From: Ziggy471 Date: Wed, 9 Mar 2011 00:11:12 +0000 (-0500) Subject: Patch 2.6.32.28 to 2.6.32.32 X-Git-Url: https://www.ziggy471.info/git/gitweb.cgi?p=ziggy471-frankenstein-kernel.git;a=commitdiff;h=eedf9238f6884b6183409688f97c47e1d5ef726b Patch 2.6.32.28 to 2.6.32.32 --- --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -878,6 +878,7 @@ and is between 256 and 4096 characters. i8042.panicblink= [HW] Frequency with which keyboard LEDs should blink when kernel panics (default is 0.5 sec) + i8042.notimeout [HW] Ignore timeout condition signalled by conroller i8042.reset [HW] Reset the controller during init and cleanup i8042.unlock [HW] Unlock (ignore) the keylock @@ -2579,6 +2580,10 @@ and is between 256 and 4096 characters. disables clocksource verification at runtime. Used to enable high-resolution timer mode on older hardware, and in virtualized environment. + [x86] noirqtime: Do not use TSC to do irq accounting. + Used to run time disable IRQ_TIME_ACCOUNTING on any + platforms where RDTSC is slow and this accounting + can add overhead. turbografx.map[2|3]= [HW,JOY] TurboGraFX parallel port interface --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ VERSION = 2 PATCHLEVEL = 6 SUBLEVEL = 32 -EXTRAVERSION = .28-ck2 +EXTRAVERSION = .32-ck2 NAME = Man-Eating Seals of Antiquity # *DOCUMENTATION* --- a/arch/arm/kernel/signal.c +++ b/arch/arm/kernel/signal.c @@ -389,7 +389,9 @@ setup_return(struct pt_regs *regs, struc unsigned long handler = (unsigned long)ka->sa.sa_handler; unsigned long retcode; int thumb = 0; - unsigned long cpsr = regs->ARM_cpsr & ~PSR_f; + unsigned long cpsr = regs->ARM_cpsr & ~(PSR_f | PSR_E_BIT); + + cpsr |= PSR_ENDSTATE; /* * Maybe we need to deliver a 32-bit signal to a 26-bit task. --- a/arch/ia64/include/asm/system.h +++ b/arch/ia64/include/asm/system.h @@ -281,10 +281,6 @@ void cpu_idle_wait(void); void default_idle(void); -#ifdef CONFIG_VIRT_CPU_ACCOUNTING -extern void account_system_vtime(struct task_struct *); -#endif - #endif /* __KERNEL__ */ #endif /* __ASSEMBLY__ */ --- a/arch/parisc/kernel/firmware.c +++ b/arch/parisc/kernel/firmware.c @@ -1126,15 +1126,13 @@ int pdc_iodc_print(const unsigned char * unsigned int i; unsigned long flags; - for (i = 0; i < count && i < 79;) { + for (i = 0; i < count;) { switch(str[i]) { case '\n': iodc_dbuf[i+0] = '\r'; iodc_dbuf[i+1] = '\n'; i += 2; goto print; - case '\b': /* BS */ - i--; /* overwrite last */ default: iodc_dbuf[i] = str[i]; i++; @@ -1142,15 +1140,6 @@ int pdc_iodc_print(const unsigned char * } } - /* if we're at the end of line, and not already inserting a newline, - * insert one anyway. iodc console doesn't claim to support >79 char - * lines. don't account for this in the return value. - */ - if (i == 79 && iodc_dbuf[i-1] != '\n') { - iodc_dbuf[i+0] = '\r'; - iodc_dbuf[i+1] = '\n'; - } - print: spin_lock_irqsave(&pdc_lock, flags); real32_call(PAGE0->mem_cons.iodc_io, --- a/arch/powerpc/include/asm/system.h +++ b/arch/powerpc/include/asm/system.h @@ -540,10 +540,6 @@ extern void reloc_got2(unsigned long); #define PTRRELOC(x) ((typeof(x)) add_reloc_offset((unsigned long)(x))) -#ifdef CONFIG_VIRT_CPU_ACCOUNTING -extern void account_system_vtime(struct task_struct *); -#endif - extern struct dentry *powerpc_debugfs_root; #endif /* __KERNEL__ */ --- a/arch/powerpc/kernel/cpu_setup_6xx.S +++ b/arch/powerpc/kernel/cpu_setup_6xx.S @@ -18,7 +18,7 @@ #include _GLOBAL(__setup_cpu_603) - mflr r4 + mflr r5 BEGIN_MMU_FTR_SECTION li r10,0 mtspr SPRN_SPRG_603_LRU,r10 /* init SW LRU tracking */ @@ -27,60 +27,60 @@ BEGIN_FTR_SECTION bl __init_fpu_registers END_FTR_SECTION_IFCLR(CPU_FTR_FPU_UNAVAILABLE) bl setup_common_caches - mtlr r4 + mtlr r5 blr _GLOBAL(__setup_cpu_604) - mflr r4 + mflr r5 bl setup_common_caches bl setup_604_hid0 - mtlr r4 + mtlr r5 blr _GLOBAL(__setup_cpu_750) - mflr r4 + mflr r5 bl __init_fpu_registers bl setup_common_caches bl setup_750_7400_hid0 - mtlr r4 + mtlr r5 blr _GLOBAL(__setup_cpu_750cx) - mflr r4 + mflr r5 bl __init_fpu_registers bl setup_common_caches bl setup_750_7400_hid0 bl setup_750cx - mtlr r4 + mtlr r5 blr _GLOBAL(__setup_cpu_750fx) - mflr r4 + mflr r5 bl __init_fpu_registers bl setup_common_caches bl setup_750_7400_hid0 bl setup_750fx - mtlr r4 + mtlr r5 blr _GLOBAL(__setup_cpu_7400) - mflr r4 + mflr r5 bl __init_fpu_registers bl setup_7400_workarounds bl setup_common_caches bl setup_750_7400_hid0 - mtlr r4 + mtlr r5 blr _GLOBAL(__setup_cpu_7410) - mflr r4 + mflr r5 bl __init_fpu_registers bl setup_7410_workarounds bl setup_common_caches bl setup_750_7400_hid0 li r3,0 mtspr SPRN_L2CR2,r3 - mtlr r4 + mtlr r5 blr _GLOBAL(__setup_cpu_745x) - mflr r4 + mflr r5 bl setup_common_caches bl setup_745x_specifics - mtlr r4 + mtlr r5 blr /* Enable caches for 603's, 604, 750 & 7400 */ @@ -194,10 +194,10 @@ setup_750cx: cror 4*cr0+eq,4*cr0+eq,4*cr1+eq cror 4*cr0+eq,4*cr0+eq,4*cr2+eq bnelr - lwz r6,CPU_SPEC_FEATURES(r5) + lwz r6,CPU_SPEC_FEATURES(r4) li r7,CPU_FTR_CAN_NAP andc r6,r6,r7 - stw r6,CPU_SPEC_FEATURES(r5) + stw r6,CPU_SPEC_FEATURES(r4) blr /* 750fx specific @@ -225,12 +225,12 @@ BEGIN_FTR_SECTION andis. r11,r11,L3CR_L3E@h beq 1f END_FTR_SECTION_IFSET(CPU_FTR_L3CR) - lwz r6,CPU_SPEC_FEATURES(r5) + lwz r6,CPU_SPEC_FEATURES(r4) andi. r0,r6,CPU_FTR_L3_DISABLE_NAP beq 1f li r7,CPU_FTR_CAN_NAP andc r6,r6,r7 - stw r6,CPU_SPEC_FEATURES(r5) + stw r6,CPU_SPEC_FEATURES(r4) 1: mfspr r11,SPRN_HID0 --- a/arch/powerpc/sysdev/fsl_rio.c +++ b/arch/powerpc/sysdev/fsl_rio.c @@ -832,7 +832,6 @@ fsl_rio_dbell_handler(int irq, void *dev if (dsr & DOORBELL_DSR_QFI) { pr_info("RIO: doorbell queue full\n"); out_be32(&priv->msg_regs->dsr, DOORBELL_DSR_QFI); - goto out; } /* XXX Need to check/dispatch until queue empty */ --- a/arch/s390/include/asm/processor.h +++ b/arch/s390/include/asm/processor.h @@ -150,11 +150,6 @@ extern int kernel_thread(int (*fn)(void */ extern unsigned long thread_saved_pc(struct task_struct *t); -/* - * Print register of task into buffer. Used in fs/proc/array.c. - */ -extern void task_show_regs(struct seq_file *m, struct task_struct *task); - extern void show_code(struct pt_regs *regs); unsigned long get_wchan(struct task_struct *p); --- a/arch/s390/include/asm/system.h +++ b/arch/s390/include/asm/system.h @@ -97,7 +97,6 @@ static inline void restore_access_regs(u extern void account_vtime(struct task_struct *, struct task_struct *); extern void account_tick_vtime(struct task_struct *); -extern void account_system_vtime(struct task_struct *); #ifdef CONFIG_PFAULT extern void pfault_irq_init(void); --- a/arch/s390/include/asm/vdso.h +++ b/arch/s390/include/asm/vdso.h @@ -7,7 +7,7 @@ #define VDSO32_LBASE 0 #define VDSO64_LBASE 0 -#define VDSO_VERSION_STRING LINUX_2.6.26 +#define VDSO_VERSION_STRING LINUX_2.6.29 #ifndef __ASSEMBLY__ --- a/arch/s390/kernel/traps.c +++ b/arch/s390/kernel/traps.c @@ -243,43 +243,6 @@ void show_regs(struct pt_regs *regs) show_last_breaking_event(regs); } -/* This is called from fs/proc/array.c */ -void task_show_regs(struct seq_file *m, struct task_struct *task) -{ - struct pt_regs *regs; - - regs = task_pt_regs(task); - seq_printf(m, "task: %p, ksp: %p\n", - task, (void *)task->thread.ksp); - seq_printf(m, "User PSW : %p %p\n", - (void *) regs->psw.mask, (void *)regs->psw.addr); - - seq_printf(m, "User GPRS: " FOURLONG, - regs->gprs[0], regs->gprs[1], - regs->gprs[2], regs->gprs[3]); - seq_printf(m, " " FOURLONG, - regs->gprs[4], regs->gprs[5], - regs->gprs[6], regs->gprs[7]); - seq_printf(m, " " FOURLONG, - regs->gprs[8], regs->gprs[9], - regs->gprs[10], regs->gprs[11]); - seq_printf(m, " " FOURLONG, - regs->gprs[12], regs->gprs[13], - regs->gprs[14], regs->gprs[15]); - seq_printf(m, "User ACRS: %08x %08x %08x %08x\n", - task->thread.acrs[0], task->thread.acrs[1], - task->thread.acrs[2], task->thread.acrs[3]); - seq_printf(m, " %08x %08x %08x %08x\n", - task->thread.acrs[4], task->thread.acrs[5], - task->thread.acrs[6], task->thread.acrs[7]); - seq_printf(m, " %08x %08x %08x %08x\n", - task->thread.acrs[8], task->thread.acrs[9], - task->thread.acrs[10], task->thread.acrs[11]); - seq_printf(m, " %08x %08x %08x %08x\n", - task->thread.acrs[12], task->thread.acrs[13], - task->thread.acrs[14], task->thread.acrs[15]); -} - static DEFINE_SPINLOCK(die_lock); void die(const char * str, struct pt_regs * regs, long err) --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -753,6 +753,17 @@ config SCHED_MC making when dealing with multi-core CPU chips at a cost of slightly increased overhead in some places. If unsure say N here. +config IRQ_TIME_ACCOUNTING + bool "Fine granularity task level IRQ time accounting" + default n + ---help--- + Select this option to enable fine granularity task irq time + accounting. This is done by reading a timestamp on each + transitions between softirq and hardirq state, so there can be a + small performance impact. + + If in doubt, say N here. + source "kernel/Kconfig.preempt" config X86_UP_APIC --- a/arch/x86/include/asm/acpi.h +++ b/arch/x86/include/asm/acpi.h @@ -89,6 +89,7 @@ extern int acpi_ht; extern int acpi_pci_disabled; extern int acpi_skip_timer_override; extern int acpi_use_timer_override; +extern int acpi_fix_pin2_polarity; extern u8 acpi_sci_flags; extern int acpi_sci_override_gsi; --- a/arch/x86/include/asm/mmu_context.h +++ b/arch/x86/include/asm/mmu_context.h @@ -36,8 +36,6 @@ static inline void switch_mm(struct mm_s unsigned cpu = smp_processor_id(); if (likely(prev != next)) { - /* stop flush ipis for the previous mm */ - cpumask_clear_cpu(cpu, mm_cpumask(prev)); #ifdef CONFIG_SMP percpu_write(cpu_tlbstate.state, TLBSTATE_OK); percpu_write(cpu_tlbstate.active_mm, next); @@ -47,6 +45,9 @@ static inline void switch_mm(struct mm_s /* Re-load page tables */ load_cr3(next->pgd); + /* stop flush ipis for the previous mm */ + cpumask_clear_cpu(cpu, mm_cpumask(prev)); + /* * load the LDT, if the LDT is different: */ --- a/arch/x86/include/asm/pvclock.h +++ b/arch/x86/include/asm/pvclock.h @@ -10,5 +10,6 @@ unsigned long pvclock_tsc_khz(struct pvc void pvclock_read_wallclock(struct pvclock_wall_clock *wall, struct pvclock_vcpu_time_info *vcpu, struct timespec *ts); +void pvclock_resume(void); #endif /* _ASM_X86_PVCLOCK_H */ --- a/arch/x86/include/asm/smpboot_hooks.h +++ b/arch/x86/include/asm/smpboot_hooks.h @@ -34,7 +34,7 @@ static inline void smpboot_restore_warm_ */ CMOS_WRITE(0, 0xf); - *((volatile long *)phys_to_virt(apic->trampoline_phys_low)) = 0; + *((volatile u32 *)phys_to_virt(apic->trampoline_phys_low)) = 0; } static inline void __init smpboot_setup_io_apic(void) --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -70,6 +70,7 @@ u8 acpi_sci_flags __initdata; int acpi_sci_override_gsi __initdata; int acpi_skip_timer_override __initdata; int acpi_use_timer_override __initdata; +int acpi_fix_pin2_polarity __initdata; #ifdef CONFIG_X86_LOCAL_APIC static u64 acpi_lapic_addr __initdata = APIC_DEFAULT_PHYS_BASE; @@ -360,10 +361,15 @@ acpi_parse_int_src_ovr(struct acpi_subta return 0; } - if (acpi_skip_timer_override && - intsrc->source_irq == 0 && intsrc->global_irq == 2) { - printk(PREFIX "BIOS IRQ0 pin2 override ignored.\n"); - return 0; + if (intsrc->source_irq == 0 && intsrc->global_irq == 2) { + if (acpi_skip_timer_override) { + printk(PREFIX "BIOS IRQ0 pin2 override ignored.\n"); + return 0; + } + if (acpi_fix_pin2_polarity && (intsrc->inti_flags & ACPI_MADT_POLARITY_MASK)) { + intsrc->inti_flags &= ~ACPI_MADT_POLARITY_MASK; + printk(PREFIX "BIOS IRQ0 pin2 override: forcing polarity to high active.\n"); + } } mp_override_legacy_irq(intsrc->source_irq, --- a/arch/x86/kernel/cpu/mtrr/main.c +++ b/arch/x86/kernel/cpu/mtrr/main.c @@ -762,13 +762,21 @@ void set_mtrr_aps_delayed_init(void) } /* - * MTRR initialization for all AP's + * Delayed MTRR initialization for all AP's */ void mtrr_aps_init(void) { if (!use_intel()) return; + /* + * Check if someone has requested the delay of AP MTRR initialization, + * by doing set_mtrr_aps_delayed_init(), prior to this point. If not, + * then we are done. + */ + if (!mtrr_aps_delayed_init) + return; + set_mtrr(~0U, 0, 0, 0); mtrr_aps_delayed_init = false; } --- a/arch/x86/kernel/early-quirks.c +++ b/arch/x86/kernel/early-quirks.c @@ -145,15 +145,10 @@ static void __init ati_bugs(int num, int static u32 __init ati_sbx00_rev(int num, int slot, int func) { - u32 old, d; + u32 d; - d = read_pci_config(num, slot, func, 0x70); - old = d; - d &= ~(1<<8); - write_pci_config(num, slot, func, 0x70, d); d = read_pci_config(num, slot, func, 0x8); d &= 0xff; - write_pci_config(num, slot, func, 0x70, old); return d; } @@ -162,13 +157,16 @@ static void __init ati_bugs_contd(int nu { u32 d, rev; - if (acpi_use_timer_override) - return; - rev = ati_sbx00_rev(num, slot, func); + if (rev >= 0x40) + acpi_fix_pin2_polarity = 1; + if (rev > 0x13) return; + if (acpi_use_timer_override) + return; + /* check for IRQ0 interrupt swap */ d = read_pci_config(num, slot, func, 0x64); if (!(d & (1<<14))) --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -606,6 +606,8 @@ static void hpet_msi_capability_lookup(u if (hpet_msi_disable) return; + if (boot_cpu_has(X86_FEATURE_ARAT)) + return; id = hpet_readl(HPET_ID); num_timers = ((id & HPET_ID_NUMBER) >> HPET_ID_NUMBER_SHIFT); @@ -894,10 +896,8 @@ int __init hpet_enable(void) if (id & HPET_ID_LEGSUP) { hpet_legacy_clockevent_register(); - hpet_msi_capability_lookup(2); return 1; } - hpet_msi_capability_lookup(0); return 0; out_nohpet: @@ -930,12 +930,20 @@ static __init int hpet_late_init(void) if (!hpet_virt_address) return -ENODEV; + if (hpet_readl(HPET_ID) & HPET_ID_LEGSUP) + hpet_msi_capability_lookup(2); + else + hpet_msi_capability_lookup(0); + hpet_reserve_platform_timers(hpet_readl(HPET_ID)); hpet_print_config(); if (hpet_msi_disable) return 0; + if (boot_cpu_has(X86_FEATURE_ARAT)) + return 0; + for_each_online_cpu(cpu) { hpet_cpuhp_notify(NULL, CPU_ONLINE, (void *)(long)cpu); } --- a/arch/x86/kernel/pvclock.c +++ b/arch/x86/kernel/pvclock.c @@ -111,6 +111,11 @@ unsigned long pvclock_tsc_khz(struct pvc static atomic64_t last_value = ATOMIC64_INIT(0); +void pvclock_resume(void) +{ + atomic64_set(&last_value, 0); +} + cycle_t pvclock_clocksource_read(struct pvclock_vcpu_time_info *src) { struct pvclock_shadow_time shadow; --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -104,10 +104,14 @@ int __init notsc_setup(char *str) __setup("notsc", notsc_setup); +static int no_sched_irq_time; + static int __init tsc_setup(char *str) { if (!strcmp(str, "reliable")) tsc_clocksource_reliable = 1; + if (!strncmp(str, "noirqtime", 9)) + no_sched_irq_time = 1; return 1; } @@ -802,6 +806,7 @@ void mark_tsc_unstable(char *reason) if (!tsc_unstable) { tsc_unstable = 1; sched_clock_stable = 0; + disable_sched_clock_irqtime(); printk(KERN_INFO "Marking TSC unstable due to %s\n", reason); /* Change only the rating, when not registered */ if (clocksource_tsc.mult) @@ -990,6 +995,9 @@ void __init tsc_init(void) /* now allow native_sched_clock() to use rdtsc */ tsc_disabled = 0; + if (!no_sched_irq_time) + enable_sched_clock_irqtime(); + lpj = ((u64)tsc_khz * 1000); do_div(lpj, HZ); lpj_fine = lpj; --- a/arch/x86/xen/time.c +++ b/arch/x86/xen/time.c @@ -424,6 +424,8 @@ void xen_timer_resume(void) { int cpu; + pvclock_resume(); + if (xen_clockevent != &xen_vcpuop_clockevent) return; --- a/drivers/ata/pata_mpc52xx.c +++ b/drivers/ata/pata_mpc52xx.c @@ -610,7 +610,7 @@ static struct scsi_host_template mpc52xx }; static struct ata_port_operations mpc52xx_ata_port_ops = { - .inherits = &ata_sff_port_ops, + .inherits = &ata_bmdma_port_ops, .sff_dev_select = mpc52xx_ata_dev_select, .set_piomode = mpc52xx_ata_set_piomode, .set_dmamode = mpc52xx_ata_set_dmamode, --- a/drivers/block/pktcdvd.c +++ b/drivers/block/pktcdvd.c @@ -2408,7 +2408,7 @@ static void pkt_release_dev(struct pktcd pkt_shrink_pktlist(pd); } -static struct pktcdvd_device *pkt_find_dev_from_minor(int dev_minor) +static struct pktcdvd_device *pkt_find_dev_from_minor(unsigned int dev_minor) { if (dev_minor >= MAX_WRITERS) return NULL; --- a/drivers/char/hvc_iucv.c +++ b/drivers/char/hvc_iucv.c @@ -139,6 +139,8 @@ struct hvc_iucv_private *hvc_iucv_get_pr * * This function allocates a new struct iucv_tty_buffer element and, optionally, * allocates an internal data buffer with the specified size @size. + * The internal data buffer is always allocated with GFP_DMA which is + * required for receiving and sending data with IUCV. * Note: The total message size arises from the internal buffer size and the * members of the iucv_tty_msg structure. * The function returns NULL if memory allocation has failed. @@ -154,7 +156,7 @@ static struct iucv_tty_buffer *alloc_tty if (size > 0) { bufp->msg.length = MSG_SIZE(size); - bufp->mbuf = kmalloc(bufp->msg.length, flags); + bufp->mbuf = kmalloc(bufp->msg.length, flags | GFP_DMA); if (!bufp->mbuf) { mempool_free(bufp, hvc_iucv_mempool); return NULL; @@ -237,7 +239,7 @@ static int hvc_iucv_write(struct hvc_iuc if (!rb->mbuf) { /* message not yet received ... */ /* allocate mem to store msg data; if no memory is available * then leave the buffer on the list and re-try later */ - rb->mbuf = kmalloc(rb->msg.length, GFP_ATOMIC); + rb->mbuf = kmalloc(rb->msg.length, GFP_ATOMIC | GFP_DMA); if (!rb->mbuf) return -ENOMEM; --- a/drivers/char/tpm/tpm.c +++ b/drivers/char/tpm/tpm.c @@ -353,12 +353,14 @@ unsigned long tpm_calc_ordinal_duration( tpm_protected_ordinal_duration[ordinal & TPM_PROTECTED_ORDINAL_MASK]; - if (duration_idx != TPM_UNDEFINED) + if (duration_idx != TPM_UNDEFINED) { duration = chip->vendor.duration[duration_idx]; - if (duration <= 0) + /* if duration is 0, it's because chip->vendor.duration wasn't */ + /* filled yet, so we set the lowest timeout just to give enough */ + /* time for tpm_get_timeouts() to succeed */ + return (duration <= 0 ? HZ : duration); + } else return 2 * 60 * HZ; - else - return duration; } EXPORT_SYMBOL_GPL(tpm_calc_ordinal_duration); @@ -564,9 +566,11 @@ duration: if (rc) return; - if (be32_to_cpu(tpm_cmd.header.out.return_code) - != 3 * sizeof(u32)) + if (be32_to_cpu(tpm_cmd.header.out.return_code) != 0 || + be32_to_cpu(tpm_cmd.header.out.length) + != sizeof(tpm_cmd.header.out) + sizeof(u32) + 3 * sizeof(u32)) return; + duration_cap = &tpm_cmd.params.getcap_out.cap.duration; chip->vendor.duration[TPM_SHORT] = usecs_to_jiffies(be32_to_cpu(duration_cap->tpm_short)); @@ -910,6 +914,18 @@ ssize_t tpm_show_caps_1_2(struct device } EXPORT_SYMBOL_GPL(tpm_show_caps_1_2); +ssize_t tpm_show_timeouts(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct tpm_chip *chip = dev_get_drvdata(dev); + + return sprintf(buf, "%d %d %d\n", + jiffies_to_usecs(chip->vendor.duration[TPM_SHORT]), + jiffies_to_usecs(chip->vendor.duration[TPM_MEDIUM]), + jiffies_to_usecs(chip->vendor.duration[TPM_LONG])); +} +EXPORT_SYMBOL_GPL(tpm_show_timeouts); + ssize_t tpm_store_cancel(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { --- a/drivers/char/tpm/tpm.h +++ b/drivers/char/tpm/tpm.h @@ -56,6 +56,8 @@ extern ssize_t tpm_show_owned(struct dev char *); extern ssize_t tpm_show_temp_deactivated(struct device *, struct device_attribute *attr, char *); +extern ssize_t tpm_show_timeouts(struct device *, + struct device_attribute *attr, char *); struct tpm_chip; --- a/drivers/char/tpm/tpm_tis.c +++ b/drivers/char/tpm/tpm_tis.c @@ -354,6 +354,7 @@ static DEVICE_ATTR(temp_deactivated, S_I NULL); static DEVICE_ATTR(caps, S_IRUGO, tpm_show_caps_1_2, NULL); static DEVICE_ATTR(cancel, S_IWUSR | S_IWGRP, NULL, tpm_store_cancel); +static DEVICE_ATTR(timeouts, S_IRUGO, tpm_show_timeouts, NULL); static struct attribute *tis_attrs[] = { &dev_attr_pubek.attr, @@ -363,7 +364,8 @@ static struct attribute *tis_attrs[] = { &dev_attr_owned.attr, &dev_attr_temp_deactivated.attr, &dev_attr_caps.attr, - &dev_attr_cancel.attr, NULL, + &dev_attr_cancel.attr, + &dev_attr_timeouts.attr, NULL, }; static struct attribute_group tis_attr_grp = { --- a/drivers/gpu/drm/Kconfig +++ b/drivers/gpu/drm/Kconfig @@ -92,7 +92,10 @@ config DRM_I830 config DRM_I915 tristate "i915 driver" depends on AGP_INTEL + # we need shmfs for the swappable backing store, and in particular + # the shmem_readpage() which depends upon tmpfs select SHMEM + select TMPFS select DRM_KMS_HELPER select FB_CFB_FILLRECT select FB_CFB_COPYAREA --- a/drivers/gpu/drm/drm_irq.c +++ b/drivers/gpu/drm/drm_irq.c @@ -540,7 +540,8 @@ int drm_modeset_ctl(struct drm_device *d struct drm_file *file_priv) { struct drm_modeset_ctl *modeset = data; - int crtc, ret = 0; + int ret = 0; + unsigned int crtc; /* If drm_vblank_init() hasn't been called yet, just no-op */ if (!dev->num_crtcs) --- a/drivers/gpu/drm/i915/intel_lvds.c +++ b/drivers/gpu/drm/i915/intel_lvds.c @@ -884,6 +884,14 @@ static const struct dmi_system_id intel_ }, { .callback = intel_no_lvds_dmi_callback, + .ident = "AOpen i915GMm-HFS", + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "AOpen"), + DMI_MATCH(DMI_BOARD_NAME, "i915GMm-HFS"), + }, + }, + { + .callback = intel_no_lvds_dmi_callback, .ident = "Aopen i945GTt-VFA", .matches = { DMI_MATCH(DMI_PRODUCT_VERSION, "AO00001JW"), --- a/drivers/gpu/drm/radeon/radeon_atombios.c +++ b/drivers/gpu/drm/radeon/radeon_atombios.c @@ -152,6 +152,13 @@ static bool radeon_atom_apply_quirks(str return false; } + /* mac rv630, rv730, others */ + if ((supported_device == ATOM_DEVICE_TV1_SUPPORT) && + (*connector_type == DRM_MODE_CONNECTOR_DVII)) { + *connector_type = DRM_MODE_CONNECTOR_9PinDIN; + *line_mux = CONNECTOR_7PIN_DIN_ENUM_ID1; + } + /* ASUS HD 3600 XT board lists the DVI port as HDMI */ if ((dev->pdev->device == 0x9598) && (dev->pdev->subsystem_vendor == 0x1043) && @@ -1210,7 +1217,7 @@ void radeon_atom_initialize_bios_scratch bios_2_scratch &= ~ATOM_S2_VRI_BRIGHT_ENABLE; /* tell the bios not to handle mode switching */ - bios_6_scratch |= (ATOM_S6_ACC_BLOCK_DISPLAY_SWITCH | ATOM_S6_ACC_MODE); + bios_6_scratch |= ATOM_S6_ACC_BLOCK_DISPLAY_SWITCH; if (rdev->family >= CHIP_R600) { WREG32(R600_BIOS_2_SCRATCH, bios_2_scratch); @@ -1261,10 +1268,13 @@ void radeon_atom_output_lock(struct drm_ else bios_6_scratch = RREG32(RADEON_BIOS_6_SCRATCH); - if (lock) + if (lock) { bios_6_scratch |= ATOM_S6_CRITICAL_STATE; - else + bios_6_scratch &= ~ATOM_S6_ACC_MODE; + } else { bios_6_scratch &= ~ATOM_S6_CRITICAL_STATE; + bios_6_scratch |= ATOM_S6_ACC_MODE; + } if (rdev->family >= CHIP_R600) WREG32(R600_BIOS_6_SCRATCH, bios_6_scratch); --- a/drivers/gpu/drm/radeon/radeon_display.c +++ b/drivers/gpu/drm/radeon/radeon_display.c @@ -540,6 +540,10 @@ void radeon_compute_pll(struct radeon_pl *frac_fb_div_p = best_frac_feedback_div; *ref_div_p = best_ref_div; *post_div_p = best_post_div; + DRM_DEBUG_KMS("%d %d, pll dividers - fb: %d.%d ref: %d, post %d\n", + freq, best_freq / 1000, best_feedback_div, best_frac_feedback_div, + best_ref_div, best_post_div); + } static void radeon_user_framebuffer_destroy(struct drm_framebuffer *fb) --- a/drivers/hid/hid-core.c +++ b/drivers/hid/hid-core.c @@ -1297,6 +1297,7 @@ static const struct hid_device_id hid_bl { HID_USB_DEVICE(USB_VENDOR_ID_CHICONY, USB_DEVICE_ID_CHICONY_TACTICAL_PAD) }, { HID_USB_DEVICE(USB_VENDOR_ID_CYPRESS, USB_DEVICE_ID_CYPRESS_BARCODE_1) }, { HID_USB_DEVICE(USB_VENDOR_ID_CYPRESS, USB_DEVICE_ID_CYPRESS_BARCODE_2) }, + { HID_USB_DEVICE(USB_VENDOR_ID_CYPRESS, USB_DEVICE_ID_CYPRESS_BARCODE_3) }, { HID_USB_DEVICE(USB_VENDOR_ID_CYPRESS, USB_DEVICE_ID_CYPRESS_MOUSE) }, { HID_USB_DEVICE(USB_VENDOR_ID_DRAGONRISE, 0x0006) }, { HID_USB_DEVICE(USB_VENDOR_ID_EZKEY, USB_DEVICE_ID_BTC_8193) }, --- a/drivers/hid/hid-cypress.c +++ b/drivers/hid/hid-cypress.c @@ -126,6 +126,8 @@ static const struct hid_device_id cp_dev .driver_data = CP_RDESC_SWAPPED_MIN_MAX }, { HID_USB_DEVICE(USB_VENDOR_ID_CYPRESS, USB_DEVICE_ID_CYPRESS_BARCODE_2), .driver_data = CP_RDESC_SWAPPED_MIN_MAX }, + { HID_USB_DEVICE(USB_VENDOR_ID_CYPRESS, USB_DEVICE_ID_CYPRESS_BARCODE_3), + .driver_data = CP_RDESC_SWAPPED_MIN_MAX }, { HID_USB_DEVICE(USB_VENDOR_ID_CYPRESS, USB_DEVICE_ID_CYPRESS_MOUSE), .driver_data = CP_2WHEEL_MOUSE_HACK }, { } --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -148,6 +148,7 @@ #define USB_DEVICE_ID_CYPRESS_ULTRAMOUSE 0x7417 #define USB_DEVICE_ID_CYPRESS_BARCODE_1 0xde61 #define USB_DEVICE_ID_CYPRESS_BARCODE_2 0xde64 +#define USB_DEVICE_ID_CYPRESS_BARCODE_3 0xbca1 #define USB_VENDOR_ID_DEALEXTREAME 0x10c5 #define USB_DEVICE_ID_DEALEXTREAME_RADIO_SI4701 0x819a --- a/drivers/hwmon/via686a.c +++ b/drivers/hwmon/via686a.c @@ -687,6 +687,13 @@ static int __devexit via686a_remove(stru return 0; } +static void via686a_update_fan_div(struct via686a_data *data) +{ + int reg = via686a_read_value(data, VIA686A_REG_FANDIV); + data->fan_div[0] = (reg >> 4) & 0x03; + data->fan_div[1] = reg >> 6; +} + static void __devinit via686a_init_device(struct via686a_data *data) { u8 reg; @@ -700,6 +707,9 @@ static void __devinit via686a_init_devic via686a_write_value(data, VIA686A_REG_TEMP_MODE, (reg & ~VIA686A_TEMP_MODE_MASK) | VIA686A_TEMP_MODE_CONTINUOUS); + + /* Pre-read fan clock divisor values */ + via686a_update_fan_div(data); } static struct via686a_data *via686a_update_device(struct device *dev) @@ -751,9 +761,7 @@ static struct via686a_data *via686a_upda (via686a_read_value(data, VIA686A_REG_TEMP_LOW23) & 0xc0) >> 6; - i = via686a_read_value(data, VIA686A_REG_FANDIV); - data->fan_div[0] = (i >> 4) & 0x03; - data->fan_div[1] = i >> 6; + via686a_update_fan_div(data); data->alarms = via686a_read_value(data, VIA686A_REG_ALARM1) | --- a/drivers/i2c/i2c-core.c +++ b/drivers/i2c/i2c-core.c @@ -745,6 +745,14 @@ static int i2c_do_del_adapter(struct dev static int __unregister_client(struct device *dev, void *dummy) { struct i2c_client *client = i2c_verify_client(dev); + if (client && strcmp(client->name, "dummy")) + i2c_unregister_device(client); + return 0; +} + +static int __unregister_dummy(struct device *dev, void *dummy) +{ + struct i2c_client *client = i2c_verify_client(dev); if (client) i2c_unregister_device(client); return 0; @@ -793,8 +801,12 @@ int i2c_del_adapter(struct i2c_adapter * } /* Detach any active clients. This can't fail, thus we do not - checking the returned value. */ + * check the returned value. This is a two-pass process, because + * we can't remove the dummy devices during the first pass: they + * could have been instantiated by real devices wishing to clean + * them up properly, so we give them a chance to do that first. */ res = device_for_each_child(&adap->dev, NULL, __unregister_client); + res = device_for_each_child(&adap->dev, NULL, __unregister_dummy); #ifdef CONFIG_I2C_COMPAT class_compat_remove_link(i2c_adapter_compat_class, &adap->dev, --- a/drivers/input/mouse/bcm5974.c +++ b/drivers/input/mouse/bcm5974.c @@ -55,6 +55,14 @@ #define USB_DEVICE_ID_APPLE_WELLSPRING3_ANSI 0x0236 #define USB_DEVICE_ID_APPLE_WELLSPRING3_ISO 0x0237 #define USB_DEVICE_ID_APPLE_WELLSPRING3_JIS 0x0238 +/* MacbookAir3,2 (unibody), aka wellspring5 */ +#define USB_DEVICE_ID_APPLE_WELLSPRING4_ANSI 0x023f +#define USB_DEVICE_ID_APPLE_WELLSPRING4_ISO 0x0240 +#define USB_DEVICE_ID_APPLE_WELLSPRING4_JIS 0x0241 +/* MacbookAir3,1 (unibody), aka wellspring4 */ +#define USB_DEVICE_ID_APPLE_WELLSPRING4A_ANSI 0x0242 +#define USB_DEVICE_ID_APPLE_WELLSPRING4A_ISO 0x0243 +#define USB_DEVICE_ID_APPLE_WELLSPRING4A_JIS 0x0244 #define BCM5974_DEVICE(prod) { \ .match_flags = (USB_DEVICE_ID_MATCH_DEVICE | \ @@ -80,6 +88,14 @@ static const struct usb_device_id bcm597 BCM5974_DEVICE(USB_DEVICE_ID_APPLE_WELLSPRING3_ANSI), BCM5974_DEVICE(USB_DEVICE_ID_APPLE_WELLSPRING3_ISO), BCM5974_DEVICE(USB_DEVICE_ID_APPLE_WELLSPRING3_JIS), + /* MacbookAir3,2 */ + BCM5974_DEVICE(USB_DEVICE_ID_APPLE_WELLSPRING4_ANSI), + BCM5974_DEVICE(USB_DEVICE_ID_APPLE_WELLSPRING4_ISO), + BCM5974_DEVICE(USB_DEVICE_ID_APPLE_WELLSPRING4_JIS), + /* MacbookAir3,1 */ + BCM5974_DEVICE(USB_DEVICE_ID_APPLE_WELLSPRING4A_ANSI), + BCM5974_DEVICE(USB_DEVICE_ID_APPLE_WELLSPRING4A_ISO), + BCM5974_DEVICE(USB_DEVICE_ID_APPLE_WELLSPRING4A_JIS), /* Terminating entry */ {} }; @@ -233,6 +249,30 @@ static const struct bcm5974_config bcm59 { DIM_X, DIM_X / SN_COORD, -4460, 5166 }, { DIM_Y, DIM_Y / SN_COORD, -75, 6700 } }, + { + USB_DEVICE_ID_APPLE_WELLSPRING4_ANSI, + USB_DEVICE_ID_APPLE_WELLSPRING4_ISO, + USB_DEVICE_ID_APPLE_WELLSPRING4_JIS, + HAS_INTEGRATED_BUTTON, + 0x84, sizeof(struct bt_data), + 0x81, TYPE2, FINGER_TYPE2, FINGER_TYPE2 + SIZEOF_ALL_FINGERS, + { DIM_PRESSURE, DIM_PRESSURE / SN_PRESSURE, 0, 300 }, + { DIM_WIDTH, DIM_WIDTH / SN_WIDTH, 0, 2048 }, + { DIM_X, DIM_X / SN_COORD, -4620, 5140 }, + { DIM_Y, DIM_Y / SN_COORD, -150, 6600 } + }, + { + USB_DEVICE_ID_APPLE_WELLSPRING4A_ANSI, + USB_DEVICE_ID_APPLE_WELLSPRING4A_ISO, + USB_DEVICE_ID_APPLE_WELLSPRING4A_JIS, + HAS_INTEGRATED_BUTTON, + 0x84, sizeof(struct bt_data), + 0x81, TYPE2, FINGER_TYPE2, FINGER_TYPE2 + SIZEOF_ALL_FINGERS, + { DIM_PRESSURE, DIM_PRESSURE / SN_PRESSURE, 0, 300 }, + { DIM_WIDTH, DIM_WIDTH / SN_WIDTH, 0, 2048 }, + { DIM_X, DIM_X / SN_COORD, -4616, 5112 }, + { DIM_Y, DIM_Y / SN_COORD, -142, 5234 } + }, {} }; --- a/drivers/input/serio/i8042-x86ia64io.h +++ b/drivers/input/serio/i8042-x86ia64io.h @@ -416,6 +416,13 @@ static const struct dmi_system_id __init DMI_MATCH(DMI_PRODUCT_VERSION, "0100"), }, }, + { + /* Dell Vostro V13 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "Vostro V13"), + }, + }, { } }; @@ -537,6 +544,17 @@ static const struct dmi_system_id __init }; #endif +static const struct dmi_system_id __initconst i8042_dmi_notimeout_table[] = { + { + /* Dell Vostro V13 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "Vostro V13"), + }, + }, + { } +}; + /* * Some Wistron based laptops need us to explicitly enable the 'Dritek * keyboard extension' to make their extra keys start generating scancodes. @@ -866,6 +884,9 @@ static int __init i8042_platform_init(vo if (dmi_check_system(i8042_dmi_nomux_table)) i8042_nomux = true; + if (dmi_check_system(i8042_dmi_notimeout_table)) + i8042_notimeout = true; + if (dmi_check_system(i8042_dmi_dritek_table)) i8042_dritek = true; #endif /* CONFIG_X86 */ --- a/drivers/input/serio/i8042.c +++ b/drivers/input/serio/i8042.c @@ -64,6 +64,10 @@ static unsigned int i8042_blink_frequenc module_param_named(panicblink, i8042_blink_frequency, uint, 0600); MODULE_PARM_DESC(panicblink, "Frequency with which keyboard LEDs should blink when kernel panics"); +static bool i8042_notimeout; +module_param_named(notimeout, i8042_notimeout, bool, 0); +MODULE_PARM_DESC(notimeout, "Ignore timeouts signalled by i8042"); + #ifdef CONFIG_X86 static bool i8042_dritek; module_param_named(dritek, i8042_dritek, bool, 0); @@ -434,7 +438,7 @@ static irqreturn_t i8042_interrupt(int i } else { dfl = ((str & I8042_STR_PARITY) ? SERIO_PARITY : 0) | - ((str & I8042_STR_TIMEOUT) ? SERIO_TIMEOUT : 0); + ((str & I8042_STR_TIMEOUT && !i8042_notimeout) ? SERIO_TIMEOUT : 0); port_no = (str & I8042_STR_AUXDATA) ? I8042_AUX_PORT_NO : I8042_KBD_PORT_NO; --- a/drivers/isdn/hisax/config.c +++ b/drivers/isdn/hisax/config.c @@ -800,6 +800,16 @@ static void closecard(int cardnr) ll_unload(csta); } +static irqreturn_t card_irq(int intno, void *dev_id) +{ + struct IsdnCardState *cs = dev_id; + irqreturn_t ret = cs->irq_func(intno, cs); + + if (ret == IRQ_HANDLED) + cs->irq_cnt++; + return ret; +} + static int init_card(struct IsdnCardState *cs) { int irq_cnt, cnt = 3, ret; @@ -808,10 +818,10 @@ static int init_card(struct IsdnCardStat ret = cs->cardmsg(cs, CARD_INIT, NULL); return(ret); } - irq_cnt = kstat_irqs(cs->irq); + irq_cnt = cs->irq_cnt = 0; printk(KERN_INFO "%s: IRQ %d count %d\n", CardType[cs->typ], cs->irq, irq_cnt); - if (request_irq(cs->irq, cs->irq_func, cs->irq_flags, "HiSax", cs)) { + if (request_irq(cs->irq, card_irq, cs->irq_flags, "HiSax", cs)) { printk(KERN_WARNING "HiSax: couldn't get interrupt %d\n", cs->irq); return 1; @@ -821,8 +831,8 @@ static int init_card(struct IsdnCardStat /* Timeout 10ms */ msleep(10); printk(KERN_INFO "%s: IRQ %d count %d\n", - CardType[cs->typ], cs->irq, kstat_irqs(cs->irq)); - if (kstat_irqs(cs->irq) == irq_cnt) { + CardType[cs->typ], cs->irq, cs->irq_cnt); + if (cs->irq_cnt == irq_cnt) { printk(KERN_WARNING "%s: IRQ(%d) getting no interrupts during init %d\n", CardType[cs->typ], cs->irq, 4 - cnt); --- a/drivers/isdn/hisax/hisax.h +++ b/drivers/isdn/hisax/hisax.h @@ -959,6 +959,7 @@ struct IsdnCardState { u_long event; struct work_struct tqueue; struct timer_list dbusytimer; + unsigned int irq_cnt; #ifdef ERROR_STATISTIC int err_crc; int err_tx; --- a/drivers/md/dm-mpath.c +++ b/drivers/md/dm-mpath.c @@ -33,7 +33,6 @@ struct pgpath { unsigned fail_count; /* Cumulative failure count */ struct dm_path path; - struct work_struct deactivate_path; struct work_struct activate_path; }; @@ -113,7 +112,6 @@ static struct workqueue_struct *kmultipa static void process_queued_ios(struct work_struct *work); static void trigger_event(struct work_struct *work); static void activate_path(struct work_struct *work); -static void deactivate_path(struct work_struct *work); /*----------------------------------------------- @@ -126,7 +124,6 @@ static struct pgpath *alloc_pgpath(void) if (pgpath) { pgpath->is_active = 1; - INIT_WORK(&pgpath->deactivate_path, deactivate_path); INIT_WORK(&pgpath->activate_path, activate_path); } @@ -138,14 +135,6 @@ static void free_pgpath(struct pgpath *p kfree(pgpath); } -static void deactivate_path(struct work_struct *work) -{ - struct pgpath *pgpath = - container_of(work, struct pgpath, deactivate_path); - - blk_abort_queue(pgpath->path.dev->bdev->bd_disk->queue); -} - static struct priority_group *alloc_priority_group(void) { struct priority_group *pg; @@ -949,7 +938,6 @@ static int fail_path(struct pgpath *pgpa pgpath->path.dev->name, m->nr_valid_paths); schedule_work(&m->trigger_event); - queue_work(kmultipathd, &pgpath->deactivate_path); out: spin_unlock_irqrestore(&m->lock, flags); --- a/drivers/md/dm-raid1.c +++ b/drivers/md/dm-raid1.c @@ -659,7 +659,7 @@ static void do_writes(struct mirror_set /* * Dispatch io. */ - if (unlikely(ms->log_failure)) { + if (unlikely(ms->log_failure) && errors_handled(ms)) { spin_lock_irq(&ms->lock); bio_list_merge(&ms->failures, &sync); spin_unlock_irq(&ms->lock); --- a/drivers/md/dm-region-hash.c +++ b/drivers/md/dm-region-hash.c @@ -643,10 +643,9 @@ void dm_rh_recovery_end(struct dm_region spin_lock_irq(&rh->region_lock); if (success) list_add(®->list, ®->rh->recovered_regions); - else { - reg->state = DM_RH_NOSYNC; + else list_add(®->list, ®->rh->failed_recovered_regions); - } + spin_unlock_irq(&rh->region_lock); rh->wakeup_workers(rh->context); --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -1925,13 +1925,14 @@ static void event_callback(void *context wake_up(&md->eventq); } +/* + * Protected by md->suspend_lock obtained by dm_swap_table(). + */ static void __set_size(struct mapped_device *md, sector_t size) { set_capacity(md->disk, size); - mutex_lock(&md->bdev->bd_inode->i_mutex); i_size_write(md->bdev->bd_inode, (loff_t)size << SECTOR_SHIFT); - mutex_unlock(&md->bdev->bd_inode->i_mutex); } static int __bind(struct mapped_device *md, struct dm_table *t, --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -305,6 +305,9 @@ static mddev_t * mddev_find(dev_t unit) { mddev_t *mddev, *new = NULL; + if (unit && MAJOR(unit) != MD_MAJOR) + unit &= ~((1<persistent) { if (info->state & (1<raid_disk < mddev->raid_disks) + info->raid_disk < mddev->raid_disks) { rdev->raid_disk = info->raid_disk; - else + set_bit(In_sync, &rdev->flags); + } else rdev->raid_disk = -1; } else super_types[mddev->major_version]. --- a/drivers/media/dvb/ttpci/av7110_ca.c +++ b/drivers/media/dvb/ttpci/av7110_ca.c @@ -277,7 +277,7 @@ static int dvb_ca_ioctl(struct inode *in { ca_slot_info_t *info=(ca_slot_info_t *)parg; - if (info->num > 1) + if (info->num < 0 || info->num > 1) return -EINVAL; av7110->ci_slot[info->num].num = info->num; av7110->ci_slot[info->num].type = FW_CI_LL_SUPPORT(av7110->arm_app) ? --- a/drivers/media/radio/radio-aimslab.c +++ b/drivers/media/radio/radio-aimslab.c @@ -31,7 +31,7 @@ #include /* Modules */ #include /* Initdata */ #include /* request_region */ -#include /* udelay */ +#include /* msleep */ #include /* kernel radio structs */ #include /* for KERNEL_VERSION MACRO */ #include /* outb, outb_p */ @@ -71,27 +71,17 @@ static struct rtrack rtrack_card; /* local things */ -static void sleep_delay(long n) -{ - /* Sleep nicely for 'n' uS */ - int d = n / msecs_to_jiffies(1000); - if (!d) - udelay(n); - else - msleep(jiffies_to_msecs(d)); -} - static void rt_decvol(struct rtrack *rt) { outb(0x58, rt->io); /* volume down + sigstr + on */ - sleep_delay(100000); + msleep(100); outb(0xd8, rt->io); /* volume steady + sigstr + on */ } static void rt_incvol(struct rtrack *rt) { outb(0x98, rt->io); /* volume up + sigstr + on */ - sleep_delay(100000); + msleep(100); outb(0xd8, rt->io); /* volume steady + sigstr + on */ } @@ -120,7 +110,7 @@ static int rt_setvol(struct rtrack *rt, if (vol == 0) { /* volume = 0 means mute the card */ outb(0x48, rt->io); /* volume down but still "on" */ - sleep_delay(2000000); /* make sure it's totally down */ + msleep(2000); /* make sure it's totally down */ outb(0xd0, rt->io); /* volume steady, off */ rt->curvol = 0; /* track the volume state! */ mutex_unlock(&rt->lock); @@ -155,7 +145,7 @@ static void send_0_byte(struct rtrack *r outb_p(128+64+16+8+ 1, rt->io); /* on + wr-enable + data low */ outb_p(128+64+16+8+2+1, rt->io); /* clock */ } - sleep_delay(1000); + msleep(1); } static void send_1_byte(struct rtrack *rt) @@ -169,7 +159,7 @@ static void send_1_byte(struct rtrack *r outb_p(128+64+16+8+4+2+1, rt->io); /* clock */ } - sleep_delay(1000); + msleep(1); } static int rt_setfreq(struct rtrack *rt, unsigned long freq) @@ -423,7 +413,7 @@ static int __init rtrack_init(void) /* this ensures that the volume is all the way down */ outb(0x48, rt->io); /* volume down but still "on" */ - sleep_delay(2000000); /* make sure it's totally down */ + msleep(2000); /* make sure it's totally down */ outb(0xc0, rt->io); /* steady volume, mute card */ return 0; --- a/drivers/media/video/em28xx/em28xx-cards.c +++ b/drivers/media/video/em28xx/em28xx-cards.c @@ -1525,11 +1525,11 @@ struct em28xx_board em28xx_boards[] = { .input = { { .type = EM28XX_VMUX_COMPOSITE1, .vmux = SAA7115_COMPOSITE0, - .amux = EM28XX_AMUX_VIDEO2, + .amux = EM28XX_AMUX_LINE_IN, }, { .type = EM28XX_VMUX_SVIDEO, .vmux = SAA7115_SVIDEO3, - .amux = EM28XX_AMUX_VIDEO2, + .amux = EM28XX_AMUX_LINE_IN, } }, }, [EM2860_BOARD_TERRATEC_AV350] = { --- a/drivers/message/fusion/mptctl.c +++ b/drivers/message/fusion/mptctl.c @@ -577,6 +577,13 @@ mptctl_event_process(MPT_ADAPTER *ioc, E } static int +mptctl_release(struct inode *inode, struct file *filep) +{ + fasync_helper(-1, filep, 0, &async_queue); + return 0; +} + +static int mptctl_fasync(int fd, struct file *filep, int mode) { MPT_ADAPTER *ioc; @@ -2778,6 +2785,7 @@ static const struct file_operations mptc .llseek = no_llseek, .fasync = mptctl_fasync, .unlocked_ioctl = mptctl_ioctl, + .release = mptctl_release, #ifdef CONFIG_COMPAT .compat_ioctl = compat_mpctl_ioctl, #endif --- a/drivers/message/fusion/mptscsih.c +++ b/drivers/message/fusion/mptscsih.c @@ -1835,8 +1835,9 @@ mptscsih_abort(struct scsi_cmnd * SCpnt) } out: - printk(MYIOC_s_INFO_FMT "task abort: %s (sc=%p)\n", - ioc->name, ((retval == SUCCESS) ? "SUCCESS" : "FAILED"), SCpnt); + printk(MYIOC_s_INFO_FMT "task abort: %s (rv=%04x) (sc=%p) (sn=%ld)\n", + ioc->name, ((retval == SUCCESS) ? "SUCCESS" : "FAILED"), retval, + SCpnt, SCpnt->serial_number); return retval; } @@ -1873,7 +1874,7 @@ mptscsih_dev_reset(struct scsi_cmnd * SC vdevice = SCpnt->device->hostdata; if (!vdevice || !vdevice->vtarget) { - retval = SUCCESS; + retval = 0; goto out; } --- a/drivers/mfd/ucb1x00-ts.c +++ b/drivers/mfd/ucb1x00-ts.c @@ -385,12 +385,18 @@ static int ucb1x00_ts_add(struct ucb1x00 idev->close = ucb1x00_ts_close; __set_bit(EV_ABS, idev->evbit); - __set_bit(ABS_X, idev->absbit); - __set_bit(ABS_Y, idev->absbit); - __set_bit(ABS_PRESSURE, idev->absbit); input_set_drvdata(idev, ts); + ucb1x00_adc_enable(ts->ucb); + ts->x_res = ucb1x00_ts_read_xres(ts); + ts->y_res = ucb1x00_ts_read_yres(ts); + ucb1x00_adc_disable(ts->ucb); + + input_set_abs_params(idev, ABS_X, 0, ts->x_res, 0, 0); + input_set_abs_params(idev, ABS_Y, 0, ts->y_res, 0, 0); + input_set_abs_params(idev, ABS_PRESSURE, 0, 0, 0, 0); + err = input_register_device(idev); if (err) goto fail; --- a/drivers/net/benet/be.h +++ b/drivers/net/benet/be.h @@ -165,6 +165,7 @@ struct be_drvr_stats { ulong be_tx_jiffies; u64 be_tx_bytes; u64 be_tx_bytes_prev; + u64 be_tx_pkts; u32 be_tx_rate; u32 cache_barrier[16]; @@ -176,6 +177,7 @@ struct be_drvr_stats { ulong be_rx_jiffies; u64 be_rx_bytes; u64 be_rx_bytes_prev; + u64 be_rx_pkts; u32 be_rx_rate; /* number of non ether type II frames dropped where * frame len > length field of Mac Hdr */ --- a/drivers/net/benet/be_main.c +++ b/drivers/net/benet/be_main.c @@ -146,13 +146,10 @@ void netdev_stats_update(struct be_adapt struct net_device_stats *dev_stats = &adapter->stats.net_stats; struct be_erx_stats *erx_stats = &hw_stats->erx; - dev_stats->rx_packets = port_stats->rx_total_frames; - dev_stats->tx_packets = port_stats->tx_unicastframes + - port_stats->tx_multicastframes + port_stats->tx_broadcastframes; - dev_stats->rx_bytes = (u64) port_stats->rx_bytes_msd << 32 | - (u64) port_stats->rx_bytes_lsd; - dev_stats->tx_bytes = (u64) port_stats->tx_bytes_msd << 32 | - (u64) port_stats->tx_bytes_lsd; + dev_stats->rx_packets = drvr_stats(adapter)->be_rx_pkts; + dev_stats->tx_packets = drvr_stats(adapter)->be_tx_pkts; + dev_stats->rx_bytes = drvr_stats(adapter)->be_rx_bytes; + dev_stats->tx_bytes = drvr_stats(adapter)->be_tx_bytes; /* bad pkts received */ dev_stats->rx_errors = port_stats->rx_crc_errors + @@ -309,12 +306,13 @@ static void be_tx_rate_update(struct be_ } static void be_tx_stats_update(struct be_adapter *adapter, - u32 wrb_cnt, u32 copied, bool stopped) + u32 wrb_cnt, u32 copied, u32 gso_segs, bool stopped) { struct be_drvr_stats *stats = drvr_stats(adapter); stats->be_tx_reqs++; stats->be_tx_wrbs += wrb_cnt; stats->be_tx_bytes += copied; + stats->be_tx_pkts += (gso_segs ? gso_segs : 1); if (stopped) stats->be_tx_stops++; } @@ -462,7 +460,8 @@ static netdev_tx_t be_xmit(struct sk_buf be_txq_notify(adapter, txq->id, wrb_cnt); - be_tx_stats_update(adapter, wrb_cnt, copied, stopped); + be_tx_stats_update(adapter, wrb_cnt, copied, + skb_shinfo(skb)->gso_segs, stopped); } else { txq->head = start; dev_kfree_skb_any(skb); @@ -605,6 +604,7 @@ static void be_rx_stats_update(struct be stats->be_rx_compl++; stats->be_rx_frags += numfrags; stats->be_rx_bytes += pktsize; + stats->be_rx_pkts++; } static inline bool do_pkt_csum(struct be_eth_rx_compl *rxcp, bool cso) --- a/drivers/net/bonding/bond_ipv6.c +++ b/drivers/net/bonding/bond_ipv6.c @@ -66,6 +66,13 @@ static void bond_na_send(struct net_devi }; struct sk_buff *skb; + /* The Ethernet header is built in ndisc_send_skb(), not + * ndisc_build_skb(), so we cannot insert a VLAN tag. Only an + * out-of-line tag inserted by the hardware will work. + */ + if (vlan_id && !(slave_dev->features & NETIF_F_HW_VLAN_TX)) + return; + icmp6h.icmp6_router = router; icmp6h.icmp6_solicited = 0; icmp6h.icmp6_override = 1; @@ -84,7 +91,7 @@ static void bond_na_send(struct net_devi } if (vlan_id) { - skb = vlan_put_tag(skb, vlan_id); + skb = __vlan_hwaccel_put_tag(skb, vlan_id); if (!skb) { pr_err(DRV_NAME ": failed to insert VLAN tag\n"); return; --- a/drivers/net/e1000e/netdev.c +++ b/drivers/net/e1000e/netdev.c @@ -5186,7 +5186,8 @@ static int __devinit e1000_probe(struct /* APME bit in EEPROM is mapped to WUC.APME */ eeprom_data = er32(WUC); eeprom_apme_mask = E1000_WUC_APME; - if (eeprom_data & E1000_WUC_PHY_WAKE) + if ((hw->mac.type > e1000_ich10lan) && + (eeprom_data & E1000_WUC_PHY_WAKE)) adapter->flags2 |= FLAG2_HAS_PHY_WAKEUP; } else if (adapter->flags & FLAG_APME_IN_CTRL3) { if (adapter->flags & FLAG_APME_CHECK_PORT_B && --- a/drivers/net/ixgbe/ixgbe_82599.c +++ b/drivers/net/ixgbe/ixgbe_82599.c @@ -338,6 +338,7 @@ static enum ixgbe_media_type ixgbe_get_m media_type = ixgbe_media_type_backplane; break; case IXGBE_DEV_ID_82599_SFP: + case IXGBE_DEV_ID_82599_SFP_EM: media_type = ixgbe_media_type_fiber; break; case IXGBE_DEV_ID_82599_CX4: --- a/drivers/net/ixgbe/ixgbe_main.c +++ b/drivers/net/ixgbe/ixgbe_main.c @@ -100,6 +100,8 @@ static struct pci_device_id ixgbe_pci_tb board_82599 }, {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_SFP), board_82599 }, + {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_SFP_EM), + board_82599 }, {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_KX4_MEZZ), board_82599 }, {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_CX4), @@ -791,6 +793,7 @@ static bool ixgbe_clean_rx_irq(struct ix break; (*work_done)++; + rmb(); /* read descriptor and rx_buffer_info after status DD */ if (rx_ring->flags & IXGBE_RING_RX_PS_ENABLED) { hdr_info = le16_to_cpu(ixgbe_get_hdr_info(rx_desc)); len = (hdr_info & IXGBE_RXDADV_HDRBUFLEN_MASK) >> --- a/drivers/net/ixgbe/ixgbe_type.h +++ b/drivers/net/ixgbe/ixgbe_type.h @@ -53,6 +53,7 @@ #define IXGBE_DEV_ID_82599_KR 0x1517 #define IXGBE_DEV_ID_82599_CX4 0x10F9 #define IXGBE_DEV_ID_82599_SFP 0x10FB +#define IXGBE_DEV_ID_82599_SFP_EM 0x1507 #define IXGBE_DEV_ID_82599_XAUI_LOM 0x10FC #define IXGBE_DEV_ID_82599_COMBO_BACKPLANE 0x10F8 --- a/drivers/net/netxen/netxen_nic_hw.c +++ b/drivers/net/netxen/netxen_nic_hw.c @@ -685,6 +685,9 @@ void netxen_p3_nic_set_multi(struct net_ struct list_head *head; nx_mac_list_t *cur; + if (adapter->is_up != NETXEN_ADAPTER_UP_MAGIC) + return; + list_splice_tail_init(&adapter->mac_list, &del_list); nx_p3_nic_add_mac(adapter, adapter->mac_addr, &del_list); --- a/drivers/net/r8169.c +++ b/drivers/net/r8169.c @@ -23,6 +23,7 @@ #include #include #include +#include #include #include @@ -3030,6 +3031,11 @@ rtl8169_init_one(struct pci_dev *pdev, c mii->reg_num_mask = 0x1f; mii->supports_gmii = !!(cfg->features & RTL_FEATURE_GMII); + /* disable ASPM completely as that cause random device stop working + * problems as well as full system hangs for some PCIe devices users */ + pci_disable_link_state(pdev, PCIE_LINK_STATE_L0S | PCIE_LINK_STATE_L1 | + PCIE_LINK_STATE_CLKPM); + /* enable device (incl. PCI PM wakeup and hotplug setup) */ rc = pci_enable_device(pdev); if (rc < 0) { --- a/drivers/net/wireless/ath/ath9k/ath9k.h +++ b/drivers/net/wireless/ath/ath9k/ath9k.h @@ -214,8 +214,8 @@ void ath_descdma_cleanup(struct ath_soft /* returns delimiter padding required given the packet length */ #define ATH_AGGR_GET_NDELIM(_len) \ - (((((_len) + ATH_AGGR_DELIM_SZ) < ATH_AGGR_MINPLEN) ? \ - (ATH_AGGR_MINPLEN - (_len) - ATH_AGGR_DELIM_SZ) : 0) >> 2) + (((_len) >= ATH_AGGR_MINPLEN) ? 0 : \ + DIV_ROUND_UP(ATH_AGGR_MINPLEN - (_len), ATH_AGGR_DELIM_SZ)) #define BAW_WITHIN(_start, _bawsz, _seqno) \ ((((_seqno) - (_start)) & 4095) < (_bawsz)) --- a/drivers/net/wireless/hostap/hostap_cs.c +++ b/drivers/net/wireless/hostap/hostap_cs.c @@ -662,12 +662,6 @@ static int prism2_config(struct pcmcia_d link->dev_node = &hw_priv->node; /* - * Make sure the IRQ handler cannot proceed until at least - * dev->base_addr is initialized. - */ - spin_lock_irqsave(&local->irq_init_lock, flags); - - /* * Allocate an interrupt line. Note that this does not assign a * handler to the interrupt, unless the 'Handler' member of the * irq structure is initialized. @@ -690,9 +684,10 @@ static int prism2_config(struct pcmcia_d CS_CHECK(RequestConfiguration, pcmcia_request_configuration(link, &link->conf)); + /* IRQ handler cannot proceed until at dev->base_addr is initialized */ + spin_lock_irqsave(&local->irq_init_lock, flags); dev->irq = link->irq.AssignedIRQ; dev->base_addr = link->io.BasePort1; - spin_unlock_irqrestore(&local->irq_init_lock, flags); /* Finally, report what we've done */ @@ -724,7 +719,6 @@ static int prism2_config(struct pcmcia_d return ret; cs_failed: - spin_unlock_irqrestore(&local->irq_init_lock, flags); cs_error(link, last_fn, last_ret); failed: --- a/drivers/net/wireless/iwlwifi/iwl-agn.c +++ b/drivers/net/wireless/iwlwifi/iwl-agn.c @@ -1044,6 +1044,9 @@ static void iwl_irq_tasklet_legacy(struc /* only Re-enable if diabled by irq */ if (test_bit(STATUS_INT_ENABLED, &priv->status)) iwl_enable_interrupts(priv); + /* Re-enable RF_KILL if it occurred */ + else if (handled & CSR_INT_BIT_RF_KILL) + iwl_enable_rfkill_int(priv); #ifdef CONFIG_IWLWIFI_DEBUG if (iwl_get_debug_level(priv) & (IWL_DL_ISR)) { @@ -1245,6 +1248,9 @@ static void iwl_irq_tasklet(struct iwl_p /* only Re-enable if diabled by irq */ if (test_bit(STATUS_INT_ENABLED, &priv->status)) iwl_enable_interrupts(priv); + /* Re-enable RF_KILL if it occurred */ + else if (handled & CSR_INT_BIT_RF_KILL) + iwl_enable_rfkill_int(priv); spin_unlock_irqrestore(&priv->lock, flags); @@ -2358,9 +2364,10 @@ static void iwl_mac_stop(struct ieee8021 flush_workqueue(priv->workqueue); - /* enable interrupts again in order to receive rfkill changes */ + /* User space software may expect getting rfkill changes + * even if interface is down */ iwl_write32(priv, CSR_INT, 0xFFFFFFFF); - iwl_enable_interrupts(priv); + iwl_enable_rfkill_int(priv); IWL_DEBUG_MAC80211(priv, "leave\n"); } @@ -3060,14 +3067,14 @@ static int iwl_pci_probe(struct pci_dev * 8. Setup and register mac80211 **********************************/ - /* enable interrupts if needed: hw bug w/a */ + /* enable rfkill interrupt: hw bug w/a */ pci_read_config_word(priv->pci_dev, PCI_COMMAND, &pci_cmd); if (pci_cmd & PCI_COMMAND_INTX_DISABLE) { pci_cmd &= ~PCI_COMMAND_INTX_DISABLE; pci_write_config_word(priv->pci_dev, PCI_COMMAND, pci_cmd); } - iwl_enable_interrupts(priv); + iwl_enable_rfkill_int(priv); err = iwl_setup_mac(priv); if (err) --- a/drivers/net/wireless/iwlwifi/iwl-helpers.h +++ b/drivers/net/wireless/iwlwifi/iwl-helpers.h @@ -160,6 +160,12 @@ static inline void iwl_disable_interrupt IWL_DEBUG_ISR(priv, "Disabled interrupts\n"); } +static inline void iwl_enable_rfkill_int(struct iwl_priv *priv) +{ + IWL_DEBUG_ISR(priv, "Enabling rfkill interrupt\n"); + iwl_write32(priv, CSR_INT_MASK, CSR_INT_BIT_RF_KILL); +} + static inline void iwl_enable_interrupts(struct iwl_priv *priv) { IWL_DEBUG_ISR(priv, "Enabling interrupts\n"); --- a/drivers/net/wireless/p54/p54pci.c +++ b/drivers/net/wireless/p54/p54pci.c @@ -198,6 +198,7 @@ static void p54p_check_rx_ring(struct ie while (i != idx) { u16 len; struct sk_buff *skb; + dma_addr_t dma_addr; desc = &ring[i]; len = le16_to_cpu(desc->len); skb = rx_buf[i]; @@ -215,17 +216,20 @@ static void p54p_check_rx_ring(struct ie len = priv->common.rx_mtu; } + dma_addr = le32_to_cpu(desc->host_addr); + pci_dma_sync_single_for_cpu(priv->pdev, dma_addr, + priv->common.rx_mtu + 32, PCI_DMA_FROMDEVICE); skb_put(skb, len); if (p54_rx(dev, skb)) { - pci_unmap_single(priv->pdev, - le32_to_cpu(desc->host_addr), - priv->common.rx_mtu + 32, - PCI_DMA_FROMDEVICE); + pci_unmap_single(priv->pdev, dma_addr, + priv->common.rx_mtu + 32, PCI_DMA_FROMDEVICE); rx_buf[i] = NULL; - desc->host_addr = 0; + desc->host_addr = cpu_to_le32(0); } else { skb_trim(skb, 0); + pci_dma_sync_single_for_device(priv->pdev, dma_addr, + priv->common.rx_mtu + 32, PCI_DMA_FROMDEVICE); desc->len = cpu_to_le16(priv->common.rx_mtu + 32); } --- a/drivers/net/wireless/p54/p54usb.c +++ b/drivers/net/wireless/p54/p54usb.c @@ -95,6 +95,7 @@ static struct usb_device_id p54u_table[] {USB_DEVICE(0x1413, 0x5400)}, /* Telsey 802.11g USB2.0 Adapter */ {USB_DEVICE(0x1435, 0x0427)}, /* Inventel UR054G */ {USB_DEVICE(0x1668, 0x1050)}, /* Actiontec 802UIG-1 */ + {USB_DEVICE(0x1740, 0x1000)}, /* Senao NUB-350 */ {USB_DEVICE(0x2001, 0x3704)}, /* DLink DWL-G122 rev A2 */ {USB_DEVICE(0x2001, 0x3705)}, /* D-Link DWL-G120 rev C1 */ {USB_DEVICE(0x413c, 0x5513)}, /* Dell WLA3310 USB Wireless Adapter */ --- a/drivers/net/wireless/p54/txrx.c +++ b/drivers/net/wireless/p54/txrx.c @@ -617,7 +617,7 @@ static void p54_tx_80211_header(struct p else *burst_possible = false; - if (info->flags & IEEE80211_TX_CTL_ASSIGN_SEQ) + if (!(info->flags & IEEE80211_TX_CTL_ASSIGN_SEQ)) *flags |= P54_HDR_FLAG_DATA_OUT_SEQNR; if (info->flags & IEEE80211_TX_CTL_PSPOLL_RESPONSE) --- a/drivers/net/wireless/rt2x00/rt73usb.c +++ b/drivers/net/wireless/rt2x00/rt73usb.c @@ -2400,6 +2400,7 @@ static struct usb_device_id rt73usb_devi { USB_DEVICE(0x04bb, 0x093d), USB_DEVICE_DATA(&rt73usb_ops) }, { USB_DEVICE(0x148f, 0x2573), USB_DEVICE_DATA(&rt73usb_ops) }, { USB_DEVICE(0x148f, 0x2671), USB_DEVICE_DATA(&rt73usb_ops) }, + { USB_DEVICE(0x0812, 0x3101), USB_DEVICE_DATA(&rt73usb_ops) }, /* Qcom */ { USB_DEVICE(0x18e8, 0x6196), USB_DEVICE_DATA(&rt73usb_ops) }, { USB_DEVICE(0x18e8, 0x6229), USB_DEVICE_DATA(&rt73usb_ops) }, --- a/drivers/pci/pci-stub.c +++ b/drivers/pci/pci-stub.c @@ -54,6 +54,9 @@ static int __init pci_stub_init(void) subdevice = PCI_ANY_ID, class=0, class_mask=0; int fields; + if (!strlen(id)) + continue; + fields = sscanf(id, "%x:%x:%x:%x:%x:%x", &vendor, &device, &subvendor, &subdevice, &class, &class_mask); --- a/drivers/platform/x86/acer-wmi.c +++ b/drivers/platform/x86/acer-wmi.c @@ -90,7 +90,7 @@ struct acer_quirks { */ #define AMW0_GUID1 "67C3371D-95A3-4C37-BB61-DD47B491DAAB" #define AMW0_GUID2 "431F16ED-0C2B-444C-B267-27DEB140CF9C" -#define WMID_GUID1 "6AF4F258-B401-42fd-BE91-3D4AC2D7C0D3" +#define WMID_GUID1 "6AF4F258-B401-42FD-BE91-3D4AC2D7C0D3" #define WMID_GUID2 "95764E09-FB56-4e83-B31A-37761F60994A" MODULE_ALIAS("wmi:67C3371D-95A3-4C37-BB61-DD47B491DAAB"); @@ -1065,7 +1065,7 @@ static ssize_t set_bool_threeg(struct de return -EINVAL; return count; } -static DEVICE_ATTR(threeg, S_IWUGO | S_IRUGO | S_IWUSR, show_bool_threeg, +static DEVICE_ATTR(threeg, S_IRUGO | S_IWUSR, show_bool_threeg, set_bool_threeg); static ssize_t show_interface(struct device *dev, struct device_attribute *attr, --- a/drivers/platform/x86/asus_acpi.c +++ b/drivers/platform/x86/asus_acpi.c @@ -1001,14 +1001,8 @@ static int asus_hotk_add_fs(struct acpi_ struct proc_dir_entry *proc; mode_t mode; - /* - * If parameter uid or gid is not changed, keep the default setting for - * our proc entries (-rw-rw-rw-) else, it means we care about security, - * and then set to -rw-rw---- - */ - if ((asus_uid == 0) && (asus_gid == 0)) { - mode = S_IFREG | S_IRUGO | S_IWUGO; + mode = S_IFREG | S_IRUGO | S_IWUSR | S_IWGRP; } else { mode = S_IFREG | S_IRUSR | S_IRGRP | S_IWUSR | S_IWGRP; printk(KERN_WARNING " asus_uid and asus_gid parameters are " --- a/drivers/platform/x86/tc1100-wmi.c +++ b/drivers/platform/x86/tc1100-wmi.c @@ -177,7 +177,7 @@ set_bool_##value(struct device *dev, str return -EINVAL; \ return count; \ } \ -static DEVICE_ATTR(value, S_IWUGO | S_IRUGO | S_IWUSR, \ +static DEVICE_ATTR(value, S_IRUGO | S_IWUSR, \ show_bool_##value, set_bool_##value); show_set_bool(wireless, TC1100_INSTANCE_WIRELESS); --- a/drivers/power/ds2760_battery.c +++ b/drivers/power/ds2760_battery.c @@ -211,7 +211,7 @@ static int ds2760_battery_read_status(st if (di->rem_capacity > 100) di->rem_capacity = 100; - if (di->current_uA >= 100L) + if (di->current_uA < -100L) di->life_sec = -((di->accum_current_uAh - di->empty_uAh) * 36L) / (di->current_uA / 100L); else --- a/drivers/rtc/rtc-cmos.c +++ b/drivers/rtc/rtc-cmos.c @@ -36,6 +36,7 @@ #include #include #include +#include /* this is for "generic access to PC-style RTC" using CMOS_READ/CMOS_WRITE */ #include @@ -855,7 +856,7 @@ static void __exit cmos_do_remove(struct #ifdef CONFIG_PM -static int cmos_suspend(struct device *dev, pm_message_t mesg) +static int cmos_suspend(struct device *dev) { struct cmos_rtc *cmos = dev_get_drvdata(dev); unsigned char tmp; @@ -902,7 +903,7 @@ static int cmos_suspend(struct device *d */ static inline int cmos_poweroff(struct device *dev) { - return cmos_suspend(dev, PMSG_HIBERNATE); + return cmos_suspend(dev); } static int cmos_resume(struct device *dev) @@ -949,9 +950,9 @@ static int cmos_resume(struct device *de return 0; } +static SIMPLE_DEV_PM_OPS(cmos_pm_ops, cmos_suspend, cmos_resume); + #else -#define cmos_suspend NULL -#define cmos_resume NULL static inline int cmos_poweroff(struct device *dev) { @@ -1087,7 +1088,7 @@ static void __exit cmos_pnp_remove(struc static int cmos_pnp_suspend(struct pnp_dev *pnp, pm_message_t mesg) { - return cmos_suspend(&pnp->dev, mesg); + return cmos_suspend(&pnp->dev); } static int cmos_pnp_resume(struct pnp_dev *pnp) @@ -1167,8 +1168,9 @@ static struct platform_driver cmos_platf .shutdown = cmos_platform_shutdown, .driver = { .name = (char *) driver_name, - .suspend = cmos_suspend, - .resume = cmos_resume, +#ifdef CONFIG_PM + .pm = &cmos_pm_ops, +#endif } }; --- a/drivers/scsi/device_handler/scsi_dh_alua.c +++ b/drivers/scsi/device_handler/scsi_dh_alua.c @@ -701,6 +701,8 @@ static const struct scsi_dh_devlist alua {"IBM", "2145" }, {"Pillar", "Axiom" }, {"Intel", "Multi-Flex"}, + {"NETAPP", "LUN"}, + {"AIX", "NVDISK"}, {NULL, NULL} }; --- a/drivers/scsi/libsas/sas_scsi_host.c +++ b/drivers/scsi/libsas/sas_scsi_host.c @@ -648,6 +648,7 @@ void sas_scsi_recover_host(struct Scsi_H spin_lock_irqsave(shost->host_lock, flags); list_splice_init(&shost->eh_cmd_q, &eh_work_q); + shost->host_eh_scheduled = 0; spin_unlock_irqrestore(shost->host_lock, flags); SAS_DPRINTK("Enter %s\n", __func__); --- a/drivers/scsi/mpt2sas/mpt2sas_base.c +++ b/drivers/scsi/mpt2sas/mpt2sas_base.c @@ -1947,9 +1947,9 @@ _base_allocate_memory_pools(struct MPT2S /* adjust hba_queue_depth, reply_free_queue_depth, * and queue_size */ - ioc->hba_queue_depth -= queue_diff; - ioc->reply_free_queue_depth -= queue_diff; - queue_size -= queue_diff; + ioc->hba_queue_depth -= (queue_diff / 2); + ioc->reply_free_queue_depth -= (queue_diff / 2); + queue_size = facts->MaxReplyDescriptorPostQueueDepth; } ioc->reply_post_queue_depth = queue_size; @@ -3595,6 +3595,8 @@ mpt2sas_base_detach(struct MPT2SAS_ADAPT static void _base_reset_handler(struct MPT2SAS_ADAPTER *ioc, int reset_phase) { + mpt2sas_scsih_reset_handler(ioc, reset_phase); + mpt2sas_ctl_reset_handler(ioc, reset_phase); switch (reset_phase) { case MPT2_IOC_PRE_RESET: dtmprintk(ioc, printk(MPT2SAS_DEBUG_FMT "%s: " @@ -3625,8 +3627,6 @@ _base_reset_handler(struct MPT2SAS_ADAPT "MPT2_IOC_DONE_RESET\n", ioc->name, __func__)); break; } - mpt2sas_scsih_reset_handler(ioc, reset_phase); - mpt2sas_ctl_reset_handler(ioc, reset_phase); } /** @@ -3680,6 +3680,7 @@ mpt2sas_base_hard_reset_handler(struct M { int r; unsigned long flags; + u8 pe_complete = ioc->wait_for_port_enable_to_complete; dtmprintk(ioc, printk(MPT2SAS_DEBUG_FMT "%s: enter\n", ioc->name, __func__)); @@ -3701,6 +3702,14 @@ mpt2sas_base_hard_reset_handler(struct M if (r) goto out; _base_reset_handler(ioc, MPT2_IOC_AFTER_RESET); + + /* If this hard reset is called while port enable is active, then + * there is no reason to call make_ioc_operational + */ + if (pe_complete) { + r = -EFAULT; + goto out; + } r = _base_make_ioc_operational(ioc, sleep_flag); if (!r) _base_reset_handler(ioc, MPT2_IOC_DONE_RESET); --- a/drivers/scsi/mpt2sas/mpt2sas_scsih.c +++ b/drivers/scsi/mpt2sas/mpt2sas_scsih.c @@ -2585,9 +2585,6 @@ _scsih_check_topo_delete_events(struct M u16 handle; for (i = 0 ; i < event_data->NumEntries; i++) { - if (event_data->PHY[i].PhyStatus & - MPI2_EVENT_SAS_TOPO_PHYSTATUS_VACANT) - continue; handle = le16_to_cpu(event_data->PHY[i].AttachedDevHandle); if (!handle) continue; --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -1040,6 +1040,12 @@ static unsigned int sd_completed_bytes(s u64 end_lba = blk_rq_pos(scmd->request) + (scsi_bufflen(scmd) / 512); u64 bad_lba; int info_valid; + /* + * resid is optional but mostly filled in. When it's unused, + * its value is zero, so we assume the whole buffer transferred + */ + unsigned int transferred = scsi_bufflen(scmd) - scsi_get_resid(scmd); + unsigned int good_bytes; if (!blk_fs_request(scmd->request)) return 0; @@ -1073,7 +1079,8 @@ static unsigned int sd_completed_bytes(s /* This computation should always be done in terms of * the resolution of the device's medium. */ - return (bad_lba - start_lba) * scmd->device->sector_size; + good_bytes = (bad_lba - start_lba) * scmd->device->sector_size; + return min(good_bytes, transferred); } /** --- a/drivers/serial/8250.c +++ b/drivers/serial/8250.c @@ -255,7 +255,8 @@ static const struct serial8250_config ua .fifo_size = 128, .tx_loadsz = 128, .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_10, - .flags = UART_CAP_FIFO | UART_CAP_EFR | UART_CAP_SLEEP, + /* UART_CAP_EFR breaks billionon CF bluetooth card. */ + .flags = UART_CAP_FIFO | UART_CAP_SLEEP, }, [PORT_RSA] = { .name = "RSA", --- a/drivers/staging/comedi/drivers/jr3_pci.c +++ b/drivers/staging/comedi/drivers/jr3_pci.c @@ -52,6 +52,7 @@ Devices: [JR3] PCI force sensor board (j #define PCI_VENDOR_ID_JR3 0x1762 #define PCI_DEVICE_ID_JR3_1_CHANNEL 0x3111 +#define PCI_DEVICE_ID_JR3_1_CHANNEL_NEW 0x1111 #define PCI_DEVICE_ID_JR3_2_CHANNEL 0x3112 #define PCI_DEVICE_ID_JR3_3_CHANNEL 0x3113 #define PCI_DEVICE_ID_JR3_4_CHANNEL 0x3114 @@ -71,6 +72,8 @@ static DEFINE_PCI_DEVICE_TABLE(jr3_pci_p { PCI_VENDOR_ID_JR3, PCI_DEVICE_ID_JR3_1_CHANNEL, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0}, { + PCI_VENDOR_ID_JR3, PCI_DEVICE_ID_JR3_1_CHANNEL_NEW, + PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0}, { PCI_VENDOR_ID_JR3, PCI_DEVICE_ID_JR3_2_CHANNEL, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0}, { PCI_VENDOR_ID_JR3, PCI_DEVICE_ID_JR3_3_CHANNEL, @@ -807,6 +810,10 @@ static int jr3_pci_attach(struct comedi_ devpriv->n_channels = 1; } break; + case PCI_DEVICE_ID_JR3_1_CHANNEL_NEW:{ + devpriv->n_channels = 1; + } + break; case PCI_DEVICE_ID_JR3_2_CHANNEL:{ devpriv->n_channels = 2; } --- a/drivers/staging/comedi/drivers/ni_labpc.c +++ b/drivers/staging/comedi/drivers/ni_labpc.c @@ -528,7 +528,8 @@ int labpc_common_attach(struct comedi_de /* grab our IRQ */ if (irq) { isr_flags = 0; - if (thisboard->bustype == pci_bustype) + if (thisboard->bustype == pci_bustype + || thisboard->bustype == pcmcia_bustype) isr_flags |= IRQF_SHARED; if (request_irq(irq, labpc_interrupt, isr_flags, driver_labpc.driver_name, dev)) { --- a/drivers/staging/hv/blkvsc_drv.c +++ b/drivers/staging/hv/blkvsc_drv.c @@ -378,6 +378,7 @@ static int blkvsc_probe(struct device *d blkdev->gd->first_minor = 0; blkdev->gd->fops = &block_ops; blkdev->gd->private_data = blkdev; + blkdev->gd->driverfs_dev = &(blkdev->device_ctx->device); sprintf(blkdev->gd->disk_name, "hd%c", 'a' + devnum); blkvsc_do_inquiry(blkdev); --- a/drivers/staging/hv/netvsc_drv.c +++ b/drivers/staging/hv/netvsc_drv.c @@ -296,6 +296,7 @@ static void netvsc_linkstatus_callback(s if (status == 1) { netif_carrier_on(net); netif_wake_queue(net); + netif_notify_peers(net); } else { netif_carrier_off(net); netif_stop_queue(net); --- a/drivers/staging/usbip/vhci.h +++ b/drivers/staging/usbip/vhci.h @@ -100,9 +100,6 @@ struct vhci_hcd { * But, the index of this array begins from 0. */ struct vhci_device vdev[VHCI_NPORTS]; - - /* vhci_device which has not been assiged its address yet */ - int pending_port; }; @@ -119,6 +116,9 @@ void rh_port_disconnect(int rhport); void vhci_rx_loop(struct usbip_task *ut); void vhci_tx_loop(struct usbip_task *ut); +struct urb *pickup_urb_and_free_priv(struct vhci_device *vdev, + __u32 seqnum); + #define hardware (&the_controller->pdev.dev) static inline struct vhci_device *port_to_vdev(__u32 port) --- a/drivers/staging/usbip/vhci_hcd.c +++ b/drivers/staging/usbip/vhci_hcd.c @@ -137,8 +137,6 @@ void rh_port_connect(int rhport, enum us * the_controller->vdev[rhport].ud.status = VDEV_CONNECT; * spin_unlock(&the_controller->vdev[rhport].ud.lock); */ - the_controller->pending_port = rhport; - spin_unlock_irqrestore(&the_controller->lock, flags); usb_hcd_poll_rh_status(vhci_to_hcd(the_controller)); @@ -558,6 +556,7 @@ static int vhci_urb_enqueue(struct usb_h struct device *dev = &urb->dev->dev; int ret = 0; unsigned long flags; + struct vhci_device *vdev; usbip_dbg_vhci_hc("enter, usb_hcd %p urb %p mem_flags %d\n", hcd, urb, mem_flags); @@ -573,6 +572,18 @@ static int vhci_urb_enqueue(struct usb_h return urb->status; } + vdev = port_to_vdev(urb->dev->portnum-1); + + /* refuse enqueue for dead connection */ + spin_lock(&vdev->ud.lock); + if (vdev->ud.status == VDEV_ST_NULL || vdev->ud.status == VDEV_ST_ERROR) { + usbip_uerr("enqueue for inactive port %d\n", vdev->rhport); + spin_unlock(&vdev->ud.lock); + spin_unlock_irqrestore(&the_controller->lock, flags); + return -ENODEV; + } + spin_unlock(&vdev->ud.lock); + ret = usb_hcd_link_urb_to_ep(hcd, urb); if (ret) goto no_need_unlink; @@ -591,8 +602,6 @@ static int vhci_urb_enqueue(struct usb_h __u8 type = usb_pipetype(urb->pipe); struct usb_ctrlrequest *ctrlreq = (struct usb_ctrlrequest *) urb->setup_packet; - struct vhci_device *vdev = - port_to_vdev(the_controller->pending_port); if (type != PIPE_CONTROL || !ctrlreq) { dev_err(dev, "invalid request to devnum 0\n"); @@ -606,7 +615,9 @@ static int vhci_urb_enqueue(struct usb_h dev_info(dev, "SetAddress Request (%d) to port %d\n", ctrlreq->wValue, vdev->rhport); - vdev->udev = urb->dev; + if (vdev->udev) + usb_put_dev(vdev->udev); + vdev->udev = usb_get_dev(urb->dev); spin_lock(&vdev->ud.lock); vdev->ud.status = VDEV_ST_USED; @@ -626,8 +637,9 @@ static int vhci_urb_enqueue(struct usb_h "Get_Descriptor to device 0 " "(get max pipe size)\n"); - /* FIXME: reference count? (usb_get_dev()) */ - vdev->udev = urb->dev; + if (vdev->udev) + usb_put_dev(vdev->udev); + vdev->udev = usb_get_dev(urb->dev); goto out; default: @@ -798,27 +810,12 @@ static int vhci_urb_dequeue(struct usb_h spin_unlock_irqrestore(&vdev->priv_lock, flags2); } - - if (!vdev->ud.tcp_socket) { - /* tcp connection is closed */ - usbip_uinfo("vhci_hcd: vhci_urb_dequeue() gives back urb %p\n", - urb); - - usb_hcd_unlink_urb_from_ep(hcd, urb); - - spin_unlock_irqrestore(&the_controller->lock, flags); - usb_hcd_giveback_urb(vhci_to_hcd(the_controller), urb, - urb->status); - spin_lock_irqsave(&the_controller->lock, flags); - } - spin_unlock_irqrestore(&the_controller->lock, flags); usbip_dbg_vhci_hc("leave\n"); return 0; } - static void vhci_device_unlink_cleanup(struct vhci_device *vdev) { struct vhci_unlink *unlink, *tmp; @@ -826,11 +823,34 @@ static void vhci_device_unlink_cleanup(s spin_lock(&vdev->priv_lock); list_for_each_entry_safe(unlink, tmp, &vdev->unlink_tx, list) { + usbip_uinfo("unlink cleanup tx %lu\n", unlink->unlink_seqnum); list_del(&unlink->list); kfree(unlink); } list_for_each_entry_safe(unlink, tmp, &vdev->unlink_rx, list) { + struct urb *urb; + + /* give back URB of unanswered unlink request */ + usbip_uinfo("unlink cleanup rx %lu\n", unlink->unlink_seqnum); + + urb = pickup_urb_and_free_priv(vdev, unlink->unlink_seqnum); + if (!urb) { + usbip_uinfo("the urb (seqnum %lu) was already given back\n", + unlink->unlink_seqnum); + list_del(&unlink->list); + kfree(unlink); + continue; + } + + urb->status = -ENODEV; + + spin_lock(&the_controller->lock); + usb_hcd_unlink_urb_from_ep(vhci_to_hcd(the_controller), urb); + spin_unlock(&the_controller->lock); + + usb_hcd_giveback_urb(vhci_to_hcd(the_controller), urb, urb->status); + list_del(&unlink->list); kfree(unlink); } @@ -900,6 +920,10 @@ static void vhci_device_reset(struct usb vdev->speed = 0; vdev->devid = 0; + if (vdev->udev) + usb_put_dev(vdev->udev); + vdev->udev = NULL; + ud->tcp_socket = NULL; ud->status = VDEV_ST_NULL; --- a/drivers/staging/usbip/vhci_rx.c +++ b/drivers/staging/usbip/vhci_rx.c @@ -21,16 +21,14 @@ #include "vhci.h" -/* get URB from transmitted urb queue */ -static struct urb *pickup_urb_and_free_priv(struct vhci_device *vdev, +/* get URB from transmitted urb queue. caller must hold vdev->priv_lock */ +struct urb *pickup_urb_and_free_priv(struct vhci_device *vdev, __u32 seqnum) { struct vhci_priv *priv, *tmp; struct urb *urb = NULL; int status; - spin_lock(&vdev->priv_lock); - list_for_each_entry_safe(priv, tmp, &vdev->priv_rx, list) { if (priv->seqnum == seqnum) { urb = priv->urb; @@ -61,8 +59,6 @@ static struct urb *pickup_urb_and_free_p } } - spin_unlock(&vdev->priv_lock); - return urb; } @@ -72,9 +68,11 @@ static void vhci_recv_ret_submit(struct struct usbip_device *ud = &vdev->ud; struct urb *urb; + spin_lock(&vdev->priv_lock); urb = pickup_urb_and_free_priv(vdev, pdu->base.seqnum); + spin_unlock(&vdev->priv_lock); if (!urb) { usbip_uerr("cannot find a urb of seqnum %u\n", @@ -159,7 +157,12 @@ static void vhci_recv_ret_unlink(struct return; } + spin_lock(&vdev->priv_lock); + urb = pickup_urb_and_free_priv(vdev, unlink->unlink_seqnum); + + spin_unlock(&vdev->priv_lock); + if (!urb) { /* * I get the result of a unlink request. But, it seems that I --- a/drivers/usb/class/cdc-acm.c +++ b/drivers/usb/class/cdc-acm.c @@ -1596,6 +1596,7 @@ static struct usb_device_id acm_ids[] = { NOKIA_PCSUITE_ACM_INFO(0x0154), }, /* Nokia 5800 XpressMusic */ { NOKIA_PCSUITE_ACM_INFO(0x04ce), }, /* Nokia E90 */ { NOKIA_PCSUITE_ACM_INFO(0x01d4), }, /* Nokia E55 */ + { NOKIA_PCSUITE_ACM_INFO(0x0302), }, /* Nokia N8 */ { SAMSUNG_PCSUITE_ACM_INFO(0x6651), }, /* Samsung GTi8510 (INNOV8) */ /* NOTE: non-Nokia COMM/ACM/0xff is likely MSFT RNDIS... NOT a modem! */ --- a/drivers/usb/core/hcd-pci.c +++ b/drivers/usb/core/hcd-pci.c @@ -197,8 +197,10 @@ void usb_hcd_pci_shutdown(struct pci_dev if (!hcd) return; - if (hcd->driver->shutdown) + if (hcd->driver->shutdown) { hcd->driver->shutdown(hcd); + pci_disable_device(dev); + } } EXPORT_SYMBOL_GPL(usb_hcd_pci_shutdown); --- a/drivers/usb/core/hub.c +++ b/drivers/usb/core/hub.c @@ -648,6 +648,8 @@ static void hub_init_func3(struct work_s static void hub_activate(struct usb_hub *hub, enum hub_activation_type type) { struct usb_device *hdev = hub->hdev; + struct usb_hcd *hcd; + int ret; int port1; int status; bool need_debounce_delay = false; @@ -686,6 +688,25 @@ static void hub_activate(struct usb_hub atomic_set(&to_usb_interface(hub->intfdev)-> pm_usage_cnt, 1); return; /* Continues at init2: below */ + } else if (type == HUB_RESET_RESUME) { + /* The internal host controller state for the hub device + * may be gone after a host power loss on system resume. + * Update the device's info so the HW knows it's a hub. + */ + hcd = bus_to_hcd(hdev->bus); + if (hcd->driver->update_hub_device) { + ret = hcd->driver->update_hub_device(hcd, hdev, + &hub->tt, GFP_NOIO); + if (ret < 0) { + dev_err(hub->intfdev, "Host not " + "accepting hub info " + "update.\n"); + dev_err(hub->intfdev, "LS/FS devices " + "and hubs may not work " + "under this hub\n."); + } + } + hub_power_on(hub, true); } else { hub_power_on(hub, true); } @@ -2683,6 +2704,11 @@ hub_port_init (struct usb_hub *hub, stru udev->ttport = hdev->ttport; } else if (udev->speed != USB_SPEED_HIGH && hdev->speed == USB_SPEED_HIGH) { + if (!hub->tt.hub) { + dev_err(&udev->dev, "parent hub has no TT\n"); + retval = -EINVAL; + goto fail; + } udev->tt = &hub->tt; udev->ttport = port1; } --- a/drivers/usb/core/quirks.c +++ b/drivers/usb/core/quirks.c @@ -48,6 +48,10 @@ static const struct usb_device_id usb_qu { USB_DEVICE(0x04b4, 0x0526), .driver_info = USB_QUIRK_CONFIG_INTF_STRINGS }, + /* Samsung Android phone modem - ID conflict with SPH-I500 */ + { USB_DEVICE(0x04e8, 0x6601), .driver_info = + USB_QUIRK_CONFIG_INTF_STRINGS }, + /* Roland SC-8820 */ { USB_DEVICE(0x0582, 0x0007), .driver_info = USB_QUIRK_RESET_RESUME }, @@ -68,6 +72,10 @@ static const struct usb_device_id usb_qu /* M-Systems Flash Disk Pioneers */ { USB_DEVICE(0x08ec, 0x1000), .driver_info = USB_QUIRK_RESET_RESUME }, + /* Keytouch QWERTY Panel keyboard */ + { USB_DEVICE(0x0926, 0x3333), .driver_info = + USB_QUIRK_CONFIG_INTF_STRINGS }, + /* X-Rite/Gretag-Macbeth Eye-One Pro display colorimeter */ { USB_DEVICE(0x0971, 0x2000), .driver_info = USB_QUIRK_NO_SET_INTF }, --- a/drivers/usb/gadget/printer.c +++ b/drivers/usb/gadget/printer.c @@ -130,31 +130,31 @@ static struct printer_dev usb_printer_ga * parameters are in UTF-8 (superset of ASCII's 7 bit characters). */ -static ushort __initdata idVendor; +static ushort idVendor; module_param(idVendor, ushort, S_IRUGO); MODULE_PARM_DESC(idVendor, "USB Vendor ID"); -static ushort __initdata idProduct; +static ushort idProduct; module_param(idProduct, ushort, S_IRUGO); MODULE_PARM_DESC(idProduct, "USB Product ID"); -static ushort __initdata bcdDevice; +static ushort bcdDevice; module_param(bcdDevice, ushort, S_IRUGO); MODULE_PARM_DESC(bcdDevice, "USB Device version (BCD)"); -static char *__initdata iManufacturer; +static char *iManufacturer; module_param(iManufacturer, charp, S_IRUGO); MODULE_PARM_DESC(iManufacturer, "USB Manufacturer string"); -static char *__initdata iProduct; +static char *iProduct; module_param(iProduct, charp, S_IRUGO); MODULE_PARM_DESC(iProduct, "USB Product string"); -static char *__initdata iSerialNum; +static char *iSerialNum; module_param(iSerialNum, charp, S_IRUGO); MODULE_PARM_DESC(iSerialNum, "1"); -static char *__initdata iPNPstring; +static char *iPNPstring; module_param(iPNPstring, charp, S_IRUGO); MODULE_PARM_DESC(iPNPstring, "MFG:linux;MDL:g_printer;CLS:PRINTER;SN:1;"); --- a/drivers/usb/host/ehci-hcd.c +++ b/drivers/usb/host/ehci-hcd.c @@ -103,6 +103,9 @@ MODULE_PARM_DESC (ignore_oc, "ignore bog #define INTR_MASK (STS_IAA | STS_FATAL | STS_PCD | STS_ERR | STS_INT) +/* for ASPM quirk of ISOC on AMD SB800 */ +static struct pci_dev *amd_nb_dev; + /*-------------------------------------------------------------------------*/ #include "ehci.h" @@ -502,6 +505,11 @@ static void ehci_stop (struct usb_hcd *h spin_unlock_irq (&ehci->lock); ehci_mem_cleanup (ehci); + if (amd_nb_dev) { + pci_dev_put(amd_nb_dev); + amd_nb_dev = NULL; + } + #ifdef EHCI_STATS ehci_dbg (ehci, "irq normal %ld err %ld reclaim %ld (lost %ld)\n", ehci->stats.normal, ehci->stats.error, ehci->stats.reclaim, @@ -537,6 +545,8 @@ static int ehci_init(struct usb_hcd *hcd ehci->iaa_watchdog.function = ehci_iaa_watchdog; ehci->iaa_watchdog.data = (unsigned long) ehci; + hcc_params = ehci_readl(ehci, &ehci->caps->hcc_params); + /* * hw default: 1K periodic list heads, one per frame. * periodic_size can shrink by USBCMD update if hcc_params allows. @@ -544,11 +554,20 @@ static int ehci_init(struct usb_hcd *hcd ehci->periodic_size = DEFAULT_I_TDPS; INIT_LIST_HEAD(&ehci->cached_itd_list); INIT_LIST_HEAD(&ehci->cached_sitd_list); + + if (HCC_PGM_FRAMELISTLEN(hcc_params)) { + /* periodic schedule size can be smaller than default */ + switch (EHCI_TUNE_FLS) { + case 0: ehci->periodic_size = 1024; break; + case 1: ehci->periodic_size = 512; break; + case 2: ehci->periodic_size = 256; break; + default: BUG(); + } + } if ((retval = ehci_mem_init(ehci, GFP_KERNEL)) < 0) return retval; /* controllers may cache some of the periodic schedule ... */ - hcc_params = ehci_readl(ehci, &ehci->caps->hcc_params); if (HCC_ISOC_CACHE(hcc_params)) // full frame cache ehci->i_thresh = 8; else // N microframes cached @@ -597,12 +616,6 @@ static int ehci_init(struct usb_hcd *hcd /* periodic schedule size can be smaller than default */ temp &= ~(3 << 2); temp |= (EHCI_TUNE_FLS << 2); - switch (EHCI_TUNE_FLS) { - case 0: ehci->periodic_size = 1024; break; - case 1: ehci->periodic_size = 512; break; - case 2: ehci->periodic_size = 256; break; - default: BUG(); - } } ehci->command = temp; --- a/drivers/usb/host/ehci-pci.c +++ b/drivers/usb/host/ehci-pci.c @@ -41,6 +41,42 @@ static int ehci_pci_reinit(struct ehci_h return 0; } +static int ehci_quirk_amd_hudson(struct ehci_hcd *ehci) +{ + struct pci_dev *amd_smbus_dev; + u8 rev = 0; + + amd_smbus_dev = pci_get_device(PCI_VENDOR_ID_ATI, 0x4385, NULL); + if (amd_smbus_dev) { + pci_read_config_byte(amd_smbus_dev, PCI_REVISION_ID, &rev); + if (rev < 0x40) { + pci_dev_put(amd_smbus_dev); + amd_smbus_dev = NULL; + return 0; + } + } else { + amd_smbus_dev = pci_get_device(PCI_VENDOR_ID_AMD, 0x780b, NULL); + if (!amd_smbus_dev) + return 0; + pci_read_config_byte(amd_smbus_dev, PCI_REVISION_ID, &rev); + if (rev < 0x11 || rev > 0x18) { + pci_dev_put(amd_smbus_dev); + amd_smbus_dev = NULL; + return 0; + } + } + + if (!amd_nb_dev) + amd_nb_dev = pci_get_device(PCI_VENDOR_ID_AMD, 0x1510, NULL); + + ehci_info(ehci, "QUIRK: Enable exception for AMD Hudson ASPM\n"); + + pci_dev_put(amd_smbus_dev); + amd_smbus_dev = NULL; + + return 1; +} + /* called during probe() after chip reset completes */ static int ehci_pci_setup(struct usb_hcd *hcd) { @@ -99,6 +135,9 @@ static int ehci_pci_setup(struct usb_hcd /* cache this readonly data; minimize chip reads */ ehci->hcs_params = ehci_readl(ehci, &ehci->caps->hcs_params); + if (ehci_quirk_amd_hudson(ehci)) + ehci->amd_l1_fix = 1; + retval = ehci_halt(ehci); if (retval) return retval; --- a/drivers/usb/host/ehci-sched.c +++ b/drivers/usb/host/ehci-sched.c @@ -1576,6 +1576,63 @@ itd_link (struct ehci_hcd *ehci, unsigne *hw_p = cpu_to_hc32(ehci, itd->itd_dma | Q_TYPE_ITD); } +#define AB_REG_BAR_LOW 0xe0 +#define AB_REG_BAR_HIGH 0xe1 +#define AB_INDX(addr) ((addr) + 0x00) +#define AB_DATA(addr) ((addr) + 0x04) +#define NB_PCIE_INDX_ADDR 0xe0 +#define NB_PCIE_INDX_DATA 0xe4 +#define NB_PIF0_PWRDOWN_0 0x01100012 +#define NB_PIF0_PWRDOWN_1 0x01100013 + +static void ehci_quirk_amd_L1(struct ehci_hcd *ehci, int disable) +{ + u32 addr, addr_low, addr_high, val; + + outb_p(AB_REG_BAR_LOW, 0xcd6); + addr_low = inb_p(0xcd7); + outb_p(AB_REG_BAR_HIGH, 0xcd6); + addr_high = inb_p(0xcd7); + addr = addr_high << 8 | addr_low; + outl_p(0x30, AB_INDX(addr)); + outl_p(0x40, AB_DATA(addr)); + outl_p(0x34, AB_INDX(addr)); + val = inl_p(AB_DATA(addr)); + + if (disable) { + val &= ~0x8; + val |= (1 << 4) | (1 << 9); + } else { + val |= 0x8; + val &= ~((1 << 4) | (1 << 9)); + } + outl_p(val, AB_DATA(addr)); + + if (amd_nb_dev) { + addr = NB_PIF0_PWRDOWN_0; + pci_write_config_dword(amd_nb_dev, NB_PCIE_INDX_ADDR, addr); + pci_read_config_dword(amd_nb_dev, NB_PCIE_INDX_DATA, &val); + if (disable) + val &= ~(0x3f << 7); + else + val |= 0x3f << 7; + + pci_write_config_dword(amd_nb_dev, NB_PCIE_INDX_DATA, val); + + addr = NB_PIF0_PWRDOWN_1; + pci_write_config_dword(amd_nb_dev, NB_PCIE_INDX_ADDR, addr); + pci_read_config_dword(amd_nb_dev, NB_PCIE_INDX_DATA, &val); + if (disable) + val &= ~(0x3f << 7); + else + val |= 0x3f << 7; + + pci_write_config_dword(amd_nb_dev, NB_PCIE_INDX_DATA, val); + } + + return; +} + /* fit urb's itds into the selected schedule slot; activate as needed */ static int itd_link_urb ( @@ -1603,6 +1660,12 @@ itd_link_urb ( next_uframe >> 3, next_uframe & 0x7); stream->start = jiffies; } + + if (ehci_to_hcd(ehci)->self.bandwidth_isoc_reqs == 0) { + if (ehci->amd_l1_fix == 1) + ehci_quirk_amd_L1(ehci, 1); + } + ehci_to_hcd(ehci)->self.bandwidth_isoc_reqs++; /* fill iTDs uframe by uframe */ @@ -1729,6 +1792,11 @@ itd_complete ( (void) disable_periodic(ehci); ehci_to_hcd(ehci)->self.bandwidth_isoc_reqs--; + if (ehci_to_hcd(ehci)->self.bandwidth_isoc_reqs == 0) { + if (ehci->amd_l1_fix == 1) + ehci_quirk_amd_L1(ehci, 0); + } + if (unlikely(list_is_singular(&stream->td_list))) { ehci_to_hcd(ehci)->self.bandwidth_allocated -= stream->bandwidth; @@ -2016,6 +2084,12 @@ sitd_link_urb ( stream->interval, hc32_to_cpu(ehci, stream->splits)); stream->start = jiffies; } + + if (ehci_to_hcd(ehci)->self.bandwidth_isoc_reqs == 0) { + if (ehci->amd_l1_fix == 1) + ehci_quirk_amd_L1(ehci, 1); + } + ehci_to_hcd(ehci)->self.bandwidth_isoc_reqs++; /* fill sITDs frame by frame */ @@ -2118,6 +2192,11 @@ sitd_complete ( (void) disable_periodic(ehci); ehci_to_hcd(ehci)->self.bandwidth_isoc_reqs--; + if (ehci_to_hcd(ehci)->self.bandwidth_isoc_reqs == 0) { + if (ehci->amd_l1_fix == 1) + ehci_quirk_amd_L1(ehci, 0); + } + if (list_is_singular(&stream->td_list)) { ehci_to_hcd(ehci)->self.bandwidth_allocated -= stream->bandwidth; --- a/drivers/usb/host/ehci.h +++ b/drivers/usb/host/ehci.h @@ -130,6 +130,7 @@ struct ehci_hcd { /* one per controlle unsigned has_amcc_usb23:1; unsigned need_io_watchdog:1; unsigned broken_periodic:1; + unsigned amd_l1_fix:1; /* required for usb32 quirk */ #define OHCI_CTRL_HCFS (3 << 6) --- a/drivers/usb/host/ohci-hcd.c +++ b/drivers/usb/host/ohci-hcd.c @@ -398,7 +398,14 @@ ohci_shutdown (struct usb_hcd *hcd) ohci = hcd_to_ohci (hcd); ohci_writel (ohci, OHCI_INTR_MIE, &ohci->regs->intrdisable); - ohci_usb_reset (ohci); + ohci->hc_control = ohci_readl(ohci, &ohci->regs->control); + + /* If the SHUTDOWN quirk is set, don't put the controller in RESET */ + ohci->hc_control &= (ohci->flags & OHCI_QUIRK_SHUTDOWN ? + OHCI_CTRL_RWC | OHCI_CTRL_HCFS : + OHCI_CTRL_RWC); + ohci_writel(ohci, ohci->hc_control, &ohci->regs->control); + /* flush the writes */ (void) ohci_readl (ohci, &ohci->regs->control); } --- a/drivers/usb/host/ohci-pci.c +++ b/drivers/usb/host/ohci-pci.c @@ -201,6 +201,20 @@ static int ohci_quirk_amd700(struct usb_ return 0; } +/* nVidia controllers continue to drive Reset signalling on the bus + * even after system shutdown, wasting power. This flag tells the + * shutdown routine to leave the controller OPERATIONAL instead of RESET. + */ +static int ohci_quirk_nvidia_shutdown(struct usb_hcd *hcd) +{ + struct ohci_hcd *ohci = hcd_to_ohci(hcd); + + ohci->flags |= OHCI_QUIRK_SHUTDOWN; + ohci_dbg(ohci, "enabled nVidia shutdown quirk\n"); + + return 0; +} + /* * The hardware normally enables the A-link power management feature, which * lets the system lower the power consumption in idle states. @@ -332,6 +346,10 @@ static const struct pci_device_id ohci_p PCI_DEVICE(PCI_VENDOR_ID_ATI, 0x4399), .driver_data = (unsigned long)ohci_quirk_amd700, }, + { + PCI_DEVICE(PCI_VENDOR_ID_NVIDIA, PCI_ANY_ID), + .driver_data = (unsigned long) ohci_quirk_nvidia_shutdown, + }, /* FIXME for some of the early AMD 760 southbridges, OHCI * won't work at all. blacklist them. --- a/drivers/usb/host/ohci.h +++ b/drivers/usb/host/ohci.h @@ -403,6 +403,7 @@ struct ohci_hcd { #define OHCI_QUIRK_HUB_POWER 0x100 /* distrust firmware power/oc setup */ #define OHCI_QUIRK_AMD_ISO 0x200 /* ISO transfers*/ #define OHCI_QUIRK_AMD_PREFETCH 0x400 /* pre-fetch for ISO transfer */ +#define OHCI_QUIRK_SHUTDOWN 0x800 /* nVidia power bug */ // there are also chip quirks/bugs in init logic struct work_struct nec_work; /* Worker for NEC quirk */ --- a/drivers/usb/host/pci-quirks.c +++ b/drivers/usb/host/pci-quirks.c @@ -169,6 +169,7 @@ static int __devinit mmio_resource_enabl static void __devinit quirk_usb_handoff_ohci(struct pci_dev *pdev) { void __iomem *base; + u32 control; if (!mmio_resource_enabled(pdev, 0)) return; @@ -177,10 +178,14 @@ static void __devinit quirk_usb_handoff_ if (base == NULL) return; + control = readl(base + OHCI_CONTROL); + /* On PA-RISC, PDC can leave IR set incorrectly; ignore it there. */ -#ifndef __hppa__ -{ - u32 control = readl(base + OHCI_CONTROL); +#ifdef __hppa__ +#define OHCI_CTRL_MASK (OHCI_CTRL_RWC | OHCI_CTRL_IR) +#else +#define OHCI_CTRL_MASK OHCI_CTRL_RWC + if (control & OHCI_CTRL_IR) { int wait_time = 500; /* arbitrary; 5 seconds */ writel(OHCI_INTR_OC, base + OHCI_INTRENABLE); @@ -194,13 +199,12 @@ static void __devinit quirk_usb_handoff_ dev_warn(&pdev->dev, "OHCI: BIOS handoff failed" " (BIOS bug?) %08x\n", readl(base + OHCI_CONTROL)); - - /* reset controller, preserving RWC */ - writel(control & OHCI_CTRL_RWC, base + OHCI_CONTROL); } -} #endif + /* reset controller, preserving RWC (and possibly IR) */ + writel(control & OHCI_CTRL_MASK, base + OHCI_CONTROL); + /* * disable interrupts */ --- a/drivers/usb/host/xhci-ring.c +++ b/drivers/usb/host/xhci-ring.c @@ -391,8 +391,11 @@ void xhci_find_new_dequeue_state(struct state->new_deq_seg = find_trb_seg(cur_td->start_seg, dev->eps[ep_index].stopped_trb, &state->new_cycle_state); - if (!state->new_deq_seg) - BUG(); + if (!state->new_deq_seg) { + WARN_ON(1); + return; + } + /* Dig out the cycle state saved by the xHC during the stop ep cmd */ xhci_dbg(xhci, "Finding endpoint context\n"); ep_ctx = xhci_get_ep_ctx(xhci, dev->out_ctx, ep_index); @@ -403,8 +406,10 @@ void xhci_find_new_dequeue_state(struct state->new_deq_seg = find_trb_seg(state->new_deq_seg, state->new_deq_ptr, &state->new_cycle_state); - if (!state->new_deq_seg) - BUG(); + if (!state->new_deq_seg) { + WARN_ON(1); + return; + } trb = &state->new_deq_ptr->generic; if ((trb->field[3] & TRB_TYPE_BITMASK) == TRB_TYPE(TRB_LINK) && @@ -1485,12 +1490,13 @@ static unsigned int count_sg_trbs_needed /* Scatter gather list entries may cross 64KB boundaries */ running_total = TRB_MAX_BUFF_SIZE - - (sg_dma_address(sg) & ((1 << TRB_MAX_BUFF_SHIFT) - 1)); + (sg_dma_address(sg) & (TRB_MAX_BUFF_SIZE - 1)); + running_total &= TRB_MAX_BUFF_SIZE - 1; if (running_total != 0) num_trbs++; /* How many more 64KB chunks to transfer, how many more TRBs? */ - while (running_total < sg_dma_len(sg)) { + while (running_total < sg_dma_len(sg) && running_total < temp) { num_trbs++; running_total += TRB_MAX_BUFF_SIZE; } @@ -1515,11 +1521,11 @@ static unsigned int count_sg_trbs_needed static void check_trb_math(struct urb *urb, int num_trbs, int running_total) { if (num_trbs != 0) - dev_dbg(&urb->dev->dev, "%s - ep %#x - Miscalculated number of " + dev_err(&urb->dev->dev, "%s - ep %#x - Miscalculated number of " "TRBs, %d left\n", __func__, urb->ep->desc.bEndpointAddress, num_trbs); if (running_total != urb->transfer_buffer_length) - dev_dbg(&urb->dev->dev, "%s - ep %#x - Miscalculated tx length, " + dev_err(&urb->dev->dev, "%s - ep %#x - Miscalculated tx length, " "queued %#x (%d), asked for %#x (%d)\n", __func__, urb->ep->desc.bEndpointAddress, @@ -1626,8 +1632,7 @@ static int queue_bulk_sg_tx(struct xhci_ sg = urb->sg->sg; addr = (u64) sg_dma_address(sg); this_sg_len = sg_dma_len(sg); - trb_buff_len = TRB_MAX_BUFF_SIZE - - (addr & ((1 << TRB_MAX_BUFF_SHIFT) - 1)); + trb_buff_len = TRB_MAX_BUFF_SIZE - (addr & (TRB_MAX_BUFF_SIZE - 1)); trb_buff_len = min_t(int, trb_buff_len, this_sg_len); if (trb_buff_len > urb->transfer_buffer_length) trb_buff_len = urb->transfer_buffer_length; @@ -1662,7 +1667,7 @@ static int queue_bulk_sg_tx(struct xhci_ (unsigned int) (addr + TRB_MAX_BUFF_SIZE) & ~(TRB_MAX_BUFF_SIZE - 1), (unsigned int) addr + trb_buff_len); if (TRB_MAX_BUFF_SIZE - - (addr & ((1 << TRB_MAX_BUFF_SHIFT) - 1)) < trb_buff_len) { + (addr & (TRB_MAX_BUFF_SIZE - 1)) < trb_buff_len) { xhci_warn(xhci, "WARN: sg dma xfer crosses 64KB boundaries!\n"); xhci_dbg(xhci, "Next boundary at %#x, end dma = %#x\n", (unsigned int) (addr + TRB_MAX_BUFF_SIZE) & ~(TRB_MAX_BUFF_SIZE - 1), @@ -1700,7 +1705,7 @@ static int queue_bulk_sg_tx(struct xhci_ } trb_buff_len = TRB_MAX_BUFF_SIZE - - (addr & ((1 << TRB_MAX_BUFF_SHIFT) - 1)); + (addr & (TRB_MAX_BUFF_SIZE - 1)); trb_buff_len = min_t(int, trb_buff_len, this_sg_len); if (running_total + trb_buff_len > urb->transfer_buffer_length) trb_buff_len = @@ -1735,7 +1740,8 @@ int xhci_queue_bulk_tx(struct xhci_hcd * num_trbs = 0; /* How much data is (potentially) left before the 64KB boundary? */ running_total = TRB_MAX_BUFF_SIZE - - (urb->transfer_dma & ((1 << TRB_MAX_BUFF_SHIFT) - 1)); + (urb->transfer_dma & (TRB_MAX_BUFF_SIZE - 1)); + running_total &= TRB_MAX_BUFF_SIZE - 1; /* If there's some data on this 64KB chunk, or we have to send a * zero-length transfer, we need at least one TRB @@ -1774,8 +1780,8 @@ int xhci_queue_bulk_tx(struct xhci_hcd * /* How much data is in the first TRB? */ addr = (u64) urb->transfer_dma; trb_buff_len = TRB_MAX_BUFF_SIZE - - (urb->transfer_dma & ((1 << TRB_MAX_BUFF_SHIFT) - 1)); - if (urb->transfer_buffer_length < trb_buff_len) + (urb->transfer_dma & (TRB_MAX_BUFF_SIZE - 1)); + if (trb_buff_len > urb->transfer_buffer_length) trb_buff_len = urb->transfer_buffer_length; first_trb = true; --- a/drivers/usb/misc/iowarrior.c +++ b/drivers/usb/misc/iowarrior.c @@ -373,7 +373,7 @@ static ssize_t iowarrior_write(struct fi case USB_DEVICE_ID_CODEMERCS_IOWPV2: case USB_DEVICE_ID_CODEMERCS_IOW40: /* IOW24 and IOW40 use a synchronous call */ - buf = kmalloc(8, GFP_KERNEL); /* 8 bytes are enough for both products */ + buf = kmalloc(count, GFP_KERNEL); if (!buf) { retval = -ENOMEM; goto exit; --- a/drivers/usb/musb/omap2430.c +++ b/drivers/usb/musb/omap2430.c @@ -309,6 +309,7 @@ static int musb_platform_resume(struct m int musb_platform_exit(struct musb *musb) { + del_timer_sync(&musb_idle_timer); omap_vbus_power(musb, 0 /*off*/, 1); --- a/drivers/usb/serial/ch341.c +++ b/drivers/usb/serial/ch341.c @@ -479,12 +479,22 @@ static void ch341_read_int_callback(stru if (actual_length >= 4) { struct ch341_private *priv = usb_get_serial_port_data(port); unsigned long flags; + u8 prev_line_status = priv->line_status; spin_lock_irqsave(&priv->lock, flags); priv->line_status = (~(data[2])) & CH341_BITS_MODEM_STAT; if ((data[1] & CH341_MULT_STAT)) priv->multi_status_change = 1; spin_unlock_irqrestore(&priv->lock, flags); + + if ((priv->line_status ^ prev_line_status) & CH341_BIT_DCD) { + struct tty_struct *tty = tty_port_tty_get(&port->port); + if (tty) + usb_serial_handle_dcd_change(port, tty, + priv->line_status & CH341_BIT_DCD); + tty_kref_put(tty); + } + wake_up_interruptible(&priv->delta_msr_wait); } --- a/drivers/usb/serial/cp210x.c +++ b/drivers/usb/serial/cp210x.c @@ -51,7 +51,6 @@ static void cp210x_break_ctl(struct tty_ static int cp210x_startup(struct usb_serial *); static void cp210x_disconnect(struct usb_serial *); static void cp210x_dtr_rts(struct usb_serial_port *p, int on); -static int cp210x_carrier_raised(struct usb_serial_port *p); static int debug; @@ -88,7 +87,6 @@ static struct usb_device_id id_table [] { USB_DEVICE(0x10C4, 0x8115) }, /* Arygon NFC/Mifare Reader */ { USB_DEVICE(0x10C4, 0x813D) }, /* Burnside Telecom Deskmobile */ { USB_DEVICE(0x10C4, 0x813F) }, /* Tams Master Easy Control */ - { USB_DEVICE(0x10C4, 0x8149) }, /* West Mountain Radio Computerized Battery Analyzer */ { USB_DEVICE(0x10C4, 0x814A) }, /* West Mountain Radio RIGblaster P&P */ { USB_DEVICE(0x10C4, 0x814B) }, /* West Mountain Radio RIGtalk */ { USB_DEVICE(0x10C4, 0x8156) }, /* B&G H3000 link cable */ @@ -111,7 +109,9 @@ static struct usb_device_id id_table [] { USB_DEVICE(0x10C4, 0x8341) }, /* Siemens MC35PU GPRS Modem */ { USB_DEVICE(0x10C4, 0x8382) }, /* Cygnal Integrated Products, Inc. */ { USB_DEVICE(0x10C4, 0x83A8) }, /* Amber Wireless AMB2560 */ + { USB_DEVICE(0x10C4, 0x83D8) }, /* DekTec DTA Plus VHF/UHF Booster/Attenuator */ { USB_DEVICE(0x10C4, 0x8411) }, /* Kyocera GPS Module */ + { USB_DEVICE(0x10C4, 0x8418) }, /* IRZ Automation Teleport SG-10 GSM/GPRS Modem */ { USB_DEVICE(0x10C4, 0x846E) }, /* BEI USB Sensor Interface (VCP) */ { USB_DEVICE(0x10C4, 0x8477) }, /* Balluff RFID */ { USB_DEVICE(0x10C4, 0xEA60) }, /* Silicon Labs factory default */ @@ -165,8 +165,7 @@ static struct usb_serial_driver cp210x_d .tiocmset = cp210x_tiocmset, .attach = cp210x_startup, .disconnect = cp210x_disconnect, - .dtr_rts = cp210x_dtr_rts, - .carrier_raised = cp210x_carrier_raised + .dtr_rts = cp210x_dtr_rts }; /* Config request types */ @@ -800,15 +799,6 @@ static int cp210x_tiocmget (struct tty_s return result; } -static int cp210x_carrier_raised(struct usb_serial_port *p) -{ - unsigned int control; - cp210x_get_config(p, CP210X_GET_MDMSTS, &control, 1); - if (control & CONTROL_DCD) - return 1; - return 0; -} - static void cp210x_break_ctl (struct tty_struct *tty, int break_state) { struct usb_serial_port *port = tty->driver_data; --- a/drivers/usb/serial/digi_acceleport.c +++ b/drivers/usb/serial/digi_acceleport.c @@ -455,7 +455,6 @@ static int digi_write_room(struct tty_st static int digi_chars_in_buffer(struct tty_struct *tty); static int digi_open(struct tty_struct *tty, struct usb_serial_port *port); static void digi_close(struct usb_serial_port *port); -static int digi_carrier_raised(struct usb_serial_port *port); static void digi_dtr_rts(struct usb_serial_port *port, int on); static int digi_startup_device(struct usb_serial *serial); static int digi_startup(struct usb_serial *serial); @@ -511,7 +510,6 @@ static struct usb_serial_driver digi_acc .open = digi_open, .close = digi_close, .dtr_rts = digi_dtr_rts, - .carrier_raised = digi_carrier_raised, .write = digi_write, .write_room = digi_write_room, .write_bulk_callback = digi_write_bulk_callback, @@ -1338,14 +1336,6 @@ static void digi_dtr_rts(struct usb_seri digi_set_modem_signals(port, on * (TIOCM_DTR|TIOCM_RTS), 1); } -static int digi_carrier_raised(struct usb_serial_port *port) -{ - struct digi_port *priv = usb_get_serial_port_data(port); - if (priv->dp_modem_signals & TIOCM_CD) - return 1; - return 0; -} - static int digi_open(struct tty_struct *tty, struct usb_serial_port *port) { int ret; --- a/drivers/usb/serial/ftdi_sio.c +++ b/drivers/usb/serial/ftdi_sio.c @@ -104,6 +104,7 @@ struct ftdi_sio_quirk { static int ftdi_jtag_probe(struct usb_serial *serial); static int ftdi_mtxorb_hack_setup(struct usb_serial *serial); static int ftdi_NDI_device_setup(struct usb_serial *serial); +static int ftdi_stmclite_probe(struct usb_serial *serial); static void ftdi_USB_UIRT_setup(struct ftdi_private *priv); static void ftdi_HE_TIRA1_setup(struct ftdi_private *priv); @@ -127,6 +128,10 @@ static struct ftdi_sio_quirk ftdi_HE_TIR .port_probe = ftdi_HE_TIRA1_setup, }; +static struct ftdi_sio_quirk ftdi_stmclite_quirk = { + .probe = ftdi_stmclite_probe, +}; + /* * The 8U232AM has the same API as the sio except for: * - it can support MUCH higher baudrates; up to: @@ -620,6 +625,7 @@ static struct usb_device_id id_table_com { USB_DEVICE(FTDI_VID, FTDI_OCEANIC_PID) }, { USB_DEVICE(TTI_VID, TTI_QL355P_PID) }, { USB_DEVICE(FTDI_VID, FTDI_RM_CANVIEW_PID) }, + { USB_DEVICE(ACTON_VID, ACTON_SPECTRAPRO_PID) }, { USB_DEVICE(CONTEC_VID, CONTEC_COM1USBH_PID) }, { USB_DEVICE(BANDB_VID, BANDB_USOTL4_PID) }, { USB_DEVICE(BANDB_VID, BANDB_USTL4_PID) }, @@ -681,7 +687,17 @@ static struct usb_device_id id_table_com { USB_DEVICE(FTDI_VID, FTDI_PCDJ_DAC2_PID) }, { USB_DEVICE(FTDI_VID, FTDI_RRCIRKITS_LOCOBUFFER_PID) }, { USB_DEVICE(FTDI_VID, FTDI_ASK_RDR400_PID) }, - { USB_DEVICE(ICOM_ID1_VID, ICOM_ID1_PID) }, + { USB_DEVICE(ICOM_VID, ICOM_ID_1_PID) }, + { USB_DEVICE(ICOM_VID, ICOM_OPC_U_UC_PID) }, + { USB_DEVICE(ICOM_VID, ICOM_ID_RP2C1_PID) }, + { USB_DEVICE(ICOM_VID, ICOM_ID_RP2C2_PID) }, + { USB_DEVICE(ICOM_VID, ICOM_ID_RP2D_PID) }, + { USB_DEVICE(ICOM_VID, ICOM_ID_RP2VT_PID) }, + { USB_DEVICE(ICOM_VID, ICOM_ID_RP2VR_PID) }, + { USB_DEVICE(ICOM_VID, ICOM_ID_RP4KVT_PID) }, + { USB_DEVICE(ICOM_VID, ICOM_ID_RP4KVR_PID) }, + { USB_DEVICE(ICOM_VID, ICOM_ID_RP2KVT_PID) }, + { USB_DEVICE(ICOM_VID, ICOM_ID_RP2KVR_PID) }, { USB_DEVICE(FTDI_VID, FTDI_ACG_HFDUAL_PID) }, { USB_DEVICE(FTDI_VID, FTDI_YEI_SERVOCENTER31_PID) }, { USB_DEVICE(FTDI_VID, FTDI_THORLABS_PID) }, @@ -805,6 +821,8 @@ static struct usb_device_id id_table_com { USB_DEVICE(FTDI_VID, FTDI_DOTEC_PID) }, { USB_DEVICE(QIHARDWARE_VID, MILKYMISTONE_JTAGSERIAL_PID), .driver_info = (kernel_ulong_t)&ftdi_jtag_quirk }, + { USB_DEVICE(ST_VID, ST_STMCLT1030_PID), + .driver_info = (kernel_ulong_t)&ftdi_stmclite_quirk }, { }, /* Optional parameter entry */ { } /* Terminating entry */ }; @@ -1738,6 +1756,25 @@ static int ftdi_jtag_probe(struct usb_se } /* + * First and second port on STMCLiteadaptors is reserved for JTAG interface + * and the forth port for pio + */ +static int ftdi_stmclite_probe(struct usb_serial *serial) +{ + struct usb_device *udev = serial->dev; + struct usb_interface *interface = serial->interface; + + dbg("%s", __func__); + + if (interface == udev->actconfig->interface[2]) + return 0; + + dev_info(&udev->dev, "Ignoring serial port reserved for JTAG\n"); + + return -ENODEV; +} + +/* * The Matrix Orbital VK204-25-USB has an invalid IN endpoint. * We have to correct it if we want to read from it. */ --- a/drivers/usb/serial/ftdi_sio_ids.h +++ b/drivers/usb/serial/ftdi_sio_ids.h @@ -518,6 +518,12 @@ #define RATOC_PRODUCT_ID_USB60F 0xb020 /* + * Acton Research Corp. + */ +#define ACTON_VID 0x0647 /* Vendor ID */ +#define ACTON_SPECTRAPRO_PID 0x0100 + +/* * Contec products (http://www.contec.com) * Submitted by Daniel Sangorrin */ @@ -576,11 +582,23 @@ #define OCT_US101_PID 0x0421 /* OCT US101 USB to RS-232 */ /* - * Icom ID-1 digital transceiver + * Definitions for Icom Inc. devices */ - -#define ICOM_ID1_VID 0x0C26 -#define ICOM_ID1_PID 0x0004 +#define ICOM_VID 0x0C26 /* Icom vendor ID */ +/* Note: ID-1 is a communications tranceiver for HAM-radio operators */ +#define ICOM_ID_1_PID 0x0004 /* ID-1 USB to RS-232 */ +/* Note: OPC is an Optional cable to connect an Icom Tranceiver */ +#define ICOM_OPC_U_UC_PID 0x0018 /* OPC-478UC, OPC-1122U cloning cable */ +/* Note: ID-RP* devices are Icom Repeater Devices for HAM-radio */ +#define ICOM_ID_RP2C1_PID 0x0009 /* ID-RP2C Asset 1 to RS-232 */ +#define ICOM_ID_RP2C2_PID 0x000A /* ID-RP2C Asset 2 to RS-232 */ +#define ICOM_ID_RP2D_PID 0x000B /* ID-RP2D configuration port*/ +#define ICOM_ID_RP2VT_PID 0x000C /* ID-RP2V Transmit config port */ +#define ICOM_ID_RP2VR_PID 0x000D /* ID-RP2V Receive config port */ +#define ICOM_ID_RP4KVT_PID 0x0010 /* ID-RP4000V Transmit config port */ +#define ICOM_ID_RP4KVR_PID 0x0011 /* ID-RP4000V Receive config port */ +#define ICOM_ID_RP2KVT_PID 0x0012 /* ID-RP2000V Transmit config port */ +#define ICOM_ID_RP2KVR_PID 0x0013 /* ID-RP2000V Receive config port */ /* * GN Otometrics (http://www.otometrics.com) @@ -1029,6 +1047,12 @@ #define WHT_PID 0x0004 /* Wireless Handheld Terminal */ /* + * STMicroelectonics + */ +#define ST_VID 0x0483 +#define ST_STMCLT1030_PID 0x3747 /* ST Micro Connect Lite STMCLT1030 */ + +/* * Papouch products (http://www.papouch.com/) * Submitted by Folkert van Heusden */ --- a/drivers/usb/serial/generic.c +++ b/drivers/usb/serial/generic.c @@ -578,6 +578,26 @@ int usb_serial_handle_break(struct usb_s } EXPORT_SYMBOL_GPL(usb_serial_handle_break); +/** + * usb_serial_handle_dcd_change - handle a change of carrier detect state + * @port: usb_serial_port structure for the open port + * @tty: tty_struct structure for the port + * @status: new carrier detect status, nonzero if active + */ +void usb_serial_handle_dcd_change(struct usb_serial_port *usb_port, + struct tty_struct *tty, unsigned int status) +{ + struct tty_port *port = &usb_port->port; + + dbg("%s - port %d, status %d", __func__, usb_port->number, status); + + if (status) + wake_up_interruptible(&port->open_wait); + else if (tty && !C_CLOCAL(tty)) + tty_hangup(tty); +} +EXPORT_SYMBOL_GPL(usb_serial_handle_dcd_change); + int usb_serial_generic_resume(struct usb_serial *serial) { struct usb_serial_port *port; --- a/drivers/usb/serial/io_edgeport.c +++ b/drivers/usb/serial/io_edgeport.c @@ -2935,8 +2935,8 @@ static void load_application_firmware(st dbg("%s %d.%d.%d", fw_info, rec->data[0], rec->data[1], build); - edge_serial->product_info.FirmwareMajorVersion = fw->data[0]; - edge_serial->product_info.FirmwareMinorVersion = fw->data[1]; + edge_serial->product_info.FirmwareMajorVersion = rec->data[0]; + edge_serial->product_info.FirmwareMinorVersion = rec->data[1]; edge_serial->product_info.FirmwareBuildNumber = cpu_to_le16(build); for (rec = ihex_next_binrec(rec); rec; --- a/drivers/usb/serial/keyspan_pda.c +++ b/drivers/usb/serial/keyspan_pda.c @@ -663,22 +663,6 @@ static void keyspan_pda_dtr_rts(struct u } } -static int keyspan_pda_carrier_raised(struct usb_serial_port *port) -{ - struct usb_serial *serial = port->serial; - unsigned char modembits; - - /* If we can read the modem status and the DCD is low then - carrier is not raised yet */ - if (keyspan_pda_get_modem_info(serial, &modembits) >= 0) { - if (!(modembits & (1>>6))) - return 0; - } - /* Carrier raised, or we failed (eg disconnected) so - progress accordingly */ - return 1; -} - static int keyspan_pda_open(struct tty_struct *tty, struct usb_serial_port *port) @@ -854,7 +838,6 @@ static struct usb_serial_driver keyspan_ .id_table = id_table_std, .num_ports = 1, .dtr_rts = keyspan_pda_dtr_rts, - .carrier_raised = keyspan_pda_carrier_raised, .open = keyspan_pda_open, .close = keyspan_pda_close, .write = keyspan_pda_write, --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -369,7 +369,16 @@ static int option_resume(struct usb_ser #define HAIER_VENDOR_ID 0x201e #define HAIER_PRODUCT_CE100 0x2009 -#define CINTERION_VENDOR_ID 0x0681 +/* Cinterion (formerly Siemens) products */ +#define SIEMENS_VENDOR_ID 0x0681 +#define CINTERION_VENDOR_ID 0x1e2d +#define CINTERION_PRODUCT_HC25_MDM 0x0047 +#define CINTERION_PRODUCT_HC25_MDMNET 0x0040 +#define CINTERION_PRODUCT_HC28_MDM 0x004C +#define CINTERION_PRODUCT_HC28_MDMNET 0x004A /* same for HC28J */ +#define CINTERION_PRODUCT_EU3_E 0x0051 +#define CINTERION_PRODUCT_EU3_P 0x0052 +#define CINTERION_PRODUCT_PH8 0x0053 /* Olivetti products */ #define OLIVETTI_VENDOR_ID 0x0b3c @@ -895,7 +904,17 @@ static struct usb_device_id option_ids[] { USB_DEVICE(PIRELLI_VENDOR_ID, PIRELLI_PRODUCT_100F) }, { USB_DEVICE(PIRELLI_VENDOR_ID, PIRELLI_PRODUCT_1011)}, { USB_DEVICE(PIRELLI_VENDOR_ID, PIRELLI_PRODUCT_1012)}, - { USB_DEVICE(CINTERION_VENDOR_ID, 0x0047) }, + /* Cinterion */ + { USB_DEVICE(CINTERION_VENDOR_ID, CINTERION_PRODUCT_EU3_E) }, + { USB_DEVICE(CINTERION_VENDOR_ID, CINTERION_PRODUCT_EU3_P) }, + { USB_DEVICE(CINTERION_VENDOR_ID, CINTERION_PRODUCT_PH8) }, + { USB_DEVICE(CINTERION_VENDOR_ID, CINTERION_PRODUCT_HC28_MDM) }, + { USB_DEVICE(CINTERION_VENDOR_ID, CINTERION_PRODUCT_HC28_MDMNET) }, + { USB_DEVICE(SIEMENS_VENDOR_ID, CINTERION_PRODUCT_HC25_MDM) }, + { USB_DEVICE(SIEMENS_VENDOR_ID, CINTERION_PRODUCT_HC25_MDMNET) }, + { USB_DEVICE(SIEMENS_VENDOR_ID, CINTERION_PRODUCT_HC28_MDM) }, /* HC28 enumerates with Siemens or Cinterion VID depending on FW revision */ + { USB_DEVICE(SIEMENS_VENDOR_ID, CINTERION_PRODUCT_HC28_MDMNET) }, + { USB_DEVICE(OLIVETTI_VENDOR_ID, OLIVETTI_PRODUCT_OLICARD100) }, { USB_DEVICE(CELOT_VENDOR_ID, CELOT_PRODUCT_CT680M) }, /* CT-650 CDMA 450 1xEVDO modem */ { } /* Terminating entry */ --- a/drivers/usb/serial/pl2303.c +++ b/drivers/usb/serial/pl2303.c @@ -59,6 +59,8 @@ static struct usb_device_id id_table [] { USB_DEVICE(PL2303_VENDOR_ID, PL2303_PRODUCT_ID_ALDIGA) }, { USB_DEVICE(PL2303_VENDOR_ID, PL2303_PRODUCT_ID_MMX) }, { USB_DEVICE(PL2303_VENDOR_ID, PL2303_PRODUCT_ID_GPRS) }, + { USB_DEVICE(PL2303_VENDOR_ID, PL2303_PRODUCT_ID_HCR331) }, + { USB_DEVICE(PL2303_VENDOR_ID, PL2303_PRODUCT_ID_MOTOROLA) }, { USB_DEVICE(IODATA_VENDOR_ID, IODATA_PRODUCT_ID) }, { USB_DEVICE(IODATA_VENDOR_ID, IODATA_PRODUCT_ID_RSAQ5) }, { USB_DEVICE(ATEN_VENDOR_ID, ATEN_PRODUCT_ID) }, @@ -955,9 +957,11 @@ static void pl2303_update_line_status(st { struct pl2303_private *priv = usb_get_serial_port_data(port); + struct tty_struct *tty; unsigned long flags; u8 status_idx = UART_STATE; u8 length = UART_STATE + 1; + u8 prev_line_status; u16 idv, idp; idv = le16_to_cpu(port->serial->dev->descriptor.idVendor); @@ -979,11 +983,20 @@ static void pl2303_update_line_status(st /* Save off the uart status for others to look at */ spin_lock_irqsave(&priv->lock, flags); + prev_line_status = priv->line_status; priv->line_status = data[status_idx]; spin_unlock_irqrestore(&priv->lock, flags); if (priv->line_status & UART_BREAK_ERROR) usb_serial_handle_break(port); wake_up_interruptible(&priv->delta_msr_wait); + + tty = tty_port_tty_get(&port->port); + if (!tty) + return; + if ((priv->line_status ^ prev_line_status) & UART_DCD) + usb_serial_handle_dcd_change(port, tty, + priv->line_status & UART_DCD); + tty_kref_put(tty); } static void pl2303_read_int_callback(struct urb *urb) --- a/drivers/usb/serial/pl2303.h +++ b/drivers/usb/serial/pl2303.h @@ -20,6 +20,8 @@ #define PL2303_PRODUCT_ID_ALDIGA 0x0611 #define PL2303_PRODUCT_ID_MMX 0x0612 #define PL2303_PRODUCT_ID_GPRS 0x0609 +#define PL2303_PRODUCT_ID_HCR331 0x331a +#define PL2303_PRODUCT_ID_MOTOROLA 0x0307 #define ATEN_VENDOR_ID 0x0557 #define ATEN_VENDOR_ID2 0x0547 --- a/drivers/usb/serial/sierra.c +++ b/drivers/usb/serial/sierra.c @@ -266,6 +266,9 @@ static struct usb_device_id id_table [] { USB_DEVICE(0x1199, 0x68A3), /* Sierra Wireless Direct IP modems */ .driver_info = (kernel_ulong_t)&direct_ip_interface_blacklist }, + { USB_DEVICE(0x0f3d, 0x68A3), /* Airprime/Sierra Wireless Direct IP modems */ + .driver_info = (kernel_ulong_t)&direct_ip_interface_blacklist + }, { } }; --- a/drivers/usb/serial/spcp8x5.c +++ b/drivers/usb/serial/spcp8x5.c @@ -137,7 +137,7 @@ struct spcp8x5_usb_ctrl_arg { /* how come ??? */ #define UART_STATE 0x08 -#define UART_STATE_TRANSIENT_MASK 0x74 +#define UART_STATE_TRANSIENT_MASK 0x75 #define UART_DCD 0x01 #define UART_DSR 0x02 #define UART_BREAK_ERROR 0x04 @@ -734,6 +734,10 @@ static void spcp8x5_read_bulk_callback(s tty_insert_flip_char(tty, data[i], tty_flag); tty_flip_buffer_push(tty); } + + if (status & UART_DCD) + usb_serial_handle_dcd_change(port, tty, + priv->line_status & MSR_STATUS_LINE_DCD); tty_kref_put(tty); /* Schedule the next read _if_ we are still open */ --- a/drivers/usb/serial/ti_usb_3410_5052.c +++ b/drivers/usb/serial/ti_usb_3410_5052.c @@ -366,9 +366,9 @@ failed_1port: static void __exit ti_exit(void) { + usb_deregister(&ti_usb_driver); usb_serial_deregister(&ti_1port_device); usb_serial_deregister(&ti_2port_device); - usb_deregister(&ti_usb_driver); } --- a/drivers/usb/serial/visor.c +++ b/drivers/usb/serial/visor.c @@ -27,6 +27,7 @@ #include #include #include +#include #include "visor.h" /* @@ -758,6 +759,17 @@ static int visor_probe(struct usb_serial dbg("%s", __func__); + /* + * some Samsung Android phones in modem mode have the same ID + * as SPH-I500, but they are ACM devices, so dont bind to them + */ + if (id->idVendor == SAMSUNG_VENDOR_ID && + id->idProduct == SAMSUNG_SPH_I500_ID && + serial->dev->descriptor.bDeviceClass == USB_CLASS_COMM && + serial->dev->descriptor.bDeviceSubClass == + USB_CDC_SUBCLASS_ACM) + return -ENODEV; + if (serial->dev->actconfig->desc.bConfigurationValue != 1) { dev_err(&serial->dev->dev, "active config #%d != 1 ??\n", serial->dev->actconfig->desc.bConfigurationValue); --- a/drivers/usb/storage/unusual_cypress.h +++ b/drivers/usb/storage/unusual_cypress.h @@ -31,4 +31,9 @@ UNUSUAL_DEV( 0x04b4, 0x6831, 0x0000, 0x "Cypress ISD-300LP", US_SC_CYP_ATACB, US_PR_DEVICE, NULL, 0), +UNUSUAL_DEV( 0x14cd, 0x6116, 0x0000, 0x9999, + "Super Top", + "USB 2.0 SATA BRIDGE", + US_SC_CYP_ATACB, US_PR_DEVICE, NULL, 0), + #endif /* defined(CONFIG_USB_STORAGE_CYPRESS_ATACB) || ... */ --- a/drivers/usb/storage/unusual_devs.h +++ b/drivers/usb/storage/unusual_devs.h @@ -1043,6 +1043,15 @@ UNUSUAL_DEV( 0x084d, 0x0011, 0x0110, 0x US_SC_DEVICE, US_PR_DEVICE, NULL, US_FL_BULK32), +/* Reported by + * The device reports a vendor-specific device class, requiring an + * explicit vendor/product match. + */ +UNUSUAL_DEV( 0x0851, 0x1542, 0x0002, 0x0002, + "MagicPixel", + "FW_Omega2", + US_SC_DEVICE, US_PR_DEVICE, NULL, 0), + /* Andrew Lunn * PanDigital Digital Picture Frame. Does not like ALLOW_MEDIUM_REMOVAL * on LUN 4. @@ -1401,6 +1410,13 @@ UNUSUAL_DEV( 0x0fca, 0x0006, 0x0001, 0x US_FL_IGNORE_DEVICE ), #endif +/* Submitted by Nick Holloway */ +UNUSUAL_DEV( 0x0f88, 0x042e, 0x0100, 0x0100, + "VTech", + "Kidizoom", + US_SC_DEVICE, US_PR_DEVICE, NULL, + US_FL_FIX_CAPACITY ), + /* Reported by Michael Stattmann */ UNUSUAL_DEV( 0x0fce, 0xd008, 0x0000, 0x0000, "Sony Ericsson", @@ -1880,6 +1896,22 @@ UNUSUAL_DEV( 0x1908, 0x1320, 0x0000, 0x0 US_SC_DEVICE, US_PR_DEVICE, NULL, US_FL_BAD_SENSE ), +/* Patch by Richard Schütz + * This external hard drive enclosure uses a JMicron chip which + * needs the US_FL_IGNORE_RESIDUE flag to work properly. */ +UNUSUAL_DEV( 0x1e68, 0x001b, 0x0000, 0x0000, + "TrekStor GmbH & Co. KG", + "DataStation maxi g.u", + US_SC_DEVICE, US_PR_DEVICE, NULL, + US_FL_IGNORE_RESIDUE | US_FL_SANE_SENSE ), + +/* Reported by Jasper Mackenzie */ +UNUSUAL_DEV( 0x1e74, 0x4621, 0x0000, 0x0000, + "Coby Electronics", + "MP3 Player", + US_SC_DEVICE, US_PR_DEVICE, NULL, + US_FL_BULK_IGNORE_TAG | US_FL_MAX_SECTORS_64 ), + UNUSUAL_DEV( 0x2116, 0x0320, 0x0001, 0x0001, "ST", "2A", --- a/drivers/virtio/virtio_pci.c +++ b/drivers/virtio/virtio_pci.c @@ -95,11 +95,6 @@ static struct pci_device_id virtio_pci_i MODULE_DEVICE_TABLE(pci, virtio_pci_id_table); -/* A PCI device has it's own struct device and so does a virtio device so - * we create a place for the virtio devices to show up in sysfs. I think it - * would make more sense for virtio to not insist on having it's own device. */ -static struct device *virtio_pci_root; - /* Convert a generic virtio device to our structure */ static struct virtio_pci_device *to_vp_device(struct virtio_device *vdev) { @@ -628,7 +623,7 @@ static int __devinit virtio_pci_probe(st if (vp_dev == NULL) return -ENOMEM; - vp_dev->vdev.dev.parent = virtio_pci_root; + vp_dev->vdev.dev.parent = &pci_dev->dev; vp_dev->vdev.dev.release = virtio_pci_release_dev; vp_dev->vdev.config = &virtio_pci_config_ops; vp_dev->pci_dev = pci_dev; @@ -652,6 +647,7 @@ static int __devinit virtio_pci_probe(st goto out_req_regions; pci_set_drvdata(pci_dev, vp_dev); + pci_set_master(pci_dev); /* we use the subsystem vendor/device id as the virtio vendor/device * id. this allows us to use the same PCI vendor/device id for all @@ -715,17 +711,7 @@ static struct pci_driver virtio_pci_driv static int __init virtio_pci_init(void) { - int err; - - virtio_pci_root = root_device_register("virtio-pci"); - if (IS_ERR(virtio_pci_root)) - return PTR_ERR(virtio_pci_root); - - err = pci_register_driver(&virtio_pci_driver); - if (err) - root_device_unregister(virtio_pci_root); - - return err; + return pci_register_driver(&virtio_pci_driver); } module_init(virtio_pci_init); @@ -733,7 +719,6 @@ module_init(virtio_pci_init); static void __exit virtio_pci_exit(void) { pci_unregister_driver(&virtio_pci_driver); - root_device_unregister(virtio_pci_root); } module_exit(virtio_pci_exit); --- a/fs/cifs/cifsproto.h +++ b/fs/cifs/cifsproto.h @@ -323,7 +323,7 @@ extern int CIFSSMBLock(const int xid, st const __u16 netfid, const __u64 len, const __u64 offset, const __u32 numUnlock, const __u32 numLock, const __u8 lockType, - const bool waitFlag); + const bool waitFlag, const __u8 oplock_level); extern int CIFSSMBPosixLock(const int xid, struct cifsTconInfo *tcon, const __u16 smb_file_id, const int get_flag, const __u64 len, struct file_lock *, --- a/fs/cifs/cifssmb.c +++ b/fs/cifs/cifssmb.c @@ -1641,7 +1641,8 @@ int CIFSSMBLock(const int xid, struct cifsTconInfo *tcon, const __u16 smb_file_id, const __u64 len, const __u64 offset, const __u32 numUnlock, - const __u32 numLock, const __u8 lockType, const bool waitFlag) + const __u32 numLock, const __u8 lockType, + const bool waitFlag, const __u8 oplock_level) { int rc = 0; LOCK_REQ *pSMB = NULL; @@ -1669,6 +1670,7 @@ CIFSSMBLock(const int xid, struct cifsTc pSMB->NumberOfLocks = cpu_to_le16(numLock); pSMB->NumberOfUnlocks = cpu_to_le16(numUnlock); pSMB->LockType = lockType; + pSMB->OplockLevel = oplock_level; pSMB->AndXCommand = 0xFF; /* none */ pSMB->Fid = smb_file_id; /* netfid stays le */ --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -825,12 +825,12 @@ int cifs_lock(struct file *file, int cmd /* BB we could chain these into one lock request BB */ rc = CIFSSMBLock(xid, tcon, netfid, length, pfLock->fl_start, - 0, 1, lockType, 0 /* wait flag */ ); + 0, 1, lockType, 0 /* wait flag */, 0); if (rc == 0) { rc = CIFSSMBLock(xid, tcon, netfid, length, pfLock->fl_start, 1 /* numUnlock */ , 0 /* numLock */ , lockType, - 0 /* wait flag */ ); + 0 /* wait flag */, 0); pfLock->fl_type = F_UNLCK; if (rc != 0) cERROR(1, ("Error unlocking previously locked " @@ -873,8 +873,8 @@ int cifs_lock(struct file *file, int cmd if (numLock) { rc = CIFSSMBLock(xid, tcon, netfid, length, - pfLock->fl_start, - 0, numLock, lockType, wait_flag); + pfLock->fl_start, 0, numLock, lockType, + wait_flag, 0); if (rc == 0) { /* For Windows locks we must store them. */ @@ -894,9 +894,9 @@ int cifs_lock(struct file *file, int cmd (pfLock->fl_start + length) >= (li->offset + li->length)) { stored_rc = CIFSSMBLock(xid, tcon, - netfid, - li->length, li->offset, - 1, 0, li->type, false); + netfid, li->length, + li->offset, 1, 0, + li->type, false, 0); if (stored_rc) rc = stored_rc; @@ -2314,7 +2314,8 @@ cifs_oplock_break(struct slow_work *work */ if (!cfile->closePend && !cfile->oplock_break_cancelled) { rc = CIFSSMBLock(0, cifs_sb->tcon, cfile->netfid, 0, 0, 0, 0, - LOCKING_ANDX_OPLOCK_RELEASE, false); + LOCKING_ANDX_OPLOCK_RELEASE, false, + cinode->clientCanCacheRead ? 1 : 0); cFYI(1, ("Oplock release rc = %d", rc)); } } --- a/fs/ecryptfs/inode.c +++ b/fs/ecryptfs/inode.c @@ -988,6 +988,8 @@ int ecryptfs_getattr(struct vfsmount *mn rc = vfs_getattr(ecryptfs_dentry_to_lower_mnt(dentry), ecryptfs_dentry_to_lower(dentry), &lower_stat); if (!rc) { + fsstack_copy_attr_all(dentry->d_inode, + ecryptfs_inode_to_lower(dentry->d_inode), NULL); generic_fillattr(dentry->d_inode, stat); stat->blocks = lower_stat.blocks; } --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -63,6 +63,13 @@ * cleanup path and it is also acquired by eventpoll_release_file() * if a file has been pushed inside an epoll set and it is then * close()d without a previous call toepoll_ctl(EPOLL_CTL_DEL). + * It is also acquired when inserting an epoll fd onto another epoll + * fd. We do this so that we walk the epoll tree and ensure that this + * insertion does not create a cycle of epoll file descriptors, which + * could lead to deadlock. We need a global mutex to prevent two + * simultaneous inserts (A into B and B into A) from racing and + * constructing a cycle without either insert observing that it is + * going to. * It is possible to drop the "ep->mtx" and to use the global * mutex "epmutex" (together with "ep->lock") to have it working, * but having "ep->mtx" will make the interface more scalable. @@ -227,6 +234,9 @@ static int max_user_watches __read_mostl */ static DEFINE_MUTEX(epmutex); +/* Used to check for epoll file descriptor inclusion loops */ +static struct nested_calls poll_loop_ncalls; + /* Used for safe wake up implementation */ static struct nested_calls poll_safewake_ncalls; @@ -1182,6 +1192,62 @@ retry: return res; } +/** + * ep_loop_check_proc - Callback function to be passed to the @ep_call_nested() + * API, to verify that adding an epoll file inside another + * epoll structure, does not violate the constraints, in + * terms of closed loops, or too deep chains (which can + * result in excessive stack usage). + * + * @priv: Pointer to the epoll file to be currently checked. + * @cookie: Original cookie for this call. This is the top-of-the-chain epoll + * data structure pointer. + * @call_nests: Current dept of the @ep_call_nested() call stack. + * + * Returns: Returns zero if adding the epoll @file inside current epoll + * structure @ep does not violate the constraints, or -1 otherwise. + */ +static int ep_loop_check_proc(void *priv, void *cookie, int call_nests) +{ + int error = 0; + struct file *file = priv; + struct eventpoll *ep = file->private_data; + struct rb_node *rbp; + struct epitem *epi; + + mutex_lock(&ep->mtx); + for (rbp = rb_first(&ep->rbr); rbp; rbp = rb_next(rbp)) { + epi = rb_entry(rbp, struct epitem, rbn); + if (unlikely(is_file_epoll(epi->ffd.file))) { + error = ep_call_nested(&poll_loop_ncalls, EP_MAX_NESTS, + ep_loop_check_proc, epi->ffd.file, + epi->ffd.file->private_data, current); + if (error != 0) + break; + } + } + mutex_unlock(&ep->mtx); + + return error; +} + +/** + * ep_loop_check - Performs a check to verify that adding an epoll file (@file) + * another epoll file (represented by @ep) does not create + * closed loops or too deep chains. + * + * @ep: Pointer to the epoll private data structure. + * @file: Pointer to the epoll file to be checked. + * + * Returns: Returns zero if adding the epoll @file inside current epoll + * structure @ep does not violate the constraints, or -1 otherwise. + */ +static int ep_loop_check(struct eventpoll *ep, struct file *file) +{ + return ep_call_nested(&poll_loop_ncalls, EP_MAX_NESTS, + ep_loop_check_proc, file, ep, current); +} + /* * Open an eventpoll file descriptor. */ @@ -1230,6 +1296,7 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, in struct epoll_event __user *, event) { int error; + int did_lock_epmutex = 0; struct file *file, *tfile; struct eventpoll *ep; struct epitem *epi; @@ -1271,6 +1338,25 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, in */ ep = file->private_data; + /* + * When we insert an epoll file descriptor, inside another epoll file + * descriptor, there is the change of creating closed loops, which are + * better be handled here, than in more critical paths. + * + * We hold epmutex across the loop check and the insert in this case, in + * order to prevent two separate inserts from racing and each doing the + * insert "at the same time" such that ep_loop_check passes on both + * before either one does the insert, thereby creating a cycle. + */ + if (unlikely(is_file_epoll(tfile) && op == EPOLL_CTL_ADD)) { + mutex_lock(&epmutex); + did_lock_epmutex = 1; + error = -ELOOP; + if (ep_loop_check(ep, tfile) != 0) + goto error_tgt_fput; + } + + mutex_lock(&ep->mtx); /* @@ -1306,6 +1392,9 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, in mutex_unlock(&ep->mtx); error_tgt_fput: + if (unlikely(did_lock_epmutex)) + mutex_unlock(&epmutex); + fput(tfile); error_fput: fput(file); @@ -1424,6 +1513,12 @@ static int __init eventpoll_init(void) max_user_watches = (((si.totalram - si.totalhigh) / 25) << PAGE_SHIFT) / EP_ITEM_COST; + /* + * Initialize the structure used to perform epoll file descriptor + * inclusion loops checks. + */ + ep_nested_calls_init(&poll_loop_ncalls); + /* Initialize the structure used to perform safe poll wait head wake ups */ ep_nested_calls_init(&poll_safewake_ncalls); --- a/fs/ext2/namei.c +++ b/fs/ext2/namei.c @@ -327,7 +327,6 @@ static int ext2_rename (struct inode * o new_de = ext2_find_entry (new_dir, &new_dentry->d_name, &new_page); if (!new_de) goto out_dir; - inode_inc_link_count(old_inode); ext2_set_link(new_dir, new_de, new_page, old_inode, 1); new_inode->i_ctime = CURRENT_TIME_SEC; if (dir_de) @@ -339,12 +338,9 @@ static int ext2_rename (struct inode * o if (new_dir->i_nlink >= EXT2_LINK_MAX) goto out_dir; } - inode_inc_link_count(old_inode); err = ext2_add_link(new_dentry, old_inode); - if (err) { - inode_dec_link_count(old_inode); + if (err) goto out_dir; - } if (dir_de) inode_inc_link_count(new_dir); } @@ -352,12 +348,11 @@ static int ext2_rename (struct inode * o /* * Like most other Unix systems, set the ctime for inodes on a * rename. - * inode_dec_link_count() will mark the inode dirty. */ old_inode->i_ctime = CURRENT_TIME_SEC; + mark_inode_dirty(old_inode); ext2_delete_entry (old_de, old_page); - inode_dec_link_count(old_inode); if (dir_de) { if (old_dir != new_dir) --- a/fs/file_table.c +++ b/fs/file_table.c @@ -121,13 +121,13 @@ struct file *get_empty_filp(void) goto fail; percpu_counter_inc(&nr_files); + f->f_cred = get_cred(cred); if (security_file_alloc(f)) goto fail_sec; INIT_LIST_HEAD(&f->f_u.fu_list); atomic_long_set(&f->f_count, 1); rwlock_init(&f->f_owner.lock); - f->f_cred = get_cred(cred); spin_lock_init(&f->f_lock); eventpoll_init_file(f); /* f->f_version: 0 */ --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -86,18 +86,52 @@ struct fuse_file *fuse_file_get(struct f return ff; } +static void fuse_release_async(struct work_struct *work) +{ + struct fuse_req *req; + struct fuse_conn *fc; + struct path path; + + req = container_of(work, struct fuse_req, misc.release.work); + path = req->misc.release.path; + fc = get_fuse_conn(path.dentry->d_inode); + + fuse_put_request(fc, req); + path_put(&path); +} + static void fuse_release_end(struct fuse_conn *fc, struct fuse_req *req) { - path_put(&req->misc.release.path); + if (fc->destroy_req) { + /* + * If this is a fuseblk mount, then it's possible that + * releasing the path will result in releasing the + * super block and sending the DESTROY request. If + * the server is single threaded, this would hang. + * For this reason do the path_put() in a separate + * thread. + */ + atomic_inc(&req->count); + INIT_WORK(&req->misc.release.work, fuse_release_async); + schedule_work(&req->misc.release.work); + } else { + path_put(&req->misc.release.path); + } } -static void fuse_file_put(struct fuse_file *ff) +static void fuse_file_put(struct fuse_file *ff, bool sync) { if (atomic_dec_and_test(&ff->count)) { struct fuse_req *req = ff->reserved_req; - req->end = fuse_release_end; - fuse_request_send_background(ff->fc, req); + if (sync) { + fuse_request_send(ff->fc, req); + path_put(&req->misc.release.path); + fuse_put_request(ff->fc, req); + } else { + req->end = fuse_release_end; + fuse_request_send_background(ff->fc, req); + } kfree(ff); } } @@ -219,8 +253,12 @@ void fuse_release_common(struct file *fi * Normally this will send the RELEASE request, however if * some asynchronous READ or WRITE requests are outstanding, * the sending will be delayed. + * + * Make the release synchronous if this is a fuseblk mount, + * synchronous RELEASE is allowed (and desirable) in this case + * because the server can be trusted not to screw up. */ - fuse_file_put(ff); + fuse_file_put(ff, ff->fc->destroy_req != NULL); } static int fuse_open(struct inode *inode, struct file *file) @@ -549,7 +587,7 @@ static void fuse_readpages_end(struct fu unlock_page(page); } if (req->ff) - fuse_file_put(req->ff); + fuse_file_put(req->ff, false); } static void fuse_send_readpages(struct fuse_req *req, struct file *file) @@ -1129,7 +1167,7 @@ static ssize_t fuse_direct_write(struct static void fuse_writepage_free(struct fuse_conn *fc, struct fuse_req *req) { __free_page(req->pages[0]); - fuse_file_put(req->ff); + fuse_file_put(req->ff, false); } static void fuse_writepage_finish(struct fuse_conn *fc, struct fuse_req *req) --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -21,6 +21,7 @@ #include #include #include +#include /** Max number of pages that can be used in a single read request */ #define FUSE_MAX_PAGES_PER_REQ 32 @@ -254,7 +255,10 @@ struct fuse_req { union { struct fuse_forget_in forget_in; struct { - struct fuse_release_in in; + union { + struct fuse_release_in in; + struct work_struct work; + }; struct path path; } release; struct fuse_init_in init_in; --- a/fs/gfs2/bmap.c +++ b/fs/gfs2/bmap.c @@ -541,7 +541,7 @@ static int gfs2_bmap_alloc(struct inode *ptr++ = cpu_to_be64(bn++); break; } - } while (state != ALLOC_DATA); + } while ((state != ALLOC_DATA) || !dblock); ip->i_height = height; gfs2_add_inode_blocks(&ip->i_inode, alloced); --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -401,15 +401,18 @@ static ssize_t nfs_direct_read_schedule_ pos += vec->iov_len; } + /* + * If no bytes were started, return the error, and let the + * generic layer handle the completion. + */ + if (requested_bytes == 0) { + nfs_direct_req_release(dreq); + return result < 0 ? result : -EIO; + } + if (put_dreq(dreq)) nfs_direct_complete(dreq); - - if (requested_bytes != 0) - return 0; - - if (result < 0) - return result; - return -EIO; + return 0; } static ssize_t nfs_direct_read(struct kiocb *iocb, const struct iovec *iov, @@ -829,15 +832,18 @@ static ssize_t nfs_direct_write_schedule pos += vec->iov_len; } + /* + * If no bytes were started, return the error, and let the + * generic layer handle the completion. + */ + if (requested_bytes == 0) { + nfs_direct_req_release(dreq); + return result < 0 ? result : -EIO; + } + if (put_dreq(dreq)) nfs_direct_write_complete(dreq, dreq->inode); - - if (requested_bytes != 0) - return 0; - - if (result < 0) - return result; - return -EIO; + return 0; } static ssize_t nfs_direct_write(struct kiocb *iocb, const struct iovec *iov, --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -220,7 +220,7 @@ static int nfs_do_fsync(struct nfs_open_ have_error |= test_bit(NFS_CONTEXT_ERROR_WRITE, &ctx->flags); if (have_error) ret = xchg(&ctx->error, 0); - if (!ret) + if (!ret && status < 0) ret = status; return ret; } --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -323,8 +323,8 @@ nfsd4_decode_fattr(struct nfsd4_compound READ_BUF(dummy32); len += (XDR_QUADLEN(dummy32) << 2); READMEM(buf, dummy32); - if ((host_err = nfsd_map_name_to_uid(argp->rqstp, buf, dummy32, &iattr->ia_uid))) - goto out_nfserr; + if ((status = nfsd_map_name_to_uid(argp->rqstp, buf, dummy32, &iattr->ia_uid))) + return status; iattr->ia_valid |= ATTR_UID; } if (bmval[1] & FATTR4_WORD1_OWNER_GROUP) { @@ -334,8 +334,8 @@ nfsd4_decode_fattr(struct nfsd4_compound READ_BUF(dummy32); len += (XDR_QUADLEN(dummy32) << 2); READMEM(buf, dummy32); - if ((host_err = nfsd_map_name_to_gid(argp->rqstp, buf, dummy32, &iattr->ia_gid))) - goto out_nfserr; + if ((status = nfsd_map_name_to_gid(argp->rqstp, buf, dummy32, &iattr->ia_gid))) + return status; iattr->ia_valid |= ATTR_GID; } if (bmval[1] & FATTR4_WORD1_TIME_ACCESS_SET) { --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -823,7 +823,7 @@ nfsd_get_raparms(dev_t dev, ino_t ino) if (ra->p_count == 0) frap = rap; } - depth = nfsdstats.ra_size*11/10; + depth = nfsdstats.ra_size; if (!frap) { spin_unlock(&rab->pb_lock); return NULL; --- a/fs/ocfs2/refcounttree.c +++ b/fs/ocfs2/refcounttree.c @@ -3236,7 +3236,7 @@ static int ocfs2_make_clusters_writable( u32 num_clusters, unsigned int e_flags) { int ret, delete, index, credits = 0; - u32 new_bit, new_len; + u32 new_bit, new_len, orig_num_clusters; unsigned int set_len; struct ocfs2_super *osb = OCFS2_SB(sb); handle_t *handle; @@ -3269,6 +3269,8 @@ static int ocfs2_make_clusters_writable( goto out; } + orig_num_clusters = num_clusters; + while (num_clusters) { ret = ocfs2_get_refcount_rec(ref_ci, context->ref_root_bh, p_cluster, num_clusters, @@ -3356,7 +3358,8 @@ static int ocfs2_make_clusters_writable( * in write-back mode. */ if (context->get_clusters == ocfs2_di_get_clusters) { - ret = ocfs2_cow_sync_writeback(sb, context, cpos, num_clusters); + ret = ocfs2_cow_sync_writeback(sb, context, cpos, + orig_num_clusters); if (ret) mlog_errno(ret); } --- a/fs/ocfs2/stack_user.c +++ b/fs/ocfs2/stack_user.c @@ -191,7 +191,7 @@ static struct ocfs2_live_connection *ocf return c; } - return c; + return NULL; } /* --- a/fs/partitions/ldm.c +++ b/fs/partitions/ldm.c @@ -251,6 +251,11 @@ static bool ldm_parse_vmdb (const u8 *da } vm->vblk_size = get_unaligned_be32(data + 0x08); + if (vm->vblk_size == 0) { + ldm_error ("Illegal VBLK size"); + return false; + } + vm->vblk_offset = get_unaligned_be32(data + 0x0C); vm->last_vblk_seq = get_unaligned_be32(data + 0x04); --- a/fs/partitions/mac.c +++ b/fs/partitions/mac.c @@ -29,10 +29,9 @@ static inline void mac_fix_string(char * int mac_partition(struct parsed_partitions *state, struct block_device *bdev) { - int slot = 1; Sector sect; unsigned char *data; - int blk, blocks_in_map; + int slot, blocks_in_map; unsigned secsize; #ifdef CONFIG_PPC_PMAC int found_root = 0; @@ -59,10 +58,14 @@ int mac_partition(struct parsed_partitio put_dev_sector(sect); return 0; /* not a MacOS disk */ } - printk(" [mac]"); blocks_in_map = be32_to_cpu(part->map_count); - for (blk = 1; blk <= blocks_in_map; ++blk) { - int pos = blk * secsize; + if (blocks_in_map < 0 || blocks_in_map >= DISK_MAX_PARTS) { + put_dev_sector(sect); + return 0; + } + printk(" [mac]"); + for (slot = 1; slot <= blocks_in_map; ++slot) { + int pos = slot * secsize; put_dev_sector(sect); data = read_dev_sector(bdev, pos/512, §); if (!data) @@ -113,13 +116,11 @@ int mac_partition(struct parsed_partitio } if (goodness > found_root_goodness) { - found_root = blk; + found_root = slot; found_root_goodness = goodness; } } #endif /* CONFIG_PPC_PMAC */ - - ++slot; } #ifdef CONFIG_PPC_PMAC if (found_root_goodness) --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -172,7 +172,7 @@ static inline void task_state(struct seq if (tracer) tpid = task_pid_nr_ns(tracer, ns); } - cred = get_cred((struct cred *) __task_cred(p)); + cred = get_task_cred(p); seq_printf(m, "State:\t%s\n" "Tgid:\t%d\n" @@ -336,9 +336,6 @@ int proc_pid_status(struct seq_file *m, task_sig(m, task); task_cap(m, task); cpuset_task_status_allowed(m, task); -#if defined(CONFIG_S390) - task_show_regs(m, task); -#endif task_context_switch_counts(m, task); return 0; } --- a/fs/read_write.c +++ b/fs/read_write.c @@ -826,8 +826,6 @@ static ssize_t do_sendfile(int out_fd, i if (!(out_file->f_mode & FMODE_WRITE)) goto fput_out; retval = -EINVAL; - if (!out_file->f_op || !out_file->f_op->sendpage) - goto fput_out; in_inode = in_file->f_path.dentry->d_inode; out_inode = out_file->f_path.dentry->d_inode; retval = rw_verify_area(WRITE, out_file, &out_file->f_pos, count); --- a/fs/splice.c +++ b/fs/splice.c @@ -638,9 +638,11 @@ static int pipe_to_sendpage(struct pipe_ ret = buf->ops->confirm(pipe, buf); if (!ret) { more = (sd->flags & SPLICE_F_MORE) || sd->len < sd->total_len; - - ret = file->f_op->sendpage(file, buf->page, buf->offset, - sd->len, &pos, more); + if (file->f_op && file->f_op->sendpage) + ret = file->f_op->sendpage(file, buf->page, buf->offset, + sd->len, &pos, more); + else + ret = -EINVAL; } return ret; @@ -1058,8 +1060,9 @@ static long do_splice_from(struct pipe_i if (unlikely(ret < 0)) return ret; - splice_write = out->f_op->splice_write; - if (!splice_write) + if (out->f_op && out->f_op->splice_write) + splice_write = out->f_op->splice_write; + else splice_write = default_file_splice_write; return splice_write(pipe, out, ppos, len, flags); @@ -1083,8 +1086,9 @@ static long do_splice_to(struct file *in if (unlikely(ret < 0)) return ret; - splice_read = in->f_op->splice_read; - if (!splice_read) + if (in->f_op && in->f_op->splice_read) + splice_read = in->f_op->splice_read; + else splice_read = default_file_splice_read; return splice_read(in, ppos, pipe, len, flags); @@ -1306,7 +1310,8 @@ static long do_splice(struct file *in, l if (off_in) return -ESPIPE; if (off_out) { - if (out->f_op->llseek == no_llseek) + if (!out->f_op || !out->f_op->llseek || + out->f_op->llseek == no_llseek) return -EINVAL; if (copy_from_user(&offset, off_out, sizeof(loff_t))) return -EFAULT; @@ -1326,7 +1331,8 @@ static long do_splice(struct file *in, l if (off_out) return -ESPIPE; if (off_in) { - if (in->f_op->llseek == no_llseek) + if (!in->f_op || !in->f_op->llseek || + in->f_op->llseek == no_llseek) return -EINVAL; if (copy_from_user(&offset, off_in, sizeof(loff_t))) return -EFAULT; --- a/fs/xfs/linux-2.6/xfs_export.c +++ b/fs/xfs/linux-2.6/xfs_export.c @@ -127,13 +127,12 @@ xfs_nfs_get_inode( return ERR_PTR(-ESTALE); /* - * The XFS_IGET_BULKSTAT means that an invalid inode number is just - * fine and not an indication of a corrupted filesystem. Because - * clients can send any kind of invalid file handle, e.g. after - * a restore on the server we have to deal with this case gracefully. + * The XFS_IGET_UNTRUSTED means that an invalid inode number is just + * fine and not an indication of a corrupted filesystem as clients can + * send invalid file handles and we have to handle it gracefully.. */ - error = xfs_iget(mp, NULL, ino, XFS_IGET_BULKSTAT, - XFS_ILOCK_SHARED, &ip, 0); + error = xfs_iget(mp, NULL, ino, XFS_IGET_UNTRUSTED, + XFS_ILOCK_SHARED, &ip); if (error) { /* * EINVAL means the inode cluster doesn't exist anymore. --- a/fs/xfs/linux-2.6/xfs_ioctl.c +++ b/fs/xfs/linux-2.6/xfs_ioctl.c @@ -673,10 +673,9 @@ xfs_ioc_bulkstat( error = xfs_bulkstat_single(mp, &inlast, bulkreq.ubuffer, &done); else /* XFS_IOC_FSBULKSTAT */ - error = xfs_bulkstat(mp, &inlast, &count, - (bulkstat_one_pf)xfs_bulkstat_one, NULL, - sizeof(xfs_bstat_t), bulkreq.ubuffer, - BULKSTAT_FG_QUICK, &done); + error = xfs_bulkstat(mp, &inlast, &count, xfs_bulkstat_one, + sizeof(xfs_bstat_t), bulkreq.ubuffer, + &done); if (error) return -error; --- a/fs/xfs/linux-2.6/xfs_ioctl32.c +++ b/fs/xfs/linux-2.6/xfs_ioctl32.c @@ -235,15 +235,12 @@ xfs_bulkstat_one_compat( xfs_ino_t ino, /* inode number to get data for */ void __user *buffer, /* buffer to place output in */ int ubsize, /* size of buffer */ - void *private_data, /* my private data */ - xfs_daddr_t bno, /* starting bno of inode cluster */ int *ubused, /* bytes used by me */ - void *dibuff, /* on-disk inode buffer */ int *stat) /* BULKSTAT_RV_... */ { return xfs_bulkstat_one_int(mp, ino, buffer, ubsize, - xfs_bulkstat_one_fmt_compat, bno, - ubused, dibuff, stat); + xfs_bulkstat_one_fmt_compat, + ubused, stat); } /* copied from xfs_ioctl.c */ @@ -296,13 +293,11 @@ xfs_compat_ioc_bulkstat( int res; error = xfs_bulkstat_one_compat(mp, inlast, bulkreq.ubuffer, - sizeof(compat_xfs_bstat_t), - NULL, 0, NULL, NULL, &res); + sizeof(compat_xfs_bstat_t), 0, &res); } else if (cmd == XFS_IOC_FSBULKSTAT_32) { error = xfs_bulkstat(mp, &inlast, &count, - xfs_bulkstat_one_compat, NULL, - sizeof(compat_xfs_bstat_t), bulkreq.ubuffer, - BULKSTAT_FG_QUICK, &done); + xfs_bulkstat_one_compat, sizeof(compat_xfs_bstat_t), + bulkreq.ubuffer, &done); } else error = XFS_ERROR(EINVAL); if (error) --- a/fs/xfs/quota/xfs_qm.c +++ b/fs/xfs/quota/xfs_qm.c @@ -1606,10 +1606,7 @@ xfs_qm_dqusage_adjust( xfs_ino_t ino, /* inode number to get data for */ void __user *buffer, /* not used */ int ubsize, /* not used */ - void *private_data, /* not used */ - xfs_daddr_t bno, /* starting block of inode cluster */ int *ubused, /* not used */ - void *dip, /* on-disk inode pointer (not used) */ int *res) /* result code value */ { xfs_inode_t *ip; @@ -1634,7 +1631,7 @@ xfs_qm_dqusage_adjust( * the case in all other instances. It's OK that we do this because * quotacheck is done only at mount time. */ - if ((error = xfs_iget(mp, NULL, ino, 0, XFS_ILOCK_EXCL, &ip, bno))) { + if ((error = xfs_iget(mp, NULL, ino, 0, XFS_ILOCK_EXCL, &ip))) { *res = BULKSTAT_RV_NOTHING; return error; } @@ -1766,12 +1763,13 @@ xfs_qm_quotacheck( * Iterate thru all the inodes in the file system, * adjusting the corresponding dquot counters in core. */ - if ((error = xfs_bulkstat(mp, &lastino, &count, - xfs_qm_dqusage_adjust, NULL, - structsz, NULL, BULKSTAT_FG_IGET, &done))) + error = xfs_bulkstat(mp, &lastino, &count, + xfs_qm_dqusage_adjust, + structsz, NULL, &done); + if (error) break; - } while (! done); + } while (!done); /* * We've made all the changes that we need to make incore. @@ -1859,14 +1857,14 @@ xfs_qm_init_quotainos( mp->m_sb.sb_uquotino != NULLFSINO) { ASSERT(mp->m_sb.sb_uquotino > 0); if ((error = xfs_iget(mp, NULL, mp->m_sb.sb_uquotino, - 0, 0, &uip, 0))) + 0, 0, &uip))) return XFS_ERROR(error); } if (XFS_IS_OQUOTA_ON(mp) && mp->m_sb.sb_gquotino != NULLFSINO) { ASSERT(mp->m_sb.sb_gquotino > 0); if ((error = xfs_iget(mp, NULL, mp->m_sb.sb_gquotino, - 0, 0, &gip, 0))) { + 0, 0, &gip))) { if (uip) IRELE(uip); return XFS_ERROR(error); --- a/fs/xfs/quota/xfs_qm_syscalls.c +++ b/fs/xfs/quota/xfs_qm_syscalls.c @@ -266,7 +266,7 @@ xfs_qm_scall_trunc_qfiles( } if ((flags & XFS_DQ_USER) && mp->m_sb.sb_uquotino != NULLFSINO) { - error = xfs_iget(mp, NULL, mp->m_sb.sb_uquotino, 0, 0, &qip, 0); + error = xfs_iget(mp, NULL, mp->m_sb.sb_uquotino, 0, 0, &qip); if (!error) { error = xfs_truncate_file(mp, qip); IRELE(qip); @@ -275,7 +275,7 @@ xfs_qm_scall_trunc_qfiles( if ((flags & (XFS_DQ_GROUP|XFS_DQ_PROJ)) && mp->m_sb.sb_gquotino != NULLFSINO) { - error2 = xfs_iget(mp, NULL, mp->m_sb.sb_gquotino, 0, 0, &qip, 0); + error2 = xfs_iget(mp, NULL, mp->m_sb.sb_gquotino, 0, 0, &qip); if (!error2) { error2 = xfs_truncate_file(mp, qip); IRELE(qip); @@ -420,12 +420,12 @@ xfs_qm_scall_getqstat( } if (!uip && mp->m_sb.sb_uquotino != NULLFSINO) { if (xfs_iget(mp, NULL, mp->m_sb.sb_uquotino, - 0, 0, &uip, 0) == 0) + 0, 0, &uip) == 0) tempuqip = B_TRUE; } if (!gip && mp->m_sb.sb_gquotino != NULLFSINO) { if (xfs_iget(mp, NULL, mp->m_sb.sb_gquotino, - 0, 0, &gip, 0) == 0) + 0, 0, &gip) == 0) tempgqip = B_TRUE; } if (uip) { @@ -1114,10 +1114,7 @@ xfs_qm_internalqcheck_adjust( xfs_ino_t ino, /* inode number to get data for */ void __user *buffer, /* not used */ int ubsize, /* not used */ - void *private_data, /* not used */ - xfs_daddr_t bno, /* starting block of inode cluster */ int *ubused, /* not used */ - void *dip, /* not used */ int *res) /* bulkstat result code */ { xfs_inode_t *ip; @@ -1139,7 +1136,7 @@ xfs_qm_internalqcheck_adjust( ipreleased = B_FALSE; again: lock_flags = XFS_ILOCK_SHARED; - if ((error = xfs_iget(mp, NULL, ino, 0, lock_flags, &ip, bno))) { + if ((error = xfs_iget(mp, NULL, ino, 0, lock_flags, &ip))) { *res = BULKSTAT_RV_NOTHING; return (error); } @@ -1212,15 +1209,15 @@ xfs_qm_internalqcheck( * Iterate thru all the inodes in the file system, * adjusting the corresponding dquot counters */ - if ((error = xfs_bulkstat(mp, &lastino, &count, - xfs_qm_internalqcheck_adjust, NULL, - 0, NULL, BULKSTAT_FG_IGET, &done))) { + error = xfs_bulkstat(mp, &lastino, &count, + xfs_qm_internalqcheck_adjust, + 0, NULL, &done); + if (error) { + cmn_err(CE_DEBUG, "Bulkstat returned error 0x%x", error); break; } - } while (! done); - if (error) { - cmn_err(CE_DEBUG, "Bulkstat returned error 0x%x", error); - } + } while (!done); + cmn_err(CE_DEBUG, "Checking results against system dquots"); for (i = 0; i < qmtest_hashmask; i++) { h1 = &qmtest_udqtab[i]; --- a/fs/xfs/xfs_ialloc.c +++ b/fs/xfs/xfs_ialloc.c @@ -1206,6 +1206,69 @@ error0: return error; } +STATIC int +xfs_imap_lookup( + struct xfs_mount *mp, + struct xfs_trans *tp, + xfs_agnumber_t agno, + xfs_agino_t agino, + xfs_agblock_t agbno, + xfs_agblock_t *chunk_agbno, + xfs_agblock_t *offset_agbno, + int flags) +{ + struct xfs_inobt_rec_incore rec; + struct xfs_btree_cur *cur; + struct xfs_buf *agbp; + int error; + int i; + + down_read(&mp->m_peraglock); + error = xfs_ialloc_read_agi(mp, tp, agno, &agbp); + up_read(&mp->m_peraglock); + if (error) { + xfs_fs_cmn_err(CE_ALERT, mp, "xfs_imap: " + "xfs_ialloc_read_agi() returned " + "error %d, agno %d", + error, agno); + return error; + } + + /* + * Lookup the inode record for the given agino. If the record cannot be + * found, then it's an invalid inode number and we should abort. Once + * we have a record, we need to ensure it contains the inode number + * we are looking up. + */ + cur = xfs_inobt_init_cursor(mp, tp, agbp, agno); + error = xfs_inobt_lookup(cur, agino, XFS_LOOKUP_LE, &i); + if (!error) { + if (i) + error = xfs_inobt_get_rec(cur, &rec, &i); + if (!error && i == 0) + error = EINVAL; + } + + xfs_trans_brelse(tp, agbp); + xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR); + if (error) + return error; + + /* check that the returned record contains the required inode */ + if (rec.ir_startino > agino || + rec.ir_startino + XFS_IALLOC_INODES(mp) <= agino) + return EINVAL; + + /* for untrusted inodes check it is allocated first */ + if ((flags & XFS_IGET_UNTRUSTED) && + (rec.ir_free & XFS_INOBT_MASK(agino - rec.ir_startino))) + return EINVAL; + + *chunk_agbno = XFS_AGINO_TO_AGBNO(mp, rec.ir_startino); + *offset_agbno = agbno - *chunk_agbno; + return 0; +} + /* * Return the location of the inode in imap, for mapping it into a buffer. */ @@ -1238,8 +1301,11 @@ xfs_imap( if (agno >= mp->m_sb.sb_agcount || agbno >= mp->m_sb.sb_agblocks || ino != XFS_AGINO_TO_INO(mp, agno, agino)) { #ifdef DEBUG - /* no diagnostics for bulkstat, ino comes from userspace */ - if (flags & XFS_IGET_BULKSTAT) + /* + * Don't output diagnostic information for untrusted inodes + * as they can be invalid without implying corruption. + */ + if (flags & XFS_IGET_UNTRUSTED) return XFS_ERROR(EINVAL); if (agno >= mp->m_sb.sb_agcount) { xfs_fs_cmn_err(CE_ALERT, mp, @@ -1266,6 +1332,23 @@ xfs_imap( return XFS_ERROR(EINVAL); } + blks_per_cluster = XFS_INODE_CLUSTER_SIZE(mp) >> mp->m_sb.sb_blocklog; + + /* + * For bulkstat and handle lookups, we have an untrusted inode number + * that we have to verify is valid. We cannot do this just by reading + * the inode buffer as it may have been unlinked and removed leaving + * inodes in stale state on disk. Hence we have to do a btree lookup + * in all cases where an untrusted inode number is passed. + */ + if (flags & XFS_IGET_UNTRUSTED) { + error = xfs_imap_lookup(mp, tp, agno, agino, agbno, + &chunk_agbno, &offset_agbno, flags); + if (error) + return error; + goto out_map; + } + /* * If the inode cluster size is the same as the blocksize or * smaller we get to the buffer by simple arithmetics. @@ -1280,24 +1363,6 @@ xfs_imap( return 0; } - blks_per_cluster = XFS_INODE_CLUSTER_SIZE(mp) >> mp->m_sb.sb_blocklog; - - /* - * If we get a block number passed from bulkstat we can use it to - * find the buffer easily. - */ - if (imap->im_blkno) { - offset = XFS_INO_TO_OFFSET(mp, ino); - ASSERT(offset < mp->m_sb.sb_inopblock); - - cluster_agbno = xfs_daddr_to_agbno(mp, imap->im_blkno); - offset += (agbno - cluster_agbno) * mp->m_sb.sb_inopblock; - - imap->im_len = XFS_FSB_TO_BB(mp, blks_per_cluster); - imap->im_boffset = (ushort)(offset << mp->m_sb.sb_inodelog); - return 0; - } - /* * If the inode chunks are aligned then use simple maths to * find the location. Otherwise we have to do a btree @@ -1307,52 +1372,13 @@ xfs_imap( offset_agbno = agbno & mp->m_inoalign_mask; chunk_agbno = agbno - offset_agbno; } else { - xfs_btree_cur_t *cur; /* inode btree cursor */ - xfs_inobt_rec_incore_t chunk_rec; - xfs_buf_t *agbp; /* agi buffer */ - int i; /* temp state */ - - down_read(&mp->m_peraglock); - error = xfs_ialloc_read_agi(mp, tp, agno, &agbp); - up_read(&mp->m_peraglock); - if (error) { - xfs_fs_cmn_err(CE_ALERT, mp, "xfs_imap: " - "xfs_ialloc_read_agi() returned " - "error %d, agno %d", - error, agno); - return error; - } - - cur = xfs_inobt_init_cursor(mp, tp, agbp, agno); - error = xfs_inobt_lookup(cur, agino, XFS_LOOKUP_LE, &i); - if (error) { - xfs_fs_cmn_err(CE_ALERT, mp, "xfs_imap: " - "xfs_inobt_lookup() failed"); - goto error0; - } - - error = xfs_inobt_get_rec(cur, &chunk_rec, &i); - if (error) { - xfs_fs_cmn_err(CE_ALERT, mp, "xfs_imap: " - "xfs_inobt_get_rec() failed"); - goto error0; - } - if (i == 0) { -#ifdef DEBUG - xfs_fs_cmn_err(CE_ALERT, mp, "xfs_imap: " - "xfs_inobt_get_rec() failed"); -#endif /* DEBUG */ - error = XFS_ERROR(EINVAL); - } - error0: - xfs_trans_brelse(tp, agbp); - xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR); + error = xfs_imap_lookup(mp, tp, agno, agino, agbno, + &chunk_agbno, &offset_agbno, flags); if (error) return error; - chunk_agbno = XFS_AGINO_TO_AGBNO(mp, chunk_rec.ir_startino); - offset_agbno = agbno - chunk_agbno; } +out_map: ASSERT(agbno >= chunk_agbno); cluster_agbno = chunk_agbno + ((offset_agbno / blks_per_cluster) * blks_per_cluster); --- a/fs/xfs/xfs_iget.c +++ b/fs/xfs/xfs_iget.c @@ -295,7 +295,6 @@ xfs_iget_cache_miss( xfs_trans_t *tp, xfs_ino_t ino, struct xfs_inode **ipp, - xfs_daddr_t bno, int flags, int lock_flags) __releases(pag->pag_ici_lock) { @@ -308,7 +307,7 @@ xfs_iget_cache_miss( if (!ip) return ENOMEM; - error = xfs_iread(mp, tp, ip, bno, flags); + error = xfs_iread(mp, tp, ip, flags); if (error) goto out_destroy; @@ -392,8 +391,6 @@ out_destroy: * within the file system for the inode being requested. * lock_flags -- flags indicating how to lock the inode. See the comment * for xfs_ilock() for a list of valid values. - * bno -- the block number starting the buffer containing the inode, - * if known (as by bulkstat), else 0. */ int xfs_iget( @@ -402,8 +399,7 @@ xfs_iget( xfs_ino_t ino, uint flags, uint lock_flags, - xfs_inode_t **ipp, - xfs_daddr_t bno) + xfs_inode_t **ipp) { xfs_inode_t *ip; int error; @@ -434,7 +430,7 @@ again: read_unlock(&pag->pag_ici_lock); XFS_STATS_INC(xs_ig_missed); - error = xfs_iget_cache_miss(mp, pag, tp, ino, &ip, bno, + error = xfs_iget_cache_miss(mp, pag, tp, ino, &ip, flags, lock_flags); if (error) goto out_error_or_again; --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -177,7 +177,7 @@ xfs_imap_to_bp( if (unlikely(XFS_TEST_ERROR(!di_ok, mp, XFS_ERRTAG_ITOBP_INOTOBP, XFS_RANDOM_ITOBP_INOTOBP))) { - if (iget_flags & XFS_IGET_BULKSTAT) { + if (iget_flags & XFS_IGET_UNTRUSTED) { xfs_trans_brelse(tp, bp); return XFS_ERROR(EINVAL); } @@ -787,7 +787,6 @@ xfs_iread( xfs_mount_t *mp, xfs_trans_t *tp, xfs_inode_t *ip, - xfs_daddr_t bno, uint iget_flags) { xfs_buf_t *bp; @@ -797,11 +796,9 @@ xfs_iread( /* * Fill in the location information in the in-core inode. */ - ip->i_imap.im_blkno = bno; error = xfs_imap(mp, tp, ip->i_ino, &ip->i_imap, iget_flags); if (error) return error; - ASSERT(bno == 0 || bno == ip->i_imap.im_blkno); /* * Get pointers to the on-disk inode and the buffer containing it. --- a/fs/xfs/xfs_inode.h +++ b/fs/xfs/xfs_inode.h @@ -468,7 +468,7 @@ static inline void xfs_ifunlock(xfs_inod * xfs_iget.c prototypes. */ int xfs_iget(struct xfs_mount *, struct xfs_trans *, xfs_ino_t, - uint, uint, xfs_inode_t **, xfs_daddr_t); + uint, uint, xfs_inode_t **); void xfs_iput(xfs_inode_t *, uint); void xfs_iput_new(xfs_inode_t *, uint); void xfs_ilock(xfs_inode_t *, uint); @@ -558,7 +558,7 @@ do { \ * Flags for xfs_iget() */ #define XFS_IGET_CREATE 0x1 -#define XFS_IGET_BULKSTAT 0x2 +#define XFS_IGET_UNTRUSTED 0x2 int xfs_inotobp(struct xfs_mount *, struct xfs_trans *, xfs_ino_t, struct xfs_dinode **, @@ -567,7 +567,7 @@ int xfs_itobp(struct xfs_mount *, struc struct xfs_inode *, struct xfs_dinode **, struct xfs_buf **, uint); int xfs_iread(struct xfs_mount *, struct xfs_trans *, - struct xfs_inode *, xfs_daddr_t, uint); + struct xfs_inode *, uint); void xfs_dinode_to_disk(struct xfs_dinode *, struct xfs_icdinode *); void xfs_idestroy_fork(struct xfs_inode *, int); --- a/fs/xfs/xfs_itable.c +++ b/fs/xfs/xfs_itable.c @@ -49,24 +49,40 @@ xfs_internal_inum( (ino == mp->m_sb.sb_uquotino || ino == mp->m_sb.sb_gquotino))); } -STATIC int -xfs_bulkstat_one_iget( - xfs_mount_t *mp, /* mount point for filesystem */ - xfs_ino_t ino, /* inode number to get data for */ - xfs_daddr_t bno, /* starting bno of inode cluster */ - xfs_bstat_t *buf, /* return buffer */ - int *stat) /* BULKSTAT_RV_... */ +/* + * Return stat information for one inode. + * Return 0 if ok, else errno. + */ +int +xfs_bulkstat_one_int( + struct xfs_mount *mp, /* mount point for filesystem */ + xfs_ino_t ino, /* inode to get data for */ + void __user *buffer, /* buffer to place output in */ + int ubsize, /* size of buffer */ + bulkstat_one_fmt_pf formatter, /* formatter, copy to user */ + int *ubused, /* bytes used by me */ + int *stat) /* BULKSTAT_RV_... */ { - xfs_icdinode_t *dic; /* dinode core info pointer */ - xfs_inode_t *ip; /* incore inode pointer */ - struct inode *inode; - int error; + struct xfs_icdinode *dic; /* dinode core info pointer */ + struct xfs_inode *ip; /* incore inode pointer */ + struct inode *inode; + struct xfs_bstat *buf; /* return buffer */ + int error = 0; /* error value */ + + *stat = BULKSTAT_RV_NOTHING; + + if (!buffer || xfs_internal_inum(mp, ino)) + return XFS_ERROR(EINVAL); + + buf = kmem_alloc(sizeof(*buf), KM_SLEEP | KM_MAYFAIL); + if (!buf) + return XFS_ERROR(ENOMEM); error = xfs_iget(mp, NULL, ino, - XFS_IGET_BULKSTAT, XFS_ILOCK_SHARED, &ip, bno); + XFS_IGET_UNTRUSTED, XFS_ILOCK_SHARED, &ip); if (error) { *stat = BULKSTAT_RV_NOTHING; - return error; + goto out_free; } ASSERT(ip != NULL); @@ -126,76 +142,16 @@ xfs_bulkstat_one_iget( buf->bs_blocks = dic->di_nblocks + ip->i_delayed_blks; break; } - xfs_iput(ip, XFS_ILOCK_SHARED); - return error; -} -STATIC void -xfs_bulkstat_one_dinode( - xfs_mount_t *mp, /* mount point for filesystem */ - xfs_ino_t ino, /* inode number to get data for */ - xfs_dinode_t *dic, /* dinode inode pointer */ - xfs_bstat_t *buf) /* return buffer */ -{ - /* - * The inode format changed when we moved the link count and - * made it 32 bits long. If this is an old format inode, - * convert it in memory to look like a new one. If it gets - * flushed to disk we will convert back before flushing or - * logging it. We zero out the new projid field and the old link - * count field. We'll handle clearing the pad field (the remains - * of the old uuid field) when we actually convert the inode to - * the new format. We don't change the version number so that we - * can distinguish this from a real new format inode. - */ - if (dic->di_version == 1) { - buf->bs_nlink = be16_to_cpu(dic->di_onlink); - buf->bs_projid = 0; - } else { - buf->bs_nlink = be32_to_cpu(dic->di_nlink); - buf->bs_projid = be16_to_cpu(dic->di_projid); - } + error = formatter(buffer, ubsize, ubused, buf); - buf->bs_ino = ino; - buf->bs_mode = be16_to_cpu(dic->di_mode); - buf->bs_uid = be32_to_cpu(dic->di_uid); - buf->bs_gid = be32_to_cpu(dic->di_gid); - buf->bs_size = be64_to_cpu(dic->di_size); - buf->bs_atime.tv_sec = be32_to_cpu(dic->di_atime.t_sec); - buf->bs_atime.tv_nsec = be32_to_cpu(dic->di_atime.t_nsec); - buf->bs_mtime.tv_sec = be32_to_cpu(dic->di_mtime.t_sec); - buf->bs_mtime.tv_nsec = be32_to_cpu(dic->di_mtime.t_nsec); - buf->bs_ctime.tv_sec = be32_to_cpu(dic->di_ctime.t_sec); - buf->bs_ctime.tv_nsec = be32_to_cpu(dic->di_ctime.t_nsec); - buf->bs_xflags = xfs_dic2xflags(dic); - buf->bs_extsize = be32_to_cpu(dic->di_extsize) << mp->m_sb.sb_blocklog; - buf->bs_extents = be32_to_cpu(dic->di_nextents); - buf->bs_gen = be32_to_cpu(dic->di_gen); - memset(buf->bs_pad, 0, sizeof(buf->bs_pad)); - buf->bs_dmevmask = be32_to_cpu(dic->di_dmevmask); - buf->bs_dmstate = be16_to_cpu(dic->di_dmstate); - buf->bs_aextents = be16_to_cpu(dic->di_anextents); + if (!error) + *stat = BULKSTAT_RV_DIDONE; - switch (dic->di_format) { - case XFS_DINODE_FMT_DEV: - buf->bs_rdev = xfs_dinode_get_rdev(dic); - buf->bs_blksize = BLKDEV_IOSIZE; - buf->bs_blocks = 0; - break; - case XFS_DINODE_FMT_LOCAL: - case XFS_DINODE_FMT_UUID: - buf->bs_rdev = 0; - buf->bs_blksize = mp->m_sb.sb_blocksize; - buf->bs_blocks = 0; - break; - case XFS_DINODE_FMT_EXTENTS: - case XFS_DINODE_FMT_BTREE: - buf->bs_rdev = 0; - buf->bs_blksize = mp->m_sb.sb_blocksize; - buf->bs_blocks = be64_to_cpu(dic->di_nblocks); - break; - } + out_free: + kmem_free(buf); + return error; } /* Return 0 on success or positive error */ @@ -215,118 +171,17 @@ xfs_bulkstat_one_fmt( return 0; } -/* - * Return stat information for one inode. - * Return 0 if ok, else errno. - */ -int /* error status */ -xfs_bulkstat_one_int( - xfs_mount_t *mp, /* mount point for filesystem */ - xfs_ino_t ino, /* inode number to get data for */ - void __user *buffer, /* buffer to place output in */ - int ubsize, /* size of buffer */ - bulkstat_one_fmt_pf formatter, /* formatter, copy to user */ - xfs_daddr_t bno, /* starting bno of inode cluster */ - int *ubused, /* bytes used by me */ - void *dibuff, /* on-disk inode buffer */ - int *stat) /* BULKSTAT_RV_... */ -{ - xfs_bstat_t *buf; /* return buffer */ - int error = 0; /* error value */ - xfs_dinode_t *dip; /* dinode inode pointer */ - - dip = (xfs_dinode_t *)dibuff; - *stat = BULKSTAT_RV_NOTHING; - - if (!buffer || xfs_internal_inum(mp, ino)) - return XFS_ERROR(EINVAL); - - buf = kmem_alloc(sizeof(*buf), KM_SLEEP); - - if (dip == NULL) { - /* We're not being passed a pointer to a dinode. This happens - * if BULKSTAT_FG_IGET is selected. Do the iget. - */ - error = xfs_bulkstat_one_iget(mp, ino, bno, buf, stat); - if (error) - goto out_free; - } else { - xfs_bulkstat_one_dinode(mp, ino, dip, buf); - } - - error = formatter(buffer, ubsize, ubused, buf); - if (error) - goto out_free; - - *stat = BULKSTAT_RV_DIDONE; - - out_free: - kmem_free(buf); - return error; -} - int xfs_bulkstat_one( xfs_mount_t *mp, /* mount point for filesystem */ xfs_ino_t ino, /* inode number to get data for */ void __user *buffer, /* buffer to place output in */ int ubsize, /* size of buffer */ - void *private_data, /* my private data */ - xfs_daddr_t bno, /* starting bno of inode cluster */ int *ubused, /* bytes used by me */ - void *dibuff, /* on-disk inode buffer */ int *stat) /* BULKSTAT_RV_... */ { return xfs_bulkstat_one_int(mp, ino, buffer, ubsize, - xfs_bulkstat_one_fmt, bno, - ubused, dibuff, stat); -} - -/* - * Test to see whether we can use the ondisk inode directly, based - * on the given bulkstat flags, filling in dipp accordingly. - * Returns zero if the inode is dodgey. - */ -STATIC int -xfs_bulkstat_use_dinode( - xfs_mount_t *mp, - int flags, - xfs_buf_t *bp, - int clustidx, - xfs_dinode_t **dipp) -{ - xfs_dinode_t *dip; - unsigned int aformat; - - *dipp = NULL; - if (!bp || (flags & BULKSTAT_FG_IGET)) - return 1; - dip = (xfs_dinode_t *) - xfs_buf_offset(bp, clustidx << mp->m_sb.sb_inodelog); - /* - * Check the buffer containing the on-disk inode for di_mode == 0. - * This is to prevent xfs_bulkstat from picking up just reclaimed - * inodes that have their in-core state initialized but not flushed - * to disk yet. This is a temporary hack that would require a proper - * fix in the future. - */ - if (be16_to_cpu(dip->di_magic) != XFS_DINODE_MAGIC || - !XFS_DINODE_GOOD_VERSION(dip->di_version) || - !dip->di_mode) - return 0; - if (flags & BULKSTAT_FG_QUICK) { - *dipp = dip; - return 1; - } - /* BULKSTAT_FG_INLINE: if attr fork is local, or not there, use it */ - aformat = dip->di_aformat; - if ((XFS_DFORK_Q(dip) == 0) || - (aformat == XFS_DINODE_FMT_LOCAL) || - (aformat == XFS_DINODE_FMT_EXTENTS && !dip->di_anextents)) { - *dipp = dip; - return 1; - } - return 1; + xfs_bulkstat_one_fmt, ubused, stat); } #define XFS_BULKSTAT_UBLEFT(ubleft) ((ubleft) >= statstruct_size) @@ -340,10 +195,8 @@ xfs_bulkstat( xfs_ino_t *lastinop, /* last inode returned */ int *ubcountp, /* size of buffer/count returned */ bulkstat_one_pf formatter, /* func that'd fill a single buf */ - void *private_data,/* private data for formatter */ size_t statstruct_size, /* sizeof struct filling */ char __user *ubuffer, /* buffer with inode stats */ - int flags, /* defined in xfs_itable.h */ int *done) /* 1 if there are more stats to get */ { xfs_agblock_t agbno=0;/* allocation group block number */ @@ -378,14 +231,12 @@ xfs_bulkstat( int ubelem; /* spaces used in user's buffer */ int ubused; /* bytes used by formatter */ xfs_buf_t *bp; /* ptr to on-disk inode cluster buf */ - xfs_dinode_t *dip; /* ptr into bp for specific inode */ /* * Get the last inode value, see if there's nothing to do. */ ino = (xfs_ino_t)*lastinop; lastino = ino; - dip = NULL; agno = XFS_INO_TO_AGNO(mp, ino); agino = XFS_INO_TO_AGINO(mp, ino); if (agno >= mp->m_sb.sb_agcount || @@ -610,37 +461,6 @@ xfs_bulkstat( irbp->ir_startino) + ((chunkidx & nimask) >> mp->m_sb.sb_inopblog); - - if (flags & (BULKSTAT_FG_QUICK | - BULKSTAT_FG_INLINE)) { - int offset; - - ino = XFS_AGINO_TO_INO(mp, agno, - agino); - bno = XFS_AGB_TO_DADDR(mp, agno, - agbno); - - /* - * Get the inode cluster buffer - */ - if (bp) - xfs_buf_relse(bp); - - error = xfs_inotobp(mp, NULL, ino, &dip, - &bp, &offset, - XFS_IGET_BULKSTAT); - - if (!error) - clustidx = offset / mp->m_sb.sb_inodesize; - if (XFS_TEST_ERROR(error != 0, - mp, XFS_ERRTAG_BULKSTAT_READ_CHUNK, - XFS_RANDOM_BULKSTAT_READ_CHUNK)) { - bp = NULL; - ubleft = 0; - rval = error; - break; - } - } } ino = XFS_AGINO_TO_INO(mp, agno, agino); bno = XFS_AGB_TO_DADDR(mp, agno, agbno); @@ -656,35 +476,13 @@ xfs_bulkstat( * when the chunk is used up. */ irbp->ir_freecount++; - if (!xfs_bulkstat_use_dinode(mp, flags, bp, - clustidx, &dip)) { - lastino = ino; - continue; - } - /* - * If we need to do an iget, cannot hold bp. - * Drop it, until starting the next cluster. - */ - if ((flags & BULKSTAT_FG_INLINE) && !dip) { - if (bp) - xfs_buf_relse(bp); - bp = NULL; - } /* * Get the inode and fill in a single buffer. - * BULKSTAT_FG_QUICK uses dip to fill it in. - * BULKSTAT_FG_IGET uses igets. - * BULKSTAT_FG_INLINE uses dip if we have an - * inline attr fork, else igets. - * See: xfs_bulkstat_one & xfs_dm_bulkstat_one. - * This is also used to count inodes/blks, etc - * in xfs_qm_quotacheck. */ ubused = statstruct_size; - error = formatter(mp, ino, ubufp, - ubleft, private_data, - bno, &ubused, dip, &fmterror); + error = formatter(mp, ino, ubufp, ubleft, + &ubused, &fmterror); if (fmterror == BULKSTAT_RV_NOTHING) { if (error && error != ENOENT && error != EINVAL) { @@ -776,8 +574,7 @@ xfs_bulkstat_single( */ ino = (xfs_ino_t)*lastinop; - error = xfs_bulkstat_one(mp, ino, buffer, sizeof(xfs_bstat_t), - NULL, 0, NULL, NULL, &res); + error = xfs_bulkstat_one(mp, ino, buffer, sizeof(xfs_bstat_t), 0, &res); if (error) { /* * Special case way failed, do it the "long" way @@ -786,8 +583,7 @@ xfs_bulkstat_single( (*lastinop)--; count = 1; if (xfs_bulkstat(mp, lastinop, &count, xfs_bulkstat_one, - NULL, sizeof(xfs_bstat_t), buffer, - BULKSTAT_FG_IGET, done)) + sizeof(xfs_bstat_t), buffer, done)) return error; if (count == 0 || (xfs_ino_t)*lastinop != ino) return error == EFSCORRUPTED ? --- a/fs/xfs/xfs_itable.h +++ b/fs/xfs/xfs_itable.h @@ -27,10 +27,7 @@ typedef int (*bulkstat_one_pf)(struct xf xfs_ino_t ino, void __user *buffer, int ubsize, - void *private_data, - xfs_daddr_t bno, int *ubused, - void *dip, int *stat); /* @@ -41,13 +38,6 @@ typedef int (*bulkstat_one_pf)(struct xf #define BULKSTAT_RV_GIVEUP 2 /* - * Values for bulkstat flag argument. - */ -#define BULKSTAT_FG_IGET 0x1 /* Go through the buffer cache */ -#define BULKSTAT_FG_QUICK 0x2 /* No iget, walk the dinode cluster */ -#define BULKSTAT_FG_INLINE 0x4 /* No iget if inline attrs */ - -/* * Return stat information in bulk (by-inode) for the filesystem. */ int /* error status */ @@ -56,10 +46,8 @@ xfs_bulkstat( xfs_ino_t *lastino, /* last inode returned */ int *count, /* size of buffer/count returned */ bulkstat_one_pf formatter, /* func that'd fill a single buf */ - void *private_data, /* private data for formatter */ size_t statstruct_size,/* sizeof struct that we're filling */ char __user *ubuffer,/* buffer with inode stats */ - int flags, /* flag to control access method */ int *done); /* 1 if there are more stats to get */ int @@ -82,9 +70,7 @@ xfs_bulkstat_one_int( void __user *buffer, int ubsize, bulkstat_one_fmt_pf formatter, - xfs_daddr_t bno, int *ubused, - void *dibuff, int *stat); int @@ -93,10 +79,7 @@ xfs_bulkstat_one( xfs_ino_t ino, void __user *buffer, int ubsize, - void *private_data, - xfs_daddr_t bno, int *ubused, - void *dibuff, int *stat); typedef int (*inumbers_fmt_pf)( --- a/fs/xfs/xfs_log_recover.c +++ b/fs/xfs/xfs_log_recover.c @@ -3209,7 +3209,7 @@ xlog_recover_process_one_iunlink( int error; ino = XFS_AGINO_TO_INO(mp, agno, agino); - error = xfs_iget(mp, NULL, ino, 0, 0, &ip, 0); + error = xfs_iget(mp, NULL, ino, 0, 0, &ip); if (error) goto fail; --- a/fs/xfs/xfs_mount.c +++ b/fs/xfs/xfs_mount.c @@ -1207,7 +1207,7 @@ xfs_mountfs( * Get and sanity-check the root inode. * Save the pointer to it in the mount structure. */ - error = xfs_iget(mp, NULL, sbp->sb_rootino, 0, XFS_ILOCK_EXCL, &rip, 0); + error = xfs_iget(mp, NULL, sbp->sb_rootino, 0, XFS_ILOCK_EXCL, &rip); if (error) { cmn_err(CE_WARN, "XFS: failed to read root inode"); goto out_log_dealloc; --- a/fs/xfs/xfs_rtalloc.c +++ b/fs/xfs/xfs_rtalloc.c @@ -2274,12 +2274,12 @@ xfs_rtmount_inodes( sbp = &mp->m_sb; if (sbp->sb_rbmino == NULLFSINO) return 0; - error = xfs_iget(mp, NULL, sbp->sb_rbmino, 0, 0, &mp->m_rbmip, 0); + error = xfs_iget(mp, NULL, sbp->sb_rbmino, 0, 0, &mp->m_rbmip); if (error) return error; ASSERT(mp->m_rbmip != NULL); ASSERT(sbp->sb_rsumino != NULLFSINO); - error = xfs_iget(mp, NULL, sbp->sb_rsumino, 0, 0, &mp->m_rsumip, 0); + error = xfs_iget(mp, NULL, sbp->sb_rsumino, 0, 0, &mp->m_rsumip); if (error) { IRELE(mp->m_rbmip); return error; --- a/fs/xfs/xfs_trans_inode.c +++ b/fs/xfs/xfs_trans_inode.c @@ -62,7 +62,7 @@ xfs_trans_iget( { int error; - error = xfs_iget(mp, tp, ino, flags, lock_flags, ipp, 0); + error = xfs_iget(mp, tp, ino, flags, lock_flags, ipp); if (!error && tp) xfs_trans_ijoin(tp, *ipp, lock_flags); return error; --- a/fs/xfs/xfs_vnodeops.c +++ b/fs/xfs/xfs_vnodeops.c @@ -1371,7 +1371,7 @@ xfs_lookup( if (error) goto out; - error = xfs_iget(dp->i_mount, NULL, inum, 0, 0, ipp, 0); + error = xfs_iget(dp->i_mount, NULL, inum, 0, 0, ipp); if (error) goto out_free_name; --- a/include/drm/drmP.h +++ b/include/drm/drmP.h @@ -1016,7 +1016,7 @@ struct drm_device { struct pci_controller *hose; #endif struct drm_sg_mem *sg; /**< Scatter gather memory */ - int num_crtcs; /**< Number of CRTCs on this device */ + unsigned int num_crtcs; /**< Number of CRTCs on this device */ void *dev_private; /**< device private data */ void *mm_private; struct address_space *dev_mapping; --- a/include/drm/drm_pciids.h +++ b/include/drm/drm_pciids.h @@ -28,7 +28,6 @@ {0x1002, 0x4156, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV350}, \ {0x1002, 0x4237, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RS200|RADEON_IS_IGP}, \ {0x1002, 0x4242, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_R200}, \ - {0x1002, 0x4243, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_R200}, \ {0x1002, 0x4336, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RS100|RADEON_IS_IGP|RADEON_IS_MOBILITY}, \ {0x1002, 0x4337, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RS200|RADEON_IS_IGP|RADEON_IS_MOBILITY}, \ {0x1002, 0x4437, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RS200|RADEON_IS_IGP|RADEON_IS_MOBILITY}, \ --- a/include/linux/cred.h +++ b/include/linux/cred.h @@ -153,6 +153,7 @@ struct cred { extern void __put_cred(struct cred *); extern void exit_creds(struct task_struct *); extern int copy_creds(struct task_struct *, unsigned long); +extern const struct cred *get_task_cred(struct task_struct *); extern struct cred *cred_alloc_blank(void); extern struct cred *prepare_creds(void); extern struct cred *prepare_exec_creds(void); @@ -283,26 +284,6 @@ static inline void put_cred(const struct ((const struct cred *)(rcu_dereference((task)->real_cred))) /** - * get_task_cred - Get another task's objective credentials - * @task: The task to query - * - * Get the objective credentials of a task, pinning them so that they can't go - * away. Accessing a task's credentials directly is not permitted. - * - * The caller must make sure task doesn't go away, either by holding a ref on - * task or by holding tasklist_lock to prevent it from being unlinked. - */ -#define get_task_cred(task) \ -({ \ - struct cred *__cred; \ - rcu_read_lock(); \ - __cred = (struct cred *) __task_cred((task)); \ - get_cred(__cred); \ - rcu_read_unlock(); \ - __cred; \ -}) - -/** * get_current_cred - Get the current task's subjective credentials * * Get the subjective credentials of the current task, pinning them so that --- a/include/linux/hardirq.h +++ b/include/linux/hardirq.h @@ -64,6 +64,8 @@ #define HARDIRQ_OFFSET (1UL << HARDIRQ_SHIFT) #define NMI_OFFSET (1UL << NMI_SHIFT) +#define SOFTIRQ_DISABLE_OFFSET (2 * SOFTIRQ_OFFSET) + #ifndef PREEMPT_ACTIVE #define PREEMPT_ACTIVE_BITS 1 #define PREEMPT_ACTIVE_SHIFT (NMI_SHIFT + NMI_BITS) @@ -82,10 +84,13 @@ /* * Are we doing bottom half or hardware interrupt processing? * Are we in a softirq context? Interrupt context? + * in_softirq - Are we currently processing softirq or have bh disabled? + * in_serving_softirq - Are we currently processing softirq? */ #define in_irq() (hardirq_count()) #define in_softirq() (softirq_count()) #define in_interrupt() (irq_count()) +#define in_serving_softirq() (softirq_count() & SOFTIRQ_OFFSET) /* * Are we in NMI context? @@ -132,10 +137,12 @@ extern void synchronize_irq(unsigned int struct task_struct; -#ifndef CONFIG_VIRT_CPU_ACCOUNTING +#if !defined(CONFIG_VIRT_CPU_ACCOUNTING) && !defined(CONFIG_IRQ_TIME_ACCOUNTING) static inline void account_system_vtime(struct task_struct *tsk) { } +#else +extern void account_system_vtime(struct task_struct *tsk); #endif #if defined(CONFIG_NO_HZ) --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -872,7 +872,7 @@ struct ieee80211_ht_info { /* block-ack parameters */ #define IEEE80211_ADDBA_PARAM_POLICY_MASK 0x0002 #define IEEE80211_ADDBA_PARAM_TID_MASK 0x003C -#define IEEE80211_ADDBA_PARAM_BUF_SIZE_MASK 0xFFA0 +#define IEEE80211_ADDBA_PARAM_BUF_SIZE_MASK 0xFFC0 #define IEEE80211_DELBA_PARAM_TID_MASK 0xF000 #define IEEE80211_DELBA_PARAM_INITIATOR_MASK 0x0800 --- a/include/linux/klist.h +++ b/include/linux/klist.h @@ -22,7 +22,7 @@ struct klist { struct list_head k_list; void (*get)(struct klist_node *); void (*put)(struct klist_node *); -} __attribute__ ((aligned (4))); +} __attribute__ ((aligned (sizeof(void *)))); #define KLIST_INIT(_name, _get, _put) \ { .k_lock = __SPIN_LOCK_UNLOCKED(_name.k_lock), \ --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -739,14 +739,6 @@ struct user_struct { uid_t uid; struct user_namespace *user_ns; -#ifdef CONFIG_USER_SCHED - struct task_group *tg; -#ifdef CONFIG_SYSFS - struct kobject kobj; - struct delayed_work work; -#endif -#endif - #ifdef CONFIG_PERF_EVENTS atomic_long_t locked_vm; #endif @@ -913,6 +905,7 @@ struct sched_group { * single CPU. */ unsigned int cpu_power; + unsigned int group_weight; /* * The CPUs this group covers. @@ -1132,7 +1125,7 @@ struct sched_class { struct task_struct *task); #ifdef CONFIG_FAIR_GROUP_SCHED - void (*moved_group) (struct task_struct *p, int on_rq); + void (*task_move_group) (struct task_struct *p, int on_rq); #endif }; @@ -1836,8 +1829,7 @@ extern int task_free_unregister(struct n /* * Per process flags */ -#define PF_ALIGNWARN 0x00000001 /* Print alignment warning msgs */ - /* Not implemented yet, only for 486*/ +#define PF_KSOFTIRQD 0x00000001 /* I am ksoftirqd */ #define PF_STARTING 0x00000002 /* being created */ #define PF_EXITING 0x00000004 /* getting shut down */ #define PF_EXITPIDONE 0x00000008 /* pi exit done on shut down */ @@ -1974,6 +1966,19 @@ extern void sched_clock_idle_wakeup_even */ extern unsigned long long cpu_clock(int cpu); +#ifdef CONFIG_IRQ_TIME_ACCOUNTING +/* + * An i/f to runtime opt-in for irq time accounting based off of sched_clock. + * The reason for this explicit opt-in is not to have perf penalty with + * slow sched_clocks. + */ +extern void enable_sched_clock_irqtime(void); +extern void disable_sched_clock_irqtime(void); +#else +static inline void enable_sched_clock_irqtime(void) {} +static inline void disable_sched_clock_irqtime(void) {} +#endif + extern unsigned long long task_sched_runtime(struct task_struct *task); extern unsigned long long thread_group_sched_runtime(struct task_struct *task); @@ -2525,9 +2530,9 @@ extern int __cond_resched_lock(spinlock_ extern int __cond_resched_softirq(void); -#define cond_resched_softirq() ({ \ - __might_sleep(__FILE__, __LINE__, SOFTIRQ_OFFSET); \ - __cond_resched_softirq(); \ +#define cond_resched_softirq() ({ \ + __might_sleep(__FILE__, __LINE__, SOFTIRQ_DISABLE_OFFSET); \ + __cond_resched_softirq(); \ }) /* @@ -2616,13 +2621,9 @@ extern long sched_getaffinity(pid_t pid, extern void normalize_rt_tasks(void); -#ifdef CONFIG_GROUP_SCHED +#ifdef CONFIG_CGROUP_SCHED extern struct task_group init_task_group; -#ifdef CONFIG_USER_SCHED -extern struct task_group root_task_group; -extern void set_tg_uid(struct user_struct *user); -#endif extern struct task_group *sched_create_group(struct task_group *parent); extern void sched_destroy_group(struct task_group *tg); --- a/include/linux/usb/serial.h +++ b/include/linux/usb/serial.h @@ -326,6 +326,9 @@ extern int usb_serial_handle_sysrq_char( struct usb_serial_port *port, unsigned int ch); extern int usb_serial_handle_break(struct usb_serial_port *port); +extern void usb_serial_handle_dcd_change(struct usb_serial_port *usb_port, + struct tty_struct *tty, + unsigned int status); extern int usb_serial_bus_register(struct usb_serial_driver *device); --- a/include/net/sctp/command.h +++ b/include/net/sctp/command.h @@ -107,6 +107,7 @@ typedef enum { SCTP_CMD_T1_RETRAN, /* Mark for retransmission after T1 timeout */ SCTP_CMD_UPDATE_INITTAG, /* Update peer inittag */ SCTP_CMD_SEND_MSG, /* Send the whole use message */ + SCTP_CMD_SEND_NEXT_ASCONF, /* Send the next ASCONF after ACK */ SCTP_CMD_LAST } sctp_verb_t; --- a/init/Kconfig +++ b/init/Kconfig @@ -439,57 +439,6 @@ config LOG_BUF_SHIFT config HAVE_UNSTABLE_SCHED_CLOCK bool -config GROUP_SCHED - bool "Group CPU scheduler" - depends on EXPERIMENTAL && !SCHED_BFS - default n - help - This feature lets CPU scheduler recognize task groups and control CPU - bandwidth allocation to such task groups. - In order to create a group from arbitrary set of processes, use - CONFIG_CGROUPS. (See Control Group support.) - -config FAIR_GROUP_SCHED - bool "Group scheduling for SCHED_OTHER" - depends on GROUP_SCHED - default GROUP_SCHED - -config RT_GROUP_SCHED - bool "Group scheduling for SCHED_RR/FIFO" - depends on EXPERIMENTAL - depends on GROUP_SCHED - default n - help - This feature lets you explicitly allocate real CPU bandwidth - to users or control groups (depending on the "Basis for grouping tasks" - setting below. If enabled, it will also make it impossible to - schedule realtime tasks for non-root users until you allocate - realtime bandwidth for them. - See Documentation/scheduler/sched-rt-group.txt for more information. - -choice - depends on GROUP_SCHED - prompt "Basis for grouping tasks" - default USER_SCHED - -config USER_SCHED - bool "user id" - help - This option will choose userid as the basis for grouping - tasks, thus providing equal CPU bandwidth to each user. - -config CGROUP_SCHED - bool "Control groups" - depends on CGROUPS - help - This option allows you to create arbitrary task groups - using the "cgroup" pseudo filesystem and control - the cpu bandwidth allocated to each such task group. - Refer to Documentation/cgroups/cgroups.txt for more - information on "cgroup" pseudo filesystem. - -endchoice - menuconfig CGROUPS boolean "Control Group support" help @@ -610,6 +559,35 @@ config CGROUP_MEM_RES_CTLR_SWAP Now, memory usage of swap_cgroup is 2 bytes per entry. If swap page size is 4096bytes, 512k per 1Gbytes of swap. +menuconfig CGROUP_SCHED + bool "Group CPU scheduler" + depends on EXPERIMENTAL && CGROUPS + default n + help + This feature lets CPU scheduler recognize task groups and control CPU + bandwidth allocation to such task groups. It uses cgroups to group + tasks. + +if CGROUP_SCHED +config FAIR_GROUP_SCHED + bool "Group scheduling for SCHED_OTHER" + depends on CGROUP_SCHED + default CGROUP_SCHED + +config RT_GROUP_SCHED + bool "Group scheduling for SCHED_RR/FIFO" + depends on EXPERIMENTAL + depends on CGROUP_SCHED + default n + help + This feature lets you explicitly allocate real CPU bandwidth + to task groups. If enabled, it will also make it impossible to + schedule realtime tasks for non-root users until you allocate + realtime bandwidth for them. + See Documentation/scheduler/sched-rt-group.txt for more information. + +endif #CGROUP_SCHED + endif # CGROUPS config SCHED_AUTOGROUP --- a/init/calibrate.c +++ b/init/calibrate.c @@ -66,7 +66,7 @@ static unsigned long __cpuinit calibrate pre_start = 0; read_current_timer(&start); start_jiffies = jiffies; - while (jiffies <= (start_jiffies + 1)) { + while (time_before_eq(jiffies, start_jiffies + 1)) { pre_start = start; read_current_timer(&start); } @@ -74,8 +74,8 @@ static unsigned long __cpuinit calibrate pre_end = 0; end = post_start; - while (jiffies <= - (start_jiffies + 1 + DELAY_CALIBRATION_TICKS)) { + while (time_before_eq(jiffies, start_jiffies + 1 + + DELAY_CALIBRATION_TICKS)) { pre_end = end; read_current_timer(&end); } --- a/kernel/capability.c +++ b/kernel/capability.c @@ -15,7 +15,6 @@ #include #include #include -#include "cred-internals.h" /* * Leveraged for setting/resetting capabilities --- a/kernel/cred-internals.h +++ /dev/null @@ -1,21 +0,0 @@ -/* Internal credentials stuff - * - * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved. - * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public Licence - * as published by the Free Software Foundation; either version - * 2 of the Licence, or (at your option) any later version. - */ - -/* - * user.c - */ -static inline void sched_switch_user(struct task_struct *p) -{ -#ifdef CONFIG_USER_SCHED - sched_move_task(p); -#endif /* CONFIG_USER_SCHED */ -} - --- a/kernel/cred.c +++ b/kernel/cred.c @@ -16,7 +16,6 @@ #include #include #include -#include "cred-internals.h" #if 0 #define kdebug(FMT, ...) \ @@ -209,6 +208,31 @@ void exit_creds(struct task_struct *tsk) } } +/** + * get_task_cred - Get another task's objective credentials + * @task: The task to query + * + * Get the objective credentials of a task, pinning them so that they can't go + * away. Accessing a task's credentials directly is not permitted. + * + * The caller must also make sure task doesn't get deleted, either by holding a + * ref on task or by holding tasklist_lock to prevent it from being unlinked. + */ +const struct cred *get_task_cred(struct task_struct *task) +{ + const struct cred *cred; + + rcu_read_lock(); + + do { + cred = __task_cred((task)); + BUG_ON(!cred); + } while (!atomic_inc_not_zero(&((struct cred *)cred)->usage)); + + rcu_read_unlock(); + return cred; +} + /* * Allocate blank credentials, such that the credentials can be filled in at a * later date without risk of ENOMEM. @@ -231,13 +255,13 @@ struct cred *cred_alloc_blank(void) #endif atomic_set(&new->usage, 1); +#ifdef CONFIG_DEBUG_CREDENTIALS + new->magic = CRED_MAGIC; +#endif if (security_cred_alloc_blank(new, GFP_KERNEL) < 0) goto error; -#ifdef CONFIG_DEBUG_CREDENTIALS - new->magic = CRED_MAGIC; -#endif return new; error: @@ -553,8 +577,6 @@ int commit_creds(struct cred *new) atomic_dec(&old->user->processes); alter_cred_subscribers(old, -2); - sched_switch_user(task); - /* send notifications */ if (new->uid != old->uid || new->euid != old->euid || @@ -696,6 +718,8 @@ struct cred *prepare_kernel_cred(struct validate_creds(old); *new = *old; + atomic_set(&new->usage, 1); + set_cred_subscribers(new, 0); get_uid(new->user); get_group_info(new->group_info); @@ -713,8 +737,6 @@ struct cred *prepare_kernel_cred(struct if (security_prepare_creds(new, old, GFP_KERNEL) < 0) goto error; - atomic_set(&new->usage, 1); - set_cred_subscribers(new, 0); put_cred(old); validate_creds(new); return new; @@ -787,7 +809,11 @@ bool creds_are_invalid(const struct cred if (cred->magic != CRED_MAGIC) return true; #ifdef CONFIG_SECURITY_SELINUX - if (selinux_is_enabled()) { + /* + * cred->security == NULL if security_cred_alloc_blank() or + * security_prepare_creds() returned an error. + */ + if (selinux_is_enabled() && cred->security) { if ((unsigned long) cred->security < PAGE_SIZE) return true; if ((*(u32 *)cred->security & 0xffffff00) == --- a/kernel/exit.c +++ b/kernel/exit.c @@ -54,7 +54,6 @@ #include #include #include -#include "cred-internals.h" static void exit_mm(struct task_struct * tsk); --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -1079,7 +1079,7 @@ int request_threaded_irq(unsigned int ir if (retval) kfree(action); -#ifdef CONFIG_DEBUG_SHIRQ +#ifdef CONFIG_DEBUG_SHIRQ_FIXME if (irqflags & IRQF_SHARED) { /* * It's a shared IRQ -- the driver ought to be prepared for it --- a/kernel/ksysfs.c +++ b/kernel/ksysfs.c @@ -176,16 +176,8 @@ static int __init ksysfs_init(void) goto group_exit; } - /* create the /sys/kernel/uids/ directory */ - error = uids_sysfs_init(); - if (error) - goto notes_exit; - return 0; -notes_exit: - if (notes_size > 0) - sysfs_remove_bin_file(kernel_kobj, ¬es_attr); group_exit: sysfs_remove_group(kernel_kobj, &kernel_attr_group); kset_exit: --- a/kernel/power/snapshot.c +++ b/kernel/power/snapshot.c @@ -1466,11 +1466,8 @@ static int swsusp_alloc(struct memory_bitmap *orig_bm, struct memory_bitmap *copy_bm, unsigned int nr_pages, unsigned int nr_highmem) { - int error = 0; - if (nr_highmem > 0) { - error = get_highmem_buffer(PG_ANY); - if (error) + if (get_highmem_buffer(PG_ANY)) goto err_out; if (nr_highmem > alloc_highmem) { nr_highmem -= alloc_highmem; @@ -1493,7 +1490,7 @@ swsusp_alloc(struct memory_bitmap *orig_ err_out: swsusp_free(); - return error; + return -ENOMEM; } asmlinkage int swsusp_save(void) --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -314,7 +314,7 @@ int ptrace_detach(struct task_struct *ch child->exit_code = data; dead = __ptrace_detach(current, child); if (!child->exit_state) - wake_up_process(child); + wake_up_state(child, TASK_TRACED | TASK_STOPPED); } write_unlock_irq(&tasklist_lock); --- a/kernel/sched.c +++ b/kernel/sched.c @@ -237,7 +237,7 @@ static void destroy_rt_bandwidth(struct */ static DEFINE_MUTEX(sched_domains_mutex); -#ifdef CONFIG_GROUP_SCHED +#ifdef CONFIG_CGROUP_SCHED #include @@ -247,13 +247,7 @@ static LIST_HEAD(task_groups); /* task group related information */ struct task_group { -#ifdef CONFIG_CGROUP_SCHED struct cgroup_subsys_state css; -#endif - -#ifdef CONFIG_USER_SCHED - uid_t uid; -#endif #ifdef CONFIG_FAIR_GROUP_SCHED /* schedulable entities of this group on each cpu */ @@ -278,35 +272,7 @@ struct task_group { struct list_head children; }; -#ifdef CONFIG_USER_SCHED - -/* Helper function to pass uid information to create_sched_user() */ -void set_tg_uid(struct user_struct *user) -{ - user->tg->uid = user->uid; -} - -/* - * Root task group. - * Every UID task group (including init_task_group aka UID-0) will - * be a child to this group. - */ -struct task_group root_task_group; - -#ifdef CONFIG_FAIR_GROUP_SCHED -/* Default task group's sched entity on each cpu */ -static DEFINE_PER_CPU(struct sched_entity, init_sched_entity); -/* Default task group's cfs_rq on each cpu */ -static DEFINE_PER_CPU_SHARED_ALIGNED(struct cfs_rq, init_tg_cfs_rq); -#endif /* CONFIG_FAIR_GROUP_SCHED */ - -#ifdef CONFIG_RT_GROUP_SCHED -static DEFINE_PER_CPU(struct sched_rt_entity, init_sched_rt_entity); -static DEFINE_PER_CPU_SHARED_ALIGNED(struct rt_rq, init_rt_rq); -#endif /* CONFIG_RT_GROUP_SCHED */ -#else /* !CONFIG_USER_SCHED */ #define root_task_group init_task_group -#endif /* CONFIG_USER_SCHED */ /* task_group_lock serializes add/remove of task groups and also changes to * a task group's cpu shares. @@ -322,11 +288,7 @@ static int root_task_group_empty(void) } #endif -#ifdef CONFIG_USER_SCHED -# define INIT_TASK_GROUP_LOAD (2*NICE_0_LOAD) -#else /* !CONFIG_USER_SCHED */ # define INIT_TASK_GROUP_LOAD NICE_0_LOAD -#endif /* CONFIG_USER_SCHED */ /* * A weight of 0 or 1 can cause arithmetics problems. @@ -352,13 +314,7 @@ static inline struct task_group *task_gr { struct task_group *tg; -#ifdef CONFIG_USER_SCHED - rcu_read_lock(); - tg = __task_cred(p)->user->tg; - rcu_read_unlock(); - - return tg; -#elif defined(CONFIG_CGROUP_SCHED) +#ifdef CONFIG_CGROUP_SCHED struct cgroup_subsys_state *css; css = task_subsys_state(p, cpu_cgroup_subsys_id); @@ -394,7 +350,7 @@ static inline struct task_group *task_gr return NULL; } -#endif /* CONFIG_GROUP_SCHED */ +#endif /* CONFIG_CGROUP_SCHED */ /* CFS-related fields in a runqueue */ struct cfs_rq { @@ -578,6 +534,7 @@ struct rq { struct mm_struct *prev_mm; u64 clock; + u64 clock_task; atomic_t nr_iowait; @@ -585,6 +542,8 @@ struct rq { struct root_domain *rd; struct sched_domain *sd; + unsigned long cpu_power; + unsigned char idle_at_tick; /* For active balancing */ int post_schedule; @@ -605,6 +564,10 @@ struct rq { u64 avg_idle; #endif +#ifdef CONFIG_IRQ_TIME_ACCOUNTING + u64 prev_irq_time; +#endif + /* calc_load related fields */ unsigned long calc_load_update; long calc_load_active; @@ -642,11 +605,7 @@ struct rq { static DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues); -static inline -void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags) -{ - rq->curr->sched_class->check_preempt_curr(rq, p, flags); -} +static void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags); static inline int cpu_of(struct rq *rq) { @@ -673,9 +632,20 @@ static inline int cpu_of(struct rq *rq) #define cpu_curr(cpu) (cpu_rq(cpu)->curr) #define raw_rq() (&__raw_get_cpu_var(runqueues)) +static u64 irq_time_cpu(int cpu); +static void sched_irq_time_avg_update(struct rq *rq, u64 irq_time); + inline void update_rq_clock(struct rq *rq) { + int cpu = cpu_of(rq); + u64 irq_time; + rq->clock = sched_clock_cpu(cpu_of(rq)); + irq_time = irq_time_cpu(cpu); + if (rq->clock - irq_time > rq->clock_task) + rq->clock_task = rq->clock - irq_time; + + sched_irq_time_avg_update(rq, irq_time); } /* @@ -1308,6 +1278,10 @@ static void resched_task(struct task_str static void sched_rt_avg_update(struct rq *rq, u64 rt_delta) { } + +static void sched_avg_update(struct rq *rq) +{ +} #endif /* CONFIG_SMP */ #if BITS_PER_LONG == 32 @@ -1557,24 +1531,9 @@ static unsigned long target_load(int cpu return max(rq->cpu_load[type-1], total); } -static struct sched_group *group_of(int cpu) -{ - struct sched_domain *sd = rcu_dereference(cpu_rq(cpu)->sd); - - if (!sd) - return NULL; - - return sd->groups; -} - static unsigned long power_of(int cpu) { - struct sched_group *group = group_of(cpu); - - if (!group) - return SCHED_LOAD_SCALE; - - return group->cpu_power; + return cpu_rq(cpu)->cpu_power; } static int task_hot(struct task_struct *p, u64 now, struct sched_domain *sd); @@ -1856,6 +1815,94 @@ static inline void __set_task_cpu(struct #endif } +#ifdef CONFIG_IRQ_TIME_ACCOUNTING + +/* + * There are no locks covering percpu hardirq/softirq time. + * They are only modified in account_system_vtime, on corresponding CPU + * with interrupts disabled. So, writes are safe. + * They are read and saved off onto struct rq in update_rq_clock(). + * This may result in other CPU reading this CPU's irq time and can + * race with irq/account_system_vtime on this CPU. We would either get old + * or new value (or semi updated value on 32 bit) with a side effect of + * accounting a slice of irq time to wrong task when irq is in progress + * while we read rq->clock. That is a worthy compromise in place of having + * locks on each irq in account_system_time. + */ +static DEFINE_PER_CPU(u64, cpu_hardirq_time); +static DEFINE_PER_CPU(u64, cpu_softirq_time); + +static DEFINE_PER_CPU(u64, irq_start_time); +static int sched_clock_irqtime; + +void enable_sched_clock_irqtime(void) +{ + sched_clock_irqtime = 1; +} + +void disable_sched_clock_irqtime(void) +{ + sched_clock_irqtime = 0; +} + +static u64 irq_time_cpu(int cpu) +{ + if (!sched_clock_irqtime) + return 0; + + return per_cpu(cpu_softirq_time, cpu) + per_cpu(cpu_hardirq_time, cpu); +} + +void account_system_vtime(struct task_struct *curr) +{ + unsigned long flags; + int cpu; + u64 now, delta; + + if (!sched_clock_irqtime) + return; + + local_irq_save(flags); + + cpu = smp_processor_id(); + now = sched_clock_cpu(cpu); + delta = now - per_cpu(irq_start_time, cpu); + per_cpu(irq_start_time, cpu) = now; + /* + * We do not account for softirq time from ksoftirqd here. + * We want to continue accounting softirq time to ksoftirqd thread + * in that case, so as not to confuse scheduler with a special task + * that do not consume any time, but still wants to run. + */ + if (hardirq_count()) + per_cpu(cpu_hardirq_time, cpu) += delta; + else if (in_serving_softirq() && !(curr->flags & PF_KSOFTIRQD)) + per_cpu(cpu_softirq_time, cpu) += delta; + + local_irq_restore(flags); +} +EXPORT_SYMBOL_GPL(account_system_vtime); + +static void sched_irq_time_avg_update(struct rq *rq, u64 curr_irq_time) +{ + if (sched_clock_irqtime && sched_feat(NONIRQ_POWER)) { + u64 delta_irq = curr_irq_time - rq->prev_irq_time; + rq->prev_irq_time = curr_irq_time; + sched_rt_avg_update(rq, delta_irq); + } +} + +#else + +static u64 irq_time_cpu(int cpu) +{ + return 0; +} + +static void sched_irq_time_avg_update(struct rq *rq, u64 curr_irq_time) { } + +#endif + #include "sched_stats.h" #include "sched_idletask.c" #include "sched_fair.c" @@ -1882,8 +1929,8 @@ static void dec_nr_running(struct rq *rq static void set_load_weight(struct task_struct *p) { if (task_has_rt_policy(p)) { - p->se.load.weight = prio_to_weight[0] * 2; - p->se.load.inv_weight = prio_to_wmult[0] >> 1; + p->se.load.weight = 0; + p->se.load.inv_weight = WMULT_CONST; return; } @@ -2064,6 +2111,9 @@ task_hot(struct task_struct *p, u64 now, if (p->sched_class != &fair_sched_class) return 0; + if (unlikely(p->policy == SCHED_IDLE)) + return 0; + /* * Buddy candidates are cache hot: */ @@ -2335,6 +2385,24 @@ void task_oncpu_function_call(struct tas preempt_enable(); } +static void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags) +{ + const struct sched_class *class; + + if (p->sched_class == rq->curr->sched_class) { + rq->curr->sched_class->check_preempt_curr(rq, p, flags); + } else { + for_each_class(class) { + if (class == rq->curr->sched_class) + break; + if (class == p->sched_class) { + resched_task(rq->curr); + break; + } + } + } +} + #ifdef CONFIG_SMP /* * ->cpus_allowed is protected by either TASK_WAKING or rq->lock held. @@ -3156,6 +3224,8 @@ static void update_cpu_load(struct rq *t this_rq->calc_load_update += LOAD_FREQ; calc_load_account_active(this_rq); } + + sched_avg_update(this_rq); } #ifdef CONFIG_SMP @@ -3287,7 +3357,7 @@ int can_migrate_task(struct task_struct * 2) too many balance attempts have failed. */ - tsk_cache_hot = task_hot(p, rq->clock, sd); + tsk_cache_hot = task_hot(p, rq->clock_task, sd); if (!tsk_cache_hot || sd->nr_balance_failed > sd->cache_nice_tries) { #ifdef CONFIG_SCHEDSTATS @@ -3470,12 +3540,17 @@ struct sd_lb_stats { unsigned long this_load; unsigned long this_load_per_task; unsigned long this_nr_running; + unsigned long this_has_capacity; + unsigned int this_idle_cpus; /* Statistics of the busiest group */ + unsigned int busiest_idle_cpus; unsigned long max_load; unsigned long busiest_load_per_task; unsigned long busiest_nr_running; unsigned long busiest_group_capacity; + unsigned long busiest_has_capacity; + unsigned int busiest_group_weight; int group_imb; /* Is there imbalance in this sd */ #if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT) @@ -3497,7 +3572,10 @@ struct sg_lb_stats { unsigned long sum_nr_running; /* Nr tasks running in the group */ unsigned long sum_weighted_load; /* Weighted load of group's tasks */ unsigned long group_capacity; + unsigned long idle_cpus; + unsigned long group_weight; int group_imb; /* Is there an imbalance in the group ? */ + int group_has_capacity; /* Is there extra capacity in the group? */ }; /** @@ -3707,10 +3785,14 @@ unsigned long scale_rt_power(int cpu) struct rq *rq = cpu_rq(cpu); u64 total, available; - sched_avg_update(rq); - total = sched_avg_period() + (rq->clock - rq->age_stamp); - available = total - rq->rt_avg; + + if (unlikely(total < rq->rt_avg)) { + /* Ensures that power won't end up being negative */ + available = 0; + } else { + available = total - rq->rt_avg; + } if (unlikely((s64)total < SCHED_LOAD_SCALE)) total = SCHED_LOAD_SCALE; @@ -3748,6 +3830,7 @@ static void update_cpu_power(struct sche if (!power) power = 1; + cpu_rq(cpu)->cpu_power = power; sdg->cpu_power = power; } @@ -3792,7 +3875,7 @@ static inline void update_sg_lb_stats(st int local_group, const struct cpumask *cpus, int *balance, struct sg_lb_stats *sgs) { - unsigned long load, max_cpu_load, min_cpu_load; + unsigned long load, max_cpu_load, min_cpu_load, max_nr_running; int i; unsigned int balance_cpu = -1, first_idle_cpu = 0; unsigned long avg_load_per_task = 0; @@ -3806,6 +3889,7 @@ static inline void update_sg_lb_stats(st /* Tally up the load of all CPUs in the group */ max_cpu_load = 0; min_cpu_load = ~0UL; + max_nr_running = 0; for_each_cpu_and(i, sched_group_cpus(group), cpus) { struct rq *rq = cpu_rq(i); @@ -3823,8 +3907,10 @@ static inline void update_sg_lb_stats(st load = target_load(i, load_idx); } else { load = source_load(i, load_idx); - if (load > max_cpu_load) + if (load > max_cpu_load) { max_cpu_load = load; + max_nr_running = rq->nr_running; + } if (min_cpu_load > load) min_cpu_load = load; } @@ -3832,7 +3918,8 @@ static inline void update_sg_lb_stats(st sgs->group_load += load; sgs->sum_nr_running += rq->nr_running; sgs->sum_weighted_load += weighted_cpuload(i); - + if (idle_cpu(i)) + sgs->idle_cpus++; } /* @@ -3862,11 +3949,14 @@ static inline void update_sg_lb_stats(st if (sgs->sum_nr_running) avg_load_per_task = sgs->sum_weighted_load / sgs->sum_nr_running; - if ((max_cpu_load - min_cpu_load) > 2*avg_load_per_task) + if ((max_cpu_load - min_cpu_load) > 2*avg_load_per_task && max_nr_running > 1) sgs->group_imb = 1; - sgs->group_capacity = - DIV_ROUND_CLOSEST(group->cpu_power, SCHED_LOAD_SCALE); + sgs->group_capacity = DIV_ROUND_CLOSEST(group->cpu_power, SCHED_LOAD_SCALE); + sgs->group_weight = group->group_weight; + + if (sgs->group_capacity > sgs->sum_nr_running) + sgs->group_has_capacity = 1; } /** @@ -3913,9 +4003,14 @@ static inline void update_sd_lb_stats(st /* * In case the child domain prefers tasks go to siblings * first, lower the group capacity to one so that we'll try - * and move all the excess tasks away. + * and move all the excess tasks away. We lower the capacity + * of a group only if the local group has the capacity to fit + * these excess tasks, i.e. nr_running < group_capacity. The + * extra check prevents the case where you always pull from the + * heaviest group when it is already under-utilized (possible + * with a large weight task outweighs the tasks on the system). */ - if (prefer_sibling) + if (prefer_sibling && !local_group && sds->this_has_capacity) sgs.group_capacity = min(sgs.group_capacity, 1UL); if (local_group) { @@ -3923,14 +4018,19 @@ static inline void update_sd_lb_stats(st sds->this = group; sds->this_nr_running = sgs.sum_nr_running; sds->this_load_per_task = sgs.sum_weighted_load; + sds->this_has_capacity = sgs.group_has_capacity; + sds->this_idle_cpus = sgs.idle_cpus; } else if (sgs.avg_load > sds->max_load && (sgs.sum_nr_running > sgs.group_capacity || sgs.group_imb)) { sds->max_load = sgs.avg_load; sds->busiest = group; sds->busiest_nr_running = sgs.sum_nr_running; + sds->busiest_idle_cpus = sgs.idle_cpus; sds->busiest_group_capacity = sgs.group_capacity; + sds->busiest_group_weight = sgs.group_weight; sds->busiest_load_per_task = sgs.sum_weighted_load; + sds->busiest_has_capacity = sgs.group_has_capacity; sds->group_imb = sgs.group_imb; } @@ -4076,6 +4176,7 @@ static inline void calculate_imbalance(s return fix_small_imbalance(sds, this_cpu, imbalance); } + /******* find_busiest_group() helpers end here *********************/ /** @@ -4127,6 +4228,11 @@ find_busiest_group(struct sched_domain * * 4) This group is more busy than the avg busieness at this * sched_domain. * 5) The imbalance is within the specified limit. + * + * Note: when doing newidle balance, if the local group has excess + * capacity (i.e. nr_running < group_capacity) and the busiest group + * does not have any capacity, we force a load balance to pull tasks + * to the local group. In this case, we skip past checks 3, 4 and 5. */ if (balance && !(*balance)) goto ret; @@ -4134,6 +4240,11 @@ find_busiest_group(struct sched_domain * if (!sds.busiest || sds.busiest_nr_running == 0) goto out_balanced; + /* SD_BALANCE_NEWIDLE trumps SMP nice when underutilized */ + if (idle == CPU_NEWLY_IDLE && sds.this_has_capacity && + !sds.busiest_has_capacity) + goto force_balance; + if (sds.this_load >= sds.max_load) goto out_balanced; @@ -4142,9 +4253,28 @@ find_busiest_group(struct sched_domain * if (sds.this_load >= sds.avg_load) goto out_balanced; - if (100 * sds.max_load <= sd->imbalance_pct * sds.this_load) - goto out_balanced; + /* + * In the CPU_NEWLY_IDLE, use imbalance_pct to be conservative. + * And to check for busy balance use !idle_cpu instead of + * CPU_NOT_IDLE. This is because HT siblings will use CPU_NOT_IDLE + * even when they are idle. + */ + if (idle == CPU_NEWLY_IDLE || !idle_cpu(this_cpu)) { + if (100 * sds.max_load <= sd->imbalance_pct * sds.this_load) + goto out_balanced; + } else { + /* + * This cpu is idle. If the busiest group load doesn't + * have more tasks than the number of available cpu's and + * there is no imbalance between this and busiest group + * wrt to idle cpu's, it is balanced. + */ + if ((sds.this_idle_cpus <= sds.busiest_idle_cpus + 1) && + sds.busiest_nr_running <= sds.busiest_group_weight) + goto out_balanced; + } +force_balance: /* Looks like there is an imbalance. Compute it */ calculate_imbalance(&sds, this_cpu, imbalance); return sds.busiest; @@ -4300,7 +4430,14 @@ redo: if (!ld_moved) { schedstat_inc(sd, lb_failed[idle]); - sd->nr_balance_failed++; + /* + * Increment the failure counter only on periodic balance. + * We do not want newidle balance, which can be very + * frequent, pollute the failure counter causing + * excessive cache_hot migrations and active balances. + */ + if (idle != CPU_NEWLY_IDLE) + sd->nr_balance_failed++; if (unlikely(sd->nr_balance_failed > sd->cache_nice_tries+2)) { @@ -5045,7 +5182,7 @@ static u64 do_task_delta_exec(struct tas if (task_current(rq, p)) { update_rq_clock(rq); - ns = rq->clock - p->se.exec_start; + ns = rq->clock_task - p->se.exec_start; if ((s64)ns < 0) ns = 0; } @@ -5189,7 +5326,7 @@ void account_system_time(struct task_str tmp = cputime_to_cputime64(cputime); if (hardirq_count() - hardirq_offset) cpustat->irq = cputime64_add(cpustat->irq, tmp); - else if (softirq_count()) + else if (in_serving_softirq()) cpustat->softirq = cputime64_add(cpustat->softirq, tmp); else cpustat->system = cputime64_add(cpustat->system, tmp); @@ -7133,7 +7270,19 @@ void __cpuinit init_idle(struct task_str idle->se.exec_start = sched_clock(); cpumask_copy(&idle->cpus_allowed, cpumask_of(cpu)); + /* + * We're having a chicken and egg problem, even though we are + * holding rq->lock, the cpu isn't yet set to this cpu so the + * lockdep check in task_group() will fail. + * + * Similar case to sched_fork(). / Alternatively we could + * use task_rq_lock() here and obtain the other rq->lock. + * + * Silence PROVE_RCU + */ + rcu_read_lock(); __set_task_cpu(idle, cpu); + rcu_read_unlock(); rq->curr = rq->idle = idle; #if defined(CONFIG_SMP) && defined(__ARCH_WANT_UNLOCKED_CTXSW) @@ -8640,6 +8789,8 @@ static void init_sched_groups_power(int if (cpu != group_first_cpu(sd->groups)) return; + sd->groups->group_weight = cpumask_weight(sched_group_cpus(sd->groups)); + child = sd->child; sd->groups->cpu_power = 0; @@ -9523,9 +9674,6 @@ void __init sched_init(void) #ifdef CONFIG_RT_GROUP_SCHED alloc_size += 2 * nr_cpu_ids * sizeof(void **); #endif -#ifdef CONFIG_USER_SCHED - alloc_size *= 2; -#endif #ifdef CONFIG_CPUMASK_OFFSTACK alloc_size += num_possible_cpus() * cpumask_size(); #endif @@ -9543,13 +9691,6 @@ void __init sched_init(void) init_task_group.cfs_rq = (struct cfs_rq **)ptr; ptr += nr_cpu_ids * sizeof(void **); -#ifdef CONFIG_USER_SCHED - root_task_group.se = (struct sched_entity **)ptr; - ptr += nr_cpu_ids * sizeof(void **); - - root_task_group.cfs_rq = (struct cfs_rq **)ptr; - ptr += nr_cpu_ids * sizeof(void **); -#endif /* CONFIG_USER_SCHED */ #endif /* CONFIG_FAIR_GROUP_SCHED */ #ifdef CONFIG_RT_GROUP_SCHED init_task_group.rt_se = (struct sched_rt_entity **)ptr; @@ -9558,13 +9699,6 @@ void __init sched_init(void) init_task_group.rt_rq = (struct rt_rq **)ptr; ptr += nr_cpu_ids * sizeof(void **); -#ifdef CONFIG_USER_SCHED - root_task_group.rt_se = (struct sched_rt_entity **)ptr; - ptr += nr_cpu_ids * sizeof(void **); - - root_task_group.rt_rq = (struct rt_rq **)ptr; - ptr += nr_cpu_ids * sizeof(void **); -#endif /* CONFIG_USER_SCHED */ #endif /* CONFIG_RT_GROUP_SCHED */ #ifdef CONFIG_CPUMASK_OFFSTACK for_each_possible_cpu(i) { @@ -9584,24 +9718,14 @@ void __init sched_init(void) #ifdef CONFIG_RT_GROUP_SCHED init_rt_bandwidth(&init_task_group.rt_bandwidth, global_rt_period(), global_rt_runtime()); -#ifdef CONFIG_USER_SCHED - init_rt_bandwidth(&root_task_group.rt_bandwidth, - global_rt_period(), RUNTIME_INF); -#endif /* CONFIG_USER_SCHED */ #endif /* CONFIG_RT_GROUP_SCHED */ -#ifdef CONFIG_GROUP_SCHED +#ifdef CONFIG_CGROUP_SCHED list_add(&init_task_group.list, &task_groups); INIT_LIST_HEAD(&init_task_group.children); -#ifdef CONFIG_USER_SCHED - INIT_LIST_HEAD(&root_task_group.children); - init_task_group.parent = &root_task_group; - list_add(&init_task_group.siblings, &root_task_group.children); -#endif /* CONFIG_USER_SCHED */ - - autogroup_init(&init_task); -#endif /* CONFIG_GROUP_SCHED */ + autogroup_init(&init_task); +#endif /* CONFIG_CGROUP_SCHED */ #if defined CONFIG_FAIR_GROUP_SCHED && defined CONFIG_SMP update_shares_data = __alloc_percpu(nr_cpu_ids * sizeof(unsigned long), @@ -9641,25 +9765,6 @@ void __init sched_init(void) * directly in rq->cfs (i.e init_task_group->se[] = NULL). */ init_tg_cfs_entry(&init_task_group, &rq->cfs, NULL, i, 1, NULL); -#elif defined CONFIG_USER_SCHED - root_task_group.shares = NICE_0_LOAD; - init_tg_cfs_entry(&root_task_group, &rq->cfs, NULL, i, 0, NULL); - /* - * In case of task-groups formed thr' the user id of tasks, - * init_task_group represents tasks belonging to root user. - * Hence it forms a sibling of all subsequent groups formed. - * In this case, init_task_group gets only a fraction of overall - * system cpu resource, based on the weight assigned to root - * user's cpu share (INIT_TASK_GROUP_LOAD). This is accomplished - * by letting tasks of init_task_group sit in a separate cfs_rq - * (init_tg_cfs_rq) and having one entity represent this group of - * tasks in rq->cfs (i.e init_task_group->se[] != NULL). - */ - init_tg_cfs_entry(&init_task_group, - &per_cpu(init_tg_cfs_rq, i), - &per_cpu(init_sched_entity, i), i, 1, - root_task_group.se[i]); - #endif #endif /* CONFIG_FAIR_GROUP_SCHED */ @@ -9682,6 +9787,7 @@ void __init sched_init(void) #ifdef CONFIG_SMP rq->sd = NULL; rq->rd = NULL; + rq->cpu_power = SCHED_LOAD_SCALE; rq->post_schedule = 0; rq->active_balance = 0; rq->next_balance = jiffies; @@ -10065,7 +10171,7 @@ static inline void unregister_rt_sched_g } #endif /* CONFIG_RT_GROUP_SCHED */ -#ifdef CONFIG_GROUP_SCHED +#ifdef CONFIG_CGROUP_SCHED static void free_sched_group(struct task_group *tg) { free_fair_sched_group(tg); @@ -10156,12 +10262,12 @@ void __sched_move_task(struct task_struc if (unlikely(running)) tsk->sched_class->put_prev_task(rq, tsk); - set_task_rq(tsk, task_cpu(tsk)); - #ifdef CONFIG_FAIR_GROUP_SCHED - if (tsk->sched_class->moved_group) - tsk->sched_class->moved_group(tsk, on_rq); + if (tsk->sched_class->task_move_group) + tsk->sched_class->task_move_group(tsk, on_rq); + else #endif + set_task_rq(tsk, task_cpu(tsk)); if (unlikely(running)) tsk->sched_class->set_curr_task(rq); @@ -10179,7 +10285,7 @@ void sched_move_task(struct task_struct task_rq_unlock(rq, &flags); } -#endif /* CONFIG_GROUP_SCHED */ +#endif /* CONFIG_CGROUP_SCHED */ #ifdef CONFIG_FAIR_GROUP_SCHED static void __set_se_shares(struct sched_entity *se, unsigned long shares) @@ -10321,13 +10427,6 @@ static int tg_schedulable(struct task_gr runtime = d->rt_runtime; } -#ifdef CONFIG_USER_SCHED - if (tg == &root_task_group) { - period = global_rt_period(); - runtime = global_rt_runtime(); - } -#endif - /* * Cannot have more runtime than the period. */ @@ -11103,4 +11202,4 @@ void synchronize_sched_expedited(void) EXPORT_SYMBOL_GPL(synchronize_sched_expedited); #endif /* #else #ifndef CONFIG_SMP */ -#endif /* CONFIG_SCHED_BFS */ \ No newline at end of file +#endif /* CONFIG_SCHED_BFS */ --- a/kernel/sched_debug.c +++ b/kernel/sched_debug.c @@ -173,11 +173,6 @@ void print_cfs_rq(struct seq_file *m, in task_group_path(tg, path, sizeof(path)); SEQ_printf(m, "\ncfs_rq[%d]:%s\n", cpu, path); -#elif defined(CONFIG_USER_SCHED) && defined(CONFIG_FAIR_GROUP_SCHED) - { - uid_t uid = cfs_rq->tg->uid; - SEQ_printf(m, "\ncfs_rq[%d] for UID: %u\n", cpu, uid); - } #else SEQ_printf(m, "\ncfs_rq[%d]:\n", cpu); #endif --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -496,7 +496,7 @@ __update_curr(struct cfs_rq *cfs_rq, str static void update_curr(struct cfs_rq *cfs_rq) { struct sched_entity *curr = cfs_rq->curr; - u64 now = rq_of(cfs_rq)->clock; + u64 now = rq_of(cfs_rq)->clock_task; unsigned long delta_exec; if (unlikely(!curr)) @@ -579,7 +579,7 @@ update_stats_curr_start(struct cfs_rq *c /* * We are starting a new run period: */ - se->exec_start = rq_of(cfs_rq)->clock; + se->exec_start = rq_of(cfs_rq)->clock_task; } /************************************************** @@ -1222,7 +1222,6 @@ static int wake_affine(struct sched_doma unsigned long this_load, load; int idx, this_cpu, prev_cpu; unsigned long tl_per_task; - unsigned int imbalance; struct task_group *tg; unsigned long weight; int balanced; @@ -1262,8 +1261,6 @@ static int wake_affine(struct sched_doma tg = task_group(p); weight = p->se.load.weight; - imbalance = 100 + (sd->imbalance_pct - 100) / 2; - /* * In low-load situations, where prev_cpu is idle and this_cpu is idle * due to the sync cause above having dropped this_load to 0, we'll @@ -1273,9 +1270,22 @@ static int wake_affine(struct sched_doma * Otherwise check if either cpus are near enough in load to allow this * task to be woken on this_cpu. */ - balanced = !this_load || - 100*(this_load + effective_load(tg, this_cpu, weight, weight)) <= - imbalance*(load + effective_load(tg, prev_cpu, 0, weight)); + if (this_load) { + unsigned long this_eff_load, prev_eff_load; + + this_eff_load = 100; + this_eff_load *= power_of(prev_cpu); + this_eff_load *= this_load + + effective_load(tg, this_cpu, weight, weight); + + prev_eff_load = 100 + (sd->imbalance_pct - 100) / 2; + prev_eff_load *= power_of(this_cpu); + prev_eff_load *= load + effective_load(tg, prev_cpu, 0, weight); + + balanced = this_eff_load <= prev_eff_load; + } else + balanced = true; + rcu_read_unlock(); /* @@ -1992,8 +2002,11 @@ static void task_fork_fair(struct task_s update_rq_clock(rq); - if (unlikely(task_cpu(p) != this_cpu)) + if (unlikely(task_cpu(p) != this_cpu)) { + rcu_read_lock(); __set_task_cpu(p, this_cpu); + rcu_read_unlock(); + } update_curr(cfs_rq); @@ -2065,13 +2078,26 @@ static void set_curr_task_fair(struct rq } #ifdef CONFIG_FAIR_GROUP_SCHED -static void moved_group_fair(struct task_struct *p, int on_rq) +static void task_move_group_fair(struct task_struct *p, int on_rq) { - struct cfs_rq *cfs_rq = task_cfs_rq(p); - - update_curr(cfs_rq); + /* + * If the task was not on the rq at the time of this cgroup movement + * it must have been asleep, sleeping tasks keep their ->vruntime + * absolute on their old rq until wakeup (needed for the fair sleeper + * bonus in place_entity()). + * + * If it was on the rq, we've just 'preempted' it, which does convert + * ->vruntime to a relative base. + * + * Make sure both cases convert their relative position when migrating + * to another cgroup's rq. This does somewhat interfere with the + * fair sleeper stuff for the first placement, but who cares. + */ + if (!on_rq) + p->se.vruntime -= cfs_rq_of(&p->se)->min_vruntime; + set_task_rq(p, task_cpu(p)); if (!on_rq) - place_entity(cfs_rq, &p->se, 1); + p->se.vruntime += cfs_rq_of(&p->se)->min_vruntime; } #endif @@ -2125,7 +2151,7 @@ static const struct sched_class fair_sch .get_rr_interval = get_rr_interval_fair, #ifdef CONFIG_FAIR_GROUP_SCHED - .moved_group = moved_group_fair, + .task_move_group = task_move_group_fair, #endif }; --- a/kernel/sched_features.h +++ b/kernel/sched_features.h @@ -121,3 +121,8 @@ SCHED_FEAT(ASYM_EFF_LOAD, 1) * release the lock. Decreases scheduling overhead. */ SCHED_FEAT(OWNER_SPIN, 1) + +/* + * Decrement CPU power based on irq activity + */ +SCHED_FEAT(NONIRQ_POWER, 1) --- a/kernel/sched_rt.c +++ b/kernel/sched_rt.c @@ -603,7 +603,7 @@ static void update_curr_rt(struct rq *rq if (!task_has_rt_policy(curr)) return; - delta_exec = rq->clock - curr->se.exec_start; + delta_exec = rq->clock_task - curr->se.exec_start; if (unlikely((s64)delta_exec < 0)) delta_exec = 0; @@ -612,7 +612,7 @@ static void update_curr_rt(struct rq *rq curr->se.sum_exec_runtime += delta_exec; account_group_exec_runtime(curr, delta_exec); - curr->se.exec_start = rq->clock; + curr->se.exec_start = rq->clock_task; cpuacct_charge(curr, delta_exec); sched_rt_avg_update(rq, delta_exec); @@ -954,18 +954,19 @@ select_task_rq_rt(struct rq *rq, struct * runqueue. Otherwise simply start this RT task * on its current runqueue. * - * We want to avoid overloading runqueues. Even if - * the RT task is of higher priority than the current RT task. - * RT tasks behave differently than other tasks. If - * one gets preempted, we try to push it off to another queue. - * So trying to keep a preempting RT task on the same - * cache hot CPU will force the running RT task to - * a cold CPU. So we waste all the cache for the lower - * RT task in hopes of saving some of a RT task - * that is just being woken and probably will have - * cold cache anyway. + * We want to avoid overloading runqueues. If the woken + * task is a higher priority, then it will stay on this CPU + * and the lower prio task should be moved to another CPU. + * Even though this will probably make the lower prio task + * lose its cache, we do not want to bounce a higher task + * around just because it gave up its CPU, perhaps for a + * lock? + * + * For equal prio tasks, we just let the scheduler sort it out. */ if (unlikely(rt_task(rq->curr)) && + (rq->curr->rt.nr_cpus_allowed < 2 || + rq->curr->prio < p->prio) && (p->rt.nr_cpus_allowed > 1)) { int cpu = find_lowest_rq(p); @@ -1068,7 +1069,7 @@ static struct task_struct *_pick_next_ta } while (rt_rq); p = rt_task_of(rt_se); - p->se.exec_start = rq->clock; + p->se.exec_start = rq->clock_task; return p; } @@ -1493,7 +1494,10 @@ static void task_woken_rt(struct rq *rq, if (!task_running(rq, p) && !test_tsk_need_resched(rq->curr) && has_pushable_tasks(rq) && - p->rt.nr_cpus_allowed > 1) + p->rt.nr_cpus_allowed > 1 && + rt_task(rq->curr) && + (rq->curr->rt.nr_cpus_allowed < 2 || + rq->curr->prio < p->prio)) push_rt_tasks(rq); } @@ -1731,7 +1735,7 @@ static void set_curr_task_rt(struct rq * { struct task_struct *p = rq->curr; - p->se.exec_start = rq->clock; + p->se.exec_start = rq->clock_task; /* The running task is never eligible for pushing */ dequeue_pushable_task(rq, p); --- a/kernel/smp.c +++ b/kernel/smp.c @@ -193,6 +193,24 @@ void generic_smp_call_function_interrupt list_for_each_entry_rcu(data, &call_function.queue, csd.list) { int refs; + /* + * Since we walk the list without any locks, we might + * see an entry that was completed, removed from the + * list and is in the process of being reused. + * + * We must check that the cpu is in the cpumask before + * checking the refs, and both must be set before + * executing the callback on this cpu. + */ + + if (!cpumask_test_cpu(cpu, data->cpumask)) + continue; + + smp_rmb(); + + if (atomic_read(&data->refs) == 0) + continue; + if (!cpumask_test_and_clear_cpu(cpu, data->cpumask)) continue; @@ -201,6 +219,8 @@ void generic_smp_call_function_interrupt refs = atomic_dec_return(&data->refs); WARN_ON(refs < 0); if (!refs) { + WARN_ON(!cpumask_empty(data->cpumask)); + spin_lock(&call_function.lock); list_del_rcu(&data->csd.list); spin_unlock(&call_function.lock); @@ -401,11 +421,21 @@ void smp_call_function_many(const struct data = &__get_cpu_var(cfd_data); csd_lock(&data->csd); + BUG_ON(atomic_read(&data->refs) || !cpumask_empty(data->cpumask)); data->csd.func = func; data->csd.info = info; cpumask_and(data->cpumask, mask, cpu_online_mask); cpumask_clear_cpu(this_cpu, data->cpumask); + + /* + * To ensure the interrupt handler gets an complete view + * we order the cpumask and refs writes and order the read + * of them in the interrupt handler. In addition we may + * only clear our own cpu bit from the mask. + */ + smp_wmb(); + atomic_set(&data->refs, cpumask_weight(data->cpumask)); spin_lock_irqsave(&call_function.lock, flags); --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -77,11 +77,21 @@ void wakeup_softirqd(void) } /* + * preempt_count and SOFTIRQ_OFFSET usage: + * - preempt_count is changed by SOFTIRQ_OFFSET on entering or leaving + * softirq processing. + * - preempt_count is changed by SOFTIRQ_DISABLE_OFFSET (= 2 * SOFTIRQ_OFFSET) + * on local_bh_disable or local_bh_enable. + * This lets us distinguish between whether we are currently processing + * softirq and whether we just have bh disabled. + */ + +/* * This one is for softirq.c-internal use, * where hardirqs are disabled legitimately: */ #ifdef CONFIG_TRACE_IRQFLAGS -static void __local_bh_disable(unsigned long ip) +static void __local_bh_disable(unsigned long ip, unsigned int cnt) { unsigned long flags; @@ -95,32 +105,43 @@ static void __local_bh_disable(unsigned * We must manually increment preempt_count here and manually * call the trace_preempt_off later. */ - preempt_count() += SOFTIRQ_OFFSET; + preempt_count() += cnt; /* * Were softirqs turned off above: */ - if (softirq_count() == SOFTIRQ_OFFSET) + if (softirq_count() == cnt) trace_softirqs_off(ip); raw_local_irq_restore(flags); - if (preempt_count() == SOFTIRQ_OFFSET) + if (preempt_count() == cnt) trace_preempt_off(CALLER_ADDR0, get_parent_ip(CALLER_ADDR1)); } #else /* !CONFIG_TRACE_IRQFLAGS */ -static inline void __local_bh_disable(unsigned long ip) +static inline void __local_bh_disable(unsigned long ip, unsigned int cnt) { - add_preempt_count(SOFTIRQ_OFFSET); + add_preempt_count(cnt); barrier(); } #endif /* CONFIG_TRACE_IRQFLAGS */ void local_bh_disable(void) { - __local_bh_disable((unsigned long)__builtin_return_address(0)); + __local_bh_disable((unsigned long)__builtin_return_address(0), + SOFTIRQ_DISABLE_OFFSET); } EXPORT_SYMBOL(local_bh_disable); +static void __local_bh_enable(unsigned int cnt) +{ + WARN_ON_ONCE(in_irq()); + WARN_ON_ONCE(!irqs_disabled()); + + if (softirq_count() == cnt) + trace_softirqs_on((unsigned long)__builtin_return_address(0)); + sub_preempt_count(cnt); +} + /* * Special-case - softirqs can safely be enabled in * cond_resched_softirq(), or by __do_softirq(), @@ -128,12 +149,7 @@ EXPORT_SYMBOL(local_bh_disable); */ void _local_bh_enable(void) { - WARN_ON_ONCE(in_irq()); - WARN_ON_ONCE(!irqs_disabled()); - - if (softirq_count() == SOFTIRQ_OFFSET) - trace_softirqs_on((unsigned long)__builtin_return_address(0)); - sub_preempt_count(SOFTIRQ_OFFSET); + __local_bh_enable(SOFTIRQ_DISABLE_OFFSET); } EXPORT_SYMBOL(_local_bh_enable); @@ -147,13 +163,13 @@ static inline void _local_bh_enable_ip(u /* * Are softirqs going to be turned on now: */ - if (softirq_count() == SOFTIRQ_OFFSET) + if (softirq_count() == SOFTIRQ_DISABLE_OFFSET) trace_softirqs_on(ip); /* * Keep preemption disabled until we are done with * softirq processing: */ - sub_preempt_count(SOFTIRQ_OFFSET - 1); + sub_preempt_count(SOFTIRQ_DISABLE_OFFSET - 1); if (unlikely(!in_interrupt() && local_softirq_pending())) do_softirq(); @@ -198,7 +214,8 @@ asmlinkage void __do_softirq(void) pending = local_softirq_pending(); account_system_vtime(current); - __local_bh_disable((unsigned long)__builtin_return_address(0)); + __local_bh_disable((unsigned long)__builtin_return_address(0), + SOFTIRQ_OFFSET); lockdep_softirq_enter(); cpu = smp_processor_id(); @@ -245,7 +262,7 @@ restart: lockdep_softirq_exit(); account_system_vtime(current); - _local_bh_enable(); + __local_bh_enable(SOFTIRQ_OFFSET); } #ifndef __ARCH_HAS_DO_SOFTIRQ @@ -279,10 +296,16 @@ void irq_enter(void) rcu_irq_enter(); if (idle_cpu(cpu) && !in_interrupt()) { - __irq_enter(); + /* + * Prevent raise_softirq from needlessly waking up ksoftirqd + * here, as softirq will be serviced on return from interrupt. + */ + local_bh_disable(); tick_check_idle(cpu); - } else - __irq_enter(); + _local_bh_enable(); + } + + __irq_enter(); } #ifdef __ARCH_IRQ_EXIT_IRQS_DISABLED @@ -701,6 +724,7 @@ static int ksoftirqd(void * __bind_cpu) { set_current_state(TASK_INTERRUPTIBLE); + current->flags |= PF_KSOFTIRQD; while (!kthread_should_stop()) { preempt_disable(); if (!local_softirq_pending()) { --- a/kernel/sys.c +++ b/kernel/sys.c @@ -567,11 +567,6 @@ static int set_user(struct cred *new) if (!new_user) return -EAGAIN; - if (!task_can_switch_user(new_user, current)) { - free_uid(new_user); - return -EINVAL; - } - if (atomic_read(&new_user->processes) >= current->signal->rlim[RLIMIT_NPROC].rlim_cur && new_user != INIT_USER) { --- a/kernel/time/tick-broadcast.c +++ b/kernel/time/tick-broadcast.c @@ -600,4 +600,14 @@ int tick_broadcast_oneshot_active(void) return tick_broadcast_device.mode == TICKDEV_MODE_ONESHOT; } +/* + * Check whether the broadcast device supports oneshot. + */ +bool tick_broadcast_oneshot_available(void) +{ + struct clock_event_device *bc = tick_broadcast_device.evtdev; + + return bc ? bc->features & CLOCK_EVT_FEAT_ONESHOT : false; +} + #endif --- a/kernel/time/tick-common.c +++ b/kernel/time/tick-common.c @@ -51,7 +51,11 @@ int tick_is_oneshot_available(void) { struct clock_event_device *dev = __get_cpu_var(tick_cpu_device).evtdev; - return dev && (dev->features & CLOCK_EVT_FEAT_ONESHOT); + if (!dev || !(dev->features & CLOCK_EVT_FEAT_ONESHOT)) + return 0; + if (!(dev->features & CLOCK_EVT_FEAT_C3STOP)) + return 1; + return tick_broadcast_oneshot_available(); } /* --- a/kernel/time/tick-internal.h +++ b/kernel/time/tick-internal.h @@ -37,6 +37,7 @@ extern void tick_shutdown_broadcast_ones extern int tick_resume_broadcast_oneshot(struct clock_event_device *bc); extern int tick_broadcast_oneshot_active(void); extern void tick_check_oneshot_broadcast(int cpu); +bool tick_broadcast_oneshot_available(void); # else /* BROADCAST */ static inline void tick_broadcast_setup_oneshot(struct clock_event_device *bc) { @@ -47,6 +48,7 @@ static inline void tick_broadcast_switch static inline void tick_shutdown_broadcast_oneshot(unsigned int *cpup) { } static inline int tick_broadcast_oneshot_active(void) { return 0; } static inline void tick_check_oneshot_broadcast(int cpu) { } +static inline bool tick_broadcast_oneshot_available(void) { return true; } # endif /* !BROADCAST */ #else /* !ONESHOT */ @@ -77,6 +79,7 @@ static inline int tick_resume_broadcast_ return 0; } static inline int tick_broadcast_oneshot_active(void) { return 0; } +static inline bool tick_broadcast_oneshot_available(void) { return false; } #endif /* !TICK_ONESHOT */ /* --- a/kernel/user.c +++ b/kernel/user.c @@ -16,7 +16,6 @@ #include #include #include -#include "cred-internals.h" struct user_namespace init_user_ns = { .kref = { @@ -56,9 +55,6 @@ struct user_struct root_user = { .sigpending = ATOMIC_INIT(0), .locked_shm = 0, .user_ns = &init_user_ns, -#ifdef CONFIG_USER_SCHED - .tg = &init_task_group, -#endif }; /* @@ -75,268 +71,6 @@ static void uid_hash_remove(struct user_ put_user_ns(up->user_ns); } -#ifdef CONFIG_USER_SCHED - -static void sched_destroy_user(struct user_struct *up) -{ - sched_destroy_group(up->tg); -} - -static int sched_create_user(struct user_struct *up) -{ - int rc = 0; - - up->tg = sched_create_group(&root_task_group); - if (IS_ERR(up->tg)) - rc = -ENOMEM; - - set_tg_uid(up); - - return rc; -} - -#else /* CONFIG_USER_SCHED */ - -static void sched_destroy_user(struct user_struct *up) { } -static int sched_create_user(struct user_struct *up) { return 0; } - -#endif /* CONFIG_USER_SCHED */ - -#if defined(CONFIG_USER_SCHED) && defined(CONFIG_SYSFS) - -static struct user_struct *uid_hash_find(uid_t uid, struct hlist_head *hashent) -{ - struct user_struct *user; - struct hlist_node *h; - - hlist_for_each_entry(user, h, hashent, uidhash_node) { - if (user->uid == uid) { - /* possibly resurrect an "almost deleted" object */ - if (atomic_inc_return(&user->__count) == 1) - cancel_delayed_work(&user->work); - return user; - } - } - - return NULL; -} - -static struct kset *uids_kset; /* represents the /sys/kernel/uids/ directory */ -static DEFINE_MUTEX(uids_mutex); - -static inline void uids_mutex_lock(void) -{ - mutex_lock(&uids_mutex); -} - -static inline void uids_mutex_unlock(void) -{ - mutex_unlock(&uids_mutex); -} - -/* uid directory attributes */ -#ifdef CONFIG_FAIR_GROUP_SCHED -static ssize_t cpu_shares_show(struct kobject *kobj, - struct kobj_attribute *attr, - char *buf) -{ - struct user_struct *up = container_of(kobj, struct user_struct, kobj); - - return sprintf(buf, "%lu\n", sched_group_shares(up->tg)); -} - -static ssize_t cpu_shares_store(struct kobject *kobj, - struct kobj_attribute *attr, - const char *buf, size_t size) -{ - struct user_struct *up = container_of(kobj, struct user_struct, kobj); - unsigned long shares; - int rc; - - sscanf(buf, "%lu", &shares); - - rc = sched_group_set_shares(up->tg, shares); - - return (rc ? rc : size); -} - -static struct kobj_attribute cpu_share_attr = - __ATTR(cpu_share, 0644, cpu_shares_show, cpu_shares_store); -#endif - -#ifdef CONFIG_RT_GROUP_SCHED -static ssize_t cpu_rt_runtime_show(struct kobject *kobj, - struct kobj_attribute *attr, - char *buf) -{ - struct user_struct *up = container_of(kobj, struct user_struct, kobj); - - return sprintf(buf, "%ld\n", sched_group_rt_runtime(up->tg)); -} - -static ssize_t cpu_rt_runtime_store(struct kobject *kobj, - struct kobj_attribute *attr, - const char *buf, size_t size) -{ - struct user_struct *up = container_of(kobj, struct user_struct, kobj); - unsigned long rt_runtime; - int rc; - - sscanf(buf, "%ld", &rt_runtime); - - rc = sched_group_set_rt_runtime(up->tg, rt_runtime); - - return (rc ? rc : size); -} - -static struct kobj_attribute cpu_rt_runtime_attr = - __ATTR(cpu_rt_runtime, 0644, cpu_rt_runtime_show, cpu_rt_runtime_store); - -static ssize_t cpu_rt_period_show(struct kobject *kobj, - struct kobj_attribute *attr, - char *buf) -{ - struct user_struct *up = container_of(kobj, struct user_struct, kobj); - - return sprintf(buf, "%lu\n", sched_group_rt_period(up->tg)); -} - -static ssize_t cpu_rt_period_store(struct kobject *kobj, - struct kobj_attribute *attr, - const char *buf, size_t size) -{ - struct user_struct *up = container_of(kobj, struct user_struct, kobj); - unsigned long rt_period; - int rc; - - sscanf(buf, "%lu", &rt_period); - - rc = sched_group_set_rt_period(up->tg, rt_period); - - return (rc ? rc : size); -} - -static struct kobj_attribute cpu_rt_period_attr = - __ATTR(cpu_rt_period, 0644, cpu_rt_period_show, cpu_rt_period_store); -#endif - -/* default attributes per uid directory */ -static struct attribute *uids_attributes[] = { -#ifdef CONFIG_FAIR_GROUP_SCHED - &cpu_share_attr.attr, -#endif -#ifdef CONFIG_RT_GROUP_SCHED - &cpu_rt_runtime_attr.attr, - &cpu_rt_period_attr.attr, -#endif - NULL -}; - -/* the lifetime of user_struct is not managed by the core (now) */ -static void uids_release(struct kobject *kobj) -{ - return; -} - -static struct kobj_type uids_ktype = { - .sysfs_ops = &kobj_sysfs_ops, - .default_attrs = uids_attributes, - .release = uids_release, -}; - -/* - * Create /sys/kernel/uids//cpu_share file for this user - * We do not create this file for users in a user namespace (until - * sysfs tagging is implemented). - * - * See Documentation/scheduler/sched-design-CFS.txt for ramifications. - */ -static int uids_user_create(struct user_struct *up) -{ - struct kobject *kobj = &up->kobj; - int error; - - memset(kobj, 0, sizeof(struct kobject)); - if (up->user_ns != &init_user_ns) - return 0; - kobj->kset = uids_kset; - error = kobject_init_and_add(kobj, &uids_ktype, NULL, "%d", up->uid); - if (error) { - kobject_put(kobj); - goto done; - } - - kobject_uevent(kobj, KOBJ_ADD); -done: - return error; -} - -/* create these entries in sysfs: - * "/sys/kernel/uids" directory - * "/sys/kernel/uids/0" directory (for root user) - * "/sys/kernel/uids/0/cpu_share" file (for root user) - */ -int __init uids_sysfs_init(void) -{ - uids_kset = kset_create_and_add("uids", NULL, kernel_kobj); - if (!uids_kset) - return -ENOMEM; - - return uids_user_create(&root_user); -} - -/* delayed work function to remove sysfs directory for a user and free up - * corresponding structures. - */ -static void cleanup_user_struct(struct work_struct *w) -{ - struct user_struct *up = container_of(w, struct user_struct, work.work); - unsigned long flags; - int remove_user = 0; - - /* Make uid_hash_remove() + sysfs_remove_file() + kobject_del() - * atomic. - */ - uids_mutex_lock(); - - spin_lock_irqsave(&uidhash_lock, flags); - if (atomic_read(&up->__count) == 0) { - uid_hash_remove(up); - remove_user = 1; - } - spin_unlock_irqrestore(&uidhash_lock, flags); - - if (!remove_user) - goto done; - - if (up->user_ns == &init_user_ns) { - kobject_uevent(&up->kobj, KOBJ_REMOVE); - kobject_del(&up->kobj); - kobject_put(&up->kobj); - } - - sched_destroy_user(up); - key_put(up->uid_keyring); - key_put(up->session_keyring); - kmem_cache_free(uid_cachep, up); - -done: - uids_mutex_unlock(); -} - -/* IRQs are disabled and uidhash_lock is held upon function entry. - * IRQ state (as stored in flags) is restored and uidhash_lock released - * upon function exit. - */ -static void free_user(struct user_struct *up, unsigned long flags) -{ - INIT_DELAYED_WORK(&up->work, cleanup_user_struct); - schedule_delayed_work(&up->work, msecs_to_jiffies(1000)); - spin_unlock_irqrestore(&uidhash_lock, flags); -} - -#else /* CONFIG_USER_SCHED && CONFIG_SYSFS */ - static struct user_struct *uid_hash_find(uid_t uid, struct hlist_head *hashent) { struct user_struct *user; @@ -352,45 +86,20 @@ static struct user_struct *uid_hash_find return NULL; } -int uids_sysfs_init(void) { return 0; } -static inline int uids_user_create(struct user_struct *up) { return 0; } -static inline void uids_mutex_lock(void) { } -static inline void uids_mutex_unlock(void) { } - /* IRQs are disabled and uidhash_lock is held upon function entry. * IRQ state (as stored in flags) is restored and uidhash_lock released * upon function exit. */ static void free_user(struct user_struct *up, unsigned long flags) + __releases(&uidhash_lock) { uid_hash_remove(up); spin_unlock_irqrestore(&uidhash_lock, flags); - sched_destroy_user(up); key_put(up->uid_keyring); key_put(up->session_keyring); kmem_cache_free(uid_cachep, up); } -#endif - -#if defined(CONFIG_RT_GROUP_SCHED) && defined(CONFIG_USER_SCHED) -/* - * We need to check if a setuid can take place. This function should be called - * before successfully completing the setuid. - */ -int task_can_switch_user(struct user_struct *up, struct task_struct *tsk) -{ - - return sched_rt_can_attach(up->tg, tsk); - -} -#else -int task_can_switch_user(struct user_struct *up, struct task_struct *tsk) -{ - return 1; -} -#endif - /* * Locate the user_struct for the passed UID. If found, take a ref on it. The * caller must undo that ref with free_uid(). @@ -428,11 +137,7 @@ struct user_struct *alloc_uid(struct use struct hlist_head *hashent = uidhashentry(ns, uid); struct user_struct *up, *new; - /* Make uid_hash_find() + uids_user_create() + uid_hash_insert() - * atomic. - */ - uids_mutex_lock(); - + /* Make uid_hash_find() + uid_hash_insert() atomic. */ spin_lock_irq(&uidhash_lock); up = uid_hash_find(uid, hashent); spin_unlock_irq(&uidhash_lock); @@ -445,14 +150,8 @@ struct user_struct *alloc_uid(struct use new->uid = uid; atomic_set(&new->__count, 1); - if (sched_create_user(new) < 0) - goto out_free_user; - new->user_ns = get_user_ns(ns); - if (uids_user_create(new)) - goto out_destoy_sched; - /* * Before adding this, check whether we raced * on adding the same user already.. @@ -460,11 +159,6 @@ struct user_struct *alloc_uid(struct use spin_lock_irq(&uidhash_lock); up = uid_hash_find(uid, hashent); if (up) { - /* This case is not possible when CONFIG_USER_SCHED - * is defined, since we serialize alloc_uid() using - * uids_mutex. Hence no need to call - * sched_destroy_user() or remove_user_sysfs_dir(). - */ key_put(new->uid_keyring); key_put(new->session_keyring); kmem_cache_free(uid_cachep, new); @@ -475,17 +169,9 @@ struct user_struct *alloc_uid(struct use spin_unlock_irq(&uidhash_lock); } - uids_mutex_unlock(); - return up; -out_destoy_sched: - sched_destroy_user(new); - put_user_ns(new->user_ns); -out_free_user: - kmem_cache_free(uid_cachep, new); out_unlock: - uids_mutex_unlock(); return NULL; } --- a/net/core/filter.c +++ b/net/core/filter.c @@ -111,39 +111,41 @@ EXPORT_SYMBOL(sk_filter); */ unsigned int sk_run_filter(struct sk_buff *skb, struct sock_filter *filter, int flen) { - struct sock_filter *fentry; /* We walk down these */ void *ptr; u32 A = 0; /* Accumulator */ u32 X = 0; /* Index Register */ u32 mem[BPF_MEMWORDS]; /* Scratch Memory Store */ + unsigned long memvalid = 0; u32 tmp; int k; int pc; + BUILD_BUG_ON(BPF_MEMWORDS > BITS_PER_LONG); /* * Process array of filter instructions. */ for (pc = 0; pc < flen; pc++) { - fentry = &filter[pc]; + const struct sock_filter *fentry = &filter[pc]; + u32 f_k = fentry->k; switch (fentry->code) { case BPF_ALU|BPF_ADD|BPF_X: A += X; continue; case BPF_ALU|BPF_ADD|BPF_K: - A += fentry->k; + A += f_k; continue; case BPF_ALU|BPF_SUB|BPF_X: A -= X; continue; case BPF_ALU|BPF_SUB|BPF_K: - A -= fentry->k; + A -= f_k; continue; case BPF_ALU|BPF_MUL|BPF_X: A *= X; continue; case BPF_ALU|BPF_MUL|BPF_K: - A *= fentry->k; + A *= f_k; continue; case BPF_ALU|BPF_DIV|BPF_X: if (X == 0) @@ -151,49 +153,49 @@ unsigned int sk_run_filter(struct sk_buf A /= X; continue; case BPF_ALU|BPF_DIV|BPF_K: - A /= fentry->k; + A /= f_k; continue; case BPF_ALU|BPF_AND|BPF_X: A &= X; continue; case BPF_ALU|BPF_AND|BPF_K: - A &= fentry->k; + A &= f_k; continue; case BPF_ALU|BPF_OR|BPF_X: A |= X; continue; case BPF_ALU|BPF_OR|BPF_K: - A |= fentry->k; + A |= f_k; continue; case BPF_ALU|BPF_LSH|BPF_X: A <<= X; continue; case BPF_ALU|BPF_LSH|BPF_K: - A <<= fentry->k; + A <<= f_k; continue; case BPF_ALU|BPF_RSH|BPF_X: A >>= X; continue; case BPF_ALU|BPF_RSH|BPF_K: - A >>= fentry->k; + A >>= f_k; continue; case BPF_ALU|BPF_NEG: A = -A; continue; case BPF_JMP|BPF_JA: - pc += fentry->k; + pc += f_k; continue; case BPF_JMP|BPF_JGT|BPF_K: - pc += (A > fentry->k) ? fentry->jt : fentry->jf; + pc += (A > f_k) ? fentry->jt : fentry->jf; continue; case BPF_JMP|BPF_JGE|BPF_K: - pc += (A >= fentry->k) ? fentry->jt : fentry->jf; + pc += (A >= f_k) ? fentry->jt : fentry->jf; continue; case BPF_JMP|BPF_JEQ|BPF_K: - pc += (A == fentry->k) ? fentry->jt : fentry->jf; + pc += (A == f_k) ? fentry->jt : fentry->jf; continue; case BPF_JMP|BPF_JSET|BPF_K: - pc += (A & fentry->k) ? fentry->jt : fentry->jf; + pc += (A & f_k) ? fentry->jt : fentry->jf; continue; case BPF_JMP|BPF_JGT|BPF_X: pc += (A > X) ? fentry->jt : fentry->jf; @@ -208,7 +210,7 @@ unsigned int sk_run_filter(struct sk_buf pc += (A & X) ? fentry->jt : fentry->jf; continue; case BPF_LD|BPF_W|BPF_ABS: - k = fentry->k; + k = f_k; load_w: ptr = load_pointer(skb, k, 4, &tmp); if (ptr != NULL) { @@ -217,7 +219,7 @@ load_w: } break; case BPF_LD|BPF_H|BPF_ABS: - k = fentry->k; + k = f_k; load_h: ptr = load_pointer(skb, k, 2, &tmp); if (ptr != NULL) { @@ -226,7 +228,7 @@ load_h: } break; case BPF_LD|BPF_B|BPF_ABS: - k = fentry->k; + k = f_k; load_b: ptr = load_pointer(skb, k, 1, &tmp); if (ptr != NULL) { @@ -241,32 +243,34 @@ load_b: X = skb->len; continue; case BPF_LD|BPF_W|BPF_IND: - k = X + fentry->k; + k = X + f_k; goto load_w; case BPF_LD|BPF_H|BPF_IND: - k = X + fentry->k; + k = X + f_k; goto load_h; case BPF_LD|BPF_B|BPF_IND: - k = X + fentry->k; + k = X + f_k; goto load_b; case BPF_LDX|BPF_B|BPF_MSH: - ptr = load_pointer(skb, fentry->k, 1, &tmp); + ptr = load_pointer(skb, f_k, 1, &tmp); if (ptr != NULL) { X = (*(u8 *)ptr & 0xf) << 2; continue; } return 0; case BPF_LD|BPF_IMM: - A = fentry->k; + A = f_k; continue; case BPF_LDX|BPF_IMM: - X = fentry->k; + X = f_k; continue; case BPF_LD|BPF_MEM: - A = mem[fentry->k]; + A = (memvalid & (1UL << f_k)) ? + mem[f_k] : 0; continue; case BPF_LDX|BPF_MEM: - X = mem[fentry->k]; + X = (memvalid & (1UL << f_k)) ? + mem[f_k] : 0; continue; case BPF_MISC|BPF_TAX: X = A; @@ -275,14 +279,16 @@ load_b: A = X; continue; case BPF_RET|BPF_K: - return fentry->k; + return f_k; case BPF_RET|BPF_A: return A; case BPF_ST: - mem[fentry->k] = A; + memvalid |= 1UL << f_k; + mem[f_k] = A; continue; case BPF_STX: - mem[fentry->k] = X; + memvalid |= 1UL << f_k; + mem[f_k] = X; continue; default: WARN_ON(1); --- a/net/dccp/input.c +++ b/net/dccp/input.c @@ -616,6 +616,9 @@ int dccp_rcv_state_process(struct sock * /* Caller (dccp_v4_do_rcv) will send Reset */ dcb->dccpd_reset_code = DCCP_RESET_CODE_NO_CONNECTION; return 1; + } else if (sk->sk_state == DCCP_CLOSED) { + dcb->dccpd_reset_code = DCCP_RESET_CODE_NO_CONNECTION; + return 1; } if (sk->sk_state != DCCP_REQUESTING && sk->sk_state != DCCP_RESPOND) { @@ -678,10 +681,6 @@ int dccp_rcv_state_process(struct sock * } switch (sk->sk_state) { - case DCCP_CLOSED: - dcb->dccpd_reset_code = DCCP_RESET_CODE_NO_CONNECTION; - return 1; - case DCCP_REQUESTING: queued = dccp_rcv_request_sent_state_process(sk, skb, dh, len); if (queued >= 0) --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1032,6 +1032,21 @@ static inline bool inetdev_valid_mtu(uns return mtu >= 68; } +static void inetdev_send_gratuitous_arp(struct net_device *dev, + struct in_device *in_dev) + +{ + struct in_ifaddr *ifa = in_dev->ifa_list; + + if (!ifa) + return; + + arp_send(ARPOP_REQUEST, ETH_P_ARP, + ifa->ifa_address, dev, + ifa->ifa_address, NULL, + dev->dev_addr, NULL); +} + /* Called only under RTNL semaphore */ static int inetdev_event(struct notifier_block *this, unsigned long event, @@ -1083,18 +1098,13 @@ static int inetdev_event(struct notifier } ip_mc_up(in_dev); /* fall through */ - case NETDEV_NOTIFY_PEERS: case NETDEV_CHANGEADDR: + if (!IN_DEV_ARP_NOTIFY(in_dev)) + break; + /* fall through */ + case NETDEV_NOTIFY_PEERS: /* Send gratuitous ARP to notify of link change */ - if (IN_DEV_ARP_NOTIFY(in_dev)) { - struct in_ifaddr *ifa = in_dev->ifa_list; - - if (ifa) - arp_send(ARPOP_REQUEST, ETH_P_ARP, - ifa->ifa_address, dev, - ifa->ifa_address, NULL, - dev->dev_addr, NULL); - } + inetdev_send_gratuitous_arp(dev, in_dev); break; case NETDEV_DOWN: ip_mc_down(in_dev); --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2117,7 +2117,7 @@ static int do_tcp_setsockopt(struct sock /* Values greater than interface MTU won't take effect. However * at the point when this call is done we typically don't yet * know which interface is going to be used */ - if (val < 8 || val > MAX_TCP_WINDOW) { + if (val < TCP_MIN_MSS || val > MAX_TCP_WINDOW) { err = -EINVAL; break; } --- a/net/sched/cls_cgroup.c +++ b/net/sched/cls_cgroup.c @@ -110,7 +110,7 @@ static int cls_cgroup_classify(struct sk * calls by looking at the number of nested bh disable calls because * softirqs always disables bh. */ - if (softirq_count() != SOFTIRQ_OFFSET) + if (in_serving_softirq()) return -1; rcu_read_lock(); --- a/net/sctp/auth.c +++ b/net/sctp/auth.c @@ -542,16 +542,20 @@ struct sctp_hmac *sctp_auth_asoc_get_hma id = ntohs(hmacs->hmac_ids[i]); /* Check the id is in the supported range */ - if (id > SCTP_AUTH_HMAC_ID_MAX) + if (id > SCTP_AUTH_HMAC_ID_MAX) { + id = 0; continue; + } /* See is we support the id. Supported IDs have name and * length fields set, so that we can allocated and use * them. We can safely just check for name, for without the * name, we can't allocate the TFM. */ - if (!sctp_hmac_list[id].hmac_name) + if (!sctp_hmac_list[id].hmac_name) { + id = 0; continue; + } break; } --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -3361,21 +3361,6 @@ int sctp_process_asconf_ack(struct sctp_ sctp_chunk_free(asconf); asoc->addip_last_asconf = NULL; - /* Send the next asconf chunk from the addip chunk queue. */ - if (!list_empty(&asoc->addip_chunk_list)) { - struct list_head *entry = asoc->addip_chunk_list.next; - asconf = list_entry(entry, struct sctp_chunk, list); - - list_del_init(entry); - - /* Hold the chunk until an ASCONF_ACK is received. */ - sctp_chunk_hold(asconf); - if (sctp_primitive_ASCONF(asoc, asconf)) - sctp_chunk_free(asconf); - else - asoc->addip_last_asconf = asconf; - } - return retval; } --- a/net/sctp/sm_sideeffect.c +++ b/net/sctp/sm_sideeffect.c @@ -997,6 +997,29 @@ static int sctp_cmd_send_msg(struct sctp } +/* Sent the next ASCONF packet currently stored in the association. + * This happens after the ASCONF_ACK was succeffully processed. + */ +static void sctp_cmd_send_asconf(struct sctp_association *asoc) +{ + /* Send the next asconf chunk from the addip chunk + * queue. + */ + if (!list_empty(&asoc->addip_chunk_list)) { + struct list_head *entry = asoc->addip_chunk_list.next; + struct sctp_chunk *asconf = list_entry(entry, + struct sctp_chunk, list); + list_del_init(entry); + + /* Hold the chunk until an ASCONF_ACK is received. */ + sctp_chunk_hold(asconf); + if (sctp_primitive_ASCONF(asoc, asconf)) + sctp_chunk_free(asconf); + else + asoc->addip_last_asconf = asconf; + } +} + /* These three macros allow us to pull the debugging code out of the * main flow of sctp_do_sm() to keep attention focused on the real @@ -1650,6 +1673,9 @@ static int sctp_cmd_interpreter(sctp_eve } error = sctp_cmd_send_msg(asoc, cmd->obj.msg); break; + case SCTP_CMD_SEND_NEXT_ASCONF: + sctp_cmd_send_asconf(asoc); + break; default: printk(KERN_WARNING "Impossible command: %u, %p\n", cmd->verb, cmd->obj.ptr); --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -3670,8 +3670,14 @@ sctp_disposition_t sctp_sf_do_asconf_ack SCTP_TO(SCTP_EVENT_TIMEOUT_T4_RTO)); if (!sctp_process_asconf_ack((struct sctp_association *)asoc, - asconf_ack)) + asconf_ack)) { + /* Successfully processed ASCONF_ACK. We can + * release the next asconf if we have one. + */ + sctp_add_cmd_sf(commands, SCTP_CMD_SEND_NEXT_ASCONF, + SCTP_NULL()); return SCTP_DISPOSITION_CONSUME; + } abort = sctp_make_abort(asoc, asconf_ack, sizeof(sctp_errhdr_t)); --- a/net/sunrpc/cache.c +++ b/net/sunrpc/cache.c @@ -1234,8 +1234,10 @@ static int content_open(struct inode *in if (!cd || !try_module_get(cd->owner)) return -EACCES; han = __seq_open_private(file, &cache_content_op, sizeof(*han)); - if (han == NULL) + if (han == NULL) { + module_put(cd->owner); return -ENOMEM; + } han->cd = cd; return 0; --- a/net/x25/x25_link.c +++ b/net/x25/x25_link.c @@ -391,8 +391,12 @@ void __exit x25_link_free(void) write_lock_bh(&x25_neigh_list_lock); list_for_each_safe(entry, tmp, &x25_neigh_list) { + struct net_device *dev; + nb = list_entry(entry, struct x25_neigh, node); + dev = nb->dev; __x25_remove_neigh(nb); + dev_put(dev); } write_unlock_bh(&x25_neigh_list_lock); } --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -2601,7 +2601,10 @@ static int selinux_inode_init_security(s sid = tsec->sid; newsid = tsec->create_sid; - if (!newsid || !(sbsec->flags & SE_SBLABELSUPP)) { + if ((sbsec->flags & SE_SBINITIALIZED) && + (sbsec->behavior == SECURITY_FS_USE_MNTPOINT)) + newsid = sbsec->mntpoint_sid; + else if (!newsid || !(sbsec->flags & SE_SBLABELSUPP)) { rc = security_transition_sid(sid, dsec->sid, inode_mode_to_security_class(inode->i_mode), &newsid); @@ -3259,7 +3262,11 @@ static void selinux_cred_free(struct cre { struct task_security_struct *tsec = cred->security; - BUG_ON((unsigned long) cred->security < PAGE_SIZE); + /* + * cred->security == NULL if security_cred_alloc_blank() or + * security_prepare_creds() returned an error. + */ + BUG_ON(cred->security && (unsigned long) cred->security < PAGE_SIZE); cred->security = (void *) 0x7UL; kfree(tsec); } --- a/security/selinux/nlmsgtab.c +++ b/security/selinux/nlmsgtab.c @@ -66,6 +66,8 @@ static struct nlmsg_perm nlmsg_route_per { RTM_NEWADDRLABEL, NETLINK_ROUTE_SOCKET__NLMSG_WRITE }, { RTM_DELADDRLABEL, NETLINK_ROUTE_SOCKET__NLMSG_WRITE }, { RTM_GETADDRLABEL, NETLINK_ROUTE_SOCKET__NLMSG_READ }, + { RTM_GETDCB, NETLINK_ROUTE_SOCKET__NLMSG_READ }, + { RTM_SETDCB, NETLINK_ROUTE_SOCKET__NLMSG_WRITE }, }; static struct nlmsg_perm nlmsg_firewall_perms[] = --- a/sound/core/hrtimer.c +++ b/sound/core/hrtimer.c @@ -44,12 +44,13 @@ static enum hrtimer_restart snd_hrtimer_ { struct snd_hrtimer *stime = container_of(hrt, struct snd_hrtimer, hrt); struct snd_timer *t = stime->timer; + unsigned long oruns; if (!atomic_read(&stime->running)) return HRTIMER_NORESTART; - hrtimer_forward_now(hrt, ns_to_ktime(t->sticks * resolution)); - snd_timer_interrupt(stime->timer, t->sticks); + oruns = hrtimer_forward_now(hrt, ns_to_ktime(t->sticks * resolution)); + snd_timer_interrupt(stime->timer, t->sticks * oruns); if (!atomic_read(&stime->running)) return HRTIMER_NORESTART; --- a/sound/pci/au88x0/au88x0_pcm.c +++ b/sound/pci/au88x0/au88x0_pcm.c @@ -42,11 +42,7 @@ static struct snd_pcm_hardware snd_vorte .rate_min = 5000, .rate_max = 48000, .channels_min = 1, -#ifdef CHIP_AU8830 - .channels_max = 4, -#else .channels_max = 2, -#endif .buffer_bytes_max = 0x10000, .period_bytes_min = 0x1, .period_bytes_max = 0x1000, @@ -115,6 +111,17 @@ static struct snd_pcm_hardware snd_vorte .periods_max = 64, }; #endif +#ifdef CHIP_AU8830 +static unsigned int au8830_channels[3] = { + 1, 2, 4, +}; + +static struct snd_pcm_hw_constraint_list hw_constraints_au8830_channels = { + .count = ARRAY_SIZE(au8830_channels), + .list = au8830_channels, + .mask = 0, +}; +#endif /* open callback */ static int snd_vortex_pcm_open(struct snd_pcm_substream *substream) { @@ -156,6 +163,15 @@ static int snd_vortex_pcm_open(struct sn if (VORTEX_PCM_TYPE(substream->pcm) == VORTEX_PCM_ADB || VORTEX_PCM_TYPE(substream->pcm) == VORTEX_PCM_I2S) runtime->hw = snd_vortex_playback_hw_adb; +#ifdef CHIP_AU8830 + if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK && + VORTEX_PCM_TYPE(substream->pcm) == VORTEX_PCM_ADB) { + runtime->hw.channels_max = 4; + snd_pcm_hw_constraint_list(runtime, 0, + SNDRV_PCM_HW_PARAM_CHANNELS, + &hw_constraints_au8830_channels); + } +#endif substream->runtime->private_data = NULL; } #ifndef CHIP_AU8810 --- a/sound/pci/hda/hda_eld.c +++ b/sound/pci/hda/hda_eld.c @@ -383,7 +383,7 @@ static void hdmi_show_short_audio_desc(s snd_print_pcm_rates(a->rates, buf, sizeof(buf)); if (a->format == AUDIO_CODING_TYPE_LPCM) - snd_print_pcm_bits(a->sample_bits, buf2 + 8, sizeof(buf2 - 8)); + snd_print_pcm_bits(a->sample_bits, buf2 + 8, sizeof(buf2) - 8); else if (a->max_bitrate) snprintf(buf2, sizeof(buf2), ", max bitrate = %d", a->max_bitrate); --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -2236,6 +2236,7 @@ static struct snd_pci_quirk position_fix SND_PCI_QUIRK(0x1043, 0x813d, "ASUS P5AD2", POS_FIX_LPIB), SND_PCI_QUIRK(0x1043, 0x81b3, "ASUS", POS_FIX_LPIB), SND_PCI_QUIRK(0x1043, 0x81e7, "ASUS M2V", POS_FIX_LPIB), + SND_PCI_QUIRK(0x1043, 0x8410, "ASUS", POS_FIX_LPIB), SND_PCI_QUIRK(0x104d, 0x9069, "Sony VPCS11V9E", POS_FIX_LPIB), SND_PCI_QUIRK(0x1106, 0x3288, "ASUS M2V-MX SE", POS_FIX_LPIB), SND_PCI_QUIRK(0x1179, 0xff10, "Toshiba A100-259", POS_FIX_LPIB), --- a/sound/pci/hda/patch_conexant.c +++ b/sound/pci/hda/patch_conexant.c @@ -366,10 +366,16 @@ static int conexant_add_jack(struct hda_ struct conexant_spec *spec; struct conexant_jack *jack; const char *name; - int err; + int i, err; spec = codec->spec; snd_array_init(&spec->jacks, sizeof(*jack), 32); + + jack = spec->jacks.list; + for (i = 0; i < spec->jacks.used; i++, jack++) + if (jack->nid == nid) + return 0 ; /* already present */ + jack = snd_array_new(&spec->jacks); name = (type == SND_JACK_HEADPHONE) ? "Headphone" : "Mic" ; --- a/sound/soc/blackfin/bf5xx-ac97.c +++ b/sound/soc/blackfin/bf5xx-ac97.c @@ -260,9 +260,9 @@ static int bf5xx_ac97_suspend(struct snd pr_debug("%s : sport %d\n", __func__, dai->id); if (!dai->active) return 0; - if (dai->capture.active) + if (dai->capture_active) sport_rx_stop(sport); - if (dai->playback.active) + if (dai->playback_active) sport_tx_stop(sport); return 0; } --- a/sound/soc/codecs/wm8990.c +++ b/sound/soc/codecs/wm8990.c @@ -1185,7 +1185,7 @@ static int wm8990_set_bias_level(struct WM8990_VMIDTOG); /* Delay to allow output caps to discharge */ - msleep(msecs_to_jiffies(300)); + msleep(300); /* Disable VMIDTOG */ snd_soc_write(codec, WM8990_ANTIPOP2, WM8990_SOFTST | @@ -1197,17 +1197,17 @@ static int wm8990_set_bias_level(struct /* Enable outputs */ snd_soc_write(codec, WM8990_POWER_MANAGEMENT_1, 0x1b00); - msleep(msecs_to_jiffies(50)); + msleep(50); /* Enable VMID at 2x50k */ snd_soc_write(codec, WM8990_POWER_MANAGEMENT_1, 0x1f02); - msleep(msecs_to_jiffies(100)); + msleep(100); /* Enable VREF */ snd_soc_write(codec, WM8990_POWER_MANAGEMENT_1, 0x1f03); - msleep(msecs_to_jiffies(600)); + msleep(600); /* Enable BUFIOEN */ snd_soc_write(codec, WM8990_ANTIPOP2, WM8990_SOFTST | @@ -1252,7 +1252,7 @@ static int wm8990_set_bias_level(struct /* Disable VMID */ snd_soc_write(codec, WM8990_POWER_MANAGEMENT_1, 0x1f01); - msleep(msecs_to_jiffies(300)); + msleep(300); /* Enable all output discharge bits */ snd_soc_write(codec, WM8990_ANTIPOP1, WM8990_DIS_LLINE | --- a/sound/usb/caiaq/audio.c +++ b/sound/usb/caiaq/audio.c @@ -639,7 +639,7 @@ int snd_usb_caiaq_audio_init(struct snd_ } dev->pcm->private_data = dev; - strcpy(dev->pcm->name, dev->product_name); + strlcpy(dev->pcm->name, dev->product_name, sizeof(dev->pcm->name)); memset(dev->sub_playback, 0, sizeof(dev->sub_playback)); memset(dev->sub_capture, 0, sizeof(dev->sub_capture)); --- a/sound/usb/caiaq/midi.c +++ b/sound/usb/caiaq/midi.c @@ -135,7 +135,7 @@ int snd_usb_caiaq_midi_init(struct snd_u if (ret < 0) return ret; - strcpy(rmidi->name, device->product_name); + strlcpy(rmidi->name, device->product_name, sizeof(rmidi->name)); rmidi->info_flags = SNDRV_RAWMIDI_INFO_DUPLEX; rmidi->private_data = device; --- a/sound/usb/usx2y/us122l.c +++ b/sound/usb/usx2y/us122l.c @@ -234,29 +234,26 @@ static unsigned int usb_stream_hwdep_pol struct file *file, poll_table *wait) { struct us122l *us122l = hw->private_data; - struct usb_stream *s = us122l->sk.s; unsigned *polled; unsigned int mask; poll_wait(file, &us122l->sk.sleep, wait); - switch (s->state) { - case usb_stream_ready: - if (us122l->first == file) - polled = &s->periods_polled; - else - polled = &us122l->second_periods_polled; - if (*polled != s->periods_done) { - *polled = s->periods_done; - mask = POLLIN | POLLOUT | POLLWRNORM; - break; + mask = POLLIN | POLLOUT | POLLWRNORM | POLLERR; + if (mutex_trylock(&us122l->mutex)) { + struct usb_stream *s = us122l->sk.s; + if (s && s->state == usb_stream_ready) { + if (us122l->first == file) + polled = &s->periods_polled; + else + polled = &us122l->second_periods_polled; + if (*polled != s->periods_done) { + *polled = s->periods_done; + mask = POLLIN | POLLOUT | POLLWRNORM; + } else + mask = 0; } - /* Fall through */ - mask = 0; - break; - default: - mask = POLLIN | POLLOUT | POLLWRNORM | POLLERR; - break; + mutex_unlock(&us122l->mutex); } return mask; } @@ -342,6 +339,7 @@ static int usb_stream_hwdep_ioctl(struct { struct usb_stream_config *cfg; struct us122l *us122l = hw->private_data; + struct usb_stream *s; unsigned min_period_frames; int err = 0; bool high_speed; @@ -387,18 +385,18 @@ static int usb_stream_hwdep_ioctl(struct snd_power_wait(hw->card, SNDRV_CTL_POWER_D0); mutex_lock(&us122l->mutex); + s = us122l->sk.s; if (!us122l->master) us122l->master = file; else if (us122l->master != file) { - if (memcmp(cfg, &us122l->sk.s->cfg, sizeof(*cfg))) { + if (!s || memcmp(cfg, &s->cfg, sizeof(*cfg))) { err = -EIO; goto unlock; } us122l->slave = file; } - if (!us122l->sk.s || - memcmp(cfg, &us122l->sk.s->cfg, sizeof(*cfg)) || - us122l->sk.s->state == usb_stream_xrun) { + if (!s || memcmp(cfg, &s->cfg, sizeof(*cfg)) || + s->state == usb_stream_xrun) { us122l_stop(us122l); if (!us122l_start(us122l, cfg->sample_rate, cfg->period_frames)) err = -EIO; @@ -409,6 +407,7 @@ unlock: mutex_unlock(&us122l->mutex); free: kfree(cfg); + wake_up_all(&us122l->sk.sleep); return err; }