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, 228 insertions, 13 deletions

diff --git a/arch/powerpc/mm/tlb_low_64e.S b/arch/powerpc/mm/tlb_low_64e.S
index af08922..4ebb34b 100644
--- a/arch/powerpc/mm/tlb_low_64e.S
+++ b/arch/powerpc/mm/tlb_low_64e.S
@@ -30,6 +30,212 @@
 #define VPTE_PGD_SHIFT	(VPTE_PUD_SHIFT + PUD_INDEX_SIZE)
 #define VPTE_INDEX_SIZE (VPTE_PGD_SHIFT + PGD_INDEX_SIZE)
 
+/**********************************************************************
+ *                                                                    *
+ * TLB miss handling for Book3E with a bolted linear mapping          *
+ * No virtual page table, no nested TLB misses                        *
+ *                                                                    *
+ **********************************************************************/
+
+.macro tlb_prolog_bolted addr
+	mtspr	SPRN_SPRG_TLB_SCRATCH,r13
+	mfspr	r13,SPRN_SPRG_PACA
+	std	r10,PACA_EXTLB+EX_TLB_R10(r13)
+	mfcr	r10
+	std	r11,PACA_EXTLB+EX_TLB_R11(r13)
+	std	r16,PACA_EXTLB+EX_TLB_R16(r13)
+	mfspr	r16,\addr		/* get faulting address */
+	std	r14,PACA_EXTLB+EX_TLB_R14(r13)
+	ld	r14,PACAPGD(r13)
+	std	r15,PACA_EXTLB+EX_TLB_R15(r13)
+	std	r10,PACA_EXTLB+EX_TLB_CR(r13)
+	TLB_MISS_PROLOG_STATS_BOLTED
+.endm
+
+.macro tlb_epilog_bolted
+	ld	r14,PACA_EXTLB+EX_TLB_CR(r13)
+	ld	r10,PACA_EXTLB+EX_TLB_R10(r13)
+	ld	r11,PACA_EXTLB+EX_TLB_R11(r13)
+	mtcr	r14
+	ld	r14,PACA_EXTLB+EX_TLB_R14(r13)
+	ld	r15,PACA_EXTLB+EX_TLB_R15(r13)
+	TLB_MISS_RESTORE_STATS_BOLTED
+	ld	r16,PACA_EXTLB+EX_TLB_R16(r13)
+	mfspr	r13,SPRN_SPRG_TLB_SCRATCH
+.endm
+
+/* Data TLB miss */
+	START_EXCEPTION(data_tlb_miss_bolted)
+	tlb_prolog_bolted SPRN_DEAR
+
+	/* We need _PAGE_PRESENT and  _PAGE_ACCESSED set */
+
+	/* We do the user/kernel test for the PID here along with the RW test
+	 */
+	/* We pre-test some combination of permissions to avoid double
+	 * faults:
+	 *
+	 * We move the ESR:ST bit into the position of _PAGE_BAP_SW in the PTE
+	 * ESR_ST   is 0x00800000
+	 * _PAGE_BAP_SW is 0x00000010
+	 * So the shift is >> 19. This tests for supervisor writeability.
+	 * If the page happens to be supervisor writeable and not user
+	 * writeable, we will take a new fault later, but that should be
+	 * a rare enough case.
+	 *
+	 * We also move ESR_ST in _PAGE_DIRTY position
+	 * _PAGE_DIRTY is 0x00001000 so the shift is >> 11
+	 *
+	 * MAS1 is preset for all we need except for TID that needs to
+	 * be cleared for kernel translations
+	 */
+
+	mfspr	r11,SPRN_ESR
+
+	srdi	r15,r16,60		/* get region */
+	rldicl.	r10,r16,64-PGTABLE_EADDR_SIZE,PGTABLE_EADDR_SIZE+4
+	bne-	dtlb_miss_fault_bolted
+
+	rlwinm	r10,r11,32-19,27,27
+	rlwimi	r10,r11,32-16,19,19
+	cmpwi	r15,0
+	ori	r10,r10,_PAGE_PRESENT
+	oris	r11,r10,_PAGE_ACCESSED@h
+
+	TLB_MISS_STATS_SAVE_INFO_BOLTED
+	bne	tlb_miss_kernel_bolted
+
+tlb_miss_common_bolted:
+/*
+ * This is the guts of the TLB miss handler for bolted-linear.
+ * We are entered with:
+ *
+ * r16 = faulting address
+ * r15 = crap (free to use)
+ * r14 = page table base
+ * r13 = PACA
+ * r11 = PTE permission mask
+ * r10 = crap (free to use)
+ */
+	rldicl	r15,r16,64-PGDIR_SHIFT+3,64-PGD_INDEX_SIZE-3
+	cmpldi	cr0,r14,0
+	clrrdi	r15,r15,3
+	beq	tlb_miss_fault_bolted
+
+BEGIN_MMU_FTR_SECTION
+	/* Set the TLB reservation and search for existing entry. Then load
+	 * the entry.
+	 */
+	PPC_TLBSRX_DOT(0,r16)
+	ldx	r14,r14,r15
+	beq	normal_tlb_miss_done
+MMU_FTR_SECTION_ELSE
+	ldx	r14,r14,r15
+ALT_MMU_FTR_SECTION_END_IFSET(MMU_FTR_USE_TLBRSRV)
+
+#ifndef CONFIG_PPC_64K_PAGES
+	rldicl	r15,r16,64-PUD_SHIFT+3,64-PUD_INDEX_SIZE-3
+	clrrdi	r15,r15,3
+
+	cmpldi	cr0,r14,0
+	beq	tlb_miss_fault_bolted
+
+	ldx	r14,r14,r15
+#endif /* CONFIG_PPC_64K_PAGES */
+
+	rldicl	r15,r16,64-PMD_SHIFT+3,64-PMD_INDEX_SIZE-3
+	clrrdi	r15,r15,3
+
+	cmpldi	cr0,r14,0
+	beq	tlb_miss_fault_bolted
+
+	ldx	r14,r14,r15
+
+	rldicl	r15,r16,64-PAGE_SHIFT+3,64-PTE_INDEX_SIZE-3
+	clrrdi	r15,r15,3
+
+	cmpldi	cr0,r14,0
+	beq	tlb_miss_fault_bolted
+
+	ldx	r14,r14,r15
+
+	/* Check if required permissions are met */
+	andc.	r15,r11,r14
+	rldicr	r15,r14,64-(PTE_RPN_SHIFT-PAGE_SHIFT),63-PAGE_SHIFT
+	bne-	tlb_miss_fault_bolted
+
+	/* Now we build the MAS:
+	 *
+	 * MAS 0   :	Fully setup with defaults in MAS4 and TLBnCFG
+	 * MAS 1   :	Almost fully setup
+	 *               - PID already updated by caller if necessary
+	 *               - TSIZE need change if !base page size, not
+	 *                 yet implemented for now
+	 * MAS 2   :	Defaults not useful, need to be redone
+	 * MAS 3+7 :	Needs to be done
+	 */
+	clrrdi	r11,r16,12		/* Clear low crap in EA */
+	clrldi	r15,r15,12		/* Clear crap at the top */
+	rlwimi	r11,r14,32-19,27,31	/* Insert WIMGE */
+	rlwimi	r15,r14,32-8,22,25	/* Move in U bits */
+	mtspr	SPRN_MAS2,r11
+	andi.	r11,r14,_PAGE_DIRTY
+	rlwimi	r15,r14,32-2,26,31	/* Move in BAP bits */
+
+	/* Mask out SW and UW if !DIRTY (XXX optimize this !) */
+	bne	1f
+	li	r11,MAS3_SW|MAS3_UW
+	andc	r15,r15,r11
+1:
+	mtspr	SPRN_MAS7_MAS3,r15
+	tlbwe
+
+	TLB_MISS_STATS_X(MMSTAT_TLB_MISS_NORM_OK)
+	tlb_epilog_bolted
+	rfi
+
+itlb_miss_kernel_bolted:
+	li	r11,_PAGE_PRESENT|_PAGE_BAP_SX	/* Base perm */
+	oris	r11,r11,_PAGE_ACCESSED@h
+tlb_miss_kernel_bolted:
+	mfspr	r10,SPRN_MAS1
+	ld	r14,PACA_KERNELPGD(r13)
+	cmpldi	cr0,r15,8		/* Check for vmalloc region */
+	rlwinm	r10,r10,0,16,1		/* Clear TID */
+	mtspr	SPRN_MAS1,r10
+	beq+	tlb_miss_common_bolted
+
+tlb_miss_fault_bolted:
+	/* We need to check if it was an instruction miss */
+	andi.	r10,r11,_PAGE_EXEC|_PAGE_BAP_SX
+	bne	itlb_miss_fault_bolted
+dtlb_miss_fault_bolted:
+	TLB_MISS_STATS_D(MMSTAT_TLB_MISS_NORM_FAULT)
+	tlb_epilog_bolted
+	b	exc_data_storage_book3e
+itlb_miss_fault_bolted:
+	TLB_MISS_STATS_I(MMSTAT_TLB_MISS_NORM_FAULT)
+	tlb_epilog_bolted
+	b	exc_instruction_storage_book3e
+
+/* Instruction TLB miss */
+	START_EXCEPTION(instruction_tlb_miss_bolted)
+	tlb_prolog_bolted SPRN_SRR0
+
+	rldicl.	r10,r16,64-PGTABLE_EADDR_SIZE,PGTABLE_EADDR_SIZE+4
+	srdi	r15,r16,60		/* get region */
+	TLB_MISS_STATS_SAVE_INFO_BOLTED
+	bne-	itlb_miss_fault_bolted
+
+	li	r11,_PAGE_PRESENT|_PAGE_EXEC	/* Base perm */
+
+	/* We do the user/kernel test for the PID here along with the RW test
+	 */
+
+	cmpldi	cr0,r15,0			/* Check for user region */
+	oris	r11,r11,_PAGE_ACCESSED@h
+	beq	tlb_miss_common_bolted
+	b	itlb_miss_kernel_bolted
 
 /**********************************************************************
  *                                                                    *
diff --git a/arch/powerpc/mm/tlb_nohash.c b/arch/powerpc/mm/tlb_nohash.c
index 5693499..3722185 100644
--- a/arch/powerpc/mm/tlb_nohash.c
+++ b/arch/powerpc/mm/tlb_nohash.c
@@ -443,14 +443,27 @@ static void setup_page_sizes(void)
 	}
 }
 
-static void setup_mmu_htw(void)
+static void __patch_exception(int exc, unsigned long addr)
 {
 	extern unsigned int interrupt_base_book3e;
-	extern unsigned int exc_data_tlb_miss_htw_book3e;
-	extern unsigned int exc_instruction_tlb_miss_htw_book3e;
+ 	unsigned int *ibase = &interrupt_base_book3e;
+ 
+	/* Our exceptions vectors start with a NOP and -then- a branch
+	 * to deal with single stepping from userspace which stops on
+	 * the second instruction. Thus we need to patch the second
+	 * instruction of the exception, not the first one
+	 */
+
+	patch_branch(ibase + (exc / 4) + 1, addr, 0);
+}
 
-	unsigned int *ibase = &interrupt_base_book3e;
+#define patch_exception(exc, name) do { \
+	extern unsigned int name; \
+	__patch_exception((exc), (unsigned long)&name); \
+} while (0)
 
+static void setup_mmu_htw(void)
+{
 	/* Check if HW tablewalk is present, and if yes, enable it by:
 	 *
 	 * - patching the TLB miss handlers to branch to the
@@ -462,15 +475,8 @@ static void setup_mmu_htw(void)
 
 	if ((tlb0cfg & TLBnCFG_IND) &&
 	    (tlb0cfg & TLBnCFG_PT)) {
-		/* Our exceptions vectors start with a NOP and -then- a branch
-		 * to deal with single stepping from userspace which stops on
-		 * the second instruction. Thus we need to patch the second
-		 * instruction of the exception, not the first one
-		 */
-		patch_branch(ibase + (0x1c0 / 4) + 1,
-			     (unsigned long)&exc_data_tlb_miss_htw_book3e, 0);
-		patch_branch(ibase + (0x1e0 / 4) + 1,
-			     (unsigned long)&exc_instruction_tlb_miss_htw_book3e, 0);
+		patch_exception(0x1c0, exc_data_tlb_miss_htw_book3e);
+		patch_exception(0x1e0, exc_instruction_tlb_miss_htw_book3e);
 		book3e_htw_enabled = 1;
 	}
 	pr_info("MMU: Book3E HW tablewalk %s\n",
@@ -549,6 +555,9 @@ static void __early_init_mmu(int boot_cpu)
 		/* limit memory so we dont have linear faults */
 		memblock_enforce_memory_limit(linear_map_top);
 		memblock_analyze();
+
+		patch_exception(0x1c0, exc_data_tlb_miss_bolted_book3e);
+		patch_exception(0x1e0, exc_instruction_tlb_miss_bolted_book3e);
 	}
 #endif