Patchwork sparc64: Don't pass a pointer to xcall_flush_tlb_pending

login
register
mail settings
Submitter David Miller
Date April 19, 2013, 12:51 a.m.
Message ID <20130418.205139.332106502286987132.davem@davemloft.net>
Download mbox | patch
Permalink /patch/237777/
State RFC
Delegated to: David Miller
Headers show

Comments

David Miller - April 19, 2013, 12:51 a.m.
From: David Miller <davem@davemloft.net>
Date: Wed, 17 Apr 2013 18:44:45 -0400 (EDT)

> It's not that difficult, I implemented a patch and will post it
> after I'm done debugging it.

Here's what I've been stress testing.

This deals with a whole slew of problems all in one go.

1) Use generic smp_call_function_many() so that we don't have to write
   our own synchronization mechanism.  This function does not return
   until all cross call siblings finish their work.

2) Use the paravirtualization hooks arch_{enter,leave}_lazy_mmu_mode,
   to guard when we actually do batching.  This also makes sure we do
   batching inside of the page table locks which will be beneficial in
   the future.

   This idea is taken from powerpc.

3) When the batcher is not active, we flush a page at a time,
   synchronously.

4) Another side effect is that the batch cross call now runs with a
   full environment rather than within an interrupt vector trap
   handler.  There has been talk of adding support for batched TLB
   flushes in the sun4v hypervisor, so that we don't have to perform a
   full hypervisor trap for every page, and having more registers to
   work with will facilitate being able to take advantage of that.

5) We no longer flush the batch from switch_to() which means we don't
   do it with interrupts disabled and the runqueue locks held.

This passed a loop of make -j128 kernel builds on a SPARC-T4 as well
as a gcc bootstrap and testsuite run.  I plan to do some quick testing
on a cheetah based system tomorrow in order to make sure the non-sun4v
code paths work fine.

Dave, can you see if this patch fixes your test case?

--
To unsubscribe from this list: send the line "unsubscribe sparclinux" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Dave Kleikamp - April 19, 2013, 2:46 p.m.
On 04/18/2013 07:51 PM, David Miller wrote:
> From: David Miller <davem@davemloft.net>
> Date: Wed, 17 Apr 2013 18:44:45 -0400 (EDT)
> 
>> It's not that difficult, I implemented a patch and will post it
>> after I'm done debugging it.
> 
> Here's what I've been stress testing.
> 
> This deals with a whole slew of problems all in one go.
> 
> 1) Use generic smp_call_function_many() so that we don't have to write
>    our own synchronization mechanism.  This function does not return
>    until all cross call siblings finish their work.
> 
> 2) Use the paravirtualization hooks arch_{enter,leave}_lazy_mmu_mode,
>    to guard when we actually do batching.  This also makes sure we do
>    batching inside of the page table locks which will be beneficial in
>    the future.
> 
>    This idea is taken from powerpc.
> 
> 3) When the batcher is not active, we flush a page at a time,
>    synchronously.
> 
> 4) Another side effect is that the batch cross call now runs with a
>    full environment rather than within an interrupt vector trap
>    handler.  There has been talk of adding support for batched TLB
>    flushes in the sun4v hypervisor, so that we don't have to perform a
>    full hypervisor trap for every page, and having more registers to
>    work with will facilitate being able to take advantage of that.
> 
> 5) We no longer flush the batch from switch_to() which means we don't
>    do it with interrupts disabled and the runqueue locks held.
> 
> This passed a loop of make -j128 kernel builds on a SPARC-T4 as well
> as a gcc bootstrap and testsuite run.  I plan to do some quick testing
> on a cheetah based system tomorrow in order to make sure the non-sun4v
> code paths work fine.
> 
> Dave, can you see if this patch fixes your test case?

It does fix it. I do have one concern though...

> diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c
> index 537eb66..33bd996 100644
> --- a/arch/sparc/kernel/smp_64.c
> +++ b/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;
> @@ -1074,23 +1074,47 @@ 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(unsigned long context, unsigned long vaddr)
> +{
> +	smp_cross_call(&xcall_flush_tlb_page,
> +		       context, vaddr, 0);
> +	__flush_tlb_page(context, vaddr);
> +}
> +

Why not pass mm into smp_flush_tlb_page() and use mm_cpumask(mm) as is
done in smp_flush_tlb_pending()? I don't see why we wouldn't want to
duplicate that logic to avoid cross calls to every cpu for every
non-batched flush.

>  void smp_flush_tlb_kernel_range(unsigned long start, unsigned long end)
>  {
>  	start &= PAGE_MASK;
--
To unsubscribe from this list: send the line "unsubscribe sparclinux" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Patch

diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h
index 08fcce9..7619f2f 100644
--- a/arch/sparc/include/asm/pgtable_64.h
+++ b/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
diff --git a/arch/sparc/include/asm/switch_to_64.h b/arch/sparc/include/asm/switch_to_64.h
index cad36f5..c7de332 100644
--- a/arch/sparc/include/asm/switch_to_64.h
+++ b/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();						\
-	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"			\
diff --git a/arch/sparc/include/asm/tlbflush_64.h b/arch/sparc/include/asm/tlbflush_64.h
index 2ef4634..d4b56bb 100644
--- 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 +54,22 @@  do {	flush_tsb_kernel_range(start,end); \
 	__flush_tlb_kernel_range(start,end); \
 } while (0)
 
+#define global_flush_tlb_page(context, vaddr) \
+	__flush_tlb_page(context, vaddr)
+
 #else /* CONFIG_SMP */
 
 extern void smp_flush_tlb_kernel_range(unsigned long start, unsigned long end);
+extern void smp_flush_tlb_page(unsigned long context, 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(context, vaddr) \
+	smp_flush_tlb_page(context, vaddr)
+
 #endif /* ! CONFIG_SMP */
 
 #endif /* _SPARC64_TLBFLUSH_H */
diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c
index 537eb66..33bd996 100644
--- a/arch/sparc/kernel/smp_64.c
+++ b/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;
@@ -1074,23 +1074,47 @@  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(unsigned long context, unsigned long vaddr)
+{
+	smp_cross_call(&xcall_flush_tlb_page,
+		       context, vaddr, 0);
+	__flush_tlb_page(context, vaddr);
+}
+
 void smp_flush_tlb_kernel_range(unsigned long start, unsigned long end)
 {
 	start &= PAGE_MASK;
diff --git a/arch/sparc/mm/tlb.c b/arch/sparc/mm/tlb.c
index ba6ae7f..26ddb58 100644
--- a/arch/sparc/mm/tlb.c
+++ b/arch/sparc/mm/tlb.c
@@ -43,6 +43,22 @@  void flush_tlb_pending(void)
 	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 +76,12 @@  static void tlb_batch_add_one(struct mm_struct *mm, unsigned long vaddr,
 		nr = 0;
 	}
 
+	if (!tb->active) {
+		global_flush_tlb_page(CTX_HWBITS(mm->context), vaddr);
+		flush_tsb_user_page(mm, vaddr);
+		return;
+	}
+
 	if (nr == 0)
 		tb->mm = mm;
 
diff --git a/arch/sparc/mm/tsb.c b/arch/sparc/mm/tsb.c
index 428982b..2cc3bce 100644
--- a/arch/sparc/mm/tsb.c
+++ b/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(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)
@@ -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
 
diff --git a/arch/sparc/mm/ultra.S b/arch/sparc/mm/ultra.S
index f8e13d4..432aa0c 100644
--- 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 */
@@ -656,15 +724,13 @@  __hypervisor_xcall_flush_tlb_mm: /* 21 insns */
 	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
@@ -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
-	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