x86/mm: Avoid redundant interrupt disable in load_mm_cr4()

load_mm_cr4() is always called with interrupts disabled from:

 - switch_mm_irqs_off()
 - refresh_pce(), which is a on_each_cpu() callback

Thus, disabling interrupts in cr4_set/clear_bits() is redundant.

Implement cr4_set/clear_bits_irqsoff() helpers, rename load_mm_cr4() to
load_mm_cr4_irqsoff() and use the new helpers. The new helpers do not need
a lockdep assert as __cr4_set() has one already.

The renaming in combination with the checks in __cr4_set() ensure that any
changes in the boundary conditions at the call sites will be detected.

[ tglx: Massaged change log ]
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lkml.kernel.org/r/0fbbcb64-5f26-4ffb-1bb9-4f5f48426893@siemens.com

arch/x86/events/core.c

@@ -2087,7 +2087,7 @@ static int x86_pmu_event_init(struct perf_event *event)
 
 static void refresh_pce(void *ignored)
 {
-	load_mm_cr4(this_cpu_read(cpu_tlbstate.loaded_mm));
+	load_mm_cr4_irqsoff(this_cpu_read(cpu_tlbstate.loaded_mm));
 }
 
 static void x86_pmu_event_mapped(struct perf_event *event, struct mm_struct *mm)

arch/x86/include/asm/mmu_context.h

@@ -28,16 +28,16 @@ static inline void paravirt_activate_mm(struct mm_struct *prev,
 
 DECLARE_STATIC_KEY_FALSE(rdpmc_always_available_key);
 
-static inline void load_mm_cr4(struct mm_struct *mm)
+static inline void load_mm_cr4_irqsoff(struct mm_struct *mm)
 {
 	if (static_branch_unlikely(&rdpmc_always_available_key) ||
 	    atomic_read(&mm->context.perf_rdpmc_allowed))
-		cr4_set_bits(X86_CR4_PCE);
+		cr4_set_bits_irqsoff(X86_CR4_PCE);
 	else
-		cr4_clear_bits(X86_CR4_PCE);
+		cr4_clear_bits_irqsoff(X86_CR4_PCE);
 }
 #else
-static inline void load_mm_cr4(struct mm_struct *mm) {}
+static inline void load_mm_cr4_irqsoff(struct mm_struct *mm) {}
 #endif
 
 #ifdef CONFIG_MODIFY_LDT_SYSCALL

arch/x86/include/asm/tlbflush.h

@@ -290,26 +290,42 @@ static inline void __cr4_set(unsigned long cr4)
 }
 
 /* Set in this cpu's CR4. */
-static inline void cr4_set_bits(unsigned long mask)
+static inline void cr4_set_bits_irqsoff(unsigned long mask)
 {
-	unsigned long cr4, flags;
+	unsigned long cr4;
 
-	local_irq_save(flags);
 	cr4 = this_cpu_read(cpu_tlbstate.cr4);
 	if ((cr4 | mask) != cr4)
 		__cr4_set(cr4 | mask);
-	local_irq_restore(flags);
 }
 
 /* Clear in this cpu's CR4. */
-static inline void cr4_clear_bits(unsigned long mask)
+static inline void cr4_clear_bits_irqsoff(unsigned long mask)
 {
-	unsigned long cr4, flags;
+	unsigned long cr4;
 
-	local_irq_save(flags);
 	cr4 = this_cpu_read(cpu_tlbstate.cr4);
 	if ((cr4 & ~mask) != cr4)
 		__cr4_set(cr4 & ~mask);
+}
+
+/* Set in this cpu's CR4. */
+static inline void cr4_set_bits(unsigned long mask)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	cr4_set_bits_irqsoff(mask);
+	local_irq_restore(flags);
+}
+
+/* Clear in this cpu's CR4. */
+static inline void cr4_clear_bits(unsigned long mask)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	cr4_clear_bits_irqsoff(mask);
 	local_irq_restore(flags);
 }
 

arch/x86/mm/tlb.c

@@ -440,7 +440,7 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
 	this_cpu_write(cpu_tlbstate.loaded_mm_asid, new_asid);
 
 	if (next != real_prev) {
-		load_mm_cr4(next);
+		load_mm_cr4_irqsoff(next);
 		switch_ldt(real_prev, next);
 	}
 }