From 6ae3983b779ea5ad87515630e9b9205b76f1e916 Mon Sep 17 00:00:00 2001 From: Russell King - ARM Linux Date: Mon, 3 Nov 2008 17:36:10 -0800 Subject: [PATCH] Fix ARMv7 memory typing * Russell King - ARM Linux [081103 07:09]: > Solving ARMv7 seems to be fairly simple, at the expense of making > build_mem_types_table() slightly more complex. If that was the only > problem, then I wouldn't be mentioning the idea of dropping the > patchset. Well, this is the fix for ARMv7 (and a few others). In making these changes, I went back to DDI0100I (ARMv6 ARM), DDI0406A (ARMv7 ARM) and the Marvell Xscale3 documentation. ... Note that this version has a bug with xscale handling, but works for omap. This patch will get reverted once the final patch is available. Signed-off-by: Tony Lindgren --- arch/arm/include/asm/system.h | 4 ++ arch/arm/mm/mmu.c | 113 +++++++++++++++++++++++++--------- arch/arm/mm/proc-v7.S | 10 +-- 3 files changed, 92 insertions(+), 35 deletions(-) diff --git a/arch/arm/include/asm/system.h b/arch/arm/include/asm/system.h index 7aad78420f1..568020b34e3 100644 --- a/arch/arm/include/asm/system.h +++ b/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 diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c index 64c5451151b..697320aab3c 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 +205,7 @@ 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] = { @@ -277,22 +277,23 @@ 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)) + 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; @@ -306,6 +307,54 @@ 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 { + /* + * For Xscale3, ARMv6 and ARMv7 without TEX remapping, + * - shared device is TEXCB=00001 + * - nonshared device is TEXCB=01000 + * - write combine device mem is TEXCB=00100 + * (Inner/Outer Uncacheable in xsc3 parlance, 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; @@ -321,12 +370,8 @@ 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. @@ -340,11 +385,6 @@ 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 @@ -364,9 +404,6 @@ 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 | @@ -391,6 +428,22 @@ static void __init build_mem_type_table(void) for (i = 0; i < ARRAY_SIZE(mem_types); i++) { struct mem_type *t = &mem_types[i]; + const char *s; +#define T(n) if (i == (n)) s = #n; + s = "???"; + T(MT_DEVICE); + T(MT_DEVICE_NONSHARED); + T(MT_DEVICE_CACHED); + T(MT_DEVICE_WC); + T(MT_CACHECLEAN); + T(MT_MINICLEAN); + T(MT_LOW_VECTORS); + T(MT_HIGH_VECTORS); + T(MT_MEMORY); + T(MT_ROM); + printk(KERN_INFO "%-19s: DOM=%#3x S=%#010x L1=%#010x P=%#010x\n", + s, t->domain, t->prot_sect, t->prot_l1, t->prot_pte); + if (t->prot_l1) t->prot_l1 |= PMD_DOMAIN(t->domain); if (t->prot_sect) diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S index 07f82db7094..f1d158f26f6 100644 --- a/arch/arm/mm/proc-v7.S +++ b/arch/arm/mm/proc-v7.S @@ -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: -- 2.41.0