[tip:x86/urgent] x86/mm: Tidy up "x86/mm: Flush more aggressively in lazy TLB mode"

[tip-bot for Andy Lutomirski <tipbot@zytor.com>]

Commit-ID:  4e57b94664fef55aa71cac33b4632fdfdd52b695
Gitweb:     https://git.kernel.org/tip/4e57b94664fef55aa71cac33b4632fdfdd52b695
Author:     Andy Lutomirski <luto@kernel.org>
AuthorDate: Sat, 14 Oct 2017 09:59:50 -0700
Committer:  Ingo Molnar <mingo@kernel.org>
CommitDate: Wed, 18 Oct 2017 15:25:02 +0200

x86/mm: Tidy up "x86/mm: Flush more aggressively in lazy TLB mode"

Due to timezones, commit:

  b956575bed91 ("x86/mm: Flush more aggressively in lazy TLB mode")

was an outdated patch that well tested and fixed the bug but didn't
address Borislav's review comments.

Tidy it up:

 - The name "tlb_use_lazy_mode()" was highly confusing.  Change it to
   "tlb_defer_switch_to_init_mm()", which describes what it actually
   means.

 - Move the static_branch crap into a helper.

 - Improve comments.

Actually removing the debugfs option is in the next patch.

Reported-by: Borislav Petkov <bp@alien8.de>
Signed-off-by: Andy Lutomirski <luto@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Fixes: b956575bed91 ("x86/mm: Flush more aggressively in lazy TLB mode")
Link: http://lkml.kernel.org/r/154ef95428d4592596b6e98b0af1d2747d6cfbf8.1508000261.git.luto@kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/include/asm/tlbflush.h |  7 ++++++-
 arch/x86/mm/tlb.c               | 30 ++++++++++++++++++------------
 2 files changed, 24 insertions(+), 13 deletions(-)

diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index d362161..0d4a1bb 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -87,7 +87,12 @@ static inline u64 inc_mm_tlb_gen(struct mm_struct *mm)
  * to init_mm when we switch to a kernel thread (e.g. the idle thread).  If
  * it's false, then we immediately switch CR3 when entering a kernel thread.
  */
-DECLARE_STATIC_KEY_TRUE(tlb_use_lazy_mode);
+DECLARE_STATIC_KEY_TRUE(__tlb_defer_switch_to_init_mm);
+
+static inline bool tlb_defer_switch_to_init_mm(void)
+{
+	return static_branch_unlikely(&__tlb_defer_switch_to_init_mm);
+}
 
 /*
  * 6 because 6 should be plenty and struct tlb_state will fit in
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 7db23f9..5ee3b59 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -30,7 +30,7 @@
 
 atomic64_t last_mm_ctx_id = ATOMIC64_INIT(1);
 
-DEFINE_STATIC_KEY_TRUE(tlb_use_lazy_mode);
+DEFINE_STATIC_KEY_TRUE(__tlb_defer_switch_to_init_mm);
 
 static void choose_new_asid(struct mm_struct *next, u64 next_tlb_gen,
 			    u16 *new_asid, bool *need_flush)
@@ -213,6 +213,9 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
 }
 
 /*
+ * 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
@@ -227,7 +230,7 @@ void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
 	if (this_cpu_read(cpu_tlbstate.loaded_mm) == &init_mm)
 		return;
 
-	if (static_branch_unlikely(&tlb_use_lazy_mode)) {
+	if (tlb_defer_switch_to_init_mm()) {
 		/*
 		 * There's a significant optimization that may be possible
 		 * here.  We have accurate enough TLB flush tracking that we
@@ -632,7 +635,8 @@ static ssize_t tlblazy_read_file(struct file *file, char __user *user_buf,
 {
 	char buf[2];
 
-	buf[0] = static_branch_likely(&tlb_use_lazy_mode) ? '1' : '0';
+	buf[0] = static_branch_likely(&__tlb_defer_switch_to_init_mm)
+		? '1' : '0';
 	buf[1] = '\n';
 
 	return simple_read_from_buffer(user_buf, count, ppos, buf, 2);
@@ -647,9 +651,9 @@ static ssize_t tlblazy_write_file(struct file *file,
 		return -EINVAL;
 
 	if (val)
-		static_branch_enable(&tlb_use_lazy_mode);
+		static_branch_enable(&__tlb_defer_switch_to_init_mm);
 	else
-		static_branch_disable(&tlb_use_lazy_mode);
+		static_branch_disable(&__tlb_defer_switch_to_init_mm);
 
 	return count;
 }
@@ -660,23 +664,25 @@ static const struct file_operations fops_tlblazy = {
 	.llseek = default_llseek,
 };
 
-static int __init init_tlb_use_lazy_mode(void)
+static int __init init_tlblazy(void)
 {
 	if (boot_cpu_has(X86_FEATURE_PCID)) {
 		/*
-		 * Heuristic: with PCID on, switching to and from
-		 * init_mm is reasonably fast, but remote flush IPIs
-		 * as expensive as ever, so turn off lazy TLB mode.
+		 * If we have PCID, then switching to init_mm is reasonably
+		 * fast.  If we don't have PCID, then switching to init_mm is
+		 * quite slow, so we default to trying to defer it in the
+		 * hopes that we can avoid it entirely.  The latter approach
+		 * runs the risk of receiving otherwise unnecessary IPIs.
 		 *
 		 * We can't do this in setup_pcid() because static keys
 		 * haven't been initialized yet, and it would blow up
 		 * badly.
 		 */
-		static_branch_disable(&tlb_use_lazy_mode);
+		static_branch_disable(&__tlb_defer_switch_to_init_mm);
 	}
 
-	debugfs_create_file("tlb_use_lazy_mode", S_IRUSR | S_IWUSR,
+	debugfs_create_file("tlb_defer_switch_to_init_mm", S_IRUSR | S_IWUSR,
 			    arch_debugfs_dir, NULL, &fops_tlblazy);
 	return 0;
 }
-late_initcall(init_tlb_use_lazy_mode);
+late_initcall(init_tlblazy);