diff --git a/Makefile b/Makefile index 40d1e3b..80bb4fd 100644 --- a/Makefile +++ b/Makefile @@ -1,6 +1,6 @@ VERSION = 3 PATCHLEVEL = 2 -SUBLEVEL = 23 +SUBLEVEL = 24 EXTRAVERSION = NAME = Saber-toothed Squirrel diff --git a/arch/arm/plat-samsung/adc.c b/arch/arm/plat-samsung/adc.c index 33ecd0c..b1e05cc 100644 --- a/arch/arm/plat-samsung/adc.c +++ b/arch/arm/plat-samsung/adc.c @@ -157,11 +157,13 @@ int s3c_adc_start(struct s3c_adc_client *client, return -EINVAL; } - if (client->is_ts && adc->ts_pend) - return -EAGAIN; - spin_lock_irqsave(&adc->lock, flags); + if (client->is_ts && adc->ts_pend) { + spin_unlock_irqrestore(&adc->lock, flags); + return -EAGAIN; + } + client->channel = channel; client->nr_samples = nr_samples; diff --git a/arch/mips/include/asm/thread_info.h b/arch/mips/include/asm/thread_info.h index 97f8bf6..adda036 100644 --- a/arch/mips/include/asm/thread_info.h +++ b/arch/mips/include/asm/thread_info.h @@ -60,6 +60,8 @@ struct thread_info { register struct thread_info *__current_thread_info __asm__("$28"); #define current_thread_info() __current_thread_info +#endif /* !__ASSEMBLY__ */ + /* thread information allocation */ #if defined(CONFIG_PAGE_SIZE_4KB) && defined(CONFIG_32BIT) #define THREAD_SIZE_ORDER (1) @@ -97,8 +99,6 @@ register struct thread_info *__current_thread_info __asm__("$28"); #define free_thread_info(info) kfree(info) -#endif /* !__ASSEMBLY__ */ - #define PREEMPT_ACTIVE 0x10000000 /* diff --git a/arch/mips/kernel/vmlinux.lds.S b/arch/mips/kernel/vmlinux.lds.S index a81176f..be281c6 100644 --- a/arch/mips/kernel/vmlinux.lds.S +++ b/arch/mips/kernel/vmlinux.lds.S @@ -1,5 +1,6 @@ #include #include +#include #include #undef mips @@ -73,7 +74,7 @@ SECTIONS .data : { /* Data */ . = . + DATAOFFSET; /* for CONFIG_MAPPED_KERNEL */ - INIT_TASK_DATA(PAGE_SIZE) + INIT_TASK_DATA(THREAD_SIZE) NOSAVE_DATA CACHELINE_ALIGNED_DATA(1 << CONFIG_MIPS_L1_CACHE_SHIFT) READ_MOSTLY_DATA(1 << CONFIG_MIPS_L1_CACHE_SHIFT) diff --git a/arch/powerpc/include/asm/cputime.h b/arch/powerpc/include/asm/cputime.h index 98b7c4b..fa3f921 100644 --- a/arch/powerpc/include/asm/cputime.h +++ b/arch/powerpc/include/asm/cputime.h @@ -126,11 +126,11 @@ static inline u64 cputime64_to_jiffies64(const cputime_t ct) /* * Convert cputime <-> microseconds */ -extern u64 __cputime_msec_factor; +extern u64 __cputime_usec_factor; static inline unsigned long cputime_to_usecs(const cputime_t ct) { - return mulhdu(ct, __cputime_msec_factor) * USEC_PER_MSEC; + return mulhdu(ct, __cputime_usec_factor); } static inline cputime_t usecs_to_cputime(const unsigned long us) @@ -143,7 +143,7 @@ static inline cputime_t usecs_to_cputime(const unsigned long us) sec = us / 1000000; if (ct) { ct *= tb_ticks_per_sec; - do_div(ct, 1000); + do_div(ct, 1000000); } if (sec) ct += (cputime_t) sec * tb_ticks_per_sec; diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index 5db163c..ec8affe 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -168,13 +168,13 @@ EXPORT_SYMBOL_GPL(ppc_tb_freq); #ifdef CONFIG_VIRT_CPU_ACCOUNTING /* * Factors for converting from cputime_t (timebase ticks) to - * jiffies, milliseconds, seconds, and clock_t (1/USER_HZ seconds). + * jiffies, microseconds, seconds, and clock_t (1/USER_HZ seconds). * These are all stored as 0.64 fixed-point binary fractions. */ u64 __cputime_jiffies_factor; EXPORT_SYMBOL(__cputime_jiffies_factor); -u64 __cputime_msec_factor; -EXPORT_SYMBOL(__cputime_msec_factor); +u64 __cputime_usec_factor; +EXPORT_SYMBOL(__cputime_usec_factor); u64 __cputime_sec_factor; EXPORT_SYMBOL(__cputime_sec_factor); u64 __cputime_clockt_factor; @@ -192,8 +192,8 @@ static void calc_cputime_factors(void) div128_by_32(HZ, 0, tb_ticks_per_sec, &res); __cputime_jiffies_factor = res.result_low; - div128_by_32(1000, 0, tb_ticks_per_sec, &res); - __cputime_msec_factor = res.result_low; + div128_by_32(1000000, 0, tb_ticks_per_sec, &res); + __cputime_usec_factor = res.result_low; div128_by_32(1, 0, tb_ticks_per_sec, &res); __cputime_sec_factor = res.result_low; div128_by_32(USER_HZ, 0, tb_ticks_per_sec, &res); diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 4558f0d..479d03c 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -416,12 +416,14 @@ acpi_parse_int_src_ovr(struct acpi_subtable_header * header, return 0; } - if (intsrc->source_irq == 0 && intsrc->global_irq == 2) { + if (intsrc->source_irq == 0) { if (acpi_skip_timer_override) { - printk(PREFIX "BIOS IRQ0 pin2 override ignored.\n"); + printk(PREFIX "BIOS IRQ0 override ignored.\n"); return 0; } - if (acpi_fix_pin2_polarity && (intsrc->inti_flags & ACPI_MADT_POLARITY_MASK)) { + + if ((intsrc->global_irq == 2) && acpi_fix_pin2_polarity + && (intsrc->inti_flags & ACPI_MADT_POLARITY_MASK)) { intsrc->inti_flags &= ~ACPI_MADT_POLARITY_MASK; printk(PREFIX "BIOS IRQ0 pin2 override: forcing polarity to high active.\n"); } @@ -1327,17 +1329,12 @@ static int __init dmi_disable_acpi(const struct dmi_system_id *d) } /* - * Force ignoring BIOS IRQ0 pin2 override + * Force ignoring BIOS IRQ0 override */ static int __init dmi_ignore_irq0_timer_override(const struct dmi_system_id *d) { - /* - * The ati_ixp4x0_rev() early PCI quirk should have set - * the acpi_skip_timer_override flag already: - */ if (!acpi_skip_timer_override) { - WARN(1, KERN_ERR "ati_ixp4x0 quirk not complete.\n"); - pr_notice("%s detected: Ignoring BIOS IRQ0 pin2 override\n", + pr_notice("%s detected: Ignoring BIOS IRQ0 override\n", d->ident); acpi_skip_timer_override = 1; } @@ -1431,7 +1428,7 @@ static struct dmi_system_id __initdata acpi_dmi_table_late[] = { * is enabled. This input is incorrectly designated the * ISA IRQ 0 via an interrupt source override even though * it is wired to the output of the master 8259A and INTIN0 - * is not connected at all. Force ignoring BIOS IRQ0 pin2 + * is not connected at all. Force ignoring BIOS IRQ0 * override in that cases. */ { @@ -1466,6 +1463,14 @@ static struct dmi_system_id __initdata acpi_dmi_table_late[] = { DMI_MATCH(DMI_PRODUCT_NAME, "HP Compaq 6715b"), }, }, + { + .callback = dmi_ignore_irq0_timer_override, + .ident = "FUJITSU SIEMENS", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU SIEMENS"), + DMI_MATCH(DMI_PRODUCT_NAME, "AMILO PRO V2030"), + }, + }, {} }; diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index 37a458b..e61f79c 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -460,6 +460,14 @@ static struct dmi_system_id __initdata pci_reboot_dmi_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex 990"), }, }, + { /* Handle problems with rebooting on the Precision M6600. */ + .callback = set_pci_reboot, + .ident = "Dell OptiPlex 990", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "Precision M6600"), + }, + }, { } }; diff --git a/block/scsi_ioctl.c b/block/scsi_ioctl.c index 688be8a..9e76a32 100644 --- a/block/scsi_ioctl.c +++ b/block/scsi_ioctl.c @@ -721,11 +721,14 @@ int scsi_verify_blk_ioctl(struct block_device *bd, unsigned int cmd) break; } + if (capable(CAP_SYS_RAWIO)) + return 0; + /* In particular, rule out all resets and host-specific ioctls. */ printk_ratelimited(KERN_WARNING "%s: sending ioctl %x to a partition!\n", current->comm, cmd); - return capable(CAP_SYS_RAWIO) ? 0 : -ENOTTY; + return -ENOTTY; } EXPORT_SYMBOL(scsi_verify_blk_ioctl); diff --git a/drivers/acpi/processor_core.c b/drivers/acpi/processor_core.c index c850de4..eff7222 100644 --- a/drivers/acpi/processor_core.c +++ b/drivers/acpi/processor_core.c @@ -189,10 +189,12 @@ int acpi_get_cpuid(acpi_handle handle, int type, u32 acpi_id) * Processor (CPU3, 0x03, 0x00000410, 0x06) {} * } * - * Ignores apic_id and always return 0 for CPU0's handle. + * Ignores apic_id and always returns 0 for the processor + * handle with acpi id 0 if nr_cpu_ids is 1. + * This should be the case if SMP tables are not found. * Return -1 for other CPU's handle. */ - if (acpi_id == 0) + if (nr_cpu_ids <= 1 && acpi_id == 0) return acpi_id; else return apic_id; diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c index ca191ff..ed6bc52 100644 --- a/drivers/acpi/sleep.c +++ b/drivers/acpi/sleep.c @@ -702,8 +702,8 @@ int acpi_pm_device_sleep_state(struct device *dev, int *d_min_p) * can wake the system. _S0W may be valid, too. */ if (acpi_target_sleep_state == ACPI_STATE_S0 || - (device_may_wakeup(dev) && - adev->wakeup.sleep_state <= acpi_target_sleep_state)) { + (device_may_wakeup(dev) && adev->wakeup.flags.valid && + adev->wakeup.sleep_state >= acpi_target_sleep_state)) { acpi_status status; acpi_method[3] = 'W'; diff --git a/drivers/acpi/sysfs.c b/drivers/acpi/sysfs.c index 9f66181..240a244 100644 --- a/drivers/acpi/sysfs.c +++ b/drivers/acpi/sysfs.c @@ -173,7 +173,7 @@ static int param_set_trace_state(const char *val, struct kernel_param *kp) { int result = 0; - if (!strncmp(val, "enable", strlen("enable") - 1)) { + if (!strncmp(val, "enable", strlen("enable"))) { result = acpi_debug_trace(trace_method_name, trace_debug_level, trace_debug_layer, 0); if (result) @@ -181,7 +181,7 @@ static int param_set_trace_state(const char *val, struct kernel_param *kp) goto exit; } - if (!strncmp(val, "disable", strlen("disable") - 1)) { + if (!strncmp(val, "disable", strlen("disable"))) { int name = 0; result = acpi_debug_trace((char *)&name, trace_debug_level, trace_debug_layer, 0); diff --git a/drivers/gpio/gpio-wm8994.c b/drivers/gpio/gpio-wm8994.c index 96198f3..a2da8f2 100644 --- a/drivers/gpio/gpio-wm8994.c +++ b/drivers/gpio/gpio-wm8994.c @@ -89,8 +89,11 @@ static int wm8994_gpio_direction_out(struct gpio_chip *chip, struct wm8994_gpio *wm8994_gpio = to_wm8994_gpio(chip); struct wm8994 *wm8994 = wm8994_gpio->wm8994; + if (value) + value = WM8994_GPN_LVL; + return wm8994_set_bits(wm8994, WM8994_GPIO_1 + offset, - WM8994_GPN_DIR, 0); + WM8994_GPN_DIR | WM8994_GPN_LVL, value); } static void wm8994_gpio_set(struct gpio_chip *chip, unsigned offset, int value) diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index 6aa7716..cc75c4b 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -8043,8 +8043,8 @@ void gen6_enable_rps(struct drm_i915_private *dev_priv) I915_WRITE(GEN6_RC6pp_THRESHOLD, 64000); /* unused */ if (intel_enable_rc6(dev_priv->dev)) - rc6_mask = GEN6_RC_CTL_RC6p_ENABLE | - GEN6_RC_CTL_RC6_ENABLE; + rc6_mask = GEN6_RC_CTL_RC6_ENABLE | + ((IS_GEN7(dev_priv->dev)) ? GEN6_RC_CTL_RC6p_ENABLE : 0); I915_WRITE(GEN6_RC_CONTROL, rc6_mask | diff --git a/drivers/hid/hid-apple.c b/drivers/hid/hid-apple.c index 299d238..899c712 100644 --- a/drivers/hid/hid-apple.c +++ b/drivers/hid/hid-apple.c @@ -514,6 +514,12 @@ static const struct hid_device_id apple_devices[] = { .driver_data = APPLE_HAS_FN | APPLE_ISO_KEYBOARD }, { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING5A_JIS), .driver_data = APPLE_HAS_FN | APPLE_RDESC_JIS }, + { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING7_ANSI), + .driver_data = APPLE_HAS_FN }, + { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING7_ISO), + .driver_data = APPLE_HAS_FN | APPLE_ISO_KEYBOARD }, + { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING7_JIS), + .driver_data = APPLE_HAS_FN | APPLE_RDESC_JIS }, { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_WIRELESS_2009_ANSI), .driver_data = APPLE_NUMLOCK_EMULATION | APPLE_HAS_FN }, { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_WIRELESS_2009_ISO), diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c index c27b402..95430a0 100644 --- a/drivers/hid/hid-core.c +++ b/drivers/hid/hid-core.c @@ -1374,6 +1374,9 @@ static const struct hid_device_id hid_have_special_driver[] = { { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING6A_ANSI) }, { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING6A_ISO) }, { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING6A_JIS) }, + { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING7_ANSI) }, + { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING7_ISO) }, + { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING7_JIS) }, { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_WIRELESS_2009_ANSI) }, { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_WIRELESS_2009_ISO) }, { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_WIRELESS_2009_JIS) }, @@ -1884,6 +1887,7 @@ static const struct hid_device_id hid_ignore_list[] = { { HID_USB_DEVICE(USB_VENDOR_ID_LD, USB_DEVICE_ID_LD_MCT) }, { HID_USB_DEVICE(USB_VENDOR_ID_LD, USB_DEVICE_ID_LD_HYBRID) }, { HID_USB_DEVICE(USB_VENDOR_ID_LD, USB_DEVICE_ID_LD_HEATCONTROL) }, + { HID_USB_DEVICE(USB_VENDOR_ID_MADCATZ, USB_DEVICE_ID_MADCATZ_BEATPAD) }, { HID_USB_DEVICE(USB_VENDOR_ID_MCC, USB_DEVICE_ID_MCC_PMD1024LS) }, { HID_USB_DEVICE(USB_VENDOR_ID_MCC, USB_DEVICE_ID_MCC_PMD1208LS) }, { HID_USB_DEVICE(USB_VENDOR_ID_MICROCHIP, USB_DEVICE_ID_PICKIT1) }, @@ -1968,6 +1972,9 @@ static const struct hid_device_id hid_mouse_ignore_list[] = { { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING6A_ANSI) }, { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING6A_ISO) }, { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING6A_JIS) }, + { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING7_ANSI) }, + { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING7_ISO) }, + { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING7_JIS) }, { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_FOUNTAIN_TP_ONLY) }, { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_GEYSER1_TP_ONLY) }, { } diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index fba3fc4..7db934d 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -125,6 +125,9 @@ #define USB_DEVICE_ID_APPLE_WELLSPRING6_ANSI 0x024c #define USB_DEVICE_ID_APPLE_WELLSPRING6_ISO 0x024d #define USB_DEVICE_ID_APPLE_WELLSPRING6_JIS 0x024e +#define USB_DEVICE_ID_APPLE_WELLSPRING7_ANSI 0x0262 +#define USB_DEVICE_ID_APPLE_WELLSPRING7_ISO 0x0263 +#define USB_DEVICE_ID_APPLE_WELLSPRING7_JIS 0x0264 #define USB_DEVICE_ID_APPLE_ALU_WIRELESS_2009_ANSI 0x0239 #define USB_DEVICE_ID_APPLE_ALU_WIRELESS_2009_ISO 0x023a #define USB_DEVICE_ID_APPLE_ALU_WIRELESS_2009_JIS 0x023b @@ -491,6 +494,9 @@ #define USB_DEVICE_ID_CRYSTALTOUCH 0x0006 #define USB_DEVICE_ID_CRYSTALTOUCH_DUAL 0x0007 +#define USB_VENDOR_ID_MADCATZ 0x0738 +#define USB_DEVICE_ID_MADCATZ_BEATPAD 0x4540 + #define USB_VENDOR_ID_MCC 0x09db #define USB_DEVICE_ID_MCC_PMD1024LS 0x0076 #define USB_DEVICE_ID_MCC_PMD1208LS 0x007a diff --git a/drivers/hwmon/it87.c b/drivers/hwmon/it87.c index d912649..1ba7af2 100644 --- a/drivers/hwmon/it87.c +++ b/drivers/hwmon/it87.c @@ -2086,7 +2086,7 @@ static void __devinit it87_init_device(struct platform_device *pdev) /* Start monitoring */ it87_write_value(data, IT87_REG_CONFIG, - (it87_read_value(data, IT87_REG_CONFIG) & 0x36) + (it87_read_value(data, IT87_REG_CONFIG) & 0x3e) | (update_vbat ? 0x41 : 0x01)); } diff --git a/drivers/hwspinlock/hwspinlock_core.c b/drivers/hwspinlock/hwspinlock_core.c index 61c9cf1..1201a15 100644 --- a/drivers/hwspinlock/hwspinlock_core.c +++ b/drivers/hwspinlock/hwspinlock_core.c @@ -345,7 +345,7 @@ int hwspin_lock_register(struct hwspinlock_device *bank, struct device *dev, spin_lock_init(&hwlock->lock); hwlock->bank = bank; - ret = hwspin_lock_register_single(hwlock, i); + ret = hwspin_lock_register_single(hwlock, base_id + i); if (ret) goto reg_failed; } @@ -354,7 +354,7 @@ int hwspin_lock_register(struct hwspinlock_device *bank, struct device *dev, reg_failed: while (--i >= 0) - hwspin_lock_unregister_single(i); + hwspin_lock_unregister_single(base_id + i); return ret; } EXPORT_SYMBOL_GPL(hwspin_lock_register); diff --git a/drivers/input/joystick/xpad.c b/drivers/input/joystick/xpad.c index d728875..2189cbf 100644 --- a/drivers/input/joystick/xpad.c +++ b/drivers/input/joystick/xpad.c @@ -142,6 +142,7 @@ static const struct xpad_device { { 0x0c12, 0x880a, "Pelican Eclipse PL-2023", 0, XTYPE_XBOX }, { 0x0c12, 0x8810, "Zeroplus Xbox Controller", 0, XTYPE_XBOX }, { 0x0c12, 0x9902, "HAMA VibraX - *FAULTY HARDWARE*", 0, XTYPE_XBOX }, + { 0x0d2f, 0x0002, "Andamiro Pump It Up pad", MAP_DPAD_TO_BUTTONS, XTYPE_XBOX }, { 0x0e4c, 0x1097, "Radica Gamester Controller", 0, XTYPE_XBOX }, { 0x0e4c, 0x2390, "Radica Games Jtech Controller", 0, XTYPE_XBOX }, { 0x0e6f, 0x0003, "Logic3 Freebird wireless Controller", 0, XTYPE_XBOX }, @@ -164,6 +165,7 @@ static const struct xpad_device { { 0x1bad, 0x0003, "Harmonix Rock Band Drumkit", MAP_DPAD_TO_BUTTONS, XTYPE_XBOX360 }, { 0x0f0d, 0x0016, "Hori Real Arcade Pro.EX", MAP_TRIGGERS_TO_BUTTONS, XTYPE_XBOX360 }, { 0x0f0d, 0x000d, "Hori Fighting Stick EX2", MAP_TRIGGERS_TO_BUTTONS, XTYPE_XBOX360 }, + { 0x1689, 0xfd00, "Razer Onza Tournament Edition", MAP_DPAD_TO_BUTTONS, XTYPE_XBOX360 }, { 0xffff, 0xffff, "Chinese-made Xbox Controller", 0, XTYPE_XBOX }, { 0x0000, 0x0000, "Generic X-Box pad", 0, XTYPE_UNKNOWN } }; @@ -238,12 +240,14 @@ static struct usb_device_id xpad_table [] = { XPAD_XBOX360_VENDOR(0x045e), /* Microsoft X-Box 360 controllers */ XPAD_XBOX360_VENDOR(0x046d), /* Logitech X-Box 360 style controllers */ XPAD_XBOX360_VENDOR(0x0738), /* Mad Catz X-Box 360 controllers */ + { USB_DEVICE(0x0738, 0x4540) }, /* Mad Catz Beat Pad */ XPAD_XBOX360_VENDOR(0x0e6f), /* 0x0e6f X-Box 360 controllers */ XPAD_XBOX360_VENDOR(0x12ab), /* X-Box 360 dance pads */ XPAD_XBOX360_VENDOR(0x1430), /* RedOctane X-Box 360 controllers */ XPAD_XBOX360_VENDOR(0x146b), /* BigBen Interactive Controllers */ XPAD_XBOX360_VENDOR(0x1bad), /* Harminix Rock Band Guitar and Drums */ - XPAD_XBOX360_VENDOR(0x0f0d), /* Hori Controllers */ + XPAD_XBOX360_VENDOR(0x0f0d), /* Hori Controllers */ + XPAD_XBOX360_VENDOR(0x1689), /* Razer Onza */ { } }; diff --git a/drivers/input/mouse/bcm5974.c b/drivers/input/mouse/bcm5974.c index 5ec617e..ec58f48 100644 --- a/drivers/input/mouse/bcm5974.c +++ b/drivers/input/mouse/bcm5974.c @@ -79,6 +79,10 @@ #define USB_DEVICE_ID_APPLE_WELLSPRING5A_ANSI 0x0252 #define USB_DEVICE_ID_APPLE_WELLSPRING5A_ISO 0x0253 #define USB_DEVICE_ID_APPLE_WELLSPRING5A_JIS 0x0254 +/* MacbookPro10,1 (unibody, June 2012) */ +#define USB_DEVICE_ID_APPLE_WELLSPRING7_ANSI 0x0262 +#define USB_DEVICE_ID_APPLE_WELLSPRING7_ISO 0x0263 +#define USB_DEVICE_ID_APPLE_WELLSPRING7_JIS 0x0264 #define BCM5974_DEVICE(prod) { \ .match_flags = (USB_DEVICE_ID_MATCH_DEVICE | \ @@ -128,6 +132,10 @@ static const struct usb_device_id bcm5974_table[] = { BCM5974_DEVICE(USB_DEVICE_ID_APPLE_WELLSPRING5A_ANSI), BCM5974_DEVICE(USB_DEVICE_ID_APPLE_WELLSPRING5A_ISO), BCM5974_DEVICE(USB_DEVICE_ID_APPLE_WELLSPRING5A_JIS), + /* MacbookPro10,1 */ + BCM5974_DEVICE(USB_DEVICE_ID_APPLE_WELLSPRING7_ANSI), + BCM5974_DEVICE(USB_DEVICE_ID_APPLE_WELLSPRING7_ISO), + BCM5974_DEVICE(USB_DEVICE_ID_APPLE_WELLSPRING7_JIS), /* Terminating entry */ {} }; @@ -354,6 +362,18 @@ static const struct bcm5974_config bcm5974_config_table[] = { { DIM_X, DIM_X / SN_COORD, -4620, 5140 }, { DIM_Y, DIM_Y / SN_COORD, -150, 6600 } }, + { + USB_DEVICE_ID_APPLE_WELLSPRING7_ANSI, + USB_DEVICE_ID_APPLE_WELLSPRING7_ISO, + USB_DEVICE_ID_APPLE_WELLSPRING7_JIS, + HAS_INTEGRATED_BUTTON, + 0x84, sizeof(struct bt_data), + 0x81, TYPE2, FINGER_TYPE2, FINGER_TYPE2 + SIZEOF_ALL_FINGERS, + { DIM_PRESSURE, DIM_PRESSURE / SN_PRESSURE, 0, 300 }, + { DIM_WIDTH, DIM_WIDTH / SN_WIDTH, 0, 2048 }, + { DIM_X, DIM_X / SN_COORD, -4750, 5280 }, + { DIM_Y, DIM_Y / SN_COORD, -150, 6730 } + }, {} }; diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c index f1d5408..a1b8caa 100644 --- a/drivers/iommu/amd_iommu.c +++ b/drivers/iommu/amd_iommu.c @@ -59,6 +59,8 @@ static struct protection_domain *pt_domain; static struct iommu_ops amd_iommu_ops; +static struct dma_map_ops amd_iommu_dma_ops; + /* * general struct to manage commands send to an IOMMU */ @@ -1878,6 +1880,11 @@ static int device_change_notifier(struct notifier_block *nb, list_add_tail(&dma_domain->list, &iommu_pd_list); spin_unlock_irqrestore(&iommu_pd_list_lock, flags); + if (!iommu_pass_through) + dev->archdata.dma_ops = &amd_iommu_dma_ops; + else + dev->archdata.dma_ops = &nommu_dma_ops; + break; case BUS_NOTIFY_DEL_DEVICE: diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c index 6269eb0..ef2d493 100644 --- a/drivers/iommu/amd_iommu_init.c +++ b/drivers/iommu/amd_iommu_init.c @@ -1468,6 +1468,8 @@ static int __init amd_iommu_init(void) register_syscore_ops(&amd_iommu_syscore_ops); + x86_platform.iommu_shutdown = disable_iommus; + if (iommu_pass_through) goto out; @@ -1476,7 +1478,6 @@ static int __init amd_iommu_init(void) else printk(KERN_INFO "AMD-Vi: Lazy IO/TLB flushing enabled\n"); - x86_platform.iommu_shutdown = disable_iommus; out: return ret; diff --git a/drivers/md/dm-raid1.c b/drivers/md/dm-raid1.c index 9bfd057..dae2b7a 100644 --- a/drivers/md/dm-raid1.c +++ b/drivers/md/dm-raid1.c @@ -1080,6 +1080,7 @@ static int mirror_ctr(struct dm_target *ti, unsigned int argc, char **argv) ti->split_io = dm_rh_get_region_size(ms->rh); ti->num_flush_requests = 1; ti->num_discard_requests = 1; + ti->discard_zeroes_data_unsupported = 1; ms->kmirrord_wq = alloc_workqueue("kmirrord", WQ_NON_REENTRANT | WQ_MEM_RECLAIM, 0); @@ -1210,7 +1211,7 @@ static int mirror_end_io(struct dm_target *ti, struct bio *bio, * We need to dec pending if this was a write. */ if (rw == WRITE) { - if (!(bio->bi_rw & REQ_FLUSH)) + if (!(bio->bi_rw & (REQ_FLUSH | REQ_DISCARD))) dm_rh_dec(ms->rh, map_context->ll); return error; } diff --git a/drivers/md/dm-region-hash.c b/drivers/md/dm-region-hash.c index 7771ed2..69732e0 100644 --- a/drivers/md/dm-region-hash.c +++ b/drivers/md/dm-region-hash.c @@ -404,6 +404,9 @@ void dm_rh_mark_nosync(struct dm_region_hash *rh, struct bio *bio) return; } + if (bio->bi_rw & REQ_DISCARD) + return; + /* We must inform the log that the sync count has changed. */ log->type->set_region_sync(log, region, 0); @@ -524,7 +527,7 @@ void dm_rh_inc_pending(struct dm_region_hash *rh, struct bio_list *bios) struct bio *bio; for (bio = bios->head; bio; bio = bio->bi_next) { - if (bio->bi_rw & REQ_FLUSH) + if (bio->bi_rw & (REQ_FLUSH | REQ_DISCARD)) continue; rh_inc(rh, dm_rh_bio_to_region(rh, bio)); } diff --git a/drivers/md/md.c b/drivers/md/md.c index 700ecae..d8646d7 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -3700,8 +3700,8 @@ array_state_show(struct mddev *mddev, char *page) return sprintf(page, "%s\n", array_states[st]); } -static int do_md_stop(struct mddev * mddev, int ro, int is_open); -static int md_set_readonly(struct mddev * mddev, int is_open); +static int do_md_stop(struct mddev * mddev, int ro, struct block_device *bdev); +static int md_set_readonly(struct mddev * mddev, struct block_device *bdev); static int do_md_run(struct mddev * mddev); static int restart_array(struct mddev *mddev); @@ -3717,14 +3717,14 @@ array_state_store(struct mddev *mddev, const char *buf, size_t len) /* stopping an active array */ if (atomic_read(&mddev->openers) > 0) return -EBUSY; - err = do_md_stop(mddev, 0, 0); + err = do_md_stop(mddev, 0, NULL); break; case inactive: /* stopping an active array */ if (mddev->pers) { if (atomic_read(&mddev->openers) > 0) return -EBUSY; - err = do_md_stop(mddev, 2, 0); + err = do_md_stop(mddev, 2, NULL); } else err = 0; /* already inactive */ break; @@ -3732,7 +3732,7 @@ array_state_store(struct mddev *mddev, const char *buf, size_t len) break; /* not supported yet */ case readonly: if (mddev->pers) - err = md_set_readonly(mddev, 0); + err = md_set_readonly(mddev, NULL); else { mddev->ro = 1; set_disk_ro(mddev->gendisk, 1); @@ -3742,7 +3742,7 @@ array_state_store(struct mddev *mddev, const char *buf, size_t len) case read_auto: if (mddev->pers) { if (mddev->ro == 0) - err = md_set_readonly(mddev, 0); + err = md_set_readonly(mddev, NULL); else if (mddev->ro == 1) err = restart_array(mddev); if (err == 0) { @@ -5078,15 +5078,17 @@ void md_stop(struct mddev *mddev) } EXPORT_SYMBOL_GPL(md_stop); -static int md_set_readonly(struct mddev *mddev, int is_open) +static int md_set_readonly(struct mddev *mddev, struct block_device *bdev) { int err = 0; mutex_lock(&mddev->open_mutex); - if (atomic_read(&mddev->openers) > is_open) { + if (atomic_read(&mddev->openers) > !!bdev) { printk("md: %s still in use.\n",mdname(mddev)); err = -EBUSY; goto out; } + if (bdev) + sync_blockdev(bdev); if (mddev->pers) { __md_stop_writes(mddev); @@ -5108,18 +5110,26 @@ out: * 0 - completely stop and dis-assemble array * 2 - stop but do not disassemble array */ -static int do_md_stop(struct mddev * mddev, int mode, int is_open) +static int do_md_stop(struct mddev * mddev, int mode, + struct block_device *bdev) { struct gendisk *disk = mddev->gendisk; struct md_rdev *rdev; mutex_lock(&mddev->open_mutex); - if (atomic_read(&mddev->openers) > is_open || + if (atomic_read(&mddev->openers) > !!bdev || mddev->sysfs_active) { printk("md: %s still in use.\n",mdname(mddev)); mutex_unlock(&mddev->open_mutex); return -EBUSY; } + if (bdev) + /* It is possible IO was issued on some other + * open file which was closed before we took ->open_mutex. + * As that was not the last close __blkdev_put will not + * have called sync_blockdev, so we must. + */ + sync_blockdev(bdev); if (mddev->pers) { if (mddev->ro) @@ -5193,7 +5203,7 @@ static void autorun_array(struct mddev *mddev) err = do_md_run(mddev); if (err) { printk(KERN_WARNING "md: do_md_run() returned %d\n", err); - do_md_stop(mddev, 0, 0); + do_md_stop(mddev, 0, NULL); } } @@ -6184,11 +6194,11 @@ static int md_ioctl(struct block_device *bdev, fmode_t mode, goto done_unlock; case STOP_ARRAY: - err = do_md_stop(mddev, 0, 1); + err = do_md_stop(mddev, 0, bdev); goto done_unlock; case STOP_ARRAY_RO: - err = md_set_readonly(mddev, 1); + err = md_set_readonly(mddev, bdev); goto done_unlock; case BLKROSET: diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index 7af60ec..2d97bf0 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -1713,8 +1713,14 @@ static void sync_request_write(struct mddev *mddev, struct r1bio *r1_bio) if (atomic_dec_and_test(&r1_bio->remaining)) { /* if we're here, all write(s) have completed, so clean up */ - md_done_sync(mddev, r1_bio->sectors, 1); - put_buf(r1_bio); + int s = r1_bio->sectors; + if (test_bit(R1BIO_MadeGood, &r1_bio->state) || + test_bit(R1BIO_WriteError, &r1_bio->state)) + reschedule_retry(r1_bio); + else { + put_buf(r1_bio); + md_done_sync(mddev, s, 1); + } } } @@ -2378,9 +2384,10 @@ static sector_t sync_request(struct mddev *mddev, sector_t sector_nr, int *skipp */ if (test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery)) { atomic_set(&r1_bio->remaining, read_targets); - for (i=0; iraid_disks; i++) { + for (i = 0; i < conf->raid_disks && read_targets; i++) { bio = r1_bio->bios[i]; if (bio->bi_end_io == end_sync_read) { + read_targets--; md_sync_acct(bio->bi_bdev, nr_sectors); generic_make_request(bio); } diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 6ba4954..26ef63a 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -196,12 +196,14 @@ static void __release_stripe(struct r5conf *conf, struct stripe_head *sh) BUG_ON(!list_empty(&sh->lru)); BUG_ON(atomic_read(&conf->active_stripes)==0); if (test_bit(STRIPE_HANDLE, &sh->state)) { - if (test_bit(STRIPE_DELAYED, &sh->state)) + if (test_bit(STRIPE_DELAYED, &sh->state) && + !test_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) list_add_tail(&sh->lru, &conf->delayed_list); else if (test_bit(STRIPE_BIT_DELAY, &sh->state) && sh->bm_seq - conf->seq_write > 0) list_add_tail(&sh->lru, &conf->bitmap_list); else { + clear_bit(STRIPE_DELAYED, &sh->state); clear_bit(STRIPE_BIT_DELAY, &sh->state); list_add_tail(&sh->lru, &conf->handle_list); } diff --git a/drivers/media/dvb/dvb-core/dvbdev.c b/drivers/media/dvb/dvb-core/dvbdev.c index f732877..d5cda35 100644 --- a/drivers/media/dvb/dvb-core/dvbdev.c +++ b/drivers/media/dvb/dvb-core/dvbdev.c @@ -243,6 +243,7 @@ int dvb_register_device(struct dvb_adapter *adap, struct dvb_device **pdvbdev, if (minor == MAX_DVB_MINORS) { kfree(dvbdevfops); kfree(dvbdev); + up_write(&minor_rwsem); mutex_unlock(&dvbdev_register_lock); return -EINVAL; } diff --git a/drivers/mtd/nand/nandsim.c b/drivers/mtd/nand/nandsim.c index 34c03be..83e8e1b 100644 --- a/drivers/mtd/nand/nandsim.c +++ b/drivers/mtd/nand/nandsim.c @@ -28,7 +28,7 @@ #include #include #include -#include +#include #include #include #include @@ -547,12 +547,6 @@ static char *get_partition_name(int i) return kstrdup(buf, GFP_KERNEL); } -static uint64_t divide(uint64_t n, uint32_t d) -{ - do_div(n, d); - return n; -} - /* * Initialize the nandsim structure. * @@ -581,7 +575,7 @@ static int init_nandsim(struct mtd_info *mtd) ns->geom.oobsz = mtd->oobsize; ns->geom.secsz = mtd->erasesize; ns->geom.pgszoob = ns->geom.pgsz + ns->geom.oobsz; - ns->geom.pgnum = divide(ns->geom.totsz, ns->geom.pgsz); + ns->geom.pgnum = div_u64(ns->geom.totsz, ns->geom.pgsz); ns->geom.totszoob = ns->geom.totsz + (uint64_t)ns->geom.pgnum * ns->geom.oobsz; ns->geom.secshift = ffs(ns->geom.secsz) - 1; ns->geom.pgshift = chip->page_shift; @@ -924,7 +918,7 @@ static int setup_wear_reporting(struct mtd_info *mtd) if (!rptwear) return 0; - wear_eb_count = divide(mtd->size, mtd->erasesize); + wear_eb_count = div_u64(mtd->size, mtd->erasesize); mem = wear_eb_count * sizeof(unsigned long); if (mem / sizeof(unsigned long) != wear_eb_count) { NS_ERR("Too many erase blocks for wear reporting\n"); diff --git a/drivers/net/bonding/bond_debugfs.c b/drivers/net/bonding/bond_debugfs.c index 3680aa2..2cf084e 100644 --- a/drivers/net/bonding/bond_debugfs.c +++ b/drivers/net/bonding/bond_debugfs.c @@ -6,7 +6,7 @@ #include "bonding.h" #include "bond_alb.h" -#ifdef CONFIG_DEBUG_FS +#if defined(CONFIG_DEBUG_FS) && !defined(CONFIG_NET_NS) #include #include diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 1a88e38..6c284d1 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -3184,6 +3184,12 @@ static int bond_master_netdev_event(unsigned long event, switch (event) { case NETDEV_CHANGENAME: return bond_event_changename(event_bond); + case NETDEV_UNREGISTER: + bond_remove_proc_entry(event_bond); + break; + case NETDEV_REGISTER: + bond_create_proc_entry(event_bond); + break; default: break; } @@ -4391,8 +4397,6 @@ static void bond_uninit(struct net_device *bond_dev) bond_work_cancel_all(bond); - bond_remove_proc_entry(bond); - bond_debug_unregister(bond); __hw_addr_flush(&bond->mc_list); @@ -4794,7 +4798,6 @@ static int bond_init(struct net_device *bond_dev) bond_set_lockdep_class(bond_dev); - bond_create_proc_entry(bond); list_add_tail(&bond->bond_list, &bn->dev_list); bond_prepare_sysfs_group(bond); diff --git a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c index eccdcff..5ae7df7 100644 --- a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c +++ b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c @@ -267,7 +267,6 @@ static void atl1c_check_link_status(struct atl1c_adapter *adapter) dev_warn(&pdev->dev, "stop mac failed\n"); atl1c_set_aspm(hw, false); netif_carrier_off(netdev); - netif_stop_queue(netdev); atl1c_phy_reset(hw); atl1c_phy_init(&adapter->hw); } else { diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h index aec7212..8dda46a 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h @@ -723,21 +723,6 @@ struct bnx2x_fastpath { #define ETH_RX_ERROR_FALGS ETH_FAST_PATH_RX_CQE_PHY_DECODE_ERR_FLG -#define BNX2X_IP_CSUM_ERR(cqe) \ - (!((cqe)->fast_path_cqe.status_flags & \ - ETH_FAST_PATH_RX_CQE_IP_XSUM_NO_VALIDATION_FLG) && \ - ((cqe)->fast_path_cqe.type_error_flags & \ - ETH_FAST_PATH_RX_CQE_IP_BAD_XSUM_FLG)) - -#define BNX2X_L4_CSUM_ERR(cqe) \ - (!((cqe)->fast_path_cqe.status_flags & \ - ETH_FAST_PATH_RX_CQE_L4_XSUM_NO_VALIDATION_FLG) && \ - ((cqe)->fast_path_cqe.type_error_flags & \ - ETH_FAST_PATH_RX_CQE_L4_BAD_XSUM_FLG)) - -#define BNX2X_RX_CSUM_OK(cqe) \ - (!(BNX2X_L4_CSUM_ERR(cqe) || BNX2X_IP_CSUM_ERR(cqe))) - #define BNX2X_PRS_FLAG_OVERETH_IPV4(flags) \ (((le16_to_cpu(flags) & \ PARSING_FLAGS_OVER_ETHERNET_PROTOCOL) >> \ diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c index 580b44e..2c1a5c0 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c @@ -220,7 +220,7 @@ int bnx2x_tx_int(struct bnx2x *bp, struct bnx2x_fp_txdata *txdata) if ((netif_tx_queue_stopped(txq)) && (bp->state == BNX2X_STATE_OPEN) && - (bnx2x_tx_avail(bp, txdata) >= MAX_SKB_FRAGS + 3)) + (bnx2x_tx_avail(bp, txdata) >= MAX_SKB_FRAGS + 4)) netif_tx_wake_queue(txq); __netif_tx_unlock(txq); @@ -551,6 +551,26 @@ static inline void bnx2x_set_skb_rxhash(struct bnx2x *bp, union eth_rx_cqe *cqe, le32_to_cpu(cqe->fast_path_cqe.rss_hash_result); } +static void bnx2x_csum_validate(struct sk_buff *skb, union eth_rx_cqe *cqe, + struct bnx2x_fastpath *fp) +{ + /* Do nothing if no IP/L4 csum validation was done */ + + if (cqe->fast_path_cqe.status_flags & + (ETH_FAST_PATH_RX_CQE_IP_XSUM_NO_VALIDATION_FLG | + ETH_FAST_PATH_RX_CQE_L4_XSUM_NO_VALIDATION_FLG)) + return; + + /* If both IP/L4 validation were done, check if an error was found. */ + + if (cqe->fast_path_cqe.type_error_flags & + (ETH_FAST_PATH_RX_CQE_IP_BAD_XSUM_FLG | + ETH_FAST_PATH_RX_CQE_L4_BAD_XSUM_FLG)) + fp->eth_q_stats.hw_csum_err++; + else + skb->ip_summed = CHECKSUM_UNNECESSARY; +} + int bnx2x_rx_int(struct bnx2x_fastpath *fp, int budget) { struct bnx2x *bp = fp->bp; @@ -746,13 +766,9 @@ reuse_rx: skb_checksum_none_assert(skb); - if (bp->dev->features & NETIF_F_RXCSUM) { + if (bp->dev->features & NETIF_F_RXCSUM) + bnx2x_csum_validate(skb, cqe, fp); - if (likely(BNX2X_RX_CSUM_OK(cqe))) - skb->ip_summed = CHECKSUM_UNNECESSARY; - else - fp->eth_q_stats.hw_csum_err++; - } } skb_record_rx_queue(skb, fp->index); @@ -2238,8 +2254,6 @@ int bnx2x_poll(struct napi_struct *napi, int budget) /* we split the first BD into headers and data BDs * to ease the pain of our fellow microcode engineers * we use one mapping for both BDs - * So far this has only been observed to happen - * in Other Operating Systems(TM) */ static noinline u16 bnx2x_tx_split(struct bnx2x *bp, struct bnx2x_fp_txdata *txdata, @@ -2890,7 +2904,7 @@ netdev_tx_t bnx2x_start_xmit(struct sk_buff *skb, struct net_device *dev) txdata->tx_bd_prod += nbd; - if (unlikely(bnx2x_tx_avail(bp, txdata) < MAX_SKB_FRAGS + 3)) { + if (unlikely(bnx2x_tx_avail(bp, txdata) < MAX_SKB_FRAGS + 4)) { netif_tx_stop_queue(txq); /* paired memory barrier is in bnx2x_tx_int(), we have to keep @@ -2899,7 +2913,7 @@ netdev_tx_t bnx2x_start_xmit(struct sk_buff *skb, struct net_device *dev) smp_mb(); fp->eth_q_stats.driver_xoff++; - if (bnx2x_tx_avail(bp, txdata) >= MAX_SKB_FRAGS + 3) + if (bnx2x_tx_avail(bp, txdata) >= MAX_SKB_FRAGS + 4) netif_tx_wake_queue(txq); } txdata->tx_pkt++; diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c index 2dcac28..6b258d9 100644 --- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -14046,7 +14046,8 @@ static int __devinit tg3_get_invariants(struct tg3 *tp) } } - if (tg3_flag(tp, 5755_PLUS)) + if (tg3_flag(tp, 5755_PLUS) || + GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5906) tg3_flag_set(tp, SHORT_DMA_BUG); if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5719) diff --git a/drivers/net/ethernet/intel/e1000e/82571.c b/drivers/net/ethernet/intel/e1000e/82571.c index e556fc3..3072d35 100644 --- a/drivers/net/ethernet/intel/e1000e/82571.c +++ b/drivers/net/ethernet/intel/e1000e/82571.c @@ -1571,6 +1571,9 @@ static s32 e1000_check_for_serdes_link_82571(struct e1000_hw *hw) ctrl = er32(CTRL); status = er32(STATUS); rxcw = er32(RXCW); + /* SYNCH bit and IV bit are sticky */ + udelay(10); + rxcw = er32(RXCW); if ((rxcw & E1000_RXCW_SYNCH) && !(rxcw & E1000_RXCW_IV)) { diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c index cc2565c..9e61d6b 100644 --- a/drivers/net/ethernet/realtek/r8169.c +++ b/drivers/net/ethernet/realtek/r8169.c @@ -4185,6 +4185,7 @@ out: return rc; err_out_msi_4: + netif_napi_del(&tp->napi); rtl_disable_msi(pdev, tp); iounmap(ioaddr); err_out_free_res_3: @@ -4210,6 +4211,8 @@ static void __devexit rtl8169_remove_one(struct pci_dev *pdev) cancel_delayed_work_sync(&tp->task); + netif_napi_del(&tp->napi); + unregister_netdev(dev); rtl_release_firmware(tp); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 72cd190..d4d2bc1 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -1174,6 +1174,7 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) priv->hw->desc->prepare_tx_desc(desc, 0, len, csum_insertion); wmb(); priv->hw->desc->set_tx_owner(desc); + wmb(); } /* Interrupt on completition only for the latest segment */ @@ -1189,6 +1190,7 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) /* To avoid raise condition */ priv->hw->desc->set_tx_owner(first); + wmb(); priv->cur_tx++; @@ -1252,6 +1254,7 @@ static inline void stmmac_rx_refill(struct stmmac_priv *priv) } wmb(); priv->hw->desc->set_rx_owner(p + entry); + wmb(); } } diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c index 1b7082d..26106c0 100644 --- a/drivers/net/macvtap.c +++ b/drivers/net/macvtap.c @@ -504,10 +504,11 @@ static int zerocopy_sg_from_iovec(struct sk_buff *skb, const struct iovec *from, if (copy > size) { ++from; --count; - } + offset = 0; + } else + offset += size; copy -= size; offset1 += size; - offset = 0; } if (len == offset1) @@ -517,24 +518,29 @@ static int zerocopy_sg_from_iovec(struct sk_buff *skb, const struct iovec *from, struct page *page[MAX_SKB_FRAGS]; int num_pages; unsigned long base; + unsigned long truesize; - len = from->iov_len - offset1; + len = from->iov_len - offset; if (!len) { - offset1 = 0; + offset = 0; ++from; continue; } - base = (unsigned long)from->iov_base + offset1; + base = (unsigned long)from->iov_base + offset; size = ((base & ~PAGE_MASK) + len + ~PAGE_MASK) >> PAGE_SHIFT; + if (i + size > MAX_SKB_FRAGS) + return -EMSGSIZE; num_pages = get_user_pages_fast(base, size, 0, &page[i]); - if ((num_pages != size) || - (num_pages > MAX_SKB_FRAGS - skb_shinfo(skb)->nr_frags)) - /* put_page is in skb free */ + if (num_pages != size) { + for (i = 0; i < num_pages; i++) + put_page(page[i]); return -EFAULT; + } + truesize = size * PAGE_SIZE; skb->data_len += len; skb->len += len; - skb->truesize += len; - atomic_add(len, &skb->sk->sk_wmem_alloc); + skb->truesize += truesize; + atomic_add(truesize, &skb->sk->sk_wmem_alloc); while (len) { int off = base & ~PAGE_MASK; int size = min_t(int, len, PAGE_SIZE - off); @@ -545,7 +551,7 @@ static int zerocopy_sg_from_iovec(struct sk_buff *skb, const struct iovec *from, len -= size; i++; } - offset1 = 0; + offset = 0; ++from; } return 0; @@ -645,7 +651,7 @@ static ssize_t macvtap_get_user(struct macvtap_queue *q, struct msghdr *m, int err; struct virtio_net_hdr vnet_hdr = { 0 }; int vnet_hdr_len = 0; - int copylen; + int copylen = 0; bool zerocopy = false; if (q->flags & IFF_VNET_HDR) { @@ -674,15 +680,31 @@ static ssize_t macvtap_get_user(struct macvtap_queue *q, struct msghdr *m, if (unlikely(len < ETH_HLEN)) goto err; + err = -EMSGSIZE; + if (unlikely(count > UIO_MAXIOV)) + goto err; + if (m && m->msg_control && sock_flag(&q->sk, SOCK_ZEROCOPY)) zerocopy = true; if (zerocopy) { + /* Userspace may produce vectors with count greater than + * MAX_SKB_FRAGS, so we need to linearize parts of the skb + * to let the rest of data to be fit in the frags. + */ + if (count > MAX_SKB_FRAGS) { + copylen = iov_length(iv, count - MAX_SKB_FRAGS); + if (copylen < vnet_hdr_len) + copylen = 0; + else + copylen -= vnet_hdr_len; + } /* There are 256 bytes to be copied in skb, so there is enough * room for skb expand head in case it is used. * The rest buffer is mapped from userspace. */ - copylen = vnet_hdr.hdr_len; + if (copylen < vnet_hdr.hdr_len) + copylen = vnet_hdr.hdr_len; if (!copylen) copylen = GOODCOPY_LEN; } else @@ -693,10 +715,9 @@ static ssize_t macvtap_get_user(struct macvtap_queue *q, struct msghdr *m, if (!skb) goto err; - if (zerocopy) { + if (zerocopy) err = zerocopy_sg_from_iovec(skb, iv, vnet_hdr_len, count); - skb_shinfo(skb)->tx_flags |= SKBTX_DEV_ZEROCOPY; - } else + else err = skb_copy_datagram_from_iovec(skb, 0, iv, vnet_hdr_len, len); if (err) @@ -715,8 +736,10 @@ static ssize_t macvtap_get_user(struct macvtap_queue *q, struct msghdr *m, rcu_read_lock_bh(); vlan = rcu_dereference_bh(q->vlan); /* copy skb_ubuf_info for callback when skb has no error */ - if (zerocopy) + if (zerocopy) { skb_shinfo(skb)->destructor_arg = m->msg_control; + skb_shinfo(skb)->tx_flags |= SKBTX_DEV_ZEROCOPY; + } if (vlan) macvlan_start_xmit(skb, vlan->dev); else diff --git a/drivers/net/usb/ipheth.c b/drivers/net/usb/ipheth.c index ad96164..00ed9c1 100644 --- a/drivers/net/usb/ipheth.c +++ b/drivers/net/usb/ipheth.c @@ -59,6 +59,7 @@ #define USB_PRODUCT_IPHONE_3G 0x1292 #define USB_PRODUCT_IPHONE_3GS 0x1294 #define USB_PRODUCT_IPHONE_4 0x1297 +#define USB_PRODUCT_IPAD 0x129a #define USB_PRODUCT_IPHONE_4_VZW 0x129c #define USB_PRODUCT_IPHONE_4S 0x12a0 @@ -101,6 +102,10 @@ static struct usb_device_id ipheth_table[] = { IPHETH_USBINTF_CLASS, IPHETH_USBINTF_SUBCLASS, IPHETH_USBINTF_PROTO) }, { USB_DEVICE_AND_INTERFACE_INFO( + USB_VENDOR_APPLE, USB_PRODUCT_IPAD, + IPHETH_USBINTF_CLASS, IPHETH_USBINTF_SUBCLASS, + IPHETH_USBINTF_PROTO) }, + { USB_DEVICE_AND_INTERFACE_INFO( USB_VENDOR_APPLE, USB_PRODUCT_IPHONE_4_VZW, IPHETH_USBINTF_CLASS, IPHETH_USBINTF_SUBCLASS, IPHETH_USBINTF_PROTO) }, diff --git a/drivers/net/wireless/brcm80211/brcmsmac/main.c b/drivers/net/wireless/brcm80211/brcmsmac/main.c index 833cbef..8a40ff9 100644 --- a/drivers/net/wireless/brcm80211/brcmsmac/main.c +++ b/drivers/net/wireless/brcm80211/brcmsmac/main.c @@ -900,8 +900,7 @@ brcms_c_dotxstatus(struct brcms_c_info *wlc, struct tx_status *txs) */ if (!(txs->status & TX_STATUS_AMPDU) && (txs->status & TX_STATUS_INTERMEDIATE)) { - wiphy_err(wlc->wiphy, "%s: INTERMEDIATE but not AMPDU\n", - __func__); + BCMMSG(wlc->wiphy, "INTERMEDIATE but not AMPDU\n"); return false; } diff --git a/drivers/net/wireless/ipw2x00/ipw.h b/drivers/net/wireless/ipw2x00/ipw.h new file mode 100644 index 0000000..4007bf5 --- /dev/null +++ b/drivers/net/wireless/ipw2x00/ipw.h @@ -0,0 +1,23 @@ +/* + * Intel Pro/Wireless 2100, 2200BG, 2915ABG network connection driver + * + * Copyright 2012 Stanislav Yakovlev + * + * 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. + */ + +#ifndef __IPW_H__ +#define __IPW_H__ + +#include + +static const u32 ipw_cipher_suites[] = { + WLAN_CIPHER_SUITE_WEP40, + WLAN_CIPHER_SUITE_WEP104, + WLAN_CIPHER_SUITE_TKIP, + WLAN_CIPHER_SUITE_CCMP, +}; + +#endif diff --git a/drivers/net/wireless/ipw2x00/ipw2100.c b/drivers/net/wireless/ipw2x00/ipw2100.c index 127e9c6..10862d4 100644 --- a/drivers/net/wireless/ipw2x00/ipw2100.c +++ b/drivers/net/wireless/ipw2x00/ipw2100.c @@ -166,6 +166,7 @@ that only one external action is invoked at a time. #include #include "ipw2100.h" +#include "ipw.h" #define IPW2100_VERSION "git-1.2.2" @@ -1955,6 +1956,9 @@ static int ipw2100_wdev_init(struct net_device *dev) wdev->wiphy->bands[IEEE80211_BAND_2GHZ] = bg_band; } + wdev->wiphy->cipher_suites = ipw_cipher_suites; + wdev->wiphy->n_cipher_suites = ARRAY_SIZE(ipw_cipher_suites); + set_wiphy_dev(wdev->wiphy, &priv->pci_dev->dev); if (wiphy_register(wdev->wiphy)) { ipw2100_down(priv); diff --git a/drivers/net/wireless/ipw2x00/ipw2200.c b/drivers/net/wireless/ipw2x00/ipw2200.c index 827889b..56bd370 100644 --- a/drivers/net/wireless/ipw2x00/ipw2200.c +++ b/drivers/net/wireless/ipw2x00/ipw2200.c @@ -34,6 +34,7 @@ #include #include #include "ipw2200.h" +#include "ipw.h" #ifndef KBUILD_EXTMOD @@ -11535,6 +11536,9 @@ static int ipw_wdev_init(struct net_device *dev) wdev->wiphy->bands[IEEE80211_BAND_5GHZ] = a_band; } + wdev->wiphy->cipher_suites = ipw_cipher_suites; + wdev->wiphy->n_cipher_suites = ARRAY_SIZE(ipw_cipher_suites); + set_wiphy_dev(wdev->wiphy, &priv->pci_dev->dev); /* With that information in place, we can now register the wiphy... */ diff --git a/drivers/net/wireless/iwlegacy/iwl-4965-sta.c b/drivers/net/wireless/iwlegacy/iwl-4965-sta.c index a262c23..0116ca8 100644 --- a/drivers/net/wireless/iwlegacy/iwl-4965-sta.c +++ b/drivers/net/wireless/iwlegacy/iwl-4965-sta.c @@ -466,7 +466,7 @@ int iwl4965_remove_dynamic_key(struct iwl_priv *priv, return 0; } - if (priv->stations[sta_id].sta.key.key_offset == WEP_INVALID_OFFSET) { + if (priv->stations[sta_id].sta.key.key_flags & STA_KEY_FLG_INVALID) { IWL_WARN(priv, "Removing wrong key %d 0x%x\n", keyconf->keyidx, key_flags); spin_unlock_irqrestore(&priv->sta_lock, flags); @@ -483,7 +483,7 @@ int iwl4965_remove_dynamic_key(struct iwl_priv *priv, sizeof(struct iwl4965_keyinfo)); priv->stations[sta_id].sta.key.key_flags = STA_KEY_FLG_NO_ENC | STA_KEY_FLG_INVALID; - priv->stations[sta_id].sta.key.key_offset = WEP_INVALID_OFFSET; + priv->stations[sta_id].sta.key.key_offset = keyconf->hw_key_idx; priv->stations[sta_id].sta.sta.modify_mask = STA_MODIFY_KEY_MASK; priv->stations[sta_id].sta.mode = STA_CONTROL_MODIFY_MSK; diff --git a/drivers/net/wireless/iwlegacy/iwl-core.c b/drivers/net/wireless/iwlegacy/iwl-core.c index 2bd5659..1bb64c9 100644 --- a/drivers/net/wireless/iwlegacy/iwl-core.c +++ b/drivers/net/wireless/iwlegacy/iwl-core.c @@ -1884,14 +1884,12 @@ void iwl_legacy_bg_watchdog(unsigned long data) return; /* monitor and check for other stuck queues */ - if (iwl_legacy_is_any_associated(priv)) { - for (cnt = 0; cnt < priv->hw_params.max_txq_num; cnt++) { - /* skip as we already checked the command queue */ - if (cnt == priv->cmd_queue) - continue; - if (iwl_legacy_check_stuck_queue(priv, cnt)) - return; - } + for (cnt = 0; cnt < priv->hw_params.max_txq_num; cnt++) { + /* skip as we already checked the command queue */ + if (cnt == priv->cmd_queue) + continue; + if (iwl_legacy_check_stuck_queue(priv, cnt)) + return; } mod_timer(&priv->watchdog, jiffies + diff --git a/drivers/net/wireless/rt2x00/rt2x00usb.c b/drivers/net/wireless/rt2x00/rt2x00usb.c index 1e31050..ba28807 100644 --- a/drivers/net/wireless/rt2x00/rt2x00usb.c +++ b/drivers/net/wireless/rt2x00/rt2x00usb.c @@ -426,8 +426,8 @@ void rt2x00usb_kick_queue(struct data_queue *queue) case QID_RX: if (!rt2x00queue_full(queue)) rt2x00queue_for_each_entry(queue, - Q_INDEX_DONE, Q_INDEX, + Q_INDEX_DONE, NULL, rt2x00usb_kick_rx_entry); break; diff --git a/drivers/net/wireless/rtl818x/rtl8187/leds.c b/drivers/net/wireless/rtl818x/rtl8187/leds.c index 2e0de2f..c2d5b49 100644 --- a/drivers/net/wireless/rtl818x/rtl8187/leds.c +++ b/drivers/net/wireless/rtl818x/rtl8187/leds.c @@ -117,7 +117,7 @@ static void rtl8187_led_brightness_set(struct led_classdev *led_dev, radio_on = true; } else if (radio_on) { radio_on = false; - cancel_delayed_work_sync(&priv->led_on); + cancel_delayed_work(&priv->led_on); ieee80211_queue_delayed_work(hw, &priv->led_off, 0); } } else if (radio_on) { diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c index 12d1e81..d024f83 100644 --- a/drivers/pci/pci-driver.c +++ b/drivers/pci/pci-driver.c @@ -742,6 +742,18 @@ static int pci_pm_suspend_noirq(struct device *dev) pci_pm_set_unknown_state(pci_dev); + /* + * Some BIOSes from ASUS have a bug: If a USB EHCI host controller's + * PCI COMMAND register isn't 0, the BIOS assumes that the controller + * hasn't been quiesced and tries to turn it off. If the controller + * is already in D3, this can hang or cause memory corruption. + * + * Since the value of the COMMAND register doesn't matter once the + * device has been suspended, we can safely set it to 0 here. + */ + if (pci_dev->class == PCI_CLASS_SERIAL_USB_EHCI) + pci_write_config_word(pci_dev, PCI_COMMAND, 0); + return 0; } diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index e5b75eb..6d4a531 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -1689,11 +1689,6 @@ int pci_prepare_to_sleep(struct pci_dev *dev) if (target_state == PCI_POWER_ERROR) return -EIO; - /* Some devices mustn't be in D3 during system sleep */ - if (target_state == PCI_D3hot && - (dev->dev_flags & PCI_DEV_FLAGS_NO_D3_DURING_SLEEP)) - return 0; - pci_enable_wake(dev, target_state, device_may_wakeup(&dev->dev)); error = pci_set_power_state(dev, target_state); diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index 3c56fec..78fda9c 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -2940,32 +2940,6 @@ static void __devinit disable_igfx_irq(struct pci_dev *dev) DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x0102, disable_igfx_irq); DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x010a, disable_igfx_irq); -/* - * The Intel 6 Series/C200 Series chipset's EHCI controllers on many - * ASUS motherboards will cause memory corruption or a system crash - * if they are in D3 while the system is put into S3 sleep. - */ -static void __devinit asus_ehci_no_d3(struct pci_dev *dev) -{ - const char *sys_info; - static const char good_Asus_board[] = "P8Z68-V"; - - if (dev->dev_flags & PCI_DEV_FLAGS_NO_D3_DURING_SLEEP) - return; - if (dev->subsystem_vendor != PCI_VENDOR_ID_ASUSTEK) - return; - sys_info = dmi_get_system_info(DMI_BOARD_NAME); - if (sys_info && memcmp(sys_info, good_Asus_board, - sizeof(good_Asus_board) - 1) == 0) - return; - - dev_info(&dev->dev, "broken D3 during system sleep on ASUS\n"); - dev->dev_flags |= PCI_DEV_FLAGS_NO_D3_DURING_SLEEP; - device_set_wakeup_capable(&dev->dev, false); -} -DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x1c26, asus_ehci_no_d3); -DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x1c2d, asus_ehci_no_d3); - static void pci_do_fixups(struct pci_dev *dev, struct pci_fixup *f, struct pci_fixup *end) { diff --git a/drivers/platform/x86/intel_ips.c b/drivers/platform/x86/intel_ips.c index 809a3ae..b46ec11 100644 --- a/drivers/platform/x86/intel_ips.c +++ b/drivers/platform/x86/intel_ips.c @@ -72,6 +72,7 @@ #include #include #include +#include #include #include #include @@ -1505,6 +1506,24 @@ static DEFINE_PCI_DEVICE_TABLE(ips_id_table) = { MODULE_DEVICE_TABLE(pci, ips_id_table); +static int ips_blacklist_callback(const struct dmi_system_id *id) +{ + pr_info("Blacklisted intel_ips for %s\n", id->ident); + return 1; +} + +static const struct dmi_system_id ips_blacklist[] = { + { + .callback = ips_blacklist_callback, + .ident = "HP ProBook", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"), + DMI_MATCH(DMI_PRODUCT_NAME, "HP ProBook"), + }, + }, + { } /* terminating entry */ +}; + static int ips_probe(struct pci_dev *dev, const struct pci_device_id *id) { u64 platform_info; @@ -1514,6 +1533,9 @@ static int ips_probe(struct pci_dev *dev, const struct pci_device_id *id) u16 htshi, trc, trc_required_mask; u8 tse; + if (dmi_check_system(ips_blacklist)) + return -ENODEV; + ips = kzalloc(sizeof(struct ips_driver), GFP_KERNEL); if (!ips) return -ENOMEM; diff --git a/drivers/platform/x86/samsung-laptop.c b/drivers/platform/x86/samsung-laptop.c index 09e26bf..af1e296 100644 --- a/drivers/platform/x86/samsung-laptop.c +++ b/drivers/platform/x86/samsung-laptop.c @@ -540,245 +540,34 @@ 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 1; -} - 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"), + DMI_MATCH(DMI_CHASSIS_TYPE, "8"), /* Portable */ }, - .callback = dmi_check_cb, }, { - .ident = "N510", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "SAMSUNG ELECTRONICS CO., LTD."), - DMI_MATCH(DMI_PRODUCT_NAME, "N510"), - DMI_MATCH(DMI_BOARD_NAME, "N510"), + DMI_MATCH(DMI_CHASSIS_TYPE, "9"), /* Laptop */ }, - .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"), + DMI_MATCH(DMI_CHASSIS_TYPE, "10"), /* Notebook */ }, - .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", - .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"), - }, - .callback = dmi_check_cb, - }, - { - .ident = "N220", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, - "SAMSUNG ELECTRONICS CO., LTD."), - DMI_MATCH(DMI_PRODUCT_NAME, "N220"), - DMI_MATCH(DMI_BOARD_NAME, "N220"), - }, - .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 = "R700", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "SAMSUNG ELECTRONICS CO., LTD."), - DMI_MATCH(DMI_PRODUCT_NAME, "SR700"), - DMI_MATCH(DMI_BOARD_NAME, "SR700"), - }, - .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, - }, - { - .ident = "R528/R728", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "SAMSUNG ELECTRONICS CO., LTD."), - DMI_MATCH(DMI_PRODUCT_NAME, "R528/R728"), - DMI_MATCH(DMI_BOARD_NAME, "R528/R728"), - }, - .callback = dmi_check_cb, - }, - { - .ident = "NC210/NC110", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "SAMSUNG ELECTRONICS CO., LTD."), - DMI_MATCH(DMI_PRODUCT_NAME, "NC210/NC110"), - DMI_MATCH(DMI_BOARD_NAME, "NC210/NC110"), - }, - .callback = dmi_check_cb, - }, - { - .ident = "X520", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "SAMSUNG ELECTRONICS CO., LTD."), - DMI_MATCH(DMI_PRODUCT_NAME, "X520"), - DMI_MATCH(DMI_BOARD_NAME, "X520"), + DMI_MATCH(DMI_CHASSIS_TYPE, "14"), /* Sub-Notebook */ }, - .callback = dmi_check_cb, }, { }, }; @@ -819,7 +608,8 @@ static int __init samsung_init(void) f0000_segment = ioremap_nocache(0xf0000, 0xffff); if (!f0000_segment) { - pr_err("Can't map the segment at 0xf0000\n"); + if (debug || force) + pr_err("Can't map the segment at 0xf0000\n"); return -EINVAL; } @@ -832,7 +622,8 @@ static int __init samsung_init(void) } if (loca == 0xffff) { - pr_err("This computer does not support SABI\n"); + if (debug || force) + pr_err("This computer does not support SABI\n"); goto error_no_signature; } diff --git a/drivers/rtc/rtc-mxc.c b/drivers/rtc/rtc-mxc.c index 39e41fb..5160354 100644 --- a/drivers/rtc/rtc-mxc.c +++ b/drivers/rtc/rtc-mxc.c @@ -191,10 +191,11 @@ static irqreturn_t mxc_rtc_interrupt(int irq, void *dev_id) struct platform_device *pdev = dev_id; struct rtc_plat_data *pdata = platform_get_drvdata(pdev); void __iomem *ioaddr = pdata->ioaddr; + unsigned long flags; u32 status; u32 events = 0; - spin_lock_irq(&pdata->rtc->irq_lock); + spin_lock_irqsave(&pdata->rtc->irq_lock, flags); status = readw(ioaddr + RTC_RTCISR) & readw(ioaddr + RTC_RTCIENR); /* clear interrupt sources */ writew(status, ioaddr + RTC_RTCISR); @@ -217,7 +218,7 @@ static irqreturn_t mxc_rtc_interrupt(int irq, void *dev_id) rtc_update_alarm(&pdev->dev, &pdata->g_rtc_alarm); rtc_update_irq(pdata->rtc, 1, events); - spin_unlock_irq(&pdata->rtc->irq_lock); + spin_unlock_irqrestore(&pdata->rtc->irq_lock, flags); return IRQ_HANDLED; } diff --git a/drivers/scsi/aic94xx/aic94xx_task.c b/drivers/scsi/aic94xx/aic94xx_task.c index 532d212..393e7ce 100644 --- a/drivers/scsi/aic94xx/aic94xx_task.c +++ b/drivers/scsi/aic94xx/aic94xx_task.c @@ -201,7 +201,7 @@ static void asd_get_response_tasklet(struct asd_ascb *ascb, if (SAS_STATUS_BUF_SIZE >= sizeof(*resp)) { resp->frame_len = le16_to_cpu(*(__le16 *)(r+6)); - memcpy(&resp->ending_fis[0], r+16, 24); + memcpy(&resp->ending_fis[0], r+16, ATA_RESP_FIS_SIZE); ts->buf_valid_size = sizeof(*resp); } } diff --git a/drivers/scsi/libsas/sas_ata.c b/drivers/scsi/libsas/sas_ata.c index db9238f..4868fc9 100644 --- a/drivers/scsi/libsas/sas_ata.c +++ b/drivers/scsi/libsas/sas_ata.c @@ -112,12 +112,12 @@ static void sas_ata_task_done(struct sas_task *task) if (stat->stat == SAS_PROTO_RESPONSE || stat->stat == SAM_STAT_GOOD || ((stat->stat == SAM_STAT_CHECK_CONDITION && dev->sata_dev.command_set == ATAPI_COMMAND_SET))) { - ata_tf_from_fis(resp->ending_fis, &dev->sata_dev.tf); + memcpy(dev->sata_dev.fis, resp->ending_fis, ATA_RESP_FIS_SIZE); if (!link->sactive) { - qc->err_mask |= ac_err_mask(dev->sata_dev.tf.command); + qc->err_mask |= ac_err_mask(dev->sata_dev.fis[2]); } else { - link->eh_info.err_mask |= ac_err_mask(dev->sata_dev.tf.command); + link->eh_info.err_mask |= ac_err_mask(dev->sata_dev.fis[2]); if (unlikely(link->eh_info.err_mask)) qc->flags |= ATA_QCFLAG_FAILED; } @@ -138,8 +138,8 @@ static void sas_ata_task_done(struct sas_task *task) qc->flags |= ATA_QCFLAG_FAILED; } - dev->sata_dev.tf.feature = 0x04; /* status err */ - dev->sata_dev.tf.command = ATA_ERR; + dev->sata_dev.fis[3] = 0x04; /* status err */ + dev->sata_dev.fis[2] = ATA_ERR; } } @@ -252,7 +252,7 @@ static bool sas_ata_qc_fill_rtf(struct ata_queued_cmd *qc) { struct domain_device *dev = qc->ap->private_data; - memcpy(&qc->result_tf, &dev->sata_dev.tf, sizeof(qc->result_tf)); + ata_tf_from_fis(dev->sata_dev.fis, &qc->result_tf); return true; } diff --git a/drivers/target/target_core_cdb.c b/drivers/target/target_core_cdb.c index 65ea65a..93b9406 100644 --- a/drivers/target/target_core_cdb.c +++ b/drivers/target/target_core_cdb.c @@ -1199,7 +1199,7 @@ int target_emulate_write_same(struct se_task *task) if (num_blocks != 0) range = num_blocks; else - range = (dev->transport->get_blocks(dev) - lba); + range = (dev->transport->get_blocks(dev) - lba) + 1; pr_debug("WRITE_SAME UNMAP: LBA: %llu Range: %llu\n", (unsigned long long)lba, (unsigned long long)range); diff --git a/drivers/target/target_core_pr.c b/drivers/target/target_core_pr.c index b75bc92..9145141 100644 --- a/drivers/target/target_core_pr.c +++ b/drivers/target/target_core_pr.c @@ -2042,7 +2042,7 @@ static int __core_scsi3_write_aptpl_to_file( if (IS_ERR(file) || !file || !file->f_dentry) { pr_err("filp_open(%s) for APTPL metadata" " failed\n", path); - return (PTR_ERR(file) < 0 ? PTR_ERR(file) : -ENOENT); + return IS_ERR(file) ? PTR_ERR(file) : -ENOENT; } iov[0].iov_base = &buf[0]; @@ -3853,7 +3853,7 @@ int target_scsi3_emulate_pr_out(struct se_task *task) " SPC-2 reservation is held, returning" " RESERVATION_CONFLICT\n"); cmd->scsi_sense_reason = TCM_RESERVATION_CONFLICT; - ret = EINVAL; + ret = -EINVAL; goto out; } @@ -3863,7 +3863,8 @@ int target_scsi3_emulate_pr_out(struct se_task *task) */ if (!cmd->se_sess) { cmd->scsi_sense_reason = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE; - return -EINVAL; + ret = -EINVAL; + goto out; } if (cmd->data_length < 24) { diff --git a/drivers/target/tcm_fc/tfc_cmd.c b/drivers/target/tcm_fc/tfc_cmd.c index d95cfe2..278819c 100644 --- a/drivers/target/tcm_fc/tfc_cmd.c +++ b/drivers/target/tcm_fc/tfc_cmd.c @@ -249,6 +249,8 @@ u32 ft_get_task_tag(struct se_cmd *se_cmd) { struct ft_cmd *cmd = container_of(se_cmd, struct ft_cmd, se_cmd); + if (cmd->aborted) + return ~0; return fc_seq_exch(cmd->seq)->rxid; } diff --git a/drivers/usb/class/cdc-wdm.c b/drivers/usb/class/cdc-wdm.c index 19fb5fa..9aaed0d 100644 --- a/drivers/usb/class/cdc-wdm.c +++ b/drivers/usb/class/cdc-wdm.c @@ -473,6 +473,8 @@ retry: goto retry; } if (!desc->reslength) { /* zero length read */ + dev_dbg(&desc->intf->dev, "%s: zero length - clearing WDM_READ\n", __func__); + clear_bit(WDM_READ, &desc->flags); spin_unlock_irq(&desc->iuspin); goto retry; } diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c index 52d27ed..175b6bb 100644 --- a/drivers/usb/core/hub.c +++ b/drivers/usb/core/hub.c @@ -2039,12 +2039,16 @@ static unsigned hub_is_wusb(struct usb_hub *hub) static int hub_port_reset(struct usb_hub *hub, int port1, struct usb_device *udev, unsigned int delay, bool warm); -/* Is a USB 3.0 port in the Inactive state? */ -static bool hub_port_inactive(struct usb_hub *hub, u16 portstatus) +/* Is a USB 3.0 port in the Inactive or Complinance Mode state? + * Port worm reset is required to recover + */ +static bool hub_port_warm_reset_required(struct usb_hub *hub, u16 portstatus) { return hub_is_superspeed(hub->hdev) && - (portstatus & USB_PORT_STAT_LINK_STATE) == - USB_SS_PORT_LS_SS_INACTIVE; + (((portstatus & USB_PORT_STAT_LINK_STATE) == + USB_SS_PORT_LS_SS_INACTIVE) || + ((portstatus & USB_PORT_STAT_LINK_STATE) == + USB_SS_PORT_LS_COMP_MOD)) ; } static int hub_port_wait_reset(struct usb_hub *hub, int port1, @@ -2080,7 +2084,7 @@ static int hub_port_wait_reset(struct usb_hub *hub, int port1, * * See https://bugzilla.kernel.org/show_bug.cgi?id=41752 */ - if (hub_port_inactive(hub, portstatus)) { + if (hub_port_warm_reset_required(hub, portstatus)) { int ret; if ((portchange & USB_PORT_STAT_C_CONNECTION)) @@ -3646,9 +3650,7 @@ static void hub_events(void) /* Warm reset a USB3 protocol port if it's in * SS.Inactive state. */ - if (hub_is_superspeed(hub->hdev) && - (portstatus & USB_PORT_STAT_LINK_STATE) - == USB_SS_PORT_LS_SS_INACTIVE) { + if (hub_port_warm_reset_required(hub, portstatus)) { dev_dbg(hub_dev, "warm reset port %d\n", i); hub_port_reset(hub, i, NULL, HUB_BH_RESET_TIME, true); diff --git a/drivers/usb/host/xhci-hub.c b/drivers/usb/host/xhci-hub.c index a8b2980..fd8a2c2 100644 --- a/drivers/usb/host/xhci-hub.c +++ b/drivers/usb/host/xhci-hub.c @@ -438,6 +438,42 @@ void xhci_test_and_clear_bit(struct xhci_hcd *xhci, __le32 __iomem **port_array, } } +/* Updates Link Status for super Speed port */ +static void xhci_hub_report_link_state(u32 *status, u32 status_reg) +{ + u32 pls = status_reg & PORT_PLS_MASK; + + /* resume state is a xHCI internal state. + * Do not report it to usb core. + */ + if (pls == XDEV_RESUME) + return; + + /* When the CAS bit is set then warm reset + * should be performed on port + */ + if (status_reg & PORT_CAS) { + /* The CAS bit can be set while the port is + * in any link state. + * Only roothubs have CAS bit, so we + * pretend to be in compliance mode + * unless we're already in compliance + * or the inactive state. + */ + if (pls != USB_SS_PORT_LS_COMP_MOD && + pls != USB_SS_PORT_LS_SS_INACTIVE) { + pls = USB_SS_PORT_LS_COMP_MOD; + } + /* Return also connection bit - + * hub state machine resets port + * when this bit is set. + */ + pls |= USB_PORT_STAT_CONNECTION; + } + /* update status field */ + *status |= pls; +} + int xhci_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue, u16 wIndex, char *buf, u16 wLength) { @@ -579,13 +615,9 @@ int xhci_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue, else status |= USB_PORT_STAT_POWER; } - /* Port Link State */ + /* Update Port Link State for super speed ports*/ if (hcd->speed == HCD_USB3) { - /* resume state is a xHCI internal state. - * Do not report it to usb core. - */ - if ((temp & PORT_PLS_MASK) != XDEV_RESUME) - status |= (temp & PORT_PLS_MASK); + xhci_hub_report_link_state(&status, temp); } if (bus_state->port_c_suspend & (1 << wIndex)) status |= 1 << USB_PORT_FEAT_C_SUSPEND; diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h index 363b141..7a56805 100644 --- a/drivers/usb/host/xhci.h +++ b/drivers/usb/host/xhci.h @@ -341,7 +341,11 @@ struct xhci_op_regs { #define PORT_PLC (1 << 22) /* port configure error change - port failed to configure its link partner */ #define PORT_CEC (1 << 23) -/* bit 24 reserved */ +/* Cold Attach Status - xHC can set this bit to report device attached during + * Sx state. Warm port reset should be perfomed to clear this bit and move port + * to connected state. + */ +#define PORT_CAS (1 << 24) /* wake on connect (enable) */ #define PORT_WKCONN_E (1 << 25) /* wake on disconnect (enable) */ diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index 21a4734..5971c95 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -496,6 +496,15 @@ static void option_instat_callback(struct urb *urb); /* MediaTek products */ #define MEDIATEK_VENDOR_ID 0x0e8d +#define MEDIATEK_PRODUCT_DC_1COM 0x00a0 +#define MEDIATEK_PRODUCT_DC_4COM 0x00a5 +#define MEDIATEK_PRODUCT_DC_5COM 0x00a4 +#define MEDIATEK_PRODUCT_7208_1COM 0x7101 +#define MEDIATEK_PRODUCT_7208_2COM 0x7102 +#define MEDIATEK_PRODUCT_FP_1COM 0x0003 +#define MEDIATEK_PRODUCT_FP_2COM 0x0023 +#define MEDIATEK_PRODUCT_FPDC_1COM 0x0043 +#define MEDIATEK_PRODUCT_FPDC_2COM 0x0033 /* Cellient products */ #define CELLIENT_VENDOR_ID 0x2692 @@ -553,6 +562,10 @@ static const struct option_blacklist_info net_intf1_blacklist = { .reserved = BIT(1), }; +static const struct option_blacklist_info net_intf2_blacklist = { + .reserved = BIT(2), +}; + static const struct option_blacklist_info net_intf3_blacklist = { .reserved = BIT(3), }; @@ -1093,6 +1106,8 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1298, 0xff, 0xff, 0xff) }, { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1299, 0xff, 0xff, 0xff) }, { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1300, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1402, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&net_intf2_blacklist }, { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x2002, 0xff, 0xff, 0xff), .driver_info = (kernel_ulong_t)&zte_k3765_z_blacklist }, { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x2003, 0xff, 0xff, 0xff) }, @@ -1234,6 +1249,17 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_AND_INTERFACE_INFO(MEDIATEK_VENDOR_ID, 0x00a1, 0xff, 0x02, 0x01) }, { USB_DEVICE_AND_INTERFACE_INFO(MEDIATEK_VENDOR_ID, 0x00a2, 0xff, 0x00, 0x00) }, { USB_DEVICE_AND_INTERFACE_INFO(MEDIATEK_VENDOR_ID, 0x00a2, 0xff, 0x02, 0x01) }, /* MediaTek MT6276M modem & app port */ + { USB_DEVICE_AND_INTERFACE_INFO(MEDIATEK_VENDOR_ID, MEDIATEK_PRODUCT_DC_1COM, 0x0a, 0x00, 0x00) }, + { USB_DEVICE_AND_INTERFACE_INFO(MEDIATEK_VENDOR_ID, MEDIATEK_PRODUCT_DC_5COM, 0xff, 0x02, 0x01) }, + { USB_DEVICE_AND_INTERFACE_INFO(MEDIATEK_VENDOR_ID, MEDIATEK_PRODUCT_DC_5COM, 0xff, 0x00, 0x00) }, + { USB_DEVICE_AND_INTERFACE_INFO(MEDIATEK_VENDOR_ID, MEDIATEK_PRODUCT_DC_4COM, 0xff, 0x02, 0x01) }, + { USB_DEVICE_AND_INTERFACE_INFO(MEDIATEK_VENDOR_ID, MEDIATEK_PRODUCT_DC_4COM, 0xff, 0x00, 0x00) }, + { USB_DEVICE_AND_INTERFACE_INFO(MEDIATEK_VENDOR_ID, MEDIATEK_PRODUCT_7208_1COM, 0x02, 0x00, 0x00) }, + { USB_DEVICE_AND_INTERFACE_INFO(MEDIATEK_VENDOR_ID, MEDIATEK_PRODUCT_7208_2COM, 0x02, 0x02, 0x01) }, + { USB_DEVICE_AND_INTERFACE_INFO(MEDIATEK_VENDOR_ID, MEDIATEK_PRODUCT_FP_1COM, 0x0a, 0x00, 0x00) }, + { USB_DEVICE_AND_INTERFACE_INFO(MEDIATEK_VENDOR_ID, MEDIATEK_PRODUCT_FP_2COM, 0x0a, 0x00, 0x00) }, + { USB_DEVICE_AND_INTERFACE_INFO(MEDIATEK_VENDOR_ID, MEDIATEK_PRODUCT_FPDC_1COM, 0x0a, 0x00, 0x00) }, + { USB_DEVICE_AND_INTERFACE_INFO(MEDIATEK_VENDOR_ID, MEDIATEK_PRODUCT_FPDC_2COM, 0x0a, 0x00, 0x00) }, { USB_DEVICE(CELLIENT_VENDOR_ID, CELLIENT_PRODUCT_MEN200) }, { } /* Terminating entry */ }; diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index c14c42b..ae66278 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -222,6 +222,8 @@ static int vhost_worker(void *data) if (work) { __set_current_state(TASK_RUNNING); work->fn(work); + if (need_resched()) + schedule(); } else schedule(); diff --git a/fs/buffer.c b/fs/buffer.c index c807931..4115eca 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -1087,6 +1087,9 @@ grow_buffers(struct block_device *bdev, sector_t block, int size) static struct buffer_head * __getblk_slow(struct block_device *bdev, sector_t block, int size) { + int ret; + struct buffer_head *bh; + /* Size must be multiple of hard sectorsize */ if (unlikely(size & (bdev_logical_block_size(bdev)-1) || (size < 512 || size > PAGE_SIZE))) { @@ -1099,20 +1102,21 @@ __getblk_slow(struct block_device *bdev, sector_t block, int size) return NULL; } - for (;;) { - struct buffer_head * bh; - int ret; +retry: + bh = __find_get_block(bdev, block, size); + if (bh) + return bh; + ret = grow_buffers(bdev, block, size); + if (ret == 0) { + free_more_memory(); + goto retry; + } else if (ret > 0) { bh = __find_get_block(bdev, block, size); if (bh) return bh; - - ret = grow_buffers(bdev, block, size); - if (ret < 0) - return NULL; - if (ret == 0) - free_more_memory(); } + return NULL; } /* diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index b21670c..56c152d 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -2925,6 +2925,18 @@ void cifs_setup_cifs_sb(struct smb_vol *pvolume_info, #define CIFS_DEFAULT_NON_POSIX_RSIZE (60 * 1024) #define CIFS_DEFAULT_NON_POSIX_WSIZE (65536) +/* + * On hosts with high memory, we can't currently support wsize/rsize that are + * larger than we can kmap at once. Cap the rsize/wsize at + * LAST_PKMAP * PAGE_SIZE. We'll never be able to fill a read or write request + * larger than that anyway. + */ +#ifdef CONFIG_HIGHMEM +#define CIFS_KMAP_SIZE_LIMIT (LAST_PKMAP * PAGE_CACHE_SIZE) +#else /* CONFIG_HIGHMEM */ +#define CIFS_KMAP_SIZE_LIMIT (1<<24) +#endif /* CONFIG_HIGHMEM */ + static unsigned int cifs_negotiate_wsize(struct cifs_tcon *tcon, struct smb_vol *pvolume_info) { @@ -2955,6 +2967,9 @@ cifs_negotiate_wsize(struct cifs_tcon *tcon, struct smb_vol *pvolume_info) wsize = min_t(unsigned int, wsize, server->maxBuf - sizeof(WRITE_REQ) + 4); + /* limit to the amount that we can kmap at once */ + wsize = min_t(unsigned int, wsize, CIFS_KMAP_SIZE_LIMIT); + /* hard limit of CIFS_MAX_WSIZE */ wsize = min_t(unsigned int, wsize, CIFS_MAX_WSIZE); @@ -2996,6 +3011,9 @@ cifs_negotiate_rsize(struct cifs_tcon *tcon, struct smb_vol *pvolume_info) if (!(server->capabilities & CAP_LARGE_READ_X)) rsize = min_t(unsigned int, CIFSMaxBufSize, rsize); + /* limit to the amount that we can kmap at once */ + rsize = min_t(unsigned int, rsize, CIFS_KMAP_SIZE_LIMIT); + /* hard limit of CIFS_MAX_RSIZE */ rsize = min_t(unsigned int, rsize, CIFS_MAX_RSIZE); diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c index db4a138..4c37ed4 100644 --- a/fs/cifs/readdir.c +++ b/fs/cifs/readdir.c @@ -86,9 +86,12 @@ cifs_readdir_lookup(struct dentry *parent, struct qstr *name, dentry = d_lookup(parent, name); if (dentry) { - /* FIXME: check for inode number changes? */ - if (dentry->d_inode != NULL) + inode = dentry->d_inode; + /* update inode in place if i_ino didn't change */ + if (inode && CIFS_I(inode)->uniqueid == fattr->cf_uniqueid) { + cifs_fattr_to_inode(inode, fattr); return dentry; + } d_drop(dentry); dput(dentry); } diff --git a/fs/ecryptfs/kthread.c b/fs/ecryptfs/kthread.c index 69f994a..0dbe58a 100644 --- a/fs/ecryptfs/kthread.c +++ b/fs/ecryptfs/kthread.c @@ -149,7 +149,7 @@ int ecryptfs_privileged_open(struct file **lower_file, (*lower_file) = dentry_open(lower_dentry, lower_mnt, flags, cred); if (!IS_ERR(*lower_file)) goto out; - if (flags & O_RDONLY) { + if ((flags & O_ACCMODE) == O_RDONLY) { rc = PTR_ERR((*lower_file)); goto out; } diff --git a/fs/ecryptfs/miscdev.c b/fs/ecryptfs/miscdev.c index 0dc5a3d..de42310 100644 --- a/fs/ecryptfs/miscdev.c +++ b/fs/ecryptfs/miscdev.c @@ -49,7 +49,10 @@ ecryptfs_miscdev_poll(struct file *file, poll_table *pt) mutex_lock(&ecryptfs_daemon_hash_mux); /* TODO: Just use file->private_data? */ rc = ecryptfs_find_daemon_by_euid(&daemon, euid, current_user_ns()); - BUG_ON(rc || !daemon); + if (rc || !daemon) { + mutex_unlock(&ecryptfs_daemon_hash_mux); + return -EINVAL; + } mutex_lock(&daemon->mux); mutex_unlock(&ecryptfs_daemon_hash_mux); if (daemon->flags & ECRYPTFS_DAEMON_ZOMBIE) { @@ -122,6 +125,7 @@ ecryptfs_miscdev_open(struct inode *inode, struct file *file) goto out_unlock_daemon; } daemon->flags |= ECRYPTFS_DAEMON_MISCDEV_OPEN; + file->private_data = daemon; atomic_inc(&ecryptfs_num_miscdev_opens); out_unlock_daemon: mutex_unlock(&daemon->mux); @@ -152,9 +156,9 @@ ecryptfs_miscdev_release(struct inode *inode, struct file *file) mutex_lock(&ecryptfs_daemon_hash_mux); rc = ecryptfs_find_daemon_by_euid(&daemon, euid, current_user_ns()); - BUG_ON(rc || !daemon); + if (rc || !daemon) + daemon = file->private_data; mutex_lock(&daemon->mux); - BUG_ON(daemon->pid != task_pid(current)); BUG_ON(!(daemon->flags & ECRYPTFS_DAEMON_MISCDEV_OPEN)); daemon->flags &= ~ECRYPTFS_DAEMON_MISCDEV_OPEN; atomic_dec(&ecryptfs_num_miscdev_opens); @@ -191,31 +195,32 @@ int ecryptfs_send_miscdev(char *data, size_t data_size, struct ecryptfs_msg_ctx *msg_ctx, u8 msg_type, u16 msg_flags, struct ecryptfs_daemon *daemon) { - int rc = 0; + struct ecryptfs_message *msg; - mutex_lock(&msg_ctx->mux); - msg_ctx->msg = kmalloc((sizeof(*msg_ctx->msg) + data_size), - GFP_KERNEL); - if (!msg_ctx->msg) { - rc = -ENOMEM; + msg = kmalloc((sizeof(*msg) + data_size), GFP_KERNEL); + if (!msg) { printk(KERN_ERR "%s: Out of memory whilst attempting " "to kmalloc(%zd, GFP_KERNEL)\n", __func__, - (sizeof(*msg_ctx->msg) + data_size)); - goto out_unlock; + (sizeof(*msg) + data_size)); + return -ENOMEM; } + + mutex_lock(&msg_ctx->mux); + msg_ctx->msg = msg; msg_ctx->msg->index = msg_ctx->index; msg_ctx->msg->data_len = data_size; msg_ctx->type = msg_type; memcpy(msg_ctx->msg->data, data, data_size); msg_ctx->msg_size = (sizeof(*msg_ctx->msg) + data_size); - mutex_lock(&daemon->mux); list_add_tail(&msg_ctx->daemon_out_list, &daemon->msg_ctx_out_queue); + mutex_unlock(&msg_ctx->mux); + + mutex_lock(&daemon->mux); daemon->num_queued_msg_ctx++; wake_up_interruptible(&daemon->wait); mutex_unlock(&daemon->mux); -out_unlock: - mutex_unlock(&msg_ctx->mux); - return rc; + + return 0; } /** @@ -246,8 +251,16 @@ ecryptfs_miscdev_read(struct file *file, char __user *buf, size_t count, mutex_lock(&ecryptfs_daemon_hash_mux); /* TODO: Just use file->private_data? */ rc = ecryptfs_find_daemon_by_euid(&daemon, euid, current_user_ns()); - BUG_ON(rc || !daemon); + if (rc || !daemon) { + mutex_unlock(&ecryptfs_daemon_hash_mux); + return -EINVAL; + } mutex_lock(&daemon->mux); + if (task_pid(current) != daemon->pid) { + mutex_unlock(&daemon->mux); + mutex_unlock(&ecryptfs_daemon_hash_mux); + return -EPERM; + } if (daemon->flags & ECRYPTFS_DAEMON_ZOMBIE) { rc = 0; mutex_unlock(&ecryptfs_daemon_hash_mux); @@ -284,9 +297,6 @@ check_list: * message from the queue; try again */ goto check_list; } - BUG_ON(euid != daemon->euid); - BUG_ON(current_user_ns() != daemon->user_ns); - BUG_ON(task_pid(current) != daemon->pid); msg_ctx = list_first_entry(&daemon->msg_ctx_out_queue, struct ecryptfs_msg_ctx, daemon_out_list); BUG_ON(!msg_ctx); diff --git a/fs/eventpoll.c b/fs/eventpoll.c index 4d9d3a4..a6f3763 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -1629,8 +1629,10 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd, if (op == EPOLL_CTL_ADD) { if (is_file_epoll(tfile)) { error = -ELOOP; - if (ep_loop_check(ep, tfile) != 0) + if (ep_loop_check(ep, tfile) != 0) { + clear_tfile_check_list(); goto error_tgt_fput; + } } else list_add(&tfile->f_tfile_llink, &tfile_check_list); } diff --git a/fs/exofs/ore.c b/fs/exofs/ore.c index 49cf230..24a49d4 100644 --- a/fs/exofs/ore.c +++ b/fs/exofs/ore.c @@ -735,13 +735,7 @@ static int _prepare_for_striping(struct ore_io_state *ios) out: ios->numdevs = devs_in_group; ios->pages_consumed = cur_pg; - if (unlikely(ret)) { - if (length == ios->length) - return ret; - else - ios->length -= length; - } - return 0; + return ret; } int ore_create(struct ore_io_state *ios) diff --git a/fs/exofs/ore_raid.c b/fs/exofs/ore_raid.c index d222c77..fff2070 100644 --- a/fs/exofs/ore_raid.c +++ b/fs/exofs/ore_raid.c @@ -461,16 +461,12 @@ static void _mark_read4write_pages_uptodate(struct ore_io_state *ios, int ret) * ios->sp2d[p][*], xor is calculated the same way. These pages are * allocated/freed and don't go through cache */ -static int _read_4_write(struct ore_io_state *ios) +static int _read_4_write_first_stripe(struct ore_io_state *ios) { - struct ore_io_state *ios_read; struct ore_striping_info read_si; struct __stripe_pages_2d *sp2d = ios->sp2d; u64 offset = ios->si.first_stripe_start; - u64 last_stripe_end; - unsigned bytes_in_stripe = ios->si.bytes_in_stripe; - unsigned i, c, p, min_p = sp2d->pages_in_unit, max_p = -1; - int ret; + unsigned c, p, min_p = sp2d->pages_in_unit, max_p = -1; if (offset == ios->offset) /* Go to start collect $200 */ goto read_last_stripe; @@ -478,6 +474,9 @@ static int _read_4_write(struct ore_io_state *ios) min_p = _sp2d_min_pg(sp2d); max_p = _sp2d_max_pg(sp2d); + ORE_DBGMSG("stripe_start=0x%llx ios->offset=0x%llx min_p=%d max_p=%d\n", + offset, ios->offset, min_p, max_p); + for (c = 0; ; c++) { ore_calc_stripe_info(ios->layout, offset, 0, &read_si); read_si.obj_offset += min_p * PAGE_SIZE; @@ -512,6 +511,18 @@ static int _read_4_write(struct ore_io_state *ios) } read_last_stripe: + return 0; +} + +static int _read_4_write_last_stripe(struct ore_io_state *ios) +{ + struct ore_striping_info read_si; + struct __stripe_pages_2d *sp2d = ios->sp2d; + u64 offset; + u64 last_stripe_end; + unsigned bytes_in_stripe = ios->si.bytes_in_stripe; + unsigned c, p, min_p = sp2d->pages_in_unit, max_p = -1; + offset = ios->offset + ios->length; if (offset % PAGE_SIZE) _add_to_r4w_last_page(ios, &offset); @@ -527,15 +538,15 @@ read_last_stripe: c = _dev_order(ios->layout->group_width * ios->layout->mirrors_p1, ios->layout->mirrors_p1, read_si.par_dev, read_si.dev); - BUG_ON(ios->si.first_stripe_start + bytes_in_stripe != last_stripe_end); - /* unaligned IO must be within a single stripe */ - if (min_p == sp2d->pages_in_unit) { /* Didn't do it yet */ min_p = _sp2d_min_pg(sp2d); max_p = _sp2d_max_pg(sp2d); } + ORE_DBGMSG("offset=0x%llx stripe_end=0x%llx min_p=%d max_p=%d\n", + offset, last_stripe_end, min_p, max_p); + while (offset < last_stripe_end) { struct __1_page_stripe *_1ps = &sp2d->_1p_stripes[p]; @@ -568,6 +579,15 @@ read_last_stripe: } read_it: + return 0; +} + +static int _read_4_write_execute(struct ore_io_state *ios) +{ + struct ore_io_state *ios_read; + unsigned i; + int ret; + ios_read = ios->ios_read_4_write; if (!ios_read) return 0; @@ -591,6 +611,8 @@ read_it: } _mark_read4write_pages_uptodate(ios_read, ret); + ore_put_io_state(ios_read); + ios->ios_read_4_write = NULL; /* Might need a reuse at last stripe */ return 0; } @@ -626,8 +648,11 @@ int _ore_add_parity_unit(struct ore_io_state *ios, /* If first stripe, Read in all read4write pages * (if needed) before we calculate the first parity. */ - _read_4_write(ios); + _read_4_write_first_stripe(ios); } + if (!cur_len) /* If last stripe r4w pages of last stripe */ + _read_4_write_last_stripe(ios); + _read_4_write_execute(ios); for (i = 0; i < num_pages; i++) { pages[i] = _raid_page_alloc(); @@ -654,34 +679,14 @@ int _ore_add_parity_unit(struct ore_io_state *ios, int _ore_post_alloc_raid_stuff(struct ore_io_state *ios) { - struct ore_layout *layout = ios->layout; - if (ios->parity_pages) { + struct ore_layout *layout = ios->layout; unsigned pages_in_unit = layout->stripe_unit / PAGE_SIZE; - unsigned stripe_size = ios->si.bytes_in_stripe; - u64 last_stripe, first_stripe; if (_sp2d_alloc(pages_in_unit, layout->group_width, layout->parity, &ios->sp2d)) { return -ENOMEM; } - - /* Round io down to last full strip */ - first_stripe = div_u64(ios->offset, stripe_size); - last_stripe = div_u64(ios->offset + ios->length, stripe_size); - - /* If an IO spans more then a single stripe it must end at - * a stripe boundary. The reminder at the end is pushed into the - * next IO. - */ - if (last_stripe != first_stripe) { - ios->length = last_stripe * stripe_size - ios->offset; - - BUG_ON(!ios->length); - ios->nr_pages = (ios->length + PAGE_SIZE - 1) / - PAGE_SIZE; - ios->si.length = ios->length; /*make it consistent */ - } } return 0; } diff --git a/fs/ext4/super.c b/fs/ext4/super.c index ab7aa3f..a93486e 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1097,7 +1097,7 @@ static int ext4_show_options(struct seq_file *seq, struct vfsmount *vfs) } if (sbi->s_max_batch_time != EXT4_DEF_MAX_BATCH_TIME) { seq_printf(seq, ",max_batch_time=%u", - (unsigned) sbi->s_min_batch_time); + (unsigned) sbi->s_max_batch_time); } /* diff --git a/fs/fifo.c b/fs/fifo.c index b1a524d..cf6f434 100644 --- a/fs/fifo.c +++ b/fs/fifo.c @@ -14,7 +14,7 @@ #include #include -static void wait_for_partner(struct inode* inode, unsigned int *cnt) +static int wait_for_partner(struct inode* inode, unsigned int *cnt) { int cur = *cnt; @@ -23,6 +23,7 @@ static void wait_for_partner(struct inode* inode, unsigned int *cnt) if (signal_pending(current)) break; } + return cur == *cnt ? -ERESTARTSYS : 0; } static void wake_up_partner(struct inode* inode) @@ -67,8 +68,7 @@ static int fifo_open(struct inode *inode, struct file *filp) * seen a writer */ filp->f_version = pipe->w_counter; } else { - wait_for_partner(inode, &pipe->w_counter); - if(signal_pending(current)) + if (wait_for_partner(inode, &pipe->w_counter)) goto err_rd; } } @@ -90,8 +90,7 @@ static int fifo_open(struct inode *inode, struct file *filp) wake_up_partner(inode); if (!pipe->readers) { - wait_for_partner(inode, &pipe->r_counter); - if (signal_pending(current)) + if (wait_for_partner(inode, &pipe->r_counter)) goto err_wr; } break; diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 2d0ca24..ebc2f4d 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -592,9 +592,15 @@ static int hugetlbfs_statfs(struct dentry *dentry, struct kstatfs *buf) spin_lock(&sbinfo->stat_lock); /* If no limits set, just report 0 for max/free/used * blocks, like simple_statfs() */ - if (sbinfo->max_blocks >= 0) { - buf->f_blocks = sbinfo->max_blocks; - buf->f_bavail = buf->f_bfree = sbinfo->free_blocks; + if (sbinfo->spool) { + long free_pages; + + spin_lock(&sbinfo->spool->lock); + buf->f_blocks = sbinfo->spool->max_hpages; + free_pages = sbinfo->spool->max_hpages + - sbinfo->spool->used_hpages; + buf->f_bavail = buf->f_bfree = free_pages; + spin_unlock(&sbinfo->spool->lock); buf->f_files = sbinfo->max_inodes; buf->f_ffree = sbinfo->free_inodes; } @@ -610,6 +616,10 @@ static void hugetlbfs_put_super(struct super_block *sb) if (sbi) { sb->s_fs_info = NULL; + + if (sbi->spool) + hugepage_put_subpool(sbi->spool); + kfree(sbi); } } @@ -841,10 +851,14 @@ hugetlbfs_fill_super(struct super_block *sb, void *data, int silent) sb->s_fs_info = sbinfo; sbinfo->hstate = config.hstate; spin_lock_init(&sbinfo->stat_lock); - sbinfo->max_blocks = config.nr_blocks; - sbinfo->free_blocks = config.nr_blocks; sbinfo->max_inodes = config.nr_inodes; sbinfo->free_inodes = config.nr_inodes; + sbinfo->spool = NULL; + if (config.nr_blocks != -1) { + sbinfo->spool = hugepage_new_subpool(config.nr_blocks); + if (!sbinfo->spool) + goto out_free; + } sb->s_maxbytes = MAX_LFS_FILESIZE; sb->s_blocksize = huge_page_size(config.hstate); sb->s_blocksize_bits = huge_page_shift(config.hstate); @@ -864,38 +878,12 @@ hugetlbfs_fill_super(struct super_block *sb, void *data, int silent) sb->s_root = root; return 0; out_free: + if (sbinfo->spool) + kfree(sbinfo->spool); kfree(sbinfo); return -ENOMEM; } -int hugetlb_get_quota(struct address_space *mapping, long delta) -{ - int ret = 0; - struct hugetlbfs_sb_info *sbinfo = HUGETLBFS_SB(mapping->host->i_sb); - - if (sbinfo->free_blocks > -1) { - spin_lock(&sbinfo->stat_lock); - if (sbinfo->free_blocks - delta >= 0) - sbinfo->free_blocks -= delta; - else - ret = -ENOMEM; - spin_unlock(&sbinfo->stat_lock); - } - - return ret; -} - -void hugetlb_put_quota(struct address_space *mapping, long delta) -{ - struct hugetlbfs_sb_info *sbinfo = HUGETLBFS_SB(mapping->host->i_sb); - - if (sbinfo->free_blocks > -1) { - spin_lock(&sbinfo->stat_lock); - sbinfo->free_blocks += delta; - spin_unlock(&sbinfo->stat_lock); - } -} - static struct dentry *hugetlbfs_mount(struct file_system_type *fs_type, int flags, const char *dev_name, void *data) { diff --git a/fs/locks.c b/fs/locks.c index 0d68f1f..6a64f15 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -1465,7 +1465,7 @@ int generic_setlease(struct file *filp, long arg, struct file_lock **flp) case F_WRLCK: return generic_add_lease(filp, arg, flp); default: - BUG(); + return -EINVAL; } } EXPORT_SYMBOL(generic_setlease); diff --git a/fs/nfs/idmap.c b/fs/nfs/idmap.c index 47d1c6f..b122af8 100644 --- a/fs/nfs/idmap.c +++ b/fs/nfs/idmap.c @@ -318,12 +318,12 @@ struct idmap_hashent { unsigned long ih_expires; __u32 ih_id; size_t ih_namelen; - char ih_name[IDMAP_NAMESZ]; + const char *ih_name; }; struct idmap_hashtable { __u8 h_type; - struct idmap_hashent h_entries[IDMAP_HASH_SZ]; + struct idmap_hashent *h_entries; }; struct idmap { @@ -378,6 +378,28 @@ nfs_idmap_new(struct nfs_client *clp) return 0; } +static void +idmap_alloc_hashtable(struct idmap_hashtable *h) +{ + if (h->h_entries != NULL) + return; + h->h_entries = kcalloc(IDMAP_HASH_SZ, + sizeof(*h->h_entries), + GFP_KERNEL); +} + +static void +idmap_free_hashtable(struct idmap_hashtable *h) +{ + int i; + + if (h->h_entries == NULL) + return; + for (i = 0; i < IDMAP_HASH_SZ; i++) + kfree(h->h_entries[i].ih_name); + kfree(h->h_entries); +} + void nfs_idmap_delete(struct nfs_client *clp) { @@ -387,6 +409,8 @@ nfs_idmap_delete(struct nfs_client *clp) return; rpc_unlink(idmap->idmap_dentry); clp->cl_idmap = NULL; + idmap_free_hashtable(&idmap->idmap_user_hash); + idmap_free_hashtable(&idmap->idmap_group_hash); kfree(idmap); } @@ -396,6 +420,8 @@ nfs_idmap_delete(struct nfs_client *clp) static inline struct idmap_hashent * idmap_name_hash(struct idmap_hashtable* h, const char *name, size_t len) { + if (h->h_entries == NULL) + return NULL; return &h->h_entries[fnvhash32(name, len) % IDMAP_HASH_SZ]; } @@ -404,6 +430,8 @@ idmap_lookup_name(struct idmap_hashtable *h, const char *name, size_t len) { struct idmap_hashent *he = idmap_name_hash(h, name, len); + if (he == NULL) + return NULL; if (he->ih_namelen != len || memcmp(he->ih_name, name, len) != 0) return NULL; if (time_after(jiffies, he->ih_expires)) @@ -414,6 +442,8 @@ idmap_lookup_name(struct idmap_hashtable *h, const char *name, size_t len) static inline struct idmap_hashent * idmap_id_hash(struct idmap_hashtable* h, __u32 id) { + if (h->h_entries == NULL) + return NULL; return &h->h_entries[fnvhash32(&id, sizeof(id)) % IDMAP_HASH_SZ]; } @@ -421,6 +451,9 @@ static struct idmap_hashent * idmap_lookup_id(struct idmap_hashtable *h, __u32 id) { struct idmap_hashent *he = idmap_id_hash(h, id); + + if (he == NULL) + return NULL; if (he->ih_id != id || he->ih_namelen == 0) return NULL; if (time_after(jiffies, he->ih_expires)) @@ -436,12 +469,14 @@ idmap_lookup_id(struct idmap_hashtable *h, __u32 id) static inline struct idmap_hashent * idmap_alloc_name(struct idmap_hashtable *h, char *name, size_t len) { + idmap_alloc_hashtable(h); return idmap_name_hash(h, name, len); } static inline struct idmap_hashent * idmap_alloc_id(struct idmap_hashtable *h, __u32 id) { + idmap_alloc_hashtable(h); return idmap_id_hash(h, id); } @@ -449,9 +484,14 @@ static void idmap_update_entry(struct idmap_hashent *he, const char *name, size_t namelen, __u32 id) { + char *str = kmalloc(namelen + 1, GFP_KERNEL); + if (str == NULL) + return; + kfree(he->ih_name); he->ih_id = id; - memcpy(he->ih_name, name, namelen); - he->ih_name[namelen] = '\0'; + memcpy(str, name, namelen); + str[namelen] = '\0'; + he->ih_name = str; he->ih_namelen = namelen; he->ih_expires = jiffies + nfs_idmap_cache_timeout; } diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index 66020ac..07354b7 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -1186,8 +1186,9 @@ restart: spin_lock(&state->state_lock); list_for_each_entry(lock, &state->lock_states, ls_locks) { if (!(lock->ls_flags & NFS_LOCK_INITIALIZED)) - printk("%s: Lock reclaim failed!\n", - __func__); + pr_warn_ratelimited("NFS: " + "%s: Lock reclaim " + "failed!\n", __func__); } spin_unlock(&state->state_lock); nfs4_put_open_state(state); diff --git a/fs/nfs/objlayout/objio_osd.c b/fs/nfs/objlayout/objio_osd.c index 55d0128..a03ee52 100644 --- a/fs/nfs/objlayout/objio_osd.c +++ b/fs/nfs/objlayout/objio_osd.c @@ -433,7 +433,10 @@ int objio_read_pagelist(struct nfs_read_data *rdata) objios->ios->done = _read_done; dprintk("%s: offset=0x%llx length=0x%x\n", __func__, rdata->args.offset, rdata->args.count); - return ore_read(objios->ios); + ret = ore_read(objios->ios); + if (unlikely(ret)) + objio_free_result(&objios->oir); + return ret; } /* @@ -464,8 +467,16 @@ static struct page *__r4w_get_page(void *priv, u64 offset, bool *uptodate) struct objio_state *objios = priv; struct nfs_write_data *wdata = objios->oir.rpcdata; pgoff_t index = offset / PAGE_SIZE; - struct page *page = find_get_page(wdata->inode->i_mapping, index); + struct page *page; + loff_t i_size = i_size_read(wdata->inode); + + if (offset >= i_size) { + *uptodate = true; + dprintk("%s: g_zero_page index=0x%lx\n", __func__, index); + return ZERO_PAGE(0); + } + page = find_get_page(wdata->inode->i_mapping, index); if (!page) { page = find_or_create_page(wdata->inode->i_mapping, index, GFP_NOFS); @@ -486,8 +497,10 @@ static struct page *__r4w_get_page(void *priv, u64 offset, bool *uptodate) static void __r4w_put_page(void *priv, struct page *page) { - dprintk("%s: index=0x%lx\n", __func__, page->index); - page_cache_release(page); + dprintk("%s: index=0x%lx\n", __func__, + (page == ZERO_PAGE(0)) ? -1UL : page->index); + if (ZERO_PAGE(0) != page) + page_cache_release(page); return; } @@ -517,8 +530,10 @@ int objio_write_pagelist(struct nfs_write_data *wdata, int how) dprintk("%s: offset=0x%llx length=0x%x\n", __func__, wdata->args.offset, wdata->args.count); ret = ore_write(objios->ios); - if (unlikely(ret)) + if (unlikely(ret)) { + objio_free_result(&objios->oir); return ret; + } if (objios->sync) _write_done(objios->ios, objios); diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index 07ee5b4..1c7d45e 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -1950,7 +1950,7 @@ static int __ocfs2_change_file_space(struct file *file, struct inode *inode, if (ret < 0) mlog_errno(ret); - if (file->f_flags & O_SYNC) + if (file && (file->f_flags & O_SYNC)) handle->h_sync = 1; ocfs2_commit_trans(osb, handle); diff --git a/fs/ramfs/file-nommu.c b/fs/ramfs/file-nommu.c index fbb0b47..d5378d0 100644 --- a/fs/ramfs/file-nommu.c +++ b/fs/ramfs/file-nommu.c @@ -110,6 +110,7 @@ int ramfs_nommu_expand_for_mapping(struct inode *inode, size_t newsize) /* prevent the page from being discarded on memory pressure */ SetPageDirty(page); + SetPageUptodate(page); unlock_page(page); put_page(page); diff --git a/fs/ubifs/sb.c b/fs/ubifs/sb.c index 6094c5a..b73ecd8 100644 --- a/fs/ubifs/sb.c +++ b/fs/ubifs/sb.c @@ -715,8 +715,12 @@ static int fixup_free_space(struct ubifs_info *c) lnum = ubifs_next_log_lnum(c, lnum); } - /* Fixup the current log head */ - err = fixup_leb(c, c->lhead_lnum, c->lhead_offs); + /* + * Fixup the log head which contains the only a CS node at the + * beginning. + */ + err = fixup_leb(c, c->lhead_lnum, + ALIGN(UBIFS_CS_NODE_SZ, c->min_io_size)); if (err) goto out; diff --git a/include/linux/Kbuild b/include/linux/Kbuild index bd21ecd..a3ce901 100644 --- a/include/linux/Kbuild +++ b/include/linux/Kbuild @@ -268,6 +268,7 @@ header-y += netfilter_ipv4.h header-y += netfilter_ipv6.h header-y += netlink.h header-y += netrom.h +header-y += nfc.h header-y += nfs.h header-y += nfs2.h header-y += nfs3.h diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index fd0dc30..cc07d27 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -165,6 +165,7 @@ enum hrtimer_base_type { * @lock: lock protecting the base and associated clock bases * and timers * @active_bases: Bitfield to mark bases with active timers + * @clock_was_set: Indicates that clock was set from irq context. * @expires_next: absolute time of the next event which was scheduled * via clock_set_next_event() * @hres_active: State of high resolution mode @@ -177,7 +178,8 @@ enum hrtimer_base_type { */ struct hrtimer_cpu_base { raw_spinlock_t lock; - unsigned long active_bases; + unsigned int active_bases; + unsigned int clock_was_set; #ifdef CONFIG_HIGH_RES_TIMERS ktime_t expires_next; int hres_active; @@ -286,6 +288,8 @@ extern void hrtimer_peek_ahead_timers(void); # define MONOTONIC_RES_NSEC HIGH_RES_NSEC # define KTIME_MONOTONIC_RES KTIME_HIGH_RES +extern void clock_was_set_delayed(void); + #else # define MONOTONIC_RES_NSEC LOW_RES_NSEC @@ -306,6 +310,9 @@ static inline int hrtimer_is_hres_active(struct hrtimer *timer) { return 0; } + +static inline void clock_was_set_delayed(void) { } + #endif extern void clock_was_set(void); @@ -320,6 +327,7 @@ extern ktime_t ktime_get(void); extern ktime_t ktime_get_real(void); extern ktime_t ktime_get_boottime(void); extern ktime_t ktime_get_monotonic_offset(void); +extern ktime_t ktime_get_update_offsets(ktime_t *offs_real, ktime_t *offs_boot); DECLARE_PER_CPU(struct tick_device, tick_cpu_device); diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index d9d6c86..c5ed2f1 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -14,6 +14,15 @@ struct user_struct; #include #include +struct hugepage_subpool { + spinlock_t lock; + long count; + long max_hpages, used_hpages; +}; + +struct hugepage_subpool *hugepage_new_subpool(long nr_blocks); +void hugepage_put_subpool(struct hugepage_subpool *spool); + int PageHuge(struct page *page); void reset_vma_resv_huge_pages(struct vm_area_struct *vma); @@ -138,12 +147,11 @@ struct hugetlbfs_config { }; struct hugetlbfs_sb_info { - long max_blocks; /* blocks allowed */ - long free_blocks; /* blocks free */ long max_inodes; /* inodes allowed */ long free_inodes; /* inodes free */ spinlock_t stat_lock; struct hstate *hstate; + struct hugepage_subpool *spool; }; @@ -166,8 +174,6 @@ extern const struct file_operations hugetlbfs_file_operations; extern const struct vm_operations_struct hugetlb_vm_ops; struct file *hugetlb_file_setup(const char *name, size_t size, vm_flags_t acct, struct user_struct **user, int creat_flags); -int hugetlb_get_quota(struct address_space *mapping, long delta); -void hugetlb_put_quota(struct address_space *mapping, long delta); static inline int is_file_hugepages(struct file *file) { diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 188cb2f..905b1e1 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -652,7 +652,7 @@ typedef struct pglist_data { range, including holes */ int node_id; wait_queue_head_t kswapd_wait; - struct task_struct *kswapd; + struct task_struct *kswapd; /* Protected by lock_memory_hotplug() */ int kswapd_max_order; enum zone_type classzone_idx; } pg_data_t; diff --git a/include/linux/pci.h b/include/linux/pci.h index c0cfa0d..7cda65b 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -176,8 +176,6 @@ enum pci_dev_flags { PCI_DEV_FLAGS_NO_D3 = (__force pci_dev_flags_t) 2, /* Provide indication device is assigned by a Virtual Machine Manager */ PCI_DEV_FLAGS_ASSIGNED = (__force pci_dev_flags_t) 4, - /* Device causes system crash if in D3 during S3 sleep */ - PCI_DEV_FLAGS_NO_D3_DURING_SLEEP = (__force pci_dev_flags_t) 8, }; enum pci_irq_reroute_variant { diff --git a/include/linux/sched.h b/include/linux/sched.h index 1c4f3e9..5afa2a3 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1892,6 +1892,14 @@ static inline int set_cpus_allowed_ptr(struct task_struct *p, } #endif +#ifdef CONFIG_NO_HZ +void calc_load_enter_idle(void); +void calc_load_exit_idle(void); +#else +static inline void calc_load_enter_idle(void) { } +static inline void calc_load_exit_idle(void) { } +#endif /* CONFIG_NO_HZ */ + #ifndef CONFIG_CPUMASK_OFFSTACK static inline int set_cpus_allowed(struct task_struct *p, cpumask_t new_mask) { diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index bdb4590..53dc7e7 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -213,11 +213,8 @@ enum { /* device driver is going to provide hardware time stamp */ SKBTX_IN_PROGRESS = 1 << 2, - /* ensure the originating sk reference is available on driver level */ - SKBTX_DRV_NEEDS_SK_REF = 1 << 3, - /* device driver supports TX zero-copy buffers */ - SKBTX_DEV_ZEROCOPY = 1 << 4, + SKBTX_DEV_ZEROCOPY = 1 << 3, }; /* diff --git a/include/linux/timex.h b/include/linux/timex.h index aa60fe7..08e90fb 100644 --- a/include/linux/timex.h +++ b/include/linux/timex.h @@ -266,7 +266,7 @@ static inline int ntp_synced(void) /* Returns how long ticks are at present, in ns / 2^NTP_SCALE_SHIFT. */ extern u64 tick_length; -extern void second_overflow(void); +extern int second_overflow(unsigned long secs); extern void update_ntp_one_tick(void); extern int do_adjtimex(struct timex *); extern void hardpps(const struct timespec *, const struct timespec *); diff --git a/include/scsi/libsas.h b/include/scsi/libsas.h index 6a308d4..1e100c6 100644 --- a/include/scsi/libsas.h +++ b/include/scsi/libsas.h @@ -159,6 +159,8 @@ enum ata_command_set { ATAPI_COMMAND_SET = 1, }; +#define ATA_RESP_FIS_SIZE 24 + struct sata_device { enum ata_command_set command_set; struct smp_resp rps_resp; /* report_phy_sata_resp */ @@ -170,7 +172,7 @@ struct sata_device { struct ata_port *ap; struct ata_host ata_host; - struct ata_taskfile tf; + u8 fis[ATA_RESP_FIS_SIZE]; u32 sstatus; u32 serror; u32 scontrol; @@ -486,7 +488,7 @@ enum exec_status { */ struct ata_task_resp { u16 frame_len; - u8 ending_fis[24]; /* dev to host or data-in */ + u8 ending_fis[ATA_RESP_FIS_SIZE]; /* dev to host or data-in */ u32 sstatus; u32 serror; u32 scontrol; diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c index ae34bf5..6db7a5e 100644 --- a/kernel/hrtimer.c +++ b/kernel/hrtimer.c @@ -657,6 +657,14 @@ static inline int hrtimer_enqueue_reprogram(struct hrtimer *timer, return 0; } +static inline ktime_t hrtimer_update_base(struct hrtimer_cpu_base *base) +{ + ktime_t *offs_real = &base->clock_base[HRTIMER_BASE_REALTIME].offset; + ktime_t *offs_boot = &base->clock_base[HRTIMER_BASE_BOOTTIME].offset; + + return ktime_get_update_offsets(offs_real, offs_boot); +} + /* * Retrigger next event is called after clock was set * @@ -665,22 +673,12 @@ static inline int hrtimer_enqueue_reprogram(struct hrtimer *timer, static void retrigger_next_event(void *arg) { struct hrtimer_cpu_base *base = &__get_cpu_var(hrtimer_bases); - struct timespec realtime_offset, xtim, wtm, sleep; if (!hrtimer_hres_active()) return; - /* Optimized out for !HIGH_RES */ - get_xtime_and_monotonic_and_sleep_offset(&xtim, &wtm, &sleep); - set_normalized_timespec(&realtime_offset, -wtm.tv_sec, -wtm.tv_nsec); - - /* Adjust CLOCK_REALTIME offset */ raw_spin_lock(&base->lock); - base->clock_base[HRTIMER_BASE_REALTIME].offset = - timespec_to_ktime(realtime_offset); - base->clock_base[HRTIMER_BASE_BOOTTIME].offset = - timespec_to_ktime(sleep); - + hrtimer_update_base(base); hrtimer_force_reprogram(base, 0); raw_spin_unlock(&base->lock); } @@ -710,13 +708,25 @@ static int hrtimer_switch_to_hres(void) base->clock_base[i].resolution = KTIME_HIGH_RES; tick_setup_sched_timer(); - /* "Retrigger" the interrupt to get things going */ retrigger_next_event(NULL); local_irq_restore(flags); return 1; } +/* + * Called from timekeeping code to reprogramm the hrtimer interrupt + * device. If called from the timer interrupt context we defer it to + * softirq context. + */ +void clock_was_set_delayed(void) +{ + struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases); + + cpu_base->clock_was_set = 1; + __raise_softirq_irqoff(HRTIMER_SOFTIRQ); +} + #else static inline int hrtimer_hres_active(void) { return 0; } @@ -1250,11 +1260,10 @@ void hrtimer_interrupt(struct clock_event_device *dev) cpu_base->nr_events++; dev->next_event.tv64 = KTIME_MAX; - entry_time = now = ktime_get(); + raw_spin_lock(&cpu_base->lock); + entry_time = now = hrtimer_update_base(cpu_base); retry: expires_next.tv64 = KTIME_MAX; - - raw_spin_lock(&cpu_base->lock); /* * We set expires_next to KTIME_MAX here with cpu_base->lock * held to prevent that a timer is enqueued in our queue via @@ -1330,8 +1339,12 @@ retry: * We need to prevent that we loop forever in the hrtimer * interrupt routine. We give it 3 attempts to avoid * overreacting on some spurious event. + * + * Acquire base lock for updating the offsets and retrieving + * the current time. */ - now = ktime_get(); + raw_spin_lock(&cpu_base->lock); + now = hrtimer_update_base(cpu_base); cpu_base->nr_retries++; if (++retries < 3) goto retry; @@ -1343,6 +1356,7 @@ retry: */ cpu_base->nr_hangs++; cpu_base->hang_detected = 1; + raw_spin_unlock(&cpu_base->lock); delta = ktime_sub(now, entry_time); if (delta.tv64 > cpu_base->max_hang_time.tv64) cpu_base->max_hang_time = delta; @@ -1395,6 +1409,13 @@ void hrtimer_peek_ahead_timers(void) static void run_hrtimer_softirq(struct softirq_action *h) { + struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases); + + if (cpu_base->clock_was_set) { + cpu_base->clock_was_set = 0; + clock_was_set(); + } + hrtimer_peek_ahead_timers(); } diff --git a/kernel/power/swap.c b/kernel/power/swap.c index b313086..64f8f97 100644 --- a/kernel/power/swap.c +++ b/kernel/power/swap.c @@ -6,7 +6,7 @@ * * Copyright (C) 1998,2001-2005 Pavel Machek * Copyright (C) 2006 Rafael J. Wysocki - * Copyright (C) 2010 Bojan Smojver + * Copyright (C) 2010-2012 Bojan Smojver * * This file is released under the GPLv2. * @@ -283,14 +283,17 @@ static int write_page(void *buf, sector_t offset, struct bio **bio_chain) return -ENOSPC; if (bio_chain) { - src = (void *)__get_free_page(__GFP_WAIT | __GFP_HIGH); + src = (void *)__get_free_page(__GFP_WAIT | __GFP_NOWARN | + __GFP_NORETRY); if (src) { copy_page(src, buf); } else { ret = hib_wait_on_bio_chain(bio_chain); /* Free pages */ if (ret) return ret; - src = (void *)__get_free_page(__GFP_WAIT | __GFP_HIGH); + src = (void *)__get_free_page(__GFP_WAIT | + __GFP_NOWARN | + __GFP_NORETRY); if (src) { copy_page(src, buf); } else { @@ -368,12 +371,17 @@ static int swap_write_page(struct swap_map_handle *handle, void *buf, clear_page(handle->cur); handle->cur_swap = offset; handle->k = 0; - } - if (bio_chain && low_free_pages() <= handle->reqd_free_pages) { - error = hib_wait_on_bio_chain(bio_chain); - if (error) - goto out; - handle->reqd_free_pages = reqd_free_pages(); + + if (bio_chain && low_free_pages() <= handle->reqd_free_pages) { + error = hib_wait_on_bio_chain(bio_chain); + if (error) + goto out; + /* + * Recalculate the number of required free pages, to + * make sure we never take more than half. + */ + handle->reqd_free_pages = reqd_free_pages(); + } } out: return error; @@ -420,8 +428,9 @@ static int swap_writer_finish(struct swap_map_handle *handle, /* Maximum number of threads for compression/decompression. */ #define LZO_THREADS 3 -/* Maximum number of pages for read buffering. */ -#define LZO_READ_PAGES (MAP_PAGE_ENTRIES * 8) +/* Minimum/maximum number of pages for read buffering. */ +#define LZO_MIN_RD_PAGES 1024 +#define LZO_MAX_RD_PAGES 8192 /** @@ -632,12 +641,6 @@ static int save_image_lzo(struct swap_map_handle *handle, } /* - * Adjust number of free pages after all allocations have been done. - * We don't want to run out of pages when writing. - */ - handle->reqd_free_pages = reqd_free_pages(); - - /* * Start the CRC32 thread. */ init_waitqueue_head(&crc->go); @@ -658,6 +661,12 @@ static int save_image_lzo(struct swap_map_handle *handle, goto out_clean; } + /* + * Adjust the number of required free pages after all allocations have + * been done. We don't want to run out of pages when writing. + */ + handle->reqd_free_pages = reqd_free_pages(); + printk(KERN_INFO "PM: Using %u thread(s) for compression.\n" "PM: Compressing and saving image data (%u pages) ... ", @@ -1067,7 +1076,7 @@ static int load_image_lzo(struct swap_map_handle *handle, unsigned i, thr, run_threads, nr_threads; unsigned ring = 0, pg = 0, ring_size = 0, have = 0, want, need, asked = 0; - unsigned long read_pages; + unsigned long read_pages = 0; unsigned char **page = NULL; struct dec_data *data = NULL; struct crc_data *crc = NULL; @@ -1079,7 +1088,7 @@ static int load_image_lzo(struct swap_map_handle *handle, nr_threads = num_online_cpus() - 1; nr_threads = clamp_val(nr_threads, 1, LZO_THREADS); - page = vmalloc(sizeof(*page) * LZO_READ_PAGES); + page = vmalloc(sizeof(*page) * LZO_MAX_RD_PAGES); if (!page) { printk(KERN_ERR "PM: Failed to allocate LZO page\n"); ret = -ENOMEM; @@ -1144,15 +1153,22 @@ static int load_image_lzo(struct swap_map_handle *handle, } /* - * Adjust number of pages for read buffering, in case we are short. + * Set the number of pages for read buffering. + * This is complete guesswork, because we'll only know the real + * picture once prepare_image() is called, which is much later on + * during the image load phase. We'll assume the worst case and + * say that none of the image pages are from high memory. */ - read_pages = (nr_free_pages() - snapshot_get_image_size()) >> 1; - read_pages = clamp_val(read_pages, LZO_CMP_PAGES, LZO_READ_PAGES); + if (low_free_pages() > snapshot_get_image_size()) + read_pages = (low_free_pages() - snapshot_get_image_size()) / 2; + read_pages = clamp_val(read_pages, LZO_MIN_RD_PAGES, LZO_MAX_RD_PAGES); for (i = 0; i < read_pages; i++) { page[i] = (void *)__get_free_page(i < LZO_CMP_PAGES ? __GFP_WAIT | __GFP_HIGH : - __GFP_WAIT); + __GFP_WAIT | __GFP_NOWARN | + __GFP_NORETRY); + if (!page[i]) { if (i < LZO_CMP_PAGES) { ring_size = i; diff --git a/kernel/sched.c b/kernel/sched.c index 576a27f..52ac69b 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -1885,7 +1885,6 @@ static void double_rq_unlock(struct rq *rq1, struct rq *rq2) #endif -static void calc_load_account_idle(struct rq *this_rq); static void update_sysctl(void); static int get_update_sysctl_factor(void); static void update_cpu_load(struct rq *this_rq); @@ -3401,11 +3400,73 @@ unsigned long this_cpu_load(void) } +/* + * Global load-average calculations + * + * We take a distributed and async approach to calculating the global load-avg + * in order to minimize overhead. + * + * The global load average is an exponentially decaying average of nr_running + + * nr_uninterruptible. + * + * Once every LOAD_FREQ: + * + * nr_active = 0; + * for_each_possible_cpu(cpu) + * nr_active += cpu_of(cpu)->nr_running + cpu_of(cpu)->nr_uninterruptible; + * + * avenrun[n] = avenrun[0] * exp_n + nr_active * (1 - exp_n) + * + * Due to a number of reasons the above turns in the mess below: + * + * - for_each_possible_cpu() is prohibitively expensive on machines with + * serious number of cpus, therefore we need to take a distributed approach + * to calculating nr_active. + * + * \Sum_i x_i(t) = \Sum_i x_i(t) - x_i(t_0) | x_i(t_0) := 0 + * = \Sum_i { \Sum_j=1 x_i(t_j) - x_i(t_j-1) } + * + * So assuming nr_active := 0 when we start out -- true per definition, we + * can simply take per-cpu deltas and fold those into a global accumulate + * to obtain the same result. See calc_load_fold_active(). + * + * Furthermore, in order to avoid synchronizing all per-cpu delta folding + * across the machine, we assume 10 ticks is sufficient time for every + * cpu to have completed this task. + * + * This places an upper-bound on the IRQ-off latency of the machine. Then + * again, being late doesn't loose the delta, just wrecks the sample. + * + * - cpu_rq()->nr_uninterruptible isn't accurately tracked per-cpu because + * this would add another cross-cpu cacheline miss and atomic operation + * to the wakeup path. Instead we increment on whatever cpu the task ran + * when it went into uninterruptible state and decrement on whatever cpu + * did the wakeup. This means that only the sum of nr_uninterruptible over + * all cpus yields the correct result. + * + * This covers the NO_HZ=n code, for extra head-aches, see the comment below. + */ + /* Variables and functions for calc_load */ static atomic_long_t calc_load_tasks; static unsigned long calc_load_update; unsigned long avenrun[3]; -EXPORT_SYMBOL(avenrun); +EXPORT_SYMBOL(avenrun); /* should be removed */ + +/** + * get_avenrun - get the load average array + * @loads: pointer to dest load array + * @offset: offset to add + * @shift: shift count to shift the result left + * + * These values are estimates at best, so no need for locking. + */ +void get_avenrun(unsigned long *loads, unsigned long offset, int shift) +{ + loads[0] = (avenrun[0] + offset) << shift; + loads[1] = (avenrun[1] + offset) << shift; + loads[2] = (avenrun[2] + offset) << shift; +} static long calc_load_fold_active(struct rq *this_rq) { @@ -3422,6 +3483,9 @@ static long calc_load_fold_active(struct rq *this_rq) return delta; } +/* + * a1 = a0 * e + a * (1 - e) + */ static unsigned long calc_load(unsigned long load, unsigned long exp, unsigned long active) { @@ -3433,30 +3497,118 @@ calc_load(unsigned long load, unsigned long exp, unsigned long active) #ifdef CONFIG_NO_HZ /* - * For NO_HZ we delay the active fold to the next LOAD_FREQ update. + * Handle NO_HZ for the global load-average. + * + * Since the above described distributed algorithm to compute the global + * load-average relies on per-cpu sampling from the tick, it is affected by + * NO_HZ. + * + * The basic idea is to fold the nr_active delta into a global idle-delta upon + * entering NO_HZ state such that we can include this as an 'extra' cpu delta + * when we read the global state. + * + * Obviously reality has to ruin such a delightfully simple scheme: + * + * - When we go NO_HZ idle during the window, we can negate our sample + * contribution, causing under-accounting. + * + * We avoid this by keeping two idle-delta counters and flipping them + * when the window starts, thus separating old and new NO_HZ load. + * + * The only trick is the slight shift in index flip for read vs write. + * + * 0s 5s 10s 15s + * +10 +10 +10 +10 + * |-|-----------|-|-----------|-|-----------|-| + * r:0 0 1 1 0 0 1 1 0 + * w:0 1 1 0 0 1 1 0 0 + * + * This ensures we'll fold the old idle contribution in this window while + * accumlating the new one. + * + * - When we wake up from NO_HZ idle during the window, we push up our + * contribution, since we effectively move our sample point to a known + * busy state. + * + * This is solved by pushing the window forward, and thus skipping the + * sample, for this cpu (effectively using the idle-delta for this cpu which + * was in effect at the time the window opened). This also solves the issue + * of having to deal with a cpu having been in NOHZ idle for multiple + * LOAD_FREQ intervals. * * When making the ILB scale, we should try to pull this in as well. */ -static atomic_long_t calc_load_tasks_idle; +static atomic_long_t calc_load_idle[2]; +static int calc_load_idx; -static void calc_load_account_idle(struct rq *this_rq) +static inline int calc_load_write_idx(void) { + int idx = calc_load_idx; + + /* + * See calc_global_nohz(), if we observe the new index, we also + * need to observe the new update time. + */ + smp_rmb(); + + /* + * If the folding window started, make sure we start writing in the + * next idle-delta. + */ + if (!time_before(jiffies, calc_load_update)) + idx++; + + return idx & 1; +} + +static inline int calc_load_read_idx(void) +{ + return calc_load_idx & 1; +} + +void calc_load_enter_idle(void) +{ + struct rq *this_rq = this_rq(); long delta; + /* + * We're going into NOHZ mode, if there's any pending delta, fold it + * into the pending idle delta. + */ delta = calc_load_fold_active(this_rq); - if (delta) - atomic_long_add(delta, &calc_load_tasks_idle); + if (delta) { + int idx = calc_load_write_idx(); + atomic_long_add(delta, &calc_load_idle[idx]); + } } -static long calc_load_fold_idle(void) +void calc_load_exit_idle(void) { - long delta = 0; + struct rq *this_rq = this_rq(); + + /* + * If we're still before the sample window, we're done. + */ + if (time_before(jiffies, this_rq->calc_load_update)) + return; /* - * Its got a race, we don't care... + * We woke inside or after the sample window, this means we're already + * accounted through the nohz accounting, so skip the entire deal and + * sync up for the next window. */ - if (atomic_long_read(&calc_load_tasks_idle)) - delta = atomic_long_xchg(&calc_load_tasks_idle, 0); + this_rq->calc_load_update = calc_load_update; + if (time_before(jiffies, this_rq->calc_load_update + 10)) + this_rq->calc_load_update += LOAD_FREQ; +} + +static long calc_load_fold_idle(void) +{ + int idx = calc_load_read_idx(); + long delta = 0; + + if (atomic_long_read(&calc_load_idle[idx])) + delta = atomic_long_xchg(&calc_load_idle[idx], 0); return delta; } @@ -3542,66 +3694,39 @@ static void calc_global_nohz(void) { long delta, active, n; - /* - * If we crossed a calc_load_update boundary, make sure to fold - * any pending idle changes, the respective CPUs might have - * missed the tick driven calc_load_account_active() update - * due to NO_HZ. - */ - delta = calc_load_fold_idle(); - if (delta) - atomic_long_add(delta, &calc_load_tasks); - - /* - * It could be the one fold was all it took, we done! - */ - if (time_before(jiffies, calc_load_update + 10)) - return; - - /* - * Catch-up, fold however many we are behind still - */ - delta = jiffies - calc_load_update - 10; - n = 1 + (delta / LOAD_FREQ); + if (!time_before(jiffies, calc_load_update + 10)) { + /* + * Catch-up, fold however many we are behind still + */ + delta = jiffies - calc_load_update - 10; + n = 1 + (delta / LOAD_FREQ); - active = atomic_long_read(&calc_load_tasks); - active = active > 0 ? active * FIXED_1 : 0; + active = atomic_long_read(&calc_load_tasks); + active = active > 0 ? active * FIXED_1 : 0; - avenrun[0] = calc_load_n(avenrun[0], EXP_1, active, n); - avenrun[1] = calc_load_n(avenrun[1], EXP_5, active, n); - avenrun[2] = calc_load_n(avenrun[2], EXP_15, active, n); + avenrun[0] = calc_load_n(avenrun[0], EXP_1, active, n); + avenrun[1] = calc_load_n(avenrun[1], EXP_5, active, n); + avenrun[2] = calc_load_n(avenrun[2], EXP_15, active, n); - calc_load_update += n * LOAD_FREQ; -} -#else -static void calc_load_account_idle(struct rq *this_rq) -{ -} + calc_load_update += n * LOAD_FREQ; + } -static inline long calc_load_fold_idle(void) -{ - return 0; + /* + * Flip the idle index... + * + * Make sure we first write the new time then flip the index, so that + * calc_load_write_idx() will see the new time when it reads the new + * index, this avoids a double flip messing things up. + */ + smp_wmb(); + calc_load_idx++; } +#else /* !CONFIG_NO_HZ */ -static void calc_global_nohz(void) -{ -} -#endif +static inline long calc_load_fold_idle(void) { return 0; } +static inline void calc_global_nohz(void) { } -/** - * get_avenrun - get the load average array - * @loads: pointer to dest load array - * @offset: offset to add - * @shift: shift count to shift the result left - * - * These values are estimates at best, so no need for locking. - */ -void get_avenrun(unsigned long *loads, unsigned long offset, int shift) -{ - loads[0] = (avenrun[0] + offset) << shift; - loads[1] = (avenrun[1] + offset) << shift; - loads[2] = (avenrun[2] + offset) << shift; -} +#endif /* CONFIG_NO_HZ */ /* * calc_load - update the avenrun load estimates 10 ticks after the @@ -3609,11 +3734,18 @@ void get_avenrun(unsigned long *loads, unsigned long offset, int shift) */ void calc_global_load(unsigned long ticks) { - long active; + long active, delta; if (time_before(jiffies, calc_load_update + 10)) return; + /* + * Fold the 'old' idle-delta to include all NO_HZ cpus. + */ + delta = calc_load_fold_idle(); + if (delta) + atomic_long_add(delta, &calc_load_tasks); + active = atomic_long_read(&calc_load_tasks); active = active > 0 ? active * FIXED_1 : 0; @@ -3624,12 +3756,7 @@ void calc_global_load(unsigned long ticks) calc_load_update += LOAD_FREQ; /* - * Account one period with whatever state we found before - * folding in the nohz state and ageing the entire idle period. - * - * This avoids loosing a sample when we go idle between - * calc_load_account_active() (10 ticks ago) and now and thus - * under-accounting. + * In case we idled for multiple LOAD_FREQ intervals, catch up in bulk. */ calc_global_nohz(); } @@ -3646,7 +3773,6 @@ static void calc_load_account_active(struct rq *this_rq) return; delta = calc_load_fold_active(this_rq); - delta += calc_load_fold_idle(); if (delta) atomic_long_add(delta, &calc_load_tasks); @@ -3654,6 +3780,10 @@ static void calc_load_account_active(struct rq *this_rq) } /* + * End of global load-average stuff + */ + +/* * The exact cpuload at various idx values, calculated at every tick would be * load = (2^idx - 1) / 2^idx * load + 1 / 2^idx * cur_load * diff --git a/kernel/sched_idletask.c b/kernel/sched_idletask.c index 0a51882..be92bfe 100644 --- a/kernel/sched_idletask.c +++ b/kernel/sched_idletask.c @@ -23,7 +23,6 @@ static void check_preempt_curr_idle(struct rq *rq, struct task_struct *p, int fl static struct task_struct *pick_next_task_idle(struct rq *rq) { schedstat_inc(rq, sched_goidle); - calc_load_account_idle(rq); return rq->idle; } diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c index 4b85a7a..f1eb182 100644 --- a/kernel/time/ntp.c +++ b/kernel/time/ntp.c @@ -31,8 +31,6 @@ unsigned long tick_nsec; u64 tick_length; static u64 tick_length_base; -static struct hrtimer leap_timer; - #define MAX_TICKADJ 500LL /* usecs */ #define MAX_TICKADJ_SCALED \ (((MAX_TICKADJ * NSEC_PER_USEC) << NTP_SCALE_SHIFT) / NTP_INTERVAL_FREQ) @@ -350,60 +348,60 @@ void ntp_clear(void) } /* - * Leap second processing. If in leap-insert state at the end of the - * day, the system clock is set back one second; if in leap-delete - * state, the system clock is set ahead one second. + * this routine handles the overflow of the microsecond field + * + * The tricky bits of code to handle the accurate clock support + * were provided by Dave Mills (Mills@UDEL.EDU) of NTP fame. + * They were originally developed for SUN and DEC kernels. + * All the kudos should go to Dave for this stuff. + * + * Also handles leap second processing, and returns leap offset */ -static enum hrtimer_restart ntp_leap_second(struct hrtimer *timer) +int second_overflow(unsigned long secs) { - enum hrtimer_restart res = HRTIMER_NORESTART; - - write_seqlock(&xtime_lock); + int leap = 0; + s64 delta; + /* + * Leap second processing. If in leap-insert state at the end of the + * day, the system clock is set back one second; if in leap-delete + * state, the system clock is set ahead one second. + */ switch (time_state) { case TIME_OK: + if (time_status & STA_INS) + time_state = TIME_INS; + else if (time_status & STA_DEL) + time_state = TIME_DEL; break; case TIME_INS: - timekeeping_leap_insert(-1); - time_state = TIME_OOP; - printk(KERN_NOTICE - "Clock: inserting leap second 23:59:60 UTC\n"); - hrtimer_add_expires_ns(&leap_timer, NSEC_PER_SEC); - res = HRTIMER_RESTART; + if (secs % 86400 == 0) { + leap = -1; + time_state = TIME_OOP; + time_tai++; + printk(KERN_NOTICE + "Clock: inserting leap second 23:59:60 UTC\n"); + } break; case TIME_DEL: - timekeeping_leap_insert(1); - time_tai--; - time_state = TIME_WAIT; - printk(KERN_NOTICE - "Clock: deleting leap second 23:59:59 UTC\n"); + if ((secs + 1) % 86400 == 0) { + leap = 1; + time_tai--; + time_state = TIME_WAIT; + printk(KERN_NOTICE + "Clock: deleting leap second 23:59:59 UTC\n"); + } break; case TIME_OOP: - time_tai++; time_state = TIME_WAIT; - /* fall through */ + break; + case TIME_WAIT: if (!(time_status & (STA_INS | STA_DEL))) time_state = TIME_OK; break; } - write_sequnlock(&xtime_lock); - - return res; -} - -/* - * this routine handles the overflow of the microsecond field - * - * The tricky bits of code to handle the accurate clock support - * were provided by Dave Mills (Mills@UDEL.EDU) of NTP fame. - * They were originally developed for SUN and DEC kernels. - * All the kudos should go to Dave for this stuff. - */ -void second_overflow(void) -{ - s64 delta; /* Bump the maxerror field */ time_maxerror += MAXFREQ / NSEC_PER_USEC; @@ -423,23 +421,25 @@ void second_overflow(void) pps_dec_valid(); if (!time_adjust) - return; + goto out; if (time_adjust > MAX_TICKADJ) { time_adjust -= MAX_TICKADJ; tick_length += MAX_TICKADJ_SCALED; - return; + goto out; } if (time_adjust < -MAX_TICKADJ) { time_adjust += MAX_TICKADJ; tick_length -= MAX_TICKADJ_SCALED; - return; + goto out; } tick_length += (s64)(time_adjust * NSEC_PER_USEC / NTP_INTERVAL_FREQ) << NTP_SCALE_SHIFT; time_adjust = 0; +out: + return leap; } #ifdef CONFIG_GENERIC_CMOS_UPDATE @@ -501,27 +501,6 @@ static void notify_cmos_timer(void) static inline void notify_cmos_timer(void) { } #endif -/* - * Start the leap seconds timer: - */ -static inline void ntp_start_leap_timer(struct timespec *ts) -{ - long now = ts->tv_sec; - - if (time_status & STA_INS) { - time_state = TIME_INS; - now += 86400 - now % 86400; - hrtimer_start(&leap_timer, ktime_set(now, 0), HRTIMER_MODE_ABS); - - return; - } - - if (time_status & STA_DEL) { - time_state = TIME_DEL; - now += 86400 - (now + 1) % 86400; - hrtimer_start(&leap_timer, ktime_set(now, 0), HRTIMER_MODE_ABS); - } -} /* * Propagate a new txc->status value into the NTP state: @@ -546,22 +525,6 @@ static inline void process_adj_status(struct timex *txc, struct timespec *ts) time_status &= STA_RONLY; time_status |= txc->status & ~STA_RONLY; - switch (time_state) { - case TIME_OK: - ntp_start_leap_timer(ts); - break; - case TIME_INS: - case TIME_DEL: - time_state = TIME_OK; - ntp_start_leap_timer(ts); - case TIME_WAIT: - if (!(time_status & (STA_INS | STA_DEL))) - time_state = TIME_OK; - break; - case TIME_OOP: - hrtimer_restart(&leap_timer); - break; - } } /* * Called with the xtime lock held, so we can access and modify @@ -643,9 +606,6 @@ int do_adjtimex(struct timex *txc) (txc->tick < 900000/USER_HZ || txc->tick > 1100000/USER_HZ)) return -EINVAL; - - if (txc->modes & ADJ_STATUS && time_state != TIME_OK) - hrtimer_cancel(&leap_timer); } if (txc->modes & ADJ_SETOFFSET) { @@ -967,6 +927,4 @@ __setup("ntp_tick_adj=", ntp_tick_adj_setup); void __init ntp_init(void) { ntp_clear(); - hrtimer_init(&leap_timer, CLOCK_REALTIME, HRTIMER_MODE_ABS); - leap_timer.function = ntp_leap_second; } diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index c923640..9955ebd 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -430,6 +430,7 @@ void tick_nohz_stop_sched_tick(int inidle) */ if (!ts->tick_stopped) { select_nohz_load_balancer(1); + calc_load_enter_idle(); ts->idle_tick = hrtimer_get_expires(&ts->sched_timer); ts->tick_stopped = 1; @@ -563,6 +564,7 @@ void tick_nohz_restart_sched_tick(void) account_idle_ticks(ticks); #endif + calc_load_exit_idle(); touch_softlockup_watchdog(); /* * Cancel the scheduled timer and restore the tick diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 2378413..03e67d4 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -161,23 +161,43 @@ static struct timespec xtime __attribute__ ((aligned (16))); static struct timespec wall_to_monotonic __attribute__ ((aligned (16))); static struct timespec total_sleep_time; +/* Offset clock monotonic -> clock realtime */ +static ktime_t offs_real; + +/* Offset clock monotonic -> clock boottime */ +static ktime_t offs_boot; + /* * The raw monotonic time for the CLOCK_MONOTONIC_RAW posix clock. */ static struct timespec raw_time; -/* flag for if timekeeping is suspended */ -int __read_mostly timekeeping_suspended; +/* must hold write on xtime_lock */ +static void update_rt_offset(void) +{ + struct timespec tmp, *wtm = &wall_to_monotonic; -/* must hold xtime_lock */ -void timekeeping_leap_insert(int leapsecond) + set_normalized_timespec(&tmp, -wtm->tv_sec, -wtm->tv_nsec); + offs_real = timespec_to_ktime(tmp); +} + +/* must hold write on xtime_lock */ +static void timekeeping_update(bool clearntp) { - xtime.tv_sec += leapsecond; - wall_to_monotonic.tv_sec -= leapsecond; - update_vsyscall(&xtime, &wall_to_monotonic, timekeeper.clock, - timekeeper.mult); + if (clearntp) { + timekeeper.ntp_error = 0; + ntp_clear(); + } + update_rt_offset(); + update_vsyscall(&xtime, &wall_to_monotonic, + timekeeper.clock, timekeeper.mult); } + + +/* flag for if timekeeping is suspended */ +int __read_mostly timekeeping_suspended; + /** * timekeeping_forward_now - update clock to the current time * @@ -375,11 +395,7 @@ int do_settimeofday(const struct timespec *tv) xtime = *tv; - timekeeper.ntp_error = 0; - ntp_clear(); - - update_vsyscall(&xtime, &wall_to_monotonic, timekeeper.clock, - timekeeper.mult); + timekeeping_update(true); write_sequnlock_irqrestore(&xtime_lock, flags); @@ -412,11 +428,7 @@ int timekeeping_inject_offset(struct timespec *ts) xtime = timespec_add(xtime, *ts); wall_to_monotonic = timespec_sub(wall_to_monotonic, *ts); - timekeeper.ntp_error = 0; - ntp_clear(); - - update_vsyscall(&xtime, &wall_to_monotonic, timekeeper.clock, - timekeeper.mult); + timekeeping_update(true); write_sequnlock_irqrestore(&xtime_lock, flags); @@ -591,6 +603,7 @@ void __init timekeeping_init(void) } set_normalized_timespec(&wall_to_monotonic, -boot.tv_sec, -boot.tv_nsec); + update_rt_offset(); total_sleep_time.tv_sec = 0; total_sleep_time.tv_nsec = 0; write_sequnlock_irqrestore(&xtime_lock, flags); @@ -599,6 +612,12 @@ void __init timekeeping_init(void) /* time in seconds when suspend began */ static struct timespec timekeeping_suspend_time; +static void update_sleep_time(struct timespec t) +{ + total_sleep_time = t; + offs_boot = timespec_to_ktime(t); +} + /** * __timekeeping_inject_sleeptime - Internal function to add sleep interval * @delta: pointer to a timespec delta value @@ -616,7 +635,7 @@ static void __timekeeping_inject_sleeptime(struct timespec *delta) xtime = timespec_add(xtime, *delta); wall_to_monotonic = timespec_sub(wall_to_monotonic, *delta); - total_sleep_time = timespec_add(total_sleep_time, *delta); + update_sleep_time(timespec_add(total_sleep_time, *delta)); } @@ -645,10 +664,7 @@ void timekeeping_inject_sleeptime(struct timespec *delta) __timekeeping_inject_sleeptime(delta); - timekeeper.ntp_error = 0; - ntp_clear(); - update_vsyscall(&xtime, &wall_to_monotonic, timekeeper.clock, - timekeeper.mult); + timekeeping_update(true); write_sequnlock_irqrestore(&xtime_lock, flags); @@ -683,6 +699,7 @@ static void timekeeping_resume(void) timekeeper.clock->cycle_last = timekeeper.clock->read(timekeeper.clock); timekeeper.ntp_error = 0; timekeeping_suspended = 0; + timekeeping_update(false); write_sequnlock_irqrestore(&xtime_lock, flags); touch_softlockup_watchdog(); @@ -942,9 +959,14 @@ static cycle_t logarithmic_accumulation(cycle_t offset, int shift) timekeeper.xtime_nsec += timekeeper.xtime_interval << shift; while (timekeeper.xtime_nsec >= nsecps) { + int leap; timekeeper.xtime_nsec -= nsecps; xtime.tv_sec++; - second_overflow(); + leap = second_overflow(xtime.tv_sec); + xtime.tv_sec += leap; + wall_to_monotonic.tv_sec -= leap; + if (leap) + clock_was_set_delayed(); } /* Accumulate raw time */ @@ -1050,14 +1072,17 @@ static void update_wall_time(void) * xtime.tv_nsec isn't larger then NSEC_PER_SEC */ if (unlikely(xtime.tv_nsec >= NSEC_PER_SEC)) { + int leap; xtime.tv_nsec -= NSEC_PER_SEC; xtime.tv_sec++; - second_overflow(); + leap = second_overflow(xtime.tv_sec); + xtime.tv_sec += leap; + wall_to_monotonic.tv_sec -= leap; + if (leap) + clock_was_set_delayed(); } - /* check to see if there is a new clocksource to use */ - update_vsyscall(&xtime, &wall_to_monotonic, timekeeper.clock, - timekeeper.mult); + timekeeping_update(false); } /** @@ -1216,6 +1241,40 @@ void get_xtime_and_monotonic_and_sleep_offset(struct timespec *xtim, } while (read_seqretry(&xtime_lock, seq)); } +#ifdef CONFIG_HIGH_RES_TIMERS +/** + * ktime_get_update_offsets - hrtimer helper + * @real: pointer to storage for monotonic -> realtime offset + * @_boot: pointer to storage for monotonic -> boottime offset + * + * Returns current monotonic time and updates the offsets + * Called from hrtimer_interupt() or retrigger_next_event() + */ +ktime_t ktime_get_update_offsets(ktime_t *real, ktime_t *boot) +{ + ktime_t now; + unsigned int seq; + u64 secs, nsecs; + + do { + seq = read_seqbegin(&xtime_lock); + + secs = xtime.tv_sec; + nsecs = xtime.tv_nsec; + nsecs += timekeeping_get_ns(); + /* If arch requires, add in gettimeoffset() */ + nsecs += arch_gettimeoffset(); + + *real = offs_real; + *boot = offs_boot; + } while (read_seqretry(&xtime_lock, seq)); + + now = ktime_add_ns(ktime_set(secs, 0), nsecs); + now = ktime_sub(now, *real); + return now; +} +#endif + /** * ktime_get_monotonic_offset() - get wall_to_monotonic in ktime_t format */ diff --git a/mm/compaction.c b/mm/compaction.c index 8fb8a40..50f1c60 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -592,8 +592,11 @@ static int compact_zone(struct zone *zone, struct compact_control *cc) if (err) { putback_lru_pages(&cc->migratepages); cc->nr_migratepages = 0; + if (err == -ENOMEM) { + ret = COMPACT_PARTIAL; + goto out; + } } - } out: diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 5f5c545..7c535b0 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -53,6 +53,84 @@ static unsigned long __initdata default_hstate_size; */ static DEFINE_SPINLOCK(hugetlb_lock); +static inline void unlock_or_release_subpool(struct hugepage_subpool *spool) +{ + bool free = (spool->count == 0) && (spool->used_hpages == 0); + + spin_unlock(&spool->lock); + + /* If no pages are used, and no other handles to the subpool + * remain, free the subpool the subpool remain */ + if (free) + kfree(spool); +} + +struct hugepage_subpool *hugepage_new_subpool(long nr_blocks) +{ + struct hugepage_subpool *spool; + + spool = kmalloc(sizeof(*spool), GFP_KERNEL); + if (!spool) + return NULL; + + spin_lock_init(&spool->lock); + spool->count = 1; + spool->max_hpages = nr_blocks; + spool->used_hpages = 0; + + return spool; +} + +void hugepage_put_subpool(struct hugepage_subpool *spool) +{ + spin_lock(&spool->lock); + BUG_ON(!spool->count); + spool->count--; + unlock_or_release_subpool(spool); +} + +static int hugepage_subpool_get_pages(struct hugepage_subpool *spool, + long delta) +{ + int ret = 0; + + if (!spool) + return 0; + + spin_lock(&spool->lock); + if ((spool->used_hpages + delta) <= spool->max_hpages) { + spool->used_hpages += delta; + } else { + ret = -ENOMEM; + } + spin_unlock(&spool->lock); + + return ret; +} + +static void hugepage_subpool_put_pages(struct hugepage_subpool *spool, + long delta) +{ + if (!spool) + return; + + spin_lock(&spool->lock); + spool->used_hpages -= delta; + /* If hugetlbfs_put_super couldn't free spool due to + * an outstanding quota reference, free it now. */ + unlock_or_release_subpool(spool); +} + +static inline struct hugepage_subpool *subpool_inode(struct inode *inode) +{ + return HUGETLBFS_SB(inode->i_sb)->spool; +} + +static inline struct hugepage_subpool *subpool_vma(struct vm_area_struct *vma) +{ + return subpool_inode(vma->vm_file->f_dentry->d_inode); +} + /* * Region tracking -- allows tracking of reservations and instantiated pages * across the pages in a mapping. @@ -533,9 +611,9 @@ static void free_huge_page(struct page *page) */ struct hstate *h = page_hstate(page); int nid = page_to_nid(page); - struct address_space *mapping; + struct hugepage_subpool *spool = + (struct hugepage_subpool *)page_private(page); - mapping = (struct address_space *) page_private(page); set_page_private(page, 0); page->mapping = NULL; BUG_ON(page_count(page)); @@ -551,8 +629,7 @@ static void free_huge_page(struct page *page) enqueue_huge_page(h, page); } spin_unlock(&hugetlb_lock); - if (mapping) - hugetlb_put_quota(mapping, 1); + hugepage_subpool_put_pages(spool, 1); } static void prep_new_huge_page(struct hstate *h, struct page *page, int nid) @@ -966,11 +1043,12 @@ static void return_unused_surplus_pages(struct hstate *h, /* * Determine if the huge page at addr within the vma has an associated * reservation. Where it does not we will need to logically increase - * reservation and actually increase quota before an allocation can occur. - * Where any new reservation would be required the reservation change is - * prepared, but not committed. Once the page has been quota'd allocated - * an instantiated the change should be committed via vma_commit_reservation. - * No action is required on failure. + * reservation and actually increase subpool usage before an allocation + * can occur. Where any new reservation would be required the + * reservation change is prepared, but not committed. Once the page + * has been allocated from the subpool and instantiated the change should + * be committed via vma_commit_reservation. No action is required on + * failure. */ static long vma_needs_reservation(struct hstate *h, struct vm_area_struct *vma, unsigned long addr) @@ -1019,24 +1097,24 @@ static void vma_commit_reservation(struct hstate *h, static struct page *alloc_huge_page(struct vm_area_struct *vma, unsigned long addr, int avoid_reserve) { + struct hugepage_subpool *spool = subpool_vma(vma); struct hstate *h = hstate_vma(vma); struct page *page; - struct address_space *mapping = vma->vm_file->f_mapping; - struct inode *inode = mapping->host; long chg; /* - * Processes that did not create the mapping will have no reserves and - * will not have accounted against quota. Check that the quota can be - * made before satisfying the allocation - * MAP_NORESERVE mappings may also need pages and quota allocated - * if no reserve mapping overlaps. + * Processes that did not create the mapping will have no + * reserves and will not have accounted against subpool + * limit. Check that the subpool limit can be made before + * satisfying the allocation MAP_NORESERVE mappings may also + * need pages and subpool limit allocated allocated if no reserve + * mapping overlaps. */ chg = vma_needs_reservation(h, vma, addr); if (chg < 0) return ERR_PTR(-VM_FAULT_OOM); if (chg) - if (hugetlb_get_quota(inode->i_mapping, chg)) + if (hugepage_subpool_get_pages(spool, chg)) return ERR_PTR(-VM_FAULT_SIGBUS); spin_lock(&hugetlb_lock); @@ -1046,12 +1124,12 @@ static struct page *alloc_huge_page(struct vm_area_struct *vma, if (!page) { page = alloc_buddy_huge_page(h, NUMA_NO_NODE); if (!page) { - hugetlb_put_quota(inode->i_mapping, chg); + hugepage_subpool_put_pages(spool, chg); return ERR_PTR(-VM_FAULT_SIGBUS); } } - set_page_private(page, (unsigned long) mapping); + set_page_private(page, (unsigned long)spool); vma_commit_reservation(h, vma, addr); @@ -2081,6 +2159,7 @@ static void hugetlb_vm_op_close(struct vm_area_struct *vma) { struct hstate *h = hstate_vma(vma); struct resv_map *reservations = vma_resv_map(vma); + struct hugepage_subpool *spool = subpool_vma(vma); unsigned long reserve; unsigned long start; unsigned long end; @@ -2096,7 +2175,7 @@ static void hugetlb_vm_op_close(struct vm_area_struct *vma) if (reserve) { hugetlb_acct_memory(h, -reserve); - hugetlb_put_quota(vma->vm_file->f_mapping, reserve); + hugepage_subpool_put_pages(spool, reserve); } } } @@ -2326,7 +2405,7 @@ static int unmap_ref_private(struct mm_struct *mm, struct vm_area_struct *vma, address = address & huge_page_mask(h); pgoff = ((address - vma->vm_start) >> PAGE_SHIFT) + (vma->vm_pgoff >> PAGE_SHIFT); - mapping = (struct address_space *)page_private(page); + mapping = vma->vm_file->f_dentry->d_inode->i_mapping; /* * Take the mapping lock for the duration of the table walk. As @@ -2865,11 +2944,12 @@ int hugetlb_reserve_pages(struct inode *inode, { long ret, chg; struct hstate *h = hstate_inode(inode); + struct hugepage_subpool *spool = subpool_inode(inode); /* * Only apply hugepage reservation if asked. At fault time, an * attempt will be made for VM_NORESERVE to allocate a page - * and filesystem quota without using reserves + * without using reserves */ if (vm_flags & VM_NORESERVE) return 0; @@ -2898,19 +2978,19 @@ int hugetlb_reserve_pages(struct inode *inode, goto out_err; } - /* There must be enough filesystem quota for the mapping */ - if (hugetlb_get_quota(inode->i_mapping, chg)) { + /* There must be enough pages in the subpool for the mapping */ + if (hugepage_subpool_get_pages(spool, chg)) { ret = -ENOSPC; goto out_err; } /* * Check enough hugepages are available for the reservation. - * Hand back the quota if there are not + * Hand the pages back to the subpool if there are not */ ret = hugetlb_acct_memory(h, chg); if (ret < 0) { - hugetlb_put_quota(inode->i_mapping, chg); + hugepage_subpool_put_pages(spool, chg); goto out_err; } @@ -2938,12 +3018,13 @@ void hugetlb_unreserve_pages(struct inode *inode, long offset, long freed) { struct hstate *h = hstate_inode(inode); long chg = region_truncate(&inode->i_mapping->private_list, offset); + struct hugepage_subpool *spool = subpool_inode(inode); spin_lock(&inode->i_lock); inode->i_blocks -= (blocks_per_huge_page(h) * freed); spin_unlock(&inode->i_lock); - hugetlb_put_quota(inode->i_mapping, (chg - freed)); + hugepage_subpool_put_pages(spool, (chg - freed)); hugetlb_acct_memory(h, -(chg - freed)); } diff --git a/mm/vmscan.c b/mm/vmscan.c index fbe2d2c..8342119 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -2824,7 +2824,10 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int order, int classzone_idx) * them before going back to sleep. */ set_pgdat_percpu_threshold(pgdat, calculate_normal_threshold); - schedule(); + + if (!kthread_should_stop()) + schedule(); + set_pgdat_percpu_threshold(pgdat, calculate_pressure_threshold); } else { if (remaining) @@ -3090,14 +3093,17 @@ int kswapd_run(int nid) } /* - * Called by memory hotplug when all memory in a node is offlined. + * Called by memory hotplug when all memory in a node is offlined. Caller must + * hold lock_memory_hotplug(). */ void kswapd_stop(int nid) { struct task_struct *kswapd = NODE_DATA(nid)->kswapd; - if (kswapd) + if (kswapd) { kthread_stop(kswapd); + NODE_DATA(nid)->kswapd = NULL; + } } static int __init kswapd_init(void) diff --git a/net/can/raw.c b/net/can/raw.c index cde1b4a..46cca3a 100644 --- a/net/can/raw.c +++ b/net/can/raw.c @@ -681,9 +681,6 @@ static int raw_sendmsg(struct kiocb *iocb, struct socket *sock, if (err < 0) goto free_skb; - /* to be able to check the received tx sock reference in raw_rcv() */ - skb_shinfo(skb)->tx_flags |= SKBTX_DRV_NEEDS_SK_REF; - skb->dev = dev; skb->sk = sk; diff --git a/net/core/dev.c b/net/core/dev.c index 1cbddc9..5738654 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2079,25 +2079,6 @@ static int dev_gso_segment(struct sk_buff *skb, int features) return 0; } -/* - * Try to orphan skb early, right before transmission by the device. - * We cannot orphan skb if tx timestamp is requested or the sk-reference - * is needed on driver level for other reasons, e.g. see net/can/raw.c - */ -static inline void skb_orphan_try(struct sk_buff *skb) -{ - struct sock *sk = skb->sk; - - if (sk && !skb_shinfo(skb)->tx_flags) { - /* skb_tx_hash() wont be able to get sk. - * We copy sk_hash into skb->rxhash - */ - if (!skb->rxhash) - skb->rxhash = sk->sk_hash; - skb_orphan(skb); - } -} - static bool can_checksum_protocol(unsigned long features, __be16 protocol) { return ((features & NETIF_F_GEN_CSUM) || @@ -2182,8 +2163,6 @@ int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, if (!list_empty(&ptype_all)) dev_queue_xmit_nit(skb, dev); - skb_orphan_try(skb); - features = netif_skb_features(skb); if (vlan_tx_tag_present(skb) && @@ -2293,7 +2272,7 @@ u16 __skb_tx_hash(const struct net_device *dev, const struct sk_buff *skb, if (skb->sk && skb->sk->sk_hash) hash = skb->sk->sk_hash; else - hash = (__force u16) skb->protocol ^ skb->rxhash; + hash = (__force u16) skb->protocol; hash = jhash_1word(hash, hashrnd); return (u16) (((u64) hash * qcount) >> 32) + qoffset; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 9726927..32e6ca2 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -5836,6 +5836,8 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb, goto discard; if (th->syn) { + if (th->fin) + goto discard; if (icsk->icsk_af_ops->conn_request(sk, skb) < 0) return 1; diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index 274d150..cf98d62 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -380,7 +380,6 @@ static int afiucv_hs_send(struct iucv_message *imsg, struct sock *sock, skb_trim(skb, skb->dev->mtu); } skb->protocol = ETH_P_AF_IUCV; - skb_shinfo(skb)->tx_flags |= SKBTX_DRV_NEEDS_SK_REF; nskb = skb_clone(skb, GFP_ATOMIC); if (!nskb) return -ENOMEM; diff --git a/net/wireless/util.c b/net/wireless/util.c index d38815d..74d5292 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -813,7 +813,7 @@ int cfg80211_change_iface(struct cfg80211_registered_device *rdev, ntype == NL80211_IFTYPE_P2P_CLIENT)) return -EBUSY; - if (ntype != otype) { + if (ntype != otype && netif_running(dev)) { err = cfg80211_can_change_interface(rdev, dev->ieee80211_ptr, ntype); if (err) diff --git a/scripts/depmod.sh b/scripts/depmod.sh index a272356..2ae4817 100755 --- a/scripts/depmod.sh +++ b/scripts/depmod.sh @@ -9,12 +9,6 @@ fi DEPMOD=$1 KERNELRELEASE=$2 -if ! "$DEPMOD" -V 2>/dev/null | grep -q module-init-tools; then - echo "Warning: you may need to install module-init-tools" >&2 - echo "See http://www.codemonkey.org.uk/docs/post-halloween-2.6.txt" >&2 - sleep 1 -fi - if ! test -r System.map -a -x "$DEPMOD"; then exit 0 fi diff --git a/virt/kvm/irq_comm.c b/virt/kvm/irq_comm.c index 9f614b4..272407c 100644 --- a/virt/kvm/irq_comm.c +++ b/virt/kvm/irq_comm.c @@ -318,6 +318,7 @@ static int setup_routing_entry(struct kvm_irq_routing_table *rt, */ hlist_for_each_entry(ei, n, &rt->map[ue->gsi], link) if (ei->type == KVM_IRQ_ROUTING_MSI || + ue->type == KVM_IRQ_ROUTING_MSI || ue->u.irqchip.irqchip == ei->irqchip.irqchip) return r;