diff options
75 files changed, 971 insertions, 1705 deletions
diff --git a/Documentation/feature-removal-schedule.txt b/Documentation/feature-removal-schedule.txt index 274b32d1253..492e81df296 100644 --- a/Documentation/feature-removal-schedule.txt +++ b/Documentation/feature-removal-schedule.txt @@ -387,26 +387,6 @@ Who: Tejun Heo <tj@kernel.org> ---------------------------- -What: Support for lcd_switch and display_get in asus-laptop driver -When: March 2010 -Why: These two features use non-standard interfaces. There are the - only features that really need multiple path to guess what's - the right method name on a specific laptop. - - Removing them will allow to remove a lot of code an significantly - clean the drivers. - - This will affect the backlight code which won't be able to know - if the backlight is on or off. The platform display file will also be - write only (like the one in eeepc-laptop). - - This should'nt affect a lot of user because they usually know - when their display is on or off. - -Who: Corentin Chary <corentin.chary@gmail.com> - ----------------------------- - What: sysfs-class-rfkill state file When: Feb 2014 Files: net/rfkill/core.c @@ -1,7 +1,7 @@ VERSION = 2 PATCHLEVEL = 6 SUBLEVEL = 39 -EXTRAVERSION = -rc2 +EXTRAVERSION = -rc3 NAME = Flesh-Eating Bats with Fangs # *DOCUMENTATION* diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 49dbd78ec3c..e3c6a06cf72 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -238,6 +238,7 @@ static void xen_cpuid(unsigned int *ax, unsigned int *bx, static __init void xen_init_cpuid_mask(void) { unsigned int ax, bx, cx, dx; + unsigned int xsave_mask; cpuid_leaf1_edx_mask = ~((1 << X86_FEATURE_MCE) | /* disable MCE */ @@ -249,24 +250,16 @@ static __init void xen_init_cpuid_mask(void) cpuid_leaf1_edx_mask &= ~((1 << X86_FEATURE_APIC) | /* disable local APIC */ (1 << X86_FEATURE_ACPI)); /* disable ACPI */ - ax = 1; - cx = 0; xen_cpuid(&ax, &bx, &cx, &dx); - /* cpuid claims we support xsave; try enabling it to see what happens */ - if (cx & (1 << (X86_FEATURE_XSAVE % 32))) { - unsigned long cr4; - - set_in_cr4(X86_CR4_OSXSAVE); - - cr4 = read_cr4(); + xsave_mask = + (1 << (X86_FEATURE_XSAVE % 32)) | + (1 << (X86_FEATURE_OSXSAVE % 32)); - if ((cr4 & X86_CR4_OSXSAVE) == 0) - cpuid_leaf1_ecx_mask &= ~(1 << (X86_FEATURE_XSAVE % 32)); - - clear_in_cr4(X86_CR4_OSXSAVE); - } + /* Xen will set CR4.OSXSAVE if supported and not disabled by force */ + if ((cx & xsave_mask) != xsave_mask) + cpuid_leaf1_ecx_mask &= ~xsave_mask; /* disable XSAVE & OSXSAVE */ } static void xen_set_debugreg(int reg, unsigned long val) diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index c82df6c9c0f..a991b57f91f 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -565,13 +565,13 @@ pte_t xen_make_pte_debug(pteval_t pte) if (io_page && (xen_initial_domain() || addr >= ISA_END_ADDRESS)) { other_addr = pfn_to_mfn(addr >> PAGE_SHIFT) << PAGE_SHIFT; - WARN(addr != other_addr, + WARN_ONCE(addr != other_addr, "0x%lx is using VM_IO, but it is 0x%lx!\n", (unsigned long)addr, (unsigned long)other_addr); } else { pteval_t iomap_set = (_pte.pte & PTE_FLAGS_MASK) & _PAGE_IOMAP; other_addr = (_pte.pte & PTE_PFN_MASK); - WARN((addr == other_addr) && (!io_page) && (!iomap_set), + WARN_ONCE((addr == other_addr) && (!io_page) && (!iomap_set), "0x%lx is missing VM_IO (and wasn't fixed)!\n", (unsigned long)addr); } diff --git a/drivers/base/platform.c b/drivers/base/platform.c index 92792313d24..9e0e4fc24c4 100644 --- a/drivers/base/platform.c +++ b/drivers/base/platform.c @@ -149,6 +149,7 @@ static void platform_device_release(struct device *dev) of_device_node_put(&pa->pdev.dev); kfree(pa->pdev.dev.platform_data); + kfree(pa->pdev.mfd_cell); kfree(pa->pdev.resource); kfree(pa); } diff --git a/drivers/dma/fsldma.c b/drivers/dma/fsldma.c index 6b396759e7f..8a781540590 100644 --- a/drivers/dma/fsldma.c +++ b/drivers/dma/fsldma.c @@ -1448,7 +1448,7 @@ static const struct of_device_id fsldma_of_ids[] = { {} }; -static struct of_platform_driver fsldma_of_driver = { +static struct platform_driver fsldma_of_driver = { .driver = { .name = "fsl-elo-dma", .owner = THIS_MODULE, diff --git a/drivers/gpio/ml_ioh_gpio.c b/drivers/gpio/ml_ioh_gpio.c index 7f6f01a4b14..0a775f7987c 100644 --- a/drivers/gpio/ml_ioh_gpio.c +++ b/drivers/gpio/ml_ioh_gpio.c @@ -116,6 +116,7 @@ static int ioh_gpio_direction_output(struct gpio_chip *gpio, unsigned nr, reg_val |= (1 << nr); else reg_val &= ~(1 << nr); + iowrite32(reg_val, &chip->reg->regs[chip->ch].po); mutex_unlock(&chip->lock); diff --git a/drivers/gpio/pca953x.c b/drivers/gpio/pca953x.c index 583e9259207..7630ab7b9be 100644 --- a/drivers/gpio/pca953x.c +++ b/drivers/gpio/pca953x.c @@ -558,7 +558,7 @@ static int __devinit pca953x_probe(struct i2c_client *client, ret = gpiochip_add(&chip->gpio_chip); if (ret) - goto out_failed; + goto out_failed_irq; if (pdata->setup) { ret = pdata->setup(client, chip->gpio_chip.base, @@ -570,8 +570,9 @@ static int __devinit pca953x_probe(struct i2c_client *client, i2c_set_clientdata(client, chip); return 0; -out_failed: +out_failed_irq: pca953x_irq_teardown(chip); +out_failed: kfree(chip->dyn_pdata); kfree(chip); return ret; diff --git a/drivers/gpio/pch_gpio.c b/drivers/gpio/pch_gpio.c index 2c6af870510..f970a5f3585 100644 --- a/drivers/gpio/pch_gpio.c +++ b/drivers/gpio/pch_gpio.c @@ -105,6 +105,7 @@ static int pch_gpio_direction_output(struct gpio_chip *gpio, unsigned nr, reg_val |= (1 << nr); else reg_val &= ~(1 << nr); + iowrite32(reg_val, &chip->reg->po); mutex_unlock(&chip->lock); diff --git a/drivers/mfd/mfd-core.c b/drivers/mfd/mfd-core.c index d01574d9887..f4c8c844b91 100644 --- a/drivers/mfd/mfd-core.c +++ b/drivers/mfd/mfd-core.c @@ -55,6 +55,19 @@ int mfd_cell_disable(struct platform_device *pdev) } EXPORT_SYMBOL(mfd_cell_disable); +static int mfd_platform_add_cell(struct platform_device *pdev, + const struct mfd_cell *cell) +{ + if (!cell) + return 0; + + pdev->mfd_cell = kmemdup(cell, sizeof(*cell), GFP_KERNEL); + if (!pdev->mfd_cell) + return -ENOMEM; + + return 0; +} + static int mfd_add_device(struct device *parent, int id, const struct mfd_cell *cell, struct resource *mem_base, @@ -75,7 +88,7 @@ static int mfd_add_device(struct device *parent, int id, pdev->dev.parent = parent; - ret = platform_device_add_data(pdev, cell, sizeof(*cell)); + ret = mfd_platform_add_cell(pdev, cell); if (ret) goto fail_res; @@ -123,7 +136,6 @@ static int mfd_add_device(struct device *parent, int id, return 0; -/* platform_device_del(pdev); */ fail_res: kfree(res); fail_device: diff --git a/drivers/platform/x86/Kconfig b/drivers/platform/x86/Kconfig index 2ee442c2a5d..0485e394712 100644 --- a/drivers/platform/x86/Kconfig +++ b/drivers/platform/x86/Kconfig @@ -187,7 +187,8 @@ config MSI_LAPTOP depends on ACPI depends on BACKLIGHT_CLASS_DEVICE depends on RFKILL - depends on SERIO_I8042 + depends on INPUT && SERIO_I8042 + select INPUT_SPARSEKMAP ---help--- This is a driver for laptops built by MSI (MICRO-STAR INTERNATIONAL): diff --git a/drivers/platform/x86/acer-wmi.c b/drivers/platform/x86/acer-wmi.c index 5ea6c3477d1..ac4e7f83ce6 100644 --- a/drivers/platform/x86/acer-wmi.c +++ b/drivers/platform/x86/acer-wmi.c @@ -89,7 +89,7 @@ MODULE_LICENSE("GPL"); #define ACERWMID_EVENT_GUID "676AA15E-6A47-4D9F-A2CC-1E6D18D14026" MODULE_ALIAS("wmi:67C3371D-95A3-4C37-BB61-DD47B491DAAB"); -MODULE_ALIAS("wmi:6AF4F258-B401-42Fd-BE91-3D4AC2D7C0D3"); +MODULE_ALIAS("wmi:6AF4F258-B401-42FD-BE91-3D4AC2D7C0D3"); MODULE_ALIAS("wmi:676AA15E-6A47-4D9F-A2CC-1E6D18D14026"); enum acer_wmi_event_ids { diff --git a/drivers/platform/x86/asus-wmi.c b/drivers/platform/x86/asus-wmi.c index efc776cb0c6..832a3fd7c1c 100644 --- a/drivers/platform/x86/asus-wmi.c +++ b/drivers/platform/x86/asus-wmi.c @@ -201,8 +201,8 @@ static int asus_wmi_input_init(struct asus_wmi *asus) if (!asus->inputdev) return -ENOMEM; - asus->inputdev->name = asus->driver->input_phys; - asus->inputdev->phys = asus->driver->input_name; + asus->inputdev->name = asus->driver->input_name; + asus->inputdev->phys = asus->driver->input_phys; asus->inputdev->id.bustype = BUS_HOST; asus->inputdev->dev.parent = &asus->platform_device->dev; diff --git a/drivers/platform/x86/eeepc-wmi.c b/drivers/platform/x86/eeepc-wmi.c index 0ddc434fb93..649dcadd8ea 100644 --- a/drivers/platform/x86/eeepc-wmi.c +++ b/drivers/platform/x86/eeepc-wmi.c @@ -67,9 +67,11 @@ static const struct key_entry eeepc_wmi_keymap[] = { { KE_KEY, 0x82, { KEY_CAMERA } }, { KE_KEY, 0x83, { KEY_CAMERA_ZOOMIN } }, { KE_KEY, 0x88, { KEY_WLAN } }, + { KE_KEY, 0xbd, { KEY_CAMERA } }, { KE_KEY, 0xcc, { KEY_SWITCHVIDEOMODE } }, { KE_KEY, 0xe0, { KEY_PROG1 } }, /* Task Manager */ { KE_KEY, 0xe1, { KEY_F14 } }, /* Change Resolution */ + { KE_KEY, 0xe8, { KEY_SCREENLOCK } }, { KE_KEY, 0xe9, { KEY_BRIGHTNESS_ZERO } }, { KE_KEY, 0xeb, { KEY_CAMERA_ZOOMOUT } }, { KE_KEY, 0xec, { KEY_CAMERA_UP } }, diff --git a/drivers/platform/x86/intel_pmic_gpio.c b/drivers/platform/x86/intel_pmic_gpio.c index d653104b59c..7bbb5388e56 100644 --- a/drivers/platform/x86/intel_pmic_gpio.c +++ b/drivers/platform/x86/intel_pmic_gpio.c @@ -74,6 +74,19 @@ struct pmic_gpio { u32 trigger_type; }; +static void pmic_program_irqtype(int gpio, int type) +{ + if (type & IRQ_TYPE_EDGE_RISING) + intel_scu_ipc_update_register(GPIO0 + gpio, 0x20, 0x20); + else + intel_scu_ipc_update_register(GPIO0 + gpio, 0x00, 0x20); + + if (type & IRQ_TYPE_EDGE_FALLING) + intel_scu_ipc_update_register(GPIO0 + gpio, 0x10, 0x10); + else + intel_scu_ipc_update_register(GPIO0 + gpio, 0x00, 0x10); +}; + static int pmic_gpio_direction_input(struct gpio_chip *chip, unsigned offset) { if (offset > 8) { @@ -166,16 +179,38 @@ static int pmic_gpio_to_irq(struct gpio_chip *chip, unsigned offset) return pg->irq_base + offset; } +static void pmic_bus_lock(struct irq_data *data) +{ + struct pmic_gpio *pg = irq_data_get_irq_chip_data(data); + + mutex_lock(&pg->buslock); +} + +static void pmic_bus_sync_unlock(struct irq_data *data) +{ + struct pmic_gpio *pg = irq_data_get_irq_chip_data(data); + + if (pg->update_type) { + unsigned int gpio = pg->update_type & ~GPIO_UPDATE_TYPE; + + pmic_program_irqtype(gpio, pg->trigger_type); + pg->update_type = 0; + } + mutex_unlock(&pg->buslock); +} + /* the gpiointr register is read-clear, so just do nothing. */ static void pmic_irq_unmask(struct irq_data *data) { } static void pmic_irq_mask(struct irq_data *data) { } static struct irq_chip pmic_irqchip = { - .name = "PMIC-GPIO", - .irq_mask = pmic_irq_mask, - .irq_unmask = pmic_irq_unmask, - .irq_set_type = pmic_irq_type, + .name = "PMIC-GPIO", + .irq_mask = pmic_irq_mask, + .irq_unmask = pmic_irq_unmask, + .irq_set_type = pmic_irq_type, + .irq_bus_lock = pmic_irq_buslock, + .irq_bus_sync_unlock = pmic_bus_sync_unlock, }; static irqreturn_t pmic_irq_handler(int irq, void *data) diff --git a/drivers/platform/x86/samsung-laptop.c b/drivers/platform/x86/samsung-laptop.c index de434c6dc2d..d347116d150 100644 --- a/drivers/platform/x86/samsung-laptop.c +++ b/drivers/platform/x86/samsung-laptop.c @@ -571,6 +571,16 @@ static struct dmi_system_id __initdata samsung_dmi_table[] = { .callback = dmi_check_cb, }, { + .ident = "R410 Plus", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, + "SAMSUNG ELECTRONICS CO., LTD."), + DMI_MATCH(DMI_PRODUCT_NAME, "R410P"), + DMI_MATCH(DMI_BOARD_NAME, "R460"), + }, + .callback = dmi_check_cb, + }, + { .ident = "R518", .matches = { DMI_MATCH(DMI_SYS_VENDOR, @@ -591,12 +601,12 @@ static struct dmi_system_id __initdata samsung_dmi_table[] = { .callback = dmi_check_cb, }, { - .ident = "N150/N210/N220", + .ident = "N150/N210/N220/N230", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "SAMSUNG ELECTRONICS CO., LTD."), - DMI_MATCH(DMI_PRODUCT_NAME, "N150/N210/N220"), - DMI_MATCH(DMI_BOARD_NAME, "N150/N210/N220"), + DMI_MATCH(DMI_PRODUCT_NAME, "N150/N210/N220/N230"), + DMI_MATCH(DMI_BOARD_NAME, "N150/N210/N220/N230"), }, .callback = dmi_check_cb, }, @@ -771,6 +781,7 @@ static int __init samsung_init(void) /* create a backlight device to talk to this one */ memset(&props, 0, sizeof(struct backlight_properties)); + props.type = BACKLIGHT_PLATFORM; props.max_brightness = sabi_config->max_brightness; backlight_device = backlight_device_register("samsung", &sdev->dev, NULL, &backlight_ops, diff --git a/drivers/platform/x86/sony-laptop.c b/drivers/platform/x86/sony-laptop.c index e642f5f2950..8f709aec4da 100644 --- a/drivers/platform/x86/sony-laptop.c +++ b/drivers/platform/x86/sony-laptop.c @@ -138,6 +138,8 @@ MODULE_PARM_DESC(kbd_backlight_timeout, "1 for 30 seconds, 2 for 60 seconds and 3 to disable timeout " "(default: 0)"); +static void sony_nc_kbd_backlight_resume(void); + enum sony_nc_rfkill { SONY_WIFI, SONY_BLUETOOTH, @@ -771,11 +773,6 @@ static int sony_nc_handles_setup(struct platform_device *pd) if (!handles) return -ENOMEM; - sysfs_attr_init(&handles->devattr.attr); - handles->devattr.attr.name = "handles"; - handles->devattr.attr.mode = S_IRUGO; - handles->devattr.show = sony_nc_handles_show; - for (i = 0; i < ARRAY_SIZE(handles->cap); i++) { if (!acpi_callsetfunc(sony_nc_acpi_handle, "SN00", i + 0x20, &result)) { @@ -785,11 +782,18 @@ static int sony_nc_handles_setup(struct platform_device *pd) } } - /* allow reading capabilities via sysfs */ - if (device_create_file(&pd->dev, &handles->devattr)) { - kfree(handles); - handles = NULL; - return -1; + if (debug) { + sysfs_attr_init(&handles->devattr.attr); + handles->devattr.attr.name = "handles"; + handles->devattr.attr.mode = S_IRUGO; + handles->devattr.show = sony_nc_handles_show; + + /* allow reading capabilities via sysfs */ + if (device_create_file(&pd->dev, &handles->devattr)) { + kfree(handles); + handles = NULL; + return -1; + } } return 0; @@ -798,7 +802,8 @@ static int sony_nc_handles_setup(struct platform_device *pd) static int sony_nc_handles_cleanup(struct platform_device *pd) { if (handles) { - device_remove_file(&pd->dev, &handles->devattr); + if (debug) + device_remove_file(&pd->dev, &handles->devattr); kfree(handles); handles = NULL; } @@ -808,6 +813,11 @@ static int sony_nc_handles_cleanup(struct platform_device *pd) static int sony_find_snc_handle(int handle) { int i; + + /* not initialized yet, return early */ + if (!handles) + return -1; + for (i = 0; i < 0x10; i++) { if (handles->cap[i] == handle) { dprintk("found handle 0x%.4x (offset: 0x%.2x)\n", @@ -1168,6 +1178,9 @@ static int sony_nc_resume(struct acpi_device *device) /* re-read rfkill state */ sony_nc_rfkill_update(); + /* restore kbd backlight states */ + sony_nc_kbd_backlight_resume(); + return 0; } @@ -1355,6 +1368,7 @@ out_no_enum: #define KBDBL_HANDLER 0x137 #define KBDBL_PRESENT 0xB00 #define SET_MODE 0xC00 +#define SET_STATE 0xD00 #define SET_TIMEOUT 0xE00 struct kbd_backlight { @@ -1377,6 +1391,10 @@ static ssize_t __sony_nc_kbd_backlight_mode_set(u8 value) (value << 0x10) | SET_MODE, &result)) return -EIO; + /* Try to turn the light on/off immediately */ + sony_call_snc_handle(KBDBL_HANDLER, (value << 0x10) | SET_STATE, + &result); + kbdbl_handle->mode = value; return 0; @@ -1458,7 +1476,7 @@ static int sony_nc_kbd_backlight_setup(struct platform_device *pd) { int result; - if (sony_call_snc_handle(0x137, KBDBL_PRESENT, &result)) + if (sony_call_snc_handle(KBDBL_HANDLER, KBDBL_PRESENT, &result)) return 0; if (!(result & 0x02)) return 0; @@ -1501,13 +1519,36 @@ outkzalloc: static int sony_nc_kbd_backlight_cleanup(struct platform_device *pd) { if (kbdbl_handle) { + int result; + device_remove_file(&pd->dev, &kbdbl_handle->mode_attr); device_remove_file(&pd->dev, &kbdbl_handle->timeout_attr); + + /* restore the default hw behaviour */ + sony_call_snc_handle(KBDBL_HANDLER, 0x1000 | SET_MODE, &result); + sony_call_snc_handle(KBDBL_HANDLER, SET_TIMEOUT, &result); + kfree(kbdbl_handle); } return 0; } +static void sony_nc_kbd_backlight_resume(void) +{ + int ignore = 0; + + if (!kbdbl_handle) + return; + + if (kbdbl_handle->mode == 0) + sony_call_snc_handle(KBDBL_HANDLER, SET_MODE, &ignore); + + if (kbdbl_handle->timeout != 0) + sony_call_snc_handle(KBDBL_HANDLER, + (kbdbl_handle->timeout << 0x10) | SET_TIMEOUT, + &ignore); +} + static void sony_nc_backlight_setup(void) { acpi_handle unused; diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c index a08561f5349..efb3b6b9bcd 100644 --- a/drivers/platform/x86/thinkpad_acpi.c +++ b/drivers/platform/x86/thinkpad_acpi.c @@ -8618,8 +8618,7 @@ static bool __pure __init tpacpi_is_valid_fw_id(const char* const s, tpacpi_is_fw_digit(s[1]) && s[2] == t && s[3] == 'T' && tpacpi_is_fw_digit(s[4]) && - tpacpi_is_fw_digit(s[5]) && - s[6] == 'W' && s[7] == 'W'; + tpacpi_is_fw_digit(s[5]); } /* returns 0 - probe ok, or < 0 - probe error. diff --git a/drivers/spi/amba-pl022.c b/drivers/spi/amba-pl022.c index 5825370bad2..08de58e7f59 100644 --- a/drivers/spi/amba-pl022.c +++ b/drivers/spi/amba-pl022.c @@ -1555,7 +1555,7 @@ static int stop_queue(struct pl022 *pl022) * A wait_queue on the pl022->busy could be used, but then the common * execution path (pump_messages) would be required to call wake_up or * friends on every SPI message. Do this instead */ - while (!list_empty(&pl022->queue) && pl022->busy && limit--) { + while ((!list_empty(&pl022->queue) || pl022->busy) && limit--) { spin_unlock_irqrestore(&pl022->queue_lock, flags); msleep(10); spin_lock_irqsave(&pl022->queue_lock, flags); diff --git a/drivers/spi/dw_spi.c b/drivers/spi/dw_spi.c index b1a4b9f503a..871e337c917 100644 --- a/drivers/spi/dw_spi.c +++ b/drivers/spi/dw_spi.c @@ -821,7 +821,7 @@ static int stop_queue(struct dw_spi *dws) spin_lock_irqsave(&dws->lock, flags); dws->run = QUEUE_STOPPED; - while (!list_empty(&dws->queue) && dws->busy && limit--) { + while ((!list_empty(&dws->queue) || dws->busy) && limit--) { spin_unlock_irqrestore(&dws->lock, flags); msleep(10); spin_lock_irqsave(&dws->lock, flags); diff --git a/drivers/spi/pxa2xx_spi.c b/drivers/spi/pxa2xx_spi.c index 9c74aad6be9..dc25bee8d33 100644 --- a/drivers/spi/pxa2xx_spi.c +++ b/drivers/spi/pxa2xx_spi.c @@ -1493,7 +1493,7 @@ static int stop_queue(struct driver_data *drv_data) * execution path (pump_messages) would be required to call wake_up or * friends on every SPI message. Do this instead */ drv_data->run = QUEUE_STOPPED; - while (!list_empty(&drv_data->queue) && drv_data->busy && limit--) { + while ((!list_empty(&drv_data->queue) || drv_data->busy) && limit--) { spin_unlock_irqrestore(&drv_data->lock, flags); msleep(10); spin_lock_irqsave(&drv_data->lock, flags); diff --git a/drivers/spi/spi_bfin5xx.c b/drivers/spi/spi_bfin5xx.c index bdb7289a1d2..f706dba165c 100644 --- a/drivers/spi/spi_bfin5xx.c +++ b/drivers/spi/spi_bfin5xx.c @@ -1284,7 +1284,7 @@ static inline int bfin_spi_stop_queue(struct bfin_spi_master_data *drv_data) * friends on every SPI message. Do this instead */ drv_data->running = false; - while (!list_empty(&drv_data->queue) && drv_data->busy && limit--) { + while ((!list_empty(&drv_data->queue) || drv_data->busy) && limit--) { spin_unlock_irqrestore(&drv_data->lock, flags); msleep(10); spin_lock_irqsave(&drv_data->lock, flags); diff --git a/drivers/staging/Kconfig b/drivers/staging/Kconfig index dca4a0bb6ca..e3786f161bc 100644 --- a/drivers/staging/Kconfig +++ b/drivers/staging/Kconfig @@ -131,8 +131,6 @@ source "drivers/staging/wlags49_h2/Kconfig" source "drivers/staging/wlags49_h25/Kconfig" -source "drivers/staging/samsung-laptop/Kconfig" - source "drivers/staging/sm7xx/Kconfig" source "drivers/staging/dt3155v4l/Kconfig" diff --git a/drivers/staging/Makefile b/drivers/staging/Makefile index eb93012b6f5..f0d5c531561 100644 --- a/drivers/staging/Makefile +++ b/drivers/staging/Makefile @@ -48,7 +48,6 @@ obj-$(CONFIG_XVMALLOC) += zram/ obj-$(CONFIG_ZCACHE) += zcache/ obj-$(CONFIG_WLAGS49_H2) += wlags49_h2/ obj-$(CONFIG_WLAGS49_H25) += wlags49_h25/ -obj-$(CONFIG_SAMSUNG_LAPTOP) += samsung-laptop/ obj-$(CONFIG_FB_SM7XX) += sm7xx/ obj-$(CONFIG_VIDEO_DT3155) += dt3155v4l/ obj-$(CONFIG_CRYSTALHD) += crystalhd/ diff --git a/drivers/staging/samsung-laptop/Kconfig b/drivers/staging/samsung-laptop/Kconfig deleted file mode 100644 index f27c60864c2..00000000000 --- a/drivers/staging/samsung-laptop/Kconfig +++ /dev/null @@ -1,10 +0,0 @@ -config SAMSUNG_LAPTOP - tristate "Samsung Laptop driver" - default n - depends on RFKILL && BACKLIGHT_CLASS_DEVICE && X86 - help - This module implements a driver for the N128 Samsung Laptop - providing control over the Wireless LED and the LCD backlight - - To compile this driver as a module, choose - M here: the module will be called samsung-laptop. diff --git a/drivers/staging/samsung-laptop/Makefile b/drivers/staging/samsung-laptop/Makefile deleted file mode 100644 index 3c6f4204521..00000000000 --- a/drivers/staging/samsung-laptop/Makefile +++ /dev/null @@ -1 +0,0 @@ -obj-$(CONFIG_SAMSUNG_LAPTOP) += samsung-laptop.o diff --git a/drivers/staging/samsung-laptop/TODO b/drivers/staging/samsung-laptop/TODO deleted file mode 100644 index f7a6d589916..00000000000 --- a/drivers/staging/samsung-laptop/TODO +++ /dev/null @@ -1,5 +0,0 @@ -TODO: - - review from other developers - - figure out ACPI video issues - -Please send patches to Greg Kroah-Hartman <gregkh@suse.de> diff --git a/drivers/staging/samsung-laptop/samsung-laptop.c b/drivers/staging/samsung-laptop/samsung-laptop.c deleted file mode 100644 index 25294462b8b..00000000000 --- a/drivers/staging/samsung-laptop/samsung-laptop.c +++ /dev/null @@ -1,843 +0,0 @@ -/* - * Samsung Laptop driver - * - * Copyright (C) 2009,2011 Greg Kroah-Hartman (gregkh@suse.de) - * Copyright (C) 2009,2011 Novell Inc. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License version 2 as published by - * the Free Software Foundation. - * - */ -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt - -#include <linux/kernel.h> -#include <linux/init.h> -#include <linux/module.h> -#include <linux/delay.h> -#include <linux/pci.h> -#include <linux/backlight.h> -#include <linux/fb.h> -#include <linux/dmi.h> -#include <linux/platform_device.h> -#include <linux/rfkill.h> - -/* - * This driver is needed because a number of Samsung laptops do not hook - * their control settings through ACPI. So we have to poke around in the - * BIOS to do things like brightness values, and "special" key controls. - */ - -/* - * We have 0 - 8 as valid brightness levels. The specs say that level 0 should - * be reserved by the BIOS (which really doesn't make much sense), we tell - * userspace that the value is 0 - 7 and then just tell the hardware 1 - 8 - */ -#define MAX_BRIGHT 0x07 - - -#define SABI_IFACE_MAIN 0x00 -#define SABI_IFACE_SUB 0x02 -#define SABI_IFACE_COMPLETE 0x04 -#define SABI_IFACE_DATA 0x05 - -/* Structure to get data back to the calling function */ -struct sabi_retval { - u8 retval[20]; -}; - -struct sabi_header_offsets { - u8 port; - u8 re_mem; - u8 iface_func; - u8 en_mem; - u8 data_offset; - u8 data_segment; -}; - -struct sabi_commands { - /* - * Brightness is 0 - 8, as described above. - * Value 0 is for the BIOS to use - */ - u8 get_brightness; - u8 set_brightness; - - /* - * first byte: - * 0x00 - wireless is off - * 0x01 - wireless is on - * second byte: - * 0x02 - 3G is off - * 0x03 - 3G is on - * TODO, verify 3G is correct, that doesn't seem right... - */ - u8 get_wireless_button; - u8 set_wireless_button; - - /* 0 is off, 1 is on */ - u8 get_backlight; - u8 set_backlight; - - /* - * 0x80 or 0x00 - no action - * 0x81 - recovery key pressed - */ - u8 get_recovery_mode; - u8 set_recovery_mode; - - /* - * on seclinux: 0 is low, 1 is high, - * on swsmi: 0 is normal, 1 is silent, 2 is turbo - */ - u8 get_performance_level; - u8 set_performance_level; - - /* - * Tell the BIOS that Linux is running on this machine. - * 81 is on, 80 is off - */ - u8 set_linux; -}; - -struct sabi_performance_level { - const char *name; - u8 value; -}; - -struct sabi_config { - const char *test_string; - u16 main_function; - const struct sabi_header_offsets header_offsets; - const struct sabi_commands commands; - const struct sabi_performance_level performance_levels[4]; - u8 min_brightness; - u8 max_brightness; -}; - -static const struct sabi_config sabi_configs[] = { - { - .test_string = "SECLINUX", - - .main_function = 0x4c49, - - .header_offsets = { - .port = 0x00, - .re_mem = 0x02, - .iface_func = 0x03, - .en_mem = 0x04, - .data_offset = 0x05, - .data_segment = 0x07, - }, - - .commands = { - .get_brightness = 0x00, - .set_brightness = 0x01, - - .get_wireless_button = 0x02, - .set_wireless_button = 0x03, - - .get_backlight = 0x04, - .set_backlight = 0x05, - - .get_recovery_mode = 0x06, - .set_recovery_mode = 0x07, - - .get_performance_level = 0x08, - .set_performance_level = 0x09, - - .set_linux = 0x0a, - }, - - .performance_levels = { - { - .name = "silent", - .value = 0, - }, - { - .name = "normal", - .value = 1, - }, - { }, - }, - .min_brightness = 1, - .max_brightness = 8, - }, - { - .test_string = "SwSmi@", - - .main_function = 0x5843, - - .header_offsets = { - .port = 0x00, - .re_mem = 0x04, - .iface_func = 0x02, - .en_mem = 0x03, - .data_offset = 0x05, - .data_segment = 0x07, - }, - - .commands = { - .get_brightness = 0x10, - .set_brightness = 0x11, - - .get_wireless_button = 0x12, - .set_wireless_button = 0x13, - - .get_backlight = 0x2d, - .set_backlight = 0x2e, - - .get_recovery_mode = 0xff, - .set_recovery_mode = 0xff, - - .get_performance_level = 0x31, - .set_performance_level = 0x32, - - .set_linux = 0xff, - }, - - .performance_levels = { - { - .name = "normal", - .value = 0, - }, - { - .name = "silent", - .value = 1, - }, - { - .name = "overclock", - .value = 2, - }, - { }, - }, - .min_brightness = 0, - .max_brightness = 8, - }, - { }, -}; - -static const struct sabi_config *sabi_config; - -static void __iomem *sabi; -static void __iomem *sabi_iface; -static void __iomem *f0000_segment; -static struct backlight_device *backlight_device; -static struct mutex sabi_mutex; -static struct platform_device *sdev; -static struct rfkill *rfk; - -static int force; -module_param(force, bool, 0); -MODULE_PARM_DESC(force, - "Disable the DMI check and forces the driver to be loaded"); - -static int debug; -module_param(debug, bool, S_IRUGO | S_IWUSR); -MODULE_PARM_DESC(debug, "Debug enabled or not"); - -static int sabi_get_command(u8 command, struct sabi_retval *sretval) -{ - int retval = 0; - u16 port = readw(sabi + sabi_config->header_offsets.port); - u8 complete, iface_data; - - mutex_lock(&sabi_mutex); - - /* enable memory to be able to write to it */ - outb(readb(sabi + sabi_config->header_offsets.en_mem), port); - - /* write out the command */ - writew(sabi_config->main_function, sabi_iface + SABI_IFACE_MAIN); - writew(command, sabi_iface + SABI_IFACE_SUB); - writeb(0, sabi_iface + SABI_IFACE_COMPLETE); - outb(readb(sabi + sabi_config->header_offsets.iface_func), port); - - /* write protect memory to make it safe */ - outb(readb(sabi + sabi_config->header_offsets.re_mem), port); - - /* see if the command actually succeeded */ - complete = readb(sabi_iface + SABI_IFACE_COMPLETE); - iface_data = readb(sabi_iface + SABI_IFACE_DATA); - if (complete != 0xaa || iface_data == 0xff) { - pr_warn("SABI get command 0x%02x failed with completion flag 0x%02x and data 0x%02x\n", - command, complete, iface_data); - retval = -EINVAL; - goto exit; - } - /* - * Save off the data into a structure so the caller use it. - * Right now we only want the first 4 bytes, - * There are commands that need more, but not for the ones we - * currently care about. - */ - sretval->retval[0] = readb(sabi_iface + SABI_IFACE_DATA); - sretval->retval[1] = readb(sabi_iface + SABI_IFACE_DATA + 1); - sretval->retval[2] = readb(sabi_iface + SABI_IFACE_DATA + 2); - sretval->retval[3] = readb(sabi_iface + SABI_IFACE_DATA + 3); - -exit: - mutex_unlock(&sabi_mutex); - return retval; - -} - -static int sabi_set_command(u8 command, u8 data) -{ - int retval = 0; - u16 port = readw(sabi + sabi_config->header_offsets.port); - u8 complete, iface_data; - - mutex_lock(&sabi_mutex); - - /* enable memory to be able to write to it */ - outb(readb(sabi + sabi_config->header_offsets.en_mem), port); - - /* write out the command */ - writew(sabi_config->main_function, sabi_iface + SABI_IFACE_MAIN); - writew(command, sabi_iface + SABI_IFACE_SUB); - writeb(0, sabi_iface + SABI_IFACE_COMPLETE); - writeb(data, sabi_iface + SABI_IFACE_DATA); - outb(readb(sabi + sabi_config->header_offsets.iface_func), port); - - /* write protect memory to make it safe */ - outb(readb(sabi + sabi_config->header_offsets.re_mem), port); - - /* see if the command actually succeeded */ - complete = readb(sabi_iface + SABI_IFACE_COMPLETE); - iface_data = readb(sabi_iface + SABI_IFACE_DATA); - if (complete != 0xaa || iface_data == 0xff) { - pr_warn("SABI set command 0x%02x failed with completion flag 0x%02x and data 0x%02x\n", - command, complete, iface_data); - retval = -EINVAL; - } - - mutex_unlock(&sabi_mutex); - return retval; -} - -static void test_backlight(void) -{ - struct sabi_retval sretval; - - sabi_get_command(sabi_config->commands.get_backlight, &sretval); - printk(KERN_DEBUG "backlight = 0x%02x\n", sretval.retval[0]); - - sabi_set_command(sabi_config->commands.set_backlight, 0); - printk(KERN_DEBUG "backlight should be off\n"); - - sabi_get_command(sabi_config->commands.get_backlight, &sretval); - printk(KERN_DEBUG "backlight = 0x%02x\n", sretval.retval[0]); - - msleep(1000); - - sabi_set_command(sabi_config->commands.set_backlight, 1); - printk(KERN_DEBUG "backlight should be on\n"); - - sabi_get_command(sabi_config->commands.get_backlight, &sretval); - printk(KERN_DEBUG "backlight = 0x%02x\n", sretval.retval[0]); -} - -static void test_wireless(void) -{ - struct sabi_retval sretval; - - sabi_get_command(sabi_config->commands.get_wireless_button, &sretval); - printk(KERN_DEBUG "wireless led = 0x%02x\n", sretval.retval[0]); - - sabi_set_command(sabi_config->commands.set_wireless_button, 0); - printk(KERN_DEBUG "wireless led should be off\n"); - - sabi_get_command(sabi_config->commands.get_wireless_button, &sretval); - printk(KERN_DEBUG "wireless led = 0x%02x\n", sretval.retval[0]); - - msleep(1000); - - sabi_set_command(sabi_config->commands.set_wireless_button, 1); - printk(KERN_DEBUG "wireless led should be on\n"); - - sabi_get_command(sabi_config->commands.get_wireless_button, &sretval); - printk(KERN_DEBUG "wireless led = 0x%02x\n", sretval.retval[0]); -} - -static u8 read_brightness(void) -{ - struct sabi_retval sretval; - int user_brightness = 0; - int retval; - - retval = sabi_get_command(sabi_config->commands.get_brightness, - &sretval); - if (!retval) { - user_brightness = sretval.retval[0]; - if (user_brightness != 0) - user_brightness -= sabi_config->min_brightness; - } - return user_brightness; -} - -static void set_brightness(u8 user_brightness) -{ - u8 user_level = user_brightness - sabi_config->min_brightness; - - sabi_set_command(sabi_config->commands.set_brightness, user_level); -} - -static int get_brightness(struct backlight_device *bd) -{ - return (int)read_brightness(); -} - -static int update_status(struct backlight_device *bd) -{ - set_brightness(bd->props.brightness); - - if (bd->props.power == FB_BLANK_UNBLANK) - sabi_set_command(sabi_config->commands.set_backlight, 1); - else - sabi_set_command(sabi_config->commands.set_backlight, 0); - return 0; -} - -static const struct backlight_ops backlight_ops = { - .get_brightness = get_brightness, - .update_status = update_status, -}; - -static int rfkill_set(void *data, bool blocked) -{ - /* Do something with blocked...*/ - /* - * blocked == false is on - * blocked == true is off - */ - if (blocked) - sabi_set_command(sabi_config->commands.set_wireless_button, 0); - else - sabi_set_command(sabi_config->commands.set_wireless_button, 1); - - return 0; -} - -static struct rfkill_ops rfkill_ops = { - .set_block = rfkill_set, -}; - -static int init_wireless(struct platform_device *sdev) -{ - int retval; - - rfk = rfkill_alloc("samsung-wifi", &sdev->dev, RFKILL_TYPE_WLAN, - &rfkill_ops, NULL); - if (!rfk) - return -ENOMEM; - - retval = rfkill_register(rfk); - if (retval) { - rfkill_destroy(rfk); - return -ENODEV; - } - - return 0; -} - -static void destroy_wireless(void) -{ - rfkill_unregister(rfk); - rfkill_destroy(rfk); -} - -static ssize_t get_performance_level(struct device *dev, - struct device_attribute *attr, char *buf) -{ - struct sabi_retval sretval; - int retval; - int i; - - /* Read the state */ - retval = sabi_get_command(sabi_config->commands.get_performance_level, - &sretval); - if (retval) - return retval; - - /* The logic is backwards, yeah, lots of fun... */ - for (i = 0; sabi_config->performance_levels[i].name; ++i) { - if (sretval.retval[0] == sabi_config->performance_levels[i].value) - return sprintf(buf, "%s\n", sabi_config->performance_levels[i].name); - } - return sprintf(buf, "%s\n", "unknown"); -} - -static ssize_t set_performance_level(struct device *dev, - struct device_attribute *attr, const char *buf, - size_t count) -{ - if (count >= 1) { - int i; - for (i = 0; sabi_config->performance_levels[i].name; ++i) { - const struct sabi_performance_level *level = - &sabi_config->performance_levels[i]; - if (!strncasecmp(level->name, buf, strlen(level->name))) { - sabi_set_command(sabi_config->commands.set_performance_level, - level->value); - break; - } - } - if (!sabi_config->performance_levels[i].name) - return -EINVAL; - } - return count; -} -static DEVICE_ATTR(performance_level, S_IWUSR | S_IRUGO, - get_performance_level, set_performance_level); - - -static int __init dmi_check_cb(const struct dmi_system_id *id) -{ - pr_info("found laptop model '%s'\n", - id->ident); - return 0; -} - -static struct dmi_system_id __initdata samsung_dmi_table[] = { - { - .ident = "N128", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, - "SAMSUNG ELECTRONICS CO., LTD."), - DMI_MATCH(DMI_PRODUCT_NAME, "N128"), - DMI_MATCH(DMI_BOARD_NAME, "N128"), - }, - .callback = dmi_check_cb, - }, - { - .ident = "N130", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, - "SAMSUNG ELECTRONICS CO., LTD."), - DMI_MATCH(DMI_PRODUCT_NAME, "N130"), - DMI_MATCH(DMI_BOARD_NAME, "N130"), - }, - .callback = dmi_check_cb, - }, - { - .ident = "X125", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, - "SAMSUNG ELECTRONICS CO., LTD."), - DMI_MATCH(DMI_PRODUCT_NAME, "X125"), - DMI_MATCH(DMI_BOARD_NAME, "X125"), - }, - .callback = dmi_check_cb, - }, - { - .ident = "X120/X170", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, - "SAMSUNG ELECTRONICS CO., LTD."), - DMI_MATCH(DMI_PRODUCT_NAME, "X120/X170"), - DMI_MATCH(DMI_BOARD_NAME, "X120/X170"), - }, - .callback = dmi_check_cb, - }, - { - .ident = "NC10", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, - "SAMSUNG ELECTRONICS CO., LTD."), - DMI_MATCH(DMI_PRODUCT_NAME, "NC10"), - DMI_MATCH(DMI_BOARD_NAME, "NC10"), - }, - .callback = dmi_check_cb, - }, - { - .ident = "NP-Q45", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, - "SAMSUNG ELECTRONICS CO., LTD."), - DMI_MATCH(DMI_PRODUCT_NAME, "SQ45S70S"), - DMI_MATCH(DMI_BOARD_NAME, "SQ45S70S"), - }, - .callback = dmi_check_cb, - }, - { - .ident = "X360", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, - "SAMSUNG ELECTRONICS CO., LTD."), - DMI_MATCH(DMI_PRODUCT_NAME, "X360"), - DMI_MATCH(DMI_BOARD_NAME, "X360"), - }, - .callback = dmi_check_cb, - }, - { - .ident = "R410 Plus", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, - "SAMSUNG ELECTRONICS CO., LTD."), - DMI_MATCH(DMI_PRODUCT_NAME, "R410P"), - DMI_MATCH(DMI_BOARD_NAME, "R460"), - }, - .callback = dmi_check_cb, - }, - { - .ident = "R518", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, - "SAMSUNG ELECTRONICS CO., LTD."), - DMI_MATCH(DMI_PRODUCT_NAME, "R518"), - DMI_MATCH(DMI_BOARD_NAME, "R518"), - }, - .callback = dmi_check_cb, - }, - { - .ident = "R519/R719", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, - "SAMSUNG ELECTRONICS CO., LTD."), - DMI_MATCH(DMI_PRODUCT_NAME, "R519/R719"), - DMI_MATCH(DMI_BOARD_NAME, "R519/R719"), - }, - .callback = dmi_check_cb, - }, - { - .ident = "N150/N210/N220/N230", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, - "SAMSUNG ELECTRONICS CO., LTD."), - DMI_MATCH(DMI_PRODUCT_NAME, "N150/N210/N220/N230"), - DMI_MATCH(DMI_BOARD_NAME, "N150/N210/N220/N230"), - }, - .callback = dmi_check_cb, - }, - { - .ident = "N150P/N210P/N220P", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, - "SAMSUNG ELECTRONICS CO., LTD."), - DMI_MATCH(DMI_PRODUCT_NAME, "N150P/N210P/N220P"), - DMI_MATCH(DMI_BOARD_NAME, "N150P/N210P/N220P"), - }, - .callback = dmi_check_cb, - }, - { - .ident = "R530/R730", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "SAMSUNG ELECTRONICS CO., LTD."), - DMI_MATCH(DMI_PRODUCT_NAME, "R530/R730"), - DMI_MATCH(DMI_BOARD_NAME, "R530/R730"), - }, - .callback = dmi_check_cb, - }, - { - .ident = "NF110/NF210/NF310", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "SAMSUNG ELECTRONICS CO., LTD."), - DMI_MATCH(DMI_PRODUCT_NAME, "NF110/NF210/NF310"), - DMI_MATCH(DMI_BOARD_NAME, "NF110/NF210/NF310"), - }, - .callback = dmi_check_cb, - }, - { - .ident = "N145P/N250P/N260P", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "SAMSUNG ELECTRONICS CO., LTD."), - DMI_MATCH(DMI_PRODUCT_NAME, "N145P/N250P/N260P"), - DMI_MATCH(DMI_BOARD_NAME, "N145P/N250P/N260P"), - }, - .callback = dmi_check_cb, - }, - { - .ident = "R70/R71", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, - "SAMSUNG ELECTRONICS CO., LTD."), - DMI_MATCH(DMI_PRODUCT_NAME, "R70/R71"), - DMI_MATCH(DMI_BOARD_NAME, "R70/R71"), - }, - .callback = dmi_check_cb, - }, - { - .ident = "P460", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "SAMSUNG ELECTRONICS CO., LTD."), - DMI_MATCH(DMI_PRODUCT_NAME, "P460"), - DMI_MATCH(DMI_BOARD_NAME, "P460"), - }, - .callback = dmi_check_cb, - }, - { }, -}; -MODULE_DEVICE_TABLE(dmi, samsung_dmi_table); - -static int find_signature(void __iomem *memcheck, const char *testStr) -{ - int i = 0; - int loca; - - for (loca = 0; loca < 0xffff; loca++) { - char temp = readb(memcheck + loca); - - if (temp == testStr[i]) { - if (i == strlen(testStr)-1) - break; - ++i; - } else { - i = 0; - } - } - return loca; -} - -static int __init samsung_init(void) -{ - struct backlight_properties props; - struct sabi_retval sretval; - unsigned int ifaceP; - int i; - int loca; - int retval; - - mutex_init(&sabi_mutex); - - if (!force && !dmi_check_system(samsung_dmi_table)) - return -ENODEV; - - f0000_segment = ioremap_nocache(0xf0000, 0xffff); - if (!f0000_segment) { - pr_err("Can't map the segment at 0xf0000\n"); - return -EINVAL; - } - - /* Try to find one of the signatures in memory to find the header */ - for (i = 0; sabi_configs[i].test_string != 0; ++i) { - sabi_config = &sabi_configs[i]; - loca = find_signature(f0000_segment, sabi_config->test_string); - if (loca != 0xffff) - break; - } - - if (loca == 0xffff) { - pr_err("This computer does not support SABI\n"); - goto error_no_signature; - } - - /* point to the SMI port Number */ - loca += 1; - sabi = (f0000_segment + loca); - - if (debug) { - printk(KERN_DEBUG "This computer supports SABI==%x\n", - loca + 0xf0000 - 6); - printk(KERN_DEBUG "SABI header:\n"); - printk(KERN_DEBUG " SMI Port Number = 0x%04x\n", - readw(sabi + sabi_config->header_offsets.port)); - printk(KERN_DEBUG " SMI Interface Function = 0x%02x\n", - readb(sabi + sabi_config->header_offsets.iface_func)); - printk(KERN_DEBUG " SMI enable memory buffer = 0x%02x\n", - readb(sabi + sabi_config->header_offsets.en_mem)); - printk(KERN_DEBUG " SMI restore memory buffer = 0x%02x\n", - readb(sabi + sabi_config->header_offsets.re_mem)); - printk(KERN_DEBUG " SABI data offset = 0x%04x\n", - readw(sabi + sabi_config->header_offsets.data_offset)); - printk(KERN_DEBUG " SABI data segment = 0x%04x\n", - readw(sabi + sabi_config->header_offsets.data_segment)); - } - - /* Get a pointer to the SABI Interface */ - ifaceP = (readw(sabi + sabi_config->header_offsets.data_segment) & 0x0ffff) << 4; - ifaceP += readw(sabi + sabi_config->header_offsets.data_offset) & 0x0ffff; - sabi_iface = ioremap_nocache(ifaceP, 16); - if (!sabi_iface) { - pr_err("Can't remap %x\n", ifaceP); - goto exit; - } - if (debug) { - printk(KERN_DEBUG "ifaceP = 0x%08x\n", ifaceP); - printk(KERN_DEBUG "sabi_iface = %p\n", sabi_iface); - - test_backlight(); - test_wireless(); - - retval = sabi_get_command(sabi_config->commands.get_brightness, - &sretval); - printk(KERN_DEBUG "brightness = 0x%02x\n", sretval.retval[0]); - } - - /* Turn on "Linux" mode in the BIOS */ - if (sabi_config->commands.set_linux != 0xff) { - retval = sabi_set_command(sabi_config->commands.set_linux, - 0x81); - if (retval) { - pr_warn("Linux mode was not set!\n"); - goto error_no_platform; - } - } - - /* knock up a platform device to hang stuff off of */ - sdev = platform_device_register_simple("samsung", -1, NULL, 0); - if (IS_ERR(sdev)) - goto error_no_platform; - - /* create a backlight device to talk to this one */ - memset(&props, 0, sizeof(struct backlight_properties)); - props.type = BACKLIGHT_PLATFORM; - props.max_brightness = sabi_config->max_brightness; - backlight_device = backlight_device_register("samsung", &sdev->dev, - NULL, &backlight_ops, - &props); - if (IS_ERR(backlight_device)) - goto error_no_backlight; - - backlight_device->props.brightness = read_brightness(); - backlight_device->props.power = FB_BLANK_UNBLANK; - backlight_update_status(backlight_device); - - retval = init_wireless(sdev); - if (retval) - goto error_no_rfk; - - retval = device_create_file(&sdev->dev, &dev_attr_performance_level); - if (retval) - goto error_file_create; - -exit: - return 0; - -error_file_create: - destroy_wireless(); - -error_no_rfk: - backlight_device_unregister(backlight_device); - -error_no_backlight: - platform_device_unregister(sdev); - -error_no_platform: - iounmap(sabi_iface); - -error_no_signature: - iounmap(f0000_segment); - return -EINVAL; -} - -static void __exit samsung_exit(void) -{ - /* Turn off "Linux" mode in the BIOS */ - if (sabi_config->commands.set_linux != 0xff) - sabi_set_command(sabi_config->commands.set_linux, 0x80); - - device_remove_file(&sdev->dev, &dev_attr_performance_level); - backlight_device_unregister(backlight_device); - destroy_wireless(); - iounmap(sabi_iface); - iounmap(f0000_segment); - platform_device_unregister(sdev); -} - -module_init(samsung_init); -module_exit(samsung_exit); - -MODULE_AUTHOR("Greg Kroah-Hartman <gregkh@suse.de>"); -MODULE_DESCRIPTION("Samsung Backlight driver"); -MODULE_LICENSE("GPL"); diff --git a/drivers/xen/events.c b/drivers/xen/events.c index 42d6c930cc8..33167b43ac7 100644 --- a/drivers/xen/events.c +++ b/drivers/xen/events.c @@ -912,8 +912,7 @@ int bind_evtchn_to_irqhandler(unsigned int evtchn, unsigned long irqflags, const char *devname, void *dev_id) { - unsigned int irq; - int retval; + int irq, retval; irq = bind_evtchn_to_irq(evtchn); if (irq < 0) @@ -955,8 +954,7 @@ int bind_virq_to_irqhandler(unsigned int virq, unsigned int cpu, irq_handler_t handler, unsigned long irqflags, const char *devname, void *dev_id) { - unsigned int irq; - int retval; + int irq, retval; irq = bind_virq_to_irq(virq, cpu); if (irq < 0) diff --git a/fs/cifs/README b/fs/cifs/README index fe168359082..74ab165fc64 100644 --- a/fs/cifs/README +++ b/fs/cifs/README @@ -685,22 +685,6 @@ LinuxExtensionsEnabled If set to one then the client will attempt to support and want to map the uid and gid fields to values supplied at mount (rather than the actual values, then set this to zero. (default 1) -Experimental When set to 1 used to enable certain experimental - features (currently enables multipage writes - when signing is enabled, the multipage write - performance enhancement was disabled when - signing turned on in case buffer was modified - just before it was sent, also this flag will - be used to use the new experimental directory change - notification code). When set to 2 enables - an additional experimental feature, "raw ntlmssp" - session establishment support (which allows - specifying "sec=ntlmssp" on mount). The Linux cifs - module will use ntlmv2 authentication encapsulated - in "raw ntlmssp" (not using SPNEGO) when - "sec=ntlmssp" is specified on mount. - This support also requires building cifs with - the CONFIG_CIFS_EXPERIMENTAL configuration flag. These experimental features and tracing can be enabled by changing flags in /proc/fs/cifs (after the cifs module has been installed or built into the diff --git a/fs/cifs/cache.c b/fs/cifs/cache.c index e654dfd092c..53d57a3fe42 100644 --- a/fs/cifs/cache.c +++ b/fs/cifs/cache.c @@ -50,7 +50,7 @@ void cifs_fscache_unregister(void) */ struct cifs_server_key { uint16_t family; /* address family */ - uint16_t port; /* IP port */ + __be16 port; /* IP port */ union { struct in_addr ipv4_addr; struct in6_addr ipv6_addr; diff --git a/fs/cifs/cifs_debug.c b/fs/cifs/cifs_debug.c index 65829d32128..30d01bc9085 100644 --- a/fs/cifs/cifs_debug.c +++ b/fs/cifs/cifs_debug.c @@ -423,7 +423,6 @@ static const struct file_operations cifs_lookup_cache_proc_fops; static const struct file_operations traceSMB_proc_fops; static const struct file_operations cifs_multiuser_mount_proc_fops; static const struct file_operations cifs_security_flags_proc_fops; -static const struct file_operations cifs_experimental_proc_fops; static const struct file_operations cifs_linux_ext_proc_fops; void @@ -441,8 +440,6 @@ cifs_proc_init(void) proc_create("cifsFYI", 0, proc_fs_cifs, &cifsFYI_proc_fops); proc_create("traceSMB", 0, proc_fs_cifs, &traceSMB_proc_fops); proc_create("OplockEnabled", 0, proc_fs_cifs, &cifs_oplock_proc_fops); - proc_create("Experimental", 0, proc_fs_cifs, - &cifs_experimental_proc_fops); proc_create("LinuxExtensionsEnabled", 0, proc_fs_cifs, &cifs_linux_ext_proc_fops); proc_create("MultiuserMount", 0, proc_fs_cifs, @@ -469,7 +466,6 @@ cifs_proc_clean(void) remove_proc_entry("OplockEnabled", proc_fs_cifs); remove_proc_entry("SecurityFlags", proc_fs_cifs); remove_proc_entry("LinuxExtensionsEnabled", proc_fs_cifs); - remove_proc_entry("Experimental", proc_fs_cifs); remove_proc_entry("LookupCacheEnabled", proc_fs_cifs); remove_proc_entry("fs/cifs", NULL); } @@ -550,45 +546,6 @@ static const struct file_operations cifs_oplock_proc_fops = { .write = cifs_oplock_proc_write, }; -static int cifs_experimental_proc_show(struct seq_file *m, void *v) -{ - seq_printf(m, "%d\n", experimEnabled); - return 0; -} - -static int cifs_experimental_proc_open(struct inode *inode, struct file *file) -{ - return single_open(file, cifs_experimental_proc_show, NULL); -} - -static ssize_t cifs_experimental_proc_write(struct file *file, - const char __user *buffer, size_t count, loff_t *ppos) -{ - char c; - int rc; - - rc = get_user(c, buffer); - if (rc) - return rc; - if (c == '0' || c == 'n' || c == 'N') - experimEnabled = 0; - else if (c == '1' || c == 'y' || c == 'Y') - experimEnabled = 1; - else if (c == '2') - experimEnabled = 2; - - return count; -} - -static const struct file_operations cifs_experimental_proc_fops = { - .owner = THIS_MODULE, - .open = cifs_experimental_proc_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, - .write = cifs_experimental_proc_write, -}; - static int cifs_linux_ext_proc_show(struct seq_file *m, void *v) { seq_printf(m, "%d\n", linuxExtEnabled); diff --git a/fs/cifs/cifs_spnego.c b/fs/cifs/cifs_spnego.c index 4dfba828316..33d221394ac 100644 --- a/fs/cifs/cifs_spnego.c +++ b/fs/cifs/cifs_spnego.c @@ -113,7 +113,7 @@ cifs_get_spnego_key(struct cifsSesInfo *sesInfo) MAX_MECH_STR_LEN + UID_KEY_LEN + (sizeof(uid_t) * 2) + CREDUID_KEY_LEN + (sizeof(uid_t) * 2) + - USER_KEY_LEN + strlen(sesInfo->userName) + + USER_KEY_LEN + strlen(sesInfo->user_name) + PID_KEY_LEN + (sizeof(pid_t) * 2) + 1; spnego_key = ERR_PTR(-ENOMEM); @@ -153,7 +153,7 @@ cifs_get_spnego_key(struct cifsSesInfo *sesInfo) sprintf(dp, ";creduid=0x%x", sesInfo->cred_uid); dp = description + strlen(description); - sprintf(dp, ";user=%s", sesInfo->userName); + sprintf(dp, ";user=%s", sesInfo->user_name); dp = description + strlen(description); sprintf(dp, ";pid=0x%x", current->pid); diff --git a/fs/cifs/cifs_unicode.c b/fs/cifs/cifs_unicode.c index fc0fd4fde30..23d43cde430 100644 --- a/fs/cifs/cifs_unicode.c +++ b/fs/cifs/cifs_unicode.c @@ -90,7 +90,7 @@ cifs_mapchar(char *target, const __u16 src_char, const struct nls_table *cp, case UNI_COLON: *target = ':'; break; - case UNI_ASTERIK: + case UNI_ASTERISK: *target = '*'; break; case UNI_QUESTION: @@ -264,40 +264,40 @@ cifs_strndup_from_ucs(const char *src, const int maxlen, const bool is_unicode, * names are little endian 16 bit Unicode on the wire */ int -cifsConvertToUCS(__le16 *target, const char *source, int maxlen, +cifsConvertToUCS(__le16 *target, const char *source, int srclen, const struct nls_table *cp, int mapChars) { int i, j, charlen; - int len_remaining = maxlen; char src_char; - __u16 temp; + __le16 dst_char; + wchar_t tmp; if (!mapChars) return cifs_strtoUCS(target, source, PATH_MAX, cp); - for (i = 0, j = 0; i < maxlen; j++) { + for (i = 0, j = 0; i < srclen; j++) { src_char = source[i]; switch (src_char) { case 0: - put_unaligned_le16(0, &target[j]); + put_unaligned(0, &target[j]); goto ctoUCS_out; case ':': - temp = UNI_COLON; + dst_char = cpu_to_le16(UNI_COLON); break; case '*': - temp = UNI_ASTERIK; + dst_char = cpu_to_le16(UNI_ASTERISK); break; case '?': - temp = UNI_QUESTION; + dst_char = cpu_to_le16(UNI_QUESTION); break; case '<': - temp = UNI_LESSTHAN; + dst_char = cpu_to_le16(UNI_LESSTHAN); break; case '>': - temp = UNI_GRTRTHAN; + dst_char = cpu_to_le16(UNI_GRTRTHAN); break; case '|': - temp = UNI_PIPE; + dst_char = cpu_to_le16(UNI_PIPE); break; /* * FIXME: We can not handle remapping backslash (UNI_SLASH) @@ -305,17 +305,17 @@ cifsConvertToUCS(__le16 *target, const char *source, int maxlen, * as they use backslash as separator. */ default: - charlen = cp->char2uni(source+i, len_remaining, - &temp); + charlen = cp->char2uni(source + i, srclen - i, &tmp); + dst_char = cpu_to_le16(tmp); + /* * if no match, use question mark, which at least in * some cases serves as wild card */ if (charlen < 1) { - temp = 0x003f; + dst_char = cpu_to_le16(0x003f); charlen = 1; } - len_remaining -= charlen; /* * character may take more than one byte in the source * string, but will take exactly two bytes in the @@ -324,9 +324,8 @@ cifsConvertToUCS(__le16 *target, const char *source, int maxlen, i += charlen; continue; } - put_unaligned_le16(temp, &target[j]); + put_unaligned(dst_char, &target[j]); i++; /* move to next char in source string */ - len_remaining--; } ctoUCS_out: diff --git a/fs/cifs/cifs_unicode.h b/fs/cifs/cifs_unicode.h index 7fe6b52df50..644dd882a56 100644 --- a/fs/cifs/cifs_unicode.h +++ b/fs/cifs/cifs_unicode.h @@ -44,7 +44,7 @@ * reserved symbols (along with \ and /), otherwise illegal to store * in filenames in NTFS */ -#define UNI_ASTERIK (__u16) ('*' + 0xF000) +#define UNI_ASTERISK (__u16) ('*' + 0xF000) #define UNI_QUESTION (__u16) ('?' + 0xF000) #define UNI_COLON (__u16) (':' + 0xF000) #define UNI_GRTRTHAN (__u16) ('>' + 0xF000) diff --git a/fs/cifs/cifsencrypt.c b/fs/cifs/cifsencrypt.c index a51585f9852..d1a016be73b 100644 --- a/fs/cifs/cifsencrypt.c +++ b/fs/cifs/cifsencrypt.c @@ -30,12 +30,13 @@ #include <linux/ctype.h> #include <linux/random.h> -/* Calculate and return the CIFS signature based on the mac key and SMB PDU */ -/* the 16 byte signature must be allocated by the caller */ -/* Note we only use the 1st eight bytes */ -/* Note that the smb header signature field on input contains the - sequence number before this function is called */ - +/* + * Calculate and return the CIFS signature based on the mac key and SMB PDU. + * The 16 byte signature must be allocated by the caller. Note we only use the + * 1st eight bytes and that the smb header signature field on input contains + * the sequence number before this function is called. Also, this function + * should be called with the server->srv_mutex held. + */ static int cifs_calculate_signature(const struct smb_hdr *cifs_pdu, struct TCP_Server_Info *server, char *signature) { @@ -209,8 +210,10 @@ int cifs_verify_signature(struct smb_hdr *cifs_pdu, cpu_to_le32(expected_sequence_number); cifs_pdu->Signature.Sequence.Reserved = 0; + mutex_lock(&server->srv_mutex); rc = cifs_calculate_signature(cifs_pdu, server, what_we_think_sig_should_be); + mutex_unlock(&server->srv_mutex); if (rc) return rc; @@ -469,15 +472,15 @@ static int calc_ntlmv2_hash(struct cifsSesInfo *ses, char *ntlmv2_hash, return rc; } - /* convert ses->userName to unicode and uppercase */ - len = strlen(ses->userName); + /* convert ses->user_name to unicode and uppercase */ + len = strlen(ses->user_name); user = kmalloc(2 + (len * 2), GFP_KERNEL); if (user == NULL) { cERROR(1, "calc_ntlmv2_hash: user mem alloc failure\n"); rc = -ENOMEM; goto calc_exit_2; } - len = cifs_strtoUCS((__le16 *)user, ses->userName, len, nls_cp); + len = cifs_strtoUCS((__le16 *)user, ses->user_name, len, nls_cp); UniStrupr(user); crypto_shash_update(&ses->server->secmech.sdeschmacmd5->shash, diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index f2970136d17..5c412b33cd7 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -53,7 +53,6 @@ int cifsFYI = 0; int cifsERROR = 1; int traceSMB = 0; unsigned int oplockEnabled = 1; -unsigned int experimEnabled = 0; unsigned int linuxExtEnabled = 1; unsigned int lookupCacheEnabled = 1; unsigned int multiuser_mount = 0; @@ -127,6 +126,7 @@ cifs_read_super(struct super_block *sb, void *data, kfree(cifs_sb); return rc; } + cifs_sb->bdi.ra_pages = default_backing_dev_info.ra_pages; #ifdef CONFIG_CIFS_DFS_UPCALL /* copy mount params to sb for use in submounts */ @@ -409,8 +409,8 @@ cifs_show_options(struct seq_file *s, struct vfsmount *m) if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MULTIUSER) seq_printf(s, ",multiuser"); - else if (tcon->ses->userName) - seq_printf(s, ",username=%s", tcon->ses->userName); + else if (tcon->ses->user_name) + seq_printf(s, ",username=%s", tcon->ses->user_name); if (tcon->ses->domainName) seq_printf(s, ",domain=%s", tcon->ses->domainName); diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index 17afb0fbcae..a5d1106fcbd 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -37,10 +37,9 @@ #define MAX_TREE_SIZE (2 + MAX_SERVER_SIZE + 1 + MAX_SHARE_SIZE + 1) #define MAX_SERVER_SIZE 15 -#define MAX_SHARE_SIZE 64 /* used to be 20, this should still be enough */ -#define MAX_USERNAME_SIZE 32 /* 32 is to allow for 15 char names + null - termination then *2 for unicode versions */ -#define MAX_PASSWORD_SIZE 512 /* max for windows seems to be 256 wide chars */ +#define MAX_SHARE_SIZE 80 +#define MAX_USERNAME_SIZE 256 /* reasonable maximum for current servers */ +#define MAX_PASSWORD_SIZE 512 /* max for windows seems to be 256 wide chars */ #define CIFS_MIN_RCV_POOL 4 @@ -92,7 +91,8 @@ enum statusEnum { CifsNew = 0, CifsGood, CifsExiting, - CifsNeedReconnect + CifsNeedReconnect, + CifsNeedNegotiate }; enum securityEnum { @@ -274,7 +274,7 @@ struct cifsSesInfo { int capabilities; char serverName[SERVER_NAME_LEN_WITH_NULL * 2]; /* BB make bigger for TCP names - will ipv6 and sctp addresses fit? */ - char userName[MAX_USERNAME_SIZE + 1]; + char *user_name; char *domainName; char *password; struct session_key auth_key; @@ -817,7 +817,6 @@ GLOBAL_EXTERN unsigned int multiuser_mount; /* if enabled allows new sessions have the uid/password or Kerberos credential or equivalent for current user */ GLOBAL_EXTERN unsigned int oplockEnabled; -GLOBAL_EXTERN unsigned int experimEnabled; GLOBAL_EXTERN unsigned int lookupCacheEnabled; GLOBAL_EXTERN unsigned int global_secflags; /* if on, session setup sent with more secure ntlmssp2 challenge/resp */ diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c index 2644a5d6cc6..df959bae672 100644 --- a/fs/cifs/cifssmb.c +++ b/fs/cifs/cifssmb.c @@ -142,9 +142,9 @@ cifs_reconnect_tcon(struct cifsTconInfo *tcon, int smb_command) */ while (server->tcpStatus == CifsNeedReconnect) { wait_event_interruptible_timeout(server->response_q, - (server->tcpStatus == CifsGood), 10 * HZ); + (server->tcpStatus != CifsNeedReconnect), 10 * HZ); - /* is TCP session is reestablished now ?*/ + /* are we still trying to reconnect? */ if (server->tcpStatus != CifsNeedReconnect) break; @@ -729,7 +729,7 @@ CIFSSMBEcho(struct TCP_Server_Info *server) return rc; /* set up echo request */ - smb->hdr.Tid = cpu_to_le16(0xffff); + smb->hdr.Tid = 0xffff; smb->hdr.WordCount = 1; put_unaligned_le16(1, &smb->EchoCount); put_bcc_le(1, &smb->hdr); @@ -1884,10 +1884,10 @@ CIFSSMBPosixLock(const int xid, struct cifsTconInfo *tcon, __constant_cpu_to_le16(CIFS_WRLCK)) pLockData->fl_type = F_WRLCK; - pLockData->fl_start = parm_data->start; - pLockData->fl_end = parm_data->start + - parm_data->length - 1; - pLockData->fl_pid = parm_data->pid; + pLockData->fl_start = le64_to_cpu(parm_data->start); + pLockData->fl_end = pLockData->fl_start + + le64_to_cpu(parm_data->length) - 1; + pLockData->fl_pid = le32_to_cpu(parm_data->pid); } } diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 6e2b2addfc7..db9d55b507d 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -199,8 +199,7 @@ cifs_reconnect(struct TCP_Server_Info *server) } spin_unlock(&GlobalMid_Lock); - while ((server->tcpStatus != CifsExiting) && - (server->tcpStatus != CifsGood)) { + while (server->tcpStatus == CifsNeedReconnect) { try_to_freeze(); /* we should try only the port we connected to before */ @@ -212,7 +211,7 @@ cifs_reconnect(struct TCP_Server_Info *server) atomic_inc(&tcpSesReconnectCount); spin_lock(&GlobalMid_Lock); if (server->tcpStatus != CifsExiting) - server->tcpStatus = CifsGood; + server->tcpStatus = CifsNeedNegotiate; spin_unlock(&GlobalMid_Lock); } } @@ -248,24 +247,24 @@ static int check2ndT2(struct smb_hdr *pSMB, unsigned int maxBufSize) total_data_size = get_unaligned_le16(&pSMBt->t2_rsp.TotalDataCount); data_in_this_rsp = get_unaligned_le16(&pSMBt->t2_rsp.DataCount); - remaining = total_data_size - data_in_this_rsp; - - if (remaining == 0) + if (total_data_size == data_in_this_rsp) return 0; - else if (remaining < 0) { + else if (total_data_size < data_in_this_rsp) { cFYI(1, "total data %d smaller than data in frame %d", total_data_size, data_in_this_rsp); return -EINVAL; - } else { - cFYI(1, "missing %d bytes from transact2, check next response", - remaining); - if (total_data_size > maxBufSize) { - cERROR(1, "TotalDataSize %d is over maximum buffer %d", - total_data_size, maxBufSize); - return -EINVAL; - } - return remaining; } + + remaining = total_data_size - data_in_this_rsp; + + cFYI(1, "missing %d bytes from transact2, check next response", + remaining); + if (total_data_size > maxBufSize) { + cERROR(1, "TotalDataSize %d is over maximum buffer %d", + total_data_size, maxBufSize); + return -EINVAL; + } + return remaining; } static int coalesce_t2(struct smb_hdr *psecond, struct smb_hdr *pTargetSMB) @@ -421,7 +420,7 @@ cifs_demultiplex_thread(struct TCP_Server_Info *server) pdu_length = 4; /* enough to get RFC1001 header */ incomplete_rcv: - if (echo_retries > 0 && + if (echo_retries > 0 && server->tcpStatus == CifsGood && time_after(jiffies, server->lstrp + (echo_retries * SMB_ECHO_INTERVAL))) { cERROR(1, "Server %s has not responded in %d seconds. " @@ -881,7 +880,8 @@ cifs_parse_mount_options(char *options, const char *devname, /* null user, ie anonymous, authentication */ vol->nullauth = 1; } - if (strnlen(value, 200) < 200) { + if (strnlen(value, MAX_USERNAME_SIZE) < + MAX_USERNAME_SIZE) { vol->username = value; } else { printk(KERN_WARNING "CIFS: username too long\n"); @@ -1472,7 +1472,7 @@ srcip_matches(struct sockaddr *srcaddr, struct sockaddr *rhs) static bool match_port(struct TCP_Server_Info *server, struct sockaddr *addr) { - unsigned short int port, *sport; + __be16 port, *sport; switch (addr->sa_family) { case AF_INET: @@ -1765,6 +1765,7 @@ cifs_get_tcp_session(struct smb_vol *volume_info) module_put(THIS_MODULE); goto out_err_crypto_release; } + tcp_ses->tcpStatus = CifsNeedNegotiate; /* thread spawned, put it on the list */ spin_lock(&cifs_tcp_ses_lock); @@ -1808,7 +1809,9 @@ cifs_find_smb_ses(struct TCP_Server_Info *server, struct smb_vol *vol) break; default: /* anything else takes username/password */ - if (strncmp(ses->userName, vol->username, + if (ses->user_name == NULL) + continue; + if (strncmp(ses->user_name, vol->username, MAX_USERNAME_SIZE)) continue; if (strlen(vol->username) != 0 && @@ -1851,6 +1854,8 @@ cifs_put_smb_ses(struct cifsSesInfo *ses) cifs_put_tcp_session(server); } +static bool warned_on_ntlm; /* globals init to false automatically */ + static struct cifsSesInfo * cifs_get_smb_ses(struct TCP_Server_Info *server, struct smb_vol *volume_info) { @@ -1906,9 +1911,11 @@ cifs_get_smb_ses(struct TCP_Server_Info *server, struct smb_vol *volume_info) else sprintf(ses->serverName, "%pI4", &addr->sin_addr); - if (volume_info->username) - strncpy(ses->userName, volume_info->username, - MAX_USERNAME_SIZE); + if (volume_info->username) { + ses->user_name = kstrdup(volume_info->username, GFP_KERNEL); + if (!ses->user_name) + goto get_ses_fail; + } /* volume_info->password freed at unmount */ if (volume_info->password) { @@ -1923,6 +1930,15 @@ cifs_get_smb_ses(struct TCP_Server_Info *server, struct smb_vol *volume_info) } ses->cred_uid = volume_info->cred_uid; ses->linux_uid = volume_info->linux_uid; + + /* ntlmv2 is much stronger than ntlm security, and has been broadly + supported for many years, time to update default security mechanism */ + if ((volume_info->secFlg == 0) && warned_on_ntlm == false) { + warned_on_ntlm = true; + cERROR(1, "default security mechanism requested. The default " + "security mechanism will be upgraded from ntlm to " + "ntlmv2 in kernel release 2.6.41"); + } ses->overrideSecFlg = volume_info->secFlg; mutex_lock(&ses->session_mutex); @@ -2276,7 +2292,7 @@ static int generic_ip_connect(struct TCP_Server_Info *server) { int rc = 0; - unsigned short int sport; + __be16 sport; int slen, sfamily; struct socket *socket = server->ssocket; struct sockaddr *saddr; @@ -2361,7 +2377,7 @@ generic_ip_connect(struct TCP_Server_Info *server) static int ip_connect(struct TCP_Server_Info *server) { - unsigned short int *sport; + __be16 *sport; struct sockaddr_in6 *addr6 = (struct sockaddr_in6 *)&server->dstaddr; struct sockaddr_in *addr = (struct sockaddr_in *)&server->dstaddr; @@ -2826,7 +2842,7 @@ try_mount_again: remote_path_check: /* check if a whole path (including prepath) is not remote */ - if (!rc && cifs_sb->prepathlen && tcon) { + if (!rc && tcon) { /* build_path_to_root works only when we have a valid tcon */ full_path = cifs_build_path_to_root(cifs_sb, tcon); if (full_path == NULL) { diff --git a/fs/cifs/file.c b/fs/cifs/file.c index c27d236738f..faf59529e84 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -575,8 +575,10 @@ reopen_error_exit: int cifs_close(struct inode *inode, struct file *file) { - cifsFileInfo_put(file->private_data); - file->private_data = NULL; + if (file->private_data != NULL) { + cifsFileInfo_put(file->private_data); + file->private_data = NULL; + } /* return code from the ->release op is always ignored */ return 0; @@ -970,6 +972,9 @@ static ssize_t cifs_write(struct cifsFileInfo *open_file, total_written += bytes_written) { rc = -EAGAIN; while (rc == -EAGAIN) { + struct kvec iov[2]; + unsigned int len; + if (open_file->invalidHandle) { /* we could deadlock if we called filemap_fdatawait from here so tell @@ -979,31 +984,14 @@ static ssize_t cifs_write(struct cifsFileInfo *open_file, if (rc != 0) break; } - if (experimEnabled || (pTcon->ses->server && - ((pTcon->ses->server->secMode & - (SECMODE_SIGN_REQUIRED | SECMODE_SIGN_ENABLED)) - == 0))) { - struct kvec iov[2]; - unsigned int len; - - len = min((size_t)cifs_sb->wsize, - write_size - total_written); - /* iov[0] is reserved for smb header */ - iov[1].iov_base = (char *)write_data + - total_written; - iov[1].iov_len = len; - rc = CIFSSMBWrite2(xid, pTcon, - open_file->netfid, len, - *poffset, &bytes_written, - iov, 1, 0); - } else - rc = CIFSSMBWrite(xid, pTcon, - open_file->netfid, - min_t(const int, cifs_sb->wsize, - write_size - total_written), - *poffset, &bytes_written, - write_data + total_written, - NULL, 0); + + len = min((size_t)cifs_sb->wsize, + write_size - total_written); + /* iov[0] is reserved for smb header */ + iov[1].iov_base = (char *)write_data + total_written; + iov[1].iov_len = len; + rc = CIFSSMBWrite2(xid, pTcon, open_file->netfid, len, + *poffset, &bytes_written, iov, 1, 0); } if (rc || (bytes_written == 0)) { if (total_written) @@ -1240,12 +1228,6 @@ static int cifs_writepages(struct address_space *mapping, } tcon = tlink_tcon(open_file->tlink); - if (!experimEnabled && tcon->ses->server->secMode & - (SECMODE_SIGN_REQUIRED | SECMODE_SIGN_ENABLED)) { - cifsFileInfo_put(open_file); - kfree(iov); - return generic_writepages(mapping, wbc); - } cifsFileInfo_put(open_file); xid = GetXid(); @@ -1980,6 +1962,24 @@ static ssize_t cifs_read(struct file *file, char *read_data, size_t read_size, return total_read; } +/* + * If the page is mmap'ed into a process' page tables, then we need to make + * sure that it doesn't change while being written back. + */ +static int +cifs_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) +{ + struct page *page = vmf->page; + + lock_page(page); + return VM_FAULT_LOCKED; +} + +static struct vm_operations_struct cifs_file_vm_ops = { + .fault = filemap_fault, + .page_mkwrite = cifs_page_mkwrite, +}; + int cifs_file_strict_mmap(struct file *file, struct vm_area_struct *vma) { int rc, xid; @@ -1991,6 +1991,8 @@ int cifs_file_strict_mmap(struct file *file, struct vm_area_struct *vma) cifs_invalidate_mapping(inode); rc = generic_file_mmap(file, vma); + if (rc == 0) + vma->vm_ops = &cifs_file_vm_ops; FreeXid(xid); return rc; } @@ -2007,6 +2009,8 @@ int cifs_file_mmap(struct file *file, struct vm_area_struct *vma) return rc; } rc = generic_file_mmap(file, vma); + if (rc == 0) + vma->vm_ops = &cifs_file_vm_ops; FreeXid(xid); return rc; } diff --git a/fs/cifs/link.c b/fs/cifs/link.c index e8804d37340..ce417a9764a 100644 --- a/fs/cifs/link.c +++ b/fs/cifs/link.c @@ -239,7 +239,7 @@ CIFSQueryMFSymLink(const int xid, struct cifsTconInfo *tcon, if (rc != 0) return rc; - if (file_info.EndOfFile != CIFS_MF_SYMLINK_FILE_SIZE) { + if (file_info.EndOfFile != cpu_to_le64(CIFS_MF_SYMLINK_FILE_SIZE)) { CIFSSMBClose(xid, tcon, netfid); /* it's not a symlink */ return -EINVAL; @@ -316,7 +316,7 @@ CIFSCheckMFSymlink(struct cifs_fattr *fattr, if (rc != 0) goto out; - if (file_info.EndOfFile != CIFS_MF_SYMLINK_FILE_SIZE) { + if (file_info.EndOfFile != cpu_to_le64(CIFS_MF_SYMLINK_FILE_SIZE)) { CIFSSMBClose(xid, pTcon, netfid); /* it's not a symlink */ goto out; diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c index 2a930a752a7..0c684ae4c07 100644 --- a/fs/cifs/misc.c +++ b/fs/cifs/misc.c @@ -100,6 +100,7 @@ sesInfoFree(struct cifsSesInfo *buf_to_free) memset(buf_to_free->password, 0, strlen(buf_to_free->password)); kfree(buf_to_free->password); } + kfree(buf_to_free->user_name); kfree(buf_to_free->domainName); kfree(buf_to_free); } @@ -520,7 +521,7 @@ is_valid_oplock_break(struct smb_hdr *buf, struct TCP_Server_Info *srv) (struct smb_com_transaction_change_notify_rsp *)buf; struct file_notify_information *pnotify; __u32 data_offset = 0; - if (pSMBr->ByteCount > sizeof(struct file_notify_information)) { + if (get_bcc_le(buf) > sizeof(struct file_notify_information)) { data_offset = le32_to_cpu(pSMBr->DataOffset); pnotify = (struct file_notify_information *) diff --git a/fs/cifs/sess.c b/fs/cifs/sess.c index 16765703131..f6728eb6f4b 100644 --- a/fs/cifs/sess.c +++ b/fs/cifs/sess.c @@ -219,12 +219,12 @@ static void unicode_ssetup_strings(char **pbcc_area, struct cifsSesInfo *ses, bcc_ptr++; } */ /* copy user */ - if (ses->userName == NULL) { + if (ses->user_name == NULL) { /* null user mount */ *bcc_ptr = 0; *(bcc_ptr+1) = 0; } else { - bytes_ret = cifs_strtoUCS((__le16 *) bcc_ptr, ses->userName, + bytes_ret = cifs_strtoUCS((__le16 *) bcc_ptr, ses->user_name, MAX_USERNAME_SIZE, nls_cp); } bcc_ptr += 2 * bytes_ret; @@ -244,12 +244,11 @@ static void ascii_ssetup_strings(char **pbcc_area, struct cifsSesInfo *ses, /* copy user */ /* BB what about null user mounts - check that we do this BB */ /* copy user */ - if (ses->userName == NULL) { - /* BB what about null user mounts - check that we do this BB */ - } else { - strncpy(bcc_ptr, ses->userName, MAX_USERNAME_SIZE); - } - bcc_ptr += strnlen(ses->userName, MAX_USERNAME_SIZE); + if (ses->user_name != NULL) + strncpy(bcc_ptr, ses->user_name, MAX_USERNAME_SIZE); + /* else null user mount */ + + bcc_ptr += strnlen(ses->user_name, MAX_USERNAME_SIZE); *bcc_ptr = 0; bcc_ptr++; /* account for null termination */ @@ -405,8 +404,8 @@ static int decode_ntlmssp_challenge(char *bcc_ptr, int blob_len, /* BB spec says that if AvId field of MsvAvTimestamp is populated then we must set the MIC field of the AUTHENTICATE_MESSAGE */ ses->ntlmssp->server_flags = le32_to_cpu(pblob->NegotiateFlags); - tioffset = cpu_to_le16(pblob->TargetInfoArray.BufferOffset); - tilen = cpu_to_le16(pblob->TargetInfoArray.Length); + tioffset = le32_to_cpu(pblob->TargetInfoArray.BufferOffset); + tilen = le16_to_cpu(pblob->TargetInfoArray.Length); if (tilen) { ses->auth_key.response = kmalloc(tilen, GFP_KERNEL); if (!ses->auth_key.response) { @@ -523,14 +522,14 @@ static int build_ntlmssp_auth_blob(unsigned char *pbuffer, tmp += len; } - if (ses->userName == NULL) { + if (ses->user_name == NULL) { sec_blob->UserName.BufferOffset = cpu_to_le32(tmp - pbuffer); sec_blob->UserName.Length = 0; sec_blob->UserName.MaximumLength = 0; tmp += 2; } else { int len; - len = cifs_strtoUCS((__le16 *)tmp, ses->userName, + len = cifs_strtoUCS((__le16 *)tmp, ses->user_name, MAX_USERNAME_SIZE, nls_cp); len *= 2; /* unicode is 2 bytes each */ sec_blob->UserName.BufferOffset = cpu_to_le32(tmp - pbuffer); diff --git a/fs/ext4/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h index e25e99bf7ee..d0f53538a57 100644 --- a/fs/ext4/ext4_jbd2.h +++ b/fs/ext4/ext4_jbd2.h @@ -86,8 +86,8 @@ #ifdef CONFIG_QUOTA /* Amount of blocks needed for quota update - we know that the structure was - * allocated so we need to update only inode+data */ -#define EXT4_QUOTA_TRANS_BLOCKS(sb) (test_opt(sb, QUOTA) ? 2 : 0) + * allocated so we need to update only data block */ +#define EXT4_QUOTA_TRANS_BLOCKS(sb) (test_opt(sb, QUOTA) ? 1 : 0) /* Amount of blocks needed for quota insert/delete - we do some block writes * but inode, sb and group updates are done only once */ #define EXT4_QUOTA_INIT_BLOCKS(sb) (test_opt(sb, QUOTA) ? (DQUOT_INIT_ALLOC*\ diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c index 4673bc05274..e9473cbe80d 100644 --- a/fs/ext4/fsync.c +++ b/fs/ext4/fsync.c @@ -125,9 +125,11 @@ extern int ext4_flush_completed_IO(struct inode *inode) * the parent directory's parent as well, and so on recursively, if * they are also freshly created. */ -static void ext4_sync_parent(struct inode *inode) +static int ext4_sync_parent(struct inode *inode) { + struct writeback_control wbc; struct dentry *dentry = NULL; + int ret = 0; while (inode && ext4_test_inode_state(inode, EXT4_STATE_NEWENTRY)) { ext4_clear_inode_state(inode, EXT4_STATE_NEWENTRY); @@ -136,8 +138,17 @@ static void ext4_sync_parent(struct inode *inode) if (!dentry || !dentry->d_parent || !dentry->d_parent->d_inode) break; inode = dentry->d_parent->d_inode; - sync_mapping_buffers(inode->i_mapping); + ret = sync_mapping_buffers(inode->i_mapping); + if (ret) + break; + memset(&wbc, 0, sizeof(wbc)); + wbc.sync_mode = WB_SYNC_ALL; + wbc.nr_to_write = 0; /* only write out the inode */ + ret = sync_inode(inode, &wbc); + if (ret) + break; } + return ret; } /* @@ -176,7 +187,7 @@ int ext4_sync_file(struct file *file, int datasync) if (!journal) { ret = generic_file_fsync(file, datasync); if (!ret && !list_empty(&inode->i_dentry)) - ext4_sync_parent(inode); + ret = ext4_sync_parent(inode); goto out; } diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index ad8e303c0d2..f2fa5e8a582 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -2502,6 +2502,7 @@ static int ext4_da_get_block_prep(struct inode *inode, sector_t iblock, * for partial write. */ set_buffer_new(bh); + set_buffer_mapped(bh); } return 0; } @@ -4429,8 +4430,8 @@ void ext4_truncate(struct inode *inode) Indirect chain[4]; Indirect *partial; __le32 nr = 0; - int n; - ext4_lblk_t last_block; + int n = 0; + ext4_lblk_t last_block, max_block; unsigned blocksize = inode->i_sb->s_blocksize; trace_ext4_truncate_enter(inode); @@ -4455,14 +4456,18 @@ void ext4_truncate(struct inode *inode) last_block = (inode->i_size + blocksize-1) >> EXT4_BLOCK_SIZE_BITS(inode->i_sb); + max_block = (EXT4_SB(inode->i_sb)->s_bitmap_maxbytes + blocksize-1) + >> EXT4_BLOCK_SIZE_BITS(inode->i_sb); if (inode->i_size & (blocksize - 1)) if (ext4_block_truncate_page(handle, mapping, inode->i_size)) goto out_stop; - n = ext4_block_to_path(inode, last_block, offsets, NULL); - if (n == 0) - goto out_stop; /* error */ + if (last_block != max_block) { + n = ext4_block_to_path(inode, last_block, offsets, NULL); + if (n == 0) + goto out_stop; /* error */ + } /* * OK. This truncate is going to happen. We add the inode to the @@ -4493,7 +4498,13 @@ void ext4_truncate(struct inode *inode) */ ei->i_disksize = inode->i_size; - if (n == 1) { /* direct blocks */ + if (last_block == max_block) { + /* + * It is unnecessary to free any data blocks if last_block is + * equal to the indirect block limit. + */ + goto out_unlock; + } else if (n == 1) { /* direct blocks */ ext4_free_data(handle, inode, NULL, i_data+offsets[0], i_data + EXT4_NDIR_BLOCKS); goto do_indirects; @@ -4553,6 +4564,7 @@ do_indirects: ; } +out_unlock: up_write(&ei->i_data_sem); inode->i_mtime = inode->i_ctime = ext4_current_time(inode); ext4_mark_inode_dirty(handle, inode); @@ -5398,13 +5410,12 @@ static int ext4_indirect_trans_blocks(struct inode *inode, int nrblocks, /* if nrblocks are contiguous */ if (chunk) { /* - * With N contiguous data blocks, it need at most - * N/EXT4_ADDR_PER_BLOCK(inode->i_sb) indirect blocks - * 2 dindirect blocks - * 1 tindirect block + * With N contiguous data blocks, we need at most + * N/EXT4_ADDR_PER_BLOCK(inode->i_sb) + 1 indirect blocks, + * 2 dindirect blocks, and 1 tindirect block */ - indirects = nrblocks / EXT4_ADDR_PER_BLOCK(inode->i_sb); - return indirects + 3; + return DIV_ROUND_UP(nrblocks, + EXT4_ADDR_PER_BLOCK(inode->i_sb)) + 4; } /* * if nrblocks are not contiguous, worse case, each block touch diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 056474b7b8e..8553dfb310a 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -242,27 +242,44 @@ static void ext4_put_nojournal(handle_t *handle) * journal_end calls result in the superblock being marked dirty, so * that sync() will call the filesystem's write_super callback if * appropriate. + * + * To avoid j_barrier hold in userspace when a user calls freeze(), + * ext4 prevents a new handle from being started by s_frozen, which + * is in an upper layer. */ handle_t *ext4_journal_start_sb(struct super_block *sb, int nblocks) { journal_t *journal; + handle_t *handle; if (sb->s_flags & MS_RDONLY) return ERR_PTR(-EROFS); - vfs_check_frozen(sb, SB_FREEZE_TRANS); - /* Special case here: if the journal has aborted behind our - * backs (eg. EIO in the commit thread), then we still need to - * take the FS itself readonly cleanly. */ journal = EXT4_SB(sb)->s_journal; - if (journal) { - if (is_journal_aborted(journal)) { - ext4_abort(sb, "Detected aborted journal"); - return ERR_PTR(-EROFS); - } - return jbd2_journal_start(journal, nblocks); + handle = ext4_journal_current_handle(); + + /* + * If a handle has been started, it should be allowed to + * finish, otherwise deadlock could happen between freeze + * and others(e.g. truncate) due to the restart of the + * journal handle if the filesystem is forzen and active + * handles are not stopped. + */ + if (!handle) + vfs_check_frozen(sb, SB_FREEZE_TRANS); + + if (!journal) + return ext4_get_nojournal(); + /* + * Special case here: if the journal has aborted behind our + * backs (eg. EIO in the commit thread), then we still need to + * take the FS itself readonly cleanly. + */ + if (is_journal_aborted(journal)) { + ext4_abort(sb, "Detected aborted journal"); + return ERR_PTR(-EROFS); } - return ext4_get_nojournal(); + return jbd2_journal_start(journal, nblocks); } /* @@ -2975,6 +2992,12 @@ static int ext4_register_li_request(struct super_block *sb, mutex_unlock(&ext4_li_info->li_list_mtx); sbi->s_li_request = elr; + /* + * set elr to NULL here since it has been inserted to + * the request_list and the removal and free of it is + * handled by ext4_clear_request_list from now on. + */ + elr = NULL; if (!(ext4_li_info->li_state & EXT4_LAZYINIT_RUNNING)) { ret = ext4_run_lazyinit_thread(); @@ -3385,6 +3408,10 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) get_random_bytes(&sbi->s_next_generation, sizeof(u32)); spin_lock_init(&sbi->s_next_gen_lock); + init_timer(&sbi->s_err_report); + sbi->s_err_report.function = print_daily_error_info; + sbi->s_err_report.data = (unsigned long) sb; + err = percpu_counter_init(&sbi->s_freeblocks_counter, ext4_count_free_blocks(sb)); if (!err) { @@ -3646,9 +3673,6 @@ no_journal: "Opts: %s%s%s", descr, sbi->s_es->s_mount_opts, *sbi->s_es->s_mount_opts ? "; " : "", orig_data); - init_timer(&sbi->s_err_report); - sbi->s_err_report.function = print_daily_error_info; - sbi->s_err_report.data = (unsigned long) sb; if (es->s_error_count) mod_timer(&sbi->s_err_report, jiffies + 300*HZ); /* 5 minutes */ @@ -3672,6 +3696,7 @@ failed_mount_wq: sbi->s_journal = NULL; } failed_mount3: + del_timer(&sbi->s_err_report); if (sbi->s_flex_groups) { if (is_vmalloc_addr(sbi->s_flex_groups)) vfree(sbi->s_flex_groups); @@ -4138,6 +4163,11 @@ static int ext4_sync_fs(struct super_block *sb, int wait) /* * LVM calls this function before a (read-only) snapshot is created. This * gives us a chance to flush the journal completely and mark the fs clean. + * + * Note that only this function cannot bring a filesystem to be in a clean + * state independently, because ext4 prevents a new handle from being started + * by @sb->s_frozen, which stays in an upper layer. It thus needs help from + * the upper layer. */ static int ext4_freeze(struct super_block *sb) { @@ -4614,11 +4644,24 @@ static int ext4_quota_on(struct super_block *sb, int type, int format_id, static int ext4_quota_off(struct super_block *sb, int type) { + struct inode *inode = sb_dqopt(sb)->files[type]; + handle_t *handle; + /* Force all delayed allocation blocks to be allocated. * Caller already holds s_umount sem */ if (test_opt(sb, DELALLOC)) sync_filesystem(sb); + /* Update modification times of quota files when userspace can + * start looking at them */ + handle = ext4_journal_start(inode, 1); + if (IS_ERR(handle)) + goto out; + inode->i_mtime = inode->i_ctime = CURRENT_TIME; + ext4_mark_inode_dirty(handle, inode); + ext4_journal_stop(handle); + +out: return dquot_quota_off(sb, type); } @@ -4714,9 +4757,8 @@ out: if (inode->i_size < off + len) { i_size_write(inode, off + len); EXT4_I(inode)->i_disksize = inode->i_size; + ext4_mark_inode_dirty(handle, inode); } - inode->i_mtime = inode->i_ctime = CURRENT_TIME; - ext4_mark_inode_dirty(handle, inode); mutex_unlock(&inode->i_mutex); return len; } diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c index 20af62f4304..6e28000a4b2 100644 --- a/fs/jbd2/commit.c +++ b/fs/jbd2/commit.c @@ -105,6 +105,8 @@ static int journal_submit_commit_record(journal_t *journal, int ret; struct timespec now = current_kernel_time(); + *cbh = NULL; + if (is_journal_aborted(journal)) return 0; @@ -806,7 +808,7 @@ wait_for_iobuf: if (err) __jbd2_journal_abort_hard(journal); } - if (!err && !is_journal_aborted(journal)) + if (cbh) err = journal_wait_on_commit_record(journal, cbh); if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT) && diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index aba8ebaec25..e0ec3db1c39 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -2413,10 +2413,12 @@ const char *jbd2_dev_to_name(dev_t device) new_dev = kmalloc(sizeof(struct devname_cache), GFP_KERNEL); if (!new_dev) return "NODEV-ALLOCFAILURE"; /* Something non-NULL */ + bd = bdget(device); spin_lock(&devname_cache_lock); if (devcache[i]) { if (devcache[i]->device == device) { kfree(new_dev); + bdput(bd); ret = devcache[i]->devname; spin_unlock(&devname_cache_lock); return ret; @@ -2425,7 +2427,6 @@ const char *jbd2_dev_to_name(dev_t device) } devcache[i] = new_dev; devcache[i]->device = device; - bd = bdget(device); if (bd) { bdevname(bd, devcache[i]->devname); bdput(bd); diff --git a/fs/namespace.c b/fs/namespace.c index 7dba2ed0342..d99bcf59e4c 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -1030,18 +1030,6 @@ const struct seq_operations mounts_op = { .show = show_vfsmnt }; -static int uuid_is_nil(u8 *uuid) -{ - int i; - u8 *cp = (u8 *)uuid; - - for (i = 0; i < 16; i++) { - if (*cp++) - return 0; - } - return 1; -} - static int show_mountinfo(struct seq_file *m, void *v) { struct proc_mounts *p = m->private; @@ -1085,10 +1073,6 @@ static int show_mountinfo(struct seq_file *m, void *v) if (IS_MNT_UNBINDABLE(mnt)) seq_puts(m, " unbindable"); - if (!uuid_is_nil(mnt->mnt_sb->s_uuid)) - /* print the uuid */ - seq_printf(m, " uuid:%pU", mnt->mnt_sb->s_uuid); - /* Filesystem specific data */ seq_puts(m, " - "); show_type(m, sb); diff --git a/fs/nfs/write.c b/fs/nfs/write.c index af0c6279a4a..e4cbc11a74a 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -542,11 +542,15 @@ nfs_scan_commit(struct inode *inode, struct list_head *dst, pgoff_t idx_start, u if (!nfs_need_commit(nfsi)) return 0; + spin_lock(&inode->i_lock); ret = nfs_scan_list(nfsi, dst, idx_start, npages, NFS_PAGE_TAG_COMMIT); if (ret > 0) nfsi->ncommit -= ret; + spin_unlock(&inode->i_lock); + if (nfs_need_commit(NFS_I(inode))) __mark_inode_dirty(inode, I_DIRTY_DATASYNC); + return ret; } #else @@ -1483,9 +1487,7 @@ int nfs_commit_inode(struct inode *inode, int how) res = nfs_commit_set_lock(NFS_I(inode), may_wait); if (res <= 0) goto out_mark_dirty; - spin_lock(&inode->i_lock); res = nfs_scan_commit(inode, &head, 0, 0); - spin_unlock(&inode->i_lock); if (res) { int error; diff --git a/fs/nfsd/lockd.c b/fs/nfsd/lockd.c index 0c6d8167013..7c831a2731f 100644 --- a/fs/nfsd/lockd.c +++ b/fs/nfsd/lockd.c @@ -38,7 +38,6 @@ nlm_fopen(struct svc_rqst *rqstp, struct nfs_fh *f, struct file **filp) exp_readlock(); nfserr = nfsd_open(rqstp, &fh, S_IFREG, NFSD_MAY_LOCK, filp); fh_put(&fh); - rqstp->rq_client = NULL; exp_readunlock(); /* We return nlm error codes as nlm doesn't know * about nfsd, but nfsd does know about nlm.. diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 4b36ec3eb8e..aa309aa93fe 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -397,10 +397,13 @@ static void unhash_generic_stateid(struct nfs4_stateid *stp) static void free_generic_stateid(struct nfs4_stateid *stp) { - int oflag = nfs4_access_bmap_to_omode(stp); + int oflag; - nfs4_file_put_access(stp->st_file, oflag); - put_nfs4_file(stp->st_file); + if (stp->st_access_bmap) { + oflag = nfs4_access_bmap_to_omode(stp); + nfs4_file_put_access(stp->st_file, oflag); + put_nfs4_file(stp->st_file); + } kmem_cache_free(stateid_slab, stp); } diff --git a/fs/xfs/linux-2.6/xfs_buf.c b/fs/xfs/linux-2.6/xfs_buf.c index 5ea402023eb..9ef9ed2cfe2 100644 --- a/fs/xfs/linux-2.6/xfs_buf.c +++ b/fs/xfs/linux-2.6/xfs_buf.c @@ -293,7 +293,6 @@ xfs_buf_allocate_memory( size_t nbytes, offset; gfp_t gfp_mask = xb_to_gfp(flags); unsigned short page_count, i; - pgoff_t first; xfs_off_t end; int error; @@ -333,7 +332,6 @@ use_alloc_page: return error; offset = bp->b_offset; - first = bp->b_file_offset >> PAGE_SHIFT; bp->b_flags |= _XBF_PAGES; for (i = 0; i < bp->b_page_count; i++) { @@ -657,8 +655,6 @@ xfs_buf_readahead( xfs_off_t ioff, size_t isize) { - struct backing_dev_info *bdi; - if (bdi_read_congested(target->bt_bdi)) return; @@ -919,8 +915,6 @@ xfs_buf_lock( if (atomic_read(&bp->b_pin_count) && (bp->b_flags & XBF_STALE)) xfs_log_force(bp->b_target->bt_mount, 0); - if (atomic_read(&bp->b_io_remaining)) - blk_flush_plug(current); down(&bp->b_sema); XB_SET_OWNER(bp); @@ -1309,8 +1303,6 @@ xfs_buf_iowait( { trace_xfs_buf_iowait(bp, _RET_IP_); - if (atomic_read(&bp->b_io_remaining)) - blk_flush_plug(current); wait_for_completion(&bp->b_iowait); trace_xfs_buf_iowait_done(bp, _RET_IP_); @@ -1747,8 +1739,8 @@ xfsbufd( do { long age = xfs_buf_age_centisecs * msecs_to_jiffies(10); long tout = xfs_buf_timer_centisecs * msecs_to_jiffies(10); - int count = 0; struct list_head tmp; + struct blk_plug plug; if (unlikely(freezing(current))) { set_bit(XBT_FORCE_SLEEP, &target->bt_flags); @@ -1764,16 +1756,15 @@ xfsbufd( xfs_buf_delwri_split(target, &tmp, age); list_sort(NULL, &tmp, xfs_buf_cmp); + + blk_start_plug(&plug); while (!list_empty(&tmp)) { struct xfs_buf *bp; bp = list_first_entry(&tmp, struct xfs_buf, b_list); list_del_init(&bp->b_list); xfs_bdstrat_cb(bp); - count++; } - if (count) - blk_flush_plug(current); - + blk_finish_plug(&plug); } while (!kthread_should_stop()); return 0; @@ -1793,6 +1784,7 @@ xfs_flush_buftarg( int pincount = 0; LIST_HEAD(tmp_list); LIST_HEAD(wait_list); + struct blk_plug plug; xfs_buf_runall_queues(xfsconvertd_workqueue); xfs_buf_runall_queues(xfsdatad_workqueue); @@ -1807,6 +1799,8 @@ xfs_flush_buftarg( * we do that after issuing all the IO. */ list_sort(NULL, &tmp_list, xfs_buf_cmp); + + blk_start_plug(&plug); while (!list_empty(&tmp_list)) { bp = list_first_entry(&tmp_list, struct xfs_buf, b_list); ASSERT(target == bp->b_target); @@ -1817,10 +1811,10 @@ xfs_flush_buftarg( } xfs_bdstrat_cb(bp); } + blk_finish_plug(&plug); if (wait) { - /* Expedite and wait for IO to complete. */ - blk_flush_plug(current); + /* Wait for IO to complete. */ while (!list_empty(&wait_list)) { bp = list_first_entry(&wait_list, struct xfs_buf, b_list); diff --git a/fs/xfs/linux-2.6/xfs_message.c b/fs/xfs/linux-2.6/xfs_message.c index 508e06fd7d1..3ca79560911 100644 --- a/fs/xfs/linux-2.6/xfs_message.c +++ b/fs/xfs/linux-2.6/xfs_message.c @@ -28,53 +28,47 @@ /* * XFS logging functions */ -static int +static void __xfs_printk( const char *level, const struct xfs_mount *mp, struct va_format *vaf) { if (mp && mp->m_fsname) - return printk("%sXFS (%s): %pV\n", level, mp->m_fsname, vaf); - return printk("%sXFS: %pV\n", level, vaf); + printk("%sXFS (%s): %pV\n", level, mp->m_fsname, vaf); + printk("%sXFS: %pV\n", level, vaf); } -int xfs_printk( +void xfs_printk( const char *level, const struct xfs_mount *mp, const char *fmt, ...) { struct va_format vaf; va_list args; - int r; va_start(args, fmt); vaf.fmt = fmt; vaf.va = &args; - r = __xfs_printk(level, mp, &vaf); + __xfs_printk(level, mp, &vaf); va_end(args); - - return r; } #define define_xfs_printk_level(func, kern_level) \ -int func(const struct xfs_mount *mp, const char *fmt, ...) \ +void func(const struct xfs_mount *mp, const char *fmt, ...) \ { \ struct va_format vaf; \ va_list args; \ - int r; \ \ va_start(args, fmt); \ \ vaf.fmt = fmt; \ vaf.va = &args; \ \ - r = __xfs_printk(kern_level, mp, &vaf); \ + __xfs_printk(kern_level, mp, &vaf); \ va_end(args); \ - \ - return r; \ } \ define_xfs_printk_level(xfs_emerg, KERN_EMERG); @@ -88,7 +82,7 @@ define_xfs_printk_level(xfs_info, KERN_INFO); define_xfs_printk_level(xfs_debug, KERN_DEBUG); #endif -int +void xfs_alert_tag( const struct xfs_mount *mp, int panic_tag, @@ -97,7 +91,6 @@ xfs_alert_tag( struct va_format vaf; va_list args; int do_panic = 0; - int r; if (xfs_panic_mask && (xfs_panic_mask & panic_tag)) { xfs_printk(KERN_ALERT, mp, @@ -110,12 +103,10 @@ xfs_alert_tag( vaf.fmt = fmt; vaf.va = &args; - r = __xfs_printk(KERN_ALERT, mp, &vaf); + __xfs_printk(KERN_ALERT, mp, &vaf); va_end(args); BUG_ON(do_panic); - - return r; } void diff --git a/fs/xfs/linux-2.6/xfs_message.h b/fs/xfs/linux-2.6/xfs_message.h index e77ffa16745..f1b3fc1b6c4 100644 --- a/fs/xfs/linux-2.6/xfs_message.h +++ b/fs/xfs/linux-2.6/xfs_message.h @@ -3,32 +3,34 @@ struct xfs_mount; -extern int xfs_printk(const char *level, const struct xfs_mount *mp, +extern void xfs_printk(const char *level, const struct xfs_mount *mp, const char *fmt, ...) __attribute__ ((format (printf, 3, 4))); -extern int xfs_emerg(const struct xfs_mount *mp, const char *fmt, ...) +extern void xfs_emerg(const struct xfs_mount *mp, const char *fmt, ...) __attribute__ ((format (printf, 2, 3))); -extern int xfs_alert(const struct xfs_mount *mp, const char *fmt, ...) +extern void xfs_alert(const struct xfs_mount *mp, const char *fmt, ...) __attribute__ ((format (printf, 2, 3))); -extern int xfs_alert_tag(const struct xfs_mount *mp, int tag, +extern void xfs_alert_tag(const struct xfs_mount *mp, int tag, const char *fmt, ...) __attribute__ ((format (printf, 3, 4))); -extern int xfs_crit(const struct xfs_mount *mp, const char *fmt, ...) +extern void xfs_crit(const struct xfs_mount *mp, const char *fmt, ...) __attribute__ ((format (printf, 2, 3))); -extern int xfs_err(const struct xfs_mount *mp, const char *fmt, ...) +extern void xfs_err(const struct xfs_mount *mp, const char *fmt, ...) __attribute__ ((format (printf, 2, 3))); -extern int xfs_warn(const struct xfs_mount *mp, const char *fmt, ...) +extern void xfs_warn(const struct xfs_mount *mp, const char *fmt, ...) __attribute__ ((format (printf, 2, 3))); -extern int xfs_notice(const struct xfs_mount *mp, const char *fmt, ...) +extern void xfs_notice(const struct xfs_mount *mp, const char *fmt, ...) __attribute__ ((format (printf, 2, 3))); -extern int xfs_info(const struct xfs_mount *mp, const char *fmt, ...) +extern void xfs_info(const struct xfs_mount *mp, const char *fmt, ...) __attribute__ ((format (printf, 2, 3))); #ifdef DEBUG -extern int xfs_debug(const struct xfs_mount *mp, const char *fmt, ...) +extern void xfs_debug(const struct xfs_mount *mp, const char *fmt, ...) __attribute__ ((format (printf, 2, 3))); #else -#define xfs_debug(mp, fmt, ...) (0) +static inline void xfs_debug(const struct xfs_mount *mp, const char *fmt, ...) +{ +} #endif extern void assfail(char *expr, char *f, int l); diff --git a/fs/xfs/linux-2.6/xfs_super.c b/fs/xfs/linux-2.6/xfs_super.c index 1ba5c451da3..b38e58d0229 100644 --- a/fs/xfs/linux-2.6/xfs_super.c +++ b/fs/xfs/linux-2.6/xfs_super.c @@ -816,75 +816,6 @@ xfs_setup_devices( return 0; } -/* - * XFS AIL push thread support - */ -void -xfsaild_wakeup( - struct xfs_ail *ailp, - xfs_lsn_t threshold_lsn) -{ - /* only ever move the target forwards */ - if (XFS_LSN_CMP(threshold_lsn, ailp->xa_target) > 0) { - ailp->xa_target = threshold_lsn; - wake_up_process(ailp->xa_task); - } -} - -STATIC int -xfsaild( - void *data) -{ - struct xfs_ail *ailp = data; - xfs_lsn_t last_pushed_lsn = 0; - long tout = 0; /* milliseconds */ - - while (!kthread_should_stop()) { - /* - * for short sleeps indicating congestion, don't allow us to - * get woken early. Otherwise all we do is bang on the AIL lock - * without making progress. - */ - if (tout && tout <= 20) - __set_current_state(TASK_KILLABLE); - else - __set_current_state(TASK_INTERRUPTIBLE); - schedule_timeout(tout ? - msecs_to_jiffies(tout) : MAX_SCHEDULE_TIMEOUT); - - /* swsusp */ - try_to_freeze(); - - ASSERT(ailp->xa_mount->m_log); - if (XFS_FORCED_SHUTDOWN(ailp->xa_mount)) - continue; - - tout = xfsaild_push(ailp, &last_pushed_lsn); - } - - return 0; -} /* xfsaild */ - -int -xfsaild_start( - struct xfs_ail *ailp) -{ - ailp->xa_target = 0; - ailp->xa_task = kthread_run(xfsaild, ailp, "xfsaild/%s", - ailp->xa_mount->m_fsname); - if (IS_ERR(ailp->xa_task)) - return -PTR_ERR(ailp->xa_task); - return 0; -} - -void -xfsaild_stop( - struct xfs_ail *ailp) -{ - kthread_stop(ailp->xa_task); -} - - /* Catch misguided souls that try to use this interface on XFS */ STATIC struct inode * xfs_fs_alloc_inode( @@ -1191,22 +1122,12 @@ xfs_fs_sync_fs( return -error; if (laptop_mode) { - int prev_sync_seq = mp->m_sync_seq; - /* * The disk must be active because we're syncing. * We schedule xfssyncd now (now that the disk is * active) instead of later (when it might not be). */ - wake_up_process(mp->m_sync_task); - /* - * We have to wait for the sync iteration to complete. - * If we don't, the disk activity caused by the sync - * will come after the sync is completed, and that - * triggers another sync from laptop mode. - */ - wait_event(mp->m_wait_single_sync_task, - mp->m_sync_seq != prev_sync_seq); + flush_delayed_work_sync(&mp->m_sync_work); } return 0; @@ -1490,9 +1411,6 @@ xfs_fs_fill_super( spin_lock_init(&mp->m_sb_lock); mutex_init(&mp->m_growlock); atomic_set(&mp->m_active_trans, 0); - INIT_LIST_HEAD(&mp->m_sync_list); - spin_lock_init(&mp->m_sync_lock); - init_waitqueue_head(&mp->m_wait_single_sync_task); mp->m_super = sb; sb->s_fs_info = mp; @@ -1799,6 +1717,38 @@ xfs_destroy_zones(void) } STATIC int __init +xfs_init_workqueues(void) +{ + /* + * max_active is set to 8 to give enough concurency to allow + * multiple work operations on each CPU to run. This allows multiple + * filesystems to be running sync work concurrently, and scales with + * the number of CPUs in the system. + */ + xfs_syncd_wq = alloc_workqueue("xfssyncd", WQ_CPU_INTENSIVE, 8); + if (!xfs_syncd_wq) + goto out; + + xfs_ail_wq = alloc_workqueue("xfsail", WQ_CPU_INTENSIVE, 8); + if (!xfs_ail_wq) + goto out_destroy_syncd; + + return 0; + +out_destroy_syncd: + destroy_workqueue(xfs_syncd_wq); +out: + return -ENOMEM; +} + +STATIC void +xfs_destroy_workqueues(void) +{ + destroy_workqueue(xfs_ail_wq); + destroy_workqueue(xfs_syncd_wq); +} + +STATIC int __init init_xfs_fs(void) { int error; @@ -1813,10 +1763,14 @@ init_xfs_fs(void) if (error) goto out; - error = xfs_mru_cache_init(); + error = xfs_init_workqueues(); if (error) goto out_destroy_zones; + error = xfs_mru_cache_init(); + if (error) + goto out_destroy_wq; + error = xfs_filestream_init(); if (error) goto out_mru_cache_uninit; @@ -1833,6 +1787,10 @@ init_xfs_fs(void) if (error) goto out_cleanup_procfs; + error = xfs_init_workqueues(); + if (error) + goto out_sysctl_unregister; + vfs_initquota(); error = register_filesystem(&xfs_fs_type); @@ -1850,6 +1808,8 @@ init_xfs_fs(void) xfs_filestream_uninit(); out_mru_cache_uninit: xfs_mru_cache_uninit(); + out_destroy_wq: + xfs_destroy_workqueues(); out_destroy_zones: xfs_destroy_zones(); out: @@ -1866,6 +1826,7 @@ exit_xfs_fs(void) xfs_buf_terminate(); xfs_filestream_uninit(); xfs_mru_cache_uninit(); + xfs_destroy_workqueues(); xfs_destroy_zones(); } diff --git a/fs/xfs/linux-2.6/xfs_sync.c b/fs/xfs/linux-2.6/xfs_sync.c index 9cf35a688f5..e4f9c1b0836 100644 --- a/fs/xfs/linux-2.6/xfs_sync.c +++ b/fs/xfs/linux-2.6/xfs_sync.c @@ -22,6 +22,7 @@ #include "xfs_log.h" #include "xfs_inum.h" #include "xfs_trans.h" +#include "xfs_trans_priv.h" #include "xfs_sb.h" #include "xfs_ag.h" #include "xfs_mount.h" @@ -39,6 +40,8 @@ #include <linux/kthread.h> #include <linux/freezer.h> +struct workqueue_struct *xfs_syncd_wq; /* sync workqueue */ + /* * The inode lookup is done in batches to keep the amount of lock traffic and * radix tree lookups to a minimum. The batch size is a trade off between @@ -431,62 +434,12 @@ xfs_quiesce_attr( xfs_unmountfs_writesb(mp); } -/* - * Enqueue a work item to be picked up by the vfs xfssyncd thread. - * Doing this has two advantages: - * - It saves on stack space, which is tight in certain situations - * - It can be used (with care) as a mechanism to avoid deadlocks. - * Flushing while allocating in a full filesystem requires both. - */ -STATIC void -xfs_syncd_queue_work( - struct xfs_mount *mp, - void *data, - void (*syncer)(struct xfs_mount *, void *), - struct completion *completion) -{ - struct xfs_sync_work *work; - - work = kmem_alloc(sizeof(struct xfs_sync_work), KM_SLEEP); - INIT_LIST_HEAD(&work->w_list); - work->w_syncer = syncer; - work->w_data = data; - work->w_mount = mp; - work->w_completion = completion; - spin_lock(&mp->m_sync_lock); - list_add_tail(&work->w_list, &mp->m_sync_list); - spin_unlock(&mp->m_sync_lock); - wake_up_process(mp->m_sync_task); -} - -/* - * Flush delayed allocate data, attempting to free up reserved space - * from existing allocations. At this point a new allocation attempt - * has failed with ENOSPC and we are in the process of scratching our - * heads, looking about for more room... - */ -STATIC void -xfs_flush_inodes_work( - struct xfs_mount *mp, - void *arg) -{ - struct inode *inode = arg; - xfs_sync_data(mp, SYNC_TRYLOCK); - xfs_sync_data(mp, SYNC_TRYLOCK | SYNC_WAIT); - iput(inode); -} - -void -xfs_flush_inodes( - xfs_inode_t *ip) +static void +xfs_syncd_queue_sync( + struct xfs_mount *mp) { - struct inode *inode = VFS_I(ip); - DECLARE_COMPLETION_ONSTACK(completion); - - igrab(inode); - xfs_syncd_queue_work(ip->i_mount, inode, xfs_flush_inodes_work, &completion); - wait_for_completion(&completion); - xfs_log_force(ip->i_mount, XFS_LOG_SYNC); + queue_delayed_work(xfs_syncd_wq, &mp->m_sync_work, + msecs_to_jiffies(xfs_syncd_centisecs * 10)); } /* @@ -496,9 +449,10 @@ xfs_flush_inodes( */ STATIC void xfs_sync_worker( - struct xfs_mount *mp, - void *unused) + struct work_struct *work) { + struct xfs_mount *mp = container_of(to_delayed_work(work), + struct xfs_mount, m_sync_work); int error; if (!(mp->m_flags & XFS_MOUNT_RDONLY)) { @@ -508,73 +462,106 @@ xfs_sync_worker( error = xfs_fs_log_dummy(mp); else xfs_log_force(mp, 0); - xfs_reclaim_inodes(mp, 0); error = xfs_qm_sync(mp, SYNC_TRYLOCK); + + /* start pushing all the metadata that is currently dirty */ + xfs_ail_push_all(mp->m_ail); } - mp->m_sync_seq++; - wake_up(&mp->m_wait_single_sync_task); + + /* queue us up again */ + xfs_syncd_queue_sync(mp); } -STATIC int -xfssyncd( - void *arg) +/* + * Queue a new inode reclaim pass if there are reclaimable inodes and there + * isn't a reclaim pass already in progress. By default it runs every 5s based + * on the xfs syncd work default of 30s. Perhaps this should have it's own + * tunable, but that can be done if this method proves to be ineffective or too + * aggressive. + */ +static void +xfs_syncd_queue_reclaim( + struct xfs_mount *mp) { - struct xfs_mount *mp = arg; - long timeleft; - xfs_sync_work_t *work, *n; - LIST_HEAD (tmp); - - set_freezable(); - timeleft = xfs_syncd_centisecs * msecs_to_jiffies(10); - for (;;) { - if (list_empty(&mp->m_sync_list)) - timeleft = schedule_timeout_interruptible(timeleft); - /* swsusp */ - try_to_freeze(); - if (kthread_should_stop() && list_empty(&mp->m_sync_list)) - break; - spin_lock(&mp->m_sync_lock); - /* - * We can get woken by laptop mode, to do a sync - - * that's the (only!) case where the list would be - * empty with time remaining. - */ - if (!timeleft || list_empty(&mp->m_sync_list)) { - if (!timeleft) - timeleft = xfs_syncd_centisecs * - msecs_to_jiffies(10); - INIT_LIST_HEAD(&mp->m_sync_work.w_list); - list_add_tail(&mp->m_sync_work.w_list, - &mp->m_sync_list); - } - list_splice_init(&mp->m_sync_list, &tmp); - spin_unlock(&mp->m_sync_lock); + /* + * We can have inodes enter reclaim after we've shut down the syncd + * workqueue during unmount, so don't allow reclaim work to be queued + * during unmount. + */ + if (!(mp->m_super->s_flags & MS_ACTIVE)) + return; - list_for_each_entry_safe(work, n, &tmp, w_list) { - (*work->w_syncer)(mp, work->w_data); - list_del(&work->w_list); - if (work == &mp->m_sync_work) - continue; - if (work->w_completion) - complete(work->w_completion); - kmem_free(work); - } + rcu_read_lock(); + if (radix_tree_tagged(&mp->m_perag_tree, XFS_ICI_RECLAIM_TAG)) { + queue_delayed_work(xfs_syncd_wq, &mp->m_reclaim_work, + msecs_to_jiffies(xfs_syncd_centisecs / 6 * 10)); } + rcu_read_unlock(); +} - return 0; +/* + * This is a fast pass over the inode cache to try to get reclaim moving on as + * many inodes as possible in a short period of time. It kicks itself every few + * seconds, as well as being kicked by the inode cache shrinker when memory + * goes low. It scans as quickly as possible avoiding locked inodes or those + * already being flushed, and once done schedules a future pass. + */ +STATIC void +xfs_reclaim_worker( + struct work_struct *work) +{ + struct xfs_mount *mp = container_of(to_delayed_work(work), + struct xfs_mount, m_reclaim_work); + + xfs_reclaim_inodes(mp, SYNC_TRYLOCK); + xfs_syncd_queue_reclaim(mp); +} + +/* + * Flush delayed allocate data, attempting to free up reserved space + * from existing allocations. At this point a new allocation attempt + * has failed with ENOSPC and we are in the process of scratching our + * heads, looking about for more room. + * + * Queue a new data flush if there isn't one already in progress and + * wait for completion of the flush. This means that we only ever have one + * inode flush in progress no matter how many ENOSPC events are occurring and + * so will prevent the system from bogging down due to every concurrent + * ENOSPC event scanning all the active inodes in the system for writeback. + */ +void +xfs_flush_inodes( + struct xfs_inode *ip) +{ + struct xfs_mount *mp = ip->i_mount; + + queue_work(xfs_syncd_wq, &mp->m_flush_work); + flush_work_sync(&mp->m_flush_work); +} + +STATIC void +xfs_flush_worker( + struct work_struct *work) +{ + struct xfs_mount *mp = container_of(work, + struct xfs_mount, m_flush_work); + + xfs_sync_data(mp, SYNC_TRYLOCK); + xfs_sync_data(mp, SYNC_TRYLOCK | SYNC_WAIT); } int xfs_syncd_init( struct xfs_mount *mp) { - mp->m_sync_work.w_syncer = xfs_sync_worker; - mp->m_sync_work.w_mount = mp; - mp->m_sync_work.w_completion = NULL; - mp->m_sync_task = kthread_run(xfssyncd, mp, "xfssyncd/%s", mp->m_fsname); - if (IS_ERR(mp->m_sync_task)) - return -PTR_ERR(mp->m_sync_task); + INIT_WORK(&mp->m_flush_work, xfs_flush_worker); + INIT_DELAYED_WORK(&mp->m_sync_work, xfs_sync_worker); + INIT_DELAYED_WORK(&mp->m_reclaim_work, xfs_reclaim_worker); + + xfs_syncd_queue_sync(mp); + xfs_syncd_queue_reclaim(mp); + return 0; } @@ -582,7 +569,9 @@ void xfs_syncd_stop( struct xfs_mount *mp) { - kthread_stop(mp->m_sync_task); + cancel_delayed_work_sync(&mp->m_sync_work); + cancel_delayed_work_sync(&mp->m_reclaim_work); + cancel_work_sync(&mp->m_flush_work); } void @@ -601,6 +590,10 @@ __xfs_inode_set_reclaim_tag( XFS_INO_TO_AGNO(ip->i_mount, ip->i_ino), XFS_ICI_RECLAIM_TAG); spin_unlock(&ip->i_mount->m_perag_lock); + + /* schedule periodic background inode reclaim */ + xfs_syncd_queue_reclaim(ip->i_mount); + trace_xfs_perag_set_reclaim(ip->i_mount, pag->pag_agno, -1, _RET_IP_); } @@ -1017,7 +1010,13 @@ xfs_reclaim_inodes( } /* - * Shrinker infrastructure. + * Inode cache shrinker. + * + * When called we make sure that there is a background (fast) inode reclaim in + * progress, while we will throttle the speed of reclaim via doiing synchronous + * reclaim of inodes. That means if we come across dirty inodes, we wait for + * them to be cleaned, which we hope will not be very long due to the + * background walker having already kicked the IO off on those dirty inodes. */ static int xfs_reclaim_inode_shrink( @@ -1032,10 +1031,15 @@ xfs_reclaim_inode_shrink( mp = container_of(shrink, struct xfs_mount, m_inode_shrink); if (nr_to_scan) { + /* kick background reclaimer and push the AIL */ + xfs_syncd_queue_reclaim(mp); + xfs_ail_push_all(mp->m_ail); + if (!(gfp_mask & __GFP_FS)) return -1; - xfs_reclaim_inodes_ag(mp, SYNC_TRYLOCK, &nr_to_scan); + xfs_reclaim_inodes_ag(mp, SYNC_TRYLOCK | SYNC_WAIT, + &nr_to_scan); /* terminate if we don't exhaust the scan */ if (nr_to_scan > 0) return -1; diff --git a/fs/xfs/linux-2.6/xfs_sync.h b/fs/xfs/linux-2.6/xfs_sync.h index 32ba6628290..e3a6ad27415 100644 --- a/fs/xfs/linux-2.6/xfs_sync.h +++ b/fs/xfs/linux-2.6/xfs_sync.h @@ -32,6 +32,8 @@ typedef struct xfs_sync_work { #define SYNC_WAIT 0x0001 /* wait for i/o to complete */ #define SYNC_TRYLOCK 0x0002 /* only try to lock inodes */ +extern struct workqueue_struct *xfs_syncd_wq; /* sync workqueue */ + int xfs_syncd_init(struct xfs_mount *mp); void xfs_syncd_stop(struct xfs_mount *mp); diff --git a/fs/xfs/quota/xfs_qm.c b/fs/xfs/quota/xfs_qm.c index 254ee062bd7..69228aa8605 100644 --- a/fs/xfs/quota/xfs_qm.c +++ b/fs/xfs/quota/xfs_qm.c @@ -461,12 +461,10 @@ xfs_qm_dqflush_all( struct xfs_quotainfo *q = mp->m_quotainfo; int recl; struct xfs_dquot *dqp; - int niters; int error; if (!q) return 0; - niters = 0; again: mutex_lock(&q->qi_dqlist_lock); list_for_each_entry(dqp, &q->qi_dqlist, q_mplist) { @@ -1314,14 +1312,9 @@ xfs_qm_dqiter_bufs( { xfs_buf_t *bp; int error; - int notcommitted; - int incr; int type; ASSERT(blkcnt > 0); - notcommitted = 0; - incr = (blkcnt > XFS_QM_MAX_DQCLUSTER_LOGSZ) ? - XFS_QM_MAX_DQCLUSTER_LOGSZ : blkcnt; type = flags & XFS_QMOPT_UQUOTA ? XFS_DQ_USER : (flags & XFS_QMOPT_PQUOTA ? XFS_DQ_PROJ : XFS_DQ_GROUP); error = 0; diff --git a/fs/xfs/quota/xfs_qm.h b/fs/xfs/quota/xfs_qm.h index c9446f1c726..567b29b9f1b 100644 --- a/fs/xfs/quota/xfs_qm.h +++ b/fs/xfs/quota/xfs_qm.h @@ -65,11 +65,6 @@ extern kmem_zone_t *qm_dqtrxzone; * block in the dquot/xqm code. */ #define XFS_DQUOT_CLUSTER_SIZE_FSB (xfs_filblks_t)1 -/* - * When doing a quotacheck, we log dquot clusters of this many FSBs at most - * in a single transaction. We don't want to ask for too huge a log reservation. - */ -#define XFS_QM_MAX_DQCLUSTER_LOGSZ 3 typedef xfs_dqhash_t xfs_dqlist_t; diff --git a/fs/xfs/quota/xfs_qm_syscalls.c b/fs/xfs/quota/xfs_qm_syscalls.c index 0d62a07b7fd..2dadb15d5ca 100644 --- a/fs/xfs/quota/xfs_qm_syscalls.c +++ b/fs/xfs/quota/xfs_qm_syscalls.c @@ -313,14 +313,12 @@ xfs_qm_scall_quotaon( { int error; uint qf; - uint accflags; __int64_t sbflags; flags &= (XFS_ALL_QUOTA_ACCT | XFS_ALL_QUOTA_ENFD); /* * Switching on quota accounting must be done at mount time. */ - accflags = flags & XFS_ALL_QUOTA_ACCT; flags &= ~(XFS_ALL_QUOTA_ACCT); sbflags = 0; diff --git a/fs/xfs/xfs_alloc.c b/fs/xfs/xfs_alloc.c index 4bc3c649aee..27d64d752ea 100644 --- a/fs/xfs/xfs_alloc.c +++ b/fs/xfs/xfs_alloc.c @@ -2395,17 +2395,33 @@ xfs_free_extent( memset(&args, 0, sizeof(xfs_alloc_arg_t)); args.tp = tp; args.mp = tp->t_mountp; + + /* + * validate that the block number is legal - the enables us to detect + * and handle a silent filesystem corruption rather than crashing. + */ args.agno = XFS_FSB_TO_AGNO(args.mp, bno); - ASSERT(args.agno < args.mp->m_sb.sb_agcount); + if (args.agno >= args.mp->m_sb.sb_agcount) + return EFSCORRUPTED; + args.agbno = XFS_FSB_TO_AGBNO(args.mp, bno); + if (args.agbno >= args.mp->m_sb.sb_agblocks) + return EFSCORRUPTED; + args.pag = xfs_perag_get(args.mp, args.agno); - if ((error = xfs_alloc_fix_freelist(&args, XFS_ALLOC_FLAG_FREEING))) + ASSERT(args.pag); + + error = xfs_alloc_fix_freelist(&args, XFS_ALLOC_FLAG_FREEING); + if (error) goto error0; -#ifdef DEBUG - ASSERT(args.agbp != NULL); - ASSERT((args.agbno + len) <= - be32_to_cpu(XFS_BUF_TO_AGF(args.agbp)->agf_length)); -#endif + + /* validate the extent size is legal now we have the agf locked */ + if (args.agbno + len > + be32_to_cpu(XFS_BUF_TO_AGF(args.agbp)->agf_length)) { + error = EFSCORRUPTED; + goto error0; + } + error = xfs_free_ag_extent(tp, args.agbp, args.agno, args.agbno, len, 0); error0: xfs_perag_put(args.pag); diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c index 46cc40131d4..576fdfe81d6 100644 --- a/fs/xfs/xfs_inode_item.c +++ b/fs/xfs/xfs_inode_item.c @@ -198,6 +198,41 @@ xfs_inode_item_size( } /* + * xfs_inode_item_format_extents - convert in-core extents to on-disk form + * + * For either the data or attr fork in extent format, we need to endian convert + * the in-core extent as we place them into the on-disk inode. In this case, we + * need to do this conversion before we write the extents into the log. Because + * we don't have the disk inode to write into here, we allocate a buffer and + * format the extents into it via xfs_iextents_copy(). We free the buffer in + * the unlock routine after the copy for the log has been made. + * + * In the case of the data fork, the in-core and on-disk fork sizes can be + * different due to delayed allocation extents. We only log on-disk extents + * here, so always use the physical fork size to determine the size of the + * buffer we need to allocate. + */ +STATIC void +xfs_inode_item_format_extents( + struct xfs_inode *ip, + struct xfs_log_iovec *vecp, + int whichfork, + int type) +{ + xfs_bmbt_rec_t *ext_buffer; + + ext_buffer = kmem_alloc(XFS_IFORK_SIZE(ip, whichfork), KM_SLEEP); + if (whichfork == XFS_DATA_FORK) + ip->i_itemp->ili_extents_buf = ext_buffer; + else + ip->i_itemp->ili_aextents_buf = ext_buffer; + + vecp->i_addr = ext_buffer; + vecp->i_len = xfs_iextents_copy(ip, ext_buffer, whichfork); + vecp->i_type = type; +} + +/* * This is called to fill in the vector of log iovecs for the * given inode log item. It fills the first item with an inode * log format structure, the second with the on-disk inode structure, @@ -213,7 +248,6 @@ xfs_inode_item_format( struct xfs_inode *ip = iip->ili_inode; uint nvecs; size_t data_bytes; - xfs_bmbt_rec_t *ext_buffer; xfs_mount_t *mp; vecp->i_addr = &iip->ili_format; @@ -320,22 +354,8 @@ xfs_inode_item_format( } else #endif { - /* - * There are delayed allocation extents - * in the inode, or we need to convert - * the extents to on disk format. - * Use xfs_iextents_copy() - * to copy only the real extents into - * a separate buffer. We'll free the - * buffer in the unlock routine. - */ - ext_buffer = kmem_alloc(ip->i_df.if_bytes, - KM_SLEEP); - iip->ili_extents_buf = ext_buffer; - vecp->i_addr = ext_buffer; - vecp->i_len = xfs_iextents_copy(ip, ext_buffer, - XFS_DATA_FORK); - vecp->i_type = XLOG_REG_TYPE_IEXT; + xfs_inode_item_format_extents(ip, vecp, + XFS_DATA_FORK, XLOG_REG_TYPE_IEXT); } ASSERT(vecp->i_len <= ip->i_df.if_bytes); iip->ili_format.ilf_dsize = vecp->i_len; @@ -445,19 +465,12 @@ xfs_inode_item_format( */ vecp->i_addr = ip->i_afp->if_u1.if_extents; vecp->i_len = ip->i_afp->if_bytes; + vecp->i_type = XLOG_REG_TYPE_IATTR_EXT; #else ASSERT(iip->ili_aextents_buf == NULL); - /* - * Need to endian flip before logging - */ - ext_buffer = kmem_alloc(ip->i_afp->if_bytes, - KM_SLEEP); - iip->ili_aextents_buf = ext_buffer; - vecp->i_addr = ext_buffer; - vecp->i_len = xfs_iextents_copy(ip, ext_buffer, - XFS_ATTR_FORK); + xfs_inode_item_format_extents(ip, vecp, + XFS_ATTR_FORK, XLOG_REG_TYPE_IATTR_EXT); #endif - vecp->i_type = XLOG_REG_TYPE_IATTR_EXT; iip->ili_format.ilf_asize = vecp->i_len; vecp++; nvecs++; diff --git a/fs/xfs/xfs_itable.c b/fs/xfs/xfs_itable.c index dc1882adaf5..751e94fe1f7 100644 --- a/fs/xfs/xfs_itable.c +++ b/fs/xfs/xfs_itable.c @@ -204,7 +204,6 @@ xfs_bulkstat( xfs_agi_t *agi; /* agi header data */ xfs_agino_t agino; /* inode # in allocation group */ xfs_agnumber_t agno; /* allocation group number */ - xfs_daddr_t bno; /* inode cluster start daddr */ int chunkidx; /* current index into inode chunk */ int clustidx; /* current index into inode cluster */ xfs_btree_cur_t *cur; /* btree cursor for ialloc btree */ @@ -463,7 +462,6 @@ xfs_bulkstat( mp->m_sb.sb_inopblog); } ino = XFS_AGINO_TO_INO(mp, agno, agino); - bno = XFS_AGB_TO_DADDR(mp, agno, agbno); /* * Skip if this inode is free. */ diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c index 25efa9b8a60..b612ce4520a 100644 --- a/fs/xfs/xfs_log.c +++ b/fs/xfs/xfs_log.c @@ -761,7 +761,7 @@ xfs_log_need_covered(xfs_mount_t *mp) break; case XLOG_STATE_COVER_NEED: case XLOG_STATE_COVER_NEED2: - if (!xfs_trans_ail_tail(log->l_ailp) && + if (!xfs_ail_min_lsn(log->l_ailp) && xlog_iclogs_empty(log)) { if (log->l_covered_state == XLOG_STATE_COVER_NEED) log->l_covered_state = XLOG_STATE_COVER_DONE; @@ -801,7 +801,7 @@ xlog_assign_tail_lsn( xfs_lsn_t tail_lsn; struct log *log = mp->m_log; - tail_lsn = xfs_trans_ail_tail(mp->m_ail); + tail_lsn = xfs_ail_min_lsn(mp->m_ail); if (!tail_lsn) tail_lsn = atomic64_read(&log->l_last_sync_lsn); @@ -1239,7 +1239,7 @@ xlog_grant_push_ail( * the filesystem is shutting down. */ if (!XLOG_FORCED_SHUTDOWN(log)) - xfs_trans_ail_push(log->l_ailp, threshold_lsn); + xfs_ail_push(log->l_ailp, threshold_lsn); } /* @@ -3407,6 +3407,17 @@ xlog_verify_dest_ptr( xfs_emerg(log->l_mp, "%s: invalid ptr", __func__); } +/* + * Check to make sure the grant write head didn't just over lap the tail. If + * the cycles are the same, we can't be overlapping. Otherwise, make sure that + * the cycles differ by exactly one and check the byte count. + * + * This check is run unlocked, so can give false positives. Rather than assert + * on failures, use a warn-once flag and a panic tag to allow the admin to + * determine if they want to panic the machine when such an error occurs. For + * debug kernels this will have the same effect as using an assert but, unlinke + * an assert, it can be turned off at runtime. + */ STATIC void xlog_verify_grant_tail( struct log *log) @@ -3414,17 +3425,22 @@ xlog_verify_grant_tail( int tail_cycle, tail_blocks; int cycle, space; - /* - * Check to make sure the grant write head didn't just over lap the - * tail. If the cycles are the same, we can't be overlapping. - * Otherwise, make sure that the cycles differ by exactly one and - * check the byte count. - */ xlog_crack_grant_head(&log->l_grant_write_head, &cycle, &space); xlog_crack_atomic_lsn(&log->l_tail_lsn, &tail_cycle, &tail_blocks); if (tail_cycle != cycle) { - ASSERT(cycle - 1 == tail_cycle); - ASSERT(space <= BBTOB(tail_blocks)); + if (cycle - 1 != tail_cycle && + !(log->l_flags & XLOG_TAIL_WARN)) { + xfs_alert_tag(log->l_mp, XFS_PTAG_LOGRES, + "%s: cycle - 1 != tail_cycle", __func__); + log->l_flags |= XLOG_TAIL_WARN; + } + + if (space > BBTOB(tail_blocks) && + !(log->l_flags & XLOG_TAIL_WARN)) { + xfs_alert_tag(log->l_mp, XFS_PTAG_LOGRES, + "%s: space > BBTOB(tail_blocks)", __func__); + log->l_flags |= XLOG_TAIL_WARN; + } } } diff --git a/fs/xfs/xfs_log_priv.h b/fs/xfs/xfs_log_priv.h index ffae692c983..5864850e9e3 100644 --- a/fs/xfs/xfs_log_priv.h +++ b/fs/xfs/xfs_log_priv.h @@ -144,6 +144,7 @@ static inline uint xlog_get_client_id(__be32 i) #define XLOG_RECOVERY_NEEDED 0x4 /* log was recovered */ #define XLOG_IO_ERROR 0x8 /* log hit an I/O error, and being shutdown */ +#define XLOG_TAIL_WARN 0x10 /* log tail verify warning issued */ #ifdef __KERNEL__ /* diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h index a62e8971539..19af0ab0d0c 100644 --- a/fs/xfs/xfs_mount.h +++ b/fs/xfs/xfs_mount.h @@ -203,12 +203,9 @@ typedef struct xfs_mount { struct mutex m_icsb_mutex; /* balancer sync lock */ #endif struct xfs_mru_cache *m_filestream; /* per-mount filestream data */ - struct task_struct *m_sync_task; /* generalised sync thread */ - xfs_sync_work_t m_sync_work; /* work item for VFS_SYNC */ - struct list_head m_sync_list; /* sync thread work item list */ - spinlock_t m_sync_lock; /* work item list lock */ - int m_sync_seq; /* sync thread generation no. */ - wait_queue_head_t m_wait_single_sync_task; + struct delayed_work m_sync_work; /* background sync work */ + struct delayed_work m_reclaim_work; /* background inode reclaim */ + struct work_struct m_flush_work; /* background inode flush */ __int64_t m_update_flags; /* sb flags we need to update on the next remount,rw */ struct shrinker m_inode_shrink; /* inode reclaim shrinker */ diff --git a/fs/xfs/xfs_trans_ail.c b/fs/xfs/xfs_trans_ail.c index 12aff9584e2..acdb92f14d5 100644 --- a/fs/xfs/xfs_trans_ail.c +++ b/fs/xfs/xfs_trans_ail.c @@ -28,74 +28,138 @@ #include "xfs_trans_priv.h" #include "xfs_error.h" -STATIC void xfs_ail_splice(struct xfs_ail *, struct list_head *, xfs_lsn_t); -STATIC void xfs_ail_delete(struct xfs_ail *, xfs_log_item_t *); -STATIC xfs_log_item_t * xfs_ail_min(struct xfs_ail *); -STATIC xfs_log_item_t * xfs_ail_next(struct xfs_ail *, xfs_log_item_t *); +struct workqueue_struct *xfs_ail_wq; /* AIL workqueue */ #ifdef DEBUG -STATIC void xfs_ail_check(struct xfs_ail *, xfs_log_item_t *); -#else +/* + * Check that the list is sorted as it should be. + */ +STATIC void +xfs_ail_check( + struct xfs_ail *ailp, + xfs_log_item_t *lip) +{ + xfs_log_item_t *prev_lip; + + if (list_empty(&ailp->xa_ail)) + return; + + /* + * Check the next and previous entries are valid. + */ + ASSERT((lip->li_flags & XFS_LI_IN_AIL) != 0); + prev_lip = list_entry(lip->li_ail.prev, xfs_log_item_t, li_ail); + if (&prev_lip->li_ail != &ailp->xa_ail) + ASSERT(XFS_LSN_CMP(prev_lip->li_lsn, lip->li_lsn) <= 0); + + prev_lip = list_entry(lip->li_ail.next, xfs_log_item_t, li_ail); + if (&prev_lip->li_ail != &ailp->xa_ail) + ASSERT(XFS_LSN_CMP(prev_lip->li_lsn, lip->li_lsn) >= 0); + + +#ifdef XFS_TRANS_DEBUG + /* + * Walk the list checking lsn ordering, and that every entry has the + * XFS_LI_IN_AIL flag set. This is really expensive, so only do it + * when specifically debugging the transaction subsystem. + */ + prev_lip = list_entry(&ailp->xa_ail, xfs_log_item_t, li_ail); + list_for_each_entry(lip, &ailp->xa_ail, li_ail) { + if (&prev_lip->li_ail != &ailp->xa_ail) + ASSERT(XFS_LSN_CMP(prev_lip->li_lsn, lip->li_lsn) <= 0); + ASSERT((lip->li_flags & XFS_LI_IN_AIL) != 0); + prev_lip = lip; + } +#endif /* XFS_TRANS_DEBUG */ +} +#else /* !DEBUG */ #define xfs_ail_check(a,l) #endif /* DEBUG */ +/* + * Return a pointer to the first item in the AIL. If the AIL is empty, then + * return NULL. + */ +static xfs_log_item_t * +xfs_ail_min( + struct xfs_ail *ailp) +{ + if (list_empty(&ailp->xa_ail)) + return NULL; + + return list_first_entry(&ailp->xa_ail, xfs_log_item_t, li_ail); +} + + /* + * Return a pointer to the last item in the AIL. If the AIL is empty, then + * return NULL. + */ +static xfs_log_item_t * +xfs_ail_max( + struct xfs_ail *ailp) +{ + if (list_empty(&ailp->xa_ail)) + return NULL; + + return list_entry(ailp->xa_ail.prev, xfs_log_item_t, li_ail); +} + +/* + * Return a pointer to the item which follows the given item in the AIL. If + * the given item is the last item in the list, then return NULL. + */ +static xfs_log_item_t * +xfs_ail_next( + struct xfs_ail *ailp, + xfs_log_item_t *lip) +{ + if (lip->li_ail.next == &ailp->xa_ail) + return NULL; + + return list_first_entry(&lip->li_ail, xfs_log_item_t, li_ail); +} /* - * This is called by the log manager code to determine the LSN - * of the tail of the log. This is exactly the LSN of the first - * item in the AIL. If the AIL is empty, then this function - * returns 0. + * This is called by the log manager code to determine the LSN of the tail of + * the log. This is exactly the LSN of the first item in the AIL. If the AIL + * is empty, then this function returns 0. * - * We need the AIL lock in order to get a coherent read of the - * lsn of the last item in the AIL. + * We need the AIL lock in order to get a coherent read of the lsn of the last + * item in the AIL. */ xfs_lsn_t -xfs_trans_ail_tail( +xfs_ail_min_lsn( struct xfs_ail *ailp) { - xfs_lsn_t lsn; + xfs_lsn_t lsn = 0; xfs_log_item_t *lip; spin_lock(&ailp->xa_lock); lip = xfs_ail_min(ailp); - if (lip == NULL) { - lsn = (xfs_lsn_t)0; - } else { + if (lip) lsn = lip->li_lsn; - } spin_unlock(&ailp->xa_lock); return lsn; } /* - * xfs_trans_push_ail - * - * This routine is called to move the tail of the AIL forward. It does this by - * trying to flush items in the AIL whose lsns are below the given - * threshold_lsn. - * - * the push is run asynchronously in a separate thread, so we return the tail - * of the log right now instead of the tail after the push. This means we will - * either continue right away, or we will sleep waiting on the async thread to - * do its work. - * - * We do this unlocked - we only need to know whether there is anything in the - * AIL at the time we are called. We don't need to access the contents of - * any of the objects, so the lock is not needed. + * Return the maximum lsn held in the AIL, or zero if the AIL is empty. */ -void -xfs_trans_ail_push( - struct xfs_ail *ailp, - xfs_lsn_t threshold_lsn) +static xfs_lsn_t +xfs_ail_max_lsn( + struct xfs_ail *ailp) { - xfs_log_item_t *lip; + xfs_lsn_t lsn = 0; + xfs_log_item_t *lip; - lip = xfs_ail_min(ailp); - if (lip && !XFS_FORCED_SHUTDOWN(ailp->xa_mount)) { - if (XFS_LSN_CMP(threshold_lsn, ailp->xa_target) > 0) - xfsaild_wakeup(ailp, threshold_lsn); - } + spin_lock(&ailp->xa_lock); + lip = xfs_ail_max(ailp); + if (lip) + lsn = lip->li_lsn; + spin_unlock(&ailp->xa_lock); + + return lsn; } /* @@ -236,16 +300,57 @@ out: } /* - * xfsaild_push does the work of pushing on the AIL. Returning a timeout of - * zero indicates that the caller should sleep until woken. + * splice the log item list into the AIL at the given LSN. */ -long -xfsaild_push( - struct xfs_ail *ailp, - xfs_lsn_t *last_lsn) +static void +xfs_ail_splice( + struct xfs_ail *ailp, + struct list_head *list, + xfs_lsn_t lsn) { - long tout = 0; - xfs_lsn_t last_pushed_lsn = *last_lsn; + xfs_log_item_t *next_lip; + + /* If the list is empty, just insert the item. */ + if (list_empty(&ailp->xa_ail)) { + list_splice(list, &ailp->xa_ail); + return; + } + + list_for_each_entry_reverse(next_lip, &ailp->xa_ail, li_ail) { + if (XFS_LSN_CMP(next_lip->li_lsn, lsn) <= 0) + break; + } + + ASSERT(&next_lip->li_ail == &ailp->xa_ail || + XFS_LSN_CMP(next_lip->li_lsn, lsn) <= 0); + + list_splice_init(list, &next_lip->li_ail); +} + +/* + * Delete the given item from the AIL. Return a pointer to the item. + */ +static void +xfs_ail_delete( + struct xfs_ail *ailp, + xfs_log_item_t *lip) +{ + xfs_ail_check(ailp, lip); + list_del(&lip->li_ail); + xfs_trans_ail_cursor_clear(ailp, lip); +} + +/* + * xfs_ail_worker does the work of pushing on the AIL. It will requeue itself + * to run at a later time if there is more work to do to complete the push. + */ +STATIC void +xfs_ail_worker( + struct work_struct *work) +{ + struct xfs_ail *ailp = container_of(to_delayed_work(work), + struct xfs_ail, xa_work); + long tout; xfs_lsn_t target = ailp->xa_target; xfs_lsn_t lsn; xfs_log_item_t *lip; @@ -256,15 +361,15 @@ xfsaild_push( spin_lock(&ailp->xa_lock); xfs_trans_ail_cursor_init(ailp, cur); - lip = xfs_trans_ail_cursor_first(ailp, cur, *last_lsn); + lip = xfs_trans_ail_cursor_first(ailp, cur, ailp->xa_last_pushed_lsn); if (!lip || XFS_FORCED_SHUTDOWN(mp)) { /* * AIL is empty or our push has reached the end. */ xfs_trans_ail_cursor_done(ailp, cur); spin_unlock(&ailp->xa_lock); - *last_lsn = 0; - return tout; + ailp->xa_last_pushed_lsn = 0; + return; } XFS_STATS_INC(xs_push_ail); @@ -301,13 +406,13 @@ xfsaild_push( case XFS_ITEM_SUCCESS: XFS_STATS_INC(xs_push_ail_success); IOP_PUSH(lip); - last_pushed_lsn = lsn; + ailp->xa_last_pushed_lsn = lsn; break; case XFS_ITEM_PUSHBUF: XFS_STATS_INC(xs_push_ail_pushbuf); IOP_PUSHBUF(lip); - last_pushed_lsn = lsn; + ailp->xa_last_pushed_lsn = lsn; push_xfsbufd = 1; break; @@ -319,7 +424,7 @@ xfsaild_push( case XFS_ITEM_LOCKED: XFS_STATS_INC(xs_push_ail_locked); - last_pushed_lsn = lsn; + ailp->xa_last_pushed_lsn = lsn; stuck++; break; @@ -374,9 +479,23 @@ xfsaild_push( wake_up_process(mp->m_ddev_targp->bt_task); } + /* assume we have more work to do in a short while */ + tout = 10; if (!count) { /* We're past our target or empty, so idle */ - last_pushed_lsn = 0; + ailp->xa_last_pushed_lsn = 0; + + /* + * Check for an updated push target before clearing the + * XFS_AIL_PUSHING_BIT. If the target changed, we've got more + * work to do. Wait a bit longer before starting that work. + */ + smp_rmb(); + if (ailp->xa_target == target) { + clear_bit(XFS_AIL_PUSHING_BIT, &ailp->xa_flags); + return; + } + tout = 50; } else if (XFS_LSN_CMP(lsn, target) >= 0) { /* * We reached the target so wait a bit longer for I/O to @@ -384,7 +503,7 @@ xfsaild_push( * start the next scan from the start of the AIL. */ tout = 50; - last_pushed_lsn = 0; + ailp->xa_last_pushed_lsn = 0; } else if ((stuck * 100) / count > 90) { /* * Either there is a lot of contention on the AIL or we @@ -396,14 +515,61 @@ xfsaild_push( * continuing from where we were. */ tout = 20; - } else { - /* more to do, but wait a short while before continuing */ - tout = 10; } - *last_lsn = last_pushed_lsn; - return tout; + + /* There is more to do, requeue us. */ + queue_delayed_work(xfs_syncd_wq, &ailp->xa_work, + msecs_to_jiffies(tout)); +} + +/* + * This routine is called to move the tail of the AIL forward. It does this by + * trying to flush items in the AIL whose lsns are below the given + * threshold_lsn. + * + * The push is run asynchronously in a workqueue, which means the caller needs + * to handle waiting on the async flush for space to become available. + * We don't want to interrupt any push that is in progress, hence we only queue + * work if we set the pushing bit approriately. + * + * We do this unlocked - we only need to know whether there is anything in the + * AIL at the time we are called. We don't need to access the contents of + * any of the objects, so the lock is not needed. + */ +void +xfs_ail_push( + struct xfs_ail *ailp, + xfs_lsn_t threshold_lsn) +{ + xfs_log_item_t *lip; + + lip = xfs_ail_min(ailp); + if (!lip || XFS_FORCED_SHUTDOWN(ailp->xa_mount) || + XFS_LSN_CMP(threshold_lsn, ailp->xa_target) <= 0) + return; + + /* + * Ensure that the new target is noticed in push code before it clears + * the XFS_AIL_PUSHING_BIT. + */ + smp_wmb(); + ailp->xa_target = threshold_lsn; + if (!test_and_set_bit(XFS_AIL_PUSHING_BIT, &ailp->xa_flags)) + queue_delayed_work(xfs_syncd_wq, &ailp->xa_work, 0); } +/* + * Push out all items in the AIL immediately + */ +void +xfs_ail_push_all( + struct xfs_ail *ailp) +{ + xfs_lsn_t threshold_lsn = xfs_ail_max_lsn(ailp); + + if (threshold_lsn) + xfs_ail_push(ailp, threshold_lsn); +} /* * This is to be called when an item is unlocked that may have @@ -615,7 +781,6 @@ xfs_trans_ail_init( xfs_mount_t *mp) { struct xfs_ail *ailp; - int error; ailp = kmem_zalloc(sizeof(struct xfs_ail), KM_MAYFAIL); if (!ailp) @@ -624,15 +789,9 @@ xfs_trans_ail_init( ailp->xa_mount = mp; INIT_LIST_HEAD(&ailp->xa_ail); spin_lock_init(&ailp->xa_lock); - error = xfsaild_start(ailp); - if (error) - goto out_free_ailp; + INIT_DELAYED_WORK(&ailp->xa_work, xfs_ail_worker); mp->m_ail = ailp; return 0; - -out_free_ailp: - kmem_free(ailp); - return error; } void @@ -641,124 +800,6 @@ xfs_trans_ail_destroy( { struct xfs_ail *ailp = mp->m_ail; - xfsaild_stop(ailp); + cancel_delayed_work_sync(&ailp->xa_work); kmem_free(ailp); } - -/* - * splice the log item list into the AIL at the given LSN. - */ -STATIC void -xfs_ail_splice( - struct xfs_ail *ailp, - struct list_head *list, - xfs_lsn_t lsn) -{ - xfs_log_item_t *next_lip; - - /* - * If the list is empty, just insert the item. - */ - if (list_empty(&ailp->xa_ail)) { - list_splice(list, &ailp->xa_ail); - return; - } - - list_for_each_entry_reverse(next_lip, &ailp->xa_ail, li_ail) { - if (XFS_LSN_CMP(next_lip->li_lsn, lsn) <= 0) - break; - } - - ASSERT((&next_lip->li_ail == &ailp->xa_ail) || - (XFS_LSN_CMP(next_lip->li_lsn, lsn) <= 0)); - - list_splice_init(list, &next_lip->li_ail); - return; -} - -/* - * Delete the given item from the AIL. Return a pointer to the item. - */ -STATIC void -xfs_ail_delete( - struct xfs_ail *ailp, - xfs_log_item_t *lip) -{ - xfs_ail_check(ailp, lip); - list_del(&lip->li_ail); - xfs_trans_ail_cursor_clear(ailp, lip); -} - -/* - * Return a pointer to the first item in the AIL. - * If the AIL is empty, then return NULL. - */ -STATIC xfs_log_item_t * -xfs_ail_min( - struct xfs_ail *ailp) -{ - if (list_empty(&ailp->xa_ail)) - return NULL; - - return list_first_entry(&ailp->xa_ail, xfs_log_item_t, li_ail); -} - -/* - * Return a pointer to the item which follows - * the given item in the AIL. If the given item - * is the last item in the list, then return NULL. - */ -STATIC xfs_log_item_t * -xfs_ail_next( - struct xfs_ail *ailp, - xfs_log_item_t *lip) -{ - if (lip->li_ail.next == &ailp->xa_ail) - return NULL; - - return list_first_entry(&lip->li_ail, xfs_log_item_t, li_ail); -} - -#ifdef DEBUG -/* - * Check that the list is sorted as it should be. - */ -STATIC void -xfs_ail_check( - struct xfs_ail *ailp, - xfs_log_item_t *lip) -{ - xfs_log_item_t *prev_lip; - - if (list_empty(&ailp->xa_ail)) - return; - - /* - * Check the next and previous entries are valid. - */ - ASSERT((lip->li_flags & XFS_LI_IN_AIL) != 0); - prev_lip = list_entry(lip->li_ail.prev, xfs_log_item_t, li_ail); - if (&prev_lip->li_ail != &ailp->xa_ail) - ASSERT(XFS_LSN_CMP(prev_lip->li_lsn, lip->li_lsn) <= 0); - - prev_lip = list_entry(lip->li_ail.next, xfs_log_item_t, li_ail); - if (&prev_lip->li_ail != &ailp->xa_ail) - ASSERT(XFS_LSN_CMP(prev_lip->li_lsn, lip->li_lsn) >= 0); - - -#ifdef XFS_TRANS_DEBUG - /* - * Walk the list checking lsn ordering, and that every entry has the - * XFS_LI_IN_AIL flag set. This is really expensive, so only do it - * when specifically debugging the transaction subsystem. - */ - prev_lip = list_entry(&ailp->xa_ail, xfs_log_item_t, li_ail); - list_for_each_entry(lip, &ailp->xa_ail, li_ail) { - if (&prev_lip->li_ail != &ailp->xa_ail) - ASSERT(XFS_LSN_CMP(prev_lip->li_lsn, lip->li_lsn) <= 0); - ASSERT((lip->li_flags & XFS_LI_IN_AIL) != 0); - prev_lip = lip; - } -#endif /* XFS_TRANS_DEBUG */ -} -#endif /* DEBUG */ diff --git a/fs/xfs/xfs_trans_priv.h b/fs/xfs/xfs_trans_priv.h index 35162c238fa..6b164e9e9a1 100644 --- a/fs/xfs/xfs_trans_priv.h +++ b/fs/xfs/xfs_trans_priv.h @@ -65,16 +65,22 @@ struct xfs_ail_cursor { struct xfs_ail { struct xfs_mount *xa_mount; struct list_head xa_ail; - uint xa_gen; - struct task_struct *xa_task; xfs_lsn_t xa_target; struct xfs_ail_cursor xa_cursors; spinlock_t xa_lock; + struct delayed_work xa_work; + xfs_lsn_t xa_last_pushed_lsn; + unsigned long xa_flags; }; +#define XFS_AIL_PUSHING_BIT 0 + /* * From xfs_trans_ail.c */ + +extern struct workqueue_struct *xfs_ail_wq; /* AIL workqueue */ + void xfs_trans_ail_update_bulk(struct xfs_ail *ailp, struct xfs_log_item **log_items, int nr_items, xfs_lsn_t lsn) __releases(ailp->xa_lock); @@ -98,12 +104,13 @@ xfs_trans_ail_delete( xfs_trans_ail_delete_bulk(ailp, &lip, 1); } -void xfs_trans_ail_push(struct xfs_ail *, xfs_lsn_t); +void xfs_ail_push(struct xfs_ail *, xfs_lsn_t); +void xfs_ail_push_all(struct xfs_ail *); +xfs_lsn_t xfs_ail_min_lsn(struct xfs_ail *ailp); + void xfs_trans_unlocked_item(struct xfs_ail *, xfs_log_item_t *); -xfs_lsn_t xfs_trans_ail_tail(struct xfs_ail *ailp); - struct xfs_log_item *xfs_trans_ail_cursor_first(struct xfs_ail *ailp, struct xfs_ail_cursor *cur, xfs_lsn_t lsn); @@ -112,11 +119,6 @@ struct xfs_log_item *xfs_trans_ail_cursor_next(struct xfs_ail *ailp, void xfs_trans_ail_cursor_done(struct xfs_ail *ailp, struct xfs_ail_cursor *cur); -long xfsaild_push(struct xfs_ail *, xfs_lsn_t *); -void xfsaild_wakeup(struct xfs_ail *, xfs_lsn_t); -int xfsaild_start(struct xfs_ail *); -void xfsaild_stop(struct xfs_ail *); - #if BITS_PER_LONG != 64 static inline void xfs_trans_ail_copy_lsn( diff --git a/include/linux/mfd/core.h b/include/linux/mfd/core.h index ad1b19aa650..aef23309a74 100644 --- a/include/linux/mfd/core.h +++ b/include/linux/mfd/core.h @@ -86,16 +86,25 @@ extern int mfd_clone_cell(const char *cell, const char **clones, */ static inline const struct mfd_cell *mfd_get_cell(struct platform_device *pdev) { - return pdev->dev.platform_data; + return pdev->mfd_cell; } /* * Given a platform device that's been created by mfd_add_devices(), fetch * the .mfd_data entry from the mfd_cell that created it. + * Otherwise just return the platform_data pointer. + * This maintains compatibility with platform drivers whose devices aren't + * created by the mfd layer, and expect platform_data to contain what would've + * otherwise been in mfd_data. */ static inline void *mfd_get_data(struct platform_device *pdev) { - return mfd_get_cell(pdev)->mfd_data; + const struct mfd_cell *cell = mfd_get_cell(pdev); + + if (cell) + return cell->mfd_data; + else + return pdev->dev.platform_data; } extern int mfd_add_devices(struct device *parent, int id, diff --git a/include/linux/platform_device.h b/include/linux/platform_device.h index d96db982570..744942c95fe 100644 --- a/include/linux/platform_device.h +++ b/include/linux/platform_device.h @@ -14,6 +14,8 @@ #include <linux/device.h> #include <linux/mod_devicetable.h> +struct mfd_cell; + struct platform_device { const char * name; int id; @@ -23,6 +25,9 @@ struct platform_device { const struct platform_device_id *id_entry; + /* MFD cell pointer */ + struct mfd_cell *mfd_cell; + /* arch specific additions */ struct pdev_archdata archdata; }; diff --git a/mm/memory.c b/mm/memory.c index 9da8cab1b1b..b623a249918 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1410,6 +1410,13 @@ no_page_table: return page; } +static inline int stack_guard_page(struct vm_area_struct *vma, unsigned long addr) +{ + return (vma->vm_flags & VM_GROWSDOWN) && + (vma->vm_start == addr) && + !vma_stack_continue(vma->vm_prev, addr); +} + /** * __get_user_pages() - pin user pages in memory * @tsk: task_struct of target task @@ -1488,7 +1495,6 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, vma = find_extend_vma(mm, start); if (!vma && in_gate_area(mm, start)) { unsigned long pg = start & PAGE_MASK; - struct vm_area_struct *gate_vma = get_gate_vma(mm); pgd_t *pgd; pud_t *pud; pmd_t *pmd; @@ -1513,10 +1519,11 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, pte_unmap(pte); return i ? : -EFAULT; } + vma = get_gate_vma(mm); if (pages) { struct page *page; - page = vm_normal_page(gate_vma, start, *pte); + page = vm_normal_page(vma, start, *pte); if (!page) { if (!(gup_flags & FOLL_DUMP) && is_zero_pfn(pte_pfn(*pte))) @@ -1530,12 +1537,7 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, get_page(page); } pte_unmap(pte); - if (vmas) - vmas[i] = gate_vma; - i++; - start += PAGE_SIZE; - nr_pages--; - continue; + goto next_page; } if (!vma || @@ -1549,6 +1551,13 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, continue; } + /* + * If we don't actually want the page itself, + * and it's the stack guard page, just skip it. + */ + if (!pages && stack_guard_page(vma, start)) + goto next_page; + do { struct page *page; unsigned int foll_flags = gup_flags; @@ -1631,6 +1640,7 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, flush_anon_page(vma, page, start); flush_dcache_page(page); } +next_page: if (vmas) vmas[i] = vma; i++; diff --git a/mm/mlock.c b/mm/mlock.c index 2689a08c79a..6b55e3efe0d 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -135,13 +135,6 @@ void munlock_vma_page(struct page *page) } } -static inline int stack_guard_page(struct vm_area_struct *vma, unsigned long addr) -{ - return (vma->vm_flags & VM_GROWSDOWN) && - (vma->vm_start == addr) && - !vma_stack_continue(vma->vm_prev, addr); -} - /** * __mlock_vma_pages_range() - mlock a range of pages in the vma. * @vma: target vma @@ -188,12 +181,6 @@ static long __mlock_vma_pages_range(struct vm_area_struct *vma, if (vma->vm_flags & VM_LOCKED) gup_flags |= FOLL_MLOCK; - /* We don't try to access the guard page of a stack vma */ - if (stack_guard_page(vma, start)) { - addr += PAGE_SIZE; - nr_pages--; - } - return __get_user_pages(current, mm, addr, nr_pages, gup_flags, NULL, NULL, nonblocking); } |