diff --git a/Documentation/filesystems/ext4.txt b/Documentation/filesystems/ext4.txt index cec829b..5c484ae 100644 --- a/Documentation/filesystems/ext4.txt +++ b/Documentation/filesystems/ext4.txt @@ -85,7 +85,7 @@ Note: More extensive information for getting started with ext4 can be * extent format more robust in face of on-disk corruption due to magics, * internal redundancy in tree * improved file allocation (multi-block alloc) -* fix 32000 subdirectory limit +* lift 32000 subdirectory limit imposed by i_links_count[1] * nsec timestamps for mtime, atime, ctime, create time * inode version field on disk (NFSv4, Lustre) * reduced e2fsck time via uninit_bg feature @@ -100,6 +100,9 @@ Note: More extensive information for getting started with ext4 can be * efficent new ordered mode in JBD2 and ext4(avoid using buffer head to force the ordering) +[1] Filesystems with a block size of 1k may see a limit imposed by the +directory hash tree having a maximum depth of two. + 2.2 Candidate features for future inclusion * Online defrag (patches available but not well tested) diff --git a/arch/powerpc/mm/tlb_nohash_low.S b/arch/powerpc/mm/tlb_nohash_low.S index f900a39..3bc41c3 100644 --- a/arch/powerpc/mm/tlb_nohash_low.S +++ b/arch/powerpc/mm/tlb_nohash_low.S @@ -161,6 +161,6 @@ _GLOBAL(_tlbil_va) isync 1: wrtee r10 blr -#elif +#else #error Unsupported processor type ! #endif diff --git a/arch/sparc/kernel/of_device_32.c b/arch/sparc/kernel/of_device_32.c index 0a83bd7..c8f14c1 100644 --- a/arch/sparc/kernel/of_device_32.c +++ b/arch/sparc/kernel/of_device_32.c @@ -246,8 +246,25 @@ static unsigned long of_bus_pci_get_flags(const u32 *addr, unsigned long flags) static int of_bus_sbus_match(struct device_node *np) { - return !strcmp(np->name, "sbus") || - !strcmp(np->name, "sbi"); + struct device_node *dp = np; + + while (dp) { + if (!strcmp(dp->name, "sbus") || + !strcmp(dp->name, "sbi")) + return 1; + + /* Have a look at use_1to1_mapping(). We're trying + * to match SBUS if that's the top-level bus and we + * don't have some intervening real bus that provides + * ranges based translations. + */ + if (of_find_property(dp, "ranges", NULL) != NULL) + break; + + dp = dp->parent; + } + + return 0; } static void of_bus_sbus_count_cells(struct device_node *child, diff --git a/arch/sparc/kernel/of_device_64.c b/arch/sparc/kernel/of_device_64.c index b4a12c9..9013c4b 100644 --- a/arch/sparc/kernel/of_device_64.c +++ b/arch/sparc/kernel/of_device_64.c @@ -301,8 +301,25 @@ static unsigned long of_bus_pci_get_flags(const u32 *addr, unsigned long flags) static int of_bus_sbus_match(struct device_node *np) { - return !strcmp(np->name, "sbus") || - !strcmp(np->name, "sbi"); + struct device_node *dp = np; + + while (dp) { + if (!strcmp(dp->name, "sbus") || + !strcmp(dp->name, "sbi")) + return 1; + + /* Have a look at use_1to1_mapping(). We're trying + * to match SBUS if that's the top-level bus and we + * don't have some intervening real bus that provides + * ranges based translations. + */ + if (of_find_property(dp, "ranges", NULL) != NULL) + break; + + dp = dp->parent; + } + + return 0; } static void of_bus_sbus_count_cells(struct device_node *child, diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c index 79457f6..a35fef7 100644 --- a/arch/sparc/kernel/smp_64.c +++ b/arch/sparc/kernel/smp_64.c @@ -118,9 +118,9 @@ void __cpuinit smp_callin(void) while (!cpu_isset(cpuid, smp_commenced_mask)) rmb(); - ipi_call_lock(); + ipi_call_lock_irq(); cpu_set(cpuid, cpu_online_map); - ipi_call_unlock(); + ipi_call_unlock_irq(); /* idle thread is expected to have preempt disabled */ preempt_disable(); diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index a00545f..db3134f 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -191,27 +191,42 @@ static struct clock_event_device hpet_clockevent = { .rating = 50, }; -static void hpet_start_counter(void) +static void hpet_stop_counter(void) { unsigned long cfg = hpet_readl(HPET_CFG); - cfg &= ~HPET_CFG_ENABLE; hpet_writel(cfg, HPET_CFG); +} + +static void hpet_reset_counter(void) +{ hpet_writel(0, HPET_COUNTER); hpet_writel(0, HPET_COUNTER + 4); +} + +static void hpet_start_counter(void) +{ + unsigned long cfg = hpet_readl(HPET_CFG); cfg |= HPET_CFG_ENABLE; hpet_writel(cfg, HPET_CFG); } +static void hpet_restart_counter(void) +{ + hpet_stop_counter(); + hpet_reset_counter(); + hpet_start_counter(); +} + static void hpet_resume_device(void) { force_hpet_resume(); } -static void hpet_restart_counter(void) +static void hpet_resume_counter(void) { hpet_resume_device(); - hpet_start_counter(); + hpet_restart_counter(); } static void hpet_enable_legacy_int(void) @@ -264,6 +279,7 @@ static void hpet_set_mode(enum clock_event_mode mode, switch (mode) { case CLOCK_EVT_MODE_PERIODIC: + hpet_stop_counter(); delta = ((uint64_t)(NSEC_PER_SEC/HZ)) * evt->mult; delta >>= evt->shift; now = hpet_readl(HPET_COUNTER); @@ -274,14 +290,17 @@ static void hpet_set_mode(enum clock_event_mode mode, cfg |= HPET_TN_ENABLE | HPET_TN_PERIODIC | HPET_TN_SETVAL | HPET_TN_32BIT; hpet_writel(cfg, HPET_Tn_CFG(timer)); - /* - * The first write after writing TN_SETVAL to the - * config register sets the counter value, the second - * write sets the period. - */ hpet_writel(cmp, HPET_Tn_CMP(timer)); udelay(1); + /* + * HPET on AMD 81xx needs a second write (with HPET_TN_SETVAL + * cleared) to T0_CMP to set the period. The HPET_TN_SETVAL + * bit is automatically cleared after the first write. + * (See AMD-8111 HyperTransport I/O Hub Data Sheet, + * Publication # 24674) + */ hpet_writel((unsigned long) delta, HPET_Tn_CMP(timer)); + hpet_start_counter(); break; case CLOCK_EVT_MODE_ONESHOT: @@ -695,7 +714,7 @@ static struct clocksource clocksource_hpet = { .mask = HPET_MASK, .shift = HPET_SHIFT, .flags = CLOCK_SOURCE_IS_CONTINUOUS, - .resume = hpet_restart_counter, + .resume = hpet_resume_counter, #ifdef CONFIG_X86_64 .vread = vread_hpet, #endif @@ -707,7 +726,7 @@ static int hpet_clocksource_register(void) cycle_t t1; /* Start the counter */ - hpet_start_counter(); + hpet_restart_counter(); /* Verify whether hpet counter works */ t1 = read_hpet(); diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 8005da2..2d2affd 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -2906,8 +2906,7 @@ static int kvm_pv_mmu_write(struct kvm_vcpu *vcpu, static int kvm_pv_mmu_flush_tlb(struct kvm_vcpu *vcpu) { - kvm_x86_ops->tlb_flush(vcpu); - set_bit(KVM_REQ_MMU_SYNC, &vcpu->requests); + kvm_set_cr3(vcpu, vcpu->arch.cr3); return 1; } diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 92f0457..570184a 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -334,6 +334,9 @@ EXPORT_SYMBOL_GPL(kvm_lmsw); void kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) { + unsigned long old_cr4 = vcpu->arch.cr4; + unsigned long pdptr_bits = X86_CR4_PGE | X86_CR4_PSE | X86_CR4_PAE; + if (cr4 & CR4_RESERVED_BITS) { printk(KERN_DEBUG "set_cr4: #GP, reserved bits\n"); kvm_inject_gp(vcpu, 0); @@ -347,7 +350,8 @@ void kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) kvm_inject_gp(vcpu, 0); return; } - } else if (is_paging(vcpu) && !is_pae(vcpu) && (cr4 & X86_CR4_PAE) + } else if (is_paging(vcpu) && (cr4 & X86_CR4_PAE) + && ((cr4 ^ old_cr4) & pdptr_bits) && !load_pdptrs(vcpu, vcpu->arch.cr3)) { printk(KERN_DEBUG "set_cr4: #GP, pdptrs reserved bits\n"); kvm_inject_gp(vcpu, 0); diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c index 8f307d9..f46c340 100644 --- a/arch/x86/mm/hugetlbpage.c +++ b/arch/x86/mm/hugetlbpage.c @@ -26,12 +26,16 @@ static unsigned long page_table_shareable(struct vm_area_struct *svma, unsigned long sbase = saddr & PUD_MASK; unsigned long s_end = sbase + PUD_SIZE; + /* Allow segments to share if only one is marked locked */ + unsigned long vm_flags = vma->vm_flags & ~VM_LOCKED; + unsigned long svm_flags = svma->vm_flags & ~VM_LOCKED; + /* * match the virtual addresses, permission and the alignment of the * page table page. */ if (pmd_index(addr) != pmd_index(saddr) || - vma->vm_flags != svma->vm_flags || + vm_flags != svm_flags || sbase < svma->vm_start || svma->vm_end < s_end) return 0; diff --git a/arch/x86/pci/mmconfig-shared.c b/arch/x86/pci/mmconfig-shared.c index 9136946..d6033b8 100644 --- a/arch/x86/pci/mmconfig-shared.c +++ b/arch/x86/pci/mmconfig-shared.c @@ -254,7 +254,7 @@ static acpi_status __init check_mcfg_resource(struct acpi_resource *res, if (!fixmem32) return AE_OK; if ((mcfg_res->start >= fixmem32->address) && - (mcfg_res->end <= (fixmem32->address + + (mcfg_res->end < (fixmem32->address + fixmem32->address_length))) { mcfg_res->flags = 1; return AE_CTRL_TERMINATE; @@ -271,7 +271,7 @@ static acpi_status __init check_mcfg_resource(struct acpi_resource *res, return AE_OK; if ((mcfg_res->start >= address.minimum) && - (mcfg_res->end <= (address.minimum + address.address_length))) { + (mcfg_res->end < (address.minimum + address.address_length))) { mcfg_res->flags = 1; return AE_CTRL_TERMINATE; } @@ -297,7 +297,7 @@ static int __init is_acpi_reserved(u64 start, u64 end, unsigned not_used) struct resource mcfg_res; mcfg_res.start = start; - mcfg_res.end = end; + mcfg_res.end = end - 1; mcfg_res.flags = 0; acpi_get_devices("PNP0C01", find_mboard_resource, &mcfg_res, NULL); diff --git a/crypto/api.c b/crypto/api.c index 38a2bc0..e7aa72d 100644 --- a/crypto/api.c +++ b/crypto/api.c @@ -221,7 +221,8 @@ struct crypto_alg *crypto_larval_lookup(const char *name, u32 type, u32 mask) request_module(name); - if (!((type ^ CRYPTO_ALG_NEED_FALLBACK) & mask) && + if (!((type ^ CRYPTO_ALG_NEED_FALLBACK) & mask & + CRYPTO_ALG_NEED_FALLBACK) && snprintf(tmp, sizeof(tmp), "%s-all", name) < sizeof(tmp)) request_module(tmp); diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c index 7bc22a4..61f6b7a 100644 --- a/drivers/acpi/processor_idle.c +++ b/drivers/acpi/processor_idle.c @@ -212,6 +212,9 @@ static void acpi_timer_check_state(int state, struct acpi_processor *pr, struct acpi_processor_power *pwr = &pr->power; u8 type = local_apic_timer_c2_ok ? ACPI_STATE_C3 : ACPI_STATE_C2; + if (boot_cpu_has(X86_FEATURE_AMDC1E)) + type = ACPI_STATE_C1; + /* * Check, if one of the previous states already marked the lapic * unstable @@ -648,6 +651,7 @@ static int acpi_processor_power_verify(struct acpi_processor *pr) switch (cx->type) { case ACPI_STATE_C1: cx->valid = 1; + acpi_timer_check_state(i, pr, cx); break; case ACPI_STATE_C2: @@ -866,17 +870,19 @@ static int acpi_idle_enter_c1(struct cpuidle_device *dev, /* Do not access any ACPI IO ports in suspend path */ if (acpi_idle_suspend) { - acpi_safe_halt(); local_irq_enable(); + cpu_relax(); return 0; } + acpi_state_timer_broadcast(pr, cx, 1); t1 = inl(acpi_gbl_FADT.xpm_timer_block.address); acpi_idle_do_entry(cx); t2 = inl(acpi_gbl_FADT.xpm_timer_block.address); local_irq_enable(); cx->usage++; + acpi_state_timer_broadcast(pr, cx, 0); return ticks_elapsed_in_us(t1, t2); } diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index 8f90508..6971a12 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -977,8 +977,10 @@ static void backend_changed(struct xenbus_device *dev, break; case XenbusStateClosing: - if (info->gd == NULL) - xenbus_dev_fatal(dev, -ENODEV, "gd is NULL"); + if (info->gd == NULL) { + xenbus_frontend_closed(dev); + break; + } bd = bdget_disk(info->gd, 0); if (bd == NULL) xenbus_dev_fatal(dev, -ENODEV, "bdget failed"); diff --git a/drivers/char/random.c b/drivers/char/random.c index 7c13581..1801245 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -1660,15 +1660,20 @@ EXPORT_SYMBOL(secure_dccp_sequence_number); * value is not cryptographically secure but for several uses the cost of * depleting entropy is too high */ +DEFINE_PER_CPU(__u32 [4], get_random_int_hash); unsigned int get_random_int(void) { - /* - * Use IP's RNG. It suits our purpose perfectly: it re-keys itself - * every second, from the entropy pool (and thus creates a limited - * drain on it), and uses halfMD4Transform within the second. We - * also mix it with jiffies and the PID: - */ - return secure_ip_id((__force __be32)(current->pid + jiffies)); + struct keydata *keyptr; + __u32 *hash = get_cpu_var(get_random_int_hash); + int ret; + + keyptr = get_keyptr(); + hash[0] += current->pid + jiffies + get_cycles(); + + ret = half_md4_transform(hash, keyptr->secret); + put_cpu_var(get_random_int_hash); + + return ret; } /* diff --git a/drivers/char/tpm/tpm_bios.c b/drivers/char/tpm/tpm_bios.c index ed306eb..0c2f55a 100644 --- a/drivers/char/tpm/tpm_bios.c +++ b/drivers/char/tpm/tpm_bios.c @@ -212,7 +212,8 @@ static int get_event_name(char *dest, struct tcpa_event *event, unsigned char * event_entry) { const char *name = ""; - char data[40] = ""; + /* 41 so there is room for 40 data and 1 nul */ + char data[41] = ""; int i, n_len = 0, d_len = 0; struct tcpa_pc_event *pc_event; diff --git a/drivers/crypto/padlock-aes.c b/drivers/crypto/padlock-aes.c index 3f0fdd1..856b3cc 100644 --- a/drivers/crypto/padlock-aes.c +++ b/drivers/crypto/padlock-aes.c @@ -489,4 +489,4 @@ MODULE_DESCRIPTION("VIA PadLock AES algorithm support"); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Michal Ludvig"); -MODULE_ALIAS("aes-all"); +MODULE_ALIAS("aes"); diff --git a/drivers/gpu/drm/r128/r128_cce.c b/drivers/gpu/drm/r128/r128_cce.c index c31afbd..c41f339 100644 --- a/drivers/gpu/drm/r128/r128_cce.c +++ b/drivers/gpu/drm/r128/r128_cce.c @@ -511,9 +511,9 @@ static int r128_do_init_cce(struct drm_device * dev, drm_r128_init_t * init) #if __OS_HAS_AGP if (!dev_priv->is_pci) { - drm_core_ioremap(dev_priv->cce_ring, dev); - drm_core_ioremap(dev_priv->ring_rptr, dev); - drm_core_ioremap(dev->agp_buffer_map, dev); + drm_core_ioremap_wc(dev_priv->cce_ring, dev); + drm_core_ioremap_wc(dev_priv->ring_rptr, dev); + drm_core_ioremap_wc(dev->agp_buffer_map, dev); if (!dev_priv->cce_ring->handle || !dev_priv->ring_rptr->handle || !dev->agp_buffer_map->handle) { diff --git a/drivers/hid/usbhid/hid-core.c b/drivers/hid/usbhid/hid-core.c index f0a0f72..5e60131 100644 --- a/drivers/hid/usbhid/hid-core.c +++ b/drivers/hid/usbhid/hid-core.c @@ -765,7 +765,7 @@ static int usbhid_parse(struct hid_device *hid) goto err; } - hid->quirks = quirks; + hid->quirks |= quirks; return 0; err: diff --git a/drivers/hwmon/lm78.c b/drivers/hwmon/lm78.c index b5e3b28..a1787fd 100644 --- a/drivers/hwmon/lm78.c +++ b/drivers/hwmon/lm78.c @@ -182,7 +182,7 @@ static struct platform_driver lm78_isa_driver = { .name = "lm78", }, .probe = lm78_isa_probe, - .remove = lm78_isa_remove, + .remove = __devexit_p(lm78_isa_remove), }; diff --git a/drivers/ide/ide-io.c b/drivers/ide/ide-io.c index af70777..ff8229c 100644 --- a/drivers/ide/ide-io.c +++ b/drivers/ide/ide-io.c @@ -967,7 +967,7 @@ void ide_timer_expiry (unsigned long data) } spin_lock_irq(&hwif->lock); enable_irq(hwif->irq); - if (startstop == ide_stopped) { + if (startstop == ide_stopped && hwif->polling == 0) { ide_unlock_port(hwif); plug_device = 1; } @@ -1145,7 +1145,7 @@ irqreturn_t ide_intr (int irq, void *dev_id) * same irq as is currently being serviced here, and Linux * won't allow another of the same (on any CPU) until we return. */ - if (startstop == ide_stopped) { + if (startstop == ide_stopped && hwif->polling == 0) { BUG_ON(hwif->handler); ide_unlock_port(hwif); plug_device = 1; diff --git a/drivers/ide/ide-iops.c b/drivers/ide/ide-iops.c index b1892bd..5defb72 100644 --- a/drivers/ide/ide-iops.c +++ b/drivers/ide/ide-iops.c @@ -587,8 +587,6 @@ EXPORT_SYMBOL_GPL(ide_in_drive_list); /* * Early UDMA66 devices don't set bit14 to 1, only bit13 is valid. - * We list them here and depend on the device side cable detection for them. - * * Some optical devices with the buggy firmwares have the same problem. */ static const struct drive_list_entry ivb_list[] = { @@ -632,10 +630,25 @@ u8 eighty_ninty_three (ide_drive_t *drive) * - force bit13 (80c cable present) check also for !ivb devices * (unless the slave device is pre-ATA3) */ - if ((id[ATA_ID_HW_CONFIG] & 0x4000) || - (ivb && (id[ATA_ID_HW_CONFIG] & 0x2000))) + if (id[ATA_ID_HW_CONFIG] & 0x4000) return 1; + if (ivb) { + const char *model = (char *)&id[ATA_ID_PROD]; + + if (strstr(model, "TSSTcorp CDDVDW SH-S202")) { + /* + * These ATAPI devices always report 80c cable + * so we have to depend on the host in this case. + */ + if (hwif->cbl == ATA_CBL_PATA80) + return 1; + } else { + /* Depend on the device side cable detection. */ + if (id[ATA_ID_HW_CONFIG] & 0x2000) + return 1; + } + } no_80w: if (drive->dev_flags & IDE_DFLAG_UDMA33_WARNED) return 0; diff --git a/drivers/ide/ide-pci-generic.c b/drivers/ide/ide-pci-generic.c index bddae2b..515fd4e 100644 --- a/drivers/ide/ide-pci-generic.c +++ b/drivers/ide/ide-pci-generic.c @@ -35,6 +35,16 @@ MODULE_PARM_DESC(all_generic_ide, "IDE generic will claim all unknown PCI IDE st #define IDE_HFLAGS_UMC (IDE_HFLAG_NO_DMA | IDE_HFLAG_FORCE_LEGACY_IRQS) +static void netcell_quirkproc(ide_drive_t *drive) +{ + /* mark words 85-87 as valid */ + drive->id[ATA_ID_CSF_DEFAULT] |= 0x4000; +} + +static const struct ide_port_ops netcell_port_ops = { + .quirkproc = netcell_quirkproc, +}; + #define DECLARE_GENERIC_PCI_DEV(extra_flags) \ { \ .name = DRV_NAME, \ @@ -76,6 +86,7 @@ static const struct ide_port_info generic_chipsets[] __devinitdata = { { /* 6: Revolution */ .name = DRV_NAME, + .port_ops = &netcell_port_ops, .host_flags = IDE_HFLAG_CLEAR_SIMPLEX | IDE_HFLAG_TRUST_BIOS_FOR_DMA | IDE_HFLAG_OFF_BOARD, diff --git a/drivers/ide/ide-tape.c b/drivers/ide/ide-tape.c index 4e6181c..af7860c 100644 --- a/drivers/ide/ide-tape.c +++ b/drivers/ide/ide-tape.c @@ -654,12 +654,6 @@ static ide_startstop_t idetape_issue_pc(ide_drive_t *drive, { idetape_tape_t *tape = drive->driver_data; - if (drive->pc->c[0] == REQUEST_SENSE && - pc->c[0] == REQUEST_SENSE) { - printk(KERN_ERR "ide-tape: possible ide-tape.c bug - " - "Two request sense in serial were issued\n"); - } - if (tape->failed_pc == NULL && pc->c[0] != REQUEST_SENSE) tape->failed_pc = pc; diff --git a/drivers/mtd/devices/mtd_dataflash.c b/drivers/mtd/devices/mtd_dataflash.c index 6d9f810..635c787 100644 --- a/drivers/mtd/devices/mtd_dataflash.c +++ b/drivers/mtd/devices/mtd_dataflash.c @@ -184,7 +184,7 @@ static int dataflash_erase(struct mtd_info *mtd, struct erase_info *instr) /* Calculate flash page address; use block erase (for speed) if * we're at a block boundary and need to erase the whole block. */ - pageaddr = div_u64(instr->len, priv->page_size); + pageaddr = div_u64(instr->addr, priv->page_size); do_block = (pageaddr & 0x7) == 0 && instr->len >= blocksize; pageaddr = pageaddr << priv->page_offset; diff --git a/drivers/net/Makefile b/drivers/net/Makefile index 471baaf..ac7b12c 100644 --- a/drivers/net/Makefile +++ b/drivers/net/Makefile @@ -100,7 +100,7 @@ obj-$(CONFIG_HAMACHI) += hamachi.o obj-$(CONFIG_NET) += Space.o loopback.o obj-$(CONFIG_SEEQ8005) += seeq8005.o obj-$(CONFIG_NET_SB1000) += sb1000.o -obj-$(CONFIG_MAC8390) += mac8390.o 8390.o +obj-$(CONFIG_MAC8390) += mac8390.o obj-$(CONFIG_APNE) += apne.o 8390.o obj-$(CONFIG_PCMCIA_PCNET) += 8390.o obj-$(CONFIG_HP100) += hp100.o diff --git a/drivers/net/bnx2.c b/drivers/net/bnx2.c index 6b6530f..a7e688a 100644 --- a/drivers/net/bnx2.c +++ b/drivers/net/bnx2.c @@ -2585,6 +2585,7 @@ bnx2_get_hw_tx_cons(struct bnx2_napi *bnapi) /* Tell compiler that status block fields can change. */ barrier(); cons = *bnapi->hw_tx_cons_ptr; + barrier(); if (unlikely((cons & MAX_TX_DESC_CNT) == MAX_TX_DESC_CNT)) cons++; return cons; @@ -2864,6 +2865,7 @@ bnx2_get_hw_rx_cons(struct bnx2_napi *bnapi) /* Tell compiler that status block fields can change. */ barrier(); cons = *bnapi->hw_rx_cons_ptr; + barrier(); if (unlikely((cons & MAX_RX_DESC_CNT) == MAX_RX_DESC_CNT)) cons++; return cons; diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c index 27fb7f5..77da4c5 100644 --- a/drivers/net/bonding/bond_alb.c +++ b/drivers/net/bonding/bond_alb.c @@ -370,8 +370,6 @@ static int rlb_arp_recv(struct sk_buff *skb, struct net_device *bond_dev, struct if (arp->op_code == htons(ARPOP_REPLY)) { /* update rx hash table for this ARP */ - printk("rar: update orig %s bond_dev %s\n", orig_dev->name, - bond_dev->name); bond = netdev_priv(bond_dev); rlb_update_entry_from_arp(bond, arp); pr_debug("Server received an ARP Reply from client\n"); @@ -1739,9 +1737,6 @@ int bond_alb_set_mac_address(struct net_device *bond_dev, void *addr) } } - write_unlock_bh(&bond->curr_slave_lock); - read_unlock(&bond->lock); - if (swap_slave) { alb_swap_mac_addr(bond, swap_slave, bond->curr_active_slave); alb_fasten_mac_swap(bond, swap_slave, bond->curr_active_slave); @@ -1749,16 +1744,15 @@ int bond_alb_set_mac_address(struct net_device *bond_dev, void *addr) alb_set_slave_mac_addr(bond->curr_active_slave, bond_dev->dev_addr, bond->alb_info.rlb_enabled); + read_lock(&bond->lock); alb_send_learning_packets(bond->curr_active_slave, bond_dev->dev_addr); if (bond->alb_info.rlb_enabled) { /* inform clients mac address has changed */ rlb_req_update_slave_clients(bond, bond->curr_active_slave); } + read_unlock(&bond->lock); } - read_lock(&bond->lock); - write_lock_bh(&bond->curr_slave_lock); - return 0; } diff --git a/drivers/net/e1000/e1000_main.c b/drivers/net/e1000/e1000_main.c index d436e27..df6459c 100644 --- a/drivers/net/e1000/e1000_main.c +++ b/drivers/net/e1000/e1000_main.c @@ -4009,8 +4009,9 @@ static bool e1000_clean_rx_irq(struct e1000_adapter *adapter, PCI_DMA_FROMDEVICE); length = le16_to_cpu(rx_desc->length); - - if (unlikely(!(status & E1000_RXD_STAT_EOP))) { + /* !EOP means multiple descriptors were used to store a single + * packet, also make sure the frame isn't just CRC only */ + if (unlikely(!(status & E1000_RXD_STAT_EOP) || (length <= 4))) { /* All receives must fit into a single buffer */ E1000_DBG("%s: Receive packet consumed multiple" " buffers\n", netdev->name); diff --git a/drivers/net/igb/igb_ethtool.c b/drivers/net/igb/igb_ethtool.c index 3c831f1..44ceb36 100644 --- a/drivers/net/igb/igb_ethtool.c +++ b/drivers/net/igb/igb_ethtool.c @@ -2024,6 +2024,10 @@ static struct ethtool_ops igb_ethtool_ops = { .get_ethtool_stats = igb_get_ethtool_stats, .get_coalesce = igb_get_coalesce, .set_coalesce = igb_set_coalesce, + .get_flags = ethtool_op_get_flags, +#ifdef CONFIG_IGB_LRO + .set_flags = ethtool_op_set_flags, +#endif }; void igb_set_ethtool_ops(struct net_device *netdev) diff --git a/drivers/net/mac8390.c b/drivers/net/mac8390.c index 8e88486..f26667d 100644 --- a/drivers/net/mac8390.c +++ b/drivers/net/mac8390.c @@ -304,7 +304,7 @@ struct net_device * __init mac8390_probe(int unit) if (!MACH_IS_MAC) return ERR_PTR(-ENODEV); - dev = alloc_ei_netdev(); + dev = ____alloc_ei_netdev(0); if (!dev) return ERR_PTR(-ENOMEM); @@ -481,10 +481,10 @@ void cleanup_module(void) static const struct net_device_ops mac8390_netdev_ops = { .ndo_open = mac8390_open, .ndo_stop = mac8390_close, - .ndo_start_xmit = ei_start_xmit, - .ndo_tx_timeout = ei_tx_timeout, - .ndo_get_stats = ei_get_stats, - .ndo_set_multicast_list = ei_set_multicast_list, + .ndo_start_xmit = __ei_start_xmit, + .ndo_tx_timeout = __ei_tx_timeout, + .ndo_get_stats = __ei_get_stats, + .ndo_set_multicast_list = __ei_set_multicast_list, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = eth_mac_addr, .ndo_change_mtu = eth_change_mtu, diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index 7e24b50..f5824af 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -329,7 +329,8 @@ static u32 macvlan_ethtool_get_rx_csum(struct net_device *dev) const struct macvlan_dev *vlan = netdev_priv(dev); struct net_device *lowerdev = vlan->lowerdev; - if (lowerdev->ethtool_ops->get_rx_csum == NULL) + if (lowerdev->ethtool_ops == NULL || + lowerdev->ethtool_ops->get_rx_csum == NULL) return 0; return lowerdev->ethtool_ops->get_rx_csum(lowerdev); } @@ -340,7 +341,8 @@ static int macvlan_ethtool_get_settings(struct net_device *dev, const struct macvlan_dev *vlan = netdev_priv(dev); struct net_device *lowerdev = vlan->lowerdev; - if (!lowerdev->ethtool_ops->get_settings) + if (!lowerdev->ethtool_ops || + !lowerdev->ethtool_ops->get_settings) return -EOPNOTSUPP; return lowerdev->ethtool_ops->get_settings(lowerdev, cmd); @@ -351,7 +353,8 @@ static u32 macvlan_ethtool_get_flags(struct net_device *dev) const struct macvlan_dev *vlan = netdev_priv(dev); struct net_device *lowerdev = vlan->lowerdev; - if (!lowerdev->ethtool_ops->get_flags) + if (!lowerdev->ethtool_ops || + !lowerdev->ethtool_ops->get_flags) return 0; return lowerdev->ethtool_ops->get_flags(lowerdev); } diff --git a/drivers/net/myri10ge/myri10ge.c b/drivers/net/myri10ge/myri10ge.c index e9c1296..53ff238 100644 --- a/drivers/net/myri10ge/myri10ge.c +++ b/drivers/net/myri10ge/myri10ge.c @@ -2446,6 +2446,7 @@ static int myri10ge_open(struct net_device *dev) lro_mgr->lro_arr = ss->rx_done.lro_desc; lro_mgr->get_frag_header = myri10ge_get_frag_header; lro_mgr->max_aggr = myri10ge_lro_max_pkts; + lro_mgr->frag_align_pad = 2; if (lro_mgr->max_aggr > MAX_SKB_FRAGS) lro_mgr->max_aggr = MAX_SKB_FRAGS; diff --git a/drivers/net/r8169.c b/drivers/net/r8169.c index 9201e5a..0b8ec7f 100644 --- a/drivers/net/r8169.c +++ b/drivers/net/r8169.c @@ -3554,54 +3554,64 @@ static irqreturn_t rtl8169_interrupt(int irq, void *dev_instance) int handled = 0; int status; + /* loop handling interrupts until we have no new ones or + * we hit a invalid/hotplug case. + */ status = RTL_R16(IntrStatus); + while (status && status != 0xffff) { + handled = 1; - /* hotplug/major error/no more work/shared irq */ - if ((status == 0xffff) || !status) - goto out; - - handled = 1; + /* Handle all of the error cases first. These will reset + * the chip, so just exit the loop. + */ + if (unlikely(!netif_running(dev))) { + rtl8169_asic_down(ioaddr); + break; + } - if (unlikely(!netif_running(dev))) { - rtl8169_asic_down(ioaddr); - goto out; - } + /* Work around for rx fifo overflow */ + if (unlikely(status & RxFIFOOver) && + (tp->mac_version == RTL_GIGA_MAC_VER_11)) { + netif_stop_queue(dev); + rtl8169_tx_timeout(dev); + break; + } - status &= tp->intr_mask; - RTL_W16(IntrStatus, - (status & RxFIFOOver) ? (status | RxOverflow) : status); + if (unlikely(status & SYSErr)) { + rtl8169_pcierr_interrupt(dev); + break; + } - if (!(status & tp->intr_event)) - goto out; + if (status & LinkChg) + rtl8169_check_link_status(dev, tp, ioaddr); - /* Work around for rx fifo overflow */ - if (unlikely(status & RxFIFOOver) && - (tp->mac_version == RTL_GIGA_MAC_VER_11)) { - netif_stop_queue(dev); - rtl8169_tx_timeout(dev); - goto out; - } + /* We need to see the lastest version of tp->intr_mask to + * avoid ignoring an MSI interrupt and having to wait for + * another event which may never come. + */ + smp_rmb(); + if (status & tp->intr_mask & tp->napi_event) { + RTL_W16(IntrMask, tp->intr_event & ~tp->napi_event); + tp->intr_mask = ~tp->napi_event; + + if (likely(netif_rx_schedule_prep(&tp->napi))) + __netif_rx_schedule(&tp->napi); + else if (netif_msg_intr(tp)) { + printk(KERN_INFO "%s: interrupt %04x in poll\n", + dev->name, status); + } + } - if (unlikely(status & SYSErr)) { - rtl8169_pcierr_interrupt(dev); - goto out; + /* We only get a new MSI interrupt when all active irq + * sources on the chip have been acknowledged. So, ack + * everything we've seen and check if new sources have become + * active to avoid blocking all interrupts from the chip. + */ + RTL_W16(IntrStatus, + (status & RxFIFOOver) ? (status | RxOverflow) : status); + status = RTL_R16(IntrStatus); } - if (status & LinkChg) - rtl8169_check_link_status(dev, tp, ioaddr); - - if (status & tp->napi_event) { - RTL_W16(IntrMask, tp->intr_event & ~tp->napi_event); - tp->intr_mask = ~tp->napi_event; - - if (likely(netif_rx_schedule_prep(&tp->napi))) - __netif_rx_schedule(&tp->napi); - else if (netif_msg_intr(tp)) { - printk(KERN_INFO "%s: interrupt %04x in poll\n", - dev->name, status); - } - } -out: return IRQ_RETVAL(handled); } @@ -3617,13 +3627,15 @@ static int rtl8169_poll(struct napi_struct *napi, int budget) if (work_done < budget) { netif_rx_complete(napi); - tp->intr_mask = 0xffff; - /* - * 20040426: the barrier is not strictly required but the - * behavior of the irq handler could be less predictable - * without it. Btw, the lack of flush for the posted pci - * write is safe - FR + + /* We need for force the visibility of tp->intr_mask + * for other CPUs, as we can loose an MSI interrupt + * and potentially wait for a retransmit timeout if we don't. + * The posted write to IntrMask is safe, as it will + * eventually make it to the chip and we won't loose anything + * until it does. */ + tp->intr_mask = 0xffff; smp_wmb(); RTL_W16(IntrMask, tp->intr_event); } diff --git a/drivers/net/wireless/iwlwifi/iwl-sta.c b/drivers/net/wireless/iwlwifi/iwl-sta.c index 70a8b21..ab621b0 100644 --- a/drivers/net/wireless/iwlwifi/iwl-sta.c +++ b/drivers/net/wireless/iwlwifi/iwl-sta.c @@ -708,6 +708,14 @@ static int iwl_set_tkip_dynamic_key_info(struct iwl_priv *priv, { unsigned long flags; int ret = 0; + __le16 key_flags = 0; + + key_flags |= (STA_KEY_FLG_TKIP | STA_KEY_FLG_MAP_KEY_MSK); + key_flags |= cpu_to_le16(keyconf->keyidx << STA_KEY_FLG_KEYID_POS); + key_flags &= ~STA_KEY_FLG_INVALID; + + if (sta_id == priv->hw_params.bcast_sta_id) + key_flags |= STA_KEY_MULTICAST_MSK; keyconf->flags |= IEEE80211_KEY_FLAG_GENERATE_IV; keyconf->flags |= IEEE80211_KEY_FLAG_GENERATE_MMIC; @@ -727,6 +735,9 @@ static int iwl_set_tkip_dynamic_key_info(struct iwl_priv *priv, WARN(priv->stations[sta_id].sta.key.key_offset == WEP_INVALID_OFFSET, "no space for new kew"); + priv->stations[sta_id].sta.key.key_flags = key_flags; + + /* This copy is acutally not needed: we get the key with each TX */ memcpy(priv->stations[sta_id].keyinfo.key, keyconf->key, 16); @@ -743,9 +754,7 @@ void iwl_update_tkip_key(struct iwl_priv *priv, { u8 sta_id = IWL_INVALID_STATION; unsigned long flags; - __le16 key_flags = 0; int i; - DECLARE_MAC_BUF(mac); sta_id = iwl_find_station(priv, addr); if (sta_id == IWL_INVALID_STATION) { @@ -760,16 +769,8 @@ void iwl_update_tkip_key(struct iwl_priv *priv, return; } - key_flags |= (STA_KEY_FLG_TKIP | STA_KEY_FLG_MAP_KEY_MSK); - key_flags |= cpu_to_le16(keyconf->keyidx << STA_KEY_FLG_KEYID_POS); - key_flags &= ~STA_KEY_FLG_INVALID; - - if (sta_id == priv->hw_params.bcast_sta_id) - key_flags |= STA_KEY_MULTICAST_MSK; - spin_lock_irqsave(&priv->sta_lock, flags); - priv->stations[sta_id].sta.key.key_flags = key_flags; priv->stations[sta_id].sta.key.tkip_rx_tsc_byte2 = (u8) iv32; for (i = 0; i < 5; i++) diff --git a/drivers/scsi/3w-xxxx.c b/drivers/scsi/3w-xxxx.c index c03f1d2..faa0fcf 100644 --- a/drivers/scsi/3w-xxxx.c +++ b/drivers/scsi/3w-xxxx.c @@ -6,7 +6,7 @@ Arnaldo Carvalho de Melo Brad Strand - Copyright (C) 1999-2007 3ware Inc. + Copyright (C) 1999-2009 3ware Inc. Kernel compatiblity By: Andre Hedrick Non-Copyright (C) 2000 Andre Hedrick @@ -1294,7 +1294,8 @@ static void tw_unmap_scsi_data(struct pci_dev *pdev, struct scsi_cmnd *cmd) { dprintk(KERN_WARNING "3w-xxxx: tw_unmap_scsi_data()\n"); - scsi_dma_unmap(cmd); + if (cmd->SCp.phase == TW_PHASE_SGLIST) + scsi_dma_unmap(cmd); } /* End tw_unmap_scsi_data() */ /* This function will reset a device extension */ diff --git a/drivers/scsi/3w-xxxx.h b/drivers/scsi/3w-xxxx.h index 0742e68..e938615 100644 --- a/drivers/scsi/3w-xxxx.h +++ b/drivers/scsi/3w-xxxx.h @@ -6,7 +6,7 @@ Arnaldo Carvalho de Melo Brad Strand - Copyright (C) 1999-2007 3ware Inc. + Copyright (C) 1999-2009 3ware Inc. Kernel compatiblity By: Andre Hedrick Non-Copyright (C) 2000 Andre Hedrick diff --git a/drivers/serial/icom.c b/drivers/serial/icom.c index 2b7531d..08eefec 100644 --- a/drivers/serial/icom.c +++ b/drivers/serial/icom.c @@ -1482,8 +1482,8 @@ static void icom_remove_adapter(struct icom_adapter *icom_adapter) free_irq(icom_adapter->pci_dev->irq, (void *) icom_adapter); iounmap(icom_adapter->base_addr); - icom_free_adapter(icom_adapter); pci_release_regions(icom_adapter->pci_dev); + icom_free_adapter(icom_adapter); } static void icom_kref_release(struct kref *kref) diff --git a/drivers/serial/mpc52xx_uart.c b/drivers/serial/mpc52xx_uart.c index 28d2c8d..28b07ce 100644 --- a/drivers/serial/mpc52xx_uart.c +++ b/drivers/serial/mpc52xx_uart.c @@ -988,7 +988,7 @@ mpc52xx_console_setup(struct console *co, char *options) pr_debug("mpc52xx_console_setup co=%p, co->index=%i, options=%s\n", co, co->index, options); - if ((co->index < 0) || (co->index > MPC52xx_PSC_MAXNUM)) { + if ((co->index < 0) || (co->index >= MPC52xx_PSC_MAXNUM)) { pr_debug("PSC%x out of range\n", co->index); return -EINVAL; } diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c index b3d5a23..7f2909a 100644 --- a/drivers/usb/class/cdc-acm.c +++ b/drivers/usb/class/cdc-acm.c @@ -546,10 +546,6 @@ static int acm_tty_open(struct tty_struct *tty, struct file *filp) tty->driver_data = acm; acm->tty = tty; - /* force low_latency on so that our tty_push actually forces the data through, - otherwise it is scheduled, and with high data rates data can get lost. */ - tty->low_latency = 1; - if (usb_autopm_get_interface(acm->control) < 0) goto early_bail; else diff --git a/drivers/usb/host/isp1760-hcd.c b/drivers/usb/host/isp1760-hcd.c index b899f1a..f14d74f 100644 --- a/drivers/usb/host/isp1760-hcd.c +++ b/drivers/usb/host/isp1760-hcd.c @@ -1644,6 +1644,7 @@ static int isp1760_urb_dequeue(struct usb_hcd *hcd, struct urb *urb, u32 reg_base, or_reg, skip_reg; unsigned long flags; struct ptd ptd; + packet_enqueue *pe; switch (usb_pipetype(urb->pipe)) { case PIPE_ISOCHRONOUS: @@ -1655,6 +1656,7 @@ static int isp1760_urb_dequeue(struct usb_hcd *hcd, struct urb *urb, reg_base = INT_REGS_OFFSET; or_reg = HC_INT_IRQ_MASK_OR_REG; skip_reg = HC_INT_PTD_SKIPMAP_REG; + pe = enqueue_an_INT_packet; break; default: @@ -1662,6 +1664,7 @@ static int isp1760_urb_dequeue(struct usb_hcd *hcd, struct urb *urb, reg_base = ATL_REGS_OFFSET; or_reg = HC_ATL_IRQ_MASK_OR_REG; skip_reg = HC_ATL_PTD_SKIPMAP_REG; + pe = enqueue_an_ATL_packet; break; } @@ -1673,6 +1676,7 @@ static int isp1760_urb_dequeue(struct usb_hcd *hcd, struct urb *urb, u32 skip_map; u32 or_map; struct isp1760_qtd *qtd; + struct isp1760_qh *qh = ints->qh; skip_map = isp1760_readl(hcd->regs + skip_reg); skip_map |= 1 << i; @@ -1685,8 +1689,7 @@ static int isp1760_urb_dequeue(struct usb_hcd *hcd, struct urb *urb, priv_write_copy(priv, (u32 *)&ptd, hcd->regs + reg_base + i * sizeof(ptd), sizeof(ptd)); qtd = ints->qtd; - - clean_up_qtdlist(qtd); + qtd = clean_up_qtdlist(qtd); free_mem(priv, ints->payload); @@ -1697,7 +1700,24 @@ static int isp1760_urb_dequeue(struct usb_hcd *hcd, struct urb *urb, ints->payload = 0; isp1760_urb_done(priv, urb, status); + if (qtd) + pe(hcd, qh, qtd); break; + + } else if (ints->qtd) { + struct isp1760_qtd *qtd, *prev_qtd = ints->qtd; + + for (qtd = ints->qtd->hw_next; qtd; qtd = qtd->hw_next) { + if (qtd->urb == urb) { + prev_qtd->hw_next = clean_up_qtdlist(qtd); + isp1760_urb_done(priv, urb, status); + break; + } + prev_qtd = qtd; + } + /* we found the urb before the end of the list */ + if (qtd) + break; } ints++; } diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c index 5daa517..4423875 100644 --- a/drivers/usb/serial/ftdi_sio.c +++ b/drivers/usb/serial/ftdi_sio.c @@ -1485,14 +1485,7 @@ static int ftdi_sio_port_remove(struct usb_serial_port *port) remove_sysfs_attrs(port); - /* all open ports are closed at this point - * (by usbserial.c:__serial_close, which calls ftdi_close) - */ - - if (priv) { - usb_set_serial_port_data(port, NULL); - kref_put(&priv->kref, ftdi_sio_priv_release); - } + kref_put(&priv->kref, ftdi_sio_priv_release); return 0; } diff --git a/drivers/usb/serial/usb-serial.c b/drivers/usb/serial/usb-serial.c index 4b36d88..61b7d9e 100644 --- a/drivers/usb/serial/usb-serial.c +++ b/drivers/usb/serial/usb-serial.c @@ -978,6 +978,7 @@ int usb_serial_probe(struct usb_interface *interface, if (retval > 0) { /* quietly accept this device, but don't bind to a serial port as it's about to disappear */ + serial->num_ports = 0; goto exit; } } diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 90909f9..a2bd86e 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -248,6 +248,30 @@ struct flex_groups { #define EXT4_FL_USER_VISIBLE 0x000BDFFF /* User visible flags */ #define EXT4_FL_USER_MODIFIABLE 0x000B80FF /* User modifiable flags */ +/* Flags that should be inherited by new inodes from their parent. */ +#define EXT4_FL_INHERITED (EXT4_SECRM_FL | EXT4_UNRM_FL | EXT4_COMPR_FL |\ + EXT4_SYNC_FL | EXT4_IMMUTABLE_FL | EXT4_APPEND_FL |\ + EXT4_NODUMP_FL | EXT4_NOATIME_FL |\ + EXT4_NOCOMPR_FL | EXT4_JOURNAL_DATA_FL |\ + EXT4_NOTAIL_FL | EXT4_DIRSYNC_FL) + +/* Flags that are appropriate for regular files (all but dir-specific ones). */ +#define EXT4_REG_FLMASK (~(EXT4_DIRSYNC_FL | EXT4_TOPDIR_FL)) + +/* Flags that are appropriate for non-directories/regular files. */ +#define EXT4_OTHER_FLMASK (EXT4_NODUMP_FL | EXT4_NOATIME_FL) + +/* Mask out flags that are inappropriate for the given type of inode. */ +static inline __u32 ext4_mask_flags(umode_t mode, __u32 flags) +{ + if (S_ISDIR(mode)) + return flags; + else if (S_ISREG(mode)) + return flags & EXT4_REG_FLMASK; + else + return flags & EXT4_OTHER_FLMASK; +} + /* * Inode dynamic state flags */ @@ -255,6 +279,7 @@ struct flex_groups { #define EXT4_STATE_NEW 0x00000002 /* inode is newly created */ #define EXT4_STATE_XATTR 0x00000004 /* has in-inode xattrs */ #define EXT4_STATE_NO_EXPAND 0x00000008 /* No space for expansion */ +#define EXT4_STATE_DA_ALLOC_CLOSE 0x00000010 /* Alloc DA blks on close */ /* Used to pass group descriptor data when online resize is done */ struct ext4_new_group_input { @@ -302,7 +327,9 @@ struct ext4_new_group_data { #define EXT4_IOC_GROUP_EXTEND _IOW('f', 7, unsigned long) #define EXT4_IOC_GROUP_ADD _IOW('f', 8, struct ext4_new_group_input) #define EXT4_IOC_MIGRATE _IO('f', 9) + /* note ioctl 10 reserved for an early version of the FIEMAP ioctl */ /* note ioctl 11 reserved for filesystem-independent FIEMAP ioctl */ +#define EXT4_IOC_ALLOC_DA_BLKS _IO('f', 12) /* * ioctl commands in 32 bit emulation @@ -530,7 +557,7 @@ do { \ #define EXT4_MOUNT_NO_UID32 0x02000 /* Disable 32-bit UIDs */ #define EXT4_MOUNT_XATTR_USER 0x04000 /* Extended user attributes */ #define EXT4_MOUNT_POSIX_ACL 0x08000 /* POSIX Access Control Lists */ -#define EXT4_MOUNT_RESERVATION 0x10000 /* Preallocation */ +#define EXT4_MOUNT_NO_AUTO_DA_ALLOC 0x10000 /* No auto delalloc mapping */ #define EXT4_MOUNT_BARRIER 0x20000 /* Use block barriers */ #define EXT4_MOUNT_NOBH 0x40000 /* No bufferheads */ #define EXT4_MOUNT_QUOTA 0x80000 /* Some quota option set */ @@ -1091,6 +1118,7 @@ extern int ext4_can_truncate(struct inode *inode); extern void ext4_truncate(struct inode *); extern void ext4_set_inode_flags(struct inode *); extern void ext4_get_inode_flags(struct ext4_inode_info *); +extern int ext4_alloc_da_blocks(struct inode *inode); extern void ext4_set_aops(struct inode *inode); extern int ext4_writepage_trans_blocks(struct inode *); extern int ext4_meta_trans_blocks(struct inode *, int nrblocks, int idxblocks); diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index e0aa4fe..8723d0b 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -1740,11 +1740,13 @@ ext4_ext_put_in_cache(struct inode *inode, ext4_lblk_t block, { struct ext4_ext_cache *cex; BUG_ON(len == 0); + spin_lock(&EXT4_I(inode)->i_block_reservation_lock); cex = &EXT4_I(inode)->i_cached_extent; cex->ec_type = type; cex->ec_block = block; cex->ec_len = len; cex->ec_start = start; + spin_unlock(&EXT4_I(inode)->i_block_reservation_lock); } /* @@ -1801,12 +1803,17 @@ ext4_ext_in_cache(struct inode *inode, ext4_lblk_t block, struct ext4_extent *ex) { struct ext4_ext_cache *cex; + int ret = EXT4_EXT_CACHE_NO; + /* + * We borrow i_block_reservation_lock to protect i_cached_extent + */ + spin_lock(&EXT4_I(inode)->i_block_reservation_lock); cex = &EXT4_I(inode)->i_cached_extent; /* has cache valid data? */ if (cex->ec_type == EXT4_EXT_CACHE_NO) - return EXT4_EXT_CACHE_NO; + goto errout; BUG_ON(cex->ec_type != EXT4_EXT_CACHE_GAP && cex->ec_type != EXT4_EXT_CACHE_EXTENT); @@ -1817,11 +1824,11 @@ ext4_ext_in_cache(struct inode *inode, ext4_lblk_t block, ext_debug("%u cached by %u:%u:%llu\n", block, cex->ec_block, cex->ec_len, cex->ec_start); - return cex->ec_type; + ret = cex->ec_type; } - - /* not in cache */ - return EXT4_EXT_CACHE_NO; +errout: + spin_unlock(&EXT4_I(inode)->i_block_reservation_lock); + return ret; } /* @@ -2776,6 +2783,8 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode, if (allocated > max_blocks) allocated = max_blocks; set_buffer_unwritten(bh_result); + bh_result->b_bdev = inode->i_sb->s_bdev; + bh_result->b_blocknr = newblock; goto out2; } diff --git a/fs/ext4/file.c b/fs/ext4/file.c index f731cb5..588af8c 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -33,9 +33,14 @@ */ static int ext4_release_file(struct inode *inode, struct file *filp) { + if (EXT4_I(inode)->i_state & EXT4_STATE_DA_ALLOC_CLOSE) { + ext4_alloc_da_blocks(inode); + EXT4_I(inode)->i_state &= ~EXT4_STATE_DA_ALLOC_CLOSE; + } /* if we are the last writer on the inode, drop the block reservation */ if ((filp->f_mode & FMODE_WRITE) && - (atomic_read(&inode->i_writecount) == 1)) + (atomic_read(&inode->i_writecount) == 1) && + !EXT4_I(inode)->i_reserved_data_blocks) { down_write(&EXT4_I(inode)->i_data_sem); ext4_discard_preallocations(inode); diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index 2d2b358..345cba1 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -720,11 +720,12 @@ struct inode *ext4_new_inode(handle_t *handle, struct inode *dir, int mode) ret2 = find_group_flex(sb, dir, &group); if (ret2 == -1) { ret2 = find_group_other(sb, dir, &group); - if (ret2 == 0 && once) + if (ret2 == 0 && once) { once = 0; printk(KERN_NOTICE "ext4: find_group_flex " "failed, fallback succeeded dir %lu\n", dir->i_ino); + } } goto got_group; } @@ -885,16 +886,12 @@ got: ei->i_disksize = 0; /* - * Don't inherit extent flag from directory. We set extent flag on - * newly created directory and file only if -o extent mount option is - * specified + * Don't inherit extent flag from directory, amongst others. We set + * extent flag on newly created directory and file only if -o extent + * mount option is specified */ - ei->i_flags = EXT4_I(dir)->i_flags & ~(EXT4_INDEX_FL|EXT4_EXTENTS_FL); - if (S_ISLNK(mode)) - ei->i_flags &= ~(EXT4_IMMUTABLE_FL|EXT4_APPEND_FL); - /* dirsync only applies to directories */ - if (!S_ISDIR(mode)) - ei->i_flags &= ~EXT4_DIRSYNC_FL; + ei->i_flags = + ext4_mask_flags(mode, EXT4_I(dir)->i_flags & EXT4_FL_INHERITED); ei->i_file_acl = 0; ei->i_dtime = 0; ei->i_block_group = group; diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 2c0439d..725f20a 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -1036,8 +1036,15 @@ static void ext4_da_update_reserve_space(struct inode *inode, int used) /* update per-inode reservations */ BUG_ON(used > EXT4_I(inode)->i_reserved_data_blocks); EXT4_I(inode)->i_reserved_data_blocks -= used; - spin_unlock(&EXT4_I(inode)->i_block_reservation_lock); + + /* + * If we have done all the pending block allocations and if + * there aren't any writers on the inode, we can discard the + * inode's preallocations. + */ + if (!total && (atomic_read(&inode->i_writecount) == 0)) + ext4_discard_preallocations(inode); } /* @@ -1069,6 +1076,7 @@ int ext4_get_blocks_wrap(handle_t *handle, struct inode *inode, sector_t block, int retval; clear_buffer_mapped(bh); + clear_buffer_unwritten(bh); /* * Try to see if we can get the block without requesting @@ -1099,6 +1107,18 @@ int ext4_get_blocks_wrap(handle_t *handle, struct inode *inode, sector_t block, return retval; /* + * When we call get_blocks without the create flag, the + * BH_Unwritten flag could have gotten set if the blocks + * requested were part of a uninitialized extent. We need to + * clear this flag now that we are committed to convert all or + * part of the uninitialized extent to be an initialized + * extent. This is because we need to avoid the combination + * of BH_Unwritten and BH_Mapped flags being simultaneously + * set on the buffer_head. + */ + clear_buffer_unwritten(bh); + + /* * New blocks allocate and/or writing to uninitialized extent * will possibly result in updating i_data, so we take * the write lock of i_data_sem, and call get_blocks() @@ -2213,6 +2233,10 @@ static int ext4_da_get_block_prep(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create) { int ret = 0; + sector_t invalid_block = ~((sector_t) 0xffff); + + if (invalid_block < ext4_blocks_count(EXT4_SB(inode->i_sb)->s_es)) + invalid_block = ~0; BUG_ON(create == 0); BUG_ON(bh_result->b_size != inode->i_sb->s_blocksize); @@ -2234,11 +2258,18 @@ static int ext4_da_get_block_prep(struct inode *inode, sector_t iblock, /* not enough space to reserve */ return ret; - map_bh(bh_result, inode->i_sb, 0); + map_bh(bh_result, inode->i_sb, invalid_block); set_buffer_new(bh_result); set_buffer_delay(bh_result); } else if (ret > 0) { bh_result->b_size = (ret << inode->i_blkbits); + /* + * With sub-block writes into unwritten extents + * we also need to mark the buffer as new so that + * the unwritten parts of the buffer gets correctly zeroed. + */ + if (buffer_unwritten(bh_result)) + set_buffer_new(bh_result); ret = 0; } @@ -2816,6 +2847,48 @@ out: return; } +/* + * Force all delayed allocation blocks to be allocated for a given inode. + */ +int ext4_alloc_da_blocks(struct inode *inode) +{ + if (!EXT4_I(inode)->i_reserved_data_blocks && + !EXT4_I(inode)->i_reserved_meta_blocks) + return 0; + + /* + * We do something simple for now. The filemap_flush() will + * also start triggering a write of the data blocks, which is + * not strictly speaking necessary (and for users of + * laptop_mode, not even desirable). However, to do otherwise + * would require replicating code paths in: + * + * ext4_da_writepages() -> + * write_cache_pages() ---> (via passed in callback function) + * __mpage_da_writepage() --> + * mpage_add_bh_to_extent() + * mpage_da_map_blocks() + * + * The problem is that write_cache_pages(), located in + * mm/page-writeback.c, marks pages clean in preparation for + * doing I/O, which is not desirable if we're not planning on + * doing I/O at all. + * + * We could call write_cache_pages(), and then redirty all of + * the pages by calling redirty_page_for_writeback() but that + * would be ugly in the extreme. So instead we would need to + * replicate parts of the code in the above functions, + * simplifying them becuase we wouldn't actually intend to + * write out the pages, but rather only collect contiguous + * logical block extents, call the multi-block allocator, and + * then update the buffer heads with the block allocations. + * + * For now, though, we'll cheat by calling filemap_flush(), + * which will map the blocks, and start the I/O, but not + * actually wait for the I/O to complete. + */ + return filemap_flush(inode->i_mapping); +} /* * bmap() is special. It gets used by applications such as lilo and by @@ -3838,6 +3911,9 @@ void ext4_truncate(struct inode *inode) if (!ext4_can_truncate(inode)) return; + if (inode->i_size == 0 && !test_opt(inode->i_sb, NO_AUTO_DA_ALLOC)) + ei->i_state |= EXT4_STATE_DA_ALLOC_CLOSE; + if (EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL) { ext4_ext_truncate(inode); return; @@ -4248,11 +4324,9 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino) ei->i_flags = le32_to_cpu(raw_inode->i_flags); inode->i_blocks = ext4_inode_blocks(raw_inode, ei); ei->i_file_acl = le32_to_cpu(raw_inode->i_file_acl_lo); - if (EXT4_SB(inode->i_sb)->s_es->s_creator_os != - cpu_to_le32(EXT4_OS_HURD)) { + if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_64BIT)) ei->i_file_acl |= ((__u64)le16_to_cpu(raw_inode->i_file_acl_high)) << 32; - } inode->i_size = ext4_isize(raw_inode); ei->i_disksize = inode->i_size; inode->i_generation = le32_to_cpu(raw_inode->i_generation); @@ -4299,6 +4373,18 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino) (__u64)(le32_to_cpu(raw_inode->i_version_hi)) << 32; } + if (ei->i_file_acl && + ((ei->i_file_acl < + (le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block) + + EXT4_SB(sb)->s_gdb_count)) || + (ei->i_file_acl >= ext4_blocks_count(EXT4_SB(sb)->s_es)))) { + ext4_error(sb, __func__, + "bad extended attribute block %llu in inode #%lu", + ei->i_file_acl, inode->i_ino); + ret = -EIO; + goto bad_inode; + } + if (S_ISREG(inode->i_mode)) { inode->i_op = &ext4_file_inode_operations; inode->i_fop = &ext4_file_operations; @@ -4315,7 +4401,8 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino) inode->i_op = &ext4_symlink_inode_operations; ext4_set_aops(inode); } - } else { + } else if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode) || + S_ISFIFO(inode->i_mode) || S_ISSOCK(inode->i_mode)) { inode->i_op = &ext4_special_inode_operations; if (raw_inode->i_block[0]) init_special_inode(inode, inode->i_mode, @@ -4323,6 +4410,13 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino) else init_special_inode(inode, inode->i_mode, new_decode_dev(le32_to_cpu(raw_inode->i_block[1]))); + } else { + brelse(bh); + ret = -EIO; + ext4_error(inode->i_sb, __func__, + "bogus i_mode (%o) for inode=%lu", + inode->i_mode, inode->i_ino); + goto bad_inode; } brelse(iloc.bh); ext4_set_inode_flags(inode); diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index 42dc83f..91e75f7 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -48,8 +48,7 @@ long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) if (err) return err; - if (!S_ISDIR(inode->i_mode)) - flags &= ~EXT4_DIRSYNC_FL; + flags = ext4_mask_flags(inode->i_mode, flags); err = -EPERM; mutex_lock(&inode->i_mutex); @@ -263,6 +262,20 @@ setversion_out: return err; } + case EXT4_IOC_ALLOC_DA_BLKS: + { + int err; + if (!is_owner_or_cap(inode)) + return -EACCES; + + err = mnt_want_write(filp->f_path.mnt); + if (err) + return err; + err = ext4_alloc_da_blocks(inode); + mnt_drop_write(filp->f_path.mnt); + return err; + } + default: return -ENOTTY; } diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index ba702bd..8977e60 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -1052,8 +1052,16 @@ static struct dentry *ext4_lookup(struct inode *dir, struct dentry *dentry, stru return ERR_PTR(-EIO); } inode = ext4_iget(dir->i_sb, ino); - if (IS_ERR(inode)) - return ERR_CAST(inode); + if (unlikely(IS_ERR(inode))) { + if (PTR_ERR(inode) == -ESTALE) { + ext4_error(dir->i_sb, __func__, + "deleted inode referenced: %u", + ino); + return ERR_PTR(-EIO); + } else { + return ERR_CAST(inode); + } + } } return d_splice_alias(inode, dentry); } @@ -2311,7 +2319,7 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry, struct inode *old_inode, *new_inode; struct buffer_head *old_bh, *new_bh, *dir_bh; struct ext4_dir_entry_2 *old_de, *new_de; - int retval; + int retval, force_da_alloc = 0; old_bh = new_bh = dir_bh = NULL; @@ -2449,6 +2457,8 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry, ext4_mark_inode_dirty(handle, new_inode); if (!new_inode->i_nlink) ext4_orphan_add(handle, new_inode); + if (!test_opt(new_dir->i_sb, NO_AUTO_DA_ALLOC)) + force_da_alloc = 1; } retval = 0; @@ -2457,6 +2467,8 @@ end_rename: brelse(old_bh); brelse(new_bh); ext4_journal_stop(handle); + if (retval == 0 && force_da_alloc) + ext4_alloc_da_blocks(old_inode); return retval; } diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 39d1993..1ad3c20 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -803,8 +803,6 @@ static int ext4_show_options(struct seq_file *seq, struct vfsmount *vfs) if (!test_opt(sb, POSIX_ACL) && (def_mount_opts & EXT4_DEFM_ACL)) seq_puts(seq, ",noacl"); #endif - if (!test_opt(sb, RESERVATION)) - seq_puts(seq, ",noreservation"); if (sbi->s_commit_interval != JBD2_DEFAULT_MAX_COMMIT_AGE*HZ) { seq_printf(seq, ",commit=%u", (unsigned) (sbi->s_commit_interval / HZ)); @@ -855,6 +853,9 @@ static int ext4_show_options(struct seq_file *seq, struct vfsmount *vfs) if (test_opt(sb, DATA_ERR_ABORT)) seq_puts(seq, ",data_err=abort"); + if (test_opt(sb, NO_AUTO_DA_ALLOC)) + seq_puts(seq, ",auto_da_alloc=0"); + ext4_show_quota_options(seq, sb); return 0; } @@ -1002,7 +1003,7 @@ enum { Opt_resgid, Opt_resuid, Opt_sb, Opt_err_cont, Opt_err_panic, Opt_err_ro, Opt_nouid32, Opt_debug, Opt_oldalloc, Opt_orlov, Opt_user_xattr, Opt_nouser_xattr, Opt_acl, Opt_noacl, - Opt_reservation, Opt_noreservation, Opt_noload, Opt_nobh, Opt_bh, + Opt_auto_da_alloc, Opt_noload, Opt_nobh, Opt_bh, Opt_commit, Opt_min_batch_time, Opt_max_batch_time, Opt_journal_update, Opt_journal_dev, Opt_journal_checksum, Opt_journal_async_commit, @@ -1037,8 +1038,6 @@ static const match_table_t tokens = { {Opt_nouser_xattr, "nouser_xattr"}, {Opt_acl, "acl"}, {Opt_noacl, "noacl"}, - {Opt_reservation, "reservation"}, - {Opt_noreservation, "noreservation"}, {Opt_noload, "noload"}, {Opt_nobh, "nobh"}, {Opt_bh, "bh"}, @@ -1073,6 +1072,7 @@ static const match_table_t tokens = { {Opt_nodelalloc, "nodelalloc"}, {Opt_inode_readahead_blks, "inode_readahead_blks=%u"}, {Opt_journal_ioprio, "journal_ioprio=%u"}, + {Opt_auto_da_alloc, "auto_da_alloc=%u"}, {Opt_err, NULL}, }; @@ -1205,12 +1205,6 @@ static int parse_options(char *options, struct super_block *sb, "not supported\n"); break; #endif - case Opt_reservation: - set_opt(sbi->s_mount_opt, RESERVATION); - break; - case Opt_noreservation: - clear_opt(sbi->s_mount_opt, RESERVATION); - break; case Opt_journal_update: /* @@@ FIXME */ /* Eventually we will want to be able to create @@ -1471,6 +1465,14 @@ set_qf_format: *journal_ioprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, option); break; + case Opt_auto_da_alloc: + if (match_int(&args[0], &option)) + return 0; + if (option) + clear_opt(sbi->s_mount_opt, NO_AUTO_DA_ALLOC); + else + set_opt(sbi->s_mount_opt,NO_AUTO_DA_ALLOC); + break; default: printk(KERN_ERR "EXT4-fs: Unrecognized mount option \"%s\" " @@ -2099,7 +2101,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) sbi->s_min_batch_time = EXT4_DEF_MIN_BATCH_TIME; sbi->s_max_batch_time = EXT4_DEF_MAX_BATCH_TIME; - set_opt(sbi->s_mount_opt, RESERVATION); set_opt(sbi->s_mount_opt, BARRIER); /* diff --git a/fs/jbd2/revoke.c b/fs/jbd2/revoke.c index 257ff26..bbe6d59 100644 --- a/fs/jbd2/revoke.c +++ b/fs/jbd2/revoke.c @@ -55,6 +55,25 @@ * need do nothing. * RevokeValid set, Revoked set: * buffer has been revoked. + * + * Locking rules: + * We keep two hash tables of revoke records. One hashtable belongs to the + * running transaction (is pointed to by journal->j_revoke), the other one + * belongs to the committing transaction. Accesses to the second hash table + * happen only from the kjournald and no other thread touches this table. Also + * journal_switch_revoke_table() which switches which hashtable belongs to the + * running and which to the committing transaction is called only from + * kjournald. Therefore we need no locks when accessing the hashtable belonging + * to the committing transaction. + * + * All users operating on the hash table belonging to the running transaction + * have a handle to the transaction. Therefore they are safe from kjournald + * switching hash tables under them. For operations on the lists of entries in + * the hash table j_revoke_lock is used. + * + * Finally, also replay code uses the hash tables but at this moment noone else + * can touch them (filesystem isn't mounted yet) and hence no locking is + * needed. */ #ifndef __KERNEL__ @@ -401,8 +420,6 @@ int jbd2_journal_revoke(handle_t *handle, unsigned long long blocknr, * the second time we would still have a pending revoke to cancel. So, * do not trust the Revoked bit on buffers unless RevokeValid is also * set. - * - * The caller must have the journal locked. */ int jbd2_journal_cancel_revoke(handle_t *handle, struct journal_head *jh) { @@ -480,10 +497,7 @@ void jbd2_journal_switch_revoke_table(journal_t *journal) /* * Write revoke records to the journal for all entries in the current * revoke hash, deleting the entries as we go. - * - * Called with the journal lock held. */ - void jbd2_journal_write_revoke_records(journal_t *journal, transaction_t *transaction) { diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index 3b2f697..5dd75c0 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -1943,7 +1943,8 @@ int nfs_permission(struct inode *inode, int mask) case S_IFREG: /* NFSv4 has atomic_open... */ if (nfs_server_capable(inode, NFS_CAP_ATOMIC_OPEN) - && (mask & MAY_OPEN)) + && (mask & MAY_OPEN) + && !(mask & MAY_EXEC)) goto out; break; case S_IFDIR: diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index 98b93ca..1a2b0cb 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -94,6 +94,7 @@ extern void ptrace_notify(int exit_code); extern void __ptrace_link(struct task_struct *child, struct task_struct *new_parent); extern void __ptrace_unlink(struct task_struct *child); +extern int __ptrace_detach(struct task_struct *tracer, struct task_struct *p); extern void ptrace_fork(struct task_struct *task, unsigned long clone_flags); #define PTRACE_MODE_READ 1 #define PTRACE_MODE_ATTACH 2 diff --git a/kernel/exit.c b/kernel/exit.c index 467ffcd..a33f399 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -703,22 +703,50 @@ static void exit_mm(struct task_struct * tsk) } /* - * Return nonzero if @parent's children should reap themselves. - * - * Called with write_lock_irq(&tasklist_lock) held. + * Called with irqs disabled, returns true if childs should reap themselves. */ -static int ignoring_children(struct task_struct *parent) +static int ignoring_children(struct sighand_struct *sigh) { int ret; - struct sighand_struct *psig = parent->sighand; - unsigned long flags; - spin_lock_irqsave(&psig->siglock, flags); - ret = (psig->action[SIGCHLD-1].sa.sa_handler == SIG_IGN || - (psig->action[SIGCHLD-1].sa.sa_flags & SA_NOCLDWAIT)); - spin_unlock_irqrestore(&psig->siglock, flags); + spin_lock(&sigh->siglock); + ret = (sigh->action[SIGCHLD-1].sa.sa_handler == SIG_IGN) || + (sigh->action[SIGCHLD-1].sa.sa_flags & SA_NOCLDWAIT); + spin_unlock(&sigh->siglock); return ret; } +/* Returns nonzero if the tracee should be released. */ +int __ptrace_detach(struct task_struct *tracer, struct task_struct *p) +{ + __ptrace_unlink(p); + + if (p->exit_state != EXIT_ZOMBIE) + return 0; + /* + * If it's a zombie, our attachedness prevented normal + * parent notification or self-reaping. Do notification + * now if it would have happened earlier. If it should + * reap itself we return true. + * + * If it's our own child, there is no notification to do. + * But if our normal children self-reap, then this child + * was prevented by ptrace and we must reap it now. + */ + if (!task_detached(p) && thread_group_empty(p)) { + if (!same_thread_group(p->real_parent, tracer)) + do_notify_parent(p, p->exit_signal); + else if (ignoring_children(tracer->sighand)) + p->exit_signal = -1; + } + + if (!task_detached(p)) + return 0; + + /* Mark it as in the process of being reaped. */ + p->exit_state = EXIT_DEAD; + return 1; +} + /* * Detach all tasks we were using ptrace on. * Any that need to be release_task'd are put on the @dead list. @@ -728,43 +756,10 @@ static int ignoring_children(struct task_struct *parent) static void ptrace_exit(struct task_struct *parent, struct list_head *dead) { struct task_struct *p, *n; - int ign = -1; list_for_each_entry_safe(p, n, &parent->ptraced, ptrace_entry) { - __ptrace_unlink(p); - - if (p->exit_state != EXIT_ZOMBIE) - continue; - - /* - * If it's a zombie, our attachedness prevented normal - * parent notification or self-reaping. Do notification - * now if it would have happened earlier. If it should - * reap itself, add it to the @dead list. We can't call - * release_task() here because we already hold tasklist_lock. - * - * If it's our own child, there is no notification to do. - * But if our normal children self-reap, then this child - * was prevented by ptrace and we must reap it now. - */ - if (!task_detached(p) && thread_group_empty(p)) { - if (!same_thread_group(p->real_parent, parent)) - do_notify_parent(p, p->exit_signal); - else { - if (ign < 0) - ign = ignoring_children(parent); - if (ign) - p->exit_signal = -1; - } - } - - if (task_detached(p)) { - /* - * Mark it as in the process of being reaped. - */ - p->exit_state = EXIT_DEAD; + if (__ptrace_detach(parent, p)) list_add(&p->ptrace_entry, dead); - } } } diff --git a/kernel/futex.c b/kernel/futex.c index 438701a..2844297 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -192,6 +192,7 @@ static void drop_futex_key_refs(union futex_key *key) * @shared: NULL for a PROCESS_PRIVATE futex, * ¤t->mm->mmap_sem for a PROCESS_SHARED futex * @key: address where result is stored. + * @rw: mapping needs to be read/write (values: VERIFY_READ, VERIFY_WRITE) * * Returns a negative error code or 0 * The key words are stored in *key on success. @@ -204,7 +205,8 @@ static void drop_futex_key_refs(union futex_key *key) * For other futexes, it points to ¤t->mm->mmap_sem and * caller must have taken the reader lock. but NOT any spinlocks. */ -static int get_futex_key(u32 __user *uaddr, int fshared, union futex_key *key) +static int +get_futex_key(u32 __user *uaddr, int fshared, union futex_key *key, int rw) { unsigned long address = (unsigned long)uaddr; struct mm_struct *mm = current->mm; @@ -227,7 +229,7 @@ static int get_futex_key(u32 __user *uaddr, int fshared, union futex_key *key) * but access_ok() should be faster than find_vma() */ if (!fshared) { - if (unlikely(!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))) + if (unlikely(!access_ok(rw, uaddr, sizeof(u32)))) return -EFAULT; key->private.mm = mm; key->private.address = address; @@ -236,7 +238,7 @@ static int get_futex_key(u32 __user *uaddr, int fshared, union futex_key *key) } again: - err = get_user_pages_fast(address, 1, 0, &page); + err = get_user_pages_fast(address, 1, rw == VERIFY_WRITE, &page); if (err < 0) return err; @@ -707,7 +709,7 @@ static int futex_wake(u32 __user *uaddr, int fshared, int nr_wake, u32 bitset) if (!bitset) return -EINVAL; - ret = get_futex_key(uaddr, fshared, &key); + ret = get_futex_key(uaddr, fshared, &key, VERIFY_READ); if (unlikely(ret != 0)) goto out; @@ -753,10 +755,10 @@ futex_wake_op(u32 __user *uaddr1, int fshared, u32 __user *uaddr2, int ret, op_ret, attempt = 0; retryfull: - ret = get_futex_key(uaddr1, fshared, &key1); + ret = get_futex_key(uaddr1, fshared, &key1, VERIFY_READ); if (unlikely(ret != 0)) goto out; - ret = get_futex_key(uaddr2, fshared, &key2); + ret = get_futex_key(uaddr2, fshared, &key2, VERIFY_WRITE); if (unlikely(ret != 0)) goto out_put_key1; @@ -859,10 +861,10 @@ static int futex_requeue(u32 __user *uaddr1, int fshared, u32 __user *uaddr2, int ret, drop_count = 0; retry: - ret = get_futex_key(uaddr1, fshared, &key1); + ret = get_futex_key(uaddr1, fshared, &key1, VERIFY_READ); if (unlikely(ret != 0)) goto out; - ret = get_futex_key(uaddr2, fshared, &key2); + ret = get_futex_key(uaddr2, fshared, &key2, VERIFY_WRITE); if (unlikely(ret != 0)) goto out_put_key1; @@ -1181,7 +1183,7 @@ static int futex_wait(u32 __user *uaddr, int fshared, q.bitset = bitset; retry: q.key = FUTEX_KEY_INIT; - ret = get_futex_key(uaddr, fshared, &q.key); + ret = get_futex_key(uaddr, fshared, &q.key, VERIFY_READ); if (unlikely(ret != 0)) goto out; @@ -1370,7 +1372,7 @@ static int futex_lock_pi(u32 __user *uaddr, int fshared, q.pi_state = NULL; retry: q.key = FUTEX_KEY_INIT; - ret = get_futex_key(uaddr, fshared, &q.key); + ret = get_futex_key(uaddr, fshared, &q.key, VERIFY_WRITE); if (unlikely(ret != 0)) goto out; @@ -1630,7 +1632,7 @@ retry: if ((uval & FUTEX_TID_MASK) != task_pid_vnr(current)) return -EPERM; - ret = get_futex_key(uaddr, fshared, &key); + ret = get_futex_key(uaddr, fshared, &key, VERIFY_WRITE); if (unlikely(ret != 0)) goto out; diff --git a/kernel/ptrace.c b/kernel/ptrace.c index dc3b98e..893c2c7 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -235,18 +235,10 @@ out: return retval; } -static inline void __ptrace_detach(struct task_struct *child, unsigned int data) -{ - child->exit_code = data; - /* .. re-parent .. */ - __ptrace_unlink(child); - /* .. and wake it up. */ - if (child->exit_state != EXIT_ZOMBIE) - wake_up_process(child); -} - int ptrace_detach(struct task_struct *child, unsigned int data) { + int dead = 0; + if (!valid_signal(data)) return -EIO; @@ -256,10 +248,19 @@ int ptrace_detach(struct task_struct *child, unsigned int data) write_lock_irq(&tasklist_lock); /* protect against de_thread()->release_task() */ - if (child->ptrace) - __ptrace_detach(child, data); + if (child->ptrace) { + child->exit_code = data; + + dead = __ptrace_detach(current, child); + + if (!child->exit_state) + wake_up_process(child); + } write_unlock_irq(&tasklist_lock); + if (unlikely(dead)) + release_task(child); + return 0; } diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 107da3d..2a9129b 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -316,7 +316,7 @@ static void resv_map_release(struct kref *ref) static struct resv_map *vma_resv_map(struct vm_area_struct *vma) { VM_BUG_ON(!is_vm_hugetlb_page(vma)); - if (!(vma->vm_flags & VM_SHARED)) + if (!(vma->vm_flags & VM_MAYSHARE)) return (struct resv_map *)(get_vma_private_data(vma) & ~HPAGE_RESV_MASK); return NULL; @@ -325,7 +325,7 @@ static struct resv_map *vma_resv_map(struct vm_area_struct *vma) static void set_vma_resv_map(struct vm_area_struct *vma, struct resv_map *map) { VM_BUG_ON(!is_vm_hugetlb_page(vma)); - VM_BUG_ON(vma->vm_flags & VM_SHARED); + VM_BUG_ON(vma->vm_flags & VM_MAYSHARE); set_vma_private_data(vma, (get_vma_private_data(vma) & HPAGE_RESV_MASK) | (unsigned long)map); @@ -334,7 +334,7 @@ static void set_vma_resv_map(struct vm_area_struct *vma, struct resv_map *map) static void set_vma_resv_flags(struct vm_area_struct *vma, unsigned long flags) { VM_BUG_ON(!is_vm_hugetlb_page(vma)); - VM_BUG_ON(vma->vm_flags & VM_SHARED); + VM_BUG_ON(vma->vm_flags & VM_MAYSHARE); set_vma_private_data(vma, get_vma_private_data(vma) | flags); } @@ -353,7 +353,7 @@ static void decrement_hugepage_resv_vma(struct hstate *h, if (vma->vm_flags & VM_NORESERVE) return; - if (vma->vm_flags & VM_SHARED) { + if (vma->vm_flags & VM_MAYSHARE) { /* Shared mappings always use reserves */ h->resv_huge_pages--; } else if (is_vma_resv_set(vma, HPAGE_RESV_OWNER)) { @@ -369,14 +369,14 @@ static void decrement_hugepage_resv_vma(struct hstate *h, void reset_vma_resv_huge_pages(struct vm_area_struct *vma) { VM_BUG_ON(!is_vm_hugetlb_page(vma)); - if (!(vma->vm_flags & VM_SHARED)) + if (!(vma->vm_flags & VM_MAYSHARE)) vma->vm_private_data = (void *)0; } /* Returns true if the VMA has associated reserve pages */ static int vma_has_reserves(struct vm_area_struct *vma) { - if (vma->vm_flags & VM_SHARED) + if (vma->vm_flags & VM_MAYSHARE) return 1; if (is_vma_resv_set(vma, HPAGE_RESV_OWNER)) return 1; @@ -924,7 +924,7 @@ static int vma_needs_reservation(struct hstate *h, struct address_space *mapping = vma->vm_file->f_mapping; struct inode *inode = mapping->host; - if (vma->vm_flags & VM_SHARED) { + if (vma->vm_flags & VM_MAYSHARE) { pgoff_t idx = vma_hugecache_offset(h, vma, addr); return region_chg(&inode->i_mapping->private_list, idx, idx + 1); @@ -949,7 +949,7 @@ static void vma_commit_reservation(struct hstate *h, struct address_space *mapping = vma->vm_file->f_mapping; struct inode *inode = mapping->host; - if (vma->vm_flags & VM_SHARED) { + if (vma->vm_flags & VM_MAYSHARE) { pgoff_t idx = vma_hugecache_offset(h, vma, addr); region_add(&inode->i_mapping->private_list, idx, idx + 1); @@ -1893,7 +1893,7 @@ retry_avoidcopy: * at the time of fork() could consume its reserves on COW instead * of the full address range. */ - if (!(vma->vm_flags & VM_SHARED) && + if (!(vma->vm_flags & VM_MAYSHARE) && is_vma_resv_set(vma, HPAGE_RESV_OWNER) && old_page != pagecache_page) outside_reserve = 1; @@ -2000,7 +2000,7 @@ retry: clear_huge_page(page, address, huge_page_size(h)); __SetPageUptodate(page); - if (vma->vm_flags & VM_SHARED) { + if (vma->vm_flags & VM_MAYSHARE) { int err; struct inode *inode = mapping->host; @@ -2104,7 +2104,7 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, goto out_mutex; } - if (!(vma->vm_flags & VM_SHARED)) + if (!(vma->vm_flags & VM_MAYSHARE)) pagecache_page = hugetlbfs_pagecache_page(h, vma, address); } @@ -2289,7 +2289,7 @@ int hugetlb_reserve_pages(struct inode *inode, * to reserve the full area even if read-only as mprotect() may be * called to make the mapping read-write. Assume !vma is a shm mapping */ - if (!vma || vma->vm_flags & VM_SHARED) + if (!vma || vma->vm_flags & VM_MAYSHARE) chg = region_chg(&inode->i_mapping->private_list, from, to); else { struct resv_map *resv_map = resv_map_alloc(); @@ -2330,7 +2330,7 @@ int hugetlb_reserve_pages(struct inode *inode, * consumed reservations are stored in the map. Hence, nothing * else has to be done for private mappings here */ - if (!vma || vma->vm_flags & VM_SHARED) + if (!vma || vma->vm_flags & VM_MAYSHARE) region_add(&inode->i_mapping->private_list, from, to); return 0; } diff --git a/mm/slub.c b/mm/slub.c index 0280eee..5663da0 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -9,6 +9,7 @@ */ #include +#include /* struct reclaim_state */ #include #include #include @@ -1175,6 +1176,8 @@ static void __free_slab(struct kmem_cache *s, struct page *page) __ClearPageSlab(page); reset_page_mapcount(page); + if (current->reclaim_state) + current->reclaim_state->reclaimed_slab += pages; __free_pages(page, order); } diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index 1b34135..6b09213 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -668,7 +668,8 @@ static int vlan_ethtool_get_settings(struct net_device *dev, const struct vlan_dev_info *vlan = vlan_dev_info(dev); struct net_device *real_dev = vlan->real_dev; - if (!real_dev->ethtool_ops->get_settings) + if (!real_dev->ethtool_ops || + !real_dev->ethtool_ops->get_settings) return -EOPNOTSUPP; return real_dev->ethtool_ops->get_settings(real_dev, cmd); diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 6549848..c4070ec 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -2447,7 +2447,7 @@ static inline void free_SAs(struct pktgen_dev *pkt_dev) if (pkt_dev->cflows) { /* let go of the SAs if we have them */ int i = 0; - for (; i < pkt_dev->nflows; i++){ + for (; i < pkt_dev->cflows; i++) { struct xfrm_state *x = pkt_dev->flows[i].x; if (x) { xfrm_state_put(x); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index eae6954..f4bbc98 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -2206,7 +2206,7 @@ unsigned int skb_seq_read(unsigned int consumed, const u8 **data, next_skb: block_limit = skb_headlen(st->cur_skb) + st->stepped_offset; - if (abs_offset < block_limit) { + if (abs_offset < block_limit && !st->frag_data) { *data = st->cur_skb->data + (abs_offset - st->stepped_offset); return block_limit - abs_offset; } diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 97f7115..4e302d1 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -784,8 +784,8 @@ static void rt_check_expire(void) { static unsigned int rover; unsigned int i = rover, goal; - struct rtable *rth, **rthp; - unsigned long length = 0, samples = 0; + struct rtable *rth, *aux, **rthp; + unsigned long samples = 0; unsigned long sum = 0, sum2 = 0; u64 mult; @@ -795,9 +795,9 @@ static void rt_check_expire(void) goal = (unsigned int)mult; if (goal > rt_hash_mask) goal = rt_hash_mask + 1; - length = 0; for (; goal > 0; goal--) { unsigned long tmo = ip_rt_gc_timeout; + unsigned long length; i = (i + 1) & rt_hash_mask; rthp = &rt_hash_table[i].chain; @@ -809,8 +809,10 @@ static void rt_check_expire(void) if (*rthp == NULL) continue; + length = 0; spin_lock_bh(rt_hash_lock_addr(i)); while ((rth = *rthp) != NULL) { + prefetch(rth->u.dst.rt_next); if (rt_is_expired(rth)) { *rthp = rth->u.dst.rt_next; rt_free(rth); @@ -819,33 +821,30 @@ static void rt_check_expire(void) if (rth->u.dst.expires) { /* Entry is expired even if it is in use */ if (time_before_eq(jiffies, rth->u.dst.expires)) { +nofree: tmo >>= 1; rthp = &rth->u.dst.rt_next; /* - * Only bump our length if the hash - * inputs on entries n and n+1 are not - * the same, we only count entries on + * We only count entries on * a chain with equal hash inputs once * so that entries for different QOS * levels, and other non-hash input * attributes don't unfairly skew * the length computation */ - if ((*rthp == NULL) || - !compare_hash_inputs(&(*rthp)->fl, - &rth->fl)) - length += ONE; + for (aux = rt_hash_table[i].chain;;) { + if (aux == rth) { + length += ONE; + break; + } + if (compare_hash_inputs(&aux->fl, &rth->fl)) + break; + aux = aux->u.dst.rt_next; + } continue; } - } else if (!rt_may_expire(rth, tmo, ip_rt_gc_timeout)) { - tmo >>= 1; - rthp = &rth->u.dst.rt_next; - if ((*rthp == NULL) || - !compare_hash_inputs(&(*rthp)->fl, - &rth->fl)) - length += ONE; - continue; - } + } else if (!rt_may_expire(rth, tmo, ip_rt_gc_timeout)) + goto nofree; /* Cleanup aged off entries. */ *rthp = rth->u.dst.rt_next; @@ -1068,7 +1067,6 @@ out: return 0; static int rt_intern_hash(unsigned hash, struct rtable *rt, struct rtable **rp) { struct rtable *rth, **rthp; - struct rtable *rthi; unsigned long now; struct rtable *cand, **candp; u32 min_score; @@ -1088,7 +1086,6 @@ restart: } rthp = &rt_hash_table[hash].chain; - rthi = NULL; spin_lock_bh(rt_hash_lock_addr(hash)); while ((rth = *rthp) != NULL) { @@ -1134,17 +1131,6 @@ restart: chain_length++; rthp = &rth->u.dst.rt_next; - - /* - * check to see if the next entry in the chain - * contains the same hash input values as rt. If it does - * This is where we will insert into the list, instead of - * at the head. This groups entries that differ by aspects not - * relvant to the hash function together, which we use to adjust - * our chain length - */ - if (*rthp && compare_hash_inputs(&(*rthp)->fl, &rt->fl)) - rthi = rth; } if (cand) { @@ -1205,10 +1191,7 @@ restart: } } - if (rthi) - rt->u.dst.rt_next = rthi->u.dst.rt_next; - else - rt->u.dst.rt_next = rt_hash_table[hash].chain; + rt->u.dst.rt_next = rt_hash_table[hash].chain; #if RT_CACHE_DEBUG >= 2 if (rt->u.dst.rt_next) { @@ -1224,10 +1207,7 @@ restart: * previous writes to rt are comitted to memory * before making rt visible to other CPUS. */ - if (rthi) - rcu_assign_pointer(rthi->u.dst.rt_next, rt); - else - rcu_assign_pointer(rt_hash_table[hash].chain, rt); + rcu_assign_pointer(rt_hash_table[hash].chain, rt); spin_unlock_bh(rt_hash_lock_addr(hash)); *rp = rt; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 76b148b..b16dc84 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1286,6 +1286,7 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, struct task_struct *user_recv = NULL; int copied_early = 0; struct sk_buff *skb; + u32 urg_hole = 0; lock_sock(sk); @@ -1497,7 +1498,8 @@ do_prequeue: } } } - if ((flags & MSG_PEEK) && peek_seq != tp->copied_seq) { + if ((flags & MSG_PEEK) && + (peek_seq - copied - urg_hole != tp->copied_seq)) { if (net_ratelimit()) printk(KERN_DEBUG "TCP(%s:%d): Application bug, race in MSG_PEEK.\n", current->comm, task_pid_nr(current)); @@ -1518,6 +1520,7 @@ do_prequeue: if (!urg_offset) { if (!sock_flag(sk, SOCK_URGINLINE)) { ++*seq; + urg_hole++; offset++; used--; if (!used) diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index c28976a..fd4317e 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -927,6 +927,8 @@ static void tcp_init_metrics(struct sock *sk) tcp_set_rto(sk); if (inet_csk(sk)->icsk_rto < TCP_TIMEOUT_INIT && !tp->rx_opt.saw_tstamp) goto reset; + +cwnd: tp->snd_cwnd = tcp_init_cwnd(tp, dst); tp->snd_cwnd_stamp = tcp_time_stamp; return; @@ -941,6 +943,7 @@ reset: tp->mdev = tp->mdev_max = tp->rttvar = TCP_TIMEOUT_INIT; inet_csk(sk)->icsk_rto = TCP_TIMEOUT_INIT; } + goto cwnd; } static void tcp_update_reordering(struct sock *sk, const int metric, diff --git a/net/mac80211/rc80211_minstrel.c b/net/mac80211/rc80211_minstrel.c index 3824990..d9233ec 100644 --- a/net/mac80211/rc80211_minstrel.c +++ b/net/mac80211/rc80211_minstrel.c @@ -476,8 +476,8 @@ minstrel_alloc_sta(void *priv, struct ieee80211_sta *sta, gfp_t gfp) return NULL; for (i = 0; i < IEEE80211_NUM_BANDS; i++) { - sband = hw->wiphy->bands[hw->conf.channel->band]; - if (sband->n_bitrates > max_rates) + sband = hw->wiphy->bands[i]; + if (sband && sband->n_bitrates > max_rates) max_rates = sband->n_bitrates; } diff --git a/net/mac80211/rc80211_pid_algo.c b/net/mac80211/rc80211_pid_algo.c index b16801c..8bef9a1 100644 --- a/net/mac80211/rc80211_pid_algo.c +++ b/net/mac80211/rc80211_pid_algo.c @@ -317,13 +317,44 @@ rate_control_pid_rate_init(void *priv, struct ieee80211_supported_band *sband, struct ieee80211_sta *sta, void *priv_sta) { struct rc_pid_sta_info *spinfo = priv_sta; + struct rc_pid_info *pinfo = priv; + struct rc_pid_rateinfo *rinfo = pinfo->rinfo; struct sta_info *si; + int i, j, tmp; + bool s; /* TODO: This routine should consider using RSSI from previous packets * as we need to have IEEE 802.1X auth succeed immediately after assoc.. * Until that method is implemented, we will use the lowest supported * rate as a workaround. */ + /* Sort the rates. This is optimized for the most common case (i.e. + * almost-sorted CCK+OFDM rates). Kind of bubble-sort with reversed + * mapping too. */ + for (i = 0; i < sband->n_bitrates; i++) { + rinfo[i].index = i; + rinfo[i].rev_index = i; + if (RC_PID_FAST_START) + rinfo[i].diff = 0; + else + rinfo[i].diff = i * pinfo->norm_offset; + } + for (i = 1; i < sband->n_bitrates; i++) { + s = 0; + for (j = 0; j < sband->n_bitrates - i; j++) + if (unlikely(sband->bitrates[rinfo[j].index].bitrate > + sband->bitrates[rinfo[j + 1].index].bitrate)) { + tmp = rinfo[j].index; + rinfo[j].index = rinfo[j + 1].index; + rinfo[j + 1].index = tmp; + rinfo[rinfo[j].index].rev_index = j; + rinfo[rinfo[j + 1].index].rev_index = j + 1; + s = 1; + } + if (!s) + break; + } + spinfo->txrate_idx = rate_lowest_index(sband, sta); /* HACK */ si = container_of(sta, struct sta_info, sta); @@ -336,21 +367,22 @@ static void *rate_control_pid_alloc(struct ieee80211_hw *hw, struct rc_pid_info *pinfo; struct rc_pid_rateinfo *rinfo; struct ieee80211_supported_band *sband; - int i, j, tmp; - bool s; + int i, max_rates = 0; #ifdef CONFIG_MAC80211_DEBUGFS struct rc_pid_debugfs_entries *de; #endif - sband = hw->wiphy->bands[hw->conf.channel->band]; - pinfo = kmalloc(sizeof(*pinfo), GFP_ATOMIC); if (!pinfo) return NULL; - /* We can safely assume that sband won't change unless we get - * reinitialized. */ - rinfo = kmalloc(sizeof(*rinfo) * sband->n_bitrates, GFP_ATOMIC); + for (i = 0; i < IEEE80211_NUM_BANDS; i++) { + sband = hw->wiphy->bands[i]; + if (sband && sband->n_bitrates > max_rates) + max_rates = sband->n_bitrates; + } + + rinfo = kmalloc(sizeof(*rinfo) * max_rates, GFP_ATOMIC); if (!rinfo) { kfree(pinfo); return NULL; @@ -368,33 +400,6 @@ static void *rate_control_pid_alloc(struct ieee80211_hw *hw, pinfo->rinfo = rinfo; pinfo->oldrate = 0; - /* Sort the rates. This is optimized for the most common case (i.e. - * almost-sorted CCK+OFDM rates). Kind of bubble-sort with reversed - * mapping too. */ - for (i = 0; i < sband->n_bitrates; i++) { - rinfo[i].index = i; - rinfo[i].rev_index = i; - if (RC_PID_FAST_START) - rinfo[i].diff = 0; - else - rinfo[i].diff = i * pinfo->norm_offset; - } - for (i = 1; i < sband->n_bitrates; i++) { - s = 0; - for (j = 0; j < sband->n_bitrates - i; j++) - if (unlikely(sband->bitrates[rinfo[j].index].bitrate > - sband->bitrates[rinfo[j + 1].index].bitrate)) { - tmp = rinfo[j].index; - rinfo[j].index = rinfo[j + 1].index; - rinfo[j + 1].index = tmp; - rinfo[rinfo[j].index].rev_index = j; - rinfo[rinfo[j + 1].index].rev_index = j + 1; - s = 1; - } - if (!s) - break; - } - #ifdef CONFIG_MAC80211_DEBUGFS de = &pinfo->dentries; de->target = debugfs_create_u32("target_pf", S_IRUSR | S_IWUSR, diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c index 5e75bbf..6c4846a 100644 --- a/net/rose/af_rose.c +++ b/net/rose/af_rose.c @@ -1072,10 +1072,6 @@ static int rose_sendmsg(struct kiocb *iocb, struct socket *sock, unsigned char *asmptr; int n, size, qbit = 0; - /* ROSE empty frame has no meaning : don't send */ - if (len == 0) - return 0; - if (msg->msg_flags & ~(MSG_DONTWAIT|MSG_EOR|MSG_CMSG_COMPAT)) return -EINVAL; @@ -1273,12 +1269,6 @@ static int rose_recvmsg(struct kiocb *iocb, struct socket *sock, skb_reset_transport_header(skb); copied = skb->len; - /* ROSE empty frame has no meaning : ignore it */ - if (copied == 0) { - skb_free_datagram(sk, skb); - return copied; - } - if (copied > size) { copied = size; msg->msg_flags |= MSG_TRUNC; diff --git a/net/sched/sch_teql.c b/net/sched/sch_teql.c index ec697ce..3b64182 100644 --- a/net/sched/sch_teql.c +++ b/net/sched/sch_teql.c @@ -303,6 +303,8 @@ restart: switch (teql_resolve(skb, skb_res, slave)) { case 0: if (__netif_tx_trylock(slave_txq)) { + unsigned int length = qdisc_pkt_len(skb); + if (!netif_tx_queue_stopped(slave_txq) && !netif_tx_queue_frozen(slave_txq) && slave_ops->ndo_start_xmit(skb, slave) == 0) { @@ -310,8 +312,7 @@ restart: master->slaves = NEXT_SLAVE(q); netif_wake_queue(dev); master->stats.tx_packets++; - master->stats.tx_bytes += - qdisc_pkt_len(skb); + master->stats.tx_bytes += length; return 0; } __netif_tx_unlock(slave_txq); diff --git a/net/wimax/op-msg.c b/net/wimax/op-msg.c index cb3b4ad..c229de3 100644 --- a/net/wimax/op-msg.c +++ b/net/wimax/op-msg.c @@ -149,7 +149,8 @@ struct sk_buff *wimax_msg_alloc(struct wimax_dev *wimax_dev, } result = nla_put(skb, WIMAX_GNL_MSG_DATA, size, msg); if (result < 0) { - dev_err(dev, "no memory to add payload in attribute\n"); + dev_err(dev, "no memory to add payload (msg %p size %zu) in " + "attribute: %d\n", msg, size, result); goto error_nla_put; } genlmsg_end(skb, genl_msg); @@ -302,10 +303,10 @@ int wimax_msg(struct wimax_dev *wimax_dev, const char *pipe_name, struct sk_buff *skb; skb = wimax_msg_alloc(wimax_dev, pipe_name, buf, size, gfp_flags); - if (skb == NULL) - goto error_msg_new; - result = wimax_msg_send(wimax_dev, skb); -error_msg_new: + if (IS_ERR(skb)) + result = PTR_ERR(skb); + else + result = wimax_msg_send(wimax_dev, skb); return result; } EXPORT_SYMBOL_GPL(wimax_msg); diff --git a/net/wireless/reg.c b/net/wireless/reg.c index 4f9ff2a..66cebb5 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -1497,6 +1497,13 @@ int regulatory_init(void) "using static definition\n"); #endif + /* + * This ensures last_request is populated once modules + * come swinging in and calling regulatory hints and + * wiphy_apply_custom_regulatory(). + */ + flush_scheduled_work(); + return 0; } diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 8227172..5f1f865 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -794,7 +794,7 @@ xfrm_state_find(xfrm_address_t *daddr, xfrm_address_t *saddr, { static xfrm_address_t saddr_wildcard = { }; struct net *net = xp_net(pol); - unsigned int h; + unsigned int h, h_wildcard; struct hlist_node *entry; struct xfrm_state *x, *x0, *to_put; int acquire_in_progress = 0; @@ -819,8 +819,8 @@ xfrm_state_find(xfrm_address_t *daddr, xfrm_address_t *saddr, if (best) goto found; - h = xfrm_dst_hash(net, daddr, &saddr_wildcard, tmpl->reqid, family); - hlist_for_each_entry(x, entry, net->xfrm.state_bydst+h, bydst) { + h_wildcard = xfrm_dst_hash(net, daddr, &saddr_wildcard, tmpl->reqid, family); + hlist_for_each_entry(x, entry, net->xfrm.state_bydst+h_wildcard, bydst) { if (x->props.family == family && x->props.reqid == tmpl->reqid && !(x->props.flags & XFRM_STATE_WILDRECV) && diff --git a/security/keys/request_key.c b/security/keys/request_key.c index 0e04f72..ab70cab 100644 --- a/security/keys/request_key.c +++ b/security/keys/request_key.c @@ -311,7 +311,8 @@ static int construct_alloc_key(struct key_type *type, set_bit(KEY_FLAG_USER_CONSTRUCT, &key->flags); - down_write(&dest_keyring->sem); + if (dest_keyring) + down_write(&dest_keyring->sem); /* attach the key to the destination keyring under lock, but we do need * to do another check just in case someone beat us to it whilst we @@ -322,10 +323,12 @@ static int construct_alloc_key(struct key_type *type, if (!IS_ERR(key_ref)) goto key_already_present; - __key_link(dest_keyring, key); + if (dest_keyring) + __key_link(dest_keyring, key); mutex_unlock(&key_construction_mutex); - up_write(&dest_keyring->sem); + if (dest_keyring) + up_write(&dest_keyring->sem); mutex_unlock(&user->cons_lock); *_key = key; kleave(" = 0 [%d]", key_serial(key)); diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index 8d24c91..9d62f29 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -4648,7 +4648,7 @@ static int selinux_ip_postroute_iptables_compat(struct sock *sk, if (err) return err; - if (send_perm != 0) + if (!send_perm) return 0; err = sel_netport_sid(sk->sk_protocol, diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 6c26afc..d76fe8f 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -11710,6 +11710,7 @@ static struct snd_pci_quirk alc268_cfg_tbl[] = { SND_PCI_QUIRK(0x1028, 0x0253, "Dell OEM", ALC268_DELL), SND_PCI_QUIRK(0x1028, 0x02b0, "Dell Inspiron Mini9", ALC268_DELL), SND_PCI_QUIRK(0x103c, 0x30cc, "TOSHIBA", ALC268_TOSHIBA), + SND_PCI_QUIRK(0x103c, 0x30f1, "HP TX25xx series", ALC268_TOSHIBA), SND_PCI_QUIRK(0x1043, 0x1205, "ASUS W7J", ALC268_3ST), SND_PCI_QUIRK(0x1179, 0xff10, "TOSHIBA A205", ALC268_TOSHIBA), SND_PCI_QUIRK(0x1179, 0xff50, "TOSHIBA A305", ALC268_TOSHIBA), diff --git a/sound/usb/usbaudio.c b/sound/usb/usbaudio.c index 19e3745..ee379cf 100644 --- a/sound/usb/usbaudio.c +++ b/sound/usb/usbaudio.c @@ -3375,7 +3375,7 @@ static int snd_usb_create_quirk(struct snd_usb_audio *chip, [QUIRK_MIDI_YAMAHA] = snd_usb_create_midi_interface, [QUIRK_MIDI_MIDIMAN] = snd_usb_create_midi_interface, [QUIRK_MIDI_NOVATION] = snd_usb_create_midi_interface, - [QUIRK_MIDI_RAW] = snd_usb_create_midi_interface, + [QUIRK_MIDI_FASTLANE] = snd_usb_create_midi_interface, [QUIRK_MIDI_EMAGIC] = snd_usb_create_midi_interface, [QUIRK_MIDI_CME] = snd_usb_create_midi_interface, [QUIRK_AUDIO_STANDARD_INTERFACE] = create_standard_audio_quirk, diff --git a/sound/usb/usbaudio.h b/sound/usb/usbaudio.h index 36e4f7a..8e7f789 100644 --- a/sound/usb/usbaudio.h +++ b/sound/usb/usbaudio.h @@ -153,7 +153,7 @@ enum quirk_type { QUIRK_MIDI_YAMAHA, QUIRK_MIDI_MIDIMAN, QUIRK_MIDI_NOVATION, - QUIRK_MIDI_RAW, + QUIRK_MIDI_FASTLANE, QUIRK_MIDI_EMAGIC, QUIRK_MIDI_CME, QUIRK_MIDI_US122L, diff --git a/sound/usb/usbmidi.c b/sound/usb/usbmidi.c index 26bad37..2fb35cc 100644 --- a/sound/usb/usbmidi.c +++ b/sound/usb/usbmidi.c @@ -1778,8 +1778,18 @@ int snd_usb_create_midi_interface(struct snd_usb_audio* chip, umidi->usb_protocol_ops = &snd_usbmidi_novation_ops; err = snd_usbmidi_detect_per_port_endpoints(umidi, endpoints); break; - case QUIRK_MIDI_RAW: + case QUIRK_MIDI_FASTLANE: umidi->usb_protocol_ops = &snd_usbmidi_raw_ops; + /* + * Interface 1 contains isochronous endpoints, but with the same + * numbers as in interface 0. Since it is interface 1 that the + * USB core has most recently seen, these descriptors are now + * associated with the endpoint numbers. This will foul up our + * attempts to submit bulk/interrupt URBs to the endpoints in + * interface 0, so we have to make sure that the USB core looks + * again at interface 0 by calling usb_set_interface() on it. + */ + usb_set_interface(umidi->chip->dev, 0, 0); err = snd_usbmidi_detect_per_port_endpoints(umidi, endpoints); break; case QUIRK_MIDI_EMAGIC: diff --git a/sound/usb/usbquirks.h b/sound/usb/usbquirks.h index 5d8ef09..25162f6 100644 --- a/sound/usb/usbquirks.h +++ b/sound/usb/usbquirks.h @@ -1858,7 +1858,7 @@ YAMAHA_DEVICE(0x7010, "UB99"), .data = & (const struct snd_usb_audio_quirk[]) { { .ifnum = 0, - .type = QUIRK_MIDI_RAW + .type = QUIRK_MIDI_FASTLANE }, { .ifnum = 1, diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index d85642e..9138d0d 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -2315,6 +2315,7 @@ int kvm_init(void *opaque, unsigned int vcpu_size, r = -ENOMEM; goto out_free_0; } + cpumask_clear(cpus_hardware_enabled); r = kvm_arch_hardware_setup(); if (r < 0)