diff options
-rw-r--r-- | Documentation/cpusets.txt | 3 | ||||
-rw-r--r-- | arch/i386/boot/video.S | 14 | ||||
-rw-r--r-- | arch/i386/kernel/apic.c | 32 | ||||
-rw-r--r-- | arch/i386/kernel/cpu/amd.c | 34 | ||||
-rw-r--r-- | arch/i386/kernel/microcode.c | 71 | ||||
-rw-r--r-- | arch/i386/kernel/nmi.c | 129 | ||||
-rw-r--r-- | arch/i386/lib/usercopy.c | 9 | ||||
-rw-r--r-- | arch/um/sys-i386/delay.c | 11 | ||||
-rw-r--r-- | arch/um/sys-x86_64/delay.c | 11 | ||||
-rw-r--r-- | arch/x86_64/boot/video.S | 14 | ||||
-rw-r--r-- | arch/x86_64/kernel/nmi.c | 120 | ||||
-rw-r--r-- | drivers/char/vt_ioctl.c | 16 | ||||
-rw-r--r-- | drivers/mfd/sm501.c | 2 | ||||
-rw-r--r-- | drivers/pnp/system.c | 13 | ||||
-rw-r--r-- | drivers/rtc/rtc-cmos.c | 50 | ||||
-rw-r--r-- | fs/binfmt_elf.c | 5 | ||||
-rw-r--r-- | fs/binfmt_elf_fdpic.c | 2 | ||||
-rw-r--r-- | fs/ext3/inode.c | 85 | ||||
-rw-r--r-- | fs/ext4/inode.c | 85 | ||||
-rw-r--r-- | fs/proc/internal.h | 4 | ||||
-rw-r--r-- | fs/proc/root.c | 2 | ||||
-rw-r--r-- | include/asm-i386/cpufeature.h | 1 | ||||
-rw-r--r-- | include/asm-i386/msr.h | 2 | ||||
-rw-r--r-- | include/asm-um/delay.h | 17 | ||||
-rw-r--r-- | include/linux/cpu.h | 4 | ||||
-rw-r--r-- | include/linux/device.h | 1 | ||||
-rw-r--r-- | kernel/cpu.c | 32 | ||||
-rw-r--r-- | kernel/module.c | 18 |
28 files changed, 469 insertions, 318 deletions
diff --git a/Documentation/cpusets.txt b/Documentation/cpusets.txt index 842f0d1ab21..f2c0a684293 100644 --- a/Documentation/cpusets.txt +++ b/Documentation/cpusets.txt @@ -557,6 +557,9 @@ Set some flags: Add some cpus: # /bin/echo 0-7 > cpus +Add some mems: +# /bin/echo 0-7 > mems + Now attach your shell to this cpuset: # /bin/echo $$ > tasks diff --git a/arch/i386/boot/video.S b/arch/i386/boot/video.S index 2c5b5cc55f7..8143c9516cb 100644 --- a/arch/i386/boot/video.S +++ b/arch/i386/boot/video.S @@ -571,6 +571,16 @@ setr1: lodsw jmp _m_s check_vesa: +#ifdef CONFIG_FIRMWARE_EDID + leaw modelist+1024, %di + movw $0x4f00, %ax + int $0x10 + cmpw $0x004f, %ax + jnz setbad + + movw 4(%di), %ax + movw %ax, vbe_version +#endif leaw modelist+1024, %di subb $VIDEO_FIRST_VESA>>8, %bh movw %bx, %cx # Get mode information structure @@ -1945,6 +1955,9 @@ store_edid: rep stosl + cmpw $0x0200, vbe_version # only do EDID on >= VBE2.0 + jl no_edid + pushw %es # save ES xorw %di, %di # Report Capability pushw %di @@ -1987,6 +2000,7 @@ do_restore: .byte 0 # Screen contents altered during mode change svga_prefix: .byte VIDEO_FIRST_BIOS>>8 # Default prefix for BIOS modes graphic_mode: .byte 0 # Graphic mode with a linear frame buffer dac_size: .byte 6 # DAC bit depth +vbe_version: .word 0 # VBE bios version # Status messages keymsg: .ascii "Press <RETURN> to see video modes available, " diff --git a/arch/i386/kernel/apic.c b/arch/i386/kernel/apic.c index e88415282a6..93aa911646a 100644 --- a/arch/i386/kernel/apic.c +++ b/arch/i386/kernel/apic.c @@ -272,32 +272,6 @@ static void __devinit setup_APIC_timer(void) } /* - * Detect systems with known broken BIOS implementations - */ -static int __init lapic_check_broken_bios(struct dmi_system_id *d) -{ - printk(KERN_NOTICE "%s detected: disabling lapic timer.\n", - d->ident); - local_apic_timer_disabled = 1; - return 0; -} - -static struct dmi_system_id __initdata broken_bios_dmi_table[] = { - { - /* - * BIOS exports only C1 state, but uses deeper power - * modes behind the kernels back. - */ - .callback = lapic_check_broken_bios, - .ident = "HP nx6325", - .matches = { - DMI_MATCH(DMI_PRODUCT_NAME, "HP Compaq nx6325"), - }, - }, - {} -}; - -/* * In this functions we calibrate APIC bus clocks to the external timer. * * We want to do the calibration only once since we want to have local timer @@ -372,12 +346,12 @@ void __init setup_boot_APIC_clock(void) long delta, deltapm; int pm_referenced = 0; - /* Detect know broken systems */ - dmi_check_system(broken_bios_dmi_table); + if (boot_cpu_has(X86_FEATURE_LAPIC_TIMER_BROKEN)) + local_apic_timer_disabled = 1; /* * The local apic timer can be disabled via the kernel - * commandline or from the dmi quirk above. Register the lapic + * commandline or from the test above. Register the lapic * timer as a dummy clock event source on SMP systems, so the * broadcast mechanism is used. On UP systems simply ignore it. */ diff --git a/arch/i386/kernel/cpu/amd.c b/arch/i386/kernel/cpu/amd.c index 41cfea57232..2d47db48297 100644 --- a/arch/i386/kernel/cpu/amd.c +++ b/arch/i386/kernel/cpu/amd.c @@ -22,6 +22,37 @@ extern void vide(void); __asm__(".align 4\nvide: ret"); +#define ENABLE_C1E_MASK 0x18000000 +#define CPUID_PROCESSOR_SIGNATURE 1 +#define CPUID_XFAM 0x0ff00000 +#define CPUID_XFAM_K8 0x00000000 +#define CPUID_XFAM_10H 0x00100000 +#define CPUID_XFAM_11H 0x00200000 +#define CPUID_XMOD 0x000f0000 +#define CPUID_XMOD_REV_F 0x00040000 + +/* AMD systems with C1E don't have a working lAPIC timer. Check for that. */ +static __cpuinit int amd_apic_timer_broken(void) +{ + u32 lo, hi; + u32 eax = cpuid_eax(CPUID_PROCESSOR_SIGNATURE); + switch (eax & CPUID_XFAM) { + case CPUID_XFAM_K8: + if ((eax & CPUID_XMOD) < CPUID_XMOD_REV_F) + break; + case CPUID_XFAM_10H: + case CPUID_XFAM_11H: + rdmsr(MSR_K8_ENABLE_C1E, lo, hi); + if (lo & ENABLE_C1E_MASK) + return 1; + break; + default: + /* err on the side of caution */ + return 1; + } + return 0; +} + static void __cpuinit init_amd(struct cpuinfo_x86 *c) { u32 l, h; @@ -241,6 +272,9 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c) if (cpuid_eax(0x80000000) >= 0x80000006) num_cache_leaves = 3; + + if (amd_apic_timer_broken()) + set_bit(X86_FEATURE_LAPIC_TIMER_BROKEN, c->x86_capability); } static unsigned int __cpuinit amd_size_cache(struct cpuinfo_x86 * c, unsigned int size) diff --git a/arch/i386/kernel/microcode.c b/arch/i386/kernel/microcode.c index b8f16633a6e..cbe7ec8dbb9 100644 --- a/arch/i386/kernel/microcode.c +++ b/arch/i386/kernel/microcode.c @@ -567,6 +567,53 @@ static int cpu_request_microcode(int cpu) return error; } +static int apply_microcode_on_cpu(int cpu) +{ + struct cpuinfo_x86 *c = cpu_data + cpu; + struct ucode_cpu_info *uci = ucode_cpu_info + cpu; + cpumask_t old; + unsigned int val[2]; + int err = 0; + + if (!uci->mc) + return -EINVAL; + + old = current->cpus_allowed; + set_cpus_allowed(current, cpumask_of_cpu(cpu)); + + /* Check if the microcode we have in memory matches the CPU */ + if (c->x86_vendor != X86_VENDOR_INTEL || c->x86 < 6 || + cpu_has(c, X86_FEATURE_IA64) || uci->sig != cpuid_eax(0x00000001)) + err = -EINVAL; + + if (!err && ((c->x86_model >= 5) || (c->x86 > 6))) { + /* get processor flags from MSR 0x17 */ + rdmsr(MSR_IA32_PLATFORM_ID, val[0], val[1]); + if (uci->pf != (1 << ((val[1] >> 18) & 7))) + err = -EINVAL; + } + + if (!err) { + wrmsr(MSR_IA32_UCODE_REV, 0, 0); + /* see notes above for revision 1.07. Apparent chip bug */ + sync_core(); + /* get the current revision from MSR 0x8B */ + rdmsr(MSR_IA32_UCODE_REV, val[0], val[1]); + if (uci->rev != val[1]) + err = -EINVAL; + } + + if (!err) + apply_microcode(cpu); + else + printk(KERN_ERR "microcode: Could not apply microcode to CPU%d:" + " sig=0x%x, pf=0x%x, rev=0x%x\n", + cpu, uci->sig, uci->pf, uci->rev); + + set_cpus_allowed(current, old); + return err; +} + static void microcode_init_cpu(int cpu) { cpumask_t old; @@ -577,7 +624,8 @@ static void microcode_init_cpu(int cpu) set_cpus_allowed(current, cpumask_of_cpu(cpu)); mutex_lock(µcode_mutex); collect_cpu_info(cpu); - if (uci->valid && system_state == SYSTEM_RUNNING) + if (uci->valid && system_state == SYSTEM_RUNNING && + !suspend_cpu_hotplug) cpu_request_microcode(cpu); mutex_unlock(µcode_mutex); set_cpus_allowed(current, old); @@ -663,13 +711,24 @@ static int mc_sysdev_add(struct sys_device *sys_dev) return 0; pr_debug("Microcode:CPU %d added\n", cpu); - memset(uci, 0, sizeof(*uci)); + /* If suspend_cpu_hotplug is set, the system is resuming and we should + * use the data from before the suspend. + */ + if (suspend_cpu_hotplug) { + err = apply_microcode_on_cpu(cpu); + if (err) + microcode_fini_cpu(cpu); + } + if (!uci->valid) + memset(uci, 0, sizeof(*uci)); err = sysfs_create_group(&sys_dev->kobj, &mc_attr_group); if (err) return err; - microcode_init_cpu(cpu); + if (!uci->valid) + microcode_init_cpu(cpu); + return 0; } @@ -680,7 +739,11 @@ static int mc_sysdev_remove(struct sys_device *sys_dev) if (!cpu_online(cpu)) return 0; pr_debug("Microcode:CPU %d removed\n", cpu); - microcode_fini_cpu(cpu); + /* If suspend_cpu_hotplug is set, the system is suspending and we should + * keep the microcode in memory for the resume. + */ + if (!suspend_cpu_hotplug) + microcode_fini_cpu(cpu); sysfs_remove_group(&sys_dev->kobj, &mc_attr_group); return 0; } diff --git a/arch/i386/kernel/nmi.c b/arch/i386/kernel/nmi.c index 14702427b10..a98ba88a8c0 100644 --- a/arch/i386/kernel/nmi.c +++ b/arch/i386/kernel/nmi.c @@ -122,64 +122,129 @@ static inline unsigned int nmi_evntsel_msr_to_bit(unsigned int msr) /* checks for a bit availability (hack for oprofile) */ int avail_to_resrv_perfctr_nmi_bit(unsigned int counter) { + int cpu; BUG_ON(counter > NMI_MAX_COUNTER_BITS); - - return (!test_bit(counter, &__get_cpu_var(perfctr_nmi_owner))); + for_each_possible_cpu (cpu) { + if (test_bit(counter, &per_cpu(perfctr_nmi_owner, cpu))) + return 0; + } + return 1; } /* checks the an msr for availability */ int avail_to_resrv_perfctr_nmi(unsigned int msr) { unsigned int counter; + int cpu; counter = nmi_perfctr_msr_to_bit(msr); BUG_ON(counter > NMI_MAX_COUNTER_BITS); - return (!test_bit(counter, &__get_cpu_var(perfctr_nmi_owner))); + for_each_possible_cpu (cpu) { + if (test_bit(counter, &per_cpu(perfctr_nmi_owner, cpu))) + return 0; + } + return 1; } -int reserve_perfctr_nmi(unsigned int msr) +static int __reserve_perfctr_nmi(int cpu, unsigned int msr) { unsigned int counter; + if (cpu < 0) + cpu = smp_processor_id(); counter = nmi_perfctr_msr_to_bit(msr); BUG_ON(counter > NMI_MAX_COUNTER_BITS); - if (!test_and_set_bit(counter, &__get_cpu_var(perfctr_nmi_owner))) + if (!test_and_set_bit(counter, &per_cpu(perfctr_nmi_owner, cpu))) return 1; return 0; } -void release_perfctr_nmi(unsigned int msr) +static void __release_perfctr_nmi(int cpu, unsigned int msr) { unsigned int counter; + if (cpu < 0) + cpu = smp_processor_id(); counter = nmi_perfctr_msr_to_bit(msr); BUG_ON(counter > NMI_MAX_COUNTER_BITS); - clear_bit(counter, &__get_cpu_var(perfctr_nmi_owner)); + clear_bit(counter, &per_cpu(perfctr_nmi_owner, cpu)); } -int reserve_evntsel_nmi(unsigned int msr) +int reserve_perfctr_nmi(unsigned int msr) +{ + int cpu, i; + for_each_possible_cpu (cpu) { + if (!__reserve_perfctr_nmi(cpu, msr)) { + for_each_possible_cpu (i) { + if (i >= cpu) + break; + __release_perfctr_nmi(i, msr); + } + return 0; + } + } + return 1; +} + +void release_perfctr_nmi(unsigned int msr) +{ + int cpu; + for_each_possible_cpu (cpu) { + __release_perfctr_nmi(cpu, msr); + } +} + +int __reserve_evntsel_nmi(int cpu, unsigned int msr) { unsigned int counter; + if (cpu < 0) + cpu = smp_processor_id(); counter = nmi_evntsel_msr_to_bit(msr); BUG_ON(counter > NMI_MAX_COUNTER_BITS); - if (!test_and_set_bit(counter, &__get_cpu_var(evntsel_nmi_owner)[0])) + if (!test_and_set_bit(counter, &per_cpu(evntsel_nmi_owner, cpu)[0])) return 1; return 0; } -void release_evntsel_nmi(unsigned int msr) +static void __release_evntsel_nmi(int cpu, unsigned int msr) { unsigned int counter; + if (cpu < 0) + cpu = smp_processor_id(); counter = nmi_evntsel_msr_to_bit(msr); BUG_ON(counter > NMI_MAX_COUNTER_BITS); - clear_bit(counter, &__get_cpu_var(evntsel_nmi_owner)[0]); + clear_bit(counter, &per_cpu(evntsel_nmi_owner, cpu)[0]); +} + +int reserve_evntsel_nmi(unsigned int msr) +{ + int cpu, i; + for_each_possible_cpu (cpu) { + if (!__reserve_evntsel_nmi(cpu, msr)) { + for_each_possible_cpu (i) { + if (i >= cpu) + break; + __release_evntsel_nmi(i, msr); + } + return 0; + } + } + return 1; +} + +void release_evntsel_nmi(unsigned int msr) +{ + int cpu; + for_each_possible_cpu (cpu) { + __release_evntsel_nmi(cpu, msr); + } } static __cpuinit inline int nmi_known_cpu(void) @@ -263,7 +328,7 @@ static int __init check_nmi_watchdog(void) for_each_possible_cpu(cpu) prev_nmi_count[cpu] = per_cpu(irq_stat, cpu).__nmi_count; local_irq_enable(); - mdelay((10*1000)/nmi_hz); // wait 10 ticks + mdelay((20*1000)/nmi_hz); // wait 20 ticks for_each_possible_cpu(cpu) { #ifdef CONFIG_SMP @@ -507,10 +572,10 @@ static int setup_k7_watchdog(void) perfctr_msr = MSR_K7_PERFCTR0; evntsel_msr = MSR_K7_EVNTSEL0; - if (!reserve_perfctr_nmi(perfctr_msr)) + if (!__reserve_perfctr_nmi(-1, perfctr_msr)) goto fail; - if (!reserve_evntsel_nmi(evntsel_msr)) + if (!__reserve_evntsel_nmi(-1, evntsel_msr)) goto fail1; wrmsrl(perfctr_msr, 0UL); @@ -533,7 +598,7 @@ static int setup_k7_watchdog(void) wd->check_bit = 1ULL<<63; return 1; fail1: - release_perfctr_nmi(perfctr_msr); + __release_perfctr_nmi(-1, perfctr_msr); fail: return 0; } @@ -544,8 +609,8 @@ static void stop_k7_watchdog(void) wrmsr(wd->evntsel_msr, 0, 0); - release_evntsel_nmi(wd->evntsel_msr); - release_perfctr_nmi(wd->perfctr_msr); + __release_evntsel_nmi(-1, wd->evntsel_msr); + __release_perfctr_nmi(-1, wd->perfctr_msr); } #define P6_EVNTSEL0_ENABLE (1 << 22) @@ -563,10 +628,10 @@ static int setup_p6_watchdog(void) perfctr_msr = MSR_P6_PERFCTR0; evntsel_msr = MSR_P6_EVNTSEL0; - if (!reserve_perfctr_nmi(perfctr_msr)) + if (!__reserve_perfctr_nmi(-1, perfctr_msr)) goto fail; - if (!reserve_evntsel_nmi(evntsel_msr)) + if (!__reserve_evntsel_nmi(-1, evntsel_msr)) goto fail1; wrmsrl(perfctr_msr, 0UL); @@ -590,7 +655,7 @@ static int setup_p6_watchdog(void) wd->check_bit = 1ULL<<39; return 1; fail1: - release_perfctr_nmi(perfctr_msr); + __release_perfctr_nmi(-1, perfctr_msr); fail: return 0; } @@ -601,8 +666,8 @@ static void stop_p6_watchdog(void) wrmsr(wd->evntsel_msr, 0, 0); - release_evntsel_nmi(wd->evntsel_msr); - release_perfctr_nmi(wd->perfctr_msr); + __release_evntsel_nmi(-1, wd->evntsel_msr); + __release_perfctr_nmi(-1, wd->perfctr_msr); } /* Note that these events don't tick when the CPU idles. This means @@ -668,10 +733,10 @@ static int setup_p4_watchdog(void) cccr_val = P4_CCCR_OVF_PMI1 | P4_CCCR_ESCR_SELECT(4); } - if (!reserve_perfctr_nmi(perfctr_msr)) + if (!__reserve_perfctr_nmi(-1, perfctr_msr)) goto fail; - if (!reserve_evntsel_nmi(evntsel_msr)) + if (!__reserve_evntsel_nmi(-1, evntsel_msr)) goto fail1; evntsel = P4_ESCR_EVENT_SELECT(0x3F) @@ -695,7 +760,7 @@ static int setup_p4_watchdog(void) wd->check_bit = 1ULL<<39; return 1; fail1: - release_perfctr_nmi(perfctr_msr); + __release_perfctr_nmi(-1, perfctr_msr); fail: return 0; } @@ -707,8 +772,8 @@ static void stop_p4_watchdog(void) wrmsr(wd->cccr_msr, 0, 0); wrmsr(wd->evntsel_msr, 0, 0); - release_evntsel_nmi(wd->evntsel_msr); - release_perfctr_nmi(wd->perfctr_msr); + __release_evntsel_nmi(-1, wd->evntsel_msr); + __release_perfctr_nmi(-1, wd->perfctr_msr); } #define ARCH_PERFMON_NMI_EVENT_SEL ARCH_PERFMON_UNHALTED_CORE_CYCLES_SEL @@ -736,10 +801,10 @@ static int setup_intel_arch_watchdog(void) perfctr_msr = MSR_ARCH_PERFMON_PERFCTR0; evntsel_msr = MSR_ARCH_PERFMON_EVENTSEL0; - if (!reserve_perfctr_nmi(perfctr_msr)) + if (!__reserve_perfctr_nmi(-1, perfctr_msr)) goto fail; - if (!reserve_evntsel_nmi(evntsel_msr)) + if (!__reserve_evntsel_nmi(-1, evntsel_msr)) goto fail1; wrmsrl(perfctr_msr, 0UL); @@ -764,7 +829,7 @@ static int setup_intel_arch_watchdog(void) wd->check_bit = 1ULL << (eax.split.bit_width - 1); return 1; fail1: - release_perfctr_nmi(perfctr_msr); + __release_perfctr_nmi(-1, perfctr_msr); fail: return 0; } @@ -787,8 +852,8 @@ static void stop_intel_arch_watchdog(void) return; wrmsr(wd->evntsel_msr, 0, 0); - release_evntsel_nmi(wd->evntsel_msr); - release_perfctr_nmi(wd->perfctr_msr); + __release_evntsel_nmi(-1, wd->evntsel_msr); + __release_perfctr_nmi(-1, wd->perfctr_msr); } void setup_apic_nmi_watchdog (void *unused) diff --git a/arch/i386/lib/usercopy.c b/arch/i386/lib/usercopy.c index d22cfc9d656..086b3726862 100644 --- a/arch/i386/lib/usercopy.c +++ b/arch/i386/lib/usercopy.c @@ -10,6 +10,7 @@ #include <linux/blkdev.h> #include <linux/module.h> #include <linux/backing-dev.h> +#include <linux/interrupt.h> #include <asm/uaccess.h> #include <asm/mmx.h> @@ -719,6 +720,14 @@ unsigned long __copy_to_user_ll(void __user *to, const void *from, #ifndef CONFIG_X86_WP_WORKS_OK if (unlikely(boot_cpu_data.wp_works_ok == 0) && ((unsigned long )to) < TASK_SIZE) { + /* + * When we are in an atomic section (see + * mm/filemap.c:file_read_actor), return the full + * length to take the slow path. + */ + if (in_atomic()) + return n; + /* * CPU does not honor the WP bit when writing * from supervisory mode, and due to preemption or SMP, diff --git a/arch/um/sys-i386/delay.c b/arch/um/sys-i386/delay.c index 2c11b9770e8..d623e074f41 100644 --- a/arch/um/sys-i386/delay.c +++ b/arch/um/sys-i386/delay.c @@ -27,14 +27,3 @@ void __udelay(unsigned long usecs) } EXPORT_SYMBOL(__udelay); - -void __const_udelay(unsigned long usecs) -{ - int i, n; - - n = (loops_per_jiffy * HZ * usecs) / MILLION; - for(i=0;i<n;i++) - cpu_relax(); -} - -EXPORT_SYMBOL(__const_udelay); diff --git a/arch/um/sys-x86_64/delay.c b/arch/um/sys-x86_64/delay.c index 137f4446b43..dee5be66da8 100644 --- a/arch/um/sys-x86_64/delay.c +++ b/arch/um/sys-x86_64/delay.c @@ -28,14 +28,3 @@ void __udelay(unsigned long usecs) } EXPORT_SYMBOL(__udelay); - -void __const_udelay(unsigned long usecs) -{ - unsigned long i, n; - - n = (loops_per_jiffy * HZ * usecs) / MILLION; - for(i=0;i<n;i++) - cpu_relax(); -} - -EXPORT_SYMBOL(__const_udelay); diff --git a/arch/x86_64/boot/video.S b/arch/x86_64/boot/video.S index d6ff88f3513..6090516c9c7 100644 --- a/arch/x86_64/boot/video.S +++ b/arch/x86_64/boot/video.S @@ -571,6 +571,16 @@ setr1: lodsw jmp _m_s check_vesa: +#ifdef CONFIG_FIRMWARE_EDID + leaw modelist+1024, %di + movw $0x4f00, %ax + int $0x10 + cmpw $0x004f, %ax + jnz setbad + + movw 4(%di), %ax + movw %ax, vbe_version +#endif leaw modelist+1024, %di subb $VIDEO_FIRST_VESA>>8, %bh movw %bx, %cx # Get mode information structure @@ -1945,6 +1955,9 @@ store_edid: rep stosl + cmpw $0x0200, vbe_version # only do EDID on >= VBE2.0 + jl no_edid + pushw %es # save ES xorw %di, %di # Report Capability pushw %di @@ -1987,6 +2000,7 @@ do_restore: .byte 0 # Screen contents altered during mode change svga_prefix: .byte VIDEO_FIRST_BIOS>>8 # Default prefix for BIOS modes graphic_mode: .byte 0 # Graphic mode with a linear frame buffer dac_size: .byte 6 # DAC bit depth +vbe_version: .word 0 # VBE bios version # Status messages keymsg: .ascii "Press <RETURN> to see video modes available, " diff --git a/arch/x86_64/kernel/nmi.c b/arch/x86_64/kernel/nmi.c index 82d9d85d527..a90996c27dc 100644 --- a/arch/x86_64/kernel/nmi.c +++ b/arch/x86_64/kernel/nmi.c @@ -108,64 +108,128 @@ static inline unsigned int nmi_evntsel_msr_to_bit(unsigned int msr) /* checks for a bit availability (hack for oprofile) */ int avail_to_resrv_perfctr_nmi_bit(unsigned int counter) { + int cpu; BUG_ON(counter > NMI_MAX_COUNTER_BITS); - - return (!test_bit(counter, &__get_cpu_var(perfctr_nmi_owner))); + for_each_possible_cpu (cpu) { + if (test_bit(counter, &per_cpu(perfctr_nmi_owner, cpu))) + return 0; + } + return 1; } /* checks the an msr for availability */ int avail_to_resrv_perfctr_nmi(unsigned int msr) { unsigned int counter; + int cpu; counter = nmi_perfctr_msr_to_bit(msr); BUG_ON(counter > NMI_MAX_COUNTER_BITS); - return (!test_bit(counter, &__get_cpu_var(perfctr_nmi_owner))); + for_each_possible_cpu (cpu) { + if (test_bit(counter, &per_cpu(perfctr_nmi_owner, cpu))) + return 0; + } + return 1; } -int reserve_perfctr_nmi(unsigned int msr) +static int __reserve_perfctr_nmi(int cpu, unsigned int msr) { unsigned int counter; + if (cpu < 0) + cpu = smp_processor_id(); counter = nmi_perfctr_msr_to_bit(msr); BUG_ON(counter > NMI_MAX_COUNTER_BITS); - if (!test_and_set_bit(counter, &__get_cpu_var(perfctr_nmi_owner))) + if (!test_and_set_bit(counter, &per_cpu(perfctr_nmi_owner, cpu))) return 1; return 0; } -void release_perfctr_nmi(unsigned int msr) +static void __release_perfctr_nmi(int cpu, unsigned int msr) { unsigned int counter; + if (cpu < 0) + cpu = smp_processor_id(); counter = nmi_perfctr_msr_to_bit(msr); BUG_ON(counter > NMI_MAX_COUNTER_BITS); - clear_bit(counter, &__get_cpu_var(perfctr_nmi_owner)); + clear_bit(counter, &per_cpu(perfctr_nmi_owner, cpu)); } -int reserve_evntsel_nmi(unsigned int msr) +int reserve_perfctr_nmi(unsigned int msr) +{ + int cpu, i; + for_each_possible_cpu (cpu) { + if (!__reserve_perfctr_nmi(cpu, msr)) { + for_each_possible_cpu (i) { + if (i >= cpu) + break; + __release_perfctr_nmi(i, msr); + } + return 0; + } + } + return 1; +} + +void release_perfctr_nmi(unsigned int msr) +{ + int cpu; + for_each_possible_cpu (cpu) + __release_perfctr_nmi(cpu, msr); +} + +int __reserve_evntsel_nmi(int cpu, unsigned int msr) { unsigned int counter; + if (cpu < 0) + cpu = smp_processor_id(); counter = nmi_evntsel_msr_to_bit(msr); BUG_ON(counter > NMI_MAX_COUNTER_BITS); - if (!test_and_set_bit(counter, &__get_cpu_var(evntsel_nmi_owner))) + if (!test_and_set_bit(counter, &per_cpu(evntsel_nmi_owner, cpu)[0])) return 1; return 0; } -void release_evntsel_nmi(unsigned int msr) +static void __release_evntsel_nmi(int cpu, unsigned int msr) { unsigned int counter; + if (cpu < 0) + cpu = smp_processor_id(); counter = nmi_evntsel_msr_to_bit(msr); BUG_ON(counter > NMI_MAX_COUNTER_BITS); - clear_bit(counter, &__get_cpu_var(evntsel_nmi_owner)); + clear_bit(counter, &per_cpu(evntsel_nmi_owner, cpu)[0]); +} + +int reserve_evntsel_nmi(unsigned int msr) +{ + int cpu, i; + for_each_possible_cpu (cpu) { + if (!__reserve_evntsel_nmi(cpu, msr)) { + for_each_possible_cpu (i) { + if (i >= cpu) + break; + __release_evntsel_nmi(i, msr); + } + return 0; + } + } + return 1; +} + +void release_evntsel_nmi(unsigned int msr) +{ + int cpu; + for_each_possible_cpu (cpu) { + __release_evntsel_nmi(cpu, msr); + } } static __cpuinit inline int nmi_known_cpu(void) @@ -253,7 +317,7 @@ int __init check_nmi_watchdog (void) for (cpu = 0; cpu < NR_CPUS; cpu++) counts[cpu] = cpu_pda(cpu)->__nmi_count; local_irq_enable(); - mdelay((10*1000)/nmi_hz); // wait 10 ticks + mdelay((20*1000)/nmi_hz); // wait 20 ticks for_each_online_cpu(cpu) { if (!per_cpu(nmi_watchdog_ctlblk, cpu).enabled) @@ -472,10 +536,10 @@ static int setup_k7_watchdog(void) perfctr_msr = MSR_K7_PERFCTR0; evntsel_msr = MSR_K7_EVNTSEL0; - if (!reserve_perfctr_nmi(perfctr_msr)) + if (!__reserve_perfctr_nmi(-1, perfctr_msr)) goto fail; - if (!reserve_evntsel_nmi(evntsel_msr)) + if (!__reserve_evntsel_nmi(-1, evntsel_msr)) goto fail1; /* Simulator may not support it */ @@ -501,9 +565,9 @@ static int setup_k7_watchdog(void) wd->check_bit = 1ULL<<63; return 1; fail2: - release_evntsel_nmi(evntsel_msr); + __release_evntsel_nmi(-1, evntsel_msr); fail1: - release_perfctr_nmi(perfctr_msr); + __release_perfctr_nmi(-1, perfctr_msr); fail: return 0; } @@ -514,8 +578,8 @@ static void stop_k7_watchdog(void) wrmsr(wd->evntsel_msr, 0, 0); - release_evntsel_nmi(wd->evntsel_msr); - release_perfctr_nmi(wd->perfctr_msr); + __release_evntsel_nmi(-1, wd->evntsel_msr); + __release_perfctr_nmi(-1, wd->perfctr_msr); } /* Note that these events don't tick when the CPU idles. This means @@ -581,10 +645,10 @@ static int setup_p4_watchdog(void) cccr_val = P4_CCCR_OVF_PMI1 | P4_CCCR_ESCR_SELECT(4); } - if (!reserve_perfctr_nmi(perfctr_msr)) + if (!__reserve_perfctr_nmi(-1, perfctr_msr)) goto fail; - if (!reserve_evntsel_nmi(evntsel_msr)) + if (!__reserve_evntsel_nmi(-1, evntsel_msr)) goto fail1; evntsel = P4_ESCR_EVENT_SELECT(0x3F) @@ -609,7 +673,7 @@ static int setup_p4_watchdog(void) wd->check_bit = 1ULL<<39; return 1; fail1: - release_perfctr_nmi(perfctr_msr); + __release_perfctr_nmi(-1, perfctr_msr); fail: return 0; } @@ -621,8 +685,8 @@ static void stop_p4_watchdog(void) wrmsr(wd->cccr_msr, 0, 0); wrmsr(wd->evntsel_msr, 0, 0); - release_evntsel_nmi(wd->evntsel_msr); - release_perfctr_nmi(wd->perfctr_msr); + __release_evntsel_nmi(-1, wd->evntsel_msr); + __release_perfctr_nmi(-1, wd->perfctr_msr); } #define ARCH_PERFMON_NMI_EVENT_SEL ARCH_PERFMON_UNHALTED_CORE_CYCLES_SEL @@ -650,10 +714,10 @@ static int setup_intel_arch_watchdog(void) perfctr_msr = MSR_ARCH_PERFMON_PERFCTR0; evntsel_msr = MSR_ARCH_PERFMON_EVENTSEL0; - if (!reserve_perfctr_nmi(perfctr_msr)) + if (!__reserve_perfctr_nmi(-1, perfctr_msr)) goto fail; - if (!reserve_evntsel_nmi(evntsel_msr)) + if (!__reserve_evntsel_nmi(-1, evntsel_msr)) goto fail1; wrmsrl(perfctr_msr, 0UL); @@ -680,7 +744,7 @@ static int setup_intel_arch_watchdog(void) wd->check_bit = 1ULL << (eax.split.bit_width - 1); return 1; fail1: - release_perfctr_nmi(perfctr_msr); + __release_perfctr_nmi(-1, perfctr_msr); fail: return 0; } @@ -704,8 +768,8 @@ static void stop_intel_arch_watchdog(void) wrmsr(wd->evntsel_msr, 0, 0); - release_evntsel_nmi(wd->evntsel_msr); - release_perfctr_nmi(wd->perfctr_msr); + __release_evntsel_nmi(-1, wd->evntsel_msr); + __release_perfctr_nmi(-1, wd->perfctr_msr); } void setup_apic_nmi_watchdog(void *unused) diff --git a/drivers/char/vt_ioctl.c b/drivers/char/vt_ioctl.c index 1fa2da8f4fb..c9f2dd620e8 100644 --- a/drivers/char/vt_ioctl.c +++ b/drivers/char/vt_ioctl.c @@ -1039,10 +1039,22 @@ int vt_waitactive(int vt) add_wait_queue(&vt_activate_queue, &wait); for (;;) { - set_current_state(TASK_INTERRUPTIBLE); retval = 0; - if (vt == fg_console) + + /* + * Synchronize with redraw_screen(). By acquiring the console + * semaphore we make sure that the console switch is completed + * before we return. If we didn't wait for the semaphore, we + * could return at a point where fg_console has already been + * updated, but the console switch hasn't been completed. + */ + acquire_console_sem(); + set_current_state(TASK_INTERRUPTIBLE); + if (vt == fg_console) { + release_console_sem(); break; + } + release_console_sem(); retval = -EINTR; if (signal_pending(current)) break; diff --git a/drivers/mfd/sm501.c b/drivers/mfd/sm501.c index c707c8ebc1a..b0b4458ae90 100644 --- a/drivers/mfd/sm501.c +++ b/drivers/mfd/sm501.c @@ -319,7 +319,7 @@ int sm501_unit_power(struct device *dev, unsigned int unit, unsigned int to) mode &= 3; /* get current power mode */ - if (unit > ARRAY_SIZE(sm->unit_power)) { + if (unit >= ARRAY_SIZE(sm->unit_power)) { dev_err(dev, "%s: bad unit %d\n", __FUNCTION__, unit); goto already; } diff --git a/drivers/pnp/system.c b/drivers/pnp/system.c index 2065e74bb63..a8a95540b1e 100644 --- a/drivers/pnp/system.c +++ b/drivers/pnp/system.c @@ -22,7 +22,7 @@ static const struct pnp_device_id pnp_dev_table[] = { { "", 0 } }; -static void reserve_range(char *pnpid, int start, int end, int port) +static void reserve_range(const char *pnpid, resource_size_t start, resource_size_t end, int port) { struct resource *res; char *regionid; @@ -32,9 +32,9 @@ static void reserve_range(char *pnpid, int start, int end, int port) return; snprintf(regionid, 16, "pnp %s", pnpid); if (port) - res = request_region(start,end-start+1,regionid); + res = request_region(start, end-start+1, regionid); else - res = request_mem_region(start,end-start+1,regionid); + res = request_mem_region(start, end-start+1, regionid); if (res == NULL) kfree(regionid); else @@ -45,12 +45,13 @@ static void reserve_range(char *pnpid, int start, int end, int port) * have double reservations. */ printk(KERN_INFO - "pnp: %s: %s range 0x%x-0x%x %s reserved\n", - pnpid, port ? "ioport" : "iomem", start, end, + "pnp: %s: %s range 0x%llx-0x%llx %s reserved\n", + pnpid, port ? "ioport" : "iomem", + (unsigned long long)start, (unsigned long long)end, NULL != res ? "has been" : "could not be"); } -static void reserve_resources_of_dev(struct pnp_dev *dev) +static void reserve_resources_of_dev(const struct pnp_dev *dev) { int i; diff --git a/drivers/rtc/rtc-cmos.c b/drivers/rtc/rtc-cmos.c index 85bf795abdc..7c0d6091007 100644 --- a/drivers/rtc/rtc-cmos.c +++ b/drivers/rtc/rtc-cmos.c @@ -59,6 +59,19 @@ struct cmos_rtc { static const char driver_name[] = "rtc_cmos"; +/* The RTC_INTR register may have e.g. RTC_PF set even if RTC_PIE is clear; + * always mask it against the irq enable bits in RTC_CONTROL. Bit values + * are the same: PF==PIE, AF=AIE, UF=UIE; so RTC_IRQMASK works with both. + */ +#define RTC_IRQMASK (RTC_PF | RTC_AF | RTC_UF) + +static inline int is_intr(u8 rtc_intr) +{ + if (!(rtc_intr & RTC_IRQF)) + return 0; + return rtc_intr & RTC_IRQMASK; +} + /*----------------------------------------------------------------*/ static int cmos_read_time(struct device *dev, struct rtc_time *t) @@ -188,7 +201,8 @@ static int cmos_set_alarm(struct device *dev, struct rtc_wkalrm *t) rtc_control &= ~RTC_AIE; CMOS_WRITE(rtc_control, RTC_CONTROL); rtc_intr = CMOS_READ(RTC_INTR_FLAGS); - if (rtc_intr) + rtc_intr &= (rtc_control & RTC_IRQMASK) | RTC_IRQF; + if (is_intr(rtc_intr)) rtc_update_irq(&cmos->rtc->class_dev, 1, rtc_intr); /* update alarm */ @@ -207,7 +221,8 @@ static int cmos_set_alarm(struct device *dev, struct rtc_wkalrm *t) rtc_control |= RTC_AIE; CMOS_WRITE(rtc_control, RTC_CONTROL); rtc_intr = CMOS_READ(RTC_INTR_FLAGS); - if (rtc_intr) + rtc_intr &= (rtc_control & RTC_IRQMASK) | RTC_IRQF; + if (is_intr(rtc_intr)) rtc_update_irq(&cmos->rtc->class_dev, 1, rtc_intr); } @@ -287,7 +302,8 @@ cmos_rtc_ioctl(struct device *dev, unsigned int cmd, unsigned long arg) } CMOS_WRITE(rtc_control, RTC_CONTROL); rtc_intr = CMOS_READ(RTC_INTR_FLAGS); - if (rtc_intr) + rtc_intr &= (rtc_control & RTC_IRQMASK) | RTC_IRQF; + if (is_intr(rtc_intr)) rtc_update_irq(&cmos->rtc->class_dev, 1, rtc_intr); spin_unlock_irqrestore(&rtc_lock, flags); return 0; @@ -353,12 +369,10 @@ static irqreturn_t cmos_interrupt(int irq, void *p) spin_lock(&rtc_lock); irqstat = CMOS_READ(RTC_INTR_FLAGS); + irqstat &= (CMOS_READ(RTC_CONTROL) & RTC_IRQMASK) | RTC_IRQF; spin_unlock(&rtc_lock); - if (irqstat) { - /* NOTE: irqstat may have e.g. RTC_PF set - * even when RTC_PIE is clear... - */ + if (is_intr(irqstat)) { rtc_update_irq(p, 1, irqstat); return IRQ_HANDLED; } else @@ -525,25 +539,26 @@ static int cmos_suspend(struct device *dev, pm_message_t mesg) { struct cmos_rtc *cmos = dev_get_drvdata(dev); int do_wake = device_may_wakeup(dev); - unsigned char tmp, irqstat; + unsigned char tmp; /* only the alarm might be a wakeup event source */ spin_lock_irq(&rtc_lock); cmos->suspend_ctrl = tmp = CMOS_READ(RTC_CONTROL); if (tmp & (RTC_PIE|RTC_AIE|RTC_UIE)) { + unsigned char irqstat; + if (do_wake) tmp &= ~(RTC_PIE|RTC_UIE); else tmp &= ~(RTC_PIE|RTC_AIE|RTC_UIE); CMOS_WRITE(tmp, RTC_CONTROL); irqstat = CMOS_READ(RTC_INTR_FLAGS); - } else - irqstat = 0; + irqstat &= (tmp & RTC_IRQMASK) | RTC_IRQF; + if (is_intr(irqstat)) + rtc_update_irq(&cmos->rtc->class_dev, 1, irqstat); + } spin_unlock_irq(&rtc_lock); - if (irqstat) - rtc_update_irq(&cmos->rtc->class_dev, 1, irqstat); - /* ACPI HOOK: enable ACPI_EVENT_RTC when (tmp & RTC_AIE) * ... it'd be best if we could do that under rtc_lock. */ @@ -573,9 +588,10 @@ static int cmos_resume(struct device *dev) spin_lock_irq(&rtc_lock); CMOS_WRITE(tmp, RTC_CONTROL); tmp = CMOS_READ(RTC_INTR_FLAGS); - spin_unlock_irq(&rtc_lock); - if (tmp) + tmp &= (cmos->suspend_ctrl & RTC_IRQMASK) | RTC_IRQF; + if (is_intr(tmp)) rtc_update_irq(&cmos->rtc->class_dev, 1, tmp); + spin_unlock_irq(&rtc_lock); } pr_debug("%s: resume, ctrl %02x\n", @@ -594,7 +610,7 @@ static int cmos_resume(struct device *dev) /*----------------------------------------------------------------*/ /* The "CMOS" RTC normally lives on the platform_bus. On ACPI systems, - * the device node may alternatively be created as a PNP device. + * the device node will always be created as a PNPACPI device. */ #ifdef CONFIG_PNPACPI @@ -673,7 +689,7 @@ module_exit(cmos_exit); /*----------------------------------------------------------------*/ /* Platform setup should have set up an RTC device, when PNPACPI is - * unavailable ... this is the normal case, common even on PCs. + * unavailable ... this could happen even on (older) PCs. */ static int __init cmos_platform_probe(struct platform_device *pdev) diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index a2fceba7ef8..9cc4f0a8aaa 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -1704,7 +1704,10 @@ static int elf_core_dump(long signr, struct pt_regs *regs, struct file *file) DUMP_SEEK(PAGE_SIZE); } else { if (page == ZERO_PAGE(addr)) { - DUMP_SEEK(PAGE_SIZE); + if (!dump_seek(file, PAGE_SIZE)) { + page_cache_release(page); + goto end_coredump; + } } else { void *kaddr; flush_cache_page(vma, addr, diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c index 47d6d49d1fb..f3ddca4a387 100644 --- a/fs/binfmt_elf_fdpic.c +++ b/fs/binfmt_elf_fdpic.c @@ -1480,8 +1480,8 @@ static int elf_fdpic_dump_segments(struct file *file, struct mm_struct *mm, DUMP_SEEK(file->f_pos + PAGE_SIZE); } else if (page == ZERO_PAGE(addr)) { - DUMP_SEEK(file->f_pos + PAGE_SIZE); page_cache_release(page); + DUMP_SEEK(file->f_pos + PAGE_SIZE); } else { void *kaddr; diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c index 8a824f4ce5c..a5b150f7e8a 100644 --- a/fs/ext3/inode.c +++ b/fs/ext3/inode.c @@ -1148,102 +1148,37 @@ static int do_journal_get_write_access(handle_t *handle, return ext3_journal_get_write_access(handle, bh); } -/* - * The idea of this helper function is following: - * if prepare_write has allocated some blocks, but not all of them, the - * transaction must include the content of the newly allocated blocks. - * This content is expected to be set to zeroes by block_prepare_write(). - * 2006/10/14 SAW - */ -static int ext3_prepare_failure(struct file *file, struct page *page, - unsigned from, unsigned to) -{ - struct address_space *mapping; - struct buffer_head *bh, *head, *next; - unsigned block_start, block_end; - unsigned blocksize; - int ret; - handle_t *handle = ext3_journal_current_handle(); - - mapping = page->mapping; - if (ext3_should_writeback_data(mapping->host)) { - /* optimization: no constraints about data */ -skip: - return ext3_journal_stop(handle); - } - - head = page_buffers(page); - blocksize = head->b_size; - for ( bh = head, block_start = 0; - bh != head || !block_start; - block_start = block_end, bh = next) - { - next = bh->b_this_page; - block_end = block_start + blocksize; - if (block_end <= from) - continue; - if (block_start >= to) { - block_start = to; - break; - } - if (!buffer_mapped(bh)) - /* prepare_write failed on this bh */ - break; - if (ext3_should_journal_data(mapping->host)) { - ret = do_journal_get_write_access(handle, bh); - if (ret) { - ext3_journal_stop(handle); - return ret; - } - } - /* - * block_start here becomes the first block where the current iteration - * of prepare_write failed. - */ - } - if (block_start <= from) - goto skip; - - /* commit allocated and zeroed buffers */ - return mapping->a_ops->commit_write(file, page, from, block_start); -} - static int ext3_prepare_write(struct file *file, struct page *page, unsigned from, unsigned to) { struct inode *inode = page->mapping->host; - int ret, ret2; - int needed_blocks = ext3_writepage_trans_blocks(inode); + int ret, needed_blocks = ext3_writepage_trans_blocks(inode); handle_t *handle; int retries = 0; retry: handle = ext3_journal_start(inode, needed_blocks); - if (IS_ERR(handle)) - return PTR_ERR(handle); + if (IS_ERR(handle)) { + ret = PTR_ERR(handle); + goto out; + } if (test_opt(inode->i_sb, NOBH) && ext3_should_writeback_data(inode)) ret = nobh_prepare_write(page, from, to, ext3_get_block); else ret = block_prepare_write(page, from, to, ext3_get_block); if (ret) - goto failure; + goto prepare_write_failed; if (ext3_should_journal_data(inode)) { ret = walk_page_buffers(handle, page_buffers(page), from, to, NULL, do_journal_get_write_access); - if (ret) - /* fatal error, just put the handle and return */ - journal_stop(handle); } - return ret; - -failure: - ret2 = ext3_prepare_failure(file, page, from, to); - if (ret2 < 0) - return ret2; +prepare_write_failed: + if (ret) + ext3_journal_stop(handle); if (ret == -ENOSPC && ext3_should_retry_alloc(inode->i_sb, &retries)) goto retry; - /* retry number exceeded, or other error like -EDQUOT */ +out: return ret; } diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index fbff4b9e122..810b6d6474b 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -1147,102 +1147,37 @@ static int do_journal_get_write_access(handle_t *handle, return ext4_journal_get_write_access(handle, bh); } -/* - * The idea of this helper function is following: - * if prepare_write has allocated some blocks, but not all of them, the - * transaction must include the content of the newly allocated blocks. - * This content is expected to be set to zeroes by block_prepare_write(). - * 2006/10/14 SAW - */ -static int ext4_prepare_failure(struct file *file, struct page *page, - unsigned from, unsigned to) -{ - struct address_space *mapping; - struct buffer_head *bh, *head, *next; - unsigned block_start, block_end; - unsigned blocksize; - int ret; - handle_t *handle = ext4_journal_current_handle(); - - mapping = page->mapping; - if (ext4_should_writeback_data(mapping->host)) { - /* optimization: no constraints about data */ -skip: - return ext4_journal_stop(handle); - } - - head = page_buffers(page); - blocksize = head->b_size; - for ( bh = head, block_start = 0; - bh != head || !block_start; - block_start = block_end, bh = next) - { - next = bh->b_this_page; - block_end = block_start + blocksize; - if (block_end <= from) - continue; - if (block_start >= to) { - block_start = to; - break; - } - if (!buffer_mapped(bh)) - /* prepare_write failed on this bh */ - break; - if (ext4_should_journal_data(mapping->host)) { - ret = do_journal_get_write_access(handle, bh); - if (ret) { - ext4_journal_stop(handle); - return ret; - } - } - /* - * block_start here becomes the first block where the current iteration - * of prepare_write failed. - */ - } - if (block_start <= from) - goto skip; - - /* commit allocated and zeroed buffers */ - return mapping->a_ops->commit_write(file, page, from, block_start); -} - static int ext4_prepare_write(struct file *file, struct page *page, unsigned from, unsigned to) { struct inode *inode = page->mapping->host; - int ret, ret2; - int needed_blocks = ext4_writepage_trans_blocks(inode); + int ret, needed_blocks = ext4_writepage_trans_blocks(inode); handle_t *handle; int retries = 0; retry: handle = ext4_journal_start(inode, needed_blocks); - if (IS_ERR(handle)) - return PTR_ERR(handle); + if (IS_ERR(handle)) { + ret = PTR_ERR(handle); + goto out; + } if (test_opt(inode->i_sb, NOBH) && ext4_should_writeback_data(inode)) ret = nobh_prepare_write(page, from, to, ext4_get_block); else ret = block_prepare_write(page, from, to, ext4_get_block); if (ret) - goto failure; + goto prepare_write_failed; if (ext4_should_journal_data(inode)) { ret = walk_page_buffers(handle, page_buffers(page), from, to, NULL, do_journal_get_write_access); - if (ret) - /* fatal error, just put the handle and return */ - ext4_journal_stop(handle); } - return ret; - -failure: - ret2 = ext4_prepare_failure(file, page, from, to); - if (ret2 < 0) - return ret2; +prepare_write_failed: + if (ret) + ext4_journal_stop(handle); if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries)) goto retry; - /* retry number exceeded, or other error like -EDQUOT */ +out: return ret; } diff --git a/fs/proc/internal.h b/fs/proc/internal.h index c932aa65e19..f771889183c 100644 --- a/fs/proc/internal.h +++ b/fs/proc/internal.h @@ -11,7 +11,11 @@ #include <linux/proc_fs.h> +#ifdef CONFIG_PROC_SYSCTL extern int proc_sys_init(void); +#else +static inline void proc_sys_init(void) { } +#endif struct vmalloc_info { unsigned long used; diff --git a/fs/proc/root.c b/fs/proc/root.c index 5834a744c2a..41f17037f73 100644 --- a/fs/proc/root.c +++ b/fs/proc/root.c @@ -79,9 +79,7 @@ void __init proc_root_init(void) proc_device_tree_init(); #endif proc_bus = proc_mkdir("bus", NULL); -#ifdef CONFIG_SYSCTL proc_sys_init(); -#endif } static int proc_root_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat diff --git a/include/asm-i386/cpufeature.h b/include/asm-i386/cpufeature.h index 3f92b94e0d7..d1b8e4ab6c1 100644 --- a/include/asm-i386/cpufeature.h +++ b/include/asm-i386/cpufeature.h @@ -75,6 +75,7 @@ #define X86_FEATURE_ARCH_PERFMON (3*32+11) /* Intel Architectural PerfMon */ #define X86_FEATURE_PEBS (3*32+12) /* Precise-Event Based Sampling */ #define X86_FEATURE_BTS (3*32+13) /* Branch Trace Store */ +#define X86_FEATURE_LAPIC_TIMER_BROKEN (3*32+ 14) /* lapic timer broken in C1 */ /* Intel-defined CPU features, CPUID level 0x00000001 (ecx), word 4 */ #define X86_FEATURE_XMM3 (4*32+ 0) /* Streaming SIMD Extensions-3 */ diff --git a/include/asm-i386/msr.h b/include/asm-i386/msr.h index ec3b6803fd3..2ad3f30b1a6 100644 --- a/include/asm-i386/msr.h +++ b/include/asm-i386/msr.h @@ -275,6 +275,8 @@ static inline void wrmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h) #define MSR_K7_FID_VID_CTL 0xC0010041 #define MSR_K7_FID_VID_STATUS 0xC0010042 +#define MSR_K8_ENABLE_C1E 0xC0010055 + /* extended feature register */ #define MSR_EFER 0xc0000080 diff --git a/include/asm-um/delay.h b/include/asm-um/delay.h index 0985bda6675..c71e32b6741 100644 --- a/include/asm-um/delay.h +++ b/include/asm-um/delay.h @@ -1,9 +1,20 @@ #ifndef __UM_DELAY_H #define __UM_DELAY_H -#include "asm/arch/delay.h" -#include "asm/archparam.h" - #define MILLION 1000000 +/* Undefined on purpose */ +extern void __bad_udelay(void); + +extern void __udelay(unsigned long usecs); +extern void __delay(unsigned long loops); + +#define udelay(n) ((__builtin_constant_p(n) && (n) > 20000) ? \ + __bad_udelay() : __udelay(n)) + +/* It appears that ndelay is not used at all for UML, and has never been + * implemented. */ +extern void __unimplemented_ndelay(void); +#define ndelay(n) __unimplemented_ndelay() + #endif diff --git a/include/linux/cpu.h b/include/linux/cpu.h index 769ddc6df49..c22b0dfcbcd 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -127,9 +127,13 @@ static inline int cpu_is_offline(int cpu) { return 0; } #endif /* CONFIG_HOTPLUG_CPU */ #ifdef CONFIG_SUSPEND_SMP +extern int suspend_cpu_hotplug; + extern int disable_nonboot_cpus(void); extern void enable_nonboot_cpus(void); #else +#define suspend_cpu_hotplug 0 + static inline int disable_nonboot_cpus(void) { return 0; } static inline void enable_nonboot_cpus(void) {} #endif diff --git a/include/linux/device.h b/include/linux/device.h index caad9bba965..5cf30e95c8b 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -128,6 +128,7 @@ struct device_driver { struct module * owner; const char * mod_name; /* used for built-in modules */ + struct module_kobject * mkobj; int (*probe) (struct device * dev); int (*remove) (struct device * dev); diff --git a/kernel/cpu.c b/kernel/cpu.c index 3d4206ada5c..36e70845cfc 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -254,6 +254,12 @@ int __cpuinit cpu_up(unsigned int cpu) } #ifdef CONFIG_SUSPEND_SMP +/* Needed to prevent the microcode driver from requesting firmware in its CPU + * hotplug notifier during the suspend/resume. + */ +int suspend_cpu_hotplug; +EXPORT_SYMBOL(suspend_cpu_hotplug); + static cpumask_t frozen_cpus; int disable_nonboot_cpus(void) @@ -261,16 +267,8 @@ int disable_nonboot_cpus(void) int cpu, first_cpu, error = 0; mutex_lock(&cpu_add_remove_lock); - first_cpu = first_cpu(cpu_present_map); - if (!cpu_online(first_cpu)) { - error = _cpu_up(first_cpu); - if (error) { - printk(KERN_ERR "Could not bring CPU%d up.\n", - first_cpu); - goto out; - } - } - + suspend_cpu_hotplug = 1; + first_cpu = first_cpu(cpu_online_map); /* We take down all of the non-boot CPUs in one shot to avoid races * with the userspace trying to use the CPU hotplug at the same time */ @@ -296,7 +294,7 @@ int disable_nonboot_cpus(void) } else { printk(KERN_ERR "Non-boot CPUs are not disabled\n"); } -out: + suspend_cpu_hotplug = 0; mutex_unlock(&cpu_add_remove_lock); return error; } @@ -308,20 +306,22 @@ void enable_nonboot_cpus(void) /* Allow everyone to use the CPU hotplug again */ mutex_lock(&cpu_add_remove_lock); cpu_hotplug_disabled = 0; - mutex_unlock(&cpu_add_remove_lock); if (cpus_empty(frozen_cpus)) - return; + goto out; + suspend_cpu_hotplug = 1; printk("Enabling non-boot CPUs ...\n"); for_each_cpu_mask(cpu, frozen_cpus) { - error = cpu_up(cpu); + error = _cpu_up(cpu); if (!error) { printk("CPU%d is up\n", cpu); continue; } - printk(KERN_WARNING "Error taking CPU%d up: %d\n", - cpu, error); + printk(KERN_WARNING "Error taking CPU%d up: %d\n", cpu, error); } cpus_clear(frozen_cpus); + suspend_cpu_hotplug = 0; +out: + mutex_unlock(&cpu_add_remove_lock); } #endif diff --git a/kernel/module.c b/kernel/module.c index fbc51de6444..dcdb32b8b13 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -2384,8 +2384,13 @@ void module_add_driver(struct module *mod, struct device_driver *drv) /* Lookup built-in module entry in /sys/modules */ mkobj = kset_find_obj(&module_subsys.kset, drv->mod_name); - if (mkobj) + if (mkobj) { mk = container_of(mkobj, struct module_kobject, kobj); + /* remember our module structure */ + drv->mkobj = mk; + /* kset_find_obj took a reference */ + kobject_put(mkobj); + } } if (!mk) @@ -2405,17 +2410,22 @@ EXPORT_SYMBOL(module_add_driver); void module_remove_driver(struct device_driver *drv) { + struct module_kobject *mk = NULL; char *driver_name; if (!drv) return; sysfs_remove_link(&drv->kobj, "module"); - if (drv->owner && drv->owner->mkobj.drivers_dir) { + + if (drv->owner) + mk = &drv->owner->mkobj; + else if (drv->mkobj) + mk = drv->mkobj; + if (mk && mk->drivers_dir) { driver_name = make_driver_name(drv); if (driver_name) { - sysfs_remove_link(drv->owner->mkobj.drivers_dir, - driver_name); + sysfs_remove_link(mk->drivers_dir, driver_name); kfree(driver_name); } } |