12 files changed, 72 insertions, 27 deletions

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/