powerpc: Add function to copy mm_context_t to the paca

PATCH Applied Michael Neuling 3 participants 8 messages Oct 28, 2015 – Jan 11, 2016 PowerPC

Share & tools

Michael Neuling

author

2015-10-28 04:54 UTC #0 lore raw

PATCH 1/2 powerpc: Add function to copy mm_context_t to the paca

This adds a function to copy the mm->context to the paca. This is only a basic conversion for now but will be used more extensively in the next patch.

This also adds #ifdef CONFIG_PPC_BOOK3S around this code since it's not used elsewhere.

Signed-off-by Michael Neuling <[email protected]>

---
 arch/powerpc/include/asm/paca.h   | 11 +++++++++++
 arch/powerpc/kernel/asm-offsets.c |  2 ++
 arch/powerpc/mm/hash_utils_64.c   |  5 +++--
 arch/powerpc/mm/slb.c             |  2 +-
 arch/powerpc/mm/slice.c           |  3 +--
 5 files changed, 18 insertions(+), 5 deletions(-)

arch/powerpc/include/asm/paca.h +11 -0

index 70bd438..1cc6e08 100644
@@ -131,7 +131,9 @@ struct paca_struct {
 	struct tlb_core_data tcd;
 #endif /* CONFIG_PPC_BOOK3E */
 
+#ifdef CONFIG_PPC_BOOK3S
 	mm_context_t context;
+#endif
 
 	/*
 	 * then miscellaneous read-write fields

@@ -194,6 +196,15 @@ struct paca_struct {
 #endif
 };
 
+#ifdef CONFIG_PPC_BOOK3S
+static inline void copy_mm_to_paca(mm_context_t *context)
+{
+	get_paca()->context = *context;
+}
+#else
+static inline void copy_mm_to_paca(mm_context_t *context){}
+#endif
+
 extern struct paca_struct *paca;
 extern void initialise_paca(struct paca_struct *new_paca, int cpu);
 extern void setup_paca(struct paca_struct *new_paca);

arch/powerpc/kernel/asm-offsets.c +2 -0

index 221d584..9db7be2 100644
@@ -185,6 +185,7 @@ int main(void)
 	DEFINE(PACAKMSR, offsetof(struct paca_struct, kernel_msr));
 	DEFINE(PACASOFTIRQEN, offsetof(struct paca_struct, soft_enabled));
 	DEFINE(PACAIRQHAPPENED, offsetof(struct paca_struct, irq_happened));
+#ifdef CONFIG_PPC_BOOK3S
 	DEFINE(PACACONTEXTID, offsetof(struct paca_struct, context.id));
 #ifdef CONFIG_PPC_MM_SLICES
 	DEFINE(PACALOWSLICESPSIZE, offsetof(struct paca_struct,

@@ -193,6 +194,7 @@ int main(void)
 					    context.high_slices_psize));
 	DEFINE(MMUPSIZEDEFSIZE, sizeof(struct mmu_psize_def));
 #endif /* CONFIG_PPC_MM_SLICES */
+#endif
 
 #ifdef CONFIG_PPC_BOOK3E
 	DEFINE(PACAPGD, offsetof(struct paca_struct, pgd));

arch/powerpc/mm/hash_utils_64.c +3 -2

index aee7017..fa62eb0 100644
@@ -906,7 +906,8 @@ void demote_segment_4k(struct mm_struct *mm, unsigned long addr)
 	slice_set_range_psize(mm, addr, 1, MMU_PAGE_4K);
 	copro_flush_all_slbs(mm);
 	if ((get_paca_psize(addr) != MMU_PAGE_4K) && (current->mm == mm)) {
-		get_paca()->context = mm->context;
+
+		copy_mm_to_paca(&mm->context);
 		slb_flush_and_rebolt();
 	}
 }

@@ -973,7 +974,7 @@ static void check_paca_psize(unsigned long ea, struct mm_struct *mm,
 {
 	if (user_region) {
 		if (psize != get_paca_psize(ea)) {
-			get_paca()->context = mm->context;
+			copy_mm_to_paca(&mm->context);
 			slb_flush_and_rebolt();
 		}
 	} else if (get_paca()->vmalloc_sllp !=

arch/powerpc/mm/slb.c +1 -1

index 8a32a2be..4412b8e 100644
@@ -223,7 +223,7 @@ void switch_slb(struct task_struct *tsk, struct mm_struct *mm)
 		asm volatile("slbie %0" : : "r" (slbie_data));
 
 	get_paca()->slb_cache_ptr = 0;
-	get_paca()->context = mm->context;
+	copy_mm_to_paca(&mm->context);
 
 	/*
 	 * preload some userspace segments into the SLB.

arch/powerpc/mm/slice.c +1 -2

index 0f432a7..42954f0 100644
@@ -185,8 +185,7 @@ static void slice_flush_segments(void *parm)
 	if (mm != current->active_mm)
 		return;
 
-	/* update the paca copy of the context struct */
-	get_paca()->context = current->active_mm->context;
+	copy_mm_to_paca(&current->active_mm->context);
 
 	local_irq_save(flags);
 	slb_flush_and_rebolt();

Signature · 1 line

2.5.0

Michael Neuling

author

2015-10-28 04:54 UTC #1 lore raw

PATCH 2/2 powerpc: Copy only required pieces of the mm_context_t to the paca

Currently we copy the whole mm_context_t to the paca but only access a few bits of it. This is wasteful of space paca and also takes quite some time in the hot path of context switching.

This patch pulls in only the required bits from the mm_context_t to the paca and on context switch, copies only those.

Benchmarking this (On top of Anton's recent MSR context switching changes [1]) using processes and yield shows an improvement of almost 3% on POWER8:

  http://ozlabs.org/~anton/junkcode/context_switch2.c
  ./context_switch2 --test=yield --process 0 0

1. https://lists.ozlabs.org/pipermail/linuxppc-dev/2015-October/135700.html

Signed-off-by Michael Neuling <[email protected]>

---
 arch/powerpc/include/asm/paca.h   | 17 +++++++++++++++--
 arch/powerpc/kernel/asm-offsets.c |  8 ++++----
 arch/powerpc/mm/hash_utils_64.c   |  4 ++--
 3 files changed, 21 insertions(+), 8 deletions(-)

arch/powerpc/include/asm/paca.h +15 -2

index 1cc6e08..1c0d9f4 100644
@@ -132,7 +132,13 @@ struct paca_struct {
 #endif /* CONFIG_PPC_BOOK3E */
 
 #ifdef CONFIG_PPC_BOOK3S
-	mm_context_t context;
+	mm_context_id_t context_id;
+#ifdef CONFIG_PPC_MM_SLICES
+	u64 context_low_slices_psize;
+	unsigned char context_high_slices_psize[SLICE_ARRAY_SIZE];
+#else
+	u16 context_sllp;
+#endif
 #endif
 
 	/*

@@ -199,7 +205,14 @@ struct paca_struct {
 #ifdef CONFIG_PPC_BOOK3S
 static inline void copy_mm_to_paca(mm_context_t *context)
 {
-	get_paca()->context = *context;
+	get_paca()->context_id = context->id;
+#ifdef CONFIG_PPC_MM_SLICES
+	get_paca()->context_low_slices_psize = context->low_slices_psize;
+	memcpy(&get_paca()->context_high_slices_psize,
+	       &context->high_slices_psize, SLICE_ARRAY_SIZE);
+#else
+	get_paca()->context_sllp = context->sllp;
+#endif
 }
 #else
 static inline void copy_mm_to_paca(mm_context_t *context){}

arch/powerpc/kernel/asm-offsets.c +4 -4

index 9db7be2..d5903a9 100644
@@ -186,12 +186,12 @@ int main(void)
 	DEFINE(PACASOFTIRQEN, offsetof(struct paca_struct, soft_enabled));
 	DEFINE(PACAIRQHAPPENED, offsetof(struct paca_struct, irq_happened));
 #ifdef CONFIG_PPC_BOOK3S
-	DEFINE(PACACONTEXTID, offsetof(struct paca_struct, context.id));
+	DEFINE(PACACONTEXTID, offsetof(struct paca_struct, context_id));
 #ifdef CONFIG_PPC_MM_SLICES
 	DEFINE(PACALOWSLICESPSIZE, offsetof(struct paca_struct,
-					    context.low_slices_psize));
+					    context_low_slices_psize));
 	DEFINE(PACAHIGHSLICEPSIZE, offsetof(struct paca_struct,
-					    context.high_slices_psize));
+					    context_high_slices_psize));
 	DEFINE(MMUPSIZEDEFSIZE, sizeof(struct mmu_psize_def));
 #endif /* CONFIG_PPC_MM_SLICES */
 #endif

@@ -224,7 +224,7 @@ int main(void)
 #ifdef CONFIG_PPC_MM_SLICES
 	DEFINE(MMUPSIZESLLP, offsetof(struct mmu_psize_def, sllp));
 #else
-	DEFINE(PACACONTEXTSLLP, offsetof(struct paca_struct, context.sllp));
+	DEFINE(PACACONTEXTSLLP, offsetof(struct paca_struct, context_sllp));
 #endif /* CONFIG_PPC_MM_SLICES */
 	DEFINE(PACA_EXGEN, offsetof(struct paca_struct, exgen));
 	DEFINE(PACA_EXMC, offsetof(struct paca_struct, exmc));

arch/powerpc/mm/hash_utils_64.c +2 -2

index fa62eb0..0e087e4 100644
@@ -877,11 +877,11 @@ static unsigned int get_paca_psize(unsigned long addr)
 	unsigned long index, mask_index;
 
 	if (addr < SLICE_LOW_TOP) {
-		lpsizes = get_paca()->context.low_slices_psize;
+		lpsizes = get_paca()->context_low_slices_psize;
 		index = GET_LOW_SLICE_INDEX(addr);
 		return (lpsizes >> (index * 4)) & 0xF;
 	}
-	hpsizes = get_paca()->context.high_slices_psize;
+	hpsizes = get_paca()->context_high_slices_psize;
 	index = GET_HIGH_SLICE_INDEX(addr);
 	mask_index = index & 0x1;
 	return (hpsizes[index >> 1] >> (mask_index * 4)) & 0xF;

Signature · 1 line

2.5.0

Anton Blanchard

2015-12-09 12:17 UTC #2 lore raw

Re: [PATCH 2/2] powerpc: Copy only required pieces of the mm_context_t to the paca

Quoted 7 lines

Currently we copy the whole mm_context_t to the paca but only access a few bits of it. This is wasteful of space paca and also takes quite some time in the hot path of context switching.
This patch pulls in only the required bits from the mm_context_t to the paca and on context switch, copies only those.

Quoted 6 lines

Benchmarking this (On top of Anton's recent MSR context switching changes [1]) using processes and yield shows an improvement of almost 3% on POWER8:
  http://ozlabs.org/~anton/junkcode/context_switch2.c
  ./context_switch2 --test=yield --process 0 0

Now the context switch series is in, I tested this against powerpc-next and still see a ~3% improvement.

Anton

Quoted 98 lines

1.
https://lists.ozlabs.org/pipermail/linuxppc-dev/2015-October/135700.html

Signed-off-by Michael Neuling <[email protected]>

---
 arch/powerpc/include/asm/paca.h   | 17 +++++++++++++++--
 arch/powerpc/kernel/asm-offsets.c |  8 ++++----
 arch/powerpc/mm/hash_utils_64.c   |  4 ++--
 3 files changed, 21 insertions(+), 8 deletions(-)

(quoted diff) +0 -0

b/arch/powerpc/include/asm/paca.h index 1cc6e08..1c0d9f4 100644

arch/powerpc/include/asm/paca.h +15 -2

@@ -132,7 +132,13 @@ struct paca_struct {
 #endif /* CONFIG_PPC_BOOK3E */
 
 #ifdef CONFIG_PPC_BOOK3S
-	mm_context_t context;
+	mm_context_id_t context_id;
+#ifdef CONFIG_PPC_MM_SLICES
+	u64 context_low_slices_psize;
+	unsigned char context_high_slices_psize[SLICE_ARRAY_SIZE];
+#else
+	u16 context_sllp;
+#endif
 #endif
 
 	/*

@@ -199,7 +205,14 @@ struct paca_struct {
 #ifdef CONFIG_PPC_BOOK3S
 static inline void copy_mm_to_paca(mm_context_t *context)
 {
-	get_paca()->context = *context;
+	get_paca()->context_id = context->id;
+#ifdef CONFIG_PPC_MM_SLICES
+	get_paca()->context_low_slices_psize =
 context->low_slices_psize;
+	memcpy(&get_paca()->context_high_slices_psize,
+	       &context->high_slices_psize, SLICE_ARRAY_SIZE);
+#else
+	get_paca()->context_sllp = context->sllp;
+#endif
 }
 #else

static inline void copy_mm_to_paca(mm_context_t *context){}

(quoted diff) +0 -0

b/arch/powerpc/kernel/asm-offsets.c index 9db7be2..d5903a9 100644

arch/powerpc/kernel/asm-offsets.c +0 -0

@@ -186,12 +186,12 @@ int main(void)
 	DEFINE(PACASOFTIRQEN, offsetof(struct paca_struct,
 soft_enabled)); DEFINE(PACAIRQHAPPENED, offsetof(struct paca_struct,

irq_happened)); #ifdef CONFIG_PPC_BOOK3S

arch/powerpc/kernel/asm-offsets.c +0 -1

-	DEFINE(PACACONTEXTID, offsetof(struct paca_struct,

context.id));

arch/powerpc/kernel/asm-offsets.c +1 -0

+	DEFINE(PACACONTEXTID, offsetof(struct paca_struct,

context_id)); #ifdef CONFIG_PPC_MM_SLICES

arch/powerpc/kernel/asm-offsets.c +0 -1

 	DEFINE(PACALOWSLICESPSIZE, offsetof(struct paca_struct,
-

context.low_slices_psize));
+
context_low_slices_psize)); DEFINE(PACAHIGHSLICEPSIZE, offsetof(struct paca_struct,
-
context.high_slices_psize));
+
context_high_slices_psize)); DEFINE(MMUPSIZEDEFSIZE, sizeof(struct mmu_psize_def)); #endif /* CONFIG_PPC_MM_SLICES */
#endif

arch/powerpc/kernel/asm-offsets.c +1 -1

@@ -224,7 +224,7 @@ int main(void)
 #ifdef CONFIG_PPC_MM_SLICES
 	DEFINE(MMUPSIZESLLP, offsetof(struct mmu_psize_def, sllp));
 #else
-	DEFINE(PACACONTEXTSLLP, offsetof(struct paca_struct,
 context.sllp));
+	DEFINE(PACACONTEXTSLLP, offsetof(struct paca_struct,

context_sllp)); #endif /* CONFIG_PPC_MM_SLICES */

arch/powerpc/kernel/asm-offsets.c +0 -0

 	DEFINE(PACA_EXGEN, offsetof(struct paca_struct, exgen));
 	DEFINE(PACA_EXMC, offsetof(struct paca_struct, exmc));

(quoted diff) +0 -0

b/arch/powerpc/mm/hash_utils_64.c index fa62eb0..0e087e4 100644

arch/powerpc/mm/hash_utils_64.c +2 -2

@@ -877,11 +877,11 @@ static unsigned int get_paca_psize(unsigned
 long addr) unsigned long index, mask_index;
 
 	if (addr < SLICE_LOW_TOP) {
-		lpsizes = get_paca()->context.low_slices_psize;
+		lpsizes = get_paca()->context_low_slices_psize;
 		index = GET_LOW_SLICE_INDEX(addr);
 		return (lpsizes >> (index * 4)) & 0xF;
 	}
-	hpsizes = get_paca()->context.high_slices_psize;
+	hpsizes = get_paca()->context_high_slices_psize;
 	index = GET_HIGH_SLICE_INDEX(addr);
 	mask_index = index & 0x1;
 	return (hpsizes[index >> 1] >> (mask_index * 4)) & 0xF;

Michael Neuling

author

2015-12-10 03:46 UTC #3 lore raw

PATCH v2 2/2 powerpc: Copy only required pieces of the mm_context_t to the paca

In reply to Michael Neuling

Currently we copy the whole mm_context_t to the paca but only access a few bits of it. This is wasteful of space paca and also takes quite some time in the hot path of context switching.

This patch pulls in only the required bits from the mm_context_t to the paca and on context switch, copies only those.

Benchmarking this (On top of Anton's recent MSR context switching changes [1]) using processes and yield shows an improvement of almost 3% on POWER8:

  http://ozlabs.org/~anton/junkcode/context_switch2.c
  ./context_switch2 --test=3Dyield --process 0 0

1. https://lists.ozlabs.org/pipermail/linuxppc-dev/2015-October/135700.
html

Signed-off-by Michael Neuling <[email protected]>

---
v2:
Added missing include which broke allmodconfig (noticed by anton)

 include/asm/paca.h   |   18 ++++++++++++++++--
 kernel/asm-offsets.c |    8 ++++----
 mm/hash_utils_64.c   |    4 ++--
 3 files changed, 22 insertions(+), 8 deletions(-)

(quoted diff) +0 -0

b/arch/powerpc/include/asm/paca.h
index 1cc6e08..06cdaee 100644

arch/powerpc/include/asm/paca.h +0 -0

@@ -16,6 +16,7 @@

=20
#ifdef CONFIG_PPC64
=20
+#include <linux/string.h>
#include <asm/types.h>
#include <asm/lppaca.h>
#include <asm/mmu.h>
@@ -132,7 +133,13 @@ struct paca_struct {
#endif /* CONFIG_PPC_BOOK3E */
=20
#ifdef CONFIG_PPC_BOOK3S
- mm_context_t context;
+ mm_context_id_t context_id;
+#ifdef CONFIG_PPC_MM_SLICES
+ u64 context_low_slices_psize;
+ unsigned char context_high_slices_psize[SLICE_ARRAY_SIZE];
+#else
+ u16 context_sllp;
+#endif
#endif
=20
/*
@@ -199,7 +206,14 @@ struct paca_struct {
#ifdef CONFIG_PPC_BOOK3S
static inline void copy_mm_to_paca(mm_context_t *context) {
- get_paca()->context =3D *context;
+ get_paca()->context_id =3D context->id;
+#ifdef CONFIG_PPC_MM_SLICES
+ get_paca()->context_low_slices_psize =3D context
->low_slices_psize;
+ memcpy(&get_paca()->context_high_slices_psize,
+ &context->high_slices_psize, SLICE_ARRAY_SIZE);
+#else
+ get_paca()->context_sllp =3D context->sllp;
+#endif
}
#else
static inline void copy_mm_to_paca(mm_context_t *context){}

(quoted diff) +0 -0

b/arch/powerpc/kernel/asm-offsets.c
index 9db7be2..d5903a9 100644

arch/powerpc/kernel/asm-offsets.c +0 -0

@@ -186,12 +186,12 @@ int main(void)
 	DEFINE(PACASOFTIRQEN, offsetof(struct paca_struct,

soft_enabled));
DEFINE(PACAIRQHAPPENED, offsetof(struct paca_struct,
irq_happened));
#ifdef CONFIG_PPC_BOOK3S
- DEFINE(PACACONTEXTID, offsetof(struct paca_struct,
context.id));
+ DEFINE(PACACONTEXTID, offsetof(struct paca_struct,
context_id));
#ifdef CONFIG_PPC_MM_SLICES
DEFINE(PACALOWSLICESPSIZE, offsetof(struct paca_struct,
- =20
context.low_slices_psize));
+ =20
context_low_slices_psize));
DEFINE(PACAHIGHSLICEPSIZE, offsetof(struct paca_struct,
- =20
context.high_slices_psize));
+ =20
context_high_slices_psize));
DEFINE(MMUPSIZEDEFSIZE, sizeof(struct mmu_psize_def));
#endif /* CONFIG_PPC_MM_SLICES */
#endif
@@ -224,7 +224,7 @@ int main(void)
#ifdef CONFIG_PPC_MM_SLICES
DEFINE(MMUPSIZESLLP, offsetof(struct mmu_psize_def, sllp));
#else
- DEFINE(PACACONTEXTSLLP, offsetof(struct paca_struct,
context.sllp));
+ DEFINE(PACACONTEXTSLLP, offsetof(struct paca_struct,
context_sllp));
#endif /* CONFIG_PPC_MM_SLICES */
DEFINE(PACA_EXGEN, offsetof(struct paca_struct, exgen)); DEFINE(PACA_EXMC, offsetof(struct paca_struct, exmc));

(quoted diff) +0 -0

b/arch/powerpc/mm/hash_utils_64.c
index 0aa526e..ae98d58 100644

arch/powerpc/mm/hash_utils_64.c +0 -0

@@ -877,11 +877,11 @@ static unsigned int get_paca_psize(unsigned long

addr)
unsigned long index, mask_index;
=20
if (addr < SLICE_LOW_TOP) {
- lpsizes =3D get_paca()->context.low_slices_psize;
+ lpsizes =3D get_paca()->context_low_slices_psize;
index =3D GET_LOW_SLICE_INDEX(addr); return (lpsizes >> (index * 4)) & 0xF;
}
- hpsizes =3D get_paca()->context.high_slices_psize;
+ hpsizes =3D get_paca()->context_high_slices_psize;
index =3D GET_HIGH_SLICE_INDEX(addr); mask_index =3D index & 0x1;
return (hpsizes[index >> 1] >> (mask_index * 4)) & 0xF;

Michael Ellerman

reviewer

2015-12-10 10:00 UTC #4 lore raw

Re: [PATCH v2 2/2] powerpc: Copy only required pieces of the mm_context_t to the paca

Quoted 10 lines · Michael Neuling

Currently we copy the whole mm_context_t to the paca but only access a few bits of it. This is wasteful of space paca and also takes quite some time in the hot path of context switching.
arch/powerpc/include/asm/paca.h +0 -0
index 1cc6e08..06cdaee 100644

arch/powerpc/include/asm/paca.h struct paca_struct { · line 203

Quoted 8 lines

arch/powerpc/include/asm/paca.h +3 -2

@@ -199,7 +206,14 @@ struct paca_struct {
 #ifdef CONFIG_PPC_BOOK3S
 static inline void copy_mm_to_paca(mm_context_t *context)
 {
-	get_paca()->context = *context;
+	get_paca()->context_id = context->id;
+#ifdef CONFIG_PPC_MM_SLICES
+	get_paca()->context_low_slices_psize = context
->low_slices_psize;

Patch is wrapped ^

And so on.

cheers

Michael Neuling

author

2015-12-10 22:34 UTC #5 lore raw

PATCH v3 2/2 powerpc: Copy only required pieces of the mm_context_t to the paca

Currently we copy the whole mm_context_t to the paca but only access a few bits of it. This is wasteful of space paca and also takes quite some time in the hot path of context switching.

This patch pulls in only the required bits from the mm_context_t to the paca and on context switch, copies only those.

Benchmarking this (On top of Anton's recent MSR context switching changes [1]) using processes and yield shows an improvement of almost 3% on POWER8:

  http://ozlabs.org/~anton/junkcode/context_switch2.c
  ./context_switch2 --test=3Dyield --process 0 0

1. https://lists.ozlabs.org/pipermail/linuxppc-dev/2015-October/135700.html

Signed-off-by Michael Neuling <[email protected]>

--
v3:
Fix line wrapping (WTF sorry!?!)
v2:
Added missing include which broke allmodconfig (noticed by anton)

arch/powerpc/include/asm/pac= renamed from arch/powerpc/include/asm/paca.h +0 -0

a.h
index 1cc6e08..06cdaee 100644

arch/powerpc/include/asm/paca.h +0 -0

@@ -16,6 +16,7 @@

=20
#ifdef CONFIG_PPC64
=20
+#include <linux/string.h>
#include <asm/types.h>
#include <asm/lppaca.h>
#include <asm/mmu.h>
@@ -132,7 +133,13 @@ struct paca_struct {
#endif /* CONFIG_PPC_BOOK3E */
=20
#ifdef CONFIG_PPC_BOOK3S
- mm_context_t context;
+ mm_context_id_t context_id;
+#ifdef CONFIG_PPC_MM_SLICES
+ u64 context_low_slices_psize;
+ unsigned char context_high_slices_psize[SLICE_ARRAY_SIZE];
+#else
+ u16 context_sllp;
+#endif
#endif
=20
/*
@@ -199,7 +206,14 @@ struct paca_struct {
#ifdef CONFIG_PPC_BOOK3S
static inline void copy_mm_to_paca(mm_context_t *context) {
- get_paca()->context =3D *context;
+ get_paca()->context_id =3D context->id;
+#ifdef CONFIG_PPC_MM_SLICES
+ get_paca()->context_low_slices_psize =3D context->low_slices_psize;
+ memcpy(&get_paca()->context_high_slices_psize,
+ &context->high_slices_psize, SLICE_ARRAY_SIZE);
+#else
+ get_paca()->context_sllp =3D context->sllp;
+#endif
}
#else
static inline void copy_mm_to_paca(mm_context_t *context){}

arch/powerpc/kernel/asm-of= renamed from arch/powerpc/kernel/asm-offsets.c +0 -0

fsets.c
index 9db7be2..d5903a9 100644

arch/powerpc/kernel/asm-offsets.c +4 -4

@@ -186,12 +186,12 @@ int main(void)
 	DEFINE(PACASOFTIRQEN, offsetof(struct paca_struct, soft_enabled));
 	DEFINE(PACAIRQHAPPENED, offsetof(struct paca_struct, irq_happened));
 #ifdef CONFIG_PPC_BOOK3S
-	DEFINE(PACACONTEXTID, offsetof(struct paca_struct, context.id));
+	DEFINE(PACACONTEXTID, offsetof(struct paca_struct, context_id));
 #ifdef CONFIG_PPC_MM_SLICES
 	DEFINE(PACALOWSLICESPSIZE, offsetof(struct paca_struct,
-					    context.low_slices_psize));
+					    context_low_slices_psize));
 	DEFINE(PACAHIGHSLICEPSIZE, offsetof(struct paca_struct,
-					    context.high_slices_psize));
+					    context_high_slices_psize));
 	DEFINE(MMUPSIZEDEFSIZE, sizeof(struct mmu_psize_def));
 #endif /* CONFIG_PPC_MM_SLICES */
 #endif

@@ -224,7 +224,7 @@ int main(void)
 #ifdef CONFIG_PPC_MM_SLICES
 	DEFINE(MMUPSIZESLLP, offsetof(struct mmu_psize_def, sllp));
 #else
-	DEFINE(PACACONTEXTSLLP, offsetof(struct paca_struct, context.sllp));
+	DEFINE(PACACONTEXTSLLP, offsetof(struct paca_struct, context_sllp));
 #endif /* CONFIG_PPC_MM_SLICES */
 	DEFINE(PACA_EXGEN, offsetof(struct paca_struct, exgen));
 	DEFINE(PACA_EXMC, offsetof(struct paca_struct, exmc));

arch/powerpc/mm/hash_utils_6= renamed from arch/powerpc/mm/hash_utils_64.c +0 -0

4.c
index 0aa526e..ae98d58 100644

arch/powerpc/mm/hash_utils_64.c +0 -0

@@ -877,11 +877,11 @@ static unsigned int get_paca_psize(unsigned long addr=

)
unsigned long index, mask_index;
=20
if (addr < SLICE_LOW_TOP) {
- lpsizes =3D get_paca()->context.low_slices_psize;
+ lpsizes =3D get_paca()->context_low_slices_psize;
index =3D GET_LOW_SLICE_INDEX(addr); return (lpsizes >> (index * 4)) & 0xF;
}
- hpsizes =3D get_paca()->context.high_slices_psize;
+ hpsizes =3D get_paca()->context_high_slices_psize;
index =3D GET_HIGH_SLICE_INDEX(addr); mask_index =3D index & 0x1;
return (hpsizes[index >> 1] >> (mask_index * 4)) & 0xF;

Michael Ellerman

reviewer Applied

2016-01-11 09:14 UTC #6 lore raw

Re: [v3, 2/2] powerpc: Copy only required pieces of the mm_context_t to the paca

Quoted 11 lines · Michael Neuling

Currently we copy the whole mm_context_t to the paca but only access a few bits of it. This is wasteful of space paca and also takes quite some time in the hot path of context switching.
This patch pulls in only the required bits from the mm_context_t to the paca and on context switch, copies only those.
Benchmarking this (On top of Anton's recent MSR context switching changes [1]) using processes and yield shows an improvement of almost 3% on POWER8:

Quoted 6 lines

  http://ozlabs.org/~anton/junkcode/context_switch2.c
  ./context_switch2 --test=yield --process 0 0
1. https://lists.ozlabs.org/pipermail/linuxppc-dev/2015-October/135700.html
Signed-off-by Michael Neuling <[email protected]>

Applied to powerpc next, thanks.

https://git.kernel.org/powerpc/c/2fc251a8dda56b71ec491bee4c

cheers

Michael Ellerman

reviewer Applied

2016-01-11 09:14 UTC #7 lore raw

In reply to Michael Neuling

Quoted 8 lines · Michael Neuling

This adds a function to copy the mm->context to the paca. This is only a basic conversion for now but will be used more extensively in the next patch.
This also adds #ifdef CONFIG_PPC_BOOK3S around this code since it's not used elsewhere.
Signed-off-by Michael Neuling <[email protected]>

Applied to powerpc next, thanks.

https://git.kernel.org/powerpc/c/c395465da68bfc3a238d5bc15f

cheers