[PATCH v3 1/9] powerpc: Move ARCH_DLINFO out of uapi

Subsystems: linux for powerpc (32-bit and 64-bit), the rest

STALE3468d

10 messages, 2 authors, 2017-02-06 · open the first message on its own page

[PATCH v3 1/9] powerpc: Move ARCH_DLINFO out of uapi

From: Michael Ellerman <mpe@ellerman.id.au>
Date: 2017-02-03 11:06:12

From: Benjamin Herrenschmidt <benh@kernel.crashing.org>

It's an kernel private macro, it doesn't belong there

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/include/asm/elf.h      | 22 ++++++++++++++++++++++
 arch/powerpc/include/uapi/asm/elf.h | 23 -----------------------
 2 files changed, 22 insertions(+), 23 deletions(-)
diff --git a/arch/powerpc/include/asm/elf.h b/arch/powerpc/include/asm/elf.h
index ee46ffef608e..730c27ed10e1 100644
--- a/arch/powerpc/include/asm/elf.h
+++ b/arch/powerpc/include/asm/elf.h
@@ -136,4 +136,26 @@ extern int arch_setup_additional_pages(struct linux_binprm *bprm,
 
 #endif /* CONFIG_SPU_BASE */
 
+/*
+ * The requirements here are:
+ * - keep the final alignment of sp (sp & 0xf)
+ * - make sure the 32-bit value at the first 16 byte aligned position of
+ *   AUXV is greater than 16 for glibc compatibility.
+ *   AT_IGNOREPPC is used for that.
+ * - for compatibility with glibc ARCH_DLINFO must always be defined on PPC,
+ *   even if DLINFO_ARCH_ITEMS goes to zero or is undefined.
+ * update AT_VECTOR_SIZE_ARCH if the number of NEW_AUX_ENT entries changes
+ */
+#define ARCH_DLINFO							\
+do {									\
+	/* Handle glibc compatibility. */				\
+	NEW_AUX_ENT(AT_IGNOREPPC, AT_IGNOREPPC);			\
+	NEW_AUX_ENT(AT_IGNOREPPC, AT_IGNOREPPC);			\
+	/* Cache size items */						\
+	NEW_AUX_ENT(AT_DCACHEBSIZE, dcache_bsize);			\
+	NEW_AUX_ENT(AT_ICACHEBSIZE, icache_bsize);			\
+	NEW_AUX_ENT(AT_UCACHEBSIZE, ucache_bsize);			\
+	VDSO_AUX_ENT(AT_SYSINFO_EHDR, current->mm->context.vdso_base);	\
+} while (0)
+
 #endif /* _ASM_POWERPC_ELF_H */
diff --git a/arch/powerpc/include/uapi/asm/elf.h b/arch/powerpc/include/uapi/asm/elf.h
index 3a9e44c45c78..b2c6fdd5ac30 100644
--- a/arch/powerpc/include/uapi/asm/elf.h
+++ b/arch/powerpc/include/uapi/asm/elf.h
@@ -162,29 +162,6 @@ typedef elf_vrreg_t elf_vrregset_t32[ELF_NVRREG32];
 typedef elf_fpreg_t elf_vsrreghalf_t32[ELF_NVSRHALFREG];
 #endif
 
-
-/*
- * The requirements here are:
- * - keep the final alignment of sp (sp & 0xf)
- * - make sure the 32-bit value at the first 16 byte aligned position of
- *   AUXV is greater than 16 for glibc compatibility.
- *   AT_IGNOREPPC is used for that.
- * - for compatibility with glibc ARCH_DLINFO must always be defined on PPC,
- *   even if DLINFO_ARCH_ITEMS goes to zero or is undefined.
- * update AT_VECTOR_SIZE_ARCH if the number of NEW_AUX_ENT entries changes
- */
-#define ARCH_DLINFO							\
-do {									\
-	/* Handle glibc compatibility. */				\
-	NEW_AUX_ENT(AT_IGNOREPPC, AT_IGNOREPPC);			\
-	NEW_AUX_ENT(AT_IGNOREPPC, AT_IGNOREPPC);			\
-	/* Cache size items */						\
-	NEW_AUX_ENT(AT_DCACHEBSIZE, dcache_bsize);			\
-	NEW_AUX_ENT(AT_ICACHEBSIZE, icache_bsize);			\
-	NEW_AUX_ENT(AT_UCACHEBSIZE, ucache_bsize);			\
-	VDSO_AUX_ENT(AT_SYSINFO_EHDR, current->mm->context.vdso_base);	\
-} while (0)
-
 /* PowerPC64 relocations defined by the ABIs */
 #define R_PPC64_NONE    R_PPC_NONE
 #define R_PPC64_ADDR32  R_PPC_ADDR32  /* 32bit absolute address.  */
-- 
2.7.4

[PATCH v3 2/9] powerpc: Move {d, i, u}cache_bsize definitions to a common place

From: Michael Ellerman <mpe@ellerman.id.au>
Date: 2017-02-03 11:06:13

From: Benjamin Herrenschmidt <benh@kernel.crashing.org>

The variables are defined twice in setup_32.c and setup_64.c, do it
once in setup-common.c instead

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/kernel/setup-common.c | 9 +++++++++
 arch/powerpc/kernel/setup_32.c     | 8 --------
 arch/powerpc/kernel/setup_64.c     | 8 --------
 3 files changed, 9 insertions(+), 16 deletions(-)
diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c
index f516ac508ae3..4697da895133 100644
--- a/arch/powerpc/kernel/setup-common.c
+++ b/arch/powerpc/kernel/setup-common.c
@@ -87,6 +87,15 @@ EXPORT_SYMBOL(machine_id);
 int boot_cpuid = -1;
 EXPORT_SYMBOL_GPL(boot_cpuid);
 
+/*
+ * These are used in binfmt_elf.c to put aux entries on the stack
+ * for each elf executable being started.
+ */
+int dcache_bsize;
+int icache_bsize;
+int ucache_bsize;
+
+
 unsigned long klimit = (unsigned long) _end;
 
 /*
diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c
index 7fcf1f7f01c1..2f88f6cf1a42 100644
--- a/arch/powerpc/kernel/setup_32.c
+++ b/arch/powerpc/kernel/setup_32.c
@@ -59,14 +59,6 @@ EXPORT_SYMBOL(DMA_MODE_READ);
 EXPORT_SYMBOL(DMA_MODE_WRITE);
 
 /*
- * These are used in binfmt_elf.c to put aux entries on the stack
- * for each elf executable being started.
- */
-int dcache_bsize;
-int icache_bsize;
-int ucache_bsize;
-
-/*
  * We're called here very early in the boot.
  *
  * Note that the kernel may be running at an address which is different
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index 6824157e4d2e..ed3362bc9a2a 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -88,14 +88,6 @@ struct ppc64_caches ppc64_caches = {
 };
 EXPORT_SYMBOL_GPL(ppc64_caches);
 
-/*
- * These are used in binfmt_elf.c to put aux entries on the stack
- * for each elf executable being started.
- */
-int dcache_bsize;
-int icache_bsize;
-int ucache_bsize;
-
 #if defined(CONFIG_PPC_BOOK3E) && defined(CONFIG_SMP)
 void __init setup_tlb_core_data(void)
 {
-- 
2.7.4

[PATCH v3 3/9] powerpc: Remove obsolete comment about patching instructions

From: Michael Ellerman <mpe@ellerman.id.au>
Date: 2017-02-03 11:06:14

From: Benjamin Herrenschmidt <benh@kernel.crashing.org>

We don't patch instructions based on the cache lines or block
sizes these days.

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/kernel/setup_64.c | 3 ---
 1 file changed, 3 deletions(-)
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index ed3362bc9a2a..ae84d345c13c 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -77,9 +77,6 @@
 int spinning_secondaries;
 u64 ppc64_pft_size;
 
-/* Pick defaults since we might want to patch instructions
- * before we've read this from the device tree.
- */
 struct ppc64_caches ppc64_caches = {
 	.dline_size = 0x40,
 	.log_dline_size = 6,
-- 
2.7.4

[PATCH v3 4/9] powerpc/64: Fix naming of cache block vs. cache line

From: Michael Ellerman <mpe@ellerman.id.au>
Date: 2017-02-03 11:06:15

From: Benjamin Herrenschmidt <benh@kernel.crashing.org>

In a number of places we called "cache line size" what is actually
the cache block size, which in the powerpc architecture, means the
effective size to use with cache management instructions (it can
be different from the actual cache line size).

We fix the naming across the board and properly retrieve both
pieces of information when available in the device-tree.

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/include/asm/cache.h   | 12 ++++---
 arch/powerpc/include/asm/page_64.h |  4 +--
 arch/powerpc/kernel/align.c        |  2 +-
 arch/powerpc/kernel/asm-offsets.c  | 12 +++----
 arch/powerpc/kernel/misc_64.S      | 28 ++++++++--------
 arch/powerpc/kernel/setup_64.c     | 65 +++++++++++++++++++++-----------------
 arch/powerpc/kernel/vdso.c         | 10 +++---
 arch/powerpc/lib/copypage_64.S     |  4 +--
 arch/powerpc/lib/string_64.S       |  6 ++--
 9 files changed, 75 insertions(+), 68 deletions(-)
diff --git a/arch/powerpc/include/asm/cache.h b/arch/powerpc/include/asm/cache.h
index 7657aa897a38..25ee433a8261 100644
--- a/arch/powerpc/include/asm/cache.h
+++ b/arch/powerpc/include/asm/cache.h
@@ -33,12 +33,14 @@
 struct ppc64_caches {
 	u32	dsize;			/* L1 d-cache size */
 	u32	dline_size;		/* L1 d-cache line size	*/
-	u32	log_dline_size;
-	u32	dlines_per_page;
+	u32	dblock_size;		/* L1 d-cache block size */
+	u32	log_dblock_size;
+	u32	dblocks_per_page;
 	u32	isize;			/* L1 i-cache size */
-	u32	iline_size;		/* L1 i-cache line size	*/
-	u32	log_iline_size;
-	u32	ilines_per_page;
+	u32	iline_size;		/* L1 d-cache line size	*/
+	u32	iblock_size;		/* L1 i-cache block size */
+	u32	log_iblock_size;
+	u32	iblocks_per_page;
 };
 
 extern struct ppc64_caches ppc64_caches;
diff --git a/arch/powerpc/include/asm/page_64.h b/arch/powerpc/include/asm/page_64.h
index dd5f0712afa2..c50a666308dd 100644
--- a/arch/powerpc/include/asm/page_64.h
+++ b/arch/powerpc/include/asm/page_64.h
@@ -47,14 +47,14 @@ static inline void clear_page(void *addr)
 	unsigned long iterations;
 	unsigned long onex, twox, fourx, eightx;
 
-	iterations = ppc64_caches.dlines_per_page / 8;
+	iterations = ppc64_caches.dblocks_per_page / 8;
 
 	/*
 	 * Some verisions of gcc use multiply instructions to
 	 * calculate the offsets so lets give it a hand to
 	 * do better.
 	 */
-	onex = ppc64_caches.dline_size;
+	onex = ppc64_caches.dblock_size;
 	twox = onex << 1;
 	fourx = onex << 2;
 	eightx = onex << 3;
diff --git a/arch/powerpc/kernel/align.c b/arch/powerpc/kernel/align.c
index 8d58c61908f7..30ff6590a2dd 100644
--- a/arch/powerpc/kernel/align.c
+++ b/arch/powerpc/kernel/align.c
@@ -204,7 +204,7 @@ static int emulate_dcbz(struct pt_regs *regs, unsigned char __user *addr)
 	int i, size;
 
 #ifdef __powerpc64__
-	size = ppc64_caches.dline_size;
+	size = ppc64_caches.dblock_size;
 #else
 	size = L1_CACHE_BYTES;
 #endif
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 0601e6a7297c..125442107b40 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -163,12 +163,12 @@ int main(void)
 	DEFINE(TI_CPU, offsetof(struct thread_info, cpu));
 
 #ifdef CONFIG_PPC64
-	DEFINE(DCACHEL1LINESIZE, offsetof(struct ppc64_caches, dline_size));
-	DEFINE(DCACHEL1LOGLINESIZE, offsetof(struct ppc64_caches, log_dline_size));
-	DEFINE(DCACHEL1LINESPERPAGE, offsetof(struct ppc64_caches, dlines_per_page));
-	DEFINE(ICACHEL1LINESIZE, offsetof(struct ppc64_caches, iline_size));
-	DEFINE(ICACHEL1LOGLINESIZE, offsetof(struct ppc64_caches, log_iline_size));
-	DEFINE(ICACHEL1LINESPERPAGE, offsetof(struct ppc64_caches, ilines_per_page));
+	DEFINE(DCACHEL1BLOCKSIZE, offsetof(struct ppc64_caches, dblock_size));
+	DEFINE(DCACHEL1LOGBLOCKSIZE, offsetof(struct ppc64_caches, log_dblock_size));
+	DEFINE(DCACHEL1BLOCKSPERPAGE, offsetof(struct ppc64_caches, dblocks_per_page));
+	DEFINE(ICACHEL1BLOCKSIZE, offsetof(struct ppc64_caches, iblock_size));
+	DEFINE(ICACHEL1LOGBLOCKSIZE, offsetof(struct ppc64_caches, log_iblock_size));
+	DEFINE(ICACHEL1BLOCKSPERPAGE, offsetof(struct ppc64_caches, iblocks_per_page));
 	/* paca */
 	DEFINE(PACA_SIZE, sizeof(struct paca_struct));
 	DEFINE(PACAPACAINDEX, offsetof(struct paca_struct, paca_index));
diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S
index 32be2a844947..ae179cb1bb3c 100644
--- a/arch/powerpc/kernel/misc_64.S
+++ b/arch/powerpc/kernel/misc_64.S
@@ -80,12 +80,12 @@ END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE)
  * each other.
  */
  	ld	r10,PPC64_CACHES@toc(r2)
-	lwz	r7,DCACHEL1LINESIZE(r10)/* Get cache line size */
+	lwz	r7,DCACHEL1BLOCKSIZE(r10)/* Get cache block size */
 	addi	r5,r7,-1
 	andc	r6,r3,r5		/* round low to line bdy */
 	subf	r8,r6,r4		/* compute length */
 	add	r8,r8,r5		/* ensure we get enough */
-	lwz	r9,DCACHEL1LOGLINESIZE(r10)	/* Get log-2 of cache line size */
+	lwz	r9,DCACHEL1LOGBLOCKSIZE(r10)	/* Get log-2 of cache block size */
 	srw.	r8,r8,r9		/* compute line count */
 	beqlr				/* nothing to do? */
 	mtctr	r8
@@ -96,12 +96,12 @@ END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE)
 
 /* Now invalidate the instruction cache */
 	
-	lwz	r7,ICACHEL1LINESIZE(r10)	/* Get Icache line size */
+	lwz	r7,ICACHEL1BLOCKSIZE(r10)	/* Get Icache block size */
 	addi	r5,r7,-1
 	andc	r6,r3,r5		/* round low to line bdy */
 	subf	r8,r6,r4		/* compute length */
 	add	r8,r8,r5
-	lwz	r9,ICACHEL1LOGLINESIZE(r10)	/* Get log-2 of Icache line size */
+	lwz	r9,ICACHEL1LOGBLOCKSIZE(r10)	/* Get log-2 of Icache block size */
 	srw.	r8,r8,r9		/* compute line count */
 	beqlr				/* nothing to do? */
 	mtctr	r8
@@ -128,12 +128,12 @@ _GLOBAL(flush_dcache_range)
  * Different systems have different cache line sizes
  */
  	ld	r10,PPC64_CACHES@toc(r2)
-	lwz	r7,DCACHEL1LINESIZE(r10)	/* Get dcache line size */
+	lwz	r7,DCACHEL1BLOCKSIZE(r10)	/* Get dcache block size */
 	addi	r5,r7,-1
 	andc	r6,r3,r5		/* round low to line bdy */
 	subf	r8,r6,r4		/* compute length */
 	add	r8,r8,r5		/* ensure we get enough */
-	lwz	r9,DCACHEL1LOGLINESIZE(r10)	/* Get log-2 of dcache line size */
+	lwz	r9,DCACHEL1LOGBLOCKSIZE(r10)	/* Get log-2 of dcache block size */
 	srw.	r8,r8,r9		/* compute line count */
 	beqlr				/* nothing to do? */
 	mtctr	r8
@@ -156,12 +156,12 @@ EXPORT_SYMBOL(flush_dcache_range)
  */
 _GLOBAL(flush_dcache_phys_range)
  	ld	r10,PPC64_CACHES@toc(r2)
-	lwz	r7,DCACHEL1LINESIZE(r10)	/* Get dcache line size */
+	lwz	r7,DCACHEL1BLOCKSIZE(r10)	/* Get dcache block size */
 	addi	r5,r7,-1
 	andc	r6,r3,r5		/* round low to line bdy */
 	subf	r8,r6,r4		/* compute length */
 	add	r8,r8,r5		/* ensure we get enough */
-	lwz	r9,DCACHEL1LOGLINESIZE(r10)	/* Get log-2 of dcache line size */
+	lwz	r9,DCACHEL1LOGBLOCKSIZE(r10)	/* Get log-2 of dcache block size */
 	srw.	r8,r8,r9		/* compute line count */
 	beqlr				/* nothing to do? */
 	mfmsr	r5			/* Disable MMU Data Relocation */
@@ -184,12 +184,12 @@ _GLOBAL(flush_dcache_phys_range)
 
 _GLOBAL(flush_inval_dcache_range)
  	ld	r10,PPC64_CACHES@toc(r2)
-	lwz	r7,DCACHEL1LINESIZE(r10)	/* Get dcache line size */
+	lwz	r7,DCACHEL1BLOCKSIZE(r10)	/* Get dcache block size */
 	addi	r5,r7,-1
 	andc	r6,r3,r5		/* round low to line bdy */
 	subf	r8,r6,r4		/* compute length */
 	add	r8,r8,r5		/* ensure we get enough */
-	lwz	r9,DCACHEL1LOGLINESIZE(r10)/* Get log-2 of dcache line size */
+	lwz	r9,DCACHEL1LOGBLOCKSIZE(r10)/* Get log-2 of dcache block size */
 	srw.	r8,r8,r9		/* compute line count */
 	beqlr				/* nothing to do? */
 	sync
@@ -225,8 +225,8 @@ END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE)
 /* Flush the dcache */
  	ld	r7,PPC64_CACHES@toc(r2)
 	clrrdi	r3,r3,PAGE_SHIFT           	    /* Page align */
-	lwz	r4,DCACHEL1LINESPERPAGE(r7)	/* Get # dcache lines per page */
-	lwz	r5,DCACHEL1LINESIZE(r7)		/* Get dcache line size */
+	lwz	r4,DCACHEL1BLOCKSPERPAGE(r7)	/* Get # dcache blocks per page */
+	lwz	r5,DCACHEL1BLOCKSIZE(r7)	/* Get dcache block size */
 	mr	r6,r3
 	mtctr	r4
 0:	dcbst	0,r6
@@ -236,8 +236,8 @@ END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE)
 
 /* Now invalidate the icache */	
 
-	lwz	r4,ICACHEL1LINESPERPAGE(r7)	/* Get # icache lines per page */
-	lwz	r5,ICACHEL1LINESIZE(r7)		/* Get icache line size */
+	lwz	r4,ICACHEL1BLOCKSPERPAGE(r7)	/* Get # icache blocks per page */
+	lwz	r5,ICACHEL1BLOCKSIZE(r7)	/* Get icache block size */
 	mtctr	r4
 1:	icbi	0,r3
 	add	r3,r3,r5
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index ae84d345c13c..08cccb2501e7 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -78,10 +78,10 @@ int spinning_secondaries;
 u64 ppc64_pft_size;
 
 struct ppc64_caches ppc64_caches = {
-	.dline_size = 0x40,
-	.log_dline_size = 6,
-	.iline_size = 0x40,
-	.log_iline_size = 6
+	.dblock_size = 0x40,
+	.log_dblock_size = 6,
+	.iblock_size = 0x40,
+	.log_iblock_size = 6
 };
 EXPORT_SYMBOL_GPL(ppc64_caches);
 
@@ -412,59 +412,66 @@ void __init initialize_cache_info(void)
 		 * d-cache and i-cache sizes... -Peter
 		 */
 		if (num_cpus == 1) {
-			const __be32 *sizep, *lsizep;
-			u32 size, lsize;
+			const __be32 *sizep, *lsizep, *bsizep;
+			u32 size, lsize, bsize;
 
 			size = 0;
-			lsize = cur_cpu_spec->dcache_bsize;
+			lsize = bsize = cur_cpu_spec->dcache_bsize;
 			sizep = of_get_property(np, "d-cache-size", NULL);
 			if (sizep != NULL)
 				size = be32_to_cpu(*sizep);
-			lsizep = of_get_property(np, "d-cache-block-size",
+			bsizep = of_get_property(np, "d-cache-block-size",
 						 NULL);
-			/* fallback if block size missing */
-			if (lsizep == NULL)
-				lsizep = of_get_property(np,
-							 "d-cache-line-size",
-							 NULL);
+			lsizep = of_get_property(np, "d-cache-line-size",
+						 NULL);
+			if (bsizep == NULL)
+				bsizep = lsizep;
 			if (lsizep != NULL)
 				lsize = be32_to_cpu(*lsizep);
-			if (sizep == NULL || lsizep == NULL)
+			if (bsizep != NULL)
+				bsize = be32_to_cpu(*bsizep);
+			if (sizep == NULL || bsizep == NULL || lsizep == NULL)
 				DBG("Argh, can't find dcache properties ! "
-				    "sizep: %p, lsizep: %p\n", sizep, lsizep);
+				    "sizep: %p, bsizep: %p, lsizep: %p\n",
+				    sizep, bsizep, lsizep);
 
 			ppc64_caches.dsize = size;
 			ppc64_caches.dline_size = lsize;
-			ppc64_caches.log_dline_size = __ilog2(lsize);
-			ppc64_caches.dlines_per_page = PAGE_SIZE / lsize;
+			ppc64_caches.dblock_size = bsize;
+			ppc64_caches.log_dblock_size = __ilog2(bsize);
+			ppc64_caches.dblocks_per_page = PAGE_SIZE / bsize;
 
 			size = 0;
-			lsize = cur_cpu_spec->icache_bsize;
+			lsize = bsize = cur_cpu_spec->icache_bsize;
 			sizep = of_get_property(np, "i-cache-size", NULL);
 			if (sizep != NULL)
 				size = be32_to_cpu(*sizep);
-			lsizep = of_get_property(np, "i-cache-block-size",
+			bsizep = of_get_property(np, "i-cache-block-size",
+						 NULL);
+			lsizep = of_get_property(np, "i-cache-line-size",
 						 NULL);
-			if (lsizep == NULL)
-				lsizep = of_get_property(np,
-							 "i-cache-line-size",
-							 NULL);
+			if (bsizep == NULL)
+				bsizep = lsizep;
 			if (lsizep != NULL)
 				lsize = be32_to_cpu(*lsizep);
-			if (sizep == NULL || lsizep == NULL)
+			if (bsizep != NULL)
+				bsize = be32_to_cpu(*bsizep);
+			if (sizep == NULL || bsizep == NULL || lsizep == NULL)
 				DBG("Argh, can't find icache properties ! "
-				    "sizep: %p, lsizep: %p\n", sizep, lsizep);
+				    "sizep: %p, bsizep: %p, lsizep: %p\n",
+				    sizep, bsizep, lsizep);
 
 			ppc64_caches.isize = size;
 			ppc64_caches.iline_size = lsize;
-			ppc64_caches.log_iline_size = __ilog2(lsize);
-			ppc64_caches.ilines_per_page = PAGE_SIZE / lsize;
+			ppc64_caches.iblock_size = bsize;
+			ppc64_caches.log_iblock_size = __ilog2(bsize);
+			ppc64_caches.iblocks_per_page = PAGE_SIZE / bsize;
 		}
 	}
 
 	/* For use by binfmt_elf */
-	dcache_bsize = ppc64_caches.dline_size;
-	icache_bsize = ppc64_caches.iline_size;
+	dcache_bsize = ppc64_caches.dblock_size;
+	icache_bsize = ppc64_caches.iblock_size;
 
 	DBG(" <- initialize_cache_info()\n");
 }
diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c
index 4111d30badfa..9c0a85776c6c 100644
--- a/arch/powerpc/kernel/vdso.c
+++ b/arch/powerpc/kernel/vdso.c
@@ -740,12 +740,10 @@ static int __init vdso_init(void)
 	vdso_data->dcache_line_size = ppc64_caches.dline_size;
 	vdso_data->icache_size = ppc64_caches.isize;
 	vdso_data->icache_line_size = ppc64_caches.iline_size;
-
-	/* XXXOJN: Blocks should be added to ppc64_caches and used instead */
-	vdso_data->dcache_block_size = ppc64_caches.dline_size;
-	vdso_data->icache_block_size = ppc64_caches.iline_size;
-	vdso_data->dcache_log_block_size = ppc64_caches.log_dline_size;
-	vdso_data->icache_log_block_size = ppc64_caches.log_iline_size;
+	vdso_data->dcache_block_size = ppc64_caches.dblock_size;
+	vdso_data->icache_block_size = ppc64_caches.iblock_size;
+	vdso_data->dcache_log_block_size = ppc64_caches.log_dblock_size;
+	vdso_data->icache_log_block_size = ppc64_caches.log_iblock_size;
 
 	/*
 	 * Calculate the size of the 64 bits vDSO
diff --git a/arch/powerpc/lib/copypage_64.S b/arch/powerpc/lib/copypage_64.S
index 21367b3a8146..4bcc9e76fb55 100644
--- a/arch/powerpc/lib/copypage_64.S
+++ b/arch/powerpc/lib/copypage_64.S
@@ -26,8 +26,8 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_VMX_COPY)
 	ori	r5,r5,PAGE_SIZE@l
 BEGIN_FTR_SECTION
 	ld      r10,PPC64_CACHES@toc(r2)
-	lwz	r11,DCACHEL1LOGLINESIZE(r10)	/* log2 of cache line size */
-	lwz     r12,DCACHEL1LINESIZE(r10)	/* get cache line size */
+	lwz	r11,DCACHEL1LOGBLOCKSIZE(r10)	/* log2 of cache block size */
+	lwz     r12,DCACHEL1BLOCKSIZE(r10)	/* get cache block size */
 	li	r9,0
 	srd	r8,r5,r11
 
diff --git a/arch/powerpc/lib/string_64.S b/arch/powerpc/lib/string_64.S
index c100f4d5d5d0..d5b4d9498c54 100644
--- a/arch/powerpc/lib/string_64.S
+++ b/arch/powerpc/lib/string_64.S
@@ -152,9 +152,9 @@ err2;	std	r0,0(r3)
 	addi	r3,r3,8
 	addi	r4,r4,-8
 
-	/* Destination is 16 byte aligned, need to get it cacheline aligned */
-11:	lwz	r7,DCACHEL1LOGLINESIZE(r5)
-	lwz	r9,DCACHEL1LINESIZE(r5)
+	/* Destination is 16 byte aligned, need to get it cache block aligned */
+11:	lwz	r7,DCACHEL1LOGBLOCKSIZE(r5)
+	lwz	r9,DCACHEL1BLOCKSIZE(r5)
 
 	/*
 	 * With worst case alignment the long clear loop takes a minimum
-- 
2.7.4

[PATCH v3 5/9] powerpc/64: Retrieve number of L1 cache sets from device-tree

From: Michael Ellerman <mpe@ellerman.id.au>
Date: 2017-02-03 11:06:16

From: Benjamin Herrenschmidt <benh@kernel.crashing.org>

It will be used to calculate the associativity

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/include/asm/cache.h |  2 ++
 arch/powerpc/kernel/setup_64.c   | 28 ++++++++++++++++++++++++++--
 2 files changed, 28 insertions(+), 2 deletions(-)
diff --git a/arch/powerpc/include/asm/cache.h b/arch/powerpc/include/asm/cache.h
index 25ee433a8261..1fa364340146 100644
--- a/arch/powerpc/include/asm/cache.h
+++ b/arch/powerpc/include/asm/cache.h
@@ -36,11 +36,13 @@ struct ppc64_caches {
 	u32	dblock_size;		/* L1 d-cache block size */
 	u32	log_dblock_size;
 	u32	dblocks_per_page;
+	u32	dsets;
 	u32	isize;			/* L1 i-cache size */
 	u32	iline_size;		/* L1 d-cache line size	*/
 	u32	iblock_size;		/* L1 i-cache block size */
 	u32	log_iblock_size;
 	u32	iblocks_per_page;
+	u32	isets;
 };
 
 extern struct ppc64_caches ppc64_caches;
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index 08cccb2501e7..75c9a8641ba1 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -412,14 +412,18 @@ void __init initialize_cache_info(void)
 		 * d-cache and i-cache sizes... -Peter
 		 */
 		if (num_cpus == 1) {
-			const __be32 *sizep, *lsizep, *bsizep;
-			u32 size, lsize, bsize;
+			const __be32 *sizep, *lsizep, *bsizep, *setsp;
+			u32 size, lsize, bsize, sets;
 
 			size = 0;
+			sets = -1u;
 			lsize = bsize = cur_cpu_spec->dcache_bsize;
 			sizep = of_get_property(np, "d-cache-size", NULL);
 			if (sizep != NULL)
 				size = be32_to_cpu(*sizep);
+			setsp = of_get_property(np, "d-cache-sets", NULL);
+			if (setsp != NULL)
+				sets = be32_to_cpu(*setsp);
 			bsizep = of_get_property(np, "d-cache-block-size",
 						 NULL);
 			lsizep = of_get_property(np, "d-cache-line-size",
@@ -435,17 +439,32 @@ void __init initialize_cache_info(void)
 				    "sizep: %p, bsizep: %p, lsizep: %p\n",
 				    sizep, bsizep, lsizep);
 
+			/*
+			 * OF is weird .. it represents fully associative caches
+			 * as "1 way" which doesn't make much sense and doesn't
+			 * leave room for direct mapped. We'll assume that 0
+			 * in OF means direct mapped for that reason.
+			 */
+			if (sets == 1)
+				sets = 0;
+			else if (sets == 0)
+				sets = 1;
 			ppc64_caches.dsize = size;
+			ppc64_caches.dsets = sets;
 			ppc64_caches.dline_size = lsize;
 			ppc64_caches.dblock_size = bsize;
 			ppc64_caches.log_dblock_size = __ilog2(bsize);
 			ppc64_caches.dblocks_per_page = PAGE_SIZE / bsize;
 
 			size = 0;
+			sets = -1u;
 			lsize = bsize = cur_cpu_spec->icache_bsize;
 			sizep = of_get_property(np, "i-cache-size", NULL);
 			if (sizep != NULL)
 				size = be32_to_cpu(*sizep);
+			setsp = of_get_property(np, "i-cache-sets", NULL);
+			if (setsp != NULL)
+				sets = be32_to_cpu(*setsp);
 			bsizep = of_get_property(np, "i-cache-block-size",
 						 NULL);
 			lsizep = of_get_property(np, "i-cache-line-size",
@@ -461,7 +480,12 @@ void __init initialize_cache_info(void)
 				    "sizep: %p, bsizep: %p, lsizep: %p\n",
 				    sizep, bsizep, lsizep);
 
+			if (sets == 1)
+				sets = 0;
+			else if (sets == 0)
+				sets = 1;
 			ppc64_caches.isize = size;
+			ppc64_caches.isets = sets;
 			ppc64_caches.iline_size = lsize;
 			ppc64_caches.iblock_size = bsize;
 			ppc64_caches.log_iblock_size = __ilog2(bsize);
-- 
2.7.4

[PATCH v3 6/9] powerpc/64: Clean up ppc64_caches using a struct per cache

From: Michael Ellerman <mpe@ellerman.id.au>
Date: 2017-02-03 11:06:17

From: Benjamin Herrenschmidt <benh@kernel.crashing.org>

We have two set of identical struct members for the I and D sides
and mostly identical bunches of code to parse the device-tree to
populate them. Instead make a ppc_cache_info structure with one
copy for I and one for D

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/include/asm/cache.h   |  24 ++---
 arch/powerpc/include/asm/page_64.h |   4 +-
 arch/powerpc/kernel/align.c        |   2 +-
 arch/powerpc/kernel/asm-offsets.c  |  12 +--
 arch/powerpc/kernel/setup_64.c     | 183 ++++++++++++++++++-------------------
 arch/powerpc/kernel/vdso.c         |  16 ++--
 6 files changed, 119 insertions(+), 122 deletions(-)

v3: Split the initialisation of the cache members into init_cache_info() so
    that we can use that in a subsequent patch. (mpe)
diff --git a/arch/powerpc/include/asm/cache.h b/arch/powerpc/include/asm/cache.h
index 1fa364340146..823750fa6e66 100644
--- a/arch/powerpc/include/asm/cache.h
+++ b/arch/powerpc/include/asm/cache.h
@@ -30,19 +30,19 @@
 #define IFETCH_ALIGN_BYTES	(1 << IFETCH_ALIGN_SHIFT)
 
 #if defined(__powerpc64__) && !defined(__ASSEMBLY__)
+
+struct ppc_cache_info {
+	u32 size;
+	u32 line_size;
+	u32 block_size;	/* L1 only */
+	u32 log_block_size;
+	u32 blocks_per_page;
+	u32 sets;
+};
+
 struct ppc64_caches {
-	u32	dsize;			/* L1 d-cache size */
-	u32	dline_size;		/* L1 d-cache line size	*/
-	u32	dblock_size;		/* L1 d-cache block size */
-	u32	log_dblock_size;
-	u32	dblocks_per_page;
-	u32	dsets;
-	u32	isize;			/* L1 i-cache size */
-	u32	iline_size;		/* L1 d-cache line size	*/
-	u32	iblock_size;		/* L1 i-cache block size */
-	u32	log_iblock_size;
-	u32	iblocks_per_page;
-	u32	isets;
+	struct ppc_cache_info l1d;
+	struct ppc_cache_info l1i;
 };
 
 extern struct ppc64_caches ppc64_caches;
diff --git a/arch/powerpc/include/asm/page_64.h b/arch/powerpc/include/asm/page_64.h
index c50a666308dd..3e83d2a20b6f 100644
--- a/arch/powerpc/include/asm/page_64.h
+++ b/arch/powerpc/include/asm/page_64.h
@@ -47,14 +47,14 @@ static inline void clear_page(void *addr)
 	unsigned long iterations;
 	unsigned long onex, twox, fourx, eightx;
 
-	iterations = ppc64_caches.dblocks_per_page / 8;
+	iterations = ppc64_caches.l1d.blocks_per_page / 8;
 
 	/*
 	 * Some verisions of gcc use multiply instructions to
 	 * calculate the offsets so lets give it a hand to
 	 * do better.
 	 */
-	onex = ppc64_caches.dblock_size;
+	onex = ppc64_caches.l1d.block_size;
 	twox = onex << 1;
 	fourx = onex << 2;
 	eightx = onex << 3;
diff --git a/arch/powerpc/kernel/align.c b/arch/powerpc/kernel/align.c
index 30ff6590a2dd..cbc7c42cdb74 100644
--- a/arch/powerpc/kernel/align.c
+++ b/arch/powerpc/kernel/align.c
@@ -204,7 +204,7 @@ static int emulate_dcbz(struct pt_regs *regs, unsigned char __user *addr)
 	int i, size;
 
 #ifdef __powerpc64__
-	size = ppc64_caches.dblock_size;
+	size = ppc64_caches.l1d.block_size;
 #else
 	size = L1_CACHE_BYTES;
 #endif
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 125442107b40..b4324db94741 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -163,12 +163,12 @@ int main(void)
 	DEFINE(TI_CPU, offsetof(struct thread_info, cpu));
 
 #ifdef CONFIG_PPC64
-	DEFINE(DCACHEL1BLOCKSIZE, offsetof(struct ppc64_caches, dblock_size));
-	DEFINE(DCACHEL1LOGBLOCKSIZE, offsetof(struct ppc64_caches, log_dblock_size));
-	DEFINE(DCACHEL1BLOCKSPERPAGE, offsetof(struct ppc64_caches, dblocks_per_page));
-	DEFINE(ICACHEL1BLOCKSIZE, offsetof(struct ppc64_caches, iblock_size));
-	DEFINE(ICACHEL1LOGBLOCKSIZE, offsetof(struct ppc64_caches, log_iblock_size));
-	DEFINE(ICACHEL1BLOCKSPERPAGE, offsetof(struct ppc64_caches, iblocks_per_page));
+	DEFINE(DCACHEL1BLOCKSIZE, offsetof(struct ppc64_caches, l1d.block_size));
+	DEFINE(DCACHEL1LOGBLOCKSIZE, offsetof(struct ppc64_caches, l1d.log_block_size));
+	DEFINE(DCACHEL1BLOCKSPERPAGE, offsetof(struct ppc64_caches, l1d.blocks_per_page));
+	DEFINE(ICACHEL1BLOCKSIZE, offsetof(struct ppc64_caches, l1i.block_size));
+	DEFINE(ICACHEL1LOGBLOCKSIZE, offsetof(struct ppc64_caches, l1i.log_block_size));
+	DEFINE(ICACHEL1BLOCKSPERPAGE, offsetof(struct ppc64_caches, l1i.blocks_per_page));
 	/* paca */
 	DEFINE(PACA_SIZE, sizeof(struct paca_struct));
 	DEFINE(PACAPACAINDEX, offsetof(struct paca_struct, paca_index));
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index 75c9a8641ba1..b87dcb2968d9 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -78,10 +78,14 @@ int spinning_secondaries;
 u64 ppc64_pft_size;
 
 struct ppc64_caches ppc64_caches = {
-	.dblock_size = 0x40,
-	.log_dblock_size = 6,
-	.iblock_size = 0x40,
-	.log_iblock_size = 6
+	.l1d = {
+		.block_size = 0x40,
+		.log_block_size = 6,
+	},
+	.l1i = {
+		.block_size = 0x40,
+		.log_block_size = 6
+	},
 };
 EXPORT_SYMBOL_GPL(ppc64_caches);
 
@@ -397,105 +401,98 @@ void smp_release_cpus(void)
  * cache informations about the CPU that will be used by cache flush
  * routines and/or provided to userland
  */
+
+static void init_cache_info(struct ppc_cache_info *info, u32 size, u32 lsize,
+			    u32 bsize, u32 sets)
+{
+	info->size = size;
+	info->sets = sets;
+	info->line_size = lsize;
+	info->block_size = bsize;
+	info->log_block_size = __ilog2(bsize);
+	info->blocks_per_page = PAGE_SIZE / bsize;
+}
+
+static bool __init parse_cache_info(struct device_node *np,
+				    bool icache,
+				    struct ppc_cache_info *info)
+{
+	static const char *ipropnames[] __initdata = {
+		"i-cache-size",
+		"i-cache-sets",
+		"i-cache-block-size",
+		"i-cache-line-size",
+	};
+	static const char *dpropnames[] __initdata = {
+		"d-cache-size",
+		"d-cache-sets",
+		"d-cache-block-size",
+		"d-cache-line-size",
+	};
+	const char **propnames = icache ? ipropnames : dpropnames;
+	const __be32 *sizep, *lsizep, *bsizep, *setsp;
+	u32 size, lsize, bsize, sets;
+	bool success = true;
+
+	size = 0;
+	sets = -1u;
+	lsize = bsize = cur_cpu_spec->dcache_bsize;
+	sizep = of_get_property(np, propnames[0], NULL);
+	if (sizep != NULL)
+		size = be32_to_cpu(*sizep);
+	setsp = of_get_property(np, propnames[1], NULL);
+	if (setsp != NULL)
+		sets = be32_to_cpu(*setsp);
+	bsizep = of_get_property(np, propnames[2], NULL);
+	lsizep = of_get_property(np, propnames[3], NULL);
+	if (bsizep == NULL)
+		bsizep = lsizep;
+	if (lsizep != NULL)
+		lsize = be32_to_cpu(*lsizep);
+	if (bsizep != NULL)
+		bsize = be32_to_cpu(*bsizep);
+	if (sizep == NULL || bsizep == NULL || lsizep == NULL)
+		success = false;
+
+	/*
+	 * OF is weird .. it represents fully associative caches
+	 * as "1 way" which doesn't make much sense and doesn't
+	 * leave room for direct mapped. We'll assume that 0
+	 * in OF means direct mapped for that reason.
+	 */
+	if (sets == 1)
+		sets = 0;
+	else if (sets == 0)
+		sets = 1;
+
+	init_cache_info(info, size, lsize, bsize, sets);
+
+	return success;
+}
+
 void __init initialize_cache_info(void)
 {
 	struct device_node *np;
-	unsigned long num_cpus = 0;
 
 	DBG(" -> initialize_cache_info()\n");
 
-	for_each_node_by_type(np, "cpu") {
-		num_cpus += 1;
+	np  = of_find_node_by_type(NULL, "cpu");
 
-		/*
-		 * We're assuming *all* of the CPUs have the same
-		 * d-cache and i-cache sizes... -Peter
-		 */
-		if (num_cpus == 1) {
-			const __be32 *sizep, *lsizep, *bsizep, *setsp;
-			u32 size, lsize, bsize, sets;
-
-			size = 0;
-			sets = -1u;
-			lsize = bsize = cur_cpu_spec->dcache_bsize;
-			sizep = of_get_property(np, "d-cache-size", NULL);
-			if (sizep != NULL)
-				size = be32_to_cpu(*sizep);
-			setsp = of_get_property(np, "d-cache-sets", NULL);
-			if (setsp != NULL)
-				sets = be32_to_cpu(*setsp);
-			bsizep = of_get_property(np, "d-cache-block-size",
-						 NULL);
-			lsizep = of_get_property(np, "d-cache-line-size",
-						 NULL);
-			if (bsizep == NULL)
-				bsizep = lsizep;
-			if (lsizep != NULL)
-				lsize = be32_to_cpu(*lsizep);
-			if (bsizep != NULL)
-				bsize = be32_to_cpu(*bsizep);
-			if (sizep == NULL || bsizep == NULL || lsizep == NULL)
-				DBG("Argh, can't find dcache properties ! "
-				    "sizep: %p, bsizep: %p, lsizep: %p\n",
-				    sizep, bsizep, lsizep);
-
-			/*
-			 * OF is weird .. it represents fully associative caches
-			 * as "1 way" which doesn't make much sense and doesn't
-			 * leave room for direct mapped. We'll assume that 0
-			 * in OF means direct mapped for that reason.
-			 */
-			if (sets == 1)
-				sets = 0;
-			else if (sets == 0)
-				sets = 1;
-			ppc64_caches.dsize = size;
-			ppc64_caches.dsets = sets;
-			ppc64_caches.dline_size = lsize;
-			ppc64_caches.dblock_size = bsize;
-			ppc64_caches.log_dblock_size = __ilog2(bsize);
-			ppc64_caches.dblocks_per_page = PAGE_SIZE / bsize;
-
-			size = 0;
-			sets = -1u;
-			lsize = bsize = cur_cpu_spec->icache_bsize;
-			sizep = of_get_property(np, "i-cache-size", NULL);
-			if (sizep != NULL)
-				size = be32_to_cpu(*sizep);
-			setsp = of_get_property(np, "i-cache-sets", NULL);
-			if (setsp != NULL)
-				sets = be32_to_cpu(*setsp);
-			bsizep = of_get_property(np, "i-cache-block-size",
-						 NULL);
-			lsizep = of_get_property(np, "i-cache-line-size",
-						 NULL);
-			if (bsizep == NULL)
-				bsizep = lsizep;
-			if (lsizep != NULL)
-				lsize = be32_to_cpu(*lsizep);
-			if (bsizep != NULL)
-				bsize = be32_to_cpu(*bsizep);
-			if (sizep == NULL || bsizep == NULL || lsizep == NULL)
-				DBG("Argh, can't find icache properties ! "
-				    "sizep: %p, bsizep: %p, lsizep: %p\n",
-				    sizep, bsizep, lsizep);
-
-			if (sets == 1)
-				sets = 0;
-			else if (sets == 0)
-				sets = 1;
-			ppc64_caches.isize = size;
-			ppc64_caches.isets = sets;
-			ppc64_caches.iline_size = lsize;
-			ppc64_caches.iblock_size = bsize;
-			ppc64_caches.log_iblock_size = __ilog2(bsize);
-			ppc64_caches.iblocks_per_page = PAGE_SIZE / bsize;
-		}
+	/*
+	 * We're assuming *all* of the CPUs have the same
+	 * d-cache and i-cache sizes... -Peter
+	 */
+	if (np) {
+		if (!parse_cache_info(np, false, &ppc64_caches.l1d))
+			DBG("Argh, can't find dcache properties !\n");
+
+		if (!parse_cache_info(np, true, &ppc64_caches.l1i))
+			DBG("Argh, can't find icache properties !\n");
 	}
 
 	/* For use by binfmt_elf */
-	dcache_bsize = ppc64_caches.dblock_size;
-	icache_bsize = ppc64_caches.iblock_size;
+	dcache_bsize = ppc64_caches.l1d.block_size;
+	icache_bsize = ppc64_caches.l1i.block_size;
 
 	DBG(" <- initialize_cache_info()\n");
 }
diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c
index 9c0a85776c6c..22b01a3962f0 100644
--- a/arch/powerpc/kernel/vdso.c
+++ b/arch/powerpc/kernel/vdso.c
@@ -736,14 +736,14 @@ static int __init vdso_init(void)
 	if (firmware_has_feature(FW_FEATURE_LPAR))
 		vdso_data->platform |= 1;
 	vdso_data->physicalMemorySize = memblock_phys_mem_size();
-	vdso_data->dcache_size = ppc64_caches.dsize;
-	vdso_data->dcache_line_size = ppc64_caches.dline_size;
-	vdso_data->icache_size = ppc64_caches.isize;
-	vdso_data->icache_line_size = ppc64_caches.iline_size;
-	vdso_data->dcache_block_size = ppc64_caches.dblock_size;
-	vdso_data->icache_block_size = ppc64_caches.iblock_size;
-	vdso_data->dcache_log_block_size = ppc64_caches.log_dblock_size;
-	vdso_data->icache_log_block_size = ppc64_caches.log_iblock_size;
+	vdso_data->dcache_size = ppc64_caches.l1d.size;
+	vdso_data->dcache_line_size = ppc64_caches.l1d.line_size;
+	vdso_data->icache_size = ppc64_caches.l1i.size;
+	vdso_data->icache_line_size = ppc64_caches.l1i.line_size;
+	vdso_data->dcache_block_size = ppc64_caches.l1d.block_size;
+	vdso_data->icache_block_size = ppc64_caches.l1i.block_size;
+	vdso_data->dcache_log_block_size = ppc64_caches.l1d.log_block_size;
+	vdso_data->icache_log_block_size = ppc64_caches.l1i.log_block_size;
 
 	/*
 	 * Calculate the size of the 64 bits vDSO
-- 
2.7.4

[PATCH v3 7/9] powerpc/64: Add L2 and L3 cache shape info

From: Michael Ellerman <mpe@ellerman.id.au>
Date: 2017-02-03 11:06:18

From: Benjamin Herrenschmidt <benh@kernel.crashing.org>

Retrieved from device-tree when available

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/include/asm/cache.h |  2 ++
 arch/powerpc/kernel/setup_64.c   | 26 +++++++++++++++++++++-----
 2 files changed, 23 insertions(+), 5 deletions(-)
diff --git a/arch/powerpc/include/asm/cache.h b/arch/powerpc/include/asm/cache.h
index 823750fa6e66..d7cf60f87604 100644
--- a/arch/powerpc/include/asm/cache.h
+++ b/arch/powerpc/include/asm/cache.h
@@ -43,6 +43,8 @@ struct ppc_cache_info {
 struct ppc64_caches {
 	struct ppc_cache_info l1d;
 	struct ppc_cache_info l1i;
+	struct ppc_cache_info l2;
+	struct ppc_cache_info l3;
 };
 
 extern struct ppc64_caches ppc64_caches;
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index b87dcb2968d9..db18f7b68a1d 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -472,22 +472,38 @@ static bool __init parse_cache_info(struct device_node *np,
 
 void __init initialize_cache_info(void)
 {
-	struct device_node *np;
+	struct device_node *cpu, *l2, *l3 = NULL;
 
 	DBG(" -> initialize_cache_info()\n");
 
-	np  = of_find_node_by_type(NULL, "cpu");
+	cpu = of_find_node_by_type(NULL, "cpu");
 
 	/*
 	 * We're assuming *all* of the CPUs have the same
 	 * d-cache and i-cache sizes... -Peter
 	 */
-	if (np) {
-		if (!parse_cache_info(np, false, &ppc64_caches.l1d))
+	if (cpu) {
+		if (!parse_cache_info(cpu, false, &ppc64_caches.l1d))
 			DBG("Argh, can't find dcache properties !\n");
 
-		if (!parse_cache_info(np, true, &ppc64_caches.l1i))
+		if (!parse_cache_info(cpu, true, &ppc64_caches.l1i))
 			DBG("Argh, can't find icache properties !\n");
+
+		/*
+		 * Try to find the L2 and L3 if any. Assume they are
+		 * unified and use the D-side properties.
+		 */
+		l2 = of_find_next_cache_node(cpu);
+		of_node_put(cpu);
+		if (l2) {
+			parse_cache_info(l2, false, &ppc64_caches.l2);
+			l3 = of_find_next_cache_node(l2);
+			of_node_put(l2);
+		}
+		if (l3) {
+			parse_cache_info(l3, false, &ppc64_caches.l3);
+			of_node_put(l3);
+		}
 	}
 
 	/* For use by binfmt_elf */
-- 
2.7.4

[PATCH v3 8/9] powerpc/64: Hard code cache geometry on POWER8

From: Michael Ellerman <mpe@ellerman.id.au>
Date: 2017-02-03 11:06:18

From: Benjamin Herrenschmidt <benh@kernel.crashing.org>

All shipping firmware versions have it wrong in the device-tree

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/kernel/setup_64.c | 20 ++++++++++++++++++--
 1 file changed, 18 insertions(+), 2 deletions(-)

v3: Rather than defining ppc_cache_info structs with the p8 values, just call
    init_cache_info() directly with the p8 values. This is less code, and means
    in the next patch info->assoc will be correctly populated for p8 which it
    wasn't in v2 of this patch. (mpe)
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index db18f7b68a1d..364fbffd7e83 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -472,11 +472,27 @@ static bool __init parse_cache_info(struct device_node *np,
 
 void __init initialize_cache_info(void)
 {
-	struct device_node *cpu, *l2, *l3 = NULL;
+	struct device_node *cpu = NULL, *l2, *l3 = NULL;
+	u32 pvr;
 
 	DBG(" -> initialize_cache_info()\n");
 
-	cpu = of_find_node_by_type(NULL, "cpu");
+	/*
+	 * All shipping POWER8 machines have a firmware bug that
+	 * puts incorrect information in the device-tree. This will
+	 * be (hopefully) fixed for future chips but for now hard
+	 * code the values if we are running on one of these
+	 */
+	pvr = PVR_VER(mfspr(SPRN_PVR));
+	if (pvr == PVR_POWER8 || pvr == PVR_POWER8E ||
+	    pvr == PVR_POWER8NVL) {
+						/* size    lsize   blk  sets */
+		init_cache_info(&ppc64_caches.l1i, 0x8000,   128,  128, 32);
+		init_cache_info(&ppc64_caches.l1d, 0x10000,  128,  128, 64);
+		init_cache_info(&ppc64_caches.l2,  0x80000,  128,  0,   512);
+		init_cache_info(&ppc64_caches.l3,  0x800000, 128,  0,   8192);
+	} else
+		cpu = of_find_node_by_type(NULL, "cpu");
 
 	/*
 	 * We're assuming *all* of the CPUs have the same
-- 
2.7.4

[PATCH v3 9/9] powerpc: Add new cache geometry aux vectors

From: Michael Ellerman <mpe@ellerman.id.au>
Date: 2017-02-03 11:06:19

From: Benjamin Herrenschmidt <benh@kernel.crashing.org>

This adds AUX vectors for the L1I,D, L2 and L3 cache levels
providing for each cache level the size of the cache in bytes
and the geometry (line size and number of ways).

We chose to not use the existing alpha/sh definition which
packs all the information in a single entry per cache level as
it is too restricted to represent some of the geometries used
on POWER.

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/include/asm/cache.h       |  1 +
 arch/powerpc/include/asm/elf.h         | 20 ++++++++++++++++++++
 arch/powerpc/include/uapi/asm/auxvec.h | 33 ++++++++++++++++++++++++++++++++-
 arch/powerpc/kernel/setup_64.c         |  5 +++++
 4 files changed, 58 insertions(+), 1 deletion(-)

v3: The initialisation of assoc is done in init_cache_info() which we also use
    for the hardcoded p8 values, so assoc is correctly initialised on p8. (mpe)
diff --git a/arch/powerpc/include/asm/cache.h b/arch/powerpc/include/asm/cache.h
index d7cf60f87604..5a90292afbad 100644
--- a/arch/powerpc/include/asm/cache.h
+++ b/arch/powerpc/include/asm/cache.h
@@ -38,6 +38,7 @@ struct ppc_cache_info {
 	u32 log_block_size;
 	u32 blocks_per_page;
 	u32 sets;
+	u32 assoc;
 };
 
 struct ppc64_caches {
diff --git a/arch/powerpc/include/asm/elf.h b/arch/powerpc/include/asm/elf.h
index 730c27ed10e1..93b9b84568e8 100644
--- a/arch/powerpc/include/asm/elf.h
+++ b/arch/powerpc/include/asm/elf.h
@@ -136,6 +136,25 @@ extern int arch_setup_additional_pages(struct linux_binprm *bprm,
 
 #endif /* CONFIG_SPU_BASE */
 
+#ifdef CONFIG_PPC64
+
+#define get_cache_geometry(level) \
+	(ppc64_caches.level.assoc << 16 | ppc64_caches.level.line_size)
+
+#define ARCH_DLINFO_CACHE_GEOMETRY					\
+	NEW_AUX_ENT(AT_L1I_CACHESIZE, ppc64_caches.l1i.size);		\
+	NEW_AUX_ENT(AT_L1I_CACHEGEOMETRY, get_cache_geometry(l1i));	\
+	NEW_AUX_ENT(AT_L1D_CACHESIZE, ppc64_caches.l1i.size);		\
+	NEW_AUX_ENT(AT_L1D_CACHEGEOMETRY, get_cache_geometry(l1i));	\
+	NEW_AUX_ENT(AT_L2_CACHESIZE, ppc64_caches.l2.size);		\
+	NEW_AUX_ENT(AT_L2_CACHEGEOMETRY, get_cache_geometry(l2));	\
+	NEW_AUX_ENT(AT_L3_CACHESIZE, ppc64_caches.l3.size);		\
+	NEW_AUX_ENT(AT_L3_CACHEGEOMETRY, get_cache_geometry(l3))
+
+#else
+#define ARCH_DLINFO_CACHE_GEOMETRY
+#endif
+
 /*
  * The requirements here are:
  * - keep the final alignment of sp (sp & 0xf)
@@ -156,6 +175,7 @@ do {									\
 	NEW_AUX_ENT(AT_ICACHEBSIZE, icache_bsize);			\
 	NEW_AUX_ENT(AT_UCACHEBSIZE, ucache_bsize);			\
 	VDSO_AUX_ENT(AT_SYSINFO_EHDR, current->mm->context.vdso_base);	\
+	ARCH_DLINFO_CACHE_GEOMETRY;					\
 } while (0)
 
 #endif /* _ASM_POWERPC_ELF_H */
diff --git a/arch/powerpc/include/uapi/asm/auxvec.h b/arch/powerpc/include/uapi/asm/auxvec.h
index ce17d2c9eb4e..be6e94ecec42 100644
--- a/arch/powerpc/include/uapi/asm/auxvec.h
+++ b/arch/powerpc/include/uapi/asm/auxvec.h
@@ -16,6 +16,37 @@
  */
 #define AT_SYSINFO_EHDR		33
 
-#define AT_VECTOR_SIZE_ARCH 6 /* entries in ARCH_DLINFO */
+/*
+ * AT_*CACHEBSIZE above represent the cache *block* size which is
+ * the size that is affected by the cache management instructions.
+ *
+ * It doesn't nececssarily matches the cache *line* size which is
+ * more of a performance tuning hint. Additionally the latter can
+ * be different for the different cache levels.
+ *
+ * The set of entries below represent more extensive information
+ * about the caches, in the form of two entry per cache type,
+ * one entry containing the cache size in bytes, and the other
+ * containing the cache line size in bytes in the bottom 16 bits
+ * and the cache associativity in the next 16 bits.
+ *
+ * The associativity is such that if N is the 16-bit value, the
+ * cache is N way set associative. A value if 0xffff means fully
+ * associative, a value of 1 means directly mapped.
+ *
+ * For all these fields, a value of 0 means that the information
+ * is not known.
+ */
+
+#define AT_L1I_CACHESIZE	40
+#define AT_L1I_CACHEGEOMETRY	41
+#define AT_L1D_CACHESIZE	42
+#define AT_L1D_CACHEGEOMETRY	43
+#define AT_L2_CACHESIZE		44
+#define AT_L2_CACHEGEOMETRY	45
+#define AT_L3_CACHESIZE		46
+#define AT_L3_CACHEGEOMETRY	47
+
+#define AT_VECTOR_SIZE_ARCH	14 /* entries in ARCH_DLINFO */
 
 #endif
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index 364fbffd7e83..b9855f1b290a 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -411,6 +411,11 @@ static void init_cache_info(struct ppc_cache_info *info, u32 size, u32 lsize,
 	info->block_size = bsize;
 	info->log_block_size = __ilog2(bsize);
 	info->blocks_per_page = PAGE_SIZE / bsize;
+
+	if (sets == 0)
+		info->assoc = 0xffff;
+	else
+		info->assoc = size / (sets * lsize);
 }
 
 static bool __init parse_cache_info(struct device_node *np,
-- 
2.7.4

Re: [v3,1/9] powerpc: Move ARCH_DLINFO out of uapi

From: Michael Ellerman <hidden>
Date: 2017-02-06 20:37:07

On Fri, 2017-02-03 at 11:05:51 UTC, Michael Ellerman wrote:
From: Benjamin Herrenschmidt <benh@kernel.crashing.org>

It's an kernel private macro, it doesn't belong there

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Series applied to powerpc next.

https://git.kernel.org/powerpc/c/2a196e24b39a

cheers
Keyboard shortcuts
hback out one level
jnext message in thread
kprevious message in thread
ldrill in
Escclose help / fold thread tree
?toggle this help