diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c
index 18d8f17f755c..0904f5676e4d 100644
--- a/arch/x86/entry/common.c
+++ b/arch/x86/entry/common.c
@@ -73,10 +73,8 @@ static __always_inline void do_syscall_32_irqs_on(struct pt_regs *regs,
 						  unsigned int nr)
 {
 	if (likely(nr < IA32_NR_syscalls)) {
-		instrumentation_begin();
 		nr = array_index_nospec(nr, IA32_NR_syscalls);
 		regs->ax = ia32_sys_call_table[nr](regs);
-		instrumentation_end();
 	}
 }
 
@@ -91,8 +89,11 @@ __visible noinstr void do_int80_syscall_32(struct pt_regs *regs)
 	 * or may not be necessary, but it matches the old asm behavior.
 	 */
 	nr = (unsigned int)syscall_enter_from_user_mode(regs, nr);
+	instrumentation_begin();
 
 	do_syscall_32_irqs_on(regs, nr);
+
+	instrumentation_end();
 	syscall_exit_to_user_mode(regs);
 }
 
@@ -121,11 +122,12 @@ static noinstr bool __do_fast_syscall_32(struct pt_regs *regs)
 		res = get_user(*(u32 *)&regs->bp,
 		       (u32 __user __force *)(unsigned long)(u32)regs->sp);
 	}
-	instrumentation_end();
 
 	if (res) {
 		/* User code screwed up. */
 		regs->ax = -EFAULT;
+
+		instrumentation_end();
 		syscall_exit_to_user_mode(regs);
 		return false;
 	}
@@ -135,6 +137,8 @@ static noinstr bool __do_fast_syscall_32(struct pt_regs *regs)
 
 	/* Now this is just like a normal syscall. */
 	do_syscall_32_irqs_on(regs, nr);
+
+	instrumentation_end();
 	syscall_exit_to_user_mode(regs);
 	return true;
 }
diff --git a/arch/x86/include/asm/fpu/api.h b/arch/x86/include/asm/fpu/api.h
index a5aba4ab0224..67a4f1cb2aac 100644
--- a/arch/x86/include/asm/fpu/api.h
+++ b/arch/x86/include/asm/fpu/api.h
@@ -16,14 +16,25 @@
  * Use kernel_fpu_begin/end() if you intend to use FPU in kernel context. It
  * disables preemption so be careful if you intend to use it for long periods
  * of time.
- * If you intend to use the FPU in softirq you need to check first with
+ * If you intend to use the FPU in irq/softirq you need to check first with
  * irq_fpu_usable() if it is possible.
  */
-extern void kernel_fpu_begin(void);
+
+/* Kernel FPU states to initialize in kernel_fpu_begin_mask() */
+#define KFPU_387	_BITUL(0)	/* 387 state will be initialized */
+#define KFPU_MXCSR	_BITUL(1)	/* MXCSR will be initialized */
+
+extern void kernel_fpu_begin_mask(unsigned int kfpu_mask);
 extern void kernel_fpu_end(void);
 extern bool irq_fpu_usable(void);
 extern void fpregs_mark_activate(void);
 
+/* Code that is unaware of kernel_fpu_begin_mask() can use this */
+static inline void kernel_fpu_begin(void)
+{
+	kernel_fpu_begin_mask(KFPU_387 | KFPU_MXCSR);
+}
+
 /*
  * Use fpregs_lock() while editing CPU's FPU registers or fpu->state.
  * A context switch will (and softirq might) save CPU's FPU registers to
diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h
index 5e658ba2654a..9abe842dbd84 100644
--- a/arch/x86/include/asm/intel-family.h
+++ b/arch/x86/include/asm/intel-family.h
@@ -97,6 +97,7 @@
 
 #define	INTEL_FAM6_LAKEFIELD		0x8A
 #define INTEL_FAM6_ALDERLAKE		0x97
+#define INTEL_FAM6_ALDERLAKE_L		0x9A
 
 /* "Small Core" Processors (Atom) */
 
diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h
index 0b4920a7238e..e16cccdd0420 100644
--- a/arch/x86/include/asm/msr.h
+++ b/arch/x86/include/asm/msr.h
@@ -86,7 +86,7 @@ static inline void do_trace_rdpmc(unsigned int msr, u64 val, int failed) {}
  * think of extending them - you will be slapped with a stinking trout or a frozen
  * shark will reach you, wherever you are! You've been warned.
  */
-static inline unsigned long long notrace __rdmsr(unsigned int msr)
+static __always_inline unsigned long long __rdmsr(unsigned int msr)
 {
 	DECLARE_ARGS(val, low, high);
 
@@ -98,7 +98,7 @@ static inline unsigned long long notrace __rdmsr(unsigned int msr)
 	return EAX_EDX_VAL(val, low, high);
 }
 
-static inline void notrace __wrmsr(unsigned int msr, u32 low, u32 high)
+static __always_inline void __wrmsr(unsigned int msr, u32 low, u32 high)
 {
 	asm volatile("1: wrmsr\n"
 		     "2:\n"
diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index 488a8e848754..9239399e5491 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -110,6 +110,8 @@ extern const struct cpumask *cpu_coregroup_mask(int cpu);
 #define topology_die_id(cpu)			(cpu_data(cpu).cpu_die_id)
 #define topology_core_id(cpu)			(cpu_data(cpu).cpu_core_id)
 
+extern unsigned int __max_die_per_package;
+
 #ifdef CONFIG_SMP
 #define topology_die_cpumask(cpu)		(per_cpu(cpu_die_map, cpu))
 #define topology_core_cpumask(cpu)		(per_cpu(cpu_core_map, cpu))
@@ -118,8 +120,6 @@ extern const struct cpumask *cpu_coregroup_mask(int cpu);
 extern unsigned int __max_logical_packages;
 #define topology_max_packages()			(__max_logical_packages)
 
-extern unsigned int __max_die_per_package;
-
 static inline int topology_max_die_per_package(void)
 {
 	return __max_die_per_package;
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index f8ca66f3d861..347a956f71ca 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -542,12 +542,12 @@ static void bsp_init_amd(struct cpuinfo_x86 *c)
 		u32 ecx;
 
 		ecx = cpuid_ecx(0x8000001e);
-		nodes_per_socket = ((ecx >> 8) & 7) + 1;
+		__max_die_per_package = nodes_per_socket = ((ecx >> 8) & 7) + 1;
 	} else if (boot_cpu_has(X86_FEATURE_NODEID_MSR)) {
 		u64 value;
 
 		rdmsrl(MSR_FAM10H_NODE_ID, value);
-		nodes_per_socket = ((value >> 3) & 7) + 1;
+		__max_die_per_package = nodes_per_socket = ((value >> 3) & 7) + 1;
 	}
 
 	if (!boot_cpu_has(X86_FEATURE_AMD_SSBD) &&
diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index 13d3f1cbda17..e133ce1e562b 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -1992,10 +1992,9 @@ static __always_inline void exc_machine_check_kernel(struct pt_regs *regs)
 	 * that out because it's an indirect call. Annotate it.
 	 */
 	instrumentation_begin();
-	trace_hardirqs_off_finish();
+
 	machine_check_vector(regs);
-	if (regs->flags & X86_EFLAGS_IF)
-		trace_hardirqs_on_prepare();
+
 	instrumentation_end();
 	irqentry_nmi_exit(regs, irq_state);
 }
@@ -2004,7 +2003,9 @@ static __always_inline void exc_machine_check_user(struct pt_regs *regs)
 {
 	irqentry_enter_from_user_mode(regs);
 	instrumentation_begin();
+
 	machine_check_vector(regs);
+
 	instrumentation_end();
 	irqentry_exit_to_user_mode(regs);
 }
diff --git a/arch/x86/kernel/cpu/topology.c b/arch/x86/kernel/cpu/topology.c
index 1068002c8532..8678864ce712 100644
--- a/arch/x86/kernel/cpu/topology.c
+++ b/arch/x86/kernel/cpu/topology.c
@@ -25,10 +25,10 @@
 #define BITS_SHIFT_NEXT_LEVEL(eax)	((eax) & 0x1f)
 #define LEVEL_MAX_SIBLINGS(ebx)		((ebx) & 0xffff)
 
-#ifdef CONFIG_SMP
 unsigned int __max_die_per_package __read_mostly = 1;
 EXPORT_SYMBOL(__max_die_per_package);
 
+#ifdef CONFIG_SMP
 /*
  * Check if given CPUID extended toplogy "leaf" is implemented
  */
diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index eb86a2b831b1..571220ac8bea 100644
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -121,7 +121,7 @@ int copy_fpregs_to_fpstate(struct fpu *fpu)
 }
 EXPORT_SYMBOL(copy_fpregs_to_fpstate);
 
-void kernel_fpu_begin(void)
+void kernel_fpu_begin_mask(unsigned int kfpu_mask)
 {
 	preempt_disable();
 
@@ -141,13 +141,14 @@ void kernel_fpu_begin(void)
 	}
 	__cpu_invalidate_fpregs_state();
 
-	if (boot_cpu_has(X86_FEATURE_XMM))
+	/* Put sane initial values into the control registers. */
+	if (likely(kfpu_mask & KFPU_MXCSR) && boot_cpu_has(X86_FEATURE_XMM))
 		ldmxcsr(MXCSR_DEFAULT);
 
-	if (boot_cpu_has(X86_FEATURE_FPU))
+	if (unlikely(kfpu_mask & KFPU_387) && boot_cpu_has(X86_FEATURE_FPU))
 		asm volatile ("fninit");
 }
-EXPORT_SYMBOL_GPL(kernel_fpu_begin);
+EXPORT_SYMBOL_GPL(kernel_fpu_begin_mask);
 
 void kernel_fpu_end(void)
 {
diff --git a/arch/x86/kernel/sev-es.c b/arch/x86/kernel/sev-es.c
index 0bd1a0fc587e..84c1821819af 100644
--- a/arch/x86/kernel/sev-es.c
+++ b/arch/x86/kernel/sev-es.c
@@ -225,7 +225,7 @@ static inline u64 sev_es_rd_ghcb_msr(void)
 	return __rdmsr(MSR_AMD64_SEV_ES_GHCB);
 }
 
-static inline void sev_es_wr_ghcb_msr(u64 val)
+static __always_inline void sev_es_wr_ghcb_msr(u64 val)
 {
 	u32 low, high;
 
@@ -286,6 +286,12 @@ static enum es_result vc_write_mem(struct es_em_ctxt *ctxt,
 	u16 d2;
 	u8  d1;
 
+	/* If instruction ran in kernel mode and the I/O buffer is in kernel space */
+	if (!user_mode(ctxt->regs) && !access_ok(target, size)) {
+		memcpy(dst, buf, size);
+		return ES_OK;
+	}
+
 	switch (size) {
 	case 1:
 		memcpy(&d1, buf, 1);
@@ -335,6 +341,12 @@ static enum es_result vc_read_mem(struct es_em_ctxt *ctxt,
 	u16 d2;
 	u8  d1;
 
+	/* If instruction ran in kernel mode and the I/O buffer is in kernel space */
+	if (!user_mode(ctxt->regs) && !access_ok(s, size)) {
+		memcpy(buf, src, size);
+		return ES_OK;
+	}
+
 	switch (size) {
 	case 1:
 		if (get_user(d1, s))
diff --git a/arch/x86/lib/mmx_32.c b/arch/x86/lib/mmx_32.c
index 4321fa02e18d..419365c48b2a 100644
--- a/arch/x86/lib/mmx_32.c
+++ b/arch/x86/lib/mmx_32.c
@@ -26,6 +26,16 @@
 #include <asm/fpu/api.h>
 #include <asm/asm.h>
 
+/*
+ * Use KFPU_387.  MMX instructions are not affected by MXCSR,
+ * but both AMD and Intel documentation states that even integer MMX
+ * operations will result in #MF if an exception is pending in FCW.
+ *
+ * EMMS is not needed afterwards because, after calling kernel_fpu_end(),
+ * any subsequent user of the 387 stack will reinitialize it using
+ * KFPU_387.
+ */
+
 void *_mmx_memcpy(void *to, const void *from, size_t len)
 {
 	void *p;
@@ -37,7 +47,7 @@ void *_mmx_memcpy(void *to, const void *from, size_t len)
 	p = to;
 	i = len >> 6; /* len/64 */
 
-	kernel_fpu_begin();
+	kernel_fpu_begin_mask(KFPU_387);
 
 	__asm__ __volatile__ (
 		"1: prefetch (%0)\n"		/* This set is 28 bytes */
@@ -127,7 +137,7 @@ static void fast_clear_page(void *page)
 {
 	int i;
 
-	kernel_fpu_begin();
+	kernel_fpu_begin_mask(KFPU_387);
 
 	__asm__ __volatile__ (
 		"  pxor %%mm0, %%mm0\n" : :
@@ -160,7 +170,7 @@ static void fast_copy_page(void *to, void *from)
 {
 	int i;
 
-	kernel_fpu_begin();
+	kernel_fpu_begin_mask(KFPU_387);
 
 	/*
 	 * maybe the prefetch stuff can go before the expensive fnsave...
@@ -247,7 +257,7 @@ static void fast_clear_page(void *page)
 {
 	int i;
 
-	kernel_fpu_begin();
+	kernel_fpu_begin_mask(KFPU_387);
 
 	__asm__ __volatile__ (
 		"  pxor %%mm0, %%mm0\n" : :
@@ -282,7 +292,7 @@ static void fast_copy_page(void *to, void *from)
 {
 	int i;
 
-	kernel_fpu_begin();
+	kernel_fpu_begin_mask(KFPU_387);
 
 	__asm__ __volatile__ (
 		"1: prefetch (%0)\n"
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index c1418b47f625..bdaf4829098c 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -79,7 +79,7 @@ module_param(lock_stat, int, 0644);
 DEFINE_PER_CPU(unsigned int, lockdep_recursion);
 EXPORT_PER_CPU_SYMBOL_GPL(lockdep_recursion);
 
-static inline bool lockdep_enabled(void)
+static __always_inline bool lockdep_enabled(void)
 {
 	if (!debug_locks)
 		return false;
@@ -5271,12 +5271,15 @@ static void __lock_unpin_lock(struct lockdep_map *lock, struct pin_cookie cookie
 /*
  * Check whether we follow the irq-flags state precisely:
  */
-static void check_flags(unsigned long flags)
+static noinstr void check_flags(unsigned long flags)
 {
 #if defined(CONFIG_PROVE_LOCKING) && defined(CONFIG_DEBUG_LOCKDEP)
 	if (!debug_locks)
 		return;
 
+	/* Get the warning out..  */
+	instrumentation_begin();
+
 	if (irqs_disabled_flags(flags)) {
 		if (DEBUG_LOCKS_WARN_ON(lockdep_hardirqs_enabled())) {
 			printk("possible reason: unannotated irqs-off.\n");
@@ -5304,6 +5307,8 @@ static void check_flags(unsigned long flags)
 
 	if (!debug_locks)
 		print_irqtrace_events(current);
+
+	instrumentation_end();
 #endif
 }