[111/118] sparc64: Fix race in TLB batch processing.

From: Ben Hutchings
Date: Fri May 10 2013 - 10:47:15 EST


3.2.45-rc1 review patch. If anyone has any objections, please let me know.

------------------

From: "David S. Miller" <davem@xxxxxxxxxxxxx>

[ Commits f36391d2790d04993f48da6a45810033a2cdf847 and
f0af97070acbad5d6a361f485828223a4faaa0ee upstream. ]

As reported by Dave Kleikamp, when we emit cross calls to do batched
TLB flush processing we have a race because we do not synchronize on
the sibling cpus completing the cross call.

So meanwhile the TLB batch can be reset (tb->tlb_nr set to zero, etc.)
and either flushes are missed or flushes will flush the wrong
addresses.

Fix this by using generic infrastructure to synchonize on the
completion of the cross call.

This first required getting the flush_tlb_pending() call out from
switch_to() which operates with locks held and interrupts disabled.
The problem is that smp_call_function_many() cannot be invoked with
IRQs disabled and this is explicitly checked for with WARN_ON_ONCE().

We get the batch processing outside of locked IRQ disabled sections by
using some ideas from the powerpc port. Namely, we only batch inside
of arch_{enter,leave}_lazy_mmu_mode() calls. If we're not in such a
region, we flush TLBs synchronously.

1) Get rid of xcall_flush_tlb_pending and per-cpu type
implementations.

2) Do TLB batch cross calls instead via:

smp_call_function_many()
tlb_pending_func()
__flush_tlb_pending()

3) Batch only in lazy mmu sequences:

a) Add 'active' member to struct tlb_batch
b) Define __HAVE_ARCH_ENTER_LAZY_MMU_MODE
c) Set 'active' in arch_enter_lazy_mmu_mode()
d) Run batch and clear 'active' in arch_leave_lazy_mmu_mode()
e) Check 'active' in tlb_batch_add_one() and do a synchronous
flush if it's clear.

4) Add infrastructure for synchronous TLB page flushes.

a) Implement __flush_tlb_page and per-cpu variants, patch
as needed.
b) Likewise for xcall_flush_tlb_page.
c) Implement smp_flush_tlb_page() to invoke the cross-call.
d) Wire up global_flush_tlb_page() to the right routine based
upon CONFIG_SMP

5) It turns out that singleton batches are very common, 2 out of every
3 batch flushes have only a single entry in them.

The batch flush waiting is very expensive, both because of the poll
on sibling cpu completeion, as well as because passing the tlb batch
pointer to the sibling cpus invokes a shared memory dereference.

Therefore, in flush_tlb_pending(), if there is only one entry in
the batch perform a completely asynchronous global_flush_tlb_page()
instead.

Reported-by: Dave Kleikamp <dave.kleikamp@xxxxxxxxxx>
Signed-off-by: David S. Miller <davem@xxxxxxxxxxxxx>
Acked-by: Dave Kleikamp <dave.kleikamp@xxxxxxxxxx>
Signed-off-by: Ben Hutchings <ben@xxxxxxxxxxxxxxx>
---
arch/sparc/include/asm/pgtable_64.h | 1 +
arch/sparc/include/asm/system_64.h | 3 +-
arch/sparc/include/asm/tlbflush_64.h | 37 +++++++++--
arch/sparc/kernel/smp_64.c | 41 ++++++++++--
arch/sparc/mm/tlb.c | 39 ++++++++++--
arch/sparc/mm/tsb.c | 57 ++++++++++++-----
arch/sparc/mm/ultra.S | 119 ++++++++++++++++++++++++++++-------
7 files changed, 242 insertions(+), 55 deletions(-)

--- a/arch/sparc/include/asm/pgtable_64.h
+++ b/arch/sparc/include/asm/pgtable_64.h
@@ -781,6 +781,7 @@ static inline int io_remap_pfn_range(str
return remap_pfn_range(vma, from, phys_base >> PAGE_SHIFT, size, prot);
}

+#include <asm/tlbflush.h>
#include <asm-generic/pgtable.h>

/* We provide our own get_unmapped_area to cope with VA holes and
--- a/arch/sparc/include/asm/system_64.h
+++ b/arch/sparc/include/asm/system_64.h
@@ -140,8 +140,7 @@ do { \
* and 2 stores in this critical code path. -DaveM
*/
#define switch_to(prev, next, last) \
-do { flush_tlb_pending(); \
- save_and_clear_fpu(); \
+do { save_and_clear_fpu(); \
/* If you are tempted to conditionalize the following */ \
/* so that ASI is only written if it changes, think again. */ \
__asm__ __volatile__("wr %%g0, %0, %%asi" \
--- a/arch/sparc/include/asm/tlbflush_64.h
+++ b/arch/sparc/include/asm/tlbflush_64.h
@@ -11,24 +11,40 @@
struct tlb_batch {
struct mm_struct *mm;
unsigned long tlb_nr;
+ unsigned long active;
unsigned long vaddrs[TLB_BATCH_NR];
};

extern void flush_tsb_kernel_range(unsigned long start, unsigned long end);
extern void flush_tsb_user(struct tlb_batch *tb);
+extern void flush_tsb_user_page(struct mm_struct *mm, unsigned long vaddr);

/* TLB flush operations. */

-extern void flush_tlb_pending(void);
+static inline void flush_tlb_mm(struct mm_struct *mm)
+{
+}
+
+static inline void flush_tlb_page(struct vm_area_struct *vma,
+ unsigned long vmaddr)
+{
+}
+
+static inline void flush_tlb_range(struct vm_area_struct *vma,
+ unsigned long start, unsigned long end)
+{
+}
+
+#define __HAVE_ARCH_ENTER_LAZY_MMU_MODE

-#define flush_tlb_range(vma,start,end) \
- do { (void)(start); flush_tlb_pending(); } while (0)
-#define flush_tlb_page(vma,addr) flush_tlb_pending()
-#define flush_tlb_mm(mm) flush_tlb_pending()
+extern void flush_tlb_pending(void);
+extern void arch_enter_lazy_mmu_mode(void);
+extern void arch_leave_lazy_mmu_mode(void);
+#define arch_flush_lazy_mmu_mode() do {} while (0)

/* Local cpu only. */
extern void __flush_tlb_all(void);
-
+extern void __flush_tlb_page(unsigned long context, unsigned long vaddr);
extern void __flush_tlb_kernel_range(unsigned long start, unsigned long end);

#ifndef CONFIG_SMP
@@ -38,15 +54,24 @@ do { flush_tsb_kernel_range(start,end);
__flush_tlb_kernel_range(start,end); \
} while (0)

+static inline void global_flush_tlb_page(struct mm_struct *mm, unsigned long vaddr)
+{
+ __flush_tlb_page(CTX_HWBITS(mm->context), vaddr);
+}
+
#else /* CONFIG_SMP */

extern void smp_flush_tlb_kernel_range(unsigned long start, unsigned long end);
+extern void smp_flush_tlb_page(struct mm_struct *mm, unsigned long vaddr);

#define flush_tlb_kernel_range(start, end) \
do { flush_tsb_kernel_range(start,end); \
smp_flush_tlb_kernel_range(start, end); \
} while (0)

+#define global_flush_tlb_page(mm, vaddr) \
+ smp_flush_tlb_page(mm, vaddr)
+
#endif /* ! CONFIG_SMP */

#endif /* _SPARC64_TLBFLUSH_H */
--- a/arch/sparc/kernel/smp_64.c
+++ b/arch/sparc/kernel/smp_64.c
@@ -856,7 +856,7 @@ void smp_tsb_sync(struct mm_struct *mm)
}

extern unsigned long xcall_flush_tlb_mm;
-extern unsigned long xcall_flush_tlb_pending;
+extern unsigned long xcall_flush_tlb_page;
extern unsigned long xcall_flush_tlb_kernel_range;
extern unsigned long xcall_fetch_glob_regs;
extern unsigned long xcall_receive_signal;
@@ -1070,22 +1070,55 @@ local_flush_and_out:
put_cpu();
}

+struct tlb_pending_info {
+ unsigned long ctx;
+ unsigned long nr;
+ unsigned long *vaddrs;
+};
+
+static void tlb_pending_func(void *info)
+{
+ struct tlb_pending_info *t = info;
+
+ __flush_tlb_pending(t->ctx, t->nr, t->vaddrs);
+}
+
void smp_flush_tlb_pending(struct mm_struct *mm, unsigned long nr, unsigned long *vaddrs)
{
u32 ctx = CTX_HWBITS(mm->context);
+ struct tlb_pending_info info;
int cpu = get_cpu();

+ info.ctx = ctx;
+ info.nr = nr;
+ info.vaddrs = vaddrs;
+
if (mm == current->mm && atomic_read(&mm->mm_users) == 1)
cpumask_copy(mm_cpumask(mm), cpumask_of(cpu));
else
- smp_cross_call_masked(&xcall_flush_tlb_pending,
- ctx, nr, (unsigned long) vaddrs,
- mm_cpumask(mm));
+ smp_call_function_many(mm_cpumask(mm), tlb_pending_func,
+ &info, 1);

__flush_tlb_pending(ctx, nr, vaddrs);

put_cpu();
}
+
+void smp_flush_tlb_page(struct mm_struct *mm, unsigned long vaddr)
+{
+ unsigned long context = CTX_HWBITS(mm->context);
+ int cpu = get_cpu();
+
+ if (mm == current->mm && atomic_read(&mm->mm_users) == 1)
+ cpumask_copy(mm_cpumask(mm), cpumask_of(cpu));
+ else
+ smp_cross_call_masked(&xcall_flush_tlb_page,
+ context, vaddr, 0,
+ mm_cpumask(mm));
+ __flush_tlb_page(context, vaddr);
+
+ put_cpu();
+}

void smp_flush_tlb_kernel_range(unsigned long start, unsigned long end)
{
--- a/arch/sparc/mm/tlb.c
+++ b/arch/sparc/mm/tlb.c
@@ -24,11 +24,17 @@ static DEFINE_PER_CPU(struct tlb_batch,
void flush_tlb_pending(void)
{
struct tlb_batch *tb = &get_cpu_var(tlb_batch);
+ struct mm_struct *mm = tb->mm;

- if (tb->tlb_nr) {
- flush_tsb_user(tb);
+ if (!tb->tlb_nr)
+ goto out;

- if (CTX_VALID(tb->mm->context)) {
+ flush_tsb_user(tb);
+
+ if (CTX_VALID(mm->context)) {
+ if (tb->tlb_nr == 1) {
+ global_flush_tlb_page(mm, tb->vaddrs[0]);
+ } else {
#ifdef CONFIG_SMP
smp_flush_tlb_pending(tb->mm, tb->tlb_nr,
&tb->vaddrs[0]);
@@ -37,12 +43,30 @@ void flush_tlb_pending(void)
tb->tlb_nr, &tb->vaddrs[0]);
#endif
}
- tb->tlb_nr = 0;
}

+ tb->tlb_nr = 0;
+
+out:
put_cpu_var(tlb_batch);
}

+void arch_enter_lazy_mmu_mode(void)
+{
+ struct tlb_batch *tb = &__get_cpu_var(tlb_batch);
+
+ tb->active = 1;
+}
+
+void arch_leave_lazy_mmu_mode(void)
+{
+ struct tlb_batch *tb = &__get_cpu_var(tlb_batch);
+
+ if (tb->tlb_nr)
+ flush_tlb_pending();
+ tb->active = 0;
+}
+
void tlb_batch_add(struct mm_struct *mm, unsigned long vaddr,
pte_t *ptep, pte_t orig, int fullmm)
{
@@ -90,6 +114,12 @@ no_cache_flush:
nr = 0;
}

+ if (!tb->active) {
+ global_flush_tlb_page(mm, vaddr);
+ flush_tsb_user_page(mm, vaddr);
+ goto out;
+ }
+
if (nr == 0)
tb->mm = mm;

@@ -98,5 +128,6 @@ no_cache_flush:
if (nr >= TLB_BATCH_NR)
flush_tlb_pending();

+out:
put_cpu_var(tlb_batch);
}
--- a/arch/sparc/mm/tsb.c
+++ b/arch/sparc/mm/tsb.c
@@ -8,11 +8,10 @@
#include <linux/slab.h>
#include <asm/system.h>
#include <asm/page.h>
-#include <asm/tlbflush.h>
-#include <asm/tlb.h>
-#include <asm/mmu_context.h>
#include <asm/pgtable.h>
+#include <asm/mmu_context.h>
#include <asm/tsb.h>
+#include <asm/tlb.h>
#include <asm/oplib.h>

extern struct tsb swapper_tsb[KERNEL_TSB_NENTRIES];
@@ -47,23 +46,27 @@ void flush_tsb_kernel_range(unsigned lon
}
}

-static void __flush_tsb_one(struct tlb_batch *tb, unsigned long hash_shift,
- unsigned long tsb, unsigned long nentries)
+static void __flush_tsb_one_entry(unsigned long tsb, unsigned long v,
+ unsigned long hash_shift,
+ unsigned long nentries)
{
- unsigned long i;
+ unsigned long tag, ent, hash;

- for (i = 0; i < tb->tlb_nr; i++) {
- unsigned long v = tb->vaddrs[i];
- unsigned long tag, ent, hash;
+ v &= ~0x1UL;
+ hash = tsb_hash(v, hash_shift, nentries);
+ ent = tsb + (hash * sizeof(struct tsb));
+ tag = (v >> 22UL);

- v &= ~0x1UL;
+ tsb_flush(ent, tag);
+}

- hash = tsb_hash(v, hash_shift, nentries);
- ent = tsb + (hash * sizeof(struct tsb));
- tag = (v >> 22UL);
+static void __flush_tsb_one(struct tlb_batch *tb, unsigned long hash_shift,
+ unsigned long tsb, unsigned long nentries)
+{
+ unsigned long i;

- tsb_flush(ent, tag);
- }
+ for (i = 0; i < tb->tlb_nr; i++)
+ __flush_tsb_one_entry(tsb, tb->vaddrs[i], hash_shift, nentries);
}

void flush_tsb_user(struct tlb_batch *tb)
@@ -89,6 +92,30 @@ void flush_tsb_user(struct tlb_batch *tb
}
#endif
spin_unlock_irqrestore(&mm->context.lock, flags);
+}
+
+void flush_tsb_user_page(struct mm_struct *mm, unsigned long vaddr)
+{
+ unsigned long nentries, base, flags;
+
+ spin_lock_irqsave(&mm->context.lock, flags);
+
+ base = (unsigned long) mm->context.tsb_block[MM_TSB_BASE].tsb;
+ nentries = mm->context.tsb_block[MM_TSB_BASE].tsb_nentries;
+ if (tlb_type == cheetah_plus || tlb_type == hypervisor)
+ base = __pa(base);
+ __flush_tsb_one_entry(base, vaddr, PAGE_SHIFT, nentries);
+
+#if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
+ if (mm->context.tsb_block[MM_TSB_HUGE].tsb) {
+ base = (unsigned long) mm->context.tsb_block[MM_TSB_HUGE].tsb;
+ nentries = mm->context.tsb_block[MM_TSB_HUGE].tsb_nentries;
+ if (tlb_type == cheetah_plus || tlb_type == hypervisor)
+ base = __pa(base);
+ __flush_tsb_one_entry(base, vaddr, HPAGE_SHIFT, nentries);
+ }
+#endif
+ spin_unlock_irqrestore(&mm->context.lock, flags);
}

#if defined(CONFIG_SPARC64_PAGE_SIZE_8KB)
--- a/arch/sparc/mm/ultra.S
+++ b/arch/sparc/mm/ultra.S
@@ -53,6 +53,33 @@ __flush_tlb_mm: /* 18 insns */
nop

.align 32
+ .globl __flush_tlb_page
+__flush_tlb_page: /* 22 insns */
+ /* %o0 = context, %o1 = vaddr */
+ rdpr %pstate, %g7
+ andn %g7, PSTATE_IE, %g2
+ wrpr %g2, %pstate
+ mov SECONDARY_CONTEXT, %o4
+ ldxa [%o4] ASI_DMMU, %g2
+ stxa %o0, [%o4] ASI_DMMU
+ andcc %o1, 1, %g0
+ andn %o1, 1, %o3
+ be,pn %icc, 1f
+ or %o3, 0x10, %o3
+ stxa %g0, [%o3] ASI_IMMU_DEMAP
+1: stxa %g0, [%o3] ASI_DMMU_DEMAP
+ membar #Sync
+ stxa %g2, [%o4] ASI_DMMU
+ sethi %hi(KERNBASE), %o4
+ flush %o4
+ retl
+ wrpr %g7, 0x0, %pstate
+ nop
+ nop
+ nop
+ nop
+
+ .align 32
.globl __flush_tlb_pending
__flush_tlb_pending: /* 26 insns */
/* %o0 = context, %o1 = nr, %o2 = vaddrs[] */
@@ -203,6 +230,31 @@ __cheetah_flush_tlb_mm: /* 19 insns */
retl
wrpr %g7, 0x0, %pstate

+__cheetah_flush_tlb_page: /* 22 insns */
+ /* %o0 = context, %o1 = vaddr */
+ rdpr %pstate, %g7
+ andn %g7, PSTATE_IE, %g2
+ wrpr %g2, 0x0, %pstate
+ wrpr %g0, 1, %tl
+ mov PRIMARY_CONTEXT, %o4
+ ldxa [%o4] ASI_DMMU, %g2
+ srlx %g2, CTX_PGSZ1_NUC_SHIFT, %o3
+ sllx %o3, CTX_PGSZ1_NUC_SHIFT, %o3
+ or %o0, %o3, %o0 /* Preserve nucleus page size fields */
+ stxa %o0, [%o4] ASI_DMMU
+ andcc %o1, 1, %g0
+ be,pn %icc, 1f
+ andn %o1, 1, %o3
+ stxa %g0, [%o3] ASI_IMMU_DEMAP
+1: stxa %g0, [%o3] ASI_DMMU_DEMAP
+ membar #Sync
+ stxa %g2, [%o4] ASI_DMMU
+ sethi %hi(KERNBASE), %o4
+ flush %o4
+ wrpr %g0, 0, %tl
+ retl
+ wrpr %g7, 0x0, %pstate
+
__cheetah_flush_tlb_pending: /* 27 insns */
/* %o0 = context, %o1 = nr, %o2 = vaddrs[] */
rdpr %pstate, %g7
@@ -269,6 +321,20 @@ __hypervisor_flush_tlb_mm: /* 10 insns *
retl
nop

+__hypervisor_flush_tlb_page: /* 11 insns */
+ /* %o0 = context, %o1 = vaddr */
+ mov %o0, %g2
+ mov %o1, %o0 /* ARG0: vaddr + IMMU-bit */
+ mov %g2, %o1 /* ARG1: mmu context */
+ mov HV_MMU_ALL, %o2 /* ARG2: flags */
+ srlx %o0, PAGE_SHIFT, %o0
+ sllx %o0, PAGE_SHIFT, %o0
+ ta HV_MMU_UNMAP_ADDR_TRAP
+ brnz,pn %o0, __hypervisor_tlb_tl0_error
+ mov HV_MMU_UNMAP_ADDR_TRAP, %o1
+ retl
+ nop
+
__hypervisor_flush_tlb_pending: /* 16 insns */
/* %o0 = context, %o1 = nr, %o2 = vaddrs[] */
sllx %o1, 3, %g1
@@ -339,6 +405,13 @@ cheetah_patch_cachetlbops:
call tlb_patch_one
mov 19, %o2

+ sethi %hi(__flush_tlb_page), %o0
+ or %o0, %lo(__flush_tlb_page), %o0
+ sethi %hi(__cheetah_flush_tlb_page), %o1
+ or %o1, %lo(__cheetah_flush_tlb_page), %o1
+ call tlb_patch_one
+ mov 22, %o2
+
sethi %hi(__flush_tlb_pending), %o0
or %o0, %lo(__flush_tlb_pending), %o0
sethi %hi(__cheetah_flush_tlb_pending), %o1
@@ -397,10 +470,9 @@ xcall_flush_tlb_mm: /* 21 insns */
nop
nop

- .globl xcall_flush_tlb_pending
-xcall_flush_tlb_pending: /* 21 insns */
- /* %g5=context, %g1=nr, %g7=vaddrs[] */
- sllx %g1, 3, %g1
+ .globl xcall_flush_tlb_page
+xcall_flush_tlb_page: /* 17 insns */
+ /* %g5=context, %g1=vaddr */
mov PRIMARY_CONTEXT, %g4
ldxa [%g4] ASI_DMMU, %g2
srlx %g2, CTX_PGSZ1_NUC_SHIFT, %g4
@@ -408,20 +480,16 @@ xcall_flush_tlb_pending: /* 21 insns */
or %g5, %g4, %g5
mov PRIMARY_CONTEXT, %g4
stxa %g5, [%g4] ASI_DMMU
-1: sub %g1, (1 << 3), %g1
- ldx [%g7 + %g1], %g5
- andcc %g5, 0x1, %g0
+ andcc %g1, 0x1, %g0
be,pn %icc, 2f
-
- andn %g5, 0x1, %g5
+ andn %g1, 0x1, %g5
stxa %g0, [%g5] ASI_IMMU_DEMAP
2: stxa %g0, [%g5] ASI_DMMU_DEMAP
membar #Sync
- brnz,pt %g1, 1b
- nop
stxa %g2, [%g4] ASI_DMMU
retry
nop
+ nop

.globl xcall_flush_tlb_kernel_range
xcall_flush_tlb_kernel_range: /* 25 insns */
@@ -596,15 +664,13 @@ __hypervisor_xcall_flush_tlb_mm: /* 21 i
membar #Sync
retry

- .globl __hypervisor_xcall_flush_tlb_pending
-__hypervisor_xcall_flush_tlb_pending: /* 21 insns */
- /* %g5=ctx, %g1=nr, %g7=vaddrs[], %g2,%g3,%g4,g6=scratch */
- sllx %g1, 3, %g1
+ .globl __hypervisor_xcall_flush_tlb_page
+__hypervisor_xcall_flush_tlb_page: /* 17 insns */
+ /* %g5=ctx, %g1=vaddr */
mov %o0, %g2
mov %o1, %g3
mov %o2, %g4
-1: sub %g1, (1 << 3), %g1
- ldx [%g7 + %g1], %o0 /* ARG0: virtual address */
+ mov %g1, %o0 /* ARG0: virtual address */
mov %g5, %o1 /* ARG1: mmu context */
mov HV_MMU_ALL, %o2 /* ARG2: flags */
srlx %o0, PAGE_SHIFT, %o0
@@ -613,8 +679,6 @@ __hypervisor_xcall_flush_tlb_pending: /*
mov HV_MMU_UNMAP_ADDR_TRAP, %g6
brnz,a,pn %o0, __hypervisor_tlb_xcall_error
mov %o0, %g5
- brnz,pt %g1, 1b
- nop
mov %g2, %o0
mov %g3, %o1
mov %g4, %o2
@@ -697,6 +761,13 @@ hypervisor_patch_cachetlbops:
call tlb_patch_one
mov 10, %o2

+ sethi %hi(__flush_tlb_page), %o0
+ or %o0, %lo(__flush_tlb_page), %o0
+ sethi %hi(__hypervisor_flush_tlb_page), %o1
+ or %o1, %lo(__hypervisor_flush_tlb_page), %o1
+ call tlb_patch_one
+ mov 11, %o2
+
sethi %hi(__flush_tlb_pending), %o0
or %o0, %lo(__flush_tlb_pending), %o0
sethi %hi(__hypervisor_flush_tlb_pending), %o1
@@ -728,12 +799,12 @@ hypervisor_patch_cachetlbops:
call tlb_patch_one
mov 21, %o2

- sethi %hi(xcall_flush_tlb_pending), %o0
- or %o0, %lo(xcall_flush_tlb_pending), %o0
- sethi %hi(__hypervisor_xcall_flush_tlb_pending), %o1
- or %o1, %lo(__hypervisor_xcall_flush_tlb_pending), %o1
+ sethi %hi(xcall_flush_tlb_page), %o0
+ or %o0, %lo(xcall_flush_tlb_page), %o0
+ sethi %hi(__hypervisor_xcall_flush_tlb_page), %o1
+ or %o1, %lo(__hypervisor_xcall_flush_tlb_page), %o1
call tlb_patch_one
- mov 21, %o2
+ mov 17, %o2

sethi %hi(xcall_flush_tlb_kernel_range), %o0
or %o0, %lo(xcall_flush_tlb_kernel_range), %o0

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/