sparc64: Fix race in TLB batch processing.

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@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Acked-by: Dave Kleikamp <dave.kleikamp@oracle.com>

arch/sparc/include/asm/pgtable_64.h

@@ -915,6 +915,7 @@ static inline int io_remap_pfn_range(struct vm_area_struct *vma,
 	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

arch/sparc/include/asm/switch_to_64.h

@@ -18,8 +18,7 @@ do {						\
 	 * and 2 stores in this critical code path.  -DaveM
 	 */
 #define switch_to(prev, next, last)					\
-do {	flush_tlb_pending();						\
+do {	save_and_clear_fpu();						\
-	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"			\

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)
+{
+}
 
-#define flush_tlb_range(vma,start,end)	\
+static inline void flush_tlb_page(struct vm_area_struct *vma,
-	do { (void)(start); flush_tlb_pending(); } while (0)
+				  unsigned long vmaddr)
-#define flush_tlb_page(vma,addr)	flush_tlb_pending()
+{
-#define flush_tlb_mm(mm)		flush_tlb_pending()
+}
+
+static inline void flush_tlb_range(struct vm_area_struct *vma,
+				   unsigned long start, unsigned long end)
+{
+}
+
+#define __HAVE_ARCH_ENTER_LAZY_MMU_MODE
+
+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 */

arch/sparc/kernel/smp_64.c

@@ -849,7 +849,7 @@ 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_fetch_glob_pmu;
@@ -1074,19 +1074,52 @@ 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_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_pending,
+		smp_cross_call_masked(&xcall_flush_tlb_page,
-				      ctx, nr, (unsigned long) vaddrs,
+				      context, vaddr, 0,
 				      mm_cpumask(mm));
-
+	__flush_tlb_page(context, vaddr);
-	__flush_tlb_pending(ctx, nr, vaddrs);
 
 	put_cpu();
 }

arch/sparc/mm/tlb.c

@@ -24,11 +24,17 @@ static DEFINE_PER_CPU(struct tlb_batch, 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) {
+	if (!tb->tlb_nr)
-		flush_tsb_user(tb);
+		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;
+}
+
 static void tlb_batch_add_one(struct mm_struct *mm, unsigned long vaddr,
 			      bool exec)
 {
@@ -60,6 +84,12 @@ static void tlb_batch_add_one(struct mm_struct *mm, unsigned long vaddr,
 		nr = 0;
 	}
 
+	if (!tb->active) {
+		global_flush_tlb_page(mm, vaddr);
+		flush_tsb_user_page(mm, vaddr);
+		return;
+	}
+
 	if (nr == 0)
 		tb->mm = mm;
 

arch/sparc/mm/tsb.c

@@ -7,11 +7,10 @@
 #include <linux/preempt.h>
 #include <linux/slab.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];
@@ -46,23 +45,27 @@ void flush_tsb_kernel_range(unsigned long start, unsigned long end)
 	}
 }
 
+static void __flush_tsb_one_entry(unsigned long tsb, unsigned long v,
+				  unsigned long hash_shift,
+				  unsigned long nentries)
+{
+	unsigned long tag, ent, hash;
+
+	v &= ~0x1UL;
+	hash = tsb_hash(v, hash_shift, nentries);
+	ent = tsb + (hash * sizeof(struct tsb));
+	tag = (v >> 22UL);
+
+	tsb_flush(ent, tag);
+}
+
 static void __flush_tsb_one(struct tlb_batch *tb, unsigned long hash_shift,
 			    unsigned long tsb, unsigned long nentries)
 {
 	unsigned long i;
 
-	for (i = 0; i < tb->tlb_nr; i++) {
+	for (i = 0; i < tb->tlb_nr; i++)
-		unsigned long v = tb->vaddrs[i];
+		__flush_tsb_one_entry(tsb, tb->vaddrs[i], hash_shift, nentries);
-		unsigned long tag, ent, hash;
-
-		v &= ~0x1UL;
-
-		hash = tsb_hash(v, hash_shift, nentries);
-		ent = tsb + (hash * sizeof(struct tsb));
-		tag = (v >> 22UL);
-
-		tsb_flush(ent, tag);
-	}
 }
 
 void flush_tsb_user(struct tlb_batch *tb)
@@ -90,6 +93,30 @@ void flush_tsb_user(struct tlb_batch *tb)
 	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);
+}
+
 #define HV_PGSZ_IDX_BASE	HV_PGSZ_IDX_8K
 #define HV_PGSZ_MASK_BASE	HV_PGSZ_MASK_8K
 

arch/sparc/mm/ultra.S

@@ -52,6 +52,33 @@ __flush_tlb_mm:		/* 18 insns */
 	nop
 	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 */
@@ -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
+	.globl		xcall_flush_tlb_page
-xcall_flush_tlb_pending:	/* 21 insns */
+xcall_flush_tlb_page:	/* 17 insns */
-	/* %g5=context, %g1=nr, %g7=vaddrs[] */
+	/* %g5=context, %g1=vaddr */
-	sllx		%g1, 3, %g1
 	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
+	andcc		%g1, 0x1, %g0
-	ldx		[%g7 + %g1], %g5
-	andcc		%g5, 0x1, %g0
 	be,pn		%icc, 2f
-
+	 andn		%g1, 0x1, %g5
-	 andn		%g5, 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 */
@@ -656,15 +724,13 @@ __hypervisor_xcall_flush_tlb_mm: /* 21 insns */
 	membar		#Sync
 	retry
 
-	.globl		__hypervisor_xcall_flush_tlb_pending
+	.globl		__hypervisor_xcall_flush_tlb_page
-__hypervisor_xcall_flush_tlb_pending: /* 21 insns */
+__hypervisor_xcall_flush_tlb_page: /* 17 insns */
-	/* %g5=ctx, %g1=nr, %g7=vaddrs[], %g2,%g3,%g4,g6=scratch */
+	/* %g5=ctx, %g1=vaddr */
-	sllx		%g1, 3, %g1
 	mov		%o0, %g2
 	mov		%o1, %g3
 	mov		%o2, %g4
-1:	sub		%g1, (1 << 3), %g1
+	mov		%g1, %o0	        /* ARG0: virtual address */
-	ldx		[%g7 + %g1], %o0	/* ARG0: virtual address */
 	mov		%g5, %o1		/* ARG1: mmu context */
 	mov		HV_MMU_ALL, %o2		/* ARG2: flags */
 	srlx		%o0, PAGE_SHIFT, %o0
@@ -673,8 +739,6 @@ __hypervisor_xcall_flush_tlb_pending: /* 21 insns */
 	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
@@ -757,6 +821,13 @@ 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
@@ -788,12 +859,12 @@ hypervisor_patch_cachetlbops:
 	call		tlb_patch_one
 	 mov		21, %o2
 
-	sethi		%hi(xcall_flush_tlb_pending), %o0
+	sethi		%hi(xcall_flush_tlb_page), %o0
-	or		%o0, %lo(xcall_flush_tlb_pending), %o0
+	or		%o0, %lo(xcall_flush_tlb_page), %o0
-	sethi		%hi(__hypervisor_xcall_flush_tlb_pending), %o1
+	sethi		%hi(__hypervisor_xcall_flush_tlb_page), %o1
-	or		%o1, %lo(__hypervisor_xcall_flush_tlb_pending), %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