diff options
Diffstat (limited to 'arch/arm/mm')
51 files changed, 1716 insertions, 675 deletions
diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig index 88633fe..4cefb57 100644 --- a/arch/arm/mm/Kconfig +++ b/arch/arm/mm/Kconfig @@ -629,6 +629,23 @@ config IO_36 comment "Processor Features" +config ARM_LPAE + bool "Support for the Large Physical Address Extension" + depends on MMU && CPU_V7 + help + Say Y if you have an ARMv7 processor supporting the LPAE page + table format and you would like to access memory beyond the + 4GB limit. The resulting kernel image will not run on + processors without the LPA extension. + + If unsure, say N. + +config ARCH_PHYS_ADDR_T_64BIT + def_bool ARM_LPAE + +config ARCH_DMA_ADDR_T_64BIT + bool + config ARM_THUMB bool "Support Thumb user binaries" depends on CPU_ARM720T || CPU_ARM740T || CPU_ARM920T || CPU_ARM922T || CPU_ARM925T || CPU_ARM926T || CPU_ARM940T || CPU_ARM946E || CPU_ARM1020 || CPU_ARM1020E || CPU_ARM1022 || CPU_ARM1026 || CPU_XSCALE || CPU_XSC3 || CPU_MOHAWK || CPU_V6 || CPU_V6K || CPU_V7 || CPU_FEROCEON @@ -816,14 +833,23 @@ config CACHE_FEROCEON_L2_WRITETHROUGH Say Y here to use the Feroceon L2 cache in writethrough mode. Unless you specifically require this, say N for writeback mode. +config MIGHT_HAVE_CACHE_L2X0 + bool + help + This option should be selected by machines which have a L2x0 + or PL310 cache controller, but where its use is optional. + + The only effect of this option is to make CACHE_L2X0 and + related options available to the user for configuration. + + Boards or SoCs which always require the cache controller + support to be present should select CACHE_L2X0 directly + instead of this option, thus preventing the user from + inadvertently configuring a broken kernel. + config CACHE_L2X0 - bool "Enable the L2x0 outer cache controller" - depends on REALVIEW_EB_ARM11MP || MACH_REALVIEW_PB11MP || MACH_REALVIEW_PB1176 || \ - REALVIEW_EB_A9MP || SOC_IMX35 || SOC_IMX31 || MACH_REALVIEW_PBX || \ - ARCH_NOMADIK || ARCH_OMAP4 || ARCH_EXYNOS4 || ARCH_TEGRA || \ - ARCH_U8500 || ARCH_VEXPRESS_CA9X4 || ARCH_SHMOBILE || \ - ARCH_PRIMA2 || ARCH_ZYNQ || ARCH_CNS3XXX - default y + bool "Enable the L2x0 outer cache controller" if MIGHT_HAVE_CACHE_L2X0 + default MIGHT_HAVE_CACHE_L2X0 select OUTER_CACHE select OUTER_CACHE_SYNC help diff --git a/arch/arm/mm/abort-macro.S b/arch/arm/mm/abort-macro.S index 52162d5..2cbf68e 100644 --- a/arch/arm/mm/abort-macro.S +++ b/arch/arm/mm/abort-macro.S @@ -17,7 +17,7 @@ cmp \tmp, # 0x5600 @ Is it ldrsb? orreq \tmp, \tmp, #1 << 11 @ Set L-bit if yes tst \tmp, #1 << 11 @ L = 0 -> write - orreq \psr, \psr, #1 << 11 @ yes. + orreq \fsr, \fsr, #1 << 11 @ yes. b do_DataAbort not_thumb: .endm diff --git a/arch/arm/mm/alignment.c b/arch/arm/mm/alignment.c index be7c638..caf14dc 100644 --- a/arch/arm/mm/alignment.c +++ b/arch/arm/mm/alignment.c @@ -22,6 +22,7 @@ #include <linux/sched.h> #include <linux/uaccess.h> +#include <asm/system.h> #include <asm/unaligned.h> #include "fault.h" @@ -85,6 +86,33 @@ core_param(alignment, ai_usermode, int, 0600); #define UM_FIXUP (1 << 1) #define UM_SIGNAL (1 << 2) +/* 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); +} + +static int safe_usermode(int new_usermode, bool warn) +{ + /* + * ARMv6 and later CPUs can perform unaligned accesses for + * most single load and store instructions up to word size. + * LDM, STM, LDRD and STRD still need to be handled. + * + * Ignoring the alignment fault is not an option on these + * CPUs since we spin re-faulting the instruction without + * making any progress. + */ + if (cpu_is_v6_unaligned() && !(new_usermode & (UM_FIXUP | UM_SIGNAL))) { + new_usermode |= UM_FIXUP; + + if (warn) + printk(KERN_WARNING "alignment: ignoring faults is unsafe on this CPU. Defaulting to fixup mode.\n"); + } + + return new_usermode; +} + #ifdef CONFIG_PROC_FS static const char *usermode_action[] = { "ignored", @@ -125,7 +153,7 @@ static ssize_t alignment_proc_write(struct file *file, const char __user *buffer if (get_user(mode, buffer)) return -EFAULT; if (mode >= '0' && mode <= '5') - ai_usermode = mode - '0'; + ai_usermode = safe_usermode(mode - '0', true); } return count; } @@ -886,9 +914,16 @@ do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs) if (ai_usermode & UM_FIXUP) goto fixup; - if (ai_usermode & UM_SIGNAL) - force_sig(SIGBUS, current); - else { + if (ai_usermode & UM_SIGNAL) { + siginfo_t si; + + si.si_signo = SIGBUS; + si.si_errno = 0; + si.si_code = BUS_ADRALN; + si.si_addr = (void __user *)addr; + + force_sig_info(si.si_signo, &si, current); + } else { /* * We're about to disable the alignment trap and return to * user space. But if an interrupt occurs before actually @@ -926,23 +961,14 @@ static int __init alignment_init(void) return -ENOMEM; #endif - /* - * ARMv6 and later CPUs can perform unaligned accesses for - * most single load and store instructions up to word size. - * LDM, STM, LDRD and STRD still need to be handled. - * - * Ignoring the alignment fault is not an option on these - * CPUs since we spin re-faulting the instruction without - * making any progress. - */ - if (cpu_architecture() >= CPU_ARCH_ARMv6 && (cr_alignment & CR_U)) { + if (cpu_is_v6_unaligned()) { cr_alignment &= ~CR_A; cr_no_alignment &= ~CR_A; set_cr(cr_alignment); - ai_usermode = UM_FIXUP; + ai_usermode = safe_usermode(ai_usermode, false); } - hook_fault_code(1, do_alignment, SIGBUS, BUS_ADRALN, + hook_fault_code(FAULT_CODE_ALIGNMENT, do_alignment, SIGBUS, BUS_ADRALN, "alignment exception"); /* diff --git a/arch/arm/mm/cache-l2x0.c b/arch/arm/mm/cache-l2x0.c index 44c0867..b1e192b 100644 --- a/arch/arm/mm/cache-l2x0.c +++ b/arch/arm/mm/cache-l2x0.c @@ -16,9 +16,12 @@ * 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/err.h> #include <linux/init.h> #include <linux/spinlock.h> #include <linux/io.h> +#include <linux/of.h> +#include <linux/of_address.h> #include <asm/cacheflush.h> #include <asm/hardware/cache-l2x0.h> @@ -26,15 +29,23 @@ #define CACHE_LINE_SIZE 32 static void __iomem *l2x0_base; -static DEFINE_SPINLOCK(l2x0_lock); +static DEFINE_RAW_SPINLOCK(l2x0_lock); static uint32_t l2x0_way_mask; /* Bitmask of active ways */ static uint32_t l2x0_size; +struct l2x0_regs l2x0_saved_regs; + +struct l2x0_of_data { + void (*setup)(const struct device_node *, __u32 *, __u32 *); + void (*save)(void); + void (*resume)(void); +}; + static inline void cache_wait_way(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 @@ -50,7 +61,7 @@ static inline void cache_sync(void) { void __iomem *base = l2x0_base; -#ifdef CONFIG_ARM_ERRATA_753970 +#ifdef CONFIG_PL310_ERRATA_753970 /* write to an unmmapped register */ writel_relaxed(0, base + L2X0_DUMMY_REG); #else @@ -115,9 +126,9 @@ static void l2x0_cache_sync(void) { unsigned long flags; - spin_lock_irqsave(&l2x0_lock, flags); + raw_spin_lock_irqsave(&l2x0_lock, flags); cache_sync(); - spin_unlock_irqrestore(&l2x0_lock, flags); + raw_spin_unlock_irqrestore(&l2x0_lock, flags); } static void __l2x0_flush_all(void) @@ -134,9 +145,9 @@ static void l2x0_flush_all(void) unsigned long flags; /* clean all ways */ - spin_lock_irqsave(&l2x0_lock, flags); + raw_spin_lock_irqsave(&l2x0_lock, flags); __l2x0_flush_all(); - spin_unlock_irqrestore(&l2x0_lock, flags); + raw_spin_unlock_irqrestore(&l2x0_lock, flags); } static void l2x0_clean_all(void) @@ -144,11 +155,11 @@ static void l2x0_clean_all(void) unsigned long flags; /* clean all ways */ - spin_lock_irqsave(&l2x0_lock, flags); + 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(); - spin_unlock_irqrestore(&l2x0_lock, flags); + raw_spin_unlock_irqrestore(&l2x0_lock, flags); } static void l2x0_inv_all(void) @@ -156,13 +167,13 @@ static void l2x0_inv_all(void) unsigned long flags; /* invalidate all ways */ - spin_lock_irqsave(&l2x0_lock, flags); + raw_spin_lock_irqsave(&l2x0_lock, flags); /* Invalidating when L2 is enabled is a nono */ BUG_ON(readl(l2x0_base + L2X0_CTRL) & 1); writel_relaxed(l2x0_way_mask, l2x0_base + L2X0_INV_WAY); cache_wait_way(l2x0_base + L2X0_INV_WAY, l2x0_way_mask); cache_sync(); - spin_unlock_irqrestore(&l2x0_lock, flags); + raw_spin_unlock_irqrestore(&l2x0_lock, flags); } static void l2x0_inv_range(unsigned long start, unsigned long end) @@ -170,7 +181,7 @@ static void l2x0_inv_range(unsigned long start, unsigned long end) void __iomem *base = l2x0_base; unsigned long flags; - spin_lock_irqsave(&l2x0_lock, flags); + raw_spin_lock_irqsave(&l2x0_lock, flags); if (start & (CACHE_LINE_SIZE - 1)) { start &= ~(CACHE_LINE_SIZE - 1); debug_writel(0x03); @@ -195,13 +206,13 @@ static void l2x0_inv_range(unsigned long start, unsigned long end) } if (blk_end < end) { - spin_unlock_irqrestore(&l2x0_lock, flags); - spin_lock_irqsave(&l2x0_lock, flags); + raw_spin_unlock_irqrestore(&l2x0_lock, flags); + raw_spin_lock_irqsave(&l2x0_lock, flags); } } cache_wait(base + L2X0_INV_LINE_PA, 1); cache_sync(); - spin_unlock_irqrestore(&l2x0_lock, flags); + raw_spin_unlock_irqrestore(&l2x0_lock, flags); } static void l2x0_clean_range(unsigned long start, unsigned long end) @@ -214,7 +225,7 @@ static void l2x0_clean_range(unsigned long start, unsigned long end) return; } - spin_lock_irqsave(&l2x0_lock, flags); + raw_spin_lock_irqsave(&l2x0_lock, flags); start &= ~(CACHE_LINE_SIZE - 1); while (start < end) { unsigned long blk_end = start + min(end - start, 4096UL); @@ -225,13 +236,13 @@ static void l2x0_clean_range(unsigned long start, unsigned long end) } if (blk_end < end) { - spin_unlock_irqrestore(&l2x0_lock, flags); - spin_lock_irqsave(&l2x0_lock, flags); + raw_spin_unlock_irqrestore(&l2x0_lock, flags); + raw_spin_lock_irqsave(&l2x0_lock, flags); } } cache_wait(base + L2X0_CLEAN_LINE_PA, 1); cache_sync(); - spin_unlock_irqrestore(&l2x0_lock, flags); + raw_spin_unlock_irqrestore(&l2x0_lock, flags); } static void l2x0_flush_range(unsigned long start, unsigned long end) @@ -244,7 +255,7 @@ static void l2x0_flush_range(unsigned long start, unsigned long end) return; } - spin_lock_irqsave(&l2x0_lock, flags); + raw_spin_lock_irqsave(&l2x0_lock, flags); start &= ~(CACHE_LINE_SIZE - 1); while (start < end) { unsigned long blk_end = start + min(end - start, 4096UL); @@ -257,24 +268,43 @@ static void l2x0_flush_range(unsigned long start, unsigned long end) debug_writel(0x00); if (blk_end < end) { - spin_unlock_irqrestore(&l2x0_lock, flags); - spin_lock_irqsave(&l2x0_lock, flags); + raw_spin_unlock_irqrestore(&l2x0_lock, flags); + raw_spin_lock_irqsave(&l2x0_lock, flags); } } cache_wait(base + L2X0_CLEAN_INV_LINE_PA, 1); cache_sync(); - spin_unlock_irqrestore(&l2x0_lock, flags); + raw_spin_unlock_irqrestore(&l2x0_lock, flags); } static void l2x0_disable(void) { unsigned long flags; - spin_lock_irqsave(&l2x0_lock, flags); + raw_spin_lock_irqsave(&l2x0_lock, flags); __l2x0_flush_all(); writel_relaxed(0, l2x0_base + L2X0_CTRL); dsb(); - spin_unlock_irqrestore(&l2x0_lock, flags); + raw_spin_unlock_irqrestore(&l2x0_lock, flags); +} + +static void l2x0_unlock(__u32 cache_id) +{ + int lockregs; + int i; + + if (cache_id == L2X0_CACHE_ID_PART_L310) + lockregs = 8; + else + /* L210 and unknown types */ + lockregs = 1; + + 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); + } } void __init l2x0_init(void __iomem *base, __u32 aux_val, __u32 aux_mask) @@ -328,10 +358,14 @@ void __init l2x0_init(void __iomem *base, __u32 aux_val, __u32 aux_mask) * accessing the below registers will fault. */ if (!(readl_relaxed(l2x0_base + L2X0_CTRL) & 1)) { + /* Make sure that I&D is not locked down when starting */ + l2x0_unlock(cache_id); /* l2x0 controller is disabled */ writel_relaxed(aux, l2x0_base + L2X0_AUX_CTRL); + l2x0_saved_regs.aux_ctrl = aux; + l2x0_inv_all(); /* enable L2X0 */ @@ -351,3 +385,202 @@ void __init l2x0_init(void __iomem *base, __u32 aux_val, __u32 aux_mask) printk(KERN_INFO "l2x0: %d ways, CACHE_ID 0x%08x, AUX_CTRL 0x%08x, Cache size: %d B\n", ways, cache_id, aux, l2x0_size); } + +#ifdef CONFIG_OF +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); + } +} + +static void l2x0_resume(void) +{ + if (!(readl_relaxed(l2x0_base + L2X0_CTRL) & 1)) { + /* 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(1, l2x0_base + L2X0_CTRL); + } +} + +static void pl310_resume(void) +{ + u32 l2x0_revision; + + if (!(readl_relaxed(l2x0_base + L2X0_CTRL) & 1)) { + /* 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 const struct l2x0_of_data pl310_data = { + pl310_of_setup, + pl310_save, + pl310_resume, +}; + +static const struct l2x0_of_data l2x0_data = { + l2x0_of_setup, + NULL, + l2x0_resume, +}; + +static const struct of_device_id l2x0_ids[] __initconst = { + { .compatible = "arm,pl310-cache", .data = (void *)&pl310_data }, + { .compatible = "arm,l220-cache", .data = (void *)&l2x0_data }, + { .compatible = "arm,l210-cache", .data = (void *)&l2x0_data }, + {} +}; + +int __init l2x0_of_init(__u32 aux_val, __u32 aux_mask) +{ + struct device_node *np; + struct l2x0_of_data *data; + struct resource res; + + np = of_find_matching_node(NULL, l2x0_ids); + if (!np) + return -ENODEV; + + if (of_address_to_resource(np, 0, &res)) + return -ENODEV; + + l2x0_base = ioremap(res.start, resource_size(&res)); + if (!l2x0_base) + return -ENOMEM; + + l2x0_saved_regs.phy_base = res.start; + + 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) & 1)) { + if (data->setup) + data->setup(np, &aux_val, &aux_mask); + } + + if (data->save) + data->save(); + + l2x0_init(l2x0_base, aux_val, aux_mask); + + outer_cache.resume = data->resume; + return 0; +} +#endif diff --git a/arch/arm/mm/cache-v7.S b/arch/arm/mm/cache-v7.S index 3b24bfa..07c4bc8 100644 --- a/arch/arm/mm/cache-v7.S +++ b/arch/arm/mm/cache-v7.S @@ -174,6 +174,10 @@ ENTRY(v7_coherent_user_range) dcache_line_size r2, r3 sub r3, r2, #1 bic r12, r0, r3 +#ifdef CONFIG_ARM_ERRATA_764369 + ALT_SMP(W(dsb)) + ALT_UP(W(nop)) +#endif 1: USER( mcr p15, 0, r12, c7, c11, 1 ) @ clean D line to the point of unification add r12, r12, r2 @@ -223,6 +227,10 @@ ENTRY(v7_flush_kern_dcache_area) add r1, r0, r1 sub r3, r2, #1 bic r0, r0, r3 +#ifdef CONFIG_ARM_ERRATA_764369 + ALT_SMP(W(dsb)) + ALT_UP(W(nop)) +#endif 1: mcr p15, 0, r0, c7, c14, 1 @ clean & invalidate D line / unified line add r0, r0, r2 @@ -247,6 +255,10 @@ v7_dma_inv_range: sub r3, r2, #1 tst r0, r3 bic r0, r0, r3 +#ifdef CONFIG_ARM_ERRATA_764369 + ALT_SMP(W(dsb)) + ALT_UP(W(nop)) +#endif mcrne p15, 0, r0, c7, c14, 1 @ clean & invalidate D / U line tst r1, r3 @@ -270,6 +282,10 @@ v7_dma_clean_range: dcache_line_size r2, r3 sub r3, r2, #1 bic r0, r0, r3 +#ifdef CONFIG_ARM_ERRATA_764369 + ALT_SMP(W(dsb)) + ALT_UP(W(nop)) +#endif 1: mcr p15, 0, r0, c7, c10, 1 @ clean D / U line add r0, r0, r2 @@ -288,6 +304,10 @@ ENTRY(v7_dma_flush_range) dcache_line_size r2, r3 sub r3, r2, #1 bic r0, r0, r3 +#ifdef CONFIG_ARM_ERRATA_764369 + ALT_SMP(W(dsb)) + ALT_UP(W(nop)) +#endif 1: mcr p15, 0, r0, c7, c14, 1 @ clean & invalidate D / U line add r0, r0, r2 diff --git a/arch/arm/mm/context.c b/arch/arm/mm/context.c index b0ee9ba..ee9bb36 100644 --- a/arch/arm/mm/context.c +++ b/arch/arm/mm/context.c @@ -16,12 +16,27 @@ #include <asm/mmu_context.h> #include <asm/tlbflush.h> -static DEFINE_SPINLOCK(cpu_asid_lock); +static DEFINE_RAW_SPINLOCK(cpu_asid_lock); unsigned int cpu_last_asid = ASID_FIRST_VERSION; #ifdef CONFIG_SMP DEFINE_PER_CPU(struct mm_struct *, current_mm); #endif +#ifdef CONFIG_ARM_LPAE +#define cpu_set_asid(asid) { \ + unsigned long ttbl, ttbh; \ + asm volatile( \ + " mrrc p15, 0, %0, %1, c2 @ read TTBR0\n" \ + " mov %1, %2, lsl #(48 - 32) @ set ASID\n" \ + " mcrr p15, 0, %0, %1, c2 @ set TTBR0\n" \ + : "=&r" (ttbl), "=&r" (ttbh) \ + : "r" (asid & ~ASID_MASK)); \ +} +#else +#define cpu_set_asid(asid) \ + asm(" mcr p15, 0, %0, c13, c0, 1\n" : : "r" (asid)) +#endif + /* * We fork()ed a process, and we need a new context for the child * to run in. We reserve version 0 for initial tasks so we will @@ -31,13 +46,13 @@ DEFINE_PER_CPU(struct mm_struct *, current_mm); void __init_new_context(struct task_struct *tsk, struct mm_struct *mm) { mm->context.id = 0; - spin_lock_init(&mm->context.id_lock); + raw_spin_lock_init(&mm->context.id_lock); } static void flush_context(void) { /* set the reserved ASID before flushing the TLB */ - asm("mcr p15, 0, %0, c13, c0, 1\n" : : "r" (0)); + cpu_set_asid(0); isb(); local_flush_tlb_all(); if (icache_is_vivt_asid_tagged()) { @@ -58,7 +73,7 @@ static void set_mm_context(struct mm_struct *mm, unsigned int asid) * the broadcast. This function is also called via IPI so the * mm->context.id_lock has to be IRQ-safe. */ - spin_lock_irqsave(&mm->context.id_lock, flags); + raw_spin_lock_irqsave(&mm->context.id_lock, flags); if (likely((mm->context.id ^ cpu_last_asid) >> ASID_BITS)) { /* * Old version of ASID found. Set the new one and @@ -67,7 +82,7 @@ static void set_mm_context(struct mm_struct *mm, unsigned int asid) mm->context.id = asid; cpumask_clear(mm_cpumask(mm)); } - spin_unlock_irqrestore(&mm->context.id_lock, flags); + raw_spin_unlock_irqrestore(&mm->context.id_lock, flags); /* * Set the mm_cpumask(mm) bit for the current CPU. @@ -99,7 +114,7 @@ static void reset_context(void *info) set_mm_context(mm, asid); /* set the new ASID */ - asm("mcr p15, 0, %0, c13, c0, 1\n" : : "r" (mm->context.id)); + cpu_set_asid(mm->context.id); isb(); } @@ -117,7 +132,7 @@ void __new_context(struct mm_struct *mm) { unsigned int asid; - spin_lock(&cpu_asid_lock); + raw_spin_lock(&cpu_asid_lock); #ifdef CONFIG_SMP /* * Check the ASID again, in case the change was broadcast from @@ -125,7 +140,7 @@ void __new_context(struct mm_struct *mm) */ if (unlikely(((mm->context.id ^ cpu_last_asid) >> ASID_BITS) == 0)) { cpumask_set_cpu(smp_processor_id(), mm_cpumask(mm)); - spin_unlock(&cpu_asid_lock); + raw_spin_unlock(&cpu_asid_lock); return; } #endif @@ -153,5 +168,5 @@ void __new_context(struct mm_struct *mm) } set_mm_context(mm, asid); - spin_unlock(&cpu_asid_lock); + raw_spin_unlock(&cpu_asid_lock); } diff --git a/arch/arm/mm/copypage-v4mc.c b/arch/arm/mm/copypage-v4mc.c index b806151..7d0a8c2 100644 --- a/arch/arm/mm/copypage-v4mc.c +++ b/arch/arm/mm/copypage-v4mc.c @@ -30,7 +30,7 @@ #define minicache_pgprot __pgprot(L_PTE_PRESENT | L_PTE_YOUNG | \ L_PTE_MT_MINICACHE) -static DEFINE_SPINLOCK(minicache_lock); +static DEFINE_RAW_SPINLOCK(minicache_lock); /* * ARMv4 mini-dcache optimised copy_user_highpage @@ -76,14 +76,14 @@ void v4_mc_copy_user_highpage(struct page *to, struct page *from, if (!test_and_set_bit(PG_dcache_clean, &from->flags)) __flush_dcache_page(page_mapping(from), from); - spin_lock(&minicache_lock); + raw_spin_lock(&minicache_lock); set_pte_ext(TOP_PTE(0xffff8000), pfn_pte(page_to_pfn(from), minicache_pgprot), 0); flush_tlb_kernel_page(0xffff8000); mc_copy_user_page((void *)0xffff8000, kto); - spin_unlock(&minicache_lock); + raw_spin_unlock(&minicache_lock); kunmap_atomic(kto, KM_USER1); } diff --git a/arch/arm/mm/copypage-v6.c b/arch/arm/mm/copypage-v6.c index 63cca00..3d9a155 100644 --- a/arch/arm/mm/copypage-v6.c +++ b/arch/arm/mm/copypage-v6.c @@ -27,7 +27,7 @@ #define from_address (0xffff8000) #define to_address (0xffffc000) -static DEFINE_SPINLOCK(v6_lock); +static DEFINE_RAW_SPINLOCK(v6_lock); /* * Copy the user page. No aliasing to deal with so we can just @@ -88,7 +88,7 @@ static void v6_copy_user_highpage_aliasing(struct page *to, * Now copy the page using the same cache colour as the * pages ultimate destination. */ - spin_lock(&v6_lock); + raw_spin_lock(&v6_lock); set_pte_ext(TOP_PTE(from_address) + offset, pfn_pte(page_to_pfn(from), PAGE_KERNEL), 0); set_pte_ext(TOP_PTE(to_address) + offset, pfn_pte(page_to_pfn(to), PAGE_KERNEL), 0); @@ -101,7 +101,7 @@ static void v6_copy_user_highpage_aliasing(struct page *to, copy_page((void *)kto, (void *)kfrom); - spin_unlock(&v6_lock); + raw_spin_unlock(&v6_lock); } /* @@ -121,13 +121,13 @@ static void v6_clear_user_highpage_aliasing(struct page *page, unsigned long vad * Now clear the page using the same cache colour as * the pages ultimate destination. */ - spin_lock(&v6_lock); + raw_spin_lock(&v6_lock); set_pte_ext(TOP_PTE(to_address) + offset, pfn_pte(page_to_pfn(page), PAGE_KERNEL), 0); flush_tlb_kernel_page(to); clear_page((void *)to); - spin_unlock(&v6_lock); + raw_spin_unlock(&v6_lock); } struct cpu_user_fns v6_user_fns __initdata = { diff --git a/arch/arm/mm/copypage-xscale.c b/arch/arm/mm/copypage-xscale.c index 649bbcd..610c24c 100644 --- a/arch/arm/mm/copypage-xscale.c +++ b/arch/arm/mm/copypage-xscale.c @@ -32,7 +32,7 @@ #define minicache_pgprot __pgprot(L_PTE_PRESENT | L_PTE_YOUNG | \ L_PTE_MT_MINICACHE) -static DEFINE_SPINLOCK(minicache_lock); +static DEFINE_RAW_SPINLOCK(minicache_lock); /* * XScale mini-dcache optimised copy_user_highpage @@ -98,14 +98,14 @@ void xscale_mc_copy_user_highpage(struct page *to, struct page *from, if (!test_and_set_bit(PG_dcache_clean, &from->flags)) __flush_dcache_page(page_mapping(from), from); - spin_lock(&minicache_lock); + raw_spin_lock(&minicache_lock); set_pte_ext(TOP_PTE(COPYPAGE_MINICACHE), pfn_pte(page_to_pfn(from), minicache_pgprot), 0); flush_tlb_kernel_page(COPYPAGE_MINICACHE); mc_copy_user_page((void *)COPYPAGE_MINICACHE, kto); - spin_unlock(&minicache_lock); + raw_spin_unlock(&minicache_lock); kunmap_atomic(kto, KM_USER1); } diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c index 0a0a1e7..1aa664a 100644 --- a/arch/arm/mm/dma-mapping.c +++ b/arch/arm/mm/dma-mapping.c @@ -18,12 +18,14 @@ #include <linux/device.h> #include <linux/dma-mapping.h> #include <linux/highmem.h> +#include <linux/slab.h> #include <asm/memory.h> #include <asm/highmem.h> #include <asm/cacheflush.h> #include <asm/tlbflush.h> #include <asm/sizes.h> +#include <asm/mach/arch.h> #include "mm.h" @@ -117,26 +119,36 @@ static void __dma_free_buffer(struct page *page, size_t size) } #ifdef CONFIG_MMU -/* Sanity check size */ -#if (CONSISTENT_DMA_SIZE % SZ_2M) -#error "CONSISTENT_DMA_SIZE must be multiple of 2MiB" -#endif -#define CONSISTENT_OFFSET(x) (((unsigned long)(x) - CONSISTENT_BASE) >> PAGE_SHIFT) -#define CONSISTENT_PTE_INDEX(x) (((unsigned long)(x) - CONSISTENT_BASE) >> PGDIR_SHIFT) -#define NUM_CONSISTENT_PTES (CONSISTENT_DMA_SIZE >> PGDIR_SHIFT) +#define CONSISTENT_OFFSET(x) (((unsigned long)(x) - consistent_base) >> PAGE_SHIFT) +#define CONSISTENT_PTE_INDEX(x) (((unsigned long)(x) - consistent_base) >> PMD_SHIFT) /* * These are the page tables (2MB each) covering uncached, DMA consistent allocations */ -static pte_t *consistent_pte[NUM_CONSISTENT_PTES]; +static pte_t **consistent_pte; + +#define DEFAULT_CONSISTENT_DMA_SIZE SZ_2M + +unsigned long consistent_base = CONSISTENT_END - DEFAULT_CONSISTENT_DMA_SIZE; + +void __init init_consistent_dma_size(unsigned long size) +{ + unsigned long base = CONSISTENT_END - ALIGN(size, SZ_2M); + + BUG_ON(consistent_pte); /* Check we're called before DMA region init */ + BUG_ON(base < VMALLOC_END); + + /* Grow region to accommodate specified size */ + if (base < consistent_base) + consistent_base = base; +} #include "vmregion.h" static struct arm_vmregion_head consistent_head = { .vm_lock = __SPIN_LOCK_UNLOCKED(&consistent_head.vm_lock), .vm_list = LIST_HEAD_INIT(consistent_head.vm_list), - .vm_start = CONSISTENT_BASE, .vm_end = CONSISTENT_END, }; @@ -155,7 +167,17 @@ static int __init consistent_init(void) pmd_t *pmd; pte_t *pte; int i = 0; - u32 base = CONSISTENT_BASE; + unsigned long base = consistent_base; + unsigned long num_ptes = (CONSISTENT_END - base) >> PMD_SHIFT; + + consistent_pte = kmalloc(num_ptes * sizeof(pte_t), GFP_KERNEL); + if (!consistent_pte) { + pr_err("%s: no memory\n", __func__); + return -ENOMEM; + } + + pr_debug("DMA memory: 0x%08lx - 0x%08lx:\n", base, CONSISTENT_END); + consistent_head.vm_start = base; do { pgd = pgd_offset(&init_mm, base); @@ -183,7 +205,7 @@ static int __init consistent_init(void) } consistent_pte[i++] = pte; - base += (1 << PGDIR_SHIFT); + base += PMD_SIZE; } while (base < CONSISTENT_END); return ret; @@ -198,7 +220,7 @@ __dma_alloc_remap(struct page *page, size_t size, gfp_t gfp, pgprot_t prot) size_t align; int bit; - if (!consistent_pte[0]) { + if (!consistent_pte) { printk(KERN_ERR "%s: not initialised\n", __func__); dump_stack(); return NULL; @@ -310,6 +332,15 @@ __dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, gfp_t gfp, struct page *page; void *addr; + /* + * Following is a work-around (a.k.a. hack) to prevent pages + * with __GFP_COMP being passed to split_page() which cannot + * handle them. The real problem is that this flag probably + * should be 0 on ARM as it is not supported on this + * platform; see CONFIG_HUGETLBFS. + */ + gfp &= ~(__GFP_COMP); + *handle = ~0; size = PAGE_ALIGN(size); @@ -324,6 +355,8 @@ __dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, gfp_t gfp, if (addr) *handle = pfn_to_dma(dev, page_to_pfn(page)); + else + __dma_free_buffer(page, size); return addr; } diff --git a/arch/arm/mm/fault-armv.c b/arch/arm/mm/fault-armv.c index 7cab791..7599e26 100644 --- a/arch/arm/mm/fault-armv.c +++ b/arch/arm/mm/fault-armv.c @@ -8,7 +8,6 @@ * it under the terms of the GNU General Public License version 2 as * published by the Free Software Foundation. */ -#include <linux/module.h> #include <linux/sched.h> #include <linux/kernel.h> #include <linux/mm.h> diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c index 3b5ea68..bb7eac3 100644 --- a/arch/arm/mm/fault.c +++ b/arch/arm/mm/fault.c @@ -20,25 +20,13 @@ #include <linux/highmem.h> #include <linux/perf_event.h> +#include <asm/exception.h> #include <asm/system.h> #include <asm/pgtable.h> #include <asm/tlbflush.h> #include "fault.h" -/* - * Fault status register encodings. We steal bit 31 for our own purposes. - */ -#define FSR_LNX_PF (1 << 31) -#define FSR_WRITE (1 << 11) -#define FSR_FS4 (1 << 10) -#define FSR_FS3_0 (15) - -static inline int fsr_fs(unsigned int fsr) -{ - return (fsr & FSR_FS3_0) | (fsr & FSR_FS4) >> 6; -} - #ifdef CONFIG_MMU #ifdef CONFIG_KPROBES @@ -122,8 +110,10 @@ void show_pte(struct mm_struct *mm, unsigned long addr) pte = pte_offset_map(pmd, addr); printk(", *pte=%08llx", (long long)pte_val(*pte)); +#ifndef CONFIG_ARM_LPAE printk(", *ppte=%08llx", (long long)pte_val(pte[PTE_HWTABLE_PTRS])); +#endif pte_unmap(pte); } while(0); @@ -230,7 +220,7 @@ static inline bool access_error(unsigned int fsr, struct vm_area_struct *vma) static int __kprobes __do_page_fault(struct mm_struct *mm, unsigned long addr, unsigned int fsr, - struct task_struct *tsk) + unsigned int flags, struct task_struct *tsk) { struct vm_area_struct *vma; int fault; @@ -252,18 +242,7 @@ good_area: goto out; } - /* - * If for any reason at all we couldn't handle the fault, make - * sure we exit gracefully rather than endlessly redo the fault. - */ - fault = handle_mm_fault(mm, vma, addr & PAGE_MASK, (fsr & FSR_WRITE) ? FAULT_FLAG_WRITE : 0); - if (unlikely(fault & VM_FAULT_ERROR)) - return fault; - if (fault & VM_FAULT_MAJOR) - tsk->maj_flt++; - else - tsk->min_flt++; - return fault; + return handle_mm_fault(mm, vma, addr & PAGE_MASK, flags); check_stack: if (vma->vm_flags & VM_GROWSDOWN && !expand_stack(vma, addr)) @@ -278,6 +257,9 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs) struct task_struct *tsk; struct mm_struct *mm; int fault, sig, code; + int write = fsr & FSR_WRITE; + unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE | + (write ? FAULT_FLAG_WRITE : 0); if (notify_page_fault(regs, fsr)) return 0; @@ -304,6 +286,7 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs) if (!down_read_trylock(&mm->mmap_sem)) { if (!user_mode(regs) && !search_exception_tables(regs->ARM_pc)) goto no_context; +retry: down_read(&mm->mmap_sem); } else { /* @@ -319,14 +302,41 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs) #endif } - fault = __do_page_fault(mm, addr, fsr, tsk); - up_read(&mm->mmap_sem); + fault = __do_page_fault(mm, addr, fsr, flags, tsk); + + /* If we need to retry but a fatal signal is pending, handle the + * signal first. We do not need to release the mmap_sem because + * it would already be released in __lock_page_or_retry in + * mm/filemap.c. */ + if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) + return 0; + + /* + * Major/minor page fault accounting is only done on the + * initial attempt. If we go through a retry, it is extremely + * likely that the page will be found in page cache at that point. + */ perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, addr); - if (fault & VM_FAULT_MAJOR) - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, regs, addr); - else if (fault & VM_FAULT_MINOR) - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, regs, addr); + if (flags & FAULT_FLAG_ALLOW_RETRY) { + if (fault & VM_FAULT_MAJOR) { + tsk->maj_flt++; + perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, + regs, addr); + } else { + tsk->min_flt++; + perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, + regs, addr); + } + if (fault & VM_FAULT_RETRY) { + /* Clear FAULT_FLAG_ALLOW_RETRY to avoid any risk + * of starvation. */ + flags &= ~FAULT_FLAG_ALLOW_RETRY; + goto retry; + } + } + + up_read(&mm->mmap_sem); /* * Handle the "normal" case first - VM_FAULT_MAJOR / VM_FAULT_MINOR @@ -440,6 +450,12 @@ do_translation_fault(unsigned long addr, unsigned int fsr, pmd = pmd_offset(pud, addr); pmd_k = pmd_offset(pud_k, addr); +#ifdef CONFIG_ARM_LPAE + /* + * Only one hardware entry per PMD with LPAE. + */ + index = 0; +#else /* * On ARM one Linux PGD entry contains two hardware entries (see page * tables layout in pgtable.h). We normally guarantee that we always @@ -449,6 +465,7 @@ do_translation_fault(unsigned long addr, unsigned int fsr, * for the first of pair. */ index = (addr >> SECTION_SHIFT) & 1; +#endif if (pmd_none(pmd_k[index])) goto bad_area; @@ -488,55 +505,20 @@ do_bad(unsigned long addr, unsigned int fsr, struct pt_regs *regs) return 1; } -static struct fsr_info { +struct fsr_info { int (*fn)(unsigned long addr, unsigned int fsr, struct pt_regs *regs); int sig; int code; const char *name; -} fsr_info[] = { - /* - * The following are the standard ARMv3 and ARMv4 aborts. ARMv5 - * defines these to be "precise" aborts. - */ - { do_bad, SIGSEGV, 0, "vector exception" }, - { do_bad, SIGBUS, BUS_ADRALN, "alignment exception" }, - { do_bad, SIGKILL, 0, "terminal exception" }, - { do_bad, SIGBUS, BUS_ADRALN, "alignment exception" }, - { do_bad, SIGBUS, 0, "external abort on linefetch" }, - { do_translation_fault, SIGSEGV, SEGV_MAPERR, "section translation fault" }, - { do_bad, SIGBUS, 0, "external abort on linefetch" }, - { do_page_fault, SIGSEGV, SEGV_MAPERR, "page translation fault" }, - { do_bad, SIGBUS, 0, "external abort on non-linefetch" }, - { do_bad, SIGSEGV, SEGV_ACCERR, "section domain fault" }, - { do_bad, SIGBUS, 0, "external abort on non-linefetch" }, - { do_bad, SIGSEGV, SEGV_ACCERR, "page domain fault" }, - { do_bad, SIGBUS, 0, "external abort on translation" }, - { do_sect_fault, SIGSEGV, SEGV_ACCERR, "section permission fault" }, - { do_bad, SIGBUS, 0, "external abort on translation" }, - { do_page_fault, SIGSEGV, SEGV_ACCERR, "page permission fault" }, - /* - * The following are "imprecise" aborts, which are signalled by bit - * 10 of the FSR, and may not be recoverable. These are only - * supported if the CPU abort handler supports bit 10. - */ - { do_bad, SIGBUS, 0, "unknown 16" }, - { do_bad, SIGBUS, 0, "unknown 17" }, - { do_bad, SIGBUS, 0, "unknown 18" }, - { do_bad, SIGBUS, 0, "unknown 19" }, - { do_bad, SIGBUS, 0, "lock abort" }, /* xscale */ - { do_bad, SIGBUS, 0, "unknown 21" }, - { do_bad, SIGBUS, BUS_OBJERR, "imprecise external abort" }, /* xscale */ - { do_bad, SIGBUS, 0, "unknown 23" }, - { do_bad, SIGBUS, 0, "dcache parity error" }, /* xscale */ - { do_bad, SIGBUS, 0, "unknown 25" }, - { do_bad, SIGBUS, 0, "unknown 26" }, - { do_bad, SIGBUS, 0, "unknown 27" }, - { do_bad, SIGBUS, 0, "unknown 28" }, - { do_bad, SIGBUS, 0, "unknown 29" }, - { do_bad, SIGBUS, 0, "unknown 30" }, - { do_bad, SIGBUS, 0, "unknown 31" } }; +/* FSR definition */ +#ifdef CONFIG_ARM_LPAE +#include "fsr-3level.c" +#else +#include "fsr-2level.c" +#endif + void __init hook_fault_code(int nr, int (*fn)(unsigned long, unsigned int, struct pt_regs *), int sig, int code, const char *name) @@ -572,42 +554,6 @@ do_DataAbort(unsigned long addr, unsigned int fsr, struct pt_regs *regs) arm_notify_die("", regs, &info, fsr, 0); } - -static struct fsr_info ifsr_info[] = { - { do_bad, SIGBUS, 0, "unknown 0" }, - { do_bad, SIGBUS, 0, "unknown 1" }, - { do_bad, SIGBUS, 0, "debug event" }, - { do_bad, SIGSEGV, SEGV_ACCERR, "section access flag fault" }, - { do_bad, SIGBUS, 0, "unknown 4" }, - { do_translation_fault, SIGSEGV, SEGV_MAPERR, "section translation fault" }, - { do_bad, SIGSEGV, SEGV_ACCERR, "page access flag fault" }, - { do_page_fault, SIGSEGV, SEGV_MAPERR, "page translation fault" }, - { do_bad, SIGBUS, 0, "external abort on non-linefetch" }, - { do_bad, SIGSEGV, SEGV_ACCERR, "section domain fault" }, - { do_bad, SIGBUS, 0, "unknown 10" }, - { do_bad, SIGSEGV, SEGV_ACCERR, "page domain fault" }, - { do_bad, SIGBUS, 0, "external abort on translation" }, - { do_sect_fault, SIGSEGV, SEGV_ACCERR, "section permission fault" }, - { do_bad, SIGBUS, 0, "external abort on translation" }, - { do_page_fault, SIGSEGV, SEGV_ACCERR, "page permission fault" }, - { do_bad, SIGBUS, 0, "unknown 16" }, - { do_bad, SIGBUS, 0, "unknown 17" }, - { do_bad, SIGBUS, 0, "unknown 18" }, - { do_bad, SIGBUS, 0, "unknown 19" }, - { do_bad, SIGBUS, 0, "unknown 20" }, - { do_bad, SIGBUS, 0, "unknown 21" }, - { do_bad, SIGBUS, 0, "unknown 22" }, - { do_bad, SIGBUS, 0, "unknown 23" }, - { do_bad, SIGBUS, 0, "unknown 24" }, - { do_bad, SIGBUS, 0, "unknown 25" }, - { do_bad, SIGBUS, 0, "unknown 26" }, - { do_bad, SIGBUS, 0, "unknown 27" }, - { do_bad, SIGBUS, 0, "unknown 28" }, - { do_bad, SIGBUS, 0, "unknown 29" }, - { do_bad, SIGBUS, 0, "unknown 30" }, - { do_bad, SIGBUS, 0, "unknown 31" }, -}; - void __init hook_ifault_code(int nr, int (*fn)(unsigned long, unsigned int, struct pt_regs *), int sig, int code, const char *name) @@ -640,6 +586,7 @@ do_PrefetchAbort(unsigned long addr, unsigned int ifsr, struct pt_regs *regs) arm_notify_die("", regs, &info, ifsr, 0); } +#ifndef CONFIG_ARM_LPAE static int __init exceptions_init(void) { if (cpu_architecture() >= CPU_ARCH_ARMv6) { @@ -662,3 +609,4 @@ static int __init exceptions_init(void) } arch_initcall(exceptions_init); +#endif diff --git a/arch/arm/mm/fault.h b/arch/arm/mm/fault.h index 49e9e38..cf08bdf 100644 --- a/arch/arm/mm/fault.h +++ b/arch/arm/mm/fault.h @@ -1,3 +1,28 @@ -void do_bad_area(unsigned long addr, unsigned int fsr, struct pt_regs *regs); +#ifndef __ARCH_ARM_FAULT_H +#define __ARCH_ARM_FAULT_H + +/* + * Fault status register encodings. We steal bit 31 for our own purposes. + */ +#define FSR_LNX_PF (1 << 31) +#define FSR_WRITE (1 << 11) +#define FSR_FS4 (1 << 10) +#define FSR_FS3_0 (15) +#define FSR_FS5_0 (0x3f) + +#ifdef CONFIG_ARM_LPAE +static inline int fsr_fs(unsigned int fsr) +{ + return fsr & FSR_FS5_0; +} +#else +static inline int fsr_fs(unsigned int fsr) +{ + return (fsr & FSR_FS3_0) | (fsr & FSR_FS4) >> 6; +} +#endif +void do_bad_area(unsigned long addr, unsigned int fsr, struct pt_regs *regs); unsigned long search_exception_table(unsigned long addr); + +#endif /* __ARCH_ARM_FAULT_H */ diff --git a/arch/arm/mm/fsr-2level.c b/arch/arm/mm/fsr-2level.c new file mode 100644 index 0000000..18ca74c --- /dev/null +++ b/arch/arm/mm/fsr-2level.c @@ -0,0 +1,78 @@ +static struct fsr_info fsr_info[] = { + /* + * The following are the standard ARMv3 and ARMv4 aborts. ARMv5 + * defines these to be "precise" aborts. + */ + { do_bad, SIGSEGV, 0, "vector exception" }, + { do_bad, SIGBUS, BUS_ADRALN, "alignment exception" }, + { do_bad, SIGKILL, 0, "terminal exception" }, + { do_bad, SIGBUS, BUS_ADRALN, "alignment exception" }, + { do_bad, SIGBUS, 0, "external abort on linefetch" }, + { do_translation_fault, SIGSEGV, SEGV_MAPERR, "section translation fault" }, + { do_bad, SIGBUS, 0, "external abort on linefetch" }, + { do_page_fault, SIGSEGV, SEGV_MAPERR, "page translation fault" }, + { do_bad, SIGBUS, 0, "external abort on non-linefetch" }, + { do_bad, SIGSEGV, SEGV_ACCERR, "section domain fault" }, + { do_bad, SIGBUS, 0, "external abort on non-linefetch" }, + { do_bad, SIGSEGV, SEGV_ACCERR, "page domain fault" }, + { do_bad, SIGBUS, 0, "external abort on translation" }, + { do_sect_fault, SIGSEGV, SEGV_ACCERR, "section permission fault" }, + { do_bad, SIGBUS, 0, "external abort on translation" }, + { do_page_fault, SIGSEGV, SEGV_ACCERR, "page permission fault" }, + /* + * The following are "imprecise" aborts, which are signalled by bit + * 10 of the FSR, and may not be recoverable. These are only + * supported if the CPU abort handler supports bit 10. + */ + { do_bad, SIGBUS, 0, "unknown 16" }, + { do_bad, SIGBUS, 0, "unknown 17" }, + { do_bad, SIGBUS, 0, "unknown 18" }, + { do_bad, SIGBUS, 0, "unknown 19" }, + { do_bad, SIGBUS, 0, "lock abort" }, /* xscale */ + { do_bad, SIGBUS, 0, "unknown 21" }, + { do_bad, SIGBUS, BUS_OBJERR, "imprecise external abort" }, /* xscale */ + { do_bad, SIGBUS, 0, "unknown 23" }, + { do_bad, SIGBUS, 0, "dcache parity error" }, /* xscale */ + { do_bad, SIGBUS, 0, "unknown 25" }, + { do_bad, SIGBUS, 0, "unknown 26" }, + { do_bad, SIGBUS, 0, "unknown 27" }, + { do_bad, SIGBUS, 0, "unknown 28" }, + { do_bad, SIGBUS, 0, "unknown 29" }, + { do_bad, SIGBUS, 0, "unknown 30" }, + { do_bad, SIGBUS, 0, "unknown 31" }, +}; + +static struct fsr_info ifsr_info[] = { + { do_bad, SIGBUS, 0, "unknown 0" }, + { do_bad, SIGBUS, 0, "unknown 1" }, + { do_bad, SIGBUS, 0, "debug event" }, + { do_bad, SIGSEGV, SEGV_ACCERR, "section access flag fault" }, + { do_bad, SIGBUS, 0, "unknown 4" }, + { do_translation_fault, SIGSEGV, SEGV_MAPERR, "section translation fault" }, + { do_bad, SIGSEGV, SEGV_ACCERR, "page access flag fault" }, + { do_page_fault, SIGSEGV, SEGV_MAPERR, "page translation fault" }, + { do_bad, SIGBUS, 0, "external abort on non-linefetch" }, + { do_bad, SIGSEGV, SEGV_ACCERR, "section domain fault" }, + { do_bad, SIGBUS, 0, "unknown 10" }, + { do_bad, SIGSEGV, SEGV_ACCERR, "page domain fault" }, + { do_bad, SIGBUS, 0, "external abort on translation" }, + { do_sect_fault, SIGSEGV, SEGV_ACCERR, "section permission fault" }, + { do_bad, SIGBUS, 0, "external abort on translation" }, + { do_page_fault, SIGSEGV, SEGV_ACCERR, "page permission fault" }, + { do_bad, SIGBUS, 0, "unknown 16" }, + { do_bad, SIGBUS, 0, "unknown 17" }, + { do_bad, SIGBUS, 0, "unknown 18" }, + { do_bad, SIGBUS, 0, "unknown 19" }, + { do_bad, SIGBUS, 0, "unknown 20" }, + { do_bad, SIGBUS, 0, "unknown 21" }, + { do_bad, SIGBUS, 0, "unknown 22" }, + { do_bad, SIGBUS, 0, "unknown 23" }, + { do_bad, SIGBUS, 0, "unknown 24" }, + { do_bad, SIGBUS, 0, "unknown 25" }, + { do_bad, SIGBUS, 0, "unknown 26" }, + { do_bad, SIGBUS, 0, "unknown 27" }, + { do_bad, SIGBUS, 0, "unknown 28" }, + { do_bad, SIGBUS, 0, "unknown 29" }, + { do_bad, SIGBUS, 0, "unknown 30" }, + { do_bad, SIGBUS, 0, "unknown 31" }, +}; diff --git a/arch/arm/mm/fsr-3level.c b/arch/arm/mm/fsr-3level.c new file mode 100644 index 0000000..05a4e94 --- /dev/null +++ b/arch/arm/mm/fsr-3level.c @@ -0,0 +1,68 @@ +static struct fsr_info fsr_info[] = { + { do_bad, SIGBUS, 0, "unknown 0" }, + { do_bad, SIGBUS, 0, "unknown 1" }, + { do_bad, SIGBUS, 0, "unknown 2" }, + { do_bad, SIGBUS, 0, "unknown 3" }, + { do_bad, SIGBUS, 0, "reserved translation fault" }, + { do_translation_fault, SIGSEGV, SEGV_MAPERR, "level 1 translation fault" }, + { do_translation_fault, SIGSEGV, SEGV_MAPERR, "level 2 translation fault" }, + { do_page_fault, SIGSEGV, SEGV_MAPERR, "level 3 translation fault" }, + { do_bad, SIGBUS, 0, "reserved access flag fault" }, + { do_bad, SIGSEGV, SEGV_ACCERR, "level 1 access flag fault" }, + { do_bad, SIGSEGV, SEGV_ACCERR, "level 2 access flag fault" }, + { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 3 access flag fault" }, + { do_bad, SIGBUS, 0, "reserved permission fault" }, + { do_bad, SIGSEGV, SEGV_ACCERR, "level 1 permission fault" }, + { do_sect_fault, SIGSEGV, SEGV_ACCERR, "level 2 permission fault" }, + { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 3 permission fault" }, + { do_bad, SIGBUS, 0, "synchronous external abort" }, + { do_bad, SIGBUS, 0, "asynchronous external abort" }, + { do_bad, SIGBUS, 0, "unknown 18" }, + { do_bad, SIGBUS, 0, "unknown 19" }, + { do_bad, SIGBUS, 0, "synchronous abort (translation table walk)" }, + { do_bad, SIGBUS, 0, "synchronous abort (translation table walk)" }, + { do_bad, SIGBUS, 0, "synchronous abort (translation table walk)" }, + { do_bad, SIGBUS, 0, "synchronous abort (translation table walk)" }, + { do_bad, SIGBUS, 0, "synchronous parity error" }, + { do_bad, SIGBUS, 0, "asynchronous parity error" }, + { do_bad, SIGBUS, 0, "unknown 26" }, + { do_bad, SIGBUS, 0, "unknown 27" }, + { do_bad, SIGBUS, 0, "synchronous parity error (translation table walk" }, + { do_bad, SIGBUS, 0, "synchronous parity error (translation table walk" }, + { do_bad, SIGBUS, 0, "synchronous parity error (translation table walk" }, + { do_bad, SIGBUS, 0, "synchronous parity error (translation table walk" }, + { do_bad, SIGBUS, 0, "unknown 32" }, + { do_bad, SIGBUS, BUS_ADRALN, "alignment fault" }, + { do_bad, SIGBUS, 0, "debug event" }, + { do_bad, SIGBUS, 0, "unknown 35" }, + { do_bad, SIGBUS, 0, "unknown 36" }, + { do_bad, SIGBUS, 0, "unknown 37" }, + { do_bad, SIGBUS, 0, "unknown 38" }, + { do_bad, SIGBUS, 0, "unknown 39" }, + { do_bad, SIGBUS, 0, "unknown 40" }, + { do_bad, SIGBUS, 0, "unknown 41" }, + { do_bad, SIGBUS, 0, "unknown 42" }, + { do_bad, SIGBUS, 0, "unknown 43" }, + { do_bad, SIGBUS, 0, "unknown 44" }, + { do_bad, SIGBUS, 0, "unknown 45" }, + { do_bad, SIGBUS, 0, "unknown 46" }, + { do_bad, SIGBUS, 0, "unknown 47" }, + { do_bad, SIGBUS, 0, "unknown 48" }, + { do_bad, SIGBUS, 0, "unknown 49" }, + { do_bad, SIGBUS, 0, "unknown 50" }, + { do_bad, SIGBUS, 0, "unknown 51" }, + { do_bad, SIGBUS, 0, "implementation fault (lockdown abort)" }, + { do_bad, SIGBUS, 0, "unknown 53" }, + { do_bad, SIGBUS, 0, "unknown 54" }, + { do_bad, SIGBUS, 0, "unknown 55" }, + { do_bad, SIGBUS, 0, "unknown 56" }, + { do_bad, SIGBUS, 0, "unknown 57" }, + { do_bad, SIGBUS, 0, "implementation fault (coprocessor abort)" }, + { do_bad, SIGBUS, 0, "unknown 59" }, + { do_bad, SIGBUS, 0, "unknown 60" }, + { do_bad, SIGBUS, 0, "unknown 61" }, + { do_bad, SIGBUS, 0, "unknown 62" }, + { do_bad, SIGBUS, 0, "unknown 63" }, +}; + +#define ifsr_info fsr_info diff --git a/arch/arm/mm/idmap.c b/arch/arm/mm/idmap.c index 2be9139..feacf4c 100644 --- a/arch/arm/mm/idmap.c +++ b/arch/arm/mm/idmap.c @@ -1,9 +1,38 @@ #include <linux/kernel.h> #include <asm/cputype.h> +#include <asm/idmap.h> #include <asm/pgalloc.h> #include <asm/pgtable.h> +#include <asm/sections.h> +pgd_t *idmap_pgd; + +#ifdef CONFIG_ARM_LPAE +static void idmap_add_pmd(pud_t *pud, unsigned long addr, unsigned long end, + unsigned long prot) +{ + pmd_t *pmd; + unsigned long next; + + if (pud_none_or_clear_bad(pud) || (pud_val(*pud) & L_PGD_SWAPPER)) { + pmd = pmd_alloc_one(&init_mm, addr); + if (!pmd) { + pr_warning("Failed to allocate identity pmd.\n"); + return; + } + pud_populate(&init_mm, pud, pmd); + pmd += pmd_index(addr); + } else + pmd = pmd_offset(pud, addr); + + do { + next = pmd_addr_end(addr, end); + *pmd = __pmd((addr & PMD_MASK) | prot); + flush_pmd_entry(pmd); + } while (pmd++, addr = next, addr != end); +} +#else /* !CONFIG_ARM_LPAE */ static void idmap_add_pmd(pud_t *pud, unsigned long addr, unsigned long end, unsigned long prot) { @@ -15,6 +44,7 @@ static void idmap_add_pmd(pud_t *pud, unsigned long addr, unsigned long end, pmd[1] = __pmd(addr); flush_pmd_entry(pmd); } +#endif /* CONFIG_ARM_LPAE */ static void idmap_add_pud(pgd_t *pgd, unsigned long addr, unsigned long end, unsigned long prot) @@ -28,11 +58,11 @@ static void idmap_add_pud(pgd_t *pgd, unsigned long addr, unsigned long end, } while (pud++, addr = next, addr != end); } -void identity_mapping_add(pgd_t *pgd, unsigned long addr, unsigned long end) +static void identity_mapping_add(pgd_t *pgd, unsigned long addr, unsigned long end) { unsigned long prot, next; - prot = PMD_TYPE_SECT | PMD_SECT_AP_WRITE; + prot = PMD_TYPE_SECT | PMD_SECT_AP_WRITE | PMD_SECT_AF; if (cpu_architecture() <= CPU_ARCH_ARMv5TEJ && !cpu_is_xscale()) prot |= PMD_BIT4; @@ -43,48 +73,41 @@ void identity_mapping_add(pgd_t *pgd, unsigned long addr, unsigned long end) } while (pgd++, addr = next, addr != end); } -#ifdef CONFIG_SMP -static void idmap_del_pmd(pud_t *pud, unsigned long addr, unsigned long end) -{ - pmd_t *pmd = pmd_offset(pud, addr); - pmd_clear(pmd); -} +extern char __idmap_text_start[], __idmap_text_end[]; -static void idmap_del_pud(pgd_t *pgd, unsigned long addr, unsigned long end) +static int __init init_static_idmap(void) { - pud_t *pud = pud_offset(pgd, addr); - unsigned long next; + phys_addr_t idmap_start, idmap_end; - do { - next = pud_addr_end(addr, end); - idmap_del_pmd(pud, addr, next); - } while (pud++, addr = next, addr != end); -} + idmap_pgd = pgd_alloc(&init_mm); + if (!idmap_pgd) + return -ENOMEM; -void identity_mapping_del(pgd_t *pgd, unsigned long addr, unsigned long end) -{ - unsigned long next; + /* Add an identity mapping for the physical address of the section. */ + idmap_start = virt_to_phys((void *)__idmap_text_start); + idmap_end = virt_to_phys((void *)__idmap_text_end); - pgd += pgd_index(addr); - do { - next = pgd_addr_end(addr, end); - idmap_del_pud(pgd, addr, next); - } while (pgd++, addr = next, addr != end); + pr_info("Setting up static identity map for 0x%llx - 0x%llx\n", + (long long)idmap_start, (long long)idmap_end); + identity_mapping_add(idmap_pgd, idmap_start, idmap_end); + + return 0; } -#endif +early_initcall(init_static_idmap); /* - * In order to soft-boot, we need to insert a 1:1 mapping in place of - * the user-mode pages. This will then ensure that we have predictable - * results when turning the mmu off + * In order to soft-boot, we need to switch to a 1:1 mapping for the + * cpu_reset functions. This will then ensure that we have predictable + * results when turning off the mmu. */ -void setup_mm_for_reboot(char mode) +void setup_mm_for_reboot(void) { - /* - * We need to access to user-mode page tables here. For kernel threads - * we don't have any user-mode mappings so we use the context that we - * "borrowed". - */ - identity_mapping_add(current->active_mm->pgd, 0, TASK_SIZE); + /* Clean and invalidate L1. */ + flush_cache_all(); + + /* Switch to the identity mapping. */ + cpu_switch_mm(idmap_pgd, &init_mm); + + /* Flush the TLB. */ local_flush_tlb_all(); } diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c index 2fee782..e34ea8a 100644 --- a/arch/arm/mm/init.c +++ b/arch/arm/mm/init.c @@ -13,13 +13,13 @@ #include <linux/init.h> #include <linux/bootmem.h> #include <linux/mman.h> +#include <linux/export.h> #include <linux/nodemask.h> #include <linux/initrd.h> #include <linux/of_fdt.h> #include <linux/highmem.h> #include <linux/gfp.h> #include <linux/memblock.h> -#include <linux/sort.h> #include <asm/mach-types.h> #include <asm/prom.h> @@ -31,6 +31,7 @@ #include <asm/mach/arch.h> #include <asm/mach/map.h> +#include <asm/memblock.h> #include "mm.h" @@ -133,30 +134,18 @@ void show_mem(unsigned int filter) } static void __init find_limits(unsigned long *min, unsigned long *max_low, - unsigned long *max_high) + unsigned long *max_high) { struct meminfo *mi = &meminfo; int i; - *min = -1UL; - *max_low = *max_high = 0; - - for_each_bank (i, mi) { - struct membank *bank = &mi->bank[i]; - unsigned long start, end; - - start = bank_pfn_start(bank); - end = bank_pfn_end(bank); - - if (*min > start) - *min = start; - if (*max_high < end) - *max_high = end; - if (bank->highmem) - continue; - if (*max_low < end) - *max_low = end; - } + /* 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]); } static void __init arm_bootmem_init(unsigned long start_pfn, @@ -298,7 +287,7 @@ static void __init arm_bootmem_free(unsigned long min, unsigned long max_low, #ifdef CONFIG_HAVE_ARCH_PFN_VALID int pfn_valid(unsigned long pfn) { - return memblock_is_memory(pfn << PAGE_SHIFT); + return memblock_is_memory(__pfn_to_phys(pfn)); } EXPORT_SYMBOL(pfn_valid); #endif @@ -318,20 +307,10 @@ static void arm_memory_present(void) } #endif -static int __init meminfo_cmp(const void *_a, const void *_b) -{ - const struct membank *a = _a, *b = _b; - long cmp = bank_pfn_start(a) - bank_pfn_start(b); - return cmp < 0 ? -1 : cmp > 0 ? 1 : 0; -} - void __init arm_memblock_init(struct meminfo *mi, struct machine_desc *mdesc) { int i; - sort(&meminfo.bank, meminfo.nr_banks, sizeof(meminfo.bank[0]), meminfo_cmp, NULL); - - memblock_init(); for (i = 0; i < mi->nr_banks; i++) memblock_add(mi->bank[i].start, mi->bank[i].size); @@ -370,7 +349,7 @@ void __init arm_memblock_init(struct meminfo *mi, struct machine_desc *mdesc) if (mdesc->reserve) mdesc->reserve(); - memblock_analyze(); + memblock_allow_resize(); memblock_dump_all(); } @@ -402,8 +381,6 @@ void __init bootmem_init(void) */ arm_bootmem_free(min, max_low, max_high); - high_memory = __va(((phys_addr_t)max_low << PAGE_SHIFT) - 1) + 1; - /* * This doesn't seem to be used by the Linux memory manager any * more, but is used by ll_rw_block. If we can get rid of it, we @@ -441,7 +418,7 @@ static inline int free_area(unsigned long pfn, unsigned long end, char *s) static inline void poison_init_mem(void *s, size_t count) { u32 *p = (u32 *)s; - while ((count = count - 4)) + for (; count != 0; count -= 4) *p++ = 0xe7fddef0; } @@ -496,6 +473,13 @@ static void __init free_unused_memmap(struct meminfo *mi) */ bank_start = min(bank_start, ALIGN(prev_bank_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); #endif /* * If we had a previous bank, and there is a space @@ -653,9 +637,6 @@ void __init mem_init(void) " ITCM : 0x%08lx - 0x%08lx (%4ld kB)\n" #endif " fixmap : 0x%08lx - 0x%08lx (%4ld kB)\n" -#ifdef CONFIG_MMU - " DMA : 0x%08lx - 0x%08lx (%4ld MB)\n" -#endif " vmalloc : 0x%08lx - 0x%08lx (%4ld MB)\n" " lowmem : 0x%08lx - 0x%08lx (%4ld MB)\n" #ifdef CONFIG_HIGHMEM @@ -674,9 +655,6 @@ void __init mem_init(void) MLK(ITCM_OFFSET, (unsigned long) itcm_end), #endif MLK(FIXADDR_START, FIXADDR_TOP), -#ifdef CONFIG_MMU - MLM(CONSISTENT_BASE, CONSISTENT_END), -#endif MLM(VMALLOC_START, VMALLOC_END), MLM(PAGE_OFFSET, (unsigned long)high_memory), #ifdef CONFIG_HIGHMEM @@ -699,9 +677,6 @@ void __init mem_init(void) * be detected at build time already. */ #ifdef CONFIG_MMU - BUILD_BUG_ON(VMALLOC_END > CONSISTENT_BASE); - BUG_ON(VMALLOC_END > CONSISTENT_BASE); - BUILD_BUG_ON(TASK_SIZE > MODULES_VADDR); BUG_ON(TASK_SIZE > MODULES_VADDR); #endif diff --git a/arch/arm/mm/iomap.c b/arch/arm/mm/iomap.c index 430df1a..e62956e 100644 --- a/arch/arm/mm/iomap.c +++ b/arch/arm/mm/iomap.c @@ -35,27 +35,6 @@ EXPORT_SYMBOL(pcibios_min_mem); unsigned int pci_flags = PCI_REASSIGN_ALL_RSRC; EXPORT_SYMBOL(pci_flags); -void __iomem *pci_iomap(struct pci_dev *dev, int bar, unsigned long maxlen) -{ - resource_size_t start = pci_resource_start(dev, bar); - resource_size_t len = pci_resource_len(dev, bar); - unsigned long flags = pci_resource_flags(dev, bar); - - if (!len || !start) - return NULL; - if (maxlen && len > maxlen) - len = maxlen; - if (flags & IORESOURCE_IO) - return ioport_map(start, len); - if (flags & IORESOURCE_MEM) { - if (flags & IORESOURCE_CACHEABLE) - return ioremap(start, len); - return ioremap_nocache(start, len); - } - return NULL; -} -EXPORT_SYMBOL(pci_iomap); - void pci_iounmap(struct pci_dev *dev, void __iomem *addr) { if ((unsigned long)addr >= VMALLOC_START && diff --git a/arch/arm/mm/ioremap.c b/arch/arm/mm/ioremap.c index ab50627..80632e8 100644 --- a/arch/arm/mm/ioremap.c +++ b/arch/arm/mm/ioremap.c @@ -36,12 +36,6 @@ #include <asm/mach/map.h> #include "mm.h" -/* - * Used by ioremap() and iounmap() code to mark (super)section-mapped - * I/O regions in vm_struct->flags field. - */ -#define VM_ARM_SECTION_MAPPING 0x80000000 - int ioremap_page(unsigned long virt, unsigned long phys, const struct mem_type *mtype) { @@ -64,7 +58,7 @@ void __check_kvm_seq(struct mm_struct *mm) } while (seq != init_mm.context.kvm_seq); } -#ifndef CONFIG_SMP +#if !defined(CONFIG_SMP) && !defined(CONFIG_ARM_LPAE) /* * Section support is unsafe on SMP - If you iounmap and ioremap a region, * the other CPUs will not see this change until their next context switch. @@ -79,13 +73,16 @@ static void unmap_area_sections(unsigned long virt, unsigned long size) { unsigned long addr = virt, end = virt + (size & ~(SZ_1M - 1)); pgd_t *pgd; + pud_t *pud; + pmd_t *pmdp; flush_cache_vunmap(addr, end); pgd = pgd_offset_k(addr); + pud = pud_offset(pgd, addr); + pmdp = pmd_offset(pud, addr); do { - pmd_t pmd, *pmdp = pmd_offset(pgd, addr); + pmd_t pmd = *pmdp; - pmd = *pmdp; if (!pmd_none(pmd)) { /* * Clear the PMD from the page table, and @@ -104,8 +101,8 @@ static void unmap_area_sections(unsigned long virt, unsigned long size) pte_free_kernel(&init_mm, pmd_page_vaddr(pmd)); } - addr += PGDIR_SIZE; - pgd++; + addr += PMD_SIZE; + pmdp += 2; } while (addr < end); /* @@ -124,6 +121,8 @@ remap_area_sections(unsigned long virt, unsigned long pfn, { unsigned long addr = virt, end = virt + size; pgd_t *pgd; + pud_t *pud; + pmd_t *pmd; /* * Remove and free any PTE-based mapping, and @@ -132,17 +131,17 @@ remap_area_sections(unsigned long virt, unsigned long pfn, unmap_area_sections(virt, size); pgd = pgd_offset_k(addr); + pud = pud_offset(pgd, addr); + pmd = pmd_offset(pud, addr); do { - pmd_t *pmd = pmd_offset(pgd, addr); - pmd[0] = __pmd(__pfn_to_phys(pfn) | type->prot_sect); pfn += SZ_1M >> PAGE_SHIFT; pmd[1] = __pmd(__pfn_to_phys(pfn) | type->prot_sect); pfn += SZ_1M >> PAGE_SHIFT; flush_pmd_entry(pmd); - addr += PGDIR_SIZE; - pgd++; + addr += PMD_SIZE; + pmd += 2; } while (addr < end); return 0; @@ -154,6 +153,8 @@ remap_area_supersections(unsigned long virt, unsigned long pfn, { unsigned long addr = virt, end = virt + size; pgd_t *pgd; + pud_t *pud; + pmd_t *pmd; /* * Remove and free any PTE-based mapping, and @@ -162,6 +163,8 @@ remap_area_supersections(unsigned long virt, unsigned long pfn, unmap_area_sections(virt, size); pgd = pgd_offset_k(virt); + pud = pud_offset(pgd, addr); + pmd = pmd_offset(pud, addr); do { unsigned long super_pmd_val, i; @@ -170,14 +173,12 @@ remap_area_supersections(unsigned long virt, unsigned long pfn, super_pmd_val |= ((pfn >> (32 - PAGE_SHIFT)) & 0xf) << 20; for (i = 0; i < 8; i++) { - pmd_t *pmd = pmd_offset(pgd, addr); - pmd[0] = __pmd(super_pmd_val); pmd[1] = __pmd(super_pmd_val); flush_pmd_entry(pmd); - addr += PGDIR_SIZE; - pgd++; + addr += PMD_SIZE; + pmd += 2; } pfn += SUPERSECTION_SIZE >> PAGE_SHIFT; @@ -195,17 +196,13 @@ void __iomem * __arm_ioremap_pfn_caller(unsigned long pfn, unsigned long addr; struct vm_struct * area; +#ifndef CONFIG_ARM_LPAE /* * High mappings must be supersection aligned */ if (pfn >= 0x100000 && (__pfn_to_phys(pfn) & ~SUPERSECTION_MASK)) return NULL; - - /* - * Don't allow RAM to be mapped - this causes problems with ARMv6+ - */ - if (WARN_ON(pfn_valid(pfn))) - return NULL; +#endif type = get_mem_type(mtype); if (!type) @@ -216,12 +213,40 @@ void __iomem * __arm_ioremap_pfn_caller(unsigned long pfn, */ size = PAGE_ALIGN(offset + size); + /* + * Try to reuse one of the static mapping whenever possible. + */ + read_lock(&vmlist_lock); + for (area = vmlist; area; area = area->next) { + if (!size || (sizeof(phys_addr_t) == 4 && pfn >= 0x100000)) + break; + if (!(area->flags & VM_ARM_STATIC_MAPPING)) + continue; + if ((area->flags & VM_ARM_MTYPE_MASK) != VM_ARM_MTYPE(mtype)) + continue; + if (__phys_to_pfn(area->phys_addr) > pfn || + __pfn_to_phys(pfn) + size-1 > area->phys_addr + area->size-1) + continue; + /* we can drop the lock here as we know *area is static */ + read_unlock(&vmlist_lock); + addr = (unsigned long)area->addr; + addr += __pfn_to_phys(pfn) - area->phys_addr; + return (void __iomem *) (offset + addr); + } + read_unlock(&vmlist_lock); + + /* + * Don't allow RAM to be mapped - this causes problems with ARMv6+ + */ + if (WARN_ON(pfn_valid(pfn))) + return NULL; + area = get_vm_area_caller(size, VM_IOREMAP, caller); if (!area) return NULL; addr = (unsigned long)area->addr; -#ifndef CONFIG_SMP +#if !defined(CONFIG_SMP) && !defined(CONFIG_ARM_LPAE) if (DOMAIN_IO == 0 && (((cpu_architecture() >= CPU_ARCH_ARMv6) && (get_cr() & CR_XP)) || cpu_is_xsc3()) && pfn >= 0x100000 && @@ -289,31 +314,58 @@ __arm_ioremap(unsigned long phys_addr, size_t size, unsigned int mtype) } EXPORT_SYMBOL(__arm_ioremap); +/* + * Remap an arbitrary physical address space into the kernel virtual + * address space as memory. Needed when the kernel wants to execute + * code in external memory. This is needed for reprogramming source + * clocks that would affect normal memory for example. Please see + * CONFIG_GENERIC_ALLOCATOR for allocating external memory. + */ +void __iomem * +__arm_ioremap_exec(unsigned long phys_addr, size_t size, bool cached) +{ + unsigned int mtype; + + if (cached) + mtype = MT_MEMORY; + else + mtype = MT_MEMORY_NONCACHED; + + return __arm_ioremap_caller(phys_addr, size, mtype, + __builtin_return_address(0)); +} + void __iounmap(volatile void __iomem *io_addr) { void *addr = (void *)(PAGE_MASK & (unsigned long)io_addr); -#ifndef CONFIG_SMP - struct vm_struct **p, *tmp; + struct vm_struct *vm; - /* - * If this is a section based mapping we need to handle it - * specially as the VM subsystem does not know how to handle - * such a beast. We need the lock here b/c we need to clear - * all the mappings before the area can be reclaimed - * by someone else. - */ - write_lock(&vmlist_lock); - for (p = &vmlist ; (tmp = *p) ; p = &tmp->next) { - if ((tmp->flags & VM_IOREMAP) && (tmp->addr == addr)) { - if (tmp->flags & VM_ARM_SECTION_MAPPING) { - unmap_area_sections((unsigned long)tmp->addr, - tmp->size); - } + read_lock(&vmlist_lock); + for (vm = vmlist; vm; vm = vm->next) { + if (vm->addr > addr) + break; + if (!(vm->flags & VM_IOREMAP)) + continue; + /* If this is a static mapping we must leave it alone */ + if ((vm->flags & VM_ARM_STATIC_MAPPING) && + (vm->addr <= addr) && (vm->addr + vm->size > addr)) { + read_unlock(&vmlist_lock); + return; + } +#if !defined(CONFIG_SMP) && !defined(CONFIG_ARM_LPAE) + /* + * If this is a section based mapping we need to handle it + * specially as the VM subsystem does not know how to handle + * such a beast. + */ + if ((vm->addr == addr) && + (vm->flags & VM_ARM_SECTION_MAPPING)) { + unmap_area_sections((unsigned long)vm->addr, vm->size); break; } - } - write_unlock(&vmlist_lock); #endif + } + read_unlock(&vmlist_lock); vunmap(addr); } diff --git a/arch/arm/mm/mm.h b/arch/arm/mm/mm.h index 0105667..70f6d3ea 100644 --- a/arch/arm/mm/mm.h +++ b/arch/arm/mm/mm.h @@ -12,8 +12,8 @@ static inline pmd_t *pmd_off_k(unsigned long virt) struct mem_type { pteval_t prot_pte; - unsigned int prot_l1; - unsigned int prot_sect; + pmdval_t prot_l1; + pmdval_t prot_sect; unsigned int domain; }; @@ -21,6 +21,20 @@ const struct mem_type *get_mem_type(unsigned int type); extern void __flush_dcache_page(struct address_space *mapping, struct page *page); +/* + * ARM specific vm_struct->flags bits. + */ + +/* (super)section-mapped I/O regions used by ioremap()/iounmap() */ +#define VM_ARM_SECTION_MAPPING 0x80000000 + +/* permanent static mappings from iotable_init() */ +#define VM_ARM_STATIC_MAPPING 0x40000000 + +/* mapping type (attributes) for permanent static mappings */ +#define VM_ARM_MTYPE(mt) ((mt) << 20) +#define VM_ARM_MTYPE_MASK (0x1f << 20) + #endif #ifdef CONFIG_ZONE_DMA diff --git a/arch/arm/mm/mmap.c b/arch/arm/mm/mmap.c index 74be05f..ce8cb19 100644 --- a/arch/arm/mm/mmap.c +++ b/arch/arm/mm/mmap.c @@ -9,13 +9,51 @@ #include <linux/io.h> #include <linux/personality.h> #include <linux/random.h> -#include <asm/cputype.h> -#include <asm/system.h> +#include <asm/cachetype.h> + +static inline unsigned long COLOUR_ALIGN_DOWN(unsigned long addr, + unsigned long pgoff) +{ + unsigned long base = addr & ~(SHMLBA-1); + unsigned long off = (pgoff << PAGE_SHIFT) & (SHMLBA-1); + + if (base + off <= addr) + return base + off; + + return base - off; +} #define COLOUR_ALIGN(addr,pgoff) \ ((((addr)+SHMLBA-1)&~(SHMLBA-1)) + \ (((pgoff)<<PAGE_SHIFT) & (SHMLBA-1))) +/* gap between mmap and stack */ +#define MIN_GAP (128*1024*1024UL) +#define MAX_GAP ((TASK_SIZE)/6*5) + +static int mmap_is_legacy(void) +{ + if (current->personality & ADDR_COMPAT_LAYOUT) + return 1; + + if (rlimit(RLIMIT_STACK) == RLIM_INFINITY) + return 1; + + return sysctl_legacy_va_layout; +} + +static unsigned long mmap_base(unsigned long rnd) +{ + unsigned long gap = rlimit(RLIMIT_STACK); + + if (gap < MIN_GAP) + gap = MIN_GAP; + else if (gap > MAX_GAP) + gap = MAX_GAP; + + return PAGE_ALIGN(TASK_SIZE - gap - rnd); +} + /* * We need to ensure that shared mappings are correctly aligned to * avoid aliasing issues with VIPT caches. We need to ensure that @@ -32,25 +70,15 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr, struct mm_struct *mm = current->mm; struct vm_area_struct *vma; unsigned long start_addr; -#if defined(CONFIG_CPU_V6) || defined(CONFIG_CPU_V6K) - unsigned int cache_type; - int do_align = 0, aliasing = 0; + int do_align = 0; + int aliasing = cache_is_vipt_aliasing(); /* * We only need to do colour alignment if either the I or D - * caches alias. This is indicated by bits 9 and 21 of the - * cache type register. + * caches alias. */ - cache_type = read_cpuid_cachetype(); - if (cache_type != read_cpuid_id()) { - aliasing = (cache_type | cache_type >> 12) & (1 << 11); - if (aliasing) - do_align = filp || flags & MAP_SHARED; - } -#else -#define do_align 0 -#define aliasing 0 -#endif + if (aliasing) + do_align = filp || (flags & MAP_SHARED); /* * We enforce the MAP_FIXED case. @@ -79,13 +107,9 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr, if (len > mm->cached_hole_size) { start_addr = addr = mm->free_area_cache; } else { - start_addr = addr = TASK_UNMAPPED_BASE; + start_addr = addr = mm->mmap_base; mm->cached_hole_size = 0; } - /* 8 bits of randomness in 20 address space bits */ - if ((current->flags & PF_RANDOMIZE) && - !(current->personality & ADDR_NO_RANDOMIZE)) - addr += (get_random_int() % (1 << 8)) << PAGE_SHIFT; full_search: if (do_align) @@ -122,6 +146,134 @@ full_search: } } +unsigned long +arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, + const unsigned long len, const unsigned long pgoff, + const unsigned long flags) +{ + struct vm_area_struct *vma; + struct mm_struct *mm = current->mm; + unsigned long addr = addr0; + int do_align = 0; + int aliasing = cache_is_vipt_aliasing(); + + /* + * We only need to do colour alignment if either the I or D + * caches alias. + */ + if (aliasing) + do_align = filp || (flags & MAP_SHARED); + + /* requested length too big for entire address space */ + if (len > TASK_SIZE) + return -ENOMEM; + + if (flags & MAP_FIXED) { + if (aliasing && flags & MAP_SHARED && + (addr - (pgoff << PAGE_SHIFT)) & (SHMLBA - 1)) + return -EINVAL; + return addr; + } + + /* requesting a specific address */ + if (addr) { + if (do_align) + addr = COLOUR_ALIGN(addr, pgoff); + else + addr = PAGE_ALIGN(addr); + vma = find_vma(mm, addr); + if (TASK_SIZE - len >= addr && + (!vma || addr + len <= vma->vm_start)) + return addr; + } + + /* check if free_area_cache is useful for us */ + if (len <= mm->cached_hole_size) { + mm->cached_hole_size = 0; + mm->free_area_cache = mm->mmap_base; + } + + /* either no address requested or can't fit in requested address hole */ + addr = mm->free_area_cache; + if (do_align) { + unsigned long base = COLOUR_ALIGN_DOWN(addr - len, pgoff); + addr = base + len; + } + + /* make sure it can fit in the remaining address space */ + if (addr > len) { + vma = find_vma(mm, addr-len); + if (!vma || addr <= vma->vm_start) + /* remember the address as a hint for next time */ + return (mm->free_area_cache = addr-len); + } + + if (mm->mmap_base < len) + goto bottomup; + + addr = mm->mmap_base - len; + if (do_align) + addr = COLOUR_ALIGN_DOWN(addr, pgoff); + + do { + /* + * Lookup failure means no vma is above this address, + * else if new region fits below vma->vm_start, + * return with success: + */ + vma = find_vma(mm, addr); + if (!vma || addr+len <= vma->vm_start) + /* remember the address as a hint for next time */ + return (mm->free_area_cache = addr); + + /* remember the largest hole we saw so far */ + if (addr + mm->cached_hole_size < vma->vm_start) + mm->cached_hole_size = vma->vm_start - addr; + + /* try just below the current vma->vm_start */ + addr = vma->vm_start - len; + if (do_align) + addr = COLOUR_ALIGN_DOWN(addr, pgoff); + } while (len < vma->vm_start); + +bottomup: + /* + * A failed mmap() very likely causes application failure, + * so fall back to the bottom-up function here. This scenario + * can happen with large stack limits and large mmap() + * allocations. + */ + mm->cached_hole_size = ~0UL; + mm->free_area_cache = TASK_UNMAPPED_BASE; + addr = arch_get_unmapped_area(filp, addr0, len, pgoff, flags); + /* + * Restore the topdown base: + */ + mm->free_area_cache = mm->mmap_base; + mm->cached_hole_size = ~0UL; + + return addr; +} + +void arch_pick_mmap_layout(struct mm_struct *mm) +{ + unsigned long random_factor = 0UL; + + /* 8 bits of randomness in 20 address space bits */ + if ((current->flags & PF_RANDOMIZE) && + !(current->personality & ADDR_NO_RANDOMIZE)) + random_factor = (get_random_int() % (1 << 8)) << PAGE_SHIFT; + + if (mmap_is_legacy()) { + mm->mmap_base = TASK_UNMAPPED_BASE + random_factor; + mm->get_unmapped_area = arch_get_unmapped_area; + mm->unmap_area = arch_unmap_area; + } else { + mm->mmap_base = mmap_base(random_factor); + mm->get_unmapped_area = arch_get_unmapped_area_topdown; + mm->unmap_area = arch_unmap_area_topdown; + } +} /* * You really shouldn't be using read() or write() on /dev/mem. This diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c index 594d677..94c5a0c 100644 --- a/arch/arm/mm/mmu.c +++ b/arch/arm/mm/mmu.c @@ -15,6 +15,7 @@ #include <linux/nodemask.h> #include <linux/memblock.h> #include <linux/fs.h> +#include <linux/vmalloc.h> #include <asm/cputype.h> #include <asm/sections.h> @@ -60,7 +61,7 @@ EXPORT_SYMBOL(pgprot_kernel); struct cachepolicy { const char policy[16]; unsigned int cr_mask; - unsigned int pmd; + pmdval_t pmd; pteval_t pte; }; @@ -150,6 +151,7 @@ static int __init early_nowrite(char *__unused) } early_param("nowb", early_nowrite); +#ifndef CONFIG_ARM_LPAE static int __init early_ecc(char *p) { if (memcmp(p, "on", 2) == 0) @@ -159,6 +161,7 @@ static int __init early_ecc(char *p) return 0; } early_param("ecc", early_ecc); +#endif static int __init noalign_setup(char *__unused) { @@ -228,10 +231,12 @@ static struct mem_type mem_types[] = { .prot_sect = PMD_TYPE_SECT | PMD_SECT_XN, .domain = DOMAIN_KERNEL, }, +#ifndef CONFIG_ARM_LPAE [MT_MINICLEAN] = { .prot_sect = PMD_TYPE_SECT | PMD_SECT_XN | PMD_SECT_MINICACHE, .domain = DOMAIN_KERNEL, }, +#endif [MT_LOW_VECTORS] = { .prot_pte = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY | L_PTE_RDONLY, @@ -273,6 +278,14 @@ static struct mem_type mem_types[] = { .prot_l1 = PMD_TYPE_TABLE, .domain = DOMAIN_KERNEL, }, + [MT_MEMORY_SO] = { + .prot_pte = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY | + L_PTE_MT_UNCACHED, + .prot_l1 = PMD_TYPE_TABLE, + .prot_sect = PMD_TYPE_SECT | PMD_SECT_AP_WRITE | PMD_SECT_S | + PMD_SECT_UNCACHED | PMD_SECT_XN, + .domain = DOMAIN_KERNEL, + }, }; const struct mem_type *get_mem_type(unsigned int type) @@ -288,7 +301,7 @@ static void __init build_mem_type_table(void) { struct cachepolicy *cp; unsigned int cr = get_cr(); - unsigned int user_pgprot, kern_pgprot, vecs_pgprot; + pteval_t user_pgprot, kern_pgprot, vecs_pgprot; int cpu_arch = cpu_architecture(); int i; @@ -421,6 +434,7 @@ static void __init build_mem_type_table(void) * ARMv6 and above have extended page tables. */ if (cpu_arch >= CPU_ARCH_ARMv6 && (cr & CR_XP)) { +#ifndef CONFIG_ARM_LPAE /* * Mark cache clean areas and XIP ROM read only * from SVC mode and no access from userspace. @@ -428,6 +442,7 @@ static void __init build_mem_type_table(void) mem_types[MT_ROM].prot_sect |= PMD_SECT_APX|PMD_SECT_AP_WRITE; mem_types[MT_MINICLEAN].prot_sect |= PMD_SECT_APX|PMD_SECT_AP_WRITE; mem_types[MT_CACHECLEAN].prot_sect |= PMD_SECT_APX|PMD_SECT_AP_WRITE; +#endif if (is_smp()) { /* @@ -466,6 +481,18 @@ static void __init build_mem_type_table(void) mem_types[MT_MEMORY_NONCACHED].prot_sect |= PMD_SECT_BUFFERABLE; } +#ifdef CONFIG_ARM_LPAE + /* + * Do not generate access flag faults for the kernel mappings. + */ + for (i = 0; i < ARRAY_SIZE(mem_types); i++) { + mem_types[i].prot_pte |= PTE_EXT_AF; + mem_types[i].prot_sect |= PMD_SECT_AF; + } + kern_pgprot |= PTE_EXT_AF; + vecs_pgprot |= PTE_EXT_AF; +#endif + for (i = 0; i < 16; i++) { unsigned long v = pgprot_val(protection_map[i]); protection_map[i] = __pgprot(v | user_pgprot); @@ -521,13 +548,18 @@ EXPORT_SYMBOL(phys_mem_access_prot); #define vectors_base() (vectors_high() ? 0xffff0000 : 0) -static void __init *early_alloc(unsigned long sz) +static void __init *early_alloc_aligned(unsigned long sz, unsigned long align) { - void *ptr = __va(memblock_alloc(sz, sz)); + void *ptr = __va(memblock_alloc(sz, align)); memset(ptr, 0, sz); return ptr; } +static void __init *early_alloc(unsigned long sz) +{ + return early_alloc_aligned(sz, sz); +} + static pte_t * __init early_pte_alloc(pmd_t *pmd, unsigned long addr, unsigned long prot) { if (pmd_none(*pmd)) { @@ -564,8 +596,10 @@ static void __init alloc_init_section(pud_t *pud, unsigned long addr, if (((addr | end | phys) & ~SECTION_MASK) == 0) { pmd_t *p = pmd; +#ifndef CONFIG_ARM_LPAE if (addr & SECTION_SIZE) pmd++; +#endif do { *pmd = __pmd(phys | type->prot_sect); @@ -595,6 +629,7 @@ static void alloc_init_pud(pgd_t *pgd, unsigned long addr, unsigned long end, } while (pud++, addr = next, addr != end); } +#ifndef CONFIG_ARM_LPAE static void __init create_36bit_mapping(struct map_desc *md, const struct mem_type *type) { @@ -654,6 +689,7 @@ static void __init create_36bit_mapping(struct map_desc *md, pgd += SUPERSECTION_SIZE >> PGDIR_SHIFT; } while (addr != end); } +#endif /* !CONFIG_ARM_LPAE */ /* * Create the page directory entries and any necessary @@ -677,14 +713,16 @@ static void __init create_mapping(struct map_desc *md) } if ((md->type == MT_DEVICE || md->type == MT_ROM) && - md->virtual >= PAGE_OFFSET && md->virtual < VMALLOC_END) { + md->virtual >= PAGE_OFFSET && + (md->virtual < VMALLOC_START || md->virtual >= VMALLOC_END)) { printk(KERN_WARNING "BUG: mapping for 0x%08llx" - " at 0x%08lx overlaps vmalloc space\n", + " at 0x%08lx out of vmalloc space\n", (long long)__pfn_to_phys((u64)md->pfn), md->virtual); } type = &mem_types[md->type]; +#ifndef CONFIG_ARM_LPAE /* * Catch 36-bit addresses */ @@ -692,6 +730,7 @@ static void __init create_mapping(struct map_desc *md) create_36bit_mapping(md, type); return; } +#endif addr = md->virtual & PAGE_MASK; phys = __pfn_to_phys(md->pfn); @@ -721,18 +760,33 @@ static void __init create_mapping(struct map_desc *md) */ void __init iotable_init(struct map_desc *io_desc, int nr) { - int i; + struct map_desc *md; + struct vm_struct *vm; - for (i = 0; i < nr; i++) - create_mapping(io_desc + i); + if (!nr) + return; + + vm = early_alloc_aligned(sizeof(*vm) * nr, __alignof__(*vm)); + + for (md = io_desc; nr; md++, nr--) { + create_mapping(md); + vm->addr = (void *)(md->virtual & PAGE_MASK); + vm->size = PAGE_ALIGN(md->length + (md->virtual & ~PAGE_MASK)); + vm->phys_addr = __pfn_to_phys(md->pfn); + vm->flags = VM_IOREMAP | VM_ARM_STATIC_MAPPING; + vm->flags |= VM_ARM_MTYPE(md->type); + vm->caller = iotable_init; + vm_area_add_early(vm++); + } } -static void * __initdata vmalloc_min = (void *)(VMALLOC_END - SZ_128M); +static void * __initdata vmalloc_min = + (void *)(VMALLOC_END - (240 << 20) - VMALLOC_OFFSET); /* * vmalloc=size forces the vmalloc area to be exactly 'size' * bytes. This can be used to increase (or decrease) the vmalloc - * area - the default is 128m. + * area - the default is 240m. */ static int __init early_vmalloc(char *arg) { @@ -767,6 +821,9 @@ void __init sanity_check_meminfo(void) struct membank *bank = &meminfo.bank[j]; *bank = meminfo.bank[i]; + if (bank->start > ULONG_MAX) + highmem = 1; + #ifdef CONFIG_HIGHMEM if (__va(bank->start) >= vmalloc_min || __va(bank->start) < (void *)PAGE_OFFSET) @@ -778,7 +835,7 @@ void __init sanity_check_meminfo(void) * Split those memory banks which are partially overlapping * the vmalloc area greatly simplifying things later. */ - if (__va(bank->start) < vmalloc_min && + if (!highmem && __va(bank->start) < vmalloc_min && bank->size > vmalloc_min - __va(bank->start)) { if (meminfo.nr_banks >= NR_BANKS) { printk(KERN_CRIT "NR_BANKS too low, " @@ -799,6 +856,17 @@ void __init sanity_check_meminfo(void) bank->highmem = highmem; /* + * 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 entirely overlap * the vmalloc area. */ @@ -852,6 +920,7 @@ void __init sanity_check_meminfo(void) } #endif meminfo.nr_banks = j; + high_memory = __va(lowmem_limit - 1) + 1; memblock_set_current_limit(lowmem_limit); } @@ -863,14 +932,14 @@ static inline void prepare_page_table(void) /* * Clear out all the mappings below the kernel image. */ - for (addr = 0; addr < MODULES_VADDR; addr += PGDIR_SIZE) + for (addr = 0; addr < MODULES_VADDR; addr += PMD_SIZE) pmd_clear(pmd_off_k(addr)); #ifdef CONFIG_XIP_KERNEL /* The XIP kernel is mapped in the module area -- skip over it */ - addr = ((unsigned long)_etext + PGDIR_SIZE - 1) & PGDIR_MASK; + addr = ((unsigned long)_etext + PMD_SIZE - 1) & PMD_MASK; #endif - for ( ; addr < PAGE_OFFSET; addr += PGDIR_SIZE) + for ( ; addr < PAGE_OFFSET; addr += PMD_SIZE) pmd_clear(pmd_off_k(addr)); /* @@ -882,13 +951,21 @@ static inline void prepare_page_table(void) /* * Clear out all the kernel space mappings, except for the first - * memory bank, up to the end of the vmalloc region. + * memory bank, up to the vmalloc region. */ for (addr = __phys_to_virt(end); - addr < VMALLOC_END; addr += PGDIR_SIZE) + addr < VMALLOC_START; addr += PMD_SIZE) pmd_clear(pmd_off_k(addr)); } +#ifdef CONFIG_ARM_LPAE +/* the first page is reserved for pgd */ +#define SWAPPER_PG_DIR_SIZE (PAGE_SIZE + \ + PTRS_PER_PGD * PTRS_PER_PMD * sizeof(pmd_t)) +#else +#define SWAPPER_PG_DIR_SIZE (PTRS_PER_PGD * sizeof(pgd_t)) +#endif + /* * Reserve the special regions of memory */ @@ -898,7 +975,7 @@ void __init arm_mm_memblock_reserve(void) * Reserve the page tables. These are already in use, * and can only be in node 0. */ - memblock_reserve(__pa(swapper_pg_dir), PTRS_PER_PGD * sizeof(pgd_t)); + memblock_reserve(__pa(swapper_pg_dir), SWAPPER_PG_DIR_SIZE); #ifdef CONFIG_SA1111 /* @@ -910,8 +987,8 @@ void __init arm_mm_memblock_reserve(void) } /* - * Set up device the mappings. Since we clear out the page tables for all - * mappings above VMALLOC_END, we will remove any debug device mappings. + * Set up the device mappings. Since we clear out the page tables for all + * mappings above VMALLOC_START, we will remove any debug device mappings. * This means you have to be careful how you debug this function, or any * called function. This means you can't use any function or debugging * method which may touch any device, otherwise the kernel _will_ crash. @@ -926,7 +1003,7 @@ static void __init devicemaps_init(struct machine_desc *mdesc) */ vectors_page = early_alloc(PAGE_SIZE); - for (addr = VMALLOC_END; addr; addr += PGDIR_SIZE) + for (addr = VMALLOC_START; addr; addr += PMD_SIZE) pmd_clear(pmd_off_k(addr)); /* diff --git a/arch/arm/mm/nommu.c b/arch/arm/mm/nommu.c index 941a98c..4fc6794 100644 --- a/arch/arm/mm/nommu.c +++ b/arch/arm/mm/nommu.c @@ -29,6 +29,8 @@ void __init arm_mm_memblock_reserve(void) void __init sanity_check_meminfo(void) { + phys_addr_t end = bank_phys_end(&meminfo.bank[meminfo.nr_banks - 1]); + high_memory = __va(end - 1) + 1; } /* @@ -43,7 +45,7 @@ void __init paging_init(struct machine_desc *mdesc) /* * We don't need to do anything here for nommu machines. */ -void setup_mm_for_reboot(char mode) +void setup_mm_for_reboot(void) { } diff --git a/arch/arm/mm/pgd.c b/arch/arm/mm/pgd.c index b2027c1..a3e78cc 100644 --- a/arch/arm/mm/pgd.c +++ b/arch/arm/mm/pgd.c @@ -10,6 +10,7 @@ #include <linux/mm.h> #include <linux/gfp.h> #include <linux/highmem.h> +#include <linux/slab.h> #include <asm/pgalloc.h> #include <asm/page.h> @@ -17,6 +18,14 @@ #include "mm.h" +#ifdef CONFIG_ARM_LPAE +#define __pgd_alloc() kmalloc(PTRS_PER_PGD * sizeof(pgd_t), GFP_KERNEL) +#define __pgd_free(pgd) kfree(pgd) +#else +#define __pgd_alloc() (pgd_t *)__get_free_pages(GFP_KERNEL, 2) +#define __pgd_free(pgd) free_pages((unsigned long)pgd, 2) +#endif + /* * need to get a 16k page for level 1 */ @@ -27,7 +36,7 @@ pgd_t *pgd_alloc(struct mm_struct *mm) pmd_t *new_pmd, *init_pmd; pte_t *new_pte, *init_pte; - new_pgd = (pgd_t *)__get_free_pages(GFP_KERNEL, 2); + new_pgd = __pgd_alloc(); if (!new_pgd) goto no_pgd; @@ -42,10 +51,25 @@ pgd_t *pgd_alloc(struct mm_struct *mm) clean_dcache_area(new_pgd, PTRS_PER_PGD * sizeof(pgd_t)); +#ifdef CONFIG_ARM_LPAE + /* + * Allocate PMD table for modules and pkmap mappings. + */ + new_pud = pud_alloc(mm, new_pgd + pgd_index(MODULES_VADDR), + MODULES_VADDR); + if (!new_pud) + goto no_pud; + + new_pmd = pmd_alloc(mm, new_pud, 0); + if (!new_pmd) + goto no_pmd; +#endif + if (!vectors_high()) { /* * On ARM, first page must always be allocated since it - * contains the machine vectors. + * contains the machine vectors. The vectors are always high + * with LPAE. */ new_pud = pud_alloc(mm, new_pgd, 0); if (!new_pud) @@ -74,7 +98,7 @@ no_pte: no_pmd: pud_free(mm, new_pud); no_pud: - free_pages((unsigned long)new_pgd, 2); + __pgd_free(new_pgd); no_pgd: return NULL; } @@ -111,5 +135,24 @@ no_pud: pgd_clear(pgd); pud_free(mm, pud); no_pgd: - free_pages((unsigned long) pgd_base, 2); +#ifdef CONFIG_ARM_LPAE + /* + * Free modules/pkmap or identity pmd tables. + */ + for (pgd = pgd_base; pgd < pgd_base + PTRS_PER_PGD; pgd++) { + if (pgd_none_or_clear_bad(pgd)) + continue; + if (pgd_val(*pgd) & L_PGD_SWAPPER) + continue; + pud = pud_offset(pgd, 0); + if (pud_none_or_clear_bad(pud)) + continue; + pmd = pmd_offset(pud, 0); + pud_clear(pud); + pmd_free(mm, pmd); + pgd_clear(pgd); + pud_free(mm, pud); + } +#endif + __pgd_free(pgd_base); } diff --git a/arch/arm/mm/proc-arm1020.S b/arch/arm/mm/proc-arm1020.S index 6746966..2349513 100644 --- a/arch/arm/mm/proc-arm1020.S +++ b/arch/arm/mm/proc-arm1020.S @@ -95,6 +95,7 @@ ENTRY(cpu_arm1020_proc_fin) * loc: location to jump to for soft reset */ .align 5 + .pushsection .idmap.text, "ax" ENTRY(cpu_arm1020_reset) mov ip, #0 mcr p15, 0, ip, c7, c7, 0 @ invalidate I,D caches @@ -107,6 +108,8 @@ ENTRY(cpu_arm1020_reset) bic ip, ip, #0x1100 @ ...i...s........ mcr p15, 0, ip, c1, c0, 0 @ ctrl register mov pc, r0 +ENDPROC(cpu_arm1020_reset) + .popsection /* * cpu_arm1020_do_idle() diff --git a/arch/arm/mm/proc-arm1020e.S b/arch/arm/mm/proc-arm1020e.S index 4251421..c244b06 100644 --- a/arch/arm/mm/proc-arm1020e.S +++ b/arch/arm/mm/proc-arm1020e.S @@ -95,6 +95,7 @@ ENTRY(cpu_arm1020e_proc_fin) * loc: location to jump to for soft reset */ .align 5 + .pushsection .idmap.text, "ax" ENTRY(cpu_arm1020e_reset) mov ip, #0 mcr p15, 0, ip, c7, c7, 0 @ invalidate I,D caches @@ -107,6 +108,8 @@ ENTRY(cpu_arm1020e_reset) bic ip, ip, #0x1100 @ ...i...s........ mcr p15, 0, ip, c1, c0, 0 @ ctrl register mov pc, r0 +ENDPROC(cpu_arm1020e_reset) + .popsection /* * cpu_arm1020e_do_idle() diff --git a/arch/arm/mm/proc-arm1022.S b/arch/arm/mm/proc-arm1022.S index d283cf3..38fe22e 100644 --- a/arch/arm/mm/proc-arm1022.S +++ b/arch/arm/mm/proc-arm1022.S @@ -84,6 +84,7 @@ ENTRY(cpu_arm1022_proc_fin) * loc: location to jump to for soft reset */ .align 5 + .pushsection .idmap.text, "ax" ENTRY(cpu_arm1022_reset) mov ip, #0 mcr p15, 0, ip, c7, c7, 0 @ invalidate I,D caches @@ -96,6 +97,8 @@ ENTRY(cpu_arm1022_reset) bic ip, ip, #0x1100 @ ...i...s........ mcr p15, 0, ip, c1, c0, 0 @ ctrl register mov pc, r0 +ENDPROC(cpu_arm1022_reset) + .popsection /* * cpu_arm1022_do_idle() diff --git a/arch/arm/mm/proc-arm1026.S b/arch/arm/mm/proc-arm1026.S index 678a1ce..3eb9c3c 100644 --- a/arch/arm/mm/proc-arm1026.S +++ b/arch/arm/mm/proc-arm1026.S @@ -84,6 +84,7 @@ ENTRY(cpu_arm1026_proc_fin) * loc: location to jump to for soft reset */ .align 5 + .pushsection .idmap.text, "ax" ENTRY(cpu_arm1026_reset) mov ip, #0 mcr p15, 0, ip, c7, c7, 0 @ invalidate I,D caches @@ -96,6 +97,8 @@ ENTRY(cpu_arm1026_reset) bic ip, ip, #0x1100 @ ...i...s........ mcr p15, 0, ip, c1, c0, 0 @ ctrl register mov pc, r0 +ENDPROC(cpu_arm1026_reset) + .popsection /* * cpu_arm1026_do_idle() diff --git a/arch/arm/mm/proc-arm6_7.S b/arch/arm/mm/proc-arm6_7.S index e5b974c..4fbeb5b 100644 --- a/arch/arm/mm/proc-arm6_7.S +++ b/arch/arm/mm/proc-arm6_7.S @@ -225,6 +225,7 @@ ENTRY(cpu_arm7_set_pte_ext) * Params : r0 = address to jump to * Notes : This sets up everything for a reset */ + .pushsection .idmap.text, "ax" ENTRY(cpu_arm6_reset) ENTRY(cpu_arm7_reset) mov r1, #0 @@ -235,6 +236,9 @@ ENTRY(cpu_arm7_reset) mov r1, #0x30 mcr p15, 0, r1, c1, c0, 0 @ turn off MMU etc mov pc, r0 +ENDPROC(cpu_arm6_reset) +ENDPROC(cpu_arm7_reset) + .popsection __CPUINIT diff --git a/arch/arm/mm/proc-arm720.S b/arch/arm/mm/proc-arm720.S index 55f4e29..0ac908c 100644 --- a/arch/arm/mm/proc-arm720.S +++ b/arch/arm/mm/proc-arm720.S @@ -101,6 +101,7 @@ ENTRY(cpu_arm720_set_pte_ext) * Params : r0 = address to jump to * Notes : This sets up everything for a reset */ + .pushsection .idmap.text, "ax" ENTRY(cpu_arm720_reset) mov ip, #0 mcr p15, 0, ip, c7, c7, 0 @ invalidate cache @@ -112,6 +113,8 @@ ENTRY(cpu_arm720_reset) bic ip, ip, #0x2100 @ ..v....s........ mcr p15, 0, ip, c1, c0, 0 @ ctrl register mov pc, r0 +ENDPROC(cpu_arm720_reset) + .popsection __CPUINIT diff --git a/arch/arm/mm/proc-arm740.S b/arch/arm/mm/proc-arm740.S index 4506be3..dc5de5d 100644 --- a/arch/arm/mm/proc-arm740.S +++ b/arch/arm/mm/proc-arm740.S @@ -49,6 +49,7 @@ ENTRY(cpu_arm740_proc_fin) * Params : r0 = address to jump to * Notes : This sets up everything for a reset */ + .pushsection .idmap.text, "ax" ENTRY(cpu_arm740_reset) mov ip, #0 mcr p15, 0, ip, c7, c0, 0 @ invalidate cache @@ -56,6 +57,8 @@ ENTRY(cpu_arm740_reset) bic ip, ip, #0x0000000c @ ............wc.. mcr p15, 0, ip, c1, c0, 0 @ ctrl register mov pc, r0 +ENDPROC(cpu_arm740_reset) + .popsection __CPUINIT diff --git a/arch/arm/mm/proc-arm7tdmi.S b/arch/arm/mm/proc-arm7tdmi.S index 7e0e1fe..6ddea3e 100644 --- a/arch/arm/mm/proc-arm7tdmi.S +++ b/arch/arm/mm/proc-arm7tdmi.S @@ -45,8 +45,11 @@ ENTRY(cpu_arm7tdmi_proc_fin) * Params : loc(r0) address to jump to * Purpose : Sets up everything for a reset and jump to the location for soft reset. */ + .pushsection .idmap.text, "ax" ENTRY(cpu_arm7tdmi_reset) mov pc, r0 +ENDPROC(cpu_arm7tdmi_reset) + .popsection __CPUINIT diff --git a/arch/arm/mm/proc-arm920.S b/arch/arm/mm/proc-arm920.S index 92bd102..cb941ae 100644 --- a/arch/arm/mm/proc-arm920.S +++ b/arch/arm/mm/proc-arm920.S @@ -85,6 +85,7 @@ ENTRY(cpu_arm920_proc_fin) * loc: location to jump to for soft reset */ .align 5 + .pushsection .idmap.text, "ax" ENTRY(cpu_arm920_reset) mov ip, #0 mcr p15, 0, ip, c7, c7, 0 @ invalidate I,D caches @@ -97,6 +98,8 @@ ENTRY(cpu_arm920_reset) bic ip, ip, #0x1100 @ ...i...s........ mcr p15, 0, ip, c1, c0, 0 @ ctrl register mov pc, r0 +ENDPROC(cpu_arm920_reset) + .popsection /* * cpu_arm920_do_idle() @@ -382,28 +385,23 @@ ENTRY(cpu_arm920_set_pte_ext) .equ cpu_arm920_suspend_size, 4 * 3 #ifdef CONFIG_PM_SLEEP ENTRY(cpu_arm920_do_suspend) - stmfd sp!, {r4 - r7, lr} + stmfd sp!, {r4 - r6, lr} mrc p15, 0, r4, c13, c0, 0 @ PID mrc p15, 0, r5, c3, c0, 0 @ Domain ID - mrc p15, 0, r6, c2, c0, 0 @ TTB address - mrc p15, 0, r7, c1, c0, 0 @ Control register - stmia r0, {r4 - r7} - ldmfd sp!, {r4 - r7, pc} + mrc p15, 0, r6, c1, c0, 0 @ Control register + stmia r0, {r4 - r6} + ldmfd sp!, {r4 - r6, pc} ENDPROC(cpu_arm920_do_suspend) ENTRY(cpu_arm920_do_resume) mov ip, #0 mcr p15, 0, ip, c8, c7, 0 @ invalidate I+D TLBs mcr p15, 0, ip, c7, c7, 0 @ invalidate I+D caches - ldmia r0, {r4 - r7} + ldmia r0, {r4 - r6} mcr p15, 0, r4, c13, c0, 0 @ PID mcr p15, 0, r5, c3, c0, 0 @ Domain ID - mcr p15, 0, r6, c2, c0, 0 @ TTB address - mov r0, r7 @ control register - mov r2, r6, lsr #14 @ get TTB0 base - mov r2, r2, lsl #14 - ldr r3, =PMD_TYPE_SECT | PMD_SECT_BUFFERABLE | \ - PMD_SECT_CACHEABLE | PMD_BIT4 | PMD_SECT_AP_WRITE + mcr p15, 0, r1, c2, c0, 0 @ TTB address + mov r0, r6 @ control register b cpu_resume_mmu ENDPROC(cpu_arm920_do_resume) #endif diff --git a/arch/arm/mm/proc-arm922.S b/arch/arm/mm/proc-arm922.S index 490e188..4ec0e07 100644 --- a/arch/arm/mm/proc-arm922.S +++ b/arch/arm/mm/proc-arm922.S @@ -87,6 +87,7 @@ ENTRY(cpu_arm922_proc_fin) * loc: location to jump to for soft reset */ .align 5 + .pushsection .idmap.text, "ax" ENTRY(cpu_arm922_reset) mov ip, #0 mcr p15, 0, ip, c7, c7, 0 @ invalidate I,D caches @@ -99,6 +100,8 @@ ENTRY(cpu_arm922_reset) bic ip, ip, #0x1100 @ ...i...s........ mcr p15, 0, ip, c1, c0, 0 @ ctrl register mov pc, r0 +ENDPROC(cpu_arm922_reset) + .popsection /* * cpu_arm922_do_idle() diff --git a/arch/arm/mm/proc-arm925.S b/arch/arm/mm/proc-arm925.S index 51d494b..9dccd9a 100644 --- a/arch/arm/mm/proc-arm925.S +++ b/arch/arm/mm/proc-arm925.S @@ -108,6 +108,7 @@ ENTRY(cpu_arm925_proc_fin) * loc: location to jump to for soft reset */ .align 5 + .pushsection .idmap.text, "ax" ENTRY(cpu_arm925_reset) /* Send software reset to MPU and DSP */ mov ip, #0xff000000 @@ -115,6 +116,8 @@ ENTRY(cpu_arm925_reset) orr ip, ip, #0x0000ce00 mov r4, #1 strh r4, [ip, #0x10] +ENDPROC(cpu_arm925_reset) + .popsection mov ip, #0 mcr p15, 0, ip, c7, c7, 0 @ invalidate I,D caches diff --git a/arch/arm/mm/proc-arm926.S b/arch/arm/mm/proc-arm926.S index 2bbcf05..820259b 100644 --- a/arch/arm/mm/proc-arm926.S +++ b/arch/arm/mm/proc-arm926.S @@ -77,6 +77,7 @@ ENTRY(cpu_arm926_proc_fin) * loc: location to jump to for soft reset */ .align 5 + .pushsection .idmap.text, "ax" ENTRY(cpu_arm926_reset) mov ip, #0 mcr p15, 0, ip, c7, c7, 0 @ invalidate I,D caches @@ -89,6 +90,8 @@ ENTRY(cpu_arm926_reset) bic ip, ip, #0x1100 @ ...i...s........ mcr p15, 0, ip, c1, c0, 0 @ ctrl register mov pc, r0 +ENDPROC(cpu_arm926_reset) + .popsection /* * cpu_arm926_do_idle() @@ -397,28 +400,23 @@ ENTRY(cpu_arm926_set_pte_ext) .equ cpu_arm926_suspend_size, 4 * 3 #ifdef CONFIG_PM_SLEEP ENTRY(cpu_arm926_do_suspend) - stmfd sp!, {r4 - r7, lr} + stmfd sp!, {r4 - r6, lr} mrc p15, 0, r4, c13, c0, 0 @ PID mrc p15, 0, r5, c3, c0, 0 @ Domain ID - mrc p15, 0, r6, c2, c0, 0 @ TTB address - mrc p15, 0, r7, c1, c0, 0 @ Control register - stmia r0, {r4 - r7} - ldmfd sp!, {r4 - r7, pc} + mrc p15, 0, r6, c1, c0, 0 @ Control register + stmia r0, {r4 - r6} + ldmfd sp!, {r4 - r6, pc} ENDPROC(cpu_arm926_do_suspend) ENTRY(cpu_arm926_do_resume) mov ip, #0 mcr p15, 0, ip, c8, c7, 0 @ invalidate I+D TLBs mcr p15, 0, ip, c7, c7, 0 @ invalidate I+D caches - ldmia r0, {r4 - r7} + ldmia r0, {r4 - r6} mcr p15, 0, r4, c13, c0, 0 @ PID mcr p15, 0, r5, c3, c0, 0 @ Domain ID - mcr p15, 0, r6, c2, c0, 0 @ TTB address - mov r0, r7 @ control register - mov r2, r6, lsr #14 @ get TTB0 base - mov r2, r2, lsl #14 - ldr r3, =PMD_TYPE_SECT | PMD_SECT_BUFFERABLE | \ - PMD_SECT_CACHEABLE | PMD_BIT4 | PMD_SECT_AP_WRITE + mcr p15, 0, r1, c2, c0, 0 @ TTB address + mov r0, r6 @ control register b cpu_resume_mmu ENDPROC(cpu_arm926_do_resume) #endif diff --git a/arch/arm/mm/proc-arm940.S b/arch/arm/mm/proc-arm940.S index ac750d5..9fdc0a17 100644 --- a/arch/arm/mm/proc-arm940.S +++ b/arch/arm/mm/proc-arm940.S @@ -48,6 +48,7 @@ ENTRY(cpu_arm940_proc_fin) * Params : r0 = address to jump to * Notes : This sets up everything for a reset */ + .pushsection .idmap.text, "ax" ENTRY(cpu_arm940_reset) mov ip, #0 mcr p15, 0, ip, c7, c5, 0 @ flush I cache @@ -58,6 +59,8 @@ ENTRY(cpu_arm940_reset) bic ip, ip, #0x00001000 @ i-cache mcr p15, 0, ip, c1, c0, 0 @ ctrl register mov pc, r0 +ENDPROC(cpu_arm940_reset) + .popsection /* * cpu_arm940_do_idle() diff --git a/arch/arm/mm/proc-arm946.S b/arch/arm/mm/proc-arm946.S index f8f7ea3..f684cfe 100644 --- a/arch/arm/mm/proc-arm946.S +++ b/arch/arm/mm/proc-arm946.S @@ -55,6 +55,7 @@ ENTRY(cpu_arm946_proc_fin) * Params : r0 = address to jump to * Notes : This sets up everything for a reset */ + .pushsection .idmap.text, "ax" ENTRY(cpu_arm946_reset) mov ip, #0 mcr p15, 0, ip, c7, c5, 0 @ flush I cache @@ -65,6 +66,8 @@ ENTRY(cpu_arm946_reset) bic ip, ip, #0x00001000 @ i-cache mcr p15, 0, ip, c1, c0, 0 @ ctrl register mov pc, r0 +ENDPROC(cpu_arm946_reset) + .popsection /* * cpu_arm946_do_idle() @@ -410,6 +413,7 @@ __arm946_proc_info: .long 0x41009460 .long 0xff00fff0 .long 0 + .long 0 b __arm946_setup .long cpu_arch_name .long cpu_elf_name @@ -418,6 +422,6 @@ __arm946_proc_info: .long arm946_processor_functions .long 0 .long 0 - .long arm940_cache_fns + .long arm946_cache_fns .size __arm946_proc_info, . - __arm946_proc_info diff --git a/arch/arm/mm/proc-arm9tdmi.S b/arch/arm/mm/proc-arm9tdmi.S index 2120f9e..8881391 100644 --- a/arch/arm/mm/proc-arm9tdmi.S +++ b/arch/arm/mm/proc-arm9tdmi.S @@ -45,8 +45,11 @@ ENTRY(cpu_arm9tdmi_proc_fin) * Params : loc(r0) address to jump to * Purpose : Sets up everything for a reset and jump to the location for soft reset. */ + .pushsection .idmap.text, "ax" ENTRY(cpu_arm9tdmi_reset) mov pc, r0 +ENDPROC(cpu_arm9tdmi_reset) + .popsection __CPUINIT diff --git a/arch/arm/mm/proc-fa526.S b/arch/arm/mm/proc-fa526.S index 4c7a571..272558a 100644 --- a/arch/arm/mm/proc-fa526.S +++ b/arch/arm/mm/proc-fa526.S @@ -57,6 +57,7 @@ ENTRY(cpu_fa526_proc_fin) * loc: location to jump to for soft reset */ .align 4 + .pushsection .idmap.text, "ax" ENTRY(cpu_fa526_reset) /* TODO: Use CP8 if possible... */ mov ip, #0 @@ -73,6 +74,8 @@ ENTRY(cpu_fa526_reset) nop nop mov pc, r0 +ENDPROC(cpu_fa526_reset) + .popsection /* * cpu_fa526_do_idle() diff --git a/arch/arm/mm/proc-feroceon.S b/arch/arm/mm/proc-feroceon.S index 8a6c2f7..ba3c500 100644 --- a/arch/arm/mm/proc-feroceon.S +++ b/arch/arm/mm/proc-feroceon.S @@ -98,6 +98,7 @@ ENTRY(cpu_feroceon_proc_fin) * loc: location to jump to for soft reset */ .align 5 + .pushsection .idmap.text, "ax" ENTRY(cpu_feroceon_reset) mov ip, #0 mcr p15, 0, ip, c7, c7, 0 @ invalidate I,D caches @@ -110,6 +111,8 @@ ENTRY(cpu_feroceon_reset) bic ip, ip, #0x1100 @ ...i...s........ mcr p15, 0, ip, c1, c0, 0 @ ctrl register mov pc, r0 +ENDPROC(cpu_feroceon_reset) + .popsection /* * cpu_feroceon_do_idle() diff --git a/arch/arm/mm/proc-macros.S b/arch/arm/mm/proc-macros.S index 307a4def..2d8ff3a 100644 --- a/arch/arm/mm/proc-macros.S +++ b/arch/arm/mm/proc-macros.S @@ -91,8 +91,9 @@ #if L_PTE_SHARED != PTE_EXT_SHARED #error PTE shared bit mismatch #endif -#if (L_PTE_XN+L_PTE_USER+L_PTE_RDONLY+L_PTE_DIRTY+L_PTE_YOUNG+\ - L_PTE_FILE+L_PTE_PRESENT) > L_PTE_SHARED +#if !defined (CONFIG_ARM_LPAE) && \ + (L_PTE_XN+L_PTE_USER+L_PTE_RDONLY+L_PTE_DIRTY+L_PTE_YOUNG+\ + L_PTE_FILE+L_PTE_PRESENT) > L_PTE_SHARED #error Invalid Linux PTE bit settings #endif #endif /* CONFIG_MMU */ diff --git a/arch/arm/mm/proc-mohawk.S b/arch/arm/mm/proc-mohawk.S index db52b0f..cdfedc5 100644 --- a/arch/arm/mm/proc-mohawk.S +++ b/arch/arm/mm/proc-mohawk.S @@ -69,6 +69,7 @@ ENTRY(cpu_mohawk_proc_fin) * (same as arm926) */ .align 5 + .pushsection .idmap.text, "ax" ENTRY(cpu_mohawk_reset) mov ip, #0 mcr p15, 0, ip, c7, c7, 0 @ invalidate I,D caches @@ -79,6 +80,8 @@ ENTRY(cpu_mohawk_reset) bic ip, ip, #0x1100 @ ...i...s........ mcr p15, 0, ip, c1, c0, 0 @ ctrl register mov pc, r0 +ENDPROC(cpu_mohawk_reset) + .popsection /* * cpu_mohawk_do_idle() diff --git a/arch/arm/mm/proc-sa110.S b/arch/arm/mm/proc-sa110.S index d50ada2..775d70f 100644 --- a/arch/arm/mm/proc-sa110.S +++ b/arch/arm/mm/proc-sa110.S @@ -62,6 +62,7 @@ ENTRY(cpu_sa110_proc_fin) * loc: location to jump to for soft reset */ .align 5 + .pushsection .idmap.text, "ax" ENTRY(cpu_sa110_reset) mov ip, #0 mcr p15, 0, ip, c7, c7, 0 @ invalidate I,D caches @@ -74,6 +75,8 @@ ENTRY(cpu_sa110_reset) bic ip, ip, #0x1100 @ ...i...s........ mcr p15, 0, ip, c1, c0, 0 @ ctrl register mov pc, r0 +ENDPROC(cpu_sa110_reset) + .popsection /* * cpu_sa110_do_idle(type) diff --git a/arch/arm/mm/proc-sa1100.S b/arch/arm/mm/proc-sa1100.S index 07219c2..3aa0da1 100644 --- a/arch/arm/mm/proc-sa1100.S +++ b/arch/arm/mm/proc-sa1100.S @@ -70,6 +70,7 @@ ENTRY(cpu_sa1100_proc_fin) * loc: location to jump to for soft reset */ .align 5 + .pushsection .idmap.text, "ax" ENTRY(cpu_sa1100_reset) mov ip, #0 mcr p15, 0, ip, c7, c7, 0 @ invalidate I,D caches @@ -82,6 +83,8 @@ ENTRY(cpu_sa1100_reset) bic ip, ip, #0x1100 @ ...i...s........ mcr p15, 0, ip, c1, c0, 0 @ ctrl register mov pc, r0 +ENDPROC(cpu_sa1100_reset) + .popsection /* * cpu_sa1100_do_idle(type) @@ -168,34 +171,29 @@ ENTRY(cpu_sa1100_set_pte_ext) mov pc, lr .globl cpu_sa1100_suspend_size -.equ cpu_sa1100_suspend_size, 4*4 +.equ cpu_sa1100_suspend_size, 4 * 3 #ifdef CONFIG_PM_SLEEP ENTRY(cpu_sa1100_do_suspend) - stmfd sp!, {r4 - r7, lr} + stmfd sp!, {r4 - r6, lr} mrc p15, 0, r4, c3, c0, 0 @ domain ID - mrc p15, 0, r5, c2, c0, 0 @ translation table base addr - mrc p15, 0, r6, c13, c0, 0 @ PID - mrc p15, 0, r7, c1, c0, 0 @ control reg - stmia r0, {r4 - r7} @ store cp regs - ldmfd sp!, {r4 - r7, pc} + mrc p15, 0, r5, c13, c0, 0 @ PID + mrc p15, 0, r6, c1, c0, 0 @ control reg + stmia r0, {r4 - r6} @ store cp regs + ldmfd sp!, {r4 - r6, pc} ENDPROC(cpu_sa1100_do_suspend) ENTRY(cpu_sa1100_do_resume) - ldmia r0, {r4 - r7} @ load cp regs - mov r1, #0 - mcr p15, 0, r1, c8, c7, 0 @ flush I+D TLBs - mcr p15, 0, r1, c7, c7, 0 @ flush I&D cache - mcr p15, 0, r1, c9, c0, 0 @ invalidate RB - mcr p15, 0, r1, c9, c0, 5 @ allow user space to use RB + ldmia r0, {r4 - r6} @ load cp regs + mov ip, #0 + mcr p15, 0, ip, c8, c7, 0 @ flush I+D TLBs + mcr p15, 0, ip, c7, c7, 0 @ flush I&D cache + mcr p15, 0, ip, c9, c0, 0 @ invalidate RB + mcr p15, 0, ip, c9, c0, 5 @ allow user space to use RB mcr p15, 0, r4, c3, c0, 0 @ domain ID - mcr p15, 0, r5, c2, c0, 0 @ translation table base addr - mcr p15, 0, r6, c13, c0, 0 @ PID - mov r0, r7 @ control register - mov r2, r5, lsr #14 @ get TTB0 base - mov r2, r2, lsl #14 - ldr r3, =PMD_TYPE_SECT | PMD_SECT_BUFFERABLE | \ - PMD_SECT_CACHEABLE | PMD_SECT_AP_WRITE + mcr p15, 0, r1, c2, c0, 0 @ translation table base addr + mcr p15, 0, r5, c13, c0, 0 @ PID + mov r0, r6 @ control register b cpu_resume_mmu ENDPROC(cpu_sa1100_do_resume) #endif diff --git a/arch/arm/mm/proc-v6.S b/arch/arm/mm/proc-v6.S index 219138d..5900cd5 100644 --- a/arch/arm/mm/proc-v6.S +++ b/arch/arm/mm/proc-v6.S @@ -55,6 +55,7 @@ ENTRY(cpu_v6_proc_fin) * - loc - location to jump to for soft reset */ .align 5 + .pushsection .idmap.text, "ax" ENTRY(cpu_v6_reset) mrc p15, 0, r1, c1, c0, 0 @ ctrl register bic r1, r1, #0x1 @ ...............m @@ -62,6 +63,8 @@ ENTRY(cpu_v6_reset) mov r1, #0 mcr p15, 0, r1, c7, c5, 4 @ ISB mov pc, r0 +ENDPROC(cpu_v6_reset) + .popsection /* * cpu_v6_do_idle() @@ -128,20 +131,18 @@ ENTRY(cpu_v6_set_pte_ext) /* Suspend/resume support: taken from arch/arm/mach-s3c64xx/sleep.S */ .globl cpu_v6_suspend_size -.equ cpu_v6_suspend_size, 4 * 8 +.equ cpu_v6_suspend_size, 4 * 6 #ifdef CONFIG_PM_SLEEP ENTRY(cpu_v6_do_suspend) - stmfd sp!, {r4 - r11, lr} + stmfd sp!, {r4 - r9, lr} mrc p15, 0, r4, c13, c0, 0 @ FCSE/PID - mrc p15, 0, r5, c13, c0, 1 @ Context ID - mrc p15, 0, r6, c3, c0, 0 @ Domain ID - mrc p15, 0, r7, c2, c0, 0 @ Translation table base 0 - mrc p15, 0, r8, c2, c0, 1 @ Translation table base 1 - mrc p15, 0, r9, c1, c0, 1 @ auxiliary control register - mrc p15, 0, r10, c1, c0, 2 @ co-processor access control - mrc p15, 0, r11, c1, c0, 0 @ control register - stmia r0, {r4 - r11} - ldmfd sp!, {r4- r11, pc} + mrc p15, 0, r5, c3, c0, 0 @ Domain ID + mrc p15, 0, r6, c2, c0, 1 @ Translation table base 1 + mrc p15, 0, r7, c1, c0, 1 @ auxiliary control register + mrc p15, 0, r8, c1, c0, 2 @ co-processor access control + mrc p15, 0, r9, c1, c0, 0 @ control register + stmia r0, {r4 - r9} + ldmfd sp!, {r4- r9, pc} ENDPROC(cpu_v6_do_suspend) ENTRY(cpu_v6_do_resume) @@ -150,25 +151,21 @@ ENTRY(cpu_v6_do_resume) mcr p15, 0, ip, c7, c5, 0 @ invalidate I cache mcr p15, 0, ip, c7, c15, 0 @ clean+invalidate cache mcr p15, 0, ip, c7, c10, 4 @ drain write buffer - ldmia r0, {r4 - r11} + mcr p15, 0, ip, c13, c0, 1 @ set reserved context ID + ldmia r0, {r4 - r9} mcr p15, 0, r4, c13, c0, 0 @ FCSE/PID - mcr p15, 0, r5, c13, c0, 1 @ Context ID - mcr p15, 0, r6, c3, c0, 0 @ Domain ID - mcr p15, 0, r7, c2, c0, 0 @ Translation table base 0 - mcr p15, 0, r8, c2, c0, 1 @ Translation table base 1 - mcr p15, 0, r9, c1, c0, 1 @ auxiliary control register - mcr p15, 0, r10, c1, c0, 2 @ co-processor access control + mcr p15, 0, r5, c3, c0, 0 @ Domain ID + ALT_SMP(orr r1, r1, #TTB_FLAGS_SMP) + ALT_UP(orr r1, r1, #TTB_FLAGS_UP) + mcr p15, 0, r1, c2, c0, 0 @ Translation table base 0 + mcr p15, 0, r6, c2, c0, 1 @ Translation table base 1 + mcr p15, 0, r7, c1, c0, 1 @ auxiliary control register + mcr p15, 0, r8, c1, c0, 2 @ co-processor access control mcr p15, 0, ip, c2, c0, 2 @ TTB control register mcr p15, 0, ip, c7, c5, 4 @ ISB - mov r0, r11 @ control register - mov r2, r7, lsr #14 @ get TTB0 base - mov r2, r2, lsl #14 - ldr r3, cpu_resume_l1_flags + mov r0, r9 @ control register b cpu_resume_mmu ENDPROC(cpu_v6_do_resume) -cpu_resume_l1_flags: - ALT_SMP(.long PMD_TYPE_SECT | PMD_SECT_AP_WRITE | PMD_FLAGS_SMP) - ALT_UP(.long PMD_TYPE_SECT | PMD_SECT_AP_WRITE | PMD_FLAGS_UP) #endif string cpu_v6_name, "ARMv6-compatible processor" @@ -223,6 +220,22 @@ __v6_setup: mrc p15, 0, r0, c1, c0, 0 @ read control register bic r0, r0, r5 @ clear bits them orr r0, r0, r6 @ set them +#ifdef CONFIG_ARM_ERRATA_364296 + /* + * Workaround for the 364296 ARM1136 r0p2 erratum (possible cache data + * corruption with hit-under-miss enabled). The conditional code below + * (setting the undocumented bit 31 in the auxiliary control register + * and the FI bit in the control register) disables hit-under-miss + * without putting the processor into full low interrupt latency mode. + */ + ldr r6, =0x4107b362 @ id for ARM1136 r0p2 + mrc p15, 0, r5, c0, c0, 0 @ get processor id + teq r5, r6 @ check for the faulty core + mrceq p15, 0, r5, c1, c0, 1 @ load aux control reg + orreq r5, r5, #(1 << 31) @ set the undocumented bit 31 + 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 /* diff --git a/arch/arm/mm/proc-v7-2level.S b/arch/arm/mm/proc-v7-2level.S new file mode 100644 index 0000000..3a4b3e7 --- /dev/null +++ b/arch/arm/mm/proc-v7-2level.S @@ -0,0 +1,171 @@ +/* + * arch/arm/mm/proc-v7-2level.S + * + * Copyright (C) 2001 Deep Blue Solutions Ltd. + * + * 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. + */ + +#define TTB_S (1 << 1) +#define TTB_RGN_NC (0 << 3) +#define TTB_RGN_OC_WBWA (1 << 3) +#define TTB_RGN_OC_WT (2 << 3) +#define TTB_RGN_OC_WB (3 << 3) +#define TTB_NOS (1 << 5) +#define TTB_IRGN_NC ((0 << 0) | (0 << 6)) +#define TTB_IRGN_WBWA ((0 << 0) | (1 << 6)) +#define TTB_IRGN_WT ((1 << 0) | (0 << 6)) +#define TTB_IRGN_WB ((1 << 0) | (1 << 6)) + +/* PTWs cacheable, inner WB not shareable, outer WB not shareable */ +#define TTB_FLAGS_UP TTB_IRGN_WB|TTB_RGN_OC_WB +#define PMD_FLAGS_UP PMD_SECT_WB + +/* PTWs cacheable, inner WBWA shareable, outer WBWA not shareable */ +#define TTB_FLAGS_SMP TTB_IRGN_WBWA|TTB_S|TTB_NOS|TTB_RGN_OC_WBWA +#define PMD_FLAGS_SMP PMD_SECT_WBWA|PMD_SECT_S + +/* + * cpu_v7_switch_mm(pgd_phys, tsk) + * + * Set the translation table base pointer to be pgd_phys + * + * - pgd_phys - physical address of new TTB + * + * It is assumed that: + * - we are not using split page tables + */ +ENTRY(cpu_v7_switch_mm) +#ifdef CONFIG_MMU + mov r2, #0 + ldr r1, [r1, #MM_CONTEXT_ID] @ get mm->context.id + ALT_SMP(orr r0, r0, #TTB_FLAGS_SMP) + ALT_UP(orr r0, r0, #TTB_FLAGS_UP) +#ifdef CONFIG_ARM_ERRATA_430973 + mcr p15, 0, r2, c7, c5, 6 @ flush BTAC/BTB +#endif +#ifdef CONFIG_ARM_ERRATA_754322 + dsb +#endif + mcr p15, 0, r2, c13, c0, 1 @ set reserved context ID + isb +1: mcr p15, 0, r0, c2, c0, 0 @ set TTB 0 + isb +#ifdef CONFIG_ARM_ERRATA_754322 + dsb +#endif + mcr p15, 0, r1, c13, c0, 1 @ set context ID + isb +#endif + mov pc, lr +ENDPROC(cpu_v7_switch_mm) + +/* + * cpu_v7_set_pte_ext(ptep, pte) + * + * Set a level 2 translation table entry. + * + * - ptep - pointer to level 2 translation table entry + * (hardware version is stored at +2048 bytes) + * - pte - PTE value to store + * - ext - value for extended PTE bits + */ +ENTRY(cpu_v7_set_pte_ext) +#ifdef CONFIG_MMU + str r1, [r0] @ linux version + + bic r3, r1, #0x000003f0 + bic r3, r3, #PTE_TYPE_MASK + orr r3, r3, r2 + orr r3, r3, #PTE_EXT_AP0 | 2 + + tst r1, #1 << 4 + orrne r3, r3, #PTE_EXT_TEX(1) + + eor r1, r1, #L_PTE_DIRTY + tst r1, #L_PTE_RDONLY | L_PTE_DIRTY + orrne r3, r3, #PTE_EXT_APX + + tst r1, #L_PTE_USER + orrne r3, r3, #PTE_EXT_AP1 +#ifdef CONFIG_CPU_USE_DOMAINS + @ allow kernel read/write access to read-only user pages + tstne r3, #PTE_EXT_APX + bicne r3, r3, #PTE_EXT_APX | PTE_EXT_AP0 +#endif + + tst r1, #L_PTE_XN + orrne r3, r3, #PTE_EXT_XN + + tst r1, #L_PTE_YOUNG + tstne r1, #L_PTE_PRESENT + moveq r3, #0 + + ARM( str r3, [r0, #2048]! ) + THUMB( add r0, r0, #2048 ) + THUMB( str r3, [r0] ) + mcr p15, 0, r0, c7, c10, 1 @ flush_pte +#endif + mov pc, lr +ENDPROC(cpu_v7_set_pte_ext) + + /* + * Memory region attributes with SCTLR.TRE=1 + * + * n = TEX[0],C,B + * TR = PRRR[2n+1:2n] - memory type + * IR = NMRR[2n+1:2n] - inner cacheable property + * OR = NMRR[2n+17:2n+16] - outer cacheable property + * + * n TR IR OR + * UNCACHED 000 00 + * BUFFERABLE 001 10 00 00 + * WRITETHROUGH 010 10 10 10 + * WRITEBACK 011 10 11 11 + * reserved 110 + * WRITEALLOC 111 10 01 01 + * DEV_SHARED 100 01 + * DEV_NONSHARED 100 01 + * DEV_WC 001 10 + * DEV_CACHED 011 10 + * + * Other attributes: + * + * DS0 = PRRR[16] = 0 - device shareable property + * DS1 = PRRR[17] = 1 - device shareable property + * NS0 = PRRR[18] = 0 - normal shareable property + * NS1 = PRRR[19] = 1 - normal shareable property + * NOS = PRRR[24+n] = 1 - not outer shareable + */ +.equ PRRR, 0xff0a81a8 +.equ NMRR, 0x40e040e0 + + /* + * Macro for setting up the TTBRx and TTBCR registers. + * - \ttb0 and \ttb1 updated with the corresponding flags. + */ + .macro v7_ttb_setup, zero, ttbr0, ttbr1, tmp + mcr p15, 0, \zero, c2, c0, 2 @ TTB control register + ALT_SMP(orr \ttbr0, \ttbr0, #TTB_FLAGS_SMP) + ALT_UP(orr \ttbr0, \ttbr0, #TTB_FLAGS_UP) + ALT_SMP(orr \ttbr1, \ttbr1, #TTB_FLAGS_SMP) + ALT_UP(orr \ttbr1, \ttbr1, #TTB_FLAGS_UP) + mcr p15, 0, \ttbr1, c2, c0, 1 @ load TTB1 + .endm + + __CPUINIT + + /* AT + * TFR EV X F I D LR S + * .EEE ..EE PUI. .T.T 4RVI ZWRS BLDP WCAM + * rxxx rrxx xxx0 0101 xxxx xxxx x111 xxxx < forced + * 1 0 110 0011 1100 .111 1101 < we want + */ + .align 2 + .type v7_crval, #object +v7_crval: + crval clear=0x0120c302, mmuset=0x10c03c7d, ucset=0x00c01c7c + + .previous diff --git a/arch/arm/mm/proc-v7-3level.S b/arch/arm/mm/proc-v7-3level.S new file mode 100644 index 0000000..8de0f1d --- /dev/null +++ b/arch/arm/mm/proc-v7-3level.S @@ -0,0 +1,150 @@ +/* + * arch/arm/mm/proc-v7-3level.S + * + * Copyright (C) 2001 Deep Blue Solutions Ltd. + * Copyright (C) 2011 ARM Ltd. + * Author: Catalin Marinas <catalin.marinas@arm.com> + * based on arch/arm/mm/proc-v7-2level.S + * + * 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. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + */ + +#define TTB_IRGN_NC (0 << 8) +#define TTB_IRGN_WBWA (1 << 8) +#define TTB_IRGN_WT (2 << 8) +#define TTB_IRGN_WB (3 << 8) +#define TTB_RGN_NC (0 << 10) +#define TTB_RGN_OC_WBWA (1 << 10) +#define TTB_RGN_OC_WT (2 << 10) +#define TTB_RGN_OC_WB (3 << 10) +#define TTB_S (3 << 12) +#define TTB_EAE (1 << 31) + +/* PTWs cacheable, inner WB not shareable, outer WB not shareable */ +#define TTB_FLAGS_UP (TTB_IRGN_WB|TTB_RGN_OC_WB) +#define PMD_FLAGS_UP (PMD_SECT_WB) + +/* PTWs cacheable, inner WBWA shareable, outer WBWA not shareable */ +#define TTB_FLAGS_SMP (TTB_IRGN_WBWA|TTB_S|TTB_RGN_OC_WBWA) +#define PMD_FLAGS_SMP (PMD_SECT_WBWA|PMD_SECT_S) + +/* + * cpu_v7_switch_mm(pgd_phys, tsk) + * + * Set the translation table base pointer to be pgd_phys (physical address of + * the new TTB). + */ +ENTRY(cpu_v7_switch_mm) +#ifdef CONFIG_MMU + ldr r1, [r1, #MM_CONTEXT_ID] @ get mm->context.id + and r3, r1, #0xff + mov r3, r3, lsl #(48 - 32) @ ASID + mcrr p15, 0, r0, r3, c2 @ set TTB 0 + isb +#endif + mov pc, lr +ENDPROC(cpu_v7_switch_mm) + +/* + * cpu_v7_set_pte_ext(ptep, pte) + * + * Set a level 2 translation table entry. + * - ptep - pointer to level 3 translation table entry + * - pte - PTE value to store (64-bit in r2 and r3) + */ +ENTRY(cpu_v7_set_pte_ext) +#ifdef CONFIG_MMU + tst r2, #L_PTE_PRESENT + beq 1f + tst r3, #1 << (55 - 32) @ L_PTE_DIRTY + orreq r2, #L_PTE_RDONLY +1: strd r2, r3, [r0] + mcr p15, 0, r0, c7, c10, 1 @ flush_pte +#endif + mov pc, lr +ENDPROC(cpu_v7_set_pte_ext) + + /* + * Memory region attributes for LPAE (defined in pgtable-3level.h): + * + * n = AttrIndx[2:0] + * + * n MAIR + * UNCACHED 000 00000000 + * BUFFERABLE 001 01000100 + * DEV_WC 001 01000100 + * WRITETHROUGH 010 10101010 + * WRITEBACK 011 11101110 + * DEV_CACHED 011 11101110 + * DEV_SHARED 100 00000100 + * DEV_NONSHARED 100 00000100 + * unused 101 + * unused 110 + * WRITEALLOC 111 11111111 + */ +.equ PRRR, 0xeeaa4400 @ MAIR0 +.equ NMRR, 0xff000004 @ MAIR1 + + /* + * Macro for setting up the TTBRx and TTBCR registers. + * - \ttbr1 updated. + */ + .macro v7_ttb_setup, zero, ttbr0, ttbr1, tmp + ldr \tmp, =swapper_pg_dir @ swapper_pg_dir virtual address + cmp \ttbr1, \tmp @ PHYS_OFFSET > PAGE_OFFSET? (branch below) + mrc p15, 0, \tmp, c2, c0, 2 @ TTB control register + orr \tmp, \tmp, #TTB_EAE + ALT_SMP(orr \tmp, \tmp, #TTB_FLAGS_SMP) + ALT_UP(orr \tmp, \tmp, #TTB_FLAGS_UP) + ALT_SMP(orr \tmp, \tmp, #TTB_FLAGS_SMP << 16) + ALT_UP(orr \tmp, \tmp, #TTB_FLAGS_UP << 16) + /* + * TTBR0/TTBR1 split (PAGE_OFFSET): + * 0x40000000: T0SZ = 2, T1SZ = 0 (not used) + * 0x80000000: T0SZ = 0, T1SZ = 1 + * 0xc0000000: T0SZ = 0, T1SZ = 2 + * + * Only use this feature if PHYS_OFFSET <= PAGE_OFFSET, otherwise + * booting secondary CPUs would end up using TTBR1 for the identity + * mapping set up in TTBR0. + */ + bhi 9001f @ PHYS_OFFSET > PAGE_OFFSET? + orr \tmp, \tmp, #(((PAGE_OFFSET >> 30) - 1) << 16) @ TTBCR.T1SZ +#if defined CONFIG_VMSPLIT_2G + /* PAGE_OFFSET == 0x80000000, T1SZ == 1 */ + add \ttbr1, \ttbr1, #1 << 4 @ skip two L1 entries +#elif defined CONFIG_VMSPLIT_3G + /* PAGE_OFFSET == 0xc0000000, T1SZ == 2 */ + add \ttbr1, \ttbr1, #4096 * (1 + 3) @ only L2 used, skip pgd+3*pmd +#endif + /* CONFIG_VMSPLIT_1G does not need TTBR1 adjustment */ +9001: mcr p15, 0, \tmp, c2, c0, 2 @ TTB control register + mcrr p15, 1, \ttbr1, \zero, c2 @ load TTBR1 + .endm + + __CPUINIT + + /* + * AT + * TFR EV X F IHD LR S + * .EEE ..EE PUI. .TAT 4RVI ZWRS BLDP WCAM + * rxxx rrxx xxx0 0101 xxxx xxxx x111 xxxx < forced + * 11 0 110 1 0011 1100 .111 1101 < we want + */ + .align 2 + .type v7_crval, #object +v7_crval: + crval clear=0x0120c302, mmuset=0x30c23c7d, ucset=0x00c01c7c + + .previous diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S index a30e785..7e9b5bf 100644 --- a/arch/arm/mm/proc-v7.S +++ b/arch/arm/mm/proc-v7.S @@ -19,24 +19,11 @@ #include "proc-macros.S" -#define TTB_S (1 << 1) -#define TTB_RGN_NC (0 << 3) -#define TTB_RGN_OC_WBWA (1 << 3) -#define TTB_RGN_OC_WT (2 << 3) -#define TTB_RGN_OC_WB (3 << 3) -#define TTB_NOS (1 << 5) -#define TTB_IRGN_NC ((0 << 0) | (0 << 6)) -#define TTB_IRGN_WBWA ((0 << 0) | (1 << 6)) -#define TTB_IRGN_WT ((1 << 0) | (0 << 6)) -#define TTB_IRGN_WB ((1 << 0) | (1 << 6)) - -/* PTWs cacheable, inner WB not shareable, outer WB not shareable */ -#define TTB_FLAGS_UP TTB_IRGN_WB|TTB_RGN_OC_WB -#define PMD_FLAGS_UP PMD_SECT_WB - -/* PTWs cacheable, inner WBWA shareable, outer WBWA not shareable */ -#define TTB_FLAGS_SMP TTB_IRGN_WBWA|TTB_S|TTB_NOS|TTB_RGN_OC_WBWA -#define PMD_FLAGS_SMP PMD_SECT_WBWA|PMD_SECT_S +#ifdef CONFIG_ARM_LPAE +#include "proc-v7-3level.S" +#else +#include "proc-v7-2level.S" +#endif ENTRY(cpu_v7_proc_init) mov pc, lr @@ -63,13 +50,16 @@ ENDPROC(cpu_v7_proc_fin) * caches disabled. */ .align 5 + .pushsection .idmap.text, "ax" ENTRY(cpu_v7_reset) mrc p15, 0, r1, c1, c0, 0 @ ctrl register bic r1, r1, #0x1 @ ...............m + THUMB( bic r1, r1, #1 << 30 ) @ SCTLR.TE (Thumb exceptions) mcr p15, 0, r1, c1, c0, 0 @ disable MMU isb mov pc, r0 ENDPROC(cpu_v7_reset) + .popsection /* * cpu_v7_do_idle() @@ -96,173 +86,58 @@ ENTRY(cpu_v7_dcache_clean_area) mov pc, lr ENDPROC(cpu_v7_dcache_clean_area) -/* - * cpu_v7_switch_mm(pgd_phys, tsk) - * - * Set the translation table base pointer to be pgd_phys - * - * - pgd_phys - physical address of new TTB - * - * It is assumed that: - * - we are not using split page tables - */ -ENTRY(cpu_v7_switch_mm) -#ifdef CONFIG_MMU - mov r2, #0 - ldr r1, [r1, #MM_CONTEXT_ID] @ get mm->context.id - ALT_SMP(orr r0, r0, #TTB_FLAGS_SMP) - ALT_UP(orr r0, r0, #TTB_FLAGS_UP) -#ifdef CONFIG_ARM_ERRATA_430973 - mcr p15, 0, r2, c7, c5, 6 @ flush BTAC/BTB -#endif -#ifdef CONFIG_ARM_ERRATA_754322 - dsb -#endif - mcr p15, 0, r2, c13, c0, 1 @ set reserved context ID - isb -1: mcr p15, 0, r0, c2, c0, 0 @ set TTB 0 - isb -#ifdef CONFIG_ARM_ERRATA_754322 - dsb -#endif - mcr p15, 0, r1, c13, c0, 1 @ set context ID - isb -#endif - mov pc, lr -ENDPROC(cpu_v7_switch_mm) - -/* - * cpu_v7_set_pte_ext(ptep, pte) - * - * Set a level 2 translation table entry. - * - * - ptep - pointer to level 2 translation table entry - * (hardware version is stored at +2048 bytes) - * - pte - PTE value to store - * - ext - value for extended PTE bits - */ -ENTRY(cpu_v7_set_pte_ext) -#ifdef CONFIG_MMU - str r1, [r0] @ linux version - - bic r3, r1, #0x000003f0 - bic r3, r3, #PTE_TYPE_MASK - orr r3, r3, r2 - orr r3, r3, #PTE_EXT_AP0 | 2 - - tst r1, #1 << 4 - orrne r3, r3, #PTE_EXT_TEX(1) - - eor r1, r1, #L_PTE_DIRTY - tst r1, #L_PTE_RDONLY | L_PTE_DIRTY - orrne r3, r3, #PTE_EXT_APX - - tst r1, #L_PTE_USER - orrne r3, r3, #PTE_EXT_AP1 -#ifdef CONFIG_CPU_USE_DOMAINS - @ allow kernel read/write access to read-only user pages - tstne r3, #PTE_EXT_APX - bicne r3, r3, #PTE_EXT_APX | PTE_EXT_AP0 -#endif - - tst r1, #L_PTE_XN - orrne r3, r3, #PTE_EXT_XN - - tst r1, #L_PTE_YOUNG - tstne r1, #L_PTE_PRESENT - moveq r3, #0 - - ARM( str r3, [r0, #2048]! ) - THUMB( add r0, r0, #2048 ) - THUMB( str r3, [r0] ) - mcr p15, 0, r0, c7, c10, 1 @ flush_pte -#endif - mov pc, lr -ENDPROC(cpu_v7_set_pte_ext) - string cpu_v7_name, "ARMv7 Processor" .align - /* - * Memory region attributes with SCTLR.TRE=1 - * - * n = TEX[0],C,B - * TR = PRRR[2n+1:2n] - memory type - * IR = NMRR[2n+1:2n] - inner cacheable property - * OR = NMRR[2n+17:2n+16] - outer cacheable property - * - * n TR IR OR - * UNCACHED 000 00 - * BUFFERABLE 001 10 00 00 - * WRITETHROUGH 010 10 10 10 - * WRITEBACK 011 10 11 11 - * reserved 110 - * WRITEALLOC 111 10 01 01 - * DEV_SHARED 100 01 - * DEV_NONSHARED 100 01 - * DEV_WC 001 10 - * DEV_CACHED 011 10 - * - * Other attributes: - * - * DS0 = PRRR[16] = 0 - device shareable property - * DS1 = PRRR[17] = 1 - device shareable property - * NS0 = PRRR[18] = 0 - normal shareable property - * NS1 = PRRR[19] = 1 - normal shareable property - * NOS = PRRR[24+n] = 1 - not outer shareable - */ -.equ PRRR, 0xff0a81a8 -.equ NMRR, 0x40e040e0 - /* Suspend/resume support: derived from arch/arm/mach-s5pv210/sleep.S */ .globl cpu_v7_suspend_size -.equ cpu_v7_suspend_size, 4 * 9 -#ifdef CONFIG_PM_SLEEP +.equ cpu_v7_suspend_size, 4 * 8 +#ifdef CONFIG_ARM_CPU_SUSPEND ENTRY(cpu_v7_do_suspend) - stmfd sp!, {r4 - r11, lr} + stmfd sp!, {r4 - r10, lr} mrc p15, 0, r4, c13, c0, 0 @ FCSE/PID - mrc p15, 0, r5, c13, c0, 1 @ Context ID - mrc p15, 0, r6, c13, c0, 3 @ User r/o thread ID - stmia r0!, {r4 - r6} + mrc p15, 0, r5, c13, c0, 3 @ User r/o thread ID + stmia r0!, {r4 - r5} mrc p15, 0, r6, c3, c0, 0 @ Domain ID - mrc p15, 0, r7, c2, c0, 0 @ TTB 0 - mrc p15, 0, r8, c2, c0, 1 @ TTB 1 - mrc p15, 0, r9, c1, c0, 0 @ Control register - mrc p15, 0, r10, c1, c0, 1 @ Auxiliary control register - mrc p15, 0, r11, c1, c0, 2 @ Co-processor access control + mrc p15, 0, r7, c2, c0, 1 @ TTB 1 + mrc p15, 0, r11, c2, c0, 2 @ TTB control register + mrc p15, 0, r8, c1, c0, 0 @ Control register + mrc p15, 0, r9, c1, c0, 1 @ Auxiliary control register + mrc p15, 0, r10, c1, c0, 2 @ Co-processor access control stmia r0, {r6 - r11} - ldmfd sp!, {r4 - r11, pc} + ldmfd sp!, {r4 - r10, pc} ENDPROC(cpu_v7_do_suspend) ENTRY(cpu_v7_do_resume) mov ip, #0 mcr p15, 0, ip, c8, c7, 0 @ invalidate TLBs mcr p15, 0, ip, c7, c5, 0 @ invalidate I cache - ldmia r0!, {r4 - r6} + mcr p15, 0, ip, c13, c0, 1 @ set reserved context ID + ldmia r0!, {r4 - r5} mcr p15, 0, r4, c13, c0, 0 @ FCSE/PID - mcr p15, 0, r5, c13, c0, 1 @ Context ID - mcr p15, 0, r6, c13, c0, 3 @ User r/o thread ID + mcr p15, 0, r5, c13, c0, 3 @ User r/o thread ID ldmia r0, {r6 - r11} mcr p15, 0, r6, c3, c0, 0 @ Domain ID - mcr p15, 0, r7, c2, c0, 0 @ TTB 0 - mcr p15, 0, r8, c2, c0, 1 @ TTB 1 - mcr p15, 0, ip, c2, c0, 2 @ TTB control register - mcr p15, 0, r10, c1, c0, 1 @ Auxiliary control register - mcr p15, 0, r11, c1, c0, 2 @ Co-processor access control +#ifndef CONFIG_ARM_LPAE + ALT_SMP(orr r1, r1, #TTB_FLAGS_SMP) + ALT_UP(orr r1, r1, #TTB_FLAGS_UP) +#endif + mcr p15, 0, r1, c2, c0, 0 @ TTB 0 + mcr p15, 0, r7, c2, c0, 1 @ TTB 1 + mcr p15, 0, r11, c2, c0, 2 @ TTB control register + mrc p15, 0, r4, c1, c0, 1 @ Read Auxiliary control register + teq r4, r9 @ Is it already set? + mcrne p15, 0, r9, c1, c0, 1 @ No, so write it + mcr p15, 0, r10, c1, c0, 2 @ Co-processor access control ldr r4, =PRRR @ PRRR ldr r5, =NMRR @ NMRR mcr p15, 0, r4, c10, c2, 0 @ write PRRR mcr p15, 0, r5, c10, c2, 1 @ write NMRR isb - mov r0, r9 @ control register - mov r2, r7, lsr #14 @ get TTB0 base - mov r2, r2, lsl #14 - ldr r3, cpu_resume_l1_flags + dsb + mov r0, r8 @ control register b cpu_resume_mmu ENDPROC(cpu_v7_do_resume) -cpu_resume_l1_flags: - ALT_SMP(.long PMD_TYPE_SECT | PMD_SECT_AP_WRITE | PMD_FLAGS_SMP) - ALT_UP(.long PMD_TYPE_SECT | PMD_SECT_AP_WRITE | PMD_FLAGS_UP) #endif __CPUINIT @@ -286,6 +161,7 @@ __v7_ca5mp_setup: __v7_ca9mp_setup: mov r10, #(1 << 0) @ TLB ops broadcasting b 1f +__v7_ca7mp_setup: __v7_ca15mp_setup: mov r10, #0 1: @@ -365,11 +241,13 @@ __v7_setup: orreq r10, r10, #1 << 6 @ set bit #6 mcreq p15, 0, r10, c15, c0, 1 @ write diagnostic register #endif -#ifdef CONFIG_ARM_ERRATA_751472 - cmp r6, #0x30 @ present prior to r3p0 +#if defined(CONFIG_ARM_ERRATA_751472) && defined(CONFIG_SMP) + ALT_SMP(cmp r6, #0x30) @ present prior to r3p0 + ALT_UP_B(1f) mrclt p15, 0, r10, c15, c0, 1 @ read diagnostic register orrlt r10, r10, #1 << 11 @ set bit #11 mcrlt p15, 0, r10, c15, c0, 1 @ write diagnostic register +1: #endif 3: mov r10, #0 @@ -379,12 +257,7 @@ __v7_setup: dsb #ifdef CONFIG_MMU mcr p15, 0, r10, c8, c7, 0 @ invalidate I + D TLBs - mcr p15, 0, r10, c2, c0, 2 @ TTB control register - ALT_SMP(orr r4, r4, #TTB_FLAGS_SMP) - ALT_UP(orr r4, r4, #TTB_FLAGS_UP) - ALT_SMP(orr r8, r8, #TTB_FLAGS_SMP) - ALT_UP(orr r8, r8, #TTB_FLAGS_UP) - mcr p15, 0, r8, c2, c0, 1 @ load TTB1 + v7_ttb_setup r10, r4, r8, r5 @ TTBCR, TTBRx setup ldr r5, =PRRR @ PRRR ldr r6, =NMRR @ NMRR mcr p15, 0, r5, c10, c2, 0 @ write PRRR @@ -406,16 +279,7 @@ __v7_setup: mov pc, lr @ return to head.S:__ret ENDPROC(__v7_setup) - /* AT - * TFR EV X F I D LR S - * .EEE ..EE PUI. .T.T 4RVI ZWRS BLDP WCAM - * rxxx rrxx xxx0 0101 xxxx xxxx x111 xxxx < forced - * 1 0 110 0011 1100 .111 1101 < we want - */ - .type v7_crval, #object -v7_crval: - crval clear=0x0120c302, mmuset=0x10c03c7d, ucset=0x00c01c7c - + .align 2 __v7_setup_stack: .space 4 * 11 @ 11 registers @@ -437,11 +301,11 @@ __v7_setup_stack: */ .macro __v7_proc initfunc, mm_mmuflags = 0, io_mmuflags = 0, hwcaps = 0 ALT_SMP(.long PMD_TYPE_SECT | PMD_SECT_AP_WRITE | PMD_SECT_AP_READ | \ - PMD_FLAGS_SMP | \mm_mmuflags) + PMD_SECT_AF | PMD_FLAGS_SMP | \mm_mmuflags) ALT_UP(.long PMD_TYPE_SECT | PMD_SECT_AP_WRITE | PMD_SECT_AP_READ | \ - PMD_FLAGS_UP | \mm_mmuflags) - .long PMD_TYPE_SECT | PMD_SECT_XN | PMD_SECT_AP_WRITE | \ - PMD_SECT_AP_READ | \io_mmuflags + PMD_SECT_AF | PMD_FLAGS_UP | \mm_mmuflags) + .long PMD_TYPE_SECT | PMD_SECT_AP_WRITE | \ + PMD_SECT_AP_READ | PMD_SECT_AF | \io_mmuflags W(b) \initfunc .long cpu_arch_name .long cpu_elf_name @@ -454,6 +318,7 @@ __v7_setup_stack: .long v7_cache_fns .endm +#ifndef CONFIG_ARM_LPAE /* * ARM Ltd. Cortex A5 processor. */ @@ -465,6 +330,16 @@ __v7_ca5mp_proc_info: .size __v7_ca5mp_proc_info, . - __v7_ca5mp_proc_info /* + * ARM Ltd. Cortex A7 processor. + */ + .type __v7_ca7mp_proc_info, #object +__v7_ca7mp_proc_info: + .long 0x410fc070 + .long 0xff0ffff0 + __v7_proc __v7_ca7mp_setup, hwcaps = HWCAP_IDIV + .size __v7_ca7mp_proc_info, . - __v7_ca7mp_proc_info + + /* * ARM Ltd. Cortex A9 processor. */ .type __v7_ca9mp_proc_info, #object @@ -473,6 +348,7 @@ __v7_ca9mp_proc_info: .long 0xff0ffff0 __v7_proc __v7_ca9mp_setup .size __v7_ca9mp_proc_info, . - __v7_ca9mp_proc_info +#endif /* CONFIG_ARM_LPAE */ /* * ARM Ltd. Cortex A15 processor. diff --git a/arch/arm/mm/proc-xsc3.S b/arch/arm/mm/proc-xsc3.S index 28c72a2..b0d5786 100644 --- a/arch/arm/mm/proc-xsc3.S +++ b/arch/arm/mm/proc-xsc3.S @@ -105,6 +105,7 @@ ENTRY(cpu_xsc3_proc_fin) * loc: location to jump to for soft reset */ .align 5 + .pushsection .idmap.text, "ax" ENTRY(cpu_xsc3_reset) mov r1, #PSR_F_BIT|PSR_I_BIT|SVC_MODE msr cpsr_c, r1 @ reset CPSR @@ -119,6 +120,8 @@ ENTRY(cpu_xsc3_reset) @ already containing those two last instructions to survive. mcr p15, 0, ip, c8, c7, 0 @ invalidate I and D TLBs mov pc, r0 +ENDPROC(cpu_xsc3_reset) + .popsection /* * cpu_xsc3_do_idle() @@ -406,24 +409,23 @@ ENTRY(cpu_xsc3_set_pte_ext) .align .globl cpu_xsc3_suspend_size -.equ cpu_xsc3_suspend_size, 4 * 8 +.equ cpu_xsc3_suspend_size, 4 * 6 #ifdef CONFIG_PM_SLEEP ENTRY(cpu_xsc3_do_suspend) - stmfd sp!, {r4 - r10, lr} + stmfd sp!, {r4 - r9, lr} mrc p14, 0, r4, c6, c0, 0 @ clock configuration, for turbo mode mrc p15, 0, r5, c15, c1, 0 @ CP access reg mrc p15, 0, r6, c13, c0, 0 @ PID mrc p15, 0, r7, c3, c0, 0 @ domain ID - mrc p15, 0, r8, c2, c0, 0 @ translation table base addr - mrc p15, 0, r9, c1, c0, 1 @ auxiliary control reg - mrc p15, 0, r10, c1, c0, 0 @ control reg + mrc p15, 0, r8, c1, c0, 1 @ auxiliary control reg + mrc p15, 0, r9, c1, c0, 0 @ control reg bic r4, r4, #2 @ clear frequency change bit - stmia r0, {r1, r4 - r10} @ store v:p offset + cp regs - ldmia sp!, {r4 - r10, pc} + stmia r0, {r4 - r9} @ store cp regs + ldmia sp!, {r4 - r9, pc} ENDPROC(cpu_xsc3_do_suspend) ENTRY(cpu_xsc3_do_resume) - ldmia r0, {r1, r4 - r10} @ load v:p offset + cp regs + ldmia r0, {r4 - r9} @ load cp regs mov ip, #0 mcr p15, 0, ip, c7, c7, 0 @ invalidate I & D caches, BTB mcr p15, 0, ip, c7, c10, 4 @ drain write (&fill) buffer @@ -433,15 +435,10 @@ ENTRY(cpu_xsc3_do_resume) mcr p15, 0, r5, c15, c1, 0 @ CP access reg mcr p15, 0, r6, c13, c0, 0 @ PID mcr p15, 0, r7, c3, c0, 0 @ domain ID - mcr p15, 0, r8, c2, c0, 0 @ translation table base addr - mcr p15, 0, r9, c1, c0, 1 @ auxiliary control reg - - @ temporarily map resume_turn_on_mmu into the page table, - @ otherwise prefetch abort occurs after MMU is turned on - mov r0, r10 @ control register - mov r2, r8, lsr #14 @ get TTB0 base - mov r2, r2, lsl #14 - ldr r3, =0x542e @ section flags + orr r1, r1, #0x18 @ cache the page table in L2 + mcr p15, 0, r1, c2, c0, 0 @ translation table base addr + mcr p15, 0, r8, c1, c0, 1 @ auxiliary control reg + mov r0, r9 @ control register b cpu_resume_mmu ENDPROC(cpu_xsc3_do_resume) #endif diff --git a/arch/arm/mm/proc-xscale.S b/arch/arm/mm/proc-xscale.S index fbc06e5..4ffebaa 100644 --- a/arch/arm/mm/proc-xscale.S +++ b/arch/arm/mm/proc-xscale.S @@ -142,6 +142,7 @@ ENTRY(cpu_xscale_proc_fin) * Beware PXA270 erratum E7. */ .align 5 + .pushsection .idmap.text, "ax" ENTRY(cpu_xscale_reset) mov r1, #PSR_F_BIT|PSR_I_BIT|SVC_MODE msr cpsr_c, r1 @ reset CPSR @@ -160,6 +161,8 @@ ENTRY(cpu_xscale_reset) @ already containing those two last instructions to survive. mcr p15, 0, ip, c8, c7, 0 @ invalidate I & D TLBs mov pc, r0 +ENDPROC(cpu_xscale_reset) + .popsection /* * cpu_xscale_do_idle() @@ -520,24 +523,23 @@ ENTRY(cpu_xscale_set_pte_ext) .align .globl cpu_xscale_suspend_size -.equ cpu_xscale_suspend_size, 4 * 7 +.equ cpu_xscale_suspend_size, 4 * 6 #ifdef CONFIG_PM_SLEEP ENTRY(cpu_xscale_do_suspend) - stmfd sp!, {r4 - r10, lr} + stmfd sp!, {r4 - r9, lr} mrc p14, 0, r4, c6, c0, 0 @ clock configuration, for turbo mode mrc p15, 0, r5, c15, c1, 0 @ CP access reg mrc p15, 0, r6, c13, c0, 0 @ PID mrc p15, 0, r7, c3, c0, 0 @ domain ID - mrc p15, 0, r8, c2, c0, 0 @ translation table base addr - mrc p15, 0, r9, c1, c1, 0 @ auxiliary control reg - mrc p15, 0, r10, c1, c0, 0 @ control reg + mrc p15, 0, r8, c1, c1, 0 @ auxiliary control reg + mrc p15, 0, r9, c1, c0, 0 @ control reg bic r4, r4, #2 @ clear frequency change bit - stmia r0, {r4 - r10} @ store cp regs - ldmfd sp!, {r4 - r10, pc} + stmia r0, {r4 - r9} @ store cp regs + ldmfd sp!, {r4 - r9, pc} ENDPROC(cpu_xscale_do_suspend) ENTRY(cpu_xscale_do_resume) - ldmia r0, {r4 - r10} @ load cp regs + ldmia r0, {r4 - r9} @ load cp regs mov ip, #0 mcr p15, 0, ip, c8, c7, 0 @ invalidate I & D TLBs mcr p15, 0, ip, c7, c7, 0 @ invalidate I & D caches, BTB @@ -545,13 +547,9 @@ ENTRY(cpu_xscale_do_resume) mcr p15, 0, r5, c15, c1, 0 @ CP access reg mcr p15, 0, r6, c13, c0, 0 @ PID mcr p15, 0, r7, c3, c0, 0 @ domain ID - mcr p15, 0, r8, c2, c0, 0 @ translation table base addr - mcr p15, 0, r9, c1, c1, 0 @ auxiliary control reg - mov r0, r10 @ control register - mov r2, r8, lsr #14 @ get TTB0 base - mov r2, r2, lsl #14 - ldr r3, =PMD_TYPE_SECT | PMD_SECT_BUFFERABLE | \ - PMD_SECT_CACHEABLE | PMD_SECT_AP_WRITE + mcr p15, 0, r1, c2, c0, 0 @ translation table base addr + mcr p15, 0, r8, c1, c1, 0 @ auxiliary control reg + mov r0, r9 @ control register b cpu_resume_mmu ENDPROC(cpu_xscale_do_resume) #endif |
