Merge commit 'v2.6.28-rc8' into x86/doc

6 files changed, 119 insertions, 46 deletions

diff --git a/arch/arm/mm/alignment.c b/arch/arm/mm/alignment.c
index 133e65d166b..2d5884ce043 100644
--- a/arch/arm/mm/alignment.c
+++ b/arch/arm/mm/alignment.c
@@ -70,6 +70,10 @@ static unsigned long ai_dword;
 static unsigned long ai_multi;
 static int ai_usermode;
 
+#define UM_WARN		(1 << 0)
+#define UM_FIXUP	(1 << 1)
+#define UM_SIGNAL	(1 << 2)
+
 #ifdef CONFIG_PROC_FS
 static const char *usermode_action[] = {
 	"ignored",
@@ -754,7 +758,7 @@ do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
  user:
 	ai_user += 1;
 
-	if (ai_usermode & 1)
+	if (ai_usermode & UM_WARN)
 		printk("Alignment trap: %s (%d) PC=0x%08lx Instr=0x%0*lx "
 		       "Address=0x%08lx FSR 0x%03x\n", current->comm,
 			task_pid_nr(current), instrptr,
@@ -762,10 +766,10 @@ do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 		        thumb_mode(regs) ? tinstr : instr,
 		        addr, fsr);
 
-	if (ai_usermode & 2)
+	if (ai_usermode & UM_FIXUP)
 		goto fixup;
 
-	if (ai_usermode & 4)
+	if (ai_usermode & UM_SIGNAL)
 		force_sig(SIGBUS, current);
 	else
 		set_cr(cr_no_alignment);
@@ -796,6 +800,22 @@ static int __init alignment_init(void)
 	res->write_proc = proc_alignment_write;
 #endif
 
+	/*
+	 * ARMv6 and later CPUs can perform unaligned accesses for
+	 * most single load and store instructions up to word size.
+	 * LDM, STM, LDRD and STRD still need to be handled.
+	 *
+	 * Ignoring the alignment fault is not an option on these
+	 * CPUs since we spin re-faulting the instruction without
+	 * making any progress.
+	 */
+	if (cpu_architecture() >= CPU_ARCH_ARMv6 && (cr_alignment & CR_U)) {
+		cr_alignment &= ~CR_A;
+		cr_no_alignment &= ~CR_A;
+		set_cr(cr_alignment);
+		ai_usermode = UM_FIXUP;
+	}
+
 	hook_fault_code(1, do_alignment, SIGILL, "alignment exception");
 	hook_fault_code(3, do_alignment, SIGILL, "alignment exception");
 
diff --git a/arch/arm/mm/cache-feroceon-l2.c b/arch/arm/mm/cache-feroceon-l2.c
index 13cdae8b0d4..80cd207cbae 100644
--- a/arch/arm/mm/cache-feroceon-l2.c
+++ b/arch/arm/mm/cache-feroceon-l2.c
@@ -150,7 +150,7 @@ static void feroceon_l2_inv_range(unsigned long start, unsigned long end)
 	/*
 	 * Clean and invalidate partial last cache line.
 	 */
-	if (end & (CACHE_LINE_SIZE - 1)) {
+	if (start < end && end & (CACHE_LINE_SIZE - 1)) {
 		l2_clean_inv_pa(end & ~(CACHE_LINE_SIZE - 1));
 		end &= ~(CACHE_LINE_SIZE - 1);
 	}
@@ -158,7 +158,7 @@ static void feroceon_l2_inv_range(unsigned long start, unsigned long end)
 	/*
 	 * Invalidate all full cache lines between 'start' and 'end'.
 	 */
-	while (start != end) {
+	while (start < end) {
 		unsigned long range_end = calc_range_end(start, end);
 		l2_inv_pa_range(start, range_end - CACHE_LINE_SIZE);
 		start = range_end;
diff --git a/arch/arm/mm/cache-xsc3l2.c b/arch/arm/mm/cache-xsc3l2.c
index 10b1bae1a25..464de893a98 100644
--- a/arch/arm/mm/cache-xsc3l2.c
+++ b/arch/arm/mm/cache-xsc3l2.c
@@ -98,7 +98,7 @@ static void xsc3_l2_inv_range(unsigned long start, unsigned long end)
 	/*
 	 * Clean and invalidate partial last cache line.
 	 */
-	if (end & (CACHE_LINE_SIZE - 1)) {
+	if (start < end && (end & (CACHE_LINE_SIZE - 1))) {
 		xsc3_l2_clean_pa(end & ~(CACHE_LINE_SIZE - 1));
 		xsc3_l2_inv_pa(end & ~(CACHE_LINE_SIZE - 1));
 		end &= ~(CACHE_LINE_SIZE - 1);
@@ -107,7 +107,7 @@ static void xsc3_l2_inv_range(unsigned long start, unsigned long end)
 	/*
 	 * Invalidate all full cache lines between 'start' and 'end'.
 	 */
-	while (start != end) {
+	while (start < end) {
 		xsc3_l2_inv_pa(start);
 		start += CACHE_LINE_SIZE;
 	}
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index 8ba75406455..7f36c825718 100644
--- a/arch/arm/mm/mmu.c
+++ b/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 +205,13 @@ 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_UNCACHED] = {
+		.prot_pte	= PROT_PTE_DEVICE,
+		.prot_l1	= PMD_TYPE_TABLE,
+		.prot_sect	= PMD_TYPE_SECT | PMD_SECT_XN,
 		.domain		= DOMAIN_IO,
 	},
 	[MT_CACHECLEAN] = {
@@ -273,22 +279,23 @@ 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 +309,64 @@ 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 +382,8 @@ 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 +397,6 @@ 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 +416,6 @@ 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 +707,7 @@ 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 +819,7 @@ 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);
diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S
index 07f82db7094..4d3c0a73e7f 100644
--- a/arch/arm/mm/proc-v7.S
+++ b/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:
diff --git a/arch/arm/mm/proc-xsc3.S b/arch/arm/mm/proc-xsc3.S
index 04dc8b65401..8f6cf56c11c 100644
--- a/arch/arm/mm/proc-xsc3.S
+++ b/arch/arm/mm/proc-xsc3.S
@@ -349,7 +349,7 @@ ENTRY(cpu_xsc3_switch_mm)
 cpu_xsc3_mt_table:
 	.long	0x00						@ L_PTE_MT_UNCACHED
 	.long	PTE_EXT_TEX(1)					@ L_PTE_MT_BUFFERABLE
-	.long	PTE_CACHEABLE					@ L_PTE_MT_WRITETHROUGH
+	.long	PTE_EXT_TEX(5) | PTE_CACHEABLE			@ L_PTE_MT_WRITETHROUGH
 	.long	PTE_CACHEABLE | PTE_BUFFERABLE			@ L_PTE_MT_WRITEBACK
 	.long	PTE_EXT_TEX(1) | PTE_BUFFERABLE			@ L_PTE_MT_DEV_SHARED
 	.long	0x00						@ unused