diff options
282 files changed, 2795 insertions, 2094 deletions
diff --git a/Documentation/vfio.txt b/Documentation/vfio.txt index 0cb6685c802..8eda3635a17 100644 --- a/Documentation/vfio.txt +++ b/Documentation/vfio.txt @@ -133,7 +133,7 @@ character devices for this group: $ lspci -n -s 0000:06:0d.0 06:0d.0 0401: 1102:0002 (rev 08) # echo 0000:06:0d.0 > /sys/bus/pci/devices/0000:06:0d.0/driver/unbind -# echo 1102 0002 > /sys/bus/pci/drivers/vfio/new_id +# echo 1102 0002 > /sys/bus/pci/drivers/vfio-pci/new_id Now we need to look at what other devices are in the group to free it for use by VFIO: diff --git a/MAINTAINERS b/MAINTAINERS index 53cc13c82cb..9a6c4da3b2f 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -3552,11 +3552,12 @@ K: \b(ABS|SYN)_MT_ INTEL C600 SERIES SAS CONTROLLER DRIVER M: Intel SCU Linux support <intel-linux-scu@intel.com> +M: Lukasz Dorau <lukasz.dorau@intel.com> +M: Maciej Patelczyk <maciej.patelczyk@intel.com> M: Dave Jiang <dave.jiang@intel.com> -M: Ed Nadolski <edmund.nadolski@intel.com> L: linux-scsi@vger.kernel.org -T: git git://git.kernel.org/pub/scm/linux/kernel/git/djbw/isci.git -S: Maintained +T: git git://git.code.sf.net/p/intel-sas/isci +S: Supported F: drivers/scsi/isci/ F: firmware/isci/ @@ -3666,11 +3667,12 @@ F: Documentation/networking/README.ipw2200 F: drivers/net/wireless/ipw2x00/ INTEL(R) TRUSTED EXECUTION TECHNOLOGY (TXT) -M: Joseph Cihula <joseph.cihula@intel.com> +M: Richard L Maliszewski <richard.l.maliszewski@intel.com> +M: Gang Wei <gang.wei@intel.com> M: Shane Wang <shane.wang@intel.com> L: tboot-devel@lists.sourceforge.net W: http://tboot.sourceforge.net -T: Mercurial http://www.bughost.org/repos.hg/tboot.hg +T: hg http://tboot.hg.sourceforge.net:8000/hgroot/tboot/tboot S: Supported F: Documentation/intel_txt.txt F: include/linux/tboot.h @@ -5543,6 +5545,8 @@ F: Documentation/devicetree/bindings/pwm/ F: include/linux/pwm.h F: include/linux/of_pwm.h F: drivers/pwm/ +F: drivers/video/backlight/pwm_bl.c +F: include/linux/pwm_backlight.h PXA2xx/PXA3xx SUPPORT M: Eric Miao <eric.y.miao@gmail.com> @@ -1,8 +1,8 @@ VERSION = 3 PATCHLEVEL = 6 SUBLEVEL = 0 -EXTRAVERSION = -rc6 -NAME = Saber-toothed Squirrel +EXTRAVERSION = +NAME = Terrified Chipmunk # *DOCUMENTATION* # To see a list of typical targets execute "make help" diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S index 81769c1341f..bc67cbff394 100644 --- a/arch/arm/boot/compressed/head.S +++ b/arch/arm/boot/compressed/head.S @@ -653,6 +653,7 @@ __armv7_mmu_cache_on: mcrne p15, 0, r0, c8, c7, 0 @ flush I,D TLBs #endif mrc p15, 0, r0, c1, c0, 0 @ read control reg + bic r0, r0, #1 << 28 @ clear SCTLR.TRE orr r0, r0, #0x5000 @ I-cache enable, RR cache replacement orr r0, r0, #0x003c @ write buffer #ifdef CONFIG_MMU diff --git a/arch/arm/boot/dts/at91sam9260.dtsi b/arch/arm/boot/dts/at91sam9260.dtsi index 66389c1c6f6..7c95f76398d 100644 --- a/arch/arm/boot/dts/at91sam9260.dtsi +++ b/arch/arm/boot/dts/at91sam9260.dtsi @@ -104,6 +104,7 @@ #gpio-cells = <2>; gpio-controller; interrupt-controller; + #interrupt-cells = <2>; }; pioB: gpio@fffff600 { @@ -113,6 +114,7 @@ #gpio-cells = <2>; gpio-controller; interrupt-controller; + #interrupt-cells = <2>; }; pioC: gpio@fffff800 { @@ -122,6 +124,7 @@ #gpio-cells = <2>; gpio-controller; interrupt-controller; + #interrupt-cells = <2>; }; dbgu: serial@fffff200 { diff --git a/arch/arm/boot/dts/at91sam9263.dtsi b/arch/arm/boot/dts/at91sam9263.dtsi index b460d6ce9eb..195019b7ca0 100644 --- a/arch/arm/boot/dts/at91sam9263.dtsi +++ b/arch/arm/boot/dts/at91sam9263.dtsi @@ -95,6 +95,7 @@ #gpio-cells = <2>; gpio-controller; interrupt-controller; + #interrupt-cells = <2>; }; pioB: gpio@fffff400 { @@ -104,6 +105,7 @@ #gpio-cells = <2>; gpio-controller; interrupt-controller; + #interrupt-cells = <2>; }; pioC: gpio@fffff600 { @@ -113,6 +115,7 @@ #gpio-cells = <2>; gpio-controller; interrupt-controller; + #interrupt-cells = <2>; }; pioD: gpio@fffff800 { @@ -122,6 +125,7 @@ #gpio-cells = <2>; gpio-controller; interrupt-controller; + #interrupt-cells = <2>; }; pioE: gpio@fffffa00 { @@ -131,6 +135,7 @@ #gpio-cells = <2>; gpio-controller; interrupt-controller; + #interrupt-cells = <2>; }; dbgu: serial@ffffee00 { diff --git a/arch/arm/boot/dts/at91sam9g45.dtsi b/arch/arm/boot/dts/at91sam9g45.dtsi index bafa8806fc1..63751b1e744 100644 --- a/arch/arm/boot/dts/at91sam9g45.dtsi +++ b/arch/arm/boot/dts/at91sam9g45.dtsi @@ -113,6 +113,7 @@ #gpio-cells = <2>; gpio-controller; interrupt-controller; + #interrupt-cells = <2>; }; pioB: gpio@fffff400 { @@ -122,6 +123,7 @@ #gpio-cells = <2>; gpio-controller; interrupt-controller; + #interrupt-cells = <2>; }; pioC: gpio@fffff600 { @@ -131,6 +133,7 @@ #gpio-cells = <2>; gpio-controller; interrupt-controller; + #interrupt-cells = <2>; }; pioD: gpio@fffff800 { @@ -140,6 +143,7 @@ #gpio-cells = <2>; gpio-controller; interrupt-controller; + #interrupt-cells = <2>; }; pioE: gpio@fffffa00 { @@ -149,6 +153,7 @@ #gpio-cells = <2>; gpio-controller; interrupt-controller; + #interrupt-cells = <2>; }; dbgu: serial@ffffee00 { diff --git a/arch/arm/boot/dts/at91sam9n12.dtsi b/arch/arm/boot/dts/at91sam9n12.dtsi index bfac0dfc332..ef9336ae961 100644 --- a/arch/arm/boot/dts/at91sam9n12.dtsi +++ b/arch/arm/boot/dts/at91sam9n12.dtsi @@ -107,6 +107,7 @@ #gpio-cells = <2>; gpio-controller; interrupt-controller; + #interrupt-cells = <2>; }; pioB: gpio@fffff600 { @@ -116,6 +117,7 @@ #gpio-cells = <2>; gpio-controller; interrupt-controller; + #interrupt-cells = <2>; }; pioC: gpio@fffff800 { @@ -125,6 +127,7 @@ #gpio-cells = <2>; gpio-controller; interrupt-controller; + #interrupt-cells = <2>; }; pioD: gpio@fffffa00 { @@ -134,6 +137,7 @@ #gpio-cells = <2>; gpio-controller; interrupt-controller; + #interrupt-cells = <2>; }; dbgu: serial@fffff200 { diff --git a/arch/arm/boot/dts/at91sam9x5.dtsi b/arch/arm/boot/dts/at91sam9x5.dtsi index 4a18c393b13..8a387a8d61b 100644 --- a/arch/arm/boot/dts/at91sam9x5.dtsi +++ b/arch/arm/boot/dts/at91sam9x5.dtsi @@ -115,6 +115,7 @@ #gpio-cells = <2>; gpio-controller; interrupt-controller; + #interrupt-cells = <2>; }; pioB: gpio@fffff600 { @@ -124,6 +125,7 @@ #gpio-cells = <2>; gpio-controller; interrupt-controller; + #interrupt-cells = <2>; }; pioC: gpio@fffff800 { @@ -133,6 +135,7 @@ #gpio-cells = <2>; gpio-controller; interrupt-controller; + #interrupt-cells = <2>; }; pioD: gpio@fffffa00 { @@ -142,6 +145,7 @@ #gpio-cells = <2>; gpio-controller; interrupt-controller; + #interrupt-cells = <2>; }; dbgu: serial@fffff200 { diff --git a/arch/arm/include/asm/unistd.h b/arch/arm/include/asm/unistd.h index 0cab47d4a83..2fde5fd1acc 100644 --- a/arch/arm/include/asm/unistd.h +++ b/arch/arm/include/asm/unistd.h @@ -404,6 +404,7 @@ #define __NR_setns (__NR_SYSCALL_BASE+375) #define __NR_process_vm_readv (__NR_SYSCALL_BASE+376) #define __NR_process_vm_writev (__NR_SYSCALL_BASE+377) + /* 378 for kcmp */ /* * The following SWIs are ARM private. @@ -483,6 +484,7 @@ */ #define __IGNORE_fadvise64_64 #define __IGNORE_migrate_pages +#define __IGNORE_kcmp #endif /* __KERNEL__ */ #endif /* __ASM_ARM_UNISTD_H */ diff --git a/arch/arm/kernel/calls.S b/arch/arm/kernel/calls.S index 463ff4a0ec8..e337879595e 100644 --- a/arch/arm/kernel/calls.S +++ b/arch/arm/kernel/calls.S @@ -387,6 +387,7 @@ /* 375 */ CALL(sys_setns) CALL(sys_process_vm_readv) CALL(sys_process_vm_writev) + CALL(sys_ni_syscall) /* reserved for sys_kcmp */ #ifndef syscalls_counted .equ syscalls_padding, ((NR_syscalls + 3) & ~3) - NR_syscalls #define syscalls_counted diff --git a/arch/arm/kernel/smp_twd.c b/arch/arm/kernel/smp_twd.c index fef42b21cec..e1f906989bb 100644 --- a/arch/arm/kernel/smp_twd.c +++ b/arch/arm/kernel/smp_twd.c @@ -11,7 +11,6 @@ #include <linux/init.h> #include <linux/kernel.h> #include <linux/clk.h> -#include <linux/cpufreq.h> #include <linux/delay.h> #include <linux/device.h> #include <linux/err.h> @@ -96,7 +95,52 @@ static void twd_timer_stop(struct clock_event_device *clk) disable_percpu_irq(clk->irq); } -#ifdef CONFIG_CPU_FREQ +#ifdef CONFIG_COMMON_CLK + +/* + * Updates clockevent frequency when the cpu frequency changes. + * Called on the cpu that is changing frequency with interrupts disabled. + */ +static void twd_update_frequency(void *new_rate) +{ + twd_timer_rate = *((unsigned long *) new_rate); + + clockevents_update_freq(*__this_cpu_ptr(twd_evt), twd_timer_rate); +} + +static int twd_rate_change(struct notifier_block *nb, + unsigned long flags, void *data) +{ + struct clk_notifier_data *cnd = data; + + /* + * The twd clock events must be reprogrammed to account for the new + * frequency. The timer is local to a cpu, so cross-call to the + * changing cpu. + */ + if (flags == POST_RATE_CHANGE) + smp_call_function(twd_update_frequency, + (void *)&cnd->new_rate, 1); + + return NOTIFY_OK; +} + +static struct notifier_block twd_clk_nb = { + .notifier_call = twd_rate_change, +}; + +static int twd_clk_init(void) +{ + if (twd_evt && *__this_cpu_ptr(twd_evt) && !IS_ERR(twd_clk)) + return clk_notifier_register(twd_clk, &twd_clk_nb); + + return 0; +} +core_initcall(twd_clk_init); + +#elif defined (CONFIG_CPU_FREQ) + +#include <linux/cpufreq.h> /* * Updates clockevent frequency when the cpu frequency changes. diff --git a/arch/arm/mach-imx/clk-imx25.c b/arch/arm/mach-imx/clk-imx25.c index 4431a62fff5..d20d4795f4e 100644 --- a/arch/arm/mach-imx/clk-imx25.c +++ b/arch/arm/mach-imx/clk-imx25.c @@ -241,6 +241,6 @@ int __init mx25_clocks_init(void) clk_register_clkdev(clk[sdma_ahb], "ahb", "imx35-sdma"); clk_register_clkdev(clk[iim_ipg], "iim", NULL); - mxc_timer_init(MX25_IO_ADDRESS(MX25_GPT1_BASE_ADDR), 54); + mxc_timer_init(MX25_IO_ADDRESS(MX25_GPT1_BASE_ADDR), MX25_INT_GPT1); return 0; } diff --git a/arch/arm/mach-imx/mach-armadillo5x0.c b/arch/arm/mach-imx/mach-armadillo5x0.c index 2c6ab3273f9..5985ed1b8c9 100644 --- a/arch/arm/mach-imx/mach-armadillo5x0.c +++ b/arch/arm/mach-imx/mach-armadillo5x0.c @@ -526,7 +526,8 @@ static void __init armadillo5x0_init(void) imx31_add_mxc_nand(&armadillo5x0_nand_board_info); /* set NAND page size to 2k if not configured via boot mode pins */ - __raw_writel(__raw_readl(MXC_CCM_RCSR) | (1 << 30), MXC_CCM_RCSR); + __raw_writel(__raw_readl(mx3_ccm_base + MXC_CCM_RCSR) | + (1 << 30), mx3_ccm_base + MXC_CCM_RCSR); /* RTC */ /* Get RTC IRQ and register the chip */ diff --git a/arch/arm/mach-mxs/mach-mxs.c b/arch/arm/mach-mxs/mach-mxs.c index 8dabfe81d07..ff886e01a0b 100644 --- a/arch/arm/mach-mxs/mach-mxs.c +++ b/arch/arm/mach-mxs/mach-mxs.c @@ -261,7 +261,7 @@ static void __init apx4devkit_init(void) enable_clk_enet_out(); if (IS_BUILTIN(CONFIG_PHYLIB)) - phy_register_fixup_for_uid(PHY_ID_KS8051, MICREL_PHY_ID_MASK, + phy_register_fixup_for_uid(PHY_ID_KSZ8051, MICREL_PHY_ID_MASK, apx4devkit_phy_fixup); mxsfb_pdata.mode_list = apx4devkit_video_modes; diff --git a/arch/arm/mach-orion5x/common.c b/arch/arm/mach-orion5x/common.c index 410291c6766..a6cd14ab1e4 100644 --- a/arch/arm/mach-orion5x/common.c +++ b/arch/arm/mach-orion5x/common.c @@ -204,6 +204,13 @@ void __init orion5x_wdt_init(void) void __init orion5x_init_early(void) { orion_time_set_base(TIMER_VIRT_BASE); + + /* + * Some Orion5x devices allocate their coherent buffers from atomic + * context. Increase size of atomic coherent pool to make sure such + * the allocations won't fail. + */ + init_dma_coherent_pool_size(SZ_1M); } int orion5x_tclk; diff --git a/arch/arm/mach-shmobile/board-kzm9g.c b/arch/arm/mach-shmobile/board-kzm9g.c index 53b7ea92c32..3b8a0171c3c 100644 --- a/arch/arm/mach-shmobile/board-kzm9g.c +++ b/arch/arm/mach-shmobile/board-kzm9g.c @@ -346,11 +346,11 @@ static struct resource sh_mmcif_resources[] = { .flags = IORESOURCE_MEM, }, [1] = { - .start = gic_spi(141), + .start = gic_spi(140), .flags = IORESOURCE_IRQ, }, [2] = { - .start = gic_spi(140), + .start = gic_spi(141), .flags = IORESOURCE_IRQ, }, }; diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c index e59c4ab71bc..13f555d6249 100644 --- a/arch/arm/mm/dma-mapping.c +++ b/arch/arm/mm/dma-mapping.c @@ -346,6 +346,8 @@ static int __init atomic_pool_init(void) (unsigned)pool->size / 1024); return 0; } + + kfree(pages); no_pages: kfree(bitmap); no_bitmap: diff --git a/arch/arm/plat-mxc/include/mach/mx25.h b/arch/arm/plat-mxc/include/mach/mx25.h index 627d94f1b01..ec466400a20 100644 --- a/arch/arm/plat-mxc/include/mach/mx25.h +++ b/arch/arm/plat-mxc/include/mach/mx25.h @@ -98,6 +98,7 @@ #define MX25_INT_UART1 (NR_IRQS_LEGACY + 45) #define MX25_INT_GPIO2 (NR_IRQS_LEGACY + 51) #define MX25_INT_GPIO1 (NR_IRQS_LEGACY + 52) +#define MX25_INT_GPT1 (NR_IRQS_LEGACY + 54) #define MX25_INT_FEC (NR_IRQS_LEGACY + 57) #define MX25_DMA_REQ_SSI2_RX1 22 diff --git a/arch/arm/plat-samsung/clock.c b/arch/arm/plat-samsung/clock.c index 65c5eca475e..d1116e2dfbe 100644 --- a/arch/arm/plat-samsung/clock.c +++ b/arch/arm/plat-samsung/clock.c @@ -144,6 +144,7 @@ long clk_round_rate(struct clk *clk, unsigned long rate) int clk_set_rate(struct clk *clk, unsigned long rate) { + unsigned long flags; int ret; if (IS_ERR(clk)) @@ -159,9 +160,9 @@ int clk_set_rate(struct clk *clk, unsigned long rate) if (clk->ops == NULL || clk->ops->set_rate == NULL) return -EINVAL; - spin_lock(&clocks_lock); + spin_lock_irqsave(&clocks_lock, flags); ret = (clk->ops->set_rate)(clk, rate); - spin_unlock(&clocks_lock); + spin_unlock_irqrestore(&clocks_lock, flags); return ret; } @@ -173,17 +174,18 @@ struct clk *clk_get_parent(struct clk *clk) int clk_set_parent(struct clk *clk, struct clk *parent) { + unsigned long flags; int ret = 0; if (IS_ERR(clk)) return -EINVAL; - spin_lock(&clocks_lock); + spin_lock_irqsave(&clocks_lock, flags); if (clk->ops && clk->ops->set_parent) ret = (clk->ops->set_parent)(clk, parent); - spin_unlock(&clocks_lock); + spin_unlock_irqrestore(&clocks_lock, flags); return ret; } diff --git a/arch/c6x/include/asm/Kbuild b/arch/c6x/include/asm/Kbuild index 3af601e31e6..f08e89183cd 100644 --- a/arch/c6x/include/asm/Kbuild +++ b/arch/c6x/include/asm/Kbuild @@ -2,6 +2,7 @@ include include/asm-generic/Kbuild.asm generic-y += atomic.h generic-y += auxvec.h +generic-y += barrier.h generic-y += bitsperlong.h generic-y += bugs.h generic-y += cputime.h diff --git a/arch/c6x/include/asm/barrier.h b/arch/c6x/include/asm/barrier.h deleted file mode 100644 index 538240e8590..00000000000 --- a/arch/c6x/include/asm/barrier.h +++ /dev/null @@ -1,27 +0,0 @@ -/* - * Port on Texas Instruments TMS320C6x architecture - * - * Copyright (C) 2004, 2009, 2010, 2011 Texas Instruments Incorporated - * Author: Aurelien Jacquiot (aurelien.jacquiot@jaluna.com) - * - * 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 _ASM_C6X_BARRIER_H -#define _ASM_C6X_BARRIER_H - -#define nop() asm("NOP\n"); - -#define mb() barrier() -#define rmb() barrier() -#define wmb() barrier() -#define set_mb(var, value) do { var = value; mb(); } while (0) -#define set_wmb(var, value) do { var = value; wmb(); } while (0) - -#define smp_mb() barrier() -#define smp_rmb() barrier() -#define smp_wmb() barrier() -#define smp_read_barrier_depends() do { } while (0) - -#endif /* _ASM_C6X_BARRIER_H */ diff --git a/arch/m68k/platform/coldfire/clk.c b/arch/m68k/platform/coldfire/clk.c index 75f9ee967ea..9cd13b4ce42 100644 --- a/arch/m68k/platform/coldfire/clk.c +++ b/arch/m68k/platform/coldfire/clk.c @@ -146,9 +146,3 @@ struct clk_ops clk_ops1 = { }; #endif /* MCFPM_PPMCR1 */ #endif /* MCFPM_PPMCR0 */ - -struct clk *devm_clk_get(struct device *dev, const char *id) -{ - return NULL; -} -EXPORT_SYMBOL(devm_clk_get); diff --git a/arch/mips/kernel/smp-cmp.c b/arch/mips/kernel/smp-cmp.c index e7e03ecf549..afc379ca375 100644 --- a/arch/mips/kernel/smp-cmp.c +++ b/arch/mips/kernel/smp-cmp.c @@ -102,7 +102,7 @@ static void cmp_init_secondary(void) c->vpe_id = (read_c0_tcbind() >> TCBIND_CURVPE_SHIFT) & TCBIND_CURVPE; #endif #ifdef CONFIG_MIPS_MT_SMTC - c->tc_id = (read_c0_tcbind() >> TCBIND_CURTC_SHIFT) & TCBIND_CURTC; + c->tc_id = (read_c0_tcbind() & TCBIND_CURTC) >> TCBIND_CURTC_SHIFT; #endif } diff --git a/arch/mips/mm/gup.c b/arch/mips/mm/gup.c index 33aadbcf170..dcfd573871c 100644 --- a/arch/mips/mm/gup.c +++ b/arch/mips/mm/gup.c @@ -152,6 +152,8 @@ static int gup_huge_pud(pud_t pud, unsigned long addr, unsigned long end, do { VM_BUG_ON(compound_head(page) != head); pages[*nr] = page; + if (PageTail(page)) + get_huge_page_tail(page); (*nr)++; page++; refs++; diff --git a/arch/mips/mti-malta/malta-int.c b/arch/mips/mti-malta/malta-int.c index 7b13a4caeea..fea823f1847 100644 --- a/arch/mips/mti-malta/malta-int.c +++ b/arch/mips/mti-malta/malta-int.c @@ -273,16 +273,19 @@ asmlinkage void plat_irq_dispatch(void) unsigned int pending = read_c0_cause() & read_c0_status() & ST0_IM; int irq; + if (unlikely(!pending)) { + spurious_interrupt(); + return; + } + irq = irq_ffs(pending); if (irq == MIPSCPU_INT_I8259A) malta_hw0_irqdispatch(); else if (gic_present && ((1 << irq) & ipi_map[smp_processor_id()])) malta_ipi_irqdispatch(); - else if (irq >= 0) - do_IRQ(MIPS_CPU_IRQ_BASE + irq); else - spurious_interrupt(); + do_IRQ(MIPS_CPU_IRQ_BASE + irq); } #ifdef CONFIG_MIPS_MT_SMP diff --git a/arch/mips/mti-malta/malta-platform.c b/arch/mips/mti-malta/malta-platform.c index 4c35301720e..80562b81f0f 100644 --- a/arch/mips/mti-malta/malta-platform.c +++ b/arch/mips/mti-malta/malta-platform.c @@ -138,11 +138,6 @@ static int __init malta_add_devices(void) if (err) return err; - /* - * Set RTC to BCD mode to support current alarm code. - */ - CMOS_WRITE(CMOS_READ(RTC_CONTROL) & ~RTC_DM_BINARY, RTC_CONTROL); - return 0; } diff --git a/arch/s390/include/asm/hugetlb.h b/arch/s390/include/asm/hugetlb.h index 799ed0f1643..2d6e6e38056 100644 --- a/arch/s390/include/asm/hugetlb.h +++ b/arch/s390/include/asm/hugetlb.h @@ -66,16 +66,6 @@ static inline pte_t huge_ptep_get(pte_t *ptep) return pte; } -static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm, - unsigned long addr, pte_t *ptep) -{ - pte_t pte = huge_ptep_get(ptep); - - mm->context.flush_mm = 1; - pmd_clear((pmd_t *) ptep); - return pte; -} - static inline void __pmd_csp(pmd_t *pmdp) { register unsigned long reg2 asm("2") = pmd_val(*pmdp); @@ -117,6 +107,15 @@ static inline void huge_ptep_invalidate(struct mm_struct *mm, __pmd_csp(pmdp); } +static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm, + unsigned long addr, pte_t *ptep) +{ + pte_t pte = huge_ptep_get(ptep); + + huge_ptep_invalidate(mm, addr, ptep); + return pte; +} + #define huge_ptep_set_access_flags(__vma, __addr, __ptep, __entry, __dirty) \ ({ \ int __changed = !pte_same(huge_ptep_get(__ptep), __entry); \ @@ -131,10 +130,7 @@ static inline void huge_ptep_invalidate(struct mm_struct *mm, ({ \ pte_t __pte = huge_ptep_get(__ptep); \ if (pte_write(__pte)) { \ - (__mm)->context.flush_mm = 1; \ - if (atomic_read(&(__mm)->context.attach_count) > 1 || \ - (__mm) != current->active_mm) \ - huge_ptep_invalidate(__mm, __addr, __ptep); \ + huge_ptep_invalidate(__mm, __addr, __ptep); \ set_huge_pte_at(__mm, __addr, __ptep, \ huge_pte_wrprotect(__pte)); \ } \ diff --git a/arch/s390/include/asm/tlbflush.h b/arch/s390/include/asm/tlbflush.h index 9fde315f3a7..1d8fe2b17ef 100644 --- a/arch/s390/include/asm/tlbflush.h +++ b/arch/s390/include/asm/tlbflush.h @@ -90,12 +90,10 @@ static inline void __tlb_flush_mm(struct mm_struct * mm) static inline void __tlb_flush_mm_cond(struct mm_struct * mm) { - spin_lock(&mm->page_table_lock); if (mm->context.flush_mm) { __tlb_flush_mm(mm); mm->context.flush_mm = 0; } - spin_unlock(&mm->page_table_lock); } /* diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index f86c81e13c3..40b57693de3 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -974,11 +974,13 @@ static void __init setup_hwcaps(void) if (MACHINE_HAS_HPAGE) elf_hwcap |= HWCAP_S390_HPAGE; +#if defined(CONFIG_64BIT) /* * 64-bit register support for 31-bit processes * HWCAP_S390_HIGH_GPRS is bit 9. */ elf_hwcap |= HWCAP_S390_HIGH_GPRS; +#endif get_cpu_id(&cpu_id); switch (cpu_id.machine) { diff --git a/arch/s390/lib/uaccess_pt.c b/arch/s390/lib/uaccess_pt.c index 60ee2b88379..2d37bb861fa 100644 --- a/arch/s390/lib/uaccess_pt.c +++ b/arch/s390/lib/uaccess_pt.c @@ -2,69 +2,82 @@ * User access functions based on page table walks for enhanced * system layout without hardware support. * - * Copyright IBM Corp. 2006 + * Copyright IBM Corp. 2006, 2012 * Author(s): Gerald Schaefer (gerald.schaefer@de.ibm.com) */ #include <linux/errno.h> #include <linux/hardirq.h> #include <linux/mm.h> +#include <linux/hugetlb.h> #include <asm/uaccess.h> #include <asm/futex.h> #include "uaccess.h" -static inline pte_t *follow_table(struct mm_struct *mm, unsigned long addr) + +/* + * Returns kernel address for user virtual address. If the returned address is + * >= -4095 (IS_ERR_VALUE(x) returns true), a fault has occured and the address + * contains the (negative) exception code. + */ +static __always_inline unsigned long follow_table(struct mm_struct *mm, + unsigned long addr, int write) { pgd_t *pgd; pud_t *pud; pmd_t *pmd; + pte_t *ptep; pgd = pgd_offset(mm, addr); if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd))) - return (pte_t *) 0x3a; + return -0x3aUL; pud = pud_offset(pgd, addr); if (pud_none(*pud) || unlikely(pud_bad(*pud))) - return (pte_t *) 0x3b; + return -0x3bUL; pmd = pmd_offset(pud, addr); - if (pmd_none(*pmd) || unlikely(pmd_bad(*pmd))) - return (pte_t *) 0x10; + if (pmd_none(*pmd)) + return -0x10UL; + if (pmd_huge(*pmd)) { + if (write && (pmd_val(*pmd) & _SEGMENT_ENTRY_RO)) + return -0x04UL; + return (pmd_val(*pmd) & HPAGE_MASK) + (addr & ~HPAGE_MASK); + } + if (unlikely(pmd_bad(*pmd))) + return -0x10UL; + + ptep = pte_offset_map(pmd, addr); + if (!pte_present(*ptep)) + return -0x11UL; + if (write && !pte_write(*ptep)) + return -0x04UL; - return pte_offset_map(pmd, addr); + return (pte_val(*ptep) & PAGE_MASK) + (addr & ~PAGE_MASK); } static __always_inline size_t __user_copy_pt(unsigned long uaddr, void *kptr, size_t n, int write_user) { struct mm_struct *mm = current->mm; - unsigned long offset, pfn, done, size; - pte_t *pte; + unsigned long offset, done, size, kaddr; void *from, *to; done = 0; retry: spin_lock(&mm->page_table_lock); do { - pte = follow_table(mm, uaddr); - if ((unsigned long) pte < 0x1000) + kaddr = follow_table(mm, uaddr, write_user); + if (IS_ERR_VALUE(kaddr)) goto fault; - if (!pte_present(*pte)) { - pte = (pte_t *) 0x11; - goto fault; - } else if (write_user && !pte_write(*pte)) { - pte = (pte_t *) 0x04; - goto fault; - } - pfn = pte_pfn(*pte); - offset = uaddr & (PAGE_SIZE - 1); + offset = uaddr & ~PAGE_MASK; size = min(n - done, PAGE_SIZE - offset); if (write_user) { - to = (void *)((pfn << PAGE_SHIFT) + offset); + to = (void *) kaddr; from = kptr + done; } else { - from = (void *)((pfn << PAGE_SHIFT) + offset); + from = (void *) kaddr; to = kptr + done; } memcpy(to, from, size); @@ -75,7 +88,7 @@ retry: return n - done; fault: spin_unlock(&mm->page_table_lock); - if (__handle_fault(uaddr, (unsigned long) pte, write_user)) + if (__handle_fault(uaddr, -kaddr, write_user)) return n - done; goto retry; } @@ -84,27 +97,22 @@ fault: * Do DAT for user address by page table walk, return kernel address. * This function needs to be called with current->mm->page_table_lock held. */ -static __always_inline unsigned long __dat_user_addr(unsigned long uaddr) +static __always_inline unsigned long __dat_user_addr(unsigned long uaddr, + int write) { struct mm_struct *mm = current->mm; - unsigned long pfn; - pte_t *pte; + unsigned long kaddr; int rc; retry: - pte = follow_table(mm, uaddr); - if ((unsigned long) pte < 0x1000) - goto fault; - if (!pte_present(*pte)) { - pte = (pte_t *) 0x11; + kaddr = follow_table(mm, uaddr, write); + if (IS_ERR_VALUE(kaddr)) goto fault; - } - pfn = pte_pfn(*pte); - return (pfn << PAGE_SHIFT) + (uaddr & (PAGE_SIZE - 1)); + return kaddr; fault: spin_unlock(&mm->page_table_lock); - rc = __handle_fault(uaddr, (unsigned long) pte, 0); + rc = __handle_fault(uaddr, -kaddr, write); spin_lock(&mm->page_table_lock); if (!rc) goto retry; @@ -159,11 +167,9 @@ static size_t clear_user_pt(size_t n, void __user *to) static size_t strnlen_user_pt(size_t count, const char __user *src) { - char *addr; unsigned long uaddr = (unsigned long) src; struct mm_struct *mm = current->mm; - unsigned long offset, pfn, done, len; - pte_t *pte; + unsigned long offset, done, len, kaddr; size_t len_str; if (segment_eq(get_fs(), KERNEL_DS)) @@ -172,19 +178,13 @@ static size_t strnlen_user_pt(size_t count, const char __user *src) retry: spin_lock(&mm->page_table_lock); do { - pte = follow_table(mm, uaddr); - if ((unsigned long) pte < 0x1000) - goto fault; - if (!pte_present(*pte)) { - pte = (pte_t *) 0x11; + kaddr = follow_table(mm, uaddr, 0); + if (IS_ERR_VALUE(kaddr)) goto fault; - } - pfn = pte_pfn(*pte); - offset = uaddr & (PAGE_SIZE-1); - addr = (char *)(pfn << PAGE_SHIFT) + offset; + offset = uaddr & ~PAGE_MASK; len = min(count - done, PAGE_SIZE - offset); - len_str = strnlen(addr, len); + len_str = strnlen((char *) kaddr, len); done += len_str; uaddr += len_str; } while ((len_str == len) && (done < count)); @@ -192,7 +192,7 @@ retry: return done + 1; fault: spin_unlock(&mm->page_table_lock); - if (__handle_fault(uaddr, (unsigned long) pte, 0)) + if (__handle_fault(uaddr, -kaddr, 0)) return 0; goto retry; } @@ -225,11 +225,10 @@ static size_t copy_in_user_pt(size_t n, void __user *to, const void __user *from) { struct mm_struct *mm = current->mm; - unsigned long offset_from, offset_to, offset_max, pfn_from, pfn_to, - uaddr, done, size, error_code; + unsigned long offset_max, uaddr, done, size, error_code; unsigned long uaddr_from = (unsigned long) from; unsigned long uaddr_to = (unsigned long) to; - pte_t *pte_from, *pte_to; + unsigned long kaddr_to, kaddr_from; int write_user; if (segment_eq(get_fs(), KERNEL_DS)) { @@ -242,38 +241,23 @@ retry: do { write_user = 0; uaddr = uaddr_from; - pte_from = follow_table(mm, uaddr_from); - error_code = (unsigned long) pte_from; - if (error_code < 0x1000) - goto fault; - if (!pte_present(*pte_from)) { - error_code = 0x11; + kaddr_from = follow_table(mm, uaddr_from, 0); + error_code = kaddr_from; + if (IS_ERR_VALUE(error_code)) goto fault; - } write_user = 1; uaddr = uaddr_to; - pte_to = follow_table(mm, uaddr_to); - error_code = (unsigned long) pte_to; - if (error_code < 0x1000) - goto fault; - if (!pte_present(*pte_to)) { - error_code = 0x11; + kaddr_to = follow_table(mm, uaddr_to, 1); + error_code = (unsigned long) kaddr_to; + if (IS_ERR_VALUE(error_code)) goto fault; - } else if (!pte_write(*pte_to)) { - error_code = 0x04; - goto fault; - } - pfn_from = pte_pfn(*pte_from); - pfn_to = pte_pfn(*pte_to); - offset_from = uaddr_from & (PAGE_SIZE-1); - offset_to = uaddr_from & (PAGE_SIZE-1); - offset_max = max(offset_from, offset_to); + offset_max = max(uaddr_from & ~PAGE_MASK, + uaddr_to & ~PAGE_MASK); size = min(n - done, PAGE_SIZE - offset_max); - memcpy((void *)(pfn_to << PAGE_SHIFT) + offset_to, - (void *)(pfn_from << PAGE_SHIFT) + offset_from, size); + memcpy((void *) kaddr_to, (void *) kaddr_from, size); done += size; uaddr_from += size; uaddr_to += size; @@ -282,7 +266,7 @@ retry: return n - done; fault: spin_unlock(&mm->page_table_lock); - if (__handle_fault(uaddr, error_code, write_user)) + if (__handle_fault(uaddr, -error_code, write_user)) return n - done; goto retry; } @@ -341,7 +325,7 @@ int futex_atomic_op_pt(int op, u32 __user *uaddr, int oparg, int *old) return __futex_atomic_op_pt(op, uaddr, oparg, old); spin_lock(¤t->mm->page_table_lock); uaddr = (u32 __force __user *) - __dat_user_addr((__force unsigned long) uaddr); + __dat_user_addr((__force unsigned long) uaddr, 1); if (!uaddr) { spin_unlock(¤t->mm->page_table_lock); return -EFAULT; @@ -378,7 +362,7 @@ int futex_atomic_cmpxchg_pt(u32 *uval, u32 __user *uaddr, return __futex_atomic_cmpxchg_pt(uval, uaddr, oldval, newval); spin_lock(¤t->mm->page_table_lock); uaddr = (u32 __force __user *) - __dat_user_addr((__force unsigned long) uaddr); + __dat_user_addr((__force unsigned long) uaddr, 1); if (!uaddr) { spin_unlock(¤t->mm->page_table_lock); return -EFAULT; diff --git a/arch/sh/kernel/cpu/sh5/entry.S b/arch/sh/kernel/cpu/sh5/entry.S index b7cf6a547f1..7e605b95592 100644 --- a/arch/sh/kernel/cpu/sh5/entry.S +++ b/arch/sh/kernel/cpu/sh5/entry.S @@ -933,7 +933,7 @@ ret_with_reschedule: pta restore_all, tr1 - movi _TIF_SIGPENDING, r8 + movi (_TIF_SIGPENDING|_TIF_NOTIFY_RESUME), r8 and r8, r7, r8 pta work_notifysig, tr0 bne r8, ZERO, tr0 diff --git a/arch/sh/kernel/entry-common.S b/arch/sh/kernel/entry-common.S index f67601cb3f1..b96489d8b27 100644 --- a/arch/sh/kernel/entry-common.S +++ b/arch/sh/kernel/entry-common.S @@ -139,7 +139,7 @@ work_pending: ! r8: current_thread_info ! t: result of "tst #_TIF_NEED_RESCHED, r0" bf/s work_resched - tst #_TIF_SIGPENDING, r0 + tst #(_TIF_SIGPENDING | _TIF_NOTIFY_RESUME), r0 work_notifysig: bt/s __restore_all mov r15, r4 diff --git a/arch/sparc/kernel/module.c b/arch/sparc/kernel/module.c index 15e0a169397..f1ddc0d2367 100644 --- a/arch/sparc/kernel/module.c +++ b/arch/sparc/kernel/module.c @@ -48,9 +48,7 @@ void *module_alloc(unsigned long size) return NULL; ret = module_map(size); - if (!ret) - ret = ERR_PTR(-ENOMEM); - else + if (ret) memset(ret, 0, size); return ret; @@ -116,6 +114,10 @@ int apply_relocate_add(Elf_Shdr *sechdrs, v = sym->st_value + rel[i].r_addend; switch (ELF_R_TYPE(rel[i].r_info) & 0xff) { + case R_SPARC_DISP32: + v -= (Elf_Addr) location; + *loc32 = v; + break; #ifdef CONFIG_SPARC64 case R_SPARC_64: location[0] = v >> 56; @@ -128,11 +130,6 @@ int apply_relocate_add(Elf_Shdr *sechdrs, location[7] = v >> 0; break; - case R_SPARC_DISP32: - v -= (Elf_Addr) location; - *loc32 = v; - break; - case R_SPARC_WDISP19: v -= (Elf_Addr) location; *loc32 = (*loc32 & ~0x7ffff) | diff --git a/arch/tile/include/gxio/iorpc_trio.h b/arch/tile/include/gxio/iorpc_trio.h index 15fb7799208..58105c31228 100644 --- a/arch/tile/include/gxio/iorpc_trio.h +++ b/arch/tile/include/gxio/iorpc_trio.h @@ -25,21 +25,23 @@ #include <linux/module.h> #include <asm/pgtable.h> -#define GXIO_TRIO_OP_ALLOC_ASIDS IORPC_OPCODE(IORPC_FORMAT_NONE, 0x1400) +#define GXIO_TRIO_OP_DEALLOC_ASID IORPC_OPCODE(IORPC_FORMAT_NONE, 0x1400) +#define GXIO_TRIO_OP_ALLOC_ASIDS IORPC_OPCODE(IORPC_FORMAT_NONE, 0x1401) -#define GXIO_TRIO_OP_ALLOC_MEMORY_MAPS IORPC_OPCODE(IORPC_FORMAT_NONE, 0x1402) +#define GXIO_TRIO_OP_ALLOC_MEMORY_MAPS IORPC_OPCODE(IORPC_FORMAT_NONE, 0x1404) -#define GXIO_TRIO_OP_ALLOC_PIO_REGIONS IORPC_OPCODE(IORPC_FORMAT_NONE, 0x140e) -#define GXIO_TRIO_OP_INIT_PIO_REGION_AUX IORPC_OPCODE(IORPC_FORMAT_NONE, 0x140f) +#define GXIO_TRIO_OP_ALLOC_PIO_REGIONS IORPC_OPCODE(IORPC_FORMAT_NONE, 0x1412) -#define GXIO_TRIO_OP_INIT_MEMORY_MAP_MMU_AUX IORPC_OPCODE(IORPC_FORMAT_NONE_NOUSER, 0x1417) -#define GXIO_TRIO_OP_GET_PORT_PROPERTY IORPC_OPCODE(IORPC_FORMAT_NONE_NOUSER, 0x1418) -#define GXIO_TRIO_OP_CONFIG_LEGACY_INTR IORPC_OPCODE(IORPC_FORMAT_KERNEL_INTERRUPT, 0x1419) -#define GXIO_TRIO_OP_CONFIG_MSI_INTR IORPC_OPCODE(IORPC_FORMAT_KERNEL_INTERRUPT, 0x141a) +#define GXIO_TRIO_OP_INIT_PIO_REGION_AUX IORPC_OPCODE(IORPC_FORMAT_NONE, 0x1414) -#define GXIO_TRIO_OP_SET_MPS_MRS IORPC_OPCODE(IORPC_FORMAT_NONE_NOUSER, 0x141c) -#define GXIO_TRIO_OP_FORCE_RC_LINK_UP IORPC_OPCODE(IORPC_FORMAT_NONE_NOUSER, 0x141d) -#define GXIO_TRIO_OP_FORCE_EP_LINK_UP IORPC_OPCODE(IORPC_FORMAT_NONE_NOUSER, 0x141e) +#define GXIO_TRIO_OP_INIT_MEMORY_MAP_MMU_AUX IORPC_OPCODE(IORPC_FORMAT_NONE_NOUSER, 0x141e) +#define GXIO_TRIO_OP_GET_PORT_PROPERTY IORPC_OPCODE(IORPC_FORMAT_NONE_NOUSER, 0x141f) +#define GXIO_TRIO_OP_CONFIG_LEGACY_INTR IORPC_OPCODE(IORPC_FORMAT_KERNEL_INTERRUPT, 0x1420) +#define GXIO_TRIO_OP_CONFIG_MSI_INTR IORPC_OPCODE(IORPC_FORMAT_KERNEL_INTERRUPT, 0x1421) + +#define GXIO_TRIO_OP_SET_MPS_MRS IORPC_OPCODE(IORPC_FORMAT_NONE_NOUSER, 0x1423) +#define GXIO_TRIO_OP_FORCE_RC_LINK_UP IORPC_OPCODE(IORPC_FORMAT_NONE_NOUSER, 0x1424) +#define GXIO_TRIO_OP_FORCE_EP_LINK_UP IORPC_OPCODE(IORPC_FORMAT_NONE_NOUSER, 0x1425) #define GXIO_TRIO_OP_GET_MMIO_BASE IORPC_OPCODE(IORPC_FORMAT_NONE_NOUSER, 0x8000) #define GXIO_TRIO_OP_CHECK_MMIO_OFFSET IORPC_OPCODE(IORPC_FORMAT_NONE_NOUSER, 0x8001) diff --git a/arch/um/include/asm/processor-generic.h b/arch/um/include/asm/processor-generic.h index 69f1c57a8d0..33a6a2423bd 100644 --- a/arch/um/include/asm/processor-generic.h +++ b/arch/um/include/asm/processor-generic.h @@ -20,14 +20,6 @@ struct mm_struct; struct thread_struct { struct task_struct *saved_task; - /* - * This flag is set to 1 before calling do_fork (and analyzed in - * copy_thread) to mark that we are begin called from userspace (fork / - * vfork / clone), and reset to 0 after. It is left to 0 when called - * from kernelspace (i.e. kernel_thread() or fork_idle(), - * as of 2.6.11). - */ - int forking; struct pt_regs regs; int singlestep_syscall; void *fault_addr; @@ -58,7 +50,6 @@ struct thread_struct { #define INIT_THREAD \ { \ - .forking = 0, \ .regs = EMPTY_REGS, \ .fault_addr = NULL, \ .prev_sched = NULL, \ diff --git a/arch/um/include/shared/common-offsets.h b/arch/um/include/shared/common-offsets.h index 40db8f71dea..2df313b6a58 100644 --- a/arch/um/include/shared/common-offsets.h +++ b/arch/um/include/shared/common-offsets.h @@ -7,16 +7,6 @@ DEFINE(UM_KERN_PAGE_MASK, PAGE_MASK); DEFINE(UM_KERN_PAGE_SHIFT, PAGE_SHIFT); DEFINE(UM_NSEC_PER_SEC, NSEC_PER_SEC); -DEFINE_STR(UM_KERN_EMERG, KERN_EMERG); -DEFINE_STR(UM_KERN_ALERT, KERN_ALERT); -DEFINE_STR(UM_KERN_CRIT, KERN_CRIT); -DEFINE_STR(UM_KERN_ERR, KERN_ERR); -DEFINE_STR(UM_KERN_WARNING, KERN_WARNING); -DEFINE_STR(UM_KERN_NOTICE, KERN_NOTICE); -DEFINE_STR(UM_KERN_INFO, KERN_INFO); -DEFINE_STR(UM_KERN_DEBUG, KERN_DEBUG); -DEFINE_STR(UM_KERN_CONT, KERN_CONT); - DEFINE(UM_ELF_CLASS, ELF_CLASS); DEFINE(UM_ELFCLASS32, ELFCLASS32); DEFINE(UM_ELFCLASS64, ELFCLASS64); diff --git a/arch/um/include/shared/user.h b/arch/um/include/shared/user.h index 4fa82c055aa..cef06856333 100644 --- a/arch/um/include/shared/user.h +++ b/arch/um/include/shared/user.h @@ -26,6 +26,17 @@ extern void panic(const char *fmt, ...) __attribute__ ((format (printf, 1, 2))); +/* Requires preincluding include/linux/kern_levels.h */ +#define UM_KERN_EMERG KERN_EMERG +#define UM_KERN_ALERT KERN_ALERT +#define UM_KERN_CRIT KERN_CRIT +#define UM_KERN_ERR KERN_ERR +#define UM_KERN_WARNING KERN_WARNING +#define UM_KERN_NOTICE KERN_NOTICE +#define UM_KERN_INFO KERN_INFO +#define UM_KERN_DEBUG KERN_DEBUG +#define UM_KERN_CONT KERN_CONT + #ifdef UML_CONFIG_PRINTK extern int printk(const char *fmt, ...) __attribute__ ((format (printf, 1, 2))); diff --git a/arch/um/kernel/exec.c b/arch/um/kernel/exec.c index 6cade936636..8c82786da82 100644 --- a/arch/um/kernel/exec.c +++ b/arch/um/kernel/exec.c @@ -39,34 +39,21 @@ void flush_thread(void) void start_thread(struct pt_regs *regs, unsigned long eip, unsigned long esp) { + get_safe_registers(regs->regs.gp, regs->regs.fp); PT_REGS_IP(regs) = eip; PT_REGS_SP(regs) = esp; -} -EXPORT_SYMBOL(start_thread); - -static long execve1(const char *file, - const char __user *const __user *argv, - const char __user *const __user *env) -{ - long error; - - error = do_execve(file, argv, env, ¤t->thread.regs); - if (error == 0) { - task_lock(current); - current->ptrace &= ~PT_DTRACE; + current->ptrace &= ~PT_DTRACE; #ifdef SUBARCH_EXECVE1 - SUBARCH_EXECVE1(¤t->thread.regs.regs); + SUBARCH_EXECVE1(regs->regs); #endif - task_unlock(current); - } - return error; } +EXPORT_SYMBOL(start_thread); long um_execve(const char *file, const char __user *const __user *argv, const char __user *const __user *env) { long err; - err = execve1(file, argv, env); + err = do_execve(file, argv, env, ¤t->thread.regs); if (!err) UML_LONGJMP(current->thread.exec_buf, 1); return err; @@ -81,7 +68,7 @@ long sys_execve(const char __user *file, const char __user *const __user *argv, filename = getname(file); error = PTR_ERR(filename); if (IS_ERR(filename)) goto out; - error = execve1(filename, argv, env); + error = do_execve(filename, argv, env, ¤t->thread.regs); putname(filename); out: return error; diff --git a/arch/um/kernel/process.c b/arch/um/kernel/process.c index 57fc7028714..c5f5afa5074 100644 --- a/arch/um/kernel/process.c +++ b/arch/um/kernel/process.c @@ -181,11 +181,12 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, struct pt_regs *regs) { void (*handler)(void); + int kthread = current->flags & PF_KTHREAD; int ret = 0; p->thread = (struct thread_struct) INIT_THREAD; - if (current->thread.forking) { + if (!kthread) { memcpy(&p->thread.regs.regs, ®s->regs, sizeof(p->thread.regs.regs)); PT_REGS_SET_SYSCALL_RETURN(&p->thread.regs, 0); @@ -195,8 +196,7 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, handler = fork_handler; arch_copy_thread(¤t->thread.arch, &p->thread.arch); - } - else { + } else { get_safe_registers(p->thread.regs.regs.gp, p->thread.regs.regs.fp); p->thread.request.u.thread = current->thread.request.u.thread; handler = new_thread_handler; @@ -204,7 +204,7 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, new_thread(task_stack_page(p), &p->thread.switch_buf, handler); - if (current->thread.forking) { + if (!kthread) { clear_flushed_tls(p); /* diff --git a/arch/um/kernel/signal.c b/arch/um/kernel/signal.c index 7362d58efc2..cc9c2350e41 100644 --- a/arch/um/kernel/signal.c +++ b/arch/um/kernel/signal.c @@ -22,9 +22,13 @@ static void handle_signal(struct pt_regs *regs, unsigned long signr, struct k_sigaction *ka, siginfo_t *info) { sigset_t *oldset = sigmask_to_save(); + int singlestep = 0; unsigned long sp; int err; + if ((current->ptrace & PT_DTRACE) && (current->ptrace & PT_PTRACED)) + singlestep = 1; + /* Did we come from a system call? */ if (PT_REGS_SYSCALL_NR(regs) >= 0) { /* If so, check system call restarting.. */ @@ -61,7 +65,7 @@ static void handle_signal(struct pt_regs *regs, unsigned long signr, if (err) force_sigsegv(signr, current); else - signal_delivered(signr, info, ka, regs, 0); + signal_delivered(signr, info, ka, regs, singlestep); } static int kern_do_signal(struct pt_regs *regs) diff --git a/arch/um/kernel/syscall.c b/arch/um/kernel/syscall.c index f958cb876ee..a4c6d8eee74 100644 --- a/arch/um/kernel/syscall.c +++ b/arch/um/kernel/syscall.c @@ -17,25 +17,25 @@ long sys_fork(void) { - long ret; - - current->thread.forking = 1; - ret = do_fork(SIGCHLD, UPT_SP(¤t->thread.regs.regs), + return do_fork(SIGCHLD, UPT_SP(¤t->thread.regs.regs), ¤t->thread.regs, 0, NULL, NULL); - current->thread.forking = 0; - return ret; } long sys_vfork(void) { - long ret; - - current->thread.forking = 1; - ret = do_fork(CLONE_VFORK | CLONE_VM | SIGCHLD, + return do_fork(CLONE_VFORK | CLONE_VM | SIGCHLD, UPT_SP(¤t->thread.regs.regs), ¤t->thread.regs, 0, NULL, NULL); - current->thread.forking = 0; - return ret; +} + +long sys_clone(unsigned long clone_flags, unsigned long newsp, + void __user *parent_tid, void __user *child_tid) +{ + if (!newsp) + newsp = UPT_SP(¤t->thread.regs.regs); + + return do_fork(clone_flags, newsp, ¤t->thread.regs, 0, parent_tid, + child_tid); } long old_mmap(unsigned long addr, unsigned long len, diff --git a/arch/um/scripts/Makefile.rules b/arch/um/scripts/Makefile.rules index d50270d26b4..15889df9b46 100644 --- a/arch/um/scripts/Makefile.rules +++ b/arch/um/scripts/Makefile.rules @@ -8,7 +8,7 @@ USER_OBJS += $(filter %_user.o,$(obj-y) $(obj-m) $(USER_SINGLE_OBJS)) USER_OBJS := $(foreach file,$(USER_OBJS),$(obj)/$(file)) $(USER_OBJS:.o=.%): \ - c_flags = -Wp,-MD,$(depfile) $(USER_CFLAGS) -include user.h $(CFLAGS_$(basetarget).o) + c_flags = -Wp,-MD,$(depfile) $(USER_CFLAGS) -include $(srctree)/include/linux/kern_levels.h -include user.h $(CFLAGS_$(basetarget).o) # These are like USER_OBJS but filter USER_CFLAGS through unprofile instead of # using it directly. diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 8ec3a1aa4ab..50a1d1f9b6d 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -746,10 +746,10 @@ config SWIOTLB def_bool y if X86_64 ---help--- Support for software bounce buffers used on x86-64 systems - which don't have a hardware IOMMU (e.g. the current generation - of Intel's x86-64 CPUs). Using this PCI devices which can only - access 32-bits of memory can be used on systems with more than - 3 GB of memory. If unsure, say Y. + which don't have a hardware IOMMU. Using this PCI devices + which can only access 32-bits of memory can be used on systems + with more than 3 GB of memory. + If unsure, say Y. config IOMMU_HELPER def_bool (CALGARY_IOMMU || GART_IOMMU || SWIOTLB || AMD_IOMMU) diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 682e9c210ba..474ca35b1bc 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -142,7 +142,7 @@ KBUILD_CFLAGS += $(call cc-option,-mno-avx,) KBUILD_CFLAGS += $(mflags-y) KBUILD_AFLAGS += $(mflags-y) -archscripts: +archscripts: scripts_basic $(Q)$(MAKE) $(build)=arch/x86/tools relocs ### diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h index 93971e841dd..472b9b78301 100644 --- a/arch/x86/include/asm/xen/page.h +++ b/arch/x86/include/asm/xen/page.h @@ -51,7 +51,8 @@ extern unsigned long set_phys_range_identity(unsigned long pfn_s, extern int m2p_add_override(unsigned long mfn, struct page *page, struct gnttab_map_grant_ref *kmap_op); -extern int m2p_remove_override(struct page *page, bool clear_pte); +extern int m2p_remove_override(struct page *page, + struct gnttab_map_grant_ref *kmap_op); extern struct page *m2p_find_override(unsigned long mfn); extern unsigned long m2p_find_override_pfn(unsigned long mfn, unsigned long pfn); diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h index 6605a81ba33..8b6defe7eef 100644 --- a/arch/x86/kernel/cpu/perf_event.h +++ b/arch/x86/kernel/cpu/perf_event.h @@ -586,6 +586,8 @@ extern struct event_constraint intel_westmere_pebs_event_constraints[]; extern struct event_constraint intel_snb_pebs_event_constraints[]; +extern struct event_constraint intel_ivb_pebs_event_constraints[]; + struct event_constraint *intel_pebs_constraints(struct perf_event *event); void intel_pmu_pebs_enable(struct perf_event *event); diff --git a/arch/x86/kernel/cpu/perf_event_amd_ibs.c b/arch/x86/kernel/cpu/perf_event_amd_ibs.c index 7bfb5bec863..eebd5ffe1bb 100644 --- a/arch/x86/kernel/cpu/perf_event_amd_ibs.c +++ b/arch/x86/kernel/cpu/perf_event_amd_ibs.c @@ -209,6 +209,15 @@ static int perf_ibs_precise_event(struct perf_event *event, u64 *config) return -EOPNOTSUPP; } +static const struct perf_event_attr ibs_notsupp = { + .exclude_user = 1, + .exclude_kernel = 1, + .exclude_hv = 1, + .exclude_idle = 1, + .exclude_host = 1, + .exclude_guest = 1, +}; + static int perf_ibs_init(struct perf_event *event) { struct hw_perf_event *hwc = &event->hw; @@ -229,6 +238,9 @@ static int perf_ibs_init(struct perf_event *event) if (event->pmu != &perf_ibs->pmu) return -ENOENT; + if (perf_flags(&event->attr) & perf_flags(&ibs_notsupp)) + return -EINVAL; + if (config & ~perf_ibs->config_mask) return -EINVAL; diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index 0d3d63afa76..6bca492b854 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -2048,7 +2048,6 @@ __init int intel_pmu_init(void) case 42: /* SandyBridge */ case 45: /* SandyBridge, "Romely-EP" */ x86_add_quirk(intel_sandybridge_quirk); - case 58: /* IvyBridge */ memcpy(hw_cache_event_ids, snb_hw_cache_event_ids, sizeof(hw_cache_event_ids)); memcpy(hw_cache_extra_regs, snb_hw_cache_extra_regs, @@ -2073,6 +2072,29 @@ __init int intel_pmu_init(void) pr_cont("SandyBridge events, "); break; + case 58: /* IvyBridge */ + memcpy(hw_cache_event_ids, snb_hw_cache_event_ids, + sizeof(hw_cache_event_ids)); + memcpy(hw_cache_extra_regs, snb_hw_cache_extra_regs, + sizeof(hw_cache_extra_regs)); + + intel_pmu_lbr_init_snb(); + + x86_pmu.event_constraints = intel_snb_event_constraints; + x86_pmu.pebs_constraints = intel_ivb_pebs_event_constraints; + x86_pmu.pebs_aliases = intel_pebs_aliases_snb; + x86_pmu.extra_regs = intel_snb_extra_regs; + /* all extra regs are per-cpu when HT is on */ + x86_pmu.er_flags |= ERF_HAS_RSP_1; + x86_pmu.er_flags |= ERF_NO_HT_SHARING; + + /* UOPS_ISSUED.ANY,c=1,i=1 to count stall cycles */ + intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = + X86_CONFIG(.event=0x0e, .umask=0x01, .inv=1, .cmask=1); + + pr_cont("IvyBridge events, "); + break; + default: switch (x86_pmu.version) { diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c index e38d97bf425..826054a4f2e 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_ds.c +++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c @@ -407,6 +407,20 @@ struct event_constraint intel_snb_pebs_event_constraints[] = { EVENT_CONSTRAINT_END }; +struct event_constraint intel_ivb_pebs_event_constraints[] = { + INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PRECDIST */ + INTEL_UEVENT_CONSTRAINT(0x01c2, 0xf), /* UOPS_RETIRED.ALL */ + INTEL_UEVENT_CONSTRAINT(0x02c2, 0xf), /* UOPS_RETIRED.RETIRE_SLOTS */ + INTEL_EVENT_CONSTRAINT(0xc4, 0xf), /* BR_INST_RETIRED.* */ + INTEL_EVENT_CONSTRAINT(0xc5, 0xf), /* BR_MISP_RETIRED.* */ + INTEL_EVENT_CONSTRAINT(0xcd, 0x8), /* MEM_TRANS_RETIRED.* */ + INTEL_EVENT_CONSTRAINT(0xd0, 0xf), /* MEM_UOP_RETIRED.* */ + INTEL_EVENT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */ + INTEL_EVENT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */ + INTEL_EVENT_CONSTRAINT(0xd3, 0xf), /* MEM_LOAD_UOPS_LLC_MISS_RETIRED.* */ + EVENT_CONSTRAINT_END +}; + struct event_constraint *intel_pebs_constraints(struct perf_event *event) { struct event_constraint *c; diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c index 0a5571080e7..38e4894165b 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c @@ -661,6 +661,11 @@ static void snb_uncore_msr_init_box(struct intel_uncore_box *box) } } +static struct uncore_event_desc snb_uncore_events[] = { + INTEL_UNCORE_EVENT_DESC(clockticks, "event=0xff,umask=0x00"), + { /* end: all zeroes */ }, +}; + static struct attribute *snb_uncore_formats_attr[] = { &format_attr_event.attr, &format_attr_umask.attr, @@ -704,6 +709,7 @@ static struct intel_uncore_type snb_uncore_cbox = { .constraints = snb_uncore_cbox_constraints, .ops = &snb_uncore_msr_ops, .format_group = &snb_uncore_format_group, + .event_descs = snb_uncore_events, }; static struct intel_uncore_type *snb_msr_uncores[] = { diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index e0e6990723e..ab1f6a93b52 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -319,7 +319,7 @@ unsigned long __init_refok init_memory_mapping(unsigned long start, */ int devmem_is_allowed(unsigned long pagenr) { - if (pagenr <= 256) + if (pagenr < 256) return 1; if (iomem_is_exclusive(pagenr << PAGE_SHIFT)) return 0; diff --git a/arch/x86/um/Kconfig b/arch/x86/um/Kconfig index 9926e11a772..aeaff8bef2f 100644 --- a/arch/x86/um/Kconfig +++ b/arch/x86/um/Kconfig @@ -21,6 +21,7 @@ config 64BIT config X86_32 def_bool !64BIT select HAVE_AOUT + select ARCH_WANT_IPC_PARSE_VERSION config X86_64 def_bool 64BIT diff --git a/arch/x86/um/shared/sysdep/kernel-offsets.h b/arch/x86/um/shared/sysdep/kernel-offsets.h index 5868526b5ee..46a9df99f3c 100644 --- a/arch/x86/um/shared/sysdep/kernel-offsets.h +++ b/arch/x86/um/shared/sysdep/kernel-offsets.h @@ -7,9 +7,6 @@ #define DEFINE(sym, val) \ asm volatile("\n->" #sym " %0 " #val : : "i" (val)) -#define STR(x) #x -#define DEFINE_STR(sym, val) asm volatile("\n->" #sym " " STR(val) " " #val: : ) - #define BLANK() asm volatile("\n->" : : ) #define OFFSET(sym, str, mem) \ diff --git a/arch/x86/um/shared/sysdep/syscalls.h b/arch/x86/um/shared/sysdep/syscalls.h index bd9a89b67e4..ca255a805ed 100644 --- a/arch/x86/um/shared/sysdep/syscalls.h +++ b/arch/x86/um/shared/sysdep/syscalls.h @@ -1,3 +1,5 @@ +extern long sys_clone(unsigned long clone_flags, unsigned long newsp, + void __user *parent_tid, void __user *child_tid); #ifdef __i386__ #include "syscalls_32.h" #else diff --git a/arch/x86/um/signal.c b/arch/x86/um/signal.c index a508cea1350..ba7363ecf89 100644 --- a/arch/x86/um/signal.c +++ b/arch/x86/um/signal.c @@ -416,9 +416,6 @@ int setup_signal_stack_sc(unsigned long stack_top, int sig, PT_REGS_AX(regs) = (unsigned long) sig; PT_REGS_DX(regs) = (unsigned long) 0; PT_REGS_CX(regs) = (unsigned long) 0; - - if ((current->ptrace & PT_DTRACE) && (current->ptrace & PT_PTRACED)) - ptrace_notify(SIGTRAP); return 0; } @@ -466,9 +463,6 @@ int setup_signal_stack_si(unsigned long stack_top, int sig, PT_REGS_AX(regs) = (unsigned long) sig; PT_REGS_DX(regs) = (unsigned long) &frame->info; PT_REGS_CX(regs) = (unsigned long) &frame->uc; - - if ((current->ptrace & PT_DTRACE) && (current->ptrace & PT_PTRACED)) - ptrace_notify(SIGTRAP); return 0; } diff --git a/arch/x86/um/sys_call_table_32.c b/arch/x86/um/sys_call_table_32.c index 68d1dc91b37..b5408cecac6 100644 --- a/arch/x86/um/sys_call_table_32.c +++ b/arch/x86/um/sys_call_table_32.c @@ -28,7 +28,7 @@ #define ptregs_execve sys_execve #define ptregs_iopl sys_iopl #define ptregs_vm86old sys_vm86old -#define ptregs_clone sys_clone +#define ptregs_clone i386_clone #define ptregs_vm86 sys_vm86 #define ptregs_sigaltstack sys_sigaltstack #define ptregs_vfork sys_vfork diff --git a/arch/x86/um/syscalls_32.c b/arch/x86/um/syscalls_32.c index b853e8600b9..db444c7218f 100644 --- a/arch/x86/um/syscalls_32.c +++ b/arch/x86/um/syscalls_32.c @@ -3,37 +3,24 @@ * Licensed under the GPL */ -#include "linux/sched.h" -#include "linux/shm.h" -#include "linux/ipc.h" -#include "linux/syscalls.h" -#include "asm/mman.h" -#include "asm/uaccess.h" -#include "asm/unistd.h" +#include <linux/syscalls.h> +#include <sysdep/syscalls.h> /* * The prototype on i386 is: * - * int clone(int flags, void * child_stack, int * parent_tidptr, struct user_desc * newtls, int * child_tidptr) + * int clone(int flags, void * child_stack, int * parent_tidptr, struct user_desc * newtls * * and the "newtls" arg. on i386 is read by copy_thread directly from the * register saved on the stack. */ -long sys_clone(unsigned long clone_flags, unsigned long newsp, - int __user *parent_tid, void *newtls, int __user *child_tid) +long i386_clone(unsigned long clone_flags, unsigned long newsp, + int __user *parent_tid, void *newtls, int __user *child_tid) { - long ret; - - if (!newsp) - newsp = UPT_SP(¤t->thread.regs.regs); - - current->thread.forking = 1; - ret = do_fork(clone_flags, newsp, ¤t->thread.regs, 0, parent_tid, - child_tid); - current->thread.forking = 0; - return ret; + return sys_clone(clone_flags, newsp, parent_tid, child_tid); } + long sys_sigaction(int sig, const struct old_sigaction __user *act, struct old_sigaction __user *oact) { diff --git a/arch/x86/um/syscalls_64.c b/arch/x86/um/syscalls_64.c index f3d82bb6e15..adb08eb5c22 100644 --- a/arch/x86/um/syscalls_64.c +++ b/arch/x86/um/syscalls_64.c @@ -5,12 +5,9 @@ * Licensed under the GPL */ -#include "linux/linkage.h" -#include "linux/personality.h" -#include "linux/utsname.h" -#include "asm/prctl.h" /* XXX This should get the constants from libc */ -#include "asm/uaccess.h" -#include "os.h" +#include <linux/sched.h> +#include <asm/prctl.h> /* XXX This should get the constants from libc */ +#include <os.h> long arch_prctl(struct task_struct *task, int code, unsigned long __user *addr) { @@ -79,20 +76,6 @@ long sys_arch_prctl(int code, unsigned long addr) return arch_prctl(current, code, (unsigned long __user *) addr); } -long sys_clone(unsigned long clone_flags, unsigned long newsp, - void __user *parent_tid, void __user *child_tid) -{ - long ret; - - if (!newsp) - newsp = UPT_SP(¤t->thread.regs.regs); - current->thread.forking = 1; - ret = do_fork(clone_flags, newsp, ¤t->thread.regs, 0, parent_tid, - child_tid); - current->thread.forking = 0; - return ret; -} - void arch_switch_to(struct task_struct *to) { if ((to->thread.arch.fs == 0) || (to->mm == NULL)) diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 9642d4a3860..1fbe75a95f1 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -1452,6 +1452,10 @@ asmlinkage void __init xen_start_kernel(void) pci_request_acs(); xen_acpi_sleep_register(); + + /* Avoid searching for BIOS MP tables */ + x86_init.mpparse.find_smp_config = x86_init_noop; + x86_init.mpparse.get_smp_config = x86_init_uint_noop; } #ifdef CONFIG_PCI /* PCI BIOS service won't work from a PV guest. */ diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c index 76ba0e97e53..72213da605f 100644 --- a/arch/x86/xen/p2m.c +++ b/arch/x86/xen/p2m.c @@ -828,9 +828,6 @@ int m2p_add_override(unsigned long mfn, struct page *page, xen_mc_issue(PARAVIRT_LAZY_MMU); } - /* let's use dev_bus_addr to record the old mfn instead */ - kmap_op->dev_bus_addr = page->index; - page->index = (unsigned long) kmap_op; } spin_lock_irqsave(&m2p_override_lock, flags); list_add(&page->lru, &m2p_overrides[mfn_hash(mfn)]); @@ -857,7 +854,8 @@ int m2p_add_override(unsigned long mfn, struct page *page, return 0; } EXPORT_SYMBOL_GPL(m2p_add_override); -int m2p_remove_override(struct page *page, bool clear_pte) +int m2p_remove_override(struct page *page, + struct gnttab_map_grant_ref *kmap_op) { unsigned long flags; unsigned long mfn; @@ -887,10 +885,8 @@ int m2p_remove_override(struct page *page, bool clear_pte) WARN_ON(!PagePrivate(page)); ClearPagePrivate(page); - if (clear_pte) { - struct gnttab_map_grant_ref *map_op = - (struct gnttab_map_grant_ref *) page->index; - set_phys_to_machine(pfn, map_op->dev_bus_addr); + set_phys_to_machine(pfn, page->index); + if (kmap_op != NULL) { if (!PageHighMem(page)) { struct multicall_space mcs; struct gnttab_unmap_grant_ref *unmap_op; @@ -902,13 +898,13 @@ int m2p_remove_override(struct page *page, bool clear_pte) * issued. In this case handle is going to -1 because * it hasn't been modified yet. */ - if (map_op->handle == -1) + if (kmap_op->handle == -1) xen_mc_flush(); /* - * Now if map_op->handle is negative it means that the + * Now if kmap_op->handle is negative it means that the * hypercall actually returned an error. */ - if (map_op->handle == GNTST_general_error) { + if (kmap_op->handle == GNTST_general_error) { printk(KERN_WARNING "m2p_remove_override: " "pfn %lx mfn %lx, failed to modify kernel mappings", pfn, mfn); @@ -918,8 +914,8 @@ int m2p_remove_override(struct page *page, bool clear_pte) mcs = xen_mc_entry( sizeof(struct gnttab_unmap_grant_ref)); unmap_op = mcs.args; - unmap_op->host_addr = map_op->host_addr; - unmap_op->handle = map_op->handle; + unmap_op->host_addr = kmap_op->host_addr; + unmap_op->handle = kmap_op->handle; unmap_op->dev_bus_addr = 0; MULTI_grant_table_op(mcs.mc, @@ -930,10 +926,9 @@ int m2p_remove_override(struct page *page, bool clear_pte) set_pte_at(&init_mm, address, ptep, pfn_pte(pfn, PAGE_KERNEL)); __flush_tlb_single(address); - map_op->host_addr = 0; + kmap_op->host_addr = 0; } - } else - set_phys_to_machine(pfn, page->index); + } /* p2m(m2p(mfn)) == FOREIGN_FRAME(mfn): the mfn is already present * somewhere in this domain, even before being added to the diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index d11ca11d14f..e2d62d697b5 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -17,6 +17,7 @@ #include <asm/e820.h> #include <asm/setup.h> #include <asm/acpi.h> +#include <asm/numa.h> #include <asm/xen/hypervisor.h> #include <asm/xen/hypercall.h> @@ -544,4 +545,7 @@ void __init xen_arch_setup(void) disable_cpufreq(); WARN_ON(set_pm_idle_to_default()); fiddle_vdso(); +#ifdef CONFIG_NUMA + numa_off = 1; +#endif } diff --git a/block/blk-core.c b/block/blk-core.c index 4b4dbdfbca8..ee3cb3a5e27 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -2254,9 +2254,11 @@ bool blk_update_request(struct request *req, int error, unsigned int nr_bytes) error_type = "I/O"; break; } - printk(KERN_ERR "end_request: %s error, dev %s, sector %llu\n", - error_type, req->rq_disk ? req->rq_disk->disk_name : "?", - (unsigned long long)blk_rq_pos(req)); + printk_ratelimited(KERN_ERR "end_request: %s error, dev %s, sector %llu\n", + error_type, req->rq_disk ? + req->rq_disk->disk_name : "?", + (unsigned long long)blk_rq_pos(req)); + } blk_account_io_completion(req, nr_bytes); diff --git a/block/ioctl.c b/block/ioctl.c index 4476e0e85d1..4a85096f541 100644 --- a/block/ioctl.c +++ b/block/ioctl.c @@ -41,7 +41,7 @@ static int blkpg_ioctl(struct block_device *bdev, struct blkpg_ioctl_arg __user sizeof(long long) > sizeof(long)) { long pstart = start, plength = length; if (pstart != start || plength != length - || pstart < 0 || plength < 0) + || pstart < 0 || plength < 0 || partno > 65535) return -EINVAL; } diff --git a/drivers/block/aoe/aoecmd.c b/drivers/block/aoe/aoecmd.c index de0435e63b0..887f68f6d79 100644 --- a/drivers/block/aoe/aoecmd.c +++ b/drivers/block/aoe/aoecmd.c @@ -35,6 +35,7 @@ new_skb(ulong len) skb_reset_mac_header(skb); skb_reset_network_header(skb); skb->protocol = __constant_htons(ETH_P_AOE); + skb_checksum_none_assert(skb); } return skb; } diff --git a/drivers/block/cciss_scsi.c b/drivers/block/cciss_scsi.c index 38aa6dda6b8..da3311129a0 100644 --- a/drivers/block/cciss_scsi.c +++ b/drivers/block/cciss_scsi.c @@ -795,6 +795,7 @@ static void complete_scsi_command(CommandList_struct *c, int timeout, } break; case CMD_PROTOCOL_ERR: + cmd->result = DID_ERROR << 16; dev_warn(&h->pdev->dev, "%p has protocol error\n", c); break; diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c index a8fddeb3d63..f946d31d691 100644 --- a/drivers/block/mtip32xx/mtip32xx.c +++ b/drivers/block/mtip32xx/mtip32xx.c @@ -1148,11 +1148,15 @@ static bool mtip_pause_ncq(struct mtip_port *port, reply = port->rxfis + RX_FIS_D2H_REG; task_file_data = readl(port->mmio+PORT_TFDATA); - if ((task_file_data & 1) || (fis->command == ATA_CMD_SEC_ERASE_UNIT)) + if (fis->command == ATA_CMD_SEC_ERASE_UNIT) + clear_bit(MTIP_DDF_SEC_LOCK_BIT, &port->dd->dd_flag); + + if ((task_file_data & 1)) return false; if (fis->command == ATA_CMD_SEC_ERASE_PREP) { set_bit(MTIP_PF_SE_ACTIVE_BIT, &port->flags); + set_bit(MTIP_DDF_SEC_LOCK_BIT, &port->dd->dd_flag); port->ic_pause_timer = jiffies; return true; } else if ((fis->command == ATA_CMD_DOWNLOAD_MICRO) && @@ -1900,7 +1904,7 @@ static int exec_drive_command(struct mtip_port *port, u8 *command, int rv = 0, xfer_sz = command[3]; if (xfer_sz) { - if (user_buffer) + if (!user_buffer) return -EFAULT; buf = dmam_alloc_coherent(&port->dd->pdev->dev, @@ -2043,7 +2047,7 @@ static void mtip_set_timeout(struct host_to_dev_fis *fis, unsigned int *timeout) *timeout = 240000; /* 4 minutes */ break; case ATA_CMD_STANDBYNOW1: - *timeout = 10000; /* 10 seconds */ + *timeout = 120000; /* 2 minutes */ break; case 0xF7: case 0xFA: @@ -2588,9 +2592,6 @@ static ssize_t mtip_hw_read_registers(struct file *f, char __user *ubuf, if (!len || size) return 0; - if (size < 0) - return -EINVAL; - size += sprintf(&buf[size], "H/ S ACTive : [ 0x"); for (n = dd->slot_groups-1; n >= 0; n--) @@ -2660,9 +2661,6 @@ static ssize_t mtip_hw_read_flags(struct file *f, char __user *ubuf, if (!len || size) return 0; - if (size < 0) - return -EINVAL; - size += sprintf(&buf[size], "Flag-port : [ %08lX ]\n", dd->port->flags); size += sprintf(&buf[size], "Flag-dd : [ %08lX ]\n", @@ -3214,8 +3212,8 @@ static int mtip_hw_init(struct driver_data *dd) "Unable to check write protect progress\n"); else dev_info(&dd->pdev->dev, - "Write protect progress: %d%% (%d blocks)\n", - attr242.cur, attr242.data); + "Write protect progress: %u%% (%u blocks)\n", + attr242.cur, le32_to_cpu(attr242.data)); return rv; out3: @@ -3619,6 +3617,10 @@ static void mtip_make_request(struct request_queue *queue, struct bio *bio) bio_endio(bio, -ENODATA); return; } + if (unlikely(test_bit(MTIP_DDF_SEC_LOCK_BIT, &dd->dd_flag))) { + bio_endio(bio, -ENODATA); + return; + } } if (unlikely(!bio_has_data(bio))) { @@ -4168,7 +4170,13 @@ static void mtip_pci_shutdown(struct pci_dev *pdev) /* Table of device ids supported by this driver. */ static DEFINE_PCI_DEVICE_TABLE(mtip_pci_tbl) = { - { PCI_DEVICE(PCI_VENDOR_ID_MICRON, P320_DEVICE_ID) }, + { PCI_DEVICE(PCI_VENDOR_ID_MICRON, P320H_DEVICE_ID) }, + { PCI_DEVICE(PCI_VENDOR_ID_MICRON, P320M_DEVICE_ID) }, + { PCI_DEVICE(PCI_VENDOR_ID_MICRON, P320S_DEVICE_ID) }, + { PCI_DEVICE(PCI_VENDOR_ID_MICRON, P325M_DEVICE_ID) }, + { PCI_DEVICE(PCI_VENDOR_ID_MICRON, P420H_DEVICE_ID) }, + { PCI_DEVICE(PCI_VENDOR_ID_MICRON, P420M_DEVICE_ID) }, + { PCI_DEVICE(PCI_VENDOR_ID_MICRON, P425M_DEVICE_ID) }, { 0 } }; @@ -4199,12 +4207,12 @@ static int __init mtip_init(void) { int error; - printk(KERN_INFO MTIP_DRV_NAME " Version " MTIP_DRV_VERSION "\n"); + pr_info(MTIP_DRV_NAME " Version " MTIP_DRV_VERSION "\n"); /* Allocate a major block device number to use with this driver. */ error = register_blkdev(0, MTIP_DRV_NAME); if (error <= 0) { - printk(KERN_ERR "Unable to register block device (%d)\n", + pr_err("Unable to register block device (%d)\n", error); return -EBUSY; } @@ -4213,7 +4221,7 @@ static int __init mtip_init(void) if (!dfs_parent) { dfs_parent = debugfs_create_dir("rssd", NULL); if (IS_ERR_OR_NULL(dfs_parent)) { - printk(KERN_WARNING "Error creating debugfs parent\n"); + pr_warn("Error creating debugfs parent\n"); dfs_parent = NULL; } } diff --git a/drivers/block/mtip32xx/mtip32xx.h b/drivers/block/mtip32xx/mtip32xx.h index f51fc23d17b..18627a1d04c 100644 --- a/drivers/block/mtip32xx/mtip32xx.h +++ b/drivers/block/mtip32xx/mtip32xx.h @@ -76,7 +76,13 @@ /* Micron Vendor ID & P320x SSD Device ID */ #define PCI_VENDOR_ID_MICRON 0x1344 -#define P320_DEVICE_ID 0x5150 +#define P320H_DEVICE_ID 0x5150 +#define P320M_DEVICE_ID 0x5151 +#define P320S_DEVICE_ID 0x5152 +#define P325M_DEVICE_ID 0x5153 +#define P420H_DEVICE_ID 0x5160 +#define P420M_DEVICE_ID 0x5161 +#define P425M_DEVICE_ID 0x5163 /* Driver name and version strings */ #define MTIP_DRV_NAME "mtip32xx" @@ -131,10 +137,12 @@ enum { MTIP_PF_SVC_THD_STOP_BIT = 8, /* below are bit numbers in 'dd_flag' defined in driver_data */ + MTIP_DDF_SEC_LOCK_BIT = 0, MTIP_DDF_REMOVE_PENDING_BIT = 1, MTIP_DDF_OVER_TEMP_BIT = 2, MTIP_DDF_WRITE_PROTECT_BIT = 3, MTIP_DDF_STOP_IO = ((1 << MTIP_DDF_REMOVE_PENDING_BIT) | \ + (1 << MTIP_DDF_SEC_LOCK_BIT) | \ (1 << MTIP_DDF_OVER_TEMP_BIT) | \ (1 << MTIP_DDF_WRITE_PROTECT_BIT)), diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index d07c9f7fded..0c03411c59e 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -449,6 +449,14 @@ static void nbd_clear_que(struct nbd_device *nbd) req->errors++; nbd_end_request(req); } + + while (!list_empty(&nbd->waiting_queue)) { + req = list_entry(nbd->waiting_queue.next, struct request, + queuelist); + list_del_init(&req->queuelist); + req->errors++; + nbd_end_request(req); + } } @@ -598,6 +606,7 @@ static int __nbd_ioctl(struct block_device *bdev, struct nbd_device *nbd, nbd->file = NULL; nbd_clear_que(nbd); BUG_ON(!list_empty(&nbd->queue_head)); + BUG_ON(!list_empty(&nbd->waiting_queue)); if (file) fput(file); return 0; diff --git a/drivers/block/nvme.c b/drivers/block/nvme.c index 38a2d063188..ad16c68c864 100644 --- a/drivers/block/nvme.c +++ b/drivers/block/nvme.c @@ -79,6 +79,7 @@ struct nvme_dev { char serial[20]; char model[40]; char firmware_rev[8]; + u32 max_hw_sectors; }; /* @@ -835,15 +836,15 @@ static int nvme_identify(struct nvme_dev *dev, unsigned nsid, unsigned cns, } static int nvme_get_features(struct nvme_dev *dev, unsigned fid, - unsigned dword11, dma_addr_t dma_addr) + unsigned nsid, dma_addr_t dma_addr) { struct nvme_command c; memset(&c, 0, sizeof(c)); c.features.opcode = nvme_admin_get_features; + c.features.nsid = cpu_to_le32(nsid); c.features.prp1 = cpu_to_le64(dma_addr); c.features.fid = cpu_to_le32(fid); - c.features.dword11 = cpu_to_le32(dword11); return nvme_submit_admin_cmd(dev, &c, NULL); } @@ -862,11 +863,51 @@ static int nvme_set_features(struct nvme_dev *dev, unsigned fid, return nvme_submit_admin_cmd(dev, &c, result); } +/** + * nvme_cancel_ios - Cancel outstanding I/Os + * @queue: The queue to cancel I/Os on + * @timeout: True to only cancel I/Os which have timed out + */ +static void nvme_cancel_ios(struct nvme_queue *nvmeq, bool timeout) +{ + int depth = nvmeq->q_depth - 1; + struct nvme_cmd_info *info = nvme_cmd_info(nvmeq); + unsigned long now = jiffies; + int cmdid; + + for_each_set_bit(cmdid, nvmeq->cmdid_data, depth) { + void *ctx; + nvme_completion_fn fn; + static struct nvme_completion cqe = { + .status = cpu_to_le16(NVME_SC_ABORT_REQ) << 1, + }; + + if (timeout && !time_after(now, info[cmdid].timeout)) + continue; + dev_warn(nvmeq->q_dmadev, "Cancelling I/O %d\n", cmdid); + ctx = cancel_cmdid(nvmeq, cmdid, &fn); + fn(nvmeq->dev, ctx, &cqe); + } +} + +static void nvme_free_queue_mem(struct nvme_queue *nvmeq) +{ + dma_free_coherent(nvmeq->q_dmadev, CQ_SIZE(nvmeq->q_depth), + (void *)nvmeq->cqes, nvmeq->cq_dma_addr); + dma_free_coherent(nvmeq->q_dmadev, SQ_SIZE(nvmeq->q_depth), + nvmeq->sq_cmds, nvmeq->sq_dma_addr); + kfree(nvmeq); +} + static void nvme_free_queue(struct nvme_dev *dev, int qid) { struct nvme_queue *nvmeq = dev->queues[qid]; int vector = dev->entry[nvmeq->cq_vector].vector; + spin_lock_irq(&nvmeq->q_lock); + nvme_cancel_ios(nvmeq, false); + spin_unlock_irq(&nvmeq->q_lock); + irq_set_affinity_hint(vector, NULL); free_irq(vector, nvmeq); @@ -876,18 +917,15 @@ static void nvme_free_queue(struct nvme_dev *dev, int qid) adapter_delete_cq(dev, qid); } - dma_free_coherent(nvmeq->q_dmadev, CQ_SIZE(nvmeq->q_depth), - (void *)nvmeq->cqes, nvmeq->cq_dma_addr); - dma_free_coherent(nvmeq->q_dmadev, SQ_SIZE(nvmeq->q_depth), - nvmeq->sq_cmds, nvmeq->sq_dma_addr); - kfree(nvmeq); + nvme_free_queue_mem(nvmeq); } static struct nvme_queue *nvme_alloc_queue(struct nvme_dev *dev, int qid, int depth, int vector) { struct device *dmadev = &dev->pci_dev->dev; - unsigned extra = (depth / 8) + (depth * sizeof(struct nvme_cmd_info)); + unsigned extra = DIV_ROUND_UP(depth, 8) + (depth * + sizeof(struct nvme_cmd_info)); struct nvme_queue *nvmeq = kzalloc(sizeof(*nvmeq) + extra, GFP_KERNEL); if (!nvmeq) return NULL; @@ -975,7 +1013,7 @@ static __devinit struct nvme_queue *nvme_create_queue(struct nvme_dev *dev, static int __devinit nvme_configure_admin_queue(struct nvme_dev *dev) { - int result; + int result = 0; u32 aqa; u64 cap; unsigned long timeout; @@ -1005,17 +1043,22 @@ static int __devinit nvme_configure_admin_queue(struct nvme_dev *dev) timeout = ((NVME_CAP_TIMEOUT(cap) + 1) * HZ / 2) + jiffies; dev->db_stride = NVME_CAP_STRIDE(cap); - while (!(readl(&dev->bar->csts) & NVME_CSTS_RDY)) { + while (!result && !(readl(&dev->bar->csts) & NVME_CSTS_RDY)) { msleep(100); if (fatal_signal_pending(current)) - return -EINTR; + result = -EINTR; if (time_after(jiffies, timeout)) { dev_err(&dev->pci_dev->dev, "Device not ready; aborting initialisation\n"); - return -ENODEV; + result = -ENODEV; } } + if (result) { + nvme_free_queue_mem(nvmeq); + return result; + } + result = queue_request_irq(dev, nvmeq, "nvme admin"); dev->queues[0] = nvmeq; return result; @@ -1037,6 +1080,8 @@ static struct nvme_iod *nvme_map_user_pages(struct nvme_dev *dev, int write, offset = offset_in_page(addr); count = DIV_ROUND_UP(offset + length, PAGE_SIZE); pages = kcalloc(count, sizeof(*pages), GFP_KERNEL); + if (!pages) + return ERR_PTR(-ENOMEM); err = get_user_pages_fast(addr, count, 1, pages); if (err < count) { @@ -1146,14 +1191,13 @@ static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio) return status; } -static int nvme_user_admin_cmd(struct nvme_ns *ns, +static int nvme_user_admin_cmd(struct nvme_dev *dev, struct nvme_admin_cmd __user *ucmd) { - struct nvme_dev *dev = ns->dev; struct nvme_admin_cmd cmd; struct nvme_command c; int status, length; - struct nvme_iod *iod; + struct nvme_iod *uninitialized_var(iod); if (!capable(CAP_SYS_ADMIN)) return -EACCES; @@ -1204,7 +1248,7 @@ static int nvme_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, case NVME_IOCTL_ID: return ns->ns_id; case NVME_IOCTL_ADMIN_CMD: - return nvme_user_admin_cmd(ns, (void __user *)arg); + return nvme_user_admin_cmd(ns->dev, (void __user *)arg); case NVME_IOCTL_SUBMIT_IO: return nvme_submit_io(ns, (void __user *)arg); default: @@ -1218,26 +1262,6 @@ static const struct block_device_operations nvme_fops = { .compat_ioctl = nvme_ioctl, }; -static void nvme_timeout_ios(struct nvme_queue *nvmeq) -{ - int depth = nvmeq->q_depth - 1; - struct nvme_cmd_info *info = nvme_cmd_info(nvmeq); - unsigned long now = jiffies; - int cmdid; - - for_each_set_bit(cmdid, nvmeq->cmdid_data, depth) { - void *ctx; - nvme_completion_fn fn; - static struct nvme_completion cqe = { .status = cpu_to_le16(NVME_SC_ABORT_REQ) << 1, }; - - if (!time_after(now, info[cmdid].timeout)) - continue; - dev_warn(nvmeq->q_dmadev, "Timing out I/O %d\n", cmdid); - ctx = cancel_cmdid(nvmeq, cmdid, &fn); - fn(nvmeq->dev, ctx, &cqe); - } -} - static void nvme_resubmit_bios(struct nvme_queue *nvmeq) { while (bio_list_peek(&nvmeq->sq_cong)) { @@ -1269,7 +1293,7 @@ static int nvme_kthread(void *data) spin_lock_irq(&nvmeq->q_lock); if (nvme_process_cq(nvmeq)) printk("process_cq did something\n"); - nvme_timeout_ios(nvmeq); + nvme_cancel_ios(nvmeq, true); nvme_resubmit_bios(nvmeq); spin_unlock_irq(&nvmeq->q_lock); } @@ -1339,6 +1363,9 @@ static struct nvme_ns *nvme_alloc_ns(struct nvme_dev *dev, int nsid, ns->disk = disk; lbaf = id->flbas & 0xf; ns->lba_shift = id->lbaf[lbaf].ds; + blk_queue_logical_block_size(ns->queue, 1 << ns->lba_shift); + if (dev->max_hw_sectors) + blk_queue_max_hw_sectors(ns->queue, dev->max_hw_sectors); disk->major = nvme_major; disk->minors = NVME_MINORS; @@ -1383,7 +1410,7 @@ static int set_queue_count(struct nvme_dev *dev, int count) static int __devinit nvme_setup_io_queues(struct nvme_dev *dev) { - int result, cpu, i, nr_io_queues, db_bar_size; + int result, cpu, i, nr_io_queues, db_bar_size, q_depth; nr_io_queues = num_online_cpus(); result = set_queue_count(dev, nr_io_queues); @@ -1429,9 +1456,10 @@ static int __devinit nvme_setup_io_queues(struct nvme_dev *dev) cpu = cpumask_next(cpu, cpu_online_mask); } + q_depth = min_t(int, NVME_CAP_MQES(readq(&dev->bar->cap)) + 1, + NVME_Q_DEPTH); for (i = 0; i < nr_io_queues; i++) { - dev->queues[i + 1] = nvme_create_queue(dev, i + 1, - NVME_Q_DEPTH, i); + dev->queues[i + 1] = nvme_create_queue(dev, i + 1, q_depth, i); if (IS_ERR(dev->queues[i + 1])) return PTR_ERR(dev->queues[i + 1]); dev->queue_count++; @@ -1480,6 +1508,10 @@ static int __devinit nvme_dev_add(struct nvme_dev *dev) memcpy(dev->serial, ctrl->sn, sizeof(ctrl->sn)); memcpy(dev->model, ctrl->mn, sizeof(ctrl->mn)); memcpy(dev->firmware_rev, ctrl->fr, sizeof(ctrl->fr)); + if (ctrl->mdts) { + int shift = NVME_CAP_MPSMIN(readq(&dev->bar->cap)) + 12; + dev->max_hw_sectors = 1 << (ctrl->mdts + shift - 9); + } id_ns = mem; for (i = 1; i <= nn; i++) { @@ -1523,8 +1555,6 @@ static int nvme_dev_remove(struct nvme_dev *dev) list_del(&dev->node); spin_unlock(&dev_list_lock); - /* TODO: wait all I/O finished or cancel them */ - list_for_each_entry_safe(ns, next, &dev->namespaces, list) { list_del(&ns->list); del_gendisk(ns->disk); @@ -1560,15 +1590,33 @@ static void nvme_release_prp_pools(struct nvme_dev *dev) dma_pool_destroy(dev->prp_small_pool); } -/* XXX: Use an ida or something to let remove / add work correctly */ -static void nvme_set_instance(struct nvme_dev *dev) +static DEFINE_IDA(nvme_instance_ida); + +static int nvme_set_instance(struct nvme_dev *dev) { - static int instance; - dev->instance = instance++; + int instance, error; + + do { + if (!ida_pre_get(&nvme_instance_ida, GFP_KERNEL)) + return -ENODEV; + + spin_lock(&dev_list_lock); + error = ida_get_new(&nvme_instance_ida, &instance); + spin_unlock(&dev_list_lock); + } while (error == -EAGAIN); + + if (error) + return -ENODEV; + + dev->instance = instance; + return 0; } static void nvme_release_instance(struct nvme_dev *dev) { + spin_lock(&dev_list_lock); + ida_remove(&nvme_instance_ida, dev->instance); + spin_unlock(&dev_list_lock); } static int __devinit nvme_probe(struct pci_dev *pdev, @@ -1601,7 +1649,10 @@ static int __devinit nvme_probe(struct pci_dev *pdev, pci_set_drvdata(pdev, dev); dma_set_mask(&pdev->dev, DMA_BIT_MASK(64)); dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(64)); - nvme_set_instance(dev); + result = nvme_set_instance(dev); + if (result) + goto disable; + dev->entry[0].vector = pdev->irq; result = nvme_setup_prp_pools(dev); @@ -1704,15 +1755,17 @@ static struct pci_driver nvme_driver = { static int __init nvme_init(void) { - int result = -EBUSY; + int result; nvme_thread = kthread_run(nvme_kthread, NULL, "nvme"); if (IS_ERR(nvme_thread)) return PTR_ERR(nvme_thread); - nvme_major = register_blkdev(nvme_major, "nvme"); - if (nvme_major <= 0) + result = register_blkdev(nvme_major, "nvme"); + if (result < 0) goto kill_kthread; + else if (result > 0) + nvme_major = result; result = pci_register_driver(&nvme_driver); if (result) diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index 9917943a357..54a55f03115 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -246,13 +246,12 @@ static int rbd_open(struct block_device *bdev, fmode_t mode) { struct rbd_device *rbd_dev = bdev->bd_disk->private_data; - rbd_get_dev(rbd_dev); - - set_device_ro(bdev, rbd_dev->read_only); - if ((mode & FMODE_WRITE) && rbd_dev->read_only) return -EROFS; + rbd_get_dev(rbd_dev); + set_device_ro(bdev, rbd_dev->read_only); + return 0; } diff --git a/drivers/block/xen-blkback/blkback.c b/drivers/block/xen-blkback/blkback.c index 73f196ca713..c6decb901e5 100644 --- a/drivers/block/xen-blkback/blkback.c +++ b/drivers/block/xen-blkback/blkback.c @@ -337,7 +337,7 @@ static void xen_blkbk_unmap(struct pending_req *req) invcount++; } - ret = gnttab_unmap_refs(unmap, pages, invcount, false); + ret = gnttab_unmap_refs(unmap, NULL, pages, invcount); BUG_ON(ret); } diff --git a/drivers/clk/Makefile b/drivers/clk/Makefile index 5869ea38705..72ce247a0e8 100644 --- a/drivers/clk/Makefile +++ b/drivers/clk/Makefile @@ -1,4 +1,5 @@ # common clock types +obj-$(CONFIG_HAVE_CLK) += clk-devres.o obj-$(CONFIG_CLKDEV_LOOKUP) += clkdev.o obj-$(CONFIG_COMMON_CLK) += clk.o clk-fixed-rate.o clk-gate.o \ clk-mux.o clk-divider.o clk-fixed-factor.o diff --git a/drivers/clk/clk-devres.c b/drivers/clk/clk-devres.c new file mode 100644 index 00000000000..8f571548870 --- /dev/null +++ b/drivers/clk/clk-devres.c @@ -0,0 +1,55 @@ +/* + * 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. + */ + +#include <linux/clk.h> +#include <linux/device.h> +#include <linux/export.h> +#include <linux/gfp.h> + +static void devm_clk_release(struct device *dev, void *res) +{ + clk_put(*(struct clk **)res); +} + +struct clk *devm_clk_get(struct device *dev, const char *id) +{ + struct clk **ptr, *clk; + + ptr = devres_alloc(devm_clk_release, sizeof(*ptr), GFP_KERNEL); + if (!ptr) + return ERR_PTR(-ENOMEM); + + clk = clk_get(dev, id); + if (!IS_ERR(clk)) { + *ptr = clk; + devres_add(dev, ptr); + } else { + devres_free(ptr); + } + + return clk; +} +EXPORT_SYMBOL(devm_clk_get); + +static int devm_clk_match(struct device *dev, void *res, void *data) +{ + struct clk **c = res; + if (!c || !*c) { + WARN_ON(!c || !*c); + return 0; + } + return *c == data; +} + +void devm_clk_put(struct device *dev, struct clk *clk) +{ + int ret; + + ret = devres_release(dev, devm_clk_release, devm_clk_match, clk); + + WARN_ON(ret); +} +EXPORT_SYMBOL(devm_clk_put); diff --git a/drivers/clk/clkdev.c b/drivers/clk/clkdev.c index d423c9bdd71..442a3136387 100644 --- a/drivers/clk/clkdev.c +++ b/drivers/clk/clkdev.c @@ -171,51 +171,6 @@ void clk_put(struct clk *clk) } EXPORT_SYMBOL(clk_put); -static void devm_clk_release(struct device *dev, void *res) -{ - clk_put(*(struct clk **)res); -} - -struct clk *devm_clk_get(struct device *dev, const char *id) -{ - struct clk **ptr, *clk; - - ptr = devres_alloc(devm_clk_release, sizeof(*ptr), GFP_KERNEL); - if (!ptr) - return ERR_PTR(-ENOMEM); - - clk = clk_get(dev, id); - if (!IS_ERR(clk)) { - *ptr = clk; - devres_add(dev, ptr); - } else { - devres_free(ptr); - } - - return clk; -} -EXPORT_SYMBOL(devm_clk_get); - -static int devm_clk_match(struct device *dev, void *res, void *data) -{ - struct clk **c = res; - if (!c || !*c) { - WARN_ON(!c || !*c); - return 0; - } - return *c == data; -} - -void devm_clk_put(struct device *dev, struct clk *clk) -{ - int ret; - - ret = devres_destroy(dev, devm_clk_release, devm_clk_match, clk); - - WARN_ON(ret); -} -EXPORT_SYMBOL(devm_clk_put); - void clkdev_add(struct clk_lookup *cl) { mutex_lock(&clocks_mutex); diff --git a/drivers/cpufreq/powernow-k8.c b/drivers/cpufreq/powernow-k8.c index c0e816468e3..1a40935c85f 100644 --- a/drivers/cpufreq/powernow-k8.c +++ b/drivers/cpufreq/powernow-k8.c @@ -35,7 +35,6 @@ #include <linux/slab.h> #include <linux/string.h> #include <linux/cpumask.h> -#include <linux/sched.h> /* for current / set_cpus_allowed() */ #include <linux/io.h> #include <linux/delay.h> @@ -1139,16 +1138,23 @@ static int transition_frequency_pstate(struct powernow_k8_data *data, return res; } -/* Driver entry point to switch to the target frequency */ -static int powernowk8_target(struct cpufreq_policy *pol, - unsigned targfreq, unsigned relation) +struct powernowk8_target_arg { + struct cpufreq_policy *pol; + unsigned targfreq; + unsigned relation; +}; + +static long powernowk8_target_fn(void *arg) { - cpumask_var_t oldmask; + struct powernowk8_target_arg *pta = arg; + struct cpufreq_policy *pol = pta->pol; + unsigned targfreq = pta->targfreq; + unsigned relation = pta->relation; struct powernow_k8_data *data = per_cpu(powernow_data, pol->cpu); u32 checkfid; u32 checkvid; unsigned int newstate; - int ret = -EIO; + int ret; if (!data) return -EINVAL; @@ -1156,29 +1162,16 @@ static int powernowk8_target(struct cpufreq_policy *pol, checkfid = data->currfid; checkvid = data->currvid; - /* only run on specific CPU from here on. */ - /* This is poor form: use a workqueue or smp_call_function_single */ - if (!alloc_cpumask_var(&oldmask, GFP_KERNEL)) - return -ENOMEM; - - cpumask_copy(oldmask, tsk_cpus_allowed(current)); - set_cpus_allowed_ptr(current, cpumask_of(pol->cpu)); - - if (smp_processor_id() != pol->cpu) { - printk(KERN_ERR PFX "limiting to cpu %u failed\n", pol->cpu); - goto err_out; - } - if (pending_bit_stuck()) { printk(KERN_ERR PFX "failing targ, change pending bit set\n"); - goto err_out; + return -EIO; } pr_debug("targ: cpu %d, %d kHz, min %d, max %d, relation %d\n", pol->cpu, targfreq, pol->min, pol->max, relation); if (query_current_values_with_pending_wait(data)) - goto err_out; + return -EIO; if (cpu_family != CPU_HW_PSTATE) { pr_debug("targ: curr fid 0x%x, vid 0x%x\n", @@ -1196,7 +1189,7 @@ static int powernowk8_target(struct cpufreq_policy *pol, if (cpufreq_frequency_table_target(pol, data->powernow_table, targfreq, relation, &newstate)) - goto err_out; + return -EIO; mutex_lock(&fidvid_mutex); @@ -1209,9 +1202,8 @@ static int powernowk8_target(struct cpufreq_policy *pol, ret = transition_frequency_fidvid(data, newstate); if (ret) { printk(KERN_ERR PFX "transition frequency failed\n"); - ret = 1; mutex_unlock(&fidvid_mutex); - goto err_out; + return 1; } mutex_unlock(&fidvid_mutex); @@ -1220,12 +1212,25 @@ static int powernowk8_target(struct cpufreq_policy *pol, data->powernow_table[newstate].index); else pol->cur = find_khz_freq_from_fid(data->currfid); - ret = 0; -err_out: - set_cpus_allowed_ptr(current, oldmask); - free_cpumask_var(oldmask); - return ret; + return 0; +} + +/* Driver entry point to switch to the target frequency */ +static int powernowk8_target(struct cpufreq_policy *pol, + unsigned targfreq, unsigned relation) +{ + struct powernowk8_target_arg pta = { .pol = pol, .targfreq = targfreq, + .relation = relation }; + + /* + * Must run on @pol->cpu. cpufreq core is responsible for ensuring + * that we're bound to the current CPU and pol->cpu stays online. + */ + if (smp_processor_id() == pol->cpu) + return powernowk8_target_fn(&pta); + else + return work_on_cpu(pol->cpu, powernowk8_target_fn, &pta); } /* Driver entry point to verify the policy and range of frequencies */ diff --git a/drivers/dma/at_hdmac.c b/drivers/dma/at_hdmac.c index 3934fcc4e00..7ab6e26664a 100644 --- a/drivers/dma/at_hdmac.c +++ b/drivers/dma/at_hdmac.c @@ -661,7 +661,7 @@ atc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl, flags); if (unlikely(!atslave || !sg_len)) { - dev_dbg(chan2dev(chan), "prep_dma_memcpy: length is zero!\n"); + dev_dbg(chan2dev(chan), "prep_slave_sg: sg length is zero!\n"); return NULL; } @@ -689,6 +689,11 @@ atc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl, mem = sg_dma_address(sg); len = sg_dma_len(sg); + if (unlikely(!len)) { + dev_dbg(chan2dev(chan), + "prep_slave_sg: sg(%d) data length is zero\n", i); + goto err; + } mem_width = 2; if (unlikely(mem & 3 || len & 3)) mem_width = 0; @@ -724,6 +729,11 @@ atc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl, mem = sg_dma_address(sg); len = sg_dma_len(sg); + if (unlikely(!len)) { + dev_dbg(chan2dev(chan), + "prep_slave_sg: sg(%d) data length is zero\n", i); + goto err; + } mem_width = 2; if (unlikely(mem & 3 || len & 3)) mem_width = 0; @@ -757,6 +767,7 @@ atc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl, err_desc_get: dev_err(chan2dev(chan), "not enough descriptors available\n"); +err: atc_desc_put(atchan, first); return NULL; } diff --git a/drivers/dma/pl330.c b/drivers/dma/pl330.c index e4feba6b03c..f5843bc80ba 100644 --- a/drivers/dma/pl330.c +++ b/drivers/dma/pl330.c @@ -1567,17 +1567,19 @@ static int pl330_submit_req(void *ch_id, struct pl330_req *r) goto xfer_exit; } - /* Prefer Secure Channel */ - if (!_manager_ns(thrd)) - r->cfg->nonsecure = 0; - else - r->cfg->nonsecure = 1; /* Use last settings, if not provided */ - if (r->cfg) + if (r->cfg) { + /* Prefer Secure Channel */ + if (!_manager_ns(thrd)) + r->cfg->nonsecure = 0; + else + r->cfg->nonsecure = 1; + ccr = _prepare_ccr(r->cfg); - else + } else { ccr = readl(regs + CC(thrd->id)); + } /* If this req doesn't have valid xfer settings */ if (!_is_valid(ccr)) { @@ -2928,6 +2930,11 @@ pl330_probe(struct amba_device *adev, const struct amba_id *id) num_chan = max_t(int, pi->pcfg.num_peri, pi->pcfg.num_chan); pdmac->peripherals = kzalloc(num_chan * sizeof(*pch), GFP_KERNEL); + if (!pdmac->peripherals) { + ret = -ENOMEM; + dev_err(&adev->dev, "unable to allocate pdmac->peripherals\n"); + goto probe_err5; + } for (i = 0; i < num_chan; i++) { pch = &pdmac->peripherals[i]; diff --git a/drivers/edac/edac_mc.c b/drivers/edac/edac_mc.c index 616d90bcb3a..d5dc9da7f99 100644 --- a/drivers/edac/edac_mc.c +++ b/drivers/edac/edac_mc.c @@ -199,6 +199,36 @@ void *edac_align_ptr(void **p, unsigned size, int n_elems) return (void *)(((unsigned long)ptr) + align - r); } +static void _edac_mc_free(struct mem_ctl_info *mci) +{ + int i, chn, row; + struct csrow_info *csr; + const unsigned int tot_dimms = mci->tot_dimms; + const unsigned int tot_channels = mci->num_cschannel; + const unsigned int tot_csrows = mci->nr_csrows; + + if (mci->dimms) { + for (i = 0; i < tot_dimms; i++) + kfree(mci->dimms[i]); + kfree(mci->dimms); + } + if (mci->csrows) { + for (row = 0; row < tot_csrows; row++) { + csr = mci->csrows[row]; + if (csr) { + if (csr->channels) { + for (chn = 0; chn < tot_channels; chn++) + kfree(csr->channels[chn]); + kfree(csr->channels); + } + kfree(csr); + } + } + kfree(mci->csrows); + } + kfree(mci); +} + /** * edac_mc_alloc: Allocate and partially fill a struct mem_ctl_info structure * @mc_num: Memory controller number @@ -413,24 +443,7 @@ struct mem_ctl_info *edac_mc_alloc(unsigned mc_num, return mci; error: - if (mci->dimms) { - for (i = 0; i < tot_dimms; i++) - kfree(mci->dimms[i]); - kfree(mci->dimms); - } - if (mci->csrows) { - for (chn = 0; chn < tot_channels; chn++) { - csr = mci->csrows[chn]; - if (csr) { - for (chn = 0; chn < tot_channels; chn++) - kfree(csr->channels[chn]); - kfree(csr); - } - kfree(mci->csrows[i]); - } - kfree(mci->csrows); - } - kfree(mci); + _edac_mc_free(mci); return NULL; } @@ -445,6 +458,14 @@ void edac_mc_free(struct mem_ctl_info *mci) { edac_dbg(1, "\n"); + /* If we're not yet registered with sysfs free only what was allocated + * in edac_mc_alloc(). + */ + if (!device_is_registered(&mci->dev)) { + _edac_mc_free(mci); + return; + } + /* the mci instance is freed here, when the sysfs object is dropped */ edac_unregister_sysfs(mci); } diff --git a/drivers/edac/i3200_edac.c b/drivers/edac/i3200_edac.c index 47180a08eda..b6653a6fc5d 100644 --- a/drivers/edac/i3200_edac.c +++ b/drivers/edac/i3200_edac.c @@ -391,7 +391,7 @@ static int i3200_probe1(struct pci_dev *pdev, int dev_idx) for (j = 0; j < nr_channels; j++) { struct dimm_info *dimm = csrow->channels[j]->dimm; - dimm->nr_pages = nr_pages / nr_channels; + dimm->nr_pages = nr_pages; dimm->grain = nr_pages << PAGE_SHIFT; dimm->mtype = MEM_DDR2; dimm->dtype = DEV_UNKNOWN; diff --git a/drivers/edac/i5000_edac.c b/drivers/edac/i5000_edac.c index 39c63757c2a..6a49dd00b81 100644 --- a/drivers/edac/i5000_edac.c +++ b/drivers/edac/i5000_edac.c @@ -1012,6 +1012,10 @@ static void handle_channel(struct i5000_pvt *pvt, int slot, int channel, /* add the number of COLUMN bits */ addrBits += MTR_DIMM_COLS_ADDR_BITS(mtr); + /* Dual-rank memories have twice the size */ + if (dinfo->dual_rank) + addrBits++; + addrBits += 6; /* add 64 bits per DIMM */ addrBits -= 20; /* divide by 2^^20 */ addrBits -= 3; /* 8 bits per bytes */ diff --git a/drivers/edac/sb_edac.c b/drivers/edac/sb_edac.c index f3b1f9fafa4..5715b7c2c51 100644 --- a/drivers/edac/sb_edac.c +++ b/drivers/edac/sb_edac.c @@ -513,7 +513,8 @@ static int get_dimm_config(struct mem_ctl_info *mci) { struct sbridge_pvt *pvt = mci->pvt_info; struct dimm_info *dimm; - int i, j, banks, ranks, rows, cols, size, npages; + unsigned i, j, banks, ranks, rows, cols, npages; + u64 size; u32 reg; enum edac_type mode; enum mem_type mtype; @@ -585,10 +586,10 @@ static int get_dimm_config(struct mem_ctl_info *mci) cols = numcol(mtr); /* DDR3 has 8 I/O banks */ - size = (rows * cols * banks * ranks) >> (20 - 3); + size = ((u64)rows * cols * banks * ranks) >> (20 - 3); npages = MiB_TO_PAGES(size); - edac_dbg(0, "mc#%d: channel %d, dimm %d, %d Mb (%d pages) bank: %d, rank: %d, row: %#x, col: %#x\n", + edac_dbg(0, "mc#%d: channel %d, dimm %d, %Ld Mb (%d pages) bank: %d, rank: %d, row: %#x, col: %#x\n", pvt->sbridge_dev->mc, i, j, size, npages, banks, ranks, rows, cols); diff --git a/drivers/gpio/gpio-lpc32xx.c b/drivers/gpio/gpio-lpc32xx.c index 8a420f13905..ed94b4ea72e 100644 --- a/drivers/gpio/gpio-lpc32xx.c +++ b/drivers/gpio/gpio-lpc32xx.c @@ -308,6 +308,7 @@ static int lpc32xx_gpio_dir_output_p012(struct gpio_chip *chip, unsigned pin, { struct lpc32xx_gpio_chip *group = to_lpc32xx_gpio(chip); + __set_gpio_level_p012(group, pin, value); __set_gpio_dir_p012(group, pin, 0); return 0; @@ -318,6 +319,7 @@ static int lpc32xx_gpio_dir_output_p3(struct gpio_chip *chip, unsigned pin, { struct lpc32xx_gpio_chip *group = to_lpc32xx_gpio(chip); + __set_gpio_level_p3(group, pin, value); __set_gpio_dir_p3(group, pin, 0); return 0; @@ -326,6 +328,9 @@ static int lpc32xx_gpio_dir_output_p3(struct gpio_chip *chip, unsigned pin, static int lpc32xx_gpio_dir_out_always(struct gpio_chip *chip, unsigned pin, int value) { + struct lpc32xx_gpio_chip *group = to_lpc32xx_gpio(chip); + + __set_gpo_level_p3(group, pin, value); return 0; } diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index 489e2b162b2..274d25de521 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -3242,7 +3242,8 @@ i915_gem_object_pin(struct drm_i915_gem_object *obj, { int ret; - BUG_ON(obj->pin_count == DRM_I915_GEM_OBJECT_MAX_PIN_COUNT); + if (WARN_ON(obj->pin_count == DRM_I915_GEM_OBJECT_MAX_PIN_COUNT)) + return -EBUSY; if (obj->gtt_space != NULL) { if ((alignment && obj->gtt_offset & (alignment - 1)) || diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index bc2ad348e5d..c040aee1341 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -4191,12 +4191,6 @@ static void i8xx_update_pll(struct drm_crtc *crtc, POSTING_READ(DPLL(pipe)); udelay(150); - I915_WRITE(DPLL(pipe), dpll); - - /* Wait for the clocks to stabilize. */ - POSTING_READ(DPLL(pipe)); - udelay(150); - /* The LVDS pin pair needs to be on before the DPLLs are enabled. * This is an exception to the general rule that mode_set doesn't turn * things on. @@ -4204,6 +4198,12 @@ static void i8xx_update_pll(struct drm_crtc *crtc, if (intel_pipe_has_type(crtc, INTEL_OUTPUT_LVDS)) intel_update_lvds(crtc, clock, adjusted_mode); + I915_WRITE(DPLL(pipe), dpll); + + /* Wait for the clocks to stabilize. */ + POSTING_READ(DPLL(pipe)); + udelay(150); + /* The pixel multiplier can only be updated once the * DPLL is enabled and the clocks are stable. * diff --git a/drivers/gpu/drm/i915/intel_hdmi.c b/drivers/gpu/drm/i915/intel_hdmi.c index 98f602427eb..12dc3308ab8 100644 --- a/drivers/gpu/drm/i915/intel_hdmi.c +++ b/drivers/gpu/drm/i915/intel_hdmi.c @@ -609,7 +609,7 @@ static void intel_hdmi_dpms(struct drm_encoder *encoder, int mode) u32 temp; u32 enable_bits = SDVO_ENABLE; - if (intel_hdmi->has_audio) + if (intel_hdmi->has_audio || mode != DRM_MODE_DPMS_ON) enable_bits |= SDVO_AUDIO_ENABLE; temp = I915_READ(intel_hdmi->sdvox_reg); diff --git a/drivers/gpu/drm/nouveau/nouveau_abi16.c b/drivers/gpu/drm/nouveau/nouveau_abi16.c index ff23d88880e..3ca240b4413 100644 --- a/drivers/gpu/drm/nouveau/nouveau_abi16.c +++ b/drivers/gpu/drm/nouveau/nouveau_abi16.c @@ -179,7 +179,7 @@ nouveau_abi16_ioctl_grobj_alloc(ABI16_IOCTL_ARGS) return 0; } else if (init->class == 0x906e) { - NV_ERROR(dev, "906e not supported yet\n"); + NV_DEBUG(dev, "906e not supported yet\n"); return -EINVAL; } diff --git a/drivers/gpu/drm/nouveau/nv50_gpio.c b/drivers/gpu/drm/nouveau/nv50_gpio.c index f0349053489..c399d510b27 100644 --- a/drivers/gpu/drm/nouveau/nv50_gpio.c +++ b/drivers/gpu/drm/nouveau/nv50_gpio.c @@ -22,6 +22,7 @@ * Authors: Ben Skeggs */ +#include <linux/dmi.h> #include "drmP.h" #include "nouveau_drv.h" #include "nouveau_hw.h" @@ -110,13 +111,25 @@ nv50_gpio_isr(struct drm_device *dev) nv_wr32(dev, 0xe074, intr1); } +static struct dmi_system_id gpio_reset_ids[] = { + { + .ident = "Apple Macbook 10,1", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Apple Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "MacBookPro10,1"), + } + }, + { } +}; + int nv50_gpio_init(struct drm_device *dev) { struct drm_nouveau_private *dev_priv = dev->dev_private; /* initialise gpios and routing to vbios defaults */ - nouveau_gpio_reset(dev); + if (dmi_check_system(gpio_reset_ids)) + nouveau_gpio_reset(dev); /* disable, and ack any pending gpio interrupts */ nv_wr32(dev, 0xe050, 0x00000000); diff --git a/drivers/gpu/drm/nouveau/nvc0_fb.c b/drivers/gpu/drm/nouveau/nvc0_fb.c index f704e942372..f376c39310d 100644 --- a/drivers/gpu/drm/nouveau/nvc0_fb.c +++ b/drivers/gpu/drm/nouveau/nvc0_fb.c @@ -124,6 +124,7 @@ nvc0_fb_init(struct drm_device *dev) priv = dev_priv->engine.fb.priv; nv_wr32(dev, 0x100c10, priv->r100c10 >> 8); + nv_mask(dev, 0x17e820, 0x00100000, 0x00000000); /* NV_PLTCG_INTR_EN */ return 0; } diff --git a/drivers/gpu/drm/nouveau/nvc0_fifo.c b/drivers/gpu/drm/nouveau/nvc0_fifo.c index 7d85553d518..cd39eb99f5b 100644 --- a/drivers/gpu/drm/nouveau/nvc0_fifo.c +++ b/drivers/gpu/drm/nouveau/nvc0_fifo.c @@ -373,7 +373,8 @@ nvc0_fifo_isr_subfifo_intr(struct drm_device *dev, int unit) static void nvc0_fifo_isr(struct drm_device *dev) { - u32 stat = nv_rd32(dev, 0x002100); + u32 mask = nv_rd32(dev, 0x002140); + u32 stat = nv_rd32(dev, 0x002100) & mask; if (stat & 0x00000100) { NV_INFO(dev, "PFIFO: unknown status 0x00000100\n"); diff --git a/drivers/gpu/drm/nouveau/nve0_fifo.c b/drivers/gpu/drm/nouveau/nve0_fifo.c index e98d144e6eb..281bece751b 100644 --- a/drivers/gpu/drm/nouveau/nve0_fifo.c +++ b/drivers/gpu/drm/nouveau/nve0_fifo.c @@ -345,7 +345,8 @@ nve0_fifo_isr_subfifo_intr(struct drm_device *dev, int unit) static void nve0_fifo_isr(struct drm_device *dev) { - u32 stat = nv_rd32(dev, 0x002100); + u32 mask = nv_rd32(dev, 0x002140); + u32 stat = nv_rd32(dev, 0x002100) & mask; if (stat & 0x00000100) { NV_INFO(dev, "PFIFO: unknown status 0x00000100\n"); diff --git a/drivers/gpu/drm/radeon/atombios_crtc.c b/drivers/gpu/drm/radeon/atombios_crtc.c index e721e3087b9..2817101fb16 100644 --- a/drivers/gpu/drm/radeon/atombios_crtc.c +++ b/drivers/gpu/drm/radeon/atombios_crtc.c @@ -1479,98 +1479,14 @@ static void radeon_legacy_atom_fixup(struct drm_crtc *crtc) } } -/** - * radeon_get_pll_use_mask - look up a mask of which pplls are in use - * - * @crtc: drm crtc - * - * Returns the mask of which PPLLs (Pixel PLLs) are in use. - */ -static u32 radeon_get_pll_use_mask(struct drm_crtc *crtc) -{ - struct drm_device *dev = crtc->dev; - struct drm_crtc *test_crtc; - struct radeon_crtc *radeon_test_crtc; - u32 pll_in_use = 0; - - list_for_each_entry(test_crtc, &dev->mode_config.crtc_list, head) { - if (crtc == test_crtc) - continue; - - radeon_test_crtc = to_radeon_crtc(test_crtc); - if (radeon_test_crtc->pll_id != ATOM_PPLL_INVALID) - pll_in_use |= (1 << radeon_test_crtc->pll_id); - } - return pll_in_use; -} - -/** - * radeon_get_shared_dp_ppll - return the PPLL used by another crtc for DP - * - * @crtc: drm crtc - * - * Returns the PPLL (Pixel PLL) used by another crtc/encoder which is - * also in DP mode. For DP, a single PPLL can be used for all DP - * crtcs/encoders. - */ -static int radeon_get_shared_dp_ppll(struct drm_crtc *crtc) -{ - struct drm_device *dev = crtc->dev; - struct drm_encoder *test_encoder; - struct radeon_crtc *radeon_test_crtc; - - list_for_each_entry(test_encoder, &dev->mode_config.encoder_list, head) { - if (test_encoder->crtc && (test_encoder->crtc != crtc)) { - if (ENCODER_MODE_IS_DP(atombios_get_encoder_mode(test_encoder))) { - /* for DP use the same PLL for all */ - radeon_test_crtc = to_radeon_crtc(test_encoder->crtc); - if (radeon_test_crtc->pll_id != ATOM_PPLL_INVALID) - return radeon_test_crtc->pll_id; - } - } - } - return ATOM_PPLL_INVALID; -} - -/** - * radeon_atom_pick_pll - Allocate a PPLL for use by the crtc. - * - * @crtc: drm crtc - * - * Returns the PPLL (Pixel PLL) to be used by the crtc. For DP monitors - * a single PPLL can be used for all DP crtcs/encoders. For non-DP - * monitors a dedicated PPLL must be used. If a particular board has - * an external DP PLL, return ATOM_PPLL_INVALID to skip PLL programming - * as there is no need to program the PLL itself. If we are not able to - * allocate a PLL, return ATOM_PPLL_INVALID to skip PLL programming to - * avoid messing up an existing monitor. - * - * Asic specific PLL information - * - * DCE 6.1 - * - PPLL2 is only available to UNIPHYA (both DP and non-DP) - * - PPLL0, PPLL1 are available for UNIPHYB/C/D/E/F (both DP and non-DP) - * - * DCE 6.0 - * - PPLL0 is available to all UNIPHY (DP only) - * - PPLL1, PPLL2 are available for all UNIPHY (both DP and non-DP) and DAC - * - * DCE 5.0 - * - DCPLL is available to all UNIPHY (DP only) - * - PPLL1, PPLL2 are available for all UNIPHY (both DP and non-DP) and DAC - * - * DCE 3.0/4.0/4.1 - * - PPLL1, PPLL2 are available for all UNIPHY (both DP and non-DP) and DAC - * - */ static int radeon_atom_pick_pll(struct drm_crtc *crtc) { struct radeon_crtc *radeon_crtc = to_radeon_crtc(crtc); struct drm_device *dev = crtc->dev; struct radeon_device *rdev = dev->dev_private; struct drm_encoder *test_encoder; - u32 pll_in_use; - int pll; + struct drm_crtc *test_crtc; + uint32_t pll_in_use = 0; if (ASIC_IS_DCE61(rdev)) { list_for_each_entry(test_encoder, &dev->mode_config.encoder_list, head) { @@ -1582,40 +1498,32 @@ static int radeon_atom_pick_pll(struct drm_crtc *crtc) if ((test_radeon_encoder->encoder_id == ENCODER_OBJECT_ID_INTERNAL_UNIPHY) && - (dig->linkb == false)) - /* UNIPHY A uses PPLL2 */ + (dig->linkb == false)) /* UNIPHY A uses PPLL2 */ return ATOM_PPLL2; - else if (ENCODER_MODE_IS_DP(atombios_get_encoder_mode(test_encoder))) { - /* UNIPHY B/C/D/E/F */ - if (rdev->clock.dp_extclk) - /* skip PPLL programming if using ext clock */ - return ATOM_PPLL_INVALID; - else { - /* use the same PPLL for all DP monitors */ - pll = radeon_get_shared_dp_ppll(crtc); - if (pll != ATOM_PPLL_INVALID) - return pll; - } - } - break; } } /* UNIPHY B/C/D/E/F */ - pll_in_use = radeon_get_pll_use_mask(crtc); - if (!(pll_in_use & (1 << ATOM_PPLL0))) + list_for_each_entry(test_crtc, &dev->mode_config.crtc_list, head) { + struct radeon_crtc *radeon_test_crtc; + + if (crtc == test_crtc) + continue; + + radeon_test_crtc = to_radeon_crtc(test_crtc); + if ((radeon_test_crtc->pll_id == ATOM_PPLL0) || + (radeon_test_crtc->pll_id == ATOM_PPLL1)) + pll_in_use |= (1 << radeon_test_crtc->pll_id); + } + if (!(pll_in_use & 4)) return ATOM_PPLL0; - if (!(pll_in_use & (1 << ATOM_PPLL1))) - return ATOM_PPLL1; - DRM_ERROR("unable to allocate a PPLL\n"); - return ATOM_PPLL_INVALID; + return ATOM_PPLL1; } else if (ASIC_IS_DCE4(rdev)) { list_for_each_entry(test_encoder, &dev->mode_config.encoder_list, head) { if (test_encoder->crtc && (test_encoder->crtc == crtc)) { /* in DP mode, the DP ref clock can come from PPLL, DCPLL, or ext clock, * depending on the asic: * DCE4: PPLL or ext clock - * DCE5: PPLL, DCPLL, or ext clock - * DCE6: PPLL, PPLL0, or ext clock + * DCE5: DCPLL or ext clock * * Setting ATOM_PPLL_INVALID will cause SetPixelClock to skip * PPLL/DCPLL programming and only program the DP DTO for the @@ -1623,34 +1531,31 @@ static int radeon_atom_pick_pll(struct drm_crtc *crtc) */ if (ENCODER_MODE_IS_DP(atombios_get_encoder_mode(test_encoder))) { if (rdev->clock.dp_extclk) - /* skip PPLL programming if using ext clock */ return ATOM_PPLL_INVALID; else if (ASIC_IS_DCE6(rdev)) - /* use PPLL0 for all DP */ return ATOM_PPLL0; else if (ASIC_IS_DCE5(rdev)) - /* use DCPLL for all DP */ return ATOM_DCPLL; - else { - /* use the same PPLL for all DP monitors */ - pll = radeon_get_shared_dp_ppll(crtc); - if (pll != ATOM_PPLL_INVALID) - return pll; - } } - break; } } - /* all other cases */ - pll_in_use = radeon_get_pll_use_mask(crtc); - if (!(pll_in_use & (1 << ATOM_PPLL2))) - return ATOM_PPLL2; - if (!(pll_in_use & (1 << ATOM_PPLL1))) + + /* otherwise, pick one of the plls */ + list_for_each_entry(test_crtc, &dev->mode_config.crtc_list, head) { + struct radeon_crtc *radeon_test_crtc; + + if (crtc == test_crtc) + continue; + + radeon_test_crtc = to_radeon_crtc(test_crtc); + if ((radeon_test_crtc->pll_id >= ATOM_PPLL1) && + (radeon_test_crtc->pll_id <= ATOM_PPLL2)) + pll_in_use |= (1 << radeon_test_crtc->pll_id); + } + if (!(pll_in_use & 1)) return ATOM_PPLL1; - DRM_ERROR("unable to allocate a PPLL\n"); - return ATOM_PPLL_INVALID; + return ATOM_PPLL2; } else - /* use PPLL1 or PPLL2 */ return radeon_crtc->crtc_id; } @@ -1792,7 +1697,7 @@ static void atombios_crtc_disable(struct drm_crtc *crtc) break; } done: - radeon_crtc->pll_id = ATOM_PPLL_INVALID; + radeon_crtc->pll_id = -1; } static const struct drm_crtc_helper_funcs atombios_helper_funcs = { @@ -1841,6 +1746,6 @@ void radeon_atombios_init_crtc(struct drm_device *dev, else radeon_crtc->crtc_offset = 0; } - radeon_crtc->pll_id = ATOM_PPLL_INVALID; + radeon_crtc->pll_id = -1; drm_crtc_helper_add(&radeon_crtc->base, &atombios_helper_funcs); } diff --git a/drivers/gpu/drm/radeon/r100.c b/drivers/gpu/drm/radeon/r100.c index 8acb34fd3fd..8d7e33a0b24 100644 --- a/drivers/gpu/drm/radeon/r100.c +++ b/drivers/gpu/drm/radeon/r100.c @@ -1182,7 +1182,8 @@ int r100_cp_init(struct radeon_device *rdev, unsigned ring_size) ring->ready = true; radeon_ttm_set_active_vram_size(rdev, rdev->mc.real_vram_size); - if (radeon_ring_supports_scratch_reg(rdev, ring)) { + if (!ring->rptr_save_reg /* not resuming from suspend */ + && radeon_ring_supports_scratch_reg(rdev, ring)) { r = radeon_scratch_get(rdev, &ring->rptr_save_reg); if (r) { DRM_ERROR("failed to get scratch reg for rptr save (%d).\n", r); diff --git a/drivers/gpu/drm/udl/udl_connector.c b/drivers/gpu/drm/udl/udl_connector.c index ba055e9ca00..8d9dc44f1f9 100644 --- a/drivers/gpu/drm/udl/udl_connector.c +++ b/drivers/gpu/drm/udl/udl_connector.c @@ -69,6 +69,13 @@ static int udl_get_modes(struct drm_connector *connector) static int udl_mode_valid(struct drm_connector *connector, struct drm_display_mode *mode) { + struct udl_device *udl = connector->dev->dev_private; + if (!udl->sku_pixel_limit) + return 0; + + if (mode->vdisplay * mode->hdisplay > udl->sku_pixel_limit) + return MODE_VIRTUAL_Y; + return 0; } diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c b/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c index f2fb8f15e2f..7e0743358df 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c @@ -1018,7 +1018,7 @@ int vmw_event_fence_action_create(struct drm_file *file_priv, } - event = kzalloc(sizeof(event->event), GFP_KERNEL); + event = kzalloc(sizeof(*event), GFP_KERNEL); if (unlikely(event == NULL)) { DRM_ERROR("Failed to allocate an event.\n"); ret = -ENOMEM; diff --git a/drivers/hid/hid-lenovo-tpkbd.c b/drivers/hid/hid-lenovo-tpkbd.c index 77d2df04c97..60c4e1e8591 100644 --- a/drivers/hid/hid-lenovo-tpkbd.c +++ b/drivers/hid/hid-lenovo-tpkbd.c @@ -519,6 +519,8 @@ static void tpkbd_remove_tp(struct hid_device *hdev) led_classdev_unregister(&data_pointer->led_mute); hid_set_drvdata(hdev, NULL); + kfree(data_pointer->led_micmute.name); + kfree(data_pointer->led_mute.name); kfree(data_pointer); } diff --git a/drivers/hid/hid-logitech-dj.c b/drivers/hid/hid-logitech-dj.c index 4d524b5f52f..9500f2f3f8f 100644 --- a/drivers/hid/hid-logitech-dj.c +++ b/drivers/hid/hid-logitech-dj.c @@ -193,6 +193,7 @@ static struct hid_ll_driver logi_dj_ll_driver; static int logi_dj_output_hidraw_report(struct hid_device *hid, u8 * buf, size_t count, unsigned char report_type); +static int logi_dj_recv_query_paired_devices(struct dj_receiver_dev *djrcv_dev); static void logi_dj_recv_destroy_djhid_device(struct dj_receiver_dev *djrcv_dev, struct dj_report *dj_report) @@ -233,6 +234,7 @@ static void logi_dj_recv_add_djhid_device(struct dj_receiver_dev *djrcv_dev, if (dj_report->report_params[DEVICE_PAIRED_PARAM_SPFUNCTION] & SPFUNCTION_DEVICE_LIST_EMPTY) { dbg_hid("%s: device list is empty\n", __func__); + djrcv_dev->querying_devices = false; return; } @@ -243,6 +245,12 @@ static void logi_dj_recv_add_djhid_device(struct dj_receiver_dev *djrcv_dev, return; } + if (djrcv_dev->paired_dj_devices[dj_report->device_index]) { + /* The device is already known. No need to reallocate it. */ + dbg_hid("%s: device is already known\n", __func__); + return; + } + dj_hiddev = hid_allocate_device(); if (IS_ERR(dj_hiddev)) { dev_err(&djrcv_hdev->dev, "%s: hid_allocate_device failed\n", @@ -306,6 +314,7 @@ static void delayedwork_callback(struct work_struct *work) struct dj_report dj_report; unsigned long flags; int count; + int retval; dbg_hid("%s\n", __func__); @@ -338,6 +347,25 @@ static void delayedwork_callback(struct work_struct *work) logi_dj_recv_destroy_djhid_device(djrcv_dev, &dj_report); break; default: + /* A normal report (i. e. not belonging to a pair/unpair notification) + * arriving here, means that the report arrived but we did not have a + * paired dj_device associated to the report's device_index, this + * means that the original "device paired" notification corresponding + * to this dj_device never arrived to this driver. The reason is that + * hid-core discards all packets coming from a device while probe() is + * executing. */ + if (!djrcv_dev->paired_dj_devices[dj_report.device_index]) { + /* ok, we don't know the device, just re-ask the + * receiver for the list of connected devices. */ + retval = logi_dj_recv_query_paired_devices(djrcv_dev); + if (!retval) { + /* everything went fine, so just leave */ + break; + } + dev_err(&djrcv_dev->hdev->dev, + "%s:logi_dj_recv_query_paired_devices " + "error:%d\n", __func__, retval); + } dbg_hid("%s: unexpected report type\n", __func__); } } @@ -368,6 +396,12 @@ static void logi_dj_recv_forward_null_report(struct dj_receiver_dev *djrcv_dev, if (!djdev) { dbg_hid("djrcv_dev->paired_dj_devices[dj_report->device_index]" " is NULL, index %d\n", dj_report->device_index); + kfifo_in(&djrcv_dev->notif_fifo, dj_report, sizeof(struct dj_report)); + + if (schedule_work(&djrcv_dev->work) == 0) { + dbg_hid("%s: did not schedule the work item, was already " + "queued\n", __func__); + } return; } @@ -398,6 +432,12 @@ static void logi_dj_recv_forward_report(struct dj_receiver_dev *djrcv_dev, if (dj_device == NULL) { dbg_hid("djrcv_dev->paired_dj_devices[dj_report->device_index]" " is NULL, index %d\n", dj_report->device_index); + kfifo_in(&djrcv_dev->notif_fifo, dj_report, sizeof(struct dj_report)); + + if (schedule_work(&djrcv_dev->work) == 0) { + dbg_hid("%s: did not schedule the work item, was already " + "queued\n", __func__); + } return; } @@ -439,6 +479,10 @@ static int logi_dj_recv_query_paired_devices(struct dj_receiver_dev *djrcv_dev) struct dj_report *dj_report; int retval; + /* no need to protect djrcv_dev->querying_devices */ + if (djrcv_dev->querying_devices) + return 0; + dj_report = kzalloc(sizeof(struct dj_report), GFP_KERNEL); if (!dj_report) return -ENOMEM; @@ -450,6 +494,7 @@ static int logi_dj_recv_query_paired_devices(struct dj_receiver_dev *djrcv_dev) return retval; } + static int logi_dj_recv_switch_to_dj_mode(struct dj_receiver_dev *djrcv_dev, unsigned timeout) { diff --git a/drivers/hid/hid-logitech-dj.h b/drivers/hid/hid-logitech-dj.h index fd28a5e0ca3..4a4000340ce 100644 --- a/drivers/hid/hid-logitech-dj.h +++ b/drivers/hid/hid-logitech-dj.h @@ -101,6 +101,7 @@ struct dj_receiver_dev { struct work_struct work; struct kfifo notif_fifo; spinlock_t lock; + bool querying_devices; }; struct dj_device { diff --git a/drivers/hwmon/ad7314.c b/drivers/hwmon/ad7314.c index cfec802cf9c..f915eb1c29f 100644 --- a/drivers/hwmon/ad7314.c +++ b/drivers/hwmon/ad7314.c @@ -87,10 +87,18 @@ static ssize_t ad7314_show_temperature(struct device *dev, } } +static ssize_t ad7314_show_name(struct device *dev, + struct device_attribute *devattr, char *buf) +{ + return sprintf(buf, "%s\n", to_spi_device(dev)->modalias); +} + +static DEVICE_ATTR(name, S_IRUGO, ad7314_show_name, NULL); static SENSOR_DEVICE_ATTR(temp1_input, S_IRUGO, ad7314_show_temperature, NULL, 0); static struct attribute *ad7314_attributes[] = { + &dev_attr_name.attr, &sensor_dev_attr_temp1_input.dev_attr.attr, NULL, }; diff --git a/drivers/hwmon/ads7871.c b/drivers/hwmon/ads7871.c index e65c6e45d36..7bf4ce3d405 100644 --- a/drivers/hwmon/ads7871.c +++ b/drivers/hwmon/ads7871.c @@ -139,6 +139,12 @@ static ssize_t show_voltage(struct device *dev, } } +static ssize_t ads7871_show_name(struct device *dev, + struct device_attribute *devattr, char *buf) +{ + return sprintf(buf, "%s\n", to_spi_device(dev)->modalias); +} + static SENSOR_DEVICE_ATTR(in0_input, S_IRUGO, show_voltage, NULL, 0); static SENSOR_DEVICE_ATTR(in1_input, S_IRUGO, show_voltage, NULL, 1); static SENSOR_DEVICE_ATTR(in2_input, S_IRUGO, show_voltage, NULL, 2); @@ -148,6 +154,8 @@ static SENSOR_DEVICE_ATTR(in5_input, S_IRUGO, show_voltage, NULL, 5); static SENSOR_DEVICE_ATTR(in6_input, S_IRUGO, show_voltage, NULL, 6); static SENSOR_DEVICE_ATTR(in7_input, S_IRUGO, show_voltage, NULL, 7); +static DEVICE_ATTR(name, S_IRUGO, ads7871_show_name, NULL); + static struct attribute *ads7871_attributes[] = { &sensor_dev_attr_in0_input.dev_attr.attr, &sensor_dev_attr_in1_input.dev_attr.attr, @@ -157,6 +165,7 @@ static struct attribute *ads7871_attributes[] = { &sensor_dev_attr_in5_input.dev_attr.attr, &sensor_dev_attr_in6_input.dev_attr.attr, &sensor_dev_attr_in7_input.dev_attr.attr, + &dev_attr_name.attr, NULL }; diff --git a/drivers/hwmon/applesmc.c b/drivers/hwmon/applesmc.c index 28270886051..8f3f6f2c45f 100644 --- a/drivers/hwmon/applesmc.c +++ b/drivers/hwmon/applesmc.c @@ -53,10 +53,10 @@ #define APPLESMC_MAX_DATA_LENGTH 32 -/* wait up to 32 ms for a status change. */ +/* wait up to 128 ms for a status change. */ #define APPLESMC_MIN_WAIT 0x0010 #define APPLESMC_RETRY_WAIT 0x0100 -#define APPLESMC_MAX_WAIT 0x8000 +#define APPLESMC_MAX_WAIT 0x20000 #define APPLESMC_READ_CMD 0x10 #define APPLESMC_WRITE_CMD 0x11 diff --git a/drivers/hwmon/coretemp.c b/drivers/hwmon/coretemp.c index 0fa356fe82c..984a3f13923 100644 --- a/drivers/hwmon/coretemp.c +++ b/drivers/hwmon/coretemp.c @@ -815,17 +815,20 @@ static int __init coretemp_init(void) if (err) goto exit; + get_online_cpus(); for_each_online_cpu(i) get_core_online(i); #ifndef CONFIG_HOTPLUG_CPU if (list_empty(&pdev_list)) { + put_online_cpus(); err = -ENODEV; goto exit_driver_unreg; } #endif register_hotcpu_notifier(&coretemp_cpu_notifier); + put_online_cpus(); return 0; #ifndef CONFIG_HOTPLUG_CPU @@ -840,6 +843,7 @@ static void __exit coretemp_exit(void) { struct pdev_entry *p, *n; + get_online_cpus(); unregister_hotcpu_notifier(&coretemp_cpu_notifier); mutex_lock(&pdev_list_mutex); list_for_each_entry_safe(p, n, &pdev_list, list) { @@ -848,6 +852,7 @@ static void __exit coretemp_exit(void) kfree(p); } mutex_unlock(&pdev_list_mutex); + put_online_cpus(); platform_driver_unregister(&coretemp_driver); } diff --git a/drivers/hwmon/fam15h_power.c b/drivers/hwmon/fam15h_power.c index 2764b78a784..af69073b3fe 100644 --- a/drivers/hwmon/fam15h_power.c +++ b/drivers/hwmon/fam15h_power.c @@ -129,12 +129,12 @@ static bool __devinit fam15h_power_is_internal_node0(struct pci_dev *f4) * counter saturations resulting in bogus power readings. * We correct this value ourselves to cope with older BIOSes. */ -static DEFINE_PCI_DEVICE_TABLE(affected_device) = { +static const struct pci_device_id affected_device[] = { { PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_15H_NB_F4) }, { 0 } }; -static void __devinit tweak_runavg_range(struct pci_dev *pdev) +static void tweak_runavg_range(struct pci_dev *pdev) { u32 val; @@ -158,6 +158,16 @@ static void __devinit tweak_runavg_range(struct pci_dev *pdev) REG_TDP_RUNNING_AVERAGE, val); } +#ifdef CONFIG_PM +static int fam15h_power_resume(struct pci_dev *pdev) +{ + tweak_runavg_range(pdev); + return 0; +} +#else +#define fam15h_power_resume NULL +#endif + static void __devinit fam15h_power_init_data(struct pci_dev *f4, struct fam15h_power_data *data) { @@ -256,6 +266,7 @@ static struct pci_driver fam15h_power_driver = { .id_table = fam15h_power_id_table, .probe = fam15h_power_probe, .remove = __devexit_p(fam15h_power_remove), + .resume = fam15h_power_resume, }; module_pci_driver(fam15h_power_driver); diff --git a/drivers/hwmon/via-cputemp.c b/drivers/hwmon/via-cputemp.c index ee4ebc198a9..2e56c6ce9fb 100644 --- a/drivers/hwmon/via-cputemp.c +++ b/drivers/hwmon/via-cputemp.c @@ -328,6 +328,7 @@ static int __init via_cputemp_init(void) if (err) goto exit; + get_online_cpus(); for_each_online_cpu(i) { struct cpuinfo_x86 *c = &cpu_data(i); @@ -347,12 +348,14 @@ static int __init via_cputemp_init(void) #ifndef CONFIG_HOTPLUG_CPU if (list_empty(&pdev_list)) { + put_online_cpus(); err = -ENODEV; goto exit_driver_unreg; } #endif register_hotcpu_notifier(&via_cputemp_cpu_notifier); + put_online_cpus(); return 0; #ifndef CONFIG_HOTPLUG_CPU @@ -367,6 +370,7 @@ static void __exit via_cputemp_exit(void) { struct pdev_entry *p, *n; + get_online_cpus(); unregister_hotcpu_notifier(&via_cputemp_cpu_notifier); mutex_lock(&pdev_list_mutex); list_for_each_entry_safe(p, n, &pdev_list, list) { @@ -375,6 +379,7 @@ static void __exit via_cputemp_exit(void) kfree(p); } mutex_unlock(&pdev_list_mutex); + put_online_cpus(); platform_driver_unregister(&via_cputemp_driver); } diff --git a/drivers/hwspinlock/hwspinlock_core.c b/drivers/hwspinlock/hwspinlock_core.c index 1201a15784c..db713c0dfba 100644 --- a/drivers/hwspinlock/hwspinlock_core.c +++ b/drivers/hwspinlock/hwspinlock_core.c @@ -552,7 +552,7 @@ EXPORT_SYMBOL_GPL(hwspin_lock_request_specific); */ int hwspin_lock_free(struct hwspinlock *hwlock) { - struct device *dev = hwlock->bank->dev; + struct device *dev; struct hwspinlock *tmp; int ret; @@ -561,6 +561,7 @@ int hwspin_lock_free(struct hwspinlock *hwlock) return -EINVAL; } + dev = hwlock->bank->dev; mutex_lock(&hwspinlock_tree_lock); /* make sure the hwspinlock is used */ diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c index 51f42061dae..6cfd4d8fd0b 100644 --- a/drivers/infiniband/hw/cxgb4/cm.c +++ b/drivers/infiniband/hw/cxgb4/cm.c @@ -1361,11 +1361,11 @@ static int abort_rpl(struct c4iw_dev *dev, struct sk_buff *skb) struct tid_info *t = dev->rdev.lldi.tids; ep = lookup_tid(t, tid); - PDBG("%s ep %p tid %u\n", __func__, ep, ep->hwtid); if (!ep) { printk(KERN_WARNING MOD "Abort rpl to freed endpoint\n"); return 0; } + PDBG("%s ep %p tid %u\n", __func__, ep, ep->hwtid); mutex_lock(&ep->com.mutex); switch (ep->com.state) { case ABORTING: diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c index cb5b7f7d4d3..b29a4246ef4 100644 --- a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c +++ b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c @@ -2219,7 +2219,6 @@ static bool ocrdma_poll_success_scqe(struct ocrdma_qp *qp, u32 wqe_idx; if (!qp->wqe_wr_id_tbl[tail].signaled) { - expand = true; /* CQE cannot be consumed yet */ *polled = false; /* WC cannot be consumed yet */ } else { ibwc->status = IB_WC_SUCCESS; @@ -2227,10 +2226,11 @@ static bool ocrdma_poll_success_scqe(struct ocrdma_qp *qp, ibwc->qp = &qp->ibqp; ocrdma_update_wc(qp, ibwc, tail); *polled = true; - wqe_idx = le32_to_cpu(cqe->wq.wqeidx) & OCRDMA_CQE_WQEIDX_MASK; - if (tail != wqe_idx) - expand = true; /* Coalesced CQE can't be consumed yet */ } + wqe_idx = le32_to_cpu(cqe->wq.wqeidx) & OCRDMA_CQE_WQEIDX_MASK; + if (tail != wqe_idx) + expand = true; /* Coalesced CQE can't be consumed yet */ + ocrdma_hwq_inc_tail(&qp->sq); return expand; } diff --git a/drivers/infiniband/hw/qib/qib_mad.c b/drivers/infiniband/hw/qib/qib_mad.c index 19f1e6c45fb..ccb119143d2 100644 --- a/drivers/infiniband/hw/qib/qib_mad.c +++ b/drivers/infiniband/hw/qib/qib_mad.c @@ -471,9 +471,10 @@ static int subn_get_portinfo(struct ib_smp *smp, struct ib_device *ibdev, if (port_num != port) { ibp = to_iport(ibdev, port_num); ret = check_mkey(ibp, smp, 0); - if (ret) + if (ret) { ret = IB_MAD_RESULT_FAILURE; goto bail; + } } } diff --git a/drivers/infiniband/ulp/ipoib/ipoib.h b/drivers/infiniband/ulp/ipoib/ipoib.h index ca43901ed86..0af216d21f8 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib.h +++ b/drivers/infiniband/ulp/ipoib/ipoib.h @@ -262,7 +262,10 @@ struct ipoib_ethtool_st { u16 max_coalesced_frames; }; +struct ipoib_neigh_table; + struct ipoib_neigh_hash { + struct ipoib_neigh_table *ntbl; struct ipoib_neigh __rcu **buckets; struct rcu_head rcu; u32 mask; @@ -271,9 +274,9 @@ struct ipoib_neigh_hash { struct ipoib_neigh_table { struct ipoib_neigh_hash __rcu *htbl; - rwlock_t rwlock; atomic_t entries; struct completion flushed; + struct completion deleted; }; /* diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c index 3e2085a3ee4..1e19b5ae7c4 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_main.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c @@ -546,15 +546,15 @@ static void neigh_add_path(struct sk_buff *skb, u8 *daddr, struct ipoib_neigh *neigh; unsigned long flags; + spin_lock_irqsave(&priv->lock, flags); neigh = ipoib_neigh_alloc(daddr, dev); if (!neigh) { + spin_unlock_irqrestore(&priv->lock, flags); ++dev->stats.tx_dropped; dev_kfree_skb_any(skb); return; } - spin_lock_irqsave(&priv->lock, flags); - path = __path_find(dev, daddr + 4); if (!path) { path = path_rec_create(dev, daddr + 4); @@ -863,10 +863,10 @@ static void __ipoib_reap_neigh(struct ipoib_dev_priv *priv) if (test_bit(IPOIB_STOP_NEIGH_GC, &priv->flags)) return; - write_lock_bh(&ntbl->rwlock); + spin_lock_irqsave(&priv->lock, flags); htbl = rcu_dereference_protected(ntbl->htbl, - lockdep_is_held(&ntbl->rwlock)); + lockdep_is_held(&priv->lock)); if (!htbl) goto out_unlock; @@ -883,16 +883,14 @@ static void __ipoib_reap_neigh(struct ipoib_dev_priv *priv) struct ipoib_neigh __rcu **np = &htbl->buckets[i]; while ((neigh = rcu_dereference_protected(*np, - lockdep_is_held(&ntbl->rwlock))) != NULL) { + lockdep_is_held(&priv->lock))) != NULL) { /* was the neigh idle for two GC periods */ if (time_after(neigh_obsolete, neigh->alive)) { rcu_assign_pointer(*np, rcu_dereference_protected(neigh->hnext, - lockdep_is_held(&ntbl->rwlock))); + lockdep_is_held(&priv->lock))); /* remove from path/mc list */ - spin_lock_irqsave(&priv->lock, flags); list_del(&neigh->list); - spin_unlock_irqrestore(&priv->lock, flags); call_rcu(&neigh->rcu, ipoib_neigh_reclaim); } else { np = &neigh->hnext; @@ -902,7 +900,7 @@ static void __ipoib_reap_neigh(struct ipoib_dev_priv *priv) } out_unlock: - write_unlock_bh(&ntbl->rwlock); + spin_unlock_irqrestore(&priv->lock, flags); } static void ipoib_reap_neigh(struct work_struct *work) @@ -947,10 +945,8 @@ struct ipoib_neigh *ipoib_neigh_alloc(u8 *daddr, struct ipoib_neigh *neigh; u32 hash_val; - write_lock_bh(&ntbl->rwlock); - htbl = rcu_dereference_protected(ntbl->htbl, - lockdep_is_held(&ntbl->rwlock)); + lockdep_is_held(&priv->lock)); if (!htbl) { neigh = NULL; goto out_unlock; @@ -961,10 +957,10 @@ struct ipoib_neigh *ipoib_neigh_alloc(u8 *daddr, */ hash_val = ipoib_addr_hash(htbl, daddr); for (neigh = rcu_dereference_protected(htbl->buckets[hash_val], - lockdep_is_held(&ntbl->rwlock)); + lockdep_is_held(&priv->lock)); neigh != NULL; neigh = rcu_dereference_protected(neigh->hnext, - lockdep_is_held(&ntbl->rwlock))) { + lockdep_is_held(&priv->lock))) { if (memcmp(daddr, neigh->daddr, INFINIBAND_ALEN) == 0) { /* found, take one ref on behalf of the caller */ if (!atomic_inc_not_zero(&neigh->refcnt)) { @@ -987,12 +983,11 @@ struct ipoib_neigh *ipoib_neigh_alloc(u8 *daddr, /* put in hash */ rcu_assign_pointer(neigh->hnext, rcu_dereference_protected(htbl->buckets[hash_val], - lockdep_is_held(&ntbl->rwlock))); + lockdep_is_held(&priv->lock))); rcu_assign_pointer(htbl->buckets[hash_val], neigh); atomic_inc(&ntbl->entries); out_unlock: - write_unlock_bh(&ntbl->rwlock); return neigh; } @@ -1040,35 +1035,29 @@ void ipoib_neigh_free(struct ipoib_neigh *neigh) struct ipoib_neigh *n; u32 hash_val; - write_lock_bh(&ntbl->rwlock); - htbl = rcu_dereference_protected(ntbl->htbl, - lockdep_is_held(&ntbl->rwlock)); + lockdep_is_held(&priv->lock)); if (!htbl) - goto out_unlock; + return; hash_val = ipoib_addr_hash(htbl, neigh->daddr); np = &htbl->buckets[hash_val]; for (n = rcu_dereference_protected(*np, - lockdep_is_held(&ntbl->rwlock)); + lockdep_is_held(&priv->lock)); n != NULL; n = rcu_dereference_protected(*np, - lockdep_is_held(&ntbl->rwlock))) { + lockdep_is_held(&priv->lock))) { if (n == neigh) { /* found */ rcu_assign_pointer(*np, rcu_dereference_protected(neigh->hnext, - lockdep_is_held(&ntbl->rwlock))); + lockdep_is_held(&priv->lock))); call_rcu(&neigh->rcu, ipoib_neigh_reclaim); - goto out_unlock; + return; } else { np = &n->hnext; } } - -out_unlock: - write_unlock_bh(&ntbl->rwlock); - } static int ipoib_neigh_hash_init(struct ipoib_dev_priv *priv) @@ -1080,7 +1069,6 @@ static int ipoib_neigh_hash_init(struct ipoib_dev_priv *priv) clear_bit(IPOIB_NEIGH_TBL_FLUSH, &priv->flags); ntbl->htbl = NULL; - rwlock_init(&ntbl->rwlock); htbl = kzalloc(sizeof(*htbl), GFP_KERNEL); if (!htbl) return -ENOMEM; @@ -1095,6 +1083,7 @@ static int ipoib_neigh_hash_init(struct ipoib_dev_priv *priv) htbl->mask = (size - 1); htbl->buckets = buckets; ntbl->htbl = htbl; + htbl->ntbl = ntbl; atomic_set(&ntbl->entries, 0); /* start garbage collection */ @@ -1111,9 +1100,11 @@ static void neigh_hash_free_rcu(struct rcu_head *head) struct ipoib_neigh_hash, rcu); struct ipoib_neigh __rcu **buckets = htbl->buckets; + struct ipoib_neigh_table *ntbl = htbl->ntbl; kfree(buckets); kfree(htbl); + complete(&ntbl->deleted); } void ipoib_del_neighs_by_gid(struct net_device *dev, u8 *gid) @@ -1125,10 +1116,10 @@ void ipoib_del_neighs_by_gid(struct net_device *dev, u8 *gid) int i; /* remove all neigh connected to a given path or mcast */ - write_lock_bh(&ntbl->rwlock); + spin_lock_irqsave(&priv->lock, flags); htbl = rcu_dereference_protected(ntbl->htbl, - lockdep_is_held(&ntbl->rwlock)); + lockdep_is_held(&priv->lock)); if (!htbl) goto out_unlock; @@ -1138,16 +1129,14 @@ void ipoib_del_neighs_by_gid(struct net_device *dev, u8 *gid) struct ipoib_neigh __rcu **np = &htbl->buckets[i]; while ((neigh = rcu_dereference_protected(*np, - lockdep_is_held(&ntbl->rwlock))) != NULL) { + lockdep_is_held(&priv->lock))) != NULL) { /* delete neighs belong to this parent */ if (!memcmp(gid, neigh->daddr + 4, sizeof (union ib_gid))) { rcu_assign_pointer(*np, rcu_dereference_protected(neigh->hnext, - lockdep_is_held(&ntbl->rwlock))); + lockdep_is_held(&priv->lock))); /* remove from parent list */ - spin_lock_irqsave(&priv->lock, flags); list_del(&neigh->list); - spin_unlock_irqrestore(&priv->lock, flags); call_rcu(&neigh->rcu, ipoib_neigh_reclaim); } else { np = &neigh->hnext; @@ -1156,7 +1145,7 @@ void ipoib_del_neighs_by_gid(struct net_device *dev, u8 *gid) } } out_unlock: - write_unlock_bh(&ntbl->rwlock); + spin_unlock_irqrestore(&priv->lock, flags); } static void ipoib_flush_neighs(struct ipoib_dev_priv *priv) @@ -1164,37 +1153,44 @@ static void ipoib_flush_neighs(struct ipoib_dev_priv *priv) struct ipoib_neigh_table *ntbl = &priv->ntbl; struct ipoib_neigh_hash *htbl; unsigned long flags; - int i; + int i, wait_flushed = 0; - write_lock_bh(&ntbl->rwlock); + init_completion(&priv->ntbl.flushed); + + spin_lock_irqsave(&priv->lock, flags); htbl = rcu_dereference_protected(ntbl->htbl, - lockdep_is_held(&ntbl->rwlock)); + lockdep_is_held(&priv->lock)); if (!htbl) goto out_unlock; + wait_flushed = atomic_read(&priv->ntbl.entries); + if (!wait_flushed) + goto free_htbl; + for (i = 0; i < htbl->size; i++) { struct ipoib_neigh *neigh; struct ipoib_neigh __rcu **np = &htbl->buckets[i]; while ((neigh = rcu_dereference_protected(*np, - lockdep_is_held(&ntbl->rwlock))) != NULL) { + lockdep_is_held(&priv->lock))) != NULL) { rcu_assign_pointer(*np, rcu_dereference_protected(neigh->hnext, - lockdep_is_held(&ntbl->rwlock))); + lockdep_is_held(&priv->lock))); /* remove from path/mc list */ - spin_lock_irqsave(&priv->lock, flags); list_del(&neigh->list); - spin_unlock_irqrestore(&priv->lock, flags); call_rcu(&neigh->rcu, ipoib_neigh_reclaim); } } +free_htbl: rcu_assign_pointer(ntbl->htbl, NULL); call_rcu(&htbl->rcu, neigh_hash_free_rcu); out_unlock: - write_unlock_bh(&ntbl->rwlock); + spin_unlock_irqrestore(&priv->lock, flags); + if (wait_flushed) + wait_for_completion(&priv->ntbl.flushed); } static void ipoib_neigh_hash_uninit(struct net_device *dev) @@ -1203,7 +1199,7 @@ static void ipoib_neigh_hash_uninit(struct net_device *dev) int stopped; ipoib_dbg(priv, "ipoib_neigh_hash_uninit\n"); - init_completion(&priv->ntbl.flushed); + init_completion(&priv->ntbl.deleted); set_bit(IPOIB_NEIGH_TBL_FLUSH, &priv->flags); /* Stop GC if called at init fail need to cancel work */ @@ -1211,10 +1207,9 @@ static void ipoib_neigh_hash_uninit(struct net_device *dev) if (!stopped) cancel_delayed_work(&priv->neigh_reap_task); - if (atomic_read(&priv->ntbl.entries)) { - ipoib_flush_neighs(priv); - wait_for_completion(&priv->ntbl.flushed); - } + ipoib_flush_neighs(priv); + + wait_for_completion(&priv->ntbl.deleted); } diff --git a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c index 13f4aa7593c..75367249f44 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c @@ -707,9 +707,7 @@ out: neigh = ipoib_neigh_get(dev, daddr); spin_lock_irqsave(&priv->lock, flags); if (!neigh) { - spin_unlock_irqrestore(&priv->lock, flags); neigh = ipoib_neigh_alloc(daddr, dev); - spin_lock_irqsave(&priv->lock, flags); if (neigh) { kref_get(&mcast->ah->ref); neigh->ah = mcast->ah; diff --git a/drivers/input/keyboard/imx_keypad.c b/drivers/input/keyboard/imx_keypad.c index ce68e361558..cdc252612c0 100644 --- a/drivers/input/keyboard/imx_keypad.c +++ b/drivers/input/keyboard/imx_keypad.c @@ -516,9 +516,9 @@ static int __devinit imx_keypad_probe(struct platform_device *pdev) input_set_drvdata(input_dev, keypad); /* Ensure that the keypad will stay dormant until opened */ - clk_enable(keypad->clk); + clk_prepare_enable(keypad->clk); imx_keypad_inhibit(keypad); - clk_disable(keypad->clk); + clk_disable_unprepare(keypad->clk); error = request_irq(irq, imx_keypad_irq_handler, 0, pdev->name, keypad); diff --git a/drivers/input/misc/ab8500-ponkey.c b/drivers/input/misc/ab8500-ponkey.c index f06231b7cab..84ec691c05a 100644 --- a/drivers/input/misc/ab8500-ponkey.c +++ b/drivers/input/misc/ab8500-ponkey.c @@ -74,8 +74,8 @@ static int __devinit ab8500_ponkey_probe(struct platform_device *pdev) ponkey->idev = input; ponkey->ab8500 = ab8500; - ponkey->irq_dbf = ab8500_irq_get_virq(ab8500, irq_dbf); - ponkey->irq_dbr = ab8500_irq_get_virq(ab8500, irq_dbr); + ponkey->irq_dbf = irq_dbf; + ponkey->irq_dbr = irq_dbr; input->name = "AB8500 POn(PowerOn) Key"; input->dev.parent = &pdev->dev; diff --git a/drivers/input/mouse/sentelic.c b/drivers/input/mouse/sentelic.c index 3f5649f1908..a261d857691 100644 --- a/drivers/input/mouse/sentelic.c +++ b/drivers/input/mouse/sentelic.c @@ -721,6 +721,17 @@ static psmouse_ret_t fsp_process_byte(struct psmouse *psmouse) switch (psmouse->packet[0] >> FSP_PKT_TYPE_SHIFT) { case FSP_PKT_TYPE_ABS: + + if ((packet[0] == 0x48 || packet[0] == 0x49) && + packet[1] == 0 && packet[2] == 0) { + /* + * Ignore coordinate noise when finger leaving the + * surface, otherwise cursor may jump to upper-left + * corner. + */ + packet[3] &= 0xf0; + } + abs_x = GET_ABS_X(packet); abs_y = GET_ABS_Y(packet); diff --git a/drivers/input/serio/ambakmi.c b/drivers/input/serio/ambakmi.c index 2ffd110bd5b..2e77246c2e5 100644 --- a/drivers/input/serio/ambakmi.c +++ b/drivers/input/serio/ambakmi.c @@ -72,7 +72,7 @@ static int amba_kmi_open(struct serio *io) unsigned int divisor; int ret; - ret = clk_enable(kmi->clk); + ret = clk_prepare_enable(kmi->clk); if (ret) goto out; @@ -92,7 +92,7 @@ static int amba_kmi_open(struct serio *io) return 0; clk_disable: - clk_disable(kmi->clk); + clk_disable_unprepare(kmi->clk); out: return ret; } @@ -104,7 +104,7 @@ static void amba_kmi_close(struct serio *io) writeb(0, KMICR); free_irq(kmi->irq, kmi); - clk_disable(kmi->clk); + clk_disable_unprepare(kmi->clk); } static int __devinit amba_kmi_probe(struct amba_device *dev, diff --git a/drivers/input/serio/i8042-x86ia64io.h b/drivers/input/serio/i8042-x86ia64io.h index 6918773ce02..d6cc77a53c7 100644 --- a/drivers/input/serio/i8042-x86ia64io.h +++ b/drivers/input/serio/i8042-x86ia64io.h @@ -335,6 +335,12 @@ static const struct dmi_system_id __initconst i8042_dmi_nomux_table[] = { }, { .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "TOSHIBA"), + DMI_MATCH(DMI_PRODUCT_NAME, "SATELLITE C850D"), + }, + }, + { + .matches = { DMI_MATCH(DMI_SYS_VENDOR, "ALIENWARE"), DMI_MATCH(DMI_PRODUCT_NAME, "Sentia"), }, diff --git a/drivers/input/touchscreen/edt-ft5x06.c b/drivers/input/touchscreen/edt-ft5x06.c index b06a5e3a665..64957770b52 100644 --- a/drivers/input/touchscreen/edt-ft5x06.c +++ b/drivers/input/touchscreen/edt-ft5x06.c @@ -566,9 +566,12 @@ static ssize_t edt_ft5x06_debugfs_raw_data_read(struct file *file, } read = min_t(size_t, count, tsdata->raw_bufsize - *off); - error = copy_to_user(buf, tsdata->raw_buffer + *off, read); - if (!error) - *off += read; + if (copy_to_user(buf, tsdata->raw_buffer + *off, read)) { + error = -EFAULT; + goto out; + } + + *off += read; out: mutex_unlock(&tsdata->mutex); return error ?: read; diff --git a/drivers/input/touchscreen/usbtouchscreen.c b/drivers/input/touchscreen/usbtouchscreen.c index e32709e0dd6..721fdb3597c 100644 --- a/drivers/input/touchscreen/usbtouchscreen.c +++ b/drivers/input/touchscreen/usbtouchscreen.c @@ -304,6 +304,45 @@ static int e2i_read_data(struct usbtouch_usb *dev, unsigned char *pkt) #define EGALAX_PKT_TYPE_REPT 0x80 #define EGALAX_PKT_TYPE_DIAG 0x0A +static int egalax_init(struct usbtouch_usb *usbtouch) +{ + int ret, i; + unsigned char *buf; + struct usb_device *udev = interface_to_usbdev(usbtouch->interface); + + /* + * An eGalax diagnostic packet kicks the device into using the right + * protocol. We send a "check active" packet. The response will be + * read later and ignored. + */ + + buf = kmalloc(3, GFP_KERNEL); + if (!buf) + return -ENOMEM; + + buf[0] = EGALAX_PKT_TYPE_DIAG; + buf[1] = 1; /* length */ + buf[2] = 'A'; /* command - check active */ + + for (i = 0; i < 3; i++) { + ret = usb_control_msg(udev, usb_sndctrlpipe(udev, 0), + 0, + USB_DIR_OUT | USB_TYPE_VENDOR | USB_RECIP_DEVICE, + 0, 0, buf, 3, + USB_CTRL_SET_TIMEOUT); + if (ret >= 0) { + ret = 0; + break; + } + if (ret != -EPIPE) + break; + } + + kfree(buf); + + return ret; +} + static int egalax_read_data(struct usbtouch_usb *dev, unsigned char *pkt) { if ((pkt[0] & EGALAX_PKT_TYPE_MASK) != EGALAX_PKT_TYPE_REPT) @@ -1056,6 +1095,7 @@ static struct usbtouch_device_info usbtouch_dev_info[] = { .process_pkt = usbtouch_process_multi, .get_pkt_len = egalax_get_pkt_len, .read_data = egalax_read_data, + .init = egalax_init, }, #endif diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c index b64502dfa9f..e89daf1b21b 100644 --- a/drivers/iommu/amd_iommu.c +++ b/drivers/iommu/amd_iommu.c @@ -266,7 +266,7 @@ static void swap_pci_ref(struct pci_dev **from, struct pci_dev *to) static int iommu_init_device(struct device *dev) { - struct pci_dev *dma_pdev, *pdev = to_pci_dev(dev); + struct pci_dev *dma_pdev = NULL, *pdev = to_pci_dev(dev); struct iommu_dev_data *dev_data; struct iommu_group *group; u16 alias; @@ -293,7 +293,9 @@ static int iommu_init_device(struct device *dev) dev_data->alias_data = alias_data; dma_pdev = pci_get_bus_and_slot(alias >> 8, alias & 0xff); - } else + } + + if (dma_pdev == NULL) dma_pdev = pci_dev_get(pdev); /* Account for quirked devices */ diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c index d8abb90a6c2..034233eefc8 100644 --- a/drivers/md/dm-mpath.c +++ b/drivers/md/dm-mpath.c @@ -1555,6 +1555,7 @@ static int multipath_ioctl(struct dm_target *ti, unsigned int cmd, unsigned long arg) { struct multipath *m = ti->private; + struct pgpath *pgpath; struct block_device *bdev; fmode_t mode; unsigned long flags; @@ -1570,12 +1571,14 @@ again: if (!m->current_pgpath) __choose_pgpath(m, 0); - if (m->current_pgpath) { - bdev = m->current_pgpath->path.dev->bdev; - mode = m->current_pgpath->path.dev->mode; + pgpath = m->current_pgpath; + + if (pgpath) { + bdev = pgpath->path.dev->bdev; + mode = pgpath->path.dev->mode; } - if (m->queue_io) + if ((pgpath && m->queue_io) || (!pgpath && m->queue_if_no_path)) r = -EAGAIN; else if (!bdev) r = -EIO; diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index f90069029aa..100368eb799 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -1212,6 +1212,41 @@ struct dm_target *dm_table_find_target(struct dm_table *t, sector_t sector) return &t->targets[(KEYS_PER_NODE * n) + k]; } +static int count_device(struct dm_target *ti, struct dm_dev *dev, + sector_t start, sector_t len, void *data) +{ + unsigned *num_devices = data; + + (*num_devices)++; + + return 0; +} + +/* + * Check whether a table has no data devices attached using each + * target's iterate_devices method. + * Returns false if the result is unknown because a target doesn't + * support iterate_devices. + */ +bool dm_table_has_no_data_devices(struct dm_table *table) +{ + struct dm_target *uninitialized_var(ti); + unsigned i = 0, num_devices = 0; + + while (i < dm_table_get_num_targets(table)) { + ti = dm_table_get_target(table, i++); + + if (!ti->type->iterate_devices) + return false; + + ti->type->iterate_devices(ti, count_device, &num_devices); + if (num_devices) + return false; + } + + return true; +} + /* * Establish the new table's queue_limits and validate them. */ @@ -1354,17 +1389,25 @@ static int device_is_nonrot(struct dm_target *ti, struct dm_dev *dev, return q && blk_queue_nonrot(q); } -static bool dm_table_is_nonrot(struct dm_table *t) +static int device_is_not_random(struct dm_target *ti, struct dm_dev *dev, + sector_t start, sector_t len, void *data) +{ + struct request_queue *q = bdev_get_queue(dev->bdev); + + return q && !blk_queue_add_random(q); +} + +static bool dm_table_all_devices_attribute(struct dm_table *t, + iterate_devices_callout_fn func) { struct dm_target *ti; unsigned i = 0; - /* Ensure that all underlying device are non-rotational. */ while (i < dm_table_get_num_targets(t)) { ti = dm_table_get_target(t, i++); if (!ti->type->iterate_devices || - !ti->type->iterate_devices(ti, device_is_nonrot, NULL)) + !ti->type->iterate_devices(ti, func, NULL)) return 0; } @@ -1396,7 +1439,8 @@ void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q, if (!dm_table_discard_zeroes_data(t)) q->limits.discard_zeroes_data = 0; - if (dm_table_is_nonrot(t)) + /* Ensure that all underlying devices are non-rotational. */ + if (dm_table_all_devices_attribute(t, device_is_nonrot)) queue_flag_set_unlocked(QUEUE_FLAG_NONROT, q); else queue_flag_clear_unlocked(QUEUE_FLAG_NONROT, q); @@ -1404,6 +1448,15 @@ void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q, dm_table_set_integrity(t); /* + * Determine whether or not this queue's I/O timings contribute + * to the entropy pool, Only request-based targets use this. + * Clear QUEUE_FLAG_ADD_RANDOM if any underlying device does not + * have it set. + */ + if (blk_queue_add_random(q) && dm_table_all_devices_attribute(t, device_is_not_random)) + queue_flag_clear_unlocked(QUEUE_FLAG_ADD_RANDOM, q); + + /* * QUEUE_FLAG_STACKABLE must be set after all queue settings are * visible to other CPUs because, once the flag is set, incoming bios * are processed by request-based dm, which refers to the queue diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c index af1fc3b2c2a..c29410af1e2 100644 --- a/drivers/md/dm-thin.c +++ b/drivers/md/dm-thin.c @@ -509,9 +509,9 @@ enum pool_mode { struct pool_features { enum pool_mode mode; - unsigned zero_new_blocks:1; - unsigned discard_enabled:1; - unsigned discard_passdown:1; + bool zero_new_blocks:1; + bool discard_enabled:1; + bool discard_passdown:1; }; struct thin_c; @@ -580,7 +580,8 @@ struct pool_c { struct dm_target_callbacks callbacks; dm_block_t low_water_blocks; - struct pool_features pf; + struct pool_features requested_pf; /* Features requested during table load */ + struct pool_features adjusted_pf; /* Features used after adjusting for constituent devices */ }; /* @@ -1839,6 +1840,47 @@ static void __requeue_bios(struct pool *pool) /*---------------------------------------------------------------- * Binding of control targets to a pool object *--------------------------------------------------------------*/ +static bool data_dev_supports_discard(struct pool_c *pt) +{ + struct request_queue *q = bdev_get_queue(pt->data_dev->bdev); + + return q && blk_queue_discard(q); +} + +/* + * If discard_passdown was enabled verify that the data device + * supports discards. Disable discard_passdown if not. + */ +static void disable_passdown_if_not_supported(struct pool_c *pt) +{ + struct pool *pool = pt->pool; + struct block_device *data_bdev = pt->data_dev->bdev; + struct queue_limits *data_limits = &bdev_get_queue(data_bdev)->limits; + sector_t block_size = pool->sectors_per_block << SECTOR_SHIFT; + const char *reason = NULL; + char buf[BDEVNAME_SIZE]; + + if (!pt->adjusted_pf.discard_passdown) + return; + + if (!data_dev_supports_discard(pt)) + reason = "discard unsupported"; + + else if (data_limits->max_discard_sectors < pool->sectors_per_block) + reason = "max discard sectors smaller than a block"; + + else if (data_limits->discard_granularity > block_size) + reason = "discard granularity larger than a block"; + + else if (block_size & (data_limits->discard_granularity - 1)) + reason = "discard granularity not a factor of block size"; + + if (reason) { + DMWARN("Data device (%s) %s: Disabling discard passdown.", bdevname(data_bdev, buf), reason); + pt->adjusted_pf.discard_passdown = false; + } +} + static int bind_control_target(struct pool *pool, struct dm_target *ti) { struct pool_c *pt = ti->private; @@ -1847,31 +1889,16 @@ static int bind_control_target(struct pool *pool, struct dm_target *ti) * We want to make sure that degraded pools are never upgraded. */ enum pool_mode old_mode = pool->pf.mode; - enum pool_mode new_mode = pt->pf.mode; + enum pool_mode new_mode = pt->adjusted_pf.mode; if (old_mode > new_mode) new_mode = old_mode; pool->ti = ti; pool->low_water_blocks = pt->low_water_blocks; - pool->pf = pt->pf; - set_pool_mode(pool, new_mode); + pool->pf = pt->adjusted_pf; - /* - * If discard_passdown was enabled verify that the data device - * supports discards. Disable discard_passdown if not; otherwise - * -EOPNOTSUPP will be returned. - */ - /* FIXME: pull this out into a sep fn. */ - if (pt->pf.discard_passdown) { - struct request_queue *q = bdev_get_queue(pt->data_dev->bdev); - if (!q || !blk_queue_discard(q)) { - char buf[BDEVNAME_SIZE]; - DMWARN("Discard unsupported by data device (%s): Disabling discard passdown.", - bdevname(pt->data_dev->bdev, buf)); - pool->pf.discard_passdown = 0; - } - } + set_pool_mode(pool, new_mode); return 0; } @@ -1889,9 +1916,9 @@ static void unbind_control_target(struct pool *pool, struct dm_target *ti) static void pool_features_init(struct pool_features *pf) { pf->mode = PM_WRITE; - pf->zero_new_blocks = 1; - pf->discard_enabled = 1; - pf->discard_passdown = 1; + pf->zero_new_blocks = true; + pf->discard_enabled = true; + pf->discard_passdown = true; } static void __pool_destroy(struct pool *pool) @@ -2119,13 +2146,13 @@ static int parse_pool_features(struct dm_arg_set *as, struct pool_features *pf, argc--; if (!strcasecmp(arg_name, "skip_block_zeroing")) - pf->zero_new_blocks = 0; + pf->zero_new_blocks = false; else if (!strcasecmp(arg_name, "ignore_discard")) - pf->discard_enabled = 0; + pf->discard_enabled = false; else if (!strcasecmp(arg_name, "no_discard_passdown")) - pf->discard_passdown = 0; + pf->discard_passdown = false; else if (!strcasecmp(arg_name, "read_only")) pf->mode = PM_READ_ONLY; @@ -2259,8 +2286,9 @@ static int pool_ctr(struct dm_target *ti, unsigned argc, char **argv) pt->metadata_dev = metadata_dev; pt->data_dev = data_dev; pt->low_water_blocks = low_water_blocks; - pt->pf = pf; + pt->adjusted_pf = pt->requested_pf = pf; ti->num_flush_requests = 1; + /* * Only need to enable discards if the pool should pass * them down to the data device. The thin device's discard @@ -2268,12 +2296,14 @@ static int pool_ctr(struct dm_target *ti, unsigned argc, char **argv) */ if (pf.discard_enabled && pf.discard_passdown) { ti->num_discard_requests = 1; + /* * Setting 'discards_supported' circumvents the normal * stacking of discard limits (this keeps the pool and * thin devices' discard limits consistent). */ ti->discards_supported = true; + ti->discard_zeroes_data_unsupported = true; } ti->private = pt; @@ -2703,7 +2733,7 @@ static int pool_status(struct dm_target *ti, status_type_t type, format_dev_t(buf2, pt->data_dev->bdev->bd_dev), (unsigned long)pool->sectors_per_block, (unsigned long long)pt->low_water_blocks); - emit_flags(&pt->pf, result, sz, maxlen); + emit_flags(&pt->requested_pf, result, sz, maxlen); break; } @@ -2732,20 +2762,21 @@ static int pool_merge(struct dm_target *ti, struct bvec_merge_data *bvm, return min(max_size, q->merge_bvec_fn(q, bvm, biovec)); } -static void set_discard_limits(struct pool *pool, struct queue_limits *limits) +static void set_discard_limits(struct pool_c *pt, struct queue_limits *limits) { - /* - * FIXME: these limits may be incompatible with the pool's data device - */ + struct pool *pool = pt->pool; + struct queue_limits *data_limits; + limits->max_discard_sectors = pool->sectors_per_block; /* - * This is just a hint, and not enforced. We have to cope with - * bios that cover a block partially. A discard that spans a block - * boundary is not sent to this target. + * discard_granularity is just a hint, and not enforced. */ - limits->discard_granularity = pool->sectors_per_block << SECTOR_SHIFT; - limits->discard_zeroes_data = pool->pf.zero_new_blocks; + if (pt->adjusted_pf.discard_passdown) { + data_limits = &bdev_get_queue(pt->data_dev->bdev)->limits; + limits->discard_granularity = data_limits->discard_granularity; + } else + limits->discard_granularity = pool->sectors_per_block << SECTOR_SHIFT; } static void pool_io_hints(struct dm_target *ti, struct queue_limits *limits) @@ -2755,15 +2786,25 @@ static void pool_io_hints(struct dm_target *ti, struct queue_limits *limits) blk_limits_io_min(limits, 0); blk_limits_io_opt(limits, pool->sectors_per_block << SECTOR_SHIFT); - if (pool->pf.discard_enabled) - set_discard_limits(pool, limits); + + /* + * pt->adjusted_pf is a staging area for the actual features to use. + * They get transferred to the live pool in bind_control_target() + * called from pool_preresume(). + */ + if (!pt->adjusted_pf.discard_enabled) + return; + + disable_passdown_if_not_supported(pt); + + set_discard_limits(pt, limits); } static struct target_type pool_target = { .name = "thin-pool", .features = DM_TARGET_SINGLETON | DM_TARGET_ALWAYS_WRITEABLE | DM_TARGET_IMMUTABLE, - .version = {1, 3, 0}, + .version = {1, 4, 0}, .module = THIS_MODULE, .ctr = pool_ctr, .dtr = pool_dtr, @@ -3042,19 +3083,19 @@ static int thin_iterate_devices(struct dm_target *ti, return 0; } +/* + * A thin device always inherits its queue limits from its pool. + */ static void thin_io_hints(struct dm_target *ti, struct queue_limits *limits) { struct thin_c *tc = ti->private; - struct pool *pool = tc->pool; - blk_limits_io_min(limits, 0); - blk_limits_io_opt(limits, pool->sectors_per_block << SECTOR_SHIFT); - set_discard_limits(pool, limits); + *limits = bdev_get_queue(tc->pool_dev->bdev)->limits; } static struct target_type thin_target = { .name = "thin", - .version = {1, 3, 0}, + .version = {1, 4, 0}, .module = THIS_MODULE, .ctr = thin_ctr, .dtr = thin_dtr, diff --git a/drivers/md/dm-verity.c b/drivers/md/dm-verity.c index 254d19268ad..892ae2766aa 100644 --- a/drivers/md/dm-verity.c +++ b/drivers/md/dm-verity.c @@ -718,8 +718,8 @@ static int verity_ctr(struct dm_target *ti, unsigned argc, char **argv) v->hash_dev_block_bits = ffs(num) - 1; if (sscanf(argv[5], "%llu%c", &num_ll, &dummy) != 1 || - num_ll << (v->data_dev_block_bits - SECTOR_SHIFT) != - (sector_t)num_ll << (v->data_dev_block_bits - SECTOR_SHIFT)) { + (sector_t)(num_ll << (v->data_dev_block_bits - SECTOR_SHIFT)) + >> (v->data_dev_block_bits - SECTOR_SHIFT) != num_ll) { ti->error = "Invalid data blocks"; r = -EINVAL; goto bad; @@ -733,8 +733,8 @@ static int verity_ctr(struct dm_target *ti, unsigned argc, char **argv) } if (sscanf(argv[6], "%llu%c", &num_ll, &dummy) != 1 || - num_ll << (v->hash_dev_block_bits - SECTOR_SHIFT) != - (sector_t)num_ll << (v->hash_dev_block_bits - SECTOR_SHIFT)) { + (sector_t)(num_ll << (v->hash_dev_block_bits - SECTOR_SHIFT)) + >> (v->hash_dev_block_bits - SECTOR_SHIFT) != num_ll) { ti->error = "Invalid hash start"; r = -EINVAL; goto bad; diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 4e09b6ff5b4..67ffa391edc 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -865,10 +865,14 @@ static void dm_done(struct request *clone, int error, bool mapped) { int r = error; struct dm_rq_target_io *tio = clone->end_io_data; - dm_request_endio_fn rq_end_io = tio->ti->type->rq_end_io; + dm_request_endio_fn rq_end_io = NULL; - if (mapped && rq_end_io) - r = rq_end_io(tio->ti, clone, error, &tio->info); + if (tio->ti) { + rq_end_io = tio->ti->type->rq_end_io; + + if (mapped && rq_end_io) + r = rq_end_io(tio->ti, clone, error, &tio->info); + } if (r <= 0) /* The target wants to complete the I/O */ @@ -1588,15 +1592,6 @@ static int map_request(struct dm_target *ti, struct request *clone, int r, requeued = 0; struct dm_rq_target_io *tio = clone->end_io_data; - /* - * Hold the md reference here for the in-flight I/O. - * We can't rely on the reference count by device opener, - * because the device may be closed during the request completion - * when all bios are completed. - * See the comment in rq_completed() too. - */ - dm_get(md); - tio->ti = ti; r = ti->type->map_rq(ti, clone, &tio->info); switch (r) { @@ -1628,6 +1623,26 @@ static int map_request(struct dm_target *ti, struct request *clone, return requeued; } +static struct request *dm_start_request(struct mapped_device *md, struct request *orig) +{ + struct request *clone; + + blk_start_request(orig); + clone = orig->special; + atomic_inc(&md->pending[rq_data_dir(clone)]); + + /* + * Hold the md reference here for the in-flight I/O. + * We can't rely on the reference count by device opener, + * because the device may be closed during the request completion + * when all bios are completed. + * See the comment in rq_completed() too. + */ + dm_get(md); + + return clone; +} + /* * q->request_fn for request-based dm. * Called with the queue lock held. @@ -1657,14 +1672,21 @@ static void dm_request_fn(struct request_queue *q) pos = blk_rq_pos(rq); ti = dm_table_find_target(map, pos); - BUG_ON(!dm_target_is_valid(ti)); + if (!dm_target_is_valid(ti)) { + /* + * Must perform setup, that dm_done() requires, + * before calling dm_kill_unmapped_request + */ + DMERR_LIMIT("request attempted access beyond the end of device"); + clone = dm_start_request(md, rq); + dm_kill_unmapped_request(clone, -EIO); + continue; + } if (ti->type->busy && ti->type->busy(ti)) goto delay_and_out; - blk_start_request(rq); - clone = rq->special; - atomic_inc(&md->pending[rq_data_dir(clone)]); + clone = dm_start_request(md, rq); spin_unlock(q->queue_lock); if (map_request(ti, clone, md)) @@ -1684,8 +1706,6 @@ delay_and_out: blk_delay_queue(q, HZ / 10); out: dm_table_put(map); - - return; } int dm_underlying_device_busy(struct request_queue *q) @@ -2409,7 +2429,7 @@ static void dm_queue_flush(struct mapped_device *md) */ struct dm_table *dm_swap_table(struct mapped_device *md, struct dm_table *table) { - struct dm_table *map = ERR_PTR(-EINVAL); + struct dm_table *live_map, *map = ERR_PTR(-EINVAL); struct queue_limits limits; int r; @@ -2419,6 +2439,19 @@ struct dm_table *dm_swap_table(struct mapped_device *md, struct dm_table *table) if (!dm_suspended_md(md)) goto out; + /* + * If the new table has no data devices, retain the existing limits. + * This helps multipath with queue_if_no_path if all paths disappear, + * then new I/O is queued based on these limits, and then some paths + * reappear. + */ + if (dm_table_has_no_data_devices(table)) { + live_map = dm_get_live_table(md); + if (live_map) + limits = md->queue->limits; + dm_table_put(live_map); + } + r = dm_calculate_queue_limits(table, &limits); if (r) { map = ERR_PTR(r); diff --git a/drivers/md/dm.h b/drivers/md/dm.h index 52eef493d26..6a99fefaa74 100644 --- a/drivers/md/dm.h +++ b/drivers/md/dm.h @@ -54,6 +54,7 @@ void dm_table_event_callback(struct dm_table *t, void (*fn)(void *), void *context); struct dm_target *dm_table_get_target(struct dm_table *t, unsigned int index); struct dm_target *dm_table_find_target(struct dm_table *t, sector_t sector); +bool dm_table_has_no_data_devices(struct dm_table *table); int dm_calculate_queue_limits(struct dm_table *table, struct queue_limits *limits); void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q, diff --git a/drivers/md/md.c b/drivers/md/md.c index 3f6203a4c7e..308e87b417e 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -7619,6 +7619,8 @@ static int remove_and_add_spares(struct mddev *mddev) } } } + if (removed) + set_bit(MD_CHANGE_DEVS, &mddev->flags); return spares; } @@ -7632,9 +7634,11 @@ static void reap_sync_thread(struct mddev *mddev) !test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery)) { /* success...*/ /* activate any spares */ - if (mddev->pers->spare_active(mddev)) + if (mddev->pers->spare_active(mddev)) { sysfs_notify(&mddev->kobj, NULL, "degraded"); + set_bit(MD_CHANGE_DEVS, &mddev->flags); + } } if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) && mddev->pers->finish_reshape) diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index 1c2eb38f3c5..0138a727c1f 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -1512,14 +1512,16 @@ static int _enough(struct r10conf *conf, struct geom *geo, int ignore) do { int n = conf->copies; int cnt = 0; + int this = first; while (n--) { - if (conf->mirrors[first].rdev && - first != ignore) + if (conf->mirrors[this].rdev && + this != ignore) cnt++; - first = (first+1) % geo->raid_disks; + this = (this+1) % geo->raid_disks; } if (cnt == 0) return 0; + first = (first + geo->near_copies) % geo->raid_disks; } while (first != 0); return 1; } diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index adda94df5eb..0689173fd9f 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -393,6 +393,8 @@ static int calc_degraded(struct r5conf *conf) degraded = 0; for (i = 0; i < conf->previous_raid_disks; i++) { struct md_rdev *rdev = rcu_dereference(conf->disks[i].rdev); + if (rdev && test_bit(Faulty, &rdev->flags)) + rdev = rcu_dereference(conf->disks[i].replacement); if (!rdev || test_bit(Faulty, &rdev->flags)) degraded++; else if (test_bit(In_sync, &rdev->flags)) @@ -417,6 +419,8 @@ static int calc_degraded(struct r5conf *conf) degraded2 = 0; for (i = 0; i < conf->raid_disks; i++) { struct md_rdev *rdev = rcu_dereference(conf->disks[i].rdev); + if (rdev && test_bit(Faulty, &rdev->flags)) + rdev = rcu_dereference(conf->disks[i].replacement); if (!rdev || test_bit(Faulty, &rdev->flags)) degraded2++; else if (test_bit(In_sync, &rdev->flags)) @@ -1587,6 +1591,7 @@ static int resize_stripes(struct r5conf *conf, int newsize) #ifdef CONFIG_MULTICORE_RAID456 init_waitqueue_head(&nsh->ops.wait_for_ops); #endif + spin_lock_init(&nsh->stripe_lock); list_add(&nsh->lru, &newstripes); } @@ -4192,7 +4197,7 @@ static void make_request(struct mddev *mddev, struct bio * bi) finish_wait(&conf->wait_for_overlap, &w); set_bit(STRIPE_HANDLE, &sh->state); clear_bit(STRIPE_DELAYED, &sh->state); - if ((bi->bi_rw & REQ_NOIDLE) && + if ((bi->bi_rw & REQ_SYNC) && !test_and_set_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) atomic_inc(&conf->preread_active_stripes); release_stripe_plug(mddev, sh); diff --git a/drivers/mtd/mtdchar.c b/drivers/mtd/mtdchar.c index f2f482bec57..a6e74514e66 100644 --- a/drivers/mtd/mtdchar.c +++ b/drivers/mtd/mtdchar.c @@ -1123,6 +1123,33 @@ static unsigned long mtdchar_get_unmapped_area(struct file *file, } #endif +static inline unsigned long get_vm_size(struct vm_area_struct *vma) +{ + return vma->vm_end - vma->vm_start; +} + +static inline resource_size_t get_vm_offset(struct vm_area_struct *vma) +{ + return (resource_size_t) vma->vm_pgoff << PAGE_SHIFT; +} + +/* + * Set a new vm offset. + * + * Verify that the incoming offset really works as a page offset, + * and that the offset and size fit in a resource_size_t. + */ +static inline int set_vm_offset(struct vm_area_struct *vma, resource_size_t off) +{ + pgoff_t pgoff = off >> PAGE_SHIFT; + if (off != (resource_size_t) pgoff << PAGE_SHIFT) + return -EINVAL; + if (off + get_vm_size(vma) - 1 < off) + return -EINVAL; + vma->vm_pgoff = pgoff; + return 0; +} + /* * set up a mapping for shared memory segments */ @@ -1132,20 +1159,29 @@ static int mtdchar_mmap(struct file *file, struct vm_area_struct *vma) struct mtd_file_info *mfi = file->private_data; struct mtd_info *mtd = mfi->mtd; struct map_info *map = mtd->priv; - unsigned long start; - unsigned long off; - u32 len; + resource_size_t start, off; + unsigned long len, vma_len; if (mtd->type == MTD_RAM || mtd->type == MTD_ROM) { - off = vma->vm_pgoff << PAGE_SHIFT; + off = get_vm_offset(vma); start = map->phys; len = PAGE_ALIGN((start & ~PAGE_MASK) + map->size); start &= PAGE_MASK; - if ((vma->vm_end - vma->vm_start + off) > len) + vma_len = get_vm_size(vma); + + /* Overflow in off+len? */ + if (vma_len + off < off) + return -EINVAL; + /* Does it fit in the mapping? */ + if (vma_len + off > len) return -EINVAL; off += start; - vma->vm_pgoff = off >> PAGE_SHIFT; + /* Did that overflow? */ + if (off < start) + return -EINVAL; + if (set_vm_offset(vma, off) < 0) + return -EINVAL; vma->vm_flags |= VM_IO | VM_RESERVED; #ifdef pgprot_noncached diff --git a/drivers/net/can/janz-ican3.c b/drivers/net/can/janz-ican3.c index 98ee4381991..7edadee487b 100644 --- a/drivers/net/can/janz-ican3.c +++ b/drivers/net/can/janz-ican3.c @@ -1391,7 +1391,6 @@ static irqreturn_t ican3_irq(int irq, void *dev_id) */ static int ican3_reset_module(struct ican3_dev *mod) { - u8 val = 1 << mod->num; unsigned long start; u8 runold, runnew; @@ -1405,8 +1404,7 @@ static int ican3_reset_module(struct ican3_dev *mod) runold = ioread8(mod->dpm + TARGET_RUNNING); /* reset the module */ - iowrite8(val, &mod->ctrl->reset_assert); - iowrite8(val, &mod->ctrl->reset_deassert); + iowrite8(0x00, &mod->dpmctrl->hwreset); /* wait until the module has finished resetting and is running */ start = jiffies; diff --git a/drivers/net/can/ti_hecc.c b/drivers/net/can/ti_hecc.c index 527dbcf9533..9ded21e79db 100644 --- a/drivers/net/can/ti_hecc.c +++ b/drivers/net/can/ti_hecc.c @@ -984,12 +984,12 @@ static int __devexit ti_hecc_remove(struct platform_device *pdev) struct net_device *ndev = platform_get_drvdata(pdev); struct ti_hecc_priv *priv = netdev_priv(ndev); + unregister_candev(ndev); clk_disable(priv->clk); clk_put(priv->clk); res = platform_get_resource(pdev, IORESOURCE_MEM, 0); iounmap(priv->base); release_mem_region(res->start, resource_size(res)); - unregister_candev(ndev); free_candev(ndev); platform_set_drvdata(pdev, NULL); diff --git a/drivers/net/ethernet/broadcom/bnx2.c b/drivers/net/ethernet/broadcom/bnx2.c index 79cebd8525c..e48312f2305 100644 --- a/drivers/net/ethernet/broadcom/bnx2.c +++ b/drivers/net/ethernet/broadcom/bnx2.c @@ -8564,7 +8564,7 @@ bnx2_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) return 0; error: - iounmap(bp->regview); + pci_iounmap(pdev, bp->regview); pci_release_regions(pdev); pci_disable_device(pdev); pci_set_drvdata(pdev, NULL); diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c index af20c6ee2cd..e8e97a7d1d0 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c @@ -662,14 +662,16 @@ void bnx2x_csum_validate(struct sk_buff *skb, union eth_rx_cqe *cqe, struct bnx2x_fastpath *fp, struct bnx2x_eth_q_stats *qstats) { - /* Do nothing if no IP/L4 csum validation was done */ - + /* Do nothing if no L4 csum validation was done. + * We do not check whether IP csum was validated. For IPv4 we assume + * that if the card got as far as validating the L4 csum, it also + * validated the IP csum. IPv6 has no IP csum. + */ 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)) + 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 L4 validation was done, check if an error was found. */ if (cqe->fast_path_cqe.type_error_flags & (ETH_FAST_PATH_RX_CQE_IP_BAD_XSUM_FLG | diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c index 211753e01f8..0875ecfe337 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c @@ -9831,12 +9831,13 @@ static void __devinit bnx2x_get_igu_cam_info(struct bnx2x *bp) } #ifdef CONFIG_PCI_MSI - /* - * It's expected that number of CAM entries for this functions is equal - * to the number evaluated based on the MSI-X table size. We want a - * harsh warning if these values are different! + /* Due to new PF resource allocation by MFW T7.4 and above, it's + * optional that number of CAM entries will not be equal to the value + * advertised in PCI. + * Driver should use the minimal value of both as the actual status + * block count */ - WARN_ON(bp->igu_sb_cnt != igu_sb_cnt); + bp->igu_sb_cnt = min_t(int, bp->igu_sb_cnt, igu_sb_cnt); #endif if (igu_sb_cnt == 0) diff --git a/drivers/net/ethernet/cadence/at91_ether.c b/drivers/net/ethernet/cadence/at91_ether.c index 77884191a8c..4e980a7886f 100644 --- a/drivers/net/ethernet/cadence/at91_ether.c +++ b/drivers/net/ethernet/cadence/at91_ether.c @@ -1086,7 +1086,7 @@ static int __init at91ether_probe(struct platform_device *pdev) /* Clock */ lp->ether_clk = clk_get(&pdev->dev, "ether_clk"); if (IS_ERR(lp->ether_clk)) { - res = -ENODEV; + res = PTR_ERR(lp->ether_clk); goto err_ioumap; } clk_enable(lp->ether_clk); diff --git a/drivers/net/ethernet/freescale/gianfar_ethtool.c b/drivers/net/ethernet/freescale/gianfar_ethtool.c index 8971921cc1c..ab6762caa95 100644 --- a/drivers/net/ethernet/freescale/gianfar_ethtool.c +++ b/drivers/net/ethernet/freescale/gianfar_ethtool.c @@ -1773,6 +1773,7 @@ static int gfar_get_nfc(struct net_device *dev, struct ethtool_rxnfc *cmd, } int gfar_phc_index = -1; +EXPORT_SYMBOL(gfar_phc_index); static int gfar_get_ts_info(struct net_device *dev, struct ethtool_ts_info *info) diff --git a/drivers/net/ethernet/freescale/gianfar_ptp.c b/drivers/net/ethernet/freescale/gianfar_ptp.c index c08e5d40fec..0daa66b8eca 100644 --- a/drivers/net/ethernet/freescale/gianfar_ptp.c +++ b/drivers/net/ethernet/freescale/gianfar_ptp.c @@ -515,7 +515,7 @@ static int gianfar_ptp_probe(struct platform_device *dev) err = PTR_ERR(etsects->clock); goto no_clock; } - gfar_phc_clock = ptp_clock_index(etsects->clock); + gfar_phc_index = ptp_clock_index(etsects->clock); dev_set_drvdata(&dev->dev, etsects); @@ -539,7 +539,7 @@ static int gianfar_ptp_remove(struct platform_device *dev) gfar_write(&etsects->regs->tmr_temask, 0); gfar_write(&etsects->regs->tmr_ctrl, 0); - gfar_phc_clock = -1; + gfar_phc_index = -1; ptp_clock_unregister(etsects->clock); iounmap(etsects->regs); release_resource(etsects->rsrc); diff --git a/drivers/net/ethernet/intel/e1000/e1000_main.c b/drivers/net/ethernet/intel/e1000/e1000_main.c index 3bfbb8df898..bde337ee1a3 100644 --- a/drivers/net/ethernet/intel/e1000/e1000_main.c +++ b/drivers/net/ethernet/intel/e1000/e1000_main.c @@ -3149,6 +3149,17 @@ static netdev_tx_t e1000_xmit_frame(struct sk_buff *skb, return NETDEV_TX_OK; } + /* On PCI/PCI-X HW, if packet size is less than ETH_ZLEN, + * packets may get corrupted during padding by HW. + * To WA this issue, pad all small packets manually. + */ + if (skb->len < ETH_ZLEN) { + if (skb_pad(skb, ETH_ZLEN - skb->len)) + return NETDEV_TX_OK; + skb->len = ETH_ZLEN; + skb_set_tail_pointer(skb, ETH_ZLEN); + } + mss = skb_shinfo(skb)->gso_size; /* The controller does a simple calculation to * make sure there is enough room in the FIFO before diff --git a/drivers/net/ethernet/mellanox/mlx4/icm.c b/drivers/net/ethernet/mellanox/mlx4/icm.c index daf41792366..31d02649be4 100644 --- a/drivers/net/ethernet/mellanox/mlx4/icm.c +++ b/drivers/net/ethernet/mellanox/mlx4/icm.c @@ -227,9 +227,10 @@ int mlx4_UNMAP_ICM_AUX(struct mlx4_dev *dev) MLX4_CMD_TIME_CLASS_B, MLX4_CMD_NATIVE); } -int mlx4_table_get(struct mlx4_dev *dev, struct mlx4_icm_table *table, int obj) +int mlx4_table_get(struct mlx4_dev *dev, struct mlx4_icm_table *table, u32 obj) { - int i = (obj & (table->num_obj - 1)) / (MLX4_TABLE_CHUNK_SIZE / table->obj_size); + u32 i = (obj & (table->num_obj - 1)) / + (MLX4_TABLE_CHUNK_SIZE / table->obj_size); int ret = 0; mutex_lock(&table->mutex); @@ -262,16 +263,18 @@ out: return ret; } -void mlx4_table_put(struct mlx4_dev *dev, struct mlx4_icm_table *table, int obj) +void mlx4_table_put(struct mlx4_dev *dev, struct mlx4_icm_table *table, u32 obj) { - int i; + u32 i; + u64 offset; i = (obj & (table->num_obj - 1)) / (MLX4_TABLE_CHUNK_SIZE / table->obj_size); mutex_lock(&table->mutex); if (--table->icm[i]->refcount == 0) { - mlx4_UNMAP_ICM(dev, table->virt + i * MLX4_TABLE_CHUNK_SIZE, + offset = (u64) i * MLX4_TABLE_CHUNK_SIZE; + mlx4_UNMAP_ICM(dev, table->virt + offset, MLX4_TABLE_CHUNK_SIZE / MLX4_ICM_PAGE_SIZE); mlx4_free_icm(dev, table->icm[i], table->coherent); table->icm[i] = NULL; @@ -280,9 +283,11 @@ void mlx4_table_put(struct mlx4_dev *dev, struct mlx4_icm_table *table, int obj) mutex_unlock(&table->mutex); } -void *mlx4_table_find(struct mlx4_icm_table *table, int obj, dma_addr_t *dma_handle) +void *mlx4_table_find(struct mlx4_icm_table *table, u32 obj, + dma_addr_t *dma_handle) { - int idx, offset, dma_offset, i; + int offset, dma_offset, i; + u64 idx; struct mlx4_icm_chunk *chunk; struct mlx4_icm *icm; struct page *page = NULL; @@ -292,7 +297,7 @@ void *mlx4_table_find(struct mlx4_icm_table *table, int obj, dma_addr_t *dma_han mutex_lock(&table->mutex); - idx = (obj & (table->num_obj - 1)) * table->obj_size; + idx = (u64) (obj & (table->num_obj - 1)) * table->obj_size; icm = table->icm[idx / MLX4_TABLE_CHUNK_SIZE]; dma_offset = offset = idx % MLX4_TABLE_CHUNK_SIZE; @@ -326,10 +331,11 @@ out: } int mlx4_table_get_range(struct mlx4_dev *dev, struct mlx4_icm_table *table, - int start, int end) + u32 start, u32 end) { int inc = MLX4_TABLE_CHUNK_SIZE / table->obj_size; - int i, err; + int err; + u32 i; for (i = start; i <= end; i += inc) { err = mlx4_table_get(dev, table, i); @@ -349,9 +355,9 @@ fail: } void mlx4_table_put_range(struct mlx4_dev *dev, struct mlx4_icm_table *table, - int start, int end) + u32 start, u32 end) { - int i; + u32 i; for (i = start; i <= end; i += MLX4_TABLE_CHUNK_SIZE / table->obj_size) mlx4_table_put(dev, table, i); diff --git a/drivers/net/ethernet/mellanox/mlx4/icm.h b/drivers/net/ethernet/mellanox/mlx4/icm.h index a67744f5350..dee67fa3910 100644 --- a/drivers/net/ethernet/mellanox/mlx4/icm.h +++ b/drivers/net/ethernet/mellanox/mlx4/icm.h @@ -71,17 +71,17 @@ struct mlx4_icm *mlx4_alloc_icm(struct mlx4_dev *dev, int npages, gfp_t gfp_mask, int coherent); void mlx4_free_icm(struct mlx4_dev *dev, struct mlx4_icm *icm, int coherent); -int mlx4_table_get(struct mlx4_dev *dev, struct mlx4_icm_table *table, int obj); -void mlx4_table_put(struct mlx4_dev *dev, struct mlx4_icm_table *table, int obj); +int mlx4_table_get(struct mlx4_dev *dev, struct mlx4_icm_table *table, u32 obj); +void mlx4_table_put(struct mlx4_dev *dev, struct mlx4_icm_table *table, u32 obj); int mlx4_table_get_range(struct mlx4_dev *dev, struct mlx4_icm_table *table, - int start, int end); + u32 start, u32 end); void mlx4_table_put_range(struct mlx4_dev *dev, struct mlx4_icm_table *table, - int start, int end); + u32 start, u32 end); int mlx4_init_icm_table(struct mlx4_dev *dev, struct mlx4_icm_table *table, u64 virt, int obj_size, u32 nobj, int reserved, int use_lowmem, int use_coherent); void mlx4_cleanup_icm_table(struct mlx4_dev *dev, struct mlx4_icm_table *table); -void *mlx4_table_find(struct mlx4_icm_table *table, int obj, dma_addr_t *dma_handle); +void *mlx4_table_find(struct mlx4_icm_table *table, u32 obj, dma_addr_t *dma_handle); static inline void mlx4_icm_first(struct mlx4_icm *icm, struct mlx4_icm_iter *iter) diff --git a/drivers/net/ethernet/octeon/octeon_mgmt.c b/drivers/net/ethernet/octeon/octeon_mgmt.c index c42bbb16cda..a688a2ddcfd 100644 --- a/drivers/net/ethernet/octeon/octeon_mgmt.c +++ b/drivers/net/ethernet/octeon/octeon_mgmt.c @@ -722,10 +722,8 @@ static int octeon_mgmt_init_phy(struct net_device *netdev) octeon_mgmt_adjust_link, 0, PHY_INTERFACE_MODE_MII); - if (IS_ERR(p->phydev)) { - p->phydev = NULL; + if (!p->phydev) return -1; - } phy_start_aneg(p->phydev); diff --git a/drivers/net/ethernet/pasemi/pasemi_mac.c b/drivers/net/ethernet/pasemi/pasemi_mac.c index e559dfa06d6..6fa74d530e4 100644 --- a/drivers/net/ethernet/pasemi/pasemi_mac.c +++ b/drivers/net/ethernet/pasemi/pasemi_mac.c @@ -1101,9 +1101,9 @@ static int pasemi_mac_phy_init(struct net_device *dev) phydev = of_phy_connect(dev, phy_dn, &pasemi_adjust_link, 0, PHY_INTERFACE_MODE_SGMII); - if (IS_ERR(phydev)) { + if (!phydev) { printk(KERN_ERR "%s: Could not attach to phy\n", dev->name); - return PTR_ERR(phydev); + return -ENODEV; } mac->phydev = phydev; diff --git a/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c b/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c index 342b3a79bd0..a77c558d8f4 100644 --- a/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c +++ b/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c @@ -1378,6 +1378,10 @@ static void netxen_mask_aer_correctable(struct netxen_adapter *adapter) struct pci_dev *root = pdev->bus->self; u32 aer_pos; + /* root bus? */ + if (!root) + return; + if (adapter->ahw.board_type != NETXEN_BRDTYPE_P3_4_GB_MM && adapter->ahw.board_type != NETXEN_BRDTYPE_P3_10G_TP) return; diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ctx.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ctx.c index b8ead696141..2a179d08720 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ctx.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ctx.c @@ -15,7 +15,7 @@ qlcnic_poll_rsp(struct qlcnic_adapter *adapter) do { /* give atleast 1ms for firmware to respond */ - msleep(1); + mdelay(1); if (++timeout > QLCNIC_OS_CRB_RETRY_COUNT) return QLCNIC_CDRP_RSP_TIMEOUT; @@ -601,7 +601,7 @@ void qlcnic_fw_destroy_ctx(struct qlcnic_adapter *adapter) qlcnic_fw_cmd_destroy_tx_ctx(adapter); /* Allow dma queues to drain after context reset */ - msleep(20); + mdelay(20); } } diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index c136162e647..3be88331d17 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -1066,7 +1066,7 @@ static int stmmac_open(struct net_device *dev) } else priv->tm->enable = 1; #endif - clk_enable(priv->stmmac_clk); + clk_prepare_enable(priv->stmmac_clk); stmmac_check_ether_addr(priv); @@ -1188,7 +1188,7 @@ open_error: if (priv->phydev) phy_disconnect(priv->phydev); - clk_disable(priv->stmmac_clk); + clk_disable_unprepare(priv->stmmac_clk); return ret; } @@ -1246,7 +1246,7 @@ static int stmmac_release(struct net_device *dev) #ifdef CONFIG_STMMAC_DEBUG_FS stmmac_exit_fs(); #endif - clk_disable(priv->stmmac_clk); + clk_disable_unprepare(priv->stmmac_clk); return 0; } @@ -2178,7 +2178,7 @@ int stmmac_suspend(struct net_device *ndev) else { stmmac_set_mac(priv->ioaddr, false); /* Disable clock in case of PWM is off */ - clk_disable(priv->stmmac_clk); + clk_disable_unprepare(priv->stmmac_clk); } spin_unlock_irqrestore(&priv->lock, flags); return 0; @@ -2203,7 +2203,7 @@ int stmmac_resume(struct net_device *ndev) priv->hw->mac->pmt(priv->ioaddr, 0); else /* enable the clk prevously disabled */ - clk_enable(priv->stmmac_clk); + clk_prepare_enable(priv->stmmac_clk); netif_device_attach(ndev); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_timer.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_timer.c index 2a0e1abde7e..4ccd4e2977b 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_timer.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_timer.c @@ -97,19 +97,19 @@ static struct clk *timer_clock; static void stmmac_tmu_start(unsigned int new_freq) { clk_set_rate(timer_clock, new_freq); - clk_enable(timer_clock); + clk_prepare_enable(timer_clock); } static void stmmac_tmu_stop(void) { - clk_disable(timer_clock); + clk_disable_unprepare(timer_clock); } int stmmac_open_ext_timer(struct net_device *dev, struct stmmac_timer *tm) { timer_clock = clk_get(NULL, TMU_CHANNEL); - if (timer_clock == NULL) + if (IS_ERR(timer_clock)) return -1; if (tmu2_register_user(stmmac_timer_handler, (void *)dev) < 0) { @@ -126,7 +126,7 @@ int stmmac_open_ext_timer(struct net_device *dev, struct stmmac_timer *tm) int stmmac_close_ext_timer(void) { - clk_disable(timer_clock); + clk_disable_unprepare(timer_clock); tmu2_unregister_user(); clk_put(timer_clock); return 0; diff --git a/drivers/net/irda/sh_sir.c b/drivers/net/irda/sh_sir.c index 256eddf1f75..79510942556 100644 --- a/drivers/net/irda/sh_sir.c +++ b/drivers/net/irda/sh_sir.c @@ -280,7 +280,7 @@ static int sh_sir_set_baudrate(struct sh_sir_self *self, u32 baudrate) } clk = clk_get(NULL, "irda_clk"); - if (!clk) { + if (IS_ERR(clk)) { dev_err(dev, "can not get irda_clk\n"); return -EIO; } diff --git a/drivers/net/phy/bcm87xx.c b/drivers/net/phy/bcm87xx.c index 2346b38b983..799789518e8 100644 --- a/drivers/net/phy/bcm87xx.c +++ b/drivers/net/phy/bcm87xx.c @@ -229,3 +229,5 @@ static void __exit bcm87xx_exit(void) ARRAY_SIZE(bcm87xx_driver)); } module_exit(bcm87xx_exit); + +MODULE_LICENSE("GPL"); diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c index cf287e0eb40..2165d5fdb8c 100644 --- a/drivers/net/phy/micrel.c +++ b/drivers/net/phy/micrel.c @@ -21,6 +21,12 @@ #include <linux/phy.h> #include <linux/micrel_phy.h> +/* Operation Mode Strap Override */ +#define MII_KSZPHY_OMSO 0x16 +#define KSZPHY_OMSO_B_CAST_OFF (1 << 9) +#define KSZPHY_OMSO_RMII_OVERRIDE (1 << 1) +#define KSZPHY_OMSO_MII_OVERRIDE (1 << 0) + /* general Interrupt control/status reg in vendor specific block. */ #define MII_KSZPHY_INTCS 0x1B #define KSZPHY_INTCS_JABBER (1 << 15) @@ -101,6 +107,13 @@ static int kszphy_config_init(struct phy_device *phydev) return 0; } +static int ksz8021_config_init(struct phy_device *phydev) +{ + const u16 val = KSZPHY_OMSO_B_CAST_OFF | KSZPHY_OMSO_RMII_OVERRIDE; + phy_write(phydev, MII_KSZPHY_OMSO, val); + return 0; +} + static int ks8051_config_init(struct phy_device *phydev) { int regval; @@ -128,9 +141,22 @@ static struct phy_driver ksphy_driver[] = { .config_intr = ks8737_config_intr, .driver = { .owner = THIS_MODULE,}, }, { - .phy_id = PHY_ID_KS8041, + .phy_id = PHY_ID_KSZ8021, + .phy_id_mask = 0x00ffffff, + .name = "Micrel KSZ8021", + .features = (PHY_BASIC_FEATURES | SUPPORTED_Pause | + SUPPORTED_Asym_Pause), + .flags = PHY_HAS_MAGICANEG | PHY_HAS_INTERRUPT, + .config_init = ksz8021_config_init, + .config_aneg = genphy_config_aneg, + .read_status = genphy_read_status, + .ack_interrupt = kszphy_ack_interrupt, + .config_intr = kszphy_config_intr, + .driver = { .owner = THIS_MODULE,}, +}, { + .phy_id = PHY_ID_KSZ8041, .phy_id_mask = 0x00fffff0, - .name = "Micrel KS8041", + .name = "Micrel KSZ8041", .features = (PHY_BASIC_FEATURES | SUPPORTED_Pause | SUPPORTED_Asym_Pause), .flags = PHY_HAS_MAGICANEG | PHY_HAS_INTERRUPT, @@ -141,9 +167,9 @@ static struct phy_driver ksphy_driver[] = { .config_intr = kszphy_config_intr, .driver = { .owner = THIS_MODULE,}, }, { - .phy_id = PHY_ID_KS8051, + .phy_id = PHY_ID_KSZ8051, .phy_id_mask = 0x00fffff0, - .name = "Micrel KS8051", + .name = "Micrel KSZ8051", .features = (PHY_BASIC_FEATURES | SUPPORTED_Pause | SUPPORTED_Asym_Pause), .flags = PHY_HAS_MAGICANEG | PHY_HAS_INTERRUPT, @@ -154,8 +180,8 @@ static struct phy_driver ksphy_driver[] = { .config_intr = kszphy_config_intr, .driver = { .owner = THIS_MODULE,}, }, { - .phy_id = PHY_ID_KS8001, - .name = "Micrel KS8001 or KS8721", + .phy_id = PHY_ID_KSZ8001, + .name = "Micrel KSZ8001 or KS8721", .phy_id_mask = 0x00ffffff, .features = (PHY_BASIC_FEATURES | SUPPORTED_Pause), .flags = PHY_HAS_MAGICANEG | PHY_HAS_INTERRUPT, @@ -201,10 +227,11 @@ MODULE_LICENSE("GPL"); static struct mdio_device_id __maybe_unused micrel_tbl[] = { { PHY_ID_KSZ9021, 0x000ffffe }, - { PHY_ID_KS8001, 0x00ffffff }, + { PHY_ID_KSZ8001, 0x00ffffff }, { PHY_ID_KS8737, 0x00fffff0 }, - { PHY_ID_KS8041, 0x00fffff0 }, - { PHY_ID_KS8051, 0x00fffff0 }, + { PHY_ID_KSZ8021, 0x00ffffff }, + { PHY_ID_KSZ8041, 0x00fffff0 }, + { PHY_ID_KSZ8051, 0x00fffff0 }, { } }; diff --git a/drivers/net/phy/smsc.c b/drivers/net/phy/smsc.c index 6d6192316b3..88e3991464e 100644 --- a/drivers/net/phy/smsc.c +++ b/drivers/net/phy/smsc.c @@ -56,6 +56,32 @@ static int smsc_phy_config_init(struct phy_device *phydev) return smsc_phy_ack_interrupt (phydev); } +static int lan87xx_config_init(struct phy_device *phydev) +{ + /* + * Make sure the EDPWRDOWN bit is NOT set. Setting this bit on + * LAN8710/LAN8720 PHY causes the PHY to misbehave, likely due + * to a bug on the chip. + * + * When the system is powered on with the network cable being + * disconnected all the way until after ifconfig ethX up is + * issued for the LAN port with this PHY, connecting the cable + * afterwards does not cause LINK change detection, while the + * expected behavior is the Link UP being detected. + */ + int rc = phy_read(phydev, MII_LAN83C185_CTRL_STATUS); + if (rc < 0) + return rc; + + rc &= ~MII_LAN83C185_EDPWRDOWN; + + rc = phy_write(phydev, MII_LAN83C185_CTRL_STATUS, rc); + if (rc < 0) + return rc; + + return smsc_phy_ack_interrupt(phydev); +} + static int lan911x_config_init(struct phy_device *phydev) { return smsc_phy_ack_interrupt(phydev); @@ -162,7 +188,7 @@ static struct phy_driver smsc_phy_driver[] = { /* basic functions */ .config_aneg = genphy_config_aneg, .read_status = genphy_read_status, - .config_init = smsc_phy_config_init, + .config_init = lan87xx_config_init, /* IRQ related */ .ack_interrupt = smsc_phy_ack_interrupt, diff --git a/drivers/net/ppp/pppoe.c b/drivers/net/ppp/pppoe.c index cbf7047decc..20f31d0d153 100644 --- a/drivers/net/ppp/pppoe.c +++ b/drivers/net/ppp/pppoe.c @@ -570,7 +570,7 @@ static int pppoe_release(struct socket *sock) po = pppox_sk(sk); - if (sk->sk_state & (PPPOX_CONNECTED | PPPOX_BOUND)) { + if (sk->sk_state & (PPPOX_CONNECTED | PPPOX_BOUND | PPPOX_ZOMBIE)) { dev_put(po->pppoe_dev); po->pppoe_dev = NULL; } diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index 341b65dbbcd..f8cd61f449a 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -848,7 +848,7 @@ static struct netpoll_info *team_netpoll_info(struct team *team) } #endif -static void __team_port_change_check(struct team_port *port, bool linkup); +static void __team_port_change_port_added(struct team_port *port, bool linkup); static int team_port_add(struct team *team, struct net_device *port_dev) { @@ -948,7 +948,7 @@ static int team_port_add(struct team *team, struct net_device *port_dev) team_port_enable(team, port); list_add_tail_rcu(&port->list, &team->port_list); __team_compute_features(team); - __team_port_change_check(port, !!netif_carrier_ok(port_dev)); + __team_port_change_port_added(port, !!netif_carrier_ok(port_dev)); __team_options_change_check(team); netdev_info(dev, "Port device %s added\n", portname); @@ -983,6 +983,8 @@ err_set_mtu: return err; } +static void __team_port_change_port_removed(struct team_port *port); + static int team_port_del(struct team *team, struct net_device *port_dev) { struct net_device *dev = team->dev; @@ -999,8 +1001,7 @@ static int team_port_del(struct team *team, struct net_device *port_dev) __team_option_inst_mark_removed_port(team, port); __team_options_change_check(team); __team_option_inst_del_port(team, port); - port->removed = true; - __team_port_change_check(port, false); + __team_port_change_port_removed(port); team_port_disable(team, port); list_del_rcu(&port->list); netdev_rx_handler_unregister(port_dev); @@ -1652,8 +1653,8 @@ static int team_nl_cmd_noop(struct sk_buff *skb, struct genl_info *info) hdr = genlmsg_put(msg, info->snd_pid, info->snd_seq, &team_nl_family, 0, TEAM_CMD_NOOP); - if (IS_ERR(hdr)) { - err = PTR_ERR(hdr); + if (!hdr) { + err = -EMSGSIZE; goto err_msg_put; } @@ -1847,8 +1848,8 @@ start_again: hdr = genlmsg_put(skb, pid, seq, &team_nl_family, flags | NLM_F_MULTI, TEAM_CMD_OPTIONS_GET); - if (IS_ERR(hdr)) - return PTR_ERR(hdr); + if (!hdr) + return -EMSGSIZE; if (nla_put_u32(skb, TEAM_ATTR_TEAM_IFINDEX, team->dev->ifindex)) goto nla_put_failure; @@ -2067,8 +2068,8 @@ static int team_nl_fill_port_list_get(struct sk_buff *skb, hdr = genlmsg_put(skb, pid, seq, &team_nl_family, flags, TEAM_CMD_PORT_LIST_GET); - if (IS_ERR(hdr)) - return PTR_ERR(hdr); + if (!hdr) + return -EMSGSIZE; if (nla_put_u32(skb, TEAM_ATTR_TEAM_IFINDEX, team->dev->ifindex)) goto nla_put_failure; @@ -2251,13 +2252,11 @@ static void __team_options_change_check(struct team *team) } /* rtnl lock is held */ -static void __team_port_change_check(struct team_port *port, bool linkup) + +static void __team_port_change_send(struct team_port *port, bool linkup) { int err; - if (!port->removed && port->state.linkup == linkup) - return; - port->changed = true; port->state.linkup = linkup; team_refresh_port_linkup(port); @@ -2282,6 +2281,23 @@ send_event: } +static void __team_port_change_check(struct team_port *port, bool linkup) +{ + if (port->state.linkup != linkup) + __team_port_change_send(port, linkup); +} + +static void __team_port_change_port_added(struct team_port *port, bool linkup) +{ + __team_port_change_send(port, linkup); +} + +static void __team_port_change_port_removed(struct team_port *port) +{ + port->removed = true; + __team_port_change_send(port, false); +} + static void team_port_change_check(struct team_port *port, bool linkup) { struct team *team = port->team; diff --git a/drivers/net/usb/asix_devices.c b/drivers/net/usb/asix_devices.c index 4fd48df6b98..32e31c5c5dc 100644 --- a/drivers/net/usb/asix_devices.c +++ b/drivers/net/usb/asix_devices.c @@ -962,6 +962,10 @@ static const struct usb_device_id products [] = { USB_DEVICE (0x2001, 0x3c05), .driver_info = (unsigned long) &ax88772_info, }, { + // DLink DUB-E100 H/W Ver C1 + USB_DEVICE (0x2001, 0x1a02), + .driver_info = (unsigned long) &ax88772_info, +}, { // Linksys USB1000 USB_DEVICE (0x1737, 0x0039), .driver_info = (unsigned long) &ax88178_info, diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index b1ba68f1a04..3543c9e5782 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -366,16 +366,20 @@ static const struct usb_device_id products[] = { }, /* 2. Combined interface devices matching on class+protocol */ + { /* Huawei E367 and possibly others in "Windows mode" */ + USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, USB_CLASS_VENDOR_SPEC, 1, 7), + .driver_info = (unsigned long)&qmi_wwan_info, + }, { /* Huawei E392, E398 and possibly others in "Windows mode" */ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, USB_CLASS_VENDOR_SPEC, 1, 17), .driver_info = (unsigned long)&qmi_wwan_shared, }, - { /* Pantech UML290 */ - USB_DEVICE_AND_INTERFACE_INFO(0x106c, 0x3718, USB_CLASS_VENDOR_SPEC, 0xf0, 0xff), + { /* Pantech UML290, P4200 and more */ + USB_VENDOR_AND_INTERFACE_INFO(0x106c, USB_CLASS_VENDOR_SPEC, 0xf0, 0xff), .driver_info = (unsigned long)&qmi_wwan_shared, }, { /* Pantech UML290 - newer firmware */ - USB_DEVICE_AND_INTERFACE_INFO(0x106c, 0x3718, USB_CLASS_VENDOR_SPEC, 0xf1, 0xff), + USB_VENDOR_AND_INTERFACE_INFO(0x106c, USB_CLASS_VENDOR_SPEC, 0xf1, 0xff), .driver_info = (unsigned long)&qmi_wwan_shared, }, @@ -383,6 +387,7 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x19d2, 0x0055, 1)}, /* ZTE (Vodafone) K3520-Z */ {QMI_FIXED_INTF(0x19d2, 0x0063, 4)}, /* ZTE (Vodafone) K3565-Z */ {QMI_FIXED_INTF(0x19d2, 0x0104, 4)}, /* ZTE (Vodafone) K4505-Z */ + {QMI_FIXED_INTF(0x19d2, 0x0157, 5)}, /* ZTE MF683 */ {QMI_FIXED_INTF(0x19d2, 0x0167, 4)}, /* ZTE MF820D */ {QMI_FIXED_INTF(0x19d2, 0x0326, 4)}, /* ZTE MF821D */ {QMI_FIXED_INTF(0x19d2, 0x1008, 4)}, /* ZTE (Vodafone) K3570-Z */ diff --git a/drivers/net/usb/smsc75xx.c b/drivers/net/usb/smsc75xx.c index f5ab6e613ec..376143e8a1a 100644 --- a/drivers/net/usb/smsc75xx.c +++ b/drivers/net/usb/smsc75xx.c @@ -1253,6 +1253,7 @@ static struct usb_driver smsc75xx_driver = { .probe = usbnet_probe, .suspend = usbnet_suspend, .resume = usbnet_resume, + .reset_resume = usbnet_resume, .disconnect = usbnet_disconnect, .disable_hub_initiated_lpm = 1, }; diff --git a/drivers/net/wireless/ath/ath9k/ar9003_eeprom.c b/drivers/net/wireless/ath/ath9k/ar9003_eeprom.c index 2588848f4a8..d066f2516e4 100644 --- a/drivers/net/wireless/ath/ath9k/ar9003_eeprom.c +++ b/drivers/net/wireless/ath/ath9k/ar9003_eeprom.c @@ -2982,6 +2982,10 @@ static u32 ath9k_hw_ar9300_get_eeprom(struct ath_hw *ah, case EEP_RX_MASK: return pBase->txrxMask & 0xf; case EEP_PAPRD: + if (AR_SREV_9462(ah)) + return false; + if (!ah->config.enable_paprd); + return false; return !!(pBase->featureEnable & BIT(5)); case EEP_CHAIN_MASK_REDUCE: return (pBase->miscConfiguration >> 0x3) & 0x1; diff --git a/drivers/net/wireless/ath/ath9k/debug.c b/drivers/net/wireless/ath/ath9k/debug.c index 68b643c8943..c8ef30127ad 100644 --- a/drivers/net/wireless/ath/ath9k/debug.c +++ b/drivers/net/wireless/ath/ath9k/debug.c @@ -1577,6 +1577,8 @@ int ath9k_init_debug(struct ath_hw *ah) sc->debug.debugfs_phy, sc, &fops_tx_chainmask); debugfs_create_file("disable_ani", S_IRUSR | S_IWUSR, sc->debug.debugfs_phy, sc, &fops_disable_ani); + debugfs_create_bool("paprd", S_IRUSR | S_IWUSR, sc->debug.debugfs_phy, + &sc->sc_ah->config.enable_paprd); debugfs_create_file("regidx", S_IRUSR | S_IWUSR, sc->debug.debugfs_phy, sc, &fops_regidx); debugfs_create_file("regval", S_IRUSR | S_IWUSR, sc->debug.debugfs_phy, diff --git a/drivers/net/wireless/ath/ath9k/hw.c b/drivers/net/wireless/ath/ath9k/hw.c index 48af40151d2..4faf0a39587 100644 --- a/drivers/net/wireless/ath/ath9k/hw.c +++ b/drivers/net/wireless/ath/ath9k/hw.c @@ -2497,10 +2497,6 @@ int ath9k_hw_fill_cap_info(struct ath_hw *ah) pCap->rx_status_len = sizeof(struct ar9003_rxs); pCap->tx_desc_len = sizeof(struct ar9003_txc); pCap->txs_len = sizeof(struct ar9003_txs); - if (!ah->config.paprd_disable && - ah->eep_ops->get_eeprom(ah, EEP_PAPRD) && - !AR_SREV_9462(ah)) - pCap->hw_caps |= ATH9K_HW_CAP_PAPRD; } else { pCap->tx_desc_len = sizeof(struct ath_desc); if (AR_SREV_9280_20(ah)) diff --git a/drivers/net/wireless/ath/ath9k/hw.h b/drivers/net/wireless/ath/ath9k/hw.h index 6599a75f01f..de6968fc64f 100644 --- a/drivers/net/wireless/ath/ath9k/hw.h +++ b/drivers/net/wireless/ath/ath9k/hw.h @@ -236,7 +236,6 @@ enum ath9k_hw_caps { ATH9K_HW_CAP_LDPC = BIT(6), ATH9K_HW_CAP_FASTCLOCK = BIT(7), ATH9K_HW_CAP_SGI_20 = BIT(8), - ATH9K_HW_CAP_PAPRD = BIT(9), ATH9K_HW_CAP_ANT_DIV_COMB = BIT(10), ATH9K_HW_CAP_2GHZ = BIT(11), ATH9K_HW_CAP_5GHZ = BIT(12), @@ -287,12 +286,12 @@ struct ath9k_ops_config { u8 pcie_clock_req; u32 pcie_waen; u8 analog_shiftreg; - u8 paprd_disable; u32 ofdm_trig_low; u32 ofdm_trig_high; u32 cck_trig_high; u32 cck_trig_low; u32 enable_ani; + u32 enable_paprd; int serialize_regmode; bool rx_intr_mitigation; bool tx_intr_mitigation; diff --git a/drivers/net/wireless/ath/ath9k/link.c b/drivers/net/wireless/ath/ath9k/link.c index 825a29cc931..7b88b9c39cc 100644 --- a/drivers/net/wireless/ath/ath9k/link.c +++ b/drivers/net/wireless/ath/ath9k/link.c @@ -423,7 +423,7 @@ set_timer: cal_interval = min(cal_interval, (u32)short_cal_interval); mod_timer(&common->ani.timer, jiffies + msecs_to_jiffies(cal_interval)); - if ((sc->sc_ah->caps.hw_caps & ATH9K_HW_CAP_PAPRD) && ah->caldata) { + if (ah->eep_ops->get_eeprom(ah, EEP_PAPRD) && ah->caldata) { if (!ah->caldata->paprd_done) ieee80211_queue_work(sc->hw, &sc->paprd_work); else if (!ah->paprd_table_write_done) diff --git a/drivers/net/wireless/brcm80211/brcmfmac/bcmsdh_sdmmc.c b/drivers/net/wireless/brcm80211/brcmfmac/bcmsdh_sdmmc.c index 49765d34b4e..7c4ee72f9d5 100644 --- a/drivers/net/wireless/brcm80211/brcmfmac/bcmsdh_sdmmc.c +++ b/drivers/net/wireless/brcm80211/brcmfmac/bcmsdh_sdmmc.c @@ -638,6 +638,8 @@ static int brcmf_sdio_pd_probe(struct platform_device *pdev) oobirq_entry = kzalloc(sizeof(struct brcmf_sdio_oobirq), GFP_KERNEL); + if (!oobirq_entry) + return -ENOMEM; oobirq_entry->irq = res->start; oobirq_entry->flags = res->flags & IRQF_TRIGGER_MASK; list_add_tail(&oobirq_entry->list, &oobirq_lh); diff --git a/drivers/net/wireless/brcm80211/brcmfmac/dhd_common.c b/drivers/net/wireless/brcm80211/brcmfmac/dhd_common.c index 2621dd3d7dc..6f70953f0ba 100644 --- a/drivers/net/wireless/brcm80211/brcmfmac/dhd_common.c +++ b/drivers/net/wireless/brcm80211/brcmfmac/dhd_common.c @@ -764,8 +764,11 @@ static void brcmf_c_arp_offload_set(struct brcmf_pub *drvr, int arp_mode) { char iovbuf[32]; int retcode; + __le32 arp_mode_le; - brcmf_c_mkiovar("arp_ol", (char *)&arp_mode, 4, iovbuf, sizeof(iovbuf)); + arp_mode_le = cpu_to_le32(arp_mode); + brcmf_c_mkiovar("arp_ol", (char *)&arp_mode_le, 4, iovbuf, + sizeof(iovbuf)); retcode = brcmf_proto_cdc_set_dcmd(drvr, 0, BRCMF_C_SET_VAR, iovbuf, sizeof(iovbuf)); retcode = retcode >= 0 ? 0 : retcode; @@ -781,8 +784,11 @@ static void brcmf_c_arp_offload_enable(struct brcmf_pub *drvr, int arp_enable) { char iovbuf[32]; int retcode; + __le32 arp_enable_le; - brcmf_c_mkiovar("arpoe", (char *)&arp_enable, 4, + arp_enable_le = cpu_to_le32(arp_enable); + + brcmf_c_mkiovar("arpoe", (char *)&arp_enable_le, 4, iovbuf, sizeof(iovbuf)); retcode = brcmf_proto_cdc_set_dcmd(drvr, 0, BRCMF_C_SET_VAR, iovbuf, sizeof(iovbuf)); @@ -800,10 +806,10 @@ int brcmf_c_preinit_dcmds(struct brcmf_pub *drvr) char iovbuf[BRCMF_EVENTING_MASK_LEN + 12]; /* Room for "event_msgs" + '\0' + bitvec */ char buf[128], *ptr; - u32 roaming = 1; - uint bcn_timeout = 3; - int scan_assoc_time = 40; - int scan_unassoc_time = 40; + __le32 roaming_le = cpu_to_le32(1); + __le32 bcn_timeout_le = cpu_to_le32(3); + __le32 scan_assoc_time_le = cpu_to_le32(40); + __le32 scan_unassoc_time_le = cpu_to_le32(40); int i; struct brcmf_bus_dcmd *cmdlst; struct list_head *cur, *q; @@ -829,14 +835,14 @@ int brcmf_c_preinit_dcmds(struct brcmf_pub *drvr) /* Setup timeout if Beacons are lost and roam is off to report link down */ - brcmf_c_mkiovar("bcn_timeout", (char *)&bcn_timeout, 4, iovbuf, + brcmf_c_mkiovar("bcn_timeout", (char *)&bcn_timeout_le, 4, iovbuf, sizeof(iovbuf)); brcmf_proto_cdc_set_dcmd(drvr, 0, BRCMF_C_SET_VAR, iovbuf, sizeof(iovbuf)); /* Enable/Disable build-in roaming to allowed ext supplicant to take of romaing */ - brcmf_c_mkiovar("roam_off", (char *)&roaming, 4, + brcmf_c_mkiovar("roam_off", (char *)&roaming_le, 4, iovbuf, sizeof(iovbuf)); brcmf_proto_cdc_set_dcmd(drvr, 0, BRCMF_C_SET_VAR, iovbuf, sizeof(iovbuf)); @@ -848,9 +854,9 @@ int brcmf_c_preinit_dcmds(struct brcmf_pub *drvr) sizeof(iovbuf)); brcmf_proto_cdc_set_dcmd(drvr, 0, BRCMF_C_SET_SCAN_CHANNEL_TIME, - (char *)&scan_assoc_time, sizeof(scan_assoc_time)); + (char *)&scan_assoc_time_le, sizeof(scan_assoc_time_le)); brcmf_proto_cdc_set_dcmd(drvr, 0, BRCMF_C_SET_SCAN_UNASSOC_TIME, - (char *)&scan_unassoc_time, sizeof(scan_unassoc_time)); + (char *)&scan_unassoc_time_le, sizeof(scan_unassoc_time_le)); /* Set and enable ARP offload feature */ brcmf_c_arp_offload_set(drvr, BRCMF_ARPOL_MODE); diff --git a/drivers/net/wireless/brcm80211/brcmfmac/wl_cfg80211.c b/drivers/net/wireless/brcm80211/brcmfmac/wl_cfg80211.c index c36e9231244..50b5553b696 100644 --- a/drivers/net/wireless/brcm80211/brcmfmac/wl_cfg80211.c +++ b/drivers/net/wireless/brcm80211/brcmfmac/wl_cfg80211.c @@ -500,8 +500,10 @@ static void wl_iscan_prep(struct brcmf_scan_params_le *params_le, params_le->active_time = cpu_to_le32(-1); params_le->passive_time = cpu_to_le32(-1); params_le->home_time = cpu_to_le32(-1); - if (ssid && ssid->SSID_len) - memcpy(¶ms_le->ssid_le, ssid, sizeof(struct brcmf_ssid)); + if (ssid && ssid->SSID_len) { + params_le->ssid_le.SSID_len = cpu_to_le32(ssid->SSID_len); + memcpy(¶ms_le->ssid_le.SSID, ssid->SSID, ssid->SSID_len); + } } static s32 diff --git a/drivers/net/wireless/brcm80211/brcmsmac/channel.c b/drivers/net/wireless/brcm80211/brcmsmac/channel.c index 7ed7d757702..64a48f06d68 100644 --- a/drivers/net/wireless/brcm80211/brcmsmac/channel.c +++ b/drivers/net/wireless/brcm80211/brcmsmac/channel.c @@ -77,7 +77,7 @@ NL80211_RRF_NO_IBSS) static const struct ieee80211_regdomain brcms_regdom_x2 = { - .n_reg_rules = 7, + .n_reg_rules = 6, .alpha2 = "X2", .reg_rules = { BRCM_2GHZ_2412_2462, diff --git a/drivers/net/wireless/iwlwifi/pcie/trans.c b/drivers/net/wireless/iwlwifi/pcie/trans.c index 1e86ea2266d..dbeebef562d 100644 --- a/drivers/net/wireless/iwlwifi/pcie/trans.c +++ b/drivers/net/wireless/iwlwifi/pcie/trans.c @@ -1442,6 +1442,7 @@ static int iwl_trans_pcie_start_hw(struct iwl_trans *trans) return err; err_free_irq: + trans_pcie->irq_requested = false; free_irq(trans_pcie->irq, trans); error: iwl_free_isr_ict(trans); diff --git a/drivers/net/wireless/rtlwifi/rtl8192ce/def.h b/drivers/net/wireless/rtlwifi/rtl8192ce/def.h index 04c3aef8a4f..2925094b2d9 100644 --- a/drivers/net/wireless/rtlwifi/rtl8192ce/def.h +++ b/drivers/net/wireless/rtlwifi/rtl8192ce/def.h @@ -117,6 +117,7 @@ #define CHIP_VER_B BIT(4) #define CHIP_92C_BITMASK BIT(0) +#define CHIP_UNKNOWN BIT(7) #define CHIP_92C_1T2R 0x03 #define CHIP_92C 0x01 #define CHIP_88C 0x00 diff --git a/drivers/net/wireless/rtlwifi/rtl8192ce/hw.c b/drivers/net/wireless/rtlwifi/rtl8192ce/hw.c index bd0da7ef290..dd4bb0950a5 100644 --- a/drivers/net/wireless/rtlwifi/rtl8192ce/hw.c +++ b/drivers/net/wireless/rtlwifi/rtl8192ce/hw.c @@ -994,8 +994,16 @@ static enum version_8192c _rtl92ce_read_chip_version(struct ieee80211_hw *hw) version = (value32 & TYPE_ID) ? VERSION_A_CHIP_92C : VERSION_A_CHIP_88C; } else { - version = (value32 & TYPE_ID) ? VERSION_B_CHIP_92C : - VERSION_B_CHIP_88C; + version = (enum version_8192c) (CHIP_VER_B | + ((value32 & TYPE_ID) ? CHIP_92C_BITMASK : 0) | + ((value32 & VENDOR_ID) ? CHIP_VENDOR_UMC : 0)); + if ((!IS_CHIP_VENDOR_UMC(version)) && (value32 & + CHIP_VER_RTL_MASK)) { + version = (enum version_8192c)(version | + ((((value32 & CHIP_VER_RTL_MASK) == BIT(12)) + ? CHIP_VENDOR_UMC_B_CUT : CHIP_UNKNOWN) | + CHIP_VENDOR_UMC)); + } } switch (version) { diff --git a/drivers/net/wireless/rtlwifi/rtl8192ce/sw.c b/drivers/net/wireless/rtlwifi/rtl8192ce/sw.c index 3aa927f8b9b..7d8f96405f4 100644 --- a/drivers/net/wireless/rtlwifi/rtl8192ce/sw.c +++ b/drivers/net/wireless/rtlwifi/rtl8192ce/sw.c @@ -162,10 +162,12 @@ int rtl92c_init_sw_vars(struct ieee80211_hw *hw) /* request fw */ if (IS_VENDOR_UMC_A_CUT(rtlhal->version) && - !IS_92C_SERIAL(rtlhal->version)) + !IS_92C_SERIAL(rtlhal->version)) { rtlpriv->cfg->fw_name = "rtlwifi/rtl8192cfwU.bin"; - else if (IS_81xxC_VENDOR_UMC_B_CUT(rtlhal->version)) + } else if (IS_81xxC_VENDOR_UMC_B_CUT(rtlhal->version)) { rtlpriv->cfg->fw_name = "rtlwifi/rtl8192cfwU_B.bin"; + pr_info("****** This B_CUT device may not work with kernels 3.6 and earlier\n"); + } rtlpriv->max_fw_size = 0x4000; pr_info("Using firmware %s\n", rtlpriv->cfg->fw_name); diff --git a/drivers/rpmsg/virtio_rpmsg_bus.c b/drivers/rpmsg/virtio_rpmsg_bus.c index 590cfafc7c1..1859f71372e 100644 --- a/drivers/rpmsg/virtio_rpmsg_bus.c +++ b/drivers/rpmsg/virtio_rpmsg_bus.c @@ -1008,8 +1008,8 @@ static int rpmsg_probe(struct virtio_device *vdev) return 0; free_coherent: - dma_free_coherent(vdev->dev.parent, RPMSG_TOTAL_BUF_SPACE, bufs_va, - vrp->bufs_dma); + dma_free_coherent(vdev->dev.parent->parent, RPMSG_TOTAL_BUF_SPACE, + bufs_va, vrp->bufs_dma); vqs_del: vdev->config->del_vqs(vrp->vdev); free_vrp: @@ -1043,7 +1043,7 @@ static void __devexit rpmsg_remove(struct virtio_device *vdev) vdev->config->del_vqs(vrp->vdev); - dma_free_coherent(vdev->dev.parent, RPMSG_TOTAL_BUF_SPACE, + dma_free_coherent(vdev->dev.parent->parent, RPMSG_TOTAL_BUF_SPACE, vrp->rbufs, vrp->bufs_dma); kfree(vrp); diff --git a/drivers/rtc/rtc-twl.c b/drivers/rtc/rtc-twl.c index c5d06fe83bb..9277d945bf4 100644 --- a/drivers/rtc/rtc-twl.c +++ b/drivers/rtc/rtc-twl.c @@ -495,6 +495,11 @@ static int __devinit twl_rtc_probe(struct platform_device *pdev) if (ret < 0) goto out1; + /* ensure interrupts are disabled, bootloaders can be strange */ + ret = twl_rtc_write_u8(0, REG_RTC_INTERRUPTS_REG); + if (ret < 0) + dev_warn(&pdev->dev, "unable to disable interrupt\n"); + /* init cached IRQ enable bits */ ret = twl_rtc_read_u8(&rtc_irq_bits, REG_RTC_INTERRUPTS_REG); if (ret < 0) diff --git a/drivers/s390/block/dasd.c b/drivers/s390/block/dasd.c index 15370a2c5ff..0595c763daf 100644 --- a/drivers/s390/block/dasd.c +++ b/drivers/s390/block/dasd.c @@ -534,11 +534,11 @@ static void dasd_change_state(struct dasd_device *device) if (rc) device->target = device->state; - if (device->state == device->target) - wake_up(&dasd_init_waitq); - /* let user-space know that the device status changed */ kobject_uevent(&device->cdev->dev.kobj, KOBJ_CHANGE); + + if (device->state == device->target) + wake_up(&dasd_init_waitq); } /* @@ -2157,6 +2157,7 @@ static int _dasd_sleep_on(struct dasd_ccw_req *maincqr, int interruptible) test_bit(DASD_CQR_FLAGS_FAILFAST, &cqr->flags) && (!dasd_eer_enabled(device))) { cqr->status = DASD_CQR_FAILED; + cqr->intrc = -EAGAIN; continue; } /* Don't try to start requests if device is stopped */ @@ -3270,6 +3271,16 @@ void dasd_generic_path_event(struct ccw_device *cdev, int *path_event) dasd_schedule_device_bh(device); } if (path_event[chp] & PE_PATHGROUP_ESTABLISHED) { + if (!(device->path_data.opm & eventlpm) && + !(device->path_data.tbvpm & eventlpm)) { + /* + * we can not establish a pathgroup on an + * unavailable path, so trigger a path + * verification first + */ + device->path_data.tbvpm |= eventlpm; + dasd_schedule_device_bh(device); + } DBF_DEV_EVENT(DBF_WARNING, device, "%s", "Pathgroup re-established\n"); if (device->discipline->kick_validate) diff --git a/drivers/s390/block/dasd_alias.c b/drivers/s390/block/dasd_alias.c index 157defe5e06..6b556995bb3 100644 --- a/drivers/s390/block/dasd_alias.c +++ b/drivers/s390/block/dasd_alias.c @@ -384,6 +384,29 @@ static void _remove_device_from_lcu(struct alias_lcu *lcu, group->next = NULL; }; +static int +suborder_not_supported(struct dasd_ccw_req *cqr) +{ + char *sense; + char reason; + char msg_format; + char msg_no; + + sense = dasd_get_sense(&cqr->irb); + if (!sense) + return 0; + + reason = sense[0]; + msg_format = (sense[7] & 0xF0); + msg_no = (sense[7] & 0x0F); + + /* command reject, Format 0 MSG 4 - invalid parameter */ + if ((reason == 0x80) && (msg_format == 0x00) && (msg_no == 0x04)) + return 1; + + return 0; +} + static int read_unit_address_configuration(struct dasd_device *device, struct alias_lcu *lcu) { @@ -435,6 +458,8 @@ static int read_unit_address_configuration(struct dasd_device *device, do { rc = dasd_sleep_on(cqr); + if (rc && suborder_not_supported(cqr)) + return -EOPNOTSUPP; } while (rc && (cqr->retries > 0)); if (rc) { spin_lock_irqsave(&lcu->lock, flags); @@ -521,7 +546,7 @@ static void lcu_update_work(struct work_struct *work) * processing the data */ spin_lock_irqsave(&lcu->lock, flags); - if (rc || (lcu->flags & NEED_UAC_UPDATE)) { + if ((rc && (rc != -EOPNOTSUPP)) || (lcu->flags & NEED_UAC_UPDATE)) { DBF_DEV_EVENT(DBF_WARNING, device, "could not update" " alias data in lcu (rc = %d), retry later", rc); schedule_delayed_work(&lcu->ruac_data.dwork, 30*HZ); diff --git a/drivers/s390/block/dasd_eckd.c b/drivers/s390/block/dasd_eckd.c index 2fb2b9ea97e..c48c72abbef 100644 --- a/drivers/s390/block/dasd_eckd.c +++ b/drivers/s390/block/dasd_eckd.c @@ -1507,7 +1507,8 @@ static struct dasd_ccw_req *dasd_eckd_build_psf_ssc(struct dasd_device *device, * call might change behaviour of DASD devices. */ static int -dasd_eckd_psf_ssc(struct dasd_device *device, int enable_pav) +dasd_eckd_psf_ssc(struct dasd_device *device, int enable_pav, + unsigned long flags) { struct dasd_ccw_req *cqr; int rc; @@ -1516,10 +1517,19 @@ dasd_eckd_psf_ssc(struct dasd_device *device, int enable_pav) if (IS_ERR(cqr)) return PTR_ERR(cqr); + /* + * set flags e.g. turn on failfast, to prevent blocking + * the calling function should handle failed requests + */ + cqr->flags |= flags; + rc = dasd_sleep_on(cqr); if (!rc) /* trigger CIO to reprobe devices */ css_schedule_reprobe(); + else if (cqr->intrc == -EAGAIN) + rc = -EAGAIN; + dasd_sfree_request(cqr, cqr->memdev); return rc; } @@ -1527,7 +1537,8 @@ dasd_eckd_psf_ssc(struct dasd_device *device, int enable_pav) /* * Valide storage server of current device. */ -static void dasd_eckd_validate_server(struct dasd_device *device) +static int dasd_eckd_validate_server(struct dasd_device *device, + unsigned long flags) { int rc; struct dasd_eckd_private *private; @@ -1536,17 +1547,18 @@ static void dasd_eckd_validate_server(struct dasd_device *device) private = (struct dasd_eckd_private *) device->private; if (private->uid.type == UA_BASE_PAV_ALIAS || private->uid.type == UA_HYPER_PAV_ALIAS) - return; + return 0; if (dasd_nopav || MACHINE_IS_VM) enable_pav = 0; else enable_pav = 1; - rc = dasd_eckd_psf_ssc(device, enable_pav); + rc = dasd_eckd_psf_ssc(device, enable_pav, flags); /* may be requested feature is not available on server, * therefore just report error and go ahead */ DBF_EVENT_DEVID(DBF_WARNING, device->cdev, "PSF-SSC for SSID %04x " "returned rc=%d", private->uid.ssid, rc); + return rc; } /* @@ -1556,7 +1568,13 @@ static void dasd_eckd_do_validate_server(struct work_struct *work) { struct dasd_device *device = container_of(work, struct dasd_device, kick_validate); - dasd_eckd_validate_server(device); + if (dasd_eckd_validate_server(device, DASD_CQR_FLAGS_FAILFAST) + == -EAGAIN) { + /* schedule worker again if failed */ + schedule_work(&device->kick_validate); + return; + } + dasd_put_device(device); } @@ -1685,7 +1703,7 @@ dasd_eckd_check_characteristics(struct dasd_device *device) if (rc) goto out_err2; - dasd_eckd_validate_server(device); + dasd_eckd_validate_server(device, 0); /* device may report different configuration data after LCU setup */ rc = dasd_eckd_read_conf(device); @@ -4153,7 +4171,7 @@ static int dasd_eckd_restore_device(struct dasd_device *device) rc = dasd_alias_make_device_known_to_lcu(device); if (rc) return rc; - dasd_eckd_validate_server(device); + dasd_eckd_validate_server(device, DASD_CQR_FLAGS_FAILFAST); /* RE-Read Configuration Data */ rc = dasd_eckd_read_conf(device); diff --git a/drivers/s390/cio/device.c b/drivers/s390/cio/device.c index ed25c8740a9..fc916f5d731 100644 --- a/drivers/s390/cio/device.c +++ b/drivers/s390/cio/device.c @@ -1426,6 +1426,8 @@ static enum io_sch_action sch_get_action(struct subchannel *sch) return IO_SCH_REPROBE; if (cdev->online) return IO_SCH_VERIFY; + if (cdev->private->state == DEV_STATE_NOT_OPER) + return IO_SCH_UNREG_ATTACH; return IO_SCH_NOP; } @@ -1519,11 +1521,14 @@ static int io_subchannel_sch_event(struct subchannel *sch, int process) goto out; break; case IO_SCH_UNREG_ATTACH: + spin_lock_irqsave(sch->lock, flags); if (cdev->private->flags.resuming) { /* Device will be handled later. */ rc = 0; - goto out; + goto out_unlock; } + sch_set_cdev(sch, NULL); + spin_unlock_irqrestore(sch->lock, flags); /* Unregister ccw device. */ ccw_device_unregister(cdev); break; diff --git a/drivers/scsi/bnx2i/bnx2i_hwi.c b/drivers/scsi/bnx2i/bnx2i_hwi.c index 33d6630529d..91eec60252e 100644 --- a/drivers/scsi/bnx2i/bnx2i_hwi.c +++ b/drivers/scsi/bnx2i/bnx2i_hwi.c @@ -1264,6 +1264,9 @@ int bnx2i_send_fw_iscsi_init_msg(struct bnx2i_hba *hba) int rc = 0; u64 mask64; + memset(&iscsi_init, 0x00, sizeof(struct iscsi_kwqe_init1)); + memset(&iscsi_init2, 0x00, sizeof(struct iscsi_kwqe_init2)); + bnx2i_adjust_qp_size(hba); iscsi_init.flags = diff --git a/drivers/scsi/hpsa.c b/drivers/scsi/hpsa.c index 796482badf1..2b4261cb774 100644 --- a/drivers/scsi/hpsa.c +++ b/drivers/scsi/hpsa.c @@ -1315,8 +1315,9 @@ static void complete_scsi_command(struct CommandList *cp) } break; case CMD_PROTOCOL_ERR: + cmd->result = DID_ERROR << 16; dev_warn(&h->pdev->dev, "cp %p has " - "protocol error \n", cp); + "protocol error\n", cp); break; case CMD_HARDWARE_ERR: cmd->result = DID_ERROR << 16; diff --git a/drivers/scsi/mpt2sas/mpt2sas_base.c b/drivers/scsi/mpt2sas/mpt2sas_base.c index b25757d1e91..9d5a56c4b33 100644 --- a/drivers/scsi/mpt2sas/mpt2sas_base.c +++ b/drivers/scsi/mpt2sas/mpt2sas_base.c @@ -1209,6 +1209,13 @@ _base_check_enable_msix(struct MPT2SAS_ADAPTER *ioc) u16 message_control; + /* Check whether controller SAS2008 B0 controller, + if it is SAS2008 B0 controller use IO-APIC instead of MSIX */ + if (ioc->pdev->device == MPI2_MFGPAGE_DEVID_SAS2008 && + ioc->pdev->revision == 0x01) { + return -EINVAL; + } + base = pci_find_capability(ioc->pdev, PCI_CAP_ID_MSIX); if (!base) { dfailprintk(ioc, printk(MPT2SAS_INFO_FMT "msix not " diff --git a/drivers/scsi/virtio_scsi.c b/drivers/scsi/virtio_scsi.c index c7030fbee79..3e79a2f0004 100644 --- a/drivers/scsi/virtio_scsi.c +++ b/drivers/scsi/virtio_scsi.c @@ -331,7 +331,7 @@ static void virtscsi_map_sgl(struct scatterlist *sg, unsigned int *p_idx, int i; for_each_sg(table->sgl, sg_elem, table->nents, i) - sg_set_buf(&sg[idx++], sg_virt(sg_elem), sg_elem->length); + sg[idx++] = *sg_elem; *p_idx = idx; } diff --git a/drivers/sh/intc/core.c b/drivers/sh/intc/core.c index 32c26d795ed..8f32a1323a7 100644 --- a/drivers/sh/intc/core.c +++ b/drivers/sh/intc/core.c @@ -355,7 +355,7 @@ int __init register_intc_controller(struct intc_desc *desc) if (unlikely(res)) { if (res == -EEXIST) { res = irq_domain_associate(d->domain, - irq, irq); + irq2, irq2); if (unlikely(res)) { pr_err("domain association " "failure\n"); diff --git a/drivers/sh/pfc/pinctrl.c b/drivers/sh/pfc/pinctrl.c index 2804eaae804..0646bf6e788 100644 --- a/drivers/sh/pfc/pinctrl.c +++ b/drivers/sh/pfc/pinctrl.c @@ -208,10 +208,13 @@ static int sh_pfc_gpio_request_enable(struct pinctrl_dev *pctldev, break; case PINMUX_TYPE_GPIO: + case PINMUX_TYPE_INPUT: + case PINMUX_TYPE_OUTPUT: break; default: pr_err("Unsupported mux type (%d), bailing...\n", pinmux_type); - return -ENOTSUPP; + ret = -ENOTSUPP; + goto err; } ret = 0; diff --git a/drivers/usb/core/devices.c b/drivers/usb/core/devices.c index d9569658476..3440812b4a8 100644 --- a/drivers/usb/core/devices.c +++ b/drivers/usb/core/devices.c @@ -624,7 +624,7 @@ static ssize_t usb_device_read(struct file *file, char __user *buf, /* print devices for all busses */ list_for_each_entry(bus, &usb_bus_list, bus_list) { /* recurse through all children of the root hub */ - if (!bus->root_hub) + if (!bus_to_hcd(bus)->rh_registered) continue; usb_lock_device(bus->root_hub); ret = usb_device_dump(&buf, &nbytes, &skip_bytes, ppos, diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c index bc84106ac05..75ba2091f9b 100644 --- a/drivers/usb/core/hcd.c +++ b/drivers/usb/core/hcd.c @@ -1011,10 +1011,7 @@ static int register_root_hub(struct usb_hcd *hcd) if (retval) { dev_err (parent_dev, "can't register root hub for %s, %d\n", dev_name(&usb_dev->dev), retval); - } - mutex_unlock(&usb_bus_list_lock); - - if (retval == 0) { + } else { spin_lock_irq (&hcd_root_hub_lock); hcd->rh_registered = 1; spin_unlock_irq (&hcd_root_hub_lock); @@ -1023,6 +1020,7 @@ static int register_root_hub(struct usb_hcd *hcd) if (HCD_DEAD(hcd)) usb_hc_died (hcd); /* This time clean up */ } + mutex_unlock(&usb_bus_list_lock); return retval; } diff --git a/drivers/usb/host/ohci-at91.c b/drivers/usb/host/ohci-at91.c index aaa8d2bce21..0bf72f943b0 100644 --- a/drivers/usb/host/ohci-at91.c +++ b/drivers/usb/host/ohci-at91.c @@ -467,7 +467,8 @@ static irqreturn_t ohci_hcd_at91_overcurrent_irq(int irq, void *data) /* From the GPIO notifying the over-current situation, find * out the corresponding port */ at91_for_each_port(port) { - if (gpio_to_irq(pdata->overcurrent_pin[port]) == irq) { + if (gpio_is_valid(pdata->overcurrent_pin[port]) && + gpio_to_irq(pdata->overcurrent_pin[port]) == irq) { gpio = pdata->overcurrent_pin[port]; break; } diff --git a/drivers/vfio/pci/vfio_pci_intrs.c b/drivers/vfio/pci/vfio_pci_intrs.c index 211a4920b88..d8dedc7d391 100644 --- a/drivers/vfio/pci/vfio_pci_intrs.c +++ b/drivers/vfio/pci/vfio_pci_intrs.c @@ -76,9 +76,24 @@ static int virqfd_wakeup(wait_queue_t *wait, unsigned mode, int sync, void *key) schedule_work(&virqfd->inject); } - if (flags & POLLHUP) - /* The eventfd is closing, detach from VFIO */ - virqfd_deactivate(virqfd); + if (flags & POLLHUP) { + unsigned long flags; + spin_lock_irqsave(&virqfd->vdev->irqlock, flags); + + /* + * The eventfd is closing, if the virqfd has not yet been + * queued for release, as determined by testing whether the + * vdev pointer to it is still valid, queue it now. As + * with kvm irqfds, we know we won't race against the virqfd + * going away because we hold wqh->lock to get here. + */ + if (*(virqfd->pvirqfd) == virqfd) { + *(virqfd->pvirqfd) = NULL; + virqfd_deactivate(virqfd); + } + + spin_unlock_irqrestore(&virqfd->vdev->irqlock, flags); + } return 0; } @@ -93,7 +108,6 @@ static void virqfd_ptable_queue_proc(struct file *file, static void virqfd_shutdown(struct work_struct *work) { struct virqfd *virqfd = container_of(work, struct virqfd, shutdown); - struct virqfd **pvirqfd = virqfd->pvirqfd; u64 cnt; eventfd_ctx_remove_wait_queue(virqfd->eventfd, &virqfd->wait, &cnt); @@ -101,7 +115,6 @@ static void virqfd_shutdown(struct work_struct *work) eventfd_ctx_put(virqfd->eventfd); kfree(virqfd); - *pvirqfd = NULL; } static void virqfd_inject(struct work_struct *work) @@ -122,15 +135,11 @@ static int virqfd_enable(struct vfio_pci_device *vdev, int ret = 0; unsigned int events; - if (*pvirqfd) - return -EBUSY; - virqfd = kzalloc(sizeof(*virqfd), GFP_KERNEL); if (!virqfd) return -ENOMEM; virqfd->pvirqfd = pvirqfd; - *pvirqfd = virqfd; virqfd->vdev = vdev; virqfd->handler = handler; virqfd->thread = thread; @@ -154,6 +163,23 @@ static int virqfd_enable(struct vfio_pci_device *vdev, virqfd->eventfd = ctx; /* + * virqfds can be released by closing the eventfd or directly + * through ioctl. These are both done through a workqueue, so + * we update the pointer to the virqfd under lock to avoid + * pushing multiple jobs to release the same virqfd. + */ + spin_lock_irq(&vdev->irqlock); + + if (*pvirqfd) { + spin_unlock_irq(&vdev->irqlock); + ret = -EBUSY; + goto fail; + } + *pvirqfd = virqfd; + + spin_unlock_irq(&vdev->irqlock); + + /* * Install our own custom wake-up handling so we are notified via * a callback whenever someone signals the underlying eventfd. */ @@ -187,19 +213,29 @@ fail: fput(file); kfree(virqfd); - *pvirqfd = NULL; return ret; } -static void virqfd_disable(struct virqfd *virqfd) +static void virqfd_disable(struct vfio_pci_device *vdev, + struct virqfd **pvirqfd) { - if (!virqfd) - return; + unsigned long flags; + + spin_lock_irqsave(&vdev->irqlock, flags); + + if (*pvirqfd) { + virqfd_deactivate(*pvirqfd); + *pvirqfd = NULL; + } - virqfd_deactivate(virqfd); + spin_unlock_irqrestore(&vdev->irqlock, flags); - /* Block until we know all outstanding shutdown jobs have completed. */ + /* + * Block until we know all outstanding shutdown jobs have completed. + * Even if we don't queue the job, flush the wq to be sure it's + * been released. + */ flush_workqueue(vfio_irqfd_cleanup_wq); } @@ -392,8 +428,8 @@ static int vfio_intx_set_signal(struct vfio_pci_device *vdev, int fd) static void vfio_intx_disable(struct vfio_pci_device *vdev) { vfio_intx_set_signal(vdev, -1); - virqfd_disable(vdev->ctx[0].unmask); - virqfd_disable(vdev->ctx[0].mask); + virqfd_disable(vdev, &vdev->ctx[0].unmask); + virqfd_disable(vdev, &vdev->ctx[0].mask); vdev->irq_type = VFIO_PCI_NUM_IRQS; vdev->num_ctx = 0; kfree(vdev->ctx); @@ -539,8 +575,8 @@ static void vfio_msi_disable(struct vfio_pci_device *vdev, bool msix) vfio_msi_set_block(vdev, 0, vdev->num_ctx, NULL, msix); for (i = 0; i < vdev->num_ctx; i++) { - virqfd_disable(vdev->ctx[i].unmask); - virqfd_disable(vdev->ctx[i].mask); + virqfd_disable(vdev, &vdev->ctx[i].unmask); + virqfd_disable(vdev, &vdev->ctx[i].mask); } if (msix) { @@ -577,7 +613,7 @@ static int vfio_pci_set_intx_unmask(struct vfio_pci_device *vdev, vfio_send_intx_eventfd, NULL, &vdev->ctx[0].unmask, fd); - virqfd_disable(vdev->ctx[0].unmask); + virqfd_disable(vdev, &vdev->ctx[0].unmask); } return 0; diff --git a/drivers/watchdog/hpwdt.c b/drivers/watchdog/hpwdt.c index 1eff743ec49..ae60406ea8a 100644 --- a/drivers/watchdog/hpwdt.c +++ b/drivers/watchdog/hpwdt.c @@ -814,6 +814,9 @@ static int __devinit hpwdt_init_one(struct pci_dev *dev, hpwdt_timer_reg = pci_mem_addr + 0x70; hpwdt_timer_con = pci_mem_addr + 0x72; + /* Make sure that timer is disabled until /dev/watchdog is opened */ + hpwdt_stop(); + /* Make sure that we have a valid soft_margin */ if (hpwdt_change_timer(soft_margin)) hpwdt_change_timer(DEFAULT_MARGIN); diff --git a/drivers/watchdog/watchdog_core.c b/drivers/watchdog/watchdog_core.c index 6aa46a90ff0..3796434991f 100644 --- a/drivers/watchdog/watchdog_core.c +++ b/drivers/watchdog/watchdog_core.c @@ -128,11 +128,12 @@ EXPORT_SYMBOL_GPL(watchdog_register_device); void watchdog_unregister_device(struct watchdog_device *wdd) { int ret; - int devno = wdd->cdev.dev; + int devno; if (wdd == NULL) return; + devno = wdd->cdev.dev; ret = watchdog_dev_unregister(wdd); if (ret) pr_err("error unregistering /dev/watchdog (err=%d)\n", ret); diff --git a/drivers/xen/gntdev.c b/drivers/xen/gntdev.c index 1ffd03bf8e1..7f124160848 100644 --- a/drivers/xen/gntdev.c +++ b/drivers/xen/gntdev.c @@ -314,8 +314,9 @@ static int __unmap_grant_pages(struct grant_map *map, int offset, int pages) } } - err = gnttab_unmap_refs(map->unmap_ops + offset, map->pages + offset, - pages, true); + err = gnttab_unmap_refs(map->unmap_ops + offset, + use_ptemod ? map->kmap_ops + offset : NULL, map->pages + offset, + pages); if (err) return err; diff --git a/drivers/xen/grant-table.c b/drivers/xen/grant-table.c index 0bfc1ef1125..006726688ba 100644 --- a/drivers/xen/grant-table.c +++ b/drivers/xen/grant-table.c @@ -870,7 +870,8 @@ int gnttab_map_refs(struct gnttab_map_grant_ref *map_ops, EXPORT_SYMBOL_GPL(gnttab_map_refs); int gnttab_unmap_refs(struct gnttab_unmap_grant_ref *unmap_ops, - struct page **pages, unsigned int count, bool clear_pte) + struct gnttab_map_grant_ref *kmap_ops, + struct page **pages, unsigned int count) { int i, ret; bool lazy = false; @@ -888,7 +889,8 @@ int gnttab_unmap_refs(struct gnttab_unmap_grant_ref *unmap_ops, } for (i = 0; i < count; i++) { - ret = m2p_remove_override(pages[i], clear_pte); + ret = m2p_remove_override(pages[i], kmap_ops ? + &kmap_ops[i] : NULL); if (ret) return ret; } diff --git a/fs/cifs/cifs_unicode.c b/fs/cifs/cifs_unicode.c index 7dab9c04ad5..53cf2aabce8 100644 --- a/fs/cifs/cifs_unicode.c +++ b/fs/cifs/cifs_unicode.c @@ -328,7 +328,7 @@ cifsConvertToUTF16(__le16 *target, const char *source, int srclen, } ctoUTF16_out: - return i; + return j; } #ifdef CONFIG_CIFS_SMB2 diff --git a/fs/dcache.c b/fs/dcache.c index 8086636bf79..693f95bf1ca 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -389,7 +389,7 @@ static struct dentry *d_kill(struct dentry *dentry, struct dentry *parent) * Inform try_to_ascend() that we are no longer attached to the * dentry tree */ - dentry->d_flags |= DCACHE_DISCONNECTED; + dentry->d_flags |= DCACHE_DENTRY_KILLED; if (parent) spin_unlock(&parent->d_lock); dentry_iput(dentry); @@ -1048,7 +1048,7 @@ static struct dentry *try_to_ascend(struct dentry *old, int locked, unsigned seq * or deletion */ if (new != old->d_parent || - (old->d_flags & DCACHE_DISCONNECTED) || + (old->d_flags & DCACHE_DENTRY_KILLED) || (!locked && read_seqretry(&rename_lock, seq))) { spin_unlock(&new->d_lock); new = NULL; @@ -1134,6 +1134,8 @@ positive: return 1; rename_retry: + if (locked) + goto again; locked = 1; write_seqlock(&rename_lock); goto again; @@ -1141,7 +1143,7 @@ rename_retry: EXPORT_SYMBOL(have_submounts); /* - * Search the dentry child list for the specified parent, + * Search the dentry child list of the specified parent, * and move any unused dentries to the end of the unused * list for prune_dcache(). We descend to the next level * whenever the d_subdirs list is non-empty and continue @@ -1236,6 +1238,8 @@ out: rename_retry: if (found) return found; + if (locked) + goto again; locked = 1; write_seqlock(&rename_lock); goto again; @@ -3035,6 +3039,8 @@ resume: return; rename_retry: + if (locked) + goto again; locked = 1; write_seqlock(&rename_lock); goto again; diff --git a/fs/debugfs/file.c b/fs/debugfs/file.c index 2340f6978d6..c5ca6ae5a30 100644 --- a/fs/debugfs/file.c +++ b/fs/debugfs/file.c @@ -526,73 +526,51 @@ struct array_data { u32 elements; }; -static int u32_array_open(struct inode *inode, struct file *file) -{ - file->private_data = NULL; - return nonseekable_open(inode, file); -} - -static size_t format_array(char *buf, size_t bufsize, const char *fmt, - u32 *array, u32 array_size) +static size_t u32_format_array(char *buf, size_t bufsize, + u32 *array, int array_size) { size_t ret = 0; - u32 i; - for (i = 0; i < array_size; i++) { + while (--array_size >= 0) { size_t len; + char term = array_size ? ' ' : '\n'; - len = snprintf(buf, bufsize, fmt, array[i]); - len++; /* ' ' or '\n' */ + len = snprintf(buf, bufsize, "%u%c", *array++, term); ret += len; - if (buf) { - buf += len; - bufsize -= len; - buf[-1] = (i == array_size-1) ? '\n' : ' '; - } + buf += len; + bufsize -= len; } - - ret++; /* \0 */ - if (buf) - *buf = '\0'; - return ret; } -static char *format_array_alloc(const char *fmt, u32 *array, - u32 array_size) +static int u32_array_open(struct inode *inode, struct file *file) { - size_t len = format_array(NULL, 0, fmt, array, array_size); - char *ret; - - ret = kmalloc(len, GFP_KERNEL); - if (ret == NULL) - return NULL; + struct array_data *data = inode->i_private; + int size, elements = data->elements; + char *buf; + + /* + * Max size: + * - 10 digits + ' '/'\n' = 11 bytes per number + * - terminating NUL character + */ + size = elements*11; + buf = kmalloc(size+1, GFP_KERNEL); + if (!buf) + return -ENOMEM; + buf[size] = 0; + + file->private_data = buf; + u32_format_array(buf, size, data->array, data->elements); - format_array(ret, len, fmt, array, array_size); - return ret; + return nonseekable_open(inode, file); } static ssize_t u32_array_read(struct file *file, char __user *buf, size_t len, loff_t *ppos) { - struct inode *inode = file->f_path.dentry->d_inode; - struct array_data *data = inode->i_private; - size_t size; - - if (*ppos == 0) { - if (file->private_data) { - kfree(file->private_data); - file->private_data = NULL; - } - - file->private_data = format_array_alloc("%u", data->array, - data->elements); - } - - size = 0; - if (file->private_data) - size = strlen(file->private_data); + size_t size = strlen(file->private_data); return simple_read_from_buffer(buf, len, ppos, file->private_data, size); diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c index d6526347d38..01c4975da4b 100644 --- a/fs/gfs2/aops.c +++ b/fs/gfs2/aops.c @@ -612,6 +612,7 @@ static int gfs2_write_begin(struct file *file, struct address_space *mapping, struct gfs2_sbd *sdp = GFS2_SB(mapping->host); struct gfs2_inode *m_ip = GFS2_I(sdp->sd_statfs_inode); unsigned int data_blocks = 0, ind_blocks = 0, rblocks; + unsigned requested = 0; int alloc_required; int error = 0; pgoff_t index = pos >> PAGE_CACHE_SHIFT; @@ -641,7 +642,8 @@ static int gfs2_write_begin(struct file *file, struct address_space *mapping, if (error) goto out_unlock; - error = gfs2_inplace_reserve(ip, data_blocks + ind_blocks); + requested = data_blocks + ind_blocks; + error = gfs2_inplace_reserve(ip, requested); if (error) goto out_qunlock; } @@ -654,7 +656,7 @@ static int gfs2_write_begin(struct file *file, struct address_space *mapping, if (&ip->i_inode == sdp->sd_rindex) rblocks += 2 * RES_STATFS; if (alloc_required) - rblocks += gfs2_rg_blocks(ip); + rblocks += gfs2_rg_blocks(ip, requested); error = gfs2_trans_begin(sdp, rblocks, PAGE_CACHE_SIZE/sdp->sd_sb.sb_bsize); @@ -868,8 +870,7 @@ static int gfs2_write_end(struct file *file, struct address_space *mapping, brelse(dibh); failed: gfs2_trans_end(sdp); - if (gfs2_mb_reserved(ip)) - gfs2_inplace_release(ip); + gfs2_inplace_release(ip); if (ip->i_res->rs_qa_qd_num) gfs2_quota_unlock(ip); if (inode == sdp->sd_rindex) { @@ -1023,7 +1024,7 @@ static ssize_t gfs2_direct_IO(int rw, struct kiocb *iocb, offset, nr_segs, gfs2_get_block_direct, NULL, NULL, 0); out: - gfs2_glock_dq_m(1, &gh); + gfs2_glock_dq(&gh); gfs2_holder_uninit(&gh); return rv; } diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c index 49cd7dd4a9f..1fd3ae237bd 100644 --- a/fs/gfs2/bmap.c +++ b/fs/gfs2/bmap.c @@ -786,7 +786,7 @@ static int do_strip(struct gfs2_inode *ip, struct buffer_head *dibh, goto out_rlist; if (gfs2_rs_active(ip->i_res)) /* needs to be done with the rgrp glock held */ - gfs2_rs_deltree(ip->i_res); + gfs2_rs_deltree(ip, ip->i_res); error = gfs2_trans_begin(sdp, rg_blocks + RES_DINODE + RES_INDIRECT + RES_STATFS + RES_QUOTA, diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c index 382000ffac1..30e21997a1a 100644 --- a/fs/gfs2/file.c +++ b/fs/gfs2/file.c @@ -441,7 +441,7 @@ static int gfs2_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) rblocks += data_blocks ? data_blocks : 1; if (ind_blocks || data_blocks) { rblocks += RES_STATFS + RES_QUOTA; - rblocks += gfs2_rg_blocks(ip); + rblocks += gfs2_rg_blocks(ip, data_blocks + ind_blocks); } ret = gfs2_trans_begin(sdp, rblocks, 0); if (ret) @@ -845,7 +845,7 @@ retry: &max_bytes, &data_blocks, &ind_blocks); rblocks = RES_DINODE + ind_blocks + RES_STATFS + RES_QUOTA + - RES_RG_HDR + gfs2_rg_blocks(ip); + RES_RG_HDR + gfs2_rg_blocks(ip, data_blocks + ind_blocks); if (gfs2_is_jdata(ip)) rblocks += data_blocks ? data_blocks : 1; diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index 1ed81f40da0..e6c2fd53cab 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -186,20 +186,6 @@ static void gfs2_glock_remove_from_lru(struct gfs2_glock *gl) } /** - * __gfs2_glock_schedule_for_reclaim - Add a glock to the reclaim list - * @gl: the glock - * - * If the glock is demotable, then we add it (or move it) to the end - * of the glock LRU list. - */ - -static void __gfs2_glock_schedule_for_reclaim(struct gfs2_glock *gl) -{ - if (demote_ok(gl)) - gfs2_glock_add_to_lru(gl); -} - -/** * gfs2_glock_put_nolock() - Decrement reference count on glock * @gl: The glock to put * @@ -883,7 +869,14 @@ static int gfs2_glock_demote_wait(void *word) return 0; } -static void wait_on_holder(struct gfs2_holder *gh) +/** + * gfs2_glock_wait - wait on a glock acquisition + * @gh: the glock holder + * + * Returns: 0 on success + */ + +int gfs2_glock_wait(struct gfs2_holder *gh) { unsigned long time1 = jiffies; @@ -894,12 +887,7 @@ static void wait_on_holder(struct gfs2_holder *gh) gh->gh_gl->gl_hold_time = min(gh->gh_gl->gl_hold_time + GL_GLOCK_HOLD_INCR, GL_GLOCK_MAX_HOLD); -} - -static void wait_on_demote(struct gfs2_glock *gl) -{ - might_sleep(); - wait_on_bit(&gl->gl_flags, GLF_DEMOTE, gfs2_glock_demote_wait, TASK_UNINTERRUPTIBLE); + return gh->gh_error; } /** @@ -929,19 +917,6 @@ static void handle_callback(struct gfs2_glock *gl, unsigned int state, trace_gfs2_demote_rq(gl); } -/** - * gfs2_glock_wait - wait on a glock acquisition - * @gh: the glock holder - * - * Returns: 0 on success - */ - -int gfs2_glock_wait(struct gfs2_holder *gh) -{ - wait_on_holder(gh); - return gh->gh_error; -} - void gfs2_print_dbg(struct seq_file *seq, const char *fmt, ...) { struct va_format vaf; @@ -979,7 +954,7 @@ __acquires(&gl->gl_spin) struct gfs2_sbd *sdp = gl->gl_sbd; struct list_head *insert_pt = NULL; struct gfs2_holder *gh2; - int try_lock = 0; + int try_futile = 0; BUG_ON(gh->gh_owner_pid == NULL); if (test_and_set_bit(HIF_WAIT, &gh->gh_iflags)) @@ -987,7 +962,7 @@ __acquires(&gl->gl_spin) if (gh->gh_flags & (LM_FLAG_TRY | LM_FLAG_TRY_1CB)) { if (test_bit(GLF_LOCK, &gl->gl_flags)) - try_lock = 1; + try_futile = !may_grant(gl, gh); if (test_bit(GLF_INVALIDATE_IN_PROGRESS, &gl->gl_flags)) goto fail; } @@ -996,9 +971,8 @@ __acquires(&gl->gl_spin) if (unlikely(gh2->gh_owner_pid == gh->gh_owner_pid && (gh->gh_gl->gl_ops->go_type != LM_TYPE_FLOCK))) goto trap_recursive; - if (try_lock && - !(gh2->gh_flags & (LM_FLAG_TRY | LM_FLAG_TRY_1CB)) && - !may_grant(gl, gh)) { + if (try_futile && + !(gh2->gh_flags & (LM_FLAG_TRY | LM_FLAG_TRY_1CB))) { fail: gh->gh_error = GLR_TRYFAILED; gfs2_holder_wake(gh); @@ -1121,8 +1095,9 @@ void gfs2_glock_dq(struct gfs2_holder *gh) !test_bit(GLF_DEMOTE, &gl->gl_flags)) fast_path = 1; } - if (!test_bit(GLF_LFLUSH, &gl->gl_flags)) - __gfs2_glock_schedule_for_reclaim(gl); + if (!test_bit(GLF_LFLUSH, &gl->gl_flags) && demote_ok(gl)) + gfs2_glock_add_to_lru(gl); + trace_gfs2_glock_queue(gh, 0); spin_unlock(&gl->gl_spin); if (likely(fast_path)) @@ -1141,7 +1116,8 @@ void gfs2_glock_dq_wait(struct gfs2_holder *gh) { struct gfs2_glock *gl = gh->gh_gl; gfs2_glock_dq(gh); - wait_on_demote(gl); + might_sleep(); + wait_on_bit(&gl->gl_flags, GLF_DEMOTE, gfs2_glock_demote_wait, TASK_UNINTERRUPTIBLE); } /** diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c index 4bdcf378418..32cc4fde975 100644 --- a/fs/gfs2/glops.c +++ b/fs/gfs2/glops.c @@ -94,6 +94,7 @@ static void gfs2_ail_empty_gl(struct gfs2_glock *gl) /* A shortened, inline version of gfs2_trans_begin() */ tr.tr_reserved = 1 + gfs2_struct2blk(sdp, tr.tr_revokes, sizeof(u64)); tr.tr_ip = (unsigned long)__builtin_return_address(0); + sb_start_intwrite(sdp->sd_vfs); gfs2_log_reserve(sdp, tr.tr_reserved); BUG_ON(current->journal_info); current->journal_info = &tr; diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h index aaecc8085fc..3d469d37345 100644 --- a/fs/gfs2/incore.h +++ b/fs/gfs2/incore.h @@ -99,9 +99,26 @@ struct gfs2_rgrpd { #define GFS2_RDF_MASK 0xf0000000 /* mask for internal flags */ spinlock_t rd_rsspin; /* protects reservation related vars */ struct rb_root rd_rstree; /* multi-block reservation tree */ - u32 rd_rs_cnt; /* count of current reservations */ }; +struct gfs2_rbm { + struct gfs2_rgrpd *rgd; + struct gfs2_bitmap *bi; /* Bitmap must belong to the rgd */ + u32 offset; /* The offset is bitmap relative */ +}; + +static inline u64 gfs2_rbm_to_block(const struct gfs2_rbm *rbm) +{ + return rbm->rgd->rd_data0 + (rbm->bi->bi_start * GFS2_NBBY) + rbm->offset; +} + +static inline bool gfs2_rbm_eq(const struct gfs2_rbm *rbm1, + const struct gfs2_rbm *rbm2) +{ + return (rbm1->rgd == rbm2->rgd) && (rbm1->bi == rbm2->bi) && + (rbm1->offset == rbm2->offset); +} + enum gfs2_state_bits { BH_Pinned = BH_PrivateStart, BH_Escaped = BH_PrivateStart + 1, @@ -250,18 +267,11 @@ struct gfs2_blkreserv { /* components used during write (step 1): */ atomic_t rs_sizehint; /* hint of the write size */ - /* components used during inplace_reserve (step 2): */ - u32 rs_requested; /* Filled in by caller of gfs2_inplace_reserve() */ - - /* components used during get_local_rgrp (step 3): */ - struct gfs2_rgrpd *rs_rgd; /* pointer to the gfs2_rgrpd */ struct gfs2_holder rs_rgd_gh; /* Filled in by get_local_rgrp */ struct rb_node rs_node; /* link to other block reservations */ - - /* components used during block searches and assignments (step 4): */ - struct gfs2_bitmap *rs_bi; /* bitmap for the current allocation */ - u32 rs_biblk; /* start block relative to the bi */ + struct gfs2_rbm rs_rbm; /* Start of reservation */ u32 rs_free; /* how many blocks are still free */ + u64 rs_inum; /* Inode number for reservation */ /* ancillary quota stuff */ struct gfs2_quota_data *rs_qa_qd[2 * MAXQUOTAS]; diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c index 753af3d86bb..381893ceefa 100644 --- a/fs/gfs2/inode.c +++ b/fs/gfs2/inode.c @@ -712,14 +712,9 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry, if (error) goto fail_gunlock2; - /* The newly created inode needs a reservation so it can allocate - xattrs. At the same time, we want new blocks allocated to the new - dinode to be as contiguous as possible. Since we allocated the - dinode block under the directory's reservation, we transfer - ownership of that reservation to the new inode. The directory - doesn't need a reservation unless it needs a new allocation. */ - ip->i_res = dip->i_res; - dip->i_res = NULL; + error = gfs2_rs_alloc(ip); + if (error) + goto fail_gunlock2; error = gfs2_acl_create(dip, inode); if (error) @@ -737,10 +732,7 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry, brelse(bh); gfs2_trans_end(sdp); - /* Check if we reserved space in the rgrp. Function link_dinode may - not, depending on whether alloc is required. */ - if (gfs2_mb_reserved(dip)) - gfs2_inplace_release(dip); + gfs2_inplace_release(dip); gfs2_quota_unlock(dip); mark_inode_dirty(inode); gfs2_glock_dq_uninit_m(2, ghs); @@ -897,7 +889,7 @@ static int gfs2_link(struct dentry *old_dentry, struct inode *dir, goto out_gunlock_q; error = gfs2_trans_begin(sdp, sdp->sd_max_dirres + - gfs2_rg_blocks(dip) + + gfs2_rg_blocks(dip, sdp->sd_max_dirres) + 2 * RES_DINODE + RES_STATFS + RES_QUOTA, 0); if (error) @@ -1378,7 +1370,7 @@ static int gfs2_rename(struct inode *odir, struct dentry *odentry, goto out_gunlock_q; error = gfs2_trans_begin(sdp, sdp->sd_max_dirres + - gfs2_rg_blocks(ndip) + + gfs2_rg_blocks(ndip, sdp->sd_max_dirres) + 4 * RES_DINODE + 4 * RES_LEAF + RES_STATFS + RES_QUOTA + 4, 0); if (error) diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c index e5af9dc420e..e443966c810 100644 --- a/fs/gfs2/ops_fstype.c +++ b/fs/gfs2/ops_fstype.c @@ -19,6 +19,7 @@ #include <linux/mount.h> #include <linux/gfs2_ondisk.h> #include <linux/quotaops.h> +#include <linux/lockdep.h> #include "gfs2.h" #include "incore.h" @@ -766,6 +767,7 @@ fail: return error; } +static struct lock_class_key gfs2_quota_imutex_key; static int init_inodes(struct gfs2_sbd *sdp, int undo) { @@ -803,6 +805,12 @@ static int init_inodes(struct gfs2_sbd *sdp, int undo) fs_err(sdp, "can't get quota file inode: %d\n", error); goto fail_rindex; } + /* + * i_mutex on quota files is special. Since this inode is hidden system + * file, we are safe to define locking ourselves. + */ + lockdep_set_class(&sdp->sd_quota_inode->i_mutex, + &gfs2_quota_imutex_key); error = gfs2_rindex_update(sdp); if (error) diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c index a3bde91645c..4021deca61e 100644 --- a/fs/gfs2/quota.c +++ b/fs/gfs2/quota.c @@ -765,6 +765,7 @@ static int do_sync(unsigned int num_qd, struct gfs2_quota_data **qda) struct gfs2_holder *ghs, i_gh; unsigned int qx, x; struct gfs2_quota_data *qd; + unsigned reserved; loff_t offset; unsigned int nalloc = 0, blocks; int error; @@ -781,7 +782,7 @@ static int do_sync(unsigned int num_qd, struct gfs2_quota_data **qda) return -ENOMEM; sort(qda, num_qd, sizeof(struct gfs2_quota_data *), sort_qd, NULL); - mutex_lock_nested(&ip->i_inode.i_mutex, I_MUTEX_QUOTA); + mutex_lock(&ip->i_inode.i_mutex); for (qx = 0; qx < num_qd; qx++) { error = gfs2_glock_nq_init(qda[qx]->qd_gl, LM_ST_EXCLUSIVE, GL_NOCACHE, &ghs[qx]); @@ -811,13 +812,13 @@ static int do_sync(unsigned int num_qd, struct gfs2_quota_data **qda) * two blocks need to be updated instead of 1 */ blocks = num_qd * data_blocks + RES_DINODE + num_qd + 3; - error = gfs2_inplace_reserve(ip, 1 + - (nalloc * (data_blocks + ind_blocks))); + reserved = 1 + (nalloc * (data_blocks + ind_blocks)); + error = gfs2_inplace_reserve(ip, reserved); if (error) goto out_alloc; if (nalloc) - blocks += gfs2_rg_blocks(ip) + nalloc * ind_blocks + RES_STATFS; + blocks += gfs2_rg_blocks(ip, reserved) + nalloc * ind_blocks + RES_STATFS; error = gfs2_trans_begin(sdp, blocks, 0); if (error) @@ -1598,7 +1599,7 @@ static int gfs2_set_dqblk(struct super_block *sb, int type, qid_t id, error = gfs2_inplace_reserve(ip, blocks); if (error) goto out_i; - blocks += gfs2_rg_blocks(ip); + blocks += gfs2_rg_blocks(ip, blocks); } /* Some quotas span block boundaries and can update two blocks, diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c index c9ed814eeb6..3cc402ce6fe 100644 --- a/fs/gfs2/rgrp.c +++ b/fs/gfs2/rgrp.c @@ -35,9 +35,6 @@ #define BFITNOENT ((u32)~0) #define NO_BLOCK ((u64)~0) -#define RSRV_CONTENTION_FACTOR 4 -#define RGRP_RSRV_MAX_CONTENDERS 2 - #if BITS_PER_LONG == 32 #define LBITMASK (0x55555555UL) #define LBITSKIP55 (0x55555555UL) @@ -67,53 +64,48 @@ static const char valid_change[16] = { 1, 0, 0, 0 }; -static u32 rgblk_search(struct gfs2_rgrpd *rgd, u32 goal, - unsigned char old_state, - struct gfs2_bitmap **rbi); +static int gfs2_rbm_find(struct gfs2_rbm *rbm, u8 state, u32 minext, + const struct gfs2_inode *ip, bool nowrap); + /** * gfs2_setbit - Set a bit in the bitmaps - * @rgd: the resource group descriptor - * @buf2: the clone buffer that holds the bitmaps - * @bi: the bitmap structure - * @block: the block to set + * @rbm: The position of the bit to set + * @do_clone: Also set the clone bitmap, if it exists * @new_state: the new state of the block * */ -static inline void gfs2_setbit(struct gfs2_rgrpd *rgd, unsigned char *buf2, - struct gfs2_bitmap *bi, u32 block, +static inline void gfs2_setbit(const struct gfs2_rbm *rbm, bool do_clone, unsigned char new_state) { unsigned char *byte1, *byte2, *end, cur_state; - unsigned int buflen = bi->bi_len; - const unsigned int bit = (block % GFS2_NBBY) * GFS2_BIT_SIZE; + unsigned int buflen = rbm->bi->bi_len; + const unsigned int bit = (rbm->offset % GFS2_NBBY) * GFS2_BIT_SIZE; - byte1 = bi->bi_bh->b_data + bi->bi_offset + (block / GFS2_NBBY); - end = bi->bi_bh->b_data + bi->bi_offset + buflen; + byte1 = rbm->bi->bi_bh->b_data + rbm->bi->bi_offset + (rbm->offset / GFS2_NBBY); + end = rbm->bi->bi_bh->b_data + rbm->bi->bi_offset + buflen; BUG_ON(byte1 >= end); cur_state = (*byte1 >> bit) & GFS2_BIT_MASK; if (unlikely(!valid_change[new_state * 4 + cur_state])) { - printk(KERN_WARNING "GFS2: buf_blk = 0x%llx old_state=%d, " - "new_state=%d\n", - (unsigned long long)block, cur_state, new_state); - printk(KERN_WARNING "GFS2: rgrp=0x%llx bi_start=0x%lx\n", - (unsigned long long)rgd->rd_addr, - (unsigned long)bi->bi_start); - printk(KERN_WARNING "GFS2: bi_offset=0x%lx bi_len=0x%lx\n", - (unsigned long)bi->bi_offset, - (unsigned long)bi->bi_len); + printk(KERN_WARNING "GFS2: buf_blk = 0x%x old_state=%d, " + "new_state=%d\n", rbm->offset, cur_state, new_state); + printk(KERN_WARNING "GFS2: rgrp=0x%llx bi_start=0x%x\n", + (unsigned long long)rbm->rgd->rd_addr, + rbm->bi->bi_start); + printk(KERN_WARNING "GFS2: bi_offset=0x%x bi_len=0x%x\n", + rbm->bi->bi_offset, rbm->bi->bi_len); dump_stack(); - gfs2_consist_rgrpd(rgd); + gfs2_consist_rgrpd(rbm->rgd); return; } *byte1 ^= (cur_state ^ new_state) << bit; - if (buf2) { - byte2 = buf2 + bi->bi_offset + (block / GFS2_NBBY); + if (do_clone && rbm->bi->bi_clone) { + byte2 = rbm->bi->bi_clone + rbm->bi->bi_offset + (rbm->offset / GFS2_NBBY); cur_state = (*byte2 >> bit) & GFS2_BIT_MASK; *byte2 ^= (cur_state ^ new_state) << bit; } @@ -121,30 +113,21 @@ static inline void gfs2_setbit(struct gfs2_rgrpd *rgd, unsigned char *buf2, /** * gfs2_testbit - test a bit in the bitmaps - * @rgd: the resource group descriptor - * @buffer: the buffer that holds the bitmaps - * @buflen: the length (in bytes) of the buffer - * @block: the block to read + * @rbm: The bit to test * + * Returns: The two bit block state of the requested bit */ -static inline unsigned char gfs2_testbit(struct gfs2_rgrpd *rgd, - const unsigned char *buffer, - unsigned int buflen, u32 block) +static inline u8 gfs2_testbit(const struct gfs2_rbm *rbm) { - const unsigned char *byte, *end; - unsigned char cur_state; + const u8 *buffer = rbm->bi->bi_bh->b_data + rbm->bi->bi_offset; + const u8 *byte; unsigned int bit; - byte = buffer + (block / GFS2_NBBY); - bit = (block % GFS2_NBBY) * GFS2_BIT_SIZE; - end = buffer + buflen; - - gfs2_assert(rgd->rd_sbd, byte < end); + byte = buffer + (rbm->offset / GFS2_NBBY); + bit = (rbm->offset % GFS2_NBBY) * GFS2_BIT_SIZE; - cur_state = (*byte >> bit) & GFS2_BIT_MASK; - - return cur_state; + return (*byte >> bit) & GFS2_BIT_MASK; } /** @@ -192,7 +175,7 @@ static inline u64 gfs2_bit_search(const __le64 *ptr, u64 mask, u8 state) */ static inline int rs_cmp(u64 blk, u32 len, struct gfs2_blkreserv *rs) { - u64 startblk = gfs2_rs_startblk(rs); + u64 startblk = gfs2_rbm_to_block(&rs->rs_rbm); if (blk >= startblk + rs->rs_free) return 1; @@ -202,36 +185,6 @@ static inline int rs_cmp(u64 blk, u32 len, struct gfs2_blkreserv *rs) } /** - * rs_find - Find a rgrp multi-block reservation that contains a given block - * @rgd: The rgrp - * @rgblk: The block we're looking for, relative to the rgrp - */ -static struct gfs2_blkreserv *rs_find(struct gfs2_rgrpd *rgd, u32 rgblk) -{ - struct rb_node **newn; - int rc; - u64 fsblk = rgblk + rgd->rd_data0; - - spin_lock(&rgd->rd_rsspin); - newn = &rgd->rd_rstree.rb_node; - while (*newn) { - struct gfs2_blkreserv *cur = - rb_entry(*newn, struct gfs2_blkreserv, rs_node); - rc = rs_cmp(fsblk, 1, cur); - if (rc < 0) - newn = &((*newn)->rb_left); - else if (rc > 0) - newn = &((*newn)->rb_right); - else { - spin_unlock(&rgd->rd_rsspin); - return cur; - } - } - spin_unlock(&rgd->rd_rsspin); - return NULL; -} - -/** * gfs2_bitfit - Search an rgrp's bitmap buffer to find a bit-pair representing * a block in a given allocation state. * @buf: the buffer that holds the bitmaps @@ -262,8 +215,6 @@ static u32 gfs2_bitfit(const u8 *buf, const unsigned int len, u64 mask = 0x5555555555555555ULL; u32 bit; - BUG_ON(state > 3); - /* Mask off bits we don't care about at the start of the search */ mask <<= spoint; tmp = gfs2_bit_search(ptr, mask, state); @@ -285,6 +236,131 @@ static u32 gfs2_bitfit(const u8 *buf, const unsigned int len, } /** + * gfs2_rbm_from_block - Set the rbm based upon rgd and block number + * @rbm: The rbm with rgd already set correctly + * @block: The block number (filesystem relative) + * + * This sets the bi and offset members of an rbm based on a + * resource group and a filesystem relative block number. The + * resource group must be set in the rbm on entry, the bi and + * offset members will be set by this function. + * + * Returns: 0 on success, or an error code + */ + +static int gfs2_rbm_from_block(struct gfs2_rbm *rbm, u64 block) +{ + u64 rblock = block - rbm->rgd->rd_data0; + u32 goal = (u32)rblock; + int x; + + if (WARN_ON_ONCE(rblock > UINT_MAX)) + return -EINVAL; + if (block >= rbm->rgd->rd_data0 + rbm->rgd->rd_data) + return -E2BIG; + + for (x = 0; x < rbm->rgd->rd_length; x++) { + rbm->bi = rbm->rgd->rd_bits + x; + if (goal < (rbm->bi->bi_start + rbm->bi->bi_len) * GFS2_NBBY) { + rbm->offset = goal - (rbm->bi->bi_start * GFS2_NBBY); + break; + } + } + + return 0; +} + +/** + * gfs2_unaligned_extlen - Look for free blocks which are not byte aligned + * @rbm: Position to search (value/result) + * @n_unaligned: Number of unaligned blocks to check + * @len: Decremented for each block found (terminate on zero) + * + * Returns: true if a non-free block is encountered + */ + +static bool gfs2_unaligned_extlen(struct gfs2_rbm *rbm, u32 n_unaligned, u32 *len) +{ + u64 block; + u32 n; + u8 res; + + for (n = 0; n < n_unaligned; n++) { + res = gfs2_testbit(rbm); + if (res != GFS2_BLKST_FREE) + return true; + (*len)--; + if (*len == 0) + return true; + block = gfs2_rbm_to_block(rbm); + if (gfs2_rbm_from_block(rbm, block + 1)) + return true; + } + + return false; +} + +/** + * gfs2_free_extlen - Return extent length of free blocks + * @rbm: Starting position + * @len: Max length to check + * + * Starting at the block specified by the rbm, see how many free blocks + * there are, not reading more than len blocks ahead. This can be done + * using memchr_inv when the blocks are byte aligned, but has to be done + * on a block by block basis in case of unaligned blocks. Also this + * function can cope with bitmap boundaries (although it must stop on + * a resource group boundary) + * + * Returns: Number of free blocks in the extent + */ + +static u32 gfs2_free_extlen(const struct gfs2_rbm *rrbm, u32 len) +{ + struct gfs2_rbm rbm = *rrbm; + u32 n_unaligned = rbm.offset & 3; + u32 size = len; + u32 bytes; + u32 chunk_size; + u8 *ptr, *start, *end; + u64 block; + + if (n_unaligned && + gfs2_unaligned_extlen(&rbm, 4 - n_unaligned, &len)) + goto out; + + n_unaligned = len & 3; + /* Start is now byte aligned */ + while (len > 3) { + start = rbm.bi->bi_bh->b_data; + if (rbm.bi->bi_clone) + start = rbm.bi->bi_clone; + end = start + rbm.bi->bi_bh->b_size; + start += rbm.bi->bi_offset; + BUG_ON(rbm.offset & 3); + start += (rbm.offset / GFS2_NBBY); + bytes = min_t(u32, len / GFS2_NBBY, (end - start)); + ptr = memchr_inv(start, 0, bytes); + chunk_size = ((ptr == NULL) ? bytes : (ptr - start)); + chunk_size *= GFS2_NBBY; + BUG_ON(len < chunk_size); + len -= chunk_size; + block = gfs2_rbm_to_block(&rbm); + gfs2_rbm_from_block(&rbm, block + chunk_size); + n_unaligned = 3; + if (ptr) + break; + n_unaligned = len & 3; + } + + /* Deal with any bits left over at the end */ + if (n_unaligned) + gfs2_unaligned_extlen(&rbm, n_unaligned, &len); +out: + return size - len; +} + +/** * gfs2_bitcount - count the number of bits in a certain state * @rgd: the resource group descriptor * @buffer: the buffer that holds the bitmaps @@ -487,6 +563,8 @@ int gfs2_rs_alloc(struct gfs2_inode *ip) if (!res) error = -ENOMEM; + RB_CLEAR_NODE(&res->rs_node); + down_write(&ip->i_rw_mutex); if (ip->i_res) kmem_cache_free(gfs2_rsrv_cachep, res); @@ -496,11 +574,12 @@ int gfs2_rs_alloc(struct gfs2_inode *ip) return error; } -static void dump_rs(struct seq_file *seq, struct gfs2_blkreserv *rs) +static void dump_rs(struct seq_file *seq, const struct gfs2_blkreserv *rs) { - gfs2_print_dbg(seq, " r: %llu s:%llu b:%u f:%u\n", - rs->rs_rgd->rd_addr, gfs2_rs_startblk(rs), rs->rs_biblk, - rs->rs_free); + gfs2_print_dbg(seq, " B: n:%llu s:%llu b:%u f:%u\n", + (unsigned long long)rs->rs_inum, + (unsigned long long)gfs2_rbm_to_block(&rs->rs_rbm), + rs->rs_rbm.offset, rs->rs_free); } /** @@ -508,41 +587,26 @@ static void dump_rs(struct seq_file *seq, struct gfs2_blkreserv *rs) * @rs: The reservation to remove * */ -static void __rs_deltree(struct gfs2_blkreserv *rs) +static void __rs_deltree(struct gfs2_inode *ip, struct gfs2_blkreserv *rs) { struct gfs2_rgrpd *rgd; if (!gfs2_rs_active(rs)) return; - rgd = rs->rs_rgd; - /* We can't do this: The reason is that when the rgrp is invalidated, - it's in the "middle" of acquiring the glock, but the HOLDER bit - isn't set yet: - BUG_ON(!gfs2_glock_is_locked_by_me(rs->rs_rgd->rd_gl));*/ - trace_gfs2_rs(NULL, rs, TRACE_RS_TREEDEL); - - if (!RB_EMPTY_ROOT(&rgd->rd_rstree)) - rb_erase(&rs->rs_node, &rgd->rd_rstree); - BUG_ON(!rgd->rd_rs_cnt); - rgd->rd_rs_cnt--; + rgd = rs->rs_rbm.rgd; + trace_gfs2_rs(rs, TRACE_RS_TREEDEL); + rb_erase(&rs->rs_node, &rgd->rd_rstree); + RB_CLEAR_NODE(&rs->rs_node); if (rs->rs_free) { /* return reserved blocks to the rgrp and the ip */ - BUG_ON(rs->rs_rgd->rd_reserved < rs->rs_free); - rs->rs_rgd->rd_reserved -= rs->rs_free; + BUG_ON(rs->rs_rbm.rgd->rd_reserved < rs->rs_free); + rs->rs_rbm.rgd->rd_reserved -= rs->rs_free; rs->rs_free = 0; - clear_bit(GBF_FULL, &rs->rs_bi->bi_flags); + clear_bit(GBF_FULL, &rs->rs_rbm.bi->bi_flags); smp_mb__after_clear_bit(); } - /* We can't change any of the step 1 or step 2 components of the rs. - E.g. We can't set rs_rgd to NULL because the rgd glock is held and - dequeued through this pointer. - Can't: atomic_set(&rs->rs_sizehint, 0); - Can't: rs->rs_requested = 0; - Can't: rs->rs_rgd = NULL;*/ - rs->rs_bi = NULL; - rs->rs_biblk = 0; } /** @@ -550,17 +614,16 @@ static void __rs_deltree(struct gfs2_blkreserv *rs) * @rs: The reservation to remove * */ -void gfs2_rs_deltree(struct gfs2_blkreserv *rs) +void gfs2_rs_deltree(struct gfs2_inode *ip, struct gfs2_blkreserv *rs) { struct gfs2_rgrpd *rgd; - if (!gfs2_rs_active(rs)) - return; - - rgd = rs->rs_rgd; - spin_lock(&rgd->rd_rsspin); - __rs_deltree(rs); - spin_unlock(&rgd->rd_rsspin); + rgd = rs->rs_rbm.rgd; + if (rgd) { + spin_lock(&rgd->rd_rsspin); + __rs_deltree(ip, rs); + spin_unlock(&rgd->rd_rsspin); + } } /** @@ -572,8 +635,7 @@ void gfs2_rs_delete(struct gfs2_inode *ip) { down_write(&ip->i_rw_mutex); if (ip->i_res) { - gfs2_rs_deltree(ip->i_res); - trace_gfs2_rs(ip, ip->i_res, TRACE_RS_DELETE); + gfs2_rs_deltree(ip, ip->i_res); BUG_ON(ip->i_res->rs_free); kmem_cache_free(gfs2_rsrv_cachep, ip->i_res); ip->i_res = NULL; @@ -597,7 +659,7 @@ static void return_all_reservations(struct gfs2_rgrpd *rgd) spin_lock(&rgd->rd_rsspin); while ((n = rb_first(&rgd->rd_rstree))) { rs = rb_entry(n, struct gfs2_blkreserv, rs_node); - __rs_deltree(rs); + __rs_deltree(NULL, rs); } spin_unlock(&rgd->rd_rsspin); } @@ -1270,211 +1332,276 @@ out: /** * rs_insert - insert a new multi-block reservation into the rgrp's rb_tree - * @bi: the bitmap with the blocks * @ip: the inode structure - * @biblk: the 32-bit block number relative to the start of the bitmap - * @amount: the number of blocks to reserve * - * Returns: NULL - reservation was already taken, so not inserted - * pointer to the inserted reservation */ -static struct gfs2_blkreserv *rs_insert(struct gfs2_bitmap *bi, - struct gfs2_inode *ip, u32 biblk, - int amount) +static void rs_insert(struct gfs2_inode *ip) { struct rb_node **newn, *parent = NULL; int rc; struct gfs2_blkreserv *rs = ip->i_res; - struct gfs2_rgrpd *rgd = rs->rs_rgd; - u64 fsblock = gfs2_bi2rgd_blk(bi, biblk) + rgd->rd_data0; + struct gfs2_rgrpd *rgd = rs->rs_rbm.rgd; + u64 fsblock = gfs2_rbm_to_block(&rs->rs_rbm); + + BUG_ON(gfs2_rs_active(rs)); spin_lock(&rgd->rd_rsspin); newn = &rgd->rd_rstree.rb_node; - BUG_ON(!ip->i_res); - BUG_ON(gfs2_rs_active(rs)); - /* Figure out where to put new node */ - /*BUG_ON(!gfs2_glock_is_locked_by_me(rgd->rd_gl));*/ while (*newn) { struct gfs2_blkreserv *cur = rb_entry(*newn, struct gfs2_blkreserv, rs_node); parent = *newn; - rc = rs_cmp(fsblock, amount, cur); + rc = rs_cmp(fsblock, rs->rs_free, cur); if (rc > 0) newn = &((*newn)->rb_right); else if (rc < 0) newn = &((*newn)->rb_left); else { spin_unlock(&rgd->rd_rsspin); - return NULL; /* reservation already in use */ + WARN_ON(1); + return; } } - /* Do our reservation work */ - rs = ip->i_res; - rs->rs_free = amount; - rs->rs_biblk = biblk; - rs->rs_bi = bi; rb_link_node(&rs->rs_node, parent, newn); rb_insert_color(&rs->rs_node, &rgd->rd_rstree); - /* Do our inode accounting for the reservation */ - /*BUG_ON(!gfs2_glock_is_locked_by_me(ip->i_gl));*/ - /* Do our rgrp accounting for the reservation */ - rgd->rd_reserved += amount; /* blocks reserved */ - rgd->rd_rs_cnt++; /* number of in-tree reservations */ + rgd->rd_reserved += rs->rs_free; /* blocks reserved */ spin_unlock(&rgd->rd_rsspin); - trace_gfs2_rs(ip, rs, TRACE_RS_INSERT); - return rs; -} - -/** - * unclaimed_blocks - return number of blocks that aren't spoken for - */ -static u32 unclaimed_blocks(struct gfs2_rgrpd *rgd) -{ - return rgd->rd_free_clone - rgd->rd_reserved; + trace_gfs2_rs(rs, TRACE_RS_INSERT); } /** - * rg_mblk_search - find a group of multiple free blocks + * rg_mblk_search - find a group of multiple free blocks to form a reservation * @rgd: the resource group descriptor - * @rs: the block reservation * @ip: pointer to the inode for which we're reserving blocks + * @requested: number of blocks required for this allocation * - * This is very similar to rgblk_search, except we're looking for whole - * 64-bit words that represent a chunk of 32 free blocks. I'm only focusing - * on aligned dwords for speed's sake. - * - * Returns: 0 if successful or BFITNOENT if there isn't enough free space */ -static int rg_mblk_search(struct gfs2_rgrpd *rgd, struct gfs2_inode *ip) +static void rg_mblk_search(struct gfs2_rgrpd *rgd, struct gfs2_inode *ip, + unsigned requested) { - struct gfs2_bitmap *bi = rgd->rd_bits; - const u32 length = rgd->rd_length; - u32 blk; - unsigned int buf, x, search_bytes; - u8 *buffer = NULL; - u8 *ptr, *end, *nonzero; - u32 goal, rsv_bytes; - struct gfs2_blkreserv *rs; - u32 best_rs_bytes, unclaimed; - int best_rs_blocks; + struct gfs2_rbm rbm = { .rgd = rgd, }; + u64 goal; + struct gfs2_blkreserv *rs = ip->i_res; + u32 extlen; + u32 free_blocks = rgd->rd_free_clone - rgd->rd_reserved; + int ret; + + extlen = max_t(u32, atomic_read(&rs->rs_sizehint), requested); + extlen = clamp(extlen, RGRP_RSRV_MINBLKS, free_blocks); + if ((rgd->rd_free_clone < rgd->rd_reserved) || (free_blocks < extlen)) + return; /* Find bitmap block that contains bits for goal block */ if (rgrp_contains_block(rgd, ip->i_goal)) - goal = ip->i_goal - rgd->rd_data0; + goal = ip->i_goal; else - goal = rgd->rd_last_alloc; - for (buf = 0; buf < length; buf++) { - bi = rgd->rd_bits + buf; - /* Convert scope of "goal" from rgrp-wide to within - found bit block */ - if (goal < (bi->bi_start + bi->bi_len) * GFS2_NBBY) { - goal -= bi->bi_start * GFS2_NBBY; - goto do_search; - } + goal = rgd->rd_last_alloc + rgd->rd_data0; + + if (WARN_ON(gfs2_rbm_from_block(&rbm, goal))) + return; + + ret = gfs2_rbm_find(&rbm, GFS2_BLKST_FREE, extlen, ip, true); + if (ret == 0) { + rs->rs_rbm = rbm; + rs->rs_free = extlen; + rs->rs_inum = ip->i_no_addr; + rs_insert(ip); } - buf = 0; - goal = 0; - -do_search: - best_rs_blocks = max_t(int, atomic_read(&ip->i_res->rs_sizehint), - (RGRP_RSRV_MINBLKS * rgd->rd_length)); - best_rs_bytes = (best_rs_blocks * - (1 + (RSRV_CONTENTION_FACTOR * rgd->rd_rs_cnt))) / - GFS2_NBBY; /* 1 + is for our not-yet-created reservation */ - best_rs_bytes = ALIGN(best_rs_bytes, sizeof(u64)); - unclaimed = unclaimed_blocks(rgd); - if (best_rs_bytes * GFS2_NBBY > unclaimed) - best_rs_bytes = unclaimed >> GFS2_BIT_SIZE; - - for (x = 0; x <= length; x++) { - bi = rgd->rd_bits + buf; +} + +/** + * gfs2_next_unreserved_block - Return next block that is not reserved + * @rgd: The resource group + * @block: The starting block + * @length: The required length + * @ip: Ignore any reservations for this inode + * + * If the block does not appear in any reservation, then return the + * block number unchanged. If it does appear in the reservation, then + * keep looking through the tree of reservations in order to find the + * first block number which is not reserved. + */ - if (test_bit(GBF_FULL, &bi->bi_flags)) - goto skip; +static u64 gfs2_next_unreserved_block(struct gfs2_rgrpd *rgd, u64 block, + u32 length, + const struct gfs2_inode *ip) +{ + struct gfs2_blkreserv *rs; + struct rb_node *n; + int rc; - WARN_ON(!buffer_uptodate(bi->bi_bh)); - if (bi->bi_clone) - buffer = bi->bi_clone + bi->bi_offset; + spin_lock(&rgd->rd_rsspin); + n = rgd->rd_rstree.rb_node; + while (n) { + rs = rb_entry(n, struct gfs2_blkreserv, rs_node); + rc = rs_cmp(block, length, rs); + if (rc < 0) + n = n->rb_left; + else if (rc > 0) + n = n->rb_right; else - buffer = bi->bi_bh->b_data + bi->bi_offset; - - /* We have to keep the reservations aligned on u64 boundaries - otherwise we could get situations where a byte can't be - used because it's after a reservation, but a free bit still - is within the reservation's area. */ - ptr = buffer + ALIGN(goal >> GFS2_BIT_SIZE, sizeof(u64)); - end = (buffer + bi->bi_len); - while (ptr < end) { - rsv_bytes = 0; - if ((ptr + best_rs_bytes) <= end) - search_bytes = best_rs_bytes; - else - search_bytes = end - ptr; - BUG_ON(!search_bytes); - nonzero = memchr_inv(ptr, 0, search_bytes); - /* If the lot is all zeroes, reserve the whole size. If - there's enough zeroes to satisfy the request, use - what we can. If there's not enough, keep looking. */ - if (nonzero == NULL) - rsv_bytes = search_bytes; - else if ((nonzero - ptr) * GFS2_NBBY >= - ip->i_res->rs_requested) - rsv_bytes = (nonzero - ptr); - - if (rsv_bytes) { - blk = ((ptr - buffer) * GFS2_NBBY); - BUG_ON(blk >= bi->bi_len * GFS2_NBBY); - rs = rs_insert(bi, ip, blk, - rsv_bytes * GFS2_NBBY); - if (IS_ERR(rs)) - return PTR_ERR(rs); - if (rs) - return 0; - } - ptr += ALIGN(search_bytes, sizeof(u64)); + break; + } + + if (n) { + while ((rs_cmp(block, length, rs) == 0) && (ip->i_res != rs)) { + block = gfs2_rbm_to_block(&rs->rs_rbm) + rs->rs_free; + n = n->rb_right; + if (n == NULL) + break; + rs = rb_entry(n, struct gfs2_blkreserv, rs_node); } -skip: - /* Try next bitmap block (wrap back to rgrp header - if at end) */ - buf++; - buf %= length; - goal = 0; } - return BFITNOENT; + spin_unlock(&rgd->rd_rsspin); + return block; } /** - * try_rgrp_fit - See if a given reservation will fit in a given RG - * @rgd: the RG data - * @ip: the inode + * gfs2_reservation_check_and_update - Check for reservations during block alloc + * @rbm: The current position in the resource group + * @ip: The inode for which we are searching for blocks + * @minext: The minimum extent length * - * If there's room for the requested blocks to be allocated from the RG: - * This will try to get a multi-block reservation first, and if that doesn't - * fit, it will take what it can. + * This checks the current position in the rgrp to see whether there is + * a reservation covering this block. If not then this function is a + * no-op. If there is, then the position is moved to the end of the + * contiguous reservation(s) so that we are pointing at the first + * non-reserved block. * - * Returns: 1 on success (it fits), 0 on failure (it doesn't fit) + * Returns: 0 if no reservation, 1 if @rbm has changed, otherwise an error */ -static int try_rgrp_fit(struct gfs2_rgrpd *rgd, struct gfs2_inode *ip) +static int gfs2_reservation_check_and_update(struct gfs2_rbm *rbm, + const struct gfs2_inode *ip, + u32 minext) { - struct gfs2_blkreserv *rs = ip->i_res; + u64 block = gfs2_rbm_to_block(rbm); + u32 extlen = 1; + u64 nblock; + int ret; - if (rgd->rd_flags & (GFS2_RGF_NOALLOC | GFS2_RDF_ERROR)) + /* + * If we have a minimum extent length, then skip over any extent + * which is less than the min extent length in size. + */ + if (minext) { + extlen = gfs2_free_extlen(rbm, minext); + nblock = block + extlen; + if (extlen < minext) + goto fail; + } + + /* + * Check the extent which has been found against the reservations + * and skip if parts of it are already reserved + */ + nblock = gfs2_next_unreserved_block(rbm->rgd, block, extlen, ip); + if (nblock == block) return 0; - /* Look for a multi-block reservation. */ - if (unclaimed_blocks(rgd) >= RGRP_RSRV_MINBLKS && - rg_mblk_search(rgd, ip) != BFITNOENT) - return 1; - if (unclaimed_blocks(rgd) >= rs->rs_requested) - return 1; +fail: + ret = gfs2_rbm_from_block(rbm, nblock); + if (ret < 0) + return ret; + return 1; +} - return 0; +/** + * gfs2_rbm_find - Look for blocks of a particular state + * @rbm: Value/result starting position and final position + * @state: The state which we want to find + * @minext: The requested extent length (0 for a single block) + * @ip: If set, check for reservations + * @nowrap: Stop looking at the end of the rgrp, rather than wrapping + * around until we've reached the starting point. + * + * Side effects: + * - If looking for free blocks, we set GBF_FULL on each bitmap which + * has no free blocks in it. + * + * Returns: 0 on success, -ENOSPC if there is no block of the requested state + */ + +static int gfs2_rbm_find(struct gfs2_rbm *rbm, u8 state, u32 minext, + const struct gfs2_inode *ip, bool nowrap) +{ + struct buffer_head *bh; + struct gfs2_bitmap *initial_bi; + u32 initial_offset; + u32 offset; + u8 *buffer; + int index; + int n = 0; + int iters = rbm->rgd->rd_length; + int ret; + + /* If we are not starting at the beginning of a bitmap, then we + * need to add one to the bitmap count to ensure that we search + * the starting bitmap twice. + */ + if (rbm->offset != 0) + iters++; + + while(1) { + if (test_bit(GBF_FULL, &rbm->bi->bi_flags) && + (state == GFS2_BLKST_FREE)) + goto next_bitmap; + + bh = rbm->bi->bi_bh; + buffer = bh->b_data + rbm->bi->bi_offset; + WARN_ON(!buffer_uptodate(bh)); + if (state != GFS2_BLKST_UNLINKED && rbm->bi->bi_clone) + buffer = rbm->bi->bi_clone + rbm->bi->bi_offset; + initial_offset = rbm->offset; + offset = gfs2_bitfit(buffer, rbm->bi->bi_len, rbm->offset, state); + if (offset == BFITNOENT) + goto bitmap_full; + rbm->offset = offset; + if (ip == NULL) + return 0; + + initial_bi = rbm->bi; + ret = gfs2_reservation_check_and_update(rbm, ip, minext); + if (ret == 0) + return 0; + if (ret > 0) { + n += (rbm->bi - initial_bi); + goto next_iter; + } + if (ret == -E2BIG) { + index = 0; + rbm->offset = 0; + n += (rbm->bi - initial_bi); + goto res_covered_end_of_rgrp; + } + return ret; + +bitmap_full: /* Mark bitmap as full and fall through */ + if ((state == GFS2_BLKST_FREE) && initial_offset == 0) + set_bit(GBF_FULL, &rbm->bi->bi_flags); + +next_bitmap: /* Find next bitmap in the rgrp */ + rbm->offset = 0; + index = rbm->bi - rbm->rgd->rd_bits; + index++; + if (index == rbm->rgd->rd_length) + index = 0; +res_covered_end_of_rgrp: + rbm->bi = &rbm->rgd->rd_bits[index]; + if ((index == 0) && nowrap) + break; + n++; +next_iter: + if (n >= iters) + break; + } + + return -ENOSPC; } /** @@ -1489,34 +1616,33 @@ static int try_rgrp_fit(struct gfs2_rgrpd *rgd, struct gfs2_inode *ip) static void try_rgrp_unlink(struct gfs2_rgrpd *rgd, u64 *last_unlinked, u64 skip) { - u32 goal = 0, block; - u64 no_addr; + u64 block; struct gfs2_sbd *sdp = rgd->rd_sbd; struct gfs2_glock *gl; struct gfs2_inode *ip; int error; int found = 0; - struct gfs2_bitmap *bi; + struct gfs2_rbm rbm = { .rgd = rgd, .bi = rgd->rd_bits, .offset = 0 }; - while (goal < rgd->rd_data) { + while (1) { down_write(&sdp->sd_log_flush_lock); - block = rgblk_search(rgd, goal, GFS2_BLKST_UNLINKED, &bi); + error = gfs2_rbm_find(&rbm, GFS2_BLKST_UNLINKED, 0, NULL, true); up_write(&sdp->sd_log_flush_lock); - if (block == BFITNOENT) + if (error == -ENOSPC) + break; + if (WARN_ON_ONCE(error)) break; - block = gfs2_bi2rgd_blk(bi, block); - /* rgblk_search can return a block < goal, so we need to - keep it marching forward. */ - no_addr = block + rgd->rd_data0; - goal = max(block + 1, goal + 1); - if (*last_unlinked != NO_BLOCK && no_addr <= *last_unlinked) + block = gfs2_rbm_to_block(&rbm); + if (gfs2_rbm_from_block(&rbm, block + 1)) + break; + if (*last_unlinked != NO_BLOCK && block <= *last_unlinked) continue; - if (no_addr == skip) + if (block == skip) continue; - *last_unlinked = no_addr; + *last_unlinked = block; - error = gfs2_glock_get(sdp, no_addr, &gfs2_inode_glops, CREATE, &gl); + error = gfs2_glock_get(sdp, block, &gfs2_inode_glops, CREATE, &gl); if (error) continue; @@ -1543,6 +1669,19 @@ static void try_rgrp_unlink(struct gfs2_rgrpd *rgd, u64 *last_unlinked, u64 skip return; } +static bool gfs2_select_rgrp(struct gfs2_rgrpd **pos, const struct gfs2_rgrpd *begin) +{ + struct gfs2_rgrpd *rgd = *pos; + + rgd = gfs2_rgrpd_get_next(rgd); + if (rgd == NULL) + rgd = gfs2_rgrpd_get_next(NULL); + *pos = rgd; + if (rgd != begin) /* If we didn't wrap */ + return true; + return false; +} + /** * gfs2_inplace_reserve - Reserve space in the filesystem * @ip: the inode to reserve space for @@ -1562,103 +1701,96 @@ int gfs2_inplace_reserve(struct gfs2_inode *ip, u32 requested) if (sdp->sd_args.ar_rgrplvb) flags |= GL_SKIP; - rs->rs_requested = requested; - if (gfs2_assert_warn(sdp, requested)) { - error = -EINVAL; - goto out; - } + if (gfs2_assert_warn(sdp, requested)) + return -EINVAL; if (gfs2_rs_active(rs)) { - begin = rs->rs_rgd; + begin = rs->rs_rbm.rgd; flags = 0; /* Yoda: Do or do not. There is no try */ } else if (ip->i_rgd && rgrp_contains_block(ip->i_rgd, ip->i_goal)) { - rs->rs_rgd = begin = ip->i_rgd; + rs->rs_rbm.rgd = begin = ip->i_rgd; } else { - rs->rs_rgd = begin = gfs2_blk2rgrpd(sdp, ip->i_goal, 1); + rs->rs_rbm.rgd = begin = gfs2_blk2rgrpd(sdp, ip->i_goal, 1); } - if (rs->rs_rgd == NULL) + if (rs->rs_rbm.rgd == NULL) return -EBADSLT; while (loops < 3) { - rg_locked = 0; - - if (gfs2_glock_is_locked_by_me(rs->rs_rgd->rd_gl)) { - rg_locked = 1; - error = 0; - } else if (!loops && !gfs2_rs_active(rs) && - rs->rs_rgd->rd_rs_cnt > RGRP_RSRV_MAX_CONTENDERS) { - /* If the rgrp already is maxed out for contenders, - we can eliminate it as a "first pass" without even - requesting the rgrp glock. */ - error = GLR_TRYFAILED; - } else { - error = gfs2_glock_nq_init(rs->rs_rgd->rd_gl, + rg_locked = 1; + + if (!gfs2_glock_is_locked_by_me(rs->rs_rbm.rgd->rd_gl)) { + rg_locked = 0; + error = gfs2_glock_nq_init(rs->rs_rbm.rgd->rd_gl, LM_ST_EXCLUSIVE, flags, &rs->rs_rgd_gh); - if (!error && sdp->sd_args.ar_rgrplvb) { - error = update_rgrp_lvb(rs->rs_rgd); - if (error) { + if (error == GLR_TRYFAILED) + goto next_rgrp; + if (unlikely(error)) + return error; + if (sdp->sd_args.ar_rgrplvb) { + error = update_rgrp_lvb(rs->rs_rbm.rgd); + if (unlikely(error)) { gfs2_glock_dq_uninit(&rs->rs_rgd_gh); return error; } } } - switch (error) { - case 0: - if (gfs2_rs_active(rs)) { - if (unclaimed_blocks(rs->rs_rgd) + - rs->rs_free >= rs->rs_requested) { - ip->i_rgd = rs->rs_rgd; - return 0; - } - /* We have a multi-block reservation, but the - rgrp doesn't have enough free blocks to - satisfy the request. Free the reservation - and look for a suitable rgrp. */ - gfs2_rs_deltree(rs); - } - if (try_rgrp_fit(rs->rs_rgd, ip)) { - if (sdp->sd_args.ar_rgrplvb) - gfs2_rgrp_bh_get(rs->rs_rgd); - ip->i_rgd = rs->rs_rgd; - return 0; - } - if (rs->rs_rgd->rd_flags & GFS2_RDF_CHECK) { - if (sdp->sd_args.ar_rgrplvb) - gfs2_rgrp_bh_get(rs->rs_rgd); - try_rgrp_unlink(rs->rs_rgd, &last_unlinked, - ip->i_no_addr); - } - if (!rg_locked) - gfs2_glock_dq_uninit(&rs->rs_rgd_gh); - /* fall through */ - case GLR_TRYFAILED: - rs->rs_rgd = gfs2_rgrpd_get_next(rs->rs_rgd); - rs->rs_rgd = rs->rs_rgd ? : begin; /* if NULL, wrap */ - if (rs->rs_rgd != begin) /* If we didn't wrap */ - break; - flags &= ~LM_FLAG_TRY; - loops++; - /* Check that fs hasn't grown if writing to rindex */ - if (ip == GFS2_I(sdp->sd_rindex) && - !sdp->sd_rindex_uptodate) { - error = gfs2_ri_update(ip); - if (error) - goto out; - } else if (loops == 2) - /* Flushing the log may release space */ - gfs2_log_flush(sdp, NULL); - break; - default: - goto out; + /* Skip unuseable resource groups */ + if (rs->rs_rbm.rgd->rd_flags & (GFS2_RGF_NOALLOC | GFS2_RDF_ERROR)) + goto skip_rgrp; + + if (sdp->sd_args.ar_rgrplvb) + gfs2_rgrp_bh_get(rs->rs_rbm.rgd); + + /* Get a reservation if we don't already have one */ + if (!gfs2_rs_active(rs)) + rg_mblk_search(rs->rs_rbm.rgd, ip, requested); + + /* Skip rgrps when we can't get a reservation on first pass */ + if (!gfs2_rs_active(rs) && (loops < 1)) + goto check_rgrp; + + /* If rgrp has enough free space, use it */ + if (rs->rs_rbm.rgd->rd_free_clone >= requested) { + ip->i_rgd = rs->rs_rbm.rgd; + return 0; + } + + /* Drop reservation, if we couldn't use reserved rgrp */ + if (gfs2_rs_active(rs)) + gfs2_rs_deltree(ip, rs); +check_rgrp: + /* Check for unlinked inodes which can be reclaimed */ + if (rs->rs_rbm.rgd->rd_flags & GFS2_RDF_CHECK) + try_rgrp_unlink(rs->rs_rbm.rgd, &last_unlinked, + ip->i_no_addr); +skip_rgrp: + /* Unlock rgrp if required */ + if (!rg_locked) + gfs2_glock_dq_uninit(&rs->rs_rgd_gh); +next_rgrp: + /* Find the next rgrp, and continue looking */ + if (gfs2_select_rgrp(&rs->rs_rbm.rgd, begin)) + continue; + + /* If we've scanned all the rgrps, but found no free blocks + * then this checks for some less likely conditions before + * trying again. + */ + flags &= ~LM_FLAG_TRY; + loops++; + /* Check that fs hasn't grown if writing to rindex */ + if (ip == GFS2_I(sdp->sd_rindex) && !sdp->sd_rindex_uptodate) { + error = gfs2_ri_update(ip); + if (error) + return error; } + /* Flushing the log may release space */ + if (loops == 2) + gfs2_log_flush(sdp, NULL); } - error = -ENOSPC; -out: - if (error) - rs->rs_requested = 0; - return error; + return -ENOSPC; } /** @@ -1672,15 +1804,8 @@ void gfs2_inplace_release(struct gfs2_inode *ip) { struct gfs2_blkreserv *rs = ip->i_res; - if (!rs) - return; - - if (!rs->rs_free) - gfs2_rs_deltree(rs); - if (rs->rs_rgd_gh.gh_gl) gfs2_glock_dq_uninit(&rs->rs_rgd_gh); - rs->rs_requested = 0; } /** @@ -1693,173 +1818,47 @@ void gfs2_inplace_release(struct gfs2_inode *ip) static unsigned char gfs2_get_block_type(struct gfs2_rgrpd *rgd, u64 block) { - struct gfs2_bitmap *bi = NULL; - u32 length, rgrp_block, buf_block; - unsigned int buf; - unsigned char type; - - length = rgd->rd_length; - rgrp_block = block - rgd->rd_data0; - - for (buf = 0; buf < length; buf++) { - bi = rgd->rd_bits + buf; - if (rgrp_block < (bi->bi_start + bi->bi_len) * GFS2_NBBY) - break; - } - - gfs2_assert(rgd->rd_sbd, buf < length); - buf_block = rgrp_block - bi->bi_start * GFS2_NBBY; + struct gfs2_rbm rbm = { .rgd = rgd, }; + int ret; - type = gfs2_testbit(rgd, bi->bi_bh->b_data + bi->bi_offset, - bi->bi_len, buf_block); + ret = gfs2_rbm_from_block(&rbm, block); + WARN_ON_ONCE(ret != 0); - return type; + return gfs2_testbit(&rbm); } -/** - * rgblk_search - find a block in @state - * @rgd: the resource group descriptor - * @goal: the goal block within the RG (start here to search for avail block) - * @state: GFS2_BLKST_XXX the before-allocation state to find - * @rbi: address of the pointer to the bitmap containing the block found - * - * Walk rgrp's bitmap to find bits that represent a block in @state. - * - * This function never fails, because we wouldn't call it unless we - * know (from reservation results, etc.) that a block is available. - * - * Scope of @goal is just within rgrp, not the whole filesystem. - * Scope of @returned block is just within bitmap, not the whole filesystem. - * - * Returns: the block number found relative to the bitmap rbi - */ - -static u32 rgblk_search(struct gfs2_rgrpd *rgd, u32 goal, unsigned char state, - struct gfs2_bitmap **rbi) -{ - struct gfs2_bitmap *bi = NULL; - const u32 length = rgd->rd_length; - u32 biblk = BFITNOENT; - unsigned int buf, x; - const u8 *buffer = NULL; - - *rbi = NULL; - /* Find bitmap block that contains bits for goal block */ - for (buf = 0; buf < length; buf++) { - bi = rgd->rd_bits + buf; - /* Convert scope of "goal" from rgrp-wide to within found bit block */ - if (goal < (bi->bi_start + bi->bi_len) * GFS2_NBBY) { - goal -= bi->bi_start * GFS2_NBBY; - goto do_search; - } - } - buf = 0; - goal = 0; - -do_search: - /* Search (up to entire) bitmap in this rgrp for allocatable block. - "x <= length", instead of "x < length", because we typically start - the search in the middle of a bit block, but if we can't find an - allocatable block anywhere else, we want to be able wrap around and - search in the first part of our first-searched bit block. */ - for (x = 0; x <= length; x++) { - bi = rgd->rd_bits + buf; - - if (test_bit(GBF_FULL, &bi->bi_flags) && - (state == GFS2_BLKST_FREE)) - goto skip; - - /* The GFS2_BLKST_UNLINKED state doesn't apply to the clone - bitmaps, so we must search the originals for that. */ - buffer = bi->bi_bh->b_data + bi->bi_offset; - WARN_ON(!buffer_uptodate(bi->bi_bh)); - if (state != GFS2_BLKST_UNLINKED && bi->bi_clone) - buffer = bi->bi_clone + bi->bi_offset; - - while (1) { - struct gfs2_blkreserv *rs; - u32 rgblk; - - biblk = gfs2_bitfit(buffer, bi->bi_len, goal, state); - if (biblk == BFITNOENT) - break; - /* Check if this block is reserved() */ - rgblk = gfs2_bi2rgd_blk(bi, biblk); - rs = rs_find(rgd, rgblk); - if (rs == NULL) - break; - - BUG_ON(rs->rs_bi != bi); - biblk = BFITNOENT; - /* This should jump to the first block after the - reservation. */ - goal = rs->rs_biblk + rs->rs_free; - if (goal >= bi->bi_len * GFS2_NBBY) - break; - } - if (biblk != BFITNOENT) - break; - - if ((goal == 0) && (state == GFS2_BLKST_FREE)) - set_bit(GBF_FULL, &bi->bi_flags); - - /* Try next bitmap block (wrap back to rgrp header if at end) */ -skip: - buf++; - buf %= length; - goal = 0; - } - - if (biblk != BFITNOENT) - *rbi = bi; - - return biblk; -} /** * gfs2_alloc_extent - allocate an extent from a given bitmap - * @rgd: the resource group descriptor - * @bi: the bitmap within the rgrp - * @blk: the block within the bitmap + * @rbm: the resource group information * @dinode: TRUE if the first block we allocate is for a dinode - * @n: The extent length + * @n: The extent length (value/result) * - * Add the found bitmap buffer to the transaction. + * Add the bitmap buffer to the transaction. * Set the found bits to @new_state to change block's allocation state. - * Returns: starting block number of the extent (fs scope) */ -static u64 gfs2_alloc_extent(struct gfs2_rgrpd *rgd, struct gfs2_bitmap *bi, - u32 blk, bool dinode, unsigned int *n) +static void gfs2_alloc_extent(const struct gfs2_rbm *rbm, bool dinode, + unsigned int *n) { + struct gfs2_rbm pos = { .rgd = rbm->rgd, }; const unsigned int elen = *n; - u32 goal, rgblk; - const u8 *buffer = NULL; - struct gfs2_blkreserv *rs; - - *n = 0; - buffer = bi->bi_bh->b_data + bi->bi_offset; - gfs2_trans_add_bh(rgd->rd_gl, bi->bi_bh, 1); - gfs2_setbit(rgd, bi->bi_clone, bi, blk, - dinode ? GFS2_BLKST_DINODE : GFS2_BLKST_USED); - (*n)++; - goal = blk; + u64 block; + int ret; + + *n = 1; + block = gfs2_rbm_to_block(rbm); + gfs2_trans_add_bh(rbm->rgd->rd_gl, rbm->bi->bi_bh, 1); + gfs2_setbit(rbm, true, dinode ? GFS2_BLKST_DINODE : GFS2_BLKST_USED); + block++; while (*n < elen) { - goal++; - if (goal >= (bi->bi_len * GFS2_NBBY)) - break; - rgblk = gfs2_bi2rgd_blk(bi, goal); - rs = rs_find(rgd, rgblk); - if (rs) /* Oops, we bumped into someone's reservation */ - break; - if (gfs2_testbit(rgd, buffer, bi->bi_len, goal) != - GFS2_BLKST_FREE) + ret = gfs2_rbm_from_block(&pos, block); + if (ret || gfs2_testbit(&pos) != GFS2_BLKST_FREE) break; - gfs2_setbit(rgd, bi->bi_clone, bi, goal, GFS2_BLKST_USED); + gfs2_trans_add_bh(pos.rgd->rd_gl, pos.bi->bi_bh, 1); + gfs2_setbit(&pos, true, GFS2_BLKST_USED); (*n)++; + block++; } - blk = gfs2_bi2rgd_blk(bi, blk); - rgd->rd_last_alloc = blk + *n - 1; - return rgd->rd_data0 + blk; } /** @@ -1875,46 +1874,30 @@ static u64 gfs2_alloc_extent(struct gfs2_rgrpd *rgd, struct gfs2_bitmap *bi, static struct gfs2_rgrpd *rgblk_free(struct gfs2_sbd *sdp, u64 bstart, u32 blen, unsigned char new_state) { - struct gfs2_rgrpd *rgd; - struct gfs2_bitmap *bi = NULL; - u32 length, rgrp_blk, buf_blk; - unsigned int buf; + struct gfs2_rbm rbm; - rgd = gfs2_blk2rgrpd(sdp, bstart, 1); - if (!rgd) { + rbm.rgd = gfs2_blk2rgrpd(sdp, bstart, 1); + if (!rbm.rgd) { if (gfs2_consist(sdp)) fs_err(sdp, "block = %llu\n", (unsigned long long)bstart); return NULL; } - length = rgd->rd_length; - - rgrp_blk = bstart - rgd->rd_data0; - while (blen--) { - for (buf = 0; buf < length; buf++) { - bi = rgd->rd_bits + buf; - if (rgrp_blk < (bi->bi_start + bi->bi_len) * GFS2_NBBY) - break; + gfs2_rbm_from_block(&rbm, bstart); + bstart++; + if (!rbm.bi->bi_clone) { + rbm.bi->bi_clone = kmalloc(rbm.bi->bi_bh->b_size, + GFP_NOFS | __GFP_NOFAIL); + memcpy(rbm.bi->bi_clone + rbm.bi->bi_offset, + rbm.bi->bi_bh->b_data + rbm.bi->bi_offset, + rbm.bi->bi_len); } - - gfs2_assert(rgd->rd_sbd, buf < length); - - buf_blk = rgrp_blk - bi->bi_start * GFS2_NBBY; - rgrp_blk++; - - if (!bi->bi_clone) { - bi->bi_clone = kmalloc(bi->bi_bh->b_size, - GFP_NOFS | __GFP_NOFAIL); - memcpy(bi->bi_clone + bi->bi_offset, - bi->bi_bh->b_data + bi->bi_offset, - bi->bi_len); - } - gfs2_trans_add_bh(rgd->rd_gl, bi->bi_bh, 1); - gfs2_setbit(rgd, NULL, bi, buf_blk, new_state); + gfs2_trans_add_bh(rbm.rgd->rd_gl, rbm.bi->bi_bh, 1); + gfs2_setbit(&rbm, false, new_state); } - return rgd; + return rbm.rgd; } /** @@ -1956,46 +1939,41 @@ static void gfs2_rgrp_error(struct gfs2_rgrpd *rgd) } /** - * claim_reserved_blks - Claim previously reserved blocks - * @ip: the inode that's claiming the reservation - * @dinode: 1 if this block is a dinode block, otherwise data block - * @nblocks: desired extent length + * gfs2_adjust_reservation - Adjust (or remove) a reservation after allocation + * @ip: The inode we have just allocated blocks for + * @rbm: The start of the allocated blocks + * @len: The extent length * - * Lay claim to previously reserved blocks. - * Returns: Starting block number of the blocks claimed. - * Sets *nblocks to the actual extent length allocated. + * Adjusts a reservation after an allocation has taken place. If the + * reservation does not match the allocation, or if it is now empty + * then it is removed. */ -static u64 claim_reserved_blks(struct gfs2_inode *ip, bool dinode, - unsigned int *nblocks) + +static void gfs2_adjust_reservation(struct gfs2_inode *ip, + const struct gfs2_rbm *rbm, unsigned len) { struct gfs2_blkreserv *rs = ip->i_res; - struct gfs2_rgrpd *rgd = rs->rs_rgd; - struct gfs2_bitmap *bi; - u64 start_block = gfs2_rs_startblk(rs); - const unsigned int elen = *nblocks; + struct gfs2_rgrpd *rgd = rbm->rgd; + unsigned rlen; + u64 block; + int ret; - bi = rs->rs_bi; - gfs2_trans_add_bh(rgd->rd_gl, bi->bi_bh, 1); - - for (*nblocks = 0; *nblocks < elen && rs->rs_free; (*nblocks)++) { - if (gfs2_testbit(rgd, bi->bi_bh->b_data + bi->bi_offset, - bi->bi_len, rs->rs_biblk) != GFS2_BLKST_FREE) - break; - gfs2_setbit(rgd, bi->bi_clone, bi, rs->rs_biblk, - dinode ? GFS2_BLKST_DINODE : GFS2_BLKST_USED); - rs->rs_biblk++; - rs->rs_free--; - - BUG_ON(!rgd->rd_reserved); - rgd->rd_reserved--; - dinode = false; + spin_lock(&rgd->rd_rsspin); + if (gfs2_rs_active(rs)) { + if (gfs2_rbm_eq(&rs->rs_rbm, rbm)) { + block = gfs2_rbm_to_block(rbm); + ret = gfs2_rbm_from_block(&rs->rs_rbm, block + len); + rlen = min(rs->rs_free, len); + rs->rs_free -= rlen; + rgd->rd_reserved -= rlen; + trace_gfs2_rs(rs, TRACE_RS_CLAIM); + if (rs->rs_free && !ret) + goto out; + } + __rs_deltree(ip, rs); } - - trace_gfs2_rs(ip, rs, TRACE_RS_CLAIM); - if (!rs->rs_free || *nblocks != elen) - gfs2_rs_deltree(rs); - - return start_block; +out: + spin_unlock(&rgd->rd_rsspin); } /** @@ -2014,47 +1992,40 @@ int gfs2_alloc_blocks(struct gfs2_inode *ip, u64 *bn, unsigned int *nblocks, { struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); struct buffer_head *dibh; - struct gfs2_rgrpd *rgd; + struct gfs2_rbm rbm = { .rgd = ip->i_rgd, }; unsigned int ndata; - u32 goal, blk; /* block, within the rgrp scope */ + u64 goal; u64 block; /* block, within the file system scope */ int error; - struct gfs2_bitmap *bi; - /* Only happens if there is a bug in gfs2, return something distinctive - * to ensure that it is noticed. - */ - if (ip->i_res->rs_requested == 0) - return -ECANCELED; - - /* If we have a reservation, claim blocks from it. */ - if (gfs2_rs_active(ip->i_res)) { - BUG_ON(!ip->i_res->rs_free); - rgd = ip->i_res->rs_rgd; - block = claim_reserved_blks(ip, dinode, nblocks); - if (*nblocks) - goto found_blocks; - } - - rgd = ip->i_rgd; - - if (!dinode && rgrp_contains_block(rgd, ip->i_goal)) - goal = ip->i_goal - rgd->rd_data0; + if (gfs2_rs_active(ip->i_res)) + goal = gfs2_rbm_to_block(&ip->i_res->rs_rbm); + else if (!dinode && rgrp_contains_block(rbm.rgd, ip->i_goal)) + goal = ip->i_goal; else - goal = rgd->rd_last_alloc; + goal = rbm.rgd->rd_last_alloc + rbm.rgd->rd_data0; - blk = rgblk_search(rgd, goal, GFS2_BLKST_FREE, &bi); + gfs2_rbm_from_block(&rbm, goal); + error = gfs2_rbm_find(&rbm, GFS2_BLKST_FREE, 0, ip, false); + + if (error == -ENOSPC) { + gfs2_rbm_from_block(&rbm, goal); + error = gfs2_rbm_find(&rbm, GFS2_BLKST_FREE, 0, NULL, false); + } /* Since all blocks are reserved in advance, this shouldn't happen */ - if (blk == BFITNOENT) { - printk(KERN_WARNING "BFITNOENT, nblocks=%u\n", *nblocks); - printk(KERN_WARNING "FULL=%d\n", - test_bit(GBF_FULL, &rgd->rd_bits->bi_flags)); + if (error) { + fs_warn(sdp, "inum=%llu error=%d, nblocks=%u, full=%d\n", + (unsigned long long)ip->i_no_addr, error, *nblocks, + test_bit(GBF_FULL, &rbm.rgd->rd_bits->bi_flags)); goto rgrp_error; } - block = gfs2_alloc_extent(rgd, bi, blk, dinode, nblocks); -found_blocks: + gfs2_alloc_extent(&rbm, dinode, nblocks); + block = gfs2_rbm_to_block(&rbm); + rbm.rgd->rd_last_alloc = block - rbm.rgd->rd_data0; + if (gfs2_rs_active(ip->i_res)) + gfs2_adjust_reservation(ip, &rbm, *nblocks); ndata = *nblocks; if (dinode) ndata--; @@ -2071,22 +2042,22 @@ found_blocks: brelse(dibh); } } - if (rgd->rd_free < *nblocks) { + if (rbm.rgd->rd_free < *nblocks) { printk(KERN_WARNING "nblocks=%u\n", *nblocks); goto rgrp_error; } - rgd->rd_free -= *nblocks; + rbm.rgd->rd_free -= *nblocks; if (dinode) { - rgd->rd_dinodes++; - *generation = rgd->rd_igeneration++; + rbm.rgd->rd_dinodes++; + *generation = rbm.rgd->rd_igeneration++; if (*generation == 0) - *generation = rgd->rd_igeneration++; + *generation = rbm.rgd->rd_igeneration++; } - gfs2_trans_add_bh(rgd->rd_gl, rgd->rd_bits[0].bi_bh, 1); - gfs2_rgrp_out(rgd, rgd->rd_bits[0].bi_bh->b_data); - gfs2_rgrp_ondisk2lvb(rgd->rd_rgl, rgd->rd_bits[0].bi_bh->b_data); + gfs2_trans_add_bh(rbm.rgd->rd_gl, rbm.rgd->rd_bits[0].bi_bh, 1); + gfs2_rgrp_out(rbm.rgd, rbm.rgd->rd_bits[0].bi_bh->b_data); + gfs2_rgrp_ondisk2lvb(rbm.rgd->rd_rgl, rbm.rgd->rd_bits[0].bi_bh->b_data); gfs2_statfs_change(sdp, 0, -(s64)*nblocks, dinode ? 1 : 0); if (dinode) @@ -2100,14 +2071,14 @@ found_blocks: gfs2_quota_change(ip, ndata, ip->i_inode.i_uid, ip->i_inode.i_gid); - rgd->rd_free_clone -= *nblocks; - trace_gfs2_block_alloc(ip, rgd, block, *nblocks, + rbm.rgd->rd_free_clone -= *nblocks; + trace_gfs2_block_alloc(ip, rbm.rgd, block, *nblocks, dinode ? GFS2_BLKST_DINODE : GFS2_BLKST_USED); *bn = block; return 0; rgrp_error: - gfs2_rgrp_error(rgd); + gfs2_rgrp_error(rbm.rgd); return -EIO; } diff --git a/fs/gfs2/rgrp.h b/fs/gfs2/rgrp.h index ca6e26729b8..24077958dcf 100644 --- a/fs/gfs2/rgrp.h +++ b/fs/gfs2/rgrp.h @@ -46,7 +46,7 @@ extern int gfs2_alloc_blocks(struct gfs2_inode *ip, u64 *bn, unsigned int *n, bool dinode, u64 *generation); extern int gfs2_rs_alloc(struct gfs2_inode *ip); -extern void gfs2_rs_deltree(struct gfs2_blkreserv *rs); +extern void gfs2_rs_deltree(struct gfs2_inode *ip, struct gfs2_blkreserv *rs); extern void gfs2_rs_delete(struct gfs2_inode *ip); extern void __gfs2_free_blocks(struct gfs2_inode *ip, u64 bstart, u32 blen, int meta); extern void gfs2_free_meta(struct gfs2_inode *ip, u64 bstart, u32 blen); @@ -73,30 +73,10 @@ extern int gfs2_rgrp_send_discards(struct gfs2_sbd *sdp, u64 offset, const struct gfs2_bitmap *bi, unsigned minlen, u64 *ptrimmed); extern int gfs2_fitrim(struct file *filp, void __user *argp); -/* This is how to tell if a multi-block reservation is "inplace" reserved: */ -static inline int gfs2_mb_reserved(struct gfs2_inode *ip) +/* This is how to tell if a reservation is in the rgrp tree: */ +static inline bool gfs2_rs_active(struct gfs2_blkreserv *rs) { - if (ip->i_res && ip->i_res->rs_requested) - return 1; - return 0; -} - -/* This is how to tell if a multi-block reservation is in the rgrp tree: */ -static inline int gfs2_rs_active(struct gfs2_blkreserv *rs) -{ - if (rs && rs->rs_bi) - return 1; - return 0; -} - -static inline u32 gfs2_bi2rgd_blk(const struct gfs2_bitmap *bi, u32 blk) -{ - return (bi->bi_start * GFS2_NBBY) + blk; -} - -static inline u64 gfs2_rs_startblk(const struct gfs2_blkreserv *rs) -{ - return gfs2_bi2rgd_blk(rs->rs_bi, rs->rs_biblk) + rs->rs_rgd->rd_data0; + return rs && !RB_EMPTY_NODE(&rs->rs_node); } #endif /* __RGRP_DOT_H__ */ diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c index fc3168f47a1..a8d90f2f576 100644 --- a/fs/gfs2/super.c +++ b/fs/gfs2/super.c @@ -1366,6 +1366,8 @@ static int gfs2_show_options(struct seq_file *s, struct dentry *root) val = sdp->sd_tune.gt_statfs_quantum; if (val != 30) seq_printf(s, ",statfs_quantum=%d", val); + else if (sdp->sd_tune.gt_statfs_slow) + seq_puts(s, ",statfs_quantum=0"); val = sdp->sd_tune.gt_quota_quantum; if (val != 60) seq_printf(s, ",quota_quantum=%d", val); @@ -1543,6 +1545,11 @@ static void gfs2_evict_inode(struct inode *inode) out_truncate: gfs2_log_flush(sdp, ip->i_gl); + if (test_bit(GLF_DIRTY, &ip->i_gl->gl_flags)) { + struct address_space *metamapping = gfs2_glock2aspace(ip->i_gl); + filemap_fdatawrite(metamapping); + filemap_fdatawait(metamapping); + } write_inode_now(inode, 1); gfs2_ail_flush(ip->i_gl, 0); @@ -1557,7 +1564,7 @@ out_truncate: out_unlock: /* Error path for case 1 */ if (gfs2_rs_active(ip->i_res)) - gfs2_rs_deltree(ip->i_res); + gfs2_rs_deltree(ip, ip->i_res); if (test_bit(HIF_HOLDER, &ip->i_iopen_gh.gh_iflags)) gfs2_glock_dq(&ip->i_iopen_gh); diff --git a/fs/gfs2/trace_gfs2.h b/fs/gfs2/trace_gfs2.h index a25c252fe41..bbdc78af60c 100644 --- a/fs/gfs2/trace_gfs2.h +++ b/fs/gfs2/trace_gfs2.h @@ -509,10 +509,9 @@ TRACE_EVENT(gfs2_block_alloc, /* Keep track of multi-block reservations as they are allocated/freed */ TRACE_EVENT(gfs2_rs, - TP_PROTO(const struct gfs2_inode *ip, const struct gfs2_blkreserv *rs, - u8 func), + TP_PROTO(const struct gfs2_blkreserv *rs, u8 func), - TP_ARGS(ip, rs, func), + TP_ARGS(rs, func), TP_STRUCT__entry( __field( dev_t, dev ) @@ -526,18 +525,17 @@ TRACE_EVENT(gfs2_rs, ), TP_fast_assign( - __entry->dev = rs->rs_rgd ? rs->rs_rgd->rd_sbd->sd_vfs->s_dev : 0; - __entry->rd_addr = rs->rs_rgd ? rs->rs_rgd->rd_addr : 0; - __entry->rd_free_clone = rs->rs_rgd ? rs->rs_rgd->rd_free_clone : 0; - __entry->rd_reserved = rs->rs_rgd ? rs->rs_rgd->rd_reserved : 0; - __entry->inum = ip ? ip->i_no_addr : 0; - __entry->start = gfs2_rs_startblk(rs); + __entry->dev = rs->rs_rbm.rgd->rd_sbd->sd_vfs->s_dev; + __entry->rd_addr = rs->rs_rbm.rgd->rd_addr; + __entry->rd_free_clone = rs->rs_rbm.rgd->rd_free_clone; + __entry->rd_reserved = rs->rs_rbm.rgd->rd_reserved; + __entry->inum = rs->rs_inum; + __entry->start = gfs2_rbm_to_block(&rs->rs_rbm); __entry->free = rs->rs_free; __entry->func = func; ), - TP_printk("%u,%u bmap %llu resrv %llu rg:%llu rf:%lu rr:%lu %s " - "f:%lu", + TP_printk("%u,%u bmap %llu resrv %llu rg:%llu rf:%lu rr:%lu %s f:%lu", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->inum, (unsigned long long)__entry->start, diff --git a/fs/gfs2/trans.h b/fs/gfs2/trans.h index 41f42cdccbb..bf2ae9aeee7 100644 --- a/fs/gfs2/trans.h +++ b/fs/gfs2/trans.h @@ -28,11 +28,10 @@ struct gfs2_glock; /* reserve either the number of blocks to be allocated plus the rg header * block, or all of the blocks in the rg, whichever is smaller */ -static inline unsigned int gfs2_rg_blocks(const struct gfs2_inode *ip) +static inline unsigned int gfs2_rg_blocks(const struct gfs2_inode *ip, unsigned requested) { - const struct gfs2_blkreserv *rs = ip->i_res; - if (rs && rs->rs_requested < ip->i_rgd->rd_length) - return rs->rs_requested + 1; + if (requested < ip->i_rgd->rd_length) + return requested + 1; return ip->i_rgd->rd_length; } diff --git a/fs/gfs2/xattr.c b/fs/gfs2/xattr.c index 27a0b4a901f..db330e5518c 100644 --- a/fs/gfs2/xattr.c +++ b/fs/gfs2/xattr.c @@ -448,17 +448,18 @@ ssize_t gfs2_listxattr(struct dentry *dentry, char *buffer, size_t size) } /** - * ea_get_unstuffed - actually copies the unstuffed data into the - * request buffer + * ea_iter_unstuffed - copies the unstuffed xattr data to/from the + * request buffer * @ip: The GFS2 inode * @ea: The extended attribute header structure - * @data: The data to be copied + * @din: The data to be copied in + * @dout: The data to be copied out (one of din,dout will be NULL) * * Returns: errno */ -static int ea_get_unstuffed(struct gfs2_inode *ip, struct gfs2_ea_header *ea, - char *data) +static int gfs2_iter_unstuffed(struct gfs2_inode *ip, struct gfs2_ea_header *ea, + const char *din, char *dout) { struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); struct buffer_head **bh; @@ -467,6 +468,8 @@ static int ea_get_unstuffed(struct gfs2_inode *ip, struct gfs2_ea_header *ea, __be64 *dataptrs = GFS2_EA2DATAPTRS(ea); unsigned int x; int error = 0; + unsigned char *pos; + unsigned cp_size; bh = kcalloc(nptrs, sizeof(struct buffer_head *), GFP_NOFS); if (!bh) @@ -497,12 +500,21 @@ static int ea_get_unstuffed(struct gfs2_inode *ip, struct gfs2_ea_header *ea, goto out; } - memcpy(data, bh[x]->b_data + sizeof(struct gfs2_meta_header), - (sdp->sd_jbsize > amount) ? amount : sdp->sd_jbsize); + pos = bh[x]->b_data + sizeof(struct gfs2_meta_header); + cp_size = (sdp->sd_jbsize > amount) ? amount : sdp->sd_jbsize; - amount -= sdp->sd_jbsize; - data += sdp->sd_jbsize; + if (dout) { + memcpy(dout, pos, cp_size); + dout += sdp->sd_jbsize; + } + + if (din) { + gfs2_trans_add_bh(ip->i_gl, bh[x], 1); + memcpy(pos, din, cp_size); + din += sdp->sd_jbsize; + } + amount -= sdp->sd_jbsize; brelse(bh[x]); } @@ -523,7 +535,7 @@ static int gfs2_ea_get_copy(struct gfs2_inode *ip, struct gfs2_ea_location *el, memcpy(data, GFS2_EA2DATA(el->el_ea), len); return len; } - ret = ea_get_unstuffed(ip, el->el_ea, data); + ret = gfs2_iter_unstuffed(ip, el->el_ea, NULL, data); if (ret < 0) return ret; return len; @@ -727,7 +739,7 @@ static int ea_alloc_skeleton(struct gfs2_inode *ip, struct gfs2_ea_request *er, goto out_gunlock_q; error = gfs2_trans_begin(GFS2_SB(&ip->i_inode), - blks + gfs2_rg_blocks(ip) + + blks + gfs2_rg_blocks(ip, blks) + RES_DINODE + RES_STATFS + RES_QUOTA, 0); if (error) goto out_ipres; @@ -1220,69 +1232,23 @@ static int gfs2_xattr_set(struct dentry *dentry, const char *name, size, flags, type); } + static int ea_acl_chmod_unstuffed(struct gfs2_inode *ip, struct gfs2_ea_header *ea, char *data) { struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); - struct buffer_head **bh; unsigned int amount = GFS2_EA_DATA_LEN(ea); unsigned int nptrs = DIV_ROUND_UP(amount, sdp->sd_jbsize); - __be64 *dataptrs = GFS2_EA2DATAPTRS(ea); - unsigned int x; - int error; - - bh = kcalloc(nptrs, sizeof(struct buffer_head *), GFP_NOFS); - if (!bh) - return -ENOMEM; - - error = gfs2_trans_begin(sdp, nptrs + RES_DINODE, 0); - if (error) - goto out; - - for (x = 0; x < nptrs; x++) { - error = gfs2_meta_read(ip->i_gl, be64_to_cpu(*dataptrs), 0, - bh + x); - if (error) { - while (x--) - brelse(bh[x]); - goto fail; - } - dataptrs++; - } - - for (x = 0; x < nptrs; x++) { - error = gfs2_meta_wait(sdp, bh[x]); - if (error) { - for (; x < nptrs; x++) - brelse(bh[x]); - goto fail; - } - if (gfs2_metatype_check(sdp, bh[x], GFS2_METATYPE_ED)) { - for (; x < nptrs; x++) - brelse(bh[x]); - error = -EIO; - goto fail; - } - - gfs2_trans_add_bh(ip->i_gl, bh[x], 1); - - memcpy(bh[x]->b_data + sizeof(struct gfs2_meta_header), data, - (sdp->sd_jbsize > amount) ? amount : sdp->sd_jbsize); - - amount -= sdp->sd_jbsize; - data += sdp->sd_jbsize; - - brelse(bh[x]); - } + int ret; -out: - kfree(bh); - return error; + ret = gfs2_trans_begin(sdp, nptrs + RES_DINODE, 0); + if (ret) + return ret; -fail: + ret = gfs2_iter_unstuffed(ip, ea, data, NULL); gfs2_trans_end(sdp); - kfree(bh); - return error; + + return ret; } int gfs2_xattr_acl_chmod(struct gfs2_inode *ip, struct iattr *attr, char *data) diff --git a/fs/lockd/svclock.c b/fs/lockd/svclock.c index fb1a2bedbe9..8d80c990dff 100644 --- a/fs/lockd/svclock.c +++ b/fs/lockd/svclock.c @@ -289,7 +289,6 @@ static void nlmsvc_free_block(struct kref *kref) dprintk("lockd: freeing block %p...\n", block); /* Remove block from file's list of blocks */ - mutex_lock(&file->f_mutex); list_del_init(&block->b_flist); mutex_unlock(&file->f_mutex); @@ -303,7 +302,7 @@ static void nlmsvc_free_block(struct kref *kref) static void nlmsvc_release_block(struct nlm_block *block) { if (block != NULL) - kref_put(&block->b_count, nlmsvc_free_block); + kref_put_mutex(&block->b_count, nlmsvc_free_block, &block->b_file->f_mutex); } /* diff --git a/fs/namespace.c b/fs/namespace.c index 4d31f73e256..7bdf7907413 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -1886,8 +1886,14 @@ static int do_add_mount(struct mount *newmnt, struct path *path, int mnt_flags) return err; err = -EINVAL; - if (!(mnt_flags & MNT_SHRINKABLE) && !check_mnt(real_mount(path->mnt))) - goto unlock; + if (unlikely(!check_mnt(real_mount(path->mnt)))) { + /* that's acceptable only for automounts done in private ns */ + if (!(mnt_flags & MNT_SHRINKABLE)) + goto unlock; + /* ... and for those we'd better have mountpoint still alive */ + if (!real_mount(path->mnt)->mnt_ns) + goto unlock; + } /* Refuse the same filesystem on the same mount point */ err = -EBUSY; diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index dfafeb2b05a..eb7cc91b725 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -462,9 +462,6 @@ static struct dentry *proc_sys_lookup(struct inode *dir, struct dentry *dentry, err = ERR_PTR(-ENOMEM); inode = proc_sys_make_inode(dir->i_sb, h ? h : head, p); - if (h) - sysctl_head_finish(h); - if (!inode) goto out; @@ -473,6 +470,8 @@ static struct dentry *proc_sys_lookup(struct inode *dir, struct dentry *dentry, d_add(dentry, inode); out: + if (h) + sysctl_head_finish(h); sysctl_head_finish(head); return err; } diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index d7a9dd735e1..933b7930b86 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -96,6 +96,7 @@ xfs_buf_lru_add( atomic_inc(&bp->b_hold); list_add_tail(&bp->b_lru, &btp->bt_lru); btp->bt_lru_nr++; + bp->b_lru_flags &= ~_XBF_LRU_DISPOSE; } spin_unlock(&btp->bt_lru_lock); } @@ -154,7 +155,8 @@ xfs_buf_stale( struct xfs_buftarg *btp = bp->b_target; spin_lock(&btp->bt_lru_lock); - if (!list_empty(&bp->b_lru)) { + if (!list_empty(&bp->b_lru) && + !(bp->b_lru_flags & _XBF_LRU_DISPOSE)) { list_del_init(&bp->b_lru); btp->bt_lru_nr--; atomic_dec(&bp->b_hold); @@ -1501,6 +1503,7 @@ xfs_buftarg_shrink( */ list_move(&bp->b_lru, &dispose); btp->bt_lru_nr--; + bp->b_lru_flags |= _XBF_LRU_DISPOSE; } spin_unlock(&btp->bt_lru_lock); diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h index d03b73b9604..7c0b6a0a155 100644 --- a/fs/xfs/xfs_buf.h +++ b/fs/xfs/xfs_buf.h @@ -38,27 +38,28 @@ typedef enum { XBRW_ZERO = 3, /* Zero target memory */ } xfs_buf_rw_t; -#define XBF_READ (1 << 0) /* buffer intended for reading from device */ -#define XBF_WRITE (1 << 1) /* buffer intended for writing to device */ -#define XBF_READ_AHEAD (1 << 2) /* asynchronous read-ahead */ -#define XBF_ASYNC (1 << 4) /* initiator will not wait for completion */ -#define XBF_DONE (1 << 5) /* all pages in the buffer uptodate */ -#define XBF_STALE (1 << 6) /* buffer has been staled, do not find it */ +#define XBF_READ (1 << 0) /* buffer intended for reading from device */ +#define XBF_WRITE (1 << 1) /* buffer intended for writing to device */ +#define XBF_READ_AHEAD (1 << 2) /* asynchronous read-ahead */ +#define XBF_ASYNC (1 << 4) /* initiator will not wait for completion */ +#define XBF_DONE (1 << 5) /* all pages in the buffer uptodate */ +#define XBF_STALE (1 << 6) /* buffer has been staled, do not find it */ /* I/O hints for the BIO layer */ -#define XBF_SYNCIO (1 << 10)/* treat this buffer as synchronous I/O */ -#define XBF_FUA (1 << 11)/* force cache write through mode */ -#define XBF_FLUSH (1 << 12)/* flush the disk cache before a write */ +#define XBF_SYNCIO (1 << 10)/* treat this buffer as synchronous I/O */ +#define XBF_FUA (1 << 11)/* force cache write through mode */ +#define XBF_FLUSH (1 << 12)/* flush the disk cache before a write */ /* flags used only as arguments to access routines */ -#define XBF_TRYLOCK (1 << 16)/* lock requested, but do not wait */ -#define XBF_UNMAPPED (1 << 17)/* do not map the buffer */ +#define XBF_TRYLOCK (1 << 16)/* lock requested, but do not wait */ +#define XBF_UNMAPPED (1 << 17)/* do not map the buffer */ /* flags used only internally */ -#define _XBF_PAGES (1 << 20)/* backed by refcounted pages */ -#define _XBF_KMEM (1 << 21)/* backed by heap memory */ -#define _XBF_DELWRI_Q (1 << 22)/* buffer on a delwri queue */ -#define _XBF_COMPOUND (1 << 23)/* compound buffer */ +#define _XBF_PAGES (1 << 20)/* backed by refcounted pages */ +#define _XBF_KMEM (1 << 21)/* backed by heap memory */ +#define _XBF_DELWRI_Q (1 << 22)/* buffer on a delwri queue */ +#define _XBF_COMPOUND (1 << 23)/* compound buffer */ +#define _XBF_LRU_DISPOSE (1 << 24)/* buffer being discarded */ typedef unsigned int xfs_buf_flags_t; @@ -72,12 +73,13 @@ typedef unsigned int xfs_buf_flags_t; { XBF_SYNCIO, "SYNCIO" }, \ { XBF_FUA, "FUA" }, \ { XBF_FLUSH, "FLUSH" }, \ - { XBF_TRYLOCK, "TRYLOCK" }, /* should never be set */\ + { XBF_TRYLOCK, "TRYLOCK" }, /* should never be set */\ { XBF_UNMAPPED, "UNMAPPED" }, /* ditto */\ { _XBF_PAGES, "PAGES" }, \ { _XBF_KMEM, "KMEM" }, \ { _XBF_DELWRI_Q, "DELWRI_Q" }, \ - { _XBF_COMPOUND, "COMPOUND" } + { _XBF_COMPOUND, "COMPOUND" }, \ + { _XBF_LRU_DISPOSE, "LRU_DISPOSE" } typedef struct xfs_buftarg { dev_t bt_dev; @@ -124,7 +126,12 @@ typedef struct xfs_buf { xfs_buf_flags_t b_flags; /* status flags */ struct semaphore b_sema; /* semaphore for lockables */ + /* + * concurrent access to b_lru and b_lru_flags are protected by + * bt_lru_lock and not by b_sema + */ struct list_head b_lru; /* lru list */ + xfs_buf_flags_t b_lru_flags; /* internal lru status flags */ wait_queue_head_t b_waiters; /* unpin waiters */ struct list_head b_list; struct xfs_perag *b_pag; /* contains rbtree root */ diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index bdaf4cb9f4a..19e2380fb86 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -919,6 +919,7 @@ xfs_fs_put_super( struct xfs_mount *mp = XFS_M(sb); xfs_filestream_unmount(mp); + cancel_delayed_work_sync(&mp->m_sync_work); xfs_unmountfs(mp); xfs_syncd_stop(mp); xfs_freesb(mp); diff --git a/include/asm-generic/unistd.h b/include/asm-generic/unistd.h index 991ef01cd77..3748ec92dcb 100644 --- a/include/asm-generic/unistd.h +++ b/include/asm-generic/unistd.h @@ -691,9 +691,11 @@ __SC_COMP(__NR_process_vm_readv, sys_process_vm_readv, \ #define __NR_process_vm_writev 271 __SC_COMP(__NR_process_vm_writev, sys_process_vm_writev, \ compat_sys_process_vm_writev) +#define __NR_kcmp 272 +__SYSCALL(__NR_kcmp, sys_kcmp) #undef __NR_syscalls -#define __NR_syscalls 272 +#define __NR_syscalls 273 /* * All syscalls below here should go away really, diff --git a/include/linux/compiler-gcc4.h b/include/linux/compiler-gcc4.h index 2f4079175af..934bc34d5f9 100644 --- a/include/linux/compiler-gcc4.h +++ b/include/linux/compiler-gcc4.h @@ -49,6 +49,13 @@ #endif #endif +#if __GNUC_MINOR__ >= 6 +/* + * Tell the optimizer that something else uses this function or variable. + */ +#define __visible __attribute__((externally_visible)) +#endif + #if __GNUC_MINOR__ > 0 #define __compiletime_object_size(obj) __builtin_object_size(obj, 0) #endif diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 923d093c9ce..f430e4162f4 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -278,6 +278,10 @@ void ftrace_likely_update(struct ftrace_branch_data *f, int val, int expect); # define __section(S) __attribute__ ((__section__(#S))) #endif +#ifndef __visible +#define __visible +#endif + /* Are two types/vars the same type (ignoring qualifiers)? */ #ifndef __same_type # define __same_type(a, b) __builtin_types_compatible_p(typeof(a), typeof(b)) diff --git a/include/linux/dcache.h b/include/linux/dcache.h index caa34e50537..59200795482 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -206,6 +206,8 @@ struct dentry_operations { #define DCACHE_MANAGED_DENTRY \ (DCACHE_MOUNTED|DCACHE_NEED_AUTOMOUNT|DCACHE_MANAGE_TRANSIT) +#define DCACHE_DENTRY_KILLED 0x100000 + extern seqlock_t rename_lock; static inline int dname_external(struct dentry *dentry) diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 7e83370e6fd..f3b99e1c104 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -256,72 +256,78 @@ static inline void iommu_set_fault_handler(struct iommu_domain *domain, { } -int iommu_attach_group(struct iommu_domain *domain, struct iommu_group *group) +static inline int iommu_attach_group(struct iommu_domain *domain, + struct iommu_group *group) { return -ENODEV; } -void iommu_detach_group(struct iommu_domain *domain, struct iommu_group *group) +static inline void iommu_detach_group(struct iommu_domain *domain, + struct iommu_group *group) { } -struct iommu_group *iommu_group_alloc(void) +static inline struct iommu_group *iommu_group_alloc(void) { return ERR_PTR(-ENODEV); } -void *iommu_group_get_iommudata(struct iommu_group *group) +static inline void *iommu_group_get_iommudata(struct iommu_group *group) { return NULL; } -void iommu_group_set_iommudata(struct iommu_group *group, void *iommu_data, - void (*release)(void *iommu_data)) +static inline void iommu_group_set_iommudata(struct iommu_group *group, + void *iommu_data, + void (*release)(void *iommu_data)) { } -int iommu_group_set_name(struct iommu_group *group, const char *name) +static inline int iommu_group_set_name(struct iommu_group *group, + const char *name) { return -ENODEV; } -int iommu_group_add_device(struct iommu_group *group, struct device *dev) +static inline int iommu_group_add_device(struct iommu_group *group, + struct device *dev) { return -ENODEV; } -void iommu_group_remove_device(struct device *dev) +static inline void iommu_group_remove_device(struct device *dev) { } -int iommu_group_for_each_dev(struct iommu_group *group, void *data, - int (*fn)(struct device *, void *)) +static inline int iommu_group_for_each_dev(struct iommu_group *group, + void *data, + int (*fn)(struct device *, void *)) { return -ENODEV; } -struct iommu_group *iommu_group_get(struct device *dev) +static inline struct iommu_group *iommu_group_get(struct device *dev) { return NULL; } -void iommu_group_put(struct iommu_group *group) +static inline void iommu_group_put(struct iommu_group *group) { } -int iommu_group_register_notifier(struct iommu_group *group, - struct notifier_block *nb) +static inline int iommu_group_register_notifier(struct iommu_group *group, + struct notifier_block *nb) { return -ENODEV; } -int iommu_group_unregister_notifier(struct iommu_group *group, - struct notifier_block *nb) +static inline int iommu_group_unregister_notifier(struct iommu_group *group, + struct notifier_block *nb) { return 0; } -int iommu_group_id(struct iommu_group *group) +static inline int iommu_group_id(struct iommu_group *group) { return -ENODEV; } diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 594b419b7d2..2451f1f7a1d 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -91,7 +91,7 @@ { \ typeof(x) __x = x; \ typeof(divisor) __d = divisor; \ - (((typeof(x))-1) >= 0 || (__x) >= 0) ? \ + (((typeof(x))-1) > 0 || (__x) > 0) ? \ (((__x) + ((__d) / 2)) / (__d)) : \ (((__x) - ((__d) / 2)) / (__d)); \ } \ diff --git a/include/linux/memory.h b/include/linux/memory.h index 1ac7f6e405f..ff9a9f8e0ed 100644 --- a/include/linux/memory.h +++ b/include/linux/memory.h @@ -19,7 +19,7 @@ #include <linux/compiler.h> #include <linux/mutex.h> -#define MIN_MEMORY_BLOCK_SIZE (1 << SECTION_SIZE_BITS) +#define MIN_MEMORY_BLOCK_SIZE (1UL << SECTION_SIZE_BITS) struct memory_block { unsigned long start_section_nr; diff --git a/include/linux/micrel_phy.h b/include/linux/micrel_phy.h index 61f0905bdc4..de201203bc7 100644 --- a/include/linux/micrel_phy.h +++ b/include/linux/micrel_phy.h @@ -1,3 +1,15 @@ +/* + * include/linux/micrel_phy.h + * + * Micrel PHY IDs + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + * + */ + #ifndef _MICREL_PHY_H #define _MICREL_PHY_H @@ -5,10 +17,11 @@ #define PHY_ID_KSZ9021 0x00221610 #define PHY_ID_KS8737 0x00221720 -#define PHY_ID_KS8041 0x00221510 -#define PHY_ID_KS8051 0x00221550 +#define PHY_ID_KSZ8021 0x00221555 +#define PHY_ID_KSZ8041 0x00221510 +#define PHY_ID_KSZ8051 0x00221550 /* both for ks8001 Rev. A/B, and for ks8721 Rev 3. */ -#define PHY_ID_KS8001 0x0022161A +#define PHY_ID_KSZ8001 0x0022161A /* struct phy_device dev_flags definitions */ #define MICREL_PHY_50MHZ_CLK 0x00000001 diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 9490a00529f..c25cccaa555 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -35,8 +35,10 @@ struct nvme_bar { __u64 acq; /* Admin CQ Base Address */ }; +#define NVME_CAP_MQES(cap) ((cap) & 0xffff) #define NVME_CAP_TIMEOUT(cap) (((cap) >> 24) & 0xff) #define NVME_CAP_STRIDE(cap) (((cap) >> 32) & 0xf) +#define NVME_CAP_MPSMIN(cap) (((cap) >> 48) & 0xf) enum { NVME_CC_ENABLE = 1 << 0, diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 33ed9d605f9..bdb41612bfe 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -274,6 +274,8 @@ struct perf_event_attr { __u64 branch_sample_type; /* enum branch_sample_type */ }; +#define perf_flags(attr) (*(&(attr)->read_format + 1)) + /* * Ioctls that can be done on a perf event fd: */ diff --git a/include/linux/security.h b/include/linux/security.h index 3dea6a9d568..d143b8e0195 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -118,6 +118,7 @@ void reset_security_ops(void); extern unsigned long mmap_min_addr; extern unsigned long dac_mmap_min_addr; #else +#define mmap_min_addr 0UL #define dac_mmap_min_addr 0UL #endif diff --git a/include/linux/xfrm.h b/include/linux/xfrm.h index 22e61fdf75a..28e493b5b94 100644 --- a/include/linux/xfrm.h +++ b/include/linux/xfrm.h @@ -84,6 +84,8 @@ struct xfrm_replay_state { __u32 bitmap; }; +#define XFRMA_REPLAY_ESN_MAX 4096 + struct xfrm_replay_state_esn { unsigned int bmp_len; __u32 oseq; diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index 0fedbd8d747..9fc7114159e 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -111,9 +111,8 @@ struct rt6_info { struct inet6_dev *rt6i_idev; unsigned long _rt6i_peer; -#ifdef CONFIG_XFRM - u32 rt6i_flow_cache_genid; -#endif + u32 rt6i_genid; + /* more non-fragment space at head required */ unsigned short rt6i_nfheader_len; diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index ae1cd6c9ba5..fd87963a0ea 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -102,6 +102,7 @@ struct net { #endif struct netns_ipvs *ipvs; struct sock *diag_nlsk; + atomic_t rt_genid; }; @@ -300,5 +301,14 @@ static inline void unregister_net_sysctl_table(struct ctl_table_header *header) } #endif +static inline int rt_genid(struct net *net) +{ + return atomic_read(&net->rt_genid); +} + +static inline void rt_genid_bump(struct net *net) +{ + atomic_inc(&net->rt_genid); +} #endif /* __NET_NET_NAMESPACE_H */ diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index 1474dd65c66..eb24dbccd81 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -65,7 +65,6 @@ struct netns_ipv4 { unsigned int sysctl_ping_group_range[2]; long sysctl_tcp_mem[3]; - atomic_t rt_genid; atomic_t dev_addr_genid; #ifdef CONFIG_IP_MROUTE diff --git a/include/net/route.h b/include/net/route.h index 776a27f1ab7..da22243d276 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -108,7 +108,7 @@ extern struct ip_rt_acct __percpu *ip_rt_acct; struct in_device; extern int ip_rt_init(void); -extern void rt_cache_flush(struct net *net, int how); +extern void rt_cache_flush(struct net *net); extern void rt_flush_dev(struct net_device *dev); extern struct rtable *__ip_route_output_key(struct net *, struct flowi4 *flp); extern struct rtable *ip_route_output_flow(struct net *, struct flowi4 *flp, diff --git a/include/net/sock.h b/include/net/sock.h index 72132aef53f..adb7da20b5a 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1332,7 +1332,7 @@ static inline bool sk_wmem_schedule(struct sock *sk, int size) } static inline bool -sk_rmem_schedule(struct sock *sk, struct sk_buff *skb, unsigned int size) +sk_rmem_schedule(struct sock *sk, struct sk_buff *skb, int size) { if (!sk_has_account(sk)) return true; diff --git a/include/trace/events/kmem.h b/include/trace/events/kmem.h index 5f889f16b0c..08fa27244da 100644 --- a/include/trace/events/kmem.h +++ b/include/trace/events/kmem.h @@ -214,7 +214,7 @@ TRACE_EVENT(mm_page_alloc, TP_printk("page=%p pfn=%lu order=%d migratetype=%d gfp_flags=%s", __entry->page, - page_to_pfn(__entry->page), + __entry->page ? page_to_pfn(__entry->page) : 0, __entry->order, __entry->migratetype, show_gfp_flags(__entry->gfp_flags)) @@ -240,7 +240,7 @@ DECLARE_EVENT_CLASS(mm_page, TP_printk("page=%p pfn=%lu order=%u migratetype=%d percpu_refill=%d", __entry->page, - page_to_pfn(__entry->page), + __entry->page ? page_to_pfn(__entry->page) : 0, __entry->order, __entry->migratetype, __entry->order == 0) diff --git a/include/xen/grant_table.h b/include/xen/grant_table.h index 11e27c3af3c..f19fff8650e 100644 --- a/include/xen/grant_table.h +++ b/include/xen/grant_table.h @@ -187,6 +187,7 @@ int gnttab_map_refs(struct gnttab_map_grant_ref *map_ops, struct gnttab_map_grant_ref *kmap_ops, struct page **pages, unsigned int count); int gnttab_unmap_refs(struct gnttab_unmap_grant_ref *unmap_ops, - struct page **pages, unsigned int count, bool clear_pte); + struct gnttab_map_grant_ref *kunmap_ops, + struct page **pages, unsigned int count); #endif /* __ASM_GNTTAB_H__ */ diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c index b3c7fd55425..6144bab8fd8 100644 --- a/kernel/pid_namespace.c +++ b/kernel/pid_namespace.c @@ -232,15 +232,19 @@ static int pid_ns_ctl_handler(struct ctl_table *table, int write, */ tmp.data = ¤t->nsproxy->pid_ns->last_pid; - return proc_dointvec(&tmp, write, buffer, lenp, ppos); + return proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos); } +extern int pid_max; +static int zero = 0; static struct ctl_table pid_ns_ctl_table[] = { { .procname = "ns_last_pid", .maxlen = sizeof(int), .mode = 0666, /* permissions are checked in the handler */ .proc_handler = pid_ns_ctl_handler, + .extra1 = &zero, + .extra2 = &pid_max, }, { } }; diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 34e5eac8142..d3b91e75cec 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -303,10 +303,11 @@ void getnstimeofday(struct timespec *ts) seq = read_seqbegin(&tk->lock); ts->tv_sec = tk->xtime_sec; - ts->tv_nsec = timekeeping_get_ns(tk); + nsecs = timekeeping_get_ns(tk); } while (read_seqretry(&tk->lock, seq)); + ts->tv_nsec = 0; timespec_add_ns(ts, nsecs); } EXPORT_SYMBOL(getnstimeofday); @@ -345,6 +346,7 @@ void ktime_get_ts(struct timespec *ts) { struct timekeeper *tk = &timekeeper; struct timespec tomono; + s64 nsec; unsigned int seq; WARN_ON(timekeeping_suspended); @@ -352,13 +354,14 @@ void ktime_get_ts(struct timespec *ts) do { seq = read_seqbegin(&tk->lock); ts->tv_sec = tk->xtime_sec; - ts->tv_nsec = timekeeping_get_ns(tk); + nsec = timekeeping_get_ns(tk); tomono = tk->wall_to_monotonic; } while (read_seqretry(&tk->lock, seq)); - set_normalized_timespec(ts, ts->tv_sec + tomono.tv_sec, - ts->tv_nsec + tomono.tv_nsec); + ts->tv_sec += tomono.tv_sec; + ts->tv_nsec = 0; + timespec_add_ns(ts, nsec + tomono.tv_nsec); } EXPORT_SYMBOL_GPL(ktime_get_ts); @@ -1244,6 +1247,7 @@ void get_monotonic_boottime(struct timespec *ts) { struct timekeeper *tk = &timekeeper; struct timespec tomono, sleep; + s64 nsec; unsigned int seq; WARN_ON(timekeeping_suspended); @@ -1251,14 +1255,15 @@ void get_monotonic_boottime(struct timespec *ts) do { seq = read_seqbegin(&tk->lock); ts->tv_sec = tk->xtime_sec; - ts->tv_nsec = timekeeping_get_ns(tk); + nsec = timekeeping_get_ns(tk); tomono = tk->wall_to_monotonic; sleep = tk->total_sleep_time; } while (read_seqretry(&tk->lock, seq)); - set_normalized_timespec(ts, ts->tv_sec + tomono.tv_sec + sleep.tv_sec, - ts->tv_nsec + tomono.tv_nsec + sleep.tv_nsec); + ts->tv_sec += tomono.tv_sec + sleep.tv_sec; + ts->tv_nsec = 0; + timespec_add_ns(ts, nsec + tomono.tv_nsec + sleep.tv_nsec); } EXPORT_SYMBOL_GPL(get_monotonic_boottime); diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 1e1373bcb3e..3c5a79e2134 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -1349,8 +1349,16 @@ static void busy_worker_rebind_fn(struct work_struct *work) struct worker *worker = container_of(work, struct worker, rebind_work); struct global_cwq *gcwq = worker->pool->gcwq; - if (worker_maybe_bind_and_lock(worker)) - worker_clr_flags(worker, WORKER_REBIND); + worker_maybe_bind_and_lock(worker); + + /* + * %WORKER_REBIND must be cleared even if the above binding failed; + * otherwise, we may confuse the next CPU_UP cycle or oops / get + * stuck by calling idle_worker_rebind() prematurely. If CPU went + * down again inbetween, %WORKER_UNBOUND would be set, so clearing + * %WORKER_REBIND is always safe. + */ + worker_clr_flags(worker, WORKER_REBIND); spin_unlock_irq(&gcwq->lock); } @@ -3568,18 +3576,17 @@ static int __devinit workqueue_cpu_down_callback(struct notifier_block *nfb, #ifdef CONFIG_SMP struct work_for_cpu { - struct completion completion; + struct work_struct work; long (*fn)(void *); void *arg; long ret; }; -static int do_work_for_cpu(void *_wfc) +static void work_for_cpu_fn(struct work_struct *work) { - struct work_for_cpu *wfc = _wfc; + struct work_for_cpu *wfc = container_of(work, struct work_for_cpu, work); + wfc->ret = wfc->fn(wfc->arg); - complete(&wfc->completion); - return 0; } /** @@ -3594,19 +3601,11 @@ static int do_work_for_cpu(void *_wfc) */ long work_on_cpu(unsigned int cpu, long (*fn)(void *), void *arg) { - struct task_struct *sub_thread; - struct work_for_cpu wfc = { - .completion = COMPLETION_INITIALIZER_ONSTACK(wfc.completion), - .fn = fn, - .arg = arg, - }; + struct work_for_cpu wfc = { .fn = fn, .arg = arg }; - sub_thread = kthread_create(do_work_for_cpu, &wfc, "work_for_cpu"); - if (IS_ERR(sub_thread)) - return PTR_ERR(sub_thread); - kthread_bind(sub_thread, cpu); - wake_up_process(sub_thread); - wait_for_completion(&wfc.completion); + INIT_WORK_ONSTACK(&wfc.work, work_for_cpu_fn); + schedule_work_on(cpu, &wfc.work); + flush_work(&wfc.work); return wfc.ret; } EXPORT_SYMBOL_GPL(work_on_cpu); diff --git a/lib/flex_proportions.c b/lib/flex_proportions.c index c785554f952..ebf3bac460b 100644 --- a/lib/flex_proportions.c +++ b/lib/flex_proportions.c @@ -62,7 +62,7 @@ void fprop_global_destroy(struct fprop_global *p) */ bool fprop_new_period(struct fprop_global *p, int periods) { - u64 events; + s64 events; unsigned long flags; local_irq_save(flags); diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 57c4b930901..141dbb69509 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1811,7 +1811,6 @@ static void __collapse_huge_page_copy(pte_t *pte, struct page *page, src_page = pte_page(pteval); copy_user_highpage(page, src_page, address, vma); VM_BUG_ON(page_mapcount(src_page) != 1); - VM_BUG_ON(page_count(src_page) != 2); release_pte_page(src_page); /* * ptl mostly unnecessary, but preempt has to diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 3ad25f9d1fc..6a5b90d0cfd 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -126,9 +126,6 @@ static void register_page_bootmem_info_section(unsigned long start_pfn) struct mem_section *ms; struct page *page, *memmap; - if (!pfn_valid(start_pfn)) - return; - section_nr = pfn_to_section_nr(start_pfn); ms = __nr_to_section(section_nr); @@ -187,9 +184,16 @@ void register_page_bootmem_info_node(struct pglist_data *pgdat) end_pfn = pfn + pgdat->node_spanned_pages; /* register_section info */ - for (; pfn < end_pfn; pfn += PAGES_PER_SECTION) - register_page_bootmem_info_section(pfn); - + for (; pfn < end_pfn; pfn += PAGES_PER_SECTION) { + /* + * Some platforms can assign the same pfn to multiple nodes - on + * node0 as well as nodeN. To avoid registering a pfn against + * multiple nodes we check that this pfn does not already + * reside in some other node. + */ + if (pfn_valid(pfn) && (pfn_to_nid(pfn) == node)) + register_page_bootmem_info_section(pfn); + } } #endif /* !CONFIG_SPARSEMEM_VMEMMAP */ diff --git a/mm/page_alloc.c b/mm/page_alloc.c index c66fb875104..c13ea753889 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -584,7 +584,7 @@ static inline void __free_one_page(struct page *page, combined_idx = buddy_idx & page_idx; higher_page = page + (combined_idx - page_idx); buddy_idx = __find_buddy_index(combined_idx, order + 1); - higher_buddy = page + (buddy_idx - combined_idx); + higher_buddy = higher_page + (buddy_idx - combined_idx); if (page_is_buddy(higher_page, higher_buddy, order + 1)) { list_add_tail(&page->lru, &zone->free_area[order].free_list[migratetype]); diff --git a/mm/slab.c b/mm/slab.c index 811af03a14e..c6854759bcf 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -983,7 +983,7 @@ static void *__ac_get_obj(struct kmem_cache *cachep, struct array_cache *ac, } /* The caller cannot use PFMEMALLOC objects, find another one */ - for (i = 1; i < ac->avail; i++) { + for (i = 0; i < ac->avail; i++) { /* If a !PFMEMALLOC object is found, swap them */ if (!is_obj_pfmemalloc(ac->entry[i])) { objp = ac->entry[i]; @@ -1000,7 +1000,7 @@ static void *__ac_get_obj(struct kmem_cache *cachep, struct array_cache *ac, l3 = cachep->nodelists[numa_mem_id()]; if (!list_empty(&l3->slabs_free) && force_refill) { struct slab *slabp = virt_to_slab(objp); - ClearPageSlabPfmemalloc(virt_to_page(slabp->s_mem)); + ClearPageSlabPfmemalloc(virt_to_head_page(slabp->s_mem)); clear_obj_pfmemalloc(&objp); recheck_pfmemalloc_active(cachep, ac); return objp; @@ -1032,7 +1032,7 @@ static void *__ac_put_obj(struct kmem_cache *cachep, struct array_cache *ac, { if (unlikely(pfmemalloc_active)) { /* Some pfmemalloc slabs exist, check if this is one */ - struct page *page = virt_to_page(objp); + struct page *page = virt_to_head_page(objp); if (PageSlabPfmemalloc(page)) set_obj_pfmemalloc(&objp); } diff --git a/mm/slub.c b/mm/slub.c index 8f78e257703..2fdd96f9e99 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -1524,12 +1524,13 @@ static inline void *acquire_slab(struct kmem_cache *s, } static int put_cpu_partial(struct kmem_cache *s, struct page *page, int drain); +static inline bool pfmemalloc_match(struct page *page, gfp_t gfpflags); /* * Try to allocate a partial slab from a specific node. */ -static void *get_partial_node(struct kmem_cache *s, - struct kmem_cache_node *n, struct kmem_cache_cpu *c) +static void *get_partial_node(struct kmem_cache *s, struct kmem_cache_node *n, + struct kmem_cache_cpu *c, gfp_t flags) { struct page *page, *page2; void *object = NULL; @@ -1545,9 +1546,13 @@ static void *get_partial_node(struct kmem_cache *s, spin_lock(&n->list_lock); list_for_each_entry_safe(page, page2, &n->partial, lru) { - void *t = acquire_slab(s, n, page, object == NULL); + void *t; int available; + if (!pfmemalloc_match(page, flags)) + continue; + + t = acquire_slab(s, n, page, object == NULL); if (!t) break; @@ -1614,7 +1619,7 @@ static void *get_any_partial(struct kmem_cache *s, gfp_t flags, if (n && cpuset_zone_allowed_hardwall(zone, flags) && n->nr_partial > s->min_partial) { - object = get_partial_node(s, n, c); + object = get_partial_node(s, n, c, flags); if (object) { /* * Return the object even if @@ -1643,7 +1648,7 @@ static void *get_partial(struct kmem_cache *s, gfp_t flags, int node, void *object; int searchnode = (node == NUMA_NO_NODE) ? numa_node_id() : node; - object = get_partial_node(s, get_node(s, searchnode), c); + object = get_partial_node(s, get_node(s, searchnode), c, flags); if (object || node != NUMA_NO_NODE) return object; diff --git a/mm/vmscan.c b/mm/vmscan.c index 8d01243d956..99b434b674c 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -3102,6 +3102,7 @@ int kswapd_run(int nid) /* failure at boot is fatal */ BUG_ON(system_state == SYSTEM_BOOTING); printk("Failed to start kswapd on node %d\n",nid); + pgdat->kswapd = NULL; ret = -1; } return ret; diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c index e877af8bdd1..469daabd90c 100644 --- a/net/batman-adv/bat_iv_ogm.c +++ b/net/batman-adv/bat_iv_ogm.c @@ -642,7 +642,8 @@ batadv_iv_ogm_orig_update(struct batadv_priv *bat_priv, struct batadv_neigh_node *router = NULL; struct batadv_orig_node *orig_node_tmp; struct hlist_node *node; - uint8_t bcast_own_sum_orig, bcast_own_sum_neigh; + int if_num; + uint8_t sum_orig, sum_neigh; uint8_t *neigh_addr; batadv_dbg(BATADV_DBG_BATMAN, bat_priv, @@ -727,17 +728,17 @@ batadv_iv_ogm_orig_update(struct batadv_priv *bat_priv, if (router && (neigh_node->tq_avg == router->tq_avg)) { orig_node_tmp = router->orig_node; spin_lock_bh(&orig_node_tmp->ogm_cnt_lock); - bcast_own_sum_orig = - orig_node_tmp->bcast_own_sum[if_incoming->if_num]; + if_num = router->if_incoming->if_num; + sum_orig = orig_node_tmp->bcast_own_sum[if_num]; spin_unlock_bh(&orig_node_tmp->ogm_cnt_lock); orig_node_tmp = neigh_node->orig_node; spin_lock_bh(&orig_node_tmp->ogm_cnt_lock); - bcast_own_sum_neigh = - orig_node_tmp->bcast_own_sum[if_incoming->if_num]; + if_num = neigh_node->if_incoming->if_num; + sum_neigh = orig_node_tmp->bcast_own_sum[if_num]; spin_unlock_bh(&orig_node_tmp->ogm_cnt_lock); - if (bcast_own_sum_orig >= bcast_own_sum_neigh) + if (sum_orig >= sum_neigh) goto update_tt; } diff --git a/net/batman-adv/bitarray.h b/net/batman-adv/bitarray.h index a081ce1c051..cebaae7e148 100644 --- a/net/batman-adv/bitarray.h +++ b/net/batman-adv/bitarray.h @@ -20,8 +20,8 @@ #ifndef _NET_BATMAN_ADV_BITARRAY_H_ #define _NET_BATMAN_ADV_BITARRAY_H_ -/* returns true if the corresponding bit in the given seq_bits indicates true - * and curr_seqno is within range of last_seqno +/* Returns 1 if the corresponding bit in the given seq_bits indicates true + * and curr_seqno is within range of last_seqno. Otherwise returns 0. */ static inline int batadv_test_bit(const unsigned long *seq_bits, uint32_t last_seqno, uint32_t curr_seqno) @@ -32,7 +32,7 @@ static inline int batadv_test_bit(const unsigned long *seq_bits, if (diff < 0 || diff >= BATADV_TQ_LOCAL_WINDOW_SIZE) return 0; else - return test_bit(diff, seq_bits); + return test_bit(diff, seq_bits) != 0; } /* turn corresponding bit on, so we can remember that we got the packet */ diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index 109ea2aae96..21c53577c8d 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -100,18 +100,21 @@ static int batadv_interface_set_mac_addr(struct net_device *dev, void *p) { struct batadv_priv *bat_priv = netdev_priv(dev); struct sockaddr *addr = p; + uint8_t old_addr[ETH_ALEN]; if (!is_valid_ether_addr(addr->sa_data)) return -EADDRNOTAVAIL; + memcpy(old_addr, dev->dev_addr, ETH_ALEN); + memcpy(dev->dev_addr, addr->sa_data, ETH_ALEN); + /* only modify transtable if it has been initialized before */ if (atomic_read(&bat_priv->mesh_state) == BATADV_MESH_ACTIVE) { - batadv_tt_local_remove(bat_priv, dev->dev_addr, + batadv_tt_local_remove(bat_priv, old_addr, "mac address changed", false); batadv_tt_local_add(dev, addr->sa_data, BATADV_NULL_IFINDEX); } - memcpy(dev->dev_addr, addr->sa_data, ETH_ALEN); dev->addr_assign_type &= ~NET_ADDR_RANDOM; return 0; } diff --git a/net/bluetooth/bnep/sock.c b/net/bluetooth/bnep/sock.c index 5e5f5b410e0..1eaacf10d19 100644 --- a/net/bluetooth/bnep/sock.c +++ b/net/bluetooth/bnep/sock.c @@ -58,7 +58,7 @@ static int bnep_sock_ioctl(struct socket *sock, unsigned int cmd, unsigned long switch (cmd) { case BNEPCONNADD: if (!capable(CAP_NET_ADMIN)) - return -EACCES; + return -EPERM; if (copy_from_user(&ca, argp, sizeof(ca))) return -EFAULT; @@ -84,7 +84,7 @@ static int bnep_sock_ioctl(struct socket *sock, unsigned int cmd, unsigned long case BNEPCONNDEL: if (!capable(CAP_NET_ADMIN)) - return -EACCES; + return -EPERM; if (copy_from_user(&cd, argp, sizeof(cd))) return -EFAULT; diff --git a/net/bluetooth/cmtp/sock.c b/net/bluetooth/cmtp/sock.c index 311668d1457..32dc83dcb6b 100644 --- a/net/bluetooth/cmtp/sock.c +++ b/net/bluetooth/cmtp/sock.c @@ -72,7 +72,7 @@ static int cmtp_sock_ioctl(struct socket *sock, unsigned int cmd, unsigned long switch (cmd) { case CMTPCONNADD: if (!capable(CAP_NET_ADMIN)) - return -EACCES; + return -EPERM; if (copy_from_user(&ca, argp, sizeof(ca))) return -EFAULT; @@ -97,7 +97,7 @@ static int cmtp_sock_ioctl(struct socket *sock, unsigned int cmd, unsigned long case CMTPCONNDEL: if (!capable(CAP_NET_ADMIN)) - return -EACCES; + return -EPERM; if (copy_from_user(&cd, argp, sizeof(cd))) return -EFAULT; diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index d4de5db18d5..0b997c8f965 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -734,6 +734,8 @@ static int hci_dev_do_close(struct hci_dev *hdev) cancel_work_sync(&hdev->le_scan); + cancel_delayed_work(&hdev->power_off); + hci_req_cancel(hdev, ENODEV); hci_req_lock(hdev); diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c index 19fdac78e55..d5ace1eda3e 100644 --- a/net/bluetooth/hci_sock.c +++ b/net/bluetooth/hci_sock.c @@ -490,7 +490,7 @@ static int hci_sock_bound_ioctl(struct sock *sk, unsigned int cmd, switch (cmd) { case HCISETRAW: if (!capable(CAP_NET_ADMIN)) - return -EACCES; + return -EPERM; if (test_bit(HCI_QUIRK_RAW_DEVICE, &hdev->quirks)) return -EPERM; @@ -510,12 +510,12 @@ static int hci_sock_bound_ioctl(struct sock *sk, unsigned int cmd, case HCIBLOCKADDR: if (!capable(CAP_NET_ADMIN)) - return -EACCES; + return -EPERM; return hci_sock_blacklist_add(hdev, (void __user *) arg); case HCIUNBLOCKADDR: if (!capable(CAP_NET_ADMIN)) - return -EACCES; + return -EPERM; return hci_sock_blacklist_del(hdev, (void __user *) arg); default: @@ -546,22 +546,22 @@ static int hci_sock_ioctl(struct socket *sock, unsigned int cmd, case HCIDEVUP: if (!capable(CAP_NET_ADMIN)) - return -EACCES; + return -EPERM; return hci_dev_open(arg); case HCIDEVDOWN: if (!capable(CAP_NET_ADMIN)) - return -EACCES; + return -EPERM; return hci_dev_close(arg); case HCIDEVRESET: if (!capable(CAP_NET_ADMIN)) - return -EACCES; + return -EPERM; return hci_dev_reset(arg); case HCIDEVRESTAT: if (!capable(CAP_NET_ADMIN)) - return -EACCES; + return -EPERM; return hci_dev_reset_stat(arg); case HCISETSCAN: @@ -573,7 +573,7 @@ static int hci_sock_ioctl(struct socket *sock, unsigned int cmd, case HCISETACLMTU: case HCISETSCOMTU: if (!capable(CAP_NET_ADMIN)) - return -EACCES; + return -EPERM; return hci_dev_cmd(cmd, argp); case HCIINQUIRY: diff --git a/net/bluetooth/hidp/sock.c b/net/bluetooth/hidp/sock.c index 18b3f6892a3..b24fb3bd862 100644 --- a/net/bluetooth/hidp/sock.c +++ b/net/bluetooth/hidp/sock.c @@ -56,7 +56,7 @@ static int hidp_sock_ioctl(struct socket *sock, unsigned int cmd, unsigned long switch (cmd) { case HIDPCONNADD: if (!capable(CAP_NET_ADMIN)) - return -EACCES; + return -EPERM; if (copy_from_user(&ca, argp, sizeof(ca))) return -EFAULT; @@ -91,7 +91,7 @@ static int hidp_sock_ioctl(struct socket *sock, unsigned int cmd, unsigned long case HIDPCONNDEL: if (!capable(CAP_NET_ADMIN)) - return -EACCES; + return -EPERM; if (copy_from_user(&cd, argp, sizeof(cd))) return -EFAULT; diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index 4ea1710a478..38c00f14220 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -1008,7 +1008,7 @@ static void l2cap_send_disconn_req(struct l2cap_conn *conn, struct l2cap_chan *c if (!conn) return; - if (chan->mode == L2CAP_MODE_ERTM) { + if (chan->mode == L2CAP_MODE_ERTM && chan->state == BT_CONNECTED) { __clear_retrans_timer(chan); __clear_monitor_timer(chan); __clear_ack_timer(chan); diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index ad6613d17ca..eba022de3c2 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -2875,6 +2875,22 @@ int mgmt_powered(struct hci_dev *hdev, u8 powered) if (scan) hci_send_cmd(hdev, HCI_OP_WRITE_SCAN_ENABLE, 1, &scan); + if (test_bit(HCI_SSP_ENABLED, &hdev->dev_flags)) { + u8 ssp = 1; + + hci_send_cmd(hdev, HCI_OP_WRITE_SSP_MODE, 1, &ssp); + } + + if (test_bit(HCI_LE_ENABLED, &hdev->dev_flags)) { + struct hci_cp_write_le_host_supported cp; + + cp.le = 1; + cp.simul = !!(hdev->features[6] & LMP_SIMUL_LE_BR); + + hci_send_cmd(hdev, HCI_OP_WRITE_LE_HOST_SUPPORTED, + sizeof(cp), &cp); + } + update_class(hdev); update_name(hdev, hdev->dev_name); update_eir(hdev); diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index 24c5eea8c45..159aa8bef9e 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -1073,16 +1073,13 @@ static int write_partial_msg_pages(struct ceph_connection *con) BUG_ON(kaddr == NULL); base = kaddr + con->out_msg_pos.page_pos + bio_offset; crc = crc32c(crc, base, len); + kunmap(page); msg->footer.data_crc = cpu_to_le32(crc); con->out_msg_pos.did_page_crc = true; } ret = ceph_tcp_sendpage(con->sock, page, con->out_msg_pos.page_pos + bio_offset, len, 1); - - if (do_datacrc) - kunmap(page); - if (ret <= 0) goto out; diff --git a/net/core/dev.c b/net/core/dev.c index d7fe32c946c..89e33a5d4d9 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2134,7 +2134,8 @@ static bool can_checksum_protocol(netdev_features_t features, __be16 protocol) static netdev_features_t harmonize_features(struct sk_buff *skb, __be16 protocol, netdev_features_t features) { - if (!can_checksum_protocol(features, protocol)) { + if (skb->ip_summed != CHECKSUM_NONE && + !can_checksum_protocol(features, protocol)) { features &= ~NETIF_F_ALL_CSUM; features &= ~NETIF_F_SG; } else if (illegal_highdma(skb->dev, skb)) { @@ -3322,7 +3323,7 @@ ncls: if (pt_prev) { if (unlikely(skb_orphan_frags(skb, GFP_ATOMIC))) - ret = -ENOMEM; + goto drop; else ret = pt_prev->func(skb, skb->dev, pt_prev, orig_dev); } else { diff --git a/net/core/skbuff.c b/net/core/skbuff.c index fe00d120816..e33ebae519c 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -3502,7 +3502,9 @@ bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from, if (!skb_cloned(from)) skb_shinfo(from)->nr_frags = 0; - /* if the skb is cloned this does nothing since we set nr_frags to 0 */ + /* if the skb is not cloned this does nothing + * since we set nr_frags to 0. + */ for (i = 0; i < skb_shinfo(from)->nr_frags; i++) skb_frag_ref(from, i); diff --git a/net/core/sock.c b/net/core/sock.c index 30579207612..a6000fbad29 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -691,7 +691,8 @@ set_rcvbuf: case SO_KEEPALIVE: #ifdef CONFIG_INET - if (sk->sk_protocol == IPPROTO_TCP) + if (sk->sk_protocol == IPPROTO_TCP && + sk->sk_type == SOCK_STREAM) tcp_set_keepalive(sk, valbool); #endif sock_valbool_flag(sk, SOCK_KEEPOPEN, valbool); diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index 77e87aff419..47800459e4c 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -1225,7 +1225,7 @@ static int arp_netdev_event(struct notifier_block *this, unsigned long event, switch (event) { case NETDEV_CHANGEADDR: neigh_changeaddr(&arp_tbl, dev); - rt_cache_flush(dev_net(dev), 0); + rt_cache_flush(dev_net(dev)); break; default: break; diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 44bf82e3aef..e12fad77385 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -725,7 +725,7 @@ int devinet_ioctl(struct net *net, unsigned int cmd, void __user *arg) break; case SIOCSIFFLAGS: - ret = -EACCES; + ret = -EPERM; if (!capable(CAP_NET_ADMIN)) goto out; break; @@ -733,7 +733,7 @@ int devinet_ioctl(struct net *net, unsigned int cmd, void __user *arg) case SIOCSIFBRDADDR: /* Set the broadcast address */ case SIOCSIFDSTADDR: /* Set the destination address */ case SIOCSIFNETMASK: /* Set the netmask for the interface */ - ret = -EACCES; + ret = -EPERM; if (!capable(CAP_NET_ADMIN)) goto out; ret = -EINVAL; @@ -1503,7 +1503,7 @@ static int devinet_conf_proc(ctl_table *ctl, int write, if (i == IPV4_DEVCONF_ACCEPT_LOCAL - 1 || i == IPV4_DEVCONF_ROUTE_LOCALNET - 1) if ((new_value == 0) && (old_value != 0)) - rt_cache_flush(net, 0); + rt_cache_flush(net); } return ret; @@ -1537,7 +1537,7 @@ static int devinet_sysctl_forward(ctl_table *ctl, int write, dev_disable_lro(idev->dev); } rtnl_unlock(); - rt_cache_flush(net, 0); + rt_cache_flush(net); } } @@ -1554,7 +1554,7 @@ static int ipv4_doint_and_flush(ctl_table *ctl, int write, struct net *net = ctl->extra2; if (write && *valp != val) - rt_cache_flush(net, 0); + rt_cache_flush(net); return ret; } diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index c43ae3fba79..8e2b475da9f 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -148,7 +148,7 @@ static void fib_flush(struct net *net) } if (flushed) - rt_cache_flush(net, -1); + rt_cache_flush(net); } /* @@ -999,11 +999,11 @@ static void nl_fib_lookup_exit(struct net *net) net->ipv4.fibnl = NULL; } -static void fib_disable_ip(struct net_device *dev, int force, int delay) +static void fib_disable_ip(struct net_device *dev, int force) { if (fib_sync_down_dev(dev, force)) fib_flush(dev_net(dev)); - rt_cache_flush(dev_net(dev), delay); + rt_cache_flush(dev_net(dev)); arp_ifdown(dev); } @@ -1020,7 +1020,7 @@ static int fib_inetaddr_event(struct notifier_block *this, unsigned long event, fib_sync_up(dev); #endif atomic_inc(&net->ipv4.dev_addr_genid); - rt_cache_flush(dev_net(dev), -1); + rt_cache_flush(dev_net(dev)); break; case NETDEV_DOWN: fib_del_ifaddr(ifa, NULL); @@ -1029,9 +1029,9 @@ static int fib_inetaddr_event(struct notifier_block *this, unsigned long event, /* Last address was deleted from this interface. * Disable IP. */ - fib_disable_ip(dev, 1, 0); + fib_disable_ip(dev, 1); } else { - rt_cache_flush(dev_net(dev), -1); + rt_cache_flush(dev_net(dev)); } break; } @@ -1045,7 +1045,7 @@ static int fib_netdev_event(struct notifier_block *this, unsigned long event, vo struct net *net = dev_net(dev); if (event == NETDEV_UNREGISTER) { - fib_disable_ip(dev, 2, -1); + fib_disable_ip(dev, 2); rt_flush_dev(dev); return NOTIFY_DONE; } @@ -1062,14 +1062,14 @@ static int fib_netdev_event(struct notifier_block *this, unsigned long event, vo fib_sync_up(dev); #endif atomic_inc(&net->ipv4.dev_addr_genid); - rt_cache_flush(dev_net(dev), -1); + rt_cache_flush(dev_net(dev)); break; case NETDEV_DOWN: - fib_disable_ip(dev, 0, 0); + fib_disable_ip(dev, 0); break; case NETDEV_CHANGEMTU: case NETDEV_CHANGE: - rt_cache_flush(dev_net(dev), 0); + rt_cache_flush(dev_net(dev)); break; case NETDEV_UNREGISTER_BATCH: break; diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c index a83d74e498d..274309d3ade 100644 --- a/net/ipv4/fib_rules.c +++ b/net/ipv4/fib_rules.c @@ -259,7 +259,7 @@ static size_t fib4_rule_nlmsg_payload(struct fib_rule *rule) static void fib4_rule_flush_cache(struct fib_rules_ops *ops) { - rt_cache_flush(ops->fro_net, -1); + rt_cache_flush(ops->fro_net); } static const struct fib_rules_ops __net_initdata fib4_rules_ops_template = { diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 57bd978483e..d1b93595b4a 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -1286,7 +1286,7 @@ int fib_table_insert(struct fib_table *tb, struct fib_config *cfg) fib_release_info(fi_drop); if (state & FA_S_ACCESSED) - rt_cache_flush(cfg->fc_nlinfo.nl_net, -1); + rt_cache_flush(cfg->fc_nlinfo.nl_net); rtmsg_fib(RTM_NEWROUTE, htonl(key), new_fa, plen, tb->tb_id, &cfg->fc_nlinfo, NLM_F_REPLACE); @@ -1333,7 +1333,7 @@ int fib_table_insert(struct fib_table *tb, struct fib_config *cfg) list_add_tail_rcu(&new_fa->fa_list, (fa ? &fa->fa_list : fa_head)); - rt_cache_flush(cfg->fc_nlinfo.nl_net, -1); + rt_cache_flush(cfg->fc_nlinfo.nl_net); rtmsg_fib(RTM_NEWROUTE, htonl(key), new_fa, plen, tb->tb_id, &cfg->fc_nlinfo, 0); succeeded: @@ -1708,7 +1708,7 @@ int fib_table_delete(struct fib_table *tb, struct fib_config *cfg) trie_leaf_remove(t, l); if (fa->fa_state & FA_S_ACCESSED) - rt_cache_flush(cfg->fc_nlinfo.nl_net, -1); + rt_cache_flush(cfg->fc_nlinfo.nl_net); fib_release_info(fa->fa_info); alias_free_mem_rcu(fa); diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c index e1e0a4e8fd3..c7527f6b9ad 100644 --- a/net/ipv4/inetpeer.c +++ b/net/ipv4/inetpeer.c @@ -510,7 +510,10 @@ relookup: secure_ipv6_id(daddr->addr.a6)); p->metrics[RTAX_LOCK-1] = INETPEER_METRICS_NEW; p->rate_tokens = 0; - p->rate_last = 0; + /* 60*HZ is arbitrary, but chosen enough high so that the first + * calculation of tokens is at its maximum. + */ + p->rate_last = jiffies - 60*HZ; INIT_LIST_HEAD(&p->gc_list); /* Link the node. */ diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index ff0f071969e..d23c6571ba1 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -131,18 +131,20 @@ found: * 0 - deliver * 1 - block */ -static __inline__ int icmp_filter(struct sock *sk, struct sk_buff *skb) +static int icmp_filter(const struct sock *sk, const struct sk_buff *skb) { - int type; + struct icmphdr _hdr; + const struct icmphdr *hdr; - if (!pskb_may_pull(skb, sizeof(struct icmphdr))) + hdr = skb_header_pointer(skb, skb_transport_offset(skb), + sizeof(_hdr), &_hdr); + if (!hdr) return 1; - type = icmp_hdr(skb)->type; - if (type < 32) { + if (hdr->type < 32) { __u32 data = raw_sk(sk)->filter.data; - return ((1 << type) & data) != 0; + return ((1U << hdr->type) & data) != 0; } /* Do not block unknown ICMP types */ diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 82cf2a722b2..fd9af60397b 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -202,11 +202,6 @@ EXPORT_SYMBOL(ip_tos2prio); static DEFINE_PER_CPU(struct rt_cache_stat, rt_cache_stat); #define RT_CACHE_STAT_INC(field) __this_cpu_inc(rt_cache_stat.field) -static inline int rt_genid(struct net *net) -{ - return atomic_read(&net->ipv4.rt_genid); -} - #ifdef CONFIG_PROC_FS static void *rt_cache_seq_start(struct seq_file *seq, loff_t *pos) { @@ -447,27 +442,9 @@ static inline bool rt_is_expired(const struct rtable *rth) return rth->rt_genid != rt_genid(dev_net(rth->dst.dev)); } -/* - * Perturbation of rt_genid by a small quantity [1..256] - * Using 8 bits of shuffling ensure we can call rt_cache_invalidate() - * many times (2^24) without giving recent rt_genid. - * Jenkins hash is strong enough that litle changes of rt_genid are OK. - */ -static void rt_cache_invalidate(struct net *net) +void rt_cache_flush(struct net *net) { - unsigned char shuffle; - - get_random_bytes(&shuffle, sizeof(shuffle)); - atomic_add(shuffle + 1U, &net->ipv4.rt_genid); -} - -/* - * delay < 0 : invalidate cache (fast : entries will be deleted later) - * delay >= 0 : invalidate & flush cache (can be long) - */ -void rt_cache_flush(struct net *net, int delay) -{ - rt_cache_invalidate(net); + rt_genid_bump(net); } static struct neighbour *ipv4_neigh_lookup(const struct dst_entry *dst, @@ -2345,7 +2322,7 @@ int ip_rt_dump(struct sk_buff *skb, struct netlink_callback *cb) void ip_rt_multicast_event(struct in_device *in_dev) { - rt_cache_flush(dev_net(in_dev->dev), 0); + rt_cache_flush(dev_net(in_dev->dev)); } #ifdef CONFIG_SYSCTL @@ -2354,16 +2331,7 @@ static int ipv4_sysctl_rtcache_flush(ctl_table *__ctl, int write, size_t *lenp, loff_t *ppos) { if (write) { - int flush_delay; - ctl_table ctl; - struct net *net; - - memcpy(&ctl, __ctl, sizeof(ctl)); - ctl.data = &flush_delay; - proc_dointvec(&ctl, write, buffer, lenp, ppos); - - net = (struct net *)__ctl->extra1; - rt_cache_flush(net, flush_delay); + rt_cache_flush((struct net *)__ctl->extra1); return 0; } @@ -2533,8 +2501,7 @@ static __net_initdata struct pernet_operations sysctl_route_ops = { static __net_init int rt_genid_init(struct net *net) { - get_random_bytes(&net->ipv4.rt_genid, - sizeof(net->ipv4.rt_genid)); + atomic_set(&net->rt_genid, 0); get_random_bytes(&net->ipv4.dev_addr_genid, sizeof(net->ipv4.dev_addr_genid)); return 0; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 2109ff4a1da..5f641934182 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1762,8 +1762,14 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, } #ifdef CONFIG_NET_DMA - if (tp->ucopy.dma_chan) - dma_async_memcpy_issue_pending(tp->ucopy.dma_chan); + if (tp->ucopy.dma_chan) { + if (tp->rcv_wnd == 0 && + !skb_queue_empty(&sk->sk_async_wait_queue)) { + tcp_service_net_dma(sk, true); + tcp_cleanup_rbuf(sk, copied); + } else + dma_async_memcpy_issue_pending(tp->ucopy.dma_chan); + } #endif if (copied >= target) { /* Do not sleep, just process backlog. */ @@ -2325,10 +2331,17 @@ static int tcp_repair_options_est(struct tcp_sock *tp, tp->rx_opt.mss_clamp = opt.opt_val; break; case TCPOPT_WINDOW: - if (opt.opt_val > 14) - return -EFBIG; + { + u16 snd_wscale = opt.opt_val & 0xFFFF; + u16 rcv_wscale = opt.opt_val >> 16; + + if (snd_wscale > 14 || rcv_wscale > 14) + return -EFBIG; - tp->rx_opt.snd_wscale = opt.opt_val; + tp->rx_opt.snd_wscale = snd_wscale; + tp->rx_opt.rcv_wscale = rcv_wscale; + tp->rx_opt.wscale_ok = 1; + } break; case TCPOPT_SACK_PERM: if (opt.opt_val != 0) diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 6e38c6c23ca..d377f4854cb 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -4661,7 +4661,7 @@ queue_and_out: if (eaten > 0) kfree_skb_partial(skb, fragstolen); - else if (!sock_flag(sk, SOCK_DEAD)) + if (!sock_flag(sk, SOCK_DEAD)) sk->sk_data_ready(sk, 0); return; } @@ -5556,8 +5556,7 @@ no_ack: #endif if (eaten) kfree_skb_partial(skb, fragstolen); - else - sk->sk_data_ready(sk, 0); + sk->sk_data_ready(sk, 0); return 0; } } diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c index 0251a6005be..c4f934176ca 100644 --- a/net/ipv6/inet6_connection_sock.c +++ b/net/ipv6/inet6_connection_sock.c @@ -175,33 +175,12 @@ void __inet6_csk_dst_store(struct sock *sk, struct dst_entry *dst, const struct in6_addr *saddr) { __ip6_dst_store(sk, dst, daddr, saddr); - -#ifdef CONFIG_XFRM - { - struct rt6_info *rt = (struct rt6_info *)dst; - rt->rt6i_flow_cache_genid = atomic_read(&flow_cache_genid); - } -#endif } static inline struct dst_entry *__inet6_csk_dst_check(struct sock *sk, u32 cookie) { - struct dst_entry *dst; - - dst = __sk_dst_check(sk, cookie); - -#ifdef CONFIG_XFRM - if (dst) { - struct rt6_info *rt = (struct rt6_info *)dst; - if (rt->rt6i_flow_cache_genid != atomic_read(&flow_cache_genid)) { - __sk_dst_reset(sk); - dst = NULL; - } - } -#endif - - return dst; + return __sk_dst_check(sk, cookie); } static struct dst_entry *inet6_csk_route_socket(struct sock *sk, diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 13690d650c3..286acfc2125 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -819,6 +819,10 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, struct nl_info *info) offsetof(struct rt6_info, rt6i_src), allow_create, replace_required); + if (IS_ERR(sn)) { + err = PTR_ERR(sn); + sn = NULL; + } if (!sn) { /* If it is failed, discard just allocated root, and then (in st_failure) stale node diff --git a/net/ipv6/mip6.c b/net/ipv6/mip6.c index 5b087c31d87..0f9bdc5ee9f 100644 --- a/net/ipv6/mip6.c +++ b/net/ipv6/mip6.c @@ -86,28 +86,30 @@ static int mip6_mh_len(int type) static int mip6_mh_filter(struct sock *sk, struct sk_buff *skb) { - struct ip6_mh *mh; + struct ip6_mh _hdr; + const struct ip6_mh *mh; - if (!pskb_may_pull(skb, (skb_transport_offset(skb)) + 8) || - !pskb_may_pull(skb, (skb_transport_offset(skb) + - ((skb_transport_header(skb)[1] + 1) << 3)))) + mh = skb_header_pointer(skb, skb_transport_offset(skb), + sizeof(_hdr), &_hdr); + if (!mh) return -1; - mh = (struct ip6_mh *)skb_transport_header(skb); + if (((mh->ip6mh_hdrlen + 1) << 3) > skb->len) + return -1; if (mh->ip6mh_hdrlen < mip6_mh_len(mh->ip6mh_type)) { LIMIT_NETDEBUG(KERN_DEBUG "mip6: MH message too short: %d vs >=%d\n", mh->ip6mh_hdrlen, mip6_mh_len(mh->ip6mh_type)); - mip6_param_prob(skb, 0, ((&mh->ip6mh_hdrlen) - - skb_network_header(skb))); + mip6_param_prob(skb, 0, offsetof(struct ip6_mh, ip6mh_hdrlen) + + skb_network_header_len(skb)); return -1; } if (mh->ip6mh_proto != IPPROTO_NONE) { LIMIT_NETDEBUG(KERN_DEBUG "mip6: MH invalid payload proto = %d\n", mh->ip6mh_proto); - mip6_param_prob(skb, 0, ((&mh->ip6mh_proto) - - skb_network_header(skb))); + mip6_param_prob(skb, 0, offsetof(struct ip6_mh, ip6mh_proto) + + skb_network_header_len(skb)); return -1; } diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index ef0579d5bca..4a5f78b5049 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -107,21 +107,20 @@ found: * 0 - deliver * 1 - block */ -static __inline__ int icmpv6_filter(struct sock *sk, struct sk_buff *skb) +static int icmpv6_filter(const struct sock *sk, const struct sk_buff *skb) { - struct icmp6hdr *icmph; - struct raw6_sock *rp = raw6_sk(sk); - - if (pskb_may_pull(skb, sizeof(struct icmp6hdr))) { - __u32 *data = &rp->filter.data[0]; - int bit_nr; + struct icmp6hdr *_hdr; + const struct icmp6hdr *hdr; - icmph = (struct icmp6hdr *) skb->data; - bit_nr = icmph->icmp6_type; + hdr = skb_header_pointer(skb, skb_transport_offset(skb), + sizeof(_hdr), &_hdr); + if (hdr) { + const __u32 *data = &raw6_sk(sk)->filter.data[0]; + unsigned int type = hdr->icmp6_type; - return (data[bit_nr >> 5] & (1 << (bit_nr & 31))) != 0; + return (data[type >> 5] & (1U << (type & 31))) != 0; } - return 0; + return 1; } #if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE) diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 8e80fd27910..854e4018d20 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -226,7 +226,7 @@ static struct rt6_info ip6_null_entry_template = { .dst = { .__refcnt = ATOMIC_INIT(1), .__use = 1, - .obsolete = -1, + .obsolete = DST_OBSOLETE_FORCE_CHK, .error = -ENETUNREACH, .input = ip6_pkt_discard, .output = ip6_pkt_discard_out, @@ -246,7 +246,7 @@ static struct rt6_info ip6_prohibit_entry_template = { .dst = { .__refcnt = ATOMIC_INIT(1), .__use = 1, - .obsolete = -1, + .obsolete = DST_OBSOLETE_FORCE_CHK, .error = -EACCES, .input = ip6_pkt_prohibit, .output = ip6_pkt_prohibit_out, @@ -261,7 +261,7 @@ static struct rt6_info ip6_blk_hole_entry_template = { .dst = { .__refcnt = ATOMIC_INIT(1), .__use = 1, - .obsolete = -1, + .obsolete = DST_OBSOLETE_FORCE_CHK, .error = -EINVAL, .input = dst_discard, .output = dst_discard, @@ -281,13 +281,14 @@ static inline struct rt6_info *ip6_dst_alloc(struct net *net, struct fib6_table *table) { struct rt6_info *rt = dst_alloc(&net->ipv6.ip6_dst_ops, dev, - 0, DST_OBSOLETE_NONE, flags); + 0, DST_OBSOLETE_FORCE_CHK, flags); if (rt) { struct dst_entry *dst = &rt->dst; memset(dst + 1, 0, sizeof(*rt) - sizeof(*dst)); rt6_init_peer(rt, table ? &table->tb6_peers : net->ipv6.peers); + rt->rt6i_genid = rt_genid(net); } return rt; } @@ -1031,6 +1032,13 @@ static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie) rt = (struct rt6_info *) dst; + /* All IPV6 dsts are created with ->obsolete set to the value + * DST_OBSOLETE_FORCE_CHK which forces validation calls down + * into this function always. + */ + if (rt->rt6i_genid != rt_genid(dev_net(rt->dst.dev))) + return NULL; + if (rt->rt6i_node && (rt->rt6i_node->fn_sernum == cookie)) { if (rt->rt6i_peer_genid != rt6_peer_genid()) { if (!rt6_has_peer(rt)) @@ -1397,8 +1405,6 @@ int ip6_route_add(struct fib6_config *cfg) goto out; } - rt->dst.obsolete = -1; - if (cfg->fc_flags & RTF_EXPIRES) rt6_set_expires(rt, jiffies + clock_t_to_jiffies(cfg->fc_expires)); @@ -2080,7 +2086,6 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev, rt->dst.input = ip6_input; rt->dst.output = ip6_output; rt->rt6i_idev = idev; - rt->dst.obsolete = -1; rt->rt6i_flags = RTF_UP | RTF_NONEXTHOP; if (anycast) diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c index d71cd9229a4..6f936358d66 100644 --- a/net/l2tp/l2tp_netlink.c +++ b/net/l2tp/l2tp_netlink.c @@ -80,8 +80,8 @@ static int l2tp_nl_cmd_noop(struct sk_buff *skb, struct genl_info *info) hdr = genlmsg_put(msg, info->snd_pid, info->snd_seq, &l2tp_nl_family, 0, L2TP_CMD_NOOP); - if (IS_ERR(hdr)) { - ret = PTR_ERR(hdr); + if (!hdr) { + ret = -EMSGSIZE; goto err_out; } @@ -250,8 +250,8 @@ static int l2tp_nl_tunnel_send(struct sk_buff *skb, u32 pid, u32 seq, int flags, hdr = genlmsg_put(skb, pid, seq, &l2tp_nl_family, flags, L2TP_CMD_TUNNEL_GET); - if (IS_ERR(hdr)) - return PTR_ERR(hdr); + if (!hdr) + return -EMSGSIZE; if (nla_put_u8(skb, L2TP_ATTR_PROTO_VERSION, tunnel->version) || nla_put_u32(skb, L2TP_ATTR_CONN_ID, tunnel->tunnel_id) || @@ -617,8 +617,8 @@ static int l2tp_nl_session_send(struct sk_buff *skb, u32 pid, u32 seq, int flags sk = tunnel->sock; hdr = genlmsg_put(skb, pid, seq, &l2tp_nl_family, flags, L2TP_CMD_SESSION_GET); - if (IS_ERR(hdr)) - return PTR_ERR(hdr); + if (!hdr) + return -EMSGSIZE; if (nla_put_u32(skb, L2TP_ATTR_CONN_ID, tunnel->tunnel_id) || nla_put_u32(skb, L2TP_ATTR_SESSION_ID, session->session_id) || diff --git a/net/netfilter/xt_limit.c b/net/netfilter/xt_limit.c index 5c22ce8ab30..a4c1e4528ca 100644 --- a/net/netfilter/xt_limit.c +++ b/net/netfilter/xt_limit.c @@ -117,11 +117,11 @@ static int limit_mt_check(const struct xt_mtchk_param *par) /* For SMP, we only want to use one set of state. */ r->master = priv; + /* User avg in seconds * XT_LIMIT_SCALE: convert to jiffies * + 128. */ + priv->prev = jiffies; + priv->credit = user2credits(r->avg * r->burst); /* Credits full. */ if (r->cost == 0) { - /* User avg in seconds * XT_LIMIT_SCALE: convert to jiffies * - 128. */ - priv->prev = jiffies; - priv->credit = user2credits(r->avg * r->burst); /* Credits full. */ r->credit_cap = priv->credit; /* Credits full. */ r->cost = user2credits(r->avg); } diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c index 1b9024ee963..7261eb81974 100644 --- a/net/netrom/af_netrom.c +++ b/net/netrom/af_netrom.c @@ -601,7 +601,7 @@ static int nr_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) if (!capable(CAP_NET_BIND_SERVICE)) { dev_put(dev); release_sock(sk); - return -EACCES; + return -EPERM; } nr->user_addr = addr->fsa_digipeater[0]; nr->source_addr = addr->fsa_ax25.sax25_call; diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c index e4723d31fdd..211a2121704 100644 --- a/net/sched/sch_qfq.c +++ b/net/sched/sch_qfq.c @@ -865,7 +865,10 @@ static void qfq_update_start(struct qfq_sched *q, struct qfq_class *cl) if (mask) { struct qfq_group *next = qfq_ffs(q, mask); if (qfq_gt(roundedF, next->F)) { - cl->S = next->F; + if (qfq_gt(limit, next->F)) + cl->S = next->F; + else /* preserve timestamp correctness */ + cl->S = limit; return; } } diff --git a/net/wireless/reg.c b/net/wireless/reg.c index 2ded3c7fad0..72d170ca340 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -350,6 +350,9 @@ static void reg_regdb_search(struct work_struct *work) struct reg_regdb_search_request *request; const struct ieee80211_regdomain *curdom, *regdom; int i, r; + bool set_reg = false; + + mutex_lock(&cfg80211_mutex); mutex_lock(®_regdb_search_mutex); while (!list_empty(®_regdb_search_list)) { @@ -365,9 +368,7 @@ static void reg_regdb_search(struct work_struct *work) r = reg_copy_regd(®dom, curdom); if (r) break; - mutex_lock(&cfg80211_mutex); - set_regdom(regdom); - mutex_unlock(&cfg80211_mutex); + set_reg = true; break; } } @@ -375,6 +376,11 @@ static void reg_regdb_search(struct work_struct *work) kfree(request); } mutex_unlock(®_regdb_search_mutex); + + if (set_reg) + set_regdom(regdom); + + mutex_unlock(&cfg80211_mutex); } static DECLARE_WORK(reg_regdb_work, reg_regdb_search); diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 5a2aa17e4d3..387848e9007 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -585,6 +585,7 @@ int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl) xfrm_pol_hold(policy); net->xfrm.policy_count[dir]++; atomic_inc(&flow_cache_genid); + rt_genid_bump(net); if (delpol) __xfrm_policy_unlink(delpol, dir); policy->index = delpol ? delpol->index : xfrm_gen_index(net, dir); @@ -1763,7 +1764,7 @@ static struct dst_entry *make_blackhole(struct net *net, u16 family, if (!afinfo) { dst_release(dst_orig); - ret = ERR_PTR(-EINVAL); + return ERR_PTR(-EINVAL); } else { ret = afinfo->blackhole_route(net, dst_orig); } diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index e75d8e47f35..289f4bf18ff 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -123,9 +123,21 @@ static inline int verify_replay(struct xfrm_usersa_info *p, struct nlattr **attrs) { struct nlattr *rt = attrs[XFRMA_REPLAY_ESN_VAL]; + struct xfrm_replay_state_esn *rs; - if ((p->flags & XFRM_STATE_ESN) && !rt) - return -EINVAL; + if (p->flags & XFRM_STATE_ESN) { + if (!rt) + return -EINVAL; + + rs = nla_data(rt); + + if (rs->bmp_len > XFRMA_REPLAY_ESN_MAX / sizeof(rs->bmp[0]) / 8) + return -EINVAL; + + if (nla_len(rt) < xfrm_replay_state_esn_len(rs) && + nla_len(rt) != sizeof(*rs)) + return -EINVAL; + } if (!rt) return 0; @@ -370,14 +382,15 @@ static inline int xfrm_replay_verify_len(struct xfrm_replay_state_esn *replay_es struct nlattr *rp) { struct xfrm_replay_state_esn *up; + int ulen; if (!replay_esn || !rp) return 0; up = nla_data(rp); + ulen = xfrm_replay_state_esn_len(up); - if (xfrm_replay_state_esn_len(replay_esn) != - xfrm_replay_state_esn_len(up)) + if (nla_len(rp) < ulen || xfrm_replay_state_esn_len(replay_esn) != ulen) return -EINVAL; return 0; @@ -388,22 +401,28 @@ static int xfrm_alloc_replay_state_esn(struct xfrm_replay_state_esn **replay_esn struct nlattr *rta) { struct xfrm_replay_state_esn *p, *pp, *up; + int klen, ulen; if (!rta) return 0; up = nla_data(rta); + klen = xfrm_replay_state_esn_len(up); + ulen = nla_len(rta) >= klen ? klen : sizeof(*up); - p = kmemdup(up, xfrm_replay_state_esn_len(up), GFP_KERNEL); + p = kzalloc(klen, GFP_KERNEL); if (!p) return -ENOMEM; - pp = kmemdup(up, xfrm_replay_state_esn_len(up), GFP_KERNEL); + pp = kzalloc(klen, GFP_KERNEL); if (!pp) { kfree(p); return -ENOMEM; } + memcpy(p, up, ulen); + memcpy(pp, up, ulen); + *replay_esn = p; *preplay_esn = pp; @@ -442,10 +461,11 @@ static void copy_from_user_state(struct xfrm_state *x, struct xfrm_usersa_info * * somehow made shareable and move it to xfrm_state.c - JHS * */ -static void xfrm_update_ae_params(struct xfrm_state *x, struct nlattr **attrs) +static void xfrm_update_ae_params(struct xfrm_state *x, struct nlattr **attrs, + int update_esn) { struct nlattr *rp = attrs[XFRMA_REPLAY_VAL]; - struct nlattr *re = attrs[XFRMA_REPLAY_ESN_VAL]; + struct nlattr *re = update_esn ? attrs[XFRMA_REPLAY_ESN_VAL] : NULL; struct nlattr *lt = attrs[XFRMA_LTIME_VAL]; struct nlattr *et = attrs[XFRMA_ETIMER_THRESH]; struct nlattr *rt = attrs[XFRMA_REPLAY_THRESH]; @@ -555,7 +575,7 @@ static struct xfrm_state *xfrm_state_construct(struct net *net, goto error; /* override default values from above */ - xfrm_update_ae_params(x, attrs); + xfrm_update_ae_params(x, attrs, 0); return x; @@ -689,6 +709,7 @@ out: static void copy_to_user_state(struct xfrm_state *x, struct xfrm_usersa_info *p) { + memset(p, 0, sizeof(*p)); memcpy(&p->id, &x->id, sizeof(p->id)); memcpy(&p->sel, &x->sel, sizeof(p->sel)); memcpy(&p->lft, &x->lft, sizeof(p->lft)); @@ -742,7 +763,7 @@ static int copy_to_user_auth(struct xfrm_algo_auth *auth, struct sk_buff *skb) return -EMSGSIZE; algo = nla_data(nla); - strcpy(algo->alg_name, auth->alg_name); + strncpy(algo->alg_name, auth->alg_name, sizeof(algo->alg_name)); memcpy(algo->alg_key, auth->alg_key, (auth->alg_key_len + 7) / 8); algo->alg_key_len = auth->alg_key_len; @@ -878,6 +899,7 @@ static struct sk_buff *xfrm_state_netlink(struct sk_buff *in_skb, { struct xfrm_dump_info info; struct sk_buff *skb; + int err; skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC); if (!skb) @@ -888,9 +910,10 @@ static struct sk_buff *xfrm_state_netlink(struct sk_buff *in_skb, info.nlmsg_seq = seq; info.nlmsg_flags = 0; - if (dump_one_state(x, 0, &info)) { + err = dump_one_state(x, 0, &info); + if (err) { kfree_skb(skb); - return NULL; + return ERR_PTR(err); } return skb; @@ -1317,6 +1340,7 @@ static void copy_from_user_policy(struct xfrm_policy *xp, struct xfrm_userpolicy static void copy_to_user_policy(struct xfrm_policy *xp, struct xfrm_userpolicy_info *p, int dir) { + memset(p, 0, sizeof(*p)); memcpy(&p->sel, &xp->selector, sizeof(p->sel)); memcpy(&p->lft, &xp->lft, sizeof(p->lft)); memcpy(&p->curlft, &xp->curlft, sizeof(p->curlft)); @@ -1421,6 +1445,7 @@ static int copy_to_user_tmpl(struct xfrm_policy *xp, struct sk_buff *skb) struct xfrm_user_tmpl *up = &vec[i]; struct xfrm_tmpl *kp = &xp->xfrm_vec[i]; + memset(up, 0, sizeof(*up)); memcpy(&up->id, &kp->id, sizeof(up->id)); up->family = kp->encap_family; memcpy(&up->saddr, &kp->saddr, sizeof(up->saddr)); @@ -1546,6 +1571,7 @@ static struct sk_buff *xfrm_policy_netlink(struct sk_buff *in_skb, { struct xfrm_dump_info info; struct sk_buff *skb; + int err; skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!skb) @@ -1556,9 +1582,10 @@ static struct sk_buff *xfrm_policy_netlink(struct sk_buff *in_skb, info.nlmsg_seq = seq; info.nlmsg_flags = 0; - if (dump_one_policy(xp, dir, 0, &info) < 0) { + err = dump_one_policy(xp, dir, 0, &info); + if (err) { kfree_skb(skb); - return NULL; + return ERR_PTR(err); } return skb; @@ -1822,7 +1849,7 @@ static int xfrm_new_ae(struct sk_buff *skb, struct nlmsghdr *nlh, goto out; spin_lock_bh(&x->lock); - xfrm_update_ae_params(x, attrs); + xfrm_update_ae_params(x, attrs, 1); spin_unlock_bh(&x->lock); c.event = nlh->nlmsg_type; diff --git a/scripts/Makefile.fwinst b/scripts/Makefile.fwinst index c3f69ae275d..4d908d16c03 100644 --- a/scripts/Makefile.fwinst +++ b/scripts/Makefile.fwinst @@ -27,7 +27,7 @@ endif installed-mod-fw := $(addprefix $(INSTALL_FW_PATH)/,$(mod-fw)) installed-fw := $(addprefix $(INSTALL_FW_PATH)/,$(fw-shipped-all)) -installed-fw-dirs := $(sort $(dir $(installed-fw))) $(INSTALL_FW_PATH)/. +installed-fw-dirs := $(sort $(dir $(installed-fw))) $(INSTALL_FW_PATH)/./ # Workaround for make < 3.81, where .SECONDEXPANSION doesn't work. PHONY += $(INSTALL_FW_PATH)/$$(%) install-all-dirs @@ -42,7 +42,7 @@ quiet_cmd_install = INSTALL $(subst $(srctree)/,,$@) $(installed-fw-dirs): $(call cmd,mkdir) -$(installed-fw): $(INSTALL_FW_PATH)/%: $(obj)/% | $$(dir $(INSTALL_FW_PATH)/%) +$(installed-fw): $(INSTALL_FW_PATH)/%: $(obj)/% | $(INSTALL_FW_PATH)/$$(dir %) $(call cmd,install) PHONY += __fw_install __fw_modinst FORCE diff --git a/scripts/checksyscalls.sh b/scripts/checksyscalls.sh index d24810fc6af..fd8fa9aa7c4 100755 --- a/scripts/checksyscalls.sh +++ b/scripts/checksyscalls.sh @@ -200,7 +200,7 @@ EOF syscall_list() { grep '^[0-9]' "$1" | sort -n | ( while read nr abi name entry ; do - echo <<EOF + cat <<EOF #if !defined(__NR_${name}) && !defined(__IGNORE_${name}) #warning syscall ${name} not implemented #endif diff --git a/security/selinux/include/xfrm.h b/security/selinux/include/xfrm.h index c220f314709..65f67cb0aef 100644 --- a/security/selinux/include/xfrm.h +++ b/security/selinux/include/xfrm.h @@ -51,6 +51,7 @@ int selinux_xfrm_decode_session(struct sk_buff *skb, u32 *sid, int ckall); static inline void selinux_xfrm_notify_policyload(void) { atomic_inc(&flow_cache_genid); + rt_genid_bump(&init_net); } #else static inline int selinux_xfrm_enabled(void) diff --git a/sound/soc/codecs/wm2000.c b/sound/soc/codecs/wm2000.c index 3fd5b29dc93..a3acb7a85f6 100644 --- a/sound/soc/codecs/wm2000.c +++ b/sound/soc/codecs/wm2000.c @@ -702,7 +702,7 @@ static bool wm2000_readable_reg(struct device *dev, unsigned int reg) } static const struct regmap_config wm2000_regmap = { - .reg_bits = 8, + .reg_bits = 16, .val_bits = 8, .max_register = WM2000_REG_IF_CTL, diff --git a/sound/usb/endpoint.c b/sound/usb/endpoint.c index d6e2bb49c59..060dccb9ec7 100644 --- a/sound/usb/endpoint.c +++ b/sound/usb/endpoint.c @@ -197,7 +197,13 @@ static void prepare_outbound_urb(struct snd_usb_endpoint *ep, /* no data provider, so send silence */ unsigned int offs = 0; for (i = 0; i < ctx->packets; ++i) { - int counts = ctx->packet_size[i]; + int counts; + + if (ctx->packet_size[i]) + counts = ctx->packet_size[i]; + else + counts = snd_usb_endpoint_next_packet_size(ep); + urb->iso_frame_desc[i].offset = offs * ep->stride; urb->iso_frame_desc[i].length = counts * ep->stride; offs += counts; |