Merge 6.14-rc6 into char-misc-next

We need the fixes in here as well to build on top of.

Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

159 files changed, 2107 insertions, 1185 deletions

diff --git a/arch/alpha/include/asm/hwrpb.h b/arch/alpha/include/asm/hwrpb.h
index fc76f36265ad..db831cf8de10 100644
--- a/arch/alpha/include/asm/hwrpb.h
+++ b/arch/alpha/include/asm/hwrpb.h
@@ -135,7 +135,7 @@ struct crb_struct {
 	/* virtual->physical map */
 	unsigned long map_entries;
 	unsigned long map_pages;
-	struct vf_map_struct map[1];
+	struct vf_map_struct map[];
 };
 
 struct memclust_struct {
diff --git a/arch/alpha/include/uapi/asm/ptrace.h b/arch/alpha/include/uapi/asm/ptrace.h
index 5ca45934fcbb..72ed913a910f 100644
--- a/arch/alpha/include/uapi/asm/ptrace.h
+++ b/arch/alpha/include/uapi/asm/ptrace.h
@@ -42,6 +42,8 @@ struct pt_regs {
 	unsigned long trap_a0;
 	unsigned long trap_a1;
 	unsigned long trap_a2;
+/* This makes the stack 16-byte aligned as GCC expects */
+	unsigned long __pad0;
 /* These are saved by PAL-code: */
 	unsigned long ps;
 	unsigned long pc;
diff --git a/arch/alpha/kernel/asm-offsets.c b/arch/alpha/kernel/asm-offsets.c
index 4cfeae42c79a..e9dad60b147f 100644
--- a/arch/alpha/kernel/asm-offsets.c
+++ b/arch/alpha/kernel/asm-offsets.c
@@ -19,9 +19,13 @@ static void __used foo(void)
 	DEFINE(TI_STATUS, offsetof(struct thread_info, status));
 	BLANK();
 
+	DEFINE(SP_OFF, offsetof(struct pt_regs, ps));
 	DEFINE(SIZEOF_PT_REGS, sizeof(struct pt_regs));
 	BLANK();
 
+	DEFINE(SWITCH_STACK_SIZE, sizeof(struct switch_stack));
+	BLANK();
+
 	DEFINE(HAE_CACHE, offsetof(struct alpha_machine_vector, hae_cache));
 	DEFINE(HAE_REG, offsetof(struct alpha_machine_vector, hae_register));
 }
diff --git a/arch/alpha/kernel/entry.S b/arch/alpha/kernel/entry.S
index dd26062d75b3..f4d41b4538c2 100644
--- a/arch/alpha/kernel/entry.S
+++ b/arch/alpha/kernel/entry.S
@@ -15,10 +15,6 @@
 	.set noat
 	.cfi_sections	.debug_frame
 
-/* Stack offsets.  */
-#define SP_OFF			184
-#define SWITCH_STACK_SIZE	64
-
 .macro	CFI_START_OSF_FRAME	func
 	.align	4
 	.globl	\func
@@ -198,8 +194,8 @@ CFI_END_OSF_FRAME entArith
 CFI_START_OSF_FRAME entMM
 	SAVE_ALL
 /* save $9 - $15 so the inline exception code can manipulate them.  */
-	subq	$sp, 56, $sp
-	.cfi_adjust_cfa_offset	56
+	subq	$sp, 64, $sp
+	.cfi_adjust_cfa_offset	64
 	stq	$9, 0($sp)
 	stq	$10, 8($sp)
 	stq	$11, 16($sp)
@@ -214,7 +210,7 @@ CFI_START_OSF_FRAME entMM
 	.cfi_rel_offset	$13, 32
 	.cfi_rel_offset	$14, 40
 	.cfi_rel_offset	$15, 48
-	addq	$sp, 56, $19
+	addq	$sp, 64, $19
 /* handle the fault */
 	lda	$8, 0x3fff
 	bic	$sp, $8, $8
@@ -227,7 +223,7 @@ CFI_START_OSF_FRAME entMM
 	ldq	$13, 32($sp)
 	ldq	$14, 40($sp)
 	ldq	$15, 48($sp)
-	addq	$sp, 56, $sp
+	addq	$sp, 64, $sp
 	.cfi_restore	$9
 	.cfi_restore	$10
 	.cfi_restore	$11
@@ -235,7 +231,7 @@ CFI_START_OSF_FRAME entMM
 	.cfi_restore	$13
 	.cfi_restore	$14
 	.cfi_restore	$15
-	.cfi_adjust_cfa_offset	-56
+	.cfi_adjust_cfa_offset	-64
 /* finish up the syscall as normal.  */
 	br	ret_from_sys_call
 CFI_END_OSF_FRAME entMM
@@ -382,8 +378,8 @@ entUnaUser:
 	.cfi_restore	$0
 	.cfi_adjust_cfa_offset	-256
 	SAVE_ALL		/* setup normal kernel stack */
-	lda	$sp, -56($sp)
-	.cfi_adjust_cfa_offset	56
+	lda	$sp, -64($sp)
+	.cfi_adjust_cfa_offset	64
 	stq	$9, 0($sp)
 	stq	$10, 8($sp)
 	stq	$11, 16($sp)
@@ -399,7 +395,7 @@ entUnaUser:
 	.cfi_rel_offset	$14, 40
 	.cfi_rel_offset	$15, 48
 	lda	$8, 0x3fff
-	addq	$sp, 56, $19
+	addq	$sp, 64, $19
 	bic	$sp, $8, $8
 	jsr	$26, do_entUnaUser
 	ldq	$9, 0($sp)
@@ -409,7 +405,7 @@ entUnaUser:
 	ldq	$13, 32($sp)
 	ldq	$14, 40($sp)
 	ldq	$15, 48($sp)
-	lda	$sp, 56($sp)
+	lda	$sp, 64($sp)
 	.cfi_restore	$9
 	.cfi_restore	$10
 	.cfi_restore	$11
@@ -417,7 +413,7 @@ entUnaUser:
 	.cfi_restore	$13
 	.cfi_restore	$14
 	.cfi_restore	$15
-	.cfi_adjust_cfa_offset	-56
+	.cfi_adjust_cfa_offset	-64
 	br	ret_from_sys_call
 CFI_END_OSF_FRAME entUna
 
diff --git a/arch/alpha/kernel/pci_iommu.c b/arch/alpha/kernel/pci_iommu.c
index 681f56089d9c..dc91de50f906 100644
--- a/arch/alpha/kernel/pci_iommu.c
+++ b/arch/alpha/kernel/pci_iommu.c
@@ -13,6 +13,7 @@
 #include <linux/log2.h>
 #include <linux/dma-map-ops.h>
 #include <linux/iommu-helper.h>
+#include <linux/string_choices.h>
 
 #include <asm/io.h>
 #include <asm/hwrpb.h>
@@ -212,7 +213,7 @@ static int pci_dac_dma_supported(struct pci_dev *dev, u64 mask)
 
 	/* If both conditions above are met, we are fine. */
 	DBGA("pci_dac_dma_supported %s from %ps\n",
-	     ok ? "yes" : "no", __builtin_return_address(0));
+	     str_yes_no(ok), __builtin_return_address(0));
 
 	return ok;
 }
diff --git a/arch/alpha/kernel/traps.c b/arch/alpha/kernel/traps.c
index a9a38c80c4a7..7004397937cf 100644
--- a/arch/alpha/kernel/traps.c
+++ b/arch/alpha/kernel/traps.c
@@ -649,7 +649,7 @@ s_reg_to_mem (unsigned long s_reg)
 static int unauser_reg_offsets[32] = {
 	R(r0), R(r1), R(r2), R(r3), R(r4), R(r5), R(r6), R(r7), R(r8),
 	/* r9 ... r15 are stored in front of regs.  */
-	-56, -48, -40, -32, -24, -16, -8,
+	-64, -56, -48, -40, -32, -24, -16,	/* padding at -8 */
 	R(r16), R(r17), R(r18),
 	R(r19), R(r20), R(r21), R(r22), R(r23), R(r24), R(r25), R(r26),
 	R(r27), R(r28), R(gp),
diff --git a/arch/alpha/mm/fault.c b/arch/alpha/mm/fault.c
index 8c9850437e67..a9816bbc9f34 100644
--- a/arch/alpha/mm/fault.c
+++ b/arch/alpha/mm/fault.c
@@ -78,8 +78,8 @@ __load_new_mm_context(struct mm_struct *next_mm)
 
 /* Macro for exception fixup code to access integer registers.  */
 #define dpf_reg(r)							\
-	(((unsigned long *)regs)[(r) <= 8 ? (r) : (r) <= 15 ? (r)-16 :	\
-				 (r) <= 18 ? (r)+10 : (r)-10])
+	(((unsigned long *)regs)[(r) <= 8 ? (r) : (r) <= 15 ? (r)-17 :	\
+				 (r) <= 18 ? (r)+11 : (r)-10])
 
 asmlinkage void
 do_page_fault(unsigned long address, unsigned long mmcsr,
diff --git a/arch/arm/mm/fault-armv.c b/arch/arm/mm/fault-armv.c
index 2bec87c3327d..39fd5df73317 100644
--- a/arch/arm/mm/fault-armv.c
+++ b/arch/arm/mm/fault-armv.c
@@ -62,7 +62,7 @@ static int do_adjust_pte(struct vm_area_struct *vma, unsigned long address,
 }
 
 static int adjust_pte(struct vm_area_struct *vma, unsigned long address,
-		      unsigned long pfn, struct vm_fault *vmf)
+		      unsigned long pfn, bool need_lock)
 {
 	spinlock_t *ptl;
 	pgd_t *pgd;
@@ -99,12 +99,11 @@ again:
 	if (!pte)
 		return 0;
 
-	/*
-	 * If we are using split PTE locks, then we need to take the page
-	 * lock here.  Otherwise we are using shared mm->page_table_lock
-	 * which is already locked, thus cannot take it.
-	 */
-	if (ptl != vmf->ptl) {
+	if (need_lock) {
+		/*
+		 * Use nested version here to indicate that we are already
+		 * holding one similar spinlock.
+		 */
 		spin_lock_nested(ptl, SINGLE_DEPTH_NESTING);
 		if (unlikely(!pmd_same(pmdval, pmdp_get_lockless(pmd)))) {
 			pte_unmap_unlock(pte, ptl);
@@ -114,7 +113,7 @@ again:
 
 	ret = do_adjust_pte(vma, address, pfn, pte);
 
-	if (ptl != vmf->ptl)
+	if (need_lock)
 		spin_unlock(ptl);
 	pte_unmap(pte);
 
@@ -123,9 +122,10 @@ again:
 
 static void
 make_coherent(struct address_space *mapping, struct vm_area_struct *vma,
-	      unsigned long addr, pte_t *ptep, unsigned long pfn,
-	      struct vm_fault *vmf)
+	      unsigned long addr, pte_t *ptep, unsigned long pfn)
 {
+	const unsigned long pmd_start_addr = ALIGN_DOWN(addr, PMD_SIZE);
+	const unsigned long pmd_end_addr = pmd_start_addr + PMD_SIZE;
 	struct mm_struct *mm = vma->vm_mm;
 	struct vm_area_struct *mpnt;
 	unsigned long offset;
@@ -142,6 +142,14 @@ make_coherent(struct address_space *mapping, struct vm_area_struct *vma,
 	flush_dcache_mmap_lock(mapping);
 	vma_interval_tree_foreach(mpnt, &mapping->i_mmap, pgoff, pgoff) {
 		/*
+		 * If we are using split PTE locks, then we need to take the pte
+		 * lock. Otherwise we are using shared mm->page_table_lock which
+		 * is already locked, thus cannot take it.
+		 */
+		bool need_lock = IS_ENABLED(CONFIG_SPLIT_PTE_PTLOCKS);
+		unsigned long mpnt_addr;
+
+		/*
 		 * If this VMA is not in our MM, we can ignore it.
 		 * Note that we intentionally mask out the VMA
 		 * that we are fixing up.
@@ -151,7 +159,12 @@ make_coherent(struct address_space *mapping, struct vm_area_struct *vma,
 		if (!(mpnt->vm_flags & VM_MAYSHARE))
 			continue;
 		offset = (pgoff - mpnt->vm_pgoff) << PAGE_SHIFT;
-		aliases += adjust_pte(mpnt, mpnt->vm_start + offset, pfn, vmf);
+		mpnt_addr = mpnt->vm_start + offset;
+
+		/* Avoid deadlocks by not grabbing the same PTE lock again. */
+		if (mpnt_addr >= pmd_start_addr && mpnt_addr < pmd_end_addr)
+			need_lock = false;
+		aliases += adjust_pte(mpnt, mpnt_addr, pfn, need_lock);
 	}
 	flush_dcache_mmap_unlock(mapping);
 	if (aliases)
@@ -194,7 +207,7 @@ void update_mmu_cache_range(struct vm_fault *vmf, struct vm_area_struct *vma,
 		__flush_dcache_folio(mapping, folio);
 	if (mapping) {
 		if (cache_is_vivt())
-			make_coherent(mapping, vma, addr, ptep, pfn, vmf);
+			make_coherent(mapping, vma, addr, ptep, pfn);
 		else if (vma->vm_flags & VM_EXEC)
 			__flush_icache_all();
 	}
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index fcdd0ed3eca8..940343beb3d4 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -225,7 +225,6 @@ config ARM64
 	select HAVE_FUNCTION_ERROR_INJECTION
 	select HAVE_FUNCTION_GRAPH_FREGS
 	select HAVE_FUNCTION_GRAPH_TRACER
-	select HAVE_FUNCTION_GRAPH_RETVAL
 	select HAVE_GCC_PLUGINS
 	select HAVE_HARDLOCKUP_DETECTOR_PERF if PERF_EVENTS && \
 		HW_PERF_EVENTS && HAVE_PERF_EVENTS_NMI
diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile
index 358c68565bfd..2b25d671365f 100644
--- a/arch/arm64/Makefile
+++ b/arch/arm64/Makefile
@@ -48,7 +48,11 @@ KBUILD_CFLAGS	+= $(CC_FLAGS_NO_FPU) \
 KBUILD_CFLAGS	+= $(call cc-disable-warning, psabi)
 KBUILD_AFLAGS	+= $(compat_vdso)
 
+ifeq ($(call test-ge, $(CONFIG_RUSTC_VERSION), 108500),y)
+KBUILD_RUSTFLAGS += --target=aarch64-unknown-none-softfloat
+else
 KBUILD_RUSTFLAGS += --target=aarch64-unknown-none -Ctarget-feature="-neon"
+endif
 
 KBUILD_CFLAGS	+= $(call cc-option,-mabi=lp64)
 KBUILD_AFLAGS	+= $(call cc-option,-mabi=lp64)
diff --git a/arch/arm64/boot/dts/rockchip/px30-ringneck-haikou.dts b/arch/arm64/boot/dts/rockchip/px30-ringneck-haikou.dts
index e4517f47d519..eb9470a00e54 100644
--- a/arch/arm64/boot/dts/rockchip/px30-ringneck-haikou.dts
+++ b/arch/arm64/boot/dts/rockchip/px30-ringneck-haikou.dts
@@ -226,7 +226,6 @@
 };
 
 &uart5 {
-	pinctrl-0 = <&uart5_xfer>;
 	rts-gpios = <&gpio0 RK_PB5 GPIO_ACTIVE_HIGH>;
 	status = "okay";
 };
diff --git a/arch/arm64/boot/dts/rockchip/px30-ringneck.dtsi b/arch/arm64/boot/dts/rockchip/px30-ringneck.dtsi
index ae050cc6cd05..e80412abec08 100644
--- a/arch/arm64/boot/dts/rockchip/px30-ringneck.dtsi
+++ b/arch/arm64/boot/dts/rockchip/px30-ringneck.dtsi
@@ -396,6 +396,12 @@
 	status = "okay";
 };
 
+&uart5 {
+	/delete-property/ dmas;
+	/delete-property/ dma-names;
+	pinctrl-0 = <&uart5_xfer>;
+};
+
 /* Mule UCAN */
 &usb_host0_ehci {
 	status = "okay";
diff --git a/arch/arm64/boot/dts/rockchip/rk3328-orangepi-r1-plus-lts.dts b/arch/arm64/boot/dts/rockchip/rk3328-orangepi-r1-plus-lts.dts
index 67c246ad8b8c..ec2ce894da1f 100644
--- a/arch/arm64/boot/dts/rockchip/rk3328-orangepi-r1-plus-lts.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3328-orangepi-r1-plus-lts.dts
@@ -17,8 +17,7 @@
 
 &gmac2io {
 	phy-handle = <&yt8531c>;
-	tx_delay = <0x19>;
-	rx_delay = <0x05>;
+	phy-mode = "rgmii-id";
 	status = "okay";
 
 	mdio {
diff --git a/arch/arm64/boot/dts/rockchip/rk3328-orangepi-r1-plus.dts b/arch/arm64/boot/dts/rockchip/rk3328-orangepi-r1-plus.dts
index 324a8e951f7e..846b931e16d2 100644
--- a/arch/arm64/boot/dts/rockchip/rk3328-orangepi-r1-plus.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3328-orangepi-r1-plus.dts
@@ -15,6 +15,7 @@
 
 &gmac2io {
 	phy-handle = <&rtl8211e>;
+	phy-mode = "rgmii";
 	tx_delay = <0x24>;
 	rx_delay = <0x18>;
 	status = "okay";
diff --git a/arch/arm64/boot/dts/rockchip/rk3328-orangepi-r1-plus.dtsi b/arch/arm64/boot/dts/rockchip/rk3328-orangepi-r1-plus.dtsi
index 4f193704e5dc..09508e324a28 100644
--- a/arch/arm64/boot/dts/rockchip/rk3328-orangepi-r1-plus.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3328-orangepi-r1-plus.dtsi
@@ -109,7 +109,6 @@
 	assigned-clocks = <&cru SCLK_MAC2IO>, <&cru SCLK_MAC2IO_EXT>;
 	assigned-clock-parents = <&gmac_clk>, <&gmac_clk>;
 	clock_in_out = "input";
-	phy-mode = "rgmii";
 	phy-supply = <&vcc_io>;
 	pinctrl-0 = <&rgmiim1_pins>;
 	pinctrl-names = "default";
diff --git a/arch/arm64/boot/dts/rockchip/rk3399-gru-chromebook.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-gru-chromebook.dtsi
index 988e6ca32fac..a9ea4b0daa04 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-gru-chromebook.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3399-gru-chromebook.dtsi
@@ -22,11 +22,11 @@
 	};
 
 	/* EC turns on w/ pp900_usb_en */
-	pp900_usb: pp900-ap {
+	pp900_usb: regulator-pp900-ap {
 	};
 
 	/* EC turns on w/ pp900_pcie_en */
-	pp900_pcie: pp900-ap {
+	pp900_pcie: regulator-pp900-ap {
 	};
 
 	pp3000: regulator-pp3000 {
@@ -126,7 +126,7 @@
 	};
 
 	/* Always on; plain and simple */
-	pp3000_ap: pp3000_emmc: pp3000 {
+	pp3000_ap: pp3000_emmc: regulator-pp3000 {
 	};
 
 	pp1500_ap_io: regulator-pp1500-ap-io {
@@ -160,7 +160,7 @@
 	};
 
 	/* EC turns on w/ pp3300_usb_en_l */
-	pp3300_usb: pp3300 {
+	pp3300_usb: regulator-pp3300 {
 	};
 
 	/* gpio is shared with pp1800_pcie and pinctrl is set there */
diff --git a/arch/arm64/boot/dts/rockchip/rk3399-gru-scarlet.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-gru-scarlet.dtsi
index 19b23b438965..5e068377a0a2 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-gru-scarlet.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3399-gru-scarlet.dtsi
@@ -92,7 +92,7 @@
 	};
 
 	/* EC turns on pp1800_s3_en */
-	pp1800_s3: pp1800 {
+	pp1800_s3: regulator-pp1800 {
 	};
 
 	/* pp3300 children, sorted by name */
@@ -109,11 +109,11 @@
 	};
 
 	/* EC turns on pp3300_s0_en */
-	pp3300_s0: pp3300 {
+	pp3300_s0: regulator-pp3300 {
 	};
 
 	/* EC turns on pp3300_s3_en */
-	pp3300_s3: pp3300 {
+	pp3300_s3: regulator-pp3300 {
 	};
 
 	/*
diff --git a/arch/arm64/boot/dts/rockchip/rk3399-gru.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-gru.dtsi
index 6d9e60b01225..7eca1da78cff 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-gru.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3399-gru.dtsi
@@ -189,39 +189,39 @@
 	};
 
 	/* EC turns on w/ pp900_ddrpll_en */
-	pp900_ddrpll: pp900-ap {
+	pp900_ddrpll: regulator-pp900-ap {
 	};
 
 	/* EC turns on w/ pp900_pll_en */
-	pp900_pll: pp900-ap {
+	pp900_pll: regulator-pp900-ap {
 	};
 
 	/* EC turns on w/ pp900_pmu_en */
-	pp900_pmu: pp900-ap {
+	pp900_pmu: regulator-pp900-ap {
 	};
 
 	/* EC turns on w/ pp1800_s0_en_l */
-	pp1800_ap_io: pp1800_emmc: pp1800_nfc: pp1800_s0: pp1800 {
+	pp1800_ap_io: pp1800_emmc: pp1800_nfc: pp1800_s0: regulator-pp1800 {
 	};
 
 	/* EC turns on w/ pp1800_avdd_en_l */
-	pp1800_avdd: pp1800 {
+	pp1800_avdd: regulator-pp1800 {
 	};
 
 	/* EC turns on w/ pp1800_lid_en_l */
-	pp1800_lid: pp1800_mic: pp1800 {
+	pp1800_lid: pp1800_mic: regulator-pp1800 {
 	};
 
 	/* EC turns on w/ lpddr_pwr_en */
-	pp1800_lpddr: pp1800 {
+	pp1800_lpddr: regulator-pp1800 {
 	};
 
 	/* EC turns on w/ pp1800_pmu_en_l */
-	pp1800_pmu: pp1800 {
+	pp1800_pmu: regulator-pp1800 {
 	};
 
 	/* EC turns on w/ pp1800_usb_en_l */
-	pp1800_usb: pp1800 {
+	pp1800_usb: regulator-pp1800 {
 	};
 
 	pp3000_sd_slot: regulator-pp3000-sd-slot {
@@ -259,11 +259,11 @@
 	};
 
 	/* EC turns on w/ pp3300_trackpad_en_l */
-	pp3300_trackpad: pp3300-trackpad {
+	pp3300_trackpad: regulator-pp3300-trackpad {
 	};
 
 	/* EC turns on w/ usb_a_en */
-	pp5000_usb_a_vbus: pp5000 {
+	pp5000_usb_a_vbus: regulator-pp5000 {
 	};
 
 	ap_rtc_clk: ap-rtc-clk {
diff --git a/arch/arm64/boot/dts/rockchip/rk3588-base.dtsi b/arch/arm64/boot/dts/rockchip/rk3588-base.dtsi
index 8cfa30837ce7..c3abdfb04f8f 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588-base.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3588-base.dtsi
@@ -549,10 +549,10 @@
 	mmu600_pcie: iommu@fc900000 {
 		compatible = "arm,smmu-v3";
 		reg = <0x0 0xfc900000 0x0 0x200000>;
-		interrupts = <GIC_SPI 369 IRQ_TYPE_LEVEL_HIGH 0>,
-			     <GIC_SPI 371 IRQ_TYPE_LEVEL_HIGH 0>,
-			     <GIC_SPI 374 IRQ_TYPE_LEVEL_HIGH 0>,
-			     <GIC_SPI 367 IRQ_TYPE_LEVEL_HIGH 0>;
+		interrupts = <GIC_SPI 369 IRQ_TYPE_EDGE_RISING 0>,
+			     <GIC_SPI 371 IRQ_TYPE_EDGE_RISING 0>,
+			     <GIC_SPI 374 IRQ_TYPE_EDGE_RISING 0>,
+			     <GIC_SPI 367 IRQ_TYPE_EDGE_RISING 0>;
 		interrupt-names = "eventq", "gerror", "priq", "cmdq-sync";
 		#iommu-cells = <1>;
 	};
@@ -560,10 +560,10 @@
 	mmu600_php: iommu@fcb00000 {
 		compatible = "arm,smmu-v3";
 		reg = <0x0 0xfcb00000 0x0 0x200000>;
-		interrupts = <GIC_SPI 381 IRQ_TYPE_LEVEL_HIGH 0>,
-			     <GIC_SPI 383 IRQ_TYPE_LEVEL_HIGH 0>,
-			     <GIC_SPI 386 IRQ_TYPE_LEVEL_HIGH 0>,
-			     <GIC_SPI 379 IRQ_TYPE_LEVEL_HIGH 0>;
+		interrupts = <GIC_SPI 381 IRQ_TYPE_EDGE_RISING 0>,
+			     <GIC_SPI 383 IRQ_TYPE_EDGE_RISING 0>,
+			     <GIC_SPI 386 IRQ_TYPE_EDGE_RISING 0>,
+			     <GIC_SPI 379 IRQ_TYPE_EDGE_RISING 0>;
 		interrupt-names = "eventq", "gerror", "priq", "cmdq-sync";
 		#iommu-cells = <1>;
 		status = "disabled";
@@ -2668,9 +2668,9 @@
 		rockchip,hw-tshut-temp = <120000>;
 		rockchip,hw-tshut-mode = <0>; /* tshut mode 0:CRU 1:GPIO */
 		rockchip,hw-tshut-polarity = <0>; /* tshut polarity 0:LOW 1:HIGH */
-		pinctrl-0 = <&tsadc_gpio_func>;
-		pinctrl-1 = <&tsadc_shut>;
-		pinctrl-names = "gpio", "otpout";
+		pinctrl-0 = <&tsadc_shut_org>;
+		pinctrl-1 = <&tsadc_gpio_func>;
+		pinctrl-names = "default", "sleep";
 		#thermal-sensor-cells = <1>;
 		status = "disabled";
 	};
diff --git a/arch/arm64/boot/dts/rockchip/rk3588-coolpi-cm5-genbook.dts b/arch/arm64/boot/dts/rockchip/rk3588-coolpi-cm5-genbook.dts
index 92f0ed83c990..bc6b43a77153 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588-coolpi-cm5-genbook.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3588-coolpi-cm5-genbook.dts
@@ -113,7 +113,7 @@
 		compatible = "regulator-fixed";
 		regulator-name = "vcc3v3_lcd";
 		enable-active-high;
-		gpio = <&gpio1 RK_PC4 GPIO_ACTIVE_HIGH>;
+		gpio = <&gpio0 RK_PC4 GPIO_ACTIVE_HIGH>;
 		pinctrl-names = "default";
 		pinctrl-0 = <&lcdpwr_en>;
 		vin-supply = <&vcc3v3_sys>;
@@ -241,7 +241,7 @@
 &pinctrl {
 	lcd {
 		lcdpwr_en: lcdpwr-en {
-			rockchip,pins = <1 RK_PC4 RK_FUNC_GPIO &pcfg_pull_down>;
+			rockchip,pins = <0 RK_PC4 RK_FUNC_GPIO &pcfg_pull_down>;
 		};
 
 		bl_en: bl-en {
diff --git a/arch/arm64/boot/dts/rockchip/rk3588-extra.dtsi b/arch/arm64/boot/dts/rockchip/rk3588-extra.dtsi
index 4a950907ea6f..840b638af1c2 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588-extra.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3588-extra.dtsi
@@ -213,7 +213,6 @@
 		interrupt-names = "sys", "pmc", "msg", "legacy", "err",
 				  "dma0", "dma1", "dma2", "dma3";
 		max-link-speed = <3>;
-		iommus = <&mmu600_pcie 0x0000>;
 		num-lanes = <4>;
 		phys = <&pcie30phy>;
 		phy-names = "pcie-phy";
diff --git a/arch/arm64/boot/dts/rockchip/rk3588-rock-5b-pcie-ep.dtso b/arch/arm64/boot/dts/rockchip/rk3588-rock-5b-pcie-ep.dtso
index 672d748fcc67..f229cb49da68 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588-rock-5b-pcie-ep.dtso
+++ b/arch/arm64/boot/dts/rockchip/rk3588-rock-5b-pcie-ep.dtso
@@ -23,3 +23,7 @@
 	vpcie3v3-supply = <&vcc3v3_pcie30>;
 	status = "okay";
 };
+
+&mmu600_pcie {
+	status = "disabled";
+};
diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig
index cb7da4415599..1f25423de383 100644
--- a/arch/arm64/configs/defconfig
+++ b/arch/arm64/configs/defconfig
@@ -1551,6 +1551,8 @@ CONFIG_PWM_VISCONTI=m
 CONFIG_SL28CPLD_INTC=y
 CONFIG_QCOM_PDC=y
 CONFIG_QCOM_MPM=y
+CONFIG_TI_SCI_INTR_IRQCHIP=y
+CONFIG_TI_SCI_INTA_IRQCHIP=y
 CONFIG_RESET_GPIO=m
 CONFIG_RESET_IMX7=y
 CONFIG_RESET_QCOM_AOSS=y
diff --git a/arch/arm64/include/asm/el2_setup.h b/arch/arm64/include/asm/el2_setup.h
index 25e162651750..555c613fd232 100644
--- a/arch/arm64/include/asm/el2_setup.h
+++ b/arch/arm64/include/asm/el2_setup.h
@@ -16,6 +16,32 @@
 #include <asm/sysreg.h>
 #include <linux/irqchip/arm-gic-v3.h>
 
+.macro init_el2_hcr	val
+	mov_q	x0, \val
+
+	/*
+	 * Compliant CPUs advertise their VHE-onlyness with
+	 * ID_AA64MMFR4_EL1.E2H0 < 0. On such CPUs HCR_EL2.E2H is RES1, but it
+	 * can reset into an UNKNOWN state and might not read as 1 until it has
+	 * been initialized explicitly.
+	 *
+	 * Fruity CPUs seem to have HCR_EL2.E2H set to RAO/WI, but
+	 * don't advertise it (they predate this relaxation).
+	 *
+	 * Initalize HCR_EL2.E2H so that later code can rely upon HCR_EL2.E2H
+	 * indicating whether the CPU is running in E2H mode.
+	 */
+	mrs_s	x1, SYS_ID_AA64MMFR4_EL1
+	sbfx	x1, x1, #ID_AA64MMFR4_EL1_E2H0_SHIFT, #ID_AA64MMFR4_EL1_E2H0_WIDTH
+	cmp	x1, #0
+	b.ge	.LnVHE_\@
+
+	orr	x0, x0, #HCR_E2H
+.LnVHE_\@:
+	msr	hcr_el2, x0
+	isb
+.endm
+
 .macro __init_el2_sctlr
 	mov_q	x0, INIT_SCTLR_EL2_MMU_OFF
 	msr	sctlr_el2, x0
@@ -244,11 +270,6 @@
 .Lskip_gcs_\@:
 .endm
 
-.macro __init_el2_nvhe_prepare_eret
-	mov	x0, #INIT_PSTATE_EL1
-	msr	spsr_el2, x0
-.endm
-
 .macro __init_el2_mpam
 	/* Memory Partitioning And Monitoring: disable EL2 traps */
 	mrs	x1, id_aa64pfr0_el1
diff --git a/arch/arm64/include/asm/hugetlb.h b/arch/arm64/include/asm/hugetlb.h
index c6dff3e69539..07fbf5bf85a7 100644
--- a/arch/arm64/include/asm/hugetlb.h
+++ b/arch/arm64/include/asm/hugetlb.h
@@ -42,8 +42,8 @@ extern int huge_ptep_set_access_flags(struct vm_area_struct *vma,
 				      unsigned long addr, pte_t *ptep,
 				      pte_t pte, int dirty);
 #define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR
-extern pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
-				     unsigned long addr, pte_t *ptep);
+extern pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
+				     pte_t *ptep, unsigned long sz);
 #define __HAVE_ARCH_HUGE_PTEP_SET_WRPROTECT
 extern void huge_ptep_set_wrprotect(struct mm_struct *mm,
 				    unsigned long addr, pte_t *ptep);
@@ -76,12 +76,22 @@ static inline void flush_hugetlb_tlb_range(struct vm_area_struct *vma,
 {
 	unsigned long stride = huge_page_size(hstate_vma(vma));
 
-	if (stride == PMD_SIZE)
-		__flush_tlb_range(vma, start, end, stride, false, 2);
-	else if (stride == PUD_SIZE)
-		__flush_tlb_range(vma, start, end, stride, false, 1);
-	else
-		__flush_tlb_range(vma, start, end, PAGE_SIZE, false, 0);
+	switch (stride) {
+#ifndef __PAGETABLE_PMD_FOLDED
+	case PUD_SIZE:
+		__flush_tlb_range(vma, start, end, PUD_SIZE, false, 1);
+		break;
+#endif
+	case CONT_PMD_SIZE:
+	case PMD_SIZE:
+		__flush_tlb_range(vma, start, end, PMD_SIZE, false, 2);
+		break;
+	case CONT_PTE_SIZE:
+		__flush_tlb_range(vma, start, end, PAGE_SIZE, false, 3);
+		break;
+	default:
+		__flush_tlb_range(vma, start, end, PAGE_SIZE, false, TLBI_TTL_UNKNOWN);
+	}
 }
 
 #endif /* __ASM_HUGETLB_H */
diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index 8d94a6c0ed5c..c2417a424b98 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -119,7 +119,7 @@
 #define TCR_EL2_IRGN0_MASK	TCR_IRGN0_MASK
 #define TCR_EL2_T0SZ_MASK	0x3f
 #define TCR_EL2_MASK	(TCR_EL2_TG0_MASK | TCR_EL2_SH0_MASK | \
-			 TCR_EL2_ORGN0_MASK | TCR_EL2_IRGN0_MASK | TCR_EL2_T0SZ_MASK)
+			 TCR_EL2_ORGN0_MASK | TCR_EL2_IRGN0_MASK)
 
 /* VTCR_EL2 Registers bits */
 #define VTCR_EL2_DS		TCR_EL2_DS
diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index 47f2cf408eed..78ec1ef2cfe8 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -605,48 +605,6 @@ static __always_inline void kvm_incr_pc(struct kvm_vcpu *vcpu)
 					 __cpacr_to_cptr_set(clr, set));\
 	} while (0)
 
-static __always_inline void kvm_write_cptr_el2(u64 val)
-{
-	if (has_vhe() || has_hvhe())
-		write_sysreg(val, cpacr_el1);
-	else
-		write_sysreg(val, cptr_el2);
-}
-
-/* Resets the value of cptr_el2 when returning to the host. */
-static __always_inline void __kvm_reset_cptr_el2(struct kvm *kvm)
-{
-	u64 val;
-
-	if (has_vhe()) {
-		val = (CPACR_EL1_FPEN | CPACR_EL1_ZEN_EL1EN);
-		if (cpus_have_final_cap(ARM64_SME))
-			val |= CPACR_EL1_SMEN_EL1EN;
-	} else if (has_hvhe()) {
-		val = CPACR_EL1_FPEN;
-
-		if (!kvm_has_sve(kvm) || !guest_owns_fp_regs())
-			val |= CPACR_EL1_ZEN;
-		if (cpus_have_final_cap(ARM64_SME))
-			val |= CPACR_EL1_SMEN;
-	} else {
-		val = CPTR_NVHE_EL2_RES1;
-
-		if (kvm_has_sve(kvm) && guest_owns_fp_regs())
-			val |= CPTR_EL2_TZ;
-		if (!cpus_have_final_cap(ARM64_SME))
-			val |= CPTR_EL2_TSM;
-	}
-
-	kvm_write_cptr_el2(val);
-}
-
-#ifdef __KVM_NVHE_HYPERVISOR__
-#define kvm_reset_cptr_el2(v)	__kvm_reset_cptr_el2(kern_hyp_va((v)->kvm))
-#else
-#define kvm_reset_cptr_el2(v)	__kvm_reset_cptr_el2((v)->kvm)
-#endif
-
 /*
  * Returns a 'sanitised' view of CPTR_EL2, translating from nVHE to the VHE
  * format if E2H isn't set.
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 7cfa024de4e3..d919557af5e5 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -100,7 +100,7 @@ static inline void push_hyp_memcache(struct kvm_hyp_memcache *mc,
 static inline void *pop_hyp_memcache(struct kvm_hyp_memcache *mc,
 				     void *(*to_va)(phys_addr_t phys))
 {
-	phys_addr_t *p = to_va(mc->head);
+	phys_addr_t *p = to_va(mc->head & PAGE_MASK);
 
 	if (!mc->nr_pages)
 		return NULL;
@@ -615,8 +615,6 @@ struct cpu_sve_state {
 struct kvm_host_data {
 #define KVM_HOST_DATA_FLAG_HAS_SPE			0
 #define KVM_HOST_DATA_FLAG_HAS_TRBE			1
-#define KVM_HOST_DATA_FLAG_HOST_SVE_ENABLED		2
-#define KVM_HOST_DATA_FLAG_HOST_SME_ENABLED		3
 #define KVM_HOST_DATA_FLAG_TRBE_ENABLED			4
 #define KVM_HOST_DATA_FLAG_EL1_TRACING_CONFIGURED	5
 	unsigned long flags;
@@ -624,23 +622,13 @@ struct kvm_host_data {
 	struct kvm_cpu_context host_ctxt;
 
 	/*
-	 * All pointers in this union are hyp VA.
+	 * Hyp VA.
 	 * sve_state is only used in pKVM and if system_supports_sve().
 	 */
-	union {
-		struct user_fpsimd_state *fpsimd_state;
-		struct cpu_sve_state *sve_state;
-	};
-
-	union {
-		/* HYP VA pointer to the host storage for FPMR */
-		u64	*fpmr_ptr;
-		/*
-		 * Used by pKVM only, as it needs to provide storage
-		 * for the host
-		 */
-		u64	fpmr;
-	};
+	struct cpu_sve_state *sve_state;
+
+	/* Used by pKVM only. */
+	u64	fpmr;
 
 	/* Ownership of the FP regs */
 	enum {
@@ -1271,7 +1259,7 @@ int kvm_arm_pvtime_has_attr(struct kvm_vcpu *vcpu,
 extern unsigned int __ro_after_init kvm_arm_vmid_bits;
 int __init kvm_arm_vmid_alloc_init(void);
 void __init kvm_arm_vmid_alloc_free(void);
-bool kvm_arm_vmid_update(struct kvm_vmid *kvm_vmid);
+void kvm_arm_vmid_update(struct kvm_vmid *kvm_vmid);
 void kvm_arm_vmid_clear_active(void);
 
 static inline void kvm_arm_pvtime_vcpu_init(struct kvm_vcpu_arch *vcpu_arch)
diff --git a/arch/arm64/kernel/cacheinfo.c b/arch/arm64/kernel/cacheinfo.c
index d9c9218fa1fd..309942b06c5b 100644
--- a/arch/arm64/kernel/cacheinfo.c
+++ b/arch/arm64/kernel/cacheinfo.c
@@ -101,16 +101,18 @@ int populate_cache_leaves(unsigned int cpu)
 	unsigned int level, idx;
 	enum cache_type type;
 	struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu);
-	struct cacheinfo *this_leaf = this_cpu_ci->info_list;
+	struct cacheinfo *infos = this_cpu_ci->info_list;
 
 	for (idx = 0, level = 1; level <= this_cpu_ci->num_levels &&
-	     idx < this_cpu_ci->num_leaves; idx++, level++) {
+	     idx < this_cpu_ci->num_leaves; level++) {
 		type = get_cache_type(level);
 		if (type == CACHE_TYPE_SEPARATE) {
-			ci_leaf_init(this_leaf++, CACHE_TYPE_DATA, level);
-			ci_leaf_init(this_leaf++, CACHE_TYPE_INST, level);
+			if (idx + 1 >= this_cpu_ci->num_leaves)
+				break;
+			ci_leaf_init(&infos[idx++], CACHE_TYPE_DATA, level);
+			ci_leaf_init(&infos[idx++], CACHE_TYPE_INST, level);
 		} else {
-			ci_leaf_init(this_leaf++, type, level);
+			ci_leaf_init(&infos[idx++], type, level);
 		}
 	}
 	return 0;
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index 4eb7c6698ae4..d561cf3b8ac7 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -3091,6 +3091,7 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = {
 	HWCAP_CAP(ID_AA64ISAR0_EL1, TS, FLAGM, CAP_HWCAP, KERNEL_HWCAP_FLAGM),
 	HWCAP_CAP(ID_AA64ISAR0_EL1, TS, FLAGM2, CAP_HWCAP, KERNEL_HWCAP_FLAGM2),
 	HWCAP_CAP(ID_AA64ISAR0_EL1, RNDR, IMP, CAP_HWCAP, KERNEL_HWCAP_RNG),
+	HWCAP_CAP(ID_AA64ISAR3_EL1, FPRCVT, IMP, CAP_HWCAP, KERNEL_HWCAP_FPRCVT),
 	HWCAP_CAP(ID_AA64PFR0_EL1, FP, IMP, CAP_HWCAP, KERNEL_HWCAP_FP),
 	HWCAP_CAP(ID_AA64PFR0_EL1, FP, FP16, CAP_HWCAP, KERNEL_HWCAP_FPHP),
 	HWCAP_CAP(ID_AA64PFR0_EL1, AdvSIMD, IMP, CAP_HWCAP, KERNEL_HWCAP_ASIMD),
@@ -3180,8 +3181,6 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = {
 	HWCAP_CAP(ID_AA64SMFR0_EL1, SF8FMA, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SF8FMA),
 	HWCAP_CAP(ID_AA64SMFR0_EL1, SF8DP4, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SF8DP4),
 	HWCAP_CAP(ID_AA64SMFR0_EL1, SF8DP2, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SF8DP2),
-	HWCAP_CAP(ID_AA64SMFR0_EL1, SF8MM8, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SF8MM8),
-	HWCAP_CAP(ID_AA64SMFR0_EL1, SF8MM4, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SF8MM4),
 	HWCAP_CAP(ID_AA64SMFR0_EL1, SBitPerm, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SBITPERM),
 	HWCAP_CAP(ID_AA64SMFR0_EL1, AES, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_AES),
 	HWCAP_CAP(ID_AA64SMFR0_EL1, SFEXPA, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SFEXPA),
@@ -3192,6 +3191,8 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = {
 	HWCAP_CAP(ID_AA64FPFR0_EL1, F8FMA, IMP, CAP_HWCAP, KERNEL_HWCAP_F8FMA),
 	HWCAP_CAP(ID_AA64FPFR0_EL1, F8DP4, IMP, CAP_HWCAP, KERNEL_HWCAP_F8DP4),
 	HWCAP_CAP(ID_AA64FPFR0_EL1, F8DP2, IMP, CAP_HWCAP, KERNEL_HWCAP_F8DP2),
+	HWCAP_CAP(ID_AA64FPFR0_EL1, F8MM8, IMP, CAP_HWCAP, KERNEL_HWCAP_F8MM8),
+	HWCAP_CAP(ID_AA64FPFR0_EL1, F8MM4, IMP, CAP_HWCAP, KERNEL_HWCAP_F8MM4),
 	HWCAP_CAP(ID_AA64FPFR0_EL1, F8E4M3, IMP, CAP_HWCAP, KERNEL_HWCAP_F8E4M3),
 	HWCAP_CAP(ID_AA64FPFR0_EL1, F8E5M2, IMP, CAP_HWCAP, KERNEL_HWCAP_F8E5M2),
 #ifdef CONFIG_ARM64_POE
diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index 2b601d88762d..8370d55f0353 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -1695,31 +1695,6 @@ void fpsimd_signal_preserve_current_state(void)
 }
 
 /*
- * Called by KVM when entering the guest.
- */
-void fpsimd_kvm_prepare(void)
-{
-	if (!system_supports_sve())
-		return;
-
-	/*
-	 * KVM does not save host SVE state since we can only enter
-	 * the guest from a syscall so the ABI means that only the
-	 * non-saved SVE state needs to be saved.  If we have left
-	 * SVE enabled for performance reasons then update the task
-	 * state to be FPSIMD only.
-	 */
-	get_cpu_fpsimd_context();
-
-	if (test_and_clear_thread_flag(TIF_SVE)) {
-		sve_to_fpsimd(current);
-		current->thread.fp_type = FP_STATE_FPSIMD;
-	}
-
-	put_cpu_fpsimd_context();
-}
-
-/*
  * Associate current's FPSIMD context with this cpu
  * The caller must have ownership of the cpu FPSIMD context before calling
  * this function.
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index 5ab1970ee543..2ce73525de2c 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -298,25 +298,8 @@ SYM_INNER_LABEL(init_el2, SYM_L_LOCAL)
 	msr	sctlr_el2, x0
 	isb
 0:
-	mov_q	x0, HCR_HOST_NVHE_FLAGS
-
-	/*
-	 * Compliant CPUs advertise their VHE-onlyness with
-	 * ID_AA64MMFR4_EL1.E2H0 < 0. HCR_EL2.E2H can be
-	 * RES1 in that case. Publish the E2H bit early so that
-	 * it can be picked up by the init_el2_state macro.
-	 *
-	 * Fruity CPUs seem to have HCR_EL2.E2H set to RAO/WI, but
-	 * don't advertise it (they predate this relaxation).
-	 */
-	mrs_s	x1, SYS_ID_AA64MMFR4_EL1
-	tbz	x1, #(ID_AA64MMFR4_EL1_E2H0_SHIFT + ID_AA64MMFR4_EL1_E2H0_WIDTH - 1), 1f
-
-	orr	x0, x0, #HCR_E2H
-1:
-	msr	hcr_el2, x0
-	isb
 
+	init_el2_hcr	HCR_HOST_NVHE_FLAGS
 	init_el2_state
 
 	/* Hypervisor stub */
@@ -339,7 +322,8 @@ SYM_INNER_LABEL(init_el2, SYM_L_LOCAL)
 	msr	sctlr_el1, x1
 	mov	x2, xzr
 3:
-	__init_el2_nvhe_prepare_eret
+	mov	x0, #INIT_PSTATE_EL1
+	msr	spsr_el2, x0
 
 	mov	w0, #BOOT_CPU_MODE_EL2
 	orr	x0, x0, x2
diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c
index 1a2c72f3e7f8..cb180684d10d 100644
--- a/arch/arm64/kernel/topology.c
+++ b/arch/arm64/kernel/topology.c
@@ -194,12 +194,19 @@ static void amu_fie_setup(const struct cpumask *cpus)
 	int cpu;
 
 	/* We are already set since the last insmod of cpufreq driver */
-	if (unlikely(cpumask_subset(cpus, amu_fie_cpus)))
+	if (cpumask_available(amu_fie_cpus) &&
+	    unlikely(cpumask_subset(cpus, amu_fie_cpus)))
 		return;
 
-	for_each_cpu(cpu, cpus) {
+	for_each_cpu(cpu, cpus)
 		if (!freq_counters_valid(cpu))
 			return;
+
+	if (!cpumask_available(amu_fie_cpus) &&
+	    !zalloc_cpumask_var(&amu_fie_cpus, GFP_KERNEL)) {
+		WARN_ONCE(1, "Failed to allocate FIE cpumask for CPUs[%*pbl]\n",
+			  cpumask_pr_args(cpus));
+		return;
 	}
 
 	cpumask_or(amu_fie_cpus, amu_fie_cpus, cpus);
@@ -237,17 +244,8 @@ static struct notifier_block init_amu_fie_notifier = {
 
 static int __init init_amu_fie(void)
 {
-	int ret;
-
-	if (!zalloc_cpumask_var(&amu_fie_cpus, GFP_KERNEL))
-		return -ENOMEM;
-
-	ret = cpufreq_register_notifier(&init_amu_fie_notifier,
+	return cpufreq_register_notifier(&init_amu_fie_notifier,
 					CPUFREQ_POLICY_NOTIFIER);
-	if (ret)
-		free_cpumask_var(amu_fie_cpus);
-
-	return ret;
 }
 core_initcall(init_amu_fie);
 
diff --git a/arch/arm64/kernel/vdso/vdso.lds.S b/arch/arm64/kernel/vdso/vdso.lds.S
index 4ec32e86a8da..47ad6944f9f0 100644
--- a/arch/arm64/kernel/vdso/vdso.lds.S
+++ b/arch/arm64/kernel/vdso/vdso.lds.S
@@ -41,6 +41,7 @@ SECTIONS
 	 */
 	/DISCARD/	: {
 		*(.note.GNU-stack .note.gnu.property)
+		*(.ARM.attributes)
 	}
 	.note		: { *(.note.*) }		:text	:note
 
diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S
index f84c71f04d9e..e73326bd3ff7 100644
--- a/arch/arm64/kernel/vmlinux.lds.S
+++ b/arch/arm64/kernel/vmlinux.lds.S
@@ -162,6 +162,7 @@ SECTIONS
 	/DISCARD/ : {
 		*(.interp .dynamic)
 		*(.dynsym .dynstr .hash .gnu.hash)
+		*(.ARM.attributes)
 	}
 
 	. = KIMAGE_VADDR;
diff --git a/arch/arm64/kvm/arch_timer.c b/arch/arm64/kvm/arch_timer.c
index 231c0cd9c7b4..70802e4c91cf 100644
--- a/arch/arm64/kvm/arch_timer.c
+++ b/arch/arm64/kvm/arch_timer.c
@@ -447,21 +447,19 @@ static void kvm_timer_update_status(struct arch_timer_context *ctx, bool level)
 static void kvm_timer_update_irq(struct kvm_vcpu *vcpu, bool new_level,
 				 struct arch_timer_context *timer_ctx)
 {
-	int ret;
-
 	kvm_timer_update_status(timer_ctx, new_level);
 
 	timer_ctx->irq.level = new_level;
 	trace_kvm_timer_update_irq(vcpu->vcpu_id, timer_irq(timer_ctx),
 				   timer_ctx->irq.level);
 
-	if (!userspace_irqchip(vcpu->kvm)) {
-		ret = kvm_vgic_inject_irq(vcpu->kvm, vcpu,
-					  timer_irq(timer_ctx),
-					  timer_ctx->irq.level,
-					  timer_ctx);
-		WARN_ON(ret);
-	}
+	if (userspace_irqchip(vcpu->kvm))
+		return;
+
+	kvm_vgic_inject_irq(vcpu->kvm, vcpu,
+			    timer_irq(timer_ctx),
+			    timer_ctx->irq.level,
+			    timer_ctx);
 }
 
 /* Only called for a fully emulated timer */
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 071a7d75be68..0160b4924351 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -560,6 +560,16 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	last_ran = this_cpu_ptr(mmu->last_vcpu_ran);
 
 	/*
+	 * Ensure a VMID is allocated for the MMU before programming VTTBR_EL2,
+	 * which happens eagerly in VHE.
+	 *
+	 * Also, the VMID allocator only preserves VMIDs that are active at the
+	 * time of rollover, so KVM might need to grab a new VMID for the MMU if
+	 * this is called from kvm_sched_in().
+	 */
+	kvm_arm_vmid_update(&mmu->vmid);
+
+	/*
 	 * We guarantee that both TLBs and I-cache are private to each
 	 * vcpu. If detecting that a vcpu from the same VM has
 	 * previously run on the same physical CPU, call into the
@@ -1138,18 +1148,6 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 		 */
 		preempt_disable();
 
-		/*
-		 * The VMID allocator only tracks active VMIDs per
-		 * physical CPU, and therefore the VMID allocated may not be
-		 * preserved on VMID roll-over if the task was preempted,
-		 * making a thread's VMID inactive. So we need to call
-		 * kvm_arm_vmid_update() in non-premptible context.
-		 */
-		if (kvm_arm_vmid_update(&vcpu->arch.hw_mmu->vmid) &&
-		    has_vhe())
-			__load_stage2(vcpu->arch.hw_mmu,
-				      vcpu->arch.hw_mmu->arch);
-
 		kvm_pmu_flush_hwstate(vcpu);
 
 		local_irq_disable();
@@ -1980,7 +1978,7 @@ static int kvm_init_vector_slots(void)
 static void __init cpu_prepare_hyp_mode(int cpu, u32 hyp_va_bits)
 {
 	struct kvm_nvhe_init_params *params = per_cpu_ptr_nvhe_sym(kvm_init_params, cpu);
-	unsigned long tcr, ips;
+	unsigned long tcr;
 
 	/*
 	 * Calculate the raw per-cpu offset without a translation from the
@@ -1994,19 +1992,18 @@ static void __init cpu_prepare_hyp_mode(int cpu, u32 hyp_va_bits)
 	params->mair_el2 = read_sysreg(mair_el1);
 
 	tcr = read_sysreg(tcr_el1);
-	ips = FIELD_GET(TCR_IPS_MASK, tcr);
 	if (cpus_have_final_cap(ARM64_KVM_HVHE)) {
+		tcr &= ~(TCR_HD | TCR_HA | TCR_A1 | TCR_T0SZ_MASK);
 		tcr |= TCR_EPD1_MASK;
 	} else {
+		unsigned long ips = FIELD_GET(TCR_IPS_MASK, tcr);
+
 		tcr &= TCR_EL2_MASK;
-		tcr |= TCR_EL2_RES1;
+		tcr |= TCR_EL2_RES1 | FIELD_PREP(TCR_EL2_PS_MASK, ips);
+		if (lpa2_is_enabled())
+			tcr |= TCR_EL2_DS;
 	}
-	tcr &= ~TCR_T0SZ_MASK;
 	tcr |= TCR_T0SZ(hyp_va_bits);
-	tcr &= ~TCR_EL2_PS_MASK;
-	tcr |= FIELD_PREP(TCR_EL2_PS_MASK, ips);
-	if (lpa2_is_enabled())
-		tcr |= TCR_EL2_DS;
 	params->tcr_el2 = tcr;
 
 	params->pgd_pa = kvm_mmu_get_httbr();
@@ -2481,14 +2478,6 @@ static void finalize_init_hyp_mode(void)
 			per_cpu_ptr_nvhe_sym(kvm_host_data, cpu)->sve_state =
 				kern_hyp_va(sve_state);
 		}
-	} else {
-		for_each_possible_cpu(cpu) {
-			struct user_fpsimd_state *fpsimd_state;
-
-			fpsimd_state = &per_cpu_ptr_nvhe_sym(kvm_host_data, cpu)->host_ctxt.fp_regs;
-			per_cpu_ptr_nvhe_sym(kvm_host_data, cpu)->fpsimd_state =
-				kern_hyp_va(fpsimd_state);
-		}
 	}
 }
 
diff --git a/arch/arm64/kvm/fpsimd.c b/arch/arm64/kvm/fpsimd.c
index 4d3d1a2eb157..7f6e43d25691 100644
--- a/arch/arm64/kvm/fpsimd.c
+++ b/arch/arm64/kvm/fpsimd.c
@@ -54,50 +54,18 @@ void kvm_arch_vcpu_load_fp(struct kvm_vcpu *vcpu)
 	if (!system_supports_fpsimd())
 		return;
 
-	fpsimd_kvm_prepare();
-
 	/*
-	 * We will check TIF_FOREIGN_FPSTATE just before entering the
-	 * guest in kvm_arch_vcpu_ctxflush_fp() and override this to
-	 * FP_STATE_FREE if the flag set.
+	 * Ensure that any host FPSIMD/SVE/SME state is saved and unbound such
+	 * that the host kernel is responsible for restoring this state upon
+	 * return to userspace, and the hyp code doesn't need to save anything.
+	 *
+	 * When the host may use SME, fpsimd_save_and_flush_cpu_state() ensures
+	 * that PSTATE.{SM,ZA} == {0,0}.
 	 */
-	*host_data_ptr(fp_owner) = FP_STATE_HOST_OWNED;
-	*host_data_ptr(fpsimd_state) = kern_hyp_va(&current->thread.uw.fpsimd_state);
-	*host_data_ptr(fpmr_ptr) = kern_hyp_va(&current->thread.uw.fpmr);
-
-	host_data_clear_flag(HOST_SVE_ENABLED);
-	if (read_sysreg(cpacr_el1) & CPACR_EL1_ZEN_EL0EN)
-		host_data_set_flag(HOST_SVE_ENABLED);
-
-	if (system_supports_sme()) {
-		host_data_clear_flag(HOST_SME_ENABLED);
-		if (read_sysreg(cpacr_el1) & CPACR_EL1_SMEN_EL0EN)
-			host_data_set_flag(HOST_SME_ENABLED);
-
-		/*
-		 * If PSTATE.SM is enabled then save any pending FP
-		 * state and disable PSTATE.SM. If we leave PSTATE.SM
-		 * enabled and the guest does not enable SME via
-		 * CPACR_EL1.SMEN then operations that should be valid
-		 * may generate SME traps from EL1 to EL1 which we
-		 * can't intercept and which would confuse the guest.
-		 *
-		 * Do the same for PSTATE.ZA in the case where there
-		 * is state in the registers which has not already
-		 * been saved, this is very unlikely to happen.
-		 */
-		if (read_sysreg_s(SYS_SVCR) & (SVCR_SM_MASK | SVCR_ZA_MASK)) {
-			*host_data_ptr(fp_owner) = FP_STATE_FREE;
-			fpsimd_save_and_flush_cpu_state();
-		}
-	}
+	fpsimd_save_and_flush_cpu_state();
+	*host_data_ptr(fp_owner) = FP_STATE_FREE;
 
-	/*
-	 * If normal guests gain SME support, maintain this behavior for pKVM
-	 * guests, which don't support SME.
-	 */
-	WARN_ON(is_protected_kvm_enabled() && system_supports_sme() &&
-		read_sysreg_s(SYS_SVCR));
+	WARN_ON_ONCE(system_supports_sme() && read_sysreg_s(SYS_SVCR));
 }
 
 /*
@@ -162,52 +130,7 @@ void kvm_arch_vcpu_put_fp(struct kvm_vcpu *vcpu)
 
 	local_irq_save(flags);
 
-	/*
-	 * If we have VHE then the Hyp code will reset CPACR_EL1 to
-	 * the default value and we need to reenable SME.
-	 */
-	if (has_vhe() && system_supports_sme()) {
-		/* Also restore EL0 state seen on entry */
-		if (host_data_test_flag(HOST_SME_ENABLED))
-			sysreg_clear_set(CPACR_EL1, 0, CPACR_EL1_SMEN);
-		else
-			sysreg_clear_set(CPACR_EL1,
-					 CPACR_EL1_SMEN_EL0EN,
-					 CPACR_EL1_SMEN_EL1EN);
-		isb();
-	}
-
 	if (guest_owns_fp_regs()) {
-		if (vcpu_has_sve(vcpu)) {
-			u64 zcr = read_sysreg_el1(SYS_ZCR);
-
-			/*
-			 * If the vCPU is in the hyp context then ZCR_EL1 is
-			 * loaded with its vEL2 counterpart.
-			 */
-			__vcpu_sys_reg(vcpu, vcpu_sve_zcr_elx(vcpu)) = zcr;
-
-			/*
-			 * Restore the VL that was saved when bound to the CPU,
-			 * which is the maximum VL for the guest. Because the
-			 * layout of the data when saving the sve state depends
-			 * on the VL, we need to use a consistent (i.e., the
-			 * maximum) VL.
-			 * Note that this means that at guest exit ZCR_EL1 is
-			 * not necessarily the same as on guest entry.
-			 *
-			 * ZCR_EL2 holds the guest hypervisor's VL when running
-			 * a nested guest, which could be smaller than the
-			 * max for the vCPU. Similar to above, we first need to
-			 * switch to a VL consistent with the layout of the
-			 * vCPU's SVE state. KVM support for NV implies VHE, so
-			 * using the ZCR_EL1 alias is safe.
-			 */
-			if (!has_vhe() || (vcpu_has_nv(vcpu) && !is_hyp_ctxt(vcpu)))
-				sve_cond_update_zcr_vq(vcpu_sve_max_vq(vcpu) - 1,
-						       SYS_ZCR_EL1);
-		}
-
 		/*
 		 * Flush (save and invalidate) the fpsimd/sve state so that if
 		 * the host tries to use fpsimd/sve, it's not using stale data
@@ -219,18 +142,6 @@ void kvm_arch_vcpu_put_fp(struct kvm_vcpu *vcpu)
 		 * when needed.
 		 */
 		fpsimd_save_and_flush_cpu_state();
-	} else if (has_vhe() && system_supports_sve()) {
-		/*
-		 * The FPSIMD/SVE state in the CPU has not been touched, and we
-		 * have SVE (and VHE): CPACR_EL1 (alias CPTR_EL2) has been
-		 * reset by kvm_reset_cptr_el2() in the Hyp code, disabling SVE
-		 * for EL0.  To avoid spurious traps, restore the trap state
-		 * seen by kvm_arch_vcpu_load_fp():
-		 */
-		if (host_data_test_flag(HOST_SVE_ENABLED))
-			sysreg_clear_set(CPACR_EL1, 0, CPACR_EL1_ZEN_EL0EN);
-		else
-			sysreg_clear_set(CPACR_EL1, CPACR_EL1_ZEN_EL0EN, 0);
 	}
 
 	local_irq_restore(flags);
diff --git a/arch/arm64/kvm/hyp/entry.S b/arch/arm64/kvm/hyp/entry.S
index 4433a234aa9b..9f4e8d68ab50 100644
--- a/arch/arm64/kvm/hyp/entry.S
+++ b/arch/arm64/kvm/hyp/entry.S
@@ -44,6 +44,11 @@ alternative_if ARM64_HAS_RAS_EXTN
 alternative_else_nop_endif
 	mrs	x1, isr_el1
 	cbz	x1,  1f
+
+	// Ensure that __guest_enter() always provides a context
+	// synchronization event so that callers don't need ISBs for anything
+	// that would usually be synchonized by the ERET.
+	isb
 	mov	x0, #ARM_EXCEPTION_IRQ
 	ret
 
diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h
index f838a45665f2..23bbe28eaaf9 100644
--- a/arch/arm64/kvm/hyp/include/hyp/switch.h
+++ b/arch/arm64/kvm/hyp/include/hyp/switch.h
@@ -326,7 +326,7 @@ static inline bool __populate_fault_info(struct kvm_vcpu *vcpu)
 	return __get_fault_info(vcpu->arch.fault.esr_el2, &vcpu->arch.fault);
 }
 
-static bool kvm_hyp_handle_mops(struct kvm_vcpu *vcpu, u64 *exit_code)
+static inline bool kvm_hyp_handle_mops(struct kvm_vcpu *vcpu, u64 *exit_code)
 {
 	*vcpu_pc(vcpu) = read_sysreg_el2(SYS_ELR);
 	arm64_mops_reset_regs(vcpu_gp_regs(vcpu), vcpu->arch.fault.esr_el2);
@@ -375,7 +375,87 @@ static inline void __hyp_sve_save_host(void)
 			 true);
 }
 
-static void kvm_hyp_save_fpsimd_host(struct kvm_vcpu *vcpu);
+static inline void fpsimd_lazy_switch_to_guest(struct kvm_vcpu *vcpu)
+{
+	u64 zcr_el1, zcr_el2;
+
+	if (!guest_owns_fp_regs())
+		return;
+
+	if (vcpu_has_sve(vcpu)) {
+		/* A guest hypervisor may restrict the effective max VL. */
+		if (vcpu_has_nv(vcpu) && !is_hyp_ctxt(vcpu))
+			zcr_el2 = __vcpu_sys_reg(vcpu, ZCR_EL2);
+		else
+			zcr_el2 = vcpu_sve_max_vq(vcpu) - 1;
+
+		write_sysreg_el2(zcr_el2, SYS_ZCR);
+
+		zcr_el1 = __vcpu_sys_reg(vcpu, vcpu_sve_zcr_elx(vcpu));
+		write_sysreg_el1(zcr_el1, SYS_ZCR);
+	}
+}
+
+static inline void fpsimd_lazy_switch_to_host(struct kvm_vcpu *vcpu)
+{
+	u64 zcr_el1, zcr_el2;
+
+	if (!guest_owns_fp_regs())
+		return;
+
+	/*
+	 * When the guest owns the FP regs, we know that guest+hyp traps for
+	 * any FPSIMD/SVE/SME features exposed to the guest have been disabled
+	 * by either fpsimd_lazy_switch_to_guest() or kvm_hyp_handle_fpsimd()
+	 * prior to __guest_entry(). As __guest_entry() guarantees a context
+	 * synchronization event, we don't need an ISB here to avoid taking
+	 * traps for anything that was exposed to the guest.
+	 */
+	if (vcpu_has_sve(vcpu)) {
+		zcr_el1 = read_sysreg_el1(SYS_ZCR);
+		__vcpu_sys_reg(vcpu, vcpu_sve_zcr_elx(vcpu)) = zcr_el1;
+
+		/*
+		 * The guest's state is always saved using the guest's max VL.
+		 * Ensure that the host has the guest's max VL active such that
+		 * the host can save the guest's state lazily, but don't
+		 * artificially restrict the host to the guest's max VL.
+		 */
+		if (has_vhe()) {
+			zcr_el2 = vcpu_sve_max_vq(vcpu) - 1;
+			write_sysreg_el2(zcr_el2, SYS_ZCR);
+		} else {
+			zcr_el2 = sve_vq_from_vl(kvm_host_sve_max_vl) - 1;
+			write_sysreg_el2(zcr_el2, SYS_ZCR);
+
+			zcr_el1 = vcpu_sve_max_vq(vcpu) - 1;
+			write_sysreg_el1(zcr_el1, SYS_ZCR);
+		}
+	}
+}
+
+static void kvm_hyp_save_fpsimd_host(struct kvm_vcpu *vcpu)
+{
+	/*
+	 * Non-protected kvm relies on the host restoring its sve state.
+	 * Protected kvm restores the host's sve state as not to reveal that
+	 * fpsimd was used by a guest nor leak upper sve bits.
+	 */
+	if (system_supports_sve()) {
+		__hyp_sve_save_host();
+
+		/* Re-enable SVE traps if not supported for the guest vcpu. */
+		if (!vcpu_has_sve(vcpu))
+			cpacr_clear_set(CPACR_EL1_ZEN, 0);
+
+	} else {
+		__fpsimd_save_state(host_data_ptr(host_ctxt.fp_regs));
+	}
+
+	if (kvm_has_fpmr(kern_hyp_va(vcpu->kvm)))
+		*host_data_ptr(fpmr) = read_sysreg_s(SYS_FPMR);
+}
+
 
 /*
  * We trap the first access to the FP/SIMD to save the host context and
@@ -383,7 +463,7 @@ static void kvm_hyp_save_fpsimd_host(struct kvm_vcpu *vcpu);
  * If FP/SIMD is not implemented, handle the trap and inject an undefined
  * instruction exception to the guest. Similarly for trapped SVE accesses.
  */
-static bool kvm_hyp_handle_fpsimd(struct kvm_vcpu *vcpu, u64 *exit_code)
+static inline bool kvm_hyp_handle_fpsimd(struct kvm_vcpu *vcpu, u64 *exit_code)
 {
 	bool sve_guest;
 	u8 esr_ec;
@@ -425,7 +505,7 @@ static bool kvm_hyp_handle_fpsimd(struct kvm_vcpu *vcpu, u64 *exit_code)
 	isb();
 
 	/* Write out the host state if it's in the registers */
-	if (host_owns_fp_regs())
+	if (is_protected_kvm_enabled() && host_owns_fp_regs())
 		kvm_hyp_save_fpsimd_host(vcpu);
 
 	/* Restore the guest state */
@@ -501,9 +581,22 @@ static inline bool handle_tx2_tvm(struct kvm_vcpu *vcpu)
 	return true;
 }
 
+/* Open-coded version of timer_get_offset() to allow for kern_hyp_va() */
+static inline u64 hyp_timer_get_offset(struct arch_timer_context *ctxt)
+{
+	u64 offset = 0;
+
+	if (ctxt->offset.vm_offset)
+		offset += *kern_hyp_va(ctxt->offset.vm_offset);
+	if (ctxt->offset.vcpu_offset)
+		offset += *kern_hyp_va(ctxt->offset.vcpu_offset);
+
+	return offset;
+}
+
 static inline u64 compute_counter_value(struct arch_timer_context *ctxt)
 {
-	return arch_timer_read_cntpct_el0() - timer_get_offset(ctxt);
+	return arch_timer_read_cntpct_el0() - hyp_timer_get_offset(ctxt);
 }
 
 static bool kvm_handle_cntxct(struct kvm_vcpu *vcpu)
@@ -587,7 +680,7 @@ static bool handle_ampere1_tcr(struct kvm_vcpu *vcpu)
 	return true;
 }
 
-static bool kvm_hyp_handle_sysreg(struct kvm_vcpu *vcpu, u64 *exit_code)
+static inline bool kvm_hyp_handle_sysreg(struct kvm_vcpu *vcpu, u64 *exit_code)
 {
 	if (cpus_have_final_cap(ARM64_WORKAROUND_CAVIUM_TX2_219_TVM) &&
 	    handle_tx2_tvm(vcpu))
@@ -607,7 +700,7 @@ static bool kvm_hyp_handle_sysreg(struct kvm_vcpu *vcpu, u64 *exit_code)
 	return false;
 }
 
-static bool kvm_hyp_handle_cp15_32(struct kvm_vcpu *vcpu, u64 *exit_code)
+static inline bool kvm_hyp_handle_cp15_32(struct kvm_vcpu *vcpu, u64 *exit_code)
 {
 	if (static_branch_unlikely(&vgic_v3_cpuif_trap) &&
 	    __vgic_v3_perform_cpuif_access(vcpu) == 1)
@@ -616,19 +709,18 @@ static bool kvm_hyp_handle_cp15_32(struct kvm_vcpu *vcpu, u64 *exit_code)
 	return false;
 }
 
-static bool kvm_hyp_handle_memory_fault(struct kvm_vcpu *vcpu, u64 *exit_code)
+static inline bool kvm_hyp_handle_memory_fault(struct kvm_vcpu *vcpu,
+					       u64 *exit_code)
 {
 	if (!__populate_fault_info(vcpu))
 		return true;
 
 	return false;
 }
-static bool kvm_hyp_handle_iabt_low(struct kvm_vcpu *vcpu, u64 *exit_code)
-	__alias(kvm_hyp_handle_memory_fault);
-static bool kvm_hyp_handle_watchpt_low(struct kvm_vcpu *vcpu, u64 *exit_code)
-	__alias(kvm_hyp_handle_memory_fault);
+#define kvm_hyp_handle_iabt_low		kvm_hyp_handle_memory_fault
+#define kvm_hyp_handle_watchpt_low	kvm_hyp_handle_memory_fault
 
-static bool kvm_hyp_handle_dabt_low(struct kvm_vcpu *vcpu, u64 *exit_code)
+static inline bool kvm_hyp_handle_dabt_low(struct kvm_vcpu *vcpu, u64 *exit_code)
 {
 	if (kvm_hyp_handle_memory_fault(vcpu, exit_code))
 		return true;
@@ -658,23 +750,16 @@ static bool kvm_hyp_handle_dabt_low(struct kvm_vcpu *vcpu, u64 *exit_code)
 
 typedef bool (*exit_handler_fn)(struct kvm_vcpu *, u64 *);
 
-static const exit_handler_fn *kvm_get_exit_handler_array(struct kvm_vcpu *vcpu);
-
-static void early_exit_filter(struct kvm_vcpu *vcpu, u64 *exit_code);
-
 /*
  * Allow the hypervisor to handle the exit with an exit handler if it has one.
  *
  * Returns true if the hypervisor handled the exit, and control should go back
  * to the guest, or false if it hasn't.
  */
-static inline bool kvm_hyp_handle_exit(struct kvm_vcpu *vcpu, u64 *exit_code)
+static inline bool kvm_hyp_handle_exit(struct kvm_vcpu *vcpu, u64 *exit_code,
+				       const exit_handler_fn *handlers)
 {
-	const exit_handler_fn *handlers = kvm_get_exit_handler_array(vcpu);
-	exit_handler_fn fn;
-
-	fn = handlers[kvm_vcpu_trap_get_class(vcpu)];
-
+	exit_handler_fn fn = handlers[kvm_vcpu_trap_get_class(vcpu)];
 	if (fn)
 		return fn(vcpu, exit_code);
 
@@ -704,20 +789,9 @@ static inline void synchronize_vcpu_pstate(struct kvm_vcpu *vcpu, u64 *exit_code
  * the guest, false when we should restore the host state and return to the
  * main run loop.
  */
-static inline bool fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code)
+static inline bool __fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code,
+				      const exit_handler_fn *handlers)
 {
-	/*
-	 * Save PSTATE early so that we can evaluate the vcpu mode
-	 * early on.
-	 */
-	synchronize_vcpu_pstate(vcpu, exit_code);
-
-	/*
-	 * Check whether we want to repaint the state one way or
-	 * another.
-	 */
-	early_exit_filter(vcpu, exit_code);
-
 	if (ARM_EXCEPTION_CODE(*exit_code) != ARM_EXCEPTION_IRQ)
 		vcpu->arch.fault.esr_el2 = read_sysreg_el2(SYS_ESR);
 
@@ -747,7 +821,7 @@ static inline bool fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code)
 		goto exit;
 
 	/* Check if there's an exit handler and allow it to handle the exit. */
-	if (kvm_hyp_handle_exit(vcpu, exit_code))
+	if (kvm_hyp_handle_exit(vcpu, exit_code, handlers))
 		goto guest;
 exit:
 	/* Return to the host kernel and handle the exit */
diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-init.S b/arch/arm64/kvm/hyp/nvhe/hyp-init.S
index fc1866226067..f8af11189572 100644
--- a/arch/arm64/kvm/hyp/nvhe/hyp-init.S
+++ b/arch/arm64/kvm/hyp/nvhe/hyp-init.S
@@ -73,8 +73,12 @@ __do_hyp_init:
 	eret
 SYM_CODE_END(__kvm_hyp_init)
 
+/*
+ * Initialize EL2 CPU state to sane values.
+ *
+ * HCR_EL2.E2H must have been initialized already.
+ */
 SYM_CODE_START_LOCAL(__kvm_init_el2_state)
-	/* Initialize EL2 CPU state to sane values. */
 	init_el2_state				// Clobbers x0..x2
 	finalise_el2_state
 	ret
@@ -206,9 +210,9 @@ SYM_CODE_START_LOCAL(__kvm_hyp_init_cpu)
 
 2:	msr	SPsel, #1			// We want to use SP_EL{1,2}
 
-	bl	__kvm_init_el2_state
+	init_el2_hcr	0
 
-	__init_el2_nvhe_prepare_eret
+	bl	__kvm_init_el2_state
 
 	/* Enable MMU, set vectors and stack. */
 	mov	x0, x28
diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
index 6e12c070832f..2c37680d954c 100644
--- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c
+++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
@@ -5,6 +5,7 @@
  */
 
 #include <hyp/adjust_pc.h>
+#include <hyp/switch.h>
 
 #include <asm/pgtable-types.h>
 #include <asm/kvm_asm.h>
@@ -83,7 +84,7 @@ static void fpsimd_sve_sync(struct kvm_vcpu *vcpu)
 	if (system_supports_sve())
 		__hyp_sve_restore_host();
 	else
-		__fpsimd_restore_state(*host_data_ptr(fpsimd_state));
+		__fpsimd_restore_state(host_data_ptr(host_ctxt.fp_regs));
 
 	if (has_fpmr)
 		write_sysreg_s(*host_data_ptr(fpmr), SYS_FPMR);
@@ -224,8 +225,12 @@ static void handle___kvm_vcpu_run(struct kvm_cpu_context *host_ctxt)
 
 		sync_hyp_vcpu(hyp_vcpu);
 	} else {
+		struct kvm_vcpu *vcpu = kern_hyp_va(host_vcpu);
+
 		/* The host is fully trusted, run its vCPU directly. */
-		ret = __kvm_vcpu_run(kern_hyp_va(host_vcpu));
+		fpsimd_lazy_switch_to_guest(vcpu);
+		ret = __kvm_vcpu_run(vcpu);
+		fpsimd_lazy_switch_to_host(vcpu);
 	}
 out:
 	cpu_reg(host_ctxt, 1) =  ret;
@@ -675,12 +680,6 @@ void handle_trap(struct kvm_cpu_context *host_ctxt)
 	case ESR_ELx_EC_SMC64:
 		handle_host_smc(host_ctxt);
 		break;
-	case ESR_ELx_EC_SVE:
-		cpacr_clear_set(0, CPACR_EL1_ZEN);
-		isb();
-		sve_cond_update_zcr_vq(sve_vq_from_vl(kvm_host_sve_max_vl) - 1,
-				       SYS_ZCR_EL2);
-		break;
 	case ESR_ELx_EC_IABT_LOW:
 	case ESR_ELx_EC_DABT_LOW:
 		handle_host_mem_abort(host_ctxt);
diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
index 7ad7b133b81a..19c3c631708c 100644
--- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c
+++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
@@ -943,10 +943,10 @@ static int __check_host_shared_guest(struct pkvm_hyp_vm *vm, u64 *__phys, u64 ip
 	ret = kvm_pgtable_get_leaf(&vm->pgt, ipa, &pte, &level);
 	if (ret)
 		return ret;
-	if (level != KVM_PGTABLE_LAST_LEVEL)
-		return -E2BIG;
 	if (!kvm_pte_valid(pte))
 		return -ENOENT;
+	if (level != KVM_PGTABLE_LAST_LEVEL)
+		return -E2BIG;
 
 	state = guest_get_page_state(pte, ipa);
 	if (state != PKVM_PAGE_SHARED_BORROWED)
@@ -998,63 +998,73 @@ unlock:
 	return ret;
 }
 
-int __pkvm_host_relax_perms_guest(u64 gfn, struct pkvm_hyp_vcpu *vcpu, enum kvm_pgtable_prot prot)
+static void assert_host_shared_guest(struct pkvm_hyp_vm *vm, u64 ipa)
 {
-	struct pkvm_hyp_vm *vm = pkvm_hyp_vcpu_to_hyp_vm(vcpu);
-	u64 ipa = hyp_pfn_to_phys(gfn);
 	u64 phys;
 	int ret;
 
-	if (prot & ~KVM_PGTABLE_PROT_RWX)
-		return -EINVAL;
+	if (!IS_ENABLED(CONFIG_NVHE_EL2_DEBUG))
+		return;
 
 	host_lock_component();
 	guest_lock_component(vm);
 
 	ret = __check_host_shared_guest(vm, &phys, ipa);
-	if (!ret)
-		ret = kvm_pgtable_stage2_relax_perms(&vm->pgt, ipa, prot, 0);
 
 	guest_unlock_component(vm);
 	host_unlock_component();
 
-	return ret;
+	WARN_ON(ret && ret != -ENOENT);
 }
 
-int __pkvm_host_wrprotect_guest(u64 gfn, struct pkvm_hyp_vm *vm)
+int __pkvm_host_relax_perms_guest(u64 gfn, struct pkvm_hyp_vcpu *vcpu, enum kvm_pgtable_prot prot)
 {
+	struct pkvm_hyp_vm *vm = pkvm_hyp_vcpu_to_hyp_vm(vcpu);
 	u64 ipa = hyp_pfn_to_phys(gfn);
-	u64 phys;
 	int ret;
 
-	host_lock_component();
-	guest_lock_component(vm);
+	if (pkvm_hyp_vm_is_protected(vm))
+		return -EPERM;
 
-	ret = __check_host_shared_guest(vm, &phys, ipa);
-	if (!ret)
-		ret = kvm_pgtable_stage2_wrprotect(&vm->pgt, ipa, PAGE_SIZE);
+	if (prot & ~KVM_PGTABLE_PROT_RWX)
+		return -EINVAL;
 
+	assert_host_shared_guest(vm, ipa);
+	guest_lock_component(vm);
+	ret = kvm_pgtable_stage2_relax_perms(&vm->pgt, ipa, prot, 0);
 	guest_unlock_component(vm);
-	host_unlock_component();
 
 	return ret;
 }
 
-int __pkvm_host_test_clear_young_guest(u64 gfn, bool mkold, struct pkvm_hyp_vm *vm)
+int __pkvm_host_wrprotect_guest(u64 gfn, struct pkvm_hyp_vm *vm)
 {
 	u64 ipa = hyp_pfn_to_phys(gfn);
-	u64 phys;
 	int ret;
 
-	host_lock_component();
+	if (pkvm_hyp_vm_is_protected(vm))
+		return -EPERM;
+
+	assert_host_shared_guest(vm, ipa);
 	guest_lock_component(vm);
+	ret = kvm_pgtable_stage2_wrprotect(&vm->pgt, ipa, PAGE_SIZE);
+	guest_unlock_component(vm);
 
-	ret = __check_host_shared_guest(vm, &phys, ipa);
-	if (!ret)
-		ret = kvm_pgtable_stage2_test_clear_young(&vm->pgt, ipa, PAGE_SIZE, mkold);
+	return ret;
+}
+
+int __pkvm_host_test_clear_young_guest(u64 gfn, bool mkold, struct pkvm_hyp_vm *vm)
+{
+	u64 ipa = hyp_pfn_to_phys(gfn);
+	int ret;
+
+	if (pkvm_hyp_vm_is_protected(vm))
+		return -EPERM;
 
+	assert_host_shared_guest(vm, ipa);
+	guest_lock_component(vm);
+	ret = kvm_pgtable_stage2_test_clear_young(&vm->pgt, ipa, PAGE_SIZE, mkold);
 	guest_unlock_component(vm);
-	host_unlock_component();
 
 	return ret;
 }
@@ -1063,18 +1073,14 @@ int __pkvm_host_mkyoung_guest(u64 gfn, struct pkvm_hyp_vcpu *vcpu)
 {
 	struct pkvm_hyp_vm *vm = pkvm_hyp_vcpu_to_hyp_vm(vcpu);
 	u64 ipa = hyp_pfn_to_phys(gfn);
-	u64 phys;
-	int ret;
-
-	host_lock_component();
-	guest_lock_component(vm);
 
-	ret = __check_host_shared_guest(vm, &phys, ipa);
-	if (!ret)
-		kvm_pgtable_stage2_mkyoung(&vm->pgt, ipa, 0);
+	if (pkvm_hyp_vm_is_protected(vm))
+		return -EPERM;
 
+	assert_host_shared_guest(vm, ipa);
+	guest_lock_component(vm);
+	kvm_pgtable_stage2_mkyoung(&vm->pgt, ipa, 0);
 	guest_unlock_component(vm);
-	host_unlock_component();
 
-	return ret;
+	return 0;
 }
diff --git a/arch/arm64/kvm/hyp/nvhe/psci-relay.c b/arch/arm64/kvm/hyp/nvhe/psci-relay.c
index 9c2ce1e0e99a..c3e196fb8b18 100644
--- a/arch/arm64/kvm/hyp/nvhe/psci-relay.c
+++ b/arch/arm64/kvm/hyp/nvhe/psci-relay.c
@@ -218,6 +218,9 @@ asmlinkage void __noreturn __kvm_host_psci_cpu_entry(bool is_cpu_on)
 	if (is_cpu_on)
 		release_boot_args(boot_args);
 
+	write_sysreg_el1(INIT_SCTLR_EL1_MMU_OFF, SYS_SCTLR);
+	write_sysreg(INIT_PSTATE_EL1, SPSR_EL2);
+
 	__host_enter(host_ctxt);
 }
 
diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c
index 6c846d033d24..7d2ba6ef0261 100644
--- a/arch/arm64/kvm/hyp/nvhe/switch.c
+++ b/arch/arm64/kvm/hyp/nvhe/switch.c
@@ -39,6 +39,9 @@ static void __activate_cptr_traps(struct kvm_vcpu *vcpu)
 {
 	u64 val = CPTR_EL2_TAM;	/* Same bit irrespective of E2H */
 
+	if (!guest_owns_fp_regs())
+		__activate_traps_fpsimd32(vcpu);
+
 	if (has_hvhe()) {
 		val |= CPACR_EL1_TTA;
 
@@ -47,6 +50,8 @@ static void __activate_cptr_traps(struct kvm_vcpu *vcpu)
 			if (vcpu_has_sve(vcpu))
 				val |= CPACR_EL1_ZEN;
 		}
+
+		write_sysreg(val, cpacr_el1);
 	} else {
 		val |= CPTR_EL2_TTA | CPTR_NVHE_EL2_RES1;
 
@@ -61,12 +66,32 @@ static void __activate_cptr_traps(struct kvm_vcpu *vcpu)
 
 		if (!guest_owns_fp_regs())
 			val |= CPTR_EL2_TFP;
+
+		write_sysreg(val, cptr_el2);
 	}
+}
 
-	if (!guest_owns_fp_regs())
-		__activate_traps_fpsimd32(vcpu);
+static void __deactivate_cptr_traps(struct kvm_vcpu *vcpu)
+{
+	if (has_hvhe()) {
+		u64 val = CPACR_EL1_FPEN;
+
+		if (cpus_have_final_cap(ARM64_SVE))
+			val |= CPACR_EL1_ZEN;
+		if (cpus_have_final_cap(ARM64_SME))
+			val |= CPACR_EL1_SMEN;
 
-	kvm_write_cptr_el2(val);
+		write_sysreg(val, cpacr_el1);
+	} else {
+		u64 val = CPTR_NVHE_EL2_RES1;
+
+		if (!cpus_have_final_cap(ARM64_SVE))
+			val |= CPTR_EL2_TZ;
+		if (!cpus_have_final_cap(ARM64_SME))
+			val |= CPTR_EL2_TSM;
+
+		write_sysreg(val, cptr_el2);
+	}
 }
 
 static void __activate_traps(struct kvm_vcpu *vcpu)
@@ -119,7 +144,7 @@ static void __deactivate_traps(struct kvm_vcpu *vcpu)
 
 	write_sysreg(this_cpu_ptr(&kvm_init_params)->hcr_el2, hcr_el2);
 
-	kvm_reset_cptr_el2(vcpu);
+	__deactivate_cptr_traps(vcpu);
 	write_sysreg(__kvm_hyp_host_vector, vbar_el2);
 }
 
@@ -192,34 +217,6 @@ static bool kvm_handle_pvm_sys64(struct kvm_vcpu *vcpu, u64 *exit_code)
 		kvm_handle_pvm_sysreg(vcpu, exit_code));
 }
 
-static void kvm_hyp_save_fpsimd_host(struct kvm_vcpu *vcpu)
-{
-	/*
-	 * Non-protected kvm relies on the host restoring its sve state.
-	 * Protected kvm restores the host's sve state as not to reveal that
-	 * fpsimd was used by a guest nor leak upper sve bits.
-	 */
-	if (unlikely(is_protected_kvm_enabled() && system_supports_sve())) {
-		__hyp_sve_save_host();
-
-		/* Re-enable SVE traps if not supported for the guest vcpu. */
-		if (!vcpu_has_sve(vcpu))
-			cpacr_clear_set(CPACR_EL1_ZEN, 0);
-
-	} else {
-		__fpsimd_save_state(*host_data_ptr(fpsimd_state));
-	}
-
-	if (kvm_has_fpmr(kern_hyp_va(vcpu->kvm))) {
-		u64 val = read_sysreg_s(SYS_FPMR);
-
-		if (unlikely(is_protected_kvm_enabled()))
-			*host_data_ptr(fpmr) = val;
-		else
-			**host_data_ptr(fpmr_ptr) = val;
-	}
-}
-
 static const exit_handler_fn hyp_exit_handlers[] = {
 	[0 ... ESR_ELx_EC_MAX]		= NULL,
 	[ESR_ELx_EC_CP15_32]		= kvm_hyp_handle_cp15_32,
@@ -251,19 +248,21 @@ static const exit_handler_fn *kvm_get_exit_handler_array(struct kvm_vcpu *vcpu)
 	return hyp_exit_handlers;
 }
 
-/*
- * Some guests (e.g., protected VMs) are not be allowed to run in AArch32.
- * The ARMv8 architecture does not give the hypervisor a mechanism to prevent a
- * guest from dropping to AArch32 EL0 if implemented by the CPU. If the
- * hypervisor spots a guest in such a state ensure it is handled, and don't
- * trust the host to spot or fix it.  The check below is based on the one in
- * kvm_arch_vcpu_ioctl_run().
- *
- * Returns false if the guest ran in AArch32 when it shouldn't have, and
- * thus should exit to the host, or true if a the guest run loop can continue.
- */
-static void early_exit_filter(struct kvm_vcpu *vcpu, u64 *exit_code)
+static inline bool fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code)
 {
+	const exit_handler_fn *handlers = kvm_get_exit_handler_array(vcpu);
+
+	synchronize_vcpu_pstate(vcpu, exit_code);
+
+	/*
+	 * Some guests (e.g., protected VMs) are not be allowed to run in
+	 * AArch32.  The ARMv8 architecture does not give the hypervisor a
+	 * mechanism to prevent a guest from dropping to AArch32 EL0 if
+	 * implemented by the CPU. If the hypervisor spots a guest in such a
+	 * state ensure it is handled, and don't trust the host to spot or fix
+	 * it.  The check below is based on the one in
+	 * kvm_arch_vcpu_ioctl_run().
+	 */
 	if (unlikely(vcpu_is_protected(vcpu) && vcpu_mode_is_32bit(vcpu))) {
 		/*
 		 * As we have caught the guest red-handed, decide that it isn't
@@ -276,6 +275,8 @@ static void early_exit_filter(struct kvm_vcpu *vcpu, u64 *exit_code)
 		*exit_code &= BIT(ARM_EXIT_WITH_SERROR_BIT);
 		*exit_code |= ARM_EXCEPTION_IL;
 	}
+
+	return __fixup_guest_exit(vcpu, exit_code, handlers);
 }
 
 /* Switch to the guest for legacy non-VHE systems */
diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c
index b5b9dbaf1fdd..647737d6e8d0 100644
--- a/arch/arm64/kvm/hyp/vhe/switch.c
+++ b/arch/arm64/kvm/hyp/vhe/switch.c
@@ -136,6 +136,16 @@ write:
 	write_sysreg(val, cpacr_el1);
 }
 
+static void __deactivate_cptr_traps(struct kvm_vcpu *vcpu)
+{
+	u64 val = CPACR_EL1_FPEN | CPACR_EL1_ZEN_EL1EN;
+
+	if (cpus_have_final_cap(ARM64_SME))
+		val |= CPACR_EL1_SMEN_EL1EN;
+
+	write_sysreg(val, cpacr_el1);
+}
+
 static void __activate_traps(struct kvm_vcpu *vcpu)
 {
 	u64 val;
@@ -207,7 +217,7 @@ static void __deactivate_traps(struct kvm_vcpu *vcpu)
 	 */
 	asm(ALTERNATIVE("nop", "isb", ARM64_WORKAROUND_SPECULATIVE_AT));
 
-	kvm_reset_cptr_el2(vcpu);
+	__deactivate_cptr_traps(vcpu);
 
 	if (!arm64_kernel_unmapped_at_el0())
 		host_vectors = __this_cpu_read(this_cpu_vector);
@@ -413,14 +423,6 @@ static bool kvm_hyp_handle_eret(struct kvm_vcpu *vcpu, u64 *exit_code)
 	return true;
 }
 
-static void kvm_hyp_save_fpsimd_host(struct kvm_vcpu *vcpu)
-{
-	__fpsimd_save_state(*host_data_ptr(fpsimd_state));
-
-	if (kvm_has_fpmr(vcpu->kvm))
-		**host_data_ptr(fpmr_ptr) = read_sysreg_s(SYS_FPMR);
-}
-
 static bool kvm_hyp_handle_tlbi_el2(struct kvm_vcpu *vcpu, u64 *exit_code)
 {
 	int ret = -EINVAL;
@@ -538,13 +540,10 @@ static const exit_handler_fn hyp_exit_handlers[] = {
 	[ESR_ELx_EC_MOPS]		= kvm_hyp_handle_mops,
 };
 
-static const exit_handler_fn *kvm_get_exit_handler_array(struct kvm_vcpu *vcpu)
+static inline bool fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code)
 {
-	return hyp_exit_handlers;
-}
+	synchronize_vcpu_pstate(vcpu, exit_code);
 
-static void early_exit_filter(struct kvm_vcpu *vcpu, u64 *exit_code)
-{
 	/*
 	 * If we were in HYP context on entry, adjust the PSTATE view
 	 * so that the usual helpers work correctly.
@@ -564,6 +563,8 @@ static void early_exit_filter(struct kvm_vcpu *vcpu, u64 *exit_code)
 		*vcpu_cpsr(vcpu) &= ~(PSR_MODE_MASK | PSR_MODE32_BIT);
 		*vcpu_cpsr(vcpu) |= mode;
 	}
+
+	return __fixup_guest_exit(vcpu, exit_code, hyp_exit_handlers);
 }
 
 /* Switch to the guest for VHE systems running in EL2 */
@@ -578,6 +579,8 @@ static int __kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu)
 
 	sysreg_save_host_state_vhe(host_ctxt);
 
+	fpsimd_lazy_switch_to_guest(vcpu);
+
 	/*
 	 * Note that ARM erratum 1165522 requires us to configure both stage 1
 	 * and stage 2 translation for the guest context before we clear
@@ -602,6 +605,8 @@ static int __kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu)
 
 	__deactivate_traps(vcpu);
 
+	fpsimd_lazy_switch_to_host(vcpu);
+
 	sysreg_restore_host_state_vhe(host_ctxt);
 
 	if (guest_owns_fp_regs())
diff --git a/arch/arm64/kvm/vgic/vgic-init.c b/arch/arm64/kvm/vgic/vgic-init.c
index bc7e22ab5d81..775461cf2d2d 100644
--- a/arch/arm64/kvm/vgic/vgic-init.c
+++ b/arch/arm64/kvm/vgic/vgic-init.c
@@ -34,9 +34,9 @@
  *
  * CPU Interface:
  *
- * - kvm_vgic_vcpu_init(): initialization of static data that
- *   doesn't depend on any sizing information or emulation type. No
- *   allocation is allowed there.
+ * - kvm_vgic_vcpu_init(): initialization of static data that doesn't depend
+ *   on any sizing information. Private interrupts are allocated if not
+ *   already allocated at vgic-creation time.
  */
 
 /* EARLY INIT */
@@ -58,6 +58,8 @@ void kvm_vgic_early_init(struct kvm *kvm)
 
 /* CREATION */
 
+static int vgic_allocate_private_irqs_locked(struct kvm_vcpu *vcpu, u32 type);
+
 /**
  * kvm_vgic_create: triggered by the instantiation of the VGIC device by
  * user space, either through the legacy KVM_CREATE_IRQCHIP ioctl (v2 only)
@@ -112,6 +114,22 @@ int kvm_vgic_create(struct kvm *kvm, u32 type)
 		goto out_unlock;
 	}
 
+	kvm_for_each_vcpu(i, vcpu, kvm) {
+		ret = vgic_allocate_private_irqs_locked(vcpu, type);
+		if (ret)
+			break;
+	}
+
+	if (ret) {
+		kvm_for_each_vcpu(i, vcpu, kvm) {
+			struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
+			kfree(vgic_cpu->private_irqs);
+			vgic_cpu->private_irqs = NULL;
+		}
+
+		goto out_unlock;
+	}
+
 	kvm->arch.vgic.in_kernel = true;
 	kvm->arch.vgic.vgic_model = type;
 
@@ -180,7 +198,7 @@ static int kvm_vgic_dist_init(struct kvm *kvm, unsigned int nr_spis)
 	return 0;
 }
 
-static int vgic_allocate_private_irqs_locked(struct kvm_vcpu *vcpu)
+static int vgic_allocate_private_irqs_locked(struct kvm_vcpu *vcpu, u32 type)
 {
 	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
 	int i;
@@ -218,17 +236,28 @@ static int vgic_allocate_private_irqs_locked(struct kvm_vcpu *vcpu)
 			/* PPIs */
 			irq->config = VGIC_CONFIG_LEVEL;
 		}
+
+		switch (type) {
+		case KVM_DEV_TYPE_ARM_VGIC_V3:
+			irq->group = 1;
+			irq->mpidr = kvm_vcpu_get_mpidr_aff(vcpu);
+			break;
+		case KVM_DEV_TYPE_ARM_VGIC_V2:
+			irq->group = 0;
+			irq->targets = BIT(vcpu->vcpu_id);
+			break;
+		}
 	}
 
 	return 0;
 }
 
-static int vgic_allocate_private_irqs(struct kvm_vcpu *vcpu)
+static int vgic_allocate_private_irqs(struct kvm_vcpu *vcpu, u32 type)
 {
 	int ret;
 
 	mutex_lock(&vcpu->kvm->arch.config_lock);
-	ret = vgic_allocate_private_irqs_locked(vcpu);
+	ret = vgic_allocate_private_irqs_locked(vcpu, type);
 	mutex_unlock(&vcpu->kvm->arch.config_lock);
 
 	return ret;
@@ -258,7 +287,7 @@ int kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu)
 	if (!irqchip_in_kernel(vcpu->kvm))
 		return 0;
 
-	ret = vgic_allocate_private_irqs(vcpu);
+	ret = vgic_allocate_private_irqs(vcpu, dist->vgic_model);
 	if (ret)
 		return ret;
 
@@ -295,7 +324,7 @@ int vgic_init(struct kvm *kvm)
 {
 	struct vgic_dist *dist = &kvm->arch.vgic;
 	struct kvm_vcpu *vcpu;
-	int ret = 0, i;
+	int ret = 0;
 	unsigned long idx;
 
 	lockdep_assert_held(&kvm->arch.config_lock);
@@ -315,35 +344,6 @@ int vgic_init(struct kvm *kvm)
 	if (ret)
 		goto out;
 
-	/* Initialize groups on CPUs created before the VGIC type was known */
-	kvm_for_each_vcpu(idx, vcpu, kvm) {
-		ret = vgic_allocate_private_irqs_locked(vcpu);
-		if (ret)
-			goto out;
-
-		for (i = 0; i < VGIC_NR_PRIVATE_IRQS; i++) {
-			struct vgic_irq *irq = vgic_get_vcpu_irq(vcpu, i);
-
-			switch (dist->vgic_model) {
-			case KVM_DEV_TYPE_ARM_VGIC_V3:
-				irq->group = 1;
-				irq->mpidr = kvm_vcpu_get_mpidr_aff(vcpu);
-				break;
-			case KVM_DEV_TYPE_ARM_VGIC_V2:
-				irq->group = 0;
-				irq->targets = 1U << idx;
-				break;
-			default:
-				ret = -EINVAL;
-			}
-
-			vgic_put_irq(kvm, irq);
-
-			if (ret)
-				goto out;
-		}
-	}
-
 	/*
 	 * If we have GICv4.1 enabled, unconditionally request enable the
 	 * v4 support so that we get HW-accelerated vSGIs. Otherwise, only
diff --git a/arch/arm64/kvm/vmid.c b/arch/arm64/kvm/vmid.c
index 806223b7022a..7fe8ba1a2851 100644
--- a/arch/arm64/kvm/vmid.c
+++ b/arch/arm64/kvm/vmid.c
@@ -135,11 +135,10 @@ void kvm_arm_vmid_clear_active(void)
 	atomic64_set(this_cpu_ptr(&active_vmids), VMID_ACTIVE_INVALID);
 }
 
-bool kvm_arm_vmid_update(struct kvm_vmid *kvm_vmid)
+void kvm_arm_vmid_update(struct kvm_vmid *kvm_vmid)
 {
 	unsigned long flags;
 	u64 vmid, old_active_vmid;
-	bool updated = false;
 
 	vmid = atomic64_read(&kvm_vmid->id);
 
@@ -157,21 +156,17 @@ bool kvm_arm_vmid_update(struct kvm_vmid *kvm_vmid)
 	if (old_active_vmid != 0 && vmid_gen_match(vmid) &&
 	    0 != atomic64_cmpxchg_relaxed(this_cpu_ptr(&active_vmids),
 					  old_active_vmid, vmid))
-		return false;
+		return;
 
 	raw_spin_lock_irqsave(&cpu_vmid_lock, flags);
 
 	/* Check that our VMID belongs to the current generation. */
 	vmid = atomic64_read(&kvm_vmid->id);
-	if (!vmid_gen_match(vmid)) {
+	if (!vmid_gen_match(vmid))
 		vmid = new_vmid(kvm_vmid);
-		updated = true;
-	}
 
 	atomic64_set(this_cpu_ptr(&active_vmids), vmid);
 	raw_spin_unlock_irqrestore(&cpu_vmid_lock, flags);
-
-	return updated;
 }
 
 /*
diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
index 98a2a0e64e25..b3a7fafe8892 100644
--- a/arch/arm64/mm/hugetlbpage.c
+++ b/arch/arm64/mm/hugetlbpage.c
@@ -100,20 +100,11 @@ static int find_num_contig(struct mm_struct *mm, unsigned long addr,
 
 static inline int num_contig_ptes(unsigned long size, size_t *pgsize)
 {
-	int contig_ptes = 0;
+	int contig_ptes = 1;
 
 	*pgsize = size;
 
 	switch (size) {
-#ifndef __PAGETABLE_PMD_FOLDED
-	case PUD_SIZE:
-		if (pud_sect_supported())
-			contig_ptes = 1;
-		break;
-#endif
-	case PMD_SIZE:
-		contig_ptes = 1;
-		break;
 	case CONT_PMD_SIZE:
 		*pgsize = PMD_SIZE;
 		contig_ptes = CONT_PMDS;
@@ -122,6 +113,8 @@ static inline int num_contig_ptes(unsigned long size, size_t *pgsize)
 		*pgsize = PAGE_SIZE;
 		contig_ptes = CONT_PTES;
 		break;
+	default:
+		WARN_ON(!__hugetlb_valid_size(size));
 	}
 
 	return contig_ptes;
@@ -163,24 +156,23 @@ static pte_t get_clear_contig(struct mm_struct *mm,
 			     unsigned long pgsize,
 			     unsigned long ncontig)
 {
-	pte_t orig_pte = __ptep_get(ptep);
-	unsigned long i;
-
-	for (i = 0; i < ncontig; i++, addr += pgsize, ptep++) {
-		pte_t pte = __ptep_get_and_clear(mm, addr, ptep);
-
-		/*
-		 * If HW_AFDBM is enabled, then the HW could turn on
-		 * the dirty or accessed bit for any page in the set,
-		 * so check them all.
-		 */
-		if (pte_dirty(pte))
-			orig_pte = pte_mkdirty(orig_pte);
-
-		if (pte_young(pte))
-			orig_pte = pte_mkyoung(orig_pte);
+	pte_t pte, tmp_pte;
+	bool present;
+
+	pte = __ptep_get_and_clear(mm, addr, ptep);
+	present = pte_present(pte);
+	while (--ncontig) {
+		ptep++;
+		addr += pgsize;
+		tmp_pte = __ptep_get_and_clear(mm, addr, ptep);
+		if (present) {
+			if (pte_dirty(tmp_pte))
+				pte = pte_mkdirty(pte);
+			if (pte_young(tmp_pte))
+				pte = pte_mkyoung(pte);
+		}
 	}
-	return orig_pte;
+	return pte;
 }
 
 static pte_t get_clear_contig_flush(struct mm_struct *mm,
@@ -396,18 +388,13 @@ void huge_pte_clear(struct mm_struct *mm, unsigned long addr,
 		__pte_clear(mm, addr, ptep);
 }
 
-pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
-			      unsigned long addr, pte_t *ptep)
+pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
+			      pte_t *ptep, unsigned long sz)
 {
 	int ncontig;
 	size_t pgsize;
-	pte_t orig_pte = __ptep_get(ptep);
-
-	if (!pte_cont(orig_pte))
-		return __ptep_get_and_clear(mm, addr, ptep);
-
-	ncontig = find_num_contig(mm, addr, ptep, &pgsize);
 
+	ncontig = num_contig_ptes(sz, &pgsize);
 	return get_clear_contig(mm, addr, ptep, pgsize, ncontig);
 }
 
@@ -549,6 +536,8 @@ bool __init arch_hugetlb_valid_size(unsigned long size)
 
 pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep)
 {
+	unsigned long psize = huge_page_size(hstate_vma(vma));
+
 	if (alternative_has_cap_unlikely(ARM64_WORKAROUND_2645198)) {
 		/*
 		 * Break-before-make (BBM) is required for all user space mappings
@@ -558,7 +547,7 @@ pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr
 		if (pte_user_exec(__ptep_get(ptep)))
 			return huge_ptep_clear_flush(vma, addr, ptep);
 	}
-	return huge_ptep_get_and_clear(vma->vm_mm, addr, ptep);
+	return huge_ptep_get_and_clear(vma->vm_mm, addr, ptep, psize);
 }
 
 void huge_ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep,
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index 9c0b8d9558fc..ccdef53872a0 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -279,12 +279,7 @@ void __init arm64_memblock_init(void)
 
 	if (IS_ENABLED(CONFIG_RANDOMIZE_BASE)) {
 		extern u16 memstart_offset_seed;
-
-		/*
-		 * Use the sanitised version of id_aa64mmfr0_el1 so that linear
-		 * map randomization can be enabled by shrinking the IPA space.
-		 */
-		u64 mmfr0 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1);
+		u64 mmfr0 = read_cpuid(ID_AA64MMFR0_EL1);
 		int parange = cpuid_feature_extract_unsigned_field(
 					mmfr0, ID_AA64MMFR0_EL1_PARANGE_SHIFT);
 		s64 range = linear_region_size -
diff --git a/arch/arm64/mm/trans_pgd.c b/arch/arm64/mm/trans_pgd.c
index 19c67ed1a21f..18543b603c77 100644
--- a/arch/arm64/mm/trans_pgd.c
+++ b/arch/arm64/mm/trans_pgd.c
@@ -162,6 +162,13 @@ static int copy_p4d(struct trans_pgd_info *info, pgd_t *dst_pgdp,
 	unsigned long next;
 	unsigned long addr = start;
 
+	if (pgd_none(READ_ONCE(*dst_pgdp))) {
+		dst_p4dp = trans_alloc(info);
+		if (!dst_p4dp)
+			return -ENOMEM;
+		pgd_populate(NULL, dst_pgdp, dst_p4dp);
+	}
+
 	dst_p4dp = p4d_offset(dst_pgdp, start);
 	src_p4dp = p4d_offset(src_pgdp, start);
 	do {
diff --git a/arch/loongarch/include/asm/cpu-info.h b/arch/loongarch/include/asm/cpu-info.h
index 35e0a230a484..7f5bc0ad9d50 100644
--- a/arch/loongarch/include/asm/cpu-info.h
+++ b/arch/loongarch/include/asm/cpu-info.h
@@ -76,27 +76,6 @@ extern const char *__cpu_full_name[];
 #define cpu_family_string()	__cpu_family[raw_smp_processor_id()]
 #define cpu_full_name_string()	__cpu_full_name[raw_smp_processor_id()]
 
-struct seq_file;
-struct notifier_block;
-
-extern int register_proc_cpuinfo_notifier(struct notifier_block *nb);
-extern int proc_cpuinfo_notifier_call_chain(unsigned long val, void *v);
-
-#define proc_cpuinfo_notifier(fn, pri)					\
-({									\
-	static struct notifier_block fn##_nb = {			\
-		.notifier_call = fn,					\
-		.priority = pri						\
-	};								\
-									\
-	register_proc_cpuinfo_notifier(&fn##_nb);			\
-})
-
-struct proc_cpuinfo_notifier_args {
-	struct seq_file *m;
-	unsigned long n;
-};
-
 static inline bool cpus_are_siblings(int cpua, int cpub)
 {
 	struct cpuinfo_loongarch *infoa = &cpu_data[cpua];
diff --git a/arch/loongarch/include/asm/hugetlb.h b/arch/loongarch/include/asm/hugetlb.h
index c8e4057734d0..4dc4b3e04225 100644
--- a/arch/loongarch/include/asm/hugetlb.h
+++ b/arch/loongarch/include/asm/hugetlb.h
@@ -36,7 +36,8 @@ static inline void huge_pte_clear(struct mm_struct *mm, unsigned long addr,
 
 #define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR
 static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
-					    unsigned long addr, pte_t *ptep)
+					    unsigned long addr, pte_t *ptep,
+					    unsigned long sz)
 {
 	pte_t clear;
 	pte_t pte = ptep_get(ptep);
@@ -51,8 +52,9 @@ static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
 					  unsigned long addr, pte_t *ptep)
 {
 	pte_t pte;
+	unsigned long sz = huge_page_size(hstate_vma(vma));
 
-	pte = huge_ptep_get_and_clear(vma->vm_mm, addr, ptep);
+	pte = huge_ptep_get_and_clear(vma->vm_mm, addr, ptep, sz);
 	flush_tlb_page(vma, addr);
 	return pte;
 }
diff --git a/arch/loongarch/include/asm/smp.h b/arch/loongarch/include/asm/smp.h
index 3383c9d24e94..b87d1d5e5890 100644
--- a/arch/loongarch/include/asm/smp.h
+++ b/arch/loongarch/include/asm/smp.h
@@ -77,6 +77,8 @@ extern int __cpu_logical_map[NR_CPUS];
 #define SMP_IRQ_WORK		BIT(ACTION_IRQ_WORK)
 #define SMP_CLEAR_VECTOR	BIT(ACTION_CLEAR_VECTOR)
 
+struct seq_file;
+
 struct secondary_data {
 	unsigned long stack;
 	unsigned long thread_info;
diff --git a/arch/loongarch/kernel/acpi.c b/arch/loongarch/kernel/acpi.c
index 382a09a7152c..1120ac2824f6 100644
--- a/arch/loongarch/kernel/acpi.c
+++ b/arch/loongarch/kernel/acpi.c
@@ -249,18 +249,6 @@ static __init int setup_node(int pxm)
 	return acpi_map_pxm_to_node(pxm);
 }
 
-/*
- * Callback for SLIT parsing.  pxm_to_node() returns NUMA_NO_NODE for
- * I/O localities since SRAT does not list them.  I/O localities are
- * not supported at this point.
- */
-unsigned int numa_distance_cnt;
-
-static inline unsigned int get_numa_distances_cnt(struct acpi_table_slit *slit)
-{
-	return slit->locality_count;
-}
-
 void __init numa_set_distance(int from, int to, int distance)
 {
 	if ((u8)distance != distance || (from == to && distance != LOCAL_DISTANCE)) {
diff --git a/arch/loongarch/kernel/genex.S b/arch/loongarch/kernel/genex.S
index 86d5d90ebefe..4f0912141781 100644
--- a/arch/loongarch/kernel/genex.S
+++ b/arch/loongarch/kernel/genex.S
@@ -18,16 +18,19 @@
 
 	.align	5
 SYM_FUNC_START(__arch_cpu_idle)
-	/* start of rollback region */
-	LONG_L	t0, tp, TI_FLAGS
-	nop
-	andi	t0, t0, _TIF_NEED_RESCHED
-	bnez	t0, 1f
-	nop
-	nop
-	nop
+	/* start of idle interrupt region */
+	ori	t0, zero, CSR_CRMD_IE
+	/* idle instruction needs irq enabled */
+	csrxchg	t0, t0, LOONGARCH_CSR_CRMD
+	/*
+	 * If an interrupt lands here; between enabling interrupts above and
+	 * going idle on the next instruction, we must *NOT* go idle since the
+	 * interrupt could have set TIF_NEED_RESCHED or caused an timer to need
+	 * reprogramming. Fall through -- see handle_vint() below -- and have
+	 * the idle loop take care of things.
+	 */
 	idle	0
-	/* end of rollback region */
+	/* end of idle interrupt region */
 1:	jr	ra
 SYM_FUNC_END(__arch_cpu_idle)
 
@@ -35,11 +38,10 @@ SYM_CODE_START(handle_vint)
 	UNWIND_HINT_UNDEFINED
 	BACKUP_T0T1
 	SAVE_ALL
-	la_abs	t1, __arch_cpu_idle
+	la_abs	t1, 1b
 	LONG_L	t0, sp, PT_ERA
-	/* 32 byte rollback region */
-	ori	t0, t0, 0x1f
-	xori	t0, t0, 0x1f
+	/* 3 instructions idle interrupt region */
+	ori	t0, t0, 0b1100
 	bne	t0, t1, 1f
 	LONG_S	t0, sp, PT_ERA
 1:	move	a0, sp
diff --git a/arch/loongarch/kernel/idle.c b/arch/loongarch/kernel/idle.c
index 0b5dd2faeb90..54b247d8cdb6 100644
--- a/arch/loongarch/kernel/idle.c
+++ b/arch/loongarch/kernel/idle.c
@@ -11,7 +11,6 @@
 
 void __cpuidle arch_cpu_idle(void)
 {
-	raw_local_irq_enable();
-	__arch_cpu_idle(); /* idle instruction needs irq enabled */
+	__arch_cpu_idle();
 	raw_local_irq_disable();
 }
diff --git a/arch/loongarch/kernel/machine_kexec.c b/arch/loongarch/kernel/machine_kexec.c
index 8ae641dc53bb..f9381800e291 100644
--- a/arch/loongarch/kernel/machine_kexec.c
+++ b/arch/loongarch/kernel/machine_kexec.c
@@ -126,14 +126,14 @@ void kexec_reboot(void)
 	/* All secondary cpus go to kexec_smp_wait */
 	if (smp_processor_id() > 0) {
 		relocated_kexec_smp_wait(NULL);
-		unreachable();
+		BUG();
 	}
 #endif
 
 	do_kexec = (void *)reboot_code_buffer;
 	do_kexec(efi_boot, cmdline_ptr, systable_ptr, start_addr, first_ind_entry);
 
-	unreachable();
+	BUG();
 }
 
 
diff --git a/arch/loongarch/kernel/proc.c b/arch/loongarch/kernel/proc.c
index 6ce46d92f1f1..cea30768ae92 100644
--- a/arch/loongarch/kernel/proc.c
+++ b/arch/loongarch/kernel/proc.c
@@ -13,28 +13,12 @@
 #include <asm/processor.h>
 #include <asm/time.h>
 
-/*
- * No lock; only written during early bootup by CPU 0.
- */
-static RAW_NOTIFIER_HEAD(proc_cpuinfo_chain);
-
-int __ref register_proc_cpuinfo_notifier(struct notifier_block *nb)
-{
-	return raw_notifier_chain_register(&proc_cpuinfo_chain, nb);
-}
-
-int proc_cpuinfo_notifier_call_chain(unsigned long val, void *v)
-{
-	return raw_notifier_call_chain(&proc_cpuinfo_chain, val, v);
-}
-
 static int show_cpuinfo(struct seq_file *m, void *v)
 {
 	unsigned long n = (unsigned long) v - 1;
 	unsigned int isa = cpu_data[n].isa_level;
 	unsigned int version = cpu_data[n].processor_id & 0xff;
 	unsigned int fp_version = cpu_data[n].fpu_vers;
-	struct proc_cpuinfo_notifier_args proc_cpuinfo_notifier_args;
 
 #ifdef CONFIG_SMP
 	if (!cpu_online(n))
@@ -91,20 +75,13 @@ static int show_cpuinfo(struct seq_file *m, void *v)
 	if (cpu_has_lbt_mips)	seq_printf(m, " lbt_mips");
 	seq_printf(m, "\n");
 
-	seq_printf(m, "Hardware Watchpoint\t: %s",
-		      cpu_has_watch ? "yes, " : "no\n");
+	seq_printf(m, "Hardware Watchpoint\t: %s", str_yes_no(cpu_has_watch));
 	if (cpu_has_watch) {
-		seq_printf(m, "iwatch count: %d, dwatch count: %d\n",
+		seq_printf(m, ", iwatch count: %d, dwatch count: %d",
 		      cpu_data[n].watch_ireg_count, cpu_data[n].watch_dreg_count);
 	}
 
-	proc_cpuinfo_notifier_args.m = m;
-	proc_cpuinfo_notifier_args.n = n;
-
-	raw_notifier_call_chain(&proc_cpuinfo_chain, 0,
-				&proc_cpuinfo_notifier_args);
-
-	seq_printf(m, "\n");
+	seq_printf(m, "\n\n");
 
 	return 0;
 }
diff --git a/arch/loongarch/kernel/reset.c b/arch/loongarch/kernel/reset.c
index 1ef8c6383535..de8fa5a8a825 100644
--- a/arch/loongarch/kernel/reset.c
+++ b/arch/loongarch/kernel/reset.c
@@ -33,7 +33,7 @@ void machine_halt(void)
 	console_flush_on_panic(CONSOLE_FLUSH_PENDING);
 
 	while (true) {
-		__arch_cpu_idle();
+		__asm__ __volatile__("idle 0" : : : "memory");
 	}
 }
 
@@ -53,7 +53,7 @@ void machine_power_off(void)
 #endif
 
 	while (true) {
-		__arch_cpu_idle();
+		__asm__ __volatile__("idle 0" : : : "memory");
 	}
 }
 
@@ -74,6 +74,6 @@ void machine_restart(char *command)
 		acpi_reboot();
 
 	while (true) {
-		__arch_cpu_idle();
+		__asm__ __volatile__("idle 0" : : : "memory");
 	}
 }
diff --git a/arch/loongarch/kernel/setup.c b/arch/loongarch/kernel/setup.c
index edcfdfcad7d2..90cb3ca96f08 100644
--- a/arch/loongarch/kernel/setup.c
+++ b/arch/loongarch/kernel/setup.c
@@ -387,6 +387,9 @@ static void __init check_kernel_sections_mem(void)
  */
 static void __init arch_mem_init(char **cmdline_p)
 {
+	/* Recalculate max_low_pfn for "mem=xxx" */
+	max_pfn = max_low_pfn = PHYS_PFN(memblock_end_of_DRAM());
+
 	if (usermem)
 		pr_info("User-defined physical RAM map overwrite\n");
 
diff --git a/arch/loongarch/kernel/smp.c b/arch/loongarch/kernel/smp.c
index fbf747447f13..4b24589c0b56 100644
--- a/arch/loongarch/kernel/smp.c
+++ b/arch/loongarch/kernel/smp.c
@@ -19,6 +19,7 @@
 #include <linux/smp.h>
 #include <linux/threads.h>
 #include <linux/export.h>
+#include <linux/suspend.h>
 #include <linux/syscore_ops.h>
 #include <linux/time.h>
 #include <linux/tracepoint.h>
@@ -423,7 +424,7 @@ void loongson_cpu_die(unsigned int cpu)
 	mb();
 }
 
-void __noreturn arch_cpu_idle_dead(void)
+static void __noreturn idle_play_dead(void)
 {
 	register uint64_t addr;
 	register void (*init_fn)(void);
@@ -447,6 +448,50 @@ void __noreturn arch_cpu_idle_dead(void)
 	BUG();
 }
 
+#ifdef CONFIG_HIBERNATION
+static void __noreturn poll_play_dead(void)
+{
+	register uint64_t addr;
+	register void (*init_fn)(void);
+
+	idle_task_exit();
+	__this_cpu_write(cpu_state, CPU_DEAD);
+
+	__smp_mb();
+	do {
+		__asm__ __volatile__("nop\n\t");
+		addr = iocsr_read64(LOONGARCH_IOCSR_MBUF0);
+	} while (addr == 0);
+
+	init_fn = (void *)TO_CACHE(addr);
+	iocsr_write32(0xffffffff, LOONGARCH_IOCSR_IPI_CLEAR);
+
+	init_fn();
+	BUG();
+}
+#endif
+
+static void (*play_dead)(void) = idle_play_dead;
+
+void __noreturn arch_cpu_idle_dead(void)
+{
+	play_dead();
+	BUG(); /* play_dead() doesn't return */
+}
+
+#ifdef CONFIG_HIBERNATION
+int hibernate_resume_nonboot_cpu_disable(void)
+{
+	int ret;
+
+	play_dead = poll_play_dead;
+	ret = suspend_disable_secondary_cpus();
+	play_dead = idle_play_dead;
+
+	return ret;
+}
+#endif
+
 #endif
 
 /*
diff --git a/arch/loongarch/kvm/exit.c b/arch/loongarch/kvm/exit.c
index c1e8ec5b941b..ea321403644a 100644
--- a/arch/loongarch/kvm/exit.c
+++ b/arch/loongarch/kvm/exit.c
@@ -669,6 +669,12 @@ static int kvm_handle_rdwr_fault(struct kvm_vcpu *vcpu, bool write)
 	struct kvm_run *run = vcpu->run;
 	unsigned long badv = vcpu->arch.badv;
 
+	/* Inject ADE exception if exceed max GPA size */
+	if (unlikely(badv >= vcpu->kvm->arch.gpa_size)) {
+		kvm_queue_exception(vcpu, EXCCODE_ADE, EXSUBCODE_ADEM);
+		return RESUME_GUEST;
+	}
+
 	ret = kvm_handle_mm_fault(vcpu, badv, write);
 	if (ret) {
 		/* Treat as MMIO */
diff --git a/arch/loongarch/kvm/main.c b/arch/loongarch/kvm/main.c
index bf9268bf26d5..b6864d6e5ec8 100644
--- a/arch/loongarch/kvm/main.c
+++ b/arch/loongarch/kvm/main.c
@@ -303,9 +303,9 @@ int kvm_arch_enable_virtualization_cpu(void)
 	 * TOE=0:       Trap on Exception.
 	 * TIT=0:       Trap on Timer.
 	 */
-	if (env & CSR_GCFG_GCIP_ALL)
+	if (env & CSR_GCFG_GCIP_SECURE)
 		gcfg |= CSR_GCFG_GCI_SECURE;
-	if (env & CSR_GCFG_MATC_ROOT)
+	if (env & CSR_GCFG_MATP_ROOT)
 		gcfg |= CSR_GCFG_MATC_ROOT;
 
 	write_csr_gcfg(gcfg);
@@ -317,6 +317,13 @@ int kvm_arch_enable_virtualization_cpu(void)
 	kvm_debug("GCFG:%lx GSTAT:%lx GINTC:%lx GTLBC:%lx",
 		  read_csr_gcfg(), read_csr_gstat(), read_csr_gintc(), read_csr_gtlbc());
 
+	/*
+	 * HW Guest CSR registers are lost after CPU suspend and resume.
+	 * Clear last_vcpu so that Guest CSR registers forced to reload
+	 * from vCPU SW state.
+	 */
+	this_cpu_ptr(vmcs)->last_vcpu = NULL;
+
 	return 0;
 }
 
diff --git a/arch/loongarch/kvm/switch.S b/arch/loongarch/kvm/switch.S
index 0c292f818492..1be185e94807 100644
--- a/arch/loongarch/kvm/switch.S
+++ b/arch/loongarch/kvm/switch.S
@@ -85,7 +85,7 @@
 	 * Guest CRMD comes from separate GCSR_CRMD register
 	 */
 	ori	t0, zero, CSR_PRMD_PIE
-	csrxchg	t0, t0,   LOONGARCH_CSR_PRMD
+	csrwr	t0, LOONGARCH_CSR_PRMD
 
 	/* Set PVM bit to setup ertn to guest context */
 	ori	t0, zero, CSR_GSTAT_PVM
diff --git a/arch/loongarch/kvm/vcpu.c b/arch/loongarch/kvm/vcpu.c
index fb72095c8077..9e1a9b4aa4c6 100644
--- a/arch/loongarch/kvm/vcpu.c
+++ b/arch/loongarch/kvm/vcpu.c
@@ -311,7 +311,7 @@ static int kvm_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu)
 {
 	int ret = RESUME_GUEST;
 	unsigned long estat = vcpu->arch.host_estat;
-	u32 intr = estat & 0x1fff; /* Ignore NMI */
+	u32 intr = estat & CSR_ESTAT_IS;
 	u32 ecode = (estat & CSR_ESTAT_EXC) >> CSR_ESTAT_EXC_SHIFT;
 
 	vcpu->mode = OUTSIDE_GUEST_MODE;
@@ -1548,9 +1548,6 @@ static int _kvm_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 
 	/* Restore timer state regardless */
 	kvm_restore_timer(vcpu);
-
-	/* Control guest page CCA attribute */
-	change_csr_gcfg(CSR_GCFG_MATC_MASK, CSR_GCFG_MATC_ROOT);
 	kvm_make_request(KVM_REQ_STEAL_UPDATE, vcpu);
 
 	/* Restore hardware PMU CSRs */
diff --git a/arch/loongarch/kvm/vm.c b/arch/loongarch/kvm/vm.c
index b8b3e1972d6e..edccfc8c9cd8 100644
--- a/arch/loongarch/kvm/vm.c
+++ b/arch/loongarch/kvm/vm.c
@@ -48,7 +48,11 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 	if (kvm_pvtime_supported())
 		kvm->arch.pv_features |= BIT(KVM_FEATURE_STEAL_TIME);
 
-	kvm->arch.gpa_size = BIT(cpu_vabits - 1);
+	/*
+	 * cpu_vabits means user address space only (a half of total).
+	 * GPA size of VM is the same with the size of user address space.
+	 */
+	kvm->arch.gpa_size = BIT(cpu_vabits);
 	kvm->arch.root_level = CONFIG_PGTABLE_LEVELS - 1;
 	kvm->arch.invalid_ptes[0] = 0;
 	kvm->arch.invalid_ptes[1] = (unsigned long)invalid_pte_table;
diff --git a/arch/loongarch/lib/csum.c b/arch/loongarch/lib/csum.c
index a5e84b403c3b..df309ae4045d 100644
--- a/arch/loongarch/lib/csum.c
+++ b/arch/loongarch/lib/csum.c
@@ -25,7 +25,7 @@ unsigned int __no_sanitize_address do_csum(const unsigned char *buff, int len)
 	const u64 *ptr;
 	u64 data, sum64 = 0;
 
-	if (unlikely(len == 0))
+	if (unlikely(len <= 0))
 		return 0;
 
 	offset = (unsigned long)buff & 7;
diff --git a/arch/loongarch/mm/mmap.c b/arch/loongarch/mm/mmap.c
index 914e82ff3f65..1df9e99582cc 100644
--- a/arch/loongarch/mm/mmap.c
+++ b/arch/loongarch/mm/mmap.c
@@ -3,6 +3,7 @@
  * Copyright (C) 2020-2022 Loongson Technology Corporation Limited
  */
 #include <linux/export.h>
+#include <linux/hugetlb.h>
 #include <linux/io.h>
 #include <linux/kfence.h>
 #include <linux/memblock.h>
@@ -63,8 +64,11 @@ static unsigned long arch_get_unmapped_area_common(struct file *filp,
 	}
 
 	info.length = len;
-	info.align_mask = do_color_align ? (PAGE_MASK & SHM_ALIGN_MASK) : 0;
 	info.align_offset = pgoff << PAGE_SHIFT;
+	if (filp && is_file_hugepages(filp))
+		info.align_mask = huge_page_mask_align(filp);
+	else
+		info.align_mask = do_color_align ? (PAGE_MASK & SHM_ALIGN_MASK) : 0;
 
 	if (dir == DOWN) {
 		info.flags = VM_UNMAPPED_AREA_TOPDOWN;
diff --git a/arch/loongarch/mm/pageattr.c b/arch/loongarch/mm/pageattr.c
index bf8678248444..99165903908a 100644
--- a/arch/loongarch/mm/pageattr.c
+++ b/arch/loongarch/mm/pageattr.c
@@ -3,6 +3,7 @@
  * Copyright (C) 2024 Loongson Technology Corporation Limited
  */
 
+#include <linux/memblock.h>
 #include <linux/pagewalk.h>
 #include <linux/pgtable.h>
 #include <asm/set_memory.h>
@@ -167,7 +168,7 @@ bool kernel_page_present(struct page *page)
 	unsigned long addr = (unsigned long)page_address(page);
 
 	if (addr < vm_map_base)
-		return true;
+		return memblock_is_memory(__pa(addr));
 
 	pgd = pgd_offset_k(addr);
 	if (pgd_none(pgdp_get(pgd)))
diff --git a/arch/m68k/include/asm/sun3_pgalloc.h b/arch/m68k/include/asm/sun3_pgalloc.h
index f1ae4ed890db..80afc3a18724 100644
--- a/arch/m68k/include/asm/sun3_pgalloc.h
+++ b/arch/m68k/include/asm/sun3_pgalloc.h
@@ -44,8 +44,10 @@ static inline pgd_t * pgd_alloc(struct mm_struct *mm)
 	pgd_t *new_pgd;
 
 	new_pgd = __pgd_alloc(mm, 0);
-	memcpy(new_pgd, swapper_pg_dir, PAGE_SIZE);
-	memset(new_pgd, 0, (PAGE_OFFSET >> PGDIR_SHIFT));
+	if (likely(new_pgd != NULL)) {
+		memcpy(new_pgd, swapper_pg_dir, PAGE_SIZE);
+		memset(new_pgd, 0, (PAGE_OFFSET >> PGDIR_SHIFT));
+	}
 	return new_pgd;
 }
 
diff --git a/arch/mips/boot/tools/relocs.c b/arch/mips/boot/tools/relocs.c
index a88d66c46d7f..9863e1d5c62e 100644
--- a/arch/mips/boot/tools/relocs.c
+++ b/arch/mips/boot/tools/relocs.c
@@ -468,6 +468,8 @@ static void walk_relocs(int (*process)(struct section *sec, Elf_Rel *rel,
 			Elf_Sym *sym, const char *symname))
 {
 	int i;
+	struct section *extab_sec = sec_lookup("__ex_table");
+	int extab_index = extab_sec ? extab_sec - secs : -1;
 
 	/* Walk through the relocations */
 	for (i = 0; i < ehdr.e_shnum; i++) {
@@ -480,6 +482,9 @@ static void walk_relocs(int (*process)(struct section *sec, Elf_Rel *rel,
 		if (sec->shdr.sh_type != SHT_REL_TYPE)
 			continue;
 
+		if (sec->shdr.sh_info == extab_index)
+			continue;
+
 		sec_symtab  = sec->link;
 		sec_applies = &secs[sec->shdr.sh_info];
 		if (!(sec_applies->shdr.sh_flags & SHF_ALLOC))
diff --git a/arch/mips/include/asm/hugetlb.h b/arch/mips/include/asm/hugetlb.h
index d0a86ce83de9..fbc71ddcf0f6 100644
--- a/arch/mips/include/asm/hugetlb.h
+++ b/arch/mips/include/asm/hugetlb.h
@@ -27,7 +27,8 @@ static inline int prepare_hugepage_range(struct file *file,
 
 #define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR
 static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
-					    unsigned long addr, pte_t *ptep)
+					    unsigned long addr, pte_t *ptep,
+					    unsigned long sz)
 {
 	pte_t clear;
 	pte_t pte = *ptep;
@@ -42,13 +43,14 @@ static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
 					  unsigned long addr, pte_t *ptep)
 {
 	pte_t pte;
+	unsigned long sz = huge_page_size(hstate_vma(vma));
 
 	/*
 	 * clear the huge pte entry firstly, so that the other smp threads will
 	 * not get old pte entry after finishing flush_tlb_page and before
 	 * setting new huge pte entry
 	 */
-	pte = huge_ptep_get_and_clear(vma->vm_mm, addr, ptep);
+	pte = huge_ptep_get_and_clear(vma->vm_mm, addr, ptep, sz);
 	flush_tlb_page(vma, addr);
 	return pte;
 }
diff --git a/arch/mips/include/asm/ptrace.h b/arch/mips/include/asm/ptrace.h
index 4a2b40ce39e0..85fa9962266a 100644
--- a/arch/mips/include/asm/ptrace.h
+++ b/arch/mips/include/asm/ptrace.h
@@ -27,8 +27,8 @@
  */
 struct pt_regs {
 #ifdef CONFIG_32BIT
-	/* Pad bytes for argument save space on the stack. */
-	unsigned long pad0[8];
+	/* Saved syscall stack arguments; entries 0-3 unused. */
+	unsigned long args[8];
 #endif
 
 	/* Saved main processor registers. */
diff --git a/arch/mips/include/asm/syscall.h b/arch/mips/include/asm/syscall.h
index ebdf4d910af2..056aa1b713e2 100644
--- a/arch/mips/include/asm/syscall.h
+++ b/arch/mips/include/asm/syscall.h
@@ -57,37 +57,21 @@ static inline void mips_syscall_update_nr(struct task_struct *task,
 static inline void mips_get_syscall_arg(unsigned long *arg,
 	struct task_struct *task, struct pt_regs *regs, unsigned int n)
 {
-	unsigned long usp __maybe_unused = regs->regs[29];
-
+#ifdef CONFIG_32BIT
 	switch (n) {
 	case 0: case 1: case 2: case 3:
 		*arg = regs->regs[4 + n];
-
-		return;
-
-#ifdef CONFIG_32BIT
-	case 4: case 5: case 6: case 7:
-		get_user(*arg, (int *)usp + n);
 		return;
-#endif
-
-#ifdef CONFIG_64BIT
 	case 4: case 5: case 6: case 7:
-#ifdef CONFIG_MIPS32_O32
-		if (test_tsk_thread_flag(task, TIF_32BIT_REGS))
-			get_user(*arg, (int *)usp + n);
-		else
-#endif
-			*arg = regs->regs[4 + n];
-
+		*arg = regs->args[n];
 		return;
-#endif
-
-	default:
-		BUG();
 	}
-
-	unreachable();
+#else
+	*arg = regs->regs[4 + n];
+	if ((IS_ENABLED(CONFIG_MIPS32_O32) &&
+	     test_tsk_thread_flag(task, TIF_32BIT_REGS)))
+		*arg = (unsigned int)*arg;
+#endif
 }
 
 static inline long syscall_get_error(struct task_struct *task,
diff --git a/arch/mips/kernel/asm-offsets.c b/arch/mips/kernel/asm-offsets.c
index cb1045ebab06..b910ec54a3a1 100644
--- a/arch/mips/kernel/asm-offsets.c
+++ b/arch/mips/kernel/asm-offsets.c
@@ -27,6 +27,12 @@ void output_ptreg_defines(void);
 void output_ptreg_defines(void)
 {
 	COMMENT("MIPS pt_regs offsets.");
+#ifdef CONFIG_32BIT
+	OFFSET(PT_ARG4, pt_regs, args[4]);
+	OFFSET(PT_ARG5, pt_regs, args[5]);
+	OFFSET(PT_ARG6, pt_regs, args[6]);
+	OFFSET(PT_ARG7, pt_regs, args[7]);
+#endif
 	OFFSET(PT_R0, pt_regs, regs[0]);
 	OFFSET(PT_R1, pt_regs, regs[1]);
 	OFFSET(PT_R2, pt_regs, regs[2]);
diff --git a/arch/mips/kernel/scall32-o32.S b/arch/mips/kernel/scall32-o32.S
index 2c604717e630..4947a4f39e37 100644
--- a/arch/mips/kernel/scall32-o32.S
+++ b/arch/mips/kernel/scall32-o32.S
@@ -64,10 +64,10 @@ load_a6: user_lw(t7, 24(t0))		# argument #7 from usp
 load_a7: user_lw(t8, 28(t0))		# argument #8 from usp
 loads_done:
 
-	sw	t5, 16(sp)		# argument #5 to ksp
-	sw	t6, 20(sp)		# argument #6 to ksp
-	sw	t7, 24(sp)		# argument #7 to ksp
-	sw	t8, 28(sp)		# argument #8 to ksp
+	sw	t5, PT_ARG4(sp)		# argument #5 to ksp
+	sw	t6, PT_ARG5(sp)		# argument #6 to ksp
+	sw	t7, PT_ARG6(sp)		# argument #7 to ksp
+	sw	t8, PT_ARG7(sp)		# argument #8 to ksp
 	.set	pop
 
 	.section __ex_table,"a"
diff --git a/arch/parisc/include/asm/hugetlb.h b/arch/parisc/include/asm/hugetlb.h
index 5b3a5429f71b..21e9ace17739 100644
--- a/arch/parisc/include/asm/hugetlb.h
+++ b/arch/parisc/include/asm/hugetlb.h
@@ -10,7 +10,7 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 
 #define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR
 pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
-			      pte_t *ptep);
+			      pte_t *ptep, unsigned long sz);
 
 #define __HAVE_ARCH_HUGE_PTEP_CLEAR_FLUSH
 static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
diff --git a/arch/parisc/mm/hugetlbpage.c b/arch/parisc/mm/hugetlbpage.c
index e9d18cf25b79..a94fe546d434 100644
--- a/arch/parisc/mm/hugetlbpage.c
+++ b/arch/parisc/mm/hugetlbpage.c
@@ -126,7 +126,7 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 
 
 pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
-			      pte_t *ptep)
+			      pte_t *ptep, unsigned long sz)
 {
 	pte_t entry;
 
diff --git a/arch/powerpc/include/asm/book3s/64/hash-4k.h b/arch/powerpc/include/asm/book3s/64/hash-4k.h
index c3efacab4b94..aa90a048f319 100644
--- a/arch/powerpc/include/asm/book3s/64/hash-4k.h
+++ b/arch/powerpc/include/asm/book3s/64/hash-4k.h
@@ -77,9 +77,17 @@
 /*
  * With 4K page size the real_pte machinery is all nops.
  */
-#define __real_pte(e, p, o)		((real_pte_t){(e)})
+static inline real_pte_t __real_pte(pte_t pte, pte_t *ptep, int offset)
+{
+	return (real_pte_t){pte};
+}
+
 #define __rpte_to_pte(r)	((r).pte)
-#define __rpte_to_hidx(r,index)	(pte_val(__rpte_to_pte(r)) >> H_PAGE_F_GIX_SHIFT)
+
+static inline unsigned long __rpte_to_hidx(real_pte_t rpte, unsigned long index)
+{
+	return pte_val(__rpte_to_pte(rpte)) >> H_PAGE_F_GIX_SHIFT;
+}
 
 #define pte_iterate_hashed_subpages(rpte, psize, va, index, shift)       \
 	do {							         \
diff --git a/arch/powerpc/include/asm/hugetlb.h b/arch/powerpc/include/asm/hugetlb.h
index dad2e7980f24..86326587e58d 100644
--- a/arch/powerpc/include/asm/hugetlb.h
+++ b/arch/powerpc/include/asm/hugetlb.h
@@ -45,7 +45,8 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep,
 
 #define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR
 static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
-					    unsigned long addr, pte_t *ptep)
+					    unsigned long addr, pte_t *ptep,
+					    unsigned long sz)
 {
 	return __pte(pte_update(mm, addr, ptep, ~0UL, 0, 1));
 }
@@ -55,8 +56,9 @@ static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
 					  unsigned long addr, pte_t *ptep)
 {
 	pte_t pte;
+	unsigned long sz = huge_page_size(hstate_vma(vma));
 
-	pte = huge_ptep_get_and_clear(vma->vm_mm, addr, ptep);
+	pte = huge_ptep_get_and_clear(vma->vm_mm, addr, ptep, sz);
 	flush_hugetlb_page(vma, addr);
 	return pte;
 }
diff --git a/arch/powerpc/lib/code-patching.c b/arch/powerpc/lib/code-patching.c
index af97fbb3c257..f84e0337cc02 100644
--- a/arch/powerpc/lib/code-patching.c
+++ b/arch/powerpc/lib/code-patching.c
@@ -108,7 +108,7 @@ static int text_area_cpu_up(unsigned int cpu)
 	unsigned long addr;
 	int err;
 
-	area = get_vm_area(PAGE_SIZE, VM_ALLOC);
+	area = get_vm_area(PAGE_SIZE, 0);
 	if (!area) {
 		WARN_ONCE(1, "Failed to create text area for cpu %d\n",
 			cpu);
@@ -493,7 +493,9 @@ static int __do_patch_instructions_mm(u32 *addr, u32 *code, size_t len, bool rep
 
 	orig_mm = start_using_temp_mm(patching_mm);
 
+	kasan_disable_current();
 	err = __patch_instructions(patch_addr, code, len, repeat_instr);
+	kasan_enable_current();
 
 	/* context synchronisation performed by __patch_instructions */
 	stop_using_temp_mm(patching_mm, orig_mm);
diff --git a/arch/riscv/include/asm/cmpxchg.h b/arch/riscv/include/asm/cmpxchg.h
index 4cadc56220fe..427c41dde643 100644
--- a/arch/riscv/include/asm/cmpxchg.h
+++ b/arch/riscv/include/asm/cmpxchg.h
@@ -231,7 +231,7 @@
 		__arch_cmpxchg(".w", ".w" sc_sfx, ".w" cas_sfx,		\
 			       sc_prepend, sc_append,			\
 			       cas_prepend, cas_append,			\
-			       __ret, __ptr, (long), __old, __new);	\
+			       __ret, __ptr, (long)(int)(long), __old, __new);	\
 		break;							\
 	case 8:								\
 		__arch_cmpxchg(".d", ".d" sc_sfx, ".d" cas_sfx,		\
diff --git a/arch/riscv/include/asm/futex.h b/arch/riscv/include/asm/futex.h
index 72be100afa23..90c86b115e00 100644
--- a/arch/riscv/include/asm/futex.h
+++ b/arch/riscv/include/asm/futex.h
@@ -93,7 +93,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 		_ASM_EXTABLE_UACCESS_ERR(1b, 3b, %[r])	\
 		_ASM_EXTABLE_UACCESS_ERR(2b, 3b, %[r])	\
 	: [r] "+r" (ret), [v] "=&r" (val), [u] "+m" (*uaddr), [t] "=&r" (tmp)
-	: [ov] "Jr" (oldval), [nv] "Jr" (newval)
+	: [ov] "Jr" ((long)(int)oldval), [nv] "Jr" (newval)
 	: "memory");
 	__disable_user_access();
 
diff --git a/arch/riscv/include/asm/hugetlb.h b/arch/riscv/include/asm/hugetlb.h
index faf3624d8057..446126497768 100644
--- a/arch/riscv/include/asm/hugetlb.h
+++ b/arch/riscv/include/asm/hugetlb.h
@@ -28,7 +28,8 @@ void set_huge_pte_at(struct mm_struct *mm,
 
 #define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR
 pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
-			      unsigned long addr, pte_t *ptep);
+			      unsigned long addr, pte_t *ptep,
+			      unsigned long sz);
 
 #define __HAVE_ARCH_HUGE_PTEP_CLEAR_FLUSH
 pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
diff --git a/arch/riscv/kernel/cacheinfo.c b/arch/riscv/kernel/cacheinfo.c
index 2d40736fc37c..26b085dbdd07 100644
--- a/arch/riscv/kernel/cacheinfo.c
+++ b/arch/riscv/kernel/cacheinfo.c
@@ -108,11 +108,11 @@ int populate_cache_leaves(unsigned int cpu)
 	if (!np)
 		return -ENOENT;
 
-	if (of_property_read_bool(np, "cache-size"))
+	if (of_property_present(np, "cache-size"))
 		ci_leaf_init(this_leaf++, CACHE_TYPE_UNIFIED, level);
-	if (of_property_read_bool(np, "i-cache-size"))
+	if (of_property_present(np, "i-cache-size"))
 		ci_leaf_init(this_leaf++, CACHE_TYPE_INST, level);
-	if (of_property_read_bool(np, "d-cache-size"))
+	if (of_property_present(np, "d-cache-size"))
 		ci_leaf_init(this_leaf++, CACHE_TYPE_DATA, level);
 
 	prev = np;
@@ -125,11 +125,11 @@ int populate_cache_leaves(unsigned int cpu)
 			break;
 		if (level <= levels)
 			break;
-		if (of_property_read_bool(np, "cache-size"))
+		if (of_property_present(np, "cache-size"))
 			ci_leaf_init(this_leaf++, CACHE_TYPE_UNIFIED, level);
-		if (of_property_read_bool(np, "i-cache-size"))
+		if (of_property_present(np, "i-cache-size"))
 			ci_leaf_init(this_leaf++, CACHE_TYPE_INST, level);
-		if (of_property_read_bool(np, "d-cache-size"))
+		if (of_property_present(np, "d-cache-size"))
 			ci_leaf_init(this_leaf++, CACHE_TYPE_DATA, level);
 		levels = level;
 	}
diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c
index c6ba750536c3..40ac72e407b6 100644
--- a/arch/riscv/kernel/cpufeature.c
+++ b/arch/riscv/kernel/cpufeature.c
@@ -479,7 +479,7 @@ static void __init riscv_resolve_isa(unsigned long *source_isa,
 			if (bit < RISCV_ISA_EXT_BASE)
 				*this_hwcap |= isa2hwcap[bit];
 		}
-	} while (loop && memcmp(prev_resolved_isa, resolved_isa, sizeof(prev_resolved_isa)));
+	} while (loop && !bitmap_equal(prev_resolved_isa, resolved_isa, RISCV_ISA_EXT_MAX));
 }
 
 static void __init match_isa_ext(const char *name, const char *name_end, unsigned long *bitmap)
diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c
index f1793630fc51..4fe45daa6281 100644
--- a/arch/riscv/kernel/setup.c
+++ b/arch/riscv/kernel/setup.c
@@ -322,8 +322,8 @@ void __init setup_arch(char **cmdline_p)
 
 	riscv_init_cbo_blocksizes();
 	riscv_fill_hwcap();
-	init_rt_signal_env();
 	apply_boot_alternatives();
+	init_rt_signal_env();
 
 	if (IS_ENABLED(CONFIG_RISCV_ISA_ZICBOM) &&
 	    riscv_isa_extension_available(NULL, ZICBOM))
diff --git a/arch/riscv/kernel/signal.c b/arch/riscv/kernel/signal.c
index 94e905eea1de..08378fea3a11 100644
--- a/arch/riscv/kernel/signal.c
+++ b/arch/riscv/kernel/signal.c
@@ -215,12 +215,6 @@ static size_t get_rt_frame_size(bool cal_all)
 		if (cal_all || riscv_v_vstate_query(task_pt_regs(current)))
 			total_context_size += riscv_v_sc_size;
 	}
-	/*
-	 * Preserved a __riscv_ctx_hdr for END signal context header if an
-	 * extension uses __riscv_extra_ext_header
-	 */
-	if (total_context_size)
-		total_context_size += sizeof(struct __riscv_ctx_hdr);
 
 	frame_size += total_context_size;
 
diff --git a/arch/riscv/kvm/aia_imsic.c b/arch/riscv/kvm/aia_imsic.c
index a8085cd8215e..29ef9c2133a9 100644
--- a/arch/riscv/kvm/aia_imsic.c
+++ b/arch/riscv/kvm/aia_imsic.c
@@ -974,7 +974,6 @@ int kvm_riscv_vcpu_aia_imsic_inject(struct kvm_vcpu *vcpu,
 
 	if (imsic->vsfile_cpu >= 0) {
 		writel(iid, imsic->vsfile_va + IMSIC_MMIO_SETIPNUM_LE);
-		kvm_vcpu_kick(vcpu);
 	} else {
 		eix = &imsic->swfile->eix[iid / BITS_PER_TYPE(u64)];
 		set_bit(iid & (BITS_PER_TYPE(u64) - 1), eix->eip);
diff --git a/arch/riscv/kvm/vcpu_sbi_hsm.c b/arch/riscv/kvm/vcpu_sbi_hsm.c
index dce667f4b6ab..3070bb31745d 100644
--- a/arch/riscv/kvm/vcpu_sbi_hsm.c
+++ b/arch/riscv/kvm/vcpu_sbi_hsm.c
@@ -9,6 +9,7 @@
 #include <linux/errno.h>
 #include <linux/err.h>
 #include <linux/kvm_host.h>
+#include <linux/wordpart.h>
 #include <asm/sbi.h>
 #include <asm/kvm_vcpu_sbi.h>
 
@@ -79,12 +80,12 @@ static int kvm_sbi_hsm_vcpu_get_status(struct kvm_vcpu *vcpu)
 	target_vcpu = kvm_get_vcpu_by_id(vcpu->kvm, target_vcpuid);
 	if (!target_vcpu)
 		return SBI_ERR_INVALID_PARAM;
-	if (!kvm_riscv_vcpu_stopped(target_vcpu))
-		return SBI_HSM_STATE_STARTED;
-	else if (vcpu->stat.generic.blocking)
+	if (kvm_riscv_vcpu_stopped(target_vcpu))
+		return SBI_HSM_STATE_STOPPED;
+	else if (target_vcpu->stat.generic.blocking)
 		return SBI_HSM_STATE_SUSPENDED;
 	else
-		return SBI_HSM_STATE_STOPPED;
+		return SBI_HSM_STATE_STARTED;
 }
 
 static int kvm_sbi_ext_hsm_handler(struct kvm_vcpu *vcpu, struct kvm_run *run,
@@ -109,7 +110,7 @@ static int kvm_sbi_ext_hsm_handler(struct kvm_vcpu *vcpu, struct kvm_run *run,
 		}
 		return 0;
 	case SBI_EXT_HSM_HART_SUSPEND:
-		switch (cp->a0) {
+		switch (lower_32_bits(cp->a0)) {
 		case SBI_HSM_SUSPEND_RET_DEFAULT:
 			kvm_riscv_vcpu_wfi(vcpu);
 			break;
diff --git a/arch/riscv/kvm/vcpu_sbi_replace.c b/arch/riscv/kvm/vcpu_sbi_replace.c
index 9c2ab3dfa93a..5fbf3f94f1e8 100644
--- a/arch/riscv/kvm/vcpu_sbi_replace.c
+++ b/arch/riscv/kvm/vcpu_sbi_replace.c
@@ -21,7 +21,7 @@ static int kvm_sbi_ext_time_handler(struct kvm_vcpu *vcpu, struct kvm_run *run,
 	u64 next_cycle;
 
 	if (cp->a6 != SBI_EXT_TIME_SET_TIMER) {
-		retdata->err_val = SBI_ERR_INVALID_PARAM;
+		retdata->err_val = SBI_ERR_NOT_SUPPORTED;
 		return 0;
 	}
 
@@ -51,9 +51,10 @@ static int kvm_sbi_ext_ipi_handler(struct kvm_vcpu *vcpu, struct kvm_run *run,
 	struct kvm_cpu_context *cp = &vcpu->arch.guest_context;
 	unsigned long hmask = cp->a0;
 	unsigned long hbase = cp->a1;
+	unsigned long hart_bit = 0, sentmask = 0;
 
 	if (cp->a6 != SBI_EXT_IPI_SEND_IPI) {
-		retdata->err_val = SBI_ERR_INVALID_PARAM;
+		retdata->err_val = SBI_ERR_NOT_SUPPORTED;
 		return 0;
 	}
 
@@ -62,15 +63,23 @@ static int kvm_sbi_ext_ipi_handler(struct kvm_vcpu *vcpu, struct kvm_run *run,
 		if (hbase != -1UL) {
 			if (tmp->vcpu_id < hbase)
 				continue;
-			if (!(hmask & (1UL << (tmp->vcpu_id - hbase))))
+			hart_bit = tmp->vcpu_id - hbase;
+			if (hart_bit >= __riscv_xlen)
+				goto done;
+			if (!(hmask & (1UL << hart_bit)))
 				continue;
 		}
 		ret = kvm_riscv_vcpu_set_interrupt(tmp, IRQ_VS_SOFT);
 		if (ret < 0)
 			break;
+		sentmask |= 1UL << hart_bit;
 		kvm_riscv_vcpu_pmu_incr_fw(tmp, SBI_PMU_FW_IPI_RCVD);
 	}
 
+done:
+	if (hbase != -1UL && (hmask ^ sentmask))
+		retdata->err_val = SBI_ERR_INVALID_PARAM;
+
 	return ret;
 }
 
diff --git a/arch/riscv/kvm/vcpu_sbi_system.c b/arch/riscv/kvm/vcpu_sbi_system.c
index 5d55e08791fa..bc0ebba89003 100644
--- a/arch/riscv/kvm/vcpu_sbi_system.c
+++ b/arch/riscv/kvm/vcpu_sbi_system.c
@@ -4,6 +4,7 @@
  */
 
 #include <linux/kvm_host.h>
+#include <linux/wordpart.h>
 
 #include <asm/kvm_vcpu_sbi.h>
 #include <asm/sbi.h>
@@ -19,7 +20,7 @@ static int kvm_sbi_ext_susp_handler(struct kvm_vcpu *vcpu, struct kvm_run *run,
 
 	switch (funcid) {
 	case SBI_EXT_SUSP_SYSTEM_SUSPEND:
-		if (cp->a0 != SBI_SUSP_SLEEP_TYPE_SUSPEND_TO_RAM) {
+		if (lower_32_bits(cp->a0) != SBI_SUSP_SLEEP_TYPE_SUSPEND_TO_RAM) {
 			retdata->err_val = SBI_ERR_INVALID_PARAM;
 			return 0;
 		}
diff --git a/arch/riscv/mm/hugetlbpage.c b/arch/riscv/mm/hugetlbpage.c
index 42314f093922..b4a78a4b35cf 100644
--- a/arch/riscv/mm/hugetlbpage.c
+++ b/arch/riscv/mm/hugetlbpage.c
@@ -293,7 +293,7 @@ int huge_ptep_set_access_flags(struct vm_area_struct *vma,
 
 pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
 			      unsigned long addr,
-			      pte_t *ptep)
+			      pte_t *ptep, unsigned long sz)
 {
 	pte_t orig_pte = ptep_get(ptep);
 	int pte_num;
diff --git a/arch/s390/boot/startup.c b/arch/s390/boot/startup.c
index 885bd1dd2c82..9276e0576d0a 100644
--- a/arch/s390/boot/startup.c
+++ b/arch/s390/boot/startup.c
@@ -86,7 +86,7 @@ static int cmma_test_essa(void)
 		: [reg1] "=&d" (reg1),
 		  [reg2] "=&a" (reg2),
 		  [rc] "+&d" (rc),
-		  [tmp] "=&d" (tmp),
+		  [tmp] "+&d" (tmp),
 		  "+Q" (get_lowcore()->program_new_psw),
 		  "=Q" (old)
 		: [psw_old] "a" (&old),
diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig
index d6beec5292a0..80bdfbae6e5b 100644
--- a/arch/s390/configs/debug_defconfig
+++ b/arch/s390/configs/debug_defconfig
@@ -469,6 +469,7 @@ CONFIG_SCSI_DH_ALUA=m
 CONFIG_MD=y
 CONFIG_BLK_DEV_MD=y
 # CONFIG_MD_BITMAP_FILE is not set
+CONFIG_MD_LINEAR=m
 CONFIG_MD_CLUSTER=m
 CONFIG_BCACHE=m
 CONFIG_BLK_DEV_DM=y
@@ -740,7 +741,6 @@ CONFIG_IMA=y
 CONFIG_IMA_DEFAULT_HASH_SHA256=y
 CONFIG_IMA_WRITE_POLICY=y
 CONFIG_IMA_APPRAISE=y
-CONFIG_LSM="yama,loadpin,safesetid,integrity,selinux,smack,tomoyo,apparmor"
 CONFIG_BUG_ON_DATA_CORRUPTION=y
 CONFIG_CRYPTO_USER=m
 # CONFIG_CRYPTO_MANAGER_DISABLE_TESTS is not set
@@ -875,6 +875,7 @@ CONFIG_RCU_CPU_STALL_TIMEOUT=300
 CONFIG_LATENCYTOP=y
 CONFIG_BOOTTIME_TRACING=y
 CONFIG_FUNCTION_GRAPH_RETVAL=y
+CONFIG_FUNCTION_GRAPH_RETADDR=y
 CONFIG_FPROBE=y
 CONFIG_FUNCTION_PROFILER=y
 CONFIG_STACK_TRACER=y
diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig
index 8cfbfb10bba8..449a0e996b96 100644
--- a/arch/s390/configs/defconfig
+++ b/arch/s390/configs/defconfig
@@ -459,6 +459,7 @@ CONFIG_SCSI_DH_ALUA=m
 CONFIG_MD=y
 CONFIG_BLK_DEV_MD=y
 # CONFIG_MD_BITMAP_FILE is not set
+CONFIG_MD_LINEAR=m
 CONFIG_MD_CLUSTER=m
 CONFIG_BCACHE=m
 CONFIG_BLK_DEV_DM=y
@@ -725,7 +726,6 @@ CONFIG_IMA=y
 CONFIG_IMA_DEFAULT_HASH_SHA256=y
 CONFIG_IMA_WRITE_POLICY=y
 CONFIG_IMA_APPRAISE=y
-CONFIG_LSM="yama,loadpin,safesetid,integrity,selinux,smack,tomoyo,apparmor"
 CONFIG_BUG_ON_DATA_CORRUPTION=y
 CONFIG_CRYPTO_FIPS=y
 CONFIG_CRYPTO_USER=m
@@ -826,6 +826,7 @@ CONFIG_RCU_CPU_STALL_TIMEOUT=60
 CONFIG_LATENCYTOP=y
 CONFIG_BOOTTIME_TRACING=y
 CONFIG_FUNCTION_GRAPH_RETVAL=y
+CONFIG_FUNCTION_GRAPH_RETADDR=y
 CONFIG_FPROBE=y
 CONFIG_FUNCTION_PROFILER=y
 CONFIG_STACK_TRACER=y
diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig
index bcbaa069de96..853b2326a171 100644
--- a/arch/s390/configs/zfcpdump_defconfig
+++ b/arch/s390/configs/zfcpdump_defconfig
@@ -62,7 +62,6 @@ CONFIG_ZFCP=y
 # CONFIG_INOTIFY_USER is not set
 # CONFIG_MISC_FILESYSTEMS is not set
 # CONFIG_NETWORK_FILESYSTEMS is not set
-CONFIG_LSM="yama,loadpin,safesetid,integrity"
 # CONFIG_ZLIB_DFLTCC is not set
 CONFIG_XZ_DEC_MICROLZMA=y
 CONFIG_PRINTK_TIME=y
diff --git a/arch/s390/include/asm/bitops.h b/arch/s390/include/asm/bitops.h
index d5125296ade2..a5ca0a947691 100644
--- a/arch/s390/include/asm/bitops.h
+++ b/arch/s390/include/asm/bitops.h
@@ -53,7 +53,11 @@ static __always_inline bool arch_test_bit(unsigned long nr, const volatile unsig
 	unsigned long mask;
 	int cc;
 
-	if (__builtin_constant_p(nr)) {
+	/*
+	 * With CONFIG_PROFILE_ALL_BRANCHES enabled gcc fails to
+	 * handle __builtin_constant_p() in some cases.
+	 */
+	if (!IS_ENABLED(CONFIG_PROFILE_ALL_BRANCHES) && __builtin_constant_p(nr)) {
 		addr = (const volatile unsigned char *)ptr;
 		addr += (nr ^ (BITS_PER_LONG - BITS_PER_BYTE)) / BITS_PER_BYTE;
 		mask = 1UL << (nr & (BITS_PER_BYTE - 1));
diff --git a/arch/s390/include/asm/hugetlb.h b/arch/s390/include/asm/hugetlb.h
index 7c52acaf9f82..663e87220e89 100644
--- a/arch/s390/include/asm/hugetlb.h
+++ b/arch/s390/include/asm/hugetlb.h
@@ -25,8 +25,16 @@ void __set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 #define __HAVE_ARCH_HUGE_PTEP_GET
 pte_t huge_ptep_get(struct mm_struct *mm, unsigned long addr, pte_t *ptep);
 
+pte_t __huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
+				pte_t *ptep);
+
 #define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR
-pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep);
+static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
+					    unsigned long addr, pte_t *ptep,
+					    unsigned long sz)
+{
+	return __huge_ptep_get_and_clear(mm, addr, ptep);
+}
 
 static inline void arch_clear_hugetlb_flags(struct folio *folio)
 {
@@ -48,7 +56,7 @@ static inline void huge_pte_clear(struct mm_struct *mm, unsigned long addr,
 static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
 					  unsigned long address, pte_t *ptep)
 {
-	return huge_ptep_get_and_clear(vma->vm_mm, address, ptep);
+	return __huge_ptep_get_and_clear(vma->vm_mm, address, ptep);
 }
 
 #define  __HAVE_ARCH_HUGE_PTEP_SET_ACCESS_FLAGS
@@ -59,7 +67,7 @@ static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma,
 	int changed = !pte_same(huge_ptep_get(vma->vm_mm, addr, ptep), pte);
 
 	if (changed) {
-		huge_ptep_get_and_clear(vma->vm_mm, addr, ptep);
+		__huge_ptep_get_and_clear(vma->vm_mm, addr, ptep);
 		__set_huge_pte_at(vma->vm_mm, addr, ptep, pte);
 	}
 	return changed;
@@ -69,7 +77,7 @@ static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma,
 static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
 					   unsigned long addr, pte_t *ptep)
 {
-	pte_t pte = huge_ptep_get_and_clear(mm, addr, ptep);
+	pte_t pte = __huge_ptep_get_and_clear(mm, addr, ptep);
 
 	__set_huge_pte_at(mm, addr, ptep, pte_wrprotect(pte));
 }
diff --git a/arch/s390/kernel/ftrace.c b/arch/s390/kernel/ftrace.c
index 63ba6306632e..e540b022ceb2 100644
--- a/arch/s390/kernel/ftrace.c
+++ b/arch/s390/kernel/ftrace.c
@@ -266,12 +266,13 @@ void ftrace_graph_func(unsigned long ip, unsigned long parent_ip,
 		       struct ftrace_ops *op, struct ftrace_regs *fregs)
 {
 	unsigned long *parent = &arch_ftrace_regs(fregs)->regs.gprs[14];
+	unsigned long sp = arch_ftrace_regs(fregs)->regs.gprs[15];
 
 	if (unlikely(ftrace_graph_is_dead()))
 		return;
 	if (unlikely(atomic_read(&current->tracing_graph_pause)))
 		return;
-	if (!function_graph_enter_regs(*parent, ip, 0, parent, fregs))
+	if (!function_graph_enter_regs(*parent, ip, 0, (unsigned long *)sp, fregs))
 		*parent = (unsigned long)&return_to_handler;
 }
 
diff --git a/arch/s390/kernel/traps.c b/arch/s390/kernel/traps.c
index 24fee11b030d..b746213d3110 100644
--- a/arch/s390/kernel/traps.c
+++ b/arch/s390/kernel/traps.c
@@ -285,10 +285,10 @@ static void __init test_monitor_call(void)
 		return;
 	asm volatile(
 		"	mc	0,0\n"
-		"0:	xgr	%0,%0\n"
+		"0:	lhi	%[val],0\n"
 		"1:\n"
-		EX_TABLE(0b,1b)
-		: "+d" (val));
+		EX_TABLE(0b, 1b)
+		: [val] "+d" (val));
 	if (!val)
 		panic("Monitor call doesn't work!\n");
 }
diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c
index d9ce199953de..2e568f175cd4 100644
--- a/arch/s390/mm/hugetlbpage.c
+++ b/arch/s390/mm/hugetlbpage.c
@@ -188,8 +188,8 @@ pte_t huge_ptep_get(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
 	return __rste_to_pte(pte_val(*ptep));
 }
 
-pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
-			      unsigned long addr, pte_t *ptep)
+pte_t __huge_ptep_get_and_clear(struct mm_struct *mm,
+				unsigned long addr, pte_t *ptep)
 {
 	pte_t pte = huge_ptep_get(mm, addr, ptep);
 	pmd_t *pmdp = (pmd_t *) ptep;
diff --git a/arch/s390/pci/pci_bus.c b/arch/s390/pci/pci_bus.c
index 857afbc4828f..39a481ec4a40 100644
--- a/arch/s390/pci/pci_bus.c
+++ b/arch/s390/pci/pci_bus.c
@@ -331,6 +331,17 @@ error:
 	return rc;
 }
 
+static bool zpci_bus_is_isolated_vf(struct zpci_bus *zbus, struct zpci_dev *zdev)
+{
+	struct pci_dev *pdev;
+
+	pdev = zpci_iov_find_parent_pf(zbus, zdev);
+	if (!pdev)
+		return true;
+	pci_dev_put(pdev);
+	return false;
+}
+
 int zpci_bus_device_register(struct zpci_dev *zdev, struct pci_ops *ops)
 {
 	bool topo_is_tid = zdev->tid_avail;
@@ -345,6 +356,15 @@ int zpci_bus_device_register(struct zpci_dev *zdev, struct pci_ops *ops)
 
 	topo = topo_is_tid ? zdev->tid : zdev->pchid;
 	zbus = zpci_bus_get(topo, topo_is_tid);
+	/*
+	 * An isolated VF gets its own domain/bus even if there exists
+	 * a matching domain/bus already
+	 */
+	if (zbus && zpci_bus_is_isolated_vf(zbus, zdev)) {
+		zpci_bus_put(zbus);
+		zbus = NULL;
+	}
+
 	if (!zbus) {
 		zbus = zpci_bus_alloc(topo, topo_is_tid);
 		if (!zbus)
diff --git a/arch/s390/pci/pci_iov.c b/arch/s390/pci/pci_iov.c
index ead062bf2b41..191e56a623f6 100644
--- a/arch/s390/pci/pci_iov.c
+++ b/arch/s390/pci/pci_iov.c
@@ -60,18 +60,35 @@ static int zpci_iov_link_virtfn(struct pci_dev *pdev, struct pci_dev *virtfn, in
 	return 0;
 }
 
-int zpci_iov_setup_virtfn(struct zpci_bus *zbus, struct pci_dev *virtfn, int vfn)
+/**
+ * zpci_iov_find_parent_pf - Find the parent PF, if any, of the given function
+ * @zbus:	The bus that the PCI function is on, or would be added on
+ * @zdev:	The PCI function
+ *
+ * Finds the parent PF, if it exists and is configured, of the given PCI function
+ * and increments its refcount. Th PF is searched for on the provided bus so the
+ * caller has to ensure that this is the correct bus to search. This function may
+ * be used before adding the PCI function to a zbus.
+ *
+ * Return: Pointer to the struct pci_dev of the parent PF or NULL if it not
+ * found. If the function is not a VF or has no RequesterID information,
+ * NULL is returned as well.
+ */
+struct pci_dev *zpci_iov_find_parent_pf(struct zpci_bus *zbus, struct zpci_dev *zdev)
 {
-	int i, cand_devfn;
-	struct zpci_dev *zdev;
+	int i, vfid, devfn, cand_devfn;
 	struct pci_dev *pdev;
-	int vfid = vfn - 1; /* Linux' vfid's start at 0 vfn at 1*/
-	int rc = 0;
 
 	if (!zbus->multifunction)
-		return 0;
-
-	/* If the parent PF for the given VF is also configured in the
+		return NULL;
+	/* Non-VFs and VFs without RID available don't have a parent */
+	if (!zdev->vfn || !zdev->rid_available)
+		return NULL;
+	/* Linux vfid starts at 0 vfn at 1 */
+	vfid = zdev->vfn - 1;
+	devfn = zdev->rid & ZPCI_RID_MASK_DEVFN;
+	/*
+	 * If the parent PF for the given VF is also configured in the
 	 * instance, it must be on the same zbus.
 	 * We can then identify the parent PF by checking what
 	 * devfn the VF would have if it belonged to that PF using the PF's
@@ -85,15 +102,26 @@ int zpci_iov_setup_virtfn(struct zpci_bus *zbus, struct pci_dev *virtfn, int vfn
 			if (!pdev)
 				continue;
 			cand_devfn = pci_iov_virtfn_devfn(pdev, vfid);
-			if (cand_devfn == virtfn->devfn) {
-				rc = zpci_iov_link_virtfn(pdev, virtfn, vfid);
-				/* balance pci_get_slot() */
-				pci_dev_put(pdev);
-				break;
-			}
+			if (cand_devfn == devfn)
+				return pdev;
 			/* balance pci_get_slot() */
 			pci_dev_put(pdev);
 		}
 	}
+	return NULL;
+}
+
+int zpci_iov_setup_virtfn(struct zpci_bus *zbus, struct pci_dev *virtfn, int vfn)
+{
+	struct zpci_dev *zdev = to_zpci(virtfn);
+	struct pci_dev *pdev_pf;
+	int rc = 0;
+
+	pdev_pf = zpci_iov_find_parent_pf(zbus, zdev);
+	if (pdev_pf) {
+		/* Linux' vfids start at 0 while zdev->vfn starts at 1 */
+		rc = zpci_iov_link_virtfn(pdev_pf, virtfn, zdev->vfn - 1);
+		pci_dev_put(pdev_pf);
+	}
 	return rc;
 }
diff --git a/arch/s390/pci/pci_iov.h b/arch/s390/pci/pci_iov.h
index e3fa4e77fc86..d2c2793eb0f3 100644
--- a/arch/s390/pci/pci_iov.h
+++ b/arch/s390/pci/pci_iov.h
@@ -19,6 +19,8 @@ void zpci_iov_map_resources(struct pci_dev *pdev);
 
 int zpci_iov_setup_virtfn(struct zpci_bus *zbus, struct pci_dev *virtfn, int vfn);
 
+struct pci_dev *zpci_iov_find_parent_pf(struct zpci_bus *zbus, struct zpci_dev *zdev);
+
 #else /* CONFIG_PCI_IOV */
 static inline void zpci_iov_remove_virtfn(struct pci_dev *pdev, int vfn) {}
 
@@ -28,5 +30,10 @@ static inline int zpci_iov_setup_virtfn(struct zpci_bus *zbus, struct pci_dev *v
 {
 	return 0;
 }
+
+static inline struct pci_dev *zpci_iov_find_parent_pf(struct zpci_bus *zbus, struct zpci_dev *zdev)
+{
+	return NULL;
+}
 #endif /* CONFIG_PCI_IOV */
 #endif /* __S390_PCI_IOV_h */
diff --git a/arch/s390/purgatory/Makefile b/arch/s390/purgatory/Makefile
index bdcf2a3b6c41..bd39b36e7bd6 100644
--- a/arch/s390/purgatory/Makefile
+++ b/arch/s390/purgatory/Makefile
@@ -8,7 +8,7 @@ PURGATORY_OBJS = $(addprefix $(obj)/,$(purgatory-y))
 $(obj)/sha256.o: $(srctree)/lib/crypto/sha256.c FORCE
 	$(call if_changed_rule,cc_o_c)
 
-CFLAGS_sha256.o := -D__DISABLE_EXPORTS -D__NO_FORTIFY
+CFLAGS_sha256.o := -D__NO_FORTIFY
 
 $(obj)/mem.o: $(srctree)/arch/s390/lib/mem.S FORCE
 	$(call if_changed_rule,as_o_S)
@@ -19,9 +19,11 @@ KBUILD_CFLAGS += -fno-zero-initialized-in-bss -fno-builtin -ffreestanding
 KBUILD_CFLAGS += -Os -m64 -msoft-float -fno-common
 KBUILD_CFLAGS += -fno-stack-protector
 KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING
+KBUILD_CFLAGS += -D__DISABLE_EXPORTS
 KBUILD_CFLAGS += $(CLANG_FLAGS)
 KBUILD_CFLAGS += $(call cc-option,-fno-PIE)
 KBUILD_AFLAGS := $(filter-out -DCC_USING_EXPOLINE,$(KBUILD_AFLAGS))
+KBUILD_AFLAGS += -D__DISABLE_EXPORTS
 
 # Since we link purgatory with -r unresolved symbols are not checked, so we
 # also link a purgatory.chk binary without -r to check for unresolved symbols.
diff --git a/arch/sparc/include/asm/hugetlb.h b/arch/sparc/include/asm/hugetlb.h
index c714ca6a05aa..e7a9cdd498dc 100644
--- a/arch/sparc/include/asm/hugetlb.h
+++ b/arch/sparc/include/asm/hugetlb.h
@@ -20,7 +20,7 @@ void __set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 
 #define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR
 pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
-			      pte_t *ptep);
+			      pte_t *ptep, unsigned long sz);
 
 #define __HAVE_ARCH_HUGE_PTEP_CLEAR_FLUSH
 static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
diff --git a/arch/sparc/mm/hugetlbpage.c b/arch/sparc/mm/hugetlbpage.c
index eee601a0d2cf..80504148d8a5 100644
--- a/arch/sparc/mm/hugetlbpage.c
+++ b/arch/sparc/mm/hugetlbpage.c
@@ -260,7 +260,7 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 }
 
 pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
-			      pte_t *ptep)
+			      pte_t *ptep, unsigned long sz)
 {
 	unsigned int i, nptes, orig_shift, shift;
 	unsigned long size;
diff --git a/arch/um/drivers/virt-pci.c b/arch/um/drivers/virt-pci.c
index 744e7f31e8ef..dd5580f975cc 100644
--- a/arch/um/drivers/virt-pci.c
+++ b/arch/um/drivers/virt-pci.c
@@ -25,8 +25,10 @@
 #define MAX_IRQ_MSG_SIZE (sizeof(struct virtio_pcidev_msg) + sizeof(u32))
 #define NUM_IRQ_MSGS	10
 
-#define HANDLE_NO_FREE(ptr) ((void *)((unsigned long)(ptr) | 1))
-#define HANDLE_IS_NO_FREE(ptr) ((unsigned long)(ptr) & 1)
+struct um_pci_message_buffer {
+	struct virtio_pcidev_msg hdr;
+	u8 data[8];
+};
 
 struct um_pci_device {
 	struct virtio_device *vdev;
@@ -36,6 +38,11 @@ struct um_pci_device {
 
 	struct virtqueue *cmd_vq, *irq_vq;
 
+#define UM_PCI_WRITE_BUFS	20
+	struct um_pci_message_buffer bufs[UM_PCI_WRITE_BUFS + 1];
+	void *extra_ptrs[UM_PCI_WRITE_BUFS + 1];
+	DECLARE_BITMAP(used_bufs, UM_PCI_WRITE_BUFS);
+
 #define UM_PCI_STAT_WAITING	0
 	unsigned long status;
 
@@ -61,12 +68,40 @@ static unsigned long um_pci_msi_used[BITS_TO_LONGS(MAX_MSI_VECTORS)];
 static unsigned int um_pci_max_delay_us = 40000;
 module_param_named(max_delay_us, um_pci_max_delay_us, uint, 0644);
 
-struct um_pci_message_buffer {
-	struct virtio_pcidev_msg hdr;
-	u8 data[8];
-};
+static int um_pci_get_buf(struct um_pci_device *dev, bool *posted)
+{
+	int i;
+
+	for (i = 0; i < UM_PCI_WRITE_BUFS; i++) {
+		if (!test_and_set_bit(i, dev->used_bufs))
+			return i;
+	}
 
-static struct um_pci_message_buffer __percpu *um_pci_msg_bufs;
+	*posted = false;
+	return UM_PCI_WRITE_BUFS;
+}
+
+static void um_pci_free_buf(struct um_pci_device *dev, void *buf)
+{
+	int i;
+
+	if (buf == &dev->bufs[UM_PCI_WRITE_BUFS]) {
+		kfree(dev->extra_ptrs[UM_PCI_WRITE_BUFS]);
+		dev->extra_ptrs[UM_PCI_WRITE_BUFS] = NULL;
+		return;
+	}
+
+	for (i = 0; i < UM_PCI_WRITE_BUFS; i++) {
+		if (buf == &dev->bufs[i]) {
+			kfree(dev->extra_ptrs[i]);
+			dev->extra_ptrs[i] = NULL;
+			WARN_ON(!test_and_clear_bit(i, dev->used_bufs));
+			return;
+		}
+	}
+
+	WARN_ON(1);
+}
 
 static int um_pci_send_cmd(struct um_pci_device *dev,
 			   struct virtio_pcidev_msg *cmd,
@@ -82,7 +117,9 @@ static int um_pci_send_cmd(struct um_pci_device *dev,
 	};
 	struct um_pci_message_buffer *buf;
 	int delay_count = 0;
+	bool bounce_out;
 	int ret, len;
+	int buf_idx;
 	bool posted;
 
 	if (WARN_ON(cmd_size < sizeof(*cmd) || cmd_size > sizeof(*buf)))
@@ -101,26 +138,28 @@ static int um_pci_send_cmd(struct um_pci_device *dev,
 		break;
 	}
 
-	buf = get_cpu_var(um_pci_msg_bufs);
-	if (buf)
-		memcpy(buf, cmd, cmd_size);
+	bounce_out = !posted && cmd_size <= sizeof(*cmd) &&
+		     out && out_size <= sizeof(buf->data);
 
-	if (posted) {
-		u8 *ncmd = kmalloc(cmd_size + extra_size, GFP_ATOMIC);
-
-		if (ncmd) {
-			memcpy(ncmd, cmd, cmd_size);
-			if (extra)
-				memcpy(ncmd + cmd_size, extra, extra_size);
-			cmd = (void *)ncmd;
-			cmd_size += extra_size;
-			extra = NULL;
-			extra_size = 0;
-		} else {
-			/* try without allocating memory */
-			posted = false;
-			cmd = (void *)buf;
+	buf_idx = um_pci_get_buf(dev, &posted);
+	buf = &dev->bufs[buf_idx];
+	memcpy(buf, cmd, cmd_size);
+
+	if (posted && extra && extra_size > sizeof(buf) - cmd_size) {
+		dev->extra_ptrs[buf_idx] = kmemdup(extra, extra_size,
+						   GFP_ATOMIC);
+
+		if (!dev->extra_ptrs[buf_idx]) {
+			um_pci_free_buf(dev, buf);
+			return -ENOMEM;
 		}
+		extra = dev->extra_ptrs[buf_idx];
+	} else if (extra && extra_size <= sizeof(buf) - cmd_size) {
+		memcpy((u8 *)buf + cmd_size, extra, extra_size);
+		cmd_size += extra_size;
+		extra_size = 0;
+		extra = NULL;
+		cmd = (void *)buf;
 	} else {
 		cmd = (void *)buf;
 	}
@@ -128,39 +167,40 @@ static int um_pci_send_cmd(struct um_pci_device *dev,
 	sg_init_one(&out_sg, cmd, cmd_size);
 	if (extra)
 		sg_init_one(&extra_sg, extra, extra_size);
-	if (out)
+	/* allow stack for small buffers */
+	if (bounce_out)
+		sg_init_one(&in_sg, buf->data, out_size);
+	else if (out)
 		sg_init_one(&in_sg, out, out_size);
 
 	/* add to internal virtio queue */
 	ret = virtqueue_add_sgs(dev->cmd_vq, sgs_list,
 				extra ? 2 : 1,
 				out ? 1 : 0,
-				posted ? cmd : HANDLE_NO_FREE(cmd),
-				GFP_ATOMIC);
+				cmd, GFP_ATOMIC);
 	if (ret) {
-		if (posted)
-			kfree(cmd);
-		goto out;
+		um_pci_free_buf(dev, buf);
+		return ret;
 	}
 
 	if (posted) {
 		virtqueue_kick(dev->cmd_vq);
-		ret = 0;
-		goto out;
+		return 0;
 	}
 
 	/* kick and poll for getting a response on the queue */
 	set_bit(UM_PCI_STAT_WAITING, &dev->status);
 	virtqueue_kick(dev->cmd_vq);
+	ret = 0;
 
 	while (1) {
 		void *completed = virtqueue_get_buf(dev->cmd_vq, &len);
 
-		if (completed == HANDLE_NO_FREE(cmd))
+		if (completed == buf)
 			break;
 
-		if (completed && !HANDLE_IS_NO_FREE(completed))
-			kfree(completed);
+		if (completed)
+			um_pci_free_buf(dev, completed);
 
 		if (WARN_ONCE(virtqueue_is_broken(dev->cmd_vq) ||
 			      ++delay_count > um_pci_max_delay_us,
@@ -172,8 +212,11 @@ static int um_pci_send_cmd(struct um_pci_device *dev,
 	}
 	clear_bit(UM_PCI_STAT_WAITING, &dev->status);
 
-out:
-	put_cpu_var(um_pci_msg_bufs);
+	if (bounce_out)
+		memcpy(out, buf->data, out_size);
+
+	um_pci_free_buf(dev, buf);
+
 	return ret;
 }
 
@@ -187,20 +230,13 @@ static unsigned long um_pci_cfgspace_read(void *priv, unsigned int offset,
 		.size = size,
 		.addr = offset,
 	};
-	/* buf->data is maximum size - we may only use parts of it */
-	struct um_pci_message_buffer *buf;
-	u8 *data;
-	unsigned long ret = ULONG_MAX;
-	size_t bytes = sizeof(buf->data);
+	/* max 8, we might not use it all */
+	u8 data[8];
 
 	if (!dev)
 		return ULONG_MAX;
 
-	buf = get_cpu_var(um_pci_msg_bufs);
-	data = buf->data;
-
-	if (buf)
-		memset(data, 0xff, bytes);
+	memset(data, 0xff, sizeof(data));
 
 	switch (size) {
 	case 1:
@@ -212,34 +248,26 @@ static unsigned long um_pci_cfgspace_read(void *priv, unsigned int offset,
 		break;
 	default:
 		WARN(1, "invalid config space read size %d\n", size);
-		goto out;
+		return ULONG_MAX;
 	}
 
-	if (um_pci_send_cmd(dev, &hdr, sizeof(hdr), NULL, 0, data, bytes))
-		goto out;
+	if (um_pci_send_cmd(dev, &hdr, sizeof(hdr), NULL, 0, data, size))
+		return ULONG_MAX;
 
 	switch (size) {
 	case 1:
-		ret = data[0];
-		break;
+		return data[0];
 	case 2:
-		ret = le16_to_cpup((void *)data);
-		break;
+		return le16_to_cpup((void *)data);
 	case 4:
-		ret = le32_to_cpup((void *)data);
-		break;
+		return le32_to_cpup((void *)data);
 #ifdef CONFIG_64BIT
 	case 8:
-		ret = le64_to_cpup((void *)data);
-		break;
+		return le64_to_cpup((void *)data);
 #endif
 	default:
-		break;
+		return ULONG_MAX;
 	}
-
-out:
-	put_cpu_var(um_pci_msg_bufs);
-	return ret;
 }
 
 static void um_pci_cfgspace_write(void *priv, unsigned int offset, int size,
@@ -312,13 +340,8 @@ static void um_pci_bar_copy_from(void *priv, void *buffer,
 static unsigned long um_pci_bar_read(void *priv, unsigned int offset,
 				     int size)
 {
-	/* buf->data is maximum size - we may only use parts of it */
-	struct um_pci_message_buffer *buf;
-	u8 *data;
-	unsigned long ret = ULONG_MAX;
-
-	buf = get_cpu_var(um_pci_msg_bufs);
-	data = buf->data;
+	/* 8 is maximum size - we may only use parts of it */
+	u8 data[8];
 
 	switch (size) {
 	case 1:
@@ -330,33 +353,25 @@ static unsigned long um_pci_bar_read(void *priv, unsigned int offset,
 		break;
 	default:
 		WARN(1, "invalid config space read size %d\n", size);
-		goto out;
+		return ULONG_MAX;
 	}
 
 	um_pci_bar_copy_from(priv, data, offset, size);
 
 	switch (size) {
 	case 1:
-		ret = data[0];
-		break;
+		return data[0];
 	case 2:
-		ret = le16_to_cpup((void *)data);
-		break;
+		return le16_to_cpup((void *)data);
 	case 4:
-		ret = le32_to_cpup((void *)data);
-		break;
+		return le32_to_cpup((void *)data);
 #ifdef CONFIG_64BIT
 	case 8:
-		ret = le64_to_cpup((void *)data);
-		break;
+		return le64_to_cpup((void *)data);
 #endif
 	default:
-		break;
+		return ULONG_MAX;
 	}
-
-out:
-	put_cpu_var(um_pci_msg_bufs);
-	return ret;
 }
 
 static void um_pci_bar_copy_to(void *priv, unsigned int offset,
@@ -523,11 +538,8 @@ static void um_pci_cmd_vq_cb(struct virtqueue *vq)
 	if (test_bit(UM_PCI_STAT_WAITING, &dev->status))
 		return;
 
-	while ((cmd = virtqueue_get_buf(vq, &len))) {
-		if (WARN_ON(HANDLE_IS_NO_FREE(cmd)))
-			continue;
-		kfree(cmd);
-	}
+	while ((cmd = virtqueue_get_buf(vq, &len)))
+		um_pci_free_buf(dev, cmd);
 }
 
 static void um_pci_irq_vq_cb(struct virtqueue *vq)
@@ -1006,10 +1018,6 @@ static int __init um_pci_init(void)
 		 "No virtio device ID configured for PCI - no PCI support\n"))
 		return 0;
 
-	um_pci_msg_bufs = alloc_percpu(struct um_pci_message_buffer);
-	if (!um_pci_msg_bufs)
-		return -ENOMEM;
-
 	bridge = pci_alloc_host_bridge(0);
 	if (!bridge) {
 		err = -ENOMEM;
@@ -1070,7 +1078,6 @@ free:
 		pci_free_resource_list(&bridge->windows);
 		pci_free_host_bridge(bridge);
 	}
-	free_percpu(um_pci_msg_bufs);
 	return err;
 }
 module_init(um_pci_init);
@@ -1082,6 +1089,5 @@ static void __exit um_pci_exit(void)
 	irq_domain_remove(um_pci_inner_domain);
 	pci_free_resource_list(&bridge->windows);
 	pci_free_host_bridge(bridge);
-	free_percpu(um_pci_msg_bufs);
 }
 module_exit(um_pci_exit);
diff --git a/arch/um/drivers/virtio_uml.c b/arch/um/drivers/virtio_uml.c
index 65df43fa9be5..ad8d78fb1d9a 100644
--- a/arch/um/drivers/virtio_uml.c
+++ b/arch/um/drivers/virtio_uml.c
@@ -52,7 +52,7 @@ struct virtio_uml_device {
 	struct platform_device *pdev;
 	struct virtio_uml_platform_data *pdata;
 
-	spinlock_t sock_lock;
+	raw_spinlock_t sock_lock;
 	int sock, req_fd, irq;
 	u64 features;
 	u64 protocol_features;
@@ -246,7 +246,7 @@ static int vhost_user_send(struct virtio_uml_device *vu_dev,
 	if (request_ack)
 		msg->header.flags |= VHOST_USER_FLAG_NEED_REPLY;
 
-	spin_lock_irqsave(&vu_dev->sock_lock, flags);
+	raw_spin_lock_irqsave(&vu_dev->sock_lock, flags);
 	rc = full_sendmsg_fds(vu_dev->sock, msg, size, fds, num_fds);
 	if (rc < 0)
 		goto out;
@@ -266,7 +266,7 @@ static int vhost_user_send(struct virtio_uml_device *vu_dev,
 	}
 
 out:
-	spin_unlock_irqrestore(&vu_dev->sock_lock, flags);
+	raw_spin_unlock_irqrestore(&vu_dev->sock_lock, flags);
 	return rc;
 }
 
@@ -1239,7 +1239,7 @@ static int virtio_uml_probe(struct platform_device *pdev)
 		goto error_free;
 	vu_dev->sock = rc;
 
-	spin_lock_init(&vu_dev->sock_lock);
+	raw_spin_lock_init(&vu_dev->sock_lock);
 
 	rc = vhost_user_init(vu_dev);
 	if (rc)
diff --git a/arch/um/kernel/irq.c b/arch/um/kernel/irq.c
index 338450741aac..a4991746f5ea 100644
--- a/arch/um/kernel/irq.c
+++ b/arch/um/kernel/irq.c
@@ -52,7 +52,7 @@ struct irq_entry {
 	bool sigio_workaround;
 };
 
-static DEFINE_SPINLOCK(irq_lock);
+static DEFINE_RAW_SPINLOCK(irq_lock);
 static LIST_HEAD(active_fds);
 static DECLARE_BITMAP(irqs_allocated, UM_LAST_SIGNAL_IRQ);
 static bool irqs_suspended;
@@ -257,7 +257,7 @@ static struct irq_entry *get_irq_entry_by_fd(int fd)
 	return NULL;
 }
 
-static void free_irq_entry(struct irq_entry *to_free, bool remove)
+static void remove_irq_entry(struct irq_entry *to_free, bool remove)
 {
 	if (!to_free)
 		return;
@@ -265,7 +265,6 @@ static void free_irq_entry(struct irq_entry *to_free, bool remove)
 	if (remove)
 		os_del_epoll_fd(to_free->fd);
 	list_del(&to_free->list);
-	kfree(to_free);
 }
 
 static bool update_irq_entry(struct irq_entry *entry)
@@ -286,17 +285,19 @@ static bool update_irq_entry(struct irq_entry *entry)
 	return false;
 }
 
-static void update_or_free_irq_entry(struct irq_entry *entry)
+static struct irq_entry *update_or_remove_irq_entry(struct irq_entry *entry)
 {
-	if (!update_irq_entry(entry))
-		free_irq_entry(entry, false);
+	if (update_irq_entry(entry))
+		return NULL;
+	remove_irq_entry(entry, false);
+	return entry;
 }
 
 static int activate_fd(int irq, int fd, enum um_irq_type type, void *dev_id,
 		       void (*timetravel_handler)(int, int, void *,
 						  struct time_travel_event *))
 {
-	struct irq_entry *irq_entry;
+	struct irq_entry *irq_entry, *to_free = NULL;
 	int err, events = os_event_mask(type);
 	unsigned long flags;
 
@@ -304,9 +305,10 @@ static int activate_fd(int irq, int fd, enum um_irq_type type, void *dev_id,
 	if (err < 0)
 		goto out;
 
-	spin_lock_irqsave(&irq_lock, flags);
+	raw_spin_lock_irqsave(&irq_lock, flags);
 	irq_entry = get_irq_entry_by_fd(fd);
 	if (irq_entry) {
+already:
 		/* cannot register the same FD twice with the same type */
 		if (WARN_ON(irq_entry->reg[type].events)) {
 			err = -EALREADY;
@@ -316,11 +318,22 @@ static int activate_fd(int irq, int fd, enum um_irq_type type, void *dev_id,
 		/* temporarily disable to avoid IRQ-side locking */
 		os_del_epoll_fd(fd);
 	} else {
-		irq_entry = kzalloc(sizeof(*irq_entry), GFP_ATOMIC);
-		if (!irq_entry) {
-			err = -ENOMEM;
-			goto out_unlock;
+		struct irq_entry *new;
+
+		/* don't restore interrupts */
+		raw_spin_unlock(&irq_lock);
+		new = kzalloc(sizeof(*irq_entry), GFP_ATOMIC);
+		if (!new) {
+			local_irq_restore(flags);
+			return -ENOMEM;
 		}
+		raw_spin_lock(&irq_lock);
+		irq_entry = get_irq_entry_by_fd(fd);
+		if (irq_entry) {
+			to_free = new;
+			goto already;
+		}
+		irq_entry = new;
 		irq_entry->fd = fd;
 		list_add_tail(&irq_entry->list, &active_fds);
 		maybe_sigio_broken(fd);
@@ -339,12 +352,11 @@ static int activate_fd(int irq, int fd, enum um_irq_type type, void *dev_id,
 #endif
 
 	WARN_ON(!update_irq_entry(irq_entry));
-	spin_unlock_irqrestore(&irq_lock, flags);
-
-	return 0;
+	err = 0;
 out_unlock:
-	spin_unlock_irqrestore(&irq_lock, flags);
+	raw_spin_unlock_irqrestore(&irq_lock, flags);
 out:
+	kfree(to_free);
 	return err;
 }
 
@@ -358,19 +370,20 @@ void free_irq_by_fd(int fd)
 	struct irq_entry *to_free;
 	unsigned long flags;
 
-	spin_lock_irqsave(&irq_lock, flags);
+	raw_spin_lock_irqsave(&irq_lock, flags);
 	to_free = get_irq_entry_by_fd(fd);
-	free_irq_entry(to_free, true);
-	spin_unlock_irqrestore(&irq_lock, flags);
+	remove_irq_entry(to_free, true);
+	raw_spin_unlock_irqrestore(&irq_lock, flags);
+	kfree(to_free);
 }
 EXPORT_SYMBOL(free_irq_by_fd);
 
 static void free_irq_by_irq_and_dev(unsigned int irq, void *dev)
 {
-	struct irq_entry *entry;
+	struct irq_entry *entry, *to_free = NULL;
 	unsigned long flags;
 
-	spin_lock_irqsave(&irq_lock, flags);
+	raw_spin_lock_irqsave(&irq_lock, flags);
 	list_for_each_entry(entry, &active_fds, list) {
 		enum um_irq_type i;
 
@@ -386,12 +399,13 @@ static void free_irq_by_irq_and_dev(unsigned int irq, void *dev)
 
 			os_del_epoll_fd(entry->fd);
 			reg->events = 0;
-			update_or_free_irq_entry(entry);
+			to_free = update_or_remove_irq_entry(entry);
 			goto out;
 		}
 	}
 out:
-	spin_unlock_irqrestore(&irq_lock, flags);
+	raw_spin_unlock_irqrestore(&irq_lock, flags);
+	kfree(to_free);
 }
 
 void deactivate_fd(int fd, int irqnum)
@@ -402,7 +416,7 @@ void deactivate_fd(int fd, int irqnum)
 
 	os_del_epoll_fd(fd);
 
-	spin_lock_irqsave(&irq_lock, flags);
+	raw_spin_lock_irqsave(&irq_lock, flags);
 	entry = get_irq_entry_by_fd(fd);
 	if (!entry)
 		goto out;
@@ -414,9 +428,10 @@ void deactivate_fd(int fd, int irqnum)
 			entry->reg[i].events = 0;
 	}
 
-	update_or_free_irq_entry(entry);
+	entry = update_or_remove_irq_entry(entry);
 out:
-	spin_unlock_irqrestore(&irq_lock, flags);
+	raw_spin_unlock_irqrestore(&irq_lock, flags);
+	kfree(entry);
 
 	ignore_sigio_fd(fd);
 }
@@ -546,7 +561,7 @@ void um_irqs_suspend(void)
 
 	irqs_suspended = true;
 
-	spin_lock_irqsave(&irq_lock, flags);
+	raw_spin_lock_irqsave(&irq_lock, flags);
 	list_for_each_entry(entry, &active_fds, list) {
 		enum um_irq_type t;
 		bool clear = true;
@@ -579,7 +594,7 @@ void um_irqs_suspend(void)
 				!__ignore_sigio_fd(entry->fd);
 		}
 	}
-	spin_unlock_irqrestore(&irq_lock, flags);
+	raw_spin_unlock_irqrestore(&irq_lock, flags);
 }
 
 void um_irqs_resume(void)
@@ -588,7 +603,7 @@ void um_irqs_resume(void)
 	unsigned long flags;
 
 
-	spin_lock_irqsave(&irq_lock, flags);
+	raw_spin_lock_irqsave(&irq_lock, flags);
 	list_for_each_entry(entry, &active_fds, list) {
 		if (entry->suspended) {
 			int err = os_set_fd_async(entry->fd);
@@ -602,7 +617,7 @@ void um_irqs_resume(void)
 			}
 		}
 	}
-	spin_unlock_irqrestore(&irq_lock, flags);
+	raw_spin_unlock_irqrestore(&irq_lock, flags);
 
 	irqs_suspended = false;
 	send_sigio_to_self();
@@ -613,7 +628,7 @@ static int normal_irq_set_wake(struct irq_data *d, unsigned int on)
 	struct irq_entry *entry;
 	unsigned long flags;
 
-	spin_lock_irqsave(&irq_lock, flags);
+	raw_spin_lock_irqsave(&irq_lock, flags);
 	list_for_each_entry(entry, &active_fds, list) {
 		enum um_irq_type t;
 
@@ -628,7 +643,7 @@ static int normal_irq_set_wake(struct irq_data *d, unsigned int on)
 		}
 	}
 unlock:
-	spin_unlock_irqrestore(&irq_lock, flags);
+	raw_spin_unlock_irqrestore(&irq_lock, flags);
 	return 0;
 }
 #else
diff --git a/arch/um/kernel/process.c b/arch/um/kernel/process.c
index e5a2d4d897e0..0cd6fad3d908 100644
--- a/arch/um/kernel/process.c
+++ b/arch/um/kernel/process.c
@@ -191,7 +191,15 @@ void initial_thread_cb(void (*proc)(void *), void *arg)
 int arch_dup_task_struct(struct task_struct *dst,
 			 struct task_struct *src)
 {
-	memcpy(dst, src, arch_task_struct_size);
+	/* init_task is not dynamically sized (missing FPU state) */
+	if (unlikely(src == &init_task)) {
+		memcpy(dst, src, sizeof(init_task));
+		memset((void *)dst + sizeof(init_task), 0,
+		       arch_task_struct_size - sizeof(init_task));
+	} else {
+		memcpy(dst, src, arch_task_struct_size);
+	}
+
 	return 0;
 }
 
diff --git a/arch/um/os-Linux/skas/process.c b/arch/um/os-Linux/skas/process.c
index f683cfc9e51a..e2f8f156402f 100644
--- a/arch/um/os-Linux/skas/process.c
+++ b/arch/um/os-Linux/skas/process.c
@@ -181,6 +181,10 @@ extern char __syscall_stub_start[];
 
 static int stub_exe_fd;
 
+#ifndef CLOSE_RANGE_CLOEXEC
+#define CLOSE_RANGE_CLOEXEC	(1U << 2)
+#endif
+
 static int userspace_tramp(void *stack)
 {
 	char *const argv[] = { "uml-userspace", NULL };
@@ -202,8 +206,12 @@ static int userspace_tramp(void *stack)
 	init_data.stub_data_fd = phys_mapping(uml_to_phys(stack), &offset);
 	init_data.stub_data_offset = MMAP_OFFSET(offset);
 
-	/* Set CLOEXEC on all FDs and then unset on all memory related FDs */
-	close_range(0, ~0U, CLOSE_RANGE_CLOEXEC);
+	/*
+	 * Avoid leaking unneeded FDs to the stub by setting CLOEXEC on all FDs
+	 * and then unsetting it on all memory related FDs.
+	 * This is not strictly necessary from a safety perspective.
+	 */
+	syscall(__NR_close_range, 0, ~0U, CLOSE_RANGE_CLOEXEC);
 
 	fcntl(init_data.stub_data_fd, F_SETFD, 0);
 	for (iomem = iomem_regions; iomem; iomem = iomem->next)
@@ -224,7 +232,9 @@ static int userspace_tramp(void *stack)
 	if (ret != sizeof(init_data))
 		exit(4);
 
-	execveat(stub_exe_fd, "", argv, NULL, AT_EMPTY_PATH);
+	/* Raw execveat for compatibility with older libc versions */
+	syscall(__NR_execveat, stub_exe_fd, (unsigned long)"",
+		(unsigned long)argv, NULL, AT_EMPTY_PATH);
 
 	exit(5);
 }
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 87198d957e2f..0e27ebd7e36a 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1341,6 +1341,7 @@ config X86_REBOOTFIXUPS
 config MICROCODE
 	def_bool y
 	depends on CPU_SUP_AMD || CPU_SUP_INTEL
+	select CRYPTO_LIB_SHA256 if CPU_SUP_AMD
 
 config MICROCODE_INITRD32
 	def_bool y
@@ -2599,7 +2600,8 @@ config MITIGATION_IBPB_ENTRY
 	depends on CPU_SUP_AMD && X86_64
 	default y
 	help
-	  Compile the kernel with support for the retbleed=ibpb mitigation.
+	  Compile the kernel with support for the retbleed=ibpb and
+	  spec_rstack_overflow={ibpb,ibpb-vmexit} mitigations.
 
 config MITIGATION_IBRS_ENTRY
 	bool "Enable IBRS on kernel entry"
diff --git a/arch/x86/boot/compressed/pgtable_64.c b/arch/x86/boot/compressed/pgtable_64.c
index c882e1f67af0..d8c5de40669d 100644
--- a/arch/x86/boot/compressed/pgtable_64.c
+++ b/arch/x86/boot/compressed/pgtable_64.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include "misc.h"
 #include <asm/bootparam.h>
+#include <asm/bootparam_utils.h>
 #include <asm/e820/types.h>
 #include <asm/processor.h>
 #include "pgtable.h"
@@ -107,6 +108,7 @@ asmlinkage void configure_5level_paging(struct boot_params *bp, void *pgtable)
 	bool l5_required = false;
 
 	/* Initialize boot_params. Required for cmdline_find_option_bool(). */
+	sanitize_boot_params(bp);
 	boot_params_ptr = bp;
 
 	/*
diff --git a/arch/x86/coco/sev/core.c b/arch/x86/coco/sev/core.c
index 82492efc5d94..96c7bc698e6b 100644
--- a/arch/x86/coco/sev/core.c
+++ b/arch/x86/coco/sev/core.c
@@ -2853,19 +2853,8 @@ struct snp_msg_desc *snp_msg_alloc(void)
 	if (!mdesc->response)
 		goto e_free_request;
 
-	mdesc->certs_data = alloc_shared_pages(SEV_FW_BLOB_MAX_SIZE);
-	if (!mdesc->certs_data)
-		goto e_free_response;
-
-	/* initial the input address for guest request */
-	mdesc->input.req_gpa = __pa(mdesc->request);
-	mdesc->input.resp_gpa = __pa(mdesc->response);
-	mdesc->input.data_gpa = __pa(mdesc->certs_data);
-
 	return mdesc;
 
-e_free_response:
-	free_shared_pages(mdesc->response, sizeof(struct snp_guest_msg));
 e_free_request:
 	free_shared_pages(mdesc->request, sizeof(struct snp_guest_msg));
 e_unmap:
@@ -2885,7 +2874,6 @@ void snp_msg_free(struct snp_msg_desc *mdesc)
 	kfree(mdesc->ctx);
 	free_shared_pages(mdesc->response, sizeof(struct snp_guest_msg));
 	free_shared_pages(mdesc->request, sizeof(struct snp_guest_msg));
-	free_shared_pages(mdesc->certs_data, SEV_FW_BLOB_MAX_SIZE);
 	iounmap((__force void __iomem *)mdesc->secrets);
 
 	memset(mdesc, 0, sizeof(*mdesc));
@@ -3054,7 +3042,7 @@ retry_request:
 	 * sequence number must be incremented or the VMPCK must be deleted to
 	 * prevent reuse of the IV.
 	 */
-	rc = snp_issue_guest_request(req, &mdesc->input, rio);
+	rc = snp_issue_guest_request(req, &req->input, rio);
 	switch (rc) {
 	case -ENOSPC:
 		/*
@@ -3064,7 +3052,7 @@ retry_request:
 		 * order to increment the sequence number and thus avoid
 		 * IV reuse.
 		 */
-		override_npages = mdesc->input.data_npages;
+		override_npages = req->input.data_npages;
 		req->exit_code	= SVM_VMGEXIT_GUEST_REQUEST;
 
 		/*
@@ -3120,7 +3108,7 @@ retry_request:
 	}
 
 	if (override_npages)
-		mdesc->input.data_npages = override_npages;
+		req->input.data_npages = override_npages;
 
 	return rc;
 }
@@ -3158,6 +3146,11 @@ int snp_send_guest_request(struct snp_msg_desc *mdesc, struct snp_guest_req *req
 	 */
 	memcpy(mdesc->request, &mdesc->secret_request, sizeof(mdesc->secret_request));
 
+	/* Initialize the input address for guest request */
+	req->input.req_gpa = __pa(mdesc->request);
+	req->input.resp_gpa = __pa(mdesc->response);
+	req->input.data_gpa = req->certs_data ? __pa(req->certs_data) : 0;
+
 	rc = __handle_guest_request(mdesc, req, rio);
 	if (rc) {
 		if (rc == -EIO &&
diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c
index 94941c5a10ac..14db5b85114c 100644
--- a/arch/x86/entry/common.c
+++ b/arch/x86/entry/common.c
@@ -190,6 +190,7 @@ static __always_inline bool int80_is_external(void)
 
 /**
  * do_int80_emulation - 32-bit legacy syscall C entry from asm
+ * @regs: syscall arguments in struct pt_args on the stack.
  *
  * This entry point can be used by 32-bit and 64-bit programs to perform
  * 32-bit system calls.  Instances of INT $0x80 can be found inline in
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 8f218ac0d445..2092d615333d 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -628,7 +628,7 @@ int x86_pmu_hw_config(struct perf_event *event)
 	if (event->attr.type == event->pmu->type)
 		event->hw.config |= x86_pmu_get_event_config(event);
 
-	if (event->attr.sample_period && x86_pmu.limit_period) {
+	if (!event->attr.freq && x86_pmu.limit_period) {
 		s64 left = event->attr.sample_period;
 		x86_pmu.limit_period(event, &left);
 		if (left > event->attr.sample_period)
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 7601196d1d18..cdb19e3ba3aa 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -397,34 +397,28 @@ static struct event_constraint intel_lnc_event_constraints[] = {
 	METRIC_EVENT_CONSTRAINT(INTEL_TD_METRIC_FETCH_LAT, 6),
 	METRIC_EVENT_CONSTRAINT(INTEL_TD_METRIC_MEM_BOUND, 7),
 
+	INTEL_EVENT_CONSTRAINT(0x20, 0xf),
+
+	INTEL_UEVENT_CONSTRAINT(0x012a, 0xf),
+	INTEL_UEVENT_CONSTRAINT(0x012b, 0xf),
 	INTEL_UEVENT_CONSTRAINT(0x0148, 0x4),
 	INTEL_UEVENT_CONSTRAINT(0x0175, 0x4),
 
 	INTEL_EVENT_CONSTRAINT(0x2e, 0x3ff),
 	INTEL_EVENT_CONSTRAINT(0x3c, 0x3ff),
-	/*
-	 * Generally event codes < 0x90 are restricted to counters 0-3.
-	 * The 0x2E and 0x3C are exception, which has no restriction.
-	 */
-	INTEL_EVENT_CONSTRAINT_RANGE(0x01, 0x8f, 0xf),
 
-	INTEL_UEVENT_CONSTRAINT(0x01a3, 0xf),
-	INTEL_UEVENT_CONSTRAINT(0x02a3, 0xf),
 	INTEL_UEVENT_CONSTRAINT(0x08a3, 0x4),
 	INTEL_UEVENT_CONSTRAINT(0x0ca3, 0x4),
 	INTEL_UEVENT_CONSTRAINT(0x04a4, 0x1),
 	INTEL_UEVENT_CONSTRAINT(0x08a4, 0x1),
 	INTEL_UEVENT_CONSTRAINT(0x10a4, 0x1),
 	INTEL_UEVENT_CONSTRAINT(0x01b1, 0x8),
+	INTEL_UEVENT_CONSTRAINT(0x01cd, 0x3fc),
 	INTEL_UEVENT_CONSTRAINT(0x02cd, 0x3),
-	INTEL_EVENT_CONSTRAINT(0xce, 0x1),
 
 	INTEL_EVENT_CONSTRAINT_RANGE(0xd0, 0xdf, 0xf),
-	/*
-	 * Generally event codes >= 0x90 are likely to have no restrictions.
-	 * The exception are defined as above.
-	 */
-	INTEL_EVENT_CONSTRAINT_RANGE(0x90, 0xfe, 0x3ff),
+
+	INTEL_UEVENT_CONSTRAINT(0x00e0, 0xf),
 
 	EVENT_CONSTRAINT_END
 };
@@ -3958,6 +3952,85 @@ static inline bool intel_pmu_has_cap(struct perf_event *event, int idx)
 	return test_bit(idx, (unsigned long *)&intel_cap->capabilities);
 }
 
+static u64 intel_pmu_freq_start_period(struct perf_event *event)
+{
+	int type = event->attr.type;
+	u64 config, factor;
+	s64 start;
+
+	/*
+	 * The 127 is the lowest possible recommended SAV (sample after value)
+	 * for a 4000 freq (default freq), according to the event list JSON file.
+	 * Also, assume the workload is idle 50% time.
+	 */
+	factor = 64 * 4000;
+	if (type != PERF_TYPE_HARDWARE && type != PERF_TYPE_HW_CACHE)
+		goto end;
+
+	/*
+	 * The estimation of the start period in the freq mode is
+	 * based on the below assumption.
+	 *
+	 * For a cycles or an instructions event, 1GHZ of the
+	 * underlying platform, 1 IPC. The workload is idle 50% time.
+	 * The start period = 1,000,000,000 * 1 / freq / 2.
+	 *		    = 500,000,000 / freq
+	 *
+	 * Usually, the branch-related events occur less than the
+	 * instructions event. According to the Intel event list JSON
+	 * file, the SAV (sample after value) of a branch-related event
+	 * is usually 1/4 of an instruction event.
+	 * The start period of branch-related events = 125,000,000 / freq.
+	 *
+	 * The cache-related events occurs even less. The SAV is usually
+	 * 1/20 of an instruction event.
+	 * The start period of cache-related events = 25,000,000 / freq.
+	 */
+	config = event->attr.config & PERF_HW_EVENT_MASK;
+	if (type == PERF_TYPE_HARDWARE) {
+		switch (config) {
+		case PERF_COUNT_HW_CPU_CYCLES:
+		case PERF_COUNT_HW_INSTRUCTIONS:
+		case PERF_COUNT_HW_BUS_CYCLES:
+		case PERF_COUNT_HW_STALLED_CYCLES_FRONTEND:
+		case PERF_COUNT_HW_STALLED_CYCLES_BACKEND:
+		case PERF_COUNT_HW_REF_CPU_CYCLES:
+			factor = 500000000;
+			break;
+		case PERF_COUNT_HW_BRANCH_INSTRUCTIONS:
+		case PERF_COUNT_HW_BRANCH_MISSES:
+			factor = 125000000;
+			break;
+		case PERF_COUNT_HW_CACHE_REFERENCES:
+		case PERF_COUNT_HW_CACHE_MISSES:
+			factor = 25000000;
+			break;
+		default:
+			goto end;
+		}
+	}
+
+	if (type == PERF_TYPE_HW_CACHE)
+		factor = 25000000;
+end:
+	/*
+	 * Usually, a prime or a number with less factors (close to prime)
+	 * is chosen as an SAV, which makes it less likely that the sampling
+	 * period synchronizes with some periodic event in the workload.
+	 * Minus 1 to make it at least avoiding values near power of twos
+	 * for the default freq.
+	 */
+	start = DIV_ROUND_UP_ULL(factor, event->attr.sample_freq) - 1;
+
+	if (start > x86_pmu.max_period)
+		start = x86_pmu.max_period;
+
+	if (x86_pmu.limit_period)
+		x86_pmu.limit_period(event, &start);
+
+	return start;
+}
+
 static int intel_pmu_hw_config(struct perf_event *event)
 {
 	int ret = x86_pmu_hw_config(event);
@@ -3969,6 +4042,12 @@ static int intel_pmu_hw_config(struct perf_event *event)
 	if (ret)
 		return ret;
 
+	if (event->attr.freq && event->attr.sample_freq) {
+		event->hw.sample_period = intel_pmu_freq_start_period(event);
+		event->hw.last_period = event->hw.sample_period;
+		local64_set(&event->hw.period_left, event->hw.sample_period);
+	}
+
 	if (event->attr.precise_ip) {
 		if ((event->attr.config & INTEL_ARCH_EVENT_MASK) == INTEL_FIXED_VLBR_EVENT)
 			return -EINVAL;
@@ -4905,20 +4984,22 @@ static inline bool intel_pmu_broken_perf_cap(void)
 
 static void update_pmu_cap(struct x86_hybrid_pmu *pmu)
 {
-	unsigned int sub_bitmaps, eax, ebx, ecx, edx;
+	unsigned int cntr, fixed_cntr, ecx, edx;
+	union cpuid35_eax eax;
+	union cpuid35_ebx ebx;
 
-	cpuid(ARCH_PERFMON_EXT_LEAF, &sub_bitmaps, &ebx, &ecx, &edx);
+	cpuid(ARCH_PERFMON_EXT_LEAF, &eax.full, &ebx.full, &ecx, &edx);
 
-	if (ebx & ARCH_PERFMON_EXT_UMASK2)
+	if (ebx.split.umask2)
 		pmu->config_mask |= ARCH_PERFMON_EVENTSEL_UMASK2;
-	if (ebx & ARCH_PERFMON_EXT_EQ)
+	if (ebx.split.eq)
 		pmu->config_mask |= ARCH_PERFMON_EVENTSEL_EQ;
 
-	if (sub_bitmaps & ARCH_PERFMON_NUM_COUNTER_LEAF_BIT) {
+	if (eax.split.cntr_subleaf) {
 		cpuid_count(ARCH_PERFMON_EXT_LEAF, ARCH_PERFMON_NUM_COUNTER_LEAF,
-			    &eax, &ebx, &ecx, &edx);
-		pmu->cntr_mask64 = eax;
-		pmu->fixed_cntr_mask64 = ebx;
+			    &cntr, &fixed_cntr, &ecx, &edx);
+		pmu->cntr_mask64 = cntr;
+		pmu->fixed_cntr_mask64 = fixed_cntr;
 	}
 
 	if (!intel_pmu_broken_perf_cap()) {
@@ -4941,11 +5022,6 @@ static void intel_pmu_check_hybrid_pmus(struct x86_hybrid_pmu *pmu)
 	else
 		pmu->intel_ctrl &= ~(1ULL << GLOBAL_CTRL_EN_PERF_METRICS);
 
-	if (pmu->intel_cap.pebs_output_pt_available)
-		pmu->pmu.capabilities |= PERF_PMU_CAP_AUX_OUTPUT;
-	else
-		pmu->pmu.capabilities &= ~PERF_PMU_CAP_AUX_OUTPUT;
-
 	intel_pmu_check_event_constraints(pmu->event_constraints,
 					  pmu->cntr_mask64,
 					  pmu->fixed_cntr_mask64,
@@ -5023,9 +5099,6 @@ static bool init_hybrid_pmu(int cpu)
 
 	pr_info("%s PMU driver: ", pmu->name);
 
-	if (pmu->intel_cap.pebs_output_pt_available)
-		pr_cont("PEBS-via-PT ");
-
 	pr_cont("\n");
 
 	x86_pmu_show_pmu_cap(&pmu->pmu);
@@ -5048,8 +5121,11 @@ static void intel_pmu_cpu_starting(int cpu)
 
 	init_debug_store_on_cpu(cpu);
 	/*
-	 * Deal with CPUs that don't clear their LBRs on power-up.
+	 * Deal with CPUs that don't clear their LBRs on power-up, and that may
+	 * even boot with LBRs enabled.
 	 */
+	if (!static_cpu_has(X86_FEATURE_ARCH_LBR) && x86_pmu.lbr_nr)
+		msr_clear_bit(MSR_IA32_DEBUGCTLMSR, DEBUGCTLMSR_LBR_BIT);
 	intel_pmu_lbr_reset();
 
 	cpuc->lbr_sel = NULL;
@@ -6370,11 +6446,9 @@ static __always_inline int intel_pmu_init_hybrid(enum hybrid_pmu_type pmus)
 		pmu->intel_cap.capabilities = x86_pmu.intel_cap.capabilities;
 		if (pmu->pmu_type & hybrid_small_tiny) {
 			pmu->intel_cap.perf_metrics = 0;
-			pmu->intel_cap.pebs_output_pt_available = 1;
 			pmu->mid_ack = true;
 		} else if (pmu->pmu_type & hybrid_big) {
 			pmu->intel_cap.perf_metrics = 1;
-			pmu->intel_cap.pebs_output_pt_available = 0;
 			pmu->late_ack = true;
 		}
 	}
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index ba74e1198328..f122882ef278 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -1199,7 +1199,7 @@ struct event_constraint intel_lnc_pebs_event_constraints[] = {
 	INTEL_FLAGS_UEVENT_CONSTRAINT(0x100, 0x100000000ULL),	/* INST_RETIRED.PREC_DIST */
 	INTEL_FLAGS_UEVENT_CONSTRAINT(0x0400, 0x800000000ULL),
 
-	INTEL_HYBRID_LDLAT_CONSTRAINT(0x1cd, 0x3ff),
+	INTEL_HYBRID_LDLAT_CONSTRAINT(0x1cd, 0x3fc),
 	INTEL_HYBRID_STLAT_CONSTRAINT(0x2cd, 0x3),
 	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x11d0, 0xf),	/* MEM_INST_RETIRED.STLB_MISS_LOADS */
 	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x12d0, 0xf),	/* MEM_INST_RETIRED.STLB_MISS_STORES */
@@ -2578,7 +2578,15 @@ void __init intel_ds_init(void)
 			}
 			pr_cont("PEBS fmt4%c%s, ", pebs_type, pebs_qual);
 
-			if (!is_hybrid() && x86_pmu.intel_cap.pebs_output_pt_available) {
+			/*
+			 * The PEBS-via-PT is not supported on hybrid platforms,
+			 * because not all CPUs of a hybrid machine support it.
+			 * The global x86_pmu.intel_cap, which only contains the
+			 * common capabilities, is used to check the availability
+			 * of the feature. The per-PMU pebs_output_pt_available
+			 * in a hybrid machine should be ignored.
+			 */
+			if (x86_pmu.intel_cap.pebs_output_pt_available) {
 				pr_cont("PEBS-via-PT, ");
 				x86_get_pmu(smp_processor_id())->capabilities |= PERF_PMU_CAP_AUX_OUTPUT;
 			}
diff --git a/arch/x86/events/rapl.c b/arch/x86/events/rapl.c
index d3bb3865c1b1..6941f4811bec 100644
--- a/arch/x86/events/rapl.c
+++ b/arch/x86/events/rapl.c
@@ -370,6 +370,10 @@ static int rapl_pmu_event_init(struct perf_event *event)
 	unsigned int rapl_pmu_idx;
 	struct rapl_pmus *rapl_pmus;
 
+	/* only look at RAPL events */
+	if (event->attr.type != event->pmu->type)
+		return -ENOENT;
+
 	/* unsupported modes and filters */
 	if (event->attr.sample_period) /* no sampling */
 		return -EINVAL;
@@ -387,10 +391,6 @@ static int rapl_pmu_event_init(struct perf_event *event)
 	rapl_pmus_scope = rapl_pmus->pmu.scope;
 
 	if (rapl_pmus_scope == PERF_PMU_SCOPE_PKG || rapl_pmus_scope == PERF_PMU_SCOPE_DIE) {
-		/* only look at RAPL package events */
-		if (event->attr.type != rapl_pmus_pkg->pmu.type)
-			return -ENOENT;
-
 		cfg = array_index_nospec((long)cfg, NR_RAPL_PKG_DOMAINS + 1);
 		if (!cfg || cfg >= NR_RAPL_PKG_DOMAINS + 1)
 			return -EINVAL;
@@ -398,10 +398,6 @@ static int rapl_pmu_event_init(struct perf_event *event)
 		bit = cfg - 1;
 		event->hw.event_base = rapl_model->rapl_pkg_msrs[bit].msr;
 	} else if (rapl_pmus_scope == PERF_PMU_SCOPE_CORE) {
-		/* only look at RAPL core events */
-		if (event->attr.type != rapl_pmus_core->pmu.type)
-			return -ENOENT;
-
 		cfg = array_index_nospec((long)cfg, NR_RAPL_CORE_DOMAINS + 1);
 		if (!cfg || cfg >= NR_RAPL_PKG_DOMAINS + 1)
 			return -EINVAL;
@@ -883,6 +879,7 @@ static const struct x86_cpu_id rapl_model_match[] __initconst = {
 	X86_MATCH_VFM(INTEL_METEORLAKE_L,	&model_skl),
 	X86_MATCH_VFM(INTEL_ARROWLAKE_H,	&model_skl),
 	X86_MATCH_VFM(INTEL_ARROWLAKE,		&model_skl),
+	X86_MATCH_VFM(INTEL_ARROWLAKE_U,	&model_skl),
 	X86_MATCH_VFM(INTEL_LUNARLAKE_M,	&model_skl),
 	{},
 };
diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h
index c35550581da0..823c0434bbad 100644
--- a/arch/x86/include/asm/kvm-x86-ops.h
+++ b/arch/x86/include/asm/kvm-x86-ops.h
@@ -48,6 +48,7 @@ KVM_X86_OP(set_idt)
 KVM_X86_OP(get_gdt)
 KVM_X86_OP(set_gdt)
 KVM_X86_OP(sync_dirty_debug_regs)
+KVM_X86_OP(set_dr6)
 KVM_X86_OP(set_dr7)
 KVM_X86_OP(cache_reg)
 KVM_X86_OP(get_rflags)
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index b15cde0a9b5c..32ae3aa50c7e 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -780,6 +780,7 @@ struct kvm_vcpu_arch {
 	u32 pkru;
 	u32 hflags;
 	u64 efer;
+	u64 host_debugctl;
 	u64 apic_base;
 	struct kvm_lapic *apic;    /* kernel irqchip context */
 	bool load_eoi_exitmap_pending;
@@ -1696,6 +1697,7 @@ struct kvm_x86_ops {
 	void (*get_gdt)(struct kvm_vcpu *vcpu, struct desc_ptr *dt);
 	void (*set_gdt)(struct kvm_vcpu *vcpu, struct desc_ptr *dt);
 	void (*sync_dirty_debug_regs)(struct kvm_vcpu *vcpu);
+	void (*set_dr6)(struct kvm_vcpu *vcpu, unsigned long value);
 	void (*set_dr7)(struct kvm_vcpu *vcpu, unsigned long value);
 	void (*cache_reg)(struct kvm_vcpu *vcpu, enum kvm_reg reg);
 	unsigned long (*get_rflags)(struct kvm_vcpu *vcpu);
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 9a71880eec07..72765b2fe0d8 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -395,7 +395,8 @@
 #define MSR_IA32_PASID_VALID		BIT_ULL(31)
 
 /* DEBUGCTLMSR bits (others vary by model): */
-#define DEBUGCTLMSR_LBR			(1UL <<  0) /* last branch recording */
+#define DEBUGCTLMSR_LBR_BIT		0	     /* last branch recording */
+#define DEBUGCTLMSR_LBR			(1UL <<  DEBUGCTLMSR_LBR_BIT)
 #define DEBUGCTLMSR_BTF_SHIFT		1
 #define DEBUGCTLMSR_BTF			(1UL <<  1) /* single-step on branches */
 #define DEBUGCTLMSR_BUS_LOCK_DETECT	(1UL <<  2)
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index 7e8bf78c03d5..aee26bb8230f 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -198,9 +198,8 @@
 .endm
 
 /*
- * Equivalent to -mindirect-branch-cs-prefix; emit the 5 byte jmp/call
- * to the retpoline thunk with a CS prefix when the register requires
- * a RAX prefix byte to encode. Also see apply_retpolines().
+ * Emits a conditional CS prefix that is compatible with
+ * -mindirect-branch-cs-prefix.
  */
 .macro __CS_PREFIX reg:req
 	.irp rs,r8,r9,r10,r11,r12,r13,r14,r15
@@ -421,19 +420,26 @@ static inline void call_depth_return_thunk(void) {}
 #ifdef CONFIG_X86_64
 
 /*
+ * Emits a conditional CS prefix that is compatible with
+ * -mindirect-branch-cs-prefix.
+ */
+#define __CS_PREFIX(reg)				\
+	".irp rs,r8,r9,r10,r11,r12,r13,r14,r15\n"	\
+	".ifc \\rs," reg "\n"				\
+	".byte 0x2e\n"					\
+	".endif\n"					\
+	".endr\n"
+
+/*
  * Inline asm uses the %V modifier which is only in newer GCC
  * which is ensured when CONFIG_MITIGATION_RETPOLINE is defined.
  */
-# define CALL_NOSPEC						\
-	ALTERNATIVE_2(						\
-	ANNOTATE_RETPOLINE_SAFE					\
-	"call *%[thunk_target]\n",				\
-	"call __x86_indirect_thunk_%V[thunk_target]\n",		\
-	X86_FEATURE_RETPOLINE,					\
-	"lfence;\n"						\
-	ANNOTATE_RETPOLINE_SAFE					\
-	"call *%[thunk_target]\n",				\
-	X86_FEATURE_RETPOLINE_LFENCE)
+#ifdef CONFIG_MITIGATION_RETPOLINE
+#define CALL_NOSPEC	__CS_PREFIX("%V[thunk_target]")	\
+			"call __x86_indirect_thunk_%V[thunk_target]\n"
+#else
+#define CALL_NOSPEC	"call *%[thunk_target]\n"
+#endif
 
 # define THUNK_TARGET(addr) [thunk_target] "r" (addr)
 
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 1ac79f361645..0ba8d20f2d1d 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -188,11 +188,33 @@ union cpuid10_edx {
  * detection/enumeration details:
  */
 #define ARCH_PERFMON_EXT_LEAF			0x00000023
-#define ARCH_PERFMON_EXT_UMASK2			0x1
-#define ARCH_PERFMON_EXT_EQ			0x2
-#define ARCH_PERFMON_NUM_COUNTER_LEAF_BIT	0x1
 #define ARCH_PERFMON_NUM_COUNTER_LEAF		0x1
 
+union cpuid35_eax {
+	struct {
+		unsigned int	leaf0:1;
+		/* Counters Sub-Leaf */
+		unsigned int    cntr_subleaf:1;
+		/* Auto Counter Reload Sub-Leaf */
+		unsigned int    acr_subleaf:1;
+		/* Events Sub-Leaf */
+		unsigned int    events_subleaf:1;
+		unsigned int	reserved:28;
+	} split;
+	unsigned int            full;
+};
+
+union cpuid35_ebx {
+	struct {
+		/* UnitMask2 Supported */
+		unsigned int    umask2:1;
+		/* EQ-bit Supported */
+		unsigned int    eq:1;
+		unsigned int	reserved:30;
+	} split;
+	unsigned int            full;
+};
+
 /*
  * Intel Architectural LBR CPUID detection/enumeration details:
  */
diff --git a/arch/x86/include/asm/pgtable-2level_types.h b/arch/x86/include/asm/pgtable-2level_types.h
index 7f6ccff0ba72..4a12c276b181 100644
--- a/arch/x86/include/asm/pgtable-2level_types.h
+++ b/arch/x86/include/asm/pgtable-2level_types.h
@@ -23,17 +23,17 @@ typedef union {
 #define ARCH_PAGE_TABLE_SYNC_MASK	PGTBL_PMD_MODIFIED
 
 /*
- * traditional i386 two-level paging structure:
+ * Traditional i386 two-level paging structure:
  */
 
 #define PGDIR_SHIFT	22
 #define PTRS_PER_PGD	1024
 
-
 /*
- * the i386 is two-level, so we don't really have any
- * PMD directory physically.
+ * The i386 is two-level, so we don't really have any
+ * PMD directory physically:
  */
+#define PTRS_PER_PMD	1
 
 #define PTRS_PER_PTE	1024
 
diff --git a/arch/x86/include/asm/sev.h b/arch/x86/include/asm/sev.h
index 5d9685f92e5c..ba7999f66abe 100644
--- a/arch/x86/include/asm/sev.h
+++ b/arch/x86/include/asm/sev.h
@@ -203,6 +203,9 @@ struct snp_guest_req {
 	unsigned int vmpck_id;
 	u8 msg_version;
 	u8 msg_type;
+
+	struct snp_req_data input;
+	void *certs_data;
 };
 
 /*
@@ -263,9 +266,6 @@ struct snp_msg_desc {
 	struct snp_guest_msg secret_request, secret_response;
 
 	struct snp_secrets_page *secrets;
-	struct snp_req_data input;
-
-	void *certs_data;
 
 	struct aesgcm_ctx *ctx;
 
@@ -531,6 +531,7 @@ static inline void __init snp_secure_tsc_init(void) { }
 
 #ifdef CONFIG_KVM_AMD_SEV
 bool snp_probe_rmptable_info(void);
+int snp_rmptable_init(void);
 int snp_lookup_rmpentry(u64 pfn, bool *assigned, int *level);
 void snp_dump_hva_rmpentry(unsigned long address);
 int psmash(u64 pfn);
@@ -541,6 +542,7 @@ void kdump_sev_callback(void);
 void snp_fixup_e820_tables(void);
 #else
 static inline bool snp_probe_rmptable_info(void) { return false; }
+static inline int snp_rmptable_init(void) { return -ENOSYS; }
 static inline int snp_lookup_rmpentry(u64 pfn, bool *assigned, int *level) { return -ENODEV; }
 static inline void snp_dump_hva_rmpentry(unsigned long address) {}
 static inline int psmash(u64 pfn) { return -ENODEV; }
diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c
index 11fac09e3a8c..67e773744edb 100644
--- a/arch/x86/kernel/amd_nb.c
+++ b/arch/x86/kernel/amd_nb.c
@@ -143,7 +143,6 @@ bool __init early_is_amd_nb(u32 device)
 
 struct resource *amd_get_mmconfig_range(struct resource *res)
 {
-	u32 address;
 	u64 base, msr;
 	unsigned int segn_busn_bits;
 
@@ -151,13 +150,11 @@ struct resource *amd_get_mmconfig_range(struct resource *res)
 	    boot_cpu_data.x86_vendor != X86_VENDOR_HYGON)
 		return NULL;
 
-	/* assume all cpus from fam10h have mmconfig */
-	if (boot_cpu_data.x86 < 0x10)
+	/* Assume CPUs from Fam10h have mmconfig, although not all VMs do */
+	if (boot_cpu_data.x86 < 0x10 ||
+	    rdmsrl_safe(MSR_FAM10H_MMIO_CONF_BASE, &msr))
 		return NULL;
 
-	address = MSR_FAM10H_MMIO_CONF_BASE;
-	rdmsrl(address, msr);
-
 	/* mmconfig is not enabled */
 	if (!(msr & FAM10H_MMIO_CONF_ENABLE))
 		return NULL;
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 5a505aa65489..a5d0998d7604 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -1115,6 +1115,8 @@ do_cmd_auto:
 
 	case RETBLEED_MITIGATION_IBPB:
 		setup_force_cpu_cap(X86_FEATURE_ENTRY_IBPB);
+		setup_force_cpu_cap(X86_FEATURE_IBPB_ON_VMEXIT);
+		mitigate_smt = true;
 
 		/*
 		 * IBPB on entry already obviates the need for
@@ -1124,9 +1126,6 @@ do_cmd_auto:
 		setup_clear_cpu_cap(X86_FEATURE_UNRET);
 		setup_clear_cpu_cap(X86_FEATURE_RETHUNK);
 
-		setup_force_cpu_cap(X86_FEATURE_IBPB_ON_VMEXIT);
-		mitigate_smt = true;
-
 		/*
 		 * There is no need for RSB filling: entry_ibpb() ensures
 		 * all predictions, including the RSB, are invalidated,
@@ -2646,6 +2645,7 @@ static void __init srso_select_mitigation(void)
 		if (IS_ENABLED(CONFIG_MITIGATION_IBPB_ENTRY)) {
 			if (has_microcode) {
 				setup_force_cpu_cap(X86_FEATURE_ENTRY_IBPB);
+				setup_force_cpu_cap(X86_FEATURE_IBPB_ON_VMEXIT);
 				srso_mitigation = SRSO_MITIGATION_IBPB;
 
 				/*
@@ -2655,6 +2655,13 @@ static void __init srso_select_mitigation(void)
 				 */
 				setup_clear_cpu_cap(X86_FEATURE_UNRET);
 				setup_clear_cpu_cap(X86_FEATURE_RETHUNK);
+
+				/*
+				 * There is no need for RSB filling: entry_ibpb() ensures
+				 * all predictions, including the RSB, are invalidated,
+				 * regardless of IBPB implementation.
+				 */
+				setup_clear_cpu_cap(X86_FEATURE_RSB_VMEXIT);
 			}
 		} else {
 			pr_err("WARNING: kernel not compiled with MITIGATION_IBPB_ENTRY.\n");
@@ -2663,8 +2670,8 @@ static void __init srso_select_mitigation(void)
 
 ibpb_on_vmexit:
 	case SRSO_CMD_IBPB_ON_VMEXIT:
-		if (IS_ENABLED(CONFIG_MITIGATION_SRSO)) {
-			if (!boot_cpu_has(X86_FEATURE_ENTRY_IBPB) && has_microcode) {
+		if (IS_ENABLED(CONFIG_MITIGATION_IBPB_ENTRY)) {
+			if (has_microcode) {
 				setup_force_cpu_cap(X86_FEATURE_IBPB_ON_VMEXIT);
 				srso_mitigation = SRSO_MITIGATION_IBPB_ON_VMEXIT;
 
@@ -2676,8 +2683,8 @@ ibpb_on_vmexit:
 				setup_clear_cpu_cap(X86_FEATURE_RSB_VMEXIT);
 			}
 		} else {
-			pr_err("WARNING: kernel not compiled with MITIGATION_SRSO.\n");
-                }
+			pr_err("WARNING: kernel not compiled with MITIGATION_IBPB_ENTRY.\n");
+		}
 		break;
 	default:
 		break;
diff --git a/arch/x86/kernel/cpu/cacheinfo.c b/arch/x86/kernel/cpu/cacheinfo.c
index e6fa03ed9172..a6c6bccfa8b8 100644
--- a/arch/x86/kernel/cpu/cacheinfo.c
+++ b/arch/x86/kernel/cpu/cacheinfo.c
@@ -808,7 +808,7 @@ void init_intel_cacheinfo(struct cpuinfo_x86 *c)
 			cpuid(2, &regs[0], &regs[1], &regs[2], &regs[3]);
 
 			/* If bit 31 is set, this is an unknown format */
-			for (j = 0 ; j < 3 ; j++)
+			for (j = 0 ; j < 4 ; j++)
 				if (regs[j] & (1 << 31))
 					regs[j] = 0;
 
diff --git a/arch/x86/kernel/cpu/cpuid-deps.c b/arch/x86/kernel/cpu/cpuid-deps.c
index 8bd84114c2d9..df838e3bdbe0 100644
--- a/arch/x86/kernel/cpu/cpuid-deps.c
+++ b/arch/x86/kernel/cpu/cpuid-deps.c
@@ -45,6 +45,7 @@ static const struct cpuid_dep cpuid_deps[] = {
 	{ X86_FEATURE_AES,			X86_FEATURE_XMM2      },
 	{ X86_FEATURE_SHA_NI,			X86_FEATURE_XMM2      },
 	{ X86_FEATURE_GFNI,			X86_FEATURE_XMM2      },
+	{ X86_FEATURE_AVX_VNNI,			X86_FEATURE_AVX       },
 	{ X86_FEATURE_FMA,			X86_FEATURE_AVX       },
 	{ X86_FEATURE_VAES,			X86_FEATURE_AVX       },
 	{ X86_FEATURE_VPCLMULQDQ,		X86_FEATURE_AVX       },
diff --git a/arch/x86/kernel/cpu/cyrix.c b/arch/x86/kernel/cpu/cyrix.c
index 9651275aecd1..dfec2c61e354 100644
--- a/arch/x86/kernel/cpu/cyrix.c
+++ b/arch/x86/kernel/cpu/cyrix.c
@@ -153,8 +153,8 @@ static void geode_configure(void)
 	u8 ccr3;
 	local_irq_save(flags);
 
-	/* Suspend on halt power saving and enable #SUSP pin */
-	setCx86(CX86_CCR2, getCx86(CX86_CCR2) | 0x88);
+	/* Suspend on halt power saving */
+	setCx86(CX86_CCR2, getCx86(CX86_CCR2) | 0x08);
 
 	ccr3 = getCx86(CX86_CCR3);
 	setCx86(CX86_CCR3, (ccr3 & 0x0f) | 0x10);	/* enable MAPEN */
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 3dce22f00dc3..134368a3f4b1 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -635,26 +635,37 @@ static unsigned int intel_size_cache(struct cpuinfo_x86 *c, unsigned int size)
 }
 #endif
 
-#define TLB_INST_4K	0x01
-#define TLB_INST_4M	0x02
-#define TLB_INST_2M_4M	0x03
+#define TLB_INST_4K		0x01
+#define TLB_INST_4M		0x02
+#define TLB_INST_2M_4M		0x03
 
-#define TLB_INST_ALL	0x05
-#define TLB_INST_1G	0x06
+#define TLB_INST_ALL		0x05
+#define TLB_INST_1G		0x06
 
-#define TLB_DATA_4K	0x11
-#define TLB_DATA_4M	0x12
-#define TLB_DATA_2M_4M	0x13
-#define TLB_DATA_4K_4M	0x14
+#define TLB_DATA_4K		0x11
+#define TLB_DATA_4M		0x12
+#define TLB_DATA_2M_4M		0x13
+#define TLB_DATA_4K_4M		0x14
 
-#define TLB_DATA_1G	0x16
+#define TLB_DATA_1G		0x16
+#define TLB_DATA_1G_2M_4M	0x17
 
-#define TLB_DATA0_4K	0x21
-#define TLB_DATA0_4M	0x22
-#define TLB_DATA0_2M_4M	0x23
+#define TLB_DATA0_4K		0x21
+#define TLB_DATA0_4M		0x22
+#define TLB_DATA0_2M_4M		0x23
 
-#define STLB_4K		0x41
-#define STLB_4K_2M	0x42
+#define STLB_4K			0x41
+#define STLB_4K_2M		0x42
+
+/*
+ * All of leaf 0x2's one-byte TLB descriptors implies the same number of
+ * entries for their respective TLB types.  The 0x63 descriptor is an
+ * exception: it implies 4 dTLB entries for 1GB pages 32 dTLB entries
+ * for 2MB or 4MB pages.  Encode descriptor 0x63 dTLB entry count for
+ * 2MB/4MB pages here, as its count for dTLB 1GB pages is already at the
+ * intel_tlb_table[] mapping.
+ */
+#define TLB_0x63_2M_4M_ENTRIES	32
 
 static const struct _tlb_table intel_tlb_table[] = {
 	{ 0x01, TLB_INST_4K,		32,	" TLB_INST 4 KByte pages, 4-way set associative" },
@@ -676,7 +687,8 @@ static const struct _tlb_table intel_tlb_table[] = {
 	{ 0x5c, TLB_DATA_4K_4M,		128,	" TLB_DATA 4 KByte and 4 MByte pages" },
 	{ 0x5d, TLB_DATA_4K_4M,		256,	" TLB_DATA 4 KByte and 4 MByte pages" },
 	{ 0x61, TLB_INST_4K,		48,	" TLB_INST 4 KByte pages, full associative" },
-	{ 0x63, TLB_DATA_1G,		4,	" TLB_DATA 1 GByte pages, 4-way set associative" },
+	{ 0x63, TLB_DATA_1G_2M_4M,	4,	" TLB_DATA 1 GByte pages, 4-way set associative"
+						" (plus 32 entries TLB_DATA 2 MByte or 4 MByte pages, not encoded here)" },
 	{ 0x6b, TLB_DATA_4K,		256,	" TLB_DATA 4 KByte pages, 8-way associative" },
 	{ 0x6c, TLB_DATA_2M_4M,		128,	" TLB_DATA 2 MByte or 4 MByte pages, 8-way associative" },
 	{ 0x6d, TLB_DATA_1G,		16,	" TLB_DATA 1 GByte pages, fully associative" },
@@ -776,6 +788,12 @@ static void intel_tlb_lookup(const unsigned char desc)
 		if (tlb_lld_4m[ENTRIES] < intel_tlb_table[k].entries)
 			tlb_lld_4m[ENTRIES] = intel_tlb_table[k].entries;
 		break;
+	case TLB_DATA_1G_2M_4M:
+		if (tlb_lld_2m[ENTRIES] < TLB_0x63_2M_4M_ENTRIES)
+			tlb_lld_2m[ENTRIES] = TLB_0x63_2M_4M_ENTRIES;
+		if (tlb_lld_4m[ENTRIES] < TLB_0x63_2M_4M_ENTRIES)
+			tlb_lld_4m[ENTRIES] = TLB_0x63_2M_4M_ENTRIES;
+		fallthrough;
 	case TLB_DATA_1G:
 		if (tlb_lld_1g[ENTRIES] < intel_tlb_table[k].entries)
 			tlb_lld_1g[ENTRIES] = intel_tlb_table[k].entries;
@@ -799,7 +817,7 @@ static void intel_detect_tlb(struct cpuinfo_x86 *c)
 		cpuid(2, &regs[0], &regs[1], &regs[2], &regs[3]);
 
 		/* If bit 31 is set, this is an unknown format */
-		for (j = 0 ; j < 3 ; j++)
+		for (j = 0 ; j < 4 ; j++)
 			if (regs[j] & (1 << 31))
 				regs[j] = 0;
 
diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c
index a5dac7f3c0a0..c69b1bc45483 100644
--- a/arch/x86/kernel/cpu/microcode/amd.c
+++ b/arch/x86/kernel/cpu/microcode/amd.c
@@ -23,14 +23,18 @@
 
 #include <linux/earlycpio.h>
 #include <linux/firmware.h>
+#include <linux/bsearch.h>
 #include <linux/uaccess.h>
 #include <linux/vmalloc.h>
 #include <linux/initrd.h>
 #include <linux/kernel.h>
 #include <linux/pci.h>
 
+#include <crypto/sha2.h>
+
 #include <asm/microcode.h>
 #include <asm/processor.h>
+#include <asm/cmdline.h>
 #include <asm/setup.h>
 #include <asm/cpu.h>
 #include <asm/msr.h>
@@ -145,6 +149,113 @@ ucode_path[] __maybe_unused = "kernel/x86/microcode/AuthenticAMD.bin";
  */
 static u32 bsp_cpuid_1_eax __ro_after_init;
 
+static bool sha_check = true;
+
+struct patch_digest {
+	u32 patch_id;
+	u8 sha256[SHA256_DIGEST_SIZE];
+};
+
+#include "amd_shas.c"
+
+static int cmp_id(const void *key, const void *elem)
+{
+	struct patch_digest *pd = (struct patch_digest *)elem;
+	u32 patch_id = *(u32 *)key;
+
+	if (patch_id == pd->patch_id)
+		return 0;
+	else if (patch_id < pd->patch_id)
+		return -1;
+	else
+		return 1;
+}
+
+static bool need_sha_check(u32 cur_rev)
+{
+	switch (cur_rev >> 8) {
+	case 0x80012: return cur_rev <= 0x800126f; break;
+	case 0x80082: return cur_rev <= 0x800820f; break;
+	case 0x83010: return cur_rev <= 0x830107c; break;
+	case 0x86001: return cur_rev <= 0x860010e; break;
+	case 0x86081: return cur_rev <= 0x8608108; break;
+	case 0x87010: return cur_rev <= 0x8701034; break;
+	case 0x8a000: return cur_rev <= 0x8a0000a; break;
+	case 0xa0010: return cur_rev <= 0xa00107a; break;
+	case 0xa0011: return cur_rev <= 0xa0011da; break;
+	case 0xa0012: return cur_rev <= 0xa001243; break;
+	case 0xa0082: return cur_rev <= 0xa00820e; break;
+	case 0xa1011: return cur_rev <= 0xa101153; break;
+	case 0xa1012: return cur_rev <= 0xa10124e; break;
+	case 0xa1081: return cur_rev <= 0xa108109; break;
+	case 0xa2010: return cur_rev <= 0xa20102f; break;
+	case 0xa2012: return cur_rev <= 0xa201212; break;
+	case 0xa4041: return cur_rev <= 0xa404109; break;
+	case 0xa5000: return cur_rev <= 0xa500013; break;
+	case 0xa6012: return cur_rev <= 0xa60120a; break;
+	case 0xa7041: return cur_rev <= 0xa704109; break;
+	case 0xa7052: return cur_rev <= 0xa705208; break;
+	case 0xa7080: return cur_rev <= 0xa708009; break;
+	case 0xa70c0: return cur_rev <= 0xa70C009; break;
+	case 0xaa001: return cur_rev <= 0xaa00116; break;
+	case 0xaa002: return cur_rev <= 0xaa00218; break;
+	default: break;
+	}
+
+	pr_info("You should not be seeing this. Please send the following couple of lines to x86-<at>-kernel.org\n");
+	pr_info("CPUID(1).EAX: 0x%x, current revision: 0x%x\n", bsp_cpuid_1_eax, cur_rev);
+	return true;
+}
+
+static bool verify_sha256_digest(u32 patch_id, u32 cur_rev, const u8 *data, unsigned int len)
+{
+	struct patch_digest *pd = NULL;
+	u8 digest[SHA256_DIGEST_SIZE];
+	struct sha256_state s;
+	int i;
+
+	if (x86_family(bsp_cpuid_1_eax) < 0x17 ||
+	    x86_family(bsp_cpuid_1_eax) > 0x19)
+		return true;
+
+	if (!need_sha_check(cur_rev))
+		return true;
+
+	if (!sha_check)
+		return true;
+
+	pd = bsearch(&patch_id, phashes, ARRAY_SIZE(phashes), sizeof(struct patch_digest), cmp_id);
+	if (!pd) {
+		pr_err("No sha256 digest for patch ID: 0x%x found\n", patch_id);
+		return false;
+	}
+
+	sha256_init(&s);
+	sha256_update(&s, data, len);
+	sha256_final(&s, digest);
+
+	if (memcmp(digest, pd->sha256, sizeof(digest))) {
+		pr_err("Patch 0x%x SHA256 digest mismatch!\n", patch_id);
+
+		for (i = 0; i < SHA256_DIGEST_SIZE; i++)
+			pr_cont("0x%x ", digest[i]);
+		pr_info("\n");
+
+		return false;
+	}
+
+	return true;
+}
+
+static u32 get_patch_level(void)
+{
+	u32 rev, dummy __always_unused;
+
+	native_rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy);
+
+	return rev;
+}
+
 static union cpuid_1_eax ucode_rev_to_cpuid(unsigned int val)
 {
 	union zen_patch_rev p;
@@ -246,8 +357,7 @@ static bool verify_equivalence_table(const u8 *buf, size_t buf_size)
  * On success, @sh_psize returns the patch size according to the section header,
  * to the caller.
  */
-static bool
-__verify_patch_section(const u8 *buf, size_t buf_size, u32 *sh_psize)
+static bool __verify_patch_section(const u8 *buf, size_t buf_size, u32 *sh_psize)
 {
 	u32 p_type, p_size;
 	const u32 *hdr;
@@ -484,10 +594,13 @@ static void scan_containers(u8 *ucode, size_t size, struct cont_desc *desc)
 	}
 }
 
-static bool __apply_microcode_amd(struct microcode_amd *mc, unsigned int psize)
+static bool __apply_microcode_amd(struct microcode_amd *mc, u32 *cur_rev,
+				  unsigned int psize)
 {
 	unsigned long p_addr = (unsigned long)&mc->hdr.data_code;
-	u32 rev, dummy;
+
+	if (!verify_sha256_digest(mc->hdr.patch_id, *cur_rev, (const u8 *)p_addr, psize))
+		return -1;
 
 	native_wrmsrl(MSR_AMD64_PATCH_LOADER, p_addr);
 
@@ -505,47 +618,13 @@ static bool __apply_microcode_amd(struct microcode_amd *mc, unsigned int psize)
 	}
 
 	/* verify patch application was successful */
-	native_rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy);
-
-	if (rev != mc->hdr.patch_id)
+	*cur_rev = get_patch_level();
+	if (*cur_rev != mc->hdr.patch_id)
 		return false;
 
 	return true;
 }
 
-/*
- * Early load occurs before we can vmalloc(). So we look for the microcode
- * patch container file in initrd, traverse equivalent cpu table, look for a
- * matching microcode patch, and update, all in initrd memory in place.
- * When vmalloc() is available for use later -- on 64-bit during first AP load,
- * and on 32-bit during save_microcode_in_initrd_amd() -- we can call
- * load_microcode_amd() to save equivalent cpu table and microcode patches in
- * kernel heap memory.
- *
- * Returns true if container found (sets @desc), false otherwise.
- */
-static bool early_apply_microcode(u32 old_rev, void *ucode, size_t size)
-{
-	struct cont_desc desc = { 0 };
-	struct microcode_amd *mc;
-
-	scan_containers(ucode, size, &desc);
-
-	mc = desc.mc;
-	if (!mc)
-		return false;
-
-	/*
-	 * Allow application of the same revision to pick up SMT-specific
-	 * changes even if the revision of the other SMT thread is already
-	 * up-to-date.
-	 */
-	if (old_rev > mc->hdr.patch_id)
-		return false;
-
-	return __apply_microcode_amd(mc, desc.psize);
-}
-
 static bool get_builtin_microcode(struct cpio_data *cp)
 {
 	char fw_name[36] = "amd-ucode/microcode_amd.bin";
@@ -583,14 +662,35 @@ static bool __init find_blobs_in_containers(struct cpio_data *ret)
 	return found;
 }
 
+/*
+ * Early load occurs before we can vmalloc(). So we look for the microcode
+ * patch container file in initrd, traverse equivalent cpu table, look for a
+ * matching microcode patch, and update, all in initrd memory in place.
+ * When vmalloc() is available for use later -- on 64-bit during first AP load,
+ * and on 32-bit during save_microcode_in_initrd() -- we can call
+ * load_microcode_amd() to save equivalent cpu table and microcode patches in
+ * kernel heap memory.
+ */
 void __init load_ucode_amd_bsp(struct early_load_data *ed, unsigned int cpuid_1_eax)
 {
+	struct cont_desc desc = { };
+	struct microcode_amd *mc;
 	struct cpio_data cp = { };
-	u32 dummy;
+	char buf[4];
+	u32 rev;
+
+	if (cmdline_find_option(boot_command_line, "microcode.amd_sha_check", buf, 4)) {
+		if (!strncmp(buf, "off", 3)) {
+			sha_check = false;
+			pr_warn_once("It is a very very bad idea to disable the blobs SHA check!\n");
+			add_taint(TAINT_CPU_OUT_OF_SPEC, LOCKDEP_STILL_OK);
+		}
+	}
 
 	bsp_cpuid_1_eax = cpuid_1_eax;
 
-	native_rdmsr(MSR_AMD64_PATCH_LEVEL, ed->old_rev, dummy);
+	rev = get_patch_level();
+	ed->old_rev = rev;
 
 	/* Needed in load_microcode_amd() */
 	ucode_cpu_info[0].cpu_sig.sig = cpuid_1_eax;
@@ -598,37 +698,23 @@ void __init load_ucode_amd_bsp(struct early_load_data *ed, unsigned int cpuid_1_
 	if (!find_blobs_in_containers(&cp))
 		return;
 
-	if (early_apply_microcode(ed->old_rev, cp.data, cp.size))
-		native_rdmsr(MSR_AMD64_PATCH_LEVEL, ed->new_rev, dummy);
-}
-
-static enum ucode_state _load_microcode_amd(u8 family, const u8 *data, size_t size);
-
-static int __init save_microcode_in_initrd(void)
-{
-	unsigned int cpuid_1_eax = native_cpuid_eax(1);
-	struct cpuinfo_x86 *c = &boot_cpu_data;
-	struct cont_desc desc = { 0 };
-	enum ucode_state ret;
-	struct cpio_data cp;
-
-	if (dis_ucode_ldr || c->x86_vendor != X86_VENDOR_AMD || c->x86 < 0x10)
-		return 0;
-
-	if (!find_blobs_in_containers(&cp))
-		return -EINVAL;
-
 	scan_containers(cp.data, cp.size, &desc);
-	if (!desc.mc)
-		return -EINVAL;
 
-	ret = _load_microcode_amd(x86_family(cpuid_1_eax), desc.data, desc.size);
-	if (ret > UCODE_UPDATED)
-		return -EINVAL;
+	mc = desc.mc;
+	if (!mc)
+		return;
 
-	return 0;
+	/*
+	 * Allow application of the same revision to pick up SMT-specific
+	 * changes even if the revision of the other SMT thread is already
+	 * up-to-date.
+	 */
+	if (ed->old_rev > mc->hdr.patch_id)
+		return;
+
+	if (__apply_microcode_amd(mc, &rev, desc.psize))
+		ed->new_rev = rev;
 }
-early_initcall(save_microcode_in_initrd);
 
 static inline bool patch_cpus_equivalent(struct ucode_patch *p,
 					 struct ucode_patch *n,
@@ -729,14 +815,9 @@ static void free_cache(void)
 static struct ucode_patch *find_patch(unsigned int cpu)
 {
 	struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
-	u32 rev, dummy __always_unused;
 	u16 equiv_id = 0;
 
-	/* fetch rev if not populated yet: */
-	if (!uci->cpu_sig.rev) {
-		rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy);
-		uci->cpu_sig.rev = rev;
-	}
+	uci->cpu_sig.rev = get_patch_level();
 
 	if (x86_family(bsp_cpuid_1_eax) < 0x17) {
 		equiv_id = find_equiv_id(&equiv_table, uci->cpu_sig.sig);
@@ -759,22 +840,20 @@ void reload_ucode_amd(unsigned int cpu)
 
 	mc = p->data;
 
-	rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy);
-
+	rev = get_patch_level();
 	if (rev < mc->hdr.patch_id) {
-		if (__apply_microcode_amd(mc, p->size))
-			pr_info_once("reload revision: 0x%08x\n", mc->hdr.patch_id);
+		if (__apply_microcode_amd(mc, &rev, p->size))
+			pr_info_once("reload revision: 0x%08x\n", rev);
 	}
 }
 
 static int collect_cpu_info_amd(int cpu, struct cpu_signature *csig)
 {
-	struct cpuinfo_x86 *c = &cpu_data(cpu);
 	struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
 	struct ucode_patch *p;
 
 	csig->sig = cpuid_eax(0x00000001);
-	csig->rev = c->microcode;
+	csig->rev = get_patch_level();
 
 	/*
 	 * a patch could have been loaded early, set uci->mc so that
@@ -815,7 +894,7 @@ static enum ucode_state apply_microcode_amd(int cpu)
 		goto out;
 	}
 
-	if (!__apply_microcode_amd(mc_amd, p->size)) {
+	if (!__apply_microcode_amd(mc_amd, &rev, p->size)) {
 		pr_err("CPU%d: update failed for patch_level=0x%08x\n",
 			cpu, mc_amd->hdr.patch_id);
 		return UCODE_ERROR;
@@ -937,8 +1016,7 @@ static int verify_and_add_patch(u8 family, u8 *fw, unsigned int leftover,
 }
 
 /* Scan the blob in @data and add microcode patches to the cache. */
-static enum ucode_state __load_microcode_amd(u8 family, const u8 *data,
-					     size_t size)
+static enum ucode_state __load_microcode_amd(u8 family, const u8 *data, size_t size)
 {
 	u8 *fw = (u8 *)data;
 	size_t offset;
@@ -1013,6 +1091,32 @@ static enum ucode_state load_microcode_amd(u8 family, const u8 *data, size_t siz
 	return ret;
 }
 
+static int __init save_microcode_in_initrd(void)
+{
+	unsigned int cpuid_1_eax = native_cpuid_eax(1);
+	struct cpuinfo_x86 *c = &boot_cpu_data;
+	struct cont_desc desc = { 0 };
+	enum ucode_state ret;
+	struct cpio_data cp;
+
+	if (dis_ucode_ldr || c->x86_vendor != X86_VENDOR_AMD || c->x86 < 0x10)
+		return 0;
+
+	if (!find_blobs_in_containers(&cp))
+		return -EINVAL;
+
+	scan_containers(cp.data, cp.size, &desc);
+	if (!desc.mc)
+		return -EINVAL;
+
+	ret = _load_microcode_amd(x86_family(cpuid_1_eax), desc.data, desc.size);
+	if (ret > UCODE_UPDATED)
+		return -EINVAL;
+
+	return 0;
+}
+early_initcall(save_microcode_in_initrd);
+
 /*
  * AMD microcode firmware naming convention, up to family 15h they are in
  * the legacy file:
diff --git a/arch/x86/kernel/cpu/microcode/amd_shas.c b/arch/x86/kernel/cpu/microcode/amd_shas.c
new file mode 100644
index 000000000000..2a1655b1fdd8
--- /dev/null
+++ b/arch/x86/kernel/cpu/microcode/amd_shas.c
@@ -0,0 +1,444 @@
+/* Keep 'em sorted. */
+static const struct patch_digest phashes[] = {
+ { 0x8001227, {
+		0x99,0xc0,0x9b,0x2b,0xcc,0x9f,0x52,0x1b,
+		0x1a,0x5f,0x1d,0x83,0xa1,0x6c,0xc4,0x46,
+		0xe2,0x6c,0xda,0x73,0xfb,0x2d,0x23,0xa8,
+		0x77,0xdc,0x15,0x31,0x33,0x4a,0x46,0x18,
+	}
+ },
+ { 0x8001250, {
+		0xc0,0x0b,0x6b,0x19,0xfd,0x5c,0x39,0x60,
+		0xd5,0xc3,0x57,0x46,0x54,0xe4,0xd1,0xaa,
+		0xa8,0xf7,0x1f,0xa8,0x6a,0x60,0x3e,0xe3,
+		0x27,0x39,0x8e,0x53,0x30,0xf8,0x49,0x19,
+	}
+ },
+ { 0x800126e, {
+		0xf3,0x8b,0x2b,0xb6,0x34,0xe3,0xc8,0x2c,
+		0xef,0xec,0x63,0x6d,0xc8,0x76,0x77,0xb3,
+		0x25,0x5a,0xb7,0x52,0x8c,0x83,0x26,0xe6,
+		0x4c,0xbe,0xbf,0xe9,0x7d,0x22,0x6a,0x43,
+	}
+ },
+ { 0x800126f, {
+		0x2b,0x5a,0xf2,0x9c,0xdd,0xd2,0x7f,0xec,
+		0xec,0x96,0x09,0x57,0xb0,0x96,0x29,0x8b,
+		0x2e,0x26,0x91,0xf0,0x49,0x33,0x42,0x18,
+		0xdd,0x4b,0x65,0x5a,0xd4,0x15,0x3d,0x33,
+	}
+ },
+ { 0x800820d, {
+		0x68,0x98,0x83,0xcd,0x22,0x0d,0xdd,0x59,
+		0x73,0x2c,0x5b,0x37,0x1f,0x84,0x0e,0x67,
+		0x96,0x43,0x83,0x0c,0x46,0x44,0xab,0x7c,
+		0x7b,0x65,0x9e,0x57,0xb5,0x90,0x4b,0x0e,
+	}
+ },
+ { 0x8301025, {
+		0xe4,0x7d,0xdb,0x1e,0x14,0xb4,0x5e,0x36,
+		0x8f,0x3e,0x48,0x88,0x3c,0x6d,0x76,0xa1,
+		0x59,0xc6,0xc0,0x72,0x42,0xdf,0x6c,0x30,
+		0x6f,0x0b,0x28,0x16,0x61,0xfc,0x79,0x77,
+	}
+ },
+ { 0x8301055, {
+		0x81,0x7b,0x99,0x1b,0xae,0x2d,0x4f,0x9a,
+		0xef,0x13,0xce,0xb5,0x10,0xaf,0x6a,0xea,
+		0xe5,0xb0,0x64,0x98,0x10,0x68,0x34,0x3b,
+		0x9d,0x7a,0xd6,0x22,0x77,0x5f,0xb3,0x5b,
+	}
+ },
+ { 0x8301072, {
+		0xcf,0x76,0xa7,0x1a,0x49,0xdf,0x2a,0x5e,
+		0x9e,0x40,0x70,0xe5,0xdd,0x8a,0xa8,0x28,
+		0x20,0xdc,0x91,0xd8,0x2c,0xa6,0xa0,0xb1,
+		0x2d,0x22,0x26,0x94,0x4b,0x40,0x85,0x30,
+	}
+ },
+ { 0x830107a, {
+		0x2a,0x65,0x8c,0x1a,0x5e,0x07,0x21,0x72,
+		0xdf,0x90,0xa6,0x51,0x37,0xd3,0x4b,0x34,
+		0xc4,0xda,0x03,0xe1,0x8a,0x6c,0xfb,0x20,
+		0x04,0xb2,0x81,0x05,0xd4,0x87,0xf4,0x0a,
+	}
+ },
+ { 0x830107b, {
+		0xb3,0x43,0x13,0x63,0x56,0xc1,0x39,0xad,
+		0x10,0xa6,0x2b,0xcc,0x02,0xe6,0x76,0x2a,
+		0x1e,0x39,0x58,0x3e,0x23,0x6e,0xa4,0x04,
+		0x95,0xea,0xf9,0x6d,0xc2,0x8a,0x13,0x19,
+	}
+ },
+ { 0x830107c, {
+		0x21,0x64,0xde,0xfb,0x9f,0x68,0x96,0x47,
+		0x70,0x5c,0xe2,0x8f,0x18,0x52,0x6a,0xac,
+		0xa4,0xd2,0x2e,0xe0,0xde,0x68,0x66,0xc3,
+		0xeb,0x1e,0xd3,0x3f,0xbc,0x51,0x1d,0x38,
+	}
+ },
+ { 0x860010d, {
+		0x86,0xb6,0x15,0x83,0xbc,0x3b,0x9c,0xe0,
+		0xb3,0xef,0x1d,0x99,0x84,0x35,0x15,0xf7,
+		0x7c,0x2a,0xc6,0x42,0xdb,0x73,0x07,0x5c,
+		0x7d,0xc3,0x02,0xb5,0x43,0x06,0x5e,0xf8,
+	}
+ },
+ { 0x8608108, {
+		0x14,0xfe,0x57,0x86,0x49,0xc8,0x68,0xe2,
+		0x11,0xa3,0xcb,0x6e,0xff,0x6e,0xd5,0x38,
+		0xfe,0x89,0x1a,0xe0,0x67,0xbf,0xc4,0xcc,
+		0x1b,0x9f,0x84,0x77,0x2b,0x9f,0xaa,0xbd,
+	}
+ },
+ { 0x8701034, {
+		0xc3,0x14,0x09,0xa8,0x9c,0x3f,0x8d,0x83,
+		0x9b,0x4c,0xa5,0xb7,0x64,0x8b,0x91,0x5d,
+		0x85,0x6a,0x39,0x26,0x1e,0x14,0x41,0xa8,
+		0x75,0xea,0xa6,0xf9,0xc9,0xd1,0xea,0x2b,
+	}
+ },
+ { 0x8a00008, {
+		0xd7,0x2a,0x93,0xdc,0x05,0x2f,0xa5,0x6e,
+		0x0c,0x61,0x2c,0x07,0x9f,0x38,0xe9,0x8e,
+		0xef,0x7d,0x2a,0x05,0x4d,0x56,0xaf,0x72,
+		0xe7,0x56,0x47,0x6e,0x60,0x27,0xd5,0x8c,
+	}
+ },
+ { 0x8a0000a, {
+		0x73,0x31,0x26,0x22,0xd4,0xf9,0xee,0x3c,
+		0x07,0x06,0xe7,0xb9,0xad,0xd8,0x72,0x44,
+		0x33,0x31,0xaa,0x7d,0xc3,0x67,0x0e,0xdb,
+		0x47,0xb5,0xaa,0xbc,0xf5,0xbb,0xd9,0x20,
+	}
+ },
+ { 0xa00104c, {
+		0x3c,0x8a,0xfe,0x04,0x62,0xd8,0x6d,0xbe,
+		0xa7,0x14,0x28,0x64,0x75,0xc0,0xa3,0x76,
+		0xb7,0x92,0x0b,0x97,0x0a,0x8e,0x9c,0x5b,
+		0x1b,0xc8,0x9d,0x3a,0x1e,0x81,0x3d,0x3b,
+	}
+ },
+ { 0xa00104e, {
+		0xc4,0x35,0x82,0x67,0xd2,0x86,0xe5,0xb2,
+		0xfd,0x69,0x12,0x38,0xc8,0x77,0xba,0xe0,
+		0x70,0xf9,0x77,0x89,0x10,0xa6,0x74,0x4e,
+		0x56,0x58,0x13,0xf5,0x84,0x70,0x28,0x0b,
+	}
+ },
+ { 0xa001053, {
+		0x92,0x0e,0xf4,0x69,0x10,0x3b,0xf9,0x9d,
+		0x31,0x1b,0xa6,0x99,0x08,0x7d,0xd7,0x25,
+		0x7e,0x1e,0x89,0xba,0x35,0x8d,0xac,0xcb,
+		0x3a,0xb4,0xdf,0x58,0x12,0xcf,0xc0,0xc3,
+	}
+ },
+ { 0xa001058, {
+		0x33,0x7d,0xa9,0xb5,0x4e,0x62,0x13,0x36,
+		0xef,0x66,0xc9,0xbd,0x0a,0xa6,0x3b,0x19,
+		0xcb,0xf5,0xc2,0xc3,0x55,0x47,0x20,0xec,
+		0x1f,0x7b,0xa1,0x44,0x0e,0x8e,0xa4,0xb2,
+	}
+ },
+ { 0xa001075, {
+		0x39,0x02,0x82,0xd0,0x7c,0x26,0x43,0xe9,
+		0x26,0xa3,0xd9,0x96,0xf7,0x30,0x13,0x0a,
+		0x8a,0x0e,0xac,0xe7,0x1d,0xdc,0xe2,0x0f,
+		0xcb,0x9e,0x8d,0xbc,0xd2,0xa2,0x44,0xe0,
+	}
+ },
+ { 0xa001078, {
+		0x2d,0x67,0xc7,0x35,0xca,0xef,0x2f,0x25,
+		0x4c,0x45,0x93,0x3f,0x36,0x01,0x8c,0xce,
+		0xa8,0x5b,0x07,0xd3,0xc1,0x35,0x3c,0x04,
+		0x20,0xa2,0xfc,0xdc,0xe6,0xce,0x26,0x3e,
+	}
+ },
+ { 0xa001079, {
+		0x43,0xe2,0x05,0x9c,0xfd,0xb7,0x5b,0xeb,
+		0x5b,0xe9,0xeb,0x3b,0x96,0xf4,0xe4,0x93,
+		0x73,0x45,0x3e,0xac,0x8d,0x3b,0xe4,0xdb,
+		0x10,0x31,0xc1,0xe4,0xa2,0xd0,0x5a,0x8a,
+	}
+ },
+ { 0xa00107a, {
+		0x5f,0x92,0xca,0xff,0xc3,0x59,0x22,0x5f,
+		0x02,0xa0,0x91,0x3b,0x4a,0x45,0x10,0xfd,
+		0x19,0xe1,0x8a,0x6d,0x9a,0x92,0xc1,0x3f,
+		0x75,0x78,0xac,0x78,0x03,0x1d,0xdb,0x18,
+	}
+ },
+ { 0xa001143, {
+		0x56,0xca,0xf7,0x43,0x8a,0x4c,0x46,0x80,
+		0xec,0xde,0xe5,0x9c,0x50,0x84,0x9a,0x42,
+		0x27,0xe5,0x51,0x84,0x8f,0x19,0xc0,0x8d,
+		0x0c,0x25,0xb4,0xb0,0x8f,0x10,0xf3,0xf8,
+	}
+ },
+ { 0xa001144, {
+		0x42,0xd5,0x9b,0xa7,0xd6,0x15,0x29,0x41,
+		0x61,0xc4,0x72,0x3f,0xf3,0x06,0x78,0x4b,
+		0x65,0xf3,0x0e,0xfa,0x9c,0x87,0xde,0x25,
+		0xbd,0xb3,0x9a,0xf4,0x75,0x13,0x53,0xdc,
+	}
+ },
+ { 0xa00115d, {
+		0xd4,0xc4,0x49,0x36,0x89,0x0b,0x47,0xdd,
+		0xfb,0x2f,0x88,0x3b,0x5f,0xf2,0x8e,0x75,
+		0xc6,0x6c,0x37,0x5a,0x90,0x25,0x94,0x3e,
+		0x36,0x9c,0xae,0x02,0x38,0x6c,0xf5,0x05,
+	}
+ },
+ { 0xa001173, {
+		0x28,0xbb,0x9b,0xd1,0xa0,0xa0,0x7e,0x3a,
+		0x59,0x20,0xc0,0xa9,0xb2,0x5c,0xc3,0x35,
+		0x53,0x89,0xe1,0x4c,0x93,0x2f,0x1d,0xc3,
+		0xe5,0xf7,0xf3,0xc8,0x9b,0x61,0xaa,0x9e,
+	}
+ },
+ { 0xa0011a8, {
+		0x97,0xc6,0x16,0x65,0x99,0xa4,0x85,0x3b,
+		0xf6,0xce,0xaa,0x49,0x4a,0x3a,0xc5,0xb6,
+		0x78,0x25,0xbc,0x53,0xaf,0x5d,0xcf,0xf4,
+		0x23,0x12,0xbb,0xb1,0xbc,0x8a,0x02,0x2e,
+	}
+ },
+ { 0xa0011ce, {
+		0xcf,0x1c,0x90,0xa3,0x85,0x0a,0xbf,0x71,
+		0x94,0x0e,0x80,0x86,0x85,0x4f,0xd7,0x86,
+		0xae,0x38,0x23,0x28,0x2b,0x35,0x9b,0x4e,
+		0xfe,0xb8,0xcd,0x3d,0x3d,0x39,0xc9,0x6a,
+	}
+ },
+ { 0xa0011d1, {
+		0xdf,0x0e,0xca,0xde,0xf6,0xce,0x5c,0x1e,
+		0x4c,0xec,0xd7,0x71,0x83,0xcc,0xa8,0x09,
+		0xc7,0xc5,0xfe,0xb2,0xf7,0x05,0xd2,0xc5,
+		0x12,0xdd,0xe4,0xf3,0x92,0x1c,0x3d,0xb8,
+	}
+ },
+ { 0xa0011d3, {
+		0x91,0xe6,0x10,0xd7,0x57,0xb0,0x95,0x0b,
+		0x9a,0x24,0xee,0xf7,0xcf,0x56,0xc1,0xa6,
+		0x4a,0x52,0x7d,0x5f,0x9f,0xdf,0xf6,0x00,
+		0x65,0xf7,0xea,0xe8,0x2a,0x88,0xe2,0x26,
+	}
+ },
+ { 0xa0011d5, {
+		0xed,0x69,0x89,0xf4,0xeb,0x64,0xc2,0x13,
+		0xe0,0x51,0x1f,0x03,0x26,0x52,0x7d,0xb7,
+		0x93,0x5d,0x65,0xca,0xb8,0x12,0x1d,0x62,
+		0x0d,0x5b,0x65,0x34,0x69,0xb2,0x62,0x21,
+	}
+ },
+ { 0xa001223, {
+		0xfb,0x32,0x5f,0xc6,0x83,0x4f,0x8c,0xb8,
+		0xa4,0x05,0xf9,0x71,0x53,0x01,0x16,0xc4,
+		0x83,0x75,0x94,0xdd,0xeb,0x7e,0xb7,0x15,
+		0x8e,0x3b,0x50,0x29,0x8a,0x9c,0xcc,0x45,
+	}
+ },
+ { 0xa001224, {
+		0x0e,0x0c,0xdf,0xb4,0x89,0xee,0x35,0x25,
+		0xdd,0x9e,0xdb,0xc0,0x69,0x83,0x0a,0xad,
+		0x26,0xa9,0xaa,0x9d,0xfc,0x3c,0xea,0xf9,
+		0x6c,0xdc,0xd5,0x6d,0x8b,0x6e,0x85,0x4a,
+	}
+ },
+ { 0xa001227, {
+		0xab,0xc6,0x00,0x69,0x4b,0x50,0x87,0xad,
+		0x5f,0x0e,0x8b,0xea,0x57,0x38,0xce,0x1d,
+		0x0f,0x75,0x26,0x02,0xf6,0xd6,0x96,0xe9,
+		0x87,0xb9,0xd6,0x20,0x27,0x7c,0xd2,0xe0,
+	}
+ },
+ { 0xa001229, {
+		0x7f,0x49,0x49,0x48,0x46,0xa5,0x50,0xa6,
+		0x28,0x89,0x98,0xe2,0x9e,0xb4,0x7f,0x75,
+		0x33,0xa7,0x04,0x02,0xe4,0x82,0xbf,0xb4,
+		0xa5,0x3a,0xba,0x24,0x8d,0x31,0x10,0x1d,
+	}
+ },
+ { 0xa00122e, {
+		0x56,0x94,0xa9,0x5d,0x06,0x68,0xfe,0xaf,
+		0xdf,0x7a,0xff,0x2d,0xdf,0x74,0x0f,0x15,
+		0x66,0xfb,0x00,0xb5,0x51,0x97,0x9b,0xfa,
+		0xcb,0x79,0x85,0x46,0x25,0xb4,0xd2,0x10,
+	}
+ },
+ { 0xa001231, {
+		0x0b,0x46,0xa5,0xfc,0x18,0x15,0xa0,0x9e,
+		0xa6,0xdc,0xb7,0xff,0x17,0xf7,0x30,0x64,
+		0xd4,0xda,0x9e,0x1b,0xc3,0xfc,0x02,0x3b,
+		0xe2,0xc6,0x0e,0x41,0x54,0xb5,0x18,0xdd,
+	}
+ },
+ { 0xa001234, {
+		0x88,0x8d,0xed,0xab,0xb5,0xbd,0x4e,0xf7,
+		0x7f,0xd4,0x0e,0x95,0x34,0x91,0xff,0xcc,
+		0xfb,0x2a,0xcd,0xf7,0xd5,0xdb,0x4c,0x9b,
+		0xd6,0x2e,0x73,0x50,0x8f,0x83,0x79,0x1a,
+	}
+ },
+ { 0xa001236, {
+		0x3d,0x30,0x00,0xb9,0x71,0xba,0x87,0x78,
+		0xa8,0x43,0x55,0xc4,0x26,0x59,0xcf,0x9d,
+		0x93,0xce,0x64,0x0e,0x8b,0x72,0x11,0x8b,
+		0xa3,0x8f,0x51,0xe9,0xca,0x98,0xaa,0x25,
+	}
+ },
+ { 0xa001238, {
+		0x72,0xf7,0x4b,0x0c,0x7d,0x58,0x65,0xcc,
+		0x00,0xcc,0x57,0x16,0x68,0x16,0xf8,0x2a,
+		0x1b,0xb3,0x8b,0xe1,0xb6,0x83,0x8c,0x7e,
+		0xc0,0xcd,0x33,0xf2,0x8d,0xf9,0xef,0x59,
+	}
+ },
+ { 0xa00820c, {
+		0xa8,0x0c,0x81,0xc0,0xa6,0x00,0xe7,0xf3,
+		0x5f,0x65,0xd3,0xb9,0x6f,0xea,0x93,0x63,
+		0xf1,0x8c,0x88,0x45,0xd7,0x82,0x80,0xd1,
+		0xe1,0x3b,0x8d,0xb2,0xf8,0x22,0x03,0xe2,
+	}
+ },
+ { 0xa10113e, {
+		0x05,0x3c,0x66,0xd7,0xa9,0x5a,0x33,0x10,
+		0x1b,0xf8,0x9c,0x8f,0xed,0xfc,0xa7,0xa0,
+		0x15,0xe3,0x3f,0x4b,0x1d,0x0d,0x0a,0xd5,
+		0xfa,0x90,0xc4,0xed,0x9d,0x90,0xaf,0x53,
+	}
+ },
+ { 0xa101144, {
+		0xb3,0x0b,0x26,0x9a,0xf8,0x7c,0x02,0x26,
+		0x35,0x84,0x53,0xa4,0xd3,0x2c,0x7c,0x09,
+		0x68,0x7b,0x96,0xb6,0x93,0xef,0xde,0xbc,
+		0xfd,0x4b,0x15,0xd2,0x81,0xd3,0x51,0x47,
+	}
+ },
+ { 0xa101148, {
+		0x20,0xd5,0x6f,0x40,0x4a,0xf6,0x48,0x90,
+		0xc2,0x93,0x9a,0xc2,0xfd,0xac,0xef,0x4f,
+		0xfa,0xc0,0x3d,0x92,0x3c,0x6d,0x01,0x08,
+		0xf1,0x5e,0xb0,0xde,0xb4,0x98,0xae,0xc4,
+	}
+ },
+ { 0xa10123e, {
+		0x03,0xb9,0x2c,0x76,0x48,0x93,0xc9,0x18,
+		0xfb,0x56,0xfd,0xf7,0xe2,0x1d,0xca,0x4d,
+		0x1d,0x13,0x53,0x63,0xfe,0x42,0x6f,0xfc,
+		0x19,0x0f,0xf1,0xfc,0xa7,0xdd,0x89,0x1b,
+	}
+ },
+ { 0xa101244, {
+		0x71,0x56,0xb5,0x9f,0x21,0xbf,0xb3,0x3c,
+		0x8c,0xd7,0x36,0xd0,0x34,0x52,0x1b,0xb1,
+		0x46,0x2f,0x04,0xf0,0x37,0xd8,0x1e,0x72,
+		0x24,0xa2,0x80,0x84,0x83,0x65,0x84,0xc0,
+	}
+ },
+ { 0xa101248, {
+		0xed,0x3b,0x95,0xa6,0x68,0xa7,0x77,0x3e,
+		0xfc,0x17,0x26,0xe2,0x7b,0xd5,0x56,0x22,
+		0x2c,0x1d,0xef,0xeb,0x56,0xdd,0xba,0x6e,
+		0x1b,0x7d,0x64,0x9d,0x4b,0x53,0x13,0x75,
+	}
+ },
+ { 0xa108108, {
+		0xed,0xc2,0xec,0xa1,0x15,0xc6,0x65,0xe9,
+		0xd0,0xef,0x39,0xaa,0x7f,0x55,0x06,0xc6,
+		0xf5,0xd4,0x3f,0x7b,0x14,0xd5,0x60,0x2c,
+		0x28,0x1e,0x9c,0x59,0x69,0x99,0x4d,0x16,
+	}
+ },
+ { 0xa20102d, {
+		0xf9,0x6e,0xf2,0x32,0xd3,0x0f,0x5f,0x11,
+		0x59,0xa1,0xfe,0xcc,0xcd,0x9b,0x42,0x89,
+		0x8b,0x89,0x2f,0xb5,0xbb,0x82,0xef,0x23,
+		0x8c,0xe9,0x19,0x3e,0xcc,0x3f,0x7b,0xb4,
+	}
+ },
+ { 0xa201210, {
+		0xe8,0x6d,0x51,0x6a,0x8e,0x72,0xf3,0xfe,
+		0x6e,0x16,0xbc,0x62,0x59,0x40,0x17,0xe9,
+		0x6d,0x3d,0x0e,0x6b,0xa7,0xac,0xe3,0x68,
+		0xf7,0x55,0xf0,0x13,0xbb,0x22,0xf6,0x41,
+	}
+ },
+ { 0xa404107, {
+		0xbb,0x04,0x4e,0x47,0xdd,0x5e,0x26,0x45,
+		0x1a,0xc9,0x56,0x24,0xa4,0x4c,0x82,0xb0,
+		0x8b,0x0d,0x9f,0xf9,0x3a,0xdf,0xc6,0x81,
+		0x13,0xbc,0xc5,0x25,0xe4,0xc5,0xc3,0x99,
+	}
+ },
+ { 0xa500011, {
+		0x23,0x3d,0x70,0x7d,0x03,0xc3,0xc4,0xf4,
+		0x2b,0x82,0xc6,0x05,0xda,0x80,0x0a,0xf1,
+		0xd7,0x5b,0x65,0x3a,0x7d,0xab,0xdf,0xa2,
+		0x11,0x5e,0x96,0x7e,0x71,0xe9,0xfc,0x74,
+	}
+ },
+ { 0xa601209, {
+		0x66,0x48,0xd4,0x09,0x05,0xcb,0x29,0x32,
+		0x66,0xb7,0x9a,0x76,0xcd,0x11,0xf3,0x30,
+		0x15,0x86,0xcc,0x5d,0x97,0x0f,0xc0,0x46,
+		0xe8,0x73,0xe2,0xd6,0xdb,0xd2,0x77,0x1d,
+	}
+ },
+ { 0xa704107, {
+		0xf3,0xc6,0x58,0x26,0xee,0xac,0x3f,0xd6,
+		0xce,0xa1,0x72,0x47,0x3b,0xba,0x2b,0x93,
+		0x2a,0xad,0x8e,0x6b,0xea,0x9b,0xb7,0xc2,
+		0x64,0x39,0x71,0x8c,0xce,0xe7,0x41,0x39,
+	}
+ },
+ { 0xa705206, {
+		0x8d,0xc0,0x76,0xbd,0x58,0x9f,0x8f,0xa4,
+		0x12,0x9d,0x21,0xfb,0x48,0x21,0xbc,0xe7,
+		0x67,0x6f,0x04,0x18,0xae,0x20,0x87,0x4b,
+		0x03,0x35,0xe9,0xbe,0xfb,0x06,0xdf,0xfc,
+	}
+ },
+ { 0xa708007, {
+		0x6b,0x76,0xcc,0x78,0xc5,0x8a,0xa3,0xe3,
+		0x32,0x2d,0x79,0xe4,0xc3,0x80,0xdb,0xb2,
+		0x07,0xaa,0x3a,0xe0,0x57,0x13,0x72,0x80,
+		0xdf,0x92,0x73,0x84,0x87,0x3c,0x73,0x93,
+	}
+ },
+ { 0xa70c005, {
+		0x88,0x5d,0xfb,0x79,0x64,0xd8,0x46,0x3b,
+		0x4a,0x83,0x8e,0x77,0x7e,0xcf,0xb3,0x0f,
+		0x1f,0x1f,0xf1,0x97,0xeb,0xfe,0x56,0x55,
+		0xee,0x49,0xac,0xe1,0x8b,0x13,0xc5,0x13,
+	}
+ },
+ { 0xaa00116, {
+		0xe8,0x4c,0x2c,0x88,0xa1,0xac,0x24,0x63,
+		0x65,0xe5,0xaa,0x2d,0x16,0xa9,0xc3,0xf5,
+		0xfe,0x1d,0x5e,0x65,0xc7,0xaa,0x92,0x4d,
+		0x91,0xee,0x76,0xbb,0x4c,0x66,0x78,0xc9,
+	}
+ },
+ { 0xaa00212, {
+		0xbd,0x57,0x5d,0x0a,0x0a,0x30,0xc1,0x75,
+		0x95,0x58,0x5e,0x93,0x02,0x28,0x43,0x71,
+		0xed,0x42,0x29,0xc8,0xec,0x34,0x2b,0xb2,
+		0x1a,0x65,0x4b,0xfe,0x07,0x0f,0x34,0xa1,
+	}
+ },
+ { 0xaa00213, {
+		0xed,0x58,0xb7,0x76,0x81,0x7f,0xd9,0x3a,
+		0x1a,0xff,0x8b,0x34,0xb8,0x4a,0x99,0x0f,
+		0x28,0x49,0x6c,0x56,0x2b,0xdc,0xb7,0xed,
+		0x96,0xd5,0x9d,0xc1,0x7a,0xd4,0x51,0x9b,
+	}
+ },
+ { 0xaa00215, {
+		0x55,0xd3,0x28,0xcb,0x87,0xa9,0x32,0xe9,
+		0x4e,0x85,0x4b,0x7c,0x6b,0xd5,0x7c,0xd4,
+		0x1b,0x51,0x71,0x3a,0x0e,0x0b,0xdc,0x9b,
+		0x68,0x2f,0x46,0xee,0xfe,0xc6,0x6d,0xef,
+	}
+ },
+};
diff --git a/arch/x86/kernel/cpu/microcode/internal.h b/arch/x86/kernel/cpu/microcode/internal.h
index 21776c529fa9..5df621752fef 100644
--- a/arch/x86/kernel/cpu/microcode/internal.h
+++ b/arch/x86/kernel/cpu/microcode/internal.h
@@ -100,14 +100,12 @@ extern bool force_minrev;
 #ifdef CONFIG_CPU_SUP_AMD
 void load_ucode_amd_bsp(struct early_load_data *ed, unsigned int family);
 void load_ucode_amd_ap(unsigned int family);
-int save_microcode_in_initrd_amd(unsigned int family);
 void reload_ucode_amd(unsigned int cpu);
 struct microcode_ops *init_amd_microcode(void);
 void exit_amd_microcode(void);
 #else /* CONFIG_CPU_SUP_AMD */
 static inline void load_ucode_amd_bsp(struct early_load_data *ed, unsigned int family) { }
 static inline void load_ucode_amd_ap(unsigned int family) { }
-static inline int save_microcode_in_initrd_amd(unsigned int family) { return -EINVAL; }
 static inline void reload_ucode_amd(unsigned int cpu) { }
 static inline struct microcode_ops *init_amd_microcode(void) { return NULL; }
 static inline void exit_amd_microcode(void) { }
diff --git a/arch/x86/kernel/cpu/sgx/ioctl.c b/arch/x86/kernel/cpu/sgx/ioctl.c
index b65ab214bdf5..776a20172867 100644
--- a/arch/x86/kernel/cpu/sgx/ioctl.c
+++ b/arch/x86/kernel/cpu/sgx/ioctl.c
@@ -64,6 +64,13 @@ static int sgx_encl_create(struct sgx_encl *encl, struct sgx_secs *secs)
 	struct file *backing;
 	long ret;
 
+	/*
+	 * ECREATE would detect this too, but checking here also ensures
+	 * that the 'encl_size' calculations below can never overflow.
+	 */
+	if (!is_power_of_2(secs->size))
+		return -EINVAL;
+
 	va_page = sgx_encl_grow(encl, true);
 	if (IS_ERR(va_page))
 		return PTR_ERR(va_page);
diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c
index 59d23cdf4ed0..dd8748c45529 100644
--- a/arch/x86/kernel/devicetree.c
+++ b/arch/x86/kernel/devicetree.c
@@ -2,6 +2,7 @@
 /*
  * Architecture specific OF callbacks.
  */
+#include <linux/acpi.h>
 #include <linux/export.h>
 #include <linux/io.h>
 #include <linux/interrupt.h>
@@ -313,6 +314,6 @@ void __init x86_flattree_get_config(void)
 	if (initial_dtb)
 		early_memunmap(dt, map_len);
 #endif
-	if (of_have_populated_dt())
+	if (acpi_disabled && of_have_populated_dt())
 		x86_init.mpparse.parse_smp_cfg = x86_dtb_parse_smp_config;
 }
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index 385e3a5fc304..feca4f20b06a 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -25,8 +25,10 @@
 #include <asm/posted_intr.h>
 #include <asm/irq_remapping.h>
 
+#if defined(CONFIG_X86_LOCAL_APIC) || defined(CONFIG_X86_THERMAL_VECTOR)
 #define CREATE_TRACE_POINTS
 #include <asm/trace/irq_vectors.h>
+#endif
 
 DEFINE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat);
 EXPORT_PER_CPU_SYMBOL(irq_stat);
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 8eb3a88707f2..121edf1f2a79 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -1763,7 +1763,7 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function)
 
 		entry->ecx = entry->edx = 0;
 		if (!enable_pmu || !kvm_cpu_cap_has(X86_FEATURE_PERFMON_V2)) {
-			entry->eax = entry->ebx;
+			entry->eax = entry->ebx = 0;
 			break;
 		}
 
diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index 6a6dd5a84f22..6ebeb6cea6c0 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -2226,6 +2226,9 @@ static u64 kvm_hv_send_ipi(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc)
 	u32 vector;
 	bool all_cpus;
 
+	if (!lapic_in_kernel(vcpu))
+		return HV_STATUS_INVALID_HYPERCALL_INPUT;
+
 	if (hc->code == HVCALL_SEND_IPI) {
 		if (!hc->fast) {
 			if (unlikely(kvm_read_guest(kvm, hc->ingpa, &send_ipi,
@@ -2852,7 +2855,8 @@ int kvm_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid,
 			ent->eax |= HV_X64_REMOTE_TLB_FLUSH_RECOMMENDED;
 			ent->eax |= HV_X64_APIC_ACCESS_RECOMMENDED;
 			ent->eax |= HV_X64_RELAXED_TIMING_RECOMMENDED;
-			ent->eax |= HV_X64_CLUSTER_IPI_RECOMMENDED;
+			if (!vcpu || lapic_in_kernel(vcpu))
+				ent->eax |= HV_X64_CLUSTER_IPI_RECOMMENDED;
 			ent->eax |= HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED;
 			if (evmcs_ver)
 				ent->eax |= HV_X64_ENLIGHTENED_VMCS_RECOMMENDED;
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 74c20dbb92da..8160870398b9 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -5540,7 +5540,7 @@ void kvm_init_shadow_npt_mmu(struct kvm_vcpu *vcpu, unsigned long cr0,
 	union kvm_mmu_page_role root_role;
 
 	/* NPT requires CR0.PG=1. */
-	WARN_ON_ONCE(cpu_role.base.direct);
+	WARN_ON_ONCE(cpu_role.base.direct || !cpu_role.base.guest_mode);
 
 	root_role = cpu_role.base;
 	root_role.level = kvm_mmu_get_tdp_level(vcpu);
@@ -7460,7 +7460,7 @@ static bool kvm_nx_huge_page_recovery_worker(void *data)
 	return true;
 }
 
-static void kvm_mmu_start_lpage_recovery(struct once *once)
+static int kvm_mmu_start_lpage_recovery(struct once *once)
 {
 	struct kvm_arch *ka = container_of(once, struct kvm_arch, nx_once);
 	struct kvm *kvm = container_of(ka, struct kvm, arch);
@@ -7471,13 +7471,14 @@ static void kvm_mmu_start_lpage_recovery(struct once *once)
 				      kvm_nx_huge_page_recovery_worker_kill,
 				      kvm, "kvm-nx-lpage-recovery");
 
-	if (!nx_thread)
-		return;
+	if (IS_ERR(nx_thread))
+		return PTR_ERR(nx_thread);
 
 	vhost_task_start(nx_thread);
 
 	/* Make the task visible only once it is fully started. */
 	WRITE_ONCE(kvm->arch.nx_huge_page_recovery_thread, nx_thread);
+	return 0;
 }
 
 int kvm_mmu_post_init_vm(struct kvm *kvm)
@@ -7485,10 +7486,7 @@ int kvm_mmu_post_init_vm(struct kvm *kvm)
 	if (nx_hugepage_mitigation_hard_disabled)
 		return 0;
 
-	call_once(&kvm->arch.nx_once, kvm_mmu_start_lpage_recovery);
-	if (!kvm->arch.nx_huge_page_recovery_thread)
-		return -ENOMEM;
-	return 0;
+	return call_once(&kvm->arch.nx_once, kvm_mmu_start_lpage_recovery);
 }
 
 void kvm_mmu_pre_destroy_vm(struct kvm *kvm)
diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c
index d77b094d9a4d..04c375bf1ac2 100644
--- a/arch/x86/kvm/svm/nested.c
+++ b/arch/x86/kvm/svm/nested.c
@@ -646,6 +646,11 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm,
 	u32 pause_count12;
 	u32 pause_thresh12;
 
+	nested_svm_transition_tlb_flush(vcpu);
+
+	/* Enter Guest-Mode */
+	enter_guest_mode(vcpu);
+
 	/*
 	 * Filled at exit: exit_code, exit_code_hi, exit_info_1, exit_info_2,
 	 * exit_int_info, exit_int_info_err, next_rip, insn_len, insn_bytes.
@@ -762,11 +767,6 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm,
 		}
 	}
 
-	nested_svm_transition_tlb_flush(vcpu);
-
-	/* Enter Guest-Mode */
-	enter_guest_mode(vcpu);
-
 	/*
 	 * Merge guest and host intercepts - must be called with vcpu in
 	 * guest-mode to take effect.
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index a2a794c32050..661108d65ee7 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -2972,6 +2972,16 @@ void __init sev_hardware_setup(void)
 	    WARN_ON_ONCE(!boot_cpu_has(X86_FEATURE_FLUSHBYASID)))
 		goto out;
 
+	/*
+	 * The kernel's initcall infrastructure lacks the ability to express
+	 * dependencies between initcalls, whereas the modules infrastructure
+	 * automatically handles dependencies via symbol loading.  Ensure the
+	 * PSP SEV driver is initialized before proceeding if KVM is built-in,
+	 * as the dependency isn't handled by the initcall infrastructure.
+	 */
+	if (IS_BUILTIN(CONFIG_KVM_AMD) && sev_module_init())
+		goto out;
+
 	/* Retrieve SEV CPUID information */
 	cpuid(0x8000001f, &eax, &ebx, &ecx, &edx);
 
@@ -4580,6 +4590,8 @@ void sev_es_vcpu_reset(struct vcpu_svm *svm)
 
 void sev_es_prepare_switch_to_guest(struct vcpu_svm *svm, struct sev_es_save_area *hostsa)
 {
+	struct kvm *kvm = svm->vcpu.kvm;
+
 	/*
 	 * All host state for SEV-ES guests is categorized into three swap types
 	 * based on how it is handled by hardware during a world switch:
@@ -4603,14 +4615,22 @@ void sev_es_prepare_switch_to_guest(struct vcpu_svm *svm, struct sev_es_save_are
 
 	/*
 	 * If DebugSwap is enabled, debug registers are loaded but NOT saved by
-	 * the CPU (Type-B). If DebugSwap is disabled/unsupported, the CPU both
-	 * saves and loads debug registers (Type-A).
+	 * the CPU (Type-B). If DebugSwap is disabled/unsupported, the CPU does
+	 * not save or load debug registers.  Sadly, KVM can't prevent SNP
+	 * guests from lying about DebugSwap on secondary vCPUs, i.e. the
+	 * SEV_FEATURES provided at "AP Create" isn't guaranteed to match what
+	 * the guest has actually enabled (or not!) in the VMSA.
+	 *
+	 * If DebugSwap is *possible*, save the masks so that they're restored
+	 * if the guest enables DebugSwap.  But for the DRs themselves, do NOT
+	 * rely on the CPU to restore the host values; KVM will restore them as
+	 * needed in common code, via hw_breakpoint_restore().  Note, KVM does
+	 * NOT support virtualizing Breakpoint Extensions, i.e. the mask MSRs
+	 * don't need to be restored per se, KVM just needs to ensure they are
+	 * loaded with the correct values *if* the CPU writes the MSRs.
 	 */
-	if (sev_vcpu_has_debug_swap(svm)) {
-		hostsa->dr0 = native_get_debugreg(0);
-		hostsa->dr1 = native_get_debugreg(1);
-		hostsa->dr2 = native_get_debugreg(2);
-		hostsa->dr3 = native_get_debugreg(3);
+	if (sev_vcpu_has_debug_swap(svm) ||
+	    (sev_snp_guest(kvm) && cpu_feature_enabled(X86_FEATURE_DEBUG_SWAP))) {
 		hostsa->dr0_addr_mask = amd_get_dr_addr_mask(0);
 		hostsa->dr1_addr_mask = amd_get_dr_addr_mask(1);
 		hostsa->dr2_addr_mask = amd_get_dr_addr_mask(2);
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 7640a84e554a..e67de787fc71 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -1991,11 +1991,11 @@ static void new_asid(struct vcpu_svm *svm, struct svm_cpu_data *sd)
 	svm->asid = sd->next_asid++;
 }
 
-static void svm_set_dr6(struct vcpu_svm *svm, unsigned long value)
+static void svm_set_dr6(struct kvm_vcpu *vcpu, unsigned long value)
 {
-	struct vmcb *vmcb = svm->vmcb;
+	struct vmcb *vmcb = to_svm(vcpu)->vmcb;
 
-	if (svm->vcpu.arch.guest_state_protected)
+	if (vcpu->arch.guest_state_protected)
 		return;
 
 	if (unlikely(value != vmcb->save.dr6)) {
@@ -3165,6 +3165,27 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
 			kvm_pr_unimpl_wrmsr(vcpu, ecx, data);
 			break;
 		}
+
+		/*
+		 * AMD changed the architectural behavior of bits 5:2.  On CPUs
+		 * without BusLockTrap, bits 5:2 control "external pins", but
+		 * on CPUs that support BusLockDetect, bit 2 enables BusLockTrap
+		 * and bits 5:3 are reserved-to-zero.  Sadly, old KVM allowed
+		 * the guest to set bits 5:2 despite not actually virtualizing
+		 * Performance-Monitoring/Breakpoint external pins.  Drop bits
+		 * 5:2 for backwards compatibility.
+		 */
+		data &= ~GENMASK(5, 2);
+
+		/*
+		 * Suppress BTF as KVM doesn't virtualize BTF, but there's no
+		 * way to communicate lack of support to the guest.
+		 */
+		if (data & DEBUGCTLMSR_BTF) {
+			kvm_pr_unimpl_wrmsr(vcpu, MSR_IA32_DEBUGCTLMSR, data);
+			data &= ~DEBUGCTLMSR_BTF;
+		}
+
 		if (data & DEBUGCTL_RESERVED_BITS)
 			return 1;
 
@@ -4189,6 +4210,18 @@ static noinstr void svm_vcpu_enter_exit(struct kvm_vcpu *vcpu, bool spec_ctrl_in
 
 	guest_state_enter_irqoff();
 
+	/*
+	 * Set RFLAGS.IF prior to VMRUN, as the host's RFLAGS.IF at the time of
+	 * VMRUN controls whether or not physical IRQs are masked (KVM always
+	 * runs with V_INTR_MASKING_MASK).  Toggle RFLAGS.IF here to avoid the
+	 * temptation to do STI+VMRUN+CLI, as AMD CPUs bleed the STI shadow
+	 * into guest state if delivery of an event during VMRUN triggers a
+	 * #VMEXIT, and the guest_state transitions already tell lockdep that
+	 * IRQs are being enabled/disabled.  Note!  GIF=0 for the entirety of
+	 * this path, so IRQs aren't actually unmasked while running host code.
+	 */
+	raw_local_irq_enable();
+
 	amd_clear_divider();
 
 	if (sev_es_guest(vcpu->kvm))
@@ -4197,6 +4230,8 @@ static noinstr void svm_vcpu_enter_exit(struct kvm_vcpu *vcpu, bool spec_ctrl_in
 	else
 		__svm_vcpu_run(svm, spec_ctrl_intercepted);
 
+	raw_local_irq_disable();
+
 	guest_state_exit_irqoff();
 }
 
@@ -4247,14 +4282,22 @@ static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu,
 	 * Run with all-zero DR6 unless needed, so that we can get the exact cause
 	 * of a #DB.
 	 */
-	if (unlikely(vcpu->arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT))
-		svm_set_dr6(svm, vcpu->arch.dr6);
-	else
-		svm_set_dr6(svm, DR6_ACTIVE_LOW);
+	if (likely(!(vcpu->arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT)))
+		svm_set_dr6(vcpu, DR6_ACTIVE_LOW);
 
 	clgi();
 	kvm_load_guest_xsave_state(vcpu);
 
+	/*
+	 * Hardware only context switches DEBUGCTL if LBR virtualization is
+	 * enabled.  Manually load DEBUGCTL if necessary (and restore it after
+	 * VM-Exit), as running with the host's DEBUGCTL can negatively affect
+	 * guest state and can even be fatal, e.g. due to Bus Lock Detect.
+	 */
+	if (!(svm->vmcb->control.virt_ext & LBR_CTL_ENABLE_MASK) &&
+	    vcpu->arch.host_debugctl != svm->vmcb->save.dbgctl)
+		update_debugctlmsr(svm->vmcb->save.dbgctl);
+
 	kvm_wait_lapic_expire(vcpu);
 
 	/*
@@ -4282,6 +4325,10 @@ static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu,
 	if (unlikely(svm->vmcb->control.exit_code == SVM_EXIT_NMI))
 		kvm_before_interrupt(vcpu, KVM_HANDLING_NMI);
 
+	if (!(svm->vmcb->control.virt_ext & LBR_CTL_ENABLE_MASK) &&
+	    vcpu->arch.host_debugctl != svm->vmcb->save.dbgctl)
+		update_debugctlmsr(vcpu->arch.host_debugctl);
+
 	kvm_load_host_xsave_state(vcpu);
 	stgi();
 
@@ -5043,6 +5090,7 @@ static struct kvm_x86_ops svm_x86_ops __initdata = {
 	.set_idt = svm_set_idt,
 	.get_gdt = svm_get_gdt,
 	.set_gdt = svm_set_gdt,
+	.set_dr6 = svm_set_dr6,
 	.set_dr7 = svm_set_dr7,
 	.sync_dirty_debug_regs = svm_sync_dirty_debug_regs,
 	.cache_reg = svm_cache_reg,
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index 9d7cdb8fbf87..ea44c1da5a7c 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -584,7 +584,7 @@ static inline bool is_vnmi_enabled(struct vcpu_svm *svm)
 /* svm.c */
 #define MSR_INVALID				0xffffffffU
 
-#define DEBUGCTL_RESERVED_BITS (~(0x3fULL))
+#define DEBUGCTL_RESERVED_BITS (~DEBUGCTLMSR_LBR)
 
 extern bool dump_invalid_vmcb;
 
diff --git a/arch/x86/kvm/svm/vmenter.S b/arch/x86/kvm/svm/vmenter.S
index 2ed80aea3bb1..0c61153b275f 100644
--- a/arch/x86/kvm/svm/vmenter.S
+++ b/arch/x86/kvm/svm/vmenter.S
@@ -170,12 +170,8 @@ SYM_FUNC_START(__svm_vcpu_run)
 	mov VCPU_RDI(%_ASM_DI), %_ASM_DI
 
 	/* Enter guest mode */
-	sti
-
 3:	vmrun %_ASM_AX
 4:
-	cli
-
 	/* Pop @svm to RAX while it's the only available register. */
 	pop %_ASM_AX
 
@@ -340,12 +336,8 @@ SYM_FUNC_START(__svm_sev_es_vcpu_run)
 	mov KVM_VMCB_pa(%rax), %rax
 
 	/* Enter guest mode */
-	sti
-
 1:	vmrun %rax
-
-2:	cli
-
+2:
 	/* IMPORTANT: Stuff the RSB immediately after VM-Exit, before RET! */
 	FILL_RETURN_BUFFER %rax, RSB_CLEAR_LOOPS, X86_FEATURE_RSB_VMEXIT
 
diff --git a/arch/x86/kvm/vmx/main.c b/arch/x86/kvm/vmx/main.c
index 2427f918e763..43ee9ed11291 100644
--- a/arch/x86/kvm/vmx/main.c
+++ b/arch/x86/kvm/vmx/main.c
@@ -61,6 +61,7 @@ struct kvm_x86_ops vt_x86_ops __initdata = {
 	.set_idt = vmx_set_idt,
 	.get_gdt = vmx_get_gdt,
 	.set_gdt = vmx_set_gdt,
+	.set_dr6 = vmx_set_dr6,
 	.set_dr7 = vmx_set_dr7,
 	.sync_dirty_debug_regs = vmx_sync_dirty_debug_regs,
 	.cache_reg = vmx_cache_reg,
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 8a7af02d466e..ed8a3cb53961 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -5084,6 +5084,17 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason,
 
 		load_vmcs12_host_state(vcpu, vmcs12);
 
+		/*
+		 * Process events if an injectable IRQ or NMI is pending, even
+		 * if the event is blocked (RFLAGS.IF is cleared on VM-Exit).
+		 * If an event became pending while L2 was active, KVM needs to
+		 * either inject the event or request an IRQ/NMI window.  SMIs
+		 * don't need to be processed as SMM is mutually exclusive with
+		 * non-root mode.  INIT/SIPI don't need to be checked as INIT
+		 * is blocked post-VMXON, and SIPIs are ignored.
+		 */
+		if (kvm_cpu_has_injectable_intr(vcpu) || vcpu->arch.nmi_pending)
+			kvm_make_request(KVM_REQ_EVENT, vcpu);
 		return;
 	}
 
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index f72835e85b6d..3b92f893b239 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -1514,16 +1514,12 @@ void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu,
  */
 void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
-	struct vcpu_vmx *vmx = to_vmx(vcpu);
-
 	if (vcpu->scheduled_out && !kvm_pause_in_guest(vcpu->kvm))
 		shrink_ple_window(vcpu);
 
 	vmx_vcpu_load_vmcs(vcpu, cpu, NULL);
 
 	vmx_vcpu_pi_load(vcpu, cpu);
-
-	vmx->host_debugctlmsr = get_debugctlmsr();
 }
 
 void vmx_vcpu_put(struct kvm_vcpu *vcpu)
@@ -5648,6 +5644,12 @@ void vmx_sync_dirty_debug_regs(struct kvm_vcpu *vcpu)
 	set_debugreg(DR6_RESERVED, 6);
 }
 
+void vmx_set_dr6(struct kvm_vcpu *vcpu, unsigned long val)
+{
+	lockdep_assert_irqs_disabled();
+	set_debugreg(vcpu->arch.dr6, 6);
+}
+
 void vmx_set_dr7(struct kvm_vcpu *vcpu, unsigned long val)
 {
 	vmcs_writel(GUEST_DR7, val);
@@ -7417,10 +7419,6 @@ fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediate_exit)
 		vmx->loaded_vmcs->host_state.cr4 = cr4;
 	}
 
-	/* When KVM_DEBUGREG_WONT_EXIT, dr6 is accessible in guest. */
-	if (unlikely(vcpu->arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT))
-		set_debugreg(vcpu->arch.dr6, 6);
-
 	/* When single-stepping over STI and MOV SS, we must clear the
 	 * corresponding interruptibility bits in the guest state. Otherwise
 	 * vmentry fails as it then expects bit 14 (BS) in pending debug
@@ -7456,8 +7454,8 @@ fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediate_exit)
 	}
 
 	/* MSR_IA32_DEBUGCTLMSR is zeroed on vmexit. Restore it if needed */
-	if (vmx->host_debugctlmsr)
-		update_debugctlmsr(vmx->host_debugctlmsr);
+	if (vcpu->arch.host_debugctl)
+		update_debugctlmsr(vcpu->arch.host_debugctl);
 
 #ifndef CONFIG_X86_64
 	/*
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index 8b111ce1087c..951e44dc9d0e 100644
--- a/arch/x86/kvm/vmx/vmx.h
+++ b/arch/x86/kvm/vmx/vmx.h
@@ -340,8 +340,6 @@ struct vcpu_vmx {
 	/* apic deadline value in host tsc */
 	u64 hv_deadline_tsc;
 
-	unsigned long host_debugctlmsr;
-
 	/*
 	 * Only bits masked by msr_ia32_feature_control_valid_bits can be set in
 	 * msr_ia32_feature_control. FEAT_CTL_LOCKED is always included
diff --git a/arch/x86/kvm/vmx/x86_ops.h b/arch/x86/kvm/vmx/x86_ops.h
index ce3295a67c04..430773a5ef8e 100644
--- a/arch/x86/kvm/vmx/x86_ops.h
+++ b/arch/x86/kvm/vmx/x86_ops.h
@@ -73,6 +73,7 @@ void vmx_get_idt(struct kvm_vcpu *vcpu, struct desc_ptr *dt);
 void vmx_set_idt(struct kvm_vcpu *vcpu, struct desc_ptr *dt);
 void vmx_get_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt);
 void vmx_set_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt);
+void vmx_set_dr6(struct kvm_vcpu *vcpu, unsigned long val);
 void vmx_set_dr7(struct kvm_vcpu *vcpu, unsigned long val);
 void vmx_sync_dirty_debug_regs(struct kvm_vcpu *vcpu);
 void vmx_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 8e77e61d4fbd..4b64ab350bcd 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -10961,10 +10961,15 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 		set_debugreg(vcpu->arch.eff_db[1], 1);
 		set_debugreg(vcpu->arch.eff_db[2], 2);
 		set_debugreg(vcpu->arch.eff_db[3], 3);
+		/* When KVM_DEBUGREG_WONT_EXIT, dr6 is accessible in guest. */
+		if (unlikely(vcpu->arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT))
+			kvm_x86_call(set_dr6)(vcpu, vcpu->arch.dr6);
 	} else if (unlikely(hw_breakpoint_active())) {
 		set_debugreg(0, 7);
 	}
 
+	vcpu->arch.host_debugctl = get_debugctlmsr();
+
 	guest_timing_enter_irqoff();
 
 	for (;;) {
@@ -12874,11 +12879,11 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
 		mutex_unlock(&kvm->slots_lock);
 	}
 	kvm_unload_vcpu_mmus(kvm);
+	kvm_destroy_vcpus(kvm);
 	kvm_x86_call(vm_destroy)(kvm);
 	kvm_free_msr_filter(srcu_dereference_check(kvm->arch.msr_filter, &kvm->srcu, 1));
 	kvm_pic_destroy(kvm);
 	kvm_ioapic_destroy(kvm);
-	kvm_destroy_vcpus(kvm);
 	kvfree(rcu_dereference_check(kvm->arch.apic_map, 1));
 	kfree(srcu_dereference_check(kvm->arch.pmu_event_filter, &kvm->srcu, 1));
 	kvm_mmu_uninit_vm(kvm);
diff --git a/arch/x86/um/os-Linux/registers.c b/arch/x86/um/os-Linux/registers.c
index 76eaeb93928c..eb1cdadc8a61 100644
--- a/arch/x86/um/os-Linux/registers.c
+++ b/arch/x86/um/os-Linux/registers.c
@@ -18,6 +18,7 @@
 #include <registers.h>
 #include <sys/mman.h>
 
+static unsigned long ptrace_regset;
 unsigned long host_fp_size;
 
 int get_fp_registers(int pid, unsigned long *regs)
@@ -27,7 +28,7 @@ int get_fp_registers(int pid, unsigned long *regs)
 		.iov_len = host_fp_size,
 	};
 
-	if (ptrace(PTRACE_GETREGSET, pid, NT_X86_XSTATE, &iov) < 0)
+	if (ptrace(PTRACE_GETREGSET, pid, ptrace_regset, &iov) < 0)
 		return -errno;
 	return 0;
 }
@@ -39,7 +40,7 @@ int put_fp_registers(int pid, unsigned long *regs)
 		.iov_len = host_fp_size,
 	};
 
-	if (ptrace(PTRACE_SETREGSET, pid, NT_X86_XSTATE, &iov) < 0)
+	if (ptrace(PTRACE_SETREGSET, pid, ptrace_regset, &iov) < 0)
 		return -errno;
 	return 0;
 }
@@ -58,9 +59,23 @@ int arch_init_registers(int pid)
 		return -ENOMEM;
 
 	/* GDB has x86_xsave_length, which uses x86_cpuid_count */
-	ret = ptrace(PTRACE_GETREGSET, pid, NT_X86_XSTATE, &iov);
+	ptrace_regset = NT_X86_XSTATE;
+	ret = ptrace(PTRACE_GETREGSET, pid, ptrace_regset, &iov);
 	if (ret)
 		ret = -errno;
+
+	if (ret == -ENODEV) {
+#ifdef CONFIG_X86_32
+		ptrace_regset = NT_PRXFPREG;
+#else
+		ptrace_regset = NT_PRFPREG;
+#endif
+		iov.iov_len = 2 * 1024 * 1024;
+		ret = ptrace(PTRACE_GETREGSET, pid, ptrace_regset, &iov);
+		if (ret)
+			ret = -errno;
+	}
+
 	munmap(iov.iov_base, 2 * 1024 * 1024);
 
 	host_fp_size = iov.iov_len;
diff --git a/arch/x86/um/signal.c b/arch/x86/um/signal.c
index 75087e85b6fd..2934e170b0fe 100644
--- a/arch/x86/um/signal.c
+++ b/arch/x86/um/signal.c
@@ -187,7 +187,12 @@ static int copy_sc_to_user(struct sigcontext __user *to,
 	 * Put magic/size values for userspace. We do not bother to verify them
 	 * later on, however, userspace needs them should it try to read the
 	 * XSTATE data. And ptrace does not fill in these parts.
+	 *
+	 * Skip this if we do not have an XSTATE frame.
 	 */
+	if (host_fp_size <= sizeof(to_fp64->fpstate))
+		return 0;
+
 	BUILD_BUG_ON(sizeof(int) != FP_XSTATE_MAGIC2_SIZE);
 #ifdef CONFIG_X86_32
 	__put_user(offsetof(struct _fpstate_32, _fxsr_env) +
@@ -367,11 +372,13 @@ int setup_signal_stack_si(unsigned long stack_top, struct ksignal *ksig,
 	int err = 0, sig = ksig->sig;
 	unsigned long fp_to;
 
-	frame = (struct rt_sigframe __user *)
-		round_down(stack_top - sizeof(struct rt_sigframe), 16);
+	frame = (void __user *)stack_top - sizeof(struct rt_sigframe);
 
 	/* Add required space for math frame */
-	frame = (struct rt_sigframe __user *)((unsigned long)frame - math_size);
+	frame = (void __user *)((unsigned long)frame - math_size);
+
+	/* ABI requires 16 byte boundary alignment */
+	frame = (void __user *)round_down((unsigned long)frame, 16);
 
 	/* Subtract 128 for a red zone and 8 for proper alignment */
 	frame = (struct rt_sigframe __user *) ((unsigned long) frame - 128 - 8);
diff --git a/arch/x86/virt/svm/sev.c b/arch/x86/virt/svm/sev.c
index 1dcc027ec77e..42e74a5a7d78 100644
--- a/arch/x86/virt/svm/sev.c
+++ b/arch/x86/virt/svm/sev.c
@@ -505,19 +505,19 @@ static bool __init setup_rmptable(void)
  * described in the SNP_INIT_EX firmware command description in the SNP
  * firmware ABI spec.
  */
-static int __init snp_rmptable_init(void)
+int __init snp_rmptable_init(void)
 {
 	unsigned int i;
 	u64 val;
 
-	if (!cc_platform_has(CC_ATTR_HOST_SEV_SNP))
-		return 0;
+	if (WARN_ON_ONCE(!cc_platform_has(CC_ATTR_HOST_SEV_SNP)))
+		return -ENOSYS;
 
-	if (!amd_iommu_snp_en)
-		goto nosnp;
+	if (WARN_ON_ONCE(!amd_iommu_snp_en))
+		return -ENOSYS;
 
 	if (!setup_rmptable())
-		goto nosnp;
+		return -ENOSYS;
 
 	/*
 	 * Check if SEV-SNP is already enabled, this can happen in case of
@@ -530,7 +530,7 @@ static int __init snp_rmptable_init(void)
 	/* Zero out the RMP bookkeeping area */
 	if (!clear_rmptable_bookkeeping()) {
 		free_rmp_segment_table();
-		goto nosnp;
+		return -ENOSYS;
 	}
 
 	/* Zero out the RMP entries */
@@ -562,17 +562,8 @@ skip_enable:
 	crash_kexec_post_notifiers = true;
 
 	return 0;
-
-nosnp:
-	cc_platform_clear(CC_ATTR_HOST_SEV_SNP);
-	return -ENOSYS;
 }
 
-/*
- * This must be called after the IOMMU has been initialized.
- */
-device_initcall(snp_rmptable_init);
-
 static void set_rmp_segment_info(unsigned int segment_shift)
 {
 	rmp_segment_shift = segment_shift;
diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c
index 2c70cd35e72c..d078de2c952b 100644
--- a/arch/x86/xen/mmu_pv.c
+++ b/arch/x86/xen/mmu_pv.c
@@ -111,6 +111,51 @@ static pud_t level3_user_vsyscall[PTRS_PER_PUD] __page_aligned_bss;
  */
 static DEFINE_SPINLOCK(xen_reservation_lock);
 
+/* Protected by xen_reservation_lock. */
+#define MIN_CONTIG_ORDER 9 /* 2MB */
+static unsigned int discontig_frames_order = MIN_CONTIG_ORDER;
+static unsigned long discontig_frames_early[1UL << MIN_CONTIG_ORDER] __initdata;
+static unsigned long *discontig_frames __refdata = discontig_frames_early;
+static bool discontig_frames_dyn;
+
+static int alloc_discontig_frames(unsigned int order)
+{
+	unsigned long *new_array, *old_array;
+	unsigned int old_order;
+	unsigned long flags;
+
+	BUG_ON(order < MIN_CONTIG_ORDER);
+	BUILD_BUG_ON(sizeof(discontig_frames_early) != PAGE_SIZE);
+
+	new_array = (unsigned long *)__get_free_pages(GFP_KERNEL,
+						      order - MIN_CONTIG_ORDER);
+	if (!new_array)
+		return -ENOMEM;
+
+	spin_lock_irqsave(&xen_reservation_lock, flags);
+
+	old_order = discontig_frames_order;
+
+	if (order > discontig_frames_order || !discontig_frames_dyn) {
+		if (!discontig_frames_dyn)
+			old_array = NULL;
+		else
+			old_array = discontig_frames;
+
+		discontig_frames = new_array;
+		discontig_frames_order = order;
+		discontig_frames_dyn = true;
+	} else {
+		old_array = new_array;
+	}
+
+	spin_unlock_irqrestore(&xen_reservation_lock, flags);
+
+	free_pages((unsigned long)old_array, old_order - MIN_CONTIG_ORDER);
+
+	return 0;
+}
+
 /*
  * Note about cr3 (pagetable base) values:
  *
@@ -814,6 +859,9 @@ static void __init xen_after_bootmem(void)
 	SetPagePinned(virt_to_page(level3_user_vsyscall));
 #endif
 	xen_pgd_walk(&init_mm, xen_mark_pinned, FIXADDR_TOP);
+
+	if (alloc_discontig_frames(MIN_CONTIG_ORDER))
+		BUG();
 }
 
 static void xen_unpin_page(struct mm_struct *mm, struct page *page,
@@ -2203,10 +2251,6 @@ void __init xen_init_mmu_ops(void)
 	memset(dummy_mapping, 0xff, PAGE_SIZE);
 }
 
-/* Protected by xen_reservation_lock. */
-#define MAX_CONTIG_ORDER 9 /* 2MB */
-static unsigned long discontig_frames[1<<MAX_CONTIG_ORDER];
-
 #define VOID_PTE (mfn_pte(0, __pgprot(0)))
 static void xen_zap_pfn_range(unsigned long vaddr, unsigned int order,
 				unsigned long *in_frames,
@@ -2323,18 +2367,25 @@ int xen_create_contiguous_region(phys_addr_t pstart, unsigned int order,
 				 unsigned int address_bits,
 				 dma_addr_t *dma_handle)
 {
-	unsigned long *in_frames = discontig_frames, out_frame;
+	unsigned long *in_frames, out_frame;
 	unsigned long  flags;
 	int            success;
 	unsigned long vstart = (unsigned long)phys_to_virt(pstart);
 
-	if (unlikely(order > MAX_CONTIG_ORDER))
-		return -ENOMEM;
+	if (unlikely(order > discontig_frames_order)) {
+		if (!discontig_frames_dyn)
+			return -ENOMEM;
+
+		if (alloc_discontig_frames(order))
+			return -ENOMEM;
+	}
 
 	memset((void *) vstart, 0, PAGE_SIZE << order);
 
 	spin_lock_irqsave(&xen_reservation_lock, flags);
 
+	in_frames = discontig_frames;
+
 	/* 1. Zap current PTEs, remembering MFNs. */
 	xen_zap_pfn_range(vstart, order, in_frames, NULL);
 
@@ -2358,12 +2409,12 @@ int xen_create_contiguous_region(phys_addr_t pstart, unsigned int order,
 
 void xen_destroy_contiguous_region(phys_addr_t pstart, unsigned int order)
 {
-	unsigned long *out_frames = discontig_frames, in_frame;
+	unsigned long *out_frames, in_frame;
 	unsigned long  flags;
 	int success;
 	unsigned long vstart;
 
-	if (unlikely(order > MAX_CONTIG_ORDER))
+	if (unlikely(order > discontig_frames_order))
 		return;
 
 	vstart = (unsigned long)phys_to_virt(pstart);
@@ -2371,6 +2422,8 @@ void xen_destroy_contiguous_region(phys_addr_t pstart, unsigned int order)
 
 	spin_lock_irqsave(&xen_reservation_lock, flags);
 
+	out_frames = discontig_frames;
+
 	/* 1. Find start MFN of contiguous extent. */
 	in_frame = virt_to_mfn((void *)vstart);