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

Cross-merge networking fixes after downstream PR.

Conflicts:

net/sched/act_ct.c
26488172b029 ("net/sched: Fix UAF when resolving a clash")
3abbd7ed8b76 ("act_ct: prepare for stolen verdict coming from conntrack and nat engine")

No adjacent changes.

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

.mailmap

···
 Li Yang <[e-mail]> <[e-mail]>
 Lior David <[e-mail]> <[e-mail]>
 Lorenzo Pieralisi <[e-mail]> <[e-mail]>
+Lorenzo Stoakes <[e-mail]> <[e-mail]>
 Luca Ceresoli <[e-mail]> <[e-mail]>
 Lukasz Luba <[e-mail]> <[e-mail]>
 Luo Jie <[e-mail]> <[e-mail]>

CREDITS

···
 S: 13353 Berlin
 S: Germany
 
-N: Gustavo Pimental
+N: Gustavo Pimentel
 E: [e-mail]
 D: PCI driver for Synopsys DesignWare
+D: Synopsys DesignWare eDMA driver
+D: Synopsys DesignWare xData traffic generator
 
 N: Emanuel Pirker
 E: [e-mail]

Documentation/arch/riscv/cmodx.rst

···
 		printf("Value before cmodx: %d\n", value);
 
 		// Call prctl before first fence.i is called inside modify_instruction
-		prctl(PR_RISCV_SET_ICACHE_FLUSH_CTX_ON, PR_RISCV_CTX_SW_FENCEI, PR_RISCV_SCOPE_PER_PROCESS);
+		prctl(PR_RISCV_SET_ICACHE_FLUSH_CTX, PR_RISCV_CTX_SW_FENCEI_ON, PR_RISCV_SCOPE_PER_PROCESS);
 		modify_instruction();
 		// Call prctl after final fence.i is called in process
-		prctl(PR_RISCV_SET_ICACHE_FLUSH_CTX_OFF, PR_RISCV_CTX_SW_FENCEI, PR_RISCV_SCOPE_PER_PROCESS);
+		prctl(PR_RISCV_SET_ICACHE_FLUSH_CTX, PR_RISCV_CTX_SW_FENCEI_OFF, PR_RISCV_SCOPE_PER_PROCESS);
 
 		value = get_value();
 		printf("Value after cmodx: %d\n", value);

Documentation/networking/devlink/devlink-region.rst

···
     $ devlink region show [ DEV/REGION ]
     $ devlink region del DEV/REGION snapshot SNAPSHOT_ID
     $ devlink region dump DEV/REGION [ snapshot SNAPSHOT_ID ]
-    $ devlink region read DEV/REGION [ snapshot SNAPSHOT_ID ] address ADDRESS length length
+    $ devlink region read DEV/REGION [ snapshot SNAPSHOT_ID ] address ADDRESS length LENGTH
 
     # Show all of the exposed regions with region sizes:
     $ devlink region show

MAINTAINERS

···
 F:	drivers/usb/dwc3/
 
 DESIGNWARE XDATA IP DRIVER
-M:	Gustavo Pimentel <[e-mail]>
 L:	[e-mail]
-S:	Maintained
+S:	Orphan
 F:	Documentation/misc-devices/dw-xdata-pcie.rst
 F:	drivers/misc/dw-xdata-pcie.c
 
···
 M:	Andrew Morton <[e-mail]>
 R:	Liam R. Howlett <[e-mail]>
 R:	Vlastimil Babka <[e-mail]>
-R:	Lorenzo Stoakes <[e-mail]>
+R:	Lorenzo Stoakes <[e-mail]>
 L:	[e-mail]
 S:	Maintained
 W:	http://www.linux-mm.org

Makefile

···
 VERSION = 6
 PATCHLEVEL = 10
 SUBLEVEL = 0
-EXTRAVERSION = -rc6
+EXTRAVERSION = -rc7
 NAME = Baby Opossum Posse
 
 # *DOCUMENTATION*

arch/powerpc/kernel/eeh_pe.c

···
 {
 	struct eeh_dev *edev;
 	struct pci_dev *pdev;
+	struct pci_bus *bus = NULL;
 
 	if (pe->type & EEH_PE_PHB)
 		return pe->phb->bus;
···
 
 	/* Retrieve the parent PCI bus of first (top) PCI device */
 	edev = list_first_entry_or_null(&pe->edevs, struct eeh_dev, entry);
+	pci_lock_rescan_remove();
 	pdev = eeh_dev_to_pci_dev(edev);
 	if (pdev)
-		return pdev->bus;
+		bus = pdev->bus;
+	pci_unlock_rescan_remove();
 
-	return NULL;
+	return bus;
 }

arch/powerpc/kernel/head_64.S

···
  * Note: This process overwrites the OF exception vectors.
  */
 	LOAD_REG_IMMEDIATE(r3, PAGE_OFFSET)
-	mr.	r4,r26			/* In some cases the loader may  */
-	beq	9f			/* have already put us at zero */
+	mr	r4,r26			/* Load the virtual source address into r4 */
+	cmpld	r3,r4			/* Check if source == dest */
+	beq	9f			/* If so skip the copy  */
 	li	r6,0x100		/* Start offset, the first 0x100 */
 					/* bytes were copied earlier.	 */
 

arch/powerpc/kexec/core_64.c

···
 #include <asm/paca.h>
 #include <asm/mmu.h>
 #include <asm/sections.h>	/* _end */
+#include <asm/setup.h>
 #include <asm/smp.h>
 #include <asm/hw_breakpoint.h>
 #include <asm/svm.h>
···
 
 	if (!kdump_in_progress())
 		kexec_prepare_cpus();
+
+#ifdef CONFIG_PPC_PSERIES
+	/*
+	 * This must be done after other CPUs have shut down, otherwise they
+	 * could execute the 'scv' instruction, which is not supported with
+	 * reloc disabled (see configure_exceptions()).
+	 */
+	if (firmware_has_feature(FW_FEATURE_SET_MODE))
+		pseries_disable_reloc_on_exc();
+#endif
 
 	printk("kexec: Starting switchover sequence.\n");
 

arch/powerpc/platforms/pseries/kexec.c

···
 	} else
 		xics_kexec_teardown_cpu(secondary);
 }
-
-void pseries_machine_kexec(struct kimage *image)
-{
-	if (firmware_has_feature(FW_FEATURE_SET_MODE))
-		pseries_disable_reloc_on_exc();
-
-	default_machine_kexec(image);
-}

arch/powerpc/platforms/pseries/pseries.h

···
 #endif
 
 extern void pseries_kexec_cpu_down(int crash_shutdown, int secondary);
-void pseries_machine_kexec(struct kimage *image);
 
 extern void pSeries_final_fixup(void);
 

arch/powerpc/platforms/pseries/setup.c

···
 {
 	void (*ctor)(void *) = get_dtl_cache_ctor();
 
-	dtl_cache = kmem_cache_create("dtl", DISPATCH_LOG_BYTES,
-						DISPATCH_LOG_BYTES, 0, ctor);
+	dtl_cache = kmem_cache_create_usercopy("dtl", DISPATCH_LOG_BYTES,
+						DISPATCH_LOG_BYTES, 0, 0, DISPATCH_LOG_BYTES, ctor);
 	if (!dtl_cache) {
 		pr_warn("Failed to create dispatch trace log buffer cache\n");
 		pr_warn("Stolen time statistics will be unreliable\n");
···
 	.machine_check_exception = pSeries_machine_check_exception,
 	.machine_check_log_err	= pSeries_machine_check_log_err,
 #ifdef CONFIG_KEXEC_CORE
-	.machine_kexec          = pseries_machine_kexec,
 	.kexec_cpu_down         = pseries_kexec_cpu_down,
 #endif
 #ifdef CONFIG_MEMORY_HOTPLUG

arch/riscv/kernel/machine_kexec.c

···
 
 	for_each_irq_desc(i, desc) {
 		struct irq_chip *chip;
-		int ret;
 
 		chip = irq_desc_get_chip(desc);
 		if (!chip)
 			continue;
 
-		/*
-		 * First try to remove the active state. If this
-		 * fails, try to EOI the interrupt.
-		 */
-		ret = irq_set_irqchip_state(i, IRQCHIP_STATE_ACTIVE, false);
-
-		if (ret && irqd_irq_inprogress(&desc->irq_data) &&
-		    chip->irq_eoi)
+		if (chip->irq_eoi && irqd_irq_inprogress(&desc->irq_data))
 			chip->irq_eoi(&desc->irq_data);
 
 		if (chip->irq_mask)

arch/riscv/kernel/stacktrace.c

···
 			     bool (*fn)(void *, unsigned long), void *arg)
 {
 	unsigned long fp, sp, pc;
+	int graph_idx = 0;
 	int level = 0;
 
 	if (regs) {
···
 			pc = regs->ra;
 		} else {
 			fp = frame->fp;
-			pc = ftrace_graph_ret_addr(current, NULL, frame->ra,
+			pc = ftrace_graph_ret_addr(current, &graph_idx, frame->ra,
 						   &frame->ra);
 			if (pc == (unsigned long)ret_from_exception) {
 				if (unlikely(!__kernel_text_address(pc) || !fn(arg, pc)))

arch/riscv/kvm/vcpu_pmu.c

···
 
 	event = perf_event_create_kernel_counter(attr, -1, current, kvm_riscv_pmu_overflow, pmc);
 	if (IS_ERR(event)) {
-		pr_err("kvm pmu event creation failed for eidx %lx: %ld\n", eidx, PTR_ERR(event));
+		pr_debug("kvm pmu event creation failed for eidx %lx: %ld\n", eidx, PTR_ERR(event));
 		return PTR_ERR(event);
 	}
 

arch/s390/include/asm/kvm_host.h

···
 	u64 instruction_io_other;
 	u64 instruction_lpsw;
 	u64 instruction_lpswe;
+	u64 instruction_lpswey;
 	u64 instruction_pfmf;
 	u64 instruction_ptff;
 	u64 instruction_sck;

arch/s390/kvm/kvm-s390.c

···
 	STATS_DESC_COUNTER(VCPU, instruction_io_other),
 	STATS_DESC_COUNTER(VCPU, instruction_lpsw),
 	STATS_DESC_COUNTER(VCPU, instruction_lpswe),
+	STATS_DESC_COUNTER(VCPU, instruction_lpswey),
 	STATS_DESC_COUNTER(VCPU, instruction_pfmf),
 	STATS_DESC_COUNTER(VCPU, instruction_ptff),
 	STATS_DESC_COUNTER(VCPU, instruction_sck),

arch/s390/kvm/kvm-s390.h

···
 	return (base2 ? vcpu->run->s.regs.gprs[base2] : 0) + disp2;
 }
 
+static inline u64 kvm_s390_get_base_disp_siy(struct kvm_vcpu *vcpu, u8 *ar)
+{
+	u32 base1 = vcpu->arch.sie_block->ipb >> 28;
+	s64 disp1;
+
+	/* The displacement is a 20bit _SIGNED_ value */
+	disp1 = sign_extend64(((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16) +
+			      ((vcpu->arch.sie_block->ipb & 0xff00) << 4), 19);
+
+	if (ar)
+		*ar = base1;
+
+	return (base1 ? vcpu->run->s.regs.gprs[base1] : 0) + disp1;
+}
+
 static inline void kvm_s390_get_base_disp_sse(struct kvm_vcpu *vcpu,
 					      u64 *address1, u64 *address2,
 					      u8 *ar_b1, u8 *ar_b2)

arch/s390/kvm/priv.c

···
 	return 0;
 }
 
+static int handle_lpswey(struct kvm_vcpu *vcpu)
+{
+	psw_t new_psw;
+	u64 addr;
+	int rc;
+	u8 ar;
+
+	vcpu->stat.instruction_lpswey++;
+
+	if (!test_kvm_facility(vcpu->kvm, 193))
+		return kvm_s390_inject_program_int(vcpu, PGM_OPERATION);
+
+	if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
+		return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
+
+	addr = kvm_s390_get_base_disp_siy(vcpu, &ar);
+	if (addr & 7)
+		return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
+
+	rc = read_guest(vcpu, addr, ar, &new_psw, sizeof(new_psw));
+	if (rc)
+		return kvm_s390_inject_prog_cond(vcpu, rc);
+
+	vcpu->arch.sie_block->gpsw = new_psw;
+	if (!is_valid_psw(&vcpu->arch.sie_block->gpsw))
+		return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
+
+	return 0;
+}
+
 static int handle_stidp(struct kvm_vcpu *vcpu)
 {
 	u64 stidp_data = vcpu->kvm->arch.model.cpuid;
···
 	case 0x61:
 	case 0x62:
 		return handle_ri(vcpu);
+	case 0x71:
+		return handle_lpswey(vcpu);
 	default:
 		return -EOPNOTSUPP;
 	}

arch/s390/mm/pgalloc.c

···
 
 void crst_table_free(struct mm_struct *mm, unsigned long *table)
 {
+	if (!table)
+		return;
 	pagetable_free(virt_to_ptdesc(table));
 }
 
···
 
 static void base_crst_free(unsigned long *table)
 {
+	if (!table)
+		return;
 	pagetable_free(virt_to_ptdesc(table));
 }
 

arch/xtensa/include/asm/current.h

···
 
 struct task_struct;
 
-static inline struct task_struct *get_current(void)
+static __always_inline struct task_struct *get_current(void)
 {
 	return current_thread_info()->task;
 }

arch/xtensa/include/asm/thread_info.h

···
 }
 
 /* how to get the thread information struct from C */
-static inline struct thread_info *current_thread_info(void)
+static __always_inline struct thread_info *current_thread_info(void)
 {
 	struct thread_info *ti;
 	 __asm__("extui %0, a1, 0, "__stringify(CURRENT_SHIFT)"\n\t"

drivers/acpi/processor_idle.c

···
 #include <linux/acpi.h>
 #include <linux/dmi.h>
 #include <linux/sched.h>       /* need_resched() */
-#include <linux/sort.h>
 #include <linux/tick.h>
 #include <linux/cpuidle.h>
 #include <linux/cpu.h>
···
 	acpi_write_bit_register(ACPI_BITREG_BUS_MASTER_RLD, 1);
 }
 
-static int acpi_cst_latency_cmp(const void *a, const void *b)
+static void acpi_cst_latency_sort(struct acpi_processor_cx *states, size_t length)
 {
-	const struct acpi_processor_cx *x = a, *y = b;
+	int i, j, k;
 
-	if (!(x->valid && y->valid))
-		return 0;
-	if (x->latency > y->latency)
-		return 1;
-	if (x->latency < y->latency)
-		return -1;
-	return 0;
-}
-static void acpi_cst_latency_swap(void *a, void *b, int n)
-{
-	struct acpi_processor_cx *x = a, *y = b;
+	for (i = 1; i < length; i++) {
+		if (!states[i].valid)
+			continue;
 
-	if (!(x->valid && y->valid))
-		return;
-	swap(x->latency, y->latency);
+		for (j = i - 1, k = i; j >= 0; j--) {
+			if (!states[j].valid)
+				continue;
+
+			if (states[j].latency > states[k].latency)
+				swap(states[j].latency, states[k].latency);
+
+			k = j;
+		}
+	}
 }
 
 static int acpi_processor_power_verify(struct acpi_processor *pr)
···
 
 	if (buggy_latency) {
 		pr_notice("FW issue: working around C-state latencies out of order\n");
-		sort(&pr->power.states[1], max_cstate,
-		     sizeof(struct acpi_processor_cx),
-		     acpi_cst_latency_cmp,
-		     acpi_cst_latency_swap);
+		acpi_cst_latency_sort(&pr->power.states[1], max_cstate);
 	}
 
 	lapic_timer_propagate_broadcast(pr);

drivers/char/tpm/Makefile

···
 tpm-y += eventlog/tpm1.o
 tpm-y += eventlog/tpm2.o
 tpm-y += tpm-buf.o
+tpm-y += tpm2-sessions.o
 
-tpm-$(CONFIG_TCG_TPM2_HMAC) += tpm2-sessions.o
 tpm-$(CONFIG_ACPI) += tpm_ppi.o eventlog/acpi.o
 tpm-$(CONFIG_EFI) += eventlog/efi.o
 tpm-$(CONFIG_OF) += eventlog/of.o

drivers/char/tpm/tpm2-sessions.c

···
 #define AES_KEY_BYTES	AES_KEYSIZE_128
 #define AES_KEY_BITS	(AES_KEY_BYTES*8)
 
-static int tpm2_create_primary(struct tpm_chip *chip, u32 hierarchy,
-			       u32 *handle, u8 *name);
-
 /*
  * This is the structure that carries all the auth information (like
  * session handle, nonces, session key and auth) from use to use it is
···
 	u8 name[AUTH_MAX_NAMES][2 + SHA512_DIGEST_SIZE];
 };
 
+#ifdef CONFIG_TCG_TPM2_HMAC
 /*
  * Name Size based on TPM algorithm (assumes no hash bigger than 255)
  */
···
 	u16 alg = get_unaligned_be16(name);
 	return size_map[alg] + 2;
 }
+
+static int tpm2_parse_read_public(char *name, struct tpm_buf *buf)
+{
+	struct tpm_header *head = (struct tpm_header *)buf->data;
+	off_t offset = TPM_HEADER_SIZE;
+	u32 tot_len = be32_to_cpu(head->length);
+	u32 val;
+
+	/* we're starting after the header so adjust the length */
+	tot_len -= TPM_HEADER_SIZE;
+
+	/* skip public */
+	val = tpm_buf_read_u16(buf, &offset);
+	if (val > tot_len)
+		return -EINVAL;
+	offset += val;
+	/* name */
+	val = tpm_buf_read_u16(buf, &offset);
+	if (val != name_size(&buf->data[offset]))
+		return -EINVAL;
+	memcpy(name, &buf->data[offset], val);
+	/* forget the rest */
+	return 0;
+}
+
+static int tpm2_read_public(struct tpm_chip *chip, u32 handle, char *name)
+{
+	struct tpm_buf buf;
+	int rc;
+
+	rc = tpm_buf_init(&buf, TPM2_ST_NO_SESSIONS, TPM2_CC_READ_PUBLIC);
+	if (rc)
+		return rc;
+
+	tpm_buf_append_u32(&buf, handle);
+	rc = tpm_transmit_cmd(chip, &buf, 0, "read public");
+	if (rc == TPM2_RC_SUCCESS)
+		rc = tpm2_parse_read_public(name, &buf);
+
+	tpm_buf_destroy(&buf);
+
+	return rc;
+}
+#endif /* CONFIG_TCG_TPM2_HMAC */
+
+/**
+ * tpm_buf_append_name() - add a handle area to the buffer
+ * @chip: the TPM chip structure
+ * @buf: The buffer to be appended
+ * @handle: The handle to be appended
+ * @name: The name of the handle (may be NULL)
+ *
+ * In order to compute session HMACs, we need to know the names of the
+ * objects pointed to by the handles.  For most objects, this is simply
+ * the actual 4 byte handle or an empty buf (in these cases @name
+ * should be NULL) but for volatile objects, permanent objects and NV
+ * areas, the name is defined as the hash (according to the name
+ * algorithm which should be set to sha256) of the public area to
+ * which the two byte algorithm id has been appended.  For these
+ * objects, the @name pointer should point to this.  If a name is
+ * required but @name is NULL, then TPM2_ReadPublic() will be called
+ * on the handle to obtain the name.
+ *
+ * As with most tpm_buf operations, success is assumed because failure
+ * will be caused by an incorrect programming model and indicated by a
+ * kernel message.
+ */
+void tpm_buf_append_name(struct tpm_chip *chip, struct tpm_buf *buf,
+			 u32 handle, u8 *name)
+{
+#ifdef CONFIG_TCG_TPM2_HMAC
+	enum tpm2_mso_type mso = tpm2_handle_mso(handle);
+	struct tpm2_auth *auth;
+	int slot;
+#endif
+
+	if (!tpm2_chip_auth(chip)) {
+		tpm_buf_append_u32(buf, handle);
+		/* count the number of handles in the upper bits of flags */
+		buf->handles++;
+		return;
+	}
+
+#ifdef CONFIG_TCG_TPM2_HMAC
+	slot = (tpm_buf_length(buf) - TPM_HEADER_SIZE) / 4;
+	if (slot >= AUTH_MAX_NAMES) {
+		dev_err(&chip->dev, "TPM: too many handles\n");
+		return;
+	}
+	auth = chip->auth;
+	WARN(auth->session != tpm_buf_length(buf),
+	     "name added in wrong place\n");
+	tpm_buf_append_u32(buf, handle);
+	auth->session += 4;
+
+	if (mso == TPM2_MSO_PERSISTENT ||
+	    mso == TPM2_MSO_VOLATILE ||
+	    mso == TPM2_MSO_NVRAM) {
+		if (!name)
+			tpm2_read_public(chip, handle, auth->name[slot]);
+	} else {
+		if (name)
+			dev_err(&chip->dev, "TPM: Handle does not require name but one is specified\n");
+	}
+
+	auth->name_h[slot] = handle;
+	if (name)
+		memcpy(auth->name[slot], name, name_size(name));
+#endif
+}
+EXPORT_SYMBOL_GPL(tpm_buf_append_name);
+
+/**
+ * tpm_buf_append_hmac_session() - Append a TPM session element
+ * @chip: the TPM chip structure
+ * @buf: The buffer to be appended
+ * @attributes: The session attributes
+ * @passphrase: The session authority (NULL if none)
+ * @passphrase_len: The length of the session authority (0 if none)
+ *
+ * This fills in a session structure in the TPM command buffer, except
+ * for the HMAC which cannot be computed until the command buffer is
+ * complete.  The type of session is controlled by the @attributes,
+ * the main ones of which are TPM2_SA_CONTINUE_SESSION which means the
+ * session won't terminate after tpm_buf_check_hmac_response(),
+ * TPM2_SA_DECRYPT which means this buffers first parameter should be
+ * encrypted with a session key and TPM2_SA_ENCRYPT, which means the
+ * response buffer's first parameter needs to be decrypted (confusing,
+ * but the defines are written from the point of view of the TPM).
+ *
+ * Any session appended by this command must be finalized by calling
+ * tpm_buf_fill_hmac_session() otherwise the HMAC will be incorrect
+ * and the TPM will reject the command.
+ *
+ * As with most tpm_buf operations, success is assumed because failure
+ * will be caused by an incorrect programming model and indicated by a
+ * kernel message.
+ */
+void tpm_buf_append_hmac_session(struct tpm_chip *chip, struct tpm_buf *buf,
+				 u8 attributes, u8 *passphrase,
+				 int passphrase_len)
+{
+#ifdef CONFIG_TCG_TPM2_HMAC
+	u8 nonce[SHA256_DIGEST_SIZE];
+	struct tpm2_auth *auth;
+	u32 len;
+#endif
+
+	if (!tpm2_chip_auth(chip)) {
+		/* offset tells us where the sessions area begins */
+		int offset = buf->handles * 4 + TPM_HEADER_SIZE;
+		u32 len = 9 + passphrase_len;
+
+		if (tpm_buf_length(buf) != offset) {
+			/* not the first session so update the existing length */
+			len += get_unaligned_be32(&buf->data[offset]);
+			put_unaligned_be32(len, &buf->data[offset]);
+		} else {
+			tpm_buf_append_u32(buf, len);
+		}
+		/* auth handle */
+		tpm_buf_append_u32(buf, TPM2_RS_PW);
+		/* nonce */
+		tpm_buf_append_u16(buf, 0);
+		/* attributes */
+		tpm_buf_append_u8(buf, 0);
+		/* passphrase */
+		tpm_buf_append_u16(buf, passphrase_len);
+		tpm_buf_append(buf, passphrase, passphrase_len);
+		return;
+	}
+
+#ifdef CONFIG_TCG_TPM2_HMAC
+	/*
+	 * The Architecture Guide requires us to strip trailing zeros
+	 * before computing the HMAC
+	 */
+	while (passphrase && passphrase_len > 0 && passphrase[passphrase_len - 1] == '\0')
+		passphrase_len--;
+
+	auth = chip->auth;
+	auth->attrs = attributes;
+	auth->passphrase_len = passphrase_len;
+	if (passphrase_len)
+		memcpy(auth->passphrase, passphrase, passphrase_len);
+
+	if (auth->session != tpm_buf_length(buf)) {
+		/* we're not the first session */
+		len = get_unaligned_be32(&buf->data[auth->session]);
+		if (4 + len + auth->session != tpm_buf_length(buf)) {
+			WARN(1, "session length mismatch, cannot append");
+			return;
+		}
+
+		/* add our new session */
+		len += 9 + 2 * SHA256_DIGEST_SIZE;
+		put_unaligned_be32(len, &buf->data[auth->session]);
+	} else {
+		tpm_buf_append_u32(buf, 9 + 2 * SHA256_DIGEST_SIZE);
+	}
+
+	/* random number for our nonce */
+	get_random_bytes(nonce, sizeof(nonce));
+	memcpy(auth->our_nonce, nonce, sizeof(nonce));
+	tpm_buf_append_u32(buf, auth->handle);
+	/* our new nonce */
+	tpm_buf_append_u16(buf, SHA256_DIGEST_SIZE);
+	tpm_buf_append(buf, nonce, SHA256_DIGEST_SIZE);
+	tpm_buf_append_u8(buf, auth->attrs);
+	/* and put a placeholder for the hmac */
+	tpm_buf_append_u16(buf, SHA256_DIGEST_SIZE);
+	tpm_buf_append(buf, nonce, SHA256_DIGEST_SIZE);
+#endif
+}
+EXPORT_SYMBOL_GPL(tpm_buf_append_hmac_session);
+
+#ifdef CONFIG_TCG_TPM2_HMAC
+
+static int tpm2_create_primary(struct tpm_chip *chip, u32 hierarchy,
+			       u32 *handle, u8 *name);
 
 /*
  * It turns out the crypto hmac(sha256) is hard for us to consume
···
 }
 
 /**
- * tpm_buf_append_hmac_session() - Append a TPM session element
- * @chip: the TPM chip structure
- * @buf: The buffer to be appended
- * @attributes: The session attributes
- * @passphrase: The session authority (NULL if none)
- * @passphrase_len: The length of the session authority (0 if none)
- *
- * This fills in a session structure in the TPM command buffer, except
- * for the HMAC which cannot be computed until the command buffer is
- * complete.  The type of session is controlled by the @attributes,
- * the main ones of which are TPM2_SA_CONTINUE_SESSION which means the
- * session won't terminate after tpm_buf_check_hmac_response(),
- * TPM2_SA_DECRYPT which means this buffers first parameter should be
- * encrypted with a session key and TPM2_SA_ENCRYPT, which means the
- * response buffer's first parameter needs to be decrypted (confusing,
- * but the defines are written from the point of view of the TPM).
- *
- * Any session appended by this command must be finalized by calling
- * tpm_buf_fill_hmac_session() otherwise the HMAC will be incorrect
- * and the TPM will reject the command.
- *
- * As with most tpm_buf operations, success is assumed because failure
- * will be caused by an incorrect programming model and indicated by a
- * kernel message.
- */
-void tpm_buf_append_hmac_session(struct tpm_chip *chip, struct tpm_buf *buf,
-				 u8 attributes, u8 *passphrase,
-				 int passphrase_len)
-{
-	u8 nonce[SHA256_DIGEST_SIZE];
-	u32 len;
-	struct tpm2_auth *auth = chip->auth;
-
-	/*
-	 * The Architecture Guide requires us to strip trailing zeros
-	 * before computing the HMAC
-	 */
-	while (passphrase && passphrase_len > 0
-	       && passphrase[passphrase_len - 1] == '\0')
-		passphrase_len--;
-
-	auth->attrs = attributes;
-	auth->passphrase_len = passphrase_len;
-	if (passphrase_len)
-		memcpy(auth->passphrase, passphrase, passphrase_len);
-
-	if (auth->session != tpm_buf_length(buf)) {
-		/* we're not the first session */
-		len = get_unaligned_be32(&buf->data[auth->session]);
-		if (4 + len + auth->session != tpm_buf_length(buf)) {
-			WARN(1, "session length mismatch, cannot append");
-			return;
-		}
-
-		/* add our new session */
-		len += 9 + 2 * SHA256_DIGEST_SIZE;
-		put_unaligned_be32(len, &buf->data[auth->session]);
-	} else {
-		tpm_buf_append_u32(buf, 9 + 2 * SHA256_DIGEST_SIZE);
-	}
-
-	/* random number for our nonce */
-	get_random_bytes(nonce, sizeof(nonce));
-	memcpy(auth->our_nonce, nonce, sizeof(nonce));
-	tpm_buf_append_u32(buf, auth->handle);
-	/* our new nonce */
-	tpm_buf_append_u16(buf, SHA256_DIGEST_SIZE);
-	tpm_buf_append(buf, nonce, SHA256_DIGEST_SIZE);
-	tpm_buf_append_u8(buf, auth->attrs);
-	/* and put a placeholder for the hmac */
-	tpm_buf_append_u16(buf, SHA256_DIGEST_SIZE);
-	tpm_buf_append(buf, nonce, SHA256_DIGEST_SIZE);
-}
-EXPORT_SYMBOL(tpm_buf_append_hmac_session);
-
-/**
  * tpm_buf_fill_hmac_session() - finalize the session HMAC
  * @chip: the TPM chip structure
  * @buf: The buffer to be appended
···
 	u32 attrs;
 	u8 cphash[SHA256_DIGEST_SIZE];
 	struct sha256_state sctx;
+
+	if (!auth)
+		return;
 
 	/* save the command code in BE format */
 	auth->ordinal = head->ordinal;
···
 }
 EXPORT_SYMBOL(tpm_buf_fill_hmac_session);
 
-static int tpm2_parse_read_public(char *name, struct tpm_buf *buf)
-{
-	struct tpm_header *head = (struct tpm_header *)buf->data;
-	off_t offset = TPM_HEADER_SIZE;
-	u32 tot_len = be32_to_cpu(head->length);
-	u32 val;
-
-	/* we're starting after the header so adjust the length */
-	tot_len -= TPM_HEADER_SIZE;
-
-	/* skip public */
-	val = tpm_buf_read_u16(buf, &offset);
-	if (val > tot_len)
-		return -EINVAL;
-	offset += val;
-	/* name */
-	val = tpm_buf_read_u16(buf, &offset);
-	if (val != name_size(&buf->data[offset]))
-		return -EINVAL;
-	memcpy(name, &buf->data[offset], val);
-	/* forget the rest */
-	return 0;
-}
-
-static int tpm2_read_public(struct tpm_chip *chip, u32 handle, char *name)
-{
-	struct tpm_buf buf;
-	int rc;
-
-	rc = tpm_buf_init(&buf, TPM2_ST_NO_SESSIONS, TPM2_CC_READ_PUBLIC);
-	if (rc)
-		return rc;
-
-	tpm_buf_append_u32(&buf, handle);
-	rc = tpm_transmit_cmd(chip, &buf, 0, "read public");
-	if (rc == TPM2_RC_SUCCESS)
-		rc = tpm2_parse_read_public(name, &buf);
-
-	tpm_buf_destroy(&buf);
-
-	return rc;
-}
-
-/**
- * tpm_buf_append_name() - add a handle area to the buffer
- * @chip: the TPM chip structure
- * @buf: The buffer to be appended
- * @handle: The handle to be appended
- * @name: The name of the handle (may be NULL)
- *
- * In order to compute session HMACs, we need to know the names of the
- * objects pointed to by the handles.  For most objects, this is simply
- * the actual 4 byte handle or an empty buf (in these cases @name
- * should be NULL) but for volatile objects, permanent objects and NV
- * areas, the name is defined as the hash (according to the name
- * algorithm which should be set to sha256) of the public area to
- * which the two byte algorithm id has been appended.  For these
- * objects, the @name pointer should point to this.  If a name is
- * required but @name is NULL, then TPM2_ReadPublic() will be called
- * on the handle to obtain the name.
- *
- * As with most tpm_buf operations, success is assumed because failure
- * will be caused by an incorrect programming model and indicated by a
- * kernel message.
- */
-void tpm_buf_append_name(struct tpm_chip *chip, struct tpm_buf *buf,
-			 u32 handle, u8 *name)
-{
-	enum tpm2_mso_type mso = tpm2_handle_mso(handle);
-	struct tpm2_auth *auth = chip->auth;
-	int slot;
-
-	slot = (tpm_buf_length(buf) - TPM_HEADER_SIZE)/4;
-	if (slot >= AUTH_MAX_NAMES) {
-		dev_err(&chip->dev, "TPM: too many handles\n");
-		return;
-	}
-	WARN(auth->session != tpm_buf_length(buf),
-	     "name added in wrong place\n");
-	tpm_buf_append_u32(buf, handle);
-	auth->session += 4;
-
-	if (mso == TPM2_MSO_PERSISTENT ||
-	    mso == TPM2_MSO_VOLATILE ||
-	    mso == TPM2_MSO_NVRAM) {
-		if (!name)
-			tpm2_read_public(chip, handle, auth->name[slot]);
-	} else {
-		if (name)
-			dev_err(&chip->dev, "TPM: Handle does not require name but one is specified\n");
-	}
-
-	auth->name_h[slot] = handle;
-	if (name)
-		memcpy(auth->name[slot], name, name_size(name));
-}
-EXPORT_SYMBOL(tpm_buf_append_name);
-
 /**
  * tpm_buf_check_hmac_response() - check the TPM return HMAC for correctness
  * @chip: the TPM chip structure
···
 	u16 tag = be16_to_cpu(head->tag);
 	u32 cc = be32_to_cpu(auth->ordinal);
 	int parm_len, len, i, handles;
+
+	if (!auth)
+		return rc;
 
 	if (auth->session >= TPM_HEADER_SIZE) {
 		WARN(1, "tpm session not filled correctly\n");
···
  */
 void tpm2_end_auth_session(struct tpm_chip *chip)
 {
-	tpm2_flush_context(chip, chip->auth->handle);
-	memzero_explicit(chip->auth, sizeof(*chip->auth));
+	struct tpm2_auth *auth = chip->auth;
+
+	if (!auth)
+		return;
+
+	tpm2_flush_context(chip, auth->handle);
+	memzero_explicit(auth, sizeof(*auth));
 }
 EXPORT_SYMBOL(tpm2_end_auth_session);
 
···
 	struct tpm2_auth *auth = chip->auth;
 	int rc;
 	u32 null_key;
+
+	if (!auth) {
+		dev_warn_once(&chip->dev, "auth session is not active\n");
+		return 0;
+	}
 
 	rc = tpm2_load_null(chip, &null_key);
 	if (rc)
···
 
 	return rc;
 }
+#endif /* CONFIG_TCG_TPM2_HMAC */

drivers/clk/mediatek/clk-mt8183-mfgcfg.c

···
 static const struct mtk_clk_desc mfg_desc = {
 	.clks = mfg_clks,
 	.num_clks = ARRAY_SIZE(mfg_clks),
+	.need_runtime_pm = true,
 };
 
 static const struct of_device_id of_match_clk_mt8183_mfg[] = {

drivers/clk/mediatek/clk-mtk.c

···
 	}
 
 
-	devm_pm_runtime_enable(&pdev->dev);
-	/*
-	 * Do a pm_runtime_resume_and_get() to workaround a possible
-	 * deadlock between clk_register() and the genpd framework.
-	 */
-	r = pm_runtime_resume_and_get(&pdev->dev);
-	if (r)
-		return r;
+	if (mcd->need_runtime_pm) {
+		devm_pm_runtime_enable(&pdev->dev);
+		/*
+		 * Do a pm_runtime_resume_and_get() to workaround a possible
+		 * deadlock between clk_register() and the genpd framework.
+		 */
+		r = pm_runtime_resume_and_get(&pdev->dev);
+		if (r)
+			return r;
+	}
 
 	/* Calculate how many clk_hw_onecell_data entries to allocate */
 	num_clks = mcd->num_clks + mcd->num_composite_clks;
···
 			goto unregister_clks;
 	}
 
-	pm_runtime_put(&pdev->dev);
+	if (mcd->need_runtime_pm)
+		pm_runtime_put(&pdev->dev);
 
 	return r;
 
···
 	if (mcd->shared_io && base)
 		iounmap(base);
 
-	pm_runtime_put(&pdev->dev);
+	if (mcd->need_runtime_pm)
+		pm_runtime_put(&pdev->dev);
 	return r;
 }
 

drivers/clk/mediatek/clk-mtk.h

···
 
 	int (*clk_notifier_func)(struct device *dev, struct clk *clk);
 	unsigned int mfg_clk_idx;
+
+	bool need_runtime_pm;
 };
 
 int mtk_clk_pdev_probe(struct platform_device *pdev);

drivers/clk/qcom/apss-ipq-pll.c

···
 static const struct alpha_pll_config ipq5018_pll_config = {
 	.l = 0x2a,
 	.config_ctl_val = 0x4001075b,
-	.config_ctl_hi_val = 0x304,
 	.main_output_mask = BIT(0),
 	.aux_output_mask = BIT(1),
 	.early_output_mask = BIT(3),
···
 static const struct alpha_pll_config ipq5332_pll_config = {
 	.l = 0x2d,
 	.config_ctl_val = 0x4001075b,
-	.config_ctl_hi_val = 0x304,
 	.main_output_mask = BIT(0),
 	.aux_output_mask = BIT(1),
 	.early_output_mask = BIT(3),

drivers/clk/qcom/clk-alpha-pll.c

···
 	regmap_write(pll->clkr.regmap, PLL_ALPHA_VAL_U(pll),
 					a >> ALPHA_BITWIDTH);
 
+	regmap_update_bits(pll->clkr.regmap, PLL_USER_CTL(pll),
+			   PLL_ALPHA_EN, PLL_ALPHA_EN);
+
 	regmap_write(pll->clkr.regmap, PLL_MODE(pll), PLL_BYPASSNL);
 
 	/* Wait five micro seconds or more */

drivers/clk/qcom/gcc-ipq9574.c

···
 
 static struct clk_branch gcc_crypto_axi_clk = {
 	.halt_reg = 0x16010,
+	.halt_check = BRANCH_HALT_VOTED,
 	.clkr = {
-		.enable_reg = 0x16010,
-		.enable_mask = BIT(0),
+		.enable_reg = 0xb004,
+		.enable_mask = BIT(15),
 		.hw.init = &(const struct clk_init_data) {
 			.name = "gcc_crypto_axi_clk",
 			.parent_hws = (const struct clk_hw *[]) {
···
 
 static struct clk_branch gcc_crypto_ahb_clk = {
 	.halt_reg = 0x16014,
+	.halt_check = BRANCH_HALT_VOTED,
 	.clkr = {
-		.enable_reg = 0x16014,
-		.enable_mask = BIT(0),
+		.enable_reg = 0xb004,
+		.enable_mask = BIT(16),
 		.hw.init = &(const struct clk_init_data) {
 			.name = "gcc_crypto_ahb_clk",
 			.parent_hws = (const struct clk_hw *[]) {

drivers/clk/qcom/gcc-sm6350.c

···
 		.enable_mask = BIT(6),
 		.hw.init = &(struct clk_init_data){
 			.name = "gpll6",
-			.parent_hws = (const struct clk_hw*[]){
-				&gpll0.clkr.hw,
+			.parent_data = &(const struct clk_parent_data){
+				.fw_name = "bi_tcxo",
 			},
 			.num_parents = 1,
 			.ops = &clk_alpha_pll_fixed_fabia_ops,
···
 	.clkr.hw.init = &(struct clk_init_data){
 		.name = "gpll6_out_even",
 		.parent_hws = (const struct clk_hw*[]){
-			&gpll0.clkr.hw,
+			&gpll6.clkr.hw,
 		},
 		.num_parents = 1,
 		.ops = &clk_alpha_pll_postdiv_fabia_ops,
···
 		.enable_mask = BIT(7),
 		.hw.init = &(struct clk_init_data){
 			.name = "gpll7",
-			.parent_hws = (const struct clk_hw*[]){
-				&gpll0.clkr.hw,
+			.parent_data = &(const struct clk_parent_data){
+				.fw_name = "bi_tcxo",
 			},
 			.num_parents = 1,
 			.ops = &clk_alpha_pll_fixed_fabia_ops,

drivers/clk/sunxi-ng/ccu_common.c

···
 
 	for (i = 0; i < desc->hw_clks->num ; i++) {
 		struct clk_hw *hw = desc->hw_clks->hws[i];
-		struct ccu_common *common = hw_to_ccu_common(hw);
 		const char *name;
 
 		if (!hw)
···
 			pr_err("Couldn't register clock %d - %s\n", i, name);
 			goto err_clk_unreg;
 		}
+	}
 
-		if (common->max_rate)
-			clk_hw_set_rate_range(hw, common->min_rate,
-					      common->max_rate);
+	for (i = 0; i < desc->num_ccu_clks; i++) {
+		struct ccu_common *cclk = desc->ccu_clks[i];
+
+		if (!cclk)
+			continue;
+
+		if (cclk->max_rate)
+			clk_hw_set_rate_range(&cclk->hw, cclk->min_rate,
+					      cclk->max_rate);
 		else
-			WARN(common->min_rate,
+			WARN(cclk->min_rate,
 			     "No max_rate, ignoring min_rate of clock %d - %s\n",
-			     i, name);
+			     i, clk_hw_get_name(&cclk->hw));
 	}
 
 	ret = of_clk_add_hw_provider(node, of_clk_hw_onecell_get,

drivers/cpufreq/acpi-cpufreq.c

···
 	if (perf->states[0].core_frequency * 1000 != freq_table[0].frequency)
 		pr_warn(FW_WARN "P-state 0 is not max freq\n");
 
-	if (acpi_cpufreq_driver.set_boost)
+	if (acpi_cpufreq_driver.set_boost) {
 		set_boost(policy, acpi_cpufreq_driver.boost_enabled);
+		policy->boost_enabled = acpi_cpufreq_driver.boost_enabled;
+	}
 
 	return result;
 

drivers/cpufreq/cpufreq.c

···
 		}
 
 		/* Let the per-policy boost flag mirror the cpufreq_driver boost during init */
-		policy->boost_enabled = cpufreq_boost_enabled() && policy_has_boost_freq(policy);
+		if (cpufreq_boost_enabled() && policy_has_boost_freq(policy))
+			policy->boost_enabled = true;
 
 		/*
 		 * The initialization has succeeded and the policy is online.

drivers/firmware/sysfb.c

···
 	if (IS_ERR(pdev)) {
 		return ERR_CAST(pdev);
 	} else if (pdev) {
-		if (!sysfb_pci_dev_is_enabled(pdev))
+		if (!sysfb_pci_dev_is_enabled(pdev)) {
+			pci_dev_put(pdev);
 			return ERR_PTR(-ENODEV);
+		}
 		return &pdev->dev;
 	}
 
···
 	if (compatible) {
 		pd = sysfb_create_simplefb(si, &mode, parent);
 		if (!IS_ERR(pd))
-			goto unlock_mutex;
+			goto put_device;
 	}
 
 	/* if the FB is incompatible, create a legacy framebuffer device */
···
 	pd = platform_device_alloc(name, 0);
 	if (!pd) {
 		ret = -ENOMEM;
-		goto unlock_mutex;
+		goto put_device;
 	}
 
 	pd->dev.parent = parent;
···
 	if (ret)
 		goto err;
 
-	goto unlock_mutex;
+	goto put_device;
 err:
 	platform_device_put(pd);
+put_device:
+	put_device(parent);
 unlock_mutex:
 	mutex_unlock(&disable_lock);
 	return ret;

drivers/gpio/gpio-mmio.c

···
 	ret = gpiochip_get_ngpios(gc, dev);
 	if (ret)
 		gc->ngpio = gc->bgpio_bits;
-	else
-		gc->bgpio_bits = roundup_pow_of_two(round_up(gc->ngpio, 8));
 
 	ret = bgpio_setup_io(gc, dat, set, clr, flags);
 	if (ret)

drivers/gpio/gpiolib-of.c

···
 		 */
 		{ "qi,lb60",		"rb-gpios",	true },
 #endif
+#if IS_ENABLED(CONFIG_PCI_LANTIQ)
+		/*
+		 * According to the PCI specification, the RST# pin is an
+		 * active-low signal. However, most of the device trees that
+		 * have been widely used for a long time incorrectly describe
+		 * reset GPIO as active-high, and were also using wrong name
+		 * for the property.
+		 */
+		{ "lantiq,pci-xway",	"gpio-reset",	false },
+#endif
+#if IS_ENABLED(CONFIG_TOUCHSCREEN_TSC2005)
+		/*
+		 * DTS for Nokia N900 incorrectly specified "active high"
+		 * polarity for the reset line, while the chip actually
+		 * treats it as "active low".
+		 */
+		{ "ti,tsc2005",		"reset-gpios",	false },
+#endif
 	};
 	unsigned int i;
 
···
 		{ "reset",	"reset-n-io",	"marvell,nfc-uart" },
 		{ "reset",	"reset-n-io",	"mrvl,nfc-uart" },
 #endif
-#if !IS_ENABLED(CONFIG_PCI_LANTIQ)
+#if IS_ENABLED(CONFIG_PCI_LANTIQ)
 		/* MIPS Lantiq PCI */
-		{ "reset",	"gpios-reset",	"lantiq,pci-xway" },
+		{ "reset",	"gpio-reset",	"lantiq,pci-xway" },
 #endif
 
 		/*

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

···
 	}
 
 	/* Update Freesync settings. */
+	reset_freesync_config_for_crtc(dm_new_crtc_state);
 	get_freesync_config_for_crtc(dm_new_crtc_state,
 				     dm_new_conn_state);
 
···
 	return ret;
 }
 
+static void parse_edid_displayid_vrr(struct drm_connector *connector,
+		struct edid *edid)
+{
+	u8 *edid_ext = NULL;
+	int i;
+	int j = 0;
+	u16 min_vfreq;
+	u16 max_vfreq;
+
+	if (edid == NULL || edid->extensions == 0)
+		return;
+
+	/* Find DisplayID extension */
+	for (i = 0; i < edid->extensions; i++) {
+		edid_ext = (void *)(edid + (i + 1));
+		if (edid_ext[0] == DISPLAYID_EXT)
+			break;
+	}
+
+	if (edid_ext == NULL)
+		return;
+
+	while (j < EDID_LENGTH) {
+		/* Get dynamic video timing range from DisplayID if available */
+		if (EDID_LENGTH - j > 13 && edid_ext[j] == 0x25	&&
+		    (edid_ext[j+1] & 0xFE) == 0 && (edid_ext[j+2] == 9)) {
+			min_vfreq = edid_ext[j+9];
+			if (edid_ext[j+1] & 7)
+				max_vfreq = edid_ext[j+10] + ((edid_ext[j+11] & 3) << 8);
+			else
+				max_vfreq = edid_ext[j+10];
+
+			if (max_vfreq && min_vfreq) {
+				connector->display_info.monitor_range.max_vfreq = max_vfreq;
+				connector->display_info.monitor_range.min_vfreq = min_vfreq;
+
+				return;
+			}
+		}
+		j++;
+	}
+}
+
 static int parse_amd_vsdb(struct amdgpu_dm_connector *aconnector,
 			  struct edid *edid, struct amdgpu_hdmi_vsdb_info *vsdb_info)
 {
···
 	if (!adev->dm.freesync_module)
 		goto update;
 
+	/* Some eDP panels only have the refresh rate range info in DisplayID */
+	if ((connector->display_info.monitor_range.min_vfreq == 0 ||
+	     connector->display_info.monitor_range.max_vfreq == 0))
+		parse_edid_displayid_vrr(connector, edid);
+
 	if (edid && (sink->sink_signal == SIGNAL_TYPE_DISPLAY_PORT ||
 		     sink->sink_signal == SIGNAL_TYPE_EDP)) {
 		bool edid_check_required = false;
···
 		if (is_dp_capable_without_timing_msa(adev->dm.dc,
 						     amdgpu_dm_connector)) {
 			if (edid->features & DRM_EDID_FEATURE_CONTINUOUS_FREQ) {
-				freesync_capable = true;
 				amdgpu_dm_connector->min_vfreq = connector->display_info.monitor_range.min_vfreq;
 				amdgpu_dm_connector->max_vfreq = connector->display_info.monitor_range.max_vfreq;
+				if (amdgpu_dm_connector->max_vfreq -
+				    amdgpu_dm_connector->min_vfreq > 10)
+					freesync_capable = true;
 			} else {
 				edid_check_required = edid->version > 1 ||
 						      (edid->version == 1 &&

drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.c

···
 							&mode_lib->vba.UrgentBurstFactorLumaPre[k],
 							&mode_lib->vba.UrgentBurstFactorChromaPre[k],
 							&mode_lib->vba.NotUrgentLatencyHidingPre[k]);
+
+					v->cursor_bw_pre[k] = mode_lib->vba.NumberOfCursors[k] * mode_lib->vba.CursorWidth[k][0] * mode_lib->vba.CursorBPP[k][0] /
+							8.0 / (mode_lib->vba.HTotal[k] / mode_lib->vba.PixelClock[k]) * v->VRatioPreY[i][j][k];
 				}
 
 				{

drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c

···
 		out->round_trip_ping_latency_dcfclk_cycles = 106;
 		out->smn_latency_us = 2;
 		out->dispclk_dppclk_vco_speed_mhz = 3600;
+		out->pct_ideal_dram_bw_after_urgent_pixel_only = 65.0;
 		break;
 
 	}

drivers/gpu/drm/amd/display/dc/dml2/dml2_utils.c

···
 	context->bw_ctx.bw.dcn.clk.dcfclk_deep_sleep_khz = (unsigned int)in_ctx->v20.dml_core_ctx.mp.DCFCLKDeepSleep * 1000;
 	context->bw_ctx.bw.dcn.clk.dppclk_khz = 0;
 
-	if (in_ctx->v20.dml_core_ctx.ms.support.FCLKChangeSupport[in_ctx->v20.scratch.mode_support_params.out_lowest_state_idx] == dml_fclock_change_unsupported)
+	if (in_ctx->v20.dml_core_ctx.ms.support.FCLKChangeSupport[0] == dml_fclock_change_unsupported)
 		context->bw_ctx.bw.dcn.clk.fclk_p_state_change_support = false;
 	else
 		context->bw_ctx.bw.dcn.clk.fclk_p_state_change_support = true;

drivers/gpu/drm/amd/include/atomfirmware.h

···
 {
   struct  atom_common_table_header  table_header;
   /*the real number of this included in the structure is calcualted by using the (whole structure size - the header size)/size of atom_gpio_pin_lut  */
-  struct  atom_gpio_pin_assignment  gpio_pin[8];
+  struct  atom_gpio_pin_assignment  gpio_pin[];
 };
 
 

drivers/gpu/drm/drm_fbdev_generic.c

···
 		    sizes->surface_width, sizes->surface_height,
 		    sizes->surface_bpp);
 
-	format = drm_mode_legacy_fb_format(sizes->surface_bpp, sizes->surface_depth);
+	format = drm_driver_legacy_fb_format(dev, sizes->surface_bpp,
+					     sizes->surface_depth);
 	buffer = drm_client_framebuffer_create(client, sizes->surface_width,
 					       sizes->surface_height, format);
 	if (IS_ERR(buffer))

drivers/gpu/drm/drm_panel_orientation_quirks.c

···
 		  DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "Galaxy Book 10.6"),
 		},
 		.driver_data = (void *)&lcd1280x1920_rightside_up,
-	}, {	/* Valve Steam Deck */
+	}, {	/* Valve Steam Deck (Jupiter) */
 		.matches = {
 		  DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Valve"),
 		  DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "Jupiter"),
+		  DMI_EXACT_MATCH(DMI_PRODUCT_VERSION, "1"),
+		},
+		.driver_data = (void *)&lcd800x1280_rightside_up,
+	}, {	/* Valve Steam Deck (Galileo) */
+		.matches = {
+		  DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Valve"),
+		  DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "Galileo"),
 		  DMI_EXACT_MATCH(DMI_PRODUCT_VERSION, "1"),
 		},
 		.driver_data = (void *)&lcd800x1280_rightside_up,

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

···
 	u32 ln0, ln1, pin_assignment;
 	u8 width;
 
+	if (DISPLAY_VER(dev_priv) >= 14)
+		return;
+
 	if (!intel_encoder_is_tc(&dig_port->base) ||
 	    intel_tc_port_in_tbt_alt_mode(dig_port))
 		return;

drivers/gpu/drm/nouveau/nouveau_connector.c

···
 		struct drm_display_mode *mode;
 
 		mode = drm_mode_duplicate(dev, nv_connector->native_mode);
+		if (!mode)
+			return 0;
+
 		drm_mode_probed_add(connector, mode);
 		ret = 1;
 	}

drivers/gpu/drm/panthor/panthor_drv.c

···
 	int ret = 0;
 	void *out_alloc;
 
+	if (!in->count)
+		return NULL;
+
 	/* User stride must be at least the minimum object size, otherwise it might
 	 * lack useful information.
 	 */
 	if (in->stride < min_stride)
 		return ERR_PTR(-EINVAL);
-
-	if (!in->count)
-		return NULL;
 
 	out_alloc = kvmalloc_array(in->count, obj_size, GFP_KERNEL);
 	if (!out_alloc)

drivers/gpu/drm/panthor/panthor_sched.c

···
 		atomic64_t seqno;
 
 		/**
+		 * @last_fence: Fence of the last submitted job.
+		 *
+		 * We return this fence when we get an empty command stream.
+		 * This way, we are guaranteed that all earlier jobs have completed
+		 * when drm_sched_job::s_fence::finished without having to feed
+		 * the CS ring buffer with a dummy job that only signals the fence.
+		 */
+		struct dma_fence *last_fence;
+
+		/**
 		 * @in_flight_jobs: List containing all in-flight jobs.
 		 *
 		 * Used to keep track and signal panthor_job::done_fence when the
···
 
 	panthor_kernel_bo_destroy(queue->ringbuf);
 	panthor_kernel_bo_destroy(queue->iface.mem);
+
+	/* Release the last_fence we were holding, if any. */
+	dma_fence_put(queue->fence_ctx.last_fence);
 
 	kfree(queue);
 }
···
 
 		spin_lock(&queue->fence_ctx.lock);
 		list_for_each_entry_safe(job, job_tmp, &queue->fence_ctx.in_flight_jobs, node) {
-			if (!job->call_info.size)
-				continue;
-
 			if (syncobj->seqno < job->done_fence->seqno)
 				break;
 
···
 	static_assert(sizeof(call_instrs) % 64 == 0,
 		      "call_instrs is not aligned on a cacheline");
 
-	/* Stream size is zero, nothing to do => return a NULL fence and let
-	 * drm_sched signal the parent.
+	/* Stream size is zero, nothing to do except making sure all previously
+	 * submitted jobs are done before we signal the
+	 * drm_sched_job::s_fence::finished fence.
 	 */
-	if (!job->call_info.size)
-		return NULL;
+	if (!job->call_info.size) {
+		job->done_fence = dma_fence_get(queue->fence_ctx.last_fence);
+		return dma_fence_get(job->done_fence);
+	}
 
 	ret = pm_runtime_resume_and_get(ptdev->base.dev);
 	if (drm_WARN_ON(&ptdev->base, ret))
···
 			sched->pm.has_ref = true;
 		}
 	}
+
+	/* Update the last fence. */
+	dma_fence_put(queue->fence_ctx.last_fence);
+	queue->fence_ctx.last_fence = dma_fence_get(job->done_fence);
 
 	done_fence = dma_fence_get(job->done_fence);
 
···
 		goto err_put_job;
 	}
 
-	job->done_fence = kzalloc(sizeof(*job->done_fence), GFP_KERNEL);
-	if (!job->done_fence) {
-		ret = -ENOMEM;
-		goto err_put_job;
+	/* Empty command streams don't need a fence, they'll pick the one from
+	 * the previously submitted job.
+	 */
+	if (job->call_info.size) {
+		job->done_fence = kzalloc(sizeof(*job->done_fence), GFP_KERNEL);
+		if (!job->done_fence) {
+			ret = -ENOMEM;
+			goto err_put_job;
+		}
 	}
 
 	ret = drm_sched_job_init(&job->base,

drivers/gpu/drm/radeon/radeon_gem.c

···
 	if (r)
 		goto error_unlock;
 
-	if (bo_va->it.start)
+	if (bo_va->it.start && bo_va->bo)
 		r = radeon_vm_bo_update(rdev, bo_va, bo_va->bo->tbo.resource);
 
 error_unlock:

drivers/gpu/drm/ttm/ttm_bo.c

···
 		if (!dma_resv_test_signaled(bo->base.resv,
 					    DMA_RESV_USAGE_BOOKKEEP) ||
 		    (want_init_on_free() && (bo->ttm != NULL)) ||
+		    bo->type == ttm_bo_type_sg ||
 		    !dma_resv_trylock(bo->base.resv)) {
 			/* The BO is not idle, resurrect it for delayed destroy */
 			ttm_bo_flush_all_fences(bo);

drivers/gpu/drm/xe/xe_gt_mcr.c

···
 	else
 		gt->steering[OADDRM].group_target = 1;
 
-	gt->steering[DSS].instance_target = 0;		/* unused */
+	gt->steering[OADDRM].instance_target = 0;	/* unused */
 }
 
 static void init_steering_sqidi_psmi(struct xe_gt *gt)
···
 
 static void init_steering_inst0(struct xe_gt *gt)
 {
-	gt->steering[DSS].group_target = 0;		/* unused */
-	gt->steering[DSS].instance_target = 0;		/* unused */
+	gt->steering[INSTANCE0].group_target = 0;	/* unused */
+	gt->steering[INSTANCE0].instance_target = 0;	/* unused */
 }
 
 static const struct {

drivers/gpu/drm/xe/xe_migrate.c

···
 						 GFP_KERNEL, true, 0);
 			if (IS_ERR(sa_bo)) {
 				err = PTR_ERR(sa_bo);
-				goto err;
+				goto err_bb;
 			}
 
 			ppgtt_ofs = NUM_KERNEL_PDE +
···
 					 update_idx);
 	if (IS_ERR(job)) {
 		err = PTR_ERR(job);
-		goto err_bb;
+		goto err_sa;
 	}
 
 	/* Wait on BO move */
···
 
 err_job:
 	xe_sched_job_put(job);
+err_sa:
+	drm_suballoc_free(sa_bo, NULL);
 err_bb:
 	if (!q)
 		mutex_unlock(&m->job_mutex);
 	xe_bb_free(bb, NULL);
-err:
-	drm_suballoc_free(sa_bo, NULL);
 	return ERR_PTR(err);
 }
 

drivers/i2c/busses/i2c-pnx.c

···
 #include <linux/ioport.h>
 #include <linux/delay.h>
 #include <linux/i2c.h>
-#include <linux/timer.h>
 #include <linux/completion.h>
 #include <linux/platform_device.h>
 #include <linux/io.h>
···
 	int			ret;		/* Return value */
 	int			mode;		/* Interface mode */
 	struct completion	complete;	/* I/O completion */
-	struct timer_list	timer;		/* Timeout */
 	u8 *			buf;		/* Data buffer */
 	int			len;		/* Length of data buffer */
 	int			order;		/* RX Bytes to order via TX */
···
 		timeout--;
 	}
 	return (timeout <= 0);
-}
-
-static inline void i2c_pnx_arm_timer(struct i2c_pnx_algo_data *alg_data)
-{
-	struct timer_list *timer = &alg_data->mif.timer;
-	unsigned long expires = msecs_to_jiffies(alg_data->timeout);
-
-	if (expires <= 1)
-		expires = 2;
-
-	del_timer_sync(timer);
-
-	dev_dbg(&alg_data->adapter.dev, "Timer armed at %lu plus %lu jiffies.\n",
-		jiffies, expires);
-
-	timer->expires = jiffies + expires;
-
-	add_timer(timer);
 }
 
 /**
···
 				~(mcntrl_afie | mcntrl_naie | mcntrl_drmie),
 				  I2C_REG_CTL(alg_data));
 
-			del_timer_sync(&alg_data->mif.timer);
-
 			dev_dbg(&alg_data->adapter.dev,
 				"%s(): Waking up xfer routine.\n",
 				__func__);
···
 			~(mcntrl_afie | mcntrl_naie | mcntrl_drmie),
 			  I2C_REG_CTL(alg_data));
 
-		/* Stop timer. */
-		del_timer_sync(&alg_data->mif.timer);
 		dev_dbg(&alg_data->adapter.dev,
 			"%s(): Waking up xfer routine after zero-xfer.\n",
 			__func__);
···
 				 mcntrl_drmie | mcntrl_daie);
 			iowrite32(ctl, I2C_REG_CTL(alg_data));
 
-			/* Kill timer. */
-			del_timer_sync(&alg_data->mif.timer);
 			complete(&alg_data->mif.complete);
 		}
 	}
···
 			 mcntrl_drmie);
 		iowrite32(ctl, I2C_REG_CTL(alg_data));
 
-		/* Stop timer, to prevent timeout. */
-		del_timer_sync(&alg_data->mif.timer);
 		complete(&alg_data->mif.complete);
 	} else if (stat & mstatus_nai) {
 		/* Slave did not acknowledge, generate a STOP */
···
 		/* Our return value. */
 		alg_data->mif.ret = -EIO;
 
-		/* Stop timer, to prevent timeout. */
-		del_timer_sync(&alg_data->mif.timer);
 		complete(&alg_data->mif.complete);
 	} else {
 		/*
···
 	return IRQ_HANDLED;
 }
 
-static void i2c_pnx_timeout(struct timer_list *t)
+static void i2c_pnx_timeout(struct i2c_pnx_algo_data *alg_data)
 {
-	struct i2c_pnx_algo_data *alg_data = from_timer(alg_data, t, mif.timer);
 	u32 ctl;
 
 	dev_err(&alg_data->adapter.dev,
···
 	iowrite32(ctl, I2C_REG_CTL(alg_data));
 	wait_reset(alg_data);
 	alg_data->mif.ret = -EIO;
-	complete(&alg_data->mif.complete);
 }
 
 static inline void bus_reset_if_active(struct i2c_pnx_algo_data *alg_data)
···
 	struct i2c_msg *pmsg;
 	int rc = 0, completed = 0, i;
 	struct i2c_pnx_algo_data *alg_data = adap->algo_data;
+	unsigned long time_left;
 	u32 stat;
 
 	dev_dbg(&alg_data->adapter.dev,
···
 		dev_dbg(&alg_data->adapter.dev, "%s(): mode %d, %d bytes\n",
 			__func__, alg_data->mif.mode, alg_data->mif.len);
 
-		i2c_pnx_arm_timer(alg_data);
 
 		/* initialize the completion var */
 		init_completion(&alg_data->mif.complete);
···
 			break;
 
 		/* Wait for completion */
-		wait_for_completion(&alg_data->mif.complete);
+		time_left = wait_for_completion_timeout(&alg_data->mif.complete,
+							alg_data->timeout);
+		if (time_left == 0)
+			i2c_pnx_timeout(alg_data);
 
 		if (!(rc = alg_data->mif.ret))
 			completed++;
···
 	alg_data->adapter.algo_data = alg_data;
 	alg_data->adapter.nr = pdev->id;
 
-	alg_data->timeout = I2C_PNX_TIMEOUT_DEFAULT;
+	alg_data->timeout = msecs_to_jiffies(I2C_PNX_TIMEOUT_DEFAULT);
+	if (alg_data->timeout <= 1)
+		alg_data->timeout = 2;
+
 #ifdef CONFIG_OF
 	alg_data->adapter.dev.of_node = of_node_get(pdev->dev.of_node);
 	if (pdev->dev.of_node) {
···
 	alg_data->clk = devm_clk_get(&pdev->dev, NULL);
 	if (IS_ERR(alg_data->clk))
 		return PTR_ERR(alg_data->clk);
-
-	timer_setup(&alg_data->mif.timer, i2c_pnx_timeout, 0);
 
 	snprintf(alg_data->adapter.name, sizeof(alg_data->adapter.name),
 		 "%s", pdev->name);

drivers/net/dsa/lan9303-core.c

···
 	return ARRAY_SIZE(lan9303_mib);
 }
 
-static int lan9303_phy_read(struct dsa_switch *ds, int phy, int regnum)
+static int lan9303_phy_read(struct dsa_switch *ds, int port, int regnum)
 {
 	struct lan9303 *chip = ds->priv;
 	int phy_base = chip->phy_addr_base;
 
-	if (phy == phy_base)
+	if (port == 0)
 		return lan9303_virt_phy_reg_read(chip, regnum);
-	if (phy > phy_base + 2)
+	if (port > 2)
 		return -ENODEV;
 
-	return chip->ops->phy_read(chip, phy, regnum);
+	return chip->ops->phy_read(chip, phy_base + port, regnum);
 }
 
-static int lan9303_phy_write(struct dsa_switch *ds, int phy, int regnum,
+static int lan9303_phy_write(struct dsa_switch *ds, int port, int regnum,
 			     u16 val)
 {
 	struct lan9303 *chip = ds->priv;
 	int phy_base = chip->phy_addr_base;
 
-	if (phy == phy_base)
+	if (port == 0)
 		return lan9303_virt_phy_reg_write(chip, regnum, val);
-	if (phy > phy_base + 2)
+	if (port > 2)
 		return -ENODEV;
 
-	return chip->ops->phy_write(chip, phy, regnum, val);
+	return chip->ops->phy_write(chip, phy_base + port, regnum, val);
 }
 
 static int lan9303_port_enable(struct dsa_switch *ds, int port,
···
 	vlan_vid_del(dsa_port_to_conduit(dp), htons(ETH_P_8021Q), port);
 
 	lan9303_disable_processing_port(chip, port);
-	lan9303_phy_write(ds, chip->phy_addr_base + port, MII_BMCR, BMCR_PDOWN);
+	lan9303_phy_write(ds, port, MII_BMCR, BMCR_PDOWN);
 }
 
 static int lan9303_port_bridge_join(struct dsa_switch *ds, int port,
···
 
 static int lan9303_register_switch(struct lan9303 *chip)
 {
-	int base;
-
 	chip->ds = devm_kzalloc(chip->dev, sizeof(*chip->ds), GFP_KERNEL);
 	if (!chip->ds)
 		return -ENOMEM;
···
 	chip->ds->priv = chip;
 	chip->ds->ops = &lan9303_switch_ops;
 	chip->ds->phylink_mac_ops = &lan9303_phylink_mac_ops;
-	base = chip->phy_addr_base;
-	chip->ds->phys_mii_mask = GENMASK(LAN9303_NUM_PORTS - 1 + base, base);
+	chip->ds->phys_mii_mask = GENMASK(LAN9303_NUM_PORTS - 1, 0);
 
 	return dsa_register_switch(chip->ds);
 }

drivers/net/ethernet/broadcom/asp2/bcmasp.c

···
 			dev_err(dev, "Cannot create eth interface %d\n", i);
 			bcmasp_remove_intfs(priv);
 			of_node_put(intf_node);
+			ret = -ENOMEM;
 			goto of_put_exit;
 		}
 		list_add_tail(&intf->list, &priv->intfs);

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

···
 	return max_ring;
 }
 
+u16 bnxt_get_max_rss_ctx_ring(struct bnxt *bp)
+{
+	u16 i, tbl_size, max_ring = 0;
+	struct bnxt_rss_ctx *rss_ctx;
+
+	tbl_size = bnxt_get_rxfh_indir_size(bp->dev);
+
+	list_for_each_entry(rss_ctx, &bp->rss_ctx_list, list) {
+		for (i = 0; i < tbl_size; i++)
+			max_ring = max(max_ring, rss_ctx->rss_indir_tbl[i]);
+	}
+
+	return max_ring;
+}
+
 int bnxt_get_nr_rss_ctxs(struct bnxt *bp, int rx_rings)
 {
 	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) {

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

···
 void bnxt_fill_ipv6_mask(__be32 mask[4]);
 int bnxt_alloc_rss_indir_tbl(struct bnxt *bp, struct bnxt_rss_ctx *rss_ctx);
 void bnxt_set_dflt_rss_indir_tbl(struct bnxt *bp, struct bnxt_rss_ctx *rss_ctx);
+u16 bnxt_get_max_rss_ctx_ring(struct bnxt *bp);
 int bnxt_get_nr_rss_ctxs(struct bnxt *bp, int rx_rings);
 int bnxt_hwrm_vnic_cfg(struct bnxt *bp, struct bnxt_vnic_info *vnic);
 int bnxt_hwrm_vnic_alloc(struct bnxt *bp, struct bnxt_vnic_info *vnic,

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

···
 		return rc;
 	}
 
+	if (req_rx_rings < bp->rx_nr_rings &&
+	    req_rx_rings <= bnxt_get_max_rss_ctx_ring(bp)) {
+		netdev_warn(dev, "Can't deactivate rings used by RSS contexts\n");
+		return -EINVAL;
+	}
+
 	if (bnxt_get_nr_rss_ctxs(bp, req_rx_rings) !=
 	    bnxt_get_nr_rss_ctxs(bp, bp->rx_nr_rings) &&
 	    netif_is_rxfh_configured(dev)) {

drivers/net/ethernet/intel/e1000e/ich8lan.c

···
 }
 
 /**
+ *  e1000e_force_smbus - Force interfaces to transition to SMBUS mode.
+ *  @hw: pointer to the HW structure
+ *
+ *  Force the MAC and the PHY to SMBUS mode. Assumes semaphore already
+ *  acquired.
+ *
+ * Return: 0 on success, negative errno on failure.
+ **/
+static s32 e1000e_force_smbus(struct e1000_hw *hw)
+{
+	u16 smb_ctrl = 0;
+	u32 ctrl_ext;
+	s32 ret_val;
+
+	/* Switching PHY interface always returns MDI error
+	 * so disable retry mechanism to avoid wasting time
+	 */
+	e1000e_disable_phy_retry(hw);
+
+	/* Force SMBus mode in the PHY */
+	ret_val = e1000_read_phy_reg_hv_locked(hw, CV_SMB_CTRL, &smb_ctrl);
+	if (ret_val) {
+		e1000e_enable_phy_retry(hw);
+		return ret_val;
+	}
+
+	smb_ctrl |= CV_SMB_CTRL_FORCE_SMBUS;
+	e1000_write_phy_reg_hv_locked(hw, CV_SMB_CTRL, smb_ctrl);
+
+	e1000e_enable_phy_retry(hw);
+
+	/* Force SMBus mode in the MAC */
+	ctrl_ext = er32(CTRL_EXT);
+	ctrl_ext |= E1000_CTRL_EXT_FORCE_SMBUS;
+	ew32(CTRL_EXT, ctrl_ext);
+
+	return 0;
+}
+
+/**
  *  e1000_enable_ulp_lpt_lp - configure Ultra Low Power mode for LynxPoint-LP
  *  @hw: pointer to the HW structure
  *  @to_sx: boolean indicating a system power state transition to Sx
···
 	ret_val = hw->phy.ops.acquire(hw);
 	if (ret_val)
 		goto out;
+
+	if (hw->mac.type != e1000_pch_mtp) {
+		ret_val = e1000e_force_smbus(hw);
+		if (ret_val) {
+			e_dbg("Failed to force SMBUS: %d\n", ret_val);
+			goto release;
+		}
+	}
 
 	/* Si workaround for ULP entry flow on i127/rev6 h/w.  Enable
 	 * LPLU and disable Gig speed when entering ULP
···
 	}
 
 release:
-	/* Switching PHY interface always returns MDI error
-	 * so disable retry mechanism to avoid wasting time
-	 */
-	e1000e_disable_phy_retry(hw);
-
-	/* Force SMBus mode in PHY */
-	ret_val = e1000_read_phy_reg_hv_locked(hw, CV_SMB_CTRL, &phy_reg);
-	if (ret_val) {
-		e1000e_enable_phy_retry(hw);
-		hw->phy.ops.release(hw);
-		goto out;
+	if (hw->mac.type == e1000_pch_mtp) {
+		ret_val = e1000e_force_smbus(hw);
+		if (ret_val)
+			e_dbg("Failed to force SMBUS over MTL system: %d\n",
+			      ret_val);
 	}
-	phy_reg |= CV_SMB_CTRL_FORCE_SMBUS;
-	e1000_write_phy_reg_hv_locked(hw, CV_SMB_CTRL, phy_reg);
-
-	e1000e_enable_phy_retry(hw);
-
-	/* Force SMBus mode in MAC */
-	mac_reg = er32(CTRL_EXT);
-	mac_reg |= E1000_CTRL_EXT_FORCE_SMBUS;
-	ew32(CTRL_EXT, mac_reg);
 
 	hw->phy.ops.release(hw);
 out:

drivers/net/ethernet/intel/i40e/i40e_main.c

···
 	bool need_reset;
 	int i;
 
+	/* VSI shall be deleted in a moment, block loading new programs */
+	if (prog && test_bit(__I40E_IN_REMOVE, pf->state))
+		return -EINVAL;
+
 	/* Don't allow frames that span over multiple buffers */
 	if (vsi->netdev->mtu > frame_size - I40E_PACKET_HDR_PAD) {
 		NL_SET_ERR_MSG_MOD(extack, "MTU too large for linear frames and XDP prog does not support frags");
···
 
 	/* When turning XDP on->off/off->on we reset and rebuild the rings. */
 	need_reset = (i40e_enabled_xdp_vsi(vsi) != !!prog);
-
 	if (need_reset)
 		i40e_prep_for_reset(pf);
-
-	/* VSI shall be deleted in a moment, just return EINVAL */
-	if (test_bit(__I40E_IN_REMOVE, pf->state))
-		return -EINVAL;
 
 	old_prog = xchg(&vsi->xdp_prog, prog);
 

drivers/net/ethernet/lantiq_etop.c

···
 	if (ch->dma.irq)
 		free_irq(ch->dma.irq, priv);
 	if (IS_RX(ch->idx)) {
-		int desc;
+		struct ltq_dma_channel *dma = &ch->dma;
 
-		for (desc = 0; desc < LTQ_DESC_NUM; desc++)
+		for (dma->desc = 0; dma->desc < LTQ_DESC_NUM; dma->desc++)
 			dev_kfree_skb_any(ch->skb[ch->dma.desc]);
 	}
 }

drivers/net/ethernet/marvell/octeontx2/af/rvu.c

···
 		if (req->ssow > block->lf.max) {
 			dev_err(&rvu->pdev->dev,
 				"Func 0x%x: Invalid SSOW req, %d > max %d\n",
-				 pcifunc, req->sso, block->lf.max);
+				 pcifunc, req->ssow, block->lf.max);
 			return -EINVAL;
 		}
 		mappedlfs = rvu_get_rsrc_mapcount(pfvf, block->addr);

drivers/net/ethernet/mediatek/mtk_star_emac.c

···
 {
 	struct device_node *of_node;
 	struct mtk_star_priv *priv;
+	struct phy_device *phydev;
 	struct net_device *ndev;
 	struct device *dev;
 	void __iomem *base;
···
 
 	netif_napi_add(ndev, &priv->rx_napi, mtk_star_rx_poll);
 	netif_napi_add_tx(ndev, &priv->tx_napi, mtk_star_tx_poll);
+
+	phydev = of_phy_find_device(priv->phy_node);
+	if (phydev) {
+		phydev->mac_managed_pm = true;
+		put_device(&phydev->mdio.dev);
+	}
 
 	return devm_register_netdev(dev, ndev);
 }

drivers/net/ethernet/micrel/ks8851_common.c

···
 		netif_dbg(ks, intr, ks->netdev,
 			  "%s: txspace %d\n", __func__, tx_space);
 
-		spin_lock(&ks->statelock);
+		spin_lock_bh(&ks->statelock);
 		ks->tx_space = tx_space;
 		if (netif_queue_stopped(ks->netdev))
 			netif_wake_queue(ks->netdev);
-		spin_unlock(&ks->statelock);
+		spin_unlock_bh(&ks->statelock);
 	}
 
 	if (status & IRQ_SPIBEI) {
···
 	ks8851_wrreg16(ks, KS_IER, ks->rc_ier);
 
 	ks->queued_len = 0;
+	ks->tx_space = ks8851_rdreg16(ks, KS_TXMIR);
 	netif_start_queue(ks->netdev);
 
 	netif_dbg(ks, ifup, ks->netdev, "network device up\n");
···
 
 	/* schedule work to do the actual set of the data if needed */
 
-	spin_lock(&ks->statelock);
+	spin_lock_bh(&ks->statelock);
 
 	if (memcmp(&rxctrl, &ks->rxctrl, sizeof(rxctrl)) != 0) {
 		memcpy(&ks->rxctrl, &rxctrl, sizeof(ks->rxctrl));
 		schedule_work(&ks->rxctrl_work);
 	}
 
-	spin_unlock(&ks->statelock);
+	spin_unlock_bh(&ks->statelock);
 }
 
 static int ks8851_set_mac_address(struct net_device *dev, void *addr)
···
 	int ret;
 
 	ks->netdev = netdev;
-	ks->tx_space = 6144;
 
 	ks->gpio = devm_gpiod_get_optional(dev, "reset", GPIOD_OUT_HIGH);
 	ret = PTR_ERR_OR_ZERO(ks->gpio);

drivers/net/ethernet/micrel/ks8851_spi.c

···
 
 	tx_space = ks8851_rdreg16_spi(ks, KS_TXMIR);
 
-	spin_lock(&ks->statelock);
+	spin_lock_bh(&ks->statelock);
 	ks->queued_len -= dequeued_len;
 	ks->tx_space = tx_space;
-	spin_unlock(&ks->statelock);
+	spin_unlock_bh(&ks->statelock);
 
 	ks8851_unlock_spi(ks, &flags);
 }

drivers/net/phy/microchip_t1.c

···
 	ethnl_cable_test_result(phydev, ETHTOOL_A_CABLE_PAIR_A,
 				lan87xx_cable_test_report_trans(detect));
 
-	return 0;
+	return phy_init_hw(phydev);
 }
 
 static int lan87xx_cable_test_get_status(struct phy_device *phydev,

drivers/net/ppp/ppp_generic.c

···
 #define MPHDRLEN_SSN	4	/* ditto with short sequence numbers */
 
 #define PPP_PROTO_LEN	2
+#define PPP_LCP_HDRLEN	4
 
 /*
  * An instance of /dev/ppp can be associated with either a ppp
···
 	return ret;
 }
 
+static bool ppp_check_packet(struct sk_buff *skb, size_t count)
+{
+	/* LCP packets must include LCP header which 4 bytes long:
+	 * 1-byte code, 1-byte identifier, and 2-byte length.
+	 */
+	return get_unaligned_be16(skb->data) != PPP_LCP ||
+		count >= PPP_PROTO_LEN + PPP_LCP_HDRLEN;
+}
+
 static ssize_t ppp_write(struct file *file, const char __user *buf,
 			 size_t count, loff_t *ppos)
 {
···
 	skb_reserve(skb, pf->hdrlen);
 	ret = -EFAULT;
 	if (copy_from_user(skb_put(skb, count), buf, count)) {
+		kfree_skb(skb);
+		goto out;
+	}
+	ret = -EINVAL;
+	if (unlikely(!ppp_check_packet(skb, count))) {
 		kfree_skb(skb);
 		goto out;
 	}

drivers/net/wireguard/allowedips.c

···
 	if (bits == 32) {
 		*(u32 *)dst = be32_to_cpu(*(const __be32 *)src);
 	} else if (bits == 128) {
-		((u64 *)dst)[0] = be64_to_cpu(((const __be64 *)src)[0]);
-		((u64 *)dst)[1] = be64_to_cpu(((const __be64 *)src)[1]);
+		((u64 *)dst)[0] = get_unaligned_be64(src);
+		((u64 *)dst)[1] = get_unaligned_be64(src + 8);
 	}
 }
 

drivers/net/wireguard/queueing.h

···
  */
 static inline int wg_cpumask_next_online(int *last_cpu)
 {
-	int cpu = cpumask_next(*last_cpu, cpu_online_mask);
+	int cpu = cpumask_next(READ_ONCE(*last_cpu), cpu_online_mask);
 	if (cpu >= nr_cpu_ids)
 		cpu = cpumask_first(cpu_online_mask);
-	*last_cpu = cpu;
+	WRITE_ONCE(*last_cpu, cpu);
 	return cpu;
 }
 

drivers/net/wireguard/send.c

···
 {
 	struct sk_buff *skb;
 
-	if (skb_queue_empty(&peer->staged_packet_queue)) {
+	if (skb_queue_empty_lockless(&peer->staged_packet_queue)) {
 		skb = alloc_skb(DATA_PACKET_HEAD_ROOM + MESSAGE_MINIMUM_LENGTH,
 				GFP_ATOMIC);
 		if (unlikely(!skb))

drivers/of/irq.c

···
 /*
  * These interrupt controllers abuse interrupt-map for unspeakable
  * reasons and rely on the core code to *ignore* it (the drivers do
- * their own parsing of the property).
+ * their own parsing of the property). The PAsemi entry covers a
+ * non-sensical interrupt-map that is better left ignored.
  *
  * If you think of adding to the list for something *new*, think
  * again. There is a high chance that you will be sent back to the
···
 	"fsl,ls1043a-extirq",
 	"fsl,ls1088a-extirq",
 	"renesas,rza1-irqc",
+	"pasemi,rootbus",
 	NULL,
 };
 
···
 			imaplen -= imap - oldimap;
 			pr_debug(" -> imaplen=%d\n", imaplen);
 		}
-		if (!match) {
-			if (intc) {
-				/*
-				 * The PASEMI Nemo is a known offender, so
-				 * let's only warn for anyone else.
-				 */
-				WARN(!IS_ENABLED(CONFIG_PPC_PASEMI),
-				     "%pOF interrupt-map failed, using interrupt-controller\n",
-				     ipar);
-				return 0;
-			}
-
+		if (!match)
 			goto fail;
-		}
 
 		/*
 		 * Successfully parsed an interrupt-map translation; copy new

drivers/perf/riscv_pmu.c

···
 	unsigned long cmask;
 	u64 oldval, delta;
 
-	if (!rvpmu->ctr_read)
+	if (!rvpmu->ctr_read || (hwc->state & PERF_HES_UPTODATE))
 		return 0;
 
 	cmask = riscv_pmu_ctr_get_width_mask(event);

drivers/perf/riscv_pmu_sbi.c

···
 #include <linux/cpu_pm.h>
 #include <linux/sched/clock.h>
 #include <linux/soc/andes/irq.h>
+#include <linux/workqueue.h>
 
 #include <asm/errata_list.h>
 #include <asm/sbi.h>
···
 	};
 };
 
-static const struct sbi_pmu_event_data pmu_hw_event_map[] = {
+static struct sbi_pmu_event_data pmu_hw_event_map[] = {
 	[PERF_COUNT_HW_CPU_CYCLES]		= {.hw_gen_event = {
 							SBI_PMU_HW_CPU_CYCLES,
 							SBI_PMU_EVENT_TYPE_HW, 0}},
···
 };
 
 #define C(x) PERF_COUNT_HW_CACHE_##x
-static const struct sbi_pmu_event_data pmu_cache_event_map[PERF_COUNT_HW_CACHE_MAX]
+static struct sbi_pmu_event_data pmu_cache_event_map[PERF_COUNT_HW_CACHE_MAX]
 [PERF_COUNT_HW_CACHE_OP_MAX]
 [PERF_COUNT_HW_CACHE_RESULT_MAX] = {
 	[C(L1D)] = {
···
 		},
 	},
 };
+
+static void pmu_sbi_check_event(struct sbi_pmu_event_data *edata)
+{
+	struct sbiret ret;
+
+	ret = sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_CFG_MATCH,
+			0, cmask, 0, edata->event_idx, 0, 0);
+	if (!ret.error) {
+		sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_STOP,
+			  ret.value, 0x1, SBI_PMU_STOP_FLAG_RESET, 0, 0, 0);
+	} else if (ret.error == SBI_ERR_NOT_SUPPORTED) {
+		/* This event cannot be monitored by any counter */
+		edata->event_idx = -EINVAL;
+	}
+}
+
+static void pmu_sbi_check_std_events(struct work_struct *work)
+{
+	for (int i = 0; i < ARRAY_SIZE(pmu_hw_event_map); i++)
+		pmu_sbi_check_event(&pmu_hw_event_map[i]);
+
+	for (int i = 0; i < ARRAY_SIZE(pmu_cache_event_map); i++)
+		for (int j = 0; j < ARRAY_SIZE(pmu_cache_event_map[i]); j++)
+			for (int k = 0; k < ARRAY_SIZE(pmu_cache_event_map[i][j]); k++)
+				pmu_sbi_check_event(&pmu_cache_event_map[i][j][k]);
+}
+
+static DECLARE_WORK(check_std_events_work, pmu_sbi_check_std_events);
 
 static int pmu_sbi_ctr_get_width(int idx)
 {
···
 	int bSoftware;
 	u64 raw_config_val;
 	int ret;
+
+	/*
+	 * Ensure we are finished checking standard hardware events for
+	 * validity before allowing userspace to configure any events.
+	 */
+	flush_work(&check_std_events_work);
 
 	switch (type) {
 	case PERF_TYPE_HARDWARE:
···
 	 * which may include counters that are not enabled yet.
 	 */
 	sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_STOP,
-		  0, pmu->cmask, 0, 0, 0, 0);
+		  0, pmu->cmask, SBI_PMU_STOP_FLAG_RESET, 0, 0, 0);
 }
 
 static inline void pmu_sbi_stop_hw_ctrs(struct riscv_pmu *pmu)
···
 	ret = cpuhp_state_add_instance(CPUHP_AP_PERF_RISCV_STARTING, &pmu->node);
 	if (ret)
 		goto out_unregister;
+
+	/* Asynchronously check which standard events are available */
+	schedule_work(&check_std_events_work);
 
 	return 0;
 

drivers/platform/x86/toshiba_acpi.c

···
 		},
 	 .driver_data = (void *)(QUIRK_TURN_ON_PANEL_ON_RESUME | QUIRK_HCI_HOTKEY_QUICKSTART),
 	},
+	{ }
 };
 
 static int toshiba_acpi_add(struct acpi_device *acpi_dev)

drivers/scsi/sd.c

···
 {
 	struct scsi_disk *sdkp = dev_get_drvdata(dev);
 
-	sd_printk(KERN_NOTICE, sdkp, "Starting disk\n");
-
 	if (opal_unlock_from_suspend(sdkp->opal_dev)) {
 		sd_printk(KERN_NOTICE, sdkp, "OPAL unlock failed\n");
 		return -EIO;
···
 	if (!sdkp)	/* E.g.: runtime resume at the start of sd_probe() */
 		return 0;
 
+	sd_printk(KERN_NOTICE, sdkp, "Starting disk\n");
+
 	if (!sd_do_start_stop(sdkp->device, runtime)) {
 		sdkp->suspended = false;
 		return 0;
 	}
 
-	sd_printk(KERN_NOTICE, sdkp, "Starting disk\n");
 	ret = sd_start_stop_device(sdkp, 1);
 	if (!ret) {
 		sd_resume(dev);

drivers/thermal/gov_power_allocator.c

···
 		return;
 	}
 
+	if (!params->trip_max)
+		return;
+
 	allocate_power(tz, params->trip_max->temperature);
 	params->update_cdevs = true;
 }

drivers/thermal/thermal_core.c

···
 		thermal_zone_device_set_polling(tz, tz->passive_delay_jiffies);
 	else if (tz->polling_delay_jiffies)
 		thermal_zone_device_set_polling(tz, tz->polling_delay_jiffies);
+	else if (tz->temperature == THERMAL_TEMP_INVALID)
+		thermal_zone_device_set_polling(tz, msecs_to_jiffies(THERMAL_RECHECK_DELAY_MS));
 }
 
 static struct thermal_governor *thermal_get_tz_governor(struct thermal_zone_device *tz)
···
 	thermal_governor_trip_crossed(governor, tz, trip, crossed_up);
 }
 
-static int thermal_trip_notify_cmp(void *ascending, const struct list_head *a,
+static int thermal_trip_notify_cmp(void *not_used, const struct list_head *a,
 				   const struct list_head *b)
 {
 	struct thermal_trip_desc *tda = container_of(a, struct thermal_trip_desc,
 						     notify_list_node);
 	struct thermal_trip_desc *tdb = container_of(b, struct thermal_trip_desc,
 						     notify_list_node);
-	int ret = tdb->notify_temp - tda->notify_temp;
-
-	return ascending ? ret : -ret;
+	return tda->notify_temp - tdb->notify_temp;
 }
 
 void __thermal_zone_device_update(struct thermal_zone_device *tz,
···
 	update_temperature(tz);
 
 	if (tz->temperature == THERMAL_TEMP_INVALID)
-		return;
+		goto monitor;
 
 	__thermal_zone_set_trips(tz);
 
···
 	for_each_trip_desc(tz, td)
 		handle_thermal_trip(tz, td, &way_up_list, &way_down_list);
 
-	list_sort(&way_up_list, &way_up_list, thermal_trip_notify_cmp);
+	list_sort(NULL, &way_up_list, thermal_trip_notify_cmp);
 	list_for_each_entry(td, &way_up_list, notify_list_node)
 		thermal_trip_crossed(tz, &td->trip, governor, true);
 
 	list_sort(NULL, &way_down_list, thermal_trip_notify_cmp);
-	list_for_each_entry(td, &way_down_list, notify_list_node)
+	list_for_each_entry_reverse(td, &way_down_list, notify_list_node)
 		thermal_trip_crossed(tz, &td->trip, governor, false);
 
 	if (governor->manage)
···
 
 	thermal_debug_update_trip_stats(tz);
 
+monitor:
 	monitor_thermal_zone(tz);
 }
 

drivers/thermal/thermal_core.h

···
 	struct thermal_trip_desc trips[] __counted_by(num_trips);
 };
 
+/*
+ * Default delay after a failing thermal zone temperature check before
+ * attempting to check it again.
+ */
+#define THERMAL_RECHECK_DELAY_MS	250
+
 /* Default Thermal Governor */
 #if defined(CONFIG_THERMAL_DEFAULT_GOV_STEP_WISE)
 #define DEFAULT_THERMAL_GOVERNOR       "step_wise"

drivers/ufs/core/ufs-mcq.c

···
  * @hba: per adapter instance
  * @req: pointer to the request to be issued
  *
- * Return: the hardware queue instance on which the request would
- * be queued.
+ * Return: the hardware queue instance on which the request will be or has
+ * been queued. %NULL if the request has already been freed.
  */
 struct ufs_hw_queue *ufshcd_mcq_req_to_hwq(struct ufs_hba *hba,
 					 struct request *req)
 {
-	u32 utag = blk_mq_unique_tag(req);
-	u32 hwq = blk_mq_unique_tag_to_hwq(utag);
+	struct blk_mq_hw_ctx *hctx = READ_ONCE(req->mq_hctx);
 
-	return &hba->uhq[hwq];
+	return hctx ? &hba->uhq[hctx->queue_num] : NULL;
 }
 
 /**
···
 		if (!cmd)
 			return -EINVAL;
 		hwq = ufshcd_mcq_req_to_hwq(hba, scsi_cmd_to_rq(cmd));
+		if (!hwq)
+			return 0;
 	} else {
 		hwq = hba->dev_cmd_queue;
 	}

drivers/ufs/core/ufshcd.c

···
 	/* Release cmd in MCQ mode if abort succeeds */
 	if (is_mcq_enabled(hba) && (*ret == 0)) {
 		hwq = ufshcd_mcq_req_to_hwq(hba, scsi_cmd_to_rq(lrbp->cmd));
+		if (!hwq)
+			return 0;
 		spin_lock_irqsave(&hwq->cq_lock, flags);
 		if (ufshcd_cmd_inflight(lrbp->cmd))
 			ufshcd_release_scsi_cmd(hba, lrbp);

drivers/vfio/pci/vfio_pci_core.c

···
 	struct vfio_pci_hot_reset_info hdr;
 	struct vfio_pci_fill_info fill = {};
 	bool slot = false;
-	int ret, count;
+	int ret, count = 0;
 
 	if (copy_from_user(&hdr, arg, minsz))
 		return -EFAULT;

fs/bcachefs/alloc_background.c

···
 #include "alloc_background.h"
 #include "alloc_foreground.h"
 #include "backpointers.h"
+#include "bkey_buf.h"
 #include "btree_cache.h"
 #include "btree_io.h"
 #include "btree_key_cache.h"
···
 }
 
 static int bch2_check_alloc_to_lru_ref(struct btree_trans *trans,
-				       struct btree_iter *alloc_iter)
+				       struct btree_iter *alloc_iter,
+				       struct bkey_buf *last_flushed)
 {
 	struct bch_fs *c = trans->c;
-	struct btree_iter lru_iter;
 	struct bch_alloc_v4 a_convert;
 	const struct bch_alloc_v4 *a;
-	struct bkey_s_c alloc_k, lru_k;
+	struct bkey_s_c alloc_k;
 	struct printbuf buf = PRINTBUF;
 	int ret;
 
···
 		return ret;
 
 	a = bch2_alloc_to_v4(alloc_k, &a_convert);
+
+	if (a->fragmentation_lru) {
+		ret = bch2_lru_check_set(trans, BCH_LRU_FRAGMENTATION_START,
+					 a->fragmentation_lru,
+					 alloc_k, last_flushed);
+		if (ret)
+			return ret;
+	}
 
 	if (a->data_type != BCH_DATA_cached)
 		return 0;
···
 		a = &a_mut->v;
 	}
 
-	lru_k = bch2_bkey_get_iter(trans, &lru_iter, BTREE_ID_lru,
-			     lru_pos(alloc_k.k->p.inode,
-				     bucket_to_u64(alloc_k.k->p),
-				     a->io_time[READ]), 0);
-	ret = bkey_err(lru_k);
+	ret = bch2_lru_check_set(trans, alloc_k.k->p.inode, a->io_time[READ],
+				 alloc_k, last_flushed);
 	if (ret)
-		return ret;
-
-	if (fsck_err_on(lru_k.k->type != KEY_TYPE_set, c,
-			alloc_key_to_missing_lru_entry,
-			"missing lru entry\n"
-			"  %s",
-			(printbuf_reset(&buf),
-			 bch2_bkey_val_to_text(&buf, c, alloc_k), buf.buf))) {
-		ret = bch2_lru_set(trans,
-				   alloc_k.k->p.inode,
-				   bucket_to_u64(alloc_k.k->p),
-				   a->io_time[READ]);
-		if (ret)
-			goto err;
-	}
+		goto err;
 err:
 fsck_err:
-	bch2_trans_iter_exit(trans, &lru_iter);
 	printbuf_exit(&buf);
 	return ret;
 }
 
 int bch2_check_alloc_to_lru_refs(struct bch_fs *c)
 {
+	struct bkey_buf last_flushed;
+
+	bch2_bkey_buf_init(&last_flushed);
+	bkey_init(&last_flushed.k->k);
+
 	int ret = bch2_trans_run(c,
 		for_each_btree_key_commit(trans, iter, BTREE_ID_alloc,
 				POS_MIN, BTREE_ITER_prefetch, k,
 				NULL, NULL, BCH_TRANS_COMMIT_no_enospc,
-			bch2_check_alloc_to_lru_ref(trans, &iter)));
+			bch2_check_alloc_to_lru_ref(trans, &iter, &last_flushed)));
+
+	bch2_bkey_buf_exit(&last_flushed, c);
 	bch_err_fn(c, ret);
 	return ret;
 }

fs/bcachefs/alloc_foreground.c

···
 	for (unsigned i = 0; i < ARRAY_SIZE(c->open_buckets); i++)
 		nr[c->open_buckets[i].data_type]++;
 
+	printbuf_tabstops_reset(out);
 	printbuf_tabstop_push(out, 24);
 
 	percpu_down_read(&c->mark_lock);
···
 	for (unsigned i = 0; i < ARRAY_SIZE(c->open_buckets); i++)
 		nr[c->open_buckets[i].data_type]++;
 
+	printbuf_tabstops_reset(out);
 	printbuf_tabstop_push(out, 12);
 	printbuf_tabstop_push(out, 16);
 	printbuf_tabstop_push(out, 16);

fs/bcachefs/backpointers.c

···
 	return ret;
 }
 
-static inline bool bkey_and_val_eq(struct bkey_s_c l, struct bkey_s_c r)
-{
-	return bpos_eq(l.k->p, r.k->p) &&
-		bkey_bytes(l.k) == bkey_bytes(r.k) &&
-		!memcmp(l.v, r.v, bkey_val_bytes(l.k));
-}
-
 struct extents_to_bp_state {
 	struct bpos	bucket_start;
 	struct bpos	bucket_end;
···
 	struct btree_iter other_extent_iter = {};
 	struct printbuf buf = PRINTBUF;
 	struct bkey_s_c bp_k;
-	struct bkey_buf tmp;
 	int ret = 0;
-
-	bch2_bkey_buf_init(&tmp);
 
 	struct bch_dev *ca = bch2_dev_bucket_tryget(c, bucket);
 	if (!ca) {
···
 
 	if (bp_k.k->type != KEY_TYPE_backpointer ||
 	    memcmp(bkey_s_c_to_backpointer(bp_k).v, &bp, sizeof(bp))) {
-		bch2_bkey_buf_reassemble(&tmp, c, orig_k);
-
-		if (!bkey_and_val_eq(orig_k, bkey_i_to_s_c(s->last_flushed.k))) {
-			if (bp.level) {
-				bch2_trans_unlock(trans);
-				bch2_btree_interior_updates_flush(c);
-			}
-
-			ret = bch2_btree_write_buffer_flush_sync(trans);
-			if (ret)
-				goto err;
-
-			bch2_bkey_buf_copy(&s->last_flushed, c, tmp.k);
-			ret = -BCH_ERR_transaction_restart_write_buffer_flush;
-			goto out;
-		}
+		ret = bch2_btree_write_buffer_maybe_flush(trans, orig_k, &s->last_flushed);
+		if (ret)
+			goto err;
 
 		goto check_existing_bp;
 	}
···
 fsck_err:
 	bch2_trans_iter_exit(trans, &other_extent_iter);
 	bch2_trans_iter_exit(trans, &bp_iter);
-	bch2_bkey_buf_exit(&tmp, c);
 	bch2_dev_put(ca);
 	printbuf_exit(&buf);
 	return ret;
···
 		    !((1U << btree) & btree_interior_mask))
 			continue;
 
+		bch2_trans_begin(trans);
+
 		__for_each_btree_node(trans, iter, btree,
 				      btree == start.btree ? start.pos : POS_MIN,
 				      0, depth, BTREE_ITER_prefetch, b, ret) {
···
 				 struct bbpos start,
 				 struct bbpos end,
 				 struct bkey_s_c_backpointer bp,
-				 struct bpos *last_flushed_pos)
+				 struct bkey_buf *last_flushed)
 {
 	struct bch_fs *c = trans->c;
 	struct btree_iter iter;
···
 	if (ret)
 		return ret;
 
-	if (!k.k && !bpos_eq(*last_flushed_pos, bp.k->p)) {
-		*last_flushed_pos = bp.k->p;
-		ret = bch2_btree_write_buffer_flush_sync(trans) ?:
-			-BCH_ERR_transaction_restart_write_buffer_flush;
-		goto out;
-	}
+	if (!k.k) {
+		ret = bch2_btree_write_buffer_maybe_flush(trans, bp.s_c, last_flushed);
+		if (ret)
+			goto out;
 
-	if (fsck_err_on(!k.k, c,
-			backpointer_to_missing_ptr,
-			"backpointer for missing %s\n  %s",
-			bp.v->level ? "btree node" : "extent",
-			(bch2_bkey_val_to_text(&buf, c, bp.s_c), buf.buf))) {
-		ret = bch2_btree_delete_at_buffered(trans, BTREE_ID_backpointers, bp.k->p);
-		goto out;
+		if (fsck_err(c, backpointer_to_missing_ptr,
+			     "backpointer for missing %s\n  %s",
+			     bp.v->level ? "btree node" : "extent",
+			     (bch2_bkey_val_to_text(&buf, c, bp.s_c), buf.buf))) {
+			ret = bch2_btree_delete_at_buffered(trans, BTREE_ID_backpointers, bp.k->p);
+			goto out;
+		}
 	}
 out:
 fsck_err:
···
 						   struct bbpos start,
 						   struct bbpos end)
 {
-	struct bpos last_flushed_pos = SPOS_MAX;
+	struct bkey_buf last_flushed;
 
-	return for_each_btree_key_commit(trans, iter, BTREE_ID_backpointers,
+	bch2_bkey_buf_init(&last_flushed);
+	bkey_init(&last_flushed.k->k);
+
+	int ret = for_each_btree_key_commit(trans, iter, BTREE_ID_backpointers,
 				  POS_MIN, BTREE_ITER_prefetch, k,
 				  NULL, NULL, BCH_TRANS_COMMIT_no_enospc,
 		check_one_backpointer(trans, start, end,
 				      bkey_s_c_to_backpointer(k),
-				      &last_flushed_pos));
+				      &last_flushed));
+
+	bch2_bkey_buf_exit(&last_flushed, trans->c);
+	return ret;
 }
 
 int bch2_check_backpointers_to_extents(struct bch_fs *c)

fs/bcachefs/bkey.c

···
 		    bch2_bkey_format_field_overflows(f, i)) {
 			unsigned unpacked_bits = bch2_bkey_format_current.bits_per_field[i];
 			u64 unpacked_max = ~((~0ULL << 1) << (unpacked_bits - 1));
-			u64 packed_max = f->bits_per_field[i]
-				? ~((~0ULL << 1) << (f->bits_per_field[i] - 1))
+			unsigned packed_bits = min(64, f->bits_per_field[i]);
+			u64 packed_max = packed_bits
+				? ~((~0ULL << 1) << (packed_bits - 1))
 				: 0;
 
 			prt_printf(err, "field %u too large: %llu + %llu > %llu",

fs/bcachefs/bkey.h

···
 	return bkey_gt(l, r) ? l : r;
 }
 
+static inline bool bkey_and_val_eq(struct bkey_s_c l, struct bkey_s_c r)
+{
+	return bpos_eq(l.k->p, r.k->p) &&
+		bkey_bytes(l.k) == bkey_bytes(r.k) &&
+		!memcmp(l.v, r.v, bkey_val_bytes(l.k));
+}
+
 void bch2_bpos_swab(struct bpos *);
 void bch2_bkey_swab_key(const struct bkey_format *, struct bkey_packed *);
 

fs/bcachefs/btree_gc.c

···
 		bch2_dev_usage_update(c, ca, &old_gc, &gc, 0, true);
 	percpu_up_read(&c->mark_lock);
 
+	gc.fragmentation_lru = alloc_lru_idx_fragmentation(gc, ca);
+
 	if (fsck_err_on(new.data_type != gc.data_type, c,
 			alloc_key_data_type_wrong,
 			"bucket %llu:%llu gen %u has wrong data_type"
···
 #define copy_bucket_field(_errtype, _f)					\
 	if (fsck_err_on(new._f != gc._f, c, _errtype,			\
 			"bucket %llu:%llu gen %u data type %s has wrong " #_f	\
-			": got %u, should be %u",			\
+			": got %llu, should be %llu",			\
 			iter->pos.inode, iter->pos.offset,		\
 			gc.gen,						\
 			bch2_data_type_str(gc.data_type),		\
-			new._f, gc._f))					\
+			(u64) new._f, (u64) gc._f))				\
 		new._f = gc._f;						\
 
-	copy_bucket_field(alloc_key_gen_wrong,
-			  gen);
-	copy_bucket_field(alloc_key_dirty_sectors_wrong,
-			  dirty_sectors);
-	copy_bucket_field(alloc_key_cached_sectors_wrong,
-			  cached_sectors);
-	copy_bucket_field(alloc_key_stripe_wrong,
-			  stripe);
-	copy_bucket_field(alloc_key_stripe_redundancy_wrong,
-			  stripe_redundancy);
+	copy_bucket_field(alloc_key_gen_wrong,			gen);
+	copy_bucket_field(alloc_key_dirty_sectors_wrong,	dirty_sectors);
+	copy_bucket_field(alloc_key_cached_sectors_wrong,	cached_sectors);
+	copy_bucket_field(alloc_key_stripe_wrong,		stripe);
+	copy_bucket_field(alloc_key_stripe_redundancy_wrong,	stripe_redundancy);
+	copy_bucket_field(alloc_key_fragmentation_lru_wrong,	fragmentation_lru);
 #undef copy_bucket_field
 
 	if (!bch2_alloc_v4_cmp(*old, new))
···
 	a->v = new;
 
 	/*
-	 * The trigger normally makes sure this is set, but we're not running
+	 * The trigger normally makes sure these are set, but we're not running
 	 * triggers:
 	 */
 	if (a->v.data_type == BCH_DATA_cached && !a->v.io_time[READ])

fs/bcachefs/btree_write_buffer.c

···
 // SPDX-License-Identifier: GPL-2.0
 
 #include "bcachefs.h"
+#include "bkey_buf.h"
 #include "btree_locking.h"
 #include "btree_update.h"
 #include "btree_update_interior.h"
 #include "btree_write_buffer.h"
 #include "error.h"
+#include "extents.h"
 #include "journal.h"
 #include "journal_io.h"
 #include "journal_reclaim.h"
···
 
 	int ret = bch2_btree_write_buffer_flush_nocheck_rw(trans);
 	bch2_write_ref_put(c, BCH_WRITE_REF_btree_write_buffer);
+	return ret;
+}
+
+/**
+ * In check and repair code, when checking references to write buffer btrees we
+ * need to issue a flush before we have a definitive error: this issues a flush
+ * if this is a key we haven't yet checked.
+ */
+int bch2_btree_write_buffer_maybe_flush(struct btree_trans *trans,
+					struct bkey_s_c referring_k,
+					struct bkey_buf *last_flushed)
+{
+	struct bch_fs *c = trans->c;
+	struct bkey_buf tmp;
+	int ret = 0;
+
+	bch2_bkey_buf_init(&tmp);
+
+	if (!bkey_and_val_eq(referring_k, bkey_i_to_s_c(last_flushed->k))) {
+		bch2_bkey_buf_reassemble(&tmp, c, referring_k);
+
+		if (bkey_is_btree_ptr(referring_k.k)) {
+			bch2_trans_unlock(trans);
+			bch2_btree_interior_updates_flush(c);
+		}
+
+		ret = bch2_btree_write_buffer_flush_sync(trans);
+		if (ret)
+			goto err;
+
+		bch2_bkey_buf_copy(last_flushed, c, tmp.k);
+		ret = -BCH_ERR_transaction_restart_write_buffer_flush;
+	}
+err:
+	bch2_bkey_buf_exit(&tmp, c);
 	return ret;
 }
 

fs/bcachefs/btree_write_buffer.h

···
 int bch2_btree_write_buffer_flush_nocheck_rw(struct btree_trans *);
 int bch2_btree_write_buffer_tryflush(struct btree_trans *);
 
+struct bkey_buf;
+int bch2_btree_write_buffer_maybe_flush(struct btree_trans *, struct bkey_s_c, struct bkey_buf *);
+
 struct journal_keys_to_wb {
 	struct btree_write_buffer_keys	*wb;
 	size_t				room;

fs/bcachefs/clock.c

···
 {
 	struct io_timer *ret = NULL;
 
-	spin_lock(&clock->timer_lock);
-
 	if (clock->timers.used &&
 	    time_after_eq(now, clock->timers.data[0]->expire))
 		heap_pop(&clock->timers, ret, io_timer_cmp, NULL);
-
-	spin_unlock(&clock->timer_lock);
-
 	return ret;
 }
 
···
 	struct io_timer *timer;
 	unsigned long now = atomic64_add_return(sectors, &clock->now);
 
+	spin_lock(&clock->timer_lock);
 	while ((timer = get_expired_timer(clock, now)))
 		timer->fn(timer);
+	spin_unlock(&clock->timer_lock);
 }
 
 void bch2_io_timers_to_text(struct printbuf *out, struct io_clock *clock)

fs/bcachefs/data_update.c

···
 #include "bkey_buf.h"
 #include "btree_update.h"
 #include "buckets.h"
+#include "compress.h"
 #include "data_update.h"
+#include "disk_groups.h"
 #include "ec.h"
 #include "error.h"
 #include "extents.h"
···
 	}
 }
 
+void bch2_data_update_opts_to_text(struct printbuf *out, struct bch_fs *c,
+				   struct bch_io_opts *io_opts,
+				   struct data_update_opts *data_opts)
+{
+	printbuf_tabstop_push(out, 20);
+	prt_str(out, "rewrite ptrs:\t");
+	bch2_prt_u64_base2(out, data_opts->rewrite_ptrs);
+	prt_newline(out);
+
+	prt_str(out, "kill ptrs:\t");
+	bch2_prt_u64_base2(out, data_opts->kill_ptrs);
+	prt_newline(out);
+
+	prt_str(out, "target:\t");
+	bch2_target_to_text(out, c, data_opts->target);
+	prt_newline(out);
+
+	prt_str(out, "compression:\t");
+	bch2_compression_opt_to_text(out, background_compression(*io_opts));
+	prt_newline(out);
+
+	prt_str(out, "extra replicas:\t");
+	prt_u64(out, data_opts->extra_replicas);
+}
+
+void bch2_data_update_to_text(struct printbuf *out, struct data_update *m)
+{
+	bch2_bkey_val_to_text(out, m->op.c, bkey_i_to_s_c(m->k.k));
+	prt_newline(out);
+	bch2_data_update_opts_to_text(out, m->op.c, &m->op.opts, &m->data_opts);
+}
+
 int bch2_extent_drop_ptrs(struct btree_trans *trans,
 			  struct btree_iter *iter,
 			  struct bkey_s_c k,
···
 	 */
 	if (!(durability_have + durability_removing))
 		m->op.nr_replicas = max((unsigned) m->op.nr_replicas, 1);
+
+	if (!m->op.nr_replicas) {
+		struct printbuf buf = PRINTBUF;
+
+		bch2_data_update_to_text(&buf, m);
+		WARN(1, "trying to move an extent, but nr_replicas=0\n%s", buf.buf);
+		printbuf_exit(&buf);
+		ret = -BCH_ERR_data_update_done;
+		goto done;
+	}
 
 	m->op.nr_replicas_required = m->op.nr_replicas;
 

fs/bcachefs/data_update.h

···
 	unsigned	write_flags;
 };
 
+void bch2_data_update_opts_to_text(struct printbuf *, struct bch_fs *,
+				   struct bch_io_opts *, struct data_update_opts *);
+
 struct data_update {
 	/* extent being updated: */
 	enum btree_id		btree_id;
···
 	struct bch_move_stats	*stats;
 	struct bch_write_op	op;
 };
+
+void bch2_data_update_to_text(struct printbuf *, struct data_update *);
 
 int bch2_data_update_index_update(struct bch_write_op *);
 

fs/bcachefs/debug.c

···
 	list_sort(&c->btree_trans_list, list_ptr_order_cmp);
 
 	list_for_each_entry(trans, &c->btree_trans_list, list) {
-		if ((ulong) trans < i->iter)
+		if ((ulong) trans <= i->iter)
 			continue;
 
 		i->iter = (ulong) trans;
···
 static void btree_deadlock_to_text(struct printbuf *out, struct bch_fs *c)
 {
 	struct btree_trans *trans;
-	pid_t iter = 0;
+	ulong iter = 0;
 restart:
 	seqmutex_lock(&c->btree_trans_lock);
-	list_for_each_entry(trans, &c->btree_trans_list, list) {
-		struct task_struct *task = READ_ONCE(trans->locking_wait.task);
+	list_sort(&c->btree_trans_list, list_ptr_order_cmp);
 
-		if (!task || task->pid <= iter)
+	list_for_each_entry(trans, &c->btree_trans_list, list) {
+		if ((ulong) trans <= iter)
 			continue;
 
-		iter = task->pid;
+		iter = (ulong) trans;
 
 		if (!closure_get_not_zero(&trans->ref))
 			continue;

fs/bcachefs/eytzinger.h

···
 
 static inline unsigned eytzinger1_first(unsigned size)
 {
-	return rounddown_pow_of_two(size);
+	return size ? rounddown_pow_of_two(size) : 0;
 }
 
 static inline unsigned eytzinger1_last(unsigned size)
···
 
 static inline unsigned eytzinger1_extra(unsigned size)
 {
-	return (size + 1 - rounddown_pow_of_two(size)) << 1;
+	return size
+		? (size + 1 - rounddown_pow_of_two(size)) << 1
+		: 0;
 }
 
 static inline unsigned __eytzinger1_to_inorder(unsigned i, unsigned size,

fs/bcachefs/fs.c

···
 		 * discard_new_inode() expects it to be set...
 		 */
 		inode->v.i_flags |= I_NEW;
+		/*
+		 * We don't want bch2_evict_inode() to delete the inode on disk,
+		 * we just raced and had another inode in cache. Normally new
+		 * inodes don't have nlink == 0 - except tmpfiles do...
+		 */
+		set_nlink(&inode->v, 1);
 		discard_new_inode(&inode->v);
 		inode = old;
 	} else {
···
 	__bch2_fs_stop(c);
 	deactivate_locked_super(sb);
 err:
+	if (ret)
+		pr_err("error: %s", bch2_err_str(ret));
 	/*
 	 * On an inconsistency error in recovery we might see an -EROFS derived
 	 * errorcode (from the journal), but we don't want to return that to
···
 {
 	int ret = -ENOMEM;
 
-	bch2_inode_cache = KMEM_CACHE(bch_inode_info, SLAB_RECLAIM_ACCOUNT);
+	bch2_inode_cache = KMEM_CACHE(bch_inode_info, SLAB_RECLAIM_ACCOUNT |
+				      SLAB_ACCOUNT);
 	if (!bch2_inode_cache)
 		goto err;
 

fs/bcachefs/io_read.c

···
 
 	bch2_bkey_buf_reassemble(&sk, c, k);
 	k = bkey_i_to_s_c(sk.k);
-	bch2_trans_unlock(trans);
 
 	if (!bch2_bkey_matches_ptr(c, k,
 				   rbio->pick.ptr,
···
 	rbio->version		= k.k->version;
 	rbio->promote		= promote;
 	INIT_WORK(&rbio->work, NULL);
+
+	if (flags & BCH_READ_NODECODE)
+		orig->pick = pick;
 
 	rbio->bio.bi_opf	= orig->bio.bi_opf;
 	rbio->bio.bi_iter.bi_sector = pick.ptr.offset;

fs/bcachefs/journal.c

···
 	return ret;
 }
 
-int bch2_dev_journal_alloc(struct bch_dev *ca)
+int bch2_dev_journal_alloc(struct bch_dev *ca, bool new_fs)
 {
 	unsigned nr;
 	int ret;
···
 		     min(1 << 13,
 			 (1 << 24) / ca->mi.bucket_size));
 
-	ret = __bch2_set_nr_journal_buckets(ca, nr, true, NULL);
+	ret = __bch2_set_nr_journal_buckets(ca, nr, new_fs, NULL);
 err:
 	bch_err_fn(ca, ret);
 	return ret;
···
 		if (ca->journal.nr)
 			continue;
 
-		int ret = bch2_dev_journal_alloc(ca);
+		int ret = bch2_dev_journal_alloc(ca, true);
 		if (ret) {
 			percpu_ref_put(&ca->io_ref);
 			return ret;
···
 	journal_quiesce(j);
 	cancel_delayed_work_sync(&j->write_work);
 
-	BUG_ON(!bch2_journal_error(j) &&
-	       test_bit(JOURNAL_replay_done, &j->flags) &&
-	       j->last_empty_seq != journal_cur_seq(j));
+	WARN(!bch2_journal_error(j) &&
+	     test_bit(JOURNAL_replay_done, &j->flags) &&
+	     j->last_empty_seq != journal_cur_seq(j),
+	     "journal shutdown error: cur seq %llu but last empty seq %llu",
+	     journal_cur_seq(j), j->last_empty_seq);
 
 	if (!bch2_journal_error(j))
 		clear_bit(JOURNAL_running, &j->flags);
···
 	unsigned long now = jiffies;
 	u64 nr_writes = j->nr_flush_writes + j->nr_noflush_writes;
 
-	if (!out->nr_tabstops)
-		printbuf_tabstop_push(out, 28);
+	printbuf_tabstops_reset(out);
+	printbuf_tabstop_push(out, 28);
 	out->atomic++;
 
 	rcu_read_lock();

fs/bcachefs/journal.h

···
 
 int bch2_set_nr_journal_buckets(struct bch_fs *, struct bch_dev *,
 				unsigned nr);
-int bch2_dev_journal_alloc(struct bch_dev *);
+int bch2_dev_journal_alloc(struct bch_dev *, bool);
 int bch2_fs_journal_alloc(struct bch_fs *);
 
 void bch2_dev_journal_stop(struct journal *, struct bch_dev *);

fs/bcachefs/journal_io.c

···
 					       flags|BCH_VALIDATE_journal);
 		if (ret == FSCK_DELETED_KEY)
 			continue;
+		else if (ret)
+			return ret;
 
 		k = bkey_next(k);
 	}
···
 
 	if (j->seq_ondisk + 1 != le64_to_cpu(w->data->seq)) {
 		spin_lock(&j->lock);
-		closure_wait(&j->async_wait, cl);
+		if (j->seq_ondisk + 1 != le64_to_cpu(w->data->seq)) {
+			closure_wait(&j->async_wait, cl);
+			spin_unlock(&j->lock);
+			continue_at(cl, journal_write_preflush, j->wq);
+			return;
+		}
 		spin_unlock(&j->lock);
-
-		continue_at(cl, journal_write_preflush, j->wq);
-		return;
 	}
 
 	if (w->separate_flush) {

fs/bcachefs/lru.c

···
 	NULL
 };
 
+int bch2_lru_check_set(struct btree_trans *trans,
+		       u16 lru_id, u64 time,
+		       struct bkey_s_c referring_k,
+		       struct bkey_buf *last_flushed)
+{
+	struct bch_fs *c = trans->c;
+	struct printbuf buf = PRINTBUF;
+	struct btree_iter lru_iter;
+	struct bkey_s_c lru_k =
+		bch2_bkey_get_iter(trans, &lru_iter, BTREE_ID_lru,
+				   lru_pos(lru_id,
+					   bucket_to_u64(referring_k.k->p),
+					   time), 0);
+	int ret = bkey_err(lru_k);
+	if (ret)
+		return ret;
+
+	if (lru_k.k->type != KEY_TYPE_set) {
+		ret = bch2_btree_write_buffer_maybe_flush(trans, referring_k, last_flushed);
+		if (ret)
+			goto err;
+
+		if (fsck_err(c, alloc_key_to_missing_lru_entry,
+			     "missing %s lru entry\n"
+			     "  %s",
+			     bch2_lru_types[lru_type(lru_k)],
+			     (bch2_bkey_val_to_text(&buf, c, referring_k), buf.buf))) {
+			ret = bch2_lru_set(trans, lru_id, bucket_to_u64(referring_k.k->p), time);
+			if (ret)
+				goto err;
+		}
+	}
+err:
+fsck_err:
+	bch2_trans_iter_exit(trans, &lru_iter);
+	printbuf_exit(&buf);
+	return ret;
+}
+
 static int bch2_check_lru_key(struct btree_trans *trans,
 			      struct btree_iter *lru_iter,
 			      struct bkey_s_c lru_k,

fs/bcachefs/lru.h

···
 int bch2_lru_set(struct btree_trans *, u16, u64, u64);
 int bch2_lru_change(struct btree_trans *, u16, u64, u64, u64);
 
+struct bkey_buf;
+int bch2_lru_check_set(struct btree_trans *, u16, u64, struct bkey_s_c, struct bkey_buf *);
+
 int bch2_check_lrus(struct bch_fs *);
 
 #endif /* _BCACHEFS_LRU_H */

fs/bcachefs/move.c

···
 	NULL
 };
 
-static void bch2_data_update_opts_to_text(struct printbuf *out, struct bch_fs *c,
-					  struct bch_io_opts *io_opts,
-					  struct data_update_opts *data_opts)
-{
-	printbuf_tabstop_push(out, 20);
-	prt_str(out, "rewrite ptrs:\t");
-	bch2_prt_u64_base2(out, data_opts->rewrite_ptrs);
-	prt_newline(out);
-
-	prt_str(out, "kill ptrs:\t");
-	bch2_prt_u64_base2(out, data_opts->kill_ptrs);
-	prt_newline(out);
-
-	prt_str(out, "target:\t");
-	bch2_target_to_text(out, c, data_opts->target);
-	prt_newline(out);
-
-	prt_str(out, "compression:\t");
-	bch2_compression_opt_to_text(out, background_compression(*io_opts));
-	prt_newline(out);
-
-	prt_str(out, "extra replicas:\t");
-	prt_u64(out, data_opts->extra_replicas);
-}
-
 static void trace_move_extent2(struct bch_fs *c, struct bkey_s_c k,
 			       struct bch_io_opts *io_opts,
 			       struct data_update_opts *data_opts)

fs/bcachefs/sb-errors_format.h

···
 	x(accounting_mismatch,					272,	0)		\
 	x(accounting_replicas_not_marked,			273,	0)		\
 	x(invalid_btree_id,					274,	0)		\
-	x(alloc_key_io_time_bad,				275,	0)
+	x(alloc_key_io_time_bad,				275,	0)		\
+	x(alloc_key_fragmentation_lru_wrong,			276,	FSCK_AUTOFIX)
 
 enum bch_sb_error_id {
 #define x(t, n, ...) BCH_FSCK_ERR_##t = n,

fs/bcachefs/super.c

···
 	BUG_ON(atomic_read(&c->journal_keys.ref));
 	bch2_fs_btree_write_buffer_exit(c);
 	percpu_free_rwsem(&c->mark_lock);
-	EBUG_ON(c->online_reserved && percpu_u64_get(c->online_reserved));
-	free_percpu(c->online_reserved);
+	if (c->online_reserved) {
+		u64 v = percpu_u64_get(c->online_reserved);
+		WARN(v, "online_reserved not 0 at shutdown: %lli", v);
+		free_percpu(c->online_reserved);
+	}
 
 	darray_exit(&c->btree_roots_extra);
 	free_percpu(c->pcpu);
···
 	if (ret)
 		goto err;
 
-	ret = bch2_dev_journal_alloc(ca);
+	ret = bch2_dev_journal_alloc(ca, true);
 	bch_err_msg(c, ret, "allocating journal");
 	if (ret)
 		goto err;
···
 	}
 
 	if (!ca->journal.nr) {
-		ret = bch2_dev_journal_alloc(ca);
+		ret = bch2_dev_journal_alloc(ca, false);
 		bch_err_msg(ca, ret, "allocating journal");
 		if (ret)
 			goto err;

fs/btrfs/extent_io.c

···
 	for (int i = 0; i < num_folios; i++) {
 		if (eb->folios[i]) {
 			detach_extent_buffer_folio(eb, eb->folios[i]);
-			__folio_put(eb->folios[i]);
+			folio_put(eb->folios[i]);
 		}
 	}
 	__free_extent_buffer(eb);

fs/btrfs/inode.c

···
 out_folios:
 	for (i = 0; i < nr_folios; i++) {
 		if (folios[i])
-			__folio_put(folios[i]);
+			folio_put(folios[i]);
 	}
 	kvfree(folios);
 out:

fs/btrfs/qgroup.c

···
 			       struct btrfs_qgroup_inherit *inherit,
 			       size_t size)
 {
-	if (!btrfs_qgroup_enabled(fs_info))
-		return 0;
 	if (inherit->flags & ~BTRFS_QGROUP_INHERIT_FLAGS_SUPP)
 		return -EOPNOTSUPP;
 	if (size < sizeof(*inherit) || size > PAGE_SIZE)
···
 
 	if (size != struct_size(inherit, qgroups, inherit->num_qgroups))
 		return -EINVAL;
+
+	/*
+	 * Skip the inherit source qgroups check if qgroup is not enabled.
+	 * Qgroup can still be later enabled causing problems, but in that case
+	 * btrfs_qgroup_inherit() would just ignore those invalid ones.
+	 */
+	if (!btrfs_qgroup_enabled(fs_info))
+		return 0;
 
 	/*
 	 * Now check all the remaining qgroups, they should all:

fs/btrfs/ref-verify.c

···
 	u32 item_size = btrfs_item_size(leaf, slot);
 	unsigned long end, ptr;
 	u64 offset, flags, count;
-	int type, ret;
+	int type;
+	int ret = 0;
 
 	ei = btrfs_item_ptr(leaf, slot, struct btrfs_extent_item);
 	flags = btrfs_extent_flags(leaf, ei);
···
 						  key->objectid, key->offset);
 			break;
 		case BTRFS_EXTENT_OWNER_REF_KEY:
-			WARN_ON(!btrfs_fs_incompat(fs_info, SIMPLE_QUOTA));
+			if (!btrfs_fs_incompat(fs_info, SIMPLE_QUOTA)) {
+				btrfs_err(fs_info,
+			  "found extent owner ref without simple quotas enabled");
+				ret = -EINVAL;
+			}
 			break;
 		default:
 			btrfs_err(fs_info, "invalid key type in iref");

fs/btrfs/space-info.c

···
 	 * "optimal" chunk size based on the fs size.  However when we actually
 	 * allocate the chunk we will strip this down further, making it no more
 	 * than 10% of the disk or 1G, whichever is smaller.
+	 *
+	 * On the zoned mode, we need to use zone_size (=
+	 * data_sinfo->chunk_size) as it is.
 	 */
 	data_sinfo = btrfs_find_space_info(fs_info, BTRFS_BLOCK_GROUP_DATA);
-	data_chunk_size = min(data_sinfo->chunk_size,
-			      mult_perc(fs_info->fs_devices->total_rw_bytes, 10));
-	data_chunk_size = min_t(u64, data_chunk_size, SZ_1G);
+	if (!btrfs_is_zoned(fs_info)) {
+		data_chunk_size = min(data_sinfo->chunk_size,
+				      mult_perc(fs_info->fs_devices->total_rw_bytes, 10));
+		data_chunk_size = min_t(u64, data_chunk_size, SZ_1G);
+	} else {
+		data_chunk_size = data_sinfo->chunk_size;
+	}
 
 	/*
 	 * Since data allocations immediately use block groups as part of the
···
 		avail >>= 3;
 	else
 		avail >>= 1;
+
+	/*
+	 * On the zoned mode, we always allocate one zone as one chunk.
+	 * Returning non-zone size alingned bytes here will result in
+	 * less pressure for the async metadata reclaim process, and it
+	 * will over-commit too much leading to ENOSPC. Align down to the
+	 * zone size to avoid that.
+	 */
+	if (btrfs_is_zoned(fs_info))
+		avail = ALIGN_DOWN(avail, fs_info->zone_size);
+
 	return avail;
 }
 

fs/cachefiles/cache.c

···
 #include <linux/slab.h>
 #include <linux/statfs.h>
 #include <linux/namei.h>
+#include <trace/events/fscache.h>
 #include "internal.h"
 
 /*
···
 }
 
 /*
- * Withdraw volumes.
+ * Withdraw fscache volumes.
+ */
+static void cachefiles_withdraw_fscache_volumes(struct cachefiles_cache *cache)
+{
+	struct list_head *cur;
+	struct cachefiles_volume *volume;
+	struct fscache_volume *vcookie;
+
+	_enter("");
+retry:
+	spin_lock(&cache->object_list_lock);
+	list_for_each(cur, &cache->volumes) {
+		volume = list_entry(cur, struct cachefiles_volume, cache_link);
+
+		if (atomic_read(&volume->vcookie->n_accesses) == 0)
+			continue;
+
+		vcookie = fscache_try_get_volume(volume->vcookie,
+						 fscache_volume_get_withdraw);
+		if (vcookie) {
+			spin_unlock(&cache->object_list_lock);
+			fscache_withdraw_volume(vcookie);
+			fscache_put_volume(vcookie, fscache_volume_put_withdraw);
+			goto retry;
+		}
+	}
+	spin_unlock(&cache->object_list_lock);
+
+	_leave("");
+}
+
+/*
+ * Withdraw cachefiles volumes.
  */
 static void cachefiles_withdraw_volumes(struct cachefiles_cache *cache)
 {
 	_enter("");
 
 	for (;;) {
+		struct fscache_volume *vcookie = NULL;
 		struct cachefiles_volume *volume = NULL;
 
 		spin_lock(&cache->object_list_lock);
 		if (!list_empty(&cache->volumes)) {
 			volume = list_first_entry(&cache->volumes,
 						  struct cachefiles_volume, cache_link);
+			vcookie = fscache_try_get_volume(volume->vcookie,
+							 fscache_volume_get_withdraw);
+			if (!vcookie) {
+				spin_unlock(&cache->object_list_lock);
+				cpu_relax();
+				continue;
+			}
 			list_del_init(&volume->cache_link);
 		}
 		spin_unlock(&cache->object_list_lock);
···
 			break;
 
 		cachefiles_withdraw_volume(volume);
+		fscache_put_volume(vcookie, fscache_volume_put_withdraw);
 	}
 
 	_leave("");
···
 	pr_info("File cache on %s unregistering\n", fscache->name);
 
 	fscache_withdraw_cache(fscache);
+	cachefiles_withdraw_fscache_volumes(cache);
 
 	/* we now have to destroy all the active objects pertaining to this
 	 * cache - which we do by passing them off to thread pool to be

fs/cachefiles/daemon.c

···
 
 	if (cachefiles_in_ondemand_mode(cache)) {
 		if (!xa_empty(&cache->reqs)) {
-			rcu_read_lock();
+			xas_lock(&xas);
 			xas_for_each_marked(&xas, req, ULONG_MAX, CACHEFILES_REQ_NEW) {
 				if (!cachefiles_ondemand_is_reopening_read(req)) {
 					mask |= EPOLLIN;
 					break;
 				}
 			}
-			rcu_read_unlock();
+			xas_unlock(&xas);
 		}
 	} else {
 		if (test_bit(CACHEFILES_STATE_CHANGED, &cache->flags))

fs/cachefiles/internal.h

···
 	CACHEFILES_ONDEMAND_OBJSTATE_CLOSE, /* Anonymous fd closed by daemon or initial state */
 	CACHEFILES_ONDEMAND_OBJSTATE_OPEN, /* Anonymous fd associated with object is available */
 	CACHEFILES_ONDEMAND_OBJSTATE_REOPENING, /* Object that was closed and is being reopened. */
+	CACHEFILES_ONDEMAND_OBJSTATE_DROPPING, /* Object is being dropped. */
 };
 
 struct cachefiles_ondemand_info {
···
 	unsigned long			req_id_next;
 	struct xarray			ondemand_ids;	/* xarray for ondemand_id allocation */
 	u32				ondemand_id_next;
+	u32				msg_id_next;
 };
 
 static inline bool cachefiles_in_ondemand_mode(struct cachefiles_cache *cache)
···
 CACHEFILES_OBJECT_STATE_FUNCS(open, OPEN);
 CACHEFILES_OBJECT_STATE_FUNCS(close, CLOSE);
 CACHEFILES_OBJECT_STATE_FUNCS(reopening, REOPENING);
+CACHEFILES_OBJECT_STATE_FUNCS(dropping, DROPPING);
 
 static inline bool cachefiles_ondemand_is_reopening_read(struct cachefiles_req *req)
 {

fs/cachefiles/ondemand.c

···
 		 */
 		xas_lock(&xas);
 
-		if (test_bit(CACHEFILES_DEAD, &cache->flags)) {
+		if (test_bit(CACHEFILES_DEAD, &cache->flags) ||
+		    cachefiles_ondemand_object_is_dropping(object)) {
 			xas_unlock(&xas);
 			ret = -EIO;
 			goto out;
···
 		smp_mb();
 
 		if (opcode == CACHEFILES_OP_CLOSE &&
-			!cachefiles_ondemand_object_is_open(object)) {
+		    !cachefiles_ondemand_object_is_open(object)) {
 			WARN_ON_ONCE(object->ondemand->ondemand_id == 0);
 			xas_unlock(&xas);
 			ret = -EIO;
 			goto out;
 		}
 
-		xas.xa_index = 0;
+		/*
+		 * Cyclically find a free xas to avoid msg_id reuse that would
+		 * cause the daemon to successfully copen a stale msg_id.
+		 */
+		xas.xa_index = cache->msg_id_next;
 		xas_find_marked(&xas, UINT_MAX, XA_FREE_MARK);
+		if (xas.xa_node == XAS_RESTART) {
+			xas.xa_index = 0;
+			xas_find_marked(&xas, cache->msg_id_next - 1, XA_FREE_MARK);
+		}
 		if (xas.xa_node == XAS_RESTART)
 			xas_set_err(&xas, -EBUSY);
+
 		xas_store(&xas, req);
-		xas_clear_mark(&xas, XA_FREE_MARK);
-		xas_set_mark(&xas, CACHEFILES_REQ_NEW);
+		if (xas_valid(&xas)) {
+			cache->msg_id_next = xas.xa_index + 1;
+			xas_clear_mark(&xas, XA_FREE_MARK);
+			xas_set_mark(&xas, CACHEFILES_REQ_NEW);
+		}
 		xas_unlock(&xas);
 	} while (xas_nomem(&xas, GFP_KERNEL));
 
···
 	 * If error occurs after creating the anonymous fd,
 	 * cachefiles_ondemand_fd_release() will set object to close.
 	 */
-	if (opcode == CACHEFILES_OP_OPEN)
+	if (opcode == CACHEFILES_OP_OPEN &&
+	    !cachefiles_ondemand_object_is_dropping(object))
 		cachefiles_ondemand_set_object_close(object);
 	kfree(req);
 	return ret;
···
 
 void cachefiles_ondemand_clean_object(struct cachefiles_object *object)
 {
+	unsigned long index;
+	struct cachefiles_req *req;
+	struct cachefiles_cache *cache;
+
+	if (!object->ondemand)
+		return;
+
 	cachefiles_ondemand_send_req(object, CACHEFILES_OP_CLOSE, 0,
 			cachefiles_ondemand_init_close_req, NULL);
+
+	if (!object->ondemand->ondemand_id)
+		return;
+
+	/* Cancel all requests for the object that is being dropped. */
+	cache = object->volume->cache;
+	xa_lock(&cache->reqs);
+	cachefiles_ondemand_set_object_dropping(object);
+	xa_for_each(&cache->reqs, index, req) {
+		if (req->object == object) {
+			req->error = -EIO;
+			complete(&req->done);
+			__xa_erase(&cache->reqs, index);
+		}
+	}
+	xa_unlock(&cache->reqs);
+
+	/* Wait for ondemand_object_worker() to finish to avoid UAF. */
+	cancel_work_sync(&object->ondemand->ondemand_work);
 }
 
 int cachefiles_ondemand_init_obj_info(struct cachefiles_object *object,

fs/cachefiles/volume.c

···
 
 void cachefiles_withdraw_volume(struct cachefiles_volume *volume)
 {
-	fscache_withdraw_volume(volume->vcookie);
 	cachefiles_set_volume_xattr(volume);
 	__cachefiles_free_volume(volume);
 }

fs/cachefiles/xattr.c

···
 	if (xlen == 0)
 		xlen = vfs_getxattr(&nop_mnt_idmap, dentry, cachefiles_xattr_cache, buf, tlen);
 	if (xlen != tlen) {
-		if (xlen < 0)
+		if (xlen < 0) {
+			ret = xlen;
 			trace_cachefiles_vfs_error(object, file_inode(file), xlen,
 						   cachefiles_trace_getxattr_error);
+		}
 		if (xlen == -EIO)
 			cachefiles_io_error_obj(
 				object,
···
 		xlen = vfs_getxattr(&nop_mnt_idmap, dentry, cachefiles_xattr_cache, buf, len);
 	if (xlen != len) {
 		if (xlen < 0) {
+			ret = xlen;
 			trace_cachefiles_vfs_error(NULL, d_inode(dentry), xlen,
 						   cachefiles_trace_getxattr_error);
 			if (xlen == -EIO)

fs/dcache.c

···
 	flags &= ~DCACHE_ENTRY_TYPE;
 	WRITE_ONCE(dentry->d_flags, flags);
 	dentry->d_inode = NULL;
-	if (flags & DCACHE_LRU_LIST)
+	/*
+	 * The negative counter only tracks dentries on the LRU. Don't inc if
+	 * d_lru is on another list.
+	 */
+	if ((flags & (DCACHE_LRU_LIST|DCACHE_SHRINK_LIST)) == DCACHE_LRU_LIST)
 		this_cpu_inc(nr_dentry_negative);
 }
 
···
 
 	spin_lock(&dentry->d_lock);
 	/*
-	 * Decrement negative dentry count if it was in the LRU list.
+	 * The negative counter only tracks dentries on the LRU. Don't dec if
+	 * d_lru is on another list.
 	 */
-	if (dentry->d_flags & DCACHE_LRU_LIST)
+	if ((dentry->d_flags &
+	     (DCACHE_LRU_LIST|DCACHE_SHRINK_LIST)) == DCACHE_LRU_LIST)
 		this_cpu_dec(nr_dentry_negative);
 	hlist_add_head(&dentry->d_u.d_alias, &inode->i_dentry);
 	raw_write_seqcount_begin(&dentry->d_seq);

fs/hfsplus/xattr.c

···
 		return err;
 	}
 
-	strbuf = kmalloc(NLS_MAX_CHARSET_SIZE * HFSPLUS_ATTR_MAX_STRLEN +
+	strbuf = kzalloc(NLS_MAX_CHARSET_SIZE * HFSPLUS_ATTR_MAX_STRLEN +
 			XATTR_MAC_OSX_PREFIX_LEN + 1, GFP_KERNEL);
 	if (!strbuf) {
 		res = -ENOMEM;

fs/locks.c

···
 		locks_wake_up_blocks(&left->c);
 	}
  out:
+	trace_posix_lock_inode(inode, request, error);
 	spin_unlock(&ctx->flc_lock);
 	percpu_up_read(&file_rwsem);
-	trace_posix_lock_inode(inode, request, error);
 	/*
 	 * Free any unused locks.
 	 */

fs/minix/namei.c

···
 		if (!new_de)
 			goto out_dir;
 		err = minix_set_link(new_de, new_page, old_inode);
-		kunmap(new_page);
-		put_page(new_page);
+		unmap_and_put_page(new_page, new_de);
 		if (err)
 			goto out_dir;
 		inode_set_ctime_current(new_inode);

fs/netfs/buffered_read.c

···
 		if (!test_bit(NETFS_RREQ_DONT_UNLOCK_FOLIOS, &rreq->flags)) {
 			if (folio->index == rreq->no_unlock_folio &&
 			    test_bit(NETFS_RREQ_NO_UNLOCK_FOLIO, &rreq->flags))
-				_debug("no unlock");
+				kdebug("no unlock");
 			else
 				folio_unlock(folio);
 		}
···
 	struct netfs_inode *ctx = netfs_inode(ractl->mapping->host);
 	int ret;
 
-	_enter("%lx,%x", readahead_index(ractl), readahead_count(ractl));
+	kenter("%lx,%x", readahead_index(ractl), readahead_count(ractl));
 
 	if (readahead_count(ractl) == 0)
 		return;
···
 	struct folio *sink = NULL;
 	int ret;
 
-	_enter("%lx", folio->index);
+	kenter("%lx", folio->index);
 
 	rreq = netfs_alloc_request(mapping, file,
 				   folio_file_pos(folio), folio_size(folio),
···
 
 have_folio:
 	*_folio = folio;
-	_leave(" = 0");
+	kleave(" = 0");
 	return 0;
 
 error_put:
···
 		folio_unlock(folio);
 		folio_put(folio);
 	}
-	_leave(" = %d", ret);
+	kleave(" = %d", ret);
 	return ret;
 }
 EXPORT_SYMBOL(netfs_write_begin);
···
 	size_t flen = folio_size(folio);
 	int ret;
 
-	_enter("%zx @%llx", flen, start);
+	kenter("%zx @%llx", flen, start);
 
 	ret = -ENOMEM;
 
···
 error_put:
 	netfs_put_request(rreq, false, netfs_rreq_trace_put_discard);
 error:
-	_leave(" = %d", ret);
+	kleave(" = %d", ret);
 	return ret;
 }
 

fs/netfs/buffered_write.c

···
 	struct netfs_group *group = netfs_folio_group(folio);
 	loff_t pos = folio_file_pos(folio);
 
-	_enter("");
+	kenter("");
 
 	if (group != netfs_group && group != NETFS_FOLIO_COPY_TO_CACHE)
 		return NETFS_FLUSH_CONTENT;
···
 		 */
 		howto = netfs_how_to_modify(ctx, file, folio, netfs_group,
 					    flen, offset, part, maybe_trouble);
-		_debug("howto %u", howto);
+		kdebug("howto %u", howto);
 		switch (howto) {
 		case NETFS_JUST_PREFETCH:
 			ret = netfs_prefetch_for_write(file, folio, offset, part);
 			if (ret < 0) {
-				_debug("prefetch = %zd", ret);
+				kdebug("prefetch = %zd", ret);
 				goto error_folio_unlock;
 			}
 			break;
···
 	}
 
 	iocb->ki_pos += written;
-	_leave(" = %zd [%zd]", written, ret);
+	kleave(" = %zd [%zd]", written, ret);
 	return written ? written : ret;
 
 error_folio_unlock:
···
 	struct netfs_inode *ictx = netfs_inode(inode);
 	ssize_t ret;
 
-	_enter("%llx,%zx,%llx", iocb->ki_pos, iov_iter_count(from), i_size_read(inode));
+	kenter("%llx,%zx,%llx", iocb->ki_pos, iov_iter_count(from), i_size_read(inode));
 
 	if (!iov_iter_count(from))
 		return 0;
···
 	vm_fault_t ret = VM_FAULT_RETRY;
 	int err;
 
-	_enter("%lx", folio->index);
+	kenter("%lx", folio->index);
 
 	sb_start_pagefault(inode->i_sb);
 

fs/netfs/direct_read.c

···
 	size_t orig_count = iov_iter_count(iter);
 	bool async = !is_sync_kiocb(iocb);
 
-	_enter("");
+	kenter("");
 
 	if (!orig_count)
 		return 0; /* Don't update atime */

fs/netfs/direct_write.c

···
 	size_t len = iov_iter_count(iter);
 	bool async = !is_sync_kiocb(iocb);
 
-	_enter("");
+	kenter("");
 
 	/* We're going to need a bounce buffer if what we transmit is going to
 	 * be different in some way to the source buffer, e.g. because it gets
···
 	 */
 	// TODO
 
-	_debug("uw %llx-%llx", start, end);
+	kdebug("uw %llx-%llx", start, end);
 
 	wreq = netfs_create_write_req(iocb->ki_filp->f_mapping, iocb->ki_filp, start,
 				      iocb->ki_flags & IOCB_DIRECT ?
···
 	wreq->cleanup = netfs_cleanup_dio_write;
 	ret = netfs_unbuffered_write(wreq, is_sync_kiocb(iocb), wreq->len);
 	if (ret < 0) {
-		_debug("begin = %zd", ret);
+		kdebug("begin = %zd", ret);
 		goto out;
 	}
 
···
 	loff_t pos = iocb->ki_pos;
 	unsigned long long end = pos + iov_iter_count(from) - 1;
 
-	_enter("%llx,%zx,%llx", pos, iov_iter_count(from), i_size_read(inode));
+	kenter("%llx,%zx,%llx", pos, iov_iter_count(from), i_size_read(inode));
 
 	if (!iov_iter_count(from))
 		return 0;

fs/netfs/fscache_cache.c

···
 {
 	int n_accesses;
 
-	_enter("{%s,%s}", ops->name, cache->name);
+	kenter("{%s,%s}", ops->name, cache->name);
 
 	BUG_ON(fscache_cache_state(cache) != FSCACHE_CACHE_IS_PREPARING);
 
···
 
 	up_write(&fscache_addremove_sem);
 	pr_notice("Cache \"%s\" added (type %s)\n", cache->name, ops->name);
-	_leave(" = 0 [%s]", cache->name);
+	kleave(" = 0 [%s]", cache->name);
 	return 0;
 }
 EXPORT_SYMBOL(fscache_add_cache);

fs/netfs/fscache_cookie.c

···
 {
 	struct fscache_cookie *cookie;
 
-	_enter("V=%x", volume->debug_id);
+	kenter("V=%x", volume->debug_id);
 
 	if (!index_key || !index_key_len || index_key_len > 255 || aux_data_len > 255)
 		return NULL;
···
 
 	trace_fscache_acquire(cookie);
 	fscache_stat(&fscache_n_acquires_ok);
-	_leave(" = c=%08x", cookie->debug_id);
+	kleave(" = c=%08x", cookie->debug_id);
 	return cookie;
 }
 EXPORT_SYMBOL(__fscache_acquire_cookie);
···
 	enum fscache_access_trace trace = fscache_access_lookup_cookie_end_failed;
 	bool need_withdraw = false;
 
-	_enter("");
+	kenter("");
 
 	if (!cookie->volume->cache_priv) {
 		fscache_create_volume(cookie->volume, true);
···
 		if (cookie->state != FSCACHE_COOKIE_STATE_FAILED)
 			fscache_set_cookie_state(cookie, FSCACHE_COOKIE_STATE_QUIESCENT);
 		need_withdraw = true;
-		_leave(" [fail]");
+		kleave(" [fail]");
 		goto out;
 	}
 
···
 	bool queue = false;
 	int n_active;
 
-	_enter("c=%08x", cookie->debug_id);
+	kenter("c=%08x", cookie->debug_id);
 
 	if (WARN(test_bit(FSCACHE_COOKIE_RELINQUISHED, &cookie->flags),
 		 "Trying to use relinquished cookie\n"))
···
 	spin_unlock(&cookie->lock);
 	if (queue)
 		fscache_queue_cookie(cookie, fscache_cookie_get_use_work);
-	_leave("");
+	kleave("");
 }
 EXPORT_SYMBOL(__fscache_use_cookie);
 
···
 	enum fscache_cookie_state state;
 	bool wake = false;
 
-	_enter("c=%x", cookie->debug_id);
+	kenter("c=%x", cookie->debug_id);
 
 again:
 	spin_lock(&cookie->lock);
···
 	spin_unlock(&cookie->lock);
 	if (wake)
 		wake_up_cookie_state(cookie);
-	_leave("");
+	kleave("");
 }
 
 static void fscache_cookie_worker(struct work_struct *work)
···
 		set_bit(FSCACHE_COOKIE_DO_LRU_DISCARD, &cookie->flags);
 		spin_unlock(&cookie->lock);
 		fscache_stat(&fscache_n_cookies_lru_expired);
-		_debug("lru c=%x", cookie->debug_id);
+		kdebug("lru c=%x", cookie->debug_id);
 		__fscache_withdraw_cookie(cookie);
 	}
 
···
 	if (retire)
 		fscache_stat(&fscache_n_relinquishes_retire);
 
-	_enter("c=%08x{%d},%d",
+	kenter("c=%08x{%d},%d",
 	       cookie->debug_id, atomic_read(&cookie->n_active), retire);
 
 	if (WARN(test_and_set_bit(FSCACHE_COOKIE_RELINQUISHED, &cookie->flags),
···
 {
 	bool is_caching;
 
-	_enter("c=%x", cookie->debug_id);
+	kenter("c=%x", cookie->debug_id);
 
 	fscache_stat(&fscache_n_invalidates);
 
···
 	case FSCACHE_COOKIE_STATE_INVALIDATING: /* is_still_valid will catch it */
 	default:
 		spin_unlock(&cookie->lock);
-		_leave(" [no %u]", cookie->state);
+		kleave(" [no %u]", cookie->state);
 		return;
 
 	case FSCACHE_COOKIE_STATE_LOOKING_UP:
···
 		fallthrough;
 	case FSCACHE_COOKIE_STATE_CREATING:
 		spin_unlock(&cookie->lock);
-		_leave(" [look %x]", cookie->inval_counter);
+		kleave(" [look %x]", cookie->inval_counter);
 		return;
 
 	case FSCACHE_COOKIE_STATE_ACTIVE:
···
 
 		if (is_caching)
 			fscache_queue_cookie(cookie, fscache_cookie_get_inval_work);
-		_leave(" [inv]");
+		kleave(" [inv]");
 		return;
 	}
 }

fs/netfs/fscache_io.c

···
 
 again:
 	if (!fscache_cache_is_live(cookie->volume->cache)) {
-		_leave(" [broken]");
+		kleave(" [broken]");
 		return false;
 	}
 
 	state = fscache_cookie_state(cookie);
-	_enter("c=%08x{%u},%x", cookie->debug_id, state, want_state);
+	kenter("c=%08x{%u},%x", cookie->debug_id, state, want_state);
 
 	switch (state) {
 	case FSCACHE_COOKIE_STATE_CREATING:
···
 	case FSCACHE_COOKIE_STATE_DROPPED:
 	case FSCACHE_COOKIE_STATE_RELINQUISHING:
 	default:
-		_leave(" [not live]");
+		kleave(" [not live]");
 		return false;
 	}
 
···
 	spin_lock(&cookie->lock);
 
 	state = fscache_cookie_state(cookie);
-	_enter("c=%08x{%u},%x", cookie->debug_id, state, want_state);
+	kenter("c=%08x{%u},%x", cookie->debug_id, state, want_state);
 
 	switch (state) {
 	case FSCACHE_COOKIE_STATE_LOOKING_UP:
···
 	cres->cache_priv = NULL;
 	cres->ops = NULL;
 	fscache_end_cookie_access(cookie, fscache_access_io_not_live);
-	_leave(" = -ENOBUFS");
+	kleave(" = -ENOBUFS");
 	return -ENOBUFS;
 }
 
···
 	if (len == 0)
 		goto abandon;
 
-	_enter("%llx,%zx", start, len);
+	kenter("%llx,%zx", start, len);
 
 	wreq = kzalloc(sizeof(struct fscache_write_request), GFP_NOFS);
 	if (!wreq)

fs/netfs/fscache_main.c

···
  */
 void __exit fscache_exit(void)
 {
-	_enter("");
+	kenter("");
 
 	kmem_cache_destroy(fscache_cookie_jar);
 	fscache_proc_cleanup();

fs/netfs/fscache_volume.c

···
 	return volume;
 }
 
+struct fscache_volume *fscache_try_get_volume(struct fscache_volume *volume,
+					      enum fscache_volume_trace where)
+{
+	int ref;
+
+	if (!__refcount_inc_not_zero(&volume->ref, &ref))
+		return NULL;
+
+	trace_fscache_volume(volume->debug_id, ref + 1, where);
+	return volume;
+}
+EXPORT_SYMBOL(fscache_try_get_volume);
+
 static void fscache_see_volume(struct fscache_volume *volume,
 			       enum fscache_volume_trace where)
 {
···
 	fscache_see_volume(volume, fscache_volume_new_acquire);
 	fscache_stat(&fscache_n_volumes);
 	up_write(&fscache_addremove_sem);
-	_leave(" = v=%x", volume->debug_id);
+	kleave(" = v=%x", volume->debug_id);
 	return volume;
 
 err_vol:
···
 			fscache_free_volume(volume);
 	}
 }
+EXPORT_SYMBOL(fscache_put_volume);
 
 /*
  * Relinquish a volume representation cookie.
···
 {
 	int n_accesses;
 
-	_debug("withdraw V=%x", volume->debug_id);
+	kdebug("withdraw V=%x", volume->debug_id);
 
 	/* Allow wakeups on dec-to-0 */
 	n_accesses = atomic_dec_return(&volume->n_accesses);

fs/netfs/internal.h

···
 /*
  * main.c
  */
-extern unsigned int netfs_debug;
 extern struct list_head netfs_io_requests;
 extern spinlock_t netfs_proc_lock;
 extern mempool_t netfs_request_pool;
···
 
 struct fscache_volume *fscache_get_volume(struct fscache_volume *volume,
 					  enum fscache_volume_trace where);
-void fscache_put_volume(struct fscache_volume *volume,
-			enum fscache_volume_trace where);
 bool fscache_begin_volume_access(struct fscache_volume *volume,
 				 struct fscache_cookie *cookie,
 				 enum fscache_access_trace why);
···
  * debug tracing
  */
 #define dbgprintk(FMT, ...) \
-	printk("[%-6.6s] "FMT"\n", current->comm, ##__VA_ARGS__)
+	pr_debug("[%-6.6s] "FMT"\n", current->comm, ##__VA_ARGS__)
 
 #define kenter(FMT, ...) dbgprintk("==> %s("FMT")", __func__, ##__VA_ARGS__)
 #define kleave(FMT, ...) dbgprintk("<== %s()"FMT"", __func__, ##__VA_ARGS__)
 #define kdebug(FMT, ...) dbgprintk(FMT, ##__VA_ARGS__)
-
-#ifdef __KDEBUG
-#define _enter(FMT, ...) kenter(FMT, ##__VA_ARGS__)
-#define _leave(FMT, ...) kleave(FMT, ##__VA_ARGS__)
-#define _debug(FMT, ...) kdebug(FMT, ##__VA_ARGS__)
-
-#elif defined(CONFIG_NETFS_DEBUG)
-#define _enter(FMT, ...)			\
-do {						\
-	if (netfs_debug)			\
-		kenter(FMT, ##__VA_ARGS__);	\
-} while (0)
-
-#define _leave(FMT, ...)			\
-do {						\
-	if (netfs_debug)			\
-		kleave(FMT, ##__VA_ARGS__);	\
-} while (0)
-
-#define _debug(FMT, ...)			\
-do {						\
-	if (netfs_debug)			\
-		kdebug(FMT, ##__VA_ARGS__);	\
-} while (0)
-
-#else
-#define _enter(FMT, ...) no_printk("==> %s("FMT")", __func__, ##__VA_ARGS__)
-#define _leave(FMT, ...) no_printk("<== %s()"FMT"", __func__, ##__VA_ARGS__)
-#define _debug(FMT, ...) no_printk(FMT, ##__VA_ARGS__)
-#endif
 
 /*
  * assertions

fs/netfs/io.c

···
 	if (count == remaining)
 		return;
 
-	_debug("R=%08x[%u] ITER RESUB-MISMATCH %zx != %zx-%zx-%llx %x\n",
+	kdebug("R=%08x[%u] ITER RESUB-MISMATCH %zx != %zx-%zx-%llx %x\n",
 	       rreq->debug_id, subreq->debug_index,
 	       iov_iter_count(&subreq->io_iter), subreq->transferred,
 	       subreq->len, rreq->i_size,
···
 	struct netfs_io_request *rreq = subreq->rreq;
 	int u;
 
-	_enter("R=%x[%x]{%llx,%lx},%zd",
+	kenter("R=%x[%x]{%llx,%lx},%zd",
 	       rreq->debug_id, subreq->debug_index,
 	       subreq->start, subreq->flags, transferred_or_error);
 
···
 	struct netfs_inode *ictx = netfs_inode(rreq->inode);
 	size_t lsize;
 
-	_enter("%llx-%llx,%llx", subreq->start, subreq->start + subreq->len, rreq->i_size);
+	kenter("%llx-%llx,%llx", subreq->start, subreq->start + subreq->len, rreq->i_size);
 
 	if (rreq->origin != NETFS_DIO_READ) {
 		source = netfs_cache_prepare_read(subreq, rreq->i_size);
···
 	subreq->start		= rreq->start + rreq->submitted;
 	subreq->len		= io_iter->count;
 
-	_debug("slice %llx,%zx,%llx", subreq->start, subreq->len, rreq->submitted);
+	kdebug("slice %llx,%zx,%llx", subreq->start, subreq->len, rreq->submitted);
 	list_add_tail(&subreq->rreq_link, &rreq->subrequests);
 
 	/* Call out to the cache to find out what it can do with the remaining
···
 	struct iov_iter io_iter;
 	int ret;
 
-	_enter("R=%x %llx-%llx",
+	kenter("R=%x %llx-%llx",
 	       rreq->debug_id, rreq->start, rreq->start + rreq->len - 1);
 
 	if (rreq->len == 0) {
···
 	atomic_set(&rreq->nr_outstanding, 1);
 	io_iter = rreq->io_iter;
 	do {
-		_debug("submit %llx + %llx >= %llx",
+		kdebug("submit %llx + %llx >= %llx",
 		       rreq->start, rreq->submitted, rreq->i_size);
 		if (rreq->origin == NETFS_DIO_READ &&
 		    rreq->start + rreq->submitted >= rreq->i_size)

fs/netfs/main.c

···
 
 EXPORT_TRACEPOINT_SYMBOL(netfs_sreq);
 
-unsigned netfs_debug;
-module_param_named(debug, netfs_debug, uint, S_IWUSR | S_IRUGO);
-MODULE_PARM_DESC(netfs_debug, "Netfs support debugging mask");
-
 static struct kmem_cache *netfs_request_slab;
 static struct kmem_cache *netfs_subrequest_slab;
 mempool_t netfs_request_pool;

fs/netfs/misc.c

···
 	struct fscache_cookie *cookie = netfs_i_cookie(ictx);
 	bool need_use = false;
 
-	_enter("");
+	kenter("");
 
 	if (!filemap_dirty_folio(mapping, folio))
 		return false;
···
 	struct netfs_folio *finfo;
 	size_t flen = folio_size(folio);
 
-	_enter("{%lx},%zx,%zx", folio->index, offset, length);
+	kenter("{%lx},%zx,%zx", folio->index, offset, length);
 
 	if (!folio_test_private(folio))
 		return;

fs/netfs/write_collect.c

···
 {
 	struct list_head *next;
 
-	_enter("R=%x[%x:]", wreq->debug_id, stream->stream_nr);
+	kenter("R=%x[%x:]", wreq->debug_id, stream->stream_nr);
 
 	if (list_empty(&stream->subrequests))
 		return;
···
 	unsigned int notes;
 	int s;
 
-	_enter("%llx-%llx", wreq->start, wreq->start + wreq->len);
+	kenter("%llx-%llx", wreq->start, wreq->start + wreq->len);
 	trace_netfs_collect(wreq);
 	trace_netfs_rreq(wreq, netfs_rreq_trace_collect);
 
···
 		front = stream->front;
 		while (front) {
 			trace_netfs_collect_sreq(wreq, front);
-			//_debug("sreq [%x] %llx %zx/%zx",
+			//kdebug("sreq [%x] %llx %zx/%zx",
 			//       front->debug_index, front->start, front->transferred, front->len);
 
 			/* Stall if there may be a discontinuity. */
···
 out:
 	netfs_put_group_many(wreq->group, wreq->nr_group_rel);
 	wreq->nr_group_rel = 0;
-	_leave(" = %x", notes);
+	kleave(" = %x", notes);
 	return;
 
 need_retry:
···
 	 * that any partially completed op will have had any wholly transferred
 	 * folios removed from it.
 	 */
-	_debug("retry");
+	kdebug("retry");
 	netfs_retry_writes(wreq);
 	goto out;
 }
···
 	size_t transferred;
 	int s;
 
-	_enter("R=%x", wreq->debug_id);
+	kenter("R=%x", wreq->debug_id);
 
 	netfs_see_request(wreq, netfs_rreq_trace_see_work);
 	if (!test_bit(NETFS_RREQ_IN_PROGRESS, &wreq->flags)) {
···
 	if (wreq->origin == NETFS_DIO_WRITE)
 		inode_dio_end(wreq->inode);
 
-	_debug("finished");
+	kdebug("finished");
 	trace_netfs_rreq(wreq, netfs_rreq_trace_wake_ip);
 	clear_bit_unlock(NETFS_RREQ_IN_PROGRESS, &wreq->flags);
 	wake_up_bit(&wreq->flags, NETFS_RREQ_IN_PROGRESS);
···
 	struct netfs_io_request *wreq = subreq->rreq;
 	struct netfs_io_stream *stream = &wreq->io_streams[subreq->stream_nr];
 
-	_enter("%x[%x] %zd", wreq->debug_id, subreq->debug_index, transferred_or_error);
+	kenter("%x[%x] %zd", wreq->debug_id, subreq->debug_index, transferred_or_error);
 
 	switch (subreq->source) {
 	case NETFS_UPLOAD_TO_SERVER:

fs/netfs/write_issue.c

···
 	if (IS_ERR(wreq))
 		return wreq;
 
-	_enter("R=%x", wreq->debug_id);
+	kenter("R=%x", wreq->debug_id);
 
 	ictx = netfs_inode(wreq->inode);
 	if (test_bit(NETFS_RREQ_WRITE_TO_CACHE, &wreq->flags))
···
 	subreq->max_nr_segs	= INT_MAX;
 	subreq->stream_nr	= stream->stream_nr;
 
-	_enter("R=%x[%x]", wreq->debug_id, subreq->debug_index);
+	kenter("R=%x[%x]", wreq->debug_id, subreq->debug_index);
 
 	trace_netfs_sreq_ref(wreq->debug_id, subreq->debug_index,
 			     refcount_read(&subreq->ref),
···
 {
 	struct netfs_io_request *wreq = subreq->rreq;
 
-	_enter("R=%x[%x],%zx", wreq->debug_id, subreq->debug_index, subreq->len);
+	kenter("R=%x[%x],%zx", wreq->debug_id, subreq->debug_index, subreq->len);
 
 	if (test_bit(NETFS_SREQ_FAILED, &subreq->flags))
 		return netfs_write_subrequest_terminated(subreq, subreq->error, false);
···
 	size_t part;
 
 	if (!stream->avail) {
-		_leave("no write");
+		kleave("no write");
 		return len;
 	}
 
-	_enter("R=%x[%x]", wreq->debug_id, subreq ? subreq->debug_index : 0);
+	kenter("R=%x[%x]", wreq->debug_id, subreq ? subreq->debug_index : 0);
 
 	if (subreq && start != subreq->start + subreq->len) {
 		netfs_issue_write(wreq, stream);
···
 	subreq = stream->construct;
 
 	part = min(subreq->max_len - subreq->len, len);
-	_debug("part %zx/%zx %zx/%zx", subreq->len, subreq->max_len, part, len);
+	kdebug("part %zx/%zx %zx/%zx", subreq->len, subreq->max_len, part, len);
 	subreq->len += part;
 	subreq->nr_segs++;
 
···
 	bool to_eof = false, streamw = false;
 	bool debug = false;
 
-	_enter("");
+	kenter("");
 
 	/* netfs_perform_write() may shift i_size around the page or from out
 	 * of the page to beyond it, but cannot move i_size into or through the
···
 
 	if (fpos >= i_size) {
 		/* mmap beyond eof. */
-		_debug("beyond eof");
+		kdebug("beyond eof");
 		folio_start_writeback(folio);
 		folio_unlock(folio);
 		wreq->nr_group_rel += netfs_folio_written_back(folio);
···
 	}
 	flen -= foff;
 
-	_debug("folio %zx %zx %zx", foff, flen, fsize);
+	kdebug("folio %zx %zx %zx", foff, flen, fsize);
 
 	/* Deal with discontinuities in the stream of dirty pages.  These can
 	 * arise from a number of sources:
···
 		for (int s = 0; s < NR_IO_STREAMS; s++)
 			netfs_issue_write(wreq, &wreq->io_streams[s]);
 
-	_leave(" = 0");
+	kleave(" = 0");
 	return 0;
 }
 
···
 	netfs_stat(&netfs_n_wh_writepages);
 
 	do {
-		_debug("wbiter %lx %llx", folio->index, wreq->start + wreq->submitted);
+		kdebug("wbiter %lx %llx", folio->index, wreq->start + wreq->submitted);
 
 		/* It appears we don't have to handle cyclic writeback wrapping. */
 		WARN_ON_ONCE(wreq && folio_pos(folio) < wreq->start + wreq->submitted);
···
 	mutex_unlock(&ictx->wb_lock);
 
 	netfs_put_request(wreq, false, netfs_rreq_trace_put_return);
-	_leave(" = %d", error);
+	kleave(" = %d", error);
 	return error;
 
 couldnt_start:
 	netfs_kill_dirty_pages(mapping, wbc, folio);
 out:
 	mutex_unlock(&ictx->wb_lock);
-	_leave(" = %d", error);
+	kleave(" = %d", error);
 	return error;
 }
 EXPORT_SYMBOL(netfs_writepages);
···
 			       struct folio *folio, size_t copied, bool to_page_end,
 			       struct folio **writethrough_cache)
 {
-	_enter("R=%x ic=%zu ws=%u cp=%zu tp=%u",
+	kenter("R=%x ic=%zu ws=%u cp=%zu tp=%u",
 	       wreq->debug_id, wreq->iter.count, wreq->wsize, copied, to_page_end);
 
 	if (!*writethrough_cache) {
···
 	struct netfs_inode *ictx = netfs_inode(wreq->inode);
 	int ret;
 
-	_enter("R=%x", wreq->debug_id);
+	kenter("R=%x", wreq->debug_id);
 
 	if (writethrough_cache)
 		netfs_write_folio(wreq, wbc, writethrough_cache);
···
 	loff_t start = wreq->start;
 	int error = 0;
 
-	_enter("%zx", len);
+	kenter("%zx", len);
 
 	if (wreq->origin == NETFS_DIO_WRITE)
 		inode_dio_begin(wreq->inode);
···
 	while (len) {
 		// TODO: Prepare content encryption
 
-		_debug("unbuffered %zx", len);
+		kdebug("unbuffered %zx", len);
 		part = netfs_advance_write(wreq, upload, start, len, false);
 		start += part;
 		len -= part;
···
 	if (list_empty(&upload->subrequests))
 		netfs_wake_write_collector(wreq, false);
 
-	_leave(" = %d", error);
+	kleave(" = %d", error);
 	return error;
 }

fs/nilfs2/dir.c

···
 
 struct nilfs_dir_entry *nilfs_dotdot(struct inode *dir, struct folio **foliop)
 {
-	struct nilfs_dir_entry *de = nilfs_get_folio(dir, 0, foliop);
+	struct folio *folio;
+	struct nilfs_dir_entry *de, *next_de;
+	size_t limit;
+	char *msg;
 
+	de = nilfs_get_folio(dir, 0, &folio);
 	if (IS_ERR(de))
 		return NULL;
-	return nilfs_next_entry(de);
+
+	limit = nilfs_last_byte(dir, 0);  /* is a multiple of chunk size */
+	if (unlikely(!limit || le64_to_cpu(de->inode) != dir->i_ino ||
+		     !nilfs_match(1, ".", de))) {
+		msg = "missing '.'";
+		goto fail;
+	}
+
+	next_de = nilfs_next_entry(de);
+	/*
+	 * If "next_de" has not reached the end of the chunk, there is
+	 * at least one more record.  Check whether it matches "..".
+	 */
+	if (unlikely((char *)next_de == (char *)de + nilfs_chunk_size(dir) ||
+		     !nilfs_match(2, "..", next_de))) {
+		msg = "missing '..'";
+		goto fail;
+	}
+	*foliop = folio;
+	return next_de;
+
+fail:
+	nilfs_error(dir->i_sb, "directory #%lu %s", dir->i_ino, msg);
+	folio_release_kmap(folio, de);
+	return NULL;
 }
 
 ino_t nilfs_inode_by_name(struct inode *dir, const struct qstr *qstr)

fs/smb/client/file.c

···
 }
 
 /*
- * Expand the size of a readahead to the size of the rsize, if at least as
- * large as a page, allowing for the possibility that rsize is not pow-2
- * aligned.
- */
-static void cifs_expand_readahead(struct netfs_io_request *rreq)
-{
-	unsigned int rsize = rreq->rsize;
-	loff_t misalignment, i_size = i_size_read(rreq->inode);
-
-	if (rsize < PAGE_SIZE)
-		return;
-
-	if (rsize < INT_MAX)
-		rsize = roundup_pow_of_two(rsize);
-	else
-		rsize = ((unsigned int)INT_MAX + 1) / 2;
-
-	misalignment = rreq->start & (rsize - 1);
-	if (misalignment) {
-		rreq->start -= misalignment;
-		rreq->len += misalignment;
-	}
-
-	rreq->len = round_up(rreq->len, rsize);
-	if (rreq->start < i_size && rreq->len > i_size - rreq->start)
-		rreq->len = i_size - rreq->start;
-}
-
-/*
  * Completion of a request operation.
  */
 static void cifs_rreq_done(struct netfs_io_request *rreq)
···
 	.init_request		= cifs_init_request,
 	.free_request		= cifs_free_request,
 	.free_subrequest	= cifs_free_subrequest,
-	.expand_readahead	= cifs_expand_readahead,
 	.clamp_length		= cifs_clamp_length,
 	.issue_read		= cifs_req_issue_read,
 	.done			= cifs_rreq_done,

fs/smb/common/smb2pdu.h

···
 	__u8   Buffer[];
 } __packed;
 
+/* DeviceType Flags */
+#define FILE_DEVICE_CD_ROM              0x00000002
+#define FILE_DEVICE_CD_ROM_FILE_SYSTEM  0x00000003
+#define FILE_DEVICE_DFS                 0x00000006
+#define FILE_DEVICE_DISK                0x00000007
+#define FILE_DEVICE_DISK_FILE_SYSTEM    0x00000008
+#define FILE_DEVICE_FILE_SYSTEM         0x00000009
+#define FILE_DEVICE_NAMED_PIPE          0x00000011
+#define FILE_DEVICE_NETWORK             0x00000012
+#define FILE_DEVICE_NETWORK_FILE_SYSTEM 0x00000014
+#define FILE_DEVICE_NULL                0x00000015
+#define FILE_DEVICE_PARALLEL_PORT       0x00000016
+#define FILE_DEVICE_PRINTER             0x00000018
+#define FILE_DEVICE_SERIAL_PORT         0x0000001b
+#define FILE_DEVICE_STREAMS             0x0000001e
+#define FILE_DEVICE_TAPE                0x0000001f
+#define FILE_DEVICE_TAPE_FILE_SYSTEM    0x00000020
+#define FILE_DEVICE_VIRTUAL_DISK        0x00000024
+#define FILE_DEVICE_NETWORK_REDIRECTOR  0x00000028
+
+/* Device Characteristics */
+#define FILE_REMOVABLE_MEDIA			0x00000001
+#define FILE_READ_ONLY_DEVICE			0x00000002
+#define FILE_FLOPPY_DISKETTE			0x00000004
+#define FILE_WRITE_ONCE_MEDIA			0x00000008
+#define FILE_REMOTE_DEVICE			0x00000010
+#define FILE_DEVICE_IS_MOUNTED			0x00000020
+#define FILE_VIRTUAL_VOLUME			0x00000040
+#define FILE_DEVICE_SECURE_OPEN			0x00000100
+#define FILE_CHARACTERISTIC_TS_DEVICE		0x00001000
+#define FILE_CHARACTERISTIC_WEBDAV_DEVICE	0x00002000
+#define FILE_PORTABLE_DEVICE			0x00004000
+#define FILE_DEVICE_ALLOW_APPCONTAINER_TRAVERSAL 0x00020000
+
 /*
  * Maximum number of iovs we need for a set-info request.
  * The largest one is rename/hardlink

fs/smb/server/smb2pdu.c

···
  * @access:		file access flags
  * @disposition:	file disposition flags
  * @may_flags:		set with MAY_ flags
+ * @is_dir:		is creating open flags for directory
  *
  * Return:      file open flags
  */
 static int smb2_create_open_flags(bool file_present, __le32 access,
 				  __le32 disposition,
-				  int *may_flags)
+				  int *may_flags,
+				  bool is_dir)
 {
 	int oflags = O_NONBLOCK | O_LARGEFILE;
+
+	if (is_dir) {
+		access &= ~FILE_WRITE_DESIRE_ACCESS_LE;
+		ksmbd_debug(SMB, "Discard write access to a directory\n");
+	}
 
 	if (access & FILE_READ_DESIRED_ACCESS_LE &&
 	    access & FILE_WRITE_DESIRE_ACCESS_LE) {
···
 
 	open_flags = smb2_create_open_flags(file_present, daccess,
 					    req->CreateDisposition,
-					    &may_flags);
+					    &may_flags,
+		req->CreateOptions & FILE_DIRECTORY_FILE_LE ||
+		(file_present && S_ISDIR(d_inode(path.dentry)->i_mode)));
 
 	if (!test_tree_conn_flag(tcon, KSMBD_TREE_CONN_FLAG_WRITABLE)) {
 		if (open_flags & (O_CREAT | O_TRUNC)) {
···
 
 		info = (struct filesystem_device_info *)rsp->Buffer;
 
-		info->DeviceType = cpu_to_le32(stfs.f_type);
-		info->DeviceCharacteristics = cpu_to_le32(0x00000020);
+		info->DeviceType = cpu_to_le32(FILE_DEVICE_DISK);
+		info->DeviceCharacteristics =
+			cpu_to_le32(FILE_DEVICE_IS_MOUNTED);
+		if (!test_tree_conn_flag(work->tcon,
+					 KSMBD_TREE_CONN_FLAG_WRITABLE))
+			info->DeviceCharacteristics |=
+				cpu_to_le32(FILE_READ_ONLY_DEVICE);
 		rsp->OutputBufferLength = cpu_to_le32(8);
 		break;
 	}

fs/userfaultfd.c

···
 		goto out;
 	features = uffdio_api.features;
 	ret = -EINVAL;
-	if (uffdio_api.api != UFFD_API || (features & ~UFFD_API_FEATURES))
+	if (uffdio_api.api != UFFD_API)
 		goto err_out;
 	ret = -EPERM;
 	if ((features & UFFD_FEATURE_EVENT_FORK) && !capable(CAP_SYS_PTRACE))
···
 	uffdio_api.features &= ~UFFD_FEATURE_WP_UNPOPULATED;
 	uffdio_api.features &= ~UFFD_FEATURE_WP_ASYNC;
 #endif
+
+	ret = -EINVAL;
+	if (features & ~uffdio_api.features)
+		goto err_out;
+
 	uffdio_api.ioctls = UFFD_API_IOCTLS;
 	ret = -EFAULT;
 	if (copy_to_user(buf, &uffdio_api, sizeof(uffdio_api)))

include/linux/closure.h

···
 #ifdef CONFIG_DEBUG_CLOSURES
 #define CLOSURE_MAGIC_DEAD	0xc054dead
 #define CLOSURE_MAGIC_ALIVE	0xc054a11e
+#define CLOSURE_MAGIC_STACK	0xc05451cc
 
 	unsigned int		magic;
 	struct list_head	all;
···
 {
 	memset(cl, 0, sizeof(struct closure));
 	atomic_set(&cl->remaining, CLOSURE_REMAINING_INITIALIZER);
+#ifdef CONFIG_DEBUG_CLOSURES
+	cl->magic = CLOSURE_MAGIC_STACK;
+#endif
 }
 
 static inline void closure_init_stack_release(struct closure *cl)
 {
 	memset(cl, 0, sizeof(struct closure));
 	atomic_set_release(&cl->remaining, CLOSURE_REMAINING_INITIALIZER);
+#ifdef CONFIG_DEBUG_CLOSURES
+	cl->magic = CLOSURE_MAGIC_STACK;
+#endif
 }
 
 /**

include/linux/fscache-cache.h

···
 enum fscache_cache_trace;
 enum fscache_cookie_trace;
 enum fscache_access_trace;
+enum fscache_volume_trace;
 
 enum fscache_cache_state {
 	FSCACHE_CACHE_IS_NOT_PRESENT,	/* No cache is present for this name */
···
 
 extern void fscache_io_error(struct fscache_cache *cache);
 
+extern struct fscache_volume *
+fscache_try_get_volume(struct fscache_volume *volume,
+		       enum fscache_volume_trace where);
+extern void fscache_put_volume(struct fscache_volume *volume,
+			       enum fscache_volume_trace where);
 extern void fscache_end_volume_access(struct fscache_volume *volume,
 				      struct fscache_cookie *cookie,
 				      enum fscache_access_trace why);

include/linux/mmzone.h

···
 static inline int pfn_section_valid(struct mem_section *ms, unsigned long pfn)
 {
 	int idx = subsection_map_index(pfn);
+	struct mem_section_usage *usage = READ_ONCE(ms->usage);
 
-	return test_bit(idx, READ_ONCE(ms->usage)->subsection_map);
+	return usage ? test_bit(idx, usage->subsection_map) : 0;
 }
 #else
 static inline int pfn_section_valid(struct mem_section *ms, unsigned long pfn)

include/linux/page_ref.h

···
 
 static inline bool page_ref_add_unless(struct page *page, int nr, int u)
 {
-	bool ret = atomic_add_unless(&page->_refcount, nr, u);
+	bool ret = false;
+
+	rcu_read_lock();
+	/* avoid writing to the vmemmap area being remapped */
+	if (!page_is_fake_head(page) && page_ref_count(page) != u)
+		ret = atomic_add_unless(&page->_refcount, nr, u);
+	rcu_read_unlock();
 
 	if (page_ref_tracepoint_active(page_ref_mod_unless))
 		__page_ref_mod_unless(page, nr, ret);
···
 	return folio_ref_add_unless(folio, 1, 0);
 }
 
-static inline bool folio_ref_try_add_rcu(struct folio *folio, int count)
+static inline bool folio_ref_try_add(struct folio *folio, int count)
 {
-#ifdef CONFIG_TINY_RCU
-	/*
-	 * The caller guarantees the folio will not be freed from interrupt
-	 * context, so (on !SMP) we only need preemption to be disabled
-	 * and TINY_RCU does that for us.
-	 */
-# ifdef CONFIG_PREEMPT_COUNT
-	VM_BUG_ON(!in_atomic() && !irqs_disabled());
-# endif
-	VM_BUG_ON_FOLIO(folio_ref_count(folio) == 0, folio);
-	folio_ref_add(folio, count);
-#else
-	if (unlikely(!folio_ref_add_unless(folio, count, 0))) {
-		/* Either the folio has been freed, or will be freed. */
-		return false;
-	}
-#endif
-	return true;
-}
-
-/**
- * folio_try_get_rcu - Attempt to increase the refcount on a folio.
- * @folio: The folio.
- *
- * This is a version of folio_try_get() optimised for non-SMP kernels.
- * If you are still holding the rcu_read_lock() after looking up the
- * page and know that the page cannot have its refcount decreased to
- * zero in interrupt context, you can use this instead of folio_try_get().
- *
- * Example users include get_user_pages_fast() (as pages are not unmapped
- * from interrupt context) and the page cache lookups (as pages are not
- * truncated from interrupt context).  We also know that pages are not
- * frozen in interrupt context for the purposes of splitting or migration.
- *
- * You can also use this function if you're holding a lock that prevents
- * pages being frozen & removed; eg the i_pages lock for the page cache
- * or the mmap_lock or page table lock for page tables.  In this case,
- * it will always succeed, and you could have used a plain folio_get(),
- * but it's sometimes more convenient to have a common function called
- * from both locked and RCU-protected contexts.
- *
- * Return: True if the reference count was successfully incremented.
- */
-static inline bool folio_try_get_rcu(struct folio *folio)
-{
-	return folio_ref_try_add_rcu(folio, 1);
+	return folio_ref_add_unless(folio, count, 0);
 }
 
 static inline int page_ref_freeze(struct page *page, int count)

include/linux/pagemap.h

···
  * a good order (that's 1MB if you're using 4kB pages)
  */
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
-#define MAX_PAGECACHE_ORDER	HPAGE_PMD_ORDER
+#define PREFERRED_MAX_PAGECACHE_ORDER	HPAGE_PMD_ORDER
 #else
-#define MAX_PAGECACHE_ORDER	8
+#define PREFERRED_MAX_PAGECACHE_ORDER	8
 #endif
+
+/*
+ * xas_split_alloc() does not support arbitrary orders. This implies no
+ * 512MB THP on ARM64 with 64KB base page size.
+ */
+#define MAX_XAS_ORDER		(XA_CHUNK_SHIFT * 2 - 1)
+#define MAX_PAGECACHE_ORDER	min(MAX_XAS_ORDER, PREFERRED_MAX_PAGECACHE_ORDER)
 
 /**
  * mapping_set_large_folios() - Indicate the file supports large folios.

include/linux/sched.h

···
 extern void sched_set_stop_task(int cpu, struct task_struct *stop);
 
 #ifdef CONFIG_MEM_ALLOC_PROFILING
-static inline struct alloc_tag *alloc_tag_save(struct alloc_tag *tag)
+static __always_inline struct alloc_tag *alloc_tag_save(struct alloc_tag *tag)
 {
 	swap(current->alloc_tag, tag);
 	return tag;
 }
 
-static inline void alloc_tag_restore(struct alloc_tag *tag, struct alloc_tag *old)
+static __always_inline void alloc_tag_restore(struct alloc_tag *tag, struct alloc_tag *old)
 {
 #ifdef CONFIG_MEM_ALLOC_PROFILING_DEBUG
 	WARN(current->alloc_tag != tag, "current->alloc_tag was changed:\n");

include/linux/swap.h

···
 }
 
 /* linux/mm/workingset.c */
-bool workingset_test_recent(void *shadow, bool file, bool *workingset);
+bool workingset_test_recent(void *shadow, bool file, bool *workingset,
+				bool flush);
 void workingset_age_nonresident(struct lruvec *lruvec, unsigned long nr_pages);
 void *workingset_eviction(struct folio *folio, struct mem_cgroup *target_memcg);
 void workingset_refault(struct folio *folio, void *shadow);

include/linux/tpm.h

···
 {
 }
 #endif
-#ifdef CONFIG_TCG_TPM2_HMAC
 
-int tpm2_start_auth_session(struct tpm_chip *chip);
+static inline struct tpm2_auth *tpm2_chip_auth(struct tpm_chip *chip)
+{
+#ifdef CONFIG_TCG_TPM2_HMAC
+	return chip->auth;
+#else
+	return NULL;
+#endif
+}
+
 void tpm_buf_append_name(struct tpm_chip *chip, struct tpm_buf *buf,
 			 u32 handle, u8 *name);
 void tpm_buf_append_hmac_session(struct tpm_chip *chip, struct tpm_buf *buf,
···
 						   u8 *passphrase,
 						   int passphraselen)
 {
-	tpm_buf_append_hmac_session(chip, buf, attributes, passphrase,
-				    passphraselen);
+	struct tpm_header *head;
+	int offset;
+
+	if (tpm2_chip_auth(chip)) {
+		tpm_buf_append_hmac_session(chip, buf, attributes, passphrase, passphraselen);
+	} else  {
+		offset = buf->handles * 4 + TPM_HEADER_SIZE;
+		head = (struct tpm_header *)buf->data;
+
+		/*
+		 * If the only sessions are optional, the command tag must change to
+		 * TPM2_ST_NO_SESSIONS.
+		 */
+		if (tpm_buf_length(buf) == offset)
+			head->tag = cpu_to_be16(TPM2_ST_NO_SESSIONS);
+	}
 }
+
+#ifdef CONFIG_TCG_TPM2_HMAC
+
+int tpm2_start_auth_session(struct tpm_chip *chip);
 void tpm_buf_fill_hmac_session(struct tpm_chip *chip, struct tpm_buf *buf);
 int tpm_buf_check_hmac_response(struct tpm_chip *chip, struct tpm_buf *buf,
 				int rc);
···
 }
 static inline void tpm2_end_auth_session(struct tpm_chip *chip)
 {
-}
-static inline void tpm_buf_append_name(struct tpm_chip *chip,
-				       struct tpm_buf *buf,
-				       u32 handle, u8 *name)
-{
-	tpm_buf_append_u32(buf, handle);
-	/* count the number of handles in the upper bits of flags */
-	buf->handles++;
-}
-static inline void tpm_buf_append_hmac_session(struct tpm_chip *chip,
-					       struct tpm_buf *buf,
-					       u8 attributes, u8 *passphrase,
-					       int passphraselen)
-{
-	/* offset tells us where the sessions area begins */
-	int offset = buf->handles * 4 + TPM_HEADER_SIZE;
-	u32 len = 9 + passphraselen;
-
-	if (tpm_buf_length(buf) != offset) {
-		/* not the first session so update the existing length */
-		len += get_unaligned_be32(&buf->data[offset]);
-		put_unaligned_be32(len, &buf->data[offset]);
-	} else {
-		tpm_buf_append_u32(buf, len);
-	}
-	/* auth handle */
-	tpm_buf_append_u32(buf, TPM2_RS_PW);
-	/* nonce */
-	tpm_buf_append_u16(buf, 0);
-	/* attributes */
-	tpm_buf_append_u8(buf, 0);
-	/* passphrase */
-	tpm_buf_append_u16(buf, passphraselen);
-	tpm_buf_append(buf, passphrase, passphraselen);
-}
-static inline void tpm_buf_append_hmac_session_opt(struct tpm_chip *chip,
-						   struct tpm_buf *buf,
-						   u8 attributes,
-						   u8 *passphrase,
-						   int passphraselen)
-{
-	int offset = buf->handles * 4 + TPM_HEADER_SIZE;
-	struct tpm_header *head = (struct tpm_header *) buf->data;
-
-	/*
-	 * if the only sessions are optional, the command tag
-	 * must change to TPM2_ST_NO_SESSIONS
-	 */
-	if (tpm_buf_length(buf) == offset)
-		head->tag = cpu_to_be16(TPM2_ST_NO_SESSIONS);
 }
 static inline void tpm_buf_fill_hmac_session(struct tpm_chip *chip,
 					     struct tpm_buf *buf)

include/net/tcx.h

···
 struct tcx_entry {
 	struct mini_Qdisc __rcu *miniq;
 	struct bpf_mprog_bundle bundle;
-	bool miniq_active;
+	u32 miniq_active;
 	struct rcu_head rcu;
 };
 
···
 	tcx_dec();
 }
 
-static inline void tcx_miniq_set_active(struct bpf_mprog_entry *entry,
-					const bool active)
+static inline void tcx_miniq_inc(struct bpf_mprog_entry *entry)
 {
 	ASSERT_RTNL();
-	tcx_entry(entry)->miniq_active = active;
+	tcx_entry(entry)->miniq_active++;
+}
+
+static inline void tcx_miniq_dec(struct bpf_mprog_entry *entry)
+{
+	ASSERT_RTNL();
+	tcx_entry(entry)->miniq_active--;
 }
 
 static inline bool tcx_entry_is_active(struct bpf_mprog_entry *entry)

include/trace/events/fscache.h

···
 	fscache_volume_get_cookie,
 	fscache_volume_get_create_work,
 	fscache_volume_get_hash_collision,
+	fscache_volume_get_withdraw,
 	fscache_volume_free,
 	fscache_volume_new_acquire,
 	fscache_volume_put_cookie,
 	fscache_volume_put_create_work,
 	fscache_volume_put_hash_collision,
 	fscache_volume_put_relinquish,
+	fscache_volume_put_withdraw,
 	fscache_volume_see_create_work,
 	fscache_volume_see_hash_wake,
 	fscache_volume_wait_create_work,
···
 	EM(fscache_volume_get_cookie,		"GET cook ")		\
 	EM(fscache_volume_get_create_work,	"GET creat")		\
 	EM(fscache_volume_get_hash_collision,	"GET hcoll")		\
+	EM(fscache_volume_get_withdraw,		"GET withd")            \
 	EM(fscache_volume_free,			"FREE     ")		\
 	EM(fscache_volume_new_acquire,		"NEW acq  ")		\
 	EM(fscache_volume_put_cookie,		"PUT cook ")		\
 	EM(fscache_volume_put_create_work,	"PUT creat")		\
 	EM(fscache_volume_put_hash_collision,	"PUT hcoll")		\
 	EM(fscache_volume_put_relinquish,	"PUT relnq")		\
+	EM(fscache_volume_put_withdraw,		"PUT withd")            \
 	EM(fscache_volume_see_create_work,	"SEE creat")		\
 	EM(fscache_volume_see_hash_wake,	"SEE hwake")		\
 	E_(fscache_volume_wait_create_work,	"WAIT crea")

include/uapi/drm/panthor_drm.h

···
 	 * Must be 64-bit/8-byte aligned (the size of a CS instruction)
 	 *
 	 * Can be zero if stream_addr is zero too.
+	 *
+	 * When the stream size is zero, the queue submit serves as a
+	 * synchronization point.
 	 */
 	__u32 stream_size;
 
···
 	 * ensure the GPU doesn't get garbage when reading the indirect command
 	 * stream buffers. If you want the cache flush to happen
 	 * unconditionally, pass a zero here.
+	 *
+	 * Ignored when stream_size is zero.
 	 */
 	__u32 latest_flush;
 

kernel/bpf/helpers.c

···
 	struct bpf_prog *prog;
 	void __rcu *callback_fn;
 	void *value;
-	struct rcu_head rcu;
+	union {
+		struct rcu_head rcu;
+		struct work_struct delete_work;
+	};
 	u64 flags;
 };
 
···
 struct bpf_hrtimer {
 	struct bpf_async_cb cb;
 	struct hrtimer timer;
+	atomic_t cancelling;
 };
 
 struct bpf_work {
···
 	kfree_rcu(w, cb.rcu);
 }
 
+static void bpf_timer_delete_work(struct work_struct *work)
+{
+	struct bpf_hrtimer *t = container_of(work, struct bpf_hrtimer, cb.delete_work);
+
+	/* Cancel the timer and wait for callback to complete if it was running.
+	 * If hrtimer_cancel() can be safely called it's safe to call
+	 * kfree_rcu(t) right after for both preallocated and non-preallocated
+	 * maps.  The async->cb = NULL was already done and no code path can see
+	 * address 't' anymore. Timer if armed for existing bpf_hrtimer before
+	 * bpf_timer_cancel_and_free will have been cancelled.
+	 */
+	hrtimer_cancel(&t->timer);
+	kfree_rcu(t, cb.rcu);
+}
+
 static int __bpf_async_init(struct bpf_async_kern *async, struct bpf_map *map, u64 flags,
 			    enum bpf_async_type type)
 {
···
 		clockid = flags & (MAX_CLOCKS - 1);
 		t = (struct bpf_hrtimer *)cb;
 
+		atomic_set(&t->cancelling, 0);
+		INIT_WORK(&t->cb.delete_work, bpf_timer_delete_work);
 		hrtimer_init(&t->timer, clockid, HRTIMER_MODE_REL_SOFT);
 		t->timer.function = bpf_timer_cb;
 		cb->value = (void *)async - map->record->timer_off;
···
 
 BPF_CALL_1(bpf_timer_cancel, struct bpf_async_kern *, timer)
 {
-	struct bpf_hrtimer *t;
+	struct bpf_hrtimer *t, *cur_t;
+	bool inc = false;
 	int ret = 0;
 
 	if (in_nmi())
···
 		ret = -EINVAL;
 		goto out;
 	}
-	if (this_cpu_read(hrtimer_running) == t) {
+
+	cur_t = this_cpu_read(hrtimer_running);
+	if (cur_t == t) {
 		/* If bpf callback_fn is trying to bpf_timer_cancel()
 		 * its own timer the hrtimer_cancel() will deadlock
-		 * since it waits for callback_fn to finish
+		 * since it waits for callback_fn to finish.
 		 */
 		ret = -EDEADLK;
 		goto out;
 	}
+
+	/* Only account in-flight cancellations when invoked from a timer
+	 * callback, since we want to avoid waiting only if other _callbacks_
+	 * are waiting on us, to avoid introducing lockups. Non-callback paths
+	 * are ok, since nobody would synchronously wait for their completion.
+	 */
+	if (!cur_t)
+		goto drop;
+	atomic_inc(&t->cancelling);
+	/* Need full barrier after relaxed atomic_inc */
+	smp_mb__after_atomic();
+	inc = true;
+	if (atomic_read(&cur_t->cancelling)) {
+		/* We're cancelling timer t, while some other timer callback is
+		 * attempting to cancel us. In such a case, it might be possible
+		 * that timer t belongs to the other callback, or some other
+		 * callback waiting upon it (creating transitive dependencies
+		 * upon us), and we will enter a deadlock if we continue
+		 * cancelling and waiting for it synchronously, since it might
+		 * do the same. Bail!
+		 */
+		ret = -EDEADLK;
+		goto out;
+	}
+drop:
 	drop_prog_refcnt(&t->cb);
 out:
 	__bpf_spin_unlock_irqrestore(&timer->lock);
···
 	 * if it was running.
 	 */
 	ret = ret ?: hrtimer_cancel(&t->timer);
+	if (inc)
+		atomic_dec(&t->cancelling);
 	rcu_read_unlock();
 	return ret;
 }
···
 
 	if (!t)
 		return;
-	/* Cancel the timer and wait for callback to complete if it was running.
-	 * If hrtimer_cancel() can be safely called it's safe to call kfree(t)
-	 * right after for both preallocated and non-preallocated maps.
-	 * The async->cb = NULL was already done and no code path can
-	 * see address 't' anymore.
-	 *
-	 * Check that bpf_map_delete/update_elem() wasn't called from timer
-	 * callback_fn. In such case don't call hrtimer_cancel() (since it will
-	 * deadlock) and don't call hrtimer_try_to_cancel() (since it will just
-	 * return -1). Though callback_fn is still running on this cpu it's
+	/* We check that bpf_map_delete/update_elem() was called from timer
+	 * callback_fn. In such case we don't call hrtimer_cancel() (since it
+	 * will deadlock) and don't call hrtimer_try_to_cancel() (since it will
+	 * just return -1). Though callback_fn is still running on this cpu it's
 	 * safe to do kfree(t) because bpf_timer_cb() read everything it needed
 	 * from 't'. The bpf subprog callback_fn won't be able to access 't',
 	 * since async->cb = NULL was already done. The timer will be
 	 * effectively cancelled because bpf_timer_cb() will return
 	 * HRTIMER_NORESTART.
+	 *
+	 * However, it is possible the timer callback_fn calling us armed the
+	 * timer _before_ calling us, such that failing to cancel it here will
+	 * cause it to possibly use struct hrtimer after freeing bpf_hrtimer.
+	 * Therefore, we _need_ to cancel any outstanding timers before we do
+	 * kfree_rcu, even though no more timers can be armed.
+	 *
+	 * Moreover, we need to schedule work even if timer does not belong to
+	 * the calling callback_fn, as on two different CPUs, we can end up in a
+	 * situation where both sides run in parallel, try to cancel one
+	 * another, and we end up waiting on both sides in hrtimer_cancel
+	 * without making forward progress, since timer1 depends on time2
+	 * callback to finish, and vice versa.
+	 *
+	 *  CPU 1 (timer1_cb)			CPU 2 (timer2_cb)
+	 *  bpf_timer_cancel_and_free(timer2)	bpf_timer_cancel_and_free(timer1)
+	 *
+	 * To avoid these issues, punt to workqueue context when we are in a
+	 * timer callback.
 	 */
-	if (this_cpu_read(hrtimer_running) != t)
-		hrtimer_cancel(&t->timer);
-	kfree_rcu(t, cb.rcu);
+	if (this_cpu_read(hrtimer_running))
+		queue_work(system_unbound_wq, &t->cb.delete_work);
+	else
+		bpf_timer_delete_work(&t->cb.delete_work);
 }
 
 /* This function is called by map_delete/update_elem for individual element and

lib/build_OID_registry

···
 #
 open C_FILE, ">$ARGV[1]" or die;
 print C_FILE "/*\n";
-print C_FILE " * Automatically generated by ", $0 =~ s#^\Q$abs_srctree/\E##r, ".  Do not edit\n";
+my $scriptname = $0;
+$scriptname =~ s#^\Q$abs_srctree/\E##;
+print C_FILE " * Automatically generated by ", $scriptname, ".  Do not edit\n";
 print C_FILE " */\n";
 
 #

lib/closure.c

···
 {
 	unsigned long flags;
 
+	if (cl->magic == CLOSURE_MAGIC_STACK)
+		return;
+
 	BUG_ON(cl->magic != CLOSURE_MAGIC_ALIVE);
 	cl->magic = CLOSURE_MAGIC_DEAD;
 

mm/damon/core.c

···
  * access frequencies are similar.  This is for minimizing the monitoring
  * overhead under the dynamically changeable access pattern.  If a merge was
  * unnecessarily made, later 'kdamond_split_regions()' will revert it.
+ *
+ * The total number of regions could be higher than the user-defined limit,
+ * max_nr_regions for some cases.  For example, the user can update
+ * max_nr_regions to a number that lower than the current number of regions
+ * while DAMON is running.  For such a case, repeat merging until the limit is
+ * met while increasing @threshold up to possible maximum level.
  */
 static void kdamond_merge_regions(struct damon_ctx *c, unsigned int threshold,
 				  unsigned long sz_limit)
 {
 	struct damon_target *t;
+	unsigned int nr_regions;
+	unsigned int max_thres;
 
-	damon_for_each_target(t, c)
-		damon_merge_regions_of(t, threshold, sz_limit);
+	max_thres = c->attrs.aggr_interval /
+		(c->attrs.sample_interval ?  c->attrs.sample_interval : 1);
+	do {
+		nr_regions = 0;
+		damon_for_each_target(t, c) {
+			damon_merge_regions_of(t, threshold, sz_limit);
+			nr_regions += damon_nr_regions(t);
+		}
+		threshold = max(1, threshold * 2);
+	} while (nr_regions > c->attrs.max_nr_regions &&
+			threshold / 2 < max_thres);
 }
 
 /*

mm/filemap.c

···
 	if (!folio || xa_is_value(folio))
 		goto out;
 
-	if (!folio_try_get_rcu(folio))
+	if (!folio_try_get(folio))
 		goto repeat;
 
 	if (unlikely(folio != xas_reload(&xas))) {
···
 	if (!folio || xa_is_value(folio))
 		return folio;
 
-	if (!folio_try_get_rcu(folio))
+	if (!folio_try_get(folio))
 		goto reset;
 
 	if (unlikely(folio != xas_reload(xas))) {
···
 		if (xa_is_value(folio))
 			goto update_start;
 
-		if (!folio_try_get_rcu(folio))
+		if (!folio_try_get(folio))
 			goto retry;
 
 		if (unlikely(folio != xas_reload(&xas)))
···
 			break;
 		if (xa_is_sibling(folio))
 			break;
-		if (!folio_try_get_rcu(folio))
+		if (!folio_try_get(folio))
 			goto retry;
 
 		if (unlikely(folio != xas_reload(&xas)))
···
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 	/* Use the readahead code, even if readahead is disabled */
-	if (vm_flags & VM_HUGEPAGE) {
+	if ((vm_flags & VM_HUGEPAGE) && HPAGE_PMD_ORDER <= MAX_PAGECACHE_ORDER) {
 		fpin = maybe_unlock_mmap_for_io(vmf, fpin);
 		ractl._index &= ~((unsigned long)HPAGE_PMD_NR - 1);
 		ra->size = HPAGE_PMD_NR;
···
 	if (!(vmf->flags & FAULT_FLAG_ORIG_PTE_VALID))
 		return 0;
 
-	ptep = pte_offset_map(vmf->pmd, vmf->address);
+	ptep = pte_offset_map_nolock(vma->vm_mm, vmf->pmd, vmf->address,
+				     &vmf->ptl);
 	if (unlikely(!ptep))
 		return VM_FAULT_NOPAGE;
 
···
 			continue;
 		if (folio_test_locked(folio))
 			continue;
-		if (!folio_try_get_rcu(folio))
+		if (!folio_try_get(folio))
 			continue;
 		/* Has the page moved or been split? */
 		if (unlikely(folio != xas_reload(xas)))
···
 	XA_STATE(xas, &mapping->i_pages, first_index);
 	struct folio *folio;
 
+	/* Flush stats (and potentially sleep) outside the RCU read section. */
+	mem_cgroup_flush_stats_ratelimited(NULL);
+
 	rcu_read_lock();
 	xas_for_each(&xas, folio, last_index) {
 		int order;
···
 					goto resched;
 			}
 #endif
-			if (workingset_test_recent(shadow, true, &workingset))
+			if (workingset_test_recent(shadow, true, &workingset, false))
 				cs->nr_recently_evicted += nr_pages;
 
 			goto resched;

mm/gup.c

···
 	folio = page_folio(page);
 	if (WARN_ON_ONCE(folio_ref_count(folio) < 0))
 		return NULL;
-	if (unlikely(!folio_ref_try_add_rcu(folio, refs)))
+	if (unlikely(!folio_ref_try_add(folio, refs)))
 		return NULL;
 
 	/*
···
 			folio_put_refs(folio, refs);
 		goto retry;
 	}
-
-	return folio;
-}
-
-/**
- * try_grab_folio() - Attempt to get or pin a folio.
- * @page:  pointer to page to be grabbed
- * @refs:  the value to (effectively) add to the folio's refcount
- * @flags: gup flags: these are the FOLL_* flag values.
- *
- * "grab" names in this file mean, "look at flags to decide whether to use
- * FOLL_PIN or FOLL_GET behavior, when incrementing the folio's refcount.
- *
- * Either FOLL_PIN or FOLL_GET (or neither) must be set, but not both at the
- * same time. (That's true throughout the get_user_pages*() and
- * pin_user_pages*() APIs.) Cases:
- *
- *    FOLL_GET: folio's refcount will be incremented by @refs.
- *
- *    FOLL_PIN on large folios: folio's refcount will be incremented by
- *    @refs, and its pincount will be incremented by @refs.
- *
- *    FOLL_PIN on single-page folios: folio's refcount will be incremented by
- *    @refs * GUP_PIN_COUNTING_BIAS.
- *
- * Return: The folio containing @page (with refcount appropriately
- * incremented) for success, or NULL upon failure. If neither FOLL_GET
- * nor FOLL_PIN was set, that's considered failure, and furthermore,
- * a likely bug in the caller, so a warning is also emitted.
- */
-struct folio *try_grab_folio(struct page *page, int refs, unsigned int flags)
-{
-	struct folio *folio;
-
-	if (WARN_ON_ONCE((flags & (FOLL_GET | FOLL_PIN)) == 0))
-		return NULL;
-
-	if (unlikely(!(flags & FOLL_PCI_P2PDMA) && is_pci_p2pdma_page(page)))
-		return NULL;
-
-	if (flags & FOLL_GET)
-		return try_get_folio(page, refs);
-
-	/* FOLL_PIN is set */
-
-	/*
-	 * Don't take a pin on the zero page - it's not going anywhere
-	 * and it is used in a *lot* of places.
-	 */
-	if (is_zero_page(page))
-		return page_folio(page);
-
-	folio = try_get_folio(page, refs);
-	if (!folio)
-		return NULL;
-
-	/*
-	 * Can't do FOLL_LONGTERM + FOLL_PIN gup fast path if not in a
-	 * right zone, so fail and let the caller fall back to the slow
-	 * path.
-	 */
-	if (unlikely((flags & FOLL_LONGTERM) &&
-		     !folio_is_longterm_pinnable(folio))) {
-		if (!put_devmap_managed_folio_refs(folio, refs))
-			folio_put_refs(folio, refs);
-		return NULL;
-	}
-
-	/*
-	 * When pinning a large folio, use an exact count to track it.
-	 *
-	 * However, be sure to *also* increment the normal folio
-	 * refcount field at least once, so that the folio really
-	 * is pinned.  That's why the refcount from the earlier
-	 * try_get_folio() is left intact.
-	 */
-	if (folio_test_large(folio))
-		atomic_add(refs, &folio->_pincount);
-	else
-		folio_ref_add(folio,
-				refs * (GUP_PIN_COUNTING_BIAS - 1));
-	/*
-	 * Adjust the pincount before re-checking the PTE for changes.
-	 * This is essentially a smp_mb() and is paired with a memory
-	 * barrier in folio_try_share_anon_rmap_*().
-	 */
-	smp_mb__after_atomic();
-
-	node_stat_mod_folio(folio, NR_FOLL_PIN_ACQUIRED, refs);
 
 	return folio;
 }
···
 }
 
 /**
- * try_grab_page() - elevate a page's refcount by a flag-dependent amount
- * @page:    pointer to page to be grabbed
- * @flags:   gup flags: these are the FOLL_* flag values.
+ * try_grab_folio() - add a folio's refcount by a flag-dependent amount
+ * @folio:    pointer to folio to be grabbed
+ * @refs:     the value to (effectively) add to the folio's refcount
+ * @flags:    gup flags: these are the FOLL_* flag values
  *
  * This might not do anything at all, depending on the flags argument.
  *
  * "grab" names in this file mean, "look at flags to decide whether to use
- * FOLL_PIN or FOLL_GET behavior, when incrementing the page's refcount.
+ * FOLL_PIN or FOLL_GET behavior, when incrementing the folio's refcount.
  *
  * Either FOLL_PIN or FOLL_GET (or neither) may be set, but not both at the same
- * time. Cases: please see the try_grab_folio() documentation, with
- * "refs=1".
+ * time.
  *
  * Return: 0 for success, or if no action was required (if neither FOLL_PIN
  * nor FOLL_GET was set, nothing is done). A negative error code for failure:
  *
- *   -ENOMEM		FOLL_GET or FOLL_PIN was set, but the page could not
+ *   -ENOMEM		FOLL_GET or FOLL_PIN was set, but the folio could not
  *			be grabbed.
+ *
+ * It is called when we have a stable reference for the folio, typically in
+ * GUP slow path.
  */
-int __must_check try_grab_page(struct page *page, unsigned int flags)
+int __must_check try_grab_folio(struct folio *folio, int refs,
+				unsigned int flags)
 {
-	struct folio *folio = page_folio(page);
-
 	if (WARN_ON_ONCE(folio_ref_count(folio) <= 0))
 		return -ENOMEM;
 
-	if (unlikely(!(flags & FOLL_PCI_P2PDMA) && is_pci_p2pdma_page(page)))
+	if (unlikely(!(flags & FOLL_PCI_P2PDMA) && is_pci_p2pdma_page(&folio->page)))
 		return -EREMOTEIO;
 
 	if (flags & FOLL_GET)
-		folio_ref_inc(folio);
+		folio_ref_add(folio, refs);
 	else if (flags & FOLL_PIN) {
 		/*
 		 * Don't take a pin on the zero page - it's not going anywhere
 		 * and it is used in a *lot* of places.
 		 */
-		if (is_zero_page(page))
+		if (is_zero_folio(folio))
 			return 0;
 
 		/*
-		 * Similar to try_grab_folio(): be sure to *also*
-		 * increment the normal page refcount field at least once,
+		 * Increment the normal page refcount field at least once,
 		 * so that the page really is pinned.
 		 */
 		if (folio_test_large(folio)) {
-			folio_ref_add(folio, 1);
-			atomic_add(1, &folio->_pincount);
+			folio_ref_add(folio, refs);
+			atomic_add(refs, &folio->_pincount);
 		} else {
-			folio_ref_add(folio, GUP_PIN_COUNTING_BIAS);
+			folio_ref_add(folio, refs * GUP_PIN_COUNTING_BIAS);
 		}
 
-		node_stat_mod_folio(folio, NR_FOLL_PIN_ACQUIRED, 1);
+		node_stat_mod_folio(folio, NR_FOLL_PIN_ACQUIRED, refs);
 	}
 
 	return 0;
···
 
 	return nr;
 }
+
+/**
+ * try_grab_folio_fast() - Attempt to get or pin a folio in fast path.
+ * @page:  pointer to page to be grabbed
+ * @refs:  the value to (effectively) add to the folio's refcount
+ * @flags: gup flags: these are the FOLL_* flag values.
+ *
+ * "grab" names in this file mean, "look at flags to decide whether to use
+ * FOLL_PIN or FOLL_GET behavior, when incrementing the folio's refcount.
+ *
+ * Either FOLL_PIN or FOLL_GET (or neither) must be set, but not both at the
+ * same time. (That's true throughout the get_user_pages*() and
+ * pin_user_pages*() APIs.) Cases:
+ *
+ *    FOLL_GET: folio's refcount will be incremented by @refs.
+ *
+ *    FOLL_PIN on large folios: folio's refcount will be incremented by
+ *    @refs, and its pincount will be incremented by @refs.
+ *
+ *    FOLL_PIN on single-page folios: folio's refcount will be incremented by
+ *    @refs * GUP_PIN_COUNTING_BIAS.
+ *
+ * Return: The folio containing @page (with refcount appropriately
+ * incremented) for success, or NULL upon failure. If neither FOLL_GET
+ * nor FOLL_PIN was set, that's considered failure, and furthermore,
+ * a likely bug in the caller, so a warning is also emitted.
+ *
+ * It uses add ref unless zero to elevate the folio refcount and must be called
+ * in fast path only.
+ */
+static struct folio *try_grab_folio_fast(struct page *page, int refs,
+					 unsigned int flags)
+{
+	struct folio *folio;
+
+	/* Raise warn if it is not called in fast GUP */
+	VM_WARN_ON_ONCE(!irqs_disabled());
+
+	if (WARN_ON_ONCE((flags & (FOLL_GET | FOLL_PIN)) == 0))
+		return NULL;
+
+	if (unlikely(!(flags & FOLL_PCI_P2PDMA) && is_pci_p2pdma_page(page)))
+		return NULL;
+
+	if (flags & FOLL_GET)
+		return try_get_folio(page, refs);
+
+	/* FOLL_PIN is set */
+
+	/*
+	 * Don't take a pin on the zero page - it's not going anywhere
+	 * and it is used in a *lot* of places.
+	 */
+	if (is_zero_page(page))
+		return page_folio(page);
+
+	folio = try_get_folio(page, refs);
+	if (!folio)
+		return NULL;
+
+	/*
+	 * Can't do FOLL_LONGTERM + FOLL_PIN gup fast path if not in a
+	 * right zone, so fail and let the caller fall back to the slow
+	 * path.
+	 */
+	if (unlikely((flags & FOLL_LONGTERM) &&
+		     !folio_is_longterm_pinnable(folio))) {
+		if (!put_devmap_managed_folio_refs(folio, refs))
+			folio_put_refs(folio, refs);
+		return NULL;
+	}
+
+	/*
+	 * When pinning a large folio, use an exact count to track it.
+	 *
+	 * However, be sure to *also* increment the normal folio
+	 * refcount field at least once, so that the folio really
+	 * is pinned.  That's why the refcount from the earlier
+	 * try_get_folio() is left intact.
+	 */
+	if (folio_test_large(folio))
+		atomic_add(refs, &folio->_pincount);
+	else
+		folio_ref_add(folio,
+				refs * (GUP_PIN_COUNTING_BIAS - 1));
+	/*
+	 * Adjust the pincount before re-checking the PTE for changes.
+	 * This is essentially a smp_mb() and is paired with a memory
+	 * barrier in folio_try_share_anon_rmap_*().
+	 */
+	smp_mb__after_atomic();
+
+	node_stat_mod_folio(folio, NR_FOLL_PIN_ACQUIRED, refs);
+
+	return folio;
+}
 #endif	/* CONFIG_ARCH_HAS_HUGEPD || CONFIG_HAVE_GUP_FAST */
 
 #ifdef CONFIG_ARCH_HAS_HUGEPD
···
  */
 static int gup_hugepte(struct vm_area_struct *vma, pte_t *ptep, unsigned long sz,
 		       unsigned long addr, unsigned long end, unsigned int flags,
-		       struct page **pages, int *nr)
+		       struct page **pages, int *nr, bool fast)
 {
 	unsigned long pte_end;
 	struct page *page;
···
 	page = pte_page(pte);
 	refs = record_subpages(page, sz, addr, end, pages + *nr);
 
-	folio = try_grab_folio(page, refs, flags);
-	if (!folio)
-		return 0;
+	if (fast) {
+		folio = try_grab_folio_fast(page, refs, flags);
+		if (!folio)
+			return 0;
+	} else {
+		folio = page_folio(page);
+		if (try_grab_folio(folio, refs, flags))
+			return 0;
+	}
 
 	if (unlikely(pte_val(pte) != pte_val(ptep_get(ptep)))) {
 		gup_put_folio(folio, refs, flags);
···
 static int gup_hugepd(struct vm_area_struct *vma, hugepd_t hugepd,
 		      unsigned long addr, unsigned int pdshift,
 		      unsigned long end, unsigned int flags,
-		      struct page **pages, int *nr)
+		      struct page **pages, int *nr, bool fast)
 {
 	pte_t *ptep;
 	unsigned long sz = 1UL << hugepd_shift(hugepd);
···
 	ptep = hugepte_offset(hugepd, addr, pdshift);
 	do {
 		next = hugepte_addr_end(addr, end, sz);
-		ret = gup_hugepte(vma, ptep, sz, addr, end, flags, pages, nr);
+		ret = gup_hugepte(vma, ptep, sz, addr, end, flags, pages, nr,
+				  fast);
 		if (ret != 1)
 			return ret;
 	} while (ptep++, addr = next, addr != end);
···
 	ptep = hugepte_offset(hugepd, addr, pdshift);
 	ptl = huge_pte_lock(h, vma->vm_mm, ptep);
 	ret = gup_hugepd(vma, hugepd, addr, pdshift, addr + PAGE_SIZE,
-			 flags, &page, &nr);
+			 flags, &page, &nr, false);
 	spin_unlock(ptl);
 
 	if (ret == 1) {
···
 static inline int gup_hugepd(struct vm_area_struct *vma, hugepd_t hugepd,
 			     unsigned long addr, unsigned int pdshift,
 			     unsigned long end, unsigned int flags,
-			     struct page **pages, int *nr)
+			     struct page **pages, int *nr, bool fast)
 {
 	return 0;
 }
···
 	    gup_must_unshare(vma, flags, page))
 		return ERR_PTR(-EMLINK);
 
-	ret = try_grab_page(page, flags);
+	ret = try_grab_folio(page_folio(page), 1, flags);
 	if (ret)
 		page = ERR_PTR(ret);
 	else
···
 	VM_BUG_ON_PAGE((flags & FOLL_PIN) && PageAnon(page) &&
 			!PageAnonExclusive(page), page);
 
-	ret = try_grab_page(page, flags);
+	ret = try_grab_folio(page_folio(page), 1, flags);
 	if (ret)
 		return ERR_PTR(ret);
 
···
 	VM_BUG_ON_PAGE((flags & FOLL_PIN) && PageAnon(page) &&
 		       !PageAnonExclusive(page), page);
 
-	/* try_grab_page() does nothing unless FOLL_GET or FOLL_PIN is set. */
-	ret = try_grab_page(page, flags);
+	/* try_grab_folio() does nothing unless FOLL_GET or FOLL_PIN is set. */
+	ret = try_grab_folio(page_folio(page), 1, flags);
 	if (unlikely(ret)) {
 		page = ERR_PTR(ret);
 		goto out;
···
 			goto unmap;
 		*page = pte_page(entry);
 	}
-	ret = try_grab_page(*page, gup_flags);
+	ret = try_grab_folio(page_folio(*page), 1, gup_flags);
 	if (unlikely(ret))
 		goto unmap;
 out:
···
 			 * pages.
 			 */
 			if (page_increm > 1) {
-				struct folio *folio;
+				struct folio *folio = page_folio(page);
 
 				/*
 				 * Since we already hold refcount on the
 				 * large folio, this should never fail.
 				 */
-				folio = try_grab_folio(page, page_increm - 1,
-						       foll_flags);
-				if (WARN_ON_ONCE(!folio)) {
+				if (try_grab_folio(folio, page_increm - 1,
+						   foll_flags)) {
 					/*
 					 * Release the 1st page ref if the
 					 * folio is problematic, fail hard.
 					 */
-					gup_put_folio(page_folio(page), 1,
+					gup_put_folio(folio, 1,
 						      foll_flags);
 					ret = -EFAULT;
 					goto out;
···
  * This code is based heavily on the PowerPC implementation by Nick Piggin.
  */
 #ifdef CONFIG_HAVE_GUP_FAST
-
 /*
  * Used in the GUP-fast path to determine whether GUP is permitted to work on
  * a specific folio.
···
 		VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
 		page = pte_page(pte);
 
-		folio = try_grab_folio(page, 1, flags);
+		folio = try_grab_folio_fast(page, 1, flags);
 		if (!folio)
 			goto pte_unmap;
 
···
 			break;
 		}
 
-		folio = try_grab_folio(page, 1, flags);
+		folio = try_grab_folio_fast(page, 1, flags);
 		if (!folio) {
 			gup_fast_undo_dev_pagemap(nr, nr_start, flags, pages);
 			break;
···
 	page = pmd_page(orig);
 	refs = record_subpages(page, PMD_SIZE, addr, end, pages + *nr);
 
-	folio = try_grab_folio(page, refs, flags);
+	folio = try_grab_folio_fast(page, refs, flags);
 	if (!folio)
 		return 0;
 
···
 	page = pud_page(orig);
 	refs = record_subpages(page, PUD_SIZE, addr, end, pages + *nr);
 
-	folio = try_grab_folio(page, refs, flags);
+	folio = try_grab_folio_fast(page, refs, flags);
 	if (!folio)
 		return 0;
 
···
 	page = pgd_page(orig);
 	refs = record_subpages(page, PGDIR_SIZE, addr, end, pages + *nr);
 
-	folio = try_grab_folio(page, refs, flags);
+	folio = try_grab_folio_fast(page, refs, flags);
 	if (!folio)
 		return 0;
 
···
 			 * pmd format and THP pmd format
 			 */
 			if (gup_hugepd(NULL, __hugepd(pmd_val(pmd)), addr,
-				       PMD_SHIFT, next, flags, pages, nr) != 1)
+				       PMD_SHIFT, next, flags, pages, nr,
+				       true) != 1)
 				return 0;
 		} else if (!gup_fast_pte_range(pmd, pmdp, addr, next, flags,
 					       pages, nr))
···
 				return 0;
 		} else if (unlikely(is_hugepd(__hugepd(pud_val(pud))))) {
 			if (gup_hugepd(NULL, __hugepd(pud_val(pud)), addr,
-				       PUD_SHIFT, next, flags, pages, nr) != 1)
+				       PUD_SHIFT, next, flags, pages, nr,
+				       true) != 1)
 				return 0;
 		} else if (!gup_fast_pmd_range(pudp, pud, addr, next, flags,
 					       pages, nr))
···
 		BUILD_BUG_ON(p4d_leaf(p4d));
 		if (unlikely(is_hugepd(__hugepd(p4d_val(p4d))))) {
 			if (gup_hugepd(NULL, __hugepd(p4d_val(p4d)), addr,
-				       P4D_SHIFT, next, flags, pages, nr) != 1)
+				       P4D_SHIFT, next, flags, pages, nr,
+				       true) != 1)
 				return 0;
 		} else if (!gup_fast_pud_range(p4dp, p4d, addr, next, flags,
 					       pages, nr))
···
 				return;
 		} else if (unlikely(is_hugepd(__hugepd(pgd_val(pgd))))) {
 			if (gup_hugepd(NULL, __hugepd(pgd_val(pgd)), addr,
-				       PGDIR_SHIFT, next, flags, pages, nr) != 1)
+				       PGDIR_SHIFT, next, flags, pages, nr,
+				       true) != 1)
 				return;
 		} else if (!gup_fast_p4d_range(pgdp, pgd, addr, next, flags,
 					       pages, nr))

mm/huge_memory.c

···
 	if (!*pgmap)
 		return ERR_PTR(-EFAULT);
 	page = pfn_to_page(pfn);
-	ret = try_grab_page(page, flags);
+	ret = try_grab_folio(page_folio(page), 1, flags);
 	if (ret)
 		page = ERR_PTR(ret);
 

mm/hugetlb.c

···
  * folio appears as just a compound page.  Otherwise, wait until after
  * allocating vmemmap to clear the flag.
  *
- * A reference is held on the folio, except in the case of demote.
- *
  * Must be called with hugetlb lock held.
  */
-static void __remove_hugetlb_folio(struct hstate *h, struct folio *folio,
-							bool adjust_surplus,
-							bool demote)
+static void remove_hugetlb_folio(struct hstate *h, struct folio *folio,
+							bool adjust_surplus)
 {
 	int nid = folio_nid(folio);
 
···
 	list_del(&folio->lru);
 
 	if (folio_test_hugetlb_freed(folio)) {
+		folio_clear_hugetlb_freed(folio);
 		h->free_huge_pages--;
 		h->free_huge_pages_node[nid]--;
 	}
···
 	if (!folio_test_hugetlb_vmemmap_optimized(folio))
 		__folio_clear_hugetlb(folio);
 
-	 /*
-	  * In the case of demote we do not ref count the page as it will soon
-	  * be turned into a page of smaller size.
-	 */
-	if (!demote)
-		folio_ref_unfreeze(folio, 1);
-
 	h->nr_huge_pages--;
 	h->nr_huge_pages_node[nid]--;
-}
-
-static void remove_hugetlb_folio(struct hstate *h, struct folio *folio,
-							bool adjust_surplus)
-{
-	__remove_hugetlb_folio(h, folio, adjust_surplus, false);
-}
-
-static void remove_hugetlb_folio_for_demote(struct hstate *h, struct folio *folio,
-							bool adjust_surplus)
-{
-	__remove_hugetlb_folio(h, folio, adjust_surplus, true);
 }
 
 static void add_hugetlb_folio(struct hstate *h, struct folio *folio,
 			     bool adjust_surplus)
 {
-	int zeroed;
 	int nid = folio_nid(folio);
 
 	VM_BUG_ON_FOLIO(!folio_test_hugetlb_vmemmap_optimized(folio), folio);
···
 	 * folio_change_private(folio, NULL) cleared it.
 	 */
 	folio_set_hugetlb_vmemmap_optimized(folio);
-
-	/*
-	 * This folio is about to be managed by the hugetlb allocator and
-	 * should have no users.  Drop our reference, and check for others
-	 * just in case.
-	 */
-	zeroed = folio_put_testzero(folio);
-	if (unlikely(!zeroed))
-		/*
-		 * It is VERY unlikely soneone else has taken a ref
-		 * on the folio.  In this case, we simply return as
-		 * free_huge_folio() will be called when this other ref
-		 * is dropped.
-		 */
-		return;
 
 	arch_clear_hugetlb_flags(folio);
 	enqueue_hugetlb_folio(h, folio);
···
 	}
 
 	/*
-	 * Move PageHWPoison flag from head page to the raw error pages,
-	 * which makes any healthy subpages reusable.
-	 */
-	if (unlikely(folio_test_hwpoison(folio)))
-		folio_clear_hugetlb_hwpoison(folio);
-
-	/*
 	 * If vmemmap pages were allocated above, then we need to clear the
 	 * hugetlb flag under the hugetlb lock.
 	 */
···
 		__folio_clear_hugetlb(folio);
 		spin_unlock_irq(&hugetlb_lock);
 	}
+
+	/*
+	 * Move PageHWPoison flag from head page to the raw error pages,
+	 * which makes any healthy subpages reusable.
+	 */
+	if (unlikely(folio_test_hwpoison(folio)))
+		folio_clear_hugetlb_hwpoison(folio);
+
+	folio_ref_unfreeze(folio, 1);
 
 	/*
 	 * Non-gigantic pages demoted from CMA allocated gigantic pages
···
 		nid = numa_mem_id();
 retry:
 	folio = __folio_alloc(gfp_mask, order, nid, nmask);
+	/* Ensure hugetlb folio won't have large_rmappable flag set. */
+	if (folio)
+		folio_clear_large_rmappable(folio);
 
 	if (folio && !folio_ref_freeze(folio, 1)) {
 		folio_put(folio);
···
 
 free_new:
 	spin_unlock_irq(&hugetlb_lock);
-	if (new_folio) {
-		/* Folio has a zero ref count, but needs a ref to be freed */
-		folio_ref_unfreeze(new_folio, 1);
+	if (new_folio)
 		update_and_free_hugetlb_folio(h, new_folio, false);
-	}
 
 	return ret;
 }
···
 
 	target_hstate = size_to_hstate(PAGE_SIZE << h->demote_order);
 
-	remove_hugetlb_folio_for_demote(h, folio, false);
+	remove_hugetlb_folio(h, folio, false);
 	spin_unlock_irq(&hugetlb_lock);
 
 	/*
···
 		if (rc) {
 			/* Allocation of vmemmmap failed, we can not demote folio */
 			spin_lock_irq(&hugetlb_lock);
-			folio_ref_unfreeze(folio, 1);
 			add_hugetlb_folio(h, folio, false);
 			return rc;
 		}

mm/hugetlb_vmemmap.c

···
 	unsigned long vmemmap_reuse;
 
 	VM_WARN_ON_ONCE_FOLIO(!folio_test_hugetlb(folio), folio);
+	VM_WARN_ON_ONCE_FOLIO(folio_ref_count(folio), folio);
+
 	if (!folio_test_hugetlb_vmemmap_optimized(folio))
 		return 0;
 
···
  */
 int hugetlb_vmemmap_restore_folio(const struct hstate *h, struct folio *folio)
 {
+	/* avoid writes from page_ref_add_unless() while unfolding vmemmap */
+	synchronize_rcu();
+
 	return __hugetlb_vmemmap_restore_folio(h, folio, 0);
 }
 
···
 	struct folio *folio, *t_folio;
 	long restored = 0;
 	long ret = 0;
+
+	/* avoid writes from page_ref_add_unless() while unfolding vmemmap */
+	synchronize_rcu();
 
 	list_for_each_entry_safe(folio, t_folio, folio_list, lru) {
 		if (folio_test_hugetlb_vmemmap_optimized(folio)) {
···
 	unsigned long vmemmap_reuse;
 
 	VM_WARN_ON_ONCE_FOLIO(!folio_test_hugetlb(folio), folio);
+	VM_WARN_ON_ONCE_FOLIO(folio_ref_count(folio), folio);
+
 	if (!vmemmap_should_optimize_folio(h, folio))
 		return ret;
 
···
 {
 	LIST_HEAD(vmemmap_pages);
 
+	/* avoid writes from page_ref_add_unless() while folding vmemmap */
+	synchronize_rcu();
+
 	__hugetlb_vmemmap_optimize_folio(h, folio, &vmemmap_pages, 0);
 	free_vmemmap_page_list(&vmemmap_pages);
 }
···
 	}
 
 	flush_tlb_all();
+
+	/* avoid writes from page_ref_add_unless() while folding vmemmap */
+	synchronize_rcu();
 
 	list_for_each_entry(folio, folio_list, lru) {
 		int ret;

mm/internal.h

···
 /*
  * mm/gup.c
  */
-struct folio *try_grab_folio(struct page *page, int refs, unsigned int flags);
-int __must_check try_grab_page(struct page *page, unsigned int flags);
+int __must_check try_grab_folio(struct folio *folio, int refs,
+				unsigned int flags);
 
 /*
  * mm/huge_memory.c

mm/memcontrol.c

···
 
 	/* Transfer the charge and the css ref */
 	commit_charge(new, memcg);
-	/*
-	 * If the old folio is a large folio and is in the split queue, it needs
-	 * to be removed from the split queue now, in case getting an incorrect
-	 * split queue in destroy_large_folio() after the memcg of the old folio
-	 * is cleared.
-	 *
-	 * In addition, the old folio is about to be freed after migration, so
-	 * removing from the split queue a bit earlier seems reasonable.
-	 */
-	if (folio_test_large(old) && folio_test_large_rmappable(old))
-		folio_undo_large_rmappable(old);
 	old->memcg_data = 0;
 }
 

mm/migrate.c

···
 		if (folio_ref_count(folio) != expected_count)
 			return -EAGAIN;
 
+		/* Take off deferred split queue while frozen and memcg set */
+		if (folio_test_large(folio) &&
+		    folio_test_large_rmappable(folio)) {
+			if (!folio_ref_freeze(folio, expected_count))
+				return -EAGAIN;
+			folio_undo_large_rmappable(folio);
+			folio_ref_unfreeze(folio, expected_count);
+		}
+
 		/* No turning back from here */
 		newfolio->index = folio->index;
 		newfolio->mapping = folio->mapping;
···
 		xas_unlock_irq(&xas);
 		return -EAGAIN;
 	}
+
+	/* Take off deferred split queue while frozen and memcg set */
+	if (folio_test_large(folio) && folio_test_large_rmappable(folio))
+		folio_undo_large_rmappable(folio);
 
 	/*
 	 * Now we know that no one else is looking at the folio:

mm/readahead.c

···
 
 	limit = min(limit, index + ra->size - 1);
 
-	if (new_order < MAX_PAGECACHE_ORDER) {
+	if (new_order < MAX_PAGECACHE_ORDER)
 		new_order += 2;
-		new_order = min_t(unsigned int, MAX_PAGECACHE_ORDER, new_order);
-		new_order = min_t(unsigned int, new_order, ilog2(ra->size));
-	}
+
+	new_order = min_t(unsigned int, MAX_PAGECACHE_ORDER, new_order);
+	new_order = min_t(unsigned int, new_order, ilog2(ra->size));
 
 	/* See comment in page_cache_ra_unbounded() */
 	nofs = memalloc_nofs_save();

mm/shmem.c

···
 
 static int shmem_huge __read_mostly = SHMEM_HUGE_NEVER;
 
-bool shmem_is_huge(struct inode *inode, pgoff_t index, bool shmem_huge_force,
-		   struct mm_struct *mm, unsigned long vm_flags)
+static bool __shmem_is_huge(struct inode *inode, pgoff_t index,
+			    bool shmem_huge_force, struct mm_struct *mm,
+			    unsigned long vm_flags)
 {
 	loff_t i_size;
 
···
 	default:
 		return false;
 	}
+}
+
+bool shmem_is_huge(struct inode *inode, pgoff_t index,
+		   bool shmem_huge_force, struct mm_struct *mm,
+		   unsigned long vm_flags)
+{
+	if (HPAGE_PMD_ORDER > MAX_PAGECACHE_ORDER)
+		return false;
+
+	return __shmem_is_huge(inode, index, shmem_huge_force, mm, vm_flags);
 }
 
 #if defined(CONFIG_SYSFS)

mm/vmalloc.c

···
 static struct xarray *
 addr_to_vb_xa(unsigned long addr)
 {
-	int index = (addr / VMAP_BLOCK_SIZE) % num_possible_cpus();
+	int index = (addr / VMAP_BLOCK_SIZE) % nr_cpu_ids;
+
+	/*
+	 * Please note, nr_cpu_ids points on a highest set
+	 * possible bit, i.e. we never invoke cpumask_next()
+	 * if an index points on it which is nr_cpu_ids - 1.
+	 */
+	if (!cpu_possible(index))
+		index = cpumask_next(index, cpu_possible_mask);
 
 	return &per_cpu(vmap_block_queue, index).vmap_blocks;
 }

mm/workingset.c

···
  * @file: whether the corresponding folio is from the file lru.
  * @workingset: where the workingset value unpacked from shadow should
  * be stored.
+ * @flush: whether to flush cgroup rstat.
  *
  * Return: true if the shadow is for a recently evicted folio; false otherwise.
  */
-bool workingset_test_recent(void *shadow, bool file, bool *workingset)
+bool workingset_test_recent(void *shadow, bool file, bool *workingset,
+				bool flush)
 {
 	struct mem_cgroup *eviction_memcg;
 	struct lruvec *eviction_lruvec;
···
 
 	/*
 	 * Flush stats (and potentially sleep) outside the RCU read section.
+	 *
+	 * Note that workingset_test_recent() itself might be called in RCU read
+	 * section (for e.g, in cachestat) - these callers need to skip flushing
+	 * stats (via the flush argument).
+	 *
 	 * XXX: With per-memcg flushing and thresholding, is ratelimiting
 	 * still needed here?
 	 */
-	mem_cgroup_flush_stats_ratelimited(eviction_memcg);
+	if (flush)
+		mem_cgroup_flush_stats_ratelimited(eviction_memcg);
 
 	eviction_lruvec = mem_cgroup_lruvec(eviction_memcg, pgdat);
 	refault = atomic_long_read(&eviction_lruvec->nonresident_age);
···
 
 	mod_lruvec_state(lruvec, WORKINGSET_REFAULT_BASE + file, nr);
 
-	if (!workingset_test_recent(shadow, file, &workingset))
+	if (!workingset_test_recent(shadow, file, &workingset, true))
 		return;
 
 	folio_set_active(folio);

net/core/datagram.c

···
 			if (copy > len)
 				copy = len;
 
+			n = 0;
 			skb_frag_foreach_page(frag,
 					      skb_frag_off(frag) + offset - start,
 					      copy, p, p_off, p_len, copied) {
 				vaddr = kmap_local_page(p);
-				n = INDIRECT_CALL_1(cb, simple_copy_to_iter,
+				n += INDIRECT_CALL_1(cb, simple_copy_to_iter,
 					vaddr + p_off, p_len, data, to);
 				kunmap_local(vaddr);
 			}

net/core/skmsg.c

···
 			page = sg_page(sge);
 			if (copied + copy > len)
 				copy = len - copied;
-			copy = copy_page_to_iter(page, sge->offset, copy, iter);
+			if (copy)
+				copy = copy_page_to_iter(page, sge->offset, copy, iter);
 			if (!copy) {
 				copied = copied ? copied : -EFAULT;
 				goto out;

net/ethtool/linkstate.c

···
 	mutex_lock(&phydev->lock);
 	if (!phydev->drv || !phydev->drv->get_sqi)
 		ret = -EOPNOTSUPP;
+	else if (!phydev->link)
+		ret = -ENETDOWN;
 	else
 		ret = phydev->drv->get_sqi(phydev);
 	mutex_unlock(&phydev->lock);
···
 	mutex_lock(&phydev->lock);
 	if (!phydev->drv || !phydev->drv->get_sqi_max)
 		ret = -EOPNOTSUPP;
+	else if (!phydev->link)
+		ret = -ENETDOWN;
 	else
 		ret = phydev->drv->get_sqi_max(phydev);
 	mutex_unlock(&phydev->lock);
 
 	return ret;
 };
+
+static bool linkstate_sqi_critical_error(int sqi)
+{
+	return sqi < 0 && sqi != -EOPNOTSUPP && sqi != -ENETDOWN;
+}
+
+static bool linkstate_sqi_valid(struct linkstate_reply_data *data)
+{
+	return data->sqi >= 0 && data->sqi_max >= 0 &&
+	       data->sqi <= data->sqi_max;
+}
 
 static int linkstate_get_link_ext_state(struct net_device *dev,
 					struct linkstate_reply_data *data)
···
 	data->link = __ethtool_get_link(dev);
 
 	ret = linkstate_get_sqi(dev);
-	if (ret < 0 && ret != -EOPNOTSUPP)
+	if (linkstate_sqi_critical_error(ret))
 		goto out;
 	data->sqi = ret;
 
 	ret = linkstate_get_sqi_max(dev);
-	if (ret < 0 && ret != -EOPNOTSUPP)
+	if (linkstate_sqi_critical_error(ret))
 		goto out;
 	data->sqi_max = ret;
 
···
 	len = nla_total_size(sizeof(u8)) /* LINKSTATE_LINK */
 		+ 0;
 
-	if (data->sqi != -EOPNOTSUPP)
-		len += nla_total_size(sizeof(u32));
-
-	if (data->sqi_max != -EOPNOTSUPP)
-		len += nla_total_size(sizeof(u32));
+	if (linkstate_sqi_valid(data)) {
+		len += nla_total_size(sizeof(u32)); /* LINKSTATE_SQI */
+		len += nla_total_size(sizeof(u32)); /* LINKSTATE_SQI_MAX */
+	}
 
 	if (data->link_ext_state_provided)
 		len += nla_total_size(sizeof(u8)); /* LINKSTATE_EXT_STATE */
···
 	    nla_put_u8(skb, ETHTOOL_A_LINKSTATE_LINK, !!data->link))
 		return -EMSGSIZE;
 
-	if (data->sqi != -EOPNOTSUPP &&
-	    nla_put_u32(skb, ETHTOOL_A_LINKSTATE_SQI, data->sqi))
-		return -EMSGSIZE;
+	if (linkstate_sqi_valid(data)) {
+		if (nla_put_u32(skb, ETHTOOL_A_LINKSTATE_SQI, data->sqi))
+			return -EMSGSIZE;
 
-	if (data->sqi_max != -EOPNOTSUPP &&
-	    nla_put_u32(skb, ETHTOOL_A_LINKSTATE_SQI_MAX, data->sqi_max))
-		return -EMSGSIZE;
+		if (nla_put_u32(skb, ETHTOOL_A_LINKSTATE_SQI_MAX,
+				data->sqi_max))
+			return -EMSGSIZE;
+	}
 
 	if (data->link_ext_state_provided) {
 		if (nla_put_u8(skb, ETHTOOL_A_LINKSTATE_EXT_STATE,

net/ipv4/tcp_input.c

···
 static inline void tcp_init_undo(struct tcp_sock *tp)
 {
 	tp->undo_marker = tp->snd_una;
+
 	/* Retransmission still in flight may cause DSACKs later. */
-	tp->undo_retrans = tp->retrans_out ? : -1;
+	/* First, account for regular retransmits in flight: */
+	tp->undo_retrans = tp->retrans_out;
+	/* Next, account for TLP retransmits in flight: */
+	if (tp->tlp_high_seq && tp->tlp_retrans)
+		tp->undo_retrans++;
+	/* Finally, avoid 0, because undo_retrans==0 means "can undo now": */
+	if (!tp->undo_retrans)
+		tp->undo_retrans = -1;
 }
 
 static bool tcp_is_rack(const struct sock *sk)
···
 
 	tcp_set_ca_state(sk, TCP_CA_Loss);
 	tp->high_seq = tp->snd_nxt;
+	tp->tlp_high_seq = 0;
 	tcp_ecn_queue_cwr(tp);
 
 	/* F-RTO RFC5682 sec 3.1 step 1: retransmit SND.UNA if no previous

net/ipv4/tcp_timer.c

···
 				     const struct sk_buff *skb,
 				     u32 rtx_delta)
 {
+	const struct inet_connection_sock *icsk = inet_csk(sk);
+	u32 user_timeout = READ_ONCE(icsk->icsk_user_timeout);
 	const struct tcp_sock *tp = tcp_sk(sk);
-	const int timeout = TCP_RTO_MAX * 2;
+	int timeout = TCP_RTO_MAX * 2;
 	s32 rcv_delta;
 
+	if (user_timeout) {
+		/* If user application specified a TCP_USER_TIMEOUT,
+		 * it does not want win 0 packets to 'reset the timer'
+		 * while retransmits are not making progress.
+		 */
+		if (rtx_delta > user_timeout)
+			return true;
+		timeout = min_t(u32, timeout, msecs_to_jiffies(user_timeout));
+	}
 	/* Note: timer interrupt might have been delayed by at least one jiffy,
 	 * and tp->rcv_tstamp might very well have been written recently.
 	 * rcv_delta can thus be negative.
 	 */
-	rcv_delta = inet_csk(sk)->icsk_timeout - tp->rcv_tstamp;
+	rcv_delta = icsk->icsk_timeout - tp->rcv_tstamp;
 	if (rcv_delta <= timeout)
 		return false;
 
···
 	skb = tcp_rtx_queue_head(sk);
 	if (WARN_ON_ONCE(!skb))
 		return;
-
-	tp->tlp_high_seq = 0;
 
 	if (!tp->snd_wnd && !sock_flag(sk, SOCK_DEAD) &&
 	    !((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV))) {

net/ipv4/udp.c

···
 			goto fail_unlock;
 		}
 
+		sock_set_flag(sk, SOCK_RCU_FREE);
+
 		sk_add_node_rcu(sk, &hslot->head);
 		hslot->count++;
 		sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1);
···
 		hslot2->count++;
 		spin_unlock(&hslot2->lock);
 	}
-	sock_set_flag(sk, SOCK_RCU_FREE);
+
 	error = 0;
 fail_unlock:
 	spin_unlock_bh(&hslot->lock);

net/netfilter/nf_tables_api.c

···
 	nf_tables_rule_destroy(ctx, rule);
 }
 
+/** nft_chain_validate - loop detection and hook validation
+ *
+ * @ctx: context containing call depth and base chain
+ * @chain: chain to validate
+ *
+ * Walk through the rules of the given chain and chase all jumps/gotos
+ * and set lookups until either the jump limit is hit or all reachable
+ * chains have been validated.
+ */
 int nft_chain_validate(const struct nft_ctx *ctx, const struct nft_chain *chain)
 {
 	struct nft_expr *expr, *last;
···
 			if (!expr->ops->validate)
 				continue;
 
+			/* This may call nft_chain_validate() recursively,
+			 * callers that do so must increment ctx->level.
+			 */
 			err = expr->ops->validate(ctx, expr, &data);
 			if (err < 0)
 				return err;
···
 }
 EXPORT_SYMBOL_GPL(nft_chain_validate_hooks);
 
-/*
- * Loop detection - walk through the ruleset beginning at the destination chain
- * of a new jump until either the source chain is reached (loop) or all
- * reachable chains have been traversed.
- *
- * The loop check is performed whenever a new jump verdict is added to an
- * expression or verdict map or a verdict map is bound to a new chain.
- */
-
-static int nf_tables_check_loops(const struct nft_ctx *ctx,
-				 const struct nft_chain *chain);
-
-static int nft_check_loops(const struct nft_ctx *ctx,
-			   const struct nft_set_ext *ext)
-{
-	const struct nft_data *data;
-	int ret;
-
-	data = nft_set_ext_data(ext);
-	switch (data->verdict.code) {
-	case NFT_JUMP:
-	case NFT_GOTO:
-		ret = nf_tables_check_loops(ctx, data->verdict.chain);
-		break;
-	default:
-		ret = 0;
-		break;
-	}
-
-	return ret;
-}
-
-static int nf_tables_loop_check_setelem(const struct nft_ctx *ctx,
-					struct nft_set *set,
-					const struct nft_set_iter *iter,
-					struct nft_elem_priv *elem_priv)
-{
-	const struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv);
-
-	if (!nft_set_elem_active(ext, iter->genmask))
-		return 0;
-
-	if (nft_set_ext_exists(ext, NFT_SET_EXT_FLAGS) &&
-	    *nft_set_ext_flags(ext) & NFT_SET_ELEM_INTERVAL_END)
-		return 0;
-
-	return nft_check_loops(ctx, ext);
-}
-
-static int nft_set_catchall_loops(const struct nft_ctx *ctx,
-				  struct nft_set *set)
-{
-	u8 genmask = nft_genmask_next(ctx->net);
-	struct nft_set_elem_catchall *catchall;
-	struct nft_set_ext *ext;
-	int ret = 0;
-
-	list_for_each_entry_rcu(catchall, &set->catchall_list, list) {
-		ext = nft_set_elem_ext(set, catchall->elem);
-		if (!nft_set_elem_active(ext, genmask))
-			continue;
-
-		ret = nft_check_loops(ctx, ext);
-		if (ret < 0)
-			return ret;
-	}
-
-	return ret;
-}
-
-static int nf_tables_check_loops(const struct nft_ctx *ctx,
-				 const struct nft_chain *chain)
-{
-	const struct nft_rule *rule;
-	const struct nft_expr *expr, *last;
-	struct nft_set *set;
-	struct nft_set_binding *binding;
-	struct nft_set_iter iter;
-
-	if (ctx->chain == chain)
-		return -ELOOP;
-
-	if (fatal_signal_pending(current))
-		return -EINTR;
-
-	list_for_each_entry(rule, &chain->rules, list) {
-		nft_rule_for_each_expr(expr, last, rule) {
-			struct nft_immediate_expr *priv;
-			const struct nft_data *data;
-			int err;
-
-			if (strcmp(expr->ops->type->name, "immediate"))
-				continue;
-
-			priv = nft_expr_priv(expr);
-			if (priv->dreg != NFT_REG_VERDICT)
-				continue;
-
-			data = &priv->data;
-			switch (data->verdict.code) {
-			case NFT_JUMP:
-			case NFT_GOTO:
-				err = nf_tables_check_loops(ctx,
-							data->verdict.chain);
-				if (err < 0)
-					return err;
-				break;
-			default:
-				break;
-			}
-		}
-	}
-
-	list_for_each_entry(set, &ctx->table->sets, list) {
-		if (!nft_is_active_next(ctx->net, set))
-			continue;
-		if (!(set->flags & NFT_SET_MAP) ||
-		    set->dtype != NFT_DATA_VERDICT)
-			continue;
-
-		list_for_each_entry(binding, &set->bindings, list) {
-			if (!(binding->flags & NFT_SET_MAP) ||
-			    binding->chain != chain)
-				continue;
-
-			iter.genmask	= nft_genmask_next(ctx->net);
-			iter.type	= NFT_ITER_UPDATE;
-			iter.skip 	= 0;
-			iter.count	= 0;
-			iter.err	= 0;
-			iter.fn		= nf_tables_loop_check_setelem;
-
-			set->ops->walk(ctx, set, &iter);
-			if (!iter.err)
-				iter.err = nft_set_catchall_loops(ctx, set);
-
-			if (iter.err < 0)
-				return iter.err;
-		}
-	}
-
-	return 0;
-}
-
 /**
  *	nft_parse_u32_check - fetch u32 attribute and check for maximum value
  *
···
 		if (data != NULL &&
 		    (data->verdict.code == NFT_GOTO ||
 		     data->verdict.code == NFT_JUMP)) {
-			err = nf_tables_check_loops(ctx, data->verdict.chain);
+			err = nft_chain_validate(ctx, data->verdict.chain);
 			if (err < 0)
 				return err;
 		}

net/netfilter/nfnetlink_queue.c

···
 	hooks = nf_hook_entries_head(net, pf, entry->state.hook);
 
 	i = entry->hook_index;
-	if (WARN_ON_ONCE(!hooks || i >= hooks->num_hook_entries)) {
+	if (!hooks || i >= hooks->num_hook_entries) {
 		kfree_skb_reason(skb, SKB_DROP_REASON_NETFILTER_DROP);
 		nf_queue_entry_free(entry);
 		return;

net/sched/act_ct.c

···
 		err = nf_conntrack_confirm(skb);
 		if (err != NF_ACCEPT)
 			goto nf_error;
+
+		/* The ct may be dropped if a clash has been resolved,
+		 * so it's necessary to retrieve it from skb again to
+		 * prevent UAF.
+		 */
+		ct = nf_ct_get(skb, &ctinfo);
+		if (!ct)
+			skip_add = true;
 	}
 
 	if (!skip_add)

net/sched/sch_ingress.c

···
 	entry = tcx_entry_fetch_or_create(dev, true, &created);
 	if (!entry)
 		return -ENOMEM;
-	tcx_miniq_set_active(entry, true);
+	tcx_miniq_inc(entry);
 	mini_qdisc_pair_init(&q->miniqp, sch, &tcx_entry(entry)->miniq);
 	if (created)
 		tcx_entry_update(dev, entry, true);
···
 	tcf_block_put_ext(q->block, sch, &q->block_info);
 
 	if (entry) {
-		tcx_miniq_set_active(entry, false);
+		tcx_miniq_dec(entry);
 		if (!tcx_entry_is_active(entry)) {
 			tcx_entry_update(dev, NULL, true);
 			tcx_entry_free(entry);
···
 	entry = tcx_entry_fetch_or_create(dev, true, &created);
 	if (!entry)
 		return -ENOMEM;
-	tcx_miniq_set_active(entry, true);
+	tcx_miniq_inc(entry);
 	mini_qdisc_pair_init(&q->miniqp_ingress, sch, &tcx_entry(entry)->miniq);
 	if (created)
 		tcx_entry_update(dev, entry, true);
···
 	entry = tcx_entry_fetch_or_create(dev, false, &created);
 	if (!entry)
 		return -ENOMEM;
-	tcx_miniq_set_active(entry, true);
+	tcx_miniq_inc(entry);
 	mini_qdisc_pair_init(&q->miniqp_egress, sch, &tcx_entry(entry)->miniq);
 	if (created)
 		tcx_entry_update(dev, entry, false);
···
 	tcf_block_put_ext(q->egress_block, sch, &q->egress_block_info);
 
 	if (ingress_entry) {
-		tcx_miniq_set_active(ingress_entry, false);
+		tcx_miniq_dec(ingress_entry);
 		if (!tcx_entry_is_active(ingress_entry)) {
 			tcx_entry_update(dev, NULL, true);
 			tcx_entry_free(ingress_entry);
···
 	}
 
 	if (egress_entry) {
-		tcx_miniq_set_active(egress_entry, false);
+		tcx_miniq_dec(egress_entry);
 		if (!tcx_entry_is_active(egress_entry)) {
 			tcx_entry_update(dev, NULL, false);
 			tcx_entry_free(egress_entry);

net/sunrpc/xprtsock.c

···
 		transport->srcport = 0;
 		status = -EAGAIN;
 		break;
+	case -EPERM:
+		/* Happens, for instance, if a BPF program is preventing
+		 * the connect. Remap the error so upper layers can better
+		 * deal with it.
+		 */
+		status = -ECONNREFUSED;
+		fallthrough;
 	case -EINVAL:
 		/* Happens, for instance, if the user specified a link
 		 * local IPv6 address without a scope-id.

security/integrity/ima/ima_fs.c

···
 
 		kfree(lists);
 	}
-
-	securityfs_measurement_list_count = 0;
 }
 
 static int __init create_securityfs_measurement_lists(void)
···
 	securityfs_remove(binary_runtime_measurements);
 	remove_securityfs_measurement_lists(ascii_securityfs_measurement_lists);
 	remove_securityfs_measurement_lists(binary_securityfs_measurement_lists);
+	securityfs_measurement_list_count = 0;
 	securityfs_remove(ima_symlink);
 	securityfs_remove(ima_dir);
 

tools/perf/util/comm.c

···
 	return result;
 }
 
-static int comm_str__cmp(const void *_lhs, const void *_rhs)
-{
-	const struct comm_str *lhs = *(const struct comm_str * const *)_lhs;
-	const struct comm_str *rhs = *(const struct comm_str * const *)_rhs;
-
-	return strcmp(comm_str__str(lhs), comm_str__str(rhs));
-}
-
 static int comm_str__search(const void *_key, const void *_member)
 {
 	const char *key = _key;
···
 		}
 		result = comm_str__new(str);
 		if (result) {
-			comm_strs->strs[comm_strs->num_strs++] = result;
-			qsort(comm_strs->strs, comm_strs->num_strs, sizeof(struct comm_str *),
-			      comm_str__cmp);
+			int low = 0, high = comm_strs->num_strs - 1;
+			int insert = comm_strs->num_strs; /* Default to inserting at the end. */
+
+			while (low <= high) {
+				int mid = low + (high - low) / 2;
+				int cmp = strcmp(comm_str__str(comm_strs->strs[mid]), str);
+
+				if (cmp < 0) {
+					low = mid + 1;
+				} else {
+					high = mid - 1;
+					insert = mid;
+				}
+			}
+			memmove(&comm_strs->strs[insert + 1], &comm_strs->strs[insert],
+				(comm_strs->num_strs - insert) * sizeof(struct comm_str *));
+			comm_strs->num_strs++;
+			comm_strs->strs[insert] = result;
 		}
 	}
 	up_write(&comm_strs->lock);

tools/perf/util/dsos.c

···
 		dsos->dsos = temp;
 		dsos->allocated = to_allocate;
 	}
-	dsos->dsos[dsos->cnt++] = dso__get(dso);
-	if (dsos->cnt >= 2 && dsos->sorted) {
-		dsos->sorted = dsos__cmp_long_name_id_short_name(&dsos->dsos[dsos->cnt - 2],
-								 &dsos->dsos[dsos->cnt - 1])
-			<= 0;
+	if (!dsos->sorted) {
+		dsos->dsos[dsos->cnt++] = dso__get(dso);
+	} else {
+		int low = 0, high = dsos->cnt - 1;
+		int insert = dsos->cnt; /* Default to inserting at the end. */
+
+		while (low <= high) {
+			int mid = low + (high - low) / 2;
+			int cmp = dsos__cmp_long_name_id_short_name(&dsos->dsos[mid], &dso);
+
+			if (cmp < 0) {
+				low = mid + 1;
+			} else {
+				high = mid - 1;
+				insert = mid;
+			}
+		}
+		memmove(&dsos->dsos[insert + 1], &dsos->dsos[insert],
+			(dsos->cnt - insert) * sizeof(struct dso *));
+		dsos->cnt++;
+		dsos->dsos[insert] = dso__get(dso);
 	}
 	dso__set_dsos(dso, dsos);
 	return 0;

tools/testing/selftests/bpf/config

···
 CONFIG_MPLS_IPTUNNEL=y
 CONFIG_MPLS_ROUTING=y
 CONFIG_MPTCP=y
+CONFIG_NET_ACT_SKBMOD=y
+CONFIG_NET_CLS=y
 CONFIG_NET_CLS_ACT=y
 CONFIG_NET_CLS_BPF=y
 CONFIG_NET_CLS_FLOWER=y
+CONFIG_NET_CLS_MATCHALL=y
 CONFIG_NET_FOU=y
 CONFIG_NET_FOU_IP_TUNNELS=y
 CONFIG_NET_IPGRE=y

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

···
 #define ping_cmd "ping -q -c1 -w1 127.0.0.1 > /dev/null"
 
 #include "test_tc_link.skel.h"
+
+#include "netlink_helpers.h"
 #include "tc_helpers.h"
 
 void serial_test_tc_links_basic(void)
···
 	test_tc_links_ingress(BPF_TCX_INGRESS, true, true);
 	test_tc_links_ingress(BPF_TCX_INGRESS, true, false);
 	test_tc_links_ingress(BPF_TCX_INGRESS, false, false);
+}
+
+struct qdisc_req {
+	struct nlmsghdr  n;
+	struct tcmsg     t;
+	char             buf[1024];
+};
+
+static int qdisc_replace(int ifindex, const char *kind, bool block)
+{
+	struct rtnl_handle rth = { .fd = -1 };
+	struct qdisc_req req;
+	int err;
+
+	err = rtnl_open(&rth, 0);
+	if (!ASSERT_OK(err, "open_rtnetlink"))
+		return err;
+
+	memset(&req, 0, sizeof(req));
+	req.n.nlmsg_len = NLMSG_LENGTH(sizeof(struct tcmsg));
+	req.n.nlmsg_flags = NLM_F_CREATE | NLM_F_REPLACE | NLM_F_REQUEST;
+	req.n.nlmsg_type = RTM_NEWQDISC;
+	req.t.tcm_family = AF_UNSPEC;
+	req.t.tcm_ifindex = ifindex;
+	req.t.tcm_parent = 0xfffffff1;
+
+	addattr_l(&req.n, sizeof(req), TCA_KIND, kind, strlen(kind) + 1);
+	if (block)
+		addattr32(&req.n, sizeof(req), TCA_INGRESS_BLOCK, 1);
+
+	err = rtnl_talk(&rth, &req.n, NULL);
+	ASSERT_OK(err, "talk_rtnetlink");
+	rtnl_close(&rth);
+	return err;
+}
+
+void serial_test_tc_links_dev_chain0(void)
+{
+	int err, ifindex;
+
+	ASSERT_OK(system("ip link add dev foo type veth peer name bar"), "add veth");
+	ifindex = if_nametoindex("foo");
+	ASSERT_NEQ(ifindex, 0, "non_zero_ifindex");
+	err = qdisc_replace(ifindex, "ingress", true);
+	if (!ASSERT_OK(err, "attaching ingress"))
+		goto cleanup;
+	ASSERT_OK(system("tc filter add block 1 matchall action skbmod swap mac"), "add block");
+	err = qdisc_replace(ifindex, "clsact", false);
+	if (!ASSERT_OK(err, "attaching clsact"))
+		goto cleanup;
+	/* Heuristic: kern_sync_rcu() alone does not work; a wait-time of ~5s
+	 * triggered the issue without the fix reliably 100% of the time.
+	 */
+	sleep(5);
+	ASSERT_OK(system("tc filter add dev foo ingress matchall action skbmod swap mac"), "add filter");
+cleanup:
+	ASSERT_OK(system("ip link del dev foo"), "del veth");
+	ASSERT_EQ(if_nametoindex("foo"), 0, "foo removed");
+	ASSERT_EQ(if_nametoindex("bar"), 0, "bar removed");
 }
 
 static void test_tc_links_dev_mixed(int target)

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

···
+// SPDX-License-Identifier: GPL-2.0
+
+#define _GNU_SOURCE
+#include <sched.h>
+#include <test_progs.h>
+#include <pthread.h>
+#include <network_helpers.h>
+
+#include "timer_lockup.skel.h"
+
+static long cpu;
+static int *timer1_err;
+static int *timer2_err;
+static bool skip;
+
+volatile int k = 0;
+
+static void *timer_lockup_thread(void *arg)
+{
+	LIBBPF_OPTS(bpf_test_run_opts, opts,
+		.data_in	= &pkt_v4,
+		.data_size_in	= sizeof(pkt_v4),
+		.repeat		= 1000,
+	);
+	int i, prog_fd = *(int *)arg;
+	cpu_set_t cpuset;
+
+	CPU_ZERO(&cpuset);
+	CPU_SET(__sync_fetch_and_add(&cpu, 1), &cpuset);
+	ASSERT_OK(pthread_setaffinity_np(pthread_self(), sizeof(cpuset),
+				         &cpuset),
+		  "cpu affinity");
+
+	for (i = 0; !READ_ONCE(*timer1_err) && !READ_ONCE(*timer2_err); i++) {
+		bpf_prog_test_run_opts(prog_fd, &opts);
+		/* Skip the test if we can't reproduce the race in a reasonable
+		 * amount of time.
+		 */
+		if (i > 50) {
+			WRITE_ONCE(skip, true);
+			break;
+		}
+	}
+
+	return NULL;
+}
+
+void test_timer_lockup(void)
+{
+	int timer1_prog, timer2_prog;
+	struct timer_lockup *skel;
+	pthread_t thrds[2];
+	void *ret;
+
+	skel = timer_lockup__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "timer_lockup__open_and_load"))
+		return;
+
+	timer1_prog = bpf_program__fd(skel->progs.timer1_prog);
+	timer2_prog = bpf_program__fd(skel->progs.timer2_prog);
+
+	timer1_err = &skel->bss->timer1_err;
+	timer2_err = &skel->bss->timer2_err;
+
+	if (!ASSERT_OK(pthread_create(&thrds[0], NULL, timer_lockup_thread,
+				      &timer1_prog),
+		       "pthread_create thread1"))
+		goto out;
+	if (!ASSERT_OK(pthread_create(&thrds[1], NULL, timer_lockup_thread,
+				      &timer2_prog),
+		       "pthread_create thread2")) {
+		pthread_exit(&thrds[0]);
+		goto out;
+	}
+
+	pthread_join(thrds[1], &ret);
+	pthread_join(thrds[0], &ret);
+
+	if (skip) {
+		test__skip();
+		goto out;
+	}
+
+	if (*timer1_err != -EDEADLK && *timer1_err != 0)
+		ASSERT_FAIL("timer1_err bad value");
+	if (*timer2_err != -EDEADLK && *timer2_err != 0)
+		ASSERT_FAIL("timer2_err bad value");
+out:
+	timer_lockup__destroy(skel);
+	return;
+}

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

···
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bpf.h>
+#include <time.h>
+#include <errno.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_misc.h"
+
+char _license[] SEC("license") = "GPL";
+
+struct elem {
+	struct bpf_timer t;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, int);
+	__type(value, struct elem);
+} timer1_map SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, int);
+	__type(value, struct elem);
+} timer2_map SEC(".maps");
+
+int timer1_err;
+int timer2_err;
+
+static int timer_cb1(void *map, int *k, struct elem *v)
+{
+	struct bpf_timer *timer;
+	int key = 0;
+
+	timer = bpf_map_lookup_elem(&timer2_map, &key);
+	if (timer)
+		timer2_err = bpf_timer_cancel(timer);
+
+	return 0;
+}
+
+static int timer_cb2(void *map, int *k, struct elem *v)
+{
+	struct bpf_timer *timer;
+	int key = 0;
+
+	timer = bpf_map_lookup_elem(&timer1_map, &key);
+	if (timer)
+		timer1_err = bpf_timer_cancel(timer);
+
+	return 0;
+}
+
+SEC("tc")
+int timer1_prog(void *ctx)
+{
+	struct bpf_timer *timer;
+	int key = 0;
+
+	timer = bpf_map_lookup_elem(&timer1_map, &key);
+	if (timer) {
+		bpf_timer_init(timer, &timer1_map, CLOCK_BOOTTIME);
+		bpf_timer_set_callback(timer, timer_cb1);
+		bpf_timer_start(timer, 1, BPF_F_TIMER_CPU_PIN);
+	}
+
+	return 0;
+}
+
+SEC("tc")
+int timer2_prog(void *ctx)
+{
+	struct bpf_timer *timer;
+	int key = 0;
+
+	timer = bpf_map_lookup_elem(&timer2_map, &key);
+	if (timer) {
+		bpf_timer_init(timer, &timer2_map, CLOCK_BOOTTIME);
+		bpf_timer_set_callback(timer, timer_cb2);
+		bpf_timer_start(timer, 1, BPF_F_TIMER_CPU_PIN);
+	}
+
+	return 0;
+}

tools/testing/selftests/powerpc/flags.mk

···
 export GIT_VERSION
 endif
 
-ifeq ($(CFLAGS),)
-CFLAGS := -std=gnu99 -O2 -Wall -Werror -DGIT_VERSION='"$(GIT_VERSION)"' -I$(selfdir)/powerpc/include $(CFLAGS)
+CFLAGS := -std=gnu99 -O2 -Wall -Werror -DGIT_VERSION='"$(GIT_VERSION)"' -I$(selfdir)/powerpc/include $(USERCFLAGS)
 export CFLAGS
-endif
-

tools/testing/selftests/riscv/sigreturn/sigreturn.c

···
 
 	asm(".option push				\n\
 		.option		arch, +v		\n\
-		vsetivli	x0, 1, e32, ta, ma	\n\
+		vsetivli	x0, 1, e32, m1, ta, ma	\n\
 		vmv.s.x		v0, %1			\n\
 		# Generate SIGSEGV			\n\
 		lw		a0, 0(x0)		\n\

tools/testing/selftests/timens/exec.c

···
 
 		for (i = 0; i < 2; i++) {
 			_gettime(CLOCK_MONOTONIC, &tst, i);
-			if (abs(tst.tv_sec - now.tv_sec) > 5)
+			if (labs(tst.tv_sec - now.tv_sec) > 5)
 				return pr_fail("%ld %ld\n", now.tv_sec, tst.tv_sec);
 		}
 		return 0;
···
 
 	for (i = 0; i < 2; i++) {
 		_gettime(CLOCK_MONOTONIC, &tst, i);
-		if (abs(tst.tv_sec - now.tv_sec) > 5)
+		if (labs(tst.tv_sec - now.tv_sec) > 5)
 			return pr_fail("%ld %ld\n",
 					now.tv_sec, tst.tv_sec);
 	}
···
 		/* Check that a child process is in the new timens. */
 		for (i = 0; i < 2; i++) {
 			_gettime(CLOCK_MONOTONIC, &tst, i);
-			if (abs(tst.tv_sec - now.tv_sec - OFFSET) > 5)
+			if (labs(tst.tv_sec - now.tv_sec - OFFSET) > 5)
 				return pr_fail("%ld %ld\n",
 						now.tv_sec + OFFSET, tst.tv_sec);
 		}

tools/testing/selftests/timens/timer.c

···
 			return pr_perror("timerfd_gettime");
 
 		elapsed = new_value.it_value.tv_sec;
-		if (abs(elapsed - 3600) > 60) {
+		if (llabs(elapsed - 3600) > 60) {
 			ksft_test_result_fail("clockid: %d elapsed: %lld\n",
 					      clockid, elapsed);
 			return 1;

tools/testing/selftests/timens/timerfd.c

···
 			return pr_perror("timerfd_gettime(%d)", clockid);
 
 		elapsed = new_value.it_value.tv_sec;
-		if (abs(elapsed - 3600) > 60) {
+		if (llabs(elapsed - 3600) > 60) {
 			ksft_test_result_fail("clockid: %d elapsed: %lld\n",
 					      clockid, elapsed);
 			return 1;

tools/testing/selftests/timens/vfork_exec.c

···
 
 	for (i = 0; i < 2; i++) {
 		_gettime(CLOCK_MONOTONIC, &tst, i);
-		if (abs(tst.tv_sec - now->tv_sec) > 5) {
+		if (labs(tst.tv_sec - now->tv_sec) > 5) {
 			pr_fail("%s: in-thread: unexpected value: %ld (%ld)\n",
 				args->tst_name, tst.tv_sec, now->tv_sec);
 			return (void *)1UL;
···
 
 	for (i = 0; i < 2; i++) {
 		_gettime(CLOCK_MONOTONIC, &tst, i);
-		if (abs(tst.tv_sec - now->tv_sec) > 5)
+		if (labs(tst.tv_sec - now->tv_sec) > 5)
 			return pr_fail("%s: unexpected value: %ld (%ld)\n",
 					tst_name, tst.tv_sec, now->tv_sec);
 	}

tools/testing/selftests/vDSO/Makefile

···
 # SPDX-License-Identifier: GPL-2.0
-include ../lib.mk
-
 uname_M := $(shell uname -m 2>/dev/null || echo not)
 ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/x86/ -e s/x86_64/x86/)
 
-TEST_GEN_PROGS := $(OUTPUT)/vdso_test_gettimeofday $(OUTPUT)/vdso_test_getcpu
-TEST_GEN_PROGS += $(OUTPUT)/vdso_test_abi
-TEST_GEN_PROGS += $(OUTPUT)/vdso_test_clock_getres
+TEST_GEN_PROGS := vdso_test_gettimeofday
+TEST_GEN_PROGS += vdso_test_getcpu
+TEST_GEN_PROGS += vdso_test_abi
+TEST_GEN_PROGS += vdso_test_clock_getres
 ifeq ($(ARCH),$(filter $(ARCH),x86 x86_64))
-TEST_GEN_PROGS += $(OUTPUT)/vdso_standalone_test_x86
+TEST_GEN_PROGS += vdso_standalone_test_x86
 endif
-TEST_GEN_PROGS += $(OUTPUT)/vdso_test_correctness
+TEST_GEN_PROGS += vdso_test_correctness
 
 CFLAGS := -std=gnu99
-CFLAGS_vdso_standalone_test_x86 := -nostdlib -fno-asynchronous-unwind-tables -fno-stack-protector
-LDFLAGS_vdso_test_correctness := -ldl
+
 ifeq ($(CONFIG_X86_32),y)
 LDLIBS += -lgcc_s
 endif
 
-all: $(TEST_GEN_PROGS)
+include ../lib.mk
 $(OUTPUT)/vdso_test_gettimeofday: parse_vdso.c vdso_test_gettimeofday.c
 $(OUTPUT)/vdso_test_getcpu: parse_vdso.c vdso_test_getcpu.c
 $(OUTPUT)/vdso_test_abi: parse_vdso.c vdso_test_abi.c
 $(OUTPUT)/vdso_test_clock_getres: vdso_test_clock_getres.c
+
 $(OUTPUT)/vdso_standalone_test_x86: vdso_standalone_test_x86.c parse_vdso.c
-	$(CC) $(CFLAGS) $(CFLAGS_vdso_standalone_test_x86) \
-		vdso_standalone_test_x86.c parse_vdso.c \
-		-o $@
+$(OUTPUT)/vdso_standalone_test_x86: CFLAGS +=-nostdlib -fno-asynchronous-unwind-tables -fno-stack-protector
+
 $(OUTPUT)/vdso_test_correctness: vdso_test_correctness.c
-	$(CC) $(CFLAGS) \
-		vdso_test_correctness.c \
-		-o $@ \
-		$(LDFLAGS_vdso_test_correctness)
+$(OUTPUT)/vdso_test_correctness: LDFLAGS += -ldl

tools/testing/selftests/vDSO/parse_vdso.c

···
 	ELF(Verdef) *verdef;
 } vdso_info;
 
-/* Straight from the ELF specification. */
-static unsigned long elf_hash(const unsigned char *name)
+/*
+ * Straight from the ELF specification...and then tweaked slightly, in order to
+ * avoid a few clang warnings.
+ */
+static unsigned long elf_hash(const char *name)
 {
 	unsigned long h = 0, g;
-	while (*name)
+	const unsigned char *uch_name = (const unsigned char *)name;
+
+	while (*uch_name)
 	{
-		h = (h << 4) + *name++;
-		if (g = h & 0xf0000000)
+		h = (h << 4) + *uch_name++;
+		g = h & 0xf0000000;
+		if (g)
 			h ^= g >> 24;
 		h &= ~g;
 	}

tools/testing/selftests/vDSO/vdso_standalone_test_x86.c

···
 
 #include "parse_vdso.h"
 
-/* We need a libc functions... */
+/* We need some libc functions... */
 int strcmp(const char *a, const char *b)
 {
 	/* This implementation is buggy: it never returns -1. */
···
 	}
 
 	return 0;
+}
+
+/*
+ * The clang build needs this, although gcc does not.
+ * Stolen from lib/string.c.
+ */
+void *memcpy(void *dest, const void *src, size_t count)
+{
+	char *tmp = dest;
+	const char *s = src;
+
+	while (count--)
+		*tmp++ = *s++;
+	return dest;
 }
 
 /* ...and two syscalls.  This is x86-specific. */
···
 	}
 }
 
-__attribute__((externally_visible)) void c_main(void **stack)
+void c_main(void **stack)
 {
 	/* Parse the stack */
 	long argc = (long)*stack;

tools/testing/selftests/wireguard/qemu/Makefile

···
 KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/x86/boot/bzImage
 QEMU_VPORT_RESULT := virtio-serial-device
 ifeq ($(HOST_ARCH),$(ARCH))
-QEMU_MACHINE := -cpu host -machine microvm,accel=kvm,pit=off,pic=off,rtc=off -no-acpi
+QEMU_MACHINE := -cpu host -machine microvm,accel=kvm,pit=off,pic=off,rtc=off,acpi=off
 else
-QEMU_MACHINE := -cpu max -machine microvm -no-acpi
+QEMU_MACHINE := -cpu max -machine microvm,acpi=off
 endif
 else ifeq ($(ARCH),i686)
 CHOST := i686-linux-musl
···
 KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/x86/boot/bzImage
 QEMU_VPORT_RESULT := virtio-serial-device
 ifeq ($(subst x86_64,i686,$(HOST_ARCH)),$(ARCH))
-QEMU_MACHINE := -cpu host -machine microvm,accel=kvm,pit=off,pic=off,rtc=off -no-acpi
+QEMU_MACHINE := -cpu host -machine microvm,accel=kvm,pit=off,pic=off,rtc=off,acpi=off
 else
-QEMU_MACHINE := -cpu coreduo -machine microvm -no-acpi
+QEMU_MACHINE := -cpu coreduo -machine microvm,acpi=off
 endif
 else ifeq ($(ARCH),mips64)
 CHOST := mips64-linux-musl