diff --git a/CREDITS b/CREDITS
index a357f9c..a687c3c3 100644
--- a/CREDITS
+++ b/CREDITS
@@ -3222,6 +3222,10 @@
 D: Starter of Linux1394 effort
 S: ask per mail for current address
 
+N: Boris Pismenny
+E: borisp@mellanox.com
+D: Kernel TLS implementation and offload support.
+
 N: Nicolas Pitre
 E: nico@fluxnic.net
 D: StrongARM SA1100 support integrator & hacker
@@ -4168,6 +4172,9 @@
 S: Carrollton, TX 75010
 S: USA
 
+N: Dave Watson
+D: Kernel TLS implementation.
+
 N: Tim Waugh
 E: tim@cyberelk.net
 D: Co-architect of the parallel-port sharing system
diff --git a/Documentation/admin-guide/hw-vuln/attack_vector_controls.rst b/Documentation/admin-guide/hw-vuln/attack_vector_controls.rst
index 6dd0800..5964901 100644
--- a/Documentation/admin-guide/hw-vuln/attack_vector_controls.rst
+++ b/Documentation/admin-guide/hw-vuln/attack_vector_controls.rst
@@ -215,7 +215,7 @@
 Spectre_v2_user                      X                           X            *       (Note 1)
 SRBDS                 X              X            X              X
 SRSO                  X              X            X              X
-SSB                                                                                   (Note 4)
+SSB                                  X
 TAA                   X              X            X              X            *       (Note 2)
 TSA                   X              X            X              X
 =============== ============== ============ ============= ============== ============ ========
@@ -229,9 +229,6 @@
    3 --  Disables SMT if cross-thread mitigations are fully enabled, the CPU is
    vulnerable, and STIBP is not supported
 
-   4 --  Speculative store bypass is always enabled by default (no kernel
-   mitigation applied) unless overridden with spec_store_bypass_disable option
-
 When an attack-vector is disabled, all mitigations for the vulnerabilities
 listed in the above table are disabled, unless mitigation is required for a
 different enabled attack-vector or a mitigation is explicitly selected via a
diff --git a/Documentation/devicetree/bindings/display/msm/qcom,mdp5.yaml b/Documentation/devicetree/bindings/display/msm/qcom,mdp5.yaml
index e153f8d2..2735c78 100644
--- a/Documentation/devicetree/bindings/display/msm/qcom,mdp5.yaml
+++ b/Documentation/devicetree/bindings/display/msm/qcom,mdp5.yaml
@@ -60,7 +60,6 @@
           - const: bus
           - const: core
           - const: vsync
-          - const: lut
           - const: tbu
           - const: tbu_rt
         # MSM8996 has additional iommu clock
diff --git a/Documentation/devicetree/bindings/vendor-prefixes.yaml b/Documentation/devicetree/bindings/vendor-prefixes.yaml
index 77160cd..9ec8947 100644
--- a/Documentation/devicetree/bindings/vendor-prefixes.yaml
+++ b/Documentation/devicetree/bindings/vendor-prefixes.yaml
@@ -507,6 +507,8 @@
     description: Espressif Systems Co. Ltd.
   "^est,.*":
     description: ESTeem Wireless Modems
+  "^eswin,.*":
+    description: Beijing ESWIN Technology Group Co. Ltd.
   "^ettus,.*":
     description: NI Ettus Research
   "^eukrea,.*":
diff --git a/MAINTAINERS b/MAINTAINERS
index fed6cd8..6dcfbd1 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -931,13 +931,13 @@
 F:	drivers/dma/altera-msgdma.c
 
 ALTERA PIO DRIVER
-M:	Mun Yew Tham <mun.yew.tham@intel.com>
+M:	Adrian Ng <adrianhoyin.ng@altera.com>
 L:	linux-gpio@vger.kernel.org
 S:	Maintained
 F:	drivers/gpio/gpio-altera.c
 
 ALTERA TRIPLE SPEED ETHERNET DRIVER
-M:	Joyce Ooi <joyce.ooi@intel.com>
+M:	Boon Khai Ng <boon.khai.ng@altera.com>
 L:	netdev@vger.kernel.org
 S:	Maintained
 F:	drivers/net/ethernet/altera/
@@ -4205,7 +4205,7 @@
 F:	drivers/net/hamradio/baycom*
 
 BCACHE (BLOCK LAYER CACHE)
-M:	Coly Li <colyli@kernel.org>
+M:	Coly Li <colyli@fnnas.com>
 M:	Kent Overstreet <kent.overstreet@linux.dev>
 L:	linux-bcache@vger.kernel.org
 S:	Maintained
@@ -4216,7 +4216,7 @@
 BCACHEFS
 M:	Kent Overstreet <kent.overstreet@linux.dev>
 L:	linux-bcachefs@vger.kernel.org
-S:	Supported
+S:	Externally maintained
 C:	irc://irc.oftc.net/bcache
 P:      Documentation/filesystems/bcachefs/SubmittingPatches.rst
 T:	git https://evilpiepirate.org/git/bcachefs.git
@@ -17848,7 +17848,6 @@
 F:	net/ipv6/tcp*.c
 
 NETWORKING [TLS]
-M:	Boris Pismenny <borisp@nvidia.com>
 M:	John Fastabend <john.fastabend@gmail.com>
 M:	Jakub Kicinski <kuba@kernel.org>
 L:	netdev@vger.kernel.org
@@ -20878,8 +20877,8 @@
 F:	drivers/firmware/qcom/qcom_qseecom_uefisecapp.c
 
 QUALCOMM RMNET DRIVER
-M:	Subash Abhinov Kasiviswanathan <quic_subashab@quicinc.com>
-M:	Sean Tranchetti <quic_stranche@quicinc.com>
+M:	Subash Abhinov Kasiviswanathan <subash.a.kasiviswanathan@oss.qualcomm.com>
+M:	Sean Tranchetti <sean.tranchetti@oss.qualcomm.com>
 L:	netdev@vger.kernel.org
 S:	Maintained
 F:	Documentation/networking/device_drivers/cellular/qualcomm/rmnet.rst
diff --git a/Makefile b/Makefile
index 06c28b1..b9c6619 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,7 @@
 VERSION = 6
 PATCHLEVEL = 17
 SUBLEVEL = 0
-EXTRAVERSION = -rc3
+EXTRAVERSION = -rc4
 NAME = Baby Opossum Posse
 
 # *DOCUMENTATION*
diff --git a/arch/arm/include/asm/stacktrace.h b/arch/arm/include/asm/stacktrace.h
index f80a85b..ba2f771 100644
--- a/arch/arm/include/asm/stacktrace.h
+++ b/arch/arm/include/asm/stacktrace.h
@@ -2,8 +2,9 @@
 #ifndef __ASM_STACKTRACE_H
 #define __ASM_STACKTRACE_H
 
-#include <asm/ptrace.h>
 #include <linux/llist.h>
+#include <asm/ptrace.h>
+#include <asm/sections.h>
 
 struct stackframe {
 	/*
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 2f2394c..2b07f0a 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -1160,115 +1160,8 @@ u64 kvm_vcpu_apply_reg_masks(const struct kvm_vcpu *, enum vcpu_sysreg, u64);
 		__v;							\
 	})
 
-u64 vcpu_read_sys_reg(const struct kvm_vcpu *vcpu, int reg);
-void vcpu_write_sys_reg(struct kvm_vcpu *vcpu, u64 val, int reg);
-
-static inline bool __vcpu_read_sys_reg_from_cpu(int reg, u64 *val)
-{
-	/*
-	 * *** VHE ONLY ***
-	 *
-	 * System registers listed in the switch are not saved on every
-	 * exit from the guest but are only saved on vcpu_put.
-	 *
-	 * SYSREGS_ON_CPU *MUST* be checked before using this helper.
-	 *
-	 * Note that MPIDR_EL1 for the guest is set by KVM via VMPIDR_EL2 but
-	 * should never be listed below, because the guest cannot modify its
-	 * own MPIDR_EL1 and MPIDR_EL1 is accessed for VCPU A from VCPU B's
-	 * thread when emulating cross-VCPU communication.
-	 */
-	if (!has_vhe())
-		return false;
-
-	switch (reg) {
-	case SCTLR_EL1:		*val = read_sysreg_s(SYS_SCTLR_EL12);	break;
-	case CPACR_EL1:		*val = read_sysreg_s(SYS_CPACR_EL12);	break;
-	case TTBR0_EL1:		*val = read_sysreg_s(SYS_TTBR0_EL12);	break;
-	case TTBR1_EL1:		*val = read_sysreg_s(SYS_TTBR1_EL12);	break;
-	case TCR_EL1:		*val = read_sysreg_s(SYS_TCR_EL12);	break;
-	case TCR2_EL1:		*val = read_sysreg_s(SYS_TCR2_EL12);	break;
-	case PIR_EL1:		*val = read_sysreg_s(SYS_PIR_EL12);	break;
-	case PIRE0_EL1:		*val = read_sysreg_s(SYS_PIRE0_EL12);	break;
-	case POR_EL1:		*val = read_sysreg_s(SYS_POR_EL12);	break;
-	case ESR_EL1:		*val = read_sysreg_s(SYS_ESR_EL12);	break;
-	case AFSR0_EL1:		*val = read_sysreg_s(SYS_AFSR0_EL12);	break;
-	case AFSR1_EL1:		*val = read_sysreg_s(SYS_AFSR1_EL12);	break;
-	case FAR_EL1:		*val = read_sysreg_s(SYS_FAR_EL12);	break;
-	case MAIR_EL1:		*val = read_sysreg_s(SYS_MAIR_EL12);	break;
-	case VBAR_EL1:		*val = read_sysreg_s(SYS_VBAR_EL12);	break;
-	case CONTEXTIDR_EL1:	*val = read_sysreg_s(SYS_CONTEXTIDR_EL12);break;
-	case TPIDR_EL0:		*val = read_sysreg_s(SYS_TPIDR_EL0);	break;
-	case TPIDRRO_EL0:	*val = read_sysreg_s(SYS_TPIDRRO_EL0);	break;
-	case TPIDR_EL1:		*val = read_sysreg_s(SYS_TPIDR_EL1);	break;
-	case AMAIR_EL1:		*val = read_sysreg_s(SYS_AMAIR_EL12);	break;
-	case CNTKCTL_EL1:	*val = read_sysreg_s(SYS_CNTKCTL_EL12);	break;
-	case ELR_EL1:		*val = read_sysreg_s(SYS_ELR_EL12);	break;
-	case SPSR_EL1:		*val = read_sysreg_s(SYS_SPSR_EL12);	break;
-	case PAR_EL1:		*val = read_sysreg_par();		break;
-	case DACR32_EL2:	*val = read_sysreg_s(SYS_DACR32_EL2);	break;
-	case IFSR32_EL2:	*val = read_sysreg_s(SYS_IFSR32_EL2);	break;
-	case DBGVCR32_EL2:	*val = read_sysreg_s(SYS_DBGVCR32_EL2);	break;
-	case ZCR_EL1:		*val = read_sysreg_s(SYS_ZCR_EL12);	break;
-	case SCTLR2_EL1:	*val = read_sysreg_s(SYS_SCTLR2_EL12);	break;
-	default:		return false;
-	}
-
-	return true;
-}
-
-static inline bool __vcpu_write_sys_reg_to_cpu(u64 val, int reg)
-{
-	/*
-	 * *** VHE ONLY ***
-	 *
-	 * System registers listed in the switch are not restored on every
-	 * entry to the guest but are only restored on vcpu_load.
-	 *
-	 * SYSREGS_ON_CPU *MUST* be checked before using this helper.
-	 *
-	 * Note that MPIDR_EL1 for the guest is set by KVM via VMPIDR_EL2 but
-	 * should never be listed below, because the MPIDR should only be set
-	 * once, before running the VCPU, and never changed later.
-	 */
-	if (!has_vhe())
-		return false;
-
-	switch (reg) {
-	case SCTLR_EL1:		write_sysreg_s(val, SYS_SCTLR_EL12);	break;
-	case CPACR_EL1:		write_sysreg_s(val, SYS_CPACR_EL12);	break;
-	case TTBR0_EL1:		write_sysreg_s(val, SYS_TTBR0_EL12);	break;
-	case TTBR1_EL1:		write_sysreg_s(val, SYS_TTBR1_EL12);	break;
-	case TCR_EL1:		write_sysreg_s(val, SYS_TCR_EL12);	break;
-	case TCR2_EL1:		write_sysreg_s(val, SYS_TCR2_EL12);	break;
-	case PIR_EL1:		write_sysreg_s(val, SYS_PIR_EL12);	break;
-	case PIRE0_EL1:		write_sysreg_s(val, SYS_PIRE0_EL12);	break;
-	case POR_EL1:		write_sysreg_s(val, SYS_POR_EL12);	break;
-	case ESR_EL1:		write_sysreg_s(val, SYS_ESR_EL12);	break;
-	case AFSR0_EL1:		write_sysreg_s(val, SYS_AFSR0_EL12);	break;
-	case AFSR1_EL1:		write_sysreg_s(val, SYS_AFSR1_EL12);	break;
-	case FAR_EL1:		write_sysreg_s(val, SYS_FAR_EL12);	break;
-	case MAIR_EL1:		write_sysreg_s(val, SYS_MAIR_EL12);	break;
-	case VBAR_EL1:		write_sysreg_s(val, SYS_VBAR_EL12);	break;
-	case CONTEXTIDR_EL1:	write_sysreg_s(val, SYS_CONTEXTIDR_EL12);break;
-	case TPIDR_EL0:		write_sysreg_s(val, SYS_TPIDR_EL0);	break;
-	case TPIDRRO_EL0:	write_sysreg_s(val, SYS_TPIDRRO_EL0);	break;
-	case TPIDR_EL1:		write_sysreg_s(val, SYS_TPIDR_EL1);	break;
-	case AMAIR_EL1:		write_sysreg_s(val, SYS_AMAIR_EL12);	break;
-	case CNTKCTL_EL1:	write_sysreg_s(val, SYS_CNTKCTL_EL12);	break;
-	case ELR_EL1:		write_sysreg_s(val, SYS_ELR_EL12);	break;
-	case SPSR_EL1:		write_sysreg_s(val, SYS_SPSR_EL12);	break;
-	case PAR_EL1:		write_sysreg_s(val, SYS_PAR_EL1);	break;
-	case DACR32_EL2:	write_sysreg_s(val, SYS_DACR32_EL2);	break;
-	case IFSR32_EL2:	write_sysreg_s(val, SYS_IFSR32_EL2);	break;
-	case DBGVCR32_EL2:	write_sysreg_s(val, SYS_DBGVCR32_EL2);	break;
-	case ZCR_EL1:		write_sysreg_s(val, SYS_ZCR_EL12);	break;
-	case SCTLR2_EL1:	write_sysreg_s(val, SYS_SCTLR2_EL12);	break;
-	default:		return false;
-	}
-
-	return true;
-}
+u64 vcpu_read_sys_reg(const struct kvm_vcpu *, enum vcpu_sysreg);
+void vcpu_write_sys_reg(struct kvm_vcpu *, u64, enum vcpu_sysreg);
 
 struct kvm_vm_stat {
 	struct kvm_vm_stat_generic generic;
diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index ae563eb..e4069f2 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -180,6 +180,7 @@ void kvm_free_stage2_pgd(struct kvm_s2_mmu *mmu);
 int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa,
 			  phys_addr_t pa, unsigned long size, bool writable);
 
+int kvm_handle_guest_sea(struct kvm_vcpu *vcpu);
 int kvm_handle_guest_abort(struct kvm_vcpu *vcpu);
 
 phys_addr_t kvm_mmu_get_httbr(void);
diff --git a/arch/arm64/include/asm/kvm_pgtable.h b/arch/arm64/include/asm/kvm_pgtable.h
index 2888b5d..1246216 100644
--- a/arch/arm64/include/asm/kvm_pgtable.h
+++ b/arch/arm64/include/asm/kvm_pgtable.h
@@ -355,6 +355,11 @@ static inline kvm_pte_t *kvm_dereference_pteref(struct kvm_pgtable_walker *walke
 	return pteref;
 }
 
+static inline kvm_pte_t *kvm_dereference_pteref_raw(kvm_pteref_t pteref)
+{
+	return pteref;
+}
+
 static inline int kvm_pgtable_walk_begin(struct kvm_pgtable_walker *walker)
 {
 	/*
@@ -384,6 +389,11 @@ static inline kvm_pte_t *kvm_dereference_pteref(struct kvm_pgtable_walker *walke
 	return rcu_dereference_check(pteref, !(walker->flags & KVM_PGTABLE_WALK_SHARED));
 }
 
+static inline kvm_pte_t *kvm_dereference_pteref_raw(kvm_pteref_t pteref)
+{
+	return rcu_dereference_raw(pteref);
+}
+
 static inline int kvm_pgtable_walk_begin(struct kvm_pgtable_walker *walker)
 {
 	if (walker->flags & KVM_PGTABLE_WALK_SHARED)
@@ -552,6 +562,26 @@ static inline int kvm_pgtable_stage2_init(struct kvm_pgtable *pgt, struct kvm_s2
 void kvm_pgtable_stage2_destroy(struct kvm_pgtable *pgt);
 
 /**
+ * kvm_pgtable_stage2_destroy_range() - Destroy the unlinked range of addresses.
+ * @pgt:	Page-table structure initialised by kvm_pgtable_stage2_init*().
+ * @addr:      Intermediate physical address at which to place the mapping.
+ * @size:      Size of the mapping.
+ *
+ * The page-table is assumed to be unreachable by any hardware walkers prior
+ * to freeing and therefore no TLB invalidation is performed.
+ */
+void kvm_pgtable_stage2_destroy_range(struct kvm_pgtable *pgt,
+					u64 addr, u64 size);
+
+/**
+ * kvm_pgtable_stage2_destroy_pgd() - Destroy the PGD of guest stage-2 page-table.
+ * @pgt:       Page-table structure initialised by kvm_pgtable_stage2_init*().
+ *
+ * It is assumed that the rest of the page-table is freed before this operation.
+ */
+void kvm_pgtable_stage2_destroy_pgd(struct kvm_pgtable *pgt);
+
+/**
  * kvm_pgtable_stage2_free_unlinked() - Free an unlinked stage-2 paging structure.
  * @mm_ops:	Memory management callbacks.
  * @pgtable:	Unlinked stage-2 paging structure to be freed.
diff --git a/arch/arm64/include/asm/kvm_pkvm.h b/arch/arm64/include/asm/kvm_pkvm.h
index ea58282..35f9d94 100644
--- a/arch/arm64/include/asm/kvm_pkvm.h
+++ b/arch/arm64/include/asm/kvm_pkvm.h
@@ -179,7 +179,9 @@ struct pkvm_mapping {
 
 int pkvm_pgtable_stage2_init(struct kvm_pgtable *pgt, struct kvm_s2_mmu *mmu,
 			     struct kvm_pgtable_mm_ops *mm_ops);
-void pkvm_pgtable_stage2_destroy(struct kvm_pgtable *pgt);
+void pkvm_pgtable_stage2_destroy_range(struct kvm_pgtable *pgt,
+					u64 addr, u64 size);
+void pkvm_pgtable_stage2_destroy_pgd(struct kvm_pgtable *pgt);
 int pkvm_pgtable_stage2_map(struct kvm_pgtable *pgt, u64 addr, u64 size, u64 phys,
 			    enum kvm_pgtable_prot prot, void *mc,
 			    enum kvm_pgtable_walk_flags flags);
diff --git a/arch/arm64/include/asm/kvm_ras.h b/arch/arm64/include/asm/kvm_ras.h
deleted file mode 100644
index 9398ade..0000000
--- a/arch/arm64/include/asm/kvm_ras.h
+++ /dev/null
@@ -1,25 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright (C) 2018 - Arm Ltd */
-
-#ifndef __ARM64_KVM_RAS_H__
-#define __ARM64_KVM_RAS_H__
-
-#include <linux/acpi.h>
-#include <linux/errno.h>
-#include <linux/types.h>
-
-#include <asm/acpi.h>
-
-/*
- * Was this synchronous external abort a RAS notification?
- * Returns '0' for errors handled by some RAS subsystem, or -ENOENT.
- */
-static inline int kvm_handle_guest_sea(void)
-{
-	/* apei_claim_sea(NULL) expects to mask interrupts itself */
-	lockdep_assert_irqs_enabled();
-
-	return apei_claim_sea(NULL);
-}
-
-#endif /* __ARM64_KVM_RAS_H__ */
diff --git a/arch/arm64/include/asm/mmu.h b/arch/arm64/include/asm/mmu.h
index 6e8aa8e..49f1a81 100644
--- a/arch/arm64/include/asm/mmu.h
+++ b/arch/arm64/include/asm/mmu.h
@@ -17,6 +17,13 @@
 #include <linux/refcount.h>
 #include <asm/cpufeature.h>
 
+enum pgtable_type {
+	TABLE_PTE,
+	TABLE_PMD,
+	TABLE_PUD,
+	TABLE_P4D,
+};
+
 typedef struct {
 	atomic64_t	id;
 #ifdef CONFIG_COMPAT
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index d5b5f2ae..6604fd6 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -1142,9 +1142,6 @@
 
 #define ARM64_FEATURE_FIELD_BITS	4
 
-/* Defined for compatibility only, do not add new users. */
-#define ARM64_FEATURE_MASK(x)	(x##_MASK)
-
 #ifdef __ASSEMBLY__
 
 	.macro	mrs_s, rt, sreg
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index 9ad065f..ef269a5 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -84,6 +84,7 @@
 #include <asm/hwcap.h>
 #include <asm/insn.h>
 #include <asm/kvm_host.h>
+#include <asm/mmu.h>
 #include <asm/mmu_context.h>
 #include <asm/mte.h>
 #include <asm/hypervisor.h>
@@ -1945,11 +1946,11 @@ static bool has_pmuv3(const struct arm64_cpu_capabilities *entry, int scope)
 extern
 void create_kpti_ng_temp_pgd(pgd_t *pgdir, phys_addr_t phys, unsigned long virt,
 			     phys_addr_t size, pgprot_t prot,
-			     phys_addr_t (*pgtable_alloc)(int), int flags);
+			     phys_addr_t (*pgtable_alloc)(enum pgtable_type), int flags);
 
 static phys_addr_t __initdata kpti_ng_temp_alloc;
 
-static phys_addr_t __init kpti_ng_pgd_alloc(int shift)
+static phys_addr_t __init kpti_ng_pgd_alloc(enum pgtable_type type)
 {
 	kpti_ng_temp_alloc -= PAGE_SIZE;
 	return kpti_ng_temp_alloc;
@@ -2269,6 +2270,24 @@ static void cpu_clear_disr(const struct arm64_cpu_capabilities *__unused)
 	/* Firmware may have left a deferred SError in this register. */
 	write_sysreg_s(0, SYS_DISR_EL1);
 }
+static bool has_rasv1p1(const struct arm64_cpu_capabilities *__unused, int scope)
+{
+	const struct arm64_cpu_capabilities rasv1p1_caps[] = {
+		{
+			ARM64_CPUID_FIELDS(ID_AA64PFR0_EL1, RAS, V1P1)
+		},
+		{
+			ARM64_CPUID_FIELDS(ID_AA64PFR0_EL1, RAS, IMP)
+		},
+		{
+			ARM64_CPUID_FIELDS(ID_AA64PFR1_EL1, RAS_frac, RASv1p1)
+		},
+	};
+
+	return (has_cpuid_feature(&rasv1p1_caps[0], scope) ||
+		(has_cpuid_feature(&rasv1p1_caps[1], scope) &&
+		 has_cpuid_feature(&rasv1p1_caps[2], scope)));
+}
 #endif /* CONFIG_ARM64_RAS_EXTN */
 
 #ifdef CONFIG_ARM64_PTR_AUTH
@@ -2687,6 +2706,12 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 		.cpu_enable = cpu_clear_disr,
 		ARM64_CPUID_FIELDS(ID_AA64PFR0_EL1, RAS, IMP)
 	},
+	{
+		.desc = "RASv1p1 Extension Support",
+		.capability = ARM64_HAS_RASV1P1_EXTN,
+		.type = ARM64_CPUCAP_SYSTEM_FEATURE,
+		.matches = has_rasv1p1,
+	},
 #endif /* CONFIG_ARM64_RAS_EXTN */
 #ifdef CONFIG_ARM64_AMU_EXTN
 	{
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 888f7c7..5bf101c8 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -2408,12 +2408,12 @@ static u64 get_hyp_id_aa64pfr0_el1(void)
 	 */
 	u64 val = read_sanitised_ftr_reg(SYS_ID_AA64PFR0_EL1);
 
-	val &= ~(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_CSV2) |
-		 ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_CSV3));
+	val &= ~(ID_AA64PFR0_EL1_CSV2 |
+		 ID_AA64PFR0_EL1_CSV3);
 
-	val |= FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_CSV2),
+	val |= FIELD_PREP(ID_AA64PFR0_EL1_CSV2,
 			  arm64_get_spectre_v2_state() == SPECTRE_UNAFFECTED);
-	val |= FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_CSV3),
+	val |= FIELD_PREP(ID_AA64PFR0_EL1_CSV3,
 			  arm64_get_meltdown_state() == SPECTRE_UNAFFECTED);
 
 	return val;
diff --git a/arch/arm64/kvm/at.c b/arch/arm64/kvm/at.c
index 0e56105..d71ca4d 100644
--- a/arch/arm64/kvm/at.c
+++ b/arch/arm64/kvm/at.c
@@ -1420,10 +1420,10 @@ void __kvm_at_s12(struct kvm_vcpu *vcpu, u32 op, u64 vaddr)
 		return;
 
 	/*
-	 * If we only have a single stage of translation (E2H=0 or
-	 * TGE=1), exit early. Same thing if {VM,DC}=={0,0}.
+	 * If we only have a single stage of translation (EL2&0), exit
+	 * early. Same thing if {VM,DC}=={0,0}.
 	 */
-	if (!vcpu_el2_e2h_is_set(vcpu) || vcpu_el2_tge_is_set(vcpu) ||
+	if (compute_translation_regime(vcpu, op) == TR_EL20 ||
 	    !(vcpu_read_sys_reg(vcpu, HCR_EL2) & (HCR_VM | HCR_DC)))
 		return;
 
diff --git a/arch/arm64/kvm/emulate-nested.c b/arch/arm64/kvm/emulate-nested.c
index 90cb4b7..af69c89 100644
--- a/arch/arm64/kvm/emulate-nested.c
+++ b/arch/arm64/kvm/emulate-nested.c
@@ -2833,7 +2833,7 @@ int kvm_inject_nested_sea(struct kvm_vcpu *vcpu, bool iabt, u64 addr)
 			     iabt ? ESR_ELx_EC_IABT_LOW : ESR_ELx_EC_DABT_LOW);
 	esr |= ESR_ELx_FSC_EXTABT | ESR_ELx_IL;
 
-	vcpu_write_sys_reg(vcpu, FAR_EL2, addr);
+	vcpu_write_sys_reg(vcpu, addr, FAR_EL2);
 
 	if (__vcpu_sys_reg(vcpu, SCTLR2_EL2) & SCTLR2_EL1_EASE)
 		return kvm_inject_nested(vcpu, esr, except_type_serror);
diff --git a/arch/arm64/kvm/hyp/exception.c b/arch/arm64/kvm/hyp/exception.c
index 95d186e..bef40dd 100644
--- a/arch/arm64/kvm/hyp/exception.c
+++ b/arch/arm64/kvm/hyp/exception.c
@@ -22,36 +22,28 @@
 
 static inline u64 __vcpu_read_sys_reg(const struct kvm_vcpu *vcpu, int reg)
 {
-	u64 val;
-
-	if (unlikely(vcpu_has_nv(vcpu)))
+	if (has_vhe())
 		return vcpu_read_sys_reg(vcpu, reg);
-	else if (vcpu_get_flag(vcpu, SYSREGS_ON_CPU) &&
-		 __vcpu_read_sys_reg_from_cpu(reg, &val))
-		return val;
 
 	return __vcpu_sys_reg(vcpu, reg);
 }
 
 static inline void __vcpu_write_sys_reg(struct kvm_vcpu *vcpu, u64 val, int reg)
 {
-	if (unlikely(vcpu_has_nv(vcpu)))
+	if (has_vhe())
 		vcpu_write_sys_reg(vcpu, val, reg);
-	else if (!vcpu_get_flag(vcpu, SYSREGS_ON_CPU) ||
-		 !__vcpu_write_sys_reg_to_cpu(val, reg))
+	else
 		__vcpu_assign_sys_reg(vcpu, reg, val);
 }
 
 static void __vcpu_write_spsr(struct kvm_vcpu *vcpu, unsigned long target_mode,
 			      u64 val)
 {
-	if (unlikely(vcpu_has_nv(vcpu))) {
+	if (has_vhe()) {
 		if (target_mode == PSR_MODE_EL1h)
 			vcpu_write_sys_reg(vcpu, val, SPSR_EL1);
 		else
 			vcpu_write_sys_reg(vcpu, val, SPSR_EL2);
-	} else if (has_vhe()) {
-		write_sysreg_el1(val, SYS_SPSR);
 	} else {
 		__vcpu_assign_sys_reg(vcpu, SPSR_EL1, val);
 	}
@@ -59,7 +51,7 @@ static void __vcpu_write_spsr(struct kvm_vcpu *vcpu, unsigned long target_mode,
 
 static void __vcpu_write_spsr_abt(struct kvm_vcpu *vcpu, u64 val)
 {
-	if (has_vhe())
+	if (has_vhe() && vcpu_get_flag(vcpu, SYSREGS_ON_CPU))
 		write_sysreg(val, spsr_abt);
 	else
 		vcpu->arch.ctxt.spsr_abt = val;
@@ -67,7 +59,7 @@ static void __vcpu_write_spsr_abt(struct kvm_vcpu *vcpu, u64 val)
 
 static void __vcpu_write_spsr_und(struct kvm_vcpu *vcpu, u64 val)
 {
-	if (has_vhe())
+	if (has_vhe() && vcpu_get_flag(vcpu, SYSREGS_ON_CPU))
 		write_sysreg(val, spsr_und);
 	else
 		vcpu->arch.ctxt.spsr_und = val;
diff --git a/arch/arm64/kvm/hyp/nvhe/list_debug.c b/arch/arm64/kvm/hyp/nvhe/list_debug.c
index 46a2d4f..baa6260 100644
--- a/arch/arm64/kvm/hyp/nvhe/list_debug.c
+++ b/arch/arm64/kvm/hyp/nvhe/list_debug.c
@@ -17,7 +17,7 @@ static inline __must_check bool nvhe_check_data_corruption(bool v)
 		bool corruption = unlikely(condition);			 \
 		if (corruption) {					 \
 			if (IS_ENABLED(CONFIG_BUG_ON_DATA_CORRUPTION)) { \
-				BUG_ON(1);				 \
+				BUG();				 	 \
 			} else						 \
 				WARN_ON(1);				 \
 		}							 \
diff --git a/arch/arm64/kvm/hyp/nvhe/sys_regs.c b/arch/arm64/kvm/hyp/nvhe/sys_regs.c
index 1ddd9ed..71d2fc9 100644
--- a/arch/arm64/kvm/hyp/nvhe/sys_regs.c
+++ b/arch/arm64/kvm/hyp/nvhe/sys_regs.c
@@ -253,6 +253,7 @@ static void inject_undef64(struct kvm_vcpu *vcpu)
 
 	*vcpu_pc(vcpu) = read_sysreg_el2(SYS_ELR);
 	*vcpu_cpsr(vcpu) = read_sysreg_el2(SYS_SPSR);
+	__vcpu_assign_sys_reg(vcpu, read_sysreg_el1(SYS_VBAR), VBAR_EL1);
 
 	kvm_pend_exception(vcpu, EXCEPT_AA64_EL1_SYNC);
 
@@ -372,6 +373,9 @@ static const struct sys_reg_desc pvm_sys_reg_descs[] = {
 
 	/* Debug and Trace Registers are restricted. */
 
+	/* Group 1 ID registers */
+	HOST_HANDLED(SYS_REVIDR_EL1),
+
 	/* AArch64 mappings of the AArch32 ID registers */
 	/* CRm=1 */
 	AARCH32(SYS_ID_PFR0_EL1),
@@ -460,6 +464,7 @@ static const struct sys_reg_desc pvm_sys_reg_descs[] = {
 
 	HOST_HANDLED(SYS_CCSIDR_EL1),
 	HOST_HANDLED(SYS_CLIDR_EL1),
+	HOST_HANDLED(SYS_AIDR_EL1),
 	HOST_HANDLED(SYS_CSSELR_EL1),
 	HOST_HANDLED(SYS_CTR_EL0),
 
diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c
index c351b4a..c36f282 100644
--- a/arch/arm64/kvm/hyp/pgtable.c
+++ b/arch/arm64/kvm/hyp/pgtable.c
@@ -1551,21 +1551,38 @@ static int stage2_free_walker(const struct kvm_pgtable_visit_ctx *ctx,
 	return 0;
 }
 
-void kvm_pgtable_stage2_destroy(struct kvm_pgtable *pgt)
+void kvm_pgtable_stage2_destroy_range(struct kvm_pgtable *pgt,
+				       u64 addr, u64 size)
 {
-	size_t pgd_sz;
 	struct kvm_pgtable_walker walker = {
 		.cb	= stage2_free_walker,
 		.flags	= KVM_PGTABLE_WALK_LEAF |
 			  KVM_PGTABLE_WALK_TABLE_POST,
 	};
 
-	WARN_ON(kvm_pgtable_walk(pgt, 0, BIT(pgt->ia_bits), &walker));
+	WARN_ON(kvm_pgtable_walk(pgt, addr, size, &walker));
+}
+
+void kvm_pgtable_stage2_destroy_pgd(struct kvm_pgtable *pgt)
+{
+	size_t pgd_sz;
+
 	pgd_sz = kvm_pgd_pages(pgt->ia_bits, pgt->start_level) * PAGE_SIZE;
-	pgt->mm_ops->free_pages_exact(kvm_dereference_pteref(&walker, pgt->pgd), pgd_sz);
+
+	/*
+	 * Since the pgtable is unlinked at this point, and not shared with
+	 * other walkers, safely deference pgd with kvm_dereference_pteref_raw()
+	 */
+	pgt->mm_ops->free_pages_exact(kvm_dereference_pteref_raw(pgt->pgd), pgd_sz);
 	pgt->pgd = NULL;
 }
 
+void kvm_pgtable_stage2_destroy(struct kvm_pgtable *pgt)
+{
+	kvm_pgtable_stage2_destroy_range(pgt, 0, BIT(pgt->ia_bits));
+	kvm_pgtable_stage2_destroy_pgd(pgt);
+}
+
 void kvm_pgtable_stage2_free_unlinked(struct kvm_pgtable_mm_ops *mm_ops, void *pgtable, s8 level)
 {
 	kvm_pteref_t ptep = (kvm_pteref_t)pgtable;
diff --git a/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c b/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c
index 87a5437..78579b3 100644
--- a/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c
+++ b/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c
@@ -20,7 +20,7 @@ static bool __is_be(struct kvm_vcpu *vcpu)
 	if (vcpu_mode_is_32bit(vcpu))
 		return !!(read_sysreg_el2(SYS_SPSR) & PSR_AA32_E_BIT);
 
-	return !!(read_sysreg(SCTLR_EL1) & SCTLR_ELx_EE);
+	return !!(read_sysreg_el1(SYS_SCTLR) & SCTLR_ELx_EE);
 }
 
 /*
diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c
index e482181..0998ad4 100644
--- a/arch/arm64/kvm/hyp/vhe/switch.c
+++ b/arch/arm64/kvm/hyp/vhe/switch.c
@@ -43,8 +43,11 @@ DEFINE_PER_CPU(unsigned long, kvm_hyp_vector);
  *
  * - API/APK: they are already accounted for by vcpu_load(), and can
  *   only take effect across a load/put cycle (such as ERET)
+ *
+ * - FIEN: no way we let a guest have access to the RAS "Common Fault
+ *   Injection" thing, whatever that does
  */
-#define NV_HCR_GUEST_EXCLUDE	(HCR_TGE | HCR_API | HCR_APK)
+#define NV_HCR_GUEST_EXCLUDE	(HCR_TGE | HCR_API | HCR_APK | HCR_FIEN)
 
 static u64 __compute_hcr(struct kvm_vcpu *vcpu)
 {
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 1c78864..86f3d80 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -4,19 +4,20 @@
  * Author: Christoffer Dall <c.dall@virtualopensystems.com>
  */
 
+#include <linux/acpi.h>
 #include <linux/mman.h>
 #include <linux/kvm_host.h>
 #include <linux/io.h>
 #include <linux/hugetlb.h>
 #include <linux/sched/signal.h>
 #include <trace/events/kvm.h>
+#include <asm/acpi.h>
 #include <asm/pgalloc.h>
 #include <asm/cacheflush.h>
 #include <asm/kvm_arm.h>
 #include <asm/kvm_mmu.h>
 #include <asm/kvm_pgtable.h>
 #include <asm/kvm_pkvm.h>
-#include <asm/kvm_ras.h>
 #include <asm/kvm_asm.h>
 #include <asm/kvm_emulate.h>
 #include <asm/virt.h>
@@ -903,6 +904,38 @@ static int kvm_init_ipa_range(struct kvm_s2_mmu *mmu, unsigned long type)
 	return 0;
 }
 
+/*
+ * Assume that @pgt is valid and unlinked from the KVM MMU to free the
+ * page-table without taking the kvm_mmu_lock and without performing any
+ * TLB invalidations.
+ *
+ * Also, the range of addresses can be large enough to cause need_resched
+ * warnings, for instance on CONFIG_PREEMPT_NONE kernels. Hence, invoke
+ * cond_resched() periodically to prevent hogging the CPU for a long time
+ * and schedule something else, if required.
+ */
+static void stage2_destroy_range(struct kvm_pgtable *pgt, phys_addr_t addr,
+				   phys_addr_t end)
+{
+	u64 next;
+
+	do {
+		next = stage2_range_addr_end(addr, end);
+		KVM_PGT_FN(kvm_pgtable_stage2_destroy_range)(pgt, addr,
+								next - addr);
+		if (next != end)
+			cond_resched();
+	} while (addr = next, addr != end);
+}
+
+static void kvm_stage2_destroy(struct kvm_pgtable *pgt)
+{
+	unsigned int ia_bits = VTCR_EL2_IPA(pgt->mmu->vtcr);
+
+	stage2_destroy_range(pgt, 0, BIT(ia_bits));
+	KVM_PGT_FN(kvm_pgtable_stage2_destroy_pgd)(pgt);
+}
+
 /**
  * kvm_init_stage2_mmu - Initialise a S2 MMU structure
  * @kvm:	The pointer to the KVM structure
@@ -979,7 +1012,7 @@ int kvm_init_stage2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu, unsigned long t
 	return 0;
 
 out_destroy_pgtable:
-	KVM_PGT_FN(kvm_pgtable_stage2_destroy)(pgt);
+	kvm_stage2_destroy(pgt);
 out_free_pgtable:
 	kfree(pgt);
 	return err;
@@ -1076,7 +1109,7 @@ void kvm_free_stage2_pgd(struct kvm_s2_mmu *mmu)
 	write_unlock(&kvm->mmu_lock);
 
 	if (pgt) {
-		KVM_PGT_FN(kvm_pgtable_stage2_destroy)(pgt);
+		kvm_stage2_destroy(pgt);
 		kfree(pgt);
 	}
 }
@@ -1811,6 +1844,19 @@ static void handle_access_fault(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa)
 	read_unlock(&vcpu->kvm->mmu_lock);
 }
 
+int kvm_handle_guest_sea(struct kvm_vcpu *vcpu)
+{
+	/*
+	 * Give APEI the opportunity to claim the abort before handling it
+	 * within KVM. apei_claim_sea() expects to be called with IRQs enabled.
+	 */
+	lockdep_assert_irqs_enabled();
+	if (apei_claim_sea(NULL) == 0)
+		return 1;
+
+	return kvm_inject_serror(vcpu);
+}
+
 /**
  * kvm_handle_guest_abort - handles all 2nd stage aborts
  * @vcpu:	the VCPU pointer
@@ -1834,17 +1880,8 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu)
 	gfn_t gfn;
 	int ret, idx;
 
-	/* Synchronous External Abort? */
-	if (kvm_vcpu_abt_issea(vcpu)) {
-		/*
-		 * For RAS the host kernel may handle this abort.
-		 * There is no need to pass the error into the guest.
-		 */
-		if (kvm_handle_guest_sea())
-			return kvm_inject_serror(vcpu);
-
-		return 1;
-	}
+	if (kvm_vcpu_abt_issea(vcpu))
+		return kvm_handle_guest_sea(vcpu);
 
 	esr = kvm_vcpu_get_esr(vcpu);
 
diff --git a/arch/arm64/kvm/nested.c b/arch/arm64/kvm/nested.c
index 153b3e11b..77db81b 100644
--- a/arch/arm64/kvm/nested.c
+++ b/arch/arm64/kvm/nested.c
@@ -1287,7 +1287,10 @@ int kvm_handle_vncr_abort(struct kvm_vcpu *vcpu)
 	struct vncr_tlb *vt = vcpu->arch.vncr_tlb;
 	u64 esr = kvm_vcpu_get_esr(vcpu);
 
-	BUG_ON(!(esr & ESR_ELx_VNCR_SHIFT));
+	WARN_ON_ONCE(!(esr & ESR_ELx_VNCR));
+
+	if (kvm_vcpu_abt_issea(vcpu))
+		return kvm_handle_guest_sea(vcpu);
 
 	if (esr_fsc_is_permission_fault(esr)) {
 		inject_vncr_perm(vcpu);
diff --git a/arch/arm64/kvm/pkvm.c b/arch/arm64/kvm/pkvm.c
index fcd70bf..61827cf 100644
--- a/arch/arm64/kvm/pkvm.c
+++ b/arch/arm64/kvm/pkvm.c
@@ -316,9 +316,16 @@ static int __pkvm_pgtable_stage2_unmap(struct kvm_pgtable *pgt, u64 start, u64 e
 	return 0;
 }
 
-void pkvm_pgtable_stage2_destroy(struct kvm_pgtable *pgt)
+void pkvm_pgtable_stage2_destroy_range(struct kvm_pgtable *pgt,
+					u64 addr, u64 size)
 {
-	__pkvm_pgtable_stage2_unmap(pgt, 0, ~(0ULL));
+	__pkvm_pgtable_stage2_unmap(pgt, addr, addr + size);
+}
+
+void pkvm_pgtable_stage2_destroy_pgd(struct kvm_pgtable *pgt)
+{
+	/* Expected to be called after all pKVM mappings have been released. */
+	WARN_ON_ONCE(!RB_EMPTY_ROOT(&pgt->pkvm_mappings.rb_root));
 }
 
 int pkvm_pgtable_stage2_map(struct kvm_pgtable *pgt, u64 addr, u64 size,
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 82ffb3b..b29f724 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -82,43 +82,105 @@ static bool write_to_read_only(struct kvm_vcpu *vcpu,
 			"sys_reg write to read-only register");
 }
 
-#define PURE_EL2_SYSREG(el2)						\
-	case el2: {							\
-		*el1r = el2;						\
-		return true;						\
-	}
+enum sr_loc_attr {
+	SR_LOC_MEMORY	= 0,	  /* Register definitely in memory */
+	SR_LOC_LOADED	= BIT(0), /* Register on CPU, unless it cannot */
+	SR_LOC_MAPPED	= BIT(1), /* Register in a different CPU register */
+	SR_LOC_XLATED	= BIT(2), /* Register translated to fit another reg */
+	SR_LOC_SPECIAL	= BIT(3), /* Demanding register, implies loaded */
+};
 
-#define MAPPED_EL2_SYSREG(el2, el1, fn)					\
-	case el2: {							\
-		*xlate = fn;						\
-		*el1r = el1;						\
-		return true;						\
-	}
+struct sr_loc {
+	enum sr_loc_attr loc;
+	enum vcpu_sysreg map_reg;
+	u64		 (*xlate)(u64);
+};
 
-static bool get_el2_to_el1_mapping(unsigned int reg,
-				   unsigned int *el1r, u64 (**xlate)(u64))
+static enum sr_loc_attr locate_direct_register(const struct kvm_vcpu *vcpu,
+					       enum vcpu_sysreg reg)
 {
 	switch (reg) {
-		PURE_EL2_SYSREG(  VPIDR_EL2	);
-		PURE_EL2_SYSREG(  VMPIDR_EL2	);
-		PURE_EL2_SYSREG(  ACTLR_EL2	);
-		PURE_EL2_SYSREG(  HCR_EL2	);
-		PURE_EL2_SYSREG(  MDCR_EL2	);
-		PURE_EL2_SYSREG(  HSTR_EL2	);
-		PURE_EL2_SYSREG(  HACR_EL2	);
-		PURE_EL2_SYSREG(  VTTBR_EL2	);
-		PURE_EL2_SYSREG(  VTCR_EL2	);
-		PURE_EL2_SYSREG(  TPIDR_EL2	);
-		PURE_EL2_SYSREG(  HPFAR_EL2	);
-		PURE_EL2_SYSREG(  HCRX_EL2	);
-		PURE_EL2_SYSREG(  HFGRTR_EL2	);
-		PURE_EL2_SYSREG(  HFGWTR_EL2	);
-		PURE_EL2_SYSREG(  HFGITR_EL2	);
-		PURE_EL2_SYSREG(  HDFGRTR_EL2	);
-		PURE_EL2_SYSREG(  HDFGWTR_EL2	);
-		PURE_EL2_SYSREG(  HAFGRTR_EL2	);
-		PURE_EL2_SYSREG(  CNTVOFF_EL2	);
-		PURE_EL2_SYSREG(  CNTHCTL_EL2	);
+	case SCTLR_EL1:
+	case CPACR_EL1:
+	case TTBR0_EL1:
+	case TTBR1_EL1:
+	case TCR_EL1:
+	case TCR2_EL1:
+	case PIR_EL1:
+	case PIRE0_EL1:
+	case POR_EL1:
+	case ESR_EL1:
+	case AFSR0_EL1:
+	case AFSR1_EL1:
+	case FAR_EL1:
+	case MAIR_EL1:
+	case VBAR_EL1:
+	case CONTEXTIDR_EL1:
+	case AMAIR_EL1:
+	case CNTKCTL_EL1:
+	case ELR_EL1:
+	case SPSR_EL1:
+	case ZCR_EL1:
+	case SCTLR2_EL1:
+		/*
+		 * EL1 registers which have an ELx2 mapping are loaded if
+		 * we're not in hypervisor context.
+		 */
+		return is_hyp_ctxt(vcpu) ? SR_LOC_MEMORY : SR_LOC_LOADED;
+
+	case TPIDR_EL0:
+	case TPIDRRO_EL0:
+	case TPIDR_EL1:
+	case PAR_EL1:
+	case DACR32_EL2:
+	case IFSR32_EL2:
+	case DBGVCR32_EL2:
+		/* These registers are always loaded, no matter what */
+		return SR_LOC_LOADED;
+
+	default:
+		/* Non-mapped EL2 registers are by definition in memory. */
+		return SR_LOC_MEMORY;
+	}
+}
+
+static void locate_mapped_el2_register(const struct kvm_vcpu *vcpu,
+				       enum vcpu_sysreg reg,
+				       enum vcpu_sysreg map_reg,
+				       u64 (*xlate)(u64),
+				       struct sr_loc *loc)
+{
+	if (!is_hyp_ctxt(vcpu)) {
+		loc->loc = SR_LOC_MEMORY;
+		return;
+	}
+
+	loc->loc = SR_LOC_LOADED | SR_LOC_MAPPED;
+	loc->map_reg = map_reg;
+
+	WARN_ON(locate_direct_register(vcpu, map_reg) != SR_LOC_MEMORY);
+
+	if (xlate != NULL && !vcpu_el2_e2h_is_set(vcpu)) {
+		loc->loc |= SR_LOC_XLATED;
+		loc->xlate = xlate;
+	}
+}
+
+#define MAPPED_EL2_SYSREG(r, m, t)					\
+	case r:	{							\
+		locate_mapped_el2_register(vcpu, r, m, t, loc);		\
+		break;							\
+	}
+
+static void locate_register(const struct kvm_vcpu *vcpu, enum vcpu_sysreg reg,
+			    struct sr_loc *loc)
+{
+	if (!vcpu_get_flag(vcpu, SYSREGS_ON_CPU)) {
+		loc->loc = SR_LOC_MEMORY;
+		return;
+	}
+
+	switch (reg) {
 		MAPPED_EL2_SYSREG(SCTLR_EL2,   SCTLR_EL1,
 				  translate_sctlr_el2_to_sctlr_el1	     );
 		MAPPED_EL2_SYSREG(CPTR_EL2,    CPACR_EL1,
@@ -144,125 +206,189 @@ static bool get_el2_to_el1_mapping(unsigned int reg,
 		MAPPED_EL2_SYSREG(ZCR_EL2,     ZCR_EL1,     NULL	     );
 		MAPPED_EL2_SYSREG(CONTEXTIDR_EL2, CONTEXTIDR_EL1, NULL	     );
 		MAPPED_EL2_SYSREG(SCTLR2_EL2,  SCTLR2_EL1,  NULL	     );
+	case CNTHCTL_EL2:
+		/* CNTHCTL_EL2 is super special, until we support NV2.1 */
+		loc->loc = ((is_hyp_ctxt(vcpu) && vcpu_el2_e2h_is_set(vcpu)) ?
+			    SR_LOC_SPECIAL : SR_LOC_MEMORY);
+		break;
 	default:
-		return false;
+		loc->loc = locate_direct_register(vcpu, reg);
 	}
 }
 
-u64 vcpu_read_sys_reg(const struct kvm_vcpu *vcpu, int reg)
+static u64 read_sr_from_cpu(enum vcpu_sysreg reg)
 {
 	u64 val = 0x8badf00d8badf00d;
-	u64 (*xlate)(u64) = NULL;
-	unsigned int el1r;
 
-	if (!vcpu_get_flag(vcpu, SYSREGS_ON_CPU))
-		goto memory_read;
+	switch (reg) {
+	case SCTLR_EL1:		val = read_sysreg_s(SYS_SCTLR_EL12);	break;
+	case CPACR_EL1:		val = read_sysreg_s(SYS_CPACR_EL12);	break;
+	case TTBR0_EL1:		val = read_sysreg_s(SYS_TTBR0_EL12);	break;
+	case TTBR1_EL1:		val = read_sysreg_s(SYS_TTBR1_EL12);	break;
+	case TCR_EL1:		val = read_sysreg_s(SYS_TCR_EL12);	break;
+	case TCR2_EL1:		val = read_sysreg_s(SYS_TCR2_EL12);	break;
+	case PIR_EL1:		val = read_sysreg_s(SYS_PIR_EL12);	break;
+	case PIRE0_EL1:		val = read_sysreg_s(SYS_PIRE0_EL12);	break;
+	case POR_EL1:		val = read_sysreg_s(SYS_POR_EL12);	break;
+	case ESR_EL1:		val = read_sysreg_s(SYS_ESR_EL12);	break;
+	case AFSR0_EL1:		val = read_sysreg_s(SYS_AFSR0_EL12);	break;
+	case AFSR1_EL1:		val = read_sysreg_s(SYS_AFSR1_EL12);	break;
+	case FAR_EL1:		val = read_sysreg_s(SYS_FAR_EL12);	break;
+	case MAIR_EL1:		val = read_sysreg_s(SYS_MAIR_EL12);	break;
+	case VBAR_EL1:		val = read_sysreg_s(SYS_VBAR_EL12);	break;
+	case CONTEXTIDR_EL1:	val = read_sysreg_s(SYS_CONTEXTIDR_EL12);break;
+	case AMAIR_EL1:		val = read_sysreg_s(SYS_AMAIR_EL12);	break;
+	case CNTKCTL_EL1:	val = read_sysreg_s(SYS_CNTKCTL_EL12);	break;
+	case ELR_EL1:		val = read_sysreg_s(SYS_ELR_EL12);	break;
+	case SPSR_EL1:		val = read_sysreg_s(SYS_SPSR_EL12);	break;
+	case ZCR_EL1:		val = read_sysreg_s(SYS_ZCR_EL12);	break;
+	case SCTLR2_EL1:	val = read_sysreg_s(SYS_SCTLR2_EL12);	break;
+	case TPIDR_EL0:		val = read_sysreg_s(SYS_TPIDR_EL0);	break;
+	case TPIDRRO_EL0:	val = read_sysreg_s(SYS_TPIDRRO_EL0);	break;
+	case TPIDR_EL1:		val = read_sysreg_s(SYS_TPIDR_EL1);	break;
+	case PAR_EL1:		val = read_sysreg_par();		break;
+	case DACR32_EL2:	val = read_sysreg_s(SYS_DACR32_EL2);	break;
+	case IFSR32_EL2:	val = read_sysreg_s(SYS_IFSR32_EL2);	break;
+	case DBGVCR32_EL2:	val = read_sysreg_s(SYS_DBGVCR32_EL2);	break;
+	default:		WARN_ON_ONCE(1);
+	}
 
-	if (unlikely(get_el2_to_el1_mapping(reg, &el1r, &xlate))) {
-		if (!is_hyp_ctxt(vcpu))
-			goto memory_read;
+	return val;
+}
+
+static void write_sr_to_cpu(enum vcpu_sysreg reg, u64 val)
+{
+	switch (reg) {
+	case SCTLR_EL1:		write_sysreg_s(val, SYS_SCTLR_EL12);	break;
+	case CPACR_EL1:		write_sysreg_s(val, SYS_CPACR_EL12);	break;
+	case TTBR0_EL1:		write_sysreg_s(val, SYS_TTBR0_EL12);	break;
+	case TTBR1_EL1:		write_sysreg_s(val, SYS_TTBR1_EL12);	break;
+	case TCR_EL1:		write_sysreg_s(val, SYS_TCR_EL12);	break;
+	case TCR2_EL1:		write_sysreg_s(val, SYS_TCR2_EL12);	break;
+	case PIR_EL1:		write_sysreg_s(val, SYS_PIR_EL12);	break;
+	case PIRE0_EL1:		write_sysreg_s(val, SYS_PIRE0_EL12);	break;
+	case POR_EL1:		write_sysreg_s(val, SYS_POR_EL12);	break;
+	case ESR_EL1:		write_sysreg_s(val, SYS_ESR_EL12);	break;
+	case AFSR0_EL1:		write_sysreg_s(val, SYS_AFSR0_EL12);	break;
+	case AFSR1_EL1:		write_sysreg_s(val, SYS_AFSR1_EL12);	break;
+	case FAR_EL1:		write_sysreg_s(val, SYS_FAR_EL12);	break;
+	case MAIR_EL1:		write_sysreg_s(val, SYS_MAIR_EL12);	break;
+	case VBAR_EL1:		write_sysreg_s(val, SYS_VBAR_EL12);	break;
+	case CONTEXTIDR_EL1:	write_sysreg_s(val, SYS_CONTEXTIDR_EL12);break;
+	case AMAIR_EL1:		write_sysreg_s(val, SYS_AMAIR_EL12);	break;
+	case CNTKCTL_EL1:	write_sysreg_s(val, SYS_CNTKCTL_EL12);	break;
+	case ELR_EL1:		write_sysreg_s(val, SYS_ELR_EL12);	break;
+	case SPSR_EL1:		write_sysreg_s(val, SYS_SPSR_EL12);	break;
+	case ZCR_EL1:		write_sysreg_s(val, SYS_ZCR_EL12);	break;
+	case SCTLR2_EL1:	write_sysreg_s(val, SYS_SCTLR2_EL12);	break;
+	case TPIDR_EL0:		write_sysreg_s(val, SYS_TPIDR_EL0);	break;
+	case TPIDRRO_EL0:	write_sysreg_s(val, SYS_TPIDRRO_EL0);	break;
+	case TPIDR_EL1:		write_sysreg_s(val, SYS_TPIDR_EL1);	break;
+	case PAR_EL1:		write_sysreg_s(val, SYS_PAR_EL1);	break;
+	case DACR32_EL2:	write_sysreg_s(val, SYS_DACR32_EL2);	break;
+	case IFSR32_EL2:	write_sysreg_s(val, SYS_IFSR32_EL2);	break;
+	case DBGVCR32_EL2:	write_sysreg_s(val, SYS_DBGVCR32_EL2);	break;
+	default:		WARN_ON_ONCE(1);
+	}
+}
+
+u64 vcpu_read_sys_reg(const struct kvm_vcpu *vcpu, enum vcpu_sysreg reg)
+{
+	struct sr_loc loc = {};
+
+	locate_register(vcpu, reg, &loc);
+
+	WARN_ON_ONCE(!has_vhe() && loc.loc != SR_LOC_MEMORY);
+
+	if (loc.loc & SR_LOC_SPECIAL) {
+		u64 val;
+
+		WARN_ON_ONCE(loc.loc & ~SR_LOC_SPECIAL);
 
 		/*
-		 * CNTHCTL_EL2 requires some special treatment to
-		 * account for the bits that can be set via CNTKCTL_EL1.
+		 * CNTHCTL_EL2 requires some special treatment to account
+		 * for the bits that can be set via CNTKCTL_EL1 when E2H==1.
 		 */
 		switch (reg) {
 		case CNTHCTL_EL2:
-			if (vcpu_el2_e2h_is_set(vcpu)) {
-				val = read_sysreg_el1(SYS_CNTKCTL);
-				val &= CNTKCTL_VALID_BITS;
-				val |= __vcpu_sys_reg(vcpu, reg) & ~CNTKCTL_VALID_BITS;
-				return val;
-			}
-			break;
+			val = read_sysreg_el1(SYS_CNTKCTL);
+			val &= CNTKCTL_VALID_BITS;
+			val |= __vcpu_sys_reg(vcpu, reg) & ~CNTKCTL_VALID_BITS;
+			return val;
+		default:
+			WARN_ON_ONCE(1);
 		}
-
-		/*
-		 * If this register does not have an EL1 counterpart,
-		 * then read the stored EL2 version.
-		 */
-		if (reg == el1r)
-			goto memory_read;
-
-		/*
-		 * If we have a non-VHE guest and that the sysreg
-		 * requires translation to be used at EL1, use the
-		 * in-memory copy instead.
-		 */
-		if (!vcpu_el2_e2h_is_set(vcpu) && xlate)
-			goto memory_read;
-
-		/* Get the current version of the EL1 counterpart. */
-		WARN_ON(!__vcpu_read_sys_reg_from_cpu(el1r, &val));
-		if (reg >= __SANITISED_REG_START__)
-			val = kvm_vcpu_apply_reg_masks(vcpu, reg, val);
-
-		return val;
 	}
 
-	/* EL1 register can't be on the CPU if the guest is in vEL2. */
-	if (unlikely(is_hyp_ctxt(vcpu)))
-		goto memory_read;
+	if (loc.loc & SR_LOC_LOADED) {
+		enum vcpu_sysreg map_reg = reg;
 
-	if (__vcpu_read_sys_reg_from_cpu(reg, &val))
-		return val;
+		if (loc.loc & SR_LOC_MAPPED)
+			map_reg = loc.map_reg;
 
-memory_read:
+		if (!(loc.loc & SR_LOC_XLATED)) {
+			u64 val = read_sr_from_cpu(map_reg);
+
+			if (reg >= __SANITISED_REG_START__)
+				val = kvm_vcpu_apply_reg_masks(vcpu, reg, val);
+
+			return val;
+		}
+	}
+
 	return __vcpu_sys_reg(vcpu, reg);
 }
 
-void vcpu_write_sys_reg(struct kvm_vcpu *vcpu, u64 val, int reg)
+void vcpu_write_sys_reg(struct kvm_vcpu *vcpu, u64 val, enum vcpu_sysreg reg)
 {
-	u64 (*xlate)(u64) = NULL;
-	unsigned int el1r;
+	struct sr_loc loc = {};
 
-	if (!vcpu_get_flag(vcpu, SYSREGS_ON_CPU))
-		goto memory_write;
+	locate_register(vcpu, reg, &loc);
 
-	if (unlikely(get_el2_to_el1_mapping(reg, &el1r, &xlate))) {
-		if (!is_hyp_ctxt(vcpu))
-			goto memory_write;
+	WARN_ON_ONCE(!has_vhe() && loc.loc != SR_LOC_MEMORY);
 
-		/*
-		 * Always store a copy of the write to memory to avoid having
-		 * to reverse-translate virtual EL2 system registers for a
-		 * non-VHE guest hypervisor.
-		 */
-		__vcpu_assign_sys_reg(vcpu, reg, val);
+	if (loc.loc & SR_LOC_SPECIAL) {
+
+		WARN_ON_ONCE(loc.loc & ~SR_LOC_SPECIAL);
 
 		switch (reg) {
 		case CNTHCTL_EL2:
 			/*
-			 * If E2H=0, CNHTCTL_EL2 is a pure shadow register.
-			 * Otherwise, some of the bits are backed by
+			 * If E2H=1, some of the bits are backed by
 			 * CNTKCTL_EL1, while the rest is kept in memory.
 			 * Yes, this is fun stuff.
 			 */
-			if (vcpu_el2_e2h_is_set(vcpu))
-				write_sysreg_el1(val, SYS_CNTKCTL);
-			return;
+			write_sysreg_el1(val, SYS_CNTKCTL);
+			break;
+		default:
+			WARN_ON_ONCE(1);
 		}
-
-		/* No EL1 counterpart? We're done here.? */
-		if (reg == el1r)
-			return;
-
-		if (!vcpu_el2_e2h_is_set(vcpu) && xlate)
-			val = xlate(val);
-
-		/* Redirect this to the EL1 version of the register. */
-		WARN_ON(!__vcpu_write_sys_reg_to_cpu(val, el1r));
-		return;
 	}
 
-	/* EL1 register can't be on the CPU if the guest is in vEL2. */
-	if (unlikely(is_hyp_ctxt(vcpu)))
-		goto memory_write;
+	if (loc.loc & SR_LOC_LOADED) {
+		enum vcpu_sysreg map_reg = reg;
+		u64 xlated_val;
 
-	if (__vcpu_write_sys_reg_to_cpu(val, reg))
-		return;
+		if (reg >= __SANITISED_REG_START__)
+			val = kvm_vcpu_apply_reg_masks(vcpu, reg, val);
 
-memory_write:
+		if (loc.loc & SR_LOC_MAPPED)
+			map_reg = loc.map_reg;
+
+		if (loc.loc & SR_LOC_XLATED)
+			xlated_val = loc.xlate(val);
+		else
+			xlated_val = val;
+
+		write_sr_to_cpu(map_reg, xlated_val);
+
+		/*
+		 * Fall through to write the backing store anyway, which
+		 * allows translated registers to be directly read without a
+		 * reverse translation.
+		 */
+	}
+
 	__vcpu_assign_sys_reg(vcpu, reg, val);
 }
 
@@ -1584,6 +1710,7 @@ static u8 pmuver_to_perfmon(u8 pmuver)
 }
 
 static u64 sanitise_id_aa64pfr0_el1(const struct kvm_vcpu *vcpu, u64 val);
+static u64 sanitise_id_aa64pfr1_el1(const struct kvm_vcpu *vcpu, u64 val);
 static u64 sanitise_id_aa64dfr0_el1(const struct kvm_vcpu *vcpu, u64 val);
 
 /* Read a sanitised cpufeature ID register by sys_reg_desc */
@@ -1606,19 +1733,7 @@ static u64 __kvm_read_sanitised_id_reg(const struct kvm_vcpu *vcpu,
 		val = sanitise_id_aa64pfr0_el1(vcpu, val);
 		break;
 	case SYS_ID_AA64PFR1_EL1:
-		if (!kvm_has_mte(vcpu->kvm)) {
-			val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_MTE);
-			val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_MTE_frac);
-		}
-
-		val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_SME);
-		val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_RNDR_trap);
-		val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_NMI);
-		val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_GCS);
-		val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_THE);
-		val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_MTEX);
-		val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_PFAR);
-		val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_MPAM_frac);
+		val = sanitise_id_aa64pfr1_el1(vcpu, val);
 		break;
 	case SYS_ID_AA64PFR2_EL1:
 		val &= ID_AA64PFR2_EL1_FPMR |
@@ -1628,18 +1743,18 @@ static u64 __kvm_read_sanitised_id_reg(const struct kvm_vcpu *vcpu,
 		break;
 	case SYS_ID_AA64ISAR1_EL1:
 		if (!vcpu_has_ptrauth(vcpu))
-			val &= ~(ARM64_FEATURE_MASK(ID_AA64ISAR1_EL1_APA) |
-				 ARM64_FEATURE_MASK(ID_AA64ISAR1_EL1_API) |
-				 ARM64_FEATURE_MASK(ID_AA64ISAR1_EL1_GPA) |
-				 ARM64_FEATURE_MASK(ID_AA64ISAR1_EL1_GPI));
+			val &= ~(ID_AA64ISAR1_EL1_APA |
+				 ID_AA64ISAR1_EL1_API |
+				 ID_AA64ISAR1_EL1_GPA |
+				 ID_AA64ISAR1_EL1_GPI);
 		break;
 	case SYS_ID_AA64ISAR2_EL1:
 		if (!vcpu_has_ptrauth(vcpu))
-			val &= ~(ARM64_FEATURE_MASK(ID_AA64ISAR2_EL1_APA3) |
-				 ARM64_FEATURE_MASK(ID_AA64ISAR2_EL1_GPA3));
+			val &= ~(ID_AA64ISAR2_EL1_APA3 |
+				 ID_AA64ISAR2_EL1_GPA3);
 		if (!cpus_have_final_cap(ARM64_HAS_WFXT) ||
 		    has_broken_cntvoff())
-			val &= ~ARM64_FEATURE_MASK(ID_AA64ISAR2_EL1_WFxT);
+			val &= ~ID_AA64ISAR2_EL1_WFxT;
 		break;
 	case SYS_ID_AA64ISAR3_EL1:
 		val &= ID_AA64ISAR3_EL1_FPRCVT | ID_AA64ISAR3_EL1_FAMINMAX;
@@ -1655,7 +1770,7 @@ static u64 __kvm_read_sanitised_id_reg(const struct kvm_vcpu *vcpu,
 		       ID_AA64MMFR3_EL1_S1PIE;
 		break;
 	case SYS_ID_MMFR4_EL1:
-		val &= ~ARM64_FEATURE_MASK(ID_MMFR4_EL1_CCIDX);
+		val &= ~ID_MMFR4_EL1_CCIDX;
 		break;
 	}
 
@@ -1836,6 +1951,31 @@ static u64 sanitise_id_aa64pfr0_el1(const struct kvm_vcpu *vcpu, u64 val)
 	return val;
 }
 
+static u64 sanitise_id_aa64pfr1_el1(const struct kvm_vcpu *vcpu, u64 val)
+{
+	u64 pfr0 = read_sanitised_ftr_reg(SYS_ID_AA64PFR0_EL1);
+
+	if (!kvm_has_mte(vcpu->kvm)) {
+		val &= ~ID_AA64PFR1_EL1_MTE;
+		val &= ~ID_AA64PFR1_EL1_MTE_frac;
+	}
+
+	if (!(cpus_have_final_cap(ARM64_HAS_RASV1P1_EXTN) &&
+	      SYS_FIELD_GET(ID_AA64PFR0_EL1, RAS, pfr0) == ID_AA64PFR0_EL1_RAS_IMP))
+		val &= ~ID_AA64PFR1_EL1_RAS_frac;
+
+	val &= ~ID_AA64PFR1_EL1_SME;
+	val &= ~ID_AA64PFR1_EL1_RNDR_trap;
+	val &= ~ID_AA64PFR1_EL1_NMI;
+	val &= ~ID_AA64PFR1_EL1_GCS;
+	val &= ~ID_AA64PFR1_EL1_THE;
+	val &= ~ID_AA64PFR1_EL1_MTEX;
+	val &= ~ID_AA64PFR1_EL1_PFAR;
+	val &= ~ID_AA64PFR1_EL1_MPAM_frac;
+
+	return val;
+}
+
 static u64 sanitise_id_aa64dfr0_el1(const struct kvm_vcpu *vcpu, u64 val)
 {
 	val = ID_REG_LIMIT_FIELD_ENUM(val, ID_AA64DFR0_EL1, DebugVer, V8P8);
@@ -2697,6 +2837,18 @@ static bool access_ras(struct kvm_vcpu *vcpu,
 	struct kvm *kvm = vcpu->kvm;
 
 	switch(reg_to_encoding(r)) {
+	case SYS_ERXPFGCDN_EL1:
+	case SYS_ERXPFGCTL_EL1:
+	case SYS_ERXPFGF_EL1:
+	case SYS_ERXMISC2_EL1:
+	case SYS_ERXMISC3_EL1:
+		if (!(kvm_has_feat(kvm, ID_AA64PFR0_EL1, RAS, V1P1) ||
+		      (kvm_has_feat_enum(kvm, ID_AA64PFR0_EL1, RAS, IMP) &&
+		       kvm_has_feat(kvm, ID_AA64PFR1_EL1, RAS_frac, RASv1p1)))) {
+			kvm_inject_undefined(vcpu);
+			return false;
+		}
+		break;
 	default:
 		if (!kvm_has_feat(kvm, ID_AA64PFR0_EL1, RAS, IMP)) {
 			kvm_inject_undefined(vcpu);
@@ -2929,7 +3081,6 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 		    ~(ID_AA64PFR0_EL1_AMU |
 		      ID_AA64PFR0_EL1_MPAM |
 		      ID_AA64PFR0_EL1_SVE |
-		      ID_AA64PFR0_EL1_RAS |
 		      ID_AA64PFR0_EL1_AdvSIMD |
 		      ID_AA64PFR0_EL1_FP)),
 	ID_FILTERED(ID_AA64PFR1_EL1, id_aa64pfr1_el1,
@@ -2943,7 +3094,6 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 				       ID_AA64PFR1_EL1_SME |
 				       ID_AA64PFR1_EL1_RES0 |
 				       ID_AA64PFR1_EL1_MPAM_frac |
-				       ID_AA64PFR1_EL1_RAS_frac |
 				       ID_AA64PFR1_EL1_MTE)),
 	ID_WRITABLE(ID_AA64PFR2_EL1,
 		    ID_AA64PFR2_EL1_FPMR |
@@ -3063,8 +3213,13 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	{ SYS_DESC(SYS_ERXCTLR_EL1), access_ras },
 	{ SYS_DESC(SYS_ERXSTATUS_EL1), access_ras },
 	{ SYS_DESC(SYS_ERXADDR_EL1), access_ras },
+	{ SYS_DESC(SYS_ERXPFGF_EL1), access_ras },
+	{ SYS_DESC(SYS_ERXPFGCTL_EL1), access_ras },
+	{ SYS_DESC(SYS_ERXPFGCDN_EL1), access_ras },
 	{ SYS_DESC(SYS_ERXMISC0_EL1), access_ras },
 	{ SYS_DESC(SYS_ERXMISC1_EL1), access_ras },
+	{ SYS_DESC(SYS_ERXMISC2_EL1), access_ras },
+	{ SYS_DESC(SYS_ERXMISC3_EL1), access_ras },
 
 	MTE_REG(TFSR_EL1),
 	MTE_REG(TFSRE0_EL1),
diff --git a/arch/arm64/kvm/vgic/vgic-mmio-v3.c b/arch/arm64/kvm/vgic/vgic-mmio-v3.c
index a3ef185..70d50c7 100644
--- a/arch/arm64/kvm/vgic/vgic-mmio-v3.c
+++ b/arch/arm64/kvm/vgic/vgic-mmio-v3.c
@@ -50,6 +50,14 @@ bool vgic_has_its(struct kvm *kvm)
 
 bool vgic_supports_direct_msis(struct kvm *kvm)
 {
+	/*
+	 * Deliberately conflate vLPI and vSGI support on GICv4.1 hardware,
+	 * indirectly allowing userspace to control whether or not vPEs are
+	 * allocated for the VM.
+	 */
+	if (system_supports_direct_sgis() && !vgic_supports_direct_sgis(kvm))
+		return false;
+
 	return kvm_vgic_global_state.has_gicv4 && vgic_has_its(kvm);
 }
 
diff --git a/arch/arm64/kvm/vgic/vgic-mmio.c b/arch/arm64/kvm/vgic/vgic-mmio.c
index e416e43..a573b1f 100644
--- a/arch/arm64/kvm/vgic/vgic-mmio.c
+++ b/arch/arm64/kvm/vgic/vgic-mmio.c
@@ -1091,7 +1091,7 @@ int vgic_register_dist_iodev(struct kvm *kvm, gpa_t dist_base_address,
 		len = vgic_v3_init_dist_iodev(io_device);
 		break;
 	default:
-		BUG_ON(1);
+		BUG();
 	}
 
 	io_device->base_addr = dist_base_address;
diff --git a/arch/arm64/kvm/vgic/vgic.h b/arch/arm64/kvm/vgic/vgic.h
index 1384a04..de1c1d3 100644
--- a/arch/arm64/kvm/vgic/vgic.h
+++ b/arch/arm64/kvm/vgic/vgic.h
@@ -396,15 +396,7 @@ bool vgic_supports_direct_sgis(struct kvm *kvm);
 
 static inline bool vgic_supports_direct_irqs(struct kvm *kvm)
 {
-	/*
-	 * Deliberately conflate vLPI and vSGI support on GICv4.1 hardware,
-	 * indirectly allowing userspace to control whether or not vPEs are
-	 * allocated for the VM.
-	 */
-	if (system_supports_direct_sgis())
-		return vgic_supports_direct_sgis(kvm);
-
-	return vgic_supports_direct_msis(kvm);
+	return vgic_supports_direct_msis(kvm) || vgic_supports_direct_sgis(kvm);
 }
 
 int vgic_v4_init(struct kvm *kvm);
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 34e5d78..1838015 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -47,13 +47,6 @@
 #define NO_CONT_MAPPINGS	BIT(1)
 #define NO_EXEC_MAPPINGS	BIT(2)	/* assumes FEAT_HPDS is not used */
 
-enum pgtable_type {
-	TABLE_PTE,
-	TABLE_PMD,
-	TABLE_PUD,
-	TABLE_P4D,
-};
-
 u64 kimage_voffset __ro_after_init;
 EXPORT_SYMBOL(kimage_voffset);
 
diff --git a/arch/arm64/tools/cpucaps b/arch/arm64/tools/cpucaps
index ef0b794..9ff5cdb 100644
--- a/arch/arm64/tools/cpucaps
+++ b/arch/arm64/tools/cpucaps
@@ -53,6 +53,7 @@
 HAS_S1POE
 HAS_SCTLR2
 HAS_RAS_EXTN
+HAS_RASV1P1_EXTN
 HAS_RNG
 HAS_SB
 HAS_STAGE2_FWB
diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile
index a7ab087..c47b78c 100644
--- a/arch/powerpc/boot/Makefile
+++ b/arch/powerpc/boot/Makefile
@@ -243,13 +243,13 @@
 hostprogs	:= addnote hack-coff mktree
 
 targets		+= $(patsubst $(obj)/%,%,$(obj-boot) wrapper.a) zImage.lds
-extra-y		:= $(obj)/wrapper.a $(obj-plat) $(obj)/empty.o \
+always-y	:= $(obj)/wrapper.a $(obj-plat) $(obj)/empty.o \
 		   $(obj)/zImage.lds $(obj)/zImage.coff.lds $(obj)/zImage.ps3.lds
 
 dtstree		:= $(src)/dts
 
 wrapper		:= $(src)/wrapper
-wrapperbits	:= $(extra-y) $(addprefix $(obj)/,addnote hack-coff mktree) \
+wrapperbits	:= $(always-y) $(addprefix $(obj)/,addnote hack-coff mktree) \
 			$(wrapper) FORCE
 
 #############
@@ -456,7 +456,7 @@
 WRAPPER_BINDIR := /usr/sbin
 INSTALL := install
 
-extra-installed		:= $(patsubst $(obj)/%, $(DESTDIR)$(WRAPPER_OBJDIR)/%, $(extra-y))
+extra-installed		:= $(patsubst $(obj)/%, $(DESTDIR)$(WRAPPER_OBJDIR)/%, $(always-y))
 hostprogs-installed	:= $(patsubst %, $(DESTDIR)$(WRAPPER_BINDIR)/%, $(hostprogs))
 wrapper-installed	:= $(DESTDIR)$(WRAPPER_BINDIR)/wrapper
 dts-installed		:= $(patsubst $(dtstree)/%, $(DESTDIR)$(WRAPPER_DTSDIR)/%, $(wildcard $(dtstree)/*.dts))
diff --git a/arch/powerpc/boot/install.sh b/arch/powerpc/boot/install.sh
index 101fcb3..c3df6c2 100755
--- a/arch/powerpc/boot/install.sh
+++ b/arch/powerpc/boot/install.sh
@@ -19,19 +19,19 @@
 set -e
 
 # this should work for both the pSeries zImage and the iSeries vmlinux.sm
-image_name=`basename $2`
+image_name=$(basename "$2")
 
 
 echo "Warning: '${INSTALLKERNEL}' command not available... Copying" \
      "directly to $4/$image_name-$1" >&2
 
-if [ -f $4/$image_name-$1 ]; then
-	mv $4/$image_name-$1 $4/$image_name-$1.old
+if [ -f "$4"/"$image_name"-"$1" ]; then
+	mv "$4"/"$image_name"-"$1" "$4"/"$image_name"-"$1".old
 fi
 
-if [ -f $4/System.map-$1 ]; then
-	mv $4/System.map-$1 $4/System-$1.old
+if [ -f "$4"/System.map-"$1" ]; then
+	mv "$4"/System.map-"$1" "$4"/System-"$1".old
 fi
 
-cat $2 > $4/$image_name-$1
-cp $3 $4/System.map-$1
+cat "$2" > "$4"/"$image_name"-"$1"
+cp "$3" "$4"/System.map-"$1"
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index fb2b952..2f0a2e6 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -199,7 +199,9 @@
 
 obj-$(CONFIG_PPC_OF_BOOT_TRAMPOLINE) += prom_init.o
 obj64-$(CONFIG_PPC_OF_BOOT_TRAMPOLINE) += prom_entry_64.o
-extra-$(CONFIG_PPC_OF_BOOT_TRAMPOLINE) += prom_init_check
+ifdef KBUILD_BUILTIN
+always-$(CONFIG_PPC_OF_BOOT_TRAMPOLINE) += prom_init_check
+endif
 
 obj-$(CONFIG_PPC64)		+= $(obj64-y)
 obj-$(CONFIG_PPC32)		+= $(obj32-y)
diff --git a/arch/powerpc/kernel/kvm.c b/arch/powerpc/kernel/kvm.c
index 5b3c093..7209d00 100644
--- a/arch/powerpc/kernel/kvm.c
+++ b/arch/powerpc/kernel/kvm.c
@@ -632,19 +632,19 @@ static void __init kvm_check_ins(u32 *inst, u32 features)
 #endif
 	}
 
-	switch (inst_no_rt & ~KVM_MASK_RB) {
 #ifdef CONFIG_PPC_BOOK3S_32
+	switch (inst_no_rt & ~KVM_MASK_RB) {
 	case KVM_INST_MTSRIN:
 		if (features & KVM_MAGIC_FEAT_SR) {
 			u32 inst_rb = _inst & KVM_MASK_RB;
 			kvm_patch_ins_mtsrin(inst, inst_rt, inst_rb);
 		}
 		break;
-#endif
 	}
+#endif
 
-	switch (_inst) {
 #ifdef CONFIG_BOOKE
+	switch (_inst) {
 	case KVM_INST_WRTEEI_0:
 		kvm_patch_ins_wrteei_0(inst);
 		break;
@@ -652,8 +652,8 @@ static void __init kvm_check_ins(u32 *inst, u32 features)
 	case KVM_INST_WRTEEI_1:
 		kvm_patch_ins_wrtee(inst, 0, 1);
 		break;
-#endif
 	}
+#endif
 }
 
 extern u32 kvm_template_start[];
diff --git a/arch/powerpc/kernel/prom_init_check.sh b/arch/powerpc/kernel/prom_init_check.sh
index 69623b9..3090b97 100644
--- a/arch/powerpc/kernel/prom_init_check.sh
+++ b/arch/powerpc/kernel/prom_init_check.sh
@@ -15,8 +15,8 @@
 
 has_renamed_memintrinsics()
 {
-	grep -q "^CONFIG_KASAN=y$" ${KCONFIG_CONFIG} && \
-		! grep -q "^CONFIG_CC_HAS_KASAN_MEMINTRINSIC_PREFIX=y" ${KCONFIG_CONFIG}
+	grep -q "^CONFIG_KASAN=y$" "${KCONFIG_CONFIG}" && \
+		! grep -q "^CONFIG_CC_HAS_KASAN_MEMINTRINSIC_PREFIX=y" "${KCONFIG_CONFIG}"
 }
 
 if has_renamed_memintrinsics
@@ -42,15 +42,15 @@
 {
     file=$1
     section=$2
-    size=$(objdump -h -j $section $file 2>/dev/null | awk "\$2 == \"$section\" {print \$3}")
+    size=$(objdump -h -j "$section" "$file" 2>/dev/null | awk "\$2 == \"$section\" {print \$3}")
     size=${size:-0}
-    if [ $size -ne 0 ]; then
+    if [ "$size" -ne 0 ]; then
 	ERROR=1
 	echo "Error: Section $section not empty in prom_init.c" >&2
     fi
 }
 
-for UNDEF in $($NM -u $OBJ | awk '{print $2}')
+for UNDEF in $($NM -u "$OBJ" | awk '{print $2}')
 do
 	# On 64-bit nm gives us the function descriptors, which have
 	# a leading . on the name, so strip it off here.
@@ -87,8 +87,8 @@
 	fi
 done
 
-check_section $OBJ .data
-check_section $OBJ .bss
-check_section $OBJ .init.data
+check_section "$OBJ" .data
+check_section "$OBJ" .bss
+check_section "$OBJ" .init.data
 
 exit $ERROR
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index 7284c80..8fd7cbf 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -141,10 +141,7 @@ void __init check_smt_enabled(void)
 			smt_enabled_at_boot = 0;
 		else {
 			int smt;
-			int rc;
-
-			rc = kstrtoint(smt_enabled_cmdline, 10, &smt);
-			if (!rc)
+			if (!kstrtoint(smt_enabled_cmdline, 10, &smt))
 				smt_enabled_at_boot =
 					min(threads_per_core, smt);
 		}
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 1535877..2ba0571 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -69,7 +69,7 @@ int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu)
 
 /*
  * Common checks before entering the guest world.  Call with interrupts
- * disabled.
+ * enabled.
  *
  * returns:
  *
diff --git a/arch/powerpc/platforms/8xx/cpm1-ic.c b/arch/powerpc/platforms/8xx/cpm1-ic.c
index a49d4a9..3292071 100644
--- a/arch/powerpc/platforms/8xx/cpm1-ic.c
+++ b/arch/powerpc/platforms/8xx/cpm1-ic.c
@@ -110,8 +110,7 @@ static int cpm_pic_probe(struct platform_device *pdev)
 
 	out_be32(&data->reg->cpic_cimr, 0);
 
-	data->host = irq_domain_create_linear(of_fwnode_handle(dev->of_node),
-					      64, &cpm_pic_host_ops, data);
+	data->host = irq_domain_create_linear(dev_fwnode(dev), 64, &cpm_pic_host_ops, data);
 	if (!data->host)
 		return -ENODEV;
 
diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype
index 613b383..7b527d1 100644
--- a/arch/powerpc/platforms/Kconfig.cputype
+++ b/arch/powerpc/platforms/Kconfig.cputype
@@ -122,16 +122,11 @@
 	  If unsure, select Generic.
 
 config POWERPC64_CPU
-	bool "Generic (POWER5 and PowerPC 970 and above)"
-	depends on PPC_BOOK3S_64 && !CPU_LITTLE_ENDIAN
+	bool "Generic 64 bits powerpc"
+	depends on PPC_BOOK3S_64
+	select ARCH_HAS_FAST_MULTIPLIER if CPU_LITTLE_ENDIAN
 	select PPC_64S_HASH_MMU
-
-config POWERPC64_CPU
-	bool "Generic (POWER8 and above)"
-	depends on PPC_BOOK3S_64 && CPU_LITTLE_ENDIAN
-	select ARCH_HAS_FAST_MULTIPLIER
-	select PPC_64S_HASH_MMU
-	select PPC_HAS_LBARX_LHARX
+	select PPC_HAS_LBARX_LHARX if CPU_LITTLE_ENDIAN
 
 config POWERPC_CPU
 	bool "Generic 32 bits powerpc"
diff --git a/arch/powerpc/sysdev/fsl_msi.c b/arch/powerpc/sysdev/fsl_msi.c
index 4fe8a7b..2a007bf 100644
--- a/arch/powerpc/sysdev/fsl_msi.c
+++ b/arch/powerpc/sysdev/fsl_msi.c
@@ -412,9 +412,8 @@ static int fsl_of_msi_probe(struct platform_device *dev)
 	}
 	platform_set_drvdata(dev, msi);
 
-	msi->irqhost = irq_domain_create_linear(of_fwnode_handle(dev->dev.of_node),
-				      NR_MSI_IRQS_MAX, &fsl_msi_host_ops, msi);
-
+	msi->irqhost = irq_domain_create_linear(dev_fwnode(&dev->dev), NR_MSI_IRQS_MAX,
+						&fsl_msi_host_ops, msi);
 	if (msi->irqhost == NULL) {
 		dev_err(&dev->dev, "No memory for MSI irqhost\n");
 		err = -ENOMEM;
diff --git a/arch/riscv/kvm/mmu.c b/arch/riscv/kvm/mmu.c
index a1c3b2e..525fb5a 100644
--- a/arch/riscv/kvm/mmu.c
+++ b/arch/riscv/kvm/mmu.c
@@ -39,6 +39,7 @@ int kvm_riscv_mmu_ioremap(struct kvm *kvm, gpa_t gpa, phys_addr_t hpa,
 			  unsigned long size, bool writable, bool in_atomic)
 {
 	int ret = 0;
+	pgprot_t prot;
 	unsigned long pfn;
 	phys_addr_t addr, end;
 	struct kvm_mmu_memory_cache pcache = {
@@ -55,10 +56,12 @@ int kvm_riscv_mmu_ioremap(struct kvm *kvm, gpa_t gpa, phys_addr_t hpa,
 
 	end = (gpa + size + PAGE_SIZE - 1) & PAGE_MASK;
 	pfn = __phys_to_pfn(hpa);
+	prot = pgprot_noncached(PAGE_WRITE);
 
 	for (addr = gpa; addr < end; addr += PAGE_SIZE) {
 		map.addr = addr;
-		map.pte = pfn_pte(pfn, PAGE_KERNEL_IO);
+		map.pte = pfn_pte(pfn, prot);
+		map.pte = pte_mkdirty(map.pte);
 		map.level = 0;
 
 		if (!writable)
diff --git a/arch/riscv/kvm/vcpu.c b/arch/riscv/kvm/vcpu.c
index f001e56..3ebcfff 100644
--- a/arch/riscv/kvm/vcpu.c
+++ b/arch/riscv/kvm/vcpu.c
@@ -683,7 +683,7 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 }
 
 /**
- * check_vcpu_requests - check and handle pending vCPU requests
+ * kvm_riscv_check_vcpu_requests - check and handle pending vCPU requests
  * @vcpu:	the VCPU pointer
  *
  * Return: 1 if we should enter the guest
diff --git a/arch/riscv/kvm/vcpu_vector.c b/arch/riscv/kvm/vcpu_vector.c
index a5f88cb..05f3cc2 100644
--- a/arch/riscv/kvm/vcpu_vector.c
+++ b/arch/riscv/kvm/vcpu_vector.c
@@ -182,6 +182,8 @@ int kvm_riscv_vcpu_set_reg_vector(struct kvm_vcpu *vcpu,
 		struct kvm_cpu_context *cntx = &vcpu->arch.guest_context;
 		unsigned long reg_val;
 
+		if (reg_size != sizeof(reg_val))
+			return -EINVAL;
 		if (copy_from_user(&reg_val, uaddr, reg_size))
 			return -EFAULT;
 		if (reg_val != cntx->vector.vlenb)
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 49ef1b8..af838b8 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -416,6 +416,10 @@ static bool __init should_mitigate_vuln(unsigned int bug)
 		       cpu_attack_vector_mitigated(CPU_MITIGATE_USER_USER) ||
 		       cpu_attack_vector_mitigated(CPU_MITIGATE_GUEST_GUEST) ||
 		       (smt_mitigations != SMT_MITIGATIONS_OFF);
+
+	case X86_BUG_SPEC_STORE_BYPASS:
+		return cpu_attack_vector_mitigated(CPU_MITIGATE_USER_USER);
+
 	default:
 		WARN(1, "Unknown bug %x\n", bug);
 		return false;
@@ -2710,6 +2714,11 @@ static void __init ssb_select_mitigation(void)
 		ssb_mode = SPEC_STORE_BYPASS_DISABLE;
 		break;
 	case SPEC_STORE_BYPASS_CMD_AUTO:
+		if (should_mitigate_vuln(X86_BUG_SPEC_STORE_BYPASS))
+			ssb_mode = SPEC_STORE_BYPASS_PRCTL;
+		else
+			ssb_mode = SPEC_STORE_BYPASS_NONE;
+		break;
 	case SPEC_STORE_BYPASS_CMD_PRCTL:
 		ssb_mode = SPEC_STORE_BYPASS_PRCTL;
 		break;
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 076eaa4..98ae4c3 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -262,7 +262,7 @@ static void early_init_intel(struct cpuinfo_x86 *c)
 	if (c->x86_power & (1 << 8)) {
 		set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
 		set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC);
-	} else if ((c->x86_vfm >= INTEL_P4_PRESCOTT && c->x86_vfm <= INTEL_P4_WILLAMETTE) ||
+	} else if ((c->x86_vfm >= INTEL_P4_PRESCOTT && c->x86_vfm <= INTEL_P4_CEDARMILL) ||
 		   (c->x86_vfm >= INTEL_CORE_YONAH  && c->x86_vfm <= INTEL_IVYBRIDGE)) {
 		set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
 	}
diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c
index 097e393..514f633 100644
--- a/arch/x86/kernel/cpu/microcode/amd.c
+++ b/arch/x86/kernel/cpu/microcode/amd.c
@@ -171,8 +171,28 @@ static int cmp_id(const void *key, const void *elem)
 		return 1;
 }
 
+static u32 cpuid_to_ucode_rev(unsigned int val)
+{
+	union zen_patch_rev p = {};
+	union cpuid_1_eax c;
+
+	c.full = val;
+
+	p.stepping  = c.stepping;
+	p.model     = c.model;
+	p.ext_model = c.ext_model;
+	p.ext_fam   = c.ext_fam;
+
+	return p.ucode_rev;
+}
+
 static bool need_sha_check(u32 cur_rev)
 {
+	if (!cur_rev) {
+		cur_rev = cpuid_to_ucode_rev(bsp_cpuid_1_eax);
+		pr_info_once("No current revision, generating the lowest one: 0x%x\n", cur_rev);
+	}
+
 	switch (cur_rev >> 8) {
 	case 0x80012: return cur_rev <= 0x800126f; break;
 	case 0x80082: return cur_rev <= 0x800820f; break;
@@ -749,8 +769,6 @@ static struct ucode_patch *cache_find_patch(struct ucode_cpu_info *uci, u16 equi
 	n.equiv_cpu = equiv_cpu;
 	n.patch_id  = uci->cpu_sig.rev;
 
-	WARN_ON_ONCE(!n.patch_id);
-
 	list_for_each_entry(p, &microcode_cache, plist)
 		if (patch_cpus_equivalent(p, &n, false))
 			return p;
diff --git a/arch/x86/kernel/cpu/topology_amd.c b/arch/x86/kernel/cpu/topology_amd.c
index 843b165..827dd0d 100644
--- a/arch/x86/kernel/cpu/topology_amd.c
+++ b/arch/x86/kernel/cpu/topology_amd.c
@@ -81,20 +81,25 @@ static bool parse_8000_001e(struct topo_scan *tscan, bool has_topoext)
 
 	cpuid_leaf(0x8000001e, &leaf);
 
-	tscan->c->topo.initial_apicid = leaf.ext_apic_id;
-
 	/*
-	 * If leaf 0xb is available, then the domain shifts are set
-	 * already and nothing to do here. Only valid for family >= 0x17.
+	 * If leaf 0xb/0x26 is available, then the APIC ID and the domain
+	 * shifts are set already.
 	 */
-	if (!has_topoext && tscan->c->x86 >= 0x17) {
-		/*
-		 * Leaf 0x80000008 set the CORE domain shift already.
-		 * Update the SMT domain, but do not propagate it.
-		 */
-		unsigned int nthreads = leaf.core_nthreads + 1;
+	if (!has_topoext) {
+		tscan->c->topo.initial_apicid = leaf.ext_apic_id;
 
-		topology_update_dom(tscan, TOPO_SMT_DOMAIN, get_count_order(nthreads), nthreads);
+		/*
+		 * Leaf 0x8000008 sets the CORE domain shift but not the
+		 * SMT domain shift. On CPUs with family >= 0x17, there
+		 * might be hyperthreads.
+		 */
+		if (tscan->c->x86 >= 0x17) {
+			/* Update the SMT domain, but do not propagate it. */
+			unsigned int nthreads = leaf.core_nthreads + 1;
+
+			topology_update_dom(tscan, TOPO_SMT_DOMAIN,
+					    get_count_order(nthreads), nthreads);
+		}
 	}
 
 	store_node(tscan, leaf.nnodes_per_socket + 1, leaf.node_id);
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 8172c20..5fc4373 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -810,6 +810,8 @@ static int __pv_send_ipi(unsigned long *ipi_bitmap, struct kvm_apic_map *map,
 	if (min > map->max_apic_id)
 		return 0;
 
+	min = array_index_nospec(min, map->max_apic_id + 1);
+
 	for_each_set_bit(i, ipi_bitmap,
 		min((u32)BITS_PER_LONG, (map->max_apic_id - min + 1))) {
 		if (map->phys_map[min + i]) {
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index 2fbdebf..0635bd7 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -719,13 +719,6 @@ static void sev_clflush_pages(struct page *pages[], unsigned long npages)
 static void sev_writeback_caches(struct kvm *kvm)
 {
 	/*
-	 * Note, the caller is responsible for ensuring correctness if the mask
-	 * can be modified, e.g. if a CPU could be doing VMRUN.
-	 */
-	if (cpumask_empty(to_kvm_sev_info(kvm)->have_run_cpus))
-		return;
-
-	/*
 	 * Ensure that all dirty guest tagged cache entries are written back
 	 * before releasing the pages back to the system for use.  CLFLUSH will
 	 * not do this without SME_COHERENT, and flushing many cache lines
@@ -739,6 +732,9 @@ static void sev_writeback_caches(struct kvm *kvm)
 	 * serializing multiple calls and having responding CPUs (to the IPI)
 	 * mark themselves as still running if they are running (or about to
 	 * run) a vCPU for the VM.
+	 *
+	 * Note, the caller is responsible for ensuring correctness if the mask
+	 * can be modified, e.g. if a CPU could be doing VMRUN.
 	 */
 	wbnoinvd_on_cpus_mask(to_kvm_sev_info(kvm)->have_run_cpus);
 }
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index a1c49bc..604490b 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -9908,8 +9908,11 @@ static void kvm_sched_yield(struct kvm_vcpu *vcpu, unsigned long dest_id)
 	rcu_read_lock();
 	map = rcu_dereference(vcpu->kvm->arch.apic_map);
 
-	if (likely(map) && dest_id <= map->max_apic_id && map->phys_map[dest_id])
-		target = map->phys_map[dest_id]->vcpu;
+	if (likely(map) && dest_id <= map->max_apic_id) {
+		dest_id = array_index_nospec(dest_id, map->max_apic_id + 1);
+		if (map->phys_map[dest_id])
+			target = map->phys_map[dest_id]->vcpu;
+	}
 
 	rcu_read_unlock();
 
diff --git a/block/blk-rq-qos.h b/block/blk-rq-qos.h
index 1fe2200..b538f2c 100644
--- a/block/blk-rq-qos.h
+++ b/block/blk-rq-qos.h
@@ -149,12 +149,15 @@ static inline void rq_qos_done_bio(struct bio *bio)
 	q = bdev_get_queue(bio->bi_bdev);
 
 	/*
-	 * If a bio has BIO_QOS_xxx set, it implicitly implies that
-	 * q->rq_qos is present. So, we skip re-checking q->rq_qos
-	 * here as an extra optimization and directly call
-	 * __rq_qos_done_bio().
+	 * A BIO may carry BIO_QOS_* flags even if the associated request_queue
+	 * does not have rq_qos enabled. This can happen with stacked block
+	 * devices — for example, NVMe multipath, where it's possible that the
+	 * bottom device has QoS enabled but the top device does not. Therefore,
+	 * always verify that q->rq_qos is present and QoS is enabled before
+	 * calling __rq_qos_done_bio().
 	 */
-	__rq_qos_done_bio(q->rq_qos, bio);
+	if (test_bit(QUEUE_FLAG_QOS_ENABLED, &q->queue_flags) && q->rq_qos)
+		__rq_qos_done_bio(q->rq_qos, bio);
 }
 
 static inline void rq_qos_throttle(struct request_queue *q, struct bio *bio)
diff --git a/block/blk-zoned.c b/block/blk-zoned.c
index ef43aac..5e2a578 100644
--- a/block/blk-zoned.c
+++ b/block/blk-zoned.c
@@ -1286,14 +1286,14 @@ static void blk_zone_wplug_bio_work(struct work_struct *work)
 	struct block_device *bdev;
 	unsigned long flags;
 	struct bio *bio;
+	bool prepared;
 
 	/*
 	 * Submit the next plugged BIO. If we do not have any, clear
 	 * the plugged flag.
 	 */
-	spin_lock_irqsave(&zwplug->lock, flags);
-
 again:
+	spin_lock_irqsave(&zwplug->lock, flags);
 	bio = bio_list_pop(&zwplug->bio_list);
 	if (!bio) {
 		zwplug->flags &= ~BLK_ZONE_WPLUG_PLUGGED;
@@ -1304,13 +1304,14 @@ static void blk_zone_wplug_bio_work(struct work_struct *work)
 	trace_blk_zone_wplug_bio(zwplug->disk->queue, zwplug->zone_no,
 				 bio->bi_iter.bi_sector, bio_sectors(bio));
 
-	if (!blk_zone_wplug_prepare_bio(zwplug, bio)) {
+	prepared = blk_zone_wplug_prepare_bio(zwplug, bio);
+	spin_unlock_irqrestore(&zwplug->lock, flags);
+
+	if (!prepared) {
 		blk_zone_wplug_bio_io_error(zwplug, bio);
 		goto again;
 	}
 
-	spin_unlock_irqrestore(&zwplug->lock, flags);
-
 	bdev = bio->bi_bdev;
 
 	/*
diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c
index e1c24bb..7a7f88b 100644
--- a/drivers/ata/ahci.c
+++ b/drivers/ata/ahci.c
@@ -689,40 +689,50 @@ MODULE_PARM_DESC(mask_port_map,
 		 "where <pci_dev> is the PCI ID of an AHCI controller in the "
 		 "form \"domain:bus:dev.func\"");
 
-static void ahci_apply_port_map_mask(struct device *dev,
-				     struct ahci_host_priv *hpriv, char *mask_s)
+static char *ahci_mask_port_ext;
+module_param_named(mask_port_ext, ahci_mask_port_ext, charp, 0444);
+MODULE_PARM_DESC(mask_port_ext,
+		 "32-bits mask to ignore the external/hotplug capability of ports. "
+		 "Valid values are: "
+		 "\"<mask>\" to apply the same mask to all AHCI controller "
+		 "devices, and \"<pci_dev>=<mask>,<pci_dev>=<mask>,...\" to "
+		 "specify different masks for the controllers specified, "
+		 "where <pci_dev> is the PCI ID of an AHCI controller in the "
+		 "form \"domain:bus:dev.func\"");
+
+static u32 ahci_port_mask(struct device *dev, char *mask_s)
 {
 	unsigned int mask;
 
 	if (kstrtouint(mask_s, 0, &mask)) {
 		dev_err(dev, "Invalid port map mask\n");
-		return;
+		return 0;
 	}
 
-	hpriv->mask_port_map = mask;
+	return mask;
 }
 
-static void ahci_get_port_map_mask(struct device *dev,
-				   struct ahci_host_priv *hpriv)
+static u32 ahci_get_port_mask(struct device *dev, char *mask_p)
 {
 	char *param, *end, *str, *mask_s;
 	char *name;
+	u32 mask = 0;
 
-	if (!strlen(ahci_mask_port_map))
-		return;
+	if (!mask_p || !strlen(mask_p))
+		return 0;
 
-	str = kstrdup(ahci_mask_port_map, GFP_KERNEL);
+	str = kstrdup(mask_p, GFP_KERNEL);
 	if (!str)
-		return;
+		return 0;
 
 	/* Handle single mask case */
 	if (!strchr(str, '=')) {
-		ahci_apply_port_map_mask(dev, hpriv, str);
+		mask = ahci_port_mask(dev, str);
 		goto free;
 	}
 
 	/*
-	 * Mask list case: parse the parameter to apply the mask only if
+	 * Mask list case: parse the parameter to get the mask only if
 	 * the device name matches.
 	 */
 	param = str;
@@ -752,11 +762,13 @@ static void ahci_get_port_map_mask(struct device *dev,
 			param++;
 		}
 
-		ahci_apply_port_map_mask(dev, hpriv, mask_s);
+		mask = ahci_port_mask(dev, mask_s);
 	}
 
 free:
 	kfree(str);
+
+	return mask;
 }
 
 static void ahci_pci_save_initial_config(struct pci_dev *pdev,
@@ -782,8 +794,10 @@ static void ahci_pci_save_initial_config(struct pci_dev *pdev,
 	}
 
 	/* Handle port map masks passed as module parameter. */
-	if (ahci_mask_port_map)
-		ahci_get_port_map_mask(&pdev->dev, hpriv);
+	hpriv->mask_port_map =
+		ahci_get_port_mask(&pdev->dev, ahci_mask_port_map);
+	hpriv->mask_port_ext =
+		ahci_get_port_mask(&pdev->dev, ahci_mask_port_ext);
 
 	ahci_save_initial_config(&pdev->dev, hpriv);
 }
@@ -1757,11 +1771,20 @@ static void ahci_mark_external_port(struct ata_port *ap)
 	void __iomem *port_mmio = ahci_port_base(ap);
 	u32 tmp;
 
-	/* mark external ports (hotplug-capable, eSATA) */
+	/*
+	 * Mark external ports (hotplug-capable, eSATA), unless we were asked to
+	 * ignore this feature.
+	 */
 	tmp = readl(port_mmio + PORT_CMD);
 	if (((tmp & PORT_CMD_ESP) && (hpriv->cap & HOST_CAP_SXS)) ||
-	    (tmp & PORT_CMD_HPCP))
+	    (tmp & PORT_CMD_HPCP)) {
+		if (hpriv->mask_port_ext & (1U << ap->port_no)) {
+			ata_port_info(ap,
+				"Ignoring external/hotplug capability\n");
+			return;
+		}
 		ap->pflags |= ATA_PFLAG_EXTERNAL;
+	}
 }
 
 static void ahci_update_initial_lpm_policy(struct ata_port *ap)
diff --git a/drivers/ata/ahci.h b/drivers/ata/ahci.h
index 2c10c8f..293b7fb 100644
--- a/drivers/ata/ahci.h
+++ b/drivers/ata/ahci.h
@@ -330,6 +330,7 @@ struct ahci_host_priv {
 	/* Input fields */
 	unsigned int		flags;		/* AHCI_HFLAG_* */
 	u32			mask_port_map;	/* Mask of valid ports */
+	u32			mask_port_ext;	/* Mask of ports ext capability */
 
 	void __iomem *		mmio;		/* bus-independent mem map */
 	u32			cap;		/* cap to use */
diff --git a/drivers/ata/ahci_xgene.c b/drivers/ata/ahci_xgene.c
index 5d5a51a..6b88446 100644
--- a/drivers/ata/ahci_xgene.c
+++ b/drivers/ata/ahci_xgene.c
@@ -450,7 +450,6 @@ static int xgene_ahci_pmp_softreset(struct ata_link *link, unsigned int *class,
 {
 	int pmp = sata_srst_pmp(link);
 	struct ata_port *ap = link->ap;
-	u32 rc;
 	void __iomem *port_mmio = ahci_port_base(ap);
 	u32 port_fbs;
 
@@ -463,9 +462,7 @@ static int xgene_ahci_pmp_softreset(struct ata_link *link, unsigned int *class,
 	port_fbs |= pmp << PORT_FBS_DEV_OFFSET;
 	writel(port_fbs, port_mmio + PORT_FBS);
 
-	rc = ahci_do_softreset(link, class, pmp, deadline, ahci_check_ready);
-
-	return rc;
+	return ahci_do_softreset(link, class, pmp, deadline, ahci_check_ready);
 }
 
 /**
@@ -500,7 +497,7 @@ static int xgene_ahci_softreset(struct ata_link *link, unsigned int *class,
 	u32 port_fbs;
 	u32 port_fbs_save;
 	u32 retry = 1;
-	u32 rc;
+	int rc;
 
 	port_fbs_save = readl(port_mmio + PORT_FBS);
 
diff --git a/drivers/atm/atmtcp.c b/drivers/atm/atmtcp.c
index eeae160..fa3c76a 100644
--- a/drivers/atm/atmtcp.c
+++ b/drivers/atm/atmtcp.c
@@ -279,6 +279,19 @@ static struct atm_vcc *find_vcc(struct atm_dev *dev, short vpi, int vci)
         return NULL;
 }
 
+static int atmtcp_c_pre_send(struct atm_vcc *vcc, struct sk_buff *skb)
+{
+	struct atmtcp_hdr *hdr;
+
+	if (skb->len < sizeof(struct atmtcp_hdr))
+		return -EINVAL;
+
+	hdr = (struct atmtcp_hdr *)skb->data;
+	if (hdr->length == ATMTCP_HDR_MAGIC)
+		return -EINVAL;
+
+	return 0;
+}
 
 static int atmtcp_c_send(struct atm_vcc *vcc,struct sk_buff *skb)
 {
@@ -288,9 +301,6 @@ static int atmtcp_c_send(struct atm_vcc *vcc,struct sk_buff *skb)
 	struct sk_buff *new_skb;
 	int result = 0;
 
-	if (skb->len < sizeof(struct atmtcp_hdr))
-		goto done;
-
 	dev = vcc->dev_data;
 	hdr = (struct atmtcp_hdr *) skb->data;
 	if (hdr->length == ATMTCP_HDR_MAGIC) {
@@ -347,6 +357,7 @@ static const struct atmdev_ops atmtcp_v_dev_ops = {
 
 static const struct atmdev_ops atmtcp_c_dev_ops = {
 	.close		= atmtcp_c_close,
+	.pre_send	= atmtcp_c_pre_send,
 	.send		= atmtcp_c_send
 };
 
diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c
index dbf5456..2ea6e05 100644
--- a/drivers/base/power/main.c
+++ b/drivers/base/power/main.c
@@ -675,7 +675,7 @@ static void dpm_async_resume_subordinate(struct device *dev, async_func_t func)
 	idx = device_links_read_lock();
 
 	/* Start processing the device's "async" consumers. */
-	list_for_each_entry_rcu(link, &dev->links.consumers, s_node)
+	list_for_each_entry_rcu_locked(link, &dev->links.consumers, s_node)
 		if (READ_ONCE(link->status) != DL_STATE_DORMANT)
 			dpm_async_with_cleanup(link->consumer, func);
 
@@ -1330,7 +1330,7 @@ static void dpm_async_suspend_superior(struct device *dev, async_func_t func)
 	idx = device_links_read_lock();
 
 	/* Start processing the device's "async" suppliers. */
-	list_for_each_entry_rcu(link, &dev->links.suppliers, c_node)
+	list_for_each_entry_rcu_locked(link, &dev->links.suppliers, c_node)
 		if (READ_ONCE(link->status) != DL_STATE_DORMANT)
 			dpm_async_with_cleanup(link->supplier, func);
 
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index 57263c2..053a086 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -139,20 +139,26 @@ static int part_shift;
 
 static loff_t lo_calculate_size(struct loop_device *lo, struct file *file)
 {
-	struct kstat stat;
 	loff_t loopsize;
 	int ret;
 
-	/*
-	 * Get the accurate file size. This provides better results than
-	 * cached inode data, particularly for network filesystems where
-	 * metadata may be stale.
-	 */
-	ret = vfs_getattr_nosec(&file->f_path, &stat, STATX_SIZE, 0);
-	if (ret)
-		return 0;
+	if (S_ISBLK(file_inode(file)->i_mode)) {
+		loopsize = i_size_read(file->f_mapping->host);
+	} else {
+		struct kstat stat;
 
-	loopsize = stat.size;
+		/*
+		 * Get the accurate file size. This provides better results than
+		 * cached inode data, particularly for network filesystems where
+		 * metadata may be stale.
+		 */
+		ret = vfs_getattr_nosec(&file->f_path, &stat, STATX_SIZE, 0);
+		if (ret)
+			return 0;
+
+		loopsize = stat.size;
+	}
+
 	if (lo->lo_offset > 0)
 		loopsize -= lo->lo_offset;
 	/* offset is beyond i_size, weird but possible */
diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c
index 99abd67..67d4a86 100644
--- a/drivers/block/ublk_drv.c
+++ b/drivers/block/ublk_drv.c
@@ -239,6 +239,7 @@ struct ublk_device {
 	struct mutex cancel_mutex;
 	bool canceling;
 	pid_t 	ublksrv_tgid;
+	struct delayed_work	exit_work;
 };
 
 /* header of ublk_params */
@@ -1595,13 +1596,63 @@ static void ublk_set_canceling(struct ublk_device *ub, bool canceling)
 		ublk_get_queue(ub, i)->canceling = canceling;
 }
 
-static int ublk_ch_release(struct inode *inode, struct file *filp)
+static bool ublk_check_and_reset_active_ref(struct ublk_device *ub)
 {
-	struct ublk_device *ub = filp->private_data;
+	int i, j;
+
+	if (!(ub->dev_info.flags & (UBLK_F_SUPPORT_ZERO_COPY |
+					UBLK_F_AUTO_BUF_REG)))
+		return false;
+
+	for (i = 0; i < ub->dev_info.nr_hw_queues; i++) {
+		struct ublk_queue *ubq = ublk_get_queue(ub, i);
+
+		for (j = 0; j < ubq->q_depth; j++) {
+			struct ublk_io *io = &ubq->ios[j];
+			unsigned int refs = refcount_read(&io->ref) +
+				io->task_registered_buffers;
+
+			/*
+			 * UBLK_REFCOUNT_INIT or zero means no active
+			 * reference
+			 */
+			if (refs != UBLK_REFCOUNT_INIT && refs != 0)
+				return true;
+
+			/* reset to zero if the io hasn't active references */
+			refcount_set(&io->ref, 0);
+			io->task_registered_buffers = 0;
+		}
+	}
+	return false;
+}
+
+static void ublk_ch_release_work_fn(struct work_struct *work)
+{
+	struct ublk_device *ub =
+		container_of(work, struct ublk_device, exit_work.work);
 	struct gendisk *disk;
 	int i;
 
 	/*
+	 * For zero-copy and auto buffer register modes, I/O references
+	 * might not be dropped naturally when the daemon is killed, but
+	 * io_uring guarantees that registered bvec kernel buffers are
+	 * unregistered finally when freeing io_uring context, then the
+	 * active references are dropped.
+	 *
+	 * Wait until active references are dropped for avoiding use-after-free
+	 *
+	 * registered buffer may be unregistered in io_ring's release hander,
+	 * so have to wait by scheduling work function for avoiding the two
+	 * file release dependency.
+	 */
+	if (ublk_check_and_reset_active_ref(ub)) {
+		schedule_delayed_work(&ub->exit_work, 1);
+		return;
+	}
+
+	/*
 	 * disk isn't attached yet, either device isn't live, or it has
 	 * been removed already, so we needn't to do anything
 	 */
@@ -1673,6 +1724,23 @@ static int ublk_ch_release(struct inode *inode, struct file *filp)
 	ublk_reset_ch_dev(ub);
 out:
 	clear_bit(UB_STATE_OPEN, &ub->state);
+
+	/* put the reference grabbed in ublk_ch_release() */
+	ublk_put_device(ub);
+}
+
+static int ublk_ch_release(struct inode *inode, struct file *filp)
+{
+	struct ublk_device *ub = filp->private_data;
+
+	/*
+	 * Grab ublk device reference, so it won't be gone until we are
+	 * really released from work function.
+	 */
+	ublk_get_device(ub);
+
+	INIT_DELAYED_WORK(&ub->exit_work, ublk_ch_release_work_fn);
+	schedule_delayed_work(&ub->exit_work, 0);
 	return 0;
 }
 
diff --git a/drivers/firmware/efi/stmm/tee_stmm_efi.c b/drivers/firmware/efi/stmm/tee_stmm_efi.c
index f741ca2..65c0fe1 100644
--- a/drivers/firmware/efi/stmm/tee_stmm_efi.c
+++ b/drivers/firmware/efi/stmm/tee_stmm_efi.c
@@ -143,6 +143,10 @@ static efi_status_t mm_communicate(u8 *comm_buf, size_t payload_size)
 	return var_hdr->ret_status;
 }
 
+#define COMM_BUF_SIZE(__payload_size)	(MM_COMMUNICATE_HEADER_SIZE + \
+					 MM_VARIABLE_COMMUNICATE_SIZE + \
+					 (__payload_size))
+
 /**
  * setup_mm_hdr() -	Allocate a buffer for StandAloneMM and initialize the
  *			header data.
@@ -150,11 +154,9 @@ static efi_status_t mm_communicate(u8 *comm_buf, size_t payload_size)
  * @dptr:		pointer address to store allocated buffer
  * @payload_size:	payload size
  * @func:		standAloneMM function number
- * @ret:		EFI return code
  * Return:		pointer to corresponding StandAloneMM function buffer or NULL
  */
-static void *setup_mm_hdr(u8 **dptr, size_t payload_size, size_t func,
-			  efi_status_t *ret)
+static void *setup_mm_hdr(u8 **dptr, size_t payload_size, size_t func)
 {
 	const efi_guid_t mm_var_guid = EFI_MM_VARIABLE_GUID;
 	struct efi_mm_communicate_header *mm_hdr;
@@ -169,17 +171,13 @@ static void *setup_mm_hdr(u8 **dptr, size_t payload_size, size_t func,
 	if (max_buffer_size &&
 	    max_buffer_size < (MM_COMMUNICATE_HEADER_SIZE +
 			       MM_VARIABLE_COMMUNICATE_SIZE + payload_size)) {
-		*ret = EFI_INVALID_PARAMETER;
 		return NULL;
 	}
 
-	comm_buf = kzalloc(MM_COMMUNICATE_HEADER_SIZE +
-				   MM_VARIABLE_COMMUNICATE_SIZE + payload_size,
-			   GFP_KERNEL);
-	if (!comm_buf) {
-		*ret = EFI_OUT_OF_RESOURCES;
+	comm_buf = alloc_pages_exact(COMM_BUF_SIZE(payload_size),
+				     GFP_KERNEL | __GFP_ZERO);
+	if (!comm_buf)
 		return NULL;
-	}
 
 	mm_hdr = (struct efi_mm_communicate_header *)comm_buf;
 	memcpy(&mm_hdr->header_guid, &mm_var_guid, sizeof(mm_hdr->header_guid));
@@ -187,9 +185,7 @@ static void *setup_mm_hdr(u8 **dptr, size_t payload_size, size_t func,
 
 	var_hdr = (struct smm_variable_communicate_header *)mm_hdr->data;
 	var_hdr->function = func;
-	if (dptr)
-		*dptr = comm_buf;
-	*ret = EFI_SUCCESS;
+	*dptr = comm_buf;
 
 	return var_hdr->data;
 }
@@ -212,10 +208,9 @@ static efi_status_t get_max_payload(size_t *size)
 
 	payload_size = sizeof(*var_payload);
 	var_payload = setup_mm_hdr(&comm_buf, payload_size,
-				   SMM_VARIABLE_FUNCTION_GET_PAYLOAD_SIZE,
-				   &ret);
+				   SMM_VARIABLE_FUNCTION_GET_PAYLOAD_SIZE);
 	if (!var_payload)
-		return EFI_OUT_OF_RESOURCES;
+		return EFI_DEVICE_ERROR;
 
 	ret = mm_communicate(comm_buf, payload_size);
 	if (ret != EFI_SUCCESS)
@@ -239,7 +234,7 @@ static efi_status_t get_max_payload(size_t *size)
 	 */
 	*size -= 2;
 out:
-	kfree(comm_buf);
+	free_pages_exact(comm_buf, COMM_BUF_SIZE(payload_size));
 	return ret;
 }
 
@@ -259,9 +254,9 @@ static efi_status_t get_property_int(u16 *name, size_t name_size,
 
 	smm_property = setup_mm_hdr(
 		&comm_buf, payload_size,
-		SMM_VARIABLE_FUNCTION_VAR_CHECK_VARIABLE_PROPERTY_GET, &ret);
+		SMM_VARIABLE_FUNCTION_VAR_CHECK_VARIABLE_PROPERTY_GET);
 	if (!smm_property)
-		return EFI_OUT_OF_RESOURCES;
+		return EFI_DEVICE_ERROR;
 
 	memcpy(&smm_property->guid, vendor, sizeof(smm_property->guid));
 	smm_property->name_size = name_size;
@@ -282,7 +277,7 @@ static efi_status_t get_property_int(u16 *name, size_t name_size,
 	memcpy(var_property, &smm_property->property, sizeof(*var_property));
 
 out:
-	kfree(comm_buf);
+	free_pages_exact(comm_buf, COMM_BUF_SIZE(payload_size));
 	return ret;
 }
 
@@ -315,9 +310,9 @@ static efi_status_t tee_get_variable(u16 *name, efi_guid_t *vendor,
 
 	payload_size = MM_VARIABLE_ACCESS_HEADER_SIZE + name_size + tmp_dsize;
 	var_acc = setup_mm_hdr(&comm_buf, payload_size,
-			       SMM_VARIABLE_FUNCTION_GET_VARIABLE, &ret);
+			       SMM_VARIABLE_FUNCTION_GET_VARIABLE);
 	if (!var_acc)
-		return EFI_OUT_OF_RESOURCES;
+		return EFI_DEVICE_ERROR;
 
 	/* Fill in contents */
 	memcpy(&var_acc->guid, vendor, sizeof(var_acc->guid));
@@ -347,7 +342,7 @@ static efi_status_t tee_get_variable(u16 *name, efi_guid_t *vendor,
 	memcpy(data, (u8 *)var_acc->name + var_acc->name_size,
 	       var_acc->data_size);
 out:
-	kfree(comm_buf);
+	free_pages_exact(comm_buf, COMM_BUF_SIZE(payload_size));
 	return ret;
 }
 
@@ -380,10 +375,9 @@ static efi_status_t tee_get_next_variable(unsigned long *name_size,
 
 	payload_size = MM_VARIABLE_GET_NEXT_HEADER_SIZE + out_name_size;
 	var_getnext = setup_mm_hdr(&comm_buf, payload_size,
-				   SMM_VARIABLE_FUNCTION_GET_NEXT_VARIABLE_NAME,
-				   &ret);
+				SMM_VARIABLE_FUNCTION_GET_NEXT_VARIABLE_NAME);
 	if (!var_getnext)
-		return EFI_OUT_OF_RESOURCES;
+		return EFI_DEVICE_ERROR;
 
 	/* Fill in contents */
 	memcpy(&var_getnext->guid, guid, sizeof(var_getnext->guid));
@@ -404,7 +398,7 @@ static efi_status_t tee_get_next_variable(unsigned long *name_size,
 	memcpy(name, var_getnext->name, var_getnext->name_size);
 
 out:
-	kfree(comm_buf);
+	free_pages_exact(comm_buf, COMM_BUF_SIZE(payload_size));
 	return ret;
 }
 
@@ -437,9 +431,9 @@ static efi_status_t tee_set_variable(efi_char16_t *name, efi_guid_t *vendor,
 	 * the properties, if the allocation fails
 	 */
 	var_acc = setup_mm_hdr(&comm_buf, payload_size,
-			       SMM_VARIABLE_FUNCTION_SET_VARIABLE, &ret);
+			       SMM_VARIABLE_FUNCTION_SET_VARIABLE);
 	if (!var_acc)
-		return EFI_OUT_OF_RESOURCES;
+		return EFI_DEVICE_ERROR;
 
 	/*
 	 * The API has the ability to override RO flags. If no RO check was
@@ -467,7 +461,7 @@ static efi_status_t tee_set_variable(efi_char16_t *name, efi_guid_t *vendor,
 	ret = mm_communicate(comm_buf, payload_size);
 	dev_dbg(pvt_data.dev, "Set Variable %s %d %lx\n", __FILE__, __LINE__, ret);
 out:
-	kfree(comm_buf);
+	free_pages_exact(comm_buf, COMM_BUF_SIZE(payload_size));
 	return ret;
 }
 
@@ -492,10 +486,9 @@ static efi_status_t tee_query_variable_info(u32 attributes,
 
 	payload_size = sizeof(*mm_query_info);
 	mm_query_info = setup_mm_hdr(&comm_buf, payload_size,
-				SMM_VARIABLE_FUNCTION_QUERY_VARIABLE_INFO,
-				&ret);
+				SMM_VARIABLE_FUNCTION_QUERY_VARIABLE_INFO);
 	if (!mm_query_info)
-		return EFI_OUT_OF_RESOURCES;
+		return EFI_DEVICE_ERROR;
 
 	mm_query_info->attr = attributes;
 	ret = mm_communicate(comm_buf, payload_size);
@@ -507,7 +500,7 @@ static efi_status_t tee_query_variable_info(u32 attributes,
 	*max_variable_size = mm_query_info->max_variable_size;
 
 out:
-	kfree(comm_buf);
+	free_pages_exact(comm_buf, COMM_BUF_SIZE(payload_size));
 	return ret;
 }
 
diff --git a/drivers/gpio/gpio-timberdale.c b/drivers/gpio/gpio-timberdale.c
index 679e27f..f488939 100644
--- a/drivers/gpio/gpio-timberdale.c
+++ b/drivers/gpio/gpio-timberdale.c
@@ -137,7 +137,7 @@ static int timbgpio_irq_type(struct irq_data *d, unsigned trigger)
 	u32 ver;
 	int ret = 0;
 
-	if (offset < 0 || offset > tgpio->gpio.ngpio)
+	if (offset < 0 || offset >= tgpio->gpio.ngpio)
 		return -EINVAL;
 
 	ver = ioread32(tgpio->membase + TGPIO_VER);
diff --git a/drivers/gpio/gpiolib-acpi-quirks.c b/drivers/gpio/gpiolib-acpi-quirks.c
index c13545d..bfb04e6 100644
--- a/drivers/gpio/gpiolib-acpi-quirks.c
+++ b/drivers/gpio/gpiolib-acpi-quirks.c
@@ -344,6 +344,20 @@ static const struct dmi_system_id gpiolib_acpi_quirks[] __initconst = {
 			.ignore_interrupt = "AMDI0030:00@8",
 		},
 	},
+	{
+		/*
+		 * Spurious wakeups from TP_ATTN# pin
+		 * Found in BIOS 5.35
+		 * https://gitlab.freedesktop.org/drm/amd/-/issues/4482
+		 */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_PRODUCT_FAMILY, "ProArt PX13"),
+		},
+		.driver_data = &(struct acpi_gpiolib_dmi_quirk) {
+			.ignore_wake = "ASCP1A00:00@8",
+		},
+	},
 	{} /* Terminating entry */
 };
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_csa.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_csa.c
index dfb6cfd..02138aa 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_csa.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_csa.c
@@ -88,8 +88,8 @@ int amdgpu_map_static_csa(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 	}
 
 	r = amdgpu_vm_bo_map(adev, *bo_va, csa_addr, 0, size,
-			     AMDGPU_VM_PAGE_READABLE | AMDGPU_VM_PAGE_WRITEABLE |
-			     AMDGPU_VM_PAGE_EXECUTABLE);
+			     AMDGPU_PTE_READABLE | AMDGPU_PTE_WRITEABLE |
+			     AMDGPU_PTE_EXECUTABLE);
 
 	if (r) {
 		DRM_ERROR("failed to do bo_map on static CSA, err=%d\n", r);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c
index 5743ebb..ce27cb5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c
@@ -285,6 +285,36 @@ static int amdgpu_dma_buf_begin_cpu_access(struct dma_buf *dma_buf,
 	return ret;
 }
 
+static int amdgpu_dma_buf_vmap(struct dma_buf *dma_buf, struct iosys_map *map)
+{
+	struct drm_gem_object *obj = dma_buf->priv;
+	struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj);
+	int ret;
+
+	/*
+	 * Pin to keep buffer in place while it's vmap'ed. The actual
+	 * domain is not that important as long as it's mapable. Using
+	 * GTT and VRAM should be compatible with most use cases.
+	 */
+	ret = amdgpu_bo_pin(bo, AMDGPU_GEM_DOMAIN_GTT | AMDGPU_GEM_DOMAIN_VRAM);
+	if (ret)
+		return ret;
+	ret = drm_gem_dmabuf_vmap(dma_buf, map);
+	if (ret)
+		amdgpu_bo_unpin(bo);
+
+	return ret;
+}
+
+static void amdgpu_dma_buf_vunmap(struct dma_buf *dma_buf, struct iosys_map *map)
+{
+	struct drm_gem_object *obj = dma_buf->priv;
+	struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj);
+
+	drm_gem_dmabuf_vunmap(dma_buf, map);
+	amdgpu_bo_unpin(bo);
+}
+
 const struct dma_buf_ops amdgpu_dmabuf_ops = {
 	.attach = amdgpu_dma_buf_attach,
 	.pin = amdgpu_dma_buf_pin,
@@ -294,8 +324,8 @@ const struct dma_buf_ops amdgpu_dmabuf_ops = {
 	.release = drm_gem_dmabuf_release,
 	.begin_cpu_access = amdgpu_dma_buf_begin_cpu_access,
 	.mmap = drm_gem_dmabuf_mmap,
-	.vmap = drm_gem_dmabuf_vmap,
-	.vunmap = drm_gem_dmabuf_vunmap,
+	.vmap = amdgpu_dma_buf_vmap,
+	.vunmap = amdgpu_dma_buf_vunmap,
 };
 
 /**
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c
index c3ace80..8190c24 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c
@@ -471,6 +471,7 @@ amdgpu_userq_create(struct drm_file *filp, union drm_amdgpu_userq *args)
 	if (index == (uint64_t)-EINVAL) {
 		drm_file_err(uq_mgr->file, "Failed to get doorbell for queue\n");
 		kfree(queue);
+		r = -EINVAL;
 		goto unlock;
 	}
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
index c01c241..c85de8c 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
@@ -1612,9 +1612,9 @@ static int gfx_v11_0_sw_init(struct amdgpu_ip_block *ip_block)
 	case IP_VERSION(11, 0, 2):
 	case IP_VERSION(11, 0, 3):
 		if (!adev->gfx.disable_uq &&
-		    adev->gfx.me_fw_version  >= 2390 &&
-		    adev->gfx.pfp_fw_version >= 2530 &&
-		    adev->gfx.mec_fw_version >= 2600 &&
+		    adev->gfx.me_fw_version  >= 2420 &&
+		    adev->gfx.pfp_fw_version >= 2580 &&
+		    adev->gfx.mec_fw_version >= 2650 &&
 		    adev->mes.fw_version[0] >= 120) {
 			adev->userq_funcs[AMDGPU_HW_IP_GFX] = &userq_mes_funcs;
 			adev->userq_funcs[AMDGPU_HW_IP_COMPUTE] = &userq_mes_funcs;
@@ -4129,6 +4129,8 @@ static int gfx_v11_0_gfx_mqd_init(struct amdgpu_device *adev, void *m,
 #endif
 	if (prop->tmz_queue)
 		tmp = REG_SET_FIELD(tmp, CP_GFX_HQD_CNTL, TMZ_MATCH, 1);
+	if (!prop->kernel_queue)
+		tmp = REG_SET_FIELD(tmp, CP_GFX_HQD_CNTL, RB_NON_PRIV, 1);
 	mqd->cp_gfx_hqd_cntl = tmp;
 
 	/* set up cp_doorbell_control */
@@ -4281,8 +4283,10 @@ static int gfx_v11_0_compute_mqd_init(struct amdgpu_device *adev, void *m,
 	tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, UNORD_DISPATCH, 1);
 	tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, TUNNEL_DISPATCH,
 			    prop->allow_tunneling);
-	tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, PRIV_STATE, 1);
-	tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, KMD_QUEUE, 1);
+	if (prop->kernel_queue) {
+		tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, PRIV_STATE, 1);
+		tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, KMD_QUEUE, 1);
+	}
 	if (prop->tmz_queue)
 		tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, TMZ, 1);
 	mqd->cp_hqd_pq_control = tmp;
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c
index 3e13852..fd44d55 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c
@@ -3026,6 +3026,8 @@ static int gfx_v12_0_gfx_mqd_init(struct amdgpu_device *adev, void *m,
 #endif
 	if (prop->tmz_queue)
 		tmp = REG_SET_FIELD(tmp, CP_GFX_HQD_CNTL, TMZ_MATCH, 1);
+	if (!prop->kernel_queue)
+		tmp = REG_SET_FIELD(tmp, CP_GFX_HQD_CNTL, RB_NON_PRIV, 1);
 	mqd->cp_gfx_hqd_cntl = tmp;
 
 	/* set up cp_doorbell_control */
@@ -3175,8 +3177,10 @@ static int gfx_v12_0_compute_mqd_init(struct amdgpu_device *adev, void *m,
 			    (order_base_2(AMDGPU_GPU_PAGE_SIZE / 4) - 1));
 	tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, UNORD_DISPATCH, 1);
 	tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, TUNNEL_DISPATCH, 0);
-	tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, PRIV_STATE, 1);
-	tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, KMD_QUEUE, 1);
+	if (prop->kernel_queue) {
+		tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, PRIV_STATE, 1);
+		tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, KMD_QUEUE, 1);
+	}
 	if (prop->tmz_queue)
 		tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, TMZ, 1);
 	mqd->cp_hqd_pq_control = tmp;
diff --git a/drivers/gpu/drm/amd/pm/amdgpu_pm.c b/drivers/gpu/drm/amd/pm/amdgpu_pm.c
index 4b64851..5fbfe73 100644
--- a/drivers/gpu/drm/amd/pm/amdgpu_pm.c
+++ b/drivers/gpu/drm/amd/pm/amdgpu_pm.c
@@ -3458,14 +3458,16 @@ static umode_t hwmon_attributes_visible(struct kobject *kobj,
 		effective_mode &= ~S_IWUSR;
 
 	/* not implemented yet for APUs other than GC 10.3.1 (vangogh) and 9.4.3 */
-	if (((adev->family == AMDGPU_FAMILY_SI) ||
-	     ((adev->flags & AMD_IS_APU) && (gc_ver != IP_VERSION(10, 3, 1)) &&
-	      (gc_ver != IP_VERSION(9, 4, 3) && gc_ver != IP_VERSION(9, 4, 4)))) &&
-	    (attr == &sensor_dev_attr_power1_cap_max.dev_attr.attr ||
-	     attr == &sensor_dev_attr_power1_cap_min.dev_attr.attr ||
-	     attr == &sensor_dev_attr_power1_cap.dev_attr.attr ||
-	     attr == &sensor_dev_attr_power1_cap_default.dev_attr.attr))
-		return 0;
+	if (attr == &sensor_dev_attr_power1_cap_max.dev_attr.attr ||
+	    attr == &sensor_dev_attr_power1_cap_min.dev_attr.attr ||
+	    attr == &sensor_dev_attr_power1_cap.dev_attr.attr ||
+	    attr == &sensor_dev_attr_power1_cap_default.dev_attr.attr) {
+		if (adev->family == AMDGPU_FAMILY_SI ||
+		    ((adev->flags & AMD_IS_APU) && gc_ver != IP_VERSION(10, 3, 1) &&
+		     (gc_ver != IP_VERSION(9, 4, 3) && gc_ver != IP_VERSION(9, 4, 4))) ||
+		    (amdgpu_sriov_vf(adev) && gc_ver == IP_VERSION(11, 0, 3)))
+			return 0;
+	}
 
 	/* not implemented yet for APUs having < GC 9.3.0 (Renoir) */
 	if (((adev->family == AMDGPU_FAMILY_SI) ||
diff --git a/drivers/gpu/drm/drm_gpuvm.c b/drivers/gpu/drm/drm_gpuvm.c
index 74d9499..db9b089 100644
--- a/drivers/gpu/drm/drm_gpuvm.c
+++ b/drivers/gpu/drm/drm_gpuvm.c
@@ -40,7 +40,7 @@
  * mapping's backing &drm_gem_object buffers.
  *
  * &drm_gem_object buffers maintain a list of &drm_gpuva objects representing
- * all existent GPU VA mappings using this &drm_gem_object as backing buffer.
+ * all existing GPU VA mappings using this &drm_gem_object as backing buffer.
  *
  * GPU VAs can be flagged as sparse, such that drivers may use GPU VAs to also
  * keep track of sparse PTEs in order to support Vulkan 'Sparse Resources'.
@@ -72,7 +72,7 @@
  * but it can also be a 'dummy' object, which can be allocated with
  * drm_gpuvm_resv_object_alloc().
  *
- * In order to connect a struct drm_gpuva its backing &drm_gem_object each
+ * In order to connect a struct drm_gpuva to its backing &drm_gem_object each
  * &drm_gem_object maintains a list of &drm_gpuvm_bo structures, and each
  * &drm_gpuvm_bo contains a list of &drm_gpuva structures.
  *
@@ -81,7 +81,7 @@
  * This is ensured by the API through drm_gpuvm_bo_obtain() and
  * drm_gpuvm_bo_obtain_prealloc() which first look into the corresponding
  * &drm_gem_object list of &drm_gpuvm_bos for an existing instance of this
- * particular combination. If not existent a new instance is created and linked
+ * particular combination. If not present, a new instance is created and linked
  * to the &drm_gem_object.
  *
  * &drm_gpuvm_bo structures, since unique for a given &drm_gpuvm, are also used
@@ -108,7 +108,7 @@
  * sequence of operations to satisfy a given map or unmap request.
  *
  * Therefore the DRM GPU VA manager provides an algorithm implementing splitting
- * and merging of existent GPU VA mappings with the ones that are requested to
+ * and merging of existing GPU VA mappings with the ones that are requested to
  * be mapped or unmapped. This feature is required by the Vulkan API to
  * implement Vulkan 'Sparse Memory Bindings' - drivers UAPIs often refer to this
  * as VM BIND.
@@ -119,7 +119,7 @@
  * execute in order to integrate the new mapping cleanly into the current state
  * of the GPU VA space.
  *
- * Depending on how the new GPU VA mapping intersects with the existent mappings
+ * Depending on how the new GPU VA mapping intersects with the existing mappings
  * of the GPU VA space the &drm_gpuvm_ops callbacks contain an arbitrary amount
  * of unmap operations, a maximum of two remap operations and a single map
  * operation. The caller might receive no callback at all if no operation is
@@ -139,16 +139,16 @@
  * one unmap operation and one or two map operations, such that drivers can
  * derive the page table update delta accordingly.
  *
- * Note that there can't be more than two existent mappings to split up, one at
+ * Note that there can't be more than two existing mappings to split up, one at
  * the beginning and one at the end of the new mapping, hence there is a
  * maximum of two remap operations.
  *
  * Analogous to drm_gpuvm_sm_map() drm_gpuvm_sm_unmap() uses &drm_gpuvm_ops to
  * call back into the driver in order to unmap a range of GPU VA space. The
- * logic behind this function is way simpler though: For all existent mappings
+ * logic behind this function is way simpler though: For all existing mappings
  * enclosed by the given range unmap operations are created. For mappings which
- * are only partically located within the given range, remap operations are
- * created such that those mappings are split up and re-mapped partically.
+ * are only partially located within the given range, remap operations are
+ * created such that those mappings are split up and re-mapped partially.
  *
  * As an alternative to drm_gpuvm_sm_map() and drm_gpuvm_sm_unmap(),
  * drm_gpuvm_sm_map_ops_create() and drm_gpuvm_sm_unmap_ops_create() can be used
@@ -168,7 +168,7 @@
  * provided helper functions drm_gpuva_map(), drm_gpuva_remap() and
  * drm_gpuva_unmap() instead.
  *
- * The following diagram depicts the basic relationships of existent GPU VA
+ * The following diagram depicts the basic relationships of existing GPU VA
  * mappings, a newly requested mapping and the resulting mappings as implemented
  * by drm_gpuvm_sm_map() - it doesn't cover any arbitrary combinations of these.
  *
@@ -218,7 +218,7 @@
  *
  *
  * 4) Existent mapping is a left aligned subset of the requested one, hence
- *    replace the existent one.
+ *    replace the existing one.
  *
  *    ::
  *
@@ -236,9 +236,9 @@
  *       and/or non-contiguous BO offset.
  *
  *
- * 5) Requested mapping's range is a left aligned subset of the existent one,
+ * 5) Requested mapping's range is a left aligned subset of the existing one,
  *    but backed by a different BO. Hence, map the requested mapping and split
- *    the existent one adjusting its BO offset.
+ *    the existing one adjusting its BO offset.
  *
  *    ::
  *
@@ -271,9 +271,9 @@
  *	new: |-----|-----| (a.bo_offset=n, a'.bo_offset=n+1)
  *
  *
- * 7) Requested mapping's range is a right aligned subset of the existent one,
+ * 7) Requested mapping's range is a right aligned subset of the existing one,
  *    but backed by a different BO. Hence, map the requested mapping and split
- *    the existent one, without adjusting the BO offset.
+ *    the existing one, without adjusting the BO offset.
  *
  *    ::
  *
@@ -304,7 +304,7 @@
  *
  * 9) Existent mapping is overlapped at the end by the requested mapping backed
  *    by a different BO. Hence, map the requested mapping and split up the
- *    existent one, without adjusting the BO offset.
+ *    existing one, without adjusting the BO offset.
  *
  *    ::
  *
@@ -334,9 +334,9 @@
  *	 new: |-----|-----------| (a'.bo_offset=n, a.bo_offset=n+1)
  *
  *
- * 11) Requested mapping's range is a centered subset of the existent one
+ * 11) Requested mapping's range is a centered subset of the existing one
  *     having a different backing BO. Hence, map the requested mapping and split
- *     up the existent one in two mappings, adjusting the BO offset of the right
+ *     up the existing one in two mappings, adjusting the BO offset of the right
  *     one accordingly.
  *
  *     ::
@@ -351,7 +351,7 @@
  *	 new: |-----|-----|-----| (a.bo_offset=n,b.bo_offset=m,a'.bo_offset=n+2)
  *
  *
- * 12) Requested mapping is a contiguous subset of the existent one. Split it
+ * 12) Requested mapping is a contiguous subset of the existing one. Split it
  *     up, but indicate that the backing PTEs could be kept.
  *
  *     ::
@@ -367,7 +367,7 @@
  *
  *
  * 13) Existent mapping is a right aligned subset of the requested one, hence
- *     replace the existent one.
+ *     replace the existing one.
  *
  *     ::
  *
@@ -386,7 +386,7 @@
  *
  *
  * 14) Existent mapping is a centered subset of the requested one, hence
- *     replace the existent one.
+ *     replace the existing one.
  *
  *     ::
  *
@@ -406,7 +406,7 @@
  *
  * 15) Existent mappings is overlapped at the beginning by the requested mapping
  *     backed by a different BO. Hence, map the requested mapping and split up
- *     the existent one, adjusting its BO offset accordingly.
+ *     the existing one, adjusting its BO offset accordingly.
  *
  *     ::
  *
@@ -469,8 +469,8 @@
  * make use of them.
  *
  * The below code is strictly limited to illustrate the generic usage pattern.
- * To maintain simplicitly, it doesn't make use of any abstractions for common
- * code, different (asyncronous) stages with fence signalling critical paths,
+ * To maintain simplicity, it doesn't make use of any abstractions for common
+ * code, different (asynchronous) stages with fence signalling critical paths,
  * any other helpers or error handling in terms of freeing memory and dropping
  * previously taken locks.
  *
@@ -479,7 +479,7 @@
  *	// Allocates a new &drm_gpuva.
  *	struct drm_gpuva * driver_gpuva_alloc(void);
  *
- *	// Typically drivers would embedd the &drm_gpuvm and &drm_gpuva
+ *	// Typically drivers would embed the &drm_gpuvm and &drm_gpuva
  *	// structure in individual driver structures and lock the dma-resv with
  *	// drm_exec or similar helpers.
  *	int driver_mapping_create(struct drm_gpuvm *gpuvm,
@@ -582,7 +582,7 @@
  *		.sm_step_unmap = driver_gpuva_unmap,
  *	};
  *
- *	// Typically drivers would embedd the &drm_gpuvm and &drm_gpuva
+ *	// Typically drivers would embed the &drm_gpuvm and &drm_gpuva
  *	// structure in individual driver structures and lock the dma-resv with
  *	// drm_exec or similar helpers.
  *	int driver_mapping_create(struct drm_gpuvm *gpuvm,
@@ -680,7 +680,7 @@
  *
  * This helper is here to provide lockless list iteration. Lockless as in, the
  * iterator releases the lock immediately after picking the first element from
- * the list, so list insertion deletion can happen concurrently.
+ * the list, so list insertion and deletion can happen concurrently.
  *
  * Elements popped from the original list are kept in a local list, so removal
  * and is_empty checks can still happen while we're iterating the list.
@@ -1160,7 +1160,7 @@ drm_gpuvm_prepare_objects_locked(struct drm_gpuvm *gpuvm,
 }
 
 /**
- * drm_gpuvm_prepare_objects() - prepare all assoiciated BOs
+ * drm_gpuvm_prepare_objects() - prepare all associated BOs
  * @gpuvm: the &drm_gpuvm
  * @exec: the &drm_exec locking context
  * @num_fences: the amount of &dma_fences to reserve
@@ -1230,13 +1230,13 @@ drm_gpuvm_prepare_range(struct drm_gpuvm *gpuvm, struct drm_exec *exec,
 EXPORT_SYMBOL_GPL(drm_gpuvm_prepare_range);
 
 /**
- * drm_gpuvm_exec_lock() - lock all dma-resv of all assoiciated BOs
+ * drm_gpuvm_exec_lock() - lock all dma-resv of all associated BOs
  * @vm_exec: the &drm_gpuvm_exec wrapper
  *
  * Acquires all dma-resv locks of all &drm_gem_objects the given
  * &drm_gpuvm contains mappings of.
  *
- * Addionally, when calling this function with struct drm_gpuvm_exec::extra
+ * Additionally, when calling this function with struct drm_gpuvm_exec::extra
  * being set the driver receives the given @fn callback to lock additional
  * dma-resv in the context of the &drm_gpuvm_exec instance. Typically, drivers
  * would call drm_exec_prepare_obj() from within this callback.
@@ -1293,7 +1293,7 @@ fn_lock_array(struct drm_gpuvm_exec *vm_exec)
 }
 
 /**
- * drm_gpuvm_exec_lock_array() - lock all dma-resv of all assoiciated BOs
+ * drm_gpuvm_exec_lock_array() - lock all dma-resv of all associated BOs
  * @vm_exec: the &drm_gpuvm_exec wrapper
  * @objs: additional &drm_gem_objects to lock
  * @num_objs: the number of additional &drm_gem_objects to lock
@@ -1588,7 +1588,7 @@ drm_gpuvm_bo_find(struct drm_gpuvm *gpuvm,
 EXPORT_SYMBOL_GPL(drm_gpuvm_bo_find);
 
 /**
- * drm_gpuvm_bo_obtain() - obtains and instance of the &drm_gpuvm_bo for the
+ * drm_gpuvm_bo_obtain() - obtains an instance of the &drm_gpuvm_bo for the
  * given &drm_gpuvm and &drm_gem_object
  * @gpuvm: The &drm_gpuvm the @obj is mapped in.
  * @obj: The &drm_gem_object being mapped in the @gpuvm.
@@ -1624,7 +1624,7 @@ drm_gpuvm_bo_obtain(struct drm_gpuvm *gpuvm,
 EXPORT_SYMBOL_GPL(drm_gpuvm_bo_obtain);
 
 /**
- * drm_gpuvm_bo_obtain_prealloc() - obtains and instance of the &drm_gpuvm_bo
+ * drm_gpuvm_bo_obtain_prealloc() - obtains an instance of the &drm_gpuvm_bo
  * for the given &drm_gpuvm and &drm_gem_object
  * @__vm_bo: A pre-allocated struct drm_gpuvm_bo.
  *
@@ -1688,7 +1688,7 @@ EXPORT_SYMBOL_GPL(drm_gpuvm_bo_extobj_add);
  * @vm_bo: the &drm_gpuvm_bo to add or remove
  * @evict: indicates whether the object is evicted
  *
- * Adds a &drm_gpuvm_bo to or removes it from the &drm_gpuvms evicted list.
+ * Adds a &drm_gpuvm_bo to or removes it from the &drm_gpuvm's evicted list.
  */
 void
 drm_gpuvm_bo_evict(struct drm_gpuvm_bo *vm_bo, bool evict)
@@ -1790,7 +1790,7 @@ __drm_gpuva_remove(struct drm_gpuva *va)
  * drm_gpuva_remove() - remove a &drm_gpuva
  * @va: the &drm_gpuva to remove
  *
- * This removes the given &va from the underlaying tree.
+ * This removes the given &va from the underlying tree.
  *
  * It is safe to use this function using the safe versions of iterating the GPU
  * VA space, such as drm_gpuvm_for_each_va_safe() and
@@ -2358,7 +2358,7 @@ EXPORT_SYMBOL_GPL(drm_gpuvm_sm_map);
  *
  * This function iterates the given range of the GPU VA space. It utilizes the
  * &drm_gpuvm_ops to call back into the driver providing the operations to
- * unmap and, if required, split existent mappings.
+ * unmap and, if required, split existing mappings.
  *
  * Drivers may use these callbacks to update the GPU VA space right away within
  * the callback. In case the driver decides to copy and store the operations for
@@ -2430,7 +2430,7 @@ static const struct drm_gpuvm_ops lock_ops = {
  * remapped, and locks+prepares (drm_exec_prepare_object()) objects that
  * will be newly mapped.
  *
- * The expected usage is:
+ * The expected usage is::
  *
  * .. code-block:: c
  *
@@ -2475,7 +2475,7 @@ static const struct drm_gpuvm_ops lock_ops = {
  *    required without the earlier DRIVER_OP_MAP.  This is safe because we've
  *    already locked the GEM object in the earlier DRIVER_OP_MAP step.
  *
- * Returns: 0 on success or a negative error codec
+ * Returns: 0 on success or a negative error code
  */
 int
 drm_gpuvm_sm_map_exec_lock(struct drm_gpuvm *gpuvm,
@@ -2619,12 +2619,12 @@ static const struct drm_gpuvm_ops gpuvm_list_ops = {
  * @req_offset: the offset within the &drm_gem_object
  *
  * This function creates a list of operations to perform splitting and merging
- * of existent mapping(s) with the newly requested one.
+ * of existing mapping(s) with the newly requested one.
  *
  * The list can be iterated with &drm_gpuva_for_each_op and must be processed
  * in the given order. It can contain map, unmap and remap operations, but it
  * also can be empty if no operation is required, e.g. if the requested mapping
- * already exists is the exact same way.
+ * already exists in the exact same way.
  *
  * There can be an arbitrary amount of unmap operations, a maximum of two remap
  * operations and a single map operation. The latter one represents the original
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_drv.c b/drivers/gpu/drm/mediatek/mtk_drm_drv.c
index d5e6bab..f8a8176 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_drv.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_drv.c
@@ -387,19 +387,19 @@ static bool mtk_drm_get_all_drm_priv(struct device *dev)
 
 		of_id = of_match_node(mtk_drm_of_ids, node);
 		if (!of_id)
-			continue;
+			goto next_put_node;
 
 		pdev = of_find_device_by_node(node);
 		if (!pdev)
-			continue;
+			goto next_put_node;
 
 		drm_dev = device_find_child(&pdev->dev, NULL, mtk_drm_match);
 		if (!drm_dev)
-			continue;
+			goto next_put_device_pdev_dev;
 
 		temp_drm_priv = dev_get_drvdata(drm_dev);
 		if (!temp_drm_priv)
-			continue;
+			goto next_put_device_drm_dev;
 
 		if (temp_drm_priv->data->main_len)
 			all_drm_priv[CRTC_MAIN] = temp_drm_priv;
@@ -411,10 +411,17 @@ static bool mtk_drm_get_all_drm_priv(struct device *dev)
 		if (temp_drm_priv->mtk_drm_bound)
 			cnt++;
 
-		if (cnt == MAX_CRTC) {
-			of_node_put(node);
+next_put_device_drm_dev:
+		put_device(drm_dev);
+
+next_put_device_pdev_dev:
+		put_device(&pdev->dev);
+
+next_put_node:
+		of_node_put(node);
+
+		if (cnt == MAX_CRTC)
 			break;
-		}
 	}
 
 	if (drm_priv->data->mmsys_dev_num == cnt) {
diff --git a/drivers/gpu/drm/mediatek/mtk_dsi.c b/drivers/gpu/drm/mediatek/mtk_dsi.c
index d772609..0e2bcd5 100644
--- a/drivers/gpu/drm/mediatek/mtk_dsi.c
+++ b/drivers/gpu/drm/mediatek/mtk_dsi.c
@@ -1002,6 +1002,12 @@ static int mtk_dsi_host_attach(struct mipi_dsi_host *host,
 			return PTR_ERR(dsi->next_bridge);
 	}
 
+	/*
+	 * set flag to request the DSI host bridge be pre-enabled before device bridge
+	 * in the chain, so the DSI host is ready when the device bridge is pre-enabled
+	 */
+	dsi->next_bridge->pre_enable_prev_first = true;
+
 	drm_bridge_add(&dsi->bridge);
 
 	ret = component_add(host->dev, &mtk_dsi_component_ops);
diff --git a/drivers/gpu/drm/mediatek/mtk_hdmi.c b/drivers/gpu/drm/mediatek/mtk_hdmi.c
index 845fd8a..b766dd5 100644
--- a/drivers/gpu/drm/mediatek/mtk_hdmi.c
+++ b/drivers/gpu/drm/mediatek/mtk_hdmi.c
@@ -182,8 +182,8 @@ static inline struct mtk_hdmi *hdmi_ctx_from_bridge(struct drm_bridge *b)
 
 static void mtk_hdmi_hw_vid_black(struct mtk_hdmi *hdmi, bool black)
 {
-	regmap_update_bits(hdmi->regs, VIDEO_SOURCE_SEL,
-			   VIDEO_CFG_4, black ? GEN_RGB : NORMAL_PATH);
+	regmap_update_bits(hdmi->regs, VIDEO_CFG_4,
+			   VIDEO_SOURCE_SEL, black ? GEN_RGB : NORMAL_PATH);
 }
 
 static void mtk_hdmi_hw_make_reg_writable(struct mtk_hdmi *hdmi, bool enable)
@@ -310,8 +310,8 @@ static void mtk_hdmi_hw_send_info_frame(struct mtk_hdmi *hdmi, u8 *buffer,
 
 static void mtk_hdmi_hw_send_aud_packet(struct mtk_hdmi *hdmi, bool enable)
 {
-	regmap_update_bits(hdmi->regs, AUDIO_PACKET_OFF,
-			   GRL_SHIFT_R2, enable ? 0 : AUDIO_PACKET_OFF);
+	regmap_update_bits(hdmi->regs, GRL_SHIFT_R2,
+			   AUDIO_PACKET_OFF, enable ? 0 : AUDIO_PACKET_OFF);
 }
 
 static void mtk_hdmi_hw_config_sys(struct mtk_hdmi *hdmi)
diff --git a/drivers/gpu/drm/mediatek/mtk_plane.c b/drivers/gpu/drm/mediatek/mtk_plane.c
index cbc4f37..02349bd 100644
--- a/drivers/gpu/drm/mediatek/mtk_plane.c
+++ b/drivers/gpu/drm/mediatek/mtk_plane.c
@@ -292,7 +292,8 @@ static void mtk_plane_atomic_disable(struct drm_plane *plane,
 	wmb(); /* Make sure the above parameter is set before update */
 	mtk_plane_state->pending.dirty = true;
 
-	mtk_crtc_plane_disable(old_state->crtc, plane);
+	if (old_state && old_state->crtc)
+		mtk_crtc_plane_disable(old_state->crtc, plane);
 }
 
 static void mtk_plane_atomic_update(struct drm_plane *plane,
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c
index faca2a0..d5d1271 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c
@@ -11,7 +11,7 @@
 static const unsigned int *gen7_0_0_external_core_regs[] __always_unused;
 static const unsigned int *gen7_2_0_external_core_regs[] __always_unused;
 static const unsigned int *gen7_9_0_external_core_regs[] __always_unused;
-static struct gen7_sptp_cluster_registers gen7_9_0_sptp_clusters[] __always_unused;
+static const struct gen7_sptp_cluster_registers gen7_9_0_sptp_clusters[] __always_unused;
 static const u32 gen7_9_0_cx_debugbus_blocks[] __always_unused;
 
 #include "adreno_gen7_0_0_snapshot.h"
@@ -174,8 +174,15 @@ static int a6xx_crashdumper_run(struct msm_gpu *gpu,
 static int debugbus_read(struct msm_gpu *gpu, u32 block, u32 offset,
 		u32 *data)
 {
-	u32 reg = A6XX_DBGC_CFG_DBGBUS_SEL_D_PING_INDEX(offset) |
-		A6XX_DBGC_CFG_DBGBUS_SEL_D_PING_BLK_SEL(block);
+	u32 reg;
+
+	if (to_adreno_gpu(gpu)->info->family >= ADRENO_7XX_GEN1) {
+		reg = A7XX_DBGC_CFG_DBGBUS_SEL_D_PING_INDEX(offset) |
+			A7XX_DBGC_CFG_DBGBUS_SEL_D_PING_BLK_SEL(block);
+	} else {
+		reg = A6XX_DBGC_CFG_DBGBUS_SEL_D_PING_INDEX(offset) |
+			A6XX_DBGC_CFG_DBGBUS_SEL_D_PING_BLK_SEL(block);
+	}
 
 	gpu_write(gpu, REG_A6XX_DBGC_CFG_DBGBUS_SEL_A, reg);
 	gpu_write(gpu, REG_A6XX_DBGC_CFG_DBGBUS_SEL_B, reg);
@@ -198,11 +205,18 @@ static int debugbus_read(struct msm_gpu *gpu, u32 block, u32 offset,
 	readl((ptr) + ((offset) << 2))
 
 /* read a value from the CX debug bus */
-static int cx_debugbus_read(void __iomem *cxdbg, u32 block, u32 offset,
+static int cx_debugbus_read(struct msm_gpu *gpu, void __iomem *cxdbg, u32 block, u32 offset,
 		u32 *data)
 {
-	u32 reg = A6XX_CX_DBGC_CFG_DBGBUS_SEL_A_PING_INDEX(offset) |
-		A6XX_CX_DBGC_CFG_DBGBUS_SEL_A_PING_BLK_SEL(block);
+	u32 reg;
+
+	if (to_adreno_gpu(gpu)->info->family >= ADRENO_7XX_GEN1) {
+		reg = A7XX_CX_DBGC_CFG_DBGBUS_SEL_A_PING_INDEX(offset) |
+			A7XX_CX_DBGC_CFG_DBGBUS_SEL_A_PING_BLK_SEL(block);
+	} else {
+		reg = A6XX_CX_DBGC_CFG_DBGBUS_SEL_A_PING_INDEX(offset) |
+			A6XX_CX_DBGC_CFG_DBGBUS_SEL_A_PING_BLK_SEL(block);
+	}
 
 	cxdbg_write(cxdbg, REG_A6XX_CX_DBGC_CFG_DBGBUS_SEL_A, reg);
 	cxdbg_write(cxdbg, REG_A6XX_CX_DBGC_CFG_DBGBUS_SEL_B, reg);
@@ -315,7 +329,8 @@ static void a6xx_get_debugbus_block(struct msm_gpu *gpu,
 		ptr += debugbus_read(gpu, block->id, i, ptr);
 }
 
-static void a6xx_get_cx_debugbus_block(void __iomem *cxdbg,
+static void a6xx_get_cx_debugbus_block(struct msm_gpu *gpu,
+		void __iomem *cxdbg,
 		struct a6xx_gpu_state *a6xx_state,
 		const struct a6xx_debugbus_block *block,
 		struct a6xx_gpu_state_obj *obj)
@@ -330,7 +345,7 @@ static void a6xx_get_cx_debugbus_block(void __iomem *cxdbg,
 	obj->handle = block;
 
 	for (ptr = obj->data, i = 0; i < block->count; i++)
-		ptr += cx_debugbus_read(cxdbg, block->id, i, ptr);
+		ptr += cx_debugbus_read(gpu, cxdbg, block->id, i, ptr);
 }
 
 static void a6xx_get_debugbus_blocks(struct msm_gpu *gpu,
@@ -423,8 +438,9 @@ static void a7xx_get_debugbus_blocks(struct msm_gpu *gpu,
 				a6xx_state, &a7xx_debugbus_blocks[gbif_debugbus_blocks[i]],
 				&a6xx_state->debugbus[i + debugbus_blocks_count]);
 		}
-	}
 
+		a6xx_state->nr_debugbus = total_debugbus_blocks;
+	}
 }
 
 static void a6xx_get_debugbus(struct msm_gpu *gpu,
@@ -526,7 +542,8 @@ static void a6xx_get_debugbus(struct msm_gpu *gpu,
 			int i;
 
 			for (i = 0; i < nr_cx_debugbus_blocks; i++)
-				a6xx_get_cx_debugbus_block(cxdbg,
+				a6xx_get_cx_debugbus_block(gpu,
+					cxdbg,
 					a6xx_state,
 					&cx_debugbus_blocks[i],
 					&a6xx_state->cx_debugbus[i]);
@@ -759,15 +776,15 @@ static void a7xx_get_cluster(struct msm_gpu *gpu,
 	size_t datasize;
 	int i, regcount = 0;
 
-	/* Some clusters need a selector register to be programmed too */
-	if (cluster->sel)
-		in += CRASHDUMP_WRITE(in, cluster->sel->cd_reg, cluster->sel->val);
-
 	in += CRASHDUMP_WRITE(in, REG_A7XX_CP_APERTURE_CNTL_CD,
 		A7XX_CP_APERTURE_CNTL_CD_PIPE(cluster->pipe_id) |
 		A7XX_CP_APERTURE_CNTL_CD_CLUSTER(cluster->cluster_id) |
 		A7XX_CP_APERTURE_CNTL_CD_CONTEXT(cluster->context_id));
 
+	/* Some clusters need a selector register to be programmed too */
+	if (cluster->sel)
+		in += CRASHDUMP_WRITE(in, cluster->sel->cd_reg, cluster->sel->val);
+
 	for (i = 0; cluster->regs[i] != UINT_MAX; i += 2) {
 		int count = RANGE(cluster->regs, i);
 
@@ -1796,6 +1813,7 @@ static void a7xx_show_shader(struct a6xx_gpu_state_obj *obj,
 
 	print_name(p, "  - type: ", a7xx_statetype_names[block->statetype]);
 	print_name(p, "    - pipe: ", a7xx_pipe_names[block->pipeid]);
+	drm_printf(p, "    - location: %d\n", block->location);
 
 	for (i = 0; i < block->num_sps; i++) {
 		drm_printf(p, "      - sp: %d\n", i);
@@ -1873,6 +1891,7 @@ static void a7xx_show_dbgahb_cluster(struct a6xx_gpu_state_obj *obj,
 		print_name(p, "  - pipe: ", a7xx_pipe_names[dbgahb->pipe_id]);
 		print_name(p, "    - cluster-name: ", a7xx_cluster_names[dbgahb->cluster_id]);
 		drm_printf(p, "      - context: %d\n", dbgahb->context_id);
+		drm_printf(p, "      - location: %d\n", dbgahb->location_id);
 		a7xx_show_registers_indented(dbgahb->regs, obj->data, p, 4);
 	}
 }
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h
index 95d93ac..1c18499 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h
@@ -419,47 +419,47 @@ static const struct a6xx_indexed_registers a6xx_indexed_reglist[] = {
 		REG_A6XX_CP_SQE_STAT_DATA, 0x33, NULL },
 	{ "CP_DRAW_STATE", REG_A6XX_CP_DRAW_STATE_ADDR,
 		REG_A6XX_CP_DRAW_STATE_DATA, 0x100, NULL },
-	{ "CP_UCODE_DBG_DATA", REG_A6XX_CP_SQE_UCODE_DBG_ADDR,
+	{ "CP_SQE_UCODE_DBG", REG_A6XX_CP_SQE_UCODE_DBG_ADDR,
 		REG_A6XX_CP_SQE_UCODE_DBG_DATA, 0x8000, NULL },
-	{ "CP_ROQ", REG_A6XX_CP_ROQ_DBG_ADDR,
+	{ "CP_ROQ_DBG", REG_A6XX_CP_ROQ_DBG_ADDR,
 		REG_A6XX_CP_ROQ_DBG_DATA, 0, a6xx_get_cp_roq_size},
 };
 
 static const struct a6xx_indexed_registers a7xx_indexed_reglist[] = {
 	{ "CP_SQE_STAT", REG_A6XX_CP_SQE_STAT_ADDR,
-		REG_A6XX_CP_SQE_STAT_DATA, 0x33, NULL },
+		REG_A6XX_CP_SQE_STAT_DATA, 0x40, NULL },
 	{ "CP_DRAW_STATE", REG_A6XX_CP_DRAW_STATE_ADDR,
 		REG_A6XX_CP_DRAW_STATE_DATA, 0x100, NULL },
-	{ "CP_UCODE_DBG_DATA", REG_A6XX_CP_SQE_UCODE_DBG_ADDR,
+	{ "CP_SQE_UCODE_DBG", REG_A6XX_CP_SQE_UCODE_DBG_ADDR,
 		REG_A6XX_CP_SQE_UCODE_DBG_DATA, 0x8000, NULL },
-	{ "CP_BV_SQE_STAT_ADDR", REG_A7XX_CP_BV_SQE_STAT_ADDR,
-		REG_A7XX_CP_BV_SQE_STAT_DATA, 0x33, NULL },
-	{ "CP_BV_DRAW_STATE_ADDR", REG_A7XX_CP_BV_DRAW_STATE_ADDR,
+	{ "CP_BV_SQE_STAT", REG_A7XX_CP_BV_SQE_STAT_ADDR,
+		REG_A7XX_CP_BV_SQE_STAT_DATA, 0x40, NULL },
+	{ "CP_BV_DRAW_STATE", REG_A7XX_CP_BV_DRAW_STATE_ADDR,
 		REG_A7XX_CP_BV_DRAW_STATE_DATA, 0x100, NULL },
-	{ "CP_BV_SQE_UCODE_DBG_ADDR", REG_A7XX_CP_BV_SQE_UCODE_DBG_ADDR,
+	{ "CP_BV_SQE_UCODE_DBG", REG_A7XX_CP_BV_SQE_UCODE_DBG_ADDR,
 		REG_A7XX_CP_BV_SQE_UCODE_DBG_DATA, 0x8000, NULL },
-	{ "CP_SQE_AC_STAT_ADDR", REG_A7XX_CP_SQE_AC_STAT_ADDR,
-		REG_A7XX_CP_SQE_AC_STAT_DATA, 0x33, NULL },
-	{ "CP_LPAC_DRAW_STATE_ADDR", REG_A7XX_CP_LPAC_DRAW_STATE_ADDR,
+	{ "CP_SQE_AC_STAT", REG_A7XX_CP_SQE_AC_STAT_ADDR,
+		REG_A7XX_CP_SQE_AC_STAT_DATA, 0x40, NULL },
+	{ "CP_LPAC_DRAW_STATE", REG_A7XX_CP_LPAC_DRAW_STATE_ADDR,
 		REG_A7XX_CP_LPAC_DRAW_STATE_DATA, 0x100, NULL },
-	{ "CP_SQE_AC_UCODE_DBG_ADDR", REG_A7XX_CP_SQE_AC_UCODE_DBG_ADDR,
+	{ "CP_SQE_AC_UCODE_DBG", REG_A7XX_CP_SQE_AC_UCODE_DBG_ADDR,
 		REG_A7XX_CP_SQE_AC_UCODE_DBG_DATA, 0x8000, NULL },
-	{ "CP_LPAC_FIFO_DBG_ADDR", REG_A7XX_CP_LPAC_FIFO_DBG_ADDR,
+	{ "CP_LPAC_FIFO_DBG", REG_A7XX_CP_LPAC_FIFO_DBG_ADDR,
 		REG_A7XX_CP_LPAC_FIFO_DBG_DATA, 0x40, NULL },
-	{ "CP_ROQ", REG_A6XX_CP_ROQ_DBG_ADDR,
+	{ "CP_ROQ_DBG", REG_A6XX_CP_ROQ_DBG_ADDR,
 		REG_A6XX_CP_ROQ_DBG_DATA, 0, a7xx_get_cp_roq_size },
 };
 
 static const struct a6xx_indexed_registers a6xx_cp_mempool_indexed = {
-	"CP_MEMPOOL", REG_A6XX_CP_MEM_POOL_DBG_ADDR,
+	"CP_MEM_POOL_DBG", REG_A6XX_CP_MEM_POOL_DBG_ADDR,
 		REG_A6XX_CP_MEM_POOL_DBG_DATA, 0x2060, NULL,
 };
 
 static const struct a6xx_indexed_registers a7xx_cp_bv_mempool_indexed[] = {
-	{ "CP_MEMPOOL", REG_A6XX_CP_MEM_POOL_DBG_ADDR,
-		REG_A6XX_CP_MEM_POOL_DBG_DATA, 0x2100, NULL },
-	{ "CP_BV_MEMPOOL", REG_A7XX_CP_BV_MEM_POOL_DBG_ADDR,
-		REG_A7XX_CP_BV_MEM_POOL_DBG_DATA, 0x2100, NULL },
+	{ "CP_MEM_POOL_DBG", REG_A6XX_CP_MEM_POOL_DBG_ADDR,
+		REG_A6XX_CP_MEM_POOL_DBG_DATA, 0x2200, NULL },
+	{ "CP_BV_MEM_POOL_DBG", REG_A7XX_CP_BV_MEM_POOL_DBG_ADDR,
+		REG_A7XX_CP_BV_MEM_POOL_DBG_DATA, 0x2200, NULL },
 };
 
 #define DEBUGBUS(_id, _count) { .id = _id, .name = #_id, .count = _count }
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gen7_0_0_snapshot.h b/drivers/gpu/drm/msm/adreno/adreno_gen7_0_0_snapshot.h
index cb66ece..04b49d3 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gen7_0_0_snapshot.h
+++ b/drivers/gpu/drm/msm/adreno/adreno_gen7_0_0_snapshot.h
@@ -81,7 +81,7 @@ static const u32 gen7_0_0_debugbus_blocks[] = {
 	A7XX_DBGBUS_USPTP_7,
 };
 
-static struct gen7_shader_block gen7_0_0_shader_blocks[] = {
+static const struct gen7_shader_block gen7_0_0_shader_blocks[] = {
 	{A7XX_TP0_TMO_DATA,                 0x200, 4, 2, A7XX_PIPE_BR, A7XX_USPTP},
 	{A7XX_TP0_SMO_DATA,                  0x80, 4, 2, A7XX_PIPE_BR, A7XX_USPTP},
 	{A7XX_TP0_MIPMAP_BASE_DATA,         0x3c0, 4, 2, A7XX_PIPE_BR, A7XX_USPTP},
@@ -668,12 +668,19 @@ static const u32 gen7_0_0_sp_noncontext_pipe_lpac_usptp_registers[] = {
 };
 static_assert(IS_ALIGNED(sizeof(gen7_0_0_sp_noncontext_pipe_lpac_usptp_registers), 8));
 
-/* Block: TPl1 Cluster: noncontext Pipeline: A7XX_PIPE_BR */
-static const u32 gen7_0_0_tpl1_noncontext_pipe_br_registers[] = {
+/* Block: TPl1 Cluster: noncontext Pipeline: A7XX_PIPE_NONE */
+static const u32 gen7_0_0_tpl1_noncontext_pipe_none_registers[] = {
 	0x0b600, 0x0b600, 0x0b602, 0x0b602, 0x0b604, 0x0b604, 0x0b608, 0x0b60c,
 	0x0b60f, 0x0b621, 0x0b630, 0x0b633,
 	UINT_MAX, UINT_MAX,
 };
+static_assert(IS_ALIGNED(sizeof(gen7_0_0_tpl1_noncontext_pipe_none_registers), 8));
+
+/* Block: TPl1 Cluster: noncontext Pipeline: A7XX_PIPE_BR */
+static const u32 gen7_0_0_tpl1_noncontext_pipe_br_registers[] = {
+	 0x0b600, 0x0b600,
+	 UINT_MAX, UINT_MAX,
+};
 static_assert(IS_ALIGNED(sizeof(gen7_0_0_tpl1_noncontext_pipe_br_registers), 8));
 
 /* Block: TPl1 Cluster: noncontext Pipeline: A7XX_PIPE_LPAC */
@@ -695,7 +702,7 @@ static const struct gen7_sel_reg gen7_0_0_rb_rbp_sel = {
 	.val = 0x9,
 };
 
-static struct gen7_cluster_registers gen7_0_0_clusters[] = {
+static const struct gen7_cluster_registers gen7_0_0_clusters[] = {
 	{ A7XX_CLUSTER_NONE, A7XX_PIPE_BR, STATE_NON_CONTEXT,
 		gen7_0_0_noncontext_pipe_br_registers, },
 	{ A7XX_CLUSTER_NONE, A7XX_PIPE_BV, STATE_NON_CONTEXT,
@@ -764,7 +771,7 @@ static struct gen7_cluster_registers gen7_0_0_clusters[] = {
 		gen7_0_0_vpc_cluster_vpc_ps_pipe_bv_registers, },
 };
 
-static struct gen7_sptp_cluster_registers gen7_0_0_sptp_clusters[] = {
+static const struct gen7_sptp_cluster_registers gen7_0_0_sptp_clusters[] = {
 	{ A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, A7XX_PIPE_BR, 0, A7XX_HLSQ_STATE,
 		gen7_0_0_sp_noncontext_pipe_br_hlsq_state_registers, 0xae00 },
 	{ A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, A7XX_PIPE_BR, 0, A7XX_SP_TOP,
@@ -914,7 +921,7 @@ static const u32 gen7_0_0_dpm_registers[] = {
 };
 static_assert(IS_ALIGNED(sizeof(gen7_0_0_dpm_registers), 8));
 
-static struct gen7_reg_list gen7_0_0_reg_list[] = {
+static const struct gen7_reg_list gen7_0_0_reg_list[] = {
 	{ gen7_0_0_gpu_registers, NULL },
 	{ gen7_0_0_cx_misc_registers, NULL },
 	{ gen7_0_0_dpm_registers, NULL },
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gen7_2_0_snapshot.h b/drivers/gpu/drm/msm/adreno/adreno_gen7_2_0_snapshot.h
index 6f8ad50..772652e 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gen7_2_0_snapshot.h
+++ b/drivers/gpu/drm/msm/adreno/adreno_gen7_2_0_snapshot.h
@@ -95,7 +95,7 @@ static const u32 gen7_2_0_debugbus_blocks[] = {
 	A7XX_DBGBUS_CCHE_2,
 };
 
-static struct gen7_shader_block gen7_2_0_shader_blocks[] = {
+static const struct gen7_shader_block gen7_2_0_shader_blocks[] = {
 	{A7XX_TP0_TMO_DATA,                 0x200, 6, 2, A7XX_PIPE_BR, A7XX_USPTP},
 	{A7XX_TP0_SMO_DATA,                  0x80, 6, 2, A7XX_PIPE_BR, A7XX_USPTP},
 	{A7XX_TP0_MIPMAP_BASE_DATA,         0x3c0, 6, 2, A7XX_PIPE_BR, A7XX_USPTP},
@@ -489,7 +489,7 @@ static const struct gen7_sel_reg gen7_2_0_rb_rbp_sel = {
 	.val = 0x9,
 };
 
-static struct gen7_cluster_registers gen7_2_0_clusters[] = {
+static const struct gen7_cluster_registers gen7_2_0_clusters[] = {
 	{ A7XX_CLUSTER_NONE, A7XX_PIPE_BR, STATE_NON_CONTEXT,
 		gen7_2_0_noncontext_pipe_br_registers, },
 	{ A7XX_CLUSTER_NONE, A7XX_PIPE_BV, STATE_NON_CONTEXT,
@@ -558,7 +558,7 @@ static struct gen7_cluster_registers gen7_2_0_clusters[] = {
 		gen7_0_0_vpc_cluster_vpc_ps_pipe_bv_registers, },
 };
 
-static struct gen7_sptp_cluster_registers gen7_2_0_sptp_clusters[] = {
+static const struct gen7_sptp_cluster_registers gen7_2_0_sptp_clusters[] = {
 	{ A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, A7XX_PIPE_BR, 0, A7XX_HLSQ_STATE,
 		gen7_0_0_sp_noncontext_pipe_br_hlsq_state_registers, 0xae00 },
 	{ A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, A7XX_PIPE_BR, 0, A7XX_SP_TOP,
@@ -573,6 +573,8 @@ static struct gen7_sptp_cluster_registers gen7_2_0_sptp_clusters[] = {
 		gen7_0_0_sp_noncontext_pipe_lpac_usptp_registers, 0xaf80 },
 	{ A7XX_CLUSTER_NONE, A7XX_TP0_NCTX_REG, A7XX_PIPE_BR, 0, A7XX_USPTP,
 		gen7_0_0_tpl1_noncontext_pipe_br_registers, 0xb600 },
+	{ A7XX_CLUSTER_NONE, A7XX_TP0_NCTX_REG, A7XX_PIPE_NONE, 0, A7XX_USPTP,
+		gen7_0_0_tpl1_noncontext_pipe_none_registers, 0xb600 },
 	{ A7XX_CLUSTER_NONE, A7XX_TP0_NCTX_REG, A7XX_PIPE_LPAC, 0, A7XX_USPTP,
 		gen7_0_0_tpl1_noncontext_pipe_lpac_registers, 0xb780 },
 	{ A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, A7XX_PIPE_BR, 0, A7XX_HLSQ_STATE,
@@ -737,7 +739,7 @@ static const u32 gen7_2_0_dpm_registers[] = {
 };
 static_assert(IS_ALIGNED(sizeof(gen7_2_0_dpm_registers), 8));
 
-static struct gen7_reg_list gen7_2_0_reg_list[] = {
+static const struct gen7_reg_list gen7_2_0_reg_list[] = {
 	{ gen7_2_0_gpu_registers, NULL },
 	{ gen7_2_0_cx_misc_registers, NULL },
 	{ gen7_2_0_dpm_registers, NULL },
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gen7_9_0_snapshot.h b/drivers/gpu/drm/msm/adreno/adreno_gen7_9_0_snapshot.h
index e02cabb..0956dfc 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gen7_9_0_snapshot.h
+++ b/drivers/gpu/drm/msm/adreno/adreno_gen7_9_0_snapshot.h
@@ -117,7 +117,7 @@ static const u32 gen7_9_0_cx_debugbus_blocks[] = {
 	A7XX_DBGBUS_GBIF_CX,
 };
 
-static struct gen7_shader_block gen7_9_0_shader_blocks[] = {
+static const struct gen7_shader_block gen7_9_0_shader_blocks[] = {
 	{ A7XX_TP0_TMO_DATA, 0x0200, 6, 2, A7XX_PIPE_BR, A7XX_USPTP },
 	{ A7XX_TP0_SMO_DATA, 0x0080, 6, 2, A7XX_PIPE_BR, A7XX_USPTP },
 	{ A7XX_TP0_MIPMAP_BASE_DATA, 0x03C0, 6, 2, A7XX_PIPE_BR, A7XX_USPTP },
@@ -1116,7 +1116,7 @@ static const struct gen7_sel_reg gen7_9_0_rb_rbp_sel = {
 	.val = 0x9,
 };
 
-static struct gen7_cluster_registers gen7_9_0_clusters[] = {
+static const struct gen7_cluster_registers gen7_9_0_clusters[] = {
 	{ A7XX_CLUSTER_NONE, A7XX_PIPE_BR, STATE_NON_CONTEXT,
 		gen7_9_0_non_context_pipe_br_registers,  },
 	{ A7XX_CLUSTER_NONE, A7XX_PIPE_BV, STATE_NON_CONTEXT,
@@ -1185,7 +1185,7 @@ static struct gen7_cluster_registers gen7_9_0_clusters[] = {
 		gen7_9_0_vpc_pipe_bv_cluster_vpc_ps_registers,  },
 };
 
-static struct gen7_sptp_cluster_registers gen7_9_0_sptp_clusters[] = {
+static const struct gen7_sptp_cluster_registers gen7_9_0_sptp_clusters[] = {
 	{ A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, A7XX_PIPE_BR, 0, A7XX_HLSQ_STATE,
 		gen7_9_0_non_context_sp_pipe_br_hlsq_state_registers, 0xae00},
 	{ A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, A7XX_PIPE_BR, 0, A7XX_SP_TOP,
@@ -1294,34 +1294,34 @@ static struct gen7_sptp_cluster_registers gen7_9_0_sptp_clusters[] = {
 		gen7_9_0_tpl1_pipe_br_cluster_sp_ps_usptp_registers, 0xb000},
 };
 
-static struct a6xx_indexed_registers gen7_9_0_cp_indexed_reg_list[] = {
+static const struct a6xx_indexed_registers gen7_9_0_cp_indexed_reg_list[] = {
 	{ "CP_SQE_STAT", REG_A6XX_CP_SQE_STAT_ADDR,
 		REG_A6XX_CP_SQE_STAT_DATA, 0x00040},
 	{ "CP_DRAW_STATE", REG_A6XX_CP_DRAW_STATE_ADDR,
 		REG_A6XX_CP_DRAW_STATE_DATA, 0x00200},
-	{ "CP_ROQ", REG_A6XX_CP_ROQ_DBG_ADDR,
+	{ "CP_ROQ_DBG", REG_A6XX_CP_ROQ_DBG_ADDR,
 		REG_A6XX_CP_ROQ_DBG_DATA, 0x00800},
-	{ "CP_UCODE_DBG_DATA", REG_A6XX_CP_SQE_UCODE_DBG_ADDR,
+	{ "CP_SQE_UCODE_DBG", REG_A6XX_CP_SQE_UCODE_DBG_ADDR,
 		REG_A6XX_CP_SQE_UCODE_DBG_DATA, 0x08000},
-	{ "CP_BV_DRAW_STATE_ADDR", REG_A7XX_CP_BV_DRAW_STATE_ADDR,
+	{ "CP_BV_DRAW_STATE", REG_A7XX_CP_BV_DRAW_STATE_ADDR,
 		REG_A7XX_CP_BV_DRAW_STATE_DATA, 0x00200},
-	{ "CP_BV_ROQ_DBG_ADDR", REG_A7XX_CP_BV_ROQ_DBG_ADDR,
+	{ "CP_BV_ROQ_DBG", REG_A7XX_CP_BV_ROQ_DBG_ADDR,
 		REG_A7XX_CP_BV_ROQ_DBG_DATA, 0x00800},
-	{ "CP_BV_SQE_UCODE_DBG_ADDR", REG_A7XX_CP_BV_SQE_UCODE_DBG_ADDR,
+	{ "CP_BV_SQE_UCODE_DBG", REG_A7XX_CP_BV_SQE_UCODE_DBG_ADDR,
 		REG_A7XX_CP_BV_SQE_UCODE_DBG_DATA, 0x08000},
-	{ "CP_BV_SQE_STAT_ADDR", REG_A7XX_CP_BV_SQE_STAT_ADDR,
+	{ "CP_BV_SQE_STAT", REG_A7XX_CP_BV_SQE_STAT_ADDR,
 		REG_A7XX_CP_BV_SQE_STAT_DATA, 0x00040},
-	{ "CP_RESOURCE_TBL", REG_A7XX_CP_RESOURCE_TABLE_DBG_ADDR,
+	{ "CP_RESOURCE_TABLE_DBG", REG_A7XX_CP_RESOURCE_TABLE_DBG_ADDR,
 		REG_A7XX_CP_RESOURCE_TABLE_DBG_DATA, 0x04100},
-	{ "CP_LPAC_DRAW_STATE_ADDR", REG_A7XX_CP_LPAC_DRAW_STATE_ADDR,
+	{ "CP_LPAC_DRAW_STATE", REG_A7XX_CP_LPAC_DRAW_STATE_ADDR,
 		REG_A7XX_CP_LPAC_DRAW_STATE_DATA, 0x00200},
-	{ "CP_LPAC_ROQ", REG_A7XX_CP_LPAC_ROQ_DBG_ADDR,
+	{ "CP_LPAC_ROQ_DBG", REG_A7XX_CP_LPAC_ROQ_DBG_ADDR,
 		REG_A7XX_CP_LPAC_ROQ_DBG_DATA, 0x00200},
-	{ "CP_SQE_AC_UCODE_DBG_ADDR", REG_A7XX_CP_SQE_AC_UCODE_DBG_ADDR,
+	{ "CP_SQE_AC_UCODE_DBG", REG_A7XX_CP_SQE_AC_UCODE_DBG_ADDR,
 		REG_A7XX_CP_SQE_AC_UCODE_DBG_DATA, 0x08000},
-	{ "CP_SQE_AC_STAT_ADDR", REG_A7XX_CP_SQE_AC_STAT_ADDR,
+	{ "CP_SQE_AC_STAT", REG_A7XX_CP_SQE_AC_STAT_ADDR,
 		REG_A7XX_CP_SQE_AC_STAT_DATA, 0x00040},
-	{ "CP_LPAC_FIFO_DBG_ADDR", REG_A7XX_CP_LPAC_FIFO_DBG_ADDR,
+	{ "CP_LPAC_FIFO_DBG", REG_A7XX_CP_LPAC_FIFO_DBG_ADDR,
 		REG_A7XX_CP_LPAC_FIFO_DBG_DATA, 0x00040},
 	{ "CP_AQE_ROQ_0", REG_A7XX_CP_AQE_ROQ_DBG_ADDR_0,
 		REG_A7XX_CP_AQE_ROQ_DBG_DATA_0, 0x00100},
@@ -1337,7 +1337,7 @@ static struct a6xx_indexed_registers gen7_9_0_cp_indexed_reg_list[] = {
 		REG_A7XX_CP_AQE_STAT_DATA_1, 0x00040},
 };
 
-static struct gen7_reg_list gen7_9_0_reg_list[] = {
+static const struct gen7_reg_list gen7_9_0_reg_list[] = {
 	{ gen7_9_0_gpu_registers, NULL},
 	{ gen7_9_0_cx_misc_registers, NULL},
 	{ gen7_9_0_cx_dbgc_registers, NULL},
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c
index d4b5454..94912b4 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c
@@ -596,7 +596,7 @@ static void _dpu_crtc_complete_flip(struct drm_crtc *crtc)
 
 	spin_lock_irqsave(&dev->event_lock, flags);
 	if (dpu_crtc->event) {
-		DRM_DEBUG_VBL("%s: send event: %pK\n", dpu_crtc->name,
+		DRM_DEBUG_VBL("%s: send event: %p\n", dpu_crtc->name,
 			      dpu_crtc->event);
 		trace_dpu_crtc_complete_flip(DRMID(crtc));
 		drm_crtc_send_vblank_event(crtc, dpu_crtc->event);
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
index 05e5f34..258edaa 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
@@ -730,6 +730,8 @@ bool dpu_encoder_needs_modeset(struct drm_encoder *drm_enc, struct drm_atomic_st
 		return false;
 
 	conn_state = drm_atomic_get_new_connector_state(state, connector);
+	if (!conn_state)
+		return false;
 
 	/**
 	 * These checks are duplicated from dpu_encoder_update_topology() since
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dspp.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dspp.c
index 11fb1bc..54b20fa 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dspp.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dspp.c
@@ -31,14 +31,14 @@ static void dpu_setup_dspp_pcc(struct dpu_hw_dspp *ctx,
 	u32 base;
 
 	if (!ctx) {
-		DRM_ERROR("invalid ctx %pK\n", ctx);
+		DRM_ERROR("invalid ctx %p\n", ctx);
 		return;
 	}
 
 	base = ctx->cap->sblk->pcc.base;
 
 	if (!base) {
-		DRM_ERROR("invalid ctx %pK pcc base 0x%x\n", ctx, base);
+		DRM_ERROR("invalid ctx %p pcc base 0x%x\n", ctx, base);
 		return;
 	}
 
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c
index 12dcb32..a306077 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c
@@ -1345,7 +1345,7 @@ static int dpu_kms_mmap_mdp5(struct dpu_kms *dpu_kms)
 		dpu_kms->mmio = NULL;
 		return ret;
 	}
-	DRM_DEBUG("mapped dpu address space @%pK\n", dpu_kms->mmio);
+	DRM_DEBUG("mapped dpu address space @%p\n", dpu_kms->mmio);
 
 	dpu_kms->vbif[VBIF_RT] = msm_ioremap_mdss(mdss_dev,
 						  dpu_kms->pdev,
@@ -1380,7 +1380,7 @@ static int dpu_kms_mmap_dpu(struct dpu_kms *dpu_kms)
 		dpu_kms->mmio = NULL;
 		return ret;
 	}
-	DRM_DEBUG("mapped dpu address space @%pK\n", dpu_kms->mmio);
+	DRM_DEBUG("mapped dpu address space @%p\n", dpu_kms->mmio);
 
 	dpu_kms->vbif[VBIF_RT] = msm_ioremap(pdev, "vbif");
 	if (IS_ERR(dpu_kms->vbif[VBIF_RT])) {
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c
index 01171c5..6859e8e 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c
@@ -1129,7 +1129,7 @@ static int dpu_plane_virtual_atomic_check(struct drm_plane *plane,
 	struct drm_plane_state *old_plane_state =
 		drm_atomic_get_old_plane_state(state, plane);
 	struct dpu_plane_state *pstate = to_dpu_plane_state(plane_state);
-	struct drm_crtc_state *crtc_state;
+	struct drm_crtc_state *crtc_state = NULL;
 	int ret;
 
 	if (IS_ERR(plane_state))
@@ -1162,7 +1162,7 @@ static int dpu_plane_virtual_atomic_check(struct drm_plane *plane,
 	if (!old_plane_state || !old_plane_state->fb ||
 	    old_plane_state->src_w != plane_state->src_w ||
 	    old_plane_state->src_h != plane_state->src_h ||
-	    old_plane_state->src_w != plane_state->src_w ||
+	    old_plane_state->crtc_w != plane_state->crtc_w ||
 	    old_plane_state->crtc_h != plane_state->crtc_h ||
 	    msm_framebuffer_format(old_plane_state->fb) !=
 	    msm_framebuffer_format(plane_state->fb))
diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c
index 221f12d..4ea6811 100644
--- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c
+++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c
@@ -5,6 +5,8 @@
 
 #include <linux/clk-provider.h>
 #include <linux/platform_device.h>
+#include <linux/pm_clock.h>
+#include <linux/pm_runtime.h>
 #include <dt-bindings/phy/phy.h>
 
 #include "dsi_phy.h"
@@ -511,30 +513,6 @@ int msm_dsi_cphy_timing_calc_v4(struct msm_dsi_dphy_timing *timing,
 	return 0;
 }
 
-static int dsi_phy_enable_resource(struct msm_dsi_phy *phy)
-{
-	struct device *dev = &phy->pdev->dev;
-	int ret;
-
-	ret = pm_runtime_resume_and_get(dev);
-	if (ret)
-		return ret;
-
-	ret = clk_prepare_enable(phy->ahb_clk);
-	if (ret) {
-		DRM_DEV_ERROR(dev, "%s: can't enable ahb clk, %d\n", __func__, ret);
-		pm_runtime_put_sync(dev);
-	}
-
-	return ret;
-}
-
-static void dsi_phy_disable_resource(struct msm_dsi_phy *phy)
-{
-	clk_disable_unprepare(phy->ahb_clk);
-	pm_runtime_put(&phy->pdev->dev);
-}
-
 static const struct of_device_id dsi_phy_dt_match[] = {
 #ifdef CONFIG_DRM_MSM_DSI_28NM_PHY
 	{ .compatible = "qcom,dsi-phy-28nm-hpm",
@@ -698,22 +676,20 @@ static int dsi_phy_driver_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
-	phy->ahb_clk = msm_clk_get(pdev, "iface");
-	if (IS_ERR(phy->ahb_clk))
-		return dev_err_probe(dev, PTR_ERR(phy->ahb_clk),
-				     "Unable to get ahb clk\n");
+	platform_set_drvdata(pdev, phy);
 
-	ret = devm_pm_runtime_enable(&pdev->dev);
+	ret = devm_pm_runtime_enable(dev);
 	if (ret)
 		return ret;
 
-	/* PLL init will call into clk_register which requires
-	 * register access, so we need to enable power and ahb clock.
-	 */
-	ret = dsi_phy_enable_resource(phy);
+	ret = devm_pm_clk_create(dev);
 	if (ret)
 		return ret;
 
+	ret = pm_clk_add(dev, "iface");
+	if (ret < 0)
+		return dev_err_probe(dev, ret, "Unable to get iface clk\n");
+
 	if (phy->cfg->ops.pll_init) {
 		ret = phy->cfg->ops.pll_init(phy);
 		if (ret)
@@ -727,18 +703,19 @@ static int dsi_phy_driver_probe(struct platform_device *pdev)
 		return dev_err_probe(dev, ret,
 				     "Failed to register clk provider\n");
 
-	dsi_phy_disable_resource(phy);
-
-	platform_set_drvdata(pdev, phy);
-
 	return 0;
 }
 
+static const struct dev_pm_ops dsi_phy_pm_ops = {
+	SET_RUNTIME_PM_OPS(pm_clk_suspend, pm_clk_resume, NULL)
+};
+
 static struct platform_driver dsi_phy_platform_driver = {
 	.probe      = dsi_phy_driver_probe,
 	.driver     = {
 		.name   = "msm_dsi_phy",
 		.of_match_table = dsi_phy_dt_match,
+		.pm = &dsi_phy_pm_ops,
 	},
 };
 
@@ -764,9 +741,9 @@ int msm_dsi_phy_enable(struct msm_dsi_phy *phy,
 
 	dev = &phy->pdev->dev;
 
-	ret = dsi_phy_enable_resource(phy);
+	ret = pm_runtime_resume_and_get(dev);
 	if (ret) {
-		DRM_DEV_ERROR(dev, "%s: resource enable failed, %d\n",
+		DRM_DEV_ERROR(dev, "%s: resume failed, %d\n",
 			__func__, ret);
 		goto res_en_fail;
 	}
@@ -810,7 +787,7 @@ int msm_dsi_phy_enable(struct msm_dsi_phy *phy,
 phy_en_fail:
 	regulator_bulk_disable(phy->cfg->num_regulators, phy->supplies);
 reg_en_fail:
-	dsi_phy_disable_resource(phy);
+	pm_runtime_put(dev);
 res_en_fail:
 	return ret;
 }
@@ -823,7 +800,7 @@ void msm_dsi_phy_disable(struct msm_dsi_phy *phy)
 	phy->cfg->ops.disable(phy);
 
 	regulator_bulk_disable(phy->cfg->num_regulators, phy->supplies);
-	dsi_phy_disable_resource(phy);
+	pm_runtime_put(&phy->pdev->dev);
 }
 
 void msm_dsi_phy_set_usecase(struct msm_dsi_phy *phy,
diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h
index c558f8d..3cbf082 100644
--- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h
+++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h
@@ -104,7 +104,6 @@ struct msm_dsi_phy {
 	phys_addr_t lane_size;
 	int id;
 
-	struct clk *ahb_clk;
 	struct regulator_bulk_data *supplies;
 
 	struct msm_dsi_dphy_timing timing;
diff --git a/drivers/gpu/drm/msm/msm_debugfs.c b/drivers/gpu/drm/msm/msm_debugfs.c
index bbda865..97dc708 100644
--- a/drivers/gpu/drm/msm/msm_debugfs.c
+++ b/drivers/gpu/drm/msm/msm_debugfs.c
@@ -325,25 +325,28 @@ static struct drm_info_list msm_debugfs_list[] = {
 
 static int late_init_minor(struct drm_minor *minor)
 {
-	struct drm_device *dev = minor->dev;
-	struct msm_drm_private *priv = dev->dev_private;
+	struct drm_device *dev;
+	struct msm_drm_private *priv;
 	int ret;
 
 	if (!minor)
 		return 0;
 
+	dev = minor->dev;
+	priv = dev->dev_private;
+
 	if (!priv->gpu_pdev)
 		return 0;
 
 	ret = msm_rd_debugfs_init(minor);
 	if (ret) {
-		DRM_DEV_ERROR(minor->dev->dev, "could not install rd debugfs\n");
+		DRM_DEV_ERROR(dev->dev, "could not install rd debugfs\n");
 		return ret;
 	}
 
 	ret = msm_perf_debugfs_init(minor);
 	if (ret) {
-		DRM_DEV_ERROR(minor->dev->dev, "could not install perf debugfs\n");
+		DRM_DEV_ERROR(dev->dev, "could not install perf debugfs\n");
 		return ret;
 	}
 
diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c
index 7ff994d..e7631f4 100644
--- a/drivers/gpu/drm/msm/msm_gem.c
+++ b/drivers/gpu/drm/msm/msm_gem.c
@@ -95,7 +95,6 @@ void msm_gem_vma_get(struct drm_gem_object *obj)
 void msm_gem_vma_put(struct drm_gem_object *obj)
 {
 	struct msm_drm_private *priv = obj->dev->dev_private;
-	struct drm_exec exec;
 
 	if (atomic_dec_return(&to_msm_bo(obj)->vma_ref))
 		return;
@@ -103,9 +102,13 @@ void msm_gem_vma_put(struct drm_gem_object *obj)
 	if (!priv->kms)
 		return;
 
+#ifdef CONFIG_DRM_MSM_KMS
+	struct drm_exec exec;
+
 	msm_gem_lock_vm_and_obj(&exec, obj, priv->kms->vm);
 	put_iova_spaces(obj, priv->kms->vm, true, "vma_put");
 	drm_exec_fini(&exec);     /* drop locks */
+#endif
 }
 
 /*
@@ -663,9 +666,13 @@ int msm_gem_set_iova(struct drm_gem_object *obj,
 
 static bool is_kms_vm(struct drm_gpuvm *vm)
 {
+#ifdef CONFIG_DRM_MSM_KMS
 	struct msm_drm_private *priv = vm->drm->dev_private;
 
 	return priv->kms && (priv->kms->vm == vm);
+#else
+	return false;
+#endif
 }
 
 /*
@@ -1113,10 +1120,12 @@ static void msm_gem_free_object(struct drm_gem_object *obj)
 		put_pages(obj);
 	}
 
-	if (msm_obj->flags & MSM_BO_NO_SHARE) {
+	if (obj->resv != &obj->_resv) {
 		struct drm_gem_object *r_obj =
 			container_of(obj->resv, struct drm_gem_object, _resv);
 
+		WARN_ON(!(msm_obj->flags & MSM_BO_NO_SHARE));
+
 		/* Drop reference we hold to shared resv obj: */
 		drm_gem_object_put(r_obj);
 	}
diff --git a/drivers/gpu/drm/msm/msm_gem.h b/drivers/gpu/drm/msm/msm_gem.h
index 88239da..751c3b4 100644
--- a/drivers/gpu/drm/msm/msm_gem.h
+++ b/drivers/gpu/drm/msm/msm_gem.h
@@ -100,7 +100,7 @@ struct msm_gem_vm {
 	 *
 	 * Only used for kernel managed VMs, unused for user managed VMs.
 	 *
-	 * Protected by @mm_lock.
+	 * Protected by vm lock.  See msm_gem_lock_vm_and_obj(), for ex.
 	 */
 	struct drm_mm mm;
 
diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c
index 5f8e939..3ab3b27 100644
--- a/drivers/gpu/drm/msm/msm_gem_submit.c
+++ b/drivers/gpu/drm/msm/msm_gem_submit.c
@@ -271,32 +271,37 @@ static int submit_lookup_cmds(struct msm_gem_submit *submit,
 	return ret;
 }
 
+static int submit_lock_objects_vmbind(struct msm_gem_submit *submit)
+{
+	unsigned flags = DRM_EXEC_INTERRUPTIBLE_WAIT | DRM_EXEC_IGNORE_DUPLICATES;
+	struct drm_exec *exec = &submit->exec;
+	int ret = 0;
+
+	drm_exec_init(&submit->exec, flags, submit->nr_bos);
+
+	drm_exec_until_all_locked (&submit->exec) {
+		ret = drm_gpuvm_prepare_vm(submit->vm, exec, 1);
+		drm_exec_retry_on_contention(exec);
+		if (ret)
+			break;
+
+		ret = drm_gpuvm_prepare_objects(submit->vm, exec, 1);
+		drm_exec_retry_on_contention(exec);
+		if (ret)
+			break;
+	}
+
+	return ret;
+}
+
 /* This is where we make sure all the bo's are reserved and pin'd: */
 static int submit_lock_objects(struct msm_gem_submit *submit)
 {
 	unsigned flags = DRM_EXEC_INTERRUPTIBLE_WAIT;
-	struct drm_exec *exec = &submit->exec;
-	int ret;
+	int ret = 0;
 
-	if (msm_context_is_vmbind(submit->queue->ctx)) {
-		flags |= DRM_EXEC_IGNORE_DUPLICATES;
-
-		drm_exec_init(&submit->exec, flags, submit->nr_bos);
-
-		drm_exec_until_all_locked (&submit->exec) {
-			ret = drm_gpuvm_prepare_vm(submit->vm, exec, 1);
-			drm_exec_retry_on_contention(exec);
-			if (ret)
-				return ret;
-
-			ret = drm_gpuvm_prepare_objects(submit->vm, exec, 1);
-			drm_exec_retry_on_contention(exec);
-			if (ret)
-				return ret;
-		}
-
-		return 0;
-	}
+	if (msm_context_is_vmbind(submit->queue->ctx))
+		return submit_lock_objects_vmbind(submit);
 
 	drm_exec_init(&submit->exec, flags, submit->nr_bos);
 
@@ -305,17 +310,17 @@ static int submit_lock_objects(struct msm_gem_submit *submit)
 					drm_gpuvm_resv_obj(submit->vm));
 		drm_exec_retry_on_contention(&submit->exec);
 		if (ret)
-			return ret;
+			break;
 		for (unsigned i = 0; i < submit->nr_bos; i++) {
 			struct drm_gem_object *obj = submit->bos[i].obj;
 			ret = drm_exec_prepare_obj(&submit->exec, obj, 1);
 			drm_exec_retry_on_contention(&submit->exec);
 			if (ret)
-				return ret;
+				break;
 		}
 	}
 
-	return 0;
+	return ret;
 }
 
 static int submit_fence_sync(struct msm_gem_submit *submit)
@@ -514,14 +519,15 @@ static int submit_reloc(struct msm_gem_submit *submit, struct drm_gem_object *ob
  */
 static void submit_cleanup(struct msm_gem_submit *submit, bool error)
 {
+	if (error)
+		submit_unpin_objects(submit);
+
 	if (submit->exec.objects)
 		drm_exec_fini(&submit->exec);
 
-	if (error) {
-		submit_unpin_objects(submit);
-		/* job wasn't enqueued to scheduler, so early retirement: */
+	/* if job wasn't enqueued to scheduler, early retirement: */
+	if (error)
 		msm_submit_retire(submit);
-	}
 }
 
 void msm_submit_retire(struct msm_gem_submit *submit)
@@ -769,12 +775,8 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data,
 
 	if (ret == 0 && args->flags & MSM_SUBMIT_FENCE_FD_OUT) {
 		sync_file = sync_file_create(submit->user_fence);
-		if (!sync_file) {
+		if (!sync_file)
 			ret = -ENOMEM;
-		} else {
-			fd_install(out_fence_fd, sync_file->file);
-			args->fence_fd = out_fence_fd;
-		}
 	}
 
 	if (ret)
@@ -812,10 +814,14 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data,
 out_unlock:
 	mutex_unlock(&queue->lock);
 out_post_unlock:
-	if (ret && (out_fence_fd >= 0)) {
-		put_unused_fd(out_fence_fd);
+	if (ret) {
+		if (out_fence_fd >= 0)
+			put_unused_fd(out_fence_fd);
 		if (sync_file)
 			fput(sync_file->file);
+	} else if (sync_file) {
+		fd_install(out_fence_fd, sync_file->file);
+		args->fence_fd = out_fence_fd;
 	}
 
 	if (!IS_ERR_OR_NULL(submit)) {
diff --git a/drivers/gpu/drm/msm/msm_gem_vma.c b/drivers/gpu/drm/msm/msm_gem_vma.c
index 3cd8562..00d0f3b 100644
--- a/drivers/gpu/drm/msm/msm_gem_vma.c
+++ b/drivers/gpu/drm/msm/msm_gem_vma.c
@@ -319,13 +319,10 @@ msm_gem_vma_map(struct drm_gpuva *vma, int prot, struct sg_table *sgt)
 		mutex_lock(&vm->mmu_lock);
 
 	/*
-	 * NOTE: iommu/io-pgtable can allocate pages, so we cannot hold
+	 * NOTE: if not using pgtable preallocation, we cannot hold
 	 * a lock across map/unmap which is also used in the job_run()
 	 * path, as this can cause deadlock in job_run() vs shrinker/
 	 * reclaim.
-	 *
-	 * Revisit this if we can come up with a scheme to pre-alloc pages
-	 * for the pgtable in map/unmap ops.
 	 */
 	ret = vm_map_op(vm, &(struct msm_vm_map_op){
 		.iova = vma->va.addr,
@@ -454,6 +451,8 @@ msm_gem_vm_bo_validate(struct drm_gpuvm_bo *vm_bo, struct drm_exec *exec)
 struct op_arg {
 	unsigned flags;
 	struct msm_vm_bind_job *job;
+	const struct msm_vm_bind_op *op;
+	bool kept;
 };
 
 static void
@@ -475,14 +474,18 @@ vma_from_op(struct op_arg *arg, struct drm_gpuva_op_map *op)
 }
 
 static int
-msm_gem_vm_sm_step_map(struct drm_gpuva_op *op, void *arg)
+msm_gem_vm_sm_step_map(struct drm_gpuva_op *op, void *_arg)
 {
-	struct msm_vm_bind_job *job = ((struct op_arg *)arg)->job;
+	struct op_arg *arg = _arg;
+	struct msm_vm_bind_job *job = arg->job;
 	struct drm_gem_object *obj = op->map.gem.obj;
 	struct drm_gpuva *vma;
 	struct sg_table *sgt;
 	unsigned prot;
 
+	if (arg->kept)
+		return 0;
+
 	vma = vma_from_op(arg, &op->map);
 	if (WARN_ON(IS_ERR(vma)))
 		return PTR_ERR(vma);
@@ -602,15 +605,41 @@ msm_gem_vm_sm_step_remap(struct drm_gpuva_op *op, void *arg)
 }
 
 static int
-msm_gem_vm_sm_step_unmap(struct drm_gpuva_op *op, void *arg)
+msm_gem_vm_sm_step_unmap(struct drm_gpuva_op *op, void *_arg)
 {
-	struct msm_vm_bind_job *job = ((struct op_arg *)arg)->job;
+	struct op_arg *arg = _arg;
+	struct msm_vm_bind_job *job = arg->job;
 	struct drm_gpuva *vma = op->unmap.va;
 	struct msm_gem_vma *msm_vma = to_msm_vma(vma);
 
 	vm_dbg("%p:%p:%p: %016llx %016llx", vma->vm, vma, vma->gem.obj,
 	       vma->va.addr, vma->va.range);
 
+	/*
+	 * Detect in-place remap.  Turnip does this to change the vma flags,
+	 * in particular MSM_VMA_DUMP.  In this case we want to avoid actually
+	 * touching the page tables, as that would require synchronization
+	 * against SUBMIT jobs running on the GPU.
+	 */
+	if (op->unmap.keep &&
+	    (arg->op->op == MSM_VM_BIND_OP_MAP) &&
+	    (vma->gem.obj == arg->op->obj) &&
+	    (vma->gem.offset == arg->op->obj_offset) &&
+	    (vma->va.addr == arg->op->iova) &&
+	    (vma->va.range == arg->op->range)) {
+		/* We are only expecting a single in-place unmap+map cb pair: */
+		WARN_ON(arg->kept);
+
+		/* Leave the existing VMA in place, but signal that to the map cb: */
+		arg->kept = true;
+
+		/* Only flags are changing, so update that in-place: */
+		unsigned orig_flags = vma->flags & (DRM_GPUVA_USERBITS - 1);
+		vma->flags = orig_flags | arg->flags;
+
+		return 0;
+	}
+
 	if (!msm_vma->mapped)
 		goto out_close;
 
@@ -1271,6 +1300,7 @@ vm_bind_job_prepare(struct msm_vm_bind_job *job)
 		const struct msm_vm_bind_op *op = &job->ops[i];
 		struct op_arg arg = {
 			.job = job,
+			.op = op,
 		};
 
 		switch (op->op) {
@@ -1460,12 +1490,8 @@ msm_ioctl_vm_bind(struct drm_device *dev, void *data, struct drm_file *file)
 
 	if (args->flags & MSM_VM_BIND_FENCE_FD_OUT) {
 		sync_file = sync_file_create(job->fence);
-		if (!sync_file) {
+		if (!sync_file)
 			ret = -ENOMEM;
-		} else {
-			fd_install(out_fence_fd, sync_file->file);
-			args->fence_fd = out_fence_fd;
-		}
 	}
 
 	if (ret)
@@ -1494,10 +1520,14 @@ msm_ioctl_vm_bind(struct drm_device *dev, void *data, struct drm_file *file)
 out_unlock:
 	mutex_unlock(&queue->lock);
 out_post_unlock:
-	if (ret && (out_fence_fd >= 0)) {
-		put_unused_fd(out_fence_fd);
+	if (ret) {
+		if (out_fence_fd >= 0)
+			put_unused_fd(out_fence_fd);
 		if (sync_file)
 			fput(sync_file->file);
+	} else if (sync_file) {
+		fd_install(out_fence_fd, sync_file->file);
+		args->fence_fd = out_fence_fd;
 	}
 
 	if (!IS_ERR_OR_NULL(job)) {
diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c
index c317b25..26c5ce8 100644
--- a/drivers/gpu/drm/msm/msm_gpu.c
+++ b/drivers/gpu/drm/msm/msm_gpu.c
@@ -465,6 +465,7 @@ static void recover_worker(struct kthread_work *work)
 	struct msm_gem_submit *submit;
 	struct msm_ringbuffer *cur_ring = gpu->funcs->active_ring(gpu);
 	char *comm = NULL, *cmd = NULL;
+	struct task_struct *task;
 	int i;
 
 	mutex_lock(&gpu->lock);
@@ -482,16 +483,20 @@ static void recover_worker(struct kthread_work *work)
 
 	/* Increment the fault counts */
 	submit->queue->faults++;
-	if (submit->vm) {
+
+	task = get_pid_task(submit->pid, PIDTYPE_PID);
+	if (!task)
+		gpu->global_faults++;
+	else {
 		struct msm_gem_vm *vm = to_msm_vm(submit->vm);
 
 		vm->faults++;
 
 		/*
 		 * If userspace has opted-in to VM_BIND (and therefore userspace
-		 * management of the VM), faults mark the VM as unusuable.  This
+		 * management of the VM), faults mark the VM as unusable. This
 		 * matches vulkan expectations (vulkan is the main target for
-		 * VM_BIND)
+		 * VM_BIND).
 		 */
 		if (!vm->managed)
 			msm_gem_vm_unusable(submit->vm);
@@ -553,8 +558,15 @@ static void recover_worker(struct kthread_work *work)
 			unsigned long flags;
 
 			spin_lock_irqsave(&ring->submit_lock, flags);
-			list_for_each_entry(submit, &ring->submits, node)
+			list_for_each_entry(submit, &ring->submits, node) {
+				/*
+				 * If the submit uses an unusable vm make sure
+				 * we don't actually run it
+				 */
+				if (to_msm_vm(submit->vm)->unusable)
+					submit->nr_cmds = 0;
 				gpu->funcs->submit(gpu, submit);
+			}
 			spin_unlock_irqrestore(&ring->submit_lock, flags);
 		}
 	}
diff --git a/drivers/gpu/drm/msm/msm_iommu.c b/drivers/gpu/drm/msm/msm_iommu.c
index 55c29f4..76cdd5e 100644
--- a/drivers/gpu/drm/msm/msm_iommu.c
+++ b/drivers/gpu/drm/msm/msm_iommu.c
@@ -14,7 +14,9 @@
 struct msm_iommu {
 	struct msm_mmu base;
 	struct iommu_domain *domain;
-	atomic_t pagetables;
+
+	struct mutex init_lock;  /* protects pagetables counter and prr_page */
+	int pagetables;
 	struct page *prr_page;
 
 	struct kmem_cache *pt_cache;
@@ -227,7 +229,8 @@ static void msm_iommu_pagetable_destroy(struct msm_mmu *mmu)
 	 * If this is the last attached pagetable for the parent,
 	 * disable TTBR0 in the arm-smmu driver
 	 */
-	if (atomic_dec_return(&iommu->pagetables) == 0) {
+	mutex_lock(&iommu->init_lock);
+	if (--iommu->pagetables == 0) {
 		adreno_smmu->set_ttbr0_cfg(adreno_smmu->cookie, NULL);
 
 		if (adreno_smmu->set_prr_bit) {
@@ -236,6 +239,7 @@ static void msm_iommu_pagetable_destroy(struct msm_mmu *mmu)
 			iommu->prr_page = NULL;
 		}
 	}
+	mutex_unlock(&iommu->init_lock);
 
 	free_io_pgtable_ops(pagetable->pgtbl_ops);
 	kfree(pagetable);
@@ -568,9 +572,12 @@ struct msm_mmu *msm_iommu_pagetable_create(struct msm_mmu *parent, bool kernel_m
 	 * If this is the first pagetable that we've allocated, send it back to
 	 * the arm-smmu driver as a trigger to set up TTBR0
 	 */
-	if (atomic_inc_return(&iommu->pagetables) == 1) {
+	mutex_lock(&iommu->init_lock);
+	if (iommu->pagetables++ == 0) {
 		ret = adreno_smmu->set_ttbr0_cfg(adreno_smmu->cookie, &ttbr0_cfg);
 		if (ret) {
+			iommu->pagetables--;
+			mutex_unlock(&iommu->init_lock);
 			free_io_pgtable_ops(pagetable->pgtbl_ops);
 			kfree(pagetable);
 			return ERR_PTR(ret);
@@ -595,6 +602,7 @@ struct msm_mmu *msm_iommu_pagetable_create(struct msm_mmu *parent, bool kernel_m
 			adreno_smmu->set_prr_bit(adreno_smmu->cookie, true);
 		}
 	}
+	mutex_unlock(&iommu->init_lock);
 
 	/* Needed later for TLB flush */
 	pagetable->parent = parent;
@@ -730,7 +738,7 @@ struct msm_mmu *msm_iommu_new(struct device *dev, unsigned long quirks)
 	iommu->domain = domain;
 	msm_mmu_init(&iommu->base, dev, &funcs, MSM_MMU_IOMMU);
 
-	atomic_set(&iommu->pagetables, 0);
+	mutex_init(&iommu->init_lock);
 
 	ret = iommu_attach_device(iommu->domain, dev);
 	if (ret) {
diff --git a/drivers/gpu/drm/msm/msm_kms.c b/drivers/gpu/drm/msm/msm_kms.c
index 6889f1c..56828d2 100644
--- a/drivers/gpu/drm/msm/msm_kms.c
+++ b/drivers/gpu/drm/msm/msm_kms.c
@@ -275,6 +275,12 @@ int msm_drm_kms_init(struct device *dev, const struct drm_driver *drv)
 	if (ret)
 		return ret;
 
+	ret = msm_disp_snapshot_init(ddev);
+	if (ret) {
+		DRM_DEV_ERROR(dev, "msm_disp_snapshot_init failed ret = %d\n", ret);
+		return ret;
+	}
+
 	ret = priv->kms_init(ddev);
 	if (ret) {
 		DRM_DEV_ERROR(dev, "failed to load kms\n");
@@ -327,10 +333,6 @@ int msm_drm_kms_init(struct device *dev, const struct drm_driver *drv)
 		goto err_msm_uninit;
 	}
 
-	ret = msm_disp_snapshot_init(ddev);
-	if (ret)
-		DRM_DEV_ERROR(dev, "msm_disp_snapshot_init failed ret = %d\n", ret);
-
 	drm_mode_config_reset(ddev);
 
 	return 0;
diff --git a/drivers/gpu/drm/msm/msm_mdss.c b/drivers/gpu/drm/msm/msm_mdss.c
index 1f5fe78..39885b3 100644
--- a/drivers/gpu/drm/msm/msm_mdss.c
+++ b/drivers/gpu/drm/msm/msm_mdss.c
@@ -423,7 +423,7 @@ static struct msm_mdss *msm_mdss_init(struct platform_device *pdev, bool is_mdp5
 	if (IS_ERR(msm_mdss->mmio))
 		return ERR_CAST(msm_mdss->mmio);
 
-	dev_dbg(&pdev->dev, "mapped mdss address space @%pK\n", msm_mdss->mmio);
+	dev_dbg(&pdev->dev, "mapped mdss address space @%p\n", msm_mdss->mmio);
 
 	ret = msm_mdss_parse_data_bus_icc_path(&pdev->dev, msm_mdss);
 	if (ret)
diff --git a/drivers/gpu/drm/msm/registers/adreno/a6xx.xml b/drivers/gpu/drm/msm/registers/adreno/a6xx.xml
index d860fd9..86fab27 100644
--- a/drivers/gpu/drm/msm/registers/adreno/a6xx.xml
+++ b/drivers/gpu/drm/msm/registers/adreno/a6xx.xml
@@ -594,10 +594,14 @@
 	<reg32 offset="0x0600" name="DBGC_CFG_DBGBUS_SEL_A"/>
 	<reg32 offset="0x0601" name="DBGC_CFG_DBGBUS_SEL_B"/>
 	<reg32 offset="0x0602" name="DBGC_CFG_DBGBUS_SEL_C"/>
-	<reg32 offset="0x0603" name="DBGC_CFG_DBGBUS_SEL_D">
+	<reg32 offset="0x0603" name="DBGC_CFG_DBGBUS_SEL_D" variants="A6XX">
 		<bitfield high="7" low="0" name="PING_INDEX"/>
 		<bitfield high="15" low="8" name="PING_BLK_SEL"/>
 	</reg32>
+	<reg32 offset="0x0603" name="DBGC_CFG_DBGBUS_SEL_D" variants="A7XX-">
+		<bitfield high="7" low="0" name="PING_INDEX"/>
+		<bitfield high="24" low="16" name="PING_BLK_SEL"/>
+	</reg32>
 	<reg32 offset="0x0604" name="DBGC_CFG_DBGBUS_CNTLT">
 		<bitfield high="5" low="0" name="TRACEEN"/>
 		<bitfield high="14" low="12" name="GRANU"/>
@@ -3796,6 +3800,14 @@
 	<reg32 offset="0x0030" name="CFG_DBGBUS_TRACE_BUF2"/>
 </domain>
 
+<domain name="A7XX_CX_DBGC" width="32">
+	<!-- Bitfields shifted, but otherwise the same: -->
+	<reg32 offset="0x0000" name="CFG_DBGBUS_SEL_A" variants="A7XX-">
+		<bitfield high="7" low="0" name="PING_INDEX"/>
+		<bitfield high="24" low="16" name="PING_BLK_SEL"/>
+	</reg32>
+</domain>
+
 <domain name="A6XX_CX_MISC" width="32" prefix="variant" varset="chip">
 	<reg32 offset="0x0001" name="SYSTEM_CACHE_CNTL_0"/>
 	<reg32 offset="0x0002" name="SYSTEM_CACHE_CNTL_1"/>
diff --git a/drivers/gpu/drm/msm/registers/display/dsi.xml b/drivers/gpu/drm/msm/registers/display/dsi.xml
index 501ffc5..c7a7b63 100644
--- a/drivers/gpu/drm/msm/registers/display/dsi.xml
+++ b/drivers/gpu/drm/msm/registers/display/dsi.xml
@@ -159,28 +159,28 @@
 		<bitfield name="RGB_SWAP" low="12" high="14" type="dsi_rgb_swap"/>
 	</reg32>
 	<reg32 offset="0x00020" name="ACTIVE_H">
-		<bitfield name="START" low="0" high="11" type="uint"/>
-		<bitfield name="END" low="16" high="27" type="uint"/>
+		<bitfield name="START" low="0" high="15" type="uint"/>
+		<bitfield name="END" low="16" high="31" type="uint"/>
 	</reg32>
 	<reg32 offset="0x00024" name="ACTIVE_V">
-		<bitfield name="START" low="0" high="11" type="uint"/>
-		<bitfield name="END" low="16" high="27" type="uint"/>
+		<bitfield name="START" low="0" high="15" type="uint"/>
+		<bitfield name="END" low="16" high="31" type="uint"/>
 	</reg32>
 	<reg32 offset="0x00028" name="TOTAL">
-		<bitfield name="H_TOTAL" low="0" high="11" type="uint"/>
-		<bitfield name="V_TOTAL" low="16" high="27" type="uint"/>
+		<bitfield name="H_TOTAL" low="0" high="15" type="uint"/>
+		<bitfield name="V_TOTAL" low="16" high="31" type="uint"/>
 	</reg32>
 	<reg32 offset="0x0002c" name="ACTIVE_HSYNC">
-		<bitfield name="START" low="0" high="11" type="uint"/>
-		<bitfield name="END" low="16" high="27" type="uint"/>
+		<bitfield name="START" low="0" high="15" type="uint"/>
+		<bitfield name="END" low="16" high="31" type="uint"/>
 	</reg32>
 	<reg32 offset="0x00030" name="ACTIVE_VSYNC_HPOS">
-		<bitfield name="START" low="0" high="11" type="uint"/>
-		<bitfield name="END" low="16" high="27" type="uint"/>
+		<bitfield name="START" low="0" high="15" type="uint"/>
+		<bitfield name="END" low="16" high="31" type="uint"/>
 	</reg32>
 	<reg32 offset="0x00034" name="ACTIVE_VSYNC_VPOS">
-		<bitfield name="START" low="0" high="11" type="uint"/>
-		<bitfield name="END" low="16" high="27" type="uint"/>
+		<bitfield name="START" low="0" high="15" type="uint"/>
+		<bitfield name="END" low="16" high="31" type="uint"/>
 	</reg32>
 
 	<reg32 offset="0x00038" name="CMD_DMA_CTRL">
@@ -209,8 +209,8 @@
 		<bitfield name="WORD_COUNT" low="16" high="31" type="uint"/>
 	</reg32>
 	<reg32 offset="0x00058" name="CMD_MDP_STREAM0_TOTAL">
-		<bitfield name="H_TOTAL" low="0" high="11" type="uint"/>
-		<bitfield name="V_TOTAL" low="16" high="27" type="uint"/>
+		<bitfield name="H_TOTAL" low="0" high="15" type="uint"/>
+		<bitfield name="V_TOTAL" low="16" high="31" type="uint"/>
 	</reg32>
 	<reg32 offset="0x0005c" name="CMD_MDP_STREAM1_CTRL">
 		<bitfield name="DATA_TYPE" low="0" high="5" type="uint"/>
diff --git a/drivers/gpu/drm/nouveau/dispnv50/wndw.c b/drivers/gpu/drm/nouveau/dispnv50/wndw.c
index 11d5b92..e2c55f4 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/wndw.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/wndw.c
@@ -795,6 +795,10 @@ static bool nv50_plane_format_mod_supported(struct drm_plane *plane,
 	struct nouveau_drm *drm = nouveau_drm(plane->dev);
 	uint8_t i;
 
+	/* All chipsets can display all formats in linear layout */
+	if (modifier == DRM_FORMAT_MOD_LINEAR)
+		return true;
+
 	if (drm->client.device.info.chipset < 0xc0) {
 		const struct drm_format_info *info = drm_format_info(format);
 		const uint8_t kind = (modifier >> 12) & 0xff;
diff --git a/drivers/gpu/drm/nouveau/nvkm/falcon/gm200.c b/drivers/gpu/drm/nouveau/nvkm/falcon/gm200.c
index b7da3ab..7c43397 100644
--- a/drivers/gpu/drm/nouveau/nvkm/falcon/gm200.c
+++ b/drivers/gpu/drm/nouveau/nvkm/falcon/gm200.c
@@ -103,7 +103,7 @@ gm200_flcn_pio_imem_wr_init(struct nvkm_falcon *falcon, u8 port, bool sec, u32 i
 static void
 gm200_flcn_pio_imem_wr(struct nvkm_falcon *falcon, u8 port, const u8 *img, int len, u16 tag)
 {
-	nvkm_falcon_wr32(falcon, 0x188 + (port * 0x10), tag++);
+	nvkm_falcon_wr32(falcon, 0x188 + (port * 0x10), tag);
 	while (len >= 4) {
 		nvkm_falcon_wr32(falcon, 0x184 + (port * 0x10), *(u32 *)img);
 		img += 4;
@@ -249,9 +249,11 @@ int
 gm200_flcn_fw_load(struct nvkm_falcon_fw *fw)
 {
 	struct nvkm_falcon *falcon = fw->falcon;
-	int target, ret;
+	int ret;
 
 	if (fw->inst) {
+		int target;
+
 		nvkm_falcon_mask(falcon, 0x048, 0x00000001, 0x00000001);
 
 		switch (nvkm_memory_target(fw->inst)) {
@@ -285,15 +287,6 @@ gm200_flcn_fw_load(struct nvkm_falcon_fw *fw)
 	}
 
 	if (fw->boot) {
-		switch (nvkm_memory_target(&fw->fw.mem.memory)) {
-		case NVKM_MEM_TARGET_VRAM: target = 4; break;
-		case NVKM_MEM_TARGET_HOST: target = 5; break;
-		case NVKM_MEM_TARGET_NCOH: target = 6; break;
-		default:
-			WARN_ON(1);
-			return -EINVAL;
-		}
-
 		ret = nvkm_falcon_pio_wr(falcon, fw->boot, 0, 0,
 					 IMEM, falcon->code.limit - fw->boot_size, fw->boot_size,
 					 fw->boot_addr >> 8, false);
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/fwsec.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/fwsec.c
index 5241296..5b721bd 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/fwsec.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/fwsec.c
@@ -209,11 +209,12 @@ nvkm_gsp_fwsec_v2(struct nvkm_gsp *gsp, const char *name,
 	fw->boot_addr = bld->start_tag << 8;
 	fw->boot_size = bld->code_size;
 	fw->boot = kmemdup(bl->data + hdr->data_offset + bld->code_off, fw->boot_size, GFP_KERNEL);
-	if (!fw->boot)
-		ret = -ENOMEM;
 
 	nvkm_firmware_put(bl);
 
+	if (!fw->boot)
+		return -ENOMEM;
+
 	/* Patch in interface data. */
 	return nvkm_gsp_fwsec_patch(gsp, fw, desc->InterfaceOffset, init_cmd);
 }
diff --git a/drivers/gpu/drm/tegra/gem.c b/drivers/gpu/drm/tegra/gem.c
index 41a285e..8ede07fb 100644
--- a/drivers/gpu/drm/tegra/gem.c
+++ b/drivers/gpu/drm/tegra/gem.c
@@ -526,7 +526,7 @@ void tegra_bo_free_object(struct drm_gem_object *gem)
 		if (drm_gem_is_imported(gem)) {
 			dma_buf_unmap_attachment_unlocked(gem->import_attach, bo->sgt,
 							  DMA_TO_DEVICE);
-			dma_buf_detach(gem->dma_buf, gem->import_attach);
+			dma_buf_detach(gem->import_attach->dmabuf, gem->import_attach);
 		}
 	}
 
diff --git a/drivers/gpu/drm/xe/xe_bo.c b/drivers/gpu/drm/xe/xe_bo.c
index 18f27da..1be2415 100644
--- a/drivers/gpu/drm/xe/xe_bo.c
+++ b/drivers/gpu/drm/xe/xe_bo.c
@@ -812,7 +812,8 @@ static int xe_bo_move(struct ttm_buffer_object *ttm_bo, bool evict,
 	}
 
 	if (ttm_bo->type == ttm_bo_type_sg) {
-		ret = xe_bo_move_notify(bo, ctx);
+		if (new_mem->mem_type == XE_PL_SYSTEM)
+			ret = xe_bo_move_notify(bo, ctx);
 		if (!ret)
 			ret = xe_bo_move_dmabuf(ttm_bo, new_mem);
 		return ret;
@@ -2438,7 +2439,6 @@ int xe_bo_validate(struct xe_bo *bo, struct xe_vm *vm, bool allow_res_evict)
 		.no_wait_gpu = false,
 		.gfp_retry_mayfail = true,
 	};
-	struct pin_cookie cookie;
 	int ret;
 
 	if (vm) {
@@ -2449,10 +2449,10 @@ int xe_bo_validate(struct xe_bo *bo, struct xe_vm *vm, bool allow_res_evict)
 		ctx.resv = xe_vm_resv(vm);
 	}
 
-	cookie = xe_vm_set_validating(vm, allow_res_evict);
+	xe_vm_set_validating(vm, allow_res_evict);
 	trace_xe_bo_validate(bo);
 	ret = ttm_bo_validate(&bo->ttm, &bo->placement, &ctx);
-	xe_vm_clear_validating(vm, allow_res_evict, cookie);
+	xe_vm_clear_validating(vm, allow_res_evict);
 
 	return ret;
 }
diff --git a/drivers/gpu/drm/xe/xe_gen_wa_oob.c b/drivers/gpu/drm/xe/xe_gen_wa_oob.c
index 6581cb0..247e41c 100644
--- a/drivers/gpu/drm/xe/xe_gen_wa_oob.c
+++ b/drivers/gpu/drm/xe/xe_gen_wa_oob.c
@@ -123,11 +123,19 @@ static int parse(FILE *input, FILE *csource, FILE *cheader, char *prefix)
 	return 0;
 }
 
+/* Avoid GNU vs POSIX basename() discrepancy, just use our own */
+static const char *xbasename(const char *s)
+{
+	const char *p = strrchr(s, '/');
+
+	return p ? p + 1 : s;
+}
+
 static int fn_to_prefix(const char *fn, char *prefix, size_t size)
 {
 	size_t len;
 
-	fn = basename(fn);
+	fn = xbasename(fn);
 	len = strlen(fn);
 
 	if (len > size - 1)
diff --git a/drivers/gpu/drm/xe/xe_sync.c b/drivers/gpu/drm/xe/xe_sync.c
index f87276d..82872a5 100644
--- a/drivers/gpu/drm/xe/xe_sync.c
+++ b/drivers/gpu/drm/xe/xe_sync.c
@@ -77,6 +77,7 @@ static void user_fence_worker(struct work_struct *w)
 {
 	struct xe_user_fence *ufence = container_of(w, struct xe_user_fence, worker);
 
+	WRITE_ONCE(ufence->signalled, 1);
 	if (mmget_not_zero(ufence->mm)) {
 		kthread_use_mm(ufence->mm);
 		if (copy_to_user(ufence->addr, &ufence->value, sizeof(ufence->value)))
@@ -91,7 +92,6 @@ static void user_fence_worker(struct work_struct *w)
 	 * Wake up waiters only after updating the ufence state, allowing the UMD
 	 * to safely reuse the same ufence without encountering -EBUSY errors.
 	 */
-	WRITE_ONCE(ufence->signalled, 1);
 	wake_up_all(&ufence->xe->ufence_wq);
 	user_fence_put(ufence);
 }
diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index ec04bef..d60c4b1 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -1610,8 +1610,12 @@ static int xe_vm_create_scratch(struct xe_device *xe, struct xe_tile *tile,
 
 	for (i = MAX_HUGEPTE_LEVEL; i < vm->pt_root[id]->level; i++) {
 		vm->scratch_pt[id][i] = xe_pt_create(vm, tile, i);
-		if (IS_ERR(vm->scratch_pt[id][i]))
-			return PTR_ERR(vm->scratch_pt[id][i]);
+		if (IS_ERR(vm->scratch_pt[id][i])) {
+			int err = PTR_ERR(vm->scratch_pt[id][i]);
+
+			vm->scratch_pt[id][i] = NULL;
+			return err;
+		}
 
 		xe_pt_populate_empty(tile, vm, vm->scratch_pt[id][i]);
 	}
diff --git a/drivers/gpu/drm/xe/xe_vm.h b/drivers/gpu/drm/xe/xe_vm.h
index 2f21373..2ecb417c 100644
--- a/drivers/gpu/drm/xe/xe_vm.h
+++ b/drivers/gpu/drm/xe/xe_vm.h
@@ -315,22 +315,14 @@ void xe_vm_snapshot_free(struct xe_vm_snapshot *snap);
  * Register this task as currently making bos resident for the vm. Intended
  * to avoid eviction by the same task of shared bos bound to the vm.
  * Call with the vm's resv lock held.
- *
- * Return: A pin cookie that should be used for xe_vm_clear_validating().
  */
-static inline struct pin_cookie xe_vm_set_validating(struct xe_vm *vm,
-						     bool allow_res_evict)
+static inline void xe_vm_set_validating(struct xe_vm *vm, bool allow_res_evict)
 {
-	struct pin_cookie cookie = {};
-
 	if (vm && !allow_res_evict) {
 		xe_vm_assert_held(vm);
-		cookie = lockdep_pin_lock(&xe_vm_resv(vm)->lock.base);
 		/* Pairs with READ_ONCE in xe_vm_is_validating() */
 		WRITE_ONCE(vm->validating, current);
 	}
-
-	return cookie;
 }
 
 /**
@@ -338,17 +330,14 @@ static inline struct pin_cookie xe_vm_set_validating(struct xe_vm *vm,
  * @vm: Pointer to the vm or NULL
  * @allow_res_evict: Eviction from @vm was allowed. Must be set to the same
  * value as for xe_vm_set_validation().
- * @cookie: Cookie obtained from xe_vm_set_validating().
  *
  * Register this task as currently making bos resident for the vm. Intended
  * to avoid eviction by the same task of shared bos bound to the vm.
  * Call with the vm's resv lock held.
  */
-static inline void xe_vm_clear_validating(struct xe_vm *vm, bool allow_res_evict,
-					  struct pin_cookie cookie)
+static inline void xe_vm_clear_validating(struct xe_vm *vm, bool allow_res_evict)
 {
 	if (vm && !allow_res_evict) {
-		lockdep_unpin_lock(&xe_vm_resv(vm)->lock.base, cookie);
 		/* Pairs with READ_ONCE in xe_vm_is_validating() */
 		WRITE_ONCE(vm->validating, NULL);
 	}
diff --git a/drivers/hid/Kconfig b/drivers/hid/Kconfig
index a579012..7999755 100644
--- a/drivers/hid/Kconfig
+++ b/drivers/hid/Kconfig
@@ -1243,7 +1243,7 @@
 
 	  U2F Zero supports custom commands for blinking the LED
 	  and getting data from the internal hardware RNG.
-	  The internal hardware can be used to feed the enthropy pool.
+	  The internal hardware can be used to feed the entropy pool.
 
 	  U2F Zero only supports blinking its LED, so this driver doesn't
 	  allow setting the brightness to anything but 1, which will
diff --git a/drivers/hid/hid-asus.c b/drivers/hid/hid-asus.c
index 4b45e31..d27dcfb 100644
--- a/drivers/hid/hid-asus.c
+++ b/drivers/hid/hid-asus.c
@@ -1213,7 +1213,13 @@ static int asus_probe(struct hid_device *hdev, const struct hid_device_id *id)
 		return ret;
 	}
 
-	if (!drvdata->input) {
+	/*
+	 * Check that input registration succeeded. Checking that
+	 * HID_CLAIMED_INPUT is set prevents a UAF when all input devices
+	 * were freed during registration due to no usages being mapped,
+	 * leaving drvdata->input pointing to freed memory.
+	 */
+	if (!drvdata->input || !(hdev->claimed & HID_CLAIMED_INPUT)) {
 		hid_err(hdev, "Asus input not registered\n");
 		ret = -ENOMEM;
 		goto err_stop_hw;
diff --git a/drivers/hid/hid-elecom.c b/drivers/hid/hid-elecom.c
index 0ad7d25..69771fd 100644
--- a/drivers/hid/hid-elecom.c
+++ b/drivers/hid/hid-elecom.c
@@ -101,6 +101,7 @@ static const __u8 *elecom_report_fixup(struct hid_device *hdev, __u8 *rdesc,
 		 */
 		mouse_button_fixup(hdev, rdesc, *rsize, 12, 30, 14, 20, 8);
 		break;
+	case USB_DEVICE_ID_ELECOM_M_DT2DRBK:
 	case USB_DEVICE_ID_ELECOM_M_HT1DRBK_011C:
 		/*
 		 * Report descriptor format:
@@ -123,6 +124,7 @@ static const struct hid_device_id elecom_devices[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_XT4DRBK) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_DT1URBK) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_DT1DRBK) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_DT2DRBK) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_HT1URBK_010C) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_HT1URBK_019B) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_HT1DRBK_010D) },
diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h
index 5a10962..1497987 100644
--- a/drivers/hid/hid-ids.h
+++ b/drivers/hid/hid-ids.h
@@ -451,6 +451,7 @@
 #define USB_DEVICE_ID_ELECOM_M_XT4DRBK	0x00fd
 #define USB_DEVICE_ID_ELECOM_M_DT1URBK	0x00fe
 #define USB_DEVICE_ID_ELECOM_M_DT1DRBK	0x00ff
+#define USB_DEVICE_ID_ELECOM_M_DT2DRBK	0x018d
 #define USB_DEVICE_ID_ELECOM_M_HT1URBK_010C	0x010c
 #define USB_DEVICE_ID_ELECOM_M_HT1URBK_019B	0x019b
 #define USB_DEVICE_ID_ELECOM_M_HT1DRBK_010D	0x010d
@@ -834,6 +835,8 @@
 #define USB_DEVICE_ID_LENOVO_PIXART_USB_MOUSE_6019	0x6019
 #define USB_DEVICE_ID_LENOVO_PIXART_USB_MOUSE_602E	0x602e
 #define USB_DEVICE_ID_LENOVO_PIXART_USB_MOUSE_6093	0x6093
+#define USB_DEVICE_ID_LENOVO_LEGION_GO_DUAL_DINPUT	0x6184
+#define USB_DEVICE_ID_LENOVO_LEGION_GO2_DUAL_DINPUT	0x61ed
 
 #define USB_VENDOR_ID_LETSKETCH		0x6161
 #define USB_DEVICE_ID_WP9620N		0x4d15
@@ -907,6 +910,7 @@
 #define USB_DEVICE_ID_LOGITECH_NANO_RECEIVER_2		0xc534
 #define USB_DEVICE_ID_LOGITECH_NANO_RECEIVER_LIGHTSPEED_1	0xc539
 #define USB_DEVICE_ID_LOGITECH_NANO_RECEIVER_LIGHTSPEED_1_1	0xc53f
+#define USB_DEVICE_ID_LOGITECH_NANO_RECEIVER_LIGHTSPEED_1_2	0xc543
 #define USB_DEVICE_ID_LOGITECH_NANO_RECEIVER_POWERPLAY	0xc53a
 #define USB_DEVICE_ID_LOGITECH_BOLT_RECEIVER	0xc548
 #define USB_DEVICE_ID_SPACETRAVELLER	0xc623
diff --git a/drivers/hid/hid-input-test.c b/drivers/hid/hid-input-test.c
index 77c2d45a..6f5c716 100644
--- a/drivers/hid/hid-input-test.c
+++ b/drivers/hid/hid-input-test.c
@@ -7,7 +7,7 @@
 
 #include <kunit/test.h>
 
-static void hid_test_input_set_battery_charge_status(struct kunit *test)
+static void hid_test_input_update_battery_charge_status(struct kunit *test)
 {
 	struct hid_device *dev;
 	bool handled;
@@ -15,15 +15,15 @@ static void hid_test_input_set_battery_charge_status(struct kunit *test)
 	dev = kunit_kzalloc(test, sizeof(*dev), GFP_KERNEL);
 	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, dev);
 
-	handled = hidinput_set_battery_charge_status(dev, HID_DG_HEIGHT, 0);
+	handled = hidinput_update_battery_charge_status(dev, HID_DG_HEIGHT, 0);
 	KUNIT_EXPECT_FALSE(test, handled);
 	KUNIT_EXPECT_EQ(test, dev->battery_charge_status, POWER_SUPPLY_STATUS_UNKNOWN);
 
-	handled = hidinput_set_battery_charge_status(dev, HID_BAT_CHARGING, 0);
+	handled = hidinput_update_battery_charge_status(dev, HID_BAT_CHARGING, 0);
 	KUNIT_EXPECT_TRUE(test, handled);
 	KUNIT_EXPECT_EQ(test, dev->battery_charge_status, POWER_SUPPLY_STATUS_DISCHARGING);
 
-	handled = hidinput_set_battery_charge_status(dev, HID_BAT_CHARGING, 1);
+	handled = hidinput_update_battery_charge_status(dev, HID_BAT_CHARGING, 1);
 	KUNIT_EXPECT_TRUE(test, handled);
 	KUNIT_EXPECT_EQ(test, dev->battery_charge_status, POWER_SUPPLY_STATUS_CHARGING);
 }
@@ -63,7 +63,7 @@ static void hid_test_input_get_battery_property(struct kunit *test)
 }
 
 static struct kunit_case hid_input_tests[] = {
-	KUNIT_CASE(hid_test_input_set_battery_charge_status),
+	KUNIT_CASE(hid_test_input_update_battery_charge_status),
 	KUNIT_CASE(hid_test_input_get_battery_property),
 	{ }
 };
diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c
index ff1784b5..f45f856 100644
--- a/drivers/hid/hid-input.c
+++ b/drivers/hid/hid-input.c
@@ -595,13 +595,33 @@ static void hidinput_cleanup_battery(struct hid_device *dev)
 	dev->battery = NULL;
 }
 
-static void hidinput_update_battery(struct hid_device *dev, int value)
+static bool hidinput_update_battery_charge_status(struct hid_device *dev,
+						  unsigned int usage, int value)
+{
+	switch (usage) {
+	case HID_BAT_CHARGING:
+		dev->battery_charge_status = value ?
+					     POWER_SUPPLY_STATUS_CHARGING :
+					     POWER_SUPPLY_STATUS_DISCHARGING;
+		return true;
+	}
+
+	return false;
+}
+
+static void hidinput_update_battery(struct hid_device *dev, unsigned int usage,
+				    int value)
 {
 	int capacity;
 
 	if (!dev->battery)
 		return;
 
+	if (hidinput_update_battery_charge_status(dev, usage, value)) {
+		power_supply_changed(dev->battery);
+		return;
+	}
+
 	if (value == 0 || value < dev->battery_min || value > dev->battery_max)
 		return;
 
@@ -617,20 +637,6 @@ static void hidinput_update_battery(struct hid_device *dev, int value)
 		power_supply_changed(dev->battery);
 	}
 }
-
-static bool hidinput_set_battery_charge_status(struct hid_device *dev,
-					       unsigned int usage, int value)
-{
-	switch (usage) {
-	case HID_BAT_CHARGING:
-		dev->battery_charge_status = value ?
-					     POWER_SUPPLY_STATUS_CHARGING :
-					     POWER_SUPPLY_STATUS_DISCHARGING;
-		return true;
-	}
-
-	return false;
-}
 #else  /* !CONFIG_HID_BATTERY_STRENGTH */
 static int hidinput_setup_battery(struct hid_device *dev, unsigned report_type,
 				  struct hid_field *field, bool is_percentage)
@@ -642,15 +648,10 @@ static void hidinput_cleanup_battery(struct hid_device *dev)
 {
 }
 
-static void hidinput_update_battery(struct hid_device *dev, int value)
+static void hidinput_update_battery(struct hid_device *dev, unsigned int usage,
+				    int value)
 {
 }
-
-static bool hidinput_set_battery_charge_status(struct hid_device *dev,
-					       unsigned int usage, int value)
-{
-	return false;
-}
 #endif	/* CONFIG_HID_BATTERY_STRENGTH */
 
 static bool hidinput_field_in_collection(struct hid_device *device, struct hid_field *field,
@@ -1515,11 +1516,7 @@ void hidinput_hid_event(struct hid_device *hid, struct hid_field *field, struct
 		return;
 
 	if (usage->type == EV_PWR) {
-		bool handled = hidinput_set_battery_charge_status(hid, usage->hid, value);
-
-		if (!handled)
-			hidinput_update_battery(hid, value);
-
+		hidinput_update_battery(hid, usage->hid, value);
 		return;
 	}
 
diff --git a/drivers/hid/hid-logitech-dj.c b/drivers/hid/hid-logitech-dj.c
index 34fa71c..cce54dd 100644
--- a/drivers/hid/hid-logitech-dj.c
+++ b/drivers/hid/hid-logitech-dj.c
@@ -1983,6 +1983,10 @@ static const struct hid_device_id logi_dj_receivers[] = {
 	  HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH,
 		USB_DEVICE_ID_LOGITECH_NANO_RECEIVER_LIGHTSPEED_1_1),
 	 .driver_data = recvr_type_gaming_hidpp},
+	{ /* Logitech lightspeed receiver (0xc543) */
+	  HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH,
+		USB_DEVICE_ID_LOGITECH_NANO_RECEIVER_LIGHTSPEED_1_2),
+	 .driver_data = recvr_type_gaming_hidpp},
 
 	{ /* Logitech 27 MHz HID++ 1.0 receiver (0xc513) */
 	  HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_MX3000_RECEIVER),
diff --git a/drivers/hid/hid-logitech-hidpp.c b/drivers/hid/hid-logitech-hidpp.c
index 10a3bc5..aaef405 100644
--- a/drivers/hid/hid-logitech-hidpp.c
+++ b/drivers/hid/hid-logitech-hidpp.c
@@ -4596,6 +4596,8 @@ static const struct hid_device_id hidpp_devices[] = {
 	  HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, 0xC094) },
 	{ /* Logitech G Pro X Superlight 2 Gaming Mouse over USB */
 	  HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, 0xC09b) },
+	{ /* Logitech G PRO 2 LIGHTSPEED Wireless Mouse over USB */
+	  HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, 0xc09a) },
 
 	{ /* G935 Gaming Headset */
 	  HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, 0x0a87),
diff --git a/drivers/hid/hid-mcp2221.c b/drivers/hid/hid-mcp2221.c
index 475ac35..33603b0 100644
--- a/drivers/hid/hid-mcp2221.c
+++ b/drivers/hid/hid-mcp2221.c
@@ -906,6 +906,10 @@ static int mcp2221_raw_event(struct hid_device *hdev,
 			}
 			if (data[2] == MCP2221_I2C_READ_COMPL ||
 			    data[2] == MCP2221_I2C_READ_PARTIAL) {
+				if (!mcp->rxbuf || mcp->rxbuf_idx < 0 || data[3] > 60) {
+					mcp->status = -EINVAL;
+					break;
+				}
 				buf = mcp->rxbuf;
 				memcpy(&buf[mcp->rxbuf_idx], &data[4], data[3]);
 				mcp->rxbuf_idx = mcp->rxbuf_idx + data[3];
diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c
index 294516a..22c6314 100644
--- a/drivers/hid/hid-multitouch.c
+++ b/drivers/hid/hid-multitouch.c
@@ -1503,6 +1503,14 @@ static const __u8 *mt_report_fixup(struct hid_device *hdev, __u8 *rdesc,
 	if (hdev->vendor == I2C_VENDOR_ID_GOODIX &&
 	    (hdev->product == I2C_DEVICE_ID_GOODIX_01E8 ||
 	     hdev->product == I2C_DEVICE_ID_GOODIX_01E9)) {
+		if (*size < 608) {
+			dev_info(
+				&hdev->dev,
+				"GT7868Q fixup: report descriptor is only %u bytes, skipping\n",
+				*size);
+			return rdesc;
+		}
+
 		if (rdesc[607] == 0x15) {
 			rdesc[607] = 0x25;
 			dev_info(
diff --git a/drivers/hid/hid-ntrig.c b/drivers/hid/hid-ntrig.c
index 2738ce94..0f76e24 100644
--- a/drivers/hid/hid-ntrig.c
+++ b/drivers/hid/hid-ntrig.c
@@ -144,6 +144,9 @@ static void ntrig_report_version(struct hid_device *hdev)
 	struct usb_device *usb_dev = hid_to_usb_dev(hdev);
 	unsigned char *data = kmalloc(8, GFP_KERNEL);
 
+	if (!hid_is_usb(hdev))
+		return;
+
 	if (!data)
 		goto err_free;
 
diff --git a/drivers/hid/hid-quirks.c b/drivers/hid/hid-quirks.c
index ff11f1a..f619ed1 100644
--- a/drivers/hid/hid-quirks.c
+++ b/drivers/hid/hid-quirks.c
@@ -124,6 +124,8 @@ static const struct hid_device_id hid_quirks[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_MOUSEPEN_I608X_V2), HID_QUIRK_MULTI_INPUT },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_PENSKETCH_T609A), HID_QUIRK_MULTI_INPUT },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LABTEC, USB_DEVICE_ID_LABTEC_ODDOR_HANDBRAKE), HID_QUIRK_ALWAYS_POLL },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_LEGION_GO_DUAL_DINPUT), HID_QUIRK_MULTI_INPUT },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_LEGION_GO2_DUAL_DINPUT), HID_QUIRK_MULTI_INPUT },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_OPTICAL_USB_MOUSE_600E), HID_QUIRK_ALWAYS_POLL },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_PIXART_USB_MOUSE_608D), HID_QUIRK_ALWAYS_POLL },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_PIXART_USB_MOUSE_6019), HID_QUIRK_ALWAYS_POLL },
@@ -411,6 +413,7 @@ static const struct hid_device_id hid_have_special_driver[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_XT4DRBK) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_DT1URBK) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_DT1DRBK) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_DT2DRBK) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_HT1URBK_010C) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_HT1URBK_019B) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_HT1DRBK_010D) },
diff --git a/drivers/hid/intel-ish-hid/ipc/pci-ish.c b/drivers/hid/intel-ish-hid/ipc/pci-ish.c
index c574832..9d150ce 100644
--- a/drivers/hid/intel-ish-hid/ipc/pci-ish.c
+++ b/drivers/hid/intel-ish-hid/ipc/pci-ish.c
@@ -264,9 +264,6 @@ static void ish_shutdown(struct pci_dev *pdev)
 
 static struct device __maybe_unused *ish_resume_device;
 
-/* 50ms to get resume response */
-#define WAIT_FOR_RESUME_ACK_MS		50
-
 /**
  * ish_resume_handler() - Work function to complete resume
  * @work:	work struct
diff --git a/drivers/hid/intel-ish-hid/ishtp-hid-client.c b/drivers/hid/intel-ish-hid/ishtp-hid-client.c
index 6550ad5..d8c3c54 100644
--- a/drivers/hid/intel-ish-hid/ishtp-hid-client.c
+++ b/drivers/hid/intel-ish-hid/ishtp-hid-client.c
@@ -759,6 +759,9 @@ static void hid_ishtp_cl_resume_handler(struct work_struct *work)
 	if (ishtp_wait_resume(ishtp_get_ishtp_device(hid_ishtp_cl))) {
 		client_data->suspended = false;
 		wake_up_interruptible(&client_data->ishtp_resume_wait);
+	} else {
+		hid_ishtp_trace(client_data, "hid client: wait for resume timed out");
+		dev_err(cl_data_to_dev(client_data), "wait for resume timed out");
 	}
 }
 
diff --git a/drivers/hid/intel-ish-hid/ishtp/bus.c b/drivers/hid/intel-ish-hid/ishtp/bus.c
index 5ac7d70..93a0432 100644
--- a/drivers/hid/intel-ish-hid/ishtp/bus.c
+++ b/drivers/hid/intel-ish-hid/ishtp/bus.c
@@ -852,9 +852,6 @@ EXPORT_SYMBOL(ishtp_device);
  */
 bool ishtp_wait_resume(struct ishtp_device *dev)
 {
-	/* 50ms to get resume response */
-	#define WAIT_FOR_RESUME_ACK_MS		50
-
 	/* Waiting to get resume response */
 	if (dev->resume_flag)
 		wait_event_interruptible_timeout(dev->resume_wait,
diff --git a/drivers/hid/intel-ish-hid/ishtp/ishtp-dev.h b/drivers/hid/intel-ish-hid/ishtp/ishtp-dev.h
index ec9f6e8..23db97e 100644
--- a/drivers/hid/intel-ish-hid/ishtp/ishtp-dev.h
+++ b/drivers/hid/intel-ish-hid/ishtp/ishtp-dev.h
@@ -47,6 +47,9 @@
 
 #define	MAX_DMA_DELAY	20
 
+/* 300ms to get resume response */
+#define WAIT_FOR_RESUME_ACK_MS		300
+
 /* ISHTP device states */
 enum ishtp_dev_state {
 	ISHTP_DEV_INITIALIZING = 0,
diff --git a/drivers/hid/intel-thc-hid/intel-quicki2c/pci-quicki2c.c b/drivers/hid/intel-thc-hid/intel-quicki2c/pci-quicki2c.c
index e944a6c..854926b 100644
--- a/drivers/hid/intel-thc-hid/intel-quicki2c/pci-quicki2c.c
+++ b/drivers/hid/intel-thc-hid/intel-quicki2c/pci-quicki2c.c
@@ -419,6 +419,7 @@ static struct quicki2c_device *quicki2c_dev_init(struct pci_dev *pdev, void __io
  */
 static void quicki2c_dev_deinit(struct quicki2c_device *qcdev)
 {
+	thc_interrupt_quiesce(qcdev->thc_hw, true);
 	thc_interrupt_enable(qcdev->thc_hw, false);
 	thc_ltr_unconfig(qcdev->thc_hw);
 	thc_wot_unconfig(qcdev->thc_hw);
diff --git a/drivers/hid/intel-thc-hid/intel-quicki2c/quicki2c-dev.h b/drivers/hid/intel-thc-hid/intel-quicki2c/quicki2c-dev.h
index 93d6fa9..d412eaf 100644
--- a/drivers/hid/intel-thc-hid/intel-quicki2c/quicki2c-dev.h
+++ b/drivers/hid/intel-thc-hid/intel-quicki2c/quicki2c-dev.h
@@ -77,6 +77,7 @@ struct quicki2c_subip_acpi_parameter {
 	u16 device_address;
 	u64 connection_speed;
 	u8 addressing_mode;
+	u8 reserved;
 } __packed;
 
 /**
@@ -126,6 +127,7 @@ struct quicki2c_subip_acpi_config {
 	u64 HMTD;
 	u64 HMRD;
 	u64 HMSL;
+	u8 reserved;
 };
 
 /**
diff --git a/drivers/hid/intel-thc-hid/intel-thc/intel-thc-dev.c b/drivers/hid/intel-thc-hid/intel-thc/intel-thc-dev.c
index 6f22638..e1cb9b1 100644
--- a/drivers/hid/intel-thc-hid/intel-thc/intel-thc-dev.c
+++ b/drivers/hid/intel-thc-hid/intel-thc/intel-thc-dev.c
@@ -1540,7 +1540,7 @@ int thc_i2c_subip_regs_save(struct thc_device *dev)
 
 	for (int i = 0; i < ARRAY_SIZE(i2c_subip_regs); i++) {
 		ret = thc_i2c_subip_pio_read(dev, i2c_subip_regs[i],
-					     &read_size, (u32 *)&dev->i2c_subip_regs + i);
+					     &read_size, &dev->i2c_subip_regs[i]);
 		if (ret < 0)
 			return ret;
 	}
@@ -1563,7 +1563,7 @@ int thc_i2c_subip_regs_restore(struct thc_device *dev)
 
 	for (int i = 0; i < ARRAY_SIZE(i2c_subip_regs); i++) {
 		ret = thc_i2c_subip_pio_write(dev, i2c_subip_regs[i],
-					      write_size, (u32 *)&dev->i2c_subip_regs + i);
+					      write_size, &dev->i2c_subip_regs[i]);
 		if (ret < 0)
 			return ret;
 	}
diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c
index 955b39d..9b2c710 100644
--- a/drivers/hid/wacom_wac.c
+++ b/drivers/hid/wacom_wac.c
@@ -684,6 +684,7 @@ static bool wacom_is_art_pen(int tool_id)
 	case 0x885:	/* Intuos3 Marker Pen */
 	case 0x804:	/* Intuos4/5 13HD/24HD Marker Pen */
 	case 0x10804:	/* Intuos4/5 13HD/24HD Art Pen */
+	case 0x204:     /* Art Pen 2 */
 		is_art_pen = true;
 		break;
 	}
diff --git a/drivers/irqchip/irq-atmel-aic.c b/drivers/irqchip/irq-atmel-aic.c
index 03aeed3..1dcc527 100644
--- a/drivers/irqchip/irq-atmel-aic.c
+++ b/drivers/irqchip/irq-atmel-aic.c
@@ -188,7 +188,7 @@ static int aic_irq_domain_xlate(struct irq_domain *d,
 
 	gc = dgc->gc[idx];
 
-	guard(raw_spinlock_irq)(&gc->lock);
+	guard(raw_spinlock_irqsave)(&gc->lock);
 	smr = irq_reg_readl(gc, AT91_AIC_SMR(*out_hwirq));
 	aic_common_set_priority(intspec[2], &smr);
 	irq_reg_writel(gc, smr, AT91_AIC_SMR(*out_hwirq));
diff --git a/drivers/irqchip/irq-atmel-aic5.c b/drivers/irqchip/irq-atmel-aic5.c
index 60b00d2..1f14b40 100644
--- a/drivers/irqchip/irq-atmel-aic5.c
+++ b/drivers/irqchip/irq-atmel-aic5.c
@@ -279,7 +279,7 @@ static int aic5_irq_domain_xlate(struct irq_domain *d,
 	if (ret)
 		return ret;
 
-	guard(raw_spinlock_irq)(&bgc->lock);
+	guard(raw_spinlock_irqsave)(&bgc->lock);
 	irq_reg_writel(bgc, *out_hwirq, AT91_AIC5_SSR);
 	smr = irq_reg_readl(bgc, AT91_AIC5_SMR);
 	aic_common_set_priority(intspec[2], &smr);
diff --git a/drivers/irqchip/irq-gic-v5-irs.c b/drivers/irqchip/irq-gic-v5-irs.c
index f845415..13c0357 100644
--- a/drivers/irqchip/irq-gic-v5-irs.c
+++ b/drivers/irqchip/irq-gic-v5-irs.c
@@ -5,6 +5,7 @@
 
 #define pr_fmt(fmt)	"GICv5 IRS: " fmt
 
+#include <linux/kmemleak.h>
 #include <linux/log2.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
@@ -117,6 +118,7 @@ static int __init gicv5_irs_init_ist_linear(struct gicv5_irs_chip_data *irs_data
 		kfree(ist);
 		return ret;
 	}
+	kmemleak_ignore(ist);
 
 	return 0;
 }
@@ -232,6 +234,7 @@ int gicv5_irs_iste_alloc(const u32 lpi)
 		kfree(l2ist);
 		return ret;
 	}
+	kmemleak_ignore(l2ist);
 
 	/*
 	 * Make sure we invalidate the cache line pulled before the IRS
@@ -623,12 +626,14 @@ static int __init gicv5_irs_of_init_affinity(struct device_node *node,
 		int cpu;
 
 		cpu_node = of_parse_phandle(node, "cpus", i);
-		if (WARN_ON(!cpu_node))
+		if (!cpu_node) {
+			pr_warn(FW_BUG "Erroneous CPU node phandle\n");
 			continue;
+		}
 
 		cpu = of_cpu_node_to_id(cpu_node);
 		of_node_put(cpu_node);
-		if (WARN_ON(cpu < 0))
+		if (cpu < 0)
 			continue;
 
 		if (iaffids[i] & ~iaffid_mask) {
diff --git a/drivers/irqchip/irq-mvebu-gicp.c b/drivers/irqchip/irq-mvebu-gicp.c
index 5483371..667bde3 100644
--- a/drivers/irqchip/irq-mvebu-gicp.c
+++ b/drivers/irqchip/irq-mvebu-gicp.c
@@ -238,7 +238,7 @@ static int mvebu_gicp_probe(struct platform_device *pdev)
 	}
 
 	base = ioremap(gicp->res->start, resource_size(gicp->res));
-	if (IS_ERR(base)) {
+	if (!base) {
 		dev_err(&pdev->dev, "ioremap() failed. Unable to clear pending interrupts.\n");
 	} else {
 		for (i = 0; i < 64; i++)
diff --git a/drivers/isdn/hardware/mISDN/hfcpci.c b/drivers/isdn/hardware/mISDN/hfcpci.c
index 2b05722..ea8a0ab 100644
--- a/drivers/isdn/hardware/mISDN/hfcpci.c
+++ b/drivers/isdn/hardware/mISDN/hfcpci.c
@@ -39,12 +39,13 @@
 
 #include "hfc_pci.h"
 
+static void hfcpci_softirq(struct timer_list *unused);
 static const char *hfcpci_revision = "2.0";
 
 static int HFC_cnt;
 static uint debug;
 static uint poll, tics;
-static struct timer_list hfc_tl;
+static DEFINE_TIMER(hfc_tl, hfcpci_softirq);
 static unsigned long hfc_jiffies;
 
 MODULE_AUTHOR("Karsten Keil");
@@ -2305,8 +2306,7 @@ hfcpci_softirq(struct timer_list *unused)
 		hfc_jiffies = jiffies + 1;
 	else
 		hfc_jiffies += tics;
-	hfc_tl.expires = hfc_jiffies;
-	add_timer(&hfc_tl);
+	mod_timer(&hfc_tl, hfc_jiffies);
 }
 
 static int __init
@@ -2332,10 +2332,8 @@ HFC_init(void)
 	if (poll != HFCPCI_BTRANS_THRESHOLD) {
 		printk(KERN_INFO "%s: Using alternative poll value of %d\n",
 		       __func__, poll);
-		timer_setup(&hfc_tl, hfcpci_softirq, 0);
-		hfc_tl.expires = jiffies + tics;
-		hfc_jiffies = hfc_tl.expires;
-		add_timer(&hfc_tl);
+		hfc_jiffies = jiffies + tics;
+		mod_timer(&hfc_tl, hfc_jiffies);
 	} else
 		tics = 0; /* indicate the use of controller's timer */
 
diff --git a/drivers/media/i2c/alvium-csi2.c b/drivers/media/i2c/alvium-csi2.c
index 05b708bd..1f088ac 100644
--- a/drivers/media/i2c/alvium-csi2.c
+++ b/drivers/media/i2c/alvium-csi2.c
@@ -1841,7 +1841,6 @@ static int alvium_s_stream(struct v4l2_subdev *sd, int enable)
 
 	} else {
 		alvium_set_stream_mipi(alvium, enable);
-		pm_runtime_mark_last_busy(&client->dev);
 		pm_runtime_put_autosuspend(&client->dev);
 	}
 
diff --git a/drivers/media/i2c/ccs/ccs-core.c b/drivers/media/i2c/ccs/ccs-core.c
index 487bcab..1c889c8 100644
--- a/drivers/media/i2c/ccs/ccs-core.c
+++ b/drivers/media/i2c/ccs/ccs-core.c
@@ -787,10 +787,8 @@ static int ccs_set_ctrl(struct v4l2_ctrl *ctrl)
 		rval = -EINVAL;
 	}
 
-	if (pm_status > 0) {
-		pm_runtime_mark_last_busy(&client->dev);
+	if (pm_status > 0)
 		pm_runtime_put_autosuspend(&client->dev);
-	}
 
 	return rval;
 }
@@ -1914,7 +1912,6 @@ static int ccs_set_stream(struct v4l2_subdev *subdev, int enable)
 	if (!enable) {
 		ccs_stop_streaming(sensor);
 		sensor->streaming = false;
-		pm_runtime_mark_last_busy(&client->dev);
 		pm_runtime_put_autosuspend(&client->dev);
 
 		return 0;
@@ -1929,7 +1926,6 @@ static int ccs_set_stream(struct v4l2_subdev *subdev, int enable)
 	rval = ccs_start_streaming(sensor);
 	if (rval < 0) {
 		sensor->streaming = false;
-		pm_runtime_mark_last_busy(&client->dev);
 		pm_runtime_put_autosuspend(&client->dev);
 	}
 
@@ -2677,7 +2673,6 @@ nvm_show(struct device *dev, struct device_attribute *attr, char *buf)
 		return -ENODEV;
 	}
 
-	pm_runtime_mark_last_busy(&client->dev);
 	pm_runtime_put_autosuspend(&client->dev);
 
 	/*
diff --git a/drivers/media/i2c/dw9768.c b/drivers/media/i2c/dw9768.c
index 3a4d100..d434721 100644
--- a/drivers/media/i2c/dw9768.c
+++ b/drivers/media/i2c/dw9768.c
@@ -374,7 +374,6 @@ static int dw9768_open(struct v4l2_subdev *sd, struct v4l2_subdev_fh *fh)
 
 static int dw9768_close(struct v4l2_subdev *sd, struct v4l2_subdev_fh *fh)
 {
-	pm_runtime_mark_last_busy(sd->dev);
 	pm_runtime_put_autosuspend(sd->dev);
 
 	return 0;
diff --git a/drivers/media/i2c/gc0308.c b/drivers/media/i2c/gc0308.c
index 069f427..cbcda0e 100644
--- a/drivers/media/i2c/gc0308.c
+++ b/drivers/media/i2c/gc0308.c
@@ -974,7 +974,6 @@ static int gc0308_s_ctrl(struct v4l2_ctrl *ctrl)
 	if (ret)
 		dev_err(gc0308->dev, "failed to set control: %d\n", ret);
 
-	pm_runtime_mark_last_busy(gc0308->dev);
 	pm_runtime_put_autosuspend(gc0308->dev);
 
 	return ret;
@@ -1157,14 +1156,12 @@ static int gc0308_start_stream(struct gc0308 *gc0308)
 	return 0;
 
 disable_pm:
-	pm_runtime_mark_last_busy(gc0308->dev);
 	pm_runtime_put_autosuspend(gc0308->dev);
 	return ret;
 }
 
 static int gc0308_stop_stream(struct gc0308 *gc0308)
 {
-	pm_runtime_mark_last_busy(gc0308->dev);
 	pm_runtime_put_autosuspend(gc0308->dev);
 	return 0;
 }
diff --git a/drivers/media/i2c/gc2145.c b/drivers/media/i2c/gc2145.c
index ba02161..559a851 100644
--- a/drivers/media/i2c/gc2145.c
+++ b/drivers/media/i2c/gc2145.c
@@ -963,7 +963,6 @@ static int gc2145_enable_streams(struct v4l2_subdev *sd,
 	return 0;
 
 err_rpm_put:
-	pm_runtime_mark_last_busy(&client->dev);
 	pm_runtime_put_autosuspend(&client->dev);
 	return ret;
 }
@@ -985,7 +984,6 @@ static int gc2145_disable_streams(struct v4l2_subdev *sd,
 	if (ret)
 		dev_err(&client->dev, "%s failed to write regs\n", __func__);
 
-	pm_runtime_mark_last_busy(&client->dev);
 	pm_runtime_put_autosuspend(&client->dev);
 
 	return ret;
@@ -1193,7 +1191,6 @@ static int gc2145_s_ctrl(struct v4l2_ctrl *ctrl)
 		break;
 	}
 
-	pm_runtime_mark_last_busy(&client->dev);
 	pm_runtime_put_autosuspend(&client->dev);
 
 	return ret;
diff --git a/drivers/media/i2c/imx219.c b/drivers/media/i2c/imx219.c
index 3b4f685..3faf48f 100644
--- a/drivers/media/i2c/imx219.c
+++ b/drivers/media/i2c/imx219.c
@@ -771,7 +771,6 @@ static int imx219_enable_streams(struct v4l2_subdev *sd,
 	return 0;
 
 err_rpm_put:
-	pm_runtime_mark_last_busy(&client->dev);
 	pm_runtime_put_autosuspend(&client->dev);
 	return ret;
 }
@@ -793,7 +792,6 @@ static int imx219_disable_streams(struct v4l2_subdev *sd,
 	__v4l2_ctrl_grab(imx219->vflip, false);
 	__v4l2_ctrl_grab(imx219->hflip, false);
 
-	pm_runtime_mark_last_busy(&client->dev);
 	pm_runtime_put_autosuspend(&client->dev);
 
 	return ret;
diff --git a/drivers/media/i2c/imx283.c b/drivers/media/i2c/imx283.c
index da618c8..67e8bb4 100644
--- a/drivers/media/i2c/imx283.c
+++ b/drivers/media/i2c/imx283.c
@@ -1143,7 +1143,6 @@ static int imx283_enable_streams(struct v4l2_subdev *sd,
 	return 0;
 
 err_rpm_put:
-	pm_runtime_mark_last_busy(imx283->dev);
 	pm_runtime_put_autosuspend(imx283->dev);
 
 	return ret;
@@ -1163,7 +1162,6 @@ static int imx283_disable_streams(struct v4l2_subdev *sd,
 	if (ret)
 		dev_err(imx283->dev, "Failed to stop stream\n");
 
-	pm_runtime_mark_last_busy(imx283->dev);
 	pm_runtime_put_autosuspend(imx283->dev);
 
 	return ret;
@@ -1558,7 +1556,6 @@ static int imx283_probe(struct i2c_client *client)
 	 * Decrease the PM usage count. The device will get suspended after the
 	 * autosuspend delay, turning the power off.
 	 */
-	pm_runtime_mark_last_busy(imx283->dev);
 	pm_runtime_put_autosuspend(imx283->dev);
 
 	return 0;
diff --git a/drivers/media/i2c/imx290.c b/drivers/media/i2c/imx290.c
index 4f3f386..ec17255 100644
--- a/drivers/media/i2c/imx290.c
+++ b/drivers/media/i2c/imx290.c
@@ -869,7 +869,6 @@ static int imx290_set_ctrl(struct v4l2_ctrl *ctrl)
 		break;
 	}
 
-	pm_runtime_mark_last_busy(imx290->dev);
 	pm_runtime_put_autosuspend(imx290->dev);
 
 	return ret;
@@ -1099,7 +1098,6 @@ static int imx290_set_stream(struct v4l2_subdev *sd, int enable)
 		}
 	} else {
 		imx290_stop_streaming(imx290);
-		pm_runtime_mark_last_busy(imx290->dev);
 		pm_runtime_put_autosuspend(imx290->dev);
 	}
 
@@ -1294,7 +1292,6 @@ static int imx290_subdev_init(struct imx290 *imx290)
 	 * will already be prevented even before the delay.
 	 */
 	v4l2_i2c_subdev_init(&imx290->sd, client, &imx290_subdev_ops);
-	pm_runtime_mark_last_busy(imx290->dev);
 	pm_runtime_put_autosuspend(imx290->dev);
 
 	imx290->sd.internal_ops = &imx290_internal_ops;
diff --git a/drivers/media/i2c/imx296.c b/drivers/media/i2c/imx296.c
index f3bec16..61116f4 100644
--- a/drivers/media/i2c/imx296.c
+++ b/drivers/media/i2c/imx296.c
@@ -604,7 +604,6 @@ static int imx296_s_stream(struct v4l2_subdev *sd, int enable)
 	if (!enable) {
 		ret = imx296_stream_off(sensor);
 
-		pm_runtime_mark_last_busy(sensor->dev);
 		pm_runtime_put_autosuspend(sensor->dev);
 
 		goto unlock;
diff --git a/drivers/media/i2c/imx415.c b/drivers/media/i2c/imx415.c
index 278e743..276bf4d 100644
--- a/drivers/media/i2c/imx415.c
+++ b/drivers/media/i2c/imx415.c
@@ -952,7 +952,6 @@ static int imx415_s_stream(struct v4l2_subdev *sd, int enable)
 	if (!enable) {
 		ret = imx415_stream_off(sensor);
 
-		pm_runtime_mark_last_busy(sensor->dev);
 		pm_runtime_put_autosuspend(sensor->dev);
 
 		goto unlock;
diff --git a/drivers/media/i2c/mt9m114.c b/drivers/media/i2c/mt9m114.c
index 3f540ca..aa3fd6c 100644
--- a/drivers/media/i2c/mt9m114.c
+++ b/drivers/media/i2c/mt9m114.c
@@ -974,7 +974,6 @@ static int mt9m114_start_streaming(struct mt9m114 *sensor,
 	return 0;
 
 error:
-	pm_runtime_mark_last_busy(&sensor->client->dev);
 	pm_runtime_put_autosuspend(&sensor->client->dev);
 
 	return ret;
@@ -988,7 +987,6 @@ static int mt9m114_stop_streaming(struct mt9m114 *sensor)
 
 	ret = mt9m114_set_state(sensor, MT9M114_SYS_STATE_ENTER_SUSPEND);
 
-	pm_runtime_mark_last_busy(&sensor->client->dev);
 	pm_runtime_put_autosuspend(&sensor->client->dev);
 
 	return ret;
@@ -1046,7 +1044,6 @@ static int mt9m114_pa_g_ctrl(struct v4l2_ctrl *ctrl)
 		break;
 	}
 
-	pm_runtime_mark_last_busy(&sensor->client->dev);
 	pm_runtime_put_autosuspend(&sensor->client->dev);
 
 	return ret;
@@ -1113,7 +1110,6 @@ static int mt9m114_pa_s_ctrl(struct v4l2_ctrl *ctrl)
 		break;
 	}
 
-	pm_runtime_mark_last_busy(&sensor->client->dev);
 	pm_runtime_put_autosuspend(&sensor->client->dev);
 
 	return ret;
@@ -1565,7 +1561,6 @@ static int mt9m114_ifp_s_ctrl(struct v4l2_ctrl *ctrl)
 		break;
 	}
 
-	pm_runtime_mark_last_busy(&sensor->client->dev);
 	pm_runtime_put_autosuspend(&sensor->client->dev);
 
 	return ret;
@@ -2472,7 +2467,6 @@ static int mt9m114_probe(struct i2c_client *client)
 	 * Decrease the PM usage count. The device will get suspended after the
 	 * autosuspend delay, turning the power off.
 	 */
-	pm_runtime_mark_last_busy(dev);
 	pm_runtime_put_autosuspend(dev);
 
 	return 0;
diff --git a/drivers/media/i2c/ov4689.c b/drivers/media/i2c/ov4689.c
index 1c3a449..7d740ad 100644
--- a/drivers/media/i2c/ov4689.c
+++ b/drivers/media/i2c/ov4689.c
@@ -497,7 +497,6 @@ static int ov4689_s_stream(struct v4l2_subdev *sd, int on)
 	} else {
 		cci_write(ov4689->regmap, OV4689_REG_CTRL_MODE,
 			  OV4689_MODE_SW_STANDBY, NULL);
-		pm_runtime_mark_last_busy(dev);
 		pm_runtime_put_autosuspend(dev);
 	}
 
@@ -702,7 +701,6 @@ static int ov4689_set_ctrl(struct v4l2_ctrl *ctrl)
 		break;
 	}
 
-	pm_runtime_mark_last_busy(dev);
 	pm_runtime_put_autosuspend(dev);
 
 	return ret;
@@ -999,7 +997,6 @@ static int ov4689_probe(struct i2c_client *client)
 		goto err_clean_subdev_pm;
 	}
 
-	pm_runtime_mark_last_busy(dev);
 	pm_runtime_put_autosuspend(dev);
 
 	return 0;
diff --git a/drivers/media/i2c/ov5640.c b/drivers/media/i2c/ov5640.c
index 0dae043..8419861 100644
--- a/drivers/media/i2c/ov5640.c
+++ b/drivers/media/i2c/ov5640.c
@@ -3341,7 +3341,6 @@ static int ov5640_g_volatile_ctrl(struct v4l2_ctrl *ctrl)
 		break;
 	}
 
-	pm_runtime_mark_last_busy(&sensor->i2c_client->dev);
 	pm_runtime_put_autosuspend(&sensor->i2c_client->dev);
 
 	return 0;
@@ -3417,7 +3416,6 @@ static int ov5640_s_ctrl(struct v4l2_ctrl *ctrl)
 		break;
 	}
 
-	pm_runtime_mark_last_busy(&sensor->i2c_client->dev);
 	pm_runtime_put_autosuspend(&sensor->i2c_client->dev);
 
 	return ret;
@@ -3754,7 +3752,6 @@ static int ov5640_s_stream(struct v4l2_subdev *sd, int enable)
 	mutex_unlock(&sensor->lock);
 
 	if (!enable || ret) {
-		pm_runtime_mark_last_busy(&sensor->i2c_client->dev);
 		pm_runtime_put_autosuspend(&sensor->i2c_client->dev);
 	}
 
@@ -3965,7 +3962,6 @@ static int ov5640_probe(struct i2c_client *client)
 
 	pm_runtime_set_autosuspend_delay(dev, 1000);
 	pm_runtime_use_autosuspend(dev);
-	pm_runtime_mark_last_busy(dev);
 	pm_runtime_put_autosuspend(dev);
 
 	return 0;
diff --git a/drivers/media/i2c/ov5645.c b/drivers/media/i2c/ov5645.c
index 004d0ee..58c846a 100644
--- a/drivers/media/i2c/ov5645.c
+++ b/drivers/media/i2c/ov5645.c
@@ -808,7 +808,6 @@ static int ov5645_s_ctrl(struct v4l2_ctrl *ctrl)
 		break;
 	}
 
-	pm_runtime_mark_last_busy(ov5645->dev);
 	pm_runtime_put_autosuspend(ov5645->dev);
 
 	return ret;
@@ -979,7 +978,6 @@ static int ov5645_disable_streams(struct v4l2_subdev *sd,
 			       OV5645_SYSTEM_CTRL0_STOP);
 
 rpm_put:
-	pm_runtime_mark_last_busy(ov5645->dev);
 	pm_runtime_put_autosuspend(ov5645->dev);
 
 	return ret;
@@ -1196,7 +1194,6 @@ static int ov5645_probe(struct i2c_client *client)
 
 	pm_runtime_set_autosuspend_delay(dev, 1000);
 	pm_runtime_use_autosuspend(dev);
-	pm_runtime_mark_last_busy(dev);
 	pm_runtime_put_autosuspend(dev);
 
 	return 0;
diff --git a/drivers/media/i2c/ov64a40.c b/drivers/media/i2c/ov64a40.c
index a5da4fe..2031cbd 100644
--- a/drivers/media/i2c/ov64a40.c
+++ b/drivers/media/i2c/ov64a40.c
@@ -2990,7 +2990,6 @@ static int ov64a40_start_streaming(struct ov64a40 *ov64a40,
 	return 0;
 
 error_power_off:
-	pm_runtime_mark_last_busy(ov64a40->dev);
 	pm_runtime_put_autosuspend(ov64a40->dev);
 
 	return ret;
@@ -3000,7 +2999,6 @@ static int ov64a40_stop_streaming(struct ov64a40 *ov64a40,
 				  struct v4l2_subdev_state *state)
 {
 	cci_update_bits(ov64a40->cci, OV64A40_REG_SMIA, BIT(0), 0, NULL);
-	pm_runtime_mark_last_busy(ov64a40->dev);
 	pm_runtime_put_autosuspend(ov64a40->dev);
 
 	__v4l2_ctrl_grab(ov64a40->link_freq, false);
@@ -3329,10 +3327,8 @@ static int ov64a40_set_ctrl(struct v4l2_ctrl *ctrl)
 		break;
 	}
 
-	if (pm_status > 0) {
-		pm_runtime_mark_last_busy(ov64a40->dev);
+	if (pm_status > 0)
 		pm_runtime_put_autosuspend(ov64a40->dev);
-	}
 
 	return ret;
 }
@@ -3622,7 +3618,6 @@ static int ov64a40_probe(struct i2c_client *client)
 		goto error_subdev_cleanup;
 	}
 
-	pm_runtime_mark_last_busy(&client->dev);
 	pm_runtime_put_autosuspend(&client->dev);
 
 	return 0;
diff --git a/drivers/media/i2c/ov8858.c b/drivers/media/i2c/ov8858.c
index 95f9ae7..6b7193e 100644
--- a/drivers/media/i2c/ov8858.c
+++ b/drivers/media/i2c/ov8858.c
@@ -1391,7 +1391,6 @@ static int ov8858_s_stream(struct v4l2_subdev *sd, int on)
 		}
 	} else {
 		ov8858_stop_stream(ov8858);
-		pm_runtime_mark_last_busy(&client->dev);
 		pm_runtime_put_autosuspend(&client->dev);
 	}
 
@@ -1945,7 +1944,6 @@ static int ov8858_probe(struct i2c_client *client)
 		goto err_power_off;
 	}
 
-	pm_runtime_mark_last_busy(dev);
 	pm_runtime_put_autosuspend(dev);
 
 	return 0;
diff --git a/drivers/media/i2c/st-mipid02.c b/drivers/media/i2c/st-mipid02.c
index f4568e8..41ae25b 100644
--- a/drivers/media/i2c/st-mipid02.c
+++ b/drivers/media/i2c/st-mipid02.c
@@ -465,7 +465,6 @@ static int mipid02_disable_streams(struct v4l2_subdev *sd,
 	if (ret)
 		goto error;
 
-	pm_runtime_mark_last_busy(&client->dev);
 	pm_runtime_put_autosuspend(&client->dev);
 
 error:
@@ -542,7 +541,6 @@ static int mipid02_enable_streams(struct v4l2_subdev *sd,
 	cci_write(bridge->regmap, MIPID02_DATA_LANE0_REG1, 0, &ret);
 	cci_write(bridge->regmap, MIPID02_DATA_LANE1_REG1, 0, &ret);
 
-	pm_runtime_mark_last_busy(&client->dev);
 	pm_runtime_put_autosuspend(&client->dev);
 	return ret;
 }
diff --git a/drivers/media/i2c/tc358746.c b/drivers/media/i2c/tc358746.c
index 143aa13..bcfc274 100644
--- a/drivers/media/i2c/tc358746.c
+++ b/drivers/media/i2c/tc358746.c
@@ -816,7 +816,6 @@ static int tc358746_s_stream(struct v4l2_subdev *sd, int enable)
 		return 0;
 
 err_out:
-		pm_runtime_mark_last_busy(sd->dev);
 		pm_runtime_put_sync_autosuspend(sd->dev);
 
 		return err;
@@ -838,7 +837,6 @@ static int tc358746_s_stream(struct v4l2_subdev *sd, int enable)
 	if (err)
 		return err;
 
-	pm_runtime_mark_last_busy(sd->dev);
 	pm_runtime_put_sync_autosuspend(sd->dev);
 
 	return v4l2_subdev_call(src, video, s_stream, 0);
@@ -1016,7 +1014,6 @@ tc358746_g_register(struct v4l2_subdev *sd, struct v4l2_dbg_register *reg)
 	err = tc358746_read(tc358746, reg->reg, &val);
 	reg->val = val;
 
-	pm_runtime_mark_last_busy(sd->dev);
 	pm_runtime_put_sync_autosuspend(sd->dev);
 
 	return err;
@@ -1032,7 +1029,6 @@ tc358746_s_register(struct v4l2_subdev *sd, const struct v4l2_dbg_register *reg)
 
 	tc358746_write(tc358746, (u32)reg->reg, (u32)reg->val);
 
-	pm_runtime_mark_last_busy(sd->dev);
 	pm_runtime_put_sync_autosuspend(sd->dev);
 
 	return 0;
@@ -1395,7 +1391,6 @@ static int tc358746_init_hw(struct tc358746 *tc358746)
 	}
 
 	err = tc358746_read(tc358746, CHIPID_REG, &val);
-	pm_runtime_mark_last_busy(dev);
 	pm_runtime_put_sync_autosuspend(dev);
 	if (err)
 		return -ENODEV;
diff --git a/drivers/media/i2c/thp7312.c b/drivers/media/i2c/thp7312.c
index 8852c56..775cfba 100644
--- a/drivers/media/i2c/thp7312.c
+++ b/drivers/media/i2c/thp7312.c
@@ -808,7 +808,6 @@ static int thp7312_s_stream(struct v4l2_subdev *sd, int enable)
 	if (!enable) {
 		thp7312_stream_enable(thp7312, false);
 
-		pm_runtime_mark_last_busy(thp7312->dev);
 		pm_runtime_put_autosuspend(thp7312->dev);
 
 		v4l2_subdev_unlock_state(sd_state);
@@ -839,7 +838,6 @@ static int thp7312_s_stream(struct v4l2_subdev *sd, int enable)
 	goto finish_unlock;
 
 finish_pm:
-	pm_runtime_mark_last_busy(thp7312->dev);
 	pm_runtime_put_autosuspend(thp7312->dev);
 finish_unlock:
 	v4l2_subdev_unlock_state(sd_state);
@@ -1147,7 +1145,6 @@ static int thp7312_s_ctrl(struct v4l2_ctrl *ctrl)
 		break;
 	}
 
-	pm_runtime_mark_last_busy(thp7312->dev);
 	pm_runtime_put_autosuspend(thp7312->dev);
 
 	return ret;
@@ -2183,7 +2180,6 @@ static int thp7312_probe(struct i2c_client *client)
 	 * Decrease the PM usage count. The device will get suspended after the
 	 * autosuspend delay, turning the power off.
 	 */
-	pm_runtime_mark_last_busy(dev);
 	pm_runtime_put_autosuspend(dev);
 
 	dev_info(dev, "THP7312 firmware version %02u.%02u\n",
diff --git a/drivers/media/i2c/vd55g1.c b/drivers/media/i2c/vd55g1.c
index c0754fd..7c39183 100644
--- a/drivers/media/i2c/vd55g1.c
+++ b/drivers/media/i2c/vd55g1.c
@@ -1104,7 +1104,6 @@ static int vd55g1_disable_streams(struct v4l2_subdev *sd,
 
 	vd55g1_grab_ctrls(sensor, false);
 
-	pm_runtime_mark_last_busy(sensor->dev);
 	pm_runtime_put_autosuspend(sensor->dev);
 
 	return ret;
@@ -1338,7 +1337,6 @@ static int vd55g1_g_volatile_ctrl(struct v4l2_ctrl *ctrl)
 		break;
 	}
 
-	pm_runtime_mark_last_busy(sensor->dev);
 	pm_runtime_put_autosuspend(sensor->dev);
 
 	return ret;
@@ -1433,7 +1431,6 @@ static int vd55g1_s_ctrl(struct v4l2_ctrl *ctrl)
 		break;
 	}
 
-	pm_runtime_mark_last_busy(sensor->dev);
 	pm_runtime_put_autosuspend(sensor->dev);
 
 	return ret;
@@ -1895,7 +1892,6 @@ static int vd55g1_probe(struct i2c_client *client)
 	pm_runtime_enable(dev);
 	pm_runtime_set_autosuspend_delay(dev, 4000);
 	pm_runtime_use_autosuspend(dev);
-	pm_runtime_mark_last_busy(dev);
 	pm_runtime_put_autosuspend(dev);
 
 	ret = vd55g1_subdev_init(sensor);
diff --git a/drivers/media/i2c/vd56g3.c b/drivers/media/i2c/vd56g3.c
index 5d951ad0..d66e21b 100644
--- a/drivers/media/i2c/vd56g3.c
+++ b/drivers/media/i2c/vd56g3.c
@@ -493,7 +493,6 @@ static int vd56g3_g_volatile_ctrl(struct v4l2_ctrl *ctrl)
 		break;
 	}
 
-	pm_runtime_mark_last_busy(sensor->dev);
 	pm_runtime_put_autosuspend(sensor->dev);
 
 	return ret;
@@ -577,7 +576,6 @@ static int vd56g3_s_ctrl(struct v4l2_ctrl *ctrl)
 		break;
 	}
 
-	pm_runtime_mark_last_busy(sensor->dev);
 	pm_runtime_put_autosuspend(sensor->dev);
 
 	return ret;
@@ -1021,7 +1019,6 @@ static int vd56g3_disable_streams(struct v4l2_subdev *sd,
 	__v4l2_ctrl_grab(sensor->vflip_ctrl, false);
 	__v4l2_ctrl_grab(sensor->patgen_ctrl, false);
 
-	pm_runtime_mark_last_busy(sensor->dev);
 	pm_runtime_put_autosuspend(sensor->dev);
 
 	return ret;
@@ -1527,7 +1524,6 @@ static int vd56g3_probe(struct i2c_client *client)
 	}
 
 	/* Sensor could now be powered off (after the autosuspend delay) */
-	pm_runtime_mark_last_busy(dev);
 	pm_runtime_put_autosuspend(dev);
 
 	dev_dbg(dev, "Successfully probe %s sensor\n",
diff --git a/drivers/media/i2c/video-i2c.c b/drivers/media/i2c/video-i2c.c
index 0dd991d..1eee2d4 100644
--- a/drivers/media/i2c/video-i2c.c
+++ b/drivers/media/i2c/video-i2c.c
@@ -288,7 +288,6 @@ static int amg88xx_read(struct device *dev, enum hwmon_sensor_types type,
 		return tmp;
 
 	tmp = regmap_bulk_read(data->regmap, AMG88XX_REG_TTHL, &buf, 2);
-	pm_runtime_mark_last_busy(regmap_get_device(data->regmap));
 	pm_runtime_put_autosuspend(regmap_get_device(data->regmap));
 	if (tmp)
 		return tmp;
@@ -527,7 +526,6 @@ static int start_streaming(struct vb2_queue *vq, unsigned int count)
 		return 0;
 
 error_rpm_put:
-	pm_runtime_mark_last_busy(dev);
 	pm_runtime_put_autosuspend(dev);
 error_del_list:
 	video_i2c_del_list(vq, VB2_BUF_STATE_QUEUED);
@@ -544,7 +542,6 @@ static void stop_streaming(struct vb2_queue *vq)
 
 	kthread_stop(data->kthread_vid_cap);
 	data->kthread_vid_cap = NULL;
-	pm_runtime_mark_last_busy(regmap_get_device(data->regmap));
 	pm_runtime_put_autosuspend(regmap_get_device(data->regmap));
 
 	video_i2c_del_list(vq, VB2_BUF_STATE_ERROR);
@@ -853,7 +850,6 @@ static int video_i2c_probe(struct i2c_client *client)
 	if (ret < 0)
 		goto error_pm_disable;
 
-	pm_runtime_mark_last_busy(&client->dev);
 	pm_runtime_put_autosuspend(&client->dev);
 
 	return 0;
diff --git a/drivers/media/platform/chips-media/wave5/wave5-vpu-dec.c b/drivers/media/platform/chips-media/wave5/wave5-vpu-dec.c
index fd71f0c..a9ce032 100644
--- a/drivers/media/platform/chips-media/wave5/wave5-vpu-dec.c
+++ b/drivers/media/platform/chips-media/wave5/wave5-vpu-dec.c
@@ -451,7 +451,6 @@ static void wave5_vpu_dec_finish_decode(struct vpu_instance *inst)
 	if (q_status.report_queue_count == 0 &&
 	    (q_status.instance_queue_count == 0 || dec_info.sequence_changed)) {
 		dev_dbg(inst->dev->dev, "%s: finishing job.\n", __func__);
-		pm_runtime_mark_last_busy(inst->dev->dev);
 		pm_runtime_put_autosuspend(inst->dev->dev);
 		v4l2_m2m_job_finish(inst->v4l2_m2m_dev, m2m_ctx);
 	}
@@ -1364,7 +1363,6 @@ static int wave5_vpu_dec_start_streaming(struct vb2_queue *q, unsigned int count
 		}
 
 	}
-	pm_runtime_mark_last_busy(inst->dev->dev);
 	pm_runtime_put_autosuspend(inst->dev->dev);
 	return ret;
 
@@ -1498,7 +1496,6 @@ static void wave5_vpu_dec_stop_streaming(struct vb2_queue *q)
 	else
 		streamoff_capture(q);
 
-	pm_runtime_mark_last_busy(inst->dev->dev);
 	pm_runtime_put_autosuspend(inst->dev->dev);
 }
 
@@ -1662,7 +1659,6 @@ static void wave5_vpu_dec_device_run(void *priv)
 
 finish_job_and_return:
 	dev_dbg(inst->dev->dev, "%s: leave and finish job", __func__);
-	pm_runtime_mark_last_busy(inst->dev->dev);
 	pm_runtime_put_autosuspend(inst->dev->dev);
 	v4l2_m2m_job_finish(inst->v4l2_m2m_dev, m2m_ctx);
 }
diff --git a/drivers/media/platform/chips-media/wave5/wave5-vpu-enc.c b/drivers/media/platform/chips-media/wave5/wave5-vpu-enc.c
index 1e5fc5f..35913a7 100644
--- a/drivers/media/platform/chips-media/wave5/wave5-vpu-enc.c
+++ b/drivers/media/platform/chips-media/wave5/wave5-vpu-enc.c
@@ -1391,12 +1391,10 @@ static int wave5_vpu_enc_start_streaming(struct vb2_queue *q, unsigned int count
 	if (ret)
 		goto return_buffers;
 
-	pm_runtime_mark_last_busy(inst->dev->dev);
 	pm_runtime_put_autosuspend(inst->dev->dev);
 	return 0;
 return_buffers:
 	wave5_return_bufs(q, VB2_BUF_STATE_QUEUED);
-	pm_runtime_mark_last_busy(inst->dev->dev);
 	pm_runtime_put_autosuspend(inst->dev->dev);
 	return ret;
 }
@@ -1465,7 +1463,6 @@ static void wave5_vpu_enc_stop_streaming(struct vb2_queue *q)
 	else
 		streamoff_capture(inst, q);
 
-	pm_runtime_mark_last_busy(inst->dev->dev);
 	pm_runtime_put_autosuspend(inst->dev->dev);
 }
 
@@ -1520,7 +1517,6 @@ static void wave5_vpu_enc_device_run(void *priv)
 			break;
 		}
 		dev_dbg(inst->dev->dev, "%s: leave with active job", __func__);
-		pm_runtime_mark_last_busy(inst->dev->dev);
 		pm_runtime_put_autosuspend(inst->dev->dev);
 		return;
 	default:
@@ -1529,7 +1525,6 @@ static void wave5_vpu_enc_device_run(void *priv)
 		break;
 	}
 	dev_dbg(inst->dev->dev, "%s: leave and finish job", __func__);
-	pm_runtime_mark_last_busy(inst->dev->dev);
 	pm_runtime_put_autosuspend(inst->dev->dev);
 	v4l2_m2m_job_finish(inst->v4l2_m2m_dev, m2m_ctx);
 }
diff --git a/drivers/media/platform/nvidia/tegra-vde/h264.c b/drivers/media/platform/nvidia/tegra-vde/h264.c
index 0e56a43..45f8f690 100644
--- a/drivers/media/platform/nvidia/tegra-vde/h264.c
+++ b/drivers/media/platform/nvidia/tegra-vde/h264.c
@@ -585,7 +585,6 @@ static int tegra_vde_decode_begin(struct tegra_vde *vde,
 	return 0;
 
 put_runtime_pm:
-	pm_runtime_mark_last_busy(dev);
 	pm_runtime_put_autosuspend(dev);
 
 unlock:
@@ -612,7 +611,6 @@ static void tegra_vde_decode_abort(struct tegra_vde *vde)
 	if (err)
 		dev_err(dev, "DEC end: Failed to assert HW reset: %d\n", err);
 
-	pm_runtime_mark_last_busy(dev);
 	pm_runtime_put_autosuspend(dev);
 
 	mutex_unlock(&vde->lock);
diff --git a/drivers/media/platform/qcom/iris/iris_hfi_queue.c b/drivers/media/platform/qcom/iris/iris_hfi_queue.c
index 221dcd0..b3ed062 100644
--- a/drivers/media/platform/qcom/iris/iris_hfi_queue.c
+++ b/drivers/media/platform/qcom/iris/iris_hfi_queue.c
@@ -142,7 +142,6 @@ int iris_hfi_queue_cmd_write(struct iris_core *core, void *pkt, u32 pkt_size)
 	}
 	mutex_unlock(&core->lock);
 
-	pm_runtime_mark_last_busy(core->dev);
 	pm_runtime_put_autosuspend(core->dev);
 
 	return 0;
diff --git a/drivers/media/platform/raspberrypi/pisp_be/pisp_be.c b/drivers/media/platform/raspberrypi/pisp_be/pisp_be.c
index b308917..d60d92d 100644
--- a/drivers/media/platform/raspberrypi/pisp_be/pisp_be.c
+++ b/drivers/media/platform/raspberrypi/pisp_be/pisp_be.c
@@ -950,7 +950,6 @@ static void pispbe_node_stop_streaming(struct vb2_queue *q)
 		kfree(job);
 	}
 
-	pm_runtime_mark_last_busy(pispbe->dev);
 	pm_runtime_put_autosuspend(pispbe->dev);
 
 	dev_dbg(pispbe->dev, "Nodes streaming now 0x%x\n",
@@ -1742,7 +1741,6 @@ static int pispbe_probe(struct platform_device *pdev)
 	if (ret)
 		goto disable_devs_err;
 
-	pm_runtime_mark_last_busy(pispbe->dev);
 	pm_runtime_put_autosuspend(pispbe->dev);
 
 	return 0;
diff --git a/drivers/media/platform/rockchip/rkvdec/rkvdec.c b/drivers/media/platform/rockchip/rkvdec/rkvdec.c
index d707088..d3b31f4 100644
--- a/drivers/media/platform/rockchip/rkvdec/rkvdec.c
+++ b/drivers/media/platform/rockchip/rkvdec/rkvdec.c
@@ -765,7 +765,6 @@ static void rkvdec_job_finish(struct rkvdec_ctx *ctx,
 {
 	struct rkvdec_dev *rkvdec = ctx->dev;
 
-	pm_runtime_mark_last_busy(rkvdec->dev);
 	pm_runtime_put_autosuspend(rkvdec->dev);
 	rkvdec_job_finish_no_pm(ctx, result);
 }
@@ -1159,13 +1158,6 @@ static int rkvdec_probe(struct platform_device *pdev)
 		return ret;
 	}
 
-	if (iommu_get_domain_for_dev(&pdev->dev)) {
-		rkvdec->empty_domain = iommu_paging_domain_alloc(rkvdec->dev);
-
-		if (!rkvdec->empty_domain)
-			dev_warn(rkvdec->dev, "cannot alloc new empty domain\n");
-	}
-
 	vb2_dma_contig_set_max_seg_size(&pdev->dev, DMA_BIT_MASK(32));
 
 	irq = platform_get_irq(pdev, 0);
@@ -1188,6 +1180,15 @@ static int rkvdec_probe(struct platform_device *pdev)
 	if (ret)
 		goto err_disable_runtime_pm;
 
+	if (iommu_get_domain_for_dev(&pdev->dev)) {
+		rkvdec->empty_domain = iommu_paging_domain_alloc(rkvdec->dev);
+
+		if (IS_ERR(rkvdec->empty_domain)) {
+			rkvdec->empty_domain = NULL;
+			dev_warn(rkvdec->dev, "cannot alloc new empty domain\n");
+		}
+	}
+
 	return 0;
 
 err_disable_runtime_pm:
diff --git a/drivers/media/platform/verisilicon/hantro_drv.c b/drivers/media/platform/verisilicon/hantro_drv.c
index 8542238..fa972ef 100644
--- a/drivers/media/platform/verisilicon/hantro_drv.c
+++ b/drivers/media/platform/verisilicon/hantro_drv.c
@@ -89,7 +89,6 @@ static void hantro_job_finish(struct hantro_dev *vpu,
 			      struct hantro_ctx *ctx,
 			      enum vb2_buffer_state result)
 {
-	pm_runtime_mark_last_busy(vpu->dev);
 	pm_runtime_put_autosuspend(vpu->dev);
 
 	clk_bulk_disable(vpu->variant->num_clocks, vpu->clocks);
diff --git a/drivers/media/rc/gpio-ir-recv.c b/drivers/media/rc/gpio-ir-recv.c
index bf6d8fa..a6418ef 100644
--- a/drivers/media/rc/gpio-ir-recv.c
+++ b/drivers/media/rc/gpio-ir-recv.c
@@ -48,10 +48,8 @@ static irqreturn_t gpio_ir_recv_irq(int irq, void *dev_id)
 	if (val >= 0)
 		ir_raw_event_store_edge(gpio_dev->rcdev, val == 1);
 
-	if (pmdev) {
-		pm_runtime_mark_last_busy(pmdev);
+	if (pmdev)
 		pm_runtime_put_autosuspend(pmdev);
-	}
 
 	return IRQ_HANDLED;
 }
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 207a8bb3..31e3d82 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -8016,7 +8016,8 @@ static int __bnxt_reserve_rings(struct bnxt *bp)
 	}
 	rx_rings = min_t(int, rx_rings, hwr.grp);
 	hwr.cp = min_t(int, hwr.cp, bp->cp_nr_rings);
-	if (hwr.stat > bnxt_get_ulp_stat_ctxs(bp))
+	if (bnxt_ulp_registered(bp->edev) &&
+	    hwr.stat > bnxt_get_ulp_stat_ctxs(bp))
 		hwr.stat -= bnxt_get_ulp_stat_ctxs(bp);
 	hwr.cp = min_t(int, hwr.cp, hwr.stat);
 	rc = bnxt_trim_rings(bp, &rx_rings, &hwr.tx, hwr.cp, sh);
@@ -8024,6 +8025,11 @@ static int __bnxt_reserve_rings(struct bnxt *bp)
 		hwr.rx = rx_rings << 1;
 	tx_cp = bnxt_num_tx_to_cp(bp, hwr.tx);
 	hwr.cp = sh ? max_t(int, tx_cp, rx_rings) : tx_cp + rx_rings;
+	if (hwr.tx != bp->tx_nr_rings) {
+		netdev_warn(bp->dev,
+			    "Able to reserve only %d out of %d requested TX rings\n",
+			    hwr.tx, bp->tx_nr_rings);
+	}
 	bp->tx_nr_rings = hwr.tx;
 
 	/* If we cannot reserve all the RX rings, reset the RSS map only
@@ -12851,6 +12857,17 @@ static int bnxt_set_xps_mapping(struct bnxt *bp)
 	return rc;
 }
 
+static int bnxt_tx_nr_rings(struct bnxt *bp)
+{
+	return bp->num_tc ? bp->tx_nr_rings_per_tc * bp->num_tc :
+			    bp->tx_nr_rings_per_tc;
+}
+
+static int bnxt_tx_nr_rings_per_tc(struct bnxt *bp)
+{
+	return bp->num_tc ? bp->tx_nr_rings / bp->num_tc : bp->tx_nr_rings;
+}
+
 static int __bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init)
 {
 	int rc = 0;
@@ -12868,6 +12885,13 @@ static int __bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init)
 	if (rc)
 		return rc;
 
+	/* Make adjustments if reserved TX rings are less than requested */
+	bp->tx_nr_rings -= bp->tx_nr_rings_xdp;
+	bp->tx_nr_rings_per_tc = bnxt_tx_nr_rings_per_tc(bp);
+	if (bp->tx_nr_rings_xdp) {
+		bp->tx_nr_rings_xdp = bp->tx_nr_rings_per_tc;
+		bp->tx_nr_rings += bp->tx_nr_rings_xdp;
+	}
 	rc = bnxt_alloc_mem(bp, irq_re_init);
 	if (rc) {
 		netdev_err(bp->dev, "bnxt_alloc_mem err: %x\n", rc);
@@ -16325,7 +16349,7 @@ static void bnxt_trim_dflt_sh_rings(struct bnxt *bp)
 	bp->cp_nr_rings = min_t(int, bp->tx_nr_rings_per_tc, bp->rx_nr_rings);
 	bp->rx_nr_rings = bp->cp_nr_rings;
 	bp->tx_nr_rings_per_tc = bp->cp_nr_rings;
-	bp->tx_nr_rings = bp->tx_nr_rings_per_tc;
+	bp->tx_nr_rings = bnxt_tx_nr_rings(bp);
 }
 
 static int bnxt_set_dflt_rings(struct bnxt *bp, bool sh)
@@ -16357,7 +16381,7 @@ static int bnxt_set_dflt_rings(struct bnxt *bp, bool sh)
 		bnxt_trim_dflt_sh_rings(bp);
 	else
 		bp->cp_nr_rings = bp->tx_nr_rings_per_tc + bp->rx_nr_rings;
-	bp->tx_nr_rings = bp->tx_nr_rings_per_tc;
+	bp->tx_nr_rings = bnxt_tx_nr_rings(bp);
 
 	avail_msix = bnxt_get_max_func_irqs(bp) - bp->cp_nr_rings;
 	if (avail_msix >= BNXT_MIN_ROCE_CP_RINGS) {
@@ -16370,7 +16394,7 @@ static int bnxt_set_dflt_rings(struct bnxt *bp, bool sh)
 	rc = __bnxt_reserve_rings(bp);
 	if (rc && rc != -ENODEV)
 		netdev_warn(bp->dev, "Unable to reserve tx rings\n");
-	bp->tx_nr_rings_per_tc = bp->tx_nr_rings;
+	bp->tx_nr_rings_per_tc = bnxt_tx_nr_rings_per_tc(bp);
 	if (sh)
 		bnxt_trim_dflt_sh_rings(bp);
 
@@ -16379,7 +16403,7 @@ static int bnxt_set_dflt_rings(struct bnxt *bp, bool sh)
 		rc = __bnxt_reserve_rings(bp);
 		if (rc && rc != -ENODEV)
 			netdev_warn(bp->dev, "2nd rings reservation failed.\n");
-		bp->tx_nr_rings_per_tc = bp->tx_nr_rings;
+		bp->tx_nr_rings_per_tc = bnxt_tx_nr_rings_per_tc(bp);
 	}
 	if (BNXT_CHIP_TYPE_NITRO_A0(bp)) {
 		bp->rx_nr_rings++;
@@ -16413,7 +16437,7 @@ static int bnxt_init_dflt_ring_mode(struct bnxt *bp)
 	if (rc)
 		goto init_dflt_ring_err;
 
-	bp->tx_nr_rings_per_tc = bp->tx_nr_rings;
+	bp->tx_nr_rings_per_tc = bnxt_tx_nr_rings_per_tc(bp);
 
 	bnxt_set_dflt_rfs(bp);
 
diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index 9693f02..16d28a8 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -3090,7 +3090,7 @@ static void gem_update_stats(struct macb *bp)
 			/* Add GEM_OCTTXH, GEM_OCTRXH */
 			val = bp->macb_reg_readl(bp, offset + 4);
 			bp->ethtool_stats[i] += ((u64)val) << 32;
-			*(p++) += ((u64)val) << 32;
+			*p += ((u64)val) << 32;
 		}
 	}
 
@@ -5399,19 +5399,16 @@ static void macb_remove(struct platform_device *pdev)
 
 	if (dev) {
 		bp = netdev_priv(dev);
+		unregister_netdev(dev);
 		phy_exit(bp->sgmii_phy);
 		mdiobus_unregister(bp->mii_bus);
 		mdiobus_free(bp->mii_bus);
 
-		unregister_netdev(dev);
+		device_set_wakeup_enable(&bp->pdev->dev, 0);
 		cancel_work_sync(&bp->hresp_err_bh_work);
 		pm_runtime_disable(&pdev->dev);
 		pm_runtime_dont_use_autosuspend(&pdev->dev);
-		if (!pm_runtime_suspended(&pdev->dev)) {
-			macb_clks_disable(bp->pclk, bp->hclk, bp->tx_clk,
-					  bp->rx_clk, bp->tsu_clk);
-			pm_runtime_set_suspended(&pdev->dev);
-		}
+		pm_runtime_set_suspended(&pdev->dev);
 		phylink_destroy(bp->phylink);
 		free_netdev(dev);
 	}
diff --git a/drivers/net/ethernet/dlink/dl2k.c b/drivers/net/ethernet/dlink/dl2k.c
index cc60ee4..6bbf6e5 100644
--- a/drivers/net/ethernet/dlink/dl2k.c
+++ b/drivers/net/ethernet/dlink/dl2k.c
@@ -1099,7 +1099,7 @@ get_stats (struct net_device *dev)
 	dev->stats.rx_bytes += dr32(OctetRcvOk);
 	dev->stats.tx_bytes += dr32(OctetXmtOk);
 
-	dev->stats.multicast = dr32(McstFramesRcvdOk);
+	dev->stats.multicast += dr32(McstFramesRcvdOk);
 	dev->stats.collisions += dr32(SingleColFrames)
 			     +  dr32(MultiColFrames);
 
diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h
index 2098f00..8a8a01a 100644
--- a/drivers/net/ethernet/intel/ice/ice.h
+++ b/drivers/net/ethernet/intel/ice/ice.h
@@ -510,6 +510,7 @@ enum ice_pf_flags {
 	ICE_FLAG_LINK_LENIENT_MODE_ENA,
 	ICE_FLAG_PLUG_AUX_DEV,
 	ICE_FLAG_UNPLUG_AUX_DEV,
+	ICE_FLAG_AUX_DEV_CREATED,
 	ICE_FLAG_MTU_CHANGED,
 	ICE_FLAG_GNSS,			/* GNSS successfully initialized */
 	ICE_FLAG_DPLL,			/* SyncE/PTP dplls initialized */
diff --git a/drivers/net/ethernet/intel/ice/ice_adapter.c b/drivers/net/ethernet/intel/ice/ice_adapter.c
index 9e4adc4..b53561c 100644
--- a/drivers/net/ethernet/intel/ice/ice_adapter.c
+++ b/drivers/net/ethernet/intel/ice/ice_adapter.c
@@ -13,16 +13,45 @@
 static DEFINE_XARRAY(ice_adapters);
 static DEFINE_MUTEX(ice_adapters_mutex);
 
-static unsigned long ice_adapter_index(u64 dsn)
+#define ICE_ADAPTER_FIXED_INDEX	BIT_ULL(63)
+
+#define ICE_ADAPTER_INDEX_E825C	\
+	(ICE_DEV_ID_E825C_BACKPLANE | ICE_ADAPTER_FIXED_INDEX)
+
+static u64 ice_adapter_index(struct pci_dev *pdev)
 {
+	switch (pdev->device) {
+	case ICE_DEV_ID_E825C_BACKPLANE:
+	case ICE_DEV_ID_E825C_QSFP:
+	case ICE_DEV_ID_E825C_SFP:
+	case ICE_DEV_ID_E825C_SGMII:
+		/* E825C devices have multiple NACs which are connected to the
+		 * same clock source, and which must share the same
+		 * ice_adapter structure. We can't use the serial number since
+		 * each NAC has its own NVM generated with its own unique
+		 * Device Serial Number. Instead, rely on the embedded nature
+		 * of the E825C devices, and use a fixed index. This relies on
+		 * the fact that all E825C physical functions in a given
+		 * system are part of the same overall device.
+		 */
+		return ICE_ADAPTER_INDEX_E825C;
+	default:
+		return pci_get_dsn(pdev) & ~ICE_ADAPTER_FIXED_INDEX;
+	}
+}
+
+static unsigned long ice_adapter_xa_index(struct pci_dev *pdev)
+{
+	u64 index = ice_adapter_index(pdev);
+
 #if BITS_PER_LONG == 64
-	return dsn;
+	return index;
 #else
-	return (u32)dsn ^ (u32)(dsn >> 32);
+	return (u32)index ^ (u32)(index >> 32);
 #endif
 }
 
-static struct ice_adapter *ice_adapter_new(u64 dsn)
+static struct ice_adapter *ice_adapter_new(struct pci_dev *pdev)
 {
 	struct ice_adapter *adapter;
 
@@ -30,7 +59,7 @@ static struct ice_adapter *ice_adapter_new(u64 dsn)
 	if (!adapter)
 		return NULL;
 
-	adapter->device_serial_number = dsn;
+	adapter->index = ice_adapter_index(pdev);
 	spin_lock_init(&adapter->ptp_gltsyn_time_lock);
 	spin_lock_init(&adapter->txq_ctx_lock);
 	refcount_set(&adapter->refcount, 1);
@@ -64,24 +93,23 @@ static void ice_adapter_free(struct ice_adapter *adapter)
  */
 struct ice_adapter *ice_adapter_get(struct pci_dev *pdev)
 {
-	u64 dsn = pci_get_dsn(pdev);
 	struct ice_adapter *adapter;
 	unsigned long index;
 	int err;
 
-	index = ice_adapter_index(dsn);
+	index = ice_adapter_xa_index(pdev);
 	scoped_guard(mutex, &ice_adapters_mutex) {
 		err = xa_insert(&ice_adapters, index, NULL, GFP_KERNEL);
 		if (err == -EBUSY) {
 			adapter = xa_load(&ice_adapters, index);
 			refcount_inc(&adapter->refcount);
-			WARN_ON_ONCE(adapter->device_serial_number != dsn);
+			WARN_ON_ONCE(adapter->index != ice_adapter_index(pdev));
 			return adapter;
 		}
 		if (err)
 			return ERR_PTR(err);
 
-		adapter = ice_adapter_new(dsn);
+		adapter = ice_adapter_new(pdev);
 		if (!adapter)
 			return ERR_PTR(-ENOMEM);
 		xa_store(&ice_adapters, index, adapter, GFP_KERNEL);
@@ -100,11 +128,10 @@ struct ice_adapter *ice_adapter_get(struct pci_dev *pdev)
  */
 void ice_adapter_put(struct pci_dev *pdev)
 {
-	u64 dsn = pci_get_dsn(pdev);
 	struct ice_adapter *adapter;
 	unsigned long index;
 
-	index = ice_adapter_index(dsn);
+	index = ice_adapter_xa_index(pdev);
 	scoped_guard(mutex, &ice_adapters_mutex) {
 		adapter = xa_load(&ice_adapters, index);
 		if (WARN_ON(!adapter))
diff --git a/drivers/net/ethernet/intel/ice/ice_adapter.h b/drivers/net/ethernet/intel/ice/ice_adapter.h
index db66d03..e95266c 100644
--- a/drivers/net/ethernet/intel/ice/ice_adapter.h
+++ b/drivers/net/ethernet/intel/ice/ice_adapter.h
@@ -33,7 +33,7 @@ struct ice_port_list {
  * @txq_ctx_lock: Spinlock protecting access to the GLCOMM_QTX_CNTX_CTL register
  * @ctrl_pf: Control PF of the adapter
  * @ports: Ports list
- * @device_serial_number: DSN cached for collision detection on 32bit systems
+ * @index: 64-bit index cached for collision detection on 32bit systems
  */
 struct ice_adapter {
 	refcount_t refcount;
@@ -44,7 +44,7 @@ struct ice_adapter {
 
 	struct ice_pf *ctrl_pf;
 	struct ice_port_list ports;
-	u64 device_serial_number;
+	u64 index;
 };
 
 struct ice_adapter *ice_adapter_get(struct pci_dev *pdev);
diff --git a/drivers/net/ethernet/intel/ice/ice_ddp.c b/drivers/net/ethernet/intel/ice/ice_ddp.c
index e2a036c..3b2d9c4 100644
--- a/drivers/net/ethernet/intel/ice/ice_ddp.c
+++ b/drivers/net/ethernet/intel/ice/ice_ddp.c
@@ -2377,7 +2377,13 @@ ice_get_set_tx_topo(struct ice_hw *hw, u8 *buf, u16 buf_size,
  * The function will apply the new Tx topology from the package buffer
  * if available.
  *
- * Return: zero when update was successful, negative values otherwise.
+ * Return:
+ * * 0 - Successfully applied topology configuration.
+ * * -EBUSY - Failed to acquire global configuration lock.
+ * * -EEXIST - Topology configuration has already been applied.
+ * * -EIO - Unable to apply topology configuration.
+ * * -ENODEV - Failed to re-initialize device after applying configuration.
+ * * Other negative error codes indicate unexpected failures.
  */
 int ice_cfg_tx_topo(struct ice_hw *hw, const void *buf, u32 len)
 {
@@ -2410,7 +2416,7 @@ int ice_cfg_tx_topo(struct ice_hw *hw, const void *buf, u32 len)
 
 	if (status) {
 		ice_debug(hw, ICE_DBG_INIT, "Get current topology is failed\n");
-		return status;
+		return -EIO;
 	}
 
 	/* Is default topology already applied ? */
@@ -2497,31 +2503,45 @@ int ice_cfg_tx_topo(struct ice_hw *hw, const void *buf, u32 len)
 				 ICE_GLOBAL_CFG_LOCK_TIMEOUT);
 	if (status) {
 		ice_debug(hw, ICE_DBG_INIT, "Failed to acquire global lock\n");
-		return status;
+		return -EBUSY;
 	}
 
 	/* Check if reset was triggered already. */
 	reg = rd32(hw, GLGEN_RSTAT);
 	if (reg & GLGEN_RSTAT_DEVSTATE_M) {
-		/* Reset is in progress, re-init the HW again */
 		ice_debug(hw, ICE_DBG_INIT, "Reset is in progress. Layer topology might be applied already\n");
 		ice_check_reset(hw);
-		return 0;
+		/* Reset is in progress, re-init the HW again */
+		goto reinit_hw;
 	}
 
 	/* Set new topology */
 	status = ice_get_set_tx_topo(hw, new_topo, size, NULL, NULL, true);
 	if (status) {
-		ice_debug(hw, ICE_DBG_INIT, "Failed setting Tx topology\n");
-		return status;
+		ice_debug(hw, ICE_DBG_INIT, "Failed to set Tx topology, status %pe\n",
+			  ERR_PTR(status));
+		/* only report -EIO here as the caller checks the error value
+		 * and reports an informational error message informing that
+		 * the driver failed to program Tx topology.
+		 */
+		status = -EIO;
 	}
 
-	/* New topology is updated, delay 1 second before issuing the CORER */
+	/* Even if Tx topology config failed, we need to CORE reset here to
+	 * clear the global configuration lock. Delay 1 second to allow
+	 * hardware to settle then issue a CORER
+	 */
 	msleep(1000);
 	ice_reset(hw, ICE_RESET_CORER);
-	/* CORER will clear the global lock, so no explicit call
-	 * required for release.
-	 */
+	ice_check_reset(hw);
 
-	return 0;
+reinit_hw:
+	/* Since we triggered a CORER, re-initialize hardware */
+	ice_deinit_hw(hw);
+	if (ice_init_hw(hw)) {
+		ice_debug(hw, ICE_DBG_INIT, "Failed to re-init hardware after setting Tx topology\n");
+		return -ENODEV;
+	}
+
+	return status;
 }
diff --git a/drivers/net/ethernet/intel/ice/ice_idc.c b/drivers/net/ethernet/intel/ice/ice_idc.c
index 6ab53e4..420d45c 100644
--- a/drivers/net/ethernet/intel/ice/ice_idc.c
+++ b/drivers/net/ethernet/intel/ice/ice_idc.c
@@ -336,6 +336,7 @@ int ice_plug_aux_dev(struct ice_pf *pf)
 	mutex_lock(&pf->adev_mutex);
 	cdev->adev = adev;
 	mutex_unlock(&pf->adev_mutex);
+	set_bit(ICE_FLAG_AUX_DEV_CREATED, pf->flags);
 
 	return 0;
 }
@@ -347,15 +348,16 @@ void ice_unplug_aux_dev(struct ice_pf *pf)
 {
 	struct auxiliary_device *adev;
 
+	if (!test_and_clear_bit(ICE_FLAG_AUX_DEV_CREATED, pf->flags))
+		return;
+
 	mutex_lock(&pf->adev_mutex);
 	adev = pf->cdev_info->adev;
 	pf->cdev_info->adev = NULL;
 	mutex_unlock(&pf->adev_mutex);
 
-	if (adev) {
-		auxiliary_device_delete(adev);
-		auxiliary_device_uninit(adev);
-	}
+	auxiliary_device_delete(adev);
+	auxiliary_device_uninit(adev);
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 8e0b06c..cae992d 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -4536,17 +4536,23 @@ ice_init_tx_topology(struct ice_hw *hw, const struct firmware *firmware)
 			dev_info(dev, "Tx scheduling layers switching feature disabled\n");
 		else
 			dev_info(dev, "Tx scheduling layers switching feature enabled\n");
-		/* if there was a change in topology ice_cfg_tx_topo triggered
-		 * a CORER and we need to re-init hw
+		return 0;
+	} else if (err == -ENODEV) {
+		/* If we failed to re-initialize the device, we can no longer
+		 * continue loading.
 		 */
-		ice_deinit_hw(hw);
-		err = ice_init_hw(hw);
-
+		dev_warn(dev, "Failed to initialize hardware after applying Tx scheduling configuration.\n");
 		return err;
 	} else if (err == -EIO) {
 		dev_info(dev, "DDP package does not support Tx scheduling layers switching feature - please update to the latest DDP package and try again\n");
+		return 0;
+	} else if (err == -EEXIST) {
+		return 0;
 	}
 
+	/* Do not treat this as a fatal error. */
+	dev_info(dev, "Failed to apply Tx scheduling configuration, err %pe\n",
+		 ERR_PTR(err));
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c
index 29e0088..d287175 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.c
@@ -1352,7 +1352,7 @@ static int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget)
 			skb = ice_construct_skb(rx_ring, xdp);
 		/* exit if we failed to retrieve a buffer */
 		if (!skb) {
-			rx_ring->ring_stats->rx_stats.alloc_page_failed++;
+			rx_ring->ring_stats->rx_stats.alloc_buf_failed++;
 			xdp_verdict = ICE_XDP_CONSUMED;
 		}
 		ice_put_rx_mbuf(rx_ring, xdp, &xdp_xmit, ntc, xdp_verdict);
diff --git a/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c
index 555879b..b19b462 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c
@@ -180,6 +180,58 @@ static int idpf_tx_singleq_csum(struct sk_buff *skb,
 }
 
 /**
+ * idpf_tx_singleq_dma_map_error - handle TX DMA map errors
+ * @txq: queue to send buffer on
+ * @skb: send buffer
+ * @first: original first buffer info buffer for packet
+ * @idx: starting point on ring to unwind
+ */
+static void idpf_tx_singleq_dma_map_error(struct idpf_tx_queue *txq,
+					  struct sk_buff *skb,
+					  struct idpf_tx_buf *first, u16 idx)
+{
+	struct libeth_sq_napi_stats ss = { };
+	struct libeth_cq_pp cp = {
+		.dev	= txq->dev,
+		.ss	= &ss,
+	};
+
+	u64_stats_update_begin(&txq->stats_sync);
+	u64_stats_inc(&txq->q_stats.dma_map_errs);
+	u64_stats_update_end(&txq->stats_sync);
+
+	/* clear dma mappings for failed tx_buf map */
+	for (;;) {
+		struct idpf_tx_buf *tx_buf;
+
+		tx_buf = &txq->tx_buf[idx];
+		libeth_tx_complete(tx_buf, &cp);
+		if (tx_buf == first)
+			break;
+		if (idx == 0)
+			idx = txq->desc_count;
+		idx--;
+	}
+
+	if (skb_is_gso(skb)) {
+		union idpf_tx_flex_desc *tx_desc;
+
+		/* If we failed a DMA mapping for a TSO packet, we will have
+		 * used one additional descriptor for a context
+		 * descriptor. Reset that here.
+		 */
+		tx_desc = &txq->flex_tx[idx];
+		memset(tx_desc, 0, sizeof(*tx_desc));
+		if (idx == 0)
+			idx = txq->desc_count;
+		idx--;
+	}
+
+	/* Update tail in case netdev_xmit_more was previously true */
+	idpf_tx_buf_hw_update(txq, idx, false);
+}
+
+/**
  * idpf_tx_singleq_map - Build the Tx base descriptor
  * @tx_q: queue to send buffer on
  * @first: first buffer info buffer to use
@@ -219,8 +271,9 @@ static void idpf_tx_singleq_map(struct idpf_tx_queue *tx_q,
 	for (frag = &skb_shinfo(skb)->frags[0];; frag++) {
 		unsigned int max_data = IDPF_TX_MAX_DESC_DATA_ALIGNED;
 
-		if (dma_mapping_error(tx_q->dev, dma))
-			return idpf_tx_dma_map_error(tx_q, skb, first, i);
+		if (unlikely(dma_mapping_error(tx_q->dev, dma)))
+			return idpf_tx_singleq_dma_map_error(tx_q, skb,
+							     first, i);
 
 		/* record length, and DMA address */
 		dma_unmap_len_set(tx_buf, len, size);
@@ -362,11 +415,11 @@ netdev_tx_t idpf_tx_singleq_frame(struct sk_buff *skb,
 {
 	struct idpf_tx_offload_params offload = { };
 	struct idpf_tx_buf *first;
+	u32 count, buf_count = 1;
 	int csum, tso, needed;
-	unsigned int count;
 	__be16 protocol;
 
-	count = idpf_tx_desc_count_required(tx_q, skb);
+	count = idpf_tx_res_count_required(tx_q, skb, &buf_count);
 	if (unlikely(!count))
 		return idpf_tx_drop_skb(tx_q, skb);
 
diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_txrx.c
index 66a1b04..eaad52a 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_txrx.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.c
@@ -8,48 +8,13 @@
 #include "idpf_ptp.h"
 #include "idpf_virtchnl.h"
 
-struct idpf_tx_stash {
-	struct hlist_node hlist;
-	struct libeth_sqe buf;
-};
-
-#define idpf_tx_buf_compl_tag(buf)	(*(u32 *)&(buf)->priv)
+#define idpf_tx_buf_next(buf)		(*(u32 *)&(buf)->priv)
 LIBETH_SQE_CHECK_PRIV(u32);
 
 static bool idpf_chk_linearize(struct sk_buff *skb, unsigned int max_bufs,
 			       unsigned int count);
 
 /**
- * idpf_buf_lifo_push - push a buffer pointer onto stack
- * @stack: pointer to stack struct
- * @buf: pointer to buf to push
- *
- * Returns 0 on success, negative on failure
- **/
-static int idpf_buf_lifo_push(struct idpf_buf_lifo *stack,
-			      struct idpf_tx_stash *buf)
-{
-	if (unlikely(stack->top == stack->size))
-		return -ENOSPC;
-
-	stack->bufs[stack->top++] = buf;
-
-	return 0;
-}
-
-/**
- * idpf_buf_lifo_pop - pop a buffer pointer from stack
- * @stack: pointer to stack struct
- **/
-static struct idpf_tx_stash *idpf_buf_lifo_pop(struct idpf_buf_lifo *stack)
-{
-	if (unlikely(!stack->top))
-		return NULL;
-
-	return stack->bufs[--stack->top];
-}
-
-/**
  * idpf_tx_timeout - Respond to a Tx Hang
  * @netdev: network interface device structure
  * @txqueue: TX queue
@@ -77,52 +42,22 @@ void idpf_tx_timeout(struct net_device *netdev, unsigned int txqueue)
 static void idpf_tx_buf_rel_all(struct idpf_tx_queue *txq)
 {
 	struct libeth_sq_napi_stats ss = { };
-	struct idpf_buf_lifo *buf_stack;
-	struct idpf_tx_stash *stash;
 	struct libeth_cq_pp cp = {
 		.dev	= txq->dev,
 		.ss	= &ss,
 	};
-	struct hlist_node *tmp;
-	u32 i, tag;
+	u32 i;
 
 	/* Buffers already cleared, nothing to do */
 	if (!txq->tx_buf)
 		return;
 
 	/* Free all the Tx buffer sk_buffs */
-	for (i = 0; i < txq->desc_count; i++)
+	for (i = 0; i < txq->buf_pool_size; i++)
 		libeth_tx_complete(&txq->tx_buf[i], &cp);
 
 	kfree(txq->tx_buf);
 	txq->tx_buf = NULL;
-
-	if (!idpf_queue_has(FLOW_SCH_EN, txq))
-		return;
-
-	buf_stack = &txq->stash->buf_stack;
-	if (!buf_stack->bufs)
-		return;
-
-	/*
-	 * If a Tx timeout occurred, there are potentially still bufs in the
-	 * hash table, free them here.
-	 */
-	hash_for_each_safe(txq->stash->sched_buf_hash, tag, tmp, stash,
-			   hlist) {
-		if (!stash)
-			continue;
-
-		libeth_tx_complete(&stash->buf, &cp);
-		hash_del(&stash->hlist);
-		idpf_buf_lifo_push(buf_stack, stash);
-	}
-
-	for (i = 0; i < buf_stack->size; i++)
-		kfree(buf_stack->bufs[i]);
-
-	kfree(buf_stack->bufs);
-	buf_stack->bufs = NULL;
 }
 
 /**
@@ -139,6 +74,9 @@ static void idpf_tx_desc_rel(struct idpf_tx_queue *txq)
 	if (!txq->desc_ring)
 		return;
 
+	if (txq->refillq)
+		kfree(txq->refillq->ring);
+
 	dmam_free_coherent(txq->dev, txq->size, txq->desc_ring, txq->dma);
 	txq->desc_ring = NULL;
 	txq->next_to_use = 0;
@@ -195,41 +133,18 @@ static void idpf_tx_desc_rel_all(struct idpf_vport *vport)
  */
 static int idpf_tx_buf_alloc_all(struct idpf_tx_queue *tx_q)
 {
-	struct idpf_buf_lifo *buf_stack;
-	int buf_size;
-	int i;
-
 	/* Allocate book keeping buffers only. Buffers to be supplied to HW
 	 * are allocated by kernel network stack and received as part of skb
 	 */
-	buf_size = sizeof(struct idpf_tx_buf) * tx_q->desc_count;
-	tx_q->tx_buf = kzalloc(buf_size, GFP_KERNEL);
+	if (idpf_queue_has(FLOW_SCH_EN, tx_q))
+		tx_q->buf_pool_size = U16_MAX;
+	else
+		tx_q->buf_pool_size = tx_q->desc_count;
+	tx_q->tx_buf = kcalloc(tx_q->buf_pool_size, sizeof(*tx_q->tx_buf),
+			       GFP_KERNEL);
 	if (!tx_q->tx_buf)
 		return -ENOMEM;
 
-	if (!idpf_queue_has(FLOW_SCH_EN, tx_q))
-		return 0;
-
-	buf_stack = &tx_q->stash->buf_stack;
-
-	/* Initialize tx buf stack for out-of-order completions if
-	 * flow scheduling offload is enabled
-	 */
-	buf_stack->bufs = kcalloc(tx_q->desc_count, sizeof(*buf_stack->bufs),
-				  GFP_KERNEL);
-	if (!buf_stack->bufs)
-		return -ENOMEM;
-
-	buf_stack->size = tx_q->desc_count;
-	buf_stack->top = tx_q->desc_count;
-
-	for (i = 0; i < tx_q->desc_count; i++) {
-		buf_stack->bufs[i] = kzalloc(sizeof(*buf_stack->bufs[i]),
-					     GFP_KERNEL);
-		if (!buf_stack->bufs[i])
-			return -ENOMEM;
-	}
-
 	return 0;
 }
 
@@ -244,6 +159,7 @@ static int idpf_tx_desc_alloc(const struct idpf_vport *vport,
 			      struct idpf_tx_queue *tx_q)
 {
 	struct device *dev = tx_q->dev;
+	struct idpf_sw_queue *refillq;
 	int err;
 
 	err = idpf_tx_buf_alloc_all(tx_q);
@@ -267,6 +183,31 @@ static int idpf_tx_desc_alloc(const struct idpf_vport *vport,
 	tx_q->next_to_clean = 0;
 	idpf_queue_set(GEN_CHK, tx_q);
 
+	if (!idpf_queue_has(FLOW_SCH_EN, tx_q))
+		return 0;
+
+	refillq = tx_q->refillq;
+	refillq->desc_count = tx_q->buf_pool_size;
+	refillq->ring = kcalloc(refillq->desc_count, sizeof(u32),
+				GFP_KERNEL);
+	if (!refillq->ring) {
+		err = -ENOMEM;
+		goto err_alloc;
+	}
+
+	for (unsigned int i = 0; i < refillq->desc_count; i++)
+		refillq->ring[i] =
+			FIELD_PREP(IDPF_RFL_BI_BUFID_M, i) |
+			FIELD_PREP(IDPF_RFL_BI_GEN_M,
+				   idpf_queue_has(GEN_CHK, refillq));
+
+	/* Go ahead and flip the GEN bit since this counts as filling
+	 * up the ring, i.e. we already ring wrapped.
+	 */
+	idpf_queue_change(GEN_CHK, refillq);
+
+	tx_q->last_re = tx_q->desc_count - IDPF_TX_SPLITQ_RE_MIN_GAP;
+
 	return 0;
 
 err_alloc:
@@ -317,8 +258,6 @@ static int idpf_tx_desc_alloc_all(struct idpf_vport *vport)
 	for (i = 0; i < vport->num_txq_grp; i++) {
 		for (j = 0; j < vport->txq_grps[i].num_txq; j++) {
 			struct idpf_tx_queue *txq = vport->txq_grps[i].txqs[j];
-			u8 gen_bits = 0;
-			u16 bufidx_mask;
 
 			err = idpf_tx_desc_alloc(vport, txq);
 			if (err) {
@@ -327,34 +266,6 @@ static int idpf_tx_desc_alloc_all(struct idpf_vport *vport)
 					i);
 				goto err_out;
 			}
-
-			if (!idpf_is_queue_model_split(vport->txq_model))
-				continue;
-
-			txq->compl_tag_cur_gen = 0;
-
-			/* Determine the number of bits in the bufid
-			 * mask and add one to get the start of the
-			 * generation bits
-			 */
-			bufidx_mask = txq->desc_count - 1;
-			while (bufidx_mask >> 1) {
-				txq->compl_tag_gen_s++;
-				bufidx_mask = bufidx_mask >> 1;
-			}
-			txq->compl_tag_gen_s++;
-
-			gen_bits = IDPF_TX_SPLITQ_COMPL_TAG_WIDTH -
-							txq->compl_tag_gen_s;
-			txq->compl_tag_gen_max = GETMAXVAL(gen_bits);
-
-			/* Set bufid mask based on location of first
-			 * gen bit; it cannot simply be the descriptor
-			 * ring size-1 since we can have size values
-			 * where not all of those bits are set.
-			 */
-			txq->compl_tag_bufid_m =
-				GETMAXVAL(txq->compl_tag_gen_s);
 		}
 
 		if (!idpf_is_queue_model_split(vport->txq_model))
@@ -603,18 +514,18 @@ static int idpf_rx_hdr_buf_alloc_all(struct idpf_buf_queue *bufq)
 }
 
 /**
- * idpf_rx_post_buf_refill - Post buffer id to refill queue
+ * idpf_post_buf_refill - Post buffer id to refill queue
  * @refillq: refill queue to post to
  * @buf_id: buffer id to post
  */
-static void idpf_rx_post_buf_refill(struct idpf_sw_queue *refillq, u16 buf_id)
+static void idpf_post_buf_refill(struct idpf_sw_queue *refillq, u16 buf_id)
 {
 	u32 nta = refillq->next_to_use;
 
 	/* store the buffer ID and the SW maintained GEN bit to the refillq */
 	refillq->ring[nta] =
-		FIELD_PREP(IDPF_RX_BI_BUFID_M, buf_id) |
-		FIELD_PREP(IDPF_RX_BI_GEN_M,
+		FIELD_PREP(IDPF_RFL_BI_BUFID_M, buf_id) |
+		FIELD_PREP(IDPF_RFL_BI_GEN_M,
 			   idpf_queue_has(GEN_CHK, refillq));
 
 	if (unlikely(++nta == refillq->desc_count)) {
@@ -995,6 +906,11 @@ static void idpf_txq_group_rel(struct idpf_vport *vport)
 		struct idpf_txq_group *txq_grp = &vport->txq_grps[i];
 
 		for (j = 0; j < txq_grp->num_txq; j++) {
+			if (flow_sch_en) {
+				kfree(txq_grp->txqs[j]->refillq);
+				txq_grp->txqs[j]->refillq = NULL;
+			}
+
 			kfree(txq_grp->txqs[j]);
 			txq_grp->txqs[j] = NULL;
 		}
@@ -1004,9 +920,6 @@ static void idpf_txq_group_rel(struct idpf_vport *vport)
 
 		kfree(txq_grp->complq);
 		txq_grp->complq = NULL;
-
-		if (flow_sch_en)
-			kfree(txq_grp->stashes);
 	}
 	kfree(vport->txq_grps);
 	vport->txq_grps = NULL;
@@ -1367,7 +1280,6 @@ static int idpf_txq_group_alloc(struct idpf_vport *vport, u16 num_txq)
 	for (i = 0; i < vport->num_txq_grp; i++) {
 		struct idpf_txq_group *tx_qgrp = &vport->txq_grps[i];
 		struct idpf_adapter *adapter = vport->adapter;
-		struct idpf_txq_stash *stashes;
 		int j;
 
 		tx_qgrp->vport = vport;
@@ -1380,15 +1292,6 @@ static int idpf_txq_group_alloc(struct idpf_vport *vport, u16 num_txq)
 				goto err_alloc;
 		}
 
-		if (split && flow_sch_en) {
-			stashes = kcalloc(num_txq, sizeof(*stashes),
-					  GFP_KERNEL);
-			if (!stashes)
-				goto err_alloc;
-
-			tx_qgrp->stashes = stashes;
-		}
-
 		for (j = 0; j < tx_qgrp->num_txq; j++) {
 			struct idpf_tx_queue *q = tx_qgrp->txqs[j];
 
@@ -1408,12 +1311,14 @@ static int idpf_txq_group_alloc(struct idpf_vport *vport, u16 num_txq)
 			if (!flow_sch_en)
 				continue;
 
-			if (split) {
-				q->stash = &stashes[j];
-				hash_init(q->stash->sched_buf_hash);
-			}
-
 			idpf_queue_set(FLOW_SCH_EN, q);
+
+			q->refillq = kzalloc(sizeof(*q->refillq), GFP_KERNEL);
+			if (!q->refillq)
+				goto err_alloc;
+
+			idpf_queue_set(GEN_CHK, q->refillq);
+			idpf_queue_set(RFL_GEN_CHK, q->refillq);
 		}
 
 		if (!split)
@@ -1697,87 +1602,6 @@ static void idpf_tx_read_tstamp(struct idpf_tx_queue *txq, struct sk_buff *skb)
 	spin_unlock_bh(&tx_tstamp_caps->status_lock);
 }
 
-/**
- * idpf_tx_clean_stashed_bufs - clean bufs that were stored for
- * out of order completions
- * @txq: queue to clean
- * @compl_tag: completion tag of packet to clean (from completion descriptor)
- * @cleaned: pointer to stats struct to track cleaned packets/bytes
- * @budget: Used to determine if we are in netpoll
- */
-static void idpf_tx_clean_stashed_bufs(struct idpf_tx_queue *txq,
-				       u16 compl_tag,
-				       struct libeth_sq_napi_stats *cleaned,
-				       int budget)
-{
-	struct idpf_tx_stash *stash;
-	struct hlist_node *tmp_buf;
-	struct libeth_cq_pp cp = {
-		.dev	= txq->dev,
-		.ss	= cleaned,
-		.napi	= budget,
-	};
-
-	/* Buffer completion */
-	hash_for_each_possible_safe(txq->stash->sched_buf_hash, stash, tmp_buf,
-				    hlist, compl_tag) {
-		if (unlikely(idpf_tx_buf_compl_tag(&stash->buf) != compl_tag))
-			continue;
-
-		hash_del(&stash->hlist);
-
-		if (stash->buf.type == LIBETH_SQE_SKB &&
-		    (skb_shinfo(stash->buf.skb)->tx_flags & SKBTX_IN_PROGRESS))
-			idpf_tx_read_tstamp(txq, stash->buf.skb);
-
-		libeth_tx_complete(&stash->buf, &cp);
-
-		/* Push shadow buf back onto stack */
-		idpf_buf_lifo_push(&txq->stash->buf_stack, stash);
-	}
-}
-
-/**
- * idpf_stash_flow_sch_buffers - store buffer parameters info to be freed at a
- * later time (only relevant for flow scheduling mode)
- * @txq: Tx queue to clean
- * @tx_buf: buffer to store
- */
-static int idpf_stash_flow_sch_buffers(struct idpf_tx_queue *txq,
-				       struct idpf_tx_buf *tx_buf)
-{
-	struct idpf_tx_stash *stash;
-
-	if (unlikely(tx_buf->type <= LIBETH_SQE_CTX))
-		return 0;
-
-	stash = idpf_buf_lifo_pop(&txq->stash->buf_stack);
-	if (unlikely(!stash)) {
-		net_err_ratelimited("%s: No out-of-order TX buffers left!\n",
-				    netdev_name(txq->netdev));
-
-		return -ENOMEM;
-	}
-
-	/* Store buffer params in shadow buffer */
-	stash->buf.skb = tx_buf->skb;
-	stash->buf.bytes = tx_buf->bytes;
-	stash->buf.packets = tx_buf->packets;
-	stash->buf.type = tx_buf->type;
-	stash->buf.nr_frags = tx_buf->nr_frags;
-	dma_unmap_addr_set(&stash->buf, dma, dma_unmap_addr(tx_buf, dma));
-	dma_unmap_len_set(&stash->buf, len, dma_unmap_len(tx_buf, len));
-	idpf_tx_buf_compl_tag(&stash->buf) = idpf_tx_buf_compl_tag(tx_buf);
-
-	/* Add buffer to buf_hash table to be freed later */
-	hash_add(txq->stash->sched_buf_hash, &stash->hlist,
-		 idpf_tx_buf_compl_tag(&stash->buf));
-
-	tx_buf->type = LIBETH_SQE_EMPTY;
-
-	return 0;
-}
-
 #define idpf_tx_splitq_clean_bump_ntc(txq, ntc, desc, buf)	\
 do {								\
 	if (unlikely(++(ntc) == (txq)->desc_count)) {		\
@@ -1805,14 +1629,8 @@ do {								\
  * Separate packet completion events will be reported on the completion queue,
  * and the buffers will be cleaned separately. The stats are not updated from
  * this function when using flow-based scheduling.
- *
- * Furthermore, in flow scheduling mode, check to make sure there are enough
- * reserve buffers to stash the packet. If there are not, return early, which
- * will leave next_to_clean pointing to the packet that failed to be stashed.
- *
- * Return: false in the scenario above, true otherwise.
  */
-static bool idpf_tx_splitq_clean(struct idpf_tx_queue *tx_q, u16 end,
+static void idpf_tx_splitq_clean(struct idpf_tx_queue *tx_q, u16 end,
 				 int napi_budget,
 				 struct libeth_sq_napi_stats *cleaned,
 				 bool descs_only)
@@ -1826,7 +1644,12 @@ static bool idpf_tx_splitq_clean(struct idpf_tx_queue *tx_q, u16 end,
 		.napi	= napi_budget,
 	};
 	struct idpf_tx_buf *tx_buf;
-	bool clean_complete = true;
+
+	if (descs_only) {
+		/* Bump ring index to mark as cleaned. */
+		tx_q->next_to_clean = end;
+		return;
+	}
 
 	tx_desc = &tx_q->flex_tx[ntc];
 	next_pending_desc = &tx_q->flex_tx[end];
@@ -1846,136 +1669,61 @@ static bool idpf_tx_splitq_clean(struct idpf_tx_queue *tx_q, u16 end,
 			break;
 
 		eop_idx = tx_buf->rs_idx;
+		libeth_tx_complete(tx_buf, &cp);
 
-		if (descs_only) {
-			if (IDPF_TX_BUF_RSV_UNUSED(tx_q) < tx_buf->nr_frags) {
-				clean_complete = false;
-				goto tx_splitq_clean_out;
-			}
+		/* unmap remaining buffers */
+		while (ntc != eop_idx) {
+			idpf_tx_splitq_clean_bump_ntc(tx_q, ntc,
+						      tx_desc, tx_buf);
 
-			idpf_stash_flow_sch_buffers(tx_q, tx_buf);
-
-			while (ntc != eop_idx) {
-				idpf_tx_splitq_clean_bump_ntc(tx_q, ntc,
-							      tx_desc, tx_buf);
-				idpf_stash_flow_sch_buffers(tx_q, tx_buf);
-			}
-		} else {
+			/* unmap any remaining paged data */
 			libeth_tx_complete(tx_buf, &cp);
-
-			/* unmap remaining buffers */
-			while (ntc != eop_idx) {
-				idpf_tx_splitq_clean_bump_ntc(tx_q, ntc,
-							      tx_desc, tx_buf);
-
-				/* unmap any remaining paged data */
-				libeth_tx_complete(tx_buf, &cp);
-			}
 		}
 
 fetch_next_txq_desc:
 		idpf_tx_splitq_clean_bump_ntc(tx_q, ntc, tx_desc, tx_buf);
 	}
 
-tx_splitq_clean_out:
 	tx_q->next_to_clean = ntc;
-
-	return clean_complete;
 }
 
-#define idpf_tx_clean_buf_ring_bump_ntc(txq, ntc, buf)	\
-do {							\
-	(buf)++;					\
-	(ntc)++;					\
-	if (unlikely((ntc) == (txq)->desc_count)) {	\
-		buf = (txq)->tx_buf;			\
-		ntc = 0;				\
-	}						\
-} while (0)
-
 /**
- * idpf_tx_clean_buf_ring - clean flow scheduling TX queue buffers
+ * idpf_tx_clean_bufs - clean flow scheduling TX queue buffers
  * @txq: queue to clean
- * @compl_tag: completion tag of packet to clean (from completion descriptor)
+ * @buf_id: packet's starting buffer ID, from completion descriptor
  * @cleaned: pointer to stats struct to track cleaned packets/bytes
  * @budget: Used to determine if we are in netpoll
  *
- * Cleans all buffers associated with the input completion tag either from the
- * TX buffer ring or from the hash table if the buffers were previously
- * stashed. Returns the byte/segment count for the cleaned packet associated
- * this completion tag.
+ * Clean all buffers associated with the packet starting at buf_id. Returns the
+ * byte/segment count for the cleaned packet.
  */
-static bool idpf_tx_clean_buf_ring(struct idpf_tx_queue *txq, u16 compl_tag,
-				   struct libeth_sq_napi_stats *cleaned,
-				   int budget)
+static void idpf_tx_clean_bufs(struct idpf_tx_queue *txq, u32 buf_id,
+			       struct libeth_sq_napi_stats *cleaned,
+			       int budget)
 {
-	u16 idx = compl_tag & txq->compl_tag_bufid_m;
 	struct idpf_tx_buf *tx_buf = NULL;
 	struct libeth_cq_pp cp = {
 		.dev	= txq->dev,
 		.ss	= cleaned,
 		.napi	= budget,
 	};
-	u16 ntc, orig_idx = idx;
 
-	tx_buf = &txq->tx_buf[idx];
-
-	if (unlikely(tx_buf->type <= LIBETH_SQE_CTX ||
-		     idpf_tx_buf_compl_tag(tx_buf) != compl_tag))
-		return false;
-
+	tx_buf = &txq->tx_buf[buf_id];
 	if (tx_buf->type == LIBETH_SQE_SKB) {
 		if (skb_shinfo(tx_buf->skb)->tx_flags & SKBTX_IN_PROGRESS)
 			idpf_tx_read_tstamp(txq, tx_buf->skb);
 
 		libeth_tx_complete(tx_buf, &cp);
+		idpf_post_buf_refill(txq->refillq, buf_id);
 	}
 
-	idpf_tx_clean_buf_ring_bump_ntc(txq, idx, tx_buf);
+	while (idpf_tx_buf_next(tx_buf) != IDPF_TXBUF_NULL) {
+		buf_id = idpf_tx_buf_next(tx_buf);
 
-	while (idpf_tx_buf_compl_tag(tx_buf) == compl_tag) {
+		tx_buf = &txq->tx_buf[buf_id];
 		libeth_tx_complete(tx_buf, &cp);
-		idpf_tx_clean_buf_ring_bump_ntc(txq, idx, tx_buf);
+		idpf_post_buf_refill(txq->refillq, buf_id);
 	}
-
-	/*
-	 * It's possible the packet we just cleaned was an out of order
-	 * completion, which means we can stash the buffers starting from
-	 * the original next_to_clean and reuse the descriptors. We need
-	 * to compare the descriptor ring next_to_clean packet's "first" buffer
-	 * to the "first" buffer of the packet we just cleaned to determine if
-	 * this is the case. Howevever, next_to_clean can point to either a
-	 * reserved buffer that corresponds to a context descriptor used for the
-	 * next_to_clean packet (TSO packet) or the "first" buffer (single
-	 * packet). The orig_idx from the packet we just cleaned will always
-	 * point to the "first" buffer. If next_to_clean points to a reserved
-	 * buffer, let's bump ntc once and start the comparison from there.
-	 */
-	ntc = txq->next_to_clean;
-	tx_buf = &txq->tx_buf[ntc];
-
-	if (tx_buf->type == LIBETH_SQE_CTX)
-		idpf_tx_clean_buf_ring_bump_ntc(txq, ntc, tx_buf);
-
-	/*
-	 * If ntc still points to a different "first" buffer, clean the
-	 * descriptor ring and stash all of the buffers for later cleaning. If
-	 * we cannot stash all of the buffers, next_to_clean will point to the
-	 * "first" buffer of the packet that could not be stashed and cleaning
-	 * will start there next time.
-	 */
-	if (unlikely(tx_buf != &txq->tx_buf[orig_idx] &&
-		     !idpf_tx_splitq_clean(txq, orig_idx, budget, cleaned,
-					   true)))
-		return true;
-
-	/*
-	 * Otherwise, update next_to_clean to reflect the cleaning that was
-	 * done above.
-	 */
-	txq->next_to_clean = idx;
-
-	return true;
 }
 
 /**
@@ -1994,22 +1742,17 @@ static void idpf_tx_handle_rs_completion(struct idpf_tx_queue *txq,
 					 struct libeth_sq_napi_stats *cleaned,
 					 int budget)
 {
-	u16 compl_tag;
+	/* RS completion contains queue head for queue based scheduling or
+	 * completion tag for flow based scheduling.
+	 */
+	u16 rs_compl_val = le16_to_cpu(desc->q_head_compl_tag.q_head);
 
 	if (!idpf_queue_has(FLOW_SCH_EN, txq)) {
-		u16 head = le16_to_cpu(desc->q_head_compl_tag.q_head);
-
-		idpf_tx_splitq_clean(txq, head, budget, cleaned, false);
+		idpf_tx_splitq_clean(txq, rs_compl_val, budget, cleaned, false);
 		return;
 	}
 
-	compl_tag = le16_to_cpu(desc->q_head_compl_tag.compl_tag);
-
-	/* If we didn't clean anything on the ring, this packet must be
-	 * in the hash table. Go clean it there.
-	 */
-	if (!idpf_tx_clean_buf_ring(txq, compl_tag, cleaned, budget))
-		idpf_tx_clean_stashed_bufs(txq, compl_tag, cleaned, budget);
+	idpf_tx_clean_bufs(txq, rs_compl_val, cleaned, budget);
 }
 
 /**
@@ -2126,8 +1869,7 @@ static bool idpf_tx_clean_complq(struct idpf_compl_queue *complq, int budget,
 		/* Update BQL */
 		nq = netdev_get_tx_queue(tx_q->netdev, tx_q->idx);
 
-		dont_wake = !complq_ok || IDPF_TX_BUF_RSV_LOW(tx_q) ||
-			    np->state != __IDPF_VPORT_UP ||
+		dont_wake = !complq_ok || np->state != __IDPF_VPORT_UP ||
 			    !netif_carrier_ok(tx_q->netdev);
 		/* Check if the TXQ needs to and can be restarted */
 		__netif_txq_completed_wake(nq, tx_q->cleaned_pkts, tx_q->cleaned_bytes,
@@ -2184,15 +1926,21 @@ void idpf_tx_splitq_build_flow_desc(union idpf_tx_flex_desc *desc,
 	desc->flow.qw1.compl_tag = cpu_to_le16(params->compl_tag);
 }
 
-/* Global conditions to tell whether the txq (and related resources)
- * has room to allow the use of "size" descriptors.
+/**
+ * idpf_tx_splitq_has_room - check if enough Tx splitq resources are available
+ * @tx_q: the queue to be checked
+ * @descs_needed: number of descriptors required for this packet
+ * @bufs_needed: number of Tx buffers required for this packet
+ *
+ * Return: 0 if no room available, 1 otherwise
  */
-static int idpf_txq_has_room(struct idpf_tx_queue *tx_q, u32 size)
+static int idpf_txq_has_room(struct idpf_tx_queue *tx_q, u32 descs_needed,
+			     u32 bufs_needed)
 {
-	if (IDPF_DESC_UNUSED(tx_q) < size ||
+	if (IDPF_DESC_UNUSED(tx_q) < descs_needed ||
 	    IDPF_TX_COMPLQ_PENDING(tx_q->txq_grp) >
 		IDPF_TX_COMPLQ_OVERFLOW_THRESH(tx_q->txq_grp->complq) ||
-	    IDPF_TX_BUF_RSV_LOW(tx_q))
+	    idpf_tx_splitq_get_free_bufs(tx_q->refillq) < bufs_needed)
 		return 0;
 	return 1;
 }
@@ -2201,14 +1949,21 @@ static int idpf_txq_has_room(struct idpf_tx_queue *tx_q, u32 size)
  * idpf_tx_maybe_stop_splitq - 1st level check for Tx splitq stop conditions
  * @tx_q: the queue to be checked
  * @descs_needed: number of descriptors required for this packet
+ * @bufs_needed: number of buffers needed for this packet
  *
- * Returns 0 if stop is not needed
+ * Return: 0 if stop is not needed
  */
 static int idpf_tx_maybe_stop_splitq(struct idpf_tx_queue *tx_q,
-				     unsigned int descs_needed)
+				     u32 descs_needed,
+				     u32 bufs_needed)
 {
+	/* Since we have multiple resources to check for splitq, our
+	 * start,stop_thrs becomes a boolean check instead of a count
+	 * threshold.
+	 */
 	if (netif_subqueue_maybe_stop(tx_q->netdev, tx_q->idx,
-				      idpf_txq_has_room(tx_q, descs_needed),
+				      idpf_txq_has_room(tx_q, descs_needed,
+							bufs_needed),
 				      1, 1))
 		return 0;
 
@@ -2250,14 +2005,16 @@ void idpf_tx_buf_hw_update(struct idpf_tx_queue *tx_q, u32 val,
 }
 
 /**
- * idpf_tx_desc_count_required - calculate number of Tx descriptors needed
+ * idpf_tx_res_count_required - get number of Tx resources needed for this pkt
  * @txq: queue to send buffer on
  * @skb: send buffer
+ * @bufs_needed: (output) number of buffers needed for this skb.
  *
- * Returns number of data descriptors needed for this skb.
+ * Return: number of data descriptors and buffers needed for this skb.
  */
-unsigned int idpf_tx_desc_count_required(struct idpf_tx_queue *txq,
-					 struct sk_buff *skb)
+unsigned int idpf_tx_res_count_required(struct idpf_tx_queue *txq,
+					struct sk_buff *skb,
+					u32 *bufs_needed)
 {
 	const struct skb_shared_info *shinfo;
 	unsigned int count = 0, i;
@@ -2268,6 +2025,7 @@ unsigned int idpf_tx_desc_count_required(struct idpf_tx_queue *txq,
 		return count;
 
 	shinfo = skb_shinfo(skb);
+	*bufs_needed += shinfo->nr_frags;
 	for (i = 0; i < shinfo->nr_frags; i++) {
 		unsigned int size;
 
@@ -2297,57 +2055,6 @@ unsigned int idpf_tx_desc_count_required(struct idpf_tx_queue *txq,
 }
 
 /**
- * idpf_tx_dma_map_error - handle TX DMA map errors
- * @txq: queue to send buffer on
- * @skb: send buffer
- * @first: original first buffer info buffer for packet
- * @idx: starting point on ring to unwind
- */
-void idpf_tx_dma_map_error(struct idpf_tx_queue *txq, struct sk_buff *skb,
-			   struct idpf_tx_buf *first, u16 idx)
-{
-	struct libeth_sq_napi_stats ss = { };
-	struct libeth_cq_pp cp = {
-		.dev	= txq->dev,
-		.ss	= &ss,
-	};
-
-	u64_stats_update_begin(&txq->stats_sync);
-	u64_stats_inc(&txq->q_stats.dma_map_errs);
-	u64_stats_update_end(&txq->stats_sync);
-
-	/* clear dma mappings for failed tx_buf map */
-	for (;;) {
-		struct idpf_tx_buf *tx_buf;
-
-		tx_buf = &txq->tx_buf[idx];
-		libeth_tx_complete(tx_buf, &cp);
-		if (tx_buf == first)
-			break;
-		if (idx == 0)
-			idx = txq->desc_count;
-		idx--;
-	}
-
-	if (skb_is_gso(skb)) {
-		union idpf_tx_flex_desc *tx_desc;
-
-		/* If we failed a DMA mapping for a TSO packet, we will have
-		 * used one additional descriptor for a context
-		 * descriptor. Reset that here.
-		 */
-		tx_desc = &txq->flex_tx[idx];
-		memset(tx_desc, 0, sizeof(*tx_desc));
-		if (idx == 0)
-			idx = txq->desc_count;
-		idx--;
-	}
-
-	/* Update tail in case netdev_xmit_more was previously true */
-	idpf_tx_buf_hw_update(txq, idx, false);
-}
-
-/**
  * idpf_tx_splitq_bump_ntu - adjust NTU and generation
  * @txq: the tx ring to wrap
  * @ntu: ring index to bump
@@ -2356,15 +2063,84 @@ static unsigned int idpf_tx_splitq_bump_ntu(struct idpf_tx_queue *txq, u16 ntu)
 {
 	ntu++;
 
-	if (ntu == txq->desc_count) {
+	if (ntu == txq->desc_count)
 		ntu = 0;
-		txq->compl_tag_cur_gen = IDPF_TX_ADJ_COMPL_TAG_GEN(txq);
-	}
 
 	return ntu;
 }
 
 /**
+ * idpf_tx_get_free_buf_id - get a free buffer ID from the refill queue
+ * @refillq: refill queue to get buffer ID from
+ * @buf_id: return buffer ID
+ *
+ * Return: true if a buffer ID was found, false if not
+ */
+static bool idpf_tx_get_free_buf_id(struct idpf_sw_queue *refillq,
+				    u32 *buf_id)
+{
+	u32 ntc = refillq->next_to_clean;
+	u32 refill_desc;
+
+	refill_desc = refillq->ring[ntc];
+
+	if (unlikely(idpf_queue_has(RFL_GEN_CHK, refillq) !=
+		     !!(refill_desc & IDPF_RFL_BI_GEN_M)))
+		return false;
+
+	*buf_id = FIELD_GET(IDPF_RFL_BI_BUFID_M, refill_desc);
+
+	if (unlikely(++ntc == refillq->desc_count)) {
+		idpf_queue_change(RFL_GEN_CHK, refillq);
+		ntc = 0;
+	}
+
+	refillq->next_to_clean = ntc;
+
+	return true;
+}
+
+/**
+ * idpf_tx_splitq_pkt_err_unmap - Unmap buffers and bump tail in case of error
+ * @txq: Tx queue to unwind
+ * @params: pointer to splitq params struct
+ * @first: starting buffer for packet to unmap
+ */
+static void idpf_tx_splitq_pkt_err_unmap(struct idpf_tx_queue *txq,
+					 struct idpf_tx_splitq_params *params,
+					 struct idpf_tx_buf *first)
+{
+	struct idpf_sw_queue *refillq = txq->refillq;
+	struct libeth_sq_napi_stats ss = { };
+	struct idpf_tx_buf *tx_buf = first;
+	struct libeth_cq_pp cp = {
+		.dev    = txq->dev,
+		.ss     = &ss,
+	};
+
+	u64_stats_update_begin(&txq->stats_sync);
+	u64_stats_inc(&txq->q_stats.dma_map_errs);
+	u64_stats_update_end(&txq->stats_sync);
+
+	libeth_tx_complete(tx_buf, &cp);
+	while (idpf_tx_buf_next(tx_buf) != IDPF_TXBUF_NULL) {
+		tx_buf = &txq->tx_buf[idpf_tx_buf_next(tx_buf)];
+		libeth_tx_complete(tx_buf, &cp);
+	}
+
+	/* Update tail in case netdev_xmit_more was previously true. */
+	idpf_tx_buf_hw_update(txq, params->prev_ntu, false);
+
+	if (!refillq)
+		return;
+
+	/* Restore refillq state to avoid leaking tags. */
+	if (params->prev_refill_gen != idpf_queue_has(RFL_GEN_CHK, refillq))
+		idpf_queue_change(RFL_GEN_CHK, refillq);
+	refillq->next_to_clean = params->prev_refill_ntc;
+}
+
+/**
  * idpf_tx_splitq_map - Build the Tx flex descriptor
  * @tx_q: queue to send buffer on
  * @params: pointer to splitq params struct
@@ -2385,6 +2161,7 @@ static void idpf_tx_splitq_map(struct idpf_tx_queue *tx_q,
 	struct netdev_queue *nq;
 	struct sk_buff *skb;
 	skb_frag_t *frag;
+	u32 next_buf_id;
 	u16 td_cmd = 0;
 	dma_addr_t dma;
 
@@ -2402,17 +2179,16 @@ static void idpf_tx_splitq_map(struct idpf_tx_queue *tx_q,
 	tx_buf = first;
 	first->nr_frags = 0;
 
-	params->compl_tag =
-		(tx_q->compl_tag_cur_gen << tx_q->compl_tag_gen_s) | i;
-
 	for (frag = &skb_shinfo(skb)->frags[0];; frag++) {
 		unsigned int max_data = IDPF_TX_MAX_DESC_DATA_ALIGNED;
 
-		if (dma_mapping_error(tx_q->dev, dma))
-			return idpf_tx_dma_map_error(tx_q, skb, first, i);
+		if (unlikely(dma_mapping_error(tx_q->dev, dma))) {
+			idpf_tx_buf_next(tx_buf) = IDPF_TXBUF_NULL;
+			return idpf_tx_splitq_pkt_err_unmap(tx_q, params,
+							    first);
+		}
 
 		first->nr_frags++;
-		idpf_tx_buf_compl_tag(tx_buf) = params->compl_tag;
 		tx_buf->type = LIBETH_SQE_FRAG;
 
 		/* record length, and DMA address */
@@ -2468,29 +2244,12 @@ static void idpf_tx_splitq_map(struct idpf_tx_queue *tx_q,
 						  max_data);
 
 			if (unlikely(++i == tx_q->desc_count)) {
-				tx_buf = tx_q->tx_buf;
 				tx_desc = &tx_q->flex_tx[0];
 				i = 0;
-				tx_q->compl_tag_cur_gen =
-					IDPF_TX_ADJ_COMPL_TAG_GEN(tx_q);
 			} else {
-				tx_buf++;
 				tx_desc++;
 			}
 
-			/* Since this packet has a buffer that is going to span
-			 * multiple descriptors, it's going to leave holes in
-			 * to the TX buffer ring. To ensure these holes do not
-			 * cause issues in the cleaning routines, we will clear
-			 * them of any stale data and assign them the same
-			 * completion tag as the current packet. Then when the
-			 * packet is being cleaned, the cleaning routines will
-			 * simply pass over these holes and finish cleaning the
-			 * rest of the packet.
-			 */
-			tx_buf->type = LIBETH_SQE_EMPTY;
-			idpf_tx_buf_compl_tag(tx_buf) = params->compl_tag;
-
 			/* Adjust the DMA offset and the remaining size of the
 			 * fragment.  On the first iteration of this loop,
 			 * max_data will be >= 12K and <= 16K-1.  On any
@@ -2515,15 +2274,25 @@ static void idpf_tx_splitq_map(struct idpf_tx_queue *tx_q,
 		idpf_tx_splitq_build_desc(tx_desc, params, td_cmd, size);
 
 		if (unlikely(++i == tx_q->desc_count)) {
-			tx_buf = tx_q->tx_buf;
 			tx_desc = &tx_q->flex_tx[0];
 			i = 0;
-			tx_q->compl_tag_cur_gen = IDPF_TX_ADJ_COMPL_TAG_GEN(tx_q);
 		} else {
-			tx_buf++;
 			tx_desc++;
 		}
 
+		if (idpf_queue_has(FLOW_SCH_EN, tx_q)) {
+			if (unlikely(!idpf_tx_get_free_buf_id(tx_q->refillq,
+							      &next_buf_id))) {
+				idpf_tx_buf_next(tx_buf) = IDPF_TXBUF_NULL;
+				return idpf_tx_splitq_pkt_err_unmap(tx_q, params,
+								    first);
+			}
+		} else {
+			next_buf_id = i;
+		}
+		idpf_tx_buf_next(tx_buf) = next_buf_id;
+		tx_buf = &tx_q->tx_buf[next_buf_id];
+
 		size = skb_frag_size(frag);
 		data_len -= size;
 
@@ -2538,6 +2307,7 @@ static void idpf_tx_splitq_map(struct idpf_tx_queue *tx_q,
 
 	/* write last descriptor with RS and EOP bits */
 	first->rs_idx = i;
+	idpf_tx_buf_next(tx_buf) = IDPF_TXBUF_NULL;
 	td_cmd |= params->eop_cmd;
 	idpf_tx_splitq_build_desc(tx_desc, params, td_cmd, size);
 	i = idpf_tx_splitq_bump_ntu(tx_q, i);
@@ -2746,8 +2516,6 @@ idpf_tx_splitq_get_ctx_desc(struct idpf_tx_queue *txq)
 	union idpf_flex_tx_ctx_desc *desc;
 	int i = txq->next_to_use;
 
-	txq->tx_buf[i].type = LIBETH_SQE_CTX;
-
 	/* grab the next descriptor */
 	desc = &txq->flex_ctx[i];
 	txq->next_to_use = idpf_tx_splitq_bump_ntu(txq, i);
@@ -2841,6 +2609,21 @@ static void idpf_tx_set_tstamp_desc(union idpf_flex_tx_ctx_desc *ctx_desc,
 #endif /* CONFIG_PTP_1588_CLOCK */
 
 /**
+ * idpf_tx_splitq_need_re - check whether RE bit needs to be set
+ * @tx_q: pointer to Tx queue
+ *
+ * Return: true if RE bit needs to be set, false otherwise
+ */
+static bool idpf_tx_splitq_need_re(struct idpf_tx_queue *tx_q)
+{
+	int gap = tx_q->next_to_use - tx_q->last_re;
+
+	gap += (gap < 0) ? tx_q->desc_count : 0;
+
+	return gap >= IDPF_TX_SPLITQ_RE_MIN_GAP;
+}
+
+/**
  * idpf_tx_splitq_frame - Sends buffer on Tx ring using flex descriptors
  * @skb: send buffer
  * @tx_q: queue to send buffer on
@@ -2850,13 +2633,16 @@ static void idpf_tx_set_tstamp_desc(union idpf_flex_tx_ctx_desc *ctx_desc,
 static netdev_tx_t idpf_tx_splitq_frame(struct sk_buff *skb,
 					struct idpf_tx_queue *tx_q)
 {
-	struct idpf_tx_splitq_params tx_params = { };
+	struct idpf_tx_splitq_params tx_params = {
+		.prev_ntu = tx_q->next_to_use,
+	};
 	union idpf_flex_tx_ctx_desc *ctx_desc;
 	struct idpf_tx_buf *first;
-	unsigned int count;
+	u32 count, buf_count = 1;
 	int tso, idx;
+	u32 buf_id;
 
-	count = idpf_tx_desc_count_required(tx_q, skb);
+	count = idpf_tx_res_count_required(tx_q, skb, &buf_count);
 	if (unlikely(!count))
 		return idpf_tx_drop_skb(tx_q, skb);
 
@@ -2866,7 +2652,7 @@ static netdev_tx_t idpf_tx_splitq_frame(struct sk_buff *skb,
 
 	/* Check for splitq specific TX resources */
 	count += (IDPF_TX_DESCS_PER_CACHE_LINE + tso);
-	if (idpf_tx_maybe_stop_splitq(tx_q, count)) {
+	if (idpf_tx_maybe_stop_splitq(tx_q, count, buf_count)) {
 		idpf_tx_buf_hw_update(tx_q, tx_q->next_to_use, false);
 
 		return NETDEV_TX_BUSY;
@@ -2898,8 +2684,55 @@ static netdev_tx_t idpf_tx_splitq_frame(struct sk_buff *skb,
 		idpf_tx_set_tstamp_desc(ctx_desc, idx);
 	}
 
-	/* record the location of the first descriptor for this packet */
-	first = &tx_q->tx_buf[tx_q->next_to_use];
+	if (idpf_queue_has(FLOW_SCH_EN, tx_q)) {
+		struct idpf_sw_queue *refillq = tx_q->refillq;
+
+		/* Save refillq state in case of a packet rollback.  Otherwise,
+		 * the tags will be leaked since they will be popped from the
+		 * refillq but never reposted during cleaning.
+		 */
+		tx_params.prev_refill_gen =
+			idpf_queue_has(RFL_GEN_CHK, refillq);
+		tx_params.prev_refill_ntc = refillq->next_to_clean;
+
+		if (unlikely(!idpf_tx_get_free_buf_id(tx_q->refillq,
+						      &buf_id))) {
+			if (tx_params.prev_refill_gen !=
+			    idpf_queue_has(RFL_GEN_CHK, refillq))
+				idpf_queue_change(RFL_GEN_CHK, refillq);
+			refillq->next_to_clean = tx_params.prev_refill_ntc;
+
+			tx_q->next_to_use = tx_params.prev_ntu;
+			return idpf_tx_drop_skb(tx_q, skb);
+		}
+		tx_params.compl_tag = buf_id;
+
+		tx_params.dtype = IDPF_TX_DESC_DTYPE_FLEX_FLOW_SCHE;
+		tx_params.eop_cmd = IDPF_TXD_FLEX_FLOW_CMD_EOP;
+		/* Set the RE bit to periodically "clean" the descriptor ring.
+		 * MIN_GAP is set to MIN_RING size to ensure it will be set at
+		 * least once each time around the ring.
+		 */
+		if (idpf_tx_splitq_need_re(tx_q)) {
+			tx_params.eop_cmd |= IDPF_TXD_FLEX_FLOW_CMD_RE;
+			tx_q->txq_grp->num_completions_pending++;
+			tx_q->last_re = tx_q->next_to_use;
+		}
+
+		if (skb->ip_summed == CHECKSUM_PARTIAL)
+			tx_params.offload.td_cmd |= IDPF_TXD_FLEX_FLOW_CMD_CS_EN;
+
+	} else {
+		buf_id = tx_q->next_to_use;
+
+		tx_params.dtype = IDPF_TX_DESC_DTYPE_FLEX_L2TAG1_L2TAG2;
+		tx_params.eop_cmd = IDPF_TXD_LAST_DESC_CMD;
+
+		if (skb->ip_summed == CHECKSUM_PARTIAL)
+			tx_params.offload.td_cmd |= IDPF_TX_FLEX_DESC_CMD_CS_EN;
+	}
+
+	first = &tx_q->tx_buf[buf_id];
 	first->skb = skb;
 
 	if (tso) {
@@ -2911,30 +2744,6 @@ static netdev_tx_t idpf_tx_splitq_frame(struct sk_buff *skb,
 		first->bytes = max_t(unsigned int, skb->len, ETH_ZLEN);
 	}
 
-	if (idpf_queue_has(FLOW_SCH_EN, tx_q)) {
-		tx_params.dtype = IDPF_TX_DESC_DTYPE_FLEX_FLOW_SCHE;
-		tx_params.eop_cmd = IDPF_TXD_FLEX_FLOW_CMD_EOP;
-		/* Set the RE bit to catch any packets that may have not been
-		 * stashed during RS completion cleaning. MIN_GAP is set to
-		 * MIN_RING size to ensure it will be set at least once each
-		 * time around the ring.
-		 */
-		if (!(tx_q->next_to_use % IDPF_TX_SPLITQ_RE_MIN_GAP)) {
-			tx_params.eop_cmd |= IDPF_TXD_FLEX_FLOW_CMD_RE;
-			tx_q->txq_grp->num_completions_pending++;
-		}
-
-		if (skb->ip_summed == CHECKSUM_PARTIAL)
-			tx_params.offload.td_cmd |= IDPF_TXD_FLEX_FLOW_CMD_CS_EN;
-
-	} else {
-		tx_params.dtype = IDPF_TX_DESC_DTYPE_FLEX_L2TAG1_L2TAG2;
-		tx_params.eop_cmd = IDPF_TXD_LAST_DESC_CMD;
-
-		if (skb->ip_summed == CHECKSUM_PARTIAL)
-			tx_params.offload.td_cmd |= IDPF_TX_FLEX_DESC_CMD_CS_EN;
-	}
-
 	idpf_tx_splitq_map(tx_q, &tx_params, first);
 
 	return NETDEV_TX_OK;
@@ -3472,7 +3281,7 @@ static int idpf_rx_splitq_clean(struct idpf_rx_queue *rxq, int budget)
 skip_data:
 		rx_buf->netmem = 0;
 
-		idpf_rx_post_buf_refill(refillq, buf_id);
+		idpf_post_buf_refill(refillq, buf_id);
 		IDPF_RX_BUMP_NTC(rxq, ntc);
 
 		/* skip if it is non EOP desc */
@@ -3580,10 +3389,10 @@ static void idpf_rx_clean_refillq(struct idpf_buf_queue *bufq,
 		bool failure;
 
 		if (idpf_queue_has(RFL_GEN_CHK, refillq) !=
-		    !!(refill_desc & IDPF_RX_BI_GEN_M))
+		    !!(refill_desc & IDPF_RFL_BI_GEN_M))
 			break;
 
-		buf_id = FIELD_GET(IDPF_RX_BI_BUFID_M, refill_desc);
+		buf_id = FIELD_GET(IDPF_RFL_BI_BUFID_M, refill_desc);
 		failure = idpf_rx_update_bufq_desc(bufq, buf_id, buf_desc);
 		if (failure)
 			break;
diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.h b/drivers/net/ethernet/intel/idpf/idpf_txrx.h
index 281de65..52753df 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_txrx.h
+++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.h
@@ -108,8 +108,8 @@ do {								\
  */
 #define IDPF_TX_SPLITQ_RE_MIN_GAP	64
 
-#define IDPF_RX_BI_GEN_M		BIT(16)
-#define IDPF_RX_BI_BUFID_M		GENMASK(15, 0)
+#define IDPF_RFL_BI_GEN_M		BIT(16)
+#define IDPF_RFL_BI_BUFID_M		GENMASK(15, 0)
 
 #define IDPF_RXD_EOF_SPLITQ		VIRTCHNL2_RX_FLEX_DESC_ADV_STATUS0_EOF_M
 #define IDPF_RXD_EOF_SINGLEQ		VIRTCHNL2_RX_BASE_DESC_STATUS_EOF_M
@@ -118,10 +118,6 @@ do {								\
 	((((txq)->next_to_clean > (txq)->next_to_use) ? 0 : (txq)->desc_count) + \
 	(txq)->next_to_clean - (txq)->next_to_use - 1)
 
-#define IDPF_TX_BUF_RSV_UNUSED(txq)	((txq)->stash->buf_stack.top)
-#define IDPF_TX_BUF_RSV_LOW(txq)	(IDPF_TX_BUF_RSV_UNUSED(txq) < \
-					 (txq)->desc_count >> 2)
-
 #define IDPF_TX_COMPLQ_OVERFLOW_THRESH(txcq)	((txcq)->desc_count >> 1)
 /* Determine the absolute number of completions pending, i.e. the number of
  * completions that are expected to arrive on the TX completion queue.
@@ -131,11 +127,7 @@ do {								\
 	0 : U32_MAX) + \
 	(txq)->num_completions_pending - (txq)->complq->num_completions)
 
-#define IDPF_TX_SPLITQ_COMPL_TAG_WIDTH	16
-/* Adjust the generation for the completion tag and wrap if necessary */
-#define IDPF_TX_ADJ_COMPL_TAG_GEN(txq) \
-	((++(txq)->compl_tag_cur_gen) >= (txq)->compl_tag_gen_max ? \
-	0 : (txq)->compl_tag_cur_gen)
+#define IDPF_TXBUF_NULL			U32_MAX
 
 #define IDPF_TXD_LAST_DESC_CMD (IDPF_TX_DESC_CMD_EOP | IDPF_TX_DESC_CMD_RS)
 
@@ -153,18 +145,6 @@ union idpf_tx_flex_desc {
 #define idpf_tx_buf libeth_sqe
 
 /**
- * struct idpf_buf_lifo - LIFO for managing OOO completions
- * @top: Used to know how many buffers are left
- * @size: Total size of LIFO
- * @bufs: Backing array
- */
-struct idpf_buf_lifo {
-	u16 top;
-	u16 size;
-	struct idpf_tx_stash **bufs;
-};
-
-/**
  * struct idpf_tx_offload_params - Offload parameters for a given packet
  * @tx_flags: Feature flags enabled for this packet
  * @hdr_offsets: Offset parameter for single queue model
@@ -196,6 +176,9 @@ struct idpf_tx_offload_params {
  * @compl_tag: Associated tag for completion
  * @td_tag: Descriptor tunneling tag
  * @offload: Offload parameters
+ * @prev_ntu: stored TxQ next_to_use in case of rollback
+ * @prev_refill_ntc: stored refillq next_to_clean in case of packet rollback
+ * @prev_refill_gen: stored refillq generation bit in case of packet rollback
  */
 struct idpf_tx_splitq_params {
 	enum idpf_tx_desc_dtype_value dtype;
@@ -206,6 +189,10 @@ struct idpf_tx_splitq_params {
 	};
 
 	struct idpf_tx_offload_params offload;
+
+	u16 prev_ntu;
+	u16 prev_refill_ntc;
+	bool prev_refill_gen;
 };
 
 enum idpf_tx_ctx_desc_eipt_offload {
@@ -468,17 +455,6 @@ struct idpf_tx_queue_stats {
 #define IDPF_DIM_DEFAULT_PROFILE_IX		1
 
 /**
- * struct idpf_txq_stash - Tx buffer stash for Flow-based scheduling mode
- * @buf_stack: Stack of empty buffers to store buffer info for out of order
- *	       buffer completions. See struct idpf_buf_lifo
- * @sched_buf_hash: Hash table to store buffers
- */
-struct idpf_txq_stash {
-	struct idpf_buf_lifo buf_stack;
-	DECLARE_HASHTABLE(sched_buf_hash, 12);
-} ____cacheline_aligned;
-
-/**
  * struct idpf_rx_queue - software structure representing a receive queue
  * @rx: universal receive descriptor array
  * @single_buf: buffer descriptor array in singleq
@@ -610,6 +586,8 @@ libeth_cacheline_set_assert(struct idpf_rx_queue, 64,
  * @netdev: &net_device corresponding to this queue
  * @next_to_use: Next descriptor to use
  * @next_to_clean: Next descriptor to clean
+ * @last_re: last descriptor index that RE bit was set
+ * @tx_max_bufs: Max buffers that can be transmitted with scatter-gather
  * @cleaned_bytes: Splitq only, TXQ only: When a TX completion is received on
  *		   the TX completion queue, it can be for any TXQ associated
  *		   with that completion queue. This means we can clean up to
@@ -620,11 +598,7 @@ libeth_cacheline_set_assert(struct idpf_rx_queue, 64,
  *		   only once at the end of the cleaning routine.
  * @clean_budget: singleq only, queue cleaning budget
  * @cleaned_pkts: Number of packets cleaned for the above said case
- * @tx_max_bufs: Max buffers that can be transmitted with scatter-gather
- * @stash: Tx buffer stash for Flow-based scheduling mode
- * @compl_tag_bufid_m: Completion tag buffer id mask
- * @compl_tag_cur_gen: Used to keep track of current completion tag generation
- * @compl_tag_gen_max: To determine when compl_tag_cur_gen should be reset
+ * @refillq: Pointer to refill queue
  * @cached_tstamp_caps: Tx timestamp capabilities negotiated with the CP
  * @tstamp_task: Work that handles Tx timestamp read
  * @stats_sync: See struct u64_stats_sync
@@ -633,6 +607,7 @@ libeth_cacheline_set_assert(struct idpf_rx_queue, 64,
  * @size: Length of descriptor ring in bytes
  * @dma: Physical address of ring
  * @q_vector: Backreference to associated vector
+ * @buf_pool_size: Total number of idpf_tx_buf
  */
 struct idpf_tx_queue {
 	__cacheline_group_begin_aligned(read_mostly);
@@ -654,7 +629,6 @@ struct idpf_tx_queue {
 	u16 desc_count;
 
 	u16 tx_min_pkt_len;
-	u16 compl_tag_gen_s;
 
 	struct net_device *netdev;
 	__cacheline_group_end_aligned(read_mostly);
@@ -662,6 +636,8 @@ struct idpf_tx_queue {
 	__cacheline_group_begin_aligned(read_write);
 	u16 next_to_use;
 	u16 next_to_clean;
+	u16 last_re;
+	u16 tx_max_bufs;
 
 	union {
 		u32 cleaned_bytes;
@@ -669,12 +645,7 @@ struct idpf_tx_queue {
 	};
 	u16 cleaned_pkts;
 
-	u16 tx_max_bufs;
-	struct idpf_txq_stash *stash;
-
-	u16 compl_tag_bufid_m;
-	u16 compl_tag_cur_gen;
-	u16 compl_tag_gen_max;
+	struct idpf_sw_queue *refillq;
 
 	struct idpf_ptp_vport_tx_tstamp_caps *cached_tstamp_caps;
 	struct work_struct *tstamp_task;
@@ -689,11 +660,12 @@ struct idpf_tx_queue {
 	dma_addr_t dma;
 
 	struct idpf_q_vector *q_vector;
+	u32 buf_pool_size;
 	__cacheline_group_end_aligned(cold);
 };
 libeth_cacheline_set_assert(struct idpf_tx_queue, 64,
-			    112 + sizeof(struct u64_stats_sync),
-			    24);
+			    104 + sizeof(struct u64_stats_sync),
+			    32);
 
 /**
  * struct idpf_buf_queue - software structure representing a buffer queue
@@ -903,7 +875,6 @@ struct idpf_rxq_group {
  * @vport: Vport back pointer
  * @num_txq: Number of TX queues associated
  * @txqs: Array of TX queue pointers
- * @stashes: array of OOO stashes for the queues
  * @complq: Associated completion queue pointer, split queue only
  * @num_completions_pending: Total number of completions pending for the
  *			     completion queue, acculumated for all TX queues
@@ -918,7 +889,6 @@ struct idpf_txq_group {
 
 	u16 num_txq;
 	struct idpf_tx_queue *txqs[IDPF_LARGE_MAX_Q];
-	struct idpf_txq_stash *stashes;
 
 	struct idpf_compl_queue *complq;
 
@@ -1011,6 +981,17 @@ static inline void idpf_vport_intr_set_wb_on_itr(struct idpf_q_vector *q_vector)
 	       reg->dyn_ctl);
 }
 
+/**
+ * idpf_tx_splitq_get_free_bufs - get number of free buf_ids in refillq
+ * @refillq: pointer to refillq containing buf_ids
+ */
+static inline u32 idpf_tx_splitq_get_free_bufs(struct idpf_sw_queue *refillq)
+{
+	return (refillq->next_to_use > refillq->next_to_clean ?
+		0 : refillq->desc_count) +
+	       refillq->next_to_use - refillq->next_to_clean - 1;
+}
+
 int idpf_vport_singleq_napi_poll(struct napi_struct *napi, int budget);
 void idpf_vport_init_num_qs(struct idpf_vport *vport,
 			    struct virtchnl2_create_vport *vport_msg);
@@ -1038,10 +1019,8 @@ void idpf_tx_buf_hw_update(struct idpf_tx_queue *tx_q, u32 val,
 			   bool xmit_more);
 unsigned int idpf_size_to_txd_count(unsigned int size);
 netdev_tx_t idpf_tx_drop_skb(struct idpf_tx_queue *tx_q, struct sk_buff *skb);
-void idpf_tx_dma_map_error(struct idpf_tx_queue *txq, struct sk_buff *skb,
-			   struct idpf_tx_buf *first, u16 ring_idx);
-unsigned int idpf_tx_desc_count_required(struct idpf_tx_queue *txq,
-					 struct sk_buff *skb);
+unsigned int idpf_tx_res_count_required(struct idpf_tx_queue *txq,
+					struct sk_buff *skb, u32 *buf_count);
 void idpf_tx_timeout(struct net_device *netdev, unsigned int txqueue);
 netdev_tx_t idpf_tx_singleq_frame(struct sk_buff *skb,
 				  struct idpf_tx_queue *tx_q);
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_e610.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_e610.c
index d741164..bfeef5b 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_e610.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_e610.c
@@ -3125,7 +3125,7 @@ static int ixgbe_get_orom_ver_info(struct ixgbe_hw *hw,
 	if (err)
 		return err;
 
-	combo_ver = le32_to_cpu(civd.combo_ver);
+	combo_ver = get_unaligned_le32(&civd.combo_ver);
 
 	orom->major = (u8)FIELD_GET(IXGBE_OROM_VER_MASK, combo_ver);
 	orom->patch = (u8)FIELD_GET(IXGBE_OROM_VER_PATCH_MASK, combo_ver);
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_type_e610.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_type_e610.h
index d2f22d8..ff8d640a 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_type_e610.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_type_e610.h
@@ -932,7 +932,7 @@ struct ixgbe_orom_civd_info {
 	__le32 combo_ver;	/* Combo Image Version number */
 	u8 combo_name_len;	/* Length of the unicode combo image version string, max of 32 */
 	__le16 combo_name[32];	/* Unicode string representing the Combo Image version */
-};
+} __packed;
 
 /* Function specific capabilities */
 struct ixgbe_hw_func_caps {
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c
index 4ff19a0..0c46ba8 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c
@@ -1978,6 +1978,13 @@ static int cgx_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		goto err_release_regions;
 	}
 
+	if (!is_cn20k(pdev) &&
+	    !is_cgx_mapped_to_nix(pdev->subsystem_device, cgx->cgx_id)) {
+		dev_notice(dev, "CGX %d not mapped to NIX, skipping probe\n",
+			   cgx->cgx_id);
+		goto err_release_regions;
+	}
+
 	cgx->lmac_count = cgx->mac_ops->get_nr_lmacs(cgx);
 	if (!cgx->lmac_count) {
 		dev_notice(dev, "CGX %d LMAC count is zero, skipping probe\n", cgx->cgx_id);
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
index 7ee1fde..18c7bb3 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
@@ -783,6 +783,20 @@ static inline bool is_cn10kb(struct rvu *rvu)
 	return false;
 }
 
+static inline bool is_cgx_mapped_to_nix(unsigned short id, u8 cgx_id)
+{
+	/* On CNF10KA and CNF10KB silicons only two CGX blocks are connected
+	 * to NIX.
+	 */
+	if (id == PCI_SUBSYS_DEVID_CNF10K_A || id == PCI_SUBSYS_DEVID_CNF10K_B)
+		return cgx_id <= 1;
+
+	return !(cgx_id && !(id == PCI_SUBSYS_DEVID_96XX ||
+			     id == PCI_SUBSYS_DEVID_98XX ||
+			     id == PCI_SUBSYS_DEVID_CN10K_A ||
+			     id == PCI_SUBSYS_DEVID_CN10K_B));
+}
+
 static inline bool is_rvu_npc_hash_extract_en(struct rvu *rvu)
 {
 	u64 npc_const3;
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
index f674729..aff17c3 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
@@ -124,7 +124,9 @@ void otx2_get_dev_stats(struct otx2_nic *pfvf)
 			       dev_stats->rx_ucast_frames;
 
 	dev_stats->tx_bytes = OTX2_GET_TX_STATS(TX_OCTS);
-	dev_stats->tx_drops = OTX2_GET_TX_STATS(TX_DROP);
+	dev_stats->tx_drops = OTX2_GET_TX_STATS(TX_DROP) +
+			       (unsigned long)atomic_long_read(&dev_stats->tx_discards);
+
 	dev_stats->tx_bcast_frames = OTX2_GET_TX_STATS(TX_BCAST);
 	dev_stats->tx_mcast_frames = OTX2_GET_TX_STATS(TX_MCAST);
 	dev_stats->tx_ucast_frames = OTX2_GET_TX_STATS(TX_UCAST);
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
index e3765b7..1c8a3c0 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
@@ -153,6 +153,7 @@ struct otx2_dev_stats {
 	u64 tx_bcast_frames;
 	u64 tx_mcast_frames;
 	u64 tx_drops;
+	atomic_long_t tx_discards;
 };
 
 /* Driver counted stats */
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
index b23585c..5027fae 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
@@ -2220,6 +2220,7 @@ static netdev_tx_t otx2_xmit(struct sk_buff *skb, struct net_device *netdev)
 {
 	struct otx2_nic *pf = netdev_priv(netdev);
 	int qidx = skb_get_queue_mapping(skb);
+	struct otx2_dev_stats *dev_stats;
 	struct otx2_snd_queue *sq;
 	struct netdev_queue *txq;
 	int sq_idx;
@@ -2232,6 +2233,8 @@ static netdev_tx_t otx2_xmit(struct sk_buff *skb, struct net_device *netdev)
 	/* Check for minimum and maximum packet length */
 	if (skb->len <= ETH_HLEN ||
 	    (!skb_shinfo(skb)->gso_size && skb->len > pf->tx_max_pktlen)) {
+		dev_stats = &pf->hw.dev_stats;
+		atomic_long_inc(&dev_stats->tx_discards);
 		dev_kfree_skb(skb);
 		return NETDEV_TX_OK;
 	}
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c
index 5589fcc..7ebb6e6 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c
@@ -417,9 +417,19 @@ static netdev_tx_t otx2vf_xmit(struct sk_buff *skb, struct net_device *netdev)
 {
 	struct otx2_nic *vf = netdev_priv(netdev);
 	int qidx = skb_get_queue_mapping(skb);
+	struct otx2_dev_stats *dev_stats;
 	struct otx2_snd_queue *sq;
 	struct netdev_queue *txq;
 
+	/* Check for minimum and maximum packet length */
+	if (skb->len <= ETH_HLEN ||
+	    (!skb_shinfo(skb)->gso_size && skb->len > vf->tx_max_pktlen)) {
+		dev_stats = &vf->hw.dev_stats;
+		atomic_long_inc(&dev_stats->tx_discards);
+		dev_kfree_skb(skb);
+		return NETDEV_TX_OK;
+	}
+
 	sq = &vf->qset.sq[qidx];
 	txq = netdev_get_tx_queue(netdev, qidx);
 
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/rep.c b/drivers/net/ethernet/marvell/octeontx2/nic/rep.c
index 25af980..b476733 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/rep.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/rep.c
@@ -371,7 +371,8 @@ static void rvu_rep_get_stats(struct work_struct *work)
 	stats->rx_mcast_frames = rsp->rx.mcast;
 	stats->tx_bytes = rsp->tx.octs;
 	stats->tx_frames = rsp->tx.ucast + rsp->tx.bcast + rsp->tx.mcast;
-	stats->tx_drops = rsp->tx.drop;
+	stats->tx_drops = rsp->tx.drop +
+			  (unsigned long)atomic_long_read(&stats->tx_discards);
 exit:
 	mutex_unlock(&priv->mbox.lock);
 }
@@ -418,6 +419,16 @@ static netdev_tx_t rvu_rep_xmit(struct sk_buff *skb, struct net_device *dev)
 	struct otx2_nic *pf = rep->mdev;
 	struct otx2_snd_queue *sq;
 	struct netdev_queue *txq;
+	struct rep_stats *stats;
+
+	/* Check for minimum and maximum packet length */
+	if (skb->len <= ETH_HLEN ||
+	    (!skb_shinfo(skb)->gso_size && skb->len > pf->tx_max_pktlen)) {
+		stats = &rep->stats;
+		atomic_long_inc(&stats->tx_discards);
+		dev_kfree_skb(skb);
+		return NETDEV_TX_OK;
+	}
 
 	sq = &pf->qset.sq[rep->rep_id];
 	txq = netdev_get_tx_queue(dev, 0);
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/rep.h b/drivers/net/ethernet/marvell/octeontx2/nic/rep.h
index 38446b3..5bc9e2c 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/rep.h
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/rep.h
@@ -27,6 +27,7 @@ struct rep_stats {
 	u64 tx_bytes;
 	u64 tx_frames;
 	u64 tx_drops;
+	atomic_long_t tx_discards;
 };
 
 struct rep_dev {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
index 3ffa3fb..2c0e0c1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
@@ -160,7 +160,7 @@ static int mlx5_devlink_reload_fw_activate(struct devlink *devlink, struct netli
 	if (err)
 		return err;
 
-	mlx5_unload_one_devl_locked(dev, true);
+	mlx5_sync_reset_unload_flow(dev, true);
 	err = mlx5_health_wait_pci_up(dev);
 	if (err)
 		NL_SET_ERR_MSG_MOD(extack, "FW activate aborted, PCI reads fail after reset");
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c b/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c
index 3efa8bf..4720523 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c
@@ -575,7 +575,6 @@ int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv,
 		if (err)
 			return err;
 	}
-	priv->dcbx.xoff = xoff;
 
 	/* Apply the settings */
 	if (update_buffer) {
@@ -584,6 +583,8 @@ int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv,
 			return err;
 	}
 
+	priv->dcbx.xoff = xoff;
+
 	if (update_prio2buffer)
 		err = mlx5e_port_set_priority2buffer(priv->mdev, prio2buffer);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.h b/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.h
index f4a19ff..66d276a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.h
@@ -66,11 +66,23 @@ struct mlx5e_port_buffer {
 	struct mlx5e_bufferx_reg  buffer[MLX5E_MAX_NETWORK_BUFFER];
 };
 
+#ifdef CONFIG_MLX5_CORE_EN_DCB
 int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv,
 				    u32 change, unsigned int mtu,
 				    struct ieee_pfc *pfc,
 				    u32 *buffer_size,
 				    u8 *prio2buffer);
+#else
+static inline int
+mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv,
+				u32 change, unsigned int mtu,
+				void *pfc,
+				u32 *buffer_size,
+				u8 *prio2buffer)
+{
+	return 0;
+}
+#endif
 
 int mlx5e_port_query_buffer(struct mlx5e_priv *priv,
 			    struct mlx5e_port_buffer *port_buffer);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 21bb88c..e680673 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -49,6 +49,7 @@
 #include "en.h"
 #include "en/dim.h"
 #include "en/txrx.h"
+#include "en/port_buffer.h"
 #include "en_tc.h"
 #include "en_rep.h"
 #include "en_accel/ipsec.h"
@@ -138,6 +139,8 @@ void mlx5e_update_carrier(struct mlx5e_priv *priv)
 	if (up) {
 		netdev_info(priv->netdev, "Link up\n");
 		netif_carrier_on(priv->netdev);
+		mlx5e_port_manual_buffer_config(priv, 0, priv->netdev->mtu,
+						NULL, NULL, NULL);
 	} else {
 		netdev_info(priv->netdev, "Link down\n");
 		netif_carrier_off(priv->netdev);
@@ -3040,9 +3043,11 @@ int mlx5e_set_dev_port_mtu(struct mlx5e_priv *priv)
 	struct mlx5e_params *params = &priv->channels.params;
 	struct net_device *netdev = priv->netdev;
 	struct mlx5_core_dev *mdev = priv->mdev;
-	u16 mtu;
+	u16 mtu, prev_mtu;
 	int err;
 
+	mlx5e_query_mtu(mdev, params, &prev_mtu);
+
 	err = mlx5e_set_mtu(mdev, params, params->sw_mtu);
 	if (err)
 		return err;
@@ -3052,6 +3057,18 @@ int mlx5e_set_dev_port_mtu(struct mlx5e_priv *priv)
 		netdev_warn(netdev, "%s: VPort MTU %d is different than netdev mtu %d\n",
 			    __func__, mtu, params->sw_mtu);
 
+	if (mtu != prev_mtu && MLX5_BUFFER_SUPPORTED(mdev)) {
+		err = mlx5e_port_manual_buffer_config(priv, 0, mtu,
+						      NULL, NULL, NULL);
+		if (err) {
+			netdev_warn(netdev, "%s: Failed to set Xon/Xoff values with MTU %d (err %d), setting back to previous MTU %d\n",
+				    __func__, mtu, err, prev_mtu);
+
+			mlx5e_set_mtu(mdev, params, prev_mtu);
+			return err;
+		}
+	}
+
 	params->sw_mtu = mtu;
 	return 0;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index d873923..cb16508 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -3734,6 +3734,13 @@ static int mlx5_fs_mode_validate(struct devlink *devlink, u32 id,
 	char *value = val.vstr;
 	u8 eswitch_mode;
 
+	eswitch_mode = mlx5_eswitch_mode(dev);
+	if (eswitch_mode == MLX5_ESWITCH_OFFLOADS) {
+		NL_SET_ERR_MSG_FMT_MOD(extack,
+				       "Changing fs mode is not supported when eswitch offloads enabled.");
+		return -EOPNOTSUPP;
+	}
+
 	if (!strcmp(value, "dmfs"))
 		return 0;
 
@@ -3759,14 +3766,6 @@ static int mlx5_fs_mode_validate(struct devlink *devlink, u32 id,
 		return -EINVAL;
 	}
 
-	eswitch_mode = mlx5_eswitch_mode(dev);
-	if (eswitch_mode == MLX5_ESWITCH_OFFLOADS) {
-		NL_SET_ERR_MSG_FMT_MOD(extack,
-				       "Moving to %s is not supported when eswitch offloads enabled.",
-				       value);
-		return -EOPNOTSUPP;
-	}
-
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
index 69933ad..2299513 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
@@ -6,13 +6,15 @@
 #include "fw_reset.h"
 #include "diag/fw_tracer.h"
 #include "lib/tout.h"
+#include "sf/sf.h"
 
 enum {
 	MLX5_FW_RESET_FLAGS_RESET_REQUESTED,
 	MLX5_FW_RESET_FLAGS_NACK_RESET_REQUEST,
 	MLX5_FW_RESET_FLAGS_PENDING_COMP,
 	MLX5_FW_RESET_FLAGS_DROP_NEW_REQUESTS,
-	MLX5_FW_RESET_FLAGS_RELOAD_REQUIRED
+	MLX5_FW_RESET_FLAGS_RELOAD_REQUIRED,
+	MLX5_FW_RESET_FLAGS_UNLOAD_EVENT,
 };
 
 struct mlx5_fw_reset {
@@ -219,7 +221,7 @@ int mlx5_fw_reset_set_live_patch(struct mlx5_core_dev *dev)
 	return mlx5_reg_mfrl_set(dev, MLX5_MFRL_REG_RESET_LEVEL0, 0, 0, false);
 }
 
-static void mlx5_fw_reset_complete_reload(struct mlx5_core_dev *dev, bool unloaded)
+static void mlx5_fw_reset_complete_reload(struct mlx5_core_dev *dev)
 {
 	struct mlx5_fw_reset *fw_reset = dev->priv.fw_reset;
 	struct devlink *devlink = priv_to_devlink(dev);
@@ -228,8 +230,7 @@ static void mlx5_fw_reset_complete_reload(struct mlx5_core_dev *dev, bool unload
 	if (test_bit(MLX5_FW_RESET_FLAGS_PENDING_COMP, &fw_reset->reset_flags)) {
 		complete(&fw_reset->done);
 	} else {
-		if (!unloaded)
-			mlx5_unload_one(dev, false);
+		mlx5_sync_reset_unload_flow(dev, false);
 		if (mlx5_health_wait_pci_up(dev))
 			mlx5_core_err(dev, "reset reload flow aborted, PCI reads still not working\n");
 		else
@@ -272,7 +273,7 @@ static void mlx5_sync_reset_reload_work(struct work_struct *work)
 
 	mlx5_sync_reset_clear_reset_requested(dev, false);
 	mlx5_enter_error_state(dev, true);
-	mlx5_fw_reset_complete_reload(dev, false);
+	mlx5_fw_reset_complete_reload(dev);
 }
 
 #define MLX5_RESET_POLL_INTERVAL	(HZ / 10)
@@ -428,6 +429,11 @@ static bool mlx5_is_reset_now_capable(struct mlx5_core_dev *dev,
 		return false;
 	}
 
+	if (!mlx5_core_is_ecpf(dev) && !mlx5_sf_table_empty(dev)) {
+		mlx5_core_warn(dev, "SFs should be removed before reset\n");
+		return false;
+	}
+
 #if IS_ENABLED(CONFIG_HOTPLUG_PCI_PCIE)
 	if (reset_method != MLX5_MFRL_REG_PCI_RESET_METHOD_HOT_RESET) {
 		err = mlx5_check_hotplug_interrupt(dev, bridge);
@@ -586,65 +592,23 @@ static int mlx5_sync_pci_reset(struct mlx5_core_dev *dev, u8 reset_method)
 	return err;
 }
 
-static void mlx5_sync_reset_now_event(struct work_struct *work)
+void mlx5_sync_reset_unload_flow(struct mlx5_core_dev *dev, bool locked)
 {
-	struct mlx5_fw_reset *fw_reset = container_of(work, struct mlx5_fw_reset,
-						      reset_now_work);
-	struct mlx5_core_dev *dev = fw_reset->dev;
-	int err;
-
-	if (mlx5_sync_reset_clear_reset_requested(dev, false))
-		return;
-
-	mlx5_core_warn(dev, "Sync Reset now. Device is going to reset.\n");
-
-	err = mlx5_cmd_fast_teardown_hca(dev);
-	if (err) {
-		mlx5_core_warn(dev, "Fast teardown failed, no reset done, err %d\n", err);
-		goto done;
-	}
-
-	err = mlx5_sync_pci_reset(dev, fw_reset->reset_method);
-	if (err) {
-		mlx5_core_warn(dev, "mlx5_sync_pci_reset failed, no reset done, err %d\n", err);
-		set_bit(MLX5_FW_RESET_FLAGS_RELOAD_REQUIRED, &fw_reset->reset_flags);
-	}
-
-	mlx5_enter_error_state(dev, true);
-done:
-	fw_reset->ret = err;
-	mlx5_fw_reset_complete_reload(dev, false);
-}
-
-static void mlx5_sync_reset_unload_event(struct work_struct *work)
-{
-	struct mlx5_fw_reset *fw_reset;
-	struct mlx5_core_dev *dev;
+	struct mlx5_fw_reset *fw_reset = dev->priv.fw_reset;
 	unsigned long timeout;
 	int poll_freq = 20;
 	bool reset_action;
 	u8 rst_state;
 	int err;
 
-	fw_reset = container_of(work, struct mlx5_fw_reset, reset_unload_work);
-	dev = fw_reset->dev;
-
-	if (mlx5_sync_reset_clear_reset_requested(dev, false))
-		return;
-
-	mlx5_core_warn(dev, "Sync Reset Unload. Function is forced down.\n");
-
-	err = mlx5_cmd_fast_teardown_hca(dev);
-	if (err)
-		mlx5_core_warn(dev, "Fast teardown failed, unloading, err %d\n", err);
-	else
-		mlx5_enter_error_state(dev, true);
-
-	if (test_bit(MLX5_FW_RESET_FLAGS_PENDING_COMP, &fw_reset->reset_flags))
+	if (locked)
 		mlx5_unload_one_devl_locked(dev, false);
 	else
 		mlx5_unload_one(dev, false);
 
+	if (!test_bit(MLX5_FW_RESET_FLAGS_UNLOAD_EVENT, &fw_reset->reset_flags))
+		return;
+
 	mlx5_set_fw_rst_ack(dev);
 	mlx5_core_warn(dev, "Sync Reset Unload done, device reset expected\n");
 
@@ -672,17 +636,73 @@ static void mlx5_sync_reset_unload_event(struct work_struct *work)
 		goto done;
 	}
 
-	mlx5_core_warn(dev, "Sync Reset, got reset action. rst_state = %u\n", rst_state);
+	mlx5_core_warn(dev, "Sync Reset, got reset action. rst_state = %u\n",
+		       rst_state);
 	if (rst_state == MLX5_FW_RST_STATE_TOGGLE_REQ) {
 		err = mlx5_sync_pci_reset(dev, fw_reset->reset_method);
 		if (err) {
-			mlx5_core_warn(dev, "mlx5_sync_pci_reset failed, err %d\n", err);
+			mlx5_core_warn(dev, "mlx5_sync_pci_reset failed, err %d\n",
+				       err);
 			fw_reset->ret = err;
 		}
 	}
 
 done:
-	mlx5_fw_reset_complete_reload(dev, true);
+	clear_bit(MLX5_FW_RESET_FLAGS_UNLOAD_EVENT, &fw_reset->reset_flags);
+}
+
+static void mlx5_sync_reset_now_event(struct work_struct *work)
+{
+	struct mlx5_fw_reset *fw_reset = container_of(work, struct mlx5_fw_reset,
+						      reset_now_work);
+	struct mlx5_core_dev *dev = fw_reset->dev;
+	int err;
+
+	if (mlx5_sync_reset_clear_reset_requested(dev, false))
+		return;
+
+	mlx5_core_warn(dev, "Sync Reset now. Device is going to reset.\n");
+
+	err = mlx5_cmd_fast_teardown_hca(dev);
+	if (err) {
+		mlx5_core_warn(dev, "Fast teardown failed, no reset done, err %d\n", err);
+		goto done;
+	}
+
+	err = mlx5_sync_pci_reset(dev, fw_reset->reset_method);
+	if (err) {
+		mlx5_core_warn(dev, "mlx5_sync_pci_reset failed, no reset done, err %d\n", err);
+		set_bit(MLX5_FW_RESET_FLAGS_RELOAD_REQUIRED, &fw_reset->reset_flags);
+	}
+
+	mlx5_enter_error_state(dev, true);
+done:
+	fw_reset->ret = err;
+	mlx5_fw_reset_complete_reload(dev);
+}
+
+static void mlx5_sync_reset_unload_event(struct work_struct *work)
+{
+	struct mlx5_fw_reset *fw_reset;
+	struct mlx5_core_dev *dev;
+	int err;
+
+	fw_reset = container_of(work, struct mlx5_fw_reset, reset_unload_work);
+	dev = fw_reset->dev;
+
+	if (mlx5_sync_reset_clear_reset_requested(dev, false))
+		return;
+
+	set_bit(MLX5_FW_RESET_FLAGS_UNLOAD_EVENT, &fw_reset->reset_flags);
+	mlx5_core_warn(dev, "Sync Reset Unload. Function is forced down.\n");
+
+	err = mlx5_cmd_fast_teardown_hca(dev);
+	if (err)
+		mlx5_core_warn(dev, "Fast teardown failed, unloading, err %d\n", err);
+	else
+		mlx5_enter_error_state(dev, true);
+
+	mlx5_fw_reset_complete_reload(dev);
 }
 
 static void mlx5_sync_reset_abort_event(struct work_struct *work)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.h b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.h
index ea527d0..d5b2852 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.h
@@ -12,6 +12,7 @@ int mlx5_fw_reset_set_reset_sync(struct mlx5_core_dev *dev, u8 reset_type_sel,
 int mlx5_fw_reset_set_live_patch(struct mlx5_core_dev *dev);
 
 int mlx5_fw_reset_wait_reset_done(struct mlx5_core_dev *dev);
+void mlx5_sync_reset_unload_flow(struct mlx5_core_dev *dev, bool locked);
 int mlx5_fw_reset_verify_fw_complete(struct mlx5_core_dev *dev,
 				     struct netlink_ext_ack *extack);
 void mlx5_fw_reset_events_start(struct mlx5_core_dev *dev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c
index 0864ba6..3304f25 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c
@@ -518,3 +518,13 @@ void mlx5_sf_table_cleanup(struct mlx5_core_dev *dev)
 	WARN_ON(!xa_empty(&table->function_ids));
 	kfree(table);
 }
+
+bool mlx5_sf_table_empty(const struct mlx5_core_dev *dev)
+{
+	struct mlx5_sf_table *table = dev->priv.sf_table;
+
+	if (!table)
+		return true;
+
+	return xa_empty(&table->function_ids);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/sf.h b/drivers/net/ethernet/mellanox/mlx5/core/sf/sf.h
index 860f9dd..89559a3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/sf/sf.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/sf.h
@@ -17,6 +17,7 @@ void mlx5_sf_hw_table_destroy(struct mlx5_core_dev *dev);
 
 int mlx5_sf_table_init(struct mlx5_core_dev *dev);
 void mlx5_sf_table_cleanup(struct mlx5_core_dev *dev);
+bool mlx5_sf_table_empty(const struct mlx5_core_dev *dev);
 
 int mlx5_devlink_sf_port_new(struct devlink *devlink,
 			     const struct devlink_port_new_attrs *add_attr,
@@ -61,6 +62,11 @@ static inline void mlx5_sf_table_cleanup(struct mlx5_core_dev *dev)
 {
 }
 
+static inline bool mlx5_sf_table_empty(const struct mlx5_core_dev *dev)
+{
+	return true;
+}
+
 #endif
 
 #endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/action.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/action.c
index 3968043..6b36a4a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/action.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/action.c
@@ -117,7 +117,7 @@ static int hws_action_get_shared_stc_nic(struct mlx5hws_context *ctx,
 		mlx5hws_err(ctx, "No such stc_type: %d\n", stc_type);
 		pr_warn("HWS: Invalid stc_type: %d\n", stc_type);
 		ret = -EINVAL;
-		goto unlock_and_out;
+		goto free_shared_stc;
 	}
 
 	ret = mlx5hws_action_alloc_single_stc(ctx, &stc_attr, tbl_type,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pat_arg.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pat_arg.c
index 51e4c551..d56271a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pat_arg.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pat_arg.c
@@ -279,7 +279,7 @@ int mlx5hws_pat_get_pattern(struct mlx5hws_context *ctx,
 	return ret;
 
 clean_pattern:
-	mlx5hws_cmd_header_modify_pattern_destroy(ctx->mdev, *pattern_id);
+	mlx5hws_cmd_header_modify_pattern_destroy(ctx->mdev, ptrn_id);
 out_unlock:
 	mutex_unlock(&ctx->pattern_cache->lock);
 	return ret;
@@ -527,7 +527,6 @@ int mlx5hws_pat_calc_nop(__be64 *pattern, size_t num_actions,
 			 u32 *nop_locations, __be64 *new_pat)
 {
 	u16 prev_src_field = INVALID_FIELD, prev_dst_field = INVALID_FIELD;
-	u16 src_field, dst_field;
 	u8 action_type;
 	bool dependent;
 	size_t i, j;
@@ -539,6 +538,9 @@ int mlx5hws_pat_calc_nop(__be64 *pattern, size_t num_actions,
 		return 0;
 
 	for (i = 0, j = 0; i < num_actions; i++, j++) {
+		u16 src_field = INVALID_FIELD;
+		u16 dst_field = INVALID_FIELD;
+
 		if (j >= max_actions)
 			return -EINVAL;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pool.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pool.c
index 7e37d6e..7b5071c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pool.c
@@ -124,6 +124,7 @@ static int hws_pool_buddy_init(struct mlx5hws_pool *pool)
 		mlx5hws_err(pool->ctx, "Failed to create resource type: %d size %zu\n",
 			    pool->type, pool->alloc_log_sz);
 		mlx5hws_buddy_cleanup(buddy);
+		kfree(buddy);
 		return -ENOMEM;
 	}
 
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c b/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c
index e67e994..4058155 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c
@@ -52,6 +52,8 @@ int __fbnic_open(struct fbnic_net *fbn)
 	fbnic_bmc_rpc_init(fbd);
 	fbnic_rss_reinit(fbd, fbn);
 
+	phylink_resume(fbn->phylink);
+
 	return 0;
 time_stop:
 	fbnic_time_stop(fbn);
@@ -84,6 +86,8 @@ static int fbnic_stop(struct net_device *netdev)
 {
 	struct fbnic_net *fbn = netdev_priv(netdev);
 
+	phylink_suspend(fbn->phylink, fbnic_bmc_present(fbn->fbd));
+
 	fbnic_down(fbn);
 	fbnic_pcs_free_irq(fbn->fbd);
 
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_pci.c b/drivers/net/ethernet/meta/fbnic/fbnic_pci.c
index b70e4ca..28e23e3 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_pci.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_pci.c
@@ -118,14 +118,12 @@ static void fbnic_service_task_start(struct fbnic_net *fbn)
 	struct fbnic_dev *fbd = fbn->fbd;
 
 	schedule_delayed_work(&fbd->service_task, HZ);
-	phylink_resume(fbn->phylink);
 }
 
 static void fbnic_service_task_stop(struct fbnic_net *fbn)
 {
 	struct fbnic_dev *fbd = fbn->fbd;
 
-	phylink_suspend(fbn->phylink, fbnic_bmc_present(fbd));
 	cancel_delayed_work(&fbd->service_task);
 }
 
@@ -443,11 +441,10 @@ static int __fbnic_pm_resume(struct device *dev)
 
 	/* Re-enable mailbox */
 	err = fbnic_fw_request_mbx(fbd);
+	devl_unlock(priv_to_devlink(fbd));
 	if (err)
 		goto err_free_irqs;
 
-	devl_unlock(priv_to_devlink(fbd));
-
 	/* Only send log history if log buffer is empty to prevent duplicate
 	 * log entries.
 	 */
@@ -464,20 +461,20 @@ static int __fbnic_pm_resume(struct device *dev)
 
 	rtnl_lock();
 
-	if (netif_running(netdev)) {
+	if (netif_running(netdev))
 		err = __fbnic_open(fbn);
-		if (err)
-			goto err_free_mbx;
-	}
 
 	rtnl_unlock();
+	if (err)
+		goto err_free_mbx;
 
 	return 0;
 err_free_mbx:
 	fbnic_fw_log_disable(fbd);
 
-	rtnl_unlock();
+	devl_lock(priv_to_devlink(fbd));
 	fbnic_fw_free_mbx(fbd);
+	devl_unlock(priv_to_devlink(fbd));
 err_free_irqs:
 	fbnic_free_irqs(fbd);
 err_invalidate_uc_addr:
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
index 6cadf8d..00e929b 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
@@ -49,6 +49,14 @@ static void dwxgmac2_core_init(struct mac_device_info *hw,
 	writel(XGMAC_INT_DEFAULT_EN, ioaddr + XGMAC_INT_EN);
 }
 
+static void dwxgmac2_update_caps(struct stmmac_priv *priv)
+{
+	if (!priv->dma_cap.mbps_10_100)
+		priv->hw->link.caps &= ~(MAC_10 | MAC_100);
+	else if (!priv->dma_cap.half_duplex)
+		priv->hw->link.caps &= ~(MAC_10HD | MAC_100HD);
+}
+
 static void dwxgmac2_set_mac(void __iomem *ioaddr, bool enable)
 {
 	u32 tx = readl(ioaddr + XGMAC_TX_CONFIG);
@@ -1424,6 +1432,7 @@ static void dwxgmac2_set_arp_offload(struct mac_device_info *hw, bool en,
 
 const struct stmmac_ops dwxgmac210_ops = {
 	.core_init = dwxgmac2_core_init,
+	.update_caps = dwxgmac2_update_caps,
 	.set_mac = dwxgmac2_set_mac,
 	.rx_ipc = dwxgmac2_rx_ipc,
 	.rx_queue_enable = dwxgmac2_rx_queue_enable,
@@ -1532,8 +1541,8 @@ int dwxgmac2_setup(struct stmmac_priv *priv)
 		mac->mcast_bits_log2 = ilog2(mac->multicast_filter_bins);
 
 	mac->link.caps = MAC_ASYM_PAUSE | MAC_SYM_PAUSE |
-			 MAC_1000FD | MAC_2500FD | MAC_5000FD |
-			 MAC_10000FD;
+			 MAC_10 | MAC_100 | MAC_1000FD |
+			 MAC_2500FD | MAC_5000FD | MAC_10000FD;
 	mac->link.duplex = 0;
 	mac->link.speed10 = XGMAC_CONFIG_SS_10_MII;
 	mac->link.speed100 = XGMAC_CONFIG_SS_100_MII;
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c
index 5dcc95bc..4d6bb99 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c
@@ -203,10 +203,6 @@ static void dwxgmac2_dma_rx_mode(struct stmmac_priv *priv, void __iomem *ioaddr,
 	}
 
 	writel(value, ioaddr + XGMAC_MTL_RXQ_OPMODE(channel));
-
-	/* Enable MTL RX overflow */
-	value = readl(ioaddr + XGMAC_MTL_QINTEN(channel));
-	writel(value | XGMAC_RXOIE, ioaddr + XGMAC_MTL_QINTEN(channel));
 }
 
 static void dwxgmac2_dma_tx_mode(struct stmmac_priv *priv, void __iomem *ioaddr,
@@ -386,8 +382,11 @@ static int dwxgmac2_dma_interrupt(struct stmmac_priv *priv,
 static int dwxgmac2_get_hw_feature(void __iomem *ioaddr,
 				   struct dma_features *dma_cap)
 {
+	struct stmmac_priv *priv;
 	u32 hw_cap;
 
+	priv = container_of(dma_cap, struct stmmac_priv, dma_cap);
+
 	/* MAC HW feature 0 */
 	hw_cap = readl(ioaddr + XGMAC_HW_FEATURE0);
 	dma_cap->edma = (hw_cap & XGMAC_HWFEAT_EDMA) >> 31;
@@ -410,6 +409,8 @@ static int dwxgmac2_get_hw_feature(void __iomem *ioaddr,
 	dma_cap->vlhash = (hw_cap & XGMAC_HWFEAT_VLHASH) >> 4;
 	dma_cap->half_duplex = (hw_cap & XGMAC_HWFEAT_HDSEL) >> 3;
 	dma_cap->mbps_1000 = (hw_cap & XGMAC_HWFEAT_GMIISEL) >> 1;
+	if (dma_cap->mbps_1000 && priv->synopsys_id >= DWXGMAC_CORE_2_20)
+		dma_cap->mbps_10_100 = 1;
 
 	/* MAC HW feature 1 */
 	hw_cap = readl(ioaddr + XGMAC_HW_FEATURE1);
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index f1abf42..7b16d12 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -2584,6 +2584,7 @@ static bool stmmac_xdp_xmit_zc(struct stmmac_priv *priv, u32 queue, u32 budget)
 	struct netdev_queue *nq = netdev_get_tx_queue(priv->dev, queue);
 	struct stmmac_tx_queue *tx_q = &priv->dma_conf.tx_queue[queue];
 	struct stmmac_txq_stats *txq_stats = &priv->xstats.txq_stats[queue];
+	bool csum = !priv->plat->tx_queues_cfg[queue].coe_unsupported;
 	struct xsk_buff_pool *pool = tx_q->xsk_pool;
 	unsigned int entry = tx_q->cur_tx;
 	struct dma_desc *tx_desc = NULL;
@@ -2671,7 +2672,7 @@ static bool stmmac_xdp_xmit_zc(struct stmmac_priv *priv, u32 queue, u32 budget)
 		}
 
 		stmmac_prepare_tx_desc(priv, tx_desc, 1, xdp_desc.len,
-				       true, priv->mode, true, true,
+				       csum, priv->mode, true, true,
 				       xdp_desc.len);
 
 		stmmac_enable_dma_transmission(priv, priv->ioaddr, queue);
@@ -4983,6 +4984,7 @@ static int stmmac_xdp_xmit_xdpf(struct stmmac_priv *priv, int queue,
 {
 	struct stmmac_txq_stats *txq_stats = &priv->xstats.txq_stats[queue];
 	struct stmmac_tx_queue *tx_q = &priv->dma_conf.tx_queue[queue];
+	bool csum = !priv->plat->tx_queues_cfg[queue].coe_unsupported;
 	unsigned int entry = tx_q->cur_tx;
 	struct dma_desc *tx_desc;
 	dma_addr_t dma_addr;
@@ -5034,7 +5036,7 @@ static int stmmac_xdp_xmit_xdpf(struct stmmac_priv *priv, int queue,
 	stmmac_set_desc_addr(priv, tx_desc, dma_addr);
 
 	stmmac_prepare_tx_desc(priv, tx_desc, 1, xdpf->len,
-			       true, priv->mode, true, true,
+			       csum, priv->mode, true, true,
 			       xdpf->len);
 
 	tx_q->tx_count_frames++;
diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c
index 7201046..60a4629 100644
--- a/drivers/net/hyperv/netvsc.c
+++ b/drivers/net/hyperv/netvsc.c
@@ -1812,6 +1812,11 @@ struct netvsc_device *netvsc_device_add(struct hv_device *device,
 
 	/* Enable NAPI handler before init callbacks */
 	netif_napi_add(ndev, &net_device->chan_table[0].napi, netvsc_poll);
+	napi_enable(&net_device->chan_table[0].napi);
+	netif_queue_set_napi(ndev, 0, NETDEV_QUEUE_TYPE_RX,
+			     &net_device->chan_table[0].napi);
+	netif_queue_set_napi(ndev, 0, NETDEV_QUEUE_TYPE_TX,
+			     &net_device->chan_table[0].napi);
 
 	/* Open the channel */
 	device->channel->next_request_id_callback = vmbus_next_request_id;
@@ -1831,12 +1836,6 @@ struct netvsc_device *netvsc_device_add(struct hv_device *device,
 	/* Channel is opened */
 	netdev_dbg(ndev, "hv_netvsc channel opened successfully\n");
 
-	napi_enable(&net_device->chan_table[0].napi);
-	netif_queue_set_napi(ndev, 0, NETDEV_QUEUE_TYPE_RX,
-			     &net_device->chan_table[0].napi);
-	netif_queue_set_napi(ndev, 0, NETDEV_QUEUE_TYPE_TX,
-			     &net_device->chan_table[0].napi);
-
 	/* Connect with the NetVsp */
 	ret = netvsc_connect_vsp(device, net_device, device_info);
 	if (ret != 0) {
@@ -1854,14 +1853,14 @@ struct netvsc_device *netvsc_device_add(struct hv_device *device,
 
 close:
 	RCU_INIT_POINTER(net_device_ctx->nvdev, NULL);
-	netif_queue_set_napi(ndev, 0, NETDEV_QUEUE_TYPE_TX, NULL);
-	netif_queue_set_napi(ndev, 0, NETDEV_QUEUE_TYPE_RX, NULL);
-	napi_disable(&net_device->chan_table[0].napi);
 
 	/* Now, we can close the channel safely */
 	vmbus_close(device->channel);
 
 cleanup:
+	netif_queue_set_napi(ndev, 0, NETDEV_QUEUE_TYPE_TX, NULL);
+	netif_queue_set_napi(ndev, 0, NETDEV_QUEUE_TYPE_RX, NULL);
+	napi_disable(&net_device->chan_table[0].napi);
 	netif_napi_del(&net_device->chan_table[0].napi);
 
 cleanup2:
diff --git a/drivers/net/hyperv/rndis_filter.c b/drivers/net/hyperv/rndis_filter.c
index 9e73959..c35f968 100644
--- a/drivers/net/hyperv/rndis_filter.c
+++ b/drivers/net/hyperv/rndis_filter.c
@@ -1252,17 +1252,26 @@ static void netvsc_sc_open(struct vmbus_channel *new_sc)
 	new_sc->rqstor_size = netvsc_rqstor_size(netvsc_ring_bytes);
 	new_sc->max_pkt_size = NETVSC_MAX_PKT_SIZE;
 
+	/* Enable napi before opening the vmbus channel to avoid races
+	 * as the host placing data on the host->guest ring may be left
+	 * out if napi was not enabled.
+	 */
+	napi_enable(&nvchan->napi);
+	netif_queue_set_napi(ndev, chn_index, NETDEV_QUEUE_TYPE_RX,
+			     &nvchan->napi);
+	netif_queue_set_napi(ndev, chn_index, NETDEV_QUEUE_TYPE_TX,
+			     &nvchan->napi);
+
 	ret = vmbus_open(new_sc, netvsc_ring_bytes,
 			 netvsc_ring_bytes, NULL, 0,
 			 netvsc_channel_cb, nvchan);
-	if (ret == 0) {
-		napi_enable(&nvchan->napi);
-		netif_queue_set_napi(ndev, chn_index, NETDEV_QUEUE_TYPE_RX,
-				     &nvchan->napi);
-		netif_queue_set_napi(ndev, chn_index, NETDEV_QUEUE_TYPE_TX,
-				     &nvchan->napi);
-	} else {
+	if (ret != 0) {
 		netdev_notice(ndev, "sub channel open failed: %d\n", ret);
+		netif_queue_set_napi(ndev, chn_index, NETDEV_QUEUE_TYPE_TX,
+				     NULL);
+		netif_queue_set_napi(ndev, chn_index, NETDEV_QUEUE_TYPE_RX,
+				     NULL);
+		napi_disable(&nvchan->napi);
 	}
 
 	if (atomic_inc_return(&nvscdev->open_chn) == nvscdev->num_chn)
diff --git a/drivers/net/phy/mscc/mscc.h b/drivers/net/phy/mscc/mscc.h
index 58c6d47..2bfe314 100644
--- a/drivers/net/phy/mscc/mscc.h
+++ b/drivers/net/phy/mscc/mscc.h
@@ -481,6 +481,7 @@ static inline void vsc8584_config_macsec_intr(struct phy_device *phydev)
 void vsc85xx_link_change_notify(struct phy_device *phydev);
 void vsc8584_config_ts_intr(struct phy_device *phydev);
 int vsc8584_ptp_init(struct phy_device *phydev);
+void vsc8584_ptp_deinit(struct phy_device *phydev);
 int vsc8584_ptp_probe_once(struct phy_device *phydev);
 int vsc8584_ptp_probe(struct phy_device *phydev);
 irqreturn_t vsc8584_handle_ts_interrupt(struct phy_device *phydev);
@@ -495,6 +496,9 @@ static inline int vsc8584_ptp_init(struct phy_device *phydev)
 {
 	return 0;
 }
+static inline void vsc8584_ptp_deinit(struct phy_device *phydev)
+{
+}
 static inline int vsc8584_ptp_probe_once(struct phy_device *phydev)
 {
 	return 0;
diff --git a/drivers/net/phy/mscc/mscc_main.c b/drivers/net/phy/mscc/mscc_main.c
index f1c9ce3..24c7590 100644
--- a/drivers/net/phy/mscc/mscc_main.c
+++ b/drivers/net/phy/mscc/mscc_main.c
@@ -2337,9 +2337,7 @@ static int vsc85xx_probe(struct phy_device *phydev)
 
 static void vsc85xx_remove(struct phy_device *phydev)
 {
-	struct vsc8531_private *priv = phydev->priv;
-
-	skb_queue_purge(&priv->rx_skbs_list);
+	vsc8584_ptp_deinit(phydev);
 }
 
 /* Microsemi VSC85xx PHYs */
diff --git a/drivers/net/phy/mscc/mscc_ptp.c b/drivers/net/phy/mscc/mscc_ptp.c
index de6c731..7284732 100644
--- a/drivers/net/phy/mscc/mscc_ptp.c
+++ b/drivers/net/phy/mscc/mscc_ptp.c
@@ -1298,7 +1298,6 @@ static void vsc8584_set_input_clk_configured(struct phy_device *phydev)
 
 static int __vsc8584_init_ptp(struct phy_device *phydev)
 {
-	struct vsc8531_private *vsc8531 = phydev->priv;
 	static const u32 ltc_seq_e[] = { 0, 400000, 0, 0, 0 };
 	static const u8  ltc_seq_a[] = { 8, 6, 5, 4, 2 };
 	u32 val;
@@ -1515,17 +1514,7 @@ static int __vsc8584_init_ptp(struct phy_device *phydev)
 
 	vsc85xx_ts_eth_cmp1_sig(phydev);
 
-	vsc8531->mii_ts.rxtstamp = vsc85xx_rxtstamp;
-	vsc8531->mii_ts.txtstamp = vsc85xx_txtstamp;
-	vsc8531->mii_ts.hwtstamp = vsc85xx_hwtstamp;
-	vsc8531->mii_ts.ts_info  = vsc85xx_ts_info;
-	phydev->mii_ts = &vsc8531->mii_ts;
-
-	memcpy(&vsc8531->ptp->caps, &vsc85xx_clk_caps, sizeof(vsc85xx_clk_caps));
-
-	vsc8531->ptp->ptp_clock = ptp_clock_register(&vsc8531->ptp->caps,
-						     &phydev->mdio.dev);
-	return PTR_ERR_OR_ZERO(vsc8531->ptp->ptp_clock);
+	return 0;
 }
 
 void vsc8584_config_ts_intr(struct phy_device *phydev)
@@ -1552,6 +1541,16 @@ int vsc8584_ptp_init(struct phy_device *phydev)
 	return 0;
 }
 
+void vsc8584_ptp_deinit(struct phy_device *phydev)
+{
+	struct vsc8531_private *vsc8531 = phydev->priv;
+
+	if (vsc8531->ptp->ptp_clock) {
+		ptp_clock_unregister(vsc8531->ptp->ptp_clock);
+		skb_queue_purge(&vsc8531->rx_skbs_list);
+	}
+}
+
 irqreturn_t vsc8584_handle_ts_interrupt(struct phy_device *phydev)
 {
 	struct vsc8531_private *priv = phydev->priv;
@@ -1612,7 +1611,16 @@ int vsc8584_ptp_probe(struct phy_device *phydev)
 
 	vsc8531->ptp->phydev = phydev;
 
-	return 0;
+	vsc8531->mii_ts.rxtstamp = vsc85xx_rxtstamp;
+	vsc8531->mii_ts.txtstamp = vsc85xx_txtstamp;
+	vsc8531->mii_ts.hwtstamp = vsc85xx_hwtstamp;
+	vsc8531->mii_ts.ts_info  = vsc85xx_ts_info;
+	phydev->mii_ts = &vsc8531->mii_ts;
+
+	memcpy(&vsc8531->ptp->caps, &vsc85xx_clk_caps, sizeof(vsc85xx_clk_caps));
+	vsc8531->ptp->ptp_clock = ptp_clock_register(&vsc8531->ptp->caps,
+						     &phydev->mdio.dev);
+	return PTR_ERR_OR_ZERO(vsc8531->ptp->ptp_clock);
 }
 
 int vsc8584_ptp_probe_once(struct phy_device *phydev)
diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index e56901b..11352d8 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -1355,6 +1355,9 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x2357, 0x0201, 4)},	/* TP-LINK HSUPA Modem MA180 */
 	{QMI_FIXED_INTF(0x2357, 0x9000, 4)},	/* TP-LINK MA260 */
 	{QMI_QUIRK_SET_DTR(0x1bc7, 0x1031, 3)}, /* Telit LE910C1-EUX */
+	{QMI_QUIRK_SET_DTR(0x1bc7, 0x1034, 2)}, /* Telit LE910C4-WWX */
+	{QMI_QUIRK_SET_DTR(0x1bc7, 0x1037, 4)}, /* Telit LE910C4-WWX */
+	{QMI_QUIRK_SET_DTR(0x1bc7, 0x1038, 3)}, /* Telit LE910C4-WWX */
 	{QMI_QUIRK_SET_DTR(0x1bc7, 0x103a, 0)}, /* Telit LE910C4-WWX */
 	{QMI_QUIRK_SET_DTR(0x1bc7, 0x1040, 2)},	/* Telit LE922A */
 	{QMI_QUIRK_SET_DTR(0x1bc7, 0x1050, 2)},	/* Telit FN980 */
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index d14e6d6..975bdc5 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -5758,14 +5758,15 @@ static void virtnet_freeze_down(struct virtio_device *vdev)
 	disable_rx_mode_work(vi);
 	flush_work(&vi->rx_mode_work);
 
-	netif_tx_lock_bh(vi->dev);
-	netif_device_detach(vi->dev);
-	netif_tx_unlock_bh(vi->dev);
 	if (netif_running(vi->dev)) {
 		rtnl_lock();
 		virtnet_close(vi->dev);
 		rtnl_unlock();
 	}
+
+	netif_tx_lock_bh(vi->dev);
+	netif_device_detach(vi->dev);
+	netif_tx_unlock_bh(vi->dev);
 }
 
 static int init_vqs(struct virtnet_info *vi);
diff --git a/drivers/of/device.c b/drivers/of/device.c
index c804265..f7e75e5 100644
--- a/drivers/of/device.c
+++ b/drivers/of/device.c
@@ -17,8 +17,8 @@
 
 /**
  * of_match_device - Tell if a struct device matches an of_device_id list
- * @matches: array of of device match structures to search in
- * @dev: the of device structure to match against
+ * @matches: array of of_device_id match structures to search in
+ * @dev: the OF device structure to match against
  *
  * Used by a driver to check whether an platform_device present in the
  * system is in its list of supported devices.
diff --git a/drivers/of/dynamic.c b/drivers/of/dynamic.c
index 0aba760f..2eaaddc 100644
--- a/drivers/of/dynamic.c
+++ b/drivers/of/dynamic.c
@@ -935,10 +935,15 @@ static int of_changeset_add_prop_helper(struct of_changeset *ocs,
 		return -ENOMEM;
 
 	ret = of_changeset_add_property(ocs, np, new_pp);
-	if (ret)
+	if (ret) {
 		__of_prop_free(new_pp);
+		return ret;
+	}
 
-	return ret;
+	new_pp->next = np->deadprops;
+	np->deadprops = new_pp;
+
+	return 0;
 }
 
 /**
diff --git a/drivers/of/of_reserved_mem.c b/drivers/of/of_reserved_mem.c
index 77016c0..2e9ea75 100644
--- a/drivers/of/of_reserved_mem.c
+++ b/drivers/of/of_reserved_mem.c
@@ -25,6 +25,7 @@
 #include <linux/memblock.h>
 #include <linux/kmemleak.h>
 #include <linux/cma.h>
+#include <linux/dma-map-ops.h>
 
 #include "of_private.h"
 
@@ -175,13 +176,17 @@ static int __init __reserved_mem_reserve_reg(unsigned long node,
 		base = dt_mem_next_cell(dt_root_addr_cells, &prop);
 		size = dt_mem_next_cell(dt_root_size_cells, &prop);
 
-		if (size &&
-		    early_init_dt_reserve_memory(base, size, nomap) == 0)
+		if (size && early_init_dt_reserve_memory(base, size, nomap) == 0) {
+			/* Architecture specific contiguous memory fixup. */
+			if (of_flat_dt_is_compatible(node, "shared-dma-pool") &&
+			    of_get_flat_dt_prop(node, "reusable", NULL))
+				dma_contiguous_early_fixup(base, size);
 			pr_debug("Reserved memory: reserved region for node '%s': base %pa, size %lu MiB\n",
 				uname, &base, (unsigned long)(size / SZ_1M));
-		else
+		} else {
 			pr_err("Reserved memory: failed to reserve memory for node '%s': base %pa, size %lu MiB\n",
 			       uname, &base, (unsigned long)(size / SZ_1M));
+		}
 
 		len -= t_len;
 	}
@@ -472,7 +477,10 @@ static int __init __reserved_mem_alloc_size(unsigned long node, const char *unam
 		       uname, (unsigned long)(size / SZ_1M));
 		return -ENOMEM;
 	}
-
+	/* Architecture specific contiguous memory fixup. */
+	if (of_flat_dt_is_compatible(node, "shared-dma-pool") &&
+	    of_get_flat_dt_prop(node, "reusable", NULL))
+		dma_contiguous_early_fixup(base, size);
 	/* Save region in the reserved_mem array */
 	fdt_reserved_mem_save_node(node, uname, base, size);
 	return 0;
@@ -771,6 +779,7 @@ int of_reserved_mem_region_to_resource(const struct device_node *np,
 		return -EINVAL;
 
 	resource_set_range(res, rmem->base, rmem->size);
+	res->flags = IORESOURCE_MEM;
 	res->name = rmem->name;
 	return 0;
 }
diff --git a/drivers/pinctrl/Kconfig b/drivers/pinctrl/Kconfig
index ddd1166..be1ca8e 100644
--- a/drivers/pinctrl/Kconfig
+++ b/drivers/pinctrl/Kconfig
@@ -539,6 +539,7 @@
 	tristate "STMicroelectronics STMFX GPIO expander pinctrl driver"
 	depends on I2C
 	depends on OF_GPIO
+	depends on HAS_IOMEM
 	select GENERIC_PINCONF
 	select GPIOLIB_IRQCHIP
 	select MFD_STMFX
diff --git a/drivers/pinctrl/mediatek/pinctrl-airoha.c b/drivers/pinctrl/mediatek/pinctrl-airoha.c
index 5f1ec9e..1b2f132 100644
--- a/drivers/pinctrl/mediatek/pinctrl-airoha.c
+++ b/drivers/pinctrl/mediatek/pinctrl-airoha.c
@@ -2696,7 +2696,7 @@ static int airoha_pinconf_get(struct pinctrl_dev *pctrl_dev,
 		arg = 1;
 		break;
 	default:
-		return -EOPNOTSUPP;
+		return -ENOTSUPP;
 	}
 
 	*config = pinconf_to_config_packed(param, arg);
@@ -2788,7 +2788,7 @@ static int airoha_pinconf_set(struct pinctrl_dev *pctrl_dev,
 			break;
 		}
 		default:
-			return -EOPNOTSUPP;
+			return -ENOTSUPP;
 		}
 	}
 
@@ -2805,10 +2805,10 @@ static int airoha_pinconf_group_get(struct pinctrl_dev *pctrl_dev,
 		if (airoha_pinconf_get(pctrl_dev,
 				       airoha_pinctrl_groups[group].pins[i],
 				       config))
-			return -EOPNOTSUPP;
+			return -ENOTSUPP;
 
 		if (i && cur_config != *config)
-			return -EOPNOTSUPP;
+			return -ENOTSUPP;
 
 		cur_config = *config;
 	}
diff --git a/drivers/pinctrl/meson/pinctrl-amlogic-a4.c b/drivers/pinctrl/meson/pinctrl-amlogic-a4.c
index e34e984..6132710 100644
--- a/drivers/pinctrl/meson/pinctrl-amlogic-a4.c
+++ b/drivers/pinctrl/meson/pinctrl-amlogic-a4.c
@@ -1093,7 +1093,7 @@ static const struct of_device_id aml_pctl_of_match[] = {
 	{ .compatible = "amlogic,pinctrl-s6", .data = &s6_priv_data, },
 	{ /* sentinel */ }
 };
-MODULE_DEVICE_TABLE(of, aml_pctl_dt_match);
+MODULE_DEVICE_TABLE(of, aml_pctl_of_match);
 
 static struct platform_driver aml_pctl_driver = {
 	.driver = {
diff --git a/drivers/platform/x86/intel/int3472/discrete.c b/drivers/platform/x86/intel/int3472/discrete.c
index 4c0aed6..bdfb8a8 100644
--- a/drivers/platform/x86/intel/int3472/discrete.c
+++ b/drivers/platform/x86/intel/int3472/discrete.c
@@ -193,6 +193,10 @@ static void int3472_get_con_id_and_polarity(struct int3472_discrete_device *int3
 		*con_id = "privacy-led";
 		*gpio_flags = GPIO_ACTIVE_HIGH;
 		break;
+	case INT3472_GPIO_TYPE_HOTPLUG_DETECT:
+		*con_id = "hpd";
+		*gpio_flags = GPIO_ACTIVE_HIGH;
+		break;
 	case INT3472_GPIO_TYPE_POWER_ENABLE:
 		*con_id = "avdd";
 		*gpio_flags = GPIO_ACTIVE_HIGH;
@@ -223,6 +227,7 @@ static void int3472_get_con_id_and_polarity(struct int3472_discrete_device *int3
  * 0x0b Power enable
  * 0x0c Clock enable
  * 0x0d Privacy LED
+ * 0x13 Hotplug detect
  *
  * There are some known platform specific quirks where that does not quite
  * hold up; for example where a pin with type 0x01 (Power down) is mapped to
@@ -292,6 +297,7 @@ static int skl_int3472_handle_gpio_resources(struct acpi_resource *ares,
 	switch (type) {
 	case INT3472_GPIO_TYPE_RESET:
 	case INT3472_GPIO_TYPE_POWERDOWN:
+	case INT3472_GPIO_TYPE_HOTPLUG_DETECT:
 		ret = skl_int3472_map_gpio_to_sensor(int3472, agpio, con_id, gpio_flags);
 		if (ret)
 			err_msg = "Failed to map GPIO pin to sensor\n";
diff --git a/drivers/regulator/qcom-pm8008-regulator.c b/drivers/regulator/qcom-pm8008-regulator.c
index da017c1..90c78ee 100644
--- a/drivers/regulator/qcom-pm8008-regulator.c
+++ b/drivers/regulator/qcom-pm8008-regulator.c
@@ -96,7 +96,7 @@ static int pm8008_regulator_get_voltage_sel(struct regulator_dev *rdev)
 
 	uV = le16_to_cpu(val) * 1000;
 
-	return (uV - preg->desc.min_uV) / preg->desc.uV_step;
+	return regulator_map_voltage_linear_range(rdev, uV, INT_MAX);
 }
 
 static const struct regulator_ops pm8008_regulator_ops = {
diff --git a/drivers/soc/qcom/ubwc_config.c b/drivers/soc/qcom/ubwc_config.c
index bd0a98a..15d373b 100644
--- a/drivers/soc/qcom/ubwc_config.c
+++ b/drivers/soc/qcom/ubwc_config.c
@@ -12,6 +12,10 @@
 
 #include <linux/soc/qcom/ubwc.h>
 
+static const struct qcom_ubwc_cfg_data no_ubwc_data = {
+	/* no UBWC, no HBB */
+};
+
 static const struct qcom_ubwc_cfg_data msm8937_data = {
 	.ubwc_enc_version = UBWC_1_0,
 	.ubwc_dec_version = UBWC_1_0,
@@ -215,12 +219,20 @@ static const struct qcom_ubwc_cfg_data x1e80100_data = {
 };
 
 static const struct of_device_id qcom_ubwc_configs[] __maybe_unused = {
+	{ .compatible = "qcom,apq8016", .data = &no_ubwc_data },
+	{ .compatible = "qcom,apq8026", .data = &no_ubwc_data },
+	{ .compatible = "qcom,apq8074", .data = &no_ubwc_data },
 	{ .compatible = "qcom,apq8096", .data = &msm8998_data },
-	{ .compatible = "qcom,msm8917", .data = &msm8937_data },
+	{ .compatible = "qcom,msm8226", .data = &no_ubwc_data },
+	{ .compatible = "qcom,msm8916", .data = &no_ubwc_data },
+	{ .compatible = "qcom,msm8917", .data = &no_ubwc_data },
 	{ .compatible = "qcom,msm8937", .data = &msm8937_data },
+	{ .compatible = "qcom,msm8929", .data = &no_ubwc_data },
+	{ .compatible = "qcom,msm8939", .data = &no_ubwc_data },
 	{ .compatible = "qcom,msm8953", .data = &msm8937_data },
-	{ .compatible = "qcom,msm8956", .data = &msm8937_data },
-	{ .compatible = "qcom,msm8976", .data = &msm8937_data },
+	{ .compatible = "qcom,msm8956", .data = &no_ubwc_data },
+	{ .compatible = "qcom,msm8974", .data = &no_ubwc_data },
+	{ .compatible = "qcom,msm8976", .data = &no_ubwc_data },
 	{ .compatible = "qcom,msm8996", .data = &msm8998_data },
 	{ .compatible = "qcom,msm8998", .data = &msm8998_data },
 	{ .compatible = "qcom,qcm2290", .data = &qcm2290_data, },
@@ -233,7 +245,10 @@ static const struct of_device_id qcom_ubwc_configs[] __maybe_unused = {
 	{ .compatible = "qcom,sc7280", .data = &sc7280_data, },
 	{ .compatible = "qcom,sc8180x", .data = &sc8180x_data, },
 	{ .compatible = "qcom,sc8280xp", .data = &sc8280xp_data, },
+	{ .compatible = "qcom,sda660", .data = &msm8937_data },
+	{ .compatible = "qcom,sdm450", .data = &msm8937_data },
 	{ .compatible = "qcom,sdm630", .data = &msm8937_data },
+	{ .compatible = "qcom,sdm632", .data = &msm8937_data },
 	{ .compatible = "qcom,sdm636", .data = &msm8937_data },
 	{ .compatible = "qcom,sdm660", .data = &msm8937_data },
 	{ .compatible = "qcom,sdm670", .data = &sdm670_data, },
@@ -246,6 +261,8 @@ static const struct of_device_id qcom_ubwc_configs[] __maybe_unused = {
 	{ .compatible = "qcom,sm6375", .data = &sm6350_data, },
 	{ .compatible = "qcom,sm7125", .data = &sc7180_data },
 	{ .compatible = "qcom,sm7150", .data = &sm7150_data, },
+	{ .compatible = "qcom,sm7225", .data = &sm6350_data, },
+	{ .compatible = "qcom,sm7325", .data = &sc7280_data, },
 	{ .compatible = "qcom,sm8150", .data = &sm8150_data, },
 	{ .compatible = "qcom,sm8250", .data = &sm8250_data, },
 	{ .compatible = "qcom,sm8350", .data = &sm8350_data, },
diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index 6edac0c..c6508fe 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -99,6 +99,7 @@ struct vhost_net_ubuf_ref {
 	atomic_t refcount;
 	wait_queue_head_t wait;
 	struct vhost_virtqueue *vq;
+	struct rcu_head rcu;
 };
 
 #define VHOST_NET_BATCH 64
@@ -250,9 +251,13 @@ vhost_net_ubuf_alloc(struct vhost_virtqueue *vq, bool zcopy)
 
 static int vhost_net_ubuf_put(struct vhost_net_ubuf_ref *ubufs)
 {
-	int r = atomic_sub_return(1, &ubufs->refcount);
+	int r;
+
+	rcu_read_lock();
+	r = atomic_sub_return(1, &ubufs->refcount);
 	if (unlikely(!r))
 		wake_up(&ubufs->wait);
+	rcu_read_unlock();
 	return r;
 }
 
@@ -265,7 +270,7 @@ static void vhost_net_ubuf_put_and_wait(struct vhost_net_ubuf_ref *ubufs)
 static void vhost_net_ubuf_put_wait_and_free(struct vhost_net_ubuf_ref *ubufs)
 {
 	vhost_net_ubuf_put_and_wait(ubufs);
-	kfree(ubufs);
+	kfree_rcu(ubufs, rcu);
 }
 
 static void vhost_net_clear_ubuf_info(struct vhost_net *n)
diff --git a/drivers/virtio/virtio_input.c b/drivers/virtio/virtio_input.c
index a5d6326..d072828 100644
--- a/drivers/virtio/virtio_input.c
+++ b/drivers/virtio/virtio_input.c
@@ -360,11 +360,15 @@ static int virtinput_freeze(struct virtio_device *vdev)
 {
 	struct virtio_input *vi = vdev->priv;
 	unsigned long flags;
+	void *buf;
 
 	spin_lock_irqsave(&vi->lock, flags);
 	vi->ready = false;
 	spin_unlock_irqrestore(&vi->lock, flags);
 
+	virtio_reset_device(vdev);
+	while ((buf = virtqueue_detach_unused_buf(vi->sts)) != NULL)
+		kfree(buf);
 	vdev->config->del_vqs(vdev);
 	return 0;
 }
diff --git a/drivers/virtio/virtio_pci_legacy_dev.c b/drivers/virtio/virtio_pci_legacy_dev.c
index 677d1f6..bbbf89c 100644
--- a/drivers/virtio/virtio_pci_legacy_dev.c
+++ b/drivers/virtio/virtio_pci_legacy_dev.c
@@ -140,9 +140,9 @@ EXPORT_SYMBOL_GPL(vp_legacy_set_status);
  * vp_legacy_queue_vector - set the MSIX vector for a specific virtqueue
  * @ldev: the legacy virtio-pci device
  * @index: queue index
- * @vector: the config vector
+ * @vector: the queue vector
  *
- * Returns the config vector read from the device
+ * Returns the queue vector read from the device
  */
 u16 vp_legacy_queue_vector(struct virtio_pci_legacy_device *ldev,
 			   u16 index, u16 vector)
diff --git a/drivers/virtio/virtio_pci_modern_dev.c b/drivers/virtio/virtio_pci_modern_dev.c
index d665f8f..9e503b7 100644
--- a/drivers/virtio/virtio_pci_modern_dev.c
+++ b/drivers/virtio/virtio_pci_modern_dev.c
@@ -546,9 +546,9 @@ EXPORT_SYMBOL_GPL(vp_modern_set_queue_reset);
  * vp_modern_queue_vector - set the MSIX vector for a specific virtqueue
  * @mdev: the modern virtio-pci device
  * @index: queue index
- * @vector: the config vector
+ * @vector: the queue vector
  *
- * Returns the config vector read from the device
+ * Returns the queue vector read from the device
  */
 u16 vp_modern_queue_vector(struct virtio_pci_modern_device *mdev,
 			   u16 index, u16 vector)
diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h
index b99fb02..0387b9f 100644
--- a/fs/btrfs/btrfs_inode.h
+++ b/fs/btrfs/btrfs_inode.h
@@ -248,7 +248,7 @@ struct btrfs_inode {
 		u64 new_delalloc_bytes;
 		/*
 		 * The offset of the last dir index key that was logged.
-		 * This is used only for directories.
+		 * This is used only for directories. Protected by 'log_mutex'.
 		 */
 		u64 last_dir_index_offset;
 	};
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 9e4aec7..dd82dcc 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -6805,7 +6805,6 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir,
 	struct fscrypt_name fname;
 	u64 index;
 	int ret;
-	int drop_inode = 0;
 
 	/* do not allow sys_link's with other subvols of the same device */
 	if (btrfs_root_id(root) != btrfs_root_id(BTRFS_I(inode)->root))
@@ -6837,44 +6836,44 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir,
 
 	/* There are several dir indexes for this inode, clear the cache. */
 	BTRFS_I(inode)->dir_index = 0ULL;
-	inc_nlink(inode);
 	inode_inc_iversion(inode);
 	inode_set_ctime_current(inode);
-	ihold(inode);
 	set_bit(BTRFS_INODE_COPY_EVERYTHING, &BTRFS_I(inode)->runtime_flags);
 
 	ret = btrfs_add_link(trans, BTRFS_I(dir), BTRFS_I(inode),
 			     &fname.disk_name, 1, index);
+	if (ret)
+		goto fail;
 
+	/* Link added now we update the inode item with the new link count. */
+	inc_nlink(inode);
+	ret = btrfs_update_inode(trans, BTRFS_I(inode));
 	if (ret) {
-		drop_inode = 1;
-	} else {
-		struct dentry *parent = dentry->d_parent;
-
-		ret = btrfs_update_inode(trans, BTRFS_I(inode));
-		if (ret)
-			goto fail;
-		if (inode->i_nlink == 1) {
-			/*
-			 * If new hard link count is 1, it's a file created
-			 * with open(2) O_TMPFILE flag.
-			 */
-			ret = btrfs_orphan_del(trans, BTRFS_I(inode));
-			if (ret)
-				goto fail;
-		}
-		d_instantiate(dentry, inode);
-		btrfs_log_new_name(trans, old_dentry, NULL, 0, parent);
+		btrfs_abort_transaction(trans, ret);
+		goto fail;
 	}
 
+	if (inode->i_nlink == 1) {
+		/*
+		 * If the new hard link count is 1, it's a file created with the
+		 * open(2) O_TMPFILE flag.
+		 */
+		ret = btrfs_orphan_del(trans, BTRFS_I(inode));
+		if (ret) {
+			btrfs_abort_transaction(trans, ret);
+			goto fail;
+		}
+	}
+
+	/* Grab reference for the new dentry passed to d_instantiate(). */
+	ihold(inode);
+	d_instantiate(dentry, inode);
+	btrfs_log_new_name(trans, old_dentry, NULL, 0, dentry->d_parent);
+
 fail:
 	fscrypt_free_filename(&fname);
 	if (trans)
 		btrfs_end_transaction(trans);
-	if (drop_inode) {
-		inode_dec_link_count(inode);
-		iput(inode);
-	}
 	btrfs_btree_balance_dirty(fs_info);
 	return ret;
 }
@@ -7830,6 +7829,7 @@ struct inode *btrfs_alloc_inode(struct super_block *sb)
 	ei->last_sub_trans = 0;
 	ei->logged_trans = 0;
 	ei->delalloc_bytes = 0;
+	/* new_delalloc_bytes and last_dir_index_offset are in a union. */
 	ei->new_delalloc_bytes = 0;
 	ei->defrag_bytes = 0;
 	ei->disk_i_size = 0;
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 69e1155..7d5d908 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -3340,6 +3340,31 @@ int btrfs_free_log_root_tree(struct btrfs_trans_handle *trans,
 	return 0;
 }
 
+static bool mark_inode_as_not_logged(const struct btrfs_trans_handle *trans,
+				     struct btrfs_inode *inode)
+{
+	bool ret = false;
+
+	/*
+	 * Do this only if ->logged_trans is still 0 to prevent races with
+	 * concurrent logging as we may see the inode not logged when
+	 * inode_logged() is called but it gets logged after inode_logged() did
+	 * not find it in the log tree and we end up setting ->logged_trans to a
+	 * value less than trans->transid after the concurrent logging task has
+	 * set it to trans->transid. As a consequence, subsequent rename, unlink
+	 * and link operations may end up not logging new names and removing old
+	 * names from the log.
+	 */
+	spin_lock(&inode->lock);
+	if (inode->logged_trans == 0)
+		inode->logged_trans = trans->transid - 1;
+	else if (inode->logged_trans == trans->transid)
+		ret = true;
+	spin_unlock(&inode->lock);
+
+	return ret;
+}
+
 /*
  * Check if an inode was logged in the current transaction. This correctly deals
  * with the case where the inode was logged but has a logged_trans of 0, which
@@ -3357,15 +3382,32 @@ static int inode_logged(const struct btrfs_trans_handle *trans,
 	struct btrfs_key key;
 	int ret;
 
-	if (inode->logged_trans == trans->transid)
+	/*
+	 * Quick lockless call, since once ->logged_trans is set to the current
+	 * transaction, we never set it to a lower value anywhere else.
+	 */
+	if (data_race(inode->logged_trans) == trans->transid)
 		return 1;
 
 	/*
-	 * If logged_trans is not 0, then we know the inode logged was not logged
-	 * in this transaction, so we can return false right away.
+	 * If logged_trans is not 0 and not trans->transid, then we know the
+	 * inode was not logged in this transaction, so we can return false
+	 * right away. We take the lock to avoid a race caused by load/store
+	 * tearing with a concurrent btrfs_log_inode() call or a concurrent task
+	 * in this function further below - an update to trans->transid can be
+	 * teared into two 32 bits updates for example, in which case we could
+	 * see a positive value that is not trans->transid and assume the inode
+	 * was not logged when it was.
 	 */
-	if (inode->logged_trans > 0)
+	spin_lock(&inode->lock);
+	if (inode->logged_trans == trans->transid) {
+		spin_unlock(&inode->lock);
+		return 1;
+	} else if (inode->logged_trans > 0) {
+		spin_unlock(&inode->lock);
 		return 0;
+	}
+	spin_unlock(&inode->lock);
 
 	/*
 	 * If no log tree was created for this root in this transaction, then
@@ -3374,10 +3416,8 @@ static int inode_logged(const struct btrfs_trans_handle *trans,
 	 * transaction's ID, to avoid the search below in a future call in case
 	 * a log tree gets created after this.
 	 */
-	if (!test_bit(BTRFS_ROOT_HAS_LOG_TREE, &inode->root->state)) {
-		inode->logged_trans = trans->transid - 1;
-		return 0;
-	}
+	if (!test_bit(BTRFS_ROOT_HAS_LOG_TREE, &inode->root->state))
+		return mark_inode_as_not_logged(trans, inode);
 
 	/*
 	 * We have a log tree and the inode's logged_trans is 0. We can't tell
@@ -3431,8 +3471,7 @@ static int inode_logged(const struct btrfs_trans_handle *trans,
 		 * Set logged_trans to a value greater than 0 and less then the
 		 * current transaction to avoid doing the search in future calls.
 		 */
-		inode->logged_trans = trans->transid - 1;
-		return 0;
+		return mark_inode_as_not_logged(trans, inode);
 	}
 
 	/*
@@ -3440,20 +3479,9 @@ static int inode_logged(const struct btrfs_trans_handle *trans,
 	 * the current transacion's ID, to avoid future tree searches as long as
 	 * the inode is not evicted again.
 	 */
+	spin_lock(&inode->lock);
 	inode->logged_trans = trans->transid;
-
-	/*
-	 * If it's a directory, then we must set last_dir_index_offset to the
-	 * maximum possible value, so that the next attempt to log the inode does
-	 * not skip checking if dir index keys found in modified subvolume tree
-	 * leaves have been logged before, otherwise it would result in attempts
-	 * to insert duplicate dir index keys in the log tree. This must be done
-	 * because last_dir_index_offset is an in-memory only field, not persisted
-	 * in the inode item or any other on-disk structure, so its value is lost
-	 * once the inode is evicted.
-	 */
-	if (S_ISDIR(inode->vfs_inode.i_mode))
-		inode->last_dir_index_offset = (u64)-1;
+	spin_unlock(&inode->lock);
 
 	return 1;
 }
@@ -4045,7 +4073,7 @@ static noinline int log_dir_items(struct btrfs_trans_handle *trans,
 
 /*
  * If the inode was logged before and it was evicted, then its
- * last_dir_index_offset is (u64)-1, so we don't the value of the last index
+ * last_dir_index_offset is 0, so we don't know the value of the last index
  * key offset. If that's the case, search for it and update the inode. This
  * is to avoid lookups in the log tree every time we try to insert a dir index
  * key from a leaf changed in the current transaction, and to allow us to always
@@ -4061,7 +4089,7 @@ static int update_last_dir_index_offset(struct btrfs_inode *inode,
 
 	lockdep_assert_held(&inode->log_mutex);
 
-	if (inode->last_dir_index_offset != (u64)-1)
+	if (inode->last_dir_index_offset != 0)
 		return 0;
 
 	if (!ctx->logged_before) {
diff --git a/fs/efivarfs/super.c b/fs/efivarfs/super.c
index c4a1399..4bb4002 100644
--- a/fs/efivarfs/super.c
+++ b/fs/efivarfs/super.c
@@ -152,6 +152,10 @@ static int efivarfs_d_compare(const struct dentry *dentry,
 {
 	int guid = len - EFI_VARIABLE_GUID_LEN;
 
+	/* Parallel lookups may produce a temporary invalid filename */
+	if (guid <= 0)
+		return 1;
+
 	if (name->len != len)
 		return 1;
 
diff --git a/fs/smb/client/cifsfs.c b/fs/smb/client/cifsfs.c
index 3bd85ab..e184827 100644
--- a/fs/smb/client/cifsfs.c
+++ b/fs/smb/client/cifsfs.c
@@ -1358,6 +1358,20 @@ static loff_t cifs_remap_file_range(struct file *src_file, loff_t off,
 			truncate_setsize(target_inode, new_size);
 			fscache_resize_cookie(cifs_inode_cookie(target_inode),
 					      new_size);
+		} else if (rc == -EOPNOTSUPP) {
+			/*
+			 * copy_file_range syscall man page indicates EINVAL
+			 * is returned e.g when "fd_in and fd_out refer to the
+			 * same file and the source and target ranges overlap."
+			 * Test generic/157 was what showed these cases where
+			 * we need to remap EOPNOTSUPP to EINVAL
+			 */
+			if (off >= src_inode->i_size) {
+				rc = -EINVAL;
+			} else if (src_inode == target_inode) {
+				if (off + len > destoff)
+					rc = -EINVAL;
+			}
 		}
 		if (rc == 0 && new_size > target_cifsi->netfs.zero_point)
 			target_cifsi->netfs.zero_point = new_size;
diff --git a/fs/smb/client/smb2inode.c b/fs/smb/client/smb2inode.c
index 2a0316c..31c13fb 100644
--- a/fs/smb/client/smb2inode.c
+++ b/fs/smb/client/smb2inode.c
@@ -207,8 +207,10 @@ static int smb2_compound_op(const unsigned int xid, struct cifs_tcon *tcon,
 	server = cifs_pick_channel(ses);
 
 	vars = kzalloc(sizeof(*vars), GFP_ATOMIC);
-	if (vars == NULL)
-		return -ENOMEM;
+	if (vars == NULL) {
+		rc = -ENOMEM;
+		goto out;
+	}
 	rqst = &vars->rqst[0];
 	rsp_iov = &vars->rsp_iov[0];
 
@@ -864,6 +866,7 @@ static int smb2_compound_op(const unsigned int xid, struct cifs_tcon *tcon,
 	    smb2_should_replay(tcon, &retries, &cur_sleep))
 		goto replay_again;
 
+out:
 	if (cfile)
 		cifsFileInfo_put(cfile);
 
diff --git a/fs/xfs/Kconfig b/fs/xfs/Kconfig
index ae0ca68..0659534 100644
--- a/fs/xfs/Kconfig
+++ b/fs/xfs/Kconfig
@@ -105,6 +105,7 @@
 config XFS_RT
 	bool "XFS Realtime subvolume support"
 	depends on XFS_FS
+	default BLK_DEV_ZONED
 	help
 	  If you say Y here you will be able to mount and use XFS filesystems
 	  which contain a realtime subvolume.  The realtime subvolume is a
diff --git a/fs/xfs/libxfs/xfs_attr_remote.c b/fs/xfs/libxfs/xfs_attr_remote.c
index 4c44ce1..bff3dc2 100644
--- a/fs/xfs/libxfs/xfs_attr_remote.c
+++ b/fs/xfs/libxfs/xfs_attr_remote.c
@@ -435,6 +435,13 @@ xfs_attr_rmtval_get(
 					0, &bp, &xfs_attr3_rmt_buf_ops);
 			if (xfs_metadata_is_sick(error))
 				xfs_dirattr_mark_sick(args->dp, XFS_ATTR_FORK);
+			/*
+			 * ENODATA from disk implies a disk medium failure;
+			 * ENODATA for xattrs means attribute not found, so
+			 * disambiguate that here.
+			 */
+			if (error == -ENODATA)
+				error = -EIO;
 			if (error)
 				return error;
 
diff --git a/fs/xfs/libxfs/xfs_da_btree.c b/fs/xfs/libxfs/xfs_da_btree.c
index 17d9e61..723a0643 100644
--- a/fs/xfs/libxfs/xfs_da_btree.c
+++ b/fs/xfs/libxfs/xfs_da_btree.c
@@ -2833,6 +2833,12 @@ xfs_da_read_buf(
 			&bp, ops);
 	if (xfs_metadata_is_sick(error))
 		xfs_dirattr_mark_sick(dp, whichfork);
+	/*
+	 * ENODATA from disk implies a disk medium failure; ENODATA for
+	 * xattrs means attribute not found, so disambiguate that here.
+	 */
+	if (error == -ENODATA && whichfork == XFS_ATTR_FORK)
+		error = -EIO;
 	if (error)
 		goto out_free;
 
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 1ee4f83..a26f798 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -760,6 +760,9 @@ xfs_vm_swap_activate(
 {
 	struct xfs_inode		*ip = XFS_I(file_inode(swap_file));
 
+	if (xfs_is_zoned_inode(ip))
+		return -EINVAL;
+
 	/*
 	 * Swap file activation can race against concurrent shared extent
 	 * removal in files that have been cloned.  If this happens,
diff --git a/fs/xfs/xfs_zone_alloc.c b/fs/xfs/xfs_zone_alloc.c
index f8bd6d7..f28214c 100644
--- a/fs/xfs/xfs_zone_alloc.c
+++ b/fs/xfs/xfs_zone_alloc.c
@@ -374,44 +374,6 @@ xfs_zone_free_blocks(
 	return 0;
 }
 
-/*
- * Check if the zone containing the data just before the offset we are
- * writing to is still open and has space.
- */
-static struct xfs_open_zone *
-xfs_last_used_zone(
-	struct iomap_ioend	*ioend)
-{
-	struct xfs_inode	*ip = XFS_I(ioend->io_inode);
-	struct xfs_mount	*mp = ip->i_mount;
-	xfs_fileoff_t		offset_fsb = XFS_B_TO_FSB(mp, ioend->io_offset);
-	struct xfs_rtgroup	*rtg = NULL;
-	struct xfs_open_zone	*oz = NULL;
-	struct xfs_iext_cursor	icur;
-	struct xfs_bmbt_irec	got;
-
-	xfs_ilock(ip, XFS_ILOCK_SHARED);
-	if (!xfs_iext_lookup_extent_before(ip, &ip->i_df, &offset_fsb,
-				&icur, &got)) {
-		xfs_iunlock(ip, XFS_ILOCK_SHARED);
-		return NULL;
-	}
-	xfs_iunlock(ip, XFS_ILOCK_SHARED);
-
-	rtg = xfs_rtgroup_grab(mp, xfs_rtb_to_rgno(mp, got.br_startblock));
-	if (!rtg)
-		return NULL;
-
-	xfs_ilock(rtg_rmap(rtg), XFS_ILOCK_SHARED);
-	oz = READ_ONCE(rtg->rtg_open_zone);
-	if (oz && (oz->oz_is_gc || !atomic_inc_not_zero(&oz->oz_ref)))
-		oz = NULL;
-	xfs_iunlock(rtg_rmap(rtg), XFS_ILOCK_SHARED);
-
-	xfs_rtgroup_rele(rtg);
-	return oz;
-}
-
 static struct xfs_group *
 xfs_find_free_zone(
 	struct xfs_mount	*mp,
@@ -918,12 +880,9 @@ xfs_zone_alloc_and_submit(
 		goto out_error;
 
 	/*
-	 * If we don't have a cached zone in this write context, see if the
-	 * last extent before the one we are writing to points to an active
-	 * zone.  If so, just continue writing to it.
+	 * If we don't have a locally cached zone in this write context, see if
+	 * the inode is still associated with a zone and use that if so.
 	 */
-	if (!*oz && ioend->io_offset)
-		*oz = xfs_last_used_zone(ioend);
 	if (!*oz)
 		*oz = xfs_cached_zone(mp, ip);
 
diff --git a/fs/xfs/xfs_zone_space_resv.c b/fs/xfs/xfs_zone_space_resv.c
index 1313c55..9cd3871 100644
--- a/fs/xfs/xfs_zone_space_resv.c
+++ b/fs/xfs/xfs_zone_space_resv.c
@@ -10,6 +10,7 @@
 #include "xfs_mount.h"
 #include "xfs_inode.h"
 #include "xfs_rtbitmap.h"
+#include "xfs_icache.h"
 #include "xfs_zone_alloc.h"
 #include "xfs_zone_priv.h"
 #include "xfs_zones.h"
@@ -230,6 +231,11 @@ xfs_zoned_space_reserve(
 
 	error = xfs_dec_freecounter(mp, XC_FREE_RTEXTENTS, count_fsb,
 			flags & XFS_ZR_RESERVED);
+	if (error == -ENOSPC && !(flags & XFS_ZR_NOWAIT)) {
+		xfs_inodegc_flush(mp);
+		error = xfs_dec_freecounter(mp, XC_FREE_RTEXTENTS, count_fsb,
+				flags & XFS_ZR_RESERVED);
+	}
 	if (error == -ENOSPC && (flags & XFS_ZR_GREEDY) && count_fsb > 1)
 		error = xfs_zoned_reserve_extents_greedy(mp, &count_fsb, flags);
 	if (error)
diff --git a/include/drm/drm_gpuvm.h b/include/drm/drm_gpuvm.h
index 274532f..2e70882 100644
--- a/include/drm/drm_gpuvm.h
+++ b/include/drm/drm_gpuvm.h
@@ -103,7 +103,7 @@ struct drm_gpuva {
 	} va;
 
 	/**
-	 * @gem: structure containing the &drm_gem_object and it's offset
+	 * @gem: structure containing the &drm_gem_object and its offset
 	 */
 	struct {
 		/**
@@ -843,7 +843,7 @@ struct drm_gpuva_op_map {
 	} va;
 
 	/**
-	 * @gem: structure containing the &drm_gem_object and it's offset
+	 * @gem: structure containing the &drm_gem_object and its offset
 	 */
 	struct {
 		/**
@@ -1189,11 +1189,11 @@ struct drm_gpuvm_ops {
 
 	/**
 	 * @sm_step_unmap: called from &drm_gpuvm_sm_map and
-	 * &drm_gpuvm_sm_unmap to unmap an existent mapping
+	 * &drm_gpuvm_sm_unmap to unmap an existing mapping
 	 *
-	 * This callback is called when existent mapping needs to be unmapped.
+	 * This callback is called when existing mapping needs to be unmapped.
 	 * This is the case when either a newly requested mapping encloses an
-	 * existent mapping or an unmap of an existent mapping is requested.
+	 * existing mapping or an unmap of an existing mapping is requested.
 	 *
 	 * The &priv pointer matches the one the driver passed to
 	 * &drm_gpuvm_sm_map or &drm_gpuvm_sm_unmap, respectively.
diff --git a/include/linux/atmdev.h b/include/linux/atmdev.h
index 45f2f278..70807c6 100644
--- a/include/linux/atmdev.h
+++ b/include/linux/atmdev.h
@@ -185,6 +185,7 @@ struct atmdev_ops { /* only send is required */
 	int (*compat_ioctl)(struct atm_dev *dev,unsigned int cmd,
 			    void __user *arg);
 #endif
+	int (*pre_send)(struct atm_vcc *vcc, struct sk_buff *skb);
 	int (*send)(struct atm_vcc *vcc,struct sk_buff *skb);
 	int (*send_bh)(struct atm_vcc *vcc, struct sk_buff *skb);
 	int (*send_oam)(struct atm_vcc *vcc,void *cell,int flags);
diff --git a/include/linux/dma-map-ops.h b/include/linux/dma-map-ops.h
index f48e5fb..332b80c 100644
--- a/include/linux/dma-map-ops.h
+++ b/include/linux/dma-map-ops.h
@@ -153,6 +153,9 @@ static inline void dma_free_contiguous(struct device *dev, struct page *page,
 {
 	__free_pages(page, get_order(size));
 }
+static inline void dma_contiguous_early_fixup(phys_addr_t base, unsigned long size)
+{
+}
 #endif /* CONFIG_DMA_CMA*/
 
 #ifdef CONFIG_DMA_DECLARE_COHERENT
diff --git a/include/linux/memblock.h b/include/linux/memblock.h
index b967463..fcda8481 100644
--- a/include/linux/memblock.h
+++ b/include/linux/memblock.h
@@ -40,8 +40,9 @@ extern unsigned long long max_possible_pfn;
  * via a driver, and never indicated in the firmware-provided memory map as
  * system RAM. This corresponds to IORESOURCE_SYSRAM_DRIVER_MANAGED in the
  * kernel resource tree.
- * @MEMBLOCK_RSRV_NOINIT: memory region for which struct pages are
- * not initialized (only for reserved regions).
+ * @MEMBLOCK_RSRV_NOINIT: reserved memory region for which struct pages are not
+ * fully initialized. Users of this flag are responsible to properly initialize
+ * struct pages of this region
  * @MEMBLOCK_RSRV_KERN: memory region that is reserved for kernel use,
  * either explictitly with memblock_reserve_kern() or via memblock
  * allocation APIs. All memblock allocations set this flag.
diff --git a/include/linux/platform_data/x86/int3472.h b/include/linux/platform_data/x86/int3472.h
index 78276a1..1571e91 100644
--- a/include/linux/platform_data/x86/int3472.h
+++ b/include/linux/platform_data/x86/int3472.h
@@ -27,6 +27,7 @@
 #define INT3472_GPIO_TYPE_CLK_ENABLE				0x0c
 #define INT3472_GPIO_TYPE_PRIVACY_LED				0x0d
 #define INT3472_GPIO_TYPE_HANDSHAKE				0x12
+#define INT3472_GPIO_TYPE_HOTPLUG_DETECT			0x13
 
 #define INT3472_PDEV_MAX_NAME_LEN				23
 #define INT3472_MAX_SENSOR_GPIOS				3
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 14b923d..fa63365 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -4172,6 +4172,8 @@ int skb_copy_and_crc32c_datagram_iter(const struct sk_buff *skb, int offset,
 				      struct iov_iter *to, int len, u32 *crcp);
 int skb_copy_datagram_from_iter(struct sk_buff *skb, int offset,
 				 struct iov_iter *from, int len);
+int skb_copy_datagram_from_iter_full(struct sk_buff *skb, int offset,
+				     struct iov_iter *from, int len);
 int zerocopy_sg_from_iter(struct sk_buff *skb, struct iov_iter *frm);
 void skb_free_datagram(struct sock *sk, struct sk_buff *skb);
 int skb_kill_datagram(struct sock *sk, struct sk_buff *skb, unsigned int flags);
diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h
index 918cf25..8bf156d 100644
--- a/include/linux/virtio_config.h
+++ b/include/linux/virtio_config.h
@@ -328,8 +328,6 @@ static inline
 bool virtio_get_shm_region(struct virtio_device *vdev,
 			   struct virtio_shm_region *region, u8 id)
 {
-	if (!region->len)
-		return false;
 	if (!vdev->config->get_shm_region)
 		return false;
 	return vdev->config->get_shm_region(vdev, region, id);
diff --git a/include/net/bluetooth/hci_sync.h b/include/net/bluetooth/hci_sync.h
index 5224f57..e352a4e 100644
--- a/include/net/bluetooth/hci_sync.h
+++ b/include/net/bluetooth/hci_sync.h
@@ -93,7 +93,7 @@ int hci_update_class_sync(struct hci_dev *hdev);
 
 int hci_update_eir_sync(struct hci_dev *hdev);
 int hci_update_class_sync(struct hci_dev *hdev);
-int hci_update_name_sync(struct hci_dev *hdev);
+int hci_update_name_sync(struct hci_dev *hdev, const u8 *name);
 int hci_write_ssp_mode_sync(struct hci_dev *hdev, u8 mode);
 
 int hci_get_random_address(struct hci_dev *hdev, bool require_privacy,
diff --git a/include/net/rose.h b/include/net/rose.h
index 23267b4e..2b5491b 100644
--- a/include/net/rose.h
+++ b/include/net/rose.h
@@ -8,6 +8,7 @@
 #ifndef _ROSE_H
 #define _ROSE_H 
 
+#include <linux/refcount.h>
 #include <linux/rose.h>
 #include <net/ax25.h>
 #include <net/sock.h>
@@ -96,7 +97,7 @@ struct rose_neigh {
 	ax25_cb			*ax25;
 	struct net_device		*dev;
 	unsigned short		count;
-	unsigned short		use;
+	refcount_t		use;
 	unsigned int		number;
 	char			restarted;
 	char			dce_mode;
@@ -151,6 +152,21 @@ struct rose_sock {
 
 #define rose_sk(sk) ((struct rose_sock *)(sk))
 
+static inline void rose_neigh_hold(struct rose_neigh *rose_neigh)
+{
+	refcount_inc(&rose_neigh->use);
+}
+
+static inline void rose_neigh_put(struct rose_neigh *rose_neigh)
+{
+	if (refcount_dec_and_test(&rose_neigh->use)) {
+		if (rose_neigh->ax25)
+			ax25_cb_put(rose_neigh->ax25);
+		kfree(rose_neigh->digipeat);
+		kfree(rose_neigh);
+	}
+}
+
 /* af_rose.c */
 extern ax25_address rose_callsign;
 extern int  sysctl_rose_restart_request_timeout;
diff --git a/include/uapi/linux/vhost.h b/include/uapi/linux/vhost.h
index 283348b..c57674a 100644
--- a/include/uapi/linux/vhost.h
+++ b/include/uapi/linux/vhost.h
@@ -260,7 +260,7 @@
  * When fork_owner is set to VHOST_FORK_OWNER_KTHREAD:
  *   - Vhost will create vhost workers as kernel threads.
  */
-#define VHOST_SET_FORK_FROM_OWNER _IOW(VHOST_VIRTIO, 0x83, __u8)
+#define VHOST_SET_FORK_FROM_OWNER _IOW(VHOST_VIRTIO, 0x84, __u8)
 
 /**
  * VHOST_GET_FORK_OWNER - Get the current fork_owner flag for the vhost device.
@@ -268,6 +268,6 @@
  *
  * @return: An 8-bit value indicating the current thread mode.
  */
-#define VHOST_GET_FORK_FROM_OWNER _IOR(VHOST_VIRTIO, 0x84, __u8)
+#define VHOST_GET_FORK_FROM_OWNER _IOR(VHOST_VIRTIO, 0x85, __u8)
 
 #endif
diff --git a/init/Kconfig b/init/Kconfig
index 8363202..d811cad 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -117,10 +117,11 @@
 
 config CC_HAS_COUNTED_BY
 	bool
-	# clang needs to be at least 19.1.3 to avoid __bdos miscalculations
-	# https://github.com/llvm/llvm-project/pull/110497
-	# https://github.com/llvm/llvm-project/pull/112636
-	default y if CC_IS_CLANG && CLANG_VERSION >= 190103
+	# clang needs to be at least 20.1.0 to avoid potential crashes
+	# when building structures that contain __counted_by
+	# https://github.com/ClangBuiltLinux/linux/issues/2114
+	# https://github.com/llvm/llvm-project/commit/160fb1121cdf703c3ef5e61fb26c5659eb581489
+	default y if CC_IS_CLANG && CLANG_VERSION >= 200100
 	# supported since gcc 15.1.0
 	# https://gcc.gnu.org/bugzilla/show_bug.cgi?id=108896
 	default y if CC_IS_GCC && GCC_VERSION >= 150100
diff --git a/io_uring/kbuf.c b/io_uring/kbuf.c
index f2d2cc3..19a8bde 100644
--- a/io_uring/kbuf.c
+++ b/io_uring/kbuf.c
@@ -36,15 +36,19 @@ static bool io_kbuf_inc_commit(struct io_buffer_list *bl, int len)
 {
 	while (len) {
 		struct io_uring_buf *buf;
-		u32 this_len;
+		u32 buf_len, this_len;
 
 		buf = io_ring_head_to_buf(bl->buf_ring, bl->head, bl->mask);
-		this_len = min_t(int, len, buf->len);
-		buf->len -= this_len;
-		if (buf->len) {
+		buf_len = READ_ONCE(buf->len);
+		this_len = min_t(u32, len, buf_len);
+		buf_len -= this_len;
+		/* Stop looping for invalid buffer length of 0 */
+		if (buf_len || !this_len) {
 			buf->addr += this_len;
+			buf->len = buf_len;
 			return false;
 		}
+		buf->len = 0;
 		bl->head++;
 		len -= this_len;
 	}
@@ -159,6 +163,7 @@ static void __user *io_ring_buffer_select(struct io_kiocb *req, size_t *len,
 	__u16 tail, head = bl->head;
 	struct io_uring_buf *buf;
 	void __user *ret;
+	u32 buf_len;
 
 	tail = smp_load_acquire(&br->tail);
 	if (unlikely(tail == head))
@@ -168,8 +173,9 @@ static void __user *io_ring_buffer_select(struct io_kiocb *req, size_t *len,
 		req->flags |= REQ_F_BL_EMPTY;
 
 	buf = io_ring_head_to_buf(br, head, bl->mask);
-	if (*len == 0 || *len > buf->len)
-		*len = buf->len;
+	buf_len = READ_ONCE(buf->len);
+	if (*len == 0 || *len > buf_len)
+		*len = buf_len;
 	req->flags |= REQ_F_BUFFER_RING | REQ_F_BUFFERS_COMMIT;
 	req->buf_list = bl;
 	req->buf_index = buf->bid;
@@ -265,7 +271,7 @@ static int io_ring_buffers_peek(struct io_kiocb *req, struct buf_sel_arg *arg,
 
 	req->buf_index = buf->bid;
 	do {
-		u32 len = buf->len;
+		u32 len = READ_ONCE(buf->len);
 
 		/* truncate end piece, if needed, for non partial buffers */
 		if (len > arg->max_len) {
diff --git a/kernel/dma/contiguous.c b/kernel/dma/contiguous.c
index 67af8a5..d9b9dcb 100644
--- a/kernel/dma/contiguous.c
+++ b/kernel/dma/contiguous.c
@@ -483,8 +483,6 @@ static int __init rmem_cma_setup(struct reserved_mem *rmem)
 		pr_err("Reserved memory: unable to setup CMA region\n");
 		return err;
 	}
-	/* Architecture specific contiguous memory fixup. */
-	dma_contiguous_early_fixup(rmem->base, rmem->size);
 
 	if (default_cma)
 		dma_contiguous_default_area = cma;
diff --git a/kernel/dma/pool.c b/kernel/dma/pool.c
index 7b04f75..ee45dee 100644
--- a/kernel/dma/pool.c
+++ b/kernel/dma/pool.c
@@ -102,8 +102,8 @@ static int atomic_pool_expand(struct gen_pool *pool, size_t pool_size,
 
 #ifdef CONFIG_DMA_DIRECT_REMAP
 	addr = dma_common_contiguous_remap(page, pool_size,
-					   pgprot_dmacoherent(PAGE_KERNEL),
-					   __builtin_return_address(0));
+			pgprot_decrypted(pgprot_dmacoherent(PAGE_KERNEL)),
+			__builtin_return_address(0));
 	if (!addr)
 		goto free_page;
 #else
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index e2d51f4..f253012 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -1496,10 +1496,12 @@ static void update_curr_dl_se(struct rq *rq, struct sched_dl_entity *dl_se, s64
 		}
 
 		if (unlikely(is_dl_boosted(dl_se) || !start_dl_timer(dl_se))) {
-			if (dl_server(dl_se))
-				enqueue_dl_entity(dl_se, ENQUEUE_REPLENISH);
-			else
+			if (dl_server(dl_se)) {
+				replenish_dl_new_period(dl_se, rq);
+				start_dl_timer(dl_se);
+			} else {
 				enqueue_task_dl(rq, dl_task_of(dl_se), ENQUEUE_REPLENISH);
+			}
 		}
 
 		if (!is_leftmost(dl_se, &rq->dl))
@@ -1611,7 +1613,7 @@ void dl_server_stop(struct sched_dl_entity *dl_se)
 static bool dl_server_stopped(struct sched_dl_entity *dl_se)
 {
 	if (!dl_se->dl_server_active)
-		return false;
+		return true;
 
 	if (dl_se->dl_server_idle) {
 		dl_server_stop(dl_se);
@@ -1849,7 +1851,9 @@ void inc_dl_tasks(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
 	u64 deadline = dl_se->deadline;
 
 	dl_rq->dl_nr_running++;
-	add_nr_running(rq_of_dl_rq(dl_rq), 1);
+
+	if (!dl_server(dl_se))
+		add_nr_running(rq_of_dl_rq(dl_rq), 1);
 
 	inc_dl_deadline(dl_rq, deadline);
 }
@@ -1859,7 +1863,9 @@ void dec_dl_tasks(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
 {
 	WARN_ON(!dl_rq->dl_nr_running);
 	dl_rq->dl_nr_running--;
-	sub_nr_running(rq_of_dl_rq(dl_rq), 1);
+
+	if (!dl_server(dl_se))
+		sub_nr_running(rq_of_dl_rq(dl_rq), 1);
 
 	dec_dl_deadline(dl_rq, dl_se->deadline);
 }
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 3f06ab8..02e16b70 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -376,10 +376,8 @@ static ssize_t sched_fair_server_write(struct file *filp, const char __user *ubu
 			return  -EINVAL;
 		}
 
-		if (rq->cfs.h_nr_queued) {
-			update_rq_clock(rq);
-			dl_server_stop(&rq->fair_server);
-		}
+		update_rq_clock(rq);
+		dl_server_stop(&rq->fair_server);
 
 		retval = dl_server_apply_params(&rq->fair_server, runtime, period, 0);
 		if (retval)
diff --git a/lib/ubsan.c b/lib/ubsan.c
index a6ca235..456e3dd 100644
--- a/lib/ubsan.c
+++ b/lib/ubsan.c
@@ -333,18 +333,18 @@ EXPORT_SYMBOL(__ubsan_handle_implicit_conversion);
 void __ubsan_handle_divrem_overflow(void *_data, void *lhs, void *rhs)
 {
 	struct overflow_data *data = _data;
-	char rhs_val_str[VALUE_LENGTH];
+	char lhs_val_str[VALUE_LENGTH];
 
 	if (suppress_report(&data->location))
 		return;
 
 	ubsan_prologue(&data->location, "division-overflow");
 
-	val_to_string(rhs_val_str, sizeof(rhs_val_str), data->type, rhs);
+	val_to_string(lhs_val_str, sizeof(lhs_val_str), data->type, lhs);
 
 	if (type_is_signed(data->type) && get_signed_val(data->type, rhs) == -1)
 		pr_err("division of %s by -1 cannot be represented in type %s\n",
-			rhs_val_str, data->type->type_name);
+			lhs_val_str, data->type->type_name);
 	else
 		pr_err("division by zero\n");
 
diff --git a/mm/memblock.c b/mm/memblock.c
index 154f1d7..117d963 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -780,9 +780,9 @@ bool __init_memblock memblock_validate_numa_coverage(unsigned long threshold_byt
 	}
 
 	if ((nr_pages << PAGE_SHIFT) > threshold_bytes) {
-		mem_size_mb = memblock_phys_mem_size() >> 20;
+		mem_size_mb = memblock_phys_mem_size() / SZ_1M;
 		pr_err("NUMA: no nodes coverage for %luMB of %luMB RAM\n",
-		       (nr_pages << PAGE_SHIFT) >> 20, mem_size_mb);
+		       (nr_pages << PAGE_SHIFT) / SZ_1M, mem_size_mb);
 		return false;
 	}
 
@@ -1091,13 +1091,20 @@ int __init_memblock memblock_clear_nomap(phys_addr_t base, phys_addr_t size)
 
 /**
  * memblock_reserved_mark_noinit - Mark a reserved memory region with flag
- * MEMBLOCK_RSRV_NOINIT which results in the struct pages not being initialized
- * for this region.
+ * MEMBLOCK_RSRV_NOINIT
+ *
  * @base: the base phys addr of the region
  * @size: the size of the region
  *
- * struct pages will not be initialized for reserved memory regions marked with
- * %MEMBLOCK_RSRV_NOINIT.
+ * The struct pages for the reserved regions marked %MEMBLOCK_RSRV_NOINIT will
+ * not be fully initialized to allow the caller optimize their initialization.
+ *
+ * When %CONFIG_DEFERRED_STRUCT_PAGE_INIT is enabled, setting this flag
+ * completely bypasses the initialization of struct pages for such region.
+ *
+ * When %CONFIG_DEFERRED_STRUCT_PAGE_INIT is disabled, struct pages in this
+ * region will be initialized with default values but won't be marked as
+ * reserved.
  *
  * Return: 0 on success, -errno on failure.
  */
diff --git a/mm/numa_emulation.c b/mm/numa_emulation.c
index 9d55679..703c8fa 100644
--- a/mm/numa_emulation.c
+++ b/mm/numa_emulation.c
@@ -73,7 +73,7 @@ static int __init emu_setup_memblk(struct numa_meminfo *ei,
 	}
 
 	printk(KERN_INFO "Faking node %d at [mem %#018Lx-%#018Lx] (%LuMB)\n",
-	       nid, eb->start, eb->end - 1, (eb->end - eb->start) >> 20);
+	       nid, eb->start, eb->end - 1, (eb->end - eb->start) / SZ_1M);
 	return 0;
 }
 
@@ -264,7 +264,7 @@ static int __init split_nodes_size_interleave_uniform(struct numa_meminfo *ei,
 	min_size = ALIGN(max(min_size, FAKE_NODE_MIN_SIZE), FAKE_NODE_MIN_SIZE);
 	if (size < min_size) {
 		pr_err("Fake node size %LuMB too small, increasing to %LuMB\n",
-			size >> 20, min_size >> 20);
+			size / SZ_1M, min_size / SZ_1M);
 		size = min_size;
 	}
 	size = ALIGN_DOWN(size, FAKE_NODE_MIN_SIZE);
diff --git a/mm/numa_memblks.c b/mm/numa_memblks.c
index 541a99c..5b009a9 100644
--- a/mm/numa_memblks.c
+++ b/mm/numa_memblks.c
@@ -76,7 +76,7 @@ static int __init numa_alloc_distance(void)
 		for (j = 0; j < cnt; j++)
 			numa_distance[i * cnt + j] = i == j ?
 				LOCAL_DISTANCE : REMOTE_DISTANCE;
-	printk(KERN_DEBUG "NUMA: Initialized distance table, cnt=%d\n", cnt);
+	pr_debug("NUMA: Initialized distance table, cnt=%d\n", cnt);
 
 	return 0;
 }
@@ -427,9 +427,9 @@ static int __init numa_register_meminfo(struct numa_meminfo *mi)
 		unsigned long pfn_align = node_map_pfn_alignment();
 
 		if (pfn_align && pfn_align < PAGES_PER_SECTION) {
-			unsigned long node_align_mb = PFN_PHYS(pfn_align) >> 20;
+			unsigned long node_align_mb = PFN_PHYS(pfn_align) / SZ_1M;
 
-			unsigned long sect_align_mb = PFN_PHYS(PAGES_PER_SECTION) >> 20;
+			unsigned long sect_align_mb = PFN_PHYS(PAGES_PER_SECTION) / SZ_1M;
 
 			pr_warn("Node alignment %luMB < min %luMB, rejecting NUMA config\n",
 				node_align_mb, sect_align_mb);
diff --git a/net/atm/common.c b/net/atm/common.c
index d7f7976..881c7f2 100644
--- a/net/atm/common.c
+++ b/net/atm/common.c
@@ -635,18 +635,27 @@ int vcc_sendmsg(struct socket *sock, struct msghdr *m, size_t size)
 
 	skb->dev = NULL; /* for paths shared with net_device interfaces */
 	if (!copy_from_iter_full(skb_put(skb, size), size, &m->msg_iter)) {
-		atm_return_tx(vcc, skb);
-		kfree_skb(skb);
 		error = -EFAULT;
-		goto out;
+		goto free_skb;
 	}
 	if (eff != size)
 		memset(skb->data + size, 0, eff-size);
+
+	if (vcc->dev->ops->pre_send) {
+		error = vcc->dev->ops->pre_send(vcc, skb);
+		if (error)
+			goto free_skb;
+	}
+
 	error = vcc->dev->ops->send(vcc, skb);
 	error = error ? error : size;
 out:
 	release_sock(sk);
 	return error;
+free_skb:
+	atm_return_tx(vcc, skb);
+	kfree_skb(skb);
+	goto out;
 }
 
 __poll_t vcc_poll(struct file *file, struct socket *sock, poll_table *wait)
diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index 7a87929..e524bb5 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -149,8 +149,6 @@ static void hci_conn_cleanup(struct hci_conn *conn)
 
 	hci_chan_list_flush(conn);
 
-	hci_conn_hash_del(hdev, conn);
-
 	if (HCI_CONN_HANDLE_UNSET(conn->handle))
 		ida_free(&hdev->unset_handle_ida, conn->handle);
 
@@ -1152,28 +1150,54 @@ void hci_conn_del(struct hci_conn *conn)
 	disable_delayed_work_sync(&conn->auto_accept_work);
 	disable_delayed_work_sync(&conn->idle_work);
 
-	if (conn->type == ACL_LINK) {
-		/* Unacked frames */
-		hdev->acl_cnt += conn->sent;
-	} else if (conn->type == LE_LINK) {
-		cancel_delayed_work(&conn->le_conn_timeout);
+	/* Remove the connection from the list so unacked logic can detect when
+	 * a certain pool is not being utilized.
+	 */
+	hci_conn_hash_del(hdev, conn);
 
-		if (hdev->le_pkts)
-			hdev->le_cnt += conn->sent;
+	/* Handle unacked frames:
+	 *
+	 * - In case there are no connection, or if restoring the buffers
+	 *   considered in transist would overflow, restore all buffers to the
+	 *   pool.
+	 * - Otherwise restore just the buffers considered in transit for the
+	 *   hci_conn
+	 */
+	switch (conn->type) {
+	case ACL_LINK:
+		if (!hci_conn_num(hdev, ACL_LINK) ||
+		    hdev->acl_cnt + conn->sent > hdev->acl_pkts)
+			hdev->acl_cnt = hdev->acl_pkts;
 		else
 			hdev->acl_cnt += conn->sent;
-	} else {
-		/* Unacked ISO frames */
-		if (conn->type == CIS_LINK ||
-		    conn->type == BIS_LINK ||
-		    conn->type == PA_LINK) {
-			if (hdev->iso_pkts)
-				hdev->iso_cnt += conn->sent;
-			else if (hdev->le_pkts)
+		break;
+	case LE_LINK:
+		cancel_delayed_work(&conn->le_conn_timeout);
+
+		if (hdev->le_pkts) {
+			if (!hci_conn_num(hdev, LE_LINK) ||
+			    hdev->le_cnt + conn->sent > hdev->le_pkts)
+				hdev->le_cnt = hdev->le_pkts;
+			else
 				hdev->le_cnt += conn->sent;
+		} else {
+			if ((!hci_conn_num(hdev, LE_LINK) &&
+			     !hci_conn_num(hdev, ACL_LINK)) ||
+			    hdev->acl_cnt + conn->sent > hdev->acl_pkts)
+				hdev->acl_cnt = hdev->acl_pkts;
 			else
 				hdev->acl_cnt += conn->sent;
 		}
+		break;
+	case CIS_LINK:
+	case BIS_LINK:
+	case PA_LINK:
+		if (!hci_iso_count(hdev) ||
+		    hdev->iso_cnt + conn->sent > hdev->iso_pkts)
+			hdev->iso_cnt = hdev->iso_pkts;
+		else
+			hdev->iso_cnt += conn->sent;
+		break;
 	}
 
 	skb_queue_purge(&conn->data_q);
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index fe7cdd6..7a21748 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -2703,7 +2703,7 @@ static void hci_cs_disconnect(struct hci_dev *hdev, u8 status)
 	if (!conn)
 		goto unlock;
 
-	if (status) {
+	if (status && status != HCI_ERROR_UNKNOWN_CONN_ID) {
 		mgmt_disconnect_failed(hdev, &conn->dst, conn->type,
 				       conn->dst_type, status);
 
@@ -2718,6 +2718,12 @@ static void hci_cs_disconnect(struct hci_dev *hdev, u8 status)
 		goto done;
 	}
 
+	/* During suspend, mark connection as closed immediately
+	 * since we might not receive HCI_EV_DISCONN_COMPLETE
+	 */
+	if (hdev->suspended)
+		conn->state = BT_CLOSED;
+
 	mgmt_conn = test_and_clear_bit(HCI_CONN_MGMT_CONNECTED, &conn->flags);
 
 	if (conn->type == ACL_LINK) {
@@ -4398,7 +4404,17 @@ static void hci_num_comp_pkts_evt(struct hci_dev *hdev, void *data,
 		if (!conn)
 			continue;
 
-		conn->sent -= count;
+		/* Check if there is really enough packets outstanding before
+		 * attempting to decrease the sent counter otherwise it could
+		 * underflow..
+		 */
+		if (conn->sent >= count) {
+			conn->sent -= count;
+		} else {
+			bt_dev_warn(hdev, "hcon %p sent %u < count %u",
+				    conn, conn->sent, count);
+			conn->sent = 0;
+		}
 
 		for (i = 0; i < count; ++i)
 			hci_conn_tx_dequeue(conn);
@@ -7008,6 +7024,7 @@ static void hci_le_big_sync_lost_evt(struct hci_dev *hdev, void *data,
 {
 	struct hci_evt_le_big_sync_lost *ev = data;
 	struct hci_conn *bis, *conn;
+	bool mgmt_conn;
 
 	bt_dev_dbg(hdev, "big handle 0x%2.2x", ev->handle);
 
@@ -7026,6 +7043,10 @@ static void hci_le_big_sync_lost_evt(struct hci_dev *hdev, void *data,
 	while ((bis = hci_conn_hash_lookup_big_state(hdev, ev->handle,
 						     BT_CONNECTED,
 						     HCI_ROLE_SLAVE))) {
+		mgmt_conn = test_and_clear_bit(HCI_CONN_MGMT_CONNECTED, &bis->flags);
+		mgmt_device_disconnected(hdev, &bis->dst, bis->type, bis->dst_type,
+					 ev->reason, mgmt_conn);
+
 		clear_bit(HCI_CONN_BIG_SYNC, &bis->flags);
 		hci_disconn_cfm(bis, ev->reason);
 		hci_conn_del(bis);
diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c
index 31d72b9..b6f888d 100644
--- a/net/bluetooth/hci_sync.c
+++ b/net/bluetooth/hci_sync.c
@@ -3481,13 +3481,13 @@ int hci_update_scan_sync(struct hci_dev *hdev)
 	return hci_write_scan_enable_sync(hdev, scan);
 }
 
-int hci_update_name_sync(struct hci_dev *hdev)
+int hci_update_name_sync(struct hci_dev *hdev, const u8 *name)
 {
 	struct hci_cp_write_local_name cp;
 
 	memset(&cp, 0, sizeof(cp));
 
-	memcpy(cp.name, hdev->dev_name, sizeof(cp.name));
+	memcpy(cp.name, name, sizeof(cp.name));
 
 	return __hci_cmd_sync_status(hdev, HCI_OP_WRITE_LOCAL_NAME,
 					    sizeof(cp), &cp,
@@ -3540,7 +3540,7 @@ int hci_powered_update_sync(struct hci_dev *hdev)
 			hci_write_fast_connectable_sync(hdev, false);
 		hci_update_scan_sync(hdev);
 		hci_update_class_sync(hdev);
-		hci_update_name_sync(hdev);
+		hci_update_name_sync(hdev, hdev->dev_name);
 		hci_update_eir_sync(hdev);
 	}
 
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 3166f5f..50634ef 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -3892,8 +3892,11 @@ static void set_name_complete(struct hci_dev *hdev, void *data, int err)
 
 static int set_name_sync(struct hci_dev *hdev, void *data)
 {
+	struct mgmt_pending_cmd *cmd = data;
+	struct mgmt_cp_set_local_name *cp = cmd->param;
+
 	if (lmp_bredr_capable(hdev)) {
-		hci_update_name_sync(hdev);
+		hci_update_name_sync(hdev, cp->name);
 		hci_update_eir_sync(hdev);
 	}
 
@@ -9705,7 +9708,9 @@ void mgmt_device_disconnected(struct hci_dev *hdev, bdaddr_t *bdaddr,
 	if (!mgmt_connected)
 		return;
 
-	if (link_type != ACL_LINK && link_type != LE_LINK)
+	if (link_type != ACL_LINK &&
+	    link_type != LE_LINK  &&
+	    link_type != BIS_LINK)
 		return;
 
 	bacpy(&ev.addr.bdaddr, bdaddr);
diff --git a/net/core/datagram.c b/net/core/datagram.c
index 94cc470..f474b9b 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -618,6 +618,20 @@ int skb_copy_datagram_from_iter(struct sk_buff *skb, int offset,
 }
 EXPORT_SYMBOL(skb_copy_datagram_from_iter);
 
+int skb_copy_datagram_from_iter_full(struct sk_buff *skb, int offset,
+				     struct iov_iter *from, int len)
+{
+	struct iov_iter_state state;
+	int ret;
+
+	iov_iter_save_state(from, &state);
+	ret = skb_copy_datagram_from_iter(skb, offset, from, len);
+	if (ret)
+		iov_iter_restore(from, &state);
+	return ret;
+}
+EXPORT_SYMBOL(skb_copy_datagram_from_iter_full);
+
 int zerocopy_fill_skb_from_iter(struct sk_buff *skb,
 				struct iov_iter *from, size_t length)
 {
diff --git a/net/core/page_pool.c b/net/core/page_pool.c
index 343a6cac..ba70569 100644
--- a/net/core/page_pool.c
+++ b/net/core/page_pool.c
@@ -287,8 +287,10 @@ static int page_pool_init(struct page_pool *pool,
 	}
 
 	if (pool->mp_ops) {
-		if (!pool->dma_map || !pool->dma_sync)
-			return -EOPNOTSUPP;
+		if (!pool->dma_map || !pool->dma_sync) {
+			err = -EOPNOTSUPP;
+			goto free_ptr_ring;
+		}
 
 		if (WARN_ON(!is_kernel_rodata((unsigned long)pool->mp_ops))) {
 			err = -EFAULT;
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index f639a2a..baa43e5 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -2575,12 +2575,16 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
 		    !netif_is_l3_master(dev_out))
 			return ERR_PTR(-EINVAL);
 
-	if (ipv4_is_lbcast(fl4->daddr))
+	if (ipv4_is_lbcast(fl4->daddr)) {
 		type = RTN_BROADCAST;
-	else if (ipv4_is_multicast(fl4->daddr))
+
+		/* reset fi to prevent gateway resolution */
+		fi = NULL;
+	} else if (ipv4_is_multicast(fl4->daddr)) {
 		type = RTN_MULTICAST;
-	else if (ipv4_is_zeronet(fl4->daddr))
+	} else if (ipv4_is_zeronet(fl4->daddr)) {
 		return ERR_PTR(-EINVAL);
+	}
 
 	if (dev_out->flags & IFF_LOOPBACK)
 		flags |= RTCF_LOCAL;
diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index fc5c2fd..5e12e7c 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -129,22 +129,12 @@ static const struct ppp_channel_ops pppol2tp_chan_ops = {
 
 static const struct proto_ops pppol2tp_ops;
 
-/* Retrieves the pppol2tp socket associated to a session.
- * A reference is held on the returned socket, so this function must be paired
- * with sock_put().
- */
+/* Retrieves the pppol2tp socket associated to a session. */
 static struct sock *pppol2tp_session_get_sock(struct l2tp_session *session)
 {
 	struct pppol2tp_session *ps = l2tp_session_priv(session);
-	struct sock *sk;
 
-	rcu_read_lock();
-	sk = rcu_dereference(ps->sk);
-	if (sk)
-		sock_hold(sk);
-	rcu_read_unlock();
-
-	return sk;
+	return rcu_dereference(ps->sk);
 }
 
 /* Helpers to obtain tunnel/session contexts from sockets.
@@ -206,14 +196,13 @@ static int pppol2tp_recvmsg(struct socket *sock, struct msghdr *msg,
 
 static void pppol2tp_recv(struct l2tp_session *session, struct sk_buff *skb, int data_len)
 {
-	struct pppol2tp_session *ps = l2tp_session_priv(session);
-	struct sock *sk = NULL;
+	struct sock *sk;
 
 	/* If the socket is bound, send it in to PPP's input queue. Otherwise
 	 * queue it on the session socket.
 	 */
 	rcu_read_lock();
-	sk = rcu_dereference(ps->sk);
+	sk = pppol2tp_session_get_sock(session);
 	if (!sk)
 		goto no_sock;
 
@@ -510,13 +499,14 @@ static void pppol2tp_show(struct seq_file *m, void *arg)
 	struct l2tp_session *session = arg;
 	struct sock *sk;
 
+	rcu_read_lock();
 	sk = pppol2tp_session_get_sock(session);
 	if (sk) {
 		struct pppox_sock *po = pppox_sk(sk);
 
 		seq_printf(m, "   interface %s\n", ppp_dev_name(&po->chan));
-		sock_put(sk);
 	}
+	rcu_read_unlock();
 }
 
 static void pppol2tp_session_init(struct l2tp_session *session)
@@ -1530,6 +1520,7 @@ static void pppol2tp_seq_session_show(struct seq_file *m, void *v)
 		port = ntohs(inet->inet_sport);
 	}
 
+	rcu_read_lock();
 	sk = pppol2tp_session_get_sock(session);
 	if (sk) {
 		state = sk->sk_state;
@@ -1565,8 +1556,8 @@ static void pppol2tp_seq_session_show(struct seq_file *m, void *v)
 		struct pppox_sock *po = pppox_sk(sk);
 
 		seq_printf(m, "   interface %s\n", ppp_dev_name(&po->chan));
-		sock_put(sk);
 	}
+	rcu_read_unlock();
 }
 
 static int pppol2tp_seq_show(struct seq_file *m, void *v)
diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c
index 4e72b63..543f9e8 100644
--- a/net/rose/af_rose.c
+++ b/net/rose/af_rose.c
@@ -170,7 +170,7 @@ void rose_kill_by_neigh(struct rose_neigh *neigh)
 
 		if (rose->neighbour == neigh) {
 			rose_disconnect(s, ENETUNREACH, ROSE_OUT_OF_ORDER, 0);
-			rose->neighbour->use--;
+			rose_neigh_put(rose->neighbour);
 			rose->neighbour = NULL;
 		}
 	}
@@ -212,7 +212,7 @@ static void rose_kill_by_device(struct net_device *dev)
 		if (rose->device == dev) {
 			rose_disconnect(sk, ENETUNREACH, ROSE_OUT_OF_ORDER, 0);
 			if (rose->neighbour)
-				rose->neighbour->use--;
+				rose_neigh_put(rose->neighbour);
 			netdev_put(rose->device, &rose->dev_tracker);
 			rose->device = NULL;
 		}
@@ -655,7 +655,7 @@ static int rose_release(struct socket *sock)
 		break;
 
 	case ROSE_STATE_2:
-		rose->neighbour->use--;
+		rose_neigh_put(rose->neighbour);
 		release_sock(sk);
 		rose_disconnect(sk, 0, -1, -1);
 		lock_sock(sk);
@@ -823,6 +823,7 @@ static int rose_connect(struct socket *sock, struct sockaddr *uaddr, int addr_le
 	rose->lci = rose_new_lci(rose->neighbour);
 	if (!rose->lci) {
 		err = -ENETUNREACH;
+		rose_neigh_put(rose->neighbour);
 		goto out_release;
 	}
 
@@ -834,12 +835,14 @@ static int rose_connect(struct socket *sock, struct sockaddr *uaddr, int addr_le
 		dev = rose_dev_first();
 		if (!dev) {
 			err = -ENETUNREACH;
+			rose_neigh_put(rose->neighbour);
 			goto out_release;
 		}
 
 		user = ax25_findbyuid(current_euid());
 		if (!user) {
 			err = -EINVAL;
+			rose_neigh_put(rose->neighbour);
 			dev_put(dev);
 			goto out_release;
 		}
@@ -874,8 +877,6 @@ static int rose_connect(struct socket *sock, struct sockaddr *uaddr, int addr_le
 
 	rose->state = ROSE_STATE_1;
 
-	rose->neighbour->use++;
-
 	rose_write_internal(sk, ROSE_CALL_REQUEST);
 	rose_start_heartbeat(sk);
 	rose_start_t1timer(sk);
@@ -1077,7 +1078,7 @@ int rose_rx_call_request(struct sk_buff *skb, struct net_device *dev, struct ros
 			     GFP_ATOMIC);
 	make_rose->facilities    = facilities;
 
-	make_rose->neighbour->use++;
+	rose_neigh_hold(make_rose->neighbour);
 
 	if (rose_sk(sk)->defer) {
 		make_rose->state = ROSE_STATE_5;
diff --git a/net/rose/rose_in.c b/net/rose/rose_in.c
index 3e99181..0276b39 100644
--- a/net/rose/rose_in.c
+++ b/net/rose/rose_in.c
@@ -56,7 +56,7 @@ static int rose_state1_machine(struct sock *sk, struct sk_buff *skb, int framety
 	case ROSE_CLEAR_REQUEST:
 		rose_write_internal(sk, ROSE_CLEAR_CONFIRMATION);
 		rose_disconnect(sk, ECONNREFUSED, skb->data[3], skb->data[4]);
-		rose->neighbour->use--;
+		rose_neigh_put(rose->neighbour);
 		break;
 
 	default:
@@ -79,12 +79,12 @@ static int rose_state2_machine(struct sock *sk, struct sk_buff *skb, int framety
 	case ROSE_CLEAR_REQUEST:
 		rose_write_internal(sk, ROSE_CLEAR_CONFIRMATION);
 		rose_disconnect(sk, 0, skb->data[3], skb->data[4]);
-		rose->neighbour->use--;
+		rose_neigh_put(rose->neighbour);
 		break;
 
 	case ROSE_CLEAR_CONFIRMATION:
 		rose_disconnect(sk, 0, -1, -1);
-		rose->neighbour->use--;
+		rose_neigh_put(rose->neighbour);
 		break;
 
 	default:
@@ -121,7 +121,7 @@ static int rose_state3_machine(struct sock *sk, struct sk_buff *skb, int framety
 	case ROSE_CLEAR_REQUEST:
 		rose_write_internal(sk, ROSE_CLEAR_CONFIRMATION);
 		rose_disconnect(sk, 0, skb->data[3], skb->data[4]);
-		rose->neighbour->use--;
+		rose_neigh_put(rose->neighbour);
 		break;
 
 	case ROSE_RR:
@@ -234,7 +234,7 @@ static int rose_state4_machine(struct sock *sk, struct sk_buff *skb, int framety
 	case ROSE_CLEAR_REQUEST:
 		rose_write_internal(sk, ROSE_CLEAR_CONFIRMATION);
 		rose_disconnect(sk, 0, skb->data[3], skb->data[4]);
-		rose->neighbour->use--;
+		rose_neigh_put(rose->neighbour);
 		break;
 
 	default:
@@ -254,7 +254,7 @@ static int rose_state5_machine(struct sock *sk, struct sk_buff *skb, int framety
 	if (frametype == ROSE_CLEAR_REQUEST) {
 		rose_write_internal(sk, ROSE_CLEAR_CONFIRMATION);
 		rose_disconnect(sk, 0, skb->data[3], skb->data[4]);
-		rose_sk(sk)->neighbour->use--;
+		rose_neigh_put(rose_sk(sk)->neighbour);
 	}
 
 	return 0;
diff --git a/net/rose/rose_route.c b/net/rose/rose_route.c
index b72bf8a..a1e9b05 100644
--- a/net/rose/rose_route.c
+++ b/net/rose/rose_route.c
@@ -93,11 +93,11 @@ static int __must_check rose_add_node(struct rose_route_struct *rose_route,
 		rose_neigh->ax25      = NULL;
 		rose_neigh->dev       = dev;
 		rose_neigh->count     = 0;
-		rose_neigh->use       = 0;
 		rose_neigh->dce_mode  = 0;
 		rose_neigh->loopback  = 0;
 		rose_neigh->number    = rose_neigh_no++;
 		rose_neigh->restarted = 0;
+		refcount_set(&rose_neigh->use, 1);
 
 		skb_queue_head_init(&rose_neigh->queue);
 
@@ -178,6 +178,7 @@ static int __must_check rose_add_node(struct rose_route_struct *rose_route,
 			}
 		}
 		rose_neigh->count++;
+		rose_neigh_hold(rose_neigh);
 
 		goto out;
 	}
@@ -187,6 +188,7 @@ static int __must_check rose_add_node(struct rose_route_struct *rose_route,
 		rose_node->neighbour[rose_node->count] = rose_neigh;
 		rose_node->count++;
 		rose_neigh->count++;
+		rose_neigh_hold(rose_neigh);
 	}
 
 out:
@@ -234,20 +236,12 @@ static void rose_remove_neigh(struct rose_neigh *rose_neigh)
 
 	if ((s = rose_neigh_list) == rose_neigh) {
 		rose_neigh_list = rose_neigh->next;
-		if (rose_neigh->ax25)
-			ax25_cb_put(rose_neigh->ax25);
-		kfree(rose_neigh->digipeat);
-		kfree(rose_neigh);
 		return;
 	}
 
 	while (s != NULL && s->next != NULL) {
 		if (s->next == rose_neigh) {
 			s->next = rose_neigh->next;
-			if (rose_neigh->ax25)
-				ax25_cb_put(rose_neigh->ax25);
-			kfree(rose_neigh->digipeat);
-			kfree(rose_neigh);
 			return;
 		}
 
@@ -263,10 +257,10 @@ static void rose_remove_route(struct rose_route *rose_route)
 	struct rose_route *s;
 
 	if (rose_route->neigh1 != NULL)
-		rose_route->neigh1->use--;
+		rose_neigh_put(rose_route->neigh1);
 
 	if (rose_route->neigh2 != NULL)
-		rose_route->neigh2->use--;
+		rose_neigh_put(rose_route->neigh2);
 
 	if ((s = rose_route_list) == rose_route) {
 		rose_route_list = rose_route->next;
@@ -330,9 +324,12 @@ static int rose_del_node(struct rose_route_struct *rose_route,
 	for (i = 0; i < rose_node->count; i++) {
 		if (rose_node->neighbour[i] == rose_neigh) {
 			rose_neigh->count--;
+			rose_neigh_put(rose_neigh);
 
-			if (rose_neigh->count == 0 && rose_neigh->use == 0)
+			if (rose_neigh->count == 0) {
 				rose_remove_neigh(rose_neigh);
+				rose_neigh_put(rose_neigh);
+			}
 
 			rose_node->count--;
 
@@ -381,11 +378,11 @@ void rose_add_loopback_neigh(void)
 	sn->ax25      = NULL;
 	sn->dev       = NULL;
 	sn->count     = 0;
-	sn->use       = 0;
 	sn->dce_mode  = 1;
 	sn->loopback  = 1;
 	sn->number    = rose_neigh_no++;
 	sn->restarted = 1;
+	refcount_set(&sn->use, 1);
 
 	skb_queue_head_init(&sn->queue);
 
@@ -436,6 +433,7 @@ int rose_add_loopback_node(const rose_address *address)
 	rose_node_list  = rose_node;
 
 	rose_loopback_neigh->count++;
+	rose_neigh_hold(rose_loopback_neigh);
 
 out:
 	spin_unlock_bh(&rose_node_list_lock);
@@ -467,6 +465,7 @@ void rose_del_loopback_node(const rose_address *address)
 	rose_remove_node(rose_node);
 
 	rose_loopback_neigh->count--;
+	rose_neigh_put(rose_loopback_neigh);
 
 out:
 	spin_unlock_bh(&rose_node_list_lock);
@@ -506,6 +505,7 @@ void rose_rt_device_down(struct net_device *dev)
 				memmove(&t->neighbour[i], &t->neighbour[i + 1],
 					sizeof(t->neighbour[0]) *
 						(t->count - i));
+				rose_neigh_put(s);
 			}
 
 			if (t->count <= 0)
@@ -513,6 +513,7 @@ void rose_rt_device_down(struct net_device *dev)
 		}
 
 		rose_remove_neigh(s);
+		rose_neigh_put(s);
 	}
 	spin_unlock_bh(&rose_neigh_list_lock);
 	spin_unlock_bh(&rose_node_list_lock);
@@ -548,6 +549,7 @@ static int rose_clear_routes(void)
 {
 	struct rose_neigh *s, *rose_neigh;
 	struct rose_node  *t, *rose_node;
+	int i;
 
 	spin_lock_bh(&rose_node_list_lock);
 	spin_lock_bh(&rose_neigh_list_lock);
@@ -558,17 +560,21 @@ static int rose_clear_routes(void)
 	while (rose_node != NULL) {
 		t         = rose_node;
 		rose_node = rose_node->next;
-		if (!t->loopback)
+
+		if (!t->loopback) {
+			for (i = 0; i < t->count; i++)
+				rose_neigh_put(t->neighbour[i]);
 			rose_remove_node(t);
+		}
 	}
 
 	while (rose_neigh != NULL) {
 		s          = rose_neigh;
 		rose_neigh = rose_neigh->next;
 
-		if (s->use == 0 && !s->loopback) {
-			s->count = 0;
+		if (!s->loopback) {
 			rose_remove_neigh(s);
+			rose_neigh_put(s);
 		}
 	}
 
@@ -684,6 +690,7 @@ struct rose_neigh *rose_get_neigh(rose_address *addr, unsigned char *cause,
 			for (i = 0; i < node->count; i++) {
 				if (node->neighbour[i]->restarted) {
 					res = node->neighbour[i];
+					rose_neigh_hold(node->neighbour[i]);
 					goto out;
 				}
 			}
@@ -695,6 +702,7 @@ struct rose_neigh *rose_get_neigh(rose_address *addr, unsigned char *cause,
 				for (i = 0; i < node->count; i++) {
 					if (!rose_ftimer_running(node->neighbour[i])) {
 						res = node->neighbour[i];
+						rose_neigh_hold(node->neighbour[i]);
 						goto out;
 					}
 					failed = 1;
@@ -784,13 +792,13 @@ static void rose_del_route_by_neigh(struct rose_neigh *rose_neigh)
 		}
 
 		if (rose_route->neigh1 == rose_neigh) {
-			rose_route->neigh1->use--;
+			rose_neigh_put(rose_route->neigh1);
 			rose_route->neigh1 = NULL;
 			rose_transmit_clear_request(rose_route->neigh2, rose_route->lci2, ROSE_OUT_OF_ORDER, 0);
 		}
 
 		if (rose_route->neigh2 == rose_neigh) {
-			rose_route->neigh2->use--;
+			rose_neigh_put(rose_route->neigh2);
 			rose_route->neigh2 = NULL;
 			rose_transmit_clear_request(rose_route->neigh1, rose_route->lci1, ROSE_OUT_OF_ORDER, 0);
 		}
@@ -919,7 +927,7 @@ int rose_route_frame(struct sk_buff *skb, ax25_cb *ax25)
 			rose_clear_queues(sk);
 			rose->cause	 = ROSE_NETWORK_CONGESTION;
 			rose->diagnostic = 0;
-			rose->neighbour->use--;
+			rose_neigh_put(rose->neighbour);
 			rose->neighbour	 = NULL;
 			rose->lci	 = 0;
 			rose->state	 = ROSE_STATE_0;
@@ -1044,12 +1052,12 @@ int rose_route_frame(struct sk_buff *skb, ax25_cb *ax25)
 
 	if ((new_lci = rose_new_lci(new_neigh)) == 0) {
 		rose_transmit_clear_request(rose_neigh, lci, ROSE_NETWORK_CONGESTION, 71);
-		goto out;
+		goto put_neigh;
 	}
 
 	if ((rose_route = kmalloc(sizeof(*rose_route), GFP_ATOMIC)) == NULL) {
 		rose_transmit_clear_request(rose_neigh, lci, ROSE_NETWORK_CONGESTION, 120);
-		goto out;
+		goto put_neigh;
 	}
 
 	rose_route->lci1      = lci;
@@ -1062,8 +1070,8 @@ int rose_route_frame(struct sk_buff *skb, ax25_cb *ax25)
 	rose_route->lci2      = new_lci;
 	rose_route->neigh2    = new_neigh;
 
-	rose_route->neigh1->use++;
-	rose_route->neigh2->use++;
+	rose_neigh_hold(rose_route->neigh1);
+	rose_neigh_hold(rose_route->neigh2);
 
 	rose_route->next = rose_route_list;
 	rose_route_list  = rose_route;
@@ -1075,6 +1083,8 @@ int rose_route_frame(struct sk_buff *skb, ax25_cb *ax25)
 	rose_transmit_link(skb, rose_route->neigh2);
 	res = 1;
 
+put_neigh:
+	rose_neigh_put(new_neigh);
 out:
 	spin_unlock_bh(&rose_route_list_lock);
 	spin_unlock_bh(&rose_neigh_list_lock);
@@ -1190,7 +1200,7 @@ static int rose_neigh_show(struct seq_file *seq, void *v)
 			   (rose_neigh->loopback) ? "RSLOOP-0" : ax2asc(buf, &rose_neigh->callsign),
 			   rose_neigh->dev ? rose_neigh->dev->name : "???",
 			   rose_neigh->count,
-			   rose_neigh->use,
+			   refcount_read(&rose_neigh->use) - rose_neigh->count - 1,
 			   (rose_neigh->dce_mode) ? "DCE" : "DTE",
 			   (rose_neigh->restarted) ? "yes" : "no",
 			   ax25_display_timer(&rose_neigh->t0timer) / HZ,
@@ -1295,18 +1305,22 @@ void __exit rose_rt_free(void)
 	struct rose_neigh *s, *rose_neigh = rose_neigh_list;
 	struct rose_node  *t, *rose_node  = rose_node_list;
 	struct rose_route *u, *rose_route = rose_route_list;
+	int i;
 
 	while (rose_neigh != NULL) {
 		s          = rose_neigh;
 		rose_neigh = rose_neigh->next;
 
 		rose_remove_neigh(s);
+		rose_neigh_put(s);
 	}
 
 	while (rose_node != NULL) {
 		t         = rose_node;
 		rose_node = rose_node->next;
 
+		for (i = 0; i < t->count; i++)
+			rose_neigh_put(t->neighbour[i]);
 		rose_remove_node(t);
 	}
 
diff --git a/net/rose/rose_timer.c b/net/rose/rose_timer.c
index 020369c..bb60a16 100644
--- a/net/rose/rose_timer.c
+++ b/net/rose/rose_timer.c
@@ -180,7 +180,7 @@ static void rose_timer_expiry(struct timer_list *t)
 		break;
 
 	case ROSE_STATE_2:	/* T3 */
-		rose->neighbour->use--;
+		rose_neigh_put(rose->neighbour);
 		rose_disconnect(sk, ETIMEDOUT, -1, -1);
 		break;
 
diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index 3336dcf..568ff87 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -547,7 +547,9 @@ static void sctp_v6_from_sk(union sctp_addr *addr, struct sock *sk)
 {
 	addr->v6.sin6_family = AF_INET6;
 	addr->v6.sin6_port = 0;
+	addr->v6.sin6_flowinfo = 0;
 	addr->v6.sin6_addr = sk->sk_v6_rcv_saddr;
+	addr->v6.sin6_scope_id = 0;
 }
 
 /* Initialize sk->sk_rcv_saddr from sctp_addr. */
diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c
index fe92e5f..dcc8a1d 100644
--- a/net/vmw_vsock/virtio_transport_common.c
+++ b/net/vmw_vsock/virtio_transport_common.c
@@ -105,12 +105,14 @@ static int virtio_transport_fill_skb(struct sk_buff *skb,
 				     size_t len,
 				     bool zcopy)
 {
+	struct msghdr *msg = info->msg;
+
 	if (zcopy)
-		return __zerocopy_sg_from_iter(info->msg, NULL, skb,
-					       &info->msg->msg_iter, len, NULL);
+		return __zerocopy_sg_from_iter(msg, NULL, skb,
+					       &msg->msg_iter, len, NULL);
 
 	virtio_vsock_skb_put(skb, len);
-	return skb_copy_datagram_from_iter(skb, 0, &info->msg->msg_iter, len);
+	return skb_copy_datagram_from_iter_full(skb, 0, &msg->msg_iter, len);
 }
 
 static void virtio_transport_init_hdr(struct sk_buff *skb,
diff --git a/tools/arch/arm64/include/asm/cputype.h b/tools/arch/arm64/include/asm/cputype.h
index 9a5d85c..139d5e8 100644
--- a/tools/arch/arm64/include/asm/cputype.h
+++ b/tools/arch/arm64/include/asm/cputype.h
@@ -75,11 +75,13 @@
 #define ARM_CPU_PART_CORTEX_A76		0xD0B
 #define ARM_CPU_PART_NEOVERSE_N1	0xD0C
 #define ARM_CPU_PART_CORTEX_A77		0xD0D
+#define ARM_CPU_PART_CORTEX_A76AE	0xD0E
 #define ARM_CPU_PART_NEOVERSE_V1	0xD40
 #define ARM_CPU_PART_CORTEX_A78		0xD41
 #define ARM_CPU_PART_CORTEX_A78AE	0xD42
 #define ARM_CPU_PART_CORTEX_X1		0xD44
 #define ARM_CPU_PART_CORTEX_A510	0xD46
+#define ARM_CPU_PART_CORTEX_X1C		0xD4C
 #define ARM_CPU_PART_CORTEX_A520	0xD80
 #define ARM_CPU_PART_CORTEX_A710	0xD47
 #define ARM_CPU_PART_CORTEX_A715	0xD4D
@@ -119,9 +121,11 @@
 #define QCOM_CPU_PART_KRYO		0x200
 #define QCOM_CPU_PART_KRYO_2XX_GOLD	0x800
 #define QCOM_CPU_PART_KRYO_2XX_SILVER	0x801
+#define QCOM_CPU_PART_KRYO_3XX_GOLD	0x802
 #define QCOM_CPU_PART_KRYO_3XX_SILVER	0x803
 #define QCOM_CPU_PART_KRYO_4XX_GOLD	0x804
 #define QCOM_CPU_PART_KRYO_4XX_SILVER	0x805
+#define QCOM_CPU_PART_ORYON_X1		0x001
 
 #define NVIDIA_CPU_PART_DENVER		0x003
 #define NVIDIA_CPU_PART_CARMEL		0x004
@@ -129,6 +133,7 @@
 #define FUJITSU_CPU_PART_A64FX		0x001
 
 #define HISI_CPU_PART_TSV110		0xD01
+#define HISI_CPU_PART_HIP09			0xD02
 #define HISI_CPU_PART_HIP12		0xD06
 
 #define APPLE_CPU_PART_M1_ICESTORM	0x022
@@ -159,11 +164,13 @@
 #define MIDR_CORTEX_A76	MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A76)
 #define MIDR_NEOVERSE_N1 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_N1)
 #define MIDR_CORTEX_A77	MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A77)
+#define MIDR_CORTEX_A76AE	MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A76AE)
 #define MIDR_NEOVERSE_V1	MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_V1)
 #define MIDR_CORTEX_A78	MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78)
 #define MIDR_CORTEX_A78AE	MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78AE)
 #define MIDR_CORTEX_X1	MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X1)
 #define MIDR_CORTEX_A510 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A510)
+#define MIDR_CORTEX_X1C MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X1C)
 #define MIDR_CORTEX_A520 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A520)
 #define MIDR_CORTEX_A710 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A710)
 #define MIDR_CORTEX_A715 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A715)
@@ -196,13 +203,26 @@
 #define MIDR_QCOM_KRYO MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO)
 #define MIDR_QCOM_KRYO_2XX_GOLD MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO_2XX_GOLD)
 #define MIDR_QCOM_KRYO_2XX_SILVER MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO_2XX_SILVER)
+#define MIDR_QCOM_KRYO_3XX_GOLD MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO_3XX_GOLD)
 #define MIDR_QCOM_KRYO_3XX_SILVER MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO_3XX_SILVER)
 #define MIDR_QCOM_KRYO_4XX_GOLD MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO_4XX_GOLD)
 #define MIDR_QCOM_KRYO_4XX_SILVER MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO_4XX_SILVER)
+#define MIDR_QCOM_ORYON_X1 MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_ORYON_X1)
+
+/*
+ * NOTES:
+ * - Qualcomm Kryo 5XX Prime / Gold ID themselves as MIDR_CORTEX_A77
+ * - Qualcomm Kryo 5XX Silver IDs itself as MIDR_QCOM_KRYO_4XX_SILVER
+ * - Qualcomm Kryo 6XX Prime IDs itself as MIDR_CORTEX_X1
+ * - Qualcomm Kryo 6XX Gold IDs itself as ARM_CPU_PART_CORTEX_A78
+ * - Qualcomm Kryo 6XX Silver IDs itself as MIDR_CORTEX_A55
+ */
+
 #define MIDR_NVIDIA_DENVER MIDR_CPU_MODEL(ARM_CPU_IMP_NVIDIA, NVIDIA_CPU_PART_DENVER)
 #define MIDR_NVIDIA_CARMEL MIDR_CPU_MODEL(ARM_CPU_IMP_NVIDIA, NVIDIA_CPU_PART_CARMEL)
 #define MIDR_FUJITSU_A64FX MIDR_CPU_MODEL(ARM_CPU_IMP_FUJITSU, FUJITSU_CPU_PART_A64FX)
 #define MIDR_HISI_TSV110 MIDR_CPU_MODEL(ARM_CPU_IMP_HISI, HISI_CPU_PART_TSV110)
+#define MIDR_HISI_HIP09 MIDR_CPU_MODEL(ARM_CPU_IMP_HISI, HISI_CPU_PART_HIP09)
 #define MIDR_HISI_HIP12 MIDR_CPU_MODEL(ARM_CPU_IMP_HISI, HISI_CPU_PART_HIP12)
 #define MIDR_APPLE_M1_ICESTORM MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_ICESTORM)
 #define MIDR_APPLE_M1_FIRESTORM MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_FIRESTORM)
@@ -291,6 +311,14 @@ static inline u32 __attribute_const__ read_cpuid_id(void)
 	return read_cpuid(MIDR_EL1);
 }
 
+struct target_impl_cpu {
+	u64 midr;
+	u64 revidr;
+	u64 aidr;
+};
+
+bool cpu_errata_set_target_impl(u64 num, void *impl_cpus);
+
 static inline u64 __attribute_const__ read_cpuid_mpidr(void)
 {
 	return read_cpuid(MPIDR_EL1);
diff --git a/tools/arch/arm64/include/asm/sysreg.h b/tools/arch/arm64/include/asm/sysreg.h
index 690b6eb..65f2759 100644
--- a/tools/arch/arm64/include/asm/sysreg.h
+++ b/tools/arch/arm64/include/asm/sysreg.h
@@ -1080,9 +1080,6 @@
 
 #define ARM64_FEATURE_FIELD_BITS	4
 
-/* Defined for compatibility only, do not add new users. */
-#define ARM64_FEATURE_MASK(x)	(x##_MASK)
-
 #ifdef __ASSEMBLY__
 
 	.macro	mrs_s, rt, sreg
diff --git a/tools/arch/powerpc/include/uapi/asm/kvm.h b/tools/arch/powerpc/include/uapi/asm/kvm.h
index eaeda00..077c543 100644
--- a/tools/arch/powerpc/include/uapi/asm/kvm.h
+++ b/tools/arch/powerpc/include/uapi/asm/kvm.h
@@ -1,18 +1,5 @@
 /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 /*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License, version 2, as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
- *
  * Copyright IBM Corp. 2007
  *
  * Authors: Hollis Blanchard <hollisb@us.ibm.com>
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index ee17623..06fc047 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -218,6 +218,7 @@
 #define X86_FEATURE_FLEXPRIORITY	( 8*32+ 1) /* "flexpriority" Intel FlexPriority */
 #define X86_FEATURE_EPT			( 8*32+ 2) /* "ept" Intel Extended Page Table */
 #define X86_FEATURE_VPID		( 8*32+ 3) /* "vpid" Intel Virtual Processor ID */
+#define X86_FEATURE_COHERENCY_SFW_NO	( 8*32+ 4) /* SNP cache coherency software work around not needed */
 
 #define X86_FEATURE_VMMCALL		( 8*32+15) /* "vmmcall" Prefer VMMCALL to VMCALL */
 #define X86_FEATURE_XENPV		( 8*32+16) /* Xen paravirtual guest */
@@ -456,10 +457,14 @@
 #define X86_FEATURE_NO_NESTED_DATA_BP	(20*32+ 0) /* No Nested Data Breakpoints */
 #define X86_FEATURE_WRMSR_XX_BASE_NS	(20*32+ 1) /* WRMSR to {FS,GS,KERNEL_GS}_BASE is non-serializing */
 #define X86_FEATURE_LFENCE_RDTSC	(20*32+ 2) /* LFENCE always serializing / synchronizes RDTSC */
+#define X86_FEATURE_VERW_CLEAR		(20*32+ 5) /* The memory form of VERW mitigates TSA */
 #define X86_FEATURE_NULL_SEL_CLR_BASE	(20*32+ 6) /* Null Selector Clears Base */
+
 #define X86_FEATURE_AUTOIBRS		(20*32+ 8) /* Automatic IBRS */
 #define X86_FEATURE_NO_SMM_CTL_MSR	(20*32+ 9) /* SMM_CTL MSR is not present */
 
+#define X86_FEATURE_GP_ON_USER_CPUID	(20*32+17) /* User CPUID faulting */
+
 #define X86_FEATURE_PREFETCHI		(20*32+20) /* Prefetch Data/Instruction to Cache Level */
 #define X86_FEATURE_SBPB		(20*32+27) /* Selective Branch Prediction Barrier */
 #define X86_FEATURE_IBPB_BRTYPE		(20*32+28) /* MSR_PRED_CMD[IBPB] flushes all branch type predictions */
@@ -487,6 +492,9 @@
 #define X86_FEATURE_PREFER_YMM		(21*32+ 8) /* Avoid ZMM registers due to downclocking */
 #define X86_FEATURE_APX			(21*32+ 9) /* Advanced Performance Extensions */
 #define X86_FEATURE_INDIRECT_THUNK_ITS	(21*32+10) /* Use thunk for indirect branches in lower half of cacheline */
+#define X86_FEATURE_TSA_SQ_NO		(21*32+11) /* AMD CPU not vulnerable to TSA-SQ */
+#define X86_FEATURE_TSA_L1_NO		(21*32+12) /* AMD CPU not vulnerable to TSA-L1 */
+#define X86_FEATURE_CLEAR_CPU_BUF_VM	(21*32+13) /* Clear CPU buffers using VERW before VMRUN */
 
 /*
  * BUG word(s)
@@ -542,5 +550,5 @@
 #define X86_BUG_OLD_MICROCODE		X86_BUG( 1*32+ 6) /* "old_microcode" CPU has old microcode, it is surely vulnerable to something */
 #define X86_BUG_ITS			X86_BUG( 1*32+ 7) /* "its" CPU is affected by Indirect Target Selection */
 #define X86_BUG_ITS_NATIVE_ONLY		X86_BUG( 1*32+ 8) /* "its_native_only" CPU is affected by ITS, VMX is not affected */
-
+#define X86_BUG_TSA			X86_BUG( 1*32+ 9) /* "tsa" CPU is affected by Transient Scheduler Attacks */
 #endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h
index 5cfb5d7..b65c3ba 100644
--- a/tools/arch/x86/include/asm/msr-index.h
+++ b/tools/arch/x86/include/asm/msr-index.h
@@ -419,6 +419,7 @@
 #define DEBUGCTLMSR_FREEZE_PERFMON_ON_PMI	(1UL << 12)
 #define DEBUGCTLMSR_FREEZE_IN_SMM_BIT	14
 #define DEBUGCTLMSR_FREEZE_IN_SMM	(1UL << DEBUGCTLMSR_FREEZE_IN_SMM_BIT)
+#define DEBUGCTLMSR_RTM_DEBUG		BIT(15)
 
 #define MSR_PEBS_FRONTEND		0x000003f7
 
@@ -733,6 +734,11 @@
 #define MSR_AMD64_PERF_CNTR_GLOBAL_CTL		0xc0000301
 #define MSR_AMD64_PERF_CNTR_GLOBAL_STATUS_CLR	0xc0000302
 
+/* AMD Hardware Feedback Support MSRs */
+#define MSR_AMD_WORKLOAD_CLASS_CONFIG		0xc0000500
+#define MSR_AMD_WORKLOAD_CLASS_ID		0xc0000501
+#define MSR_AMD_WORKLOAD_HRST			0xc0000502
+
 /* AMD Last Branch Record MSRs */
 #define MSR_AMD64_LBR_SELECT			0xc000010e
 
@@ -831,6 +837,7 @@
 #define MSR_K7_HWCR_SMMLOCK		BIT_ULL(MSR_K7_HWCR_SMMLOCK_BIT)
 #define MSR_K7_HWCR_IRPERF_EN_BIT	30
 #define MSR_K7_HWCR_IRPERF_EN		BIT_ULL(MSR_K7_HWCR_IRPERF_EN_BIT)
+#define MSR_K7_HWCR_CPUID_USER_DIS_BIT	35
 #define MSR_K7_FID_VID_CTL		0xc0010041
 #define MSR_K7_FID_VID_STATUS		0xc0010042
 #define MSR_K7_HWCR_CPB_DIS_BIT		25
diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h
index 6f34995..0f15d68 100644
--- a/tools/arch/x86/include/uapi/asm/kvm.h
+++ b/tools/arch/x86/include/uapi/asm/kvm.h
@@ -965,7 +965,13 @@ struct kvm_tdx_cmd {
 struct kvm_tdx_capabilities {
 	__u64 supported_attrs;
 	__u64 supported_xfam;
-	__u64 reserved[254];
+
+	__u64 kernel_tdvmcallinfo_1_r11;
+	__u64 user_tdvmcallinfo_1_r11;
+	__u64 kernel_tdvmcallinfo_1_r12;
+	__u64 user_tdvmcallinfo_1_r12;
+
+	__u64 reserved[250];
 
 	/* Configurable CPUID bits for userspace */
 	struct kvm_cpuid2 cpuid;
diff --git a/tools/include/linux/bits.h b/tools/include/linux/bits.h
index 7ad0562..a40cc86 100644
--- a/tools/include/linux/bits.h
+++ b/tools/include/linux/bits.h
@@ -2,10 +2,8 @@
 #ifndef __LINUX_BITS_H
 #define __LINUX_BITS_H
 
-#include <linux/const.h>
 #include <vdso/bits.h>
 #include <uapi/linux/bits.h>
-#include <asm/bitsperlong.h>
 
 #define BIT_MASK(nr)		(UL(1) << ((nr) % BITS_PER_LONG))
 #define BIT_WORD(nr)		((nr) / BITS_PER_LONG)
@@ -50,10 +48,14 @@
 	     (type_max(t) << (l) &				\
 	      type_max(t) >> (BITS_PER_TYPE(t) - 1 - (h)))))
 
+#define GENMASK(h, l)		GENMASK_TYPE(unsigned long, h, l)
+#define GENMASK_ULL(h, l)	GENMASK_TYPE(unsigned long long, h, l)
+
 #define GENMASK_U8(h, l)	GENMASK_TYPE(u8, h, l)
 #define GENMASK_U16(h, l)	GENMASK_TYPE(u16, h, l)
 #define GENMASK_U32(h, l)	GENMASK_TYPE(u32, h, l)
 #define GENMASK_U64(h, l)	GENMASK_TYPE(u64, h, l)
+#define GENMASK_U128(h, l)	GENMASK_TYPE(u128, h, l)
 
 /*
  * Fixed-type variants of BIT(), with additional checks like GENMASK_TYPE(). The
@@ -79,28 +81,9 @@
  * BUILD_BUG_ON_ZERO is not available in h files included from asm files,
  * disable the input check if that is the case.
  */
-#define GENMASK_INPUT_CHECK(h, l) 0
+#define GENMASK(h, l)		__GENMASK(h, l)
+#define GENMASK_ULL(h, l)	__GENMASK_ULL(h, l)
 
 #endif /* !defined(__ASSEMBLY__) */
 
-#define GENMASK(h, l) \
-	(GENMASK_INPUT_CHECK(h, l) + __GENMASK(h, l))
-#define GENMASK_ULL(h, l) \
-	(GENMASK_INPUT_CHECK(h, l) + __GENMASK_ULL(h, l))
-
-#if !defined(__ASSEMBLY__)
-/*
- * Missing asm support
- *
- * __GENMASK_U128() depends on _BIT128() which would not work
- * in the asm code, as it shifts an 'unsigned __int128' data
- * type instead of direct representation of 128 bit constants
- * such as long and unsigned long. The fundamental problem is
- * that a 128 bit constant will get silently truncated by the
- * gcc compiler.
- */
-#define GENMASK_U128(h, l) \
-	(GENMASK_INPUT_CHECK(h, l) + __GENMASK_U128(h, l))
-#endif
-
 #endif	/* __LINUX_BITS_H */
diff --git a/tools/include/linux/cfi_types.h b/tools/include/linux/cfi_types.h
index 6b87136..685f718 100644
--- a/tools/include/linux/cfi_types.h
+++ b/tools/include/linux/cfi_types.h
@@ -41,5 +41,28 @@
 	SYM_TYPED_START(name, SYM_L_GLOBAL, SYM_A_ALIGN)
 #endif
 
+#else /* __ASSEMBLY__ */
+
+#ifdef CONFIG_CFI_CLANG
+#define DEFINE_CFI_TYPE(name, func)						\
+	/*									\
+	 * Force a reference to the function so the compiler generates		\
+	 * __kcfi_typeid_<func>.						\
+	 */									\
+	__ADDRESSABLE(func);							\
+	/* u32 name __ro_after_init = __kcfi_typeid_<func> */			\
+	extern u32 name;							\
+	asm (									\
+	"	.pushsection	.data..ro_after_init,\"aw\",\%progbits	\n"	\
+	"	.type	" #name ",\%object				\n"	\
+	"	.globl	" #name "					\n"	\
+	"	.p2align	2, 0x0					\n"	\
+	#name ":							\n"	\
+	"	.4byte	__kcfi_typeid_" #func "				\n"	\
+	"	.size	" #name ", 4					\n"	\
+	"	.popsection						\n"	\
+	);
+#endif
+
 #endif /* __ASSEMBLY__ */
 #endif /* _LINUX_CFI_TYPES_H */
diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h
index 2892a45..04e0077 100644
--- a/tools/include/uapi/asm-generic/unistd.h
+++ b/tools/include/uapi/asm-generic/unistd.h
@@ -852,8 +852,14 @@ __SYSCALL(__NR_removexattrat, sys_removexattrat)
 #define __NR_open_tree_attr 467
 __SYSCALL(__NR_open_tree_attr, sys_open_tree_attr)
 
+/* fs/inode.c */
+#define __NR_file_getattr 468
+__SYSCALL(__NR_file_getattr, sys_file_getattr)
+#define __NR_file_setattr 469
+__SYSCALL(__NR_file_setattr, sys_file_setattr)
+
 #undef __NR_syscalls
-#define __NR_syscalls 468
+#define __NR_syscalls 470
 
 /*
  * 32 bit systems traditionally used different
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index 7415a38..f0f0d49 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -178,6 +178,7 @@ struct kvm_xen_exit {
 #define KVM_EXIT_NOTIFY           37
 #define KVM_EXIT_LOONGARCH_IOCSR  38
 #define KVM_EXIT_MEMORY_FAULT     39
+#define KVM_EXIT_TDX              40
 
 /* For KVM_EXIT_INTERNAL_ERROR */
 /* Emulate instruction failed. */
@@ -447,6 +448,31 @@ struct kvm_run {
 			__u64 gpa;
 			__u64 size;
 		} memory_fault;
+		/* KVM_EXIT_TDX */
+		struct {
+			__u64 flags;
+			__u64 nr;
+			union {
+				struct {
+					__u64 ret;
+					__u64 data[5];
+				} unknown;
+				struct {
+					__u64 ret;
+					__u64 gpa;
+					__u64 size;
+				} get_quote;
+				struct {
+					__u64 ret;
+					__u64 leaf;
+					__u64 r11, r12, r13, r14;
+				} get_tdvmcall_info;
+				struct {
+					__u64 ret;
+					__u64 vector;
+				} setup_event_notify;
+			};
+		} tdx;
 		/* Fix the size of the union. */
 		char padding[256];
 	};
@@ -935,6 +961,7 @@ struct kvm_enable_cap {
 #define KVM_CAP_ARM_EL2 240
 #define KVM_CAP_ARM_EL2_E2H0 241
 #define KVM_CAP_RISCV_MP_STATE_RESET 242
+#define KVM_CAP_ARM_CACHEABLE_PFNMAP_SUPPORTED 243
 
 struct kvm_irq_routing_irqchip {
 	__u32 irqchip;
diff --git a/tools/perf/arch/arm/entry/syscalls/syscall.tbl b/tools/perf/arch/arm/entry/syscalls/syscall.tbl
index 27c1d5e..b07e699 100644
--- a/tools/perf/arch/arm/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/arm/entry/syscalls/syscall.tbl
@@ -482,3 +482,5 @@
 465	common	listxattrat			sys_listxattrat
 466	common	removexattrat			sys_removexattrat
 467	common	open_tree_attr			sys_open_tree_attr
+468	common	file_getattr			sys_file_getattr
+469	common	file_setattr			sys_file_setattr
diff --git a/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl b/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl
index 1e8c44c..7a7049c 100644
--- a/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl
+++ b/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl
@@ -382,3 +382,5 @@
 465	n64	listxattrat			sys_listxattrat
 466	n64	removexattrat			sys_removexattrat
 467	n64	open_tree_attr			sys_open_tree_attr
+468	n64	file_getattr			sys_file_getattr
+469	n64	file_setattr			sys_file_setattr
diff --git a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
index 9a084bd..b453e80 100644
--- a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
@@ -558,3 +558,5 @@
 465	common	listxattrat			sys_listxattrat
 466	common	removexattrat			sys_removexattrat
 467	common	open_tree_attr			sys_open_tree_attr
+468	common	file_getattr			sys_file_getattr
+469	common	file_setattr			sys_file_setattr
diff --git a/tools/perf/arch/s390/entry/syscalls/syscall.tbl b/tools/perf/arch/s390/entry/syscalls/syscall.tbl
index a4569b9..8a6744d 100644
--- a/tools/perf/arch/s390/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/s390/entry/syscalls/syscall.tbl
@@ -470,3 +470,5 @@
 465  common	listxattrat		sys_listxattrat			sys_listxattrat
 466  common	removexattrat		sys_removexattrat		sys_removexattrat
 467  common	open_tree_attr		sys_open_tree_attr		sys_open_tree_attr
+468  common	file_getattr		sys_file_getattr		sys_file_getattr
+469  common	file_setattr		sys_file_setattr		sys_file_setattr
diff --git a/tools/perf/arch/sh/entry/syscalls/syscall.tbl b/tools/perf/arch/sh/entry/syscalls/syscall.tbl
index 52a7652..5e9c9ef 100644
--- a/tools/perf/arch/sh/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/sh/entry/syscalls/syscall.tbl
@@ -471,3 +471,5 @@
 465	common	listxattrat			sys_listxattrat
 466	common	removexattrat			sys_removexattrat
 467	common	open_tree_attr			sys_open_tree_attr
+468	common	file_getattr			sys_file_getattr
+469	common	file_setattr			sys_file_setattr
diff --git a/tools/perf/arch/sparc/entry/syscalls/syscall.tbl b/tools/perf/arch/sparc/entry/syscalls/syscall.tbl
index 83e45eb..ebb7d06 100644
--- a/tools/perf/arch/sparc/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/sparc/entry/syscalls/syscall.tbl
@@ -513,3 +513,5 @@
 465	common	listxattrat			sys_listxattrat
 466	common	removexattrat			sys_removexattrat
 467	common	open_tree_attr			sys_open_tree_attr
+468	common	file_getattr			sys_file_getattr
+469	common	file_setattr			sys_file_setattr
diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_32.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_32.tbl
index ac007ea..4877e16 100644
--- a/tools/perf/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/tools/perf/arch/x86/entry/syscalls/syscall_32.tbl
@@ -473,3 +473,5 @@
 465	i386	listxattrat		sys_listxattrat
 466	i386	removexattrat		sys_removexattrat
 467	i386	open_tree_attr		sys_open_tree_attr
+468	i386	file_getattr		sys_file_getattr
+469	i386	file_setattr		sys_file_setattr
diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
index cfb5ca4..92cf0fe 100644
--- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
@@ -391,6 +391,8 @@
 465	common	listxattrat		sys_listxattrat
 466	common	removexattrat		sys_removexattrat
 467	common	open_tree_attr		sys_open_tree_attr
+468	common	file_getattr		sys_file_getattr
+469	common	file_setattr		sys_file_setattr
 
 #
 # Due to a historical design error, certain syscalls are numbered differently
diff --git a/tools/perf/arch/x86/tests/topdown.c b/tools/perf/arch/x86/tests/topdown.c
index 8d0ea7a..1eba3b4 100644
--- a/tools/perf/arch/x86/tests/topdown.c
+++ b/tools/perf/arch/x86/tests/topdown.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include "arch-tests.h"
 #include "../util/topdown.h"
+#include "debug.h"
 #include "evlist.h"
 #include "parse-events.h"
 #include "pmu.h"
diff --git a/tools/perf/arch/xtensa/entry/syscalls/syscall.tbl b/tools/perf/arch/xtensa/entry/syscalls/syscall.tbl
index f657a77..374e4cb 100644
--- a/tools/perf/arch/xtensa/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/xtensa/entry/syscalls/syscall.tbl
@@ -438,3 +438,5 @@
 465	common	listxattrat			sys_listxattrat
 466	common	removexattrat			sys_removexattrat
 467	common	open_tree_attr			sys_open_tree_attr
+468	common	file_getattr			sys_file_getattr
+469	common	file_setattr			sys_file_setattr
diff --git a/tools/perf/bench/inject-buildid.c b/tools/perf/bench/inject-buildid.c
index aad572a..12387ea 100644
--- a/tools/perf/bench/inject-buildid.c
+++ b/tools/perf/bench/inject-buildid.c
@@ -85,7 +85,7 @@ static int add_dso(const char *fpath, const struct stat *sb __maybe_unused,
 	if (typeflag == FTW_D || typeflag == FTW_SL)
 		return 0;
 
-	if (filename__read_build_id(fpath, &bid) < 0)
+	if (filename__read_build_id(fpath, &bid, /*block=*/true) < 0)
 		return 0;
 
 	dso->name = realpath(fpath, NULL);
diff --git a/tools/perf/builtin-buildid-cache.c b/tools/perf/builtin-buildid-cache.c
index c981044..2e0f200 100644
--- a/tools/perf/builtin-buildid-cache.c
+++ b/tools/perf/builtin-buildid-cache.c
@@ -180,7 +180,7 @@ static int build_id_cache__add_file(const char *filename, struct nsinfo *nsi)
 	struct nscookie nsc;
 
 	nsinfo__mountns_enter(nsi, &nsc);
-	err = filename__read_build_id(filename, &bid);
+	err = filename__read_build_id(filename, &bid, /*block=*/true);
 	nsinfo__mountns_exit(&nsc);
 	if (err < 0) {
 		pr_debug("Couldn't read a build-id in %s\n", filename);
@@ -204,7 +204,7 @@ static int build_id_cache__remove_file(const char *filename, struct nsinfo *nsi)
 	int err;
 
 	nsinfo__mountns_enter(nsi, &nsc);
-	err = filename__read_build_id(filename, &bid);
+	err = filename__read_build_id(filename, &bid, /*block=*/true);
 	nsinfo__mountns_exit(&nsc);
 	if (err < 0) {
 		pr_debug("Couldn't read a build-id in %s\n", filename);
@@ -280,7 +280,7 @@ static bool dso__missing_buildid_cache(struct dso *dso, int parm __maybe_unused)
 	if (!dso__build_id_filename(dso, filename, sizeof(filename), false))
 		return true;
 
-	if (filename__read_build_id(filename, &bid) == -1) {
+	if (filename__read_build_id(filename, &bid, /*block=*/true) == -1) {
 		if (errno == ENOENT)
 			return false;
 
@@ -309,7 +309,7 @@ static int build_id_cache__update_file(const char *filename, struct nsinfo *nsi)
 	int err;
 
 	nsinfo__mountns_enter(nsi, &nsc);
-	err = filename__read_build_id(filename, &bid);
+	err = filename__read_build_id(filename, &bid, /*block=*/true);
 	nsinfo__mountns_exit(&nsc);
 	if (err < 0) {
 		pr_debug("Couldn't read a build-id in %s\n", filename);
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index 40ba6a9..a114b3f 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -680,12 +680,12 @@ static int dso__read_build_id(struct dso *dso)
 
 	mutex_lock(dso__lock(dso));
 	nsinfo__mountns_enter(dso__nsinfo(dso), &nsc);
-	if (filename__read_build_id(dso__long_name(dso), &bid) > 0)
+	if (filename__read_build_id(dso__long_name(dso), &bid, /*block=*/true) > 0)
 		dso__set_build_id(dso, &bid);
 	else if (dso__nsinfo(dso)) {
 		char *new_name = dso__filename_with_chroot(dso, dso__long_name(dso));
 
-		if (new_name && filename__read_build_id(new_name, &bid) > 0)
+		if (new_name && filename__read_build_id(new_name, &bid, /*block=*/true) > 0)
 			dso__set_build_id(dso, &bid);
 		free(new_name);
 	}
diff --git a/tools/perf/tests/sdt.c b/tools/perf/tests/sdt.c
index 93baee2..6132f1a 100644
--- a/tools/perf/tests/sdt.c
+++ b/tools/perf/tests/sdt.c
@@ -31,7 +31,7 @@ static int build_id_cache__add_file(const char *filename)
 	struct build_id bid = { .size = 0, };
 	int err;
 
-	err = filename__read_build_id(filename, &bid);
+	err = filename__read_build_id(filename, &bid, /*block=*/true);
 	if (err < 0) {
 		pr_debug("Failed to read build id of %s\n", filename);
 		return err;
diff --git a/tools/perf/trace/beauty/include/uapi/linux/fcntl.h b/tools/perf/trace/beauty/include/uapi/linux/fcntl.h
index a15ac2f..f291ab4 100644
--- a/tools/perf/trace/beauty/include/uapi/linux/fcntl.h
+++ b/tools/perf/trace/beauty/include/uapi/linux/fcntl.h
@@ -90,10 +90,28 @@
 #define DN_ATTRIB	0x00000020	/* File changed attibutes */
 #define DN_MULTISHOT	0x80000000	/* Don't remove notifier */
 
+/* Reserved kernel ranges [-100], [-10000, -40000]. */
 #define AT_FDCWD		-100    /* Special value for dirfd used to
 					   indicate openat should use the
 					   current working directory. */
 
+/*
+ * The concept of process and threads in userland and the kernel is a confusing
+ * one - within the kernel every thread is a 'task' with its own individual PID,
+ * however from userland's point of view threads are grouped by a single PID,
+ * which is that of the 'thread group leader', typically the first thread
+ * spawned.
+ *
+ * To cut the Gideon knot, for internal kernel usage, we refer to
+ * PIDFD_SELF_THREAD to refer to the current thread (or task from a kernel
+ * perspective), and PIDFD_SELF_THREAD_GROUP to refer to the current thread
+ * group leader...
+ */
+#define PIDFD_SELF_THREAD		-10000 /* Current thread. */
+#define PIDFD_SELF_THREAD_GROUP		-10001 /* Current thread group leader. */
+
+#define FD_PIDFS_ROOT			-10002 /* Root of the pidfs filesystem */
+#define FD_INVALID			-10009 /* Invalid file descriptor: -10000 - EBADF = -10009 */
 
 /* Generic flags for the *at(2) family of syscalls. */
 
diff --git a/tools/perf/trace/beauty/include/uapi/linux/fs.h b/tools/perf/trace/beauty/include/uapi/linux/fs.h
index 0098b0c..0bd678a 100644
--- a/tools/perf/trace/beauty/include/uapi/linux/fs.h
+++ b/tools/perf/trace/beauty/include/uapi/linux/fs.h
@@ -60,6 +60,17 @@
 #define RENAME_EXCHANGE		(1 << 1)	/* Exchange source and dest */
 #define RENAME_WHITEOUT		(1 << 2)	/* Whiteout source */
 
+/*
+ * The root inode of procfs is guaranteed to always have the same inode number.
+ * For programs that make heavy use of procfs, verifying that the root is a
+ * real procfs root and using openat2(RESOLVE_{NO_{XDEV,MAGICLINKS},BENEATH})
+ * will allow you to make sure you are never tricked into operating on the
+ * wrong procfs file.
+ */
+enum procfs_ino {
+	PROCFS_ROOT_INO = 1,
+};
+
 struct file_clone_range {
 	__s64 src_fd;
 	__u64 src_offset;
@@ -91,6 +102,63 @@ struct fs_sysfs_path {
 	__u8			name[128];
 };
 
+/* Protection info capability flags */
+#define	LBMD_PI_CAP_INTEGRITY		(1 << 0)
+#define	LBMD_PI_CAP_REFTAG		(1 << 1)
+
+/* Checksum types for Protection Information */
+#define LBMD_PI_CSUM_NONE		0
+#define LBMD_PI_CSUM_IP			1
+#define LBMD_PI_CSUM_CRC16_T10DIF	2
+#define LBMD_PI_CSUM_CRC64_NVME		4
+
+/* sizeof first published struct */
+#define LBMD_SIZE_VER0			16
+
+/*
+ * Logical block metadata capability descriptor
+ * If the device does not support metadata, all the fields will be zero.
+ * Applications must check lbmd_flags to determine whether metadata is
+ * supported or not.
+ */
+struct logical_block_metadata_cap {
+	/* Bitmask of logical block metadata capability flags */
+	__u32	lbmd_flags;
+	/*
+	 * The amount of data described by each unit of logical block
+	 * metadata
+	 */
+	__u16	lbmd_interval;
+	/*
+	 * Size in bytes of the logical block metadata associated with each
+	 * interval
+	 */
+	__u8	lbmd_size;
+	/*
+	 * Size in bytes of the opaque block tag associated with each
+	 * interval
+	 */
+	__u8	lbmd_opaque_size;
+	/*
+	 * Offset in bytes of the opaque block tag within the logical block
+	 * metadata
+	 */
+	__u8	lbmd_opaque_offset;
+	/* Size in bytes of the T10 PI tuple associated with each interval */
+	__u8	lbmd_pi_size;
+	/* Offset in bytes of T10 PI tuple within the logical block metadata */
+	__u8	lbmd_pi_offset;
+	/* T10 PI guard tag type */
+	__u8	lbmd_guard_tag_type;
+	/* Size in bytes of the T10 PI application tag */
+	__u8	lbmd_app_tag_size;
+	/* Size in bytes of the T10 PI reference tag */
+	__u8	lbmd_ref_tag_size;
+	/* Size in bytes of the T10 PI storage tag */
+	__u8	lbmd_storage_tag_size;
+	__u8	pad;
+};
+
 /* extent-same (dedupe) ioctls; these MUST match the btrfs ioctl definitions */
 #define FILE_DEDUPE_RANGE_SAME		0
 #define FILE_DEDUPE_RANGE_DIFFERS	1
@@ -149,6 +217,24 @@ struct fsxattr {
 };
 
 /*
+ * Variable size structure for file_[sg]et_attr().
+ *
+ * Note. This is alternative to the structure 'struct file_kattr'/'struct fsxattr'.
+ * As this structure is passed to/from userspace with its size, this can
+ * be versioned based on the size.
+ */
+struct file_attr {
+	__u64 fa_xflags;	/* xflags field value (get/set) */
+	__u32 fa_extsize;	/* extsize field value (get/set)*/
+	__u32 fa_nextents;	/* nextents field value (get)   */
+	__u32 fa_projid;	/* project identifier (get/set) */
+	__u32 fa_cowextsize;	/* CoW extsize field value (get/set) */
+};
+
+#define FILE_ATTR_SIZE_VER0 24
+#define FILE_ATTR_SIZE_LATEST FILE_ATTR_SIZE_VER0
+
+/*
  * Flags for the fsx_xflags field
  */
 #define FS_XFLAG_REALTIME	0x00000001	/* data in realtime volume */
@@ -247,6 +333,8 @@ struct fsxattr {
  * also /sys/kernel/debug/ for filesystems with debugfs exports
  */
 #define FS_IOC_GETFSSYSFSPATH		_IOR(0x15, 1, struct fs_sysfs_path)
+/* Get logical block metadata capability details */
+#define FS_IOC_GETLBMD_CAP		_IOWR(0x15, 2, struct logical_block_metadata_cap)
 
 /*
  * Inode flags (FS_IOC_GETFLAGS / FS_IOC_SETFLAGS)
diff --git a/tools/perf/trace/beauty/include/uapi/linux/prctl.h b/tools/perf/trace/beauty/include/uapi/linux/prctl.h
index 3b93fb9..ed3aed2 100644
--- a/tools/perf/trace/beauty/include/uapi/linux/prctl.h
+++ b/tools/perf/trace/beauty/include/uapi/linux/prctl.h
@@ -244,6 +244,8 @@ struct prctl_mm_map {
 # define PR_MTE_TAG_MASK		(0xffffUL << PR_MTE_TAG_SHIFT)
 /* Unused; kept only for source compatibility */
 # define PR_MTE_TCF_SHIFT		1
+/* MTE tag check store only */
+# define PR_MTE_STORE_ONLY		(1UL << 19)
 /* RISC-V pointer masking tag length */
 # define PR_PMLEN_SHIFT			24
 # define PR_PMLEN_MASK			(0x7fUL << PR_PMLEN_SHIFT)
@@ -255,7 +257,12 @@ struct prctl_mm_map {
 /* Dispatch syscalls to a userspace handler */
 #define PR_SET_SYSCALL_USER_DISPATCH	59
 # define PR_SYS_DISPATCH_OFF		0
-# define PR_SYS_DISPATCH_ON		1
+/* Enable dispatch except for the specified range */
+# define PR_SYS_DISPATCH_EXCLUSIVE_ON	1
+/* Enable dispatch for the specified range */
+# define PR_SYS_DISPATCH_INCLUSIVE_ON	2
+/* Legacy name for backwards compatibility */
+# define PR_SYS_DISPATCH_ON		PR_SYS_DISPATCH_EXCLUSIVE_ON
 /* The control values for the user space selector when dispatch is enabled */
 # define SYSCALL_DISPATCH_FILTER_ALLOW	0
 # define SYSCALL_DISPATCH_FILTER_BLOCK	1
diff --git a/tools/perf/trace/beauty/include/uapi/linux/vhost.h b/tools/perf/trace/beauty/include/uapi/linux/vhost.h
index d4b3e2a..c57674a 100644
--- a/tools/perf/trace/beauty/include/uapi/linux/vhost.h
+++ b/tools/perf/trace/beauty/include/uapi/linux/vhost.h
@@ -235,4 +235,39 @@
  */
 #define VHOST_VDPA_GET_VRING_SIZE	_IOWR(VHOST_VIRTIO, 0x82,	\
 					      struct vhost_vring_state)
+
+/* Extended features manipulation */
+#define VHOST_GET_FEATURES_ARRAY _IOR(VHOST_VIRTIO, 0x83, \
+				       struct vhost_features_array)
+#define VHOST_SET_FEATURES_ARRAY _IOW(VHOST_VIRTIO, 0x83, \
+				       struct vhost_features_array)
+
+/* fork_owner values for vhost */
+#define VHOST_FORK_OWNER_KTHREAD 0
+#define VHOST_FORK_OWNER_TASK 1
+
+/**
+ * VHOST_SET_FORK_FROM_OWNER - Set the fork_owner flag for the vhost device,
+ * This ioctl must called before VHOST_SET_OWNER.
+ * Only available when CONFIG_VHOST_ENABLE_FORK_OWNER_CONTROL=y
+ *
+ * @param fork_owner: An 8-bit value that determines the vhost thread mode
+ *
+ * When fork_owner is set to VHOST_FORK_OWNER_TASK(default value):
+ *   - Vhost will create vhost worker as tasks forked from the owner,
+ *     inheriting all of the owner's attributes.
+ *
+ * When fork_owner is set to VHOST_FORK_OWNER_KTHREAD:
+ *   - Vhost will create vhost workers as kernel threads.
+ */
+#define VHOST_SET_FORK_FROM_OWNER _IOW(VHOST_VIRTIO, 0x84, __u8)
+
+/**
+ * VHOST_GET_FORK_OWNER - Get the current fork_owner flag for the vhost device.
+ * Only available when CONFIG_VHOST_ENABLE_FORK_OWNER_CONTROL=y
+ *
+ * @return: An 8-bit value indicating the current thread mode.
+ */
+#define VHOST_GET_FORK_FROM_OWNER _IOR(VHOST_VIRTIO, 0x85, __u8)
+
 #endif
diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index a7018a3..bf7f326 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -115,7 +115,7 @@ int filename__snprintf_build_id(const char *pathname, char *sbuild_id, size_t sb
 	struct build_id bid = { .size = 0, };
 	int ret;
 
-	ret = filename__read_build_id(pathname, &bid);
+	ret = filename__read_build_id(pathname, &bid, /*block=*/true);
 	if (ret < 0)
 		return ret;
 
@@ -841,7 +841,7 @@ static int filename__read_build_id_ns(const char *filename,
 	int ret;
 
 	nsinfo__mountns_enter(nsi, &nsc);
-	ret = filename__read_build_id(filename, bid);
+	ret = filename__read_build_id(filename, bid, /*block=*/true);
 	nsinfo__mountns_exit(&nsc);
 
 	return ret;
diff --git a/tools/perf/util/debuginfo.c b/tools/perf/util/debuginfo.c
index a44c70f..bb9ebd8 100644
--- a/tools/perf/util/debuginfo.c
+++ b/tools/perf/util/debuginfo.c
@@ -110,8 +110,12 @@ struct debuginfo *debuginfo__new(const char *path)
 	if (!dso)
 		goto out;
 
-	/* Set the build id for DSO_BINARY_TYPE__BUILDID_DEBUGINFO */
-	if (is_regular_file(path) && filename__read_build_id(path, &bid) > 0)
+	/*
+	 * Set the build id for DSO_BINARY_TYPE__BUILDID_DEBUGINFO. Don't block
+	 * incase the path isn't for a regular file.
+	 */
+	assert(!dso__has_build_id(dso));
+	if (filename__read_build_id(path, &bid, /*block=*/false) > 0)
 		dso__set_build_id(dso, &bid);
 
 	for (type = distro_dwarf_types;
diff --git a/tools/perf/util/dsos.c b/tools/perf/util/dsos.c
index 0a7645c..64c1d65b 100644
--- a/tools/perf/util/dsos.c
+++ b/tools/perf/util/dsos.c
@@ -81,13 +81,13 @@ static int dsos__read_build_ids_cb(struct dso *dso, void *data)
 		return 0;
 	}
 	nsinfo__mountns_enter(dso__nsinfo(dso), &nsc);
-	if (filename__read_build_id(dso__long_name(dso), &bid) > 0) {
+	if (filename__read_build_id(dso__long_name(dso), &bid, /*block=*/true) > 0) {
 		dso__set_build_id(dso, &bid);
 		args->have_build_id = true;
 	} else if (errno == ENOENT && dso__nsinfo(dso)) {
 		char *new_name = dso__filename_with_chroot(dso, dso__long_name(dso));
 
-		if (new_name && filename__read_build_id(new_name, &bid) > 0) {
+		if (new_name && filename__read_build_id(new_name, &bid, /*block=*/true) > 0) {
 			dso__set_build_id(dso, &bid);
 			args->have_build_id = true;
 		}
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 6d2c280..033c792 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -902,7 +902,7 @@ static int read_build_id(const char *filename, struct build_id *bid)
 
 #else // HAVE_LIBBFD_BUILDID_SUPPORT
 
-static int read_build_id(const char *filename, struct build_id *bid)
+static int read_build_id(const char *filename, struct build_id *bid, bool block)
 {
 	size_t size = sizeof(bid->data);
 	int fd, err = -1;
@@ -911,7 +911,7 @@ static int read_build_id(const char *filename, struct build_id *bid)
 	if (size < BUILD_ID_SIZE)
 		goto out;
 
-	fd = open(filename, O_RDONLY);
+	fd = open(filename, block ? O_RDONLY : (O_RDONLY | O_NONBLOCK));
 	if (fd < 0)
 		goto out;
 
@@ -934,7 +934,7 @@ static int read_build_id(const char *filename, struct build_id *bid)
 
 #endif // HAVE_LIBBFD_BUILDID_SUPPORT
 
-int filename__read_build_id(const char *filename, struct build_id *bid)
+int filename__read_build_id(const char *filename, struct build_id *bid, bool block)
 {
 	struct kmod_path m = { .name = NULL, };
 	char path[PATH_MAX];
@@ -958,9 +958,10 @@ int filename__read_build_id(const char *filename, struct build_id *bid)
 		}
 		close(fd);
 		filename = path;
+		block = true;
 	}
 
-	err = read_build_id(filename, bid);
+	err = read_build_id(filename, bid, block);
 
 	if (m.comp)
 		unlink(filename);
diff --git a/tools/perf/util/symbol-minimal.c b/tools/perf/util/symbol-minimal.c
index 7201494c..41e4ebe 100644
--- a/tools/perf/util/symbol-minimal.c
+++ b/tools/perf/util/symbol-minimal.c
@@ -4,7 +4,6 @@
 
 #include <errno.h>
 #include <unistd.h>
-#include <stdio.h>
 #include <fcntl.h>
 #include <string.h>
 #include <stdlib.h>
@@ -86,13 +85,10 @@ int filename__read_debuglink(const char *filename __maybe_unused,
 /*
  * Just try PT_NOTE header otherwise fails
  */
-int filename__read_build_id(const char *filename, struct build_id *bid)
+int filename__read_build_id(const char *filename, struct build_id *bid, bool block)
 {
-	FILE *fp;
-	int ret = -1;
+	int fd, ret = -1;
 	bool need_swap = false, elf32;
-	u8 e_ident[EI_NIDENT];
-	int i;
 	union {
 		struct {
 			Elf32_Ehdr ehdr32;
@@ -103,28 +99,27 @@ int filename__read_build_id(const char *filename, struct build_id *bid)
 			Elf64_Phdr *phdr64;
 		};
 	} hdrs;
-	void *phdr;
-	size_t phdr_size;
-	void *buf = NULL;
-	size_t buf_size = 0;
+	void *phdr, *buf = NULL;
+	ssize_t phdr_size, ehdr_size, buf_size = 0;
 
-	fp = fopen(filename, "r");
-	if (fp == NULL)
+	fd = open(filename, block ? O_RDONLY : (O_RDONLY | O_NONBLOCK));
+	if (fd < 0)
 		return -1;
 
-	if (fread(e_ident, sizeof(e_ident), 1, fp) != 1)
+	if (read(fd, hdrs.ehdr32.e_ident, EI_NIDENT) != EI_NIDENT)
 		goto out;
 
-	if (memcmp(e_ident, ELFMAG, SELFMAG) ||
-	    e_ident[EI_VERSION] != EV_CURRENT)
+	if (memcmp(hdrs.ehdr32.e_ident, ELFMAG, SELFMAG) ||
+	    hdrs.ehdr32.e_ident[EI_VERSION] != EV_CURRENT)
 		goto out;
 
-	need_swap = check_need_swap(e_ident[EI_DATA]);
-	elf32 = e_ident[EI_CLASS] == ELFCLASS32;
+	need_swap = check_need_swap(hdrs.ehdr32.e_ident[EI_DATA]);
+	elf32 = hdrs.ehdr32.e_ident[EI_CLASS] == ELFCLASS32;
+	ehdr_size = (elf32 ? sizeof(hdrs.ehdr32) : sizeof(hdrs.ehdr64)) - EI_NIDENT;
 
-	if (fread(elf32 ? (void *)&hdrs.ehdr32 : (void *)&hdrs.ehdr64,
-		  elf32 ? sizeof(hdrs.ehdr32) : sizeof(hdrs.ehdr64),
-		  1, fp) != 1)
+	if (read(fd,
+		 (elf32 ? (void *)&hdrs.ehdr32 : (void *)&hdrs.ehdr64) + EI_NIDENT,
+		 ehdr_size) != ehdr_size)
 		goto out;
 
 	if (need_swap) {
@@ -138,14 +133,18 @@ int filename__read_build_id(const char *filename, struct build_id *bid)
 			hdrs.ehdr64.e_phnum = bswap_16(hdrs.ehdr64.e_phnum);
 		}
 	}
-	phdr_size = elf32 ? hdrs.ehdr32.e_phentsize * hdrs.ehdr32.e_phnum
-			  : hdrs.ehdr64.e_phentsize * hdrs.ehdr64.e_phnum;
+	if ((elf32 && hdrs.ehdr32.e_phentsize != sizeof(Elf32_Phdr)) ||
+	    (!elf32 && hdrs.ehdr64.e_phentsize != sizeof(Elf64_Phdr)))
+		goto out;
+
+	phdr_size = elf32 ? sizeof(Elf32_Phdr) * hdrs.ehdr32.e_phnum
+			  : sizeof(Elf64_Phdr) * hdrs.ehdr64.e_phnum;
 	phdr = malloc(phdr_size);
 	if (phdr == NULL)
 		goto out;
 
-	fseek(fp, elf32 ? hdrs.ehdr32.e_phoff : hdrs.ehdr64.e_phoff, SEEK_SET);
-	if (fread(phdr, phdr_size, 1, fp) != 1)
+	lseek(fd, elf32 ? hdrs.ehdr32.e_phoff : hdrs.ehdr64.e_phoff, SEEK_SET);
+	if (read(fd, phdr, phdr_size) != phdr_size)
 		goto out_free;
 
 	if (elf32)
@@ -153,8 +152,8 @@ int filename__read_build_id(const char *filename, struct build_id *bid)
 	else
 		hdrs.phdr64 = phdr;
 
-	for (i = 0; i < elf32 ? hdrs.ehdr32.e_phnum : hdrs.ehdr64.e_phnum; i++) {
-		size_t p_filesz;
+	for (int i = 0; i < (elf32 ? hdrs.ehdr32.e_phnum : hdrs.ehdr64.e_phnum); i++) {
+		ssize_t p_filesz;
 
 		if (need_swap) {
 			if (elf32) {
@@ -180,8 +179,8 @@ int filename__read_build_id(const char *filename, struct build_id *bid)
 				goto out_free;
 			buf = tmp;
 		}
-		fseek(fp, elf32 ? hdrs.phdr32[i].p_offset : hdrs.phdr64[i].p_offset, SEEK_SET);
-		if (fread(buf, p_filesz, 1, fp) != 1)
+		lseek(fd, elf32 ? hdrs.phdr32[i].p_offset : hdrs.phdr64[i].p_offset, SEEK_SET);
+		if (read(fd, buf, p_filesz) != p_filesz)
 			goto out_free;
 
 		ret = read_build_id(buf, p_filesz, bid, need_swap);
@@ -194,7 +193,7 @@ int filename__read_build_id(const char *filename, struct build_id *bid)
 	free(buf);
 	free(phdr);
 out:
-	fclose(fp);
+	close(fd);
 	return ret;
 }
 
@@ -324,7 +323,7 @@ int dso__load_sym(struct dso *dso, struct map *map __maybe_unused,
 	if (ret >= 0)
 		RC_CHK_ACCESS(dso)->is_64_bit = ret;
 
-	if (filename__read_build_id(ss->name, &bid) > 0)
+	if (filename__read_build_id(ss->name, &bid, /*block=*/true) > 0)
 		dso__set_build_id(dso, &bid);
 	return 0;
 }
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index e816e42..3fed54d 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -1869,14 +1869,14 @@ int dso__load(struct dso *dso, struct map *map)
 
 	/*
 	 * Read the build id if possible. This is required for
-	 * DSO_BINARY_TYPE__BUILDID_DEBUGINFO to work
+	 * DSO_BINARY_TYPE__BUILDID_DEBUGINFO to work. Don't block in case path
+	 * isn't for a regular file.
 	 */
-	if (!dso__has_build_id(dso) &&
-	    is_regular_file(dso__long_name(dso))) {
+	if (!dso__has_build_id(dso)) {
 		struct build_id bid = { .size = 0, };
 
 		__symbol__join_symfs(name, PATH_MAX, dso__long_name(dso));
-		if (filename__read_build_id(name, &bid) > 0)
+		if (filename__read_build_id(name, &bid, /*block=*/false) > 0)
 			dso__set_build_id(dso, &bid);
 	}
 
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 3fb5d14..3471062 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -140,7 +140,7 @@ struct symbol *dso__next_symbol(struct symbol *sym);
 
 enum dso_type dso__type_fd(int fd);
 
-int filename__read_build_id(const char *filename, struct build_id *id);
+int filename__read_build_id(const char *filename, struct build_id *id, bool block);
 int sysfs__read_build_id(const char *filename, struct build_id *bid);
 int modules__parse(const char *filename, void *arg,
 		   int (*process_module)(void *arg, const char *name,
diff --git a/tools/perf/util/synthetic-events.c b/tools/perf/util/synthetic-events.c
index cb2c1ac..fcd1fd1 100644
--- a/tools/perf/util/synthetic-events.c
+++ b/tools/perf/util/synthetic-events.c
@@ -401,7 +401,7 @@ static void perf_record_mmap2__read_build_id(struct perf_record_mmap2 *event,
 	nsi = nsinfo__new(event->pid);
 	nsinfo__mountns_enter(nsi, &nc);
 
-	rc = filename__read_build_id(event->filename, &bid) > 0 ? 0 : -1;
+	rc = filename__read_build_id(event->filename, &bid, /*block=*/false) > 0 ? 0 : -1;
 
 	nsinfo__mountns_exit(&nc);
 	nsinfo__put(nsi);
diff --git a/tools/scripts/syscall.tbl b/tools/scripts/syscall.tbl
index 580b4e24..d1ae5e9 100644
--- a/tools/scripts/syscall.tbl
+++ b/tools/scripts/syscall.tbl
@@ -408,3 +408,5 @@
 465	common	listxattrat			sys_listxattrat
 466	common	removexattrat			sys_removexattrat
 467	common	open_tree_attr			sys_open_tree_attr
+468	common	file_getattr			sys_file_getattr
+469	common	file_setattr			sys_file_setattr
diff --git a/tools/testing/selftests/arm64/fp/fp-ptrace.c b/tools/testing/selftests/arm64/fp/fp-ptrace.c
index 124bc88..cdd7a45 100644
--- a/tools/testing/selftests/arm64/fp/fp-ptrace.c
+++ b/tools/testing/selftests/arm64/fp/fp-ptrace.c
@@ -1187,7 +1187,7 @@ static void sve_write_sve(pid_t child, struct test_config *config)
 	if (!vl)
 		return;
 
-	iov.iov_len = SVE_PT_SVE_OFFSET + SVE_PT_SVE_SIZE(vq, SVE_PT_REGS_SVE);
+	iov.iov_len = SVE_PT_SIZE(vq, SVE_PT_REGS_SVE);
 	iov.iov_base = malloc(iov.iov_len);
 	if (!iov.iov_base) {
 		ksft_print_msg("Failed allocating %lu byte SVE write buffer\n",
@@ -1234,8 +1234,7 @@ static void sve_write_fpsimd(pid_t child, struct test_config *config)
 	if (!vl)
 		return;
 
-	iov.iov_len = SVE_PT_SVE_OFFSET + SVE_PT_SVE_SIZE(vq,
-							  SVE_PT_REGS_FPSIMD);
+	iov.iov_len = SVE_PT_SIZE(vq, SVE_PT_REGS_FPSIMD);
 	iov.iov_base = malloc(iov.iov_len);
 	if (!iov.iov_base) {
 		ksft_print_msg("Failed allocating %lu byte SVE write buffer\n",
diff --git a/tools/testing/selftests/kselftest_harness.h b/tools/testing/selftests/kselftest_harness.h
index 2925e47..8516e84 100644
--- a/tools/testing/selftests/kselftest_harness.h
+++ b/tools/testing/selftests/kselftest_harness.h
@@ -751,7 +751,7 @@
 	for (; _metadata->trigger; _metadata->trigger = \
 			__bail(_assert, _metadata))
 
-#define is_signed_type(var)       (!!(((__typeof__(var))(-1)) < (__typeof__(var))1))
+#define is_signed_var(var)	(!!(((__typeof__(var))(-1)) < (__typeof__(var))1))
 
 #define __EXPECT(_expected, _expected_str, _seen, _seen_str, _t, _assert) do { \
 	/* Avoid multiple evaluation of the cases */ \
@@ -759,7 +759,7 @@
 	__typeof__(_seen) __seen = (_seen); \
 	if (!(__exp _t __seen)) { \
 		/* Report with actual signedness to avoid weird output. */ \
-		switch (is_signed_type(__exp) * 2 + is_signed_type(__seen)) { \
+		switch (is_signed_var(__exp) * 2 + is_signed_var(__seen)) { \
 		case 0: { \
 			uintmax_t __exp_print = (uintmax_t)__exp; \
 			uintmax_t __seen_print = (uintmax_t)__seen; \
diff --git a/tools/testing/selftests/kvm/Makefile.kvm b/tools/testing/selftests/kvm/Makefile.kvm
index f6fe7a0..41b40c6 100644
--- a/tools/testing/selftests/kvm/Makefile.kvm
+++ b/tools/testing/selftests/kvm/Makefile.kvm
@@ -169,6 +169,7 @@
 TEST_GEN_PROGS_arm64 += arm64/vgic_lpi_stress
 TEST_GEN_PROGS_arm64 += arm64/vpmu_counter_access
 TEST_GEN_PROGS_arm64 += arm64/no-vgic-v3
+TEST_GEN_PROGS_arm64 += arm64/kvm-uuid
 TEST_GEN_PROGS_arm64 += access_tracking_perf_test
 TEST_GEN_PROGS_arm64 += arch_timer
 TEST_GEN_PROGS_arm64 += coalesced_io_test
diff --git a/tools/testing/selftests/kvm/arm64/aarch32_id_regs.c b/tools/testing/selftests/kvm/arm64/aarch32_id_regs.c
index cef8f73..713005b 100644
--- a/tools/testing/selftests/kvm/arm64/aarch32_id_regs.c
+++ b/tools/testing/selftests/kvm/arm64/aarch32_id_regs.c
@@ -146,7 +146,7 @@ static bool vcpu_aarch64_only(struct kvm_vcpu *vcpu)
 
 	val = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64PFR0_EL1));
 
-	el0 = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_EL0), val);
+	el0 = FIELD_GET(ID_AA64PFR0_EL1_EL0, val);
 	return el0 == ID_AA64PFR0_EL1_EL0_IMP;
 }
 
diff --git a/tools/testing/selftests/kvm/arm64/debug-exceptions.c b/tools/testing/selftests/kvm/arm64/debug-exceptions.c
index e349639..1d431de 100644
--- a/tools/testing/selftests/kvm/arm64/debug-exceptions.c
+++ b/tools/testing/selftests/kvm/arm64/debug-exceptions.c
@@ -116,12 +116,12 @@ static void reset_debug_state(void)
 
 	/* Reset all bcr/bvr/wcr/wvr registers */
 	dfr0 = read_sysreg(id_aa64dfr0_el1);
-	brps = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_BRPs), dfr0);
+	brps = FIELD_GET(ID_AA64DFR0_EL1_BRPs, dfr0);
 	for (i = 0; i <= brps; i++) {
 		write_dbgbcr(i, 0);
 		write_dbgbvr(i, 0);
 	}
-	wrps = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_WRPs), dfr0);
+	wrps = FIELD_GET(ID_AA64DFR0_EL1_WRPs, dfr0);
 	for (i = 0; i <= wrps; i++) {
 		write_dbgwcr(i, 0);
 		write_dbgwvr(i, 0);
@@ -418,7 +418,7 @@ static void guest_code_ss(int test_cnt)
 
 static int debug_version(uint64_t id_aa64dfr0)
 {
-	return FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_DebugVer), id_aa64dfr0);
+	return FIELD_GET(ID_AA64DFR0_EL1_DebugVer, id_aa64dfr0);
 }
 
 static void test_guest_debug_exceptions(uint8_t bpn, uint8_t wpn, uint8_t ctx_bpn)
@@ -539,14 +539,14 @@ void test_guest_debug_exceptions_all(uint64_t aa64dfr0)
 	int b, w, c;
 
 	/* Number of breakpoints */
-	brp_num = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_BRPs), aa64dfr0) + 1;
+	brp_num = FIELD_GET(ID_AA64DFR0_EL1_BRPs, aa64dfr0) + 1;
 	__TEST_REQUIRE(brp_num >= 2, "At least two breakpoints are required");
 
 	/* Number of watchpoints */
-	wrp_num = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_WRPs), aa64dfr0) + 1;
+	wrp_num = FIELD_GET(ID_AA64DFR0_EL1_WRPs, aa64dfr0) + 1;
 
 	/* Number of context aware breakpoints */
-	ctx_brp_num = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_CTX_CMPs), aa64dfr0) + 1;
+	ctx_brp_num = FIELD_GET(ID_AA64DFR0_EL1_CTX_CMPs, aa64dfr0) + 1;
 
 	pr_debug("%s brp_num:%d, wrp_num:%d, ctx_brp_num:%d\n", __func__,
 		 brp_num, wrp_num, ctx_brp_num);
diff --git a/tools/testing/selftests/kvm/arm64/kvm-uuid.c b/tools/testing/selftests/kvm/arm64/kvm-uuid.c
new file mode 100644
index 0000000..af9581b
--- /dev/null
+++ b/tools/testing/selftests/kvm/arm64/kvm-uuid.c
@@ -0,0 +1,70 @@
+// SPDX-License-Identifier: GPL-2.0
+
+// Check that nobody has tampered with KVM's UID
+
+#include <errno.h>
+#include <linux/arm-smccc.h>
+#include <asm/kvm.h>
+#include <kvm_util.h>
+
+#include "processor.h"
+
+/*
+ * Do NOT redefine these constants, or try to replace them with some
+ * "common" version. They are hardcoded here to detect any potential
+ * breakage happening in the rest of the kernel.
+ *
+ * KVM UID value: 28b46fb6-2ec5-11e9-a9ca-4b564d003a74
+ */
+#define ARM_SMCCC_VENDOR_HYP_UID_KVM_REG_0	0xb66fb428U
+#define ARM_SMCCC_VENDOR_HYP_UID_KVM_REG_1	0xe911c52eU
+#define ARM_SMCCC_VENDOR_HYP_UID_KVM_REG_2	0x564bcaa9U
+#define ARM_SMCCC_VENDOR_HYP_UID_KVM_REG_3	0x743a004dU
+
+static void guest_code(void)
+{
+	struct arm_smccc_res res = {};
+
+	smccc_hvc(ARM_SMCCC_VENDOR_HYP_CALL_UID_FUNC_ID, 0, 0, 0, 0, 0, 0, 0, &res);
+
+	__GUEST_ASSERT(res.a0 == ARM_SMCCC_VENDOR_HYP_UID_KVM_REG_0 &&
+		       res.a1 == ARM_SMCCC_VENDOR_HYP_UID_KVM_REG_1 &&
+		       res.a2 == ARM_SMCCC_VENDOR_HYP_UID_KVM_REG_2 &&
+		       res.a3 == ARM_SMCCC_VENDOR_HYP_UID_KVM_REG_3,
+		       "Unexpected KVM-specific UID %lx %lx %lx %lx\n", res.a0, res.a1, res.a2, res.a3);
+	GUEST_DONE();
+}
+
+int main (int argc, char *argv[])
+{
+	struct kvm_vcpu *vcpu;
+	struct kvm_vm *vm;
+	struct ucall uc;
+	bool guest_done = false;
+
+	vm = vm_create_with_one_vcpu(&vcpu, guest_code);
+
+	while (!guest_done) {
+		vcpu_run(vcpu);
+
+		switch (get_ucall(vcpu, &uc)) {
+		case UCALL_SYNC:
+			break;
+		case UCALL_DONE:
+			guest_done = true;
+			break;
+		case UCALL_ABORT:
+			REPORT_GUEST_ASSERT(uc);
+			break;
+		case UCALL_PRINTF:
+			printf("%s", uc.buffer);
+			break;
+		default:
+			TEST_FAIL("Unexpected guest exit");
+		}
+	}
+
+	kvm_vm_free(vm);
+
+	return 0;
+}
diff --git a/tools/testing/selftests/kvm/arm64/no-vgic-v3.c b/tools/testing/selftests/kvm/arm64/no-vgic-v3.c
index ebd7043..f222538e 100644
--- a/tools/testing/selftests/kvm/arm64/no-vgic-v3.c
+++ b/tools/testing/selftests/kvm/arm64/no-vgic-v3.c
@@ -54,7 +54,7 @@ static void guest_code(void)
 	 * Check that we advertise that ID_AA64PFR0_EL1.GIC == 0, having
 	 * hidden the feature at runtime without any other userspace action.
 	 */
-	__GUEST_ASSERT(FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_GIC),
+	__GUEST_ASSERT(FIELD_GET(ID_AA64PFR0_EL1_GIC,
 				 read_sysreg(id_aa64pfr0_el1)) == 0,
 		       "GICv3 wrongly advertised");
 
@@ -165,7 +165,7 @@ int main(int argc, char *argv[])
 
 	vm = vm_create_with_one_vcpu(&vcpu, NULL);
 	pfr0 = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64PFR0_EL1));
-	__TEST_REQUIRE(FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_GIC), pfr0),
+	__TEST_REQUIRE(FIELD_GET(ID_AA64PFR0_EL1_GIC, pfr0),
 		       "GICv3 not supported.");
 	kvm_vm_free(vm);
 
diff --git a/tools/testing/selftests/kvm/arm64/page_fault_test.c b/tools/testing/selftests/kvm/arm64/page_fault_test.c
index dc6559d..4ccbd38 100644
--- a/tools/testing/selftests/kvm/arm64/page_fault_test.c
+++ b/tools/testing/selftests/kvm/arm64/page_fault_test.c
@@ -95,14 +95,14 @@ static bool guest_check_lse(void)
 	uint64_t isar0 = read_sysreg(id_aa64isar0_el1);
 	uint64_t atomic;
 
-	atomic = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64ISAR0_EL1_ATOMIC), isar0);
+	atomic = FIELD_GET(ID_AA64ISAR0_EL1_ATOMIC, isar0);
 	return atomic >= 2;
 }
 
 static bool guest_check_dc_zva(void)
 {
 	uint64_t dczid = read_sysreg(dczid_el0);
-	uint64_t dzp = FIELD_GET(ARM64_FEATURE_MASK(DCZID_EL0_DZP), dczid);
+	uint64_t dzp = FIELD_GET(DCZID_EL0_DZP, dczid);
 
 	return dzp == 0;
 }
@@ -195,7 +195,7 @@ static bool guest_set_ha(void)
 	uint64_t hadbs, tcr;
 
 	/* Skip if HA is not supported. */
-	hadbs = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64MMFR1_EL1_HAFDBS), mmfr1);
+	hadbs = FIELD_GET(ID_AA64MMFR1_EL1_HAFDBS, mmfr1);
 	if (hadbs == 0)
 		return false;
 
diff --git a/tools/testing/selftests/kvm/arm64/set_id_regs.c b/tools/testing/selftests/kvm/arm64/set_id_regs.c
index d3bf920..189321e 100644
--- a/tools/testing/selftests/kvm/arm64/set_id_regs.c
+++ b/tools/testing/selftests/kvm/arm64/set_id_regs.c
@@ -243,6 +243,7 @@ static void guest_code(void)
 	GUEST_REG_SYNC(SYS_ID_AA64MMFR0_EL1);
 	GUEST_REG_SYNC(SYS_ID_AA64MMFR1_EL1);
 	GUEST_REG_SYNC(SYS_ID_AA64MMFR2_EL1);
+	GUEST_REG_SYNC(SYS_ID_AA64MMFR3_EL1);
 	GUEST_REG_SYNC(SYS_ID_AA64ZFR0_EL1);
 	GUEST_REG_SYNC(SYS_CTR_EL0);
 	GUEST_REG_SYNC(SYS_MIDR_EL1);
@@ -594,8 +595,8 @@ static void test_user_set_mte_reg(struct kvm_vcpu *vcpu)
 	 */
 	val = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64PFR1_EL1));
 
-	mte = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_MTE), val);
-	mte_frac = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_MTE_frac), val);
+	mte = FIELD_GET(ID_AA64PFR1_EL1_MTE, val);
+	mte_frac = FIELD_GET(ID_AA64PFR1_EL1_MTE_frac, val);
 	if (mte != ID_AA64PFR1_EL1_MTE_MTE2 ||
 	    mte_frac != ID_AA64PFR1_EL1_MTE_frac_NI) {
 		ksft_test_result_skip("MTE_ASYNC or MTE_ASYMM are supported, nothing to test\n");
@@ -612,7 +613,7 @@ static void test_user_set_mte_reg(struct kvm_vcpu *vcpu)
 	}
 
 	val = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64PFR1_EL1));
-	mte_frac = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_MTE_frac), val);
+	mte_frac = FIELD_GET(ID_AA64PFR1_EL1_MTE_frac, val);
 	if (mte_frac == ID_AA64PFR1_EL1_MTE_frac_NI)
 		ksft_test_result_pass("ID_AA64PFR1_EL1.MTE_frac=0 accepted and still 0xF\n");
 	else
@@ -774,7 +775,7 @@ int main(void)
 
 	/* Check for AARCH64 only system */
 	val = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64PFR0_EL1));
-	el0 = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_EL0), val);
+	el0 = FIELD_GET(ID_AA64PFR0_EL1_EL0, val);
 	aarch64_only = (el0 == ID_AA64PFR0_EL1_EL0_IMP);
 
 	ksft_print_header();
diff --git a/tools/testing/selftests/kvm/arm64/vpmu_counter_access.c b/tools/testing/selftests/kvm/arm64/vpmu_counter_access.c
index f16b3b2..a0c4ab8 100644
--- a/tools/testing/selftests/kvm/arm64/vpmu_counter_access.c
+++ b/tools/testing/selftests/kvm/arm64/vpmu_counter_access.c
@@ -441,7 +441,7 @@ static void create_vpmu_vm(void *guest_code)
 
 	/* Make sure that PMUv3 support is indicated in the ID register */
 	dfr0 = vcpu_get_reg(vpmu_vm.vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64DFR0_EL1));
-	pmuver = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_PMUVer), dfr0);
+	pmuver = FIELD_GET(ID_AA64DFR0_EL1_PMUVer, dfr0);
 	TEST_ASSERT(pmuver != ID_AA64DFR0_EL1_PMUVer_IMP_DEF &&
 		    pmuver >= ID_AA64DFR0_EL1_PMUVer_IMP,
 		    "Unexpected PMUVER (0x%x) on the vCPU with PMUv3", pmuver);
diff --git a/tools/testing/selftests/kvm/lib/arm64/processor.c b/tools/testing/selftests/kvm/lib/arm64/processor.c
index 9d69904..eb11512 100644
--- a/tools/testing/selftests/kvm/lib/arm64/processor.c
+++ b/tools/testing/selftests/kvm/lib/arm64/processor.c
@@ -573,15 +573,15 @@ void aarch64_get_supported_page_sizes(uint32_t ipa, uint32_t *ipa4k,
 	err = ioctl(vcpu_fd, KVM_GET_ONE_REG, &reg);
 	TEST_ASSERT(err == 0, KVM_IOCTL_ERROR(KVM_GET_ONE_REG, vcpu_fd));
 
-	gran = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64MMFR0_EL1_TGRAN4), val);
+	gran = FIELD_GET(ID_AA64MMFR0_EL1_TGRAN4, val);
 	*ipa4k = max_ipa_for_page_size(ipa, gran, ID_AA64MMFR0_EL1_TGRAN4_NI,
 					ID_AA64MMFR0_EL1_TGRAN4_52_BIT);
 
-	gran = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64MMFR0_EL1_TGRAN64), val);
+	gran = FIELD_GET(ID_AA64MMFR0_EL1_TGRAN64, val);
 	*ipa64k = max_ipa_for_page_size(ipa, gran, ID_AA64MMFR0_EL1_TGRAN64_NI,
 					ID_AA64MMFR0_EL1_TGRAN64_IMP);
 
-	gran = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64MMFR0_EL1_TGRAN16), val);
+	gran = FIELD_GET(ID_AA64MMFR0_EL1_TGRAN16, val);
 	*ipa16k = max_ipa_for_page_size(ipa, gran, ID_AA64MMFR0_EL1_TGRAN16_NI,
 					ID_AA64MMFR0_EL1_TGRAN16_52_BIT);
 
diff --git a/tools/testing/selftests/ublk/file_backed.c b/tools/testing/selftests/ublk/file_backed.c
index 2d93ac8..cd9fe69 100644
--- a/tools/testing/selftests/ublk/file_backed.c
+++ b/tools/testing/selftests/ublk/file_backed.c
@@ -20,7 +20,7 @@ static int loop_queue_flush_io(struct ublk_thread *t, struct ublk_queue *q,
 	struct io_uring_sqe *sqe[1];
 
 	ublk_io_alloc_sqes(t, sqe, 1);
-	io_uring_prep_fsync(sqe[0], 1 /*fds[1]*/, IORING_FSYNC_DATASYNC);
+	io_uring_prep_fsync(sqe[0], ublk_get_registered_fd(q, 1) /*fds[1]*/, IORING_FSYNC_DATASYNC);
 	io_uring_sqe_set_flags(sqe[0], IOSQE_FIXED_FILE);
 	/* bit63 marks us as tgt io */
 	sqe[0]->user_data = build_user_data(tag, ublk_op, 0, q->q_id, 1);
@@ -42,7 +42,7 @@ static int loop_queue_tgt_rw_io(struct ublk_thread *t, struct ublk_queue *q,
 		if (!sqe[0])
 			return -ENOMEM;
 
-		io_uring_prep_rw(op, sqe[0], 1 /*fds[1]*/,
+		io_uring_prep_rw(op, sqe[0], ublk_get_registered_fd(q, 1) /*fds[1]*/,
 				addr,
 				iod->nr_sectors << 9,
 				iod->start_sector << 9);
@@ -56,19 +56,19 @@ static int loop_queue_tgt_rw_io(struct ublk_thread *t, struct ublk_queue *q,
 
 	ublk_io_alloc_sqes(t, sqe, 3);
 
-	io_uring_prep_buf_register(sqe[0], 0, tag, q->q_id, ublk_get_io(q, tag)->buf_index);
+	io_uring_prep_buf_register(sqe[0], q, tag, q->q_id, ublk_get_io(q, tag)->buf_index);
 	sqe[0]->flags |= IOSQE_CQE_SKIP_SUCCESS | IOSQE_IO_HARDLINK;
 	sqe[0]->user_data = build_user_data(tag,
 			ublk_cmd_op_nr(sqe[0]->cmd_op), 0, q->q_id, 1);
 
-	io_uring_prep_rw(op, sqe[1], 1 /*fds[1]*/, 0,
+	io_uring_prep_rw(op, sqe[1], ublk_get_registered_fd(q, 1) /*fds[1]*/, 0,
 		iod->nr_sectors << 9,
 		iod->start_sector << 9);
 	sqe[1]->buf_index = tag;
 	sqe[1]->flags |= IOSQE_FIXED_FILE | IOSQE_IO_HARDLINK;
 	sqe[1]->user_data = build_user_data(tag, ublk_op, 0, q->q_id, 1);
 
-	io_uring_prep_buf_unregister(sqe[2], 0, tag, q->q_id, ublk_get_io(q, tag)->buf_index);
+	io_uring_prep_buf_unregister(sqe[2], q, tag, q->q_id, ublk_get_io(q, tag)->buf_index);
 	sqe[2]->user_data = build_user_data(tag, ublk_cmd_op_nr(sqe[2]->cmd_op), 0, q->q_id, 1);
 
 	return 2;
diff --git a/tools/testing/selftests/ublk/kublk.c b/tools/testing/selftests/ublk/kublk.c
index 6512dfb..b71faba 100644
--- a/tools/testing/selftests/ublk/kublk.c
+++ b/tools/testing/selftests/ublk/kublk.c
@@ -432,7 +432,7 @@ static void ublk_thread_deinit(struct ublk_thread *t)
 	}
 }
 
-static int ublk_queue_init(struct ublk_queue *q, unsigned extra_flags)
+static int ublk_queue_init(struct ublk_queue *q, unsigned long long extra_flags)
 {
 	struct ublk_dev *dev = q->dev;
 	int depth = dev->dev_info.queue_depth;
@@ -446,6 +446,9 @@ static int ublk_queue_init(struct ublk_queue *q, unsigned extra_flags)
 	q->flags = dev->dev_info.flags;
 	q->flags |= extra_flags;
 
+	/* Cache fd in queue for fast path access */
+	q->ublk_fd = dev->fds[0];
+
 	cmd_buf_size = ublk_queue_cmd_buf_sz(q);
 	off = UBLKSRV_CMD_BUF_OFFSET + q->q_id * ublk_queue_max_cmd_buf_sz();
 	q->io_cmd_buf = mmap(0, cmd_buf_size, PROT_READ,
@@ -481,9 +484,10 @@ static int ublk_queue_init(struct ublk_queue *q, unsigned extra_flags)
 	return -ENOMEM;
 }
 
-static int ublk_thread_init(struct ublk_thread *t)
+static int ublk_thread_init(struct ublk_thread *t, unsigned long long extra_flags)
 {
 	struct ublk_dev *dev = t->dev;
+	unsigned long long flags = dev->dev_info.flags | extra_flags;
 	int ring_depth = dev->tgt.sq_depth, cq_depth = dev->tgt.cq_depth;
 	int ret;
 
@@ -512,7 +516,17 @@ static int ublk_thread_init(struct ublk_thread *t)
 
 	io_uring_register_ring_fd(&t->ring);
 
-	ret = io_uring_register_files(&t->ring, dev->fds, dev->nr_fds);
+	if (flags & UBLKS_Q_NO_UBLK_FIXED_FD) {
+		/* Register only backing files starting from index 1, exclude ublk control device */
+		if (dev->nr_fds > 1) {
+			ret = io_uring_register_files(&t->ring, &dev->fds[1], dev->nr_fds - 1);
+		} else {
+			/* No backing files to register, skip file registration */
+			ret = 0;
+		}
+	} else {
+		ret = io_uring_register_files(&t->ring, dev->fds, dev->nr_fds);
+	}
 	if (ret) {
 		ublk_err("ublk dev %d thread %d register files failed %d\n",
 				t->dev->dev_info.dev_id, t->idx, ret);
@@ -626,9 +640,12 @@ int ublk_queue_io_cmd(struct ublk_thread *t, struct ublk_io *io)
 
 	/* These fields should be written once, never change */
 	ublk_set_sqe_cmd_op(sqe[0], cmd_op);
-	sqe[0]->fd		= 0;	/* dev->fds[0] */
+	sqe[0]->fd	= ublk_get_registered_fd(q, 0);	/* dev->fds[0] */
 	sqe[0]->opcode	= IORING_OP_URING_CMD;
-	sqe[0]->flags	= IOSQE_FIXED_FILE;
+	if (q->flags & UBLKS_Q_NO_UBLK_FIXED_FD)
+		sqe[0]->flags	= 0;  /* Use raw FD, not fixed file */
+	else
+		sqe[0]->flags	= IOSQE_FIXED_FILE;
 	sqe[0]->rw_flags	= 0;
 	cmd->tag	= io->tag;
 	cmd->q_id	= q->q_id;
@@ -832,6 +849,7 @@ struct ublk_thread_info {
 	unsigned		idx;
 	sem_t 			*ready;
 	cpu_set_t 		*affinity;
+	unsigned long long	extra_flags;
 };
 
 static void *ublk_io_handler_fn(void *data)
@@ -844,7 +862,7 @@ static void *ublk_io_handler_fn(void *data)
 	t->dev = info->dev;
 	t->idx = info->idx;
 
-	ret = ublk_thread_init(t);
+	ret = ublk_thread_init(t, info->extra_flags);
 	if (ret) {
 		ublk_err("ublk dev %d thread %u init failed\n",
 				dev_id, t->idx);
@@ -934,6 +952,8 @@ static int ublk_start_daemon(const struct dev_ctx *ctx, struct ublk_dev *dev)
 
 	if (ctx->auto_zc_fallback)
 		extra_flags = UBLKS_Q_AUTO_BUF_REG_FALLBACK;
+	if (ctx->no_ublk_fixed_fd)
+		extra_flags |= UBLKS_Q_NO_UBLK_FIXED_FD;
 
 	for (i = 0; i < dinfo->nr_hw_queues; i++) {
 		dev->q[i].dev = dev;
@@ -951,6 +971,7 @@ static int ublk_start_daemon(const struct dev_ctx *ctx, struct ublk_dev *dev)
 		tinfo[i].dev = dev;
 		tinfo[i].idx = i;
 		tinfo[i].ready = &ready;
+		tinfo[i].extra_flags = extra_flags;
 
 		/*
 		 * If threads are not tied 1:1 to queues, setting thread
@@ -1471,7 +1492,7 @@ static void __cmd_create_help(char *exe, bool recovery)
 	printf("%s %s -t [null|loop|stripe|fault_inject] [-q nr_queues] [-d depth] [-n dev_id]\n",
 			exe, recovery ? "recover" : "add");
 	printf("\t[--foreground] [--quiet] [-z] [--auto_zc] [--auto_zc_fallback] [--debug_mask mask] [-r 0|1 ] [-g]\n");
-	printf("\t[-e 0|1 ] [-i 0|1]\n");
+	printf("\t[-e 0|1 ] [-i 0|1] [--no_ublk_fixed_fd]\n");
 	printf("\t[--nthreads threads] [--per_io_tasks]\n");
 	printf("\t[target options] [backfile1] [backfile2] ...\n");
 	printf("\tdefault: nr_queues=2(max 32), depth=128(max 1024), dev_id=-1(auto allocation)\n");
@@ -1534,6 +1555,7 @@ int main(int argc, char *argv[])
 		{ "size",		1,	NULL, 's'},
 		{ "nthreads",		1,	NULL,  0 },
 		{ "per_io_tasks",	0,	NULL,  0 },
+		{ "no_ublk_fixed_fd",	0,	NULL,  0 },
 		{ 0, 0, 0, 0 }
 	};
 	const struct ublk_tgt_ops *ops = NULL;
@@ -1613,6 +1635,8 @@ int main(int argc, char *argv[])
 				ctx.nthreads = strtol(optarg, NULL, 10);
 			if (!strcmp(longopts[option_idx].name, "per_io_tasks"))
 				ctx.per_io_tasks = 1;
+			if (!strcmp(longopts[option_idx].name, "no_ublk_fixed_fd"))
+				ctx.no_ublk_fixed_fd = 1;
 			break;
 		case '?':
 			/*
diff --git a/tools/testing/selftests/ublk/kublk.h b/tools/testing/selftests/ublk/kublk.h
index 219233f..5e55484 100644
--- a/tools/testing/selftests/ublk/kublk.h
+++ b/tools/testing/selftests/ublk/kublk.h
@@ -77,6 +77,7 @@ struct dev_ctx {
 	unsigned int	recovery:1;
 	unsigned int	auto_zc_fallback:1;
 	unsigned int	per_io_tasks:1;
+	unsigned int	no_ublk_fixed_fd:1;
 
 	int _evtfd;
 	int _shmid;
@@ -166,7 +167,9 @@ struct ublk_queue {
 
 /* borrow one bit of ublk uapi flags, which may never be used */
 #define UBLKS_Q_AUTO_BUF_REG_FALLBACK	(1ULL << 63)
+#define UBLKS_Q_NO_UBLK_FIXED_FD	(1ULL << 62)
 	__u64 flags;
+	int ublk_fd;	/* cached ublk char device fd */
 	struct ublk_io ios[UBLK_QUEUE_DEPTH];
 };
 
@@ -273,34 +276,48 @@ static inline int ublk_io_alloc_sqes(struct ublk_thread *t,
 	return nr_sqes;
 }
 
-static inline void io_uring_prep_buf_register(struct io_uring_sqe *sqe,
-		int dev_fd, int tag, int q_id, __u64 index)
+static inline int ublk_get_registered_fd(struct ublk_queue *q, int fd_index)
+{
+	if (q->flags & UBLKS_Q_NO_UBLK_FIXED_FD) {
+		if (fd_index == 0)
+			/* Return the raw ublk FD for index 0 */
+			return q->ublk_fd;
+		/* Adjust index for backing files (index 1 becomes 0, etc.) */
+		return fd_index - 1;
+	}
+	return fd_index;
+}
+
+static inline void __io_uring_prep_buf_reg_unreg(struct io_uring_sqe *sqe,
+		struct ublk_queue *q, int tag, int q_id, __u64 index)
 {
 	struct ublksrv_io_cmd *cmd = (struct ublksrv_io_cmd *)sqe->cmd;
+	int dev_fd = ublk_get_registered_fd(q, 0);
 
 	io_uring_prep_read(sqe, dev_fd, 0, 0, 0);
 	sqe->opcode		= IORING_OP_URING_CMD;
-	sqe->flags		|= IOSQE_FIXED_FILE;
-	sqe->cmd_op		= UBLK_U_IO_REGISTER_IO_BUF;
+	if (q->flags & UBLKS_Q_NO_UBLK_FIXED_FD)
+		sqe->flags	&= ~IOSQE_FIXED_FILE;
+	else
+		sqe->flags	|= IOSQE_FIXED_FILE;
 
 	cmd->tag		= tag;
 	cmd->addr		= index;
 	cmd->q_id		= q_id;
 }
 
-static inline void io_uring_prep_buf_unregister(struct io_uring_sqe *sqe,
-		int dev_fd, int tag, int q_id, __u64 index)
+static inline void io_uring_prep_buf_register(struct io_uring_sqe *sqe,
+		struct ublk_queue *q, int tag, int q_id, __u64 index)
 {
-	struct ublksrv_io_cmd *cmd = (struct ublksrv_io_cmd *)sqe->cmd;
+	__io_uring_prep_buf_reg_unreg(sqe, q, tag, q_id, index);
+	sqe->cmd_op		= UBLK_U_IO_REGISTER_IO_BUF;
+}
 
-	io_uring_prep_read(sqe, dev_fd, 0, 0, 0);
-	sqe->opcode		= IORING_OP_URING_CMD;
-	sqe->flags		|= IOSQE_FIXED_FILE;
+static inline void io_uring_prep_buf_unregister(struct io_uring_sqe *sqe,
+		struct ublk_queue *q, int tag, int q_id, __u64 index)
+{
+	__io_uring_prep_buf_reg_unreg(sqe, q, tag, q_id, index);
 	sqe->cmd_op		= UBLK_U_IO_UNREGISTER_IO_BUF;
-
-	cmd->tag		= tag;
-	cmd->addr		= index;
-	cmd->q_id		= q_id;
 }
 
 static inline void *ublk_get_sqe_cmd(const struct io_uring_sqe *sqe)
diff --git a/tools/testing/selftests/ublk/null.c b/tools/testing/selftests/ublk/null.c
index f0e0003..280043f 100644
--- a/tools/testing/selftests/ublk/null.c
+++ b/tools/testing/selftests/ublk/null.c
@@ -63,7 +63,7 @@ static int null_queue_zc_io(struct ublk_thread *t, struct ublk_queue *q,
 
 	ublk_io_alloc_sqes(t, sqe, 3);
 
-	io_uring_prep_buf_register(sqe[0], 0, tag, q->q_id, ublk_get_io(q, tag)->buf_index);
+	io_uring_prep_buf_register(sqe[0], q, tag, q->q_id, ublk_get_io(q, tag)->buf_index);
 	sqe[0]->user_data = build_user_data(tag,
 			ublk_cmd_op_nr(sqe[0]->cmd_op), 0, q->q_id, 1);
 	sqe[0]->flags |= IOSQE_CQE_SKIP_SUCCESS | IOSQE_IO_HARDLINK;
@@ -71,7 +71,7 @@ static int null_queue_zc_io(struct ublk_thread *t, struct ublk_queue *q,
 	__setup_nop_io(tag, iod, sqe[1], q->q_id);
 	sqe[1]->flags |= IOSQE_IO_HARDLINK;
 
-	io_uring_prep_buf_unregister(sqe[2], 0, tag, q->q_id, ublk_get_io(q, tag)->buf_index);
+	io_uring_prep_buf_unregister(sqe[2], q, tag, q->q_id, ublk_get_io(q, tag)->buf_index);
 	sqe[2]->user_data = build_user_data(tag, ublk_cmd_op_nr(sqe[2]->cmd_op), 0, q->q_id, 1);
 
 	// buf register is marked as IOSQE_CQE_SKIP_SUCCESS
diff --git a/tools/testing/selftests/ublk/stripe.c b/tools/testing/selftests/ublk/stripe.c
index 1fb9b7c..791fa8d 100644
--- a/tools/testing/selftests/ublk/stripe.c
+++ b/tools/testing/selftests/ublk/stripe.c
@@ -142,7 +142,7 @@ static int stripe_queue_tgt_rw_io(struct ublk_thread *t, struct ublk_queue *q,
 	ublk_io_alloc_sqes(t, sqe, s->nr + extra);
 
 	if (zc) {
-		io_uring_prep_buf_register(sqe[0], 0, tag, q->q_id, io->buf_index);
+		io_uring_prep_buf_register(sqe[0], q, tag, q->q_id, io->buf_index);
 		sqe[0]->flags |= IOSQE_CQE_SKIP_SUCCESS | IOSQE_IO_HARDLINK;
 		sqe[0]->user_data = build_user_data(tag,
 			ublk_cmd_op_nr(sqe[0]->cmd_op), 0, q->q_id, 1);
@@ -168,7 +168,7 @@ static int stripe_queue_tgt_rw_io(struct ublk_thread *t, struct ublk_queue *q,
 	if (zc) {
 		struct io_uring_sqe *unreg = sqe[s->nr + 1];
 
-		io_uring_prep_buf_unregister(unreg, 0, tag, q->q_id, io->buf_index);
+		io_uring_prep_buf_unregister(unreg, q, tag, q->q_id, io->buf_index);
 		unreg->user_data = build_user_data(
 			tag, ublk_cmd_op_nr(unreg->cmd_op), 0, q->q_id, 1);
 	}
diff --git a/tools/testing/selftests/ublk/test_stress_04.sh b/tools/testing/selftests/ublk/test_stress_04.sh
index 40d1437..3f901db 100755
--- a/tools/testing/selftests/ublk/test_stress_04.sh
+++ b/tools/testing/selftests/ublk/test_stress_04.sh
@@ -28,14 +28,14 @@
 _create_backfile 1 128M
 _create_backfile 2 128M
 
-ublk_io_and_kill_daemon 8G -t null -q 4 -z &
-ublk_io_and_kill_daemon 256M -t loop -q 4 -z "${UBLK_BACKFILES[0]}" &
+ublk_io_and_kill_daemon 8G -t null -q 4 -z --no_ublk_fixed_fd &
+ublk_io_and_kill_daemon 256M -t loop -q 4 -z --no_ublk_fixed_fd "${UBLK_BACKFILES[0]}" &
 ublk_io_and_kill_daemon 256M -t stripe -q 4 -z "${UBLK_BACKFILES[1]}" "${UBLK_BACKFILES[2]}" &
 
 if _have_feature "AUTO_BUF_REG"; then
 	ublk_io_and_kill_daemon 8G -t null -q 4 --auto_zc &
 	ublk_io_and_kill_daemon 256M -t loop -q 4 --auto_zc "${UBLK_BACKFILES[0]}" &
-	ublk_io_and_kill_daemon 256M -t stripe -q 4 --auto_zc "${UBLK_BACKFILES[1]}" "${UBLK_BACKFILES[2]}" &
+	ublk_io_and_kill_daemon 256M -t stripe -q 4 --auto_zc --no_ublk_fixed_fd "${UBLK_BACKFILES[1]}" "${UBLK_BACKFILES[2]}" &
 	ublk_io_and_kill_daemon 8G -t null -q 4 -z --auto_zc --auto_zc_fallback &
 fi