Merging upstream version 6.9.7.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

1 files changed, 23 insertions, 26 deletions

diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 5768d386ef..44ac64f3a0 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -89,10 +89,10 @@
 #define CR3_HW_ASID_BITS		12
 
 /*
- * When enabled, PAGE_TABLE_ISOLATION consumes a single bit for
+ * When enabled, MITIGATION_PAGE_TABLE_ISOLATION consumes a single bit for
  * user/kernel switches
  */
-#ifdef CONFIG_PAGE_TABLE_ISOLATION
+#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION
 # define PTI_CONSUMED_PCID_BITS	1
 #else
 # define PTI_CONSUMED_PCID_BITS	0
@@ -114,7 +114,7 @@ static inline u16 kern_pcid(u16 asid)
 {
 	VM_WARN_ON_ONCE(asid > MAX_ASID_AVAILABLE);
 
-#ifdef CONFIG_PAGE_TABLE_ISOLATION
+#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION
 	/*
 	 * Make sure that the dynamic ASID space does not conflict with the
 	 * bit we are using to switch between user and kernel ASIDs.
@@ -149,7 +149,7 @@ static inline u16 kern_pcid(u16 asid)
 static inline u16 user_pcid(u16 asid)
 {
 	u16 ret = kern_pcid(asid);
-#ifdef CONFIG_PAGE_TABLE_ISOLATION
+#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION
 	ret |= 1 << X86_CR3_PTI_PCID_USER_BIT;
 #endif
 	return ret;
@@ -262,7 +262,7 @@ static void choose_new_asid(struct mm_struct *next, u64 next_tlb_gen,
 static inline void invalidate_user_asid(u16 asid)
 {
 	/* There is no user ASID if address space separation is off */
-	if (!IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION))
+	if (!IS_ENABLED(CONFIG_MITIGATION_PAGE_TABLE_ISOLATION))
 		return;
 
 	/*
@@ -299,7 +299,7 @@ static void load_new_mm_cr3(pgd_t *pgdir, u16 new_asid, unsigned long lam,
 	write_cr3(new_mm_cr3);
 }
 
-void leave_mm(int cpu)
+void leave_mm(void)
 {
 	struct mm_struct *loaded_mm = this_cpu_read(cpu_tlbstate.loaded_mm);
 
@@ -327,7 +327,7 @@ void switch_mm(struct mm_struct *prev, struct mm_struct *next,
 	unsigned long flags;
 
 	local_irq_save(flags);
-	switch_mm_irqs_off(prev, next, tsk);
+	switch_mm_irqs_off(NULL, next, tsk);
 	local_irq_restore(flags);
 }
 
@@ -492,10 +492,16 @@ void cr4_update_pce(void *ignored)
 static inline void cr4_update_pce_mm(struct mm_struct *mm) { }
 #endif
 
-void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
+/*
+ * This optimizes when not actually switching mm's.  Some architectures use the
+ * 'unused' argument for this optimization, but x86 must use
+ * 'cpu_tlbstate.loaded_mm' instead because it does not always keep
+ * 'current->active_mm' up to date.
+ */
+void switch_mm_irqs_off(struct mm_struct *unused, struct mm_struct *next,
 			struct task_struct *tsk)
 {
-	struct mm_struct *real_prev = this_cpu_read(cpu_tlbstate.loaded_mm);
+	struct mm_struct *prev = this_cpu_read(cpu_tlbstate.loaded_mm);
 	u16 prev_asid = this_cpu_read(cpu_tlbstate.loaded_mm_asid);
 	unsigned long new_lam = mm_lam_cr3_mask(next);
 	bool was_lazy = this_cpu_read(cpu_tlbstate_shared.is_lazy);
@@ -504,15 +510,6 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
 	bool need_flush;
 	u16 new_asid;
 
-	/*
-	 * NB: The scheduler will call us with prev == next when switching
-	 * from lazy TLB mode to normal mode if active_mm isn't changing.
-	 * When this happens, we don't assume that CR3 (and hence
-	 * cpu_tlbstate.loaded_mm) matches next.
-	 *
-	 * NB: leave_mm() calls us with prev == NULL and tsk == NULL.
-	 */
-
 	/* We don't want flush_tlb_func() to run concurrently with us. */
 	if (IS_ENABLED(CONFIG_PROVE_LOCKING))
 		WARN_ON_ONCE(!irqs_disabled());
@@ -527,7 +524,7 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
 	 * isn't free.
 	 */
 #ifdef CONFIG_DEBUG_VM
-	if (WARN_ON_ONCE(__read_cr3() != build_cr3(real_prev->pgd, prev_asid,
+	if (WARN_ON_ONCE(__read_cr3() != build_cr3(prev->pgd, prev_asid,
 						   tlbstate_lam_cr3_mask()))) {
 		/*
 		 * If we were to BUG here, we'd be very likely to kill
@@ -559,7 +556,7 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
 	 * provides that full memory barrier and core serializing
 	 * instruction.
 	 */
-	if (real_prev == next) {
+	if (prev == next) {
 		/* Not actually switching mm's */
 		VM_WARN_ON(this_cpu_read(cpu_tlbstate.ctxs[prev_asid].ctx_id) !=
 			   next->context.ctx_id);
@@ -574,7 +571,7 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
 		 * mm_cpumask. The TLB shootdown code can figure out from
 		 * cpu_tlbstate_shared.is_lazy whether or not to send an IPI.
 		 */
-		if (WARN_ON_ONCE(real_prev != &init_mm &&
+		if (WARN_ON_ONCE(prev != &init_mm &&
 				 !cpumask_test_cpu(cpu, mm_cpumask(next))))
 			cpumask_set_cpu(cpu, mm_cpumask(next));
 
@@ -616,10 +613,10 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
 		 * Skip kernel threads; we never send init_mm TLB flushing IPIs,
 		 * but the bitmap manipulation can cause cache line contention.
 		 */
-		if (real_prev != &init_mm) {
+		if (prev != &init_mm) {
 			VM_WARN_ON_ONCE(!cpumask_test_cpu(cpu,
-						mm_cpumask(real_prev)));
-			cpumask_clear_cpu(cpu, mm_cpumask(real_prev));
+						mm_cpumask(prev)));
+			cpumask_clear_cpu(cpu, mm_cpumask(prev));
 		}
 
 		/*
@@ -656,9 +653,9 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
 	this_cpu_write(cpu_tlbstate.loaded_mm, next);
 	this_cpu_write(cpu_tlbstate.loaded_mm_asid, new_asid);
 
-	if (next != real_prev) {
+	if (next != prev) {
 		cr4_update_pce_mm(next);
-		switch_ldt(real_prev, next);
+		switch_ldt(prev, next);
 	}
 }