---

yaml
---
r: 118520
b: refs/heads/master
c: 878708f
h: refs/heads/master
v: v3

[refs]

@@ -1,2 +1,2 @@
 ---
-refs/heads/master: c7cf72dcadbe39c2077b32460f86c9f8167be3be
+refs/heads/master: 878708f290f6ed8b108d73fd6ab624cda6266a1e

trunk/Documentation/io-mapping.txt

@@ -0,0 +1,82 @@
+The io_mapping functions in linux/io-mapping.h provide an abstraction for
+efficiently mapping small regions of an I/O device to the CPU. The initial
+usage is to support the large graphics aperture on 32-bit processors where
+ioremap_wc cannot be used to statically map the entire aperture to the CPU
+as it would consume too much of the kernel address space.
+
+A mapping object is created during driver initialization using
+
+	struct io_mapping *io_mapping_create_wc(unsigned long base,
+						unsigned long size)
+
+		'base' is the bus address of the region to be made
+		mappable, while 'size' indicates how large a mapping region to
+		enable. Both are in bytes.
+
+		This _wc variant provides a mapping which may only be used
+		with the io_mapping_map_atomic_wc or io_mapping_map_wc.
+
+With this mapping object, individual pages can be mapped either atomically
+or not, depending on the necessary scheduling environment. Of course, atomic
+maps are more efficient:
+
+	void *io_mapping_map_atomic_wc(struct io_mapping *mapping,
+				       unsigned long offset)
+
+		'offset' is the offset within the defined mapping region.
+		Accessing addresses beyond the region specified in the
+		creation function yields undefined results. Using an offset
+		which is not page aligned yields an undefined result. The
+		return value points to a single page in CPU address space.
+
+		This _wc variant returns a write-combining map to the
+		page and may only be used with mappings created by
+		io_mapping_create_wc
+
+		Note that the task may not sleep while holding this page
+		mapped.
+
+	void io_mapping_unmap_atomic(void *vaddr)
+
+		'vaddr' must be the the value returned by the last
+		io_mapping_map_atomic_wc call. This unmaps the specified
+		page and allows the task to sleep once again.
+
+If you need to sleep while holding the lock, you can use the non-atomic
+variant, although they may be significantly slower.
+
+	void *io_mapping_map_wc(struct io_mapping *mapping,
+				unsigned long offset)
+
+		This works like io_mapping_map_atomic_wc except it allows
+		the task to sleep while holding the page mapped.
+
+	void io_mapping_unmap(void *vaddr)
+
+		This works like io_mapping_unmap_atomic, except it is used
+		for pages mapped with io_mapping_map_wc.
+
+At driver close time, the io_mapping object must be freed:
+
+	void io_mapping_free(struct io_mapping *mapping)
+
+Current Implementation:
+
+The initial implementation of these functions uses existing mapping
+mechanisms and so provides only an abstraction layer and no new
+functionality.
+
+On 64-bit processors, io_mapping_create_wc calls ioremap_wc for the whole
+range, creating a permanent kernel-visible mapping to the resource. The
+map_atomic and map functions add the requested offset to the base of the
+virtual address returned by ioremap_wc.
+
+On 32-bit processors with HIGHMEM defined, io_mapping_map_atomic_wc uses
+kmap_atomic_pfn to map the specified page in an atomic fashion;
+kmap_atomic_pfn isn't really supposed to be used with device pages, but it
+provides an efficient mapping for this usage.
+
+On 32-bit processors without HIGHMEM defined, io_mapping_map_atomic_wc and
+io_mapping_map_wc both use ioremap_wc, a terribly inefficient function which
+performs an IPI to inform all processors about the new mapping. This results
+in a significant performance penalty.

trunk/arch/arm/include/asm/memory.h

@@ -44,10 +44,10 @@
  * The module space lives between the addresses given by TASK_SIZE
  * and PAGE_OFFSET - it must be within 32MB of the kernel text.
  */
-#define MODULE_END		(PAGE_OFFSET)
-#define MODULE_START		(MODULE_END - 16*1048576)
+#define MODULES_END		(PAGE_OFFSET)
+#define MODULES_VADDR		(MODULES_END - 16*1048576)
 
-#if TASK_SIZE > MODULE_START
+#if TASK_SIZE > MODULES_VADDR
 #error Top of user space clashes with start of module space
 #endif
 
@@ -56,7 +56,7 @@
  * Since we use sections to map it, this macro replaces the physical address
  * with its virtual address while keeping offset from the base section.
  */
-#define XIP_VIRT_ADDR(physaddr)  (MODULE_START + ((physaddr) & 0x000fffff))
+#define XIP_VIRT_ADDR(physaddr)  (MODULES_VADDR + ((physaddr) & 0x000fffff))
 
 /*
  * Allow 16MB-aligned ioremap pages
@@ -94,8 +94,8 @@
 /*
  * The module can be at any place in ram in nommu mode.
  */
-#define MODULE_END		(END_MEM)
-#define MODULE_START		(PHYS_OFFSET)
+#define MODULES_END		(END_MEM)
+#define MODULES_VADDR		(PHYS_OFFSET)
 
 #endif /* !CONFIG_MMU */
 

trunk/arch/arm/include/asm/system.h

@@ -42,6 +42,10 @@
 #define CR_U	(1 << 22)	/* Unaligned access operation		*/
 #define CR_XP	(1 << 23)	/* Extended page tables			*/
 #define CR_VE	(1 << 24)	/* Vectored interrupts			*/
+#define CR_EE	(1 << 25)	/* Exception (Big) Endian		*/
+#define CR_TRE	(1 << 28)	/* TEX remap enable			*/
+#define CR_AFE	(1 << 29)	/* Access flag enable			*/
+#define CR_TE	(1 << 30)	/* Thumb exception enable		*/
 
 /*
  * This is used to ensure the compiler did actually allocate the register we

trunk/arch/arm/kernel/elf.c

@@ -21,12 +21,16 @@ int elf_check_arch(const struct elf32_hdr *x)
 
 	eflags = x->e_flags;
 	if ((eflags & EF_ARM_EABI_MASK) == EF_ARM_EABI_UNKNOWN) {
+		unsigned int flt_fmt;
+
 		/* APCS26 is only allowed if the CPU supports it */
 		if ((eflags & EF_ARM_APCS_26) && !(elf_hwcap & HWCAP_26BIT))
 			return 0;
 
+		flt_fmt = eflags & (EF_ARM_VFP_FLOAT | EF_ARM_SOFT_FLOAT);
+
 		/* VFP requires the supporting code */
-		if ((eflags & EF_ARM_VFP_FLOAT) && !(elf_hwcap & HWCAP_VFP))
+		if (flt_fmt == EF_ARM_VFP_FLOAT && !(elf_hwcap & HWCAP_VFP))
 			return 0;
 	}
 	return 1;

trunk/arch/arm/kernel/module.c

@@ -26,12 +26,12 @@
 /*
  * The XIP kernel text is mapped in the module area for modules and
  * some other stuff to work without any indirect relocations.
- * MODULE_START is redefined here and not in asm/memory.h to avoid
+ * MODULES_VADDR is redefined here and not in asm/memory.h to avoid
  * recompiling the whole kernel when CONFIG_XIP_KERNEL is turned on/off.
  */
 extern void _etext;
-#undef MODULE_START
-#define MODULE_START	(((unsigned long)&_etext + ~PGDIR_MASK) & PGDIR_MASK)
+#undef MODULES_VADDR
+#define MODULES_VADDR	(((unsigned long)&_etext + ~PGDIR_MASK) & PGDIR_MASK)
 #endif
 
 #ifdef CONFIG_MMU
@@ -43,7 +43,7 @@ void *module_alloc(unsigned long size)
 	if (!size)
 		return NULL;
 
-	area = __get_vm_area(size, VM_ALLOC, MODULE_START, MODULE_END);
+	area = __get_vm_area(size, VM_ALLOC, MODULES_VADDR, MODULES_END);
 	if (!area)
 		return NULL;
 

trunk/arch/arm/mm/mmu.c

@@ -180,20 +180,20 @@ void adjust_cr(unsigned long mask, unsigned long set)
 #endif
 
 #define PROT_PTE_DEVICE		L_PTE_PRESENT|L_PTE_YOUNG|L_PTE_DIRTY|L_PTE_WRITE
-#define PROT_SECT_DEVICE	PMD_TYPE_SECT|PMD_SECT_XN|PMD_SECT_AP_WRITE
+#define PROT_SECT_DEVICE	PMD_TYPE_SECT|PMD_SECT_AP_WRITE
 
 static struct mem_type mem_types[] = {
 	[MT_DEVICE] = {		  /* Strongly ordered / ARMv6 shared device */
 		.prot_pte	= PROT_PTE_DEVICE | L_PTE_MT_DEV_SHARED |
 				  L_PTE_SHARED,
 		.prot_l1	= PMD_TYPE_TABLE,
-		.prot_sect	= PROT_SECT_DEVICE | PMD_SECT_UNCACHED,
+		.prot_sect	= PROT_SECT_DEVICE | PMD_SECT_S,
 		.domain		= DOMAIN_IO,
 	},
 	[MT_DEVICE_NONSHARED] = { /* ARMv6 non-shared device */
 		.prot_pte	= PROT_PTE_DEVICE | L_PTE_MT_DEV_NONSHARED,
 		.prot_l1	= PMD_TYPE_TABLE,
-		.prot_sect	= PROT_SECT_DEVICE | PMD_SECT_TEX(2),
+		.prot_sect	= PROT_SECT_DEVICE,
 		.domain		= DOMAIN_IO,
 	},
 	[MT_DEVICE_CACHED] = {	  /* ioremap_cached */
@@ -205,7 +205,7 @@ static struct mem_type mem_types[] = {
 	[MT_DEVICE_WC] = {	/* ioremap_wc */
 		.prot_pte	= PROT_PTE_DEVICE | L_PTE_MT_DEV_WC,
 		.prot_l1	= PMD_TYPE_TABLE,
-		.prot_sect	= PROT_SECT_DEVICE | PMD_SECT_BUFFERABLE,
+		.prot_sect	= PROT_SECT_DEVICE,
 		.domain		= DOMAIN_IO,
 	},
 	[MT_CACHECLEAN] = {
@@ -273,22 +273,23 @@ static void __init build_mem_type_table(void)
 #endif
 
 	/*
-	 * On non-Xscale3 ARMv5-and-older systems, use CB=01
-	 * (Uncached/Buffered) for ioremap_wc() mappings.  On XScale3
-	 * and ARMv6+, use TEXCB=00100 mappings (Inner/Outer Uncacheable
-	 * in xsc3 parlance, Uncached Normal in ARMv6 parlance).
+	 * Strip out features not present on earlier architectures.
+	 * Pre-ARMv5 CPUs don't have TEX bits.  Pre-ARMv6 CPUs or those
+	 * without extended page tables don't have the 'Shared' bit.
 	 */
-	if (cpu_is_xsc3() || cpu_arch >= CPU_ARCH_ARMv6) {
-		mem_types[MT_DEVICE_WC].prot_sect |= PMD_SECT_TEX(1);
-		mem_types[MT_DEVICE_WC].prot_sect &= ~PMD_SECT_BUFFERABLE;
-	}
+	if (cpu_arch < CPU_ARCH_ARMv5)
+		for (i = 0; i < ARRAY_SIZE(mem_types); i++)
+			mem_types[i].prot_sect &= ~PMD_SECT_TEX(7);
+	if ((cpu_arch < CPU_ARCH_ARMv6 || !(cr & CR_XP)) && !cpu_is_xsc3())
+		for (i = 0; i < ARRAY_SIZE(mem_types); i++)
+			mem_types[i].prot_sect &= ~PMD_SECT_S;
 
 	/*
-	 * ARMv5 and lower, bit 4 must be set for page tables.
-	 * (was: cache "update-able on write" bit on ARM610)
-	 * However, Xscale cores require this bit to be cleared.
+	 * ARMv5 and lower, bit 4 must be set for page tables (was: cache
+	 * "update-able on write" bit on ARM610).  However, Xscale and
+	 * Xscale3 require this bit to be cleared.
 	 */
-	if (cpu_is_xscale()) {
+	if (cpu_is_xscale() || cpu_is_xsc3()) {
 		for (i = 0; i < ARRAY_SIZE(mem_types); i++) {
 			mem_types[i].prot_sect &= ~PMD_BIT4;
 			mem_types[i].prot_l1 &= ~PMD_BIT4;
@@ -302,6 +303,64 @@ static void __init build_mem_type_table(void)
 		}
 	}
 
+	/*
+	 * Mark the device areas according to the CPU/architecture.
+	 */
+	if (cpu_is_xsc3() || (cpu_arch >= CPU_ARCH_ARMv6 && (cr & CR_XP))) {
+		if (!cpu_is_xsc3()) {
+			/*
+			 * Mark device regions on ARMv6+ as execute-never
+			 * to prevent speculative instruction fetches.
+			 */
+			mem_types[MT_DEVICE].prot_sect |= PMD_SECT_XN;
+			mem_types[MT_DEVICE_NONSHARED].prot_sect |= PMD_SECT_XN;
+			mem_types[MT_DEVICE_CACHED].prot_sect |= PMD_SECT_XN;
+			mem_types[MT_DEVICE_WC].prot_sect |= PMD_SECT_XN;
+		}
+		if (cpu_arch >= CPU_ARCH_ARMv7 && (cr & CR_TRE)) {
+			/*
+			 * For ARMv7 with TEX remapping,
+			 * - shared device is SXCB=1100
+			 * - nonshared device is SXCB=0100
+			 * - write combine device mem is SXCB=0001
+			 * (Uncached Normal memory)
+			 */
+			mem_types[MT_DEVICE].prot_sect |= PMD_SECT_TEX(1);
+			mem_types[MT_DEVICE_NONSHARED].prot_sect |= PMD_SECT_TEX(1);
+			mem_types[MT_DEVICE_WC].prot_sect |= PMD_SECT_BUFFERABLE;
+		} else if (cpu_is_xsc3()) {
+			/*
+			 * For Xscale3,
+			 * - shared device is TEXCB=00101
+			 * - nonshared device is TEXCB=01000
+			 * - write combine device mem is TEXCB=00100
+			 * (Inner/Outer Uncacheable in xsc3 parlance)
+			 */
+			mem_types[MT_DEVICE].prot_sect |= PMD_SECT_TEX(1) | PMD_SECT_BUFFERED;
+			mem_types[MT_DEVICE_NONSHARED].prot_sect |= PMD_SECT_TEX(2);
+			mem_types[MT_DEVICE_WC].prot_sect |= PMD_SECT_TEX(1);
+		} else {
+			/*
+			 * For ARMv6 and ARMv7 without TEX remapping,
+			 * - shared device is TEXCB=00001
+			 * - nonshared device is TEXCB=01000
+			 * - write combine device mem is TEXCB=00100
+			 * (Uncached Normal in ARMv6 parlance).
+			 */
+			mem_types[MT_DEVICE].prot_sect |= PMD_SECT_BUFFERED;
+			mem_types[MT_DEVICE_NONSHARED].prot_sect |= PMD_SECT_TEX(2);
+			mem_types[MT_DEVICE_WC].prot_sect |= PMD_SECT_TEX(1);
+		}
+	} else {
+		/*
+		 * On others, write combining is "Uncached/Buffered"
+		 */
+		mem_types[MT_DEVICE_WC].prot_sect |= PMD_SECT_BUFFERABLE;
+	}
+
+	/*
+	 * Now deal with the memory-type mappings
+	 */
 	cp = &cache_policies[cachepolicy];
 	vecs_pgprot = kern_pgprot = user_pgprot = cp->pte;
 
@@ -317,12 +376,8 @@ static void __init build_mem_type_table(void)
 	 * Enable CPU-specific coherency if supported.
 	 * (Only available on XSC3 at the moment.)
 	 */
-	if (arch_is_coherent()) {
-		if (cpu_is_xsc3()) {
-			mem_types[MT_MEMORY].prot_sect |= PMD_SECT_S;
-			mem_types[MT_MEMORY].prot_pte |= L_PTE_SHARED;
-		}
-	}
+	if (arch_is_coherent() && cpu_is_xsc3())
+		mem_types[MT_MEMORY].prot_sect |= PMD_SECT_S;
 
 	/*
 	 * ARMv6 and above have extended page tables.
@@ -336,11 +391,6 @@ static void __init build_mem_type_table(void)
 		mem_types[MT_MINICLEAN].prot_sect |= PMD_SECT_APX|PMD_SECT_AP_WRITE;
 		mem_types[MT_CACHECLEAN].prot_sect |= PMD_SECT_APX|PMD_SECT_AP_WRITE;
 
-		/*
-		 * Mark the device area as "shared device"
-		 */
-		mem_types[MT_DEVICE].prot_sect |= PMD_SECT_BUFFERED;
-
 #ifdef CONFIG_SMP
 		/*
 		 * Mark memory with the "shared" attribute for SMP systems
@@ -360,9 +410,6 @@ static void __init build_mem_type_table(void)
 	mem_types[MT_LOW_VECTORS].prot_pte |= vecs_pgprot;
 	mem_types[MT_HIGH_VECTORS].prot_pte |= vecs_pgprot;
 
-	if (cpu_arch < CPU_ARCH_ARMv5)
-		mem_types[MT_MINICLEAN].prot_sect &= ~PMD_SECT_TEX(1);
-
 	pgprot_user   = __pgprot(L_PTE_PRESENT | L_PTE_YOUNG | user_pgprot);
 	pgprot_kernel = __pgprot(L_PTE_PRESENT | L_PTE_YOUNG |
 				 L_PTE_DIRTY | L_PTE_WRITE |
@@ -654,7 +701,7 @@ static inline void prepare_page_table(struct meminfo *mi)
 	/*
 	 * Clear out all the mappings below the kernel image.
 	 */
-	for (addr = 0; addr < MODULE_START; addr += PGDIR_SIZE)
+	for (addr = 0; addr < MODULES_VADDR; addr += PGDIR_SIZE)
 		pmd_clear(pmd_off_k(addr));
 
 #ifdef CONFIG_XIP_KERNEL
@@ -766,7 +813,7 @@ static void __init devicemaps_init(struct machine_desc *mdesc)
 	 */
 #ifdef CONFIG_XIP_KERNEL
 	map.pfn = __phys_to_pfn(CONFIG_XIP_PHYS_ADDR & SECTION_MASK);
-	map.virtual = MODULE_START;
+	map.virtual = MODULES_VADDR;
 	map.length = ((unsigned long)&_etext - map.virtual + ~SECTION_MASK) & SECTION_MASK;
 	map.type = MT_ROM;
 	create_mapping(&map);

trunk/arch/arm/mm/proc-v7.S

@@ -115,7 +115,7 @@ ENTRY(cpu_v7_set_pte_ext)
 	orr	r3, r3, r2
 	orr	r3, r3, #PTE_EXT_AP0 | 2
 
-	tst	r2, #1 << 4
+	tst	r1, #1 << 4
 	orrne	r3, r3, #PTE_EXT_TEX(1)
 
 	tst	r1, #L_PTE_WRITE
@@ -192,11 +192,11 @@ __v7_setup:
 	mov	pc, lr				@ return to head.S:__ret
 ENDPROC(__v7_setup)
 
-	/*
-	 *         V X F   I D LR
-	 * .... ...E PUI. .T.T 4RVI ZFRS BLDP WCAM
-	 * rrrr rrrx xxx0 0101 xxxx xxxx x111 xxxx < forced
-	 *         0 110       0011 1.00 .111 1101 < we want
+	/*   AT
+	 *  TFR   EV X F   I D LR
+	 * .EEE ..EE PUI. .T.T 4RVI ZFRS BLDP WCAM
+	 * rxxx rrxx xxx0 0101 xxxx xxxx x111 xxxx < forced
+	 *    1    0 110       0011 1.00 .111 1101 < we want
 	 */
 	.type	v7_crval, #object
 v7_crval: