[ARM] mm: fix page table initialization

As a result of the ptebits changes, we ended up marking device mappings
as normal memory on ARMv7 CPUs, resulting in undesirable behaviour with
serial ports and the like.  While reviewing the section mapping table
entries, other errors in the memory type settings for devices were
detected and confirmed to prevent Xscale3 platforms booting.

Tested on:
	OMAP34xx (ARMv7),
	OMAP24xx (ARMv6),
	OMAP16xx (ARM926T, ARMv5),
	PXA311 (Xscale3),
	PXA272 (Xscale),
	PXA255 (Xscale),
	IXP42x (Xscale),
	S3C2410 (ARM920T, ARMv4T),
	ARM720T (ARMv4T)
	StrongARM-110 (ARMv4)
Acked-by: NTony Lindgren <tony@atomide.com>
Tested-by: NRobert Jarzmik <robert.jarzmik@free.fr>
Tested-by: NMike Rapoport <mike@compulab.co.il>
Tested-by: NBen Dooks <ben-linux@fluff.org>
Tested-by: NAnders Grafström <grfstrm@users.sourceforge.net>
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

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

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 |

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: