diff options
Diffstat (limited to 'arch/arm/mm')
37 files changed, 2581 insertions, 1086 deletions
diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig index db5c2cab8fd..c348eaee7ee 100644 --- a/arch/arm/mm/Kconfig +++ b/arch/arm/mm/Kconfig @@ -264,7 +264,7 @@ config CPU_ARM1026 # SA110 config CPU_SA110 - bool "Support StrongARM(R) SA-110 processor" if ARCH_RPC + bool select CPU_32v3 if ARCH_RPC select CPU_32v4 if !ARCH_RPC select CPU_ABRT_EV4 @@ -420,33 +420,32 @@ config CPU_32v3 bool select CPU_USE_DOMAINS if MMU select NEEDS_SYSCALL_FOR_CMPXCHG if SMP - select TLS_REG_EMUL if SMP || !MMU select NEED_KUSER_HELPERS + select TLS_REG_EMUL if SMP || !MMU config CPU_32v4 bool select CPU_USE_DOMAINS if MMU select NEEDS_SYSCALL_FOR_CMPXCHG if SMP - select TLS_REG_EMUL if SMP || !MMU select NEED_KUSER_HELPERS + select TLS_REG_EMUL if SMP || !MMU config CPU_32v4T bool select CPU_USE_DOMAINS if MMU select NEEDS_SYSCALL_FOR_CMPXCHG if SMP - select TLS_REG_EMUL if SMP || !MMU select NEED_KUSER_HELPERS + select TLS_REG_EMUL if SMP || !MMU config CPU_32v5 bool select CPU_USE_DOMAINS if MMU select NEEDS_SYSCALL_FOR_CMPXCHG if SMP - select TLS_REG_EMUL if SMP || !MMU select NEED_KUSER_HELPERS + select TLS_REG_EMUL if SMP || !MMU config CPU_32v6 bool - select CPU_USE_DOMAINS if CPU_V6 && MMU select TLS_REG_EMUL if !CPU_32v6K && !MMU config CPU_32v6K @@ -671,7 +670,7 @@ config ARM_VIRT_EXT config SWP_EMULATE bool "Emulate SWP/SWPB instructions" - depends on !CPU_USE_DOMAINS && CPU_V7 + depends on CPU_V7 default y if SMP select HAVE_PROC_CPU if PROC_FS help @@ -809,15 +808,18 @@ config KUSER_HELPERS the CPU type fitted to the system. This permits binaries to be run on ARMv4 through to ARMv7 without modification. + See Documentation/arm/kernel_user_helpers.txt for details. + However, the fixed address nature of these helpers can be used by ROP (return orientated programming) authors when creating exploits. If all of the binaries and libraries which run on your platform are built specifically for your platform, and make no use of - these helpers, then you can turn this option off. However, - when such an binary or library is run, it will receive a SIGILL - signal, which will terminate the program. + these helpers, then you can turn this option off to hinder + such exploits. However, in that case, if a binary or library + relying on those helpers is run, it will receive a SIGILL signal, + which will terminate the program. Say N here only if you are absolutely certain that you do not need these helpers; otherwise, the safe option is to say Y. @@ -852,7 +854,7 @@ config OUTER_CACHE_SYNC config CACHE_FEROCEON_L2 bool "Enable the Feroceon L2 cache controller" - depends on ARCH_KIRKWOOD || ARCH_MV78XX0 + depends on ARCH_KIRKWOOD || ARCH_MV78XX0 || ARCH_MVEBU default y select OUTER_CACHE help @@ -887,14 +889,64 @@ config CACHE_L2X0 help This option enables the L2x0 PrimeCell. +if CACHE_L2X0 + config CACHE_PL310 bool - depends on CACHE_L2X0 default y if CPU_V7 && !(CPU_V6 || CPU_V6K) help This option enables optimisations for the PL310 cache controller. +config PL310_ERRATA_588369 + bool "PL310 errata: Clean & Invalidate maintenance operations do not invalidate clean lines" + help + The PL310 L2 cache controller implements three types of Clean & + Invalidate maintenance operations: by Physical Address + (offset 0x7F0), by Index/Way (0x7F8) and by Way (0x7FC). + They are architecturally defined to behave as the execution of a + clean operation followed immediately by an invalidate operation, + both performing to the same memory location. This functionality + is not correctly implemented in PL310 as clean lines are not + invalidated as a result of these operations. + +config PL310_ERRATA_727915 + bool "PL310 errata: Background Clean & Invalidate by Way operation can cause data corruption" + help + PL310 implements the Clean & Invalidate by Way L2 cache maintenance + operation (offset 0x7FC). This operation runs in background so that + PL310 can handle normal accesses while it is in progress. Under very + rare circumstances, due to this erratum, write data can be lost when + PL310 treats a cacheable write transaction during a Clean & + Invalidate by Way operation. + +config PL310_ERRATA_753970 + bool "PL310 errata: cache sync operation may be faulty" + help + This option enables the workaround for the 753970 PL310 (r3p0) erratum. + + Under some condition the effect of cache sync operation on + the store buffer still remains when the operation completes. + This means that the store buffer is always asked to drain and + this prevents it from merging any further writes. The workaround + is to replace the normal offset of cache sync operation (0x730) + by another offset targeting an unmapped PL310 register 0x740. + This has the same effect as the cache sync operation: store buffer + drain and waiting for all buffers empty. + +config PL310_ERRATA_769419 + bool "PL310 errata: no automatic Store Buffer drain" + help + On revisions of the PL310 prior to r3p2, the Store Buffer does + not automatically drain. This can cause normal, non-cacheable + writes to be retained when the memory system is idle, leading + to suboptimal I/O performance for drivers using coherent DMA. + This option adds a write barrier to the cpu_idle loop so that, + on systems with an outer cache, the store buffer is drained + explicitly. + +endif + config CACHE_TAUROS2 bool "Enable the Tauros2 L2 cache controller" depends on (ARCH_DOVE || ARCH_MMP || CPU_PJ4) @@ -949,3 +1001,9 @@ config ARCH_HAS_BARRIERS help This option allows the use of custom mandatory barriers included via the mach/barriers.h file. + +config ARCH_SUPPORTS_BIG_ENDIAN + bool + help + This option specifies the architecture can support big endian + operation. diff --git a/arch/arm/mm/Makefile b/arch/arm/mm/Makefile index ecfe6e53f6e..91da64de440 100644 --- a/arch/arm/mm/Makefile +++ b/arch/arm/mm/Makefile @@ -12,6 +12,7 @@ ifneq ($(CONFIG_MMU),y) obj-y += nommu.o endif +obj-$(CONFIG_ARM_PTDUMP) += dump.o obj-$(CONFIG_MODULES) += proc-syms.o obj-$(CONFIG_ALIGNMENT_TRAP) += alignment.o @@ -94,7 +95,8 @@ obj-$(CONFIG_CPU_V7M) += proc-v7m.o AFLAGS_proc-v6.o :=-Wa,-march=armv6 AFLAGS_proc-v7.o :=-Wa,-march=armv7-a +obj-$(CONFIG_OUTER_CACHE) += l2c-common.o obj-$(CONFIG_CACHE_FEROCEON_L2) += cache-feroceon-l2.o -obj-$(CONFIG_CACHE_L2X0) += cache-l2x0.o +obj-$(CONFIG_CACHE_L2X0) += cache-l2x0.o l2c-l2x0-resume.o obj-$(CONFIG_CACHE_XSC3L2) += cache-xsc3l2.o obj-$(CONFIG_CACHE_TAUROS2) += cache-tauros2.o diff --git a/arch/arm/mm/abort-ev6.S b/arch/arm/mm/abort-ev6.S index 80741992a9f..3815a8262af 100644 --- a/arch/arm/mm/abort-ev6.S +++ b/arch/arm/mm/abort-ev6.S @@ -38,9 +38,8 @@ ENTRY(v6_early_abort) bne do_DataAbort bic r1, r1, #1 << 11 @ clear bit 11 of FSR ldr r3, [r4] @ read aborted ARM instruction -#ifdef CONFIG_CPU_ENDIAN_BE8 - rev r3, r3 -#endif + ARM_BE8(rev r3, r3) + do_ldrd_abort tmp=ip, insn=r3 tst r3, #1 << 20 @ L = 0 -> write orreq r1, r1, #1 << 11 @ yes. diff --git a/arch/arm/mm/alignment.c b/arch/arm/mm/alignment.c index 6f4585b8907..b8cb1a2688a 100644 --- a/arch/arm/mm/alignment.c +++ b/arch/arm/mm/alignment.c @@ -25,8 +25,10 @@ #include <asm/cp15.h> #include <asm/system_info.h> #include <asm/unaligned.h> +#include <asm/opcodes.h> #include "fault.h" +#include "mm.h" /* * 32-bit misaligned trap handler (c) 1998 San Mehat (CCC) -July 1998 @@ -80,6 +82,7 @@ static unsigned long ai_word; static unsigned long ai_dword; static unsigned long ai_multi; static int ai_usermode; +static unsigned long cr_no_alignment; core_param(alignment, ai_usermode, int, 0600); @@ -90,7 +93,7 @@ core_param(alignment, ai_usermode, int, 0600); /* Return true if and only if the ARMv6 unaligned access model is in use. */ static bool cpu_is_v6_unaligned(void) { - return cpu_architecture() >= CPU_ARCH_ARMv6 && (cr_alignment & CR_U); + return cpu_architecture() >= CPU_ARCH_ARMv6 && get_cr() & CR_U; } static int safe_usermode(int new_usermode, bool warn) @@ -762,21 +765,25 @@ do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs) if (thumb_mode(regs)) { u16 *ptr = (u16 *)(instrptr & ~1); fault = probe_kernel_address(ptr, tinstr); + tinstr = __mem_to_opcode_thumb16(tinstr); if (!fault) { if (cpu_architecture() >= CPU_ARCH_ARMv7 && IS_T32(tinstr)) { /* Thumb-2 32-bit */ u16 tinst2 = 0; fault = probe_kernel_address(ptr + 1, tinst2); - instr = (tinstr << 16) | tinst2; + tinst2 = __mem_to_opcode_thumb16(tinst2); + instr = __opcode_thumb32_compose(tinstr, tinst2); thumb2_32b = 1; } else { isize = 2; instr = thumb2arm(tinstr); } } - } else + } else { fault = probe_kernel_address(instrptr, instr); + instr = __mem_to_opcode_arm(instr); + } if (fault) { type = TYPE_FAULT; @@ -944,6 +951,13 @@ do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs) return 0; } +static int __init noalign_setup(char *__unused) +{ + set_cr(__clear_cr(CR_A)); + return 1; +} +__setup("noalign", noalign_setup); + /* * This needs to be done after sysctl_init, otherwise sys/ will be * overwritten. Actually, this shouldn't be in sys/ at all since @@ -961,14 +975,12 @@ static int __init alignment_init(void) return -ENOMEM; #endif -#ifdef CONFIG_CPU_CP15 if (cpu_is_v6_unaligned()) { - cr_alignment &= ~CR_A; - cr_no_alignment &= ~CR_A; - set_cr(cr_alignment); + set_cr(__clear_cr(CR_A)); ai_usermode = safe_usermode(ai_usermode, false); } -#endif + + cr_no_alignment = get_cr() & ~CR_A; hook_fault_code(FAULT_CODE_ALIGNMENT, do_alignment, SIGBUS, BUS_ADRALN, "alignment exception"); diff --git a/arch/arm/mm/cache-feroceon-l2.c b/arch/arm/mm/cache-feroceon-l2.c index 48bc3c0a87c..e028a7f2ebc 100644 --- a/arch/arm/mm/cache-feroceon-l2.c +++ b/arch/arm/mm/cache-feroceon-l2.c @@ -13,10 +13,15 @@ */ #include <linux/init.h> +#include <linux/of.h> +#include <linux/of_address.h> #include <linux/highmem.h> +#include <linux/io.h> #include <asm/cacheflush.h> #include <asm/cp15.h> -#include <plat/cache-feroceon-l2.h> +#include <asm/hardware/cache-feroceon-l2.h> + +#define L2_WRITETHROUGH_KIRKWOOD BIT(4) /* * Low-level cache maintenance operations. @@ -331,7 +336,9 @@ static void __init enable_l2(void) enable_icache(); if (d) enable_dcache(); - } + } else + pr_err(FW_BUG + "Feroceon L2: bootloader left the L2 cache on!\n"); } void __init feroceon_l2_init(int __l2_wt_override) @@ -343,10 +350,47 @@ void __init feroceon_l2_init(int __l2_wt_override) outer_cache.inv_range = feroceon_l2_inv_range; outer_cache.clean_range = feroceon_l2_clean_range; outer_cache.flush_range = feroceon_l2_flush_range; - outer_cache.inv_all = l2_inv_all; enable_l2(); printk(KERN_INFO "Feroceon L2: Cache support initialised%s.\n", l2_wt_override ? ", in WT override mode" : ""); } +#ifdef CONFIG_OF +static const struct of_device_id feroceon_ids[] __initconst = { + { .compatible = "marvell,kirkwood-cache"}, + { .compatible = "marvell,feroceon-cache"}, + {} +}; + +int __init feroceon_of_init(void) +{ + struct device_node *node; + void __iomem *base; + bool l2_wt_override = false; + struct resource res; + +#if defined(CONFIG_CACHE_FEROCEON_L2_WRITETHROUGH) + l2_wt_override = true; +#endif + + node = of_find_matching_node(NULL, feroceon_ids); + if (node && of_device_is_compatible(node, "marvell,kirkwood-cache")) { + if (of_address_to_resource(node, 0, &res)) + return -ENODEV; + + base = ioremap(res.start, resource_size(&res)); + if (!base) + return -ENOMEM; + + if (l2_wt_override) + writel(readl(base) | L2_WRITETHROUGH_KIRKWOOD, base); + else + writel(readl(base) & ~L2_WRITETHROUGH_KIRKWOOD, base); + } + + feroceon_l2_init(l2_wt_override); + + return 0; +} +#endif diff --git a/arch/arm/mm/cache-l2x0.c b/arch/arm/mm/cache-l2x0.c index d70e0aba0c9..7c3fb41a462 100644 --- a/arch/arm/mm/cache-l2x0.c +++ b/arch/arm/mm/cache-l2x0.c @@ -16,17 +16,33 @@ * along with this program; if not, write to the Free Software * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ +#include <linux/cpu.h> #include <linux/err.h> #include <linux/init.h> +#include <linux/smp.h> #include <linux/spinlock.h> #include <linux/io.h> #include <linux/of.h> #include <linux/of_address.h> #include <asm/cacheflush.h> +#include <asm/cp15.h> +#include <asm/cputype.h> #include <asm/hardware/cache-l2x0.h> +#include "cache-tauros3.h" #include "cache-aurora-l2.h" +struct l2c_init_data { + const char *type; + unsigned way_size_0; + unsigned num_lock; + void (*of_parse)(const struct device_node *, u32 *, u32 *); + void (*enable)(void __iomem *, u32, unsigned); + void (*fixup)(void __iomem *, u32, struct outer_cache_fns *); + void (*save)(void __iomem *); + struct outer_cache_fns outer_cache; +}; + #define CACHE_LINE_SIZE 32 static void __iomem *l2x0_base; @@ -35,96 +51,116 @@ static u32 l2x0_way_mask; /* Bitmask of active ways */ static u32 l2x0_size; static unsigned long sync_reg_offset = L2X0_CACHE_SYNC; -/* Aurora don't have the cache ID register available, so we have to - * pass it though the device tree */ -static u32 cache_id_part_number_from_dt; - struct l2x0_regs l2x0_saved_regs; -struct l2x0_of_data { - void (*setup)(const struct device_node *, u32 *, u32 *); - void (*save)(void); - struct outer_cache_fns outer_cache; -}; - -static bool of_init = false; - -static inline void cache_wait_way(void __iomem *reg, unsigned long mask) +/* + * Common code for all cache controllers. + */ +static inline void l2c_wait_mask(void __iomem *reg, unsigned long mask) { /* wait for cache operation by line or way to complete */ while (readl_relaxed(reg) & mask) cpu_relax(); } -#ifdef CONFIG_CACHE_PL310 -static inline void cache_wait(void __iomem *reg, unsigned long mask) +/* + * By default, we write directly to secure registers. Platforms must + * override this if they are running non-secure. + */ +static void l2c_write_sec(unsigned long val, void __iomem *base, unsigned reg) { - /* cache operations by line are atomic on PL310 */ + if (val == readl_relaxed(base + reg)) + return; + if (outer_cache.write_sec) + outer_cache.write_sec(val, reg); + else + writel_relaxed(val, base + reg); } -#else -#define cache_wait cache_wait_way -#endif -static inline void cache_sync(void) +/* + * This should only be called when we have a requirement that the + * register be written due to a work-around, as platforms running + * in non-secure mode may not be able to access this register. + */ +static inline void l2c_set_debug(void __iomem *base, unsigned long val) { - void __iomem *base = l2x0_base; - - writel_relaxed(0, base + sync_reg_offset); - cache_wait(base + L2X0_CACHE_SYNC, 1); + l2c_write_sec(val, base, L2X0_DEBUG_CTRL); } -static inline void l2x0_clean_line(unsigned long addr) +static void __l2c_op_way(void __iomem *reg) { - void __iomem *base = l2x0_base; - cache_wait(base + L2X0_CLEAN_LINE_PA, 1); - writel_relaxed(addr, base + L2X0_CLEAN_LINE_PA); + writel_relaxed(l2x0_way_mask, reg); + l2c_wait_mask(reg, l2x0_way_mask); } -static inline void l2x0_inv_line(unsigned long addr) +static inline void l2c_unlock(void __iomem *base, unsigned num) { - void __iomem *base = l2x0_base; - cache_wait(base + L2X0_INV_LINE_PA, 1); - writel_relaxed(addr, base + L2X0_INV_LINE_PA); + unsigned i; + + for (i = 0; i < num; i++) { + writel_relaxed(0, base + L2X0_LOCKDOWN_WAY_D_BASE + + i * L2X0_LOCKDOWN_STRIDE); + writel_relaxed(0, base + L2X0_LOCKDOWN_WAY_I_BASE + + i * L2X0_LOCKDOWN_STRIDE); + } } -#if defined(CONFIG_PL310_ERRATA_588369) || defined(CONFIG_PL310_ERRATA_727915) -static inline void debug_writel(unsigned long val) +/* + * Enable the L2 cache controller. This function must only be + * called when the cache controller is known to be disabled. + */ +static void l2c_enable(void __iomem *base, u32 aux, unsigned num_lock) { - if (outer_cache.set_debug) - outer_cache.set_debug(val); + unsigned long flags; + + l2c_write_sec(aux, base, L2X0_AUX_CTRL); + + l2c_unlock(base, num_lock); + + local_irq_save(flags); + __l2c_op_way(base + L2X0_INV_WAY); + writel_relaxed(0, base + sync_reg_offset); + l2c_wait_mask(base + sync_reg_offset, 1); + local_irq_restore(flags); + + l2c_write_sec(L2X0_CTRL_EN, base, L2X0_CTRL); } -static void pl310_set_debug(unsigned long val) +static void l2c_disable(void) { - writel_relaxed(val, l2x0_base + L2X0_DEBUG_CTRL); + void __iomem *base = l2x0_base; + + outer_cache.flush_all(); + l2c_write_sec(0, base, L2X0_CTRL); + dsb(st); } -#else -/* Optimised out for non-errata case */ -static inline void debug_writel(unsigned long val) + +#ifdef CONFIG_CACHE_PL310 +static inline void cache_wait(void __iomem *reg, unsigned long mask) { + /* cache operations by line are atomic on PL310 */ } - -#define pl310_set_debug NULL +#else +#define cache_wait l2c_wait_mask #endif -#ifdef CONFIG_PL310_ERRATA_588369 -static inline void l2x0_flush_line(unsigned long addr) +static inline void cache_sync(void) { void __iomem *base = l2x0_base; - /* Clean by PA followed by Invalidate by PA */ - cache_wait(base + L2X0_CLEAN_LINE_PA, 1); - writel_relaxed(addr, base + L2X0_CLEAN_LINE_PA); - cache_wait(base + L2X0_INV_LINE_PA, 1); - writel_relaxed(addr, base + L2X0_INV_LINE_PA); + writel_relaxed(0, base + sync_reg_offset); + cache_wait(base + L2X0_CACHE_SYNC, 1); } -#else -static inline void l2x0_flush_line(unsigned long addr) +#if defined(CONFIG_PL310_ERRATA_588369) || defined(CONFIG_PL310_ERRATA_727915) +static inline void debug_writel(unsigned long val) +{ + l2c_set_debug(l2x0_base, val); +} +#else +/* Optimised out for non-errata case */ +static inline void debug_writel(unsigned long val) { - void __iomem *base = l2x0_base; - cache_wait(base + L2X0_CLEAN_INV_LINE_PA, 1); - writel_relaxed(addr, base + L2X0_CLEAN_INV_LINE_PA); } #endif @@ -140,8 +176,7 @@ static void l2x0_cache_sync(void) static void __l2x0_flush_all(void) { debug_writel(0x03); - writel_relaxed(l2x0_way_mask, l2x0_base + L2X0_CLEAN_INV_WAY); - cache_wait_way(l2x0_base + L2X0_CLEAN_INV_WAY, l2x0_way_mask); + __l2c_op_way(l2x0_base + L2X0_CLEAN_INV_WAY); cache_sync(); debug_writel(0x00); } @@ -156,275 +191,910 @@ static void l2x0_flush_all(void) raw_spin_unlock_irqrestore(&l2x0_lock, flags); } -static void l2x0_clean_all(void) +static void l2x0_disable(void) { unsigned long flags; - /* clean all ways */ raw_spin_lock_irqsave(&l2x0_lock, flags); - writel_relaxed(l2x0_way_mask, l2x0_base + L2X0_CLEAN_WAY); - cache_wait_way(l2x0_base + L2X0_CLEAN_WAY, l2x0_way_mask); - cache_sync(); + __l2x0_flush_all(); + l2c_write_sec(0, l2x0_base, L2X0_CTRL); + dsb(st); raw_spin_unlock_irqrestore(&l2x0_lock, flags); } -static void l2x0_inv_all(void) +static void l2c_save(void __iomem *base) { - unsigned long flags; + l2x0_saved_regs.aux_ctrl = readl_relaxed(l2x0_base + L2X0_AUX_CTRL); +} - /* invalidate all ways */ - raw_spin_lock_irqsave(&l2x0_lock, flags); - /* Invalidating when L2 is enabled is a nono */ - BUG_ON(readl(l2x0_base + L2X0_CTRL) & L2X0_CTRL_EN); - writel_relaxed(l2x0_way_mask, l2x0_base + L2X0_INV_WAY); - cache_wait_way(l2x0_base + L2X0_INV_WAY, l2x0_way_mask); - cache_sync(); - raw_spin_unlock_irqrestore(&l2x0_lock, flags); +/* + * L2C-210 specific code. + * + * The L2C-2x0 PA, set/way and sync operations are atomic, but we must + * ensure that no background operation is running. The way operations + * are all background tasks. + * + * While a background operation is in progress, any new operation is + * ignored (unspecified whether this causes an error.) Thankfully, not + * used on SMP. + * + * Never has a different sync register other than L2X0_CACHE_SYNC, but + * we use sync_reg_offset here so we can share some of this with L2C-310. + */ +static void __l2c210_cache_sync(void __iomem *base) +{ + writel_relaxed(0, base + sync_reg_offset); } -static void l2x0_inv_range(unsigned long start, unsigned long end) +static void __l2c210_op_pa_range(void __iomem *reg, unsigned long start, + unsigned long end) +{ + while (start < end) { + writel_relaxed(start, reg); + start += CACHE_LINE_SIZE; + } +} + +static void l2c210_inv_range(unsigned long start, unsigned long end) { void __iomem *base = l2x0_base; - unsigned long flags; - raw_spin_lock_irqsave(&l2x0_lock, flags); if (start & (CACHE_LINE_SIZE - 1)) { start &= ~(CACHE_LINE_SIZE - 1); - debug_writel(0x03); - l2x0_flush_line(start); - debug_writel(0x00); + writel_relaxed(start, base + L2X0_CLEAN_INV_LINE_PA); start += CACHE_LINE_SIZE; } if (end & (CACHE_LINE_SIZE - 1)) { end &= ~(CACHE_LINE_SIZE - 1); - debug_writel(0x03); - l2x0_flush_line(end); - debug_writel(0x00); + writel_relaxed(end, base + L2X0_CLEAN_INV_LINE_PA); } + __l2c210_op_pa_range(base + L2X0_INV_LINE_PA, start, end); + __l2c210_cache_sync(base); +} + +static void l2c210_clean_range(unsigned long start, unsigned long end) +{ + void __iomem *base = l2x0_base; + + start &= ~(CACHE_LINE_SIZE - 1); + __l2c210_op_pa_range(base + L2X0_CLEAN_LINE_PA, start, end); + __l2c210_cache_sync(base); +} + +static void l2c210_flush_range(unsigned long start, unsigned long end) +{ + void __iomem *base = l2x0_base; + + start &= ~(CACHE_LINE_SIZE - 1); + __l2c210_op_pa_range(base + L2X0_CLEAN_INV_LINE_PA, start, end); + __l2c210_cache_sync(base); +} + +static void l2c210_flush_all(void) +{ + void __iomem *base = l2x0_base; + + BUG_ON(!irqs_disabled()); + + __l2c_op_way(base + L2X0_CLEAN_INV_WAY); + __l2c210_cache_sync(base); +} + +static void l2c210_sync(void) +{ + __l2c210_cache_sync(l2x0_base); +} + +static void l2c210_resume(void) +{ + void __iomem *base = l2x0_base; + + if (!(readl_relaxed(base + L2X0_CTRL) & L2X0_CTRL_EN)) + l2c_enable(base, l2x0_saved_regs.aux_ctrl, 1); +} + +static const struct l2c_init_data l2c210_data __initconst = { + .type = "L2C-210", + .way_size_0 = SZ_8K, + .num_lock = 1, + .enable = l2c_enable, + .save = l2c_save, + .outer_cache = { + .inv_range = l2c210_inv_range, + .clean_range = l2c210_clean_range, + .flush_range = l2c210_flush_range, + .flush_all = l2c210_flush_all, + .disable = l2c_disable, + .sync = l2c210_sync, + .resume = l2c210_resume, + }, +}; + +/* + * L2C-220 specific code. + * + * All operations are background operations: they have to be waited for. + * Conflicting requests generate a slave error (which will cause an + * imprecise abort.) Never uses sync_reg_offset, so we hard-code the + * sync register here. + * + * However, we can re-use the l2c210_resume call. + */ +static inline void __l2c220_cache_sync(void __iomem *base) +{ + writel_relaxed(0, base + L2X0_CACHE_SYNC); + l2c_wait_mask(base + L2X0_CACHE_SYNC, 1); +} + +static void l2c220_op_way(void __iomem *base, unsigned reg) +{ + unsigned long flags; + + raw_spin_lock_irqsave(&l2x0_lock, flags); + __l2c_op_way(base + reg); + __l2c220_cache_sync(base); + raw_spin_unlock_irqrestore(&l2x0_lock, flags); +} + +static unsigned long l2c220_op_pa_range(void __iomem *reg, unsigned long start, + unsigned long end, unsigned long flags) +{ + raw_spinlock_t *lock = &l2x0_lock; + while (start < end) { unsigned long blk_end = start + min(end - start, 4096UL); while (start < blk_end) { - l2x0_inv_line(start); + l2c_wait_mask(reg, 1); + writel_relaxed(start, reg); start += CACHE_LINE_SIZE; } if (blk_end < end) { - raw_spin_unlock_irqrestore(&l2x0_lock, flags); - raw_spin_lock_irqsave(&l2x0_lock, flags); + raw_spin_unlock_irqrestore(lock, flags); + raw_spin_lock_irqsave(lock, flags); } } - cache_wait(base + L2X0_INV_LINE_PA, 1); - cache_sync(); - raw_spin_unlock_irqrestore(&l2x0_lock, flags); + + return flags; } -static void l2x0_clean_range(unsigned long start, unsigned long end) +static void l2c220_inv_range(unsigned long start, unsigned long end) { void __iomem *base = l2x0_base; unsigned long flags; - if ((end - start) >= l2x0_size) { - l2x0_clean_all(); - return; - } - raw_spin_lock_irqsave(&l2x0_lock, flags); - start &= ~(CACHE_LINE_SIZE - 1); - while (start < end) { - unsigned long blk_end = start + min(end - start, 4096UL); - - while (start < blk_end) { - l2x0_clean_line(start); + if ((start | end) & (CACHE_LINE_SIZE - 1)) { + if (start & (CACHE_LINE_SIZE - 1)) { + start &= ~(CACHE_LINE_SIZE - 1); + writel_relaxed(start, base + L2X0_CLEAN_INV_LINE_PA); start += CACHE_LINE_SIZE; } - if (blk_end < end) { - raw_spin_unlock_irqrestore(&l2x0_lock, flags); - raw_spin_lock_irqsave(&l2x0_lock, flags); + if (end & (CACHE_LINE_SIZE - 1)) { + end &= ~(CACHE_LINE_SIZE - 1); + l2c_wait_mask(base + L2X0_CLEAN_INV_LINE_PA, 1); + writel_relaxed(end, base + L2X0_CLEAN_INV_LINE_PA); } } - cache_wait(base + L2X0_CLEAN_LINE_PA, 1); - cache_sync(); + + flags = l2c220_op_pa_range(base + L2X0_INV_LINE_PA, + start, end, flags); + l2c_wait_mask(base + L2X0_INV_LINE_PA, 1); + __l2c220_cache_sync(base); raw_spin_unlock_irqrestore(&l2x0_lock, flags); } -static void l2x0_flush_range(unsigned long start, unsigned long end) +static void l2c220_clean_range(unsigned long start, unsigned long end) { void __iomem *base = l2x0_base; unsigned long flags; + start &= ~(CACHE_LINE_SIZE - 1); if ((end - start) >= l2x0_size) { - l2x0_flush_all(); + l2c220_op_way(base, L2X0_CLEAN_WAY); return; } raw_spin_lock_irqsave(&l2x0_lock, flags); + flags = l2c220_op_pa_range(base + L2X0_CLEAN_LINE_PA, + start, end, flags); + l2c_wait_mask(base + L2X0_CLEAN_INV_LINE_PA, 1); + __l2c220_cache_sync(base); + raw_spin_unlock_irqrestore(&l2x0_lock, flags); +} + +static void l2c220_flush_range(unsigned long start, unsigned long end) +{ + void __iomem *base = l2x0_base; + unsigned long flags; + start &= ~(CACHE_LINE_SIZE - 1); + if ((end - start) >= l2x0_size) { + l2c220_op_way(base, L2X0_CLEAN_INV_WAY); + return; + } + + raw_spin_lock_irqsave(&l2x0_lock, flags); + flags = l2c220_op_pa_range(base + L2X0_CLEAN_INV_LINE_PA, + start, end, flags); + l2c_wait_mask(base + L2X0_CLEAN_INV_LINE_PA, 1); + __l2c220_cache_sync(base); + raw_spin_unlock_irqrestore(&l2x0_lock, flags); +} + +static void l2c220_flush_all(void) +{ + l2c220_op_way(l2x0_base, L2X0_CLEAN_INV_WAY); +} + +static void l2c220_sync(void) +{ + unsigned long flags; + + raw_spin_lock_irqsave(&l2x0_lock, flags); + __l2c220_cache_sync(l2x0_base); + raw_spin_unlock_irqrestore(&l2x0_lock, flags); +} + +static void l2c220_enable(void __iomem *base, u32 aux, unsigned num_lock) +{ + /* + * Always enable non-secure access to the lockdown registers - + * we write to them as part of the L2C enable sequence so they + * need to be accessible. + */ + aux |= L220_AUX_CTRL_NS_LOCKDOWN; + + l2c_enable(base, aux, num_lock); +} + +static const struct l2c_init_data l2c220_data = { + .type = "L2C-220", + .way_size_0 = SZ_8K, + .num_lock = 1, + .enable = l2c220_enable, + .save = l2c_save, + .outer_cache = { + .inv_range = l2c220_inv_range, + .clean_range = l2c220_clean_range, + .flush_range = l2c220_flush_range, + .flush_all = l2c220_flush_all, + .disable = l2c_disable, + .sync = l2c220_sync, + .resume = l2c210_resume, + }, +}; + +/* + * L2C-310 specific code. + * + * Very similar to L2C-210, the PA, set/way and sync operations are atomic, + * and the way operations are all background tasks. However, issuing an + * operation while a background operation is in progress results in a + * SLVERR response. We can reuse: + * + * __l2c210_cache_sync (using sync_reg_offset) + * l2c210_sync + * l2c210_inv_range (if 588369 is not applicable) + * l2c210_clean_range + * l2c210_flush_range (if 588369 is not applicable) + * l2c210_flush_all (if 727915 is not applicable) + * + * Errata: + * 588369: PL310 R0P0->R1P0, fixed R2P0. + * Affects: all clean+invalidate operations + * clean and invalidate skips the invalidate step, so we need to issue + * separate operations. We also require the above debug workaround + * enclosing this code fragment on affected parts. On unaffected parts, + * we must not use this workaround without the debug register writes + * to avoid exposing a problem similar to 727915. + * + * 727915: PL310 R2P0->R3P0, fixed R3P1. + * Affects: clean+invalidate by way + * clean and invalidate by way runs in the background, and a store can + * hit the line between the clean operation and invalidate operation, + * resulting in the store being lost. + * + * 752271: PL310 R3P0->R3P1-50REL0, fixed R3P2. + * Affects: 8x64-bit (double fill) line fetches + * double fill line fetches can fail to cause dirty data to be evicted + * from the cache before the new data overwrites the second line. + * + * 753970: PL310 R3P0, fixed R3P1. + * Affects: sync + * prevents merging writes after the sync operation, until another L2C + * operation is performed (or a number of other conditions.) + * + * 769419: PL310 R0P0->R3P1, fixed R3P2. + * Affects: store buffer + * store buffer is not automatically drained. + */ +static void l2c310_inv_range_erratum(unsigned long start, unsigned long end) +{ + void __iomem *base = l2x0_base; + + if ((start | end) & (CACHE_LINE_SIZE - 1)) { + unsigned long flags; + + /* Erratum 588369 for both clean+invalidate operations */ + raw_spin_lock_irqsave(&l2x0_lock, flags); + l2c_set_debug(base, 0x03); + + if (start & (CACHE_LINE_SIZE - 1)) { + start &= ~(CACHE_LINE_SIZE - 1); + writel_relaxed(start, base + L2X0_CLEAN_LINE_PA); + writel_relaxed(start, base + L2X0_INV_LINE_PA); + start += CACHE_LINE_SIZE; + } + + if (end & (CACHE_LINE_SIZE - 1)) { + end &= ~(CACHE_LINE_SIZE - 1); + writel_relaxed(end, base + L2X0_CLEAN_LINE_PA); + writel_relaxed(end, base + L2X0_INV_LINE_PA); + } + + l2c_set_debug(base, 0x00); + raw_spin_unlock_irqrestore(&l2x0_lock, flags); + } + + __l2c210_op_pa_range(base + L2X0_INV_LINE_PA, start, end); + __l2c210_cache_sync(base); +} + +static void l2c310_flush_range_erratum(unsigned long start, unsigned long end) +{ + raw_spinlock_t *lock = &l2x0_lock; + unsigned long flags; + void __iomem *base = l2x0_base; + + raw_spin_lock_irqsave(lock, flags); while (start < end) { unsigned long blk_end = start + min(end - start, 4096UL); - debug_writel(0x03); + l2c_set_debug(base, 0x03); while (start < blk_end) { - l2x0_flush_line(start); + writel_relaxed(start, base + L2X0_CLEAN_LINE_PA); + writel_relaxed(start, base + L2X0_INV_LINE_PA); start += CACHE_LINE_SIZE; } - debug_writel(0x00); + l2c_set_debug(base, 0x00); if (blk_end < end) { - raw_spin_unlock_irqrestore(&l2x0_lock, flags); - raw_spin_lock_irqsave(&l2x0_lock, flags); + raw_spin_unlock_irqrestore(lock, flags); + raw_spin_lock_irqsave(lock, flags); } } - cache_wait(base + L2X0_CLEAN_INV_LINE_PA, 1); - cache_sync(); - raw_spin_unlock_irqrestore(&l2x0_lock, flags); + raw_spin_unlock_irqrestore(lock, flags); + __l2c210_cache_sync(base); } -static void l2x0_disable(void) +static void l2c310_flush_all_erratum(void) { + void __iomem *base = l2x0_base; unsigned long flags; raw_spin_lock_irqsave(&l2x0_lock, flags); - __l2x0_flush_all(); - writel_relaxed(0, l2x0_base + L2X0_CTRL); - dsb(); + l2c_set_debug(base, 0x03); + __l2c_op_way(base + L2X0_CLEAN_INV_WAY); + l2c_set_debug(base, 0x00); + __l2c210_cache_sync(base); raw_spin_unlock_irqrestore(&l2x0_lock, flags); } -static void l2x0_unlock(u32 cache_id) +static void __init l2c310_save(void __iomem *base) { - int lockregs; - int i; + unsigned revision; - switch (cache_id & L2X0_CACHE_ID_PART_MASK) { - case L2X0_CACHE_ID_PART_L310: - lockregs = 8; - break; - case AURORA_CACHE_ID: - lockregs = 4; + l2c_save(base); + + l2x0_saved_regs.tag_latency = readl_relaxed(base + + L310_TAG_LATENCY_CTRL); + l2x0_saved_regs.data_latency = readl_relaxed(base + + L310_DATA_LATENCY_CTRL); + l2x0_saved_regs.filter_end = readl_relaxed(base + + L310_ADDR_FILTER_END); + l2x0_saved_regs.filter_start = readl_relaxed(base + + L310_ADDR_FILTER_START); + + revision = readl_relaxed(base + L2X0_CACHE_ID) & + L2X0_CACHE_ID_RTL_MASK; + + /* From r2p0, there is Prefetch offset/control register */ + if (revision >= L310_CACHE_ID_RTL_R2P0) + l2x0_saved_regs.prefetch_ctrl = readl_relaxed(base + + L310_PREFETCH_CTRL); + + /* From r3p0, there is Power control register */ + if (revision >= L310_CACHE_ID_RTL_R3P0) + l2x0_saved_regs.pwr_ctrl = readl_relaxed(base + + L310_POWER_CTRL); +} + +static void l2c310_resume(void) +{ + void __iomem *base = l2x0_base; + + if (!(readl_relaxed(base + L2X0_CTRL) & L2X0_CTRL_EN)) { + unsigned revision; + + /* restore pl310 setup */ + writel_relaxed(l2x0_saved_regs.tag_latency, + base + L310_TAG_LATENCY_CTRL); + writel_relaxed(l2x0_saved_regs.data_latency, + base + L310_DATA_LATENCY_CTRL); + writel_relaxed(l2x0_saved_regs.filter_end, + base + L310_ADDR_FILTER_END); + writel_relaxed(l2x0_saved_regs.filter_start, + base + L310_ADDR_FILTER_START); + + revision = readl_relaxed(base + L2X0_CACHE_ID) & + L2X0_CACHE_ID_RTL_MASK; + + if (revision >= L310_CACHE_ID_RTL_R2P0) + l2c_write_sec(l2x0_saved_regs.prefetch_ctrl, base, + L310_PREFETCH_CTRL); + if (revision >= L310_CACHE_ID_RTL_R3P0) + l2c_write_sec(l2x0_saved_regs.pwr_ctrl, base, + L310_POWER_CTRL); + + l2c_enable(base, l2x0_saved_regs.aux_ctrl, 8); + + /* Re-enable full-line-of-zeros for Cortex-A9 */ + if (l2x0_saved_regs.aux_ctrl & L310_AUX_CTRL_FULL_LINE_ZERO) + set_auxcr(get_auxcr() | BIT(3) | BIT(2) | BIT(1)); + } +} + +static int l2c310_cpu_enable_flz(struct notifier_block *nb, unsigned long act, void *data) +{ + switch (act & ~CPU_TASKS_FROZEN) { + case CPU_STARTING: + set_auxcr(get_auxcr() | BIT(3) | BIT(2) | BIT(1)); break; - default: - /* L210 and unknown types */ - lockregs = 1; + case CPU_DYING: + set_auxcr(get_auxcr() & ~(BIT(3) | BIT(2) | BIT(1))); break; } + return NOTIFY_OK; +} - for (i = 0; i < lockregs; i++) { - writel_relaxed(0x0, l2x0_base + L2X0_LOCKDOWN_WAY_D_BASE + - i * L2X0_LOCKDOWN_STRIDE); - writel_relaxed(0x0, l2x0_base + L2X0_LOCKDOWN_WAY_I_BASE + - i * L2X0_LOCKDOWN_STRIDE); +static void __init l2c310_enable(void __iomem *base, u32 aux, unsigned num_lock) +{ + unsigned rev = readl_relaxed(base + L2X0_CACHE_ID) & L2X0_CACHE_ID_RTL_MASK; + bool cortex_a9 = read_cpuid_part_number() == ARM_CPU_PART_CORTEX_A9; + + if (rev >= L310_CACHE_ID_RTL_R2P0) { + if (cortex_a9) { + aux |= L310_AUX_CTRL_EARLY_BRESP; + pr_info("L2C-310 enabling early BRESP for Cortex-A9\n"); + } else if (aux & L310_AUX_CTRL_EARLY_BRESP) { + pr_warn("L2C-310 early BRESP only supported with Cortex-A9\n"); + aux &= ~L310_AUX_CTRL_EARLY_BRESP; + } + } + + if (cortex_a9) { + u32 aux_cur = readl_relaxed(base + L2X0_AUX_CTRL); + u32 acr = get_auxcr(); + + pr_debug("Cortex-A9 ACR=0x%08x\n", acr); + + if (acr & BIT(3) && !(aux_cur & L310_AUX_CTRL_FULL_LINE_ZERO)) + pr_err("L2C-310: full line of zeros enabled in Cortex-A9 but not L2C-310 - invalid\n"); + + if (aux & L310_AUX_CTRL_FULL_LINE_ZERO && !(acr & BIT(3))) + pr_err("L2C-310: enabling full line of zeros but not enabled in Cortex-A9\n"); + + if (!(aux & L310_AUX_CTRL_FULL_LINE_ZERO) && !outer_cache.write_sec) { + aux |= L310_AUX_CTRL_FULL_LINE_ZERO; + pr_info("L2C-310 full line of zeros enabled for Cortex-A9\n"); + } + } else if (aux & (L310_AUX_CTRL_FULL_LINE_ZERO | L310_AUX_CTRL_EARLY_BRESP)) { + pr_err("L2C-310: disabling Cortex-A9 specific feature bits\n"); + aux &= ~(L310_AUX_CTRL_FULL_LINE_ZERO | L310_AUX_CTRL_EARLY_BRESP); + } + + if (aux & (L310_AUX_CTRL_DATA_PREFETCH | L310_AUX_CTRL_INSTR_PREFETCH)) { + u32 prefetch = readl_relaxed(base + L310_PREFETCH_CTRL); + + pr_info("L2C-310 %s%s prefetch enabled, offset %u lines\n", + aux & L310_AUX_CTRL_INSTR_PREFETCH ? "I" : "", + aux & L310_AUX_CTRL_DATA_PREFETCH ? "D" : "", + 1 + (prefetch & L310_PREFETCH_CTRL_OFFSET_MASK)); + } + + /* r3p0 or later has power control register */ + if (rev >= L310_CACHE_ID_RTL_R3P0) { + u32 power_ctrl; + + l2c_write_sec(L310_DYNAMIC_CLK_GATING_EN | L310_STNDBY_MODE_EN, + base, L310_POWER_CTRL); + power_ctrl = readl_relaxed(base + L310_POWER_CTRL); + pr_info("L2C-310 dynamic clock gating %sabled, standby mode %sabled\n", + power_ctrl & L310_DYNAMIC_CLK_GATING_EN ? "en" : "dis", + power_ctrl & L310_STNDBY_MODE_EN ? "en" : "dis"); + } + + /* + * Always enable non-secure access to the lockdown registers - + * we write to them as part of the L2C enable sequence so they + * need to be accessible. + */ + aux |= L310_AUX_CTRL_NS_LOCKDOWN; + + l2c_enable(base, aux, num_lock); + + if (aux & L310_AUX_CTRL_FULL_LINE_ZERO) { + set_auxcr(get_auxcr() | BIT(3) | BIT(2) | BIT(1)); + cpu_notifier(l2c310_cpu_enable_flz, 0); } } -void __init l2x0_init(void __iomem *base, u32 aux_val, u32 aux_mask) +static void __init l2c310_fixup(void __iomem *base, u32 cache_id, + struct outer_cache_fns *fns) { - u32 aux; - u32 cache_id; - u32 way_size = 0; - int ways; - int way_size_shift = L2X0_WAY_SIZE_SHIFT; - const char *type; + unsigned revision = cache_id & L2X0_CACHE_ID_RTL_MASK; + const char *errata[8]; + unsigned n = 0; + + if (IS_ENABLED(CONFIG_PL310_ERRATA_588369) && + revision < L310_CACHE_ID_RTL_R2P0 && + /* For bcm compatibility */ + fns->inv_range == l2c210_inv_range) { + fns->inv_range = l2c310_inv_range_erratum; + fns->flush_range = l2c310_flush_range_erratum; + errata[n++] = "588369"; + } - l2x0_base = base; - if (cache_id_part_number_from_dt) - cache_id = cache_id_part_number_from_dt; - else - cache_id = readl_relaxed(l2x0_base + L2X0_CACHE_ID); - aux = readl_relaxed(l2x0_base + L2X0_AUX_CTRL); + if (IS_ENABLED(CONFIG_PL310_ERRATA_727915) && + revision >= L310_CACHE_ID_RTL_R2P0 && + revision < L310_CACHE_ID_RTL_R3P1) { + fns->flush_all = l2c310_flush_all_erratum; + errata[n++] = "727915"; + } + + if (revision >= L310_CACHE_ID_RTL_R3P0 && + revision < L310_CACHE_ID_RTL_R3P2) { + u32 val = readl_relaxed(base + L310_PREFETCH_CTRL); + /* I don't think bit23 is required here... but iMX6 does so */ + if (val & (BIT(30) | BIT(23))) { + val &= ~(BIT(30) | BIT(23)); + l2c_write_sec(val, base, L310_PREFETCH_CTRL); + errata[n++] = "752271"; + } + } + + if (IS_ENABLED(CONFIG_PL310_ERRATA_753970) && + revision == L310_CACHE_ID_RTL_R3P0) { + sync_reg_offset = L2X0_DUMMY_REG; + errata[n++] = "753970"; + } + + if (IS_ENABLED(CONFIG_PL310_ERRATA_769419)) + errata[n++] = "769419"; + + if (n) { + unsigned i; + + pr_info("L2C-310 errat%s", n > 1 ? "a" : "um"); + for (i = 0; i < n; i++) + pr_cont(" %s", errata[i]); + pr_cont(" enabled\n"); + } +} + +static void l2c310_disable(void) +{ + /* + * If full-line-of-zeros is enabled, we must first disable it in the + * Cortex-A9 auxiliary control register before disabling the L2 cache. + */ + if (l2x0_saved_regs.aux_ctrl & L310_AUX_CTRL_FULL_LINE_ZERO) + set_auxcr(get_auxcr() & ~(BIT(3) | BIT(2) | BIT(1))); + l2c_disable(); +} + +static const struct l2c_init_data l2c310_init_fns __initconst = { + .type = "L2C-310", + .way_size_0 = SZ_8K, + .num_lock = 8, + .enable = l2c310_enable, + .fixup = l2c310_fixup, + .save = l2c310_save, + .outer_cache = { + .inv_range = l2c210_inv_range, + .clean_range = l2c210_clean_range, + .flush_range = l2c210_flush_range, + .flush_all = l2c210_flush_all, + .disable = l2c310_disable, + .sync = l2c210_sync, + .resume = l2c310_resume, + }, +}; + +static void __init __l2c_init(const struct l2c_init_data *data, + u32 aux_val, u32 aux_mask, u32 cache_id) +{ + struct outer_cache_fns fns; + unsigned way_size_bits, ways; + u32 aux, old_aux; + + /* + * Sanity check the aux values. aux_mask is the bits we preserve + * from reading the hardware register, and aux_val is the bits we + * set. + */ + if (aux_val & aux_mask) + pr_alert("L2C: platform provided aux values permit register corruption.\n"); + + old_aux = aux = readl_relaxed(l2x0_base + L2X0_AUX_CTRL); aux &= aux_mask; aux |= aux_val; + if (old_aux != aux) + pr_warn("L2C: DT/platform modifies aux control register: 0x%08x -> 0x%08x\n", + old_aux, aux); + /* Determine the number of ways */ switch (cache_id & L2X0_CACHE_ID_PART_MASK) { case L2X0_CACHE_ID_PART_L310: + if ((aux_val | ~aux_mask) & (L2C_AUX_CTRL_WAY_SIZE_MASK | L310_AUX_CTRL_ASSOCIATIVITY_16)) + pr_warn("L2C: DT/platform tries to modify or specify cache size\n"); if (aux & (1 << 16)) ways = 16; else ways = 8; - type = "L310"; -#ifdef CONFIG_PL310_ERRATA_753970 - /* Unmapped register. */ - sync_reg_offset = L2X0_DUMMY_REG; -#endif - if ((cache_id & L2X0_CACHE_ID_RTL_MASK) <= L2X0_CACHE_ID_RTL_R3P0) - outer_cache.set_debug = pl310_set_debug; break; + case L2X0_CACHE_ID_PART_L210: + case L2X0_CACHE_ID_PART_L220: ways = (aux >> 13) & 0xf; - type = "L210"; break; case AURORA_CACHE_ID: - sync_reg_offset = AURORA_SYNC_REG; ways = (aux >> 13) & 0xf; ways = 2 << ((ways + 1) >> 2); - way_size_shift = AURORA_WAY_SIZE_SHIFT; - type = "Aurora"; break; + default: /* Assume unknown chips have 8 ways */ ways = 8; - type = "L2x0 series"; break; } l2x0_way_mask = (1 << ways) - 1; /* - * L2 cache Size = Way size * Number of ways + * way_size_0 is the size that a way_size value of zero would be + * given the calculation: way_size = way_size_0 << way_size_bits. + * So, if way_size_bits=0 is reserved, but way_size_bits=1 is 16k, + * then way_size_0 would be 8k. + * + * L2 cache size = number of ways * way size. */ - way_size = (aux & L2X0_AUX_CTRL_WAY_SIZE_MASK) >> 17; - way_size = 1 << (way_size + way_size_shift); + way_size_bits = (aux & L2C_AUX_CTRL_WAY_SIZE_MASK) >> + L2C_AUX_CTRL_WAY_SIZE_SHIFT; + l2x0_size = ways * (data->way_size_0 << way_size_bits); - l2x0_size = ways * way_size * SZ_1K; + fns = data->outer_cache; + fns.write_sec = outer_cache.write_sec; + if (data->fixup) + data->fixup(l2x0_base, cache_id, &fns); /* - * Check if l2x0 controller is already enabled. - * If you are booting from non-secure mode - * accessing the below registers will fault. + * Check if l2x0 controller is already enabled. If we are booting + * in non-secure mode accessing the below registers will fault. */ - if (!(readl_relaxed(l2x0_base + L2X0_CTRL) & L2X0_CTRL_EN)) { - /* Make sure that I&D is not locked down when starting */ - l2x0_unlock(cache_id); - - /* l2x0 controller is disabled */ - writel_relaxed(aux, l2x0_base + L2X0_AUX_CTRL); + if (!(readl_relaxed(l2x0_base + L2X0_CTRL) & L2X0_CTRL_EN)) + data->enable(l2x0_base, aux, data->num_lock); - l2x0_inv_all(); + outer_cache = fns; - /* enable L2X0 */ - writel_relaxed(L2X0_CTRL_EN, l2x0_base + L2X0_CTRL); - } + /* + * It is strange to save the register state before initialisation, + * but hey, this is what the DT implementations decided to do. + */ + if (data->save) + data->save(l2x0_base); /* Re-read it in case some bits are reserved. */ aux = readl_relaxed(l2x0_base + L2X0_AUX_CTRL); - /* Save the value for resuming. */ - l2x0_saved_regs.aux_ctrl = aux; + pr_info("%s cache controller enabled, %d ways, %d kB\n", + data->type, ways, l2x0_size >> 10); + pr_info("%s: CACHE_ID 0x%08x, AUX_CTRL 0x%08x\n", + data->type, cache_id, aux); +} + +void __init l2x0_init(void __iomem *base, u32 aux_val, u32 aux_mask) +{ + const struct l2c_init_data *data; + u32 cache_id; - if (!of_init) { - outer_cache.inv_range = l2x0_inv_range; - outer_cache.clean_range = l2x0_clean_range; - outer_cache.flush_range = l2x0_flush_range; - outer_cache.sync = l2x0_cache_sync; - outer_cache.flush_all = l2x0_flush_all; - outer_cache.inv_all = l2x0_inv_all; - outer_cache.disable = l2x0_disable; + l2x0_base = base; + + cache_id = readl_relaxed(base + L2X0_CACHE_ID); + + switch (cache_id & L2X0_CACHE_ID_PART_MASK) { + default: + case L2X0_CACHE_ID_PART_L210: + data = &l2c210_data; + break; + + case L2X0_CACHE_ID_PART_L220: + data = &l2c220_data; + break; + + case L2X0_CACHE_ID_PART_L310: + data = &l2c310_init_fns; + break; } - printk(KERN_INFO "%s cache controller enabled\n", type); - 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); + __l2c_init(data, aux_val, aux_mask, cache_id); } #ifdef CONFIG_OF static int l2_wt_override; +/* Aurora don't have the cache ID register available, so we have to + * pass it though the device tree */ +static u32 cache_id_part_number_from_dt; + +static void __init l2x0_of_parse(const struct device_node *np, + u32 *aux_val, u32 *aux_mask) +{ + u32 data[2] = { 0, 0 }; + u32 tag = 0; + u32 dirty = 0; + u32 val = 0, mask = 0; + + of_property_read_u32(np, "arm,tag-latency", &tag); + if (tag) { + mask |= L2X0_AUX_CTRL_TAG_LATENCY_MASK; + val |= (tag - 1) << L2X0_AUX_CTRL_TAG_LATENCY_SHIFT; + } + + of_property_read_u32_array(np, "arm,data-latency", + data, ARRAY_SIZE(data)); + if (data[0] && data[1]) { + mask |= L2X0_AUX_CTRL_DATA_RD_LATENCY_MASK | + L2X0_AUX_CTRL_DATA_WR_LATENCY_MASK; + val |= ((data[0] - 1) << L2X0_AUX_CTRL_DATA_RD_LATENCY_SHIFT) | + ((data[1] - 1) << L2X0_AUX_CTRL_DATA_WR_LATENCY_SHIFT); + } + + of_property_read_u32(np, "arm,dirty-latency", &dirty); + if (dirty) { + mask |= L2X0_AUX_CTRL_DIRTY_LATENCY_MASK; + val |= (dirty - 1) << L2X0_AUX_CTRL_DIRTY_LATENCY_SHIFT; + } + + *aux_val &= ~mask; + *aux_val |= val; + *aux_mask &= ~mask; +} + +static const struct l2c_init_data of_l2c210_data __initconst = { + .type = "L2C-210", + .way_size_0 = SZ_8K, + .num_lock = 1, + .of_parse = l2x0_of_parse, + .enable = l2c_enable, + .save = l2c_save, + .outer_cache = { + .inv_range = l2c210_inv_range, + .clean_range = l2c210_clean_range, + .flush_range = l2c210_flush_range, + .flush_all = l2c210_flush_all, + .disable = l2c_disable, + .sync = l2c210_sync, + .resume = l2c210_resume, + }, +}; + +static const struct l2c_init_data of_l2c220_data __initconst = { + .type = "L2C-220", + .way_size_0 = SZ_8K, + .num_lock = 1, + .of_parse = l2x0_of_parse, + .enable = l2c220_enable, + .save = l2c_save, + .outer_cache = { + .inv_range = l2c220_inv_range, + .clean_range = l2c220_clean_range, + .flush_range = l2c220_flush_range, + .flush_all = l2c220_flush_all, + .disable = l2c_disable, + .sync = l2c220_sync, + .resume = l2c210_resume, + }, +}; + +static void __init l2c310_of_parse(const struct device_node *np, + u32 *aux_val, u32 *aux_mask) +{ + u32 data[3] = { 0, 0, 0 }; + u32 tag[3] = { 0, 0, 0 }; + u32 filter[2] = { 0, 0 }; + + of_property_read_u32_array(np, "arm,tag-latency", tag, ARRAY_SIZE(tag)); + if (tag[0] && tag[1] && tag[2]) + writel_relaxed( + L310_LATENCY_CTRL_RD(tag[0] - 1) | + L310_LATENCY_CTRL_WR(tag[1] - 1) | + L310_LATENCY_CTRL_SETUP(tag[2] - 1), + l2x0_base + L310_TAG_LATENCY_CTRL); + + of_property_read_u32_array(np, "arm,data-latency", + data, ARRAY_SIZE(data)); + if (data[0] && data[1] && data[2]) + writel_relaxed( + L310_LATENCY_CTRL_RD(data[0] - 1) | + L310_LATENCY_CTRL_WR(data[1] - 1) | + L310_LATENCY_CTRL_SETUP(data[2] - 1), + l2x0_base + L310_DATA_LATENCY_CTRL); + + of_property_read_u32_array(np, "arm,filter-ranges", + filter, ARRAY_SIZE(filter)); + if (filter[1]) { + writel_relaxed(ALIGN(filter[0] + filter[1], SZ_1M), + l2x0_base + L310_ADDR_FILTER_END); + writel_relaxed((filter[0] & ~(SZ_1M - 1)) | L310_ADDR_FILTER_EN, + l2x0_base + L310_ADDR_FILTER_START); + } +} + +static const struct l2c_init_data of_l2c310_data __initconst = { + .type = "L2C-310", + .way_size_0 = SZ_8K, + .num_lock = 8, + .of_parse = l2c310_of_parse, + .enable = l2c310_enable, + .fixup = l2c310_fixup, + .save = l2c310_save, + .outer_cache = { + .inv_range = l2c210_inv_range, + .clean_range = l2c210_clean_range, + .flush_range = l2c210_flush_range, + .flush_all = l2c210_flush_all, + .disable = l2c310_disable, + .sync = l2c210_sync, + .resume = l2c310_resume, + }, +}; + +/* + * This is a variant of the of_l2c310_data with .sync set to + * NULL. Outer sync operations are not needed when the system is I/O + * coherent, and potentially harmful in certain situations (PCIe/PL310 + * deadlock on Armada 375/38x due to hardware I/O coherency). The + * other operations are kept because they are infrequent (therefore do + * not cause the deadlock in practice) and needed for secondary CPU + * boot and other power management activities. + */ +static const struct l2c_init_data of_l2c310_coherent_data __initconst = { + .type = "L2C-310 Coherent", + .way_size_0 = SZ_8K, + .num_lock = 8, + .of_parse = l2c310_of_parse, + .enable = l2c310_enable, + .fixup = l2c310_fixup, + .save = l2c310_save, + .outer_cache = { + .inv_range = l2c210_inv_range, + .clean_range = l2c210_clean_range, + .flush_range = l2c210_flush_range, + .flush_all = l2c210_flush_all, + .disable = l2c310_disable, + .resume = l2c310_resume, + }, +}; + /* * Note that the end addresses passed to Linux primitives are * noninclusive, while the hardware cache range operations use @@ -523,6 +1193,100 @@ static void aurora_flush_range(unsigned long start, unsigned long end) } } +static void aurora_save(void __iomem *base) +{ + l2x0_saved_regs.ctrl = readl_relaxed(base + L2X0_CTRL); + l2x0_saved_regs.aux_ctrl = readl_relaxed(base + L2X0_AUX_CTRL); +} + +static void aurora_resume(void) +{ + void __iomem *base = l2x0_base; + + if (!(readl(base + L2X0_CTRL) & L2X0_CTRL_EN)) { + writel_relaxed(l2x0_saved_regs.aux_ctrl, base + L2X0_AUX_CTRL); + writel_relaxed(l2x0_saved_regs.ctrl, base + L2X0_CTRL); + } +} + +/* + * For Aurora cache in no outer mode, enable via the CP15 coprocessor + * broadcasting of cache commands to L2. + */ +static void __init aurora_enable_no_outer(void __iomem *base, u32 aux, + unsigned num_lock) +{ + u32 u; + + asm volatile("mrc p15, 1, %0, c15, c2, 0" : "=r" (u)); + u |= AURORA_CTRL_FW; /* Set the FW bit */ + asm volatile("mcr p15, 1, %0, c15, c2, 0" : : "r" (u)); + + isb(); + + l2c_enable(base, aux, num_lock); +} + +static void __init aurora_fixup(void __iomem *base, u32 cache_id, + struct outer_cache_fns *fns) +{ + sync_reg_offset = AURORA_SYNC_REG; +} + +static void __init aurora_of_parse(const struct device_node *np, + u32 *aux_val, u32 *aux_mask) +{ + u32 val = AURORA_ACR_REPLACEMENT_TYPE_SEMIPLRU; + u32 mask = AURORA_ACR_REPLACEMENT_MASK; + + of_property_read_u32(np, "cache-id-part", + &cache_id_part_number_from_dt); + + /* Determine and save the write policy */ + l2_wt_override = of_property_read_bool(np, "wt-override"); + + if (l2_wt_override) { + val |= AURORA_ACR_FORCE_WRITE_THRO_POLICY; + mask |= AURORA_ACR_FORCE_WRITE_POLICY_MASK; + } + + *aux_val &= ~mask; + *aux_val |= val; + *aux_mask &= ~mask; +} + +static const struct l2c_init_data of_aurora_with_outer_data __initconst = { + .type = "Aurora", + .way_size_0 = SZ_4K, + .num_lock = 4, + .of_parse = aurora_of_parse, + .enable = l2c_enable, + .fixup = aurora_fixup, + .save = aurora_save, + .outer_cache = { + .inv_range = aurora_inv_range, + .clean_range = aurora_clean_range, + .flush_range = aurora_flush_range, + .flush_all = l2x0_flush_all, + .disable = l2x0_disable, + .sync = l2x0_cache_sync, + .resume = aurora_resume, + }, +}; + +static const struct l2c_init_data of_aurora_no_outer_data __initconst = { + .type = "Aurora", + .way_size_0 = SZ_4K, + .num_lock = 4, + .of_parse = aurora_of_parse, + .enable = aurora_enable_no_outer, + .fixup = aurora_fixup, + .save = aurora_save, + .outer_cache = { + .resume = aurora_resume, + }, +}; + /* * For certain Broadcom SoCs, depending on the address range, different offsets * need to be added to the address before passing it to L2 for @@ -587,16 +1351,16 @@ static void bcm_inv_range(unsigned long start, unsigned long end) /* normal case, no cross section between start and end */ if (likely(bcm_addr_is_sys_emi(end) || !bcm_addr_is_sys_emi(start))) { - l2x0_inv_range(new_start, new_end); + l2c210_inv_range(new_start, new_end); return; } /* They cross sections, so it can only be a cross from section * 2 to section 3 */ - l2x0_inv_range(new_start, + l2c210_inv_range(new_start, bcm_l2_phys_addr(BCM_VC_EMI_SEC3_START_ADDR-1)); - l2x0_inv_range(bcm_l2_phys_addr(BCM_VC_EMI_SEC3_START_ADDR), + l2c210_inv_range(bcm_l2_phys_addr(BCM_VC_EMI_SEC3_START_ADDR), new_end); } @@ -609,26 +1373,21 @@ static void bcm_clean_range(unsigned long start, unsigned long end) if (unlikely(end <= start)) return; - if ((end - start) >= l2x0_size) { - l2x0_clean_all(); - return; - } - new_start = bcm_l2_phys_addr(start); new_end = bcm_l2_phys_addr(end); /* normal case, no cross section between start and end */ if (likely(bcm_addr_is_sys_emi(end) || !bcm_addr_is_sys_emi(start))) { - l2x0_clean_range(new_start, new_end); + l2c210_clean_range(new_start, new_end); return; } /* They cross sections, so it can only be a cross from section * 2 to section 3 */ - l2x0_clean_range(new_start, + l2c210_clean_range(new_start, bcm_l2_phys_addr(BCM_VC_EMI_SEC3_START_ADDR-1)); - l2x0_clean_range(bcm_l2_phys_addr(BCM_VC_EMI_SEC3_START_ADDR), + l2c210_clean_range(bcm_l2_phys_addr(BCM_VC_EMI_SEC3_START_ADDR), new_end); } @@ -642,7 +1401,7 @@ static void bcm_flush_range(unsigned long start, unsigned long end) return; if ((end - start) >= l2x0_size) { - l2x0_flush_all(); + outer_cache.flush_all(); return; } @@ -651,294 +1410,94 @@ static void bcm_flush_range(unsigned long start, unsigned long end) /* normal case, no cross section between start and end */ if (likely(bcm_addr_is_sys_emi(end) || !bcm_addr_is_sys_emi(start))) { - l2x0_flush_range(new_start, new_end); + l2c210_flush_range(new_start, new_end); return; } /* They cross sections, so it can only be a cross from section * 2 to section 3 */ - l2x0_flush_range(new_start, + l2c210_flush_range(new_start, bcm_l2_phys_addr(BCM_VC_EMI_SEC3_START_ADDR-1)); - l2x0_flush_range(bcm_l2_phys_addr(BCM_VC_EMI_SEC3_START_ADDR), + l2c210_flush_range(bcm_l2_phys_addr(BCM_VC_EMI_SEC3_START_ADDR), new_end); } -static void __init l2x0_of_setup(const struct device_node *np, - u32 *aux_val, u32 *aux_mask) -{ - u32 data[2] = { 0, 0 }; - u32 tag = 0; - u32 dirty = 0; - u32 val = 0, mask = 0; - - of_property_read_u32(np, "arm,tag-latency", &tag); - if (tag) { - mask |= L2X0_AUX_CTRL_TAG_LATENCY_MASK; - val |= (tag - 1) << L2X0_AUX_CTRL_TAG_LATENCY_SHIFT; - } - - of_property_read_u32_array(np, "arm,data-latency", - data, ARRAY_SIZE(data)); - if (data[0] && data[1]) { - mask |= L2X0_AUX_CTRL_DATA_RD_LATENCY_MASK | - L2X0_AUX_CTRL_DATA_WR_LATENCY_MASK; - val |= ((data[0] - 1) << L2X0_AUX_CTRL_DATA_RD_LATENCY_SHIFT) | - ((data[1] - 1) << L2X0_AUX_CTRL_DATA_WR_LATENCY_SHIFT); - } - - of_property_read_u32(np, "arm,dirty-latency", &dirty); - if (dirty) { - mask |= L2X0_AUX_CTRL_DIRTY_LATENCY_MASK; - val |= (dirty - 1) << L2X0_AUX_CTRL_DIRTY_LATENCY_SHIFT; - } - - *aux_val &= ~mask; - *aux_val |= val; - *aux_mask &= ~mask; -} - -static void __init pl310_of_setup(const struct device_node *np, - u32 *aux_val, u32 *aux_mask) -{ - u32 data[3] = { 0, 0, 0 }; - u32 tag[3] = { 0, 0, 0 }; - u32 filter[2] = { 0, 0 }; - - of_property_read_u32_array(np, "arm,tag-latency", tag, ARRAY_SIZE(tag)); - if (tag[0] && tag[1] && tag[2]) - writel_relaxed( - ((tag[0] - 1) << L2X0_LATENCY_CTRL_RD_SHIFT) | - ((tag[1] - 1) << L2X0_LATENCY_CTRL_WR_SHIFT) | - ((tag[2] - 1) << L2X0_LATENCY_CTRL_SETUP_SHIFT), - l2x0_base + L2X0_TAG_LATENCY_CTRL); - - of_property_read_u32_array(np, "arm,data-latency", - data, ARRAY_SIZE(data)); - if (data[0] && data[1] && data[2]) - writel_relaxed( - ((data[0] - 1) << L2X0_LATENCY_CTRL_RD_SHIFT) | - ((data[1] - 1) << L2X0_LATENCY_CTRL_WR_SHIFT) | - ((data[2] - 1) << L2X0_LATENCY_CTRL_SETUP_SHIFT), - l2x0_base + L2X0_DATA_LATENCY_CTRL); - - of_property_read_u32_array(np, "arm,filter-ranges", - filter, ARRAY_SIZE(filter)); - if (filter[1]) { - writel_relaxed(ALIGN(filter[0] + filter[1], SZ_1M), - l2x0_base + L2X0_ADDR_FILTER_END); - writel_relaxed((filter[0] & ~(SZ_1M - 1)) | L2X0_ADDR_FILTER_EN, - l2x0_base + L2X0_ADDR_FILTER_START); - } -} - -static void __init pl310_save(void) -{ - u32 l2x0_revision = readl_relaxed(l2x0_base + L2X0_CACHE_ID) & - L2X0_CACHE_ID_RTL_MASK; - - l2x0_saved_regs.tag_latency = readl_relaxed(l2x0_base + - L2X0_TAG_LATENCY_CTRL); - l2x0_saved_regs.data_latency = readl_relaxed(l2x0_base + - L2X0_DATA_LATENCY_CTRL); - l2x0_saved_regs.filter_end = readl_relaxed(l2x0_base + - L2X0_ADDR_FILTER_END); - l2x0_saved_regs.filter_start = readl_relaxed(l2x0_base + - L2X0_ADDR_FILTER_START); - - if (l2x0_revision >= L2X0_CACHE_ID_RTL_R2P0) { - /* - * From r2p0, there is Prefetch offset/control register - */ - l2x0_saved_regs.prefetch_ctrl = readl_relaxed(l2x0_base + - L2X0_PREFETCH_CTRL); - /* - * From r3p0, there is Power control register - */ - if (l2x0_revision >= L2X0_CACHE_ID_RTL_R3P0) - l2x0_saved_regs.pwr_ctrl = readl_relaxed(l2x0_base + - L2X0_POWER_CTRL); - } -} - -static void aurora_save(void) -{ - l2x0_saved_regs.ctrl = readl_relaxed(l2x0_base + L2X0_CTRL); - l2x0_saved_regs.aux_ctrl = readl_relaxed(l2x0_base + L2X0_AUX_CTRL); -} - -static void l2x0_resume(void) -{ - if (!(readl_relaxed(l2x0_base + L2X0_CTRL) & L2X0_CTRL_EN)) { - /* restore aux ctrl and enable l2 */ - l2x0_unlock(readl_relaxed(l2x0_base + L2X0_CACHE_ID)); - - writel_relaxed(l2x0_saved_regs.aux_ctrl, l2x0_base + - L2X0_AUX_CTRL); - - l2x0_inv_all(); - - writel_relaxed(L2X0_CTRL_EN, l2x0_base + L2X0_CTRL); - } -} - -static void pl310_resume(void) -{ - u32 l2x0_revision; - - if (!(readl_relaxed(l2x0_base + L2X0_CTRL) & L2X0_CTRL_EN)) { - /* restore pl310 setup */ - writel_relaxed(l2x0_saved_regs.tag_latency, - l2x0_base + L2X0_TAG_LATENCY_CTRL); - writel_relaxed(l2x0_saved_regs.data_latency, - l2x0_base + L2X0_DATA_LATENCY_CTRL); - writel_relaxed(l2x0_saved_regs.filter_end, - l2x0_base + L2X0_ADDR_FILTER_END); - writel_relaxed(l2x0_saved_regs.filter_start, - l2x0_base + L2X0_ADDR_FILTER_START); - - l2x0_revision = readl_relaxed(l2x0_base + L2X0_CACHE_ID) & - L2X0_CACHE_ID_RTL_MASK; - - if (l2x0_revision >= L2X0_CACHE_ID_RTL_R2P0) { - writel_relaxed(l2x0_saved_regs.prefetch_ctrl, - l2x0_base + L2X0_PREFETCH_CTRL); - if (l2x0_revision >= L2X0_CACHE_ID_RTL_R3P0) - writel_relaxed(l2x0_saved_regs.pwr_ctrl, - l2x0_base + L2X0_POWER_CTRL); - } - } - - l2x0_resume(); -} +/* Broadcom L2C-310 start from ARMs R3P2 or later, and require no fixups */ +static const struct l2c_init_data of_bcm_l2x0_data __initconst = { + .type = "BCM-L2C-310", + .way_size_0 = SZ_8K, + .num_lock = 8, + .of_parse = l2c310_of_parse, + .enable = l2c310_enable, + .save = l2c310_save, + .outer_cache = { + .inv_range = bcm_inv_range, + .clean_range = bcm_clean_range, + .flush_range = bcm_flush_range, + .flush_all = l2c210_flush_all, + .disable = l2c310_disable, + .sync = l2c210_sync, + .resume = l2c310_resume, + }, +}; -static void aurora_resume(void) +static void __init tauros3_save(void __iomem *base) { - if (!(readl(l2x0_base + L2X0_CTRL) & L2X0_CTRL_EN)) { - writel_relaxed(l2x0_saved_regs.aux_ctrl, - l2x0_base + L2X0_AUX_CTRL); - writel_relaxed(l2x0_saved_regs.ctrl, l2x0_base + L2X0_CTRL); - } -} + l2c_save(base); -static void __init aurora_broadcast_l2_commands(void) -{ - __u32 u; - /* Enable Broadcasting of cache commands to L2*/ - __asm__ __volatile__("mrc p15, 1, %0, c15, c2, 0" : "=r"(u)); - u |= AURORA_CTRL_FW; /* Set the FW bit */ - __asm__ __volatile__("mcr p15, 1, %0, c15, c2, 0\n" : : "r"(u)); - isb(); + l2x0_saved_regs.aux2_ctrl = + readl_relaxed(base + TAUROS3_AUX2_CTRL); + l2x0_saved_regs.prefetch_ctrl = + readl_relaxed(base + L310_PREFETCH_CTRL); } -static void __init aurora_of_setup(const struct device_node *np, - u32 *aux_val, u32 *aux_mask) +static void tauros3_resume(void) { - u32 val = AURORA_ACR_REPLACEMENT_TYPE_SEMIPLRU; - u32 mask = AURORA_ACR_REPLACEMENT_MASK; - - of_property_read_u32(np, "cache-id-part", - &cache_id_part_number_from_dt); + void __iomem *base = l2x0_base; - /* Determine and save the write policy */ - l2_wt_override = of_property_read_bool(np, "wt-override"); + if (!(readl_relaxed(base + L2X0_CTRL) & L2X0_CTRL_EN)) { + writel_relaxed(l2x0_saved_regs.aux2_ctrl, + base + TAUROS3_AUX2_CTRL); + writel_relaxed(l2x0_saved_regs.prefetch_ctrl, + base + L310_PREFETCH_CTRL); - if (l2_wt_override) { - val |= AURORA_ACR_FORCE_WRITE_THRO_POLICY; - mask |= AURORA_ACR_FORCE_WRITE_POLICY_MASK; + l2c_enable(base, l2x0_saved_regs.aux_ctrl, 8); } - - *aux_val &= ~mask; - *aux_val |= val; - *aux_mask &= ~mask; } -static const struct l2x0_of_data pl310_data = { - .setup = pl310_of_setup, - .save = pl310_save, - .outer_cache = { - .resume = pl310_resume, - .inv_range = l2x0_inv_range, - .clean_range = l2x0_clean_range, - .flush_range = l2x0_flush_range, - .sync = l2x0_cache_sync, - .flush_all = l2x0_flush_all, - .inv_all = l2x0_inv_all, - .disable = l2x0_disable, - }, -}; - -static const struct l2x0_of_data l2x0_data = { - .setup = l2x0_of_setup, - .save = NULL, +static const struct l2c_init_data of_tauros3_data __initconst = { + .type = "Tauros3", + .way_size_0 = SZ_8K, + .num_lock = 8, + .enable = l2c_enable, + .save = tauros3_save, + /* Tauros3 broadcasts L1 cache operations to L2 */ .outer_cache = { - .resume = l2x0_resume, - .inv_range = l2x0_inv_range, - .clean_range = l2x0_clean_range, - .flush_range = l2x0_flush_range, - .sync = l2x0_cache_sync, - .flush_all = l2x0_flush_all, - .inv_all = l2x0_inv_all, - .disable = l2x0_disable, - }, -}; - -static const struct l2x0_of_data aurora_with_outer_data = { - .setup = aurora_of_setup, - .save = aurora_save, - .outer_cache = { - .resume = aurora_resume, - .inv_range = aurora_inv_range, - .clean_range = aurora_clean_range, - .flush_range = aurora_flush_range, - .sync = l2x0_cache_sync, - .flush_all = l2x0_flush_all, - .inv_all = l2x0_inv_all, - .disable = l2x0_disable, - }, -}; - -static const struct l2x0_of_data aurora_no_outer_data = { - .setup = aurora_of_setup, - .save = aurora_save, - .outer_cache = { - .resume = aurora_resume, - }, -}; - -static const struct l2x0_of_data bcm_l2x0_data = { - .setup = pl310_of_setup, - .save = pl310_save, - .outer_cache = { - .resume = pl310_resume, - .inv_range = bcm_inv_range, - .clean_range = bcm_clean_range, - .flush_range = bcm_flush_range, - .sync = l2x0_cache_sync, - .flush_all = l2x0_flush_all, - .inv_all = l2x0_inv_all, - .disable = l2x0_disable, + .resume = tauros3_resume, }, }; +#define L2C_ID(name, fns) { .compatible = name, .data = (void *)&fns } 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 }, - { .compatible = "marvell,aurora-system-cache", - .data = (void *)&aurora_no_outer_data}, - { .compatible = "marvell,aurora-outer-cache", - .data = (void *)&aurora_with_outer_data}, - { .compatible = "bcm,bcm11351-a2-pl310-cache", - .data = (void *)&bcm_l2x0_data}, + L2C_ID("arm,l210-cache", of_l2c210_data), + L2C_ID("arm,l220-cache", of_l2c220_data), + L2C_ID("arm,pl310-cache", of_l2c310_data), + L2C_ID("brcm,bcm11351-a2-pl310-cache", of_bcm_l2x0_data), + L2C_ID("marvell,aurora-outer-cache", of_aurora_with_outer_data), + L2C_ID("marvell,aurora-system-cache", of_aurora_no_outer_data), + L2C_ID("marvell,tauros3-cache", of_tauros3_data), + /* Deprecated IDs */ + L2C_ID("bcm,bcm11351-a2-pl310-cache", of_bcm_l2x0_data), {} }; int __init l2x0_of_init(u32 aux_val, u32 aux_mask) { + const struct l2c_init_data *data; struct device_node *np; - const struct l2x0_of_data *data; struct resource res; + u32 cache_id, old_aux; np = of_find_matching_node(NULL, l2x0_ids); if (!np) @@ -955,23 +1514,33 @@ int __init l2x0_of_init(u32 aux_val, u32 aux_mask) data = of_match_node(l2x0_ids, np)->data; - /* L2 configuration can only be changed if the cache is disabled */ - if (!(readl_relaxed(l2x0_base + L2X0_CTRL) & L2X0_CTRL_EN)) { - if (data->setup) - data->setup(np, &aux_val, &aux_mask); + if (of_device_is_compatible(np, "arm,pl310-cache") && + of_property_read_bool(np, "arm,io-coherent")) + data = &of_l2c310_coherent_data; - /* For aurora cache in no outer mode select the - * correct mode using the coprocessor*/ - if (data == &aurora_no_outer_data) - aurora_broadcast_l2_commands(); + old_aux = readl_relaxed(l2x0_base + L2X0_AUX_CTRL); + if (old_aux != ((old_aux & aux_mask) | aux_val)) { + pr_warn("L2C: platform modifies aux control register: 0x%08x -> 0x%08x\n", + old_aux, (old_aux & aux_mask) | aux_val); + } else if (aux_mask != ~0U && aux_val != 0) { + pr_alert("L2C: platform provided aux values match the hardware, so have no effect. Please remove them.\n"); } - if (data->save) - data->save(); + /* All L2 caches are unified, so this property should be specified */ + if (!of_property_read_bool(np, "cache-unified")) + pr_err("L2C: device tree omits to specify unified cache\n"); + + /* L2 configuration can only be changed if the cache is disabled */ + if (!(readl_relaxed(l2x0_base + L2X0_CTRL) & L2X0_CTRL_EN)) + if (data->of_parse) + data->of_parse(np, &aux_val, &aux_mask); + + if (cache_id_part_number_from_dt) + cache_id = cache_id_part_number_from_dt; + else + cache_id = readl_relaxed(l2x0_base + L2X0_CACHE_ID); - of_init = true; - memcpy(&outer_cache, &data->outer_cache, sizeof(outer_cache)); - l2x0_init(l2x0_base, aux_val, aux_mask); + __l2c_init(data, aux_val, aux_mask, cache_id); return 0; } diff --git a/arch/arm/mm/cache-tauros2.c b/arch/arm/mm/cache-tauros2.c index 1be0f4e5e6e..b273739e635 100644 --- a/arch/arm/mm/cache-tauros2.c +++ b/arch/arm/mm/cache-tauros2.c @@ -33,7 +33,7 @@ * outer cache operations into the kernel image if the kernel has been * configured to support a pre-v7 CPU. */ -#if __LINUX_ARM_ARCH__ < 7 +#ifdef CONFIG_CPU_32v5 /* * Low-level cache maintenance operations. */ @@ -229,33 +229,6 @@ static void __init tauros2_internal_init(unsigned int features) } #endif -#ifdef CONFIG_CPU_32v6 - /* - * Check whether this CPU lacks support for the v7 hierarchical - * cache ops. (PJ4 is in its v6 personality mode if the MMFR3 - * register indicates no support for the v7 hierarchical cache - * ops.) - */ - if (cpuid_scheme() && (read_mmfr3() & 0xf) == 0) { - /* - * When Tauros2 is used in an ARMv6 system, the L2 - * enable bit is in the ARMv6 ARM-mandated position - * (bit [26] of the System Control Register). - */ - if (!(get_cr() & 0x04000000)) { - printk(KERN_INFO "Tauros2: Enabling L2 cache.\n"); - adjust_cr(0x04000000, 0x04000000); - } - - mode = "ARMv6"; - outer_cache.inv_range = tauros2_inv_range; - outer_cache.clean_range = tauros2_clean_range; - outer_cache.flush_range = tauros2_flush_range; - outer_cache.disable = tauros2_disable; - outer_cache.resume = tauros2_resume; - } -#endif - #ifdef CONFIG_CPU_32v7 /* * Check whether this CPU has support for the v7 hierarchical diff --git a/arch/arm/mm/cache-tauros3.h b/arch/arm/mm/cache-tauros3.h new file mode 100644 index 00000000000..02c0a97cbc0 --- /dev/null +++ b/arch/arm/mm/cache-tauros3.h @@ -0,0 +1,41 @@ +/* + * Marvell Tauros3 cache controller includes + * + * Sebastian Hesselbarth <sebastian.hesselbarth@gmail.com> + * + * based on GPL'ed 2.6 kernel sources + * (c) Marvell International 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. + * + * 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 + */ + +#ifndef __ASM_ARM_HARDWARE_TAUROS3_H +#define __ASM_ARM_HARDWARE_TAUROS3_H + +/* + * Marvell Tauros3 L2CC is compatible with PL310 r0p0 + * but with PREFETCH_CTRL (r2p0) and an additional event counter. + * Also, there is AUX2_CTRL for some Marvell specific control. + */ + +#define TAUROS3_EVENT_CNT2_CFG 0x224 +#define TAUROS3_EVENT_CNT2_VAL 0x228 +#define TAUROS3_INV_ALL 0x780 +#define TAUROS3_CLEAN_ALL 0x784 +#define TAUROS3_AUX2_CTRL 0x820 + +/* Registers shifts and masks */ +#define TAUROS3_AUX2_CTRL_LINEFILL_BURST8_EN (1 << 2) + +#endif diff --git a/arch/arm/mm/cache-v7.S b/arch/arm/mm/cache-v7.S index 515b00064da..615c99e38ba 100644 --- a/arch/arm/mm/cache-v7.S +++ b/arch/arm/mm/cache-v7.S @@ -59,7 +59,7 @@ ENTRY(v7_invalidate_l1) bgt 2b cmp r2, #0 bgt 1b - dsb + dsb st isb mov pc, lr ENDPROC(v7_invalidate_l1) @@ -146,18 +146,18 @@ flush_levels: ldr r7, =0x7fff ands r7, r7, r1, lsr #13 @ extract max number of the index size loop1: - mov r9, r4 @ create working copy of max way size + mov r9, r7 @ create working copy of max index loop2: - ARM( orr r11, r10, r9, lsl r5 ) @ factor way and cache number into r11 - THUMB( lsl r6, r9, r5 ) + ARM( orr r11, r10, r4, lsl r5 ) @ factor way and cache number into r11 + THUMB( lsl r6, r4, r5 ) THUMB( orr r11, r10, r6 ) @ factor way and cache number into r11 - ARM( orr r11, r11, r7, lsl r2 ) @ factor index number into r11 - THUMB( lsl r6, r7, r2 ) + ARM( orr r11, r11, r9, lsl r2 ) @ factor index number into r11 + THUMB( lsl r6, r9, r2 ) THUMB( orr r11, r11, r6 ) @ factor index number into r11 mcr p15, 0, r11, c7, c14, 2 @ clean & invalidate by set/way - subs r9, r9, #1 @ decrement the way + subs r9, r9, #1 @ decrement the index bge loop2 - subs r7, r7, #1 @ decrement the index + subs r4, r4, #1 @ decrement the way bge loop1 skip: add r10, r10, #2 @ increment cache number @@ -166,7 +166,7 @@ skip: finished: mov r10, #0 @ swith back to cache level 0 mcr p15, 2, r10, c0, c0, 0 @ select current cache level in cssr - dsb + dsb st isb mov pc, lr ENDPROC(v7_flush_dcache_all) @@ -282,7 +282,7 @@ ENTRY(v7_coherent_user_range) add r12, r12, r2 cmp r12, r1 blo 1b - dsb + dsb ishst icache_line_size r2, r3 sub r3, r2, #1 bic r12, r0, r3 @@ -294,7 +294,7 @@ ENTRY(v7_coherent_user_range) mov r0, #0 ALT_SMP(mcr p15, 0, r0, c7, c1, 6) @ invalidate BTB Inner Shareable ALT_UP(mcr p15, 0, r0, c7, c5, 6) @ invalidate BTB - dsb + dsb ishst isb mov pc, lr @@ -335,7 +335,7 @@ ENTRY(v7_flush_kern_dcache_area) add r0, r0, r2 cmp r0, r1 blo 1b - dsb + dsb st mov pc, lr ENDPROC(v7_flush_kern_dcache_area) @@ -368,7 +368,7 @@ v7_dma_inv_range: add r0, r0, r2 cmp r0, r1 blo 1b - dsb + dsb st mov pc, lr ENDPROC(v7_dma_inv_range) @@ -390,7 +390,7 @@ v7_dma_clean_range: add r0, r0, r2 cmp r0, r1 blo 1b - dsb + dsb st mov pc, lr ENDPROC(v7_dma_clean_range) @@ -412,7 +412,7 @@ ENTRY(v7_dma_flush_range) add r0, r0, r2 cmp r0, r1 blo 1b - dsb + dsb st mov pc, lr ENDPROC(v7_dma_flush_range) diff --git a/arch/arm/mm/context.c b/arch/arm/mm/context.c index 4a0544492f1..6eb97b3a748 100644 --- a/arch/arm/mm/context.c +++ b/arch/arm/mm/context.c @@ -36,8 +36,8 @@ * The context ID is used by debuggers and trace logic, and * should be unique within all running processes. * - * In big endian operation, the two 32 bit words are swapped if accesed by - * non 64-bit operations. + * In big endian operation, the two 32 bit words are swapped if accessed + * by non-64-bit operations. */ #define ASID_FIRST_VERSION (1ULL << ASID_BITS) #define NUM_USER_ASIDS ASID_FIRST_VERSION @@ -78,20 +78,21 @@ void a15_erratum_get_cpumask(int this_cpu, struct mm_struct *mm, #endif #ifdef CONFIG_ARM_LPAE -static void cpu_set_reserved_ttbr0(void) -{ - /* - * Set TTBR0 to swapper_pg_dir which contains only global entries. The - * ASID is set to 0. - */ - cpu_set_ttbr(0, __pa(swapper_pg_dir)); - isb(); -} +/* + * With LPAE, the ASID and page tables are updated atomicly, so there is + * no need for a reserved set of tables (the active ASID tracking prevents + * any issues across a rollover). + */ +#define cpu_set_reserved_ttbr0() #else static void cpu_set_reserved_ttbr0(void) { u32 ttb; - /* Copy TTBR1 into TTBR0 */ + /* + * Copy TTBR1 into TTBR0. + * This points at swapper_pg_dir, which contains only global + * entries so any speculative walks are perfectly safe. + */ asm volatile( " mrc p15, 0, %0, c2, c0, 1 @ read TTBR1\n" " mcr p15, 0, %0, c2, c0, 0 @ set TTBR0\n" @@ -162,10 +163,7 @@ static void flush_context(unsigned int cpu) } /* Queue a TLB invalidate and flush the I-cache if necessary. */ - if (!tlb_ops_need_broadcast()) - cpumask_set_cpu(cpu, &tlb_flush_pending); - else - cpumask_setall(&tlb_flush_pending); + cpumask_setall(&tlb_flush_pending); if (icache_is_vivt_asid_tagged()) __flush_icache_all(); @@ -182,6 +180,7 @@ static int is_reserved_asid(u64 asid) static u64 new_context(struct mm_struct *mm, unsigned int cpu) { + static u32 cur_idx = 1; u64 asid = atomic64_read(&mm->context.id); u64 generation = atomic64_read(&asid_generation); @@ -196,10 +195,13 @@ static u64 new_context(struct mm_struct *mm, unsigned int cpu) * Allocate a free ASID. If we can't find one, take a * note of the currently active ASIDs and mark the TLBs * as requiring flushes. We always count from ASID #1, - * as we reserve ASID #0 to switch via TTBR0 and indicate - * rollover events. + * as we reserve ASID #0 to switch via TTBR0 and to + * avoid speculative page table walks from hitting in + * any partial walk caches, which could be populated + * from overlapping level-1 descriptors used to map both + * the module area and the userspace stack. */ - asid = find_next_zero_bit(asid_map, NUM_USER_ASIDS, 1); + asid = find_next_zero_bit(asid_map, NUM_USER_ASIDS, cur_idx); if (asid == NUM_USER_ASIDS) { generation = atomic64_add_return(ASID_FIRST_VERSION, &asid_generation); @@ -207,6 +209,7 @@ static u64 new_context(struct mm_struct *mm, unsigned int cpu) asid = find_next_zero_bit(asid_map, NUM_USER_ASIDS, 1); } __set_bit(asid, asid_map); + cur_idx = asid; asid |= generation; cpumask_clear(mm_cpumask(mm)); } @@ -224,8 +227,9 @@ void check_and_switch_context(struct mm_struct *mm, struct task_struct *tsk) __check_vmalloc_seq(mm); /* - * Required during context switch to avoid speculative page table - * walking with the wrong TTBR. + * We cannot update the pgd and the ASID atomicly with classic + * MMU, so switch exclusively to global mappings to avoid + * speculative page table walking with the wrong TTBR. */ cpu_set_reserved_ttbr0(); @@ -245,8 +249,6 @@ void check_and_switch_context(struct mm_struct *mm, struct task_struct *tsk) if (cpumask_test_and_clear_cpu(cpu, &tlb_flush_pending)) { local_flush_bp_all(); local_flush_tlb_all(); - if (erratum_a15_798181()) - dummy_flush_tlb_a15_erratum(); } atomic64_set(&per_cpu(active_asids, cpu), asid); diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c index 7f9b1798c6c..1f88db06b13 100644 --- a/arch/arm/mm/dma-mapping.c +++ b/arch/arm/mm/dma-mapping.c @@ -9,6 +9,7 @@ * * DMA uncached mapping support. */ +#include <linux/bootmem.h> #include <linux/module.h> #include <linux/mm.h> #include <linux/gfp.h> @@ -157,9 +158,47 @@ struct dma_map_ops arm_coherent_dma_ops = { }; EXPORT_SYMBOL(arm_coherent_dma_ops); +static int __dma_supported(struct device *dev, u64 mask, bool warn) +{ + unsigned long max_dma_pfn; + + /* + * If the mask allows for more memory than we can address, + * and we actually have that much memory, then we must + * indicate that DMA to this device is not supported. + */ + if (sizeof(mask) != sizeof(dma_addr_t) && + mask > (dma_addr_t)~0 && + dma_to_pfn(dev, ~0) < max_pfn) { + if (warn) { + dev_warn(dev, "Coherent DMA mask %#llx is larger than dma_addr_t allows\n", + mask); + dev_warn(dev, "Driver did not use or check the return value from dma_set_coherent_mask()?\n"); + } + return 0; + } + + max_dma_pfn = min(max_pfn, arm_dma_pfn_limit); + + /* + * Translate the device's DMA mask to a PFN limit. This + * PFN number includes the page which we can DMA to. + */ + if (dma_to_pfn(dev, mask) < max_dma_pfn) { + if (warn) + dev_warn(dev, "Coherent DMA mask %#llx (pfn %#lx-%#lx) covers a smaller range of system memory than the DMA zone pfn 0x0-%#lx\n", + mask, + dma_to_pfn(dev, 0), dma_to_pfn(dev, mask) + 1, + max_dma_pfn + 1); + return 0; + } + + return 1; +} + static u64 get_coherent_dma_mask(struct device *dev) { - u64 mask = (u64)arm_dma_limit; + u64 mask = (u64)DMA_BIT_MASK(32); if (dev) { mask = dev->coherent_dma_mask; @@ -173,12 +212,8 @@ static u64 get_coherent_dma_mask(struct device *dev) return 0; } - if ((~mask) & (u64)arm_dma_limit) { - dev_warn(dev, "coherent DMA mask %#llx is smaller " - "than system GFP_DMA mask %#llx\n", - mask, (u64)arm_dma_limit); + if (!__dma_supported(dev, mask, true)) return 0; - } } return mask; @@ -249,9 +284,6 @@ static void __dma_free_buffer(struct page *page, size_t size) } #ifdef CONFIG_MMU -#ifdef CONFIG_HUGETLB_PAGE -#warning ARM Coherent DMA allocator does not (yet) support huge TLB -#endif static void *__alloc_from_contiguous(struct device *dev, size_t size, pgprot_t prot, struct page **ret_page, @@ -341,7 +373,7 @@ void __init init_dma_coherent_pool_size(unsigned long size) static int __init atomic_pool_init(void) { struct dma_pool *pool = &atomic_pool; - pgprot_t prot = pgprot_dmacoherent(pgprot_kernel); + pgprot_t prot = pgprot_dmacoherent(PAGE_KERNEL); gfp_t gfp = GFP_KERNEL | GFP_DMA; unsigned long nr_pages = pool->size >> PAGE_SHIFT; unsigned long *bitmap; @@ -358,7 +390,7 @@ static int __init atomic_pool_init(void) if (!pages) goto no_pages; - if (IS_ENABLED(CONFIG_CMA)) + if (dev_get_cma_area(NULL)) ptr = __alloc_from_contiguous(NULL, pool->size, prot, &page, atomic_pool_init); else @@ -429,12 +461,21 @@ void __init dma_contiguous_remap(void) map.type = MT_MEMORY_DMA_READY; /* - * Clear previous low-memory mapping + * Clear previous low-memory mapping to ensure that the + * TLB does not see any conflicting entries, then flush + * the TLB of the old entries before creating new mappings. + * + * This ensures that any speculatively loaded TLB entries + * (even though they may be rare) can not cause any problems, + * and ensures that this code is architecturally compliant. */ for (addr = __phys_to_virt(start); addr < __phys_to_virt(end); addr += PMD_SIZE) pmd_clear(pmd_off_k(addr)); + flush_tlb_kernel_range(__phys_to_virt(start), + __phys_to_virt(end)); + iotable_init(&map, 1); } } @@ -455,7 +496,6 @@ static void __dma_remap(struct page *page, size_t size, pgprot_t prot) unsigned end = start + size; apply_to_page_range(&init_mm, start, size, __dma_update_pte, &prot); - dsb(); flush_tlb_kernel_range(start, end); } @@ -590,7 +630,7 @@ static void __free_from_contiguous(struct device *dev, struct page *page, if (PageHighMem(page)) __dma_free_remap(cpu_addr, size); else - __dma_remap(page, size, pgprot_kernel); + __dma_remap(page, size, PAGE_KERNEL); dma_release_from_contiguous(dev, page, size >> PAGE_SHIFT); } @@ -670,7 +710,7 @@ static void *__dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, addr = __alloc_simple_buffer(dev, size, gfp, &page); else if (!(gfp & __GFP_WAIT)) addr = __alloc_from_pool(size, &page); - else if (!IS_ENABLED(CONFIG_CMA)) + else if (!dev_get_cma_area(dev)) addr = __alloc_remap_buffer(dev, size, gfp, prot, &page, caller); else addr = __alloc_from_contiguous(dev, size, prot, &page, caller); @@ -688,7 +728,7 @@ static void *__dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, void *arm_dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, gfp_t gfp, struct dma_attrs *attrs) { - pgprot_t prot = __get_dma_pgprot(attrs, pgprot_kernel); + pgprot_t prot = __get_dma_pgprot(attrs, PAGE_KERNEL); void *memory; if (dma_alloc_from_coherent(dev, size, handle, &memory)) @@ -701,7 +741,7 @@ void *arm_dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, static void *arm_coherent_dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, gfp_t gfp, struct dma_attrs *attrs) { - pgprot_t prot = __get_dma_pgprot(attrs, pgprot_kernel); + pgprot_t prot = __get_dma_pgprot(attrs, PAGE_KERNEL); void *memory; if (dma_alloc_from_coherent(dev, size, handle, &memory)) @@ -759,7 +799,7 @@ static void __arm_dma_free(struct device *dev, size_t size, void *cpu_addr, __dma_free_buffer(page, size); } else if (__free_from_pool(cpu_addr, size)) { return; - } else if (!IS_ENABLED(CONFIG_CMA)) { + } else if (!dev_get_cma_area(dev)) { __dma_free_remap(cpu_addr, size); __dma_free_buffer(page, size); } else { @@ -854,7 +894,7 @@ static void dma_cache_maint_page(struct page *page, unsigned long offset, static void __dma_page_cpu_to_dev(struct page *page, unsigned long off, size_t size, enum dma_data_direction dir) { - unsigned long paddr; + phys_addr_t paddr; dma_cache_maint_page(page, off, size, dir, dmac_map_area); @@ -870,14 +910,15 @@ static void __dma_page_cpu_to_dev(struct page *page, unsigned long off, static void __dma_page_dev_to_cpu(struct page *page, unsigned long off, size_t size, enum dma_data_direction dir) { - unsigned long paddr = page_to_phys(page) + off; + phys_addr_t paddr = page_to_phys(page) + off; /* FIXME: non-speculating: not required */ - /* don't bother invalidating if DMA to device */ - if (dir != DMA_TO_DEVICE) + /* in any case, don't bother invalidating if DMA to device */ + if (dir != DMA_TO_DEVICE) { outer_inv_range(paddr, paddr + size); - dma_cache_maint_page(page, off, size, dir, dmac_unmap_area); + dma_cache_maint_page(page, off, size, dir, dmac_unmap_area); + } /* * Mark the D-cache clean for these pages to avoid extra flushing. @@ -1008,9 +1049,7 @@ void arm_dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, */ int dma_supported(struct device *dev, u64 mask) { - if (mask < (u64)arm_dma_limit) - return 0; - return 1; + return __dma_supported(dev, mask, false); } EXPORT_SYMBOL(dma_supported); @@ -1037,48 +1076,98 @@ fs_initcall(dma_debug_do_init); /* IOMMU */ +static int extend_iommu_mapping(struct dma_iommu_mapping *mapping); + static inline dma_addr_t __alloc_iova(struct dma_iommu_mapping *mapping, size_t size) { unsigned int order = get_order(size); unsigned int align = 0; unsigned int count, start; + size_t mapping_size = mapping->bits << PAGE_SHIFT; unsigned long flags; + dma_addr_t iova; + int i; if (order > CONFIG_ARM_DMA_IOMMU_ALIGNMENT) order = CONFIG_ARM_DMA_IOMMU_ALIGNMENT; - count = ((PAGE_ALIGN(size) >> PAGE_SHIFT) + - (1 << mapping->order) - 1) >> mapping->order; - - if (order > mapping->order) - align = (1 << (order - mapping->order)) - 1; + count = PAGE_ALIGN(size) >> PAGE_SHIFT; + align = (1 << order) - 1; spin_lock_irqsave(&mapping->lock, flags); - start = bitmap_find_next_zero_area(mapping->bitmap, mapping->bits, 0, - count, align); - if (start > mapping->bits) { - spin_unlock_irqrestore(&mapping->lock, flags); - return DMA_ERROR_CODE; + for (i = 0; i < mapping->nr_bitmaps; i++) { + start = bitmap_find_next_zero_area(mapping->bitmaps[i], + mapping->bits, 0, count, align); + + if (start > mapping->bits) + continue; + + bitmap_set(mapping->bitmaps[i], start, count); + break; } - bitmap_set(mapping->bitmap, start, count); + /* + * No unused range found. Try to extend the existing mapping + * and perform a second attempt to reserve an IO virtual + * address range of size bytes. + */ + if (i == mapping->nr_bitmaps) { + if (extend_iommu_mapping(mapping)) { + spin_unlock_irqrestore(&mapping->lock, flags); + return DMA_ERROR_CODE; + } + + start = bitmap_find_next_zero_area(mapping->bitmaps[i], + mapping->bits, 0, count, align); + + if (start > mapping->bits) { + spin_unlock_irqrestore(&mapping->lock, flags); + return DMA_ERROR_CODE; + } + + bitmap_set(mapping->bitmaps[i], start, count); + } spin_unlock_irqrestore(&mapping->lock, flags); - return mapping->base + (start << (mapping->order + PAGE_SHIFT)); + iova = mapping->base + (mapping_size * i); + iova += start << PAGE_SHIFT; + + return iova; } static inline void __free_iova(struct dma_iommu_mapping *mapping, dma_addr_t addr, size_t size) { - unsigned int start = (addr - mapping->base) >> - (mapping->order + PAGE_SHIFT); - unsigned int count = ((size >> PAGE_SHIFT) + - (1 << mapping->order) - 1) >> mapping->order; + unsigned int start, count; + size_t mapping_size = mapping->bits << PAGE_SHIFT; unsigned long flags; + dma_addr_t bitmap_base; + u32 bitmap_index; + + if (!size) + return; + + bitmap_index = (u32) (addr - mapping->base) / (u32) mapping_size; + BUG_ON(addr < mapping->base || bitmap_index > mapping->extensions); + + bitmap_base = mapping->base + mapping_size * bitmap_index; + + start = (addr - bitmap_base) >> PAGE_SHIFT; + + if (addr + size > bitmap_base + mapping_size) { + /* + * The address range to be freed reaches into the iova + * range of the next bitmap. This should not happen as + * we don't allow this in __alloc_iova (at the + * moment). + */ + BUG(); + } else + count = size >> PAGE_SHIFT; spin_lock_irqsave(&mapping->lock, flags); - bitmap_clear(mapping->bitmap, start, count); + bitmap_clear(mapping->bitmaps[bitmap_index], start, count); spin_unlock_irqrestore(&mapping->lock, flags); } @@ -1233,7 +1322,8 @@ __iommu_create_mapping(struct device *dev, struct page **pages, size_t size) break; len = (j - i) << PAGE_SHIFT; - ret = iommu_map(mapping->domain, iova, phys, len, 0); + ret = iommu_map(mapping->domain, iova, phys, len, + IOMMU_READ|IOMMU_WRITE); if (ret < 0) goto fail; iova += len; @@ -1318,14 +1408,14 @@ static void __iommu_free_atomic(struct device *dev, void *cpu_addr, static void *arm_iommu_alloc_attrs(struct device *dev, size_t size, dma_addr_t *handle, gfp_t gfp, struct dma_attrs *attrs) { - pgprot_t prot = __get_dma_pgprot(attrs, pgprot_kernel); + pgprot_t prot = __get_dma_pgprot(attrs, PAGE_KERNEL); struct page **pages; void *addr = NULL; *handle = DMA_ERROR_CODE; size = PAGE_ALIGN(size); - if (gfp & GFP_ATOMIC) + if (!(gfp & __GFP_WAIT)) return __iommu_alloc_atomic(dev, size, handle); /* @@ -1432,6 +1522,27 @@ static int arm_iommu_get_sgtable(struct device *dev, struct sg_table *sgt, GFP_KERNEL); } +static int __dma_direction_to_prot(enum dma_data_direction dir) +{ + int prot; + + switch (dir) { + case DMA_BIDIRECTIONAL: + prot = IOMMU_READ | IOMMU_WRITE; + break; + case DMA_TO_DEVICE: + prot = IOMMU_READ; + break; + case DMA_FROM_DEVICE: + prot = IOMMU_WRITE; + break; + default: + prot = 0; + } + + return prot; +} + /* * Map a part of the scatter-gather list into contiguous io address space */ @@ -1445,6 +1556,7 @@ static int __map_sg_chunk(struct device *dev, struct scatterlist *sg, int ret = 0; unsigned int count; struct scatterlist *s; + int prot; size = PAGE_ALIGN(size); *handle = DMA_ERROR_CODE; @@ -1461,7 +1573,9 @@ static int __map_sg_chunk(struct device *dev, struct scatterlist *sg, !dma_get_attr(DMA_ATTR_SKIP_CPU_SYNC, attrs)) __dma_page_cpu_to_dev(sg_page(s), s->offset, s->length, dir); - ret = iommu_map(mapping->domain, iova, phys, len, 0); + prot = __dma_direction_to_prot(dir); + + ret = iommu_map(mapping->domain, iova, phys, len, prot); if (ret < 0) goto fail; count += len >> PAGE_SHIFT; @@ -1666,19 +1780,7 @@ static dma_addr_t arm_coherent_iommu_map_page(struct device *dev, struct page *p if (dma_addr == DMA_ERROR_CODE) return dma_addr; - switch (dir) { - case DMA_BIDIRECTIONAL: - prot = IOMMU_READ | IOMMU_WRITE; - break; - case DMA_TO_DEVICE: - prot = IOMMU_READ; - break; - case DMA_FROM_DEVICE: - prot = IOMMU_WRITE; - break; - default: - prot = 0; - } + prot = __dma_direction_to_prot(dir); ret = iommu_map(mapping->domain, dma_addr, page_to_phys(page), len, prot); if (ret < 0) @@ -1830,8 +1932,7 @@ struct dma_map_ops iommu_coherent_ops = { * arm_iommu_create_mapping * @bus: pointer to the bus holding the client device (for IOMMU calls) * @base: start address of the valid IO address space - * @size: size of the valid IO address space - * @order: accuracy of the IO addresses allocations + * @size: maximum size of the valid IO address space * * Creates a mapping structure which holds information about used/unused * IO address ranges, which is required to perform memory allocation and @@ -1841,38 +1942,53 @@ struct dma_map_ops iommu_coherent_ops = { * arm_iommu_attach_device function. */ struct dma_iommu_mapping * -arm_iommu_create_mapping(struct bus_type *bus, dma_addr_t base, size_t size, - int order) +arm_iommu_create_mapping(struct bus_type *bus, dma_addr_t base, size_t size) { - unsigned int count = size >> (PAGE_SHIFT + order); - unsigned int bitmap_size = BITS_TO_LONGS(count) * sizeof(long); + unsigned int bits = size >> PAGE_SHIFT; + unsigned int bitmap_size = BITS_TO_LONGS(bits) * sizeof(long); struct dma_iommu_mapping *mapping; + int extensions = 1; int err = -ENOMEM; - if (!count) + if (!bitmap_size) return ERR_PTR(-EINVAL); + if (bitmap_size > PAGE_SIZE) { + extensions = bitmap_size / PAGE_SIZE; + bitmap_size = PAGE_SIZE; + } + mapping = kzalloc(sizeof(struct dma_iommu_mapping), GFP_KERNEL); if (!mapping) goto err; - mapping->bitmap = kzalloc(bitmap_size, GFP_KERNEL); - if (!mapping->bitmap) + mapping->bitmap_size = bitmap_size; + mapping->bitmaps = kzalloc(extensions * sizeof(unsigned long *), + GFP_KERNEL); + if (!mapping->bitmaps) goto err2; + mapping->bitmaps[0] = kzalloc(bitmap_size, GFP_KERNEL); + if (!mapping->bitmaps[0]) + goto err3; + + mapping->nr_bitmaps = 1; + mapping->extensions = extensions; mapping->base = base; mapping->bits = BITS_PER_BYTE * bitmap_size; - mapping->order = order; + spin_lock_init(&mapping->lock); mapping->domain = iommu_domain_alloc(bus); if (!mapping->domain) - goto err3; + goto err4; kref_init(&mapping->kref); return mapping; +err4: + kfree(mapping->bitmaps[0]); err3: - kfree(mapping->bitmap); + kfree(mapping->bitmaps); err2: kfree(mapping); err: @@ -1882,14 +1998,35 @@ EXPORT_SYMBOL_GPL(arm_iommu_create_mapping); static void release_iommu_mapping(struct kref *kref) { + int i; struct dma_iommu_mapping *mapping = container_of(kref, struct dma_iommu_mapping, kref); iommu_domain_free(mapping->domain); - kfree(mapping->bitmap); + for (i = 0; i < mapping->nr_bitmaps; i++) + kfree(mapping->bitmaps[i]); + kfree(mapping->bitmaps); kfree(mapping); } +static int extend_iommu_mapping(struct dma_iommu_mapping *mapping) +{ + int next_bitmap; + + if (mapping->nr_bitmaps > mapping->extensions) + return -EINVAL; + + next_bitmap = mapping->nr_bitmaps; + mapping->bitmaps[next_bitmap] = kzalloc(mapping->bitmap_size, + GFP_ATOMIC); + if (!mapping->bitmaps[next_bitmap]) + return -ENOMEM; + + mapping->nr_bitmaps++; + + return 0; +} + void arm_iommu_release_mapping(struct dma_iommu_mapping *mapping) { if (mapping) diff --git a/arch/arm/mm/dump.c b/arch/arm/mm/dump.c new file mode 100644 index 00000000000..c508f41a43b --- /dev/null +++ b/arch/arm/mm/dump.c @@ -0,0 +1,365 @@ +/* + * Debug helper to dump the current kernel pagetables of the system + * so that we can see what the various memory ranges are set to. + * + * Derived from x86 implementation: + * (C) Copyright 2008 Intel Corporation + * + * Author: Arjan van de Ven <arjan@linux.intel.com> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; version 2 + * of the License. + */ +#include <linux/debugfs.h> +#include <linux/fs.h> +#include <linux/mm.h> +#include <linux/seq_file.h> + +#include <asm/fixmap.h> +#include <asm/pgtable.h> + +struct addr_marker { + unsigned long start_address; + const char *name; +}; + +static struct addr_marker address_markers[] = { + { MODULES_VADDR, "Modules" }, + { PAGE_OFFSET, "Kernel Mapping" }, + { 0, "vmalloc() Area" }, + { VMALLOC_END, "vmalloc() End" }, + { FIXADDR_START, "Fixmap Area" }, + { CONFIG_VECTORS_BASE, "Vectors" }, + { CONFIG_VECTORS_BASE + PAGE_SIZE * 2, "Vectors End" }, + { -1, NULL }, +}; + +struct pg_state { + struct seq_file *seq; + const struct addr_marker *marker; + unsigned long start_address; + unsigned level; + u64 current_prot; +}; + +struct prot_bits { + u64 mask; + u64 val; + const char *set; + const char *clear; +}; + +static const struct prot_bits pte_bits[] = { + { + .mask = L_PTE_USER, + .val = L_PTE_USER, + .set = "USR", + .clear = " ", + }, { + .mask = L_PTE_RDONLY, + .val = L_PTE_RDONLY, + .set = "ro", + .clear = "RW", + }, { + .mask = L_PTE_XN, + .val = L_PTE_XN, + .set = "NX", + .clear = "x ", + }, { + .mask = L_PTE_SHARED, + .val = L_PTE_SHARED, + .set = "SHD", + .clear = " ", + }, { + .mask = L_PTE_MT_MASK, + .val = L_PTE_MT_UNCACHED, + .set = "SO/UNCACHED", + }, { + .mask = L_PTE_MT_MASK, + .val = L_PTE_MT_BUFFERABLE, + .set = "MEM/BUFFERABLE/WC", + }, { + .mask = L_PTE_MT_MASK, + .val = L_PTE_MT_WRITETHROUGH, + .set = "MEM/CACHED/WT", + }, { + .mask = L_PTE_MT_MASK, + .val = L_PTE_MT_WRITEBACK, + .set = "MEM/CACHED/WBRA", +#ifndef CONFIG_ARM_LPAE + }, { + .mask = L_PTE_MT_MASK, + .val = L_PTE_MT_MINICACHE, + .set = "MEM/MINICACHE", +#endif + }, { + .mask = L_PTE_MT_MASK, + .val = L_PTE_MT_WRITEALLOC, + .set = "MEM/CACHED/WBWA", + }, { + .mask = L_PTE_MT_MASK, + .val = L_PTE_MT_DEV_SHARED, + .set = "DEV/SHARED", +#ifndef CONFIG_ARM_LPAE + }, { + .mask = L_PTE_MT_MASK, + .val = L_PTE_MT_DEV_NONSHARED, + .set = "DEV/NONSHARED", +#endif + }, { + .mask = L_PTE_MT_MASK, + .val = L_PTE_MT_DEV_WC, + .set = "DEV/WC", + }, { + .mask = L_PTE_MT_MASK, + .val = L_PTE_MT_DEV_CACHED, + .set = "DEV/CACHED", + }, +}; + +static const struct prot_bits section_bits[] = { +#ifdef CONFIG_ARM_LPAE + { + .mask = PMD_SECT_USER, + .val = PMD_SECT_USER, + .set = "USR", + }, { + .mask = PMD_SECT_RDONLY, + .val = PMD_SECT_RDONLY, + .set = "ro", + .clear = "RW", +#elif __LINUX_ARM_ARCH__ >= 6 + { + .mask = PMD_SECT_APX | PMD_SECT_AP_READ | PMD_SECT_AP_WRITE, + .val = PMD_SECT_APX | PMD_SECT_AP_WRITE, + .set = " ro", + }, { + .mask = PMD_SECT_APX | PMD_SECT_AP_READ | PMD_SECT_AP_WRITE, + .val = PMD_SECT_AP_WRITE, + .set = " RW", + }, { + .mask = PMD_SECT_APX | PMD_SECT_AP_READ | PMD_SECT_AP_WRITE, + .val = PMD_SECT_AP_READ, + .set = "USR ro", + }, { + .mask = PMD_SECT_APX | PMD_SECT_AP_READ | PMD_SECT_AP_WRITE, + .val = PMD_SECT_AP_READ | PMD_SECT_AP_WRITE, + .set = "USR RW", +#else /* ARMv4/ARMv5 */ + /* These are approximate */ + { + .mask = PMD_SECT_AP_READ | PMD_SECT_AP_WRITE, + .val = 0, + .set = " ro", + }, { + .mask = PMD_SECT_AP_READ | PMD_SECT_AP_WRITE, + .val = PMD_SECT_AP_WRITE, + .set = " RW", + }, { + .mask = PMD_SECT_AP_READ | PMD_SECT_AP_WRITE, + .val = PMD_SECT_AP_READ, + .set = "USR ro", + }, { + .mask = PMD_SECT_AP_READ | PMD_SECT_AP_WRITE, + .val = PMD_SECT_AP_READ | PMD_SECT_AP_WRITE, + .set = "USR RW", +#endif + }, { + .mask = PMD_SECT_XN, + .val = PMD_SECT_XN, + .set = "NX", + .clear = "x ", + }, { + .mask = PMD_SECT_S, + .val = PMD_SECT_S, + .set = "SHD", + .clear = " ", + }, +}; + +struct pg_level { + const struct prot_bits *bits; + size_t num; + u64 mask; +}; + +static struct pg_level pg_level[] = { + { + }, { /* pgd */ + }, { /* pud */ + }, { /* pmd */ + .bits = section_bits, + .num = ARRAY_SIZE(section_bits), + }, { /* pte */ + .bits = pte_bits, + .num = ARRAY_SIZE(pte_bits), + }, +}; + +static void dump_prot(struct pg_state *st, const struct prot_bits *bits, size_t num) +{ + unsigned i; + + for (i = 0; i < num; i++, bits++) { + const char *s; + + if ((st->current_prot & bits->mask) == bits->val) + s = bits->set; + else + s = bits->clear; + + if (s) + seq_printf(st->seq, " %s", s); + } +} + +static void note_page(struct pg_state *st, unsigned long addr, unsigned level, u64 val) +{ + static const char units[] = "KMGTPE"; + u64 prot = val & pg_level[level].mask; + + if (addr < USER_PGTABLES_CEILING) + return; + + if (!st->level) { + st->level = level; + st->current_prot = prot; + seq_printf(st->seq, "---[ %s ]---\n", st->marker->name); + } else if (prot != st->current_prot || level != st->level || + addr >= st->marker[1].start_address) { + const char *unit = units; + unsigned long delta; + + if (st->current_prot) { + seq_printf(st->seq, "0x%08lx-0x%08lx ", + st->start_address, addr); + + delta = (addr - st->start_address) >> 10; + while (!(delta & 1023) && unit[1]) { + delta >>= 10; + unit++; + } + seq_printf(st->seq, "%9lu%c", delta, *unit); + if (pg_level[st->level].bits) + dump_prot(st, pg_level[st->level].bits, pg_level[st->level].num); + seq_printf(st->seq, "\n"); + } + + if (addr >= st->marker[1].start_address) { + st->marker++; + seq_printf(st->seq, "---[ %s ]---\n", st->marker->name); + } + st->start_address = addr; + st->current_prot = prot; + st->level = level; + } +} + +static void walk_pte(struct pg_state *st, pmd_t *pmd, unsigned long start) +{ + pte_t *pte = pte_offset_kernel(pmd, 0); + unsigned long addr; + unsigned i; + + for (i = 0; i < PTRS_PER_PTE; i++, pte++) { + addr = start + i * PAGE_SIZE; + note_page(st, addr, 4, pte_val(*pte)); + } +} + +static void walk_pmd(struct pg_state *st, pud_t *pud, unsigned long start) +{ + pmd_t *pmd = pmd_offset(pud, 0); + unsigned long addr; + unsigned i; + + for (i = 0; i < PTRS_PER_PMD; i++, pmd++) { + addr = start + i * PMD_SIZE; + if (pmd_none(*pmd) || pmd_large(*pmd) || !pmd_present(*pmd)) + note_page(st, addr, 3, pmd_val(*pmd)); + else + walk_pte(st, pmd, addr); + + if (SECTION_SIZE < PMD_SIZE && pmd_large(pmd[1])) + note_page(st, addr + SECTION_SIZE, 3, pmd_val(pmd[1])); + } +} + +static void walk_pud(struct pg_state *st, pgd_t *pgd, unsigned long start) +{ + pud_t *pud = pud_offset(pgd, 0); + unsigned long addr; + unsigned i; + + for (i = 0; i < PTRS_PER_PUD; i++, pud++) { + addr = start + i * PUD_SIZE; + if (!pud_none(*pud)) { + walk_pmd(st, pud, addr); + } else { + note_page(st, addr, 2, pud_val(*pud)); + } + } +} + +static void walk_pgd(struct seq_file *m) +{ + pgd_t *pgd = swapper_pg_dir; + struct pg_state st; + unsigned long addr; + unsigned i, pgdoff = USER_PGTABLES_CEILING / PGDIR_SIZE; + + memset(&st, 0, sizeof(st)); + st.seq = m; + st.marker = address_markers; + + pgd += pgdoff; + + for (i = pgdoff; i < PTRS_PER_PGD; i++, pgd++) { + addr = i * PGDIR_SIZE; + if (!pgd_none(*pgd)) { + walk_pud(&st, pgd, addr); + } else { + note_page(&st, addr, 1, pgd_val(*pgd)); + } + } + + note_page(&st, 0, 0, 0); +} + +static int ptdump_show(struct seq_file *m, void *v) +{ + walk_pgd(m); + return 0; +} + +static int ptdump_open(struct inode *inode, struct file *file) +{ + return single_open(file, ptdump_show, NULL); +} + +static const struct file_operations ptdump_fops = { + .open = ptdump_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static int ptdump_init(void) +{ + struct dentry *pe; + unsigned i, j; + + for (i = 0; i < ARRAY_SIZE(pg_level); i++) + if (pg_level[i].bits) + for (j = 0; j < pg_level[i].num; j++) + pg_level[i].mask |= pg_level[i].bits[j].mask; + + address_markers[2].start_address = VMALLOC_START; + + pe = debugfs_create_file("kernel_page_tables", 0400, NULL, NULL, + &ptdump_fops); + return pe ? 0 : -ENOMEM; +} +__initcall(ptdump_init); diff --git a/arch/arm/mm/extable.c b/arch/arm/mm/extable.c index 9d285626bc7..312e15e6d00 100644 --- a/arch/arm/mm/extable.c +++ b/arch/arm/mm/extable.c @@ -9,8 +9,13 @@ int fixup_exception(struct pt_regs *regs) const struct exception_table_entry *fixup; fixup = search_exception_tables(instruction_pointer(regs)); - if (fixup) + if (fixup) { regs->ARM_pc = fixup->fixup; +#ifdef CONFIG_THUMB2_KERNEL + /* Clear the IT state to avoid nasty surprises in the fixup */ + regs->ARM_cpsr &= ~PSR_IT_MASK; +#endif + } return fixup != NULL; } diff --git a/arch/arm/mm/fault-armv.c b/arch/arm/mm/fault-armv.c index 2a5907b5c8d..ff379ac115d 100644 --- a/arch/arm/mm/fault-armv.c +++ b/arch/arm/mm/fault-armv.c @@ -65,7 +65,7 @@ static int do_adjust_pte(struct vm_area_struct *vma, unsigned long address, return ret; } -#if USE_SPLIT_PTLOCKS +#if USE_SPLIT_PTE_PTLOCKS /* * If we are using split PTE locks, then we need to take the page * lock here. Otherwise we are using shared mm->page_table_lock @@ -84,10 +84,10 @@ static inline void do_pte_unlock(spinlock_t *ptl) { spin_unlock(ptl); } -#else /* !USE_SPLIT_PTLOCKS */ +#else /* !USE_SPLIT_PTE_PTLOCKS */ static inline void do_pte_lock(spinlock_t *ptl) {} static inline void do_pte_unlock(spinlock_t *ptl) {} -#endif /* USE_SPLIT_PTLOCKS */ +#endif /* USE_SPLIT_PTE_PTLOCKS */ static int adjust_pte(struct vm_area_struct *vma, unsigned long address, unsigned long pfn) diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c index c97f7940cb9..eb8830a4c5e 100644 --- a/arch/arm/mm/fault.c +++ b/arch/arm/mm/fault.c @@ -261,9 +261,7 @@ 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); + unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; if (notify_page_fault(regs, fsr)) return 0; @@ -282,6 +280,11 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs) if (in_atomic() || !mm) goto no_context; + if (user_mode(regs)) + flags |= FAULT_FLAG_USER; + if (fsr & FSR_WRITE) + flags |= FAULT_FLAG_WRITE; + /* * As per x86, we may deadlock here. However, since the kernel only * validly references user space from well defined areas of the code, @@ -349,6 +352,13 @@ retry: if (likely(!(fault & (VM_FAULT_ERROR | VM_FAULT_BADMAP | VM_FAULT_BADACCESS)))) return 0; + /* + * If we are in kernel mode at this point, we + * have no context to handle this fault with. + */ + if (!user_mode(regs)) + goto no_context; + if (fault & VM_FAULT_OOM) { /* * We ran out of memory, call the OOM killer, and return to @@ -359,13 +369,6 @@ retry: return 0; } - /* - * If we are in kernel mode at this point, we - * have no context to handle this fault with. - */ - if (!user_mode(regs)) - goto no_context; - if (fault & VM_FAULT_SIGBUS) { /* * We had some memory, but were unable to diff --git a/arch/arm/mm/flush.c b/arch/arm/mm/flush.c index 6d5ba9afb16..43d54f5b26b 100644 --- a/arch/arm/mm/flush.c +++ b/arch/arm/mm/flush.c @@ -104,17 +104,20 @@ void flush_cache_page(struct vm_area_struct *vma, unsigned long user_addr, unsig #define flush_icache_alias(pfn,vaddr,len) do { } while (0) #endif +#define FLAG_PA_IS_EXEC 1 +#define FLAG_PA_CORE_IN_MM 2 + static void flush_ptrace_access_other(void *args) { __flush_icache_all(); } -static -void flush_ptrace_access(struct vm_area_struct *vma, struct page *page, - unsigned long uaddr, void *kaddr, unsigned long len) +static inline +void __flush_ptrace_access(struct page *page, unsigned long uaddr, void *kaddr, + unsigned long len, unsigned int flags) { if (cache_is_vivt()) { - if (cpumask_test_cpu(smp_processor_id(), mm_cpumask(vma->vm_mm))) { + if (flags & FLAG_PA_CORE_IN_MM) { unsigned long addr = (unsigned long)kaddr; __cpuc_coherent_kern_range(addr, addr + len); } @@ -128,7 +131,7 @@ void flush_ptrace_access(struct vm_area_struct *vma, struct page *page, } /* VIPT non-aliasing D-cache */ - if (vma->vm_flags & VM_EXEC) { + if (flags & FLAG_PA_IS_EXEC) { unsigned long addr = (unsigned long)kaddr; if (icache_is_vipt_aliasing()) flush_icache_alias(page_to_pfn(page), uaddr, len); @@ -140,6 +143,26 @@ void flush_ptrace_access(struct vm_area_struct *vma, struct page *page, } } +static +void flush_ptrace_access(struct vm_area_struct *vma, struct page *page, + unsigned long uaddr, void *kaddr, unsigned long len) +{ + unsigned int flags = 0; + if (cpumask_test_cpu(smp_processor_id(), mm_cpumask(vma->vm_mm))) + flags |= FLAG_PA_CORE_IN_MM; + if (vma->vm_flags & VM_EXEC) + flags |= FLAG_PA_IS_EXEC; + __flush_ptrace_access(page, uaddr, kaddr, len, flags); +} + +void flush_uprobe_xol_access(struct page *page, unsigned long uaddr, + void *kaddr, unsigned long len) +{ + unsigned int flags = FLAG_PA_CORE_IN_MM|FLAG_PA_IS_EXEC; + + __flush_ptrace_access(page, uaddr, kaddr, len, flags); +} + /* * Copy user data from/to a page which is mapped into a different * processes address space. Really, we want to allow our "user @@ -175,16 +198,16 @@ void __flush_dcache_page(struct address_space *mapping, struct page *page) unsigned long i; if (cache_is_vipt_nonaliasing()) { for (i = 0; i < (1 << compound_order(page)); i++) { - void *addr = kmap_atomic(page); + void *addr = kmap_atomic(page + i); __cpuc_flush_dcache_area(addr, PAGE_SIZE); kunmap_atomic(addr); } } else { for (i = 0; i < (1 << compound_order(page)); i++) { - void *addr = kmap_high_get(page); + void *addr = kmap_high_get(page + i); if (addr) { __cpuc_flush_dcache_area(addr, PAGE_SIZE); - kunmap_high(page); + kunmap_high(page + i); } } } diff --git a/arch/arm/mm/highmem.c b/arch/arm/mm/highmem.c index 21b9e1bf9b7..45aeaaca905 100644 --- a/arch/arm/mm/highmem.c +++ b/arch/arm/mm/highmem.c @@ -18,6 +18,21 @@ #include <asm/tlbflush.h> #include "mm.h" +pte_t *fixmap_page_table; + +static inline void set_fixmap_pte(int idx, pte_t pte) +{ + unsigned long vaddr = __fix_to_virt(idx); + set_pte_ext(fixmap_page_table + idx, pte, 0); + local_flush_tlb_kernel_page(vaddr); +} + +static inline pte_t get_fixmap_pte(unsigned long vaddr) +{ + unsigned long idx = __virt_to_fix(vaddr); + return *(fixmap_page_table + idx); +} + void *kmap(struct page *page) { might_sleep(); @@ -63,20 +78,20 @@ void *kmap_atomic(struct page *page) type = kmap_atomic_idx_push(); idx = type + KM_TYPE_NR * smp_processor_id(); - vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx); + vaddr = __fix_to_virt(idx); #ifdef CONFIG_DEBUG_HIGHMEM /* * With debugging enabled, kunmap_atomic forces that entry to 0. * Make sure it was indeed properly unmapped. */ - BUG_ON(!pte_none(get_top_pte(vaddr))); + BUG_ON(!pte_none(*(fixmap_page_table + idx))); #endif /* * When debugging is off, kunmap_atomic leaves the previous mapping * in place, so the contained TLB flush ensures the TLB is updated * with the new mapping. */ - set_top_pte(vaddr, mk_pte(page, kmap_prot)); + set_fixmap_pte(idx, mk_pte(page, kmap_prot)); return (void *)vaddr; } @@ -94,8 +109,8 @@ void __kunmap_atomic(void *kvaddr) if (cache_is_vivt()) __cpuc_flush_dcache_area((void *)vaddr, PAGE_SIZE); #ifdef CONFIG_DEBUG_HIGHMEM - BUG_ON(vaddr != __fix_to_virt(FIX_KMAP_BEGIN + idx)); - set_top_pte(vaddr, __pte(0)); + BUG_ON(vaddr != __fix_to_virt(idx)); + set_fixmap_pte(idx, __pte(0)); #else (void) idx; /* to kill a warning */ #endif @@ -117,11 +132,11 @@ void *kmap_atomic_pfn(unsigned long pfn) type = kmap_atomic_idx_push(); idx = type + KM_TYPE_NR * smp_processor_id(); - vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx); + vaddr = __fix_to_virt(idx); #ifdef CONFIG_DEBUG_HIGHMEM - BUG_ON(!pte_none(get_top_pte(vaddr))); + BUG_ON(!pte_none(*(fixmap_page_table + idx))); #endif - set_top_pte(vaddr, pfn_pte(pfn, kmap_prot)); + set_fixmap_pte(idx, pfn_pte(pfn, kmap_prot)); return (void *)vaddr; } @@ -133,5 +148,5 @@ struct page *kmap_atomic_to_page(const void *ptr) if (vaddr < FIXADDR_START) return virt_to_page(ptr); - return pte_page(get_top_pte(vaddr)); + return pte_page(get_fixmap_pte(vaddr)); } diff --git a/arch/arm/mm/hugetlbpage.c b/arch/arm/mm/hugetlbpage.c index 3d1e4a205b0..66781bf3407 100644 --- a/arch/arm/mm/hugetlbpage.c +++ b/arch/arm/mm/hugetlbpage.c @@ -36,22 +36,6 @@ * of type casting from pmd_t * to pte_t *. */ -pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr) -{ - pgd_t *pgd; - pud_t *pud; - pmd_t *pmd = NULL; - - pgd = pgd_offset(mm, addr); - if (pgd_present(*pgd)) { - pud = pud_offset(pgd, addr); - if (pud_present(*pud)) - pmd = pmd_offset(pud, addr); - } - - return (pte_t *)pmd; -} - struct page *follow_huge_addr(struct mm_struct *mm, unsigned long address, int write) { @@ -68,33 +52,6 @@ int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep) return 0; } -pte_t *huge_pte_alloc(struct mm_struct *mm, - unsigned long addr, unsigned long sz) -{ - pgd_t *pgd; - pud_t *pud; - pte_t *pte = NULL; - - pgd = pgd_offset(mm, addr); - pud = pud_alloc(mm, pgd, addr); - if (pud) - pte = (pte_t *)pmd_alloc(mm, pud, addr); - - return pte; -} - -struct page * -follow_huge_pmd(struct mm_struct *mm, unsigned long address, - pmd_t *pmd, int write) -{ - struct page *page; - - page = pte_page(*(pte_t *)pmd); - if (page) - page += ((address & ~PMD_MASK) >> PAGE_SHIFT); - return page; -} - int pmd_huge(pmd_t pmd) { return pmd_val(pmd) && !(pmd_val(pmd) & PMD_TABLE_BIT); diff --git a/arch/arm/mm/idmap.c b/arch/arm/mm/idmap.c index 83cb3ac2709..c447ec70e86 100644 --- a/arch/arm/mm/idmap.c +++ b/arch/arm/mm/idmap.c @@ -9,7 +9,13 @@ #include <asm/sections.h> #include <asm/system_info.h> +/* + * Note: accesses outside of the kernel image and the identity map area + * are not supported on any CPU using the idmap tables as its current + * page tables. + */ pgd_t *idmap_pgd; +phys_addr_t (*arch_virt_to_idmap) (unsigned long x); #ifdef CONFIG_ARM_LPAE static void idmap_add_pmd(pud_t *pud, unsigned long addr, unsigned long end, @@ -24,6 +30,13 @@ static void idmap_add_pmd(pud_t *pud, unsigned long addr, unsigned long end, pr_warning("Failed to allocate identity pmd.\n"); return; } + /* + * Copy the original PMD to ensure that the PMD entries for + * the kernel image are preserved. + */ + if (!pud_none(*pud)) + memcpy(pmd, pmd_offset(pud, 0), + PTRS_PER_PMD * sizeof(pmd_t)); pud_populate(&init_mm, pud, pmd); pmd += pmd_index(addr); } else @@ -67,8 +80,9 @@ static void identity_mapping_add(pgd_t *pgd, const char *text_start, unsigned long addr, end; unsigned long next; - addr = virt_to_phys(text_start); - end = virt_to_phys(text_end); + addr = virt_to_idmap(text_start); + end = virt_to_idmap(text_end); + pr_info("Setting up static identity map for 0x%lx - 0x%lx\n", addr, end); prot |= PMD_TYPE_SECT | PMD_SECT_AP_WRITE | PMD_SECT_AF; @@ -90,8 +104,6 @@ static int __init init_static_idmap(void) if (!idmap_pgd) return -ENOMEM; - pr_info("Setting up static identity map for 0x%p - 0x%p\n", - __idmap_text_start, __idmap_text_end); identity_mapping_add(idmap_pgd, __idmap_text_start, __idmap_text_end, 0); diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c index 15225d829d7..659c75d808d 100644 --- a/arch/arm/mm/init.c +++ b/arch/arm/mm/init.c @@ -23,6 +23,7 @@ #include <linux/dma-contiguous.h> #include <linux/sizes.h> +#include <asm/cp15.h> #include <asm/mach-types.h> #include <asm/memblock.h> #include <asm/prom.h> @@ -36,6 +37,14 @@ #include "mm.h" +#ifdef CONFIG_CPU_CP15_MMU +unsigned long __init __clear_cr(unsigned long mask) +{ + cr_alignment = cr_alignment & ~mask; + return cr_alignment; +} +#endif + static phys_addr_t phys_initrd_start __initdata = 0; static unsigned long phys_initrd_size __initdata = 0; @@ -76,40 +85,26 @@ static int __init parse_tag_initrd2(const struct tag *tag) __tagtable(ATAG_INITRD2, parse_tag_initrd2); -#ifdef CONFIG_OF_FLATTREE -void __init early_init_dt_setup_initrd_arch(unsigned long start, unsigned long end) -{ - phys_initrd_start = start; - phys_initrd_size = end - start; -} -#endif /* CONFIG_OF_FLATTREE */ - /* * This keeps memory configuration data used by a couple memory * initialization functions, as well as show_mem() for the skipping * of holes in the memory map. It is populated by arm_add_memory(). */ -struct meminfo meminfo; - void show_mem(unsigned int filter) { int free = 0, total = 0, reserved = 0; - int shared = 0, cached = 0, slab = 0, i; - struct meminfo * mi = &meminfo; + int shared = 0, cached = 0, slab = 0; + struct memblock_region *reg; printk("Mem-info:\n"); show_free_areas(filter); - if (filter & SHOW_MEM_FILTER_PAGE_COUNT) - return; - - for_each_bank (i, mi) { - struct membank *bank = &mi->bank[i]; + for_each_memblock (memory, reg) { unsigned int pfn1, pfn2; struct page *page, *end; - pfn1 = bank_pfn_start(bank); - pfn2 = bank_pfn_end(bank); + pfn1 = memblock_region_memory_base_pfn(reg); + pfn2 = memblock_region_memory_end_pfn(reg); page = pfn_to_page(pfn1); end = pfn_to_page(pfn2 - 1) + 1; @@ -126,8 +121,9 @@ void show_mem(unsigned int filter) free++; else shared += page_count(page) - 1; - page++; - } while (page < end); + pfn1++; + page = pfn_to_page(pfn1); + } while (pfn1 < pfn2); } printk("%d pages of RAM\n", total); @@ -141,73 +137,14 @@ void show_mem(unsigned int filter) static void __init find_limits(unsigned long *min, unsigned long *max_low, unsigned long *max_high) { - struct meminfo *mi = &meminfo; - int i; - - /* This assumes the meminfo array is properly sorted */ - *min = bank_pfn_start(&mi->bank[0]); - for_each_bank (i, mi) - if (mi->bank[i].highmem) - break; - *max_low = bank_pfn_end(&mi->bank[i - 1]); - *max_high = bank_pfn_end(&mi->bank[mi->nr_banks - 1]); -} - -static void __init arm_bootmem_init(unsigned long start_pfn, - unsigned long end_pfn) -{ - struct memblock_region *reg; - unsigned int boot_pages; - phys_addr_t bitmap; - pg_data_t *pgdat; - - /* - * Allocate the bootmem bitmap page. This must be in a region - * of memory which has already been mapped. - */ - boot_pages = bootmem_bootmap_pages(end_pfn - start_pfn); - bitmap = memblock_alloc_base(boot_pages << PAGE_SHIFT, L1_CACHE_BYTES, - __pfn_to_phys(end_pfn)); - - /* - * Initialise the bootmem allocator, handing the - * memory banks over to bootmem. - */ - node_set_online(0); - pgdat = NODE_DATA(0); - init_bootmem_node(pgdat, __phys_to_pfn(bitmap), start_pfn, end_pfn); - - /* Free the lowmem regions from memblock into bootmem. */ - for_each_memblock(memory, reg) { - unsigned long start = memblock_region_memory_base_pfn(reg); - unsigned long end = memblock_region_memory_end_pfn(reg); - - if (end >= end_pfn) - end = end_pfn; - if (start >= end) - break; - - free_bootmem(__pfn_to_phys(start), (end - start) << PAGE_SHIFT); - } - - /* Reserve the lowmem memblock reserved regions in bootmem. */ - for_each_memblock(reserved, reg) { - unsigned long start = memblock_region_reserved_base_pfn(reg); - unsigned long end = memblock_region_reserved_end_pfn(reg); - - if (end >= end_pfn) - end = end_pfn; - if (start >= end) - break; - - reserve_bootmem(__pfn_to_phys(start), - (end - start) << PAGE_SHIFT, BOOTMEM_DEFAULT); - } + *max_low = PFN_DOWN(memblock_get_current_limit()); + *min = PFN_UP(memblock_start_of_DRAM()); + *max_high = PFN_DOWN(memblock_end_of_DRAM()); } #ifdef CONFIG_ZONE_DMA -unsigned long arm_dma_zone_size __read_mostly; +phys_addr_t arm_dma_zone_size __read_mostly; EXPORT_SYMBOL(arm_dma_zone_size); /* @@ -217,6 +154,7 @@ EXPORT_SYMBOL(arm_dma_zone_size); * so a successful GFP_DMA allocation will always satisfy this. */ phys_addr_t arm_dma_limit; +unsigned long arm_dma_pfn_limit; static void __init arm_adjust_dma_zone(unsigned long *size, unsigned long *hole, unsigned long dma_size) @@ -231,7 +169,7 @@ static void __init arm_adjust_dma_zone(unsigned long *size, unsigned long *hole, } #endif -void __init setup_dma_zone(struct machine_desc *mdesc) +void __init setup_dma_zone(const struct machine_desc *mdesc) { #ifdef CONFIG_ZONE_DMA if (mdesc->dma_zone_size) { @@ -239,10 +177,11 @@ void __init setup_dma_zone(struct machine_desc *mdesc) arm_dma_limit = PHYS_OFFSET + arm_dma_zone_size - 1; } else arm_dma_limit = 0xffffffff; + arm_dma_pfn_limit = arm_dma_limit >> PAGE_SHIFT; #endif } -static void __init arm_bootmem_free(unsigned long min, unsigned long max_low, +static void __init zone_sizes_init(unsigned long min, unsigned long max_low, unsigned long max_high) { unsigned long zone_size[MAX_NR_ZONES], zhole_size[MAX_NR_ZONES]; @@ -335,13 +274,8 @@ phys_addr_t __init arm_memblock_steal(phys_addr_t size, phys_addr_t align) return phys; } -void __init arm_memblock_init(struct meminfo *mi, struct machine_desc *mdesc) +void __init arm_memblock_init(const struct machine_desc *mdesc) { - int i; - - for (i = 0; i < mi->nr_banks; i++) - memblock_add(mi->bank[i].start, mi->bank[i].size); - /* Register the kernel text, kernel data and initrd with memblock. */ #ifdef CONFIG_XIP_KERNEL memblock_reserve(__pa(_sdata), _end - _sdata); @@ -349,6 +283,12 @@ void __init arm_memblock_init(struct meminfo *mi, struct machine_desc *mdesc) memblock_reserve(__pa(_stext), _end - _stext); #endif #ifdef CONFIG_BLK_DEV_INITRD + /* FDT scan will populate initrd_start */ + if (initrd_start && !phys_initrd_size) { + phys_initrd_start = __virt_to_phys(initrd_start); + phys_initrd_size = initrd_end - initrd_start; + } + initrd_start = initrd_end = 0; if (phys_initrd_size && !memblock_is_region_memory(phys_initrd_start, phys_initrd_size)) { pr_err("INITRD: 0x%08llx+0x%08lx is not a memory region - disabling initrd\n", @@ -371,12 +311,13 @@ void __init arm_memblock_init(struct meminfo *mi, struct machine_desc *mdesc) #endif arm_mm_memblock_reserve(); - arm_dt_memblock_reserve(); /* reserve any platform specific memblock areas */ if (mdesc->reserve) mdesc->reserve(); + early_init_fdt_scan_reserved_mem(); + /* * reserve memory for DMA contigouos allocations, * must come from DMA area inside low memory @@ -384,7 +325,6 @@ void __init arm_memblock_init(struct meminfo *mi, struct machine_desc *mdesc) dma_contiguous_reserve(min(arm_dma_limit, arm_lowmem_limit)); arm_memblock_steal_permitted = false; - memblock_allow_resize(); memblock_dump_all(); } @@ -392,12 +332,11 @@ void __init bootmem_init(void) { unsigned long min, max_low, max_high; + memblock_allow_resize(); max_low = max_high = 0; find_limits(&min, &max_low, &max_high); - arm_bootmem_init(min, max_low); - /* * Sparsemem tries to allocate bootmem in memory_present(), * so must be done after the fixed reservations @@ -414,18 +353,16 @@ void __init bootmem_init(void) * the sparse mem_map arrays initialized by sparse_init() * for memmap_init_zone(), otherwise all PFNs are invalid. */ - arm_bootmem_free(min, max_low, max_high); + zone_sizes_init(min, max_low, max_high); /* * 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 * also get rid of some of the stuff above as well. - * - * Note: max_low_pfn and max_pfn reflect the number of _pages_ in - * the system, not the maximum PFN. */ - max_low_pfn = max_low - PHYS_PFN_OFFSET; - max_pfn = max_high - PHYS_PFN_OFFSET; + min_low_pfn = min; + max_low_pfn = max_low; + max_pfn = max_high; } /* @@ -463,60 +400,59 @@ free_memmap(unsigned long start_pfn, unsigned long end_pfn) * free the section of the memmap array. */ if (pg < pgend) - free_bootmem(pg, pgend - pg); + memblock_free_early(pg, pgend - pg); } /* * The mem_map array can get very big. Free the unused area of the memory map. */ -static void __init free_unused_memmap(struct meminfo *mi) +static void __init free_unused_memmap(void) { - unsigned long bank_start, prev_bank_end = 0; - unsigned int i; + unsigned long start, prev_end = 0; + struct memblock_region *reg; /* * This relies on each bank being in address order. * The banks are sorted previously in bootmem_init(). */ - for_each_bank(i, mi) { - struct membank *bank = &mi->bank[i]; - - bank_start = bank_pfn_start(bank); + for_each_memblock(memory, reg) { + start = memblock_region_memory_base_pfn(reg); #ifdef CONFIG_SPARSEMEM /* * Take care not to free memmap entries that don't exist * due to SPARSEMEM sections which aren't present. */ - bank_start = min(bank_start, - ALIGN(prev_bank_end, PAGES_PER_SECTION)); + start = min(start, + ALIGN(prev_end, PAGES_PER_SECTION)); #else /* * Align down here since the VM subsystem insists that the * memmap entries are valid from the bank start aligned to * MAX_ORDER_NR_PAGES. */ - bank_start = round_down(bank_start, MAX_ORDER_NR_PAGES); + start = round_down(start, MAX_ORDER_NR_PAGES); #endif /* * If we had a previous bank, and there is a space * between the current bank and the previous, free it. */ - if (prev_bank_end && prev_bank_end < bank_start) - free_memmap(prev_bank_end, bank_start); + if (prev_end && prev_end < start) + free_memmap(prev_end, start); /* * Align up here since the VM subsystem insists that the * memmap entries are valid from the bank end aligned to * MAX_ORDER_NR_PAGES. */ - prev_bank_end = ALIGN(bank_pfn_end(bank), MAX_ORDER_NR_PAGES); + prev_end = ALIGN(memblock_region_memory_end_pfn(reg), + MAX_ORDER_NR_PAGES); } #ifdef CONFIG_SPARSEMEM - if (!IS_ALIGNED(prev_bank_end, PAGES_PER_SECTION)) - free_memmap(prev_bank_end, - ALIGN(prev_bank_end, PAGES_PER_SECTION)); + if (!IS_ALIGNED(prev_end, PAGES_PER_SECTION)) + free_memmap(prev_end, + ALIGN(prev_end, PAGES_PER_SECTION)); #endif } @@ -531,7 +467,7 @@ static inline void free_area_high(unsigned long pfn, unsigned long end) static void __init free_highpages(void) { #ifdef CONFIG_HIGHMEM - unsigned long max_low = max_low_pfn + PHYS_PFN_OFFSET; + unsigned long max_low = max_low_pfn; struct memblock_region *mem, *res; /* set highmem page free */ @@ -589,10 +525,10 @@ void __init mem_init(void) extern u32 itcm_end; #endif - max_mapnr = pfn_to_page(max_pfn + PHYS_PFN_OFFSET) - mem_map; + set_max_mapnr(pfn_to_page(max_pfn) - mem_map); /* this will put all unused low memory onto the freelists */ - free_unused_memmap(&meminfo); + free_unused_memmap(); free_all_bootmem(); #ifdef CONFIG_SA1111 diff --git a/arch/arm/mm/ioremap.c b/arch/arm/mm/ioremap.c index f123d6eb074..d1e5ad7ab3b 100644 --- a/arch/arm/mm/ioremap.c +++ b/arch/arm/mm/ioremap.c @@ -392,9 +392,9 @@ __arm_ioremap_exec(phys_addr_t phys_addr, size_t size, bool cached) unsigned int mtype; if (cached) - mtype = MT_MEMORY; + mtype = MT_MEMORY_RWX; else - mtype = MT_MEMORY_NONCACHED; + mtype = MT_MEMORY_RWX_NONCACHED; return __arm_ioremap_caller(phys_addr, size, mtype, __builtin_return_address(0)); @@ -438,6 +438,13 @@ void __arm_iounmap(volatile void __iomem *io_addr) EXPORT_SYMBOL(__arm_iounmap); #ifdef CONFIG_PCI +static int pci_ioremap_mem_type = MT_DEVICE; + +void pci_ioremap_set_mem_type(int mem_type) +{ + pci_ioremap_mem_type = mem_type; +} + int pci_ioremap_io(unsigned int offset, phys_addr_t phys_addr) { BUG_ON(offset + SZ_64K > IO_SPACE_LIMIT); @@ -445,7 +452,7 @@ int pci_ioremap_io(unsigned int offset, phys_addr_t phys_addr) return ioremap_page_range(PCI_IO_VIRT_BASE + offset, PCI_IO_VIRT_BASE + offset + SZ_64K, phys_addr, - __pgprot(get_mem_type(MT_DEVICE)->prot_pte)); + __pgprot(get_mem_type(pci_ioremap_mem_type)->prot_pte)); } EXPORT_SYMBOL_GPL(pci_ioremap_io); #endif diff --git a/arch/arm/mm/l2c-common.c b/arch/arm/mm/l2c-common.c new file mode 100644 index 00000000000..10a3cf28c36 --- /dev/null +++ b/arch/arm/mm/l2c-common.c @@ -0,0 +1,20 @@ +/* + * Copyright (C) 2010 ARM Ltd. + * Written by Catalin Marinas <catalin.marinas@arm.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ +#include <linux/bug.h> +#include <linux/smp.h> +#include <asm/outercache.h> + +void outer_disable(void) +{ + WARN_ON(!irqs_disabled()); + WARN_ON(num_online_cpus() > 1); + + if (outer_cache.disable) + outer_cache.disable(); +} diff --git a/arch/arm/mm/l2c-l2x0-resume.S b/arch/arm/mm/l2c-l2x0-resume.S new file mode 100644 index 00000000000..99b05f21a59 --- /dev/null +++ b/arch/arm/mm/l2c-l2x0-resume.S @@ -0,0 +1,58 @@ +/* + * L2C-310 early resume code. This can be used by platforms to restore + * the settings of their L2 cache controller before restoring the + * processor state. + * + * This code can only be used to if you are running in the secure world. + */ +#include <linux/linkage.h> +#include <asm/hardware/cache-l2x0.h> + + .text + +ENTRY(l2c310_early_resume) + adr r0, 1f + ldr r2, [r0] + add r0, r2, r0 + + ldmia r0, {r1, r2, r3, r4, r5, r6, r7, r8} + @ r1 = phys address of L2C-310 controller + @ r2 = aux_ctrl + @ r3 = tag_latency + @ r4 = data_latency + @ r5 = filter_start + @ r6 = filter_end + @ r7 = prefetch_ctrl + @ r8 = pwr_ctrl + + @ Check that the address has been initialised + teq r1, #0 + moveq pc, lr + + @ The prefetch and power control registers are revision dependent + @ and can be written whether or not the L2 cache is enabled + ldr r0, [r1, #L2X0_CACHE_ID] + and r0, r0, #L2X0_CACHE_ID_RTL_MASK + cmp r0, #L310_CACHE_ID_RTL_R2P0 + strcs r7, [r1, #L310_PREFETCH_CTRL] + cmp r0, #L310_CACHE_ID_RTL_R3P0 + strcs r8, [r1, #L310_POWER_CTRL] + + @ Don't setup the L2 cache if it is already enabled + ldr r0, [r1, #L2X0_CTRL] + tst r0, #L2X0_CTRL_EN + movne pc, lr + + str r3, [r1, #L310_TAG_LATENCY_CTRL] + str r4, [r1, #L310_DATA_LATENCY_CTRL] + str r6, [r1, #L310_ADDR_FILTER_END] + str r5, [r1, #L310_ADDR_FILTER_START] + + str r2, [r1, #L2X0_AUX_CTRL] + mov r9, #L2X0_CTRL_EN + str r9, [r1, #L2X0_CTRL] + mov pc, lr +ENDPROC(l2c310_early_resume) + + .align +1: .long l2x0_saved_regs - . diff --git a/arch/arm/mm/mm.h b/arch/arm/mm/mm.h index d5a4e9ad8f0..ce727d47275 100644 --- a/arch/arm/mm/mm.h +++ b/arch/arm/mm/mm.h @@ -2,6 +2,8 @@ #include <linux/list.h> #include <linux/vmalloc.h> +#include <asm/pgtable.h> + /* the upper-most page table pointer */ extern pmd_t *top_pmd; @@ -38,6 +40,7 @@ static inline pmd_t *pmd_off_k(unsigned long virt) struct mem_type { pteval_t prot_pte; + pteval_t prot_pte_s2; pmdval_t prot_l1; pmdval_t prot_sect; unsigned int domain; @@ -81,8 +84,10 @@ extern __init void add_static_vm_early(struct static_vm *svm); #ifdef CONFIG_ZONE_DMA extern phys_addr_t arm_dma_limit; +extern unsigned long arm_dma_pfn_limit; #else #define arm_dma_limit ((phys_addr_t)~0) +#define arm_dma_pfn_limit (~0ul >> PAGE_SHIFT) #endif extern phys_addr_t arm_lowmem_limit; @@ -90,3 +95,5 @@ extern phys_addr_t arm_lowmem_limit; void __init bootmem_init(void); void arm_mm_memblock_reserve(void); void dma_contiguous_remap(void); + +unsigned long __clear_cr(unsigned long mask); diff --git a/arch/arm/mm/mmap.c b/arch/arm/mm/mmap.c index 0c6356255fe..5e85ed37136 100644 --- a/arch/arm/mm/mmap.c +++ b/arch/arm/mm/mmap.c @@ -146,7 +146,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, info.flags = VM_UNMAPPED_AREA_TOPDOWN; info.length = len; - info.low_limit = PAGE_SIZE; + info.low_limit = FIRST_USER_ADDRESS; info.high_limit = mm->mmap_base; info.align_mask = do_align ? (PAGE_MASK & (SHMLBA - 1)) : 0; info.align_offset = pgoff << PAGE_SHIFT; @@ -202,13 +202,11 @@ int valid_phys_addr_range(phys_addr_t addr, size_t size) } /* - * We don't use supersection mappings for mmap() on /dev/mem, which - * means that we can't map the memory area above the 4G barrier into - * userspace. + * Do not allow /dev/mem mappings beyond the supported physical range. */ int valid_mmap_phys_addr_range(unsigned long pfn, size_t size) { - return !(pfn + (size >> PAGE_SHIFT) > 0x00100000); + return (pfn + (size >> PAGE_SHIFT)) <= (1 + (PHYS_MASK >> PAGE_SHIFT)); } #ifdef CONFIG_STRICT_DEVMEM diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c index 53cdbd39ec8..6e3ba8d112a 100644 --- a/arch/arm/mm/mmu.c +++ b/arch/arm/mm/mmu.c @@ -22,16 +22,20 @@ #include <asm/cputype.h> #include <asm/sections.h> #include <asm/cachetype.h> +#include <asm/sections.h> #include <asm/setup.h> #include <asm/smp_plat.h> #include <asm/tlb.h> #include <asm/highmem.h> #include <asm/system_info.h> #include <asm/traps.h> +#include <asm/procinfo.h> +#include <asm/memory.h> #include <asm/mach/arch.h> #include <asm/mach/map.h> #include <asm/mach/pci.h> +#include <asm/fixmap.h> #include "mm.h" #include "tcm.h" @@ -114,28 +118,54 @@ static struct cachepolicy cache_policies[] __initdata = { }; #ifdef CONFIG_CPU_CP15 +static unsigned long initial_pmd_value __initdata = 0; + /* - * These are useful for identifying cache coherency - * problems by allowing the cache or the cache and - * writebuffer to be turned off. (Note: the write - * buffer should not be on and the cache off). + * Initialise the cache_policy variable with the initial state specified + * via the "pmd" value. This is used to ensure that on ARMv6 and later, + * the C code sets the page tables up with the same policy as the head + * assembly code, which avoids an illegal state where the TLBs can get + * confused. See comments in early_cachepolicy() for more information. */ -static int __init early_cachepolicy(char *p) +void __init init_default_cache_policy(unsigned long pmd) { int i; + initial_pmd_value = pmd; + + pmd &= PMD_SECT_TEX(1) | PMD_SECT_BUFFERABLE | PMD_SECT_CACHEABLE; + + for (i = 0; i < ARRAY_SIZE(cache_policies); i++) + if (cache_policies[i].pmd == pmd) { + cachepolicy = i; + break; + } + + if (i == ARRAY_SIZE(cache_policies)) + pr_err("ERROR: could not find cache policy\n"); +} + +/* + * These are useful for identifying cache coherency problems by allowing + * the cache or the cache and writebuffer to be turned off. (Note: the + * write buffer should not be on and the cache off). + */ +static int __init early_cachepolicy(char *p) +{ + int i, selected = -1; + for (i = 0; i < ARRAY_SIZE(cache_policies); i++) { int len = strlen(cache_policies[i].policy); if (memcmp(p, cache_policies[i].policy, len) == 0) { - cachepolicy = i; - cr_alignment &= ~cache_policies[i].cr_mask; - cr_no_alignment &= ~cache_policies[i].cr_mask; + selected = i; break; } } - if (i == ARRAY_SIZE(cache_policies)) - printk(KERN_ERR "ERROR: unknown or unsupported cache policy\n"); + + if (selected == -1) + pr_err("ERROR: unknown or unsupported cache policy\n"); + /* * This restriction is partly to do with the way we boot; it is * unpredictable to have memory mapped using two different sets of @@ -143,12 +173,18 @@ static int __init early_cachepolicy(char *p) * change these attributes once the initial assembly has setup the * page tables. */ - if (cpu_architecture() >= CPU_ARCH_ARMv6) { - printk(KERN_WARNING "Only cachepolicy=writeback supported on ARMv6 and later\n"); - cachepolicy = CPOLICY_WRITEBACK; + if (cpu_architecture() >= CPU_ARCH_ARMv6 && selected != cachepolicy) { + pr_warn("Only cachepolicy=%s supported on ARMv6 and later\n", + cache_policies[cachepolicy].policy); + return 0; + } + + if (selected != cachepolicy) { + unsigned long cr = __clear_cr(cache_policies[selected].cr_mask); + cachepolicy = selected; + flush_cache_all(); + set_cr(cr); } - flush_cache_all(); - set_cr(cr_alignment); return 0; } early_param("cachepolicy", early_cachepolicy); @@ -183,35 +219,6 @@ static int __init early_ecc(char *p) early_param("ecc", early_ecc); #endif -static int __init noalign_setup(char *__unused) -{ - cr_alignment &= ~CR_A; - cr_no_alignment &= ~CR_A; - set_cr(cr_alignment); - return 1; -} -__setup("noalign", noalign_setup); - -#ifndef CONFIG_SMP -void adjust_cr(unsigned long mask, unsigned long set) -{ - unsigned long flags; - - mask &= ~CR_A; - - set &= mask; - - local_irq_save(flags); - - cr_no_alignment = (cr_no_alignment & ~mask) | set; - cr_alignment = (cr_alignment & ~mask) | set; - - set_cr((get_cr() & ~mask) | set); - - local_irq_restore(flags); -} -#endif - #else /* ifdef CONFIG_CPU_CP15 */ static int __init early_cachepolicy(char *p) @@ -229,12 +236,16 @@ __setup("noalign", noalign_setup); #endif /* ifdef CONFIG_CPU_CP15 / else */ #define PROT_PTE_DEVICE L_PTE_PRESENT|L_PTE_YOUNG|L_PTE_DIRTY|L_PTE_XN +#define PROT_PTE_S2_DEVICE PROT_PTE_DEVICE #define PROT_SECT_DEVICE PMD_TYPE_SECT|PMD_SECT_AP_WRITE static struct mem_type mem_types[] = { [MT_DEVICE] = { /* Strongly ordered / ARMv6 shared device */ .prot_pte = PROT_PTE_DEVICE | L_PTE_MT_DEV_SHARED | L_PTE_SHARED, + .prot_pte_s2 = s2_policy(PROT_PTE_S2_DEVICE) | + s2_policy(L_PTE_S2_MT_DEV_SHARED) | + L_PTE_SHARED, .prot_l1 = PMD_TYPE_TABLE, .prot_sect = PROT_SECT_DEVICE | PMD_SECT_S, .domain = DOMAIN_IO, @@ -285,36 +296,43 @@ static struct mem_type mem_types[] = { .prot_l1 = PMD_TYPE_TABLE, .domain = DOMAIN_USER, }, - [MT_MEMORY] = { + [MT_MEMORY_RWX] = { .prot_pte = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY, .prot_l1 = PMD_TYPE_TABLE, .prot_sect = PMD_TYPE_SECT | PMD_SECT_AP_WRITE, .domain = DOMAIN_KERNEL, }, + [MT_MEMORY_RW] = { + .prot_pte = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY | + L_PTE_XN, + .prot_l1 = PMD_TYPE_TABLE, + .prot_sect = PMD_TYPE_SECT | PMD_SECT_AP_WRITE, + .domain = DOMAIN_KERNEL, + }, [MT_ROM] = { .prot_sect = PMD_TYPE_SECT, .domain = DOMAIN_KERNEL, }, - [MT_MEMORY_NONCACHED] = { + [MT_MEMORY_RWX_NONCACHED] = { .prot_pte = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY | L_PTE_MT_BUFFERABLE, .prot_l1 = PMD_TYPE_TABLE, .prot_sect = PMD_TYPE_SECT | PMD_SECT_AP_WRITE, .domain = DOMAIN_KERNEL, }, - [MT_MEMORY_DTCM] = { + [MT_MEMORY_RW_DTCM] = { .prot_pte = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY | L_PTE_XN, .prot_l1 = PMD_TYPE_TABLE, .prot_sect = PMD_TYPE_SECT | PMD_SECT_XN, .domain = DOMAIN_KERNEL, }, - [MT_MEMORY_ITCM] = { + [MT_MEMORY_RWX_ITCM] = { .prot_pte = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY, .prot_l1 = PMD_TYPE_TABLE, .domain = DOMAIN_KERNEL, }, - [MT_MEMORY_SO] = { + [MT_MEMORY_RW_SO] = { .prot_pte = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY | L_PTE_MT_UNCACHED | L_PTE_XN, .prot_l1 = PMD_TYPE_TABLE, @@ -323,7 +341,8 @@ static struct mem_type mem_types[] = { .domain = DOMAIN_KERNEL, }, [MT_MEMORY_DMA_READY] = { - .prot_pte = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY, + .prot_pte = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY | + L_PTE_XN, .prot_l1 = PMD_TYPE_TABLE, .domain = DOMAIN_KERNEL, }, @@ -335,6 +354,44 @@ const struct mem_type *get_mem_type(unsigned int type) } EXPORT_SYMBOL(get_mem_type); +#define PTE_SET_FN(_name, pteop) \ +static int pte_set_##_name(pte_t *ptep, pgtable_t token, unsigned long addr, \ + void *data) \ +{ \ + pte_t pte = pteop(*ptep); \ +\ + set_pte_ext(ptep, pte, 0); \ + return 0; \ +} \ + +#define SET_MEMORY_FN(_name, callback) \ +int set_memory_##_name(unsigned long addr, int numpages) \ +{ \ + unsigned long start = addr; \ + unsigned long size = PAGE_SIZE*numpages; \ + unsigned end = start + size; \ +\ + if (start < MODULES_VADDR || start >= MODULES_END) \ + return -EINVAL;\ +\ + if (end < MODULES_VADDR || end >= MODULES_END) \ + return -EINVAL; \ +\ + apply_to_page_range(&init_mm, start, size, callback, NULL); \ + flush_tlb_kernel_range(start, end); \ + return 0;\ +} + +PTE_SET_FN(ro, pte_wrprotect) +PTE_SET_FN(rw, pte_mkwrite) +PTE_SET_FN(x, pte_mkexec) +PTE_SET_FN(nx, pte_mknexec) + +SET_MEMORY_FN(ro, pte_set_ro) +SET_MEMORY_FN(rw, pte_set_rw) +SET_MEMORY_FN(x, pte_set_x) +SET_MEMORY_FN(nx, pte_set_nx) + /* * Adjust the PMD section entries according to the CPU in use. */ @@ -361,8 +418,17 @@ static void __init build_mem_type_table(void) cachepolicy = CPOLICY_WRITEBACK; ecc_mask = 0; } - if (is_smp()) - cachepolicy = CPOLICY_WRITEALLOC; + + if (is_smp()) { + if (cachepolicy != CPOLICY_WRITEALLOC) { + pr_warn("Forcing write-allocate cache policy for SMP\n"); + cachepolicy = CPOLICY_WRITEALLOC; + } + if (!(initial_pmd_value & PMD_SECT_S)) { + pr_warn("Forcing shared mappings for SMP\n"); + initial_pmd_value |= PMD_SECT_S; + } + } /* * Strip out features not present on earlier architectures. @@ -408,6 +474,9 @@ static void __init build_mem_type_table(void) mem_types[MT_DEVICE_NONSHARED].prot_sect |= PMD_SECT_XN; mem_types[MT_DEVICE_CACHED].prot_sect |= PMD_SECT_XN; mem_types[MT_DEVICE_WC].prot_sect |= PMD_SECT_XN; + + /* Also setup NX memory mapping */ + mem_types[MT_MEMORY_RW].prot_sect |= PMD_SECT_XN; } if (cpu_arch >= CPU_ARCH_ARMv7 && (cr & CR_TRE)) { /* @@ -456,7 +525,18 @@ static void __init build_mem_type_table(void) cp = &cache_policies[cachepolicy]; vecs_pgprot = kern_pgprot = user_pgprot = cp->pte; s2_pgprot = cp->pte_s2; - hyp_device_pgprot = s2_device_pgprot = mem_types[MT_DEVICE].prot_pte; + hyp_device_pgprot = mem_types[MT_DEVICE].prot_pte; + s2_device_pgprot = mem_types[MT_DEVICE].prot_pte_s2; + + /* + * We don't use domains on ARMv6 (since this causes problems with + * v6/v7 kernels), so we must use a separate memory type for user + * r/o, kernel r/w to map the vectors page. + */ +#ifndef CONFIG_ARM_LPAE + if (cpu_arch == CPU_ARCH_ARMv6) + vecs_pgprot |= L_PTE_MT_VECTORS; +#endif /* * ARMv6 and above have extended page tables. @@ -472,11 +552,12 @@ static void __init build_mem_type_table(void) mem_types[MT_CACHECLEAN].prot_sect |= PMD_SECT_APX|PMD_SECT_AP_WRITE; #endif - if (is_smp()) { - /* - * Mark memory with the "shared" attribute - * for SMP systems - */ + /* + * If the initial page tables were created with the S bit + * set, then we need to do the same here for the same + * reasons given in early_cachepolicy(). + */ + if (initial_pmd_value & PMD_SECT_S) { user_pgprot |= L_PTE_SHARED; kern_pgprot |= L_PTE_SHARED; vecs_pgprot |= L_PTE_SHARED; @@ -485,11 +566,13 @@ static void __init build_mem_type_table(void) mem_types[MT_DEVICE_WC].prot_pte |= L_PTE_SHARED; mem_types[MT_DEVICE_CACHED].prot_sect |= PMD_SECT_S; mem_types[MT_DEVICE_CACHED].prot_pte |= L_PTE_SHARED; - mem_types[MT_MEMORY].prot_sect |= PMD_SECT_S; - mem_types[MT_MEMORY].prot_pte |= L_PTE_SHARED; + mem_types[MT_MEMORY_RWX].prot_sect |= PMD_SECT_S; + mem_types[MT_MEMORY_RWX].prot_pte |= L_PTE_SHARED; + mem_types[MT_MEMORY_RW].prot_sect |= PMD_SECT_S; + mem_types[MT_MEMORY_RW].prot_pte |= L_PTE_SHARED; mem_types[MT_MEMORY_DMA_READY].prot_pte |= L_PTE_SHARED; - mem_types[MT_MEMORY_NONCACHED].prot_sect |= PMD_SECT_S; - mem_types[MT_MEMORY_NONCACHED].prot_pte |= L_PTE_SHARED; + mem_types[MT_MEMORY_RWX_NONCACHED].prot_sect |= PMD_SECT_S; + mem_types[MT_MEMORY_RWX_NONCACHED].prot_pte |= L_PTE_SHARED; } } @@ -500,15 +583,15 @@ static void __init build_mem_type_table(void) if (cpu_arch >= CPU_ARCH_ARMv6) { if (cpu_arch >= CPU_ARCH_ARMv7 && (cr & CR_TRE)) { /* Non-cacheable Normal is XCB = 001 */ - mem_types[MT_MEMORY_NONCACHED].prot_sect |= + mem_types[MT_MEMORY_RWX_NONCACHED].prot_sect |= PMD_SECT_BUFFERED; } else { /* For both ARMv6 and non-TEX-remapping ARMv7 */ - mem_types[MT_MEMORY_NONCACHED].prot_sect |= + mem_types[MT_MEMORY_RWX_NONCACHED].prot_sect |= PMD_SECT_TEX(1); } } else { - mem_types[MT_MEMORY_NONCACHED].prot_sect |= PMD_SECT_BUFFERABLE; + mem_types[MT_MEMORY_RWX_NONCACHED].prot_sect |= PMD_SECT_BUFFERABLE; } #ifdef CONFIG_ARM_LPAE @@ -541,10 +624,12 @@ static void __init build_mem_type_table(void) mem_types[MT_LOW_VECTORS].prot_l1 |= ecc_mask; mem_types[MT_HIGH_VECTORS].prot_l1 |= ecc_mask; - mem_types[MT_MEMORY].prot_sect |= ecc_mask | cp->pmd; - mem_types[MT_MEMORY].prot_pte |= kern_pgprot; + mem_types[MT_MEMORY_RWX].prot_sect |= ecc_mask | cp->pmd; + mem_types[MT_MEMORY_RWX].prot_pte |= kern_pgprot; + mem_types[MT_MEMORY_RW].prot_sect |= ecc_mask | cp->pmd; + mem_types[MT_MEMORY_RW].prot_pte |= kern_pgprot; mem_types[MT_MEMORY_DMA_READY].prot_pte |= kern_pgprot; - mem_types[MT_MEMORY_NONCACHED].prot_sect |= ecc_mask; + mem_types[MT_MEMORY_RWX_NONCACHED].prot_sect |= ecc_mask; mem_types[MT_ROM].prot_sect |= cp->pmd; switch (cp->pmd) { @@ -556,8 +641,8 @@ static void __init build_mem_type_table(void) mem_types[MT_CACHECLEAN].prot_sect |= PMD_SECT_WB; break; } - printk("Memory policy: ECC %sabled, Data cache %s\n", - ecc_mask ? "en" : "dis", cp->policy); + pr_info("Memory policy: %sData cache %s\n", + ecc_mask ? "ECC enabled, " : "", cp->policy); for (i = 0; i < ARRAY_SIZE(mem_types); i++) { struct mem_type *t = &mem_types[i]; @@ -990,74 +1075,47 @@ phys_addr_t arm_lowmem_limit __initdata = 0; void __init sanity_check_meminfo(void) { phys_addr_t memblock_limit = 0; - int i, j, highmem = 0; + int highmem = 0; phys_addr_t vmalloc_limit = __pa(vmalloc_min - 1) + 1; + struct memblock_region *reg; - for (i = 0, j = 0; i < meminfo.nr_banks; i++) { - struct membank *bank = &meminfo.bank[j]; - phys_addr_t size_limit; - - *bank = meminfo.bank[i]; - size_limit = bank->size; + for_each_memblock(memory, reg) { + phys_addr_t block_start = reg->base; + phys_addr_t block_end = reg->base + reg->size; + phys_addr_t size_limit = reg->size; - if (bank->start >= vmalloc_limit) + if (reg->base >= vmalloc_limit) highmem = 1; else - size_limit = vmalloc_limit - bank->start; + size_limit = vmalloc_limit - reg->base; - bank->highmem = highmem; -#ifdef CONFIG_HIGHMEM - /* - * Split those memory banks which are partially overlapping - * the vmalloc area greatly simplifying things later. - */ - if (!highmem && bank->size > size_limit) { - if (meminfo.nr_banks >= NR_BANKS) { - printk(KERN_CRIT "NR_BANKS too low, " - "ignoring high memory\n"); - } else { - memmove(bank + 1, bank, - (meminfo.nr_banks - i) * sizeof(*bank)); - meminfo.nr_banks++; - i++; - bank[1].size -= size_limit; - bank[1].start = vmalloc_limit; - bank[1].highmem = highmem = 1; - j++; + if (!IS_ENABLED(CONFIG_HIGHMEM) || cache_is_vipt_aliasing()) { + + if (highmem) { + pr_notice("Ignoring RAM at %pa-%pa (!CONFIG_HIGHMEM)\n", + &block_start, &block_end); + memblock_remove(reg->base, reg->size); + continue; } - bank->size = size_limit; - } -#else - /* - * Highmem banks not allowed with !CONFIG_HIGHMEM. - */ - if (highmem) { - printk(KERN_NOTICE "Ignoring RAM at %.8llx-%.8llx " - "(!CONFIG_HIGHMEM).\n", - (unsigned long long)bank->start, - (unsigned long long)bank->start + bank->size - 1); - continue; - } - /* - * Check whether this memory bank would partially overlap - * the vmalloc area. - */ - if (bank->size > size_limit) { - printk(KERN_NOTICE "Truncating RAM at %.8llx-%.8llx " - "to -%.8llx (vmalloc region overlap).\n", - (unsigned long long)bank->start, - (unsigned long long)bank->start + bank->size - 1, - (unsigned long long)bank->start + size_limit - 1); - bank->size = size_limit; + if (reg->size > size_limit) { + phys_addr_t overlap_size = reg->size - size_limit; + + pr_notice("Truncating RAM at %pa-%pa to -%pa", + &block_start, &block_end, &vmalloc_limit); + memblock_remove(vmalloc_limit, overlap_size); + block_end = vmalloc_limit; + } } -#endif - if (!bank->highmem) { - phys_addr_t bank_end = bank->start + bank->size; - if (bank_end > arm_lowmem_limit) - arm_lowmem_limit = bank_end; + if (!highmem) { + if (block_end > arm_lowmem_limit) { + if (reg->size > size_limit) + arm_lowmem_limit = vmalloc_limit; + else + arm_lowmem_limit = block_end; + } /* * Find the first non-section-aligned page, and point @@ -1073,35 +1131,15 @@ void __init sanity_check_meminfo(void) * occurs before any free memory is mapped. */ if (!memblock_limit) { - if (!IS_ALIGNED(bank->start, SECTION_SIZE)) - memblock_limit = bank->start; - else if (!IS_ALIGNED(bank_end, SECTION_SIZE)) - memblock_limit = bank_end; + if (!IS_ALIGNED(block_start, SECTION_SIZE)) + memblock_limit = block_start; + else if (!IS_ALIGNED(block_end, SECTION_SIZE)) + memblock_limit = arm_lowmem_limit; } - } - j++; - } -#ifdef CONFIG_HIGHMEM - if (highmem) { - const char *reason = NULL; - if (cache_is_vipt_aliasing()) { - /* - * Interactions between kmap and other mappings - * make highmem support with aliasing VIPT caches - * rather difficult. - */ - reason = "with VIPT aliasing cache"; - } - if (reason) { - printk(KERN_CRIT "HIGHMEM is not supported %s, ignoring high memory\n", - reason); - while (j > 0 && meminfo.bank[j - 1].highmem) - j--; } } -#endif - meminfo.nr_banks = j; + high_memory = __va(arm_lowmem_limit - 1) + 1; /* @@ -1186,7 +1224,7 @@ void __init arm_mm_memblock_reserve(void) * called function. This means you can't use any function or debugging * method which may touch any device, otherwise the kernel _will_ crash. */ -static void __init devicemaps_init(struct machine_desc *mdesc) +static void __init devicemaps_init(const struct machine_desc *mdesc) { struct map_desc map; unsigned long addr; @@ -1288,12 +1326,17 @@ static void __init kmap_init(void) #ifdef CONFIG_HIGHMEM pkmap_page_table = early_pte_alloc(pmd_off_k(PKMAP_BASE), PKMAP_BASE, _PAGE_KERNEL_TABLE); + + fixmap_page_table = early_pte_alloc(pmd_off_k(FIXADDR_START), + FIXADDR_START, _PAGE_KERNEL_TABLE); #endif } static void __init map_lowmem(void) { struct memblock_region *reg; + unsigned long kernel_x_start = round_down(__pa(_stext), SECTION_SIZE); + unsigned long kernel_x_end = round_up(__pa(__init_end), SECTION_SIZE); /* Map all the lowmem memory banks. */ for_each_memblock(memory, reg) { @@ -1306,20 +1349,128 @@ static void __init map_lowmem(void) if (start >= end) break; - map.pfn = __phys_to_pfn(start); - map.virtual = __phys_to_virt(start); - map.length = end - start; - map.type = MT_MEMORY; + if (end < kernel_x_start || start >= kernel_x_end) { + map.pfn = __phys_to_pfn(start); + map.virtual = __phys_to_virt(start); + map.length = end - start; + map.type = MT_MEMORY_RWX; - create_mapping(&map); + create_mapping(&map); + } else { + /* This better cover the entire kernel */ + if (start < kernel_x_start) { + map.pfn = __phys_to_pfn(start); + map.virtual = __phys_to_virt(start); + map.length = kernel_x_start - start; + map.type = MT_MEMORY_RW; + + create_mapping(&map); + } + + map.pfn = __phys_to_pfn(kernel_x_start); + map.virtual = __phys_to_virt(kernel_x_start); + map.length = kernel_x_end - kernel_x_start; + map.type = MT_MEMORY_RWX; + + create_mapping(&map); + + if (kernel_x_end < end) { + map.pfn = __phys_to_pfn(kernel_x_end); + map.virtual = __phys_to_virt(kernel_x_end); + map.length = end - kernel_x_end; + map.type = MT_MEMORY_RW; + + create_mapping(&map); + } + } } } +#ifdef CONFIG_ARM_LPAE +/* + * early_paging_init() recreates boot time page table setup, allowing machines + * to switch over to a high (>4G) address space on LPAE systems + */ +void __init early_paging_init(const struct machine_desc *mdesc, + struct proc_info_list *procinfo) +{ + pmdval_t pmdprot = procinfo->__cpu_mm_mmu_flags; + unsigned long map_start, map_end; + pgd_t *pgd0, *pgdk; + pud_t *pud0, *pudk, *pud_start; + pmd_t *pmd0, *pmdk; + phys_addr_t phys; + int i; + + if (!(mdesc->init_meminfo)) + return; + + /* remap kernel code and data */ + map_start = init_mm.start_code & PMD_MASK; + map_end = ALIGN(init_mm.brk, PMD_SIZE); + + /* get a handle on things... */ + pgd0 = pgd_offset_k(0); + pud_start = pud0 = pud_offset(pgd0, 0); + pmd0 = pmd_offset(pud0, 0); + + pgdk = pgd_offset_k(map_start); + pudk = pud_offset(pgdk, map_start); + pmdk = pmd_offset(pudk, map_start); + + mdesc->init_meminfo(); + + /* Run the patch stub to update the constants */ + fixup_pv_table(&__pv_table_begin, + (&__pv_table_end - &__pv_table_begin) << 2); + + /* + * Cache cleaning operations for self-modifying code + * We should clean the entries by MVA but running a + * for loop over every pv_table entry pointer would + * just complicate the code. + */ + flush_cache_louis(); + dsb(ishst); + isb(); + + /* remap level 1 table */ + for (i = 0; i < PTRS_PER_PGD; pud0++, i++) { + set_pud(pud0, + __pud(__pa(pmd0) | PMD_TYPE_TABLE | L_PGD_SWAPPER)); + pmd0 += PTRS_PER_PMD; + } + + /* remap pmds for kernel mapping */ + phys = __pa(map_start); + do { + *pmdk++ = __pmd(phys | pmdprot); + phys += PMD_SIZE; + } while (phys < map_end); + + flush_cache_all(); + cpu_switch_mm(pgd0, &init_mm); + cpu_set_ttbr(1, __pa(pgd0) + TTBR1_OFFSET); + local_flush_bp_all(); + local_flush_tlb_all(); +} + +#else + +void __init early_paging_init(const struct machine_desc *mdesc, + struct proc_info_list *procinfo) +{ + if (mdesc->init_meminfo) + mdesc->init_meminfo(); +} + +#endif + /* * paging_init() sets up the page tables, initialises the zone memory * maps, and sets up the zero page, bad page and bad page tables. */ -void __init paging_init(struct machine_desc *mdesc) +void __init paging_init(const struct machine_desc *mdesc) { void *zero_page; diff --git a/arch/arm/mm/nommu.c b/arch/arm/mm/nommu.c index 1fa50100ab6..a014dfacd5c 100644 --- a/arch/arm/mm/nommu.c +++ b/arch/arm/mm/nommu.c @@ -18,6 +18,7 @@ #include <asm/mach/arch.h> #include <asm/cputype.h> #include <asm/mpu.h> +#include <asm/procinfo.h> #include "mm.h" @@ -87,30 +88,35 @@ static unsigned long irbar_read(void) void __init sanity_check_meminfo_mpu(void) { int i; - struct membank *bank = meminfo.bank; phys_addr_t phys_offset = PHYS_OFFSET; phys_addr_t aligned_region_size, specified_mem_size, rounded_mem_size; - - /* Initially only use memory continuous from PHYS_OFFSET */ - if (bank_phys_start(&bank[0]) != phys_offset) - panic("First memory bank must be contiguous from PHYS_OFFSET"); - - /* Banks have already been sorted by start address */ - for (i = 1; i < meminfo.nr_banks; i++) { - if (bank[i].start <= bank_phys_end(&bank[0]) && - bank_phys_end(&bank[i]) > bank_phys_end(&bank[0])) { - bank[0].size = bank_phys_end(&bank[i]) - bank[0].start; + struct memblock_region *reg; + bool first = true; + phys_addr_t mem_start; + phys_addr_t mem_end; + + for_each_memblock(memory, reg) { + if (first) { + /* + * Initially only use memory continuous from + * PHYS_OFFSET */ + if (reg->base != phys_offset) + panic("First memory bank must be contiguous from PHYS_OFFSET"); + + mem_start = reg->base; + mem_end = reg->base + reg->size; + specified_mem_size = reg->size; + first = false; } else { - pr_notice("Ignoring RAM after 0x%.8lx. " - "First non-contiguous (ignored) bank start: 0x%.8lx\n", - (unsigned long)bank_phys_end(&bank[0]), - (unsigned long)bank_phys_start(&bank[i])); - break; + /* + * memblock auto merges contiguous blocks, remove + * all blocks afterwards + */ + pr_notice("Ignoring RAM after %pa, memory at %pa ignored\n", + &mem_start, ®->base); + memblock_remove(reg->base, reg->size); } } - /* All contiguous banks are now merged in to the first bank */ - meminfo.nr_banks = 1; - specified_mem_size = bank[0].size; /* * MPU has curious alignment requirements: Size must be power of 2, and @@ -127,23 +133,24 @@ void __init sanity_check_meminfo_mpu(void) */ aligned_region_size = (phys_offset - 1) ^ (phys_offset); /* Find the max power-of-two sized region that fits inside our bank */ - rounded_mem_size = (1 << __fls(bank[0].size)) - 1; + rounded_mem_size = (1 << __fls(specified_mem_size)) - 1; /* The actual region size is the smaller of the two */ aligned_region_size = aligned_region_size < rounded_mem_size ? aligned_region_size + 1 : rounded_mem_size + 1; - if (aligned_region_size != specified_mem_size) - pr_warn("Truncating memory from 0x%.8lx to 0x%.8lx (MPU region constraints)", - (unsigned long)specified_mem_size, - (unsigned long)aligned_region_size); + if (aligned_region_size != specified_mem_size) { + pr_warn("Truncating memory from %pa to %pa (MPU region constraints)", + &specified_mem_size, &aligned_region_size); + memblock_remove(mem_start + aligned_region_size, + specified_mem_size - aligned_round_size); - meminfo.bank[0].size = aligned_region_size; - pr_debug("MPU Region from 0x%.8lx size 0x%.8lx (end 0x%.8lx))\n", - (unsigned long)phys_offset, - (unsigned long)aligned_region_size, - (unsigned long)bank_phys_end(&bank[0])); + mem_end = mem_start + aligned_region_size; + } + + pr_debug("MPU Region from %pa size %pa (end %pa))\n", + &phys_offset, &aligned_region_size, &mem_end); } @@ -291,15 +298,25 @@ void __init sanity_check_meminfo(void) { phys_addr_t end; sanity_check_meminfo_mpu(); - end = bank_phys_end(&meminfo.bank[meminfo.nr_banks - 1]); + end = memblock_end_of_DRAM(); high_memory = __va(end - 1) + 1; + memblock_set_current_limit(end); +} + +/* + * early_paging_init() recreates boot time page table setup, allowing machines + * to switch over to a high (>4G) address space on LPAE systems + */ +void __init early_paging_init(const struct machine_desc *mdesc, + struct proc_info_list *procinfo) +{ } /* * paging_init() sets up the page tables, initialises the zone memory * maps, and sets up the zero page, bad page and bad page tables. */ -void __init paging_init(struct machine_desc *mdesc) +void __init paging_init(const struct machine_desc *mdesc) { early_trap_init((void *)CONFIG_VECTORS_BASE); mpu_setup(); diff --git a/arch/arm/mm/pgd.c b/arch/arm/mm/pgd.c index 0acb089d0f7..249379535be 100644 --- a/arch/arm/mm/pgd.c +++ b/arch/arm/mm/pgd.c @@ -23,7 +23,7 @@ #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_alloc() (pgd_t *)__get_free_pages(GFP_KERNEL | __GFP_REPEAT, 2) #define __pgd_free(pgd) free_pages((unsigned long)pgd, 2) #endif @@ -87,7 +87,8 @@ pgd_t *pgd_alloc(struct mm_struct *mm) init_pud = pud_offset(init_pgd, 0); init_pmd = pmd_offset(init_pud, 0); init_pte = pte_offset_map(init_pmd, 0); - set_pte_ext(new_pte, *init_pte, 0); + set_pte_ext(new_pte + 0, init_pte[0], 0); + set_pte_ext(new_pte + 1, init_pte[1], 0); pte_unmap(init_pte); pte_unmap(new_pte); } diff --git a/arch/arm/mm/proc-arm925.S b/arch/arm/mm/proc-arm925.S index 97448c3acf3..ba0d58e1a2a 100644 --- a/arch/arm/mm/proc-arm925.S +++ b/arch/arm/mm/proc-arm925.S @@ -502,6 +502,7 @@ __\name\()_proc_info: .long \cpu_val .long \cpu_mask .long PMD_TYPE_SECT | \ + PMD_SECT_CACHEABLE | \ PMD_BIT4 | \ PMD_SECT_AP_WRITE | \ PMD_SECT_AP_READ diff --git a/arch/arm/mm/proc-feroceon.S b/arch/arm/mm/proc-feroceon.S index d5146b98c8d..db79b62c92f 100644 --- a/arch/arm/mm/proc-feroceon.S +++ b/arch/arm/mm/proc-feroceon.S @@ -514,6 +514,32 @@ ENTRY(cpu_feroceon_set_pte_ext) #endif mov pc, lr +/* Suspend/resume support: taken from arch/arm/mm/proc-arm926.S */ +.globl cpu_feroceon_suspend_size +.equ cpu_feroceon_suspend_size, 4 * 3 +#ifdef CONFIG_ARM_CPU_SUSPEND +ENTRY(cpu_feroceon_do_suspend) + 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, c1, c0, 0 @ Control register + stmia r0, {r4 - r6} + ldmfd sp!, {r4 - r6, pc} +ENDPROC(cpu_feroceon_do_suspend) + +ENTRY(cpu_feroceon_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 - r6} + mcr p15, 0, r4, c13, c0, 0 @ PID + mcr p15, 0, r5, c3, c0, 0 @ Domain ID + mcr p15, 0, r1, c2, c0, 0 @ TTB address + mov r0, r6 @ control register + b cpu_resume_mmu +ENDPROC(cpu_feroceon_do_resume) +#endif + .type __feroceon_setup, #function __feroceon_setup: mov r0, #0 diff --git a/arch/arm/mm/proc-macros.S b/arch/arm/mm/proc-macros.S index e3c48a3fe06..ee1d8059395 100644 --- a/arch/arm/mm/proc-macros.S +++ b/arch/arm/mm/proc-macros.S @@ -112,13 +112,9 @@ * 100x 1 0 1 r/o no acc * 10x0 1 0 1 r/o no acc * 1011 0 0 1 r/w no acc - * 110x 0 1 0 r/w r/o - * 11x0 0 1 0 r/w r/o - * 1111 0 1 1 r/w r/w - * - * If !CONFIG_CPU_USE_DOMAINS, the following permissions are changed: * 110x 1 1 1 r/o r/o * 11x0 1 1 1 r/o r/o + * 1111 0 1 1 r/w r/w */ .macro armv6_mt_table pfx \pfx\()_mt_table: @@ -137,7 +133,7 @@ .long PTE_EXT_TEX(2) @ L_PTE_MT_DEV_NONSHARED .long 0x00 @ unused .long 0x00 @ unused - .long 0x00 @ unused + .long PTE_CACHEABLE | PTE_BUFFERABLE | PTE_EXT_APX @ L_PTE_MT_VECTORS .endm .macro armv6_set_pte_ext pfx @@ -158,24 +154,21 @@ 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 + + @ user read-only -> kernel read-only + bicne r3, r3, #PTE_EXT_AP0 tst r1, #L_PTE_XN orrne r3, r3, #PTE_EXT_XN - orr r3, r3, r2 + eor r3, r3, r2 tst r1, #L_PTE_YOUNG tstne r1, #L_PTE_PRESENT moveq r3, #0 -#ifndef CONFIG_CPU_USE_DOMAINS tstne r1, #L_PTE_NONE movne r3, #0 -#endif str r3, [r0] mcr p15, 0, r0, c7, c10, 1 @ flush_pte diff --git a/arch/arm/mm/proc-v6.S b/arch/arm/mm/proc-v6.S index 1128064fddc..32b3558321c 100644 --- a/arch/arm/mm/proc-v6.S +++ b/arch/arm/mm/proc-v6.S @@ -208,7 +208,6 @@ __v6_setup: mcr p15, 0, r0, c7, c14, 0 @ clean+invalidate D cache mcr p15, 0, r0, c7, c5, 0 @ invalidate I cache mcr p15, 0, r0, c7, c15, 0 @ clean+invalidate cache - mcr p15, 0, r0, c7, c10, 4 @ drain write buffer #ifdef CONFIG_MMU mcr p15, 0, r0, c8, c7, 0 @ invalidate I + D TLBs mcr p15, 0, r0, c2, c0, 2 @ TTB control register @@ -218,11 +217,11 @@ __v6_setup: ALT_UP(orr r8, r8, #TTB_FLAGS_UP) mcr p15, 0, r8, c2, c0, 1 @ load TTB1 #endif /* CONFIG_MMU */ + mcr p15, 0, r0, c7, c10, 4 @ drain write buffer and + @ complete invalidations adr r5, v6_crval ldmia r5, {r5, r6} -#ifdef CONFIG_CPU_ENDIAN_BE8 - orr r6, r6, #1 << 25 @ big-endian page tables -#endif + ARM_BE8(orr r6, r6, #1 << 25) @ big-endian page tables mrc p15, 0, r0, c1, c0, 0 @ read control register bic r0, r0, r5 @ clear bits them orr r0, r0, r6 @ set them diff --git a/arch/arm/mm/proc-v7-2level.S b/arch/arm/mm/proc-v7-2level.S index bdd3be4be77..1f52915f2b2 100644 --- a/arch/arm/mm/proc-v7-2level.S +++ b/arch/arm/mm/proc-v7-2level.S @@ -90,21 +90,14 @@ ENTRY(cpu_v7_set_pte_ext) 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_VALID -#ifndef CONFIG_CPU_USE_DOMAINS eorne r1, r1, #L_PTE_NONE tstne r1, #L_PTE_NONE -#endif moveq r3, #0 ARM( str r3, [r0, #2048]! ) diff --git a/arch/arm/mm/proc-v7-3level.S b/arch/arm/mm/proc-v7-3level.S index 01a719e18bb..22e3ad63500 100644 --- a/arch/arm/mm/proc-v7-3level.S +++ b/arch/arm/mm/proc-v7-3level.S @@ -64,6 +64,14 @@ ENTRY(cpu_v7_switch_mm) mov pc, lr ENDPROC(cpu_v7_switch_mm) +#ifdef __ARMEB__ +#define rl r3 +#define rh r2 +#else +#define rl r2 +#define rh r3 +#endif + /* * cpu_v7_set_pte_ext(ptep, pte) * @@ -73,13 +81,13 @@ ENDPROC(cpu_v7_switch_mm) */ ENTRY(cpu_v7_set_pte_ext) #ifdef CONFIG_MMU - tst r2, #L_PTE_VALID + tst rl, #L_PTE_VALID beq 1f - tst r3, #1 << (57 - 32) @ L_PTE_NONE - bicne r2, #L_PTE_VALID + tst rh, #1 << (57 - 32) @ L_PTE_NONE + bicne rl, #L_PTE_VALID bne 1f - tst r3, #1 << (55 - 32) @ L_PTE_DIRTY - orreq r2, #L_PTE_RDONLY + tst rh, #1 << (55 - 32) @ L_PTE_DIRTY + orreq rl, #L_PTE_RDONLY 1: strd r2, r3, [r0] ALT_SMP(W(nop)) ALT_UP (mcr p15, 0, r0, c7, c10, 1) @ flush_pte diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S index 73398bcf9bd..3db2c2f04a3 100644 --- a/arch/arm/mm/proc-v7.S +++ b/arch/arm/mm/proc-v7.S @@ -83,7 +83,7 @@ ENTRY(cpu_v7_dcache_clean_area) add r0, r0, r2 subs r1, r1, r2 bhi 2b - dsb + dsb ishst mov pc, lr ENDPROC(cpu_v7_dcache_clean_area) @@ -92,7 +92,7 @@ ENDPROC(cpu_v7_dcache_clean_area) /* Suspend/resume support: derived from arch/arm/mach-s5pv210/sleep.S */ .globl cpu_v7_suspend_size -.equ cpu_v7_suspend_size, 4 * 8 +.equ cpu_v7_suspend_size, 4 * 9 #ifdef CONFIG_ARM_CPU_SUSPEND ENTRY(cpu_v7_do_suspend) stmfd sp!, {r4 - r10, lr} @@ -101,13 +101,17 @@ ENTRY(cpu_v7_do_suspend) stmia r0!, {r4 - r5} #ifdef CONFIG_MMU mrc p15, 0, r6, c3, c0, 0 @ Domain ID +#ifdef CONFIG_ARM_LPAE + mrrc p15, 1, r5, r7, c2 @ TTB 1 +#else mrc p15, 0, r7, c2, c0, 1 @ TTB 1 +#endif mrc p15, 0, r11, c2, c0, 2 @ TTB control register #endif 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} + stmia r0, {r5 - r11} ldmfd sp!, {r4 - r10, pc} ENDPROC(cpu_v7_do_suspend) @@ -118,16 +122,19 @@ ENTRY(cpu_v7_do_resume) ldmia r0!, {r4 - r5} mcr p15, 0, r4, c13, c0, 0 @ FCSE/PID mcr p15, 0, r5, c13, c0, 3 @ User r/o thread ID - ldmia r0, {r6 - r11} + ldmia r0, {r5 - r11} #ifdef CONFIG_MMU mcr p15, 0, ip, c8, c7, 0 @ invalidate TLBs mcr p15, 0, r6, c3, c0, 0 @ Domain ID -#ifndef CONFIG_ARM_LPAE +#ifdef CONFIG_ARM_LPAE + mcrr p15, 0, r1, ip, c2 @ TTB 0 + mcrr p15, 1, r5, r7, c2 @ TTB 1 +#else 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 +#endif mcr p15, 0, r11, c2, c0, 2 @ TTB control register ldr r4, =PRRR @ PRRR ldr r5, =NMRR @ NMRR @@ -162,9 +169,31 @@ ENDPROC(cpu_pj4b_do_idle) globl_equ cpu_pj4b_do_idle, cpu_v7_do_idle #endif globl_equ cpu_pj4b_dcache_clean_area, cpu_v7_dcache_clean_area - globl_equ cpu_pj4b_do_suspend, cpu_v7_do_suspend - globl_equ cpu_pj4b_do_resume, cpu_v7_do_resume - globl_equ cpu_pj4b_suspend_size, cpu_v7_suspend_size +#ifdef CONFIG_ARM_CPU_SUSPEND +ENTRY(cpu_pj4b_do_suspend) + stmfd sp!, {r6 - r10} + mrc p15, 1, r6, c15, c1, 0 @ save CP15 - extra features + mrc p15, 1, r7, c15, c2, 0 @ save CP15 - Aux Func Modes Ctrl 0 + mrc p15, 1, r8, c15, c1, 2 @ save CP15 - Aux Debug Modes Ctrl 2 + mrc p15, 1, r9, c15, c1, 1 @ save CP15 - Aux Debug Modes Ctrl 1 + mrc p15, 0, r10, c9, c14, 0 @ save CP15 - PMC + stmia r0!, {r6 - r10} + ldmfd sp!, {r6 - r10} + b cpu_v7_do_suspend +ENDPROC(cpu_pj4b_do_suspend) + +ENTRY(cpu_pj4b_do_resume) + ldmia r0!, {r6 - r10} + mcr p15, 1, r6, c15, c1, 0 @ save CP15 - extra features + mcr p15, 1, r7, c15, c2, 0 @ save CP15 - Aux Func Modes Ctrl 0 + mcr p15, 1, r8, c15, c1, 2 @ save CP15 - Aux Debug Modes Ctrl 2 + mcr p15, 1, r9, c15, c1, 1 @ save CP15 - Aux Debug Modes Ctrl 1 + mcr p15, 0, r10, c9, c14, 0 @ save CP15 - PMC + b cpu_v7_do_resume +ENDPROC(cpu_pj4b_do_resume) +#endif +.globl cpu_pj4b_suspend_size +.equ cpu_pj4b_suspend_size, 4 * 14 #endif @@ -185,7 +214,9 @@ __v7_cr7mp_setup: mov r10, #(1 << 0) @ Cache/TLB ops broadcasting b 1f __v7_ca7mp_setup: +__v7_ca12mp_setup: __v7_ca15mp_setup: +__v7_ca17mp_setup: mov r10, #0 1: #ifdef CONFIG_SMP @@ -330,9 +361,20 @@ __v7_setup: 1: #endif -3: mov r10, #0 + /* Cortex-A15 Errata */ +3: ldr r10, =0x00000c0f @ Cortex-A15 primary part number + teq r0, r10 + bne 4f + +#ifdef CONFIG_ARM_ERRATA_773022 + cmp r6, #0x4 @ only present up to r0p4 + mrcle p15, 0, r10, c1, c0, 1 @ read aux control register + orrle r10, r10, #1 << 1 @ disable loop buffer + mcrle p15, 0, r10, c1, c0, 1 @ write aux control register +#endif + +4: mov r10, #0 mcr p15, 0, r10, c7, c5, 0 @ I+BTB cache invalidate - dsb #ifdef CONFIG_MMU mcr p15, 0, r10, c8, c7, 0 @ invalidate I + D TLBs v7_ttb_setup r10, r4, r8, r5 @ TTBCR, TTBRx setup @@ -341,6 +383,7 @@ __v7_setup: mcr p15, 0, r5, c10, c2, 0 @ write PRRR mcr p15, 0, r6, c10, c2, 1 @ write NMRR #endif + dsb @ Complete invalidations #ifndef CONFIG_ARM_THUMBEE mrc p15, 0, r0, c0, c1, 0 @ read ID_PFR0 for ThumbEE and r0, r0, #(0xf << 12) @ ThumbEE enabled field @@ -355,9 +398,7 @@ __v7_setup: #endif adr r5, v7_crval ldmia r5, {r5, r6} -#ifdef CONFIG_CPU_ENDIAN_BE8 - orr r6, r6, #1 << 25 @ big-endian page tables -#endif + ARM_BE8(orr r6, r6, #1 << 25) @ big-endian page tables #ifdef CONFIG_SWP_EMULATE orr r5, r5, #(1 << 10) @ set SW bit in "clear" bic r6, r6, #(1 << 10) @ clear it in "mmuset" @@ -467,6 +508,16 @@ __v7_ca7mp_proc_info: .size __v7_ca7mp_proc_info, . - __v7_ca7mp_proc_info /* + * ARM Ltd. Cortex A12 processor. + */ + .type __v7_ca12mp_proc_info, #object +__v7_ca12mp_proc_info: + .long 0x410fc0d0 + .long 0xff0ffff0 + __v7_proc __v7_ca12mp_setup + .size __v7_ca12mp_proc_info, . - __v7_ca12mp_proc_info + + /* * ARM Ltd. Cortex A15 processor. */ .type __v7_ca15mp_proc_info, #object @@ -477,6 +528,16 @@ __v7_ca15mp_proc_info: .size __v7_ca15mp_proc_info, . - __v7_ca15mp_proc_info /* + * ARM Ltd. Cortex A17 processor. + */ + .type __v7_ca17mp_proc_info, #object +__v7_ca17mp_proc_info: + .long 0x410fc0e0 + .long 0xff0ffff0 + __v7_proc __v7_ca17mp_setup + .size __v7_ca17mp_proc_info, . - __v7_ca17mp_proc_info + + /* * Qualcomm Inc. Krait processors. */ .type __krait_proc_info, #object diff --git a/arch/arm/mm/proc-v7m.S b/arch/arm/mm/proc-v7m.S index 0c93588fcb9..1ca37c72f12 100644 --- a/arch/arm/mm/proc-v7m.S +++ b/arch/arm/mm/proc-v7m.S @@ -123,6 +123,11 @@ __v7m_setup: mov pc, lr ENDPROC(__v7m_setup) + .align 2 +__v7m_setup_stack: + .space 4 * 8 @ 8 registers +__v7m_setup_stack_top: + define_processor_functions v7m, dabort=nommu_early_abort, pabort=legacy_pabort, nommu=1 .section ".rodata" @@ -152,6 +157,3 @@ __v7m_proc_info: .long nop_cache_fns @ proc_info_list.cache .size __v7m_proc_info, . - __v7m_proc_info -__v7m_setup_stack: - .space 4 * 8 @ 8 registers -__v7m_setup_stack_top: diff --git a/arch/arm/mm/tlb-v7.S b/arch/arm/mm/tlb-v7.S index ea94765acf9..355308767ba 100644 --- a/arch/arm/mm/tlb-v7.S +++ b/arch/arm/mm/tlb-v7.S @@ -35,7 +35,7 @@ ENTRY(v7wbi_flush_user_tlb_range) vma_vm_mm r3, r2 @ get vma->vm_mm mmid r3, r3 @ get vm_mm->context.id - dsb + dsb ish mov r0, r0, lsr #PAGE_SHIFT @ align address mov r1, r1, lsr #PAGE_SHIFT asid r3, r3 @ mask ASID @@ -56,7 +56,7 @@ ENTRY(v7wbi_flush_user_tlb_range) add r0, r0, #PAGE_SZ cmp r0, r1 blo 1b - dsb + dsb ish mov pc, lr ENDPROC(v7wbi_flush_user_tlb_range) @@ -69,7 +69,7 @@ ENDPROC(v7wbi_flush_user_tlb_range) * - end - end address (exclusive, may not be aligned) */ ENTRY(v7wbi_flush_kern_tlb_range) - dsb + dsb ish mov r0, r0, lsr #PAGE_SHIFT @ align address mov r1, r1, lsr #PAGE_SHIFT mov r0, r0, lsl #PAGE_SHIFT @@ -84,7 +84,7 @@ ENTRY(v7wbi_flush_kern_tlb_range) add r0, r0, #PAGE_SZ cmp r0, r1 blo 1b - dsb + dsb ish isb mov pc, lr ENDPROC(v7wbi_flush_kern_tlb_range) |