diff options
110 files changed, 1664 insertions, 1271 deletions
diff --git a/Documentation/devicetree/bindings/tty/serial/of-serial.txt b/Documentation/devicetree/bindings/tty/serial/of-serial.txt index b8b27b0aca10..0847fdeee11a 100644 --- a/Documentation/devicetree/bindings/tty/serial/of-serial.txt +++ b/Documentation/devicetree/bindings/tty/serial/of-serial.txt @@ -9,6 +9,7 @@ Required properties: - "ns16750" - "ns16850" - "nvidia,tegra20-uart" + - "nxp,lpc3220-uart" - "ibm,qpace-nwp-serial" - "serial" if the port type is unknown. - reg : offset and length of the register set for the device. diff --git a/Documentation/feature-removal-schedule.txt b/Documentation/feature-removal-schedule.txt index 61d1a89baeaf..76112dac7659 100644 --- a/Documentation/feature-removal-schedule.txt +++ b/Documentation/feature-removal-schedule.txt @@ -512,14 +512,6 @@ Who: Sebastian Andrzej Siewior <sebastian@breakpoint.cc> ---------------------------- -What: kmap_atomic(page, km_type) -When: 3.5 -Why: The old kmap_atomic() with two arguments is deprecated, we only - keep it for backward compatibility for few cycles and then drop it. -Who: Cong Wang <amwang@redhat.com> - ----------------------------- - What: get_robust_list syscall When: 2013 Why: There appear to be no production users of the get_robust_list syscall, diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 9124ff75fe53..fbdd8533c05d 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -45,6 +45,9 @@ config ARM select GENERIC_SMP_IDLE_THREAD select KTIME_SCALAR select GENERIC_CLOCKEVENTS_BROADCAST if SMP + select GENERIC_STRNCPY_FROM_USER + select GENERIC_STRNLEN_USER + select DCACHE_WORD_ACCESS if (CPU_V6 || CPU_V6K || CPU_V7) && !CPU_BIG_ENDIAN help The ARM series is a line of low-power-consumption RISC chip designs licensed by ARM Ltd and targeted at embedded applications and @@ -2004,6 +2007,25 @@ config ARM_ATAG_DTB_COMPAT bootloaders, this option allows zImage to extract the information from the ATAG list and store it at run time into the appended DTB. +choice + prompt "Kernel command line type" if ARM_ATAG_DTB_COMPAT + default ARM_ATAG_DTB_COMPAT_CMDLINE_FROM_BOOTLOADER + +config ARM_ATAG_DTB_COMPAT_CMDLINE_FROM_BOOTLOADER + bool "Use bootloader kernel arguments if available" + help + Uses the command-line options passed by the boot loader instead of + the device tree bootargs property. If the boot loader doesn't provide + any, the device tree bootargs property will be used. + +config ARM_ATAG_DTB_COMPAT_CMDLINE_EXTEND + bool "Extend with bootloader kernel arguments" + help + The command-line arguments provided by the boot loader will be + appended to the the device tree bootargs property. + +endchoice + config CMDLINE string "Default kernel command string" default "" diff --git a/arch/arm/Kconfig.debug b/arch/arm/Kconfig.debug index a03b5a7059e2..f15f82bf3a50 100644 --- a/arch/arm/Kconfig.debug +++ b/arch/arm/Kconfig.debug @@ -395,4 +395,13 @@ config ARM_KPROBES_TEST help Perform tests of kprobes API and instruction set simulation. +config PID_IN_CONTEXTIDR + bool "Write the current PID to the CONTEXTIDR register" + depends on CPU_COPY_V6 + help + Enabling this option causes the kernel to write the current PID to + the PROCID field of the CONTEXTIDR register, at the expense of some + additional instructions during context switch. Say Y here only if you + are planning to use hardware trace tools with this kernel. + endmenu diff --git a/arch/arm/Makefile b/arch/arm/Makefile index 4d6d31115cf2..30eae87ead6d 100644 --- a/arch/arm/Makefile +++ b/arch/arm/Makefile @@ -10,6 +10,9 @@ # # Copyright (C) 1995-2001 by Russell King +# Ensure linker flags are correct +LDFLAGS := + LDFLAGS_vmlinux :=-p --no-undefined -X ifeq ($(CONFIG_CPU_ENDIAN_BE8),y) LDFLAGS_vmlinux += --be8 diff --git a/arch/arm/boot/compressed/atags_to_fdt.c b/arch/arm/boot/compressed/atags_to_fdt.c index 797f04bedb47..aabc02a68482 100644 --- a/arch/arm/boot/compressed/atags_to_fdt.c +++ b/arch/arm/boot/compressed/atags_to_fdt.c @@ -1,6 +1,12 @@ #include <asm/setup.h> #include <libfdt.h> +#if defined(CONFIG_ARM_ATAG_DTB_COMPAT_CMDLINE_EXTEND) +#define do_extend_cmdline 1 +#else +#define do_extend_cmdline 0 +#endif + static int node_offset(void *fdt, const char *node_path) { int offset = fdt_path_offset(fdt, node_path); @@ -36,6 +42,48 @@ static int setprop_cell(void *fdt, const char *node_path, return fdt_setprop_cell(fdt, offset, property, val); } +static const void *getprop(const void *fdt, const char *node_path, + const char *property, int *len) +{ + int offset = fdt_path_offset(fdt, node_path); + + if (offset == -FDT_ERR_NOTFOUND) + return NULL; + + return fdt_getprop(fdt, offset, property, len); +} + +static void merge_fdt_bootargs(void *fdt, const char *fdt_cmdline) +{ + char cmdline[COMMAND_LINE_SIZE]; + const char *fdt_bootargs; + char *ptr = cmdline; + int len = 0; + + /* copy the fdt command line into the buffer */ + fdt_bootargs = getprop(fdt, "/chosen", "bootargs", &len); + if (fdt_bootargs) + if (len < COMMAND_LINE_SIZE) { + memcpy(ptr, fdt_bootargs, len); + /* len is the length of the string + * including the NULL terminator */ + ptr += len - 1; + } + + /* and append the ATAG_CMDLINE */ + if (fdt_cmdline) { + len = strlen(fdt_cmdline); + if (ptr - cmdline + len + 2 < COMMAND_LINE_SIZE) { + *ptr++ = ' '; + memcpy(ptr, fdt_cmdline, len); + ptr += len; + } + } + *ptr = '\0'; + + setprop_string(fdt, "/chosen", "bootargs", cmdline); +} + /* * Convert and fold provided ATAGs into the provided FDT. * @@ -72,8 +120,18 @@ int atags_to_fdt(void *atag_list, void *fdt, int total_space) for_each_tag(atag, atag_list) { if (atag->hdr.tag == ATAG_CMDLINE) { - setprop_string(fdt, "/chosen", "bootargs", - atag->u.cmdline.cmdline); + /* Append the ATAGS command line to the device tree + * command line. + * NB: This means that if the same parameter is set in + * the device tree and in the tags, the one from the + * tags will be chosen. + */ + if (do_extend_cmdline) + merge_fdt_bootargs(fdt, + atag->u.cmdline.cmdline); + else + setprop_string(fdt, "/chosen", "bootargs", + atag->u.cmdline.cmdline); } else if (atag->hdr.tag == ATAG_MEM) { if (memcount >= sizeof(mem_reg_property)/4) continue; diff --git a/arch/arm/include/asm/arch_timer.h b/arch/arm/include/asm/arch_timer.h index ed2e95d46e29..62e75475e57e 100644 --- a/arch/arm/include/asm/arch_timer.h +++ b/arch/arm/include/asm/arch_timer.h @@ -1,7 +1,10 @@ #ifndef __ASMARM_ARCH_TIMER_H #define __ASMARM_ARCH_TIMER_H +#include <asm/errno.h> + #ifdef CONFIG_ARM_ARCH_TIMER +#define ARCH_HAS_READ_CURRENT_TIMER int arch_timer_of_register(void); int arch_timer_sched_clock_init(void); #else diff --git a/arch/arm/include/asm/delay.h b/arch/arm/include/asm/delay.h index b2deda181549..dc6145120de3 100644 --- a/arch/arm/include/asm/delay.h +++ b/arch/arm/include/asm/delay.h @@ -6,9 +6,22 @@ #ifndef __ASM_ARM_DELAY_H #define __ASM_ARM_DELAY_H +#include <asm/memory.h> #include <asm/param.h> /* HZ */ -extern void __delay(int loops); +#define MAX_UDELAY_MS 2 +#define UDELAY_MULT ((UL(2199023) * HZ) >> 11) +#define UDELAY_SHIFT 30 + +#ifndef __ASSEMBLY__ + +extern struct arm_delay_ops { + void (*delay)(unsigned long); + void (*const_udelay)(unsigned long); + void (*udelay)(unsigned long); +} arm_delay_ops; + +#define __delay(n) arm_delay_ops.delay(n) /* * This function intentionally does not exist; if you see references to @@ -23,22 +36,27 @@ extern void __bad_udelay(void); * division by multiplication: you don't have to worry about * loss of precision. * - * Use only for very small delays ( < 1 msec). Should probably use a + * Use only for very small delays ( < 2 msec). Should probably use a * lookup table, really, as the multiplications take much too long with * short delays. This is a "reasonable" implementation, though (and the * first constant multiplications gets optimized away if the delay is * a constant) */ -extern void __udelay(unsigned long usecs); -extern void __const_udelay(unsigned long); - -#define MAX_UDELAY_MS 2 +#define __udelay(n) arm_delay_ops.udelay(n) +#define __const_udelay(n) arm_delay_ops.const_udelay(n) #define udelay(n) \ (__builtin_constant_p(n) ? \ ((n) > (MAX_UDELAY_MS * 1000) ? __bad_udelay() : \ - __const_udelay((n) * ((2199023U*HZ)>>11))) : \ + __const_udelay((n) * UDELAY_MULT)) : \ __udelay(n)) +/* Loop-based definitions for assembly code. */ +extern void __loop_delay(unsigned long loops); +extern void __loop_udelay(unsigned long usecs); +extern void __loop_const_udelay(unsigned long); + +#endif /* __ASSEMBLY__ */ + #endif /* defined(_ARM_DELAY_H) */ diff --git a/arch/arm/include/asm/kmap_types.h b/arch/arm/include/asm/kmap_types.h index e51b1e81df05..83eb2f772911 100644 --- a/arch/arm/include/asm/kmap_types.h +++ b/arch/arm/include/asm/kmap_types.h @@ -4,30 +4,6 @@ /* * This is the "bare minimum". AIO seems to require this. */ -enum km_type { - KM_BOUNCE_READ, - KM_SKB_SUNRPC_DATA, - KM_SKB_DATA_SOFTIRQ, - KM_USER0, - KM_USER1, - KM_BIO_SRC_IRQ, - KM_BIO_DST_IRQ, - KM_PTE0, - KM_PTE1, - KM_IRQ0, - KM_IRQ1, - KM_SOFTIRQ0, - KM_SOFTIRQ1, - KM_L1_CACHE, - KM_L2_CACHE, - KM_KDB, - KM_TYPE_NR -}; - -#ifdef CONFIG_DEBUG_HIGHMEM -#define KM_NMI (-1) -#define KM_NMI_PTE (-1) -#define KM_IRQ_PTE (-1) -#endif +#define KM_TYPE_NR 16 #endif diff --git a/arch/arm/include/asm/locks.h b/arch/arm/include/asm/locks.h deleted file mode 100644 index ef4c897772d1..000000000000 --- a/arch/arm/include/asm/locks.h +++ /dev/null @@ -1,274 +0,0 @@ -/* - * arch/arm/include/asm/locks.h - * - * Copyright (C) 2000 Russell King - * - * 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. - * - * Interrupt safe locking assembler. - */ -#ifndef __ASM_PROC_LOCKS_H -#define __ASM_PROC_LOCKS_H - -#if __LINUX_ARM_ARCH__ >= 6 - -#define __down_op(ptr,fail) \ - ({ \ - __asm__ __volatile__( \ - "@ down_op\n" \ -"1: ldrex lr, [%0]\n" \ -" sub lr, lr, %1\n" \ -" strex ip, lr, [%0]\n" \ -" teq ip, #0\n" \ -" bne 1b\n" \ -" teq lr, #0\n" \ -" movmi ip, %0\n" \ -" blmi " #fail \ - : \ - : "r" (ptr), "I" (1) \ - : "ip", "lr", "cc"); \ - smp_mb(); \ - }) - -#define __down_op_ret(ptr,fail) \ - ({ \ - unsigned int ret; \ - __asm__ __volatile__( \ - "@ down_op_ret\n" \ -"1: ldrex lr, [%1]\n" \ -" sub lr, lr, %2\n" \ -" strex ip, lr, [%1]\n" \ -" teq ip, #0\n" \ -" bne 1b\n" \ -" teq lr, #0\n" \ -" movmi ip, %1\n" \ -" movpl ip, #0\n" \ -" blmi " #fail "\n" \ -" mov %0, ip" \ - : "=&r" (ret) \ - : "r" (ptr), "I" (1) \ - : "ip", "lr", "cc"); \ - smp_mb(); \ - ret; \ - }) - -#define __up_op(ptr,wake) \ - ({ \ - smp_mb(); \ - __asm__ __volatile__( \ - "@ up_op\n" \ -"1: ldrex lr, [%0]\n" \ -" add lr, lr, %1\n" \ -" strex ip, lr, [%0]\n" \ -" teq ip, #0\n" \ -" bne 1b\n" \ -" cmp lr, #0\n" \ -" movle ip, %0\n" \ -" blle " #wake \ - : \ - : "r" (ptr), "I" (1) \ - : "ip", "lr", "cc"); \ - }) - -/* - * The value 0x01000000 supports up to 128 processors and - * lots of processes. BIAS must be chosen such that sub'ing - * BIAS once per CPU will result in the long remaining - * negative. - */ -#define RW_LOCK_BIAS 0x01000000 -#define RW_LOCK_BIAS_STR "0x01000000" - -#define __down_op_write(ptr,fail) \ - ({ \ - __asm__ __volatile__( \ - "@ down_op_write\n" \ -"1: ldrex lr, [%0]\n" \ -" sub lr, lr, %1\n" \ -" strex ip, lr, [%0]\n" \ -" teq ip, #0\n" \ -" bne 1b\n" \ -" teq lr, #0\n" \ -" movne ip, %0\n" \ -" blne " #fail \ - : \ - : "r" (ptr), "I" (RW_LOCK_BIAS) \ - : "ip", "lr", "cc"); \ - smp_mb(); \ - }) - -#define __up_op_write(ptr,wake) \ - ({ \ - smp_mb(); \ - __asm__ __volatile__( \ - "@ up_op_write\n" \ -"1: ldrex lr, [%0]\n" \ -" adds lr, lr, %1\n" \ -" strex ip, lr, [%0]\n" \ -" teq ip, #0\n" \ -" bne 1b\n" \ -" movcs ip, %0\n" \ -" blcs " #wake \ - : \ - : "r" (ptr), "I" (RW_LOCK_BIAS) \ - : "ip", "lr", "cc"); \ - }) - -#define __down_op_read(ptr,fail) \ - __down_op(ptr, fail) - -#define __up_op_read(ptr,wake) \ - ({ \ - smp_mb(); \ - __asm__ __volatile__( \ - "@ up_op_read\n" \ -"1: ldrex lr, [%0]\n" \ -" add lr, lr, %1\n" \ -" strex ip, lr, [%0]\n" \ -" teq ip, #0\n" \ -" bne 1b\n" \ -" teq lr, #0\n" \ -" moveq ip, %0\n" \ -" bleq " #wake \ - : \ - : "r" (ptr), "I" (1) \ - : "ip", "lr", "cc"); \ - }) - -#else - -#define __down_op(ptr,fail) \ - ({ \ - __asm__ __volatile__( \ - "@ down_op\n" \ -" mrs ip, cpsr\n" \ -" orr lr, ip, #128\n" \ -" msr cpsr_c, lr\n" \ -" ldr lr, [%0]\n" \ -" subs lr, lr, %1\n" \ -" str lr, [%0]\n" \ -" msr cpsr_c, ip\n" \ -" movmi ip, %0\n" \ -" blmi " #fail \ - : \ - : "r" (ptr), "I" (1) \ - : "ip", "lr", "cc"); \ - smp_mb(); \ - }) - -#define __down_op_ret(ptr,fail) \ - ({ \ - unsigned int ret; \ - __asm__ __volatile__( \ - "@ down_op_ret\n" \ -" mrs ip, cpsr\n" \ -" orr lr, ip, #128\n" \ -" msr cpsr_c, lr\n" \ -" ldr lr, [%1]\n" \ -" subs lr, lr, %2\n" \ -" str lr, [%1]\n" \ -" msr cpsr_c, ip\n" \ -" movmi ip, %1\n" \ -" movpl ip, #0\n" \ -" blmi " #fail "\n" \ -" mov %0, ip" \ - : "=&r" (ret) \ - : "r" (ptr), "I" (1) \ - : "ip", "lr", "cc"); \ - smp_mb(); \ - ret; \ - }) - -#define __up_op(ptr,wake) \ - ({ \ - smp_mb(); \ - __asm__ __volatile__( \ - "@ up_op\n" \ -" mrs ip, cpsr\n" \ -" orr lr, ip, #128\n" \ -" msr cpsr_c, lr\n" \ -" ldr lr, [%0]\n" \ -" adds lr, lr, %1\n" \ -" str lr, [%0]\n" \ -" msr cpsr_c, ip\n" \ -" movle ip, %0\n" \ -" blle " #wake \ - : \ - : "r" (ptr), "I" (1) \ - : "ip", "lr", "cc"); \ - }) - -/* - * The value 0x01000000 supports up to 128 processors and - * lots of processes. BIAS must be chosen such that sub'ing - * BIAS once per CPU will result in the long remaining - * negative. - */ -#define RW_LOCK_BIAS 0x01000000 -#define RW_LOCK_BIAS_STR "0x01000000" - -#define __down_op_write(ptr,fail) \ - ({ \ - __asm__ __volatile__( \ - "@ down_op_write\n" \ -" mrs ip, cpsr\n" \ -" orr lr, ip, #128\n" \ -" msr cpsr_c, lr\n" \ -" ldr lr, [%0]\n" \ -" subs lr, lr, %1\n" \ -" str lr, [%0]\n" \ -" msr cpsr_c, ip\n" \ -" movne ip, %0\n" \ -" blne " #fail \ - : \ - : "r" (ptr), "I" (RW_LOCK_BIAS) \ - : "ip", "lr", "cc"); \ - smp_mb(); \ - }) - -#define __up_op_write(ptr,wake) \ - ({ \ - __asm__ __volatile__( \ - "@ up_op_write\n" \ -" mrs ip, cpsr\n" \ -" orr lr, ip, #128\n" \ -" msr cpsr_c, lr\n" \ -" ldr lr, [%0]\n" \ -" adds lr, lr, %1\n" \ -" str lr, [%0]\n" \ -" msr cpsr_c, ip\n" \ -" movcs ip, %0\n" \ -" blcs " #wake \ - : \ - : "r" (ptr), "I" (RW_LOCK_BIAS) \ - : "ip", "lr", "cc"); \ - smp_mb(); \ - }) - -#define __down_op_read(ptr,fail) \ - __down_op(ptr, fail) - -#define __up_op_read(ptr,wake) \ - ({ \ - smp_mb(); \ - __asm__ __volatile__( \ - "@ up_op_read\n" \ -" mrs ip, cpsr\n" \ -" orr lr, ip, #128\n" \ -" msr cpsr_c, lr\n" \ -" ldr lr, [%0]\n" \ -" adds lr, lr, %1\n" \ -" str lr, [%0]\n" \ -" msr cpsr_c, ip\n" \ -" moveq ip, %0\n" \ -" bleq " #wake \ - : \ - : "r" (ptr), "I" (1) \ - : "ip", "lr", "cc"); \ - }) - -#endif - -#endif diff --git a/arch/arm/include/asm/memory.h b/arch/arm/include/asm/memory.h index fcb575747e5e..e965f1b560f1 100644 --- a/arch/arm/include/asm/memory.h +++ b/arch/arm/include/asm/memory.h @@ -16,7 +16,7 @@ #include <linux/compiler.h> #include <linux/const.h> #include <linux/types.h> -#include <asm/sizes.h> +#include <linux/sizes.h> #ifdef CONFIG_NEED_MACH_MEMORY_H #include <mach/memory.h> diff --git a/arch/arm/include/asm/perf_event.h b/arch/arm/include/asm/perf_event.h index 00cbe10a50e3..e074948d8143 100644 --- a/arch/arm/include/asm/perf_event.h +++ b/arch/arm/include/asm/perf_event.h @@ -12,21 +12,6 @@ #ifndef __ARM_PERF_EVENT_H__ #define __ARM_PERF_EVENT_H__ -/* ARM perf PMU IDs for use by internal perf clients. */ -enum arm_perf_pmu_ids { - ARM_PERF_PMU_ID_XSCALE1 = 0, - ARM_PERF_PMU_ID_XSCALE2, - ARM_PERF_PMU_ID_V6, - ARM_PERF_PMU_ID_V6MP, - ARM_PERF_PMU_ID_CA8, - ARM_PERF_PMU_ID_CA9, - ARM_PERF_PMU_ID_CA5, - ARM_PERF_PMU_ID_CA15, - ARM_PERF_PMU_ID_CA7, - ARM_NUM_PMU_IDS, -}; - -extern enum arm_perf_pmu_ids -armpmu_get_pmu_id(void); +/* Nothing to see here... */ #endif /* __ARM_PERF_EVENT_H__ */ diff --git a/arch/arm/include/asm/pmu.h b/arch/arm/include/asm/pmu.h index 90114faa9f3c..4432305f4a2a 100644 --- a/arch/arm/include/asm/pmu.h +++ b/arch/arm/include/asm/pmu.h @@ -103,10 +103,9 @@ struct pmu_hw_events { struct arm_pmu { struct pmu pmu; - enum arm_perf_pmu_ids id; enum arm_pmu_type type; cpumask_t active_irqs; - const char *name; + char *name; irqreturn_t (*handle_irq)(int irq_num, void *dev); void (*enable)(struct hw_perf_event *evt, int idx); void (*disable)(struct hw_perf_event *evt, int idx); diff --git a/arch/arm/include/asm/spinlock.h b/arch/arm/include/asm/spinlock.h index 65fa3c88095c..b4ca707d0a69 100644 --- a/arch/arm/include/asm/spinlock.h +++ b/arch/arm/include/asm/spinlock.h @@ -59,18 +59,13 @@ static inline void dsb_sev(void) } /* - * ARMv6 Spin-locking. + * ARMv6 ticket-based spin-locking. * - * We exclusively read the old value. If it is zero, we may have - * won the lock, so we try exclusively storing it. A memory barrier - * is required after we get a lock, and before we release it, because - * V6 CPUs are assumed to have weakly ordered memory. - * - * Unlocked value: 0 - * Locked value: 1 + * A memory barrier is required after we get a lock, and before we + * release it, because V6 CPUs are assumed to have weakly ordered + * memory. */ -#define arch_spin_is_locked(x) ((x)->lock != 0) #define arch_spin_unlock_wait(lock) \ do { while (arch_spin_is_locked(lock)) cpu_relax(); } while (0) @@ -79,31 +74,39 @@ static inline void dsb_sev(void) static inline void arch_spin_lock(arch_spinlock_t *lock) { unsigned long tmp; + u32 newval; + arch_spinlock_t lockval; __asm__ __volatile__( -"1: ldrex %0, [%1]\n" -" teq %0, #0\n" - WFE("ne") -" strexeq %0, %2, [%1]\n" -" teqeq %0, #0\n" +"1: ldrex %0, [%3]\n" +" add %1, %0, %4\n" +" strex %2, %1, [%3]\n" +" teq %2, #0\n" " bne 1b" - : "=&r" (tmp) - : "r" (&lock->lock), "r" (1) + : "=&r" (lockval), "=&r" (newval), "=&r" (tmp) + : "r" (&lock->slock), "I" (1 << TICKET_SHIFT) : "cc"); + while (lockval.tickets.next != lockval.tickets.owner) { + wfe(); + lockval.tickets.owner = ACCESS_ONCE(lock->tickets.owner); + } + smp_mb(); } static inline int arch_spin_trylock(arch_spinlock_t *lock) { unsigned long tmp; + u32 slock; __asm__ __volatile__( -" ldrex %0, [%1]\n" -" teq %0, #0\n" -" strexeq %0, %2, [%1]" - : "=&r" (tmp) - : "r" (&lock->lock), "r" (1) +" ldrex %0, [%2]\n" +" subs %1, %0, %0, ror #16\n" +" addeq %0, %0, %3\n" +" strexeq %1, %0, [%2]" + : "=&r" (slock), "=&r" (tmp) + : "r" (&lock->slock), "I" (1 << TICKET_SHIFT) : "cc"); if (tmp == 0) { @@ -116,17 +119,38 @@ static inline int arch_spin_trylock(arch_spinlock_t *lock) static inline void arch_spin_unlock(arch_spinlock_t *lock) { + unsigned long tmp; + u32 slock; + smp_mb(); __asm__ __volatile__( -" str %1, [%0]\n" - : - : "r" (&lock->lock), "r" (0) +" mov %1, #1\n" +"1: ldrex %0, [%2]\n" +" uadd16 %0, %0, %1\n" +" strex %1, %0, [%2]\n" +" teq %1, #0\n" +" bne 1b" + : "=&r" (slock), "=&r" (tmp) + : "r" (&lock->slock) : "cc"); dsb_sev(); } +static inline int arch_spin_is_locked(arch_spinlock_t *lock) +{ + struct __raw_tickets tickets = ACCESS_ONCE(lock->tickets); + return tickets.owner != tickets.next; +} + +static inline int arch_spin_is_contended(arch_spinlock_t *lock) +{ + struct __raw_tickets tickets = ACCESS_ONCE(lock->tickets); + return (tickets.next - tickets.owner) > 1; +} +#define arch_spin_is_contended arch_spin_is_contended + /* * RWLOCKS * @@ -158,7 +182,7 @@ static inline int arch_write_trylock(arch_rwlock_t *rw) unsigned long tmp; __asm__ __volatile__( -"1: ldrex %0, [%1]\n" +" ldrex %0, [%1]\n" " teq %0, #0\n" " strexeq %0, %2, [%1]" : "=&r" (tmp) @@ -244,7 +268,7 @@ static inline int arch_read_trylock(arch_rwlock_t *rw) unsigned long tmp, tmp2 = 1; __asm__ __volatile__( -"1: ldrex %0, [%2]\n" +" ldrex %0, [%2]\n" " adds %0, %0, #1\n" " strexpl %1, %0, [%2]\n" : "=&r" (tmp), "+r" (tmp2) diff --git a/arch/arm/include/asm/spinlock_types.h b/arch/arm/include/asm/spinlock_types.h index d14d197ae04a..b262d2f8b478 100644 --- a/arch/arm/include/asm/spinlock_types.h +++ b/arch/arm/include/asm/spinlock_types.h @@ -5,11 +5,24 @@ # error "please don't include this file directly" #endif +#define TICKET_SHIFT 16 + typedef struct { - volatile unsigned int lock; + union { + u32 slock; + struct __raw_tickets { +#ifdef __ARMEB__ + u16 next; + u16 owner; +#else + u16 owner; + u16 next; +#endif + } tickets; + }; } arch_spinlock_t; -#define __ARCH_SPIN_LOCK_UNLOCKED { 0 } +#define __ARCH_SPIN_LOCK_UNLOCKED { { 0 } } typedef struct { volatile unsigned int lock; diff --git a/arch/arm/include/asm/timex.h b/arch/arm/include/asm/timex.h index 3be8de3adaba..ce119442277c 100644 --- a/arch/arm/include/asm/timex.h +++ b/arch/arm/include/asm/timex.h @@ -12,13 +12,15 @@ #ifndef _ASMARM_TIMEX_H #define _ASMARM_TIMEX_H +#include <asm/arch_timer.h> #include <mach/timex.h> typedef unsigned long cycles_t; -static inline cycles_t get_cycles (void) -{ - return 0; -} +#ifdef ARCH_HAS_READ_CURRENT_TIMER +#define get_cycles() ({ cycles_t c; read_current_timer(&c) ? 0 : c; }) +#else +#define get_cycles() (0) +#endif #endif diff --git a/arch/arm/include/asm/uaccess.h b/arch/arm/include/asm/uaccess.h index 71f6536d17ac..479a6352e0b5 100644 --- a/arch/arm/include/asm/uaccess.h +++ b/arch/arm/include/asm/uaccess.h @@ -189,6 +189,9 @@ static inline void set_fs(mm_segment_t fs) #define access_ok(type,addr,size) (__range_ok(addr,size) == 0) +#define user_addr_max() \ + (segment_eq(get_fs(), USER_DS) ? TASK_SIZE : ~0UL) + /* * The "__xxx" versions of the user access functions do not verify the * address space - it must have been done previously with a separate @@ -398,9 +401,6 @@ extern unsigned long __must_check __clear_user_std(void __user *addr, unsigned l #define __clear_user(addr,n) (memset((void __force *)addr, 0, n), 0) #endif -extern unsigned long __must_check __strncpy_from_user(char *to, const char __user *from, unsigned long count); -extern unsigned long __must_check __strnlen_user(const char __user *s, long n); - static inline unsigned long __must_check copy_from_user(void *to, const void __user *from, unsigned long n) { if (access_ok(VERIFY_READ, from, n)) @@ -427,24 +427,9 @@ static inline unsigned long __must_check clear_user(void __user *to, unsigned lo return n; } -static inline long __must_check strncpy_from_user(char *dst, const char __user *src, long count) -{ - long res = -EFAULT; - if (access_ok(VERIFY_READ, src, 1)) - res = __strncpy_from_user(dst, src, count); - return res; -} - -#define strlen_user(s) strnlen_user(s, ~0UL >> 1) +extern long strncpy_from_user(char *dest, const char __user *src, long count); -static inline long __must_check strnlen_user(const char __user *s, long n) -{ - unsigned long res = 0; - - if (__addr_ok(s)) - res = __strnlen_user(s, n); - - return res; -} +extern __must_check long strlen_user(const char __user *str); +extern __must_check long strnlen_user(const char __user *str, long n); #endif /* _ASMARM_UACCESS_H */ diff --git a/arch/arm/include/asm/word-at-a-time.h b/arch/arm/include/asm/word-at-a-time.h new file mode 100644 index 000000000000..4d52f92967a6 --- /dev/null +++ b/arch/arm/include/asm/word-at-a-time.h @@ -0,0 +1,96 @@ +#ifndef __ASM_ARM_WORD_AT_A_TIME_H +#define __ASM_ARM_WORD_AT_A_TIME_H + +#ifndef __ARMEB__ + +/* + * Little-endian word-at-a-time zero byte handling. + * Heavily based on the x86 algorithm. + */ +#include <linux/kernel.h> + +struct word_at_a_time { + const unsigned long one_bits, high_bits; +}; + +#define WORD_AT_A_TIME_CONSTANTS { REPEAT_BYTE(0x01), REPEAT_BYTE(0x80) } + +static inline unsigned long has_zero(unsigned long a, unsigned long *bits, + const struct word_at_a_time *c) +{ + unsigned long mask = ((a - c->one_bits) & ~a) & c->high_bits; + *bits = mask; + return mask; +} + +#define prep_zero_mask(a, bits, c) (bits) + +static inline unsigned long create_zero_mask(unsigned long bits) +{ + bits = (bits - 1) & ~bits; + return bits >> 7; +} + +static inline unsigned long find_zero(unsigned long mask) +{ + unsigned long ret; + +#if __LINUX_ARM_ARCH__ >= 5 + /* We have clz available. */ + ret = fls(mask) >> 3; +#else + /* (000000 0000ff 00ffff ffffff) -> ( 1 1 2 3 ) */ + ret = (0x0ff0001 + mask) >> 23; + /* Fix the 1 for 00 case */ + ret &= mask; +#endif + + return ret; +} + +#ifdef CONFIG_DCACHE_WORD_ACCESS + +#define zero_bytemask(mask) (mask) + +/* + * Load an unaligned word from kernel space. + * + * In the (very unlikely) case of the word being a page-crosser + * and the next page not being mapped, take the exception and + * return zeroes in the non-existing part. + */ +static inline unsigned long load_unaligned_zeropad(const void *addr) +{ + unsigned long ret, offset; + + /* Load word from unaligned pointer addr */ + asm( + "1: ldr %0, [%2]\n" + "2:\n" + " .pushsection .fixup,\"ax\"\n" + " .align 2\n" + "3: and %1, %2, #0x3\n" + " bic %2, %2, #0x3\n" + " ldr %0, [%2]\n" + " lsl %1, %1, #0x3\n" + " lsr %0, %0, %1\n" + " b 2b\n" + " .popsection\n" + " .pushsection __ex_table,\"a\"\n" + " .align 3\n" + " .long 1b, 3b\n" + " .popsection" + : "=&r" (ret), "=&r" (offset) + : "r" (addr), "Qo" (*(unsigned long *)addr)); + + return ret; +} + + +#endif /* DCACHE_WORD_ACCESS */ + +#else /* __ARMEB__ */ +#include <asm-generic/word-at-a-time.h> +#endif + +#endif /* __ASM_ARM_WORD_AT_A_TIME_H */ diff --git a/arch/arm/kernel/arch_timer.c b/arch/arm/kernel/arch_timer.c index dd58035621f7..cf258807160d 100644 --- a/arch/arm/kernel/arch_timer.c +++ b/arch/arm/kernel/arch_timer.c @@ -32,6 +32,8 @@ static int arch_timer_ppi2; static struct clock_event_device __percpu **arch_timer_evt; +extern void init_current_timer_delay(unsigned long freq); + /* * Architected system timer support. */ @@ -137,7 +139,7 @@ static int __cpuinit arch_timer_setup(struct clock_event_device *clk) /* Be safe... */ arch_timer_disable(); - clk->features = CLOCK_EVT_FEAT_ONESHOT; + clk->features = CLOCK_EVT_FEAT_ONESHOT | CLOCK_EVT_FEAT_C3STOP; clk->name = "arch_sys_timer"; clk->rating = 450; clk->set_mode = arch_timer_set_mode; @@ -223,6 +225,14 @@ static cycle_t arch_counter_read(struct clocksource *cs) return arch_counter_get_cntpct(); } +int read_current_timer(unsigned long *timer_val) +{ + if (!arch_timer_rate) + return -ENXIO; + *timer_val = arch_counter_get_cntpct(); + return 0; +} + static struct clocksource clocksource_counter = { .name = "arch_sys_counter", .rating = 400, @@ -296,6 +306,7 @@ static int __init arch_timer_register(void) if (err) goto out_free_irq; + init_current_timer_delay(arch_timer_rate); return 0; out_free_irq: diff --git a/arch/arm/kernel/armksyms.c b/arch/arm/kernel/armksyms.c index b57c75e0b01f..60d3b738d420 100644 --- a/arch/arm/kernel/armksyms.c +++ b/arch/arm/kernel/armksyms.c @@ -49,8 +49,7 @@ extern void __aeabi_ulcmp(void); extern void fpundefinstr(void); /* platform dependent support */ -EXPORT_SYMBOL(__udelay); -EXPORT_SYMBOL(__const_udelay); +EXPORT_SYMBOL(arm_delay_ops); /* networking */ EXPORT_SYMBOL(csum_partial); @@ -87,10 +86,6 @@ EXPORT_SYMBOL(memmove); EXPORT_SYMBOL(memchr); EXPORT_SYMBOL(__memzero); - /* user mem (segment) */ -EXPORT_SYMBOL(__strnlen_user); -EXPORT_SYMBOL(__strncpy_from_user); - #ifdef CONFIG_MMU EXPORT_SYMBOL(copy_page); diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S index 4afed88d250a..49d9f9305247 100644 --- a/arch/arm/kernel/entry-common.S +++ b/arch/arm/kernel/entry-common.S @@ -95,13 +95,7 @@ ENDPROC(ret_to_user) ENTRY(ret_from_fork) bl schedule_tail get_thread_info tsk - ldr r1, [tsk, #TI_FLAGS] @ check for syscall tracing mov why, #1 - tst r1, #_TIF_SYSCALL_WORK @ are we tracing syscalls? - beq ret_slow_syscall - mov r1, sp - mov r0, #1 @ trace exit [IP = 1] - bl syscall_trace b ret_slow_syscall ENDPROC(ret_from_fork) @@ -448,10 +442,9 @@ ENDPROC(vector_swi) * context switches, and waiting for our parent to respond. */ __sys_trace: - mov r2, scno - add r1, sp, #S_OFF - mov r0, #0 @ trace entry [IP = 0] - bl syscall_trace + mov r1, scno + add r0, sp, #S_OFF + bl syscall_trace_enter adr lr, BSYM(__sys_trace_return) @ return address mov scno, r0 @ syscall number (possibly new) @@ -463,10 +456,9 @@ __sys_trace: __sys_trace_return: str r0, [sp, #S_R0 + S_OFF]! @ save returned r0 - mov r2, scno - mov r1, sp - mov r0, #1 @ trace exit [IP = 1] - bl syscall_trace + mov r1, scno + mov r0, sp + bl syscall_trace_exit b ret_slow_syscall .align 5 diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S index 835898e7d704..3db960e20cb8 100644 --- a/arch/arm/kernel/head.S +++ b/arch/arm/kernel/head.S @@ -55,14 +55,6 @@ add \rd, \phys, #TEXT_OFFSET - PG_DIR_SIZE .endm -#ifdef CONFIG_XIP_KERNEL -#define KERNEL_START XIP_VIRT_ADDR(CONFIG_XIP_PHYS_ADDR) -#define KERNEL_END _edata_loc -#else -#define KERNEL_START KERNEL_RAM_VADDR -#define KERNEL_END _end -#endif - /* * Kernel startup entry point. * --------------------------- @@ -218,51 +210,46 @@ __create_page_tables: blo 1b /* - * Now setup the pagetables for our kernel direct - * mapped region. + * Map our RAM from the start to the end of the kernel .bss section. */ - mov r3, pc - mov r3, r3, lsr #SECTION_SHIFT - orr r3, r7, r3, lsl #SECTION_SHIFT - add r0, r4, #(KERNEL_START & 0xff000000) >> (SECTION_SHIFT - PMD_ORDER) - str r3, [r0, #((KERNEL_START & 0x00f00000) >> SECTION_SHIFT) << PMD_ORDER]! - ldr r6, =(KERNEL_END - 1) - add r0, r0, #1 << PMD_ORDER + add r0, r4, #PAGE_OFFSET >> (SECTION_SHIFT - PMD_ORDER) + ldr r6, =(_end - 1) + orr r3, r8, r7 add r6, r4, r6, lsr #(SECTION_SHIFT - PMD_ORDER) -1: cmp r0, r6 +1: str r3, [r0], #1 << PMD_ORDER add r3, r3, #1 << SECTION_SHIFT - strls r3, [r0], #1 << PMD_ORDER + cmp r0, r6 bls 1b #ifdef CONFIG_XIP_KERNEL /* - * Map some ram to cover our .data and .bss areas. + * Map the kernel image separately as it is not located in RAM. */ - add r3, r8, #TEXT_OFFSET - orr r3, r3, r7 - add r0, r4, #(KERNEL_RAM_VADDR & 0xff000000) >> (SECTION_SHIFT - PMD_ORDER) - str r3, [r0, #(KERNEL_RAM_VADDR & 0x00f00000) >> (SECTION_SHIFT - PMD_ORDER)]! - ldr r6, =(_end - 1) - add r0, r0, #4 +#define XIP_START XIP_VIRT_ADDR(CONFIG_XIP_PHYS_ADDR) + mov r3, pc + mov r3, r3, lsr #SECTION_SHIFT + orr r3, r7, r3, lsl #SECTION_SHIFT + add r0, r4, #(XIP_START & 0xff000000) >> (SECTION_SHIFT - PMD_ORDER) + str r3, [r0, #((XIP_START & 0x00f00000) >> SECTION_SHIFT) << PMD_ORDER]! + ldr r6, =(_edata_loc - 1) + add r0, r0, #1 << PMD_ORDER add r6, r4, r6, lsr #(SECTION_SHIFT - PMD_ORDER) 1: cmp r0, r6 - add r3, r3, #1 << 20 - strls r3, [r0], #4 + add r3, r3, #1 << SECTION_SHIFT + strls r3, [r0], #1 << PMD_ORDER bls 1b #endif /* - * Then map boot params address in r2 or the first 1MB (2MB with LPAE) - * of ram if boot params address is not specified. + * Then map boot params address in r2 if specified. */ mov r0, r2, lsr #SECTION_SHIFT movs r0, r0, lsl #SECTION_SHIFT - moveq r0, r8 - sub r3, r0, r8 - add r3, r3, #PAGE_OFFSET - add r3, r4, r3, lsr #(SECTION_SHIFT - PMD_ORDER) - orr r6, r7, r0 - str r6, [r3] + subne r3, r0, r8 + addne r3, r3, #PAGE_OFFSET + addne r3, r4, r3, lsr #(SECTION_SHIFT - PMD_ORDER) + orrne r6, r7, r0 + strne r6, [r3] #ifdef CONFIG_DEBUG_LL #if !defined(CONFIG_DEBUG_ICEDCC) && !defined(CONFIG_DEBUG_SEMIHOSTING) diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c index a02eada3aa5d..ab243b87118d 100644 --- a/arch/arm/kernel/perf_event.c +++ b/arch/arm/kernel/perf_event.c @@ -47,17 +47,14 @@ static DEFINE_PER_CPU(struct pmu_hw_events, cpu_hw_events); /* Set at runtime when we know what CPU type we are. */ static struct arm_pmu *cpu_pmu; -enum arm_perf_pmu_ids -armpmu_get_pmu_id(void) +const char *perf_pmu_name(void) { - int id = -ENODEV; - - if (cpu_pmu != NULL) - id = cpu_pmu->id; + if (!cpu_pmu) + return NULL; - return id; + return cpu_pmu->pmu.name; } -EXPORT_SYMBOL_GPL(armpmu_get_pmu_id); +EXPORT_SYMBOL_GPL(perf_pmu_name); int perf_num_counters(void) { @@ -760,7 +757,7 @@ init_hw_perf_events(void) cpu_pmu->name, cpu_pmu->num_events); cpu_pmu_init(cpu_pmu); register_cpu_notifier(&pmu_cpu_notifier); - armpmu_register(cpu_pmu, "cpu", PERF_TYPE_RAW); + armpmu_register(cpu_pmu, cpu_pmu->name, PERF_TYPE_RAW); } else { pr_info("no hardware support available\n"); } diff --git a/arch/arm/kernel/perf_event_v6.c b/arch/arm/kernel/perf_event_v6.c index ab627a740fa3..c90fcb2b6967 100644 --- a/arch/arm/kernel/perf_event_v6.c +++ b/arch/arm/kernel/perf_event_v6.c @@ -650,7 +650,6 @@ static int armv6_map_event(struct perf_event *event) } static struct arm_pmu armv6pmu = { - .id = ARM_PERF_PMU_ID_V6, .name = "v6", .handle_irq = armv6pmu_handle_irq, .enable = armv6pmu_enable_event, @@ -685,7 +684,6 @@ static int armv6mpcore_map_event(struct perf_event *event) } static struct arm_pmu armv6mpcore_pmu = { - .id = ARM_PERF_PMU_ID_V6MP, .name = "v6mpcore", .handle_irq = armv6pmu_handle_irq, .enable = armv6pmu_enable_event, diff --git a/arch/arm/kernel/perf_event_v7.c b/arch/arm/kernel/perf_event_v7.c index d3c536068162..f04070bd2183 100644 --- a/arch/arm/kernel/perf_event_v7.c +++ b/arch/arm/kernel/perf_event_v7.c @@ -1258,7 +1258,6 @@ static u32 __init armv7_read_num_pmnc_events(void) static struct arm_pmu *__init armv7_a8_pmu_init(void) { - armv7pmu.id = ARM_PERF_PMU_ID_CA8; armv7pmu.name = "ARMv7 Cortex-A8"; armv7pmu.map_event = armv7_a8_map_event; armv7pmu.num_events = armv7_read_num_pmnc_events(); @@ -1267,7 +1266,6 @@ static struct arm_pmu *__init armv7_a8_pmu_init(void) static struct arm_pmu *__init armv7_a9_pmu_init(void) { - armv7pmu.id = ARM_PERF_PMU_ID_CA9; armv7pmu.name = "ARMv7 Cortex-A9"; armv7pmu.map_event = armv7_a9_map_event; armv7pmu.num_events = armv7_read_num_pmnc_events(); @@ -1276,7 +1274,6 @@ static struct arm_pmu *__init armv7_a9_pmu_init(void) static struct arm_pmu *__init armv7_a5_pmu_init(void) { - armv7pmu.id = ARM_PERF_PMU_ID_CA5; armv7pmu.name = "ARMv7 Cortex-A5"; armv7pmu.map_event = armv7_a5_map_event; armv7pmu.num_events = armv7_read_num_pmnc_events(); @@ -1285,7 +1282,6 @@ static struct arm_pmu *__init armv7_a5_pmu_init(void) static struct arm_pmu *__init armv7_a15_pmu_init(void) { - armv7pmu.id = ARM_PERF_PMU_ID_CA15; armv7pmu.name = "ARMv7 Cortex-A15"; armv7pmu.map_event = armv7_a15_map_event; armv7pmu.num_events = armv7_read_num_pmnc_events(); @@ -1295,7 +1291,6 @@ static struct arm_pmu *__init armv7_a15_pmu_init(void) static struct arm_pmu *__init armv7_a7_pmu_init(void) { - armv7pmu.id = ARM_PERF_PMU_ID_CA7; armv7pmu.name = "ARMv7 Cortex-A7"; armv7pmu.map_event = armv7_a7_map_event; armv7pmu.num_events = armv7_read_num_pmnc_events(); diff --git a/arch/arm/kernel/perf_event_xscale.c b/arch/arm/kernel/perf_event_xscale.c index e34e7254e652..f759fe0bab63 100644 --- a/arch/arm/kernel/perf_event_xscale.c +++ b/arch/arm/kernel/perf_event_xscale.c @@ -435,7 +435,6 @@ static int xscale_map_event(struct perf_event *event) } static struct arm_pmu xscale1pmu = { - .id = ARM_PERF_PMU_ID_XSCALE1, .name = "xscale1", .handle_irq = xscale1pmu_handle_irq, .enable = xscale1pmu_enable_event, @@ -803,7 +802,6 @@ xscale2pmu_write_counter(int counter, u32 val) } static struct arm_pmu xscale2pmu = { - .id = ARM_PERF_PMU_ID_XSCALE2, .name = "xscale2", .handle_irq = xscale2pmu_handle_irq, .enable = xscale2pmu_enable_event, diff --git a/arch/arm/kernel/ptrace.c b/arch/arm/kernel/ptrace.c index 14e38261cd31..dab711e6e1ca 100644 --- a/arch/arm/kernel/ptrace.c +++ b/arch/arm/kernel/ptrace.c @@ -907,16 +907,16 @@ long arch_ptrace(struct task_struct *child, long request, return ret; } -asmlinkage int syscall_trace(int why, struct pt_regs *regs, int scno) +enum ptrace_syscall_dir { + PTRACE_SYSCALL_ENTER = 0, + PTRACE_SYSCALL_EXIT, +}; + +static int ptrace_syscall_trace(struct pt_regs *regs, int scno, + enum ptrace_syscall_dir dir) { unsigned long ip; - if (why) - audit_syscall_exit(regs); - else - audit_syscall_entry(AUDIT_ARCH_ARM, scno, regs->ARM_r0, - regs->ARM_r1, regs->ARM_r2, regs->ARM_r3); - if (!test_thread_flag(TIF_SYSCALL_TRACE)) return scno; @@ -927,14 +927,28 @@ asmlinkage int syscall_trace(int why, struct pt_regs *regs, int scno) * IP = 0 -> entry, =1 -> exit */ ip = regs->ARM_ip; - regs->ARM_ip = why; + regs->ARM_ip = dir; - if (why) + if (dir == PTRACE_SYSCALL_EXIT) tracehook_report_syscall_exit(regs, 0); else if (tracehook_report_syscall_entry(regs)) current_thread_info()->syscall = -1; regs->ARM_ip = ip; - return current_thread_info()->syscall; } + +asmlinkage int syscall_trace_enter(struct pt_regs *regs, int scno) +{ + int ret = ptrace_syscall_trace(regs, scno, PTRACE_SYSCALL_ENTER); + audit_syscall_entry(AUDIT_ARCH_ARM, scno, regs->ARM_r0, regs->ARM_r1, + regs->ARM_r2, regs->ARM_r3); + return ret; +} + +asmlinkage int syscall_trace_exit(struct pt_regs *regs, int scno) +{ + int ret = ptrace_syscall_trace(regs, scno, PTRACE_SYSCALL_EXIT); + audit_syscall_exit(regs); + return ret; +} diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c index 2c7217d971db..aea74f5bc34a 100644 --- a/arch/arm/kernel/smp.c +++ b/arch/arm/kernel/smp.c @@ -179,7 +179,7 @@ void __ref cpu_die(void) mb(); /* Tell __cpu_die() that this CPU is now safe to dispose of */ - complete(&cpu_died); + RCU_NONIDLE(complete(&cpu_died)); /* * actual CPU shutdown procedure is at least platform (if not diff --git a/arch/arm/kernel/topology.c b/arch/arm/kernel/topology.c index 8200deaa14f6..198b08456e90 100644 --- a/arch/arm/kernel/topology.c +++ b/arch/arm/kernel/topology.c @@ -17,11 +17,190 @@ #include <linux/percpu.h> #include <linux/node.h> #include <linux/nodemask.h> +#include <linux/of.h> #include <linux/sched.h> +#include <linux/slab.h> #include <asm/cputype.h> #include <asm/topology.h> +/* + * cpu power scale management + */ + +/* + * cpu power table + * This per cpu data structure describes the relative capacity of each core. + * On a heteregenous system, cores don't have the same computation capacity + * and we reflect that difference in the cpu_power field so the scheduler can + * take this difference into account during load balance. A per cpu structure + * is preferred because each CPU updates its own cpu_power field during the + * load balance except for idle cores. One idle core is selected to run the + * rebalance_domains for all idle cores and the cpu_power can be updated + * during this sequence. + */ +static DEFINE_PER_CPU(unsigned long, cpu_scale); + +unsigned long arch_scale_freq_power(struct sched_domain *sd, int cpu) +{ + return per_cpu(cpu_scale, cpu); +} + +static void set_power_scale(unsigned int cpu, unsigned long power) +{ + per_cpu(cpu_scale, cpu) = power; +} + +#ifdef CONFIG_OF +struct cpu_efficiency { + const char *compatible; + unsigned long efficiency; +}; + +/* + * Table of relative efficiency of each processors + * The efficiency value must fit in 20bit and the final + * cpu_scale value must be in the range + * 0 < cpu_scale < 3*SCHED_POWER_SCALE/2 + * in order to return at most 1 when DIV_ROUND_CLOSEST + * is used to compute the capacity of a CPU. + * Processors that are not defined in the table, + * use the default SCHED_POWER_SCALE value for cpu_scale. + */ +struct cpu_efficiency table_efficiency[] = { + {"arm,cortex-a15", 3891}, + {"arm,cortex-a7", 2048}, + {NULL, }, +}; + +struct cpu_capacity { + unsigned long hwid; + unsigned long capacity; +}; + +struct cpu_capacity *cpu_capacity; + +unsigned long middle_capacity = 1; + +/* + * Iterate all CPUs' descriptor in DT and compute the efficiency + * (as per table_efficiency). Also calculate a middle efficiency + * as close as possible to (max{eff_i} - min{eff_i}) / 2 + * This is later used to scale the cpu_power field such that an + * 'average' CPU is of middle power. Also see the comments near + * table_efficiency[] and update_cpu_power(). + */ +static void __init parse_dt_topology(void) +{ + struct cpu_efficiency *cpu_eff; + struct device_node *cn = NULL; + unsigned long min_capacity = (unsigned long)(-1); + unsigned long max_capacity = 0; + unsigned long capacity = 0; + int alloc_size, cpu = 0; + + alloc_size = nr_cpu_ids * sizeof(struct cpu_capacity); + cpu_capacity = (struct cpu_capacity *)kzalloc(alloc_size, GFP_NOWAIT); + + while ((cn = of_find_node_by_type(cn, "cpu"))) { + const u32 *rate, *reg; + int len; + + if (cpu >= num_possible_cpus()) + break; + + for (cpu_eff = table_efficiency; cpu_eff->compatible; cpu_eff++) + if (of_device_is_compatible(cn, cpu_eff->compatible)) + break; + + if (cpu_eff->compatible == NULL) + continue; + + rate = of_get_property(cn, "clock-frequency", &len); + if (!rate || len != 4) { + pr_err("%s missing clock-frequency property\n", + cn->full_name); + continue; + } + + reg = of_get_property(cn, "reg", &len); + if (!reg || len != 4) { + pr_err("%s missing reg property\n", cn->full_name); + continue; + } + + capacity = ((be32_to_cpup(rate)) >> 20) * cpu_eff->efficiency; + + /* Save min capacity of the system */ + if (capacity < min_capacity) + min_capacity = capacity; + + /* Save max capacity of the system */ + if (capacity > max_capacity) + max_capacity = capacity; + + cpu_capacity[cpu].capacity = capacity; + cpu_capacity[cpu++].hwid = be32_to_cpup(reg); + } + + if (cpu < num_possible_cpus()) + cpu_capacity[cpu].hwid = (unsigned long)(-1); + + /* If min and max capacities are equals, we bypass the update of the + * cpu_scale because all CPUs have the same capacity. Otherwise, we + * compute a middle_capacity factor that will ensure that the capacity + * of an 'average' CPU of the system will be as close as possible to + * SCHED_POWER_SCALE, which is the default value, but with the + * constraint explained near table_efficiency[]. + */ + if (min_capacity == max_capacity) + cpu_capacity[0].hwid = (unsigned long)(-1); + else if (4*max_capacity < (3*(max_capacity + min_capacity))) + middle_capacity = (min_capacity + max_capacity) + >> (SCHED_POWER_SHIFT+1); + else + middle_capacity = ((max_capacity / 3) + >> (SCHED_POWER_SHIFT-1)) + 1; + +} + +/* + * Look for a customed capacity of a CPU in the cpu_capacity table during the + * boot. The update of all CPUs is in O(n^2) for heteregeneous system but the + * function returns directly for SMP system. + */ +void update_cpu_power(unsigned int cpu, unsigned long hwid) +{ + unsigned int idx = 0; + + /* look for the cpu's hwid in the cpu capacity table */ + for (idx = 0; idx < num_possible_cpus(); idx++) { + if (cpu_capacity[idx].hwid == hwid) + break; + + if (cpu_capacity[idx].hwid == -1) + return; + } + + if (idx == num_possible_cpus()) + return; + + set_power_scale(cpu, cpu_capacity[idx].capacity / middle_capacity); + + printk(KERN_INFO "CPU%u: update cpu_power %lu\n", + cpu, arch_scale_freq_power(NULL, cpu)); +} + +#else +static inline void parse_dt_topology(void) {} +static inline void update_cpu_power(unsigned int cpuid, unsigned int mpidr) {} +#endif + + +/* + * cpu topology management + */ + #define MPIDR_SMP_BITMASK (0x3 << 30) #define MPIDR_SMP_VALUE (0x2 << 30) @@ -31,6 +210,7 @@ * These masks reflect the current use of the affinity levels. * The affinity level can be up to 16 bits according to ARM ARM */ +#define MPIDR_HWID_BITMASK 0xFFFFFF #define MPIDR_LEVEL0_MASK 0x3 #define MPIDR_LEVEL0_SHIFT 0 @@ -41,6 +221,9 @@ #define MPIDR_LEVEL2_MASK 0xFF #define MPIDR_LEVEL2_SHIFT 16 +/* + * cpu topology table + */ struct cputopo_arm cpu_topology[NR_CPUS]; const struct cpumask *cpu_coregroup_mask(int cpu) @@ -48,6 +231,32 @@ const struct cpumask *cpu_coregroup_mask(int cpu) return &cpu_topology[cpu].core_sibling; } +void update_siblings_masks(unsigned int cpuid) +{ + struct cputopo_arm *cpu_topo, *cpuid_topo = &cpu_topology[cpuid]; + int cpu; + + /* update core and thread sibling masks */ + for_each_possible_cpu(cpu) { + cpu_topo = &cpu_topology[cpu]; + + if (cpuid_topo->socket_id != cpu_topo->socket_id) + continue; + + cpumask_set_cpu(cpuid, &cpu_topo->core_sibling); + if (cpu != cpuid) + cpumask_set_cpu(cpu, &cpuid_topo->core_sibling); + + if (cpuid_topo->core_id != cpu_topo->core_id) + continue; + + cpumask_set_cpu(cpuid, &cpu_topo->thread_sibling); + if (cpu != cpuid) + cpumask_set_cpu(cpu, &cpuid_topo->thread_sibling); + } + smp_wmb(); +} + /* * store_cpu_topology is called at boot when only one cpu is running * and with the mutex cpu_hotplug.lock locked, when several cpus have booted, @@ -57,7 +266,6 @@ void store_cpu_topology(unsigned int cpuid) { struct cputopo_arm *cpuid_topo = &cpu_topology[cpuid]; unsigned int mpidr; - unsigned int cpu; /* If the cpu topology has been already set, just return */ if (cpuid_topo->core_id != -1) @@ -99,26 +307,9 @@ void store_cpu_topology(unsigned int cpuid) cpuid_topo->socket_id = -1; } - /* update core and thread sibling masks */ - for_each_possible_cpu(cpu) { - struct cputopo_arm *cpu_topo = &cpu_topology[cpu]; - - if (cpuid_topo->socket_id == cpu_topo->socket_id) { - cpumask_set_cpu(cpuid, &cpu_topo->core_sibling); - if (cpu != cpuid) - cpumask_set_cpu(cpu, - &cpuid_topo->core_sibling); - - if (cpuid_topo->core_id == cpu_topo->core_id) { - cpumask_set_cpu(cpuid, - &cpu_topo->thread_sibling); - if (cpu != cpuid) - cpumask_set_cpu(cpu, - &cpuid_topo->thread_sibling); - } - } - } - smp_wmb(); + update_siblings_masks(cpuid); + + update_cpu_power(cpuid, mpidr & MPIDR_HWID_BITMASK); printk(KERN_INFO "CPU%u: thread %d, cpu %d, socket %d, mpidr %x\n", cpuid, cpu_topology[cpuid].thread_id, @@ -134,7 +325,7 @@ void init_cpu_topology(void) { unsigned int cpu; - /* init core mask */ + /* init core mask and power*/ for_each_possible_cpu(cpu) { struct cputopo_arm *cpu_topo = &(cpu_topology[cpu]); @@ -143,6 +334,10 @@ void init_cpu_topology(void) cpu_topo->socket_id = -1; cpumask_clear(&cpu_topo->core_sibling); cpumask_clear(&cpu_topo->thread_sibling); + + set_power_scale(cpu, SCHED_POWER_SCALE); } smp_wmb(); + + parse_dt_topology(); } diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c index 3647170e9a16..8b97d739b17b 100644 --- a/arch/arm/kernel/traps.c +++ b/arch/arm/kernel/traps.c @@ -233,9 +233,9 @@ void show_stack(struct task_struct *tsk, unsigned long *sp) #define S_ISA " ARM" #endif -static int __die(const char *str, int err, struct thread_info *thread, struct pt_regs *regs) +static int __die(const char *str, int err, struct pt_regs *regs) { - struct task_struct *tsk = thread->task; + struct task_struct *tsk = current; static int die_counter; int ret; @@ -245,12 +245,12 @@ static int __die(const char *str, int err, struct thread_info *thread, struct pt /* trap and error numbers are mostly meaningless on ARM */ ret = notify_die(DIE_OOPS, str, regs, err, tsk->thread.trap_no, SIGSEGV); if (ret == NOTIFY_STOP) - return ret; + return 1; print_modules(); __show_regs(regs); printk(KERN_EMERG "Process %.*s (pid: %d, stack limit = 0x%p)\n", - TASK_COMM_LEN, tsk->comm, task_pid_nr(tsk), thread + 1); + TASK_COMM_LEN, tsk->comm, task_pid_nr(tsk), end_of_stack(tsk)); if (!user_mode(regs) || in_interrupt()) { dump_mem(KERN_EMERG, "Stack: ", regs->ARM_sp, @@ -259,45 +259,77 @@ static int __die(const char *str, int err, struct thread_info *thread, struct pt dump_instr(KERN_EMERG, regs); } - return ret; + return 0; } -static DEFINE_RAW_SPINLOCK(die_lock); +static arch_spinlock_t die_lock = __ARCH_SPIN_LOCK_UNLOCKED; +static int die_owner = -1; +static unsigned int die_nest_count; -/* - * This function is protected against re-entrancy. - */ -void die(const char *str, struct pt_regs *regs, int err) +static unsigned long oops_begin(void) { - struct thread_info *thread = current_thread_info(); - int ret; - enum bug_trap_type bug_type = BUG_TRAP_TYPE_NONE; + int cpu; + unsigned long flags; oops_enter(); - raw_spin_lock_irq(&die_lock); + /* racy, but better than risking deadlock. */ + raw_local_irq_save(flags); + cpu = smp_processor_id(); + if (!arch_spin_trylock(&die_lock)) { + if (cpu == die_owner) + /* nested oops. should stop eventually */; + else + arch_spin_lock(&die_lock); + } + die_nest_count++; + die_owner = cpu; console_verbose(); bust_spinlocks(1); - if (!user_mode(regs)) - bug_type = report_bug(regs->ARM_pc, regs); - if (bug_type != BUG_TRAP_TYPE_NONE) - str = "Oops - BUG"; - ret = __die(str, err, thread, regs); + return flags; +} - if (regs && kexec_should_crash(thread->task)) +static void oops_end(unsigned long flags, struct pt_regs *regs, int signr) +{ + if (regs && kexec_should_crash(current)) crash_kexec(regs); bust_spinlocks(0); + die_owner = -1; add_taint(TAINT_DIE); - raw_spin_unlock_irq(&die_lock); + die_nest_count--; + if (!die_nest_count) + /* Nest count reaches zero, release the lock. */ + arch_spin_unlock(&die_lock); + raw_local_irq_restore(flags); oops_exit(); if (in_interrupt()) panic("Fatal exception in interrupt"); if (panic_on_oops) panic("Fatal exception"); - if (ret != NOTIFY_STOP) - do_exit(SIGSEGV); + if (signr) + do_exit(signr); +} + +/* + * This function is protected against re-entrancy. + */ +void die(const char *str, struct pt_regs *regs, int err) +{ + enum bug_trap_type bug_type = BUG_TRAP_TYPE_NONE; + unsigned long flags = oops_begin(); + int sig = SIGSEGV; + + if (!user_mode(regs)) + bug_type = report_bug(regs->ARM_pc, regs); + if (bug_type != BUG_TRAP_TYPE_NONE) + str = "Oops - BUG"; + + if (__die(str, err, regs)) + sig = 0; + + oops_end(flags, regs, sig); } void arm_notify_die(const char *str, struct pt_regs *regs, diff --git a/arch/arm/lib/Makefile b/arch/arm/lib/Makefile index 992769ae2599..2473fd1fd51c 100644 --- a/arch/arm/lib/Makefile +++ b/arch/arm/lib/Makefile @@ -6,9 +6,8 @@ lib-y := backtrace.o changebit.o csumipv6.o csumpartial.o \ csumpartialcopy.o csumpartialcopyuser.o clearbit.o \ - delay.o findbit.o memchr.o memcpy.o \ + delay.o delay-loop.o findbit.o memchr.o memcpy.o \ memmove.o memset.o memzero.o setbit.o \ - strncpy_from_user.o strnlen_user.o \ strchr.o strrchr.o \ testchangebit.o testclearbit.o testsetbit.o \ ashldi3.o ashrdi3.o lshrdi3.o muldi3.o \ diff --git a/arch/arm/lib/delay.S b/arch/arm/lib/delay-loop.S index 3c9a05c8d20b..36b668d8e121 100644 --- a/arch/arm/lib/delay.S +++ b/arch/arm/lib/delay-loop.S @@ -9,11 +9,11 @@ */ #include <linux/linkage.h> #include <asm/assembler.h> -#include <asm/param.h> +#include <asm/delay.h> .text .LC0: .word loops_per_jiffy -.LC1: .word (2199023*HZ)>>11 +.LC1: .word UDELAY_MULT /* * r0 <= 2000 @@ -21,10 +21,10 @@ * HZ <= 1000 */ -ENTRY(__udelay) +ENTRY(__loop_udelay) ldr r2, .LC1 mul r0, r2, r0 -ENTRY(__const_udelay) @ 0 <= r0 <= 0x7fffff06 +ENTRY(__loop_const_udelay) @ 0 <= r0 <= 0x7fffff06 mov r1, #-1 ldr r2, .LC0 ldr r2, [r2] @ max = 0x01ffffff @@ -39,12 +39,10 @@ ENTRY(__const_udelay) @ 0 <= r0 <= 0x7fffff06 /* * loops = r0 * HZ * loops_per_jiffy / 1000000 - * - * Oh, if only we had a cycle counter... */ @ Delay routine -ENTRY(__delay) +ENTRY(__loop_delay) subs r0, r0, #1 #if 0 movls pc, lr @@ -62,8 +60,8 @@ ENTRY(__delay) movls pc, lr subs r0, r0, #1 #endif - bhi __delay + bhi __loop_delay mov pc, lr -ENDPROC(__udelay) -ENDPROC(__const_udelay) -ENDPROC(__delay) +ENDPROC(__loop_udelay) +ENDPROC(__loop_const_udelay) +ENDPROC(__loop_delay) diff --git a/arch/arm/lib/delay.c b/arch/arm/lib/delay.c new file mode 100644 index 000000000000..d6dacc69254e --- /dev/null +++ b/arch/arm/lib/delay.c @@ -0,0 +1,71 @@ +/* + * Delay loops based on the OpenRISC implementation. + * + * Copyright (C) 2012 ARM Limited + * + * 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 + * + * Author: Will Deacon <will.deacon@arm.com> + */ + +#include <linux/delay.h> +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/timex.h> + +/* + * Default to the loop-based delay implementation. + */ +struct arm_delay_ops arm_delay_ops = { + .delay = __loop_delay, + .const_udelay = __loop_const_udelay, + .udelay = __loop_udelay, +}; + +#ifdef ARCH_HAS_READ_CURRENT_TIMER +static void __timer_delay(unsigned long cycles) +{ + cycles_t start = get_cycles(); + + while ((get_cycles() - start) < cycles) + cpu_relax(); +} + +static void __timer_const_udelay(unsigned long xloops) +{ + unsigned long long loops = xloops; + loops *= loops_per_jiffy; + __timer_delay(loops >> UDELAY_SHIFT); +} + +static void __timer_udelay(unsigned long usecs) +{ + __timer_const_udelay(usecs * UDELAY_MULT); +} + +void __init init_current_timer_delay(unsigned long freq) +{ + pr_info("Switching to timer-based delay loop\n"); + lpj_fine = freq / HZ; + arm_delay_ops.delay = __timer_delay; + arm_delay_ops.const_udelay = __timer_const_udelay; + arm_delay_ops.udelay = __timer_udelay; +} + +unsigned long __cpuinit calibrate_delay_is_known(void) +{ + return lpj_fine; +} +#endif diff --git a/arch/arm/lib/strncpy_from_user.S b/arch/arm/lib/strncpy_from_user.S deleted file mode 100644 index f202d7bd1647..000000000000 --- a/arch/arm/lib/strncpy_from_user.S +++ /dev/null @@ -1,43 +0,0 @@ -/* - * linux/arch/arm/lib/strncpy_from_user.S - * - * Copyright (C) 1995-2000 Russell King - * - * 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/linkage.h> -#include <asm/assembler.h> -#include <asm/errno.h> - - .text - .align 5 - -/* - * Copy a string from user space to kernel space. - * r0 = dst, r1 = src, r2 = byte length - * returns the number of characters copied (strlen of copied string), - * -EFAULT on exception, or "len" if we fill the whole buffer - */ -ENTRY(__strncpy_from_user) - mov ip, r1 -1: subs r2, r2, #1 - ldrusr r3, r1, 1, pl - bmi 2f - strb r3, [r0], #1 - teq r3, #0 - bne 1b - sub r1, r1, #1 @ take NUL character out of count -2: sub r0, r1, ip - mov pc, lr -ENDPROC(__strncpy_from_user) - - .pushsection .fixup,"ax" - .align 0 -9001: mov r3, #0 - strb r3, [r0, #0] @ null terminate - mov r0, #-EFAULT - mov pc, lr - .popsection - diff --git a/arch/arm/lib/strnlen_user.S b/arch/arm/lib/strnlen_user.S deleted file mode 100644 index 0ecbb459c4f1..000000000000 --- a/arch/arm/lib/strnlen_user.S +++ /dev/null @@ -1,40 +0,0 @@ -/* - * linux/arch/arm/lib/strnlen_user.S - * - * Copyright (C) 1995-2000 Russell King - * - * 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/linkage.h> -#include <asm/assembler.h> -#include <asm/errno.h> - - .text - .align 5 - -/* Prototype: unsigned long __strnlen_user(const char *str, long n) - * Purpose : get length of a string in user memory - * Params : str - address of string in user memory - * Returns : length of string *including terminator* - * or zero on exception, or n + 1 if too long - */ -ENTRY(__strnlen_user) - mov r2, r0 -1: - ldrusr r3, r0, 1 - teq r3, #0 - beq 2f - subs r1, r1, #1 - bne 1b - add r0, r0, #1 -2: sub r0, r0, r2 - mov pc, lr -ENDPROC(__strnlen_user) - - .pushsection .fixup,"ax" - .align 0 -9001: mov r0, #0 - mov pc, lr - .popsection diff --git a/arch/arm/mach-msm/platsmp.c b/arch/arm/mach-msm/platsmp.c index db0117ec55f4..e012dc8391cf 100644 --- a/arch/arm/mach-msm/platsmp.c +++ b/arch/arm/mach-msm/platsmp.c @@ -127,7 +127,7 @@ int __cpuinit boot_secondary(unsigned int cpu, struct task_struct *idle) * the boot monitor to read the system wide flags register, * and branch to the address found there. */ - gic_raise_softirq(cpumask_of(cpu), 1); + gic_raise_softirq(cpumask_of(cpu), 0); timeout = jiffies + (1 * HZ); while (time_before(jiffies, timeout)) { diff --git a/arch/arm/mach-omap2/omap-smp.c b/arch/arm/mach-omap2/omap-smp.c index 7d118b9bdd5f..9a35adf91232 100644 --- a/arch/arm/mach-omap2/omap-smp.c +++ b/arch/arm/mach-omap2/omap-smp.c @@ -125,7 +125,7 @@ int __cpuinit boot_secondary(unsigned int cpu, struct task_struct *idle) booted = true; } - gic_raise_softirq(cpumask_of(cpu), 1); + gic_raise_softirq(cpumask_of(cpu), 0); /* * Now the secondary core is starting up let it run its diff --git a/arch/arm/mach-pxa/include/mach/regs-ost.h b/arch/arm/mach-pxa/include/mach/regs-ost.h index a3e5f86ef67e..628819995c52 100644 --- a/arch/arm/mach-pxa/include/mach/regs-ost.h +++ b/arch/arm/mach-pxa/include/mach/regs-ost.h @@ -7,17 +7,17 @@ * OS Timer & Match Registers */ -#define OSMR0 __REG(0x40A00000) /* */ -#define OSMR1 __REG(0x40A00004) /* */ -#define OSMR2 __REG(0x40A00008) /* */ -#define OSMR3 __REG(0x40A0000C) /* */ -#define OSMR4 __REG(0x40A00080) /* */ -#define OSCR __REG(0x40A00010) /* OS Timer Counter Register */ -#define OSCR4 __REG(0x40A00040) /* OS Timer Counter Register */ -#define OMCR4 __REG(0x40A000C0) /* */ -#define OSSR __REG(0x40A00014) /* OS Timer Status Register */ -#define OWER __REG(0x40A00018) /* OS Timer Watchdog Enable Register */ -#define OIER __REG(0x40A0001C) /* OS Timer Interrupt Enable Register */ +#define OSMR0 io_p2v(0x40A00000) /* */ +#define OSMR1 io_p2v(0x40A00004) /* */ +#define OSMR2 io_p2v(0x40A00008) /* */ +#define OSMR3 io_p2v(0x40A0000C) /* */ +#define OSMR4 io_p2v(0x40A00080) /* */ +#define OSCR io_p2v(0x40A00010) /* OS Timer Counter Register */ +#define OSCR4 io_p2v(0x40A00040) /* OS Timer Counter Register */ +#define OMCR4 io_p2v(0x40A000C0) /* */ +#define OSSR io_p2v(0x40A00014) /* OS Timer Status Register */ +#define OWER io_p2v(0x40A00018) /* OS Timer Watchdog Enable Register */ +#define OIER io_p2v(0x40A0001C) /* OS Timer Interrupt Enable Register */ #define OSSR_M3 (1 << 3) /* Match status channel 3 */ #define OSSR_M2 (1 << 2) /* Match status channel 2 */ diff --git a/arch/arm/mach-pxa/reset.c b/arch/arm/mach-pxa/reset.c index b4528899ef08..3fab583755d4 100644 --- a/arch/arm/mach-pxa/reset.c +++ b/arch/arm/mach-pxa/reset.c @@ -77,9 +77,10 @@ static void do_gpio_reset(void) static void do_hw_reset(void) { /* Initialize the watchdog and let it fire */ - OWER = OWER_WME; - OSSR = OSSR_M3; - OSMR3 = OSCR + 368640; /* ... in 100 ms */ + writel_relaxed(OWER_WME, OWER); + writel_relaxed(OSSR_M3, OSSR); + /* ... in 100 ms */ + writel_relaxed(readl_relaxed(OSCR) + 368640, OSMR3); } void pxa_restart(char mode, const char *cmd) diff --git a/arch/arm/mach-pxa/time.c b/arch/arm/mach-pxa/time.c index 3d6c9bd90de6..4bc47d63698b 100644 --- a/arch/arm/mach-pxa/time.c +++ b/arch/arm/mach-pxa/time.c @@ -35,7 +35,7 @@ static u32 notrace pxa_read_sched_clock(void) { - return OSCR; + return readl_relaxed(OSCR); } @@ -47,8 +47,8 @@ pxa_ost0_interrupt(int irq, void *dev_id) struct clock_event_device *c = dev_id; /* Disarm the compare/match, signal the event. */ - OIER &= ~OIER_E0; - OSSR = OSSR_M0; + writel_relaxed(readl_relaxed(OIER) & ~OIER_E0, OIER); + writel_relaxed(OSSR_M0, OSSR); c->event_handler(c); return IRQ_HANDLED; @@ -59,10 +59,10 @@ pxa_osmr0_set_next_event(unsigned long delta, struct clock_event_device *dev) { unsigned long next, oscr; - OIER |= OIER_E0; - next = OSCR + delta; - OSMR0 = next; - oscr = OSCR; + writel_relaxed(readl_relaxed(OIER) | OIER_E0, OIER); + next = readl_relaxed(OSCR) + delta; + writel_relaxed(next, OSMR0); + oscr = readl_relaxed(OSCR); return (signed)(next - oscr) <= MIN_OSCR_DELTA ? -ETIME : 0; } @@ -72,15 +72,15 @@ pxa_osmr0_set_mode(enum clock_event_mode mode, struct clock_event_device *dev) { switch (mode) { case CLOCK_EVT_MODE_ONESHOT: - OIER &= ~OIER_E0; - OSSR = OSSR_M0; + writel_relaxed(readl_relaxed(OIER) & ~OIER_E0, OIER); + writel_relaxed(OSSR_M0, OSSR); break; case CLOCK_EVT_MODE_UNUSED: case CLOCK_EVT_MODE_SHUTDOWN: /* initializing, released, or preparing for suspend */ - OIER &= ~OIER_E0; - OSSR = OSSR_M0; + writel_relaxed(readl_relaxed(OIER) & ~OIER_E0, OIER); + writel_relaxed(OSSR_M0, OSSR); break; case CLOCK_EVT_MODE_RESUME: @@ -108,8 +108,8 @@ static void __init pxa_timer_init(void) { unsigned long clock_tick_rate = get_clock_tick_rate(); - OIER = 0; - OSSR = OSSR_M0 | OSSR_M1 | OSSR_M2 | OSSR_M3; + writel_relaxed(0, OIER); + writel_relaxed(OSSR_M0 | OSSR_M1 | OSSR_M2 | OSSR_M3, OSSR); setup_sched_clock(pxa_read_sched_clock, 32, clock_tick_rate); @@ -122,7 +122,7 @@ static void __init pxa_timer_init(void) setup_irq(IRQ_OST0, &pxa_ost0_irq); - clocksource_mmio_init(&OSCR, "oscr0", clock_tick_rate, 200, 32, + clocksource_mmio_init(OSCR, "oscr0", clock_tick_rate, 200, 32, clocksource_mmio_readl_up); clockevents_register_device(&ckevt_pxa_osmr0); } @@ -132,12 +132,12 @@ static unsigned long osmr[4], oier, oscr; static void pxa_timer_suspend(void) { - osmr[0] = OSMR0; - osmr[1] = OSMR1; - osmr[2] = OSMR2; - osmr[3] = OSMR3; - oier = OIER; - oscr = OSCR; + osmr[0] = readl_relaxed(OSMR0); + osmr[1] = readl_relaxed(OSMR1); + osmr[2] = readl_relaxed(OSMR2); + osmr[3] = readl_relaxed(OSMR3); + oier = readl_relaxed(OIER); + oscr = readl_relaxed(OSCR); } static void pxa_timer_resume(void) @@ -151,12 +151,12 @@ static void pxa_timer_resume(void) if (osmr[0] - oscr < MIN_OSCR_DELTA) osmr[0] += MIN_OSCR_DELTA; - OSMR0 = osmr[0]; - OSMR1 = osmr[1]; - OSMR2 = osmr[2]; - OSMR3 = osmr[3]; - OIER = oier; - OSCR = oscr; + writel_relaxed(osmr[0], OSMR0); + writel_relaxed(osmr[1], OSMR1); + writel_relaxed(osmr[2], OSMR2); + writel_relaxed(osmr[3], OSMR3); + writel_relaxed(oier, OIER); + writel_relaxed(oscr, OSCR); } #else #define pxa_timer_suspend NULL diff --git a/arch/arm/mach-sa1100/assabet.c b/arch/arm/mach-sa1100/assabet.c index d1dc7f1a239c..d673211f121c 100644 --- a/arch/arm/mach-sa1100/assabet.c +++ b/arch/arm/mach-sa1100/assabet.c @@ -362,7 +362,7 @@ static void __init assabet_init(void) static void __init map_sa1100_gpio_regs( void ) { unsigned long phys = __PREG(GPLR) & PMD_MASK; - unsigned long virt = io_p2v(phys); + unsigned long virt = (unsigned long)io_p2v(phys); int prot = PMD_TYPE_SECT | PMD_SECT_AP_WRITE | PMD_DOMAIN(DOMAIN_IO); pmd_t *pmd; diff --git a/arch/arm/mach-sa1100/cpu-sa1100.c b/arch/arm/mach-sa1100/cpu-sa1100.c index 19b2053f5af4..e8f4d1e19233 100644 --- a/arch/arm/mach-sa1100/cpu-sa1100.c +++ b/arch/arm/mach-sa1100/cpu-sa1100.c @@ -87,6 +87,7 @@ #include <linux/types.h> #include <linux/init.h> #include <linux/cpufreq.h> +#include <linux/io.h> #include <asm/cputype.h> diff --git a/arch/arm/mach-sa1100/cpu-sa1110.c b/arch/arm/mach-sa1100/cpu-sa1110.c index 675bf8ef97e8..48c45b0c92bb 100644 --- a/arch/arm/mach-sa1100/cpu-sa1110.c +++ b/arch/arm/mach-sa1100/cpu-sa1110.c @@ -19,6 +19,7 @@ #include <linux/cpufreq.h> #include <linux/delay.h> #include <linux/init.h> +#include <linux/io.h> #include <linux/kernel.h> #include <linux/moduleparam.h> #include <linux/types.h> diff --git a/arch/arm/mach-sa1100/include/mach/SA-1100.h b/arch/arm/mach-sa1100/include/mach/SA-1100.h index 3f2d1b60188c..0ac6cc08a19c 100644 --- a/arch/arm/mach-sa1100/include/mach/SA-1100.h +++ b/arch/arm/mach-sa1100/include/mach/SA-1100.h @@ -830,14 +830,14 @@ * (read/write). */ -#define OSMR0 __REG(0x90000000) /* OS timer Match Reg. 0 */ -#define OSMR1 __REG(0x90000004) /* OS timer Match Reg. 1 */ -#define OSMR2 __REG(0x90000008) /* OS timer Match Reg. 2 */ -#define OSMR3 __REG(0x9000000c) /* OS timer Match Reg. 3 */ -#define OSCR __REG(0x90000010) /* OS timer Counter Reg. */ -#define OSSR __REG(0x90000014 ) /* OS timer Status Reg. */ -#define OWER __REG(0x90000018 ) /* OS timer Watch-dog Enable Reg. */ -#define OIER __REG(0x9000001C ) /* OS timer Interrupt Enable Reg. */ +#define OSMR0 io_p2v(0x90000000) /* OS timer Match Reg. 0 */ +#define OSMR1 io_p2v(0x90000004) /* OS timer Match Reg. 1 */ +#define OSMR2 io_p2v(0x90000008) /* OS timer Match Reg. 2 */ +#define OSMR3 io_p2v(0x9000000c) /* OS timer Match Reg. 3 */ +#define OSCR io_p2v(0x90000010) /* OS timer Counter Reg. */ +#define OSSR io_p2v(0x90000014) /* OS timer Status Reg. */ +#define OWER io_p2v(0x90000018) /* OS timer Watch-dog Enable Reg. */ +#define OIER io_p2v(0x9000001C) /* OS timer Interrupt Enable Reg. */ #define OSSR_M(Nb) /* Match detected [0..3] */ \ (0x00000001 << (Nb)) diff --git a/arch/arm/mach-sa1100/include/mach/gpio.h b/arch/arm/mach-sa1100/include/mach/gpio.h index a38fc4f54241..6a9eecf3137e 100644 --- a/arch/arm/mach-sa1100/include/mach/gpio.h +++ b/arch/arm/mach-sa1100/include/mach/gpio.h @@ -24,6 +24,7 @@ #ifndef __ASM_ARCH_SA1100_GPIO_H #define __ASM_ARCH_SA1100_GPIO_H +#include <linux/io.h> #include <mach/hardware.h> #include <asm/irq.h> #include <asm-generic/gpio.h> diff --git a/arch/arm/mach-sa1100/include/mach/hardware.h b/arch/arm/mach-sa1100/include/mach/hardware.h index 99f5856d8de4..cbedd75a9d65 100644 --- a/arch/arm/mach-sa1100/include/mach/hardware.h +++ b/arch/arm/mach-sa1100/include/mach/hardware.h @@ -32,7 +32,7 @@ #define PIO_START 0x80000000 /* physical start of IO space */ #define io_p2v( x ) \ - ( (((x)&0x00ffffff) | (((x)&0x30000000)>>VIO_SHIFT)) + VIO_BASE ) + IOMEM( (((x)&0x00ffffff) | (((x)&0x30000000)>>VIO_SHIFT)) + VIO_BASE ) #define io_v2p( x ) \ ( (((x)&0x00ffffff) | (((x)&(0x30000000>>VIO_SHIFT))<<VIO_SHIFT)) + PIO_START ) @@ -47,6 +47,8 @@ #define CPU_SA1110_ID (0x6901b110) #define CPU_SA1110_MASK (0xfffffff0) +#define __MREG(x) IOMEM(io_p2v(x)) + #ifndef __ASSEMBLY__ #include <asm/cputype.h> @@ -56,7 +58,7 @@ #define cpu_is_sa1100() ((read_cpuid_id() & CPU_SA1100_MASK) == CPU_SA1100_ID) #define cpu_is_sa1110() ((read_cpuid_id() & CPU_SA1110_MASK) == CPU_SA1110_ID) -# define __REG(x) (*((volatile unsigned long *)io_p2v(x))) +# define __REG(x) (*((volatile unsigned long __iomem *)io_p2v(x))) # define __PREG(x) (io_v2p((unsigned long)&(x))) static inline unsigned long get_clock_tick_rate(void) diff --git a/arch/arm/mach-sa1100/include/mach/uncompress.h b/arch/arm/mach-sa1100/include/mach/uncompress.h index 6cb39ddde656..5cf71da60e42 100644 --- a/arch/arm/mach-sa1100/include/mach/uncompress.h +++ b/arch/arm/mach-sa1100/include/mach/uncompress.h @@ -8,6 +8,8 @@ #include "hardware.h" +#define IOMEM(x) (x) + /* * The following code assumes the serial port has already been * initialized by the bootloader. We search for the first enabled diff --git a/arch/arm/mach-sa1100/irq.c b/arch/arm/mach-sa1100/irq.c index 516ccc25d7fd..2124f1fc2fbe 100644 --- a/arch/arm/mach-sa1100/irq.c +++ b/arch/arm/mach-sa1100/irq.c @@ -12,6 +12,7 @@ #include <linux/init.h> #include <linux/module.h> #include <linux/interrupt.h> +#include <linux/io.h> #include <linux/irq.h> #include <linux/ioport.h> #include <linux/syscore_ops.h> diff --git a/arch/arm/mach-sa1100/jornada720_ssp.c b/arch/arm/mach-sa1100/jornada720_ssp.c index b412fc09c80c..7f07f08d8968 100644 --- a/arch/arm/mach-sa1100/jornada720_ssp.c +++ b/arch/arm/mach-sa1100/jornada720_ssp.c @@ -18,6 +18,7 @@ #include <linux/module.h> #include <linux/platform_device.h> #include <linux/sched.h> +#include <linux/io.h> #include <mach/hardware.h> #include <mach/jornada720.h> diff --git a/arch/arm/mach-sa1100/leds-cerf.c b/arch/arm/mach-sa1100/leds-cerf.c index 040540fb7d8a..30fc3b2bf555 100644 --- a/arch/arm/mach-sa1100/leds-cerf.c +++ b/arch/arm/mach-sa1100/leds-cerf.c @@ -4,6 +4,7 @@ * Author: ??? */ #include <linux/init.h> +#include <linux/io.h> #include <mach/hardware.h> #include <asm/leds.h> diff --git a/arch/arm/mach-sa1100/leds-lart.c b/arch/arm/mach-sa1100/leds-lart.c index a51830c60e53..50a5b143b460 100644 --- a/arch/arm/mach-sa1100/leds-lart.c +++ b/arch/arm/mach-sa1100/leds-lart.c @@ -10,6 +10,7 @@ * pace of the LED. */ #include <linux/init.h> +#include <linux/io.h> #include <mach/hardware.h> #include <asm/leds.h> diff --git a/arch/arm/mach-sa1100/pm.c b/arch/arm/mach-sa1100/pm.c index 690cf0ce5c0c..6645d1e31f14 100644 --- a/arch/arm/mach-sa1100/pm.c +++ b/arch/arm/mach-sa1100/pm.c @@ -23,6 +23,7 @@ * Storage is local on the stack now. */ #include <linux/init.h> +#include <linux/io.h> #include <linux/suspend.h> #include <linux/errno.h> #include <linux/time.h> diff --git a/arch/arm/mach-sa1100/sleep.S b/arch/arm/mach-sa1100/sleep.S index 30cc6721665b..85863741ef8b 100644 --- a/arch/arm/mach-sa1100/sleep.S +++ b/arch/arm/mach-sa1100/sleep.S @@ -38,9 +38,9 @@ ENTRY(sa1100_finish_suspend) orr r4, r4, #MDREFR_K1DB2 ldr r5, =PPCR - @ Pre-load __udelay into the I-cache + @ Pre-load __loop_udelay into the I-cache mov r0, #1 - bl __udelay + bl __loop_udelay mov r0, r0 @ The following must all exist in a single cache line to @@ -53,11 +53,11 @@ ENTRY(sa1100_finish_suspend) @ delay 90us and set CPU PLL to lowest speed @ fixes resume problem on high speed SA1110 mov r0, #90 - bl __udelay + bl __loop_udelay mov r1, #0 str r1, [r5] mov r0, #90 - bl __udelay + bl __loop_udelay /* * SA1110 SDRAM controller workaround. register values: diff --git a/arch/arm/mach-sa1100/time.c b/arch/arm/mach-sa1100/time.c index 6af26e8d55e6..80702c9ecc77 100644 --- a/arch/arm/mach-sa1100/time.c +++ b/arch/arm/mach-sa1100/time.c @@ -22,7 +22,7 @@ static u32 notrace sa1100_read_sched_clock(void) { - return OSCR; + return readl_relaxed(OSCR); } #define MIN_OSCR_DELTA 2 @@ -32,8 +32,8 @@ static irqreturn_t sa1100_ost0_interrupt(int irq, void *dev_id) struct clock_event_device *c = dev_id; /* Disarm the compare/match, signal the event. */ - OIER &= ~OIER_E0; - OSSR = OSSR_M0; + writel_relaxed(readl_relaxed(OIER) & ~OIER_E0, OIER); + writel_relaxed(OSSR_M0, OSSR); c->event_handler(c); return IRQ_HANDLED; @@ -44,10 +44,10 @@ sa1100_osmr0_set_next_event(unsigned long delta, struct clock_event_device *c) { unsigned long next, oscr; - OIER |= OIER_E0; - next = OSCR + delta; - OSMR0 = next; - oscr = OSCR; + writel_relaxed(readl_relaxed(OIER) | OIER_E0, OIER); + next = readl_relaxed(OSCR) + delta; + writel_relaxed(next, OSMR0); + oscr = readl_relaxed(OSCR); return (signed)(next - oscr) <= MIN_OSCR_DELTA ? -ETIME : 0; } @@ -59,8 +59,8 @@ sa1100_osmr0_set_mode(enum clock_event_mode mode, struct clock_event_device *c) case CLOCK_EVT_MODE_ONESHOT: case CLOCK_EVT_MODE_UNUSED: case CLOCK_EVT_MODE_SHUTDOWN: - OIER &= ~OIER_E0; - OSSR = OSSR_M0; + writel_relaxed(readl_relaxed(OIER) & ~OIER_E0, OIER); + writel_relaxed(OSSR_M0, OSSR); break; case CLOCK_EVT_MODE_RESUME: @@ -86,8 +86,8 @@ static struct irqaction sa1100_timer_irq = { static void __init sa1100_timer_init(void) { - OIER = 0; - OSSR = OSSR_M0 | OSSR_M1 | OSSR_M2 | OSSR_M3; + writel_relaxed(0, OIER); + writel_relaxed(OSSR_M0 | OSSR_M1 | OSSR_M2 | OSSR_M3, OSSR); setup_sched_clock(sa1100_read_sched_clock, 32, 3686400); @@ -100,7 +100,7 @@ static void __init sa1100_timer_init(void) setup_irq(IRQ_OST0, &sa1100_timer_irq); - clocksource_mmio_init(&OSCR, "oscr", CLOCK_TICK_RATE, 200, 32, + clocksource_mmio_init(OSCR, "oscr", CLOCK_TICK_RATE, 200, 32, clocksource_mmio_readl_up); clockevents_register_device(&ckevt_sa1100_osmr0); } @@ -110,26 +110,26 @@ unsigned long osmr[4], oier; static void sa1100_timer_suspend(void) { - osmr[0] = OSMR0; - osmr[1] = OSMR1; - osmr[2] = OSMR2; - osmr[3] = OSMR3; - oier = OIER; + osmr[0] = readl_relaxed(OSMR0); + osmr[1] = readl_relaxed(OSMR1); + osmr[2] = readl_relaxed(OSMR2); + osmr[3] = readl_relaxed(OSMR3); + oier = readl_relaxed(OIER); } static void sa1100_timer_resume(void) { - OSSR = 0x0f; - OSMR0 = osmr[0]; - OSMR1 = osmr[1]; - OSMR2 = osmr[2]; - OSMR3 = osmr[3]; - OIER = oier; + writel_relaxed(0x0f, OSSR); + writel_relaxed(osmr[0], OSMR0); + writel_relaxed(osmr[1], OSMR1); + writel_relaxed(osmr[2], OSMR2); + writel_relaxed(osmr[3], OSMR3); + writel_relaxed(oier, OIER); /* * OSMR0 is the system timer: make sure OSCR is sufficiently behind */ - OSCR = OSMR0 - LATCH; + writel_relaxed(OSMR0 - LATCH, OSCR); } #else #define sa1100_timer_suspend NULL diff --git a/arch/arm/mm/context.c b/arch/arm/mm/context.c index 806cc4f63516..119bc52ab93e 100644 --- a/arch/arm/mm/context.c +++ b/arch/arm/mm/context.c @@ -14,6 +14,7 @@ #include <linux/percpu.h> #include <asm/mmu_context.h> +#include <asm/thread_notify.h> #include <asm/tlbflush.h> static DEFINE_RAW_SPINLOCK(cpu_asid_lock); @@ -48,6 +49,40 @@ void cpu_set_reserved_ttbr0(void) } #endif +#ifdef CONFIG_PID_IN_CONTEXTIDR +static int contextidr_notifier(struct notifier_block *unused, unsigned long cmd, + void *t) +{ + u32 contextidr; + pid_t pid; + struct thread_info *thread = t; + + if (cmd != THREAD_NOTIFY_SWITCH) + return NOTIFY_DONE; + + pid = task_pid_nr(thread->task) << ASID_BITS; + asm volatile( + " mrc p15, 0, %0, c13, c0, 1\n" + " bfi %1, %0, #0, %2\n" + " mcr p15, 0, %1, c13, c0, 1\n" + : "=r" (contextidr), "+r" (pid) + : "I" (ASID_BITS)); + isb(); + + return NOTIFY_OK; +} + +static struct notifier_block contextidr_notifier_block = { + .notifier_call = contextidr_notifier, +}; + +static int __init contextidr_notifier_init(void) +{ + return thread_register_notifier(&contextidr_notifier_block); +} +arch_initcall(contextidr_notifier_init); +#endif + /* * We fork()ed a process, and we need a new context for the child * to run in. diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c index 655878bcc96d..5cfc98994076 100644 --- a/arch/arm/mm/dma-mapping.c +++ b/arch/arm/mm/dma-mapping.c @@ -23,12 +23,12 @@ #include <linux/slab.h> #include <linux/iommu.h> #include <linux/vmalloc.h> +#include <linux/sizes.h> #include <asm/memory.h> #include <asm/highmem.h> #include <asm/cacheflush.h> #include <asm/tlbflush.h> -#include <asm/sizes.h> #include <asm/mach/arch.h> #include <asm/dma-iommu.h> #include <asm/mach/map.h> diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c index f54d59219764..9aec41fa80ae 100644 --- a/arch/arm/mm/init.c +++ b/arch/arm/mm/init.c @@ -21,13 +21,13 @@ #include <linux/gfp.h> #include <linux/memblock.h> #include <linux/dma-contiguous.h> +#include <linux/sizes.h> #include <asm/mach-types.h> #include <asm/memblock.h> #include <asm/prom.h> #include <asm/sections.h> #include <asm/setup.h> -#include <asm/sizes.h> #include <asm/tlb.h> #include <asm/fixmap.h> diff --git a/arch/arm/mm/ioremap.c b/arch/arm/mm/ioremap.c index 4f55f5062ab7..566750fa57d4 100644 --- a/arch/arm/mm/ioremap.c +++ b/arch/arm/mm/ioremap.c @@ -25,6 +25,7 @@ #include <linux/mm.h> #include <linux/vmalloc.h> #include <linux/io.h> +#include <linux/sizes.h> #include <asm/cp15.h> #include <asm/cputype.h> @@ -32,7 +33,6 @@ #include <asm/mmu_context.h> #include <asm/pgalloc.h> #include <asm/tlbflush.h> -#include <asm/sizes.h> #include <asm/system_info.h> #include <asm/mach/map.h> diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c index cf4528d51774..4c2d0451e84a 100644 --- a/arch/arm/mm/mmu.c +++ b/arch/arm/mm/mmu.c @@ -16,13 +16,13 @@ #include <linux/memblock.h> #include <linux/fs.h> #include <linux/vmalloc.h> +#include <linux/sizes.h> #include <asm/cp15.h> #include <asm/cputype.h> #include <asm/sections.h> #include <asm/cachetype.h> #include <asm/setup.h> -#include <asm/sizes.h> #include <asm/smp_plat.h> #include <asm/tlb.h> #include <asm/highmem.h> @@ -422,12 +422,6 @@ static void __init build_mem_type_table(void) vecs_pgprot = kern_pgprot = user_pgprot = cp->pte; /* - * Only use write-through for non-SMP systems - */ - if (!is_smp() && cpu_arch >= CPU_ARCH_ARMv5 && cachepolicy > CPOLICY_WRITETHROUGH) - vecs_pgprot = cache_policies[CPOLICY_WRITETHROUGH].pte; - - /* * Enable CPU-specific coherency if supported. * (Only available on XSC3 at the moment.) */ diff --git a/arch/arm/mm/proc-v6.S b/arch/arm/mm/proc-v6.S index 5900cd520e84..86b8b480634f 100644 --- a/arch/arm/mm/proc-v6.S +++ b/arch/arm/mm/proc-v6.S @@ -107,6 +107,12 @@ ENTRY(cpu_v6_switch_mm) mcr p15, 0, r2, c7, c5, 6 @ flush BTAC/BTB mcr p15, 0, r2, c7, c10, 4 @ drain write buffer mcr p15, 0, r0, c2, c0, 0 @ set TTB 0 +#ifdef CONFIG_PID_IN_CONTEXTIDR + mrc p15, 0, r2, c13, c0, 1 @ read current context ID + bic r2, r2, #0xff @ extract the PID + and r1, r1, #0xff + orr r1, r1, r2 @ insert into new context ID +#endif mcr p15, 0, r1, c13, c0, 1 @ set context ID #endif mov pc, lr diff --git a/arch/arm/mm/proc-v7-2level.S b/arch/arm/mm/proc-v7-2level.S index 42ac069c8012..fd045e706390 100644 --- a/arch/arm/mm/proc-v7-2level.S +++ b/arch/arm/mm/proc-v7-2level.S @@ -46,6 +46,11 @@ ENTRY(cpu_v7_switch_mm) #ifdef CONFIG_ARM_ERRATA_430973 mcr p15, 0, r2, c7, c5, 6 @ flush BTAC/BTB #endif +#ifdef CONFIG_PID_IN_CONTEXTIDR + mrc p15, 0, r2, c13, c0, 1 @ read current context ID + lsr r2, r2, #8 @ extract the PID + bfi r1, r2, #8, #24 @ insert into new context ID +#endif #ifdef CONFIG_ARM_ERRATA_754322 dsb #endif diff --git a/arch/arm/oprofile/common.c b/arch/arm/oprofile/common.c index 4e0a371630b3..99c63d4b6af8 100644 --- a/arch/arm/oprofile/common.c +++ b/arch/arm/oprofile/common.c @@ -23,26 +23,37 @@ #include <asm/ptrace.h> #ifdef CONFIG_HW_PERF_EVENTS + +/* + * OProfile has a curious naming scheme for the ARM PMUs, but they are + * part of the user ABI so we need to map from the perf PMU name for + * supported PMUs. + */ +static struct op_perf_name { + char *perf_name; + char *op_name; +} op_perf_name_map[] = { + { "xscale1", "arm/xscale1" }, + { "xscale1", "arm/xscale2" }, + { "v6", "arm/armv6" }, + { "v6mpcore", "arm/mpcore" }, + { "ARMv7 Cortex-A8", "arm/armv7" }, + { "ARMv7 Cortex-A9", "arm/armv7-ca9" }, +}; + char *op_name_from_perf_id(void) { - enum arm_perf_pmu_ids id = armpmu_get_pmu_id(); - - switch (id) { - case ARM_PERF_PMU_ID_XSCALE1: - return "arm/xscale1"; - case ARM_PERF_PMU_ID_XSCALE2: - return "arm/xscale2"; - case ARM_PERF_PMU_ID_V6: - return "arm/armv6"; - case ARM_PERF_PMU_ID_V6MP: - return "arm/mpcore"; - case ARM_PERF_PMU_ID_CA8: - return "arm/armv7"; - case ARM_PERF_PMU_ID_CA9: - return "arm/armv7-ca9"; - default: - return NULL; + int i; + struct op_perf_name names; + const char *perf_name = perf_pmu_name(); + + for (i = 0; i < ARRAY_SIZE(op_perf_name_map); ++i) { + names = op_perf_name_map[i]; + if (!strcmp(names.perf_name, perf_name)) + return names.op_name; } + + return NULL; } #endif diff --git a/arch/arm/plat-versatile/platsmp.c b/arch/arm/plat-versatile/platsmp.c index 49c7db48c7f1..d7c5c171f5aa 100644 --- a/arch/arm/plat-versatile/platsmp.c +++ b/arch/arm/plat-versatile/platsmp.c @@ -85,7 +85,7 @@ int __cpuinit boot_secondary(unsigned int cpu, struct task_struct *idle) * the boot monitor to read the system wide flags register, * and branch to the address found there. */ - gic_raise_softirq(cpumask_of(cpu), 1); + gic_raise_softirq(cpumask_of(cpu), 0); timeout = jiffies + (1 * HZ); while (time_before(jiffies, timeout)) { diff --git a/arch/avr32/include/asm/kmap_types.h b/arch/avr32/include/asm/kmap_types.h index b7f5c6870107..479330b89796 100644 --- a/arch/avr32/include/asm/kmap_types.h +++ b/arch/avr32/include/asm/kmap_types.h @@ -2,29 +2,9 @@ #define __ASM_AVR32_KMAP_TYPES_H #ifdef CONFIG_DEBUG_HIGHMEM -# define D(n) __KM_FENCE_##n , +# define KM_TYPE_NR 29 #else -# define D(n) +# define KM_TYPE_NR 14 #endif -enum km_type { -D(0) KM_BOUNCE_READ, -D(1) KM_SKB_SUNRPC_DATA, -D(2) KM_SKB_DATA_SOFTIRQ, -D(3) KM_USER0, -D(4) KM_USER1, -D(5) KM_BIO_SRC_IRQ, -D(6) KM_BIO_DST_IRQ, -D(7) KM_PTE0, -D(8) KM_PTE1, -D(9) KM_PTE2, -D(10) KM_IRQ0, -D(11) KM_IRQ1, -D(12) KM_SOFTIRQ0, -D(13) KM_SOFTIRQ1, -D(14) KM_TYPE_NR -}; - -#undef D - #endif /* __ASM_AVR32_KMAP_TYPES_H */ diff --git a/arch/frv/include/asm/highmem.h b/arch/frv/include/asm/highmem.h index 716956a5317b..b3adc93611f3 100644 --- a/arch/frv/include/asm/highmem.h +++ b/arch/frv/include/asm/highmem.h @@ -76,15 +76,16 @@ extern struct page *kmap_atomic_to_page(void *ptr); #ifndef __ASSEMBLY__ -#define __kmap_atomic_primary(type, paddr, ampr) \ +#define __kmap_atomic_primary(cached, paddr, ampr) \ ({ \ unsigned long damlr, dampr; \ \ dampr = paddr | xAMPRx_L | xAMPRx_M | xAMPRx_S | xAMPRx_SS_16Kb | xAMPRx_V; \ \ - if (type != __KM_CACHE) \ + if (!cached) \ asm volatile("movgs %0,dampr"#ampr :: "r"(dampr) : "memory"); \ else \ + /* cache flush page attachment point */ \ asm volatile("movgs %0,iampr"#ampr"\n" \ "movgs %0,dampr"#ampr"\n" \ :: "r"(dampr) : "memory" \ @@ -112,29 +113,20 @@ extern struct page *kmap_atomic_to_page(void *ptr); (void *) damlr; \ }) -static inline void *kmap_atomic_primary(struct page *page, enum km_type type) +static inline void *kmap_atomic_primary(struct page *page) { unsigned long paddr; pagefault_disable(); paddr = page_to_phys(page); - switch (type) { - case 0: return __kmap_atomic_primary(0, paddr, 2); - case 1: return __kmap_atomic_primary(1, paddr, 3); - case 2: return __kmap_atomic_primary(2, paddr, 4); - case 3: return __kmap_atomic_primary(3, paddr, 5); - - default: - BUG(); - return NULL; - } + return __kmap_atomic_primary(1, paddr, 2); } -#define __kunmap_atomic_primary(type, ampr) \ +#define __kunmap_atomic_primary(cached, ampr) \ do { \ asm volatile("movgs gr0,dampr"#ampr"\n" ::: "memory"); \ - if (type == __KM_CACHE) \ + if (cached) \ asm volatile("movgs gr0,iampr"#ampr"\n" ::: "memory"); \ } while(0) @@ -143,17 +135,9 @@ do { \ asm volatile("tlbpr %0,gr0,#4,#1" : : "r"(vaddr) : "memory"); \ } while(0) -static inline void kunmap_atomic_primary(void *kvaddr, enum km_type type) +static inline void kunmap_atomic_primary(void *kvaddr) { - switch (type) { - case 0: __kunmap_atomic_primary(0, 2); break; - case 1: __kunmap_atomic_primary(1, 3); break; - case 2: __kunmap_atomic_primary(2, 4); break; - case 3: __kunmap_atomic_primary(3, 5); break; - - default: - BUG(); - } + __kunmap_atomic_primary(1, 2); pagefault_enable(); } diff --git a/arch/frv/include/asm/kmap_types.h b/arch/frv/include/asm/kmap_types.h index f8e16b2a5804..43901f220963 100644 --- a/arch/frv/include/asm/kmap_types.h +++ b/arch/frv/include/asm/kmap_types.h @@ -2,28 +2,6 @@ #ifndef _ASM_KMAP_TYPES_H #define _ASM_KMAP_TYPES_H -enum km_type { - /* arch specific kmaps - change the numbers attached to these at your peril */ - __KM_CACHE, /* cache flush page attachment point */ - __KM_PGD, /* current page directory */ - __KM_ITLB_PTD, /* current instruction TLB miss page table lookup */ - __KM_DTLB_PTD, /* current data TLB miss page table lookup */ - - /* general kmaps */ - KM_BOUNCE_READ, - KM_SKB_SUNRPC_DATA, - KM_SKB_DATA_SOFTIRQ, - KM_USER0, - KM_USER1, - KM_BIO_SRC_IRQ, - KM_BIO_DST_IRQ, - KM_PTE0, - KM_PTE1, - KM_IRQ0, - KM_IRQ1, - KM_SOFTIRQ0, - KM_SOFTIRQ1, - KM_TYPE_NR -}; +#define KM_TYPE_NR 17 #endif diff --git a/arch/frv/mb93090-mb00/pci-dma.c b/arch/frv/mb93090-mb00/pci-dma.c index 4f8d8bcdc7de..82478979ac9a 100644 --- a/arch/frv/mb93090-mb00/pci-dma.c +++ b/arch/frv/mb93090-mb00/pci-dma.c @@ -62,14 +62,14 @@ int dma_map_sg(struct device *dev, struct scatterlist *sg, int nents, dampr2 = __get_DAMPR(2); for (i = 0; i < nents; i++) { - vaddr = kmap_atomic_primary(sg_page(&sg[i]), __KM_CACHE); + vaddr = kmap_atomic_primary(sg_page(&sg[i])); frv_dcache_writeback((unsigned long) vaddr, (unsigned long) vaddr + PAGE_SIZE); } - kunmap_atomic_primary(vaddr, __KM_CACHE); + kunmap_atomic_primary(vaddr); if (dampr2) { __set_DAMPR(2, dampr2); __set_IAMPR(2, dampr2); diff --git a/arch/frv/mm/cache-page.c b/arch/frv/mm/cache-page.c index b24ade27a0f0..8e09dae0ec3f 100644 --- a/arch/frv/mm/cache-page.c +++ b/arch/frv/mm/cache-page.c @@ -26,11 +26,11 @@ void flush_dcache_page(struct page *page) dampr2 = __get_DAMPR(2); - vaddr = kmap_atomic_primary(page, __KM_CACHE); + vaddr = kmap_atomic_primary(page); frv_dcache_writeback((unsigned long) vaddr, (unsigned long) vaddr + PAGE_SIZE); - kunmap_atomic_primary(vaddr, __KM_CACHE); + kunmap_atomic_primary(vaddr); if (dampr2) { __set_DAMPR(2, dampr2); @@ -54,12 +54,12 @@ void flush_icache_user_range(struct vm_area_struct *vma, struct page *page, dampr2 = __get_DAMPR(2); - vaddr = kmap_atomic_primary(page, __KM_CACHE); + vaddr = kmap_atomic_primary(page); start = (start & ~PAGE_MASK) | (unsigned long) vaddr; frv_cache_wback_inv(start, start + len); - kunmap_atomic_primary(vaddr, __KM_CACHE); + kunmap_atomic_primary(vaddr); if (dampr2) { __set_DAMPR(2, dampr2); diff --git a/arch/frv/mm/highmem.c b/arch/frv/mm/highmem.c index 31902c9d5be5..bed9a9bd3c10 100644 --- a/arch/frv/mm/highmem.c +++ b/arch/frv/mm/highmem.c @@ -50,11 +50,11 @@ void *kmap_atomic(struct page *page) /* * The first 4 primary maps are reserved for architecture code */ - case 0: return __kmap_atomic_primary(4, paddr, 6); - case 1: return __kmap_atomic_primary(5, paddr, 7); - case 2: return __kmap_atomic_primary(6, paddr, 8); - case 3: return __kmap_atomic_primary(7, paddr, 9); - case 4: return __kmap_atomic_primary(8, paddr, 10); + case 0: return __kmap_atomic_primary(0, paddr, 6); + case 1: return __kmap_atomic_primary(0, paddr, 7); + case 2: return __kmap_atomic_primary(0, paddr, 8); + case 3: return __kmap_atomic_primary(0, paddr, 9); + case 4: return __kmap_atomic_primary(0, paddr, 10); case 5 ... 5 + NR_TLB_LINES - 1: return __kmap_atomic_secondary(type - 5, paddr); @@ -70,11 +70,11 @@ void __kunmap_atomic(void *kvaddr) { int type = kmap_atomic_idx(); switch (type) { - case 0: __kunmap_atomic_primary(4, 6); break; - case 1: __kunmap_atomic_primary(5, 7); break; - case 2: __kunmap_atomic_primary(6, 8); break; - case 3: __kunmap_atomic_primary(7, 9); break; - case 4: __kunmap_atomic_primary(8, 10); break; + case 0: __kunmap_atomic_primary(0, 6); break; + case 1: __kunmap_atomic_primary(0, 7); break; + case 2: __kunmap_atomic_primary(0, 8); break; + case 3: __kunmap_atomic_primary(0, 9); break; + case 4: __kunmap_atomic_primary(0, 10); break; case 5 ... 5 + NR_TLB_LINES - 1: __kunmap_atomic_secondary(type - 5, kvaddr); diff --git a/arch/powerpc/include/asm/kmap_types.h b/arch/powerpc/include/asm/kmap_types.h index bca8fdcd2542..5acabbd7ac6f 100644 --- a/arch/powerpc/include/asm/kmap_types.h +++ b/arch/powerpc/include/asm/kmap_types.h @@ -10,36 +10,7 @@ * 2 of the License, or (at your option) any later version. */ -enum km_type { - KM_BOUNCE_READ, - KM_SKB_SUNRPC_DATA, - KM_SKB_DATA_SOFTIRQ, - KM_USER0, - KM_USER1, - KM_BIO_SRC_IRQ, - KM_BIO_DST_IRQ, - KM_PTE0, - KM_PTE1, - KM_IRQ0, - KM_IRQ1, - KM_SOFTIRQ0, - KM_SOFTIRQ1, - KM_PPC_SYNC_PAGE, - KM_PPC_SYNC_ICACHE, - KM_KDB, - KM_TYPE_NR -}; - -/* - * This is a temporary build fix that (so they say on lkml....) should no longer - * be required after 2.6.33, because of changes planned to the kmap code. - * Let's try to remove this cruft then. - */ -#ifdef CONFIG_DEBUG_HIGHMEM -#define KM_NMI (-1) -#define KM_NMI_PTE (-1) -#define KM_IRQ_PTE (-1) -#endif +#define KM_TYPE_NR 16 #endif /* __KERNEL__ */ #endif /* _ASM_POWERPC_KMAP_TYPES_H */ diff --git a/arch/tile/include/asm/kmap_types.h b/arch/tile/include/asm/kmap_types.h index 3d0f20246260..92b28e3e9972 100644 --- a/arch/tile/include/asm/kmap_types.h +++ b/arch/tile/include/asm/kmap_types.h @@ -23,35 +23,6 @@ * adds 4MB of required address-space. For now we leave KM_TYPE_NR * set to depth 8. */ -enum km_type { - KM_TYPE_NR = 8 -}; - -/* - * We provide dummy definitions of all the stray values that used to be - * required for kmap_atomic() and no longer are. - */ -enum { - KM_BOUNCE_READ, - KM_SKB_SUNRPC_DATA, - KM_SKB_DATA_SOFTIRQ, - KM_USER0, - KM_USER1, - KM_BIO_SRC_IRQ, - KM_BIO_DST_IRQ, - KM_PTE0, - KM_PTE1, - KM_IRQ0, - KM_IRQ1, - KM_SOFTIRQ0, - KM_SOFTIRQ1, - KM_SYNC_ICACHE, - KM_SYNC_DCACHE, - KM_UML_USERCOPY, - KM_IRQ_PTE, - KM_NMI, - KM_NMI_PTE, - KM_KDB -}; +#define KM_TYPE_NR 8 #endif /* _ASM_TILE_KMAP_TYPES_H */ diff --git a/arch/tile/mm/highmem.c b/arch/tile/mm/highmem.c index ef8e5a62b6e3..347d123b14be 100644 --- a/arch/tile/mm/highmem.c +++ b/arch/tile/mm/highmem.c @@ -93,7 +93,7 @@ static DEFINE_PER_CPU(struct kmap_amps, amps); * If we examine it earlier we are exposed to a race where it looks * writable earlier, but becomes immutable before we write the PTE. */ -static void kmap_atomic_register(struct page *page, enum km_type type, +static void kmap_atomic_register(struct page *page, int type, unsigned long va, pte_t *ptep, pte_t pteval) { unsigned long flags; diff --git a/arch/um/include/asm/kmap_types.h b/arch/um/include/asm/kmap_types.h index 6c03acdb4405..2e0a6b1d8300 100644 --- a/arch/um/include/asm/kmap_types.h +++ b/arch/um/include/asm/kmap_types.h @@ -8,22 +8,6 @@ /* No more #include "asm/arch/kmap_types.h" ! */ -enum km_type { - KM_BOUNCE_READ, - KM_SKB_SUNRPC_DATA, - KM_SKB_DATA_SOFTIRQ, - KM_USER0, - KM_USER1, - KM_UML_USERCOPY, /* UML specific, for copy_*_user - used in do_op_one_page */ - KM_BIO_SRC_IRQ, - KM_BIO_DST_IRQ, - KM_PTE0, - KM_PTE1, - KM_IRQ0, - KM_IRQ1, - KM_SOFTIRQ0, - KM_SOFTIRQ1, - KM_TYPE_NR -}; +#define KM_TYPE_NR 14 #endif diff --git a/drivers/amba/bus.c b/drivers/amba/bus.c index b7e728517284..e8eb91bd0d28 100644 --- a/drivers/amba/bus.c +++ b/drivers/amba/bus.c @@ -16,9 +16,9 @@ #include <linux/pm.h> #include <linux/pm_runtime.h> #include <linux/amba/bus.h> +#include <linux/sizes.h> #include <asm/irq.h> -#include <asm/sizes.h> #define to_amba_driver(d) container_of(d, struct amba_driver, drv) diff --git a/drivers/input/touchscreen/jornada720_ts.c b/drivers/input/touchscreen/jornada720_ts.c index d9be6eac99b1..7f03d1bd916e 100644 --- a/drivers/input/touchscreen/jornada720_ts.c +++ b/drivers/input/touchscreen/jornada720_ts.c @@ -19,6 +19,7 @@ #include <linux/interrupt.h> #include <linux/module.h> #include <linux/slab.h> +#include <linux/io.h> #include <mach/hardware.h> #include <mach/jornada720.h> diff --git a/drivers/net/irda/pxaficp_ir.c b/drivers/net/irda/pxaficp_ir.c index ff16daf33ae1..8d5476707912 100644 --- a/drivers/net/irda/pxaficp_ir.c +++ b/drivers/net/irda/pxaficp_ir.c @@ -289,7 +289,7 @@ static irqreturn_t pxa_irda_sir_irq(int irq, void *dev_id) } lsr = STLSR; } - si->last_oscr = OSCR; + si->last_oscr = readl_relaxed(OSCR); break; case 0x04: /* Received Data Available */ @@ -300,7 +300,7 @@ static irqreturn_t pxa_irda_sir_irq(int irq, void *dev_id) dev->stats.rx_bytes++; async_unwrap_char(dev, &dev->stats, &si->rx_buff, STRBR); } while (STLSR & LSR_DR); - si->last_oscr = OSCR; + si->last_oscr = readl_relaxed(OSCR); break; case 0x02: /* Transmit FIFO Data Request */ @@ -316,7 +316,7 @@ static irqreturn_t pxa_irda_sir_irq(int irq, void *dev_id) /* We need to ensure that the transmitter has finished. */ while ((STLSR & LSR_TEMT) == 0) cpu_relax(); - si->last_oscr = OSCR; + si->last_oscr = readl_relaxed(OSCR); /* * Ok, we've finished transmitting. Now enable @@ -370,7 +370,7 @@ static void pxa_irda_fir_dma_tx_irq(int channel, void *data) while (ICSR1 & ICSR1_TBY) cpu_relax(); - si->last_oscr = OSCR; + si->last_oscr = readl_relaxed(OSCR); /* * HACK: It looks like the TBY bit is dropped too soon. @@ -470,7 +470,7 @@ static irqreturn_t pxa_irda_fir_irq(int irq, void *dev_id) /* stop RX DMA */ DCSR(si->rxdma) &= ~DCSR_RUN; - si->last_oscr = OSCR; + si->last_oscr = readl_relaxed(OSCR); icsr0 = ICSR0; if (icsr0 & (ICSR0_FRE | ICSR0_RAB)) { @@ -546,7 +546,7 @@ static int pxa_irda_hard_xmit(struct sk_buff *skb, struct net_device *dev) skb_copy_from_linear_data(skb, si->dma_tx_buff, skb->len); if (mtt) - while ((unsigned)(OSCR - si->last_oscr)/4 < mtt) + while ((unsigned)(readl_relaxed(OSCR) - si->last_oscr)/4 < mtt) cpu_relax(); /* stop RX DMA, disable FICP */ diff --git a/drivers/pcmcia/sa1100_shannon.c b/drivers/pcmcia/sa1100_shannon.c index decb34730bcf..56ab73915602 100644 --- a/drivers/pcmcia/sa1100_shannon.c +++ b/drivers/pcmcia/sa1100_shannon.c @@ -8,6 +8,7 @@ #include <linux/kernel.h> #include <linux/device.h> #include <linux/init.h> +#include <linux/io.h> #include <mach/hardware.h> #include <asm/mach-types.h> diff --git a/drivers/tty/serial/8250/8250.c b/drivers/tty/serial/8250/8250.c index 6e1958a325bd..8123f784bcda 100644 --- a/drivers/tty/serial/8250/8250.c +++ b/drivers/tty/serial/8250/8250.c @@ -282,6 +282,14 @@ static const struct serial8250_config uart_config[] = { .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_10, .flags = UART_CAP_FIFO | UART_CAP_AFE | UART_CAP_EFR, }, + [PORT_LPC3220] = { + .name = "LPC3220", + .fifo_size = 64, + .tx_loadsz = 32, + .fcr = UART_FCR_DMA_SELECT | UART_FCR_ENABLE_FIFO | + UART_FCR_R_TRIG_00 | UART_FCR_T_TRIG_00, + .flags = UART_CAP_FIFO, + }, }; /* Uart divisor latch read */ diff --git a/drivers/tty/serial/amba-pl011.c b/drivers/tty/serial/amba-pl011.c index c17923ec6e95..d3553b5d3fca 100644 --- a/drivers/tty/serial/amba-pl011.c +++ b/drivers/tty/serial/amba-pl011.c @@ -53,9 +53,9 @@ #include <linux/delay.h> #include <linux/types.h> #include <linux/pinctrl/consumer.h> +#include <linux/sizes.h> #include <asm/io.h> -#include <asm/sizes.h> #define UART_NR 14 diff --git a/drivers/tty/serial/of_serial.c b/drivers/tty/serial/of_serial.c index 5410c0637266..34e71874a892 100644 --- a/drivers/tty/serial/of_serial.c +++ b/drivers/tty/serial/of_serial.c @@ -208,6 +208,7 @@ static struct of_device_id __devinitdata of_platform_serial_table[] = { { .compatible = "ns16750", .data = (void *)PORT_16750, }, { .compatible = "ns16850", .data = (void *)PORT_16850, }, { .compatible = "nvidia,tegra20-uart", .data = (void *)PORT_TEGRA, }, + { .compatible = "nxp,lpc3220-uart", .data = (void *)PORT_LPC3220, }, #ifdef CONFIG_SERIAL_OF_PLATFORM_NWPSERIAL { .compatible = "ibm,qpace-nwp-serial", .data = (void *)PORT_NWPSERIAL, }, diff --git a/drivers/tty/serial/pch_uart.c b/drivers/tty/serial/pch_uart.c index 4fdec6a6b758..558ce8509a9a 100644 --- a/drivers/tty/serial/pch_uart.c +++ b/drivers/tty/serial/pch_uart.c @@ -253,6 +253,9 @@ struct eg20t_port { dma_addr_t rx_buf_dma; struct dentry *debugfs; + + /* protect the eg20t_port private structure and io access to membase */ + spinlock_t lock; }; /** @@ -754,7 +757,8 @@ static void pch_dma_rx_complete(void *arg) tty_flip_buffer_push(tty); tty_kref_put(tty); async_tx_ack(priv->desc_rx); - pch_uart_hal_enable_interrupt(priv, PCH_UART_HAL_RX_INT); + pch_uart_hal_enable_interrupt(priv, PCH_UART_HAL_RX_INT | + PCH_UART_HAL_RX_ERR_INT); } static void pch_dma_tx_complete(void *arg) @@ -809,7 +813,8 @@ static int handle_rx_to(struct eg20t_port *priv) int rx_size; int ret; if (!priv->start_rx) { - pch_uart_hal_disable_interrupt(priv, PCH_UART_HAL_RX_INT); + pch_uart_hal_disable_interrupt(priv, PCH_UART_HAL_RX_INT | + PCH_UART_HAL_RX_ERR_INT); return 0; } buf = &priv->rxbuf; @@ -1058,7 +1063,7 @@ static irqreturn_t pch_uart_interrupt(int irq, void *dev_id) int next = 1; u8 msr; - spin_lock_irqsave(&priv->port.lock, flags); + spin_lock_irqsave(&priv->lock, flags); handled = 0; while (next) { iid = pch_uart_hal_get_iid(priv); @@ -1078,11 +1083,13 @@ static irqreturn_t pch_uart_interrupt(int irq, void *dev_id) case PCH_UART_IID_RDR: /* Received Data Ready */ if (priv->use_dma) { pch_uart_hal_disable_interrupt(priv, - PCH_UART_HAL_RX_INT); + PCH_UART_HAL_RX_INT | + PCH_UART_HAL_RX_ERR_INT); ret = dma_handle_rx(priv); if (!ret) pch_uart_hal_enable_interrupt(priv, - PCH_UART_HAL_RX_INT); + PCH_UART_HAL_RX_INT | + PCH_UART_HAL_RX_ERR_INT); } else { ret = handle_rx(priv); } @@ -1116,7 +1123,7 @@ static irqreturn_t pch_uart_interrupt(int irq, void *dev_id) handled |= (unsigned int)ret; } - spin_unlock_irqrestore(&priv->port.lock, flags); + spin_unlock_irqrestore(&priv->lock, flags); return IRQ_RETVAL(handled); } @@ -1208,7 +1215,8 @@ static void pch_uart_stop_rx(struct uart_port *port) struct eg20t_port *priv; priv = container_of(port, struct eg20t_port, port); priv->start_rx = 0; - pch_uart_hal_disable_interrupt(priv, PCH_UART_HAL_RX_INT); + pch_uart_hal_disable_interrupt(priv, PCH_UART_HAL_RX_INT | + PCH_UART_HAL_RX_ERR_INT); } /* Enable the modem status interrupts. */ @@ -1226,9 +1234,9 @@ static void pch_uart_break_ctl(struct uart_port *port, int ctl) unsigned long flags; priv = container_of(port, struct eg20t_port, port); - spin_lock_irqsave(&port->lock, flags); + spin_lock_irqsave(&priv->lock, flags); pch_uart_hal_set_break(priv, ctl); - spin_unlock_irqrestore(&port->lock, flags); + spin_unlock_irqrestore(&priv->lock, flags); } /* Grab any interrupt resources and initialise any low level driver state. */ @@ -1263,6 +1271,7 @@ static int pch_uart_startup(struct uart_port *port) break; case 16: fifo_size = PCH_UART_HAL_FIFO16; + break; case 1: default: fifo_size = PCH_UART_HAL_FIFO_DIS; @@ -1300,7 +1309,8 @@ static int pch_uart_startup(struct uart_port *port) pch_request_dma(port); priv->start_rx = 1; - pch_uart_hal_enable_interrupt(priv, PCH_UART_HAL_RX_INT); + pch_uart_hal_enable_interrupt(priv, PCH_UART_HAL_RX_INT | + PCH_UART_HAL_RX_ERR_INT); uart_update_timeout(port, CS8, default_baud); return 0; @@ -1358,7 +1368,7 @@ static void pch_uart_set_termios(struct uart_port *port, stb = PCH_UART_HAL_STB1; if (termios->c_cflag & PARENB) { - if (!(termios->c_cflag & PARODD)) + if (termios->c_cflag & PARODD) parity = PCH_UART_HAL_PARITY_ODD; else parity = PCH_UART_HAL_PARITY_EVEN; @@ -1376,7 +1386,8 @@ static void pch_uart_set_termios(struct uart_port *port, baud = uart_get_baud_rate(port, termios, old, 0, port->uartclk / 16); - spin_lock_irqsave(&port->lock, flags); + spin_lock_irqsave(&priv->lock, flags); + spin_lock(&port->lock); uart_update_timeout(port, termios->c_cflag, baud); rtn = pch_uart_hal_set_line(priv, baud, parity, bits, stb); @@ -1389,7 +1400,8 @@ static void pch_uart_set_termios(struct uart_port *port, tty_termios_encode_baud_rate(termios, baud, baud); out: - spin_unlock_irqrestore(&port->lock, flags); + spin_unlock(&port->lock); + spin_unlock_irqrestore(&priv->lock, flags); } static const char *pch_uart_type(struct uart_port *port) @@ -1538,8 +1550,9 @@ pch_console_write(struct console *co, const char *s, unsigned int count) { struct eg20t_port *priv; unsigned long flags; + int priv_locked = 1; + int port_locked = 1; u8 ier; - int locked = 1; priv = pch_uart_ports[co->index]; @@ -1547,12 +1560,16 @@ pch_console_write(struct console *co, const char *s, unsigned int count) local_irq_save(flags); if (priv->port.sysrq) { - /* serial8250_handle_port() already took the lock */ - locked = 0; + spin_lock(&priv->lock); + /* serial8250_handle_port() already took the port lock */ + port_locked = 0; } else if (oops_in_progress) { - locked = spin_trylock(&priv->port.lock); - } else + priv_locked = spin_trylock(&priv->lock); + port_locked = spin_trylock(&priv->port.lock); + } else { + spin_lock(&priv->lock); spin_lock(&priv->port.lock); + } /* * First save the IER then disable the interrupts @@ -1570,8 +1587,10 @@ pch_console_write(struct console *co, const char *s, unsigned int count) wait_for_xmitr(priv, BOTH_EMPTY); iowrite8(ier, priv->membase + UART_IER); - if (locked) + if (port_locked) spin_unlock(&priv->port.lock); + if (priv_locked) + spin_unlock(&priv->lock); local_irq_restore(flags); } @@ -1669,6 +1688,8 @@ static struct eg20t_port *pch_uart_init_port(struct pci_dev *pdev, pci_enable_msi(pdev); pci_set_master(pdev); + spin_lock_init(&priv->lock); + iobase = pci_resource_start(pdev, 0); mapbase = pci_resource_start(pdev, 1); priv->mapbase = mapbase; diff --git a/drivers/tty/serial/samsung.c b/drivers/tty/serial/samsung.c index d8b0aee35632..02d07bfcfa8a 100644 --- a/drivers/tty/serial/samsung.c +++ b/drivers/tty/serial/samsung.c @@ -1014,10 +1014,10 @@ static int s3c24xx_serial_cpufreq_transition(struct notifier_block *nb, * a disturbance in the clock-rate over the change. */ - if (IS_ERR(port->clk)) + if (IS_ERR(port->baudclk)) goto exit; - if (port->baudclk_rate == clk_get_rate(port->clk)) + if (port->baudclk_rate == clk_get_rate(port->baudclk)) goto exit; if (val == CPUFREQ_PRECHANGE) { diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c index 246b823c1b27..a21dc8e3b7c0 100644 --- a/drivers/tty/serial/serial_core.c +++ b/drivers/tty/serial/serial_core.c @@ -2527,14 +2527,16 @@ void uart_insert_char(struct uart_port *port, unsigned int status, struct tty_struct *tty = port->state->port.tty; if ((status & port->ignore_status_mask & ~overrun) == 0) - tty_insert_flip_char(tty, ch, flag); + if (tty_insert_flip_char(tty, ch, flag) == 0) + ++port->icount.buf_overrun; /* * Overrun is special. Since it's reported immediately, * it doesn't affect the current character. */ if (status & ~port->ignore_status_mask & overrun) - tty_insert_flip_char(tty, 0, TTY_OVERRUN); + if (tty_insert_flip_char(tty, 0, TTY_OVERRUN) == 0) + ++port->icount.buf_overrun; } EXPORT_SYMBOL_GPL(uart_insert_char); diff --git a/drivers/tty/tty_ldisc.c b/drivers/tty/tty_ldisc.c index 9911eb6b34cd..6f99c9959f0c 100644 --- a/drivers/tty/tty_ldisc.c +++ b/drivers/tty/tty_ldisc.c @@ -659,7 +659,7 @@ int tty_set_ldisc(struct tty_struct *tty, int ldisc) goto enable; } - if (test_bit(TTY_HUPPED, &tty->flags)) { + if (test_bit(TTY_HUPPING, &tty->flags)) { /* We were raced by the hangup method. It will have stomped the ldisc data and closed the ldisc down */ clear_bit(TTY_LDISC_CHANGING, &tty->flags); diff --git a/drivers/tty/vt/vt_ioctl.c b/drivers/tty/vt/vt_ioctl.c index 64618547be11..b841f56d2e66 100644 --- a/drivers/tty/vt/vt_ioctl.c +++ b/drivers/tty/vt/vt_ioctl.c @@ -110,16 +110,7 @@ void vt_event_post(unsigned int event, unsigned int old, unsigned int new) wake_up_interruptible(&vt_event_waitqueue); } -/** - * vt_event_wait - wait for an event - * @vw: our event - * - * Waits for an event to occur which completes our vt_event_wait - * structure. On return the structure has wv->done set to 1 for success - * or 0 if some event such as a signal ended the wait. - */ - -static void vt_event_wait(struct vt_event_wait *vw) +static void __vt_event_queue(struct vt_event_wait *vw) { unsigned long flags; /* Prepare the event */ @@ -129,8 +120,18 @@ static void vt_event_wait(struct vt_event_wait *vw) spin_lock_irqsave(&vt_event_lock, flags); list_add(&vw->list, &vt_events); spin_unlock_irqrestore(&vt_event_lock, flags); +} + +static void __vt_event_wait(struct vt_event_wait *vw) +{ /* Wait for it to pass */ wait_event_interruptible(vt_event_waitqueue, vw->done); +} + +static void __vt_event_dequeue(struct vt_event_wait *vw) +{ + unsigned long flags; + /* Dequeue it */ spin_lock_irqsave(&vt_event_lock, flags); list_del(&vw->list); @@ -138,6 +139,22 @@ static void vt_event_wait(struct vt_event_wait *vw) } /** + * vt_event_wait - wait for an event + * @vw: our event + * + * Waits for an event to occur which completes our vt_event_wait + * structure. On return the structure has wv->done set to 1 for success + * or 0 if some event such as a signal ended the wait. + */ + +static void vt_event_wait(struct vt_event_wait *vw) +{ + __vt_event_queue(vw); + __vt_event_wait(vw); + __vt_event_dequeue(vw); +} + +/** * vt_event_wait_ioctl - event ioctl handler * @arg: argument to ioctl * @@ -177,10 +194,14 @@ int vt_waitactive(int n) { struct vt_event_wait vw; do { - if (n == fg_console + 1) - break; vw.event.event = VT_EVENT_SWITCH; - vt_event_wait(&vw); + __vt_event_queue(&vw); + if (n == fg_console + 1) { + __vt_event_dequeue(&vw); + break; + } + __vt_event_wait(&vw); + __vt_event_dequeue(&vw); if (vw.done == 0) return -EINTR; } while (vw.event.newev != n); diff --git a/drivers/watchdog/sa1100_wdt.c b/drivers/watchdog/sa1100_wdt.c index 54984deb8561..ccd6b29e21bf 100644 --- a/drivers/watchdog/sa1100_wdt.c +++ b/drivers/watchdog/sa1100_wdt.c @@ -54,10 +54,10 @@ static int sa1100dog_open(struct inode *inode, struct file *file) return -EBUSY; /* Activate SA1100 Watchdog timer */ - OSMR3 = OSCR + pre_margin; - OSSR = OSSR_M3; - OWER = OWER_WME; - OIER |= OIER_E3; + writel_relaxed(readl_relaxed(OSCR) + pre_margin, OSMR3); + writel_relaxed(OSSR_M3, OSSR); + writel_relaxed(OWER_WME, OWER); + writel_relaxed(readl_relaxed(OIER) | OIER_E3, OIER); return nonseekable_open(inode, file); } @@ -80,7 +80,7 @@ static ssize_t sa1100dog_write(struct file *file, const char __user *data, { if (len) /* Refresh OSMR3 timer. */ - OSMR3 = OSCR + pre_margin; + writel_relaxed(readl_relaxed(OSCR) + pre_margin, OSMR3); return len; } @@ -114,7 +114,7 @@ static long sa1100dog_ioctl(struct file *file, unsigned int cmd, break; case WDIOC_KEEPALIVE: - OSMR3 = OSCR + pre_margin; + writel_relaxed(readl_relaxed(OSCR) + pre_margin, OSMR3); ret = 0; break; @@ -129,7 +129,7 @@ static long sa1100dog_ioctl(struct file *file, unsigned int cmd, } pre_margin = oscr_freq * time; - OSMR3 = OSCR + pre_margin; + writel_relaxed(readl_relaxed(OSCR) + pre_margin, OSMR3); /*fall through*/ case WDIOC_GETTIMEOUT: diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index cee7812cc3cf..d23b31ca9d7a 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -609,7 +609,8 @@ ext4_fsblk_t ext4_count_free_clusters(struct super_block *sb) if (bitmap_bh == NULL) continue; - x = ext4_count_free(bitmap_bh, sb->s_blocksize); + x = ext4_count_free(bitmap_bh->b_data, + EXT4_BLOCKS_PER_GROUP(sb) / 8); printk(KERN_DEBUG "group %u: stored = %d, counted = %u\n", i, ext4_free_group_clusters(sb, gdp), x); bitmap_count += x; diff --git a/fs/ext4/bitmap.c b/fs/ext4/bitmap.c index b319721da26a..a94b9c63ee5c 100644 --- a/fs/ext4/bitmap.c +++ b/fs/ext4/bitmap.c @@ -11,24 +11,18 @@ #include <linux/jbd2.h> #include "ext4.h" -#ifdef EXT4FS_DEBUG - static const int nibblemap[] = {4, 3, 3, 2, 3, 2, 2, 1, 3, 2, 2, 1, 2, 1, 1, 0}; -unsigned int ext4_count_free(struct buffer_head *map, unsigned int numchars) +unsigned int ext4_count_free(char *bitmap, unsigned int numchars) { unsigned int i, sum = 0; - if (!map) - return 0; for (i = 0; i < numchars; i++) - sum += nibblemap[map->b_data[i] & 0xf] + - nibblemap[(map->b_data[i] >> 4) & 0xf]; + sum += nibblemap[bitmap[i] & 0xf] + + nibblemap[(bitmap[i] >> 4) & 0xf]; return sum; } -#endif /* EXT4FS_DEBUG */ - int ext4_inode_bitmap_csum_verify(struct super_block *sb, ext4_group_t group, struct ext4_group_desc *gdp, struct buffer_head *bh, int sz) diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index cfc4e01b3c83..c3411d4ce2da 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -571,6 +571,8 @@ enum { #define EXT4_GET_BLOCKS_NO_NORMALIZE 0x0040 /* Request will not result in inode size update (user for fallocate) */ #define EXT4_GET_BLOCKS_KEEP_SIZE 0x0080 + /* Do not take i_data_sem locking in ext4_map_blocks */ +#define EXT4_GET_BLOCKS_NO_LOCK 0x0100 /* * Flags used by ext4_free_blocks @@ -1161,8 +1163,7 @@ struct ext4_sb_info { unsigned long s_desc_per_block; /* Number of group descriptors per block */ ext4_group_t s_groups_count; /* Number of groups in the fs */ ext4_group_t s_blockfile_groups;/* Groups acceptable for non-extent files */ - unsigned long s_overhead_last; /* Last calculated overhead */ - unsigned long s_blocks_last; /* Last seen block count */ + unsigned long s_overhead; /* # of fs overhead clusters */ unsigned int s_cluster_ratio; /* Number of blocks per cluster */ unsigned int s_cluster_bits; /* log2 of s_cluster_ratio */ loff_t s_bitmap_maxbytes; /* max bytes for bitmap files */ @@ -1314,6 +1315,8 @@ static inline struct timespec ext4_current_time(struct inode *inode) static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino) { return ino == EXT4_ROOT_INO || + ino == EXT4_USR_QUOTA_INO || + ino == EXT4_GRP_QUOTA_INO || ino == EXT4_JOURNAL_INO || ino == EXT4_RESIZE_INO || (ino >= EXT4_FIRST_INO(sb) && @@ -1496,7 +1499,8 @@ static inline void ext4_clear_state_flags(struct ext4_inode_info *ei) EXT4_FEATURE_RO_COMPAT_BTREE_DIR |\ EXT4_FEATURE_RO_COMPAT_HUGE_FILE |\ EXT4_FEATURE_RO_COMPAT_BIGALLOC |\ - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM) + EXT4_FEATURE_RO_COMPAT_METADATA_CSUM|\ + EXT4_FEATURE_RO_COMPAT_QUOTA) /* * Default values for user and/or group using reserved blocks @@ -1663,10 +1667,12 @@ static inline u32 ext4_chksum(struct ext4_sb_info *sbi, u32 crc, { struct { struct shash_desc shash; - char ctx[crypto_shash_descsize(sbi->s_chksum_driver)]; + char ctx[4]; } desc; int err; + BUG_ON(crypto_shash_descsize(sbi->s_chksum_driver)!=sizeof(desc.ctx)); + desc.shash.tfm = sbi->s_chksum_driver; desc.shash.flags = 0; *(u32 *)desc.ctx = crc; @@ -1852,7 +1858,7 @@ struct mmpd_data { # define NORET_AND noreturn, /* bitmap.c */ -extern unsigned int ext4_count_free(struct buffer_head *, unsigned); +extern unsigned int ext4_count_free(char *bitmap, unsigned numchars); void ext4_inode_bitmap_csum_set(struct super_block *sb, ext4_group_t group, struct ext4_group_desc *gdp, struct buffer_head *bh, int sz); @@ -2037,6 +2043,7 @@ extern int ext4_group_extend(struct super_block *sb, extern int ext4_resize_fs(struct super_block *sb, ext4_fsblk_t n_blocks_count); /* super.c */ +extern int ext4_calculate_overhead(struct super_block *sb); extern int ext4_superblock_csum_verify(struct super_block *sb, struct ext4_super_block *es); extern void ext4_superblock_csum_set(struct super_block *sb, @@ -2321,15 +2328,6 @@ static inline void ext4_unlock_group(struct super_block *sb, spin_unlock(ext4_group_lock_ptr(sb, group)); } -static inline void ext4_mark_super_dirty(struct super_block *sb) -{ - struct ext4_super_block *es = EXT4_SB(sb)->s_es; - - ext4_superblock_csum_set(sb, es); - if (EXT4_SB(sb)->s_journal == NULL) - sb->s_dirt =1; -} - /* * Block validity checking */ diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c index 90f7c2e84db1..bfa65b49d424 100644 --- a/fs/ext4/ext4_jbd2.c +++ b/fs/ext4/ext4_jbd2.c @@ -138,8 +138,7 @@ int __ext4_handle_dirty_metadata(const char *where, unsigned int line, } int __ext4_handle_dirty_super(const char *where, unsigned int line, - handle_t *handle, struct super_block *sb, - int now) + handle_t *handle, struct super_block *sb) { struct buffer_head *bh = EXT4_SB(sb)->s_sbh; int err = 0; @@ -151,11 +150,10 @@ int __ext4_handle_dirty_super(const char *where, unsigned int line, if (err) ext4_journal_abort_handle(where, line, __func__, bh, handle, err); - } else if (now) { + } else { ext4_superblock_csum_set(sb, (struct ext4_super_block *)bh->b_data); mark_buffer_dirty(bh); - } else - sb->s_dirt = 1; + } return err; } diff --git a/fs/ext4/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h index f440e8f1841f..56d258c18303 100644 --- a/fs/ext4/ext4_jbd2.h +++ b/fs/ext4/ext4_jbd2.h @@ -87,14 +87,20 @@ #ifdef CONFIG_QUOTA /* Amount of blocks needed for quota update - we know that the structure was * allocated so we need to update only data block */ -#define EXT4_QUOTA_TRANS_BLOCKS(sb) (test_opt(sb, QUOTA) ? 1 : 0) +#define EXT4_QUOTA_TRANS_BLOCKS(sb) ((test_opt(sb, QUOTA) ||\ + EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA)) ?\ + 1 : 0) /* Amount of blocks needed for quota insert/delete - we do some block writes * but inode, sb and group updates are done only once */ -#define EXT4_QUOTA_INIT_BLOCKS(sb) (test_opt(sb, QUOTA) ? (DQUOT_INIT_ALLOC*\ - (EXT4_SINGLEDATA_TRANS_BLOCKS(sb)-3)+3+DQUOT_INIT_REWRITE) : 0) - -#define EXT4_QUOTA_DEL_BLOCKS(sb) (test_opt(sb, QUOTA) ? (DQUOT_DEL_ALLOC*\ - (EXT4_SINGLEDATA_TRANS_BLOCKS(sb)-3)+3+DQUOT_DEL_REWRITE) : 0) +#define EXT4_QUOTA_INIT_BLOCKS(sb) ((test_opt(sb, QUOTA) ||\ + EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA)) ?\ + (DQUOT_INIT_ALLOC*(EXT4_SINGLEDATA_TRANS_BLOCKS(sb)-3)\ + +3+DQUOT_INIT_REWRITE) : 0) + +#define EXT4_QUOTA_DEL_BLOCKS(sb) ((test_opt(sb, QUOTA) ||\ + EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA)) ?\ + (DQUOT_DEL_ALLOC*(EXT4_SINGLEDATA_TRANS_BLOCKS(sb)-3)\ + +3+DQUOT_DEL_REWRITE) : 0) #else #define EXT4_QUOTA_TRANS_BLOCKS(sb) 0 #define EXT4_QUOTA_INIT_BLOCKS(sb) 0 @@ -213,8 +219,7 @@ int __ext4_handle_dirty_metadata(const char *where, unsigned int line, struct buffer_head *bh); int __ext4_handle_dirty_super(const char *where, unsigned int line, - handle_t *handle, struct super_block *sb, - int now); + handle_t *handle, struct super_block *sb); #define ext4_journal_get_write_access(handle, bh) \ __ext4_journal_get_write_access(__func__, __LINE__, (handle), (bh)) @@ -226,10 +231,8 @@ int __ext4_handle_dirty_super(const char *where, unsigned int line, #define ext4_handle_dirty_metadata(handle, inode, bh) \ __ext4_handle_dirty_metadata(__func__, __LINE__, (handle), (inode), \ (bh)) -#define ext4_handle_dirty_super_now(handle, sb) \ - __ext4_handle_dirty_super(__func__, __LINE__, (handle), (sb), 1) #define ext4_handle_dirty_super(handle, sb) \ - __ext4_handle_dirty_super(__func__, __LINE__, (handle), (sb), 0) + __ext4_handle_dirty_super(__func__, __LINE__, (handle), (sb)) handle_t *ext4_journal_start_sb(struct super_block *sb, int nblocks); int __ext4_journal_stop(const char *where, unsigned int line, handle_t *handle); diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 91341ec6e06a..cd0c7ed06772 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -1891,11 +1891,10 @@ has_space: nearex->ee_len = newext->ee_len; merge: - /* try to merge extents to the right */ + /* try to merge extents */ if (!(flag & EXT4_GET_BLOCKS_PRE_IO)) ext4_ext_try_to_merge(inode, path, nearex); - /* try to merge extents to the left */ /* time to correct all indexes above */ err = ext4_ext_correct_indexes(handle, inode, path); @@ -2570,10 +2569,10 @@ static int ext4_ext_remove_space(struct inode *inode, ext4_lblk_t start, { struct super_block *sb = inode->i_sb; int depth = ext_depth(inode); - struct ext4_ext_path *path; + struct ext4_ext_path *path = NULL; ext4_fsblk_t partial_cluster = 0; handle_t *handle; - int i, err; + int i = 0, err; ext_debug("truncate since %u to %u\n", start, end); @@ -2606,8 +2605,12 @@ again: } depth = ext_depth(inode); ex = path[depth].p_ext; - if (!ex) + if (!ex) { + ext4_ext_drop_refs(path); + kfree(path); + path = NULL; goto cont; + } ee_block = le32_to_cpu(ex->ee_block); @@ -2637,8 +2640,6 @@ again: if (err < 0) goto out; } - ext4_ext_drop_refs(path); - kfree(path); } cont: @@ -2647,19 +2648,27 @@ cont: * after i_size and walking into the tree depth-wise. */ depth = ext_depth(inode); - path = kzalloc(sizeof(struct ext4_ext_path) * (depth + 1), GFP_NOFS); - if (path == NULL) { - ext4_journal_stop(handle); - return -ENOMEM; - } - path[0].p_depth = depth; - path[0].p_hdr = ext_inode_hdr(inode); + if (path) { + int k = i = depth; + while (--k > 0) + path[k].p_block = + le16_to_cpu(path[k].p_hdr->eh_entries)+1; + } else { + path = kzalloc(sizeof(struct ext4_ext_path) * (depth + 1), + GFP_NOFS); + if (path == NULL) { + ext4_journal_stop(handle); + return -ENOMEM; + } + path[0].p_depth = depth; + path[0].p_hdr = ext_inode_hdr(inode); - if (ext4_ext_check(inode, path[0].p_hdr, depth)) { - err = -EIO; - goto out; + if (ext4_ext_check(inode, path[0].p_hdr, depth)) { + err = -EIO; + goto out; + } } - i = err = 0; + err = 0; while (i >= 0 && err == 0) { if (i == depth) { @@ -2773,8 +2782,10 @@ cont: out: ext4_ext_drop_refs(path); kfree(path); - if (err == -EAGAIN) + if (err == -EAGAIN) { + path = NULL; goto again; + } ext4_journal_stop(handle); return err; @@ -4420,6 +4431,8 @@ retry: ext4_falloc_update_inode(inode, mode, new_size, (map.m_flags & EXT4_MAP_NEW)); ext4_mark_inode_dirty(handle, inode); + if ((file->f_flags & O_SYNC) && ret >= max_blocks) + ext4_handle_sync(handle); ret2 = ext4_journal_stop(handle); if (ret2) break; diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 782eecb57e43..3b0e3bdaabfc 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -90,11 +90,91 @@ ext4_unaligned_aio(struct inode *inode, const struct iovec *iov, } static ssize_t +ext4_file_dio_write(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t pos) +{ + struct file *file = iocb->ki_filp; + struct inode *inode = file->f_mapping->host; + struct blk_plug plug; + int unaligned_aio = 0; + ssize_t ret; + int overwrite = 0; + size_t length = iov_length(iov, nr_segs); + + if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS) && + !is_sync_kiocb(iocb)) + unaligned_aio = ext4_unaligned_aio(inode, iov, nr_segs, pos); + + /* Unaligned direct AIO must be serialized; see comment above */ + if (unaligned_aio) { + static unsigned long unaligned_warn_time; + + /* Warn about this once per day */ + if (printk_timed_ratelimit(&unaligned_warn_time, 60*60*24*HZ)) + ext4_msg(inode->i_sb, KERN_WARNING, + "Unaligned AIO/DIO on inode %ld by %s; " + "performance will be poor.", + inode->i_ino, current->comm); + mutex_lock(ext4_aio_mutex(inode)); + ext4_aiodio_wait(inode); + } + + BUG_ON(iocb->ki_pos != pos); + + mutex_lock(&inode->i_mutex); + blk_start_plug(&plug); + + iocb->private = &overwrite; + + /* check whether we do a DIO overwrite or not */ + if (ext4_should_dioread_nolock(inode) && !unaligned_aio && + !file->f_mapping->nrpages && pos + length <= i_size_read(inode)) { + struct ext4_map_blocks map; + unsigned int blkbits = inode->i_blkbits; + int err, len; + + map.m_lblk = pos >> blkbits; + map.m_len = (EXT4_BLOCK_ALIGN(pos + length, blkbits) >> blkbits) + - map.m_lblk; + len = map.m_len; + + err = ext4_map_blocks(NULL, inode, &map, 0); + /* + * 'err==len' means that all of blocks has been preallocated no + * matter they are initialized or not. For excluding + * uninitialized extents, we need to check m_flags. There are + * two conditions that indicate for initialized extents. + * 1) If we hit extent cache, EXT4_MAP_MAPPED flag is returned; + * 2) If we do a real lookup, non-flags are returned. + * So we should check these two conditions. + */ + if (err == len && (map.m_flags & EXT4_MAP_MAPPED)) + overwrite = 1; + } + + ret = __generic_file_aio_write(iocb, iov, nr_segs, &iocb->ki_pos); + mutex_unlock(&inode->i_mutex); + + if (ret > 0 || ret == -EIOCBQUEUED) { + ssize_t err; + + err = generic_write_sync(file, pos, ret); + if (err < 0 && ret > 0) + ret = err; + } + blk_finish_plug(&plug); + + if (unaligned_aio) + mutex_unlock(ext4_aio_mutex(inode)); + + return ret; +} + +static ssize_t ext4_file_write(struct kiocb *iocb, const struct iovec *iov, unsigned long nr_segs, loff_t pos) { struct inode *inode = iocb->ki_filp->f_path.dentry->d_inode; - int unaligned_aio = 0; ssize_t ret; /* @@ -114,29 +194,12 @@ ext4_file_write(struct kiocb *iocb, const struct iovec *iov, nr_segs = iov_shorten((struct iovec *)iov, nr_segs, sbi->s_bitmap_maxbytes - pos); } - } else if (unlikely((iocb->ki_filp->f_flags & O_DIRECT) && - !is_sync_kiocb(iocb))) { - unaligned_aio = ext4_unaligned_aio(inode, iov, nr_segs, pos); } - /* Unaligned direct AIO must be serialized; see comment above */ - if (unaligned_aio) { - static unsigned long unaligned_warn_time; - - /* Warn about this once per day */ - if (printk_timed_ratelimit(&unaligned_warn_time, 60*60*24*HZ)) - ext4_msg(inode->i_sb, KERN_WARNING, - "Unaligned AIO/DIO on inode %ld by %s; " - "performance will be poor.", - inode->i_ino, current->comm); - mutex_lock(ext4_aio_mutex(inode)); - ext4_aiodio_wait(inode); - } - - ret = generic_file_aio_write(iocb, iov, nr_segs, pos); - - if (unaligned_aio) - mutex_unlock(ext4_aio_mutex(inode)); + if (unlikely(iocb->ki_filp->f_flags & O_DIRECT)) + ret = ext4_file_dio_write(iocb, iov, nr_segs, pos); + else + ret = generic_file_aio_write(iocb, iov, nr_segs, pos); return ret; } @@ -181,9 +244,21 @@ static int ext4_file_open(struct inode * inode, struct file * filp) path.dentry = mnt->mnt_root; cp = d_path(&path, buf, sizeof(buf)); if (!IS_ERR(cp)) { + handle_t *handle; + int err; + + handle = ext4_journal_start_sb(sb, 1); + if (IS_ERR(handle)) + return PTR_ERR(handle); + err = ext4_journal_get_write_access(handle, sbi->s_sbh); + if (err) { + ext4_journal_stop(handle); + return err; + } strlcpy(sbi->s_es->s_last_mounted, cp, sizeof(sbi->s_es->s_last_mounted)); - ext4_mark_super_dirty(sb); + ext4_handle_dirty_super(handle, sb); + ext4_journal_stop(handle); } } /* diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index d48e8b14928c..26154b81b836 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -315,7 +315,6 @@ out: err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh); if (!fatal) fatal = err; - ext4_mark_super_dirty(sb); } else ext4_error(sb, "bit already cleared for inode %lu", ino); @@ -830,7 +829,6 @@ got: percpu_counter_dec(&sbi->s_freeinodes_counter); if (S_ISDIR(mode)) percpu_counter_inc(&sbi->s_dirs_counter); - ext4_mark_super_dirty(sb); if (sbi->s_log_groups_per_flex) { flex_group = ext4_flex_group(sbi, group); @@ -1054,7 +1052,8 @@ unsigned long ext4_count_free_inodes(struct super_block *sb) if (!bitmap_bh) continue; - x = ext4_count_free(bitmap_bh, EXT4_INODES_PER_GROUP(sb) / 8); + x = ext4_count_free(bitmap_bh->b_data, + EXT4_INODES_PER_GROUP(sb) / 8); printk(KERN_DEBUG "group %lu: stored = %d, counted = %lu\n", (unsigned long) i, ext4_free_inodes_count(sb, gdp), x); bitmap_count += x; diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 02bc8cbe7281..89b59cb7f9b8 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -346,6 +346,15 @@ void ext4_da_update_reserve_space(struct inode *inode, used = ei->i_reserved_data_blocks; } + if (unlikely(ei->i_allocated_meta_blocks > ei->i_reserved_meta_blocks)) { + ext4_msg(inode->i_sb, KERN_NOTICE, "%s: ino %lu, allocated %d " + "with only %d reserved metadata blocks\n", __func__, + inode->i_ino, ei->i_allocated_meta_blocks, + ei->i_reserved_meta_blocks); + WARN_ON(1); + ei->i_allocated_meta_blocks = ei->i_reserved_meta_blocks; + } + /* Update per-inode reservations */ ei->i_reserved_data_blocks -= used; ei->i_reserved_meta_blocks -= ei->i_allocated_meta_blocks; @@ -544,7 +553,8 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode, * Try to see if we can get the block without requesting a new * file system block. */ - down_read((&EXT4_I(inode)->i_data_sem)); + if (!(flags & EXT4_GET_BLOCKS_NO_LOCK)) + down_read((&EXT4_I(inode)->i_data_sem)); if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) { retval = ext4_ext_map_blocks(handle, inode, map, flags & EXT4_GET_BLOCKS_KEEP_SIZE); @@ -552,7 +562,8 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode, retval = ext4_ind_map_blocks(handle, inode, map, flags & EXT4_GET_BLOCKS_KEEP_SIZE); } - up_read((&EXT4_I(inode)->i_data_sem)); + if (!(flags & EXT4_GET_BLOCKS_NO_LOCK)) + up_read((&EXT4_I(inode)->i_data_sem)); if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED) { int ret = check_block_validity(inode, map); @@ -1171,6 +1182,17 @@ static int ext4_da_reserve_space(struct inode *inode, ext4_lblk_t lblock) struct ext4_inode_info *ei = EXT4_I(inode); unsigned int md_needed; int ret; + ext4_lblk_t save_last_lblock; + int save_len; + + /* + * We will charge metadata quota at writeout time; this saves + * us from metadata over-estimation, though we may go over by + * a small amount in the end. Here we just reserve for data. + */ + ret = dquot_reserve_block(inode, EXT4_C2B(sbi, 1)); + if (ret) + return ret; /* * recalculate the amount of metadata blocks to reserve @@ -1179,32 +1201,31 @@ static int ext4_da_reserve_space(struct inode *inode, ext4_lblk_t lblock) */ repeat: spin_lock(&ei->i_block_reservation_lock); + /* + * ext4_calc_metadata_amount() has side effects, which we have + * to be prepared undo if we fail to claim space. + */ + save_len = ei->i_da_metadata_calc_len; + save_last_lblock = ei->i_da_metadata_calc_last_lblock; md_needed = EXT4_NUM_B2C(sbi, ext4_calc_metadata_amount(inode, lblock)); trace_ext4_da_reserve_space(inode, md_needed); - spin_unlock(&ei->i_block_reservation_lock); /* - * We will charge metadata quota at writeout time; this saves - * us from metadata over-estimation, though we may go over by - * a small amount in the end. Here we just reserve for data. - */ - ret = dquot_reserve_block(inode, EXT4_C2B(sbi, 1)); - if (ret) - return ret; - /* * We do still charge estimated metadata to the sb though; * we cannot afford to run out of free blocks. */ if (ext4_claim_free_clusters(sbi, md_needed + 1, 0)) { - dquot_release_reservation_block(inode, EXT4_C2B(sbi, 1)); + ei->i_da_metadata_calc_len = save_len; + ei->i_da_metadata_calc_last_lblock = save_last_lblock; + spin_unlock(&ei->i_block_reservation_lock); if (ext4_should_retry_alloc(inode->i_sb, &retries)) { yield(); goto repeat; } + dquot_release_reservation_block(inode, EXT4_C2B(sbi, 1)); return -ENOSPC; } - spin_lock(&ei->i_block_reservation_lock); ei->i_reserved_data_blocks++; ei->i_reserved_meta_blocks += md_needed; spin_unlock(&ei->i_block_reservation_lock); @@ -2818,6 +2839,32 @@ static int ext4_get_block_write(struct inode *inode, sector_t iblock, EXT4_GET_BLOCKS_IO_CREATE_EXT); } +static int ext4_get_block_write_nolock(struct inode *inode, sector_t iblock, + struct buffer_head *bh_result, int flags) +{ + handle_t *handle = ext4_journal_current_handle(); + struct ext4_map_blocks map; + int ret = 0; + + ext4_debug("ext4_get_block_write_nolock: inode %lu, flag %d\n", + inode->i_ino, flags); + + flags = EXT4_GET_BLOCKS_NO_LOCK; + + map.m_lblk = iblock; + map.m_len = bh_result->b_size >> inode->i_blkbits; + + ret = ext4_map_blocks(handle, inode, &map, flags); + if (ret > 0) { + map_bh(bh_result, inode->i_sb, map.m_pblk); + bh_result->b_state = (bh_result->b_state & ~EXT4_MAP_FLAGS) | + map.m_flags; + bh_result->b_size = inode->i_sb->s_blocksize * map.m_len; + ret = 0; + } + return ret; +} + static void ext4_end_io_dio(struct kiocb *iocb, loff_t offset, ssize_t size, void *private, int ret, bool is_async) @@ -2966,6 +3013,18 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb, loff_t final_size = offset + count; if (rw == WRITE && final_size <= inode->i_size) { + int overwrite = 0; + + BUG_ON(iocb->private == NULL); + + /* If we do a overwrite dio, i_mutex locking can be released */ + overwrite = *((int *)iocb->private); + + if (overwrite) { + down_read(&EXT4_I(inode)->i_data_sem); + mutex_unlock(&inode->i_mutex); + } + /* * We could direct write to holes and fallocate. * @@ -2991,8 +3050,10 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb, if (!is_sync_kiocb(iocb)) { ext4_io_end_t *io_end = ext4_init_io_end(inode, GFP_NOFS); - if (!io_end) - return -ENOMEM; + if (!io_end) { + ret = -ENOMEM; + goto retake_lock; + } io_end->flag |= EXT4_IO_END_DIRECT; iocb->private = io_end; /* @@ -3005,13 +3066,22 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb, EXT4_I(inode)->cur_aio_dio = iocb->private; } - ret = __blockdev_direct_IO(rw, iocb, inode, - inode->i_sb->s_bdev, iov, - offset, nr_segs, - ext4_get_block_write, - ext4_end_io_dio, - NULL, - DIO_LOCKING); + if (overwrite) + ret = __blockdev_direct_IO(rw, iocb, inode, + inode->i_sb->s_bdev, iov, + offset, nr_segs, + ext4_get_block_write_nolock, + ext4_end_io_dio, + NULL, + 0); + else + ret = __blockdev_direct_IO(rw, iocb, inode, + inode->i_sb->s_bdev, iov, + offset, nr_segs, + ext4_get_block_write, + ext4_end_io_dio, + NULL, + DIO_LOCKING); if (iocb->private) EXT4_I(inode)->cur_aio_dio = NULL; /* @@ -3031,7 +3101,7 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb, if (ret != -EIOCBQUEUED && ret <= 0 && iocb->private) { ext4_free_io_end(iocb->private); iocb->private = NULL; - } else if (ret > 0 && ext4_test_inode_state(inode, + } else if (ret > 0 && !overwrite && ext4_test_inode_state(inode, EXT4_STATE_DIO_UNWRITTEN)) { int err; /* @@ -3044,6 +3114,14 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb, ret = err; ext4_clear_inode_state(inode, EXT4_STATE_DIO_UNWRITTEN); } + + retake_lock: + /* take i_mutex locking again if we do a ovewrite dio */ + if (overwrite) { + up_read(&EXT4_I(inode)->i_data_sem); + mutex_lock(&inode->i_mutex); + } + return ret; } @@ -4034,7 +4112,7 @@ static int ext4_do_update_inode(handle_t *handle, EXT4_SET_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_LARGE_FILE); ext4_handle_sync(handle); - err = ext4_handle_dirty_super_now(handle, sb); + err = ext4_handle_dirty_super(handle, sb); } } raw_inode->i_generation = cpu_to_le32(inode->i_generation); diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 1cd6994fc446..8eae94771c45 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -969,7 +969,6 @@ static int ext4_mb_get_buddy_page_lock(struct super_block *sb, block++; pnum = block / blocks_per_page; - poff = block % blocks_per_page; page = find_or_create_page(inode->i_mapping, pnum, GFP_NOFS); if (!page) return -EIO; @@ -2077,8 +2076,9 @@ static int ext4_mb_seq_groups_show(struct seq_file *seq, void *v) struct super_block *sb = seq->private; ext4_group_t group = (ext4_group_t) ((unsigned long) v); int i; - int err; + int err, buddy_loaded = 0; struct ext4_buddy e4b; + struct ext4_group_info *grinfo; struct sg { struct ext4_group_info info; ext4_grpblk_t counters[16]; @@ -2095,15 +2095,21 @@ static int ext4_mb_seq_groups_show(struct seq_file *seq, void *v) i = (sb->s_blocksize_bits + 2) * sizeof(sg.info.bb_counters[0]) + sizeof(struct ext4_group_info); - err = ext4_mb_load_buddy(sb, group, &e4b); - if (err) { - seq_printf(seq, "#%-5u: I/O error\n", group); - return 0; + grinfo = ext4_get_group_info(sb, group); + /* Load the group info in memory only if not already loaded. */ + if (unlikely(EXT4_MB_GRP_NEED_INIT(grinfo))) { + err = ext4_mb_load_buddy(sb, group, &e4b); + if (err) { + seq_printf(seq, "#%-5u: I/O error\n", group); + return 0; + } + buddy_loaded = 1; } - ext4_lock_group(sb, group); + memcpy(&sg, ext4_get_group_info(sb, group), i); - ext4_unlock_group(sb, group); - ext4_mb_unload_buddy(&e4b); + + if (buddy_loaded) + ext4_mb_unload_buddy(&e4b); seq_printf(seq, "#%-5u: %-5u %-5u %-5u [", group, sg.info.bb_free, sg.info.bb_fragments, sg.info.bb_first_free); @@ -2825,7 +2831,6 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac, err = ext4_handle_dirty_metadata(handle, NULL, gdp_bh); out_err: - ext4_mark_super_dirty(sb); brelse(bitmap_bh); return err; } @@ -4694,7 +4699,6 @@ do_more: put_bh(bitmap_bh); goto do_more; } - ext4_mark_super_dirty(sb); error_return: brelse(bitmap_bh); ext4_std_error(sb, err); diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index d0d3f0e87f99..2a42cc04466f 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -2397,7 +2397,7 @@ int ext4_orphan_add(handle_t *handle, struct inode *inode) /* Insert this inode at the head of the on-disk orphan list... */ NEXT_ORPHAN(inode) = le32_to_cpu(EXT4_SB(sb)->s_es->s_last_orphan); EXT4_SB(sb)->s_es->s_last_orphan = cpu_to_le32(inode->i_ino); - err = ext4_handle_dirty_super_now(handle, sb); + err = ext4_handle_dirty_super(handle, sb); rc = ext4_mark_iloc_dirty(handle, inode, &iloc); if (!err) err = rc; @@ -2470,7 +2470,7 @@ int ext4_orphan_del(handle_t *handle, struct inode *inode) if (err) goto out_brelse; sbi->s_es->s_last_orphan = cpu_to_le32(ino_next); - err = ext4_handle_dirty_super_now(handle, inode->i_sb); + err = ext4_handle_dirty_super(handle, inode->i_sb); } else { struct ext4_iloc iloc2; struct inode *i_prev = @@ -2918,8 +2918,15 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry, PARENT_INO(dir_bh->b_data, new_dir->i_sb->s_blocksize) = cpu_to_le32(new_dir->i_ino); BUFFER_TRACE(dir_bh, "call ext4_handle_dirty_metadata"); - retval = ext4_handle_dirty_dirent_node(handle, old_inode, - dir_bh); + if (is_dx(old_inode)) { + retval = ext4_handle_dirty_dx_node(handle, + old_inode, + dir_bh); + } else { + retval = ext4_handle_dirty_dirent_node(handle, + old_inode, + dir_bh); + } if (retval) { ext4_std_error(old_dir->i_sb, retval); goto end_rename; diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index 7ea6cbb44121..41f6ef68e2e1 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -798,7 +798,7 @@ static int add_new_gdb(handle_t *handle, struct inode *inode, ext4_kvfree(o_group_desc); le16_add_cpu(&es->s_reserved_gdt_blocks, -1); - err = ext4_handle_dirty_super_now(handle, sb); + err = ext4_handle_dirty_super(handle, sb); if (err) ext4_std_error(sb, err); @@ -1272,6 +1272,11 @@ static void ext4_update_super(struct super_block *sb, &sbi->s_flex_groups[flex_group].free_inodes); } + /* + * Update the fs overhead information + */ + ext4_calculate_overhead(sb); + if (test_opt(sb, DEBUG)) printk(KERN_DEBUG "EXT4-fs: added group %u:" "%llu blocks(%llu free %llu reserved)\n", flex_gd->count, diff --git a/fs/ext4/super.c b/fs/ext4/super.c index d8759401ecae..2d51cd9af225 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -74,7 +74,6 @@ static const char *ext4_decode_error(struct super_block *sb, int errno, static int ext4_remount(struct super_block *sb, int *flags, char *data); static int ext4_statfs(struct dentry *dentry, struct kstatfs *buf); static int ext4_unfreeze(struct super_block *sb); -static void ext4_write_super(struct super_block *sb); static int ext4_freeze(struct super_block *sb); static struct dentry *ext4_mount(struct file_system_type *fs_type, int flags, const char *dev_name, void *data); @@ -896,7 +895,7 @@ static void ext4_put_super(struct super_block *sb) EXT4_CLEAR_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER); es->s_state = cpu_to_le16(sbi->s_mount_state); } - if (sb->s_dirt || !(sb->s_flags & MS_RDONLY)) + if (!(sb->s_flags & MS_RDONLY)) ext4_commit_super(sb, 1); if (sbi->s_proc) { @@ -1137,12 +1136,18 @@ static int ext4_mark_dquot_dirty(struct dquot *dquot); static int ext4_write_info(struct super_block *sb, int type); static int ext4_quota_on(struct super_block *sb, int type, int format_id, struct path *path); +static int ext4_quota_on_sysfile(struct super_block *sb, int type, + int format_id); static int ext4_quota_off(struct super_block *sb, int type); +static int ext4_quota_off_sysfile(struct super_block *sb, int type); static int ext4_quota_on_mount(struct super_block *sb, int type); static ssize_t ext4_quota_read(struct super_block *sb, int type, char *data, size_t len, loff_t off); static ssize_t ext4_quota_write(struct super_block *sb, int type, const char *data, size_t len, loff_t off); +static int ext4_quota_enable(struct super_block *sb, int type, int format_id, + unsigned int flags); +static int ext4_enable_quotas(struct super_block *sb); static const struct dquot_operations ext4_quota_operations = { .get_reserved_space = ext4_get_reserved_space, @@ -1164,6 +1169,16 @@ static const struct quotactl_ops ext4_qctl_operations = { .get_dqblk = dquot_get_dqblk, .set_dqblk = dquot_set_dqblk }; + +static const struct quotactl_ops ext4_qctl_sysfile_operations = { + .quota_on_meta = ext4_quota_on_sysfile, + .quota_off = ext4_quota_off_sysfile, + .quota_sync = dquot_quota_sync, + .get_info = dquot_get_dqinfo, + .set_info = dquot_set_dqinfo, + .get_dqblk = dquot_get_dqblk, + .set_dqblk = dquot_set_dqblk +}; #endif static const struct super_operations ext4_sops = { @@ -1194,7 +1209,6 @@ static const struct super_operations ext4_nojournal_sops = { .dirty_inode = ext4_dirty_inode, .drop_inode = ext4_drop_inode, .evict_inode = ext4_evict_inode, - .write_super = ext4_write_super, .put_super = ext4_put_super, .statfs = ext4_statfs, .remount_fs = ext4_remount, @@ -2661,6 +2675,16 @@ static int ext4_feature_set_ok(struct super_block *sb, int readonly) "extents feature\n"); return 0; } + +#ifndef CONFIG_QUOTA + if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA) && + !readonly) { + ext4_msg(sb, KERN_ERR, + "Filesystem with quota feature cannot be mounted RDWR " + "without CONFIG_QUOTA"); + return 0; + } +#endif /* CONFIG_QUOTA */ return 1; } @@ -3085,6 +3109,114 @@ static int set_journal_csum_feature_set(struct super_block *sb) return ret; } +/* + * Note: calculating the overhead so we can be compatible with + * historical BSD practice is quite difficult in the face of + * clusters/bigalloc. This is because multiple metadata blocks from + * different block group can end up in the same allocation cluster. + * Calculating the exact overhead in the face of clustered allocation + * requires either O(all block bitmaps) in memory or O(number of block + * groups**2) in time. We will still calculate the superblock for + * older file systems --- and if we come across with a bigalloc file + * system with zero in s_overhead_clusters the estimate will be close to + * correct especially for very large cluster sizes --- but for newer + * file systems, it's better to calculate this figure once at mkfs + * time, and store it in the superblock. If the superblock value is + * present (even for non-bigalloc file systems), we will use it. + */ +static int count_overhead(struct super_block *sb, ext4_group_t grp, + char *buf) +{ + struct ext4_sb_info *sbi = EXT4_SB(sb); + struct ext4_group_desc *gdp; + ext4_fsblk_t first_block, last_block, b; + ext4_group_t i, ngroups = ext4_get_groups_count(sb); + int s, j, count = 0; + + first_block = le32_to_cpu(sbi->s_es->s_first_data_block) + + (grp * EXT4_BLOCKS_PER_GROUP(sb)); + last_block = first_block + EXT4_BLOCKS_PER_GROUP(sb) - 1; + for (i = 0; i < ngroups; i++) { + gdp = ext4_get_group_desc(sb, i, NULL); + b = ext4_block_bitmap(sb, gdp); + if (b >= first_block && b <= last_block) { + ext4_set_bit(EXT4_B2C(sbi, b - first_block), buf); + count++; + } + b = ext4_inode_bitmap(sb, gdp); + if (b >= first_block && b <= last_block) { + ext4_set_bit(EXT4_B2C(sbi, b - first_block), buf); + count++; + } + b = ext4_inode_table(sb, gdp); + if (b >= first_block && b + sbi->s_itb_per_group <= last_block) + for (j = 0; j < sbi->s_itb_per_group; j++, b++) { + int c = EXT4_B2C(sbi, b - first_block); + ext4_set_bit(c, buf); + count++; + } + if (i != grp) + continue; + s = 0; + if (ext4_bg_has_super(sb, grp)) { + ext4_set_bit(s++, buf); + count++; + } + for (j = ext4_bg_num_gdb(sb, grp); j > 0; j--) { + ext4_set_bit(EXT4_B2C(sbi, s++), buf); + count++; + } + } + if (!count) + return 0; + return EXT4_CLUSTERS_PER_GROUP(sb) - + ext4_count_free(buf, EXT4_CLUSTERS_PER_GROUP(sb) / 8); +} + +/* + * Compute the overhead and stash it in sbi->s_overhead + */ +int ext4_calculate_overhead(struct super_block *sb) +{ + struct ext4_sb_info *sbi = EXT4_SB(sb); + struct ext4_super_block *es = sbi->s_es; + ext4_group_t i, ngroups = ext4_get_groups_count(sb); + ext4_fsblk_t overhead = 0; + char *buf = (char *) get_zeroed_page(GFP_KERNEL); + + memset(buf, 0, PAGE_SIZE); + if (!buf) + return -ENOMEM; + + /* + * Compute the overhead (FS structures). This is constant + * for a given filesystem unless the number of block groups + * changes so we cache the previous value until it does. + */ + + /* + * All of the blocks before first_data_block are overhead + */ + overhead = EXT4_B2C(sbi, le32_to_cpu(es->s_first_data_block)); + + /* + * Add the overhead found in each block group + */ + for (i = 0; i < ngroups; i++) { + int blks; + + blks = count_overhead(sb, i, buf); + overhead += blks; + if (blks) + memset(buf, 0, PAGE_SIZE); + cond_resched(); + } + sbi->s_overhead = overhead; + smp_wmb(); + free_page((unsigned long) buf); + return 0; +} + static int ext4_fill_super(struct super_block *sb, void *data, int silent) { char *orig_data = kstrdup(data, GFP_KERNEL); @@ -3640,6 +3772,11 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) #ifdef CONFIG_QUOTA sb->s_qcop = &ext4_qctl_operations; sb->dq_op = &ext4_quota_operations; + + if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA)) { + /* Use qctl operations for hidden quota files. */ + sb->s_qcop = &ext4_qctl_sysfile_operations; + } #endif memcpy(sb->s_uuid, es->s_uuid, sizeof(es->s_uuid)); @@ -3735,6 +3872,18 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) no_journal: /* + * Get the # of file system overhead blocks from the + * superblock if present. + */ + if (es->s_overhead_clusters) + sbi->s_overhead = le32_to_cpu(es->s_overhead_clusters); + else { + ret = ext4_calculate_overhead(sb); + if (ret) + goto failed_mount_wq; + } + + /* * The maximum number of concurrent works can be high and * concurrency isn't really necessary. Limit it to 1. */ @@ -3840,6 +3989,16 @@ no_journal: } else descr = "out journal"; +#ifdef CONFIG_QUOTA + /* Enable quota usage during mount. */ + if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA) && + !(sb->s_flags & MS_RDONLY)) { + ret = ext4_enable_quotas(sb); + if (ret) + goto failed_mount7; + } +#endif /* CONFIG_QUOTA */ + ext4_msg(sb, KERN_INFO, "mounted filesystem with%s. " "Opts: %s%s%s", descr, sbi->s_es->s_mount_opts, *sbi->s_es->s_mount_opts ? "; " : "", orig_data); @@ -4203,7 +4362,6 @@ static int ext4_commit_super(struct super_block *sb, int sync) es->s_free_inodes_count = cpu_to_le32(percpu_counter_sum_positive( &EXT4_SB(sb)->s_freeinodes_counter)); - sb->s_dirt = 0; BUFFER_TRACE(sbh, "marking dirty"); ext4_superblock_csum_set(sb, es); mark_buffer_dirty(sbh); @@ -4310,13 +4468,6 @@ int ext4_force_commit(struct super_block *sb) return ret; } -static void ext4_write_super(struct super_block *sb) -{ - lock_super(sb); - ext4_commit_super(sb, 1); - unlock_super(sb); -} - static int ext4_sync_fs(struct super_block *sb, int wait) { int ret = 0; @@ -4567,16 +4718,26 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) if (sbi->s_journal == NULL) ext4_commit_super(sb, 1); + unlock_super(sb); #ifdef CONFIG_QUOTA /* Release old quota file names */ for (i = 0; i < MAXQUOTAS; i++) if (old_opts.s_qf_names[i] && old_opts.s_qf_names[i] != sbi->s_qf_names[i]) kfree(old_opts.s_qf_names[i]); + if (enable_quota) { + if (sb_any_quota_suspended(sb)) + dquot_resume(sb, -1); + else if (EXT4_HAS_RO_COMPAT_FEATURE(sb, + EXT4_FEATURE_RO_COMPAT_QUOTA)) { + err = ext4_enable_quotas(sb); + if (err) { + lock_super(sb); + goto restore_opts; + } + } + } #endif - unlock_super(sb); - if (enable_quota) - dquot_resume(sb, -1); ext4_msg(sb, KERN_INFO, "re-mounted. Opts: %s", orig_data); kfree(orig_data); @@ -4605,67 +4766,21 @@ restore_opts: return err; } -/* - * Note: calculating the overhead so we can be compatible with - * historical BSD practice is quite difficult in the face of - * clusters/bigalloc. This is because multiple metadata blocks from - * different block group can end up in the same allocation cluster. - * Calculating the exact overhead in the face of clustered allocation - * requires either O(all block bitmaps) in memory or O(number of block - * groups**2) in time. We will still calculate the superblock for - * older file systems --- and if we come across with a bigalloc file - * system with zero in s_overhead_clusters the estimate will be close to - * correct especially for very large cluster sizes --- but for newer - * file systems, it's better to calculate this figure once at mkfs - * time, and store it in the superblock. If the superblock value is - * present (even for non-bigalloc file systems), we will use it. - */ static int ext4_statfs(struct dentry *dentry, struct kstatfs *buf) { struct super_block *sb = dentry->d_sb; struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_super_block *es = sbi->s_es; - struct ext4_group_desc *gdp; + ext4_fsblk_t overhead = 0; u64 fsid; s64 bfree; - if (test_opt(sb, MINIX_DF)) { - sbi->s_overhead_last = 0; - } else if (es->s_overhead_clusters) { - sbi->s_overhead_last = le32_to_cpu(es->s_overhead_clusters); - } else if (sbi->s_blocks_last != ext4_blocks_count(es)) { - ext4_group_t i, ngroups = ext4_get_groups_count(sb); - ext4_fsblk_t overhead = 0; - - /* - * Compute the overhead (FS structures). This is constant - * for a given filesystem unless the number of block groups - * changes so we cache the previous value until it does. - */ - - /* - * All of the blocks before first_data_block are - * overhead - */ - overhead = EXT4_B2C(sbi, le32_to_cpu(es->s_first_data_block)); - - /* - * Add the overhead found in each block group - */ - for (i = 0; i < ngroups; i++) { - gdp = ext4_get_group_desc(sb, i, NULL); - overhead += ext4_num_overhead_clusters(sb, i, gdp); - cond_resched(); - } - sbi->s_overhead_last = overhead; - smp_wmb(); - sbi->s_blocks_last = ext4_blocks_count(es); - } + if (!test_opt(sb, MINIX_DF)) + overhead = sbi->s_overhead; buf->f_type = EXT4_SUPER_MAGIC; buf->f_bsize = sb->s_blocksize; - buf->f_blocks = (ext4_blocks_count(es) - - EXT4_C2B(sbi, sbi->s_overhead_last)); + buf->f_blocks = ext4_blocks_count(es) - EXT4_C2B(sbi, sbi->s_overhead); bfree = percpu_counter_sum_positive(&sbi->s_freeclusters_counter) - percpu_counter_sum_positive(&sbi->s_dirtyclusters_counter); /* prevent underflow in case that few free space is available */ @@ -4835,6 +4950,74 @@ static int ext4_quota_on(struct super_block *sb, int type, int format_id, return dquot_quota_on(sb, type, format_id, path); } +static int ext4_quota_enable(struct super_block *sb, int type, int format_id, + unsigned int flags) +{ + int err; + struct inode *qf_inode; + unsigned long qf_inums[MAXQUOTAS] = { + le32_to_cpu(EXT4_SB(sb)->s_es->s_usr_quota_inum), + le32_to_cpu(EXT4_SB(sb)->s_es->s_grp_quota_inum) + }; + + BUG_ON(!EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA)); + + if (!qf_inums[type]) + return -EPERM; + + qf_inode = ext4_iget(sb, qf_inums[type]); + if (IS_ERR(qf_inode)) { + ext4_error(sb, "Bad quota inode # %lu", qf_inums[type]); + return PTR_ERR(qf_inode); + } + + err = dquot_enable(qf_inode, type, format_id, flags); + iput(qf_inode); + + return err; +} + +/* Enable usage tracking for all quota types. */ +static int ext4_enable_quotas(struct super_block *sb) +{ + int type, err = 0; + unsigned long qf_inums[MAXQUOTAS] = { + le32_to_cpu(EXT4_SB(sb)->s_es->s_usr_quota_inum), + le32_to_cpu(EXT4_SB(sb)->s_es->s_grp_quota_inum) + }; + + sb_dqopt(sb)->flags |= DQUOT_QUOTA_SYS_FILE; + for (type = 0; type < MAXQUOTAS; type++) { + if (qf_inums[type]) { + err = ext4_quota_enable(sb, type, QFMT_VFS_V1, + DQUOT_USAGE_ENABLED); + if (err) { + ext4_warning(sb, + "Failed to enable quota (type=%d) " + "tracking. Please run e2fsck to fix.", + type); + return err; + } + } + } + return 0; +} + +/* + * quota_on function that is used when QUOTA feature is set. + */ +static int ext4_quota_on_sysfile(struct super_block *sb, int type, + int format_id) +{ + if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA)) + return -EINVAL; + + /* + * USAGE was enabled at mount time. Only need to enable LIMITS now. + */ + return ext4_quota_enable(sb, type, format_id, DQUOT_LIMITS_ENABLED); +} + static int ext4_quota_off(struct super_block *sb, int type) { struct inode *inode = sb_dqopt(sb)->files[type]; @@ -4861,6 +5044,18 @@ out: return dquot_quota_off(sb, type); } +/* + * quota_off function that is used when QUOTA feature is set. + */ +static int ext4_quota_off_sysfile(struct super_block *sb, int type) +{ + if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA)) + return -EINVAL; + + /* Disable only the limits. */ + return dquot_disable(sb, type, DQUOT_LIMITS_ENABLED); +} + /* Read data from quotafile - avoid pagecache and such because we cannot afford * acquiring the locks... As quota files are never truncated and quota code * itself serializes the operations (and no one else should touch the files) diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index e56c9ed7d6e3..2cdb98d62980 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -127,19 +127,16 @@ static __le32 ext4_xattr_block_csum(struct inode *inode, struct ext4_xattr_header *hdr) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); - struct ext4_inode_info *ei = EXT4_I(inode); __u32 csum, old; old = hdr->h_checksum; hdr->h_checksum = 0; - if (le32_to_cpu(hdr->h_refcount) != 1) { - block_nr = cpu_to_le64(block_nr); - csum = ext4_chksum(sbi, sbi->s_csum_seed, (__u8 *)&block_nr, - sizeof(block_nr)); - } else - csum = ei->i_csum_seed; + block_nr = cpu_to_le64(block_nr); + csum = ext4_chksum(sbi, sbi->s_csum_seed, (__u8 *)&block_nr, + sizeof(block_nr)); csum = ext4_chksum(sbi, csum, (__u8 *)hdr, EXT4_BLOCK_SIZE(inode->i_sb)); + hdr->h_checksum = old; return cpu_to_le32(csum); } diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c index 216f4299f65e..af5280fb579b 100644 --- a/fs/jbd2/commit.c +++ b/fs/jbd2/commit.c @@ -349,12 +349,12 @@ static void jbd2_block_tag_csum_set(journal_t *j, journal_block_tag_t *tag, return; sequence = cpu_to_be32(sequence); - addr = kmap_atomic(page, KM_USER0); + addr = kmap_atomic(page); csum = jbd2_chksum(j, j->j_csum_seed, (__u8 *)&sequence, sizeof(sequence)); csum = jbd2_chksum(j, csum, addr + offset_in_page(bh->b_data), bh->b_size); - kunmap_atomic(addr, KM_USER0); + kunmap_atomic(addr); tag->t_checksum = cpu_to_be32(csum); } diff --git a/fs/pipe.c b/fs/pipe.c index 49c1065256fd..95cbd6b227e6 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -224,7 +224,7 @@ static void anon_pipe_buf_release(struct pipe_inode_info *pipe, * and the caller has to be careful not to fault before calling * the unmap function. * - * Note that this function occupies KM_USER0 if @atomic != 0. + * Note that this function calls kmap_atomic() if @atomic != 0. */ void *generic_pipe_buf_map(struct pipe_inode_info *pipe, struct pipe_buffer *buf, int atomic) diff --git a/include/asm-generic/kmap_types.h b/include/asm-generic/kmap_types.h index 0232ccb76f2b..90f99c74dd38 100644 --- a/include/asm-generic/kmap_types.h +++ b/include/asm-generic/kmap_types.h @@ -2,39 +2,9 @@ #define _ASM_GENERIC_KMAP_TYPES_H #ifdef __WITH_KM_FENCE -# define KMAP_D(n) __KM_FENCE_##n , +# define KM_TYPE_NR 41 #else -# define KMAP_D(n) +# define KM_TYPE_NR 20 #endif -enum km_type { -KMAP_D(0) KM_BOUNCE_READ, -KMAP_D(1) KM_SKB_SUNRPC_DATA, -KMAP_D(2) KM_SKB_DATA_SOFTIRQ, -KMAP_D(3) KM_USER0, -KMAP_D(4) KM_USER1, -KMAP_D(5) KM_BIO_SRC_IRQ, -KMAP_D(6) KM_BIO_DST_IRQ, -KMAP_D(7) KM_PTE0, -KMAP_D(8) KM_PTE1, -KMAP_D(9) KM_IRQ0, -KMAP_D(10) KM_IRQ1, -KMAP_D(11) KM_SOFTIRQ0, -KMAP_D(12) KM_SOFTIRQ1, -KMAP_D(13) KM_SYNC_ICACHE, -KMAP_D(14) KM_SYNC_DCACHE, -/* UML specific, for copy_*_user - used in do_op_one_page */ -KMAP_D(15) KM_UML_USERCOPY, -KMAP_D(16) KM_IRQ_PTE, -KMAP_D(17) KM_NMI, -KMAP_D(18) KM_NMI_PTE, -KMAP_D(19) KM_KDB, -/* - * Remember to update debug_kmap_atomic() when adding new kmap types! - */ -KMAP_D(20) KM_TYPE_NR -}; - -#undef KMAP_D - #endif diff --git a/include/asm-generic/sizes.h b/include/asm-generic/sizes.h index ea5d4ef81061..1dcfad9629ef 100644 --- a/include/asm-generic/sizes.h +++ b/include/asm-generic/sizes.h @@ -1,47 +1,2 @@ -/* - * linux/include/asm-generic/sizes.h - * - * 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. - */ -#ifndef __ASM_GENERIC_SIZES_H__ -#define __ASM_GENERIC_SIZES_H__ - -#define SZ_1 0x00000001 -#define SZ_2 0x00000002 -#define SZ_4 0x00000004 -#define SZ_8 0x00000008 -#define SZ_16 0x00000010 -#define SZ_32 0x00000020 -#define SZ_64 0x00000040 -#define SZ_128 0x00000080 -#define SZ_256 0x00000100 -#define SZ_512 0x00000200 - -#define SZ_1K 0x00000400 -#define SZ_2K 0x00000800 -#define SZ_4K 0x00001000 -#define SZ_8K 0x00002000 -#define SZ_16K 0x00004000 -#define SZ_32K 0x00008000 -#define SZ_64K 0x00010000 -#define SZ_128K 0x00020000 -#define SZ_256K 0x00040000 -#define SZ_512K 0x00080000 - -#define SZ_1M 0x00100000 -#define SZ_2M 0x00200000 -#define SZ_4M 0x00400000 -#define SZ_8M 0x00800000 -#define SZ_16M 0x01000000 -#define SZ_32M 0x02000000 -#define SZ_64M 0x04000000 -#define SZ_128M 0x08000000 -#define SZ_256M 0x10000000 -#define SZ_512M 0x20000000 - -#define SZ_1G 0x40000000 -#define SZ_2G 0x80000000 - -#endif /* __ASM_GENERIC_SIZES_H__ */ +/* This is a placeholder, to be removed over time */ +#include <linux/sizes.h> diff --git a/include/linux/highmem.h b/include/linux/highmem.h index d3999b4e26cc..774fa47b3b5b 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -110,54 +110,15 @@ static inline void kmap_atomic_idx_pop(void) #endif /* - * NOTE: - * kmap_atomic() and kunmap_atomic() with two arguments are deprecated. - * We only keep them for backward compatibility, any usage of them - * are now warned. - */ - -#define PASTE(a, b) a ## b -#define PASTE2(a, b) PASTE(a, b) - -#define NARG_(_2, _1, n, ...) n -#define NARG(...) NARG_(__VA_ARGS__, 2, 1, :) - -static inline void __deprecated *kmap_atomic_deprecated(struct page *page, - enum km_type km) -{ - return kmap_atomic(page); -} - -#define kmap_atomic1(...) kmap_atomic(__VA_ARGS__) -#define kmap_atomic2(...) kmap_atomic_deprecated(__VA_ARGS__) -#define kmap_atomic(...) PASTE2(kmap_atomic, NARG(__VA_ARGS__)(__VA_ARGS__)) - -static inline void __deprecated __kunmap_atomic_deprecated(void *addr, - enum km_type km) -{ - __kunmap_atomic(addr); -} - -/* * Prevent people trying to call kunmap_atomic() as if it were kunmap() * kunmap_atomic() should get the return value of kmap_atomic, not the page. */ -#define kunmap_atomic_deprecated(addr, km) \ -do { \ - BUILD_BUG_ON(__same_type((addr), struct page *)); \ - __kunmap_atomic_deprecated(addr, km); \ -} while (0) - -#define kunmap_atomic_withcheck(addr) \ +#define kunmap_atomic(addr) \ do { \ BUILD_BUG_ON(__same_type((addr), struct page *)); \ __kunmap_atomic(addr); \ } while (0) -#define kunmap_atomic1(...) kunmap_atomic_withcheck(__VA_ARGS__) -#define kunmap_atomic2(...) kunmap_atomic_deprecated(__VA_ARGS__) -#define kunmap_atomic(...) PASTE2(kunmap_atomic, NARG(__VA_ARGS__)(__VA_ARGS__)) -/**** End of C pre-processor tricks for deprecated macros ****/ /* when CONFIG_HIGHMEM is not set these will be plain clear/copy_page */ #ifndef clear_user_highpage diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h index e1ac1ce16fb0..e11d1c0fc60f 100644 --- a/include/linux/pipe_fs_i.h +++ b/include/linux/pipe_fs_i.h @@ -86,11 +86,9 @@ struct pipe_buf_operations { * mapping or not. The atomic map is faster, however you can't take * page faults before calling ->unmap() again. So if you need to eg * access user data through copy_to/from_user(), then you must get - * a non-atomic map. ->map() uses the KM_USER0 atomic slot for - * atomic maps, so you can't map more than one pipe_buffer at once - * and you have to be careful if mapping another page as source - * or destination for a copy (IOW, it has to use something else - * than KM_USER0). + * a non-atomic map. ->map() uses the kmap_atomic slot for + * atomic maps, you have to be careful if mapping another page as + * source or destination for a copy. */ void * (*map)(struct pipe_inode_info *, struct pipe_buffer *, int); diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index 65db9928e15f..0253c2022e53 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -47,7 +47,8 @@ #define PORT_U6_16550A 19 /* ST-Ericsson U6xxx internal UART */ #define PORT_TEGRA 20 /* NVIDIA Tegra internal UART */ #define PORT_XR17D15X 21 /* Exar XR17D15x UART */ -#define PORT_MAX_8250 21 /* max port ID */ +#define PORT_LPC3220 22 /* NXP LPC32xx SoC "Standard" UART */ +#define PORT_MAX_8250 22 /* max port ID */ /* * ARM specific type numbers. These are not currently guaranteed diff --git a/include/linux/sizes.h b/include/linux/sizes.h new file mode 100644 index 000000000000..ce3e8150c174 --- /dev/null +++ b/include/linux/sizes.h @@ -0,0 +1,47 @@ +/* + * include/linux/sizes.h + * + * 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. + */ +#ifndef __LINUX_SIZES_H__ +#define __LINUX_SIZES_H__ + +#define SZ_1 0x00000001 +#define SZ_2 0x00000002 +#define SZ_4 0x00000004 +#define SZ_8 0x00000008 +#define SZ_16 0x00000010 +#define SZ_32 0x00000020 +#define SZ_64 0x00000040 +#define SZ_128 0x00000080 +#define SZ_256 0x00000100 +#define SZ_512 0x00000200 + +#define SZ_1K 0x00000400 +#define SZ_2K 0x00000800 +#define SZ_4K 0x00001000 +#define SZ_8K 0x00002000 +#define SZ_16K 0x00004000 +#define SZ_32K 0x00008000 +#define SZ_64K 0x00010000 +#define SZ_128K 0x00020000 +#define SZ_256K 0x00040000 +#define SZ_512K 0x00080000 + +#define SZ_1M 0x00100000 +#define SZ_2M 0x00200000 +#define SZ_4M 0x00400000 +#define SZ_8M 0x00800000 +#define SZ_16M 0x01000000 +#define SZ_32M 0x02000000 +#define SZ_64M 0x04000000 +#define SZ_128M 0x08000000 +#define SZ_256M 0x10000000 +#define SZ_512M 0x20000000 + +#define SZ_1G 0x40000000 +#define SZ_2G 0x80000000 + +#endif /* __LINUX_SIZES_H__ */ diff --git a/init/Kconfig b/init/Kconfig index d07dcf9fc8a9..b3f55f15e107 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -357,7 +357,7 @@ config AUDIT config AUDITSYSCALL bool "Enable system-call auditing support" - depends on AUDIT && (X86 || PPC || S390 || IA64 || UML || SPARC64 || SUPERH || ARM) + depends on AUDIT && (X86 || PPC || S390 || IA64 || UML || SPARC64 || SUPERH || (ARM && AEABI && !OABI_COMPAT)) default y if SECURITY_SELINUX help Enable low-overhead system-call auditing infrastructure that diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 2aad49981b57..c7ac8e1b3ac7 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -1975,9 +1975,7 @@ static int aligned_vwrite(char *buf, char *addr, unsigned long count) * IOREMAP area is treated as memory hole and no copy is done. * * If [addr...addr+count) doesn't includes any intersects with alive - * vm_struct area, returns 0. - * @buf should be kernel's buffer. Because this function uses KM_USER0, - * the caller should guarantee KM_USER0 is not used. + * vm_struct area, returns 0. @buf should be kernel's buffer. * * Note: In usual ops, vread() is never necessary because the caller * should know vmalloc() area is valid and can use memcpy(). @@ -2051,9 +2049,7 @@ finished: * IOREMAP area is treated as memory hole and no copy is done. * * If [addr...addr+count) doesn't includes any intersects with alive - * vm_struct area, returns 0. - * @buf should be kernel's buffer. Because this function uses KM_USER0, - * the caller should guarantee KM_USER0 is not used. + * vm_struct area, returns 0. @buf should be kernel's buffer. * * Note: In usual ops, vwrite() is never necessary because the caller * should know vmalloc() area is valid and can use memcpy(). |