[PATCH 4.1 17/65] x86/mm: Remove the UP asm/tlbflush.h code, always use the (formerly) SMP code

From: Pavel Tatashin
Date: Mon Mar 05 2018 - 19:37:01 EST


From: Andy Lutomirski <luto@xxxxxxxxxx>

commit ce4a4e565f5264909a18c733b864c3f74467f69e upstream.

The UP asm/tlbflush.h generates somewhat nicer code than the SMP version.
Aside from that, it's fallen quite a bit behind the SMP code:

- flush_tlb_mm_range() didn't flush individual pages if the range
was small.

- The lazy TLB code was much weaker. This usually wouldn't matter,
but, if a kernel thread flushed its lazy "active_mm" more than
once (due to reclaim or similar), it wouldn't be unlazied and
would instead pointlessly flush repeatedly.

- Tracepoints were missing.

Aside from that, simply having the UP code around was a maintanence
burden, since it means that any change to the TLB flush code had to
make sure not to break it.

Simplify everything by deleting the UP code.

Signed-off-by: Andy Lutomirski <luto@xxxxxxxxxx>
Cc: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Cc: Arjan van de Ven <arjan@xxxxxxxxxxxxxxx>
Cc: Borislav Petkov <bpetkov@xxxxxxx>
Cc: Dave Hansen <dave.hansen@xxxxxxxxx>
Cc: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Cc: Mel Gorman <mgorman@xxxxxxx>
Cc: Michal Hocko <mhocko@xxxxxxxx>
Cc: Nadav Amit <nadav.amit@xxxxxxxxx>
Cc: Nadav Amit <namit@xxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Rik van Riel <riel@xxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: linux-mm@xxxxxxxxx
Signed-off-by: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: Hugh Dickins <hughd@xxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>

(cherry picked from commit b2e24274d50e0ecdf560ebe06dbed0cc648ad3f9)
Signed-off-by: Pavel Tatashin <pasha.tatashin@xxxxxxxxxx>

Conflicts:
arch/x86/Kconfig
---
arch/x86/include/asm/hardirq.h | 2 +-
arch/x86/include/asm/mmu.h | 6 ---
arch/x86/include/asm/mmu_context.h | 2 -
arch/x86/include/asm/tlbflush.h | 78 +-------------------------------------
arch/x86/mm/init.c | 2 -
arch/x86/mm/tlb.c | 17 +--------
6 files changed, 4 insertions(+), 103 deletions(-)

diff --git a/arch/x86/include/asm/hardirq.h b/arch/x86/include/asm/hardirq.h
index ebaf64d0a785..edd280d39a31 100644
--- a/arch/x86/include/asm/hardirq.h
+++ b/arch/x86/include/asm/hardirq.h
@@ -21,8 +21,8 @@ typedef struct {
#ifdef CONFIG_SMP
unsigned int irq_resched_count;
unsigned int irq_call_count;
- unsigned int irq_tlb_count;
#endif
+ unsigned int irq_tlb_count;
#ifdef CONFIG_X86_THERMAL_VECTOR
unsigned int irq_thermal_count;
#endif
diff --git a/arch/x86/include/asm/mmu.h b/arch/x86/include/asm/mmu.h
index 364d27481a52..652517e86e01 100644
--- a/arch/x86/include/asm/mmu.h
+++ b/arch/x86/include/asm/mmu.h
@@ -22,12 +22,6 @@ typedef struct {
atomic_t perf_rdpmc_allowed; /* nonzero if rdpmc is allowed */
} mm_context_t;

-#ifdef CONFIG_SMP
void leave_mm(int cpu);
-#else
-static inline void leave_mm(int cpu)
-{
-}
-#endif

#endif /* _ASM_X86_MMU_H */
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index 2bf4bae1c65e..29292b7aa370 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -86,10 +86,8 @@ void destroy_context(struct mm_struct *mm);

static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
{
-#ifdef CONFIG_SMP
if (this_cpu_read(cpu_tlbstate.state) == TLBSTATE_OK)
this_cpu_write(cpu_tlbstate.state, TLBSTATE_LAZY);
-#endif
}

extern void switch_mm(struct mm_struct *prev, struct mm_struct *next,
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index f23ee750bb68..4f7017c9cae8 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -6,6 +6,7 @@

#include <asm/processor.h>
#include <asm/special_insns.h>
+#include <asm/smp.h>

static inline void __invpcid(unsigned long pcid, unsigned long addr,
unsigned long type)
@@ -64,10 +65,8 @@ static inline void invpcid_flush_all_nonglobals(void)
#endif

struct tlb_state {
-#ifdef CONFIG_SMP
struct mm_struct *active_mm;
int state;
-#endif

/*
* Access to this CR4 shadow and to H/W CR4 is protected by
@@ -208,79 +207,6 @@ static inline void __flush_tlb_one(unsigned long addr)
* and page-granular flushes are available only on i486 and up.
*/

-#ifndef CONFIG_SMP
-
-/* "_up" is for UniProcessor.
- *
- * This is a helper for other header functions. *Not* intended to be called
- * directly. All global TLB flushes need to either call this, or to bump the
- * vm statistics themselves.
- */
-static inline void __flush_tlb_up(void)
-{
- count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL);
- __flush_tlb();
-}
-
-static inline void flush_tlb_all(void)
-{
- count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL);
- __flush_tlb_all();
-}
-
-static inline void local_flush_tlb(void)
-{
- __flush_tlb_up();
-}
-
-static inline void flush_tlb_mm(struct mm_struct *mm)
-{
- if (mm == current->active_mm)
- __flush_tlb_up();
-}
-
-static inline void flush_tlb_page(struct vm_area_struct *vma,
- unsigned long addr)
-{
- if (vma->vm_mm == current->active_mm)
- __flush_tlb_one(addr);
-}
-
-static inline void flush_tlb_range(struct vm_area_struct *vma,
- unsigned long start, unsigned long end)
-{
- if (vma->vm_mm == current->active_mm)
- __flush_tlb_up();
-}
-
-static inline void flush_tlb_mm_range(struct mm_struct *mm,
- unsigned long start, unsigned long end, unsigned long vmflag)
-{
- if (mm == current->active_mm)
- __flush_tlb_up();
-}
-
-static inline void native_flush_tlb_others(const struct cpumask *cpumask,
- struct mm_struct *mm,
- unsigned long start,
- unsigned long end)
-{
-}
-
-static inline void reset_lazy_tlbstate(void)
-{
-}
-
-static inline void flush_tlb_kernel_range(unsigned long start,
- unsigned long end)
-{
- flush_tlb_all();
-}
-
-#else /* SMP */
-
-#include <asm/smp.h>
-
#define local_flush_tlb() __flush_tlb()

#define flush_tlb_mm(mm) flush_tlb_mm_range(mm, 0UL, TLB_FLUSH_ALL, 0UL)
@@ -311,8 +237,6 @@ static inline void reset_lazy_tlbstate(void)
this_cpu_write(cpu_tlbstate.active_mm, &init_mm);
}

-#endif /* SMP */
-
#ifndef CONFIG_PARAVIRT
#define flush_tlb_others(mask, mm, start, end) \
native_flush_tlb_others(mask, mm, start, end)
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 3e1bb1c8daea..0a06e5a14278 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -752,10 +752,8 @@ void __init zone_sizes_init(void)
}

DEFINE_PER_CPU_SHARED_ALIGNED(struct tlb_state, cpu_tlbstate) = {
-#ifdef CONFIG_SMP
.active_mm = &init_mm,
.state = 0,
-#endif
.cr4 = ~0UL, /* fail hard if we screw up cr4 shadow initialization */
};
EXPORT_SYMBOL_GPL(cpu_tlbstate);
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 77fdf801efde..95624d903c0e 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -15,7 +15,7 @@
#include <linux/debugfs.h>

/*
- * Smarter SMP flushing macros.
+ * TLB flushing, formerly SMP-only
* c/o Linus Torvalds.
*
* These mean you can really definitely utterly forget about
@@ -28,8 +28,6 @@
* Implement flush IPI by CALL_FUNCTION_VECTOR, Alex Shi
*/

-#ifdef CONFIG_SMP
-
struct flush_tlb_info {
struct mm_struct *flush_mm;
unsigned long flush_start;
@@ -59,8 +57,6 @@ void leave_mm(int cpu)
}
EXPORT_SYMBOL_GPL(leave_mm);

-#endif /* CONFIG_SMP */
-
void switch_mm(struct mm_struct *prev, struct mm_struct *next,
struct task_struct *tsk)
{
@@ -77,10 +73,8 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
unsigned cpu = smp_processor_id();

if (likely(prev != next)) {
-#ifdef CONFIG_SMP
this_cpu_write(cpu_tlbstate.state, TLBSTATE_OK);
this_cpu_write(cpu_tlbstate.active_mm, next);
-#endif
cpumask_set_cpu(cpu, mm_cpumask(next));

/*
@@ -135,9 +129,7 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
*/
if (unlikely(prev->context.ldt != next->context.ldt))
load_mm_ldt(next);
- }
-#ifdef CONFIG_SMP
- else {
+ } else {
this_cpu_write(cpu_tlbstate.state, TLBSTATE_OK);
BUG_ON(this_cpu_read(cpu_tlbstate.active_mm) != next);

@@ -164,11 +156,8 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
load_mm_ldt(next);
}
}
-#endif
}

-#ifdef CONFIG_SMP
-
/*
* The flush IPI assumes that a thread switch happens in this order:
* [cpu0: the cpu that switches]
@@ -416,5 +405,3 @@ static int __init create_tlb_single_page_flush_ceiling(void)
return 0;
}
late_initcall(create_tlb_single_page_flush_ceiling);
-
-#endif /* CONFIG_SMP */
--
2.16.2