				       struct intel_crtc_state *crtc_state)
+{
+	return 0;
+}
 
 static inline int
 intel_dp_tunnel_atomic_add_state_for_crtc(struct intel_atomic_state *state,

drivers/gpu/drm/i915/display/intel_gmbus.c

···
 
 		val = intel_de_read_fw(display, GMBUS3(display));
 		do {
-			if (extra_byte_added && len == 1)
+			if (extra_byte_added && len == 1) {
+				len--;
 				break;
+			}
 
 			*buf++ = val & 0xff;
 			val >>= 8;

drivers/gpu/drm/i915/display/intel_plane.c

···
 		drm_framebuffer_get(plane_state->hw.fb);
 }
 
+static void unlink_nv12_plane(struct intel_crtc_state *crtc_state,
+			      struct intel_plane_state *plane_state);
+
 void intel_plane_set_invisible(struct intel_crtc_state *crtc_state,
 			       struct intel_plane_state *plane_state)
 {
 	struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane);
+
+	unlink_nv12_plane(crtc_state, plane_state);
 
 	crtc_state->active_planes &= ~BIT(plane->id);
 	crtc_state->scaled_planes &= ~BIT(plane->id);
···
 	struct intel_display *display = to_intel_display(plane_state);
 	struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane);
 
+	if (!plane_state->planar_linked_plane)
+		return;
+
 	plane_state->planar_linked_plane = NULL;
 
 	if (!plane_state->is_y_plane)
···
 		if (plane->pipe != crtc->pipe)
 			continue;
 
-		if (plane_state->planar_linked_plane)
-			unlink_nv12_plane(crtc_state, plane_state);
+		unlink_nv12_plane(crtc_state, plane_state);
 	}
 
 	if (!crtc_state->nv12_planes)

drivers/gpu/drm/i915/i915_wait_util.h

···
 	might_sleep();							\
 	for (;;) {							\
 		const bool expired__ = ktime_after(ktime_get_raw(), end__); \
-		OP;							\
 		/* Guarantee COND check prior to timeout */		\
 		barrier();						\
+		OP;							\
 		if (COND) {						\
 			ret__ = 0;					\
 			break;						\

drivers/gpu/drm/mediatek/mtk_dsi.c

···
 
 	dsi->host.ops = &mtk_dsi_ops;
 	dsi->host.dev = dev;
+
+	init_waitqueue_head(&dsi->irq_wait_queue);
+
+	platform_set_drvdata(pdev, dsi);
+
 	ret = mipi_dsi_host_register(&dsi->host);
 	if (ret < 0)
 		return dev_err_probe(dev, ret, "Failed to register DSI host\n");
···
 		mipi_dsi_host_unregister(&dsi->host);
 		return dev_err_probe(&pdev->dev, ret, "Failed to request DSI irq\n");
 	}
-
-	init_waitqueue_head(&dsi->irq_wait_queue);
-
-	platform_set_drvdata(pdev, dsi);
 
 	dsi->bridge.of_node = dev->of_node;
 	dsi->bridge.type = DRM_MODE_CONNECTOR_DSI;

drivers/gpu/drm/xe/regs/xe_gt_regs.h

···
 #define   ENABLE_SMP_LD_RENDER_SURFACE_CONTROL	REG_BIT(44 - 32)
 #define   FORCE_SLM_FENCE_SCOPE_TO_TILE		REG_BIT(42 - 32)
 #define   FORCE_UGM_FENCE_SCOPE_TO_TILE		REG_BIT(41 - 32)
+#define   L3_128B_256B_WRT_DIS			REG_BIT(40 - 32)
 #define   MAXREQS_PER_BANK			REG_GENMASK(39 - 32, 37 - 32)
 #define   DISABLE_128B_EVICTION_COMMAND_UDW	REG_BIT(36 - 32)
 

drivers/gpu/drm/xe/xe_pt.c

···
 		err = vma_check_userptr(vm, op->map.vma, pt_update);
 		break;
 	case DRM_GPUVA_OP_REMAP:
-		if (op->remap.prev)
+		if (op->remap.prev && !op->remap.skip_prev)
 			err = vma_check_userptr(vm, op->remap.prev, pt_update);
-		if (!err && op->remap.next)
+		if (!err && op->remap.next && !op->remap.skip_next)
 			err = vma_check_userptr(vm, op->remap.next, pt_update);
 		break;
 	case DRM_GPUVA_OP_UNMAP:
···
 
 		err = unbind_op_prepare(tile, pt_update_ops, old);
 
-		if (!err && op->remap.prev) {
+		if (!err && op->remap.prev && !op->remap.skip_prev) {
 			err = bind_op_prepare(vm, tile, pt_update_ops,
 					      op->remap.prev, false);
 			pt_update_ops->wait_vm_bookkeep = true;
 		}
-		if (!err && op->remap.next) {
+		if (!err && op->remap.next && !op->remap.skip_next) {
 			err = bind_op_prepare(vm, tile, pt_update_ops,
 					      op->remap.next, false);
 			pt_update_ops->wait_vm_bookkeep = true;
···
 
 		unbind_op_commit(vm, tile, pt_update_ops, old, fence, fence2);
 
-		if (op->remap.prev)
+		if (op->remap.prev && !op->remap.skip_prev)
 			bind_op_commit(vm, tile, pt_update_ops, op->remap.prev,
 				       fence, fence2, false);
-		if (op->remap.next)
+		if (op->remap.next && !op->remap.skip_next)
 			bind_op_commit(vm, tile, pt_update_ops, op->remap.next,
 				       fence, fence2, false);
 		break;

drivers/gpu/drm/xe/xe_sriov_packet.c

···
 		ret = xe_sriov_pf_migration_restore_produce(xe, vfid, *data);
 		if (ret) {
 			xe_sriov_packet_free(*data);
+			*data = NULL;
+
 			return ret;
 		}
 

drivers/gpu/drm/xe/xe_vm.c

···
 			if (!err && op->remap.skip_prev) {
 				op->remap.prev->tile_present =
 					tile_present;
-				op->remap.prev = NULL;
 			}
 		}
 		if (op->remap.next) {
···
 			if (!err && op->remap.skip_next) {
 				op->remap.next->tile_present =
 					tile_present;
-				op->remap.next = NULL;
 			}
 		}
 
-		/* Adjust for partial unbind after removing VMA from VM */
+		/*
+		 * Adjust for partial unbind after removing VMA from VM. In case
+		 * of unwind we might need to undo this later.
+		 */
 		if (!err) {
 			op->base.remap.unmap->va->va.addr = op->remap.start;
 			op->base.remap.unmap->va->va.range = op->remap.range;
···
 
 			op->remap.start = xe_vma_start(old);
 			op->remap.range = xe_vma_size(old);
+			op->remap.old_start = op->remap.start;
+			op->remap.old_range = op->remap.range;
 
 			flags |= op->base.remap.unmap->va->flags & XE_VMA_CREATE_MASK;
 			if (op->base.remap.prev) {
···
 			xe_svm_notifier_lock(vm);
 			vma->gpuva.flags &= ~XE_VMA_DESTROYED;
 			xe_svm_notifier_unlock(vm);
-			if (post_commit)
+			if (post_commit) {
+				/*
+				 * Restore the old va range, in case of the
+				 * prev/next skip optimisation. Otherwise what
+				 * we re-insert here could be smaller than the
+				 * original range.
+				 */
+				op->base.remap.unmap->va->va.addr =
+					op->remap.old_start;
+				op->base.remap.unmap->va->va.range =
+					op->remap.old_range;
 				xe_vm_insert_vma(vm, vma);
+			}
 		}
 		break;
 	}

drivers/gpu/drm/xe/xe_vm_types.h

···
 	u64 start;
 	/** @range: range of the VMA unmap */
 	u64 range;
+	/** @old_start: Original start of the VMA we unmap */
+	u64 old_start;
+	/** @old_range: Original range of the VMA we unmap */
+	u64 old_range;
 	/** @skip_prev: skip prev rebind */
 	bool skip_prev;
 	/** @skip_next: skip next rebind */

drivers/gpu/drm/xe/xe_wa.c

···
 				   LSN_DIM_Z_WGT_MASK,
 				   LSN_LNI_WGT(1) | LSN_LNE_WGT(1) |
 				   LSN_DIM_X_WGT(1) | LSN_DIM_Y_WGT(1) |
-				   LSN_DIM_Z_WGT(1)))
+				   LSN_DIM_Z_WGT(1)),
+			SET(LSC_CHICKEN_BIT_0_UDW, L3_128B_256B_WRT_DIS))
 	},
 
 	/* Xe2_HPM */

drivers/hwmon/adm1177.c

···
 #include <linux/hwmon.h>
 #include <linux/i2c.h>
 #include <linux/init.h>
+#include <linux/math64.h>
+#include <linux/minmax.h>
 #include <linux/module.h>
 #include <linux/regulator/consumer.h>
 
···
 struct adm1177_state {
 	struct i2c_client	*client;
 	u32			r_sense_uohm;
-	u32			alert_threshold_ua;
+	u64			alert_threshold_ua;
 	bool			vrange_high;
 };
 
···
 }
 
 static int adm1177_write_alert_thr(struct adm1177_state *st,
-				   u32 alert_threshold_ua)
+				   u64 alert_threshold_ua)
 {
 	u64 val;
 	int ret;
···
 			*val = div_u64((105840000ull * dummy),
 				       4096 * st->r_sense_uohm);
 			return 0;
-		case hwmon_curr_max_alarm:
-			*val = st->alert_threshold_ua;
+		case hwmon_curr_max:
+			*val = div_u64(st->alert_threshold_ua, 1000);
 			return 0;
 		default:
 			return -EOPNOTSUPP;
···
 	switch (type) {
 	case hwmon_curr:
 		switch (attr) {
-		case hwmon_curr_max_alarm:
-			adm1177_write_alert_thr(st, val);
-			return 0;
+		case hwmon_curr_max:
+			val = clamp_val(val, 0,
+					div_u64(105840000ULL, st->r_sense_uohm));
+			return adm1177_write_alert_thr(st, (u64)val * 1000);
 		default:
 			return -EOPNOTSUPP;
 		}
···
 			if (st->r_sense_uohm)
 				return 0444;
 			return 0;
-		case hwmon_curr_max_alarm:
+		case hwmon_curr_max:
 			if (st->r_sense_uohm)
 				return 0644;
 			return 0;
···
 
 static const struct hwmon_channel_info * const adm1177_info[] = {
 	HWMON_CHANNEL_INFO(curr,
-			   HWMON_C_INPUT | HWMON_C_MAX_ALARM),
+			   HWMON_C_INPUT | HWMON_C_MAX),
 	HWMON_CHANNEL_INFO(in,
 			   HWMON_I_INPUT),
 	NULL
···
 	struct device *dev = &client->dev;
 	struct device *hwmon_dev;
 	struct adm1177_state *st;
-	u32 alert_threshold_ua;
+	u64 alert_threshold_ua;
+	u32 prop;
 	int ret;
 
 	st = devm_kzalloc(dev, sizeof(*st), GFP_KERNEL);
···
 	if (device_property_read_u32(dev, "shunt-resistor-micro-ohms",
 				     &st->r_sense_uohm))
 		st->r_sense_uohm = 0;
-	if (device_property_read_u32(dev, "adi,shutdown-threshold-microamp",
-				     &alert_threshold_ua)) {
-		if (st->r_sense_uohm)
-			/*
-			 * set maximum default value from datasheet based on
-			 * shunt-resistor
-			 */
-			alert_threshold_ua = div_u64(105840000000,
-						     st->r_sense_uohm);
-		else
-			alert_threshold_ua = 0;
+	if (!device_property_read_u32(dev, "adi,shutdown-threshold-microamp",
+				      &prop)) {
+		alert_threshold_ua = prop;
+	} else if (st->r_sense_uohm) {
+		/*
+		 * set maximum default value from datasheet based on
+		 * shunt-resistor
+		 */
+		alert_threshold_ua = div_u64(105840000000ULL,
+					     st->r_sense_uohm);
+	} else {
+		alert_threshold_ua = 0;
 	}
 	st->vrange_high = device_property_read_bool(dev,
 						    "adi,vrange-high-enable");
-	if (alert_threshold_ua && st->r_sense_uohm)
-		adm1177_write_alert_thr(st, alert_threshold_ua);
+	if (alert_threshold_ua && st->r_sense_uohm) {
+		ret = adm1177_write_alert_thr(st, alert_threshold_ua);
+		if (ret)
+			return ret;
+	}
 
 	ret = adm1177_write_cmd(st, ADM1177_CMD_V_CONT |
 				    ADM1177_CMD_I_CONT |

drivers/hwmon/peci/cputemp.c

···
 		*val = priv->temp.target.tjmax;
 		break;
 	case crit_hyst_type:
-		*val = priv->temp.target.tjmax - priv->temp.target.tcontrol;
+		*val = priv->temp.target.tcontrol;
 		break;
 	default:
 		ret = -EOPNOTSUPP;
···
 {
 	const struct peci_cputemp *priv = data;
 
-	if (channel > CPUTEMP_CHANNEL_NUMS)
+	if (channel >= CPUTEMP_CHANNEL_NUMS)
 		return 0;
 
 	if (channel < channel_core)

drivers/hwmon/pmbus/ina233.c

···
 
 		/* Adjust returned value to match VIN coefficients */
 		/* VIN: 1.25 mV VSHUNT: 2.5 uV LSB */
-		ret = DIV_ROUND_CLOSEST(ret * 25, 12500);
+		ret = clamp_val(DIV_ROUND_CLOSEST((s16)ret * 25, 12500),
+				S16_MIN, S16_MAX) & 0xffff;
 		break;
 	default:
 		ret = -ENODATA;

drivers/hwmon/pmbus/isl68137.c

···
 					     int page,
 					     char *buf)
 {
-	int val = pmbus_read_byte_data(client, page, PMBUS_OPERATION);
+	int val;
+
+	val = pmbus_lock_interruptible(client);
+	if (val)
+		return val;
+
+	val = pmbus_read_byte_data(client, page, PMBUS_OPERATION);
+
+	pmbus_unlock(client);
 
 	if (val < 0)
 		return val;
···
 
 	op_val = result ? ISL68137_VOUT_AVS : 0;
 
+	rc = pmbus_lock_interruptible(client);
+	if (rc)
+		return rc;
+
 	/*
 	 * Writes to VOUT setpoint over AVSBus will persist after the VRM is
 	 * switched to PMBus control. Switching back to AVSBus control
···
 		rc = pmbus_read_word_data(client, page, 0xff,
 					  PMBUS_VOUT_COMMAND);
 		if (rc < 0)
-			return rc;
+			goto unlock;
 
 		rc = pmbus_write_word_data(client, page, PMBUS_VOUT_COMMAND,
 					   rc);
 		if (rc < 0)
-			return rc;
+			goto unlock;
 	}
 
 	rc = pmbus_update_byte_data(client, page, PMBUS_OPERATION,
 				    ISL68137_VOUT_AVS, op_val);
+
+unlock:
+	pmbus_unlock(client);
 
 	return (rc < 0) ? rc : count;
 }

drivers/hwmon/pmbus/pmbus_core.c

···
  * Copyright (c) 2012 Guenter Roeck
  */
 
+#include <linux/atomic.h>
 #include <linux/debugfs.h>
 #include <linux/delay.h>
 #include <linux/dcache.h>
···
 #include <linux/pmbus.h>
 #include <linux/regulator/driver.h>
 #include <linux/regulator/machine.h>
-#include <linux/of.h>
 #include <linux/thermal.h>
+#include <linux/workqueue.h>
 #include "pmbus.h"
 
 /*
···
 	struct pmbus_sensor *sensors;
 
 	struct mutex update_lock;
+
+#if IS_ENABLED(CONFIG_REGULATOR)
+	atomic_t regulator_events[PMBUS_PAGES];
+	struct work_struct regulator_notify_work;
+#endif
 
 	bool has_status_word;		/* device uses STATUS_WORD register */
 	int (*read_status)(struct i2c_client *client, int page);
···
 	return sysfs_emit(buf, "%d\n", val);
 }
 
+static ssize_t pmbus_show_zero(struct device *dev,
+			       struct device_attribute *devattr, char *buf)
+{
+	return sysfs_emit(buf, "0\n");
+}
+
 static ssize_t pmbus_show_sensor(struct device *dev,
 				 struct device_attribute *devattr, char *buf)
 {
···
 					     int reg,
 					     enum pmbus_sensor_classes class,
 					     bool update, bool readonly,
-					     bool convert)
+					     bool writeonly, bool convert)
 {
 	struct pmbus_sensor *sensor;
 	struct device_attribute *a;
···
 	sensor->data = -ENODATA;
 	pmbus_dev_attr_init(a, sensor->name,
 			    readonly ? 0444 : 0644,
-			    pmbus_show_sensor, pmbus_set_sensor);
+			    writeonly ? pmbus_show_zero : pmbus_show_sensor,
+			    pmbus_set_sensor);
 
 	if (pmbus_add_attribute(data, &a->attr))
 		return NULL;
···
 struct pmbus_limit_attr {
 	u16 reg;		/* Limit register */
 	u16 sbit;		/* Alarm attribute status bit */
-	bool update;		/* True if register needs updates */
-	bool low;		/* True if low limit; for limits with compare functions only */
+	bool readonly:1;	/* True if the attribute is read-only */
+	bool writeonly:1;	/* True if the attribute is write-only */
+	bool update:1;		/* True if register needs updates */
+	bool low:1;		/* True if low limit; for limits with compare functions only */
 	const char *attr;	/* Attribute name */
 	const char *alarm;	/* Alarm attribute name */
 };
···
 	u8 nlimit;			/* # of limit registers */
 	enum pmbus_sensor_classes class;/* sensor class */
 	const char *label;		/* sensor label */
-	bool paged;			/* true if paged sensor */
-	bool update;			/* true if update needed */
-	bool compare;			/* true if compare function needed */
+	bool paged:1;			/* true if paged sensor */
+	bool update:1;			/* true if update needed */
+	bool compare:1;			/* true if compare function needed */
 	u32 func;			/* sensor mask */
 	u32 sfunc;			/* sensor status mask */
 	int sreg;			/* status register */
···
 			curr = pmbus_add_sensor(data, name, l->attr, index,
 						page, 0xff, l->reg, attr->class,
 						attr->update || l->update,
-						false, true);
+						l->readonly, l->writeonly, true);
 			if (!curr)
 				return -ENOMEM;
 			if (l->sbit && (info->func[page] & attr->sfunc)) {
···
 			return ret;
 	}
 	base = pmbus_add_sensor(data, name, "input", index, page, phase,
-				attr->reg, attr->class, true, true, true);
+				attr->reg, attr->class, true, true, false, true);
 	if (!base)
 		return -ENOMEM;
 	/* No limit and alarm attributes for phase specific sensors */
···
 	}, {
 		.reg = PMBUS_VIRT_READ_VIN_AVG,
 		.update = true,
+		.readonly = true,
 		.attr = "average",
 	}, {
 		.reg = PMBUS_VIRT_READ_VIN_MIN,
 		.update = true,
+		.readonly = true,
 		.attr = "lowest",
 	}, {
 		.reg = PMBUS_VIRT_READ_VIN_MAX,
 		.update = true,
+		.readonly = true,
 		.attr = "highest",
 	}, {
 		.reg = PMBUS_VIRT_RESET_VIN_HISTORY,
+		.writeonly = true,
 		.attr = "reset_history",
 	}, {
 		.reg = PMBUS_MFR_VIN_MIN,
+		.readonly = true,
 		.attr = "rated_min",
 	}, {
 		.reg = PMBUS_MFR_VIN_MAX,
+		.readonly = true,
 		.attr = "rated_max",
 	},
 };
···
 	}, {
 		.reg = PMBUS_VIRT_READ_VOUT_AVG,
 		.update = true,
+		.readonly = true,
 		.attr = "average",
 	}, {
 		.reg = PMBUS_VIRT_READ_VOUT_MIN,
 		.update = true,
+		.readonly = true,
 		.attr = "lowest",
 	}, {
 		.reg = PMBUS_VIRT_READ_VOUT_MAX,
 		.update = true,
+		.readonly = true,
 		.attr = "highest",
 	}, {
 		.reg = PMBUS_VIRT_RESET_VOUT_HISTORY,
+		.writeonly = true,
 		.attr = "reset_history",
 	}, {
 		.reg = PMBUS_MFR_VOUT_MIN,
+		.readonly = true,
 		.attr = "rated_min",
 	}, {
 		.reg = PMBUS_MFR_VOUT_MAX,
+		.readonly = true,
 		.attr = "rated_max",
 	},
 };
···
 	}, {
 		.reg = PMBUS_VIRT_READ_IIN_AVG,
 		.update = true,
+		.readonly = true,
 		.attr = "average",
 	}, {
 		.reg = PMBUS_VIRT_READ_IIN_MIN,
 		.update = true,
+		.readonly = true,
 		.attr = "lowest",
 	}, {
 		.reg = PMBUS_VIRT_READ_IIN_MAX,
 		.update = true,
+		.readonly = true,
 		.attr = "highest",
 	}, {
 		.reg = PMBUS_VIRT_RESET_IIN_HISTORY,
+		.writeonly = true,
 		.attr = "reset_history",
 	}, {
 		.reg = PMBUS_MFR_IIN_MAX,
+		.readonly = true,
 		.attr = "rated_max",
 	},
 };
···
 	}, {
 		.reg = PMBUS_VIRT_READ_IOUT_AVG,
 		.update = true,
+		.readonly = true,
 		.attr = "average",
 	}, {
 		.reg = PMBUS_VIRT_READ_IOUT_MIN,
 		.update = true,
+		.readonly = true,
 		.attr = "lowest",
 	}, {
 		.reg = PMBUS_VIRT_READ_IOUT_MAX,
 		.update = true,
+		.readonly = true,
 		.attr = "highest",
 	}, {
 		.reg = PMBUS_VIRT_RESET_IOUT_HISTORY,
+		.writeonly = true,
 		.attr = "reset_history",
 	}, {
 		.reg = PMBUS_MFR_IOUT_MAX,
+		.readonly = true,
 		.attr = "rated_max",
 	},
 };
···
 	}, {
 		.reg = PMBUS_VIRT_READ_PIN_AVG,
 		.update = true,
+		.readonly = true,
 		.attr = "average",
 	}, {
 		.reg = PMBUS_VIRT_READ_PIN_MIN,
 		.update = true,
+		.readonly = true,
 		.attr = "input_lowest",
 	}, {
 		.reg = PMBUS_VIRT_READ_PIN_MAX,
 		.update = true,
+		.readonly = true,
 		.attr = "input_highest",
 	}, {
 		.reg = PMBUS_VIRT_RESET_PIN_HISTORY,
+		.writeonly = true,
 		.attr = "reset_history",
 	}, {
 		.reg = PMBUS_MFR_PIN_MAX,
+		.readonly = true,
 		.attr = "rated_max",
 	},
 };
···
 	}, {
 		.reg = PMBUS_VIRT_READ_POUT_AVG,
 		.update = true,
+		.readonly = true,
 		.attr = "average",
 	}, {
 		.reg = PMBUS_VIRT_READ_POUT_MIN,
 		.update = true,
+		.readonly = true,
 		.attr = "input_lowest",
 	}, {
 		.reg = PMBUS_VIRT_READ_POUT_MAX,
 		.update = true,
+		.readonly = true,
 		.attr = "input_highest",
 	}, {
 		.reg = PMBUS_VIRT_RESET_POUT_HISTORY,
+		.writeonly = true,
 		.attr = "reset_history",
 	}, {
 		.reg = PMBUS_MFR_POUT_MAX,
+		.readonly = true,
 		.attr = "rated_max",
 	},
 };
···
 		.sbit = PB_TEMP_OT_FAULT,
 	}, {
 		.reg = PMBUS_VIRT_READ_TEMP_MIN,
+		.readonly = true,
 		.attr = "lowest",
 	}, {
 		.reg = PMBUS_VIRT_READ_TEMP_AVG,
+		.readonly = true,
 		.attr = "average",
 	}, {
 		.reg = PMBUS_VIRT_READ_TEMP_MAX,
+		.readonly = true,
 		.attr = "highest",
 	}, {
 		.reg = PMBUS_VIRT_RESET_TEMP_HISTORY,
+		.writeonly = true,
 		.attr = "reset_history",
 	}, {
 		.reg = PMBUS_MFR_MAX_TEMP_1,
+		.readonly = true,
 		.attr = "rated_max",
 	},
 };
···
 		.sbit = PB_TEMP_OT_FAULT,
 	}, {
 		.reg = PMBUS_VIRT_READ_TEMP2_MIN,
+		.readonly = true,
 		.attr = "lowest",
 	}, {
 		.reg = PMBUS_VIRT_READ_TEMP2_AVG,
+		.readonly = true,
 		.attr = "average",
 	}, {
 		.reg = PMBUS_VIRT_READ_TEMP2_MAX,
+		.readonly = true,
 		.attr = "highest",
 	}, {
 		.reg = PMBUS_VIRT_RESET_TEMP2_HISTORY,
+		.writeonly = true,
 		.attr = "reset_history",
 	}, {
 		.reg = PMBUS_MFR_MAX_TEMP_2,
+		.readonly = true,
 		.attr = "rated_max",
 	},
 };
···
 		.sbit = PB_TEMP_OT_FAULT,
 	}, {
 		.reg = PMBUS_MFR_MAX_TEMP_3,
+		.readonly = true,
 		.attr = "rated_max",
 	},
 };
···
 
 	sensor = pmbus_add_sensor(data, "fan", "target", index, page,
 				  0xff, PMBUS_VIRT_FAN_TARGET_1 + id, PSC_FAN,
-				  false, false, true);
+				  false, false, false, true);
 
 	if (!sensor)
 		return -ENOMEM;
···
 
 	sensor = pmbus_add_sensor(data, "pwm", NULL, index, page,
 				  0xff, PMBUS_VIRT_PWM_1 + id, PSC_PWM,
-				  false, false, true);
+				  false, false, false, true);
 
 	if (!sensor)
 		return -ENOMEM;
 
 	sensor = pmbus_add_sensor(data, "pwm", "enable", index, page,
 				  0xff, PMBUS_VIRT_PWM_ENABLE_1 + id, PSC_PWM,
-				  true, false, false);
+				  true, false, false, false);
 
 	if (!sensor)
 		return -ENOMEM;
···
 
 			if (pmbus_add_sensor(data, "fan", "input", index,
 					     page, 0xff, pmbus_fan_registers[f],
-					     PSC_FAN, true, true, true) == NULL)
+					     PSC_FAN, true, true, false, true) == NULL)
 				return -ENOMEM;
 
 			/* Fan control */
···
 		.class = PSC_VOLTAGE_OUT,
 		.convert = true,
 	};
+	int ret;
 
+	mutex_lock(&data->update_lock);
 	s.data = _pmbus_read_word_data(client, s.page, 0xff, PMBUS_READ_VOUT);
-	if (s.data < 0)
-		return s.data;
+	if (s.data < 0) {
+		ret = s.data;
+		goto unlock;
+	}
 
-	return (int)pmbus_reg2data(data, &s) * 1000; /* unit is uV */
+	ret = (int)pmbus_reg2data(data, &s) * 1000; /* unit is uV */
+unlock:
+	mutex_unlock(&data->update_lock);
+	return ret;
 }
 
 static int pmbus_regulator_set_voltage(struct regulator_dev *rdev, int min_uv,
···
 	};
 	int val = DIV_ROUND_CLOSEST(min_uv, 1000); /* convert to mV */
 	int low, high;
+	int ret;
 
 	*selector = 0;
 
+	mutex_lock(&data->update_lock);
 	low = pmbus_regulator_get_low_margin(client, s.page);
-	if (low < 0)
-		return low;
+	if (low < 0) {
+		ret = low;
+		goto unlock;
+	}
 
 	high = pmbus_regulator_get_high_margin(client, s.page);
-	if (high < 0)
-		return high;
+	if (high < 0) {
+		ret = high;
+		goto unlock;
+	}
 
 	/* Make sure we are within margins */
 	if (low > val)
···
 
 	val = pmbus_data2reg(data, &s, val);
 
-	return _pmbus_write_word_data(client, s.page, PMBUS_VOUT_COMMAND, (u16)val);
+	ret = _pmbus_write_word_data(client, s.page, PMBUS_VOUT_COMMAND, (u16)val);
+unlock:
+	mutex_unlock(&data->update_lock);
+	return ret;
 }
 
 static int pmbus_regulator_list_voltage(struct regulator_dev *rdev,
···
 	struct i2c_client *client = to_i2c_client(dev->parent);
 	struct pmbus_data *data = i2c_get_clientdata(client);
 	int val, low, high;
+	int ret;
 
 	if (data->flags & PMBUS_VOUT_PROTECTED)
 		return 0;
···
 	val = DIV_ROUND_CLOSEST(rdev->desc->min_uV +
 				(rdev->desc->uV_step * selector), 1000); /* convert to mV */
 
+	mutex_lock(&data->update_lock);
+
 	low = pmbus_regulator_get_low_margin(client, rdev_get_id(rdev));
-	if (low < 0)
-		return low;
+	if (low < 0) {
+		ret = low;
+		goto unlock;
+	}
 
 	high = pmbus_regulator_get_high_margin(client, rdev_get_id(rdev));
-	if (high < 0)
-		return high;
+	if (high < 0) {
+		ret = high;
+		goto unlock;
+	}
 
-	if (val >= low && val <= high)
-		return val * 1000; /* unit is uV */
+	if (val >= low && val <= high) {
+		ret = val * 1000; /* unit is uV */
+		goto unlock;
+	}
 
-	return 0;
+	ret = 0;
+unlock:
+	mutex_unlock(&data->update_lock);
+	return ret;
 }
 
 const struct regulator_ops pmbus_regulator_ops = {
···
 }
 EXPORT_SYMBOL_NS_GPL(pmbus_regulator_init_cb, "PMBUS");
 
+static void pmbus_regulator_notify_work_cancel(void *data)
+{
+	struct pmbus_data *pdata = data;
+
+	cancel_work_sync(&pdata->regulator_notify_work);
+}
+
+static void pmbus_regulator_notify_worker(struct work_struct *work)
+{
+	struct pmbus_data *data =
+		container_of(work, struct pmbus_data, regulator_notify_work);
+	int i, j;
+
+	for (i = 0; i < data->info->pages; i++) {
+		int event;
+
+		event = atomic_xchg(&data->regulator_events[i], 0);
+		if (!event)
+			continue;
+
+		for (j = 0; j < data->info->num_regulators; j++) {
+			if (i == rdev_get_id(data->rdevs[j])) {
+				regulator_notifier_call_chain(data->rdevs[j],
+							      event, NULL);
+				break;
+			}
+		}
+	}
+}
+
 static int pmbus_regulator_register(struct pmbus_data *data)
 {
 	struct device *dev = data->dev;
 	const struct pmbus_driver_info *info = data->info;
 	const struct pmbus_platform_data *pdata = dev_get_platdata(dev);
-	int i;
+	int i, ret;
 
 	data->rdevs = devm_kzalloc(dev, sizeof(struct regulator_dev *) * info->num_regulators,
 				   GFP_KERNEL);
···
 					     info->reg_desc[i].name);
 	}
 
+	INIT_WORK(&data->regulator_notify_work, pmbus_regulator_notify_worker);
+
+	ret = devm_add_action_or_reset(dev, pmbus_regulator_notify_work_cancel, data);
+	if (ret)
+		return ret;
+
 	return 0;
 }
 
 static void pmbus_regulator_notify(struct pmbus_data *data, int page, int event)
 {
-	int j;
-
-	for (j = 0; j < data->info->num_regulators; j++) {
-		if (page == rdev_get_id(data->rdevs[j])) {
-			regulator_notifier_call_chain(data->rdevs[j], event, NULL);
-			break;
-		}
-	}
+	atomic_or(event, &data->regulator_events[page]);
+	schedule_work(&data->regulator_notify_work);
 }
 #else
 static int pmbus_regulator_register(struct pmbus_data *data)

drivers/i2c/busses/i2c-designware-amdisp.c

···
 
 #include <linux/module.h>
 #include <linux/platform_device.h>
+#include <linux/pm_domain.h>
 #include <linux/pm_runtime.h>
 #include <linux/soc/amd/isp4_misc.h>
 
···
 
 	device_enable_async_suspend(&pdev->dev);
 
-	pm_runtime_enable(&pdev->dev);
-	pm_runtime_get_sync(&pdev->dev);
-
+	dev_pm_genpd_resume(&pdev->dev);
 	ret = i2c_dw_probe(isp_i2c_dev);
 	if (ret) {
 		dev_err_probe(&pdev->dev, ret, "i2c_dw_probe failed\n");
 		goto error_release_rpm;
 	}
-
-	pm_runtime_put_sync(&pdev->dev);
+	dev_pm_genpd_suspend(&pdev->dev);
+	pm_runtime_set_suspended(&pdev->dev);
+	pm_runtime_enable(&pdev->dev);
 
 	return 0;
 
 error_release_rpm:
 	amd_isp_dw_i2c_plat_pm_cleanup(isp_i2c_dev);
-	pm_runtime_put_sync(&pdev->dev);
 	return ret;
 }
 

drivers/i2c/busses/i2c-imx.c

···
 	return 0;
 }
 
-static inline void i2c_imx_isr_read_continue(struct imx_i2c_struct *i2c_imx)
+static inline enum imx_i2c_state i2c_imx_isr_read_continue(struct imx_i2c_struct *i2c_imx)
 {
+	enum imx_i2c_state next_state = IMX_I2C_STATE_READ_CONTINUE;
 	unsigned int temp;
 
 	if ((i2c_imx->msg->len - 1) == i2c_imx->msg_buf_idx) {
···
 				i2c_imx->stopped =  1;
 			temp &= ~(I2CR_MSTA | I2CR_MTX);
 			imx_i2c_write_reg(temp, i2c_imx, IMX_I2C_I2CR);
-		} else {
-			/*
-			 * For i2c master receiver repeat restart operation like:
-			 * read -> repeat MSTA -> read/write
-			 * The controller must set MTX before read the last byte in
-			 * the first read operation, otherwise the first read cost
-			 * one extra clock cycle.
-			 */
-			temp = imx_i2c_read_reg(i2c_imx, IMX_I2C_I2CR);
-			temp |= I2CR_MTX;
-			imx_i2c_write_reg(temp, i2c_imx, IMX_I2C_I2CR);
+
+			return IMX_I2C_STATE_DONE;
 		}
+		/*
+		 * For i2c master receiver repeat restart operation like:
+		 * read -> repeat MSTA -> read/write
+		 * The controller must set MTX before read the last byte in
+		 * the first read operation, otherwise the first read cost
+		 * one extra clock cycle.
+		 */
+		temp = imx_i2c_read_reg(i2c_imx, IMX_I2C_I2CR);
+		temp |= I2CR_MTX;
+		imx_i2c_write_reg(temp, i2c_imx, IMX_I2C_I2CR);
+		next_state = IMX_I2C_STATE_DONE;
 	} else if (i2c_imx->msg_buf_idx == (i2c_imx->msg->len - 2)) {
 		temp = imx_i2c_read_reg(i2c_imx, IMX_I2C_I2CR);
 		temp |= I2CR_TXAK;
···
 	}
 
 	i2c_imx->msg->buf[i2c_imx->msg_buf_idx++] = imx_i2c_read_reg(i2c_imx, IMX_I2C_I2DR);
+	return next_state;
 }
 
 static inline void i2c_imx_isr_read_block_data_len(struct imx_i2c_struct *i2c_imx)
···
 		break;
 
 	case IMX_I2C_STATE_READ_CONTINUE:
-		i2c_imx_isr_read_continue(i2c_imx);
-		if (i2c_imx->msg_buf_idx == i2c_imx->msg->len) {
-			i2c_imx->state = IMX_I2C_STATE_DONE;
+		i2c_imx->state = i2c_imx_isr_read_continue(i2c_imx);
+		if (i2c_imx->state == IMX_I2C_STATE_DONE)
 			wake_up(&i2c_imx->queue);
-		}
 		break;
 
 	case IMX_I2C_STATE_READ_BLOCK_DATA:
···
 			bool is_lastmsg)
 {
 	int block_data = msgs->flags & I2C_M_RECV_LEN;
+	int ret = 0;
 
 	dev_dbg(&i2c_imx->adapter.dev,
 		"<%s> write slave address: addr=0x%x\n",
···
 		dev_err(&i2c_imx->adapter.dev, "<%s> read timedout\n", __func__);
 		return -ETIMEDOUT;
 	}
-	if (!i2c_imx->stopped)
-		return i2c_imx_bus_busy(i2c_imx, 0, false);
+	if (i2c_imx->is_lastmsg) {
+		if (!i2c_imx->stopped)
+			ret = i2c_imx_bus_busy(i2c_imx, 0, false);
+		/*
+		 * Only read the last byte of the last message after the bus is
+		 * not busy. Else the controller generates another clock which
+		 * might confuse devices.
+		 */
+		if (!ret)
+			i2c_imx->msg->buf[i2c_imx->msg_buf_idx++] = imx_i2c_read_reg(i2c_imx,
+										     IMX_I2C_I2DR);
+	}
 
-	return 0;
+	return ret;
 }
 
 static int i2c_imx_xfer_common(struct i2c_adapter *adapter,

drivers/infiniband/core/rw.c

···
 	if (rdma_rw_io_needs_mr(qp->device, port_num, dir, sg_cnt)) {
 		ret = rdma_rw_init_mr_wrs(ctx, qp, port_num, sg, sg_cnt,
 				sg_offset, remote_addr, rkey, dir);
-	} else if (sg_cnt > 1) {
-		ret = rdma_rw_init_map_wrs(ctx, qp, sg, sg_cnt, sg_offset,
-				remote_addr, rkey, dir);
-	} else {
-		ret = rdma_rw_init_single_wr(ctx, qp, sg, sg_offset,
-				remote_addr, rkey, dir);
+		/*
+		 * If MR init succeeded or failed for a reason other
+		 * than pool exhaustion, that result is final.
+		 *
+		 * Pool exhaustion (-EAGAIN) from the max_sgl_rd
+		 * optimization is recoverable: fall back to
+		 * direct SGE posting. iWARP and force_mr require
+		 * MRs unconditionally, so -EAGAIN is terminal.
+		 */
+		if (ret != -EAGAIN ||
+		    rdma_protocol_iwarp(qp->device, port_num) ||
+		    unlikely(rdma_rw_force_mr))
+			goto out;
 	}
 
+	if (sg_cnt > 1)
+		ret = rdma_rw_init_map_wrs(ctx, qp, sg, sg_cnt, sg_offset,
+				remote_addr, rkey, dir);
+	else
+		ret = rdma_rw_init_single_wr(ctx, qp, sg, sg_offset,
+				remote_addr, rkey, dir);
+
+out:
 	if (ret < 0)
 		goto out_unmap_sg;
 	return ret;
···
 		return ret;
 
 	/*
-	 * IOVA mapping not available. Check if MR registration provides
-	 * better performance than multiple SGE entries.
+	 * IOVA not available; fall back to the map_wrs path, which maps
+	 * each bvec as a direct SGE. This is always correct: the MR path
+	 * is a throughput optimization, not a correctness requirement.
+	 * (iWARP, which does require MRs, is handled by the check above.)
+	 *
+	 * The rdma_rw_io_needs_mr() gate is not used here because nr_bvec
+	 * is a raw page count that overstates DMA entry demand -- the bvec
+	 * caller has no post-DMA-coalescing segment count, and feeding the
+	 * inflated count into the MR path exhausts the pool on RDMA READs.
 	 */
-	if (rdma_rw_io_needs_mr(dev, port_num, dir, nr_bvec))
-		return rdma_rw_init_mr_wrs_bvec(ctx, qp, port_num, bvecs,
-						nr_bvec, &iter, remote_addr,
-						rkey, dir);
-
 	return rdma_rw_init_map_wrs_bvec(ctx, qp, bvecs, nr_bvec, &iter,
 			remote_addr, rkey, dir);
 }

drivers/infiniband/hw/bng_re/bng_dev.c

···
 	return rc;
 }
 
-static void bng_re_query_hwrm_version(struct bng_re_dev *rdev)
+static int bng_re_query_hwrm_version(struct bng_re_dev *rdev)
 {
 	struct bnge_auxr_dev *aux_dev = rdev->aux_dev;
 	struct hwrm_ver_get_output ver_get_resp = {};
···
 	if (rc) {
 		ibdev_err(&rdev->ibdev, "Failed to query HW version, rc = 0x%x",
 			  rc);
-		return;
+		return rc;
 	}
 
 	cctx = rdev->chip_ctx;
···
 
 	if (!cctx->hwrm_cmd_max_timeout)
 		cctx->hwrm_cmd_max_timeout = BNG_ROCE_FW_MAX_TIMEOUT;
+
+	return 0;
 }
 
 static void bng_re_dev_uninit(struct bng_re_dev *rdev)
···
 		goto msix_ctx_fail;
 	}
 
-	bng_re_query_hwrm_version(rdev);
+	rc = bng_re_query_hwrm_version(rdev);
+	if (rc)
+		goto destroy_chip_ctx;
 
 	rc = bng_re_alloc_fw_channel(&rdev->bng_res, &rdev->rcfw);
 	if (rc) {
 		ibdev_err(&rdev->ibdev,
 			  "Failed to allocate RCFW Channel: %#x\n", rc);
-		goto alloc_fw_chl_fail;
+		goto destroy_chip_ctx;
 	}
 
 	/* Allocate nq record memory */
···
 	kfree(rdev->nqr);
 nq_alloc_fail:
 	bng_re_free_rcfw_channel(&rdev->rcfw);
-alloc_fw_chl_fail:
+destroy_chip_ctx:
 	bng_re_destroy_chip_ctx(rdev);
 msix_ctx_fail:
 	bnge_unregister_dev(rdev->aux_dev);

drivers/infiniband/hw/efa/efa_com.c

···
 // SPDX-License-Identifier: GPL-2.0 OR BSD-2-Clause
 /*
- * Copyright 2018-2025 Amazon.com, Inc. or its affiliates. All rights reserved.
+ * Copyright 2018-2026 Amazon.com, Inc. or its affiliates. All rights reserved.
  */
 
 #include <linux/log2.h>
···
 	return &aq->comp_ctx[ctx_id];
 }
 
-static struct efa_comp_ctx *__efa_com_submit_admin_cmd(struct efa_com_admin_queue *aq,
-						       struct efa_admin_aq_entry *cmd,
-						       size_t cmd_size_in_bytes,
-						       struct efa_admin_acq_entry *comp,
-						       size_t comp_size_in_bytes)
+static void __efa_com_submit_admin_cmd(struct efa_com_admin_queue *aq,
+				       struct efa_comp_ctx *comp_ctx,
+				       struct efa_admin_aq_entry *cmd,
+				       size_t cmd_size_in_bytes,
+				       struct efa_admin_acq_entry *comp,
+				       size_t comp_size_in_bytes)
 {
 	struct efa_admin_aq_entry *aqe;
-	struct efa_comp_ctx *comp_ctx;
 	u16 queue_size_mask;
 	u16 cmd_id;
 	u16 ctx_id;
 	u16 pi;
-
-	comp_ctx = efa_com_alloc_comp_ctx(aq);
-	if (!comp_ctx)
-		return ERR_PTR(-EINVAL);
 
 	queue_size_mask = aq->depth - 1;
 	pi = aq->sq.pc & queue_size_mask;
···
 
 	/* barrier not needed in case of writel */
 	writel(aq->sq.pc, aq->sq.db_addr);
-
-	return comp_ctx;
 }
 
 static inline int efa_com_init_comp_ctxt(struct efa_com_admin_queue *aq)
···
 	return 0;
 }
 
-static struct efa_comp_ctx *efa_com_submit_admin_cmd(struct efa_com_admin_queue *aq,
-						     struct efa_admin_aq_entry *cmd,
-						     size_t cmd_size_in_bytes,
-						     struct efa_admin_acq_entry *comp,
-						     size_t comp_size_in_bytes)
+static int efa_com_submit_admin_cmd(struct efa_com_admin_queue *aq,
+				    struct efa_comp_ctx *comp_ctx,
+				    struct efa_admin_aq_entry *cmd,
+				    size_t cmd_size_in_bytes,
+				    struct efa_admin_acq_entry *comp,
+				    size_t comp_size_in_bytes)
 {
-	struct efa_comp_ctx *comp_ctx;
-
 	spin_lock(&aq->sq.lock);
 	if (!test_bit(EFA_AQ_STATE_RUNNING_BIT, &aq->state)) {
 		ibdev_err_ratelimited(aq->efa_dev, "Admin queue is closed\n");
 		spin_unlock(&aq->sq.lock);
-		return ERR_PTR(-ENODEV);
+		return -ENODEV;
 	}
 
-	comp_ctx = __efa_com_submit_admin_cmd(aq, cmd, cmd_size_in_bytes, comp,
-					      comp_size_in_bytes);
+	__efa_com_submit_admin_cmd(aq, comp_ctx, cmd, cmd_size_in_bytes, comp,
+				   comp_size_in_bytes);
 	spin_unlock(&aq->sq.lock);
-	if (IS_ERR(comp_ctx))
-		clear_bit(EFA_AQ_STATE_RUNNING_BIT, &aq->state);
 
-	return comp_ctx;
+	return 0;
 }
 
 static int efa_com_handle_single_admin_completion(struct efa_com_admin_queue *aq,
···
 {
 	unsigned long timeout;
 	unsigned long flags;
-	int err;
 
 	timeout = jiffies + usecs_to_jiffies(aq->completion_timeout);
 
···
 			atomic64_inc(&aq->stats.no_completion);
 
 			clear_bit(EFA_AQ_STATE_RUNNING_BIT, &aq->state);
-			err = -ETIME;
-			goto out;
+			return -ETIME;
 		}
 
 		msleep(aq->poll_interval);
 	}
 
-	err = efa_com_comp_status_to_errno(comp_ctx->user_cqe->acq_common_descriptor.status);
-out:
-	efa_com_dealloc_comp_ctx(aq, comp_ctx);
-	return err;
+	return efa_com_comp_status_to_errno(
+		comp_ctx->user_cqe->acq_common_descriptor.status);
 }
 
 static int efa_com_wait_and_process_admin_cq_interrupts(struct efa_comp_ctx *comp_ctx,
 							struct efa_com_admin_queue *aq)
 {
 	unsigned long flags;
-	int err;
 
 	wait_for_completion_timeout(&comp_ctx->wait_event,
 				    usecs_to_jiffies(aq->completion_timeout));
···
 				aq->cq.cc);
 
 		clear_bit(EFA_AQ_STATE_RUNNING_BIT, &aq->state);
-		err = -ETIME;
-		goto out;
+		return -ETIME;
 	}
 
-	err = efa_com_comp_status_to_errno(comp_ctx->user_cqe->acq_common_descriptor.status);
-out:
-	efa_com_dealloc_comp_ctx(aq, comp_ctx);
-	return err;
+	return efa_com_comp_status_to_errno(
+		comp_ctx->user_cqe->acq_common_descriptor.status);
 }
 
 /*
···
 	ibdev_dbg(aq->efa_dev, "%s (opcode %d)\n",
 		  efa_com_cmd_str(cmd->aq_common_descriptor.opcode),
 		  cmd->aq_common_descriptor.opcode);
-	comp_ctx = efa_com_submit_admin_cmd(aq, cmd, cmd_size, comp, comp_size);
-	if (IS_ERR(comp_ctx)) {
+
+	comp_ctx = efa_com_alloc_comp_ctx(aq);
+	if (!comp_ctx) {
+		clear_bit(EFA_AQ_STATE_RUNNING_BIT, &aq->state);
+		up(&aq->avail_cmds);
+		return -EINVAL;
+	}
+
+	err = efa_com_submit_admin_cmd(aq, comp_ctx, cmd, cmd_size, comp, comp_size);
+	if (err) {
 		ibdev_err_ratelimited(
 			aq->efa_dev,
-			"Failed to submit command %s (opcode %u) err %pe\n",
+			"Failed to submit command %s (opcode %u) err %d\n",
 			efa_com_cmd_str(cmd->aq_common_descriptor.opcode),
-			cmd->aq_common_descriptor.opcode, comp_ctx);
+			cmd->aq_common_descriptor.opcode, err);
 
+		efa_com_dealloc_comp_ctx(aq, comp_ctx);
 		up(&aq->avail_cmds);
 		atomic64_inc(&aq->stats.cmd_err);
-		return PTR_ERR(comp_ctx);
+		return err;
 	}
 
 	err = efa_com_wait_and_process_admin_cq(comp_ctx, aq);
 	if (err) {
 		ibdev_err_ratelimited(
 			aq->efa_dev,
-			"Failed to process command %s (opcode %u) comp_status %d err %d\n",
+			"Failed to process command %s (opcode %u) err %d\n",
 			efa_com_cmd_str(cmd->aq_common_descriptor.opcode),
-			cmd->aq_common_descriptor.opcode,
-			comp_ctx->user_cqe->acq_common_descriptor.status, err);
+			cmd->aq_common_descriptor.opcode, err);
 		atomic64_inc(&aq->stats.cmd_err);
 	}
 
+	efa_com_dealloc_comp_ctx(aq, comp_ctx);
 	up(&aq->avail_cmds);
 
 	return err;

drivers/infiniband/hw/ionic/ionic_controlpath.c

···
 {
 	const struct ib_global_route *grh;
 	enum rdma_network_type net;
+	u8 smac[ETH_ALEN];
 	u16 vlan;
 	int rc;
 
···
 
 	grh = rdma_ah_read_grh(attr);
 
-	rc = rdma_read_gid_l2_fields(grh->sgid_attr, &vlan, &hdr->eth.smac_h[0]);
+	rc = rdma_read_gid_l2_fields(grh->sgid_attr, &vlan, smac);
 	if (rc)
 		return rc;
 
···
 	if (rc)
 		return rc;
 
+	ether_addr_copy(hdr->eth.smac_h, smac);
 	ether_addr_copy(hdr->eth.dmac_h, attr->roce.dmac);
 
 	if (net == RDMA_NETWORK_IPV4) {

drivers/infiniband/hw/irdma/cm.c

···
 	int oldarpindex;
 	int arpindex;
 	struct net_device *netdev = iwdev->netdev;
+	int ret;
 
 	/* create an hte and cm_node for this instance */
 	cm_node = kzalloc_obj(*cm_node, GFP_ATOMIC);
 	if (!cm_node)
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 
 	/* set our node specific transport info */
 	cm_node->ipv4 = cm_info->ipv4;
···
 			arpindex = -EINVAL;
 	}
 
-	if (arpindex < 0)
+	if (arpindex < 0) {
+		ret = -EINVAL;
 		goto err;
+	}
 
 	ether_addr_copy(cm_node->rem_mac,
 			iwdev->rf->arp_table[arpindex].mac_addr);
···
 err:
 	kfree(cm_node);
 
-	return NULL;
+	return ERR_PTR(ret);
 }
 
 static void irdma_destroy_connection(struct irdma_cm_node *cm_node)
···
 
 	/* create a CM connection node */
 	cm_node = irdma_make_cm_node(cm_core, iwdev, cm_info, NULL);
-	if (!cm_node)
-		return -ENOMEM;
+	if (IS_ERR(cm_node))
+		return PTR_ERR(cm_node);
 
 	/* set our node side to client (active) side */
 	cm_node->tcp_cntxt.client = 1;
···
 		cm_info.cm_id = listener->cm_id;
 		cm_node = irdma_make_cm_node(cm_core, iwdev, &cm_info,
 					     listener);
-		if (!cm_node) {
+		if (IS_ERR(cm_node)) {
 			ibdev_dbg(&cm_core->iwdev->ibdev,
-				  "CM: allocate node failed\n");
+				  "CM: allocate node failed ret=%ld\n", PTR_ERR(cm_node));
 			refcount_dec(&listener->refcnt);
 			return;
 		}
···
 		irdma_cm_event_reset(event);
 		break;
 	case IRDMA_CM_EVENT_CONNECTED:
-		if (!event->cm_node->cm_id ||
-		    event->cm_node->state != IRDMA_CM_STATE_OFFLOADED)
+		if (!cm_node->cm_id ||
+		    cm_node->state != IRDMA_CM_STATE_OFFLOADED)
 			break;
 		irdma_cm_event_connected(event);
 		break;
 	case IRDMA_CM_EVENT_MPA_REJECT:
-		if (!event->cm_node->cm_id ||
+		if (!cm_node->cm_id ||
 		    cm_node->state == IRDMA_CM_STATE_OFFLOADED)
 			break;
 		irdma_send_cm_event(cm_node, cm_node->cm_id,
 				    IW_CM_EVENT_CONNECT_REPLY, -ECONNREFUSED);
 		break;
 	case IRDMA_CM_EVENT_ABORTED:
-		if (!event->cm_node->cm_id ||
-		    event->cm_node->state == IRDMA_CM_STATE_OFFLOADED)
+		if (!cm_node->cm_id ||
+		    cm_node->state == IRDMA_CM_STATE_OFFLOADED)
 			break;
 		irdma_event_connect_error(event);
 		break;
···
 		break;
 	}
 
-	irdma_rem_ref_cm_node(event->cm_node);
+	irdma_rem_ref_cm_node(cm_node);
 	kfree(event);
 }
 

drivers/infiniband/hw/irdma/uk.c

···
  * irdma_round_up_wq - return round up qp wq depth
  * @wqdepth: wq depth in quanta to round up
  */
-static int irdma_round_up_wq(u32 wqdepth)
+static u64 irdma_round_up_wq(u64 wqdepth)
 {
 	int scount = 1;
 
···
 int irdma_get_sqdepth(struct irdma_uk_attrs *uk_attrs, u32 sq_size, u8 shift,
 		      u32 *sqdepth)
 {
-	u32 min_size = (u32)uk_attrs->min_hw_wq_size << shift;
+	u32 min_hw_quanta = (u32)uk_attrs->min_hw_wq_size << shift;
+	u64 hw_quanta =
+		irdma_round_up_wq(((u64)sq_size << shift) + IRDMA_SQ_RSVD);
 
-	*sqdepth = irdma_round_up_wq((sq_size << shift) + IRDMA_SQ_RSVD);
-
-	if (*sqdepth < min_size)
-		*sqdepth = min_size;
-	else if (*sqdepth > uk_attrs->max_hw_wq_quanta)
+	if (hw_quanta < min_hw_quanta)
+		hw_quanta = min_hw_quanta;
+	else if (hw_quanta > uk_attrs->max_hw_wq_quanta)
 		return -EINVAL;
 
+	*sqdepth = hw_quanta;
 	return 0;
 }
 
···
 int irdma_get_rqdepth(struct irdma_uk_attrs *uk_attrs, u32 rq_size, u8 shift,
 		      u32 *rqdepth)
 {
-	u32 min_size = (u32)uk_attrs->min_hw_wq_size << shift;
+	u32 min_hw_quanta = (u32)uk_attrs->min_hw_wq_size << shift;
+	u64 hw_quanta =
+		irdma_round_up_wq(((u64)rq_size << shift) + IRDMA_RQ_RSVD);
 
-	*rqdepth = irdma_round_up_wq((rq_size << shift) + IRDMA_RQ_RSVD);
-
-	if (*rqdepth < min_size)
-		*rqdepth = min_size;
-	else if (*rqdepth > uk_attrs->max_hw_rq_quanta)
+	if (hw_quanta < min_hw_quanta)
+		hw_quanta = min_hw_quanta;
+	else if (hw_quanta > uk_attrs->max_hw_rq_quanta)
 		return -EINVAL;
 
+	*rqdepth = hw_quanta;
 	return 0;
 }
 
···
 int irdma_get_srqdepth(struct irdma_uk_attrs *uk_attrs, u32 srq_size, u8 shift,
 		       u32 *srqdepth)
 {
-	*srqdepth = irdma_round_up_wq((srq_size << shift) + IRDMA_RQ_RSVD);
+	u32 min_hw_quanta = (u32)uk_attrs->min_hw_wq_size << shift;
+	u64 hw_quanta =
+		irdma_round_up_wq(((u64)srq_size << shift) + IRDMA_RQ_RSVD);
 
-	if (*srqdepth < ((u32)uk_attrs->min_hw_wq_size << shift))
-		*srqdepth = uk_attrs->min_hw_wq_size << shift;
-	else if (*srqdepth > uk_attrs->max_hw_srq_quanta)
+	if (hw_quanta < min_hw_quanta)
+		hw_quanta = min_hw_quanta;
+	else if (hw_quanta > uk_attrs->max_hw_srq_quanta)
 		return -EINVAL;
 
+	*srqdepth = hw_quanta;
 	return 0;
 }
 

drivers/infiniband/hw/irdma/utils.c

···
 	struct irdma_qp *qp = sc_qp->qp_uk.back_qp;
 	struct ib_qp_attr attr;
 
-	if (qp->iwdev->rf->reset)
-		return;
 	attr.qp_state = IB_QPS_ERR;
 
 	if (rdma_protocol_roce(qp->ibqp.device, 1))

drivers/infiniband/hw/irdma/verbs.c

···
 	}
 
 	irdma_qp_rem_ref(&iwqp->ibqp);
-	wait_for_completion(&iwqp->free_qp);
+	if (!iwdev->rf->reset)
+		wait_for_completion(&iwqp->free_qp);
 	irdma_free_lsmm_rsrc(iwqp);
 	irdma_cqp_qp_destroy_cmd(&iwdev->rf->sc_dev, &iwqp->sc_qp);
 
···
 	spin_lock_init(&iwqp->sc_qp.pfpdu.lock);
 	iwqp->sig_all = init_attr->sq_sig_type == IB_SIGNAL_ALL_WR;
 	rf->qp_table[qp_num] = iwqp;
+	init_completion(&iwqp->free_qp);
 
 	if (udata) {
 		/* GEN_1 legacy support with libi40iw does not have expanded uresp struct */
···
 		}
 	}
 
-	init_completion(&iwqp->free_qp);
 	return 0;
 
 error:
···
 				ctx_info->remote_atomics_en = true;
 	}
 
-	wait_event(iwqp->mod_qp_waitq, !atomic_read(&iwqp->hw_mod_qp_pend));
-
 	ibdev_dbg(&iwdev->ibdev,
 		  "VERBS: caller: %pS qp_id=%d to_ibqpstate=%d ibqpstate=%d irdma_qpstate=%d attr_mask=0x%x\n",
 		  __builtin_return_address(0), ibqp->qp_num, attr->qp_state,
···
 		case IB_QPS_ERR:
 		case IB_QPS_RESET:
 			if (iwqp->iwarp_state == IRDMA_QP_STATE_ERROR) {
+				iwqp->ibqp_state = attr->qp_state;
 				spin_unlock_irqrestore(&iwqp->lock, flags);
 				if (udata && udata->inlen) {
 					if (ib_copy_from_udata(&ureq, udata,
···
 		case IB_QPS_ERR:
 		case IB_QPS_RESET:
 			if (iwqp->iwarp_state == IRDMA_QP_STATE_ERROR) {
+				iwqp->ibqp_state = attr->qp_state;
 				spin_unlock_irqrestore(&iwqp->lock, flags);
 				if (udata && udata->inlen) {
 					if (ib_copy_from_udata(&ureq, udata,
···
 
 err:
 	ib_umem_release(region);
+	iwmr->region = NULL;
 	return err;
 }
 

drivers/iommu/generic_pt/fmt/amdv1.h

···
 }
 #define pt_load_entry_raw amdv1pt_load_entry_raw
 
-static inline void
+static __always_inline void
 amdv1pt_install_leaf_entry(struct pt_state *pts, pt_oaddr_t oa,
 			   unsigned int oasz_lg2,
 			   const struct pt_write_attrs *attrs)

drivers/iommu/generic_pt/iommu_pt.h

···
 
 	pt_walk_range(&range, __unmap_range, &unmap);
 
-	gather_range_pages(iotlb_gather, iommu_table, iova, len,
+	gather_range_pages(iotlb_gather, iommu_table, iova, unmap.unmapped,
 			   &unmap.free_list);
 
 	return unmap.unmapped;

drivers/irqchip/irq-qcom-mpm.c

···
 	if (ret < 0)
 		return ret;
 
+	mbox_client_txdone(priv->mbox_chan, 0);
+
 	return 0;
 }
 
···
 	}
 
 	priv->mbox_client.dev = dev;
+	priv->mbox_client.knows_txdone = true;
 	priv->mbox_chan = mbox_request_channel(&priv->mbox_client, 0);
 	if (IS_ERR(priv->mbox_chan)) {
 		ret = PTR_ERR(priv->mbox_chan);

drivers/irqchip/irq-renesas-rzv2h.c

···
 	return 0;
 
 pm_put:
-	pm_runtime_put(&pdev->dev);
+	pm_runtime_put_sync(&pdev->dev);
 
 	return ret;
 }

drivers/media/i2c/ccs/ccs-core.c

···
 	struct v4l2_rect *crop =
 		v4l2_subdev_state_get_crop(sd_state, pad);
 
-	guard(mutex)(&sensor->mutex);
-
 	ccs_get_native_size(ssd, crop);
 
 	fmt->width = crop->width;

drivers/media/usb/uvc/uvc_video.c

···
 /*
  * Free transfer buffers.
  */
-static void uvc_free_urb_buffers(struct uvc_streaming *stream)
+static void uvc_free_urb_buffers(struct uvc_streaming *stream,
+				 unsigned int size)
 {
 	struct usb_device *udev = stream->dev->udev;
 	struct uvc_urb *uvc_urb;
···
 		if (!uvc_urb->buffer)
 			continue;
 
-		usb_free_noncoherent(udev, stream->urb_size, uvc_urb->buffer,
+		usb_free_noncoherent(udev, size, uvc_urb->buffer,
 				     uvc_stream_dir(stream), uvc_urb->sgt);
 		uvc_urb->buffer = NULL;
 		uvc_urb->sgt = NULL;
···
 
 			if (!uvc_alloc_urb_buffer(stream, uvc_urb, urb_size,
 						  gfp_flags)) {
-				uvc_free_urb_buffers(stream);
+				uvc_free_urb_buffers(stream, urb_size);
 				break;
 			}
 
···
 	}
 
 	if (free_buffers)
-		uvc_free_urb_buffers(stream);
+		uvc_free_urb_buffers(stream, stream->urb_size);
 }
 
 /*

drivers/net/bonding/bond_main.c

···
 		if (!(bond_slave_is_up(slave) && slave->link == BOND_LINK_UP))
 			continue;
 
-		if (bond_is_last_slave(bond, slave)) {
+		if (i + 1 == slaves_count) {
 			skb2 = skb;
 			skb_used = true;
 		} else {

drivers/net/ethernet/airoha/airoha_eth.c

···
 
 static void airoha_qdma_cleanup_rx_queue(struct airoha_queue *q)
 {
-	struct airoha_eth *eth = q->qdma->eth;
+	struct airoha_qdma *qdma = q->qdma;
+	struct airoha_eth *eth = qdma->eth;
+	int qid = q - &qdma->q_rx[0];
 
 	while (q->queued) {
 		struct airoha_queue_entry *e = &q->entry[q->tail];
+		struct airoha_qdma_desc *desc = &q->desc[q->tail];
 		struct page *page = virt_to_head_page(e->buf);
 
 		dma_sync_single_for_cpu(eth->dev, e->dma_addr, e->dma_len,
 					page_pool_get_dma_dir(q->page_pool));
 		page_pool_put_full_page(q->page_pool, page, false);
+		/* Reset DMA descriptor */
+		WRITE_ONCE(desc->ctrl, 0);
+		WRITE_ONCE(desc->addr, 0);
+		WRITE_ONCE(desc->data, 0);
+		WRITE_ONCE(desc->msg0, 0);
+		WRITE_ONCE(desc->msg1, 0);
+		WRITE_ONCE(desc->msg2, 0);
+		WRITE_ONCE(desc->msg3, 0);
+
 		q->tail = (q->tail + 1) % q->ndesc;
 		q->queued--;
 	}
+
+	q->head = q->tail;
+	airoha_qdma_rmw(qdma, REG_RX_DMA_IDX(qid), RX_RING_DMA_IDX_MASK,
+			FIELD_PREP(RX_RING_DMA_IDX_MASK, q->tail));
 }
 
 static int airoha_qdma_init_rx(struct airoha_qdma *qdma)
···
 		if (err)
 			return err;
 	}
+
+	set_bit(DEV_STATE_REGISTERED, &eth->state);
 
 	return 0;
 }

drivers/net/ethernet/airoha/airoha_eth.h

···
 
 enum {
 	DEV_STATE_INITIALIZED,
+	DEV_STATE_REGISTERED,
 };
 
 enum {

drivers/net/ethernet/airoha/airoha_ppe.c

···
 	struct airoha_eth *eth = ppe->eth;
 	int err = 0;
 
+	/* Netfilter flowtable can try to offload flower rules while not all
+	 * the net_devices are registered or initialized. Delay offloading
+	 * until all net_devices are registered in the system.
+	 */
+	if (!test_bit(DEV_STATE_REGISTERED, &eth->state))
+		return -EBUSY;
+
 	mutex_lock(&flow_offload_mutex);
 
 	if (!eth->npu)

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

···
 		ulp_msix = bnxt_get_avail_msix(bp, bp->ulp_num_msix_want);
 		if (!ulp_msix)
 			bnxt_set_ulp_stat_ctxs(bp, 0);
+		else
+			bnxt_set_dflt_ulp_stat_ctxs(bp);
 
 		if (ulp_msix > bp->ulp_num_msix_want)
 			ulp_msix = bp->ulp_num_msix_want;
···
 	struct hwrm_func_backing_store_qcaps_v2_output *resp;
 	struct hwrm_func_backing_store_qcaps_v2_input *req;
 	struct bnxt_ctx_mem_info *ctx = bp->ctx;
-	u16 type;
+	u16 type, next_type = 0;
 	int rc;
 
 	rc = hwrm_req_init(bp, req, HWRM_FUNC_BACKING_STORE_QCAPS_V2);
···
 
 	resp = hwrm_req_hold(bp, req);
 
-	for (type = 0; type < BNXT_CTX_V2_MAX; ) {
+	for (type = 0; type < BNXT_CTX_V2_MAX; type = next_type) {
 		struct bnxt_ctx_mem_type *ctxm = &ctx->ctx_arr[type];
 		u8 init_val, init_off, i;
 		u32 max_entries;
···
 		if (rc)
 			goto ctx_done;
 		flags = le32_to_cpu(resp->flags);
-		type = le16_to_cpu(resp->next_valid_type);
+		next_type = le16_to_cpu(resp->next_valid_type);
 		if (!(flags & BNXT_CTX_MEM_TYPE_VALID)) {
 			bnxt_free_one_ctx_mem(bp, ctxm, true);
 			continue;
···
 			else
 				continue;
 		}
-		ctxm->type = le16_to_cpu(resp->type);
+		ctxm->type = type;
 		ctxm->entry_size = entry_size;
 		ctxm->flags = flags;
 		ctxm->instance_bmap = le32_to_cpu(resp->instance_bit_map);
···
 	return bp->num_tc ? bp->tx_nr_rings / bp->num_tc : bp->tx_nr_rings;
 }
 
+static void bnxt_set_xdp_tx_rings(struct bnxt *bp)
+{
+	bp->tx_nr_rings_xdp = bp->tx_nr_rings_per_tc;
+	bp->tx_nr_rings += bp->tx_nr_rings_xdp;
+}
+
+static void bnxt_adj_tx_rings(struct bnxt *bp)
+{
+	/* Make adjustments if reserved TX rings are less than requested */
+	bp->tx_nr_rings -= bp->tx_nr_rings_xdp;
+	bp->tx_nr_rings_per_tc = bnxt_tx_nr_rings_per_tc(bp);
+	if (bp->tx_nr_rings_xdp)
+		bnxt_set_xdp_tx_rings(bp);
+}
+
 static int __bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init)
 {
 	int rc = 0;
···
 	if (rc)
 		return rc;
 
-	/* Make adjustments if reserved TX rings are less than requested */
-	bp->tx_nr_rings -= bp->tx_nr_rings_xdp;
-	bp->tx_nr_rings_per_tc = bnxt_tx_nr_rings_per_tc(bp);
-	if (bp->tx_nr_rings_xdp) {
-		bp->tx_nr_rings_xdp = bp->tx_nr_rings_per_tc;
-		bp->tx_nr_rings += bp->tx_nr_rings_xdp;
-	}
+	bnxt_adj_tx_rings(bp);
 	rc = bnxt_alloc_mem(bp, irq_re_init);
 	if (rc) {
 		netdev_err(bp->dev, "bnxt_alloc_mem err: %x\n", rc);
···
 	return 0;
 }
 
+void bnxt_set_cp_rings(struct bnxt *bp, bool sh)
+{
+	int tx_cp = bnxt_num_tx_to_cp(bp, bp->tx_nr_rings);
+
+	bp->cp_nr_rings = sh ? max_t(int, tx_cp, bp->rx_nr_rings) :
+			       tx_cp + bp->rx_nr_rings;
+}
+
 int bnxt_setup_mq_tc(struct net_device *dev, u8 tc)
 {
 	struct bnxt *bp = netdev_priv(dev);
 	bool sh = false;
-	int rc, tx_cp;
+	int rc;
 
 	if (tc > bp->max_tc) {
 		netdev_err(dev, "Too many traffic classes requested: %d. Max supported is %d.\n",
···
 		bp->num_tc = 0;
 	}
 	bp->tx_nr_rings += bp->tx_nr_rings_xdp;
-	tx_cp = bnxt_num_tx_to_cp(bp, bp->tx_nr_rings);
-	bp->cp_nr_rings = sh ? max_t(int, tx_cp, bp->rx_nr_rings) :
-			       tx_cp + bp->rx_nr_rings;
+	bnxt_set_cp_rings(bp, sh);
 
 	if (netif_running(bp->dev))
 		return bnxt_open_nic(bp, true, false);
···
 	bp->tx_nr_rings = bnxt_tx_nr_rings(bp);
 }
 
+static void bnxt_adj_dflt_rings(struct bnxt *bp, bool sh)
+{
+	if (sh)
+		bnxt_trim_dflt_sh_rings(bp);
+	else
+		bp->cp_nr_rings = bp->tx_nr_rings_per_tc + bp->rx_nr_rings;
+	bp->tx_nr_rings = bnxt_tx_nr_rings(bp);
+	if (sh && READ_ONCE(bp->xdp_prog)) {
+		bnxt_set_xdp_tx_rings(bp);
+		bnxt_set_cp_rings(bp, true);
+	}
+}
+
 static int bnxt_set_dflt_rings(struct bnxt *bp, bool sh)
 {
 	int dflt_rings, max_rx_rings, max_tx_rings, rc;
···
 		return rc;
 	bp->rx_nr_rings = min_t(int, dflt_rings, max_rx_rings);
 	bp->tx_nr_rings_per_tc = min_t(int, dflt_rings, max_tx_rings);
-	if (sh)
-		bnxt_trim_dflt_sh_rings(bp);
-	else
-		bp->cp_nr_rings = bp->tx_nr_rings_per_tc + bp->rx_nr_rings;
-	bp->tx_nr_rings = bnxt_tx_nr_rings(bp);
+
+	bnxt_adj_dflt_rings(bp, sh);
 
 	avail_msix = bnxt_get_max_func_irqs(bp) - bp->cp_nr_rings;
 	if (avail_msix >= BNXT_MIN_ROCE_CP_RINGS) {
···
 	rc = __bnxt_reserve_rings(bp);
 	if (rc && rc != -ENODEV)
 		netdev_warn(bp->dev, "Unable to reserve tx rings\n");
-	bp->tx_nr_rings_per_tc = bnxt_tx_nr_rings_per_tc(bp);
+
+	bnxt_adj_tx_rings(bp);
 	if (sh)
-		bnxt_trim_dflt_sh_rings(bp);
+		bnxt_adj_dflt_rings(bp, true);
 
 	/* Rings may have been trimmed, re-reserve the trimmed rings. */
 	if (bnxt_need_reserve_rings(bp)) {
 		rc = __bnxt_reserve_rings(bp);
 		if (rc && rc != -ENODEV)
 			netdev_warn(bp->dev, "2nd rings reservation failed.\n");
-		bp->tx_nr_rings_per_tc = bnxt_tx_nr_rings_per_tc(bp);
+		bnxt_adj_tx_rings(bp);
 	}
 	if (BNXT_CHIP_TYPE_NITRO_A0(bp)) {
 		bp->rx_nr_rings++;
···
 	if (rc)
 		goto init_dflt_ring_err;
 
-	bp->tx_nr_rings_per_tc = bnxt_tx_nr_rings_per_tc(bp);
+	bnxt_adj_tx_rings(bp);
 
 	bnxt_set_dflt_rfs(bp);
 

drivers/net/ethernet/broadcom/bnxt/bnxt.h

···
 		     int tx_xdp);
 int bnxt_fw_init_one(struct bnxt *bp);
 bool bnxt_hwrm_reset_permitted(struct bnxt *bp);
+void bnxt_set_cp_rings(struct bnxt *bp, bool sh);
 int bnxt_setup_mq_tc(struct net_device *dev, u8 tc);
 struct bnxt_ntuple_filter *bnxt_lookup_ntp_filter_from_idx(struct bnxt *bp,
 				struct bnxt_ntuple_filter *fltr, u32 idx);

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

···
 	bool sh = false;
 	int tx_xdp = 0;
 	int rc = 0;
-	int tx_cp;
 
 	if (channel->other_count)
 		return -EINVAL;
···
 	if (tcs > 1)
 		bp->tx_nr_rings = bp->tx_nr_rings_per_tc * tcs + tx_xdp;
 
-	tx_cp = bnxt_num_tx_to_cp(bp, bp->tx_nr_rings);
-	bp->cp_nr_rings = sh ? max_t(int, tx_cp, bp->rx_nr_rings) :
-			       tx_cp + bp->rx_nr_rings;
+	bnxt_set_cp_rings(bp, sh);
 
 	/* After changing number of rx channels, update NTUPLE feature. */
 	netdev_update_features(dev);

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

···
 static int bnxt_xdp_set(struct bnxt *bp, struct bpf_prog *prog)
 {
 	struct net_device *dev = bp->dev;
-	int tx_xdp = 0, tx_cp, rc, tc;
+	int tx_xdp = 0, rc, tc;
 	struct bpf_prog *old;
 
 	netdev_assert_locked(dev);
···
 	}
 	bp->tx_nr_rings_xdp = tx_xdp;
 	bp->tx_nr_rings = bp->tx_nr_rings_per_tc * tc + tx_xdp;
-	tx_cp = bnxt_num_tx_to_cp(bp, bp->tx_nr_rings);
-	bp->cp_nr_rings = max_t(int, tx_cp, bp->rx_nr_rings);
+	bnxt_set_cp_rings(bp, true);
 	bnxt_set_tpa_flags(bp);
 	bnxt_set_ring_params(bp);
 

drivers/net/ethernet/broadcom/tg3.c

···
 	ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.advertising,
 						advertising);
 
-	if (netif_running(dev) && tp->link_up) {
+	if (netif_running(dev) && netif_carrier_ok(dev)) {
 		cmd->base.speed = tp->link_config.active_speed;
 		cmd->base.duplex = tp->link_config.active_duplex;
 		ethtool_convert_legacy_u32_to_link_mode(

drivers/net/ethernet/cadence/macb_pci.c

···
 	return 0;
 
 err_plat_dev_register:
-	clk_unregister(plat_data.hclk);
+	clk_unregister_fixed_rate(plat_data.hclk);
 
 err_hclk_register:
-	clk_unregister(plat_data.pclk);
+	clk_unregister_fixed_rate(plat_data.pclk);
 
 err_pclk_register:
 	return err;
···
 {
 	struct platform_device *plat_dev = pci_get_drvdata(pdev);
 	struct macb_platform_data *plat_data = dev_get_platdata(&plat_dev->dev);
+	struct clk *pclk = plat_data->pclk;
+	struct clk *hclk = plat_data->hclk;
 
-	clk_unregister(plat_data->pclk);
-	clk_unregister(plat_data->hclk);
 	platform_device_unregister(plat_dev);
+	clk_unregister_fixed_rate(pclk);
+	clk_unregister_fixed_rate(hclk);
 }
 
 static const struct pci_device_id dev_id_table[] = {

drivers/net/ethernet/faraday/ftgmac100.c

···
 	priv->tx_skbs = kcalloc(MAX_TX_QUEUE_ENTRIES, sizeof(void *),
 				GFP_KERNEL);
 	if (!priv->tx_skbs)
-		return -ENOMEM;
+		goto err_free_rx_skbs;
 
 	/* Allocate descriptors */
 	priv->rxdes = dma_alloc_coherent(priv->dev,
 					 MAX_RX_QUEUE_ENTRIES * sizeof(struct ftgmac100_rxdes),
 					 &priv->rxdes_dma, GFP_KERNEL);
 	if (!priv->rxdes)
-		return -ENOMEM;
+		goto err_free_tx_skbs;
 	priv->txdes = dma_alloc_coherent(priv->dev,
 					 MAX_TX_QUEUE_ENTRIES * sizeof(struct ftgmac100_txdes),
 					 &priv->txdes_dma, GFP_KERNEL);
 	if (!priv->txdes)
-		return -ENOMEM;
+		goto err_free_rxdes;
 
 	/* Allocate scratch packet buffer */
 	priv->rx_scratch = dma_alloc_coherent(priv->dev,
···
 					      &priv->rx_scratch_dma,
 					      GFP_KERNEL);
 	if (!priv->rx_scratch)
-		return -ENOMEM;
+		goto err_free_txdes;
 
 	return 0;
+
+err_free_txdes:
+	dma_free_coherent(priv->dev,
+			  MAX_TX_QUEUE_ENTRIES *
+			  sizeof(struct ftgmac100_txdes),
+			  priv->txdes, priv->txdes_dma);
+	priv->txdes = NULL;
+err_free_rxdes:
+	dma_free_coherent(priv->dev,
+			  MAX_RX_QUEUE_ENTRIES *
+			  sizeof(struct ftgmac100_rxdes),
+			  priv->rxdes, priv->rxdes_dma);
+	priv->rxdes = NULL;
+err_free_tx_skbs:
+	kfree(priv->tx_skbs);
+	priv->tx_skbs = NULL;
+err_free_rx_skbs:
+	kfree(priv->rx_skbs);
+	priv->rx_skbs = NULL;
+	return -ENOMEM;
 }
 
 static void ftgmac100_init_rings(struct ftgmac100 *priv)

drivers/net/ethernet/freescale/enetc/enetc.c

···
 
 static void enetc_setup_txbdr(struct enetc_hw *hw, struct enetc_bdr *tx_ring)
 {
+	struct enetc_si *si = container_of(hw, struct enetc_si, hw);
 	int idx = tx_ring->index;
 	u32 tbmr;
 
···
 	enetc_txbdr_wr(hw, idx, ENETC_TBLENR,
 		       ENETC_RTBLENR_LEN(tx_ring->bd_count));
 
-	/* clearing PI/CI registers for Tx not supported, adjust sw indexes */
+	/* For ENETC v1, clearing PI/CI registers for Tx not supported,
+	 * adjust sw indexes
+	 */
 	tx_ring->next_to_use = enetc_txbdr_rd(hw, idx, ENETC_TBPIR);
 	tx_ring->next_to_clean = enetc_txbdr_rd(hw, idx, ENETC_TBCIR);
+
+	if (tx_ring->next_to_use != tx_ring->next_to_clean &&
+	    !is_enetc_rev1(si)) {
+		tx_ring->next_to_use = 0;
+		tx_ring->next_to_clean = 0;
+		enetc_txbdr_wr(hw, idx, ENETC_TBPIR, 0);
+		enetc_txbdr_wr(hw, idx, ENETC_TBCIR, 0);
+	}
 
 	/* enable Tx ints by setting pkt thr to 1 */
 	enetc_txbdr_wr(hw, idx, ENETC_TBICR0, ENETC_TBICR0_ICEN | 0x1);

drivers/net/ethernet/freescale/enetc/enetc4_hw.h

···
 
 /* Port operational register */
 #define ENETC4_POR			0x4100
+#define  POR_TXDIS			BIT(0)
+#define  POR_RXDIS			BIT(1)
+
+/* Port status register */
+#define ENETC4_PSR			0x4104
+#define  PSR_RX_BUSY			BIT(1)
 
 /* Port traffic class a transmit maximum SDU register */
 #define ENETC4_PTCTMSDUR(a)		((a) * 0x20 + 0x4208)
···
 
 /* Port internal MDIO base address, use to access PCS */
 #define ENETC4_PM_IMDIO_BASE		0x5030
+
+/* Port MAC 0/1 Interrupt Event Register */
+#define ENETC4_PM_IEVENT(mac)		(0x5040 + (mac) * 0x400)
+#define  PM_IEVENT_TX_EMPTY		BIT(5)
+#define  PM_IEVENT_RX_EMPTY		BIT(6)
 
 /* Port MAC 0/1 Pause Quanta Register */
 #define ENETC4_PM_PAUSE_QUANTA(mac)	(0x5054 + (mac) * 0x400)

drivers/net/ethernet/freescale/enetc/enetc4_pf.c

···
 	enetc4_pf_reset_tc_msdu(&si->hw);
 }
 
-static void enetc4_enable_trx(struct enetc_pf *pf)
-{
-	struct enetc_hw *hw = &pf->si->hw;
-
-	/* Enable port transmit/receive */
-	enetc_port_wr(hw, ENETC4_POR, 0);
-}
-
 static void enetc4_configure_port(struct enetc_pf *pf)
 {
 	enetc4_configure_port_si(pf);
 	enetc4_set_trx_frame_size(pf);
 	enetc_set_default_rss_key(pf);
-	enetc4_enable_trx(pf);
 }
 
 static int enetc4_init_ntmp_user(struct enetc_si *si)
···
 	enetc_port_wr(hw, ENETC4_PPAUOFFTR, pause_off_thresh);
 }
 
-static void enetc4_enable_mac(struct enetc_pf *pf, bool en)
+static void enetc4_mac_wait_tx_empty(struct enetc_si *si, int mac)
 {
+	u32 val;
+
+	if (read_poll_timeout(enetc_port_rd, val,
+			      val & PM_IEVENT_TX_EMPTY,
+			      100, 10000, false, &si->hw,
+			      ENETC4_PM_IEVENT(mac)))
+		dev_warn(&si->pdev->dev,
+			 "MAC %d TX is not empty\n", mac);
+}
+
+static void enetc4_mac_tx_graceful_stop(struct enetc_pf *pf)
+{
+	struct enetc_hw *hw = &pf->si->hw;
+	struct enetc_si *si = pf->si;
+	u32 val;
+
+	val = enetc_port_rd(hw, ENETC4_POR);
+	val |= POR_TXDIS;
+	enetc_port_wr(hw, ENETC4_POR, val);
+
+	if (enetc_is_pseudo_mac(si))
+		return;
+
+	enetc4_mac_wait_tx_empty(si, 0);
+	if (si->hw_features & ENETC_SI_F_QBU)
+		enetc4_mac_wait_tx_empty(si, 1);
+
+	val = enetc_port_mac_rd(si, ENETC4_PM_CMD_CFG(0));
+	val &= ~PM_CMD_CFG_TX_EN;
+	enetc_port_mac_wr(si, ENETC4_PM_CMD_CFG(0), val);
+}
+
+static void enetc4_mac_tx_enable(struct enetc_pf *pf)
+{
+	struct enetc_hw *hw = &pf->si->hw;
 	struct enetc_si *si = pf->si;
 	u32 val;
 
 	val = enetc_port_mac_rd(si, ENETC4_PM_CMD_CFG(0));
-	val &= ~(PM_CMD_CFG_TX_EN | PM_CMD_CFG_RX_EN);
-	val |= en ? (PM_CMD_CFG_TX_EN | PM_CMD_CFG_RX_EN) : 0;
+	val |= PM_CMD_CFG_TX_EN;
+	enetc_port_mac_wr(si, ENETC4_PM_CMD_CFG(0), val);
 
+	val = enetc_port_rd(hw, ENETC4_POR);
+	val &= ~POR_TXDIS;
+	enetc_port_wr(hw, ENETC4_POR, val);
+}
+
+static void enetc4_mac_wait_rx_empty(struct enetc_si *si, int mac)
+{
+	u32 val;
+
+	if (read_poll_timeout(enetc_port_rd, val,
+			      val & PM_IEVENT_RX_EMPTY,
+			      100, 10000, false, &si->hw,
+			      ENETC4_PM_IEVENT(mac)))
+		dev_warn(&si->pdev->dev,
+			 "MAC %d RX is not empty\n", mac);
+}
+
+static void enetc4_mac_rx_graceful_stop(struct enetc_pf *pf)
+{
+	struct enetc_hw *hw = &pf->si->hw;
+	struct enetc_si *si = pf->si;
+	u32 val;
+
+	if (enetc_is_pseudo_mac(si))
+		goto check_rx_busy;
+
+	if (si->hw_features & ENETC_SI_F_QBU) {
+		val = enetc_port_rd(hw, ENETC4_PM_CMD_CFG(1));
+		val &= ~PM_CMD_CFG_RX_EN;
+		enetc_port_wr(hw, ENETC4_PM_CMD_CFG(1), val);
+		enetc4_mac_wait_rx_empty(si, 1);
+	}
+
+	val = enetc_port_rd(hw, ENETC4_PM_CMD_CFG(0));
+	val &= ~PM_CMD_CFG_RX_EN;
+	enetc_port_wr(hw, ENETC4_PM_CMD_CFG(0), val);
+	enetc4_mac_wait_rx_empty(si, 0);
+
+check_rx_busy:
+	if (read_poll_timeout(enetc_port_rd, val,
+			      !(val & PSR_RX_BUSY),
+			      100, 10000, false, hw,
+			      ENETC4_PSR))
+		dev_warn(&si->pdev->dev, "Port RX busy\n");
+
+	val = enetc_port_rd(hw, ENETC4_POR);
+	val |= POR_RXDIS;
+	enetc_port_wr(hw, ENETC4_POR, val);
+}
+
+static void enetc4_mac_rx_enable(struct enetc_pf *pf)
+{
+	struct enetc_hw *hw = &pf->si->hw;
+	struct enetc_si *si = pf->si;
+	u32 val;
+
+	val = enetc_port_rd(hw, ENETC4_POR);
+	val &= ~POR_RXDIS;
+	enetc_port_wr(hw, ENETC4_POR, val);
+
+	val = enetc_port_mac_rd(si, ENETC4_PM_CMD_CFG(0));
+	val |= PM_CMD_CFG_RX_EN;
 	enetc_port_mac_wr(si, ENETC4_PM_CMD_CFG(0), val);
 }
 
···
 	enetc4_set_hd_flow_control(pf, hd_fc);
 	enetc4_set_tx_pause(pf, priv->num_rx_rings, tx_pause);
 	enetc4_set_rx_pause(pf, rx_pause);
-	enetc4_enable_mac(pf, true);
+	enetc4_mac_tx_enable(pf);
+	enetc4_mac_rx_enable(pf);
 }
 
 static void enetc4_pl_mac_link_down(struct phylink_config *config,
···
 {
 	struct enetc_pf *pf = phylink_to_enetc_pf(config);
 
-	enetc4_enable_mac(pf, false);
+	enetc4_mac_rx_graceful_stop(pf);
+	enetc4_mac_tx_graceful_stop(pf);
 }
 
 static const struct phylink_mac_ops enetc_pl_mac_ops = {

drivers/net/ethernet/freescale/enetc/enetc_ethtool.c

···
 	struct enetc_si *si = priv->si;
 	int err = 0;
 
+	if (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE &&
+	    rxfh->hfunc != ETH_RSS_HASH_TOP)
+		return -EOPNOTSUPP;
+
 	/* set hash key, if PF */
-	if (rxfh->key && enetc_si_is_pf(si))
+	if (rxfh->key) {
+		if (!enetc_si_is_pf(si))
+			return -EOPNOTSUPP;
+
 		enetc_set_rss_key(si, rxfh->key);
+	}
 
 	/* set RSS table */
 	if (rxfh->indir)

drivers/net/ethernet/freescale/fec_ptp.c

···
 		if (rq->perout.flags)
 			return -EOPNOTSUPP;
 
-		if (rq->perout.index != fep->pps_channel)
-			return -EOPNOTSUPP;
-
 		period.tv_sec = rq->perout.period.sec;
 		period.tv_nsec = rq->perout.period.nsec;
 		period_ns = timespec64_to_ns(&period);

drivers/net/ethernet/mediatek/mtk_ppe_offload.c

···
 	return 0;
 }
 
+static bool
+mtk_flow_is_valid_idev(const struct mtk_eth *eth, const struct net_device *idev)
+{
+	size_t i;
+
+	if (!idev)
+		return false;
+
+	for (i = 0; i < ARRAY_SIZE(eth->netdev); i++) {
+		if (!eth->netdev[i])
+			continue;
+
+		if (idev->netdev_ops == eth->netdev[i]->netdev_ops)
+			return true;
+	}
+
+	return false;
+}
+
 static int
 mtk_flow_offload_replace(struct mtk_eth *eth, struct flow_cls_offload *f,
 			 int ppe_index)
···
 		flow_rule_match_meta(rule, &match);
 		if (mtk_is_netsys_v2_or_greater(eth)) {
 			idev = __dev_get_by_index(&init_net, match.key->ingress_ifindex);
-			if (idev && idev->netdev_ops == eth->netdev[0]->netdev_ops) {
+			if (mtk_flow_is_valid_idev(eth, idev)) {
 				struct mtk_mac *mac = netdev_priv(idev);
 
 				if (WARN_ON(mac->ppe_idx >= eth->soc->ppe_num))

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

···
 	if (err)
 		return err;
 
-	err = mlx5_fw_version_query(dev, &running_fw, &stored_fw);
-	if (err)
-		return err;
+	mlx5_fw_version_query(dev, &running_fw, &stored_fw);
 
 	snprintf(version_str, sizeof(version_str), "%d.%d.%04d",
 		 mlx5_fw_ver_major(running_fw), mlx5_fw_ver_minor(running_fw),

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

···
 	return 0;
 
 err_vports:
+	/* rollback to legacy, indicates don't unregister the uplink netdev */
+	esw->dev->priv.flags |= MLX5_PRIV_FLAGS_SWITCH_LEGACY;
 	mlx5_esw_offloads_rep_unload(esw, MLX5_VPORT_UPLINK);
 err_uplink:
 	esw_offloads_steering_cleanup(esw);

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

···
 	return 0;
 }
 
-int mlx5_fw_version_query(struct mlx5_core_dev *dev,
-			  u32 *running_ver, u32 *pending_ver)
+void mlx5_fw_version_query(struct mlx5_core_dev *dev,
+			   u32 *running_ver, u32 *pending_ver)
 {
 	u32 reg_mcqi_version[MLX5_ST_SZ_DW(mcqi_version)] = {};
 	bool pending_version_exists;
 	int component_index;
 	int err;
 
+	*running_ver = 0;
+	*pending_ver = 0;
+
 	if (!MLX5_CAP_GEN(dev, mcam_reg) || !MLX5_CAP_MCAM_REG(dev, mcqi) ||
 	    !MLX5_CAP_MCAM_REG(dev, mcqs)) {
 		mlx5_core_warn(dev, "fw query isn't supported by the FW\n");
-		return -EOPNOTSUPP;
+		return;
 	}
 
 	component_index = mlx5_get_boot_img_component_index(dev);
-	if (component_index < 0)
-		return component_index;
+	if (component_index < 0) {
+		mlx5_core_warn(dev, "fw query failed to find boot img component index, err %d\n",
+			       component_index);
+		return;
+	}
 
+	*running_ver = U32_MAX; /* indicate failure */
 	err = mlx5_reg_mcqi_version_query(dev, component_index,
 					  MCQI_FW_RUNNING_VERSION,
 					  reg_mcqi_version);
-	if (err)
-		return err;
+	if (!err)
+		*running_ver = MLX5_GET(mcqi_version, reg_mcqi_version,
+					version);
+	else
+		mlx5_core_warn(dev, "failed to query running version, err %d\n",
+			       err);
 
-	*running_ver = MLX5_GET(mcqi_version, reg_mcqi_version, version);
-
+	*pending_ver = U32_MAX; /* indicate failure */
 	err = mlx5_fw_image_pending(dev, component_index, &pending_version_exists);
-	if (err)
-		return err;
+	if (err) {
+		mlx5_core_warn(dev, "failed to query pending image, err %d\n",
+			       err);
+		return;
+	}
 
 	if (!pending_version_exists) {
 		*pending_ver = 0;
-		return 0;
+		return;
 	}
 
 	err = mlx5_reg_mcqi_version_query(dev, component_index,
 					  MCQI_FW_STORED_VERSION,
 					  reg_mcqi_version);
-	if (err)
-		return err;
+	if (!err)
+		*pending_ver = MLX5_GET(mcqi_version, reg_mcqi_version,
+					version);
+	else
+		mlx5_core_warn(dev, "failed to query pending version, err %d\n",
+			       err);
 
-	*pending_ver = MLX5_GET(mcqi_version, reg_mcqi_version, version);
-
-	return 0;
+	return;
 }

drivers/net/ethernet/mellanox/mlx5/core/lag/debugfs.c

···
 
 void mlx5_ldev_add_debugfs(struct mlx5_core_dev *dev)
 {
+	struct mlx5_lag *ldev = mlx5_lag_dev(dev);
 	struct dentry *dbg;
 
+	if (!ldev)
+		return;
 	dbg = debugfs_create_dir("lag", mlx5_debugfs_get_dev_root(dev));
 	dev->priv.dbg.lag_debugfs = dbg;
 

drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h

···
 
 int mlx5_firmware_flash(struct mlx5_core_dev *dev, const struct firmware *fw,
 			struct netlink_ext_ack *extack);
-int mlx5_fw_version_query(struct mlx5_core_dev *dev,
-			  u32 *running_ver, u32 *stored_ver);
+void mlx5_fw_version_query(struct mlx5_core_dev *dev, u32 *running_ver,
+			   u32 *stored_ver);
 
 #ifdef CONFIG_MLX5_CORE_EN
 int mlx5e_init(void);

drivers/net/ethernet/meta/fbnic/fbnic_debugfs.c

···
 		return 0;
 	}
 
-	for (i = 0; i <= ring->size_mask; i++) {
+	for (i = 0; i < (ring->size_mask + 1) * FBNIC_BD_FRAG_COUNT; i++) {
 		u64 bd = le64_to_cpu(ring->desc[i]);
 
 		seq_printf(s, "%04x %#04llx %#014llx\n", i,

drivers/net/ethernet/meta/fbnic/fbnic_txrx.c

···
 		/* Force DMA writes to flush before writing to tail */
 		dma_wmb();
 
-		writel(i, bdq->doorbell);
+		writel(i * FBNIC_BD_FRAG_COUNT, bdq->doorbell);
 	}
 }
 
···
 	hpq->tail = 0;
 	hpq->head = 0;
 
-	log_size = fls(hpq->size_mask);
+	log_size = fls(hpq->size_mask) + ilog2(FBNIC_BD_FRAG_COUNT);
 
 	/* Store descriptor ring address and size */
 	fbnic_ring_wr32(hpq, FBNIC_QUEUE_BDQ_HPQ_BAL, lower_32_bits(hpq->dma));
···
 	if (!ppq->size_mask)
 		goto write_ctl;
 
-	log_size = fls(ppq->size_mask);
+	log_size = fls(ppq->size_mask) + ilog2(FBNIC_BD_FRAG_COUNT);
 
 	/* Add enabling of PPQ to BDQ control */
 	bdq_ctl |= FBNIC_QUEUE_BDQ_CTL_PPQ_ENABLE;

drivers/net/ethernet/meta/fbnic/fbnic_txrx.h

···
 #define FBNIC_MAX_XDPQS			128u
 
 /* These apply to TWQs, TCQ, RCQ */
-#define FBNIC_QUEUE_SIZE_MIN		16u
+#define FBNIC_QUEUE_SIZE_MIN		64u
 #define FBNIC_QUEUE_SIZE_MAX		SZ_64K
 
 #define FBNIC_TXQ_SIZE_DEFAULT		1024

drivers/net/ethernet/microsoft/mana/mana_en.c

···
 		}
 
 		*frag_count = 1;
+
+		/* In the single-buffer path, napi_build_skb() must see the
+		 * actual backing allocation size so skb->truesize reflects
+		 * the full page (or higher-order page), not just the usable
+		 * packet area.
+		 */
+		*alloc_size = PAGE_SIZE << get_order(*alloc_size);
 		return;
 	}
 

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

···
 static void stmmac_flush_tx_descriptors(struct stmmac_priv *priv, int queue);
 static void stmmac_set_dma_operation_mode(struct stmmac_priv *priv, u32 txmode,
 					  u32 rxmode, u32 chan);
-static int stmmac_vlan_restore(struct stmmac_priv *priv);
+static void stmmac_vlan_restore(struct stmmac_priv *priv);
 
 #ifdef CONFIG_DEBUG_FS
 static const struct net_device_ops stmmac_netdev_ops;
···
 	return ret;
 }
 
-static int stmmac_vlan_restore(struct stmmac_priv *priv)
+static void stmmac_vlan_restore(struct stmmac_priv *priv)
 {
-	int ret;
-
 	if (!(priv->dev->features & NETIF_F_VLAN_FEATURES))
-		return 0;
+		return;
 
 	if (priv->hw->num_vlan)
 		stmmac_restore_hw_vlan_rx_fltr(priv, priv->dev, priv->hw);
 
-	ret = stmmac_vlan_update(priv, priv->num_double_vlans);
-	if (ret)
-		netdev_err(priv->dev, "Failed to restore VLANs\n");
-
-	return ret;
+	stmmac_vlan_update(priv, priv->num_double_vlans);
 }
 
 static int stmmac_bpf(struct net_device *dev, struct netdev_bpf *bpf)

drivers/net/ethernet/ti/icssg/icssg_common.c

···
 
 	skb_reserve(skb, headroom);
 	skb_put(skb, pkt_len);
+	skb_copy_to_linear_data(skb, xdp->data, pkt_len);
 	skb->dev = ndev;
 
 	/* RX HW timestamp */
···
 		skb->offload_fwd_mark = emac->offload_fwd_mark;
 	skb->protocol = eth_type_trans(skb, ndev);
 
-	skb_mark_for_recycle(skb);
 	napi_gro_receive(&emac->napi_rx, skb);
 	ndev->stats.rx_bytes += pkt_len;
 	ndev->stats.rx_packets++;

drivers/net/ethernet/xilinx/xilinx_axienet.h

···
 #define XAXIDMA_BD_HAS_DRE_MASK		0xF00 /* Whether has DRE mask */
 #define XAXIDMA_BD_WORDLEN_MASK		0xFF /* Whether has DRE mask */
 
-#define XAXIDMA_BD_CTRL_LENGTH_MASK	0x007FFFFF /* Requested len */
+#define XAXIDMA_BD_CTRL_LENGTH_MASK	GENMASK(25, 0) /* Requested len */
 #define XAXIDMA_BD_CTRL_TXSOF_MASK	0x08000000 /* First tx packet */
 #define XAXIDMA_BD_CTRL_TXEOF_MASK	0x04000000 /* Last tx packet */
 #define XAXIDMA_BD_CTRL_ALL_MASK	0x0C000000 /* All control bits */
···
 #define XAXIDMA_BD_CTRL_TXEOF_MASK	0x04000000 /* Last tx packet */
 #define XAXIDMA_BD_CTRL_ALL_MASK	0x0C000000 /* All control bits */
 
-#define XAXIDMA_BD_STS_ACTUAL_LEN_MASK	0x007FFFFF /* Actual len */
+#define XAXIDMA_BD_STS_ACTUAL_LEN_MASK	GENMASK(25, 0) /* Actual len */
 #define XAXIDMA_BD_STS_COMPLETE_MASK	0x80000000 /* Completed */
 #define XAXIDMA_BD_STS_DEC_ERR_MASK	0x40000000 /* Decode error */
 #define XAXIDMA_BD_STS_SLV_ERR_MASK	0x20000000 /* Slave error */

drivers/net/ethernet/xilinx/xilinx_axienet_main.c

···
  * @first_bd:	Index of first descriptor to clean up
  * @nr_bds:	Max number of descriptors to clean up
  * @force:	Whether to clean descriptors even if not complete
- * @sizep:	Pointer to a u32 filled with the total sum of all bytes
- *		in all cleaned-up descriptors. Ignored if NULL.
+ * @sizep:	Pointer to a u32 accumulating the total byte count of
+ *		completed packets (using skb->len). Ignored if NULL.
  * @budget:	NAPI budget (use 0 when not called from NAPI poll)
  *
  * Would either be called after a successful transmit operation, or after
···
 				 DMA_TO_DEVICE);
 
 		if (cur_p->skb && (status & XAXIDMA_BD_STS_COMPLETE_MASK)) {
+			if (sizep)
+				*sizep += cur_p->skb->len;
 			napi_consume_skb(cur_p->skb, budget);
 			packets++;
 		}
···
 		wmb();
 		cur_p->cntrl = 0;
 		cur_p->status = 0;
-
-		if (sizep)
-			*sizep += status & XAXIDMA_BD_STS_ACTUAL_LEN_MASK;
 	}
 
 	if (!force) {

drivers/net/phy/sfp.c

···
 {
 	/* Ubiquiti U-Fiber Instant module claims that support all transceiver
 	 * types including 10G Ethernet which is not truth. So clear all claimed
-	 * modes and set only one mode which module supports: 1000baseX_Full.
+	 * modes and set only one mode which module supports: 1000baseX_Full,
+	 * along with the Autoneg and pause bits.
 	 */
 	linkmode_zero(caps->link_modes);
 	linkmode_set_bit(ETHTOOL_LINK_MODE_1000baseX_Full_BIT,
 			 caps->link_modes);
+	linkmode_set_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, caps->link_modes);
+	linkmode_set_bit(ETHTOOL_LINK_MODE_Pause_BIT, caps->link_modes);
+	linkmode_set_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, caps->link_modes);
+
 	phy_interface_zero(caps->interfaces);
 	__set_bit(PHY_INTERFACE_MODE_1000BASEX, caps->interfaces);
 }

drivers/net/virtio_net.c

···
 	struct xdp_buff **xsk_buffs;
 };
 
-#define VIRTIO_NET_RSS_MAX_KEY_SIZE     40
-
 /* Control VQ buffers: protected by the rtnl lock */
 struct control_buf {
 	struct virtio_net_ctrl_hdr hdr;
···
 
 	/* Must be last as it ends in a flexible-array member. */
 	TRAILING_OVERLAP(struct virtio_net_rss_config_trailer, rss_trailer, hash_key_data,
-		u8 rss_hash_key_data[VIRTIO_NET_RSS_MAX_KEY_SIZE];
+		u8 rss_hash_key_data[NETDEV_RSS_KEY_LEN];
 	);
 };
 static_assert(offsetof(struct virtnet_info, rss_trailer.hash_key_data) ==
···
 	struct virtnet_info *vi;
 	u16 max_queue_pairs;
 	int mtu = 0;
+	u16 key_sz;
 
 	/* Find if host supports multiqueue/rss virtio_net device */
 	max_queue_pairs = 1;
···
 	}
 
 	if (vi->has_rss || vi->has_rss_hash_report) {
-		vi->rss_key_size =
-			virtio_cread8(vdev, offsetof(struct virtio_net_config, rss_max_key_size));
-		if (vi->rss_key_size > VIRTIO_NET_RSS_MAX_KEY_SIZE) {
-			dev_err(&vdev->dev, "rss_max_key_size=%u exceeds the limit %u.\n",
-				vi->rss_key_size, VIRTIO_NET_RSS_MAX_KEY_SIZE);
-			err = -EINVAL;
-			goto free;
-		}
+		key_sz = virtio_cread8(vdev, offsetof(struct virtio_net_config, rss_max_key_size));
+
+		vi->rss_key_size = min_t(u16, key_sz, NETDEV_RSS_KEY_LEN);
+		if (key_sz > vi->rss_key_size)
+			dev_warn(&vdev->dev,
+				 "rss_max_key_size=%u exceeds driver limit %u, clamping\n",
+				 key_sz, vi->rss_key_size);
 
 		vi->rss_hash_types_supported =
 		    virtio_cread32(vdev, offsetof(struct virtio_net_config, supported_hash_types));

drivers/net/vxlan/vxlan_core.c

···
 	ns_olen = request->len - skb_network_offset(request) -
 		sizeof(struct ipv6hdr) - sizeof(*ns);
 	for (i = 0; i < ns_olen-1; i += (ns->opt[i+1]<<3)) {
-		if (!ns->opt[i + 1]) {
+		if (!ns->opt[i + 1] || i + (ns->opt[i + 1] << 3) > ns_olen) {
 			kfree_skb(reply);
 			return NULL;
 		}
 		if (ns->opt[i] == ND_OPT_SOURCE_LL_ADDR) {
-			daddr = ns->opt + i + sizeof(struct nd_opt_hdr);
+			if ((ns->opt[i + 1] << 3) >=
+			    sizeof(struct nd_opt_hdr) + ETH_ALEN)
+				daddr = ns->opt + i + sizeof(struct nd_opt_hdr);
 			break;
 		}
 	}

drivers/net/wireless/ath/ath11k/dp_rx.c

···
 // SPDX-License-Identifier: BSD-3-Clause-Clear
 /*
  * Copyright (c) 2018-2019 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2025 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) Qualcomm Technologies, Inc. and/or its subsidiaries.
  */
 
 #include <linux/ieee80211.h>
···
 	struct ath11k_base *ab = ar->ab;
 	struct ath11k_peer *peer;
 	struct ath11k_sta *arsta = ath11k_sta_to_arsta(params->sta);
+	struct dp_rx_tid *rx_tid;
 	int vdev_id = arsta->arvif->vdev_id;
-	dma_addr_t paddr;
-	bool active;
 	int ret;
 
 	spin_lock_bh(&ab->base_lock);
···
 		return -ENOENT;
 	}
 
-	paddr = peer->rx_tid[params->tid].paddr;
-	active = peer->rx_tid[params->tid].active;
+	rx_tid = &peer->rx_tid[params->tid];
 
-	if (!active) {
+	if (!rx_tid->active) {
 		spin_unlock_bh(&ab->base_lock);
 		return 0;
 	}
 
-	ret = ath11k_peer_rx_tid_reo_update(ar, peer, peer->rx_tid, 1, 0, false);
+	ret = ath11k_peer_rx_tid_reo_update(ar, peer, rx_tid, 1, 0, false);
 	spin_unlock_bh(&ab->base_lock);
 	if (ret) {
 		ath11k_warn(ab, "failed to update reo for rx tid %d: %d\n",
···
 	}
 
 	ret = ath11k_wmi_peer_rx_reorder_queue_setup(ar, vdev_id,
-						     params->sta->addr, paddr,
+						     params->sta->addr,
+						     rx_tid->paddr,
 						     params->tid, 1, 1);
 	if (ret)
 		ath11k_warn(ab, "failed to send wmi to delete rx tid %d\n",

drivers/net/wireless/ath/ath12k/dp_rx.c

···
 	struct ath12k_dp *dp = ath12k_ab_to_dp(ab);
 	struct ath12k_dp_link_peer *peer;
 	struct ath12k_sta *ahsta = ath12k_sta_to_ahsta(params->sta);
+	struct ath12k_dp_rx_tid *rx_tid;
 	struct ath12k_link_sta *arsta;
 	int vdev_id;
 	bool active;
···
 		return 0;
 	}
 
-	ret = ath12k_dp_arch_peer_rx_tid_reo_update(dp, peer, peer->dp_peer->rx_tid,
+	rx_tid = &peer->dp_peer->rx_tid[params->tid];
+	ret = ath12k_dp_arch_peer_rx_tid_reo_update(dp, peer, rx_tid,
 						    1, 0, false);
 	spin_unlock_bh(&dp->dp_lock);
 	if (ret) {

drivers/net/wireless/intel/iwlwifi/fw/api/commands.h

···
 	SCAN_OFFLOAD_UPDATE_PROFILES_CMD = 0x6E,
 
 	/**
+	 * @SCAN_START_NOTIFICATION_UMAC: uses &struct iwl_umac_scan_start
+	 */
+	SCAN_START_NOTIFICATION_UMAC = 0xb2,
+
+	/**
 	 * @MATCH_FOUND_NOTIFICATION: scan match found
 	 */
 	MATCH_FOUND_NOTIFICATION = 0xd9,

drivers/net/wireless/intel/iwlwifi/fw/api/scan.h

···
 };
 
 /**
+ * struct iwl_umac_scan_start - scan start notification
+ * @uid: scan id, &enum iwl_umac_scan_uid_offsets
+ * @reserved: for future use
+ */
+struct iwl_umac_scan_start {
+	__le32 uid;
+	__le32 reserved;
+} __packed; /* SCAN_START_UMAC_API_S_VER_1 */
+
+/**
  * struct iwl_umac_scan_complete - scan complete notification
  * @uid: scan id, &enum iwl_umac_scan_uid_offsets
  * @last_schedule: last scheduling line

drivers/net/wireless/intel/iwlwifi/mld/iface.c

···
 			       IEEE80211_HE_MAC_CAP2_ACK_EN);
 }
 
-static void iwl_mld_set_he_support(struct iwl_mld *mld,
-				   struct ieee80211_vif *vif,
-				   struct iwl_mac_config_cmd *cmd)
+struct iwl_mld_mac_wifi_gen_sta_iter_data {
+	struct ieee80211_vif *vif;
+	struct iwl_mac_wifi_gen_support *support;
+};
+
+static void iwl_mld_mac_wifi_gen_sta_iter(void *_data,
+					  struct ieee80211_sta *sta)
 {
-	if (vif->type == NL80211_IFTYPE_AP)
-		cmd->wifi_gen.he_ap_support = 1;
-	else
-		cmd->wifi_gen.he_support = 1;
+	struct iwl_mld_sta *mld_sta = iwl_mld_sta_from_mac80211(sta);
+	struct iwl_mld_mac_wifi_gen_sta_iter_data *data = _data;
+	struct ieee80211_link_sta *link_sta;
+	unsigned int link_id;
+
+	if (mld_sta->vif != data->vif)
+		return;
+
+	for_each_sta_active_link(data->vif, sta, link_sta, link_id) {
+		if (link_sta->he_cap.has_he)
+			data->support->he_support = 1;
+		if (link_sta->eht_cap.has_eht)
+			data->support->eht_support = 1;
+	}
+}
+
+static void iwl_mld_set_wifi_gen(struct iwl_mld *mld,
+				 struct ieee80211_vif *vif,
+				 struct iwl_mac_wifi_gen_support *support)
+{
+	struct iwl_mld_mac_wifi_gen_sta_iter_data sta_iter_data = {
+		.vif = vif,
+		.support = support,
+	};
+	struct ieee80211_bss_conf *link_conf;
+	unsigned int link_id;
+
+	switch (vif->type) {
+	case NL80211_IFTYPE_MONITOR:
+		/* for sniffer, set to HW capabilities */
+		support->he_support = 1;
+		support->eht_support = mld->trans->cfg->eht_supported;
+		break;
+	case NL80211_IFTYPE_AP:
+		/* for AP set according to the link configs */
+		for_each_vif_active_link(vif, link_conf, link_id) {
+			support->he_ap_support |= link_conf->he_support;
+			support->eht_support |= link_conf->eht_support;
+		}
+		break;
+	default:
+		/*
+		 * If we have MLO enabled, then the firmware needs to enable
+		 * address translation for the station(s) we add. That depends
+		 * on having EHT enabled in firmware, which in turn depends on
+		 * mac80211 in the iteration below.
+		 * However, mac80211 doesn't enable capabilities on the AP STA
+		 * until it has parsed the association response successfully,
+		 * so set EHT (and HE as a pre-requisite for EHT) when the vif
+		 * is an MLD.
+		 */
+		if (ieee80211_vif_is_mld(vif)) {
+			support->he_support = 1;
+			support->eht_support = 1;
+		}
+
+		ieee80211_iterate_stations_mtx(mld->hw,
+					       iwl_mld_mac_wifi_gen_sta_iter,
+					       &sta_iter_data);
+		break;
+	}
 }
 
 /* fill the common part for all interface types */
···
 					u32 action)
 {
 	struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(vif);
-	struct ieee80211_bss_conf *link_conf;
-	unsigned int link_id;
 
 	lockdep_assert_wiphy(mld->wiphy);
 
···
 	cmd->nic_not_ack_enabled =
 		cpu_to_le32(!iwl_mld_is_nic_ack_enabled(mld, vif));
 
-	/* If we have MLO enabled, then the firmware needs to enable
-	 * address translation for the station(s) we add. That depends
-	 * on having EHT enabled in firmware, which in turn depends on
-	 * mac80211 in the code below.
-	 * However, mac80211 doesn't enable HE/EHT until it has parsed
-	 * the association response successfully, so just skip all that
-	 * and enable both when we have MLO.
-	 */
-	if (ieee80211_vif_is_mld(vif)) {
-		iwl_mld_set_he_support(mld, vif, cmd);
-		cmd->wifi_gen.eht_support = 1;
-		return;
-	}
-
-	for_each_vif_active_link(vif, link_conf, link_id) {
-		if (!link_conf->he_support)
-			continue;
-
-		iwl_mld_set_he_support(mld, vif, cmd);
-
-		/* EHT, if supported, was already set above */
-		break;
-	}
+	iwl_mld_set_wifi_gen(mld, vif, &cmd->wifi_gen);
 }
 
 static void iwl_mld_fill_mac_cmd_sta(struct iwl_mld *mld,

drivers/net/wireless/intel/iwlwifi/mld/mac80211.c

···
 
 		if (vif->type == NL80211_IFTYPE_STATION)
 			iwl_mld_link_set_2mhz_block(mld, vif, sta);
+
+		if (sta->tdls) {
+			/*
+			 * update MAC since wifi generation flags may change,
+			 * we also update MAC on association to the AP via the
+			 * vif assoc change
+			 */
+			iwl_mld_mac_fw_action(mld, vif, FW_CTXT_ACTION_MODIFY);
+		}
+
 		/* Now the link_sta's capabilities are set, update the FW */
 		iwl_mld_config_tlc(mld, vif, sta);
 
···
 			/* Unblock EMLSR when TDLS connection is torn down */
 			iwl_mld_unblock_emlsr(mld, vif,
 					      IWL_MLD_EMLSR_BLOCKED_TDLS);
+		}
+
+		if (sta->tdls) {
+			/*
+			 * update MAC since wifi generation flags may change,
+			 * we also update MAC on disassociation to the AP via
+			 * the vif assoc change
+			 */
+			iwl_mld_mac_fw_action(mld, vif, FW_CTXT_ACTION_MODIFY);
 		}
 	} else {
 		return -EINVAL;

drivers/net/wireless/intel/iwlwifi/mld/mld.c

···
 	HCMD_NAME(MISSED_BEACONS_NOTIFICATION),
 	HCMD_NAME(MAC_PM_POWER_TABLE),
 	HCMD_NAME(MFUART_LOAD_NOTIFICATION),
+	HCMD_NAME(SCAN_START_NOTIFICATION_UMAC),
 	HCMD_NAME(RSS_CONFIG_CMD),
 	HCMD_NAME(SCAN_ITERATION_COMPLETE_UMAC),
 	HCMD_NAME(REPLY_RX_MPDU_CMD),

drivers/net/wireless/intel/iwlwifi/mld/mlo.c

···
 
 		/* Ignore any BSS that was not seen in the last MLO scan */
 		if (ktime_before(link_conf->bss->ts_boottime,
-				 mld->scan.last_mlo_scan_time))
+				 mld->scan.last_mlo_scan_start_time))
 			continue;
 
 		data[n_data].link_id = link_id;
···
 	if (!mld_vif->authorized || hweight16(usable_links) <= 1)
 		return;
 
-	if (WARN(ktime_before(mld->scan.last_mlo_scan_time,
+	if (WARN(ktime_before(mld->scan.last_mlo_scan_start_time,
 			      ktime_sub_ns(ktime_get_boottime_ns(),
 					   5ULL * NSEC_PER_SEC)),
 		"Last MLO scan was too long ago, can't select links\n"))

drivers/net/wireless/intel/iwlwifi/mld/notif.c

···
  * at least enough bytes to cover the structure listed in the CMD_VER_ENTRY.
  */
 
+CMD_VERSIONS(scan_start_notif,
+	     CMD_VER_ENTRY(1, iwl_umac_scan_start))
 CMD_VERSIONS(scan_complete_notif,
 	     CMD_VER_ENTRY(1, iwl_umac_scan_complete))
 CMD_VERSIONS(scan_iter_complete_notif,
···
 			   link_id)
 DEFINE_SIMPLE_CANCELLATION(roc, iwl_roc_notif, activity)
 DEFINE_SIMPLE_CANCELLATION(scan_complete, iwl_umac_scan_complete, uid)
+DEFINE_SIMPLE_CANCELLATION(scan_start, iwl_umac_scan_start, uid)
 DEFINE_SIMPLE_CANCELLATION(probe_resp_data, iwl_probe_resp_data_notif,
 			   mac_id)
 DEFINE_SIMPLE_CANCELLATION(uapsd_misbehaving_ap, iwl_uapsd_misbehaving_ap_notif,
···
 			     RX_HANDLER_SYNC)
 	RX_HANDLER_NO_OBJECT(LEGACY_GROUP, BA_NOTIF, compressed_ba_notif,
 			     RX_HANDLER_SYNC)
+	RX_HANDLER_OF_SCAN(LEGACY_GROUP, SCAN_START_NOTIFICATION_UMAC,
+			   scan_start_notif)
 	RX_HANDLER_OF_SCAN(LEGACY_GROUP, SCAN_COMPLETE_UMAC,
 			   scan_complete_notif)
 	RX_HANDLER_NO_OBJECT(LEGACY_GROUP, SCAN_ITERATION_COMPLETE_UMAC,

drivers/net/wireless/intel/iwlwifi/mld/scan.c

···
 	    params->flags & NL80211_SCAN_FLAG_COLOCATED_6GHZ)
 		flags |= IWL_UMAC_SCAN_GEN_FLAGS_V2_TRIGGER_UHB_SCAN;
 
+	if (scan_status == IWL_MLD_SCAN_INT_MLO)
+		flags |= IWL_UMAC_SCAN_GEN_FLAGS_V2_NTF_START;
+
 	if (params->enable_6ghz_passive)
 		flags |= IWL_UMAC_SCAN_GEN_FLAGS_V2_6GHZ_PASSIVE_SCAN;
 
···
 	ret = _iwl_mld_single_scan_start(mld, vif, req, &ies,
 					 IWL_MLD_SCAN_INT_MLO);
 
-	if (!ret)
-		mld->scan.last_mlo_scan_time = ktime_get_boottime_ns();
-
 	IWL_DEBUG_SCAN(mld, "Internal MLO scan: ret=%d\n", ret);
 }
 
···
 {
 	IWL_DEBUG_SCAN(mld, "Scheduled scan results\n");
 	ieee80211_sched_scan_results(mld->hw);
+}
+
+void iwl_mld_handle_scan_start_notif(struct iwl_mld *mld,
+				     struct iwl_rx_packet *pkt)
+{
+	struct iwl_umac_scan_complete *notif = (void *)pkt->data;
+	u32 uid = le32_to_cpu(notif->uid);
+
+	if (IWL_FW_CHECK(mld, uid >= ARRAY_SIZE(mld->scan.uid_status),
+			 "FW reports out-of-range scan UID %d\n", uid))
+		return;
+
+	if (IWL_FW_CHECK(mld, !(mld->scan.uid_status[uid] & mld->scan.status),
+			 "FW reports scan UID %d we didn't trigger\n", uid))
+		return;
+
+	IWL_DEBUG_SCAN(mld, "Scan started: uid=%u type=%u\n", uid,
+		       mld->scan.uid_status[uid]);
+	if (IWL_FW_CHECK(mld, mld->scan.uid_status[uid] != IWL_MLD_SCAN_INT_MLO,
+			 "FW reports scan start notification %d we didn't trigger\n",
+			 mld->scan.uid_status[uid]))
+		return;
+
+	mld->scan.last_mlo_scan_start_time = ktime_get_boottime_ns();
 }
 
 void iwl_mld_handle_scan_complete_notif(struct iwl_mld *mld,

drivers/net/wireless/intel/iwlwifi/mld/scan.h

···
 void iwl_mld_handle_match_found_notif(struct iwl_mld *mld,
 				      struct iwl_rx_packet *pkt);
 
+void iwl_mld_handle_scan_start_notif(struct iwl_mld *mld,
+				     struct iwl_rx_packet *pkt);
+
 void iwl_mld_handle_scan_complete_notif(struct iwl_mld *mld,
 					struct iwl_rx_packet *pkt);
 
···
  *	in jiffies.
  * @last_start_time_jiffies: stores the last start time in jiffies
  *	(interface up/reset/resume).
- * @last_mlo_scan_time: start time of the last MLO scan in nanoseconds since
- *	boot.
+ * @last_mlo_scan_start_time: start time of the last MLO scan in nanoseconds
+ * since boot.
  */
 struct iwl_mld_scan {
 	/* Add here fields that need clean up on restart */
···
 	u8 cmd_ver;
 	unsigned long last_6ghz_passive_jiffies;
 	unsigned long last_start_time_jiffies;
-	u64 last_mlo_scan_time;
+	u64 last_mlo_scan_start_time;
 };
 
 /**

drivers/net/wireless/intel/iwlwifi/mvm/d3.c

···
 	if (IS_ERR_OR_NULL(vif))
 		return;
 
-	if (len < sizeof(struct iwl_scan_offload_match_info)) {
+	if (len < sizeof(struct iwl_scan_offload_match_info) + matches_len) {
 		IWL_ERR(mvm, "Invalid scan match info notification\n");
 		return;
 	}

drivers/net/wireless/intel/iwlwifi/mvm/fw.c

···
 	u8 cmd_ver;
 	int ret;
 
-	if (mvm->trans->mac_cfg->device_family < IWL_DEVICE_FAMILY_AX210) {
+	if (mvm->trans->mac_cfg->device_family < IWL_DEVICE_FAMILY_AX210 ||
+	    !mvm->trans->cfg->uhb_supported) {
 		IWL_DEBUG_RADIO(mvm, "UATS feature is not supported\n");
 		return;
 	}

drivers/net/wireless/microchip/wilc1000/hif.c

···
 	u32 index = 0;
 	u32 i, scan_timeout;
 	u8 *buffer;
-	u8 valuesize = 0;
+	u32 valuesize = 0;
 	u8 *search_ssid_vals = NULL;
 	const u8 ch_list_len = request->n_channels;
 	struct host_if_drv *hif_drv = vif->hif_drv;

drivers/net/wireless/ti/wl1251/tx.c

···
 	int hdrlen;
 	u8 *frame;
 
-	skb = wl->tx_frames[result->id];
-	if (skb == NULL) {
-		wl1251_error("SKB for packet %d is NULL", result->id);
+	if (unlikely(result->id >= ARRAY_SIZE(wl->tx_frames) ||
+		     wl->tx_frames[result->id] == NULL)) {
+		wl1251_error("invalid packet id %u", result->id);
 		return;
 	}
+
+	skb = wl->tx_frames[result->id];
 
 	info = IEEE80211_SKB_CB(skb);
 

drivers/net/wireless/virtual/virt_wifi.c

···
 	eth_hw_addr_inherit(dev, priv->lowerdev);
 	netif_stacked_transfer_operstate(priv->lowerdev, dev);
 
-	SET_NETDEV_DEV(dev, &priv->lowerdev->dev);
 	dev->ieee80211_ptr = kzalloc_obj(*dev->ieee80211_ptr);
 
 	if (!dev->ieee80211_ptr) {

drivers/nfc/pn533/uart.c

···
 
 	timer_delete(&dev->cmd_timeout);
 	for (i = 0; i < count; i++) {
+		if (unlikely(!skb_tailroom(dev->recv_skb)))
+			skb_trim(dev->recv_skb, 0);
+
 		skb_put_u8(dev->recv_skb, *data++);
 		if (!pn532_uart_rx_is_frame(dev->recv_skb))
 			continue;

drivers/pci/pwrctrl/core.c

···
 			struct device_node *remote __free(device_node) =
 				of_graph_get_remote_port_parent(endpoint);
 			if (remote) {
-				if (of_pci_supply_present(remote))
+				if (of_pci_supply_present(remote)) {
+					of_node_put(endpoint);
 					return true;
+				}
 			}
 		}
 	}

drivers/pci/pwrctrl/pci-pwrctrl-pwrseq.c

···
 	return pwrseq_power_off(pwrseq->pwrseq);
 }
 
-static void devm_pwrseq_pwrctrl_power_off(void *data)
-{
-	struct pwrseq_pwrctrl *pwrseq = data;
-
-	pwrseq_pwrctrl_power_off(&pwrseq->pwrctrl);
-}
-
 static int pwrseq_pwrctrl_probe(struct platform_device *pdev)
 {
 	const struct pwrseq_pwrctrl_pdata *pdata;
···
 	if (IS_ERR(pwrseq->pwrseq))
 		return dev_err_probe(dev, PTR_ERR(pwrseq->pwrseq),
 				     "Failed to get the power sequencer\n");
-
-	ret = devm_add_action_or_reset(dev, devm_pwrseq_pwrctrl_power_off,
-				       pwrseq);
-	if (ret)
-		return ret;
 
 	pwrseq->pwrctrl.power_on = pwrseq_pwrctrl_power_on;
 	pwrseq->pwrctrl.power_off = pwrseq_pwrctrl_power_off;

drivers/pci/pwrctrl/slot.c

···
 {
 	struct slot_pwrctrl *slot = data;
 
-	slot_pwrctrl_power_off(&slot->pwrctrl);
 	regulator_bulk_free(slot->num_supplies, slot->supplies);
 }
 

drivers/phy/Kconfig

···
 menu "PHY Subsystem"
 
 config PHY_COMMON_PROPS
-	bool
+	bool "PHY common properties" if KUNIT_ALL_TESTS
 	help
 	  This parses properties common between generic PHYs and Ethernet PHYs.
 
···
 
 config PHY_COMMON_PROPS_TEST
 	tristate "KUnit tests for PHY common props" if !KUNIT_ALL_TESTS
-	select PHY_COMMON_PROPS
-	depends on KUNIT
+	depends on KUNIT && PHY_COMMON_PROPS
 	default KUNIT_ALL_TESTS
 	help
 	  This builds KUnit tests for the PHY common property API.

drivers/phy/freescale/phy-fsl-lynx-28g.c

···
 
 	for (i = 0; i < LYNX_28G_NUM_LANE; i++) {
 		lane = &priv->lane[i];
+		if (!lane->phy)
+			continue;
 
 		mutex_lock(&lane->phy->mutex);
 

drivers/phy/qualcomm/phy-qcom-qmp-ufs.c

···
 	QMP_PHY_INIT_CFG(QPHY_V6_PCS_UFS_MULTI_LANE_CTRL1, 0x02),
 	QMP_PHY_INIT_CFG(QPHY_V6_PCS_UFS_TX_MID_TERM_CTRL1, 0x43),
 	QMP_PHY_INIT_CFG(QPHY_V6_PCS_UFS_PCS_CTRL1, 0xc1),
+	QMP_PHY_INIT_CFG(QPHY_V6_PCS_UFS_PLL_CNTL, 0x33),
 	QMP_PHY_INIT_CFG(QPHY_V6_PCS_UFS_TX_LARGE_AMP_DRV_LVL, 0x0f),
 	QMP_PHY_INIT_CFG(QPHY_V6_PCS_UFS_RX_SIGDET_CTRL2, 0x68),
 	QMP_PHY_INIT_CFG(QPHY_V6_PCS_UFS_TX_POST_EMP_LVL_S4, 0x0e),
···
 };
 
 static const struct qmp_phy_init_tbl sm8650_ufsphy_g4_pcs[] = {
-	QMP_PHY_INIT_CFG(QPHY_V6_PCS_UFS_PLL_CNTL, 0x13),
 	QMP_PHY_INIT_CFG(QPHY_V6_PCS_UFS_TX_HSGEAR_CAPABILITY, 0x04),
 	QMP_PHY_INIT_CFG(QPHY_V6_PCS_UFS_RX_HSGEAR_CAPABILITY, 0x04),
 };
 
 static const struct qmp_phy_init_tbl sm8650_ufsphy_g5_pcs[] = {
-	QMP_PHY_INIT_CFG(QPHY_V6_PCS_UFS_PLL_CNTL, 0x33),
 	QMP_PHY_INIT_CFG(QPHY_V6_PCS_UFS_TX_HSGEAR_CAPABILITY, 0x05),
 	QMP_PHY_INIT_CFG(QPHY_V6_PCS_UFS_RX_HSGEAR_CAPABILITY, 0x05),
 	QMP_PHY_INIT_CFG(QPHY_V6_PCS_UFS_RX_HS_G5_SYNC_LENGTH_CAPABILITY, 0x4d),

drivers/phy/spacemit/phy-k1-usb2.c

···
 #define  PHY_CLK_HSTXP_EN		BIT(3)		/* clock hstxp enable */
 #define  PHY_HSTXP_MODE			BIT(4)		/* 0: force en_txp to be 1; 1: no force */
 
+#define PHY_K1_HS_HOST_DISC		0x40
+#define  PHY_K1_HS_HOST_DISC_CLR		BIT(0)
+
 #define PHY_PLL_DIV_CFG			0x98
 #define  PHY_FDIV_FRACT_8_15		GENMASK(7, 0)
 #define  PHY_FDIV_FRACT_16_19		GENMASK(11, 8)
···
 	return 0;
 }
 
+static int spacemit_usb2phy_disconnect(struct phy *phy, int port)
+{
+	struct spacemit_usb2phy *sphy = phy_get_drvdata(phy);
+
+	regmap_update_bits(sphy->regmap_base, PHY_K1_HS_HOST_DISC,
+			   PHY_K1_HS_HOST_DISC_CLR, PHY_K1_HS_HOST_DISC_CLR);
+
+	return 0;
+}
+
 static const struct phy_ops spacemit_usb2phy_ops = {
 	.init = spacemit_usb2phy_init,
 	.exit = spacemit_usb2phy_exit,
+	.disconnect = spacemit_usb2phy_disconnect,
 	.owner = THIS_MODULE,
 };
 

drivers/phy/ti/phy-j721e-wiz.c

···
 			dev_err(dev,
 				"%s: Reading \"reg\" from \"%s\" failed: %d\n",
 				__func__, subnode->name, ret);
+			of_node_put(serdes);
 			return ret;
 		}
 		of_property_read_u32(subnode, "cdns,num-lanes", &num_lanes);
···
 		}
 	}
 
+	of_node_put(serdes);
 	return 0;
 }
 

drivers/scsi/ibmvscsi/ibmvfc.c

···
 	switch (mad_status) {
 	case IBMVFC_MAD_SUCCESS:
 		ibmvfc_dbg(vhost, "Discover Targets succeeded\n");
-		vhost->num_targets = be32_to_cpu(rsp->num_written);
+		vhost->num_targets = min_t(u32, be32_to_cpu(rsp->num_written),
+					   max_targets);
 		ibmvfc_set_host_action(vhost, IBMVFC_HOST_ACTION_ALLOC_TGTS);
 		break;
 	case IBMVFC_MAD_FAILED:

drivers/scsi/scsi_transport_sas.c

···
 		break;
 
 	default:
-		if (channel < shost->max_channel) {
+		if (channel <= shost->max_channel) {
 			res = scsi_scan_host_selected(shost, channel, id, lun,
 						      SCSI_SCAN_MANUAL);
 		} else {

drivers/scsi/ses.c

···
 	unsigned char *type_ptr = ses_dev->page1_types;
 	unsigned char *desc_ptr = ses_dev->page2 + 8;
 
-	if (ses_recv_diag(sdev, 2, ses_dev->page2, ses_dev->page2_len) < 0)
+	if (ses_recv_diag(sdev, 2, ses_dev->page2, ses_dev->page2_len))
 		return NULL;
 
 	for (i = 0; i < ses_dev->page1_num_types; i++, type_ptr += 4) {

drivers/spi/spi-fsl-lpspi.c

···
 		enable_irq(irq);
 	}
 
-	ret = devm_spi_register_controller(&pdev->dev, controller);
+	ret = spi_register_controller(controller);
 	if (ret < 0) {
 		dev_err_probe(&pdev->dev, ret, "spi_register_controller error\n");
 		goto free_dma;
···
 	struct fsl_lpspi_data *fsl_lpspi =
 				spi_controller_get_devdata(controller);
 
+	spi_unregister_controller(controller);
 	fsl_lpspi_dma_exit(controller);
 
 	pm_runtime_dont_use_autosuspend(fsl_lpspi->dev);

drivers/spi/spi-meson-spicc.c

···
 
 	/* Disable SPI */
 	writel(0, spicc->base + SPICC_CONREG);
-
-	spi_controller_put(spicc->host);
 }
 
 static const struct meson_spicc_data meson_spicc_gx_data = {

drivers/spi/spi-sn-f-ospi.c

···
 	u32 num_cs = OSPI_NUM_CS;
 	int ret;
 
-	ctlr = spi_alloc_host(dev, sizeof(*ospi));
+	ctlr = devm_spi_alloc_host(dev, sizeof(*ospi));
 	if (!ctlr)
 		return -ENOMEM;
 
···
 	platform_set_drvdata(pdev, ospi);
 
 	ospi->base = devm_platform_ioremap_resource(pdev, 0);
-	if (IS_ERR(ospi->base)) {
-		ret = PTR_ERR(ospi->base);
-		goto err_put_ctlr;
-	}
+	if (IS_ERR(ospi->base))
+		return PTR_ERR(ospi->base);
 
 	ospi->clk = devm_clk_get_enabled(dev, NULL);
-	if (IS_ERR(ospi->clk)) {
-		ret = PTR_ERR(ospi->clk);
-		goto err_put_ctlr;
-	}
+	if (IS_ERR(ospi->clk))
+		return PTR_ERR(ospi->clk);
 
-	mutex_init(&ospi->mlock);
+	ret = devm_mutex_init(dev, &ospi->mlock);
+	if (ret)
+		return ret;
 
 	ret = f_ospi_init(ospi);
 	if (ret)
-		goto err_destroy_mutex;
+		return ret;
 
-	ret = devm_spi_register_controller(dev, ctlr);
-	if (ret)
-		goto err_destroy_mutex;
-
-	return 0;
-
-err_destroy_mutex:
-	mutex_destroy(&ospi->mlock);
-
-err_put_ctlr:
-	spi_controller_put(ctlr);
-
-	return ret;
-}
-
-static void f_ospi_remove(struct platform_device *pdev)
-{
-	struct f_ospi *ospi = platform_get_drvdata(pdev);
-
-	mutex_destroy(&ospi->mlock);
+	return devm_spi_register_controller(dev, ctlr);
 }
 
 static const struct of_device_id f_ospi_dt_ids[] = {
···
 		.of_match_table = f_ospi_dt_ids,
 	},
 	.probe = f_ospi_probe,
-	.remove = f_ospi_remove,
 };
 module_platform_driver(f_ospi_driver);
 

drivers/spi/spi.c

···
 	struct spi_device	*spi = to_spi_device(dev);
 
 	spi_controller_put(spi->controller);
-	kfree(spi->driver_override);
 	free_percpu(spi->pcpu_statistics);
 	kfree(spi);
 }
···
 				     struct device_attribute *a,
 				     const char *buf, size_t count)
 {
-	struct spi_device *spi = to_spi_device(dev);
 	int ret;
 
-	ret = driver_set_override(dev, &spi->driver_override, buf, count);
+	ret = __device_set_driver_override(dev, buf, count);
 	if (ret)
 		return ret;
 
···
 static ssize_t driver_override_show(struct device *dev,
 				    struct device_attribute *a, char *buf)
 {
-	const struct spi_device *spi = to_spi_device(dev);
-	ssize_t len;
-
-	device_lock(dev);
-	len = sysfs_emit(buf, "%s\n", spi->driver_override ? : "");
-	device_unlock(dev);
-	return len;
+	guard(spinlock)(&dev->driver_override.lock);
+	return sysfs_emit(buf, "%s\n", dev->driver_override.name ?: "");
 }
 static DEVICE_ATTR_RW(driver_override);
 
···
 {
 	const struct spi_device	*spi = to_spi_device(dev);
 	const struct spi_driver	*sdrv = to_spi_driver(drv);
+	int ret;
 
 	/* Check override first, and if set, only use the named driver */
-	if (spi->driver_override)
-		return strcmp(spi->driver_override, drv->name) == 0;
+	ret = device_match_driver_override(dev, drv);
+	if (ret >= 0)
+		return ret;
 
 	/* Attempt an OF style match */
 	if (of_driver_match_device(dev, drv))
···
 	if (ret)
 		return ret;
 
-	return devm_add_action_or_reset(dev, devm_spi_unregister_controller, ctlr);
+	/*
+	 * Prevent controller from being freed by spi_unregister_controller()
+	 * if devm_add_action_or_reset() fails for a non-devres allocated
+	 * controller.
+	 */
+	spi_controller_get(ctlr);
 
+	ret = devm_add_action_or_reset(dev, devm_spi_unregister_controller, ctlr);
+
+	if (ret == 0 || ctlr->devm_allocated)
+		spi_controller_put(ctlr);
+
+	return ret;
 }
 EXPORT_SYMBOL_GPL(devm_spi_register_controller);
 

drivers/target/loopback/tcm_loop.c

···
 #include <linux/slab.h>
 #include <linux/types.h>
 #include <linux/configfs.h>
+#include <linux/blk-mq.h>
 #include <scsi/scsi.h>
 #include <scsi/scsi_tcq.h>
 #include <scsi/scsi_host.h>
···
 	return (ret == TMR_FUNCTION_COMPLETE) ? SUCCESS : FAILED;
 }
 
+static bool tcm_loop_flush_work_iter(struct request *rq, void *data)
+{
+	struct scsi_cmnd *sc = blk_mq_rq_to_pdu(rq);
+	struct tcm_loop_cmd *tl_cmd = scsi_cmd_priv(sc);
+	struct se_cmd *se_cmd = &tl_cmd->tl_se_cmd;
+
+	flush_work(&se_cmd->work);
+	return true;
+}
+
 static int tcm_loop_target_reset(struct scsi_cmnd *sc)
 {
 	struct tcm_loop_hba *tl_hba;
 	struct tcm_loop_tpg *tl_tpg;
+	struct Scsi_Host *sh = sc->device->host;
+	int ret;
 
 	/*
 	 * Locate the tcm_loop_hba_t pointer
 	 */
-	tl_hba = *(struct tcm_loop_hba **)shost_priv(sc->device->host);
+	tl_hba = *(struct tcm_loop_hba **)shost_priv(sh);
 	if (!tl_hba) {
 		pr_err("Unable to perform device reset without active I_T Nexus\n");
 		return FAILED;
···
 	 * Locate the tl_tpg pointer from TargetID in sc->device->id
 	 */
 	tl_tpg = &tl_hba->tl_hba_tpgs[sc->device->id];
-	if (tl_tpg) {
-		tl_tpg->tl_transport_status = TCM_TRANSPORT_ONLINE;
-		return SUCCESS;
-	}
-	return FAILED;
+	if (!tl_tpg)
+		return FAILED;
+
+	/*
+	 * Issue a LUN_RESET to drain all commands that the target core
+	 * knows about.  This handles commands not yet marked CMD_T_COMPLETE.
+	 */
+	ret = tcm_loop_issue_tmr(tl_tpg, sc->device->lun, 0, TMR_LUN_RESET);
+	if (ret != TMR_FUNCTION_COMPLETE)
+		return FAILED;
+
+	/*
+	 * Flush any deferred target core completion work that may still be
+	 * queued.  Commands that already had CMD_T_COMPLETE set before the TMR
+	 * are skipped by the TMR drain, but their async completion work
+	 * (transport_lun_remove_cmd → percpu_ref_put, release_cmd → scsi_done)
+	 * may still be pending in target_completion_wq.
+	 *
+	 * The SCSI EH will reuse in-flight scsi_cmnd structures for recovery
+	 * commands (e.g. TUR) immediately after this handler returns SUCCESS —
+	 * if deferred work is still pending, the memset in queuecommand would
+	 * zero the se_cmd while the work accesses it, leaking the LUN
+	 * percpu_ref and hanging configfs unlink forever.
+	 *
+	 * Use blk_mq_tagset_busy_iter() to find all started requests and
+	 * flush_work() on each — the same pattern used by mpi3mr, scsi_debug,
+	 * and other SCSI drivers to drain outstanding commands during reset.
+	 */
+	blk_mq_tagset_busy_iter(&sh->tag_set, tcm_loop_flush_work_iter, NULL);
+
+	tl_tpg->tl_transport_status = TCM_TRANSPORT_ONLINE;
+	return SUCCESS;
 }
 
 static const struct scsi_host_template tcm_loop_driver_template = {

drivers/target/target_core_file.c

···
 	ssize_t len = 0;
 	int ret = 0, i;
 
-	aio_cmd = kmalloc_flex(*aio_cmd, bvecs, sgl_nents);
+	aio_cmd = kzalloc_flex(*aio_cmd, bvecs, sgl_nents);
 	if (!aio_cmd)
 		return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
 

drivers/thermal/intel/int340x_thermal/processor_thermal_soc_slider.c

···
 
 static void set_soc_power_profile(struct proc_thermal_device *proc_priv, int slider)
 {
+	u8 offset;
 	u64 val;
 
 	val = read_soc_slider(proc_priv);
 	val &= ~SLIDER_MASK;
 	val |= FIELD_PREP(SLIDER_MASK, slider) | BIT(SLIDER_ENABLE_BIT);
 
+	if (slider == SOC_SLIDER_VALUE_MINIMUM || slider == SOC_SLIDER_VALUE_MAXIMUM)
+		offset = 0;
+	else
+		offset = slider_offset;
+
 	/* Set the slider offset from module params */
 	val &= ~SLIDER_OFFSET_MASK;
-	val |= FIELD_PREP(SLIDER_OFFSET_MASK, slider_offset);
+	val |= FIELD_PREP(SLIDER_OFFSET_MASK, offset);
 
 	write_soc_slider(proc_priv, val);
 }

drivers/vfio/pci/vfio_pci_dmabuf.c

···
 	 */
 	ret = dma_buf_fd(priv->dmabuf, get_dma_buf.open_flags);
 	if (ret < 0)
-		goto err_dma_buf;
+		dma_buf_put(priv->dmabuf);
+
 	return ret;
 
-err_dma_buf:
-	dma_buf_put(priv->dmabuf);
 err_dev_put:
 	vfio_device_put_registration(&vdev->vdev);
 err_free_phys:

drivers/virt/coco/tdx-guest/tdx-guest.c

···
 #define GET_QUOTE_SUCCESS		0
 #define GET_QUOTE_IN_FLIGHT		0xffffffffffffffff
 
+#define TDX_QUOTE_MAX_LEN		(GET_QUOTE_BUF_SIZE - sizeof(struct tdx_quote_buf))
+
 /* struct tdx_quote_buf: Format of Quote request buffer.
  * @version: Quote format version, filled by TD.
  * @status: Status code of Quote request, filled by VMM.
···
 	u8 *buf;
 	struct tdx_quote_buf *quote_buf = quote_data;
 	struct tsm_report_desc *desc = &report->desc;
+	u32 out_len;
 	int ret;
 	u64 err;
 
···
 		return ret;
 	}
 
-	buf = kvmemdup(quote_buf->data, quote_buf->out_len, GFP_KERNEL);
+	out_len = READ_ONCE(quote_buf->out_len);
+
+	if (out_len > TDX_QUOTE_MAX_LEN)
+		return -EFBIG;
+
+	buf = kvmemdup(quote_buf->data, out_len, GFP_KERNEL);
 	if (!buf)
 		return -ENOMEM;
 
 	report->outblob = buf;
-	report->outblob_len = quote_buf->out_len;
+	report->outblob_len = out_len;
 
 	/*
 	 * TODO: parse the PEM-formatted cert chain out of the quote buffer when

drivers/xen/privcmd.c

···
 
 static void __exit privcmd_exit(void)
 {
+	if (!xen_initial_domain())
+		unregister_xenstore_notifier(&xenstore_notifier);
+
 	privcmd_ioeventfd_exit();
 	privcmd_irqfd_exit();
 	misc_deregister(&privcmd_dev);

fs/btrfs/block-group.c

···
 		for (int i = 0; i < BTRFS_SPACE_INFO_SUB_GROUP_MAX; i++) {
 			if (space_info->sub_group[i]) {
 				check_removing_space_info(space_info->sub_group[i]);
-				kfree(space_info->sub_group[i]);
+				btrfs_sysfs_remove_space_info(space_info->sub_group[i]);
 				space_info->sub_group[i] = NULL;
 			}
 		}

fs/btrfs/disk-io.c

···
 
 	if (mirror_num >= 0 &&
 	    btrfs_super_bytenr(sb) != btrfs_sb_offset(mirror_num)) {
-		btrfs_err(fs_info, "super offset mismatch %llu != %u",
-			  btrfs_super_bytenr(sb), BTRFS_SUPER_INFO_OFFSET);
+		btrfs_err(fs_info, "super offset mismatch %llu != %llu",
+			  btrfs_super_bytenr(sb), btrfs_sb_offset(mirror_num));
 		ret = -EINVAL;
 	}
 

fs/btrfs/tree-log.c

···
 			    struct inode *inode, bool log_inode_only,
 			    u64 logged_isize)
 {
+	u64 gen = BTRFS_I(inode)->generation;
 	u64 flags;
 
 	if (log_inode_only) {
-		/* set the generation to zero so the recover code
-		 * can tell the difference between an logging
-		 * just to say 'this inode exists' and a logging
-		 * to say 'update this inode with these values'
+		/*
+		 * Set the generation to zero so the recover code can tell the
+		 * difference between a logging just to say 'this inode exists'
+		 * and a logging to say 'update this inode with these values'.
+		 * But only if the inode was not already logged before.
+		 * We access ->logged_trans directly since it was already set
+		 * up in the call chain by btrfs_log_inode(), and data_race()
+		 * to avoid false alerts from KCSAN and since it was set already
+		 * and one can set it to 0 since that only happens on eviction
+		 * and we are holding a ref on the inode.
 		 */
-		btrfs_set_inode_generation(leaf, item, 0);
+		ASSERT(data_race(BTRFS_I(inode)->logged_trans) > 0);
+		if (data_race(BTRFS_I(inode)->logged_trans) < trans->transid)
+			gen = 0;
+
 		btrfs_set_inode_size(leaf, item, logged_isize);
 	} else {
-		btrfs_set_inode_generation(leaf, item, BTRFS_I(inode)->generation);
 		btrfs_set_inode_size(leaf, item, inode->i_size);
 	}
+
+	btrfs_set_inode_generation(leaf, item, gen);
 
 	btrfs_set_inode_uid(leaf, item, i_uid_read(inode));
 	btrfs_set_inode_gid(leaf, item, i_gid_read(inode));
···
 	return 0;
 }
 
-static int logged_inode_size(struct btrfs_root *log, struct btrfs_inode *inode,
-			     struct btrfs_path *path, u64 *size_ret)
+static int get_inode_size_to_log(struct btrfs_trans_handle *trans,
+				 struct btrfs_inode *inode,
+				 struct btrfs_path *path, u64 *size_ret)
 {
 	struct btrfs_key key;
+	struct btrfs_inode_item *item;
 	int ret;
 
 	key.objectid = btrfs_ino(inode);
 	key.type = BTRFS_INODE_ITEM_KEY;
 	key.offset = 0;
 
-	ret = btrfs_search_slot(NULL, log, &key, path, 0, 0);
-	if (ret < 0) {
-		return ret;
-	} else if (ret > 0) {
-		*size_ret = 0;
-	} else {
-		struct btrfs_inode_item *item;
+	/*
+	 * Our caller called inode_logged(), so logged_trans is up to date.
+	 * Use data_race() to silence any warning from KCSAN. Once logged_trans
+	 * is set, it can only be reset to 0 after inode eviction.
+	 */
+	if (data_race(inode->logged_trans) == trans->transid) {
+		ret = btrfs_search_slot(NULL, inode->root->log_root, &key, path, 0, 0);
+	} else if (inode->generation < trans->transid) {
+		path->search_commit_root = true;
+		path->skip_locking = true;
+		ret = btrfs_search_slot(NULL, inode->root, &key, path, 0, 0);
+		path->search_commit_root = false;
+		path->skip_locking = false;
 
-		item = btrfs_item_ptr(path->nodes[0], path->slots[0],
-				      struct btrfs_inode_item);
-		*size_ret = btrfs_inode_size(path->nodes[0], item);
-		/*
-		 * If the in-memory inode's i_size is smaller then the inode
-		 * size stored in the btree, return the inode's i_size, so
-		 * that we get a correct inode size after replaying the log
-		 * when before a power failure we had a shrinking truncate
-		 * followed by addition of a new name (rename / new hard link).
-		 * Otherwise return the inode size from the btree, to avoid
-		 * data loss when replaying a log due to previously doing a
-		 * write that expands the inode's size and logging a new name
-		 * immediately after.
-		 */
-		if (*size_ret > inode->vfs_inode.i_size)
-			*size_ret = inode->vfs_inode.i_size;
+	} else {
+		*size_ret = 0;
+		return 0;
 	}
+
+	/*
+	 * If the inode was logged before or is from a past transaction, then
+	 * its inode item must exist in the log root or in the commit root.
+	 */
+	ASSERT(ret <= 0);
+	if (WARN_ON_ONCE(ret > 0))
+		ret = -ENOENT;
+
+	if (ret < 0)
+		return ret;
+
+	item = btrfs_item_ptr(path->nodes[0], path->slots[0],
+			      struct btrfs_inode_item);
+	*size_ret = btrfs_inode_size(path->nodes[0], item);
+	/*
+	 * If the in-memory inode's i_size is smaller then the inode size stored
+	 * in the btree, return the inode's i_size, so that we get a correct
+	 * inode size after replaying the log when before a power failure we had
+	 * a shrinking truncate followed by addition of a new name (rename / new
+	 * hard link). Otherwise return the inode size from the btree, to avoid
+	 * data loss when replaying a log due to previously doing a write that
+	 * expands the inode's size and logging a new name immediately after.
+	 */
+	if (*size_ret > inode->vfs_inode.i_size)
+		*size_ret = inode->vfs_inode.i_size;
 
 	btrfs_release_path(path);
 	return 0;
···
 			ret = drop_inode_items(trans, log, path, inode,
 					       BTRFS_XATTR_ITEM_KEY);
 	} else {
-		if (inode_only == LOG_INODE_EXISTS && ctx->logged_before) {
+		if (inode_only == LOG_INODE_EXISTS) {
 			/*
 			 * Make sure the new inode item we write to the log has
 			 * the same isize as the current one (if it exists).
···
 			 * (zeroes), as if an expanding truncate happened,
 			 * instead of getting a file of 4Kb only.
 			 */
-			ret = logged_inode_size(log, inode, path, &logged_isize);
+			ret = get_inode_size_to_log(trans, inode, path, &logged_isize);
 			if (ret)
 				goto out_unlock;
 		}

fs/btrfs/volumes.c

···
 		smp_rmb();
 
 		ret = update_dev_stat_item(trans, device);
-		if (!ret)
-			atomic_sub(stats_cnt, &device->dev_stats_ccnt);
+		if (ret)
+			break;
+		atomic_sub(stats_cnt, &device->dev_stats_ccnt);
 	}
 	mutex_unlock(&fs_devices->device_list_mutex);
 

fs/btrfs/zlib.c

···
 	}
 	/* Queue the remaining part of the folio. */
 	if (workspace->strm.total_out > bio->bi_iter.bi_size) {
-		u32 cur_len = offset_in_folio(out_folio, workspace->strm.total_out);
+		const u32 cur_len = workspace->strm.total_out - bio->bi_iter.bi_size;
+
+		ASSERT(cur_len <= folio_size(out_folio));
 
 		if (!bio_add_folio(bio, out_folio, cur_len, 0)) {
 			ret = -E2BIG;

fs/ext4/Makefile

···
 
 ext4-$(CONFIG_EXT4_FS_POSIX_ACL)	+= acl.o
 ext4-$(CONFIG_EXT4_FS_SECURITY)		+= xattr_security.o
-ext4-inode-test-objs			+= inode-test.o
-obj-$(CONFIG_EXT4_KUNIT_TESTS)		+= ext4-inode-test.o
+ext4-test-objs				+= inode-test.o mballoc-test.o \
+					   extents-test.o
+obj-$(CONFIG_EXT4_KUNIT_TESTS)		+= ext4-test.o
 ext4-$(CONFIG_FS_VERITY)		+= verity.o
 ext4-$(CONFIG_FS_ENCRYPTION)		+= crypto.o

fs/ext4/crypto.c

···
 	 */
 
 	if (handle) {
+		/*
+		 * Since the inode is new it is ok to pass the
+		 * XATTR_CREATE flag. This is necessary to match the
+		 * remaining journal credits check in the set_handle
+		 * function with the credits allocated for the new
+		 * inode.
+		 */
 		res = ext4_xattr_set_handle(handle, inode,
 					    EXT4_XATTR_INDEX_ENCRYPTION,
 					    EXT4_XATTR_NAME_ENCRYPTION_CONTEXT,
-					    ctx, len, 0);
+					    ctx, len, XATTR_CREATE);
 		if (!res) {
 			ext4_set_inode_flag(inode, EXT4_INODE_ENCRYPT);
 			ext4_clear_inode_state(inode,

fs/ext4/ext4.h

···
 	struct proc_dir_entry *s_proc;
 	struct kobject s_kobj;
 	struct completion s_kobj_unregister;
+	struct mutex s_error_notify_mutex; /* protects sysfs_notify vs kobject_del */
 	struct super_block *s_sb;
 	struct buffer_head *s_mmp_bh;
 
···
 extern int ext4_block_write_begin(handle_t *handle, struct folio *folio,
 				  loff_t pos, unsigned len,
 				  get_block_t *get_block);
+
+#if IS_ENABLED(CONFIG_EXT4_KUNIT_TESTS)
+#define EXPORT_SYMBOL_FOR_EXT4_TEST(sym) \
+	EXPORT_SYMBOL_FOR_MODULES(sym, "ext4-test")
+#endif
 #endif	/* __KERNEL__ */
 
 #endif	/* _EXT4_H */

fs/ext4/ext4_extents.h

···
 				     0xffff);
 }
 
+extern int __ext4_ext_dirty(const char *where, unsigned int line,
+			    handle_t *handle, struct inode *inode,
+			    struct ext4_ext_path *path);
+extern int ext4_ext_zeroout(struct inode *inode, struct ext4_extent *ex);
+#if IS_ENABLED(CONFIG_EXT4_KUNIT_TESTS)
+extern int ext4_ext_space_root_idx_test(struct inode *inode, int check);
+extern struct ext4_ext_path *ext4_split_convert_extents_test(
+				handle_t *handle, struct inode *inode,
+				struct ext4_map_blocks *map,
+				struct ext4_ext_path *path,
+				int flags, unsigned int *allocated);
+#endif
 #endif /* _EXT4_EXTENTS */
 

fs/ext4/extents-test.c

···
 
 static void extents_kunit_exit(struct kunit *test)
 {
-	struct ext4_sb_info *sbi = k_ctx.k_ei->vfs_inode.i_sb->s_fs_info;
+	struct super_block *sb = k_ctx.k_ei->vfs_inode.i_sb;
+	struct ext4_sb_info *sbi = sb->s_fs_info;
 
+	ext4_es_unregister_shrinker(sbi);
 	kfree(sbi);
 	kfree(k_ctx.k_ei);
 	kfree(k_ctx.k_data);
···
 	eh->eh_depth = 0;
 	eh->eh_entries = cpu_to_le16(1);
 	eh->eh_magic = EXT4_EXT_MAGIC;
-	eh->eh_max =
-		cpu_to_le16(ext4_ext_space_root_idx(&k_ctx.k_ei->vfs_inode, 0));
+	eh->eh_max = cpu_to_le16(ext4_ext_space_root_idx_test(
+					&k_ctx.k_ei->vfs_inode, 0));
 	eh->eh_generation = 0;
 
 	/*
···
 
 	switch (param->type) {
 	case TEST_SPLIT_CONVERT:
-		path = ext4_split_convert_extents(NULL, inode, &map, path,
-						  param->split_flags, NULL);
+		path = ext4_split_convert_extents_test(NULL, inode, &map,
+					path, param->split_flags, NULL);
 		break;
 	case TEST_CREATE_BLOCKS:
 		ext4_map_create_blocks_helper(test, inode, &map, param->split_flags);

fs/ext4/extents.c

···
  *  - ENOMEM
  *  - EIO
  */
-static int __ext4_ext_dirty(const char *where, unsigned int line,
-			    handle_t *handle, struct inode *inode,
-			    struct ext4_ext_path *path)
+int __ext4_ext_dirty(const char *where, unsigned int line,
+		     handle_t *handle, struct inode *inode,
+		     struct ext4_ext_path *path)
 {
 	int err;
 
···
 	err = ext4_ext_get_access(handle, inode, path + k);
 	if (err)
 		return err;
+	if (unlikely(path[k].p_idx > EXT_LAST_INDEX(path[k].p_hdr))) {
+		EXT4_ERROR_INODE(inode,
+				 "path[%d].p_idx %p > EXT_LAST_INDEX %p",
+				 k, path[k].p_idx,
+				 EXT_LAST_INDEX(path[k].p_hdr));
+		return -EFSCORRUPTED;
+	}
 	path[k].p_idx->ei_block = border;
 	err = ext4_ext_dirty(handle, inode, path + k);
 	if (err)
···
 		err = ext4_ext_get_access(handle, inode, path + k);
 		if (err)
 			goto clean;
+		if (unlikely(path[k].p_idx > EXT_LAST_INDEX(path[k].p_hdr))) {
+			EXT4_ERROR_INODE(inode,
+					 "path[%d].p_idx %p > EXT_LAST_INDEX %p",
+					 k, path[k].p_idx,
+					 EXT_LAST_INDEX(path[k].p_hdr));
+			err = -EFSCORRUPTED;
+			goto clean;
+		}
 		path[k].p_idx->ei_block = border;
 		err = ext4_ext_dirty(handle, inode, path + k);
 		if (err)
···
 }
 
 /* FIXME!! we need to try to merge to left or right after zero-out  */
-static int ext4_ext_zeroout(struct inode *inode, struct ext4_extent *ex)
+int ext4_ext_zeroout(struct inode *inode, struct ext4_extent *ex)
 {
 	ext4_fsblk_t ee_pblock;
 	unsigned int ee_len;
···
 
 	insert_err = PTR_ERR(path);
 	err = 0;
+	if (insert_err != -ENOSPC && insert_err != -EDQUOT &&
+	    insert_err != -ENOMEM)
+		goto out_path;
 
 	/*
 	 * Get a new path to try to zeroout or fix the extent length.
···
 		goto out_path;
 	}
 
+	depth = ext_depth(inode);
+	ex = path[depth].p_ext;
+	if (!ex) {
+		EXT4_ERROR_INODE(inode,
+				 "bad extent address lblock: %lu, depth: %d pblock %llu",
+				 (unsigned long)ee_block, depth, path[depth].p_block);
+		err = -EFSCORRUPTED;
+		goto out;
+	}
+
 	err = ext4_ext_get_access(handle, inode, path + depth);
 	if (err)
 		goto out;
-
-	depth = ext_depth(inode);
-	ex = path[depth].p_ext;
 
 fix_extent_len:
 	ex->ee_len = orig_ex.ee_len;
···
 
 	ext4_ext_mark_initialized(ex);
 
-	ext4_ext_dirty(handle, inode, path + depth);
+	err = ext4_ext_dirty(handle, inode, path + depth);
 	if (err)
 		return err;
 
···
 	path = ext4_ext_insert_extent(handle, inode, path, &newex, flags);
 	if (IS_ERR(path)) {
 		err = PTR_ERR(path);
-		if (allocated_clusters) {
+		/*
+		 * Gracefully handle out of space conditions. If the filesystem
+		 * is inconsistent, we'll just leak allocated blocks to avoid
+		 * causing even more damage.
+		 */
+		if (allocated_clusters && (err == -EDQUOT || err == -ENOSPC)) {
 			int fb_flags = 0;
-
 			/*
 			 * free data blocks we just allocated.
 			 * not a good idea to call discard here directly,
···
 	return 0;
 }
 
-#ifdef CONFIG_EXT4_KUNIT_TESTS
-#include "extents-test.c"
+#if IS_ENABLED(CONFIG_EXT4_KUNIT_TESTS)
+int ext4_ext_space_root_idx_test(struct inode *inode, int check)
+{
+	return ext4_ext_space_root_idx(inode, check);
+}
+EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_ext_space_root_idx_test);
+
+struct ext4_ext_path *ext4_split_convert_extents_test(handle_t *handle,
+			struct inode *inode, struct ext4_map_blocks *map,
+			struct ext4_ext_path *path, int flags,
+			unsigned int *allocated)
+{
+	return ext4_split_convert_extents(handle, inode, map, path,
+					  flags, allocated);
+}
+EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_split_convert_extents_test);
+
+EXPORT_SYMBOL_FOR_EXT4_TEST(__ext4_ext_dirty);
+EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_ext_zeroout);
+EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_es_register_shrinker);
+EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_es_unregister_shrinker);
+EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_map_create_blocks);
+EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_es_init_tree);
+EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_es_lookup_extent);
+EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_es_insert_extent);
+EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_ext_insert_extent);
+EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_find_extent);
+EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_issue_zeroout);
+EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_map_query_blocks);
 #endif

fs/ext4/fast_commit.c

···
 	int ret = 0;
 
 	list_for_each_entry(ei, &sbi->s_fc_q[FC_Q_MAIN], i_fc_list) {
-		ret = jbd2_submit_inode_data(journal, ei->jinode);
+		ret = jbd2_submit_inode_data(journal, READ_ONCE(ei->jinode));
 		if (ret)
 			return ret;
 	}
 
 	list_for_each_entry(ei, &sbi->s_fc_q[FC_Q_MAIN], i_fc_list) {
-		ret = jbd2_wait_inode_data(journal, ei->jinode);
+		ret = jbd2_wait_inode_data(journal, READ_ONCE(ei->jinode));
 		if (ret)
 			return ret;
 	}
···
 	/* Immediately update the inode on disk. */
 	ret = ext4_handle_dirty_metadata(NULL, NULL, iloc.bh);
 	if (ret)
-		goto out;
+		goto out_brelse;
 	ret = sync_dirty_buffer(iloc.bh);
 	if (ret)
-		goto out;
+		goto out_brelse;
 	ret = ext4_mark_inode_used(sb, ino);
 	if (ret)
-		goto out;
+		goto out_brelse;
 
 	/* Given that we just wrote the inode on disk, this SHOULD succeed. */
 	inode = ext4_iget(sb, ino, EXT4_IGET_NORMAL);
 	if (IS_ERR(inode)) {
 		ext4_debug("Inode not found.");
-		return -EFSCORRUPTED;
+		inode = NULL;
+		ret = -EFSCORRUPTED;
+		goto out_brelse;
 	}
 
 	/*
···
 	ext4_inode_csum_set(inode, ext4_raw_inode(&iloc), EXT4_I(inode));
 	ret = ext4_handle_dirty_metadata(NULL, NULL, iloc.bh);
 	sync_dirty_buffer(iloc.bh);
+out_brelse:
 	brelse(iloc.bh);
 out:
 	iput(inode);
 	if (!ret)
 		blkdev_issue_flush(sb->s_bdev);
 
-	return 0;
+	return ret;
 }
 
 /*

fs/ext4/fsync.c

···
 				int datasync, bool *needs_barrier)
 {
 	struct inode *inode = file->f_inode;
+	struct writeback_control wbc = {
+		.sync_mode = WB_SYNC_ALL,
+		.nr_to_write = 0,
+	};
 	int ret;
 
 	ret = generic_buffers_fsync_noflush(file, start, end, datasync);
-	if (!ret)
-		ret = ext4_sync_parent(inode);
+	if (ret)
+		return ret;
+
+	/* Force writeout of inode table buffer to disk */
+	ret = ext4_write_inode(inode, &wbc);
+	if (ret)
+		return ret;
+
+	ret = ext4_sync_parent(inode);
+
 	if (test_opt(inode->i_sb, BARRIER))
 		*needs_barrier = true;
 

fs/ext4/ialloc.c

···
 	if (unlikely(!gdp))
 		return 0;
 
+	/* Inode was never used in this filesystem? */
+	if (ext4_has_group_desc_csum(sb) &&
+	    (gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_UNINIT) ||
+	     ino >= EXT4_INODES_PER_GROUP(sb) - ext4_itable_unused_count(sb, gdp)))
+		return 0;
+
 	bh = sb_find_get_block(sb, ext4_inode_table(sb, gdp) +
 		       (ino / inodes_per_block));
 	if (!bh || !buffer_uptodate(bh))

fs/ext4/inline.c

···
 		goto out;
 
 	len = min_t(size_t, ext4_get_inline_size(inode), i_size_read(inode));
-	BUG_ON(len > PAGE_SIZE);
+
+	if (len > PAGE_SIZE) {
+		ext4_error_inode(inode, __func__, __LINE__, 0,
+				 "inline size %zu exceeds PAGE_SIZE", len);
+		ret = -EFSCORRUPTED;
+		brelse(iloc.bh);
+		goto out;
+	}
+
 	kaddr = kmap_local_folio(folio, 0);
 	ret = ext4_read_inline_data(inode, kaddr, len, &iloc);
 	kaddr = folio_zero_tail(folio, len, kaddr + len);

fs/ext4/inode.c

···
 static inline int ext4_begin_ordered_truncate(struct inode *inode,
 					      loff_t new_size)
 {
+	struct jbd2_inode *jinode = READ_ONCE(EXT4_I(inode)->jinode);
+
 	trace_ext4_begin_ordered_truncate(inode, new_size);
 	/*
 	 * If jinode is zero, then we never opened the file for
···
 	 * jbd2_journal_begin_ordered_truncate() since there's no
 	 * outstanding writes we need to flush.
 	 */
-	if (!EXT4_I(inode)->jinode)
+	if (!jinode)
 		return 0;
 	return jbd2_journal_begin_ordered_truncate(EXT4_JOURNAL(inode),
-						   EXT4_I(inode)->jinode,
+						   jinode,
 						   new_size);
 }
 
···
 	if (EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL)
 		ext4_evict_ea_inode(inode);
 	if (inode->i_nlink) {
+		/*
+		 * If there's dirty page will lead to data loss, user
+		 * could see stale data.
+		 */
+		if (unlikely(!ext4_emergency_state(inode->i_sb) &&
+		    mapping_tagged(&inode->i_data, PAGECACHE_TAG_DIRTY)))
+			ext4_warning_inode(inode, "data will be lost");
+
 		truncate_inode_pages_final(&inode->i_data);
 
 		goto no_delete;
···
 			spin_unlock(&inode->i_lock);
 			return -ENOMEM;
 		}
-		ei->jinode = jinode;
-		jbd2_journal_init_jbd_inode(ei->jinode, inode);
+		jbd2_journal_init_jbd_inode(jinode, inode);
+		/*
+		 * Publish ->jinode only after it is fully initialized so that
+		 * readers never observe a partially initialized jbd2_inode.
+		 */
+		smp_wmb();
+		WRITE_ONCE(ei->jinode, jinode);
 		jinode = NULL;
 	}
 	spin_unlock(&inode->i_lock);
···
 			inode->i_op = &ext4_encrypted_symlink_inode_operations;
 		} else if (ext4_inode_is_fast_symlink(inode)) {
 			inode->i_op = &ext4_fast_symlink_inode_operations;
-			if (inode->i_size == 0 ||
-			    inode->i_size >= sizeof(ei->i_data) ||
-			    strnlen((char *)ei->i_data, inode->i_size + 1) !=
-								inode->i_size) {
-				ext4_error_inode(inode, function, line, 0,
-					"invalid fast symlink length %llu",
-					 (unsigned long long)inode->i_size);
-				ret = -EFSCORRUPTED;
-				goto bad_inode;
+
+			/*
+			 * Orphan cleanup can see inodes with i_size == 0
+			 * and i_data uninitialized. Skip size checks in
+			 * that case. This is safe because the first thing
+			 * ext4_evict_inode() does for fast symlinks is
+			 * clearing of i_data and i_size.
+			 */
+			if ((EXT4_SB(sb)->s_mount_state & EXT4_ORPHAN_FS)) {
+				if (inode->i_nlink != 0) {
+					ext4_error_inode(inode, function, line, 0,
+						"invalid orphan symlink nlink %d",
+						inode->i_nlink);
+					ret = -EFSCORRUPTED;
+					goto bad_inode;
+				}
+			} else {
+				if (inode->i_size == 0 ||
+				    inode->i_size >= sizeof(ei->i_data) ||
+				    strnlen((char *)ei->i_data, inode->i_size + 1) !=
+						inode->i_size) {
+					ext4_error_inode(inode, function, line, 0,
+						"invalid fast symlink length %llu",
+						(unsigned long long)inode->i_size);
+					ret = -EFSCORRUPTED;
+					goto bad_inode;
+				}
+				inode_set_cached_link(inode, (char *)ei->i_data,
+						      inode->i_size);
 			}
-			inode_set_cached_link(inode, (char *)ei->i_data,
-					      inode->i_size);
 		} else {
 			inode->i_op = &ext4_symlink_inode_operations;
 		}
···
 
 		if (attr->ia_size == inode->i_size)
 			inc_ivers = false;
+
+		/*
+		 * If file has inline data but new size exceeds inline capacity,
+		 * convert to extent-based storage first to prevent inconsistent
+		 * state (inline flag set but size exceeds inline capacity).
+		 */
+		if (ext4_has_inline_data(inode) &&
+		    attr->ia_size > EXT4_I(inode)->i_inline_size) {
+			error = ext4_convert_inline_data(inode);
+			if (error)
+				goto err_out;
+		}
 
 		if (shrink) {
 			if (ext4_should_order_data(inode)) {

fs/ext4/mballoc-test.c

···
 #include <linux/random.h>
 
 #include "ext4.h"
+#include "mballoc.h"
 
 struct mbt_grp_ctx {
 	struct buffer_head bitmap_bh;
···
 	if (state)
 		mb_set_bits(bitmap_bh->b_data, blkoff, len);
 	else
-		mb_clear_bits(bitmap_bh->b_data, blkoff, len);
+		mb_clear_bits_test(bitmap_bh->b_data, blkoff, len);
 
 	return 0;
 }
···
 
 	/* get block at goal */
 	ar.goal = ext4_group_first_block_no(sb, goal_group);
-	found = ext4_mb_new_blocks_simple(&ar, &err);
+	found = ext4_mb_new_blocks_simple_test(&ar, &err);
 	KUNIT_ASSERT_EQ_MSG(test, ar.goal, found,
 		"failed to alloc block at goal, expected %llu found %llu",
 		ar.goal, found);
 
 	/* get block after goal in goal group */
 	ar.goal = ext4_group_first_block_no(sb, goal_group);
-	found = ext4_mb_new_blocks_simple(&ar, &err);
+	found = ext4_mb_new_blocks_simple_test(&ar, &err);
 	KUNIT_ASSERT_EQ_MSG(test, ar.goal + EXT4_C2B(sbi, 1), found,
 		"failed to alloc block after goal in goal group, expected %llu found %llu",
 		ar.goal + 1, found);
···
 	/* get block after goal group */
 	mbt_ctx_mark_used(sb, goal_group, 0, EXT4_CLUSTERS_PER_GROUP(sb));
 	ar.goal = ext4_group_first_block_no(sb, goal_group);
-	found = ext4_mb_new_blocks_simple(&ar, &err);
+	found = ext4_mb_new_blocks_simple_test(&ar, &err);
 	KUNIT_ASSERT_EQ_MSG(test,
 		ext4_group_first_block_no(sb, goal_group + 1), found,
 		"failed to alloc block after goal group, expected %llu found %llu",
···
 	for (i = goal_group; i < ext4_get_groups_count(sb); i++)
 		mbt_ctx_mark_used(sb, i, 0, EXT4_CLUSTERS_PER_GROUP(sb));
 	ar.goal = ext4_group_first_block_no(sb, goal_group);
-	found = ext4_mb_new_blocks_simple(&ar, &err);
+	found = ext4_mb_new_blocks_simple_test(&ar, &err);
 	KUNIT_ASSERT_EQ_MSG(test,
 		ext4_group_first_block_no(sb, 0) + EXT4_C2B(sbi, 1), found,
 		"failed to alloc block before goal group, expected %llu found %llu",
···
 	for (i = 0; i < ext4_get_groups_count(sb); i++)
 		mbt_ctx_mark_used(sb, i, 0, EXT4_CLUSTERS_PER_GROUP(sb));
 	ar.goal = ext4_group_first_block_no(sb, goal_group);
-	found = ext4_mb_new_blocks_simple(&ar, &err);
+	found = ext4_mb_new_blocks_simple_test(&ar, &err);
 	KUNIT_ASSERT_NE_MSG(test, err, 0,
 		"unexpectedly get block when no block is available");
 }
···
 			continue;
 
 		bitmap = mbt_ctx_bitmap(sb, i);
-		bit = mb_find_next_zero_bit(bitmap, max, 0);
+		bit = mb_find_next_zero_bit_test(bitmap, max, 0);
 		KUNIT_ASSERT_EQ_MSG(test, bit, max,
 				    "free block on unexpected group %d", i);
 	}
 
 	bitmap = mbt_ctx_bitmap(sb, goal_group);
-	bit = mb_find_next_zero_bit(bitmap, max, 0);
+	bit = mb_find_next_zero_bit_test(bitmap, max, 0);
 	KUNIT_ASSERT_EQ(test, bit, start);
 
-	bit = mb_find_next_bit(bitmap, max, bit + 1);
+	bit = mb_find_next_bit_test(bitmap, max, bit + 1);
 	KUNIT_ASSERT_EQ(test, bit, start + len);
 }
 
···
 
 	block = ext4_group_first_block_no(sb, goal_group) +
 		EXT4_C2B(sbi, start);
-	ext4_free_blocks_simple(inode, block, len);
+	ext4_free_blocks_simple_test(inode, block, len);
 	validate_free_blocks_simple(test, sb, goal_group, start, len);
 	mbt_ctx_mark_used(sb, goal_group, 0, EXT4_CLUSTERS_PER_GROUP(sb));
 }
···
 
 	bitmap = mbt_ctx_bitmap(sb, TEST_GOAL_GROUP);
 	memset(bitmap, 0, sb->s_blocksize);
-	ret = ext4_mb_mark_diskspace_used(ac, NULL);
+	ret = ext4_mb_mark_diskspace_used_test(ac, NULL);
 	KUNIT_ASSERT_EQ(test, ret, 0);
 
 	max = EXT4_CLUSTERS_PER_GROUP(sb);
-	i = mb_find_next_bit(bitmap, max, 0);
+	i = mb_find_next_bit_test(bitmap, max, 0);
 	KUNIT_ASSERT_EQ(test, i, start);
-	i = mb_find_next_zero_bit(bitmap, max, i + 1);
+	i = mb_find_next_zero_bit_test(bitmap, max, i + 1);
 	KUNIT_ASSERT_EQ(test, i, start + len);
-	i = mb_find_next_bit(bitmap, max, i + 1);
+	i = mb_find_next_bit_test(bitmap, max, i + 1);
 	KUNIT_ASSERT_EQ(test, max, i);
 }
 
···
 	max = EXT4_CLUSTERS_PER_GROUP(sb);
 	bb_h = buddy + sbi->s_mb_offsets[1];
 
-	off = mb_find_next_zero_bit(bb, max, 0);
+	off = mb_find_next_zero_bit_test(bb, max, 0);
 	grp->bb_first_free = off;
 	while (off < max) {
 		grp->bb_counters[0]++;
 		grp->bb_free++;
 
-		if (!(off & 1) && !mb_test_bit(off + 1, bb)) {
+		if (!(off & 1) && !mb_test_bit_test(off + 1, bb)) {
 			grp->bb_free++;
 			grp->bb_counters[0]--;
-			mb_clear_bit(off >> 1, bb_h);
+			mb_clear_bit_test(off >> 1, bb_h);
 			grp->bb_counters[1]++;
 			grp->bb_largest_free_order = 1;
 			off++;
 		}
 
-		off = mb_find_next_zero_bit(bb, max, off + 1);
+		off = mb_find_next_zero_bit_test(bb, max, off + 1);
 	}
 
 	for (order = 1; order < MB_NUM_ORDERS(sb) - 1; order++) {
 		bb = buddy + sbi->s_mb_offsets[order];
 		bb_h = buddy + sbi->s_mb_offsets[order + 1];
 		max = max >> 1;
-		off = mb_find_next_zero_bit(bb, max, 0);
+		off = mb_find_next_zero_bit_test(bb, max, 0);
 
 		while (off < max) {
-			if (!(off & 1) && !mb_test_bit(off + 1, bb)) {
+			if (!(off & 1) && !mb_test_bit_test(off + 1, bb)) {
 				mb_set_bits(bb, off, 2);
 				grp->bb_counters[order] -= 2;
-				mb_clear_bit(off >> 1, bb_h);
+				mb_clear_bit_test(off >> 1, bb_h);
 				grp->bb_counters[order + 1]++;
 				grp->bb_largest_free_order = order + 1;
 				off++;
 			}
 
-			off = mb_find_next_zero_bit(bb, max, off + 1);
+			off = mb_find_next_zero_bit_test(bb, max, off + 1);
 		}
 	}
 
 	max = EXT4_CLUSTERS_PER_GROUP(sb);
-	off = mb_find_next_zero_bit(bitmap, max, 0);
+	off = mb_find_next_zero_bit_test(bitmap, max, 0);
 	while (off < max) {
 		grp->bb_fragments++;
 
-		off = mb_find_next_bit(bitmap, max, off + 1);
+		off = mb_find_next_bit_test(bitmap, max, off + 1);
 		if (off + 1 >= max)
 			break;
 
-		off = mb_find_next_zero_bit(bitmap, max, off + 1);
+		off = mb_find_next_zero_bit_test(bitmap, max, off + 1);
 	}
 }
 
···
 	/* needed by validation in ext4_mb_generate_buddy */
 	ext4_grp->bb_free = mbt_grp->bb_free;
 	memset(ext4_buddy, 0xff, sb->s_blocksize);
-	ext4_mb_generate_buddy(sb, ext4_buddy, bitmap, TEST_GOAL_GROUP,
+	ext4_mb_generate_buddy_test(sb, ext4_buddy, bitmap, TEST_GOAL_GROUP,
 			       ext4_grp);
 
 	KUNIT_ASSERT_EQ(test, memcmp(mbt_buddy, ext4_buddy, sb->s_blocksize),
···
 	ex.fe_group = TEST_GOAL_GROUP;
 
 	ext4_lock_group(sb, TEST_GOAL_GROUP);
-	mb_mark_used(e4b, &ex);
+	mb_mark_used_test(e4b, &ex);
 	ext4_unlock_group(sb, TEST_GOAL_GROUP);
 
 	mb_set_bits(bitmap, start, len);
···
 	memset(buddy, 0xff, sb->s_blocksize);
 	for (i = 0; i < MB_NUM_ORDERS(sb); i++)
 		grp->bb_counters[i] = 0;
-	ext4_mb_generate_buddy(sb, buddy, bitmap, 0, grp);
+	ext4_mb_generate_buddy_test(sb, buddy, bitmap, 0, grp);
 
 	KUNIT_ASSERT_EQ(test, memcmp(buddy, e4b->bd_buddy, sb->s_blocksize),
 			0);
···
 				bb_counters[MB_NUM_ORDERS(sb)]), GFP_KERNEL);
 	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, grp);
 
-	ret = ext4_mb_load_buddy(sb, TEST_GOAL_GROUP, &e4b);
+	ret = ext4_mb_load_buddy_test(sb, TEST_GOAL_GROUP, &e4b);
 	KUNIT_ASSERT_EQ(test, ret, 0);
 
 	grp->bb_free = EXT4_CLUSTERS_PER_GROUP(sb);
···
 		test_mb_mark_used_range(test, &e4b, ranges[i].start,
 					ranges[i].len, bitmap, buddy, grp);
 
-	ext4_mb_unload_buddy(&e4b);
+	ext4_mb_unload_buddy_test(&e4b);
 }
 
 static void
···
 		return;
 
 	ext4_lock_group(sb, e4b->bd_group);
-	mb_free_blocks(NULL, e4b, start, len);
+	mb_free_blocks_test(NULL, e4b, start, len);
 	ext4_unlock_group(sb, e4b->bd_group);
 
-	mb_clear_bits(bitmap, start, len);
+	mb_clear_bits_test(bitmap, start, len);
 	/* bypass bb_free validatoin in ext4_mb_generate_buddy */
 	grp->bb_free += len;
 	memset(buddy, 0xff, sb->s_blocksize);
 	for (i = 0; i < MB_NUM_ORDERS(sb); i++)
 		grp->bb_counters[i] = 0;
-	ext4_mb_generate_buddy(sb, buddy, bitmap, 0, grp);
+	ext4_mb_generate_buddy_test(sb, buddy, bitmap, 0, grp);
 
 	KUNIT_ASSERT_EQ(test, memcmp(buddy, e4b->bd_buddy, sb->s_blocksize),
 			0);
···
 				bb_counters[MB_NUM_ORDERS(sb)]), GFP_KERNEL);
 	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, grp);
 
-	ret = ext4_mb_load_buddy(sb, TEST_GOAL_GROUP, &e4b);
+	ret = ext4_mb_load_buddy_test(sb, TEST_GOAL_GROUP, &e4b);
 	KUNIT_ASSERT_EQ(test, ret, 0);
 
 	ex.fe_start = 0;
···
 	ex.fe_group = TEST_GOAL_GROUP;
 
 	ext4_lock_group(sb, TEST_GOAL_GROUP);
-	mb_mark_used(&e4b, &ex);
+	mb_mark_used_test(&e4b, &ex);
 	ext4_unlock_group(sb, TEST_GOAL_GROUP);
 
 	grp->bb_free = 0;
···
 		test_mb_free_blocks_range(test, &e4b, ranges[i].start,
 					  ranges[i].len, bitmap, buddy, grp);
 
-	ext4_mb_unload_buddy(&e4b);
+	ext4_mb_unload_buddy_test(&e4b);
 }
 
 #define COUNT_FOR_ESTIMATE 100000
···
 	if (sb->s_blocksize > PAGE_SIZE)
 		kunit_skip(test, "blocksize exceeds pagesize");
 
-	ret = ext4_mb_load_buddy(sb, TEST_GOAL_GROUP, &e4b);
+	ret = ext4_mb_load_buddy_test(sb, TEST_GOAL_GROUP, &e4b);
 	KUNIT_ASSERT_EQ(test, ret, 0);
 
 	ex.fe_group = TEST_GOAL_GROUP;
···
 			ex.fe_start = ranges[i].start;
 			ex.fe_len = ranges[i].len;
 			ext4_lock_group(sb, TEST_GOAL_GROUP);
-			mb_mark_used(&e4b, &ex);
+			mb_mark_used_test(&e4b, &ex);
 			ext4_unlock_group(sb, TEST_GOAL_GROUP);
 		}
 		end = jiffies;
···
 				continue;
 
 			ext4_lock_group(sb, TEST_GOAL_GROUP);
-			mb_free_blocks(NULL, &e4b, ranges[i].start,
+			mb_free_blocks_test(NULL, &e4b, ranges[i].start,
 				       ranges[i].len);
 			ext4_unlock_group(sb, TEST_GOAL_GROUP);
 		}
 	}
 
 	kunit_info(test, "costed jiffies %lu\n", all);
-	ext4_mb_unload_buddy(&e4b);
+	ext4_mb_unload_buddy_test(&e4b);
 }
 
 static const struct mbt_ext4_block_layout mbt_test_layouts[] = {

fs/ext4/mballoc.c

···
 
 	/* searching for the right group start from the goal value specified */
 	start = ac->ac_g_ex.fe_group;
+	if (start >= ngroups)
+		start = 0;
 	ac->ac_prefetch_grp = start;
 	ac->ac_prefetch_nr = 0;
 
···
 		return 0;
 
 	err = ext4_mb_load_buddy(ac->ac_sb, group, e4b);
-	if (err)
+	if (err) {
+		if (EXT4_MB_GRP_BBITMAP_CORRUPT(e4b->bd_info) &&
+		    !(ac->ac_flags & EXT4_MB_HINT_GOAL_ONLY))
+			return 0;
 		return err;
+	}
 
 	ext4_lock_group(ac->ac_sb, group);
 	if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(e4b->bd_info)))
···
 	rcu_read_unlock();
 	iput(sbi->s_buddy_cache);
 err_freesgi:
-	rcu_read_lock();
-	kvfree(rcu_dereference(sbi->s_group_info));
-	rcu_read_unlock();
+	kvfree(rcu_access_pointer(sbi->s_group_info));
 	return -ENOMEM;
 }
 
···
 	struct kmem_cache *cachep = get_groupinfo_cache(sb->s_blocksize_bits);
 	int count;
 
-	if (test_opt(sb, DISCARD)) {
-		/*
-		 * wait the discard work to drain all of ext4_free_data
-		 */
-		flush_work(&sbi->s_discard_work);
-		WARN_ON_ONCE(!list_empty(&sbi->s_discard_list));
-	}
+	/*
+	 * wait the discard work to drain all of ext4_free_data
+	 */
+	flush_work(&sbi->s_discard_work);
+	WARN_ON_ONCE(!list_empty(&sbi->s_discard_list));
 
-	if (sbi->s_group_info) {
+	group_info = rcu_access_pointer(sbi->s_group_info);
+	if (group_info) {
 		for (i = 0; i < ngroups; i++) {
 			cond_resched();
 			grinfo = ext4_get_group_info(sb, i);
···
 		num_meta_group_infos = (ngroups +
 				EXT4_DESC_PER_BLOCK(sb) - 1) >>
 			EXT4_DESC_PER_BLOCK_BITS(sb);
-		rcu_read_lock();
-		group_info = rcu_dereference(sbi->s_group_info);
 		for (i = 0; i < num_meta_group_infos; i++)
 			kfree(group_info[i]);
 		kvfree(group_info);
-		rcu_read_unlock();
 	}
 	ext4_mb_avg_fragment_size_destroy(sbi);
 	ext4_mb_largest_free_orders_destroy(sbi);
···
 
 #define EXT4_MB_BITMAP_MARKED_CHECK 0x0001
 #define EXT4_MB_SYNC_UPDATE 0x0002
-static int
+int
 ext4_mb_mark_context(handle_t *handle, struct super_block *sb, bool state,
 		     ext4_group_t group, ext4_grpblk_t blkoff,
 		     ext4_grpblk_t len, int flags, ext4_grpblk_t *ret_changed)
···
 	return error;
 }
 
-#ifdef CONFIG_EXT4_KUNIT_TESTS
-#include "mballoc-test.c"
+#if IS_ENABLED(CONFIG_EXT4_KUNIT_TESTS)
+void mb_clear_bits_test(void *bm, int cur, int len)
+{
+	 mb_clear_bits(bm, cur, len);
+}
+EXPORT_SYMBOL_FOR_EXT4_TEST(mb_clear_bits_test);
+
+ext4_fsblk_t
+ext4_mb_new_blocks_simple_test(struct ext4_allocation_request *ar,
+			       int *errp)
+{
+	return ext4_mb_new_blocks_simple(ar, errp);
+}
+EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_mb_new_blocks_simple_test);
+
+int mb_find_next_zero_bit_test(void *addr, int max, int start)
+{
+	return mb_find_next_zero_bit(addr, max, start);
+}
+EXPORT_SYMBOL_FOR_EXT4_TEST(mb_find_next_zero_bit_test);
+
+int mb_find_next_bit_test(void *addr, int max, int start)
+{
+	return mb_find_next_bit(addr, max, start);
+}
+EXPORT_SYMBOL_FOR_EXT4_TEST(mb_find_next_bit_test);
+
+void mb_clear_bit_test(int bit, void *addr)
+{
+	mb_clear_bit(bit, addr);
+}
+EXPORT_SYMBOL_FOR_EXT4_TEST(mb_clear_bit_test);
+
+int mb_test_bit_test(int bit, void *addr)
+{
+	return mb_test_bit(bit, addr);
+}
+EXPORT_SYMBOL_FOR_EXT4_TEST(mb_test_bit_test);
+
+int ext4_mb_mark_diskspace_used_test(struct ext4_allocation_context *ac,
+				     handle_t *handle)
+{
+	return ext4_mb_mark_diskspace_used(ac, handle);
+}
+EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_mb_mark_diskspace_used_test);
+
+int mb_mark_used_test(struct ext4_buddy *e4b, struct ext4_free_extent *ex)
+{
+	return mb_mark_used(e4b, ex);
+}
+EXPORT_SYMBOL_FOR_EXT4_TEST(mb_mark_used_test);
+
+void ext4_mb_generate_buddy_test(struct super_block *sb, void *buddy,
+				 void *bitmap, ext4_group_t group,
+				 struct ext4_group_info *grp)
+{
+	ext4_mb_generate_buddy(sb, buddy, bitmap, group, grp);
+}
+EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_mb_generate_buddy_test);
+
+int ext4_mb_load_buddy_test(struct super_block *sb, ext4_group_t group,
+			    struct ext4_buddy *e4b)
+{
+	return ext4_mb_load_buddy(sb, group, e4b);
+}
+EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_mb_load_buddy_test);
+
+void ext4_mb_unload_buddy_test(struct ext4_buddy *e4b)
+{
+	ext4_mb_unload_buddy(e4b);
+}
+EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_mb_unload_buddy_test);
+
+void mb_free_blocks_test(struct inode *inode, struct ext4_buddy *e4b,
+			 int first, int count)
+{
+	mb_free_blocks(inode, e4b, first, count);
+}
+EXPORT_SYMBOL_FOR_EXT4_TEST(mb_free_blocks_test);
+
+void ext4_free_blocks_simple_test(struct inode *inode, ext4_fsblk_t block,
+				  unsigned long count)
+{
+	return ext4_free_blocks_simple(inode, block, count);
+}
+EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_free_blocks_simple_test);
+
+EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_wait_block_bitmap);
+EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_mb_init);
+EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_get_group_desc);
+EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_count_free_clusters);
+EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_get_group_info);
+EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_free_group_clusters_set);
+EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_mb_release);
+EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_read_block_bitmap_nowait);
+EXPORT_SYMBOL_FOR_EXT4_TEST(mb_set_bits);
+EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_fc_init_inode);
+EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_mb_mark_context);
 #endif

fs/ext4/mballoc.h

···
 	ext4_mballoc_query_range_fn	formatter,
 	void				*priv);
 
+extern int ext4_mb_mark_context(handle_t *handle,
+		struct super_block *sb, bool state,
+		ext4_group_t group, ext4_grpblk_t blkoff,
+		ext4_grpblk_t len, int flags,
+		ext4_grpblk_t *ret_changed);
+#if IS_ENABLED(CONFIG_EXT4_KUNIT_TESTS)
+extern void mb_clear_bits_test(void *bm, int cur, int len);
+extern ext4_fsblk_t
+ext4_mb_new_blocks_simple_test(struct ext4_allocation_request *ar,
+			       int *errp);
+extern int mb_find_next_zero_bit_test(void *addr, int max, int start);
+extern int mb_find_next_bit_test(void *addr, int max, int start);
+extern void mb_clear_bit_test(int bit, void *addr);
+extern int mb_test_bit_test(int bit, void *addr);
+extern int
+ext4_mb_mark_diskspace_used_test(struct ext4_allocation_context *ac,
+				 handle_t *handle);
+extern int mb_mark_used_test(struct ext4_buddy *e4b,
+			     struct ext4_free_extent *ex);
+extern void ext4_mb_generate_buddy_test(struct super_block *sb,
+		void *buddy, void *bitmap, ext4_group_t group,
+		struct ext4_group_info *grp);
+extern int ext4_mb_load_buddy_test(struct super_block *sb,
+		ext4_group_t group, struct ext4_buddy *e4b);
+extern void ext4_mb_unload_buddy_test(struct ext4_buddy *e4b);
+extern void mb_free_blocks_test(struct inode *inode,
+		struct ext4_buddy *e4b, int first, int count);
+extern void ext4_free_blocks_simple_test(struct inode *inode,
+		ext4_fsblk_t block, unsigned long count);
+#endif
 #endif

fs/ext4/page-io.c

···
 		nr_to_submit++;
 	} while ((bh = bh->b_this_page) != head);
 
-	/* Nothing to submit? Just unlock the folio... */
-	if (!nr_to_submit)
+	if (!nr_to_submit) {
+		/*
+		 * We have nothing to submit. Just cycle the folio through
+		 * writeback state to properly update xarray tags.
+		 */
+		__folio_start_writeback(folio, keep_towrite);
+		folio_end_writeback(folio);
 		return 0;
+	}
 
 	bh = head = folio_buffers(folio);
 

fs/ext4/super.c

···
 	struct buffer_head **group_desc;
 	int i;
 
-	rcu_read_lock();
-	group_desc = rcu_dereference(sbi->s_group_desc);
+	group_desc = rcu_access_pointer(sbi->s_group_desc);
 	for (i = 0; i < sbi->s_gdb_count; i++)
 		brelse(group_desc[i]);
 	kvfree(group_desc);
-	rcu_read_unlock();
 }
 
 static void ext4_flex_groups_free(struct ext4_sb_info *sbi)
···
 	struct flex_groups **flex_groups;
 	int i;
 
-	rcu_read_lock();
-	flex_groups = rcu_dereference(sbi->s_flex_groups);
+	flex_groups = rcu_access_pointer(sbi->s_flex_groups);
 	if (flex_groups) {
 		for (i = 0; i < sbi->s_flex_groups_allocated; i++)
 			kvfree(flex_groups[i]);
 		kvfree(flex_groups);
 	}
-	rcu_read_unlock();
 }
 
 static void ext4_put_super(struct super_block *sb)
···
 	invalidate_inode_buffers(inode);
 	clear_inode(inode);
 	ext4_discard_preallocations(inode);
+	/*
+	 * We must remove the inode from the hash before ext4_free_inode()
+	 * clears the bit in inode bitmap as otherwise another process reusing
+	 * the inode will block in insert_inode_hash() waiting for inode
+	 * eviction to complete while holding transaction handle open, but
+	 * ext4_evict_inode() still running for that inode could block waiting
+	 * for transaction commit if the inode is marked as IS_SYNC => deadlock.
+	 *
+	 * Removing the inode from the hash here is safe. There are two cases
+	 * to consider:
+	 * 1) The inode still has references to it (i_nlink > 0). In that case
+	 * we are keeping the inode and once we remove the inode from the hash,
+	 * iget() can create the new inode structure for the same inode number
+	 * and we are fine with that as all IO on behalf of the inode is
+	 * finished.
+	 * 2) We are deleting the inode (i_nlink == 0). In that case inode
+	 * number cannot be reused until ext4_free_inode() clears the bit in
+	 * the inode bitmap, at which point all IO is done and reuse is fine
+	 * again.
+	 */
+	remove_inode_hash(inode);
 	ext4_es_remove_extent(inode, 0, EXT_MAX_BLOCKS);
 	dquot_drop(inode);
 	if (EXT4_I(inode)->jinode) {
···
 			 "extents feature\n");
 		return 0;
 	}
+	if (ext4_has_feature_bigalloc(sb) &&
+	    le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block)) {
+		ext4_msg(sb, KERN_WARNING,
+			 "bad geometry: bigalloc file system with non-zero "
+			 "first_data_block\n");
+		return 0;
+	}
 
 #if !IS_ENABLED(CONFIG_QUOTA) || !IS_ENABLED(CONFIG_QFMT_V2)
 	if (!readonly && (ext4_has_feature_quota(sb) ||
···
 
 	timer_setup(&sbi->s_err_report, print_daily_error_info, 0);
 	spin_lock_init(&sbi->s_error_lock);
+	mutex_init(&sbi->s_error_notify_mutex);
 	INIT_WORK(&sbi->s_sb_upd_work, update_super_work);
 
 	err = ext4_group_desc_init(sb, es, logical_sb_block, &first_not_zeroed);

fs/ext4/sysfs.c

···
 
 void ext4_notify_error_sysfs(struct ext4_sb_info *sbi)
 {
-	sysfs_notify(&sbi->s_kobj, NULL, "errors_count");
+	mutex_lock(&sbi->s_error_notify_mutex);
+	if (sbi->s_kobj.state_in_sysfs)
+		sysfs_notify(&sbi->s_kobj, NULL, "errors_count");
+	mutex_unlock(&sbi->s_error_notify_mutex);
 }
 
 static struct kobject *ext4_root;
···
 	int err;
 
 	init_completion(&sbi->s_kobj_unregister);
+	mutex_lock(&sbi->s_error_notify_mutex);
 	err = kobject_init_and_add(&sbi->s_kobj, &ext4_sb_ktype, ext4_root,
 				   "%s", sb->s_id);
+	mutex_unlock(&sbi->s_error_notify_mutex);
 	if (err) {
 		kobject_put(&sbi->s_kobj);
 		wait_for_completion(&sbi->s_kobj_unregister);
···
 
 	if (sbi->s_proc)
 		remove_proc_subtree(sb->s_id, ext4_proc_root);
+
+	mutex_lock(&sbi->s_error_notify_mutex);
 	kobject_del(&sbi->s_kobj);
+	mutex_unlock(&sbi->s_error_notify_mutex);
 }
 
 int __init ext4_init_sysfs(void)

fs/fs-writeback.c

···
 	}
 }
 
+static bool __sync_lazytime(struct inode *inode)
+{
+	spin_lock(&inode->i_lock);
+	if (!(inode_state_read(inode) & I_DIRTY_TIME)) {
+		spin_unlock(&inode->i_lock);
+		return false;
+	}
+	inode_state_clear(inode, I_DIRTY_TIME);
+	spin_unlock(&inode->i_lock);
+	inode->i_op->sync_lazytime(inode);
+	return true;
+}
+
 bool sync_lazytime(struct inode *inode)
 {
 	if (!(inode_state_read_once(inode) & I_DIRTY_TIME))
···
 
 	trace_writeback_lazytime(inode);
 	if (inode->i_op->sync_lazytime)
-		inode->i_op->sync_lazytime(inode);
-	else
-		mark_inode_dirty_sync(inode);
+		return __sync_lazytime(inode);
+	mark_inode_dirty_sync(inode);
 	return true;
 }
 
···
 		 * The mapping can appear untagged while still on-list since we
 		 * do not have the mapping lock. Skip it here, wb completion
 		 * will remove it.
-		 *
-		 * If the mapping does not have data integrity semantics,
-		 * there's no need to wait for the writeout to complete, as the
-		 * mapping cannot guarantee that data is persistently stored.
 		 */
-		if (!mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK) ||
-		    mapping_no_data_integrity(mapping))
+		if (!mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK))
 			continue;
 
 		spin_unlock_irq(&sb->s_inode_wblist_lock);
···
 	 */
 	if (bdi == &noop_backing_dev_info)
 		return;
+
+	/*
+	 * If the superblock has SB_I_NO_DATA_INTEGRITY set, there's no need to
+	 * wait for the writeout to complete, as the filesystem cannot guarantee
+	 * data persistence on sync. Just kick off writeback and return.
+	 */
+	if (sb->s_iflags & SB_I_NO_DATA_INTEGRITY) {
+		wakeup_flusher_threads_bdi(bdi, WB_REASON_SYNC);
+		return;
+	}
+
 	WARN_ON(!rwsem_is_locked(&sb->s_umount));
 
 	/* protect against inode wb switch, see inode_switch_wbs_work_fn() */

fs/fuse/file.c

···
 
 	inode->i_fop = &fuse_file_operations;
 	inode->i_data.a_ops = &fuse_file_aops;
-	if (fc->writeback_cache) {
+	if (fc->writeback_cache)
 		mapping_set_writeback_may_deadlock_on_reclaim(&inode->i_data);
-		mapping_set_no_data_integrity(&inode->i_data);
-	}
 
 	INIT_LIST_HEAD(&fi->write_files);
 	INIT_LIST_HEAD(&fi->queued_writes);

fs/fuse/inode.c

···
 	sb->s_export_op = &fuse_export_operations;
 	sb->s_iflags |= SB_I_IMA_UNVERIFIABLE_SIGNATURE;
 	sb->s_iflags |= SB_I_NOIDMAP;
+	sb->s_iflags |= SB_I_NO_DATA_INTEGRITY;
 	if (sb->s_user_ns != &init_user_ns)
 		sb->s_iflags |= SB_I_UNTRUSTED_MOUNTER;
 	sb->s_flags &= ~(SB_NOSEC | SB_I_VERSION);

fs/iomap/bio.c

···
 #include "internal.h"
 #include "trace.h"
 
-static void iomap_read_end_io(struct bio *bio)
+static DEFINE_SPINLOCK(failed_read_lock);
+static struct bio_list failed_read_list = BIO_EMPTY_LIST;
+
+static void __iomap_read_end_io(struct bio *bio)
 {
 	int error = blk_status_to_errno(bio->bi_status);
 	struct folio_iter fi;
···
 	bio_for_each_folio_all(fi, bio)
 		iomap_finish_folio_read(fi.folio, fi.offset, fi.length, error);
 	bio_put(bio);
+}
+
+static void
+iomap_fail_reads(
+	struct work_struct	*work)
+{
+	struct bio		*bio;
+	struct bio_list		tmp = BIO_EMPTY_LIST;
+	unsigned long		flags;
+
+	spin_lock_irqsave(&failed_read_lock, flags);
+	bio_list_merge_init(&tmp, &failed_read_list);
+	spin_unlock_irqrestore(&failed_read_lock, flags);
+
+	while ((bio = bio_list_pop(&tmp)) != NULL) {
+		__iomap_read_end_io(bio);
+		cond_resched();
+	}
+}
+
+static DECLARE_WORK(failed_read_work, iomap_fail_reads);
+
+static void iomap_fail_buffered_read(struct bio *bio)
+{
+	unsigned long flags;
+
+	/*
+	 * Bounce I/O errors to a workqueue to avoid nested i_lock acquisitions
+	 * in the fserror code.  The caller no longer owns the bio reference
+	 * after the spinlock drops.
+	 */
+	spin_lock_irqsave(&failed_read_lock, flags);
+	if (bio_list_empty(&failed_read_list))
+		WARN_ON_ONCE(!schedule_work(&failed_read_work));
+	bio_list_add(&failed_read_list, bio);
+	spin_unlock_irqrestore(&failed_read_lock, flags);
+}
+
+static void iomap_read_end_io(struct bio *bio)
+{
+	if (bio->bi_status) {
+		iomap_fail_buffered_read(bio);
+		return;
+	}
+
+	__iomap_read_end_io(bio);
 }
 
 static void iomap_bio_submit_read(struct iomap_read_folio_ctx *ctx)

fs/iomap/buffered-io.c

···
 	loff_t length = iomap_length(iter);
 	struct folio *folio = ctx->cur_folio;
 	size_t folio_len = folio_size(folio);
+	struct iomap_folio_state *ifs;
 	size_t poff, plen;
 	loff_t pos_diff;
 	int ret;
···
 		return iomap_iter_advance(iter, length);
 	}
 
-	ifs_alloc(iter->inode, folio, iter->flags);
+	ifs = ifs_alloc(iter->inode, folio, iter->flags);
 
 	length = min_t(loff_t, length, folio_len - offset_in_folio(folio, pos));
 	while (length) {
···
 
 			*bytes_submitted += plen;
 			/*
-			 * If the entire folio has been read in by the IO
-			 * helper, then the helper owns the folio and will end
-			 * the read on it.
+			 * Hand off folio ownership to the IO helper when:
+			 * 1) The entire folio has been submitted for IO, or
+			 * 2) There is no ifs attached to the folio
+			 *
+			 * Case (2) occurs when 1 << i_blkbits matches the folio
+			 * size but the underlying filesystem or block device
+			 * uses a smaller granularity for IO.
 			 */
-			if (*bytes_submitted == folio_len)
+			if (*bytes_submitted == folio_len || !ifs)
 				ctx->cur_folio = NULL;
 		}
 

fs/jbd2/checkpoint.c

···
 			 */
 			BUFFER_TRACE(bh, "queue");
 			get_bh(bh);
-			J_ASSERT_BH(bh, !buffer_jwrite(bh));
+			if (WARN_ON_ONCE(buffer_jwrite(bh))) {
+				put_bh(bh); /* drop the ref we just took */
+				spin_unlock(&journal->j_list_lock);
+				/* Clean up any previously batched buffers */
+				if (batch_count)
+					__flush_batch(journal, &batch_count);
+				jbd2_journal_abort(journal, -EFSCORRUPTED);
+				return -EFSCORRUPTED;
+			}
 			journal->j_chkpt_bhs[batch_count++] = bh;
 			transaction->t_chp_stats.cs_written++;
 			transaction->t_checkpoint_list = jh->b_cpnext;
···
 
 	if (!jbd2_journal_get_log_tail(journal, &first_tid, &blocknr))
 		return 1;
-	J_ASSERT(blocknr != 0);
+	if (WARN_ON_ONCE(blocknr == 0)) {
+		jbd2_journal_abort(journal, -EFSCORRUPTED);
+		return -EFSCORRUPTED;
+	}
 
 	/*
 	 * We need to make sure that any blocks that were recently written out

fs/mpage.c

···
 }
 
 /**
- * mpage_writepages - walk the list of dirty pages of the given address space & writepage() all of them
+ * __mpage_writepages - walk the list of dirty pages of the given address space
+ * 			& writepage() all of them
  * @mapping: address space structure to write
  * @wbc: subtract the number of written pages from *@wbc->nr_to_write
  * @get_block: the filesystem's block mapper function.
+ * @write_folio: handler to call for each folio before calling
+ *		 mpage_write_folio()
  *
  * This is a library function, which implements the writepages()
- * address_space_operation.
+ * address_space_operation. It calls @write_folio handler for each folio. If
+ * the handler returns value > 0, it calls mpage_write_folio() to do the
+ * folio writeback.
  */
 int
-mpage_writepages(struct address_space *mapping,
-		struct writeback_control *wbc, get_block_t get_block)
+__mpage_writepages(struct address_space *mapping,
+		   struct writeback_control *wbc, get_block_t get_block,
+		   int (*write_folio)(struct folio *folio,
+				      struct writeback_control *wbc))
 {
 	struct mpage_data mpd = {
 		.get_block	= get_block,
···
 	int error;
 
 	blk_start_plug(&plug);
-	while ((folio = writeback_iter(mapping, wbc, folio, &error)))
+	while ((folio = writeback_iter(mapping, wbc, folio, &error))) {
+		if (write_folio) {
+			error = write_folio(folio, wbc);
+			/*
+			 * == 0 means folio is handled, < 0 means error. In
+			 * both cases hand back control to writeback_iter()
+			 */
+			if (error <= 0)
+				continue;
+			/* Let mpage_write_folio() handle the folio. */
+		}
 		error = mpage_write_folio(wbc, folio, &mpd);
+	}
 	if (mpd.bio)
 		mpage_bio_submit_write(mpd.bio);
 	blk_finish_plug(&plug);
 	return error;
 }
-EXPORT_SYMBOL(mpage_writepages);
+EXPORT_SYMBOL(__mpage_writepages);

fs/namei.c

···
 EXPORT_SYMBOL(hashlen_string);
 
 /*
- * Calculate the length and hash of the path component, and
- * return the length as the result.
+ * hash_name - Calculate the length and hash of the path component
+ * @nd: the path resolution state
+ * @name: the pathname to read the component from
+ * @lastword: if the component fits in a single word, LAST_WORD_IS_DOT,
+ * LAST_WORD_IS_DOTDOT, or some other value depending on whether the
+ * component is '.', '..', or something else. Otherwise, @lastword is 0.
+ *
+ * Returns: a pointer to the terminating '/' or NUL character in @name.
  */
 static inline const char *hash_name(struct nameidata *nd,
 				    const char *name,

fs/netfs/buffered_read.c

···
 	spin_lock(&rreq->lock);
 	list_add_tail(&subreq->rreq_link, &stream->subrequests);
 	if (list_is_first(&subreq->rreq_link, &stream->subrequests)) {
-		stream->front = subreq;
 		if (!stream->active) {
-			stream->collected_to = stream->front->start;
+			stream->collected_to = subreq->start;
 			/* Store list pointers before active flag */
 			smp_store_release(&stream->active, true);
 		}

fs/netfs/direct_read.c

···
 		spin_lock(&rreq->lock);
 		list_add_tail(&subreq->rreq_link, &stream->subrequests);
 		if (list_is_first(&subreq->rreq_link, &stream->subrequests)) {
-			stream->front = subreq;
 			if (!stream->active) {
-				stream->collected_to = stream->front->start;
+				stream->collected_to = subreq->start;
 				/* Store list pointers before active flag */
 				smp_store_release(&stream->active, true);
 			}

fs/netfs/direct_write.c

···
 			netfs_prepare_write(wreq, stream, wreq->start + wreq->transferred);
 			subreq = stream->construct;
 			stream->construct = NULL;
-			stream->front = NULL;
 		}
 
 		/* Check if (re-)preparation failed. */
···
 		stream->sreq_max_segs	= INT_MAX;
 
 		netfs_get_subrequest(subreq, netfs_sreq_trace_get_resubmit);
-		stream->prepare_write(subreq);
 
-		__set_bit(NETFS_SREQ_IN_PROGRESS, &subreq->flags);
-		netfs_stat(&netfs_n_wh_retry_write_subreq);
+		if (stream->prepare_write) {
+			stream->prepare_write(subreq);
+			__set_bit(NETFS_SREQ_IN_PROGRESS, &subreq->flags);
+			netfs_stat(&netfs_n_wh_retry_write_subreq);
+		} else {
+			struct iov_iter source;
+
+			netfs_reset_iter(subreq);
+			source = subreq->io_iter;
+			netfs_reissue_write(stream, subreq, &source);
+		}
 	}
 
 	netfs_unbuffered_write_done(wreq);

fs/netfs/iterator.c

···
 }
 
 /*
+ * Select the span of a kvec iterator we're going to use.  Limit it by both
+ * maximum size and maximum number of segments.  Returns the size of the span
+ * in bytes.
+ */
+static size_t netfs_limit_kvec(const struct iov_iter *iter, size_t start_offset,
+			       size_t max_size, size_t max_segs)
+{
+	const struct kvec *kvecs = iter->kvec;
+	unsigned int nkv = iter->nr_segs, ix = 0, nsegs = 0;
+	size_t len, span = 0, n = iter->count;
+	size_t skip = iter->iov_offset + start_offset;
+
+	if (WARN_ON(!iov_iter_is_kvec(iter)) ||
+	    WARN_ON(start_offset > n) ||
+	    n == 0)
+		return 0;
+
+	while (n && ix < nkv && skip) {
+		len = kvecs[ix].iov_len;
+		if (skip < len)
+			break;
+		skip -= len;
+		n -= len;
+		ix++;
+	}
+
+	while (n && ix < nkv) {
+		len = min3(n, kvecs[ix].iov_len - skip, max_size);
+		span += len;
+		nsegs++;
+		ix++;
+		if (span >= max_size || nsegs >= max_segs)
+			break;
+		skip = 0;
+		n -= len;
+	}
+
+	return min(span, max_size);
+}
+
+/*
  * Select the span of an xarray iterator we're going to use.  Limit it by both
  * maximum size and maximum number of segments.  It is assumed that segments
  * can be larger than a page in size, provided they're physically contiguous.
···
 		return netfs_limit_bvec(iter, start_offset, max_size, max_segs);
 	if (iov_iter_is_xarray(iter))
 		return netfs_limit_xarray(iter, start_offset, max_size, max_segs);
+	if (iov_iter_is_kvec(iter))
+		return netfs_limit_kvec(iter, start_offset, max_size, max_segs);
 	BUG();
 }
 EXPORT_SYMBOL(netfs_limit_iter);

fs/netfs/read_collect.c

···
 	 * in progress.  The issuer thread may be adding stuff to the tail
 	 * whilst we're doing this.
 	 */
-	front = READ_ONCE(stream->front);
+	front = list_first_entry_or_null(&stream->subrequests,
+					 struct netfs_io_subrequest, rreq_link);
 	while (front) {
 		size_t transferred;
 
···
 		list_del_init(&front->rreq_link);
 		front = list_first_entry_or_null(&stream->subrequests,
 						 struct netfs_io_subrequest, rreq_link);
-		stream->front = front;
 		spin_unlock(&rreq->lock);
 		netfs_put_subrequest(remove,
 				     notes & ABANDON_SREQ ?

fs/netfs/read_retry.c

···
 		       from->start, from->transferred, from->len);
 
 		if (test_bit(NETFS_SREQ_FAILED, &from->flags) ||
-		    !test_bit(NETFS_SREQ_NEED_RETRY, &from->flags))
+		    !test_bit(NETFS_SREQ_NEED_RETRY, &from->flags)) {
+			subreq = from;
 			goto abandon;
+		}
 
 		list_for_each_continue(next, &stream->subrequests) {
 			subreq = list_entry(next, struct netfs_io_subrequest, rreq_link);
···
 				if (subreq == to)
 					break;
 			}
+			subreq = NULL;
 			continue;
 		}
 

fs/netfs/read_single.c

···
 	spin_lock(&rreq->lock);
 	list_add_tail(&subreq->rreq_link, &stream->subrequests);
 	trace_netfs_sreq(subreq, netfs_sreq_trace_added);
-	stream->front = subreq;
 	/* Store list pointers before active flag */
 	smp_store_release(&stream->active, true);
 	spin_unlock(&rreq->lock);

fs/netfs/write_collect.c

···
 		if (!smp_load_acquire(&stream->active))
 			continue;
 
-		front = stream->front;
+		front = list_first_entry_or_null(&stream->subrequests,
+						 struct netfs_io_subrequest, rreq_link);
 		while (front) {
 			trace_netfs_collect_sreq(wreq, front);
 			//_debug("sreq [%x] %llx %zx/%zx",
···
 			list_del_init(&front->rreq_link);
 			front = list_first_entry_or_null(&stream->subrequests,
 							 struct netfs_io_subrequest, rreq_link);
-			stream->front = front;
 			spin_unlock(&wreq->lock);
 			netfs_put_subrequest(remove,
 					     notes & SAW_FAILURE ?

fs/netfs/write_issue.c

···
 	spin_lock(&wreq->lock);
 	list_add_tail(&subreq->rreq_link, &stream->subrequests);
 	if (list_is_first(&subreq->rreq_link, &stream->subrequests)) {
-		stream->front = subreq;
 		if (!stream->active) {
-			stream->collected_to = stream->front->start;
+			stream->collected_to = subreq->start;
 			/* Write list pointers before active flag */
 			smp_store_release(&stream->active, true);
 		}

fs/overlayfs/copy_up.c

···
 		return -EOVERFLOW;
 
 	/*
-	 * With metacopy disabled, we fsync after final metadata copyup, for
+	 * With "fsync=strict", we fsync after final metadata copyup, for
 	 * both regular files and directories to get atomic copyup semantics
 	 * on filesystems that do not use strict metadata ordering (e.g. ubifs).
 	 *
-	 * With metacopy enabled we want to avoid fsync on all meta copyup
+	 * By default, we want to avoid fsync on all meta copyup, because
 	 * that will hurt performance of workloads such as chown -R, so we
 	 * only fsync on data copyup as legacy behavior.
 	 */
-	ctx.metadata_fsync = !OVL_FS(dentry->d_sb)->config.metacopy &&
+	ctx.metadata_fsync = ovl_should_sync_metadata(OVL_FS(dentry->d_sb)) &&
 			     (S_ISREG(ctx.stat.mode) || S_ISDIR(ctx.stat.mode));
 	ctx.metacopy = ovl_need_meta_copy_up(dentry, ctx.stat.mode, flags);
 

fs/overlayfs/overlayfs.h

···
 	OVL_VERITY_REQUIRE,
 };
 
+enum {
+	OVL_FSYNC_VOLATILE,
+	OVL_FSYNC_AUTO,
+	OVL_FSYNC_STRICT,
+};
+
 /*
  * The tuple (fh,uuid) is a universal unique identifier for a copy up origin,
  * where:
···
 static inline bool ovl_xino_warn(struct ovl_fs *ofs)
 {
 	return ofs->config.xino == OVL_XINO_ON;
+}
+
+static inline bool ovl_should_sync(struct ovl_fs *ofs)
+{
+	return ofs->config.fsync_mode != OVL_FSYNC_VOLATILE;
+}
+
+static inline bool ovl_should_sync_metadata(struct ovl_fs *ofs)
+{
+	return ofs->config.fsync_mode == OVL_FSYNC_STRICT;
+}
+
+static inline bool ovl_is_volatile(struct ovl_config *config)
+{
+	return config->fsync_mode == OVL_FSYNC_VOLATILE;
 }
 
 /*

fs/overlayfs/ovl_entry.h

···
 	int xino;
 	bool metacopy;
 	bool userxattr;
-	bool ovl_volatile;
+	int fsync_mode;
 };
 
 struct ovl_sb {
···
 		WARN_ON_ONCE(sb->s_type != &ovl_fs_type);
 
 	return (struct ovl_fs *)sb->s_fs_info;
-}
-
-static inline bool ovl_should_sync(struct ovl_fs *ofs)
-{
-	return !ofs->config.ovl_volatile;
 }
 
 static inline unsigned int ovl_numlower(struct ovl_entry *oe)

fs/overlayfs/params.c

···
 	Opt_xino,
 	Opt_metacopy,
 	Opt_verity,
+	Opt_fsync,
 	Opt_volatile,
 	Opt_override_creds,
 };
···
 	return OVL_VERITY_OFF;
 }
 
+static const struct constant_table ovl_parameter_fsync[] = {
+	{ "volatile",	OVL_FSYNC_VOLATILE },
+	{ "auto",	OVL_FSYNC_AUTO     },
+	{ "strict",	OVL_FSYNC_STRICT   },
+	{}
+};
+
+static const char *ovl_fsync_mode(struct ovl_config *config)
+{
+	return ovl_parameter_fsync[config->fsync_mode].name;
+}
+
+static int ovl_fsync_mode_def(void)
+{
+	return OVL_FSYNC_AUTO;
+}
+
 const struct fs_parameter_spec ovl_parameter_spec[] = {
 	fsparam_string_empty("lowerdir",    Opt_lowerdir),
 	fsparam_file_or_string("lowerdir+", Opt_lowerdir_add),
···
 	fsparam_enum("xino",                Opt_xino, ovl_parameter_xino),
 	fsparam_enum("metacopy",            Opt_metacopy, ovl_parameter_bool),
 	fsparam_enum("verity",              Opt_verity, ovl_parameter_verity),
+	fsparam_enum("fsync",               Opt_fsync, ovl_parameter_fsync),
 	fsparam_flag("volatile",            Opt_volatile),
 	fsparam_flag_no("override_creds",   Opt_override_creds),
 	{}
···
 	case Opt_verity:
 		config->verity_mode = result.uint_32;
 		break;
+	case Opt_fsync:
+		config->fsync_mode = result.uint_32;
+		break;
 	case Opt_volatile:
-		config->ovl_volatile = true;
+		config->fsync_mode = OVL_FSYNC_VOLATILE;
 		break;
 	case Opt_userxattr:
 		config->userxattr = true;
···
 	ofs->config.nfs_export		= ovl_nfs_export_def;
 	ofs->config.xino		= ovl_xino_def();
 	ofs->config.metacopy		= ovl_metacopy_def;
+	ofs->config.fsync_mode		= ovl_fsync_mode_def();
 
 	fc->s_fs_info		= ofs;
 	fc->fs_private		= ctx;
···
 		config->index = false;
 	}
 
-	if (!config->upperdir && config->ovl_volatile) {
+	if (!config->upperdir && ovl_is_volatile(config)) {
 		pr_info("option \"volatile\" is meaningless in a non-upper mount, ignoring it.\n");
-		config->ovl_volatile = false;
+		config->fsync_mode = ovl_fsync_mode_def();
 	}
 
 	if (!config->upperdir && config->uuid == OVL_UUID_ON) {
···
 		seq_printf(m, ",xino=%s", ovl_xino_mode(&ofs->config));
 	if (ofs->config.metacopy != ovl_metacopy_def)
 		seq_printf(m, ",metacopy=%s", str_on_off(ofs->config.metacopy));
-	if (ofs->config.ovl_volatile)
-		seq_puts(m, ",volatile");
+	if (ofs->config.fsync_mode != ovl_fsync_mode_def())
+		seq_printf(m, ",fsync=%s", ovl_fsync_mode(&ofs->config));
 	if (ofs->config.userxattr)
 		seq_puts(m, ",userxattr");
 	if (ofs->config.verity_mode != ovl_verity_mode_def())

fs/overlayfs/super.c

···
 	 * For volatile mount, create a incompat/volatile/dirty file to keep
 	 * track of it.
 	 */
-	if (ofs->config.ovl_volatile) {
+	if (ovl_is_volatile(&ofs->config)) {
 		err = ovl_create_volatile_dirty(ofs);
 		if (err < 0) {
 			pr_err("Failed to create volatile/dirty file.\n");

fs/overlayfs/util.c

···
 	if (!exportfs_can_decode_fh(sb->s_export_op))
 		return 0;
 
-	return sb->s_export_op->encode_fh ? -1 : FILEID_INO32_GEN;
+	if (sb->s_export_op->encode_fh == generic_encode_ino32_fh)
+		return FILEID_INO32_GEN;
+
+	return -1;
 }
 
 struct dentry *ovl_indexdir(struct super_block *sb)

fs/smb/client/Makefile

···
 # Build the SMB2 error mapping table from smb2status.h
 #
 $(obj)/smb2_mapping_table.c: $(src)/../common/smb2status.h \
-			    $(src)/gen_smb2_mapping
-	$(call cmd,gen_smb2_mapping)
+			     $(src)/gen_smb2_mapping FORCE
+	$(call if_changed,gen_smb2_mapping)
 
 $(obj)/smb2maperror.o: $(obj)/smb2_mapping_table.c
 
···
 
 obj-$(CONFIG_SMB_KUNIT_TESTS) += smb2maperror_test.o
 
-clean-files	+= smb2_mapping_table.c
+# Let Kbuild handle tracking and cleaning
+targets += smb2_mapping_table.c

fs/smb/server/oplock.c

···
 	spin_unlock(&lb->lb_lock);
 }
 
-static void lb_add(struct lease_table *lb)
+static struct lease_table *alloc_lease_table(struct oplock_info *opinfo)
 {
-	write_lock(&lease_list_lock);
-	list_add(&lb->l_entry, &lease_table_list);
-	write_unlock(&lease_list_lock);
+	struct lease_table *lb;
+
+	lb = kmalloc_obj(struct lease_table, KSMBD_DEFAULT_GFP);
+	if (!lb)
+		return NULL;
+
+	memcpy(lb->client_guid, opinfo->conn->ClientGUID,
+	       SMB2_CLIENT_GUID_SIZE);
+	INIT_LIST_HEAD(&lb->lease_list);
+	spin_lock_init(&lb->lb_lock);
+	return lb;
 }
 
 static int alloc_lease(struct oplock_info *opinfo, struct lease_ctx_info *lctx)
···
 	lease2->version = lease1->version;
 }
 
-static int add_lease_global_list(struct oplock_info *opinfo)
+static void add_lease_global_list(struct oplock_info *opinfo,
+				  struct lease_table *new_lb)
 {
 	struct lease_table *lb;
 
-	read_lock(&lease_list_lock);
+	write_lock(&lease_list_lock);
 	list_for_each_entry(lb, &lease_table_list, l_entry) {
 		if (!memcmp(lb->client_guid, opinfo->conn->ClientGUID,
 			    SMB2_CLIENT_GUID_SIZE)) {
 			opinfo->o_lease->l_lb = lb;
 			lease_add_list(opinfo);
-			read_unlock(&lease_list_lock);
-			return 0;
+			write_unlock(&lease_list_lock);
+			kfree(new_lb);
+			return;
 		}
 	}
-	read_unlock(&lease_list_lock);
 
-	lb = kmalloc_obj(struct lease_table, KSMBD_DEFAULT_GFP);
-	if (!lb)
-		return -ENOMEM;
-
-	memcpy(lb->client_guid, opinfo->conn->ClientGUID,
-	       SMB2_CLIENT_GUID_SIZE);
-	INIT_LIST_HEAD(&lb->lease_list);
-	spin_lock_init(&lb->lb_lock);
-	opinfo->o_lease->l_lb = lb;
+	opinfo->o_lease->l_lb = new_lb;
 	lease_add_list(opinfo);
-	lb_add(lb);
-	return 0;
+	list_add(&new_lb->l_entry, &lease_table_list);
+	write_unlock(&lease_list_lock);
 }
 
 static void set_oplock_level(struct oplock_info *opinfo, int level,
···
 	int err = 0;
 	struct oplock_info *opinfo = NULL, *prev_opinfo = NULL;
 	struct ksmbd_inode *ci = fp->f_ci;
+	struct lease_table *new_lb = NULL;
 	bool prev_op_has_lease;
 	__le32 prev_op_state = 0;
 
···
 	set_oplock_level(opinfo, req_op_level, lctx);
 
 out:
+	/*
+	 * Set o_fp before any publication so that concurrent readers
+	 * (e.g. find_same_lease_key() on the lease list) that
+	 * dereference opinfo->o_fp don't hit a NULL pointer.
+	 *
+	 * Keep the original publication order so concurrent opens can
+	 * still observe the in-flight grant via ci->m_op_list, but make
+	 * everything after opinfo_add() no-fail by preallocating any new
+	 * lease_table first.
+	 */
+	opinfo->o_fp = fp;
+	if (opinfo->is_lease) {
+		new_lb = alloc_lease_table(opinfo);
+		if (!new_lb) {
+			err = -ENOMEM;
+			goto err_out;
+		}
+	}
+
 	opinfo_count_inc(fp);
 	opinfo_add(opinfo, fp);
 
-	if (opinfo->is_lease) {
-		err = add_lease_global_list(opinfo);
-		if (err)
-			goto err_out;
-	}
+	if (opinfo->is_lease)
+		add_lease_global_list(opinfo, new_lb);
 
 	rcu_assign_pointer(fp->f_opinfo, opinfo);
-	opinfo->o_fp = fp;
 
 	return 0;
 err_out:
-	__free_opinfo(opinfo);
+	kfree(new_lb);
+	opinfo_put(opinfo);
 	return err;
 }
 

fs/smb/server/smb2pdu.c

···
 			if (sess->user && sess->user->flags & KSMBD_USER_FLAG_DELAY_SESSION)
 				try_delay = true;
 
-			sess->last_active = jiffies;
-			sess->state = SMB2_SESSION_EXPIRED;
+			/*
+			 * For binding requests, session belongs to another
+			 * connection. Do not expire it.
+			 */
+			if (!(req->Flags & SMB2_SESSION_REQ_FLAG_BINDING)) {
+				sess->last_active = jiffies;
+				sess->state = SMB2_SESSION_EXPIRED;
+			}
 			ksmbd_user_session_put(sess);
 			work->sess = NULL;
 			if (try_delay) {
···
 	d_info.wptr = (char *)rsp->Buffer;
 	d_info.rptr = (char *)rsp->Buffer;
 	d_info.out_buf_len =
-		smb2_calc_max_out_buf_len(work, 8,
-					  le32_to_cpu(req->OutputBufferLength));
+		smb2_calc_max_out_buf_len(work,
+				offsetof(struct smb2_query_directory_rsp, Buffer),
+				le32_to_cpu(req->OutputBufferLength));
 	if (d_info.out_buf_len < 0) {
 		rc = -EINVAL;
 		goto err_out;
···
 	}
 
 	buf_free_len =
-		smb2_calc_max_out_buf_len(work, 8,
-					  le32_to_cpu(req->OutputBufferLength));
+		smb2_calc_max_out_buf_len(work,
+				offsetof(struct smb2_query_info_rsp, Buffer),
+				le32_to_cpu(req->OutputBufferLength));
 	if (buf_free_len < 0)
 		return -EINVAL;
 
···
 	int conv_len;
 	char *filename;
 	u64 time;
-	int ret;
+	int ret, buf_free_len, filename_len;
+	struct smb2_query_info_req *req = ksmbd_req_buf_next(work);
 
 	if (!(fp->daccess & FILE_READ_ATTRIBUTES_LE)) {
 		ksmbd_debug(SMB, "no right to read the attributes : 0x%x\n",
···
 	filename = convert_to_nt_pathname(work->tcon->share_conf, &fp->filp->f_path);
 	if (IS_ERR(filename))
 		return PTR_ERR(filename);
+
+	filename_len = strlen(filename);
+	buf_free_len = smb2_calc_max_out_buf_len(work,
+			offsetof(struct smb2_query_info_rsp, Buffer) +
+			offsetof(struct smb2_file_all_info, FileName),
+			le32_to_cpu(req->OutputBufferLength));
+	if (buf_free_len < (filename_len + 1) * 2) {
+		kfree(filename);
+		return -EINVAL;
+	}
 
 	ret = vfs_getattr(&fp->filp->f_path, &stat, STATX_BASIC_STATS,
 			  AT_STATX_SYNC_AS_STAT);
···
 	file_info->Mode = fp->coption;
 	file_info->AlignmentRequirement = 0;
 	conv_len = smbConvertToUTF16((__le16 *)file_info->FileName, filename,
-				     PATH_MAX, conn->local_nls, 0);
+				     min(filename_len, PATH_MAX),
+				     conn->local_nls, 0);
 	conv_len *= 2;
 	file_info->FileNameLength = cpu_to_le32(conv_len);
 	rsp->OutputBufferLength =
···
 	file_info = (struct smb2_file_stream_info *)rsp->Buffer;
 
 	buf_free_len =
-		smb2_calc_max_out_buf_len(work, 8,
-					  le32_to_cpu(req->OutputBufferLength));
+		smb2_calc_max_out_buf_len(work,
+				offsetof(struct smb2_query_info_rsp, Buffer),
+				le32_to_cpu(req->OutputBufferLength));
 	if (buf_free_len < 0)
 		goto out;
 
···
 		rc = vfs_lock_file(filp, smb_lock->cmd, flock, NULL);
 skip:
 		if (smb_lock->flags & SMB2_LOCKFLAG_UNLOCK) {
+			locks_free_lock(flock);
+			kfree(smb_lock);
 			if (!rc) {
 				ksmbd_debug(SMB, "File unlocked\n");
 			} else if (rc == -ENOENT) {
 				rsp->hdr.Status = STATUS_NOT_LOCKED;
+				err = rc;
 				goto out;
 			}
-			locks_free_lock(flock);
-			kfree(smb_lock);
 		} else {
 			if (rc == FILE_LOCK_DEFERRED) {
 				void **argv;
···
 				spin_unlock(&work->conn->llist_lock);
 				ksmbd_debug(SMB, "successful in taking lock\n");
 			} else {
+				locks_free_lock(flock);
+				kfree(smb_lock);
+				err = rc;
 				goto out;
 			}
 		}
···
 		struct file_lock *rlock = NULL;
 
 		rlock = smb_flock_init(filp);
-		rlock->c.flc_type = F_UNLCK;
-		rlock->fl_start = smb_lock->start;
-		rlock->fl_end = smb_lock->end;
+		if (rlock) {
+			rlock->c.flc_type = F_UNLCK;
+			rlock->fl_start = smb_lock->start;
+			rlock->fl_end = smb_lock->end;
 
-		rc = vfs_lock_file(filp, F_SETLK, rlock, NULL);
-		if (rc)
-			pr_err("rollback unlock fail : %d\n", rc);
+			rc = vfs_lock_file(filp, F_SETLK, rlock, NULL);
+			if (rc)
+				pr_err("rollback unlock fail : %d\n", rc);
+		} else {
+			pr_err("rollback unlock alloc failed\n");
+		}
 
 		list_del(&smb_lock->llist);
 		spin_lock(&work->conn->llist_lock);
···
 		spin_unlock(&work->conn->llist_lock);
 
 		locks_free_lock(smb_lock->fl);
-		locks_free_lock(rlock);
+		if (rlock)
+			locks_free_lock(rlock);
 		kfree(smb_lock);
 	}
 out2:
···
 	buffer = (char *)req + le32_to_cpu(req->InputOffset);
 
 	cnt_code = le32_to_cpu(req->CtlCode);
-	ret = smb2_calc_max_out_buf_len(work, 48,
-					le32_to_cpu(req->MaxOutputResponse));
+	ret = smb2_calc_max_out_buf_len(work,
+			offsetof(struct smb2_ioctl_rsp, Buffer),
+			le32_to_cpu(req->MaxOutputResponse));
 	if (ret < 0) {
 		rsp->hdr.Status = STATUS_INVALID_PARAMETER;
 		goto out;

fs/udf/inode.c

···
 	}
 }
 
-static int udf_adinicb_writepages(struct address_space *mapping,
-		      struct writeback_control *wbc)
+static int udf_handle_page_wb(struct folio *folio,
+			      struct writeback_control *wbc)
 {
-	struct inode *inode = mapping->host;
+	struct inode *inode = folio->mapping->host;
 	struct udf_inode_info *iinfo = UDF_I(inode);
-	struct folio *folio = NULL;
-	int error = 0;
 
-	while ((folio = writeback_iter(mapping, wbc, folio, &error))) {
-		BUG_ON(!folio_test_locked(folio));
-		BUG_ON(folio->index != 0);
-		memcpy_from_file_folio(iinfo->i_data + iinfo->i_lenEAttr, folio,
+	/*
+	 * Inodes in the normal format are handled by the generic code. This
+	 * check is race-free as the folio lock protects us from inode type
+	 * conversion.
+	 */
+	if (iinfo->i_alloc_type != ICBTAG_FLAG_AD_IN_ICB)
+		return 1;
+
+	memcpy_from_file_folio(iinfo->i_data + iinfo->i_lenEAttr, folio,
 				0, i_size_read(inode));
-		folio_unlock(folio);
-	}
-
+	folio_unlock(folio);
 	mark_inode_dirty(inode);
 	return 0;
 }
···
 static int udf_writepages(struct address_space *mapping,
 			  struct writeback_control *wbc)
 {
-	struct inode *inode = mapping->host;
-	struct udf_inode_info *iinfo = UDF_I(inode);
-
-	if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB)
-		return udf_adinicb_writepages(mapping, wbc);
-	return mpage_writepages(mapping, wbc, udf_get_block_wb);
+	return __mpage_writepages(mapping, wbc, udf_get_block_wb,
+				  udf_handle_page_wb);
 }
 
 static void udf_adinicb_read_folio(struct folio *folio)

fs/xfs/libxfs/xfs_attr.h

···
 	struct xfs_trans	*tp;
 	struct xfs_inode	*dp;		/* inode */
 	struct xfs_attrlist_cursor_kern cursor;	/* position in list */
-	void			*buffer;	/* output buffer */
+	/* output buffer */
+	void			*buffer __counted_by_ptr(bufsize);
 
 	/*
 	 * Abort attribute list iteration if non-zero.  Can be used to pass

fs/xfs/libxfs/xfs_attr_leaf.c

···
 }
 
 /*
+ * Reinitialize an existing attr fork block as an empty leaf, and attach
+ * the buffer to tp.
+ */
+int
+xfs_attr3_leaf_init(
+	struct xfs_trans	*tp,
+	struct xfs_inode	*dp,
+	xfs_dablk_t		blkno)
+{
+	struct xfs_buf		*bp = NULL;
+	struct xfs_da_args	args = {
+		.trans		= tp,
+		.dp		= dp,
+		.owner		= dp->i_ino,
+		.geo		= dp->i_mount->m_attr_geo,
+	};
+
+	ASSERT(tp != NULL);
+
+	return xfs_attr3_leaf_create(&args, blkno, &bp);
+}
+/*
  * Split the leaf node, rebalance, then add the new entry.
  *
  * Returns 0 if the entry was added, 1 if a further split is needed or a

fs/xfs/libxfs/xfs_attr_leaf.h

···
 /*
  * Routines used for shrinking the Btree.
  */
+
+int	xfs_attr3_leaf_init(struct xfs_trans *tp, struct xfs_inode *dp,
+				xfs_dablk_t blkno);
 int	xfs_attr3_leaf_toosmall(struct xfs_da_state *state, int *retval);
 void	xfs_attr3_leaf_unbalance(struct xfs_da_state *state,
 				       struct xfs_da_state_blk *drop_blk,

fs/xfs/libxfs/xfs_da_btree.c

···
 }
 
 /*
- * Remove an entry from an intermediate node.
+ * Internal implementation to remove an entry from an intermediate node.
  */
 STATIC void
-xfs_da3_node_remove(
-	struct xfs_da_state	*state,
-	struct xfs_da_state_blk	*drop_blk)
+__xfs_da3_node_remove(
+	struct xfs_trans	*tp,
+	struct xfs_inode	*dp,
+	struct xfs_da_geometry  *geo,
+	struct xfs_da_state_blk *drop_blk)
 {
 	struct xfs_da_intnode	*node;
 	struct xfs_da3_icnode_hdr nodehdr;
 	struct xfs_da_node_entry *btree;
 	int			index;
 	int			tmp;
-	struct xfs_inode	*dp = state->args->dp;
-
-	trace_xfs_da_node_remove(state->args);
 
 	node = drop_blk->bp->b_addr;
 	xfs_da3_node_hdr_from_disk(dp->i_mount, &nodehdr, node);
···
 		tmp  = nodehdr.count - index - 1;
 		tmp *= (uint)sizeof(xfs_da_node_entry_t);
 		memmove(&btree[index], &btree[index + 1], tmp);
-		xfs_trans_log_buf(state->args->trans, drop_blk->bp,
+		xfs_trans_log_buf(tp, drop_blk->bp,
 		    XFS_DA_LOGRANGE(node, &btree[index], tmp));
 		index = nodehdr.count - 1;
 	}
 	memset(&btree[index], 0, sizeof(xfs_da_node_entry_t));
-	xfs_trans_log_buf(state->args->trans, drop_blk->bp,
+	xfs_trans_log_buf(tp, drop_blk->bp,
 	    XFS_DA_LOGRANGE(node, &btree[index], sizeof(btree[index])));
 	nodehdr.count -= 1;
 	xfs_da3_node_hdr_to_disk(dp->i_mount, node, &nodehdr);
-	xfs_trans_log_buf(state->args->trans, drop_blk->bp,
-	    XFS_DA_LOGRANGE(node, &node->hdr, state->args->geo->node_hdr_size));
+	xfs_trans_log_buf(tp, drop_blk->bp,
+	    XFS_DA_LOGRANGE(node, &node->hdr, geo->node_hdr_size));
 
 	/*
 	 * Copy the last hash value from the block to propagate upwards.
 	 */
 	drop_blk->hashval = be32_to_cpu(btree[index - 1].hashval);
+}
+
+/*
+ * Remove an entry from an intermediate node.
+ */
+STATIC void
+xfs_da3_node_remove(
+	struct xfs_da_state	*state,
+	struct xfs_da_state_blk	*drop_blk)
+{
+	trace_xfs_da_node_remove(state->args);
+
+	__xfs_da3_node_remove(state->args->trans, state->args->dp,
+			state->args->geo, drop_blk);
+}
+
+/*
+ * Remove an entry from an intermediate attr node at the specified index.
+ */
+void
+xfs_attr3_node_entry_remove(
+	struct xfs_trans	*tp,
+	struct xfs_inode	*dp,
+	struct xfs_buf		*bp,
+	int			index)
+{
+	struct xfs_da_state_blk blk = {
+		.index		= index,
+		.bp		= bp,
+	};
+
+	__xfs_da3_node_remove(tp, dp, dp->i_mount->m_attr_geo, &blk);
 }
 
 /*

fs/xfs/libxfs/xfs_da_btree.h

···
 int	xfs_da3_join(xfs_da_state_t *state);
 void	xfs_da3_fixhashpath(struct xfs_da_state *state,
 			    struct xfs_da_state_path *path_to_to_fix);
+void	xfs_attr3_node_entry_remove(struct xfs_trans *tp, struct xfs_inode *dp,
+			    struct xfs_buf *bp, int index);
 
 /*
  * Routines used for finding things in the Btree.

fs/xfs/scrub/quota.c

···
 
 	error = xchk_quota_item_bmap(sc, dq, offset);
 	xchk_iunlock(sc, XFS_ILOCK_SHARED);
-	if (!xchk_fblock_process_error(sc, XFS_DATA_FORK, offset, &error))
+	if (!xchk_fblock_process_error(sc, XFS_DATA_FORK, offset, &error)) {
+		mutex_unlock(&dq->q_qlock);
 		return error;
+	}
 
 	/*
 	 * Warn if the hard limits are larger than the fs.

fs/xfs/scrub/trace.h

···
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
 		__field(unsigned long, ino)
-		__array(char, pathname, MAXNAMELEN)
 	),
 	TP_fast_assign(
-		char		*path;
-
 		__entry->ino = file_inode(xf->file)->i_ino;
-		path = file_path(xf->file, __entry->pathname, MAXNAMELEN);
-		if (IS_ERR(path))
-			strncpy(__entry->pathname, "(unknown)",
-					sizeof(__entry->pathname));
 	),
-	TP_printk("xfino 0x%lx path '%s'",
-		  __entry->ino,
-		  __entry->pathname)
+	TP_printk("xfino 0x%lx",
+		  __entry->ino)
 );
 
 TRACE_EVENT(xfile_destroy,

fs/xfs/xfs_attr_inactive.c

···
 	xfs_daddr_t		parent_blkno, child_blkno;
 	struct xfs_buf		*child_bp;
 	struct xfs_da3_icnode_hdr ichdr;
-	int			error, i;
+	int			error;
 
 	/*
 	 * Since this code is recursive (gasp!) we must protect ourselves.
···
 		return -EFSCORRUPTED;
 	}
 
-	xfs_da3_node_hdr_from_disk(dp->i_mount, &ichdr, bp->b_addr);
+	xfs_da3_node_hdr_from_disk(mp, &ichdr, bp->b_addr);
 	parent_blkno = xfs_buf_daddr(bp);
 	if (!ichdr.count) {
 		xfs_trans_brelse(*trans, bp);
···
 	 * over the leaves removing all of them.  If this is higher up
 	 * in the tree, recurse downward.
 	 */
-	for (i = 0; i < ichdr.count; i++) {
+	while (ichdr.count > 0) {
 		/*
 		 * Read the subsidiary block to see what we have to work with.
 		 * Don't do this in a transaction.  This is a depth-first
···
 		xfs_trans_binval(*trans, child_bp);
 		child_bp = NULL;
 
-		/*
-		 * If we're not done, re-read the parent to get the next
-		 * child block number.
-		 */
-		if (i + 1 < ichdr.count) {
-			struct xfs_da3_icnode_hdr phdr;
+		error = xfs_da3_node_read_mapped(*trans, dp,
+				parent_blkno, &bp, XFS_ATTR_FORK);
+		if (error)
+			return error;
 
-			error = xfs_da3_node_read_mapped(*trans, dp,
-					parent_blkno, &bp, XFS_ATTR_FORK);
+		/*
+		 * Remove entry from parent node, prevents being indexed to.
+		 */
+		xfs_attr3_node_entry_remove(*trans, dp, bp, 0);
+
+		xfs_da3_node_hdr_from_disk(mp, &ichdr, bp->b_addr);
+		bp = NULL;
+
+		if (ichdr.count > 0) {
+			/*
+			 * If we're not done, get the next child block number.
+			 */
+			child_fsb = be32_to_cpu(ichdr.btree[0].before);
+
+			/*
+			 * Atomically commit the whole invalidate stuff.
+			 */
+			error = xfs_trans_roll_inode(trans, dp);
 			if (error)
 				return error;
-			xfs_da3_node_hdr_from_disk(dp->i_mount, &phdr,
-						  bp->b_addr);
-			child_fsb = be32_to_cpu(phdr.btree[i + 1].before);
-			xfs_trans_brelse(*trans, bp);
-			bp = NULL;
 		}
-		/*
-		 * Atomically commit the whole invalidate stuff.
-		 */
-		error = xfs_trans_roll_inode(trans, dp);
-		if (error)
-			return  error;
 	}
 
 	return 0;
···
 	struct xfs_trans	**trans,
 	struct xfs_inode	*dp)
 {
-	struct xfs_mount	*mp = dp->i_mount;
 	struct xfs_da_blkinfo	*info;
 	struct xfs_buf		*bp;
-	xfs_daddr_t		blkno;
 	int			error;
 
 	/*
···
 	error = xfs_da3_node_read(*trans, dp, 0, &bp, XFS_ATTR_FORK);
 	if (error)
 		return error;
-	blkno = xfs_buf_daddr(bp);
 
 	/*
 	 * Invalidate the tree, even if the "tree" is only a single leaf block.
···
 	case cpu_to_be16(XFS_DA_NODE_MAGIC):
 	case cpu_to_be16(XFS_DA3_NODE_MAGIC):
 		error = xfs_attr3_node_inactive(trans, dp, bp, 1);
+		/*
+		 * Empty root node block are not allowed, convert it to leaf.
+		 */
+		if (!error)
+			error = xfs_attr3_leaf_init(*trans, dp, 0);
+		if (!error)
+			error = xfs_trans_roll_inode(trans, dp);
 		break;
 	case cpu_to_be16(XFS_ATTR_LEAF_MAGIC):
 	case cpu_to_be16(XFS_ATTR3_LEAF_MAGIC):
 		error = xfs_attr3_leaf_inactive(trans, dp, bp);
+		/*
+		 * Reinit the leaf before truncating extents so that a crash
+		 * mid-truncation leaves an empty leaf rather than one with
+		 * entries that may reference freed remote value blocks.
+		 */
+		if (!error)
+			error = xfs_attr3_leaf_init(*trans, dp, 0);
+		if (!error)
+			error = xfs_trans_roll_inode(trans, dp);
 		break;
 	default:
 		xfs_dirattr_mark_sick(dp, XFS_ATTR_FORK);
···
 		xfs_trans_brelse(*trans, bp);
 		break;
 	}
-	if (error)
-		return error;
-
-	/*
-	 * Invalidate the incore copy of the root block.
-	 */
-	error = xfs_trans_get_buf(*trans, mp->m_ddev_targp, blkno,
-			XFS_FSB_TO_BB(mp, mp->m_attr_geo->fsbcount), 0, &bp);
-	if (error)
-		return error;
-	xfs_trans_binval(*trans, bp);	/* remove from cache */
-	/*
-	 * Commit the invalidate and start the next transaction.
-	 */
-	error = xfs_trans_roll_inode(trans, dp);
 
 	return error;
 }
···
 {
 	struct xfs_trans	*trans;
 	struct xfs_mount	*mp;
+	struct xfs_buf          *bp;
 	int			lock_mode = XFS_ILOCK_SHARED;
 	int			error = 0;
 
···
 	 * removal below.
 	 */
 	if (dp->i_af.if_nextents > 0) {
+		/*
+		 * Invalidate and truncate all blocks but leave the root block.
+		 */
 		error = xfs_attr3_root_inactive(&trans, dp);
 		if (error)
 			goto out_cancel;
 
+		error = xfs_itruncate_extents(&trans, dp, XFS_ATTR_FORK,
+				XFS_FSB_TO_B(mp, mp->m_attr_geo->fsbcount));
+		if (error)
+			goto out_cancel;
+
+		/*
+		 * Invalidate and truncate the root block and ensure that the
+		 * operation is completed within a single transaction.
+		 */
+		error = xfs_da_get_buf(trans, dp, 0, &bp, XFS_ATTR_FORK);
+		if (error)
+			goto out_cancel;
+
+		xfs_trans_binval(trans, bp);
 		error = xfs_itruncate_extents(&trans, dp, XFS_ATTR_FORK, 0);
 		if (error)
 			goto out_cancel;

fs/xfs/xfs_attr_item.c

···
 		break;
 	}
 	if (error) {
-		xfs_irele(ip);
 		XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, attrp,
 				sizeof(*attrp));
 		return ERR_PTR(-EFSCORRUPTED);
···
 		break;
 	case XFS_ATTRI_OP_FLAGS_SET:
 	case XFS_ATTRI_OP_FLAGS_REPLACE:
-		/* Log item, attr name, attr value */
-		if (item->ri_total != 3) {
+		/* Log item, attr name, optional attr value */
+		if (item->ri_total != 2 + !!attri_formatp->alfi_value_len) {
 			XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
 					     attri_formatp, len);
 			return -EFSCORRUPTED;
···
 		XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
 				attri_formatp, len);
 		return -EFSCORRUPTED;
-	}
-
-	switch (op) {
-	case XFS_ATTRI_OP_FLAGS_REMOVE:
-		/* Regular remove operations operate only on names. */
-		if (attr_value != NULL || value_len != 0) {
-			XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
-					     attri_formatp, len);
-			return -EFSCORRUPTED;
-		}
-		fallthrough;
-	case XFS_ATTRI_OP_FLAGS_PPTR_REMOVE:
-	case XFS_ATTRI_OP_FLAGS_PPTR_SET:
-	case XFS_ATTRI_OP_FLAGS_SET:
-	case XFS_ATTRI_OP_FLAGS_REPLACE:
-		/*
-		 * Regular xattr set/remove/replace operations require a name
-		 * and do not take a newname.  Values are optional for set and
-		 * replace.
-		 *
-		 * Name-value set/remove operations must have a name, do not
-		 * take a newname, and can take a value.
-		 */
-		if (attr_name == NULL || name_len == 0) {
-			XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
-					     attri_formatp, len);
-			return -EFSCORRUPTED;
-		}
-		break;
-	case XFS_ATTRI_OP_FLAGS_PPTR_REPLACE:
-		/*
-		 * Name-value replace operations require the caller to
-		 * specify the old and new names and values explicitly.
-		 * Values are optional.
-		 */
-		if (attr_name == NULL || name_len == 0) {
-			XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
-					     attri_formatp, len);
-			return -EFSCORRUPTED;
-		}
-		if (attr_new_name == NULL || new_name_len == 0) {
-			XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
-					     attri_formatp, len);
-			return -EFSCORRUPTED;
-		}
-		break;
 	}
 
 	/*

fs/xfs/xfs_dquot_item.c

···
 	struct xfs_dq_logitem	*qlip = DQUOT_ITEM(lip);
 	struct xfs_dquot	*dqp = qlip->qli_dquot;
 	struct xfs_buf		*bp;
+	struct xfs_ail		*ailp = lip->li_ailp;
 	uint			rval = XFS_ITEM_SUCCESS;
 	int			error;
 
···
 		goto out_unlock;
 	}
 
-	spin_unlock(&lip->li_ailp->ail_lock);
+	spin_unlock(&ailp->ail_lock);
 
 	error = xfs_dquot_use_attached_buf(dqp, &bp);
 	if (error == -EAGAIN) {
···
 			rval = XFS_ITEM_FLUSHING;
 	}
 	xfs_buf_relse(bp);
+	/*
+	 * The buffer no longer protects the log item from reclaim, so
+	 * do not reference lip after this point.
+	 */
 
 out_relock_ail:
-	spin_lock(&lip->li_ailp->ail_lock);
+	spin_lock(&ailp->ail_lock);
 out_unlock:
 	mutex_unlock(&dqp->q_qlock);
 	return rval;

fs/xfs/xfs_handle.c

···
 	context.dp = dp;
 	context.resynch = 1;
 	context.attr_filter = xfs_attr_filter(flags);
-	context.buffer = buffer;
 	context.bufsize = round_down(bufsize, sizeof(uint32_t));
+	context.buffer = buffer;
 	context.firstu = context.bufsize;
 	context.put_listent = xfs_ioc_attr_put_listent;
 

fs/xfs/xfs_inode.c

···
 	xfs_assert_ilocked(ip, XFS_ILOCK_EXCL);
 	if (icount_read(VFS_I(ip)))
 		xfs_assert_ilocked(ip, XFS_IOLOCK_EXCL);
-	ASSERT(new_size <= XFS_ISIZE(ip));
+	if (whichfork == XFS_DATA_FORK)
+		ASSERT(new_size <= XFS_ISIZE(ip));
 	ASSERT(tp->t_flags & XFS_TRANS_PERM_LOG_RES);
 	ASSERT(ip->i_itemp != NULL);
 	ASSERT(ip->i_itemp->ili_lock_flags == 0);

fs/xfs/xfs_inode_item.c

···
 	struct xfs_inode_log_item *iip = INODE_ITEM(lip);
 	struct xfs_inode	*ip = iip->ili_inode;
 	struct xfs_buf		*bp = lip->li_buf;
+	struct xfs_ail		*ailp = lip->li_ailp;
 	uint			rval = XFS_ITEM_SUCCESS;
 	int			error;
 
···
 	if (!xfs_buf_trylock(bp))
 		return XFS_ITEM_LOCKED;
 
-	spin_unlock(&lip->li_ailp->ail_lock);
+	spin_unlock(&ailp->ail_lock);
 
 	/*
 	 * We need to hold a reference for flushing the cluster buffer as it may
···
 		rval = XFS_ITEM_LOCKED;
 	}
 
-	spin_lock(&lip->li_ailp->ail_lock);
+	/*
+	 * The buffer no longer protects the log item from reclaim, so
+	 * do not reference lip after this point.
+	 */
+	spin_lock(&ailp->ail_lock);
 	return rval;
 }
 

fs/xfs/xfs_mount.c

···
  * have been retrying in the background.  This will prevent never-ending
  * retries in AIL pushing from hanging the unmount.
  *
- * Finally, we can push the AIL to clean all the remaining dirty objects, then
- * reclaim the remaining inodes that are still in memory at this point in time.
+ * Stop inodegc and background reclaim before pushing the AIL so that they
+ * are not running while the AIL is being flushed. Then push the AIL to
+ * clean all the remaining dirty objects and reclaim the remaining inodes.
  */
 static void
 xfs_unmount_flush_inodes(
···
 
 	xfs_set_unmounting(mp);
 
-	xfs_ail_push_all_sync(mp->m_ail);
 	xfs_inodegc_stop(mp);
 	cancel_delayed_work_sync(&mp->m_reclaim_work);
+	xfs_ail_push_all_sync(mp->m_ail);
 	xfs_reclaim_inodes(mp);
 	xfs_health_unmount(mp);
 	xfs_healthmon_unmount(mp);

fs/xfs/xfs_trace.h

···
 #include <linux/tracepoint.h>
 
 struct xfs_agf;
+struct xfs_ail;
 struct xfs_alloc_arg;
 struct xfs_attr_list_context;
 struct xfs_buf_log_item;
···
 DEFINE_EVENT(xfs_log_item_class, name, \
 	TP_PROTO(struct xfs_log_item *lip), \
 	TP_ARGS(lip))
-DEFINE_LOG_ITEM_EVENT(xfs_ail_push);
-DEFINE_LOG_ITEM_EVENT(xfs_ail_pinned);
-DEFINE_LOG_ITEM_EVENT(xfs_ail_locked);
-DEFINE_LOG_ITEM_EVENT(xfs_ail_flushing);
 DEFINE_LOG_ITEM_EVENT(xfs_cil_whiteout_mark);
 DEFINE_LOG_ITEM_EVENT(xfs_cil_whiteout_skip);
 DEFINE_LOG_ITEM_EVENT(xfs_cil_whiteout_unpin);
 DEFINE_LOG_ITEM_EVENT(xlog_ail_insert_abort);
 DEFINE_LOG_ITEM_EVENT(xfs_trans_free_abort);
+
+DECLARE_EVENT_CLASS(xfs_ail_push_class,
+	TP_PROTO(struct xfs_ail *ailp, uint type, unsigned long flags, xfs_lsn_t lsn),
+	TP_ARGS(ailp, type, flags, lsn),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(uint, type)
+		__field(unsigned long, flags)
+		__field(xfs_lsn_t, lsn)
+	),
+	TP_fast_assign(
+		__entry->dev = ailp->ail_log->l_mp->m_super->s_dev;
+		__entry->type = type;
+		__entry->flags = flags;
+		__entry->lsn = lsn;
+	),
+	TP_printk("dev %d:%d lsn %d/%d type %s flags %s",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  CYCLE_LSN(__entry->lsn), BLOCK_LSN(__entry->lsn),
+		  __print_symbolic(__entry->type, XFS_LI_TYPE_DESC),
+		  __print_flags(__entry->flags, "|", XFS_LI_FLAGS))
+)
+
+#define DEFINE_AIL_PUSH_EVENT(name) \
+DEFINE_EVENT(xfs_ail_push_class, name, \
+	TP_PROTO(struct xfs_ail *ailp, uint type, unsigned long flags, xfs_lsn_t lsn), \
+	TP_ARGS(ailp, type, flags, lsn))
+DEFINE_AIL_PUSH_EVENT(xfs_ail_push);
+DEFINE_AIL_PUSH_EVENT(xfs_ail_pinned);
+DEFINE_AIL_PUSH_EVENT(xfs_ail_locked);
+DEFINE_AIL_PUSH_EVENT(xfs_ail_flushing);
 
 DECLARE_EVENT_CLASS(xfs_ail_class,
 	TP_PROTO(struct xfs_log_item *lip, xfs_lsn_t old_lsn, xfs_lsn_t new_lsn),
···
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
 		__field(unsigned long, ino)
-		__array(char, pathname, MAXNAMELEN)
 	),
 	TP_fast_assign(
-		char		*path;
 		struct file	*file = btp->bt_file;
 
 		__entry->dev = btp->bt_mount->m_super->s_dev;
 		__entry->ino = file_inode(file)->i_ino;
-		path = file_path(file, __entry->pathname, MAXNAMELEN);
-		if (IS_ERR(path))
-			strncpy(__entry->pathname, "(unknown)",
-					sizeof(__entry->pathname));
 	),
-	TP_printk("dev %d:%d xmino 0x%lx path '%s'",
+	TP_printk("dev %d:%d xmino 0x%lx",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
-		  __entry->ino,
-		  __entry->pathname)
+		  __entry->ino)
 );
 
 TRACE_EVENT(xmbuf_free,

fs/xfs/xfs_trans_ail.c

···
 	return XFS_ITEM_SUCCESS;
 }
 
+/*
+ * Push a single log item from the AIL.
+ *
+ * @lip may have been released and freed by the time this function returns,
+ * so callers must not dereference the log item afterwards.
+ */
 static inline uint
 xfsaild_push_item(
 	struct xfs_ail		*ailp,
···
 	return target_lsn;
 }
 
+static void
+xfsaild_process_logitem(
+	struct xfs_ail		*ailp,
+	struct xfs_log_item	*lip,
+	int			*stuck,
+	int			*flushing)
+{
+	struct xfs_mount	*mp = ailp->ail_log->l_mp;
+	uint			type = lip->li_type;
+	unsigned long		flags = lip->li_flags;
+	xfs_lsn_t		item_lsn = lip->li_lsn;
+	int			lock_result;
+
+	/*
+	 * Note that iop_push may unlock and reacquire the AIL lock. We
+	 * rely on the AIL cursor implementation to be able to deal with
+	 * the dropped lock.
+	 *
+	 * The log item may have been freed by the push, so it must not
+	 * be accessed or dereferenced below this line.
+	 */
+	lock_result = xfsaild_push_item(ailp, lip);
+	switch (lock_result) {
+	case XFS_ITEM_SUCCESS:
+		XFS_STATS_INC(mp, xs_push_ail_success);
+		trace_xfs_ail_push(ailp, type, flags, item_lsn);
+
+		ailp->ail_last_pushed_lsn = item_lsn;
+		break;
+
+	case XFS_ITEM_FLUSHING:
+		/*
+		 * The item or its backing buffer is already being
+		 * flushed.  The typical reason for that is that an
+		 * inode buffer is locked because we already pushed the
+		 * updates to it as part of inode clustering.
+		 *
+		 * We do not want to stop flushing just because lots
+		 * of items are already being flushed, but we need to
+		 * re-try the flushing relatively soon if most of the
+		 * AIL is being flushed.
+		 */
+		XFS_STATS_INC(mp, xs_push_ail_flushing);
+		trace_xfs_ail_flushing(ailp, type, flags, item_lsn);
+
+		(*flushing)++;
+		ailp->ail_last_pushed_lsn = item_lsn;
+		break;
+
+	case XFS_ITEM_PINNED:
+		XFS_STATS_INC(mp, xs_push_ail_pinned);
+		trace_xfs_ail_pinned(ailp, type, flags, item_lsn);
+
+		(*stuck)++;
+		ailp->ail_log_flush++;
+		break;
+	case XFS_ITEM_LOCKED:
+		XFS_STATS_INC(mp, xs_push_ail_locked);
+		trace_xfs_ail_locked(ailp, type, flags, item_lsn);
+
+		(*stuck)++;
+		break;
+	default:
+		ASSERT(0);
+		break;
+	}
+}
+
 static long
 xfsaild_push(
 	struct xfs_ail		*ailp)
···
 
 	lsn = lip->li_lsn;
 	while ((XFS_LSN_CMP(lip->li_lsn, ailp->ail_target) <= 0)) {
-		int	lock_result;
 
 		if (test_bit(XFS_LI_FLUSHING, &lip->li_flags))
 			goto next_item;
 
-		/*
-		 * Note that iop_push may unlock and reacquire the AIL lock.  We
-		 * rely on the AIL cursor implementation to be able to deal with
-		 * the dropped lock.
-		 */
-		lock_result = xfsaild_push_item(ailp, lip);
-		switch (lock_result) {
-		case XFS_ITEM_SUCCESS:
-			XFS_STATS_INC(mp, xs_push_ail_success);
-			trace_xfs_ail_push(lip);
-
-			ailp->ail_last_pushed_lsn = lsn;
-			break;
-
-		case XFS_ITEM_FLUSHING:
-			/*
-			 * The item or its backing buffer is already being
-			 * flushed.  The typical reason for that is that an
-			 * inode buffer is locked because we already pushed the
-			 * updates to it as part of inode clustering.
-			 *
-			 * We do not want to stop flushing just because lots
-			 * of items are already being flushed, but we need to
-			 * re-try the flushing relatively soon if most of the
-			 * AIL is being flushed.
-			 */
-			XFS_STATS_INC(mp, xs_push_ail_flushing);
-			trace_xfs_ail_flushing(lip);
-
-			flushing++;
-			ailp->ail_last_pushed_lsn = lsn;
-			break;
-
-		case XFS_ITEM_PINNED:
-			XFS_STATS_INC(mp, xs_push_ail_pinned);
-			trace_xfs_ail_pinned(lip);
-
-			stuck++;
-			ailp->ail_log_flush++;
-			break;
-		case XFS_ITEM_LOCKED:
-			XFS_STATS_INC(mp, xs_push_ail_locked);
-			trace_xfs_ail_locked(lip);
-
-			stuck++;
-			break;
-		default:
-			ASSERT(0);
-			break;
-		}
-
+		xfsaild_process_logitem(ailp, lip, &stuck, &flushing);
 		count++;
 
 		/*

fs/xfs/xfs_verify_media.c

···
 			min_not_zero(SZ_1M, me->me_max_io_size);
 
 	BUILD_BUG_ON(BBSHIFT != SECTOR_SHIFT);
-	ASSERT(BBTOB(bbcount) >= bdev_logical_block_size(btp->bt_bdev));
+	ASSERT(BBTOB(bbcount) >= btp->bt_logical_sectorsize);
 
-	return clamp(iosize, bdev_logical_block_size(btp->bt_bdev),
-			BBTOB(bbcount));
+	return clamp(iosize, btp->bt_logical_sectorsize, BBTOB(bbcount));
 }
 
 /* Allocate as much memory as we can get for verification buffer. */
···
 	unsigned int		bio_bbcount,
 	blk_status_t		bio_status)
 {
-	trace_xfs_verify_media_error(mp, me, btp->bt_bdev->bd_dev, daddr,
-			bio_bbcount, bio_status);
+	trace_xfs_verify_media_error(mp, me, btp->bt_dev, daddr, bio_bbcount,
+			bio_status);
 
 	/*
 	 * Pass any error, I/O or otherwise, up to the caller if we didn't
···
 		btp = mp->m_ddev_targp;
 		break;
 	case XFS_DEV_LOG:
-		if (mp->m_logdev_targp->bt_bdev != mp->m_ddev_targp->bt_bdev)
+		if (mp->m_logdev_targp != mp->m_ddev_targp)
 			btp = mp->m_logdev_targp;
 		break;
 	case XFS_DEV_RT:
···
 
 	/* start and end have to be aligned to the lba size */
 	if (!IS_ALIGNED(BBTOB(me->me_start_daddr | me->me_end_daddr),
-			bdev_logical_block_size(btp->bt_bdev)))
+			btp->bt_logical_sectorsize))
 		return -EINVAL;
 
 	/*
···
 	if (!folio)
 		return -ENOMEM;
 
-	trace_xfs_verify_media(mp, me, btp->bt_bdev->bd_dev, daddr, bbcount,
-			folio);
+	trace_xfs_verify_media(mp, me, btp->bt_dev, daddr, bbcount, folio);
 
 	bio = bio_alloc(btp->bt_bdev, 1, REQ_OP_READ, GFP_KERNEL);
 	if (!bio) {
···
 	 * an operational error.
 	 */
 	me->me_start_daddr = daddr;
-	trace_xfs_verify_media_end(mp, me, btp->bt_bdev->bd_dev);
+	trace_xfs_verify_media_end(mp, me, btp->bt_dev);
 	return 0;
 }
 

fs/xfs/xfs_xattr.c

···
 	memset(&context, 0, sizeof(context));
 	context.dp = XFS_I(inode);
 	context.resynch = 1;
-	context.buffer = size ? data : NULL;
 	context.bufsize = size;
+	context.buffer = size ? data : NULL;
 	context.firstu = context.bufsize;
 	context.put_listent = xfs_xattr_put_listent;
 

include/linux/cgroup-defs.h

···
 	/* used to wait for offlining of csses */
 	wait_queue_head_t offline_waitq;
 
+	/* used by cgroup_rmdir() to wait for dying tasks to leave */
+	wait_queue_head_t dying_populated_waitq;
+
 	/* used to schedule release agent */
 	struct work_struct release_agent_work;
 

include/linux/fs/super_types.h

···
 #define SB_I_NOUMASK	0x00001000	/* VFS does not apply umask */
 #define SB_I_NOIDMAP	0x00002000	/* No idmapped mounts on this superblock */
 #define SB_I_ALLOW_HSM	0x00004000	/* Allow HSM events on this superblock */
+#define SB_I_NO_DATA_INTEGRITY	0x00008000 /* fs cannot guarantee data persistence on sync */
 
 #endif /* _LINUX_FS_SUPER_TYPES_H */

include/linux/iommu.h

···
 static inline void iommu_iotlb_sync(struct iommu_domain *domain,
 				  struct iommu_iotlb_gather *iotlb_gather)
 {
-	if (domain->ops->iotlb_sync)
+	if (domain->ops->iotlb_sync &&
+	    likely(iotlb_gather->start < iotlb_gather->end))
 		domain->ops->iotlb_sync(domain, iotlb_gather);
 
 	iommu_iotlb_gather_init(iotlb_gather);

include/linux/leafops.h

···
 	return swp_offset(entry) & SWP_PFN_MASK;
 }
 
+static inline void softleaf_migration_sync(softleaf_t entry,
+		struct folio *folio)
+{
+	/*
+	 * Ensure we do not race with split, which might alter tail pages into new
+	 * folios and thus result in observing an unlocked folio.
+	 * This matches the write barrier in __split_folio_to_order().
+	 */
+	smp_rmb();
+
+	/*
+	 * Any use of migration entries may only occur while the
+	 * corresponding page is locked
+	 */
+	VM_WARN_ON_ONCE(!folio_test_locked(folio));
+}
+
 /**
  * softleaf_to_page() - Obtains struct page for PFN encoded within leaf entry.
  * @entry: Leaf entry, softleaf_has_pfn(@entry) must return true.
···
 	struct page *page = pfn_to_page(softleaf_to_pfn(entry));
 
 	VM_WARN_ON_ONCE(!softleaf_has_pfn(entry));
-	/*
-	 * Any use of migration entries may only occur while the
-	 * corresponding page is locked
-	 */
-	VM_WARN_ON_ONCE(softleaf_is_migration(entry) && !PageLocked(page));
+	if (softleaf_is_migration(entry))
+		softleaf_migration_sync(entry, page_folio(page));
 
 	return page;
 }
···
 	struct folio *folio = pfn_folio(softleaf_to_pfn(entry));
 
 	VM_WARN_ON_ONCE(!softleaf_has_pfn(entry));
-	/*
-	 * Any use of migration entries may only occur while the
-	 * corresponding folio is locked.
-	 */
-	VM_WARN_ON_ONCE(softleaf_is_migration(entry) &&
-			!folio_test_locked(folio));
+	if (softleaf_is_migration(entry))
+		softleaf_migration_sync(entry, folio);
 
 	return folio;
 }

include/linux/mempolicy.h

···
 		nodemask_t cpuset_mems_allowed;	/* relative to these nodes */
 		nodemask_t user_nodemask;	/* nodemask passed by user */
 	} w;
+	struct rcu_head rcu;
 };
 
 /*

include/linux/mpage.h

···
 
 void mpage_readahead(struct readahead_control *, get_block_t get_block);
 int mpage_read_folio(struct folio *folio, get_block_t get_block);
-int mpage_writepages(struct address_space *mapping,
-		struct writeback_control *wbc, get_block_t get_block);
+int __mpage_writepages(struct address_space *mapping,
+		struct writeback_control *wbc, get_block_t get_block,
+		int (*write_folio)(struct folio *folio,
+				   struct writeback_control *wbc));
+static inline int mpage_writepages(struct address_space *mapping,
+		struct writeback_control *wbc, get_block_t get_block)
+{
+	return __mpage_writepages(mapping, wbc, get_block, NULL);
+}
 
 #endif

include/linux/netfilter/ipset/ip_set.h

···
 
 /* register and unregister set references */
 extern ip_set_id_t ip_set_get_byname(struct net *net,
-				     const char *name, struct ip_set **set);
+				     const struct nlattr *name, struct ip_set **set);
 extern void ip_set_put_byindex(struct net *net, ip_set_id_t index);
 extern void ip_set_name_byindex(struct net *net, ip_set_id_t index, char *name);
 extern ip_set_id_t ip_set_nfnl_get_byindex(struct net *net, ip_set_id_t index);

include/linux/netfs.h

···
 	void (*issue_write)(struct netfs_io_subrequest *subreq);
 	/* Collection tracking */
 	struct list_head	subrequests;	/* Contributory I/O operations */
-	struct netfs_io_subrequest *front;	/* Op being collected */
 	unsigned long long	collected_to;	/* Position we've collected results to */
 	size_t			transferred;	/* The amount transferred from this stream */
 	unsigned short		error;		/* Aggregate error for the stream */

include/linux/pagemap.h

···
 	AS_WRITEBACK_MAY_DEADLOCK_ON_RECLAIM = 9,
 	AS_KERNEL_FILE = 10,	/* mapping for a fake kernel file that shouldn't
 				   account usage to user cgroups */
-	AS_NO_DATA_INTEGRITY = 11, /* no data integrity guarantees */
 	/* Bits 16-25 are used for FOLIO_ORDER */
 	AS_FOLIO_ORDER_BITS = 5,
 	AS_FOLIO_ORDER_MIN = 16,
···
 static inline bool mapping_writeback_may_deadlock_on_reclaim(const struct address_space *mapping)
 {
 	return test_bit(AS_WRITEBACK_MAY_DEADLOCK_ON_RECLAIM, &mapping->flags);
-}
-
-static inline void mapping_set_no_data_integrity(struct address_space *mapping)
-{
-	set_bit(AS_NO_DATA_INTEGRITY, &mapping->flags);
-}
-
-static inline bool mapping_no_data_integrity(const struct address_space *mapping)
-{
-	return test_bit(AS_NO_DATA_INTEGRITY, &mapping->flags);
 }
 
 static inline gfp_t mapping_gfp_mask(const struct address_space *mapping)

include/linux/skbuff.h

···
 	return unlikely(skb->active_extensions);
 }
 #else
+static inline void __skb_ext_put(struct skb_ext *ext) {}
 static inline void skb_ext_put(struct sk_buff *skb) {}
 static inline void skb_ext_reset(struct sk_buff *skb) {}
 static inline void skb_ext_del(struct sk_buff *skb, int unused) {}

include/linux/spi/spi.h

···
  * @modalias: Name of the driver to use with this device, or an alias
  *	for that name.  This appears in the sysfs "modalias" attribute
  *	for driver coldplugging, and in uevents used for hotplugging
- * @driver_override: If the name of a driver is written to this attribute, then
- *	the device will bind to the named driver and only the named driver.
- *	Do not set directly, because core frees it; use driver_set_override() to
- *	set or clear it.
  * @pcpu_statistics: statistics for the spi_device
  * @word_delay: delay to be inserted between consecutive
  *	words of a transfer
···
 	void			*controller_state;
 	void			*controller_data;
 	char			modalias[SPI_NAME_SIZE];
-	const char		*driver_override;
 
 	/* The statistics */
 	struct spi_statistics __percpu	*pcpu_statistics;

include/net/netns/mpls.h

···
 	size_t platform_labels;
 	struct mpls_route __rcu * __rcu *platform_label;
 	struct mutex platform_mutex;
+	seqcount_mutex_t platform_label_seq;
 
 	struct ctl_table_header *ctl;
 };

include/sound/sdca_function.h

···
 #define SDCA_MAX_ENTITY_COUNT 128
 
 /*
- * Sanity check on number of initialization writes, can be expanded if needed.
- */
-#define SDCA_MAX_INIT_COUNT 2048
-
-/*
  * The Cluster IDs are 16-bit, so a maximum of 65535 Clusters per
  * function can be represented, however limit this to a slightly
  * more reasonable value. Can be expanded if needed.

include/trace/events/btrfs.h

···
 	),
 
 	TP_fast_assign(
-		const struct dentry *dentry = file->f_path.dentry;
-		const struct inode *inode = d_inode(dentry);
+		struct dentry *dentry = file_dentry(file);
+		struct inode *inode = file_inode(file);
+		struct dentry *parent = dget_parent(dentry);
+		struct inode *parent_inode = d_inode(parent);
 
-		TP_fast_assign_fsid(btrfs_sb(file->f_path.dentry->d_sb));
+		dput(parent);
+		TP_fast_assign_fsid(btrfs_sb(inode->i_sb));
 		__entry->ino		= btrfs_ino(BTRFS_I(inode));
-		__entry->parent		= btrfs_ino(BTRFS_I(d_inode(dentry->d_parent)));
+		__entry->parent		= btrfs_ino(BTRFS_I(parent_inode));
 		__entry->datasync	= datasync;
 		__entry->root_objectid	= btrfs_root_id(BTRFS_I(inode)->root);
 	),

include/trace/events/netfs.h

···
 		    __field(unsigned int,	wreq)
 		    __field(unsigned char,	stream)
 		    __field(unsigned long long,	collected_to)
-		    __field(unsigned long long,	front)
+		    __field(unsigned long long,	issued_to)
 			     ),
 
 	    TP_fast_assign(
 		    __entry->wreq	= wreq->debug_id;
 		    __entry->stream	= stream->stream_nr;
 		    __entry->collected_to = stream->collected_to;
-		    __entry->front	= stream->front ? stream->front->start : UINT_MAX;
+		    __entry->issued_to	= atomic64_read(&wreq->issued_to);
 			   ),
 
-	    TP_printk("R=%08x[%x:] cto=%llx frn=%llx",
+	    TP_printk("R=%08x[%x:] cto=%llx ito=%llx",
 		      __entry->wreq, __entry->stream,
-		      __entry->collected_to, __entry->front)
+		      __entry->collected_to, __entry->issued_to)
 	    );
 
 TRACE_EVENT(netfs_folioq,

io_uring/fdinfo.c

···
 					sq_idx);
 				break;
 			}
-			if ((++sq_head & sq_mask) == 0) {
+			if (sq_idx == sq_mask) {
 				seq_printf(m,
 					"%5u: corrupted sqe, wrapping 128B entry\n",
 					sq_idx);
 				break;
 			}
+			sq_head++;
+			i++;
 			sqe128 = true;
 		}
 		seq_printf(m, "%5u: opcode:%s, fd:%d, flags:%x, off:%llu, "

kernel/cgroup/cgroup.c

···
 #endif
 
 	init_waitqueue_head(&cgrp->offline_waitq);
+	init_waitqueue_head(&cgrp->dying_populated_waitq);
 	INIT_WORK(&cgrp->release_agent_work, cgroup1_release_agent);
 }
 
···
 	return 0;
 };
 
+/**
+ * cgroup_drain_dying - wait for dying tasks to leave before rmdir
+ * @cgrp: the cgroup being removed
+ *
+ * cgroup.procs and cgroup.threads use css_task_iter which filters out
+ * PF_EXITING tasks so that userspace doesn't see tasks that have already been
+ * reaped via waitpid(). However, cgroup_has_tasks() - which tests whether the
+ * cgroup has non-empty css_sets - is only updated when dying tasks pass through
+ * cgroup_task_dead() in finish_task_switch(). This creates a window where
+ * cgroup.procs reads empty but cgroup_has_tasks() is still true, making rmdir
+ * fail with -EBUSY from cgroup_destroy_locked() even though userspace sees no
+ * tasks.
+ *
+ * This function aligns cgroup_has_tasks() with what userspace can observe. If
+ * cgroup_has_tasks() but the task iterator sees nothing (all remaining tasks are
+ * PF_EXITING), we wait for cgroup_task_dead() to finish processing them. As the
+ * window between PF_EXITING and cgroup_task_dead() is short, the wait is brief.
+ *
+ * This function only concerns itself with this cgroup's own dying tasks.
+ * Whether the cgroup has children is cgroup_destroy_locked()'s problem.
+ *
+ * Each cgroup_task_dead() kicks the waitqueue via cset->cgrp_links, and we
+ * retry the full check from scratch.
+ *
+ * Must be called with cgroup_mutex held.
+ */
+static int cgroup_drain_dying(struct cgroup *cgrp)
+	__releases(&cgroup_mutex) __acquires(&cgroup_mutex)
+{
+	struct css_task_iter it;
+	struct task_struct *task;
+	DEFINE_WAIT(wait);
+
+	lockdep_assert_held(&cgroup_mutex);
+retry:
+	if (!cgroup_has_tasks(cgrp))
+		return 0;
+
+	/* Same iterator as cgroup.threads - if any task is visible, it's busy */
+	css_task_iter_start(&cgrp->self, 0, &it);
+	task = css_task_iter_next(&it);
+	css_task_iter_end(&it);
+
+	if (task)
+		return -EBUSY;
+
+	/*
+	 * All remaining tasks are PF_EXITING and will pass through
+	 * cgroup_task_dead() shortly. Wait for a kick and retry.
+	 *
+	 * cgroup_has_tasks() can't transition from false to true while we're
+	 * holding cgroup_mutex, but the true to false transition happens
+	 * under css_set_lock (via cgroup_task_dead()). We must retest and
+	 * prepare_to_wait() under css_set_lock. Otherwise, the transition
+	 * can happen between our first test and prepare_to_wait(), and we
+	 * sleep with no one to wake us.
+	 */
+	spin_lock_irq(&css_set_lock);
+	if (!cgroup_has_tasks(cgrp)) {
+		spin_unlock_irq(&css_set_lock);
+		return 0;
+	}
+	prepare_to_wait(&cgrp->dying_populated_waitq, &wait,
+			TASK_UNINTERRUPTIBLE);
+	spin_unlock_irq(&css_set_lock);
+	mutex_unlock(&cgroup_mutex);
+	schedule();
+	finish_wait(&cgrp->dying_populated_waitq, &wait);
+	mutex_lock(&cgroup_mutex);
+	goto retry;
+}
+
 int cgroup_rmdir(struct kernfs_node *kn)
 {
 	struct cgroup *cgrp;
···
 	if (!cgrp)
 		return 0;
 
-	ret = cgroup_destroy_locked(cgrp);
-	if (!ret)
-		TRACE_CGROUP_PATH(rmdir, cgrp);
+	ret = cgroup_drain_dying(cgrp);
+	if (!ret) {
+		ret = cgroup_destroy_locked(cgrp);
+		if (!ret)
+			TRACE_CGROUP_PATH(rmdir, cgrp);
+	}
 
 	cgroup_kn_unlock(kn);
 	return ret;
···
 
 static void do_cgroup_task_dead(struct task_struct *tsk)
 {
+	struct cgrp_cset_link *link;
 	struct css_set *cset;
 	unsigned long flags;
 
···
 	/* matches the signal->live check in css_task_iter_advance() */
 	if (thread_group_leader(tsk) && atomic_read(&tsk->signal->live))
 		list_add_tail(&tsk->cg_list, &cset->dying_tasks);
+
+	/* kick cgroup_drain_dying() waiters, see cgroup_rmdir() */
+	list_for_each_entry(link, &cset->cgrp_links, cgrp_link)
+		if (waitqueue_active(&link->cgrp->dying_populated_waitq))
+			wake_up(&link->cgrp->dying_populated_waitq);
 
 	if (dl_task(tsk))
 		dec_dl_tasks_cs(tsk);

kernel/cgroup/cpuset.c

···
 	struct cgroup_subsys_state *css;
 	struct cpuset *cs, *oldcs;
 	struct task_struct *task;
-	bool cpus_updated, mems_updated;
+	bool setsched_check;
 	int ret;
 
 	/* used later by cpuset_attach() */
···
 	if (ret)
 		goto out_unlock;
 
-	cpus_updated = !cpumask_equal(cs->effective_cpus, oldcs->effective_cpus);
-	mems_updated = !nodes_equal(cs->effective_mems, oldcs->effective_mems);
+	/*
+	 * Skip rights over task setsched check in v2 when nothing changes,
+	 * migration permission derives from hierarchy ownership in
+	 * cgroup_procs_write_permission()).
+	 */
+	setsched_check = !cpuset_v2() ||
+		!cpumask_equal(cs->effective_cpus, oldcs->effective_cpus) ||
+		!nodes_equal(cs->effective_mems, oldcs->effective_mems);
+
+	/*
+	 * A v1 cpuset with tasks will have no CPU left only when CPU hotplug
+	 * brings the last online CPU offline as users are not allowed to empty
+	 * cpuset.cpus when there are active tasks inside. When that happens,
+	 * we should allow tasks to migrate out without security check to make
+	 * sure they will be able to run after migration.
+	 */
+	if (!is_in_v2_mode() && cpumask_empty(oldcs->effective_cpus))
+		setsched_check = false;
 
 	cgroup_taskset_for_each(task, css, tset) {
 		ret = task_can_attach(task);
 		if (ret)
 			goto out_unlock;
 
-		/*
-		 * Skip rights over task check in v2 when nothing changes,
-		 * migration permission derives from hierarchy ownership in
-		 * cgroup_procs_write_permission()).
-		 */
-		if (!cpuset_v2() || (cpus_updated || mems_updated)) {
+		if (setsched_check) {
 			ret = security_task_setscheduler(task);
 			if (ret)
 				goto out_unlock;

kernel/futex/core.c

···
 	if (!vma)
 		return FUTEX_NO_NODE;
 
-	mpol = vma_policy(vma);
+	mpol = READ_ONCE(vma->vm_policy);
 	if (!mpol)
 		return FUTEX_NO_NODE;
 

kernel/futex/pi.c

···
 int futex_lock_pi(u32 __user *uaddr, unsigned int flags, ktime_t *time, int trylock)
 {
 	struct hrtimer_sleeper timeout, *to;
-	struct task_struct *exiting = NULL;
+	struct task_struct *exiting;
 	struct rt_mutex_waiter rt_waiter;
 	struct futex_q q = futex_q_init;
 	DEFINE_WAKE_Q(wake_q);
···
 	to = futex_setup_timer(time, &timeout, flags, 0);
 
 retry:
+	exiting = NULL;
 	ret = get_futex_key(uaddr, flags, &q.key, FUTEX_WRITE);
 	if (unlikely(ret != 0))
 		goto out;

kernel/futex/syscalls.c

···
 	if (ret)
 		return ret;
 
+	/*
+	 * For now mandate both flags are identical, like the sys_futex()
+	 * interface has. If/when we merge the variable sized futex support,
+	 * that patch can modify this test to allow a difference in size.
+	 */
+	if (futexes[0].w.flags != futexes[1].w.flags)
+		return -EINVAL;
+
 	cmpval = futexes[0].w.val;
 
 	return futex_requeue(u64_to_user_ptr(futexes[0].w.uaddr), futexes[0].w.flags,

kernel/power/main.c

···
 {
 	WARN_ON(!mutex_is_locked(&system_transition_mutex));
 
-	if (WARN_ON(!saved_gfp_count) || --saved_gfp_count)
+	if (!saved_gfp_count || --saved_gfp_count)
 		return;
 
 	gfp_allowed_mask = saved_gfp_mask;

kernel/power/snapshot.c

···
 {
 	int error;
 
+	/*
+	 * Call snapshot_write_next() to drain any trailing zero pages,
+	 * but make sure we're in the data page region first.
+	 * This function can return PAGE_SIZE if the kernel was expecting
+	 * another copy page. Return -ENODATA in that situation.
+	 */
+	if (handle->cur > nr_meta_pages + 1) {
+		error = snapshot_write_next(handle);
+		if (error)
+			return error > 0 ? -ENODATA : error;
+	}
 	copy_last_highmem_page();
 	error = hibernate_restore_protect_page(handle->buffer);
 	/* Do that only if we have loaded the image entirely */

kernel/sched/ext.c

···
 {
 	struct scx_sched *sch = scx_root;
 
-	/* see kick_cpus_irq_workfn() */
+	/* see kick_sync_wait_bal_cb() */
 	smp_store_release(&rq->scx.kick_sync, rq->scx.kick_sync + 1);
 
 	update_curr_scx(rq);
···
 		switch_class(rq, next);
 }
 
+static void kick_sync_wait_bal_cb(struct rq *rq)
+{
+	struct scx_kick_syncs __rcu *ks = __this_cpu_read(scx_kick_syncs);
+	unsigned long *ksyncs = rcu_dereference_sched(ks)->syncs;
+	bool waited;
+	s32 cpu;
+
+	/*
+	 * Drop rq lock and enable IRQs while waiting. IRQs must be enabled
+	 * — a target CPU may be waiting for us to process an IPI (e.g. TLB
+	 * flush) while we wait for its kick_sync to advance.
+	 *
+	 * Also, keep advancing our own kick_sync so that new kick_sync waits
+	 * targeting us, which can start after we drop the lock, cannot form
+	 * cyclic dependencies.
+	 */
+retry:
+	waited = false;
+	for_each_cpu(cpu, rq->scx.cpus_to_sync) {
+		/*
+		 * smp_load_acquire() pairs with smp_store_release() on
+		 * kick_sync updates on the target CPUs.
+		 */
+		if (cpu == cpu_of(rq) ||
+		    smp_load_acquire(&cpu_rq(cpu)->scx.kick_sync) != ksyncs[cpu]) {
+			cpumask_clear_cpu(cpu, rq->scx.cpus_to_sync);
+			continue;
+		}
+
+		raw_spin_rq_unlock_irq(rq);
+		while (READ_ONCE(cpu_rq(cpu)->scx.kick_sync) == ksyncs[cpu]) {
+			smp_store_release(&rq->scx.kick_sync, rq->scx.kick_sync + 1);
+			cpu_relax();
+		}
+		raw_spin_rq_lock_irq(rq);
+		waited = true;
+	}
+
+	if (waited)
+		goto retry;
+}
+
 static struct task_struct *first_local_task(struct rq *rq)
 {
 	return list_first_entry_or_null(&rq->scx.local_dsq.list,
···
 	bool keep_prev;
 	struct task_struct *p;
 
-	/* see kick_cpus_irq_workfn() */
+	/* see kick_sync_wait_bal_cb() */
 	smp_store_release(&rq->scx.kick_sync, rq->scx.kick_sync + 1);
 
 	rq_modified_begin(rq, &ext_sched_class);
···
 	balance_one(rq, prev);
 	rq_repin_lock(rq, rf);
 	maybe_queue_balance_callback(rq);
+
+	/*
+	 * Defer to a balance callback which can drop rq lock and enable
+	 * IRQs. Waiting directly in the pick path would deadlock against
+	 * CPUs sending us IPIs (e.g. TLB flushes) while we wait for them.
+	 */
+	if (unlikely(rq->scx.kick_sync_pending)) {
+		rq->scx.kick_sync_pending = false;
+		queue_balance_callback(rq, &rq->scx.kick_sync_bal_cb,
+				       kick_sync_wait_bal_cb);
+	}
 
 	/*
 	 * If any higher-priority sched class enqueued a runnable task on
···
 		if (!cpumask_empty(rq->scx.cpus_to_wait))
 			dump_line(&ns, "  cpus_to_wait   : %*pb",
 				  cpumask_pr_args(rq->scx.cpus_to_wait));
+		if (!cpumask_empty(rq->scx.cpus_to_sync))
+			dump_line(&ns, "  cpus_to_sync   : %*pb",
+				  cpumask_pr_args(rq->scx.cpus_to_sync));
 
 		used = seq_buf_used(&ns);
 		if (SCX_HAS_OP(sch, dump_cpu)) {
···
 
 		if (cpumask_test_cpu(cpu, this_scx->cpus_to_wait)) {
 			if (cur_class == &ext_sched_class) {
+				cpumask_set_cpu(cpu, this_scx->cpus_to_sync);
 				ksyncs[cpu] = rq->scx.kick_sync;
 				should_wait = true;
-			} else {
-				cpumask_clear_cpu(cpu, this_scx->cpus_to_wait);
 			}
+			cpumask_clear_cpu(cpu, this_scx->cpus_to_wait);
 		}
 
 		resched_curr(rq);
···
 		cpumask_clear_cpu(cpu, this_scx->cpus_to_kick_if_idle);
 	}
 
-	if (!should_wait)
-		return;
-
-	for_each_cpu(cpu, this_scx->cpus_to_wait) {
-		unsigned long *wait_kick_sync = &cpu_rq(cpu)->scx.kick_sync;
-
-		/*
-		 * Busy-wait until the task running at the time of kicking is no
-		 * longer running. This can be used to implement e.g. core
-		 * scheduling.
-		 *
-		 * smp_cond_load_acquire() pairs with store_releases in
-		 * pick_task_scx() and put_prev_task_scx(). The former breaks
-		 * the wait if SCX's scheduling path is entered even if the same
-		 * task is picked subsequently. The latter is necessary to break
-		 * the wait when $cpu is taken by a higher sched class.
-		 */
-		if (cpu != cpu_of(this_rq))
-			smp_cond_load_acquire(wait_kick_sync, VAL != ksyncs[cpu]);
-
-		cpumask_clear_cpu(cpu, this_scx->cpus_to_wait);
+	/*
+	 * Can't wait in hardirq — kick_sync can't advance, deadlocking if
+	 * CPUs wait for each other. Defer to kick_sync_wait_bal_cb().
+	 */
+	if (should_wait) {
+		raw_spin_rq_lock(this_rq);
+		this_scx->kick_sync_pending = true;
+		resched_curr(this_rq);
+		raw_spin_rq_unlock(this_rq);
 	}
 }
 
···
 		BUG_ON(!zalloc_cpumask_var_node(&rq->scx.cpus_to_kick_if_idle, GFP_KERNEL, n));
 		BUG_ON(!zalloc_cpumask_var_node(&rq->scx.cpus_to_preempt, GFP_KERNEL, n));
 		BUG_ON(!zalloc_cpumask_var_node(&rq->scx.cpus_to_wait, GFP_KERNEL, n));
+		BUG_ON(!zalloc_cpumask_var_node(&rq->scx.cpus_to_sync, GFP_KERNEL, n));
 		rq->scx.deferred_irq_work = IRQ_WORK_INIT_HARD(deferred_irq_workfn);
 		rq->scx.kick_cpus_irq_work = IRQ_WORK_INIT_HARD(kick_cpus_irq_workfn);
 

kernel/sched/ext_idle.c

···
 		 * piled up on it even if there is an idle core elsewhere on
 		 * the system.
 		 */
-		waker_node = cpu_to_node(cpu);
+		waker_node = scx_cpu_node_if_enabled(cpu);
 		if (!(current->flags & PF_EXITING) &&
 		    cpu_rq(cpu)->scx.local_dsq.nr == 0 &&
 		    (!(flags & SCX_PICK_IDLE_IN_NODE) || (waker_node == node)) &&

kernel/sched/sched.h

···
 	cpumask_var_t		cpus_to_kick_if_idle;
 	cpumask_var_t		cpus_to_preempt;
 	cpumask_var_t		cpus_to_wait;
+	cpumask_var_t		cpus_to_sync;
+	bool			kick_sync_pending;
 	unsigned long		kick_sync;
 	local_t			reenq_local_deferred;
 	struct balance_callback	deferred_bal_cb;
+	struct balance_callback	kick_sync_bal_cb;
 	struct irq_work		deferred_irq_work;
 	struct irq_work		kick_cpus_irq_work;
 	struct scx_dispatch_q	bypass_dsq;

kernel/sysctl.c

···
 	unsigned long bitmap_len = table->maxlen;
 	unsigned long *bitmap = *(unsigned long **) table->data;
 	unsigned long *tmp_bitmap = NULL;
-	char tr_a[] = { '-', ',', '\n' }, tr_b[] = { ',', '\n', 0 }, c;
+	char tr_a[] = { '-', ',', '\n' }, tr_b[] = { ',', '\n', 0 }, c = 0;
 
 	if (!bitmap || !bitmap_len || !left || (*ppos && SYSCTL_KERN_TO_USER(dir))) {
 		*lenp = 0;

kernel/time/alarmtimer.c

···
 {
 	struct alarm *alarm = &timr->it.alarm.alarmtimer;
 
-	return alarm_forward(alarm, timr->it_interval, now);
+	return alarm_forward(alarm, now, timr->it_interval);
 }
 
 /**

kernel/trace/trace_events_trigger.c

···
 static struct llist_head trigger_data_free_list;
 static DEFINE_MUTEX(trigger_data_kthread_mutex);
 
+static int trigger_kthread_fn(void *ignore);
+
+static void trigger_create_kthread_locked(void)
+{
+	lockdep_assert_held(&trigger_data_kthread_mutex);
+
+	if (!trigger_kthread) {
+		struct task_struct *kthread;
+
+		kthread = kthread_create(trigger_kthread_fn, NULL,
+					 "trigger_data_free");
+		if (!IS_ERR(kthread))
+			WRITE_ONCE(trigger_kthread, kthread);
+	}
+}
+
+static void trigger_data_free_queued_locked(void)
+{
+	struct event_trigger_data *data, *tmp;
+	struct llist_node *llnodes;
+
+	lockdep_assert_held(&trigger_data_kthread_mutex);
+
+	llnodes = llist_del_all(&trigger_data_free_list);
+	if (!llnodes)
+		return;
+
+	tracepoint_synchronize_unregister();
+
+	llist_for_each_entry_safe(data, tmp, llnodes, llist)
+		kfree(data);
+}
+
 /* Bulk garbage collection of event_trigger_data elements */
 static int trigger_kthread_fn(void *ignore)
 {
···
 	if (data->cmd_ops->set_filter)
 		data->cmd_ops->set_filter(NULL, data, NULL);
 
-	if (unlikely(!trigger_kthread)) {
-		guard(mutex)(&trigger_data_kthread_mutex);
-		/* Check again after taking mutex */
-		if (!trigger_kthread) {
-			struct task_struct *kthread;
-
-			kthread = kthread_create(trigger_kthread_fn, NULL,
-						 "trigger_data_free");
-			if (!IS_ERR(kthread))
-				WRITE_ONCE(trigger_kthread, kthread);
-		}
+	/*
+	 * Boot-time trigger registration can fail before kthread creation
+	 * works. Keep the deferred-free semantics during boot and let late
+	 * init start the kthread to drain the list.
+	 */
+	if (system_state == SYSTEM_BOOTING && !trigger_kthread) {
+		llist_add(&data->llist, &trigger_data_free_list);
+		return;
 	}
 
-	if (!trigger_kthread) {
-		/* Do it the slow way */
-		tracepoint_synchronize_unregister();
-		kfree(data);
-		return;
+	if (unlikely(!trigger_kthread)) {
+		guard(mutex)(&trigger_data_kthread_mutex);
+
+		trigger_create_kthread_locked();
+		/* Check again after taking mutex */
+		if (!trigger_kthread) {
+			llist_add(&data->llist, &trigger_data_free_list);
+			/* Drain the queued frees synchronously if creation failed. */
+			trigger_data_free_queued_locked();
+			return;
+		}
 	}
 
 	llist_add(&data->llist, &trigger_data_free_list);
 	wake_up_process(trigger_kthread);
 }
+
+static int __init trigger_data_free_init(void)
+{
+	guard(mutex)(&trigger_data_kthread_mutex);
+
+	if (llist_empty(&trigger_data_free_list))
+		return 0;
+
+	trigger_create_kthread_locked();
+	if (trigger_kthread)
+		wake_up_process(trigger_kthread);
+	else
+		trigger_data_free_queued_locked();
+
+	return 0;
+}
+late_initcall(trigger_data_free_init);
 
 static inline void data_ops_trigger(struct event_trigger_data *data,
 				    struct trace_buffer *buffer,  void *rec,

kernel/trace/trace_osnoise.c

···
 	if (!osnoise_has_registered_instances())
 		return;
 
-	guard(mutex)(&interface_lock);
 	guard(cpus_read_lock)();
+	guard(mutex)(&interface_lock);
 
 	if (!cpu_online(cpu))
 		return;
···
 	if (running)
 		stop_per_cpu_kthreads();
 
-	mutex_lock(&interface_lock);
 	/*
 	 * avoid CPU hotplug operations that might read options.
 	 */
 	cpus_read_lock();
+	mutex_lock(&interface_lock);
 
 	retval = cnt;
 
···
 			clear_bit(option, &osnoise_options);
 	}
 
-	cpus_read_unlock();
 	mutex_unlock(&interface_lock);
+	cpus_read_unlock();
 
 	if (running)
 		start_per_cpu_kthreads();
···
 	if (running)
 		stop_per_cpu_kthreads();
 
-	mutex_lock(&interface_lock);
 	/*
 	 * osnoise_cpumask is read by CPU hotplug operations.
 	 */
 	cpus_read_lock();
+	mutex_lock(&interface_lock);
 
 	cpumask_copy(&osnoise_cpumask, osnoise_cpumask_new);
 
-	cpus_read_unlock();
 	mutex_unlock(&interface_lock);
+	cpus_read_unlock();
 
 	if (running)
 		start_per_cpu_kthreads();

kernel/workqueue.c

···
 		else
 			ts = touched;
 
-		/* did we stall? */
+		/*
+		 * Did we stall?
+		 *
+		 * Do a lockless check first to do not disturb the system.
+		 *
+		 * Prevent false positives by double checking the timestamp
+		 * under pool->lock. The lock makes sure that the check reads
+		 * an updated pool->last_progress_ts when this CPU saw
+		 * an already updated pool->worklist above. It seems better
+		 * than adding another barrier into __queue_work() which
+		 * is a hotter path.
+		 */
 		if (time_after(now, ts + thresh)) {
+			scoped_guard(raw_spinlock_irqsave, &pool->lock) {
+				pool_ts = pool->last_progress_ts;
+				if (time_after(pool_ts, touched))
+					ts = pool_ts;
+				else
+					ts = touched;
+			}
+			if (!time_after(now, ts + thresh))
+				continue;
+
 			lockup_detected = true;
 			stall_time = jiffies_to_msecs(now - pool_ts) / 1000;
 			max_stall_time = max(max_stall_time, stall_time);
···
 			pr_cont_pool_info(pool);
 			pr_cont(" stuck for %us!\n", stall_time);
 		}
-
-
 	}
 
 	if (lockup_detected)

lib/bug.c

···
 	return module_find_bug(bugaddr);
 }
 
-__diag_push();
-__diag_ignore(GCC, all, "-Wsuggest-attribute=format",
-	      "Not a valid __printf() conversion candidate.");
-static void __warn_printf(const char *fmt, struct pt_regs *regs)
+static __printf(1, 0)
+void __warn_printf(const char *fmt, struct pt_regs *regs)
 {
 	if (!fmt)
 		return;
···
 
 	printk("%s", fmt);
 }
-__diag_pop();
 
 static enum bug_trap_type __report_bug(struct bug_entry *bug, unsigned long bugaddr, struct pt_regs *regs)
 {

lib/crypto/chacha-block-generic.c

···
 				   &out[i * sizeof(u32)]);
 
 	state->x[12]++;
+
+	chacha_zeroize_state(&permuted_state);
 }
 EXPORT_SYMBOL(chacha_block_generic);
 
···
 
 	memcpy(&out[0], &permuted_state.x[0], 16);
 	memcpy(&out[4], &permuted_state.x[12], 16);
+
+	chacha_zeroize_state(&permuted_state);
 }
 EXPORT_SYMBOL(hchacha_block_generic);

mm/damon/sysfs.c

···
 	if (IS_ERR(param_ctx))
 		return PTR_ERR(param_ctx);
 	test_ctx = damon_sysfs_new_test_ctx(kdamond->damon_ctx);
-	if (!test_ctx)
+	if (!test_ctx) {
+		damon_destroy_ctx(param_ctx);
 		return -ENOMEM;
+	}
 	err = damon_commit_ctx(test_ctx, param_ctx);
 	if (err)
 		goto out;
···
 
 	if (!mutex_trylock(&damon_sysfs_lock))
 		return 0;
+	if (sysfs_kdamond->contexts->nr != 1)
+		goto out;
 	damon_sysfs_upd_tuned_intervals(sysfs_kdamond);
 	damon_sysfs_upd_schemes_stats(sysfs_kdamond);
 	damon_sysfs_upd_schemes_effective_quotas(sysfs_kdamond);
+out:
 	mutex_unlock(&damon_sysfs_lock);
 	return 0;
 }
···
 static int damon_sysfs_handle_cmd(enum damon_sysfs_cmd cmd,
 		struct damon_sysfs_kdamond *kdamond)
 {
+	if (cmd != DAMON_SYSFS_CMD_OFF && kdamond->contexts->nr != 1)
+		return -EINVAL;
+
 	switch (cmd) {
 	case DAMON_SYSFS_CMD_ON:
 		return damon_sysfs_turn_damon_on(kdamond);

mm/memory.c

···
 
 	pudp = pud_offset(p4dp, address);
 	pud = pudp_get(pudp);
-	if (pud_none(pud))
+	if (!pud_present(pud))
 		goto out;
 	if (pud_leaf(pud)) {
 		lock = pud_lock(mm, pudp);
-		if (!unlikely(pud_leaf(pud))) {
+		pud = pudp_get(pudp);
+
+		if (unlikely(!pud_present(pud))) {
+			spin_unlock(lock);
+			goto out;
+		} else if (unlikely(!pud_leaf(pud))) {
 			spin_unlock(lock);
 			goto retry;
 		}
···
 
 	pmdp = pmd_offset(pudp, address);
 	pmd = pmdp_get_lockless(pmdp);
+	if (!pmd_present(pmd))
+		goto out;
 	if (pmd_leaf(pmd)) {
 		lock = pmd_lock(mm, pmdp);
-		if (!unlikely(pmd_leaf(pmd))) {
+		pmd = pmdp_get(pmdp);
+
+		if (unlikely(!pmd_present(pmd))) {
+			spin_unlock(lock);
+			goto out;
+		} else if (unlikely(!pmd_leaf(pmd))) {
 			spin_unlock(lock);
 			goto retry;
 		}

mm/mempolicy.c

···
 {
 	if (!atomic_dec_and_test(&pol->refcnt))
 		return;
-	kmem_cache_free(policy_cache, pol);
+	/*
+	 * Required to allow mmap_lock_speculative*() access, see for example
+	 * futex_key_to_node_opt(). All accesses are serialized by mmap_lock,
+	 * however the speculative lock section unbound by the normal lock
+	 * boundaries, requiring RCU freeing.
+	 */
+	kfree_rcu(pol, rcu);
 }
 EXPORT_SYMBOL_FOR_MODULES(__mpol_put, "kvm");
 
···
 	}
 
 	old = vma->vm_policy;
-	vma->vm_policy = new; /* protected by mmap_lock */
+	WRITE_ONCE(vma->vm_policy, new); /* protected by mmap_lock */
 	mpol_put(old);
 
 	return 0;

mm/mseal.c

···
 		unsigned long start, unsigned long end)
 {
 	struct vm_area_struct *vma, *prev;
-	unsigned long curr_start = start;
 	VMA_ITERATOR(vmi, mm, start);
 
 	/* We know there are no gaps so this will be non-NULL. */
···
 		prev = vma;
 
 	for_each_vma_range(vmi, vma, end) {
+		const unsigned long curr_start = MAX(vma->vm_start, start);
 		const unsigned long curr_end = MIN(vma->vm_end, end);
 
 		if (!(vma->vm_flags & VM_SEALED)) {
···
 		}
 
 		prev = vma;
-		curr_start = curr_end;
 	}
 
 	return 0;

mm/pagewalk.c

···
 static int walk_pmd_range(pud_t *pud, unsigned long addr, unsigned long end,
 			  struct mm_walk *walk)
 {
+	pud_t pudval = pudp_get(pud);
 	pmd_t *pmd;
 	unsigned long next;
 	const struct mm_walk_ops *ops = walk->ops;
···
 	bool has_install = ops->install_pte;
 	int err = 0;
 	int depth = real_depth(3);
+
+	/*
+	 * For PTE handling, pte_offset_map_lock() takes care of checking
+	 * whether there actually is a page table. But it also has to be
+	 * very careful about concurrent page table reclaim.
+	 *
+	 * Similarly, we have to be careful here - a PUD entry that points
+	 * to a PMD table cannot go away, so we can just walk it. But if
+	 * it's something else, we need to ensure we didn't race something,
+	 * so need to retry.
+	 *
+	 * A pertinent example of this is a PUD refault after PUD split -
+	 * we will need to split again or risk accessing invalid memory.
+	 */
+	if (!pud_present(pudval) || pud_leaf(pudval)) {
+		walk->action = ACTION_AGAIN;
+		return 0;
+	}
 
 	pmd = pmd_offset(pud, addr);
 	do {
···
 		else if (pud_leaf(*pud) || !pud_present(*pud))
 			continue; /* Nothing to do. */
 
-		if (pud_none(*pud))
-			goto again;
-
 		err = walk_pmd_range(pud, addr, next, walk);
 		if (err)
 			break;
+
+		if (walk->action == ACTION_AGAIN)
+			goto again;
 	} while (pud++, addr = next, addr != end);
 
 	return err;

mm/swap_state.c

···
 
 	__folio_set_locked(folio);
 	__folio_set_swapbacked(folio);
+
+	if (!charged && mem_cgroup_swapin_charge_folio(folio, NULL, gfp, entry))
+		goto failed;
+
 	for (;;) {
 		ret = swap_cache_add_folio(folio, entry, &shadow);
 		if (!ret)
···
 		swapcache = swap_cache_get_folio(entry);
 		if (swapcache)
 			goto failed;
-	}
-
-	if (!charged && mem_cgroup_swapin_charge_folio(folio, NULL, gfp, entry)) {
-		swap_cache_del_folio(folio);
-		goto failed;
 	}
 
 	memcg1_swapin(entry, folio_nr_pages(folio));

net/bluetooth/hci_conn.c

···
 	u8 aux_num_cis = 0;
 	u8 cis_id;
 
+	hci_dev_lock(hdev);
+
 	conn = hci_conn_hash_lookup_cig(hdev, cig_id);
-	if (!conn)
+	if (!conn) {
+		hci_dev_unlock(hdev);
 		return 0;
+	}
 
 	qos = &conn->iso_qos;
 	pdu->cig_id = cig_id;
···
 		cis->p_rtn  = qos->ucast.in.rtn;
 	}
 	pdu->num_cis = aux_num_cis;
+
+	hci_dev_unlock(hdev);
 
 	if (!pdu->num_cis)
 		return 0;

net/bluetooth/hci_event.c

···
 	return data;
 }
 
+static void hci_store_wake_reason(struct hci_dev *hdev,
+				  const bdaddr_t *bdaddr, u8 addr_type)
+	__must_hold(&hdev->lock);
+
 static u8 hci_cc_inquiry_cancel(struct hci_dev *hdev, void *data,
 				struct sk_buff *skb)
 {
···
 	bt_dev_dbg(hdev, "status 0x%2.2x", status);
 
 	hci_dev_lock(hdev);
+	hci_store_wake_reason(hdev, &ev->bdaddr, BDADDR_BREDR);
 
 	/* Check for existing connection:
 	 *
···
 	__u8 flags = 0;
 
 	bt_dev_dbg(hdev, "bdaddr %pMR type 0x%x", &ev->bdaddr, ev->link_type);
+
+	hci_dev_lock(hdev);
+	hci_store_wake_reason(hdev, &ev->bdaddr, BDADDR_BREDR);
+	hci_dev_unlock(hdev);
 
 	/* Reject incoming connection from device with same BD ADDR against
 	 * CVE-2020-26555
···
 	bt_dev_dbg(hdev, "status 0x%2.2x", status);
 
 	hci_dev_lock(hdev);
+	hci_store_wake_reason(hdev, &ev->bdaddr, BDADDR_BREDR);
 
 	conn = hci_conn_hash_lookup_ba(hdev, ev->link_type, &ev->bdaddr);
 	if (!conn) {
···
 	int err;
 
 	hci_dev_lock(hdev);
+	hci_store_wake_reason(hdev, bdaddr, bdaddr_type);
 
 	/* All controllers implicitly stop advertising in the event of a
 	 * connection, so ensure that the state bit is cleared.
···
 	bt_dev_dbg(hdev, "status 0x%2.2x", ev->status);
 
 	hci_dev_lock(hdev);
+	hci_store_wake_reason(hdev, &ev->bdaddr, ev->bdaddr_type);
 
 	hci_dev_clear_flag(hdev, HCI_PA_SYNC);
 
···
 					info->length + 1))
 			break;
 
+		hci_store_wake_reason(hdev, &info->bdaddr, info->bdaddr_type);
+
 		if (info->length <= max_adv_len(hdev)) {
 			rssi = info->data[info->length];
 			process_adv_report(hdev, info->type, &info->bdaddr,
···
 					info->length))
 			break;
 
+		hci_store_wake_reason(hdev, &info->bdaddr, info->bdaddr_type);
+
 		evt_type = __le16_to_cpu(info->type) & LE_EXT_ADV_EVT_TYPE_MASK;
 		legacy_evt_type = ext_evt_type_to_legacy(hdev, evt_type);
 
···
 	bt_dev_dbg(hdev, "status 0x%2.2x", ev->status);
 
 	hci_dev_lock(hdev);
+	hci_store_wake_reason(hdev, &ev->bdaddr, ev->bdaddr_type);
 
 	hci_dev_clear_flag(hdev, HCI_PA_SYNC);
 
···
 	latency = le16_to_cpu(ev->latency);
 	timeout = le16_to_cpu(ev->timeout);
 
+	hci_dev_lock(hdev);
+
 	hcon = hci_conn_hash_lookup_handle(hdev, handle);
-	if (!hcon || hcon->state != BT_CONNECTED)
-		return send_conn_param_neg_reply(hdev, handle,
-						 HCI_ERROR_UNKNOWN_CONN_ID);
+	if (!hcon || hcon->state != BT_CONNECTED) {
+		send_conn_param_neg_reply(hdev, handle,
+					  HCI_ERROR_UNKNOWN_CONN_ID);
+		goto unlock;
+	}
 
-	if (max > hcon->le_conn_max_interval)
-		return send_conn_param_neg_reply(hdev, handle,
-						 HCI_ERROR_INVALID_LL_PARAMS);
+	if (max > hcon->le_conn_max_interval) {
+		send_conn_param_neg_reply(hdev, handle,
+					  HCI_ERROR_INVALID_LL_PARAMS);
+		goto unlock;
+	}
 
-	if (hci_check_conn_params(min, max, latency, timeout))
-		return send_conn_param_neg_reply(hdev, handle,
-						 HCI_ERROR_INVALID_LL_PARAMS);
+	if (hci_check_conn_params(min, max, latency, timeout)) {
+		send_conn_param_neg_reply(hdev, handle,
+					  HCI_ERROR_INVALID_LL_PARAMS);
+		goto unlock;
+	}
 
 	if (hcon->role == HCI_ROLE_MASTER) {
 		struct hci_conn_params *params;
 		u8 store_hint;
-
-		hci_dev_lock(hdev);
 
 		params = hci_conn_params_lookup(hdev, &hcon->dst,
 						hcon->dst_type);
···
 		} else {
 			store_hint = 0x00;
 		}
-
-		hci_dev_unlock(hdev);
 
 		mgmt_new_conn_param(hdev, &hcon->dst, hcon->dst_type,
 				    store_hint, min, max, latency, timeout);
···
 	cp.max_ce_len = 0;
 
 	hci_send_cmd(hdev, HCI_OP_LE_CONN_PARAM_REQ_REPLY, sizeof(cp), &cp);
+
+unlock:
+	hci_dev_unlock(hdev);
 }
 
 static void hci_le_direct_adv_report_evt(struct hci_dev *hdev, void *data,
···
 
 	for (i = 0; i < ev->num; i++) {
 		struct hci_ev_le_direct_adv_info *info = &ev->info[i];
+
+		hci_store_wake_reason(hdev, &info->bdaddr, info->bdaddr_type);
 
 		process_adv_report(hdev, info->type, &info->bdaddr,
 				   info->bdaddr_type, &info->direct_addr,
···
 	return true;
 }
 
-static void hci_store_wake_reason(struct hci_dev *hdev, u8 event,
-				  struct sk_buff *skb)
+static void hci_store_wake_reason(struct hci_dev *hdev,
+				  const bdaddr_t *bdaddr, u8 addr_type)
+	__must_hold(&hdev->lock)
 {
-	struct hci_ev_le_advertising_info *adv;
-	struct hci_ev_le_direct_adv_info *direct_adv;
-	struct hci_ev_le_ext_adv_info *ext_adv;
-	const struct hci_ev_conn_complete *conn_complete = (void *)skb->data;
-	const struct hci_ev_conn_request *conn_request = (void *)skb->data;
-
-	hci_dev_lock(hdev);
+	lockdep_assert_held(&hdev->lock);
 
 	/* If we are currently suspended and this is the first BT event seen,
 	 * save the wake reason associated with the event.
 	 */
 	if (!hdev->suspended || hdev->wake_reason)
-		goto unlock;
+		return;
+
+	if (!bdaddr) {
+		hdev->wake_reason = MGMT_WAKE_REASON_UNEXPECTED;
+		return;
+	}
 
 	/* Default to remote wake. Values for wake_reason are documented in the
 	 * Bluez mgmt api docs.
 	 */
 	hdev->wake_reason = MGMT_WAKE_REASON_REMOTE_WAKE;
-
-	/* Once configured for remote wakeup, we should only wake up for
-	 * reconnections. It's useful to see which device is waking us up so
-	 * keep track of the bdaddr of the connection event that woke us up.
-	 */
-	if (event == HCI_EV_CONN_REQUEST) {
-		bacpy(&hdev->wake_addr, &conn_request->bdaddr);
-		hdev->wake_addr_type = BDADDR_BREDR;
-	} else if (event == HCI_EV_CONN_COMPLETE) {
-		bacpy(&hdev->wake_addr, &conn_complete->bdaddr);
-		hdev->wake_addr_type = BDADDR_BREDR;
-	} else if (event == HCI_EV_LE_META) {
-		struct hci_ev_le_meta *le_ev = (void *)skb->data;
-		u8 subevent = le_ev->subevent;
-		u8 *ptr = &skb->data[sizeof(*le_ev)];
-		u8 num_reports = *ptr;
-
-		if ((subevent == HCI_EV_LE_ADVERTISING_REPORT ||
-		     subevent == HCI_EV_LE_DIRECT_ADV_REPORT ||
-		     subevent == HCI_EV_LE_EXT_ADV_REPORT) &&
-		    num_reports) {
-			adv = (void *)(ptr + 1);
-			direct_adv = (void *)(ptr + 1);
-			ext_adv = (void *)(ptr + 1);
-
-			switch (subevent) {
-			case HCI_EV_LE_ADVERTISING_REPORT:
-				bacpy(&hdev->wake_addr, &adv->bdaddr);
-				hdev->wake_addr_type = adv->bdaddr_type;
-				break;
-			case HCI_EV_LE_DIRECT_ADV_REPORT:
-				bacpy(&hdev->wake_addr, &direct_adv->bdaddr);
-				hdev->wake_addr_type = direct_adv->bdaddr_type;
-				break;
-			case HCI_EV_LE_EXT_ADV_REPORT:
-				bacpy(&hdev->wake_addr, &ext_adv->bdaddr);
-				hdev->wake_addr_type = ext_adv->bdaddr_type;
-				break;
-			}
-		}
-	} else {
-		hdev->wake_reason = MGMT_WAKE_REASON_UNEXPECTED;
-	}
-
-unlock:
-	hci_dev_unlock(hdev);
+	bacpy(&hdev->wake_addr, bdaddr);
+	hdev->wake_addr_type = addr_type;
 }
 
 #define HCI_EV_VL(_op, _func, _min_len, _max_len) \
···
 
 	skb_pull(skb, HCI_EVENT_HDR_SIZE);
 
-	/* Store wake reason if we're suspended */
-	hci_store_wake_reason(hdev, event, skb);
-
 	bt_dev_dbg(hdev, "event 0x%2.2x", event);
 
 	hci_event_func(hdev, event, skb, &opcode, &status, &req_complete,
 		       &req_complete_skb);
+
+	hci_dev_lock(hdev);
+	hci_store_wake_reason(hdev, NULL, 0);
+	hci_dev_unlock(hdev);
 
 	if (req_complete) {
 		req_complete(hdev, status, opcode);

net/bluetooth/hci_sync.c

···
 			    void *data, hci_cmd_sync_work_destroy_t destroy)
 {
 	if (hci_cmd_sync_lookup_entry(hdev, func, data, destroy))
-		return 0;
+		return -EEXIST;
 
 	return hci_cmd_sync_queue(hdev, func, data, destroy);
 }
···
 		return -ENETDOWN;
 
 	/* If on cmd_sync_work then run immediately otherwise queue */
-	if (current_work() == &hdev->cmd_sync_work)
-		return func(hdev, data);
+	if (current_work() == &hdev->cmd_sync_work) {
+		int err;
+
+		err = func(hdev, data);
+		if (destroy)
+			destroy(hdev, data, err);
+
+		return 0;
+	}
 
 	return hci_cmd_sync_submit(hdev, func, data, destroy);
 }
···
 
 int hci_update_passive_scan(struct hci_dev *hdev)
 {
+	int err;
+
 	/* Only queue if it would have any effect */
 	if (!test_bit(HCI_UP, &hdev->flags) ||
 	    test_bit(HCI_INIT, &hdev->flags) ||
···
 	    hci_dev_test_flag(hdev, HCI_UNREGISTER))
 		return 0;
 
-	return hci_cmd_sync_queue_once(hdev, update_passive_scan_sync, NULL,
-				       NULL);
+	err = hci_cmd_sync_queue_once(hdev, update_passive_scan_sync, NULL,
+				      NULL);
+	return (err == -EEXIST) ? 0 : err;
 }
 
 int hci_write_sc_support_sync(struct hci_dev *hdev, u8 val)
···
 
 int hci_connect_acl_sync(struct hci_dev *hdev, struct hci_conn *conn)
 {
-	return hci_cmd_sync_queue_once(hdev, hci_acl_create_conn_sync, conn,
-				       NULL);
+	int err;
+
+	err = hci_cmd_sync_queue_once(hdev, hci_acl_create_conn_sync, conn,
+				      NULL);
+	return (err == -EEXIST) ? 0 : err;
 }
 
 static void create_le_conn_complete(struct hci_dev *hdev, void *data, int err)
···
 
 int hci_connect_le_sync(struct hci_dev *hdev, struct hci_conn *conn)
 {
-	return hci_cmd_sync_queue_once(hdev, hci_le_create_conn_sync, conn,
-				       create_le_conn_complete);
+	int err;
+
+	err = hci_cmd_sync_queue_once(hdev, hci_le_create_conn_sync, conn,
+				      create_le_conn_complete);
+	return (err == -EEXIST) ? 0 : err;
 }
 
 int hci_cancel_connect_sync(struct hci_dev *hdev, struct hci_conn *conn)
···
 
 int hci_connect_pa_sync(struct hci_dev *hdev, struct hci_conn *conn)
 {
-	return hci_cmd_sync_queue_once(hdev, hci_le_pa_create_sync, conn,
-				       create_pa_complete);
+	int err;
+
+	err = hci_cmd_sync_queue_once(hdev, hci_le_pa_create_sync, conn,
+				      create_pa_complete);
+	return (err == -EEXIST) ? 0 : err;
 }
 
 static void create_big_complete(struct hci_dev *hdev, void *data, int err)
···
 
 static int hci_le_big_create_sync(struct hci_dev *hdev, void *data)
 {
-	DEFINE_FLEX(struct hci_cp_le_big_create_sync, cp, bis, num_bis, 0x11);
+	DEFINE_FLEX(struct hci_cp_le_big_create_sync, cp, bis, num_bis,
+		    HCI_MAX_ISO_BIS);
 	struct hci_conn *conn = data;
 	struct bt_iso_qos *qos = &conn->iso_qos;
 	int err;
···
 
 int hci_connect_big_sync(struct hci_dev *hdev, struct hci_conn *conn)
 {
-	return hci_cmd_sync_queue_once(hdev, hci_le_big_create_sync, conn,
-				       create_big_complete);
+	int err;
+
+	err = hci_cmd_sync_queue_once(hdev, hci_le_big_create_sync, conn,
+				      create_big_complete);
+	return (err == -EEXIST) ? 0 : err;
 }
 
 struct past_data {
···
 	if (err)
 		kfree(data);
 
-	return err;
+	return (err == -EEXIST) ? 0 : err;
 }
 
 static void le_read_features_complete(struct hci_dev *hdev, void *data, int err)
···
 
 	bt_dev_dbg(hdev, "err %d", err);
 
-	if (err == -ECANCELED)
-		return;
-
 	hci_conn_drop(conn);
+	hci_conn_put(conn);
 }
 
 static int hci_le_read_all_remote_features_sync(struct hci_dev *hdev,
···
 	 * role is possible. Otherwise just transition into the
 	 * connected state without requesting the remote features.
 	 */
-	if (conn->out || (hdev->le_features[0] & HCI_LE_PERIPHERAL_FEATURES))
+	if (conn->out || (hdev->le_features[0] & HCI_LE_PERIPHERAL_FEATURES)) {
 		err = hci_cmd_sync_queue_once(hdev,
 					      hci_le_read_remote_features_sync,
-					      hci_conn_hold(conn),
+					      hci_conn_hold(hci_conn_get(conn)),
 					      le_read_features_complete);
-	else
+		if (err) {
+			hci_conn_drop(conn);
+			hci_conn_put(conn);
+		}
+	} else {
 		err = -EOPNOTSUPP;
+	}
 
-	return err;
+	return (err == -EEXIST) ? 0 : err;
 }
 
 static void pkt_type_changed(struct hci_dev *hdev, void *data, int err)
···
 {
 	struct hci_dev *hdev = conn->hdev;
 	struct hci_cp_change_conn_ptype *cp;
+	int err;
 
 	cp = kmalloc_obj(*cp);
 	if (!cp)
···
 	cp->handle = cpu_to_le16(conn->handle);
 	cp->pkt_type = cpu_to_le16(pkt_type);
 
-	return hci_cmd_sync_queue_once(hdev, hci_change_conn_ptype_sync, cp,
-				       pkt_type_changed);
+	err = hci_cmd_sync_queue_once(hdev, hci_change_conn_ptype_sync, cp,
+				      pkt_type_changed);
+	if (err)
+		kfree(cp);
+
+	return (err == -EEXIST) ? 0 : err;
 }
 
 static void le_phy_update_complete(struct hci_dev *hdev, void *data, int err)
···
 {
 	struct hci_dev *hdev = conn->hdev;
 	struct hci_cp_le_set_phy *cp;
+	int err;
 
 	cp = kmalloc_obj(*cp);
 	if (!cp)
···
 	cp->tx_phys = tx_phys;
 	cp->rx_phys = rx_phys;
 
-	return hci_cmd_sync_queue_once(hdev, hci_le_set_phy_sync, cp,
-				       le_phy_update_complete);
+	err = hci_cmd_sync_queue_once(hdev, hci_le_set_phy_sync, cp,
+				      le_phy_update_complete);
+	if (err)
+		kfree(cp);
+
+	return (err == -EEXIST) ? 0 : err;
 }

net/bluetooth/mgmt.c

···
 	struct mgmt_mesh_tx *mesh_tx;
 	struct mgmt_cp_mesh_send *send = data;
 	struct mgmt_rp_mesh_read_features rp;
+	u16 expected_len;
 	bool sending;
 	int err = 0;
 
···
 	    !hci_dev_test_flag(hdev, HCI_MESH_EXPERIMENTAL))
 		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_MESH_SEND,
 				       MGMT_STATUS_NOT_SUPPORTED);
-	if (!hci_dev_test_flag(hdev, HCI_LE_ENABLED) ||
-	    len <= MGMT_MESH_SEND_SIZE ||
-	    len > (MGMT_MESH_SEND_SIZE + 31))
+	if (!hci_dev_test_flag(hdev, HCI_LE_ENABLED))
 		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_MESH_SEND,
 				       MGMT_STATUS_REJECTED);
+
+	if (!send->adv_data_len || send->adv_data_len > 31)
+		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_MESH_SEND,
+				       MGMT_STATUS_REJECTED);
+
+	expected_len = struct_size(send, adv_data, send->adv_data_len);
+	if (expected_len != len)
+		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_MESH_SEND,
+				       MGMT_STATUS_INVALID_PARAMS);
 
 	hci_dev_lock(hdev);
 
···
 static bool ltk_is_valid(struct mgmt_ltk_info *key)
 {
 	if (key->initiator != 0x00 && key->initiator != 0x01)
+		return false;
+
+	if (key->enc_size > sizeof(key->val))
 		return false;
 
 	switch (key->addr.type) {

net/bluetooth/sco.c

···
 	int err = 0;
 
 	sco_conn_lock(conn);
-	if (conn->sk)
+	if (conn->sk || sco_pi(sk)->conn)
 		err = -EBUSY;
 	else
 		__sco_chan_add(conn, sk, parent);
···
 
 	lock_sock(sk);
 
+	/* Recheck state after reacquiring the socket lock, as another
+	 * thread may have changed it (e.g., closed the socket).
+	 */
+	if (sk->sk_state != BT_OPEN && sk->sk_state != BT_BOUND) {
+		release_sock(sk);
+		hci_conn_drop(hcon);
+		err = -EBADFD;
+		goto unlock;
+	}
+
 	err = sco_chan_add(conn, sk, NULL);
 	if (err) {
 		release_sock(sk);
+		hci_conn_drop(hcon);
 		goto unlock;
 	}
 
···
 	    addr->sa_family != AF_BLUETOOTH)
 		return -EINVAL;
 
-	if (sk->sk_state != BT_OPEN && sk->sk_state != BT_BOUND)
-		return -EBADFD;
-
-	if (sk->sk_type != SOCK_SEQPACKET)
-		err = -EINVAL;
-
 	lock_sock(sk);
+
+	if (sk->sk_state != BT_OPEN && sk->sk_state != BT_BOUND) {
+		release_sock(sk);
+		return -EBADFD;
+	}
+
+	if (sk->sk_type != SOCK_SEQPACKET) {
+		release_sock(sk);
+		return -EINVAL;
+	}
+
 	/* Set destination address and psm */
 	bacpy(&sco_pi(sk)->dst, &sa->sco_bdaddr);
 	release_sock(sk);

net/bluetooth/smp.c

···
 
 		smp_s1(smp->tk, smp->prnd, smp->rrnd, stk);
 
-		if (hcon->pending_sec_level == BT_SECURITY_HIGH)
-			auth = 1;
-		else
-			auth = 0;
+		auth = test_bit(SMP_FLAG_MITM_AUTH, &smp->flags) ? 1 : 0;
 
 		/* Even though there's no _RESPONDER suffix this is the
 		 * responder STK we're adding for later lookup (the initiator
···
 	if (sec_level > conn->hcon->pending_sec_level)
 		conn->hcon->pending_sec_level = sec_level;
 
-	/* If we need MITM check that it can be achieved */
+	/* If we need MITM check that it can be achieved. */
 	if (conn->hcon->pending_sec_level >= BT_SECURITY_HIGH) {
 		u8 method;
 
···
 					 req->io_capability);
 		if (method == JUST_WORKS || method == JUST_CFM)
 			return SMP_AUTH_REQUIREMENTS;
+
+		/* Force MITM bit if it isn't set by the initiator. */
+		auth |= SMP_AUTH_MITM;
+		rsp.auth_req |= SMP_AUTH_MITM;
 	}
 
 	key_size = min(req->max_key_size, rsp.max_key_size);

net/bridge/br_arp_nd_proxy.c

···
 
 static void br_nd_send(struct net_bridge *br, struct net_bridge_port *p,
 		       struct sk_buff *request, struct neighbour *n,
-		       __be16 vlan_proto, u16 vlan_tci, struct nd_msg *ns)
+		       __be16 vlan_proto, u16 vlan_tci)
 {
 	struct net_device *dev = request->dev;
 	struct net_bridge_vlan_group *vg;
+	struct nd_msg *na, *ns;
 	struct sk_buff *reply;
-	struct nd_msg *na;
 	struct ipv6hdr *pip6;
 	int na_olen = 8; /* opt hdr + ETH_ALEN for target */
 	int ns_olen;
···
 	u8 *daddr;
 	u16 pvid;
 
-	if (!dev)
+	if (!dev || skb_linearize(request))
 		return;
 
 	len = LL_RESERVED_SPACE(dev) + sizeof(struct ipv6hdr) +
···
 	skb_set_mac_header(reply, 0);
 
 	daddr = eth_hdr(request)->h_source;
+	ns = (struct nd_msg *)(skb_network_header(request) +
+			       sizeof(struct ipv6hdr));
 
 	/* Do we need option processing ? */
 	ns_olen = request->len - (skb_network_offset(request) +
 				  sizeof(struct ipv6hdr)) - sizeof(*ns);
 	for (i = 0; i < ns_olen - 1; i += (ns->opt[i + 1] << 3)) {
-		if (!ns->opt[i + 1]) {
+		if (!ns->opt[i + 1] || i + (ns->opt[i + 1] << 3) > ns_olen) {
 			kfree_skb(reply);
 			return;
 		}
 		if (ns->opt[i] == ND_OPT_SOURCE_LL_ADDR) {
-			daddr = ns->opt + i + sizeof(struct nd_opt_hdr);
+			if ((ns->opt[i + 1] << 3) >=
+			    sizeof(struct nd_opt_hdr) + ETH_ALEN)
+				daddr = ns->opt + i + sizeof(struct nd_opt_hdr);
 			break;
 		}
 	}
···
 				if (vid != 0)
 					br_nd_send(br, p, skb, n,
 						   skb->vlan_proto,
-						   skb_vlan_tag_get(skb), msg);
+						   skb_vlan_tag_get(skb));
 				else
-					br_nd_send(br, p, skb, n, 0, 0, msg);
+					br_nd_send(br, p, skb, n, 0, 0);
 				replied = true;
 			}
 

net/bridge/br_mrp_netlink.c

···
 br_mrp_start_test_policy[IFLA_BRIDGE_MRP_START_TEST_MAX + 1] = {
 	[IFLA_BRIDGE_MRP_START_TEST_UNSPEC]	= { .type = NLA_REJECT },
 	[IFLA_BRIDGE_MRP_START_TEST_RING_ID]	= { .type = NLA_U32 },
-	[IFLA_BRIDGE_MRP_START_TEST_INTERVAL]	= { .type = NLA_U32 },
+	[IFLA_BRIDGE_MRP_START_TEST_INTERVAL]	= NLA_POLICY_MIN(NLA_U32, 1),
 	[IFLA_BRIDGE_MRP_START_TEST_MAX_MISS]	= { .type = NLA_U32 },
 	[IFLA_BRIDGE_MRP_START_TEST_PERIOD]	= { .type = NLA_U32 },
 	[IFLA_BRIDGE_MRP_START_TEST_MONITOR]	= { .type = NLA_U32 },
···
 br_mrp_start_in_test_policy[IFLA_BRIDGE_MRP_START_IN_TEST_MAX + 1] = {
 	[IFLA_BRIDGE_MRP_START_IN_TEST_UNSPEC]	= { .type = NLA_REJECT },
 	[IFLA_BRIDGE_MRP_START_IN_TEST_IN_ID]	= { .type = NLA_U32 },
-	[IFLA_BRIDGE_MRP_START_IN_TEST_INTERVAL]	= { .type = NLA_U32 },
+	[IFLA_BRIDGE_MRP_START_IN_TEST_INTERVAL]	= NLA_POLICY_MIN(NLA_U32, 1),
 	[IFLA_BRIDGE_MRP_START_IN_TEST_MAX_MISS]	= { .type = NLA_U32 },
 	[IFLA_BRIDGE_MRP_START_IN_TEST_PERIOD]	= { .type = NLA_U32 },
 };

net/core/dev.c

···
 	 * segmentation-offloads.rst).
 	 */
 	if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4) {
-		struct iphdr *iph = skb->encapsulation ?
-				    inner_ip_hdr(skb) : ip_hdr(skb);
+		const struct iphdr *iph;
+		struct iphdr _iph;
+		int nhoff = skb->encapsulation ?
+			    skb_inner_network_offset(skb) :
+			    skb_network_offset(skb);
 
-		if (!(iph->frag_off & htons(IP_DF)))
+		iph = skb_header_pointer(skb, nhoff, sizeof(_iph), &_iph);
+
+		if (!iph || !(iph->frag_off & htons(IP_DF)))
 			features &= ~dev->mangleid_features;
 	}
 

net/hsr/hsr_device.c

···
 static int hsr_ndo_vlan_rx_add_vid(struct net_device *dev,
 				   __be16 proto, u16 vid)
 {
-	bool is_slave_a_added = false;
-	bool is_slave_b_added = false;
+	struct net_device *slave_a_dev = NULL;
+	struct net_device *slave_b_dev = NULL;
 	struct hsr_port *port;
 	struct hsr_priv *hsr;
 	int ret = 0;
···
 		switch (port->type) {
 		case HSR_PT_SLAVE_A:
 			if (ret) {
-				/* clean up Slave-B */
 				netdev_err(dev, "add vid failed for Slave-A\n");
-				if (is_slave_b_added)
-					vlan_vid_del(port->dev, proto, vid);
-				return ret;
+				goto unwind;
 			}
-
-			is_slave_a_added = true;
+			slave_a_dev = port->dev;
 			break;
-
 		case HSR_PT_SLAVE_B:
 			if (ret) {
-				/* clean up Slave-A */
 				netdev_err(dev, "add vid failed for Slave-B\n");
-				if (is_slave_a_added)
-					vlan_vid_del(port->dev, proto, vid);
-				return ret;
+				goto unwind;
 			}
-
-			is_slave_b_added = true;
+			slave_b_dev = port->dev;
 			break;
 		default:
+			if (ret)
+				goto unwind;
 			break;
 		}
 	}
 
 	return 0;
+
+unwind:
+	if (slave_a_dev)
+		vlan_vid_del(slave_a_dev, proto, vid);
+
+	if (slave_b_dev)
+		vlan_vid_del(slave_b_dev, proto, vid);
+
+	return ret;
 }
 
 static int hsr_ndo_vlan_rx_kill_vid(struct net_device *dev,

net/hsr/hsr_framereg.c

···
 	hsr_free_node(node);
 }
 
+static void hsr_lock_seq_out_pair(struct hsr_node *node_a,
+				  struct hsr_node *node_b)
+{
+	if (node_a == node_b) {
+		spin_lock_bh(&node_a->seq_out_lock);
+		return;
+	}
+
+	if (node_a < node_b) {
+		spin_lock_bh(&node_a->seq_out_lock);
+		spin_lock_nested(&node_b->seq_out_lock, SINGLE_DEPTH_NESTING);
+	} else {
+		spin_lock_bh(&node_b->seq_out_lock);
+		spin_lock_nested(&node_a->seq_out_lock, SINGLE_DEPTH_NESTING);
+	}
+}
+
+static void hsr_unlock_seq_out_pair(struct hsr_node *node_a,
+				    struct hsr_node *node_b)
+{
+	if (node_a == node_b) {
+		spin_unlock_bh(&node_a->seq_out_lock);
+		return;
+	}
+
+	if (node_a < node_b) {
+		spin_unlock(&node_b->seq_out_lock);
+		spin_unlock_bh(&node_a->seq_out_lock);
+	} else {
+		spin_unlock(&node_a->seq_out_lock);
+		spin_unlock_bh(&node_b->seq_out_lock);
+	}
+}
+
 void hsr_del_nodes(struct list_head *node_db)
 {
 	struct hsr_node *node;
···
 	}
 
 	ether_addr_copy(node_real->macaddress_B, ethhdr->h_source);
-	spin_lock_bh(&node_real->seq_out_lock);
+	hsr_lock_seq_out_pair(node_real, node_curr);
 	for (i = 0; i < HSR_PT_PORTS; i++) {
 		if (!node_curr->time_in_stale[i] &&
 		    time_after(node_curr->time_in[i], node_real->time_in[i])) {
···
 				  src_blk->seq_nrs[i], HSR_SEQ_BLOCK_SIZE);
 		}
 	}
-	spin_unlock_bh(&node_real->seq_out_lock);
+	hsr_unlock_seq_out_pair(node_real, node_curr);
 	node_real->addr_B_port = port_rcv->type;
 
 	spin_lock_bh(&hsr->list_lock);

net/ipv6/addrconf.c

···
 		if ((ifp->flags & IFA_F_PERMANENT) &&
 		    fixup_permanent_addr(net, idev, ifp) < 0) {
 			write_unlock_bh(&idev->lock);
-			in6_ifa_hold(ifp);
-			ipv6_del_addr(ifp);
-			write_lock_bh(&idev->lock);
 
 			net_info_ratelimited("%s: Failed to add prefix route for address %pI6c; dropping\n",
 					     idev->dev->name, &ifp->addr);
+			in6_ifa_hold(ifp);
+			ipv6_del_addr(ifp);
+			write_lock_bh(&idev->lock);
 		}
 	}
 

net/ipv6/datagram.c

···
 {
 	struct in6_pktinfo *src_info;
 	struct cmsghdr *cmsg;
+	struct ipv6_rt_hdr *orthdr;
 	struct ipv6_rt_hdr *rthdr;
 	struct ipv6_opt_hdr *hdr;
 	struct ipv6_txoptions *opt = ipc6->opt;
···
 				goto exit_f;
 			}
 			if (cmsg->cmsg_type == IPV6_DSTOPTS) {
+				if (opt->dst1opt)
+					opt->opt_flen -= ipv6_optlen(opt->dst1opt);
 				opt->opt_flen += len;
 				opt->dst1opt = hdr;
 			} else {
+				if (opt->dst0opt)
+					opt->opt_nflen -= ipv6_optlen(opt->dst0opt);
 				opt->opt_nflen += len;
 				opt->dst0opt = hdr;
 			}
···
 				goto exit_f;
 			}
 
+			orthdr = opt->srcrt;
+			if (orthdr)
+				opt->opt_nflen -= ((orthdr->hdrlen + 1) << 3);
 			opt->opt_nflen += len;
 			opt->srcrt = rthdr;
 
 			if (cmsg->cmsg_type == IPV6_2292RTHDR && opt->dst1opt) {
 				int dsthdrlen = ((opt->dst1opt->hdrlen+1)<<3);
 
+				if (opt->dst0opt)
+					opt->opt_nflen -= ipv6_optlen(opt->dst0opt);
 				opt->opt_nflen += dsthdrlen;
 				opt->dst0opt = opt->dst1opt;
 				opt->dst1opt = NULL;

net/ipv6/icmp.c

···
 	if (!skb2)
 		return 1;
 
+	/* Remove debris left by IPv4 stack. */
+	memset(IP6CB(skb2), 0, sizeof(*IP6CB(skb2)));
+
 	skb_dst_drop(skb2);
 	skb_pull(skb2, nhs);
 	skb_reset_network_header(skb2);

net/ipv6/ioam6.c

···
 				    struct ioam6_namespace *ns,
 				    struct ioam6_trace_hdr *trace,
 				    struct ioam6_schema *sc,
-				    u8 sclen, bool is_input)
+				    unsigned int sclen, bool is_input)
 {
 	struct net_device *dev = skb_dst_dev(skb);
 	struct timespec64 ts;
···
 			   bool is_input)
 {
 	struct ioam6_schema *sc;
-	u8 sclen = 0;
+	unsigned int sclen = 0;
 
 	/* Skip if Overflow flag is set
 	 */

net/ipv6/ip6_fib.c

···
 
 void fib6_metric_set(struct fib6_info *f6i, int metric, u32 val)
 {
+	struct dst_metrics *m;
+
 	if (!f6i)
 		return;
 
-	if (f6i->fib6_metrics == &dst_default_metrics) {
+	if (READ_ONCE(f6i->fib6_metrics) == &dst_default_metrics) {
+		struct dst_metrics *dflt = (struct dst_metrics *)&dst_default_metrics;
 		struct dst_metrics *p = kzalloc_obj(*p, GFP_ATOMIC);
 
 		if (!p)
 			return;
 
+		p->metrics[metric - 1] = val;
 		refcount_set(&p->refcnt, 1);
-		f6i->fib6_metrics = p;
+		if (cmpxchg(&f6i->fib6_metrics, dflt, p) != dflt)
+			kfree(p);
+		else
+			return;
 	}
 
-	f6i->fib6_metrics->metrics[metric - 1] = val;
+	m = READ_ONCE(f6i->fib6_metrics);
+	WRITE_ONCE(m->metrics[metric - 1], val);
 }
 
 /*

net/ipv6/ip6_flowlabel.c

···
 		if (time_after(ttd, fl->expires))
 			fl->expires = ttd;
 		ttd = fl->expires;
-		if (fl->opt && fl->share == IPV6_FL_S_EXCL) {
-			struct ipv6_txoptions *opt = fl->opt;
-			fl->opt = NULL;
-			kfree(opt);
-		}
 		if (!timer_pending(&ip6_fl_gc_timer) ||
 		    time_after(ip6_fl_gc_timer.expires, ttd))
 			mod_timer(&ip6_fl_gc_timer, ttd);

net/ipv6/ip6_tunnel.c

···
 	if (!skb2)
 		return 0;
 
+	/* Remove debris left by IPv6 stack. */
+	memset(IPCB(skb2), 0, sizeof(*IPCB(skb2)));
+
 	skb_dst_drop(skb2);
 
 	skb_pull(skb2, offset);
 	skb_reset_network_header(skb2);
 	eiph = ip_hdr(skb2);
+	if (eiph->version != 4 || eiph->ihl < 5)
+		goto out;
 
 	/* Try to guess incoming interface */
 	rt = ip_route_output_ports(dev_net(skb->dev), &fl4, NULL, eiph->saddr,

net/ipv6/ndisc.c

···
 	ndmsg->nduseropt_icmp_type = icmp6h->icmp6_type;
 	ndmsg->nduseropt_icmp_code = icmp6h->icmp6_code;
 	ndmsg->nduseropt_opts_len = opt->nd_opt_len << 3;
+	ndmsg->nduseropt_pad1 = 0;
+	ndmsg->nduseropt_pad2 = 0;
+	ndmsg->nduseropt_pad3 = 0;
 
 	memcpy(ndmsg + 1, opt, opt->nd_opt_len << 3);
 

net/mpls/af_mpls.c

···
 	return mpls_dereference(net, platform_label[index]);
 }
 
+static struct mpls_route __rcu **mpls_platform_label_rcu(struct net *net, size_t *platform_labels)
+{
+	struct mpls_route __rcu **platform_label;
+	unsigned int sequence;
+
+	do {
+		sequence = read_seqcount_begin(&net->mpls.platform_label_seq);
+		platform_label = rcu_dereference(net->mpls.platform_label);
+		*platform_labels = net->mpls.platform_labels;
+	} while (read_seqcount_retry(&net->mpls.platform_label_seq, sequence));
+
+	return platform_label;
+}
+
 static struct mpls_route *mpls_route_input_rcu(struct net *net, unsigned int index)
 {
 	struct mpls_route __rcu **platform_label;
+	size_t platform_labels;
 
-	if (index >= net->mpls.platform_labels)
+	platform_label = mpls_platform_label_rcu(net, &platform_labels);
+
+	if (index >= platform_labels)
 		return NULL;
 
-	platform_label = rcu_dereference(net->mpls.platform_label);
 	return rcu_dereference(platform_label[index]);
 }
 
···
 	if (index < MPLS_LABEL_FIRST_UNRESERVED)
 		index = MPLS_LABEL_FIRST_UNRESERVED;
 
-	platform_label = rcu_dereference(net->mpls.platform_label);
-	platform_labels = net->mpls.platform_labels;
+	platform_label = mpls_platform_label_rcu(net, &platform_labels);
 
 	if (filter.filter_set)
 		flags |= NLM_F_DUMP_FILTERED;
···
 	}
 
 	/* Update the global pointers */
+	local_bh_disable();
+	write_seqcount_begin(&net->mpls.platform_label_seq);
 	net->mpls.platform_labels = limit;
 	rcu_assign_pointer(net->mpls.platform_label, labels);
+	write_seqcount_end(&net->mpls.platform_label_seq);
+	local_bh_enable();
 
 	mutex_unlock(&net->mpls.platform_mutex);
 
···
 	int i;
 
 	mutex_init(&net->mpls.platform_mutex);
+	seqcount_mutex_init(&net->mpls.platform_label_seq, &net->mpls.platform_mutex);
+
 	net->mpls.platform_labels = 0;
 	net->mpls.platform_label = NULL;
 	net->mpls.ip_ttl_propagate = 1;

net/mptcp/protocol.c

···
 static int __mptcp_recvmsg_mskq(struct sock *sk, struct msghdr *msg,
 				size_t len, int flags, int copied_total,
 				struct scm_timestamping_internal *tss,
-				int *cmsg_flags)
+				int *cmsg_flags, struct sk_buff **last)
 {
 	struct mptcp_sock *msk = mptcp_sk(sk);
 	struct sk_buff *skb, *tmp;
···
 			/* skip already peeked skbs */
 			if (total_data_len + data_len <= copied_total) {
 				total_data_len += data_len;
+				*last = skb;
 				continue;
 			}
 
···
 			}
 
 			mptcp_eat_recv_skb(sk, skb);
+		} else {
+			*last = skb;
 		}
 
 		if (copied >= len)
···
 		cmsg_flags = MPTCP_CMSG_INQ;
 
 	while (copied < len) {
+		struct sk_buff *last = NULL;
 		int err, bytes_read;
 
 		bytes_read = __mptcp_recvmsg_mskq(sk, msg, len - copied, flags,
-						  copied, &tss, &cmsg_flags);
+						  copied, &tss, &cmsg_flags,
+						  &last);
 		if (unlikely(bytes_read < 0)) {
 			if (!copied)
 				copied = bytes_read;
···
 
 		pr_debug("block timeout %ld\n", timeo);
 		mptcp_cleanup_rbuf(msk, copied);
-		err = sk_wait_data(sk, &timeo, NULL);
+		err = sk_wait_data(sk, &timeo, last);
 		if (err < 0) {
 			err = copied ? : err;
 			goto out_err;

net/netfilter/ipset/ip_set_core.c

···
  *
  */
 ip_set_id_t
-ip_set_get_byname(struct net *net, const char *name, struct ip_set **set)
+ip_set_get_byname(struct net *net, const struct nlattr *name, struct ip_set **set)
 {
 	ip_set_id_t i, index = IPSET_INVALID_ID;
 	struct ip_set *s;
···
 	rcu_read_lock();
 	for (i = 0; i < inst->ip_set_max; i++) {
 		s = rcu_dereference(inst->ip_set_list)[i];
-		if (s && STRNCMP(s->name, name)) {
+		if (s && nla_strcmp(name, s->name) == 0) {
 			__ip_set_get(s);
 			index = i;
 			*set = s;

net/netfilter/ipset/ip_set_hash_gen.h

···
 			if (!test_bit(i, n->used))
 				k++;
 		}
-		if (n->pos == 0 && k == 0) {
+		if (k == n->pos) {
 			t->hregion[r].ext_size -= ext_size(n->size, dsize);
 			rcu_assign_pointer(hbucket(t, key), NULL);
 			kfree_rcu(n, rcu);

net/netfilter/ipset/ip_set_list_set.c

···
 	ret = ip_set_get_extensions(set, tb, &ext);
 	if (ret)
 		return ret;
-	e.id = ip_set_get_byname(map->net, nla_data(tb[IPSET_ATTR_NAME]), &s);
+	e.id = ip_set_get_byname(map->net, tb[IPSET_ATTR_NAME], &s);
 	if (e.id == IPSET_INVALID_ID)
 		return -IPSET_ERR_NAME;
 	/* "Loop detection" */
···
 
 	if (tb[IPSET_ATTR_NAMEREF]) {
 		e.refid = ip_set_get_byname(map->net,
-					    nla_data(tb[IPSET_ATTR_NAMEREF]),
+					    tb[IPSET_ATTR_NAMEREF],
 					    &s);
 		if (e.refid == IPSET_INVALID_ID) {
 			ret = -IPSET_ERR_NAMEREF;

net/netfilter/nf_conntrack_helper.c

···
 	 */
 	synchronize_rcu();
 
-	nf_ct_expect_iterate_destroy(expect_iter_me, NULL);
+	nf_ct_expect_iterate_destroy(expect_iter_me, me);
 	nf_ct_iterate_destroy(unhelp, me);
 
 	/* nf_ct_iterate_destroy() does an unconditional synchronize_rcu() as

net/netfilter/nf_conntrack_netlink.c

···
 
 static struct nf_conntrack_expect *
 ctnetlink_alloc_expect(const struct nlattr *const cda[], struct nf_conn *ct,
-		       struct nf_conntrack_helper *helper,
 		       struct nf_conntrack_tuple *tuple,
 		       struct nf_conntrack_tuple *mask);
 
···
 {
 	struct nlattr *cda[CTA_EXPECT_MAX+1];
 	struct nf_conntrack_tuple tuple, mask;
-	struct nf_conntrack_helper *helper = NULL;
 	struct nf_conntrack_expect *exp;
 	int err;
 
···
 	if (err < 0)
 		return err;
 
-	if (cda[CTA_EXPECT_HELP_NAME]) {
-		const char *helpname = nla_data(cda[CTA_EXPECT_HELP_NAME]);
-
-		helper = __nf_conntrack_helper_find(helpname, nf_ct_l3num(ct),
-						    nf_ct_protonum(ct));
-		if (helper == NULL)
-			return -EOPNOTSUPP;
-	}
-
 	exp = ctnetlink_alloc_expect((const struct nlattr * const *)cda, ct,
-				     helper, &tuple, &mask);
+				     &tuple, &mask);
 	if (IS_ERR(exp))
 		return PTR_ERR(exp);
 
···
 
 static struct nf_conntrack_expect *
 ctnetlink_alloc_expect(const struct nlattr * const cda[], struct nf_conn *ct,
-		       struct nf_conntrack_helper *helper,
 		       struct nf_conntrack_tuple *tuple,
 		       struct nf_conntrack_tuple *mask)
 {
 	struct net *net = read_pnet(&ct->ct_net);
+	struct nf_conntrack_helper *helper;
 	struct nf_conntrack_expect *exp;
 	struct nf_conn_help *help;
 	u32 class = 0;
···
 	if (!help)
 		return ERR_PTR(-EOPNOTSUPP);
 
-	if (cda[CTA_EXPECT_CLASS] && helper) {
+	helper = rcu_dereference(help->helper);
+	if (!helper)
+		return ERR_PTR(-EOPNOTSUPP);
+
+	if (cda[CTA_EXPECT_CLASS]) {
 		class = ntohl(nla_get_be32(cda[CTA_EXPECT_CLASS]));
 		if (class > helper->expect_class_max)
 			return ERR_PTR(-EINVAL);
···
 #ifdef CONFIG_NF_CONNTRACK_ZONES
 	exp->zone = ct->zone;
 #endif
-	if (!helper)
-		helper = rcu_dereference(help->helper);
 	rcu_assign_pointer(exp->helper, helper);
 	exp->tuple = *tuple;
 	exp->mask.src.u3 = mask->src.u3;
···
 						 exp, nf_ct_l3num(ct));
 		if (err < 0)
 			goto err_out;
+#if IS_ENABLED(CONFIG_NF_NAT)
+	} else {
+		memset(&exp->saved_addr, 0, sizeof(exp->saved_addr));
+		memset(&exp->saved_proto, 0, sizeof(exp->saved_proto));
+		exp->dir = 0;
+#endif
 	}
 	return exp;
 err_out:
···
 {
 	struct nf_conntrack_tuple tuple, mask, master_tuple;
 	struct nf_conntrack_tuple_hash *h = NULL;
-	struct nf_conntrack_helper *helper = NULL;
 	struct nf_conntrack_expect *exp;
 	struct nf_conn *ct;
 	int err;
···
 	ct = nf_ct_tuplehash_to_ctrack(h);
 
 	rcu_read_lock();
-	if (cda[CTA_EXPECT_HELP_NAME]) {
-		const char *helpname = nla_data(cda[CTA_EXPECT_HELP_NAME]);
-
-		helper = __nf_conntrack_helper_find(helpname, u3,
-						    nf_ct_protonum(ct));
-		if (helper == NULL) {
-			rcu_read_unlock();
-#ifdef CONFIG_MODULES
-			if (request_module("nfct-helper-%s", helpname) < 0) {
-				err = -EOPNOTSUPP;
-				goto err_ct;
-			}
-			rcu_read_lock();
-			helper = __nf_conntrack_helper_find(helpname, u3,
-							    nf_ct_protonum(ct));
-			if (helper) {
-				err = -EAGAIN;
-				goto err_rcu;
-			}
-			rcu_read_unlock();
-#endif
-			err = -EOPNOTSUPP;
-			goto err_ct;
-		}
-	}
-
-	exp = ctnetlink_alloc_expect(cda, ct, helper, &tuple, &mask);
+	exp = ctnetlink_alloc_expect(cda, ct, &tuple, &mask);
 	if (IS_ERR(exp)) {
 		err = PTR_ERR(exp);
 		goto err_rcu;
···
 	nf_ct_expect_put(exp);
 err_rcu:
 	rcu_read_unlock();
-err_ct:
 	nf_ct_put(ct);
+
 	return err;
 }
 

net/netfilter/nf_flow_table_offload.c

···
 #include <net/netfilter/nf_conntrack_core.h>
 #include <net/netfilter/nf_conntrack_tuple.h>
 
+#define NF_FLOW_RULE_ACTION_MAX	24
+
 static struct workqueue_struct *nf_flow_offload_add_wq;
 static struct workqueue_struct *nf_flow_offload_del_wq;
 static struct workqueue_struct *nf_flow_offload_stats_wq;
···
 static inline struct flow_action_entry *
 flow_action_entry_next(struct nf_flow_rule *flow_rule)
 {
-	int i = flow_rule->rule->action.num_entries++;
+	int i;
+
+	if (unlikely(flow_rule->rule->action.num_entries >= NF_FLOW_RULE_ACTION_MAX))
+		return NULL;
+
+	i = flow_rule->rule->action.num_entries++;
 
 	return &flow_rule->rule->action.entries[i];
 }
···
 	const unsigned char *addr;
 	u32 mask, val;
 	u16 val16;
+
+	if (!entry0 || !entry1)
+		return -E2BIG;
 
 	this_tuple = &flow->tuplehash[dir].tuple;
 
···
 	u8 nud_state;
 	u16 val16;
 
+	if (!entry0 || !entry1)
+		return -E2BIG;
+
 	this_tuple = &flow->tuplehash[dir].tuple;
 
 	switch (this_tuple->xmit_type) {
···
 	return 0;
 }
 
-static void flow_offload_ipv4_snat(struct net *net,
-				   const struct flow_offload *flow,
-				   enum flow_offload_tuple_dir dir,
-				   struct nf_flow_rule *flow_rule)
+static int flow_offload_ipv4_snat(struct net *net,
+				  const struct flow_offload *flow,
+				  enum flow_offload_tuple_dir dir,
+				  struct nf_flow_rule *flow_rule)
 {
 	struct flow_action_entry *entry = flow_action_entry_next(flow_rule);
 	u32 mask = ~htonl(0xffffffff);
 	__be32 addr;
 	u32 offset;
+
+	if (!entry)
+		return -E2BIG;
 
 	switch (dir) {
 	case FLOW_OFFLOAD_DIR_ORIGINAL:
···
 		offset = offsetof(struct iphdr, daddr);
 		break;
 	default:
-		return;
+		return -EOPNOTSUPP;
 	}
 
 	flow_offload_mangle(entry, FLOW_ACT_MANGLE_HDR_TYPE_IP4, offset,
 			    &addr, &mask);
+	return 0;
 }
 
-static void flow_offload_ipv4_dnat(struct net *net,
-				   const struct flow_offload *flow,
-				   enum flow_offload_tuple_dir dir,
-				   struct nf_flow_rule *flow_rule)
+static int flow_offload_ipv4_dnat(struct net *net,
+				  const struct flow_offload *flow,
+				  enum flow_offload_tuple_dir dir,
+				  struct nf_flow_rule *flow_rule)
 {
 	struct flow_action_entry *entry = flow_action_entry_next(flow_rule);
 	u32 mask = ~htonl(0xffffffff);
 	__be32 addr;
 	u32 offset;
+
+	if (!entry)
+		return -E2BIG;
 
 	switch (dir) {
 	case FLOW_OFFLOAD_DIR_ORIGINAL:
···
 		offset = offsetof(struct iphdr, saddr);
 		break;
 	default:
-		return;
+		return -EOPNOTSUPP;
 	}
 
 	flow_offload_mangle(entry, FLOW_ACT_MANGLE_HDR_TYPE_IP4, offset,
 			    &addr, &mask);
+	return 0;
 }
 
-static void flow_offload_ipv6_mangle(struct nf_flow_rule *flow_rule,
+static int flow_offload_ipv6_mangle(struct nf_flow_rule *flow_rule,
 				     unsigned int offset,
 				     const __be32 *addr, const __be32 *mask)
 {
···
 
 	for (i = 0; i < sizeof(struct in6_addr) / sizeof(u32); i++) {
 		entry = flow_action_entry_next(flow_rule);
+		if (!entry)
+			return -E2BIG;
+
 		flow_offload_mangle(entry, FLOW_ACT_MANGLE_HDR_TYPE_IP6,
 				    offset + i * sizeof(u32), &addr[i], mask);
 	}
+
+	return 0;
 }
 
-static void flow_offload_ipv6_snat(struct net *net,
-				   const struct flow_offload *flow,
-				   enum flow_offload_tuple_dir dir,
-				   struct nf_flow_rule *flow_rule)
+static int flow_offload_ipv6_snat(struct net *net,
+				  const struct flow_offload *flow,
+				  enum flow_offload_tuple_dir dir,
+				  struct nf_flow_rule *flow_rule)
 {
 	u32 mask = ~htonl(0xffffffff);
 	const __be32 *addr;
···
 		offset = offsetof(struct ipv6hdr, daddr);
 		break;
 	default:
-		return;
+		return -EOPNOTSUPP;
 	}
 
-	flow_offload_ipv6_mangle(flow_rule, offset, addr, &mask);
+	return flow_offload_ipv6_mangle(flow_rule, offset, addr, &mask);
 }
 
-static void flow_offload_ipv6_dnat(struct net *net,
-				   const struct flow_offload *flow,
-				   enum flow_offload_tuple_dir dir,
-				   struct nf_flow_rule *flow_rule)
+static int flow_offload_ipv6_dnat(struct net *net,
+				  const struct flow_offload *flow,
+				  enum flow_offload_tuple_dir dir,
+				  struct nf_flow_rule *flow_rule)
 {
 	u32 mask = ~htonl(0xffffffff);
 	const __be32 *addr;
···
 		offset = offsetof(struct ipv6hdr, saddr);
 		break;
 	default:
-		return;
+		return -EOPNOTSUPP;
 	}
 
-	flow_offload_ipv6_mangle(flow_rule, offset, addr, &mask);
+	return flow_offload_ipv6_mangle(flow_rule, offset, addr, &mask);
 }
 
 static int flow_offload_l4proto(const struct flow_offload *flow)
···
 	return type;
 }
 
-static void flow_offload_port_snat(struct net *net,
-				   const struct flow_offload *flow,
-				   enum flow_offload_tuple_dir dir,
-				   struct nf_flow_rule *flow_rule)
+static int flow_offload_port_snat(struct net *net,
+				  const struct flow_offload *flow,
+				  enum flow_offload_tuple_dir dir,
+				  struct nf_flow_rule *flow_rule)
 {
 	struct flow_action_entry *entry = flow_action_entry_next(flow_rule);
 	u32 mask, port;
 	u32 offset;
+
+	if (!entry)
+		return -E2BIG;
 
 	switch (dir) {
 	case FLOW_OFFLOAD_DIR_ORIGINAL:
···
 		mask = ~htonl(0xffff);
 		break;
 	default:
-		return;
+		return -EOPNOTSUPP;
 	}
 
 	flow_offload_mangle(entry, flow_offload_l4proto(flow), offset,
 			    &port, &mask);
+	return 0;
 }
 
-static void flow_offload_port_dnat(struct net *net,
-				   const struct flow_offload *flow,
-				   enum flow_offload_tuple_dir dir,
-				   struct nf_flow_rule *flow_rule)
+static int flow_offload_port_dnat(struct net *net,
+				  const struct flow_offload *flow,
+				  enum flow_offload_tuple_dir dir,
+				  struct nf_flow_rule *flow_rule)
 {
 	struct flow_action_entry *entry = flow_action_entry_next(flow_rule);
 	u32 mask, port;
 	u32 offset;
+
+	if (!entry)
+		return -E2BIG;
 
 	switch (dir) {
 	case FLOW_OFFLOAD_DIR_ORIGINAL:
···
 		mask = ~htonl(0xffff0000);
 		break;
 	default:
-		return;
+		return -EOPNOTSUPP;
 	}
 
 	flow_offload_mangle(entry, flow_offload_l4proto(flow), offset,
 			    &port, &mask);
+	return 0;
 }
 
-static void flow_offload_ipv4_checksum(struct net *net,
-				       const struct flow_offload *flow,
-				       struct nf_flow_rule *flow_rule)
+static int flow_offload_ipv4_checksum(struct net *net,
+				      const struct flow_offload *flow,
+				      struct nf_flow_rule *flow_rule)
 {
 	u8 protonum = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.l4proto;
 	struct flow_action_entry *entry = flow_action_entry_next(flow_rule);
+
+	if (!entry)
+		return -E2BIG;
 
 	entry->id = FLOW_ACTION_CSUM;
 	entry->csum_flags = TCA_CSUM_UPDATE_FLAG_IPV4HDR;
···
 		entry->csum_flags |= TCA_CSUM_UPDATE_FLAG_UDP;
 		break;
 	}
+
+	return 0;
 }
 
-static void flow_offload_redirect(struct net *net,
-				  const struct flow_offload *flow,
-				  enum flow_offload_tuple_dir dir,
-				  struct nf_flow_rule *flow_rule)
+static int flow_offload_redirect(struct net *net,
+				 const struct flow_offload *flow,
+				 enum flow_offload_tuple_dir dir,
+				 struct nf_flow_rule *flow_rule)
 {
 	const struct flow_offload_tuple *this_tuple, *other_tuple;
 	struct flow_action_entry *entry;
···
 		ifindex = other_tuple->iifidx;
 		break;
 	default:
-		return;
+		return -EOPNOTSUPP;
 	}
 
 	dev = dev_get_by_index(net, ifindex);
 	if (!dev)
-		return;
+		return -ENODEV;
 
 	entry = flow_action_entry_next(flow_rule);
+	if (!entry) {
+		dev_put(dev);
+		return -E2BIG;
+	}
+
 	entry->id = FLOW_ACTION_REDIRECT;
 	entry->dev = dev;
+
+	return 0;
 }
 
-static void flow_offload_encap_tunnel(const struct flow_offload *flow,
-				      enum flow_offload_tuple_dir dir,
-				      struct nf_flow_rule *flow_rule)
+static int flow_offload_encap_tunnel(const struct flow_offload *flow,
+				     enum flow_offload_tuple_dir dir,
+				     struct nf_flow_rule *flow_rule)
 {
 	const struct flow_offload_tuple *this_tuple;
 	struct flow_action_entry *entry;
···
 
 	this_tuple = &flow->tuplehash[dir].tuple;
 	if (this_tuple->xmit_type == FLOW_OFFLOAD_XMIT_DIRECT)
-		return;
+		return 0;
 
 	dst = this_tuple->dst_cache;
 	if (dst && dst->lwtstate) {
···
 		tun_info = lwt_tun_info(dst->lwtstate);
 		if (tun_info && (tun_info->mode & IP_TUNNEL_INFO_TX)) {
 			entry = flow_action_entry_next(flow_rule);
+			if (!entry)
+				return -E2BIG;
 			entry->id = FLOW_ACTION_TUNNEL_ENCAP;
 			entry->tunnel = tun_info;
 		}
 	}
+
+	return 0;
 }
 
-static void flow_offload_decap_tunnel(const struct flow_offload *flow,
-				      enum flow_offload_tuple_dir dir,
-				      struct nf_flow_rule *flow_rule)
+static int flow_offload_decap_tunnel(const struct flow_offload *flow,
+				     enum flow_offload_tuple_dir dir,
+				     struct nf_flow_rule *flow_rule)
 {
 	const struct flow_offload_tuple *other_tuple;
 	struct flow_action_entry *entry;
···
 
 	other_tuple = &flow->tuplehash[!dir].tuple;
 	if (other_tuple->xmit_type == FLOW_OFFLOAD_XMIT_DIRECT)
-		return;
+		return 0;
 
 	dst = other_tuple->dst_cache;
 	if (dst && dst->lwtstate) {
···
 		tun_info = lwt_tun_info(dst->lwtstate);
 		if (tun_info && (tun_info->mode & IP_TUNNEL_INFO_TX)) {
 			entry = flow_action_entry_next(flow_rule);
+			if (!entry)
+				return -E2BIG;
 			entry->id = FLOW_ACTION_TUNNEL_DECAP;
 		}
 	}
+
+	return 0;
 }
 
 static int
···
 	const struct flow_offload_tuple *tuple;
 	int i;
 
-	flow_offload_decap_tunnel(flow, dir, flow_rule);
-	flow_offload_encap_tunnel(flow, dir, flow_rule);
+	if (flow_offload_decap_tunnel(flow, dir, flow_rule) < 0 ||
+	    flow_offload_encap_tunnel(flow, dir, flow_rule) < 0)
+		return -1;
 
 	if (flow_offload_eth_src(net, flow, dir, flow_rule) < 0 ||
 	    flow_offload_eth_dst(net, flow, dir, flow_rule) < 0)
···
 
 		if (tuple->encap[i].proto == htons(ETH_P_8021Q)) {
 			entry = flow_action_entry_next(flow_rule);
+			if (!entry)
+				return -1;
 			entry->id = FLOW_ACTION_VLAN_POP;
 		}
 	}
···
 			continue;
 
 		entry = flow_action_entry_next(flow_rule);
+		if (!entry)
+			return -1;
 
 		switch (other_tuple->encap[i].proto) {
 		case htons(ETH_P_PPP_SES):
···
 		return -1;
 
 	if (test_bit(NF_FLOW_SNAT, &flow->flags)) {
-		flow_offload_ipv4_snat(net, flow, dir, flow_rule);
-		flow_offload_port_snat(net, flow, dir, flow_rule);
+		if (flow_offload_ipv4_snat(net, flow, dir, flow_rule) < 0 ||
+		    flow_offload_port_snat(net, flow, dir, flow_rule) < 0)
+			return -1;
 	}
 	if (test_bit(NF_FLOW_DNAT, &flow->flags)) {
-		flow_offload_ipv4_dnat(net, flow, dir, flow_rule);
-		flow_offload_port_dnat(net, flow, dir, flow_rule);
+		if (flow_offload_ipv4_dnat(net, flow, dir, flow_rule) < 0 ||
+		    flow_offload_port_dnat(net, flow, dir, flow_rule) < 0)
+			return -1;
 	}
 	if (test_bit(NF_FLOW_SNAT, &flow->flags) ||
 	    test_bit(NF_FLOW_DNAT, &flow->flags))
-		flow_offload_ipv4_checksum(net, flow, flow_rule);
+		if (flow_offload_ipv4_checksum(net, flow, flow_rule) < 0)
+			return -1;
 
-	flow_offload_redirect(net, flow, dir, flow_rule);
+	if (flow_offload_redirect(net, flow, dir, flow_rule) < 0)
+		return -1;
 
 	return 0;
 }
···
 		return -1;
 
 	if (test_bit(NF_FLOW_SNAT, &flow->flags)) {
-		flow_offload_ipv6_snat(net, flow, dir, flow_rule);
-		flow_offload_port_snat(net, flow, dir, flow_rule);
+		if (flow_offload_ipv6_snat(net, flow, dir, flow_rule) < 0 ||
+		    flow_offload_port_snat(net, flow, dir, flow_rule) < 0)
+			return -1;
 	}
 	if (test_bit(NF_FLOW_DNAT, &flow->flags)) {
-		flow_offload_ipv6_dnat(net, flow, dir, flow_rule);
-		flow_offload_port_dnat(net, flow, dir, flow_rule);
+		if (flow_offload_ipv6_dnat(net, flow, dir, flow_rule) < 0 ||
+		    flow_offload_port_dnat(net, flow, dir, flow_rule) < 0)
+			return -1;
 	}
 
-	flow_offload_redirect(net, flow, dir, flow_rule);
+	if (flow_offload_redirect(net, flow, dir, flow_rule) < 0)
+		return -1;
 
 	return 0;
 }
 EXPORT_SYMBOL_GPL(nf_flow_rule_route_ipv6);
-
-#define NF_FLOW_RULE_ACTION_MAX	16
 
 static struct nf_flow_rule *
 nf_flow_offload_rule_alloc(struct net *net,

net/netfilter/nf_tables_api.c

···
 	switch (data->verdict.code) {
 	case NF_ACCEPT:
 	case NF_DROP:
-	case NF_QUEUE:
-		break;
 	case NFT_CONTINUE:
 	case NFT_BREAK:
 	case NFT_RETURN:
···
 
 		data->verdict.chain = chain;
 		break;
+	case NF_QUEUE:
+		/* The nft_queue expression is used for this purpose, an
+		 * immediate NF_QUEUE verdict should not ever be seen here.
+		 */
+		fallthrough;
 	default:
 		return -EINVAL;
 	}

net/netfilter/nfnetlink_log.c

···
 		+ nla_total_size(plen)			/* prefix */
 		+ nla_total_size(sizeof(struct nfulnl_msg_packet_hw))
 		+ nla_total_size(sizeof(struct nfulnl_msg_packet_timestamp))
-		+ nla_total_size(sizeof(struct nfgenmsg));	/* NLMSG_DONE */
+		+ nlmsg_total_size(sizeof(struct nfgenmsg));	/* NLMSG_DONE */
 
 	if (in && skb_mac_header_was_set(skb)) {
 		size += nla_total_size(skb->dev->hard_header_len)

net/netfilter/x_tables.c

···
 				    par->match->table, par->table);
 		return -EINVAL;
 	}
+
+	/* NFPROTO_UNSPEC implies NF_INET_* hooks which do not overlap with
+	 * NF_ARP_IN,OUT,FORWARD, allow explicit extensions with NFPROTO_ARP
+	 * support.
+	 */
+	if (par->family == NFPROTO_ARP &&
+	    par->match->family != NFPROTO_ARP) {
+		pr_info_ratelimited("%s_tables: %s match: not valid for this family\n",
+				    xt_prefix[par->family], par->match->name);
+		return -EINVAL;
+	}
 	if (par->match->hooks && (par->hook_mask & ~par->match->hooks) != 0) {
 		char used[64], allow[64];
 
···
 				    par->target->table, par->table);
 		return -EINVAL;
 	}
+
+	/* NFPROTO_UNSPEC implies NF_INET_* hooks which do not overlap with
+	 * NF_ARP_IN,OUT,FORWARD, allow explicit extensions with NFPROTO_ARP
+	 * support.
+	 */
+	if (par->family == NFPROTO_ARP &&
+	    par->target->family != NFPROTO_ARP) {
+		pr_info_ratelimited("%s_tables: %s target: not valid for this family\n",
+				    xt_prefix[par->family], par->target->name);
+		return -EINVAL;
+	}
+
 	if (par->target->hooks && (par->hook_mask & ~par->target->hooks) != 0) {
 		char used[64], allow[64];
 

net/netfilter/xt_cgroup.c

···
 
 	info->priv = NULL;
 	if (info->has_path) {
+		if (strnlen(info->path, sizeof(info->path)) >= sizeof(info->path))
+			return -ENAMETOOLONG;
+
 		cgrp = cgroup_get_from_path(info->path);
 		if (IS_ERR(cgrp)) {
 			pr_info_ratelimited("invalid path, errno=%ld\n",
···
 
 	info->priv = NULL;
 	if (info->has_path) {
+		if (strnlen(info->path, sizeof(info->path)) >= sizeof(info->path))
+			return -ENAMETOOLONG;
+
 		cgrp = cgroup_get_from_path(info->path);
 		if (IS_ERR(cgrp)) {
 			pr_info_ratelimited("invalid path, errno=%ld\n",

net/netfilter/xt_rateest.c

···
 		goto err1;
 	}
 
+	if (strnlen(info->name1, sizeof(info->name1)) >= sizeof(info->name1))
+		return -ENAMETOOLONG;
+	if (strnlen(info->name2, sizeof(info->name2)) >= sizeof(info->name2))
+		return -ENAMETOOLONG;
+
 	ret  = -ENOENT;
 	est1 = xt_rateest_lookup(par->net, info->name1);
 	if (!est1)

net/qrtr/af_qrtr.c

···
  * @ep: endpoint
  * @ref: reference count for node
  * @nid: node id
- * @qrtr_tx_flow: tree of qrtr_tx_flow, keyed by node << 32 | port
+ * @qrtr_tx_flow: xarray of qrtr_tx_flow, keyed by node << 32 | port
  * @qrtr_tx_lock: lock for qrtr_tx_flow inserts
  * @rx_queue: receive queue
  * @item: list item for broadcast list
···
 	struct kref ref;
 	unsigned int nid;
 
-	struct radix_tree_root qrtr_tx_flow;
+	struct xarray qrtr_tx_flow;
 	struct mutex qrtr_tx_lock; /* for qrtr_tx_flow */
 
 	struct sk_buff_head rx_queue;
···
 	struct qrtr_tx_flow *flow;
 	unsigned long flags;
 	void __rcu **slot;
+	unsigned long index;
 
 	spin_lock_irqsave(&qrtr_nodes_lock, flags);
 	/* If the node is a bridge for other nodes, there are possibly
···
 	skb_queue_purge(&node->rx_queue);
 
 	/* Free tx flow counters */
-	radix_tree_for_each_slot(slot, &node->qrtr_tx_flow, &iter, 0) {
-		flow = *slot;
-		radix_tree_iter_delete(&node->qrtr_tx_flow, &iter, slot);
+	xa_for_each(&node->qrtr_tx_flow, index, flow)
 		kfree(flow);
-	}
+	xa_destroy(&node->qrtr_tx_flow);
 	kfree(node);
 }
 
···
 
 	key = remote_node << 32 | remote_port;
 
-	rcu_read_lock();
-	flow = radix_tree_lookup(&node->qrtr_tx_flow, key);
-	rcu_read_unlock();
+	flow = xa_load(&node->qrtr_tx_flow, key);
 	if (flow) {
 		spin_lock(&flow->resume_tx.lock);
 		flow->pending = 0;
···
 		return 0;
 
 	mutex_lock(&node->qrtr_tx_lock);
-	flow = radix_tree_lookup(&node->qrtr_tx_flow, key);
+	flow = xa_load(&node->qrtr_tx_flow, key);
 	if (!flow) {
 		flow = kzalloc_obj(*flow);
 		if (flow) {
 			init_waitqueue_head(&flow->resume_tx);
-			if (radix_tree_insert(&node->qrtr_tx_flow, key, flow)) {
+			if (xa_err(xa_store(&node->qrtr_tx_flow, key, flow,
+					    GFP_KERNEL))) {
 				kfree(flow);
 				flow = NULL;
 			}
···
 	unsigned long key = (u64)dest_node << 32 | dest_port;
 	struct qrtr_tx_flow *flow;
 
-	rcu_read_lock();
-	flow = radix_tree_lookup(&node->qrtr_tx_flow, key);
-	rcu_read_unlock();
+	flow = xa_load(&node->qrtr_tx_flow, key);
 	if (flow) {
 		spin_lock_irq(&flow->resume_tx.lock);
 		flow->tx_failed = 1;
···
 	node->nid = QRTR_EP_NID_AUTO;
 	node->ep = ep;
 
-	INIT_RADIX_TREE(&node->qrtr_tx_flow, GFP_KERNEL);
+	xa_init(&node->qrtr_tx_flow);
 	mutex_init(&node->qrtr_tx_lock);
 
 	qrtr_node_assign(node, nid);
···
 	struct qrtr_tx_flow *flow;
 	struct sk_buff *skb;
 	unsigned long flags;
+	unsigned long index;
 	void __rcu **slot;
 
 	mutex_lock(&node->ep_lock);
···
 
 	/* Wake up any transmitters waiting for resume-tx from the node */
 	mutex_lock(&node->qrtr_tx_lock);
-	radix_tree_for_each_slot(slot, &node->qrtr_tx_flow, &iter, 0) {
-		flow = *slot;
+	xa_for_each(&node->qrtr_tx_flow, index, flow)
 		wake_up_interruptible_all(&flow->resume_tx);
-	}
 	mutex_unlock(&node->qrtr_tx_lock);
 
 	qrtr_node_release(node);

net/rds/ib_rdma.c

···
 		return ibmr;
 	}
 
-	if (conn)
+	if (conn) {
 		ic = conn->c_transport_data;
+		if (!ic || !ic->i_cm_id || !ic->i_cm_id->qp) {
+			ret = -ENODEV;
+			goto out;
+		}
+	}
 
 	if (!rds_ibdev->mr_8k_pool || !rds_ibdev->mr_1m_pool) {
 		ret = -ENODEV;

net/sched/cls_api.c

···
 	tcm->tcm__pad1 = 0;
 	tcm->tcm__pad2 = 0;
 	tcm->tcm_handle = 0;
+	tcm->tcm_info = 0;
 	if (block->q) {
 		tcm->tcm_ifindex = qdisc_dev(block->q)->ifindex;
 		tcm->tcm_parent = block->q->handle;

net/sched/cls_flow.c

···
 		}
 
 		if (TC_H_MAJ(baseclass) == 0) {
-			struct Qdisc *q = tcf_block_q(tp->chain->block);
+			struct tcf_block *block = tp->chain->block;
+			struct Qdisc *q;
 
+			if (tcf_block_shared(block)) {
+				NL_SET_ERR_MSG(extack,
+					       "Must specify baseclass when attaching flow filter to block");
+				goto err2;
+			}
+
+			q = tcf_block_q(block);
 			baseclass = TC_H_MAKE(q->handle, baseclass);
 		}
 		if (TC_H_MIN(baseclass) == 0)

net/sched/cls_fw.c

···
 	struct nlattr *tb[TCA_FW_MAX + 1];
 	int err;
 
-	if (!opt)
-		return handle ? -EINVAL : 0; /* Succeed if it is old method. */
+	if (!opt) {
+		if (handle)
+			return -EINVAL;
+
+		if (tcf_block_shared(tp->chain->block)) {
+			NL_SET_ERR_MSG(extack,
+				       "Must specify mark when attaching fw filter to block");
+			return -EINVAL;
+		}
+
+		return 0; /* Succeed if it is old method. */
+	}
 
 	err = nla_parse_nested_deprecated(tb, TCA_FW_MAX, opt, fw_policy,
 					  NULL);

net/sched/sch_hfsc.c

···
 rtsc_min(struct runtime_sc *rtsc, struct internal_sc *isc, u64 x, u64 y)
 {
 	u64 y1, y2, dx, dy;
-	u32 dsm;
+	u64 dsm;
 
 	if (isc->sm1 <= isc->sm2) {
 		/* service curve is convex */
···
 	 */
 	dx = (y1 - y) << SM_SHIFT;
 	dsm = isc->sm1 - isc->sm2;
-	do_div(dx, dsm);
+	dx = div64_u64(dx, dsm);
 	/*
 	 * check if (x, y1) belongs to the 1st segment of rtsc.
 	 * if so, add the offset.

net/sched/sch_netem.c

···
 			goto finish_segs;
 		}
 
-		skb->data[get_random_u32_below(skb_headlen(skb))] ^=
-			1<<get_random_u32_below(8);
+		if (skb_headlen(skb))
+			skb->data[get_random_u32_below(skb_headlen(skb))] ^=
+				1 << get_random_u32_below(8);
 	}
 
 	if (unlikely(q->t_len >= sch->limit)) {

net/vmw_vsock/af_vsock.c

···
 		net->vsock.mode = vsock_net_child_mode(current->nsproxy->net_ns);
 
 	net->vsock.child_ns_mode = net->vsock.mode;
+	net->vsock.child_ns_mode_locked = 0;
 	net->vsock.g2h_fallback = 1;
 }
 

net/x25/x25_in.c

···
 	struct sk_buff *skbo, *skbn = skb;
 	struct x25_sock *x25 = x25_sk(sk);
 
+	/* make sure we don't overflow */
+	if (x25->fraglen + skb->len > USHRT_MAX)
+		return 1;
+
 	if (more) {
 		x25->fraglen += skb->len;
 		skb_queue_tail(&x25->fragment_queue, skb);
···
 	if (x25->fraglen > 0) {	/* End of fragment */
 		int len = x25->fraglen + skb->len;
 
-		if ((skbn = alloc_skb(len, GFP_ATOMIC)) == NULL){
-			kfree_skb(skb);
+		skbn = alloc_skb(len, GFP_ATOMIC);
+		if (!skbn)
 			return 1;
-		}
 
 		skb_queue_tail(&x25->fragment_queue, skb);
 

net/x25/x25_subr.c

···
 	skb_queue_purge(&x25->interrupt_in_queue);
 	skb_queue_purge(&x25->interrupt_out_queue);
 	skb_queue_purge(&x25->fragment_queue);
+	x25->fraglen = 0;
 }
 
 

rust/kernel/regulator.rs

···
     prelude::*,
 };
 
-use core::{marker::PhantomData, mem::ManuallyDrop, ptr::NonNull};
+use core::{
+    marker::PhantomData,
+    mem::ManuallyDrop, //
+};
 
 mod private {
     pub trait Sealed {}
···
 ///
 /// # Invariants
 ///
-/// - `inner` is a non-null wrapper over a pointer to a `struct
-///   regulator` obtained from [`regulator_get()`].
+/// - `inner` is a pointer obtained from a successful call to
+///   [`regulator_get()`]. It is treated as an opaque token that may only be
+///   accessed using C API methods (e.g., it may be `NULL` if the C API returns
+///   `NULL`).
 ///
 /// [`regulator_get()`]: https://docs.kernel.org/driver-api/regulator.html#c.regulator_get
 pub struct Regulator<State>
 where
     State: RegulatorState,
 {
-    inner: NonNull<bindings::regulator>,
+    inner: *mut bindings::regulator,
     _phantom: PhantomData<State>,
 }
 
···
         // SAFETY: Safe as per the type invariants of `Regulator`.
         to_result(unsafe {
             bindings::regulator_set_voltage(
-                self.inner.as_ptr(),
+                self.inner,
                 min_voltage.as_microvolts(),
                 max_voltage.as_microvolts(),
             )
···
     /// Gets the current voltage of the regulator.
     pub fn get_voltage(&self) -> Result<Voltage> {
         // SAFETY: Safe as per the type invariants of `Regulator`.
-        let voltage = unsafe { bindings::regulator_get_voltage(self.inner.as_ptr()) };
+        let voltage = unsafe { bindings::regulator_get_voltage(self.inner) };
 
         to_result(voltage).map(|()| Voltage::from_microvolts(voltage))
     }
···
             // received from the C code.
             from_err_ptr(unsafe { bindings::regulator_get(dev.as_raw(), name.as_char_ptr()) })?;
 
-        // SAFETY: We can safely trust `inner` to be a pointer to a valid
-        // regulator if `ERR_PTR` was not returned.
-        let inner = unsafe { NonNull::new_unchecked(inner) };
-
+        // INVARIANT: `inner` is a pointer obtained from `regulator_get()`, and
+        // the call was successful.
         Ok(Self {
             inner,
             _phantom: PhantomData,
···
 
     fn enable_internal(&self) -> Result {
         // SAFETY: Safe as per the type invariants of `Regulator`.
-        to_result(unsafe { bindings::regulator_enable(self.inner.as_ptr()) })
+        to_result(unsafe { bindings::regulator_enable(self.inner) })
     }
 
     fn disable_internal(&self) -> Result {
         // SAFETY: Safe as per the type invariants of `Regulator`.
-        to_result(unsafe { bindings::regulator_disable(self.inner.as_ptr()) })
+        to_result(unsafe { bindings::regulator_disable(self.inner) })
     }
 }
 
···
     /// Checks if the regulator is enabled.
     pub fn is_enabled(&self) -> bool {
         // SAFETY: Safe as per the type invariants of `Regulator`.
-        unsafe { bindings::regulator_is_enabled(self.inner.as_ptr()) != 0 }
+        unsafe { bindings::regulator_is_enabled(self.inner) != 0 }
     }
 }
 
···
             // SAFETY: By the type invariants, we know that `self` owns a
             // reference on the enabled refcount, so it is safe to relinquish it
             // now.
-            unsafe { bindings::regulator_disable(self.inner.as_ptr()) };
+            unsafe { bindings::regulator_disable(self.inner) };
         }
         // SAFETY: By the type invariants, we know that `self` owns a reference,
         // so it is safe to relinquish it now.
-        unsafe { bindings::regulator_put(self.inner.as_ptr()) };
+        unsafe { bindings::regulator_put(self.inner) };
     }
 }
 

samples/landlock/sandboxer.c

···
 
 /* clang-format on */
 
-#define LANDLOCK_ABI_LAST 7
+#define LANDLOCK_ABI_LAST 8
 
 #define XSTR(s) #s
 #define STR(s) XSTR(s)
···
 		/* Removes LANDLOCK_RESTRICT_SELF_LOG_NEW_EXEC_ON for ABI < 7 */
 		supported_restrict_flags &=
 			~LANDLOCK_RESTRICT_SELF_LOG_NEW_EXEC_ON;
-
+		__attribute__((fallthrough));
+	case 7:
 		/* Must be printed for any ABI < LANDLOCK_ABI_LAST. */
 		fprintf(stderr,
 			"Hint: You should update the running kernel "

security/landlock/domain.c

···
 	 * allocate with GFP_KERNEL_ACCOUNT because it is independent from the
 	 * caller.
 	 */
-	details =
-		kzalloc_flex(*details, exe_path, path_size);
+	details = kzalloc_flex(*details, exe_path, path_size);
 	if (!details)
 		return ERR_PTR(-ENOMEM);
 

security/landlock/ruleset.c

···
 {
 	struct landlock_ruleset *new_ruleset;
 
-	new_ruleset =
-		kzalloc_flex(*new_ruleset, access_masks, num_layers,
-			     GFP_KERNEL_ACCOUNT);
+	new_ruleset = kzalloc_flex(*new_ruleset, access_masks, num_layers,
+				   GFP_KERNEL_ACCOUNT);
 	if (!new_ruleset)
 		return ERR_PTR(-ENOMEM);
 	refcount_set(&new_ruleset->usage, 1);
···
 	if (IS_ERR(new_dom))
 		return new_dom;
 
-	new_dom->hierarchy = kzalloc_obj(*new_dom->hierarchy,
-					 GFP_KERNEL_ACCOUNT);
+	new_dom->hierarchy =
+		kzalloc_obj(*new_dom->hierarchy, GFP_KERNEL_ACCOUNT);
 	if (!new_dom->hierarchy)
 		return ERR_PTR(-ENOMEM);
 

security/landlock/tsync.c

···
 	return ctx;
 }
 
+/**
+ * tsync_works_trim - Put the last tsync_work element
+ *
+ * @s: TSYNC works to trim.
+ *
+ * Put the last task and decrement the size of @s.
+ *
+ * This helper does not cancel a running task, but just reset the last element
+ * to zero.
+ */
+static void tsync_works_trim(struct tsync_works *s)
+{
+	struct tsync_work *ctx;
+
+	if (WARN_ON_ONCE(s->size <= 0))
+		return;
+
+	ctx = s->works[s->size - 1];
+
+	/*
+	 * For consistency, remove the task from ctx so that it does not look like
+	 * we handed it a task_work.
+	 */
+	put_task_struct(ctx->task);
+	*ctx = (typeof(*ctx)){};
+
+	/*
+	 * Cancel the tsync_works_provide() change to recycle the reserved memory
+	 * for the next thread, if any.  This also ensures that cancel_tsync_works()
+	 * and tsync_works_release() do not see any NULL task pointers.
+	 */
+	s->size--;
+}
+
 /*
  * tsync_works_grow_by - preallocates space for n more contexts in s
  *
···
  * tsync_works_contains - checks for presence of task in s
  */
 static bool tsync_works_contains_task(const struct tsync_works *s,
-				      struct task_struct *task)
+				      const struct task_struct *task)
 {
 	size_t i;
 
 	for (i = 0; i < s->size; i++)
 		if (s->works[i]->task == task)
 			return true;
+
 	return false;
 }
 
···
 	size_t i;
 
 	for (i = 0; i < s->size; i++) {
-		if (!s->works[i]->task)
+		if (WARN_ON_ONCE(!s->works[i]->task))
 			continue;
 
 		put_task_struct(s->works[i]->task);
···
 
 	for (i = 0; i < s->capacity; i++)
 		kfree(s->works[i]);
+
 	kfree(s->works);
 	s->works = NULL;
 	s->size = 0;
···
  */
 static size_t count_additional_threads(const struct tsync_works *works)
 {
-	struct task_struct *thread, *caller;
+	const struct task_struct *caller, *thread;
 	size_t n = 0;
 
 	caller = current;
···
 			       struct tsync_shared_context *shared_ctx)
 {
 	int err;
-	struct task_struct *thread, *caller;
+	const struct task_struct *caller;
+	struct task_struct *thread;
 	struct tsync_work *ctx;
 	bool found_more_threads = false;
 
···
 
 		init_task_work(&ctx->work, restrict_one_thread_callback);
 		err = task_work_add(thread, &ctx->work, TWA_SIGNAL);
-		if (err) {
+		if (unlikely(err)) {
 			/*
 			 * task_work_add() only fails if the task is about to exit.  We
 			 * checked that earlier, but it can happen as a race.  Resume
 			 * without setting an error, as the task is probably gone in the
-			 * next loop iteration.  For consistency, remove the task from ctx
-			 * so that it does not look like we handed it a task_work.
+			 * next loop iteration.
 			 */
-			put_task_struct(ctx->task);
-			ctx->task = NULL;
+			tsync_works_trim(works);
 
 			atomic_dec(&shared_ctx->num_preparing);
 			atomic_dec(&shared_ctx->num_unfinished);
···
  * shared_ctx->num_preparing and shared_ctx->num_unfished and mark the two
  * completions if needed, as if the task was never scheduled.
  */
-static void cancel_tsync_works(struct tsync_works *works,
+static void cancel_tsync_works(const struct tsync_works *works,
 			       struct tsync_shared_context *shared_ctx)
 {
-	int i;
+	size_t i;
 
 	for (i = 0; i < works->size; i++) {
+		if (WARN_ON_ONCE(!works->works[i]->task))
+			continue;
+
 		if (!task_work_cancel(works->works[i]->task,
 				      &works->works[i]->work))
 			continue;
···
 	shared_ctx.old_cred = old_cred;
 	shared_ctx.new_cred = new_cred;
 	shared_ctx.set_no_new_privs = task_no_new_privs(current);
+
+	/*
+	 * Serialize concurrent TSYNC operations to prevent deadlocks when
+	 * multiple threads call landlock_restrict_self() simultaneously.
+	 * If the lock is already held, we gracefully yield by restarting the
+	 * syscall. This allows the current thread to process pending
+	 * task_works before retrying.
+	 */
+	if (!down_write_trylock(&current->signal->exec_update_lock))
+		return restart_syscall();
 
 	/*
 	 * We schedule a pseudo-signal task_work for each of the calling task's
···
 					   -ERESTARTNOINTR);
 
 				/*
-				 * Cancel task works for tasks that did not start running yet,
-				 * and decrement all_prepared and num_unfinished accordingly.
+				 * Opportunistic improvement: try to cancel task
+				 * works for tasks that did not start running
+				 * yet. We do not have a guarantee that it
+				 * cancels any of the enqueued task works
+				 * because task_work_run() might already have
+				 * dequeued them.
 				 */
 				cancel_tsync_works(&works, &shared_ctx);
 
 				/*
-				 * The remaining task works have started running, so waiting for
-				 * their completion will finish.
+				 * Break the loop with error. The cleanup code
+				 * after the loop unblocks the remaining
+				 * task_works.
 				 */
-				wait_for_completion(&shared_ctx.all_prepared);
+				break;
 			}
 		}
 	} while (found_more_threads &&
 		 !atomic_read(&shared_ctx.preparation_error));
 
 	/*
-	 * We now have all sibling threads blocking and in "prepared" state in the
-	 * task work. Ask all threads to commit.
+	 * We now have either (a) all sibling threads blocking and in "prepared"
+	 * state in the task work, or (b) the preparation error is set. Ask all
+	 * threads to commit (or abort).
 	 */
 	complete_all(&shared_ctx.ready_to_commit);
 
···
 		wait_for_completion(&shared_ctx.all_finished);
 
 	tsync_works_release(&works);
-
+	up_write(&current->signal->exec_update_lock);
 	return atomic_read(&shared_ctx.preparation_error);
 }

sound/firewire/amdtp-stream.c

···
 	struct pkt_desc *desc = s->packet_descs_cursor;
 	unsigned int pkt_header_length;
 	unsigned int packets;
-	u32 curr_cycle_time;
+	u32 curr_cycle_time = 0;
 	bool need_hw_irq;
 	int i;
 

sound/hda/codecs/realtek/alc269.c

···
 	return 0;
 }
 
-#define STARLABS_STARFIGHTER_SHUTUP_DELAY_MS	30
+#define ALC233_STARFIGHTER_SPK_PIN	0x1b
+#define ALC233_STARFIGHTER_GPIO2	0x04
 
-static void starlabs_starfighter_shutup(struct hda_codec *codec)
+static void alc233_starfighter_update_amp(struct hda_codec *codec, bool on)
 {
-	if (snd_hda_gen_shutup_speakers(codec))
-		msleep(STARLABS_STARFIGHTER_SHUTUP_DELAY_MS);
+	snd_hda_codec_write(codec, ALC233_STARFIGHTER_SPK_PIN, 0,
+			    AC_VERB_SET_EAPD_BTLENABLE,
+			    on ? AC_EAPDBTL_EAPD : 0);
+	alc_update_gpio_data(codec, ALC233_STARFIGHTER_GPIO2, on);
+}
+
+static void alc233_starfighter_pcm_hook(struct hda_pcm_stream *hinfo,
+					struct hda_codec *codec,
+					struct snd_pcm_substream *substream,
+					int action)
+{
+	switch (action) {
+	case HDA_GEN_PCM_ACT_PREPARE:
+		alc233_starfighter_update_amp(codec, true);
+		break;
+	case HDA_GEN_PCM_ACT_CLEANUP:
+		alc233_starfighter_update_amp(codec, false);
+		break;
+	}
 }
 
 static void alc233_fixup_starlabs_starfighter(struct hda_codec *codec,
···
 {
 	struct alc_spec *spec = codec->spec;
 
-	if (action == HDA_FIXUP_ACT_PRE_PROBE)
-		spec->shutup = starlabs_starfighter_shutup;
+	switch (action) {
+	case HDA_FIXUP_ACT_PRE_PROBE:
+		spec->gpio_mask |= ALC233_STARFIGHTER_GPIO2;
+		spec->gpio_dir |= ALC233_STARFIGHTER_GPIO2;
+		spec->gpio_data &= ~ALC233_STARFIGHTER_GPIO2;
+		break;
+	case HDA_FIXUP_ACT_PROBE:
+		spec->gen.pcm_playback_hook = alc233_starfighter_pcm_hook;
+		break;
+	}
 }
 
 static void alc269_fixup_pincfg_no_hp_to_lineout(struct hda_codec *codec,
···
 	alc_fixup_hp_gpio_led(codec, action, 0x04, 0x0);
 	alc285_fixup_hp_coef_micmute_led(codec, fix, action);
 }
+
+static void alc245_hp_spk_mute_led_update(void *private_data, int enabled)
+{
+	struct hda_codec *codec = private_data;
+	unsigned int val;
+
+	val = enabled ? 0x08 : 0x04; /* 0x08 led on, 0x04 led off */
+	alc_update_coef_idx(codec, 0x0b, 0x0c, val);
+}
+
 /* JD2: mute led GPIO3: micmute led */
 static void alc245_tas2781_i2c_hp_fixup_muteled(struct hda_codec *codec,
 					  const struct hda_fixup *fix, int action)
 {
 	struct alc_spec *spec = codec->spec;
+	hda_nid_t hp_pin = alc_get_hp_pin(spec);
 	static const hda_nid_t conn[] = { 0x02 };
 
 	switch (action) {
 	case HDA_FIXUP_ACT_PRE_PROBE:
+		if (!hp_pin) {
+			spec->gen.vmaster_mute.hook = alc245_hp_spk_mute_led_update;
+			spec->gen.vmaster_mute_led = 1;
+		}
 		spec->gen.auto_mute_via_amp = 1;
 		snd_hda_override_conn_list(codec, 0x17, ARRAY_SIZE(conn), conn);
+		break;
+	case HDA_FIXUP_ACT_INIT:
+		if (!hp_pin)
+			alc245_hp_spk_mute_led_update(codec, !spec->gen.master_mute);
 		break;
 	}
 
 	tas2781_fixup_txnw_i2c(codec, fix, action);
-	alc245_fixup_hp_mute_led_coefbit(codec, fix, action);
+	if (hp_pin)
+		alc245_fixup_hp_mute_led_coefbit(codec, fix, action);
 	alc285_fixup_hp_coef_micmute_led(codec, fix, action);
 }
 /*
···
 	ALC233_FIXUP_LENOVO_GPIO2_MIC_HOTKEY,
 	ALC245_FIXUP_BASS_HP_DAC,
 	ALC245_FIXUP_ACER_MICMUTE_LED,
+	ALC245_FIXUP_CS35L41_I2C_2_MUTE_LED,
+	ALC236_FIXUP_HP_DMIC,
 };
 
 /* A special fixup for Lenovo C940 and Yoga Duet 7;
···
 		.v.func = alc285_fixup_hp_coef_micmute_led,
 		.chained = true,
 		.chain_id = ALC2XX_FIXUP_HEADSET_MIC,
+	},
+	[ALC245_FIXUP_CS35L41_I2C_2_MUTE_LED] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc245_fixup_hp_mute_led_coefbit,
+		.chained = true,
+		.chain_id = ALC287_FIXUP_CS35L41_I2C_2,
+	},
+	[ALC236_FIXUP_HP_DMIC] = {
+		.type = HDA_FIXUP_PINS,
+		.v.pins = (const struct hda_pintbl[]) {
+			{ 0x12, 0x90a60160 }, /* use as internal mic */
+			{ }
+		},
 	}
 };
 
···
 	SND_PCI_QUIRK(0x1025, 0x1597, "Acer Nitro 5 AN517-55", ALC2XX_FIXUP_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1025, 0x169a, "Acer Swift SFG16", ALC256_FIXUP_ACER_SFG16_MICMUTE_LED),
 	SND_PCI_QUIRK(0x1025, 0x171e, "Acer Nitro ANV15-51", ALC245_FIXUP_ACER_MICMUTE_LED),
+	SND_PCI_QUIRK(0x1025, 0x173a, "Acer Swift SFG14-73", ALC245_FIXUP_ACER_MICMUTE_LED),
 	SND_PCI_QUIRK(0x1025, 0x1826, "Acer Helios ZPC", ALC287_FIXUP_PREDATOR_SPK_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x1025, 0x182c, "Acer Helios ZPD", ALC287_FIXUP_PREDATOR_SPK_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x1025, 0x1844, "Acer Helios ZPS", ALC287_FIXUP_PREDATOR_SPK_CS35L41_I2C_2),
···
 	SND_PCI_QUIRK(0x103c, 0x8730, "HP ProBook 445 G7", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF),
 	SND_PCI_QUIRK(0x103c, 0x8735, "HP ProBook 435 G7", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF),
 	SND_PCI_QUIRK(0x103c, 0x8736, "HP", ALC285_FIXUP_HP_GPIO_AMP_INIT),
+	SND_PCI_QUIRK(0x103c, 0x8756, "HP ENVY Laptop 13-ba0xxx", ALC245_FIXUP_HP_X360_MUTE_LEDS),
 	SND_PCI_QUIRK(0x103c, 0x8760, "HP EliteBook 8{4,5}5 G7", ALC285_FIXUP_HP_BEEP_MICMUTE_LED),
 	SND_PCI_QUIRK(0x103c, 0x876e, "HP ENVY x360 Convertible 13-ay0xxx", ALC245_FIXUP_HP_X360_MUTE_LEDS),
 	SND_PCI_QUIRK(0x103c, 0x877a, "HP", ALC285_FIXUP_HP_MUTE_LED),
···
 	SND_PCI_QUIRK(0x103c, 0x8788, "HP OMEN 15", ALC285_FIXUP_HP_MUTE_LED),
 	SND_PCI_QUIRK(0x103c, 0x87b7, "HP Laptop 14-fq0xxx", ALC236_FIXUP_HP_MUTE_LED_COEFBIT2),
 	SND_PCI_QUIRK(0x103c, 0x87c8, "HP", ALC287_FIXUP_HP_GPIO_LED),
+	SND_PCI_QUIRK(0x103c, 0x87cb, "HP Pavilion 15-eg0xxx", ALC287_FIXUP_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x87cc, "HP Pavilion 15-eg0xxx", ALC287_FIXUP_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x87d3, "HP Laptop 15-gw0xxx", ALC236_FIXUP_HP_MUTE_LED_COEFBIT2),
 	SND_PCI_QUIRK(0x103c, 0x87df, "HP ProBook 430 G8 Notebook PC", ALC236_FIXUP_HP_GPIO_LED),
···
 	SND_PCI_QUIRK(0x103c, 0x8a30, "HP Envy 17", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x103c, 0x8a31, "HP Envy 15", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x103c, 0x8a34, "HP Pavilion x360 2-in-1 Laptop 14-ek0xxx", ALC245_FIXUP_HP_MUTE_LED_COEFBIT),
+	SND_PCI_QUIRK(0x103c, 0x8a3d, "HP Victus 15-fb0xxx (MB 8A3D)", ALC245_FIXUP_HP_MUTE_LED_V2_COEFBIT),
 	SND_PCI_QUIRK(0x103c, 0x8a4f, "HP Victus 15-fa0xxx (MB 8A4F)", ALC245_FIXUP_HP_MUTE_LED_COEFBIT),
 	SND_PCI_QUIRK(0x103c, 0x8a6e, "HP EDNA 360", ALC287_FIXUP_CS35L41_I2C_4),
 	SND_PCI_QUIRK(0x103c, 0x8a74, "HP ProBook 440 G8 Notebook PC", ALC236_FIXUP_HP_GPIO_LED),
···
 	SND_PCI_QUIRK(0x103c, 0x8da1, "HP 16 Clipper OmniBook X", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x103c, 0x8da7, "HP 14 Enstrom OmniBook X", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x103c, 0x8da8, "HP 16 Piston OmniBook X", ALC287_FIXUP_CS35L41_I2C_2),
+	SND_PCI_QUIRK(0x103c, 0x8dc9, "HP Laptop 15-fc0xxx", ALC236_FIXUP_HP_DMIC),
 	SND_PCI_QUIRK(0x103c, 0x8dd4, "HP EliteStudio 8 AIO", ALC274_FIXUP_HP_AIO_BIND_DACS),
+	SND_PCI_QUIRK(0x103c, 0x8dd7, "HP Laptop 15-fd0xxx", ALC236_FIXUP_HP_MUTE_LED_COEFBIT2),
 	SND_PCI_QUIRK(0x103c, 0x8de8, "HP Gemtree", ALC245_FIXUP_TAS2781_SPI_2),
 	SND_PCI_QUIRK(0x103c, 0x8de9, "HP Gemtree", ALC245_FIXUP_TAS2781_SPI_2),
 	SND_PCI_QUIRK(0x103c, 0x8dec, "HP EliteBook 640 G12", ALC236_FIXUP_HP_GPIO_LED),
···
 	SND_PCI_QUIRK(0x103c, 0x8e37, "HP 16 Piston OmniBook X", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x103c, 0x8e3a, "HP Agusta", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x103c, 0x8e3b, "HP Agusta", ALC287_FIXUP_CS35L41_I2C_2),
-	SND_PCI_QUIRK(0x103c, 0x8e60, "HP Trekker ", ALC287_FIXUP_CS35L41_I2C_2),
+	SND_PCI_QUIRK(0x103c, 0x8e60, "HP OmniBook 7 Laptop 16-bh0xxx", ALC245_FIXUP_CS35L41_I2C_2_MUTE_LED),
 	SND_PCI_QUIRK(0x103c, 0x8e61, "HP Trekker ", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x103c, 0x8e62, "HP Trekker ", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x103c, 0x8e8a, "HP NexusX", ALC245_FIXUP_HP_TAS2781_I2C_MUTE_LED),
···
 	SND_PCI_QUIRK(0x1043, 0x115d, "Asus 1015E", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
 	SND_PCI_QUIRK(0x1043, 0x1194, "ASUS UM3406KA", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x1043, 0x11c0, "ASUS X556UR", ALC255_FIXUP_ASUS_MIC_NO_PRESENCE),
+	HDA_CODEC_QUIRK(0x1043, 0x1204, "ASUS Strix G16 G615JMR", ALC287_FIXUP_TXNW2781_I2C_ASUS),
 	SND_PCI_QUIRK(0x1043, 0x1204, "ASUS Strix G615JHR_JMR_JPR", ALC287_FIXUP_TAS2781_I2C),
 	SND_PCI_QUIRK(0x1043, 0x1214, "ASUS Strix G615LH_LM_LP", ALC287_FIXUP_TAS2781_I2C),
 	SND_PCI_QUIRK(0x1043, 0x125e, "ASUS Q524UQK", ALC255_FIXUP_ASUS_MIC_NO_PRESENCE),
···
 	SND_PCI_QUIRK(0x1043, 0x14e3, "ASUS G513PI/PU/PV", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x1043, 0x14f2, "ASUS VivoBook X515JA", ALC256_FIXUP_ASUS_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1043, 0x1503, "ASUS G733PY/PZ/PZV/PYV", ALC287_FIXUP_CS35L41_I2C_2),
+	SND_PCI_QUIRK(0x1043, 0x1514, "ASUS ROG Flow Z13 GZ302EAC", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x1043, 0x1517, "Asus Zenbook UX31A", ALC269VB_FIXUP_ASUS_ZENBOOK_UX31A),
 	SND_PCI_QUIRK(0x1043, 0x1533, "ASUS GV302XA/XJ/XQ/XU/XV/XI", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x1043, 0x1573, "ASUS GZ301VV/VQ/VU/VJ/VA/VC/VE/VVC/VQC/VUC/VJC/VEC/VCC", ALC285_FIXUP_ASUS_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1043, 0x1584, "ASUS UM3406GA ", ALC287_FIXUP_CS35L41_I2C_2),
+	SND_PCI_QUIRK(0x1043, 0x1602, "ASUS ROG Strix SCAR 15", ALC285_FIXUP_ASUS_G533Z_PINS),
 	SND_PCI_QUIRK(0x1043, 0x1652, "ASUS ROG Zephyrus Do 15 SE", ALC289_FIXUP_ASUS_ZEPHYRUS_DUAL_SPK),
 	SND_PCI_QUIRK(0x1043, 0x1662, "ASUS GV301QH", ALC294_FIXUP_ASUS_DUAL_SPK),
 	SND_PCI_QUIRK(0x1043, 0x1663, "ASUS GU603ZI/ZJ/ZQ/ZU/ZV", ALC285_FIXUP_ASUS_HEADSET_MIC),
···
 	SND_PCI_QUIRK(0x144d, 0xc188, "Samsung Galaxy Book Flex (NT950QCT-A38A)", ALC298_FIXUP_SAMSUNG_AMP),
 	SND_PCI_QUIRK(0x144d, 0xc189, "Samsung Galaxy Book Flex (NT950QCG-X716)", ALC298_FIXUP_SAMSUNG_AMP),
 	SND_PCI_QUIRK(0x144d, 0xc18a, "Samsung Galaxy Book Ion (NP930XCJ-K01US)", ALC298_FIXUP_SAMSUNG_AMP),
+	SND_PCI_QUIRK(0x144d, 0xc1ac, "Samsung Galaxy Book2 Pro 360 (NP950QED)", ALC298_FIXUP_SAMSUNG_AMP_V2_2_AMPS),
 	SND_PCI_QUIRK(0x144d, 0xc1a3, "Samsung Galaxy Book Pro (NP935XDB-KC1SE)", ALC298_FIXUP_SAMSUNG_AMP),
 	SND_PCI_QUIRK(0x144d, 0xc1a4, "Samsung Galaxy Book Pro 360 (NT935QBD)", ALC298_FIXUP_SAMSUNG_AMP),
 	SND_PCI_QUIRK(0x144d, 0xc1a6, "Samsung Galaxy Book Pro 360 (NP930QBD)", ALC298_FIXUP_SAMSUNG_AMP),
···
 	SND_PCI_QUIRK(0x17aa, 0x3834, "Lenovo IdeaPad Slim 9i 14ITL5", ALC287_FIXUP_YOGA7_14ITL_SPEAKERS),
 	SND_PCI_QUIRK(0x17aa, 0x383d, "Legion Y9000X 2019", ALC285_FIXUP_LEGION_Y9000X_SPEAKERS),
 	SND_PCI_QUIRK(0x17aa, 0x3843, "Lenovo Yoga 9i / Yoga Book 9i", ALC287_FIXUP_LENOVO_YOGA_BOOK_9I),
+	/* Yoga Pro 7 14IMH9 shares PCI SSID 17aa:3847 with Legion 7 16ACHG6;
+	 * use codec SSID to distinguish them
+	 */
+	HDA_CODEC_QUIRK(0x17aa, 0x38cf, "Lenovo Yoga Pro 7 14IMH9", ALC287_FIXUP_YOGA9_14IMH9_BASS_SPK_PIN),
 	SND_PCI_QUIRK(0x17aa, 0x3847, "Legion 7 16ACHG6", ALC287_FIXUP_LEGION_16ACHG6),
 	SND_PCI_QUIRK(0x17aa, 0x384a, "Lenovo Yoga 7 15ITL5", ALC287_FIXUP_YOGA7_14ITL_SPEAKERS),
 	SND_PCI_QUIRK(0x17aa, 0x3852, "Lenovo Yoga 7 14ITL5", ALC287_FIXUP_YOGA7_14ITL_SPEAKERS),
···
 	SND_PCI_QUIRK(0x17aa, 0x38ab, "Thinkbook 16P", ALC287_FIXUP_MG_RTKC_CSAMP_CS35L41_I2C_THINKPAD),
 	SND_PCI_QUIRK(0x17aa, 0x38b4, "Legion Slim 7 16IRH8", ALC287_FIXUP_CS35L41_I2C_2),
 	HDA_CODEC_QUIRK(0x17aa, 0x391c, "Lenovo Yoga 7 2-in-1 14AKP10", ALC287_FIXUP_YOGA9_14IAP7_BASS_SPK_PIN),
+	HDA_CODEC_QUIRK(0x17aa, 0x391d, "Lenovo Yoga 7 2-in-1 16AKP10", ALC287_FIXUP_YOGA9_14IAP7_BASS_SPK_PIN),
 	SND_PCI_QUIRK(0x17aa, 0x38b5, "Legion Slim 7 16IRH8", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x17aa, 0x38b6, "Legion Slim 7 16APH8", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x17aa, 0x38b7, "Legion Slim 7 16APH8", ALC287_FIXUP_CS35L41_I2C_2),
···
 	SND_PCI_QUIRK(0x17aa, 0x3902, "Lenovo E50-80", ALC269_FIXUP_DMIC_THINKPAD_ACPI),
 	SND_PCI_QUIRK(0x17aa, 0x390d, "Lenovo Yoga Pro 7 14ASP10", ALC287_FIXUP_YOGA9_14IAP7_BASS_SPK_PIN),
 	SND_PCI_QUIRK(0x17aa, 0x3913, "Lenovo 145", ALC236_FIXUP_LENOVO_INV_DMIC),
+	SND_PCI_QUIRK(0x17aa, 0x391a, "Lenovo Yoga Slim 7 14AKP10", ALC287_FIXUP_YOGA9_14IAP7_BASS_SPK_PIN),
 	SND_PCI_QUIRK(0x17aa, 0x391f, "Yoga S990-16 pro Quad YC Quad", ALC287_FIXUP_TXNW2781_I2C),
 	SND_PCI_QUIRK(0x17aa, 0x3920, "Yoga S990-16 pro Quad VECO Quad", ALC287_FIXUP_TXNW2781_I2C),
 	SND_PCI_QUIRK(0x17aa, 0x3929, "Thinkbook 13x Gen 5", ALC287_FIXUP_MG_RTKC_CSAMP_CS35L41_I2C_THINKPAD),
···
 	SND_PCI_QUIRK(0xf111, 0x0009, "Framework Laptop", ALC295_FIXUP_FRAMEWORK_LAPTOP_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0xf111, 0x000b, "Framework Laptop", ALC295_FIXUP_FRAMEWORK_LAPTOP_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0xf111, 0x000c, "Framework Laptop", ALC295_FIXUP_FRAMEWORK_LAPTOP_MIC_NO_PRESENCE),
+	SND_PCI_QUIRK(0xf111, 0x000f, "Framework Laptop", ALC295_FIXUP_FRAMEWORK_LAPTOP_MIC_NO_PRESENCE),
 
 #if 0
 	/* Below is a quirk table taken from the old code.

sound/hda/controllers/intel.c

···
 	{ PCI_DEVICE_SUB(0x1022, 0x1487, 0x1043, 0x874f) }, /* ASUS ROG Zenith II / Strix */
 	{ PCI_DEVICE_SUB(0x1022, 0x1487, 0x1462, 0xcb59) }, /* MSI TRX40 Creator */
 	{ PCI_DEVICE_SUB(0x1022, 0x1487, 0x1462, 0xcb60) }, /* MSI TRX40 */
-	{ PCI_DEVICE_SUB(0x1022, 0x15e3, 0x1462, 0xee59) }, /* MSI X870E Tomahawk WiFi */
 	{}
 };
 
 static struct pci_device_id driver_denylist_ideapad_z570[] = {
 	{ PCI_DEVICE_SUB(0x10de, 0x0bea, 0x0000, 0x0000) }, /* NVIDIA GF108 HDA */
+	{}
+};
+
+static struct pci_device_id driver_denylist_msi_x870e[] = {
+	{ PCI_DEVICE_SUB(0x1022, 0x15e3, 0x1462, 0xee59) }, /* MSI X870E Tomahawk WiFi */
 	{}
 };
 
···
 			DMI_MATCH(DMI_PRODUCT_VERSION, "Ideapad Z570"),
 		},
 		.driver_data = &driver_denylist_ideapad_z570,
+	},
+	{
+		/* PCI device matching alone incorrectly matches some laptops */
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "Micro-Star International Co., Ltd."),
+			DMI_MATCH(DMI_BOARD_NAME, "MAG X870E TOMAHAWK WIFI (MS-7E59)"),
+		},
+		.driver_data = &driver_denylist_msi_x870e,
 	},
 	{}
 };

sound/pci/asihpi/hpimsgx.c

···
 		HPI_ADAPTER_OPEN);
 	hm.adapter_index = adapter;
 	hw_entry_point(&hm, &hr);
-	memcpy(&rESP_HPI_ADAPTER_OPEN[adapter], &hr,
-		sizeof(rESP_HPI_ADAPTER_OPEN[0]));
+	memcpy(&rESP_HPI_ADAPTER_OPEN[adapter].h, &hr,
+		sizeof(rESP_HPI_ADAPTER_OPEN[adapter].h));
+	memcpy(&rESP_HPI_ADAPTER_OPEN[adapter].a, &hr.u.ax.info,
+		sizeof(rESP_HPI_ADAPTER_OPEN[adapter].a));
 	if (hr.error)
 		return hr.error;
 

sound/pci/ctxfi/ctatc.c

···
 	daio_mgr = (struct daio_mgr *)atc->rsc_mgrs[DAIO];
 	da_desc.msr = atc->msr;
 	for (i = 0; i < NUM_DAIOTYP; i++) {
-		if (((i == MIC) && !cap.dedicated_mic) || ((i == RCA) && !cap.dedicated_rca))
+		if (((i == MIC) && !cap.dedicated_mic) ||
+		    ((i == RCA) && !cap.dedicated_rca) ||
+		    i == SPDIFI1)
 			continue;
-		da_desc.type = (atc->model != CTSB073X) ? i :
-			     ((i == SPDIFIO) ? SPDIFI1 : i);
+		if (atc->model == CTSB073X && i == SPDIFIO)
+			da_desc.type = SPDIFI1;
+		else
+			da_desc.type = i;
 		da_desc.output = (i < LINEIM) || (i == RCA);
 		err = daio_mgr->get_daio(daio_mgr, &da_desc,
 					(struct daio **)&atc->daios[i]);

sound/pci/ctxfi/ctdaio.c

···
 	.output_slot	= daio_index,
 };
 
-static unsigned int daio_device_index(enum DAIOTYP type, struct hw *hw)
+static int daio_device_index(enum DAIOTYP type, struct hw *hw)
 {
 	switch (hw->chip_type) {
 	case ATC20K1:
···
 		case LINEO3:	return 5;
 		case LINEO4:	return 6;
 		case LINEIM:	return 7;
-		default:	return -EINVAL;
+		default:
+			pr_err("ctxfi: Invalid type %d for hw20k1\n", type);
+			return -EINVAL;
 		}
 	case ATC20K2:
 		switch (type) {
 		case SPDIFOO:	return 0;
 		case SPDIFIO:	return 0;
+		case SPDIFI1:	return 1;
 		case LINEO1:	return 4;
 		case LINEO2:	return 7;
 		case LINEO3:	return 5;
···
 		case LINEIM:	return 4;
 		case MIC:	return 5;
 		case RCA:	return 3;
-		default:	return -EINVAL;
+		default:
+			pr_err("ctxfi: Invalid type %d for hw20k2\n", type);
+			return -EINVAL;
 		}
 	default:
+		pr_err("ctxfi: Invalid chip type %d\n", hw->chip_type);
 		return -EINVAL;
 	}
 }
···
 
 static int dao_commit_write(struct dao *dao)
 {
-	dao->hw->dao_commit_write(dao->hw,
-		daio_device_index(dao->daio.type, dao->hw), dao->ctrl_blk);
+	int idx = daio_device_index(dao->daio.type, dao->hw);
+
+	if (idx < 0)
+		return idx;
+	dao->hw->dao_commit_write(dao->hw, idx, dao->ctrl_blk);
 	return 0;
 }
 
···
 
 static int dai_commit_write(struct dai *dai)
 {
-	dai->hw->dai_commit_write(dai->hw,
-		daio_device_index(dai->daio.type, dai->hw), dai->ctrl_blk);
+	int idx = daio_device_index(dai->daio.type, dai->hw);
+
+	if (idx < 0)
+		return idx;
+	dai->hw->dai_commit_write(dai->hw, idx, dai->ctrl_blk);
 	return 0;
 }
 
···
 {
 	struct hw *hw = mgr->mgr.hw;
 	unsigned int conf;
-	int err;
+	int idx, err;
 
 	err = daio_rsc_init(&dao->daio, desc, mgr->mgr.hw);
 	if (err)
···
 	if (err)
 		goto error2;
 
-	hw->daio_mgr_dsb_dao(mgr->mgr.ctrl_blk,
-			daio_device_index(dao->daio.type, hw));
+	idx = daio_device_index(dao->daio.type, hw);
+	if (idx < 0) {
+		err = idx;
+		goto error2;
+	}
+
+	hw->daio_mgr_dsb_dao(mgr->mgr.ctrl_blk, idx);
 	hw->daio_mgr_commit_write(hw, mgr->mgr.ctrl_blk);
 
 	conf = (desc->msr & 0x7) | (desc->passthru << 3);
-	hw->daio_mgr_dao_init(hw, mgr->mgr.ctrl_blk,
-			daio_device_index(dao->daio.type, hw), conf);
-	hw->daio_mgr_enb_dao(mgr->mgr.ctrl_blk,
-			daio_device_index(dao->daio.type, hw));
+	hw->daio_mgr_dao_init(hw, mgr->mgr.ctrl_blk, idx, conf);
+	hw->daio_mgr_enb_dao(mgr->mgr.ctrl_blk, idx);
 	hw->daio_mgr_commit_write(hw, mgr->mgr.ctrl_blk);
 
 	return 0;
···
 			const struct daio_desc *desc,
 			struct daio_mgr *mgr)
 {
-	int err;
+	int idx, err;
 	struct hw *hw = mgr->mgr.hw;
 	unsigned int rsr, msr;
 
···
 	if (err)
 		goto error1;
 
+	idx = daio_device_index(dai->daio.type, dai->hw);
+	if (idx < 0) {
+		err = idx;
+		goto error1;
+	}
+
 	for (rsr = 0, msr = desc->msr; msr > 1; msr >>= 1)
 		rsr++;
 
···
 	/* default to disabling control of a SRC */
 	hw->dai_srt_set_ec(dai->ctrl_blk, 0);
 	hw->dai_srt_set_et(dai->ctrl_blk, 0); /* default to disabling SRT */
-	hw->dai_commit_write(hw,
-		daio_device_index(dai->daio.type, dai->hw), dai->ctrl_blk);
+	hw->dai_commit_write(hw, idx, dai->ctrl_blk);
 
 	return 0;
 
···
 static int daio_mgr_enb_daio(struct daio_mgr *mgr, struct daio *daio)
 {
 	struct hw *hw = mgr->mgr.hw;
+	int idx = daio_device_index(daio->type, hw);
 
-	if (daio->output) {
-		hw->daio_mgr_enb_dao(mgr->mgr.ctrl_blk,
-				daio_device_index(daio->type, hw));
-	} else {
-		hw->daio_mgr_enb_dai(mgr->mgr.ctrl_blk,
-				daio_device_index(daio->type, hw));
-	}
+	if (idx < 0)
+		return idx;
+	if (daio->output)
+		hw->daio_mgr_enb_dao(mgr->mgr.ctrl_blk, idx);
+	else
+		hw->daio_mgr_enb_dai(mgr->mgr.ctrl_blk, idx);
 	return 0;
 }
 
 static int daio_mgr_dsb_daio(struct daio_mgr *mgr, struct daio *daio)
 {
 	struct hw *hw = mgr->mgr.hw;
+	int idx = daio_device_index(daio->type, hw);
 
-	if (daio->output) {
-		hw->daio_mgr_dsb_dao(mgr->mgr.ctrl_blk,
-				daio_device_index(daio->type, hw));
-	} else {
-		hw->daio_mgr_dsb_dai(mgr->mgr.ctrl_blk,
-				daio_device_index(daio->type, hw));
-	}
+	if (idx < 0)
+		return idx;
+	if (daio->output)
+		hw->daio_mgr_dsb_dao(mgr->mgr.ctrl_blk, idx);
+	else
+		hw->daio_mgr_dsb_dai(mgr->mgr.ctrl_blk, idx);
 	return 0;
 }
 

sound/soc/amd/acp-config.c

···
 
 static int acp_quirk_data;
 
+static const struct dmi_system_id acp70_acpi_flag_override_table[] = {
+	{
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "HN7306EA"),
+		},
+	},
+	{}
+};
+
 static const struct config_entry config_table[] = {
 	{
 		.flags = FLAG_AMD_SOF,
···
 	 */
 	if (!pci->revision)
 		return 0;
-	else if (pci->revision >= ACP_7_0_REV)
+	else if (pci->revision >= ACP_7_0_REV) {
+		if (dmi_check_system(acp70_acpi_flag_override_table))
+			return 0;
 		return snd_amd_acp_acpi_find_config(pci);
+	}
 
 	for (i = 0; i < ARRAY_SIZE(config_table); i++, table++) {
 		if (table->device != device)

sound/soc/amd/acp/acp-sdw-legacy-mach.c

···
 		},
 		.driver_data = (void *)(ASOC_SDW_CODEC_SPKR),
 	},
+	{
+		.callback = soc_sdw_quirk_cb,
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "HN7306EA"),
+		},
+		.driver_data = (void *)(ASOC_SDW_ACP_DMIC),
+	},
 	{}
 };
 

sound/soc/amd/acp/amd-acp70-acpi-match.c

···
 	},
 };
 
+static const struct snd_soc_acpi_endpoint jack_dmic_endpoints[] = {
+	/* Jack Endpoint */
+	{
+		.num = 0,
+		.aggregated = 0,
+		.group_position = 0,
+		.group_id = 0,
+	},
+	/* DMIC Endpoint */
+	{
+		/*
+		 * rt721 endpoint #2 maps to AIF3 (internal DMIC capture).
+		 * Endpoint #1 is AIF2 amp path and is handled by external amps
+		 * on this platform.
+		 */
+		.num = 2,
+		.aggregated = 0,
+		.group_position = 0,
+		.group_id = 0,
+	},
+};
+
 static const struct snd_soc_acpi_adr_device rt712_vb_1_group1_adr[] = {
 	{
 		.adr = 0x000130025D071201ull,
···
 	{}
 };
 
+static const struct snd_soc_acpi_adr_device rt721_l1u0_tas2783x2_l1u8b_adr[] = {
+	{
+		.adr = 0x000130025D072101ull,
+		/*
+		 * On this platform speakers are provided by two TAS2783 amps.
+		 * Keep rt721 as UAJ + DMIC only.
+		 */
+		.num_endpoints = ARRAY_SIZE(jack_dmic_endpoints),
+		.endpoints = jack_dmic_endpoints,
+		.name_prefix = "rt721",
+	},
+	{
+		.adr = 0x0001380102000001ull,
+		.num_endpoints = 1,
+		.endpoints = &spk_l_endpoint,
+		.name_prefix = "tas2783-1",
+	},
+	{
+		.adr = 0x00013B0102000001ull,
+		.num_endpoints = 1,
+		.endpoints = &spk_r_endpoint,
+		.name_prefix = "tas2783-2",
+	},
+};
+
+static const struct snd_soc_acpi_link_adr acp70_rt721_l1u0_tas2783x2_l1u8b[] = {
+	{
+		.mask = BIT(1),
+		.num_adr = ARRAY_SIZE(rt721_l1u0_tas2783x2_l1u8b_adr),
+		.adr_d = rt721_l1u0_tas2783x2_l1u8b_adr,
+	},
+	{}
+};
+
 struct snd_soc_acpi_mach snd_soc_acpi_amd_acp70_sdw_machines[] = {
 	{
 		.link_mask = BIT(0) | BIT(1),
···
 		.link_mask = BIT(1),
 		.links = acp70_alc712_vb_l1,
 		.machine_check = snd_soc_acpi_amd_sdca_is_device_rt712_vb,
+		.drv_name = "amd_sdw",
+	},
+	{
+		.link_mask = BIT(1),
+		.links = acp70_rt721_l1u0_tas2783x2_l1u8b,
 		.drv_name = "amd_sdw",
 	},
 	{},

sound/soc/amd/ps/pci-ps.c

···
 			mach->mach_params.subsystem_device = acp_data->subsystem_device;
 			mach->mach_params.subsystem_id_set = true;
 
-			dev_dbg(dev, "SSID %x%x\n", mach->mach_params.subsystem_vendor,
+			dev_dbg(dev, "SSID %x%04x\n", mach->mach_params.subsystem_vendor,
 				mach->mach_params.subsystem_device);
 			return mach;
 		}

sound/soc/amd/yc/acp6x-mach.c

···
 	{
 		.driver_data = &acp6x_card,
 		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "HP"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "HP Laptop 15-fc0xxx"),
+		}
+	},
+	{
+		.driver_data = &acp6x_card,
+		.matches = {
 			DMI_MATCH(DMI_BOARD_VENDOR, "Dell Inc."),
 			DMI_MATCH(DMI_PRODUCT_NAME, "Dell G15 5525"),
 		}
···
 		.matches = {
 			DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK COMPUTER INC."),
 			DMI_MATCH(DMI_BOARD_NAME, "PM1503CDA"),
+		}
+	},
+	{
+		.driver_data = &acp6x_card,
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_BOARD_NAME, "BM1403CDA"),
+		}
+	},
+	{
+		.driver_data = &acp6x_card,
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "Micro-Star International Co., Ltd."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Thin A15 B7VE"),
+		}
+	},
+	{
+		.driver_data = &acp6x_card,
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "M7601RM"),
 		}
 	},
 	{}

sound/soc/cirrus/ep93xx-i2s.c

···
 	return __raw_readl(info->regs + reg);
 }
 
-static void ep93xx_i2s_enable(struct ep93xx_i2s_info *info, int stream)
+static int ep93xx_i2s_enable(struct ep93xx_i2s_info *info, int stream)
 {
 	unsigned base_reg;
+	int err;
 
 	if ((ep93xx_i2s_read_reg(info, EP93XX_I2S_TX0EN) & 0x1) == 0 &&
 	    (ep93xx_i2s_read_reg(info, EP93XX_I2S_RX0EN) & 0x1) == 0) {
 		/* Enable clocks */
-		clk_prepare_enable(info->mclk);
-		clk_prepare_enable(info->sclk);
-		clk_prepare_enable(info->lrclk);
+		err = clk_prepare_enable(info->mclk);
+		if (err)
+			return err;
+		err = clk_prepare_enable(info->sclk);
+		if (err) {
+			clk_disable_unprepare(info->mclk);
+			return err;
+		}
+		err = clk_prepare_enable(info->lrclk);
+		if (err) {
+			clk_disable_unprepare(info->sclk);
+			clk_disable_unprepare(info->mclk);
+			return err;
+		}
 
 		/* Enable i2s */
 		ep93xx_i2s_write_reg(info, EP93XX_I2S_GLCTRL, 1);
···
 		ep93xx_i2s_write_reg(info, EP93XX_I2S_TXCTRL,
 				     EP93XX_I2S_TXCTRL_TXEMPTY_LVL |
 				     EP93XX_I2S_TXCTRL_TXUFIE);
+
+	return 0;
 }
 
 static void ep93xx_i2s_disable(struct ep93xx_i2s_info *info, int stream)
···
 {
 	struct ep93xx_i2s_info *info = snd_soc_dai_get_drvdata(dai);
 
-	ep93xx_i2s_enable(info, substream->stream);
-
-	return 0;
+	return ep93xx_i2s_enable(info, substream->stream);
 }
 
 static void ep93xx_i2s_shutdown(struct snd_pcm_substream *substream,
···
 static int ep93xx_i2s_resume(struct snd_soc_component *component)
 {
 	struct ep93xx_i2s_info *info = snd_soc_component_get_drvdata(component);
+	int err;
 
 	if (!snd_soc_component_active(component))
 		return 0;
 
-	ep93xx_i2s_enable(info, SNDRV_PCM_STREAM_PLAYBACK);
-	ep93xx_i2s_enable(info, SNDRV_PCM_STREAM_CAPTURE);
+	err = ep93xx_i2s_enable(info, SNDRV_PCM_STREAM_PLAYBACK);
+	if (err)
+		return err;
 
-	return 0;
+	return ep93xx_i2s_enable(info, SNDRV_PCM_STREAM_CAPTURE);
 }
 #else
 #define ep93xx_i2s_suspend	NULL

sound/soc/codecs/adau1372.c

···
 	return 0;
 }
 
-static void adau1372_enable_pll(struct adau1372 *adau1372)
+static int adau1372_enable_pll(struct adau1372 *adau1372)
 {
 	unsigned int val, timeout = 0;
 	int ret;
···
 		timeout++;
 	} while (!(val & 1) && timeout < 3);
 
-	if (ret < 0 || !(val & 1))
+	if (ret < 0 || !(val & 1)) {
 		dev_err(adau1372->dev, "Failed to lock PLL\n");
+		return ret < 0 ? ret : -ETIMEDOUT;
+	}
+
+	return 0;
 }
 
-static void adau1372_set_power(struct adau1372 *adau1372, bool enable)
+static int adau1372_set_power(struct adau1372 *adau1372, bool enable)
 {
 	if (adau1372->enabled == enable)
-		return;
+		return 0;
 
 	if (enable) {
 		unsigned int clk_ctrl = ADAU1372_CLK_CTRL_MCLK_EN;
+		int ret;
 
-		clk_prepare_enable(adau1372->mclk);
+		ret = clk_prepare_enable(adau1372->mclk);
+		if (ret)
+			return ret;
 		if (adau1372->pd_gpio)
 			gpiod_set_value(adau1372->pd_gpio, 0);
 
···
 		 * accessed.
 		 */
 		if (adau1372->use_pll) {
-			adau1372_enable_pll(adau1372);
+			ret = adau1372_enable_pll(adau1372);
+			if (ret) {
+				regcache_cache_only(adau1372->regmap, true);
+				if (adau1372->pd_gpio)
+					gpiod_set_value(adau1372->pd_gpio, 1);
+				clk_disable_unprepare(adau1372->mclk);
+				return ret;
+			}
 			clk_ctrl |= ADAU1372_CLK_CTRL_CLKSRC;
 		}
 
···
 	}
 
 	adau1372->enabled = enable;
+
+	return 0;
 }
 
 static int adau1372_set_bias_level(struct snd_soc_component *component,
···
 	case SND_SOC_BIAS_PREPARE:
 		break;
 	case SND_SOC_BIAS_STANDBY:
-		adau1372_set_power(adau1372, true);
-		break;
+		return adau1372_set_power(adau1372, true);
 	case SND_SOC_BIAS_OFF:
-		adau1372_set_power(adau1372, false);
-		break;
+		return adau1372_set_power(adau1372, false);
 	}
 
 	return 0;

sound/soc/codecs/sma1307.c

···
 				   sma1307->set.mode_size * 2 * sizeof(int),
 				   GFP_KERNEL);
 		if (!sma1307->set.mode_set[i]) {
-			for (int j = 0; j < i; j++)
-				kfree(sma1307->set.mode_set[j]);
+			for (int j = 0; j < i; j++) {
+				devm_kfree(sma1307->dev, sma1307->set.mode_set[j]);
+				sma1307->set.mode_set[j] = NULL;
+			}
 			sma1307->set.status = false;
 			return;
 		}

sound/soc/codecs/tas2781-fmwlib.c

···
 	int k = i * (cali_data->cali_dat_sz_per_dev + 1);
 	int rc;
 
+	if (!data || !cali_data->total_sz)
+		return;
+
 	if (data[k] != i) {
 		dev_err(priv->dev, "%s: no cal-data for dev %d from usr-spc\n",
 			__func__, i);

sound/soc/codecs/wcd934x.c

···
 	u32 def_dmic_rate, dmic_clk_drv;
 	int ret;
 
-	ret = wcd_dt_parse_mbhc_data(comp->dev, &wcd->mbhc_cfg);
+	ret = wcd_dt_parse_micbias_info(&wcd->common);
 	if (ret)
 		return ret;
 

sound/soc/fsl/imx-card.c

···
 			link->ops = &imx_aif_ops;
 		}
 
+		playback_only = false;
+		capture_only  = false;
 		graph_util_parse_link_direction(np, &playback_only, &capture_only);
 		link->playback_only = playback_only;
 		link->capture_only = capture_only;

sound/soc/generic/simple-card-utils.c

···
 	bool is_playback_only = of_property_read_bool(np, "playback-only");
 	bool is_capture_only  = of_property_read_bool(np, "capture-only");
 
-	if (np && playback_only)
+	if (playback_only && is_playback_only)
 		*playback_only = is_playback_only;
-	if (np && capture_only)
+	if (capture_only && is_capture_only)
 		*capture_only = is_capture_only;
 }
 EXPORT_SYMBOL_GPL(graph_util_parse_link_direction);

sound/soc/intel/boards/Kconfig

···
 	select SND_SOC_CS42L43_SDW
 	select MFD_CS42L43
 	select MFD_CS42L43_SDW
-	select PINCTRL_CS42L43
-	select SPI_CS42L43
 	select SND_SOC_CS35L56_SPI
 	select SND_SOC_CS35L56_SDW
 	select SND_SOC_DMIC

sound/soc/intel/boards/ehl_rt5660.c

···
 				  params_rate(params) * 50,
 				  params_rate(params) * 512);
 	if (ret < 0)
-		dev_err(codec_dai->dev, "can't set codec pll: %d\n", ret);
+		dev_err(rtd->dev, "can't set codec pll: %d\n", ret);
 
 	return ret;
 }

sound/soc/intel/catpt/device.c

···
 	if (IS_ERR(cdev->pci_ba))
 		return PTR_ERR(cdev->pci_ba);
 
-	/* alloc buffer for storing DRAM context during dx transitions */
+	/*
+	 * As per design HOST is responsible for preserving firmware's runtime
+	 * context during D0 -> D3 -> D0 transitions.  Addresses used for DMA
+	 * to/from HOST memory shall be outside the reserved range of 0xFFFxxxxx.
+	 */
+	ret = dma_coerce_mask_and_coherent(cdev->dev, DMA_BIT_MASK(31));
+	if (ret)
+		return ret;
+
 	cdev->dxbuf_vaddr = dmam_alloc_coherent(dev, catpt_dram_size(cdev),
 						&cdev->dxbuf_paddr, GFP_KERNEL);
 	if (!cdev->dxbuf_vaddr)

sound/soc/intel/catpt/dsp.c

···
 	dmac->dev = cdev->dev;
 	dmac->irq = cdev->irq;
 
-	ret = dma_coerce_mask_and_coherent(cdev->dev, DMA_BIT_MASK(31));
-	if (ret)
-		return ret;
 	/*
 	 * Caller is responsible for putting device in D0 to allow
 	 * for I/O and memory access before probing DW.

sound/soc/sdca/sdca_functions.c

···
 	} else if (num_init_writes % sizeof(*raw) != 0) {
 		dev_err(dev, "%pfwP: init table size invalid\n", function_node);
 		return -EINVAL;
-	} else if ((num_init_writes / sizeof(*raw)) > SDCA_MAX_INIT_COUNT) {
-		dev_err(dev, "%pfwP: maximum init table size exceeded\n", function_node);
-		return -EINVAL;
 	}
 
 	raw = kzalloc(num_init_writes, GFP_KERNEL);
···
 static struct sdca_entity *find_sdca_entity_by_label(struct sdca_function_data *function,
 						     const char *entity_label)
 {
+	struct sdca_entity *entity = NULL;
 	int i;
 
 	for (i = 0; i < function->num_entities; i++) {
-		struct sdca_entity *entity = &function->entities[i];
+		entity = &function->entities[i];
+
+		/* check whole string first*/
+		if (!strcmp(entity->label, entity_label))
+			return entity;
+	}
+
+	for (i = 0; i < function->num_entities; i++) {
+		entity = &function->entities[i];
 
 		if (!strncmp(entity->label, entity_label, strlen(entity_label)))
 			return entity;

sound/soc/soc-core.c

···
 	INIT_LIST_HEAD(&component->dobj_list);
 	INIT_LIST_HEAD(&component->card_list);
 	INIT_LIST_HEAD(&component->list);
+	INIT_LIST_HEAD(&component->card_aux_list);
 	mutex_init(&component->io_mutex);
 
 	if (!component->name) {

sound/soc/sof/ipc4-topology.c

···
 		return -EINVAL;
 	}
 
-	if (scontrol->priv_size < sizeof(struct sof_abi_hdr)) {
+	if (scontrol->priv_size && scontrol->priv_size < sizeof(struct sof_abi_hdr)) {
 		dev_err(sdev->dev,
 			"bytes control %s initial data size %zu is insufficient.\n",
 			scontrol->name, scontrol->priv_size);

sound/soc/sof/topology.c

···
 		asize = le32_to_cpu(array->size);
 
 		/* validate asize */
-		if (asize < 0) { /* FIXME: A zero-size array makes no sense */
+		if (asize < sizeof(*array)) {
 			dev_err(scomp->dev, "error: invalid array size 0x%x\n",
 				asize);
 			return -EINVAL;

sound/usb/Kconfig

···
 	tristate "Qualcomm Audio Offload driver"
 	depends on QCOM_QMI_HELPERS && SND_USB_AUDIO && SND_SOC_USB
 	depends on USB_XHCI_HCD && USB_XHCI_SIDEBAND
+	select AUXILIARY_BUS
 	help
 	  Say Y here to enable the Qualcomm USB audio offloading feature.
 

sound/usb/caiaq/device.c

···
 		memset(id, 0, sizeof(id));
 
 		for (c = card->shortname, len = 0;
-			*c && len < sizeof(card->id); c++)
+			*c && len < sizeof(card->id) - 1; c++)
 			if (*c != ' ')
 				id[len++] = *c;
 

sound/usb/qcom/qc_audio_offload.c

···
 // SPDX-License-Identifier: GPL-2.0
 /*
- * Copyright (c) 2022-2025 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) Qualcomm Technologies, Inc. and/or its subsidiaries.
  */
 
 #include <linux/auxiliary_bus.h>

sound/usb/quirks.c

···
 	/* Device matches */
 	DEVICE_FLG(0x001f, 0x0b21, /* AB13X USB Audio */
 		   QUIRK_FLAG_FORCE_IFACE_RESET | QUIRK_FLAG_IFACE_DELAY),
+	DEVICE_FLG(0x001f, 0x0b23, /* AB17X USB Audio */
+		   QUIRK_FLAG_FORCE_IFACE_RESET | QUIRK_FLAG_IFACE_DELAY),
 	DEVICE_FLG(0x0020, 0x0b21, /* GHW-123P */
 		   QUIRK_FLAG_FORCE_IFACE_RESET | QUIRK_FLAG_IFACE_DELAY),
 	DEVICE_FLG(0x03f0, 0x654a, /* HP 320 FHD Webcam */
···
 		   QUIRK_FLAG_PLAYBACK_FIRST | QUIRK_FLAG_GENERIC_IMPLICIT_FB),
 	DEVICE_FLG(0x13e5, 0x0001, /* Serato Phono */
 		   QUIRK_FLAG_IGNORE_CTL_ERROR),
+	DEVICE_FLG(0x152a, 0x880a, /* NeuralDSP Quad Cortex */
+		   0), /* Doesn't have the vendor quirk which would otherwise apply */
 	DEVICE_FLG(0x154e, 0x1002, /* Denon DCD-1500RE */
 		   QUIRK_FLAG_ITF_USB_DSD_DAC | QUIRK_FLAG_CTL_MSG_DELAY),
 	DEVICE_FLG(0x154e, 0x1003, /* Denon DA-300USB */
···
 		   QUIRK_FLAG_CTL_MSG_DELAY | QUIRK_FLAG_IFACE_DELAY),
 	VENDOR_FLG(0x07fd, /* MOTU */
 		   QUIRK_FLAG_VALIDATE_RATES),
+	DEVICE_FLG(0x1235, 0x8006, 0), /* Focusrite Scarlett 2i2 1st Gen */
+	DEVICE_FLG(0x1235, 0x800a, 0), /* Focusrite Scarlett 2i4 1st Gen */
+	DEVICE_FLG(0x1235, 0x8016, 0), /* Focusrite Scarlett 2i2 1st Gen */
+	DEVICE_FLG(0x1235, 0x801c, 0), /* Focusrite Scarlett Solo 1st Gen */
 	VENDOR_FLG(0x1235, /* Focusrite Novation */
 		   QUIRK_FLAG_SKIP_CLOCK_SELECTOR |
 		   QUIRK_FLAG_SKIP_IFACE_SETUP),

tools/testing/selftests/cgroup/lib/cgroup_util.c

···
 	return ret;
 }
 
+int cg_read_strcmp_wait(const char *cgroup, const char *control,
+			    const char *expected)
+{
+	int i, ret;
+
+	for (i = 0; i < 100; i++) {
+		ret = cg_read_strcmp(cgroup, control, expected);
+		if (!ret)
+			return ret;
+		usleep(10000);
+	}
+
+	return ret;
+}
+
 int cg_read_strstr(const char *cgroup, const char *control, const char *needle)
 {
 	char buf[PAGE_SIZE];

tools/testing/selftests/cgroup/lib/include/cgroup_util.h

···
 		   char *buf, size_t len);
 extern int cg_read_strcmp(const char *cgroup, const char *control,
 			  const char *expected);
+extern int cg_read_strcmp_wait(const char *cgroup, const char *control,
+				   const char *expected);
 extern int cg_read_strstr(const char *cgroup, const char *control,
 			  const char *needle);
 extern long cg_read_long(const char *cgroup, const char *control);

tools/testing/selftests/cgroup/test_core.c

···
 	if (err)
 		goto cleanup;
 
-	if (cg_read_strcmp(cg_test_d, "cgroup.events", "populated 0\n"))
+	if (cg_read_strcmp_wait(cg_test_d, "cgroup.events",
+				   "populated 0\n"))
 		goto cleanup;
 
 	/* Remove cgroup. */

tools/testing/selftests/cgroup/test_kill.c

···
 		wait_for_pid(pids[i]);
 
 	if (ret == KSFT_PASS &&
-	    cg_read_strcmp(cgroup, "cgroup.events", "populated 0\n"))
+	    cg_read_strcmp_wait(cgroup, "cgroup.events", "populated 0\n"))
 		ret = KSFT_FAIL;
 
 	if (cgroup)
···
 		wait_for_pid(pids[i]);
 
 	if (ret == KSFT_PASS &&
-	    cg_read_strcmp(cgroup[0], "cgroup.events", "populated 0\n"))
+	    cg_read_strcmp_wait(cgroup[0], "cgroup.events",
+				   "populated 0\n"))
 		ret = KSFT_FAIL;
 
 	for (i = 9; i >= 0 && cgroup[i]; i--) {
···
 		wait_for_pid(pid);
 
 	if (ret == KSFT_PASS &&
-	    cg_read_strcmp(cgroup, "cgroup.events", "populated 0\n"))
+	    cg_read_strcmp_wait(cgroup, "cgroup.events", "populated 0\n"))
 		ret = KSFT_FAIL;
 
 	if (cgroup)

tools/testing/selftests/landlock/tsync_test.c

···
  */
 
 #define _GNU_SOURCE
-#include <pthread.h>
-#include <sys/prctl.h>
 #include <linux/landlock.h>
+#include <pthread.h>
+#include <signal.h>
+#include <sys/prctl.h>
 
 #include "common.h"
 
···
 	/* Expect that both succeeded. */
 	EXPECT_EQ(0, d[0].result);
 	EXPECT_EQ(0, d[1].result);
+
+	EXPECT_EQ(0, close(ruleset_fd));
+}
+
+static void signal_nop_handler(int sig)
+{
+}
+
+struct signaler_data {
+	pthread_t target;
+	volatile bool stop;
+};
+
+static void *signaler_thread(void *data)
+{
+	struct signaler_data *sd = data;
+
+	while (!sd->stop)
+		pthread_kill(sd->target, SIGUSR1);
+
+	return NULL;
+}
+
+/*
+ * Number of idle sibling threads.  This must be large enough that even on
+ * machines with many cores, the sibling threads cannot all complete their
+ * credential preparation in a single parallel wave, otherwise the signaler
+ * thread has no window to interrupt wait_for_completion_interruptible().
+ * 200 threads on a 64-core machine yields ~3 serialized waves, giving the
+ * tight signal loop enough time to land an interruption.
+ */
+#define NUM_IDLE_THREADS 200
+
+/*
+ * Exercises the tsync interruption and cancellation paths in tsync.c.
+ *
+ * When a signal interrupts the calling thread while it waits for sibling
+ * threads to finish their credential preparation
+ * (wait_for_completion_interruptible in landlock_restrict_sibling_threads),
+ * the kernel sets ERESTARTNOINTR, cancels queued task works that have not
+ * started yet (cancel_tsync_works), then waits for the remaining works to
+ * finish.  On the error return, syscalls.c aborts the prepared credentials.
+ * The kernel automatically restarts the syscall, so userspace sees success.
+ */
+TEST(tsync_interrupt)
+{
+	size_t i;
+	pthread_t threads[NUM_IDLE_THREADS];
+	pthread_t signaler;
+	struct signaler_data sd;
+	struct sigaction sa = {};
+	const int ruleset_fd = create_ruleset(_metadata);
+
+	disable_caps(_metadata);
+
+	/* Install a no-op SIGUSR1 handler so the signal does not kill us. */
+	sa.sa_handler = signal_nop_handler;
+	sigemptyset(&sa.sa_mask);
+	ASSERT_EQ(0, sigaction(SIGUSR1, &sa, NULL));
+
+	ASSERT_EQ(0, prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0));
+
+	for (i = 0; i < NUM_IDLE_THREADS; i++)
+		ASSERT_EQ(0, pthread_create(&threads[i], NULL, idle, NULL));
+
+	/*
+	 * Start a signaler thread that continuously sends SIGUSR1 to the
+	 * calling thread.  This maximizes the chance of interrupting
+	 * wait_for_completion_interruptible() in the kernel's tsync path.
+	 */
+	sd.target = pthread_self();
+	sd.stop = false;
+	ASSERT_EQ(0, pthread_create(&signaler, NULL, signaler_thread, &sd));
+
+	/*
+	 * The syscall may be interrupted and transparently restarted by the
+	 * kernel (ERESTARTNOINTR).  From userspace, it should always succeed.
+	 */
+	EXPECT_EQ(0, landlock_restrict_self(ruleset_fd,
+					    LANDLOCK_RESTRICT_SELF_TSYNC));
+
+	sd.stop = true;
+	ASSERT_EQ(0, pthread_join(signaler, NULL));
+
+	for (i = 0; i < NUM_IDLE_THREADS; i++) {
+		ASSERT_EQ(0, pthread_cancel(threads[i]));
+		ASSERT_EQ(0, pthread_join(threads[i], NULL));
+	}
 
 	EXPECT_EQ(0, close(ruleset_fd));
 }

tools/testing/selftests/mount_setattr/mount_setattr_test.c

···
 			"size=100000,mode=700"), 0);
 
 	ASSERT_EQ(mount("testing", "/mnt", "tmpfs", MS_NOATIME | MS_NODEV,
-			"size=2m,mode=700"), 0);
+			"size=256m,mode=700"), 0);
 
 	ASSERT_EQ(mkdir("/mnt/A", 0777), 0);
 

tools/testing/selftests/sched_ext/Makefile

···
 	rt_stall			\
 	test_example			\
 	total_bw			\
+	cyclic_kick_wait		\
 
 testcase-targets := $(addsuffix .o,$(addprefix $(SCXOBJ_DIR)/,$(auto-test-targets)))
 

tools/testing/selftests/sched_ext/cyclic_kick_wait.bpf.c

···
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Stress concurrent SCX_KICK_WAIT calls to reproduce wait-cycle deadlock.
+ *
+ * Three CPUs are designated from userspace. Every enqueue from one of the
+ * three CPUs kicks the next CPU in the ring with SCX_KICK_WAIT, creating a
+ * persistent A -> B -> C -> A wait cycle pressure.
+ */
+#include <scx/common.bpf.h>
+
+char _license[] SEC("license") = "GPL";
+
+const volatile s32 test_cpu_a;
+const volatile s32 test_cpu_b;
+const volatile s32 test_cpu_c;
+
+u64 nr_enqueues;
+u64 nr_wait_kicks;
+
+UEI_DEFINE(uei);
+
+static s32 target_cpu(s32 cpu)
+{
+	if (cpu == test_cpu_a)
+		return test_cpu_b;
+	if (cpu == test_cpu_b)
+		return test_cpu_c;
+	if (cpu == test_cpu_c)
+		return test_cpu_a;
+	return -1;
+}
+
+void BPF_STRUCT_OPS(cyclic_kick_wait_enqueue, struct task_struct *p,
+		    u64 enq_flags)
+{
+	s32 this_cpu = bpf_get_smp_processor_id();
+	s32 tgt;
+
+	__sync_fetch_and_add(&nr_enqueues, 1);
+
+	if (p->flags & PF_KTHREAD) {
+		scx_bpf_dsq_insert(p, SCX_DSQ_LOCAL, SCX_SLICE_INF,
+				   enq_flags | SCX_ENQ_PREEMPT);
+		return;
+	}
+
+	scx_bpf_dsq_insert(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, enq_flags);
+
+	tgt = target_cpu(this_cpu);
+	if (tgt < 0 || tgt == this_cpu)
+		return;
+
+	__sync_fetch_and_add(&nr_wait_kicks, 1);
+	scx_bpf_kick_cpu(tgt, SCX_KICK_WAIT);
+}
+
+void BPF_STRUCT_OPS(cyclic_kick_wait_exit, struct scx_exit_info *ei)
+{
+	UEI_RECORD(uei, ei);
+}
+
+SEC(".struct_ops.link")
+struct sched_ext_ops cyclic_kick_wait_ops = {
+	.enqueue		= cyclic_kick_wait_enqueue,
+	.exit			= cyclic_kick_wait_exit,
+	.name			= "cyclic_kick_wait",
+	.timeout_ms		= 1000U,
+};

tools/testing/selftests/sched_ext/cyclic_kick_wait.c

···
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Test SCX_KICK_WAIT forward progress under cyclic wait pressure.
+ *
+ * SCX_KICK_WAIT busy-waits until the target CPU enters the scheduling path.
+ * If multiple CPUs form a wait cycle (A waits for B, B waits for C, C waits
+ * for A), all CPUs deadlock unless the implementation breaks the cycle.
+ *
+ * This test creates that scenario: three CPUs are arranged in a ring. The BPF
+ * scheduler's ops.enqueue() kicks the next CPU in the ring with SCX_KICK_WAIT
+ * on every enqueue. Userspace pins 4 worker threads per CPU that loop calling
+ * sched_yield(), generating a steady stream of enqueues and thus sustained
+ * A->B->C->A kick_wait cycle pressure. The test passes if the system remains
+ * responsive for 5 seconds without the scheduler being killed by the watchdog.
+ */
+#define _GNU_SOURCE
+
+#include <bpf/bpf.h>
+#include <errno.h>
+#include <pthread.h>
+#include <sched.h>
+#include <scx/common.h>
+#include <stdint.h>
+#include <string.h>
+#include <time.h>
+#include <unistd.h>
+
+#include "scx_test.h"
+#include "cyclic_kick_wait.bpf.skel.h"
+
+#define WORKERS_PER_CPU	4
+#define NR_TEST_CPUS	3
+#define NR_WORKERS	(NR_TEST_CPUS * WORKERS_PER_CPU)
+
+struct worker_ctx {
+	pthread_t tid;
+	int cpu;
+	volatile bool stop;
+	volatile __u64 iters;
+	bool started;
+};
+
+static void *worker_fn(void *arg)
+{
+	struct worker_ctx *worker = arg;
+	cpu_set_t mask;
+
+	CPU_ZERO(&mask);
+	CPU_SET(worker->cpu, &mask);
+
+	if (sched_setaffinity(0, sizeof(mask), &mask))
+		return (void *)(uintptr_t)errno;
+
+	while (!worker->stop) {
+		sched_yield();
+		worker->iters++;
+	}
+
+	return NULL;
+}
+
+static int join_worker(struct worker_ctx *worker)
+{
+	void *ret;
+	struct timespec ts;
+	int err;
+
+	if (!worker->started)
+		return 0;
+
+	if (clock_gettime(CLOCK_REALTIME, &ts))
+		return -errno;
+
+	ts.tv_sec += 2;
+	err = pthread_timedjoin_np(worker->tid, &ret, &ts);
+	if (err == ETIMEDOUT)
+		pthread_detach(worker->tid);
+	if (err)
+		return -err;
+
+	if ((uintptr_t)ret)
+		return -(int)(uintptr_t)ret;
+
+	return 0;
+}
+
+static enum scx_test_status setup(void **ctx)
+{
+	struct cyclic_kick_wait *skel;
+
+	skel = cyclic_kick_wait__open();
+	SCX_FAIL_IF(!skel, "Failed to open skel");
+	SCX_ENUM_INIT(skel);
+
+	*ctx = skel;
+	return SCX_TEST_PASS;
+}
+
+static enum scx_test_status run(void *ctx)
+{
+	struct cyclic_kick_wait *skel = ctx;
+	struct worker_ctx workers[NR_WORKERS] = {};
+	struct bpf_link *link = NULL;
+	enum scx_test_status status = SCX_TEST_PASS;
+	int test_cpus[NR_TEST_CPUS];
+	int nr_cpus = 0;
+	cpu_set_t mask;
+	int ret, i;
+
+	if (sched_getaffinity(0, sizeof(mask), &mask)) {
+		SCX_ERR("Failed to get affinity (%d)", errno);
+		return SCX_TEST_FAIL;
+	}
+
+	for (i = 0; i < CPU_SETSIZE; i++) {
+		if (CPU_ISSET(i, &mask))
+			test_cpus[nr_cpus++] = i;
+		if (nr_cpus == NR_TEST_CPUS)
+			break;
+	}
+
+	if (nr_cpus < NR_TEST_CPUS)
+		return SCX_TEST_SKIP;
+
+	skel->rodata->test_cpu_a = test_cpus[0];
+	skel->rodata->test_cpu_b = test_cpus[1];
+	skel->rodata->test_cpu_c = test_cpus[2];
+
+	if (cyclic_kick_wait__load(skel)) {
+		SCX_ERR("Failed to load skel");
+		return SCX_TEST_FAIL;
+	}
+
+	link = bpf_map__attach_struct_ops(skel->maps.cyclic_kick_wait_ops);
+	if (!link) {
+		SCX_ERR("Failed to attach scheduler");
+		return SCX_TEST_FAIL;
+	}
+
+	for (i = 0; i < NR_WORKERS; i++)
+		workers[i].cpu = test_cpus[i / WORKERS_PER_CPU];
+
+	for (i = 0; i < NR_WORKERS; i++) {
+		ret = pthread_create(&workers[i].tid, NULL, worker_fn, &workers[i]);
+		if (ret) {
+			SCX_ERR("Failed to create worker thread %d (%d)", i, ret);
+			status = SCX_TEST_FAIL;
+			goto out;
+		}
+		workers[i].started = true;
+	}
+
+	sleep(5);
+
+	if (skel->data->uei.kind != EXIT_KIND(SCX_EXIT_NONE)) {
+		SCX_ERR("Scheduler exited unexpectedly (kind=%llu code=%lld)",
+			(unsigned long long)skel->data->uei.kind,
+			(long long)skel->data->uei.exit_code);
+		status = SCX_TEST_FAIL;
+	}
+
+out:
+	for (i = 0; i < NR_WORKERS; i++)
+		workers[i].stop = true;
+
+	for (i = 0; i < NR_WORKERS; i++) {
+		ret = join_worker(&workers[i]);
+		if (ret && status == SCX_TEST_PASS) {
+			SCX_ERR("Failed to join worker thread %d (%d)", i, ret);
+			status = SCX_TEST_FAIL;
+		}
+	}
+
+	if (link)
+		bpf_link__destroy(link);
+
+	return status;
+}
+
+static void cleanup(void *ctx)
+{
+	struct cyclic_kick_wait *skel = ctx;
+
+	cyclic_kick_wait__destroy(skel);
+}
+
+struct scx_test cyclic_kick_wait = {
+	.name = "cyclic_kick_wait",
+	.description = "Verify SCX_KICK_WAIT forward progress under a 3-CPU wait cycle",
+	.setup = setup,
+	.run = run,
+	.cleanup = cleanup,
+};
+REGISTER_SCX_TEST(&cyclic_kick_wait)

tools/testing/selftests/tc-testing/tc-tests/infra/filter.json

···
         "teardown": [
             "$TC qdisc del dev $DUMMY root handle 1: htb default 1"
         ]
+    },
+    {
+        "id": "b7e3",
+        "name": "Empty fw filter on shared block - rejected at config time",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
+        "setup": [
+            "$TC qdisc add dev $DEV1 egress_block 1 clsact"
+        ],
+        "cmdUnderTest": "$TC filter add block 1 protocol ip prio 1 fw",
+        "expExitCode": "2",
+        "verifyCmd": "$TC filter show block 1",
+        "matchPattern": "fw",
+        "matchCount": "0",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 clsact"
+        ]
+    },
+    {
+        "id": "c8f4",
+        "name": "Flow filter on shared block without baseclass - rejected at config time",
+        "category": [
+            "filter",
+            "flow"
+        ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress_block 1 clsact"
+        ],
+        "cmdUnderTest": "$TC filter add block 1 protocol ip prio 1 handle 1 flow map key dst",
+        "expExitCode": "2",
+        "verifyCmd": "$TC filter show block 1",
+        "matchPattern": "flow",
+        "matchCount": "0",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 clsact"
+        ]
     }
 ]

tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json

···
         "teardown": [
             "$TC qdisc del dev $DUMMY root handle 1:"
         ]
+    },
+    {
+        "id": "a3d7",
+        "name": "HFSC with large m1 - no divide-by-zero on class reactivation",
+        "category": [
+            "qdisc",
+            "hfsc"
+        ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
+        "setup": [
+            "$TC qdisc replace dev $DUMMY root handle 1: hfsc default 1",
+            "$TC class replace dev $DUMMY parent 1: classid 1:1 hfsc rt m1 32gbit d 1ms m2 0bit ls m1 32gbit d 1ms m2 0bit",
+            "ping -I$DUMMY -f -c1 -s64 -W1 10.10.10.1 || true",
+            "sleep 1"
+        ],
+        "cmdUnderTest": "ping -I$DUMMY -f -c1 -s64 -W1 10.10.10.1 || true",
+        "expExitCode": "0",
+        "verifyCmd": "$TC qdisc show dev $DUMMY",
+        "matchPattern": "qdisc hfsc 1: root",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DUMMY handle 1: root"
+        ]
     }
 ]

tools/tracing/rtla/src/timerlat_bpf.h

···
 };
 
 #ifndef __bpf__
-#include <bpf/libbpf.h>
 #ifdef HAVE_BPF_SKEL
 int timerlat_bpf_init(struct timerlat_params *params);
 int timerlat_bpf_attach(void);