From daece59689e76ed55d8863cae04993679a8e844e Mon Sep 17 00:00:00 2001 From: Nicolas Pitre Date: Fri, 12 Aug 2011 00:14:29 +0100 Subject: ARM: 7013/1: P2V: Remove ARM_PATCH_PHYS_VIRT_16BIT This code can be removed now that MSM targets no longer need the 16-bit offsets for P2V. Signed-off-by: Nicolas Pitre Signed-off-by: Stephen Boyd Signed-off-by: Russell King --- arch/arm/include/asm/memory.h | 7 ------- arch/arm/include/asm/module.h | 4 ---- 2 files changed, 11 deletions(-) (limited to 'arch/arm/include') diff --git a/arch/arm/include/asm/memory.h b/arch/arm/include/asm/memory.h index b8de516e600e..441fc4fe8263 100644 --- a/arch/arm/include/asm/memory.h +++ b/arch/arm/include/asm/memory.h @@ -160,7 +160,6 @@ * so that all we need to do is modify the 8-bit constant field. */ #define __PV_BITS_31_24 0x81000000 -#define __PV_BITS_23_16 0x00810000 extern unsigned long __pv_phys_offset; #define PHYS_OFFSET __pv_phys_offset @@ -178,9 +177,6 @@ static inline unsigned long __virt_to_phys(unsigned long x) { unsigned long t; __pv_stub(x, t, "add", __PV_BITS_31_24); -#ifdef CONFIG_ARM_PATCH_PHYS_VIRT_16BIT - __pv_stub(t, t, "add", __PV_BITS_23_16); -#endif return t; } @@ -188,9 +184,6 @@ static inline unsigned long __phys_to_virt(unsigned long x) { unsigned long t; __pv_stub(x, t, "sub", __PV_BITS_31_24); -#ifdef CONFIG_ARM_PATCH_PHYS_VIRT_16BIT - __pv_stub(t, t, "sub", __PV_BITS_23_16); -#endif return t; } #else diff --git a/arch/arm/include/asm/module.h b/arch/arm/include/asm/module.h index 543b44916d2c..6c6809f982f1 100644 --- a/arch/arm/include/asm/module.h +++ b/arch/arm/include/asm/module.h @@ -31,11 +31,7 @@ struct mod_arch_specific { /* Add __virt_to_phys patching state as well */ #ifdef CONFIG_ARM_PATCH_PHYS_VIRT -#ifdef CONFIG_ARM_PATCH_PHYS_VIRT_16BIT -#define MODULE_ARCH_VERMAGIC_P2V "p2v16 " -#else #define MODULE_ARCH_VERMAGIC_P2V "p2v8 " -#endif #else #define MODULE_ARCH_VERMAGIC_P2V "" #endif -- cgit v1.2.3 From 1ace756628443ac41e8b6b409277fc4ee847472e Mon Sep 17 00:00:00 2001 From: Russell King Date: Thu, 7 Jul 2011 10:56:41 +0100 Subject: ARM: io: ecard: move ioaddr() inside __ecard_address Signed-off-by: Russell King --- arch/arm/include/asm/ecard.h | 1 - arch/arm/kernel/ecard.c | 11 ++++++----- 2 files changed, 6 insertions(+), 6 deletions(-) (limited to 'arch/arm/include') diff --git a/arch/arm/include/asm/ecard.h b/arch/arm/include/asm/ecard.h index 29f2610efc70..eaea14676d57 100644 --- a/arch/arm/include/asm/ecard.h +++ b/arch/arm/include/asm/ecard.h @@ -161,7 +161,6 @@ struct expansion_card { /* Private internal data */ const char *card_desc; /* Card description */ - CONST unsigned int podaddr; /* Base Linux address for card */ CONST loader_t loader; /* loader program */ u64 dma_mask; }; diff --git a/arch/arm/kernel/ecard.c b/arch/arm/kernel/ecard.c index d16500110ee9..920f1a371a22 100644 --- a/arch/arm/kernel/ecard.c +++ b/arch/arm/kernel/ecard.c @@ -678,13 +678,13 @@ static int __init ecard_probeirqhw(void) #define IO_EC_MEMC8_BASE 0 #endif -static unsigned int __ecard_address(ecard_t *ec, card_type_t type, card_speed_t speed) +static void __iomem *__ecard_address(ecard_t *ec, card_type_t type, card_speed_t speed) { unsigned long address = 0; int slot = ec->slot_no; if (ec->slot_no == 8) - return IO_EC_MEMC8_BASE; + return (void __iomem *)ioaddr(IO_EC_MEMC8_BASE); ectcr &= ~(1 << slot); @@ -719,7 +719,7 @@ static unsigned int __ecard_address(ecard_t *ec, card_type_t type, card_speed_t #ifdef IOMD_ECTCR iomd_writeb(ectcr, IOMD_ECTCR); #endif - return address; + return (void __iomem *)(address ? ioaddr(address) : NULL); } static int ecard_prints(struct seq_file *m, ecard_t *ec) @@ -990,6 +990,7 @@ ecard_probe(int slot, card_type_t type) ecard_t **ecp; ecard_t *ec; struct ex_ecid cid; + void __iomem *addr; int i, rc; ec = ecard_alloc_card(type, slot); @@ -999,7 +1000,7 @@ ecard_probe(int slot, card_type_t type) } rc = -ENODEV; - if ((ec->podaddr = __ecard_address(ec, type, ECARD_SYNC)) == 0) + if ((addr = __ecard_address(ec, type, ECARD_SYNC)) == NULL) goto nodev; cid.r_zero = 1; @@ -1019,7 +1020,7 @@ ecard_probe(int slot, card_type_t type) ec->cid.fiqmask = cid.r_fiqmask; ec->cid.fiqoff = ecard_gets24(cid.r_fiqoff); ec->fiqaddr = - ec->irqaddr = (void __iomem *)ioaddr(ec->podaddr); + ec->irqaddr = addr; if (ec->cid.is) { ec->irqmask = ec->cid.irqmask; -- cgit v1.2.3 From 04e1c83806e30ae339fc45def595960c7fef1697 Mon Sep 17 00:00:00 2001 From: Russell King Date: Wed, 6 Jul 2011 12:49:59 +0100 Subject: ARM: io: add a default IO_SPACE_LIMIT definition Add a default IO_SPACE_LIMIT definition. Explain the chosen value and suggest why platforms would want to make it larger. Signed-off-by: Russell King --- arch/arm/include/asm/io.h | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) (limited to 'arch/arm/include') diff --git a/arch/arm/include/asm/io.h b/arch/arm/include/asm/io.h index d66605dea55a..ffb089d46a17 100644 --- a/arch/arm/include/asm/io.h +++ b/arch/arm/include/asm/io.h @@ -109,6 +109,27 @@ static inline void __iomem *__typesafe_io(unsigned long addr) */ #include +/* + * This is the limit of PC card/PCI/ISA IO space, which is by default + * 64K if we have PC card, PCI or ISA support. Otherwise, default to + * zero to prevent ISA/PCI drivers claiming IO space (and potentially + * oopsing.) + * + * Only set this larger if you really need inb() et.al. to operate over + * a larger address space. Note that SOC_COMMON ioremaps each sockets + * IO space area, and so inb() et.al. must be defined to operate as per + * readb() et.al. on such platforms. + */ +#ifndef IO_SPACE_LIMIT +#if defined(CONFIG_PCMCIA_SOC_COMMON) || defined(CONFIG_PCMCIA_SOC_COMMON_MODULE) +#define IO_SPACE_LIMIT ((resource_size_t)0xffffffff) +#elif defined(CONFIG_PCI) || defined(CONFIG_ISA) || defined(CONFIG_PCCARD) +#define IO_SPACE_LIMIT ((resource_size_t)0xffff) +#else +#define IO_SPACE_LIMIT ((resource_size_t)0) +#endif +#endif + /* * IO port access primitives * ------------------------- -- cgit v1.2.3 From 01f461a3a4321a9f98b6b508f32d2396c5704b7c Mon Sep 17 00:00:00 2001 From: Catalin Marinas Date: Tue, 23 Aug 2011 13:59:14 +0100 Subject: ARM: 7058/1: LPAE: Cast the dma_addr_t argument to unsigned long in dma_to_virt This is to avoid a compiler warning when invoking the __bus_to_virt() macro. The dma_to_virt() function gets addresses within the 32-bit range. Signed-off-by: Catalin Marinas Signed-off-by: Russell King --- arch/arm/include/asm/dma-mapping.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/arm/include') diff --git a/arch/arm/include/asm/dma-mapping.h b/arch/arm/include/asm/dma-mapping.h index 7a21d0bf7134..28b7ee8d7398 100644 --- a/arch/arm/include/asm/dma-mapping.h +++ b/arch/arm/include/asm/dma-mapping.h @@ -32,7 +32,7 @@ static inline unsigned long dma_to_pfn(struct device *dev, dma_addr_t addr) static inline void *dma_to_virt(struct device *dev, dma_addr_t addr) { - return (void *)__bus_to_virt(addr); + return (void *)__bus_to_virt((unsigned long)addr); } static inline dma_addr_t virt_to_dma(struct device *dev, void *addr) -- cgit v1.2.3 From 06901bd83412db5a31de7526e637101ed0c2c472 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Sat, 3 Sep 2011 17:54:44 +0200 Subject: ARM: add io{read,write}{16,32}be functions These functions are used in some PCI drivers with big-endian MMIO space, and they are trivial to add here. Signed-off-by: Arnd Bergmann --- arch/arm/include/asm/io.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'arch/arm/include') diff --git a/arch/arm/include/asm/io.h b/arch/arm/include/asm/io.h index d66605dea55a..bad7bfb7af20 100644 --- a/arch/arm/include/asm/io.h +++ b/arch/arm/include/asm/io.h @@ -260,10 +260,16 @@ extern void _memset_io(volatile void __iomem *, int, size_t); #define ioread16(p) ({ unsigned int __v = le16_to_cpu((__force __le16)__raw_readw(p)); __iormb(); __v; }) #define ioread32(p) ({ unsigned int __v = le32_to_cpu((__force __le32)__raw_readl(p)); __iormb(); __v; }) +#define ioread16be(p) ({ unsigned int __v = be16_to_cpu((__force __be16)__raw_readw(p)); __iormb(); __v; }) +#define ioread32be(p) ({ unsigned int __v = be32_to_cpu((__force __be32)__raw_readl(p)); __iormb(); __v; }) + #define iowrite8(v,p) ({ __iowmb(); (void)__raw_writeb(v, p); }) #define iowrite16(v,p) ({ __iowmb(); (void)__raw_writew((__force __u16)cpu_to_le16(v), p); }) #define iowrite32(v,p) ({ __iowmb(); (void)__raw_writel((__force __u32)cpu_to_le32(v), p); }) +#define iowrite16be(v,p) ({ __iowmb(); (void)__raw_writew((__force __u16)cpu_to_be16(v), p); }) +#define iowrite32be(v,p) ({ __iowmb(); (void)__raw_writel((__force __u32)cpu_to_be32(v), p); }) + #define ioread8_rep(p,d,c) __raw_readsb(p,d,c) #define ioread16_rep(p,d,c) __raw_readsw(p,d,c) #define ioread32_rep(p,d,c) __raw_readsl(p,d,c) -- cgit v1.2.3 From 17f57211969bddca2e922299a2530b1c65ccabfa Mon Sep 17 00:00:00 2001 From: Catalin Marinas Date: Mon, 5 Sep 2011 17:41:02 +0100 Subject: ARM: 7075/1: LPAE: Factor out 2-level page table definitions into separate files This patch moves page table definitions from asm/page.h, asm/pgtable.h and asm/ptgable-hwdef.h into corresponding *-2level* files. Signed-off-by: Catalin Marinas Signed-off-by: Russell King --- arch/arm/include/asm/page.h | 42 +------- arch/arm/include/asm/pgtable-2level-hwdef.h | 91 ++++++++++++++++++ arch/arm/include/asm/pgtable-2level-types.h | 64 +++++++++++++ arch/arm/include/asm/pgtable-2level.h | 143 ++++++++++++++++++++++++++++ arch/arm/include/asm/pgtable-hwdef.h | 77 +-------------- arch/arm/include/asm/pgtable.h | 135 +------------------------- 6 files changed, 302 insertions(+), 250 deletions(-) create mode 100644 arch/arm/include/asm/pgtable-2level-hwdef.h create mode 100644 arch/arm/include/asm/pgtable-2level-types.h create mode 100644 arch/arm/include/asm/pgtable-2level.h (limited to 'arch/arm/include') diff --git a/arch/arm/include/asm/page.h b/arch/arm/include/asm/page.h index ac75d0848889..ca94653f1ecb 100644 --- a/arch/arm/include/asm/page.h +++ b/arch/arm/include/asm/page.h @@ -151,47 +151,7 @@ extern void __cpu_copy_user_highpage(struct page *to, struct page *from, #define clear_page(page) memset((void *)(page), 0, PAGE_SIZE) extern void copy_page(void *to, const void *from); -typedef unsigned long pteval_t; - -#undef STRICT_MM_TYPECHECKS - -#ifdef STRICT_MM_TYPECHECKS -/* - * These are used to make use of C type-checking.. - */ -typedef struct { pteval_t pte; } pte_t; -typedef struct { unsigned long pmd; } pmd_t; -typedef struct { unsigned long pgd[2]; } pgd_t; -typedef struct { unsigned long pgprot; } pgprot_t; - -#define pte_val(x) ((x).pte) -#define pmd_val(x) ((x).pmd) -#define pgd_val(x) ((x).pgd[0]) -#define pgprot_val(x) ((x).pgprot) - -#define __pte(x) ((pte_t) { (x) } ) -#define __pmd(x) ((pmd_t) { (x) } ) -#define __pgprot(x) ((pgprot_t) { (x) } ) - -#else -/* - * .. while these make it easier on the compiler - */ -typedef pteval_t pte_t; -typedef unsigned long pmd_t; -typedef unsigned long pgd_t[2]; -typedef unsigned long pgprot_t; - -#define pte_val(x) (x) -#define pmd_val(x) (x) -#define pgd_val(x) ((x)[0]) -#define pgprot_val(x) (x) - -#define __pte(x) (x) -#define __pmd(x) (x) -#define __pgprot(x) (x) - -#endif /* STRICT_MM_TYPECHECKS */ +#include #endif /* CONFIG_MMU */ diff --git a/arch/arm/include/asm/pgtable-2level-hwdef.h b/arch/arm/include/asm/pgtable-2level-hwdef.h new file mode 100644 index 000000000000..436529c1cda2 --- /dev/null +++ b/arch/arm/include/asm/pgtable-2level-hwdef.h @@ -0,0 +1,91 @@ +/* + * arch/arm/include/asm/pgtable-2level-hwdef.h + * + * Copyright (C) 1995-2002 Russell King + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ +#ifndef _ASM_PGTABLE_2LEVEL_HWDEF_H +#define _ASM_PGTABLE_2LEVEL_HWDEF_H + +/* + * Hardware page table definitions. + * + * + Level 1 descriptor (PMD) + * - common + */ +#define PMD_TYPE_MASK (3 << 0) +#define PMD_TYPE_FAULT (0 << 0) +#define PMD_TYPE_TABLE (1 << 0) +#define PMD_TYPE_SECT (2 << 0) +#define PMD_BIT4 (1 << 4) +#define PMD_DOMAIN(x) ((x) << 5) +#define PMD_PROTECTION (1 << 9) /* v5 */ +/* + * - section + */ +#define PMD_SECT_BUFFERABLE (1 << 2) +#define PMD_SECT_CACHEABLE (1 << 3) +#define PMD_SECT_XN (1 << 4) /* v6 */ +#define PMD_SECT_AP_WRITE (1 << 10) +#define PMD_SECT_AP_READ (1 << 11) +#define PMD_SECT_TEX(x) ((x) << 12) /* v5 */ +#define PMD_SECT_APX (1 << 15) /* v6 */ +#define PMD_SECT_S (1 << 16) /* v6 */ +#define PMD_SECT_nG (1 << 17) /* v6 */ +#define PMD_SECT_SUPER (1 << 18) /* v6 */ +#define PMD_SECT_AF (0) + +#define PMD_SECT_UNCACHED (0) +#define PMD_SECT_BUFFERED (PMD_SECT_BUFFERABLE) +#define PMD_SECT_WT (PMD_SECT_CACHEABLE) +#define PMD_SECT_WB (PMD_SECT_CACHEABLE | PMD_SECT_BUFFERABLE) +#define PMD_SECT_MINICACHE (PMD_SECT_TEX(1) | PMD_SECT_CACHEABLE) +#define PMD_SECT_WBWA (PMD_SECT_TEX(1) | PMD_SECT_CACHEABLE | PMD_SECT_BUFFERABLE) +#define PMD_SECT_NONSHARED_DEV (PMD_SECT_TEX(2)) + +/* + * - coarse table (not used) + */ + +/* + * + Level 2 descriptor (PTE) + * - common + */ +#define PTE_TYPE_MASK (3 << 0) +#define PTE_TYPE_FAULT (0 << 0) +#define PTE_TYPE_LARGE (1 << 0) +#define PTE_TYPE_SMALL (2 << 0) +#define PTE_TYPE_EXT (3 << 0) /* v5 */ +#define PTE_BUFFERABLE (1 << 2) +#define PTE_CACHEABLE (1 << 3) + +/* + * - extended small page/tiny page + */ +#define PTE_EXT_XN (1 << 0) /* v6 */ +#define PTE_EXT_AP_MASK (3 << 4) +#define PTE_EXT_AP0 (1 << 4) +#define PTE_EXT_AP1 (2 << 4) +#define PTE_EXT_AP_UNO_SRO (0 << 4) +#define PTE_EXT_AP_UNO_SRW (PTE_EXT_AP0) +#define PTE_EXT_AP_URO_SRW (PTE_EXT_AP1) +#define PTE_EXT_AP_URW_SRW (PTE_EXT_AP1|PTE_EXT_AP0) +#define PTE_EXT_TEX(x) ((x) << 6) /* v5 */ +#define PTE_EXT_APX (1 << 9) /* v6 */ +#define PTE_EXT_COHERENT (1 << 9) /* XScale3 */ +#define PTE_EXT_SHARED (1 << 10) /* v6 */ +#define PTE_EXT_NG (1 << 11) /* v6 */ + +/* + * - small page + */ +#define PTE_SMALL_AP_MASK (0xff << 4) +#define PTE_SMALL_AP_UNO_SRO (0x00 << 4) +#define PTE_SMALL_AP_UNO_SRW (0x55 << 4) +#define PTE_SMALL_AP_URO_SRW (0xaa << 4) +#define PTE_SMALL_AP_URW_SRW (0xff << 4) + +#endif diff --git a/arch/arm/include/asm/pgtable-2level-types.h b/arch/arm/include/asm/pgtable-2level-types.h new file mode 100644 index 000000000000..8a01f62d8a16 --- /dev/null +++ b/arch/arm/include/asm/pgtable-2level-types.h @@ -0,0 +1,64 @@ +/* + * arch/arm/include/asm/pgtable-2level-types.h + * + * Copyright (C) 1995-2003 Russell King + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + */ +#ifndef _ASM_PGTABLE_2LEVEL_TYPES_H +#define _ASM_PGTABLE_2LEVEL_TYPES_H + +typedef unsigned long pteval_t; + +#undef STRICT_MM_TYPECHECKS + +#ifdef STRICT_MM_TYPECHECKS +/* + * These are used to make use of C type-checking.. + */ +typedef struct { pteval_t pte; } pte_t; +typedef struct { unsigned long pmd; } pmd_t; +typedef struct { unsigned long pgd[2]; } pgd_t; +typedef struct { unsigned long pgprot; } pgprot_t; + +#define pte_val(x) ((x).pte) +#define pmd_val(x) ((x).pmd) +#define pgd_val(x) ((x).pgd[0]) +#define pgprot_val(x) ((x).pgprot) + +#define __pte(x) ((pte_t) { (x) } ) +#define __pmd(x) ((pmd_t) { (x) } ) +#define __pgprot(x) ((pgprot_t) { (x) } ) + +#else +/* + * .. while these make it easier on the compiler + */ +typedef pteval_t pte_t; +typedef unsigned long pmd_t; +typedef unsigned long pgd_t[2]; +typedef unsigned long pgprot_t; + +#define pte_val(x) (x) +#define pmd_val(x) (x) +#define pgd_val(x) ((x)[0]) +#define pgprot_val(x) (x) + +#define __pte(x) (x) +#define __pmd(x) (x) +#define __pgprot(x) (x) + +#endif /* STRICT_MM_TYPECHECKS */ + +#endif /* _ASM_PGTABLE_2LEVEL_TYPES_H */ diff --git a/arch/arm/include/asm/pgtable-2level.h b/arch/arm/include/asm/pgtable-2level.h new file mode 100644 index 000000000000..470457e1cfc5 --- /dev/null +++ b/arch/arm/include/asm/pgtable-2level.h @@ -0,0 +1,143 @@ +/* + * arch/arm/include/asm/pgtable-2level.h + * + * Copyright (C) 1995-2002 Russell King + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ +#ifndef _ASM_PGTABLE_2LEVEL_H +#define _ASM_PGTABLE_2LEVEL_H + +/* + * Hardware-wise, we have a two level page table structure, where the first + * level has 4096 entries, and the second level has 256 entries. Each entry + * is one 32-bit word. Most of the bits in the second level entry are used + * by hardware, and there aren't any "accessed" and "dirty" bits. + * + * Linux on the other hand has a three level page table structure, which can + * be wrapped to fit a two level page table structure easily - using the PGD + * and PTE only. However, Linux also expects one "PTE" table per page, and + * at least a "dirty" bit. + * + * Therefore, we tweak the implementation slightly - we tell Linux that we + * have 2048 entries in the first level, each of which is 8 bytes (iow, two + * hardware pointers to the second level.) The second level contains two + * hardware PTE tables arranged contiguously, preceded by Linux versions + * which contain the state information Linux needs. We, therefore, end up + * with 512 entries in the "PTE" level. + * + * This leads to the page tables having the following layout: + * + * pgd pte + * | | + * +--------+ + * | | +------------+ +0 + * +- - - - + | Linux pt 0 | + * | | +------------+ +1024 + * +--------+ +0 | Linux pt 1 | + * | |-----> +------------+ +2048 + * +- - - - + +4 | h/w pt 0 | + * | |-----> +------------+ +3072 + * +--------+ +8 | h/w pt 1 | + * | | +------------+ +4096 + * + * See L_PTE_xxx below for definitions of bits in the "Linux pt", and + * PTE_xxx for definitions of bits appearing in the "h/w pt". + * + * PMD_xxx definitions refer to bits in the first level page table. + * + * The "dirty" bit is emulated by only granting hardware write permission + * iff the page is marked "writable" and "dirty" in the Linux PTE. This + * means that a write to a clean page will cause a permission fault, and + * the Linux MM layer will mark the page dirty via handle_pte_fault(). + * For the hardware to notice the permission change, the TLB entry must + * be flushed, and ptep_set_access_flags() does that for us. + * + * The "accessed" or "young" bit is emulated by a similar method; we only + * allow accesses to the page if the "young" bit is set. Accesses to the + * page will cause a fault, and handle_pte_fault() will set the young bit + * for us as long as the page is marked present in the corresponding Linux + * PTE entry. Again, ptep_set_access_flags() will ensure that the TLB is + * up to date. + * + * However, when the "young" bit is cleared, we deny access to the page + * by clearing the hardware PTE. Currently Linux does not flush the TLB + * for us in this case, which means the TLB will retain the transation + * until either the TLB entry is evicted under pressure, or a context + * switch which changes the user space mapping occurs. + */ +#define PTRS_PER_PTE 512 +#define PTRS_PER_PMD 1 +#define PTRS_PER_PGD 2048 + +#define PTE_HWTABLE_PTRS (PTRS_PER_PTE) +#define PTE_HWTABLE_OFF (PTE_HWTABLE_PTRS * sizeof(pte_t)) +#define PTE_HWTABLE_SIZE (PTRS_PER_PTE * sizeof(u32)) + +/* + * PMD_SHIFT determines the size of the area a second-level page table can map + * PGDIR_SHIFT determines what a third-level page table entry can map + */ +#define PMD_SHIFT 21 +#define PGDIR_SHIFT 21 + +#define PMD_SIZE (1UL << PMD_SHIFT) +#define PMD_MASK (~(PMD_SIZE-1)) +#define PGDIR_SIZE (1UL << PGDIR_SHIFT) +#define PGDIR_MASK (~(PGDIR_SIZE-1)) + +/* + * section address mask and size definitions. + */ +#define SECTION_SHIFT 20 +#define SECTION_SIZE (1UL << SECTION_SHIFT) +#define SECTION_MASK (~(SECTION_SIZE-1)) + +/* + * ARMv6 supersection address mask and size definitions. + */ +#define SUPERSECTION_SHIFT 24 +#define SUPERSECTION_SIZE (1UL << SUPERSECTION_SHIFT) +#define SUPERSECTION_MASK (~(SUPERSECTION_SIZE-1)) + +#define USER_PTRS_PER_PGD (TASK_SIZE / PGDIR_SIZE) + +/* + * "Linux" PTE definitions. + * + * We keep two sets of PTEs - the hardware and the linux version. + * This allows greater flexibility in the way we map the Linux bits + * onto the hardware tables, and allows us to have YOUNG and DIRTY + * bits. + * + * The PTE table pointer refers to the hardware entries; the "Linux" + * entries are stored 1024 bytes below. + */ +#define L_PTE_PRESENT (_AT(pteval_t, 1) << 0) +#define L_PTE_YOUNG (_AT(pteval_t, 1) << 1) +#define L_PTE_FILE (_AT(pteval_t, 1) << 2) /* only when !PRESENT */ +#define L_PTE_DIRTY (_AT(pteval_t, 1) << 6) +#define L_PTE_RDONLY (_AT(pteval_t, 1) << 7) +#define L_PTE_USER (_AT(pteval_t, 1) << 8) +#define L_PTE_XN (_AT(pteval_t, 1) << 9) +#define L_PTE_SHARED (_AT(pteval_t, 1) << 10) /* shared(v6), coherent(xsc3) */ + +/* + * These are the memory types, defined to be compatible with + * pre-ARMv6 CPUs cacheable and bufferable bits: XXCB + */ +#define L_PTE_MT_UNCACHED (_AT(pteval_t, 0x00) << 2) /* 0000 */ +#define L_PTE_MT_BUFFERABLE (_AT(pteval_t, 0x01) << 2) /* 0001 */ +#define L_PTE_MT_WRITETHROUGH (_AT(pteval_t, 0x02) << 2) /* 0010 */ +#define L_PTE_MT_WRITEBACK (_AT(pteval_t, 0x03) << 2) /* 0011 */ +#define L_PTE_MT_MINICACHE (_AT(pteval_t, 0x06) << 2) /* 0110 (sa1100, xscale) */ +#define L_PTE_MT_WRITEALLOC (_AT(pteval_t, 0x07) << 2) /* 0111 */ +#define L_PTE_MT_DEV_SHARED (_AT(pteval_t, 0x04) << 2) /* 0100 */ +#define L_PTE_MT_DEV_NONSHARED (_AT(pteval_t, 0x0c) << 2) /* 1100 */ +#define L_PTE_MT_DEV_WC (_AT(pteval_t, 0x09) << 2) /* 1001 */ +#define L_PTE_MT_DEV_CACHED (_AT(pteval_t, 0x0b) << 2) /* 1011 */ +#define L_PTE_MT_MASK (_AT(pteval_t, 0x0f) << 2) + +#endif /* _ASM_PGTABLE_2LEVEL_H */ diff --git a/arch/arm/include/asm/pgtable-hwdef.h b/arch/arm/include/asm/pgtable-hwdef.h index fd1521d5cb9d..183111164ce9 100644 --- a/arch/arm/include/asm/pgtable-hwdef.h +++ b/arch/arm/include/asm/pgtable-hwdef.h @@ -10,81 +10,6 @@ #ifndef _ASMARM_PGTABLE_HWDEF_H #define _ASMARM_PGTABLE_HWDEF_H -/* - * Hardware page table definitions. - * - * + Level 1 descriptor (PMD) - * - common - */ -#define PMD_TYPE_MASK (3 << 0) -#define PMD_TYPE_FAULT (0 << 0) -#define PMD_TYPE_TABLE (1 << 0) -#define PMD_TYPE_SECT (2 << 0) -#define PMD_BIT4 (1 << 4) -#define PMD_DOMAIN(x) ((x) << 5) -#define PMD_PROTECTION (1 << 9) /* v5 */ -/* - * - section - */ -#define PMD_SECT_BUFFERABLE (1 << 2) -#define PMD_SECT_CACHEABLE (1 << 3) -#define PMD_SECT_XN (1 << 4) /* v6 */ -#define PMD_SECT_AP_WRITE (1 << 10) -#define PMD_SECT_AP_READ (1 << 11) -#define PMD_SECT_TEX(x) ((x) << 12) /* v5 */ -#define PMD_SECT_APX (1 << 15) /* v6 */ -#define PMD_SECT_S (1 << 16) /* v6 */ -#define PMD_SECT_nG (1 << 17) /* v6 */ -#define PMD_SECT_SUPER (1 << 18) /* v6 */ - -#define PMD_SECT_UNCACHED (0) -#define PMD_SECT_BUFFERED (PMD_SECT_BUFFERABLE) -#define PMD_SECT_WT (PMD_SECT_CACHEABLE) -#define PMD_SECT_WB (PMD_SECT_CACHEABLE | PMD_SECT_BUFFERABLE) -#define PMD_SECT_MINICACHE (PMD_SECT_TEX(1) | PMD_SECT_CACHEABLE) -#define PMD_SECT_WBWA (PMD_SECT_TEX(1) | PMD_SECT_CACHEABLE | PMD_SECT_BUFFERABLE) -#define PMD_SECT_NONSHARED_DEV (PMD_SECT_TEX(2)) - -/* - * - coarse table (not used) - */ - -/* - * + Level 2 descriptor (PTE) - * - common - */ -#define PTE_TYPE_MASK (3 << 0) -#define PTE_TYPE_FAULT (0 << 0) -#define PTE_TYPE_LARGE (1 << 0) -#define PTE_TYPE_SMALL (2 << 0) -#define PTE_TYPE_EXT (3 << 0) /* v5 */ -#define PTE_BUFFERABLE (1 << 2) -#define PTE_CACHEABLE (1 << 3) - -/* - * - extended small page/tiny page - */ -#define PTE_EXT_XN (1 << 0) /* v6 */ -#define PTE_EXT_AP_MASK (3 << 4) -#define PTE_EXT_AP0 (1 << 4) -#define PTE_EXT_AP1 (2 << 4) -#define PTE_EXT_AP_UNO_SRO (0 << 4) -#define PTE_EXT_AP_UNO_SRW (PTE_EXT_AP0) -#define PTE_EXT_AP_URO_SRW (PTE_EXT_AP1) -#define PTE_EXT_AP_URW_SRW (PTE_EXT_AP1|PTE_EXT_AP0) -#define PTE_EXT_TEX(x) ((x) << 6) /* v5 */ -#define PTE_EXT_APX (1 << 9) /* v6 */ -#define PTE_EXT_COHERENT (1 << 9) /* XScale3 */ -#define PTE_EXT_SHARED (1 << 10) /* v6 */ -#define PTE_EXT_NG (1 << 11) /* v6 */ - -/* - * - small page - */ -#define PTE_SMALL_AP_MASK (0xff << 4) -#define PTE_SMALL_AP_UNO_SRO (0x00 << 4) -#define PTE_SMALL_AP_UNO_SRW (0x55 << 4) -#define PTE_SMALL_AP_URO_SRW (0xaa << 4) -#define PTE_SMALL_AP_URW_SRW (0xff << 4) +#include #endif diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h index 5750704e0271..d6436dacb17b 100644 --- a/arch/arm/include/asm/pgtable.h +++ b/arch/arm/include/asm/pgtable.h @@ -24,6 +24,8 @@ #include #include +#include + /* * Just any arbitrary offset to the start of the vmalloc VM area: the * current 8MB value just means that there will be a 8MB "hole" after the @@ -41,79 +43,6 @@ #define VMALLOC_START (((unsigned long)high_memory + VMALLOC_OFFSET) & ~(VMALLOC_OFFSET-1)) #endif -/* - * Hardware-wise, we have a two level page table structure, where the first - * level has 4096 entries, and the second level has 256 entries. Each entry - * is one 32-bit word. Most of the bits in the second level entry are used - * by hardware, and there aren't any "accessed" and "dirty" bits. - * - * Linux on the other hand has a three level page table structure, which can - * be wrapped to fit a two level page table structure easily - using the PGD - * and PTE only. However, Linux also expects one "PTE" table per page, and - * at least a "dirty" bit. - * - * Therefore, we tweak the implementation slightly - we tell Linux that we - * have 2048 entries in the first level, each of which is 8 bytes (iow, two - * hardware pointers to the second level.) The second level contains two - * hardware PTE tables arranged contiguously, preceded by Linux versions - * which contain the state information Linux needs. We, therefore, end up - * with 512 entries in the "PTE" level. - * - * This leads to the page tables having the following layout: - * - * pgd pte - * | | - * +--------+ - * | | +------------+ +0 - * +- - - - + | Linux pt 0 | - * | | +------------+ +1024 - * +--------+ +0 | Linux pt 1 | - * | |-----> +------------+ +2048 - * +- - - - + +4 | h/w pt 0 | - * | |-----> +------------+ +3072 - * +--------+ +8 | h/w pt 1 | - * | | +------------+ +4096 - * - * See L_PTE_xxx below for definitions of bits in the "Linux pt", and - * PTE_xxx for definitions of bits appearing in the "h/w pt". - * - * PMD_xxx definitions refer to bits in the first level page table. - * - * The "dirty" bit is emulated by only granting hardware write permission - * iff the page is marked "writable" and "dirty" in the Linux PTE. This - * means that a write to a clean page will cause a permission fault, and - * the Linux MM layer will mark the page dirty via handle_pte_fault(). - * For the hardware to notice the permission change, the TLB entry must - * be flushed, and ptep_set_access_flags() does that for us. - * - * The "accessed" or "young" bit is emulated by a similar method; we only - * allow accesses to the page if the "young" bit is set. Accesses to the - * page will cause a fault, and handle_pte_fault() will set the young bit - * for us as long as the page is marked present in the corresponding Linux - * PTE entry. Again, ptep_set_access_flags() will ensure that the TLB is - * up to date. - * - * However, when the "young" bit is cleared, we deny access to the page - * by clearing the hardware PTE. Currently Linux does not flush the TLB - * for us in this case, which means the TLB will retain the transation - * until either the TLB entry is evicted under pressure, or a context - * switch which changes the user space mapping occurs. - */ -#define PTRS_PER_PTE 512 -#define PTRS_PER_PMD 1 -#define PTRS_PER_PGD 2048 - -#define PTE_HWTABLE_PTRS (PTRS_PER_PTE) -#define PTE_HWTABLE_OFF (PTE_HWTABLE_PTRS * sizeof(pte_t)) -#define PTE_HWTABLE_SIZE (PTRS_PER_PTE * sizeof(u32)) - -/* - * PMD_SHIFT determines the size of the area a second-level page table can map - * PGDIR_SHIFT determines what a third-level page table entry can map - */ -#define PMD_SHIFT 21 -#define PGDIR_SHIFT 21 - #define LIBRARY_TEXT_START 0x0c000000 #ifndef __ASSEMBLY__ @@ -124,12 +53,6 @@ extern void __pgd_error(const char *file, int line, pgd_t); #define pte_ERROR(pte) __pte_error(__FILE__, __LINE__, pte) #define pmd_ERROR(pmd) __pmd_error(__FILE__, __LINE__, pmd) #define pgd_ERROR(pgd) __pgd_error(__FILE__, __LINE__, pgd) -#endif /* !__ASSEMBLY__ */ - -#define PMD_SIZE (1UL << PMD_SHIFT) -#define PMD_MASK (~(PMD_SIZE-1)) -#define PGDIR_SIZE (1UL << PGDIR_SHIFT) -#define PGDIR_MASK (~(PGDIR_SIZE-1)) /* * This is the lowest virtual address we can permit any user space @@ -138,60 +61,6 @@ extern void __pgd_error(const char *file, int line, pgd_t); */ #define FIRST_USER_ADDRESS PAGE_SIZE -#define USER_PTRS_PER_PGD (TASK_SIZE / PGDIR_SIZE) - -/* - * section address mask and size definitions. - */ -#define SECTION_SHIFT 20 -#define SECTION_SIZE (1UL << SECTION_SHIFT) -#define SECTION_MASK (~(SECTION_SIZE-1)) - -/* - * ARMv6 supersection address mask and size definitions. - */ -#define SUPERSECTION_SHIFT 24 -#define SUPERSECTION_SIZE (1UL << SUPERSECTION_SHIFT) -#define SUPERSECTION_MASK (~(SUPERSECTION_SIZE-1)) - -/* - * "Linux" PTE definitions. - * - * We keep two sets of PTEs - the hardware and the linux version. - * This allows greater flexibility in the way we map the Linux bits - * onto the hardware tables, and allows us to have YOUNG and DIRTY - * bits. - * - * The PTE table pointer refers to the hardware entries; the "Linux" - * entries are stored 1024 bytes below. - */ -#define L_PTE_PRESENT (_AT(pteval_t, 1) << 0) -#define L_PTE_YOUNG (_AT(pteval_t, 1) << 1) -#define L_PTE_FILE (_AT(pteval_t, 1) << 2) /* only when !PRESENT */ -#define L_PTE_DIRTY (_AT(pteval_t, 1) << 6) -#define L_PTE_RDONLY (_AT(pteval_t, 1) << 7) -#define L_PTE_USER (_AT(pteval_t, 1) << 8) -#define L_PTE_XN (_AT(pteval_t, 1) << 9) -#define L_PTE_SHARED (_AT(pteval_t, 1) << 10) /* shared(v6), coherent(xsc3) */ - -/* - * These are the memory types, defined to be compatible with - * pre-ARMv6 CPUs cacheable and bufferable bits: XXCB - */ -#define L_PTE_MT_UNCACHED (_AT(pteval_t, 0x00) << 2) /* 0000 */ -#define L_PTE_MT_BUFFERABLE (_AT(pteval_t, 0x01) << 2) /* 0001 */ -#define L_PTE_MT_WRITETHROUGH (_AT(pteval_t, 0x02) << 2) /* 0010 */ -#define L_PTE_MT_WRITEBACK (_AT(pteval_t, 0x03) << 2) /* 0011 */ -#define L_PTE_MT_MINICACHE (_AT(pteval_t, 0x06) << 2) /* 0110 (sa1100, xscale) */ -#define L_PTE_MT_WRITEALLOC (_AT(pteval_t, 0x07) << 2) /* 0111 */ -#define L_PTE_MT_DEV_SHARED (_AT(pteval_t, 0x04) << 2) /* 0100 */ -#define L_PTE_MT_DEV_NONSHARED (_AT(pteval_t, 0x0c) << 2) /* 1100 */ -#define L_PTE_MT_DEV_WC (_AT(pteval_t, 0x09) << 2) /* 1001 */ -#define L_PTE_MT_DEV_CACHED (_AT(pteval_t, 0x0b) << 2) /* 1011 */ -#define L_PTE_MT_MASK (_AT(pteval_t, 0x0f) << 2) - -#ifndef __ASSEMBLY__ - /* * The pgprot_* and protection_map entries will be fixed up in runtime * to include the cachable and bufferable bits based on memory policy, -- cgit v1.2.3 From 442e70c0b3536e832547eed89629435462f4b515 Mon Sep 17 00:00:00 2001 From: Catalin Marinas Date: Mon, 5 Sep 2011 17:51:56 +0100 Subject: ARM: 7076/1: LPAE: Add (pte|pmd)val_t type definitions as u32 This patch defines the (pte|pmd)val_t as u32 and changes the page table types to be based on these. The PMD bits are converted to the corresponding type using the _AT macro. The flush_pmd_entry/clean_pmd_entry argument was changed to (void *) to allow them to be used with both PGD and PMD pointers and avoid code duplication. Signed-off-by: Catalin Marinas Signed-off-by: Russell King --- arch/arm/include/asm/pgalloc.h | 4 +- arch/arm/include/asm/pgtable-2level-hwdef.h | 82 ++++++++++++++--------------- arch/arm/include/asm/pgtable-2level-types.h | 17 +++--- arch/arm/include/asm/tlbflush.h | 4 +- arch/arm/mm/mm.h | 4 +- arch/arm/mm/mmu.c | 4 +- 6 files changed, 59 insertions(+), 56 deletions(-) (limited to 'arch/arm/include') diff --git a/arch/arm/include/asm/pgalloc.h b/arch/arm/include/asm/pgalloc.h index 22de005f159c..3e08fd3fbb6b 100644 --- a/arch/arm/include/asm/pgalloc.h +++ b/arch/arm/include/asm/pgalloc.h @@ -105,9 +105,9 @@ static inline void pte_free(struct mm_struct *mm, pgtable_t pte) } static inline void __pmd_populate(pmd_t *pmdp, phys_addr_t pte, - unsigned long prot) + pmdval_t prot) { - unsigned long pmdval = (pte + PTE_HWTABLE_OFF) | prot; + pmdval_t pmdval = (pte + PTE_HWTABLE_OFF) | prot; pmdp[0] = __pmd(pmdval); pmdp[1] = __pmd(pmdval + 256 * sizeof(pte_t)); flush_pmd_entry(pmdp); diff --git a/arch/arm/include/asm/pgtable-2level-hwdef.h b/arch/arm/include/asm/pgtable-2level-hwdef.h index 436529c1cda2..2b52c40edd80 100644 --- a/arch/arm/include/asm/pgtable-2level-hwdef.h +++ b/arch/arm/include/asm/pgtable-2level-hwdef.h @@ -16,29 +16,29 @@ * + Level 1 descriptor (PMD) * - common */ -#define PMD_TYPE_MASK (3 << 0) -#define PMD_TYPE_FAULT (0 << 0) -#define PMD_TYPE_TABLE (1 << 0) -#define PMD_TYPE_SECT (2 << 0) -#define PMD_BIT4 (1 << 4) -#define PMD_DOMAIN(x) ((x) << 5) -#define PMD_PROTECTION (1 << 9) /* v5 */ +#define PMD_TYPE_MASK (_AT(pmdval_t, 3) << 0) +#define PMD_TYPE_FAULT (_AT(pmdval_t, 0) << 0) +#define PMD_TYPE_TABLE (_AT(pmdval_t, 1) << 0) +#define PMD_TYPE_SECT (_AT(pmdval_t, 2) << 0) +#define PMD_BIT4 (_AT(pmdval_t, 1) << 4) +#define PMD_DOMAIN(x) (_AT(pmdval_t, (x)) << 5) +#define PMD_PROTECTION (_AT(pmdval_t, 1) << 9) /* v5 */ /* * - section */ -#define PMD_SECT_BUFFERABLE (1 << 2) -#define PMD_SECT_CACHEABLE (1 << 3) -#define PMD_SECT_XN (1 << 4) /* v6 */ -#define PMD_SECT_AP_WRITE (1 << 10) -#define PMD_SECT_AP_READ (1 << 11) -#define PMD_SECT_TEX(x) ((x) << 12) /* v5 */ -#define PMD_SECT_APX (1 << 15) /* v6 */ -#define PMD_SECT_S (1 << 16) /* v6 */ -#define PMD_SECT_nG (1 << 17) /* v6 */ -#define PMD_SECT_SUPER (1 << 18) /* v6 */ -#define PMD_SECT_AF (0) +#define PMD_SECT_BUFFERABLE (_AT(pmdval_t, 1) << 2) +#define PMD_SECT_CACHEABLE (_AT(pmdval_t, 1) << 3) +#define PMD_SECT_XN (_AT(pmdval_t, 1) << 4) /* v6 */ +#define PMD_SECT_AP_WRITE (_AT(pmdval_t, 1) << 10) +#define PMD_SECT_AP_READ (_AT(pmdval_t, 1) << 11) +#define PMD_SECT_TEX(x) (_AT(pmdval_t, (x)) << 12) /* v5 */ +#define PMD_SECT_APX (_AT(pmdval_t, 1) << 15) /* v6 */ +#define PMD_SECT_S (_AT(pmdval_t, 1) << 16) /* v6 */ +#define PMD_SECT_nG (_AT(pmdval_t, 1) << 17) /* v6 */ +#define PMD_SECT_SUPER (_AT(pmdval_t, 1) << 18) /* v6 */ +#define PMD_SECT_AF (_AT(pmdval_t, 0)) -#define PMD_SECT_UNCACHED (0) +#define PMD_SECT_UNCACHED (_AT(pmdval_t, 0)) #define PMD_SECT_BUFFERED (PMD_SECT_BUFFERABLE) #define PMD_SECT_WT (PMD_SECT_CACHEABLE) #define PMD_SECT_WB (PMD_SECT_CACHEABLE | PMD_SECT_BUFFERABLE) @@ -54,38 +54,38 @@ * + Level 2 descriptor (PTE) * - common */ -#define PTE_TYPE_MASK (3 << 0) -#define PTE_TYPE_FAULT (0 << 0) -#define PTE_TYPE_LARGE (1 << 0) -#define PTE_TYPE_SMALL (2 << 0) -#define PTE_TYPE_EXT (3 << 0) /* v5 */ -#define PTE_BUFFERABLE (1 << 2) -#define PTE_CACHEABLE (1 << 3) +#define PTE_TYPE_MASK (_AT(pteval_t, 3) << 0) +#define PTE_TYPE_FAULT (_AT(pteval_t, 0) << 0) +#define PTE_TYPE_LARGE (_AT(pteval_t, 1) << 0) +#define PTE_TYPE_SMALL (_AT(pteval_t, 2) << 0) +#define PTE_TYPE_EXT (_AT(pteval_t, 3) << 0) /* v5 */ +#define PTE_BUFFERABLE (_AT(pteval_t, 1) << 2) +#define PTE_CACHEABLE (_AT(pteval_t, 1) << 3) /* * - extended small page/tiny page */ -#define PTE_EXT_XN (1 << 0) /* v6 */ -#define PTE_EXT_AP_MASK (3 << 4) -#define PTE_EXT_AP0 (1 << 4) -#define PTE_EXT_AP1 (2 << 4) -#define PTE_EXT_AP_UNO_SRO (0 << 4) +#define PTE_EXT_XN (_AT(pteval_t, 1) << 0) /* v6 */ +#define PTE_EXT_AP_MASK (_AT(pteval_t, 3) << 4) +#define PTE_EXT_AP0 (_AT(pteval_t, 1) << 4) +#define PTE_EXT_AP1 (_AT(pteval_t, 2) << 4) +#define PTE_EXT_AP_UNO_SRO (_AT(pteval_t, 0) << 4) #define PTE_EXT_AP_UNO_SRW (PTE_EXT_AP0) #define PTE_EXT_AP_URO_SRW (PTE_EXT_AP1) #define PTE_EXT_AP_URW_SRW (PTE_EXT_AP1|PTE_EXT_AP0) -#define PTE_EXT_TEX(x) ((x) << 6) /* v5 */ -#define PTE_EXT_APX (1 << 9) /* v6 */ -#define PTE_EXT_COHERENT (1 << 9) /* XScale3 */ -#define PTE_EXT_SHARED (1 << 10) /* v6 */ -#define PTE_EXT_NG (1 << 11) /* v6 */ +#define PTE_EXT_TEX(x) (_AT(pteval_t, (x)) << 6) /* v5 */ +#define PTE_EXT_APX (_AT(pteval_t, 1) << 9) /* v6 */ +#define PTE_EXT_COHERENT (_AT(pteval_t, 1) << 9) /* XScale3 */ +#define PTE_EXT_SHARED (_AT(pteval_t, 1) << 10) /* v6 */ +#define PTE_EXT_NG (_AT(pteval_t, 1) << 11) /* v6 */ /* * - small page */ -#define PTE_SMALL_AP_MASK (0xff << 4) -#define PTE_SMALL_AP_UNO_SRO (0x00 << 4) -#define PTE_SMALL_AP_UNO_SRW (0x55 << 4) -#define PTE_SMALL_AP_URO_SRW (0xaa << 4) -#define PTE_SMALL_AP_URW_SRW (0xff << 4) +#define PTE_SMALL_AP_MASK (_AT(pteval_t, 0xff) << 4) +#define PTE_SMALL_AP_UNO_SRO (_AT(pteval_t, 0x00) << 4) +#define PTE_SMALL_AP_UNO_SRW (_AT(pteval_t, 0x55) << 4) +#define PTE_SMALL_AP_URO_SRW (_AT(pteval_t, 0xaa) << 4) +#define PTE_SMALL_AP_URW_SRW (_AT(pteval_t, 0xff) << 4) #endif diff --git a/arch/arm/include/asm/pgtable-2level-types.h b/arch/arm/include/asm/pgtable-2level-types.h index 8a01f62d8a16..66cb5b0e89c5 100644 --- a/arch/arm/include/asm/pgtable-2level-types.h +++ b/arch/arm/include/asm/pgtable-2level-types.h @@ -19,7 +19,10 @@ #ifndef _ASM_PGTABLE_2LEVEL_TYPES_H #define _ASM_PGTABLE_2LEVEL_TYPES_H -typedef unsigned long pteval_t; +#include + +typedef u32 pteval_t; +typedef u32 pmdval_t; #undef STRICT_MM_TYPECHECKS @@ -28,9 +31,9 @@ typedef unsigned long pteval_t; * These are used to make use of C type-checking.. */ typedef struct { pteval_t pte; } pte_t; -typedef struct { unsigned long pmd; } pmd_t; -typedef struct { unsigned long pgd[2]; } pgd_t; -typedef struct { unsigned long pgprot; } pgprot_t; +typedef struct { pmdval_t pmd; } pmd_t; +typedef struct { pmdval_t pgd[2]; } pgd_t; +typedef struct { pteval_t pgprot; } pgprot_t; #define pte_val(x) ((x).pte) #define pmd_val(x) ((x).pmd) @@ -46,9 +49,9 @@ typedef struct { unsigned long pgprot; } pgprot_t; * .. while these make it easier on the compiler */ typedef pteval_t pte_t; -typedef unsigned long pmd_t; -typedef unsigned long pgd_t[2]; -typedef unsigned long pgprot_t; +typedef pmdval_t pmd_t; +typedef pmdval_t pgd_t[2]; +typedef pteval_t pgprot_t; #define pte_val(x) (x) #define pmd_val(x) (x) diff --git a/arch/arm/include/asm/tlbflush.h b/arch/arm/include/asm/tlbflush.h index 8077145698ff..02b2f8203982 100644 --- a/arch/arm/include/asm/tlbflush.h +++ b/arch/arm/include/asm/tlbflush.h @@ -471,7 +471,7 @@ static inline void local_flush_tlb_kernel_page(unsigned long kaddr) * these operations. This is typically used when we are removing * PMD entries. */ -static inline void flush_pmd_entry(pmd_t *pmd) +static inline void flush_pmd_entry(void *pmd) { const unsigned int __tlb_flag = __cpu_tlb_flags; @@ -487,7 +487,7 @@ static inline void flush_pmd_entry(pmd_t *pmd) dsb(); } -static inline void clean_pmd_entry(pmd_t *pmd) +static inline void clean_pmd_entry(void *pmd) { const unsigned int __tlb_flag = __cpu_tlb_flags; diff --git a/arch/arm/mm/mm.h b/arch/arm/mm/mm.h index 010566799c80..ad7cce3bc431 100644 --- a/arch/arm/mm/mm.h +++ b/arch/arm/mm/mm.h @@ -12,8 +12,8 @@ static inline pmd_t *pmd_off_k(unsigned long virt) struct mem_type { pteval_t prot_pte; - unsigned int prot_l1; - unsigned int prot_sect; + pmdval_t prot_l1; + pmdval_t prot_sect; unsigned int domain; }; diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c index 36e983d98315..226f1804be12 100644 --- a/arch/arm/mm/mmu.c +++ b/arch/arm/mm/mmu.c @@ -60,7 +60,7 @@ EXPORT_SYMBOL(pgprot_kernel); struct cachepolicy { const char policy[16]; unsigned int cr_mask; - unsigned int pmd; + pmdval_t pmd; pteval_t pte; }; @@ -288,7 +288,7 @@ static void __init build_mem_type_table(void) { struct cachepolicy *cp; unsigned int cr = get_cr(); - unsigned int user_pgprot, kern_pgprot, vecs_pgprot; + pteval_t user_pgprot, kern_pgprot, vecs_pgprot; int cpu_arch = cpu_architecture(); int i; -- cgit v1.2.3 From d7c5d0dcffb3b5702d9477faceff4b8398e6fed0 Mon Sep 17 00:00:00 2001 From: Catalin Marinas Date: Mon, 5 Sep 2011 17:52:36 +0100 Subject: ARM: 7077/1: LPAE: Use a mask for physical addresses in page table entries With LPAE, the physical address mask is 40-bit while the page table entry is 64-bit. This patch introduces PHYS_MASK for the 2-level page table format, defined as ~0UL. Signed-off-by: Catalin Marinas Signed-off-by: Russell King --- arch/arm/include/asm/pgtable-2level-hwdef.h | 2 ++ arch/arm/include/asm/pgtable.h | 6 +++--- 2 files changed, 5 insertions(+), 3 deletions(-) (limited to 'arch/arm/include') diff --git a/arch/arm/include/asm/pgtable-2level-hwdef.h b/arch/arm/include/asm/pgtable-2level-hwdef.h index 2b52c40edd80..5cfba15cb401 100644 --- a/arch/arm/include/asm/pgtable-2level-hwdef.h +++ b/arch/arm/include/asm/pgtable-2level-hwdef.h @@ -88,4 +88,6 @@ #define PTE_SMALL_AP_URO_SRW (_AT(pteval_t, 0xaa) << 4) #define PTE_SMALL_AP_URW_SRW (_AT(pteval_t, 0xff) << 4) +#define PHYS_MASK (~0UL) + #endif diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h index d6436dacb17b..8ade1840c6f2 100644 --- a/arch/arm/include/asm/pgtable.h +++ b/arch/arm/include/asm/pgtable.h @@ -196,10 +196,10 @@ extern pgd_t swapper_pg_dir[PTRS_PER_PGD]; static inline pte_t *pmd_page_vaddr(pmd_t pmd) { - return __va(pmd_val(pmd) & PAGE_MASK); + return __va(pmd_val(pmd) & PHYS_MASK & (s32)PAGE_MASK); } -#define pmd_page(pmd) pfn_to_page(__phys_to_pfn(pmd_val(pmd))) +#define pmd_page(pmd) pfn_to_page(__phys_to_pfn(pmd_val(pmd) & PHYS_MASK)) /* we don't need complex calculations here as the pmd is folded into the pgd */ #define pmd_addr_end(addr,end) (end) @@ -220,7 +220,7 @@ static inline pte_t *pmd_page_vaddr(pmd_t pmd) #define pte_offset_map(pmd,addr) (__pte_map(pmd) + pte_index(addr)) #define pte_unmap(pte) __pte_unmap(pte) -#define pte_pfn(pte) (pte_val(pte) >> PAGE_SHIFT) +#define pte_pfn(pte) ((pte_val(pte) & PHYS_MASK) >> PAGE_SHIFT) #define pfn_pte(pfn,prot) __pte(__pfn_to_phys(pfn) | pgprot_val(prot)) #define pte_page(pte) pfn_to_page(pte_pfn(pte)) -- cgit v1.2.3 From c9018aab8eee24b993c12c7aff7fc99d3d73f298 Mon Sep 17 00:00:00 2001 From: Vincent Guittot Date: Mon, 8 Aug 2011 13:21:59 +0100 Subject: ARM: 7011/1: Add ARM cpu topology definition The affinity between ARM processors is defined in the MPIDR register. We can identify which processors are in the same cluster, and which ones have performance interdependency. We can define the cpu topology of ARM platform, that is then used by sched_mc and sched_smt. The default state of sched_mc and sched_smt config is disable. When enabled, the behavior of the scheduler can be modified with sched_mc_power_savings and sched_smt_power_savings sysfs interfaces. Changes since v4 : * Remove unnecessary parentheses and blank lines Changes since v3 : * Update the format of printk message * Remove blank line Changes since v2 : * Update the commit message and some comments Changes since v1 : * Update the commit message * Add read_cpuid_mpidr in arch/arm/include/asm/cputype.h * Modify header of arch/arm/kernel/topology.c * Modify tests and manipulation of MPIDR's bitfields * Modify the place and dependancy of the config * Modify Noop functions Signed-off-by: Vincent Guittot Reviewed-by: Amit Kucheria Signed-off-by: Russell King --- arch/arm/Kconfig | 25 +++++++ arch/arm/include/asm/cputype.h | 6 ++ arch/arm/include/asm/topology.h | 33 +++++++++ arch/arm/kernel/Makefile | 1 + arch/arm/kernel/smp.c | 5 ++ arch/arm/kernel/topology.c | 148 ++++++++++++++++++++++++++++++++++++++++ 6 files changed, 218 insertions(+) create mode 100644 arch/arm/kernel/topology.c (limited to 'arch/arm/include') diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 3269576dbfa8..c208fd97c180 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -1393,6 +1393,31 @@ config SMP_ON_UP If you don't know what to do here, say Y. +config ARM_CPU_TOPOLOGY + bool "Support cpu topology definition" + depends on SMP && CPU_V7 + default y + help + Support ARM cpu topology definition. The MPIDR register defines + affinity between processors which is then used to describe the cpu + topology of an ARM System. + +config SCHED_MC + bool "Multi-core scheduler support" + depends on ARM_CPU_TOPOLOGY + help + Multi-core scheduler support improves the CPU scheduler's decision + making when dealing with multi-core CPU chips at a cost of slightly + increased overhead in some places. If unsure say N here. + +config SCHED_SMT + bool "SMT scheduler support" + depends on ARM_CPU_TOPOLOGY + help + Improves the CPU scheduler's decision making when dealing with + MultiThreading at a cost of slightly increased overhead in some + places. If unsure say N here. + config HAVE_ARM_SCU bool help diff --git a/arch/arm/include/asm/cputype.h b/arch/arm/include/asm/cputype.h index cd4458f64171..cb47d28cbe1f 100644 --- a/arch/arm/include/asm/cputype.h +++ b/arch/arm/include/asm/cputype.h @@ -8,6 +8,7 @@ #define CPUID_CACHETYPE 1 #define CPUID_TCM 2 #define CPUID_TLBTYPE 3 +#define CPUID_MPIDR 5 #define CPUID_EXT_PFR0 "c1, 0" #define CPUID_EXT_PFR1 "c1, 1" @@ -70,6 +71,11 @@ static inline unsigned int __attribute_const__ read_cpuid_tcmstatus(void) return read_cpuid(CPUID_TCM); } +static inline unsigned int __attribute_const__ read_cpuid_mpidr(void) +{ + return read_cpuid(CPUID_MPIDR); +} + /* * Intel's XScale3 core supports some v6 features (supersections, L2) * but advertises itself as v5 as it does not support the v6 ISA. For diff --git a/arch/arm/include/asm/topology.h b/arch/arm/include/asm/topology.h index accbd7cad9b5..a7e457ed27c3 100644 --- a/arch/arm/include/asm/topology.h +++ b/arch/arm/include/asm/topology.h @@ -1,6 +1,39 @@ #ifndef _ASM_ARM_TOPOLOGY_H #define _ASM_ARM_TOPOLOGY_H +#ifdef CONFIG_ARM_CPU_TOPOLOGY + +#include + +struct cputopo_arm { + int thread_id; + int core_id; + int socket_id; + cpumask_t thread_sibling; + cpumask_t core_sibling; +}; + +extern struct cputopo_arm cpu_topology[NR_CPUS]; + +#define topology_physical_package_id(cpu) (cpu_topology[cpu].socket_id) +#define topology_core_id(cpu) (cpu_topology[cpu].core_id) +#define topology_core_cpumask(cpu) (&cpu_topology[cpu].core_sibling) +#define topology_thread_cpumask(cpu) (&cpu_topology[cpu].thread_sibling) + +#define mc_capable() (cpu_topology[0].socket_id != -1) +#define smt_capable() (cpu_topology[0].thread_id != -1) + +void init_cpu_topology(void); +void store_cpu_topology(unsigned int cpuid); +const struct cpumask *cpu_coregroup_mask(unsigned int cpu); + +#else + +static inline void init_cpu_topology(void) { } +static inline void store_cpu_topology(unsigned int cpuid) { } + +#endif + #include #endif /* _ASM_ARM_TOPOLOGY_H */ diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile index f7887dc53c1f..c687bceba7da 100644 --- a/arch/arm/kernel/Makefile +++ b/arch/arm/kernel/Makefile @@ -66,6 +66,7 @@ obj-$(CONFIG_IWMMXT) += iwmmxt.o obj-$(CONFIG_CPU_HAS_PMU) += pmu.o obj-$(CONFIG_HW_PERF_EVENTS) += perf_event.o AFLAGS_iwmmxt.o := -Wa,-mcpu=iwmmxt +obj-$(CONFIG_ARM_CPU_TOPOLOGY) += topology.o ifneq ($(CONFIG_ARCH_EBSA110),y) obj-y += io.o diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c index d88ff0230e82..62775c5c5ba0 100644 --- a/arch/arm/kernel/smp.c +++ b/arch/arm/kernel/smp.c @@ -31,6 +31,7 @@ #include #include #include +#include #include #include #include @@ -268,6 +269,8 @@ static void __cpuinit smp_store_cpu_info(unsigned int cpuid) struct cpuinfo_arm *cpu_info = &per_cpu(cpu_data, cpuid); cpu_info->loops_per_jiffy = loops_per_jiffy; + + store_cpu_topology(cpuid); } /* @@ -358,6 +361,8 @@ void __init smp_prepare_cpus(unsigned int max_cpus) { unsigned int ncores = num_possible_cpus(); + init_cpu_topology(); + smp_store_cpu_info(smp_processor_id()); /* diff --git a/arch/arm/kernel/topology.c b/arch/arm/kernel/topology.c new file mode 100644 index 000000000000..1040c00405d0 --- /dev/null +++ b/arch/arm/kernel/topology.c @@ -0,0 +1,148 @@ +/* + * arch/arm/kernel/topology.c + * + * Copyright (C) 2011 Linaro Limited. + * Written by: Vincent Guittot + * + * based on arch/sh/kernel/topology.c + * + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file "COPYING" in the main directory of this archive + * for more details. + */ + +#include +#include +#include +#include +#include +#include +#include + +#include +#include + +#define MPIDR_SMP_BITMASK (0x3 << 30) +#define MPIDR_SMP_VALUE (0x2 << 30) + +#define MPIDR_MT_BITMASK (0x1 << 24) + +/* + * These masks reflect the current use of the affinity levels. + * The affinity level can be up to 16 bits according to ARM ARM + */ + +#define MPIDR_LEVEL0_MASK 0x3 +#define MPIDR_LEVEL0_SHIFT 0 + +#define MPIDR_LEVEL1_MASK 0xF +#define MPIDR_LEVEL1_SHIFT 8 + +#define MPIDR_LEVEL2_MASK 0xFF +#define MPIDR_LEVEL2_SHIFT 16 + +struct cputopo_arm cpu_topology[NR_CPUS]; + +const struct cpumask *cpu_coregroup_mask(unsigned int cpu) +{ + return &cpu_topology[cpu].core_sibling; +} + +/* + * store_cpu_topology is called at boot when only one cpu is running + * and with the mutex cpu_hotplug.lock locked, when several cpus have booted, + * which prevents simultaneous write access to cpu_topology array + */ +void store_cpu_topology(unsigned int cpuid) +{ + struct cputopo_arm *cpuid_topo = &cpu_topology[cpuid]; + unsigned int mpidr; + unsigned int cpu; + + /* If the cpu topology has been already set, just return */ + if (cpuid_topo->core_id != -1) + return; + + mpidr = read_cpuid_mpidr(); + + /* create cpu topology mapping */ + if ((mpidr & MPIDR_SMP_BITMASK) == MPIDR_SMP_VALUE) { + /* + * This is a multiprocessor system + * multiprocessor format & multiprocessor mode field are set + */ + + if (mpidr & MPIDR_MT_BITMASK) { + /* core performance interdependency */ + cpuid_topo->thread_id = (mpidr >> MPIDR_LEVEL0_SHIFT) + & MPIDR_LEVEL0_MASK; + cpuid_topo->core_id = (mpidr >> MPIDR_LEVEL1_SHIFT) + & MPIDR_LEVEL1_MASK; + cpuid_topo->socket_id = (mpidr >> MPIDR_LEVEL2_SHIFT) + & MPIDR_LEVEL2_MASK; + } else { + /* largely independent cores */ + cpuid_topo->thread_id = -1; + cpuid_topo->core_id = (mpidr >> MPIDR_LEVEL0_SHIFT) + & MPIDR_LEVEL0_MASK; + cpuid_topo->socket_id = (mpidr >> MPIDR_LEVEL1_SHIFT) + & MPIDR_LEVEL1_MASK; + } + } else { + /* + * This is an uniprocessor system + * we are in multiprocessor format but uniprocessor system + * or in the old uniprocessor format + */ + cpuid_topo->thread_id = -1; + cpuid_topo->core_id = 0; + cpuid_topo->socket_id = -1; + } + + /* update core and thread sibling masks */ + for_each_possible_cpu(cpu) { + struct cputopo_arm *cpu_topo = &cpu_topology[cpu]; + + if (cpuid_topo->socket_id == cpu_topo->socket_id) { + cpumask_set_cpu(cpuid, &cpu_topo->core_sibling); + if (cpu != cpuid) + cpumask_set_cpu(cpu, + &cpuid_topo->core_sibling); + + if (cpuid_topo->core_id == cpu_topo->core_id) { + cpumask_set_cpu(cpuid, + &cpu_topo->thread_sibling); + if (cpu != cpuid) + cpumask_set_cpu(cpu, + &cpuid_topo->thread_sibling); + } + } + } + smp_wmb(); + + printk(KERN_INFO "CPU%u: thread %d, cpu %d, socket %d, mpidr %x\n", + cpuid, cpu_topology[cpuid].thread_id, + cpu_topology[cpuid].core_id, + cpu_topology[cpuid].socket_id, mpidr); +} + +/* + * init_cpu_topology is called at boot when only one cpu is running + * which prevent simultaneous write access to cpu_topology array + */ +void init_cpu_topology(void) +{ + unsigned int cpu; + + /* init core mask */ + for_each_possible_cpu(cpu) { + struct cputopo_arm *cpu_topo = &(cpu_topology[cpu]); + + cpu_topo->thread_id = -1; + cpu_topo->core_id = -1; + cpu_topo->socket_id = -1; + cpumask_clear(&cpu_topo->core_sibling); + cpumask_clear(&cpu_topo->thread_sibling); + } + smp_wmb(); +} -- cgit v1.2.3 From d6257288c4052465feeff7e283e35ec0ed06ca03 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Tue, 23 Aug 2011 22:19:29 +0100 Subject: ARM: 7060/1: smp: populate logical CPU mapping during boot To allow booting Linux on a CPU with physical ID != 0, we need to provide a mapping from the logical CPU number to the physical CPU number. This patch adds such a mapping and populates it during boot. Signed-off-by: Will Deacon Signed-off-by: Russell King --- arch/arm/include/asm/smp.h | 6 ++++++ arch/arm/kernel/smp.c | 15 +++++++++++++++ 2 files changed, 21 insertions(+) (limited to 'arch/arm/include') diff --git a/arch/arm/include/asm/smp.h b/arch/arm/include/asm/smp.h index e42d96a45d3e..674ebcd337fe 100644 --- a/arch/arm/include/asm/smp.h +++ b/arch/arm/include/asm/smp.h @@ -65,6 +65,12 @@ extern void platform_secondary_init(unsigned int cpu); */ extern void platform_smp_prepare_cpus(unsigned int); +/* + * Logical CPU mapping. + */ +extern int __cpu_logical_map[NR_CPUS]; +#define cpu_logical_map(cpu) __cpu_logical_map[cpu] + /* * Initial data for bringing up a secondary CPU. */ diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c index 62775c5c5ba0..3f12ce9b0796 100644 --- a/arch/arm/kernel/smp.c +++ b/arch/arm/kernel/smp.c @@ -40,6 +40,7 @@ #include #include #include +#include /* * as from 2.5, kernels no longer have an init_tasks structure @@ -260,6 +261,20 @@ void __ref cpu_die(void) } #endif /* CONFIG_HOTPLUG_CPU */ +int __cpu_logical_map[NR_CPUS]; + +void __init smp_setup_processor_id(void) +{ + int i; + u32 cpu = is_smp() ? read_cpuid_mpidr() & 0xff : 0; + + cpu_logical_map(0) = cpu; + for (i = 1; i < NR_CPUS; ++i) + cpu_logical_map(i) = i == cpu ? 0 : i; + + printk(KERN_INFO "Booting Linux on physical CPU %d\n", cpu); +} + /* * Called by both boot and secondaries to move global data into * per-processor storage. -- cgit v1.2.3 From 0b5a1b95dcdfa451125132d5ce3f79a27ffb0950 Mon Sep 17 00:00:00 2001 From: Shawn Guo Date: Thu, 6 Oct 2011 15:18:14 +0100 Subject: ARM: 7123/1: smp: Add an IPI handler callable from C code In order to be able to handle IPI directly from C code instead of assembly code, introduce handle_IPI(), which is modeled after handle_IRQ(). Signed-off-by: Marc Zyngier Signed-off-by: Russell King --- arch/arm/include/asm/smp.h | 5 +++++ arch/arm/kernel/smp.c | 5 +++++ 2 files changed, 10 insertions(+) (limited to 'arch/arm/include') diff --git a/arch/arm/include/asm/smp.h b/arch/arm/include/asm/smp.h index 674ebcd337fe..0a17b62538c2 100644 --- a/arch/arm/include/asm/smp.h +++ b/arch/arm/include/asm/smp.h @@ -32,6 +32,11 @@ extern void show_ipi_list(struct seq_file *, int); */ asmlinkage void do_IPI(int ipinr, struct pt_regs *regs); +/* + * Called from C code, this handles an IPI. + */ +void handle_IPI(int ipinr, struct pt_regs *regs); + /* * Setup the set of possible CPUs (via set_cpu_possible) */ diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c index 3f12ce9b0796..2e49f1883fe9 100644 --- a/arch/arm/kernel/smp.c +++ b/arch/arm/kernel/smp.c @@ -586,6 +586,11 @@ static void ipi_cpu_stop(unsigned int cpu) * Main handler for inter-processor interrupts */ asmlinkage void __exception_irq_entry do_IPI(int ipinr, struct pt_regs *regs) +{ + handle_IPI(ipinr, regs); +} + +void handle_IPI(int ipinr, struct pt_regs *regs) { unsigned int cpu = smp_processor_id(); struct pt_regs *old_regs = set_irq_regs(regs); -- cgit v1.2.3 From 0af8aa0069e43f90d59666510342c05e97d8c4b8 Mon Sep 17 00:00:00 2001 From: Shawn Guo Date: Thu, 6 Oct 2011 15:19:14 +0100 Subject: ARM: 7124/1: smp: Add a localtimer handler callable from C code In order to be able to handle localtimer directly from C code instead of assembly code, introduce handle_local_timer(), which is modeled after handle_IRQ(). Signed-off-by: Shawn Guo Signed-off-by: Russell King --- arch/arm/include/asm/localtimer.h | 4 ++++ arch/arm/kernel/smp.c | 5 +++++ 2 files changed, 9 insertions(+) (limited to 'arch/arm/include') diff --git a/arch/arm/include/asm/localtimer.h b/arch/arm/include/asm/localtimer.h index 080d74f8128d..3306f281333c 100644 --- a/arch/arm/include/asm/localtimer.h +++ b/arch/arm/include/asm/localtimer.h @@ -22,6 +22,10 @@ void percpu_timer_setup(void); */ asmlinkage void do_local_timer(struct pt_regs *); +/* + * Called from C code + */ +void handle_local_timer(struct pt_regs *); #ifdef CONFIG_LOCAL_TIMERS diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c index 2e49f1883fe9..0949007d09a8 100644 --- a/arch/arm/kernel/smp.c +++ b/arch/arm/kernel/smp.c @@ -479,6 +479,11 @@ static void ipi_timer(void) #ifdef CONFIG_LOCAL_TIMERS asmlinkage void __exception_irq_entry do_local_timer(struct pt_regs *regs) +{ + handle_local_timer(regs); +} + +void handle_local_timer(struct pt_regs *regs) { struct pt_regs *old_regs = set_irq_regs(regs); int cpu = smp_processor_id(); -- cgit v1.2.3 From 5a567d78c437e3be1c512734cdfe64b4ae6b82d7 Mon Sep 17 00:00:00 2001 From: Jamie Iles Date: Sat, 8 Oct 2011 11:20:42 +0100 Subject: ARM: 7115/4: move __exception and friends to asm/exception.h The definition of __exception_irq_entry for CONFIG_FUNCTION_GRAPH_TRACER=y needs linux/ftrace.h, but this creates a circular dependency with it's current home in asm/system.h. Create asm/exception.h and update all current users. v4: - rebase to rmk/for-next v3: - remove redundant includes of linux/ftrace.h v2: - document the usage restricitions of __exception* Cc: Zoltan Devai Signed-off-by: Jamie Iles Signed-off-by: Russell King --- arch/arm/include/asm/exception.h | 19 +++++++++++++++++++ arch/arm/include/asm/system.h | 7 ------- arch/arm/kernel/irq.c | 2 +- arch/arm/kernel/smp.c | 2 +- arch/arm/kernel/traps.c | 1 + arch/arm/mach-pxa/irq.c | 2 ++ arch/arm/mm/fault.c | 1 + 7 files changed, 25 insertions(+), 9 deletions(-) create mode 100644 arch/arm/include/asm/exception.h (limited to 'arch/arm/include') diff --git a/arch/arm/include/asm/exception.h b/arch/arm/include/asm/exception.h new file mode 100644 index 000000000000..5abaf5bbd985 --- /dev/null +++ b/arch/arm/include/asm/exception.h @@ -0,0 +1,19 @@ +/* + * Annotations for marking C functions as exception handlers. + * + * These should only be used for C functions that are called from the low + * level exception entry code and not any intervening C code. + */ +#ifndef __ASM_ARM_EXCEPTION_H +#define __ASM_ARM_EXCEPTION_H + +#include + +#define __exception __attribute__((section(".exception.text"))) +#ifdef CONFIG_FUNCTION_GRAPH_TRACER +#define __exception_irq_entry __irq_entry +#else +#define __exception_irq_entry __exception +#endif + +#endif /* __ASM_ARM_EXCEPTION_H */ diff --git a/arch/arm/include/asm/system.h b/arch/arm/include/asm/system.h index 832888d0c20c..ed6b0499a106 100644 --- a/arch/arm/include/asm/system.h +++ b/arch/arm/include/asm/system.h @@ -62,13 +62,6 @@ #include -#define __exception __attribute__((section(".exception.text"))) -#ifdef CONFIG_FUNCTION_GRAPH_TRACER -#define __exception_irq_entry __irq_entry -#else -#define __exception_irq_entry __exception -#endif - struct thread_info; struct task_struct; diff --git a/arch/arm/kernel/irq.c b/arch/arm/kernel/irq.c index de3dcab8610b..53919b230e8b 100644 --- a/arch/arm/kernel/irq.c +++ b/arch/arm/kernel/irq.c @@ -35,8 +35,8 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c index 0949007d09a8..35417d0fb8ab 100644 --- a/arch/arm/kernel/smp.c +++ b/arch/arm/kernel/smp.c @@ -16,7 +16,6 @@ #include #include #include -#include #include #include #include @@ -31,6 +30,7 @@ #include #include #include +#include #include #include #include diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c index bc9f9da782cb..210382555af1 100644 --- a/arch/arm/kernel/traps.c +++ b/arch/arm/kernel/traps.c @@ -27,6 +27,7 @@ #include #include +#include #include #include #include diff --git a/arch/arm/mach-pxa/irq.c b/arch/arm/mach-pxa/irq.c index b09e848eb6c6..ca6075717824 100644 --- a/arch/arm/mach-pxa/irq.c +++ b/arch/arm/mach-pxa/irq.c @@ -19,6 +19,8 @@ #include #include +#include + #include #include #include diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c index 3b5ea68acbb8..aa33949fef60 100644 --- a/arch/arm/mm/fault.c +++ b/arch/arm/mm/fault.c @@ -20,6 +20,7 @@ #include #include +#include #include #include #include -- cgit v1.2.3 From 8c369264b6de3b2ab796f330a4d85770a6b8b033 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Wed, 3 Aug 2011 18:12:05 +0100 Subject: ARM: 7009/1: l2x0: Add OF based initialization This adds probing for ARM L2x0 cache controllers via device tree. Support includes the L210, L220, and PL310 controllers. The binding allows setting up cache RAM latencies and filter addresses (PL310 only). Signed-off-by: Rob Herring Acked-by: Grant Likely Acked-by: Arnd Bergmann Acked-by: Olof Johansson Acked-by: Barry Song <21cnbao@gmail.com> Signed-off-by: Russell King --- Documentation/devicetree/bindings/arm/l2cc.txt | 42 ++++++++++ arch/arm/include/asm/hardware/cache-l2x0.h | 17 ++++ arch/arm/mm/cache-l2x0.c | 103 +++++++++++++++++++++++++ 3 files changed, 162 insertions(+) create mode 100644 Documentation/devicetree/bindings/arm/l2cc.txt (limited to 'arch/arm/include') diff --git a/Documentation/devicetree/bindings/arm/l2cc.txt b/Documentation/devicetree/bindings/arm/l2cc.txt new file mode 100644 index 000000000000..f50e021a0998 --- /dev/null +++ b/Documentation/devicetree/bindings/arm/l2cc.txt @@ -0,0 +1,42 @@ +* ARM L2 Cache Controller + +ARM cores often have a separate level 2 cache controller. There are various +implementations of the L2 cache controller with compatible programming models. +The ARM L2 cache representation in the device tree should be done as follows: + +Required properties: + +- compatible : should be one of: + "arm,pl310-cache" + "arm,l220-cache" + "arm,l210-cache" +- cache-unified : Specifies the cache is a unified cache. +- cache-level : Should be set to 2 for a level 2 cache. +- reg : Physical base address and size of cache controller's memory mapped + registers. + +Optional properties: + +- arm,data-latency : Cycles of latency for Data RAM accesses. Specifies 3 cells of + read, write and setup latencies. Minimum valid values are 1. Controllers + without setup latency control should use a value of 0. +- arm,tag-latency : Cycles of latency for Tag RAM accesses. Specifies 3 cells of + read, write and setup latencies. Controllers without setup latency control + should use 0. Controllers without separate read and write Tag RAM latency + values should only use the first cell. +- arm,dirty-latency : Cycles of latency for Dirty RAMs. This is a single cell. +- arm,filter-ranges : Starting address and length of window to + filter. Addresses in the filter window are directed to the M1 port. Other + addresses will go to the M0 port. + +Example: + +L2: cache-controller { + compatible = "arm,pl310-cache"; + reg = <0xfff12000 0x1000>; + arm,data-latency = <1 1 1>; + arm,tag-latency = <2 2 2>; + arm,filter-latency = <0x80000000 0x8000000>; + cache-unified; + cache-level = <2>; +}; diff --git a/arch/arm/include/asm/hardware/cache-l2x0.h b/arch/arm/include/asm/hardware/cache-l2x0.h index 99a6ed7e1bfd..c48cb1e1c46c 100644 --- a/arch/arm/include/asm/hardware/cache-l2x0.h +++ b/arch/arm/include/asm/hardware/cache-l2x0.h @@ -52,6 +52,8 @@ #define L2X0_LOCKDOWN_WAY_D_BASE 0x900 #define L2X0_LOCKDOWN_WAY_I_BASE 0x904 #define L2X0_LOCKDOWN_STRIDE 0x08 +#define L2X0_ADDR_FILTER_START 0xC00 +#define L2X0_ADDR_FILTER_END 0xC04 #define L2X0_TEST_OPERATION 0xF00 #define L2X0_LINE_DATA 0xF10 #define L2X0_LINE_TAG 0xF30 @@ -67,6 +69,14 @@ #define L2X0_CACHE_ID_PART_L310 (3 << 6) #define L2X0_AUX_CTRL_MASK 0xc0000fff +#define L2X0_AUX_CTRL_DATA_RD_LATENCY_SHIFT 0 +#define L2X0_AUX_CTRL_DATA_RD_LATENCY_MASK 0x7 +#define L2X0_AUX_CTRL_DATA_WR_LATENCY_SHIFT 3 +#define L2X0_AUX_CTRL_DATA_WR_LATENCY_MASK (0x7 << 3) +#define L2X0_AUX_CTRL_TAG_LATENCY_SHIFT 6 +#define L2X0_AUX_CTRL_TAG_LATENCY_MASK (0x7 << 6) +#define L2X0_AUX_CTRL_DIRTY_LATENCY_SHIFT 9 +#define L2X0_AUX_CTRL_DIRTY_LATENCY_MASK (0x7 << 9) #define L2X0_AUX_CTRL_ASSOCIATIVITY_SHIFT 16 #define L2X0_AUX_CTRL_WAY_SIZE_SHIFT 17 #define L2X0_AUX_CTRL_WAY_SIZE_MASK (0x7 << 17) @@ -77,8 +87,15 @@ #define L2X0_AUX_CTRL_INSTR_PREFETCH_SHIFT 29 #define L2X0_AUX_CTRL_EARLY_BRESP_SHIFT 30 +#define L2X0_LATENCY_CTRL_SETUP_SHIFT 0 +#define L2X0_LATENCY_CTRL_RD_SHIFT 4 +#define L2X0_LATENCY_CTRL_WR_SHIFT 8 + +#define L2X0_ADDR_FILTER_EN 1 + #ifndef __ASSEMBLY__ extern void __init l2x0_init(void __iomem *base, __u32 aux_val, __u32 aux_mask); +extern int l2x0_of_init(__u32 aux_val, __u32 aux_mask); #endif #endif diff --git a/arch/arm/mm/cache-l2x0.c b/arch/arm/mm/cache-l2x0.c index 9ecfdb511951..db4484f5bf98 100644 --- a/arch/arm/mm/cache-l2x0.c +++ b/arch/arm/mm/cache-l2x0.c @@ -16,9 +16,12 @@ * along with this program; if not, write to the Free Software * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ +#include #include #include #include +#include +#include #include #include @@ -372,3 +375,103 @@ void __init l2x0_init(void __iomem *base, __u32 aux_val, __u32 aux_mask) printk(KERN_INFO "l2x0: %d ways, CACHE_ID 0x%08x, AUX_CTRL 0x%08x, Cache size: %d B\n", ways, cache_id, aux, l2x0_size); } + +#ifdef CONFIG_OF +static void __init l2x0_of_setup(const struct device_node *np, + __u32 *aux_val, __u32 *aux_mask) +{ + u32 data[2] = { 0, 0 }; + u32 tag = 0; + u32 dirty = 0; + u32 val = 0, mask = 0; + + of_property_read_u32(np, "arm,tag-latency", &tag); + if (tag) { + mask |= L2X0_AUX_CTRL_TAG_LATENCY_MASK; + val |= (tag - 1) << L2X0_AUX_CTRL_TAG_LATENCY_SHIFT; + } + + of_property_read_u32_array(np, "arm,data-latency", + data, ARRAY_SIZE(data)); + if (data[0] && data[1]) { + mask |= L2X0_AUX_CTRL_DATA_RD_LATENCY_MASK | + L2X0_AUX_CTRL_DATA_WR_LATENCY_MASK; + val |= ((data[0] - 1) << L2X0_AUX_CTRL_DATA_RD_LATENCY_SHIFT) | + ((data[1] - 1) << L2X0_AUX_CTRL_DATA_WR_LATENCY_SHIFT); + } + + of_property_read_u32(np, "arm,dirty-latency", &dirty); + if (dirty) { + mask |= L2X0_AUX_CTRL_DIRTY_LATENCY_MASK; + val |= (dirty - 1) << L2X0_AUX_CTRL_DIRTY_LATENCY_SHIFT; + } + + *aux_val &= ~mask; + *aux_val |= val; + *aux_mask &= ~mask; +} + +static void __init pl310_of_setup(const struct device_node *np, + __u32 *aux_val, __u32 *aux_mask) +{ + u32 data[3] = { 0, 0, 0 }; + u32 tag[3] = { 0, 0, 0 }; + u32 filter[2] = { 0, 0 }; + + of_property_read_u32_array(np, "arm,tag-latency", tag, ARRAY_SIZE(tag)); + if (tag[0] && tag[1] && tag[2]) + writel_relaxed( + ((tag[0] - 1) << L2X0_LATENCY_CTRL_RD_SHIFT) | + ((tag[1] - 1) << L2X0_LATENCY_CTRL_WR_SHIFT) | + ((tag[2] - 1) << L2X0_LATENCY_CTRL_SETUP_SHIFT), + l2x0_base + L2X0_TAG_LATENCY_CTRL); + + of_property_read_u32_array(np, "arm,data-latency", + data, ARRAY_SIZE(data)); + if (data[0] && data[1] && data[2]) + writel_relaxed( + ((data[0] - 1) << L2X0_LATENCY_CTRL_RD_SHIFT) | + ((data[1] - 1) << L2X0_LATENCY_CTRL_WR_SHIFT) | + ((data[2] - 1) << L2X0_LATENCY_CTRL_SETUP_SHIFT), + l2x0_base + L2X0_DATA_LATENCY_CTRL); + + of_property_read_u32_array(np, "arm,filter-ranges", + filter, ARRAY_SIZE(filter)); + if (filter[0] && filter[1]) { + writel_relaxed(ALIGN(filter[0] + filter[1], SZ_1M), + l2x0_base + L2X0_ADDR_FILTER_END); + writel_relaxed((filter[0] & ~(SZ_1M - 1)) | L2X0_ADDR_FILTER_EN, + l2x0_base + L2X0_ADDR_FILTER_START); + } +} + +static const struct of_device_id l2x0_ids[] __initconst = { + { .compatible = "arm,pl310-cache", .data = pl310_of_setup }, + { .compatible = "arm,l220-cache", .data = l2x0_of_setup }, + { .compatible = "arm,l210-cache", .data = l2x0_of_setup }, + {} +}; + +int __init l2x0_of_init(__u32 aux_val, __u32 aux_mask) +{ + struct device_node *np; + void (*l2_setup)(const struct device_node *np, + __u32 *aux_val, __u32 *aux_mask); + + np = of_find_matching_node(NULL, l2x0_ids); + if (!np) + return -ENODEV; + l2x0_base = of_iomap(np, 0); + if (!l2x0_base) + return -ENOMEM; + + /* L2 configuration can only be changed if the cache is disabled */ + if (!(readl_relaxed(l2x0_base + L2X0_CTRL) & 1)) { + l2_setup = of_match_node(l2x0_ids, np)->data; + if (l2_setup) + l2_setup(np, &aux_val, &aux_mask); + } + l2x0_init(l2x0_base, aux_val, aux_mask); + return 0; +} +#endif -- cgit v1.2.3 From 91c2ebb90b1890abc648ba9dec5608cbc97e1cb9 Mon Sep 17 00:00:00 2001 From: Barry Song Date: Fri, 30 Sep 2011 14:43:12 +0100 Subject: ARM: 7114/1: cache-l2x0: add resume entry for l2 in secure mode we save the l2x0 registers at the first initialization, and platform codes can get them to restore l2x0 status after wakeup. Cc: Lorenzo Pieralisi Signed-off-by: Barry Song Reviewed-by: Santosh Shilimkar Tested-by: Shawn Guo Signed-off-by: Russell King --- arch/arm/include/asm/hardware/cache-l2x0.h | 25 ++++++ arch/arm/include/asm/outercache.h | 7 ++ arch/arm/kernel/asm-offsets.c | 12 +++ arch/arm/mm/cache-l2x0.c | 129 ++++++++++++++++++++++++++--- 4 files changed, 163 insertions(+), 10 deletions(-) (limited to 'arch/arm/include') diff --git a/arch/arm/include/asm/hardware/cache-l2x0.h b/arch/arm/include/asm/hardware/cache-l2x0.h index c48cb1e1c46c..434edccdf7f3 100644 --- a/arch/arm/include/asm/hardware/cache-l2x0.h +++ b/arch/arm/include/asm/hardware/cache-l2x0.h @@ -67,6 +67,13 @@ #define L2X0_CACHE_ID_PART_MASK (0xf << 6) #define L2X0_CACHE_ID_PART_L210 (1 << 6) #define L2X0_CACHE_ID_PART_L310 (3 << 6) +#define L2X0_CACHE_ID_RTL_MASK 0x3f +#define L2X0_CACHE_ID_RTL_R0P0 0x0 +#define L2X0_CACHE_ID_RTL_R1P0 0x2 +#define L2X0_CACHE_ID_RTL_R2P0 0x4 +#define L2X0_CACHE_ID_RTL_R3P0 0x5 +#define L2X0_CACHE_ID_RTL_R3P1 0x6 +#define L2X0_CACHE_ID_RTL_R3P2 0x8 #define L2X0_AUX_CTRL_MASK 0xc0000fff #define L2X0_AUX_CTRL_DATA_RD_LATENCY_SHIFT 0 @@ -96,6 +103,24 @@ #ifndef __ASSEMBLY__ extern void __init l2x0_init(void __iomem *base, __u32 aux_val, __u32 aux_mask); extern int l2x0_of_init(__u32 aux_val, __u32 aux_mask); + +struct l2x0_regs { + unsigned long phy_base; + unsigned long aux_ctrl; + /* + * Whether the following registers need to be saved/restored + * depends on platform + */ + unsigned long tag_latency; + unsigned long data_latency; + unsigned long filter_start; + unsigned long filter_end; + unsigned long prefetch_ctrl; + unsigned long pwr_ctrl; +}; + +extern struct l2x0_regs l2x0_saved_regs; + #endif #endif diff --git a/arch/arm/include/asm/outercache.h b/arch/arm/include/asm/outercache.h index d8387437ec5a..53426c66352a 100644 --- a/arch/arm/include/asm/outercache.h +++ b/arch/arm/include/asm/outercache.h @@ -34,6 +34,7 @@ struct outer_cache_fns { void (*sync)(void); #endif void (*set_debug)(unsigned long); + void (*resume)(void); }; #ifdef CONFIG_OUTER_CACHE @@ -74,6 +75,12 @@ static inline void outer_disable(void) outer_cache.disable(); } +static inline void outer_resume(void) +{ + if (outer_cache.resume) + outer_cache.resume(); +} + #else static inline void outer_inv_range(phys_addr_t start, phys_addr_t end) diff --git a/arch/arm/kernel/asm-offsets.c b/arch/arm/kernel/asm-offsets.c index 16baba2e4369..1429d8989fb9 100644 --- a/arch/arm/kernel/asm-offsets.c +++ b/arch/arm/kernel/asm-offsets.c @@ -20,6 +20,7 @@ #include #include #include +#include #include /* @@ -92,6 +93,17 @@ int main(void) DEFINE(S_OLD_R0, offsetof(struct pt_regs, ARM_ORIG_r0)); DEFINE(S_FRAME_SIZE, sizeof(struct pt_regs)); BLANK(); +#ifdef CONFIG_CACHE_L2X0 + DEFINE(L2X0_R_PHY_BASE, offsetof(struct l2x0_regs, phy_base)); + DEFINE(L2X0_R_AUX_CTRL, offsetof(struct l2x0_regs, aux_ctrl)); + DEFINE(L2X0_R_TAG_LATENCY, offsetof(struct l2x0_regs, tag_latency)); + DEFINE(L2X0_R_DATA_LATENCY, offsetof(struct l2x0_regs, data_latency)); + DEFINE(L2X0_R_FILTER_START, offsetof(struct l2x0_regs, filter_start)); + DEFINE(L2X0_R_FILTER_END, offsetof(struct l2x0_regs, filter_end)); + DEFINE(L2X0_R_PREFETCH_CTRL, offsetof(struct l2x0_regs, prefetch_ctrl)); + DEFINE(L2X0_R_PWR_CTRL, offsetof(struct l2x0_regs, pwr_ctrl)); + BLANK(); +#endif #ifdef CONFIG_CPU_HAS_ASID DEFINE(MM_CONTEXT_ID, offsetof(struct mm_struct, context.id)); BLANK(); diff --git a/arch/arm/mm/cache-l2x0.c b/arch/arm/mm/cache-l2x0.c index 0d85d221d7b0..3f9b9980478e 100644 --- a/arch/arm/mm/cache-l2x0.c +++ b/arch/arm/mm/cache-l2x0.c @@ -33,6 +33,14 @@ static DEFINE_SPINLOCK(l2x0_lock); static uint32_t l2x0_way_mask; /* Bitmask of active ways */ static uint32_t l2x0_size; +struct l2x0_regs l2x0_saved_regs; + +struct l2x0_of_data { + void (*setup)(const struct device_node *, __u32 *, __u32 *); + void (*save)(void); + void (*resume)(void); +}; + static inline void cache_wait_way(void __iomem *reg, unsigned long mask) { /* wait for cache operation by line or way to complete */ @@ -280,7 +288,7 @@ static void l2x0_disable(void) spin_unlock_irqrestore(&l2x0_lock, flags); } -static void __init l2x0_unlock(__u32 cache_id) +static void l2x0_unlock(__u32 cache_id) { int lockregs; int i; @@ -356,6 +364,8 @@ void __init l2x0_init(void __iomem *base, __u32 aux_val, __u32 aux_mask) /* l2x0 controller is disabled */ writel_relaxed(aux, l2x0_base + L2X0_AUX_CTRL); + l2x0_saved_regs.aux_ctrl = aux; + l2x0_inv_all(); /* enable L2X0 */ @@ -445,33 +455,132 @@ static void __init pl310_of_setup(const struct device_node *np, } } +static void __init pl310_save(void) +{ + u32 l2x0_revision = readl_relaxed(l2x0_base + L2X0_CACHE_ID) & + L2X0_CACHE_ID_RTL_MASK; + + l2x0_saved_regs.tag_latency = readl_relaxed(l2x0_base + + L2X0_TAG_LATENCY_CTRL); + l2x0_saved_regs.data_latency = readl_relaxed(l2x0_base + + L2X0_DATA_LATENCY_CTRL); + l2x0_saved_regs.filter_end = readl_relaxed(l2x0_base + + L2X0_ADDR_FILTER_END); + l2x0_saved_regs.filter_start = readl_relaxed(l2x0_base + + L2X0_ADDR_FILTER_START); + + if (l2x0_revision >= L2X0_CACHE_ID_RTL_R2P0) { + /* + * From r2p0, there is Prefetch offset/control register + */ + l2x0_saved_regs.prefetch_ctrl = readl_relaxed(l2x0_base + + L2X0_PREFETCH_CTRL); + /* + * From r3p0, there is Power control register + */ + if (l2x0_revision >= L2X0_CACHE_ID_RTL_R3P0) + l2x0_saved_regs.pwr_ctrl = readl_relaxed(l2x0_base + + L2X0_POWER_CTRL); + } +} + +static void l2x0_resume(void) +{ + if (!(readl_relaxed(l2x0_base + L2X0_CTRL) & 1)) { + /* restore aux ctrl and enable l2 */ + l2x0_unlock(readl_relaxed(l2x0_base + L2X0_CACHE_ID)); + + writel_relaxed(l2x0_saved_regs.aux_ctrl, l2x0_base + + L2X0_AUX_CTRL); + + l2x0_inv_all(); + + writel_relaxed(1, l2x0_base + L2X0_CTRL); + } +} + +static void pl310_resume(void) +{ + u32 l2x0_revision; + + if (!(readl_relaxed(l2x0_base + L2X0_CTRL) & 1)) { + /* restore pl310 setup */ + writel_relaxed(l2x0_saved_regs.tag_latency, + l2x0_base + L2X0_TAG_LATENCY_CTRL); + writel_relaxed(l2x0_saved_regs.data_latency, + l2x0_base + L2X0_DATA_LATENCY_CTRL); + writel_relaxed(l2x0_saved_regs.filter_end, + l2x0_base + L2X0_ADDR_FILTER_END); + writel_relaxed(l2x0_saved_regs.filter_start, + l2x0_base + L2X0_ADDR_FILTER_START); + + l2x0_revision = readl_relaxed(l2x0_base + L2X0_CACHE_ID) & + L2X0_CACHE_ID_RTL_MASK; + + if (l2x0_revision >= L2X0_CACHE_ID_RTL_R2P0) { + writel_relaxed(l2x0_saved_regs.prefetch_ctrl, + l2x0_base + L2X0_PREFETCH_CTRL); + if (l2x0_revision >= L2X0_CACHE_ID_RTL_R3P0) + writel_relaxed(l2x0_saved_regs.pwr_ctrl, + l2x0_base + L2X0_POWER_CTRL); + } + } + + l2x0_resume(); +} + +static const struct l2x0_of_data pl310_data = { + pl310_of_setup, + pl310_save, + pl310_resume, +}; + +static const struct l2x0_of_data l2x0_data = { + l2x0_of_setup, + NULL, + l2x0_resume, +}; + static const struct of_device_id l2x0_ids[] __initconst = { - { .compatible = "arm,pl310-cache", .data = pl310_of_setup }, - { .compatible = "arm,l220-cache", .data = l2x0_of_setup }, - { .compatible = "arm,l210-cache", .data = l2x0_of_setup }, + { .compatible = "arm,pl310-cache", .data = (void *)&pl310_data }, + { .compatible = "arm,l220-cache", .data = (void *)&l2x0_data }, + { .compatible = "arm,l210-cache", .data = (void *)&l2x0_data }, {} }; int __init l2x0_of_init(__u32 aux_val, __u32 aux_mask) { struct device_node *np; - void (*l2_setup)(const struct device_node *np, - __u32 *aux_val, __u32 *aux_mask); + struct l2x0_of_data *data; + struct resource res; np = of_find_matching_node(NULL, l2x0_ids); if (!np) return -ENODEV; - l2x0_base = of_iomap(np, 0); + + if (of_address_to_resource(np, 0, &res)) + return -ENODEV; + + l2x0_base = ioremap(res.start, resource_size(&res)); if (!l2x0_base) return -ENOMEM; + l2x0_saved_regs.phy_base = res.start; + + data = of_match_node(l2x0_ids, np)->data; + /* L2 configuration can only be changed if the cache is disabled */ if (!(readl_relaxed(l2x0_base + L2X0_CTRL) & 1)) { - l2_setup = of_match_node(l2x0_ids, np)->data; - if (l2_setup) - l2_setup(np, &aux_val, &aux_mask); + if (data->setup) + data->setup(np, &aux_val, &aux_mask); } + + if (data->save) + data->save(); + l2x0_init(l2x0_base, aux_val, aux_mask); + + outer_cache.resume = data->resume; return 0; } #endif -- cgit v1.2.3