Merge branch '7.0/fixes' into 7.0/base

Signed-off-by: Eric Naim <dnaim@cachyos.org>

Author: 1Naim

Documentation/admin-guide/kernel-parameters.txt

@@ -1750,8 +1750,8 @@ Kernel parameters
 	fred=		[X86-64]
 			Enable/disable Flexible Return and Event Delivery.
 			Format: { on | off }
-			on: enable FRED when it's present.
-			off: disable FRED, the default setting.
+			on: enable FRED when it's present, the default setting.
+			off: disable FRED.
 
 	ftrace=[tracer]
 			[FTRACE] will set and start the specified tracer

arch/arm/include/asm/mmu_context.h

@@ -80,7 +80,7 @@ static inline void check_and_switch_context(struct mm_struct *mm,
 #ifndef MODULE
 #define finish_arch_post_lock_switch \
 	finish_arch_post_lock_switch
-static inline void finish_arch_post_lock_switch(void)
+static __always_inline void finish_arch_post_lock_switch(void)
 {
 	struct mm_struct *mm = current->mm;
 

arch/riscv/include/asm/sync_core.h

@@ -6,7 +6,7 @@
  * RISC-V implements return to user-space through an xRET instruction,
  * which is not core serializing.
  */
-static inline void sync_core_before_usermode(void)
+static __always_inline void sync_core_before_usermode(void)
 {
 	asm volatile ("fence.i" ::: "memory");
 }

arch/s390/include/asm/mmu_context.h

@@ -93,7 +93,7 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
 }
 
 #define finish_arch_post_lock_switch finish_arch_post_lock_switch
-static inline void finish_arch_post_lock_switch(void)
+static __always_inline void finish_arch_post_lock_switch(void)
 {
 	struct task_struct *tsk = current;
 	struct mm_struct *mm = tsk->mm;

arch/sparc/include/asm/mmu_context_64.h

@@ -160,7 +160,7 @@ static inline void arch_start_context_switch(struct task_struct *prev)
 }
 
 #define finish_arch_post_lock_switch	finish_arch_post_lock_switch
-static inline void finish_arch_post_lock_switch(void)
+static __always_inline void finish_arch_post_lock_switch(void)
 {
 	/* Restore the state of MCDPER register for the new process
 	 * just switched to.

arch/x86/Kconfig

@@ -557,7 +557,7 @@ config X86_FRED
 	bool "Flexible Return and Event Delivery"
 	depends on X86_64
 	help
-	  When enabled, try to use Flexible Return and Event Delivery
+	  When enabled, use Flexible Return and Event Delivery
 	  instead of the legacy SYSCALL/SYSENTER/IDT architecture for
 	  ring transitions and exception/interrupt handling if the
 	  system supports it.

arch/x86/include/asm/mmu_context.h

@@ -136,9 +136,6 @@ static inline void mm_reset_untag_mask(struct mm_struct *mm)
 }
 #endif
 
-#define enter_lazy_tlb enter_lazy_tlb
-extern void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk);
-
 extern void mm_init_global_asid(struct mm_struct *mm);
 extern void mm_free_global_asid(struct mm_struct *mm);
 

arch/x86/include/asm/sync_core.h

@@ -93,7 +93,7 @@ static __always_inline void sync_core(void)
  * to user-mode. x86 implements return to user-space through sysexit,
  * sysrel, and sysretq, which are not core serializing.
  */
-static inline void sync_core_before_usermode(void)
+static __always_inline void sync_core_before_usermode(void)
 {
 	/* With PTI, we unconditionally serialize before running user code. */
 	if (static_cpu_has(X86_FEATURE_PTI))

arch/x86/include/asm/tlbflush.h

@@ -172,6 +172,28 @@ struct tlb_state_shared {
 };
 DECLARE_PER_CPU_SHARED_ALIGNED(struct tlb_state_shared, cpu_tlbstate_shared);
 
+/*
+ * Please ignore the name of this function.  It should be called
+ * switch_to_kernel_thread().
+ *
+ * enter_lazy_tlb() is a hint from the scheduler that we are entering a
+ * kernel thread or other context without an mm.  Acceptable implementations
+ * include doing nothing whatsoever, switching to init_mm, or various clever
+ * lazy tricks to try to minimize TLB flushes.
+ *
+ * The scheduler reserves the right to call enter_lazy_tlb() several times
+ * in a row.  It will notify us that we're going back to a real mm by
+ * calling switch_mm_irqs_off().
+ */
+#define enter_lazy_tlb enter_lazy_tlb
+static __always_inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
+{
+	if (this_cpu_read(cpu_tlbstate.loaded_mm) == &init_mm)
+		return;
+
+	this_cpu_write(cpu_tlbstate_shared.is_lazy, true);
+}
+
 bool nmi_uaccess_okay(void);
 #define nmi_uaccess_okay nmi_uaccess_okay
 
@@ -480,6 +502,10 @@ static inline void cpu_tlbstate_update_lam(unsigned long lam, u64 untag_mask)
 {
 }
 #endif
+#else /* !MODULE */
+#define enter_lazy_tlb enter_lazy_tlb
+extern void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
+	__compiletime_error("enter_lazy_tlb() should not be used in modules");
 #endif /* !MODULE */
 
 static inline void __native_tlb_flush_global(unsigned long cr4)

arch/x86/kernel/cpu/common.c

@@ -1759,7 +1759,7 @@ static void __init cpu_parse_early_param(void)
 
 	/* Minimize the gap between FRED is available and available but disabled. */
 	arglen = cmdline_find_option(boot_command_line, "fred", arg, sizeof(arg));
-	if (arglen != 2 || strncmp(arg, "on", 2))
+	if (arglen > 0 && (arglen != 2 || strncmp(arg, "on", 2)))
 		setup_clear_cpu_cap(X86_FEATURE_FRED);
 
 	arglen = cmdline_find_option(boot_command_line, "clearcpuid", arg, sizeof(arg));