Merge tag 'v6.6.18' of git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable into odroid-6.6.y

This is the 6.6.18 stable release Change-Id: Ia858c852fcc18cc41b5e2e99ce138f7c2d1ed2f3
2026-06-06 02:50:49 +09:00 · 2024-04-30 10:38:17 -03:00
parent e0e9afa736 d8a27ea2c9
commit d88ecb202f
329 changed files with 4092 additions and 3171 deletions
--- a/Documentation/ABI/testing/sysfs-class-net-statistics
+++ b/Documentation/ABI/testing/sysfs-class-net-statistics
@@ -1,4 +1,4 @@
-What:		/sys/class/<iface>/statistics/collisions
+What:		/sys/class/net/<iface>/statistics/collisions
 Date:		April 2005
 KernelVersion:	2.6.12
 Contact:	netdev@vger.kernel.org
@@ -6,7 +6,7 @@ Description:
 		Indicates the number of collisions seen by this network device.
 		This value might not be relevant with all MAC layers.

-What:		/sys/class/<iface>/statistics/multicast
+What:		/sys/class/net/<iface>/statistics/multicast
 Date:		April 2005
 KernelVersion:	2.6.12
 Contact:	netdev@vger.kernel.org
@@ -14,7 +14,7 @@ Description:
 		Indicates the number of multicast packets received by this
 		network device.

-What:		/sys/class/<iface>/statistics/rx_bytes
+What:		/sys/class/net/<iface>/statistics/rx_bytes
 Date:		April 2005
 KernelVersion:	2.6.12
 Contact:	netdev@vger.kernel.org
@@ -23,7 +23,7 @@ Description:
 		See the network driver for the exact meaning of when this
 		value is incremented.

-What:		/sys/class/<iface>/statistics/rx_compressed
+What:		/sys/class/net/<iface>/statistics/rx_compressed
 Date:		April 2005
 KernelVersion:	2.6.12
 Contact:	netdev@vger.kernel.org
@@ -32,7 +32,7 @@ Description:
 		network device. This value might only be relevant for interfaces
 		that support packet compression (e.g: PPP).

-What:		/sys/class/<iface>/statistics/rx_crc_errors
+What:		/sys/class/net/<iface>/statistics/rx_crc_errors
 Date:		April 2005
 KernelVersion:	2.6.12
 Contact:	netdev@vger.kernel.org
@@ -41,7 +41,7 @@ Description:
 		by this network device. Note that the specific meaning might
 		depend on the MAC layer used by the interface.

-What:		/sys/class/<iface>/statistics/rx_dropped
+What:		/sys/class/net/<iface>/statistics/rx_dropped
 Date:		April 2005
 KernelVersion:	2.6.12
 Contact:	netdev@vger.kernel.org
@@ -51,7 +51,7 @@ Description:
 		packet processing. See the network driver for the exact
 		meaning of this value.

-What:		/sys/class/<iface>/statistics/rx_errors
+What:		/sys/class/net/<iface>/statistics/rx_errors
 Date:		April 2005
 KernelVersion:	2.6.12
 Contact:	netdev@vger.kernel.org
@@ -59,7 +59,7 @@ Description:
 		Indicates the number of receive errors on this network device.
 		See the network driver for the exact meaning of this value.

-What:		/sys/class/<iface>/statistics/rx_fifo_errors
+What:		/sys/class/net/<iface>/statistics/rx_fifo_errors
 Date:		April 2005
 KernelVersion:	2.6.12
 Contact:	netdev@vger.kernel.org
@@ -68,7 +68,7 @@ Description:
 		network device. See the network driver for the exact
 		meaning of this value.

-What:		/sys/class/<iface>/statistics/rx_frame_errors
+What:		/sys/class/net/<iface>/statistics/rx_frame_errors
 Date:		April 2005
 KernelVersion:	2.6.12
 Contact:	netdev@vger.kernel.org
@@ -78,7 +78,7 @@ Description:
 		on the MAC layer protocol used. See the network driver for
 		the exact meaning of this value.

-What:		/sys/class/<iface>/statistics/rx_length_errors
+What:		/sys/class/net/<iface>/statistics/rx_length_errors
 Date:		April 2005
 KernelVersion:	2.6.12
 Contact:	netdev@vger.kernel.org
@@ -87,7 +87,7 @@ Description:
 		error, oversized or undersized. See the network driver for the
 		exact meaning of this value.

-What:		/sys/class/<iface>/statistics/rx_missed_errors
+What:		/sys/class/net/<iface>/statistics/rx_missed_errors
 Date:		April 2005
 KernelVersion:	2.6.12
 Contact:	netdev@vger.kernel.org
@@ -96,7 +96,7 @@ Description:
 		due to lack of capacity in the receive side. See the network
 		driver for the exact meaning of this value.

-What:		/sys/class/<iface>/statistics/rx_nohandler
+What:		/sys/class/net/<iface>/statistics/rx_nohandler
 Date:		February 2016
 KernelVersion:	4.6
 Contact:	netdev@vger.kernel.org
@@ -104,7 +104,7 @@ Description:
 		Indicates the number of received packets that were dropped on
 		an inactive device by the network core.

-What:		/sys/class/<iface>/statistics/rx_over_errors
+What:		/sys/class/net/<iface>/statistics/rx_over_errors
 Date:		April 2005
 KernelVersion:	2.6.12
 Contact:	netdev@vger.kernel.org
@@ -114,7 +114,7 @@ Description:
 		(e.g: larger than MTU). See the network driver for the exact
 		meaning of this value.

-What:		/sys/class/<iface>/statistics/rx_packets
+What:		/sys/class/net/<iface>/statistics/rx_packets
 Date:		April 2005
 KernelVersion:	2.6.12
 Contact:	netdev@vger.kernel.org
@@ -122,7 +122,7 @@ Description:
 		Indicates the total number of good packets received by this
 		network device.

-What:		/sys/class/<iface>/statistics/tx_aborted_errors
+What:		/sys/class/net/<iface>/statistics/tx_aborted_errors
 Date:		April 2005
 KernelVersion:	2.6.12
 Contact:	netdev@vger.kernel.org
@@ -132,7 +132,7 @@ Description:
 		a medium collision). See the network driver for the exact
 		meaning of this value.

-What:		/sys/class/<iface>/statistics/tx_bytes
+What:		/sys/class/net/<iface>/statistics/tx_bytes
 Date:		April 2005
 KernelVersion:	2.6.12
 Contact:	netdev@vger.kernel.org
@@ -143,7 +143,7 @@ Description:
 		transmitted packets or all packets that have been queued for
 		transmission.

-What:		/sys/class/<iface>/statistics/tx_carrier_errors
+What:		/sys/class/net/<iface>/statistics/tx_carrier_errors
 Date:		April 2005
 KernelVersion:	2.6.12
 Contact:	netdev@vger.kernel.org
@@ -152,7 +152,7 @@ Description:
 		because of carrier errors (e.g: physical link down). See the
 		network driver for the exact meaning of this value.

-What:		/sys/class/<iface>/statistics/tx_compressed
+What:		/sys/class/net/<iface>/statistics/tx_compressed
 Date:		April 2005
 KernelVersion:	2.6.12
 Contact:	netdev@vger.kernel.org
@@ -161,7 +161,7 @@ Description:
 		this might only be relevant for devices that support
 		compression (e.g: PPP).

-What:		/sys/class/<iface>/statistics/tx_dropped
+What:		/sys/class/net/<iface>/statistics/tx_dropped
 Date:		April 2005
 KernelVersion:	2.6.12
 Contact:	netdev@vger.kernel.org
@@ -170,7 +170,7 @@ Description:
 		See the driver for the exact reasons as to why the packets were
 		dropped.

-What:		/sys/class/<iface>/statistics/tx_errors
+What:		/sys/class/net/<iface>/statistics/tx_errors
 Date:		April 2005
 KernelVersion:	2.6.12
 Contact:	netdev@vger.kernel.org
@@ -179,7 +179,7 @@ Description:
 		a network device. See the driver for the exact reasons as to
 		why the packets were dropped.

-What:		/sys/class/<iface>/statistics/tx_fifo_errors
+What:		/sys/class/net/<iface>/statistics/tx_fifo_errors
 Date:		April 2005
 KernelVersion:	2.6.12
 Contact:	netdev@vger.kernel.org
@@ -188,7 +188,7 @@ Description:
 		FIFO error. See the driver for the exact reasons as to why the
 		packets were dropped.

-What:		/sys/class/<iface>/statistics/tx_heartbeat_errors
+What:		/sys/class/net/<iface>/statistics/tx_heartbeat_errors
 Date:		April 2005
 KernelVersion:	2.6.12
 Contact:	netdev@vger.kernel.org
@@ -197,7 +197,7 @@ Description:
 		reported as heartbeat errors. See the driver for the exact
 		reasons as to why the packets were dropped.

-What:		/sys/class/<iface>/statistics/tx_packets
+What:		/sys/class/net/<iface>/statistics/tx_packets
 Date:		April 2005
 KernelVersion:	2.6.12
 Contact:	netdev@vger.kernel.org
@@ -206,7 +206,7 @@ Description:
 		device. See the driver for whether this reports the number of all
 		attempted or successful transmissions.

-What:		/sys/class/<iface>/statistics/tx_window_errors
+What:		/sys/class/net/<iface>/statistics/tx_window_errors
 Date:		April 2005
 KernelVersion:	2.6.12
 Contact:	netdev@vger.kernel.org
--- a/Documentation/arch/arm64/silicon-errata.rst
+++ b/Documentation/arch/arm64/silicon-errata.rst
@@ -235,3 +235,10 @@ stable kernels.
 +----------------+-----------------+-----------------+-----------------------------+
 | ASR            | ASR8601         | #8601001        | N/A                         |
 +----------------+-----------------+-----------------+-----------------------------+
+----------------+-----------------+-----------------+-----------------------------+
+| Microsoft      | Azure Cobalt 100| #2139208        | ARM64_ERRATUM_2139208       |
+----------------+-----------------+-----------------+-----------------------------+
+| Microsoft      | Azure Cobalt 100| #2067961        | ARM64_ERRATUM_2067961       |
+----------------+-----------------+-----------------+-----------------------------+
+| Microsoft      | Azure Cobalt 100| #2253138        | ARM64_ERRATUM_2253138       |
+----------------+-----------------+-----------------+-----------------------------+
--- a/Documentation/arch/ia64/features.rst
+++ b/Documentation/arch/ia64/features.rst
@@ -1,3 +1,3 @@
 .. SPDX-License-Identifier: GPL-2.0

-.. kernel-feat:: $srctree/Documentation/features ia64
+.. kernel-feat:: features ia64
--- a/Documentation/networking/devlink/devlink-port.rst
+++ b/Documentation/networking/devlink/devlink-port.rst
@@ -126,7 +126,7 @@ Users may also set the RoCE capability of the function using
 `devlink port function set roce` command.

 Users may also set the function as migratable using
-'devlink port function set migratable' command.
+`devlink port function set migratable` command.

 Users may also set the IPsec crypto capability of the function using
 `devlink port function set ipsec_crypto` command.
--- a/Documentation/sphinx/kernel_feat.py
+++ b/Documentation/sphinx/kernel_feat.py
@@ -109,7 +109,7 @@ class KernelFeat(Directive):
            else:
                out_lines += line + "\n"

-        nodeList = self.nestedParse(out_lines, fname)
+        nodeList = self.nestedParse(out_lines, self.arguments[0])
        return nodeList

    def nestedParse(self, lines, fname):
--- a/2
+++ b/2
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 VERSION = 6
 PATCHLEVEL = 6
-SUBLEVEL = 17
+SUBLEVEL = 18
 EXTRAVERSION =
 NAME = Hurr durr I'ma ninja sloth

--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -681,6 +681,7 @@ config SHADOW_CALL_STACK
 	bool "Shadow Call Stack"
 	depends on ARCH_SUPPORTS_SHADOW_CALL_STACK
 	depends on DYNAMIC_FTRACE_WITH_ARGS || DYNAMIC_FTRACE_WITH_REGS || !FUNCTION_GRAPH_TRACER
+	depends on MMU
 	help
 	  This option enables the compiler's Shadow Call Stack, which
 	  uses a shadow stack to protect function return addresses from
--- a/arch/arc/include/asm/jump_label.h
+++ b/arch/arc/include/asm/jump_label.h
@@ -31,7 +31,7 @@
 static __always_inline bool arch_static_branch(struct static_key *key,
 					       bool branch)
 {
-	asm_volatile_goto(".balign "__stringify(JUMP_LABEL_NOP_SIZE)"	\n"
+	asm goto(".balign "__stringify(JUMP_LABEL_NOP_SIZE)"		\n"
 		 "1:							\n"
 		 "nop							\n"
 		 ".pushsection __jump_table, \"aw\"			\n"
@@ -47,7 +47,7 @@ l_yes:
 static __always_inline bool arch_static_branch_jump(struct static_key *key,
 						    bool branch)
 {
-	asm_volatile_goto(".balign "__stringify(JUMP_LABEL_NOP_SIZE)"	\n"
+	asm goto(".balign "__stringify(JUMP_LABEL_NOP_SIZE)"		\n"
 		 "1:							\n"
 		 "b %l[l_yes]						\n"
 		 ".pushsection __jump_table, \"aw\"			\n"
--- a/arch/arm/include/asm/jump_label.h
+++ b/arch/arm/include/asm/jump_label.h
@@ -11,7 +11,7 @@

 static __always_inline bool arch_static_branch(struct static_key *key, bool branch)
 {
-	asm_volatile_goto("1:\n\t"
+	asm goto("1:\n\t"
 		 WASM(nop) "\n\t"
 		 ".pushsection __jump_table,  \"aw\"\n\t"
 		 ".word 1b, %l[l_yes], %c0\n\t"
@@ -25,7 +25,7 @@ l_yes:

 static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch)
 {
-	asm_volatile_goto("1:\n\t"
+	asm goto("1:\n\t"
 		 WASM(b) " %l[l_yes]\n\t"
 		 ".pushsection __jump_table,  \"aw\"\n\t"
 		 ".word 1b, %l[l_yes], %c0\n\t"
--- a/arch/arm64/include/asm/alternative-macros.h
+++ b/arch/arm64/include/asm/alternative-macros.h
@@ -229,7 +229,7 @@ alternative_has_cap_likely(const unsigned long cpucap)
 	compiletime_assert(cpucap < ARM64_NCAPS,
 			   "cpucap must be < ARM64_NCAPS");

-	asm_volatile_goto(
+	asm goto(
 	ALTERNATIVE_CB("b	%l[l_no]", %[cpucap], alt_cb_patch_nops)
 	:
 	: [cpucap] "i" (cpucap)
@@ -247,7 +247,7 @@ alternative_has_cap_unlikely(const unsigned long cpucap)
 	compiletime_assert(cpucap < ARM64_NCAPS,
 			   "cpucap must be < ARM64_NCAPS");

-	asm_volatile_goto(
+	asm goto(
 	ALTERNATIVE("nop", "b	%l[l_yes]", %[cpucap])
 	:
 	: [cpucap] "i" (cpucap)
--- a/arch/arm64/include/asm/cputype.h
+++ b/arch/arm64/include/asm/cputype.h
@@ -61,6 +61,7 @@
 #define ARM_CPU_IMP_HISI		0x48
 #define ARM_CPU_IMP_APPLE		0x61
 #define ARM_CPU_IMP_AMPERE		0xC0
+#define ARM_CPU_IMP_MICROSOFT		0x6D

 #define ARM_CPU_PART_AEM_V8		0xD0F
 #define ARM_CPU_PART_FOUNDATION		0xD00
@@ -135,6 +136,8 @@

 #define AMPERE_CPU_PART_AMPERE1		0xAC3

+#define MICROSOFT_CPU_PART_AZURE_COBALT_100	0xD49 /* Based on r0p0 of ARM Neoverse N2 */
+
 #define MIDR_CORTEX_A53 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A53)
 #define MIDR_CORTEX_A57 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A57)
 #define MIDR_CORTEX_A72 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A72)
@@ -193,6 +196,7 @@
 #define MIDR_APPLE_M2_BLIZZARD_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_BLIZZARD_MAX)
 #define MIDR_APPLE_M2_AVALANCHE_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_AVALANCHE_MAX)
 #define MIDR_AMPERE1 MIDR_CPU_MODEL(ARM_CPU_IMP_AMPERE, AMPERE_CPU_PART_AMPERE1)
+#define MIDR_MICROSOFT_AZURE_COBALT_100 MIDR_CPU_MODEL(ARM_CPU_IMP_MICROSOFT, MICROSOFT_CPU_PART_AZURE_COBALT_100)

 /* Fujitsu Erratum 010001 affects A64FX 1.0 and 1.1, (v0r0 and v1r0) */
 #define MIDR_FUJITSU_ERRATUM_010001		MIDR_FUJITSU_A64FX
--- a/arch/arm64/include/asm/jump_label.h
+++ b/arch/arm64/include/asm/jump_label.h
@@ -18,7 +18,7 @@
 static __always_inline bool arch_static_branch(struct static_key * const key,
 					       const bool branch)
 {
-	asm_volatile_goto(
+	asm goto(
 		"1:	nop					\n\t"
 		 "	.pushsection	__jump_table, \"aw\"	\n\t"
 		 "	.align		3			\n\t"
@@ -35,7 +35,7 @@ l_yes:
 static __always_inline bool arch_static_branch_jump(struct static_key * const key,
 						    const bool branch)
 {
-	asm_volatile_goto(
+	asm goto(
 		"1:	b		%l[l_yes]		\n\t"
 		 "	.pushsection	__jump_table, \"aw\"	\n\t"
 		 "	.align		3			\n\t"
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -390,6 +390,7 @@ static const struct midr_range erratum_1463225[] = {
 static const struct midr_range trbe_overwrite_fill_mode_cpus[] = {
 #ifdef CONFIG_ARM64_ERRATUM_2139208
 	MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N2),
+	MIDR_ALL_VERSIONS(MIDR_MICROSOFT_AZURE_COBALT_100),
 #endif
 #ifdef CONFIG_ARM64_ERRATUM_2119858
 	MIDR_ALL_VERSIONS(MIDR_CORTEX_A710),
@@ -403,6 +404,7 @@ static const struct midr_range trbe_overwrite_fill_mode_cpus[] = {
 static const struct midr_range tsb_flush_fail_cpus[] = {
 #ifdef CONFIG_ARM64_ERRATUM_2067961
 	MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N2),
+	MIDR_ALL_VERSIONS(MIDR_MICROSOFT_AZURE_COBALT_100),
 #endif
 #ifdef CONFIG_ARM64_ERRATUM_2054223
 	MIDR_ALL_VERSIONS(MIDR_CORTEX_A710),
@@ -415,6 +417,7 @@ static const struct midr_range tsb_flush_fail_cpus[] = {
 static struct midr_range trbe_write_out_of_range_cpus[] = {
 #ifdef CONFIG_ARM64_ERRATUM_2253138
 	MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N2),
+	MIDR_ALL_VERSIONS(MIDR_MICROSOFT_AZURE_COBALT_100),
 #endif
 #ifdef CONFIG_ARM64_ERRATUM_2224489
 	MIDR_ALL_VERSIONS(MIDR_CORTEX_A710),
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -1686,7 +1686,7 @@ void fpsimd_preserve_current_state(void)
 void fpsimd_signal_preserve_current_state(void)
 {
 	fpsimd_preserve_current_state();
-	if (test_thread_flag(TIF_SVE))
+	if (current->thread.fp_type == FP_STATE_SVE)
 		sve_to_fpsimd(current);
 }

--- a/arch/arm64/kernel/signal.c
+++ b/arch/arm64/kernel/signal.c
@@ -242,7 +242,7 @@ static int preserve_sve_context(struct sve_context __user *ctx)
 		vl = task_get_sme_vl(current);
 		vq = sve_vq_from_vl(vl);
 		flags |= SVE_SIG_FLAG_SM;
-	} else if (test_thread_flag(TIF_SVE)) {
+	} else if (current->thread.fp_type == FP_STATE_SVE) {
 		vq = sve_vq_from_vl(vl);
 	}

@@ -878,7 +878,7 @@ static int setup_sigframe_layout(struct rt_sigframe_user_layout *user,
 	if (system_supports_sve() || system_supports_sme()) {
 		unsigned int vq = 0;

-		if (add_all || test_thread_flag(TIF_SVE) ||
+		if (add_all || current->thread.fp_type == FP_STATE_SVE ||
 		    thread_sm_enabled(&current->thread)) {
 			int vl = max(sve_max_vl(), sme_max_vl());

--- a/arch/arm64/kvm/pkvm.c
+++ b/arch/arm64/kvm/pkvm.c
@@ -101,6 +101,17 @@ void __init kvm_hyp_reserve(void)
 		 hyp_mem_base);
 }

+static void __pkvm_destroy_hyp_vm(struct kvm *host_kvm)
+{
+	if (host_kvm->arch.pkvm.handle) {
+		WARN_ON(kvm_call_hyp_nvhe(__pkvm_teardown_vm,
+					  host_kvm->arch.pkvm.handle));
+	}
+
+	host_kvm->arch.pkvm.handle = 0;
+	free_hyp_memcache(&host_kvm->arch.pkvm.teardown_mc);
+}
+
 /*
 * Allocates and donates memory for hypervisor VM structs at EL2.
 *
@@ -181,7 +192,7 @@ static int __pkvm_create_hyp_vm(struct kvm *host_kvm)
 	return 0;

 destroy_vm:
-	pkvm_destroy_hyp_vm(host_kvm);
+	__pkvm_destroy_hyp_vm(host_kvm);
 	return ret;
 free_vm:
 	free_pages_exact(hyp_vm, hyp_vm_sz);
@@ -194,23 +205,19 @@ int pkvm_create_hyp_vm(struct kvm *host_kvm)
 {
 	int ret = 0;

-	mutex_lock(&host_kvm->lock);
+	mutex_lock(&host_kvm->arch.config_lock);
 	if (!host_kvm->arch.pkvm.handle)
 		ret = __pkvm_create_hyp_vm(host_kvm);
-	mutex_unlock(&host_kvm->lock);
+	mutex_unlock(&host_kvm->arch.config_lock);

 	return ret;
 }

 void pkvm_destroy_hyp_vm(struct kvm *host_kvm)
 {
-	if (host_kvm->arch.pkvm.handle) {
-		WARN_ON(kvm_call_hyp_nvhe(__pkvm_teardown_vm,
-					  host_kvm->arch.pkvm.handle));
-	}
-
-	host_kvm->arch.pkvm.handle = 0;
-	free_hyp_memcache(&host_kvm->arch.pkvm.teardown_mc);
+	mutex_lock(&host_kvm->arch.config_lock);
+	__pkvm_destroy_hyp_vm(host_kvm);
+	mutex_unlock(&host_kvm->arch.config_lock);
 }

 int pkvm_init_host_vm(struct kvm *host_kvm)
--- a/arch/csky/include/asm/jump_label.h
+++ b/arch/csky/include/asm/jump_label.h
@@ -12,7 +12,7 @@
 static __always_inline bool arch_static_branch(struct static_key *key,
 					       bool branch)
 {
-	asm_volatile_goto(
+	asm goto(
 		"1:	nop32					\n"
 		"	.pushsection	__jump_table, \"aw\"	\n"
 		"	.align		2			\n"
@@ -29,7 +29,7 @@ label:
 static __always_inline bool arch_static_branch_jump(struct static_key *key,
 						    bool branch)
 {
-	asm_volatile_goto(
+	asm goto(
 		"1:	bsr32		%l[label]		\n"
 		"	.pushsection	__jump_table, \"aw\"	\n"
 		"	.align		2			\n"
--- a/arch/loongarch/include/asm/jump_label.h
+++ b/arch/loongarch/include/asm/jump_label.h
@@ -22,7 +22,7 @@

 static __always_inline bool arch_static_branch(struct static_key * const key, const bool branch)
 {
-	asm_volatile_goto(
+	asm goto(
 		"1:	nop			\n\t"
 		JUMP_TABLE_ENTRY
 		:  :  "i"(&((char *)key)[branch]) :  : l_yes);
@@ -35,7 +35,7 @@ l_yes:

 static __always_inline bool arch_static_branch_jump(struct static_key * const key, const bool branch)
 {
-	asm_volatile_goto(
+	asm goto(
 		"1:	b	%l[l_yes]	\n\t"
 		JUMP_TABLE_ENTRY
 		:  :  "i"(&((char *)key)[branch]) :  : l_yes);
--- a/arch/loongarch/mm/kasan_init.c
+++ b/arch/loongarch/mm/kasan_init.c
@@ -44,6 +44,9 @@ void *kasan_mem_to_shadow(const void *addr)
 		unsigned long xrange = (maddr >> XRANGE_SHIFT) & 0xffff;
 		unsigned long offset = 0;

+		if (maddr >= FIXADDR_START)
+			return (void *)(kasan_early_shadow_page);
+
 		maddr &= XRANGE_SHADOW_MASK;
 		switch (xrange) {
 		case XKPRANGE_CC_SEG:
--- a/arch/mips/include/asm/checksum.h
+++ b/arch/mips/include/asm/checksum.h
@@ -241,7 +241,8 @@ static __inline__ __sum16 csum_ipv6_magic(const struct in6_addr *saddr,
 	"	.set	pop"
 	: "=&r" (sum), "=&r" (tmp)
 	: "r" (saddr), "r" (daddr),
-	  "0" (htonl(len)), "r" (htonl(proto)), "r" (sum));
+	  "0" (htonl(len)), "r" (htonl(proto)), "r" (sum)
+	: "memory");

 	return csum_fold(sum);
 }
--- a/arch/mips/include/asm/jump_label.h
+++ b/arch/mips/include/asm/jump_label.h
@@ -36,7 +36,7 @@

 static __always_inline bool arch_static_branch(struct static_key *key, bool branch)
 {
-	asm_volatile_goto("1:\t" B_INSN " 2f\n\t"
+	asm goto("1:\t" B_INSN " 2f\n\t"
 		"2:\t.insn\n\t"
 		".pushsection __jump_table,  \"aw\"\n\t"
 		WORD_INSN " 1b, %l[l_yes], %0\n\t"
@@ -50,7 +50,7 @@ l_yes:

 static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch)
 {
-	asm_volatile_goto("1:\t" J_INSN " %l[l_yes]\n\t"
+	asm goto("1:\t" J_INSN " %l[l_yes]\n\t"
 		".pushsection __jump_table,  \"aw\"\n\t"
 		WORD_INSN " 1b, %l[l_yes], %0\n\t"
 		".popsection\n\t"
--- a/arch/mips/include/asm/ptrace.h
+++ b/arch/mips/include/asm/ptrace.h
@@ -154,6 +154,8 @@ static inline long regs_return_value(struct pt_regs *regs)
 }

 #define instruction_pointer(regs) ((regs)->cp0_epc)
+extern unsigned long exception_ip(struct pt_regs *regs);
+#define exception_ip(regs) exception_ip(regs)
 #define profile_pc(regs) instruction_pointer(regs)

 extern asmlinkage long syscall_trace_enter(struct pt_regs *regs, long syscall);
--- a/arch/mips/kernel/ptrace.c
+++ b/arch/mips/kernel/ptrace.c
@@ -31,6 +31,7 @@
 #include <linux/seccomp.h>
 #include <linux/ftrace.h>

+#include <asm/branch.h>
 #include <asm/byteorder.h>
 #include <asm/cpu.h>
 #include <asm/cpu-info.h>
@@ -48,6 +49,12 @@
 #define CREATE_TRACE_POINTS
 #include <trace/events/syscalls.h>

+unsigned long exception_ip(struct pt_regs *regs)
+{
+	return exception_epc(regs);
+}
+EXPORT_SYMBOL(exception_ip);
+
 /*
 * Called by kernel/ptrace.c when detaching..
 *
--- a/arch/parisc/Kconfig
+++ b/arch/parisc/Kconfig
@@ -24,7 +24,6 @@ config PARISC
 	select RTC_DRV_GENERIC
 	select INIT_ALL_POSSIBLE
 	select BUG
-	select BUILDTIME_TABLE_SORT
 	select HAVE_PCI
 	select HAVE_PERF_EVENTS
 	select HAVE_KERNEL_BZIP2
--- a/arch/parisc/include/asm/assembly.h
+++ b/arch/parisc/include/asm/assembly.h
@@ -576,6 +576,7 @@
 	.section __ex_table,"aw"			!	\
 	.align 4					!	\
 	.word (fault_addr - .), (except_addr - .)	!	\
+	or %r0,%r0,%r0					!	\
 	.previous


--- a/arch/parisc/include/asm/extable.h
+++ b/arch/parisc/include/asm/extable.h
@@ -0,0 +1,64 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __PARISC_EXTABLE_H
+#define __PARISC_EXTABLE_H
+
+#include <asm/ptrace.h>
+#include <linux/compiler.h>
+
+/*
+ * The exception table consists of three addresses:
+ *
+ * - A relative address to the instruction that is allowed to fault.
+ * - A relative address at which the program should continue (fixup routine)
+ * - An asm statement which specifies which CPU register will
+ *   receive -EFAULT when an exception happens if the lowest bit in
+ *   the fixup address is set.
+ *
+ * Note: The register specified in the err_opcode instruction will be
+ * modified at runtime if a fault happens. Register %r0 will be ignored.
+ *
+ * Since relative addresses are used, 32bit values are sufficient even on
+ * 64bit kernel.
+ */
+
+struct pt_regs;
+int fixup_exception(struct pt_regs *regs);
+
+#define ARCH_HAS_RELATIVE_EXTABLE
+struct exception_table_entry {
+	int insn;	/* relative address of insn that is allowed to fault. */
+	int fixup;	/* relative address of fixup routine */
+	int err_opcode; /* sample opcode with register which holds error code */
+};
+
+#define ASM_EXCEPTIONTABLE_ENTRY( fault_addr, except_addr, opcode )\
+	".section __ex_table,\"aw\"\n"			   \
+	".align 4\n"					   \
+	".word (" #fault_addr " - .), (" #except_addr " - .)\n" \
+	opcode "\n"					   \
+	".previous\n"
+
+/*
+ * ASM_EXCEPTIONTABLE_ENTRY_EFAULT() creates a special exception table entry
+ * (with lowest bit set) for which the fault handler in fixup_exception() will
+ * load -EFAULT on fault into the register specified by the err_opcode instruction,
+ * and zeroes the target register in case of a read fault in get_user().
+ */
+#define ASM_EXCEPTIONTABLE_VAR(__err_var)		\
+	int __err_var = 0
+#define ASM_EXCEPTIONTABLE_ENTRY_EFAULT( fault_addr, except_addr, register )\
+	ASM_EXCEPTIONTABLE_ENTRY( fault_addr, except_addr + 1, "or %%r0,%%r0," register)
+
+static inline void swap_ex_entry_fixup(struct exception_table_entry *a,
+				       struct exception_table_entry *b,
+				       struct exception_table_entry tmp,
+				       int delta)
+{
+	a->fixup = b->fixup + delta;
+	b->fixup = tmp.fixup - delta;
+	a->err_opcode = b->err_opcode;
+	b->err_opcode = tmp.err_opcode;
+}
+#define swap_ex_entry_fixup swap_ex_entry_fixup
+
+#endif
--- a/arch/parisc/include/asm/jump_label.h
+++ b/arch/parisc/include/asm/jump_label.h
@@ -12,7 +12,7 @@

 static __always_inline bool arch_static_branch(struct static_key *key, bool branch)
 {
-	asm_volatile_goto("1:\n\t"
+	asm goto("1:\n\t"
 		 "nop\n\t"
 		 ".pushsection __jump_table,  \"aw\"\n\t"
 		 ".align %1\n\t"
@@ -29,7 +29,7 @@ l_yes:

 static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch)
 {
-	asm_volatile_goto("1:\n\t"
+	asm goto("1:\n\t"
 		 "b,n %l[l_yes]\n\t"
 		 ".pushsection __jump_table,  \"aw\"\n\t"
 		 ".align %1\n\t"
--- a/arch/parisc/include/asm/special_insns.h
+++ b/arch/parisc/include/asm/special_insns.h
@@ -8,7 +8,8 @@
 		"copy %%r0,%0\n"			\
 		"8:\tlpa %%r0(%1),%0\n"			\
 		"9:\n"					\
-		ASM_EXCEPTIONTABLE_ENTRY(8b, 9b)	\
+		ASM_EXCEPTIONTABLE_ENTRY(8b, 9b,	\
+				"or %%r0,%%r0,%%r0")	\
 		: "=&r" (pa)				\
 		: "r" (va)				\
 		: "memory"				\
@@ -22,7 +23,8 @@
 		"copy %%r0,%0\n"			\
 		"8:\tlpa %%r0(%%sr3,%1),%0\n"		\
 		"9:\n"					\
-		ASM_EXCEPTIONTABLE_ENTRY(8b, 9b)	\
+		ASM_EXCEPTIONTABLE_ENTRY(8b, 9b,	\
+				"or %%r0,%%r0,%%r0")	\
 		: "=&r" (pa)				\
 		: "r" (va)				\
 		: "memory"				\
--- a/arch/parisc/include/asm/uaccess.h
+++ b/arch/parisc/include/asm/uaccess.h
@@ -7,6 +7,7 @@
 */
 #include <asm/page.h>
 #include <asm/cache.h>
+#include <asm/extable.h>

 #include <linux/bug.h>
 #include <linux/string.h>
@@ -26,37 +27,6 @@
 #define STD_USER(sr, x, ptr)	__put_user_asm(sr, "std", x, ptr)
 #endif

-/*
- * The exception table contains two values: the first is the relative offset to
- * the address of the instruction that is allowed to fault, and the second is
- * the relative offset to the address of the fixup routine. Since relative
- * addresses are used, 32bit values are sufficient even on 64bit kernel.
- */
-
-#define ARCH_HAS_RELATIVE_EXTABLE
-struct exception_table_entry {
-	int insn;	/* relative address of insn that is allowed to fault. */
-	int fixup;	/* relative address of fixup routine */
-};
-
-#define ASM_EXCEPTIONTABLE_ENTRY( fault_addr, except_addr )\
-	".section __ex_table,\"aw\"\n"			   \
-	".align 4\n"					   \
-	".word (" #fault_addr " - .), (" #except_addr " - .)\n\t" \
-	".previous\n"
-
-/*
- * ASM_EXCEPTIONTABLE_ENTRY_EFAULT() creates a special exception table entry
- * (with lowest bit set) for which the fault handler in fixup_exception() will
- * load -EFAULT into %r29 for a read or write fault, and zeroes the target
- * register in case of a read fault in get_user().
- */
-#define ASM_EXCEPTIONTABLE_REG	29
-#define ASM_EXCEPTIONTABLE_VAR(__variable)		\
-	register long __variable __asm__ ("r29") = 0
-#define ASM_EXCEPTIONTABLE_ENTRY_EFAULT( fault_addr, except_addr )\
-	ASM_EXCEPTIONTABLE_ENTRY( fault_addr, except_addr + 1)
-
 #define __get_user_internal(sr, val, ptr)		\
 ({							\
 	ASM_EXCEPTIONTABLE_VAR(__gu_err);		\
@@ -83,7 +53,7 @@ struct exception_table_entry {
 							\
 	__asm__("1: " ldx " 0(%%sr%2,%3),%0\n"		\
 		"9:\n"					\
-		ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 9b)	\
+		ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 9b, "%1")	\
 		: "=r"(__gu_val), "+r"(__gu_err)        \
 		: "i"(sr), "r"(ptr));			\
 							\
@@ -115,8 +85,8 @@ struct exception_table_entry {
 		"1: ldw 0(%%sr%2,%3),%0\n"		\
 		"2: ldw 4(%%sr%2,%3),%R0\n"		\
 		"9:\n"					\
-		ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 9b)	\
-		ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 9b)	\
+		ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 9b, "%1")	\
+		ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 9b, "%1")	\
 		: "=&r"(__gu_tmp.l), "+r"(__gu_err)	\
 		: "i"(sr), "r"(ptr));			\
 							\
@@ -174,7 +144,7 @@ struct exception_table_entry {
 	__asm__ __volatile__ (					\
 		"1: " stx " %1,0(%%sr%2,%3)\n"			\
 		"9:\n"						\
-		ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 9b)		\
+		ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 9b, "%0")	\
 		: "+r"(__pu_err)				\
 		: "r"(x), "i"(sr), "r"(ptr))

@@ -186,15 +156,14 @@ struct exception_table_entry {
 		"1: stw %1,0(%%sr%2,%3)\n"			\
 		"2: stw %R1,4(%%sr%2,%3)\n"			\
 		"9:\n"						\
-		ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 9b)		\
-		ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 9b)		\
+		ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 9b, "%0")	\
+		ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 9b, "%0")	\
 		: "+r"(__pu_err)				\
 		: "r"(__val), "i"(sr), "r"(ptr));		\
 } while (0)

 #endif /* !defined(CONFIG_64BIT) */

-
 /*
 * Complex access routines -- external declarations
 */
@@ -216,7 +185,4 @@ unsigned long __must_check raw_copy_from_user(void *dst, const void __user *src,
 #define INLINE_COPY_TO_USER
 #define INLINE_COPY_FROM_USER

-struct pt_regs;
-int fixup_exception(struct pt_regs *regs);
-
 #endif /* __PARISC_UACCESS_H */
--- a/arch/parisc/kernel/cache.c
+++ b/arch/parisc/kernel/cache.c
@@ -58,7 +58,7 @@ int pa_serialize_tlb_flushes __ro_after_init;

 struct pdc_cache_info cache_info __ro_after_init;
 #ifndef CONFIG_PA20
-struct pdc_btlb_info btlb_info __ro_after_init;
+struct pdc_btlb_info btlb_info;
 #endif

 DEFINE_STATIC_KEY_TRUE(parisc_has_cache);
@@ -850,7 +850,7 @@ SYSCALL_DEFINE3(cacheflush, unsigned long, addr, unsigned long, bytes,
 #endif
 			"   fic,m	%3(%4,%0)\n"
 			"2: sync\n"
-			ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 2b)
+			ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 2b, "%1")
 			: "+r" (start), "+r" (error)
 			: "r" (end), "r" (dcache_stride), "i" (SR_USER));
 	}
@@ -865,7 +865,7 @@ SYSCALL_DEFINE3(cacheflush, unsigned long, addr, unsigned long, bytes,
 #endif
 			"   fdc,m	%3(%4,%0)\n"
 			"2: sync\n"
-			ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 2b)
+			ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 2b, "%1")
 			: "+r" (start), "+r" (error)
 			: "r" (end), "r" (icache_stride), "i" (SR_USER));
 	}
--- a/arch/parisc/kernel/drivers.c
+++ b/arch/parisc/kernel/drivers.c
@@ -1004,6 +1004,9 @@ static __init int qemu_print_iodc_data(struct device *lin_dev, void *data)

 	pr_info("\n");

+	/* Prevent hung task messages when printing on serial console */
+	cond_resched();
+
 	pr_info("#define HPA_%08lx_DESCRIPTION \"%s\"\n",
 		hpa, parisc_hardware_description(&dev->id));

--- a/arch/parisc/kernel/unaligned.c
+++ b/arch/parisc/kernel/unaligned.c
@@ -120,8 +120,8 @@ static int emulate_ldh(struct pt_regs *regs, int toreg)
 "2:	ldbs	1(%%sr1,%3), %0\n"
 "	depw	%2, 23, 24, %0\n"
 "3:	\n"
-	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 3b)
-	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 3b)
+	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 3b, "%1")
+	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 3b, "%1")
 	: "+r" (val), "+r" (ret), "=&r" (temp1)
 	: "r" (saddr), "r" (regs->isr) );

@@ -152,8 +152,8 @@ static int emulate_ldw(struct pt_regs *regs, int toreg, int flop)
 "	mtctl	%2,11\n"
 "	vshd	%0,%3,%0\n"
 "3:	\n"
-	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 3b)
-	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 3b)
+	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 3b, "%1")
+	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 3b, "%1")
 	: "+r" (val), "+r" (ret), "=&r" (temp1), "=&r" (temp2)
 	: "r" (saddr), "r" (regs->isr) );

@@ -189,8 +189,8 @@ static int emulate_ldd(struct pt_regs *regs, int toreg, int flop)
 "	mtsar	%%r19\n"
 "	shrpd	%0,%%r20,%%sar,%0\n"
 "3:	\n"
-	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 3b)
-	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 3b)
+	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 3b, "%1")
+	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 3b, "%1")
 	: "=r" (val), "+r" (ret)
 	: "0" (val), "r" (saddr), "r" (regs->isr)
 	: "r19", "r20" );
@@ -209,9 +209,9 @@ static int emulate_ldd(struct pt_regs *regs, int toreg, int flop)
 "	vshd	%0,%R0,%0\n"
 "	vshd	%R0,%4,%R0\n"
 "4:	\n"
-	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 4b)
-	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 4b)
-	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(3b, 4b)
+	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 4b, "%1")
+	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 4b, "%1")
+	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(3b, 4b, "%1")
 	: "+r" (val), "+r" (ret), "+r" (saddr), "=&r" (shift), "=&r" (temp1)
 	: "r" (regs->isr) );
    }
@@ -244,8 +244,8 @@ static int emulate_sth(struct pt_regs *regs, int frreg)
 "1:	stb %1, 0(%%sr1, %3)\n"
 "2:	stb %2, 1(%%sr1, %3)\n"
 "3:	\n"
-	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 3b)
-	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 3b)
+	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 3b, "%0")
+	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 3b, "%0")
 	: "+r" (ret), "=&r" (temp1)
 	: "r" (val), "r" (regs->ior), "r" (regs->isr) );

@@ -285,8 +285,8 @@ static int emulate_stw(struct pt_regs *regs, int frreg, int flop)
 "	stw	%%r20,0(%%sr1,%2)\n"
 "	stw	%%r21,4(%%sr1,%2)\n"
 "3:	\n"
-	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 3b)
-	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 3b)
+	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 3b, "%0")
+	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 3b, "%0")
 	: "+r" (ret)
 	: "r" (val), "r" (regs->ior), "r" (regs->isr)
 	: "r19", "r20", "r21", "r22", "r1" );
@@ -329,10 +329,10 @@ static int emulate_std(struct pt_regs *regs, int frreg, int flop)
 "3:	std	%%r20,0(%%sr1,%2)\n"
 "4:	std	%%r21,8(%%sr1,%2)\n"
 "5:	\n"
-	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 5b)
-	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 5b)
-	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(3b, 5b)
-	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(4b, 5b)
+	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 5b, "%0")
+	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 5b, "%0")
+	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(3b, 5b, "%0")
+	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(4b, 5b, "%0")
 	: "+r" (ret)
 	: "r" (val), "r" (regs->ior), "r" (regs->isr)
 	: "r19", "r20", "r21", "r22", "r1" );
@@ -357,11 +357,11 @@ static int emulate_std(struct pt_regs *regs, int frreg, int flop)
 "4:	stw	%%r1,4(%%sr1,%2)\n"
 "5:	stw	%R1,8(%%sr1,%2)\n"
 "6:	\n"
-	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 6b)
-	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 6b)
-	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(3b, 6b)
-	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(4b, 6b)
-	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(5b, 6b)
+	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 6b, "%0")
+	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 6b, "%0")
+	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(3b, 6b, "%0")
+	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(4b, 6b, "%0")
+	ASM_EXCEPTIONTABLE_ENTRY_EFAULT(5b, 6b, "%0")
 	: "+r" (ret)
 	: "r" (val), "r" (regs->ior), "r" (regs->isr)
 	: "r19", "r20", "r21", "r1" );
--- a/arch/parisc/mm/fault.c
+++ b/arch/parisc/mm/fault.c
@@ -150,11 +150,16 @@ int fixup_exception(struct pt_regs *regs)
 		 * Fix up get_user() and put_user().
 		 * ASM_EXCEPTIONTABLE_ENTRY_EFAULT() sets the least-significant
 		 * bit in the relative address of the fixup routine to indicate
-		 * that gr[ASM_EXCEPTIONTABLE_REG] should be loaded with
-		 * -EFAULT to report a userspace access error.
+		 * that the register encoded in the "or %r0,%r0,register"
+		 * opcode should be loaded with -EFAULT to report a userspace
+		 * access error.
 		 */
 		if (fix->fixup & 1) {
-			regs->gr[ASM_EXCEPTIONTABLE_REG] = -EFAULT;
+			int fault_error_reg = fix->err_opcode & 0x1f;
+			if (!WARN_ON(!fault_error_reg))
+				regs->gr[fault_error_reg] = -EFAULT;
+			pr_debug("Unalignment fixup of register %d at %pS\n",
+				fault_error_reg, (void*)regs->iaoq[0]);

 			/* zero target register for get_user() */
 			if (parisc_acctyp(0, regs->iir) == VM_READ) {
--- a/arch/powerpc/include/asm/jump_label.h
+++ b/arch/powerpc/include/asm/jump_label.h
@@ -17,7 +17,7 @@

 static __always_inline bool arch_static_branch(struct static_key *key, bool branch)
 {
-	asm_volatile_goto("1:\n\t"
+	asm goto("1:\n\t"
 		 "nop # arch_static_branch\n\t"
 		 ".pushsection __jump_table,  \"aw\"\n\t"
 		 ".long 1b - ., %l[l_yes] - .\n\t"
@@ -32,7 +32,7 @@ l_yes:

 static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch)
 {
-	asm_volatile_goto("1:\n\t"
+	asm goto("1:\n\t"
 		 "b %l[l_yes] # arch_static_branch_jump\n\t"
 		 ".pushsection __jump_table,  \"aw\"\n\t"
 		 ".long 1b - ., %l[l_yes] - .\n\t"
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -617,6 +617,8 @@
 #endif
 #define SPRN_HID2	0x3F8		/* Hardware Implementation Register 2 */
 #define SPRN_HID2_GEKKO	0x398		/* Gekko HID2 Register */
+#define SPRN_HID2_G2_LE	0x3F3		/* G2_LE HID2 Register */
+#define  HID2_G2_LE_HBE	(1<<18)		/* High BAT Enable (G2_LE) */
 #define SPRN_IABR	0x3F2	/* Instruction Address Breakpoint Register */
 #define SPRN_IABR2	0x3FA		/* 83xx */
 #define SPRN_IBCR	0x135		/* 83xx Insn Breakpoint Control Reg */
--- a/arch/powerpc/include/asm/thread_info.h
+++ b/arch/powerpc/include/asm/thread_info.h
@@ -14,7 +14,7 @@

 #ifdef __KERNEL__

-#ifdef CONFIG_KASAN
+#if defined(CONFIG_KASAN) && CONFIG_THREAD_SHIFT < 15
 #define MIN_THREAD_SHIFT	(CONFIG_THREAD_SHIFT + 1)
 #else
 #define MIN_THREAD_SHIFT	CONFIG_THREAD_SHIFT
--- a/arch/powerpc/include/asm/uaccess.h
+++ b/arch/powerpc/include/asm/uaccess.h
@@ -74,7 +74,7 @@ __pu_failed:							\
 /* -mprefixed can generate offsets beyond range, fall back hack */
 #ifdef CONFIG_PPC_KERNEL_PREFIXED
 #define __put_user_asm_goto(x, addr, label, op)			\
-	asm_volatile_goto(					\
+	asm goto(					\
 		"1:	" op " %0,0(%1)	# put_user\n"		\
 		EX_TABLE(1b, %l2)				\
 		:						\
@@ -83,7 +83,7 @@ __pu_failed:							\
 		: label)
 #else
 #define __put_user_asm_goto(x, addr, label, op)			\
-	asm_volatile_goto(					\
+	asm goto(					\
 		"1:	" op "%U1%X1 %0,%1	# put_user\n"	\
 		EX_TABLE(1b, %l2)				\
 		:						\
@@ -97,7 +97,7 @@ __pu_failed:							\
 	__put_user_asm_goto(x, ptr, label, "std")
 #else /* __powerpc64__ */
 #define __put_user_asm2_goto(x, addr, label)			\
-	asm_volatile_goto(					\
+	asm goto(					\
 		"1:	stw%X1 %0, %1\n"			\
 		"2:	stw%X1 %L0, %L1\n"			\
 		EX_TABLE(1b, %l2)				\
@@ -146,7 +146,7 @@ do {								\
 /* -mprefixed can generate offsets beyond range, fall back hack */
 #ifdef CONFIG_PPC_KERNEL_PREFIXED
 #define __get_user_asm_goto(x, addr, label, op)			\
-	asm_volatile_goto(					\
+	asm_goto_output(					\
 		"1:	"op" %0,0(%1)	# get_user\n"		\
 		EX_TABLE(1b, %l2)				\
 		: "=r" (x)					\
@@ -155,7 +155,7 @@ do {								\
 		: label)
 #else
 #define __get_user_asm_goto(x, addr, label, op)			\
-	asm_volatile_goto(					\
+	asm_goto_output(					\
 		"1:	"op"%U1%X1 %0, %1	# get_user\n"	\
 		EX_TABLE(1b, %l2)				\
 		: "=r" (x)					\
@@ -169,7 +169,7 @@ do {								\
 	__get_user_asm_goto(x, addr, label, "ld")
 #else /* __powerpc64__ */
 #define __get_user_asm2_goto(x, addr, label)			\
-	asm_volatile_goto(					\
+	asm_goto_output(					\
 		"1:	lwz%X1 %0, %1\n"			\
 		"2:	lwz%X1 %L0, %L1\n"			\
 		EX_TABLE(1b, %l2)				\
--- a/arch/powerpc/kernel/cpu_setup_6xx.S
+++ b/arch/powerpc/kernel/cpu_setup_6xx.S
@@ -26,6 +26,15 @@ BEGIN_FTR_SECTION
 	bl	__init_fpu_registers
 END_FTR_SECTION_IFCLR(CPU_FTR_FPU_UNAVAILABLE)
 	bl	setup_common_caches
+
+	/*
+	 * This assumes that all cores using __setup_cpu_603 with
+	 * MMU_FTR_USE_HIGH_BATS are G2_LE compatible
+	 */
+BEGIN_MMU_FTR_SECTION
+	bl      setup_g2_le_hid2
+END_MMU_FTR_SECTION_IFSET(MMU_FTR_USE_HIGH_BATS)
+
 	mtlr	r5
 	blr
 _GLOBAL(__setup_cpu_604)
@@ -115,6 +124,16 @@ SYM_FUNC_START_LOCAL(setup_604_hid0)
 	blr
 SYM_FUNC_END(setup_604_hid0)

+/* Enable high BATs for G2_LE and derivatives like e300cX */
+SYM_FUNC_START_LOCAL(setup_g2_le_hid2)
+	mfspr	r11,SPRN_HID2_G2_LE
+	oris	r11,r11,HID2_G2_LE_HBE@h
+	mtspr	SPRN_HID2_G2_LE,r11
+	sync
+	isync
+	blr
+SYM_FUNC_END(setup_g2_le_hid2)
+
 /* 7400 <= rev 2.7 and 7410 rev = 1.0 suffer from some
 * erratas we work around here.
 * Moto MPC710CE.pdf describes them, those are errata
@@ -495,4 +514,3 @@ _GLOBAL(__restore_cpu_setup)
 	mtcr	r7
 	blr
 _ASM_NOKPROBE_SYMBOL(__restore_cpu_setup)
-
--- a/arch/powerpc/kernel/cpu_specs_e500mc.h
+++ b/arch/powerpc/kernel/cpu_specs_e500mc.h
@@ -8,7 +8,8 @@

 #ifdef CONFIG_PPC64
 #define COMMON_USER_BOOKE	(PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU | \
-				 PPC_FEATURE_HAS_FPU | PPC_FEATURE_64)
+				 PPC_FEATURE_HAS_FPU | PPC_FEATURE_64 | \
+				 PPC_FEATURE_BOOKE)
 #else
 #define COMMON_USER_BOOKE	(PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU | \
 				 PPC_FEATURE_BOOKE)
--- a/arch/powerpc/kernel/interrupt_64.S
+++ b/arch/powerpc/kernel/interrupt_64.S
@@ -52,7 +52,8 @@ _ASM_NOKPROBE_SYMBOL(system_call_vectored_\name)
 	mr	r10,r1
 	ld	r1,PACAKSAVE(r13)
 	std	r10,0(r1)
-	std	r11,_NIP(r1)
+	std	r11,_LINK(r1)
+	std	r11,_NIP(r1)	/* Saved LR is also the next instruction */
 	std	r12,_MSR(r1)
 	std	r0,GPR0(r1)
 	std	r10,GPR1(r1)
@@ -70,7 +71,6 @@ _ASM_NOKPROBE_SYMBOL(system_call_vectored_\name)
 	std	r9,GPR13(r1)
 	SAVE_NVGPRS(r1)
 	std	r11,_XER(r1)
-	std	r11,_LINK(r1)
 	std	r11,_CTR(r1)

 	li	r11,\trapnr
--- a/arch/powerpc/kernel/irq_64.c
+++ b/arch/powerpc/kernel/irq_64.c
@@ -230,7 +230,7 @@ again:
 	 * This allows interrupts to be unmasked without hard disabling, and
 	 * also without new hard interrupts coming in ahead of pending ones.
 	 */
-	asm_volatile_goto(
+	asm goto(
 "1:					\n"
 "		lbz	9,%0(13)	\n"
 "		cmpwi	9,0		\n"
--- a/arch/powerpc/mm/kasan/init_32.c
+++ b/arch/powerpc/mm/kasan/init_32.c
@@ -64,6 +64,7 @@ int __init __weak kasan_init_region(void *start, size_t size)
 	if (ret)
 		return ret;

+	k_start = k_start & PAGE_MASK;
 	block = memblock_alloc(k_end - k_start, PAGE_SIZE);
 	if (!block)
 		return -ENOMEM;
--- a/arch/powerpc/platforms/pseries/lpar.c
+++ b/arch/powerpc/platforms/pseries/lpar.c
@@ -662,8 +662,12 @@ u64 pseries_paravirt_steal_clock(int cpu)
 {
 	struct lppaca *lppaca = &lppaca_of(cpu);

-	return be64_to_cpu(READ_ONCE(lppaca->enqueue_dispatch_tb)) +
-		be64_to_cpu(READ_ONCE(lppaca->ready_enqueue_tb));
+	/*
+	 * VPA steal time counters are reported at TB frequency. Hence do a
+	 * conversion to ns before returning
+	 */
+	return tb_to_ns(be64_to_cpu(READ_ONCE(lppaca->enqueue_dispatch_tb)) +
+			be64_to_cpu(READ_ONCE(lppaca->ready_enqueue_tb)));
 }
 #endif

--- a/arch/riscv/include/asm/hwcap.h
+++ b/arch/riscv/include/asm/hwcap.h
@@ -98,7 +98,7 @@ riscv_has_extension_likely(const unsigned long ext)
 			   "ext must be < RISCV_ISA_EXT_MAX");

 	if (IS_ENABLED(CONFIG_RISCV_ALTERNATIVE)) {
-		asm_volatile_goto(
+		asm goto(
 		ALTERNATIVE("j	%l[l_no]", "nop", 0, %[ext], 1)
 		:
 		: [ext] "i" (ext)
@@ -121,7 +121,7 @@ riscv_has_extension_unlikely(const unsigned long ext)
 			   "ext must be < RISCV_ISA_EXT_MAX");

 	if (IS_ENABLED(CONFIG_RISCV_ALTERNATIVE)) {
-		asm_volatile_goto(
+		asm goto(
 		ALTERNATIVE("nop", "j	%l[l_yes]", 0, %[ext], 1)
 		:
 		: [ext] "i" (ext)
--- a/arch/riscv/include/asm/jump_label.h
+++ b/arch/riscv/include/asm/jump_label.h
@@ -17,7 +17,7 @@
 static __always_inline bool arch_static_branch(struct static_key * const key,
 					       const bool branch)
 {
-	asm_volatile_goto(
+	asm goto(
 		"	.align		2			\n\t"
 		"	.option push				\n\t"
 		"	.option norelax				\n\t"
@@ -39,7 +39,7 @@ label:
 static __always_inline bool arch_static_branch_jump(struct static_key * const key,
 						    const bool branch)
 {
-	asm_volatile_goto(
+	asm goto(
 		"	.align		2			\n\t"
 		"	.option push				\n\t"
 		"	.option norelax				\n\t"
--- a/arch/s390/include/asm/jump_label.h
+++ b/arch/s390/include/asm/jump_label.h
@@ -25,7 +25,7 @@
 */
 static __always_inline bool arch_static_branch(struct static_key *key, bool branch)
 {
-	asm_volatile_goto("0:	brcl 0,%l[label]\n"
+	asm goto("0:	brcl 0,%l[label]\n"
 			  ".pushsection __jump_table,\"aw\"\n"
 			  ".balign	8\n"
 			  ".long	0b-.,%l[label]-.\n"
@@ -39,7 +39,7 @@ label:

 static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch)
 {
-	asm_volatile_goto("0:	brcl 15,%l[label]\n"
+	asm goto("0:	brcl 15,%l[label]\n"
 			  ".pushsection __jump_table,\"aw\"\n"
 			  ".balign	8\n"
 			  ".long	0b-.,%l[label]-.\n"
--- a/arch/sparc/include/asm/jump_label.h
+++ b/arch/sparc/include/asm/jump_label.h
@@ -10,7 +10,7 @@

 static __always_inline bool arch_static_branch(struct static_key *key, bool branch)
 {
-	asm_volatile_goto("1:\n\t"
+	asm goto("1:\n\t"
 		 "nop\n\t"
 		 "nop\n\t"
 		 ".pushsection __jump_table,  \"aw\"\n\t"
@@ -26,7 +26,7 @@ l_yes:

 static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch)
 {
-	asm_volatile_goto("1:\n\t"
+	asm goto("1:\n\t"
 		 "b %l[l_yes]\n\t"
 		 "nop\n\t"
 		 ".pushsection __jump_table,  \"aw\"\n\t"
--- a/arch/um/Makefile
+++ b/arch/um/Makefile
@@ -115,7 +115,9 @@ archprepare:
 	$(Q)$(MAKE) $(build)=$(HOST_DIR)/um include/generated/user_constants.h

 LINK-$(CONFIG_LD_SCRIPT_STATIC) += -static
-LINK-$(CONFIG_LD_SCRIPT_DYN) += $(call cc-option, -no-pie)
+ifdef CONFIG_LD_SCRIPT_DYN
+LINK-$(call gcc-min-version, 60100)$(CONFIG_CC_IS_CLANG) += -no-pie
+endif
 LINK-$(CONFIG_LD_SCRIPT_DYN_RPATH) += -Wl,-rpath,/lib

 CFLAGS_NO_HARDENING := $(call cc-option, -fno-PIC,) $(call cc-option, -fno-pic,) \
--- a/arch/um/include/asm/cpufeature.h
+++ b/arch/um/include/asm/cpufeature.h
@@ -75,7 +75,7 @@ extern void setup_clear_cpu_cap(unsigned int bit);
 */
 static __always_inline bool _static_cpu_has(u16 bit)
 {
-	asm_volatile_goto("1: jmp 6f\n"
+	asm goto("1: jmp 6f\n"
 		 "2:\n"
 		 ".skip -(((5f-4f) - (2b-1b)) > 0) * "
 			 "((5f-4f) - (2b-1b)),0x90\n"
--- a/arch/x86/Kconfig.cpu
+++ b/arch/x86/Kconfig.cpu
@@ -375,7 +375,7 @@ config X86_CMOV
 config X86_MINIMUM_CPU_FAMILY
 	int
 	default "64" if X86_64
-	default "6" if X86_32 && (MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MVIAC3_2 || MVIAC7 || MEFFICEON || MATOM || MCRUSOE || MCORE2 || MK7 || MK8)
+	default "6" if X86_32 && (MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MVIAC3_2 || MVIAC7 || MEFFICEON || MATOM || MCORE2 || MK7 || MK8)
 	default "5" if X86_32 && X86_CMPXCHG64
 	default "4"

--- a/arch/x86/boot/Makefile
+++ b/arch/x86/boot/Makefile
@@ -89,7 +89,7 @@ $(obj)/vmlinux.bin: $(obj)/compressed/vmlinux FORCE

 SETUP_OBJS = $(addprefix $(obj)/,$(setup-y))

-sed-zoffset := -e 's/^\([0-9a-fA-F]*\) [a-zA-Z] \(startup_32\|startup_64\|efi32_stub_entry\|efi64_stub_entry\|efi_pe_entry\|efi32_pe_entry\|input_data\|kernel_info\|_end\|_ehead\|_text\|z_.*\)$$/\#define ZO_\2 0x\1/p'
+sed-zoffset := -e 's/^\([0-9a-fA-F]*\) [a-zA-Z] \(startup_32\|efi.._stub_entry\|efi\(32\)\?_pe_entry\|input_data\|kernel_info\|_end\|_ehead\|_text\|_e\?data\|z_.*\)$$/\#define ZO_\2 0x\1/p'

 quiet_cmd_zoffset = ZOFFSET $@
      cmd_zoffset = $(NM) $< | sed -n $(sed-zoffset) > $@
--- a/arch/x86/boot/compressed/vmlinux.lds.S
+++ b/arch/x86/boot/compressed/vmlinux.lds.S
@@ -43,11 +43,13 @@ SECTIONS
 		*(.rodata.*)
 		_erodata = . ;
 	}
-	.data :	{
+	.data :	ALIGN(0x1000) {
 		_data = . ;
 		*(.data)
 		*(.data.*)
-		*(.bss.efistub)
+
+		/* Add 4 bytes of extra space for a CRC-32 checksum */
+		. = ALIGN(. + 4, 0x200);
 		_edata = . ;
 	}
 	. = ALIGN(L1_CACHE_BYTES);
--- a/arch/x86/boot/header.S
+++ b/arch/x86/boot/header.S
@@ -36,66 +36,20 @@ SYSSEG		= 0x1000		/* historical load address >> 4 */
 #define ROOT_RDONLY 1
 #endif

+	.set	salign, 0x1000
+	.set	falign, 0x200
+
 	.code16
 	.section ".bstext", "ax"
-
-	.global bootsect_start
-bootsect_start:
 #ifdef CONFIG_EFI_STUB
 	# "MZ", MS-DOS header
 	.word	MZ_MAGIC
-#endif
-
-	# Normalize the start address
-	ljmp	$BOOTSEG, $start2
-
-start2:
-	movw	%cs, %ax
-	movw	%ax, %ds
-	movw	%ax, %es
-	movw	%ax, %ss
-	xorw	%sp, %sp
-	sti
-	cld
-
-	movw	$bugger_off_msg, %si
-
-msg_loop:
-	lodsb
-	andb	%al, %al
-	jz	bs_die
-	movb	$0xe, %ah
-	movw	$7, %bx
-	int	$0x10
-	jmp	msg_loop
-
-bs_die:
-	# Allow the user to press a key, then reboot
-	xorw	%ax, %ax
-	int	$0x16
-	int	$0x19
-
-	# int 0x19 should never return.  In case it does anyway,
-	# invoke the BIOS reset code...
-	ljmp	$0xf000,$0xfff0
-
-#ifdef CONFIG_EFI_STUB
 	.org	0x38
 	#
 	# Offset to the PE header.
 	#
 	.long	LINUX_PE_MAGIC
 	.long	pe_header
-#endif /* CONFIG_EFI_STUB */
-
-	.section ".bsdata", "a"
-bugger_off_msg:
-	.ascii	"Use a boot loader.\r\n"
-	.ascii	"\n"
-	.ascii	"Remove disk and press any key to reboot...\r\n"
-	.byte	0
-
-#ifdef CONFIG_EFI_STUB
 pe_header:
 	.long	PE_MAGIC

@@ -124,30 +78,26 @@ optional_header:
 	.byte	0x02				# MajorLinkerVersion
 	.byte	0x14				# MinorLinkerVersion

-	# Filled in by build.c
-	.long	0				# SizeOfCode
+	.long	ZO__data			# SizeOfCode

-	.long	0				# SizeOfInitializedData
+	.long	ZO__end - ZO__data		# SizeOfInitializedData
 	.long	0				# SizeOfUninitializedData

-	# Filled in by build.c
-	.long	0x0000				# AddressOfEntryPoint
+	.long	setup_size + ZO_efi_pe_entry	# AddressOfEntryPoint

-	.long	0x0200				# BaseOfCode
+	.long	setup_size			# BaseOfCode
 #ifdef CONFIG_X86_32
 	.long	0				# data
 #endif

 extra_header_fields:
-	# PE specification requires ImageBase to be 64k aligned
-	.set	image_base, (LOAD_PHYSICAL_ADDR + 0xffff) & ~0xffff
 #ifdef CONFIG_X86_32
-	.long	image_base			# ImageBase
+	.long	0				# ImageBase
 #else
-	.quad	image_base			# ImageBase
+	.quad	0				# ImageBase
 #endif
-	.long	0x20				# SectionAlignment
-	.long	0x20				# FileAlignment
+	.long	salign				# SectionAlignment
+	.long	falign				# FileAlignment
 	.word	0				# MajorOperatingSystemVersion
 	.word	0				# MinorOperatingSystemVersion
 	.word	LINUX_EFISTUB_MAJOR_VERSION	# MajorImageVersion
@@ -156,12 +106,9 @@ extra_header_fields:
 	.word	0				# MinorSubsystemVersion
 	.long	0				# Win32VersionValue

-	#
-	# The size of the bzImage is written in tools/build.c
-	#
-	.long	0				# SizeOfImage
+	.long	setup_size + ZO__end		# SizeOfImage

-	.long	0x200				# SizeOfHeaders
+	.long	salign				# SizeOfHeaders
 	.long	0				# CheckSum
 	.word	IMAGE_SUBSYSTEM_EFI_APPLICATION	# Subsystem (EFI application)
 #ifdef CONFIG_EFI_DXE_MEM_ATTRIBUTES
@@ -192,87 +139,77 @@ extra_header_fields:

 	# Section table
 section_table:
-	#
-	# The offset & size fields are filled in by build.c.
-	#
 	.ascii	".setup"
 	.byte	0
 	.byte	0
-	.long	0
-	.long	0x0				# startup_{32,64}
-	.long	0				# Size of initialized data
-						# on disk
-	.long	0x0				# startup_{32,64}
-	.long	0				# PointerToRelocations
-	.long	0				# PointerToLineNumbers
-	.word	0				# NumberOfRelocations
-	.word	0				# NumberOfLineNumbers
-	.long	IMAGE_SCN_CNT_CODE		| \
-		IMAGE_SCN_MEM_READ		| \
-		IMAGE_SCN_MEM_EXECUTE		| \
-		IMAGE_SCN_ALIGN_16BYTES		# Characteristics
+	.long	pecompat_fstart - salign 	# VirtualSize
+	.long	salign				# VirtualAddress
+	.long	pecompat_fstart - salign	# SizeOfRawData
+	.long	salign				# PointerToRawData

-	#
-	# The EFI application loader requires a relocation section
-	# because EFI applications must be relocatable. The .reloc
-	# offset & size fields are filled in by build.c.
-	#
-	.ascii	".reloc"
-	.byte	0
-	.byte	0
-	.long	0
-	.long	0
-	.long	0				# SizeOfRawData
-	.long	0				# PointerToRawData
-	.long	0				# PointerToRelocations
-	.long	0				# PointerToLineNumbers
-	.word	0				# NumberOfRelocations
-	.word	0				# NumberOfLineNumbers
+	.long	0, 0, 0
 	.long	IMAGE_SCN_CNT_INITIALIZED_DATA	| \
 		IMAGE_SCN_MEM_READ		| \
-		IMAGE_SCN_MEM_DISCARDABLE	| \
-		IMAGE_SCN_ALIGN_1BYTES		# Characteristics
+		IMAGE_SCN_MEM_DISCARDABLE	# Characteristics

 #ifdef CONFIG_EFI_MIXED
-	#
-	# The offset & size fields are filled in by build.c.
-	#
 	.asciz	".compat"
-	.long	0
-	.long	0x0
-	.long	0				# Size of initialized data
-						# on disk
-	.long	0x0
-	.long	0				# PointerToRelocations
-	.long	0				# PointerToLineNumbers
-	.word	0				# NumberOfRelocations
-	.word	0				# NumberOfLineNumbers
+
+	.long	pecompat_fsize			# VirtualSize
+	.long	pecompat_fstart			# VirtualAddress
+	.long	pecompat_fsize			# SizeOfRawData
+	.long	pecompat_fstart			# PointerToRawData
+
+	.long	0, 0, 0
 	.long	IMAGE_SCN_CNT_INITIALIZED_DATA	| \
 		IMAGE_SCN_MEM_READ		| \
-		IMAGE_SCN_MEM_DISCARDABLE	| \
-		IMAGE_SCN_ALIGN_1BYTES		# Characteristics
-#endif
+		IMAGE_SCN_MEM_DISCARDABLE	# Characteristics

-	#
-	# The offset & size fields are filled in by build.c.
-	#
+	/*
+	 * Put the IA-32 machine type and the associated entry point address in
+	 * the .compat section, so loaders can figure out which other execution
+	 * modes this image supports.
+	 */
+	.pushsection ".pecompat", "a", @progbits
+	.balign	salign
+	.globl	pecompat_fstart
+pecompat_fstart:
+	.byte	0x1				# Version
+	.byte	8				# Size
+	.word	IMAGE_FILE_MACHINE_I386		# PE machine type
+	.long	setup_size + ZO_efi32_pe_entry	# Entrypoint
+	.byte	0x0				# Sentinel
+	.popsection
+#else
+	.set	pecompat_fstart, setup_size
+#endif
 	.ascii	".text"
 	.byte	0
 	.byte	0
 	.byte	0
-	.long	0
-	.long	0x0				# startup_{32,64}
-	.long	0				# Size of initialized data
+	.long	ZO__data
+	.long	setup_size
+	.long	ZO__data			# Size of initialized data
 						# on disk
-	.long	0x0				# startup_{32,64}
+	.long	setup_size
 	.long	0				# PointerToRelocations
 	.long	0				# PointerToLineNumbers
 	.word	0				# NumberOfRelocations
 	.word	0				# NumberOfLineNumbers
 	.long	IMAGE_SCN_CNT_CODE		| \
 		IMAGE_SCN_MEM_READ		| \
-		IMAGE_SCN_MEM_EXECUTE		| \
-		IMAGE_SCN_ALIGN_16BYTES		# Characteristics
+		IMAGE_SCN_MEM_EXECUTE		# Characteristics
+
+	.ascii	".data\0\0\0"
+	.long	ZO__end - ZO__data		# VirtualSize
+	.long	setup_size + ZO__data		# VirtualAddress
+	.long	ZO__edata - ZO__data		# SizeOfRawData
+	.long	setup_size + ZO__data		# PointerToRawData
+
+	.long	0, 0, 0
+	.long	IMAGE_SCN_CNT_INITIALIZED_DATA	| \
+		IMAGE_SCN_MEM_READ		| \
+		IMAGE_SCN_MEM_WRITE		# Characteristics

 	.set	section_count, (. - section_table) / 40
 #endif /* CONFIG_EFI_STUB */
@@ -286,12 +223,12 @@ sentinel:	.byte 0xff, 0xff        /* Used to detect broken loaders */

 	.globl	hdr
 hdr:
-setup_sects:	.byte 0			/* Filled in by build.c */
+		.byte setup_sects - 1
 root_flags:	.word ROOT_RDONLY
-syssize:	.long 0			/* Filled in by build.c */
+syssize:	.long ZO__edata / 16
 ram_size:	.word 0			/* Obsolete */
 vid_mode:	.word SVGA_MODE
-root_dev:	.word 0			/* Filled in by build.c */
+root_dev:	.word 0			/* Default to major/minor 0/0 */
 boot_flag:	.word 0xAA55

 	# offset 512, entry point
@@ -579,9 +516,25 @@ pref_address:		.quad LOAD_PHYSICAL_ADDR	# preferred load addr
 # define INIT_SIZE VO_INIT_SIZE
 #endif

+	.macro		__handover_offset
+#ifndef CONFIG_EFI_HANDOVER_PROTOCOL
+	.long		0
+#elif !defined(CONFIG_X86_64)
+	.long		ZO_efi32_stub_entry
+#else
+	/* Yes, this is really how we defined it :( */
+	.long		ZO_efi64_stub_entry - 0x200
+#ifdef CONFIG_EFI_MIXED
+	.if		ZO_efi32_stub_entry != ZO_efi64_stub_entry - 0x200
+	.error		"32-bit and 64-bit EFI entry points do not match"
+	.endif
+#endif
+#endif
+	.endm
+
 init_size:		.long INIT_SIZE		# kernel initialization size
-handover_offset:	.long 0			# Filled in by build.c
-kernel_info_offset:	.long 0			# Filled in by build.c
+handover_offset:	__handover_offset
+kernel_info_offset:	.long ZO_kernel_info

 # End of setup header #####################################################

--- a/arch/x86/boot/setup.ld
+++ b/arch/x86/boot/setup.ld
@@ -10,10 +10,11 @@ ENTRY(_start)
 SECTIONS
 {
 	. = 0;
-	.bstext		: { *(.bstext) }
-	.bsdata		: { *(.bsdata) }
+	.bstext	: {
+		*(.bstext)
+		. = 495;
+	} =0xffffffff

-	. = 495;
 	.header		: { *(.header) }
 	.entrytext	: { *(.entrytext) }
 	.inittext	: { *(.inittext) }
@@ -23,6 +24,9 @@ SECTIONS
 	.text		: { *(.text .text.*) }
 	.text32		: { *(.text32) }

+	.pecompat	: { *(.pecompat) }
+	PROVIDE(pecompat_fsize = setup_size - pecompat_fstart);
+
 	. = ALIGN(16);
 	.rodata		: { *(.rodata*) }

@@ -38,8 +42,10 @@ SECTIONS
 	.signature	: {
 		setup_sig = .;
 		LONG(0x5a5aaa55)
-	}

+		setup_size = ALIGN(ABSOLUTE(.), 4096);
+		setup_sects = ABSOLUTE(setup_size / 512);
+	}

 	. = ALIGN(16);
 	.bss		:
--- a/arch/x86/boot/tools/build.c
+++ b/arch/x86/boot/tools/build.c
@@ -40,10 +40,6 @@ typedef unsigned char  u8;
 typedef unsigned short u16;
 typedef unsigned int   u32;

-#define DEFAULT_MAJOR_ROOT 0
-#define DEFAULT_MINOR_ROOT 0
-#define DEFAULT_ROOT_DEV (DEFAULT_MAJOR_ROOT << 8 | DEFAULT_MINOR_ROOT)
-
 /* Minimal number of setup sectors */
 #define SETUP_SECT_MIN 5
 #define SETUP_SECT_MAX 64
@@ -51,22 +47,7 @@ typedef unsigned int   u32;
 /* This must be large enough to hold the entire setup */
 u8 buf[SETUP_SECT_MAX*512];

-#define PECOFF_RELOC_RESERVE 0x20
-
-#ifdef CONFIG_EFI_MIXED
-#define PECOFF_COMPAT_RESERVE 0x20
-#else
-#define PECOFF_COMPAT_RESERVE 0x0
-#endif
-
-static unsigned long efi32_stub_entry;
-static unsigned long efi64_stub_entry;
-static unsigned long efi_pe_entry;
-static unsigned long efi32_pe_entry;
-static unsigned long kernel_info;
-static unsigned long startup_64;
-static unsigned long _ehead;
-static unsigned long _end;
+static unsigned long _edata;

 /*----------------------------------------------------------------------*/

@@ -152,180 +133,6 @@ static void usage(void)
 	die("Usage: build setup system zoffset.h image");
 }

-#ifdef CONFIG_EFI_STUB
-
-static void update_pecoff_section_header_fields(char *section_name, u32 vma, u32 size, u32 datasz, u32 offset)
-{
-	unsigned int pe_header;
-	unsigned short num_sections;
-	u8 *section;
-
-	pe_header = get_unaligned_le32(&buf[0x3c]);
-	num_sections = get_unaligned_le16(&buf[pe_header + 6]);
-
-#ifdef CONFIG_X86_32
-	section = &buf[pe_header + 0xa8];
-#else
-	section = &buf[pe_header + 0xb8];
-#endif
-
-	while (num_sections > 0) {
-		if (strncmp((char*)section, section_name, 8) == 0) {
-			/* section header size field */
-			put_unaligned_le32(size, section + 0x8);
-
-			/* section header vma field */
-			put_unaligned_le32(vma, section + 0xc);
-
-			/* section header 'size of initialised data' field */
-			put_unaligned_le32(datasz, section + 0x10);
-
-			/* section header 'file offset' field */
-			put_unaligned_le32(offset, section + 0x14);
-
-			break;
-		}
-		section += 0x28;
-		num_sections--;
-	}
-}
-
-static void update_pecoff_section_header(char *section_name, u32 offset, u32 size)
-{
-	update_pecoff_section_header_fields(section_name, offset, size, size, offset);
-}
-
-static void update_pecoff_setup_and_reloc(unsigned int size)
-{
-	u32 setup_offset = 0x200;
-	u32 reloc_offset = size - PECOFF_RELOC_RESERVE - PECOFF_COMPAT_RESERVE;
-#ifdef CONFIG_EFI_MIXED
-	u32 compat_offset = reloc_offset + PECOFF_RELOC_RESERVE;
-#endif
-	u32 setup_size = reloc_offset - setup_offset;
-
-	update_pecoff_section_header(".setup", setup_offset, setup_size);
-	update_pecoff_section_header(".reloc", reloc_offset, PECOFF_RELOC_RESERVE);
-
-	/*
-	 * Modify .reloc section contents with a single entry. The
-	 * relocation is applied to offset 10 of the relocation section.
-	 */
-	put_unaligned_le32(reloc_offset + 10, &buf[reloc_offset]);
-	put_unaligned_le32(10, &buf[reloc_offset + 4]);
-
-#ifdef CONFIG_EFI_MIXED
-	update_pecoff_section_header(".compat", compat_offset, PECOFF_COMPAT_RESERVE);
-
-	/*
-	 * Put the IA-32 machine type (0x14c) and the associated entry point
-	 * address in the .compat section, so loaders can figure out which other
-	 * execution modes this image supports.
-	 */
-	buf[compat_offset] = 0x1;
-	buf[compat_offset + 1] = 0x8;
-	put_unaligned_le16(0x14c, &buf[compat_offset + 2]);
-	put_unaligned_le32(efi32_pe_entry + size, &buf[compat_offset + 4]);
-#endif
-}
-
-static void update_pecoff_text(unsigned int text_start, unsigned int file_sz,
-			       unsigned int init_sz)
-{
-	unsigned int pe_header;
-	unsigned int text_sz = file_sz - text_start;
-	unsigned int bss_sz = init_sz - file_sz;
-
-	pe_header = get_unaligned_le32(&buf[0x3c]);
-
-	/*
-	 * The PE/COFF loader may load the image at an address which is
-	 * misaligned with respect to the kernel_alignment field in the setup
-	 * header.
-	 *
-	 * In order to avoid relocating the kernel to correct the misalignment,
-	 * add slack to allow the buffer to be aligned within the declared size
-	 * of the image.
-	 */
-	bss_sz	+= CONFIG_PHYSICAL_ALIGN;
-	init_sz	+= CONFIG_PHYSICAL_ALIGN;
-
-	/*
-	 * Size of code: Subtract the size of the first sector (512 bytes)
-	 * which includes the header.
-	 */
-	put_unaligned_le32(file_sz - 512 + bss_sz, &buf[pe_header + 0x1c]);
-
-	/* Size of image */
-	put_unaligned_le32(init_sz, &buf[pe_header + 0x50]);
-
-	/*
-	 * Address of entry point for PE/COFF executable
-	 */
-	put_unaligned_le32(text_start + efi_pe_entry, &buf[pe_header + 0x28]);
-
-	update_pecoff_section_header_fields(".text", text_start, text_sz + bss_sz,
-					    text_sz, text_start);
-}
-
-static int reserve_pecoff_reloc_section(int c)
-{
-	/* Reserve 0x20 bytes for .reloc section */
-	memset(buf+c, 0, PECOFF_RELOC_RESERVE);
-	return PECOFF_RELOC_RESERVE;
-}
-
-static void efi_stub_defaults(void)
-{
-	/* Defaults for old kernel */
-#ifdef CONFIG_X86_32
-	efi_pe_entry = 0x10;
-#else
-	efi_pe_entry = 0x210;
-	startup_64 = 0x200;
-#endif
-}
-
-static void efi_stub_entry_update(void)
-{
-	unsigned long addr = efi32_stub_entry;
-
-#ifdef CONFIG_EFI_HANDOVER_PROTOCOL
-#ifdef CONFIG_X86_64
-	/* Yes, this is really how we defined it :( */
-	addr = efi64_stub_entry - 0x200;
-#endif
-
-#ifdef CONFIG_EFI_MIXED
-	if (efi32_stub_entry != addr)
-		die("32-bit and 64-bit EFI entry points do not match\n");
-#endif
-#endif
-	put_unaligned_le32(addr, &buf[0x264]);
-}
-
-#else
-
-static inline void update_pecoff_setup_and_reloc(unsigned int size) {}
-static inline void update_pecoff_text(unsigned int text_start,
-				      unsigned int file_sz,
-				      unsigned int init_sz) {}
-static inline void efi_stub_defaults(void) {}
-static inline void efi_stub_entry_update(void) {}
-
-static inline int reserve_pecoff_reloc_section(int c)
-{
-	return 0;
-}
-#endif /* CONFIG_EFI_STUB */
-
-static int reserve_pecoff_compat_section(int c)
-{
-	/* Reserve 0x20 bytes for .compat section */
-	memset(buf+c, 0, PECOFF_COMPAT_RESERVE);
-	return PECOFF_COMPAT_RESERVE;
-}
-
 /*
 * Parse zoffset.h and find the entry points. We could just #include zoffset.h
 * but that would mean tools/build would have to be rebuilt every time. It's
@@ -354,14 +161,7 @@ static void parse_zoffset(char *fname)
 	p = (char *)buf;

 	while (p && *p) {
-		PARSE_ZOFS(p, efi32_stub_entry);
-		PARSE_ZOFS(p, efi64_stub_entry);
-		PARSE_ZOFS(p, efi_pe_entry);
-		PARSE_ZOFS(p, efi32_pe_entry);
-		PARSE_ZOFS(p, kernel_info);
-		PARSE_ZOFS(p, startup_64);
-		PARSE_ZOFS(p, _ehead);
-		PARSE_ZOFS(p, _end);
+		PARSE_ZOFS(p, _edata);

 		p = strchr(p, '\n');
 		while (p && (*p == '\r' || *p == '\n'))
@@ -371,17 +171,14 @@ static void parse_zoffset(char *fname)

 int main(int argc, char ** argv)
 {
-	unsigned int i, sz, setup_sectors, init_sz;
+	unsigned int i, sz, setup_sectors;
 	int c;
-	u32 sys_size;
 	struct stat sb;
 	FILE *file, *dest;
 	int fd;
 	void *kernel;
 	u32 crc = 0xffffffffUL;

-	efi_stub_defaults();
-
 	if (argc != 5)
 		usage();
 	parse_zoffset(argv[3]);
@@ -403,72 +200,27 @@ int main(int argc, char ** argv)
 		die("Boot block hasn't got boot flag (0xAA55)");
 	fclose(file);

-	c += reserve_pecoff_compat_section(c);
-	c += reserve_pecoff_reloc_section(c);
-
 	/* Pad unused space with zeros */
-	setup_sectors = (c + 511) / 512;
+	setup_sectors = (c + 4095) / 4096;
+	setup_sectors *= 8;
 	if (setup_sectors < SETUP_SECT_MIN)
 		setup_sectors = SETUP_SECT_MIN;
 	i = setup_sectors*512;
 	memset(buf+c, 0, i-c);

-	update_pecoff_setup_and_reloc(i);
-
-	/* Set the default root device */
-	put_unaligned_le16(DEFAULT_ROOT_DEV, &buf[508]);
-
 	/* Open and stat the kernel file */
 	fd = open(argv[2], O_RDONLY);
 	if (fd < 0)
 		die("Unable to open `%s': %m", argv[2]);
 	if (fstat(fd, &sb))
 		die("Unable to stat `%s': %m", argv[2]);
-	sz = sb.st_size;
+	if (_edata != sb.st_size)
+		die("Unexpected file size `%s': %u != %u", argv[2], _edata,
+		    sb.st_size);
+	sz = _edata - 4;
 	kernel = mmap(NULL, sz, PROT_READ, MAP_SHARED, fd, 0);
 	if (kernel == MAP_FAILED)
 		die("Unable to mmap '%s': %m", argv[2]);
-	/* Number of 16-byte paragraphs, including space for a 4-byte CRC */
-	sys_size = (sz + 15 + 4) / 16;
-#ifdef CONFIG_EFI_STUB
-	/*
-	 * COFF requires minimum 32-byte alignment of sections, and
-	 * adding a signature is problematic without that alignment.
-	 */
-	sys_size = (sys_size + 1) & ~1;
-#endif
-
-	/* Patch the setup code with the appropriate size parameters */
-	buf[0x1f1] = setup_sectors-1;
-	put_unaligned_le32(sys_size, &buf[0x1f4]);
-
-	init_sz = get_unaligned_le32(&buf[0x260]);
-#ifdef CONFIG_EFI_STUB
-	/*
-	 * The decompression buffer will start at ImageBase. When relocating
-	 * the compressed kernel to its end, we must ensure that the head
-	 * section does not get overwritten.  The head section occupies
-	 * [i, i + _ehead), and the destination is [init_sz - _end, init_sz).
-	 *
-	 * At present these should never overlap, because 'i' is at most 32k
-	 * because of SETUP_SECT_MAX, '_ehead' is less than 1k, and the
-	 * calculation of INIT_SIZE in boot/header.S ensures that
-	 * 'init_sz - _end' is at least 64k.
-	 *
-	 * For future-proofing, increase init_sz if necessary.
-	 */
-
-	if (init_sz - _end < i + _ehead) {
-		init_sz = (i + _ehead + _end + 4095) & ~4095;
-		put_unaligned_le32(init_sz, &buf[0x260]);
-	}
-#endif
-	update_pecoff_text(setup_sectors * 512, i + (sys_size * 16), init_sz);
-
-	efi_stub_entry_update();
-
-	/* Update kernel_info offset. */
-	put_unaligned_le32(kernel_info, &buf[0x268]);

 	crc = partial_crc32(buf, i, crc);
 	if (fwrite(buf, 1, i, dest) != i)
@@ -479,13 +231,6 @@ int main(int argc, char ** argv)
 	if (fwrite(kernel, 1, sz, dest) != sz)
 		die("Writing kernel failed");

-	/* Add padding leaving 4 bytes for the checksum */
-	while (sz++ < (sys_size*16) - 4) {
-		crc = partial_crc32_one('\0', crc);
-		if (fwrite("\0", 1, 1, dest) != 1)
-			die("Writing padding failed");
-	}
-
 	/* Write the CRC */
 	put_unaligned_le32(crc, buf);
 	if (fwrite(buf, 1, 4, dest) != 4)
--- a/arch/x86/include/asm/barrier.h
+++ b/arch/x86/include/asm/barrier.h
@@ -81,22 +81,4 @@ do {									\

 #include <asm-generic/barrier.h>

-/*
- * Make previous memory operations globally visible before
- * a WRMSR.
- *
- * MFENCE makes writes visible, but only affects load/store
- * instructions.  WRMSR is unfortunately not a load/store
- * instruction and is unaffected by MFENCE.  The LFENCE ensures
- * that the WRMSR is not reordered.
- *
- * Most WRMSRs are full serializing instructions themselves and
- * do not require this barrier.  This is only required for the
- * IA32_TSC_DEADLINE and X2APIC MSRs.
- */
-static inline void weak_wrmsr_fence(void)
-{
-	asm volatile("mfence; lfence" : : : "memory");
-}
-
 #endif /* _ASM_X86_BARRIER_H */
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -168,7 +168,7 @@ extern void clear_cpu_cap(struct cpuinfo_x86 *c, unsigned int bit);
 */
 static __always_inline bool _static_cpu_has(u16 bit)
 {
-	asm_volatile_goto(
+	asm goto(
 		ALTERNATIVE_TERNARY("jmp 6f", %P[feature], "", "jmp %l[t_no]")
 		".pushsection .altinstr_aux,\"ax\"\n"
 		"6:\n"
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -308,10 +308,10 @@
 #define X86_FEATURE_SMBA		(11*32+21) /* "" Slow Memory Bandwidth Allocation */
 #define X86_FEATURE_BMEC		(11*32+22) /* "" Bandwidth Monitoring Event Configuration */
 #define X86_FEATURE_USER_SHSTK		(11*32+23) /* Shadow stack support for user mode applications */
-
 #define X86_FEATURE_SRSO		(11*32+24) /* "" AMD BTB untrain RETs */
 #define X86_FEATURE_SRSO_ALIAS		(11*32+25) /* "" AMD BTB untrain RETs through aliasing */
 #define X86_FEATURE_IBPB_ON_VMEXIT	(11*32+26) /* "" Issue an IBPB only on VMEXIT */
+#define X86_FEATURE_APIC_MSRS_FENCE	(11*32+27) /* "" IA32_TSC_DEADLINE and X2APIC MSRs need fencing */

 /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */
 #define X86_FEATURE_AVX_VNNI		(12*32+ 4) /* AVX VNNI instructions */
--- a/arch/x86/include/asm/jump_label.h
+++ b/arch/x86/include/asm/jump_label.h
@@ -24,7 +24,7 @@

 static __always_inline bool arch_static_branch(struct static_key *key, bool branch)
 {
-	asm_volatile_goto("1:"
+	asm goto("1:"
 		"jmp %l[l_yes] # objtool NOPs this \n\t"
 		JUMP_TABLE_ENTRY
 		: :  "i" (key), "i" (2 | branch) : : l_yes);
@@ -38,7 +38,7 @@ l_yes:

 static __always_inline bool arch_static_branch(struct static_key * const key, const bool branch)
 {
-	asm_volatile_goto("1:"
+	asm goto("1:"
 		".byte " __stringify(BYTES_NOP5) "\n\t"
 		JUMP_TABLE_ENTRY
 		: :  "i" (key), "i" (branch) : : l_yes);
@@ -52,7 +52,7 @@ l_yes:

 static __always_inline bool arch_static_branch_jump(struct static_key * const key, const bool branch)
 {
-	asm_volatile_goto("1:"
+	asm goto("1:"
 		"jmp %l[l_yes]\n\t"
 		JUMP_TABLE_ENTRY
 		: :  "i" (key), "i" (branch) : : l_yes);
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -734,4 +734,22 @@ bool arch_is_platform_page(u64 paddr);

 extern bool gds_ucode_mitigated(void);

+/*
+ * Make previous memory operations globally visible before
+ * a WRMSR.
+ *
+ * MFENCE makes writes visible, but only affects load/store
+ * instructions.  WRMSR is unfortunately not a load/store
+ * instruction and is unaffected by MFENCE.  The LFENCE ensures
+ * that the WRMSR is not reordered.
+ *
+ * Most WRMSRs are full serializing instructions themselves and
+ * do not require this barrier.  This is only required for the
+ * IA32_TSC_DEADLINE and X2APIC MSRs.
+ */
+static inline void weak_wrmsr_fence(void)
+{
+	alternative("mfence; lfence", "", ALT_NOT(X86_FEATURE_APIC_MSRS_FENCE));
+}
+
 #endif /* _ASM_X86_PROCESSOR_H */
--- a/arch/x86/include/asm/rmwcc.h
+++ b/arch/x86/include/asm/rmwcc.h
@@ -13,7 +13,7 @@
 #define __GEN_RMWcc(fullop, _var, cc, clobbers, ...)			\
 ({									\
 	bool c = false;							\
-	asm_volatile_goto (fullop "; j" #cc " %l[cc_label]"		\
+	asm goto (fullop "; j" #cc " %l[cc_label]"		\
 			: : [var] "m" (_var), ## __VA_ARGS__		\
 			: clobbers : cc_label);				\
 	if (0) {							\
--- a/arch/x86/include/asm/special_insns.h
+++ b/arch/x86/include/asm/special_insns.h
@@ -205,7 +205,7 @@ static inline void clwb(volatile void *__p)
 #ifdef CONFIG_X86_USER_SHADOW_STACK
 static inline int write_user_shstk_64(u64 __user *addr, u64 val)
 {
-	asm_volatile_goto("1: wrussq %[val], (%[addr])\n"
+	asm goto("1: wrussq %[val], (%[addr])\n"
 			  _ASM_EXTABLE(1b, %l[fail])
 			  :: [addr] "r" (addr), [val] "r" (val)
 			  :: fail);
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -133,7 +133,7 @@ extern int __get_user_bad(void);

 #ifdef CONFIG_X86_32
 #define __put_user_goto_u64(x, addr, label)			\
-	asm_volatile_goto("\n"					\
+	asm goto("\n"					\
 		     "1:	movl %%eax,0(%1)\n"		\
 		     "2:	movl %%edx,4(%1)\n"		\
 		     _ASM_EXTABLE_UA(1b, %l2)			\
@@ -295,7 +295,7 @@ do {									\
 } while (0)

 #define __get_user_asm(x, addr, itype, ltype, label)			\
-	asm_volatile_goto("\n"						\
+	asm_goto_output("\n"						\
 		     "1:	mov"itype" %[umem],%[output]\n"		\
 		     _ASM_EXTABLE_UA(1b, %l2)				\
 		     : [output] ltype(x)				\
@@ -375,7 +375,7 @@ do {									\
 	__typeof__(_ptr) _old = (__typeof__(_ptr))(_pold);		\
 	__typeof__(*(_ptr)) __old = *_old;				\
 	__typeof__(*(_ptr)) __new = (_new);				\
-	asm_volatile_goto("\n"						\
+	asm_goto_output("\n"						\
 		     "1: " LOCK_PREFIX "cmpxchg"itype" %[new], %[ptr]\n"\
 		     _ASM_EXTABLE_UA(1b, %l[label])			\
 		     : CC_OUT(z) (success),				\
@@ -394,7 +394,7 @@ do {									\
 	__typeof__(_ptr) _old = (__typeof__(_ptr))(_pold);		\
 	__typeof__(*(_ptr)) __old = *_old;				\
 	__typeof__(*(_ptr)) __new = (_new);				\
-	asm_volatile_goto("\n"						\
+	asm_goto_output("\n"						\
 		     "1: " LOCK_PREFIX "cmpxchg8b %[ptr]\n"		\
 		     _ASM_EXTABLE_UA(1b, %l[label])			\
 		     : CC_OUT(z) (success),				\
@@ -477,7 +477,7 @@ struct __large_struct { unsigned long buf[100]; };
 * aliasing issues.
 */
 #define __put_user_goto(x, addr, itype, ltype, label)			\
-	asm_volatile_goto("\n"						\
+	asm goto("\n"							\
 		"1:	mov"itype" %0,%1\n"				\
 		_ASM_EXTABLE_UA(1b, %l2)				\
 		: : ltype(x), "m" (__m(addr))				\
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -1157,6 +1157,9 @@ static void init_amd(struct cpuinfo_x86 *c)
 	if (!cpu_has(c, X86_FEATURE_HYPERVISOR) &&
 	     cpu_has_amd_erratum(c, amd_erratum_1485))
 		msr_set_bit(MSR_ZEN4_BP_CFG, MSR_ZEN4_BP_CFG_SHARED_BTB_FIX_BIT);
+
+	/* AMD CPUs don't need fencing after x2APIC/TSC_DEADLINE MSR writes. */
+	clear_cpu_cap(c, X86_FEATURE_APIC_MSRS_FENCE);
 }

 #ifdef CONFIG_X86_32
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1858,6 +1858,13 @@ static void identify_cpu(struct cpuinfo_x86 *c)
 	c->apicid = apic->phys_pkg_id(c->initial_apicid, 0);
 #endif

+
+	/*
+	 * Set default APIC and TSC_DEADLINE MSR fencing flag. AMD and
+	 * Hygon will clear it in ->c_init() below.
+	 */
+	set_cpu_cap(c, X86_FEATURE_APIC_MSRS_FENCE);
+
 	/*
 	 * Vendor-specific initialization.  In this section we
 	 * canonicalize the feature flags, meaning if there are
--- a/arch/x86/kernel/cpu/hygon.c
+++ b/arch/x86/kernel/cpu/hygon.c
@@ -348,6 +348,9 @@ static void init_hygon(struct cpuinfo_x86 *c)
 		set_cpu_bug(c, X86_BUG_SYSRET_SS_ATTRS);

 	check_null_seg_clears_base(c);
+
+	/* Hygon CPUs don't need fencing after x2APIC/TSC_DEADLINE MSR writes. */
+	clear_cpu_cap(c, X86_FEATURE_APIC_MSRS_FENCE);
 }

 static void cpu_detect_tlb_hygon(struct cpuinfo_x86 *c)
--- a/arch/x86/kernel/fpu/signal.c
+++ b/arch/x86/kernel/fpu/signal.c
@@ -274,12 +274,13 @@ static int __restore_fpregs_from_user(void __user *buf, u64 ufeatures,
 * Attempt to restore the FPU registers directly from user memory.
 * Pagefaults are handled and any errors returned are fatal.
 */
-static bool restore_fpregs_from_user(void __user *buf, u64 xrestore,
-				     bool fx_only, unsigned int size)
+static bool restore_fpregs_from_user(void __user *buf, u64 xrestore, bool fx_only)
 {
 	struct fpu *fpu = &current->thread.fpu;
 	int ret;

+	/* Restore enabled features only. */
+	xrestore &= fpu->fpstate->user_xfeatures;
 retry:
 	fpregs_lock();
 	/* Ensure that XFD is up to date */
@@ -309,7 +310,7 @@ retry:
 		if (ret != X86_TRAP_PF)
 			return false;

-		if (!fault_in_readable(buf, size))
+		if (!fault_in_readable(buf, fpu->fpstate->user_size))
 			goto retry;
 		return false;
 	}
@@ -339,7 +340,6 @@ static bool __fpu_restore_sig(void __user *buf, void __user *buf_fx,
 	struct user_i387_ia32_struct env;
 	bool success, fx_only = false;
 	union fpregs_state *fpregs;
-	unsigned int state_size;
 	u64 user_xfeatures = 0;

 	if (use_xsave()) {
@@ -349,17 +349,14 @@ static bool __fpu_restore_sig(void __user *buf, void __user *buf_fx,
 			return false;

 		fx_only = !fx_sw_user.magic1;
-		state_size = fx_sw_user.xstate_size;
 		user_xfeatures = fx_sw_user.xfeatures;
 	} else {
 		user_xfeatures = XFEATURE_MASK_FPSSE;
-		state_size = fpu->fpstate->user_size;
 	}

 	if (likely(!ia32_fxstate)) {
 		/* Restore the FPU registers directly from user memory. */
-		return restore_fpregs_from_user(buf_fx, user_xfeatures, fx_only,
-						state_size);
+		return restore_fpregs_from_user(buf_fx, user_xfeatures, fx_only);
 	}

 	/*
--- a/arch/x86/kvm/svm/svm_ops.h
+++ b/arch/x86/kvm/svm/svm_ops.h
@@ -8,7 +8,7 @@

 #define svm_asm(insn, clobber...)				\
 do {								\
-	asm_volatile_goto("1: " __stringify(insn) "\n\t"	\
+	asm goto("1: " __stringify(insn) "\n\t"	\
 			  _ASM_EXTABLE(1b, %l[fault])		\
 			  ::: clobber : fault);			\
 	return;							\
@@ -18,7 +18,7 @@ fault:								\

 #define svm_asm1(insn, op1, clobber...)				\
 do {								\
-	asm_volatile_goto("1: "  __stringify(insn) " %0\n\t"	\
+	asm goto("1: "  __stringify(insn) " %0\n\t"	\
 			  _ASM_EXTABLE(1b, %l[fault])		\
 			  :: op1 : clobber : fault);		\
 	return;							\
@@ -28,7 +28,7 @@ fault:								\

 #define svm_asm2(insn, op1, op2, clobber...)				\
 do {									\
-	asm_volatile_goto("1: "  __stringify(insn) " %1, %0\n\t"	\
+	asm goto("1: "  __stringify(insn) " %1, %0\n\t"	\
 			  _ASM_EXTABLE(1b, %l[fault])			\
 			  :: op1, op2 : clobber : fault);		\
 	return;								\
--- a/arch/x86/kvm/vmx/pmu_intel.c
+++ b/arch/x86/kvm/vmx/pmu_intel.c
@@ -71,7 +71,7 @@ static int fixed_pmc_events[] = {
 static void reprogram_fixed_counters(struct kvm_pmu *pmu, u64 data)
 {
 	struct kvm_pmc *pmc;
-	u8 old_fixed_ctr_ctrl = pmu->fixed_ctr_ctrl;
+	u64 old_fixed_ctr_ctrl = pmu->fixed_ctr_ctrl;
 	int i;

 	pmu->fixed_ctr_ctrl = data;
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -745,7 +745,7 @@ static int vmx_set_guest_uret_msr(struct vcpu_vmx *vmx,
 */
 static int kvm_cpu_vmxoff(void)
 {
-	asm_volatile_goto("1: vmxoff\n\t"
+	asm goto("1: vmxoff\n\t"
 			  _ASM_EXTABLE(1b, %l[fault])
 			  ::: "cc", "memory" : fault);

@@ -2789,7 +2789,7 @@ static int kvm_cpu_vmxon(u64 vmxon_pointer)

 	cr4_set_bits(X86_CR4_VMXE);

-	asm_volatile_goto("1: vmxon %[vmxon_pointer]\n\t"
+	asm goto("1: vmxon %[vmxon_pointer]\n\t"
 			  _ASM_EXTABLE(1b, %l[fault])
 			  : : [vmxon_pointer] "m"(vmxon_pointer)
 			  : : fault);
--- a/arch/x86/kvm/vmx/vmx_ops.h
+++ b/arch/x86/kvm/vmx/vmx_ops.h
@@ -94,7 +94,7 @@ static __always_inline unsigned long __vmcs_readl(unsigned long field)

 #ifdef CONFIG_CC_HAS_ASM_GOTO_OUTPUT

-	asm_volatile_goto("1: vmread %[field], %[output]\n\t"
+	asm_goto_output("1: vmread %[field], %[output]\n\t"
 			  "jna %l[do_fail]\n\t"

 			  _ASM_EXTABLE(1b, %l[do_exception])
@@ -188,7 +188,7 @@ static __always_inline unsigned long vmcs_readl(unsigned long field)

 #define vmx_asm1(insn, op1, error_args...)				\
 do {									\
-	asm_volatile_goto("1: " __stringify(insn) " %0\n\t"		\
+	asm goto("1: " __stringify(insn) " %0\n\t"			\
 			  ".byte 0x2e\n\t" /* branch not taken hint */	\
 			  "jna %l[error]\n\t"				\
 			  _ASM_EXTABLE(1b, %l[fault])			\
@@ -205,7 +205,7 @@ fault:									\

 #define vmx_asm2(insn, op1, op2, error_args...)				\
 do {									\
-	asm_volatile_goto("1: "  __stringify(insn) " %1, %0\n\t"	\
+	asm goto("1: "  __stringify(insn) " %1, %0\n\t"			\
 			  ".byte 0x2e\n\t" /* branch not taken hint */	\
 			  "jna %l[error]\n\t"				\
 			  _ASM_EXTABLE(1b, %l[fault])			\
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -5300,7 +5300,8 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
 	if (events->flags & KVM_VCPUEVENT_VALID_NMI_PENDING) {
 		vcpu->arch.nmi_pending = 0;
 		atomic_set(&vcpu->arch.nmi_queued, events->nmi.pending);
-		kvm_make_request(KVM_REQ_NMI, vcpu);
+		if (events->nmi.pending)
+			kvm_make_request(KVM_REQ_NMI, vcpu);
 	}
 	static_call(kvm_x86_set_nmi_mask)(vcpu, events->nmi.masked);

--- a/arch/x86/mm/ident_map.c
+++ b/arch/x86/mm/ident_map.c
@@ -26,18 +26,31 @@ static int ident_pud_init(struct x86_mapping_info *info, pud_t *pud_page,
 	for (; addr < end; addr = next) {
 		pud_t *pud = pud_page + pud_index(addr);
 		pmd_t *pmd;
+		bool use_gbpage;

 		next = (addr & PUD_MASK) + PUD_SIZE;
 		if (next > end)
 			next = end;

-		if (info->direct_gbpages) {
+		/* if this is already a gbpage, this portion is already mapped */
+		if (pud_large(*pud))
+			continue;
+
+		/* Is using a gbpage allowed? */
+		use_gbpage = info->direct_gbpages;
+
+		/* Don't use gbpage if it maps more than the requested region. */
+		/* at the begining: */
+		use_gbpage &= ((addr & ~PUD_MASK) == 0);
+		/* ... or at the end: */
+		use_gbpage &= ((next & ~PUD_MASK) == 0);
+
+		/* Never overwrite existing mappings */
+		use_gbpage &= !pud_present(*pud);
+
+		if (use_gbpage) {
 			pud_t pudval;

-			if (pud_present(*pud))
-				continue;
-
-			addr &= PUD_MASK;
 			pudval = __pud((addr - info->offset) | info->page_flag);
 			set_pud(pud, pudval);
 			continue;
--- a/arch/xtensa/include/asm/jump_label.h
+++ b/arch/xtensa/include/asm/jump_label.h
@@ -13,7 +13,7 @@
 static __always_inline bool arch_static_branch(struct static_key *key,
 					       bool branch)
 {
-	asm_volatile_goto("1:\n\t"
+	asm goto("1:\n\t"
 			  "_nop\n\t"
 			  ".pushsection __jump_table,  \"aw\"\n\t"
 			  ".word 1b, %l[l_yes], %c0\n\t"
@@ -38,7 +38,7 @@ static __always_inline bool arch_static_branch_jump(struct static_key *key,
 	 * make it reachable and wrap both into a no-transform block
 	 * to avoid any assembler interference with this.
 	 */
-	asm_volatile_goto("1:\n\t"
+	asm goto("1:\n\t"
 			  ".begin no-transform\n\t"
 			  "_j %l[l_yes]\n\t"
 			  "2:\n\t"
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -767,11 +767,16 @@ static void req_bio_endio(struct request *rq, struct bio *bio,
 		/*
 		 * Partial zone append completions cannot be supported as the
 		 * BIO fragments may end up not being written sequentially.
+		 * For such case, force the completed nbytes to be equal to
+		 * the BIO size so that bio_advance() sets the BIO remaining
+		 * size to 0 and we end up calling bio_endio() before returning.
 		 */
-		if (bio->bi_iter.bi_size != nbytes)
+		if (bio->bi_iter.bi_size != nbytes) {
 			bio->bi_status = BLK_STS_IOERR;
-		else
+			nbytes = bio->bi_iter.bi_size;
+		} else {
 			bio->bi_iter.bi_sector = rq->__sector;
+		}
 	}

 	bio_advance(bio, nbytes);
--- a/block/blk-wbt.c
+++ b/block/blk-wbt.c
@@ -165,9 +165,9 @@ static void wb_timestamp(struct rq_wb *rwb, unsigned long *var)
 */
 static bool wb_recent_wait(struct rq_wb *rwb)
 {
-	struct bdi_writeback *wb = &rwb->rqos.disk->bdi->wb;
+	struct backing_dev_info *bdi = rwb->rqos.disk->bdi;

-	return time_before(jiffies, wb->dirty_sleep + HZ);
+	return time_before(jiffies, bdi->last_bdp_sleep + HZ);
 }

 static inline struct rq_wait *get_rq_wait(struct rq_wb *rwb,
--- a/crypto/algif_hash.c
+++ b/crypto/algif_hash.c
@@ -91,13 +91,13 @@ static int hash_sendmsg(struct socket *sock, struct msghdr *msg,
 		if (!(msg->msg_flags & MSG_MORE)) {
 			err = hash_alloc_result(sk, ctx);
 			if (err)
-				goto unlock_free;
+				goto unlock_free_result;
 			ahash_request_set_crypt(&ctx->req, NULL,
 						ctx->result, 0);
 			err = crypto_wait_req(crypto_ahash_final(&ctx->req),
 					      &ctx->wait);
 			if (err)
-				goto unlock_free;
+				goto unlock_free_result;
 		}
 		goto done_more;
 	}
@@ -170,6 +170,7 @@ unlock:

 unlock_free:
 	af_alg_free_sg(&ctx->sgl);
+unlock_free_result:
 	hash_free_result(sk, ctx);
 	ctx->more = false;
 	goto unlock;
--- a/drivers/android/binder.c
+++ b/drivers/android/binder.c
@@ -478,6 +478,16 @@ binder_enqueue_thread_work_ilocked(struct binder_thread *thread,
 {
 	WARN_ON(!list_empty(&thread->waiting_thread_node));
 	binder_enqueue_work_ilocked(work, &thread->todo);
+
+	/* (e)poll-based threads require an explicit wakeup signal when
+	 * queuing their own work; they rely on these events to consume
+	 * messages without I/O block. Without it, threads risk waiting
+	 * indefinitely without handling the work.
+	 */
+	if (thread->looper & BINDER_LOOPER_STATE_POLL &&
+	    thread->pid == current->pid && !thread->process_todo)
+		wake_up_interruptible_sync(&thread->wait);
+
 	thread->process_todo = true;
 }

--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -283,10 +283,12 @@ static bool device_is_ancestor(struct device *dev, struct device *target)
 	return false;
 }

+#define DL_MARKER_FLAGS		(DL_FLAG_INFERRED | \
+				 DL_FLAG_CYCLE | \
+				 DL_FLAG_MANAGED)
 static inline bool device_link_flag_is_sync_state_only(u32 flags)
 {
-	return (flags & ~(DL_FLAG_INFERRED | DL_FLAG_CYCLE)) ==
-		(DL_FLAG_SYNC_STATE_ONLY | DL_FLAG_MANAGED);
+	return (flags & ~DL_MARKER_FLAGS) == DL_FLAG_SYNC_STATE_ONLY;
 }

 /**
@@ -2057,9 +2059,14 @@ static int fw_devlink_create_devlink(struct device *con,

 	/*
 	 * SYNC_STATE_ONLY device links don't block probing and supports cycles.
-	 * So cycle detection isn't necessary and shouldn't be done.
+	 * So, one might expect that cycle detection isn't necessary for them.
+	 * However, if the device link was marked as SYNC_STATE_ONLY because
+	 * it's part of a cycle, then we still need to do cycle detection. This
+	 * is because the consumer and supplier might be part of multiple cycles
+	 * and we need to detect all those cycles.
 	 */
-	if (!(flags & DL_FLAG_SYNC_STATE_ONLY)) {
+	if (!device_link_flag_is_sync_state_only(flags) ||
+	    flags & DL_FLAG_CYCLE) {
 		device_links_write_lock();
 		if (__fw_devlink_relax_cycles(con, sup_handle)) {
 			__fwnode_link_cycle(link);
--- a/drivers/base/power/domain.c
+++ b/drivers/base/power/domain.c
@@ -1102,7 +1102,7 @@ static int __init genpd_power_off_unused(void)

 	return 0;
 }
-late_initcall(genpd_power_off_unused);
+late_initcall_sync(genpd_power_off_unused);

 #ifdef CONFIG_PM_SLEEP

--- a/drivers/connector/cn_proc.c
+++ b/drivers/connector/cn_proc.c
@@ -108,9 +108,8 @@ static inline void send_msg(struct cn_msg *msg)
 		filter_data[1] = 0;
 	}

-	if (cn_netlink_send_mult(msg, msg->len, 0, CN_IDX_PROC, GFP_NOWAIT,
-			     cn_filter, (void *)filter_data) == -ESRCH)
-		atomic_set(&proc_event_num_listeners, 0);
+	cn_netlink_send_mult(msg, msg->len, 0, CN_IDX_PROC, GFP_NOWAIT,
+			     cn_filter, (void *)filter_data);

 	local_unlock(&local_event.lock);
 }
--- a/drivers/crypto/ccp/sev-dev.c
+++ b/drivers/crypto/ccp/sev-dev.c
@@ -520,10 +520,16 @@ EXPORT_SYMBOL_GPL(sev_platform_init);

 static int __sev_platform_shutdown_locked(int *error)
 {
-	struct sev_device *sev = psp_master->sev_data;
+	struct psp_device *psp = psp_master;
+	struct sev_device *sev;
 	int ret;

-	if (!sev || sev->state == SEV_STATE_UNINIT)
+	if (!psp || !psp->sev_data)
+		return 0;
+
+	sev = psp->sev_data;
+
+	if (sev->state == SEV_STATE_UNINIT)
 		return 0;

 	ret = __sev_do_cmd_locked(SEV_CMD_SHUTDOWN, NULL, error);
--- a/drivers/firewire/core-device.c
+++ b/drivers/firewire/core-device.c
@@ -100,10 +100,9 @@ static int textual_leaf_to_string(const u32 *block, char *buf, size_t size)
 * @buf:	where to put the string
 * @size:	size of @buf, in bytes
 *
- * The string is taken from a minimal ASCII text descriptor leaf after
- * the immediate entry with @key.  The string is zero-terminated.
- * An overlong string is silently truncated such that it and the
- * zero byte fit into @size.
+ * The string is taken from a minimal ASCII text descriptor leaf just after the entry with the
+ * @key. The string is zero-terminated. An overlong string is silently truncated such that it
+ * and the zero byte fit into @size.
 *
 * Returns strlen(buf) or a negative error code.
 */
--- a/drivers/firmware/efi/libstub/Makefile
+++ b/drivers/firmware/efi/libstub/Makefile
@@ -108,13 +108,6 @@ lib-y				:= $(patsubst %.o,%.stub.o,$(lib-y))
 # https://bugs.llvm.org/show_bug.cgi?id=46480
 STUBCOPY_FLAGS-y		+= --remove-section=.note.gnu.property

-#
-# For x86, bootloaders like systemd-boot or grub-efi do not zero-initialize the
-# .bss section, so the .bss section of the EFI stub needs to be included in the
-# .data section of the compressed kernel to ensure initialization. Rename the
-# .bss section here so it's easy to pick out in the linker script.
-#
-STUBCOPY_FLAGS-$(CONFIG_X86)	+= --rename-section .bss=.bss.efistub,load,alloc
 STUBCOPY_RELOC-$(CONFIG_X86_32)	:= R_386_32
 STUBCOPY_RELOC-$(CONFIG_X86_64)	:= R_X86_64_64

--- a/drivers/firmware/efi/libstub/x86-stub.c
+++ b/drivers/firmware/efi/libstub/x86-stub.c
@@ -458,9 +458,8 @@ void __noreturn efi_stub_entry(efi_handle_t handle,
 efi_status_t __efiapi efi_pe_entry(efi_handle_t handle,
 				   efi_system_table_t *sys_table_arg)
 {
-	struct boot_params *boot_params;
-	struct setup_header *hdr;
-	void *image_base;
+	static struct boot_params boot_params __page_aligned_bss;
+	struct setup_header *hdr = &boot_params.hdr;
 	efi_guid_t proto = LOADED_IMAGE_PROTOCOL_GUID;
 	int options_size = 0;
 	efi_status_t status;
@@ -478,30 +477,9 @@ efi_status_t __efiapi efi_pe_entry(efi_handle_t handle,
 		efi_exit(handle, status);
 	}

-	image_base = efi_table_attr(image, image_base);
-
-	status = efi_allocate_pages(sizeof(struct boot_params),
-				    (unsigned long *)&boot_params, ULONG_MAX);
-	if (status != EFI_SUCCESS) {
-		efi_err("Failed to allocate lowmem for boot params\n");
-		efi_exit(handle, status);
-	}
-
-	memset(boot_params, 0x0, sizeof(struct boot_params));
-
-	hdr = &boot_params->hdr;
-
-	/* Copy the setup header from the second sector to boot_params */
-	memcpy(&hdr->jump, image_base + 512,
-	       sizeof(struct setup_header) - offsetof(struct setup_header, jump));
-
-	/*
-	 * Fill out some of the header fields ourselves because the
-	 * EFI firmware loader doesn't load the first sector.
-	 */
+	/* Assign the setup_header fields that the kernel actually cares about */
 	hdr->root_flags	= 1;
 	hdr->vid_mode	= 0xffff;
-	hdr->boot_flag	= 0xAA55;

 	hdr->type_of_loader = 0x21;

@@ -510,25 +488,13 @@ efi_status_t __efiapi efi_pe_entry(efi_handle_t handle,
 	if (!cmdline_ptr)
 		goto fail;

-	efi_set_u64_split((unsigned long)cmdline_ptr,
-			  &hdr->cmd_line_ptr, &boot_params->ext_cmd_line_ptr);
+	efi_set_u64_split((unsigned long)cmdline_ptr, &hdr->cmd_line_ptr,
+			  &boot_params.ext_cmd_line_ptr);

-	hdr->ramdisk_image = 0;
-	hdr->ramdisk_size = 0;
-
-	/*
-	 * Disregard any setup data that was provided by the bootloader:
-	 * setup_data could be pointing anywhere, and we have no way of
-	 * authenticating or validating the payload.
-	 */
-	hdr->setup_data = 0;
-
-	efi_stub_entry(handle, sys_table_arg, boot_params);
+	efi_stub_entry(handle, sys_table_arg, &boot_params);
 	/* not reached */

 fail:
-	efi_free(sizeof(struct boot_params), (unsigned long)boot_params);
-
 	efi_exit(handle, status);
 }

--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -4133,7 +4133,6 @@ int amdgpu_device_suspend(struct drm_device *dev, bool fbcon)
 		drm_fb_helper_set_suspend_unlocked(adev_to_drm(adev)->fb_helper, true);

 	cancel_delayed_work_sync(&adev->delayed_init_work);
-	flush_delayed_work(&adev->gfx.gfx_off_delay_work);

 	amdgpu_ras_suspend(adev);

--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
@@ -702,8 +702,15 @@ void amdgpu_gfx_off_ctrl(struct amdgpu_device *adev, bool enable)

 		if (adev->gfx.gfx_off_req_count == 0 &&
 		    !adev->gfx.gfx_off_state) {
-			schedule_delayed_work(&adev->gfx.gfx_off_delay_work,
+			/* If going to s2idle, no need to wait */
+			if (adev->in_s0ix) {
+				if (!amdgpu_dpm_set_powergating_by_smu(adev,
+						AMD_IP_BLOCK_TYPE_GFX, true))
+					adev->gfx.gfx_off_state = true;
+			} else {
+				schedule_delayed_work(&adev->gfx.gfx_off_delay_work,
 					      delay);
+			}
 		}
 	} else {
 		if (adev->gfx.gfx_off_req_count == 0) {
--- a/drivers/gpu/drm/amd/amdgpu/cik_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/cik_ih.c
@@ -204,6 +204,12 @@ static u32 cik_ih_get_wptr(struct amdgpu_device *adev,
 		tmp = RREG32(mmIH_RB_CNTL);
 		tmp |= IH_RB_CNTL__WPTR_OVERFLOW_CLEAR_MASK;
 		WREG32(mmIH_RB_CNTL, tmp);
+
+		/* Unset the CLEAR_OVERFLOW bit immediately so new overflows
+		 * can be detected.
+		 */
+		tmp &= ~IH_RB_CNTL__WPTR_OVERFLOW_CLEAR_MASK;
+		WREG32(mmIH_RB_CNTL, tmp);
 	}
 	return (wptr & ih->ptr_mask);
 }
--- a/drivers/gpu/drm/amd/amdgpu/cz_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/cz_ih.c
@@ -216,6 +216,11 @@ static u32 cz_ih_get_wptr(struct amdgpu_device *adev,
 	tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 1);
 	WREG32(mmIH_RB_CNTL, tmp);

+	/* Unset the CLEAR_OVERFLOW bit immediately so new overflows
+	 * can be detected.
+	 */
+	tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 0);
+	WREG32(mmIH_RB_CNTL, tmp);

 out:
 	return (wptr & ih->ptr_mask);
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
@@ -4020,8 +4020,6 @@ static int gfx_v10_0_init_microcode(struct amdgpu_device *adev)
 		err = 0;
 		adev->gfx.mec2_fw = NULL;
 	}
-	amdgpu_gfx_cp_init_microcode(adev, AMDGPU_UCODE_ID_CP_MEC2);
-	amdgpu_gfx_cp_init_microcode(adev, AMDGPU_UCODE_ID_CP_MEC2_JT);

 	gfx_v10_0_check_fw_write_wait(adev);
 out:
--- a/drivers/gpu/drm/amd/amdgpu/iceland_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/iceland_ih.c
@@ -215,6 +215,11 @@ static u32 iceland_ih_get_wptr(struct amdgpu_device *adev,
 	tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 1);
 	WREG32(mmIH_RB_CNTL, tmp);

+	/* Unset the CLEAR_OVERFLOW bit immediately so new overflows
+	 * can be detected.
+	 */
+	tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 0);
+	WREG32(mmIH_RB_CNTL, tmp);

 out:
 	return (wptr & ih->ptr_mask);
--- a/drivers/gpu/drm/amd/amdgpu/ih_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/ih_v6_0.c
@@ -418,6 +418,12 @@ static u32 ih_v6_0_get_wptr(struct amdgpu_device *adev,
 	tmp = RREG32_NO_KIQ(ih_regs->ih_rb_cntl);
 	tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 1);
 	WREG32_NO_KIQ(ih_regs->ih_rb_cntl, tmp);
+
+	/* Unset the CLEAR_OVERFLOW bit immediately so new overflows
+	 * can be detected.
+	 */
+	tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 0);
+	WREG32_NO_KIQ(ih_regs->ih_rb_cntl, tmp);
 out:
 	return (wptr & ih->ptr_mask);
 }
--- a/drivers/gpu/drm/amd/amdgpu/ih_v6_1.c
+++ b/drivers/gpu/drm/amd/amdgpu/ih_v6_1.c
@@ -418,6 +418,13 @@ static u32 ih_v6_1_get_wptr(struct amdgpu_device *adev,
 	tmp = RREG32_NO_KIQ(ih_regs->ih_rb_cntl);
 	tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 1);
 	WREG32_NO_KIQ(ih_regs->ih_rb_cntl, tmp);
+
+	/* Unset the CLEAR_OVERFLOW bit immediately so new overflows
+	 * can be detected.
+	 */
+	tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 0);
+	WREG32_NO_KIQ(ih_regs->ih_rb_cntl, tmp);
+
 out:
 	return (wptr & ih->ptr_mask);
 }
--- a/drivers/gpu/drm/amd/amdgpu/navi10_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/navi10_ih.c
@@ -442,6 +442,12 @@ static u32 navi10_ih_get_wptr(struct amdgpu_device *adev,
 	tmp = RREG32_NO_KIQ(ih_regs->ih_rb_cntl);
 	tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 1);
 	WREG32_NO_KIQ(ih_regs->ih_rb_cntl, tmp);
+
+	/* Unset the CLEAR_OVERFLOW bit immediately so new overflows
+	 * can be detected.
+	 */
+	tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 0);
+	WREG32_NO_KIQ(ih_regs->ih_rb_cntl, tmp);
 out:
 	return (wptr & ih->ptr_mask);
 }
--- a/drivers/gpu/drm/amd/amdgpu/si_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/si_ih.c
@@ -119,6 +119,12 @@ static u32 si_ih_get_wptr(struct amdgpu_device *adev,
 		tmp = RREG32(IH_RB_CNTL);
 		tmp |= IH_RB_CNTL__WPTR_OVERFLOW_CLEAR_MASK;
 		WREG32(IH_RB_CNTL, tmp);
+
+		/* Unset the CLEAR_OVERFLOW bit immediately so new overflows
+		 * can be detected.
+		 */
+		tmp &= ~IH_RB_CNTL__WPTR_OVERFLOW_CLEAR_MASK;
+		WREG32(IH_RB_CNTL, tmp);
 	}
 	return (wptr & ih->ptr_mask);
 }
--- a/drivers/gpu/drm/amd/amdgpu/soc21.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc21.c
@@ -50,13 +50,13 @@ static const struct amd_ip_funcs soc21_common_ip_funcs;
 /* SOC21 */
 static const struct amdgpu_video_codec_info vcn_4_0_0_video_codecs_encode_array_vcn0[] = {
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 2304, 0)},
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 4096, 2304, 0)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 0)},
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_AV1, 8192, 4352, 0)},
 };

 static const struct amdgpu_video_codec_info vcn_4_0_0_video_codecs_encode_array_vcn1[] = {
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 2304, 0)},
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 4096, 2304, 0)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 0)},
 };

 static const struct amdgpu_video_codecs vcn_4_0_0_video_codecs_encode_vcn0 = {
--- a/drivers/gpu/drm/amd/amdgpu/tonga_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/tonga_ih.c
@@ -219,6 +219,12 @@ static u32 tonga_ih_get_wptr(struct amdgpu_device *adev,
 	tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 1);
 	WREG32(mmIH_RB_CNTL, tmp);

+	/* Unset the CLEAR_OVERFLOW bit immediately so new overflows
+	 * can be detected.
+	 */
+	tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 0);
+	WREG32(mmIH_RB_CNTL, tmp);
+
 out:
 	return (wptr & ih->ptr_mask);
 }
--- a/drivers/gpu/drm/amd/amdgpu/vega10_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/vega10_ih.c
@@ -373,6 +373,12 @@ static u32 vega10_ih_get_wptr(struct amdgpu_device *adev,
 	tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 1);
 	WREG32_NO_KIQ(ih_regs->ih_rb_cntl, tmp);

+	/* Unset the CLEAR_OVERFLOW bit immediately so new overflows
+	 * can be detected.
+	 */
+	tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 0);
+	WREG32_NO_KIQ(ih_regs->ih_rb_cntl, tmp);
+
 out:
 	return (wptr & ih->ptr_mask);
 }
--- a/drivers/gpu/drm/amd/amdgpu/vega20_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/vega20_ih.c
@@ -421,6 +421,12 @@ static u32 vega20_ih_get_wptr(struct amdgpu_device *adev,
 	tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 1);
 	WREG32_NO_KIQ(ih_regs->ih_rb_cntl, tmp);

+	/* Unset the CLEAR_OVERFLOW bit immediately so new overflows
+	 * can be detected.
+	 */
+	tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 0);
+	WREG32_NO_KIQ(ih_regs->ih_rb_cntl, tmp);
+
 out:
 	return (wptr & ih->ptr_mask);
 }
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -6072,7 +6072,9 @@ create_stream_for_sink(struct amdgpu_dm_connector *aconnector,
 		if (recalculate_timing) {
 			freesync_mode = get_highest_refresh_rate_mode(aconnector, false);
 			drm_mode_copy(&saved_mode, &mode);
+			saved_mode.picture_aspect_ratio = mode.picture_aspect_ratio;
 			drm_mode_copy(&mode, freesync_mode);
+			mode.picture_aspect_ratio = saved_mode.picture_aspect_ratio;
 		} else {
 			decide_crtc_timing_for_drm_display_mode(
 					&mode, preferred_mode, scale);
@@ -10358,11 +10360,13 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev,
 			goto fail;
 		}

-		ret = compute_mst_dsc_configs_for_state(state, dm_state->context, vars);
-		if (ret) {
-			DRM_DEBUG_DRIVER("compute_mst_dsc_configs_for_state() failed\n");
-			ret = -EINVAL;
-			goto fail;
+		if (dc_resource_is_dsc_encoding_supported(dc)) {
+			ret = compute_mst_dsc_configs_for_state(state, dm_state->context, vars);
+			if (ret) {
+				DRM_DEBUG_DRIVER("compute_mst_dsc_configs_for_state() failed\n");
+				ret = -EINVAL;
+				goto fail;
+			}
 		}

 		ret = dm_update_mst_vcpi_slots_for_dsc(state, dm_state->context, vars);
--- a/Show More
+++ b/Show More