diff options
81 files changed, 491 insertions, 502 deletions
diff --git a/arch/alpha/kernel/vmlinux.lds.S b/arch/alpha/kernel/vmlinux.lds.S index 71470e9d93b..76bf071e376 100644 --- a/arch/alpha/kernel/vmlinux.lds.S +++ b/arch/alpha/kernel/vmlinux.lds.S @@ -48,13 +48,7 @@ SECTIONS . = ALIGN(8); __initcall_start = .; .initcall.init : { - *(.initcall1.init) - *(.initcall2.init) - *(.initcall3.init) - *(.initcall4.init) - *(.initcall5.init) - *(.initcall6.init) - *(.initcall7.init) + INITCALLS } __initcall_end = .; diff --git a/arch/arm/kernel/vmlinux.lds.S b/arch/arm/kernel/vmlinux.lds.S index 3ca574ee277..a8fa75ea07a 100644 --- a/arch/arm/kernel/vmlinux.lds.S +++ b/arch/arm/kernel/vmlinux.lds.S @@ -45,13 +45,7 @@ SECTIONS *(.early_param.init) __early_end = .; __initcall_start = .; - *(.initcall1.init) - *(.initcall2.init) - *(.initcall3.init) - *(.initcall4.init) - *(.initcall5.init) - *(.initcall6.init) - *(.initcall7.init) + INITCALLS __initcall_end = .; __con_initcall_start = .; *(.con_initcall.init) diff --git a/arch/avr32/kernel/vmlinux.lds.c b/arch/avr32/kernel/vmlinux.lds.c index cdd627c6b7d..5c4424e362b 100644 --- a/arch/avr32/kernel/vmlinux.lds.c +++ b/arch/avr32/kernel/vmlinux.lds.c @@ -38,13 +38,7 @@ SECTIONS __setup_end = .; . = ALIGN(4); __initcall_start = .; - *(.initcall1.init) - *(.initcall2.init) - *(.initcall3.init) - *(.initcall4.init) - *(.initcall5.init) - *(.initcall6.init) - *(.initcall7.init) + INITCALLS __initcall_end = .; __con_initcall_start = .; *(.con_initcall.init) diff --git a/arch/frv/kernel/vmlinux.lds.S b/arch/frv/kernel/vmlinux.lds.S index f474534ba78..9c1fb12367f 100644 --- a/arch/frv/kernel/vmlinux.lds.S +++ b/arch/frv/kernel/vmlinux.lds.S @@ -44,13 +44,7 @@ SECTIONS __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/h8300/kernel/vmlinux.lds.S b/arch/h8300/kernel/vmlinux.lds.S index 6406c388f88..756325dd480 100644 --- a/arch/h8300/kernel/vmlinux.lds.S +++ b/arch/h8300/kernel/vmlinux.lds.S @@ -118,13 +118,7 @@ SECTIONS . = ALIGN(0x4) ; ___setup_end = .; ___initcall_start = .; - *(.initcall1.init) - *(.initcall2.init) - *(.initcall3.init) - *(.initcall4.init) - *(.initcall5.init) - *(.initcall6.init) - *(.initcall7.init) + INITCALLS ___initcall_end = .; ___con_initcall_start = .; *(.con_initcall.init) 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/kernel/vmlinux.lds.S b/arch/i386/kernel/vmlinux.lds.S index 1e7ac1c44dd..adc1f232afe 100644 --- a/arch/i386/kernel/vmlinux.lds.S +++ b/arch/i386/kernel/vmlinux.lds.S @@ -126,13 +126,7 @@ SECTIONS __setup_end = .; __initcall_start = .; .initcall.init : AT(ADDR(.initcall.init) - LOAD_OFFSET) { - *(.initcall1.init) - *(.initcall2.init) - *(.initcall3.init) - *(.initcall4.init) - *(.initcall5.init) - *(.initcall6.init) - *(.initcall7.init) + INITCALLS } __initcall_end = .; __con_initcall_start = .; 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/i386/pci/fixup.c b/arch/i386/pci/fixup.c index 908b410f4c9..c1949ff38d6 100644 --- a/arch/i386/pci/fixup.c +++ b/arch/i386/pci/fixup.c @@ -343,6 +343,61 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_MCH_PC, pcie_ro DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_MCH_PC1, pcie_rootport_aspm_quirk ); /* + * Fixup to mark boot BIOS video selected by BIOS before it changes + * + * From information provided by "Jon Smirl" <jonsmirl@gmail.com> + * + * The standard boot ROM sequence for an x86 machine uses the BIOS + * to select an initial video card for boot display. This boot video + * card will have it's BIOS copied to C0000 in system RAM. + * IORESOURCE_ROM_SHADOW is used to associate the boot video + * card with this copy. On laptops this copy has to be used since + * the main ROM may be compressed or combined with another image. + * See pci_map_rom() for use of this flag. IORESOURCE_ROM_SHADOW + * is marked here since the boot video device will be the only enabled + * video device at this point. + */ + +static void __devinit pci_fixup_video(struct pci_dev *pdev) +{ + struct pci_dev *bridge; + struct pci_bus *bus; + u16 config; + + if ((pdev->class >> 8) != PCI_CLASS_DISPLAY_VGA) + return; + + /* Is VGA routed to us? */ + bus = pdev->bus; + while (bus) { + bridge = bus->self; + + /* + * From information provided by + * "David Miller" <davem@davemloft.net> + * The bridge control register is valid for PCI header + * type BRIDGE, or CARDBUS. Host to PCI controllers use + * PCI header type NORMAL. + */ + if (bridge + &&((bridge->hdr_type == PCI_HEADER_TYPE_BRIDGE) + ||(bridge->hdr_type == PCI_HEADER_TYPE_CARDBUS))) { + pci_read_config_word(bridge, PCI_BRIDGE_CONTROL, + &config); + if (!(config & PCI_BRIDGE_CTL_VGA)) + return; + } + bus = bus->parent; + } + pci_read_config_word(pdev, PCI_COMMAND, &config); + if (config & (PCI_COMMAND_IO | PCI_COMMAND_MEMORY)) { + pdev->resource[PCI_ROM_RESOURCE].flags |= IORESOURCE_ROM_SHADOW; + printk(KERN_DEBUG "Boot video device is %s\n", pci_name(pdev)); + } +} +DECLARE_PCI_FIXUP_HEADER(PCI_ANY_ID, PCI_ANY_ID, pci_fixup_video); + +/* * Some Toshiba laptops need extra code to enable their TI TSB43AB22/A. * * We pretend to bring them out of full D3 state, and restore the proper diff --git a/arch/ia64/kernel/vmlinux.lds.S b/arch/ia64/kernel/vmlinux.lds.S index b3b2e389d6b..d6083a0936f 100644 --- a/arch/ia64/kernel/vmlinux.lds.S +++ b/arch/ia64/kernel/vmlinux.lds.S @@ -128,13 +128,7 @@ SECTIONS .initcall.init : AT(ADDR(.initcall.init) - LOAD_OFFSET) { __initcall_start = .; - *(.initcall1.init) - *(.initcall2.init) - *(.initcall3.init) - *(.initcall4.init) - *(.initcall5.init) - *(.initcall6.init) - *(.initcall7.init) + INITCALLS __initcall_end = .; } diff --git a/arch/ia64/pci/Makefile b/arch/ia64/pci/Makefile index e66889e6922..fb14dc520d2 100644 --- a/arch/ia64/pci/Makefile +++ b/arch/ia64/pci/Makefile @@ -1,4 +1,4 @@ # # Makefile for the ia64-specific parts of the pci bus # -obj-y := pci.o +obj-y := pci.o fixup.o diff --git a/arch/ia64/pci/fixup.c b/arch/ia64/pci/fixup.c new file mode 100644 index 00000000000..245dc1fedc2 --- /dev/null +++ b/arch/ia64/pci/fixup.c @@ -0,0 +1,69 @@ +/* + * Exceptions for specific devices. Usually work-arounds for fatal design flaws. + * Derived from fixup.c of i386 tree. + */ + +#include <linux/pci.h> +#include <linux/init.h> + +#include <asm/machvec.h> + +/* + * Fixup to mark boot BIOS video selected by BIOS before it changes + * + * From information provided by "Jon Smirl" <jonsmirl@gmail.com> + * + * The standard boot ROM sequence for an x86 machine uses the BIOS + * to select an initial video card for boot display. This boot video + * card will have it's BIOS copied to C0000 in system RAM. + * IORESOURCE_ROM_SHADOW is used to associate the boot video + * card with this copy. On laptops this copy has to be used since + * the main ROM may be compressed or combined with another image. + * See pci_map_rom() for use of this flag. IORESOURCE_ROM_SHADOW + * is marked here since the boot video device will be the only enabled + * video device at this point. + */ + +static void __devinit pci_fixup_video(struct pci_dev *pdev) +{ + struct pci_dev *bridge; + struct pci_bus *bus; + u16 config; + + if ((strcmp(platform_name, "dig") != 0) + && (strcmp(platform_name, "hpzx1") != 0)) + return; + /* Maybe, this machine supports legacy memory map. */ + + if ((pdev->class >> 8) != PCI_CLASS_DISPLAY_VGA) + return; + + /* Is VGA routed to us? */ + bus = pdev->bus; + while (bus) { + bridge = bus->self; + + /* + * From information provided by + * "David Miller" <davem@davemloft.net> + * The bridge control register is valid for PCI header + * type BRIDGE, or CARDBUS. Host to PCI controllers use + * PCI header type NORMAL. + */ + if (bridge + &&((bridge->hdr_type == PCI_HEADER_TYPE_BRIDGE) + ||(bridge->hdr_type == PCI_HEADER_TYPE_CARDBUS))) { + pci_read_config_word(bridge, PCI_BRIDGE_CONTROL, + &config); + if (!(config & PCI_BRIDGE_CTL_VGA)) + return; + } + bus = bus->parent; + } + pci_read_config_word(pdev, PCI_COMMAND, &config); + if (config & (PCI_COMMAND_IO | PCI_COMMAND_MEMORY)) { + pdev->resource[PCI_ROM_RESOURCE].flags |= IORESOURCE_ROM_SHADOW; + printk(KERN_DEBUG "Boot video device is %s\n", pci_name(pdev)); + } +} +DECLARE_PCI_FIXUP_HEADER(PCI_ANY_ID, PCI_ANY_ID, pci_fixup_video); diff --git a/arch/m32r/kernel/vmlinux.lds.S b/arch/m32r/kernel/vmlinux.lds.S index 13c7bb698e3..358b9cee2c6 100644 --- a/arch/m32r/kernel/vmlinux.lds.S +++ b/arch/m32r/kernel/vmlinux.lds.S @@ -83,13 +83,7 @@ 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/m68knommu/kernel/vmlinux.lds.S b/arch/m68knommu/kernel/vmlinux.lds.S index ccd2ceb05cf..58afa8be604 100644 --- a/arch/m68knommu/kernel/vmlinux.lds.S +++ b/arch/m68knommu/kernel/vmlinux.lds.S @@ -140,13 +140,7 @@ SECTIONS { *(.init.setup) __setup_end = .; __initcall_start = .; - *(.initcall1.init) - *(.initcall2.init) - *(.initcall3.init) - *(.initcall4.init) - *(.initcall5.init) - *(.initcall6.init) - *(.initcall7.init) + INITCALLS __initcall_end = .; __con_initcall_start = .; *(.con_initcall.init) diff --git a/arch/mips/kernel/vmlinux.lds.S b/arch/mips/kernel/vmlinux.lds.S index 0bb9cd88945..25ed3337ce3 100644 --- a/arch/mips/kernel/vmlinux.lds.S +++ b/arch/mips/kernel/vmlinux.lds.S @@ -91,13 +91,7 @@ SECTIONS __initcall_start = .; .initcall.init : { - *(.initcall1.init) - *(.initcall2.init) - *(.initcall3.init) - *(.initcall4.init) - *(.initcall5.init) - *(.initcall6.init) - *(.initcall7.init) + INITCALLS } __initcall_end = .; diff --git a/arch/parisc/kernel/vmlinux.lds.S b/arch/parisc/kernel/vmlinux.lds.S index b3677fc8eef..7b943b45f7c 100644 --- a/arch/parisc/kernel/vmlinux.lds.S +++ b/arch/parisc/kernel/vmlinux.lds.S @@ -153,13 +153,7 @@ 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/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S index cb0e8d46c3e..e8342d86753 100644 --- a/arch/powerpc/kernel/vmlinux.lds.S +++ b/arch/powerpc/kernel/vmlinux.lds.S @@ -108,13 +108,7 @@ SECTIONS .initcall.init : { __initcall_start = .; - *(.initcall1.init) - *(.initcall2.init) - *(.initcall3.init) - *(.initcall4.init) - *(.initcall5.init) - *(.initcall6.init) - *(.initcall7.init) + INITCALLS __initcall_end = .; } diff --git a/arch/ppc/kernel/vmlinux.lds.S b/arch/ppc/kernel/vmlinux.lds.S index 095fd332332..16e8661e1fe 100644 --- a/arch/ppc/kernel/vmlinux.lds.S +++ b/arch/ppc/kernel/vmlinux.lds.S @@ -115,13 +115,7 @@ SECTIONS __setup_end = .; __initcall_start = .; .initcall.init : { - *(.initcall1.init) - *(.initcall2.init) - *(.initcall3.init) - *(.initcall4.init) - *(.initcall5.init) - *(.initcall6.init) - *(.initcall7.init) + INITCALLS } __initcall_end = .; diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S index af9e69a0301..fe0f2e97ba7 100644 --- a/arch/s390/kernel/vmlinux.lds.S +++ b/arch/s390/kernel/vmlinux.lds.S @@ -83,13 +83,7 @@ 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/sh/kernel/vmlinux.lds.S b/arch/sh/kernel/vmlinux.lds.S index 5eb93091818..77b4026d568 100644 --- a/arch/sh/kernel/vmlinux.lds.S +++ b/arch/sh/kernel/vmlinux.lds.S @@ -76,13 +76,7 @@ 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/sh64/kernel/vmlinux.lds.S b/arch/sh64/kernel/vmlinux.lds.S index a8fcc3a7158..95c4d753e35 100644 --- a/arch/sh64/kernel/vmlinux.lds.S +++ b/arch/sh64/kernel/vmlinux.lds.S @@ -108,13 +108,7 @@ SECTIONS __setup_end = .; __initcall_start = .; .initcall.init : C_PHYS(.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/sparc/kernel/ebus.c b/arch/sparc/kernel/ebus.c index 75ac24d229b..ba58c3a061f 100644 --- a/arch/sparc/kernel/ebus.c +++ b/arch/sparc/kernel/ebus.c @@ -237,12 +237,12 @@ void __init fill_ebus_device(struct device_node *dp, struct linux_ebus_device *d dev->ofdev.node = dp; dev->ofdev.dev.parent = &dev->bus->ofdev.dev; dev->ofdev.dev.bus = &ebus_bus_type; - strcpy(dev->ofdev.dev.bus_id, dp->path_component_name); + sprintf(dev->ofdev.dev.bus_id, "ebus[%08x]", dp->node); /* Register with core */ if (of_device_register(&dev->ofdev) != 0) printk(KERN_DEBUG "ebus: device registration error for %s!\n", - dev->ofdev.dev.bus_id); + dp->path_component_name); if ((dp = dp->child) != NULL) { dev->children = (struct linux_ebus_child *) @@ -332,12 +332,12 @@ void __init ebus_init(void) ebus->ofdev.node = dp; ebus->ofdev.dev.parent = &pdev->dev; ebus->ofdev.dev.bus = &ebus_bus_type; - strcpy(ebus->ofdev.dev.bus_id, dp->path_component_name); + sprintf(ebus->ofdev.dev.bus_id, "ebus%d", num_ebus); /* Register with core */ if (of_device_register(&ebus->ofdev) != 0) printk(KERN_DEBUG "ebus: device registration error for %s!\n", - ebus->ofdev.dev.bus_id); + dp->path_component_name); nd = dp->child; diff --git a/arch/sparc/kernel/of_device.c b/arch/sparc/kernel/of_device.c index 74bef2a2d37..46200c43ffb 100644 --- a/arch/sparc/kernel/of_device.c +++ b/arch/sparc/kernel/of_device.c @@ -651,7 +651,7 @@ build_resources: if (!parent) strcpy(op->dev.bus_id, "root"); else - strcpy(op->dev.bus_id, dp->path_component_name); + sprintf(op->dev.bus_id, "%08x", dp->node); if (of_device_register(op)) { printk("%s: Could not register of device.\n", diff --git a/arch/sparc/kernel/vmlinux.lds.S b/arch/sparc/kernel/vmlinux.lds.S index 1dd78c84888..5cc5ff7f882 100644 --- a/arch/sparc/kernel/vmlinux.lds.S +++ b/arch/sparc/kernel/vmlinux.lds.S @@ -49,13 +49,7 @@ 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/sparc64/kernel/ebus.c b/arch/sparc64/kernel/ebus.c index 2df25c2b407..35bf895fdee 100644 --- a/arch/sparc64/kernel/ebus.c +++ b/arch/sparc64/kernel/ebus.c @@ -389,12 +389,12 @@ static void __init fill_ebus_device(struct device_node *dp, struct linux_ebus_de dev->ofdev.node = dp; dev->ofdev.dev.parent = &dev->bus->ofdev.dev; dev->ofdev.dev.bus = &ebus_bus_type; - strcpy(dev->ofdev.dev.bus_id, dp->path_component_name); + sprintf(dev->ofdev.dev.bus_id, "ebus[%08x]", dp->node); /* Register with core */ if (of_device_register(&dev->ofdev) != 0) printk(KERN_DEBUG "ebus: device registration error for %s!\n", - dev->ofdev.dev.bus_id); + dp->path_component_name); dp = dp->child; if (dp) { @@ -494,12 +494,12 @@ void __init ebus_init(void) ebus->ofdev.node = dp; ebus->ofdev.dev.parent = &pdev->dev; ebus->ofdev.dev.bus = &ebus_bus_type; - strcpy(ebus->ofdev.dev.bus_id, dp->path_component_name); + sprintf(ebus->ofdev.dev.bus_id, "ebus%d", num_ebus); /* Register with core */ if (of_device_register(&ebus->ofdev) != 0) printk(KERN_DEBUG "ebus: device registration error for %s!\n", - ebus->ofdev.dev.bus_id); + dp->path_component_name); child = dp->child; diff --git a/arch/sparc64/kernel/isa.c b/arch/sparc64/kernel/isa.c index 0f3aec72ef5..f028e68b23f 100644 --- a/arch/sparc64/kernel/isa.c +++ b/arch/sparc64/kernel/isa.c @@ -115,12 +115,12 @@ static void __init isa_fill_devices(struct sparc_isa_bridge *isa_br) isa_dev->ofdev.node = dp; isa_dev->ofdev.dev.parent = &isa_br->ofdev.dev; isa_dev->ofdev.dev.bus = &isa_bus_type; - strcpy(isa_dev->ofdev.dev.bus_id, dp->path_component_name); + sprintf(isa_dev->ofdev.dev.bus_id, "isa[%08x]", dp->node); /* Register with core */ if (of_device_register(&isa_dev->ofdev) != 0) { printk(KERN_DEBUG "isa: device registration error for %s!\n", - isa_dev->ofdev.dev.bus_id); + dp->path_component_name); kfree(isa_dev); goto next_sibling; } @@ -191,12 +191,12 @@ void __init isa_init(void) isa_br->ofdev.node = dp; isa_br->ofdev.dev.parent = &pdev->dev; isa_br->ofdev.dev.bus = &isa_bus_type; - strcpy(isa_br->ofdev.dev.bus_id, dp->path_component_name); + sprintf(isa_br->ofdev.dev.bus_id, "isa%d", index); /* Register with core */ if (of_device_register(&isa_br->ofdev) != 0) { printk(KERN_DEBUG "isa: device registration error for %s!\n", - isa_br->ofdev.dev.bus_id); + dp->path_component_name); kfree(isa_br); return; } diff --git a/arch/sparc64/kernel/of_device.c b/arch/sparc64/kernel/of_device.c index 983ca5f485c..8cc14fc6b6f 100644 --- a/arch/sparc64/kernel/of_device.c +++ b/arch/sparc64/kernel/of_device.c @@ -861,7 +861,7 @@ static struct of_device * __init scan_one_device(struct device_node *dp, if (!parent) strcpy(op->dev.bus_id, "root"); else - sprintf(op->dev.bus_id, "%s@%08x", dp->name, dp->node); + sprintf(op->dev.bus_id, "%08x", dp->node); if (of_device_register(op)) { printk("%s: Could not register of device.\n", diff --git a/arch/sparc64/kernel/vmlinux.lds.S b/arch/sparc64/kernel/vmlinux.lds.S index b097379a49a..bd9de8c2a2a 100644 --- a/arch/sparc64/kernel/vmlinux.lds.S +++ b/arch/sparc64/kernel/vmlinux.lds.S @@ -57,13 +57,7 @@ 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/v850/kernel/vmlinux.lds.S b/arch/v850/kernel/vmlinux.lds.S index 63399219cd9..88d087f527c 100644 --- a/arch/v850/kernel/vmlinux.lds.S +++ b/arch/v850/kernel/vmlinux.lds.S @@ -140,13 +140,7 @@ ___setup_end = . ; \ ___initcall_start = . ; \ *(.initcall.init) \ - *(.initcall1.init) \ - *(.initcall2.init) \ - *(.initcall3.init) \ - *(.initcall4.init) \ - *(.initcall5.init) \ - *(.initcall6.init) \ - *(.initcall7.init) \ + INITCALLS \ . = ALIGN (4) ; \ ___initcall_end = . ; \ ___con_initcall_start = .; \ diff --git a/arch/x86_64/kernel/vmlinux.lds.S b/arch/x86_64/kernel/vmlinux.lds.S index 1283614c9b2..edb24aa714b 100644 --- a/arch/x86_64/kernel/vmlinux.lds.S +++ b/arch/x86_64/kernel/vmlinux.lds.S @@ -175,13 +175,7 @@ SECTIONS __setup_end = .; __initcall_start = .; .initcall.init : AT(ADDR(.initcall.init) - LOAD_OFFSET) { - *(.initcall1.init) - *(.initcall2.init) - *(.initcall3.init) - *(.initcall4.init) - *(.initcall5.init) - *(.initcall6.init) - *(.initcall7.init) + INITCALLS } __initcall_end = .; __con_initcall_start = .; diff --git a/arch/x86_64/pci/mmconfig.c b/arch/x86_64/pci/mmconfig.c index 7732f4254d2..e61093b34c2 100644 --- a/arch/x86_64/pci/mmconfig.c +++ b/arch/x86_64/pci/mmconfig.c @@ -220,7 +220,7 @@ void __init pci_mmcfg_init(int type) pci_mmcfg_virt = kmalloc(sizeof(*pci_mmcfg_virt) * pci_mmcfg_config_num, GFP_KERNEL); if (pci_mmcfg_virt == NULL) { - printk("PCI: Can not allocate memory for mmconfig structures\n"); + printk(KERN_ERR "PCI: Can not allocate memory for mmconfig structures\n"); return; } for (i = 0; i < pci_mmcfg_config_num; ++i) { @@ -228,7 +228,8 @@ void __init pci_mmcfg_init(int type) pci_mmcfg_virt[i].virt = ioremap_nocache(pci_mmcfg_config[i].base_address, MMCONFIG_APER_MAX); if (!pci_mmcfg_virt[i].virt) { - printk("PCI: Cannot map mmconfig aperture for segment %d\n", + printk(KERN_ERR "PCI: Cannot map mmconfig aperture for " + "segment %d\n", pci_mmcfg_config[i].pci_segment_group_number); return; } diff --git a/arch/xtensa/kernel/vmlinux.lds.S b/arch/xtensa/kernel/vmlinux.lds.S index ab6cdbd5eb6..cfe75f52872 100644 --- a/arch/xtensa/kernel/vmlinux.lds.S +++ b/arch/xtensa/kernel/vmlinux.lds.S @@ -184,13 +184,7 @@ SECTIONS __initcall_start = .; .initcall.init : { - *(.initcall1.init) - *(.initcall2.init) - *(.initcall3.init) - *(.initcall4.init) - *(.initcall5.init) - *(.initcall6.init) - *(.initcall7.init) + INITCALLS } __initcall_end = .; 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/base/dd.c b/drivers/base/dd.c index db01b95a47a..c5d6bb4290a 100644 --- a/drivers/base/dd.c +++ b/drivers/base/dd.c @@ -18,6 +18,7 @@ #include <linux/device.h> #include <linux/module.h> #include <linux/kthread.h> +#include <linux/wait.h> #include "base.h" #include "power/power.h" @@ -70,6 +71,8 @@ struct stupid_thread_structure { }; static atomic_t probe_count = ATOMIC_INIT(0); +static DECLARE_WAIT_QUEUE_HEAD(probe_waitqueue); + static int really_probe(void *void_data) { struct stupid_thread_structure *data = void_data; @@ -121,6 +124,7 @@ probe_failed: done: kfree(data); atomic_dec(&probe_count); + wake_up(&probe_waitqueue); return ret; } @@ -337,6 +341,32 @@ void driver_detach(struct device_driver * drv) } } +#ifdef CONFIG_PCI_MULTITHREAD_PROBE +static int __init wait_for_probes(void) +{ + DEFINE_WAIT(wait); + + printk(KERN_INFO "%s: waiting for %d threads\n", __FUNCTION__, + atomic_read(&probe_count)); + if (!atomic_read(&probe_count)) + return 0; + while (atomic_read(&probe_count)) { + prepare_to_wait(&probe_waitqueue, &wait, TASK_UNINTERRUPTIBLE); + if (atomic_read(&probe_count)) + schedule(); + } + finish_wait(&probe_waitqueue, &wait); + return 0; +} + +core_initcall_sync(wait_for_probes); +postcore_initcall_sync(wait_for_probes); +arch_initcall_sync(wait_for_probes); +subsys_initcall_sync(wait_for_probes); +fs_initcall_sync(wait_for_probes); +device_initcall_sync(wait_for_probes); +late_initcall_sync(wait_for_probes); +#endif EXPORT_SYMBOL_GPL(device_bind_driver); EXPORT_SYMBOL_GPL(device_release_driver); 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/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/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/mtd/nand/nand_base.c b/drivers/mtd/nand/nand_base.c index baece61169f..41bfcae1fbf 100644 --- a/drivers/mtd/nand/nand_base.c +++ b/drivers/mtd/nand/nand_base.c @@ -1479,6 +1479,7 @@ static void nand_write_page_syndrome(struct mtd_info *mtd, * @buf: the data to write * @page: page number to write * @cached: cached programming + * @raw: use _raw version of write_page */ static int nand_write_page(struct mtd_info *mtd, struct nand_chip *chip, const uint8_t *buf, int page, int cached, int raw) diff --git a/drivers/pci/hotplug/acpiphp_glue.c b/drivers/pci/hotplug/acpiphp_glue.c index c44311ac2fd..16167b01626 100644 --- a/drivers/pci/hotplug/acpiphp_glue.c +++ b/drivers/pci/hotplug/acpiphp_glue.c @@ -1807,8 +1807,8 @@ u8 acpiphp_get_power_status(struct acpiphp_slot *slot) /* - * latch closed: 1 - * latch open: 0 + * latch open: 1 + * latch closed: 0 */ u8 acpiphp_get_latch_status(struct acpiphp_slot *slot) { @@ -1816,7 +1816,7 @@ u8 acpiphp_get_latch_status(struct acpiphp_slot *slot) sta = get_slot_status(slot); - return (sta & ACPI_STA_SHOW_IN_UI) ? 1 : 0; + return (sta & ACPI_STA_SHOW_IN_UI) ? 0 : 1; } diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c index b1c0c707d96..194f1d21d3d 100644 --- a/drivers/pci/pci-driver.c +++ b/drivers/pci/pci-driver.c @@ -265,6 +265,13 @@ static int pci_device_remove(struct device * dev) } /* + * If the device is still on, set the power state as "unknown", + * since it might change by the next time we load the driver. + */ + if (pci_dev->current_state == PCI_D0) + pci_dev->current_state = PCI_UNKNOWN; + + /* * We would love to complain here if pci_dev->is_enabled is set, that * the driver should have called pci_disable_device(), but the * unfortunate fact is there are too many odd BIOS and bridge setups @@ -288,6 +295,12 @@ static int pci_device_suspend(struct device * dev, pm_message_t state) suspend_report_result(drv->suspend, i); } else { pci_save_state(pci_dev); + /* + * mark its power state as "unknown", since we don't know if + * e.g. the BIOS will change its device state when we suspend. + */ + if (pci_dev->current_state == PCI_D0) + pci_dev->current_state = PCI_UNKNOWN; } return i; } diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index e8a7f1b1b2b..204b1c8e972 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -714,33 +714,6 @@ static void __devinit quirk_vt82c598_id(struct pci_dev *dev) } DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_VIA, PCI_DEVICE_ID_VIA_82C597_0, quirk_vt82c598_id ); -#ifdef CONFIG_ACPI_SLEEP - -/* - * Some VIA systems boot with the abnormal status flag set. This can cause - * the BIOS to re-POST the system on resume rather than passing control - * back to the OS. Clear the flag on boot - */ -static void __devinit quirk_via_abnormal_poweroff(struct pci_dev *dev) -{ - u32 reg; - - acpi_hw_register_read(ACPI_MTX_DO_NOT_LOCK, ACPI_REGISTER_PM1_STATUS, - ®); - - if (reg & 0x800) { - printk("Clearing abnormal poweroff flag\n"); - acpi_hw_register_write(ACPI_MTX_DO_NOT_LOCK, - ACPI_REGISTER_PM1_STATUS, - (u16)0x800); - } -} - -DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_VIA, PCI_DEVICE_ID_VIA_8235, quirk_via_abnormal_poweroff); -DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_VIA, PCI_DEVICE_ID_VIA_8237, quirk_via_abnormal_poweroff); - -#endif - /* * CardBus controllers have a legacy base address that enables them * to respond as i82365 pcmcia controllers. We don't want them to @@ -1619,52 +1592,6 @@ static void __devinit fixup_rev1_53c810(struct pci_dev* dev) } DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_NCR, PCI_DEVICE_ID_NCR_53C810, fixup_rev1_53c810); -/* - * Fixup to mark boot BIOS video selected by BIOS before it changes - * - * From information provided by "Jon Smirl" <jonsmirl@gmail.com> - * - * The standard boot ROM sequence for an x86 machine uses the BIOS - * to select an initial video card for boot display. This boot video - * card will have it's BIOS copied to C0000 in system RAM. - * IORESOURCE_ROM_SHADOW is used to associate the boot video - * card with this copy. On laptops this copy has to be used since - * the main ROM may be compressed or combined with another image. - * See pci_map_rom() for use of this flag. IORESOURCE_ROM_SHADOW - * is marked here since the boot video device will be the only enabled - * video device at this point. - */ - -static void __devinit fixup_video(struct pci_dev *pdev) -{ - struct pci_dev *bridge; - struct pci_bus *bus; - u16 config; - - if ((pdev->class >> 8) != PCI_CLASS_DISPLAY_VGA) - return; - - /* Is VGA routed to us? */ - bus = pdev->bus; - while (bus) { - bridge = bus->self; - if (bridge) { - pci_read_config_word(bridge, PCI_BRIDGE_CONTROL, - &config); - if (!(config & PCI_BRIDGE_CTL_VGA)) - return; - } - bus = bus->parent; - } - pci_read_config_word(pdev, PCI_COMMAND, &config); - if (config & (PCI_COMMAND_IO | PCI_COMMAND_MEMORY)) { - pdev->resource[PCI_ROM_RESOURCE].flags |= IORESOURCE_ROM_SHADOW; - printk(KERN_DEBUG "Boot video device is %s\n", pci_name(pdev)); - } -} -DECLARE_PCI_FIXUP_HEADER(PCI_ANY_ID, PCI_ANY_ID, fixup_video); - - static void pci_do_fixups(struct pci_dev *dev, struct pci_fixup *f, struct pci_fixup *end) { while (f < end) { diff --git a/drivers/pci/rom.c b/drivers/pci/rom.c index 43e4a49f2cc..e1dcefc69bb 100644 --- a/drivers/pci/rom.c +++ b/drivers/pci/rom.c @@ -72,8 +72,9 @@ void __iomem *pci_map_rom(struct pci_dev *pdev, size_t *size) int last_image; /* - * IORESOURCE_ROM_SHADOW set if the VGA enable bit of the Bridge Control - * register is set for embedded VGA. + * IORESOURCE_ROM_SHADOW set on x86, x86_64 and IA64 supports legacy + * memory map if the VGA enable bit of the Bridge Control register is + * set for embedded VGA. */ if (res->flags & IORESOURCE_ROM_SHADOW) { /* primary video rom always starts here */ diff --git a/drivers/sbus/sbus.c b/drivers/sbus/sbus.c index 935952ef88f..98fcbb3d556 100644 --- a/drivers/sbus/sbus.c +++ b/drivers/sbus/sbus.c @@ -61,11 +61,11 @@ static void __init fill_sbus_device(struct device_node *dp, struct sbus_dev *sde else sdev->ofdev.dev.parent = &sdev->bus->ofdev.dev; sdev->ofdev.dev.bus = &sbus_bus_type; - strcpy(sdev->ofdev.dev.bus_id, dp->path_component_name); + sprintf(sdev->ofdev.dev.bus_id, "sbus[%08x]", dp->node); if (of_device_register(&sdev->ofdev) != 0) printk(KERN_DEBUG "sbus: device registration error for %s!\n", - sdev->ofdev.dev.bus_id); + dp->path_component_name); } static void __init sbus_bus_ranges_init(struct device_node *dp, struct sbus_bus *sbus) 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-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index 9d0d11c180d..9d873163a7a 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -213,3 +213,20 @@ #define NOTES \ .notes : { *(.note.*) } :note + +#define INITCALLS \ + *(.initcall1.init) \ + *(.initcall1s.init) \ + *(.initcall2.init) \ + *(.initcall2s.init) \ + *(.initcall3.init) \ + *(.initcall3s.init) \ + *(.initcall4.init) \ + *(.initcall4s.init) \ + *(.initcall5.init) \ + *(.initcall5s.init) \ + *(.initcall6.init) \ + *(.initcall6s.init) \ + *(.initcall7.init) \ + *(.initcall7s.init) + 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/init.h b/include/linux/init.h index e92b1455d7a..ff40ea118e3 100644 --- a/include/linux/init.h +++ b/include/linux/init.h @@ -84,19 +84,29 @@ extern void setup_arch(char **); * by link order. * For backwards compatibility, initcall() puts the call in * the device init subsection. + * + * The `id' arg to __define_initcall() is needed so that multiple initcalls + * can point at the same handler without causing duplicate-symbol build errors. */ -#define __define_initcall(level,fn) \ - static initcall_t __initcall_##fn __attribute_used__ \ +#define __define_initcall(level,fn,id) \ + static initcall_t __initcall_##fn##id __attribute_used__ \ __attribute__((__section__(".initcall" level ".init"))) = fn -#define core_initcall(fn) __define_initcall("1",fn) -#define postcore_initcall(fn) __define_initcall("2",fn) -#define arch_initcall(fn) __define_initcall("3",fn) -#define subsys_initcall(fn) __define_initcall("4",fn) -#define fs_initcall(fn) __define_initcall("5",fn) -#define device_initcall(fn) __define_initcall("6",fn) -#define late_initcall(fn) __define_initcall("7",fn) +#define core_initcall(fn) __define_initcall("1",fn,1) +#define core_initcall_sync(fn) __define_initcall("1s",fn,1s) +#define postcore_initcall(fn) __define_initcall("2",fn,2) +#define postcore_initcall_sync(fn) __define_initcall("2s",fn,2s) +#define arch_initcall(fn) __define_initcall("3",fn,3) +#define arch_initcall_sync(fn) __define_initcall("3s",fn,3s) +#define subsys_initcall(fn) __define_initcall("4",fn,4) +#define subsys_initcall_sync(fn) __define_initcall("4s",fn,4s) +#define fs_initcall(fn) __define_initcall("5",fn,5) +#define fs_initcall_sync(fn) __define_initcall("5s",fn,5s) +#define device_initcall(fn) __define_initcall("6",fn,6) +#define device_initcall_sync(fn) __define_initcall("6s",fn,6s) +#define late_initcall(fn) __define_initcall("7",fn,7) +#define late_initcall_sync(fn) __define_initcall("7s",fn,7s) #define __initcall(fn) device_initcall(fn) 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..8adfb8069c6 100644 --- a/kernel/taskstats.c +++ b/kernel/taskstats.c @@ -174,21 +174,19 @@ 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 +212,30 @@ 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 +246,18 @@ 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 +265,7 @@ 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 +277,7 @@ 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; } @@ -461,15 +453,10 @@ 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 +464,7 @@ 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 */ 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..6d381df7c9b 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, 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'); |