diff options
Diffstat (limited to 'arch/arm/mm')
50 files changed, 876 insertions, 439 deletions
diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig index a0a2928ae4d..4414a01e1e8 100644 --- a/arch/arm/mm/Kconfig +++ b/arch/arm/mm/Kconfig @@ -779,6 +779,14 @@ config CACHE_L2X0 help This option enables the L2x0 PrimeCell. +config CACHE_PL310 + bool + depends on CACHE_L2X0 + default y if CPU_V7 && !CPU_V6 + help + This option enables optimisations for the PL310 cache + controller. + config CACHE_TAUROS2 bool "Enable the Tauros2 L2 cache controller" depends on (ARCH_DOVE || ARCH_MMP) diff --git a/arch/arm/mm/cache-fa.S b/arch/arm/mm/cache-fa.S index 7148e53e607..1fa6f71470d 100644 --- a/arch/arm/mm/cache-fa.S +++ b/arch/arm/mm/cache-fa.S @@ -38,6 +38,17 @@ #define CACHE_DLIMIT (CACHE_DSIZE * 2) /* + * flush_icache_all() + * + * Unconditionally clean and invalidate the entire icache. + */ +ENTRY(fa_flush_icache_all) + mov r0, #0 + mcr p15, 0, r0, c7, c5, 0 @ invalidate I cache + mov pc, lr +ENDPROC(fa_flush_icache_all) + +/* * flush_user_cache_all() * * Clean and invalidate all cache entries in a particular address @@ -233,6 +244,7 @@ ENDPROC(fa_dma_unmap_area) .type fa_cache_fns, #object ENTRY(fa_cache_fns) + .long fa_flush_icache_all .long fa_flush_kern_cache_all .long fa_flush_user_cache_all .long fa_flush_user_cache_range diff --git a/arch/arm/mm/cache-feroceon-l2.c b/arch/arm/mm/cache-feroceon-l2.c index 6e77c042d8e..e0b0e7a4ec6 100644 --- a/arch/arm/mm/cache-feroceon-l2.c +++ b/arch/arm/mm/cache-feroceon-l2.c @@ -13,13 +13,9 @@ */ #include <linux/init.h> +#include <linux/highmem.h> #include <asm/cacheflush.h> -#include <asm/kmap_types.h> -#include <asm/fixmap.h> -#include <asm/pgtable.h> -#include <asm/tlbflush.h> #include <plat/cache-feroceon-l2.h> -#include "mm.h" /* * Low-level cache maintenance operations. @@ -39,27 +35,30 @@ * between which we don't want to be preempted. */ -static inline unsigned long l2_start_va(unsigned long paddr) +static inline unsigned long l2_get_va(unsigned long paddr) { #ifdef CONFIG_HIGHMEM /* - * Let's do our own fixmap stuff in a minimal way here. * Because range ops can't be done on physical addresses, * we simply install a virtual mapping for it only for the * TLB lookup to occur, hence no need to flush the untouched - * memory mapping. This is protected with the disabling of - * interrupts by the caller. + * memory mapping afterwards (note: a cache flush may happen + * in some circumstances depending on the path taken in kunmap_atomic). */ - unsigned long idx = KM_L2_CACHE + KM_TYPE_NR * smp_processor_id(); - unsigned long vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx); - set_pte_ext(TOP_PTE(vaddr), pfn_pte(paddr >> PAGE_SHIFT, PAGE_KERNEL), 0); - local_flush_tlb_kernel_page(vaddr); - return vaddr + (paddr & ~PAGE_MASK); + void *vaddr = kmap_atomic_pfn(paddr >> PAGE_SHIFT); + return (unsigned long)vaddr + (paddr & ~PAGE_MASK); #else return __phys_to_virt(paddr); #endif } +static inline void l2_put_va(unsigned long vaddr) +{ +#ifdef CONFIG_HIGHMEM + kunmap_atomic((void *)vaddr); +#endif +} + static inline void l2_clean_pa(unsigned long addr) { __asm__("mcr p15, 1, %0, c15, c9, 3" : : "r" (addr)); @@ -76,13 +75,14 @@ static inline void l2_clean_pa_range(unsigned long start, unsigned long end) */ BUG_ON((start ^ end) >> PAGE_SHIFT); - raw_local_irq_save(flags); - va_start = l2_start_va(start); + va_start = l2_get_va(start); va_end = va_start + (end - start); + raw_local_irq_save(flags); __asm__("mcr p15, 1, %0, c15, c9, 4\n\t" "mcr p15, 1, %1, c15, c9, 5" : : "r" (va_start), "r" (va_end)); raw_local_irq_restore(flags); + l2_put_va(va_start); } static inline void l2_clean_inv_pa(unsigned long addr) @@ -106,13 +106,14 @@ static inline void l2_inv_pa_range(unsigned long start, unsigned long end) */ BUG_ON((start ^ end) >> PAGE_SHIFT); - raw_local_irq_save(flags); - va_start = l2_start_va(start); + va_start = l2_get_va(start); va_end = va_start + (end - start); + raw_local_irq_save(flags); __asm__("mcr p15, 1, %0, c15, c11, 4\n\t" "mcr p15, 1, %1, c15, c11, 5" : : "r" (va_start), "r" (va_end)); raw_local_irq_restore(flags); + l2_put_va(va_start); } static inline void l2_inv_all(void) diff --git a/arch/arm/mm/cache-l2x0.c b/arch/arm/mm/cache-l2x0.c index 9982eb385c0..170c9bb9586 100644 --- a/arch/arm/mm/cache-l2x0.c +++ b/arch/arm/mm/cache-l2x0.c @@ -28,14 +28,24 @@ static void __iomem *l2x0_base; static DEFINE_SPINLOCK(l2x0_lock); static uint32_t l2x0_way_mask; /* Bitmask of active ways */ +static uint32_t l2x0_size; -static inline void cache_wait(void __iomem *reg, unsigned long mask) +static inline void cache_wait_way(void __iomem *reg, unsigned long mask) { - /* wait for the operation to complete */ + /* wait for cache operation by line or way to complete */ while (readl_relaxed(reg) & mask) ; } +#ifdef CONFIG_CACHE_PL310 +static inline void cache_wait(void __iomem *reg, unsigned long mask) +{ + /* cache operations by line are atomic on PL310 */ +} +#else +#define cache_wait cache_wait_way +#endif + static inline void cache_sync(void) { void __iomem *base = l2x0_base; @@ -103,14 +113,40 @@ static void l2x0_cache_sync(void) spin_unlock_irqrestore(&l2x0_lock, flags); } -static inline void l2x0_inv_all(void) +static void l2x0_flush_all(void) +{ + unsigned long flags; + + /* clean all ways */ + spin_lock_irqsave(&l2x0_lock, flags); + writel_relaxed(l2x0_way_mask, l2x0_base + L2X0_CLEAN_INV_WAY); + cache_wait_way(l2x0_base + L2X0_CLEAN_INV_WAY, l2x0_way_mask); + cache_sync(); + spin_unlock_irqrestore(&l2x0_lock, flags); +} + +static void l2x0_clean_all(void) +{ + unsigned long flags; + + /* clean all ways */ + spin_lock_irqsave(&l2x0_lock, flags); + writel_relaxed(l2x0_way_mask, l2x0_base + L2X0_CLEAN_WAY); + cache_wait_way(l2x0_base + L2X0_CLEAN_WAY, l2x0_way_mask); + cache_sync(); + spin_unlock_irqrestore(&l2x0_lock, flags); +} + +static void l2x0_inv_all(void) { unsigned long flags; /* invalidate all ways */ spin_lock_irqsave(&l2x0_lock, flags); + /* Invalidating when L2 is enabled is a nono */ + BUG_ON(readl(l2x0_base + L2X0_CTRL) & 1); writel_relaxed(l2x0_way_mask, l2x0_base + L2X0_INV_WAY); - cache_wait(l2x0_base + L2X0_INV_WAY, l2x0_way_mask); + cache_wait_way(l2x0_base + L2X0_INV_WAY, l2x0_way_mask); cache_sync(); spin_unlock_irqrestore(&l2x0_lock, flags); } @@ -159,6 +195,11 @@ static void l2x0_clean_range(unsigned long start, unsigned long end) void __iomem *base = l2x0_base; unsigned long flags; + if ((end - start) >= l2x0_size) { + l2x0_clean_all(); + return; + } + spin_lock_irqsave(&l2x0_lock, flags); start &= ~(CACHE_LINE_SIZE - 1); while (start < end) { @@ -184,6 +225,11 @@ static void l2x0_flush_range(unsigned long start, unsigned long end) void __iomem *base = l2x0_base; unsigned long flags; + if ((end - start) >= l2x0_size) { + l2x0_flush_all(); + return; + } + spin_lock_irqsave(&l2x0_lock, flags); start &= ~(CACHE_LINE_SIZE - 1); while (start < end) { @@ -206,10 +252,20 @@ static void l2x0_flush_range(unsigned long start, unsigned long end) spin_unlock_irqrestore(&l2x0_lock, flags); } +static void l2x0_disable(void) +{ + unsigned long flags; + + spin_lock_irqsave(&l2x0_lock, flags); + writel(0, l2x0_base + L2X0_CTRL); + spin_unlock_irqrestore(&l2x0_lock, flags); +} + void __init l2x0_init(void __iomem *base, __u32 aux_val, __u32 aux_mask) { __u32 aux; __u32 cache_id; + __u32 way_size = 0; int ways; const char *type; @@ -244,6 +300,13 @@ void __init l2x0_init(void __iomem *base, __u32 aux_val, __u32 aux_mask) l2x0_way_mask = (1 << ways) - 1; /* + * L2 cache Size = Way size * Number of ways + */ + way_size = (aux & L2X0_AUX_CTRL_WAY_SIZE_MASK) >> 17; + way_size = 1 << (way_size + 3); + l2x0_size = ways * way_size * SZ_1K; + + /* * Check if l2x0 controller is already enabled. * If you are booting from non-secure mode * accessing the below registers will fault. @@ -263,8 +326,11 @@ void __init l2x0_init(void __iomem *base, __u32 aux_val, __u32 aux_mask) outer_cache.clean_range = l2x0_clean_range; outer_cache.flush_range = l2x0_flush_range; outer_cache.sync = l2x0_cache_sync; + outer_cache.flush_all = l2x0_flush_all; + outer_cache.inv_all = l2x0_inv_all; + outer_cache.disable = l2x0_disable; printk(KERN_INFO "%s cache controller enabled\n", type); - printk(KERN_INFO "l2x0: %d ways, CACHE_ID 0x%08x, AUX_CTRL 0x%08x\n", - ways, cache_id, aux); + 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); } diff --git a/arch/arm/mm/cache-v3.S b/arch/arm/mm/cache-v3.S index c2ff3c599fe..2e2bc406a18 100644 --- a/arch/arm/mm/cache-v3.S +++ b/arch/arm/mm/cache-v3.S @@ -13,6 +13,15 @@ #include "proc-macros.S" /* + * flush_icache_all() + * + * Unconditionally clean and invalidate the entire icache. + */ +ENTRY(v3_flush_icache_all) + mov pc, lr +ENDPROC(v3_flush_icache_all) + +/* * flush_user_cache_all() * * Invalidate all cache entries in a particular address @@ -122,6 +131,7 @@ ENDPROC(v3_dma_map_area) .type v3_cache_fns, #object ENTRY(v3_cache_fns) + .long v3_flush_icache_all .long v3_flush_kern_cache_all .long v3_flush_user_cache_all .long v3_flush_user_cache_range diff --git a/arch/arm/mm/cache-v4.S b/arch/arm/mm/cache-v4.S index 4810f7e3e81..a8fefb523f1 100644 --- a/arch/arm/mm/cache-v4.S +++ b/arch/arm/mm/cache-v4.S @@ -13,6 +13,15 @@ #include "proc-macros.S" /* + * flush_icache_all() + * + * Unconditionally clean and invalidate the entire icache. + */ +ENTRY(v4_flush_icache_all) + mov pc, lr +ENDPROC(v4_flush_icache_all) + +/* * flush_user_cache_all() * * Invalidate all cache entries in a particular address @@ -134,6 +143,7 @@ ENDPROC(v4_dma_map_area) .type v4_cache_fns, #object ENTRY(v4_cache_fns) + .long v4_flush_icache_all .long v4_flush_kern_cache_all .long v4_flush_user_cache_all .long v4_flush_user_cache_range diff --git a/arch/arm/mm/cache-v4wb.S b/arch/arm/mm/cache-v4wb.S index df8368afa10..d3644db467b 100644 --- a/arch/arm/mm/cache-v4wb.S +++ b/arch/arm/mm/cache-v4wb.S @@ -51,6 +51,17 @@ flush_base: .text /* + * flush_icache_all() + * + * Unconditionally clean and invalidate the entire icache. + */ +ENTRY(v4wb_flush_icache_all) + mov r0, #0 + mcr p15, 0, r0, c7, c5, 0 @ invalidate I cache + mov pc, lr +ENDPROC(v4wb_flush_icache_all) + +/* * flush_user_cache_all() * * Clean and invalidate all cache entries in a particular address @@ -244,6 +255,7 @@ ENDPROC(v4wb_dma_unmap_area) .type v4wb_cache_fns, #object ENTRY(v4wb_cache_fns) + .long v4wb_flush_icache_all .long v4wb_flush_kern_cache_all .long v4wb_flush_user_cache_all .long v4wb_flush_user_cache_range diff --git a/arch/arm/mm/cache-v4wt.S b/arch/arm/mm/cache-v4wt.S index 45c70312f43..49c2b66cf3d 100644 --- a/arch/arm/mm/cache-v4wt.S +++ b/arch/arm/mm/cache-v4wt.S @@ -41,6 +41,17 @@ #define CACHE_DLIMIT 16384 /* + * flush_icache_all() + * + * Unconditionally clean and invalidate the entire icache. + */ +ENTRY(v4wt_flush_icache_all) + mov r0, #0 + mcr p15, 0, r0, c7, c5, 0 @ invalidate I cache + mov pc, lr +ENDPROC(v4wt_flush_icache_all) + +/* * flush_user_cache_all() * * Invalidate all cache entries in a particular address @@ -188,6 +199,7 @@ ENDPROC(v4wt_dma_map_area) .type v4wt_cache_fns, #object ENTRY(v4wt_cache_fns) + .long v4wt_flush_icache_all .long v4wt_flush_kern_cache_all .long v4wt_flush_user_cache_all .long v4wt_flush_user_cache_range diff --git a/arch/arm/mm/cache-v6.S b/arch/arm/mm/cache-v6.S index 86aa689ef1a..c96fa1b3f49 100644 --- a/arch/arm/mm/cache-v6.S +++ b/arch/arm/mm/cache-v6.S @@ -21,18 +21,22 @@ #define D_CACHE_LINE_SIZE 32 #define BTB_FLUSH_SIZE 8 -#ifdef CONFIG_ARM_ERRATA_411920 /* - * Invalidate the entire I cache (this code is a workaround for the ARM1136 - * erratum 411920 - Invalidate Instruction Cache operation can fail. This - * erratum is present in 1136, 1156 and 1176. It does not affect the MPCore. + * v6_flush_icache_all() + * + * Flush the whole I-cache. + * + * ARM1136 erratum 411920 - Invalidate Instruction Cache operation can fail. + * This erratum is present in 1136, 1156 and 1176. It does not affect the + * MPCore. * - * Registers: - * r0 - set to 0 - * r1 - corrupted + * Registers: + * r0 - set to 0 + * r1 - corrupted */ -ENTRY(v6_icache_inval_all) +ENTRY(v6_flush_icache_all) mov r0, #0 +#ifdef CONFIG_ARM_ERRATA_411920 mrs r1, cpsr cpsid ifa @ disable interrupts mcr p15, 0, r0, c7, c5, 0 @ invalidate entire I-cache @@ -43,8 +47,11 @@ ENTRY(v6_icache_inval_all) .rept 11 @ ARM Ltd recommends at least nop @ 11 NOPs .endr - mov pc, lr +#else + mcr p15, 0, r0, c7, c5, 0 @ invalidate I-cache #endif + mov pc, lr +ENDPROC(v6_flush_icache_all) /* * v6_flush_cache_all() @@ -60,7 +67,7 @@ ENTRY(v6_flush_kern_cache_all) #ifndef CONFIG_ARM_ERRATA_411920 mcr p15, 0, r0, c7, c5, 0 @ I+BTB cache invalidate #else - b v6_icache_inval_all + b v6_flush_icache_all #endif #else mcr p15, 0, r0, c7, c15, 0 @ Cache clean+invalidate @@ -138,7 +145,7 @@ ENTRY(v6_coherent_user_range) #ifndef CONFIG_ARM_ERRATA_411920 mcr p15, 0, r0, c7, c5, 0 @ I+BTB cache invalidate #else - b v6_icache_inval_all + b v6_flush_icache_all #endif #else mcr p15, 0, r0, c7, c5, 6 @ invalidate BTB @@ -196,6 +203,10 @@ ENTRY(v6_flush_kern_dcache_area) * - end - virtual end address of region */ v6_dma_inv_range: +#ifdef CONFIG_DMA_CACHE_RWFO + ldrb r2, [r0] @ read for ownership + strb r2, [r0] @ write for ownership +#endif tst r0, #D_CACHE_LINE_SIZE - 1 bic r0, r0, #D_CACHE_LINE_SIZE - 1 #ifdef HARVARD_CACHE @@ -204,6 +215,10 @@ v6_dma_inv_range: mcrne p15, 0, r0, c7, c11, 1 @ clean unified line #endif tst r1, #D_CACHE_LINE_SIZE - 1 +#ifdef CONFIG_DMA_CACHE_RWFO + ldrneb r2, [r1, #-1] @ read for ownership + strneb r2, [r1, #-1] @ write for ownership +#endif bic r1, r1, #D_CACHE_LINE_SIZE - 1 #ifdef HARVARD_CACHE mcrne p15, 0, r1, c7, c14, 1 @ clean & invalidate D line @@ -211,10 +226,6 @@ v6_dma_inv_range: mcrne p15, 0, r1, c7, c15, 1 @ clean & invalidate unified line #endif 1: -#ifdef CONFIG_DMA_CACHE_RWFO - ldr r2, [r0] @ read for ownership - str r2, [r0] @ write for ownership -#endif #ifdef HARVARD_CACHE mcr p15, 0, r0, c7, c6, 1 @ invalidate D line #else @@ -222,6 +233,10 @@ v6_dma_inv_range: #endif add r0, r0, #D_CACHE_LINE_SIZE cmp r0, r1 +#ifdef CONFIG_DMA_CACHE_RWFO + ldrlo r2, [r0] @ read for ownership + strlo r2, [r0] @ write for ownership +#endif blo 1b mov r0, #0 mcr p15, 0, r0, c7, c10, 4 @ drain write buffer @@ -256,12 +271,12 @@ v6_dma_clean_range: * - end - virtual end address of region */ ENTRY(v6_dma_flush_range) - bic r0, r0, #D_CACHE_LINE_SIZE - 1 -1: #ifdef CONFIG_DMA_CACHE_RWFO - ldr r2, [r0] @ read for ownership - str r2, [r0] @ write for ownership + ldrb r2, [r0] @ read for ownership + strb r2, [r0] @ write for ownership #endif + bic r0, r0, #D_CACHE_LINE_SIZE - 1 +1: #ifdef HARVARD_CACHE mcr p15, 0, r0, c7, c14, 1 @ clean & invalidate D line #else @@ -269,6 +284,10 @@ ENTRY(v6_dma_flush_range) #endif add r0, r0, #D_CACHE_LINE_SIZE cmp r0, r1 +#ifdef CONFIG_DMA_CACHE_RWFO + ldrlob r2, [r0] @ read for ownership + strlob r2, [r0] @ write for ownership +#endif blo 1b mov r0, #0 mcr p15, 0, r0, c7, c10, 4 @ drain write buffer @@ -312,6 +331,7 @@ ENDPROC(v6_dma_unmap_area) .type v6_cache_fns, #object ENTRY(v6_cache_fns) + .long v6_flush_icache_all .long v6_flush_kern_cache_all .long v6_flush_user_cache_all .long v6_flush_user_cache_range diff --git a/arch/arm/mm/cache-v7.S b/arch/arm/mm/cache-v7.S index 37c8157e116..6136e68ce95 100644 --- a/arch/arm/mm/cache-v7.S +++ b/arch/arm/mm/cache-v7.S @@ -18,6 +18,21 @@ #include "proc-macros.S" /* + * v7_flush_icache_all() + * + * Flush the whole I-cache. + * + * Registers: + * r0 - set to 0 + */ +ENTRY(v7_flush_icache_all) + mov r0, #0 + ALT_SMP(mcr p15, 0, r0, c7, c1, 0) @ invalidate I-cache inner shareable + ALT_UP(mcr p15, 0, r0, c7, c5, 0) @ I+BTB cache invalidate + mov pc, lr +ENDPROC(v7_flush_icache_all) + +/* * v7_flush_dcache_all() * * Flush the whole D-cache. @@ -91,11 +106,8 @@ ENTRY(v7_flush_kern_cache_all) THUMB( stmfd sp!, {r4-r7, r9-r11, lr} ) bl v7_flush_dcache_all mov r0, #0 -#ifdef CONFIG_SMP - mcr p15, 0, r0, c7, c1, 0 @ invalidate I-cache inner shareable -#else - mcr p15, 0, r0, c7, c5, 0 @ I+BTB cache invalidate -#endif + ALT_SMP(mcr p15, 0, r0, c7, c1, 0) @ invalidate I-cache inner shareable + ALT_UP(mcr p15, 0, r0, c7, c5, 0) @ I+BTB cache invalidate ARM( ldmfd sp!, {r4-r5, r7, r9-r11, lr} ) THUMB( ldmfd sp!, {r4-r7, r9-r11, lr} ) mov pc, lr @@ -161,21 +173,25 @@ ENTRY(v7_coherent_user_range) UNWIND(.fnstart ) dcache_line_size r2, r3 sub r3, r2, #1 - bic r0, r0, r3 + bic r12, r0, r3 1: - USER( mcr p15, 0, r0, c7, c11, 1 ) @ clean D line to the point of unification + USER( mcr p15, 0, r12, c7, c11, 1 ) @ clean D line to the point of unification + add r12, r12, r2 + cmp r12, r1 + blo 1b dsb - USER( mcr p15, 0, r0, c7, c5, 1 ) @ invalidate I line - add r0, r0, r2 + icache_line_size r2, r3 + sub r3, r2, #1 + bic r12, r0, r3 2: - cmp r0, r1 - blo 1b + USER( mcr p15, 0, r12, c7, c5, 1 ) @ invalidate I line + add r12, r12, r2 + cmp r12, r1 + blo 2b +3: mov r0, #0 -#ifdef CONFIG_SMP - mcr p15, 0, r0, c7, c1, 6 @ invalidate BTB Inner Shareable -#else - mcr p15, 0, r0, c7, c5, 6 @ invalidate BTB -#endif + ALT_SMP(mcr p15, 0, r0, c7, c1, 6) @ invalidate BTB Inner Shareable + ALT_UP(mcr p15, 0, r0, c7, c5, 6) @ invalidate BTB dsb isb mov pc, lr @@ -185,10 +201,10 @@ ENTRY(v7_coherent_user_range) * isn't mapped, just try the next page. */ 9001: - mov r0, r0, lsr #12 - mov r0, r0, lsl #12 - add r0, r0, #4096 - b 2b + mov r12, r12, lsr #12 + mov r12, r12, lsl #12 + add r12, r12, #4096 + b 3b UNWIND(.fnend ) ENDPROC(v7_coherent_kern_range) ENDPROC(v7_coherent_user_range) @@ -309,6 +325,7 @@ ENDPROC(v7_dma_unmap_area) .type v7_cache_fns, #object ENTRY(v7_cache_fns) + .long v7_flush_icache_all .long v7_flush_kern_cache_all .long v7_flush_user_cache_all .long v7_flush_user_cache_range diff --git a/arch/arm/mm/cache-xsc3l2.c b/arch/arm/mm/cache-xsc3l2.c index c3154928bcc..5a32020471e 100644 --- a/arch/arm/mm/cache-xsc3l2.c +++ b/arch/arm/mm/cache-xsc3l2.c @@ -17,14 +17,10 @@ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #include <linux/init.h> +#include <linux/highmem.h> #include <asm/system.h> #include <asm/cputype.h> #include <asm/cacheflush.h> -#include <asm/kmap_types.h> -#include <asm/fixmap.h> -#include <asm/pgtable.h> -#include <asm/tlbflush.h> -#include "mm.h" #define CR_L2 (1 << 26) @@ -71,16 +67,15 @@ static inline void xsc3_l2_inv_all(void) dsb(); } +static inline void l2_unmap_va(unsigned long va) +{ #ifdef CONFIG_HIGHMEM -#define l2_map_save_flags(x) raw_local_save_flags(x) -#define l2_map_restore_flags(x) raw_local_irq_restore(x) -#else -#define l2_map_save_flags(x) ((x) = 0) -#define l2_map_restore_flags(x) ((void)(x)) + if (va != -1) + kunmap_atomic((void *)va); #endif +} -static inline unsigned long l2_map_va(unsigned long pa, unsigned long prev_va, - unsigned long flags) +static inline unsigned long l2_map_va(unsigned long pa, unsigned long prev_va) { #ifdef CONFIG_HIGHMEM unsigned long va = prev_va & PAGE_MASK; @@ -89,17 +84,10 @@ static inline unsigned long l2_map_va(unsigned long pa, unsigned long prev_va, /* * Switching to a new page. Because cache ops are * using virtual addresses only, we must put a mapping - * in place for it. We also enable interrupts for a - * short while and disable them again to protect this - * mapping. + * in place for it. */ - unsigned long idx; - raw_local_irq_restore(flags); - idx = KM_L2_CACHE + KM_TYPE_NR * smp_processor_id(); - va = __fix_to_virt(FIX_KMAP_BEGIN + idx); - raw_local_irq_restore(flags | PSR_I_BIT); - set_pte_ext(TOP_PTE(va), pfn_pte(pa >> PAGE_SHIFT, PAGE_KERNEL), 0); - local_flush_tlb_kernel_page(va); + l2_unmap_va(prev_va); + va = (unsigned long)kmap_atomic_pfn(pa >> PAGE_SHIFT); } return va + (pa_offset >> (32 - PAGE_SHIFT)); #else @@ -109,7 +97,7 @@ static inline unsigned long l2_map_va(unsigned long pa, unsigned long prev_va, static void xsc3_l2_inv_range(unsigned long start, unsigned long end) { - unsigned long vaddr, flags; + unsigned long vaddr; if (start == 0 && end == -1ul) { xsc3_l2_inv_all(); @@ -117,13 +105,12 @@ static void xsc3_l2_inv_range(unsigned long start, unsigned long end) } vaddr = -1; /* to force the first mapping */ - l2_map_save_flags(flags); /* * Clean and invalidate partial first cache line. */ if (start & (CACHE_LINE_SIZE - 1)) { - vaddr = l2_map_va(start & ~(CACHE_LINE_SIZE - 1), vaddr, flags); + vaddr = l2_map_va(start & ~(CACHE_LINE_SIZE - 1), vaddr); xsc3_l2_clean_mva(vaddr); xsc3_l2_inv_mva(vaddr); start = (start | (CACHE_LINE_SIZE - 1)) + 1; @@ -133,7 +120,7 @@ static void xsc3_l2_inv_range(unsigned long start, unsigned long end) * Invalidate all full cache lines between 'start' and 'end'. */ while (start < (end & ~(CACHE_LINE_SIZE - 1))) { - vaddr = l2_map_va(start, vaddr, flags); + vaddr = l2_map_va(start, vaddr); xsc3_l2_inv_mva(vaddr); start += CACHE_LINE_SIZE; } @@ -142,31 +129,30 @@ static void xsc3_l2_inv_range(unsigned long start, unsigned long end) * Clean and invalidate partial last cache line. */ if (start < end) { - vaddr = l2_map_va(start, vaddr, flags); + vaddr = l2_map_va(start, vaddr); xsc3_l2_clean_mva(vaddr); xsc3_l2_inv_mva(vaddr); } - l2_map_restore_flags(flags); + l2_unmap_va(vaddr); dsb(); } static void xsc3_l2_clean_range(unsigned long start, unsigned long end) { - unsigned long vaddr, flags; + unsigned long vaddr; vaddr = -1; /* to force the first mapping */ - l2_map_save_flags(flags); start &= ~(CACHE_LINE_SIZE - 1); while (start < end) { - vaddr = l2_map_va(start, vaddr, flags); + vaddr = l2_map_va(start, vaddr); xsc3_l2_clean_mva(vaddr); start += CACHE_LINE_SIZE; } - l2_map_restore_flags(flags); + l2_unmap_va(vaddr); dsb(); } @@ -193,7 +179,7 @@ static inline void xsc3_l2_flush_all(void) static void xsc3_l2_flush_range(unsigned long start, unsigned long end) { - unsigned long vaddr, flags; + unsigned long vaddr; if (start == 0 && end == -1ul) { xsc3_l2_flush_all(); @@ -201,17 +187,16 @@ static void xsc3_l2_flush_range(unsigned long start, unsigned long end) } vaddr = -1; /* to force the first mapping */ - l2_map_save_flags(flags); start &= ~(CACHE_LINE_SIZE - 1); while (start < end) { - vaddr = l2_map_va(start, vaddr, flags); + vaddr = l2_map_va(start, vaddr); xsc3_l2_clean_mva(vaddr); xsc3_l2_inv_mva(vaddr); start += CACHE_LINE_SIZE; } - l2_map_restore_flags(flags); + l2_unmap_va(vaddr); dsb(); } diff --git a/arch/arm/mm/copypage-v4mc.c b/arch/arm/mm/copypage-v4mc.c index 598c51ad507..b8061519ce7 100644 --- a/arch/arm/mm/copypage-v4mc.c +++ b/arch/arm/mm/copypage-v4mc.c @@ -73,7 +73,7 @@ void v4_mc_copy_user_highpage(struct page *to, struct page *from, { void *kto = kmap_atomic(to, KM_USER1); - if (test_and_clear_bit(PG_dcache_dirty, &from->flags)) + if (!test_and_set_bit(PG_dcache_clean, &from->flags)) __flush_dcache_page(page_mapping(from), from); spin_lock(&minicache_lock); diff --git a/arch/arm/mm/copypage-v6.c b/arch/arm/mm/copypage-v6.c index f55fa1044f7..bdba6c65c90 100644 --- a/arch/arm/mm/copypage-v6.c +++ b/arch/arm/mm/copypage-v6.c @@ -79,7 +79,7 @@ static void v6_copy_user_highpage_aliasing(struct page *to, unsigned int offset = CACHE_COLOUR(vaddr); unsigned long kfrom, kto; - if (test_and_clear_bit(PG_dcache_dirty, &from->flags)) + if (!test_and_set_bit(PG_dcache_clean, &from->flags)) __flush_dcache_page(page_mapping(from), from); /* FIXME: not highmem safe */ diff --git a/arch/arm/mm/copypage-xscale.c b/arch/arm/mm/copypage-xscale.c index 9920c0ae209..649bbcd325b 100644 --- a/arch/arm/mm/copypage-xscale.c +++ b/arch/arm/mm/copypage-xscale.c @@ -95,7 +95,7 @@ void xscale_mc_copy_user_highpage(struct page *to, struct page *from, { void *kto = kmap_atomic(to, KM_USER1); - if (test_and_clear_bit(PG_dcache_dirty, &from->flags)) + if (!test_and_set_bit(PG_dcache_clean, &from->flags)) __flush_dcache_page(page_mapping(from), from); spin_lock(&minicache_lock); diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c index 4bc43e535d3..809f1bf9fa2 100644 --- a/arch/arm/mm/dma-mapping.c +++ b/arch/arm/mm/dma-mapping.c @@ -17,6 +17,7 @@ #include <linux/init.h> #include <linux/device.h> #include <linux/dma-mapping.h> +#include <linux/highmem.h> #include <asm/memory.h> #include <asm/highmem.h> @@ -198,7 +199,7 @@ __dma_alloc_remap(struct page *page, size_t size, gfp_t gfp, pgprot_t prot) * fragmentation of the DMA space, and also prevents allocations * smaller than a section from crossing a section boundary. */ - bit = fls(size - 1) + 1; + bit = fls(size - 1); if (bit > SECTION_SHIFT) bit = SECTION_SHIFT; align = 1 << bit; @@ -480,10 +481,10 @@ static void dma_cache_maint_page(struct page *page, unsigned long offset, op(vaddr, len, dir); kunmap_high(page); } else if (cache_is_vipt()) { - pte_t saved_pte; - vaddr = kmap_high_l1_vipt(page, &saved_pte); + /* unmapped pages might still be cached */ + vaddr = kmap_atomic(page); op(vaddr + offset, len, dir); - kunmap_high_l1_vipt(page, saved_pte); + kunmap_atomic(vaddr); } } else { vaddr = page_address(page) + offset; @@ -523,6 +524,12 @@ void ___dma_page_dev_to_cpu(struct page *page, unsigned long off, outer_inv_range(paddr, paddr + size); dma_cache_maint_page(page, off, size, dir, dmac_unmap_area); + + /* + * Mark the D-cache clean for this page to avoid extra flushing. + */ + if (dir != DMA_TO_DEVICE && off == 0 && size >= PAGE_SIZE) + set_bit(PG_dcache_clean, &page->flags); } EXPORT_SYMBOL(___dma_page_dev_to_cpu); diff --git a/arch/arm/mm/fault-armv.c b/arch/arm/mm/fault-armv.c index 9b906dec1ca..83e59f87042 100644 --- a/arch/arm/mm/fault-armv.c +++ b/arch/arm/mm/fault-armv.c @@ -28,6 +28,7 @@ static unsigned long shared_pte_mask = L_PTE_MT_BUFFERABLE; +#if __LINUX_ARM_ARCH__ < 6 /* * We take the easy way out of this problem - we make the * PTE uncacheable. However, we leave the write buffer on. @@ -65,6 +66,30 @@ static int do_adjust_pte(struct vm_area_struct *vma, unsigned long address, return ret; } +#if USE_SPLIT_PTLOCKS +/* + * If we are using split PTE locks, then we need to take the page + * lock here. Otherwise we are using shared mm->page_table_lock + * which is already locked, thus cannot take it. + */ +static inline void do_pte_lock(spinlock_t *ptl) +{ + /* + * Use nested version here to indicate that we are already + * holding one similar spinlock. + */ + spin_lock_nested(ptl, SINGLE_DEPTH_NESTING); +} + +static inline void do_pte_unlock(spinlock_t *ptl) +{ + spin_unlock(ptl); +} +#else /* !USE_SPLIT_PTLOCKS */ +static inline void do_pte_lock(spinlock_t *ptl) {} +static inline void do_pte_unlock(spinlock_t *ptl) {} +#endif /* USE_SPLIT_PTLOCKS */ + static int adjust_pte(struct vm_area_struct *vma, unsigned long address, unsigned long pfn) { @@ -88,13 +113,13 @@ static int adjust_pte(struct vm_area_struct *vma, unsigned long address, * open-code the spin-locking. */ ptl = pte_lockptr(vma->vm_mm, pmd); - pte = pte_offset_map_nested(pmd, address); - spin_lock(ptl); + pte = pte_offset_map(pmd, address); + do_pte_lock(ptl); ret = do_adjust_pte(vma, address, pfn, pte); - spin_unlock(ptl); - pte_unmap_nested(pte); + do_pte_unlock(ptl); + pte_unmap(pte); return ret; } @@ -141,7 +166,7 @@ make_coherent(struct address_space *mapping, struct vm_area_struct *vma, * a page table, or changing an existing PTE. Basically, there are two * things that we need to take care of: * - * 1. If PG_dcache_dirty is set for the page, we need to ensure + * 1. If PG_dcache_clean is not set for the page, we need to ensure * that any cache entries for the kernels virtual memory * range are written back to the page. * 2. If we have multiple shared mappings of the same space in @@ -168,10 +193,8 @@ void update_mmu_cache(struct vm_area_struct *vma, unsigned long addr, return; mapping = page_mapping(page); -#ifndef CONFIG_SMP - if (test_and_clear_bit(PG_dcache_dirty, &page->flags)) + if (!test_and_set_bit(PG_dcache_clean, &page->flags)) __flush_dcache_page(mapping, page); -#endif if (mapping) { if (cache_is_vivt()) make_coherent(mapping, vma, addr, ptep, pfn); @@ -179,6 +202,7 @@ void update_mmu_cache(struct vm_area_struct *vma, unsigned long addr, __flush_icache_all(); } } +#endif /* __LINUX_ARM_ARCH__ < 6 */ /* * Check whether the write buffer has physical address aliasing diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c index 23b0b03af5e..1e21e125fe3 100644 --- a/arch/arm/mm/fault.c +++ b/arch/arm/mm/fault.c @@ -581,6 +581,19 @@ static struct fsr_info ifsr_info[] = { { do_bad, SIGBUS, 0, "unknown 31" }, }; +void __init +hook_ifault_code(int nr, int (*fn)(unsigned long, unsigned int, struct pt_regs *), + int sig, int code, const char *name) +{ + if (nr < 0 || nr >= ARRAY_SIZE(ifsr_info)) + BUG(); + + ifsr_info[nr].fn = fn; + ifsr_info[nr].sig = sig; + ifsr_info[nr].code = code; + ifsr_info[nr].name = name; +} + asmlinkage void __exception do_PrefetchAbort(unsigned long addr, unsigned int ifsr, struct pt_regs *regs) { diff --git a/arch/arm/mm/flush.c b/arch/arm/mm/flush.c index c6844cb9b50..c29f2839f1d 100644 --- a/arch/arm/mm/flush.c +++ b/arch/arm/mm/flush.c @@ -10,6 +10,7 @@ #include <linux/module.h> #include <linux/mm.h> #include <linux/pagemap.h> +#include <linux/highmem.h> #include <asm/cacheflush.h> #include <asm/cachetype.h> @@ -17,6 +18,7 @@ #include <asm/smp_plat.h> #include <asm/system.h> #include <asm/tlbflush.h> +#include <asm/smp_plat.h> #include "mm.h" @@ -39,6 +41,18 @@ static void flush_pfn_alias(unsigned long pfn, unsigned long vaddr) : "cc"); } +static void flush_icache_alias(unsigned long pfn, unsigned long vaddr, unsigned long len) +{ + unsigned long colour = CACHE_COLOUR(vaddr); + unsigned long offset = vaddr & (PAGE_SIZE - 1); + unsigned long to; + + set_pte_ext(TOP_PTE(ALIAS_FLUSH_START) + colour, pfn_pte(pfn, PAGE_KERNEL), 0); + to = ALIAS_FLUSH_START + (colour << PAGE_SHIFT) + offset; + flush_tlb_kernel_page(to); + flush_icache_range(to, to + len); +} + void flush_cache_mm(struct mm_struct *mm) { if (cache_is_vivt()) { @@ -89,16 +103,16 @@ void flush_cache_page(struct vm_area_struct *vma, unsigned long user_addr, unsig if (vma->vm_flags & VM_EXEC && icache_is_vivt_asid_tagged()) __flush_icache_all(); } + #else -#define flush_pfn_alias(pfn,vaddr) do { } while (0) +#define flush_pfn_alias(pfn,vaddr) do { } while (0) +#define flush_icache_alias(pfn,vaddr,len) do { } while (0) #endif -#ifdef CONFIG_SMP static void flush_ptrace_access_other(void *args) { __flush_icache_all(); } -#endif static void flush_ptrace_access(struct vm_area_struct *vma, struct page *page, @@ -118,15 +132,16 @@ void flush_ptrace_access(struct vm_area_struct *vma, struct page *page, return; } - /* VIPT non-aliasing cache */ + /* VIPT non-aliasing D-cache */ if (vma->vm_flags & VM_EXEC) { unsigned long addr = (unsigned long)kaddr; - __cpuc_coherent_kern_range(addr, addr + len); -#ifdef CONFIG_SMP + if (icache_is_vipt_aliasing()) + flush_icache_alias(page_to_pfn(page), uaddr, len); + else + __cpuc_coherent_kern_range(addr, addr + len); if (cache_ops_need_broadcast()) smp_call_function(flush_ptrace_access_other, NULL, 1); -#endif } } @@ -166,10 +181,10 @@ void __flush_dcache_page(struct address_space *mapping, struct page *page) __cpuc_flush_dcache_area(addr, PAGE_SIZE); kunmap_high(page); } else if (cache_is_vipt()) { - pte_t saved_pte; - addr = kmap_high_l1_vipt(page, &saved_pte); + /* unmapped pages might still be cached */ + addr = kmap_atomic(page); __cpuc_flush_dcache_area(addr, PAGE_SIZE); - kunmap_high_l1_vipt(page, saved_pte); + kunmap_atomic(addr); } } @@ -215,6 +230,36 @@ static void __flush_dcache_aliases(struct address_space *mapping, struct page *p flush_dcache_mmap_unlock(mapping); } +#if __LINUX_ARM_ARCH__ >= 6 +void __sync_icache_dcache(pte_t pteval) +{ + unsigned long pfn; + struct page *page; + struct address_space *mapping; + + if (!pte_present_user(pteval)) + return; + if (cache_is_vipt_nonaliasing() && !pte_exec(pteval)) + /* only flush non-aliasing VIPT caches for exec mappings */ + return; + pfn = pte_pfn(pteval); + if (!pfn_valid(pfn)) + return; + + page = pfn_to_page(pfn); + if (cache_is_vipt_aliasing()) + mapping = page_mapping(page); + else + mapping = NULL; + + if (!test_and_set_bit(PG_dcache_clean, &page->flags)) + __flush_dcache_page(mapping, page); + /* pte_exec() already checked above for non-aliasing VIPT cache */ + if (cache_is_vipt_nonaliasing() || pte_exec(pteval)) + __flush_icache_all(); +} +#endif + /* * Ensure cache coherency between kernel mapping and userspace mapping * of this page. @@ -246,17 +291,16 @@ void flush_dcache_page(struct page *page) mapping = page_mapping(page); -#ifndef CONFIG_SMP - if (!PageHighMem(page) && mapping && !mapping_mapped(mapping)) - set_bit(PG_dcache_dirty, &page->flags); - else -#endif - { + if (!cache_ops_need_broadcast() && + mapping && !mapping_mapped(mapping)) + clear_bit(PG_dcache_clean, &page->flags); + else { __flush_dcache_page(mapping, page); if (mapping && cache_is_vivt()) __flush_dcache_aliases(mapping, page); else if (mapping) __flush_icache_all(); + set_bit(PG_dcache_clean, &page->flags); } } EXPORT_SYMBOL(flush_dcache_page); diff --git a/arch/arm/mm/highmem.c b/arch/arm/mm/highmem.c index 1fbdb55bfd1..807c0573abb 100644 --- a/arch/arm/mm/highmem.c +++ b/arch/arm/mm/highmem.c @@ -36,18 +36,17 @@ void kunmap(struct page *page) } EXPORT_SYMBOL(kunmap); -void *kmap_atomic(struct page *page, enum km_type type) +void *__kmap_atomic(struct page *page) { unsigned int idx; unsigned long vaddr; void *kmap; + int type; pagefault_disable(); if (!PageHighMem(page)) return page_address(page); - debug_kmap_atomic(type); - #ifdef CONFIG_DEBUG_HIGHMEM /* * There is no cache coherency issue when non VIVT, so force the @@ -61,6 +60,8 @@ void *kmap_atomic(struct page *page, enum km_type type) if (kmap) return kmap; + type = kmap_atomic_idx_push(); + idx = type + KM_TYPE_NR * smp_processor_id(); vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx); #ifdef CONFIG_DEBUG_HIGHMEM @@ -80,14 +81,17 @@ void *kmap_atomic(struct page *page, enum km_type type) return (void *)vaddr; } -EXPORT_SYMBOL(kmap_atomic); +EXPORT_SYMBOL(__kmap_atomic); -void kunmap_atomic_notypecheck(void *kvaddr, enum km_type type) +void __kunmap_atomic(void *kvaddr) { unsigned long vaddr = (unsigned long) kvaddr & PAGE_MASK; - unsigned int idx = type + KM_TYPE_NR * smp_processor_id(); + int idx, type; if (kvaddr >= (void *)FIXADDR_START) { + type = kmap_atomic_idx(); + idx = type + KM_TYPE_NR * smp_processor_id(); + if (cache_is_vivt()) __cpuc_flush_dcache_area((void *)vaddr, PAGE_SIZE); #ifdef CONFIG_DEBUG_HIGHMEM @@ -97,21 +101,23 @@ void kunmap_atomic_notypecheck(void *kvaddr, enum km_type type) #else (void) idx; /* to kill a warning */ #endif + kmap_atomic_idx_pop(); } else if (vaddr >= PKMAP_ADDR(0) && vaddr < PKMAP_ADDR(LAST_PKMAP)) { /* this address was obtained through kmap_high_get() */ kunmap_high(pte_page(pkmap_page_table[PKMAP_NR(vaddr)])); } pagefault_enable(); } -EXPORT_SYMBOL(kunmap_atomic_notypecheck); +EXPORT_SYMBOL(__kunmap_atomic); -void *kmap_atomic_pfn(unsigned long pfn, enum km_type type) +void *kmap_atomic_pfn(unsigned long pfn) { - unsigned int idx; unsigned long vaddr; + int idx, type; pagefault_disable(); + type = kmap_atomic_idx_push(); idx = type + KM_TYPE_NR * smp_processor_id(); vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx); #ifdef CONFIG_DEBUG_HIGHMEM @@ -134,90 +140,3 @@ struct page *kmap_atomic_to_page(const void *ptr) pte = TOP_PTE(vaddr); return pte_page(*pte); } - -#ifdef CONFIG_CPU_CACHE_VIPT - -#include <linux/percpu.h> - -/* - * The VIVT cache of a highmem page is always flushed before the page - * is unmapped. Hence unmapped highmem pages need no cache maintenance - * in that case. - * - * However unmapped pages may still be cached with a VIPT cache, and - * it is not possible to perform cache maintenance on them using physical - * addresses unfortunately. So we have no choice but to set up a temporary - * virtual mapping for that purpose. - * - * Yet this VIPT cache maintenance may be triggered from DMA support - * functions which are possibly called from interrupt context. As we don't - * want to keep interrupt disabled all the time when such maintenance is - * taking place, we therefore allow for some reentrancy by preserving and - * restoring the previous fixmap entry before the interrupted context is - * resumed. If the reentrancy depth is 0 then there is no need to restore - * the previous fixmap, and leaving the current one in place allow it to - * be reused the next time without a TLB flush (common with DMA). - */ - -static DEFINE_PER_CPU(int, kmap_high_l1_vipt_depth); - -void *kmap_high_l1_vipt(struct page *page, pte_t *saved_pte) -{ - unsigned int idx, cpu; - int *depth; - unsigned long vaddr, flags; - pte_t pte, *ptep; - - if (!in_interrupt()) - preempt_disable(); - - cpu = smp_processor_id(); - depth = &per_cpu(kmap_high_l1_vipt_depth, cpu); - - idx = KM_L1_CACHE + KM_TYPE_NR * cpu; - vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx); - ptep = TOP_PTE(vaddr); - pte = mk_pte(page, kmap_prot); - - raw_local_irq_save(flags); - (*depth)++; - if (pte_val(*ptep) == pte_val(pte)) { - *saved_pte = pte; - } else { - *saved_pte = *ptep; - set_pte_ext(ptep, pte, 0); - local_flush_tlb_kernel_page(vaddr); - } - raw_local_irq_restore(flags); - - return (void *)vaddr; -} - -void kunmap_high_l1_vipt(struct page *page, pte_t saved_pte) -{ - unsigned int idx, cpu = smp_processor_id(); - int *depth = &per_cpu(kmap_high_l1_vipt_depth, cpu); - unsigned long vaddr, flags; - pte_t pte, *ptep; - - idx = KM_L1_CACHE + KM_TYPE_NR * cpu; - vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx); - ptep = TOP_PTE(vaddr); - pte = mk_pte(page, kmap_prot); - - BUG_ON(pte_val(*ptep) != pte_val(pte)); - BUG_ON(*depth <= 0); - - raw_local_irq_save(flags); - (*depth)--; - if (*depth != 0 && pte_val(pte) != pte_val(saved_pte)) { - set_pte_ext(ptep, saved_pte, 0); - local_flush_tlb_kernel_page(vaddr); - } - raw_local_irq_restore(flags); - - if (!in_interrupt()) - preempt_enable(); -} - -#endif /* CONFIG_CPU_CACHE_VIPT */ diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c index 7185b00650f..5164069ced4 100644 --- a/arch/arm/mm/init.c +++ b/arch/arm/mm/init.c @@ -18,6 +18,7 @@ #include <linux/highmem.h> #include <linux/gfp.h> #include <linux/memblock.h> +#include <linux/sort.h> #include <asm/mach-types.h> #include <asm/sections.h> @@ -121,9 +122,10 @@ void show_mem(void) printk("%d pages swap cached\n", cached); } -static void __init find_limits(struct meminfo *mi, - unsigned long *min, unsigned long *max_low, unsigned long *max_high) +static void __init find_limits(unsigned long *min, unsigned long *max_low, + unsigned long *max_high) { + struct meminfo *mi = &meminfo; int i; *min = -1UL; @@ -147,13 +149,13 @@ static void __init find_limits(struct meminfo *mi, } } -static void __init arm_bootmem_init(struct meminfo *mi, - unsigned long start_pfn, unsigned long end_pfn) +static void __init arm_bootmem_init(unsigned long start_pfn, + unsigned long end_pfn) { + struct memblock_region *reg; unsigned int boot_pages; phys_addr_t bitmap; pg_data_t *pgdat; - int i; /* * Allocate the bootmem bitmap page. This must be in a region @@ -171,30 +173,39 @@ static void __init arm_bootmem_init(struct meminfo *mi, pgdat = NODE_DATA(0); init_bootmem_node(pgdat, __phys_to_pfn(bitmap), start_pfn, end_pfn); - for_each_bank(i, mi) { - struct membank *bank = &mi->bank[i]; - if (!bank->highmem) - free_bootmem(bank_phys_start(bank), bank_phys_size(bank)); + /* Free the lowmem regions from memblock into bootmem. */ + for_each_memblock(memory, reg) { + unsigned long start = memblock_region_memory_base_pfn(reg); + unsigned long end = memblock_region_memory_end_pfn(reg); + + if (end >= end_pfn) + end = end_pfn; + if (start >= end) + break; + + free_bootmem(__pfn_to_phys(start), (end - start) << PAGE_SHIFT); } - /* - * Reserve the memblock reserved regions in bootmem. - */ - for (i = 0; i < memblock.reserved.cnt; i++) { - phys_addr_t start = memblock_start_pfn(&memblock.reserved, i); - if (start >= start_pfn && - memblock_end_pfn(&memblock.reserved, i) <= end_pfn) - reserve_bootmem_node(pgdat, __pfn_to_phys(start), - memblock_size_bytes(&memblock.reserved, i), - BOOTMEM_DEFAULT); + /* Reserve the lowmem memblock reserved regions in bootmem. */ + for_each_memblock(reserved, reg) { + unsigned long start = memblock_region_reserved_base_pfn(reg); + unsigned long end = memblock_region_reserved_end_pfn(reg); + + if (end >= end_pfn) + end = end_pfn; + if (start >= end) + break; + + reserve_bootmem(__pfn_to_phys(start), + (end - start) << PAGE_SHIFT, BOOTMEM_DEFAULT); } } -static void __init arm_bootmem_free(struct meminfo *mi, unsigned long min, - unsigned long max_low, unsigned long max_high) +static void __init arm_bootmem_free(unsigned long min, unsigned long max_low, + unsigned long max_high) { unsigned long zone_size[MAX_NR_ZONES], zhole_size[MAX_NR_ZONES]; - int i; + struct memblock_region *reg; /* * initialise the zones. @@ -216,13 +227,20 @@ static void __init arm_bootmem_free(struct meminfo *mi, unsigned long min, * holes = node_size - sum(bank_sizes) */ memcpy(zhole_size, zone_size, sizeof(zhole_size)); - for_each_bank(i, mi) { - int idx = 0; + for_each_memblock(memory, reg) { + unsigned long start = memblock_region_memory_base_pfn(reg); + unsigned long end = memblock_region_memory_end_pfn(reg); + + if (start < max_low) { + unsigned long low_end = min(end, max_low); + zhole_size[0] -= low_end - start; + } #ifdef CONFIG_HIGHMEM - if (mi->bank[i].highmem) - idx = ZONE_HIGHMEM; + if (end > max_low) { + unsigned long high_start = max(start, max_low); + zhole_size[ZONE_HIGHMEM] -= end - high_start; + } #endif - zhole_size[idx] -= bank_pfn_size(&mi->bank[i]); } /* @@ -237,20 +255,7 @@ static void __init arm_bootmem_free(struct meminfo *mi, unsigned long min, #ifndef CONFIG_SPARSEMEM int pfn_valid(unsigned long pfn) { - struct memblock_region *mem = &memblock.memory; - unsigned int left = 0, right = mem->cnt; - - do { - unsigned int mid = (right + left) / 2; - - if (pfn < memblock_start_pfn(mem, mid)) - right = mid; - else if (pfn >= memblock_end_pfn(mem, mid)) - left = mid + 1; - else - return 1; - } while (left < right); - return 0; + return memblock_is_memory(pfn << PAGE_SHIFT); } EXPORT_SYMBOL(pfn_valid); @@ -260,24 +265,34 @@ static void arm_memory_present(void) #else static void arm_memory_present(void) { - int i; - for (i = 0; i < memblock.memory.cnt; i++) - memory_present(0, memblock_start_pfn(&memblock.memory, i), - memblock_end_pfn(&memblock.memory, i)); + struct memblock_region *reg; + + for_each_memblock(memory, reg) + memory_present(0, memblock_region_memory_base_pfn(reg), + memblock_region_memory_end_pfn(reg)); } #endif +static int __init meminfo_cmp(const void *_a, const void *_b) +{ + const struct membank *a = _a, *b = _b; + long cmp = bank_pfn_start(a) - bank_pfn_start(b); + return cmp < 0 ? -1 : cmp > 0 ? 1 : 0; +} + void __init arm_memblock_init(struct meminfo *mi, struct machine_desc *mdesc) { int i; + sort(&meminfo.bank, meminfo.nr_banks, sizeof(meminfo.bank[0]), meminfo_cmp, NULL); + memblock_init(); for (i = 0; i < mi->nr_banks; i++) memblock_add(mi->bank[i].start, mi->bank[i].size); /* Register the kernel text, kernel data and initrd with memblock. */ #ifdef CONFIG_XIP_KERNEL - memblock_reserve(__pa(_data), _end - _data); + memblock_reserve(__pa(_sdata), _end - _sdata); #else memblock_reserve(__pa(_stext), _end - _stext); #endif @@ -303,14 +318,13 @@ void __init arm_memblock_init(struct meminfo *mi, struct machine_desc *mdesc) void __init bootmem_init(void) { - struct meminfo *mi = &meminfo; unsigned long min, max_low, max_high; max_low = max_high = 0; - find_limits(mi, &min, &max_low, &max_high); + find_limits(&min, &max_low, &max_high); - arm_bootmem_init(mi, min, max_low); + arm_bootmem_init(min, max_low); /* * Sparsemem tries to allocate bootmem in memory_present(), @@ -328,7 +342,7 @@ void __init bootmem_init(void) * the sparse mem_map arrays initialized by sparse_init() * for memmap_init_zone(), otherwise all PFNs are invalid. */ - arm_bootmem_free(mi, min, max_low, max_high); + arm_bootmem_free(min, max_low, max_high); high_memory = __va((max_low << PAGE_SHIFT) - 1) + 1; @@ -422,6 +436,56 @@ static void __init free_unused_memmap(struct meminfo *mi) } } +static void __init free_highpages(void) +{ +#ifdef CONFIG_HIGHMEM + unsigned long max_low = max_low_pfn + PHYS_PFN_OFFSET; + struct memblock_region *mem, *res; + + /* set highmem page free */ + for_each_memblock(memory, mem) { + unsigned long start = memblock_region_memory_base_pfn(mem); + unsigned long end = memblock_region_memory_end_pfn(mem); + + /* Ignore complete lowmem entries */ + if (end <= max_low) + continue; + + /* Truncate partial highmem entries */ + if (start < max_low) + start = max_low; + + /* Find and exclude any reserved regions */ + for_each_memblock(reserved, res) { + unsigned long res_start, res_end; + + res_start = memblock_region_reserved_base_pfn(res); + res_end = memblock_region_reserved_end_pfn(res); + + if (res_end < start) + continue; + if (res_start < start) + res_start = start; + if (res_start > end) + res_start = end; + if (res_end > end) + res_end = end; + if (res_start != start) + totalhigh_pages += free_area(start, res_start, + NULL); + start = res_end; + if (start == end) + break; + } + + /* And now free anything which remains */ + if (start < end) + totalhigh_pages += free_area(start, end, NULL); + } + totalram_pages += totalhigh_pages; +#endif +} + /* * mem_init() marks the free areas in the mem_map and tells us how much * memory is free. This is done after various parts of the system have @@ -430,6 +494,7 @@ static void __init free_unused_memmap(struct meminfo *mi) void __init mem_init(void) { unsigned long reserved_pages, free_pages; + struct memblock_region *reg; int i; #ifdef CONFIG_HAVE_TCM /* These pointers are filled in on TCM detection */ @@ -450,16 +515,7 @@ void __init mem_init(void) __phys_to_pfn(__pa(swapper_pg_dir)), NULL); #endif -#ifdef CONFIG_HIGHMEM - /* set highmem page free */ - for_each_bank (i, &meminfo) { - unsigned long start = bank_pfn_start(&meminfo.bank[i]); - unsigned long end = bank_pfn_end(&meminfo.bank[i]); - if (start >= max_low_pfn + PHYS_PFN_OFFSET) - totalhigh_pages += free_area(start, end, NULL); - } - totalram_pages += totalhigh_pages; -#endif + free_highpages(); reserved_pages = free_pages = 0; @@ -489,9 +545,11 @@ void __init mem_init(void) */ printk(KERN_INFO "Memory:"); num_physpages = 0; - for (i = 0; i < meminfo.nr_banks; i++) { - num_physpages += bank_pfn_size(&meminfo.bank[i]); - printk(" %ldMB", bank_phys_size(&meminfo.bank[i]) >> 20); + for_each_memblock(memory, reg) { + unsigned long pages = memblock_region_memory_end_pfn(reg) - + memblock_region_memory_base_pfn(reg); + num_physpages += pages; + printk(" %ldMB", pages >> (20 - PAGE_SHIFT)); } printk(" = %luMB total\n", num_physpages >> (20 - PAGE_SHIFT)); @@ -545,7 +603,7 @@ void __init mem_init(void) MLK_ROUNDUP(__init_begin, __init_end), MLK_ROUNDUP(_text, _etext), - MLK_ROUNDUP(_data, _edata)); + MLK_ROUNDUP(_sdata, _edata)); #undef MLK #undef MLM diff --git a/arch/arm/mm/ioremap.c b/arch/arm/mm/ioremap.c index 17e7b0b57e4..55c17a6fb22 100644 --- a/arch/arm/mm/ioremap.c +++ b/arch/arm/mm/ioremap.c @@ -206,8 +206,8 @@ void __iomem * __arm_ioremap_pfn_caller(unsigned long pfn, */ if (pfn_valid(pfn)) { printk(KERN_WARNING "BUG: Your driver calls ioremap() on system memory. This leads\n" - KERN_WARNING "to architecturally unpredictable behaviour on ARMv6+, and ioremap()\n" - KERN_WARNING "will fail in the next kernel release. Please fix your driver.\n"); + "to architecturally unpredictable behaviour on ARMv6+, and ioremap()\n" + "will fail in the next kernel release. Please fix your driver.\n"); WARN_ON(1); } diff --git a/arch/arm/mm/mmap.c b/arch/arm/mm/mmap.c index 4f5b39687df..b0a98305055 100644 --- a/arch/arm/mm/mmap.c +++ b/arch/arm/mm/mmap.c @@ -144,3 +144,25 @@ int valid_mmap_phys_addr_range(unsigned long pfn, size_t size) { return !(pfn + (size >> PAGE_SHIFT) > 0x00100000); } + +#ifdef CONFIG_STRICT_DEVMEM + +#include <linux/ioport.h> + +/* + * devmem_is_allowed() checks to see if /dev/mem access to a certain + * address is valid. The argument is a physical page number. + * We mimic x86 here by disallowing access to system RAM as well as + * device-exclusive MMIO regions. This effectively disable read()/write() + * on /dev/mem. + */ +int devmem_is_allowed(unsigned long pfn) +{ + if (iomem_is_exclusive(pfn << PAGE_SHIFT)) + return 0; + if (!page_is_ram(pfn)) + return 1; + return 0; +} + +#endif diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c index e8ed9dc461f..72ad3e1f56c 100644 --- a/arch/arm/mm/mmu.c +++ b/arch/arm/mm/mmu.c @@ -14,7 +14,6 @@ #include <linux/mman.h> #include <linux/nodemask.h> #include <linux/memblock.h> -#include <linux/sort.h> #include <linux/fs.h> #include <asm/cputype.h> @@ -265,17 +264,17 @@ static struct mem_type mem_types[] = { .domain = DOMAIN_KERNEL, }, [MT_MEMORY_DTCM] = { - .prot_pte = L_PTE_PRESENT | L_PTE_YOUNG | - L_PTE_DIRTY | L_PTE_WRITE, - .prot_l1 = PMD_TYPE_TABLE, - .prot_sect = PMD_TYPE_SECT | PMD_SECT_XN, - .domain = DOMAIN_KERNEL, + .prot_pte = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY | + L_PTE_WRITE, + .prot_l1 = PMD_TYPE_TABLE, + .prot_sect = PMD_TYPE_SECT | PMD_SECT_XN, + .domain = DOMAIN_KERNEL, }, [MT_MEMORY_ITCM] = { .prot_pte = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY | - L_PTE_USER | L_PTE_EXEC, + L_PTE_WRITE | L_PTE_EXEC, .prot_l1 = PMD_TYPE_TABLE, - .domain = DOMAIN_IO, + .domain = DOMAIN_KERNEL, }, }; @@ -310,9 +309,8 @@ static void __init build_mem_type_table(void) cachepolicy = CPOLICY_WRITEBACK; ecc_mask = 0; } -#ifdef CONFIG_SMP - cachepolicy = CPOLICY_WRITEALLOC; -#endif + if (is_smp()) + cachepolicy = CPOLICY_WRITEALLOC; /* * Strip out features not present on earlier architectures. @@ -406,13 +404,11 @@ static void __init build_mem_type_table(void) cp = &cache_policies[cachepolicy]; vecs_pgprot = kern_pgprot = user_pgprot = cp->pte; -#ifndef CONFIG_SMP /* * Only use write-through for non-SMP systems */ - if (cpu_arch >= CPU_ARCH_ARMv5 && cachepolicy > CPOLICY_WRITETHROUGH) + if (!is_smp() && cpu_arch >= CPU_ARCH_ARMv5 && cachepolicy > CPOLICY_WRITETHROUGH) vecs_pgprot = cache_policies[CPOLICY_WRITETHROUGH].pte; -#endif /* * Enable CPU-specific coherency if supported. @@ -436,22 +432,23 @@ 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; -#ifdef CONFIG_SMP - /* - * Mark memory with the "shared" attribute for SMP systems - */ - user_pgprot |= L_PTE_SHARED; - kern_pgprot |= L_PTE_SHARED; - vecs_pgprot |= L_PTE_SHARED; - mem_types[MT_DEVICE_WC].prot_sect |= PMD_SECT_S; - mem_types[MT_DEVICE_WC].prot_pte |= L_PTE_SHARED; - mem_types[MT_DEVICE_CACHED].prot_sect |= PMD_SECT_S; - mem_types[MT_DEVICE_CACHED].prot_pte |= L_PTE_SHARED; - mem_types[MT_MEMORY].prot_sect |= PMD_SECT_S; - mem_types[MT_MEMORY].prot_pte |= L_PTE_SHARED; - mem_types[MT_MEMORY_NONCACHED].prot_sect |= PMD_SECT_S; - mem_types[MT_MEMORY_NONCACHED].prot_pte |= L_PTE_SHARED; -#endif + if (is_smp()) { + /* + * Mark memory with the "shared" attribute + * for SMP systems + */ + user_pgprot |= L_PTE_SHARED; + kern_pgprot |= L_PTE_SHARED; + vecs_pgprot |= L_PTE_SHARED; + mem_types[MT_DEVICE_WC].prot_sect |= PMD_SECT_S; + mem_types[MT_DEVICE_WC].prot_pte |= L_PTE_SHARED; + mem_types[MT_DEVICE_CACHED].prot_sect |= PMD_SECT_S; + mem_types[MT_DEVICE_CACHED].prot_pte |= L_PTE_SHARED; + mem_types[MT_MEMORY].prot_sect |= PMD_SECT_S; + mem_types[MT_MEMORY].prot_pte |= L_PTE_SHARED; + mem_types[MT_MEMORY_NONCACHED].prot_sect |= PMD_SECT_S; + mem_types[MT_MEMORY_NONCACHED].prot_pte |= L_PTE_SHARED; + } } /* @@ -747,13 +744,14 @@ static int __init early_vmalloc(char *arg) } early_param("vmalloc", early_vmalloc); -phys_addr_t lowmem_end_addr; +static phys_addr_t lowmem_limit __initdata = 0; static void __init sanity_check_meminfo(void) { int i, j, highmem = 0; - lowmem_end_addr = __pa(vmalloc_min - 1) + 1; + lowmem_limit = __pa(vmalloc_min - 1) + 1; + memblock_set_current_limit(lowmem_limit); for (i = 0, j = 0; i < meminfo.nr_banks; i++) { struct membank *bank = &meminfo.bank[j]; @@ -829,8 +827,7 @@ static void __init sanity_check_meminfo(void) * rather difficult. */ reason = "with VIPT aliasing cache"; -#ifdef CONFIG_SMP - } else if (tlb_ops_need_broadcast()) { + } else if (is_smp() && tlb_ops_need_broadcast()) { /* * kmap_high needs to occasionally flush TLB entries, * however, if the TLB entries need to be broadcast @@ -840,7 +837,6 @@ static void __init sanity_check_meminfo(void) * (must not be called with irqs off) */ reason = "without hardware TLB ops broadcasting"; -#endif } if (reason) { printk(KERN_CRIT "HIGHMEM is not supported %s, ignoring high memory\n", @@ -856,6 +852,7 @@ static void __init sanity_check_meminfo(void) static inline void prepare_page_table(void) { unsigned long addr; + phys_addr_t end; /* * Clear out all the mappings below the kernel image. @@ -871,10 +868,17 @@ static inline void prepare_page_table(void) pmd_clear(pmd_off_k(addr)); /* + * Find the end of the first block of lowmem. + */ + end = memblock.memory.regions[0].base + memblock.memory.regions[0].size; + if (end >= lowmem_limit) + end = lowmem_limit; + + /* * Clear out all the kernel space mappings, except for the first * memory bank, up to the end of the vmalloc region. */ - for (addr = __phys_to_virt(bank_phys_end(&meminfo.bank[0])); + for (addr = __phys_to_virt(end); addr < VMALLOC_END; addr += PGDIR_SIZE) pmd_clear(pmd_off_k(addr)); } @@ -991,37 +995,28 @@ static void __init kmap_init(void) #endif } -static inline void map_memory_bank(struct membank *bank) -{ - struct map_desc map; - - map.pfn = bank_pfn_start(bank); - map.virtual = __phys_to_virt(bank_phys_start(bank)); - map.length = bank_phys_size(bank); - map.type = MT_MEMORY; - - create_mapping(&map); -} - static void __init map_lowmem(void) { - struct meminfo *mi = &meminfo; - int i; + struct memblock_region *reg; /* Map all the lowmem memory banks. */ - for (i = 0; i < mi->nr_banks; i++) { - struct membank *bank = &mi->bank[i]; + for_each_memblock(memory, reg) { + phys_addr_t start = reg->base; + phys_addr_t end = start + reg->size; + struct map_desc map; + + if (end > lowmem_limit) + end = lowmem_limit; + if (start >= end) + break; - if (!bank->highmem) - map_memory_bank(bank); - } -} + map.pfn = __phys_to_pfn(start); + map.virtual = __phys_to_virt(start); + map.length = end - start; + map.type = MT_MEMORY; -static int __init meminfo_cmp(const void *_a, const void *_b) -{ - const struct membank *a = _a, *b = _b; - long cmp = bank_pfn_start(a) - bank_pfn_start(b); - return cmp < 0 ? -1 : cmp > 0 ? 1 : 0; + create_mapping(&map); + } } /* @@ -1032,8 +1027,6 @@ void __init paging_init(struct machine_desc *mdesc) { void *zero_page; - sort(&meminfo.bank, meminfo.nr_banks, sizeof(meminfo.bank[0]), meminfo_cmp, NULL); - build_mem_type_table(); sanity_check_meminfo(); prepare_page_table(); diff --git a/arch/arm/mm/pgd.c b/arch/arm/mm/pgd.c index be5f58e153b..69bbfc6645a 100644 --- a/arch/arm/mm/pgd.c +++ b/arch/arm/mm/pgd.c @@ -57,9 +57,9 @@ pgd_t *get_pgd_slow(struct mm_struct *mm) goto no_pte; init_pmd = pmd_offset(init_pgd, 0); - init_pte = pte_offset_map_nested(init_pmd, 0); + init_pte = pte_offset_map(init_pmd, 0); set_pte_ext(new_pte, *init_pte, 0); - pte_unmap_nested(init_pte); + pte_unmap(init_pte); pte_unmap(new_pte); } diff --git a/arch/arm/mm/proc-arm1020.S b/arch/arm/mm/proc-arm1020.S index 203a4e944d9..bcf748d9f4e 100644 --- a/arch/arm/mm/proc-arm1020.S +++ b/arch/arm/mm/proc-arm1020.S @@ -119,6 +119,20 @@ ENTRY(cpu_arm1020_do_idle) /* ================================= CACHE ================================ */ .align 5 + +/* + * flush_icache_all() + * + * Unconditionally clean and invalidate the entire icache. + */ +ENTRY(arm1020_flush_icache_all) +#ifndef CONFIG_CPU_ICACHE_DISABLE + mov r0, #0 + mcr p15, 0, r0, c7, c5, 0 @ invalidate I cache +#endif + mov pc, lr +ENDPROC(arm1020_flush_icache_all) + /* * flush_user_cache_all() * @@ -351,6 +365,7 @@ ENTRY(arm1020_dma_unmap_area) ENDPROC(arm1020_dma_unmap_area) ENTRY(arm1020_cache_fns) + .long arm1020_flush_icache_all .long arm1020_flush_kern_cache_all .long arm1020_flush_user_cache_all .long arm1020_flush_user_cache_range @@ -430,7 +445,7 @@ ENTRY(cpu_arm1020_set_pte_ext) #endif /* CONFIG_MMU */ mov pc, lr - __INIT + __CPUINIT .type __arm1020_setup, #function __arm1020_setup: diff --git a/arch/arm/mm/proc-arm1020e.S b/arch/arm/mm/proc-arm1020e.S index 1a511e76590..ab7ec26657e 100644 --- a/arch/arm/mm/proc-arm1020e.S +++ b/arch/arm/mm/proc-arm1020e.S @@ -119,6 +119,20 @@ ENTRY(cpu_arm1020e_do_idle) /* ================================= CACHE ================================ */ .align 5 + +/* + * flush_icache_all() + * + * Unconditionally clean and invalidate the entire icache. + */ +ENTRY(arm1020e_flush_icache_all) +#ifndef CONFIG_CPU_ICACHE_DISABLE + mov r0, #0 + mcr p15, 0, r0, c7, c5, 0 @ invalidate I cache +#endif + mov pc, lr +ENDPROC(arm1020e_flush_icache_all) + /* * flush_user_cache_all() * @@ -337,6 +351,7 @@ ENTRY(arm1020e_dma_unmap_area) ENDPROC(arm1020e_dma_unmap_area) ENTRY(arm1020e_cache_fns) + .long arm1020e_flush_icache_all .long arm1020e_flush_kern_cache_all .long arm1020e_flush_user_cache_all .long arm1020e_flush_user_cache_range @@ -412,7 +427,7 @@ ENTRY(cpu_arm1020e_set_pte_ext) #endif /* CONFIG_MMU */ mov pc, lr - __INIT + __CPUINIT .type __arm1020e_setup, #function __arm1020e_setup: diff --git a/arch/arm/mm/proc-arm1022.S b/arch/arm/mm/proc-arm1022.S index 1ffa4eb9c34..831c5e54e22 100644 --- a/arch/arm/mm/proc-arm1022.S +++ b/arch/arm/mm/proc-arm1022.S @@ -108,6 +108,20 @@ ENTRY(cpu_arm1022_do_idle) /* ================================= CACHE ================================ */ .align 5 + +/* + * flush_icache_all() + * + * Unconditionally clean and invalidate the entire icache. + */ +ENTRY(arm1022_flush_icache_all) +#ifndef CONFIG_CPU_ICACHE_DISABLE + mov r0, #0 + mcr p15, 0, r0, c7, c5, 0 @ invalidate I cache +#endif + mov pc, lr +ENDPROC(arm1022_flush_icache_all) + /* * flush_user_cache_all() * @@ -326,6 +340,7 @@ ENTRY(arm1022_dma_unmap_area) ENDPROC(arm1022_dma_unmap_area) ENTRY(arm1022_cache_fns) + .long arm1022_flush_icache_all .long arm1022_flush_kern_cache_all .long arm1022_flush_user_cache_all .long arm1022_flush_user_cache_range @@ -394,7 +409,7 @@ ENTRY(cpu_arm1022_set_pte_ext) #endif /* CONFIG_MMU */ mov pc, lr - __INIT + __CPUINIT .type __arm1022_setup, #function __arm1022_setup: diff --git a/arch/arm/mm/proc-arm1026.S b/arch/arm/mm/proc-arm1026.S index 5697c34b95b..e3f7e9a166b 100644 --- a/arch/arm/mm/proc-arm1026.S +++ b/arch/arm/mm/proc-arm1026.S @@ -108,6 +108,20 @@ ENTRY(cpu_arm1026_do_idle) /* ================================= CACHE ================================ */ .align 5 + +/* + * flush_icache_all() + * + * Unconditionally clean and invalidate the entire icache. + */ +ENTRY(arm1026_flush_icache_all) +#ifndef CONFIG_CPU_ICACHE_DISABLE + mov r0, #0 + mcr p15, 0, r0, c7, c5, 0 @ invalidate I cache +#endif + mov pc, lr +ENDPROC(arm1026_flush_icache_all) + /* * flush_user_cache_all() * @@ -320,6 +334,7 @@ ENTRY(arm1026_dma_unmap_area) ENDPROC(arm1026_dma_unmap_area) ENTRY(arm1026_cache_fns) + .long arm1026_flush_icache_all .long arm1026_flush_kern_cache_all .long arm1026_flush_user_cache_all .long arm1026_flush_user_cache_range @@ -384,7 +399,7 @@ ENTRY(cpu_arm1026_set_pte_ext) mov pc, lr - __INIT + __CPUINIT .type __arm1026_setup, #function __arm1026_setup: diff --git a/arch/arm/mm/proc-arm6_7.S b/arch/arm/mm/proc-arm6_7.S index 64e0b327c7c..6a7be1863ed 100644 --- a/arch/arm/mm/proc-arm6_7.S +++ b/arch/arm/mm/proc-arm6_7.S @@ -238,7 +238,7 @@ ENTRY(cpu_arm7_reset) mcr p15, 0, r1, c1, c0, 0 @ turn off MMU etc mov pc, r0 - __INIT + __CPUINIT .type __arm6_setup, #function __arm6_setup: mov r0, #0 diff --git a/arch/arm/mm/proc-arm720.S b/arch/arm/mm/proc-arm720.S index 9d96824134f..c285395f44b 100644 --- a/arch/arm/mm/proc-arm720.S +++ b/arch/arm/mm/proc-arm720.S @@ -113,7 +113,7 @@ ENTRY(cpu_arm720_reset) mcr p15, 0, ip, c1, c0, 0 @ ctrl register mov pc, r0 - __INIT + __CPUINIT .type __arm710_setup, #function __arm710_setup: diff --git a/arch/arm/mm/proc-arm740.S b/arch/arm/mm/proc-arm740.S index 6c1a9ab059a..38b27dcba72 100644 --- a/arch/arm/mm/proc-arm740.S +++ b/arch/arm/mm/proc-arm740.S @@ -55,7 +55,7 @@ ENTRY(cpu_arm740_reset) mcr p15, 0, ip, c1, c0, 0 @ ctrl register mov pc, r0 - __INIT + __CPUINIT .type __arm740_setup, #function __arm740_setup: diff --git a/arch/arm/mm/proc-arm7tdmi.S b/arch/arm/mm/proc-arm7tdmi.S index 6a850dbba22..0c9786de20a 100644 --- a/arch/arm/mm/proc-arm7tdmi.S +++ b/arch/arm/mm/proc-arm7tdmi.S @@ -46,7 +46,7 @@ ENTRY(cpu_arm7tdmi_proc_fin) ENTRY(cpu_arm7tdmi_reset) mov pc, r0 - __INIT + __CPUINIT .type __arm7tdmi_setup, #function __arm7tdmi_setup: diff --git a/arch/arm/mm/proc-arm920.S b/arch/arm/mm/proc-arm920.S index 86f80aa5621..6109f278a90 100644 --- a/arch/arm/mm/proc-arm920.S +++ b/arch/arm/mm/proc-arm920.S @@ -110,6 +110,17 @@ ENTRY(cpu_arm920_do_idle) #ifndef CONFIG_CPU_DCACHE_WRITETHROUGH /* + * flush_icache_all() + * + * Unconditionally clean and invalidate the entire icache. + */ +ENTRY(arm920_flush_icache_all) + mov r0, #0 + mcr p15, 0, r0, c7, c5, 0 @ invalidate I cache + mov pc, lr +ENDPROC(arm920_flush_icache_all) + +/* * flush_user_cache_all() * * Invalidate all cache entries in a particular address @@ -305,6 +316,7 @@ ENTRY(arm920_dma_unmap_area) ENDPROC(arm920_dma_unmap_area) ENTRY(arm920_cache_fns) + .long arm920_flush_icache_all .long arm920_flush_kern_cache_all .long arm920_flush_user_cache_all .long arm920_flush_user_cache_range @@ -375,7 +387,7 @@ ENTRY(cpu_arm920_set_pte_ext) #endif mov pc, lr - __INIT + __CPUINIT .type __arm920_setup, #function __arm920_setup: diff --git a/arch/arm/mm/proc-arm922.S b/arch/arm/mm/proc-arm922.S index f76ce9b6288..bb2f0f46a5e 100644 --- a/arch/arm/mm/proc-arm922.S +++ b/arch/arm/mm/proc-arm922.S @@ -112,6 +112,17 @@ ENTRY(cpu_arm922_do_idle) #ifndef CONFIG_CPU_DCACHE_WRITETHROUGH /* + * flush_icache_all() + * + * Unconditionally clean and invalidate the entire icache. + */ +ENTRY(arm922_flush_icache_all) + mov r0, #0 + mcr p15, 0, r0, c7, c5, 0 @ invalidate I cache + mov pc, lr +ENDPROC(arm922_flush_icache_all) + +/* * flush_user_cache_all() * * Clean and invalidate all cache entries in a particular @@ -307,6 +318,7 @@ ENTRY(arm922_dma_unmap_area) ENDPROC(arm922_dma_unmap_area) ENTRY(arm922_cache_fns) + .long arm922_flush_icache_all .long arm922_flush_kern_cache_all .long arm922_flush_user_cache_all .long arm922_flush_user_cache_range @@ -379,7 +391,7 @@ ENTRY(cpu_arm922_set_pte_ext) #endif /* CONFIG_MMU */ mov pc, lr - __INIT + __CPUINIT .type __arm922_setup, #function __arm922_setup: diff --git a/arch/arm/mm/proc-arm925.S b/arch/arm/mm/proc-arm925.S index 657bd3f7c15..c13e01accfe 100644 --- a/arch/arm/mm/proc-arm925.S +++ b/arch/arm/mm/proc-arm925.S @@ -145,6 +145,17 @@ ENTRY(cpu_arm925_do_idle) mov pc, lr /* + * flush_icache_all() + * + * Unconditionally clean and invalidate the entire icache. + */ +ENTRY(arm925_flush_icache_all) + mov r0, #0 + mcr p15, 0, r0, c7, c5, 0 @ invalidate I cache + mov pc, lr +ENDPROC(arm925_flush_icache_all) + +/* * flush_user_cache_all() * * Clean and invalidate all cache entries in a particular @@ -362,6 +373,7 @@ ENTRY(arm925_dma_unmap_area) ENDPROC(arm925_dma_unmap_area) ENTRY(arm925_cache_fns) + .long arm925_flush_icache_all .long arm925_flush_kern_cache_all .long arm925_flush_user_cache_all .long arm925_flush_user_cache_range @@ -428,7 +440,7 @@ ENTRY(cpu_arm925_set_pte_ext) #endif /* CONFIG_MMU */ mov pc, lr - __INIT + __CPUINIT .type __arm925_setup, #function __arm925_setup: diff --git a/arch/arm/mm/proc-arm926.S b/arch/arm/mm/proc-arm926.S index 73f1f3c6891..42eb4315740 100644 --- a/arch/arm/mm/proc-arm926.S +++ b/arch/arm/mm/proc-arm926.S @@ -111,6 +111,17 @@ ENTRY(cpu_arm926_do_idle) mov pc, lr /* + * flush_icache_all() + * + * Unconditionally clean and invalidate the entire icache. + */ +ENTRY(arm926_flush_icache_all) + mov r0, #0 + mcr p15, 0, r0, c7, c5, 0 @ invalidate I cache + mov pc, lr +ENDPROC(arm926_flush_icache_all) + +/* * flush_user_cache_all() * * Clean and invalidate all cache entries in a particular @@ -325,6 +336,7 @@ ENTRY(arm926_dma_unmap_area) ENDPROC(arm926_dma_unmap_area) ENTRY(arm926_cache_fns) + .long arm926_flush_icache_all .long arm926_flush_kern_cache_all .long arm926_flush_user_cache_all .long arm926_flush_user_cache_range @@ -389,7 +401,7 @@ ENTRY(cpu_arm926_set_pte_ext) #endif mov pc, lr - __INIT + __CPUINIT .type __arm926_setup, #function __arm926_setup: diff --git a/arch/arm/mm/proc-arm940.S b/arch/arm/mm/proc-arm940.S index fffb061a45a..7b11cdb9935 100644 --- a/arch/arm/mm/proc-arm940.S +++ b/arch/arm/mm/proc-arm940.S @@ -68,6 +68,17 @@ ENTRY(cpu_arm940_do_idle) mov pc, lr /* + * flush_icache_all() + * + * Unconditionally clean and invalidate the entire icache. + */ +ENTRY(arm940_flush_icache_all) + mov r0, #0 + mcr p15, 0, r0, c7, c5, 0 @ invalidate I cache + mov pc, lr +ENDPROC(arm940_flush_icache_all) + +/* * flush_user_cache_all() */ ENTRY(arm940_flush_user_cache_all) @@ -254,6 +265,7 @@ ENTRY(arm940_dma_unmap_area) ENDPROC(arm940_dma_unmap_area) ENTRY(arm940_cache_fns) + .long arm940_flush_icache_all .long arm940_flush_kern_cache_all .long arm940_flush_user_cache_all .long arm940_flush_user_cache_range @@ -264,7 +276,7 @@ ENTRY(arm940_cache_fns) .long arm940_dma_unmap_area .long arm940_dma_flush_range - __INIT + __CPUINIT .type __arm940_setup, #function __arm940_setup: diff --git a/arch/arm/mm/proc-arm946.S b/arch/arm/mm/proc-arm946.S index 249a6053760..1a5bbf08034 100644 --- a/arch/arm/mm/proc-arm946.S +++ b/arch/arm/mm/proc-arm946.S @@ -75,6 +75,17 @@ ENTRY(cpu_arm946_do_idle) mov pc, lr /* + * flush_icache_all() + * + * Unconditionally clean and invalidate the entire icache. + */ +ENTRY(arm946_flush_icache_all) + mov r0, #0 + mcr p15, 0, r0, c7, c5, 0 @ invalidate I cache + mov pc, lr +ENDPROC(arm946_flush_icache_all) + +/* * flush_user_cache_all() */ ENTRY(arm946_flush_user_cache_all) @@ -296,6 +307,7 @@ ENTRY(arm946_dma_unmap_area) ENDPROC(arm946_dma_unmap_area) ENTRY(arm946_cache_fns) + .long arm946_flush_icache_all .long arm946_flush_kern_cache_all .long arm946_flush_user_cache_all .long arm946_flush_user_cache_range @@ -317,7 +329,7 @@ ENTRY(cpu_arm946_dcache_clean_area) mcr p15, 0, r0, c7, c10, 4 @ drain WB mov pc, lr - __INIT + __CPUINIT .type __arm946_setup, #function __arm946_setup: diff --git a/arch/arm/mm/proc-arm9tdmi.S b/arch/arm/mm/proc-arm9tdmi.S index db475667fac..db67e3134d7 100644 --- a/arch/arm/mm/proc-arm9tdmi.S +++ b/arch/arm/mm/proc-arm9tdmi.S @@ -46,7 +46,7 @@ ENTRY(cpu_arm9tdmi_proc_fin) ENTRY(cpu_arm9tdmi_reset) mov pc, r0 - __INIT + __CPUINIT .type __arm9tdmi_setup, #function __arm9tdmi_setup: diff --git a/arch/arm/mm/proc-fa526.S b/arch/arm/mm/proc-fa526.S index 7803fdf7002..7c9ad621f0e 100644 --- a/arch/arm/mm/proc-fa526.S +++ b/arch/arm/mm/proc-fa526.S @@ -134,7 +134,7 @@ ENTRY(cpu_fa526_set_pte_ext) #endif mov pc, lr - __INIT + __CPUINIT .type __fa526_setup, #function __fa526_setup: diff --git a/arch/arm/mm/proc-feroceon.S b/arch/arm/mm/proc-feroceon.S index b304d0104a4..b4597edbff9 100644 --- a/arch/arm/mm/proc-feroceon.S +++ b/arch/arm/mm/proc-feroceon.S @@ -124,6 +124,17 @@ ENTRY(cpu_feroceon_do_idle) mov pc, lr /* + * flush_icache_all() + * + * Unconditionally clean and invalidate the entire icache. + */ +ENTRY(feroceon_flush_icache_all) + mov r0, #0 + mcr p15, 0, r0, c7, c5, 0 @ invalidate I cache + mov pc, lr +ENDPROC(feroceon_flush_icache_all) + +/* * flush_user_cache_all() * * Clean and invalidate all cache entries in a particular @@ -401,6 +412,7 @@ ENTRY(feroceon_dma_unmap_area) ENDPROC(feroceon_dma_unmap_area) ENTRY(feroceon_cache_fns) + .long feroceon_flush_icache_all .long feroceon_flush_kern_cache_all .long feroceon_flush_user_cache_all .long feroceon_flush_user_cache_range @@ -412,6 +424,7 @@ ENTRY(feroceon_cache_fns) .long feroceon_dma_flush_range ENTRY(feroceon_range_cache_fns) + .long feroceon_flush_icache_all .long feroceon_flush_kern_cache_all .long feroceon_flush_user_cache_all .long feroceon_flush_user_cache_range @@ -494,7 +507,7 @@ ENTRY(cpu_feroceon_set_pte_ext) #endif mov pc, lr - __INIT + __CPUINIT .type __feroceon_setup, #function __feroceon_setup: diff --git a/arch/arm/mm/proc-macros.S b/arch/arm/mm/proc-macros.S index 7d63beaf974..b795afd0a2c 100644 --- a/arch/arm/mm/proc-macros.S +++ b/arch/arm/mm/proc-macros.S @@ -61,17 +61,27 @@ .endm /* - * cache_line_size - get the cache line size from the CSIDR register - * (available on ARMv7+). It assumes that the CSSR register was configured - * to access the L1 data cache CSIDR. + * dcache_line_size - get the minimum D-cache line size from the CTR register + * on ARMv7. */ .macro dcache_line_size, reg, tmp - mrc p15, 1, \tmp, c0, c0, 0 @ read CSIDR - and \tmp, \tmp, #7 @ cache line size encoding - mov \reg, #16 @ size offset + mrc p15, 0, \tmp, c0, c0, 1 @ read ctr + lsr \tmp, \tmp, #16 + and \tmp, \tmp, #0xf @ cache line size encoding + mov \reg, #4 @ bytes per word mov \reg, \reg, lsl \tmp @ actual cache line size .endm +/* + * icache_line_size - get the minimum I-cache line size from the CTR register + * on ARMv7. + */ + .macro icache_line_size, reg, tmp + mrc p15, 0, \tmp, c0, c0, 1 @ read ctr + and \tmp, \tmp, #0xf @ cache line size encoding + mov \reg, #4 @ bytes per word + mov \reg, \reg, lsl \tmp @ actual cache line size + .endm /* * Sanity check the PTE configuration for the code below - which makes diff --git a/arch/arm/mm/proc-mohawk.S b/arch/arm/mm/proc-mohawk.S index 5f6892fcc16..4458ee6aa71 100644 --- a/arch/arm/mm/proc-mohawk.S +++ b/arch/arm/mm/proc-mohawk.S @@ -338,7 +338,7 @@ ENTRY(cpu_mohawk_set_pte_ext) mcr p15, 0, r0, c7, c10, 4 @ drain WB mov pc, lr - __INIT + __CPUINIT .type __mohawk_setup, #function __mohawk_setup: diff --git a/arch/arm/mm/proc-sa110.S b/arch/arm/mm/proc-sa110.S index a201eb04b5e..5aa8d59c2e8 100644 --- a/arch/arm/mm/proc-sa110.S +++ b/arch/arm/mm/proc-sa110.S @@ -156,7 +156,7 @@ ENTRY(cpu_sa110_set_pte_ext) #endif mov pc, lr - __INIT + __CPUINIT .type __sa110_setup, #function __sa110_setup: diff --git a/arch/arm/mm/proc-sa1100.S b/arch/arm/mm/proc-sa1100.S index 7ddc4805bf9..2ac4e6f1071 100644 --- a/arch/arm/mm/proc-sa1100.S +++ b/arch/arm/mm/proc-sa1100.S @@ -169,7 +169,7 @@ ENTRY(cpu_sa1100_set_pte_ext) #endif mov pc, lr - __INIT + __CPUINIT .type __sa1100_setup, #function __sa1100_setup: diff --git a/arch/arm/mm/proc-v6.S b/arch/arm/mm/proc-v6.S index 22aac851519..59a7e1ffe7b 100644 --- a/arch/arm/mm/proc-v6.S +++ b/arch/arm/mm/proc-v6.S @@ -30,13 +30,10 @@ #define TTB_RGN_WT (2 << 3) #define TTB_RGN_WB (3 << 3) -#ifndef CONFIG_SMP -#define TTB_FLAGS TTB_RGN_WBWA -#define PMD_FLAGS PMD_SECT_WB -#else -#define TTB_FLAGS TTB_RGN_WBWA|TTB_S -#define PMD_FLAGS PMD_SECT_WBWA|PMD_SECT_S -#endif +#define TTB_FLAGS_UP TTB_RGN_WBWA +#define PMD_FLAGS_UP PMD_SECT_WB +#define TTB_FLAGS_SMP TTB_RGN_WBWA|TTB_S +#define PMD_FLAGS_SMP PMD_SECT_WBWA|PMD_SECT_S ENTRY(cpu_v6_proc_init) mov pc, lr @@ -97,7 +94,8 @@ ENTRY(cpu_v6_switch_mm) #ifdef CONFIG_MMU mov r2, #0 ldr r1, [r1, #MM_CONTEXT_ID] @ get mm->context.id - orr r0, r0, #TTB_FLAGS + ALT_SMP(orr r0, r0, #TTB_FLAGS_SMP) + ALT_UP(orr r0, r0, #TTB_FLAGS_UP) mcr p15, 0, r2, c7, c5, 6 @ flush BTAC/BTB mcr p15, 0, r2, c7, c10, 4 @ drain write buffer mcr p15, 0, r0, c2, c0, 0 @ set TTB 0 @@ -137,7 +135,7 @@ cpu_pj4_name: .align - __INIT + __CPUINIT /* * __v6_setup @@ -156,9 +154,11 @@ cpu_pj4_name: */ __v6_setup: #ifdef CONFIG_SMP - mrc p15, 0, r0, c1, c0, 1 @ Enable SMP/nAMP mode + ALT_SMP(mrc p15, 0, r0, c1, c0, 1) @ Enable SMP/nAMP mode + ALT_UP(nop) orr r0, r0, #0x20 - mcr p15, 0, r0, c1, c0, 1 + ALT_SMP(mcr p15, 0, r0, c1, c0, 1) + ALT_UP(nop) #endif mov r0, #0 @@ -169,7 +169,8 @@ __v6_setup: #ifdef CONFIG_MMU mcr p15, 0, r0, c8, c7, 0 @ invalidate I + D TLBs mcr p15, 0, r0, c2, c0, 2 @ TTB control register - orr r4, r4, #TTB_FLAGS + ALT_SMP(orr r4, r4, #TTB_FLAGS_SMP) + ALT_UP(orr r4, r4, #TTB_FLAGS_UP) mcr p15, 0, r4, c2, c0, 1 @ load TTB1 #endif /* CONFIG_MMU */ adr r5, v6_crval @@ -192,6 +193,8 @@ __v6_setup: v6_crval: crval clear=0x01e0fb7f, mmuset=0x00c0387d, ucset=0x00c0187c + __INITDATA + .type v6_processor_functions, #object ENTRY(v6_processor_functions) .word v6_early_abort @@ -205,6 +208,8 @@ ENTRY(v6_processor_functions) .word cpu_v6_set_pte_ext .size v6_processor_functions, . - v6_processor_functions + .section ".rodata" + .type cpu_arch_name, #object cpu_arch_name: .asciz "armv6" @@ -225,10 +230,16 @@ cpu_elf_name: __v6_proc_info: .long 0x0007b000 .long 0x0007f000 - .long PMD_TYPE_SECT | \ + ALT_SMP(.long \ + PMD_TYPE_SECT | \ PMD_SECT_AP_WRITE | \ PMD_SECT_AP_READ | \ - PMD_FLAGS + PMD_FLAGS_SMP) + ALT_UP(.long \ + PMD_TYPE_SECT | \ + PMD_SECT_AP_WRITE | \ + PMD_SECT_AP_READ | \ + PMD_FLAGS_UP) .long PMD_TYPE_SECT | \ PMD_SECT_XN | \ PMD_SECT_AP_WRITE | \ @@ -249,10 +260,16 @@ __v6_proc_info: __pj4_v6_proc_info: .long 0x560f5810 .long 0xff0ffff0 - .long PMD_TYPE_SECT | \ + ALT_SMP(.long \ + PMD_TYPE_SECT | \ + PMD_SECT_AP_WRITE | \ + PMD_SECT_AP_READ | \ + PMD_FLAGS_SMP) + ALT_UP(.long \ + PMD_TYPE_SECT | \ PMD_SECT_AP_WRITE | \ PMD_SECT_AP_READ | \ - PMD_FLAGS + PMD_FLAGS_UP) .long PMD_TYPE_SECT | \ PMD_SECT_XN | \ PMD_SECT_AP_WRITE | \ diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S index 197f21bed5e..9b9ff5d949f 100644 --- a/arch/arm/mm/proc-v7.S +++ b/arch/arm/mm/proc-v7.S @@ -30,15 +30,13 @@ #define TTB_IRGN_WT ((1 << 0) | (0 << 6)) #define TTB_IRGN_WB ((1 << 0) | (1 << 6)) -#ifndef CONFIG_SMP /* PTWs cacheable, inner WB not shareable, outer WB not shareable */ -#define TTB_FLAGS TTB_IRGN_WB|TTB_RGN_OC_WB -#define PMD_FLAGS PMD_SECT_WB -#else +#define TTB_FLAGS_UP TTB_IRGN_WB|TTB_RGN_OC_WB +#define PMD_FLAGS_UP PMD_SECT_WB + /* PTWs cacheable, inner WBWA shareable, outer WBWA not shareable */ -#define TTB_FLAGS TTB_IRGN_WBWA|TTB_S|TTB_NOS|TTB_RGN_OC_WBWA -#define PMD_FLAGS PMD_SECT_WBWA|PMD_SECT_S -#endif +#define TTB_FLAGS_SMP TTB_IRGN_WBWA|TTB_S|TTB_NOS|TTB_RGN_OC_WBWA +#define PMD_FLAGS_SMP PMD_SECT_WBWA|PMD_SECT_S ENTRY(cpu_v7_proc_init) mov pc, lr @@ -105,7 +103,8 @@ ENTRY(cpu_v7_switch_mm) #ifdef CONFIG_MMU mov r2, #0 ldr r1, [r1, #MM_CONTEXT_ID] @ get mm->context.id - orr r0, r0, #TTB_FLAGS + ALT_SMP(orr r0, r0, #TTB_FLAGS_SMP) + ALT_UP(orr r0, r0, #TTB_FLAGS_UP) #ifdef CONFIG_ARM_ERRATA_430973 mcr p15, 0, r2, c7, c5, 6 @ flush BTAC/BTB #endif @@ -169,7 +168,7 @@ cpu_v7_name: .ascii "ARMv7 Processor" .align - __INIT + __CPUINIT /* * __v7_setup @@ -188,7 +187,8 @@ cpu_v7_name: */ __v7_ca9mp_setup: #ifdef CONFIG_SMP - mrc p15, 0, r0, c1, c0, 1 + ALT_SMP(mrc p15, 0, r0, c1, c0, 1) + ALT_UP(mov r0, #(1 << 6)) @ fake it for UP tst r0, #(1 << 6) @ SMP/nAMP mode enabled? orreq r0, r0, #(1 << 6) | (1 << 0) @ Enable SMP/nAMP mode and mcreq p15, 0, r0, c1, c0, 1 @ TLB ops broadcasting @@ -270,7 +270,8 @@ __v7_setup: #ifdef CONFIG_MMU mcr p15, 0, r10, c8, c7, 0 @ invalidate I + D TLBs mcr p15, 0, r10, c2, c0, 2 @ TTB control register - orr r4, r4, #TTB_FLAGS + ALT_SMP(orr r4, r4, #TTB_FLAGS_SMP) + ALT_UP(orr r4, r4, #TTB_FLAGS_UP) mcr p15, 0, r4, c2, c0, 1 @ load TTB1 mov r10, #0x1f @ domains 0, 1 = manager mcr p15, 0, r10, c3, c0, 0 @ load domain access register @@ -332,6 +333,8 @@ v7_crval: __v7_setup_stack: .space 4 * 11 @ 11 registers + __INITDATA + .type v7_processor_functions, #object ENTRY(v7_processor_functions) .word v7_early_abort @@ -345,6 +348,8 @@ ENTRY(v7_processor_functions) .word cpu_v7_set_pte_ext .size v7_processor_functions, . - v7_processor_functions + .section ".rodata" + .type cpu_arch_name, #object cpu_arch_name: .asciz "armv7" @@ -362,15 +367,21 @@ cpu_elf_name: __v7_ca9mp_proc_info: .long 0x410fc090 @ Required ID value .long 0xff0ffff0 @ Mask for ID - .long PMD_TYPE_SECT | \ + ALT_SMP(.long \ + PMD_TYPE_SECT | \ PMD_SECT_AP_WRITE | \ PMD_SECT_AP_READ | \ - PMD_FLAGS + PMD_FLAGS_SMP) + ALT_UP(.long \ + PMD_TYPE_SECT | \ + PMD_SECT_AP_WRITE | \ + PMD_SECT_AP_READ | \ + PMD_FLAGS_UP) .long PMD_TYPE_SECT | \ PMD_SECT_XN | \ PMD_SECT_AP_WRITE | \ PMD_SECT_AP_READ - b __v7_ca9mp_setup + W(b) __v7_ca9mp_setup .long cpu_arch_name .long cpu_elf_name .long HWCAP_SWP|HWCAP_HALF|HWCAP_THUMB|HWCAP_FAST_MULT|HWCAP_EDSP|HWCAP_TLS @@ -388,15 +399,21 @@ __v7_ca9mp_proc_info: __v7_proc_info: .long 0x000f0000 @ Required ID value .long 0x000f0000 @ Mask for ID - .long PMD_TYPE_SECT | \ + ALT_SMP(.long \ + PMD_TYPE_SECT | \ + PMD_SECT_AP_WRITE | \ + PMD_SECT_AP_READ | \ + PMD_FLAGS_SMP) + ALT_UP(.long \ + PMD_TYPE_SECT | \ PMD_SECT_AP_WRITE | \ PMD_SECT_AP_READ | \ - PMD_FLAGS + PMD_FLAGS_UP) .long PMD_TYPE_SECT | \ PMD_SECT_XN | \ PMD_SECT_AP_WRITE | \ PMD_SECT_AP_READ - b __v7_setup + W(b) __v7_setup .long cpu_arch_name .long cpu_elf_name .long HWCAP_SWP|HWCAP_HALF|HWCAP_THUMB|HWCAP_FAST_MULT|HWCAP_EDSP|HWCAP_TLS diff --git a/arch/arm/mm/proc-xsc3.S b/arch/arm/mm/proc-xsc3.S index 361a51e4903..ec26355cb7c 100644 --- a/arch/arm/mm/proc-xsc3.S +++ b/arch/arm/mm/proc-xsc3.S @@ -141,6 +141,17 @@ ENTRY(cpu_xsc3_do_idle) /* ================================= CACHE ================================ */ /* + * flush_icache_all() + * + * Unconditionally clean and invalidate the entire icache. + */ +ENTRY(xsc3_flush_icache_all) + mov r0, #0 + mcr p15, 0, r0, c7, c5, 0 @ invalidate I cache + mov pc, lr +ENDPROC(xsc3_flush_icache_all) + +/* * flush_user_cache_all() * * Invalidate all cache entries in a particular address @@ -325,6 +336,7 @@ ENTRY(xsc3_dma_unmap_area) ENDPROC(xsc3_dma_unmap_area) ENTRY(xsc3_cache_fns) + .long xsc3_flush_icache_all .long xsc3_flush_kern_cache_all .long xsc3_flush_user_cache_all .long xsc3_flush_user_cache_range @@ -404,7 +416,7 @@ ENTRY(cpu_xsc3_set_pte_ext) .align - __INIT + __CPUINIT .type __xsc3_setup, #function __xsc3_setup: diff --git a/arch/arm/mm/proc-xscale.S b/arch/arm/mm/proc-xscale.S index 14075979bcb..523408c0bb3 100644 --- a/arch/arm/mm/proc-xscale.S +++ b/arch/arm/mm/proc-xscale.S @@ -181,6 +181,17 @@ ENTRY(cpu_xscale_do_idle) /* ================================= CACHE ================================ */ /* + * flush_icache_all() + * + * Unconditionally clean and invalidate the entire icache. + */ +ENTRY(xscale_flush_icache_all) + mov r0, #0 + mcr p15, 0, r0, c7, c5, 0 @ invalidate I cache + mov pc, lr +ENDPROC(xscale_flush_icache_all) + +/* * flush_user_cache_all() * * Invalidate all cache entries in a particular address @@ -397,6 +408,7 @@ ENTRY(xscale_dma_unmap_area) ENDPROC(xscale_dma_unmap_area) ENTRY(xscale_cache_fns) + .long xscale_flush_icache_all .long xscale_flush_kern_cache_all .long xscale_flush_user_cache_all .long xscale_flush_user_cache_range @@ -506,7 +518,7 @@ ENTRY(cpu_xscale_set_pte_ext) .align - __INIT + __CPUINIT .type __xscale_setup, #function __xscale_setup: diff --git a/arch/arm/mm/tlb-v7.S b/arch/arm/mm/tlb-v7.S index f3f288a9546..53cd5b45467 100644 --- a/arch/arm/mm/tlb-v7.S +++ b/arch/arm/mm/tlb-v7.S @@ -13,6 +13,7 @@ */ #include <linux/init.h> #include <linux/linkage.h> +#include <asm/assembler.h> #include <asm/asm-offsets.h> #include <asm/page.h> #include <asm/tlbflush.h> @@ -41,20 +42,15 @@ ENTRY(v7wbi_flush_user_tlb_range) orr r0, r3, r0, lsl #PAGE_SHIFT @ Create initial MVA mov r1, r1, lsl #PAGE_SHIFT 1: -#ifdef CONFIG_SMP - mcr p15, 0, r0, c8, c3, 1 @ TLB invalidate U MVA (shareable) -#else - mcr p15, 0, r0, c8, c7, 1 @ TLB invalidate U MVA -#endif + ALT_SMP(mcr p15, 0, r0, c8, c3, 1) @ TLB invalidate U MVA (shareable) + ALT_UP(mcr p15, 0, r0, c8, c7, 1) @ TLB invalidate U MVA + add r0, r0, #PAGE_SZ cmp r0, r1 blo 1b mov ip, #0 -#ifdef CONFIG_SMP - mcr p15, 0, ip, c7, c1, 6 @ flush BTAC/BTB Inner Shareable -#else - mcr p15, 0, ip, c7, c5, 6 @ flush BTAC/BTB -#endif + ALT_SMP(mcr p15, 0, ip, c7, c1, 6) @ flush BTAC/BTB Inner Shareable + ALT_UP(mcr p15, 0, ip, c7, c5, 6) @ flush BTAC/BTB dsb mov pc, lr ENDPROC(v7wbi_flush_user_tlb_range) @@ -74,20 +70,14 @@ ENTRY(v7wbi_flush_kern_tlb_range) mov r0, r0, lsl #PAGE_SHIFT mov r1, r1, lsl #PAGE_SHIFT 1: -#ifdef CONFIG_SMP - mcr p15, 0, r0, c8, c3, 1 @ TLB invalidate U MVA (shareable) -#else - mcr p15, 0, r0, c8, c7, 1 @ TLB invalidate U MVA -#endif + ALT_SMP(mcr p15, 0, r0, c8, c3, 1) @ TLB invalidate U MVA (shareable) + ALT_UP(mcr p15, 0, r0, c8, c7, 1) @ TLB invalidate U MVA add r0, r0, #PAGE_SZ cmp r0, r1 blo 1b mov r2, #0 -#ifdef CONFIG_SMP - mcr p15, 0, r2, c7, c1, 6 @ flush BTAC/BTB Inner Shareable -#else - mcr p15, 0, r2, c7, c5, 6 @ flush BTAC/BTB -#endif + ALT_SMP(mcr p15, 0, r2, c7, c1, 6) @ flush BTAC/BTB Inner Shareable + ALT_UP(mcr p15, 0, r2, c7, c5, 6) @ flush BTAC/BTB dsb isb mov pc, lr @@ -99,5 +89,6 @@ ENDPROC(v7wbi_flush_kern_tlb_range) ENTRY(v7wbi_tlb_fns) .long v7wbi_flush_user_tlb_range .long v7wbi_flush_kern_tlb_range - .long v7wbi_tlb_flags + ALT_SMP(.long v7wbi_tlb_flags_smp) + ALT_UP(.long v7wbi_tlb_flags_up) .size v7wbi_tlb_fns, . - v7wbi_tlb_fns |