diff options
Diffstat (limited to 'arch/arm/mm')
57 files changed, 2009 insertions, 1152 deletions
diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig index 5bf7c3c3b301..577039a3f6e5 100644 --- a/arch/arm/mm/Kconfig +++ b/arch/arm/mm/Kconfig @@ -669,7 +669,7 @@ config ARM_VIRT_EXT details. config SWP_EMULATE - bool "Emulate SWP/SWPB instructions" + bool "Emulate SWP/SWPB instructions" if !SMP depends on CPU_V7 default y if SMP select HAVE_PROC_CPU if PROC_FS @@ -889,14 +889,65 @@ config CACHE_L2X0 help This option enables the L2x0 PrimeCell. +if CACHE_L2X0 + config CACHE_PL310 bool - depends on CACHE_L2X0 default y if CPU_V7 && !(CPU_V6 || CPU_V6K) help This option enables optimisations for the PL310 cache controller. +config PL310_ERRATA_588369 + bool "PL310 errata: Clean & Invalidate maintenance operations do not invalidate clean lines" + help + The PL310 L2 cache controller implements three types of Clean & + Invalidate maintenance operations: by Physical Address + (offset 0x7F0), by Index/Way (0x7F8) and by Way (0x7FC). + They are architecturally defined to behave as the execution of a + clean operation followed immediately by an invalidate operation, + both performing to the same memory location. This functionality + is not correctly implemented in PL310 prior to r2p0 (fixed in r2p0) + as clean lines are not invalidated as a result of these operations. + +config PL310_ERRATA_727915 + bool "PL310 errata: Background Clean & Invalidate by Way operation can cause data corruption" + help + PL310 implements the Clean & Invalidate by Way L2 cache maintenance + operation (offset 0x7FC). This operation runs in background so that + PL310 can handle normal accesses while it is in progress. Under very + rare circumstances, due to this erratum, write data can be lost when + PL310 treats a cacheable write transaction during a Clean & + Invalidate by Way operation. Revisions prior to r3p1 are affected by + this errata (fixed in r3p1). + +config PL310_ERRATA_753970 + bool "PL310 errata: cache sync operation may be faulty" + help + This option enables the workaround for the 753970 PL310 (r3p0) erratum. + + Under some condition the effect of cache sync operation on + the store buffer still remains when the operation completes. + This means that the store buffer is always asked to drain and + this prevents it from merging any further writes. The workaround + is to replace the normal offset of cache sync operation (0x730) + by another offset targeting an unmapped PL310 register 0x740. + This has the same effect as the cache sync operation: store buffer + drain and waiting for all buffers empty. + +config PL310_ERRATA_769419 + bool "PL310 errata: no automatic Store Buffer drain" + help + On revisions of the PL310 prior to r3p2, the Store Buffer does + not automatically drain. This can cause normal, non-cacheable + writes to be retained when the memory system is idle, leading + to suboptimal I/O performance for drivers using coherent DMA. + This option adds a write barrier to the cpu_idle loop so that, + on systems with an outer cache, the store buffer is drained + explicitly. + +endif + config CACHE_TAUROS2 bool "Enable the Tauros2 L2 cache controller" depends on (ARCH_DOVE || ARCH_MMP || CPU_PJ4) diff --git a/arch/arm/mm/Makefile b/arch/arm/mm/Makefile index 7f39ce2f841f..91da64de440f 100644 --- a/arch/arm/mm/Makefile +++ b/arch/arm/mm/Makefile @@ -95,7 +95,8 @@ obj-$(CONFIG_CPU_V7M) += proc-v7m.o AFLAGS_proc-v6.o :=-Wa,-march=armv6 AFLAGS_proc-v7.o :=-Wa,-march=armv7-a +obj-$(CONFIG_OUTER_CACHE) += l2c-common.o obj-$(CONFIG_CACHE_FEROCEON_L2) += cache-feroceon-l2.o -obj-$(CONFIG_CACHE_L2X0) += cache-l2x0.o +obj-$(CONFIG_CACHE_L2X0) += cache-l2x0.o l2c-l2x0-resume.o obj-$(CONFIG_CACHE_XSC3L2) += cache-xsc3l2.o obj-$(CONFIG_CACHE_TAUROS2) += cache-tauros2.o diff --git a/arch/arm/mm/alignment.c b/arch/arm/mm/alignment.c index 924036473b16..0c1ab49e5f7b 100644 --- a/arch/arm/mm/alignment.c +++ b/arch/arm/mm/alignment.c @@ -28,6 +28,7 @@ #include <asm/opcodes.h> #include "fault.h" +#include "mm.h" /* * 32-bit misaligned trap handler (c) 1998 San Mehat (CCC) -July 1998 @@ -75,12 +76,14 @@ static unsigned long ai_user; static unsigned long ai_sys; +static void *ai_sys_last_pc; static unsigned long ai_skipped; static unsigned long ai_half; static unsigned long ai_word; static unsigned long ai_dword; static unsigned long ai_multi; static int ai_usermode; +static unsigned long cr_no_alignment; core_param(alignment, ai_usermode, int, 0600); @@ -91,7 +94,7 @@ core_param(alignment, ai_usermode, int, 0600); /* Return true if and only if the ARMv6 unaligned access model is in use. */ static bool cpu_is_v6_unaligned(void) { - return cpu_architecture() >= CPU_ARCH_ARMv6 && (cr_alignment & CR_U); + return cpu_architecture() >= CPU_ARCH_ARMv6 && get_cr() & CR_U; } static int safe_usermode(int new_usermode, bool warn) @@ -128,7 +131,7 @@ static const char *usermode_action[] = { static int alignment_proc_show(struct seq_file *m, void *v) { seq_printf(m, "User:\t\t%lu\n", ai_user); - seq_printf(m, "System:\t\t%lu\n", ai_sys); + seq_printf(m, "System:\t\t%lu (%pF)\n", ai_sys, ai_sys_last_pc); seq_printf(m, "Skipped:\t%lu\n", ai_skipped); seq_printf(m, "Half:\t\t%lu\n", ai_half); seq_printf(m, "Word:\t\t%lu\n", ai_word); @@ -792,6 +795,7 @@ do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs) goto user; ai_sys += 1; + ai_sys_last_pc = (void *)instruction_pointer(regs); fixup: @@ -949,6 +953,13 @@ do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs) return 0; } +static int __init noalign_setup(char *__unused) +{ + set_cr(__clear_cr(CR_A)); + return 1; +} +__setup("noalign", noalign_setup); + /* * This needs to be done after sysctl_init, otherwise sys/ will be * overwritten. Actually, this shouldn't be in sys/ at all since @@ -966,14 +977,12 @@ static int __init alignment_init(void) return -ENOMEM; #endif -#ifdef CONFIG_CPU_CP15 if (cpu_is_v6_unaligned()) { - cr_alignment &= ~CR_A; - cr_no_alignment &= ~CR_A; - set_cr(cr_alignment); + set_cr(__clear_cr(CR_A)); ai_usermode = safe_usermode(ai_usermode, false); } -#endif + + cr_no_alignment = get_cr() & ~CR_A; hook_fault_code(FAULT_CODE_ALIGNMENT, do_alignment, SIGBUS, BUS_ADRALN, "alignment exception"); diff --git a/arch/arm/mm/cache-fa.S b/arch/arm/mm/cache-fa.S index e505befe51b5..2f0c58836ae7 100644 --- a/arch/arm/mm/cache-fa.S +++ b/arch/arm/mm/cache-fa.S @@ -15,6 +15,7 @@ */ #include <linux/linkage.h> #include <linux/init.h> +#include <asm/assembler.h> #include <asm/memory.h> #include <asm/page.h> @@ -45,7 +46,7 @@ ENTRY(fa_flush_icache_all) mov r0, #0 mcr p15, 0, r0, c7, c5, 0 @ invalidate I cache - mov pc, lr + ret lr ENDPROC(fa_flush_icache_all) /* @@ -71,7 +72,7 @@ __flush_whole_cache: mcrne p15, 0, ip, c7, c5, 6 @ invalidate BTB mcrne p15, 0, ip, c7, c10, 4 @ drain write buffer mcrne p15, 0, ip, c7, c5, 4 @ prefetch flush - mov pc, lr + ret lr /* * flush_user_cache_range(start, end, flags) @@ -99,7 +100,7 @@ ENTRY(fa_flush_user_cache_range) mcrne p15, 0, ip, c7, c5, 6 @ invalidate BTB mcrne p15, 0, ip, c7, c10, 4 @ data write barrier mcrne p15, 0, ip, c7, c5, 4 @ prefetch flush - mov pc, lr + ret lr /* * coherent_kern_range(start, end) @@ -135,7 +136,7 @@ ENTRY(fa_coherent_user_range) mcr p15, 0, r0, c7, c5, 6 @ invalidate BTB mcr p15, 0, r0, c7, c10, 4 @ drain write buffer mcr p15, 0, r0, c7, c5, 4 @ prefetch flush - mov pc, lr + ret lr /* * flush_kern_dcache_area(void *addr, size_t size) @@ -155,7 +156,7 @@ ENTRY(fa_flush_kern_dcache_area) mov r0, #0 mcr p15, 0, r0, c7, c5, 0 @ invalidate I cache mcr p15, 0, r0, c7, c10, 4 @ drain write buffer - mov pc, lr + ret lr /* * dma_inv_range(start, end) @@ -181,7 +182,7 @@ fa_dma_inv_range: blo 1b mov r0, #0 mcr p15, 0, r0, c7, c10, 4 @ drain write buffer - mov pc, lr + ret lr /* * dma_clean_range(start, end) @@ -199,7 +200,7 @@ fa_dma_clean_range: blo 1b mov r0, #0 mcr p15, 0, r0, c7, c10, 4 @ drain write buffer - mov pc, lr + ret lr /* * dma_flush_range(start,end) @@ -214,7 +215,7 @@ ENTRY(fa_dma_flush_range) blo 1b mov r0, #0 mcr p15, 0, r0, c7, c10, 4 @ drain write buffer - mov pc, lr + ret lr /* * dma_map_area(start, size, dir) @@ -237,7 +238,7 @@ ENDPROC(fa_dma_map_area) * - dir - DMA direction */ ENTRY(fa_dma_unmap_area) - mov pc, lr + ret lr ENDPROC(fa_dma_unmap_area) .globl fa_flush_kern_cache_louis diff --git a/arch/arm/mm/cache-feroceon-l2.c b/arch/arm/mm/cache-feroceon-l2.c index dc814a548056..e028a7f2ebcc 100644 --- a/arch/arm/mm/cache-feroceon-l2.c +++ b/arch/arm/mm/cache-feroceon-l2.c @@ -350,7 +350,6 @@ void __init feroceon_l2_init(int __l2_wt_override) outer_cache.inv_range = feroceon_l2_inv_range; outer_cache.clean_range = feroceon_l2_clean_range; outer_cache.flush_range = feroceon_l2_flush_range; - outer_cache.inv_all = l2_inv_all; enable_l2(); diff --git a/arch/arm/mm/cache-l2x0.c b/arch/arm/mm/cache-l2x0.c index 7abde2ce8973..5f2c988a06ac 100644 --- a/arch/arm/mm/cache-l2x0.c +++ b/arch/arm/mm/cache-l2x0.c @@ -16,18 +16,33 @@ * along with this program; if not, write to the Free Software * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ +#include <linux/cpu.h> #include <linux/err.h> #include <linux/init.h> +#include <linux/smp.h> #include <linux/spinlock.h> #include <linux/io.h> #include <linux/of.h> #include <linux/of_address.h> #include <asm/cacheflush.h> +#include <asm/cp15.h> +#include <asm/cputype.h> #include <asm/hardware/cache-l2x0.h> #include "cache-tauros3.h" #include "cache-aurora-l2.h" +struct l2c_init_data { + const char *type; + unsigned way_size_0; + unsigned num_lock; + void (*of_parse)(const struct device_node *, u32 *, u32 *); + void (*enable)(void __iomem *, u32, unsigned); + void (*fixup)(void __iomem *, u32, struct outer_cache_fns *); + void (*save)(void __iomem *); + struct outer_cache_fns outer_cache; +}; + #define CACHE_LINE_SIZE 32 static void __iomem *l2x0_base; @@ -36,96 +51,116 @@ static u32 l2x0_way_mask; /* Bitmask of active ways */ static u32 l2x0_size; static unsigned long sync_reg_offset = L2X0_CACHE_SYNC; -/* Aurora don't have the cache ID register available, so we have to - * pass it though the device tree */ -static u32 cache_id_part_number_from_dt; - struct l2x0_regs l2x0_saved_regs; -struct l2x0_of_data { - void (*setup)(const struct device_node *, u32 *, u32 *); - void (*save)(void); - struct outer_cache_fns outer_cache; -}; - -static bool of_init = false; - -static inline void cache_wait_way(void __iomem *reg, unsigned long mask) +/* + * Common code for all cache controllers. + */ +static inline void l2c_wait_mask(void __iomem *reg, unsigned long mask) { /* wait for cache operation by line or way to complete */ while (readl_relaxed(reg) & mask) cpu_relax(); } -#ifdef CONFIG_CACHE_PL310 -static inline void cache_wait(void __iomem *reg, unsigned long mask) +/* + * By default, we write directly to secure registers. Platforms must + * override this if they are running non-secure. + */ +static void l2c_write_sec(unsigned long val, void __iomem *base, unsigned reg) { - /* cache operations by line are atomic on PL310 */ + if (val == readl_relaxed(base + reg)) + return; + if (outer_cache.write_sec) + outer_cache.write_sec(val, reg); + else + writel_relaxed(val, base + reg); } -#else -#define cache_wait cache_wait_way -#endif -static inline void cache_sync(void) +/* + * This should only be called when we have a requirement that the + * register be written due to a work-around, as platforms running + * in non-secure mode may not be able to access this register. + */ +static inline void l2c_set_debug(void __iomem *base, unsigned long val) { - void __iomem *base = l2x0_base; - - writel_relaxed(0, base + sync_reg_offset); - cache_wait(base + L2X0_CACHE_SYNC, 1); + l2c_write_sec(val, base, L2X0_DEBUG_CTRL); } -static inline void l2x0_clean_line(unsigned long addr) +static void __l2c_op_way(void __iomem *reg) { - void __iomem *base = l2x0_base; - cache_wait(base + L2X0_CLEAN_LINE_PA, 1); - writel_relaxed(addr, base + L2X0_CLEAN_LINE_PA); + writel_relaxed(l2x0_way_mask, reg); + l2c_wait_mask(reg, l2x0_way_mask); } -static inline void l2x0_inv_line(unsigned long addr) +static inline void l2c_unlock(void __iomem *base, unsigned num) { - void __iomem *base = l2x0_base; - cache_wait(base + L2X0_INV_LINE_PA, 1); - writel_relaxed(addr, base + L2X0_INV_LINE_PA); + unsigned i; + + for (i = 0; i < num; i++) { + writel_relaxed(0, base + L2X0_LOCKDOWN_WAY_D_BASE + + i * L2X0_LOCKDOWN_STRIDE); + writel_relaxed(0, base + L2X0_LOCKDOWN_WAY_I_BASE + + i * L2X0_LOCKDOWN_STRIDE); + } } -#if defined(CONFIG_PL310_ERRATA_588369) || defined(CONFIG_PL310_ERRATA_727915) -static inline void debug_writel(unsigned long val) +/* + * Enable the L2 cache controller. This function must only be + * called when the cache controller is known to be disabled. + */ +static void l2c_enable(void __iomem *base, u32 aux, unsigned num_lock) { - if (outer_cache.set_debug) - outer_cache.set_debug(val); + unsigned long flags; + + l2c_write_sec(aux, base, L2X0_AUX_CTRL); + + l2c_unlock(base, num_lock); + + local_irq_save(flags); + __l2c_op_way(base + L2X0_INV_WAY); + writel_relaxed(0, base + sync_reg_offset); + l2c_wait_mask(base + sync_reg_offset, 1); + local_irq_restore(flags); + + l2c_write_sec(L2X0_CTRL_EN, base, L2X0_CTRL); } -static void pl310_set_debug(unsigned long val) +static void l2c_disable(void) { - writel_relaxed(val, l2x0_base + L2X0_DEBUG_CTRL); + void __iomem *base = l2x0_base; + + outer_cache.flush_all(); + l2c_write_sec(0, base, L2X0_CTRL); + dsb(st); } -#else -/* Optimised out for non-errata case */ -static inline void debug_writel(unsigned long val) + +#ifdef CONFIG_CACHE_PL310 +static inline void cache_wait(void __iomem *reg, unsigned long mask) { + /* cache operations by line are atomic on PL310 */ } - -#define pl310_set_debug NULL +#else +#define cache_wait l2c_wait_mask #endif -#ifdef CONFIG_PL310_ERRATA_588369 -static inline void l2x0_flush_line(unsigned long addr) +static inline void cache_sync(void) { void __iomem *base = l2x0_base; - /* Clean by PA followed by Invalidate by PA */ - cache_wait(base + L2X0_CLEAN_LINE_PA, 1); - writel_relaxed(addr, base + L2X0_CLEAN_LINE_PA); - cache_wait(base + L2X0_INV_LINE_PA, 1); - writel_relaxed(addr, base + L2X0_INV_LINE_PA); + writel_relaxed(0, base + sync_reg_offset); + cache_wait(base + L2X0_CACHE_SYNC, 1); } -#else -static inline void l2x0_flush_line(unsigned long addr) +#if defined(CONFIG_PL310_ERRATA_588369) || defined(CONFIG_PL310_ERRATA_727915) +static inline void debug_writel(unsigned long val) +{ + l2c_set_debug(l2x0_base, val); +} +#else +/* Optimised out for non-errata case */ +static inline void debug_writel(unsigned long val) { - void __iomem *base = l2x0_base; - cache_wait(base + L2X0_CLEAN_INV_LINE_PA, 1); - writel_relaxed(addr, base + L2X0_CLEAN_INV_LINE_PA); } #endif @@ -141,8 +176,7 @@ static void l2x0_cache_sync(void) static void __l2x0_flush_all(void) { debug_writel(0x03); - writel_relaxed(l2x0_way_mask, l2x0_base + L2X0_CLEAN_INV_WAY); - cache_wait_way(l2x0_base + L2X0_CLEAN_INV_WAY, l2x0_way_mask); + __l2c_op_way(l2x0_base + L2X0_CLEAN_INV_WAY); cache_sync(); debug_writel(0x00); } @@ -157,275 +191,910 @@ static void l2x0_flush_all(void) raw_spin_unlock_irqrestore(&l2x0_lock, flags); } -static void l2x0_clean_all(void) +static void l2x0_disable(void) { unsigned long flags; - /* clean all ways */ raw_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(); + __l2x0_flush_all(); + l2c_write_sec(0, l2x0_base, L2X0_CTRL); + dsb(st); raw_spin_unlock_irqrestore(&l2x0_lock, flags); } -static void l2x0_inv_all(void) +static void l2c_save(void __iomem *base) { - unsigned long flags; + l2x0_saved_regs.aux_ctrl = readl_relaxed(l2x0_base + L2X0_AUX_CTRL); +} - /* invalidate all ways */ - raw_spin_lock_irqsave(&l2x0_lock, flags); - /* Invalidating when L2 is enabled is a nono */ - BUG_ON(readl(l2x0_base + L2X0_CTRL) & L2X0_CTRL_EN); - writel_relaxed(l2x0_way_mask, l2x0_base + L2X0_INV_WAY); - cache_wait_way(l2x0_base + L2X0_INV_WAY, l2x0_way_mask); - cache_sync(); - raw_spin_unlock_irqrestore(&l2x0_lock, flags); +/* + * L2C-210 specific code. + * + * The L2C-2x0 PA, set/way and sync operations are atomic, but we must + * ensure that no background operation is running. The way operations + * are all background tasks. + * + * While a background operation is in progress, any new operation is + * ignored (unspecified whether this causes an error.) Thankfully, not + * used on SMP. + * + * Never has a different sync register other than L2X0_CACHE_SYNC, but + * we use sync_reg_offset here so we can share some of this with L2C-310. + */ +static void __l2c210_cache_sync(void __iomem *base) +{ + writel_relaxed(0, base + sync_reg_offset); } -static void l2x0_inv_range(unsigned long start, unsigned long end) +static void __l2c210_op_pa_range(void __iomem *reg, unsigned long start, + unsigned long end) +{ + while (start < end) { + writel_relaxed(start, reg); + start += CACHE_LINE_SIZE; + } +} + +static void l2c210_inv_range(unsigned long start, unsigned long end) { void __iomem *base = l2x0_base; - unsigned long flags; - raw_spin_lock_irqsave(&l2x0_lock, flags); if (start & (CACHE_LINE_SIZE - 1)) { start &= ~(CACHE_LINE_SIZE - 1); - debug_writel(0x03); - l2x0_flush_line(start); - debug_writel(0x00); + writel_relaxed(start, base + L2X0_CLEAN_INV_LINE_PA); start += CACHE_LINE_SIZE; } if (end & (CACHE_LINE_SIZE - 1)) { end &= ~(CACHE_LINE_SIZE - 1); - debug_writel(0x03); - l2x0_flush_line(end); - debug_writel(0x00); + writel_relaxed(end, base + L2X0_CLEAN_INV_LINE_PA); } + __l2c210_op_pa_range(base + L2X0_INV_LINE_PA, start, end); + __l2c210_cache_sync(base); +} + +static void l2c210_clean_range(unsigned long start, unsigned long end) +{ + void __iomem *base = l2x0_base; + + start &= ~(CACHE_LINE_SIZE - 1); + __l2c210_op_pa_range(base + L2X0_CLEAN_LINE_PA, start, end); + __l2c210_cache_sync(base); +} + +static void l2c210_flush_range(unsigned long start, unsigned long end) +{ + void __iomem *base = l2x0_base; + + start &= ~(CACHE_LINE_SIZE - 1); + __l2c210_op_pa_range(base + L2X0_CLEAN_INV_LINE_PA, start, end); + __l2c210_cache_sync(base); +} + +static void l2c210_flush_all(void) +{ + void __iomem *base = l2x0_base; + + BUG_ON(!irqs_disabled()); + + __l2c_op_way(base + L2X0_CLEAN_INV_WAY); + __l2c210_cache_sync(base); +} + +static void l2c210_sync(void) +{ + __l2c210_cache_sync(l2x0_base); +} + +static void l2c210_resume(void) +{ + void __iomem *base = l2x0_base; + + if (!(readl_relaxed(base + L2X0_CTRL) & L2X0_CTRL_EN)) + l2c_enable(base, l2x0_saved_regs.aux_ctrl, 1); +} + +static const struct l2c_init_data l2c210_data __initconst = { + .type = "L2C-210", + .way_size_0 = SZ_8K, + .num_lock = 1, + .enable = l2c_enable, + .save = l2c_save, + .outer_cache = { + .inv_range = l2c210_inv_range, + .clean_range = l2c210_clean_range, + .flush_range = l2c210_flush_range, + .flush_all = l2c210_flush_all, + .disable = l2c_disable, + .sync = l2c210_sync, + .resume = l2c210_resume, + }, +}; + +/* + * L2C-220 specific code. + * + * All operations are background operations: they have to be waited for. + * Conflicting requests generate a slave error (which will cause an + * imprecise abort.) Never uses sync_reg_offset, so we hard-code the + * sync register here. + * + * However, we can re-use the l2c210_resume call. + */ +static inline void __l2c220_cache_sync(void __iomem *base) +{ + writel_relaxed(0, base + L2X0_CACHE_SYNC); + l2c_wait_mask(base + L2X0_CACHE_SYNC, 1); +} + +static void l2c220_op_way(void __iomem *base, unsigned reg) +{ + unsigned long flags; + + raw_spin_lock_irqsave(&l2x0_lock, flags); + __l2c_op_way(base + reg); + __l2c220_cache_sync(base); + raw_spin_unlock_irqrestore(&l2x0_lock, flags); +} + +static unsigned long l2c220_op_pa_range(void __iomem *reg, unsigned long start, + unsigned long end, unsigned long flags) +{ + raw_spinlock_t *lock = &l2x0_lock; + while (start < end) { unsigned long blk_end = start + min(end - start, 4096UL); while (start < blk_end) { - l2x0_inv_line(start); + l2c_wait_mask(reg, 1); + writel_relaxed(start, reg); start += CACHE_LINE_SIZE; } if (blk_end < end) { - raw_spin_unlock_irqrestore(&l2x0_lock, flags); - raw_spin_lock_irqsave(&l2x0_lock, flags); + raw_spin_unlock_irqrestore(lock, flags); + raw_spin_lock_irqsave(lock, flags); } } - cache_wait(base + L2X0_INV_LINE_PA, 1); - cache_sync(); - raw_spin_unlock_irqrestore(&l2x0_lock, flags); + + return flags; } -static void l2x0_clean_range(unsigned long start, unsigned long end) +static void l2c220_inv_range(unsigned long start, unsigned long end) { void __iomem *base = l2x0_base; unsigned long flags; - if ((end - start) >= l2x0_size) { - l2x0_clean_all(); - return; - } - raw_spin_lock_irqsave(&l2x0_lock, flags); - start &= ~(CACHE_LINE_SIZE - 1); - while (start < end) { - unsigned long blk_end = start + min(end - start, 4096UL); - - while (start < blk_end) { - l2x0_clean_line(start); + if ((start | end) & (CACHE_LINE_SIZE - 1)) { + if (start & (CACHE_LINE_SIZE - 1)) { + start &= ~(CACHE_LINE_SIZE - 1); + writel_relaxed(start, base + L2X0_CLEAN_INV_LINE_PA); start += CACHE_LINE_SIZE; } - if (blk_end < end) { - raw_spin_unlock_irqrestore(&l2x0_lock, flags); - raw_spin_lock_irqsave(&l2x0_lock, flags); + if (end & (CACHE_LINE_SIZE - 1)) { + end &= ~(CACHE_LINE_SIZE - 1); + l2c_wait_mask(base + L2X0_CLEAN_INV_LINE_PA, 1); + writel_relaxed(end, base + L2X0_CLEAN_INV_LINE_PA); } } - cache_wait(base + L2X0_CLEAN_LINE_PA, 1); - cache_sync(); + + flags = l2c220_op_pa_range(base + L2X0_INV_LINE_PA, + start, end, flags); + l2c_wait_mask(base + L2X0_INV_LINE_PA, 1); + __l2c220_cache_sync(base); raw_spin_unlock_irqrestore(&l2x0_lock, flags); } -static void l2x0_flush_range(unsigned long start, unsigned long end) +static void l2c220_clean_range(unsigned long start, unsigned long end) { void __iomem *base = l2x0_base; unsigned long flags; + start &= ~(CACHE_LINE_SIZE - 1); if ((end - start) >= l2x0_size) { - l2x0_flush_all(); + l2c220_op_way(base, L2X0_CLEAN_WAY); return; } raw_spin_lock_irqsave(&l2x0_lock, flags); + flags = l2c220_op_pa_range(base + L2X0_CLEAN_LINE_PA, + start, end, flags); + l2c_wait_mask(base + L2X0_CLEAN_INV_LINE_PA, 1); + __l2c220_cache_sync(base); + raw_spin_unlock_irqrestore(&l2x0_lock, flags); +} + +static void l2c220_flush_range(unsigned long start, unsigned long end) +{ + void __iomem *base = l2x0_base; + unsigned long flags; + start &= ~(CACHE_LINE_SIZE - 1); + if ((end - start) >= l2x0_size) { + l2c220_op_way(base, L2X0_CLEAN_INV_WAY); + return; + } + + raw_spin_lock_irqsave(&l2x0_lock, flags); + flags = l2c220_op_pa_range(base + L2X0_CLEAN_INV_LINE_PA, + start, end, flags); + l2c_wait_mask(base + L2X0_CLEAN_INV_LINE_PA, 1); + __l2c220_cache_sync(base); + raw_spin_unlock_irqrestore(&l2x0_lock, flags); +} + +static void l2c220_flush_all(void) +{ + l2c220_op_way(l2x0_base, L2X0_CLEAN_INV_WAY); +} + +static void l2c220_sync(void) +{ + unsigned long flags; + + raw_spin_lock_irqsave(&l2x0_lock, flags); + __l2c220_cache_sync(l2x0_base); + raw_spin_unlock_irqrestore(&l2x0_lock, flags); +} + +static void l2c220_enable(void __iomem *base, u32 aux, unsigned num_lock) +{ + /* + * Always enable non-secure access to the lockdown registers - + * we write to them as part of the L2C enable sequence so they + * need to be accessible. + */ + aux |= L220_AUX_CTRL_NS_LOCKDOWN; + + l2c_enable(base, aux, num_lock); +} + +static const struct l2c_init_data l2c220_data = { + .type = "L2C-220", + .way_size_0 = SZ_8K, + .num_lock = 1, + .enable = l2c220_enable, + .save = l2c_save, + .outer_cache = { + .inv_range = l2c220_inv_range, + .clean_range = l2c220_clean_range, + .flush_range = l2c220_flush_range, + .flush_all = l2c220_flush_all, + .disable = l2c_disable, + .sync = l2c220_sync, + .resume = l2c210_resume, + }, +}; + +/* + * L2C-310 specific code. + * + * Very similar to L2C-210, the PA, set/way and sync operations are atomic, + * and the way operations are all background tasks. However, issuing an + * operation while a background operation is in progress results in a + * SLVERR response. We can reuse: + * + * __l2c210_cache_sync (using sync_reg_offset) + * l2c210_sync + * l2c210_inv_range (if 588369 is not applicable) + * l2c210_clean_range + * l2c210_flush_range (if 588369 is not applicable) + * l2c210_flush_all (if 727915 is not applicable) + * + * Errata: + * 588369: PL310 R0P0->R1P0, fixed R2P0. + * Affects: all clean+invalidate operations + * clean and invalidate skips the invalidate step, so we need to issue + * separate operations. We also require the above debug workaround + * enclosing this code fragment on affected parts. On unaffected parts, + * we must not use this workaround without the debug register writes + * to avoid exposing a problem similar to 727915. + * + * 727915: PL310 R2P0->R3P0, fixed R3P1. + * Affects: clean+invalidate by way + * clean and invalidate by way runs in the background, and a store can + * hit the line between the clean operation and invalidate operation, + * resulting in the store being lost. + * + * 752271: PL310 R3P0->R3P1-50REL0, fixed R3P2. + * Affects: 8x64-bit (double fill) line fetches + * double fill line fetches can fail to cause dirty data to be evicted + * from the cache before the new data overwrites the second line. + * + * 753970: PL310 R3P0, fixed R3P1. + * Affects: sync + * prevents merging writes after the sync operation, until another L2C + * operation is performed (or a number of other conditions.) + * + * 769419: PL310 R0P0->R3P1, fixed R3P2. + * Affects: store buffer + * store buffer is not automatically drained. + */ +static void l2c310_inv_range_erratum(unsigned long start, unsigned long end) +{ + void __iomem *base = l2x0_base; + + if ((start | end) & (CACHE_LINE_SIZE - 1)) { + unsigned long flags; + + /* Erratum 588369 for both clean+invalidate operations */ + raw_spin_lock_irqsave(&l2x0_lock, flags); + l2c_set_debug(base, 0x03); + + if (start & (CACHE_LINE_SIZE - 1)) { + start &= ~(CACHE_LINE_SIZE - 1); + writel_relaxed(start, base + L2X0_CLEAN_LINE_PA); + writel_relaxed(start, base + L2X0_INV_LINE_PA); + start += CACHE_LINE_SIZE; + } + + if (end & (CACHE_LINE_SIZE - 1)) { + end &= ~(CACHE_LINE_SIZE - 1); + writel_relaxed(end, base + L2X0_CLEAN_LINE_PA); + writel_relaxed(end, base + L2X0_INV_LINE_PA); + } + + l2c_set_debug(base, 0x00); + raw_spin_unlock_irqrestore(&l2x0_lock, flags); + } + + __l2c210_op_pa_range(base + L2X0_INV_LINE_PA, start, end); + __l2c210_cache_sync(base); +} + +static void l2c310_flush_range_erratum(unsigned long start, unsigned long end) +{ + raw_spinlock_t *lock = &l2x0_lock; + unsigned long flags; + void __iomem *base = l2x0_base; + + raw_spin_lock_irqsave(lock, flags); while (start < end) { unsigned long blk_end = start + min(end - start, 4096UL); - debug_writel(0x03); + l2c_set_debug(base, 0x03); while (start < blk_end) { - l2x0_flush_line(start); + writel_relaxed(start, base + L2X0_CLEAN_LINE_PA); + writel_relaxed(start, base + L2X0_INV_LINE_PA); start += CACHE_LINE_SIZE; } - debug_writel(0x00); + l2c_set_debug(base, 0x00); if (blk_end < end) { - raw_spin_unlock_irqrestore(&l2x0_lock, flags); - raw_spin_lock_irqsave(&l2x0_lock, flags); + raw_spin_unlock_irqrestore(lock, flags); + raw_spin_lock_irqsave(lock, flags); } } - cache_wait(base + L2X0_CLEAN_INV_LINE_PA, 1); - cache_sync(); - raw_spin_unlock_irqrestore(&l2x0_lock, flags); + raw_spin_unlock_irqrestore(lock, flags); + __l2c210_cache_sync(base); } -static void l2x0_disable(void) +static void l2c310_flush_all_erratum(void) { + void __iomem *base = l2x0_base; unsigned long flags; raw_spin_lock_irqsave(&l2x0_lock, flags); - __l2x0_flush_all(); - writel_relaxed(0, l2x0_base + L2X0_CTRL); - dsb(st); + l2c_set_debug(base, 0x03); + __l2c_op_way(base + L2X0_CLEAN_INV_WAY); + l2c_set_debug(base, 0x00); + __l2c210_cache_sync(base); raw_spin_unlock_irqrestore(&l2x0_lock, flags); } -static void l2x0_unlock(u32 cache_id) +static void __init l2c310_save(void __iomem *base) { - int lockregs; - int i; + unsigned revision; - switch (cache_id & L2X0_CACHE_ID_PART_MASK) { - case L2X0_CACHE_ID_PART_L310: - lockregs = 8; - break; - case AURORA_CACHE_ID: - lockregs = 4; + l2c_save(base); + + l2x0_saved_regs.tag_latency = readl_relaxed(base + + L310_TAG_LATENCY_CTRL); + l2x0_saved_regs.data_latency = readl_relaxed(base + + L310_DATA_LATENCY_CTRL); + l2x0_saved_regs.filter_end = readl_relaxed(base + + L310_ADDR_FILTER_END); + l2x0_saved_regs.filter_start = readl_relaxed(base + + L310_ADDR_FILTER_START); + + revision = readl_relaxed(base + L2X0_CACHE_ID) & + L2X0_CACHE_ID_RTL_MASK; + + /* From r2p0, there is Prefetch offset/control register */ + if (revision >= L310_CACHE_ID_RTL_R2P0) + l2x0_saved_regs.prefetch_ctrl = readl_relaxed(base + + L310_PREFETCH_CTRL); + + /* From r3p0, there is Power control register */ + if (revision >= L310_CACHE_ID_RTL_R3P0) + l2x0_saved_regs.pwr_ctrl = readl_relaxed(base + + L310_POWER_CTRL); +} + +static void l2c310_resume(void) +{ + void __iomem *base = l2x0_base; + + if (!(readl_relaxed(base + L2X0_CTRL) & L2X0_CTRL_EN)) { + unsigned revision; + + /* restore pl310 setup */ + writel_relaxed(l2x0_saved_regs.tag_latency, + base + L310_TAG_LATENCY_CTRL); + writel_relaxed(l2x0_saved_regs.data_latency, + base + L310_DATA_LATENCY_CTRL); + writel_relaxed(l2x0_saved_regs.filter_end, + base + L310_ADDR_FILTER_END); + writel_relaxed(l2x0_saved_regs.filter_start, + base + L310_ADDR_FILTER_START); + + revision = readl_relaxed(base + L2X0_CACHE_ID) & + L2X0_CACHE_ID_RTL_MASK; + + if (revision >= L310_CACHE_ID_RTL_R2P0) + l2c_write_sec(l2x0_saved_regs.prefetch_ctrl, base, + L310_PREFETCH_CTRL); + if (revision >= L310_CACHE_ID_RTL_R3P0) + l2c_write_sec(l2x0_saved_regs.pwr_ctrl, base, + L310_POWER_CTRL); + + l2c_enable(base, l2x0_saved_regs.aux_ctrl, 8); + + /* Re-enable full-line-of-zeros for Cortex-A9 */ + if (l2x0_saved_regs.aux_ctrl & L310_AUX_CTRL_FULL_LINE_ZERO) + set_auxcr(get_auxcr() | BIT(3) | BIT(2) | BIT(1)); + } +} + +static int l2c310_cpu_enable_flz(struct notifier_block *nb, unsigned long act, void *data) +{ + switch (act & ~CPU_TASKS_FROZEN) { + case CPU_STARTING: + set_auxcr(get_auxcr() | BIT(3) | BIT(2) | BIT(1)); break; - default: - /* L210 and unknown types */ - lockregs = 1; + case CPU_DYING: + set_auxcr(get_auxcr() & ~(BIT(3) | BIT(2) | BIT(1))); break; } + return NOTIFY_OK; +} - for (i = 0; i < lockregs; i++) { - writel_relaxed(0x0, l2x0_base + L2X0_LOCKDOWN_WAY_D_BASE + - i * L2X0_LOCKDOWN_STRIDE); - writel_relaxed(0x0, l2x0_base + L2X0_LOCKDOWN_WAY_I_BASE + - i * L2X0_LOCKDOWN_STRIDE); +static void __init l2c310_enable(void __iomem *base, u32 aux, unsigned num_lock) +{ + unsigned rev = readl_relaxed(base + L2X0_CACHE_ID) & L2X0_CACHE_ID_RTL_MASK; + bool cortex_a9 = read_cpuid_part() == ARM_CPU_PART_CORTEX_A9; + + if (rev >= L310_CACHE_ID_RTL_R2P0) { + if (cortex_a9) { + aux |= L310_AUX_CTRL_EARLY_BRESP; + pr_info("L2C-310 enabling early BRESP for Cortex-A9\n"); + } else if (aux & L310_AUX_CTRL_EARLY_BRESP) { + pr_warn("L2C-310 early BRESP only supported with Cortex-A9\n"); + aux &= ~L310_AUX_CTRL_EARLY_BRESP; + } + } + + if (cortex_a9) { + u32 aux_cur = readl_relaxed(base + L2X0_AUX_CTRL); + u32 acr = get_auxcr(); + + pr_debug("Cortex-A9 ACR=0x%08x\n", acr); + + if (acr & BIT(3) && !(aux_cur & L310_AUX_CTRL_FULL_LINE_ZERO)) + pr_err("L2C-310: full line of zeros enabled in Cortex-A9 but not L2C-310 - invalid\n"); + + if (aux & L310_AUX_CTRL_FULL_LINE_ZERO && !(acr & BIT(3))) + pr_err("L2C-310: enabling full line of zeros but not enabled in Cortex-A9\n"); + + if (!(aux & L310_AUX_CTRL_FULL_LINE_ZERO) && !outer_cache.write_sec) { + aux |= L310_AUX_CTRL_FULL_LINE_ZERO; + pr_info("L2C-310 full line of zeros enabled for Cortex-A9\n"); + } + } else if (aux & (L310_AUX_CTRL_FULL_LINE_ZERO | L310_AUX_CTRL_EARLY_BRESP)) { + pr_err("L2C-310: disabling Cortex-A9 specific feature bits\n"); + aux &= ~(L310_AUX_CTRL_FULL_LINE_ZERO | L310_AUX_CTRL_EARLY_BRESP); + } + + if (aux & (L310_AUX_CTRL_DATA_PREFETCH | L310_AUX_CTRL_INSTR_PREFETCH)) { + u32 prefetch = readl_relaxed(base + L310_PREFETCH_CTRL); + + pr_info("L2C-310 %s%s prefetch enabled, offset %u lines\n", + aux & L310_AUX_CTRL_INSTR_PREFETCH ? "I" : "", + aux & L310_AUX_CTRL_DATA_PREFETCH ? "D" : "", + 1 + (prefetch & L310_PREFETCH_CTRL_OFFSET_MASK)); + } + + /* r3p0 or later has power control register */ + if (rev >= L310_CACHE_ID_RTL_R3P0) { + u32 power_ctrl; + + l2c_write_sec(L310_DYNAMIC_CLK_GATING_EN | L310_STNDBY_MODE_EN, + base, L310_POWER_CTRL); + power_ctrl = readl_relaxed(base + L310_POWER_CTRL); + pr_info("L2C-310 dynamic clock gating %sabled, standby mode %sabled\n", + power_ctrl & L310_DYNAMIC_CLK_GATING_EN ? "en" : "dis", + power_ctrl & L310_STNDBY_MODE_EN ? "en" : "dis"); + } + + /* + * Always enable non-secure access to the lockdown registers - + * we write to them as part of the L2C enable sequence so they + * need to be accessible. + */ + aux |= L310_AUX_CTRL_NS_LOCKDOWN; + + l2c_enable(base, aux, num_lock); + + if (aux & L310_AUX_CTRL_FULL_LINE_ZERO) { + set_auxcr(get_auxcr() | BIT(3) | BIT(2) | BIT(1)); + cpu_notifier(l2c310_cpu_enable_flz, 0); } } -void __init l2x0_init(void __iomem *base, u32 aux_val, u32 aux_mask) +static void __init l2c310_fixup(void __iomem *base, u32 cache_id, + struct outer_cache_fns *fns) { - u32 aux; - u32 cache_id; - u32 way_size = 0; - int ways; - int way_size_shift = L2X0_WAY_SIZE_SHIFT; - const char *type; + unsigned revision = cache_id & L2X0_CACHE_ID_RTL_MASK; + const char *errata[8]; + unsigned n = 0; + + if (IS_ENABLED(CONFIG_PL310_ERRATA_588369) && + revision < L310_CACHE_ID_RTL_R2P0 && + /* For bcm compatibility */ + fns->inv_range == l2c210_inv_range) { + fns->inv_range = l2c310_inv_range_erratum; + fns->flush_range = l2c310_flush_range_erratum; + errata[n++] = "588369"; + } - l2x0_base = base; - if (cache_id_part_number_from_dt) - cache_id = cache_id_part_number_from_dt; - else - cache_id = readl_relaxed(l2x0_base + L2X0_CACHE_ID); - aux = readl_relaxed(l2x0_base + L2X0_AUX_CTRL); + if (IS_ENABLED(CONFIG_PL310_ERRATA_727915) && + revision >= L310_CACHE_ID_RTL_R2P0 && + revision < L310_CACHE_ID_RTL_R3P1) { + fns->flush_all = l2c310_flush_all_erratum; + errata[n++] = "727915"; + } + if (revision >= L310_CACHE_ID_RTL_R3P0 && + revision < L310_CACHE_ID_RTL_R3P2) { + u32 val = readl_relaxed(base + L310_PREFETCH_CTRL); + /* I don't think bit23 is required here... but iMX6 does so */ + if (val & (BIT(30) | BIT(23))) { + val &= ~(BIT(30) | BIT(23)); + l2c_write_sec(val, base, L310_PREFETCH_CTRL); + errata[n++] = "752271"; + } + } + + if (IS_ENABLED(CONFIG_PL310_ERRATA_753970) && + revision == L310_CACHE_ID_RTL_R3P0) { + sync_reg_offset = L2X0_DUMMY_REG; + errata[n++] = "753970"; + } + + if (IS_ENABLED(CONFIG_PL310_ERRATA_769419)) + errata[n++] = "769419"; + + if (n) { + unsigned i; + + pr_info("L2C-310 errat%s", n > 1 ? "a" : "um"); + for (i = 0; i < n; i++) + pr_cont(" %s", errata[i]); + pr_cont(" enabled\n"); + } +} + +static void l2c310_disable(void) +{ + /* + * If full-line-of-zeros is enabled, we must first disable it in the + * Cortex-A9 auxiliary control register before disabling the L2 cache. + */ + if (l2x0_saved_regs.aux_ctrl & L310_AUX_CTRL_FULL_LINE_ZERO) + set_auxcr(get_auxcr() & ~(BIT(3) | BIT(2) | BIT(1))); + + l2c_disable(); +} + +static const struct l2c_init_data l2c310_init_fns __initconst = { + .type = "L2C-310", + .way_size_0 = SZ_8K, + .num_lock = 8, + .enable = l2c310_enable, + .fixup = l2c310_fixup, + .save = l2c310_save, + .outer_cache = { + .inv_range = l2c210_inv_range, + .clean_range = l2c210_clean_range, + .flush_range = l2c210_flush_range, + .flush_all = l2c210_flush_all, + .disable = l2c310_disable, + .sync = l2c210_sync, + .resume = l2c310_resume, + }, +}; + +static void __init __l2c_init(const struct l2c_init_data *data, + u32 aux_val, u32 aux_mask, u32 cache_id) +{ + struct outer_cache_fns fns; + unsigned way_size_bits, ways; + u32 aux, old_aux; + + /* + * Sanity check the aux values. aux_mask is the bits we preserve + * from reading the hardware register, and aux_val is the bits we + * set. + */ + if (aux_val & aux_mask) + pr_alert("L2C: platform provided aux values permit register corruption.\n"); + + old_aux = aux = readl_relaxed(l2x0_base + L2X0_AUX_CTRL); aux &= aux_mask; aux |= aux_val; + if (old_aux != aux) + pr_warn("L2C: DT/platform modifies aux control register: 0x%08x -> 0x%08x\n", + old_aux, aux); + /* Determine the number of ways */ switch (cache_id & L2X0_CACHE_ID_PART_MASK) { case L2X0_CACHE_ID_PART_L310: + if ((aux_val | ~aux_mask) & (L2C_AUX_CTRL_WAY_SIZE_MASK | L310_AUX_CTRL_ASSOCIATIVITY_16)) + pr_warn("L2C: DT/platform tries to modify or specify cache size\n"); if (aux & (1 << 16)) ways = 16; else ways = 8; - type = "L310"; -#ifdef CONFIG_PL310_ERRATA_753970 - /* Unmapped register. */ - sync_reg_offset = L2X0_DUMMY_REG; -#endif - if ((cache_id & L2X0_CACHE_ID_RTL_MASK) <= L2X0_CACHE_ID_RTL_R3P0) - outer_cache.set_debug = pl310_set_debug; break; + case L2X0_CACHE_ID_PART_L210: + case L2X0_CACHE_ID_PART_L220: ways = (aux >> 13) & 0xf; - type = "L210"; break; case AURORA_CACHE_ID: - sync_reg_offset = AURORA_SYNC_REG; ways = (aux >> 13) & 0xf; ways = 2 << ((ways + 1) >> 2); - way_size_shift = AURORA_WAY_SIZE_SHIFT; - type = "Aurora"; break; + default: /* Assume unknown chips have 8 ways */ ways = 8; - type = "L2x0 series"; break; } l2x0_way_mask = (1 << ways) - 1; /* - * L2 cache Size = Way size * Number of ways + * way_size_0 is the size that a way_size value of zero would be + * given the calculation: way_size = way_size_0 << way_size_bits. + * So, if way_size_bits=0 is reserved, but way_size_bits=1 is 16k, + * then way_size_0 would be 8k. + * + * L2 cache size = number of ways * way size. */ - way_size = (aux & L2X0_AUX_CTRL_WAY_SIZE_MASK) >> 17; - way_size = 1 << (way_size + way_size_shift); + way_size_bits = (aux & L2C_AUX_CTRL_WAY_SIZE_MASK) >> + L2C_AUX_CTRL_WAY_SIZE_SHIFT; + l2x0_size = ways * (data->way_size_0 << way_size_bits); - l2x0_size = ways * way_size * SZ_1K; + fns = data->outer_cache; + fns.write_sec = outer_cache.write_sec; + if (data->fixup) + data->fixup(l2x0_base, cache_id, &fns); /* - * Check if l2x0 controller is already enabled. - * If you are booting from non-secure mode - * accessing the below registers will fault. + * Check if l2x0 controller is already enabled. If we are booting + * in non-secure mode accessing the below registers will fault. */ - if (!(readl_relaxed(l2x0_base + L2X0_CTRL) & L2X0_CTRL_EN)) { - /* Make sure that I&D is not locked down when starting */ - l2x0_unlock(cache_id); + if (!(readl_relaxed(l2x0_base + L2X0_CTRL) & L2X0_CTRL_EN)) + data->enable(l2x0_base, aux, data->num_lock); - /* l2x0 controller is disabled */ - writel_relaxed(aux, l2x0_base + L2X0_AUX_CTRL); + outer_cache = fns; - l2x0_inv_all(); - - /* enable L2X0 */ - writel_relaxed(L2X0_CTRL_EN, l2x0_base + L2X0_CTRL); - } + /* + * It is strange to save the register state before initialisation, + * but hey, this is what the DT implementations decided to do. + */ + if (data->save) + data->save(l2x0_base); /* Re-read it in case some bits are reserved. */ aux = readl_relaxed(l2x0_base + L2X0_AUX_CTRL); - /* Save the value for resuming. */ - l2x0_saved_regs.aux_ctrl = aux; + pr_info("%s cache controller enabled, %d ways, %d kB\n", + data->type, ways, l2x0_size >> 10); + pr_info("%s: CACHE_ID 0x%08x, AUX_CTRL 0x%08x\n", + data->type, cache_id, aux); +} + +void __init l2x0_init(void __iomem *base, u32 aux_val, u32 aux_mask) +{ + const struct l2c_init_data *data; + u32 cache_id; - if (!of_init) { - outer_cache.inv_range = l2x0_inv_range; - 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; + l2x0_base = base; + + cache_id = readl_relaxed(base + L2X0_CACHE_ID); + + switch (cache_id & L2X0_CACHE_ID_PART_MASK) { + default: + case L2X0_CACHE_ID_PART_L210: + data = &l2c210_data; + break; + + case L2X0_CACHE_ID_PART_L220: + data = &l2c220_data; + break; + + case L2X0_CACHE_ID_PART_L310: + data = &l2c310_init_fns; + break; } - pr_info("%s cache controller enabled\n", type); - pr_info("l2x0: %d ways, CACHE_ID 0x%08x, AUX_CTRL 0x%08x, Cache size: %d kB\n", - ways, cache_id, aux, l2x0_size >> 10); + __l2c_init(data, aux_val, aux_mask, cache_id); } #ifdef CONFIG_OF static int l2_wt_override; +/* Aurora don't have the cache ID register available, so we have to + * pass it though the device tree */ +static u32 cache_id_part_number_from_dt; + +static void __init l2x0_of_parse(const struct device_node *np, + u32 *aux_val, u32 *aux_mask) +{ + u32 data[2] = { 0, 0 }; + u32 tag = 0; + u32 dirty = 0; + u32 val = 0, mask = 0; + + of_property_read_u32(np, "arm,tag-latency", &tag); + if (tag) { + mask |= L2X0_AUX_CTRL_TAG_LATENCY_MASK; + val |= (tag - 1) << L2X0_AUX_CTRL_TAG_LATENCY_SHIFT; + } + + of_property_read_u32_array(np, "arm,data-latency", + data, ARRAY_SIZE(data)); + if (data[0] && data[1]) { + mask |= L2X0_AUX_CTRL_DATA_RD_LATENCY_MASK | + L2X0_AUX_CTRL_DATA_WR_LATENCY_MASK; + val |= ((data[0] - 1) << L2X0_AUX_CTRL_DATA_RD_LATENCY_SHIFT) | + ((data[1] - 1) << L2X0_AUX_CTRL_DATA_WR_LATENCY_SHIFT); + } + + of_property_read_u32(np, "arm,dirty-latency", &dirty); + if (dirty) { + mask |= L2X0_AUX_CTRL_DIRTY_LATENCY_MASK; + val |= (dirty - 1) << L2X0_AUX_CTRL_DIRTY_LATENCY_SHIFT; + } + + *aux_val &= ~mask; + *aux_val |= val; + *aux_mask &= ~mask; +} + +static const struct l2c_init_data of_l2c210_data __initconst = { + .type = "L2C-210", + .way_size_0 = SZ_8K, + .num_lock = 1, + .of_parse = l2x0_of_parse, + .enable = l2c_enable, + .save = l2c_save, + .outer_cache = { + .inv_range = l2c210_inv_range, + .clean_range = l2c210_clean_range, + .flush_range = l2c210_flush_range, + .flush_all = l2c210_flush_all, + .disable = l2c_disable, + .sync = l2c210_sync, + .resume = l2c210_resume, + }, +}; + +static const struct l2c_init_data of_l2c220_data __initconst = { + .type = "L2C-220", + .way_size_0 = SZ_8K, + .num_lock = 1, + .of_parse = l2x0_of_parse, + .enable = l2c220_enable, + .save = l2c_save, + .outer_cache = { + .inv_range = l2c220_inv_range, + .clean_range = l2c220_clean_range, + .flush_range = l2c220_flush_range, + .flush_all = l2c220_flush_all, + .disable = l2c_disable, + .sync = l2c220_sync, + .resume = l2c210_resume, + }, +}; + +static void __init l2c310_of_parse(const struct device_node *np, + u32 *aux_val, u32 *aux_mask) +{ + u32 data[3] = { 0, 0, 0 }; + u32 tag[3] = { 0, 0, 0 }; + u32 filter[2] = { 0, 0 }; + + of_property_read_u32_array(np, "arm,tag-latency", tag, ARRAY_SIZE(tag)); + if (tag[0] && tag[1] && tag[2]) + writel_relaxed( + L310_LATENCY_CTRL_RD(tag[0] - 1) | + L310_LATENCY_CTRL_WR(tag[1] - 1) | + L310_LATENCY_CTRL_SETUP(tag[2] - 1), + l2x0_base + L310_TAG_LATENCY_CTRL); + + of_property_read_u32_array(np, "arm,data-latency", + data, ARRAY_SIZE(data)); + if (data[0] && data[1] && data[2]) + writel_relaxed( + L310_LATENCY_CTRL_RD(data[0] - 1) | + L310_LATENCY_CTRL_WR(data[1] - 1) | + L310_LATENCY_CTRL_SETUP(data[2] - 1), + l2x0_base + L310_DATA_LATENCY_CTRL); + + of_property_read_u32_array(np, "arm,filter-ranges", + filter, ARRAY_SIZE(filter)); + if (filter[1]) { + writel_relaxed(ALIGN(filter[0] + filter[1], SZ_1M), + l2x0_base + L310_ADDR_FILTER_END); + writel_relaxed((filter[0] & ~(SZ_1M - 1)) | L310_ADDR_FILTER_EN, + l2x0_base + L310_ADDR_FILTER_START); + } +} + +static const struct l2c_init_data of_l2c310_data __initconst = { + .type = "L2C-310", + .way_size_0 = SZ_8K, + .num_lock = 8, + .of_parse = l2c310_of_parse, + .enable = l2c310_enable, + .fixup = l2c310_fixup, + .save = l2c310_save, + .outer_cache = { + .inv_range = l2c210_inv_range, + .clean_range = l2c210_clean_range, + .flush_range = l2c210_flush_range, + .flush_all = l2c210_flush_all, + .disable = l2c310_disable, + .sync = l2c210_sync, + .resume = l2c310_resume, + }, +}; + +/* + * This is a variant of the of_l2c310_data with .sync set to + * NULL. Outer sync operations are not needed when the system is I/O + * coherent, and potentially harmful in certain situations (PCIe/PL310 + * deadlock on Armada 375/38x due to hardware I/O coherency). The + * other operations are kept because they are infrequent (therefore do + * not cause the deadlock in practice) and needed for secondary CPU + * boot and other power management activities. + */ +static const struct l2c_init_data of_l2c310_coherent_data __initconst = { + .type = "L2C-310 Coherent", + .way_size_0 = SZ_8K, + .num_lock = 8, + .of_parse = l2c310_of_parse, + .enable = l2c310_enable, + .fixup = l2c310_fixup, + .save = l2c310_save, + .outer_cache = { + .inv_range = l2c210_inv_range, + .clean_range = l2c210_clean_range, + .flush_range = l2c210_flush_range, + .flush_all = l2c210_flush_all, + .disable = l2c310_disable, + .resume = l2c310_resume, + }, +}; + /* * Note that the end addresses passed to Linux primitives are * noninclusive, while the hardware cache range operations use @@ -524,6 +1193,100 @@ static void aurora_flush_range(unsigned long start, unsigned long end) } } +static void aurora_save(void __iomem *base) +{ + l2x0_saved_regs.ctrl = readl_relaxed(base + L2X0_CTRL); + l2x0_saved_regs.aux_ctrl = readl_relaxed(base + L2X0_AUX_CTRL); +} + +static void aurora_resume(void) +{ + void __iomem *base = l2x0_base; + + if (!(readl(base + L2X0_CTRL) & L2X0_CTRL_EN)) { + writel_relaxed(l2x0_saved_regs.aux_ctrl, base + L2X0_AUX_CTRL); + writel_relaxed(l2x0_saved_regs.ctrl, base + L2X0_CTRL); + } +} + +/* + * For Aurora cache in no outer mode, enable via the CP15 coprocessor + * broadcasting of cache commands to L2. + */ +static void __init aurora_enable_no_outer(void __iomem *base, u32 aux, + unsigned num_lock) +{ + u32 u; + + asm volatile("mrc p15, 1, %0, c15, c2, 0" : "=r" (u)); + u |= AURORA_CTRL_FW; /* Set the FW bit */ + asm volatile("mcr p15, 1, %0, c15, c2, 0" : : "r" (u)); + + isb(); + + l2c_enable(base, aux, num_lock); +} + +static void __init aurora_fixup(void __iomem *base, u32 cache_id, + struct outer_cache_fns *fns) +{ + sync_reg_offset = AURORA_SYNC_REG; +} + +static void __init aurora_of_parse(const struct device_node *np, + u32 *aux_val, u32 *aux_mask) +{ + u32 val = AURORA_ACR_REPLACEMENT_TYPE_SEMIPLRU; + u32 mask = AURORA_ACR_REPLACEMENT_MASK; + + of_property_read_u32(np, "cache-id-part", + &cache_id_part_number_from_dt); + + /* Determine and save the write policy */ + l2_wt_override = of_property_read_bool(np, "wt-override"); + + if (l2_wt_override) { + val |= AURORA_ACR_FORCE_WRITE_THRO_POLICY; + mask |= AURORA_ACR_FORCE_WRITE_POLICY_MASK; + } + + *aux_val &= ~mask; + *aux_val |= val; + *aux_mask &= ~mask; +} + +static const struct l2c_init_data of_aurora_with_outer_data __initconst = { + .type = "Aurora", + .way_size_0 = SZ_4K, + .num_lock = 4, + .of_parse = aurora_of_parse, + .enable = l2c_enable, + .fixup = aurora_fixup, + .save = aurora_save, + .outer_cache = { + .inv_range = aurora_inv_range, + .clean_range = aurora_clean_range, + .flush_range = aurora_flush_range, + .flush_all = l2x0_flush_all, + .disable = l2x0_disable, + .sync = l2x0_cache_sync, + .resume = aurora_resume, + }, +}; + +static const struct l2c_init_data of_aurora_no_outer_data __initconst = { + .type = "Aurora", + .way_size_0 = SZ_4K, + .num_lock = 4, + .of_parse = aurora_of_parse, + .enable = aurora_enable_no_outer, + .fixup = aurora_fixup, + .save = aurora_save, + .outer_cache = { + .resume = aurora_resume, + }, +}; + /* * For certain Broadcom SoCs, depending on the address range, different offsets * need to be added to the address before passing it to L2 for @@ -588,16 +1351,16 @@ static void bcm_inv_range(unsigned long start, unsigned long end) /* normal case, no cross section between start and end */ if (likely(bcm_addr_is_sys_emi(end) || !bcm_addr_is_sys_emi(start))) { - l2x0_inv_range(new_start, new_end); + l2c210_inv_range(new_start, new_end); return; } /* They cross sections, so it can only be a cross from section * 2 to section 3 */ - l2x0_inv_range(new_start, + l2c210_inv_range(new_start, bcm_l2_phys_addr(BCM_VC_EMI_SEC3_START_ADDR-1)); - l2x0_inv_range(bcm_l2_phys_addr(BCM_VC_EMI_SEC3_START_ADDR), + l2c210_inv_range(bcm_l2_phys_addr(BCM_VC_EMI_SEC3_START_ADDR), new_end); } @@ -610,26 +1373,21 @@ static void bcm_clean_range(unsigned long start, unsigned long end) if (unlikely(end <= start)) return; - if ((end - start) >= l2x0_size) { - l2x0_clean_all(); - return; - } - new_start = bcm_l2_phys_addr(start); new_end = bcm_l2_phys_addr(end); /* normal case, no cross section between start and end */ if (likely(bcm_addr_is_sys_emi(end) || !bcm_addr_is_sys_emi(start))) { - l2x0_clean_range(new_start, new_end); + l2c210_clean_range(new_start, new_end); return; } /* They cross sections, so it can only be a cross from section * 2 to section 3 */ - l2x0_clean_range(new_start, + l2c210_clean_range(new_start, bcm_l2_phys_addr(BCM_VC_EMI_SEC3_START_ADDR-1)); - l2x0_clean_range(bcm_l2_phys_addr(BCM_VC_EMI_SEC3_START_ADDR), + l2c210_clean_range(bcm_l2_phys_addr(BCM_VC_EMI_SEC3_START_ADDR), new_end); } @@ -643,7 +1401,7 @@ static void bcm_flush_range(unsigned long start, unsigned long end) return; if ((end - start) >= l2x0_size) { - l2x0_flush_all(); + outer_cache.flush_all(); return; } @@ -652,283 +1410,67 @@ static void bcm_flush_range(unsigned long start, unsigned long end) /* normal case, no cross section between start and end */ if (likely(bcm_addr_is_sys_emi(end) || !bcm_addr_is_sys_emi(start))) { - l2x0_flush_range(new_start, new_end); + l2c210_flush_range(new_start, new_end); return; } /* They cross sections, so it can only be a cross from section * 2 to section 3 */ - l2x0_flush_range(new_start, + l2c210_flush_range(new_start, bcm_l2_phys_addr(BCM_VC_EMI_SEC3_START_ADDR-1)); - l2x0_flush_range(bcm_l2_phys_addr(BCM_VC_EMI_SEC3_START_ADDR), + l2c210_flush_range(bcm_l2_phys_addr(BCM_VC_EMI_SEC3_START_ADDR), new_end); } -static void __init l2x0_of_setup(const struct device_node *np, - u32 *aux_val, u32 *aux_mask) -{ - u32 data[2] = { 0, 0 }; - u32 tag = 0; - u32 dirty = 0; - u32 val = 0, mask = 0; - - of_property_read_u32(np, "arm,tag-latency", &tag); - if (tag) { - mask |= L2X0_AUX_CTRL_TAG_LATENCY_MASK; - val |= (tag - 1) << L2X0_AUX_CTRL_TAG_LATENCY_SHIFT; - } - - of_property_read_u32_array(np, "arm,data-latency", - data, ARRAY_SIZE(data)); - if (data[0] && data[1]) { - mask |= L2X0_AUX_CTRL_DATA_RD_LATENCY_MASK | - L2X0_AUX_CTRL_DATA_WR_LATENCY_MASK; - val |= ((data[0] - 1) << L2X0_AUX_CTRL_DATA_RD_LATENCY_SHIFT) | - ((data[1] - 1) << L2X0_AUX_CTRL_DATA_WR_LATENCY_SHIFT); - } - - of_property_read_u32(np, "arm,dirty-latency", &dirty); - if (dirty) { - mask |= L2X0_AUX_CTRL_DIRTY_LATENCY_MASK; - val |= (dirty - 1) << L2X0_AUX_CTRL_DIRTY_LATENCY_SHIFT; - } - - *aux_val &= ~mask; - *aux_val |= val; - *aux_mask &= ~mask; -} - -static void __init pl310_of_setup(const struct device_node *np, - u32 *aux_val, u32 *aux_mask) -{ - u32 data[3] = { 0, 0, 0 }; - u32 tag[3] = { 0, 0, 0 }; - u32 filter[2] = { 0, 0 }; - - of_property_read_u32_array(np, "arm,tag-latency", tag, ARRAY_SIZE(tag)); - if (tag[0] && tag[1] && tag[2]) - writel_relaxed( - ((tag[0] - 1) << L2X0_LATENCY_CTRL_RD_SHIFT) | - ((tag[1] - 1) << L2X0_LATENCY_CTRL_WR_SHIFT) | - ((tag[2] - 1) << L2X0_LATENCY_CTRL_SETUP_SHIFT), - l2x0_base + L2X0_TAG_LATENCY_CTRL); - - of_property_read_u32_array(np, "arm,data-latency", - data, ARRAY_SIZE(data)); - if (data[0] && data[1] && data[2]) - writel_relaxed( - ((data[0] - 1) << L2X0_LATENCY_CTRL_RD_SHIFT) | - ((data[1] - 1) << L2X0_LATENCY_CTRL_WR_SHIFT) | - ((data[2] - 1) << L2X0_LATENCY_CTRL_SETUP_SHIFT), - l2x0_base + L2X0_DATA_LATENCY_CTRL); - - of_property_read_u32_array(np, "arm,filter-ranges", - filter, ARRAY_SIZE(filter)); - if (filter[1]) { - writel_relaxed(ALIGN(filter[0] + filter[1], SZ_1M), - l2x0_base + L2X0_ADDR_FILTER_END); - writel_relaxed((filter[0] & ~(SZ_1M - 1)) | L2X0_ADDR_FILTER_EN, - l2x0_base + L2X0_ADDR_FILTER_START); - } -} - -static void __init pl310_save(void) -{ - u32 l2x0_revision = readl_relaxed(l2x0_base + L2X0_CACHE_ID) & - L2X0_CACHE_ID_RTL_MASK; - - l2x0_saved_regs.tag_latency = readl_relaxed(l2x0_base + - L2X0_TAG_LATENCY_CTRL); - l2x0_saved_regs.data_latency = readl_relaxed(l2x0_base + - L2X0_DATA_LATENCY_CTRL); - l2x0_saved_regs.filter_end = readl_relaxed(l2x0_base + - L2X0_ADDR_FILTER_END); - l2x0_saved_regs.filter_start = readl_relaxed(l2x0_base + - L2X0_ADDR_FILTER_START); - - if (l2x0_revision >= L2X0_CACHE_ID_RTL_R2P0) { - /* - * From r2p0, there is Prefetch offset/control register - */ - l2x0_saved_regs.prefetch_ctrl = readl_relaxed(l2x0_base + - L2X0_PREFETCH_CTRL); - /* - * From r3p0, there is Power control register - */ - if (l2x0_revision >= L2X0_CACHE_ID_RTL_R3P0) - l2x0_saved_regs.pwr_ctrl = readl_relaxed(l2x0_base + - L2X0_POWER_CTRL); - } -} +/* Broadcom L2C-310 start from ARMs R3P2 or later, and require no fixups */ +static const struct l2c_init_data of_bcm_l2x0_data __initconst = { + .type = "BCM-L2C-310", + .way_size_0 = SZ_8K, + .num_lock = 8, + .of_parse = l2c310_of_parse, + .enable = l2c310_enable, + .save = l2c310_save, + .outer_cache = { + .inv_range = bcm_inv_range, + .clean_range = bcm_clean_range, + .flush_range = bcm_flush_range, + .flush_all = l2c210_flush_all, + .disable = l2c310_disable, + .sync = l2c210_sync, + .resume = l2c310_resume, + }, +}; -static void aurora_save(void) +static void __init tauros3_save(void __iomem *base) { - l2x0_saved_regs.ctrl = readl_relaxed(l2x0_base + L2X0_CTRL); - l2x0_saved_regs.aux_ctrl = readl_relaxed(l2x0_base + L2X0_AUX_CTRL); -} + l2c_save(base); -static void __init tauros3_save(void) -{ l2x0_saved_regs.aux2_ctrl = - readl_relaxed(l2x0_base + TAUROS3_AUX2_CTRL); + readl_relaxed(base + TAUROS3_AUX2_CTRL); l2x0_saved_regs.prefetch_ctrl = - readl_relaxed(l2x0_base + L2X0_PREFETCH_CTRL); -} - -static void l2x0_resume(void) -{ - if (!(readl_relaxed(l2x0_base + L2X0_CTRL) & L2X0_CTRL_EN)) { - /* restore aux ctrl and enable l2 */ - l2x0_unlock(readl_relaxed(l2x0_base + L2X0_CACHE_ID)); - - writel_relaxed(l2x0_saved_regs.aux_ctrl, l2x0_base + - L2X0_AUX_CTRL); - - l2x0_inv_all(); - - writel_relaxed(L2X0_CTRL_EN, l2x0_base + L2X0_CTRL); - } -} - -static void pl310_resume(void) -{ - u32 l2x0_revision; - - if (!(readl_relaxed(l2x0_base + L2X0_CTRL) & L2X0_CTRL_EN)) { - /* restore pl310 setup */ - writel_relaxed(l2x0_saved_regs.tag_latency, - l2x0_base + L2X0_TAG_LATENCY_CTRL); - writel_relaxed(l2x0_saved_regs.data_latency, - l2x0_base + L2X0_DATA_LATENCY_CTRL); - writel_relaxed(l2x0_saved_regs.filter_end, - l2x0_base + L2X0_ADDR_FILTER_END); - writel_relaxed(l2x0_saved_regs.filter_start, - l2x0_base + L2X0_ADDR_FILTER_START); - - l2x0_revision = readl_relaxed(l2x0_base + L2X0_CACHE_ID) & - L2X0_CACHE_ID_RTL_MASK; - - if (l2x0_revision >= L2X0_CACHE_ID_RTL_R2P0) { - writel_relaxed(l2x0_saved_regs.prefetch_ctrl, - l2x0_base + L2X0_PREFETCH_CTRL); - if (l2x0_revision >= L2X0_CACHE_ID_RTL_R3P0) - writel_relaxed(l2x0_saved_regs.pwr_ctrl, - l2x0_base + L2X0_POWER_CTRL); - } - } - - l2x0_resume(); -} - -static void aurora_resume(void) -{ - if (!(readl(l2x0_base + L2X0_CTRL) & L2X0_CTRL_EN)) { - writel_relaxed(l2x0_saved_regs.aux_ctrl, - l2x0_base + L2X0_AUX_CTRL); - writel_relaxed(l2x0_saved_regs.ctrl, l2x0_base + L2X0_CTRL); - } + readl_relaxed(base + L310_PREFETCH_CTRL); } static void tauros3_resume(void) { - if (!(readl_relaxed(l2x0_base + L2X0_CTRL) & L2X0_CTRL_EN)) { + void __iomem *base = l2x0_base; + + if (!(readl_relaxed(base + L2X0_CTRL) & L2X0_CTRL_EN)) { writel_relaxed(l2x0_saved_regs.aux2_ctrl, - l2x0_base + TAUROS3_AUX2_CTRL); + base + TAUROS3_AUX2_CTRL); writel_relaxed(l2x0_saved_regs.prefetch_ctrl, - l2x0_base + L2X0_PREFETCH_CTRL); - } - - l2x0_resume(); -} - -static void __init aurora_broadcast_l2_commands(void) -{ - __u32 u; - /* Enable Broadcasting of cache commands to L2*/ - __asm__ __volatile__("mrc p15, 1, %0, c15, c2, 0" : "=r"(u)); - u |= AURORA_CTRL_FW; /* Set the FW bit */ - __asm__ __volatile__("mcr p15, 1, %0, c15, c2, 0\n" : : "r"(u)); - isb(); -} - -static void __init aurora_of_setup(const struct device_node *np, - u32 *aux_val, u32 *aux_mask) -{ - u32 val = AURORA_ACR_REPLACEMENT_TYPE_SEMIPLRU; - u32 mask = AURORA_ACR_REPLACEMENT_MASK; - - of_property_read_u32(np, "cache-id-part", - &cache_id_part_number_from_dt); + base + L310_PREFETCH_CTRL); - /* Determine and save the write policy */ - l2_wt_override = of_property_read_bool(np, "wt-override"); - - if (l2_wt_override) { - val |= AURORA_ACR_FORCE_WRITE_THRO_POLICY; - mask |= AURORA_ACR_FORCE_WRITE_POLICY_MASK; + l2c_enable(base, l2x0_saved_regs.aux_ctrl, 8); } - - *aux_val &= ~mask; - *aux_val |= val; - *aux_mask &= ~mask; } -static const struct l2x0_of_data pl310_data = { - .setup = pl310_of_setup, - .save = pl310_save, - .outer_cache = { - .resume = pl310_resume, - .inv_range = l2x0_inv_range, - .clean_range = l2x0_clean_range, - .flush_range = l2x0_flush_range, - .sync = l2x0_cache_sync, - .flush_all = l2x0_flush_all, - .inv_all = l2x0_inv_all, - .disable = l2x0_disable, - }, -}; - -static const struct l2x0_of_data l2x0_data = { - .setup = l2x0_of_setup, - .save = NULL, - .outer_cache = { - .resume = l2x0_resume, - .inv_range = l2x0_inv_range, - .clean_range = l2x0_clean_range, - .flush_range = l2x0_flush_range, - .sync = l2x0_cache_sync, - .flush_all = l2x0_flush_all, - .inv_all = l2x0_inv_all, - .disable = l2x0_disable, - }, -}; - -static const struct l2x0_of_data aurora_with_outer_data = { - .setup = aurora_of_setup, - .save = aurora_save, - .outer_cache = { - .resume = aurora_resume, - .inv_range = aurora_inv_range, - .clean_range = aurora_clean_range, - .flush_range = aurora_flush_range, - .sync = l2x0_cache_sync, - .flush_all = l2x0_flush_all, - .inv_all = l2x0_inv_all, - .disable = l2x0_disable, - }, -}; - -static const struct l2x0_of_data aurora_no_outer_data = { - .setup = aurora_of_setup, - .save = aurora_save, - .outer_cache = { - .resume = aurora_resume, - }, -}; - -static const struct l2x0_of_data tauros3_data = { - .setup = NULL, +static const struct l2c_init_data of_tauros3_data __initconst = { + .type = "Tauros3", + .way_size_0 = SZ_8K, + .num_lock = 8, + .enable = l2c_enable, .save = tauros3_save, /* Tauros3 broadcasts L1 cache operations to L2 */ .outer_cache = { @@ -936,43 +1478,26 @@ static const struct l2x0_of_data tauros3_data = { }, }; -static const struct l2x0_of_data bcm_l2x0_data = { - .setup = pl310_of_setup, - .save = pl310_save, - .outer_cache = { - .resume = pl310_resume, - .inv_range = bcm_inv_range, - .clean_range = bcm_clean_range, - .flush_range = bcm_flush_range, - .sync = l2x0_cache_sync, - .flush_all = l2x0_flush_all, - .inv_all = l2x0_inv_all, - .disable = l2x0_disable, - }, -}; - +#define L2C_ID(name, fns) { .compatible = name, .data = (void *)&fns } static const struct of_device_id l2x0_ids[] __initconst = { - { .compatible = "arm,l210-cache", .data = (void *)&l2x0_data }, - { .compatible = "arm,l220-cache", .data = (void *)&l2x0_data }, - { .compatible = "arm,pl310-cache", .data = (void *)&pl310_data }, - { .compatible = "bcm,bcm11351-a2-pl310-cache", /* deprecated name */ - .data = (void *)&bcm_l2x0_data}, - { .compatible = "brcm,bcm11351-a2-pl310-cache", - .data = (void *)&bcm_l2x0_data}, - { .compatible = "marvell,aurora-outer-cache", - .data = (void *)&aurora_with_outer_data}, - { .compatible = "marvell,aurora-system-cache", - .data = (void *)&aurora_no_outer_data}, - { .compatible = "marvell,tauros3-cache", - .data = (void *)&tauros3_data }, + L2C_ID("arm,l210-cache", of_l2c210_data), + L2C_ID("arm,l220-cache", of_l2c220_data), + L2C_ID("arm,pl310-cache", of_l2c310_data), + L2C_ID("brcm,bcm11351-a2-pl310-cache", of_bcm_l2x0_data), + L2C_ID("marvell,aurora-outer-cache", of_aurora_with_outer_data), + L2C_ID("marvell,aurora-system-cache", of_aurora_no_outer_data), + L2C_ID("marvell,tauros3-cache", of_tauros3_data), + /* Deprecated IDs */ + L2C_ID("bcm,bcm11351-a2-pl310-cache", of_bcm_l2x0_data), {} }; int __init l2x0_of_init(u32 aux_val, u32 aux_mask) { + const struct l2c_init_data *data; struct device_node *np; - const struct l2x0_of_data *data; struct resource res; + u32 cache_id, old_aux; np = of_find_matching_node(NULL, l2x0_ids); if (!np) @@ -989,23 +1514,33 @@ int __init l2x0_of_init(u32 aux_val, u32 aux_mask) data = of_match_node(l2x0_ids, np)->data; - /* L2 configuration can only be changed if the cache is disabled */ - if (!(readl_relaxed(l2x0_base + L2X0_CTRL) & L2X0_CTRL_EN)) { - if (data->setup) - data->setup(np, &aux_val, &aux_mask); + if (of_device_is_compatible(np, "arm,pl310-cache") && + of_property_read_bool(np, "arm,io-coherent")) + data = &of_l2c310_coherent_data; - /* For aurora cache in no outer mode select the - * correct mode using the coprocessor*/ - if (data == &aurora_no_outer_data) - aurora_broadcast_l2_commands(); + old_aux = readl_relaxed(l2x0_base + L2X0_AUX_CTRL); + if (old_aux != ((old_aux & aux_mask) | aux_val)) { + pr_warn("L2C: platform modifies aux control register: 0x%08x -> 0x%08x\n", + old_aux, (old_aux & aux_mask) | aux_val); + } else if (aux_mask != ~0U && aux_val != 0) { + pr_alert("L2C: platform provided aux values match the hardware, so have no effect. Please remove them.\n"); } - if (data->save) - data->save(); + /* All L2 caches are unified, so this property should be specified */ + if (!of_property_read_bool(np, "cache-unified")) + pr_err("L2C: device tree omits to specify unified cache\n"); + + /* L2 configuration can only be changed if the cache is disabled */ + if (!(readl_relaxed(l2x0_base + L2X0_CTRL) & L2X0_CTRL_EN)) + if (data->of_parse) + data->of_parse(np, &aux_val, &aux_mask); + + if (cache_id_part_number_from_dt) + cache_id = cache_id_part_number_from_dt; + else + cache_id = readl_relaxed(l2x0_base + L2X0_CACHE_ID); - of_init = true; - memcpy(&outer_cache, &data->outer_cache, sizeof(outer_cache)); - l2x0_init(l2x0_base, aux_val, aux_mask); + __l2c_init(data, aux_val, aux_mask, cache_id); return 0; } diff --git a/arch/arm/mm/cache-nop.S b/arch/arm/mm/cache-nop.S index 8e12ddca0031..f1cc9861031f 100644 --- a/arch/arm/mm/cache-nop.S +++ b/arch/arm/mm/cache-nop.S @@ -5,11 +5,12 @@ */ #include <linux/linkage.h> #include <linux/init.h> +#include <asm/assembler.h> #include "proc-macros.S" ENTRY(nop_flush_icache_all) - mov pc, lr + ret lr ENDPROC(nop_flush_icache_all) .globl nop_flush_kern_cache_all @@ -29,7 +30,7 @@ ENDPROC(nop_flush_icache_all) ENTRY(nop_coherent_user_range) mov r0, 0 - mov pc, lr + ret lr ENDPROC(nop_coherent_user_range) .globl nop_flush_kern_dcache_area diff --git a/arch/arm/mm/cache-v4.S b/arch/arm/mm/cache-v4.S index a7ba68f59f0c..91e3adf155cb 100644 --- a/arch/arm/mm/cache-v4.S +++ b/arch/arm/mm/cache-v4.S @@ -9,6 +9,7 @@ */ #include <linux/linkage.h> #include <linux/init.h> +#include <asm/assembler.h> #include <asm/page.h> #include "proc-macros.S" @@ -18,7 +19,7 @@ * Unconditionally clean and invalidate the entire icache. */ ENTRY(v4_flush_icache_all) - mov pc, lr + ret lr ENDPROC(v4_flush_icache_all) /* @@ -40,7 +41,7 @@ ENTRY(v4_flush_kern_cache_all) #ifdef CONFIG_CPU_CP15 mov r0, #0 mcr p15, 0, r0, c7, c7, 0 @ flush ID cache - mov pc, lr + ret lr #else /* FALLTHROUGH */ #endif @@ -59,7 +60,7 @@ ENTRY(v4_flush_user_cache_range) #ifdef CONFIG_CPU_CP15 mov ip, #0 mcr p15, 0, ip, c7, c7, 0 @ flush ID cache - mov pc, lr + ret lr #else /* FALLTHROUGH */ #endif @@ -89,7 +90,7 @@ ENTRY(v4_coherent_kern_range) */ ENTRY(v4_coherent_user_range) mov r0, #0 - mov pc, lr + ret lr /* * flush_kern_dcache_area(void *addr, size_t size) @@ -116,7 +117,7 @@ ENTRY(v4_dma_flush_range) mov r0, #0 mcr p15, 0, r0, c7, c7, 0 @ flush ID cache #endif - mov pc, lr + ret lr /* * dma_unmap_area(start, size, dir) @@ -136,7 +137,7 @@ ENTRY(v4_dma_unmap_area) * - dir - DMA direction */ ENTRY(v4_dma_map_area) - mov pc, lr + ret lr ENDPROC(v4_dma_unmap_area) ENDPROC(v4_dma_map_area) diff --git a/arch/arm/mm/cache-v4wb.S b/arch/arm/mm/cache-v4wb.S index cd4945321407..2522f8c8fbb1 100644 --- a/arch/arm/mm/cache-v4wb.S +++ b/arch/arm/mm/cache-v4wb.S @@ -9,6 +9,7 @@ */ #include <linux/linkage.h> #include <linux/init.h> +#include <asm/assembler.h> #include <asm/memory.h> #include <asm/page.h> #include "proc-macros.S" @@ -58,7 +59,7 @@ flush_base: ENTRY(v4wb_flush_icache_all) mov r0, #0 mcr p15, 0, r0, c7, c5, 0 @ invalidate I cache - mov pc, lr + ret lr ENDPROC(v4wb_flush_icache_all) /* @@ -94,7 +95,7 @@ __flush_whole_cache: blo 1b #endif mcr p15, 0, ip, c7, c10, 4 @ drain write buffer - mov pc, lr + ret lr /* * flush_user_cache_range(start, end, flags) @@ -122,7 +123,7 @@ ENTRY(v4wb_flush_user_cache_range) blo 1b tst r2, #VM_EXEC mcrne p15, 0, ip, c7, c10, 4 @ drain write buffer - mov pc, lr + ret lr /* * flush_kern_dcache_area(void *addr, size_t size) @@ -170,7 +171,7 @@ ENTRY(v4wb_coherent_user_range) mov r0, #0 mcr p15, 0, r0, c7, c5, 0 @ invalidate I cache mcr p15, 0, r0, c7, c10, 4 @ drain WB - mov pc, lr + ret lr /* @@ -195,7 +196,7 @@ v4wb_dma_inv_range: cmp r0, r1 blo 1b mcr p15, 0, r0, c7, c10, 4 @ drain write buffer - mov pc, lr + ret lr /* * dma_clean_range(start, end) @@ -212,7 +213,7 @@ v4wb_dma_clean_range: cmp r0, r1 blo 1b mcr p15, 0, r0, c7, c10, 4 @ drain write buffer - mov pc, lr + ret lr /* * dma_flush_range(start, end) @@ -248,7 +249,7 @@ ENDPROC(v4wb_dma_map_area) * - dir - DMA direction */ ENTRY(v4wb_dma_unmap_area) - mov pc, lr + ret lr ENDPROC(v4wb_dma_unmap_area) .globl v4wb_flush_kern_cache_louis diff --git a/arch/arm/mm/cache-v4wt.S b/arch/arm/mm/cache-v4wt.S index 11e5e5838bc5..a0982ce49007 100644 --- a/arch/arm/mm/cache-v4wt.S +++ b/arch/arm/mm/cache-v4wt.S @@ -13,6 +13,7 @@ */ #include <linux/linkage.h> #include <linux/init.h> +#include <asm/assembler.h> #include <asm/page.h> #include "proc-macros.S" @@ -48,7 +49,7 @@ ENTRY(v4wt_flush_icache_all) mov r0, #0 mcr p15, 0, r0, c7, c5, 0 @ invalidate I cache - mov pc, lr + ret lr ENDPROC(v4wt_flush_icache_all) /* @@ -71,7 +72,7 @@ __flush_whole_cache: tst r2, #VM_EXEC mcrne p15, 0, ip, c7, c5, 0 @ invalidate I cache mcr p15, 0, ip, c7, c6, 0 @ invalidate D cache - mov pc, lr + ret lr /* * flush_user_cache_range(start, end, flags) @@ -94,7 +95,7 @@ ENTRY(v4wt_flush_user_cache_range) add r0, r0, #CACHE_DLINESIZE cmp r0, r1 blo 1b - mov pc, lr + ret lr /* * coherent_kern_range(start, end) @@ -126,7 +127,7 @@ ENTRY(v4wt_coherent_user_range) cmp r0, r1 blo 1b mov r0, #0 - mov pc, lr + ret lr /* * flush_kern_dcache_area(void *addr, size_t size) @@ -160,7 +161,7 @@ v4wt_dma_inv_range: add r0, r0, #CACHE_DLINESIZE cmp r0, r1 blo 1b - mov pc, lr + ret lr /* * dma_flush_range(start, end) @@ -192,7 +193,7 @@ ENTRY(v4wt_dma_unmap_area) * - dir - DMA direction */ ENTRY(v4wt_dma_map_area) - mov pc, lr + ret lr ENDPROC(v4wt_dma_unmap_area) ENDPROC(v4wt_dma_map_area) diff --git a/arch/arm/mm/cache-v6.S b/arch/arm/mm/cache-v6.S index d8fd4d4bd3d4..24659952c278 100644 --- a/arch/arm/mm/cache-v6.S +++ b/arch/arm/mm/cache-v6.S @@ -51,7 +51,7 @@ ENTRY(v6_flush_icache_all) #else mcr p15, 0, r0, c7, c5, 0 @ invalidate I-cache #endif - mov pc, lr + ret lr ENDPROC(v6_flush_icache_all) /* @@ -73,7 +73,7 @@ ENTRY(v6_flush_kern_cache_all) #else mcr p15, 0, r0, c7, c15, 0 @ Cache clean+invalidate #endif - mov pc, lr + ret lr /* * v6_flush_cache_all() @@ -98,7 +98,7 @@ ENTRY(v6_flush_user_cache_all) * - we have a VIPT cache. */ ENTRY(v6_flush_user_cache_range) - mov pc, lr + ret lr /* * v6_coherent_kern_range(start,end) @@ -150,7 +150,7 @@ ENTRY(v6_coherent_user_range) #else mcr p15, 0, r0, c7, c5, 6 @ invalidate BTB #endif - mov pc, lr + ret lr /* * Fault handling for the cache operation above. If the virtual address in r0 @@ -158,7 +158,7 @@ ENTRY(v6_coherent_user_range) */ 9001: mov r0, #-EFAULT - mov pc, lr + ret lr UNWIND(.fnend ) ENDPROC(v6_coherent_user_range) ENDPROC(v6_coherent_kern_range) @@ -188,7 +188,7 @@ ENTRY(v6_flush_kern_dcache_area) mov r0, #0 mcr p15, 0, r0, c7, c10, 4 #endif - mov pc, lr + ret lr /* @@ -239,7 +239,7 @@ v6_dma_inv_range: blo 1b mov r0, #0 mcr p15, 0, r0, c7, c10, 4 @ drain write buffer - mov pc, lr + ret lr /* * v6_dma_clean_range(start,end) @@ -262,7 +262,7 @@ v6_dma_clean_range: blo 1b mov r0, #0 mcr p15, 0, r0, c7, c10, 4 @ drain write buffer - mov pc, lr + ret lr /* * v6_dma_flush_range(start,end) @@ -290,7 +290,7 @@ ENTRY(v6_dma_flush_range) blo 1b mov r0, #0 mcr p15, 0, r0, c7, c10, 4 @ drain write buffer - mov pc, lr + ret lr /* * dma_map_area(start, size, dir) @@ -323,7 +323,7 @@ ENTRY(v6_dma_unmap_area) teq r2, #DMA_TO_DEVICE bne v6_dma_inv_range #endif - mov pc, lr + ret lr ENDPROC(v6_dma_unmap_area) .globl v6_flush_kern_cache_louis diff --git a/arch/arm/mm/cache-v7.S b/arch/arm/mm/cache-v7.S index 778bcf88ee79..b966656d2c2d 100644 --- a/arch/arm/mm/cache-v7.S +++ b/arch/arm/mm/cache-v7.S @@ -59,9 +59,9 @@ ENTRY(v7_invalidate_l1) bgt 2b cmp r2, #0 bgt 1b - dsb + dsb st isb - mov pc, lr + ret lr ENDPROC(v7_invalidate_l1) /* @@ -76,7 +76,7 @@ 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 + ret lr ENDPROC(v7_flush_icache_all) /* @@ -94,7 +94,7 @@ ENTRY(v7_flush_dcache_louis) ALT_UP(ands r3, r0, #(7 << 27)) @ extract LoUU from clidr #ifdef CONFIG_ARM_ERRATA_643719 ALT_SMP(mrceq p15, 0, r2, c0, c0, 0) @ read main ID register - ALT_UP(moveq pc, lr) @ LoUU is zero, so nothing to do + ALT_UP(reteq lr) @ LoUU is zero, so nothing to do ldreq r1, =0x410fc090 @ ID of ARM Cortex A9 r0p? biceq r2, r2, #0x0000000f @ clear minor revision number teqeq r2, r1 @ test for errata affected core and if so... @@ -102,7 +102,7 @@ ENTRY(v7_flush_dcache_louis) #endif ALT_SMP(mov r3, r3, lsr #20) @ r3 = LoUIS * 2 ALT_UP(mov r3, r3, lsr #26) @ r3 = LoUU * 2 - moveq pc, lr @ return if level == 0 + reteq lr @ return if level == 0 mov r10, #0 @ r10 (starting level) = 0 b flush_levels @ start flushing cache levels ENDPROC(v7_flush_dcache_louis) @@ -166,9 +166,9 @@ skip: finished: mov r10, #0 @ swith back to cache level 0 mcr p15, 2, r10, c0, c0, 0 @ select current cache level in cssr - dsb + dsb st isb - mov pc, lr + ret lr ENDPROC(v7_flush_dcache_all) /* @@ -191,7 +191,7 @@ ENTRY(v7_flush_kern_cache_all) 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 + ret lr ENDPROC(v7_flush_kern_cache_all) /* @@ -209,7 +209,7 @@ ENTRY(v7_flush_kern_cache_louis) 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 + ret lr ENDPROC(v7_flush_kern_cache_louis) /* @@ -235,7 +235,7 @@ ENTRY(v7_flush_user_cache_all) * - we have a VIPT cache. */ ENTRY(v7_flush_user_cache_range) - mov pc, lr + ret lr ENDPROC(v7_flush_user_cache_all) ENDPROC(v7_flush_user_cache_range) @@ -296,7 +296,7 @@ ENTRY(v7_coherent_user_range) ALT_UP(mcr p15, 0, r0, c7, c5, 6) @ invalidate BTB dsb ishst isb - mov pc, lr + ret lr /* * Fault handling for the cache operation above. If the virtual address in r0 @@ -307,7 +307,7 @@ ENTRY(v7_coherent_user_range) dsb #endif mov r0, #-EFAULT - mov pc, lr + ret lr UNWIND(.fnend ) ENDPROC(v7_coherent_kern_range) ENDPROC(v7_coherent_user_range) @@ -335,8 +335,8 @@ ENTRY(v7_flush_kern_dcache_area) add r0, r0, r2 cmp r0, r1 blo 1b - dsb - mov pc, lr + dsb st + ret lr ENDPROC(v7_flush_kern_dcache_area) /* @@ -368,8 +368,8 @@ v7_dma_inv_range: add r0, r0, r2 cmp r0, r1 blo 1b - dsb - mov pc, lr + dsb st + ret lr ENDPROC(v7_dma_inv_range) /* @@ -390,8 +390,8 @@ v7_dma_clean_range: add r0, r0, r2 cmp r0, r1 blo 1b - dsb - mov pc, lr + dsb st + ret lr ENDPROC(v7_dma_clean_range) /* @@ -412,8 +412,8 @@ ENTRY(v7_dma_flush_range) add r0, r0, r2 cmp r0, r1 blo 1b - dsb - mov pc, lr + dsb st + ret lr ENDPROC(v7_dma_flush_range) /* @@ -439,7 +439,7 @@ ENTRY(v7_dma_unmap_area) add r1, r1, r0 teq r2, #DMA_TO_DEVICE bne v7_dma_inv_range - mov pc, lr + ret lr ENDPROC(v7_dma_unmap_area) __INITDATA diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c index 6b00be1f971e..1f88db06b133 100644 --- a/arch/arm/mm/dma-mapping.c +++ b/arch/arm/mm/dma-mapping.c @@ -390,7 +390,7 @@ static int __init atomic_pool_init(void) if (!pages) goto no_pages; - if (IS_ENABLED(CONFIG_DMA_CMA)) + if (dev_get_cma_area(NULL)) ptr = __alloc_from_contiguous(NULL, pool->size, prot, &page, atomic_pool_init); else @@ -461,12 +461,21 @@ void __init dma_contiguous_remap(void) map.type = MT_MEMORY_DMA_READY; /* - * Clear previous low-memory mapping + * Clear previous low-memory mapping to ensure that the + * TLB does not see any conflicting entries, then flush + * the TLB of the old entries before creating new mappings. + * + * This ensures that any speculatively loaded TLB entries + * (even though they may be rare) can not cause any problems, + * and ensures that this code is architecturally compliant. */ for (addr = __phys_to_virt(start); addr < __phys_to_virt(end); addr += PMD_SIZE) pmd_clear(pmd_off_k(addr)); + flush_tlb_kernel_range(__phys_to_virt(start), + __phys_to_virt(end)); + iotable_init(&map, 1); } } @@ -701,7 +710,7 @@ static void *__dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, addr = __alloc_simple_buffer(dev, size, gfp, &page); else if (!(gfp & __GFP_WAIT)) addr = __alloc_from_pool(size, &page); - else if (!IS_ENABLED(CONFIG_DMA_CMA)) + else if (!dev_get_cma_area(dev)) addr = __alloc_remap_buffer(dev, size, gfp, prot, &page, caller); else addr = __alloc_from_contiguous(dev, size, prot, &page, caller); @@ -790,7 +799,7 @@ static void __arm_dma_free(struct device *dev, size_t size, void *cpu_addr, __dma_free_buffer(page, size); } else if (__free_from_pool(cpu_addr, size)) { return; - } else if (!IS_ENABLED(CONFIG_DMA_CMA)) { + } else if (!dev_get_cma_area(dev)) { __dma_free_remap(cpu_addr, size); __dma_free_buffer(page, size); } else { @@ -885,7 +894,7 @@ static void dma_cache_maint_page(struct page *page, unsigned long offset, static void __dma_page_cpu_to_dev(struct page *page, unsigned long off, size_t size, enum dma_data_direction dir) { - unsigned long paddr; + phys_addr_t paddr; dma_cache_maint_page(page, off, size, dir, dmac_map_area); @@ -901,14 +910,15 @@ static void __dma_page_cpu_to_dev(struct page *page, unsigned long off, static void __dma_page_dev_to_cpu(struct page *page, unsigned long off, size_t size, enum dma_data_direction dir) { - unsigned long paddr = page_to_phys(page) + off; + phys_addr_t paddr = page_to_phys(page) + off; /* FIXME: non-speculating: not required */ - /* don't bother invalidating if DMA to device */ - if (dir != DMA_TO_DEVICE) + /* in any case, don't bother invalidating if DMA to device */ + if (dir != DMA_TO_DEVICE) { outer_inv_range(paddr, paddr + size); - dma_cache_maint_page(page, off, size, dir, dmac_unmap_area); + dma_cache_maint_page(page, off, size, dir, dmac_unmap_area); + } /* * Mark the D-cache clean for these pages to avoid extra flushing. @@ -1074,6 +1084,7 @@ static inline dma_addr_t __alloc_iova(struct dma_iommu_mapping *mapping, unsigned int order = get_order(size); unsigned int align = 0; unsigned int count, start; + size_t mapping_size = mapping->bits << PAGE_SHIFT; unsigned long flags; dma_addr_t iova; int i; @@ -1119,7 +1130,7 @@ static inline dma_addr_t __alloc_iova(struct dma_iommu_mapping *mapping, } spin_unlock_irqrestore(&mapping->lock, flags); - iova = mapping->base + (mapping->size * i); + iova = mapping->base + (mapping_size * i); iova += start << PAGE_SHIFT; return iova; @@ -1129,6 +1140,7 @@ static inline void __free_iova(struct dma_iommu_mapping *mapping, dma_addr_t addr, size_t size) { unsigned int start, count; + size_t mapping_size = mapping->bits << PAGE_SHIFT; unsigned long flags; dma_addr_t bitmap_base; u32 bitmap_index; @@ -1136,14 +1148,14 @@ static inline void __free_iova(struct dma_iommu_mapping *mapping, if (!size) return; - bitmap_index = (u32) (addr - mapping->base) / (u32) mapping->size; + bitmap_index = (u32) (addr - mapping->base) / (u32) mapping_size; BUG_ON(addr < mapping->base || bitmap_index > mapping->extensions); - bitmap_base = mapping->base + mapping->size * bitmap_index; + bitmap_base = mapping->base + mapping_size * bitmap_index; start = (addr - bitmap_base) >> PAGE_SHIFT; - if (addr + size > bitmap_base + mapping->size) { + if (addr + size > bitmap_base + mapping_size) { /* * The address range to be freed reaches into the iova * range of the next bitmap. This should not happen as @@ -1964,7 +1976,6 @@ arm_iommu_create_mapping(struct bus_type *bus, dma_addr_t base, size_t size) mapping->extensions = extensions; mapping->base = base; mapping->bits = BITS_PER_BYTE * bitmap_size; - mapping->size = mapping->bits << PAGE_SHIFT; spin_lock_init(&mapping->lock); diff --git a/arch/arm/mm/dump.c b/arch/arm/mm/dump.c index c508f41a43bc..59424937e52b 100644 --- a/arch/arm/mm/dump.c +++ b/arch/arm/mm/dump.c @@ -126,8 +126,8 @@ static const struct prot_bits section_bits[] = { .val = PMD_SECT_USER, .set = "USR", }, { - .mask = PMD_SECT_RDONLY, - .val = PMD_SECT_RDONLY, + .mask = L_PMD_SECT_RDONLY, + .val = L_PMD_SECT_RDONLY, .set = "ro", .clear = "RW", #elif __LINUX_ARM_ARCH__ >= 6 diff --git a/arch/arm/mm/flush.c b/arch/arm/mm/flush.c index 3387e60e4ea3..43d54f5b26b9 100644 --- a/arch/arm/mm/flush.c +++ b/arch/arm/mm/flush.c @@ -104,17 +104,20 @@ void flush_cache_page(struct vm_area_struct *vma, unsigned long user_addr, unsig #define flush_icache_alias(pfn,vaddr,len) do { } while (0) #endif +#define FLAG_PA_IS_EXEC 1 +#define FLAG_PA_CORE_IN_MM 2 + static void flush_ptrace_access_other(void *args) { __flush_icache_all(); } -static -void flush_ptrace_access(struct vm_area_struct *vma, struct page *page, - unsigned long uaddr, void *kaddr, unsigned long len) +static inline +void __flush_ptrace_access(struct page *page, unsigned long uaddr, void *kaddr, + unsigned long len, unsigned int flags) { if (cache_is_vivt()) { - if (cpumask_test_cpu(smp_processor_id(), mm_cpumask(vma->vm_mm))) { + if (flags & FLAG_PA_CORE_IN_MM) { unsigned long addr = (unsigned long)kaddr; __cpuc_coherent_kern_range(addr, addr + len); } @@ -128,7 +131,7 @@ void flush_ptrace_access(struct vm_area_struct *vma, struct page *page, } /* VIPT non-aliasing D-cache */ - if (vma->vm_flags & VM_EXEC) { + if (flags & FLAG_PA_IS_EXEC) { unsigned long addr = (unsigned long)kaddr; if (icache_is_vipt_aliasing()) flush_icache_alias(page_to_pfn(page), uaddr, len); @@ -140,6 +143,26 @@ void flush_ptrace_access(struct vm_area_struct *vma, struct page *page, } } +static +void flush_ptrace_access(struct vm_area_struct *vma, struct page *page, + unsigned long uaddr, void *kaddr, unsigned long len) +{ + unsigned int flags = 0; + if (cpumask_test_cpu(smp_processor_id(), mm_cpumask(vma->vm_mm))) + flags |= FLAG_PA_CORE_IN_MM; + if (vma->vm_flags & VM_EXEC) + flags |= FLAG_PA_IS_EXEC; + __flush_ptrace_access(page, uaddr, kaddr, len, flags); +} + +void flush_uprobe_xol_access(struct page *page, unsigned long uaddr, + void *kaddr, unsigned long len) +{ + unsigned int flags = FLAG_PA_CORE_IN_MM|FLAG_PA_IS_EXEC; + + __flush_ptrace_access(page, uaddr, kaddr, len, flags); +} + /* * Copy user data from/to a page which is mapped into a different * processes address space. Really, we want to allow our "user diff --git a/arch/arm/mm/highmem.c b/arch/arm/mm/highmem.c index 21b9e1bf9b77..45aeaaca9052 100644 --- a/arch/arm/mm/highmem.c +++ b/arch/arm/mm/highmem.c @@ -18,6 +18,21 @@ #include <asm/tlbflush.h> #include "mm.h" +pte_t *fixmap_page_table; + +static inline void set_fixmap_pte(int idx, pte_t pte) +{ + unsigned long vaddr = __fix_to_virt(idx); + set_pte_ext(fixmap_page_table + idx, pte, 0); + local_flush_tlb_kernel_page(vaddr); +} + +static inline pte_t get_fixmap_pte(unsigned long vaddr) +{ + unsigned long idx = __virt_to_fix(vaddr); + return *(fixmap_page_table + idx); +} + void *kmap(struct page *page) { might_sleep(); @@ -63,20 +78,20 @@ void *kmap_atomic(struct page *page) type = kmap_atomic_idx_push(); idx = type + KM_TYPE_NR * smp_processor_id(); - vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx); + vaddr = __fix_to_virt(idx); #ifdef CONFIG_DEBUG_HIGHMEM /* * With debugging enabled, kunmap_atomic forces that entry to 0. * Make sure it was indeed properly unmapped. */ - BUG_ON(!pte_none(get_top_pte(vaddr))); + BUG_ON(!pte_none(*(fixmap_page_table + idx))); #endif /* * When debugging is off, kunmap_atomic leaves the previous mapping * in place, so the contained TLB flush ensures the TLB is updated * with the new mapping. */ - set_top_pte(vaddr, mk_pte(page, kmap_prot)); + set_fixmap_pte(idx, mk_pte(page, kmap_prot)); return (void *)vaddr; } @@ -94,8 +109,8 @@ void __kunmap_atomic(void *kvaddr) if (cache_is_vivt()) __cpuc_flush_dcache_area((void *)vaddr, PAGE_SIZE); #ifdef CONFIG_DEBUG_HIGHMEM - BUG_ON(vaddr != __fix_to_virt(FIX_KMAP_BEGIN + idx)); - set_top_pte(vaddr, __pte(0)); + BUG_ON(vaddr != __fix_to_virt(idx)); + set_fixmap_pte(idx, __pte(0)); #else (void) idx; /* to kill a warning */ #endif @@ -117,11 +132,11 @@ void *kmap_atomic_pfn(unsigned long pfn) type = kmap_atomic_idx_push(); idx = type + KM_TYPE_NR * smp_processor_id(); - vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx); + vaddr = __fix_to_virt(idx); #ifdef CONFIG_DEBUG_HIGHMEM - BUG_ON(!pte_none(get_top_pte(vaddr))); + BUG_ON(!pte_none(*(fixmap_page_table + idx))); #endif - set_top_pte(vaddr, pfn_pte(pfn, kmap_prot)); + set_fixmap_pte(idx, pfn_pte(pfn, kmap_prot)); return (void *)vaddr; } @@ -133,5 +148,5 @@ struct page *kmap_atomic_to_page(const void *ptr) if (vaddr < FIXADDR_START) return virt_to_page(ptr); - return pte_page(get_top_pte(vaddr)); + return pte_page(get_fixmap_pte(vaddr)); } diff --git a/arch/arm/mm/hugetlbpage.c b/arch/arm/mm/hugetlbpage.c index 54ee6163c181..66781bf34077 100644 --- a/arch/arm/mm/hugetlbpage.c +++ b/arch/arm/mm/hugetlbpage.c @@ -56,8 +56,3 @@ int pmd_huge(pmd_t pmd) { return pmd_val(pmd) && !(pmd_val(pmd) & PMD_TABLE_BIT); } - -int pmd_huge_support(void) -{ - return 1; -} diff --git a/arch/arm/mm/idmap.c b/arch/arm/mm/idmap.c index 8e0e52eb76b5..c447ec70e868 100644 --- a/arch/arm/mm/idmap.c +++ b/arch/arm/mm/idmap.c @@ -9,6 +9,11 @@ #include <asm/sections.h> #include <asm/system_info.h> +/* + * Note: accesses outside of the kernel image and the identity map area + * are not supported on any CPU using the idmap tables as its current + * page tables. + */ pgd_t *idmap_pgd; phys_addr_t (*arch_virt_to_idmap) (unsigned long x); @@ -25,6 +30,13 @@ static void idmap_add_pmd(pud_t *pud, unsigned long addr, unsigned long end, pr_warning("Failed to allocate identity pmd.\n"); return; } + /* + * Copy the original PMD to ensure that the PMD entries for + * the kernel image are preserved. + */ + if (!pud_none(*pud)) + memcpy(pmd, pmd_offset(pud, 0), + PTRS_PER_PMD * sizeof(pmd_t)); pud_populate(&init_mm, pud, pmd); pmd += pmd_index(addr); } else diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c index 2a77ba8796ae..659c75d808dc 100644 --- a/arch/arm/mm/init.c +++ b/arch/arm/mm/init.c @@ -23,6 +23,7 @@ #include <linux/dma-contiguous.h> #include <linux/sizes.h> +#include <asm/cp15.h> #include <asm/mach-types.h> #include <asm/memblock.h> #include <asm/prom.h> @@ -36,6 +37,14 @@ #include "mm.h" +#ifdef CONFIG_CPU_CP15_MMU +unsigned long __init __clear_cr(unsigned long mask) +{ + cr_alignment = cr_alignment & ~mask; + return cr_alignment; +} +#endif + static phys_addr_t phys_initrd_start __initdata = 0; static unsigned long phys_initrd_size __initdata = 0; @@ -81,24 +90,21 @@ __tagtable(ATAG_INITRD2, parse_tag_initrd2); * initialization functions, as well as show_mem() for the skipping * of holes in the memory map. It is populated by arm_add_memory(). */ -struct meminfo meminfo; - void show_mem(unsigned int filter) { int free = 0, total = 0, reserved = 0; - int shared = 0, cached = 0, slab = 0, i; - struct meminfo * mi = &meminfo; + int shared = 0, cached = 0, slab = 0; + struct memblock_region *reg; printk("Mem-info:\n"); show_free_areas(filter); - for_each_bank (i, mi) { - struct membank *bank = &mi->bank[i]; + for_each_memblock (memory, reg) { unsigned int pfn1, pfn2; struct page *page, *end; - pfn1 = bank_pfn_start(bank); - pfn2 = bank_pfn_end(bank); + pfn1 = memblock_region_memory_base_pfn(reg); + pfn2 = memblock_region_memory_end_pfn(reg); page = pfn_to_page(pfn1); end = pfn_to_page(pfn2 - 1) + 1; @@ -115,8 +121,9 @@ void show_mem(unsigned int filter) free++; else shared += page_count(page) - 1; - page++; - } while (page < end); + pfn1++; + page = pfn_to_page(pfn1); + } while (pfn1 < pfn2); } printk("%d pages of RAM\n", total); @@ -130,16 +137,9 @@ void show_mem(unsigned int filter) static void __init find_limits(unsigned long *min, unsigned long *max_low, unsigned long *max_high) { - struct meminfo *mi = &meminfo; - int i; - - /* This assumes the meminfo array is properly sorted */ - *min = bank_pfn_start(&mi->bank[0]); - for_each_bank (i, mi) - if (mi->bank[i].highmem) - break; - *max_low = bank_pfn_end(&mi->bank[i - 1]); - *max_high = bank_pfn_end(&mi->bank[mi->nr_banks - 1]); + *max_low = PFN_DOWN(memblock_get_current_limit()); + *min = PFN_UP(memblock_start_of_DRAM()); + *max_high = PFN_DOWN(memblock_end_of_DRAM()); } #ifdef CONFIG_ZONE_DMA @@ -274,14 +274,8 @@ phys_addr_t __init arm_memblock_steal(phys_addr_t size, phys_addr_t align) return phys; } -void __init arm_memblock_init(struct meminfo *mi, - const struct machine_desc *mdesc) +void __init arm_memblock_init(const struct machine_desc *mdesc) { - int i; - - 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(_sdata), _end - _sdata); @@ -317,7 +311,6 @@ void __init arm_memblock_init(struct meminfo *mi, #endif arm_mm_memblock_reserve(); - arm_dt_memblock_reserve(); /* reserve any platform specific memblock areas */ if (mdesc->reserve) @@ -413,54 +406,53 @@ free_memmap(unsigned long start_pfn, unsigned long end_pfn) /* * The mem_map array can get very big. Free the unused area of the memory map. */ -static void __init free_unused_memmap(struct meminfo *mi) +static void __init free_unused_memmap(void) { - unsigned long bank_start, prev_bank_end = 0; - unsigned int i; + unsigned long start, prev_end = 0; + struct memblock_region *reg; /* * This relies on each bank being in address order. * The banks are sorted previously in bootmem_init(). */ - for_each_bank(i, mi) { - struct membank *bank = &mi->bank[i]; - - bank_start = bank_pfn_start(bank); + for_each_memblock(memory, reg) { + start = memblock_region_memory_base_pfn(reg); #ifdef CONFIG_SPARSEMEM /* * Take care not to free memmap entries that don't exist * due to SPARSEMEM sections which aren't present. */ - bank_start = min(bank_start, - ALIGN(prev_bank_end, PAGES_PER_SECTION)); + start = min(start, + ALIGN(prev_end, PAGES_PER_SECTION)); #else /* * Align down here since the VM subsystem insists that the * memmap entries are valid from the bank start aligned to * MAX_ORDER_NR_PAGES. */ - bank_start = round_down(bank_start, MAX_ORDER_NR_PAGES); + start = round_down(start, MAX_ORDER_NR_PAGES); #endif /* * If we had a previous bank, and there is a space * between the current bank and the previous, free it. */ - if (prev_bank_end && prev_bank_end < bank_start) - free_memmap(prev_bank_end, bank_start); + if (prev_end && prev_end < start) + free_memmap(prev_end, start); /* * Align up here since the VM subsystem insists that the * memmap entries are valid from the bank end aligned to * MAX_ORDER_NR_PAGES. */ - prev_bank_end = ALIGN(bank_pfn_end(bank), MAX_ORDER_NR_PAGES); + prev_end = ALIGN(memblock_region_memory_end_pfn(reg), + MAX_ORDER_NR_PAGES); } #ifdef CONFIG_SPARSEMEM - if (!IS_ALIGNED(prev_bank_end, PAGES_PER_SECTION)) - free_memmap(prev_bank_end, - ALIGN(prev_bank_end, PAGES_PER_SECTION)); + if (!IS_ALIGNED(prev_end, PAGES_PER_SECTION)) + free_memmap(prev_end, + ALIGN(prev_end, PAGES_PER_SECTION)); #endif } @@ -536,7 +528,7 @@ void __init mem_init(void) set_max_mapnr(pfn_to_page(max_pfn) - mem_map); /* this will put all unused low memory onto the freelists */ - free_unused_memmap(&meminfo); + free_unused_memmap(); free_all_bootmem(); #ifdef CONFIG_SA1111 diff --git a/arch/arm/mm/ioremap.c b/arch/arm/mm/ioremap.c index f9c32ba73544..d1e5ad7ab3bc 100644 --- a/arch/arm/mm/ioremap.c +++ b/arch/arm/mm/ioremap.c @@ -438,6 +438,13 @@ void __arm_iounmap(volatile void __iomem *io_addr) EXPORT_SYMBOL(__arm_iounmap); #ifdef CONFIG_PCI +static int pci_ioremap_mem_type = MT_DEVICE; + +void pci_ioremap_set_mem_type(int mem_type) +{ + pci_ioremap_mem_type = mem_type; +} + int pci_ioremap_io(unsigned int offset, phys_addr_t phys_addr) { BUG_ON(offset + SZ_64K > IO_SPACE_LIMIT); @@ -445,7 +452,7 @@ int pci_ioremap_io(unsigned int offset, phys_addr_t phys_addr) return ioremap_page_range(PCI_IO_VIRT_BASE + offset, PCI_IO_VIRT_BASE + offset + SZ_64K, phys_addr, - __pgprot(get_mem_type(MT_DEVICE)->prot_pte)); + __pgprot(get_mem_type(pci_ioremap_mem_type)->prot_pte)); } EXPORT_SYMBOL_GPL(pci_ioremap_io); #endif diff --git a/arch/arm/mm/l2c-common.c b/arch/arm/mm/l2c-common.c new file mode 100644 index 000000000000..10a3cf28c362 --- /dev/null +++ b/arch/arm/mm/l2c-common.c @@ -0,0 +1,20 @@ +/* + * Copyright (C) 2010 ARM Ltd. + * Written by Catalin Marinas <catalin.marinas@arm.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ +#include <linux/bug.h> +#include <linux/smp.h> +#include <asm/outercache.h> + +void outer_disable(void) +{ + WARN_ON(!irqs_disabled()); + WARN_ON(num_online_cpus() > 1); + + if (outer_cache.disable) + outer_cache.disable(); +} diff --git a/arch/arm/mm/l2c-l2x0-resume.S b/arch/arm/mm/l2c-l2x0-resume.S new file mode 100644 index 000000000000..fda415e4ca8f --- /dev/null +++ b/arch/arm/mm/l2c-l2x0-resume.S @@ -0,0 +1,59 @@ +/* + * L2C-310 early resume code. This can be used by platforms to restore + * the settings of their L2 cache controller before restoring the + * processor state. + * + * This code can only be used to if you are running in the secure world. + */ +#include <linux/linkage.h> +#include <asm/assembler.h> +#include <asm/hardware/cache-l2x0.h> + + .text + +ENTRY(l2c310_early_resume) + adr r0, 1f + ldr r2, [r0] + add r0, r2, r0 + + ldmia r0, {r1, r2, r3, r4, r5, r6, r7, r8} + @ r1 = phys address of L2C-310 controller + @ r2 = aux_ctrl + @ r3 = tag_latency + @ r4 = data_latency + @ r5 = filter_start + @ r6 = filter_end + @ r7 = prefetch_ctrl + @ r8 = pwr_ctrl + + @ Check that the address has been initialised + teq r1, #0 + reteq lr + + @ The prefetch and power control registers are revision dependent + @ and can be written whether or not the L2 cache is enabled + ldr r0, [r1, #L2X0_CACHE_ID] + and r0, r0, #L2X0_CACHE_ID_RTL_MASK + cmp r0, #L310_CACHE_ID_RTL_R2P0 + strcs r7, [r1, #L310_PREFETCH_CTRL] + cmp r0, #L310_CACHE_ID_RTL_R3P0 + strcs r8, [r1, #L310_POWER_CTRL] + + @ Don't setup the L2 cache if it is already enabled + ldr r0, [r1, #L2X0_CTRL] + tst r0, #L2X0_CTRL_EN + retne lr + + str r3, [r1, #L310_TAG_LATENCY_CTRL] + str r4, [r1, #L310_DATA_LATENCY_CTRL] + str r6, [r1, #L310_ADDR_FILTER_END] + str r5, [r1, #L310_ADDR_FILTER_START] + + str r2, [r1, #L2X0_AUX_CTRL] + mov r9, #L2X0_CTRL_EN + str r9, [r1, #L2X0_CTRL] + ret lr +ENDPROC(l2c310_early_resume) + + .align +1: .long l2x0_saved_regs - . diff --git a/arch/arm/mm/mm.h b/arch/arm/mm/mm.h index 7ea641b7aa7d..ce727d47275c 100644 --- a/arch/arm/mm/mm.h +++ b/arch/arm/mm/mm.h @@ -2,6 +2,8 @@ #include <linux/list.h> #include <linux/vmalloc.h> +#include <asm/pgtable.h> + /* the upper-most page table pointer */ extern pmd_t *top_pmd; @@ -93,3 +95,5 @@ extern phys_addr_t arm_lowmem_limit; void __init bootmem_init(void); void arm_mm_memblock_reserve(void); void dma_contiguous_remap(void); + +unsigned long __clear_cr(unsigned long mask); diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c index b68c6b22e1c8..8348ed6b2efe 100644 --- a/arch/arm/mm/mmu.c +++ b/arch/arm/mm/mmu.c @@ -35,6 +35,7 @@ #include <asm/mach/arch.h> #include <asm/mach/map.h> #include <asm/mach/pci.h> +#include <asm/fixmap.h> #include "mm.h" #include "tcm.h" @@ -117,28 +118,54 @@ static struct cachepolicy cache_policies[] __initdata = { }; #ifdef CONFIG_CPU_CP15 +static unsigned long initial_pmd_value __initdata = 0; + /* - * These are useful for identifying cache coherency - * problems by allowing the cache or the cache and - * writebuffer to be turned off. (Note: the write - * buffer should not be on and the cache off). + * Initialise the cache_policy variable with the initial state specified + * via the "pmd" value. This is used to ensure that on ARMv6 and later, + * the C code sets the page tables up with the same policy as the head + * assembly code, which avoids an illegal state where the TLBs can get + * confused. See comments in early_cachepolicy() for more information. */ -static int __init early_cachepolicy(char *p) +void __init init_default_cache_policy(unsigned long pmd) { int i; + initial_pmd_value = pmd; + + pmd &= PMD_SECT_TEX(1) | PMD_SECT_BUFFERABLE | PMD_SECT_CACHEABLE; + + for (i = 0; i < ARRAY_SIZE(cache_policies); i++) + if (cache_policies[i].pmd == pmd) { + cachepolicy = i; + break; + } + + if (i == ARRAY_SIZE(cache_policies)) + pr_err("ERROR: could not find cache policy\n"); +} + +/* + * These are useful for identifying cache coherency problems by allowing + * the cache or the cache and writebuffer to be turned off. (Note: the + * write buffer should not be on and the cache off). + */ +static int __init early_cachepolicy(char *p) +{ + int i, selected = -1; + for (i = 0; i < ARRAY_SIZE(cache_policies); i++) { int len = strlen(cache_policies[i].policy); if (memcmp(p, cache_policies[i].policy, len) == 0) { - cachepolicy = i; - cr_alignment &= ~cache_policies[i].cr_mask; - cr_no_alignment &= ~cache_policies[i].cr_mask; + selected = i; break; } } - if (i == ARRAY_SIZE(cache_policies)) - printk(KERN_ERR "ERROR: unknown or unsupported cache policy\n"); + + if (selected == -1) + pr_err("ERROR: unknown or unsupported cache policy\n"); + /* * This restriction is partly to do with the way we boot; it is * unpredictable to have memory mapped using two different sets of @@ -146,12 +173,18 @@ static int __init early_cachepolicy(char *p) * change these attributes once the initial assembly has setup the * page tables. */ - if (cpu_architecture() >= CPU_ARCH_ARMv6) { - printk(KERN_WARNING "Only cachepolicy=writeback supported on ARMv6 and later\n"); - cachepolicy = CPOLICY_WRITEBACK; + if (cpu_architecture() >= CPU_ARCH_ARMv6 && selected != cachepolicy) { + pr_warn("Only cachepolicy=%s supported on ARMv6 and later\n", + cache_policies[cachepolicy].policy); + return 0; + } + + if (selected != cachepolicy) { + unsigned long cr = __clear_cr(cache_policies[selected].cr_mask); + cachepolicy = selected; + flush_cache_all(); + set_cr(cr); } - flush_cache_all(); - set_cr(cr_alignment); return 0; } early_param("cachepolicy", early_cachepolicy); @@ -186,35 +219,6 @@ static int __init early_ecc(char *p) early_param("ecc", early_ecc); #endif -static int __init noalign_setup(char *__unused) -{ - cr_alignment &= ~CR_A; - cr_no_alignment &= ~CR_A; - set_cr(cr_alignment); - return 1; -} -__setup("noalign", noalign_setup); - -#ifndef CONFIG_SMP -void adjust_cr(unsigned long mask, unsigned long set) -{ - unsigned long flags; - - mask &= ~CR_A; - - set &= mask; - - local_irq_save(flags); - - cr_no_alignment = (cr_no_alignment & ~mask) | set; - cr_alignment = (cr_alignment & ~mask) | set; - - set_cr((get_cr() & ~mask) | set); - - local_irq_restore(flags); -} -#endif - #else /* ifdef CONFIG_CPU_CP15 */ static int __init early_cachepolicy(char *p) @@ -414,8 +418,17 @@ static void __init build_mem_type_table(void) cachepolicy = CPOLICY_WRITEBACK; ecc_mask = 0; } - if (is_smp()) - cachepolicy = CPOLICY_WRITEALLOC; + + if (is_smp()) { + if (cachepolicy != CPOLICY_WRITEALLOC) { + pr_warn("Forcing write-allocate cache policy for SMP\n"); + cachepolicy = CPOLICY_WRITEALLOC; + } + if (!(initial_pmd_value & PMD_SECT_S)) { + pr_warn("Forcing shared mappings for SMP\n"); + initial_pmd_value |= PMD_SECT_S; + } + } /* * Strip out features not present on earlier architectures. @@ -539,11 +552,12 @@ static void __init build_mem_type_table(void) mem_types[MT_CACHECLEAN].prot_sect |= PMD_SECT_APX|PMD_SECT_AP_WRITE; #endif - if (is_smp()) { - /* - * Mark memory with the "shared" attribute - * for SMP systems - */ + /* + * If the initial page tables were created with the S bit + * set, then we need to do the same here for the same + * reasons given in early_cachepolicy(). + */ + if (initial_pmd_value & PMD_SECT_S) { user_pgprot |= L_PTE_SHARED; kern_pgprot |= L_PTE_SHARED; vecs_pgprot |= L_PTE_SHARED; @@ -1061,74 +1075,47 @@ phys_addr_t arm_lowmem_limit __initdata = 0; void __init sanity_check_meminfo(void) { phys_addr_t memblock_limit = 0; - int i, j, highmem = 0; + int highmem = 0; phys_addr_t vmalloc_limit = __pa(vmalloc_min - 1) + 1; + struct memblock_region *reg; - for (i = 0, j = 0; i < meminfo.nr_banks; i++) { - struct membank *bank = &meminfo.bank[j]; - phys_addr_t size_limit; - - *bank = meminfo.bank[i]; - size_limit = bank->size; + for_each_memblock(memory, reg) { + phys_addr_t block_start = reg->base; + phys_addr_t block_end = reg->base + reg->size; + phys_addr_t size_limit = reg->size; - if (bank->start >= vmalloc_limit) + if (reg->base >= vmalloc_limit) highmem = 1; else - size_limit = vmalloc_limit - bank->start; + size_limit = vmalloc_limit - reg->base; - bank->highmem = highmem; -#ifdef CONFIG_HIGHMEM - /* - * Split those memory banks which are partially overlapping - * the vmalloc area greatly simplifying things later. - */ - if (!highmem && bank->size > size_limit) { - if (meminfo.nr_banks >= NR_BANKS) { - printk(KERN_CRIT "NR_BANKS too low, " - "ignoring high memory\n"); - } else { - memmove(bank + 1, bank, - (meminfo.nr_banks - i) * sizeof(*bank)); - meminfo.nr_banks++; - i++; - bank[1].size -= size_limit; - bank[1].start = vmalloc_limit; - bank[1].highmem = highmem = 1; - j++; + if (!IS_ENABLED(CONFIG_HIGHMEM) || cache_is_vipt_aliasing()) { + + if (highmem) { + pr_notice("Ignoring RAM at %pa-%pa (!CONFIG_HIGHMEM)\n", + &block_start, &block_end); + memblock_remove(reg->base, reg->size); + continue; } - bank->size = size_limit; - } -#else - /* - * Highmem banks not allowed with !CONFIG_HIGHMEM. - */ - if (highmem) { - printk(KERN_NOTICE "Ignoring RAM at %.8llx-%.8llx " - "(!CONFIG_HIGHMEM).\n", - (unsigned long long)bank->start, - (unsigned long long)bank->start + bank->size - 1); - continue; - } - /* - * Check whether this memory bank would partially overlap - * the vmalloc area. - */ - if (bank->size > size_limit) { - printk(KERN_NOTICE "Truncating RAM at %.8llx-%.8llx " - "to -%.8llx (vmalloc region overlap).\n", - (unsigned long long)bank->start, - (unsigned long long)bank->start + bank->size - 1, - (unsigned long long)bank->start + size_limit - 1); - bank->size = size_limit; + if (reg->size > size_limit) { + phys_addr_t overlap_size = reg->size - size_limit; + + pr_notice("Truncating RAM at %pa-%pa to -%pa", + &block_start, &block_end, &vmalloc_limit); + memblock_remove(vmalloc_limit, overlap_size); + block_end = vmalloc_limit; + } } -#endif - if (!bank->highmem) { - phys_addr_t bank_end = bank->start + bank->size; - if (bank_end > arm_lowmem_limit) - arm_lowmem_limit = bank_end; + if (!highmem) { + if (block_end > arm_lowmem_limit) { + if (reg->size > size_limit) + arm_lowmem_limit = vmalloc_limit; + else + arm_lowmem_limit = block_end; + } /* * Find the first non-section-aligned page, and point @@ -1144,35 +1131,15 @@ void __init sanity_check_meminfo(void) * occurs before any free memory is mapped. */ if (!memblock_limit) { - if (!IS_ALIGNED(bank->start, SECTION_SIZE)) - memblock_limit = bank->start; - else if (!IS_ALIGNED(bank_end, SECTION_SIZE)) - memblock_limit = bank_end; + if (!IS_ALIGNED(block_start, SECTION_SIZE)) + memblock_limit = block_start; + else if (!IS_ALIGNED(block_end, SECTION_SIZE)) + memblock_limit = arm_lowmem_limit; } - } - j++; - } -#ifdef CONFIG_HIGHMEM - if (highmem) { - const char *reason = NULL; - if (cache_is_vipt_aliasing()) { - /* - * Interactions between kmap and other mappings - * make highmem support with aliasing VIPT caches - * rather difficult. - */ - reason = "with VIPT aliasing cache"; - } - if (reason) { - printk(KERN_CRIT "HIGHMEM is not supported %s, ignoring high memory\n", - reason); - while (j > 0 && meminfo.bank[j - 1].highmem) - j--; } } -#endif - meminfo.nr_banks = j; + high_memory = __va(arm_lowmem_limit - 1) + 1; /* @@ -1359,6 +1326,9 @@ static void __init kmap_init(void) #ifdef CONFIG_HIGHMEM pkmap_page_table = early_pte_alloc(pmd_off_k(PKMAP_BASE), PKMAP_BASE, _PAGE_KERNEL_TABLE); + + fixmap_page_table = early_pte_alloc(pmd_off_k(FIXADDR_START), + FIXADDR_START, _PAGE_KERNEL_TABLE); #endif } @@ -1436,8 +1406,8 @@ void __init early_paging_init(const struct machine_desc *mdesc, return; /* remap kernel code and data */ - map_start = init_mm.start_code; - map_end = init_mm.brk; + map_start = init_mm.start_code & PMD_MASK; + map_end = ALIGN(init_mm.brk, PMD_SIZE); /* get a handle on things... */ pgd0 = pgd_offset_k(0); @@ -1461,26 +1431,67 @@ void __init early_paging_init(const struct machine_desc *mdesc, * just complicate the code. */ flush_cache_louis(); - dsb(); + dsb(ishst); isb(); - /* remap level 1 table */ + /* + * FIXME: This code is not architecturally compliant: we modify + * the mappings in-place, indeed while they are in use by this + * very same code. This may lead to unpredictable behaviour of + * the CPU. + * + * Even modifying the mappings in a separate page table does + * not resolve this. + * + * The architecture strongly recommends that when a mapping is + * changed, that it is changed by first going via an invalid + * mapping and back to the new mapping. This is to ensure that + * no TLB conflicts (caused by the TLB having more than one TLB + * entry match a translation) can occur. However, doing that + * here will result in unmapping the code we are running. + */ + pr_warn("WARNING: unsafe modification of in-place page tables - tainting kernel\n"); + add_taint(TAINT_CPU_OUT_OF_SPEC, LOCKDEP_STILL_OK); + + /* + * Remap level 1 table. This changes the physical addresses + * used to refer to the level 2 page tables to the high + * physical address alias, leaving everything else the same. + */ for (i = 0; i < PTRS_PER_PGD; pud0++, i++) { set_pud(pud0, __pud(__pa(pmd0) | PMD_TYPE_TABLE | L_PGD_SWAPPER)); pmd0 += PTRS_PER_PMD; } - /* remap pmds for kernel mapping */ - phys = __pa(map_start) & PMD_MASK; + /* + * Remap the level 2 table, pointing the mappings at the high + * physical address alias of these pages. + */ + phys = __pa(map_start); do { *pmdk++ = __pmd(phys | pmdprot); phys += PMD_SIZE; } while (phys < map_end); + /* + * Ensure that the above updates are flushed out of the cache. + * This is not strictly correct; on a system where the caches + * are coherent with each other, but the MMU page table walks + * may not be coherent, flush_cache_all() may be a no-op, and + * this will fail. + */ flush_cache_all(); + + /* + * Re-write the TTBR values to point them at the high physical + * alias of the page tables. We expect __va() will work on + * cpu_get_pgd(), which returns the value of TTBR0. + */ cpu_switch_mm(pgd0, &init_mm); cpu_set_ttbr(1, __pa(pgd0) + TTBR1_OFFSET); + + /* Finally flush any stale TLB values. */ local_flush_bp_all(); local_flush_tlb_all(); } diff --git a/arch/arm/mm/nommu.c b/arch/arm/mm/nommu.c index 55764a7ef1f0..a014dfacd5ca 100644 --- a/arch/arm/mm/nommu.c +++ b/arch/arm/mm/nommu.c @@ -88,30 +88,35 @@ static unsigned long irbar_read(void) void __init sanity_check_meminfo_mpu(void) { int i; - struct membank *bank = meminfo.bank; phys_addr_t phys_offset = PHYS_OFFSET; phys_addr_t aligned_region_size, specified_mem_size, rounded_mem_size; - - /* Initially only use memory continuous from PHYS_OFFSET */ - if (bank_phys_start(&bank[0]) != phys_offset) - panic("First memory bank must be contiguous from PHYS_OFFSET"); - - /* Banks have already been sorted by start address */ - for (i = 1; i < meminfo.nr_banks; i++) { - if (bank[i].start <= bank_phys_end(&bank[0]) && - bank_phys_end(&bank[i]) > bank_phys_end(&bank[0])) { - bank[0].size = bank_phys_end(&bank[i]) - bank[0].start; + struct memblock_region *reg; + bool first = true; + phys_addr_t mem_start; + phys_addr_t mem_end; + + for_each_memblock(memory, reg) { + if (first) { + /* + * Initially only use memory continuous from + * PHYS_OFFSET */ + if (reg->base != phys_offset) + panic("First memory bank must be contiguous from PHYS_OFFSET"); + + mem_start = reg->base; + mem_end = reg->base + reg->size; + specified_mem_size = reg->size; + first = false; } else { - pr_notice("Ignoring RAM after 0x%.8lx. " - "First non-contiguous (ignored) bank start: 0x%.8lx\n", - (unsigned long)bank_phys_end(&bank[0]), - (unsigned long)bank_phys_start(&bank[i])); - break; + /* + * memblock auto merges contiguous blocks, remove + * all blocks afterwards + */ + pr_notice("Ignoring RAM after %pa, memory at %pa ignored\n", + &mem_start, ®->base); + memblock_remove(reg->base, reg->size); } } - /* All contiguous banks are now merged in to the first bank */ - meminfo.nr_banks = 1; - specified_mem_size = bank[0].size; /* * MPU has curious alignment requirements: Size must be power of 2, and @@ -128,23 +133,24 @@ void __init sanity_check_meminfo_mpu(void) */ aligned_region_size = (phys_offset - 1) ^ (phys_offset); /* Find the max power-of-two sized region that fits inside our bank */ - rounded_mem_size = (1 << __fls(bank[0].size)) - 1; + rounded_mem_size = (1 << __fls(specified_mem_size)) - 1; /* The actual region size is the smaller of the two */ aligned_region_size = aligned_region_size < rounded_mem_size ? aligned_region_size + 1 : rounded_mem_size + 1; - if (aligned_region_size != specified_mem_size) - pr_warn("Truncating memory from 0x%.8lx to 0x%.8lx (MPU region constraints)", - (unsigned long)specified_mem_size, - (unsigned long)aligned_region_size); + if (aligned_region_size != specified_mem_size) { + pr_warn("Truncating memory from %pa to %pa (MPU region constraints)", + &specified_mem_size, &aligned_region_size); + memblock_remove(mem_start + aligned_region_size, + specified_mem_size - aligned_round_size); + + mem_end = mem_start + aligned_region_size; + } - meminfo.bank[0].size = aligned_region_size; - pr_debug("MPU Region from 0x%.8lx size 0x%.8lx (end 0x%.8lx))\n", - (unsigned long)phys_offset, - (unsigned long)aligned_region_size, - (unsigned long)bank_phys_end(&bank[0])); + pr_debug("MPU Region from %pa size %pa (end %pa))\n", + &phys_offset, &aligned_region_size, &mem_end); } @@ -292,8 +298,9 @@ void __init sanity_check_meminfo(void) { phys_addr_t end; sanity_check_meminfo_mpu(); - end = bank_phys_end(&meminfo.bank[meminfo.nr_banks - 1]); + end = memblock_end_of_DRAM(); high_memory = __va(end - 1) + 1; + memblock_set_current_limit(end); } /* diff --git a/arch/arm/mm/proc-arm1020.S b/arch/arm/mm/proc-arm1020.S index d1a2d05971e0..86ee5d47ce3c 100644 --- a/arch/arm/mm/proc-arm1020.S +++ b/arch/arm/mm/proc-arm1020.S @@ -73,7 +73,7 @@ * cpu_arm1020_proc_init() */ ENTRY(cpu_arm1020_proc_init) - mov pc, lr + ret lr /* * cpu_arm1020_proc_fin() @@ -83,7 +83,7 @@ ENTRY(cpu_arm1020_proc_fin) bic r0, r0, #0x1000 @ ...i............ bic r0, r0, #0x000e @ ............wca. mcr p15, 0, r0, c1, c0, 0 @ disable caches - mov pc, lr + ret lr /* * cpu_arm1020_reset(loc) @@ -107,7 +107,7 @@ ENTRY(cpu_arm1020_reset) bic ip, ip, #0x000f @ ............wcam bic ip, ip, #0x1100 @ ...i...s........ mcr p15, 0, ip, c1, c0, 0 @ ctrl register - mov pc, r0 + ret r0 ENDPROC(cpu_arm1020_reset) .popsection @@ -117,7 +117,7 @@ ENDPROC(cpu_arm1020_reset) .align 5 ENTRY(cpu_arm1020_do_idle) mcr p15, 0, r0, c7, c0, 4 @ Wait for interrupt - mov pc, lr + ret lr /* ================================= CACHE ================================ */ @@ -133,7 +133,7 @@ ENTRY(arm1020_flush_icache_all) mov r0, #0 mcr p15, 0, r0, c7, c5, 0 @ invalidate I cache #endif - mov pc, lr + ret lr ENDPROC(arm1020_flush_icache_all) /* @@ -169,7 +169,7 @@ __flush_whole_cache: mcrne p15, 0, ip, c7, c5, 0 @ invalidate I cache #endif mcrne p15, 0, ip, c7, c10, 4 @ drain WB - mov pc, lr + ret lr /* * flush_user_cache_range(start, end, flags) @@ -200,7 +200,7 @@ ENTRY(arm1020_flush_user_cache_range) mcrne p15, 0, ip, c7, c5, 0 @ invalidate I cache #endif mcrne p15, 0, ip, c7, c10, 4 @ drain WB - mov pc, lr + ret lr /* * coherent_kern_range(start, end) @@ -242,7 +242,7 @@ ENTRY(arm1020_coherent_user_range) blo 1b mcr p15, 0, ip, c7, c10, 4 @ drain WB mov r0, #0 - mov pc, lr + ret lr /* * flush_kern_dcache_area(void *addr, size_t size) @@ -264,7 +264,7 @@ ENTRY(arm1020_flush_kern_dcache_area) blo 1b #endif mcr p15, 0, ip, c7, c10, 4 @ drain WB - mov pc, lr + ret lr /* * dma_inv_range(start, end) @@ -297,7 +297,7 @@ arm1020_dma_inv_range: blo 1b #endif mcr p15, 0, ip, c7, c10, 4 @ drain WB - mov pc, lr + ret lr /* * dma_clean_range(start, end) @@ -320,7 +320,7 @@ arm1020_dma_clean_range: blo 1b #endif mcr p15, 0, ip, c7, c10, 4 @ drain WB - mov pc, lr + ret lr /* * dma_flush_range(start, end) @@ -342,7 +342,7 @@ ENTRY(arm1020_dma_flush_range) blo 1b #endif mcr p15, 0, ip, c7, c10, 4 @ drain WB - mov pc, lr + ret lr /* * dma_map_area(start, size, dir) @@ -365,7 +365,7 @@ ENDPROC(arm1020_dma_map_area) * - dir - DMA direction */ ENTRY(arm1020_dma_unmap_area) - mov pc, lr + ret lr ENDPROC(arm1020_dma_unmap_area) .globl arm1020_flush_kern_cache_louis @@ -384,7 +384,7 @@ ENTRY(cpu_arm1020_dcache_clean_area) subs r1, r1, #CACHE_DLINESIZE bhi 1b #endif - mov pc, lr + ret lr /* =============================== PageTable ============================== */ @@ -423,7 +423,7 @@ ENTRY(cpu_arm1020_switch_mm) mcr p15, 0, r0, c2, c0, 0 @ load page table pointer mcr p15, 0, r1, c8, c7, 0 @ invalidate I & D TLBs #endif /* CONFIG_MMU */ - mov pc, lr + ret lr /* * cpu_arm1020_set_pte(ptep, pte) @@ -441,7 +441,7 @@ ENTRY(cpu_arm1020_set_pte_ext) #endif mcr p15, 0, r0, c7, c10, 4 @ drain WB #endif /* CONFIG_MMU */ - mov pc, lr + ret lr .type __arm1020_setup, #function __arm1020_setup: @@ -460,7 +460,7 @@ __arm1020_setup: #ifdef CONFIG_CPU_CACHE_ROUND_ROBIN orr r0, r0, #0x4000 @ .R.. .... .... .... #endif - mov pc, lr + ret lr .size __arm1020_setup, . - __arm1020_setup /* diff --git a/arch/arm/mm/proc-arm1020e.S b/arch/arm/mm/proc-arm1020e.S index 9d89405c3d03..a6331d78601f 100644 --- a/arch/arm/mm/proc-arm1020e.S +++ b/arch/arm/mm/proc-arm1020e.S @@ -73,7 +73,7 @@ * cpu_arm1020e_proc_init() */ ENTRY(cpu_arm1020e_proc_init) - mov pc, lr + ret lr /* * cpu_arm1020e_proc_fin() @@ -83,7 +83,7 @@ ENTRY(cpu_arm1020e_proc_fin) bic r0, r0, #0x1000 @ ...i............ bic r0, r0, #0x000e @ ............wca. mcr p15, 0, r0, c1, c0, 0 @ disable caches - mov pc, lr + ret lr /* * cpu_arm1020e_reset(loc) @@ -107,7 +107,7 @@ ENTRY(cpu_arm1020e_reset) bic ip, ip, #0x000f @ ............wcam bic ip, ip, #0x1100 @ ...i...s........ mcr p15, 0, ip, c1, c0, 0 @ ctrl register - mov pc, r0 + ret r0 ENDPROC(cpu_arm1020e_reset) .popsection @@ -117,7 +117,7 @@ ENDPROC(cpu_arm1020e_reset) .align 5 ENTRY(cpu_arm1020e_do_idle) mcr p15, 0, r0, c7, c0, 4 @ Wait for interrupt - mov pc, lr + ret lr /* ================================= CACHE ================================ */ @@ -133,7 +133,7 @@ ENTRY(arm1020e_flush_icache_all) mov r0, #0 mcr p15, 0, r0, c7, c5, 0 @ invalidate I cache #endif - mov pc, lr + ret lr ENDPROC(arm1020e_flush_icache_all) /* @@ -168,7 +168,7 @@ __flush_whole_cache: mcrne p15, 0, ip, c7, c5, 0 @ invalidate I cache #endif mcrne p15, 0, ip, c7, c10, 4 @ drain WB - mov pc, lr + ret lr /* * flush_user_cache_range(start, end, flags) @@ -197,7 +197,7 @@ ENTRY(arm1020e_flush_user_cache_range) mcrne p15, 0, ip, c7, c5, 0 @ invalidate I cache #endif mcrne p15, 0, ip, c7, c10, 4 @ drain WB - mov pc, lr + ret lr /* * coherent_kern_range(start, end) @@ -236,7 +236,7 @@ ENTRY(arm1020e_coherent_user_range) blo 1b mcr p15, 0, ip, c7, c10, 4 @ drain WB mov r0, #0 - mov pc, lr + ret lr /* * flush_kern_dcache_area(void *addr, size_t size) @@ -257,7 +257,7 @@ ENTRY(arm1020e_flush_kern_dcache_area) blo 1b #endif mcr p15, 0, ip, c7, c10, 4 @ drain WB - mov pc, lr + ret lr /* * dma_inv_range(start, end) @@ -286,7 +286,7 @@ arm1020e_dma_inv_range: blo 1b #endif mcr p15, 0, ip, c7, c10, 4 @ drain WB - mov pc, lr + ret lr /* * dma_clean_range(start, end) @@ -308,7 +308,7 @@ arm1020e_dma_clean_range: blo 1b #endif mcr p15, 0, ip, c7, c10, 4 @ drain WB - mov pc, lr + ret lr /* * dma_flush_range(start, end) @@ -328,7 +328,7 @@ ENTRY(arm1020e_dma_flush_range) blo 1b #endif mcr p15, 0, ip, c7, c10, 4 @ drain WB - mov pc, lr + ret lr /* * dma_map_area(start, size, dir) @@ -351,7 +351,7 @@ ENDPROC(arm1020e_dma_map_area) * - dir - DMA direction */ ENTRY(arm1020e_dma_unmap_area) - mov pc, lr + ret lr ENDPROC(arm1020e_dma_unmap_area) .globl arm1020e_flush_kern_cache_louis @@ -369,7 +369,7 @@ ENTRY(cpu_arm1020e_dcache_clean_area) subs r1, r1, #CACHE_DLINESIZE bhi 1b #endif - mov pc, lr + ret lr /* =============================== PageTable ============================== */ @@ -407,7 +407,7 @@ ENTRY(cpu_arm1020e_switch_mm) mcr p15, 0, r0, c2, c0, 0 @ load page table pointer mcr p15, 0, r1, c8, c7, 0 @ invalidate I & D TLBs #endif - mov pc, lr + ret lr /* * cpu_arm1020e_set_pte(ptep, pte) @@ -423,7 +423,7 @@ ENTRY(cpu_arm1020e_set_pte_ext) mcr p15, 0, r0, c7, c10, 1 @ clean D entry #endif #endif /* CONFIG_MMU */ - mov pc, lr + ret lr .type __arm1020e_setup, #function __arm1020e_setup: @@ -441,7 +441,7 @@ __arm1020e_setup: #ifdef CONFIG_CPU_CACHE_ROUND_ROBIN orr r0, r0, #0x4000 @ .R.. .... .... .... #endif - mov pc, lr + ret lr .size __arm1020e_setup, . - __arm1020e_setup /* diff --git a/arch/arm/mm/proc-arm1022.S b/arch/arm/mm/proc-arm1022.S index 6f01a0ae3b30..a126b7a59928 100644 --- a/arch/arm/mm/proc-arm1022.S +++ b/arch/arm/mm/proc-arm1022.S @@ -62,7 +62,7 @@ * cpu_arm1022_proc_init() */ ENTRY(cpu_arm1022_proc_init) - mov pc, lr + ret lr /* * cpu_arm1022_proc_fin() @@ -72,7 +72,7 @@ ENTRY(cpu_arm1022_proc_fin) bic r0, r0, #0x1000 @ ...i............ bic r0, r0, #0x000e @ ............wca. mcr p15, 0, r0, c1, c0, 0 @ disable caches - mov pc, lr + ret lr /* * cpu_arm1022_reset(loc) @@ -96,7 +96,7 @@ ENTRY(cpu_arm1022_reset) bic ip, ip, #0x000f @ ............wcam bic ip, ip, #0x1100 @ ...i...s........ mcr p15, 0, ip, c1, c0, 0 @ ctrl register - mov pc, r0 + ret r0 ENDPROC(cpu_arm1022_reset) .popsection @@ -106,7 +106,7 @@ ENDPROC(cpu_arm1022_reset) .align 5 ENTRY(cpu_arm1022_do_idle) mcr p15, 0, r0, c7, c0, 4 @ Wait for interrupt - mov pc, lr + ret lr /* ================================= CACHE ================================ */ @@ -122,7 +122,7 @@ ENTRY(arm1022_flush_icache_all) mov r0, #0 mcr p15, 0, r0, c7, c5, 0 @ invalidate I cache #endif - mov pc, lr + ret lr ENDPROC(arm1022_flush_icache_all) /* @@ -156,7 +156,7 @@ __flush_whole_cache: mcrne p15, 0, ip, c7, c5, 0 @ invalidate I cache #endif mcrne p15, 0, ip, c7, c10, 4 @ drain WB - mov pc, lr + ret lr /* * flush_user_cache_range(start, end, flags) @@ -185,7 +185,7 @@ ENTRY(arm1022_flush_user_cache_range) mcrne p15, 0, ip, c7, c5, 0 @ invalidate I cache #endif mcrne p15, 0, ip, c7, c10, 4 @ drain WB - mov pc, lr + ret lr /* * coherent_kern_range(start, end) @@ -225,7 +225,7 @@ ENTRY(arm1022_coherent_user_range) blo 1b mcr p15, 0, ip, c7, c10, 4 @ drain WB mov r0, #0 - mov pc, lr + ret lr /* * flush_kern_dcache_area(void *addr, size_t size) @@ -246,7 +246,7 @@ ENTRY(arm1022_flush_kern_dcache_area) blo 1b #endif mcr p15, 0, ip, c7, c10, 4 @ drain WB - mov pc, lr + ret lr /* * dma_inv_range(start, end) @@ -275,7 +275,7 @@ arm1022_dma_inv_range: blo 1b #endif mcr p15, 0, ip, c7, c10, 4 @ drain WB - mov pc, lr + ret lr /* * dma_clean_range(start, end) @@ -297,7 +297,7 @@ arm1022_dma_clean_range: blo 1b #endif mcr p15, 0, ip, c7, c10, 4 @ drain WB - mov pc, lr + ret lr /* * dma_flush_range(start, end) @@ -317,7 +317,7 @@ ENTRY(arm1022_dma_flush_range) blo 1b #endif mcr p15, 0, ip, c7, c10, 4 @ drain WB - mov pc, lr + ret lr /* * dma_map_area(start, size, dir) @@ -340,7 +340,7 @@ ENDPROC(arm1022_dma_map_area) * - dir - DMA direction */ ENTRY(arm1022_dma_unmap_area) - mov pc, lr + ret lr ENDPROC(arm1022_dma_unmap_area) .globl arm1022_flush_kern_cache_louis @@ -358,7 +358,7 @@ ENTRY(cpu_arm1022_dcache_clean_area) subs r1, r1, #CACHE_DLINESIZE bhi 1b #endif - mov pc, lr + ret lr /* =============================== PageTable ============================== */ @@ -389,7 +389,7 @@ ENTRY(cpu_arm1022_switch_mm) mcr p15, 0, r0, c2, c0, 0 @ load page table pointer mcr p15, 0, r1, c8, c7, 0 @ invalidate I & D TLBs #endif - mov pc, lr + ret lr /* * cpu_arm1022_set_pte_ext(ptep, pte, ext) @@ -405,7 +405,7 @@ ENTRY(cpu_arm1022_set_pte_ext) mcr p15, 0, r0, c7, c10, 1 @ clean D entry #endif #endif /* CONFIG_MMU */ - mov pc, lr + ret lr .type __arm1022_setup, #function __arm1022_setup: @@ -423,7 +423,7 @@ __arm1022_setup: #ifdef CONFIG_CPU_CACHE_ROUND_ROBIN orr r0, r0, #0x4000 @ .R.............. #endif - mov pc, lr + ret lr .size __arm1022_setup, . - __arm1022_setup /* diff --git a/arch/arm/mm/proc-arm1026.S b/arch/arm/mm/proc-arm1026.S index 4799a24b43e6..fc294067e977 100644 --- a/arch/arm/mm/proc-arm1026.S +++ b/arch/arm/mm/proc-arm1026.S @@ -62,7 +62,7 @@ * cpu_arm1026_proc_init() */ ENTRY(cpu_arm1026_proc_init) - mov pc, lr + ret lr /* * cpu_arm1026_proc_fin() @@ -72,7 +72,7 @@ ENTRY(cpu_arm1026_proc_fin) bic r0, r0, #0x1000 @ ...i............ bic r0, r0, #0x000e @ ............wca. mcr p15, 0, r0, c1, c0, 0 @ disable caches - mov pc, lr + ret lr /* * cpu_arm1026_reset(loc) @@ -96,7 +96,7 @@ ENTRY(cpu_arm1026_reset) bic ip, ip, #0x000f @ ............wcam bic ip, ip, #0x1100 @ ...i...s........ mcr p15, 0, ip, c1, c0, 0 @ ctrl register - mov pc, r0 + ret r0 ENDPROC(cpu_arm1026_reset) .popsection @@ -106,7 +106,7 @@ ENDPROC(cpu_arm1026_reset) .align 5 ENTRY(cpu_arm1026_do_idle) mcr p15, 0, r0, c7, c0, 4 @ Wait for interrupt - mov pc, lr + ret lr /* ================================= CACHE ================================ */ @@ -122,7 +122,7 @@ ENTRY(arm1026_flush_icache_all) mov r0, #0 mcr p15, 0, r0, c7, c5, 0 @ invalidate I cache #endif - mov pc, lr + ret lr ENDPROC(arm1026_flush_icache_all) /* @@ -151,7 +151,7 @@ __flush_whole_cache: mcrne p15, 0, ip, c7, c5, 0 @ invalidate I cache #endif mcrne p15, 0, ip, c7, c10, 4 @ drain WB - mov pc, lr + ret lr /* * flush_user_cache_range(start, end, flags) @@ -180,7 +180,7 @@ ENTRY(arm1026_flush_user_cache_range) mcrne p15, 0, ip, c7, c5, 0 @ invalidate I cache #endif mcrne p15, 0, ip, c7, c10, 4 @ drain WB - mov pc, lr + ret lr /* * coherent_kern_range(start, end) @@ -219,7 +219,7 @@ ENTRY(arm1026_coherent_user_range) blo 1b mcr p15, 0, ip, c7, c10, 4 @ drain WB mov r0, #0 - mov pc, lr + ret lr /* * flush_kern_dcache_area(void *addr, size_t size) @@ -240,7 +240,7 @@ ENTRY(arm1026_flush_kern_dcache_area) blo 1b #endif mcr p15, 0, ip, c7, c10, 4 @ drain WB - mov pc, lr + ret lr /* * dma_inv_range(start, end) @@ -269,7 +269,7 @@ arm1026_dma_inv_range: blo 1b #endif mcr p15, 0, ip, c7, c10, 4 @ drain WB - mov pc, lr + ret lr /* * dma_clean_range(start, end) @@ -291,7 +291,7 @@ arm1026_dma_clean_range: blo 1b #endif mcr p15, 0, ip, c7, c10, 4 @ drain WB - mov pc, lr + ret lr /* * dma_flush_range(start, end) @@ -311,7 +311,7 @@ ENTRY(arm1026_dma_flush_range) blo 1b #endif mcr p15, 0, ip, c7, c10, 4 @ drain WB - mov pc, lr + ret lr /* * dma_map_area(start, size, dir) @@ -334,7 +334,7 @@ ENDPROC(arm1026_dma_map_area) * - dir - DMA direction */ ENTRY(arm1026_dma_unmap_area) - mov pc, lr + ret lr ENDPROC(arm1026_dma_unmap_area) .globl arm1026_flush_kern_cache_louis @@ -352,7 +352,7 @@ ENTRY(cpu_arm1026_dcache_clean_area) subs r1, r1, #CACHE_DLINESIZE bhi 1b #endif - mov pc, lr + ret lr /* =============================== PageTable ============================== */ @@ -378,7 +378,7 @@ ENTRY(cpu_arm1026_switch_mm) mcr p15, 0, r0, c2, c0, 0 @ load page table pointer mcr p15, 0, r1, c8, c7, 0 @ invalidate I & D TLBs #endif - mov pc, lr + ret lr /* * cpu_arm1026_set_pte_ext(ptep, pte, ext) @@ -394,7 +394,7 @@ ENTRY(cpu_arm1026_set_pte_ext) mcr p15, 0, r0, c7, c10, 1 @ clean D entry #endif #endif /* CONFIG_MMU */ - mov pc, lr + ret lr .type __arm1026_setup, #function __arm1026_setup: @@ -417,7 +417,7 @@ __arm1026_setup: #ifdef CONFIG_CPU_CACHE_ROUND_ROBIN orr r0, r0, #0x4000 @ .R.. .... .... .... #endif - mov pc, lr + ret lr .size __arm1026_setup, . - __arm1026_setup /* diff --git a/arch/arm/mm/proc-arm720.S b/arch/arm/mm/proc-arm720.S index d42c37f9f5bc..2baa66b3ac9b 100644 --- a/arch/arm/mm/proc-arm720.S +++ b/arch/arm/mm/proc-arm720.S @@ -51,14 +51,14 @@ */ ENTRY(cpu_arm720_dcache_clean_area) ENTRY(cpu_arm720_proc_init) - mov pc, lr + ret lr ENTRY(cpu_arm720_proc_fin) mrc p15, 0, r0, c1, c0, 0 bic r0, r0, #0x1000 @ ...i............ bic r0, r0, #0x000e @ ............wca. mcr p15, 0, r0, c1, c0, 0 @ disable caches - mov pc, lr + ret lr /* * Function: arm720_proc_do_idle(void) @@ -66,7 +66,7 @@ ENTRY(cpu_arm720_proc_fin) * Purpose : put the processor in proper idle mode */ ENTRY(cpu_arm720_do_idle) - mov pc, lr + ret lr /* * Function: arm720_switch_mm(unsigned long pgd_phys) @@ -81,7 +81,7 @@ ENTRY(cpu_arm720_switch_mm) mcr p15, 0, r0, c2, c0, 0 @ update page table ptr mcr p15, 0, r1, c8, c7, 0 @ flush TLB (v4) #endif - mov pc, lr + ret lr /* * Function: arm720_set_pte_ext(pte_t *ptep, pte_t pte, unsigned int ext) @@ -94,7 +94,7 @@ ENTRY(cpu_arm720_set_pte_ext) #ifdef CONFIG_MMU armv3_set_pte_ext wc_disable=0 #endif - mov pc, lr + ret lr /* * Function: arm720_reset @@ -112,7 +112,7 @@ ENTRY(cpu_arm720_reset) bic ip, ip, #0x000f @ ............wcam bic ip, ip, #0x2100 @ ..v....s........ mcr p15, 0, ip, c1, c0, 0 @ ctrl register - mov pc, r0 + ret r0 ENDPROC(cpu_arm720_reset) .popsection @@ -128,7 +128,7 @@ __arm710_setup: bic r0, r0, r5 ldr r5, arm710_cr1_set orr r0, r0, r5 - mov pc, lr @ __ret (head.S) + ret lr @ __ret (head.S) .size __arm710_setup, . - __arm710_setup /* @@ -156,7 +156,7 @@ __arm720_setup: mrc p15, 0, r0, c1, c0 @ get control register bic r0, r0, r5 orr r0, r0, r6 - mov pc, lr @ __ret (head.S) + ret lr @ __ret (head.S) .size __arm720_setup, . - __arm720_setup /* diff --git a/arch/arm/mm/proc-arm740.S b/arch/arm/mm/proc-arm740.S index 9b0ae90cbf17..ac1ea6b3bce4 100644 --- a/arch/arm/mm/proc-arm740.S +++ b/arch/arm/mm/proc-arm740.S @@ -32,7 +32,7 @@ ENTRY(cpu_arm740_proc_init) ENTRY(cpu_arm740_do_idle) ENTRY(cpu_arm740_dcache_clean_area) ENTRY(cpu_arm740_switch_mm) - mov pc, lr + ret lr /* * cpu_arm740_proc_fin() @@ -42,7 +42,7 @@ ENTRY(cpu_arm740_proc_fin) bic r0, r0, #0x3f000000 @ bank/f/lock/s bic r0, r0, #0x0000000c @ w-buffer/cache mcr p15, 0, r0, c1, c0, 0 @ disable caches - mov pc, lr + ret lr /* * cpu_arm740_reset(loc) @@ -56,7 +56,7 @@ ENTRY(cpu_arm740_reset) mrc p15, 0, ip, c1, c0, 0 @ get ctrl register bic ip, ip, #0x0000000c @ ............wc.. mcr p15, 0, ip, c1, c0, 0 @ ctrl register - mov pc, r0 + ret r0 ENDPROC(cpu_arm740_reset) .popsection @@ -115,7 +115,7 @@ __arm740_setup: @ need some benchmark orr r0, r0, #0x0000000d @ MPU/Cache/WB - mov pc, lr + ret lr .size __arm740_setup, . - __arm740_setup diff --git a/arch/arm/mm/proc-arm7tdmi.S b/arch/arm/mm/proc-arm7tdmi.S index f6cc3f63ce39..bf6ba4bc30ff 100644 --- a/arch/arm/mm/proc-arm7tdmi.S +++ b/arch/arm/mm/proc-arm7tdmi.S @@ -32,13 +32,13 @@ ENTRY(cpu_arm7tdmi_proc_init) ENTRY(cpu_arm7tdmi_do_idle) ENTRY(cpu_arm7tdmi_dcache_clean_area) ENTRY(cpu_arm7tdmi_switch_mm) - mov pc, lr + ret lr /* * cpu_arm7tdmi_proc_fin() */ ENTRY(cpu_arm7tdmi_proc_fin) - mov pc, lr + ret lr /* * Function: cpu_arm7tdmi_reset(loc) @@ -47,13 +47,13 @@ ENTRY(cpu_arm7tdmi_proc_fin) */ .pushsection .idmap.text, "ax" ENTRY(cpu_arm7tdmi_reset) - mov pc, r0 + ret r0 ENDPROC(cpu_arm7tdmi_reset) .popsection .type __arm7tdmi_setup, #function __arm7tdmi_setup: - mov pc, lr + ret lr .size __arm7tdmi_setup, . - __arm7tdmi_setup __INITDATA diff --git a/arch/arm/mm/proc-arm920.S b/arch/arm/mm/proc-arm920.S index 549557df6d57..22bf8dde4f84 100644 --- a/arch/arm/mm/proc-arm920.S +++ b/arch/arm/mm/proc-arm920.S @@ -63,7 +63,7 @@ * cpu_arm920_proc_init() */ ENTRY(cpu_arm920_proc_init) - mov pc, lr + ret lr /* * cpu_arm920_proc_fin() @@ -73,7 +73,7 @@ ENTRY(cpu_arm920_proc_fin) bic r0, r0, #0x1000 @ ...i............ bic r0, r0, #0x000e @ ............wca. mcr p15, 0, r0, c1, c0, 0 @ disable caches - mov pc, lr + ret lr /* * cpu_arm920_reset(loc) @@ -97,7 +97,7 @@ ENTRY(cpu_arm920_reset) bic ip, ip, #0x000f @ ............wcam bic ip, ip, #0x1100 @ ...i...s........ mcr p15, 0, ip, c1, c0, 0 @ ctrl register - mov pc, r0 + ret r0 ENDPROC(cpu_arm920_reset) .popsection @@ -107,7 +107,7 @@ ENDPROC(cpu_arm920_reset) .align 5 ENTRY(cpu_arm920_do_idle) mcr p15, 0, r0, c7, c0, 4 @ Wait for interrupt - mov pc, lr + ret lr #ifndef CONFIG_CPU_DCACHE_WRITETHROUGH @@ -120,7 +120,7 @@ ENTRY(cpu_arm920_do_idle) ENTRY(arm920_flush_icache_all) mov r0, #0 mcr p15, 0, r0, c7, c5, 0 @ invalidate I cache - mov pc, lr + ret lr ENDPROC(arm920_flush_icache_all) /* @@ -151,7 +151,7 @@ __flush_whole_cache: tst r2, #VM_EXEC mcrne p15, 0, ip, c7, c5, 0 @ invalidate I cache mcrne p15, 0, ip, c7, c10, 4 @ drain WB - mov pc, lr + ret lr /* * flush_user_cache_range(start, end, flags) @@ -177,7 +177,7 @@ ENTRY(arm920_flush_user_cache_range) blo 1b tst r2, #VM_EXEC mcrne p15, 0, ip, c7, c10, 4 @ drain WB - mov pc, lr + ret lr /* * coherent_kern_range(start, end) @@ -211,7 +211,7 @@ ENTRY(arm920_coherent_user_range) blo 1b mcr p15, 0, r0, c7, c10, 4 @ drain WB mov r0, #0 - mov pc, lr + ret lr /* * flush_kern_dcache_area(void *addr, size_t size) @@ -231,7 +231,7 @@ ENTRY(arm920_flush_kern_dcache_area) mov r0, #0 mcr p15, 0, r0, c7, c5, 0 @ invalidate I cache mcr p15, 0, r0, c7, c10, 4 @ drain WB - mov pc, lr + ret lr /* * dma_inv_range(start, end) @@ -257,7 +257,7 @@ arm920_dma_inv_range: cmp r0, r1 blo 1b mcr p15, 0, r0, c7, c10, 4 @ drain WB - mov pc, lr + ret lr /* * dma_clean_range(start, end) @@ -276,7 +276,7 @@ arm920_dma_clean_range: cmp r0, r1 blo 1b mcr p15, 0, r0, c7, c10, 4 @ drain WB - mov pc, lr + ret lr /* * dma_flush_range(start, end) @@ -293,7 +293,7 @@ ENTRY(arm920_dma_flush_range) cmp r0, r1 blo 1b mcr p15, 0, r0, c7, c10, 4 @ drain WB - mov pc, lr + ret lr /* * dma_map_area(start, size, dir) @@ -316,7 +316,7 @@ ENDPROC(arm920_dma_map_area) * - dir - DMA direction */ ENTRY(arm920_dma_unmap_area) - mov pc, lr + ret lr ENDPROC(arm920_dma_unmap_area) .globl arm920_flush_kern_cache_louis @@ -332,7 +332,7 @@ ENTRY(cpu_arm920_dcache_clean_area) add r0, r0, #CACHE_DLINESIZE subs r1, r1, #CACHE_DLINESIZE bhi 1b - mov pc, lr + ret lr /* =============================== PageTable ============================== */ @@ -367,7 +367,7 @@ ENTRY(cpu_arm920_switch_mm) mcr p15, 0, r0, c2, c0, 0 @ load page table pointer mcr p15, 0, ip, c8, c7, 0 @ invalidate I & D TLBs #endif - mov pc, lr + ret lr /* * cpu_arm920_set_pte(ptep, pte, ext) @@ -382,7 +382,7 @@ ENTRY(cpu_arm920_set_pte_ext) mcr p15, 0, r0, c7, c10, 1 @ clean D entry mcr p15, 0, r0, c7, c10, 4 @ drain WB #endif - mov pc, lr + ret lr /* Suspend/resume support: taken from arch/arm/plat-s3c24xx/sleep.S */ .globl cpu_arm920_suspend_size @@ -423,7 +423,7 @@ __arm920_setup: mrc p15, 0, r0, c1, c0 @ get control register v4 bic r0, r0, r5 orr r0, r0, r6 - mov pc, lr + ret lr .size __arm920_setup, . - __arm920_setup /* diff --git a/arch/arm/mm/proc-arm922.S b/arch/arm/mm/proc-arm922.S index 2a758b06c6f6..0c6d5ac5a6d4 100644 --- a/arch/arm/mm/proc-arm922.S +++ b/arch/arm/mm/proc-arm922.S @@ -65,7 +65,7 @@ * cpu_arm922_proc_init() */ ENTRY(cpu_arm922_proc_init) - mov pc, lr + ret lr /* * cpu_arm922_proc_fin() @@ -75,7 +75,7 @@ ENTRY(cpu_arm922_proc_fin) bic r0, r0, #0x1000 @ ...i............ bic r0, r0, #0x000e @ ............wca. mcr p15, 0, r0, c1, c0, 0 @ disable caches - mov pc, lr + ret lr /* * cpu_arm922_reset(loc) @@ -99,7 +99,7 @@ ENTRY(cpu_arm922_reset) bic ip, ip, #0x000f @ ............wcam bic ip, ip, #0x1100 @ ...i...s........ mcr p15, 0, ip, c1, c0, 0 @ ctrl register - mov pc, r0 + ret r0 ENDPROC(cpu_arm922_reset) .popsection @@ -109,7 +109,7 @@ ENDPROC(cpu_arm922_reset) .align 5 ENTRY(cpu_arm922_do_idle) mcr p15, 0, r0, c7, c0, 4 @ Wait for interrupt - mov pc, lr + ret lr #ifndef CONFIG_CPU_DCACHE_WRITETHROUGH @@ -122,7 +122,7 @@ ENTRY(cpu_arm922_do_idle) ENTRY(arm922_flush_icache_all) mov r0, #0 mcr p15, 0, r0, c7, c5, 0 @ invalidate I cache - mov pc, lr + ret lr ENDPROC(arm922_flush_icache_all) /* @@ -153,7 +153,7 @@ __flush_whole_cache: tst r2, #VM_EXEC mcrne p15, 0, ip, c7, c5, 0 @ invalidate I cache mcrne p15, 0, ip, c7, c10, 4 @ drain WB - mov pc, lr + ret lr /* * flush_user_cache_range(start, end, flags) @@ -179,7 +179,7 @@ ENTRY(arm922_flush_user_cache_range) blo 1b tst r2, #VM_EXEC mcrne p15, 0, ip, c7, c10, 4 @ drain WB - mov pc, lr + ret lr /* * coherent_kern_range(start, end) @@ -213,7 +213,7 @@ ENTRY(arm922_coherent_user_range) blo 1b mcr p15, 0, r0, c7, c10, 4 @ drain WB mov r0, #0 - mov pc, lr + ret lr /* * flush_kern_dcache_area(void *addr, size_t size) @@ -233,7 +233,7 @@ ENTRY(arm922_flush_kern_dcache_area) mov r0, #0 mcr p15, 0, r0, c7, c5, 0 @ invalidate I cache mcr p15, 0, r0, c7, c10, 4 @ drain WB - mov pc, lr + ret lr /* * dma_inv_range(start, end) @@ -259,7 +259,7 @@ arm922_dma_inv_range: cmp r0, r1 blo 1b mcr p15, 0, r0, c7, c10, 4 @ drain WB - mov pc, lr + ret lr /* * dma_clean_range(start, end) @@ -278,7 +278,7 @@ arm922_dma_clean_range: cmp r0, r1 blo 1b mcr p15, 0, r0, c7, c10, 4 @ drain WB - mov pc, lr + ret lr /* * dma_flush_range(start, end) @@ -295,7 +295,7 @@ ENTRY(arm922_dma_flush_range) cmp r0, r1 blo 1b mcr p15, 0, r0, c7, c10, 4 @ drain WB - mov pc, lr + ret lr /* * dma_map_area(start, size, dir) @@ -318,7 +318,7 @@ ENDPROC(arm922_dma_map_area) * - dir - DMA direction */ ENTRY(arm922_dma_unmap_area) - mov pc, lr + ret lr ENDPROC(arm922_dma_unmap_area) .globl arm922_flush_kern_cache_louis @@ -336,7 +336,7 @@ ENTRY(cpu_arm922_dcache_clean_area) subs r1, r1, #CACHE_DLINESIZE bhi 1b #endif - mov pc, lr + ret lr /* =============================== PageTable ============================== */ @@ -371,7 +371,7 @@ ENTRY(cpu_arm922_switch_mm) mcr p15, 0, r0, c2, c0, 0 @ load page table pointer mcr p15, 0, ip, c8, c7, 0 @ invalidate I & D TLBs #endif - mov pc, lr + ret lr /* * cpu_arm922_set_pte_ext(ptep, pte, ext) @@ -386,7 +386,7 @@ ENTRY(cpu_arm922_set_pte_ext) mcr p15, 0, r0, c7, c10, 1 @ clean D entry mcr p15, 0, r0, c7, c10, 4 @ drain WB #endif /* CONFIG_MMU */ - mov pc, lr + ret lr .type __arm922_setup, #function __arm922_setup: @@ -401,7 +401,7 @@ __arm922_setup: mrc p15, 0, r0, c1, c0 @ get control register v4 bic r0, r0, r5 orr r0, r0, r6 - mov pc, lr + ret lr .size __arm922_setup, . - __arm922_setup /* diff --git a/arch/arm/mm/proc-arm925.S b/arch/arm/mm/proc-arm925.S index 97448c3acf38..c32d073282ea 100644 --- a/arch/arm/mm/proc-arm925.S +++ b/arch/arm/mm/proc-arm925.S @@ -86,7 +86,7 @@ * cpu_arm925_proc_init() */ ENTRY(cpu_arm925_proc_init) - mov pc, lr + ret lr /* * cpu_arm925_proc_fin() @@ -96,7 +96,7 @@ ENTRY(cpu_arm925_proc_fin) bic r0, r0, #0x1000 @ ...i............ bic r0, r0, #0x000e @ ............wca. mcr p15, 0, r0, c1, c0, 0 @ disable caches - mov pc, lr + ret lr /* * cpu_arm925_reset(loc) @@ -129,7 +129,7 @@ ENDPROC(cpu_arm925_reset) bic ip, ip, #0x000f @ ............wcam bic ip, ip, #0x1100 @ ...i...s........ mcr p15, 0, ip, c1, c0, 0 @ ctrl register - mov pc, r0 + ret r0 /* * cpu_arm925_do_idle() @@ -145,7 +145,7 @@ ENTRY(cpu_arm925_do_idle) mcr p15, 0, r2, c1, c0, 0 @ Disable I cache mcr p15, 0, r0, c7, c0, 4 @ Wait for interrupt mcr p15, 0, r1, c1, c0, 0 @ Restore ICache enable - mov pc, lr + ret lr /* * flush_icache_all() @@ -155,7 +155,7 @@ ENTRY(cpu_arm925_do_idle) ENTRY(arm925_flush_icache_all) mov r0, #0 mcr p15, 0, r0, c7, c5, 0 @ invalidate I cache - mov pc, lr + ret lr ENDPROC(arm925_flush_icache_all) /* @@ -188,7 +188,7 @@ __flush_whole_cache: tst r2, #VM_EXEC mcrne p15, 0, ip, c7, c5, 0 @ invalidate I cache mcrne p15, 0, ip, c7, c10, 4 @ drain WB - mov pc, lr + ret lr /* * flush_user_cache_range(start, end, flags) @@ -225,7 +225,7 @@ ENTRY(arm925_flush_user_cache_range) blo 1b tst r2, #VM_EXEC mcrne p15, 0, ip, c7, c10, 4 @ drain WB - mov pc, lr + ret lr /* * coherent_kern_range(start, end) @@ -259,7 +259,7 @@ ENTRY(arm925_coherent_user_range) blo 1b mcr p15, 0, r0, c7, c10, 4 @ drain WB mov r0, #0 - mov pc, lr + ret lr /* * flush_kern_dcache_area(void *addr, size_t size) @@ -279,7 +279,7 @@ ENTRY(arm925_flush_kern_dcache_area) mov r0, #0 mcr p15, 0, r0, c7, c5, 0 @ invalidate I cache mcr p15, 0, r0, c7, c10, 4 @ drain WB - mov pc, lr + ret lr /* * dma_inv_range(start, end) @@ -307,7 +307,7 @@ arm925_dma_inv_range: cmp r0, r1 blo 1b mcr p15, 0, r0, c7, c10, 4 @ drain WB - mov pc, lr + ret lr /* * dma_clean_range(start, end) @@ -328,7 +328,7 @@ arm925_dma_clean_range: blo 1b #endif mcr p15, 0, r0, c7, c10, 4 @ drain WB - mov pc, lr + ret lr /* * dma_flush_range(start, end) @@ -350,7 +350,7 @@ ENTRY(arm925_dma_flush_range) cmp r0, r1 blo 1b mcr p15, 0, r0, c7, c10, 4 @ drain WB - mov pc, lr + ret lr /* * dma_map_area(start, size, dir) @@ -373,7 +373,7 @@ ENDPROC(arm925_dma_map_area) * - dir - DMA direction */ ENTRY(arm925_dma_unmap_area) - mov pc, lr + ret lr ENDPROC(arm925_dma_unmap_area) .globl arm925_flush_kern_cache_louis @@ -390,7 +390,7 @@ ENTRY(cpu_arm925_dcache_clean_area) bhi 1b #endif mcr p15, 0, r0, c7, c10, 4 @ drain WB - mov pc, lr + ret lr /* =============================== PageTable ============================== */ @@ -419,7 +419,7 @@ ENTRY(cpu_arm925_switch_mm) mcr p15, 0, r0, c2, c0, 0 @ load page table pointer mcr p15, 0, ip, c8, c7, 0 @ invalidate I & D TLBs #endif - mov pc, lr + ret lr /* * cpu_arm925_set_pte_ext(ptep, pte, ext) @@ -436,7 +436,7 @@ ENTRY(cpu_arm925_set_pte_ext) #endif mcr p15, 0, r0, c7, c10, 4 @ drain WB #endif /* CONFIG_MMU */ - mov pc, lr + ret lr .type __arm925_setup, #function __arm925_setup: @@ -469,7 +469,7 @@ __arm925_setup: #ifdef CONFIG_CPU_CACHE_ROUND_ROBIN orr r0, r0, #0x4000 @ .1.. .... .... .... #endif - mov pc, lr + ret lr .size __arm925_setup, . - __arm925_setup /* @@ -502,6 +502,7 @@ __\name\()_proc_info: .long \cpu_val .long \cpu_mask .long PMD_TYPE_SECT | \ + PMD_SECT_CACHEABLE | \ PMD_BIT4 | \ PMD_SECT_AP_WRITE | \ PMD_SECT_AP_READ diff --git a/arch/arm/mm/proc-arm926.S b/arch/arm/mm/proc-arm926.S index 0f098f407c9f..252b2503038d 100644 --- a/arch/arm/mm/proc-arm926.S +++ b/arch/arm/mm/proc-arm926.S @@ -55,7 +55,7 @@ * cpu_arm926_proc_init() */ ENTRY(cpu_arm926_proc_init) - mov pc, lr + ret lr /* * cpu_arm926_proc_fin() @@ -65,7 +65,7 @@ ENTRY(cpu_arm926_proc_fin) bic r0, r0, #0x1000 @ ...i............ bic r0, r0, #0x000e @ ............wca. mcr p15, 0, r0, c1, c0, 0 @ disable caches - mov pc, lr + ret lr /* * cpu_arm926_reset(loc) @@ -89,7 +89,7 @@ ENTRY(cpu_arm926_reset) bic ip, ip, #0x000f @ ............wcam bic ip, ip, #0x1100 @ ...i...s........ mcr p15, 0, ip, c1, c0, 0 @ ctrl register - mov pc, r0 + ret r0 ENDPROC(cpu_arm926_reset) .popsection @@ -111,7 +111,7 @@ ENTRY(cpu_arm926_do_idle) mcr p15, 0, r0, c7, c0, 4 @ Wait for interrupt mcr p15, 0, r1, c1, c0, 0 @ Restore ICache enable msr cpsr_c, r3 @ Restore FIQ state - mov pc, lr + ret lr /* * flush_icache_all() @@ -121,7 +121,7 @@ ENTRY(cpu_arm926_do_idle) ENTRY(arm926_flush_icache_all) mov r0, #0 mcr p15, 0, r0, c7, c5, 0 @ invalidate I cache - mov pc, lr + ret lr ENDPROC(arm926_flush_icache_all) /* @@ -151,7 +151,7 @@ __flush_whole_cache: tst r2, #VM_EXEC mcrne p15, 0, ip, c7, c5, 0 @ invalidate I cache mcrne p15, 0, ip, c7, c10, 4 @ drain WB - mov pc, lr + ret lr /* * flush_user_cache_range(start, end, flags) @@ -188,7 +188,7 @@ ENTRY(arm926_flush_user_cache_range) blo 1b tst r2, #VM_EXEC mcrne p15, 0, ip, c7, c10, 4 @ drain WB - mov pc, lr + ret lr /* * coherent_kern_range(start, end) @@ -222,7 +222,7 @@ ENTRY(arm926_coherent_user_range) blo 1b mcr p15, 0, r0, c7, c10, 4 @ drain WB mov r0, #0 - mov pc, lr + ret lr /* * flush_kern_dcache_area(void *addr, size_t size) @@ -242,7 +242,7 @@ ENTRY(arm926_flush_kern_dcache_area) mov r0, #0 mcr p15, 0, r0, c7, c5, 0 @ invalidate I cache mcr p15, 0, r0, c7, c10, 4 @ drain WB - mov pc, lr + ret lr /* * dma_inv_range(start, end) @@ -270,7 +270,7 @@ arm926_dma_inv_range: cmp r0, r1 blo 1b mcr p15, 0, r0, c7, c10, 4 @ drain WB - mov pc, lr + ret lr /* * dma_clean_range(start, end) @@ -291,7 +291,7 @@ arm926_dma_clean_range: blo 1b #endif mcr p15, 0, r0, c7, c10, 4 @ drain WB - mov pc, lr + ret lr /* * dma_flush_range(start, end) @@ -313,7 +313,7 @@ ENTRY(arm926_dma_flush_range) cmp r0, r1 blo 1b mcr p15, 0, r0, c7, c10, 4 @ drain WB - mov pc, lr + ret lr /* * dma_map_area(start, size, dir) @@ -336,7 +336,7 @@ ENDPROC(arm926_dma_map_area) * - dir - DMA direction */ ENTRY(arm926_dma_unmap_area) - mov pc, lr + ret lr ENDPROC(arm926_dma_unmap_area) .globl arm926_flush_kern_cache_louis @@ -353,7 +353,7 @@ ENTRY(cpu_arm926_dcache_clean_area) bhi 1b #endif mcr p15, 0, r0, c7, c10, 4 @ drain WB - mov pc, lr + ret lr /* =============================== PageTable ============================== */ @@ -380,7 +380,7 @@ ENTRY(cpu_arm926_switch_mm) mcr p15, 0, r0, c2, c0, 0 @ load page table pointer mcr p15, 0, ip, c8, c7, 0 @ invalidate I & D TLBs #endif - mov pc, lr + ret lr /* * cpu_arm926_set_pte_ext(ptep, pte, ext) @@ -397,7 +397,7 @@ ENTRY(cpu_arm926_set_pte_ext) #endif mcr p15, 0, r0, c7, c10, 4 @ drain WB #endif - mov pc, lr + ret lr /* Suspend/resume support: taken from arch/arm/plat-s3c24xx/sleep.S */ .globl cpu_arm926_suspend_size @@ -448,7 +448,7 @@ __arm926_setup: #ifdef CONFIG_CPU_CACHE_ROUND_ROBIN orr r0, r0, #0x4000 @ .1.. .... .... .... #endif - mov pc, lr + ret lr .size __arm926_setup, . - __arm926_setup /* diff --git a/arch/arm/mm/proc-arm940.S b/arch/arm/mm/proc-arm940.S index 1c39a704ff6e..e5212d489377 100644 --- a/arch/arm/mm/proc-arm940.S +++ b/arch/arm/mm/proc-arm940.S @@ -31,7 +31,7 @@ */ ENTRY(cpu_arm940_proc_init) ENTRY(cpu_arm940_switch_mm) - mov pc, lr + ret lr /* * cpu_arm940_proc_fin() @@ -41,7 +41,7 @@ ENTRY(cpu_arm940_proc_fin) bic r0, r0, #0x00001000 @ i-cache bic r0, r0, #0x00000004 @ d-cache mcr p15, 0, r0, c1, c0, 0 @ disable caches - mov pc, lr + ret lr /* * cpu_arm940_reset(loc) @@ -58,7 +58,7 @@ ENTRY(cpu_arm940_reset) bic ip, ip, #0x00000005 @ .............c.p bic ip, ip, #0x00001000 @ i-cache mcr p15, 0, ip, c1, c0, 0 @ ctrl register - mov pc, r0 + ret r0 ENDPROC(cpu_arm940_reset) .popsection @@ -68,7 +68,7 @@ ENDPROC(cpu_arm940_reset) .align 5 ENTRY(cpu_arm940_do_idle) mcr p15, 0, r0, c7, c0, 4 @ Wait for interrupt - mov pc, lr + ret lr /* * flush_icache_all() @@ -78,7 +78,7 @@ ENTRY(cpu_arm940_do_idle) ENTRY(arm940_flush_icache_all) mov r0, #0 mcr p15, 0, r0, c7, c5, 0 @ invalidate I cache - mov pc, lr + ret lr ENDPROC(arm940_flush_icache_all) /* @@ -122,7 +122,7 @@ ENTRY(arm940_flush_user_cache_range) tst r2, #VM_EXEC mcrne p15, 0, ip, c7, c5, 0 @ invalidate I cache mcrne p15, 0, ip, c7, c10, 4 @ drain WB - mov pc, lr + ret lr /* * coherent_kern_range(start, end) @@ -170,7 +170,7 @@ ENTRY(arm940_flush_kern_dcache_area) bcs 1b @ segments 7 to 0 mcr p15, 0, r0, c7, c5, 0 @ invalidate I cache mcr p15, 0, r0, c7, c10, 4 @ drain WB - mov pc, lr + ret lr /* * dma_inv_range(start, end) @@ -191,7 +191,7 @@ arm940_dma_inv_range: subs r1, r1, #1 << 4 bcs 1b @ segments 7 to 0 mcr p15, 0, ip, c7, c10, 4 @ drain WB - mov pc, lr + ret lr /* * dma_clean_range(start, end) @@ -215,7 +215,7 @@ ENTRY(cpu_arm940_dcache_clean_area) bcs 1b @ segments 7 to 0 #endif mcr p15, 0, ip, c7, c10, 4 @ drain WB - mov pc, lr + ret lr /* * dma_flush_range(start, end) @@ -241,7 +241,7 @@ ENTRY(arm940_dma_flush_range) subs r1, r1, #1 << 4 bcs 1b @ segments 7 to 0 mcr p15, 0, ip, c7, c10, 4 @ drain WB - mov pc, lr + ret lr /* * dma_map_area(start, size, dir) @@ -264,7 +264,7 @@ ENDPROC(arm940_dma_map_area) * - dir - DMA direction */ ENTRY(arm940_dma_unmap_area) - mov pc, lr + ret lr ENDPROC(arm940_dma_unmap_area) .globl arm940_flush_kern_cache_louis @@ -337,7 +337,7 @@ __arm940_setup: orr r0, r0, #0x00001000 @ I-cache orr r0, r0, #0x00000005 @ MPU/D-cache - mov pc, lr + ret lr .size __arm940_setup, . - __arm940_setup diff --git a/arch/arm/mm/proc-arm946.S b/arch/arm/mm/proc-arm946.S index 0289cd905e73..b3dd9b2d0b8e 100644 --- a/arch/arm/mm/proc-arm946.S +++ b/arch/arm/mm/proc-arm946.S @@ -38,7 +38,7 @@ */ ENTRY(cpu_arm946_proc_init) ENTRY(cpu_arm946_switch_mm) - mov pc, lr + ret lr /* * cpu_arm946_proc_fin() @@ -48,7 +48,7 @@ ENTRY(cpu_arm946_proc_fin) bic r0, r0, #0x00001000 @ i-cache bic r0, r0, #0x00000004 @ d-cache mcr p15, 0, r0, c1, c0, 0 @ disable caches - mov pc, lr + ret lr /* * cpu_arm946_reset(loc) @@ -65,7 +65,7 @@ ENTRY(cpu_arm946_reset) bic ip, ip, #0x00000005 @ .............c.p bic ip, ip, #0x00001000 @ i-cache mcr p15, 0, ip, c1, c0, 0 @ ctrl register - mov pc, r0 + ret r0 ENDPROC(cpu_arm946_reset) .popsection @@ -75,7 +75,7 @@ ENDPROC(cpu_arm946_reset) .align 5 ENTRY(cpu_arm946_do_idle) mcr p15, 0, r0, c7, c0, 4 @ Wait for interrupt - mov pc, lr + ret lr /* * flush_icache_all() @@ -85,7 +85,7 @@ ENTRY(cpu_arm946_do_idle) ENTRY(arm946_flush_icache_all) mov r0, #0 mcr p15, 0, r0, c7, c5, 0 @ invalidate I cache - mov pc, lr + ret lr ENDPROC(arm946_flush_icache_all) /* @@ -117,7 +117,7 @@ __flush_whole_cache: tst r2, #VM_EXEC mcrne p15, 0, ip, c7, c5, 0 @ flush I cache mcrne p15, 0, ip, c7, c10, 4 @ drain WB - mov pc, lr + ret lr /* * flush_user_cache_range(start, end, flags) @@ -156,7 +156,7 @@ ENTRY(arm946_flush_user_cache_range) blo 1b tst r2, #VM_EXEC mcrne p15, 0, ip, c7, c10, 4 @ drain WB - mov pc, lr + ret lr /* * coherent_kern_range(start, end) @@ -191,7 +191,7 @@ ENTRY(arm946_coherent_user_range) blo 1b mcr p15, 0, r0, c7, c10, 4 @ drain WB mov r0, #0 - mov pc, lr + ret lr /* * flush_kern_dcache_area(void *addr, size_t size) @@ -212,7 +212,7 @@ ENTRY(arm946_flush_kern_dcache_area) mov r0, #0 mcr p15, 0, r0, c7, c5, 0 @ invalidate I cache mcr p15, 0, r0, c7, c10, 4 @ drain WB - mov pc, lr + ret lr /* * dma_inv_range(start, end) @@ -239,7 +239,7 @@ arm946_dma_inv_range: cmp r0, r1 blo 1b mcr p15, 0, r0, c7, c10, 4 @ drain WB - mov pc, lr + ret lr /* * dma_clean_range(start, end) @@ -260,7 +260,7 @@ arm946_dma_clean_range: blo 1b #endif mcr p15, 0, r0, c7, c10, 4 @ drain WB - mov pc, lr + ret lr /* * dma_flush_range(start, end) @@ -284,7 +284,7 @@ ENTRY(arm946_dma_flush_range) cmp r0, r1 blo 1b mcr p15, 0, r0, c7, c10, 4 @ drain WB - mov pc, lr + ret lr /* * dma_map_area(start, size, dir) @@ -307,7 +307,7 @@ ENDPROC(arm946_dma_map_area) * - dir - DMA direction */ ENTRY(arm946_dma_unmap_area) - mov pc, lr + ret lr ENDPROC(arm946_dma_unmap_area) .globl arm946_flush_kern_cache_louis @@ -324,7 +324,7 @@ ENTRY(cpu_arm946_dcache_clean_area) bhi 1b #endif mcr p15, 0, r0, c7, c10, 4 @ drain WB - mov pc, lr + ret lr .type __arm946_setup, #function __arm946_setup: @@ -392,7 +392,7 @@ __arm946_setup: #ifdef CONFIG_CPU_CACHE_ROUND_ROBIN orr r0, r0, #0x00004000 @ .1.. .... .... .... #endif - mov pc, lr + ret lr .size __arm946_setup, . - __arm946_setup diff --git a/arch/arm/mm/proc-arm9tdmi.S b/arch/arm/mm/proc-arm9tdmi.S index f51197ba754a..8227322bbb8f 100644 --- a/arch/arm/mm/proc-arm9tdmi.S +++ b/arch/arm/mm/proc-arm9tdmi.S @@ -32,13 +32,13 @@ ENTRY(cpu_arm9tdmi_proc_init) ENTRY(cpu_arm9tdmi_do_idle) ENTRY(cpu_arm9tdmi_dcache_clean_area) ENTRY(cpu_arm9tdmi_switch_mm) - mov pc, lr + ret lr /* * cpu_arm9tdmi_proc_fin() */ ENTRY(cpu_arm9tdmi_proc_fin) - mov pc, lr + ret lr /* * Function: cpu_arm9tdmi_reset(loc) @@ -47,13 +47,13 @@ ENTRY(cpu_arm9tdmi_proc_fin) */ .pushsection .idmap.text, "ax" ENTRY(cpu_arm9tdmi_reset) - mov pc, r0 + ret r0 ENDPROC(cpu_arm9tdmi_reset) .popsection .type __arm9tdmi_setup, #function __arm9tdmi_setup: - mov pc, lr + ret lr .size __arm9tdmi_setup, . - __arm9tdmi_setup __INITDATA diff --git a/arch/arm/mm/proc-fa526.S b/arch/arm/mm/proc-fa526.S index 2dfc0f1d3bfd..c494886892ba 100644 --- a/arch/arm/mm/proc-fa526.S +++ b/arch/arm/mm/proc-fa526.S @@ -32,7 +32,7 @@ * cpu_fa526_proc_init() */ ENTRY(cpu_fa526_proc_init) - mov pc, lr + ret lr /* * cpu_fa526_proc_fin() @@ -44,7 +44,7 @@ ENTRY(cpu_fa526_proc_fin) mcr p15, 0, r0, c1, c0, 0 @ disable caches nop nop - mov pc, lr + ret lr /* * cpu_fa526_reset(loc) @@ -72,7 +72,7 @@ ENTRY(cpu_fa526_reset) mcr p15, 0, ip, c1, c0, 0 @ ctrl register nop nop - mov pc, r0 + ret r0 ENDPROC(cpu_fa526_reset) .popsection @@ -81,7 +81,7 @@ ENDPROC(cpu_fa526_reset) */ .align 4 ENTRY(cpu_fa526_do_idle) - mov pc, lr + ret lr ENTRY(cpu_fa526_dcache_clean_area) @@ -90,7 +90,7 @@ ENTRY(cpu_fa526_dcache_clean_area) subs r1, r1, #CACHE_DLINESIZE bhi 1b mcr p15, 0, r0, c7, c10, 4 @ drain WB - mov pc, lr + ret lr /* =============================== PageTable ============================== */ @@ -117,7 +117,7 @@ ENTRY(cpu_fa526_switch_mm) mcr p15, 0, r0, c2, c0, 0 @ load page table pointer mcr p15, 0, ip, c8, c7, 0 @ invalidate UTLB #endif - mov pc, lr + ret lr /* * cpu_fa526_set_pte_ext(ptep, pte, ext) @@ -133,7 +133,7 @@ ENTRY(cpu_fa526_set_pte_ext) mov r0, #0 mcr p15, 0, r0, c7, c10, 4 @ drain WB #endif - mov pc, lr + ret lr .type __fa526_setup, #function __fa526_setup: @@ -162,7 +162,7 @@ __fa526_setup: bic r0, r0, r5 ldr r5, fa526_cr1_set orr r0, r0, r5 - mov pc, lr + ret lr .size __fa526_setup, . - __fa526_setup /* diff --git a/arch/arm/mm/proc-feroceon.S b/arch/arm/mm/proc-feroceon.S index db79b62c92fb..03a1b75f2e16 100644 --- a/arch/arm/mm/proc-feroceon.S +++ b/arch/arm/mm/proc-feroceon.S @@ -69,7 +69,7 @@ ENTRY(cpu_feroceon_proc_init) movne r2, r2, lsr #2 @ turned into # of sets sub r2, r2, #(1 << 5) stmia r1, {r2, r3} - mov pc, lr + ret lr /* * cpu_feroceon_proc_fin() @@ -86,7 +86,7 @@ ENTRY(cpu_feroceon_proc_fin) bic r0, r0, #0x1000 @ ...i............ bic r0, r0, #0x000e @ ............wca. mcr p15, 0, r0, c1, c0, 0 @ disable caches - mov pc, lr + ret lr /* * cpu_feroceon_reset(loc) @@ -110,7 +110,7 @@ ENTRY(cpu_feroceon_reset) bic ip, ip, #0x000f @ ............wcam bic ip, ip, #0x1100 @ ...i...s........ mcr p15, 0, ip, c1, c0, 0 @ ctrl register - mov pc, r0 + ret r0 ENDPROC(cpu_feroceon_reset) .popsection @@ -124,7 +124,7 @@ ENTRY(cpu_feroceon_do_idle) mov r0, #0 mcr p15, 0, r0, c7, c10, 4 @ Drain write buffer mcr p15, 0, r0, c7, c0, 4 @ Wait for interrupt - mov pc, lr + ret lr /* * flush_icache_all() @@ -134,7 +134,7 @@ ENTRY(cpu_feroceon_do_idle) ENTRY(feroceon_flush_icache_all) mov r0, #0 mcr p15, 0, r0, c7, c5, 0 @ invalidate I cache - mov pc, lr + ret lr ENDPROC(feroceon_flush_icache_all) /* @@ -169,7 +169,7 @@ __flush_whole_cache: mov ip, #0 mcrne p15, 0, ip, c7, c5, 0 @ invalidate I cache mcrne p15, 0, ip, c7, c10, 4 @ drain WB - mov pc, lr + ret lr /* * flush_user_cache_range(start, end, flags) @@ -198,7 +198,7 @@ ENTRY(feroceon_flush_user_cache_range) tst r2, #VM_EXEC mov ip, #0 mcrne p15, 0, ip, c7, c10, 4 @ drain WB - mov pc, lr + ret lr /* * coherent_kern_range(start, end) @@ -233,7 +233,7 @@ ENTRY(feroceon_coherent_user_range) blo 1b mcr p15, 0, r0, c7, c10, 4 @ drain WB mov r0, #0 - mov pc, lr + ret lr /* * flush_kern_dcache_area(void *addr, size_t size) @@ -254,7 +254,7 @@ ENTRY(feroceon_flush_kern_dcache_area) mov r0, #0 mcr p15, 0, r0, c7, c5, 0 @ invalidate I cache mcr p15, 0, r0, c7, c10, 4 @ drain WB - mov pc, lr + ret lr .align 5 ENTRY(feroceon_range_flush_kern_dcache_area) @@ -268,7 +268,7 @@ ENTRY(feroceon_range_flush_kern_dcache_area) mov r0, #0 mcr p15, 0, r0, c7, c5, 0 @ invalidate I cache mcr p15, 0, r0, c7, c10, 4 @ drain WB - mov pc, lr + ret lr /* * dma_inv_range(start, end) @@ -295,7 +295,7 @@ feroceon_dma_inv_range: cmp r0, r1 blo 1b mcr p15, 0, r0, c7, c10, 4 @ drain WB - mov pc, lr + ret lr .align 5 feroceon_range_dma_inv_range: @@ -311,7 +311,7 @@ feroceon_range_dma_inv_range: mcr p15, 5, r0, c15, c14, 0 @ D inv range start mcr p15, 5, r1, c15, c14, 1 @ D inv range top msr cpsr_c, r2 @ restore interrupts - mov pc, lr + ret lr /* * dma_clean_range(start, end) @@ -331,7 +331,7 @@ feroceon_dma_clean_range: cmp r0, r1 blo 1b mcr p15, 0, r0, c7, c10, 4 @ drain WB - mov pc, lr + ret lr .align 5 feroceon_range_dma_clean_range: @@ -344,7 +344,7 @@ feroceon_range_dma_clean_range: mcr p15, 5, r1, c15, c13, 1 @ D clean range top msr cpsr_c, r2 @ restore interrupts mcr p15, 0, r0, c7, c10, 4 @ drain WB - mov pc, lr + ret lr /* * dma_flush_range(start, end) @@ -362,7 +362,7 @@ ENTRY(feroceon_dma_flush_range) cmp r0, r1 blo 1b mcr p15, 0, r0, c7, c10, 4 @ drain WB - mov pc, lr + ret lr .align 5 ENTRY(feroceon_range_dma_flush_range) @@ -375,7 +375,7 @@ ENTRY(feroceon_range_dma_flush_range) mcr p15, 5, r1, c15, c15, 1 @ D clean/inv range top msr cpsr_c, r2 @ restore interrupts mcr p15, 0, r0, c7, c10, 4 @ drain WB - mov pc, lr + ret lr /* * dma_map_area(start, size, dir) @@ -412,7 +412,7 @@ ENDPROC(feroceon_range_dma_map_area) * - dir - DMA direction */ ENTRY(feroceon_dma_unmap_area) - mov pc, lr + ret lr ENDPROC(feroceon_dma_unmap_area) .globl feroceon_flush_kern_cache_louis @@ -461,7 +461,7 @@ ENTRY(cpu_feroceon_dcache_clean_area) bhi 1b #endif mcr p15, 0, r0, c7, c10, 4 @ drain WB - mov pc, lr + ret lr /* =============================== PageTable ============================== */ @@ -490,9 +490,9 @@ ENTRY(cpu_feroceon_switch_mm) mcr p15, 0, r0, c2, c0, 0 @ load page table pointer mcr p15, 0, ip, c8, c7, 0 @ invalidate I & D TLBs - mov pc, r2 + ret r2 #else - mov pc, lr + ret lr #endif /* @@ -512,7 +512,7 @@ ENTRY(cpu_feroceon_set_pte_ext) #endif mcr p15, 0, r0, c7, c10, 4 @ drain WB #endif - mov pc, lr + ret lr /* Suspend/resume support: taken from arch/arm/mm/proc-arm926.S */ .globl cpu_feroceon_suspend_size @@ -554,7 +554,7 @@ __feroceon_setup: mrc p15, 0, r0, c1, c0 @ get control register v4 bic r0, r0, r5 orr r0, r0, r6 - mov pc, lr + ret lr .size __feroceon_setup, . - __feroceon_setup /* diff --git a/arch/arm/mm/proc-mohawk.S b/arch/arm/mm/proc-mohawk.S index 40acba595731..53d393455f13 100644 --- a/arch/arm/mm/proc-mohawk.S +++ b/arch/arm/mm/proc-mohawk.S @@ -45,7 +45,7 @@ * cpu_mohawk_proc_init() */ ENTRY(cpu_mohawk_proc_init) - mov pc, lr + ret lr /* * cpu_mohawk_proc_fin() @@ -55,7 +55,7 @@ ENTRY(cpu_mohawk_proc_fin) bic r0, r0, #0x1800 @ ...iz........... bic r0, r0, #0x0006 @ .............ca. mcr p15, 0, r0, c1, c0, 0 @ disable caches - mov pc, lr + ret lr /* * cpu_mohawk_reset(loc) @@ -79,7 +79,7 @@ ENTRY(cpu_mohawk_reset) bic ip, ip, #0x0007 @ .............cam bic ip, ip, #0x1100 @ ...i...s........ mcr p15, 0, ip, c1, c0, 0 @ ctrl register - mov pc, r0 + ret r0 ENDPROC(cpu_mohawk_reset) .popsection @@ -93,7 +93,7 @@ ENTRY(cpu_mohawk_do_idle) mov r0, #0 mcr p15, 0, r0, c7, c10, 4 @ drain write buffer mcr p15, 0, r0, c7, c0, 4 @ wait for interrupt - mov pc, lr + ret lr /* * flush_icache_all() @@ -103,7 +103,7 @@ ENTRY(cpu_mohawk_do_idle) ENTRY(mohawk_flush_icache_all) mov r0, #0 mcr p15, 0, r0, c7, c5, 0 @ invalidate I cache - mov pc, lr + ret lr ENDPROC(mohawk_flush_icache_all) /* @@ -128,7 +128,7 @@ __flush_whole_cache: tst r2, #VM_EXEC mcrne p15, 0, ip, c7, c5, 0 @ invalidate I cache mcrne p15, 0, ip, c7, c10, 0 @ drain write buffer - mov pc, lr + ret lr /* * flush_user_cache_range(start, end, flags) @@ -158,7 +158,7 @@ ENTRY(mohawk_flush_user_cache_range) blo 1b tst r2, #VM_EXEC mcrne p15, 0, ip, c7, c10, 4 @ drain WB - mov pc, lr + ret lr /* * coherent_kern_range(start, end) @@ -194,7 +194,7 @@ ENTRY(mohawk_coherent_user_range) blo 1b mcr p15, 0, r0, c7, c10, 4 @ drain WB mov r0, #0 - mov pc, lr + ret lr /* * flush_kern_dcache_area(void *addr, size_t size) @@ -214,7 +214,7 @@ ENTRY(mohawk_flush_kern_dcache_area) mov r0, #0 mcr p15, 0, r0, c7, c5, 0 @ invalidate I cache mcr p15, 0, r0, c7, c10, 4 @ drain WB - mov pc, lr + ret lr /* * dma_inv_range(start, end) @@ -240,7 +240,7 @@ mohawk_dma_inv_range: cmp r0, r1 blo 1b mcr p15, 0, r0, c7, c10, 4 @ drain WB - mov pc, lr + ret lr /* * dma_clean_range(start, end) @@ -259,7 +259,7 @@ mohawk_dma_clean_range: cmp r0, r1 blo 1b mcr p15, 0, r0, c7, c10, 4 @ drain WB - mov pc, lr + ret lr /* * dma_flush_range(start, end) @@ -277,7 +277,7 @@ ENTRY(mohawk_dma_flush_range) cmp r0, r1 blo 1b mcr p15, 0, r0, c7, c10, 4 @ drain WB - mov pc, lr + ret lr /* * dma_map_area(start, size, dir) @@ -300,7 +300,7 @@ ENDPROC(mohawk_dma_map_area) * - dir - DMA direction */ ENTRY(mohawk_dma_unmap_area) - mov pc, lr + ret lr ENDPROC(mohawk_dma_unmap_area) .globl mohawk_flush_kern_cache_louis @@ -315,7 +315,7 @@ ENTRY(cpu_mohawk_dcache_clean_area) subs r1, r1, #CACHE_DLINESIZE bhi 1b mcr p15, 0, r0, c7, c10, 4 @ drain WB - mov pc, lr + ret lr /* * cpu_mohawk_switch_mm(pgd) @@ -333,7 +333,7 @@ ENTRY(cpu_mohawk_switch_mm) orr r0, r0, #0x18 @ cache the page table in L2 mcr p15, 0, r0, c2, c0, 0 @ load page table pointer mcr p15, 0, ip, c8, c7, 0 @ invalidate I & D TLBs - mov pc, lr + ret lr /* * cpu_mohawk_set_pte_ext(ptep, pte, ext) @@ -346,7 +346,7 @@ ENTRY(cpu_mohawk_set_pte_ext) mov r0, r0 mcr p15, 0, r0, c7, c10, 1 @ clean D entry mcr p15, 0, r0, c7, c10, 4 @ drain WB - mov pc, lr + ret lr .globl cpu_mohawk_suspend_size .equ cpu_mohawk_suspend_size, 4 * 6 @@ -400,7 +400,7 @@ __mohawk_setup: mrc p15, 0, r0, c1, c0 @ get control register bic r0, r0, r5 orr r0, r0, r6 - mov pc, lr + ret lr .size __mohawk_setup, . - __mohawk_setup diff --git a/arch/arm/mm/proc-sa110.S b/arch/arm/mm/proc-sa110.S index c45319c8f1d9..8008a0461cf5 100644 --- a/arch/arm/mm/proc-sa110.S +++ b/arch/arm/mm/proc-sa110.S @@ -38,7 +38,7 @@ ENTRY(cpu_sa110_proc_init) mov r0, #0 mcr p15, 0, r0, c15, c1, 2 @ Enable clock switching - mov pc, lr + ret lr /* * cpu_sa110_proc_fin() @@ -50,7 +50,7 @@ ENTRY(cpu_sa110_proc_fin) bic r0, r0, #0x1000 @ ...i............ bic r0, r0, #0x000e @ ............wca. mcr p15, 0, r0, c1, c0, 0 @ disable caches - mov pc, lr + ret lr /* * cpu_sa110_reset(loc) @@ -74,7 +74,7 @@ ENTRY(cpu_sa110_reset) bic ip, ip, #0x000f @ ............wcam bic ip, ip, #0x1100 @ ...i...s........ mcr p15, 0, ip, c1, c0, 0 @ ctrl register - mov pc, r0 + ret r0 ENDPROC(cpu_sa110_reset) .popsection @@ -103,7 +103,7 @@ ENTRY(cpu_sa110_do_idle) mov r0, r0 @ safety mov r0, r0 @ safety mcr p15, 0, r0, c15, c1, 2 @ enable clock switching - mov pc, lr + ret lr /* ================================= CACHE ================================ */ @@ -121,7 +121,7 @@ ENTRY(cpu_sa110_dcache_clean_area) add r0, r0, #DCACHELINESIZE subs r1, r1, #DCACHELINESIZE bhi 1b - mov pc, lr + ret lr /* =============================== PageTable ============================== */ @@ -141,7 +141,7 @@ ENTRY(cpu_sa110_switch_mm) mcr p15, 0, ip, c8, c7, 0 @ invalidate I & D TLBs ldr pc, [sp], #4 #else - mov pc, lr + ret lr #endif /* @@ -157,7 +157,7 @@ ENTRY(cpu_sa110_set_pte_ext) mcr p15, 0, r0, c7, c10, 1 @ clean D entry mcr p15, 0, r0, c7, c10, 4 @ drain WB #endif - mov pc, lr + ret lr .type __sa110_setup, #function __sa110_setup: @@ -173,7 +173,7 @@ __sa110_setup: mrc p15, 0, r0, c1, c0 @ get control register v4 bic r0, r0, r5 orr r0, r0, r6 - mov pc, lr + ret lr .size __sa110_setup, . - __sa110_setup /* diff --git a/arch/arm/mm/proc-sa1100.S b/arch/arm/mm/proc-sa1100.S index 09d241ae2dbe..89f97ac648a9 100644 --- a/arch/arm/mm/proc-sa1100.S +++ b/arch/arm/mm/proc-sa1100.S @@ -43,7 +43,7 @@ ENTRY(cpu_sa1100_proc_init) mov r0, #0 mcr p15, 0, r0, c15, c1, 2 @ Enable clock switching mcr p15, 0, r0, c9, c0, 5 @ Allow read-buffer operations from userland - mov pc, lr + ret lr /* * cpu_sa1100_proc_fin() @@ -58,7 +58,7 @@ ENTRY(cpu_sa1100_proc_fin) bic r0, r0, #0x1000 @ ...i............ bic r0, r0, #0x000e @ ............wca. mcr p15, 0, r0, c1, c0, 0 @ disable caches - mov pc, lr + ret lr /* * cpu_sa1100_reset(loc) @@ -82,7 +82,7 @@ ENTRY(cpu_sa1100_reset) bic ip, ip, #0x000f @ ............wcam bic ip, ip, #0x1100 @ ...i...s........ mcr p15, 0, ip, c1, c0, 0 @ ctrl register - mov pc, r0 + ret r0 ENDPROC(cpu_sa1100_reset) .popsection @@ -113,7 +113,7 @@ ENTRY(cpu_sa1100_do_idle) mcr p15, 0, r0, c15, c8, 2 @ wait for interrupt mov r0, r0 @ safety mcr p15, 0, r0, c15, c1, 2 @ enable clock switching - mov pc, lr + ret lr /* ================================= CACHE ================================ */ @@ -131,7 +131,7 @@ ENTRY(cpu_sa1100_dcache_clean_area) add r0, r0, #DCACHELINESIZE subs r1, r1, #DCACHELINESIZE bhi 1b - mov pc, lr + ret lr /* =============================== PageTable ============================== */ @@ -152,7 +152,7 @@ ENTRY(cpu_sa1100_switch_mm) mcr p15, 0, ip, c8, c7, 0 @ invalidate I & D TLBs ldr pc, [sp], #4 #else - mov pc, lr + ret lr #endif /* @@ -168,7 +168,7 @@ ENTRY(cpu_sa1100_set_pte_ext) mcr p15, 0, r0, c7, c10, 1 @ clean D entry mcr p15, 0, r0, c7, c10, 4 @ drain WB #endif - mov pc, lr + ret lr .globl cpu_sa1100_suspend_size .equ cpu_sa1100_suspend_size, 4 * 3 @@ -211,7 +211,7 @@ __sa1100_setup: mrc p15, 0, r0, c1, c0 @ get control register v4 bic r0, r0, r5 orr r0, r0, r6 - mov pc, lr + ret lr .size __sa1100_setup, . - __sa1100_setup /* diff --git a/arch/arm/mm/proc-v6.S b/arch/arm/mm/proc-v6.S index 32b3558321c4..d0390f4b3f18 100644 --- a/arch/arm/mm/proc-v6.S +++ b/arch/arm/mm/proc-v6.S @@ -36,14 +36,14 @@ #define PMD_FLAGS_SMP PMD_SECT_WBWA|PMD_SECT_S ENTRY(cpu_v6_proc_init) - mov pc, lr + ret lr ENTRY(cpu_v6_proc_fin) mrc p15, 0, r0, c1, c0, 0 @ ctrl register bic r0, r0, #0x1000 @ ...i............ bic r0, r0, #0x0006 @ .............ca. mcr p15, 0, r0, c1, c0, 0 @ disable caches - mov pc, lr + ret lr /* * cpu_v6_reset(loc) @@ -62,7 +62,7 @@ ENTRY(cpu_v6_reset) mcr p15, 0, r1, c1, c0, 0 @ disable MMU mov r1, #0 mcr p15, 0, r1, c7, c5, 4 @ ISB - mov pc, r0 + ret r0 ENDPROC(cpu_v6_reset) .popsection @@ -77,14 +77,14 @@ ENTRY(cpu_v6_do_idle) mov r1, #0 mcr p15, 0, r1, c7, c10, 4 @ DWB - WFI may enter a low-power mode mcr p15, 0, r1, c7, c0, 4 @ wait for interrupt - mov pc, lr + ret lr ENTRY(cpu_v6_dcache_clean_area) 1: mcr p15, 0, r0, c7, c10, 1 @ clean D entry add r0, r0, #D_CACHE_LINE_SIZE subs r1, r1, #D_CACHE_LINE_SIZE bhi 1b - mov pc, lr + ret lr /* * cpu_v6_switch_mm(pgd_phys, tsk) @@ -113,7 +113,7 @@ ENTRY(cpu_v6_switch_mm) #endif mcr p15, 0, r1, c13, c0, 1 @ set context ID #endif - mov pc, lr + ret lr /* * cpu_v6_set_pte_ext(ptep, pte, ext) @@ -131,7 +131,7 @@ ENTRY(cpu_v6_set_pte_ext) #ifdef CONFIG_MMU armv6_set_pte_ext cpu_v6 #endif - mov pc, lr + ret lr /* Suspend/resume support: taken from arch/arm/mach-s3c64xx/sleep.S */ .globl cpu_v6_suspend_size @@ -241,7 +241,7 @@ __v6_setup: mcreq p15, 0, r5, c1, c0, 1 @ write aux control reg orreq r0, r0, #(1 << 21) @ low interrupt latency configuration #endif - mov pc, lr @ return to head.S:__ret + ret lr @ return to head.S:__ret /* * V X F I D LR diff --git a/arch/arm/mm/proc-v7-2level.S b/arch/arm/mm/proc-v7-2level.S index 1f52915f2b28..ed448d8a596b 100644 --- a/arch/arm/mm/proc-v7-2level.S +++ b/arch/arm/mm/proc-v7-2level.S @@ -59,7 +59,7 @@ ENTRY(cpu_v7_switch_mm) mcr p15, 0, r0, c2, c0, 0 @ set TTB 0 isb #endif - mov pc, lr + bx lr ENDPROC(cpu_v7_switch_mm) /* @@ -106,7 +106,7 @@ ENTRY(cpu_v7_set_pte_ext) ALT_SMP(W(nop)) ALT_UP (mcr p15, 0, r0, c7, c10, 1) @ flush_pte #endif - mov pc, lr + bx lr ENDPROC(cpu_v7_set_pte_ext) /* diff --git a/arch/arm/mm/proc-v7-3level.S b/arch/arm/mm/proc-v7-3level.S index 01a719e18bb0..e4c8acfc1323 100644 --- a/arch/arm/mm/proc-v7-3level.S +++ b/arch/arm/mm/proc-v7-3level.S @@ -19,6 +19,7 @@ * along with this program; if not, write to the Free Software * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ +#include <asm/assembler.h> #define TTB_IRGN_NC (0 << 8) #define TTB_IRGN_WBWA (1 << 8) @@ -61,9 +62,17 @@ ENTRY(cpu_v7_switch_mm) mcrr p15, 0, rpgdl, rpgdh, c2 @ set TTB 0 isb #endif - mov pc, lr + ret lr ENDPROC(cpu_v7_switch_mm) +#ifdef __ARMEB__ +#define rl r3 +#define rh r2 +#else +#define rl r2 +#define rh r3 +#endif + /* * cpu_v7_set_pte_ext(ptep, pte) * @@ -73,18 +82,23 @@ ENDPROC(cpu_v7_switch_mm) */ ENTRY(cpu_v7_set_pte_ext) #ifdef CONFIG_MMU - tst r2, #L_PTE_VALID + tst rl, #L_PTE_VALID beq 1f - tst r3, #1 << (57 - 32) @ L_PTE_NONE - bicne r2, #L_PTE_VALID + tst rh, #1 << (57 - 32) @ L_PTE_NONE + bicne rl, #L_PTE_VALID bne 1f - tst r3, #1 << (55 - 32) @ L_PTE_DIRTY - orreq r2, #L_PTE_RDONLY + + eor ip, rh, #1 << (55 - 32) @ toggle L_PTE_DIRTY in temp reg to + @ test for !L_PTE_DIRTY || L_PTE_RDONLY + tst ip, #1 << (55 - 32) | 1 << (58 - 32) + orrne rl, #PTE_AP2 + biceq rl, #PTE_AP2 + 1: strd r2, r3, [r0] ALT_SMP(W(nop)) ALT_UP (mcr p15, 0, r0, c7, c10, 1) @ flush_pte #endif - mov pc, lr + ret lr ENDPROC(cpu_v7_set_pte_ext) /* diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S index 195731d3813b..b5d67db20897 100644 --- a/arch/arm/mm/proc-v7.S +++ b/arch/arm/mm/proc-v7.S @@ -26,7 +26,7 @@ #endif ENTRY(cpu_v7_proc_init) - mov pc, lr + ret lr ENDPROC(cpu_v7_proc_init) ENTRY(cpu_v7_proc_fin) @@ -34,7 +34,7 @@ ENTRY(cpu_v7_proc_fin) bic r0, r0, #0x1000 @ ...i............ bic r0, r0, #0x0006 @ .............ca. mcr p15, 0, r0, c1, c0, 0 @ disable caches - mov pc, lr + ret lr ENDPROC(cpu_v7_proc_fin) /* @@ -71,20 +71,20 @@ ENDPROC(cpu_v7_reset) ENTRY(cpu_v7_do_idle) dsb @ WFI may enter a low-power mode wfi - mov pc, lr + ret lr ENDPROC(cpu_v7_do_idle) ENTRY(cpu_v7_dcache_clean_area) ALT_SMP(W(nop)) @ MP extensions imply L1 PTW ALT_UP_B(1f) - mov pc, lr + ret lr 1: dcache_line_size r2, r3 2: mcr p15, 0, r0, c7, c10, 1 @ clean D entry add r0, r0, r2 subs r1, r1, r2 bhi 2b dsb ishst - mov pc, lr + ret lr ENDPROC(cpu_v7_dcache_clean_area) string cpu_v7_name, "ARMv7 Processor" @@ -152,6 +152,40 @@ ENTRY(cpu_v7_do_resume) ENDPROC(cpu_v7_do_resume) #endif +/* + * Cortex-A9 processor functions + */ + globl_equ cpu_ca9mp_proc_init, cpu_v7_proc_init + globl_equ cpu_ca9mp_proc_fin, cpu_v7_proc_fin + globl_equ cpu_ca9mp_reset, cpu_v7_reset + globl_equ cpu_ca9mp_do_idle, cpu_v7_do_idle + globl_equ cpu_ca9mp_dcache_clean_area, cpu_v7_dcache_clean_area + globl_equ cpu_ca9mp_switch_mm, cpu_v7_switch_mm + globl_equ cpu_ca9mp_set_pte_ext, cpu_v7_set_pte_ext +.globl cpu_ca9mp_suspend_size +.equ cpu_ca9mp_suspend_size, cpu_v7_suspend_size + 4 * 2 +#ifdef CONFIG_ARM_CPU_SUSPEND +ENTRY(cpu_ca9mp_do_suspend) + stmfd sp!, {r4 - r5} + mrc p15, 0, r4, c15, c0, 1 @ Diagnostic register + mrc p15, 0, r5, c15, c0, 0 @ Power register + stmia r0!, {r4 - r5} + ldmfd sp!, {r4 - r5} + b cpu_v7_do_suspend +ENDPROC(cpu_ca9mp_do_suspend) + +ENTRY(cpu_ca9mp_do_resume) + ldmia r0!, {r4 - r5} + mrc p15, 0, r10, c15, c0, 1 @ Read Diagnostic register + teq r4, r10 @ Already restored? + mcrne p15, 0, r4, c15, c0, 1 @ No, so restore it + mrc p15, 0, r10, c15, c0, 0 @ Read Power register + teq r5, r10 @ Already restored? + mcrne p15, 0, r5, c15, c0, 0 @ No, so restore it + b cpu_v7_do_resume +ENDPROC(cpu_ca9mp_do_resume) +#endif + #ifdef CONFIG_CPU_PJ4B globl_equ cpu_pj4b_switch_mm, cpu_v7_switch_mm globl_equ cpu_pj4b_set_pte_ext, cpu_v7_set_pte_ext @@ -163,15 +197,37 @@ ENTRY(cpu_pj4b_do_idle) dsb @ WFI may enter a low-power mode wfi dsb @barrier - mov pc, lr + ret lr ENDPROC(cpu_pj4b_do_idle) #else globl_equ cpu_pj4b_do_idle, cpu_v7_do_idle #endif globl_equ cpu_pj4b_dcache_clean_area, cpu_v7_dcache_clean_area - globl_equ cpu_pj4b_do_suspend, cpu_v7_do_suspend - globl_equ cpu_pj4b_do_resume, cpu_v7_do_resume - globl_equ cpu_pj4b_suspend_size, cpu_v7_suspend_size +#ifdef CONFIG_ARM_CPU_SUSPEND +ENTRY(cpu_pj4b_do_suspend) + stmfd sp!, {r6 - r10} + mrc p15, 1, r6, c15, c1, 0 @ save CP15 - extra features + mrc p15, 1, r7, c15, c2, 0 @ save CP15 - Aux Func Modes Ctrl 0 + mrc p15, 1, r8, c15, c1, 2 @ save CP15 - Aux Debug Modes Ctrl 2 + mrc p15, 1, r9, c15, c1, 1 @ save CP15 - Aux Debug Modes Ctrl 1 + mrc p15, 0, r10, c9, c14, 0 @ save CP15 - PMC + stmia r0!, {r6 - r10} + ldmfd sp!, {r6 - r10} + b cpu_v7_do_suspend +ENDPROC(cpu_pj4b_do_suspend) + +ENTRY(cpu_pj4b_do_resume) + ldmia r0!, {r6 - r10} + mcr p15, 1, r6, c15, c1, 0 @ restore CP15 - extra features + mcr p15, 1, r7, c15, c2, 0 @ restore CP15 - Aux Func Modes Ctrl 0 + mcr p15, 1, r8, c15, c1, 2 @ restore CP15 - Aux Debug Modes Ctrl 2 + mcr p15, 1, r9, c15, c1, 1 @ restore CP15 - Aux Debug Modes Ctrl 1 + mcr p15, 0, r10, c9, c14, 0 @ restore CP15 - PMC + b cpu_v7_do_resume +ENDPROC(cpu_pj4b_do_resume) +#endif +.globl cpu_pj4b_suspend_size +.equ cpu_pj4b_suspend_size, cpu_v7_suspend_size + 4 * 5 #endif @@ -194,6 +250,8 @@ __v7_cr7mp_setup: __v7_ca7mp_setup: __v7_ca12mp_setup: __v7_ca15mp_setup: +__v7_b15mp_setup: +__v7_ca17mp_setup: mov r10, #0 1: #ifdef CONFIG_SMP @@ -384,7 +442,7 @@ __v7_setup: bic r0, r0, r5 @ clear bits them orr r0, r0, r6 @ set them THUMB( orr r0, r0, #1 << 30 ) @ Thumb exceptions - mov pc, lr @ return to head.S:__ret + ret lr @ return to head.S:__ret ENDPROC(__v7_setup) .align 2 @@ -395,6 +453,7 @@ __v7_setup_stack: @ define struct processor (see <asm/proc-fns.h> and proc-macros.S) define_processor_functions v7, dabort=v7_early_abort, pabort=v7_pabort, suspend=1 + define_processor_functions ca9mp, dabort=v7_early_abort, pabort=v7_pabort, suspend=1 #ifdef CONFIG_CPU_PJ4B define_processor_functions pj4b, dabort=v7_early_abort, pabort=v7_pabort, suspend=1 #endif @@ -447,7 +506,7 @@ __v7_ca5mp_proc_info: __v7_ca9mp_proc_info: .long 0x410fc090 .long 0xff0ffff0 - __v7_proc __v7_ca9mp_setup + __v7_proc __v7_ca9mp_setup, proc_fns = ca9mp_processor_functions .size __v7_ca9mp_proc_info, . - __v7_ca9mp_proc_info #endif /* CONFIG_ARM_LPAE */ @@ -505,6 +564,26 @@ __v7_ca15mp_proc_info: .size __v7_ca15mp_proc_info, . - __v7_ca15mp_proc_info /* + * Broadcom Corporation Brahma-B15 processor. + */ + .type __v7_b15mp_proc_info, #object +__v7_b15mp_proc_info: + .long 0x420f00f0 + .long 0xff0ffff0 + __v7_proc __v7_b15mp_setup, hwcaps = HWCAP_IDIV + .size __v7_b15mp_proc_info, . - __v7_b15mp_proc_info + + /* + * ARM Ltd. Cortex A17 processor. + */ + .type __v7_ca17mp_proc_info, #object +__v7_ca17mp_proc_info: + .long 0x410fc0e0 + .long 0xff0ffff0 + __v7_proc __v7_ca17mp_setup + .size __v7_ca17mp_proc_info, . - __v7_ca17mp_proc_info + + /* * Qualcomm Inc. Krait processors. */ .type __krait_proc_info, #object diff --git a/arch/arm/mm/proc-v7m.S b/arch/arm/mm/proc-v7m.S index 0c93588fcb91..d1e68b553d3b 100644 --- a/arch/arm/mm/proc-v7m.S +++ b/arch/arm/mm/proc-v7m.S @@ -16,11 +16,11 @@ #include "proc-macros.S" ENTRY(cpu_v7m_proc_init) - mov pc, lr + ret lr ENDPROC(cpu_v7m_proc_init) ENTRY(cpu_v7m_proc_fin) - mov pc, lr + ret lr ENDPROC(cpu_v7m_proc_fin) /* @@ -34,7 +34,7 @@ ENDPROC(cpu_v7m_proc_fin) */ .align 5 ENTRY(cpu_v7m_reset) - mov pc, r0 + ret r0 ENDPROC(cpu_v7m_reset) /* @@ -46,18 +46,18 @@ ENDPROC(cpu_v7m_reset) */ ENTRY(cpu_v7m_do_idle) wfi - mov pc, lr + ret lr ENDPROC(cpu_v7m_do_idle) ENTRY(cpu_v7m_dcache_clean_area) - mov pc, lr + ret lr ENDPROC(cpu_v7m_dcache_clean_area) /* * There is no MMU, so here is nothing to do. */ ENTRY(cpu_v7m_switch_mm) - mov pc, lr + ret lr ENDPROC(cpu_v7m_switch_mm) .globl cpu_v7m_suspend_size @@ -65,11 +65,11 @@ ENDPROC(cpu_v7m_switch_mm) #ifdef CONFIG_ARM_CPU_SUSPEND ENTRY(cpu_v7m_do_suspend) - mov pc, lr + ret lr ENDPROC(cpu_v7m_do_suspend) ENTRY(cpu_v7m_do_resume) - mov pc, lr + ret lr ENDPROC(cpu_v7m_do_resume) #endif @@ -120,9 +120,14 @@ __v7m_setup: ldr r12, [r0, V7M_SCB_CCR] @ system control register orr r12, #V7M_SCB_CCR_STKALIGN str r12, [r0, V7M_SCB_CCR] - mov pc, lr + ret lr ENDPROC(__v7m_setup) + .align 2 +__v7m_setup_stack: + .space 4 * 8 @ 8 registers +__v7m_setup_stack_top: + define_processor_functions v7m, dabort=nommu_early_abort, pabort=legacy_pabort, nommu=1 .section ".rodata" @@ -152,6 +157,3 @@ __v7m_proc_info: .long nop_cache_fns @ proc_info_list.cache .size __v7m_proc_info, . - __v7m_proc_info -__v7m_setup_stack: - .space 4 * 8 @ 8 registers -__v7m_setup_stack_top: diff --git a/arch/arm/mm/proc-xsc3.S b/arch/arm/mm/proc-xsc3.S index dc1645890042..f8acdfece036 100644 --- a/arch/arm/mm/proc-xsc3.S +++ b/arch/arm/mm/proc-xsc3.S @@ -83,7 +83,7 @@ * Nothing too exciting at the moment */ ENTRY(cpu_xsc3_proc_init) - mov pc, lr + ret lr /* * cpu_xsc3_proc_fin() @@ -93,7 +93,7 @@ ENTRY(cpu_xsc3_proc_fin) bic r0, r0, #0x1800 @ ...IZ........... bic r0, r0, #0x0006 @ .............CA. mcr p15, 0, r0, c1, c0, 0 @ disable caches - mov pc, lr + ret lr /* * cpu_xsc3_reset(loc) @@ -119,7 +119,7 @@ ENTRY(cpu_xsc3_reset) @ CAUTION: MMU turned off from this point. We count on the pipeline @ already containing those two last instructions to survive. mcr p15, 0, ip, c8, c7, 0 @ invalidate I and D TLBs - mov pc, r0 + ret r0 ENDPROC(cpu_xsc3_reset) .popsection @@ -138,7 +138,7 @@ ENDPROC(cpu_xsc3_reset) ENTRY(cpu_xsc3_do_idle) mov r0, #1 mcr p14, 0, r0, c7, c0, 0 @ go to idle - mov pc, lr + ret lr /* ================================= CACHE ================================ */ @@ -150,7 +150,7 @@ ENTRY(cpu_xsc3_do_idle) ENTRY(xsc3_flush_icache_all) mov r0, #0 mcr p15, 0, r0, c7, c5, 0 @ invalidate I cache - mov pc, lr + ret lr ENDPROC(xsc3_flush_icache_all) /* @@ -176,7 +176,7 @@ __flush_whole_cache: mcrne p15, 0, ip, c7, c5, 0 @ invalidate L1 I cache and BTB mcrne p15, 0, ip, c7, c10, 4 @ data write barrier mcrne p15, 0, ip, c7, c5, 4 @ prefetch flush - mov pc, lr + ret lr /* * flush_user_cache_range(start, end, vm_flags) @@ -205,7 +205,7 @@ ENTRY(xsc3_flush_user_cache_range) mcrne p15, 0, ip, c7, c5, 6 @ invalidate BTB mcrne p15, 0, ip, c7, c10, 4 @ data write barrier mcrne p15, 0, ip, c7, c5, 4 @ prefetch flush - mov pc, lr + ret lr /* * coherent_kern_range(start, end) @@ -232,7 +232,7 @@ ENTRY(xsc3_coherent_user_range) mcr p15, 0, r0, c7, c5, 0 @ invalidate L1 I cache and BTB mcr p15, 0, r0, c7, c10, 4 @ data write barrier mcr p15, 0, r0, c7, c5, 4 @ prefetch flush - mov pc, lr + ret lr /* * flush_kern_dcache_area(void *addr, size_t size) @@ -253,7 +253,7 @@ ENTRY(xsc3_flush_kern_dcache_area) mcr p15, 0, r0, c7, c5, 0 @ invalidate L1 I cache and BTB mcr p15, 0, r0, c7, c10, 4 @ data write barrier mcr p15, 0, r0, c7, c5, 4 @ prefetch flush - mov pc, lr + ret lr /* * dma_inv_range(start, end) @@ -277,7 +277,7 @@ xsc3_dma_inv_range: cmp r0, r1 blo 1b mcr p15, 0, r0, c7, c10, 4 @ data write barrier - mov pc, lr + ret lr /* * dma_clean_range(start, end) @@ -294,7 +294,7 @@ xsc3_dma_clean_range: cmp r0, r1 blo 1b mcr p15, 0, r0, c7, c10, 4 @ data write barrier - mov pc, lr + ret lr /* * dma_flush_range(start, end) @@ -311,7 +311,7 @@ ENTRY(xsc3_dma_flush_range) cmp r0, r1 blo 1b mcr p15, 0, r0, c7, c10, 4 @ data write barrier - mov pc, lr + ret lr /* * dma_map_area(start, size, dir) @@ -334,7 +334,7 @@ ENDPROC(xsc3_dma_map_area) * - dir - DMA direction */ ENTRY(xsc3_dma_unmap_area) - mov pc, lr + ret lr ENDPROC(xsc3_dma_unmap_area) .globl xsc3_flush_kern_cache_louis @@ -348,7 +348,7 @@ ENTRY(cpu_xsc3_dcache_clean_area) add r0, r0, #CACHELINESIZE subs r1, r1, #CACHELINESIZE bhi 1b - mov pc, lr + ret lr /* =============================== PageTable ============================== */ @@ -406,7 +406,7 @@ ENTRY(cpu_xsc3_set_pte_ext) orr r2, r2, ip xscale_set_pte_ext_epilogue - mov pc, lr + ret lr .ltorg .align @@ -478,7 +478,7 @@ __xsc3_setup: bic r0, r0, r5 @ ..V. ..R. .... ..A. orr r0, r0, r6 @ ..VI Z..S .... .C.M (mmu) @ ...I Z..S .... .... (uc) - mov pc, lr + ret lr .size __xsc3_setup, . - __xsc3_setup diff --git a/arch/arm/mm/proc-xscale.S b/arch/arm/mm/proc-xscale.S index d19b1cfcad91..23259f104c66 100644 --- a/arch/arm/mm/proc-xscale.S +++ b/arch/arm/mm/proc-xscale.S @@ -118,7 +118,7 @@ ENTRY(cpu_xscale_proc_init) mrc p15, 0, r1, c1, c0, 1 bic r1, r1, #1 mcr p15, 0, r1, c1, c0, 1 - mov pc, lr + ret lr /* * cpu_xscale_proc_fin() @@ -128,7 +128,7 @@ ENTRY(cpu_xscale_proc_fin) bic r0, r0, #0x1800 @ ...IZ........... bic r0, r0, #0x0006 @ .............CA. mcr p15, 0, r0, c1, c0, 0 @ disable caches - mov pc, lr + ret lr /* * cpu_xscale_reset(loc) @@ -160,7 +160,7 @@ ENTRY(cpu_xscale_reset) @ CAUTION: MMU turned off from this point. We count on the pipeline @ already containing those two last instructions to survive. mcr p15, 0, ip, c8, c7, 0 @ invalidate I & D TLBs - mov pc, r0 + ret r0 ENDPROC(cpu_xscale_reset) .popsection @@ -179,7 +179,7 @@ ENDPROC(cpu_xscale_reset) ENTRY(cpu_xscale_do_idle) mov r0, #1 mcr p14, 0, r0, c7, c0, 0 @ Go to IDLE - mov pc, lr + ret lr /* ================================= CACHE ================================ */ @@ -191,7 +191,7 @@ ENTRY(cpu_xscale_do_idle) ENTRY(xscale_flush_icache_all) mov r0, #0 mcr p15, 0, r0, c7, c5, 0 @ invalidate I cache - mov pc, lr + ret lr ENDPROC(xscale_flush_icache_all) /* @@ -216,7 +216,7 @@ __flush_whole_cache: tst r2, #VM_EXEC mcrne p15, 0, ip, c7, c5, 0 @ Invalidate I cache & BTB mcrne p15, 0, ip, c7, c10, 4 @ Drain Write (& Fill) Buffer - mov pc, lr + ret lr /* * flush_user_cache_range(start, end, vm_flags) @@ -245,7 +245,7 @@ ENTRY(xscale_flush_user_cache_range) tst r2, #VM_EXEC mcrne p15, 0, ip, c7, c5, 6 @ Invalidate BTB mcrne p15, 0, ip, c7, c10, 4 @ Drain Write (& Fill) Buffer - mov pc, lr + ret lr /* * coherent_kern_range(start, end) @@ -269,7 +269,7 @@ ENTRY(xscale_coherent_kern_range) mov r0, #0 mcr p15, 0, r0, c7, c5, 0 @ Invalidate I cache & BTB mcr p15, 0, r0, c7, c10, 4 @ Drain Write (& Fill) Buffer - mov pc, lr + ret lr /* * coherent_user_range(start, end) @@ -291,7 +291,7 @@ ENTRY(xscale_coherent_user_range) mov r0, #0 mcr p15, 0, r0, c7, c5, 6 @ Invalidate BTB mcr p15, 0, r0, c7, c10, 4 @ Drain Write (& Fill) Buffer - mov pc, lr + ret lr /* * flush_kern_dcache_area(void *addr, size_t size) @@ -312,7 +312,7 @@ ENTRY(xscale_flush_kern_dcache_area) mov r0, #0 mcr p15, 0, r0, c7, c5, 0 @ Invalidate I cache & BTB mcr p15, 0, r0, c7, c10, 4 @ Drain Write (& Fill) Buffer - mov pc, lr + ret lr /* * dma_inv_range(start, end) @@ -336,7 +336,7 @@ xscale_dma_inv_range: cmp r0, r1 blo 1b mcr p15, 0, r0, c7, c10, 4 @ Drain Write (& Fill) Buffer - mov pc, lr + ret lr /* * dma_clean_range(start, end) @@ -353,7 +353,7 @@ xscale_dma_clean_range: cmp r0, r1 blo 1b mcr p15, 0, r0, c7, c10, 4 @ Drain Write (& Fill) Buffer - mov pc, lr + ret lr /* * dma_flush_range(start, end) @@ -371,7 +371,7 @@ ENTRY(xscale_dma_flush_range) cmp r0, r1 blo 1b mcr p15, 0, r0, c7, c10, 4 @ Drain Write (& Fill) Buffer - mov pc, lr + ret lr /* * dma_map_area(start, size, dir) @@ -407,7 +407,7 @@ ENDPROC(xscale_80200_A0_A1_dma_map_area) * - dir - DMA direction */ ENTRY(xscale_dma_unmap_area) - mov pc, lr + ret lr ENDPROC(xscale_dma_unmap_area) .globl xscale_flush_kern_cache_louis @@ -458,7 +458,7 @@ ENTRY(cpu_xscale_dcache_clean_area) add r0, r0, #CACHELINESIZE subs r1, r1, #CACHELINESIZE bhi 1b - mov pc, lr + ret lr /* =============================== PageTable ============================== */ @@ -521,7 +521,7 @@ ENTRY(cpu_xscale_set_pte_ext) orr r2, r2, ip xscale_set_pte_ext_epilogue - mov pc, lr + ret lr .ltorg .align @@ -572,7 +572,7 @@ __xscale_setup: mrc p15, 0, r0, c1, c0, 0 @ get control register bic r0, r0, r5 orr r0, r0, r6 - mov pc, lr + ret lr .size __xscale_setup, . - __xscale_setup /* diff --git a/arch/arm/mm/tlb-fa.S b/arch/arm/mm/tlb-fa.S index d3ddcf9a76ca..d2d9ecbe0aac 100644 --- a/arch/arm/mm/tlb-fa.S +++ b/arch/arm/mm/tlb-fa.S @@ -18,6 +18,7 @@ */ #include <linux/linkage.h> #include <linux/init.h> +#include <asm/assembler.h> #include <asm/asm-offsets.h> #include <asm/tlbflush.h> #include "proc-macros.S" @@ -37,7 +38,7 @@ ENTRY(fa_flush_user_tlb_range) vma_vm_mm ip, r2 act_mm r3 @ get current->active_mm eors r3, ip, r3 @ == mm ? - movne pc, lr @ no, we dont do anything + retne lr @ no, we dont do anything mov r3, #0 mcr p15, 0, r3, c7, c10, 4 @ drain WB bic r0, r0, #0x0ff @@ -47,7 +48,7 @@ ENTRY(fa_flush_user_tlb_range) cmp r0, r1 blo 1b mcr p15, 0, r3, c7, c10, 4 @ data write barrier - mov pc, lr + ret lr ENTRY(fa_flush_kern_tlb_range) @@ -61,7 +62,7 @@ ENTRY(fa_flush_kern_tlb_range) blo 1b mcr p15, 0, r3, c7, c10, 4 @ data write barrier mcr p15, 0, r3, c7, c5, 4 @ prefetch flush (isb) - mov pc, lr + ret lr __INITDATA diff --git a/arch/arm/mm/tlb-v4.S b/arch/arm/mm/tlb-v4.S index 17a025ade573..a2b5dca42048 100644 --- a/arch/arm/mm/tlb-v4.S +++ b/arch/arm/mm/tlb-v4.S @@ -14,6 +14,7 @@ */ #include <linux/linkage.h> #include <linux/init.h> +#include <asm/assembler.h> #include <asm/asm-offsets.h> #include <asm/tlbflush.h> #include "proc-macros.S" @@ -33,7 +34,7 @@ ENTRY(v4_flush_user_tlb_range) vma_vm_mm ip, r2 act_mm r3 @ get current->active_mm eors r3, ip, r3 @ == mm ? - movne pc, lr @ no, we dont do anything + retne lr @ no, we dont do anything .v4_flush_kern_tlb_range: bic r0, r0, #0x0ff bic r0, r0, #0xf00 @@ -41,7 +42,7 @@ ENTRY(v4_flush_user_tlb_range) add r0, r0, #PAGE_SZ cmp r0, r1 blo 1b - mov pc, lr + ret lr /* * v4_flush_kern_tlb_range(start, end) diff --git a/arch/arm/mm/tlb-v4wb.S b/arch/arm/mm/tlb-v4wb.S index c04598fa4d4a..5a093b458dbc 100644 --- a/arch/arm/mm/tlb-v4wb.S +++ b/arch/arm/mm/tlb-v4wb.S @@ -14,6 +14,7 @@ */ #include <linux/linkage.h> #include <linux/init.h> +#include <asm/assembler.h> #include <asm/asm-offsets.h> #include <asm/tlbflush.h> #include "proc-macros.S" @@ -33,7 +34,7 @@ ENTRY(v4wb_flush_user_tlb_range) vma_vm_mm ip, r2 act_mm r3 @ get current->active_mm eors r3, ip, r3 @ == mm ? - movne pc, lr @ no, we dont do anything + retne lr @ no, we dont do anything vma_vm_flags r2, r2 mcr p15, 0, r3, c7, c10, 4 @ drain WB tst r2, #VM_EXEC @@ -44,7 +45,7 @@ ENTRY(v4wb_flush_user_tlb_range) add r0, r0, #PAGE_SZ cmp r0, r1 blo 1b - mov pc, lr + ret lr /* * v4_flush_kern_tlb_range(start, end) @@ -65,7 +66,7 @@ ENTRY(v4wb_flush_kern_tlb_range) add r0, r0, #PAGE_SZ cmp r0, r1 blo 1b - mov pc, lr + ret lr __INITDATA diff --git a/arch/arm/mm/tlb-v4wbi.S b/arch/arm/mm/tlb-v4wbi.S index 1f6062b6c1c1..058861548f68 100644 --- a/arch/arm/mm/tlb-v4wbi.S +++ b/arch/arm/mm/tlb-v4wbi.S @@ -14,6 +14,7 @@ */ #include <linux/linkage.h> #include <linux/init.h> +#include <asm/assembler.h> #include <asm/asm-offsets.h> #include <asm/tlbflush.h> #include "proc-macros.S" @@ -32,7 +33,7 @@ ENTRY(v4wbi_flush_user_tlb_range) vma_vm_mm ip, r2 act_mm r3 @ get current->active_mm eors r3, ip, r3 @ == mm ? - movne pc, lr @ no, we dont do anything + retne lr @ no, we dont do anything mov r3, #0 mcr p15, 0, r3, c7, c10, 4 @ drain WB vma_vm_flags r2, r2 @@ -44,7 +45,7 @@ ENTRY(v4wbi_flush_user_tlb_range) add r0, r0, #PAGE_SZ cmp r0, r1 blo 1b - mov pc, lr + ret lr ENTRY(v4wbi_flush_kern_tlb_range) mov r3, #0 @@ -56,7 +57,7 @@ ENTRY(v4wbi_flush_kern_tlb_range) add r0, r0, #PAGE_SZ cmp r0, r1 blo 1b - mov pc, lr + ret lr __INITDATA diff --git a/arch/arm/mm/tlb-v6.S b/arch/arm/mm/tlb-v6.S index eca07f550a0b..6f689be638bd 100644 --- a/arch/arm/mm/tlb-v6.S +++ b/arch/arm/mm/tlb-v6.S @@ -13,6 +13,7 @@ #include <linux/init.h> #include <linux/linkage.h> #include <asm/asm-offsets.h> +#include <asm/assembler.h> #include <asm/page.h> #include <asm/tlbflush.h> #include "proc-macros.S" @@ -55,7 +56,7 @@ ENTRY(v6wbi_flush_user_tlb_range) cmp r0, r1 blo 1b mcr p15, 0, ip, c7, c10, 4 @ data synchronization barrier - mov pc, lr + ret lr /* * v6wbi_flush_kern_tlb_range(start,end) @@ -84,7 +85,7 @@ ENTRY(v6wbi_flush_kern_tlb_range) blo 1b mcr p15, 0, r2, c7, c10, 4 @ data synchronization barrier mcr p15, 0, r2, c7, c5, 4 @ prefetch flush (isb) - mov pc, lr + ret lr __INIT diff --git a/arch/arm/mm/tlb-v7.S b/arch/arm/mm/tlb-v7.S index 355308767bae..e5101a3bc57c 100644 --- a/arch/arm/mm/tlb-v7.S +++ b/arch/arm/mm/tlb-v7.S @@ -57,7 +57,7 @@ ENTRY(v7wbi_flush_user_tlb_range) cmp r0, r1 blo 1b dsb ish - mov pc, lr + ret lr ENDPROC(v7wbi_flush_user_tlb_range) /* @@ -86,7 +86,7 @@ ENTRY(v7wbi_flush_kern_tlb_range) blo 1b dsb ish isb - mov pc, lr + ret lr ENDPROC(v7wbi_flush_kern_tlb_range) __INIT |