powerpc/book3e-64: use a separate TLB handler when linear map is bolted

On MMUs such as FSL where we can guarantee the entire linear mapping is
bolted, we don't need to worry about linear TLB misses.  If on top of
that we do a full table walk, we get rid of all recursive TLB faults, and
can dispense with some state saving.  This gains a few percent on
TLB-miss-heavy workloads, and around 50% on a benchmark that had a high
rate of virtual page table faults under the normal handler.

While touching the EX_TLB layout, remove EX_TLB_MMUCR0, EX_TLB_SRR0, and
EX_TLB_SRR1 as they're not used.

[BenH: Fixed build with 64K pages (wsp config)]

Signed-off-by: Scott Wood <scottwood@freescale.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>

2 files changed, 38 insertions, 21 deletions

diff --git a/arch/powerpc/include/asm/exception-64e.h b/arch/powerpc/include/asm/exception-64e.h
index 6d53f311d94..ac13addb849 100644
--- a/arch/powerpc/include/asm/exception-64e.h
+++ b/arch/powerpc/include/asm/exception-64e.h
@@ -48,30 +48,33 @@
 #define EX_R14		(4 * 8)
 #define EX_R15		(5 * 8)
 
-/* The TLB miss exception uses different slots */
+/*
+ * The TLB miss exception uses different slots.
+ *
+ * The bolted variant uses only the first six fields,
+ * which in combination with pgd and kernel_pgd fits in
+ * one 64-byte cache line.
+ */
 
 #define EX_TLB_R10	( 0 * 8)
 #define EX_TLB_R11	( 1 * 8)
-#define EX_TLB_R12	( 2 * 8)
-#define EX_TLB_R13	( 3 * 8)
-#define EX_TLB_R14	( 4 * 8)
-#define EX_TLB_R15	( 5 * 8)
-#define EX_TLB_R16	( 6 * 8)
-#define EX_TLB_CR	( 7 * 8)
+#define EX_TLB_R14	( 2 * 8)
+#define EX_TLB_R15	( 3 * 8)
+#define EX_TLB_R16	( 4 * 8)
+#define EX_TLB_CR	( 5 * 8)
+#define EX_TLB_R12	( 6 * 8)
+#define EX_TLB_R13	( 7 * 8)
 #define EX_TLB_DEAR	( 8 * 8) /* Level 0 and 2 only */
 #define EX_TLB_ESR	( 9 * 8) /* Level 0 and 2 only */
 #define EX_TLB_SRR0	(10 * 8)
 #define EX_TLB_SRR1	(11 * 8)
-#define EX_TLB_MMUCR0	(12 * 8) /* Level 0 */
-#define EX_TLB_MAS1	(12 * 8) /* Level 0 */
-#define EX_TLB_MAS2	(13 * 8) /* Level 0 */
 #ifdef CONFIG_BOOK3E_MMU_TLB_STATS
-#define EX_TLB_R8	(14 * 8)
-#define EX_TLB_R9	(15 * 8)
-#define EX_TLB_LR	(16 * 8)
-#define EX_TLB_SIZE	(17 * 8)
+#define EX_TLB_R8	(12 * 8)
+#define EX_TLB_R9	(13 * 8)
+#define EX_TLB_LR	(14 * 8)
+#define EX_TLB_SIZE	(15 * 8)
 #else
-#define EX_TLB_SIZE	(14 * 8)
+#define EX_TLB_SIZE	(12 * 8)
 #endif
 
 #define	START_EXCEPTION(label)						\
@@ -168,6 +171,16 @@ exc_##label##_book3e:
 	ld	r9,EX_TLB_R9(r12);					    \
 	ld	r8,EX_TLB_R8(r12);					    \
 	mtlr	r16;
+#define TLB_MISS_PROLOG_STATS_BOLTED						    \
+	mflr	r10;							    \
+	std	r8,PACA_EXTLB+EX_TLB_R8(r13);				    \
+	std	r9,PACA_EXTLB+EX_TLB_R9(r13);				    \
+	std	r10,PACA_EXTLB+EX_TLB_LR(r13);
+#define TLB_MISS_RESTORE_STATS_BOLTED					            \
+	ld	r16,PACA_EXTLB+EX_TLB_LR(r13);				    \
+	ld	r9,PACA_EXTLB+EX_TLB_R9(r13);				    \
+	ld	r8,PACA_EXTLB+EX_TLB_R8(r13);				    \
+	mtlr	r16;
 #define TLB_MISS_STATS_D(name)						    \
 	addi	r9,r13,MMSTAT_DSTATS+name;				    \
 	bl	.tlb_stat_inc;
@@ -183,17 +196,20 @@ exc_##label##_book3e:
 61:	addi	r9,r13,MMSTAT_ISTATS+name;				    \
 62:	bl	.tlb_stat_inc;
 #define TLB_MISS_STATS_SAVE_INFO					    \
-	std	r14,EX_TLB_ESR(r12);	/* save ESR */			    \
-
-
+	std	r14,EX_TLB_ESR(r12);	/* save ESR */
+#define TLB_MISS_STATS_SAVE_INFO_BOLTED					    \
+	std	r14,PACA_EXTLB+EX_TLB_ESR(r13);	/* save ESR */
 #else
 #define TLB_MISS_PROLOG_STATS
 #define TLB_MISS_RESTORE_STATS
+#define TLB_MISS_PROLOG_STATS_BOLTED
+#define TLB_MISS_RESTORE_STATS_BOLTED
 #define TLB_MISS_STATS_D(name)
 #define TLB_MISS_STATS_I(name)
 #define TLB_MISS_STATS_X(name)
 #define TLB_MISS_STATS_Y(name)
 #define TLB_MISS_STATS_SAVE_INFO
+#define TLB_MISS_STATS_SAVE_INFO_BOLTED
 #endif
 
 #define SET_IVOR(vector_number, vector_offset)	\
diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h
index 74126765106..c1f65f59792 100644
--- a/arch/powerpc/include/asm/paca.h
+++ b/arch/powerpc/include/asm/paca.h
@@ -103,11 +103,12 @@ struct paca_struct {
 #endif /* CONFIG_PPC_STD_MMU_64 */
 
 #ifdef CONFIG_PPC_BOOK3E
-	pgd_t *pgd;			/* Current PGD */
-	pgd_t *kernel_pgd;		/* Kernel PGD */
 	u64 exgen[8] __attribute__((aligned(0x80)));
+	/* Keep pgd in the same cacheline as the start of extlb */
+	pgd_t *pgd __attribute__((aligned(0x80))); /* Current PGD */
+	pgd_t *kernel_pgd;		/* Kernel PGD */
 	/* We can have up to 3 levels of reentrancy in the TLB miss handler */
-	u64 extlb[3][EX_TLB_SIZE / sizeof(u64)] __attribute__((aligned(0x80)));
+	u64 extlb[3][EX_TLB_SIZE / sizeof(u64)];
 	u64 exmc[8];		/* used for machine checks */
 	u64 excrit[8];		/* used for crit interrupts */
 	u64 exdbg[8];		/* used for debug interrupts */