diff options
68 files changed, 411 insertions, 350 deletions
diff --git a/arch/i386/kernel/setup.c b/arch/i386/kernel/setup.c index 519e63c3c13..141041dde74 100644 --- a/arch/i386/kernel/setup.c +++ b/arch/i386/kernel/setup.c @@ -846,7 +846,7 @@ efi_find_max_pfn(unsigned long start, unsigned long end, void *arg) static int __init efi_memory_present_wrapper(unsigned long start, unsigned long end, void *arg) { - memory_present(0, start, end); + memory_present(0, PFN_UP(start), PFN_DOWN(end)); return 0; } diff --git a/arch/i386/mach-visws/visws_apic.c b/arch/i386/mach-visws/visws_apic.c index 07097ed4889..38c2b13124d 100644 --- a/arch/i386/mach-visws/visws_apic.c +++ b/arch/i386/mach-visws/visws_apic.c @@ -122,7 +122,7 @@ static void end_cobalt_irq(unsigned int irq) spin_unlock_irqrestore(&cobalt_lock, flags); } -static struct hw_interrupt_type cobalt_irq_type = { +static struct irq_chip cobalt_irq_type = { .typename = "Cobalt-APIC", .startup = startup_cobalt_irq, .shutdown = disable_cobalt_irq, @@ -159,7 +159,7 @@ static void end_piix4_master_irq(unsigned int irq) spin_unlock_irqrestore(&cobalt_lock, flags); } -static struct hw_interrupt_type piix4_master_irq_type = { +static struct irq_chip piix4_master_irq_type = { .typename = "PIIX4-master", .startup = startup_piix4_master_irq, .ack = ack_cobalt_irq, @@ -167,9 +167,8 @@ static struct hw_interrupt_type piix4_master_irq_type = { }; -static struct hw_interrupt_type piix4_virtual_irq_type = { +static struct irq_chip piix4_virtual_irq_type = { .typename = "PIIX4-virtual", - .startup = startup_8259A_irq, .shutdown = disable_8259A_irq, .enable = enable_8259A_irq, .disable = disable_8259A_irq, diff --git a/arch/m68k/kernel/vmlinux-std.lds b/arch/m68k/kernel/vmlinux-std.lds index 69d1d3d30c7..d2794452b19 100644 --- a/arch/m68k/kernel/vmlinux-std.lds +++ b/arch/m68k/kernel/vmlinux-std.lds @@ -54,13 +54,7 @@ SECTIONS __setup_end = .; __initcall_start = .; .initcall.init : { - *(.initcall1.init) - *(.initcall2.init) - *(.initcall3.init) - *(.initcall4.init) - *(.initcall5.init) - *(.initcall6.init) - *(.initcall7.init) + INITCALLS } __initcall_end = .; __con_initcall_start = .; diff --git a/arch/m68k/kernel/vmlinux-sun3.lds b/arch/m68k/kernel/vmlinux-sun3.lds index 65cc39c2418..2550b4ae273 100644 --- a/arch/m68k/kernel/vmlinux-sun3.lds +++ b/arch/m68k/kernel/vmlinux-sun3.lds @@ -48,13 +48,7 @@ __init_begin = .; __setup_end = .; __initcall_start = .; .initcall.init : { - *(.initcall1.init) - *(.initcall2.init) - *(.initcall3.init) - *(.initcall4.init) - *(.initcall5.init) - *(.initcall6.init) - *(.initcall7.init) + INITCALLS } __initcall_end = .; __con_initcall_start = .; diff --git a/arch/s390/appldata/appldata_base.c b/arch/s390/appldata/appldata_base.c index 45c9fa7d754..af1e8fc7d98 100644 --- a/arch/s390/appldata/appldata_base.c +++ b/arch/s390/appldata/appldata_base.c @@ -310,6 +310,7 @@ appldata_interval_handler(ctl_table *ctl, int write, struct file *filp, if (copy_from_user(buf, buffer, len > sizeof(buf) ? sizeof(buf) : len)) { return -EFAULT; } + interval = 0; sscanf(buf, "%i", &interval); if (interval <= 0) { P_ERROR("Timer CPU interval has to be > 0!\n"); diff --git a/arch/s390/kernel/compat_linux.c b/arch/s390/kernel/compat_linux.c index 2001767e1dc..5b33f823863 100644 --- a/arch/s390/kernel/compat_linux.c +++ b/arch/s390/kernel/compat_linux.c @@ -757,7 +757,9 @@ asmlinkage long sys32_sysctl(struct __sysctl_args32 __user *args) put_user(oldlen, (u32 __user *)compat_ptr(tmp.oldlenp))) error = -EFAULT; } - copy_to_user(args->__unused, tmp.__unused, sizeof(tmp.__unused)); + if (copy_to_user(args->__unused, tmp.__unused, + sizeof(tmp.__unused))) + error = -EFAULT; } return error; } diff --git a/arch/s390/kernel/compat_signal.c b/arch/s390/kernel/compat_signal.c index d49b876a83b..861888ab8c1 100644 --- a/arch/s390/kernel/compat_signal.c +++ b/arch/s390/kernel/compat_signal.c @@ -169,12 +169,12 @@ sys32_sigaction(int sig, const struct old_sigaction32 __user *act, compat_old_sigset_t mask; if (!access_ok(VERIFY_READ, act, sizeof(*act)) || __get_user(sa_handler, &act->sa_handler) || - __get_user(sa_restorer, &act->sa_restorer)) + __get_user(sa_restorer, &act->sa_restorer) || + __get_user(new_ka.sa.sa_flags, &act->sa_flags) || + __get_user(mask, &act->sa_mask)) return -EFAULT; new_ka.sa.sa_handler = (__sighandler_t) sa_handler; new_ka.sa.sa_restorer = (void (*)(void)) sa_restorer; - __get_user(new_ka.sa.sa_flags, &act->sa_flags); - __get_user(mask, &act->sa_mask); siginitset(&new_ka.sa.sa_mask, mask); } @@ -185,10 +185,10 @@ sys32_sigaction(int sig, const struct old_sigaction32 __user *act, sa_restorer = (unsigned long) old_ka.sa.sa_restorer; if (!access_ok(VERIFY_WRITE, oact, sizeof(*oact)) || __put_user(sa_handler, &oact->sa_handler) || - __put_user(sa_restorer, &oact->sa_restorer)) + __put_user(sa_restorer, &oact->sa_restorer) || + __put_user(old_ka.sa.sa_flags, &oact->sa_flags) || + __put_user(old_ka.sa.sa_mask.sig[0], &oact->sa_mask)) return -EFAULT; - __put_user(old_ka.sa.sa_flags, &oact->sa_flags); - __put_user(old_ka.sa.sa_mask.sig[0], &oact->sa_mask); } return ret; diff --git a/arch/s390/kernel/compat_wrapper.S b/arch/s390/kernel/compat_wrapper.S index cb0efae6802..71e54ef0931 100644 --- a/arch/s390/kernel/compat_wrapper.S +++ b/arch/s390/kernel/compat_wrapper.S @@ -1664,4 +1664,4 @@ sys_getcpu_wrapper: llgtr %r2,%r2 # unsigned * llgtr %r3,%r3 # unsigned * llgtr %r4,%r4 # struct getcpu_cache * - jg sys_tee + jg sys_getcpu diff --git a/arch/s390/kernel/signal.c b/arch/s390/kernel/signal.c index 4392a77cbae..4c8a7954ef4 100644 --- a/arch/s390/kernel/signal.c +++ b/arch/s390/kernel/signal.c @@ -80,10 +80,10 @@ sys_sigaction(int sig, const struct old_sigaction __user *act, old_sigset_t mask; if (!access_ok(VERIFY_READ, act, sizeof(*act)) || __get_user(new_ka.sa.sa_handler, &act->sa_handler) || - __get_user(new_ka.sa.sa_restorer, &act->sa_restorer)) + __get_user(new_ka.sa.sa_restorer, &act->sa_restorer) || + __get_user(new_ka.sa.sa_flags, &act->sa_flags) || + __get_user(mask, &act->sa_mask)) return -EFAULT; - __get_user(new_ka.sa.sa_flags, &act->sa_flags); - __get_user(mask, &act->sa_mask); siginitset(&new_ka.sa.sa_mask, mask); } @@ -92,10 +92,10 @@ sys_sigaction(int sig, const struct old_sigaction __user *act, if (!ret && oact) { if (!access_ok(VERIFY_WRITE, oact, sizeof(*oact)) || __put_user(old_ka.sa.sa_handler, &oact->sa_handler) || - __put_user(old_ka.sa.sa_restorer, &oact->sa_restorer)) + __put_user(old_ka.sa.sa_restorer, &oact->sa_restorer) || + __put_user(old_ka.sa.sa_flags, &oact->sa_flags) || + __put_user(old_ka.sa.sa_mask.sig[0], &oact->sa_mask)) return -EFAULT; - __put_user(old_ka.sa.sa_flags, &oact->sa_flags); - __put_user(old_ka.sa.sa_mask.sig[0], &oact->sa_mask); } return ret; diff --git a/arch/s390/kernel/traps.c b/arch/s390/kernel/traps.c index 66375a5e3d1..92ecffbc8d8 100644 --- a/arch/s390/kernel/traps.c +++ b/arch/s390/kernel/traps.c @@ -462,7 +462,8 @@ asmlinkage void illegal_op(struct pt_regs * regs, long interruption_code) local_irq_enable(); if (regs->psw.mask & PSW_MASK_PSTATE) { - get_user(*((__u16 *) opcode), (__u16 __user *) location); + if (get_user(*((__u16 *) opcode), (__u16 __user *) location)) + return; if (*((__u16 *) opcode) == S390_BREAKPOINT_U16) { if (current->ptrace & PT_PTRACED) force_sig(SIGTRAP, current); @@ -470,20 +471,25 @@ asmlinkage void illegal_op(struct pt_regs * regs, long interruption_code) signal = SIGILL; #ifdef CONFIG_MATHEMU } else if (opcode[0] == 0xb3) { - get_user(*((__u16 *) (opcode+2)), location+1); + if (get_user(*((__u16 *) (opcode+2)), location+1)) + return; signal = math_emu_b3(opcode, regs); } else if (opcode[0] == 0xed) { - get_user(*((__u32 *) (opcode+2)), - (__u32 __user *)(location+1)); + if (get_user(*((__u32 *) (opcode+2)), + (__u32 __user *)(location+1))) + return; signal = math_emu_ed(opcode, regs); } else if (*((__u16 *) opcode) == 0xb299) { - get_user(*((__u16 *) (opcode+2)), location+1); + if (get_user(*((__u16 *) (opcode+2)), location+1)) + return; signal = math_emu_srnm(opcode, regs); } else if (*((__u16 *) opcode) == 0xb29c) { - get_user(*((__u16 *) (opcode+2)), location+1); + if (get_user(*((__u16 *) (opcode+2)), location+1)) + return; signal = math_emu_stfpc(opcode, regs); } else if (*((__u16 *) opcode) == 0xb29d) { - get_user(*((__u16 *) (opcode+2)), location+1); + if (get_user(*((__u16 *) (opcode+2)), location+1)) + return; signal = math_emu_lfpc(opcode, regs); #endif } else diff --git a/drivers/base/Kconfig b/drivers/base/Kconfig index 0b4e2243693..1429f3a2629 100644 --- a/drivers/base/Kconfig +++ b/drivers/base/Kconfig @@ -37,8 +37,8 @@ config DEBUG_DRIVER If you are unsure about this, say N here. -endmenu - config SYS_HYPERVISOR bool default n + +endmenu diff --git a/drivers/block/cciss.c b/drivers/block/cciss.c index bc6602606fb..6ffe2b2bdac 100644 --- a/drivers/block/cciss.c +++ b/drivers/block/cciss.c @@ -1992,8 +1992,8 @@ cciss_read_capacity(int ctlr, int logvol, int withirq, sector_t *total_size, *block_size = BLOCK_SIZE; } if (*total_size != (__u32) 0) - printk(KERN_INFO " blocks= %lld block_size= %d\n", - *total_size, *block_size); + printk(KERN_INFO " blocks= %llu block_size= %d\n", + (unsigned long long)*total_size, *block_size); kfree(buf); return; } @@ -2027,8 +2027,8 @@ cciss_read_capacity_16(int ctlr, int logvol, int withirq, sector_t *total_size, *total_size = 0; *block_size = BLOCK_SIZE; } - printk(KERN_INFO " blocks= %lld block_size= %d\n", - *total_size, *block_size); + printk(KERN_INFO " blocks= %llu block_size= %d\n", + (unsigned long long)*total_size, *block_size); kfree(buf); return; } diff --git a/drivers/char/watchdog/sc1200wdt.c b/drivers/char/watchdog/sc1200wdt.c index d8d0f28e0ac..e3239833e4b 100644 --- a/drivers/char/watchdog/sc1200wdt.c +++ b/drivers/char/watchdog/sc1200wdt.c @@ -392,7 +392,7 @@ static int __init sc1200wdt_init(void) if (io == -1) { printk(KERN_ERR PFX "io parameter must be specified\n"); ret = -EINVAL; - goto out_clean; + goto out_pnp; } #if defined CONFIG_PNP @@ -405,7 +405,7 @@ static int __init sc1200wdt_init(void) if (!request_region(io, io_len, SC1200_MODULE_NAME)) { printk(KERN_ERR PFX "Unable to register IO port %#x\n", io); ret = -EBUSY; - goto out_clean; + goto out_pnp; } ret = sc1200wdt_probe(); @@ -435,6 +435,11 @@ out_rbt: out_io: release_region(io, io_len); +out_pnp: +#if defined CONFIG_PNP + if (isapnp) + pnp_unregister_driver(&scl200wdt_pnp_driver); +#endif goto out_clean; } diff --git a/drivers/ide/pci/generic.c b/drivers/ide/pci/generic.c index ad418ce882c..e72ab36a549 100644 --- a/drivers/ide/pci/generic.c +++ b/drivers/ide/pci/generic.c @@ -247,8 +247,10 @@ static int __devinit generic_init_one(struct pci_dev *dev, const struct pci_devi (!(PCI_FUNC(dev->devfn) & 1))) goto out; - if (dev->vendor == PCI_VENDOR_ID_JMICRON && PCI_FUNC(dev->devfn) != 1) - goto out; + if (dev->vendor == PCI_VENDOR_ID_JMICRON) { + if (dev->device != PCI_DEVICE_ID_JMICRON_JMB368 && PCI_FUNC(dev->devfn) != 1) + goto out; + } if (dev->vendor != PCI_VENDOR_ID_JMICRON) { pci_read_config_word(dev, PCI_COMMAND, &command); diff --git a/drivers/ieee1394/ohci1394.c b/drivers/ieee1394/ohci1394.c index dea13525df8..6e8ea9110c4 100644 --- a/drivers/ieee1394/ohci1394.c +++ b/drivers/ieee1394/ohci1394.c @@ -3552,12 +3552,21 @@ static int ohci1394_pci_suspend (struct pci_dev *pdev, pm_message_t state) { int err; + printk(KERN_INFO "%s does not fully support suspend and resume yet\n", + OHCI1394_DRIVER_NAME); + err = pci_save_state(pdev); - if (err) - goto out; + if (err) { + printk(KERN_ERR "%s: pci_save_state failed with %d\n", + OHCI1394_DRIVER_NAME, err); + return err; + } err = pci_set_power_state(pdev, pci_choose_state(pdev, state)); +#ifdef OHCI1394_DEBUG if (err) - goto out; + printk(KERN_DEBUG "%s: pci_set_power_state failed with %d\n", + OHCI1394_DRIVER_NAME, err); +#endif /* OHCI1394_DEBUG */ /* PowerMac suspend code comes last */ #ifdef CONFIG_PPC_PMAC @@ -3570,8 +3579,8 @@ static int ohci1394_pci_suspend (struct pci_dev *pdev, pm_message_t state) pmac_call_feature(PMAC_FTR_1394_ENABLE, of_node, 0, 0); } #endif /* CONFIG_PPC_PMAC */ -out: - return err; + + return 0; } #endif /* CONFIG_PM */ diff --git a/drivers/md/md.c b/drivers/md/md.c index 7daa7b1e145..50ab4a936e3 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -2003,6 +2003,7 @@ static mdk_rdev_t *md_import_device(dev_t newdev, int super_format, int super_mi kobject_init(&rdev->kobj); rdev->desc_nr = -1; + rdev->saved_raid_disk = -1; rdev->flags = 0; rdev->data_offset = 0; rdev->sb_events = 0; @@ -4044,11 +4045,8 @@ static int update_size(mddev_t *mddev, unsigned long size) return -EBUSY; ITERATE_RDEV(mddev,rdev,tmp) { sector_t avail; - if (rdev->sb_offset > rdev->data_offset) - avail = (rdev->sb_offset*2) - rdev->data_offset; - else - avail = get_capacity(rdev->bdev->bd_disk) - - rdev->data_offset; + avail = rdev->size * 2; + if (fit && (size == 0 || size > avail/2)) size = avail/2; if (avail < ((sector_t)size << 1)) diff --git a/drivers/md/multipath.c b/drivers/md/multipath.c index a6260f0e3b9..14da37fee37 100644 --- a/drivers/md/multipath.c +++ b/drivers/md/multipath.c @@ -277,6 +277,7 @@ static void multipath_error (mddev_t *mddev, mdk_rdev_t *rdev) set_bit(Faulty, &rdev->flags); set_bit(MD_CHANGE_DEVS, &mddev->flags); conf->working_disks--; + mddev->degraded++; printk(KERN_ALERT "multipath: IO failure on %s," " disabling IO path. \n Operation continuing" " on %d IO paths.\n", @@ -336,6 +337,7 @@ static int multipath_add_disk(mddev_t *mddev, mdk_rdev_t *rdev) blk_queue_max_sectors(mddev->queue, PAGE_SIZE>>9); conf->working_disks++; + mddev->degraded--; rdev->raid_disk = path; set_bit(In_sync, &rdev->flags); rcu_assign_pointer(p->rdev, rdev); diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index dc9d2def027..656fae912fe 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -1474,8 +1474,8 @@ static void fix_read_error(conf_t *conf, int read_disk, "raid1:%s: read error corrected " "(%d sectors at %llu on %s)\n", mdname(mddev), s, - (unsigned long long)sect + - rdev->data_offset, + (unsigned long long)(sect + + rdev->data_offset), bdevname(rdev->bdev, b)); } } diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index 74f17a9a6eb..7492d6033ac 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -1470,8 +1470,8 @@ static void fix_read_error(conf_t *conf, mddev_t *mddev, r10bio_t *r10_bio) "raid10:%s: read error corrected" " (%d sectors at %llu on %s)\n", mdname(mddev), s, - (unsigned long long)sect+ - rdev->data_offset, + (unsigned long long)(sect+ + rdev->data_offset), bdevname(rdev->bdev, b)); rdev_dec_pending(rdev, mddev); diff --git a/drivers/misc/ioc4.c b/drivers/misc/ioc4.c index 79354bbbbd6..b995a15b752 100644 --- a/drivers/misc/ioc4.c +++ b/drivers/misc/ioc4.c @@ -210,8 +210,8 @@ ioc4_clock_calibrate(struct ioc4_driver_data *idd) do_div(ns, IOC4_EXTINT_COUNT_DIVISOR); printk(KERN_DEBUG - "IOC4 %s: PCI clock is %lld ns.\n", - pci_name(idd->idd_pdev), ns); + "IOC4 %s: PCI clock is %llu ns.\n", + pci_name(idd->idd_pdev), (unsigned long long)ns); } /* Remember results. We store the extint clock period rather diff --git a/drivers/net/wireless/hostap/hostap_cs.c b/drivers/net/wireless/hostap/hostap_cs.c index 686d895116d..f63909e4bc3 100644 --- a/drivers/net/wireless/hostap/hostap_cs.c +++ b/drivers/net/wireless/hostap/hostap_cs.c @@ -887,6 +887,13 @@ static struct pcmcia_device_id hostap_cs_ids[] = { PCMCIA_DEVICE_PROD_ID123( "U.S. Robotics", "IEEE 802.11b PC-CARD", "Version 01.02", 0xc7b8df9d, 0x1700d087, 0x4b74baa0), + PCMCIA_DEVICE_PROD_ID123( + "Allied Telesyn", "AT-WCL452 Wireless PCMCIA Radio", + "Ver. 1.00", + 0x5cd01705, 0x4271660f, 0x9d08ee12), + PCMCIA_DEVICE_PROD_ID123( + "corega", "WL PCCL-11", "ISL37300P", + 0xa21501a, 0x59868926, 0xc9049a39), PCMCIA_DEVICE_NULL }; MODULE_DEVICE_TABLE(pcmcia, hostap_cs_ids); diff --git a/drivers/pcmcia/at91_cf.c b/drivers/pcmcia/at91_cf.c index 7f5df9a9f39..3bcb7dc3299 100644 --- a/drivers/pcmcia/at91_cf.c +++ b/drivers/pcmcia/at91_cf.c @@ -241,12 +241,6 @@ static int __init at91_cf_probe(struct platform_device *pdev) csa = at91_sys_read(AT91_EBI_CSA); at91_sys_write(AT91_EBI_CSA, csa | AT91_EBI_CS4A_SMC_COMPACTFLASH); - /* force poweron defaults for these pins ... */ - (void) at91_set_A_periph(AT91_PIN_PC9, 0); /* A25/CFRNW */ - (void) at91_set_A_periph(AT91_PIN_PC10, 0); /* NCS4/CFCS */ - (void) at91_set_A_periph(AT91_PIN_PC11, 0); /* NCS5/CFCE1 */ - (void) at91_set_A_periph(AT91_PIN_PC12, 0); /* NCS6/CFCE2 */ - /* nWAIT is _not_ a default setting */ (void) at91_set_A_periph(AT91_PIN_PC6, 1); /* nWAIT */ @@ -316,12 +310,14 @@ static int __init at91_cf_probe(struct platform_device *pdev) return 0; fail2: - iounmap((void __iomem *) cf->socket.io_offset); release_mem_region(io->start, io->end + 1 - io->start); fail1: + if (cf->socket.io_offset) + iounmap((void __iomem *) cf->socket.io_offset); if (board->irq_pin) free_irq(board->irq_pin, cf); fail0a: + device_init_wakeup(&pdev->dev, 0); free_irq(board->det_pin, cf); device_init_wakeup(&pdev->dev, 0); fail0: @@ -360,26 +356,20 @@ static int at91_cf_suspend(struct platform_device *pdev, pm_message_t mesg) struct at91_cf_data *board = cf->board; pcmcia_socket_dev_suspend(&pdev->dev, mesg); - if (device_may_wakeup(&pdev->dev)) + if (device_may_wakeup(&pdev->dev)) { enable_irq_wake(board->det_pin); - else { + if (board->irq_pin) + enable_irq_wake(board->irq_pin); + } else { disable_irq_wake(board->det_pin); - disable_irq(board->det_pin); + if (board->irq_pin) + disable_irq_wake(board->irq_pin); } - if (board->irq_pin) - disable_irq(board->irq_pin); return 0; } static int at91_cf_resume(struct platform_device *pdev) { - struct at91_cf_socket *cf = platform_get_drvdata(pdev); - struct at91_cf_data *board = cf->board; - - if (board->irq_pin) - enable_irq(board->irq_pin); - if (!device_may_wakeup(&pdev->dev)) - enable_irq(board->det_pin); pcmcia_socket_dev_resume(&pdev->dev); return 0; } diff --git a/drivers/pcmcia/au1000_generic.c b/drivers/pcmcia/au1000_generic.c index d5dd0ce6553..551bde5d943 100644 --- a/drivers/pcmcia/au1000_generic.c +++ b/drivers/pcmcia/au1000_generic.c @@ -351,6 +351,7 @@ struct skt_dev_info { int au1x00_pcmcia_socket_probe(struct device *dev, struct pcmcia_low_level *ops, int first, int nr) { struct skt_dev_info *sinfo; + struct au1000_pcmcia_socket *skt; int ret, i; sinfo = kzalloc(sizeof(struct skt_dev_info), GFP_KERNEL); @@ -365,7 +366,7 @@ int au1x00_pcmcia_socket_probe(struct device *dev, struct pcmcia_low_level *ops, * Initialise the per-socket structure. */ for (i = 0; i < nr; i++) { - struct au1000_pcmcia_socket *skt = PCMCIA_SOCKET(i); + skt = PCMCIA_SOCKET(i); memset(skt, 0, sizeof(*skt)); skt->socket.resource_ops = &pccard_static_ops; @@ -438,17 +439,29 @@ int au1x00_pcmcia_socket_probe(struct device *dev, struct pcmcia_low_level *ops, dev_set_drvdata(dev, sinfo); return 0; - do { - struct au1000_pcmcia_socket *skt = PCMCIA_SOCKET(i); + +out_err: + flush_scheduled_work(); + ops->hw_shutdown(skt); + while (i-- > 0) { + skt = PCMCIA_SOCKET(i); del_timer_sync(&skt->poll_timer); pcmcia_unregister_socket(&skt->socket); -out_err: flush_scheduled_work(); + if (i == 0) { + iounmap(skt->virt_io + (u32)mips_io_port_base); + skt->virt_io = NULL; + } +#ifndef CONFIG_MIPS_XXS1500 + else { + iounmap(skt->virt_io + (u32)mips_io_port_base); + skt->virt_io = NULL; + } +#endif ops->hw_shutdown(skt); - i--; - } while (i > 0); + } kfree(sinfo); out: return ret; diff --git a/drivers/pcmcia/ds.c b/drivers/pcmcia/ds.c index 74b3124e824..0f701921c13 100644 --- a/drivers/pcmcia/ds.c +++ b/drivers/pcmcia/ds.c @@ -717,6 +717,7 @@ static int pcmcia_requery(struct device *dev, void * _data) static void pcmcia_bus_rescan(struct pcmcia_socket *skt) { int no_devices=0; + int ret = 0; unsigned long flags; /* must be called with skt_mutex held */ @@ -729,7 +730,7 @@ static void pcmcia_bus_rescan(struct pcmcia_socket *skt) * missing resource information or other trouble, we need to * do this now. */ if (no_devices) { - int ret = pcmcia_card_add(skt); + ret = pcmcia_card_add(skt); if (ret) return; } @@ -741,7 +742,9 @@ static void pcmcia_bus_rescan(struct pcmcia_socket *skt) /* we re-scan all devices, not just the ones connected to this * socket. This does not matter, though. */ - bus_rescan_devices(&pcmcia_bus_type); + ret = bus_rescan_devices(&pcmcia_bus_type); + if (ret) + printk(KERN_INFO "pcmcia: bus_rescan_devices failed\n"); } static inline int pcmcia_devmatch(struct pcmcia_device *dev, @@ -1001,6 +1004,7 @@ static ssize_t pcmcia_store_allow_func_id_match(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct pcmcia_device *p_dev = to_pcmcia_dev(dev); + int ret; if (!count) return -EINVAL; @@ -1009,7 +1013,10 @@ static ssize_t pcmcia_store_allow_func_id_match(struct device *dev, p_dev->allow_func_id_match = 1; mutex_unlock(&p_dev->socket->skt_mutex); - bus_rescan_devices(&pcmcia_bus_type); + ret = bus_rescan_devices(&pcmcia_bus_type); + if (ret) + printk(KERN_INFO "pcmcia: bus_rescan_devices failed after " + "allowing func_id matches\n"); return count; } @@ -1292,10 +1299,22 @@ struct bus_type pcmcia_bus_type = { static int __init init_pcmcia_bus(void) { + int ret; + spin_lock_init(&pcmcia_dev_list_lock); - bus_register(&pcmcia_bus_type); - class_interface_register(&pcmcia_bus_interface); + ret = bus_register(&pcmcia_bus_type); + if (ret < 0) { + printk(KERN_WARNING "pcmcia: bus_register error: %d\n", ret); + return ret; + } + ret = class_interface_register(&pcmcia_bus_interface); + if (ret < 0) { + printk(KERN_WARNING + "pcmcia: class_interface_register error: %d\n", ret); + bus_unregister(&pcmcia_bus_type); + return ret; + } pcmcia_setup_ioctl(); diff --git a/drivers/pcmcia/i82092.c b/drivers/pcmcia/i82092.c index 82715f44895..c2ea07aa7a1 100644 --- a/drivers/pcmcia/i82092.c +++ b/drivers/pcmcia/i82092.c @@ -41,6 +41,7 @@ static struct pci_device_id i82092aa_pci_ids[] = { }; MODULE_DEVICE_TABLE(pci, i82092aa_pci_ids); +#ifdef CONFIG_PM static int i82092aa_socket_suspend (struct pci_dev *dev, pm_message_t state) { return pcmcia_socket_dev_suspend(&dev->dev, state); @@ -50,14 +51,17 @@ static int i82092aa_socket_resume (struct pci_dev *dev) { return pcmcia_socket_dev_resume(&dev->dev); } +#endif static struct pci_driver i82092aa_pci_drv = { .name = "i82092aa", .id_table = i82092aa_pci_ids, .probe = i82092aa_pci_probe, .remove = __devexit_p(i82092aa_pci_remove), +#ifdef CONFIG_PM .suspend = i82092aa_socket_suspend, .resume = i82092aa_socket_resume, +#endif }; @@ -705,10 +709,7 @@ static int i82092aa_set_mem_map(struct pcmcia_socket *socket, struct pccard_mem_ static int i82092aa_module_init(void) { - enter("i82092aa_module_init"); - pci_register_driver(&i82092aa_pci_drv); - leave("i82092aa_module_init"); - return 0; + return pci_register_driver(&i82092aa_pci_drv); } static void i82092aa_module_exit(void) diff --git a/drivers/pcmcia/m8xx_pcmcia.c b/drivers/pcmcia/m8xx_pcmcia.c index e070a289676..3b72be88040 100644 --- a/drivers/pcmcia/m8xx_pcmcia.c +++ b/drivers/pcmcia/m8xx_pcmcia.c @@ -427,7 +427,7 @@ static int voltage_set(int slot, int vcc, int vpp) reg |= BCSR1_PCCVCC1; break; default: - return 1; + goto out_unmap; } switch(vpp) { @@ -438,15 +438,15 @@ static int voltage_set(int slot, int vcc, int vpp) if(vcc == vpp) reg |= BCSR1_PCCVPP1; else - return 1; + goto out_unmap; break; case 120: if ((vcc == 33) || (vcc == 50)) reg |= BCSR1_PCCVPP0; else - return 1; + goto out_unmap; default: - return 1; + goto out_unmap; } /* first, turn off all power */ @@ -457,6 +457,10 @@ static int voltage_set(int slot, int vcc, int vpp) iounmap(bcsr_io); return 0; + +out_unmap: + iounmap(bcsr_io); + return 1; } #define socket_get(_slot_) PCMCIA_SOCKET_KEY_5V diff --git a/drivers/pcmcia/omap_cf.c b/drivers/pcmcia/omap_cf.c index c8e838c6976..06bf7f48836 100644 --- a/drivers/pcmcia/omap_cf.c +++ b/drivers/pcmcia/omap_cf.c @@ -309,9 +309,10 @@ static int __devinit omap_cf_probe(struct device *dev) return 0; fail2: - iounmap((void __iomem *) cf->socket.io_offset); release_mem_region(cf->phys_cf, SZ_8K); fail1: + if (cf->socket.io_offset) + iounmap((void __iomem *) cf->socket.io_offset); free_irq(irq, cf); fail0: kfree(cf); diff --git a/drivers/pcmcia/pcmcia_ioctl.c b/drivers/pcmcia/pcmcia_ioctl.c index 9ad18e62658..310ede575ca 100644 --- a/drivers/pcmcia/pcmcia_ioctl.c +++ b/drivers/pcmcia/pcmcia_ioctl.c @@ -128,9 +128,12 @@ static int proc_read_drivers(char *buf, char **start, off_t pos, int count, int *eof, void *data) { char *p = buf; + int rc; - bus_for_each_drv(&pcmcia_bus_type, NULL, - (void *) &p, proc_read_drivers_callback); + rc = bus_for_each_drv(&pcmcia_bus_type, NULL, + (void *) &p, proc_read_drivers_callback); + if (rc < 0) + return rc; return (p - buf); } @@ -269,8 +272,10 @@ rescan: * Prevent this racing with a card insertion. */ mutex_lock(&s->skt_mutex); - bus_rescan_devices(&pcmcia_bus_type); + ret = bus_rescan_devices(&pcmcia_bus_type); mutex_unlock(&s->skt_mutex); + if (ret) + goto err_put_module; /* check whether the driver indeed matched. I don't care if this * is racy or not, because it can only happen on cardmgr access diff --git a/drivers/pcmcia/pcmcia_resource.c b/drivers/pcmcia/pcmcia_resource.c index 74cebd42403..b9201c2ec38 100644 --- a/drivers/pcmcia/pcmcia_resource.c +++ b/drivers/pcmcia/pcmcia_resource.c @@ -95,7 +95,7 @@ static int alloc_io_space(struct pcmcia_socket *s, u_int attr, ioaddr_t *base, * potential conflicts, just the most obvious ones. */ for (i = 0; i < MAX_IO_WIN; i++) - if ((s->io[i].res) && + if ((s->io[i].res) && *base && ((s->io[i].res->start & (align-1)) == *base)) return 1; for (i = 0; i < MAX_IO_WIN; i++) { diff --git a/drivers/pcmcia/pd6729.c b/drivers/pcmcia/pd6729.c index c83a0a6b158..a70f97fdbbd 100644 --- a/drivers/pcmcia/pd6729.c +++ b/drivers/pcmcia/pd6729.c @@ -755,6 +755,7 @@ static void __devexit pd6729_pci_remove(struct pci_dev *dev) kfree(socket); } +#ifdef CONFIG_PM static int pd6729_socket_suspend(struct pci_dev *dev, pm_message_t state) { return pcmcia_socket_dev_suspend(&dev->dev, state); @@ -764,6 +765,7 @@ static int pd6729_socket_resume(struct pci_dev *dev) { return pcmcia_socket_dev_resume(&dev->dev); } +#endif static struct pci_device_id pd6729_pci_ids[] = { { @@ -781,8 +783,10 @@ static struct pci_driver pd6729_pci_drv = { .id_table = pd6729_pci_ids, .probe = pd6729_pci_probe, .remove = __devexit_p(pd6729_pci_remove), +#ifdef CONFIG_PM .suspend = pd6729_socket_suspend, .resume = pd6729_socket_resume, +#endif }; static int pd6729_module_init(void) diff --git a/drivers/pcmcia/soc_common.c b/drivers/pcmcia/soc_common.c index 3627e52e0c2..e433704e026 100644 --- a/drivers/pcmcia/soc_common.c +++ b/drivers/pcmcia/soc_common.c @@ -824,3 +824,4 @@ int soc_common_drv_pcmcia_remove(struct device *dev) return 0; } +EXPORT_SYMBOL(soc_common_drv_pcmcia_remove); diff --git a/drivers/pcmcia/yenta_socket.c b/drivers/pcmcia/yenta_socket.c index 26229d9da76..da471bddc97 100644 --- a/drivers/pcmcia/yenta_socket.c +++ b/drivers/pcmcia/yenta_socket.c @@ -1197,8 +1197,12 @@ static int __devinit yenta_probe (struct pci_dev *dev, const struct pci_device_i ret = pcmcia_register_socket(&socket->socket); if (ret == 0) { /* Add the yenta register attributes */ - device_create_file(&dev->dev, &dev_attr_yenta_registers); - goto out; + ret = device_create_file(&dev->dev, &dev_attr_yenta_registers); + if (ret == 0) + goto out; + + /* error path... */ + pcmcia_unregister_socket(&socket->socket); } unmap: @@ -1213,7 +1217,7 @@ static int __devinit yenta_probe (struct pci_dev *dev, const struct pci_device_i return ret; } - +#ifdef CONFIG_PM static int yenta_dev_suspend (struct pci_dev *dev, pm_message_t state) { struct yenta_socket *socket = pci_get_drvdata(dev); @@ -1248,12 +1252,18 @@ static int yenta_dev_resume (struct pci_dev *dev) struct yenta_socket *socket = pci_get_drvdata(dev); if (socket) { + int rc; + pci_set_power_state(dev, 0); /* FIXME: pci_restore_state needs to have a better interface */ pci_restore_state(dev); pci_write_config_dword(dev, 16*4, socket->saved_state[0]); pci_write_config_dword(dev, 17*4, socket->saved_state[1]); - pci_enable_device(dev); + + rc = pci_enable_device(dev); + if (rc) + return rc; + pci_set_master(dev); if (socket->type && socket->type->restore_state) @@ -1262,7 +1272,7 @@ static int yenta_dev_resume (struct pci_dev *dev) return pcmcia_socket_dev_resume(&dev->dev); } - +#endif #define CB_ID(vend,dev,type) \ { \ @@ -1359,8 +1369,10 @@ static struct pci_driver yenta_cardbus_driver = { .id_table = yenta_table, .probe = yenta_probe, .remove = __devexit_p(yenta_close), +#ifdef CONFIG_PM .suspend = yenta_dev_suspend, .resume = yenta_dev_resume, +#endif }; diff --git a/drivers/s390/cio/css.c b/drivers/s390/cio/css.c index a2dee5bf5a1..ad7f7e1c016 100644 --- a/drivers/s390/cio/css.c +++ b/drivers/s390/cio/css.c @@ -271,10 +271,6 @@ static int css_evaluate_known_subchannel(struct subchannel *sch, int slow) /* Reset intparm to zeroes. */ sch->schib.pmcw.intparm = 0; cio_modify(sch); - - /* Probe if necessary. */ - if (action == UNREGISTER_PROBE) - ret = css_probe_device(sch->schid); break; case REPROBE: device_trigger_reprobe(sch); @@ -283,6 +279,9 @@ static int css_evaluate_known_subchannel(struct subchannel *sch, int slow) break; } spin_unlock_irqrestore(&sch->lock, flags); + /* Probe if necessary. */ + if (action == UNREGISTER_PROBE) + ret = css_probe_device(sch->schid); return ret; } diff --git a/drivers/s390/cio/device.c b/drivers/s390/cio/device.c index 94bdd4d8a4c..39c98f94050 100644 --- a/drivers/s390/cio/device.c +++ b/drivers/s390/cio/device.c @@ -532,8 +532,7 @@ device_remove_files(struct device *dev) /* this is a simple abstraction for device_register that sets the * correct bus type and adds the bus specific files */ -int -ccw_device_register(struct ccw_device *cdev) +static int ccw_device_register(struct ccw_device *cdev) { struct device *dev = &cdev->dev; int ret; diff --git a/drivers/s390/cio/device.h b/drivers/s390/cio/device.h index c6140cc97a8..9233b5c0bcc 100644 --- a/drivers/s390/cio/device.h +++ b/drivers/s390/cio/device.h @@ -78,7 +78,6 @@ void io_subchannel_recog_done(struct ccw_device *cdev); int ccw_device_cancel_halt_clear(struct ccw_device *); -int ccw_device_register(struct ccw_device *); void ccw_device_do_unreg_rereg(void *); void ccw_device_call_sch_unregister(void *); diff --git a/drivers/s390/crypto/ap_bus.c b/drivers/s390/crypto/ap_bus.c index c5ccd20b110..79d89c36891 100644 --- a/drivers/s390/crypto/ap_bus.c +++ b/drivers/s390/crypto/ap_bus.c @@ -739,11 +739,16 @@ static void ap_scan_bus(void *data) dev = bus_find_device(&ap_bus_type, NULL, (void *)(unsigned long)qid, __ap_scan_bus); + rc = ap_query_queue(qid, &queue_depth, &device_type); + if (dev && rc) { + put_device(dev); + device_unregister(dev); + continue; + } if (dev) { put_device(dev); continue; } - rc = ap_query_queue(qid, &queue_depth, &device_type); if (rc) continue; rc = ap_init_queue(qid); diff --git a/fs/block_dev.c b/fs/block_dev.c index bc8f27cc448..702b88cbd91 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -1131,6 +1131,8 @@ static int blkdev_open(struct inode * inode, struct file * filp) filp->f_flags |= O_LARGEFILE; bdev = bd_acquire(inode); + if (bdev == NULL) + return -ENOMEM; res = do_open(bdev, filp, BD_MUTEX_NORMAL); if (res) diff --git a/fs/dcache.c b/fs/dcache.c index a1ff91eef10..fd4a428998e 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -478,11 +478,12 @@ static void prune_dcache(int count, struct super_block *sb) up_read(s_umount); } spin_unlock(&dentry->d_lock); - /* Cannot remove the first dentry, and it isn't appropriate - * to move it to the head of the list, so give up, and try - * later + /* + * Insert dentry at the head of the list as inserting at the + * tail leads to a cycle. */ - break; + list_add(&dentry->d_lru, &dentry_unused); + dentry_stat.nr_unused++; } spin_unlock(&dcache_lock); } @@ -556,6 +557,7 @@ repeat: static void shrink_dcache_for_umount_subtree(struct dentry *dentry) { struct dentry *parent; + unsigned detached = 0; BUG_ON(!IS_ROOT(dentry)); @@ -620,7 +622,7 @@ static void shrink_dcache_for_umount_subtree(struct dentry *dentry) atomic_dec(&parent->d_count); list_del(&dentry->d_u.d_child); - dentry_stat.nr_dentry--; /* For d_free, below */ + detached++; inode = dentry->d_inode; if (inode) { @@ -638,7 +640,7 @@ static void shrink_dcache_for_umount_subtree(struct dentry *dentry) * otherwise we ascend to the parent and move to the * next sibling if there is one */ if (!parent) - return; + goto out; dentry = parent; @@ -647,6 +649,11 @@ static void shrink_dcache_for_umount_subtree(struct dentry *dentry) dentry = list_entry(dentry->d_subdirs.next, struct dentry, d_u.d_child); } +out: + /* several dentries were freed, need to correct nr_dentry */ + spin_lock(&dcache_lock); + dentry_stat.nr_dentry -= detached; + spin_unlock(&dcache_lock); } /* diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index 1e9578052cd..4fe49c3661b 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -69,44 +69,49 @@ static int verify_group_input(struct super_block *sb, else if (outside(input->block_bitmap, start, end)) ext4_warning(sb, __FUNCTION__, "Block bitmap not in group (block %llu)", - input->block_bitmap); + (unsigned long long)input->block_bitmap); else if (outside(input->inode_bitmap, start, end)) ext4_warning(sb, __FUNCTION__, "Inode bitmap not in group (block %llu)", - input->inode_bitmap); + (unsigned long long)input->inode_bitmap); else if (outside(input->inode_table, start, end) || outside(itend - 1, start, end)) ext4_warning(sb, __FUNCTION__, "Inode table not in group (blocks %llu-%llu)", - input->inode_table, itend - 1); + (unsigned long long)input->inode_table, itend - 1); else if (input->inode_bitmap == input->block_bitmap) ext4_warning(sb, __FUNCTION__, "Block bitmap same as inode bitmap (%llu)", - input->block_bitmap); + (unsigned long long)input->block_bitmap); else if (inside(input->block_bitmap, input->inode_table, itend)) ext4_warning(sb, __FUNCTION__, "Block bitmap (%llu) in inode table (%llu-%llu)", - input->block_bitmap, input->inode_table, itend-1); + (unsigned long long)input->block_bitmap, + (unsigned long long)input->inode_table, itend - 1); else if (inside(input->inode_bitmap, input->inode_table, itend)) ext4_warning(sb, __FUNCTION__, "Inode bitmap (%llu) in inode table (%llu-%llu)", - input->inode_bitmap, input->inode_table, itend-1); + (unsigned long long)input->inode_bitmap, + (unsigned long long)input->inode_table, itend - 1); else if (inside(input->block_bitmap, start, metaend)) ext4_warning(sb, __FUNCTION__, "Block bitmap (%llu) in GDT table" " (%llu-%llu)", - input->block_bitmap, start, metaend - 1); + (unsigned long long)input->block_bitmap, + start, metaend - 1); else if (inside(input->inode_bitmap, start, metaend)) ext4_warning(sb, __FUNCTION__, "Inode bitmap (%llu) in GDT table" " (%llu-%llu)", - input->inode_bitmap, start, metaend - 1); + (unsigned long long)input->inode_bitmap, + start, metaend - 1); else if (inside(input->inode_table, start, metaend) || inside(itend - 1, start, metaend)) ext4_warning(sb, __FUNCTION__, "Inode table (%llu-%llu) overlaps" "GDT table (%llu-%llu)", - input->inode_table, itend - 1, start, metaend - 1); + (unsigned long long)input->inode_table, + itend - 1, start, metaend - 1); else err = 0; brelse(bh); diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 4ee3f006b86..0bea6a619e1 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -271,26 +271,24 @@ static void hugetlbfs_drop_inode(struct inode *inode) hugetlbfs_forget_inode(inode); } -/* - * h_pgoff is in HPAGE_SIZE units. - * vma->vm_pgoff is in PAGE_SIZE units. - */ static inline void -hugetlb_vmtruncate_list(struct prio_tree_root *root, unsigned long h_pgoff) +hugetlb_vmtruncate_list(struct prio_tree_root *root, pgoff_t pgoff) { struct vm_area_struct *vma; struct prio_tree_iter iter; - vma_prio_tree_foreach(vma, &iter, root, h_pgoff, ULONG_MAX) { - unsigned long h_vm_pgoff; + vma_prio_tree_foreach(vma, &iter, root, pgoff, ULONG_MAX) { unsigned long v_offset; - h_vm_pgoff = vma->vm_pgoff >> (HPAGE_SHIFT - PAGE_SHIFT); - v_offset = (h_pgoff - h_vm_pgoff) << HPAGE_SHIFT; /* - * Is this VMA fully outside the truncation point? + * Can the expression below overflow on 32-bit arches? + * No, because the prio_tree returns us only those vmas + * which overlap the truncated area starting at pgoff, + * and no vma on a 32-bit arch can span beyond the 4GB. */ - if (h_vm_pgoff >= h_pgoff) + if (vma->vm_pgoff < pgoff) + v_offset = (pgoff - vma->vm_pgoff) << PAGE_SHIFT; + else v_offset = 0; __unmap_hugepage_range(vma, @@ -303,14 +301,14 @@ hugetlb_vmtruncate_list(struct prio_tree_root *root, unsigned long h_pgoff) */ static int hugetlb_vmtruncate(struct inode *inode, loff_t offset) { - unsigned long pgoff; + pgoff_t pgoff; struct address_space *mapping = inode->i_mapping; if (offset > inode->i_size) return -EINVAL; BUG_ON(offset & ~HPAGE_MASK); - pgoff = offset >> HPAGE_SHIFT; + pgoff = offset >> PAGE_SHIFT; inode->i_size = offset; spin_lock(&mapping->i_mmap_lock); @@ -624,7 +622,6 @@ hugetlbfs_parse_options(char *options, struct hugetlbfs_config *pconfig) do_div(size, 100); rest++; } - size &= HPAGE_MASK; pconfig->nr_blocks = (size >> HPAGE_SHIFT); value = rest; } else if (!strcmp(opt,"nr_inodes")) { diff --git a/fs/jbd/transaction.c b/fs/jbd/transaction.c index d5c63047a8b..4f82bcd63e4 100644 --- a/fs/jbd/transaction.c +++ b/fs/jbd/transaction.c @@ -967,6 +967,13 @@ int journal_dirty_data(handle_t *handle, struct buffer_head *bh) */ jbd_lock_bh_state(bh); spin_lock(&journal->j_list_lock); + + /* Now that we have bh_state locked, are we really still mapped? */ + if (!buffer_mapped(bh)) { + JBUFFER_TRACE(jh, "unmapped buffer, bailing out"); + goto no_journal; + } + if (jh->b_transaction) { JBUFFER_TRACE(jh, "has transaction"); if (jh->b_transaction != handle->h_transaction) { @@ -1028,6 +1035,11 @@ int journal_dirty_data(handle_t *handle, struct buffer_head *bh) sync_dirty_buffer(bh); jbd_lock_bh_state(bh); spin_lock(&journal->j_list_lock); + /* Since we dropped the lock... */ + if (!buffer_mapped(bh)) { + JBUFFER_TRACE(jh, "buffer got unmapped"); + goto no_journal; + } /* The buffer may become locked again at any time if it is redirtied */ } @@ -1824,6 +1836,7 @@ static int journal_unmap_buffer(journal_t *journal, struct buffer_head *bh) } } } else if (transaction == journal->j_committing_transaction) { + JBUFFER_TRACE(jh, "on committing transaction"); if (jh->b_jlist == BJ_Locked) { /* * The buffer is on the committing transaction's locked @@ -1838,7 +1851,6 @@ static int journal_unmap_buffer(journal_t *journal, struct buffer_head *bh) * can remove it's next_transaction pointer from the * running transaction if that is set, but nothing * else. */ - JBUFFER_TRACE(jh, "on committing transaction"); set_buffer_freed(bh); if (jh->b_next_transaction) { J_ASSERT(jh->b_next_transaction == @@ -1858,6 +1870,7 @@ static int journal_unmap_buffer(journal_t *journal, struct buffer_head *bh) * i_size already for this truncate so recovery will not * expose the disk blocks we are discarding here.) */ J_ASSERT_JH(jh, transaction == journal->j_running_transaction); + JBUFFER_TRACE(jh, "on running transaction"); may_free = __dispose_buffer(jh, transaction); } diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index b6cf2be845a..c051a94c8a9 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -967,6 +967,13 @@ int jbd2_journal_dirty_data(handle_t *handle, struct buffer_head *bh) */ jbd_lock_bh_state(bh); spin_lock(&journal->j_list_lock); + + /* Now that we have bh_state locked, are we really still mapped? */ + if (!buffer_mapped(bh)) { + JBUFFER_TRACE(jh, "unmapped buffer, bailing out"); + goto no_journal; + } + if (jh->b_transaction) { JBUFFER_TRACE(jh, "has transaction"); if (jh->b_transaction != handle->h_transaction) { @@ -1028,6 +1035,11 @@ int jbd2_journal_dirty_data(handle_t *handle, struct buffer_head *bh) sync_dirty_buffer(bh); jbd_lock_bh_state(bh); spin_lock(&journal->j_list_lock); + /* Since we dropped the lock... */ + if (!buffer_mapped(bh)) { + JBUFFER_TRACE(jh, "buffer got unmapped"); + goto no_journal; + } /* The buffer may become locked again at any time if it is redirtied */ } @@ -1824,6 +1836,7 @@ static int journal_unmap_buffer(journal_t *journal, struct buffer_head *bh) } } } else if (transaction == journal->j_committing_transaction) { + JBUFFER_TRACE(jh, "on committing transaction"); if (jh->b_jlist == BJ_Locked) { /* * The buffer is on the committing transaction's locked @@ -1838,7 +1851,6 @@ static int journal_unmap_buffer(journal_t *journal, struct buffer_head *bh) * can remove it's next_transaction pointer from the * running transaction if that is set, but nothing * else. */ - JBUFFER_TRACE(jh, "on committing transaction"); set_buffer_freed(bh); if (jh->b_next_transaction) { J_ASSERT(jh->b_next_transaction == @@ -1858,6 +1870,7 @@ static int journal_unmap_buffer(journal_t *journal, struct buffer_head *bh) * i_size already for this truncate so recovery will not * expose the disk blocks we are discarding here.) */ J_ASSERT_JH(jh, transaction == journal->j_running_transaction); + JBUFFER_TRACE(jh, "on running transaction"); may_free = __dispose_buffer(jh, transaction); } diff --git a/fs/splice.c b/fs/splice.c index 49fb9f12993..8d705954d29 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -74,7 +74,7 @@ static int page_cache_pipe_buf_steal(struct pipe_inode_info *pipe, wait_on_page_writeback(page); if (PagePrivate(page)) - try_to_release_page(page, mapping_gfp_mask(mapping)); + try_to_release_page(page, GFP_KERNEL); /* * If we succeeded in removing the mapping, set LRU flag @@ -333,7 +333,7 @@ __generic_file_splice_read(struct file *in, loff_t *ppos, break; error = add_to_page_cache_lru(page, mapping, index, - mapping_gfp_mask(mapping)); + GFP_KERNEL); if (unlikely(error)) { page_cache_release(page); if (error == -EEXIST) @@ -557,7 +557,6 @@ static int pipe_to_file(struct pipe_inode_info *pipe, struct pipe_buffer *buf, { struct file *file = sd->file; struct address_space *mapping = file->f_mapping; - gfp_t gfp_mask = mapping_gfp_mask(mapping); unsigned int offset, this_len; struct page *page; pgoff_t index; @@ -591,7 +590,7 @@ static int pipe_to_file(struct pipe_inode_info *pipe, struct pipe_buffer *buf, goto find_page; page = buf->page; - if (add_to_page_cache(page, mapping, index, gfp_mask)) { + if (add_to_page_cache(page, mapping, index, GFP_KERNEL)) { unlock_page(page); goto find_page; } @@ -613,7 +612,7 @@ find_page: * This will also lock the page */ ret = add_to_page_cache_lru(page, mapping, index, - gfp_mask); + GFP_KERNEL); if (unlikely(ret)) goto out; } diff --git a/include/asm-i386/mach-visws/do_timer.h b/include/asm-i386/mach-visws/do_timer.h deleted file mode 100644 index 21cd696d4d0..00000000000 --- a/include/asm-i386/mach-visws/do_timer.h +++ /dev/null @@ -1,53 +0,0 @@ -/* defines for inline arch setup functions */ - -#include <asm/fixmap.h> -#include <asm/i8259.h> -#include "cobalt.h" - -static inline void do_timer_interrupt_hook(void) -{ - /* Clear the interrupt */ - co_cpu_write(CO_CPU_STAT,co_cpu_read(CO_CPU_STAT) & ~CO_STAT_TIMEINTR); - - do_timer(1); -#ifndef CONFIG_SMP - update_process_times(user_mode_vm(irq_regs)); -#endif -/* - * In the SMP case we use the local APIC timer interrupt to do the - * profiling, except when we simulate SMP mode on a uniprocessor - * system, in that case we have to call the local interrupt handler. - */ -#ifndef CONFIG_X86_LOCAL_APIC - profile_tick(CPU_PROFILING); -#else - if (!using_apic_timer) - smp_local_timer_interrupt(); -#endif -} - -static inline int do_timer_overflow(int count) -{ - int i; - - spin_lock(&i8259A_lock); - /* - * This is tricky when I/O APICs are used; - * see do_timer_interrupt(). - */ - i = inb(0x20); - spin_unlock(&i8259A_lock); - - /* assumption about timer being IRQ0 */ - if (i & 0x01) { - /* - * We cannot detect lost timer interrupts ... - * well, that's why we call them lost, don't we? :) - * [hmm, on the Pentium and Alpha we can ... sort of] - */ - count -= LATCH; - } else { - printk("do_slow_gettimeoffset(): hardware timer problem?\n"); - } - return count; -} diff --git a/include/asm-i386/mach-visws/mach_apic.h b/include/asm-i386/mach-visws/mach_apic.h index de438c7147a..18afe6b6fc4 100644 --- a/include/asm-i386/mach-visws/mach_apic.h +++ b/include/asm-i386/mach-visws/mach_apic.h @@ -51,6 +51,11 @@ static inline void clustered_apic_check(void) { } +static inline int apicid_to_node(int logical_apicid) +{ + return 0; +} + /* Mapping from cpu number to logical apicid */ static inline int cpu_to_logical_apicid(int cpu) { diff --git a/include/linux/compat.h b/include/linux/compat.h index f4ebf96f530..f1553196826 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -196,7 +196,7 @@ asmlinkage long compat_sys_select(int n, compat_ulong_t __user *inp, #define BITS_TO_COMPAT_LONGS(bits) \ (((bits)+BITS_PER_COMPAT_LONG-1)/BITS_PER_COMPAT_LONG) -long compat_get_bitmap(unsigned long *mask, compat_ulong_t __user *umask, +long compat_get_bitmap(unsigned long *mask, const compat_ulong_t __user *umask, unsigned long bitmap_size); long compat_put_bitmap(compat_ulong_t __user *umask, unsigned long *mask, unsigned long bitmap_size); diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index ed0762b283a..e06683e2bea 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -218,13 +218,9 @@ struct zone { * under - it drives the swappiness decision: whether to unmap mapped * pages. * - * temp_priority is used to remember the scanning priority at which - * this zone was successfully refilled to free_pages == pages_high. - * - * Access to both these fields is quite racy even on uniprocessor. But + * Access to both this field is quite racy even on uniprocessor. But * it is expected to average out OK. */ - int temp_priority; int prev_priority; diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 64f95092515..c3e255bf859 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -52,19 +52,23 @@ static inline void mapping_set_gfp_mask(struct address_space *m, gfp_t mask) void release_pages(struct page **pages, int nr, int cold); #ifdef CONFIG_NUMA -extern struct page *page_cache_alloc(struct address_space *x); -extern struct page *page_cache_alloc_cold(struct address_space *x); +extern struct page *__page_cache_alloc(gfp_t gfp); #else +static inline struct page *__page_cache_alloc(gfp_t gfp) +{ + return alloc_pages(gfp, 0); +} +#endif + static inline struct page *page_cache_alloc(struct address_space *x) { - return alloc_pages(mapping_gfp_mask(x), 0); + return __page_cache_alloc(mapping_gfp_mask(x)); } static inline struct page *page_cache_alloc_cold(struct address_space *x) { - return alloc_pages(mapping_gfp_mask(x)|__GFP_COLD, 0); + return __page_cache_alloc(mapping_gfp_mask(x)|__GFP_COLD); } -#endif typedef int filler_t(void *, struct page *); diff --git a/include/linux/sched.h b/include/linux/sched.h index 6735c1cf334..eafe4a7b823 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -466,7 +466,6 @@ struct signal_struct { struct pacct_struct pacct; /* per-process accounting information */ #endif #ifdef CONFIG_TASKSTATS - spinlock_t stats_lock; struct taskstats *stats; #endif }; diff --git a/include/linux/taskstats_kern.h b/include/linux/taskstats_kern.h index 16894b7edcc..6562a2050a2 100644 --- a/include/linux/taskstats_kern.h +++ b/include/linux/taskstats_kern.h @@ -23,25 +23,26 @@ static inline void taskstats_exit_free(struct taskstats *tidstats) static inline void taskstats_tgid_init(struct signal_struct *sig) { - spin_lock_init(&sig->stats_lock); sig->stats = NULL; } -static inline void taskstats_tgid_alloc(struct signal_struct *sig) +static inline void taskstats_tgid_alloc(struct task_struct *tsk) { + struct signal_struct *sig = tsk->signal; struct taskstats *stats; - unsigned long flags; - stats = kmem_cache_zalloc(taskstats_cache, SLAB_KERNEL); - if (!stats) + if (sig->stats != NULL) return; - spin_lock_irqsave(&sig->stats_lock, flags); + /* No problem if kmem_cache_zalloc() fails */ + stats = kmem_cache_zalloc(taskstats_cache, SLAB_KERNEL); + + spin_lock_irq(&tsk->sighand->siglock); if (!sig->stats) { sig->stats = stats; stats = NULL; } - spin_unlock_irqrestore(&sig->stats_lock, flags); + spin_unlock_irq(&tsk->sighand->siglock); if (stats) kmem_cache_free(taskstats_cache, stats); @@ -49,23 +50,13 @@ static inline void taskstats_tgid_alloc(struct signal_struct *sig) static inline void taskstats_tgid_free(struct signal_struct *sig) { - struct taskstats *stats = NULL; - unsigned long flags; - - spin_lock_irqsave(&sig->stats_lock, flags); - if (sig->stats) { - stats = sig->stats; - sig->stats = NULL; - } - spin_unlock_irqrestore(&sig->stats_lock, flags); - if (stats) - kmem_cache_free(taskstats_cache, stats); + if (sig->stats) + kmem_cache_free(taskstats_cache, sig->stats); } extern void taskstats_exit_alloc(struct taskstats **, unsigned int *); extern void taskstats_exit_send(struct task_struct *, struct taskstats *, int, unsigned int); extern void taskstats_init_early(void); -extern void taskstats_tgid_alloc(struct signal_struct *); #else static inline void taskstats_exit_alloc(struct taskstats **ptidstats, unsigned int *mycpu) {} @@ -77,7 +68,7 @@ static inline void taskstats_exit_send(struct task_struct *tsk, {} static inline void taskstats_tgid_init(struct signal_struct *sig) {} -static inline void taskstats_tgid_alloc(struct signal_struct *sig) +static inline void taskstats_tgid_alloc(struct task_struct *tsk) {} static inline void taskstats_tgid_free(struct signal_struct *sig) {} diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index ce5f1482e6b..dc9a29d84ab 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -60,7 +60,8 @@ extern struct vm_struct *get_vm_area(unsigned long size, unsigned long flags); extern struct vm_struct *__get_vm_area(unsigned long size, unsigned long flags, unsigned long start, unsigned long end); extern struct vm_struct *get_vm_area_node(unsigned long size, - unsigned long flags, int node); + unsigned long flags, int node, + gfp_t gfp_mask); extern struct vm_struct *remove_vm_area(void *addr); extern int map_vm_area(struct vm_struct *area, pgprot_t prot, struct page ***pages); diff --git a/kernel/compat.c b/kernel/compat.c index 75573e5d27b..d4898aad6cf 100644 --- a/kernel/compat.c +++ b/kernel/compat.c @@ -678,7 +678,7 @@ int get_compat_sigevent(struct sigevent *event, ? -EFAULT : 0; } -long compat_get_bitmap(unsigned long *mask, compat_ulong_t __user *umask, +long compat_get_bitmap(unsigned long *mask, const compat_ulong_t __user *umask, unsigned long bitmap_size) { int i, j; diff --git a/kernel/cpu.c b/kernel/cpu.c index 27dd3ee4709..663c920b223 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -150,18 +150,18 @@ static int _cpu_down(unsigned int cpu) p = __stop_machine_run(take_cpu_down, NULL, cpu); mutex_unlock(&cpu_bitmask_lock); - if (IS_ERR(p)) { + if (IS_ERR(p) || cpu_online(cpu)) { /* CPU didn't die: tell everyone. Can't complain. */ if (raw_notifier_call_chain(&cpu_chain, CPU_DOWN_FAILED, (void *)(long)cpu) == NOTIFY_BAD) BUG(); - err = PTR_ERR(p); - goto out_allowed; - } - - if (cpu_online(cpu)) + if (IS_ERR(p)) { + err = PTR_ERR(p); + goto out_allowed; + } goto out_thread; + } /* Wait for it to sleep (leaving idle task). */ while (!idle_cpu(cpu)) diff --git a/kernel/exit.c b/kernel/exit.c index f250a5e3e28..06de6c4e8ca 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -128,6 +128,7 @@ static void __exit_signal(struct task_struct *tsk) flush_sigqueue(&tsk->pending); if (sig) { flush_sigqueue(&sig->shared_pending); + taskstats_tgid_free(sig); __cleanup_signal(sig); } } diff --git a/kernel/fork.c b/kernel/fork.c index 29ebb30850e..3da978eec79 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -830,7 +830,7 @@ static inline int copy_signal(unsigned long clone_flags, struct task_struct * ts if (clone_flags & CLONE_THREAD) { atomic_inc(¤t->signal->count); atomic_inc(¤t->signal->live); - taskstats_tgid_alloc(current->signal); + taskstats_tgid_alloc(current); return 0; } sig = kmem_cache_alloc(signal_cachep, GFP_KERNEL); @@ -897,7 +897,6 @@ static inline int copy_signal(unsigned long clone_flags, struct task_struct * ts void __cleanup_signal(struct signal_struct *sig) { exit_thread_group_keys(sig); - taskstats_tgid_free(sig); kmem_cache_free(signal_cachep, sig); } diff --git a/kernel/module.c b/kernel/module.c index 67009bd56c5..5072a943fe3 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -1342,7 +1342,7 @@ static void set_license(struct module *mod, const char *license) if (!license_is_gpl_compatible(license)) { if (!(tainted & TAINT_PROPRIETARY_MODULE)) - printk(KERN_WARNING "%s: module license '%s' taints" + printk(KERN_WARNING "%s: module license '%s' taints " "kernel.\n", mod->name, license); add_taint_module(mod, TAINT_PROPRIETARY_MODULE); } diff --git a/kernel/taskstats.c b/kernel/taskstats.c index 5d6a8c54ee8..2039585ec5e 100644 --- a/kernel/taskstats.c +++ b/kernel/taskstats.c @@ -77,7 +77,8 @@ static int prepare_reply(struct genl_info *info, u8 cmd, struct sk_buff **skbp, /* * If new attributes are added, please revisit this allocation */ - skb = nlmsg_new(genlmsg_total_size(size), GFP_KERNEL); + size = nlmsg_total_size(genlmsg_total_size(size)); + skb = nlmsg_new(size, GFP_KERNEL); if (!skb) return -ENOMEM; @@ -174,21 +175,19 @@ static void send_cpu_listeners(struct sk_buff *skb, unsigned int cpu) up_write(&listeners->sem); } -static int fill_pid(pid_t pid, struct task_struct *pidtsk, +static int fill_pid(pid_t pid, struct task_struct *tsk, struct taskstats *stats) { int rc = 0; - struct task_struct *tsk = pidtsk; - if (!pidtsk) { - read_lock(&tasklist_lock); + if (!tsk) { + rcu_read_lock(); tsk = find_task_by_pid(pid); - if (!tsk) { - read_unlock(&tasklist_lock); + if (tsk) + get_task_struct(tsk); + rcu_read_unlock(); + if (!tsk) return -ESRCH; - } - get_task_struct(tsk); - read_unlock(&tasklist_lock); } else get_task_struct(tsk); @@ -214,39 +213,30 @@ static int fill_pid(pid_t pid, struct task_struct *pidtsk, } -static int fill_tgid(pid_t tgid, struct task_struct *tgidtsk, +static int fill_tgid(pid_t tgid, struct task_struct *first, struct taskstats *stats) { - struct task_struct *tsk, *first; + struct task_struct *tsk; unsigned long flags; + int rc = -ESRCH; /* * Add additional stats from live tasks except zombie thread group * leaders who are already counted with the dead tasks */ - first = tgidtsk; - if (!first) { - read_lock(&tasklist_lock); + rcu_read_lock(); + if (!first) first = find_task_by_pid(tgid); - if (!first) { - read_unlock(&tasklist_lock); - return -ESRCH; - } - get_task_struct(first); - read_unlock(&tasklist_lock); - } else - get_task_struct(first); - /* Start with stats from dead tasks */ - spin_lock_irqsave(&first->signal->stats_lock, flags); + if (!first || !lock_task_sighand(first, &flags)) + goto out; + if (first->signal->stats) memcpy(stats, first->signal->stats, sizeof(*stats)); - spin_unlock_irqrestore(&first->signal->stats_lock, flags); tsk = first; - read_lock(&tasklist_lock); do { - if (tsk->exit_state == EXIT_ZOMBIE && thread_group_leader(tsk)) + if (tsk->exit_state) continue; /* * Accounting subsystem can call its functions here to @@ -257,15 +247,18 @@ static int fill_tgid(pid_t tgid, struct task_struct *tgidtsk, delayacct_add_tsk(stats, tsk); } while_each_thread(first, tsk); - read_unlock(&tasklist_lock); - stats->version = TASKSTATS_VERSION; + unlock_task_sighand(first, &flags); + rc = 0; +out: + rcu_read_unlock(); + + stats->version = TASKSTATS_VERSION; /* * Accounting subsytems can also add calls here to modify * fields of taskstats. */ - - return 0; + return rc; } @@ -273,7 +266,7 @@ static void fill_tgid_exit(struct task_struct *tsk) { unsigned long flags; - spin_lock_irqsave(&tsk->signal->stats_lock, flags); + spin_lock_irqsave(&tsk->sighand->siglock, flags); if (!tsk->signal->stats) goto ret; @@ -285,7 +278,7 @@ static void fill_tgid_exit(struct task_struct *tsk) */ delayacct_add_tsk(tsk->signal->stats, tsk); ret: - spin_unlock_irqrestore(&tsk->signal->stats_lock, flags); + spin_unlock_irqrestore(&tsk->sighand->siglock, flags); return; } @@ -419,7 +412,7 @@ static int taskstats_user_cmd(struct sk_buff *skb, struct genl_info *info) return send_reply(rep_skb, info->snd_pid); nla_put_failure: - return genlmsg_cancel(rep_skb, reply); + rc = genlmsg_cancel(rep_skb, reply); err: nlmsg_free(rep_skb); return rc; @@ -461,15 +454,10 @@ void taskstats_exit_send(struct task_struct *tsk, struct taskstats *tidstats, size_t size; int is_thread_group; struct nlattr *na; - unsigned long flags; if (!family_registered || !tidstats) return; - spin_lock_irqsave(&tsk->signal->stats_lock, flags); - is_thread_group = tsk->signal->stats ? 1 : 0; - spin_unlock_irqrestore(&tsk->signal->stats_lock, flags); - rc = 0; /* * Size includes space for nested attributes @@ -477,6 +465,7 @@ void taskstats_exit_send(struct task_struct *tsk, struct taskstats *tidstats, size = nla_total_size(sizeof(u32)) + nla_total_size(sizeof(struct taskstats)) + nla_total_size(0); + is_thread_group = (tsk->signal->stats != NULL); if (is_thread_group) size = 2 * size; /* PID + STATS + TGID + STATS */ @@ -519,7 +508,6 @@ send: nla_put_failure: genlmsg_cancel(rep_skb, reply); - goto ret; err_skb: nlmsg_free(rep_skb); ret: diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c index 47195fa0ec4..3afeaa3a73f 100644 --- a/kernel/time/ntp.c +++ b/kernel/time/ntp.c @@ -161,9 +161,9 @@ void second_overflow(void) time_adjust += MAX_TICKADJ; tick_length -= MAX_TICKADJ_SCALED; } else { - time_adjust = 0; tick_length += (s64)(time_adjust * NSEC_PER_USEC / HZ) << TICK_LENGTH_SHIFT; + time_adjust = 0; } } } diff --git a/kernel/tsacct.c b/kernel/tsacct.c index db443221ba5..65a5036a3d9 100644 --- a/kernel/tsacct.c +++ b/kernel/tsacct.c @@ -36,7 +36,7 @@ void bacct_add_tsk(struct taskstats *stats, struct task_struct *tsk) /* calculate task elapsed time in timespec */ do_posix_clock_monotonic_gettime(&uptime); - ts = timespec_sub(uptime, current->group_leader->start_time); + ts = timespec_sub(uptime, tsk->start_time); /* rebase elapsed time to usec */ ac_etime = timespec_to_ns(&ts); do_div(ac_etime, NSEC_PER_USEC); @@ -58,7 +58,10 @@ void bacct_add_tsk(struct taskstats *stats, struct task_struct *tsk) stats->ac_uid = tsk->uid; stats->ac_gid = tsk->gid; stats->ac_pid = tsk->pid; - stats->ac_ppid = (tsk->parent) ? tsk->parent->pid : 0; + rcu_read_lock(); + stats->ac_ppid = pid_alive(tsk) ? + rcu_dereference(tsk->real_parent)->tgid : 0; + rcu_read_unlock(); stats->ac_utime = cputime_to_msecs(tsk->utime) * USEC_PER_MSEC; stats->ac_stime = cputime_to_msecs(tsk->stime) * USEC_PER_MSEC; stats->ac_minflt = tsk->min_flt; diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 3df9bfc7ff7..17c2f03d2c2 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -99,7 +99,7 @@ static void __queue_work(struct cpu_workqueue_struct *cwq, * @wq: workqueue to use * @work: work to queue * - * Returns non-zero if it was successfully added. + * Returns 0 if @work was already on a queue, non-zero otherwise. * * We queue the work to the CPU it was submitted, but there is no * guarantee that it will be processed by that CPU. @@ -138,7 +138,7 @@ static void delayed_work_timer_fn(unsigned long __data) * @work: work to queue * @delay: number of jiffies to wait before queueing * - * Returns non-zero if it was successfully added. + * Returns 0 if @work was already on a queue, non-zero otherwise. */ int fastcall queue_delayed_work(struct workqueue_struct *wq, struct work_struct *work, unsigned long delay) @@ -169,7 +169,7 @@ EXPORT_SYMBOL_GPL(queue_delayed_work); * @work: work to queue * @delay: number of jiffies to wait before queueing * - * Returns non-zero if it was successfully added. + * Returns 0 if @work was already on a queue, non-zero otherwise. */ int queue_delayed_work_on(int cpu, struct workqueue_struct *wq, struct work_struct *work, unsigned long delay) diff --git a/lib/string.c b/lib/string.c index 63077267367..a485d75962a 100644 --- a/lib/string.c +++ b/lib/string.c @@ -320,7 +320,7 @@ char *strstrip(char *s) return s; end = s + size - 1; - while (end != s && isspace(*end)) + while (end >= s && isspace(*end)) end--; *(end + 1) = '\0'; diff --git a/mm/filemap.c b/mm/filemap.c index cb26e33fd0f..7b84dc81434 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -467,25 +467,15 @@ int add_to_page_cache_lru(struct page *page, struct address_space *mapping, } #ifdef CONFIG_NUMA -struct page *page_cache_alloc(struct address_space *x) +struct page *__page_cache_alloc(gfp_t gfp) { if (cpuset_do_page_mem_spread()) { int n = cpuset_mem_spread_node(); - return alloc_pages_node(n, mapping_gfp_mask(x), 0); + return alloc_pages_node(n, gfp, 0); } - return alloc_pages(mapping_gfp_mask(x), 0); + return alloc_pages(gfp, 0); } -EXPORT_SYMBOL(page_cache_alloc); - -struct page *page_cache_alloc_cold(struct address_space *x) -{ - if (cpuset_do_page_mem_spread()) { - int n = cpuset_mem_spread_node(); - return alloc_pages_node(n, mapping_gfp_mask(x)|__GFP_COLD, 0); - } - return alloc_pages(mapping_gfp_mask(x)|__GFP_COLD, 0); -} -EXPORT_SYMBOL(page_cache_alloc_cold); +EXPORT_SYMBOL(__page_cache_alloc); #endif static int __sleep_on_page_lock(void *word) @@ -826,7 +816,6 @@ struct page * grab_cache_page_nowait(struct address_space *mapping, unsigned long index) { struct page *page = find_get_page(mapping, index); - gfp_t gfp_mask; if (page) { if (!TestSetPageLocked(page)) @@ -834,9 +823,8 @@ grab_cache_page_nowait(struct address_space *mapping, unsigned long index) page_cache_release(page); return NULL; } - gfp_mask = mapping_gfp_mask(mapping) & ~__GFP_FS; - page = alloc_pages(gfp_mask, 0); - if (page && add_to_page_cache_lru(page, mapping, index, gfp_mask)) { + page = __page_cache_alloc(mapping_gfp_mask(mapping) & ~__GFP_FS); + if (page && add_to_page_cache_lru(page, mapping, index, GFP_KERNEL)) { page_cache_release(page); page = NULL; } diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 2dbec90dc3b..a088f593a80 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -478,6 +478,9 @@ int hugetlb_no_page(struct mm_struct *mm, struct vm_area_struct *vma, retry: page = find_lock_page(mapping, idx); if (!page) { + size = i_size_read(mapping->host) >> HPAGE_SHIFT; + if (idx >= size) + goto out; if (hugetlb_get_quota(mapping)) goto out; page = alloc_huge_page(vma, address); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index f5fc45472d5..b55bb358b83 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -2261,7 +2261,7 @@ unsigned long __init __absent_pages_in_range(int nid, /* Account for ranges past physical memory on this node */ if (range_end_pfn > prev_end_pfn) - hole_pages = range_end_pfn - + hole_pages += range_end_pfn - max(range_start_pfn, prev_end_pfn); return hole_pages; @@ -2407,7 +2407,7 @@ static void __meminit free_area_init_core(struct pglist_data *pgdat, zone->zone_pgdat = pgdat; zone->free_pages = 0; - zone->temp_priority = zone->prev_priority = DEF_PRIORITY; + zone->prev_priority = DEF_PRIORITY; zone_pcp_init(zone); INIT_LIST_HEAD(&zone->active_list); diff --git a/mm/sparse.c b/mm/sparse.c index 86c52ab8087..b3c82ba3001 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -211,7 +211,7 @@ static struct page *__kmalloc_section_memmap(unsigned long nr_pages) struct page *page, *ret; unsigned long memmap_size = sizeof(struct page) * nr_pages; - page = alloc_pages(GFP_KERNEL, get_order(memmap_size)); + page = alloc_pages(GFP_KERNEL|__GFP_NOWARN, get_order(memmap_size)); if (page) goto got_map_page; diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 1133dd3aafc..46606c133e8 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -160,13 +160,15 @@ int map_vm_area(struct vm_struct *area, pgprot_t prot, struct page ***pages) return err; } -struct vm_struct *__get_vm_area_node(unsigned long size, unsigned long flags, - unsigned long start, unsigned long end, int node) +static struct vm_struct *__get_vm_area_node(unsigned long size, unsigned long flags, + unsigned long start, unsigned long end, + int node, gfp_t gfp_mask) { struct vm_struct **p, *tmp, *area; unsigned long align = 1; unsigned long addr; + BUG_ON(in_interrupt()); if (flags & VM_IOREMAP) { int bit = fls(size); @@ -180,7 +182,7 @@ struct vm_struct *__get_vm_area_node(unsigned long size, unsigned long flags, addr = ALIGN(start, align); size = PAGE_ALIGN(size); - area = kmalloc_node(sizeof(*area), GFP_KERNEL, node); + area = kmalloc_node(sizeof(*area), gfp_mask & GFP_LEVEL_MASK, node); if (unlikely(!area)) return NULL; @@ -236,7 +238,7 @@ out: struct vm_struct *__get_vm_area(unsigned long size, unsigned long flags, unsigned long start, unsigned long end) { - return __get_vm_area_node(size, flags, start, end, -1); + return __get_vm_area_node(size, flags, start, end, -1, GFP_KERNEL); } /** @@ -253,9 +255,11 @@ struct vm_struct *get_vm_area(unsigned long size, unsigned long flags) return __get_vm_area(size, flags, VMALLOC_START, VMALLOC_END); } -struct vm_struct *get_vm_area_node(unsigned long size, unsigned long flags, int node) +struct vm_struct *get_vm_area_node(unsigned long size, unsigned long flags, + int node, gfp_t gfp_mask) { - return __get_vm_area_node(size, flags, VMALLOC_START, VMALLOC_END, node); + return __get_vm_area_node(size, flags, VMALLOC_START, VMALLOC_END, node, + gfp_mask); } /* Caller must hold vmlist_lock */ @@ -487,7 +491,7 @@ static void *__vmalloc_node(unsigned long size, gfp_t gfp_mask, pgprot_t prot, if (!size || (size >> PAGE_SHIFT) > num_physpages) return NULL; - area = get_vm_area_node(size, VM_ALLOC, node); + area = get_vm_area_node(size, VM_ALLOC, node, gfp_mask); if (!area) return NULL; diff --git a/mm/vmscan.c b/mm/vmscan.c index f05527bf792..518540a4a2a 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -723,6 +723,20 @@ done: return nr_reclaimed; } +/* + * We are about to scan this zone at a certain priority level. If that priority + * level is smaller (ie: more urgent) than the previous priority, then note + * that priority level within the zone. This is done so that when the next + * process comes in to scan this zone, it will immediately start out at this + * priority level rather than having to build up its own scanning priority. + * Here, this priority affects only the reclaim-mapped threshold. + */ +static inline void note_zone_scanning_priority(struct zone *zone, int priority) +{ + if (priority < zone->prev_priority) + zone->prev_priority = priority; +} + static inline int zone_is_near_oom(struct zone *zone) { return zone->pages_scanned >= (zone->nr_active + zone->nr_inactive)*3; @@ -746,7 +760,7 @@ static inline int zone_is_near_oom(struct zone *zone) * But we had to alter page->flags anyway. */ static void shrink_active_list(unsigned long nr_pages, struct zone *zone, - struct scan_control *sc) + struct scan_control *sc, int priority) { unsigned long pgmoved; int pgdeactivate = 0; @@ -770,7 +784,7 @@ static void shrink_active_list(unsigned long nr_pages, struct zone *zone, * `distress' is a measure of how much trouble we're having * reclaiming pages. 0 -> no problems. 100 -> great trouble. */ - distress = 100 >> zone->prev_priority; + distress = 100 >> min(zone->prev_priority, priority); /* * The point of this algorithm is to decide when to start @@ -922,7 +936,7 @@ static unsigned long shrink_zone(int priority, struct zone *zone, nr_to_scan = min(nr_active, (unsigned long)sc->swap_cluster_max); nr_active -= nr_to_scan; - shrink_active_list(nr_to_scan, zone, sc); + shrink_active_list(nr_to_scan, zone, sc, priority); } if (nr_inactive) { @@ -972,9 +986,7 @@ static unsigned long shrink_zones(int priority, struct zone **zones, if (!cpuset_zone_allowed(zone, __GFP_HARDWALL)) continue; - zone->temp_priority = priority; - if (zone->prev_priority > priority) - zone->prev_priority = priority; + note_zone_scanning_priority(zone, priority); if (zone->all_unreclaimable && priority != DEF_PRIORITY) continue; /* Let kswapd poll it */ @@ -1024,7 +1036,6 @@ unsigned long try_to_free_pages(struct zone **zones, gfp_t gfp_mask) if (!cpuset_zone_allowed(zone, __GFP_HARDWALL)) continue; - zone->temp_priority = DEF_PRIORITY; lru_pages += zone->nr_active + zone->nr_inactive; } @@ -1065,13 +1076,22 @@ unsigned long try_to_free_pages(struct zone **zones, gfp_t gfp_mask) if (!sc.all_unreclaimable) ret = 1; out: + /* + * Now that we've scanned all the zones at this priority level, note + * that level within the zone so that the next thread which performs + * scanning of this zone will immediately start out at this priority + * level. This affects only the decision whether or not to bring + * mapped pages onto the inactive list. + */ + if (priority < 0) + priority = 0; for (i = 0; zones[i] != 0; i++) { struct zone *zone = zones[i]; if (!cpuset_zone_allowed(zone, __GFP_HARDWALL)) continue; - zone->prev_priority = zone->temp_priority; + zone->prev_priority = priority; } return ret; } @@ -1111,6 +1131,11 @@ static unsigned long balance_pgdat(pg_data_t *pgdat, int order) .swap_cluster_max = SWAP_CLUSTER_MAX, .swappiness = vm_swappiness, }; + /* + * temp_priority is used to remember the scanning priority at which + * this zone was successfully refilled to free_pages == pages_high. + */ + int temp_priority[MAX_NR_ZONES]; loop_again: total_scanned = 0; @@ -1118,11 +1143,8 @@ loop_again: sc.may_writepage = !laptop_mode; count_vm_event(PAGEOUTRUN); - for (i = 0; i < pgdat->nr_zones; i++) { - struct zone *zone = pgdat->node_zones + i; - - zone->temp_priority = DEF_PRIORITY; - } + for (i = 0; i < pgdat->nr_zones; i++) + temp_priority[i] = DEF_PRIORITY; for (priority = DEF_PRIORITY; priority >= 0; priority--) { int end_zone = 0; /* Inclusive. 0 = ZONE_DMA */ @@ -1183,10 +1205,9 @@ scan: if (!zone_watermark_ok(zone, order, zone->pages_high, end_zone, 0)) all_zones_ok = 0; - zone->temp_priority = priority; - if (zone->prev_priority > priority) - zone->prev_priority = priority; + temp_priority[i] = priority; sc.nr_scanned = 0; + note_zone_scanning_priority(zone, priority); nr_reclaimed += shrink_zone(priority, zone, &sc); reclaim_state->reclaimed_slab = 0; nr_slab = shrink_slab(sc.nr_scanned, GFP_KERNEL, @@ -1226,10 +1247,15 @@ scan: break; } out: + /* + * Note within each zone the priority level at which this zone was + * brought into a happy state. So that the next thread which scans this + * zone will start out at that priority level. + */ for (i = 0; i < pgdat->nr_zones; i++) { struct zone *zone = pgdat->node_zones + i; - zone->prev_priority = zone->temp_priority; + zone->prev_priority = temp_priority[i]; } if (!all_zones_ok) { cond_resched(); @@ -1358,7 +1384,7 @@ static unsigned long shrink_all_zones(unsigned long nr_pages, int pass, if (zone->nr_scan_active >= nr_pages || pass > 3) { zone->nr_scan_active = 0; nr_to_scan = min(nr_pages, zone->nr_active); - shrink_active_list(nr_to_scan, zone, sc); + shrink_active_list(nr_to_scan, zone, sc, prio); } } @@ -1614,6 +1640,7 @@ static int __zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order) */ priority = ZONE_RECLAIM_PRIORITY; do { + note_zone_scanning_priority(zone, priority); nr_reclaimed += shrink_zone(priority, zone, &sc); priority--; } while (priority >= 0 && nr_reclaimed < nr_pages); diff --git a/mm/vmstat.c b/mm/vmstat.c index 45b124e012f..8614e8f6743 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -587,11 +587,9 @@ static int zoneinfo_show(struct seq_file *m, void *arg) seq_printf(m, "\n all_unreclaimable: %u" "\n prev_priority: %i" - "\n temp_priority: %i" "\n start_pfn: %lu", zone->all_unreclaimable, zone->prev_priority, - zone->temp_priority, zone->zone_start_pfn); spin_unlock_irqrestore(&zone->lock, flags); seq_putc(m, '\n'); |