diff options
152 files changed, 1507 insertions, 612 deletions
diff --git a/MAINTAINERS b/MAINTAINERS index e1a9511fc..8faa7d030 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -10302,9 +10302,11 @@ S: Maintained F: drivers/net/ethernet/dlink/sundance.c SUPERH +M: Yoshinori Sato <ysato@users.sourceforge.jp> +M: Rich Felker <dalias@libc.org> L: linux-sh@vger.kernel.org Q: http://patchwork.kernel.org/project/linux-sh/list/ -S: Orphan +S: Maintained F: Documentation/sh/ F: arch/sh/ F: drivers/sh/ @@ -1,6 +1,6 @@ VERSION = 4 PATCHLEVEL = 4 -SUBLEVEL = 2 +SUBLEVEL = 3 EXTRAVERSION = -gnu NAME = Blurry Fish Butt diff --git a/arch/arm/boot/dts/armada-388-gp.dts b/arch/arm/boot/dts/armada-388-gp.dts index a633be3de..cd316021d 100644 --- a/arch/arm/boot/dts/armada-388-gp.dts +++ b/arch/arm/boot/dts/armada-388-gp.dts @@ -303,16 +303,6 @@ gpio = <&expander0 4 GPIO_ACTIVE_HIGH>; }; - reg_usb2_1_vbus: v5-vbus1 { - compatible = "regulator-fixed"; - regulator-name = "v5.0-vbus1"; - regulator-min-microvolt = <5000000>; - regulator-max-microvolt = <5000000>; - enable-active-high; - regulator-always-on; - gpio = <&expander0 4 GPIO_ACTIVE_HIGH>; - }; - reg_sata0: pwr-sata0 { compatible = "regulator-fixed"; regulator-name = "pwr_en_sata0"; diff --git a/arch/arm/boot/dts/at91-sama5d4_xplained.dts b/arch/arm/boot/dts/at91-sama5d4_xplained.dts index 131614f28..569026e8f 100644 --- a/arch/arm/boot/dts/at91-sama5d4_xplained.dts +++ b/arch/arm/boot/dts/at91-sama5d4_xplained.dts @@ -86,10 +86,12 @@ macb0: ethernet@f8020000 { phy-mode = "rmii"; status = "okay"; + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_macb0_rmii &pinctrl_macb0_phy_irq>; phy0: ethernet-phy@1 { interrupt-parent = <&pioE>; - interrupts = <1 IRQ_TYPE_EDGE_FALLING>; + interrupts = <1 IRQ_TYPE_LEVEL_LOW>; reg = <1>; }; }; @@ -152,6 +154,10 @@ atmel,pins = <AT91_PIOE 8 AT91_PERIPH_GPIO AT91_PINCTRL_PULL_UP_DEGLITCH>; }; + pinctrl_macb0_phy_irq: macb0_phy_irq_0 { + atmel,pins = + <AT91_PIOE 1 AT91_PERIPH_GPIO AT91_PINCTRL_PULL_UP_DEGLITCH>; + }; }; }; }; diff --git a/arch/arm/boot/dts/at91-sama5d4ek.dts b/arch/arm/boot/dts/at91-sama5d4ek.dts index 2d4a33100..4e98cda97 100644 --- a/arch/arm/boot/dts/at91-sama5d4ek.dts +++ b/arch/arm/boot/dts/at91-sama5d4ek.dts @@ -160,8 +160,15 @@ }; macb0: ethernet@f8020000 { + pinctrl-0 = <&pinctrl_macb0_rmii &pinctrl_macb0_phy_irq>; phy-mode = "rmii"; status = "okay"; + + ethernet-phy@1 { + reg = <0x1>; + interrupt-parent = <&pioE>; + interrupts = <1 IRQ_TYPE_LEVEL_LOW>; + }; }; mmc1: mmc@fc000000 { @@ -193,6 +200,10 @@ pinctrl@fc06a000 { board { + pinctrl_macb0_phy_irq: macb0_phy_irq { + atmel,pins = + <AT91_PIOE 1 AT91_PERIPH_GPIO AT91_PINCTRL_NONE>; + }; pinctrl_mmc0_cd: mmc0_cd { atmel,pins = <AT91_PIOE 5 AT91_PERIPH_GPIO AT91_PINCTRL_PULL_UP_DEGLITCH>; diff --git a/arch/arm/boot/dts/logicpd-torpedo-som.dtsi b/arch/arm/boot/dts/logicpd-torpedo-som.dtsi index 36387b114..80f6c786a 100644 --- a/arch/arm/boot/dts/logicpd-torpedo-som.dtsi +++ b/arch/arm/boot/dts/logicpd-torpedo-som.dtsi @@ -122,6 +122,7 @@ interrupt-parent = <&gpio5>; interrupts = <24 IRQ_TYPE_LEVEL_HIGH>; /* gpio 152 */ ref-clock-frequency = <26000000>; + tcxo-clock-frequency = <26000000>; }; }; diff --git a/arch/arm/boot/dts/omap5-board-common.dtsi b/arch/arm/boot/dts/omap5-board-common.dtsi index 5cf76a1c5..41e80e7f2 100644 --- a/arch/arm/boot/dts/omap5-board-common.dtsi +++ b/arch/arm/boot/dts/omap5-board-common.dtsi @@ -130,6 +130,16 @@ }; }; +&gpio8 { + /* TI trees use GPIO instead of msecure, see also muxing */ + p234 { + gpio-hog; + gpios = <10 GPIO_ACTIVE_HIGH>; + output-high; + line-name = "gpio8_234/msecure"; + }; +}; + &omap5_pmx_core { pinctrl-names = "default"; pinctrl-0 = < @@ -213,6 +223,13 @@ >; }; + /* TI trees use GPIO mode; msecure mode does not work reliably? */ + palmas_msecure_pins: palmas_msecure_pins { + pinctrl-single,pins = < + OMAP5_IOPAD(0x180, PIN_OUTPUT | MUX_MODE6) /* gpio8_234 */ + >; + }; + usbhost_pins: pinmux_usbhost_pins { pinctrl-single,pins = < 0x84 (PIN_INPUT | MUX_MODE0) /* usbb2_hsic_strobe */ @@ -278,6 +295,12 @@ &usbhost_wkup_pins >; + palmas_sys_nirq_pins: pinmux_palmas_sys_nirq_pins { + pinctrl-single,pins = < + OMAP5_IOPAD(0x068, PIN_INPUT_PULLUP | MUX_MODE0) /* sys_nirq1 */ + >; + }; + usbhost_wkup_pins: pinmux_usbhost_wkup_pins { pinctrl-single,pins = < 0x1A (PIN_OUTPUT | MUX_MODE0) /* fref_clk1_out, USB hub clk */ @@ -345,6 +368,8 @@ interrupt-controller; #interrupt-cells = <2>; ti,system-power-controller; + pinctrl-names = "default"; + pinctrl-0 = <&palmas_sys_nirq_pins &palmas_msecure_pins>; extcon_usb3: palmas_usb { compatible = "ti,palmas-usb-vid"; @@ -358,6 +383,14 @@ #clock-cells = <0>; }; + rtc { + compatible = "ti,palmas-rtc"; + interrupt-parent = <&palmas>; + interrupts = <8 IRQ_TYPE_NONE>; + ti,backup-battery-chargeable; + ti,backup-battery-charge-high-current; + }; + palmas_pmic { compatible = "ti,palmas-pmic"; interrupt-parent = <&palmas>; diff --git a/arch/arm/boot/dts/sama5d4.dtsi b/arch/arm/boot/dts/sama5d4.dtsi index 2193637b9..3daf8d5d7 100644 --- a/arch/arm/boot/dts/sama5d4.dtsi +++ b/arch/arm/boot/dts/sama5d4.dtsi @@ -1342,7 +1342,7 @@ dbgu: serial@fc069000 { compatible = "atmel,at91sam9260-dbgu", "atmel,at91sam9260-usart"; reg = <0xfc069000 0x200>; - interrupts = <2 IRQ_TYPE_LEVEL_HIGH 7>; + interrupts = <45 IRQ_TYPE_LEVEL_HIGH 7>; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_dbgu>; clocks = <&dbgu_clk>; diff --git a/arch/arm/boot/dts/ste-nomadik-stn8815.dtsi b/arch/arm/boot/dts/ste-nomadik-stn8815.dtsi index d0c743853..27a333eb8 100644 --- a/arch/arm/boot/dts/ste-nomadik-stn8815.dtsi +++ b/arch/arm/boot/dts/ste-nomadik-stn8815.dtsi @@ -127,22 +127,14 @@ }; mmcsd_default_mode: mmcsd_default { mmcsd_default_cfg1 { - /* MCCLK */ - pins = "GPIO8_B10"; - ste,output = <0>; - }; - mmcsd_default_cfg2 { - /* MCCMDDIR, MCDAT0DIR, MCDAT31DIR, MCDATDIR2 */ - pins = "GPIO10_C11", "GPIO15_A12", - "GPIO16_C13", "GPIO23_D15"; - ste,output = <1>; - }; - mmcsd_default_cfg3 { - /* MCCMD, MCDAT3-0, MCMSFBCLK */ - pins = "GPIO9_A10", "GPIO11_B11", - "GPIO12_A11", "GPIO13_C12", - "GPIO14_B12", "GPIO24_C15"; - ste,input = <1>; + /* + * MCCLK, MCCMDDIR, MCDAT0DIR, MCDAT31DIR, MCDATDIR2 + * MCCMD, MCDAT3-0, MCMSFBCLK + */ + pins = "GPIO8_B10", "GPIO9_A10", "GPIO10_C11", "GPIO11_B11", + "GPIO12_A11", "GPIO13_C12", "GPIO14_B12", "GPIO15_A12", + "GPIO16_C13", "GPIO23_D15", "GPIO24_C15"; + ste,output = <2>; }; }; }; @@ -802,10 +794,21 @@ clock-names = "mclk", "apb_pclk"; interrupt-parent = <&vica>; interrupts = <22>; - max-frequency = <48000000>; + max-frequency = <400000>; bus-width = <4>; cap-mmc-highspeed; cap-sd-highspeed; + full-pwr-cycle; + /* + * The STw4811 circuit used with the Nomadik strictly + * requires that all of these signal direction pins be + * routed and used for its 4-bit levelshifter. + */ + st,sig-dir-dat0; + st,sig-dir-dat2; + st,sig-dir-dat31; + st,sig-dir-cmd; + st,sig-pin-fbclk; pinctrl-names = "default"; pinctrl-0 = <&mmcsd_default_mux>, <&mmcsd_default_mode>; vmmc-supply = <&vmmc_regulator>; diff --git a/arch/arm/common/icst.c b/arch/arm/common/icst.c index 2dc6da70a..d7ed25270 100644 --- a/arch/arm/common/icst.c +++ b/arch/arm/common/icst.c @@ -16,7 +16,7 @@ */ #include <linux/module.h> #include <linux/kernel.h> - +#include <asm/div64.h> #include <asm/hardware/icst.h> /* @@ -29,7 +29,11 @@ EXPORT_SYMBOL(icst525_s2div); unsigned long icst_hz(const struct icst_params *p, struct icst_vco vco) { - return p->ref * 2 * (vco.v + 8) / ((vco.r + 2) * p->s2div[vco.s]); + u64 dividend = p->ref * 2 * (u64)(vco.v + 8); + u32 divisor = (vco.r + 2) * p->s2div[vco.s]; + + do_div(dividend, divisor); + return (unsigned long)dividend; } EXPORT_SYMBOL(icst_hz); @@ -58,6 +62,7 @@ icst_hz_to_vco(const struct icst_params *p, unsigned long freq) if (f > p->vco_min && f <= p->vco_max) break; + i++; } while (i < 8); if (i >= 8) diff --git a/arch/arm/mach-omap2/sleep34xx.S b/arch/arm/mach-omap2/sleep34xx.S index eafd120b5..1b9f0520d 100644 --- a/arch/arm/mach-omap2/sleep34xx.S +++ b/arch/arm/mach-omap2/sleep34xx.S @@ -86,13 +86,18 @@ ENTRY(enable_omap3630_toggle_l2_on_restore) stmfd sp!, {lr} @ save registers on stack /* Setup so that we will disable and enable l2 */ mov r1, #0x1 - adrl r2, l2dis_3630 @ may be too distant for plain adr - str r1, [r2] + adrl r3, l2dis_3630_offset @ may be too distant for plain adr + ldr r2, [r3] @ value for offset + str r1, [r2, r3] @ write to l2dis_3630 ldmfd sp!, {pc} @ restore regs and return ENDPROC(enable_omap3630_toggle_l2_on_restore) - .text -/* Function to call rom code to save secure ram context */ +/* + * Function to call rom code to save secure ram context. This gets + * relocated to SRAM, so it can be all in .data section. Otherwise + * we need to initialize api_params separately. + */ + .data .align 3 ENTRY(save_secure_ram_context) stmfd sp!, {r4 - r11, lr} @ save registers on stack @@ -126,6 +131,8 @@ ENDPROC(save_secure_ram_context) ENTRY(save_secure_ram_context_sz) .word . - save_secure_ram_context + .text + /* * ====================== * == Idle entry point == @@ -289,12 +296,6 @@ wait_sdrc_ready: bic r5, r5, #0x40 str r5, [r4] -/* - * PC-relative stores lead to undefined behaviour in Thumb-2: use a r7 as a - * base instead. - * Be careful not to clobber r7 when maintaing this code. - */ - is_dll_in_lock_mode: /* Is dll in lock mode? */ ldr r4, sdrc_dlla_ctrl @@ -302,11 +303,7 @@ is_dll_in_lock_mode: tst r5, #0x4 bne exit_nonoff_modes @ Return if locked /* wait till dll locks */ - adr r7, kick_counter wait_dll_lock_timed: - ldr r4, wait_dll_lock_counter - add r4, r4, #1 - str r4, [r7, #wait_dll_lock_counter - kick_counter] ldr r4, sdrc_dlla_status /* Wait 20uS for lock */ mov r6, #8 @@ -330,9 +327,6 @@ kick_dll: orr r6, r6, #(1<<3) @ enable dll str r6, [r4] dsb - ldr r4, kick_counter - add r4, r4, #1 - str r4, [r7] @ kick_counter b wait_dll_lock_timed exit_nonoff_modes: @@ -360,15 +354,6 @@ sdrc_dlla_status: .word SDRC_DLLA_STATUS_V sdrc_dlla_ctrl: .word SDRC_DLLA_CTRL_V - /* - * When exporting to userspace while the counters are in SRAM, - * these 2 words need to be at the end to facilitate retrival! - */ -kick_counter: - .word 0 -wait_dll_lock_counter: - .word 0 - ENTRY(omap3_do_wfi_sz) .word . - omap3_do_wfi @@ -437,7 +422,9 @@ ENTRY(omap3_restore) cmp r2, #0x0 @ Check if target power state was OFF or RET bne logic_l1_restore - ldr r0, l2dis_3630 + adr r1, l2dis_3630_offset @ address for offset + ldr r0, [r1] @ value for offset + ldr r0, [r1, r0] @ value at l2dis_3630 cmp r0, #0x1 @ should we disable L2 on 3630? bne skipl2dis mrc p15, 0, r0, c1, c0, 1 @@ -449,12 +436,14 @@ skipl2dis: and r1, #0x700 cmp r1, #0x300 beq l2_inv_gp + adr r0, l2_inv_api_params_offset + ldr r3, [r0] + add r3, r3, r0 @ r3 points to dummy parameters mov r0, #40 @ set service ID for PPA mov r12, r0 @ copy secure Service ID in r12 mov r1, #0 @ set task id for ROM code in r1 mov r2, #4 @ set some flags in r2, r6 mov r6, #0xff - adr r3, l2_inv_api_params @ r3 points to dummy parameters dsb @ data write barrier dmb @ data memory barrier smc #1 @ call SMI monitor (smi #1) @@ -488,8 +477,8 @@ skipl2dis: b logic_l1_restore .align -l2_inv_api_params: - .word 0x1, 0x00 +l2_inv_api_params_offset: + .long l2_inv_api_params - . l2_inv_gp: /* Execute smi to invalidate L2 cache */ mov r12, #0x1 @ set up to invalidate L2 @@ -506,7 +495,9 @@ l2_inv_gp: mov r12, #0x2 smc #0 @ Call SMI monitor (smieq) logic_l1_restore: - ldr r1, l2dis_3630 + adr r0, l2dis_3630_offset @ adress for offset + ldr r1, [r0] @ value for offset + ldr r1, [r0, r1] @ value at l2dis_3630 cmp r1, #0x1 @ Test if L2 re-enable needed on 3630 bne skipl2reen mrc p15, 0, r1, c1, c0, 1 @@ -535,9 +526,17 @@ control_stat: .word CONTROL_STAT control_mem_rta: .word CONTROL_MEM_RTA_CTRL +l2dis_3630_offset: + .long l2dis_3630 - . + + .data l2dis_3630: .word 0 + .data +l2_inv_api_params: + .word 0x1, 0x00 + /* * Internal functions */ diff --git a/arch/arm/mach-omap2/sleep44xx.S b/arch/arm/mach-omap2/sleep44xx.S index 9b09d85d8..c7a3b4aab 100644 --- a/arch/arm/mach-omap2/sleep44xx.S +++ b/arch/arm/mach-omap2/sleep44xx.S @@ -29,12 +29,6 @@ dsb .endm -ppa_zero_params: - .word 0x0 - -ppa_por_params: - .word 1, 0 - #ifdef CONFIG_ARCH_OMAP4 /* @@ -266,7 +260,9 @@ ENTRY(omap4_cpu_resume) beq skip_ns_smp_enable ppa_actrl_retry: mov r0, #OMAP4_PPA_CPU_ACTRL_SMP_INDEX - adr r3, ppa_zero_params @ Pointer to parameters + adr r1, ppa_zero_params_offset + ldr r3, [r1] + add r3, r3, r1 @ Pointer to ppa_zero_params mov r1, #0x0 @ Process ID mov r2, #0x4 @ Flag mov r6, #0xff @@ -303,7 +299,9 @@ skip_ns_smp_enable: ldr r0, =OMAP4_PPA_L2_POR_INDEX ldr r1, =OMAP44XX_SAR_RAM_BASE ldr r4, [r1, #L2X0_PREFETCH_CTRL_OFFSET] - adr r3, ppa_por_params + adr r1, ppa_por_params_offset + ldr r3, [r1] + add r3, r3, r1 @ Pointer to ppa_por_params str r4, [r3, #0x04] mov r1, #0x0 @ Process ID mov r2, #0x4 @ Flag @@ -328,6 +326,8 @@ skip_l2en: #endif b cpu_resume @ Jump to generic resume +ppa_por_params_offset: + .long ppa_por_params - . ENDPROC(omap4_cpu_resume) #endif /* CONFIG_ARCH_OMAP4 */ @@ -380,4 +380,13 @@ ENTRY(omap_do_wfi) nop ldmfd sp!, {pc} +ppa_zero_params_offset: + .long ppa_zero_params - . ENDPROC(omap_do_wfi) + + .data +ppa_zero_params: + .word 0 + +ppa_por_params: + .word 1, 0 diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c index 7963aa4b5..354144e33 100644 --- a/arch/arm64/mm/dma-mapping.c +++ b/arch/arm64/mm/dma-mapping.c @@ -933,6 +933,10 @@ static int __init __iommu_dma_init(void) ret = register_iommu_dma_ops_notifier(&platform_bus_type); if (!ret) ret = register_iommu_dma_ops_notifier(&amba_bustype); + + /* handle devices queued before this arch_initcall */ + if (!ret) + __iommu_attach_notifier(NULL, BUS_NOTIFY_ADD_DEVICE, NULL); return ret; } arch_initcall(__iommu_dma_init); diff --git a/arch/arm64/mm/pageattr.c b/arch/arm64/mm/pageattr.c index 3571c7309..cf6240741 100644 --- a/arch/arm64/mm/pageattr.c +++ b/arch/arm64/mm/pageattr.c @@ -57,6 +57,9 @@ static int change_memory_common(unsigned long addr, int numpages, if (end < MODULES_VADDR || end >= MODULES_END) return -EINVAL; + if (!numpages) + return 0; + data.set_mask = set_mask; data.clear_mask = clear_mask; diff --git a/arch/m32r/kernel/setup.c b/arch/m32r/kernel/setup.c index 0392112a5..a5ecef718 100644 --- a/arch/m32r/kernel/setup.c +++ b/arch/m32r/kernel/setup.c @@ -81,7 +81,10 @@ static struct resource code_resource = { }; unsigned long memory_start; +EXPORT_SYMBOL(memory_start); + unsigned long memory_end; +EXPORT_SYMBOL(memory_end); void __init setup_arch(char **); int get_cpuinfo(char *); diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h index c5eb86f3d..867c39b45 100644 --- a/arch/powerpc/include/asm/eeh.h +++ b/arch/powerpc/include/asm/eeh.h @@ -81,6 +81,7 @@ struct pci_dn; #define EEH_PE_KEEP (1 << 8) /* Keep PE on hotplug */ #define EEH_PE_CFG_RESTRICTED (1 << 9) /* Block config on error */ #define EEH_PE_REMOVED (1 << 10) /* Removed permanently */ +#define EEH_PE_PRI_BUS (1 << 11) /* Cached primary bus */ struct eeh_pe { int type; /* PE type: PHB/Bus/Device */ diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c index 8d14feb40..f69ecaa7c 100644 --- a/arch/powerpc/kernel/eeh_driver.c +++ b/arch/powerpc/kernel/eeh_driver.c @@ -564,6 +564,7 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus) */ eeh_pe_state_mark(pe, EEH_PE_KEEP); if (bus) { + eeh_pe_state_clear(pe, EEH_PE_PRI_BUS); pci_lock_rescan_remove(); pcibios_remove_pci_devices(bus); pci_unlock_rescan_remove(); @@ -803,6 +804,7 @@ perm_error: * the their PCI config any more. */ if (frozen_bus) { + eeh_pe_state_clear(pe, EEH_PE_PRI_BUS); eeh_pe_dev_mode_mark(pe, EEH_DEV_REMOVED); pci_lock_rescan_remove(); @@ -886,6 +888,7 @@ static void eeh_handle_special_event(void) continue; /* Notify all devices to be down */ + eeh_pe_state_clear(pe, EEH_PE_PRI_BUS); bus = eeh_pe_bus_get(phb_pe); eeh_pe_dev_traverse(pe, eeh_report_failure, NULL); diff --git a/arch/powerpc/kernel/eeh_pe.c b/arch/powerpc/kernel/eeh_pe.c index 8654cb166..98f81800e 100644 --- a/arch/powerpc/kernel/eeh_pe.c +++ b/arch/powerpc/kernel/eeh_pe.c @@ -883,32 +883,29 @@ void eeh_pe_restore_bars(struct eeh_pe *pe) const char *eeh_pe_loc_get(struct eeh_pe *pe) { struct pci_bus *bus = eeh_pe_bus_get(pe); - struct device_node *dn = pci_bus_to_OF_node(bus); + struct device_node *dn; const char *loc = NULL; - if (!dn) - goto out; + while (bus) { + dn = pci_bus_to_OF_node(bus); + if (!dn) { + bus = bus->parent; + continue; + } - /* PHB PE or root PE ? */ - if (pci_is_root_bus(bus)) { - loc = of_get_property(dn, "ibm,loc-code", NULL); - if (!loc) + if (pci_is_root_bus(bus)) loc = of_get_property(dn, "ibm,io-base-loc-code", NULL); + else + loc = of_get_property(dn, "ibm,slot-location-code", + NULL); + if (loc) - goto out; + return loc; - /* Check the root port */ - dn = dn->child; - if (!dn) - goto out; + bus = bus->parent; } - loc = of_get_property(dn, "ibm,loc-code", NULL); - if (!loc) - loc = of_get_property(dn, "ibm,slot-location-code", NULL); - -out: - return loc ? loc : "N/A"; + return "N/A"; } /** @@ -931,7 +928,7 @@ struct pci_bus *eeh_pe_bus_get(struct eeh_pe *pe) bus = pe->phb->bus; } else if (pe->type & EEH_PE_BUS || pe->type & EEH_PE_DEVICE) { - if (pe->bus) { + if (pe->state & EEH_PE_PRI_BUS) { bus = pe->bus; goto out; } diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index 3c6badcd5..e57cc383e 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -2153,7 +2153,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) /* Emulate H_SET_DABR/X on P8 for the sake of compat mode guests */ 2: rlwimi r5, r4, 5, DAWRX_DR | DAWRX_DW - rlwimi r5, r4, 1, DAWRX_WT + rlwimi r5, r4, 2, DAWRX_WT clrrdi r4, r4, 3 std r4, VCPU_DAWR(r3) std r5, VCPU_DAWRX(r3) diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 6fd2405c7..a3b182dcb 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -919,21 +919,17 @@ int kvm_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg) r = -ENXIO; break; } - vcpu->arch.vr.vr[reg->id - KVM_REG_PPC_VR0] = val.vval; + val.vval = vcpu->arch.vr.vr[reg->id - KVM_REG_PPC_VR0]; break; case KVM_REG_PPC_VSCR: if (!cpu_has_feature(CPU_FTR_ALTIVEC)) { r = -ENXIO; break; } - vcpu->arch.vr.vscr.u[3] = set_reg_val(reg->id, val); + val = get_reg_val(reg->id, vcpu->arch.vr.vscr.u[3]); break; case KVM_REG_PPC_VRSAVE: - if (!cpu_has_feature(CPU_FTR_ALTIVEC)) { - r = -ENXIO; - break; - } - vcpu->arch.vrsave = set_reg_val(reg->id, val); + val = get_reg_val(reg->id, vcpu->arch.vrsave); break; #endif /* CONFIG_ALTIVEC */ default: @@ -974,17 +970,21 @@ int kvm_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg) r = -ENXIO; break; } - val.vval = vcpu->arch.vr.vr[reg->id - KVM_REG_PPC_VR0]; + vcpu->arch.vr.vr[reg->id - KVM_REG_PPC_VR0] = val.vval; break; case KVM_REG_PPC_VSCR: if (!cpu_has_feature(CPU_FTR_ALTIVEC)) { r = -ENXIO; break; } - val = get_reg_val(reg->id, vcpu->arch.vr.vscr.u[3]); + vcpu->arch.vr.vscr.u[3] = set_reg_val(reg->id, val); break; case KVM_REG_PPC_VRSAVE: - val = get_reg_val(reg->id, vcpu->arch.vrsave); + if (!cpu_has_feature(CPU_FTR_ALTIVEC)) { + r = -ENXIO; + break; + } + vcpu->arch.vrsave = set_reg_val(reg->id, val); break; #endif /* CONFIG_ALTIVEC */ default: diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c index e1c907255..2ba602591 100644 --- a/arch/powerpc/platforms/powernv/eeh-powernv.c +++ b/arch/powerpc/platforms/powernv/eeh-powernv.c @@ -444,9 +444,12 @@ static void *pnv_eeh_probe(struct pci_dn *pdn, void *data) * PCI devices of the PE are expected to be removed prior * to PE reset. */ - if (!edev->pe->bus) + if (!(edev->pe->state & EEH_PE_PRI_BUS)) { edev->pe->bus = pci_find_bus(hose->global_number, pdn->busno); + if (edev->pe->bus) + edev->pe->state |= EEH_PE_PRI_BUS; + } /* * Enable EEH explicitly so that we will do EEH check diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index 414fd1a00..e40d07146 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -3034,6 +3034,7 @@ static void pnv_pci_ioda_shutdown(struct pci_controller *hose) static const struct pci_controller_ops pnv_pci_ioda_controller_ops = { .dma_dev_setup = pnv_pci_dma_dev_setup, + .dma_bus_setup = pnv_pci_dma_bus_setup, #ifdef CONFIG_PCI_MSI .setup_msi_irqs = pnv_setup_msi_irqs, .teardown_msi_irqs = pnv_teardown_msi_irqs, diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c index f2dd77234..ad8c3f4a5 100644 --- a/arch/powerpc/platforms/powernv/pci.c +++ b/arch/powerpc/platforms/powernv/pci.c @@ -601,6 +601,9 @@ int pnv_tce_build(struct iommu_table *tbl, long index, long npages, u64 rpn = __pa(uaddr) >> tbl->it_page_shift; long i; + if (proto_tce & TCE_PCI_WRITE) + proto_tce |= TCE_PCI_READ; + for (i = 0; i < npages; i++) { unsigned long newtce = proto_tce | ((rpn + i) << tbl->it_page_shift); @@ -622,6 +625,9 @@ int pnv_tce_xchg(struct iommu_table *tbl, long index, BUG_ON(*hpa & ~IOMMU_PAGE_MASK(tbl)); + if (newtce & TCE_PCI_WRITE) + newtce |= TCE_PCI_READ; + oldtce = xchg(pnv_tce(tbl, idx), cpu_to_be64(newtce)); *hpa = be64_to_cpu(oldtce) & ~(TCE_PCI_READ | TCE_PCI_WRITE); *direction = iommu_tce_direction(oldtce); @@ -762,6 +768,26 @@ void pnv_pci_dma_dev_setup(struct pci_dev *pdev) phb->dma_dev_setup(phb, pdev); } +void pnv_pci_dma_bus_setup(struct pci_bus *bus) +{ + struct pci_controller *hose = bus->sysdata; + struct pnv_phb *phb = hose->private_data; + struct pnv_ioda_pe *pe; + + list_for_each_entry(pe, &phb->ioda.pe_list, list) { + if (!(pe->flags & (PNV_IODA_PE_BUS | PNV_IODA_PE_BUS_ALL))) + continue; + + if (!pe->pbus) + continue; + + if (bus->number == ((pe->rid >> 8) & 0xFF)) { + pe->pbus = bus; + break; + } + } +} + void pnv_pci_shutdown(void) { struct pci_controller *hose; diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h index c8ff50e90..36a99feab 100644 --- a/arch/powerpc/platforms/powernv/pci.h +++ b/arch/powerpc/platforms/powernv/pci.h @@ -235,6 +235,7 @@ extern void pnv_pci_reset_secondary_bus(struct pci_dev *dev); extern int pnv_eeh_phb_reset(struct pci_controller *hose, int option); extern void pnv_pci_dma_dev_setup(struct pci_dev *pdev); +extern void pnv_pci_dma_bus_setup(struct pci_bus *bus); extern int pnv_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type); extern void pnv_teardown_msi_irqs(struct pci_dev *pdev); diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index a471cadb9..79c91853e 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -363,20 +363,18 @@ static inline enum page_cache_mode pgprot2cachemode(pgprot_t pgprot) } static inline pgprot_t pgprot_4k_2_large(pgprot_t pgprot) { + pgprotval_t val = pgprot_val(pgprot); pgprot_t new; - unsigned long val; - val = pgprot_val(pgprot); pgprot_val(new) = (val & ~(_PAGE_PAT | _PAGE_PAT_LARGE)) | ((val & _PAGE_PAT) << (_PAGE_BIT_PAT_LARGE - _PAGE_BIT_PAT)); return new; } static inline pgprot_t pgprot_large_2_4k(pgprot_t pgprot) { + pgprotval_t val = pgprot_val(pgprot); pgprot_t new; - unsigned long val; - val = pgprot_val(pgprot); pgprot_val(new) = (val & ~(_PAGE_PAT | _PAGE_PAT_LARGE)) | ((val & _PAGE_PAT_LARGE) >> (_PAGE_BIT_PAT_LARGE - _PAGE_BIT_PAT)); diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S index 982ce34f4..27f89c79a 100644 --- a/arch/x86/lib/copy_user_64.S +++ b/arch/x86/lib/copy_user_64.S @@ -232,17 +232,31 @@ ENDPROC(copy_user_enhanced_fast_string) /* * copy_user_nocache - Uncached memory copy with exception handling - * This will force destination/source out of cache for more performance. + * This will force destination out of cache for more performance. + * + * Note: Cached memory copy is used when destination or size is not + * naturally aligned. That is: + * - Require 8-byte alignment when size is 8 bytes or larger. + * - Require 4-byte alignment when size is 4 bytes. */ ENTRY(__copy_user_nocache) ASM_STAC + + /* If size is less than 8 bytes, go to 4-byte copy */ cmpl $8,%edx - jb 20f /* less then 8 bytes, go to byte copy loop */ + jb .L_4b_nocache_copy_entry + + /* If destination is not 8-byte aligned, "cache" copy to align it */ ALIGN_DESTINATION + + /* Set 4x8-byte copy count and remainder */ movl %edx,%ecx andl $63,%edx shrl $6,%ecx - jz 17f + jz .L_8b_nocache_copy_entry /* jump if count is 0 */ + + /* Perform 4x8-byte nocache loop-copy */ +.L_4x8b_nocache_copy_loop: 1: movq (%rsi),%r8 2: movq 1*8(%rsi),%r9 3: movq 2*8(%rsi),%r10 @@ -262,60 +276,106 @@ ENTRY(__copy_user_nocache) leaq 64(%rsi),%rsi leaq 64(%rdi),%rdi decl %ecx - jnz 1b -17: movl %edx,%ecx + jnz .L_4x8b_nocache_copy_loop + + /* Set 8-byte copy count and remainder */ +.L_8b_nocache_copy_entry: + movl %edx,%ecx andl $7,%edx shrl $3,%ecx - jz 20f -18: movq (%rsi),%r8 -19: movnti %r8,(%rdi) + jz .L_4b_nocache_copy_entry /* jump if count is 0 */ + + /* Perform 8-byte nocache loop-copy */ +.L_8b_nocache_copy_loop: +20: movq (%rsi),%r8 +21: movnti %r8,(%rdi) leaq 8(%rsi),%rsi leaq 8(%rdi),%rdi decl %ecx - jnz 18b -20: andl %edx,%edx - jz 23f + jnz .L_8b_nocache_copy_loop + + /* If no byte left, we're done */ +.L_4b_nocache_copy_entry: + andl %edx,%edx + jz .L_finish_copy + + /* If destination is not 4-byte aligned, go to byte copy: */ + movl %edi,%ecx + andl $3,%ecx + jnz .L_1b_cache_copy_entry + + /* Set 4-byte copy count (1 or 0) and remainder */ movl %edx,%ecx -21: movb (%rsi),%al -22: movb %al,(%rdi) + andl $3,%edx + shrl $2,%ecx + jz .L_1b_cache_copy_entry /* jump if count is 0 */ + + /* Perform 4-byte nocache copy: */ +30: movl (%rsi),%r8d +31: movnti %r8d,(%rdi) + leaq 4(%rsi),%rsi + leaq 4(%rdi),%rdi + + /* If no bytes left, we're done: */ + andl %edx,%edx + jz .L_finish_copy + + /* Perform byte "cache" loop-copy for the remainder */ +.L_1b_cache_copy_entry: + movl %edx,%ecx +.L_1b_cache_copy_loop: +40: movb (%rsi),%al +41: movb %al,(%rdi) incq %rsi incq %rdi decl %ecx - jnz 21b -23: xorl %eax,%eax + jnz .L_1b_cache_copy_loop + + /* Finished copying; fence the prior stores */ +.L_finish_copy: + xorl %eax,%eax ASM_CLAC sfence ret .section .fixup,"ax" -30: shll $6,%ecx +.L_fixup_4x8b_copy: + shll $6,%ecx addl %ecx,%edx - jmp 60f -40: lea (%rdx,%rcx,8),%rdx - jmp 60f -50: movl %ecx,%edx -60: sfence + jmp .L_fixup_handle_tail +.L_fixup_8b_copy: + lea (%rdx,%rcx,8),%rdx + jmp .L_fixup_handle_tail +.L_fixup_4b_copy: + lea (%rdx,%rcx,4),%rdx + jmp .L_fixup_handle_tail +.L_fixup_1b_copy: + movl %ecx,%edx +.L_fixup_handle_tail: + sfence jmp copy_user_handle_tail .previous - _ASM_EXTABLE(1b,30b) - _ASM_EXTABLE(2b,30b) - _ASM_EXTABLE(3b,30b) - _ASM_EXTABLE(4b,30b) - _ASM_EXTABLE(5b,30b) - _ASM_EXTABLE(6b,30b) - _ASM_EXTABLE(7b,30b) - _ASM_EXTABLE(8b,30b) - _ASM_EXTABLE(9b,30b) - _ASM_EXTABLE(10b,30b) - _ASM_EXTABLE(11b,30b) - _ASM_EXTABLE(12b,30b) - _ASM_EXTABLE(13b,30b) - _ASM_EXTABLE(14b,30b) - _ASM_EXTABLE(15b,30b) - _ASM_EXTABLE(16b,30b) - _ASM_EXTABLE(18b,40b) - _ASM_EXTABLE(19b,40b) - _ASM_EXTABLE(21b,50b) - _ASM_EXTABLE(22b,50b) + _ASM_EXTABLE(1b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(2b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(3b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(4b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(5b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(6b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(7b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(8b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(9b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(10b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(11b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(12b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(13b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(14b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(15b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(16b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(20b,.L_fixup_8b_copy) + _ASM_EXTABLE(21b,.L_fixup_8b_copy) + _ASM_EXTABLE(30b,.L_fixup_4b_copy) + _ASM_EXTABLE(31b,.L_fixup_4b_copy) + _ASM_EXTABLE(40b,.L_fixup_1b_copy) + _ASM_EXTABLE(41b,.L_fixup_1b_copy) ENDPROC(__copy_user_nocache) diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 3b544e4c1..8d2472be4 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -288,6 +288,9 @@ static noinline int vmalloc_fault(unsigned long address) if (!pmd_k) return -1; + if (pmd_huge(*pmd_k)) + return 0; + pte_k = pte_offset_kernel(pmd_k, address); if (!pte_present(*pte_k)) return -1; @@ -361,8 +364,6 @@ void vmalloc_sync_all(void) * 64-bit: * * Handle a fault on the vmalloc area - * - * This assumes no large pages in there. */ static noinline int vmalloc_fault(unsigned long address) { @@ -404,17 +405,23 @@ static noinline int vmalloc_fault(unsigned long address) if (pud_none(*pud_ref)) return -1; - if (pud_none(*pud) || pud_page_vaddr(*pud) != pud_page_vaddr(*pud_ref)) + if (pud_none(*pud) || pud_pfn(*pud) != pud_pfn(*pud_ref)) BUG(); + if (pud_huge(*pud)) + return 0; + pmd = pmd_offset(pud, address); pmd_ref = pmd_offset(pud_ref, address); if (pmd_none(*pmd_ref)) return -1; - if (pmd_none(*pmd) || pmd_page(*pmd) != pmd_page(*pmd_ref)) + if (pmd_none(*pmd) || pmd_pfn(*pmd) != pmd_pfn(*pmd_ref)) BUG(); + if (pmd_huge(*pmd)) + return 0; + pte_ref = pte_offset_kernel(pmd_ref, address); if (!pte_present(*pte_ref)) return -1; diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index a3137a4fe..db20ee9a4 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -33,7 +33,7 @@ struct cpa_data { pgd_t *pgd; pgprot_t mask_set; pgprot_t mask_clr; - int numpages; + unsigned long numpages; int flags; unsigned long pfn; unsigned force_split : 1; @@ -1345,7 +1345,7 @@ static int __change_page_attr_set_clr(struct cpa_data *cpa, int checkalias) * CPA operation. Either a large page has been * preserved or a single page update happened. */ - BUG_ON(cpa->numpages > numpages); + BUG_ON(cpa->numpages > numpages || !cpa->numpages); numpages -= cpa->numpages; if (cpa->flags & (CPA_PAGES_ARRAY | CPA_ARRAY)) cpa->curpage++; diff --git a/drivers/gpu/drm/drm_irq.c b/drivers/gpu/drm/drm_irq.c index 607f493ae..809098918 100644 --- a/drivers/gpu/drm/drm_irq.c +++ b/drivers/gpu/drm/drm_irq.c @@ -221,6 +221,64 @@ static void drm_update_vblank_count(struct drm_device *dev, unsigned int pipe, diff = (flags & DRM_CALLED_FROM_VBLIRQ) != 0; } + /* + * Within a drm_vblank_pre_modeset - drm_vblank_post_modeset + * interval? If so then vblank irqs keep running and it will likely + * happen that the hardware vblank counter is not trustworthy as it + * might reset at some point in that interval and vblank timestamps + * are not trustworthy either in that interval. Iow. this can result + * in a bogus diff >> 1 which must be avoided as it would cause + * random large forward jumps of the software vblank counter. + */ + if (diff > 1 && (vblank->inmodeset & 0x2)) { + DRM_DEBUG_VBL("clamping vblank bump to 1 on crtc %u: diffr=%u" + " due to pre-modeset.\n", pipe, diff); + diff = 1; + } + + /* + * FIMXE: Need to replace this hack with proper seqlocks. + * + * Restrict the bump of the software vblank counter to a safe maximum + * value of +1 whenever there is the possibility that concurrent readers + * of vblank timestamps could be active at the moment, as the current + * implementation of the timestamp caching and updating is not safe + * against concurrent readers for calls to store_vblank() with a bump + * of anything but +1. A bump != 1 would very likely return corrupted + * timestamps to userspace, because the same slot in the cache could + * be concurrently written by store_vblank() and read by one of those + * readers without the read-retry logic detecting the collision. + * + * Concurrent readers can exist when we are called from the + * drm_vblank_off() or drm_vblank_on() functions and other non-vblank- + * irq callers. However, all those calls to us are happening with the + * vbl_lock locked to prevent drm_vblank_get(), so the vblank refcount + * can't increase while we are executing. Therefore a zero refcount at + * this point is safe for arbitrary counter bumps if we are called + * outside vblank irq, a non-zero count is not 100% safe. Unfortunately + * we must also accept a refcount of 1, as whenever we are called from + * drm_vblank_get() -> drm_vblank_enable() the refcount will be 1 and + * we must let that one pass through in order to not lose vblank counts + * during vblank irq off - which would completely defeat the whole + * point of this routine. + * + * Whenever we are called from vblank irq, we have to assume concurrent + * readers exist or can show up any time during our execution, even if + * the refcount is currently zero, as vblank irqs are usually only + * enabled due to the presence of readers, and because when we are called + * from vblank irq we can't hold the vbl_lock to protect us from sudden + * bumps in vblank refcount. Therefore also restrict bumps to +1 when + * called from vblank irq. + */ + if ((diff > 1) && (atomic_read(&vblank->refcount) > 1 || + (flags & DRM_CALLED_FROM_VBLIRQ))) { + DRM_DEBUG_VBL("clamping vblank bump to 1 on crtc %u: diffr=%u " + "refcount %u, vblirq %u\n", pipe, diff, + atomic_read(&vblank->refcount), + (flags & DRM_CALLED_FROM_VBLIRQ) != 0); + diff = 1; + } + DRM_DEBUG_VBL("updating vblank count on crtc %u:" " current=%u, diff=%u, hw=%u hw_last=%u\n", pipe, vblank->count, diff, cur_vblank, vblank->last); @@ -1313,7 +1371,13 @@ void drm_vblank_off(struct drm_device *dev, unsigned int pipe) spin_lock_irqsave(&dev->event_lock, irqflags); spin_lock(&dev->vbl_lock); - vblank_disable_and_save(dev, pipe); + DRM_DEBUG_VBL("crtc %d, vblank enabled %d, inmodeset %d\n", + pipe, vblank->enabled, vblank->inmodeset); + + /* Avoid redundant vblank disables without previous drm_vblank_on(). */ + if (drm_core_check_feature(dev, DRIVER_ATOMIC) || !vblank->inmodeset) + vblank_disable_and_save(dev, pipe); + wake_up(&vblank->queue); /* @@ -1415,6 +1479,9 @@ void drm_vblank_on(struct drm_device *dev, unsigned int pipe) return; spin_lock_irqsave(&dev->vbl_lock, irqflags); + DRM_DEBUG_VBL("crtc %d, vblank enabled %d, inmodeset %d\n", + pipe, vblank->enabled, vblank->inmodeset); + /* Drop our private "prevent drm_vblank_get" refcount */ if (vblank->inmodeset) { atomic_dec(&vblank->refcount); @@ -1427,8 +1494,7 @@ void drm_vblank_on(struct drm_device *dev, unsigned int pipe) * re-enable interrupts if there are users left, or the * user wishes vblank interrupts to be enabled all the time. */ - if (atomic_read(&vblank->refcount) != 0 || - (!dev->vblank_disable_immediate && drm_vblank_offdelay == 0)) + if (atomic_read(&vblank->refcount) != 0 || drm_vblank_offdelay == 0) WARN_ON(drm_vblank_enable(dev, pipe)); spin_unlock_irqrestore(&dev->vbl_lock, irqflags); } @@ -1523,6 +1589,7 @@ void drm_vblank_post_modeset(struct drm_device *dev, unsigned int pipe) if (vblank->inmodeset) { spin_lock_irqsave(&dev->vbl_lock, irqflags); dev->vblank_disable_allowed = true; + drm_reset_vblank_timestamp(dev, pipe); spin_unlock_irqrestore(&dev->vbl_lock, irqflags); if (vblank->inmodeset & 0x2) diff --git a/drivers/gpu/drm/nouveau/nouveau_display.c b/drivers/gpu/drm/nouveau/nouveau_display.c index 64c8d932d..58a3f7cf2 100644 --- a/drivers/gpu/drm/nouveau/nouveau_display.c +++ b/drivers/gpu/drm/nouveau/nouveau_display.c @@ -634,10 +634,6 @@ nouveau_display_resume(struct drm_device *dev, bool runtime) nv_crtc->lut.depth = 0; } - /* Make sure that drm and hw vblank irqs get resumed if needed. */ - for (head = 0; head < dev->mode_config.num_crtc; head++) - drm_vblank_on(dev, head); - /* This should ensure we don't hit a locking problem when someone * wakes us up via a connector. We should never go into suspend * while the display is on anyways. @@ -647,6 +643,10 @@ nouveau_display_resume(struct drm_device *dev, bool runtime) drm_helper_resume_force_mode(dev); + /* Make sure that drm and hw vblank irqs get resumed if needed. */ + for (head = 0; head < dev->mode_config.num_crtc; head++) + drm_vblank_on(dev, head); + list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) { struct nouveau_crtc *nv_crtc = nouveau_crtc(crtc); diff --git a/drivers/gpu/drm/radeon/radeon_pm.c b/drivers/gpu/drm/radeon/radeon_pm.c index 59abebd6b..a94979f59 100644 --- a/drivers/gpu/drm/radeon/radeon_pm.c +++ b/drivers/gpu/drm/radeon/radeon_pm.c @@ -276,8 +276,12 @@ static void radeon_pm_set_clocks(struct radeon_device *rdev) if (rdev->irq.installed) { for (i = 0; i < rdev->num_crtc; i++) { if (rdev->pm.active_crtcs & (1 << i)) { - rdev->pm.req_vblank |= (1 << i); - drm_vblank_get(rdev->ddev, i); + /* This can fail if a modeset is in progress */ + if (drm_vblank_get(rdev->ddev, i) == 0) + rdev->pm.req_vblank |= (1 << i); + else + DRM_DEBUG_DRIVER("crtc %d no vblank, can glitch\n", + i); } } } diff --git a/drivers/hwspinlock/hwspinlock_core.c b/drivers/hwspinlock/hwspinlock_core.c index 52f708bcf..d50c701b1 100644 --- a/drivers/hwspinlock/hwspinlock_core.c +++ b/drivers/hwspinlock/hwspinlock_core.c @@ -313,6 +313,10 @@ int of_hwspin_lock_get_id(struct device_node *np, int index) hwlock = radix_tree_deref_slot(slot); if (unlikely(!hwlock)) continue; + if (radix_tree_is_indirect_ptr(hwlock)) { + slot = radix_tree_iter_retry(&iter); + continue; + } if (hwlock->bank->dev->of_node == args.np) { ret = 0; diff --git a/drivers/iio/accel/Kconfig b/drivers/iio/accel/Kconfig index 969428dd6..16cc5c691 100644 --- a/drivers/iio/accel/Kconfig +++ b/drivers/iio/accel/Kconfig @@ -173,6 +173,7 @@ config STK8312 config STK8BA50 tristate "Sensortek STK8BA50 3-Axis Accelerometer Driver" depends on I2C + depends on IIO_TRIGGER help Say yes here to get support for the Sensortek STK8BA50 3-axis accelerometer. diff --git a/drivers/iio/adc/Kconfig b/drivers/iio/adc/Kconfig index 7868c744f..1e7aded53 100644 --- a/drivers/iio/adc/Kconfig +++ b/drivers/iio/adc/Kconfig @@ -372,6 +372,7 @@ config TWL6030_GPADC config VF610_ADC tristate "Freescale vf610 ADC driver" depends on OF + depends on HAS_IOMEM select IIO_BUFFER select IIO_TRIGGERED_BUFFER help diff --git a/drivers/iio/adc/ti_am335x_adc.c b/drivers/iio/adc/ti_am335x_adc.c index 942320e32..c1e05532d 100644 --- a/drivers/iio/adc/ti_am335x_adc.c +++ b/drivers/iio/adc/ti_am335x_adc.c @@ -289,7 +289,7 @@ static int tiadc_iio_buffered_hardware_setup(struct iio_dev *indio_dev, goto error_kfifo_free; indio_dev->setup_ops = setup_ops; - indio_dev->modes |= INDIO_BUFFER_HARDWARE; + indio_dev->modes |= INDIO_BUFFER_SOFTWARE; return 0; diff --git a/drivers/iio/dac/mcp4725.c b/drivers/iio/dac/mcp4725.c index 43d145884..b4dde8315 100644 --- a/drivers/iio/dac/mcp4725.c +++ b/drivers/iio/dac/mcp4725.c @@ -300,6 +300,7 @@ static int mcp4725_probe(struct i2c_client *client, data->client = client; indio_dev->dev.parent = &client->dev; + indio_dev->name = id->name; indio_dev->info = &mcp4725_info; indio_dev->channels = &mcp4725_channel; indio_dev->num_channels = 1; diff --git a/drivers/iio/imu/adis_buffer.c b/drivers/iio/imu/adis_buffer.c index cb32b593f..36607d52f 100644 --- a/drivers/iio/imu/adis_buffer.c +++ b/drivers/iio/imu/adis_buffer.c @@ -43,7 +43,7 @@ int adis_update_scan_mode(struct iio_dev *indio_dev, return -ENOMEM; rx = adis->buffer; - tx = rx + indio_dev->scan_bytes; + tx = rx + scan_count; spi_message_init(&adis->msg); diff --git a/drivers/iio/inkern.c b/drivers/iio/inkern.c index c8bad3cf8..217e9306a 100644 --- a/drivers/iio/inkern.c +++ b/drivers/iio/inkern.c @@ -351,6 +351,8 @@ EXPORT_SYMBOL_GPL(iio_channel_get); void iio_channel_release(struct iio_channel *channel) { + if (!channel) + return; iio_device_put(channel->indio_dev); kfree(channel); } diff --git a/drivers/iio/light/acpi-als.c b/drivers/iio/light/acpi-als.c index 60537ec0c..53201d99a 100644 --- a/drivers/iio/light/acpi-als.c +++ b/drivers/iio/light/acpi-als.c @@ -54,7 +54,9 @@ static const struct iio_chan_spec acpi_als_channels[] = { .realbits = 32, .storagebits = 32, }, - .info_mask_separate = BIT(IIO_CHAN_INFO_RAW), + /* _RAW is here for backward ABI compatibility */ + .info_mask_separate = BIT(IIO_CHAN_INFO_RAW) | + BIT(IIO_CHAN_INFO_PROCESSED), }, }; @@ -152,7 +154,7 @@ static int acpi_als_read_raw(struct iio_dev *indio_dev, s32 temp_val; int ret; - if (mask != IIO_CHAN_INFO_RAW) + if ((mask != IIO_CHAN_INFO_PROCESSED) && (mask != IIO_CHAN_INFO_RAW)) return -EINVAL; /* we support only illumination (_ALI) so far. */ diff --git a/drivers/iio/light/ltr501.c b/drivers/iio/light/ltr501.c index 809a961b9..6bf89d8f3 100644 --- a/drivers/iio/light/ltr501.c +++ b/drivers/iio/light/ltr501.c @@ -180,7 +180,7 @@ static const struct ltr501_samp_table ltr501_ps_samp_table[] = { {500000, 2000000} }; -static unsigned int ltr501_match_samp_freq(const struct ltr501_samp_table *tab, +static int ltr501_match_samp_freq(const struct ltr501_samp_table *tab, int len, int val, int val2) { int i, freq; diff --git a/drivers/iio/pressure/mpl115.c b/drivers/iio/pressure/mpl115.c index f5ecd6e19..a0d7deeac 100644 --- a/drivers/iio/pressure/mpl115.c +++ b/drivers/iio/pressure/mpl115.c @@ -117,7 +117,7 @@ static int mpl115_read_raw(struct iio_dev *indio_dev, *val = ret >> 6; return IIO_VAL_INT; case IIO_CHAN_INFO_OFFSET: - *val = 605; + *val = -605; *val2 = 750000; return IIO_VAL_INT_PLUS_MICRO; case IIO_CHAN_INFO_SCALE: diff --git a/drivers/input/mouse/elantech.c b/drivers/input/mouse/elantech.c index 537ebb0e1..78f93cf68 100644 --- a/drivers/input/mouse/elantech.c +++ b/drivers/input/mouse/elantech.c @@ -1222,7 +1222,7 @@ static int elantech_set_input_params(struct psmouse *psmouse) input_set_abs_params(dev, ABS_TOOL_WIDTH, ETP_WMIN_V2, ETP_WMAX_V2, 0, 0); } - input_mt_init_slots(dev, 2, 0); + input_mt_init_slots(dev, 2, INPUT_MT_SEMI_MT); input_set_abs_params(dev, ABS_MT_POSITION_X, x_min, x_max, 0, 0); input_set_abs_params(dev, ABS_MT_POSITION_Y, y_min, y_max, 0, 0); break; diff --git a/drivers/input/mouse/vmmouse.c b/drivers/input/mouse/vmmouse.c index e272f0625..a3f0f5a47 100644 --- a/drivers/input/mouse/vmmouse.c +++ b/drivers/input/mouse/vmmouse.c @@ -458,8 +458,6 @@ int vmmouse_init(struct psmouse *psmouse) priv->abs_dev = abs_dev; psmouse->private = priv; - input_set_capability(rel_dev, EV_REL, REL_WHEEL); - /* Set up and register absolute device */ snprintf(priv->phys, sizeof(priv->phys), "%s/input1", psmouse->ps2dev.serio->phys); @@ -475,10 +473,6 @@ int vmmouse_init(struct psmouse *psmouse) abs_dev->id.version = psmouse->model; abs_dev->dev.parent = &psmouse->ps2dev.serio->dev; - error = input_register_device(priv->abs_dev); - if (error) - goto init_fail; - /* Set absolute device capabilities */ input_set_capability(abs_dev, EV_KEY, BTN_LEFT); input_set_capability(abs_dev, EV_KEY, BTN_RIGHT); @@ -488,6 +482,13 @@ int vmmouse_init(struct psmouse *psmouse) input_set_abs_params(abs_dev, ABS_X, 0, VMMOUSE_MAX_X, 0, 0); input_set_abs_params(abs_dev, ABS_Y, 0, VMMOUSE_MAX_Y, 0, 0); + error = input_register_device(priv->abs_dev); + if (error) + goto init_fail; + + /* Add wheel capability to the relative device */ + input_set_capability(rel_dev, EV_REL, REL_WHEEL); + psmouse->protocol_handler = vmmouse_process_byte; psmouse->disconnect = vmmouse_disconnect; psmouse->reconnect = vmmouse_reconnect; diff --git a/drivers/input/serio/i8042-x86ia64io.h b/drivers/input/serio/i8042-x86ia64io.h index c11556563..68f5f4a0f 100644 --- a/drivers/input/serio/i8042-x86ia64io.h +++ b/drivers/input/serio/i8042-x86ia64io.h @@ -258,6 +258,13 @@ static const struct dmi_system_id __initconst i8042_dmi_nomux_table[] = { }, }, { + /* Fujitsu Lifebook U745 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"), + DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK U745"), + }, + }, + { /* Fujitsu T70H */ .matches = { DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"), diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c index 8b2be1e77..fc836f523 100644 --- a/drivers/iommu/amd_iommu.c +++ b/drivers/iommu/amd_iommu.c @@ -1905,7 +1905,7 @@ static void do_attach(struct iommu_dev_data *dev_data, /* Update device table */ set_dte_entry(dev_data->devid, domain, ats); if (alias != dev_data->devid) - set_dte_entry(dev_data->devid, domain, ats); + set_dte_entry(alias, domain, ats); device_flush_dte(dev_data); } diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c index 80e3c1760..55a19e492 100644 --- a/drivers/iommu/dmar.c +++ b/drivers/iommu/dmar.c @@ -1347,7 +1347,7 @@ void dmar_disable_qi(struct intel_iommu *iommu) raw_spin_lock_irqsave(&iommu->register_lock, flags); - sts = dmar_readq(iommu->reg + DMAR_GSTS_REG); + sts = readl(iommu->reg + DMAR_GSTS_REG); if (!(sts & DMA_GSTS_QIES)) goto end; diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index ac7387686..986a53e3e 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -1489,7 +1489,7 @@ static void iommu_disable_dev_iotlb(struct device_domain_info *info) { struct pci_dev *pdev; - if (dev_is_pci(info->dev)) + if (!dev_is_pci(info->dev)) return; pdev = to_pci_dev(info->dev); diff --git a/drivers/iommu/intel-svm.c b/drivers/iommu/intel-svm.c index 50464833d..d9939fa9b 100644 --- a/drivers/iommu/intel-svm.c +++ b/drivers/iommu/intel-svm.c @@ -249,12 +249,30 @@ static void intel_flush_pasid_dev(struct intel_svm *svm, struct intel_svm_dev *s static void intel_mm_release(struct mmu_notifier *mn, struct mm_struct *mm) { struct intel_svm *svm = container_of(mn, struct intel_svm, notifier); + struct intel_svm_dev *sdev; + /* This might end up being called from exit_mmap(), *before* the page + * tables are cleared. And __mmu_notifier_release() will delete us from + * the list of notifiers so that our invalidate_range() callback doesn't + * get called when the page tables are cleared. So we need to protect + * against hardware accessing those page tables. + * + * We do it by clearing the entry in the PASID table and then flushing + * the IOTLB and the PASID table caches. This might upset hardware; + * perhaps we'll want to point the PASID to a dummy PGD (like the zero + * page) so that we end up taking a fault that the hardware really + * *has* to handle gracefully without affecting other processes. + */ svm->iommu->pasid_table[svm->pasid].val = 0; + wmb(); + + rcu_read_lock(); + list_for_each_entry_rcu(sdev, &svm->devs, list) { + intel_flush_pasid_dev(svm, sdev, svm->pasid); + intel_flush_svm_range_dev(svm, sdev, 0, -1, 0, !svm->mm); + } + rcu_read_unlock(); - /* There's no need to do any flush because we can't get here if there - * are any devices left anyway. */ - WARN_ON(!list_empty(&svm->devs)); } static const struct mmu_notifier_ops intel_mmuops = { @@ -379,7 +397,6 @@ int intel_svm_bind_mm(struct device *dev, int *pasid, int flags, struct svm_dev_ goto out; } iommu->pasid_table[svm->pasid].val = (u64)__pa(mm->pgd) | 1; - mm = NULL; } else iommu->pasid_table[svm->pasid].val = (u64)__pa(init_mm.pgd) | 1 | (1ULL << 11); wmb(); @@ -442,11 +459,11 @@ int intel_svm_unbind_mm(struct device *dev, int pasid) kfree_rcu(sdev, rcu); if (list_empty(&svm->devs)) { - mmu_notifier_unregister(&svm->notifier, svm->mm); idr_remove(&svm->iommu->pasid_idr, svm->pasid); if (svm->mm) - mmput(svm->mm); + mmu_notifier_unregister(&svm->notifier, svm->mm); + /* We mandate that no page faults may be outstanding * for the PASID when intel_svm_unbind_mm() is called. * If that is not obeyed, subtle errors will happen. @@ -507,6 +524,10 @@ static irqreturn_t prq_event_thread(int irq, void *d) struct intel_svm *svm = NULL; int head, tail, handled = 0; + /* Clear PPR bit before reading head/tail registers, to + * ensure that we get a new interrupt if needed. */ + writel(DMA_PRS_PPR, iommu->reg + DMAR_PRS_REG); + tail = dmar_readq(iommu->reg + DMAR_PQT_REG) & PRQ_RING_MASK; head = dmar_readq(iommu->reg + DMAR_PQH_REG) & PRQ_RING_MASK; while (head != tail) { @@ -551,6 +572,9 @@ static irqreturn_t prq_event_thread(int irq, void *d) * any faults on kernel addresses. */ if (!svm->mm) goto bad_req; + /* If the mm is already defunct, don't handle faults. */ + if (!atomic_inc_not_zero(&svm->mm->mm_users)) + goto bad_req; down_read(&svm->mm->mmap_sem); vma = find_extend_vma(svm->mm, address); if (!vma || address < vma->vm_start) @@ -567,6 +591,7 @@ static irqreturn_t prq_event_thread(int irq, void *d) result = QI_RESP_SUCCESS; invalid: up_read(&svm->mm->mmap_sem); + mmput(svm->mm); bad_req: /* Accounting for major/minor faults? */ rcu_read_lock(); diff --git a/drivers/iommu/intel_irq_remapping.c b/drivers/iommu/intel_irq_remapping.c index 1fae18816..e9b241b1c 100644 --- a/drivers/iommu/intel_irq_remapping.c +++ b/drivers/iommu/intel_irq_remapping.c @@ -629,7 +629,7 @@ static void iommu_disable_irq_remapping(struct intel_iommu *iommu) raw_spin_lock_irqsave(&iommu->register_lock, flags); - sts = dmar_readq(iommu->reg + DMAR_GSTS_REG); + sts = readl(iommu->reg + DMAR_GSTS_REG); if (!(sts & DMA_GSTS_IRES)) goto end; diff --git a/drivers/nvdimm/namespace_devs.c b/drivers/nvdimm/namespace_devs.c index 0955b2cb1..62120c38d 100644 --- a/drivers/nvdimm/namespace_devs.c +++ b/drivers/nvdimm/namespace_devs.c @@ -77,6 +77,59 @@ static bool is_namespace_io(struct device *dev) return dev ? dev->type == &namespace_io_device_type : false; } +static int is_uuid_busy(struct device *dev, void *data) +{ + u8 *uuid1 = data, *uuid2 = NULL; + + if (is_namespace_pmem(dev)) { + struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev); + + uuid2 = nspm->uuid; + } else if (is_namespace_blk(dev)) { + struct nd_namespace_blk *nsblk = to_nd_namespace_blk(dev); + + uuid2 = nsblk->uuid; + } else if (is_nd_btt(dev)) { + struct nd_btt *nd_btt = to_nd_btt(dev); + + uuid2 = nd_btt->uuid; + } else if (is_nd_pfn(dev)) { + struct nd_pfn *nd_pfn = to_nd_pfn(dev); + + uuid2 = nd_pfn->uuid; + } + + if (uuid2 && memcmp(uuid1, uuid2, NSLABEL_UUID_LEN) == 0) + return -EBUSY; + + return 0; +} + +static int is_namespace_uuid_busy(struct device *dev, void *data) +{ + if (is_nd_pmem(dev) || is_nd_blk(dev)) + return device_for_each_child(dev, data, is_uuid_busy); + return 0; +} + +/** + * nd_is_uuid_unique - verify that no other namespace has @uuid + * @dev: any device on a nvdimm_bus + * @uuid: uuid to check + */ +bool nd_is_uuid_unique(struct device *dev, u8 *uuid) +{ + struct nvdimm_bus *nvdimm_bus = walk_to_nvdimm_bus(dev); + + if (!nvdimm_bus) + return false; + WARN_ON_ONCE(!is_nvdimm_bus_locked(&nvdimm_bus->dev)); + if (device_for_each_child(&nvdimm_bus->dev, uuid, + is_namespace_uuid_busy) != 0) + return false; + return true; +} + bool pmem_should_map_pages(struct device *dev) { struct nd_region *nd_region = to_nd_region(dev->parent); diff --git a/drivers/nvdimm/region_devs.c b/drivers/nvdimm/region_devs.c index 529f3f02e..9521696c9 100644 --- a/drivers/nvdimm/region_devs.c +++ b/drivers/nvdimm/region_devs.c @@ -134,62 +134,6 @@ int nd_region_to_nstype(struct nd_region *nd_region) } EXPORT_SYMBOL(nd_region_to_nstype); -static int is_uuid_busy(struct device *dev, void *data) -{ - struct nd_region *nd_region = to_nd_region(dev->parent); - u8 *uuid = data; - - switch (nd_region_to_nstype(nd_region)) { - case ND_DEVICE_NAMESPACE_PMEM: { - struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev); - - if (!nspm->uuid) - break; - if (memcmp(uuid, nspm->uuid, NSLABEL_UUID_LEN) == 0) - return -EBUSY; - break; - } - case ND_DEVICE_NAMESPACE_BLK: { - struct nd_namespace_blk *nsblk = to_nd_namespace_blk(dev); - - if (!nsblk->uuid) - break; - if (memcmp(uuid, nsblk->uuid, NSLABEL_UUID_LEN) == 0) - return -EBUSY; - break; - } - default: - break; - } - - return 0; -} - -static int is_namespace_uuid_busy(struct device *dev, void *data) -{ - if (is_nd_pmem(dev) || is_nd_blk(dev)) - return device_for_each_child(dev, data, is_uuid_busy); - return 0; -} - -/** - * nd_is_uuid_unique - verify that no other namespace has @uuid - * @dev: any device on a nvdimm_bus - * @uuid: uuid to check - */ -bool nd_is_uuid_unique(struct device *dev, u8 *uuid) -{ - struct nvdimm_bus *nvdimm_bus = walk_to_nvdimm_bus(dev); - - if (!nvdimm_bus) - return false; - WARN_ON_ONCE(!is_nvdimm_bus_locked(&nvdimm_bus->dev)); - if (device_for_each_child(&nvdimm_bus->dev, uuid, - is_namespace_uuid_busy) != 0) - return false; - return true; -} - static ssize_t size_show(struct device *dev, struct device_attribute *attr, char *buf) { diff --git a/drivers/phy/phy-twl4030-usb.c b/drivers/phy/phy-twl4030-usb.c index 3a707dd14..f96065a81 100644 --- a/drivers/phy/phy-twl4030-usb.c +++ b/drivers/phy/phy-twl4030-usb.c @@ -715,6 +715,7 @@ static int twl4030_usb_probe(struct platform_device *pdev) pm_runtime_use_autosuspend(&pdev->dev); pm_runtime_set_autosuspend_delay(&pdev->dev, 2000); pm_runtime_enable(&pdev->dev); + pm_runtime_get_sync(&pdev->dev); /* Our job is to use irqs and status from the power module * to keep the transceiver disabled when nothing's connected. @@ -750,6 +751,7 @@ static int twl4030_usb_remove(struct platform_device *pdev) struct twl4030_usb *twl = platform_get_drvdata(pdev); int val; + usb_remove_phy(&twl->phy); pm_runtime_get_sync(twl->dev); cancel_delayed_work(&twl->id_workaround_work); device_remove_file(twl->dev, &dev_attr_vbus); @@ -757,6 +759,13 @@ static int twl4030_usb_remove(struct platform_device *pdev) /* set transceiver mode to power on defaults */ twl4030_usb_set_mode(twl, -1); + /* idle ulpi before powering off */ + if (cable_present(twl->linkstat)) + pm_runtime_put_noidle(twl->dev); + pm_runtime_mark_last_busy(twl->dev); + pm_runtime_put_sync_suspend(twl->dev); + pm_runtime_disable(twl->dev); + /* autogate 60MHz ULPI clock, * clear dpll clock request for i2c access, * disable 32KHz @@ -771,11 +780,6 @@ static int twl4030_usb_remove(struct platform_device *pdev) /* disable complete OTG block */ twl4030_usb_clear_bits(twl, POWER_CTRL, POWER_CTRL_OTG_ENAB); - if (cable_present(twl->linkstat)) - pm_runtime_put_noidle(twl->dev); - pm_runtime_mark_last_busy(twl->dev); - pm_runtime_put(twl->dev); - return 0; } diff --git a/drivers/platform/x86/intel_scu_ipcutil.c b/drivers/platform/x86/intel_scu_ipcutil.c index 02bc5a634..aa4542414 100644 --- a/drivers/platform/x86/intel_scu_ipcutil.c +++ b/drivers/platform/x86/intel_scu_ipcutil.c @@ -49,7 +49,7 @@ struct scu_ipc_data { static int scu_reg_access(u32 cmd, struct scu_ipc_data *data) { - int count = data->count; + unsigned int count = data->count; if (count == 0 || count == 3 || count > 4) return -EINVAL; diff --git a/drivers/scsi/device_handler/scsi_dh_rdac.c b/drivers/scsi/device_handler/scsi_dh_rdac.c index 361358134..93880ed62 100644 --- a/drivers/scsi/device_handler/scsi_dh_rdac.c +++ b/drivers/scsi/device_handler/scsi_dh_rdac.c @@ -562,7 +562,7 @@ static int mode_select_handle_sense(struct scsi_device *sdev, /* * Command Lock contention */ - err = SCSI_DH_RETRY; + err = SCSI_DH_IMM_RETRY; break; default: break; @@ -612,6 +612,8 @@ retry: err = mode_select_handle_sense(sdev, h->sense); if (err == SCSI_DH_RETRY && retry_cnt--) goto retry; + if (err == SCSI_DH_IMM_RETRY) + goto retry; } if (err == SCSI_DH_OK) { h->state = RDAC_STATE_ACTIVE; diff --git a/drivers/scsi/scsi_devinfo.c b/drivers/scsi/scsi_devinfo.c index 2c1160c7e..da2e068ee 100644 --- a/drivers/scsi/scsi_devinfo.c +++ b/drivers/scsi/scsi_devinfo.c @@ -205,6 +205,7 @@ static struct { {"Intel", "Multi-Flex", NULL, BLIST_NO_RSOC}, {"iRiver", "iFP Mass Driver", NULL, BLIST_NOT_LOCKABLE | BLIST_INQUIRY_36}, {"LASOUND", "CDX7405", "3.10", BLIST_MAX5LUN | BLIST_SINGLELUN}, + {"Marvell", "Console", NULL, BLIST_SKIP_VPD_PAGES}, {"MATSHITA", "PD-1", NULL, BLIST_FORCELUN | BLIST_SINGLELUN}, {"MATSHITA", "DMC-LC5", NULL, BLIST_NOT_LOCKABLE | BLIST_INQUIRY_36}, {"MATSHITA", "DMC-LC40", NULL, BLIST_NOT_LOCKABLE | BLIST_INQUIRY_36}, @@ -227,6 +228,7 @@ static struct { {"Promise", "VTrak E610f", NULL, BLIST_SPARSELUN | BLIST_NO_RSOC}, {"Promise", "", NULL, BLIST_SPARSELUN}, {"QNAP", "iSCSI Storage", NULL, BLIST_MAX_1024}, + {"SYNOLOGY", "iSCSI Storage", NULL, BLIST_MAX_1024}, {"QUANTUM", "XP34301", "1071", BLIST_NOTQ}, {"REGAL", "CDC-4X", NULL, BLIST_MAX5LUN | BLIST_SINGLELUN}, {"SanDisk", "ImageMate CF-SD1", NULL, BLIST_FORCELUN}, diff --git a/drivers/scsi/scsi_sysfs.c b/drivers/scsi/scsi_sysfs.c index 21930c9ac..c8115b4fe 100644 --- a/drivers/scsi/scsi_sysfs.c +++ b/drivers/scsi/scsi_sysfs.c @@ -1192,16 +1192,18 @@ static void __scsi_remove_target(struct scsi_target *starget) void scsi_remove_target(struct device *dev) { struct Scsi_Host *shost = dev_to_shost(dev->parent); - struct scsi_target *starget; + struct scsi_target *starget, *last_target = NULL; unsigned long flags; restart: spin_lock_irqsave(shost->host_lock, flags); list_for_each_entry(starget, &shost->__targets, siblings) { - if (starget->state == STARGET_DEL) + if (starget->state == STARGET_DEL || + starget == last_target) continue; if (starget->dev.parent == dev || &starget->dev == dev) { kref_get(&starget->reap_ref); + last_target = starget; spin_unlock_irqrestore(shost->host_lock, flags); __scsi_remove_target(starget); scsi_target_reap(starget); diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index 4e08d1cd7..84fa4c46e 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -3268,8 +3268,8 @@ static int sd_suspend_common(struct device *dev, bool ignore_stop_errors) struct scsi_disk *sdkp = dev_get_drvdata(dev); int ret = 0; - if (!sdkp) - return 0; /* this can happen */ + if (!sdkp) /* E.g.: runtime suspend following sd_remove() */ + return 0; if (sdkp->WCE && sdkp->media_present) { sd_printk(KERN_NOTICE, sdkp, "Synchronizing SCSI cache\n"); @@ -3308,6 +3308,9 @@ static int sd_resume(struct device *dev) { struct scsi_disk *sdkp = dev_get_drvdata(dev); + if (!sdkp) /* E.g.: runtime resume at the start of sd_probe() */ + return 0; + if (!sdkp->device->manage_start_stop) return 0; diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c index 503ab8b46..5e8206744 100644 --- a/drivers/scsi/sg.c +++ b/drivers/scsi/sg.c @@ -1261,7 +1261,7 @@ sg_mmap(struct file *filp, struct vm_area_struct *vma) } sfp->mmap_called = 1; - vma->vm_flags |= VM_DONTEXPAND | VM_DONTDUMP; + vma->vm_flags |= VM_IO | VM_DONTEXPAND | VM_DONTDUMP; vma->vm_private_data = sfp; vma->vm_ops = &sg_mmap_vm_ops; return 0; diff --git a/drivers/scsi/sr.c b/drivers/scsi/sr.c index 8bd54a64e..64c867405 100644 --- a/drivers/scsi/sr.c +++ b/drivers/scsi/sr.c @@ -144,6 +144,9 @@ static int sr_runtime_suspend(struct device *dev) { struct scsi_cd *cd = dev_get_drvdata(dev); + if (!cd) /* E.g.: runtime suspend following sr_remove() */ + return 0; + if (cd->media_present) return -EBUSY; else @@ -985,6 +988,7 @@ static int sr_remove(struct device *dev) scsi_autopm_get_device(cd->device); del_gendisk(cd->disk); + dev_set_drvdata(dev, NULL); mutex_lock(&sr_ref_mutex); kref_put(&cd->kref, sr_kref_release); diff --git a/drivers/staging/speakup/selection.c b/drivers/staging/speakup/selection.c index aa5ab6c80..41ef099b7 100644 --- a/drivers/staging/speakup/selection.c +++ b/drivers/staging/speakup/selection.c @@ -142,7 +142,9 @@ static void __speakup_paste_selection(struct work_struct *work) struct tty_ldisc *ld; DECLARE_WAITQUEUE(wait, current); - ld = tty_ldisc_ref_wait(tty); + ld = tty_ldisc_ref(tty); + if (!ld) + goto tty_unref; tty_buffer_lock_exclusive(&vc->port); add_wait_queue(&vc->paste_wait, &wait); @@ -162,6 +164,7 @@ static void __speakup_paste_selection(struct work_struct *work) tty_buffer_unlock_exclusive(&vc->port); tty_ldisc_deref(ld); +tty_unref: tty_kref_put(tty); } diff --git a/drivers/target/iscsi/iscsi_target_configfs.c b/drivers/target/iscsi/iscsi_target_configfs.c index 255204cc4..b4bfd706a 100644 --- a/drivers/target/iscsi/iscsi_target_configfs.c +++ b/drivers/target/iscsi/iscsi_target_configfs.c @@ -1593,7 +1593,8 @@ static int lio_tpg_check_prot_fabric_only( } /* - * Called with spin_lock_bh(struct se_portal_group->session_lock) held.. + * Called with spin_lock_irq(struct se_portal_group->session_lock) held + * or not held. * * Also, this function calls iscsit_inc_session_usage_count() on the * struct iscsi_session in question. @@ -1601,19 +1602,32 @@ static int lio_tpg_check_prot_fabric_only( static int lio_tpg_shutdown_session(struct se_session *se_sess) { struct iscsi_session *sess = se_sess->fabric_sess_ptr; + struct se_portal_group *se_tpg = se_sess->se_tpg; + bool local_lock = false; + + if (!spin_is_locked(&se_tpg->session_lock)) { + spin_lock_irq(&se_tpg->session_lock); + local_lock = true; + } spin_lock(&sess->conn_lock); if (atomic_read(&sess->session_fall_back_to_erl0) || atomic_read(&sess->session_logout) || (sess->time2retain_timer_flags & ISCSI_TF_EXPIRED)) { spin_unlock(&sess->conn_lock); + if (local_lock) + spin_unlock_irq(&sess->conn_lock); return 0; } atomic_set(&sess->session_reinstatement, 1); spin_unlock(&sess->conn_lock); iscsit_stop_time2retain_timer(sess); + spin_unlock_irq(&se_tpg->session_lock); + iscsit_stop_session(sess, 1, 1); + if (!local_lock) + spin_lock_irq(&se_tpg->session_lock); return 1; } diff --git a/drivers/tty/pty.c b/drivers/tty/pty.c index a45660f62..78e983677 100644 --- a/drivers/tty/pty.c +++ b/drivers/tty/pty.c @@ -681,7 +681,14 @@ static void pty_unix98_remove(struct tty_driver *driver, struct tty_struct *tty) /* this is called once with whichever end is closed last */ static void pty_unix98_shutdown(struct tty_struct *tty) { - devpts_kill_index(tty->driver_data, tty->index); + struct inode *ptmx_inode; + + if (tty->driver->subtype == PTY_TYPE_MASTER) + ptmx_inode = tty->driver_data; + else + ptmx_inode = tty->link->driver_data; + devpts_kill_index(ptmx_inode, tty->index); + devpts_del_ref(ptmx_inode); } static const struct tty_operations ptm_unix98_ops = { @@ -773,6 +780,18 @@ static int ptmx_open(struct inode *inode, struct file *filp) set_bit(TTY_PTY_LOCK, &tty->flags); /* LOCK THE SLAVE */ tty->driver_data = inode; + /* + * In the case where all references to ptmx inode are dropped and we + * still have /dev/tty opened pointing to the master/slave pair (ptmx + * is closed/released before /dev/tty), we must make sure that the inode + * is still valid when we call the final pty_unix98_shutdown, thus we + * hold an additional reference to the ptmx inode. For the same /dev/tty + * last close case, we also need to make sure the super_block isn't + * destroyed (devpts instance unmounted), before /dev/tty is closed and + * on its release devpts_kill_index is called. + */ + devpts_add_ref(inode); + tty_add_file(tty, filp); slave_inode = devpts_pty_new(inode, diff --git a/drivers/tty/serial/8250/8250_pci.c b/drivers/tty/serial/8250/8250_pci.c index 4097f3f65..7cd6f9a90 100644 --- a/drivers/tty/serial/8250/8250_pci.c +++ b/drivers/tty/serial/8250/8250_pci.c @@ -1379,6 +1379,9 @@ ce4100_serial_setup(struct serial_private *priv, #define PCI_DEVICE_ID_INTEL_BSW_UART1 0x228a #define PCI_DEVICE_ID_INTEL_BSW_UART2 0x228c +#define PCI_DEVICE_ID_INTEL_BDW_UART1 0x9ce3 +#define PCI_DEVICE_ID_INTEL_BDW_UART2 0x9ce4 + #define BYT_PRV_CLK 0x800 #define BYT_PRV_CLK_EN (1 << 0) #define BYT_PRV_CLK_M_VAL_SHIFT 1 @@ -1461,11 +1464,13 @@ byt_serial_setup(struct serial_private *priv, switch (pdev->device) { case PCI_DEVICE_ID_INTEL_BYT_UART1: case PCI_DEVICE_ID_INTEL_BSW_UART1: + case PCI_DEVICE_ID_INTEL_BDW_UART1: rx_param->src_id = 3; tx_param->dst_id = 2; break; case PCI_DEVICE_ID_INTEL_BYT_UART2: case PCI_DEVICE_ID_INTEL_BSW_UART2: + case PCI_DEVICE_ID_INTEL_BDW_UART2: rx_param->src_id = 5; tx_param->dst_id = 4; break; @@ -1936,6 +1941,7 @@ pci_wch_ch38x_setup(struct serial_private *priv, #define PCIE_VENDOR_ID_WCH 0x1c00 #define PCIE_DEVICE_ID_WCH_CH382_2S1P 0x3250 #define PCIE_DEVICE_ID_WCH_CH384_4S 0x3470 +#define PCIE_DEVICE_ID_WCH_CH382_2S 0x3253 #define PCI_VENDOR_ID_PERICOM 0x12D8 #define PCI_DEVICE_ID_PERICOM_PI7C9X7951 0x7951 @@ -2062,6 +2068,20 @@ static struct pci_serial_quirk pci_serial_quirks[] __refdata = { .subdevice = PCI_ANY_ID, .setup = byt_serial_setup, }, + { + .vendor = PCI_VENDOR_ID_INTEL, + .device = PCI_DEVICE_ID_INTEL_BDW_UART1, + .subvendor = PCI_ANY_ID, + .subdevice = PCI_ANY_ID, + .setup = byt_serial_setup, + }, + { + .vendor = PCI_VENDOR_ID_INTEL, + .device = PCI_DEVICE_ID_INTEL_BDW_UART2, + .subvendor = PCI_ANY_ID, + .subdevice = PCI_ANY_ID, + .setup = byt_serial_setup, + }, /* * ITE */ @@ -2618,6 +2638,14 @@ static struct pci_serial_quirk pci_serial_quirks[] __refdata = { .subdevice = PCI_ANY_ID, .setup = pci_wch_ch353_setup, }, + /* WCH CH382 2S card (16850 clone) */ + { + .vendor = PCIE_VENDOR_ID_WCH, + .device = PCIE_DEVICE_ID_WCH_CH382_2S, + .subvendor = PCI_ANY_ID, + .subdevice = PCI_ANY_ID, + .setup = pci_wch_ch38x_setup, + }, /* WCH CH382 2S1P card (16850 clone) */ { .vendor = PCIE_VENDOR_ID_WCH, @@ -2936,6 +2964,7 @@ enum pci_board_num_t { pbn_fintek_4, pbn_fintek_8, pbn_fintek_12, + pbn_wch382_2, pbn_wch384_4, pbn_pericom_PI7C9X7951, pbn_pericom_PI7C9X7952, @@ -3756,6 +3785,13 @@ static struct pciserial_board pci_boards[] = { .base_baud = 115200, .first_offset = 0x40, }, + [pbn_wch382_2] = { + .flags = FL_BASE0, + .num_ports = 2, + .base_baud = 115200, + .uart_offset = 8, + .first_offset = 0xC0, + }, [pbn_wch384_4] = { .flags = FL_BASE0, .num_ports = 4, @@ -5506,6 +5542,16 @@ static struct pci_device_id serial_pci_tbl[] = { PCI_CLASS_COMMUNICATION_SERIAL << 8, 0xff0000, pbn_byt }, + /* Intel Broadwell */ + { PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_BDW_UART1, + PCI_ANY_ID, PCI_ANY_ID, + PCI_CLASS_COMMUNICATION_SERIAL << 8, 0xff0000, + pbn_byt }, + { PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_BDW_UART2, + PCI_ANY_ID, PCI_ANY_ID, + PCI_CLASS_COMMUNICATION_SERIAL << 8, 0xff0000, + pbn_byt }, + /* * Intel Quark x1000 */ @@ -5545,6 +5591,10 @@ static struct pci_device_id serial_pci_tbl[] = { PCI_ANY_ID, PCI_ANY_ID, 0, 0, pbn_b0_bt_2_115200 }, + { PCIE_VENDOR_ID_WCH, PCIE_DEVICE_ID_WCH_CH382_2S, + PCI_ANY_ID, PCI_ANY_ID, + 0, 0, pbn_wch382_2 }, + { PCIE_VENDOR_ID_WCH, PCIE_DEVICE_ID_WCH_CH384_4S, PCI_ANY_ID, PCI_ANY_ID, 0, 0, pbn_wch384_4 }, diff --git a/drivers/tty/serial/omap-serial.c b/drivers/tty/serial/omap-serial.c index 9d4c84f74..24280d9a0 100644 --- a/drivers/tty/serial/omap-serial.c +++ b/drivers/tty/serial/omap-serial.c @@ -1343,7 +1343,7 @@ static inline void serial_omap_add_console_port(struct uart_omap_port *up) /* Enable or disable the rs485 support */ static int -serial_omap_config_rs485(struct uart_port *port, struct serial_rs485 *rs485conf) +serial_omap_config_rs485(struct uart_port *port, struct serial_rs485 *rs485) { struct uart_omap_port *up = to_uart_omap_port(port); unsigned int mode; @@ -1356,8 +1356,12 @@ serial_omap_config_rs485(struct uart_port *port, struct serial_rs485 *rs485conf) up->ier = 0; serial_out(up, UART_IER, 0); + /* Clamp the delays to [0, 100ms] */ + rs485->delay_rts_before_send = min(rs485->delay_rts_before_send, 100U); + rs485->delay_rts_after_send = min(rs485->delay_rts_after_send, 100U); + /* store new config */ - port->rs485 = *rs485conf; + port->rs485 = *rs485; /* * Just as a precaution, only allow rs485 diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c index eeaa6c6bd..db0f0831b 100644 --- a/drivers/usb/host/xhci-ring.c +++ b/drivers/usb/host/xhci-ring.c @@ -2192,10 +2192,6 @@ static int process_bulk_intr_td(struct xhci_hcd *xhci, struct xhci_td *td, } /* Fast path - was this the last TRB in the TD for this URB? */ } else if (event_trb == td->last_trb) { - if (td->urb_length_set && trb_comp_code == COMP_SHORT_TX) - return finish_td(xhci, td, event_trb, event, ep, - status, false); - if (EVENT_TRB_LEN(le32_to_cpu(event->transfer_len)) != 0) { td->urb->actual_length = td->urb->transfer_buffer_length - @@ -2247,12 +2243,6 @@ static int process_bulk_intr_td(struct xhci_hcd *xhci, struct xhci_td *td, td->urb->actual_length += TRB_LEN(le32_to_cpu(cur_trb->generic.field[2])) - EVENT_TRB_LEN(le32_to_cpu(event->transfer_len)); - - if (trb_comp_code == COMP_SHORT_TX) { - xhci_dbg(xhci, "mid bulk/intr SP, wait for last TRB event\n"); - td->urb_length_set = true; - return 0; - } } return finish_td(xhci, td, event_trb, event, ep, status, false); diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c index dca0a4692..776d59c32 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -1549,7 +1549,9 @@ int xhci_urb_dequeue(struct usb_hcd *hcd, struct urb *urb, int status) xhci_dbg_trace(xhci, trace_xhci_dbg_cancel_urb, "HW died, freeing TD."); urb_priv = urb->hcpriv; - for (i = urb_priv->td_cnt; i < urb_priv->length; i++) { + for (i = urb_priv->td_cnt; + i < urb_priv->length && xhci->devs[urb->dev->slot_id]; + i++) { td = urb_priv->td[i]; if (!list_empty(&td->td_list)) list_del_init(&td->td_list); diff --git a/fs/aufs/cpup.c b/fs/aufs/cpup.c index a34648874..d34a6d283 100644 --- a/fs/aufs/cpup.c +++ b/fs/aufs/cpup.c @@ -512,6 +512,55 @@ out: return err; } +/* + * regardless 'acl' option, reset all ACL. + * All ACL will be copied up later from the original entry on the lower branch. + */ +static int au_reset_acl(struct inode *h_dir, struct path *h_path, umode_t mode) +{ + int err; + struct dentry *h_dentry; + struct inode *h_inode; + + h_dentry = h_path->dentry; + h_inode = d_inode(h_dentry); + /* forget_all_cached_acls(h_inode)); */ + err = vfsub_removexattr(h_dentry, XATTR_NAME_POSIX_ACL_ACCESS); + AuTraceErr(err); + if (!err) + err = vfsub_acl_chmod(h_inode, mode); + + AuTraceErr(err); + return err; +} + +static int au_do_cpup_dir(struct au_cp_generic *cpg, struct dentry *dst_parent, + struct inode *h_dir, struct path *h_path) +{ + int err; + struct inode *dir, *inode; + + err = vfsub_removexattr(h_path->dentry, XATTR_NAME_POSIX_ACL_DEFAULT); + AuTraceErr(err); + if (err == -EOPNOTSUPP) + err = 0; + if (unlikely(err)) + goto out; + + /* + * strange behaviour from the users view, + * particularry setattr case + */ + dir = d_inode(dst_parent); + if (au_ibstart(dir) == cpg->bdst) + au_cpup_attr_nlink(dir, /*force*/1); + inode = d_inode(cpg->dentry); + au_cpup_attr_nlink(inode, /*force*/1); + +out: + return err; +} + static noinline_for_stack int cpup_entry(struct au_cp_generic *cpg, struct dentry *dst_parent, struct au_cpup_reg_attr *h_src_attr) @@ -524,7 +573,7 @@ int cpup_entry(struct au_cp_generic *cpg, struct dentry *dst_parent, struct au_dtime dt; struct path h_path; struct dentry *h_src, *h_dst, *h_parent; - struct inode *h_inode, *h_dir, *dir, *inode; + struct inode *h_inode, *h_dir; struct super_block *sb; /* bsrc branch can be ro/rw. */ @@ -564,17 +613,8 @@ int cpup_entry(struct au_cp_generic *cpg, struct dentry *dst_parent, case S_IFDIR: isdir = 1; err = vfsub_mkdir(h_dir, &h_path, mode); - if (!err) { - /* - * strange behaviour from the users view, - * particularry setattr case - */ - dir = d_inode(dst_parent); - if (au_ibstart(dir) == cpg->bdst) - au_cpup_attr_nlink(dir, /*force*/1); - inode = d_inode(cpg->dentry); - au_cpup_attr_nlink(inode, /*force*/1); - } + if (!err) + err = au_do_cpup_dir(cpg, dst_parent, h_dir, &h_path); break; case S_IFLNK: err = au_do_cpup_symlink(&h_path, h_src, h_dir); @@ -591,6 +631,8 @@ int cpup_entry(struct au_cp_generic *cpg, struct dentry *dst_parent, AuIOErr("Unknown inode type 0%o\n", mode); err = -EIO; } + if (!err) + err = au_reset_acl(h_dir, &h_path, mode); mnt_flags = au_mntflags(sb); if (!au_opt_test(mnt_flags, UDBA_NONE) diff --git a/fs/aufs/dir.c b/fs/aufs/dir.c index 8a619062a..a994e0862 100644 --- a/fs/aufs/dir.c +++ b/fs/aufs/dir.c @@ -237,11 +237,13 @@ static int do_open_dir(struct file *file, int flags, struct file *h_file) int err; aufs_bindex_t bindex, btail; struct dentry *dentry, *h_dentry; + struct vfsmount *mnt; FiMustWriteLock(file); AuDebugOn(h_file); err = 0; + mnt = file->f_path.mnt; dentry = file->f_path.dentry; file->f_version = d_inode(dentry)->i_version; bindex = au_dbstart(dentry); @@ -253,6 +255,9 @@ static int do_open_dir(struct file *file, int flags, struct file *h_file) if (!h_dentry) continue; + err = vfsub_test_mntns(mnt, h_dentry->d_sb); + if (unlikely(err)) + break; h_file = au_h_open(dentry, bindex, flags, file, /*force_wr*/0); if (IS_ERR(h_file)) { err = PTR_ERR(h_file); diff --git a/fs/aufs/export.c b/fs/aufs/export.c index 4ce7732b7..7f6fec61f 100644 --- a/fs/aufs/export.c +++ b/fs/aufs/export.c @@ -597,7 +597,7 @@ aufs_fh_to_dentry(struct super_block *sb, struct fid *fid, int fh_len, ino = decode_ino(fh + Fh_ino); /* it should never happen */ if (unlikely(ino == AUFS_ROOT_INO)) - goto out; + goto out_unlock; dir_ino = decode_ino(fh + Fh_dir_ino); dentry = decode_by_ino(sb, ino, dir_ino); diff --git a/fs/aufs/f_op.c b/fs/aufs/f_op.c index c1be75cb0..2baacd7a6 100644 --- a/fs/aufs/f_op.c +++ b/fs/aufs/f_op.c @@ -16,7 +16,7 @@ int au_do_open_nondir(struct file *file, int flags, struct file *h_file) { int err; aufs_bindex_t bindex; - struct dentry *dentry; + struct dentry *dentry, *h_dentry; struct au_finfo *finfo; struct inode *h_inode; @@ -29,10 +29,19 @@ int au_do_open_nondir(struct file *file, int flags, struct file *h_file) memset(&finfo->fi_htop, 0, sizeof(finfo->fi_htop)); atomic_set(&finfo->fi_mmapped, 0); bindex = au_dbstart(dentry); - if (!h_file) + if (!h_file) { + h_dentry = au_h_dptr(dentry, bindex); + err = vfsub_test_mntns(file->f_path.mnt, h_dentry->d_sb); + if (unlikely(err)) + goto out; h_file = au_h_open(dentry, bindex, flags, file, /*force_wr*/0); - else + } else { + h_dentry = h_file->f_path.dentry; + err = vfsub_test_mntns(file->f_path.mnt, h_dentry->d_sb); + if (unlikely(err)) + goto out; get_file(h_file); + } if (IS_ERR(h_file)) err = PTR_ERR(h_file); else { @@ -50,6 +59,7 @@ int au_do_open_nondir(struct file *file, int flags, struct file *h_file) /* file->f_ra = h_file->f_ra; */ } +out: return err; } diff --git a/fs/aufs/fstype.h b/fs/aufs/fstype.h index e429a8b17..725b2ffff 100644 --- a/fs/aufs/fstype.h +++ b/fs/aufs/fstype.h @@ -240,7 +240,6 @@ static inline int au_test_hfsplus(struct super_block *sb __maybe_unused) static inline int au_test_fs_unsuppoted(struct super_block *sb) { return - au_test_fuse(sb) || /* for a security reason, temporarily */ #ifndef CONFIG_AUFS_BR_RAMFS au_test_ramfs(sb) || #endif diff --git a/fs/aufs/i_op.c b/fs/aufs/i_op.c index 1c634bab9..6e50526d8 100644 --- a/fs/aufs/i_op.c +++ b/fs/aufs/i_op.c @@ -963,6 +963,12 @@ static int aufs_setattr(struct dentry *dentry, struct iattr *ia) break; } } + /* + * regardless aufs 'acl' option setting. + * why don't all acl-aware fs call this func from their ->setattr()? + */ + if (!err && (ia->ia_valid & ATTR_MODE)) + err = vfsub_acl_chmod(a->h_inode, ia->ia_mode); if (!err) au_cpup_attr_changeable(inode); diff --git a/fs/aufs/module.c b/fs/aufs/module.c index ec12f2e66..8a28377c5 100644 --- a/fs/aufs/module.c +++ b/fs/aufs/module.c @@ -95,7 +95,7 @@ MODULE_PARM_DESC(brs, "use <sysfs>/fs/aufs/si_*/brN"); module_param_named(brs, sysaufs_brs, int, S_IRUGO); /* this module parameter has no meaning when USER_NS is disabled */ -static bool au_userns; +bool au_userns; MODULE_PARM_DESC(allow_userns, "allow unprivileged to mount under userns"); module_param_named(allow_userns, au_userns, bool, S_IRUGO); diff --git a/fs/aufs/module.h b/fs/aufs/module.h index b129ad4b6..bb8644730 100644 --- a/fs/aufs/module.h +++ b/fs/aufs/module.h @@ -18,6 +18,7 @@ struct seq_file; /* module parameters */ extern int sysaufs_brs; +extern bool au_userns; /* ---------------------------------------------------------------------- */ diff --git a/fs/aufs/posix_acl.c b/fs/aufs/posix_acl.c index 1c19e629b..a3c442c08 100644 --- a/fs/aufs/posix_acl.c +++ b/fs/aufs/posix_acl.c @@ -7,7 +7,6 @@ */ #include <linux/fs.h> -#include <linux/posix_acl.h> #include "aufs.h" struct posix_acl *aufs_get_acl(struct inode *inode, int type) diff --git a/fs/aufs/vfsub.c b/fs/aufs/vfsub.c index f072c59c0..89f999c97 100644 --- a/fs/aufs/vfsub.c +++ b/fs/aufs/vfsub.c @@ -7,10 +7,28 @@ */ #include <linux/namei.h> +#include <linux/nsproxy.h> #include <linux/security.h> #include <linux/splice.h> +#include "../fs/mount.h" #include "aufs.h" +#ifdef CONFIG_AUFS_BR_FUSE +int vfsub_test_mntns(struct vfsmount *mnt, struct super_block *h_sb) +{ + struct nsproxy *ns; + + if (!au_test_fuse(h_sb) || !au_userns) + return 0; + + ns = current->nsproxy; + /* no {get,put}_nsproxy(ns) */ + return real_mount(mnt)->mnt_ns == ns->mnt_ns ? 0 : -EACCES; +} +#endif + +/* ---------------------------------------------------------------------- */ + int vfsub_update_h_iattr(struct path *h_path, int *did) { int err; diff --git a/fs/aufs/vfsub.h b/fs/aufs/vfsub.h index a7d8a1cf9..f2e1c49af 100644 --- a/fs/aufs/vfsub.h +++ b/fs/aufs/vfsub.h @@ -13,6 +13,7 @@ #include <linux/fs.h> #include <linux/mount.h> +#include <linux/posix_acl.h> #include <linux/xattr.h> #include "debug.h" @@ -63,6 +64,12 @@ static inline int vfsub_native_ro(struct inode *inode) || IS_IMMUTABLE(inode); } +#ifdef CONFIG_AUFS_BR_FUSE +int vfsub_test_mntns(struct vfsmount *mnt, struct super_block *h_sb); +#else +AuStubInt0(vfsub_test_mntns, struct vfsmount *mnt, struct super_block *h_sb); +#endif + /* ---------------------------------------------------------------------- */ int vfsub_update_h_iattr(struct path *h_path, int *did); @@ -202,6 +209,20 @@ static inline int vfsub_update_time(struct inode *h_inode, struct timespec *ts, /* no vfsub_update_h_iattr() since we don't have struct path */ } +#ifdef CONFIG_FS_POSIX_ACL +static inline int vfsub_acl_chmod(struct inode *h_inode, umode_t h_mode) +{ + int err; + + err = posix_acl_chmod(h_inode, h_mode); + if (err == -EOPNOTSUPP) + err = 0; + return err; +} +#else +AuStubInt0(vfsub_acl_chmod, struct inode *h_inode, umode_t h_mode); +#endif + long vfsub_splice_to(struct file *in, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags); diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index d453d62ab..e2f659dc5 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -1417,7 +1417,8 @@ char *btrfs_ref_to_path(struct btrfs_root *fs_root, struct btrfs_path *path, read_extent_buffer(eb, dest + bytes_left, name_off, name_len); if (eb != eb_in) { - btrfs_tree_read_unlock_blocking(eb); + if (!path->skip_locking) + btrfs_tree_read_unlock_blocking(eb); free_extent_buffer(eb); } ret = btrfs_find_item(fs_root, path, parent, 0, @@ -1437,9 +1438,10 @@ char *btrfs_ref_to_path(struct btrfs_root *fs_root, struct btrfs_path *path, eb = path->nodes[0]; /* make sure we can use eb after releasing the path */ if (eb != eb_in) { - atomic_inc(&eb->refs); - btrfs_tree_read_lock(eb); - btrfs_set_lock_blocking_rw(eb, BTRFS_READ_LOCK); + if (!path->skip_locking) + btrfs_set_lock_blocking_rw(eb, BTRFS_READ_LOCK); + path->nodes[0] = NULL; + path->locks[0] = 0; } btrfs_release_path(path); iref = btrfs_item_ptr(eb, slot, struct btrfs_inode_ref); diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c index e0941fbb9..02b934d0e 100644 --- a/fs/btrfs/delayed-inode.c +++ b/fs/btrfs/delayed-inode.c @@ -1694,7 +1694,7 @@ int btrfs_should_delete_dir_index(struct list_head *del_list, * */ int btrfs_readdir_delayed_dir_index(struct dir_context *ctx, - struct list_head *ins_list) + struct list_head *ins_list, bool *emitted) { struct btrfs_dir_item *di; struct btrfs_delayed_item *curr, *next; @@ -1738,6 +1738,7 @@ int btrfs_readdir_delayed_dir_index(struct dir_context *ctx, if (over) return 1; + *emitted = true; } return 0; } diff --git a/fs/btrfs/delayed-inode.h b/fs/btrfs/delayed-inode.h index f70119f25..0167853c8 100644 --- a/fs/btrfs/delayed-inode.h +++ b/fs/btrfs/delayed-inode.h @@ -144,7 +144,7 @@ void btrfs_put_delayed_items(struct list_head *ins_list, int btrfs_should_delete_dir_index(struct list_head *del_list, u64 index); int btrfs_readdir_delayed_dir_index(struct dir_context *ctx, - struct list_head *ins_list); + struct list_head *ins_list, bool *emitted); /* for init */ int __init btrfs_delayed_inode_init(void); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index a70c5790f..54b5f0de6 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -5741,6 +5741,7 @@ static int btrfs_real_readdir(struct file *file, struct dir_context *ctx) char *name_ptr; int name_len; int is_curr = 0; /* ctx->pos points to the current index? */ + bool emitted; /* FIXME, use a real flag for deciding about the key type */ if (root->fs_info->tree_root == root) @@ -5769,6 +5770,7 @@ static int btrfs_real_readdir(struct file *file, struct dir_context *ctx) if (ret < 0) goto err; + emitted = false; while (1) { leaf = path->nodes[0]; slot = path->slots[0]; @@ -5848,6 +5850,7 @@ skip: if (over) goto nopos; + emitted = true; di_len = btrfs_dir_name_len(leaf, di) + btrfs_dir_data_len(leaf, di) + sizeof(*di); di_cur += di_len; @@ -5860,11 +5863,20 @@ next: if (key_type == BTRFS_DIR_INDEX_KEY) { if (is_curr) ctx->pos++; - ret = btrfs_readdir_delayed_dir_index(ctx, &ins_list); + ret = btrfs_readdir_delayed_dir_index(ctx, &ins_list, &emitted); if (ret) goto nopos; } + /* + * If we haven't emitted any dir entry, we must not touch ctx->pos as + * it was was set to the termination value in previous call. We assume + * that "." and ".." were emitted if we reach this point and set the + * termination value as well for an empty directory. + */ + if (ctx->pos > 2 && !emitted) + goto nopos; + /* Reached end of directory/root. Bump pos past the last item. */ ctx->pos++; @@ -7985,6 +7997,7 @@ static void btrfs_endio_direct_read(struct bio *bio) kfree(dip); + dio_bio->bi_error = bio->bi_error; dio_end_io(dio_bio, bio->bi_error); if (io_bio->end_io) @@ -8030,6 +8043,7 @@ out_test: kfree(dip); + dio_bio->bi_error = bio->bi_error; dio_end_io(dio_bio, bio->bi_error); bio_put(bio); } diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index da94138eb..08fd3f0f3 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -2782,24 +2782,29 @@ out: static struct page *extent_same_get_page(struct inode *inode, pgoff_t index) { struct page *page; - struct extent_io_tree *tree = &BTRFS_I(inode)->io_tree; page = grab_cache_page(inode->i_mapping, index); if (!page) - return NULL; + return ERR_PTR(-ENOMEM); if (!PageUptodate(page)) { - if (extent_read_full_page_nolock(tree, page, btrfs_get_extent, - 0)) - return NULL; + int ret; + + ret = btrfs_readpage(NULL, page); + if (ret) + return ERR_PTR(ret); lock_page(page); if (!PageUptodate(page)) { unlock_page(page); page_cache_release(page); - return NULL; + return ERR_PTR(-EIO); + } + if (page->mapping != inode->i_mapping) { + unlock_page(page); + page_cache_release(page); + return ERR_PTR(-EAGAIN); } } - unlock_page(page); return page; } @@ -2811,17 +2816,31 @@ static int gather_extent_pages(struct inode *inode, struct page **pages, pgoff_t index = off >> PAGE_CACHE_SHIFT; for (i = 0; i < num_pages; i++) { +again: pages[i] = extent_same_get_page(inode, index + i); - if (!pages[i]) - return -ENOMEM; + if (IS_ERR(pages[i])) { + int err = PTR_ERR(pages[i]); + + if (err == -EAGAIN) + goto again; + pages[i] = NULL; + return err; + } } return 0; } -static inline void lock_extent_range(struct inode *inode, u64 off, u64 len) +static int lock_extent_range(struct inode *inode, u64 off, u64 len, + bool retry_range_locking) { - /* do any pending delalloc/csum calc on src, one way or - another, and lock file content */ + /* + * Do any pending delalloc/csum calculations on inode, one way or + * another, and lock file content. + * The locking order is: + * + * 1) pages + * 2) range in the inode's io tree + */ while (1) { struct btrfs_ordered_extent *ordered; lock_extent(&BTRFS_I(inode)->io_tree, off, off + len - 1); @@ -2839,8 +2858,11 @@ static inline void lock_extent_range(struct inode *inode, u64 off, u64 len) unlock_extent(&BTRFS_I(inode)->io_tree, off, off + len - 1); if (ordered) btrfs_put_ordered_extent(ordered); + if (!retry_range_locking) + return -EAGAIN; btrfs_wait_ordered_range(inode, off, len); } + return 0; } static void btrfs_double_inode_unlock(struct inode *inode1, struct inode *inode2) @@ -2865,15 +2887,24 @@ static void btrfs_double_extent_unlock(struct inode *inode1, u64 loff1, unlock_extent(&BTRFS_I(inode2)->io_tree, loff2, loff2 + len - 1); } -static void btrfs_double_extent_lock(struct inode *inode1, u64 loff1, - struct inode *inode2, u64 loff2, u64 len) +static int btrfs_double_extent_lock(struct inode *inode1, u64 loff1, + struct inode *inode2, u64 loff2, u64 len, + bool retry_range_locking) { + int ret; + if (inode1 < inode2) { swap(inode1, inode2); swap(loff1, loff2); } - lock_extent_range(inode1, loff1, len); - lock_extent_range(inode2, loff2, len); + ret = lock_extent_range(inode1, loff1, len, retry_range_locking); + if (ret) + return ret; + ret = lock_extent_range(inode2, loff2, len, retry_range_locking); + if (ret) + unlock_extent(&BTRFS_I(inode1)->io_tree, loff1, + loff1 + len - 1); + return ret; } struct cmp_pages { @@ -2889,11 +2920,15 @@ static void btrfs_cmp_data_free(struct cmp_pages *cmp) for (i = 0; i < cmp->num_pages; i++) { pg = cmp->src_pages[i]; - if (pg) + if (pg) { + unlock_page(pg); page_cache_release(pg); + } pg = cmp->dst_pages[i]; - if (pg) + if (pg) { + unlock_page(pg); page_cache_release(pg); + } } kfree(cmp->src_pages); kfree(cmp->dst_pages); @@ -2954,6 +2989,8 @@ static int btrfs_cmp_data(struct inode *src, u64 loff, struct inode *dst, src_page = cmp->src_pages[i]; dst_page = cmp->dst_pages[i]; + ASSERT(PageLocked(src_page)); + ASSERT(PageLocked(dst_page)); addr = kmap_atomic(src_page); dst_addr = kmap_atomic(dst_page); @@ -3066,14 +3103,46 @@ static int btrfs_extent_same(struct inode *src, u64 loff, u64 olen, goto out_unlock; } +again: ret = btrfs_cmp_data_prepare(src, loff, dst, dst_loff, olen, &cmp); if (ret) goto out_unlock; if (same_inode) - lock_extent_range(src, same_lock_start, same_lock_len); + ret = lock_extent_range(src, same_lock_start, same_lock_len, + false); else - btrfs_double_extent_lock(src, loff, dst, dst_loff, len); + ret = btrfs_double_extent_lock(src, loff, dst, dst_loff, len, + false); + /* + * If one of the inodes has dirty pages in the respective range or + * ordered extents, we need to flush dellaloc and wait for all ordered + * extents in the range. We must unlock the pages and the ranges in the + * io trees to avoid deadlocks when flushing delalloc (requires locking + * pages) and when waiting for ordered extents to complete (they require + * range locking). + */ + if (ret == -EAGAIN) { + /* + * Ranges in the io trees already unlocked. Now unlock all + * pages before waiting for all IO to complete. + */ + btrfs_cmp_data_free(&cmp); + if (same_inode) { + btrfs_wait_ordered_range(src, same_lock_start, + same_lock_len); + } else { + btrfs_wait_ordered_range(src, loff, len); + btrfs_wait_ordered_range(dst, dst_loff, len); + } + goto again; + } + ASSERT(ret == 0); + if (WARN_ON(ret)) { + /* ranges in the io trees already unlocked */ + btrfs_cmp_data_free(&cmp); + return ret; + } /* pass original length for comparison so we stay within i_size */ ret = btrfs_cmp_data(src, loff, dst, dst_loff, olen, &cmp); @@ -3895,9 +3964,15 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd, u64 lock_start = min_t(u64, off, destoff); u64 lock_len = max_t(u64, off, destoff) + len - lock_start; - lock_extent_range(src, lock_start, lock_len); + ret = lock_extent_range(src, lock_start, lock_len, true); } else { - btrfs_double_extent_lock(src, off, inode, destoff, len); + ret = btrfs_double_extent_lock(src, off, inode, destoff, len, + true); + } + ASSERT(ret == 0); + if (WARN_ON(ret)) { + /* ranges in the io trees already unlocked */ + goto out_unlock; } ret = btrfs_clone(src, inode, off, olen, len, destoff, 0); diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index a23399e8e..9e084477d 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -1257,6 +1257,15 @@ int find_free_dev_extent_start(struct btrfs_transaction *transaction, int ret; int slot; struct extent_buffer *l; + u64 min_search_start; + + /* + * We don't want to overwrite the superblock on the drive nor any area + * used by the boot loader (grub for example), so we make sure to start + * at an offset of at least 1MB. + */ + min_search_start = max(root->fs_info->alloc_start, 1024ull * 1024); + search_start = max(search_start, min_search_start); path = btrfs_alloc_path(); if (!path) @@ -1397,18 +1406,9 @@ int find_free_dev_extent(struct btrfs_trans_handle *trans, struct btrfs_device *device, u64 num_bytes, u64 *start, u64 *len) { - struct btrfs_root *root = device->dev_root; - u64 search_start; - /* FIXME use last free of some kind */ - - /* - * we don't want to overwrite the superblock on the drive, - * so we make sure to start at an offset of at least 1MB - */ - search_start = max(root->fs_info->alloc_start, 1024ull * 1024); return find_free_dev_extent_start(trans->transaction, device, - num_bytes, search_start, start, len); + num_bytes, 0, start, len); } static int btrfs_free_dev_extent(struct btrfs_trans_handle *trans, @@ -6512,6 +6512,14 @@ int btrfs_read_sys_array(struct btrfs_root *root) goto out_short_read; num_stripes = btrfs_chunk_num_stripes(sb, chunk); + if (!num_stripes) { + printk(KERN_ERR + "BTRFS: invalid number of stripes %u in sys_array at offset %u\n", + num_stripes, cur_offset); + ret = -EIO; + break; + } + len = btrfs_chunk_item_size(num_stripes); if (cur_offset + len > array_size) goto out_short_read; diff --git a/fs/cifs/cifs_debug.c b/fs/cifs/cifs_debug.c index 7febcf247..50b268483 100644 --- a/fs/cifs/cifs_debug.c +++ b/fs/cifs/cifs_debug.c @@ -50,7 +50,7 @@ void cifs_vfs_err(const char *fmt, ...) vaf.fmt = fmt; vaf.va = &args; - pr_err("CIFS VFS: %pV", &vaf); + pr_err_ratelimited("CIFS VFS: %pV", &vaf); va_end(args); } diff --git a/fs/cifs/cifs_debug.h b/fs/cifs/cifs_debug.h index f40fbaca1..66cf0f9ff 100644 --- a/fs/cifs/cifs_debug.h +++ b/fs/cifs/cifs_debug.h @@ -51,14 +51,13 @@ __printf(1, 2) void cifs_vfs_err(const char *fmt, ...); /* information message: e.g., configuration, major event */ #define cifs_dbg(type, fmt, ...) \ do { \ - if (type == FYI) { \ - if (cifsFYI & CIFS_INFO) { \ - pr_debug("%s: " fmt, __FILE__, ##__VA_ARGS__); \ - } \ + if (type == FYI && cifsFYI & CIFS_INFO) { \ + pr_debug_ratelimited("%s: " \ + fmt, __FILE__, ##__VA_ARGS__); \ } else if (type == VFS) { \ cifs_vfs_err(fmt, ##__VA_ARGS__); \ } else if (type == NOISY && type != 0) { \ - pr_debug(fmt, ##__VA_ARGS__); \ + pr_debug_ratelimited(fmt, ##__VA_ARGS__); \ } \ } while (0) diff --git a/fs/cifs/cifsencrypt.c b/fs/cifs/cifsencrypt.c index afa09fce8..e682b36a2 100644 --- a/fs/cifs/cifsencrypt.c +++ b/fs/cifs/cifsencrypt.c @@ -714,7 +714,7 @@ setup_ntlmv2_rsp(struct cifs_ses *ses, const struct nls_table *nls_cp) ses->auth_key.response = kmalloc(baselen + tilen, GFP_KERNEL); if (!ses->auth_key.response) { - rc = ENOMEM; + rc = -ENOMEM; ses->auth_key.len = 0; goto setup_ntlmv2_rsp_ret; } diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index ecb0803bd..3c194ff0d 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -368,7 +368,6 @@ cifs_reconnect(struct TCP_Server_Info *server) server->session_key.response = NULL; server->session_key.len = 0; server->lstrp = jiffies; - mutex_unlock(&server->srv_mutex); /* mark submitted MIDs for retry and issue callback */ INIT_LIST_HEAD(&retry_list); @@ -381,6 +380,7 @@ cifs_reconnect(struct TCP_Server_Info *server) list_move(&mid_entry->qhead, &retry_list); } spin_unlock(&GlobalMid_Lock); + mutex_unlock(&server->srv_mutex); cifs_dbg(FYI, "%s: issuing mid callbacks\n", __func__); list_for_each_safe(tmp, tmp2, &retry_list) { diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c index 0557c45e9..b30a4a6d9 100644 --- a/fs/cifs/readdir.c +++ b/fs/cifs/readdir.c @@ -847,6 +847,7 @@ int cifs_readdir(struct file *file, struct dir_context *ctx) * if buggy server returns . and .. late do we want to * check for that here? */ + *tmp_buf = 0; rc = cifs_filldir(current_entry, file, ctx, tmp_buf, max_len); if (rc) { diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c index 2a24c524f..87abe8ed0 100644 --- a/fs/cifs/transport.c +++ b/fs/cifs/transport.c @@ -576,14 +576,16 @@ cifs_call_async(struct TCP_Server_Info *server, struct smb_rqst *rqst, cifs_in_send_dec(server); cifs_save_when_sent(mid); - if (rc < 0) + if (rc < 0) { server->sequence_number -= 2; + cifs_delete_mid(mid); + } + mutex_unlock(&server->srv_mutex); if (rc == 0) return 0; - cifs_delete_mid(mid); add_credits_and_wake_if(server, credits, optype); return rc; } diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c index c35ffdc12..706de324f 100644 --- a/fs/devpts/inode.c +++ b/fs/devpts/inode.c @@ -575,6 +575,26 @@ void devpts_kill_index(struct inode *ptmx_inode, int idx) mutex_unlock(&allocated_ptys_lock); } +/* + * pty code needs to hold extra references in case of last /dev/tty close + */ + +void devpts_add_ref(struct inode *ptmx_inode) +{ + struct super_block *sb = pts_sb_from_inode(ptmx_inode); + + atomic_inc(&sb->s_active); + ihold(ptmx_inode); +} + +void devpts_del_ref(struct inode *ptmx_inode) +{ + struct super_block *sb = pts_sb_from_inode(ptmx_inode); + + iput(ptmx_inode); + deactivate_super(sb); +} + /** * devpts_pty_new -- create a new inode in /dev/pts/ * @ptmx_inode: inode of the master diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index ec0668a60..fe1f50fe7 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -191,7 +191,6 @@ static int ext4_init_block_bitmap(struct super_block *sb, /* If checksum is bad mark all blocks used to prevent allocation * essentially implementing a per-group read-only flag. */ if (!ext4_group_desc_csum_verify(sb, block_group, gdp)) { - ext4_error(sb, "Checksum bad for group %u", block_group); grp = ext4_get_group_info(sb, block_group); if (!EXT4_MB_GRP_BBITMAP_CORRUPT(grp)) percpu_counter_sub(&sbi->s_freeclusters_counter, @@ -442,14 +441,16 @@ ext4_read_block_bitmap_nowait(struct super_block *sb, ext4_group_t block_group) } ext4_lock_group(sb, block_group); if (desc->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) { - err = ext4_init_block_bitmap(sb, bh, block_group, desc); set_bitmap_uptodate(bh); set_buffer_uptodate(bh); ext4_unlock_group(sb, block_group); unlock_buffer(bh); - if (err) + if (err) { + ext4_error(sb, "Failed to init block bitmap for group " + "%u: %d", block_group, err); goto out; + } goto verify; } ext4_unlock_group(sb, block_group); diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index 1b8024d26..53f2b98a6 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -76,7 +76,6 @@ static int ext4_init_inode_bitmap(struct super_block *sb, /* If checksum is bad mark all blocks and inodes use to prevent * allocation, essentially implementing a per-group read-only flag. */ if (!ext4_group_desc_csum_verify(sb, block_group, gdp)) { - ext4_error(sb, "Checksum bad for group %u", block_group); grp = ext4_get_group_info(sb, block_group); if (!EXT4_MB_GRP_BBITMAP_CORRUPT(grp)) percpu_counter_sub(&sbi->s_freeclusters_counter, @@ -191,8 +190,11 @@ ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group) set_buffer_verified(bh); ext4_unlock_group(sb, block_group); unlock_buffer(bh); - if (err) + if (err) { + ext4_error(sb, "Failed to init inode bitmap for group " + "%u: %d", block_group, err); goto out; + } return bh; } ext4_unlock_group(sb, block_group); diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c index fb6f11709..e032a0423 100644 --- a/fs/ext4/move_extent.c +++ b/fs/ext4/move_extent.c @@ -265,11 +265,12 @@ move_extent_per_page(struct file *o_filp, struct inode *donor_inode, ext4_lblk_t orig_blk_offset, donor_blk_offset; unsigned long blocksize = orig_inode->i_sb->s_blocksize; unsigned int tmp_data_size, data_size, replaced_size; - int err2, jblocks, retries = 0; + int i, err2, jblocks, retries = 0; int replaced_count = 0; int from = data_offset_in_page << orig_inode->i_blkbits; int blocks_per_page = PAGE_CACHE_SIZE >> orig_inode->i_blkbits; struct super_block *sb = orig_inode->i_sb; + struct buffer_head *bh = NULL; /* * It needs twice the amount of ordinary journal buffers because @@ -380,8 +381,16 @@ data_copy: } /* Perform all necessary steps similar write_begin()/write_end() * but keeping in mind that i_size will not change */ - *err = __block_write_begin(pagep[0], from, replaced_size, - ext4_get_block); + if (!page_has_buffers(pagep[0])) + create_empty_buffers(pagep[0], 1 << orig_inode->i_blkbits, 0); + bh = page_buffers(pagep[0]); + for (i = 0; i < data_offset_in_page; i++) + bh = bh->b_this_page; + for (i = 0; i < block_len_in_page; i++) { + *err = ext4_get_block(orig_inode, orig_blk_offset + i, bh, 0); + if (*err < 0) + break; + } if (!*err) *err = block_commit_write(pagep[0], from, from + replaced_size); diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index ad62d7acc..34038e359 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -198,7 +198,7 @@ static struct ext4_new_flex_group_data *alloc_flex_gd(unsigned long flexbg_size) if (flex_gd == NULL) goto out3; - if (flexbg_size >= UINT_MAX / sizeof(struct ext4_new_flex_group_data)) + if (flexbg_size >= UINT_MAX / sizeof(struct ext4_new_group_data)) goto out2; flex_gd->count = flexbg_size; diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index de4bdfac0..595ebdb41 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -463,6 +463,7 @@ hugetlb_vmdelete_list(struct rb_root *root, pgoff_t start, pgoff_t end) */ vma_interval_tree_foreach(vma, root, start, end ? end : ULONG_MAX) { unsigned long v_offset; + unsigned long v_end; /* * Can the expression below overflow on 32-bit arches? @@ -475,15 +476,17 @@ hugetlb_vmdelete_list(struct rb_root *root, pgoff_t start, pgoff_t end) else v_offset = 0; - if (end) { - end = ((end - start) << PAGE_SHIFT) + - vma->vm_start + v_offset; - if (end > vma->vm_end) - end = vma->vm_end; - } else - end = vma->vm_end; + if (!end) + v_end = vma->vm_end; + else { + v_end = ((end - vma->vm_pgoff) << PAGE_SHIFT) + + vma->vm_start; + if (v_end > vma->vm_end) + v_end = vma->vm_end; + } - unmap_hugepage_range(vma, vma->vm_start + v_offset, end, NULL); + unmap_hugepage_range(vma, vma->vm_start + v_offset, v_end, + NULL); } } diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c index 03516c808..2a2e2d8dd 100644 --- a/fs/nfs/flexfilelayout/flexfilelayout.c +++ b/fs/nfs/flexfilelayout/flexfilelayout.c @@ -145,7 +145,7 @@ static bool ff_mirror_match_fh(const struct nfs4_ff_layout_mirror *m1, return false; for (i = 0; i < m1->fh_versions_cnt; i++) { bool found_fh = false; - for (j = 0; j < m2->fh_versions_cnt; i++) { + for (j = 0; j < m2->fh_versions_cnt; j++) { if (nfs_compare_fh(&m1->fh_versions[i], &m2->fh_versions[j]) == 0) { found_fh = true; @@ -1859,11 +1859,9 @@ ff_layout_encode_layoutreturn(struct pnfs_layout_hdr *lo, start = xdr_reserve_space(xdr, 4); BUG_ON(!start); - if (ff_layout_encode_ioerr(flo, xdr, args)) - goto out; - + ff_layout_encode_ioerr(flo, xdr, args); ff_layout_encode_iostats(flo, xdr, args); -out: + *start = cpu_to_be32((xdr->p - start - 1) * 4); dprintk("%s: Return\n", __func__); } diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index c7e8b87da..3e2071a17 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -1641,6 +1641,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) unsigned long invalid = 0; unsigned long now = jiffies; unsigned long save_cache_validity; + bool cache_revalidated = true; dfprintk(VFS, "NFS: %s(%s/%lu fh_crc=0x%08x ct=%d info=0x%x)\n", __func__, inode->i_sb->s_id, inode->i_ino, @@ -1702,22 +1703,28 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) nfs_force_lookup_revalidate(inode); inode->i_version = fattr->change_attr; } - } else + } else { nfsi->cache_validity |= save_cache_validity; + cache_revalidated = false; + } if (fattr->valid & NFS_ATTR_FATTR_MTIME) { memcpy(&inode->i_mtime, &fattr->mtime, sizeof(inode->i_mtime)); - } else if (server->caps & NFS_CAP_MTIME) + } else if (server->caps & NFS_CAP_MTIME) { nfsi->cache_validity |= save_cache_validity & (NFS_INO_INVALID_ATTR | NFS_INO_REVAL_FORCED); + cache_revalidated = false; + } if (fattr->valid & NFS_ATTR_FATTR_CTIME) { memcpy(&inode->i_ctime, &fattr->ctime, sizeof(inode->i_ctime)); - } else if (server->caps & NFS_CAP_CTIME) + } else if (server->caps & NFS_CAP_CTIME) { nfsi->cache_validity |= save_cache_validity & (NFS_INO_INVALID_ATTR | NFS_INO_REVAL_FORCED); + cache_revalidated = false; + } /* Check if our cached file size is stale */ if (fattr->valid & NFS_ATTR_FATTR_SIZE) { @@ -1737,19 +1744,23 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) (long long)cur_isize, (long long)new_isize); } - } else + } else { nfsi->cache_validity |= save_cache_validity & (NFS_INO_INVALID_ATTR | NFS_INO_REVAL_PAGECACHE | NFS_INO_REVAL_FORCED); + cache_revalidated = false; + } if (fattr->valid & NFS_ATTR_FATTR_ATIME) memcpy(&inode->i_atime, &fattr->atime, sizeof(inode->i_atime)); - else if (server->caps & NFS_CAP_ATIME) + else if (server->caps & NFS_CAP_ATIME) { nfsi->cache_validity |= save_cache_validity & (NFS_INO_INVALID_ATIME | NFS_INO_REVAL_FORCED); + cache_revalidated = false; + } if (fattr->valid & NFS_ATTR_FATTR_MODE) { if ((inode->i_mode & S_IALLUGO) != (fattr->mode & S_IALLUGO)) { @@ -1758,36 +1769,42 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) inode->i_mode = newmode; invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL; } - } else if (server->caps & NFS_CAP_MODE) + } else if (server->caps & NFS_CAP_MODE) { nfsi->cache_validity |= save_cache_validity & (NFS_INO_INVALID_ATTR | NFS_INO_INVALID_ACCESS | NFS_INO_INVALID_ACL | NFS_INO_REVAL_FORCED); + cache_revalidated = false; + } if (fattr->valid & NFS_ATTR_FATTR_OWNER) { if (!uid_eq(inode->i_uid, fattr->uid)) { invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL; inode->i_uid = fattr->uid; } - } else if (server->caps & NFS_CAP_OWNER) + } else if (server->caps & NFS_CAP_OWNER) { nfsi->cache_validity |= save_cache_validity & (NFS_INO_INVALID_ATTR | NFS_INO_INVALID_ACCESS | NFS_INO_INVALID_ACL | NFS_INO_REVAL_FORCED); + cache_revalidated = false; + } if (fattr->valid & NFS_ATTR_FATTR_GROUP) { if (!gid_eq(inode->i_gid, fattr->gid)) { invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL; inode->i_gid = fattr->gid; } - } else if (server->caps & NFS_CAP_OWNER_GROUP) + } else if (server->caps & NFS_CAP_OWNER_GROUP) { nfsi->cache_validity |= save_cache_validity & (NFS_INO_INVALID_ATTR | NFS_INO_INVALID_ACCESS | NFS_INO_INVALID_ACL | NFS_INO_REVAL_FORCED); + cache_revalidated = false; + } if (fattr->valid & NFS_ATTR_FATTR_NLINK) { if (inode->i_nlink != fattr->nlink) { @@ -1796,19 +1813,22 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) invalid |= NFS_INO_INVALID_DATA; set_nlink(inode, fattr->nlink); } - } else if (server->caps & NFS_CAP_NLINK) + } else if (server->caps & NFS_CAP_NLINK) { nfsi->cache_validity |= save_cache_validity & (NFS_INO_INVALID_ATTR | NFS_INO_REVAL_FORCED); + cache_revalidated = false; + } if (fattr->valid & NFS_ATTR_FATTR_SPACE_USED) { /* * report the blocks in 512byte units */ inode->i_blocks = nfs_calc_block_size(fattr->du.nfs3.used); - } - if (fattr->valid & NFS_ATTR_FATTR_BLOCKS_USED) + } else if (fattr->valid & NFS_ATTR_FATTR_BLOCKS_USED) inode->i_blocks = fattr->du.nfs2.blocks; + else + cache_revalidated = false; /* Update attrtimeo value if we're out of the unstable period */ if (invalid & NFS_INO_INVALID_ATTR) { @@ -1818,9 +1838,13 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) /* Set barrier to be more recent than all outstanding updates */ nfsi->attr_gencount = nfs_inc_attr_generation_counter(); } else { - if (!time_in_range_open(now, nfsi->attrtimeo_timestamp, nfsi->attrtimeo_timestamp + nfsi->attrtimeo)) { - if ((nfsi->attrtimeo <<= 1) > NFS_MAXATTRTIMEO(inode)) - nfsi->attrtimeo = NFS_MAXATTRTIMEO(inode); + if (cache_revalidated) { + if (!time_in_range_open(now, nfsi->attrtimeo_timestamp, + nfsi->attrtimeo_timestamp + nfsi->attrtimeo)) { + nfsi->attrtimeo <<= 1; + if (nfsi->attrtimeo > NFS_MAXATTRTIMEO(inode)) + nfsi->attrtimeo = NFS_MAXATTRTIMEO(inode); + } nfsi->attrtimeo_timestamp = now; } /* Set the barrier to be more recent than this fattr */ @@ -1829,7 +1853,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) } /* Don't declare attrcache up to date if there were no attrs! */ - if (fattr->valid != 0) + if (cache_revalidated) invalid &= ~NFS_INO_INVALID_ATTR; /* Don't invalidate the data if we were to blame */ diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 343b0f1f1..f496ed721 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -1385,6 +1385,7 @@ static void __update_open_stateid(struct nfs4_state *state, nfs4_stateid *open_s * Protect the call to nfs4_state_set_mode_locked and * serialise the stateid update */ + spin_lock(&state->owner->so_lock); write_seqlock(&state->seqlock); if (deleg_stateid != NULL) { nfs4_stateid_copy(&state->stateid, deleg_stateid); @@ -1393,7 +1394,6 @@ static void __update_open_stateid(struct nfs4_state *state, nfs4_stateid *open_s if (open_stateid != NULL) nfs_set_open_stateid_locked(state, open_stateid, fmode); write_sequnlock(&state->seqlock); - spin_lock(&state->owner->so_lock); update_open_stateflags(state, fmode); spin_unlock(&state->owner->so_lock); } diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c index 0a8983492..eff6319d5 100644 --- a/fs/overlayfs/copy_up.c +++ b/fs/overlayfs/copy_up.c @@ -22,9 +22,9 @@ int ovl_copy_xattr(struct dentry *old, struct dentry *new) { - ssize_t list_size, size; - char *buf, *name, *value; - int error; + ssize_t list_size, size, value_size = 0; + char *buf, *name, *value = NULL; + int uninitialized_var(error); if (!old->d_inode->i_op->getxattr || !new->d_inode->i_op->getxattr) @@ -41,29 +41,40 @@ int ovl_copy_xattr(struct dentry *old, struct dentry *new) if (!buf) return -ENOMEM; - error = -ENOMEM; - value = kmalloc(XATTR_SIZE_MAX, GFP_KERNEL); - if (!value) - goto out; - list_size = vfs_listxattr(old, buf, list_size); if (list_size <= 0) { error = list_size; - goto out_free_value; + goto out; } for (name = buf; name < (buf + list_size); name += strlen(name) + 1) { - size = vfs_getxattr(old, name, value, XATTR_SIZE_MAX); - if (size <= 0) { +retry: + size = vfs_getxattr(old, name, value, value_size); + if (size == -ERANGE) + size = vfs_getxattr(old, name, NULL, 0); + + if (size < 0) { error = size; - goto out_free_value; + break; + } + + if (size > value_size) { + void *new; + + new = krealloc(value, size, GFP_KERNEL); + if (!new) { + error = -ENOMEM; + break; + } + value = new; + value_size = size; + goto retry; } + error = vfs_setxattr(new, name, value, size, 0); if (error) - goto out_free_value; + break; } - -out_free_value: kfree(value); out: kfree(buf); diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c index 4060ffde8..b29036aa8 100644 --- a/fs/overlayfs/inode.c +++ b/fs/overlayfs/inode.c @@ -42,6 +42,19 @@ int ovl_setattr(struct dentry *dentry, struct iattr *attr) int err; struct dentry *upperdentry; + /* + * Check for permissions before trying to copy-up. This is redundant + * since it will be rechecked later by ->setattr() on upper dentry. But + * without this, copy-up can be triggered by just about anybody. + * + * We don't initialize inode->size, which just means that + * inode_newsize_ok() will always check against MAX_LFS_FILESIZE and not + * check for a swapfile (which this won't be anyway). + */ + err = inode_change_ok(dentry->d_inode, attr); + if (err) + return err; + err = ovl_want_write(dentry); if (err) goto out; diff --git a/fs/overlayfs/readdir.c b/fs/overlayfs/readdir.c index 70e9af551..adcb1398c 100644 --- a/fs/overlayfs/readdir.c +++ b/fs/overlayfs/readdir.c @@ -571,7 +571,8 @@ void ovl_cleanup_whiteouts(struct dentry *upper, struct list_head *list) (int) PTR_ERR(dentry)); continue; } - ovl_cleanup(upper->d_inode, dentry); + if (dentry->d_inode) + ovl_cleanup(upper->d_inode, dentry); dput(dentry); } mutex_unlock(&upper->d_inode->i_mutex); diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index e38ee0fed..f42c9407f 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -9,6 +9,7 @@ #include <linux/fs.h> #include <linux/namei.h> +#include <linux/pagemap.h> #include <linux/xattr.h> #include <linux/security.h> #include <linux/mount.h> @@ -910,6 +911,7 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent) } sb->s_stack_depth = 0; + sb->s_maxbytes = MAX_LFS_FILESIZE; if (ufs->config.upperdir) { if (!ufs->config.workdir) { pr_err("overlayfs: missing 'workdir'\n"); @@ -1053,6 +1055,9 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent) root_dentry->d_fsdata = oe; + ovl_copyattr(ovl_dentry_real(root_dentry)->d_inode, + root_dentry->d_inode); + sb->s_magic = OVERLAYFS_SUPER_MAGIC; sb->s_op = &ovl_super_operations; sb->s_root = root_dentry; diff --git a/fs/proc/array.c b/fs/proc/array.c index d73291f5f..b6c00ce0e 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -395,7 +395,7 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, state = *get_task_state(task); vsize = eip = esp = 0; - permitted = ptrace_may_access(task, PTRACE_MODE_READ | PTRACE_MODE_NOAUDIT); + permitted = ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS | PTRACE_MODE_NOAUDIT); mm = get_task_mm(task); if (mm) { vsize = task_vsize(mm); diff --git a/fs/proc/base.c b/fs/proc/base.c index aa41f2a7b..8be0e4cd2 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -403,7 +403,7 @@ static const struct file_operations proc_pid_cmdline_ops = { static int proc_pid_auxv(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task) { - struct mm_struct *mm = mm_access(task, PTRACE_MODE_READ); + struct mm_struct *mm = mm_access(task, PTRACE_MODE_READ_FSCREDS); if (mm && !IS_ERR(mm)) { unsigned int nwords = 0; do { @@ -430,7 +430,8 @@ static int proc_pid_wchan(struct seq_file *m, struct pid_namespace *ns, wchan = get_wchan(task); - if (wchan && ptrace_may_access(task, PTRACE_MODE_READ) && !lookup_symbol_name(wchan, symname)) + if (wchan && ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS) + && !lookup_symbol_name(wchan, symname)) seq_printf(m, "%s", symname); else seq_putc(m, '0'); @@ -444,7 +445,7 @@ static int lock_trace(struct task_struct *task) int err = mutex_lock_killable(&task->signal->cred_guard_mutex); if (err) return err; - if (!ptrace_may_access(task, PTRACE_MODE_ATTACH)) { + if (!ptrace_may_access(task, PTRACE_MODE_ATTACH_FSCREDS)) { mutex_unlock(&task->signal->cred_guard_mutex); return -EPERM; } @@ -697,7 +698,7 @@ static int proc_fd_access_allowed(struct inode *inode) */ task = get_proc_task(inode); if (task) { - allowed = ptrace_may_access(task, PTRACE_MODE_READ); + allowed = ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS); put_task_struct(task); } return allowed; @@ -732,7 +733,7 @@ static bool has_pid_permissions(struct pid_namespace *pid, return true; if (in_group_p(pid->pid_gid)) return true; - return ptrace_may_access(task, PTRACE_MODE_READ); + return ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS); } @@ -809,7 +810,7 @@ struct mm_struct *proc_mem_open(struct inode *inode, unsigned int mode) struct mm_struct *mm = ERR_PTR(-ESRCH); if (task) { - mm = mm_access(task, mode); + mm = mm_access(task, mode | PTRACE_MODE_FSCREDS); put_task_struct(task); if (!IS_ERR_OR_NULL(mm)) { @@ -1856,7 +1857,7 @@ static int map_files_d_revalidate(struct dentry *dentry, unsigned int flags) if (!task) goto out_notask; - mm = mm_access(task, PTRACE_MODE_READ); + mm = mm_access(task, PTRACE_MODE_READ_FSCREDS); if (IS_ERR_OR_NULL(mm)) goto out; @@ -2007,7 +2008,7 @@ static struct dentry *proc_map_files_lookup(struct inode *dir, goto out; result = -EACCES; - if (!ptrace_may_access(task, PTRACE_MODE_READ)) + if (!ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS)) goto out_put_task; result = -ENOENT; @@ -2060,7 +2061,7 @@ proc_map_files_readdir(struct file *file, struct dir_context *ctx) goto out; ret = -EACCES; - if (!ptrace_may_access(task, PTRACE_MODE_READ)) + if (!ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS)) goto out_put_task; ret = 0; @@ -2530,7 +2531,7 @@ static int do_io_accounting(struct task_struct *task, struct seq_file *m, int wh if (result) return result; - if (!ptrace_may_access(task, PTRACE_MODE_READ)) { + if (!ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS)) { result = -EACCES; goto out_unlock; } diff --git a/fs/proc/namespaces.c b/fs/proc/namespaces.c index f6e8354b8..1b0ea4a5d 100644 --- a/fs/proc/namespaces.c +++ b/fs/proc/namespaces.c @@ -42,7 +42,7 @@ static const char *proc_ns_follow_link(struct dentry *dentry, void **cookie) if (!task) return error; - if (ptrace_may_access(task, PTRACE_MODE_READ)) { + if (ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS)) { error = ns_get_path(&ns_path, task, ns_ops); if (!error) nd_jump_link(&ns_path); @@ -63,7 +63,7 @@ static int proc_ns_readlink(struct dentry *dentry, char __user *buffer, int bufl if (!task) return res; - if (ptrace_may_access(task, PTRACE_MODE_READ)) { + if (ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS)) { res = ns_get_name(name, sizeof(name), task, ns_ops); if (res >= 0) res = readlink_copy(buffer, buflen, name); diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index e03793e75..e4733feb0 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -1476,18 +1476,19 @@ static int gather_pte_stats(pmd_t *pmd, unsigned long addr, static int gather_hugetlb_stats(pte_t *pte, unsigned long hmask, unsigned long addr, unsigned long end, struct mm_walk *walk) { + pte_t huge_pte = huge_ptep_get(pte); struct numa_maps *md; struct page *page; - if (!pte_present(*pte)) + if (!pte_present(huge_pte)) return 0; - page = pte_page(*pte); + page = pte_page(huge_pte); if (!page) return 0; md = walk->private; - gather_stats(page, md, pte_dirty(*pte), 1); + gather_stats(page, md, pte_dirty(huge_pte), 1); return 0; } diff --git a/fs/timerfd.c b/fs/timerfd.c index b94fa6c3c..053818dd6 100644 --- a/fs/timerfd.c +++ b/fs/timerfd.c @@ -153,7 +153,7 @@ static ktime_t timerfd_get_remaining(struct timerfd_ctx *ctx) if (isalarm(ctx)) remaining = alarm_expires_remaining(&ctx->t.alarm); else - remaining = hrtimer_expires_remaining(&ctx->t.tmr); + remaining = hrtimer_expires_remaining_adjusted(&ctx->t.tmr); return remaining.tv64 < 0 ? ktime_set(0, 0): remaining; } diff --git a/fs/udf/inode.c b/fs/udf/inode.c index 8d0b3ade0..566df9b5a 100644 --- a/fs/udf/inode.c +++ b/fs/udf/inode.c @@ -2047,14 +2047,29 @@ void udf_write_aext(struct inode *inode, struct extent_position *epos, epos->offset += adsize; } +/* + * Only 1 indirect extent in a row really makes sense but allow upto 16 in case + * someone does some weird stuff. + */ +#define UDF_MAX_INDIR_EXTS 16 + int8_t udf_next_aext(struct inode *inode, struct extent_position *epos, struct kernel_lb_addr *eloc, uint32_t *elen, int inc) { int8_t etype; + unsigned int indirections = 0; while ((etype = udf_current_aext(inode, epos, eloc, elen, inc)) == (EXT_NEXT_EXTENT_ALLOCDECS >> 30)) { int block; + + if (++indirections > UDF_MAX_INDIR_EXTS) { + udf_err(inode->i_sb, + "too many indirect extents in inode %lu\n", + inode->i_ino); + return -1; + } + epos->block = *eloc; epos->offset = sizeof(struct allocExtDesc); brelse(epos->bh); diff --git a/fs/udf/unicode.c b/fs/udf/unicode.c index ab478e62b..e788a05aa 100644 --- a/fs/udf/unicode.c +++ b/fs/udf/unicode.c @@ -128,11 +128,15 @@ int udf_CS0toUTF8(struct ustr *utf_o, const struct ustr *ocu_i) if (c < 0x80U) utf_o->u_name[utf_o->u_len++] = (uint8_t)c; else if (c < 0x800U) { + if (utf_o->u_len > (UDF_NAME_LEN - 4)) + break; utf_o->u_name[utf_o->u_len++] = (uint8_t)(0xc0 | (c >> 6)); utf_o->u_name[utf_o->u_len++] = (uint8_t)(0x80 | (c & 0x3f)); } else { + if (utf_o->u_len > (UDF_NAME_LEN - 5)) + break; utf_o->u_name[utf_o->u_len++] = (uint8_t)(0xe0 | (c >> 12)); utf_o->u_name[utf_o->u_len++] = @@ -173,17 +177,22 @@ int udf_CS0toUTF8(struct ustr *utf_o, const struct ustr *ocu_i) static int udf_UTF8toCS0(dstring *ocu, struct ustr *utf, int length) { unsigned c, i, max_val, utf_char; - int utf_cnt, u_len; + int utf_cnt, u_len, u_ch; memset(ocu, 0, sizeof(dstring) * length); ocu[0] = 8; max_val = 0xffU; + u_ch = 1; try_again: u_len = 0U; utf_char = 0U; utf_cnt = 0U; for (i = 0U; i < utf->u_len; i++) { + /* Name didn't fit? */ + if (u_len + 1 + u_ch >= length) + return 0; + c = (uint8_t)utf->u_name[i]; /* Complete a multi-byte UTF-8 character */ @@ -225,6 +234,7 @@ try_again: if (max_val == 0xffU) { max_val = 0xffffU; ocu[0] = (uint8_t)0x10U; + u_ch = 2; goto try_again; } goto error_out; @@ -277,7 +287,7 @@ static int udf_CS0toNLS(struct nls_table *nls, struct ustr *utf_o, c = (c << 8) | ocu[i++]; len = nls->uni2char(c, &utf_o->u_name[utf_o->u_len], - UDF_NAME_LEN - utf_o->u_len); + UDF_NAME_LEN - 2 - utf_o->u_len); /* Valid character? */ if (len >= 0) utf_o->u_len += len; @@ -295,15 +305,19 @@ static int udf_NLStoCS0(struct nls_table *nls, dstring *ocu, struct ustr *uni, int len; unsigned i, max_val; uint16_t uni_char; - int u_len; + int u_len, u_ch; memset(ocu, 0, sizeof(dstring) * length); ocu[0] = 8; max_val = 0xffU; + u_ch = 1; try_again: u_len = 0U; for (i = 0U; i < uni->u_len; i++) { + /* Name didn't fit? */ + if (u_len + 1 + u_ch >= length) + return 0; len = nls->char2uni(&uni->u_name[i], uni->u_len - i, &uni_char); if (!len) continue; @@ -316,6 +330,7 @@ try_again: if (uni_char > max_val) { max_val = 0xffffU; ocu[0] = (uint8_t)0x10U; + u_ch = 2; goto try_again; } diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h index 8774498ce..e2536bb1c 100644 --- a/fs/xfs/libxfs/xfs_format.h +++ b/fs/xfs/libxfs/xfs_format.h @@ -786,7 +786,7 @@ typedef struct xfs_agfl { __be64 agfl_lsn; __be32 agfl_crc; __be32 agfl_bno[]; /* actually XFS_AGFL_SIZE(mp) */ -} xfs_agfl_t; +} __attribute__((packed)) xfs_agfl_t; #define XFS_AGFL_CRC_OFF offsetof(struct xfs_agfl, agfl_crc) diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c index 268c00f4f..65485cfc4 100644 --- a/fs/xfs/libxfs/xfs_inode_buf.c +++ b/fs/xfs/libxfs/xfs_inode_buf.c @@ -62,11 +62,12 @@ xfs_inobp_check( * has not had the inode cores stamped into it. Hence for readahead, the buffer * may be potentially invalid. * - * If the readahead buffer is invalid, we don't want to mark it with an error, - * but we do want to clear the DONE status of the buffer so that a followup read - * will re-read it from disk. This will ensure that we don't get an unnecessary - * warnings during log recovery and we don't get unnecssary panics on debug - * kernels. + * If the readahead buffer is invalid, we need to mark it with an error and + * clear the DONE status of the buffer so that a followup read will re-read it + * from disk. We don't report the error otherwise to avoid warnings during log + * recovery and we don't get unnecssary panics on debug kernels. We use EIO here + * because all we want to do is say readahead failed; there is no-one to report + * the error to, so this will distinguish it from a non-ra verifier failure. */ static void xfs_inode_buf_verify( @@ -93,6 +94,7 @@ xfs_inode_buf_verify( XFS_RANDOM_ITOBP_INOTOBP))) { if (readahead) { bp->b_flags &= ~XBF_DONE; + xfs_buf_ioerror(bp, -EIO); return; } diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index 3243cdf97..39090fc56 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -604,6 +604,13 @@ found: } } + /* + * Clear b_error if this is a lookup from a caller that doesn't expect + * valid data to be found in the buffer. + */ + if (!(flags & XBF_READ)) + xfs_buf_ioerror(bp, 0); + XFS_STATS_INC(target->bt_mount, xb_get); trace_xfs_buf_get(bp, flags, _RET_IP_); return bp; @@ -1520,6 +1527,16 @@ xfs_wait_buftarg( LIST_HEAD(dispose); int loop = 0; + /* + * We need to flush the buffer workqueue to ensure that all IO + * completion processing is 100% done. Just waiting on buffer locks is + * not sufficient for async IO as the reference count held over IO is + * not released until after the buffer lock is dropped. Hence we need to + * ensure here that all reference counts have been dropped before we + * start walking the LRU list. + */ + drain_workqueue(btp->bt_mount->m_buf_workqueue); + /* loop until there is nothing left on the lru list. */ while (list_lru_count(&btp->bt_lru)) { list_lru_walk(&btp->bt_lru, xfs_buftarg_wait_rele, diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 4dac10365..6fc9a6dd5 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -144,7 +144,7 @@ void ftrace_likely_update(struct ftrace_branch_data *f, int val, int expect); */ #define if(cond, ...) __trace_if( (cond , ## __VA_ARGS__) ) #define __trace_if(cond) \ - if (__builtin_constant_p((cond)) ? !!(cond) : \ + if (__builtin_constant_p(!!(cond)) ? !!(cond) : \ ({ \ int ______r; \ static struct ftrace_branch_data \ diff --git a/include/linux/devpts_fs.h b/include/linux/devpts_fs.h index 251a2090a..e0ee0b300 100644 --- a/include/linux/devpts_fs.h +++ b/include/linux/devpts_fs.h @@ -19,6 +19,8 @@ int devpts_new_index(struct inode *ptmx_inode); void devpts_kill_index(struct inode *ptmx_inode, int idx); +void devpts_add_ref(struct inode *ptmx_inode); +void devpts_del_ref(struct inode *ptmx_inode); /* mknod in devpts */ struct inode *devpts_pty_new(struct inode *ptmx_inode, dev_t device, int index, void *priv); @@ -32,6 +34,8 @@ void devpts_pty_kill(struct inode *inode); /* Dummy stubs in the no-pty case */ static inline int devpts_new_index(struct inode *ptmx_inode) { return -EINVAL; } static inline void devpts_kill_index(struct inode *ptmx_inode, int idx) { } +static inline void devpts_add_ref(struct inode *ptmx_inode) { } +static inline void devpts_del_ref(struct inode *ptmx_inode) { } static inline struct inode *devpts_pty_new(struct inode *ptmx_inode, dev_t device, int index, void *priv) { diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index 821273ca4..2d9b65004 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -235,6 +235,9 @@ static inline void dmar_writeq(void __iomem *addr, u64 val) /* low 64 bit */ #define dma_frcd_page_addr(d) (d & (((u64)-1) << PAGE_SHIFT)) +/* PRS_REG */ +#define DMA_PRS_PPR ((u32)1) + #define IOMMU_WAIT_OP(iommu, offset, op, cond, sts) \ do { \ cycles_t start_time = get_cycles(); \ diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index 061265f92..504c98a27 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -57,7 +57,29 @@ extern void exit_ptrace(struct task_struct *tracer, struct list_head *dead); #define PTRACE_MODE_READ 0x01 #define PTRACE_MODE_ATTACH 0x02 #define PTRACE_MODE_NOAUDIT 0x04 -/* Returns true on success, false on denial. */ +#define PTRACE_MODE_FSCREDS 0x08 +#define PTRACE_MODE_REALCREDS 0x10 + +/* shorthands for READ/ATTACH and FSCREDS/REALCREDS combinations */ +#define PTRACE_MODE_READ_FSCREDS (PTRACE_MODE_READ | PTRACE_MODE_FSCREDS) +#define PTRACE_MODE_READ_REALCREDS (PTRACE_MODE_READ | PTRACE_MODE_REALCREDS) +#define PTRACE_MODE_ATTACH_FSCREDS (PTRACE_MODE_ATTACH | PTRACE_MODE_FSCREDS) +#define PTRACE_MODE_ATTACH_REALCREDS (PTRACE_MODE_ATTACH | PTRACE_MODE_REALCREDS) + +/** + * ptrace_may_access - check whether the caller is permitted to access + * a target task. + * @task: target task + * @mode: selects type of access and caller credentials + * + * Returns true on success, false on denial. + * + * One of the flags PTRACE_MODE_FSCREDS and PTRACE_MODE_REALCREDS must + * be set in @mode to specify whether the access was requested through + * a filesystem syscall (should use effective capabilities and fsuid + * of the caller) or through an explicit syscall such as + * process_vm_writev or ptrace (and should use the real credentials). + */ extern bool ptrace_may_access(struct task_struct *task, unsigned int mode); static inline int ptrace_reparented(struct task_struct *child) diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index 33170dbd9..5d5174b59 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -370,12 +370,28 @@ void **radix_tree_next_chunk(struct radix_tree_root *root, struct radix_tree_iter *iter, unsigned flags); /** + * radix_tree_iter_retry - retry this chunk of the iteration + * @iter: iterator state + * + * If we iterate over a tree protected only by the RCU lock, a race + * against deletion or creation may result in seeing a slot for which + * radix_tree_deref_retry() returns true. If so, call this function + * and continue the iteration. + */ +static inline __must_check +void **radix_tree_iter_retry(struct radix_tree_iter *iter) +{ + iter->next_index = iter->index; + return NULL; +} + +/** * radix_tree_chunk_size - get current chunk size * * @iter: pointer to radix tree iterator * Returns: current chunk size */ -static __always_inline unsigned +static __always_inline long radix_tree_chunk_size(struct radix_tree_iter *iter) { return iter->next_index - iter->index; @@ -409,9 +425,9 @@ radix_tree_next_slot(void **slot, struct radix_tree_iter *iter, unsigned flags) return slot + offset + 1; } } else { - unsigned size = radix_tree_chunk_size(iter) - 1; + long size = radix_tree_chunk_size(iter); - while (size--) { + while (--size > 0) { slot++; iter->index++; if (likely(*slot)) diff --git a/include/linux/rmap.h b/include/linux/rmap.h index 29446aeef..ddda2ac34 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -108,20 +108,6 @@ static inline void put_anon_vma(struct anon_vma *anon_vma) __put_anon_vma(anon_vma); } -static inline void vma_lock_anon_vma(struct vm_area_struct *vma) -{ - struct anon_vma *anon_vma = vma->anon_vma; - if (anon_vma) - down_write(&anon_vma->root->rwsem); -} - -static inline void vma_unlock_anon_vma(struct vm_area_struct *vma) -{ - struct anon_vma *anon_vma = vma->anon_vma; - if (anon_vma) - up_write(&anon_vma->root->rwsem); -} - static inline void anon_vma_lock_write(struct anon_vma *anon_vma) { down_write(&anon_vma->root->rwsem); diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index 696a339c5..03c7efb60 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -14,8 +14,10 @@ * See the file COPYING for more details. */ +#include <linux/smp.h> #include <linux/errno.h> #include <linux/types.h> +#include <linux/cpumask.h> #include <linux/rcupdate.h> #include <linux/static_key.h> @@ -146,6 +148,9 @@ extern void syscall_unregfunc(void); void *it_func; \ void *__data; \ \ + if (!cpu_online(raw_smp_processor_id())) \ + return; \ + \ if (!(cond)) \ return; \ prercu; \ @@ -156,11 +156,12 @@ static inline struct shmid_kernel *shm_lock(struct ipc_namespace *ns, int id) struct kern_ipc_perm *ipcp = ipc_lock(&shm_ids(ns), id); /* - * We raced in the idr lookup or with shm_destroy(). Either way, the - * ID is busted. + * Callers of shm_lock() must validate the status of the returned ipc + * object pointer (as returned by ipc_lock()), and error out as + * appropriate. */ - WARN_ON(IS_ERR(ipcp)); - + if (IS_ERR(ipcp)) + return (void *)ipcp; return container_of(ipcp, struct shmid_kernel, shm_perm); } @@ -186,18 +187,33 @@ static inline void shm_rmid(struct ipc_namespace *ns, struct shmid_kernel *s) } -/* This is called by fork, once for every shm attach. */ -static void shm_open(struct vm_area_struct *vma) +static int __shm_open(struct vm_area_struct *vma) { struct file *file = vma->vm_file; struct shm_file_data *sfd = shm_file_data(file); struct shmid_kernel *shp; shp = shm_lock(sfd->ns, sfd->id); + + if (IS_ERR(shp)) + return PTR_ERR(shp); + shp->shm_atim = get_seconds(); shp->shm_lprid = task_tgid_vnr(current); shp->shm_nattch++; shm_unlock(shp); + return 0; +} + +/* This is called by fork, once for every shm attach. */ +static void shm_open(struct vm_area_struct *vma) +{ + int err = __shm_open(vma); + /* + * We raced in the idr lookup or with shm_destroy(). + * Either way, the ID is busted. + */ + WARN_ON_ONCE(err); } /* @@ -260,6 +276,14 @@ static void shm_close(struct vm_area_struct *vma) down_write(&shm_ids(ns).rwsem); /* remove from the list of attaches of the shm segment */ shp = shm_lock(ns, sfd->id); + + /* + * We raced in the idr lookup or with shm_destroy(). + * Either way, the ID is busted. + */ + if (WARN_ON_ONCE(IS_ERR(shp))) + goto done; /* no-op */ + shp->shm_lprid = task_tgid_vnr(current); shp->shm_dtim = get_seconds(); shp->shm_nattch--; @@ -267,6 +291,7 @@ static void shm_close(struct vm_area_struct *vma) shm_destroy(ns, shp); else shm_unlock(shp); +done: up_write(&shm_ids(ns).rwsem); } @@ -388,17 +413,25 @@ static int shm_mmap(struct file *file, struct vm_area_struct *vma) struct shm_file_data *sfd = shm_file_data(file); int ret; + /* + * In case of remap_file_pages() emulation, the file can represent + * removed IPC ID: propogate shm_lock() error to caller. + */ + ret =__shm_open(vma); + if (ret) + return ret; + ret = sfd->file->f_op->mmap(sfd->file, vma); - if (ret != 0) + if (ret) { + shm_close(vma); return ret; + } sfd->vm_ops = vma->vm_ops; #ifdef CONFIG_MMU WARN_ON(!sfd->vm_ops->fault); #endif vma->vm_ops = &shm_vm_ops; - shm_open(vma); - - return ret; + return 0; } static int shm_release(struct inode *ino, struct file *file) diff --git a/kernel/events/core.c b/kernel/events/core.c index cfc227ccf..1087bbeb1 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -3434,7 +3434,7 @@ find_lively_task_by_vpid(pid_t vpid) /* Reuse ptrace permission checks for now. */ err = -EACCES; - if (!ptrace_may_access(task, PTRACE_MODE_READ)) + if (!ptrace_may_access(task, PTRACE_MODE_READ_REALCREDS)) goto errout; return task; diff --git a/kernel/futex.c b/kernel/futex.c index 684d75498..461c72b2d 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -2755,6 +2755,11 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, if (q.pi_state && (q.pi_state->owner != current)) { spin_lock(q.lock_ptr); ret = fixup_pi_state_owner(uaddr2, &q, current); + /* + * Drop the reference to the pi state which + * the requeue_pi() code acquired for us. + */ + free_pi_state(q.pi_state); spin_unlock(q.lock_ptr); } } else { @@ -2881,7 +2886,7 @@ SYSCALL_DEFINE3(get_robust_list, int, pid, } ret = -EPERM; - if (!ptrace_may_access(p, PTRACE_MODE_READ)) + if (!ptrace_may_access(p, PTRACE_MODE_READ_REALCREDS)) goto err_unlock; head = p->robust_list; diff --git a/kernel/futex_compat.c b/kernel/futex_compat.c index 55c8c9349..4ae3232e7 100644 --- a/kernel/futex_compat.c +++ b/kernel/futex_compat.c @@ -155,7 +155,7 @@ COMPAT_SYSCALL_DEFINE3(get_robust_list, int, pid, } ret = -EPERM; - if (!ptrace_may_access(p, PTRACE_MODE_READ)) + if (!ptrace_may_access(p, PTRACE_MODE_READ_REALCREDS)) goto err_unlock; head = p->compat_robust_list; diff --git a/kernel/kcmp.c b/kernel/kcmp.c index 0aa69ea1d..3a47fa998 100644 --- a/kernel/kcmp.c +++ b/kernel/kcmp.c @@ -122,8 +122,8 @@ SYSCALL_DEFINE5(kcmp, pid_t, pid1, pid_t, pid2, int, type, &task2->signal->cred_guard_mutex); if (ret) goto err; - if (!ptrace_may_access(task1, PTRACE_MODE_READ) || - !ptrace_may_access(task2, PTRACE_MODE_READ)) { + if (!ptrace_may_access(task1, PTRACE_MODE_READ_REALCREDS) || + !ptrace_may_access(task2, PTRACE_MODE_READ_REALCREDS)) { ret = -EPERM; goto err_unlock; } diff --git a/kernel/memremap.c b/kernel/memremap.c index 7658d32c5..7a4e473ce 100644 --- a/kernel/memremap.c +++ b/kernel/memremap.c @@ -111,7 +111,7 @@ EXPORT_SYMBOL(memunmap); static void devm_memremap_release(struct device *dev, void *res) { - memunmap(res); + memunmap(*(void **)res); } static int devm_memremap_match(struct device *dev, void *res, void *match_data) diff --git a/kernel/module.c b/kernel/module.c index 38c7bd558..14833e6d5 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -3515,7 +3515,7 @@ static int load_module(struct load_info *info, const char __user *uargs, /* Module is ready to execute: parsing args may do that. */ after_dashes = parse_args(mod->name, mod->args, mod->kp, mod->num_kp, - -32768, 32767, NULL, + -32768, 32767, mod, unknown_module_param_cb); if (IS_ERR(after_dashes)) { err = PTR_ERR(after_dashes); @@ -3646,6 +3646,11 @@ static inline int is_arm_mapping_symbol(const char *str) && (str[2] == '\0' || str[2] == '.'); } +static const char *symname(struct module *mod, unsigned int symnum) +{ + return mod->strtab + mod->symtab[symnum].st_name; +} + static const char *get_ksymbol(struct module *mod, unsigned long addr, unsigned long *size, @@ -3668,15 +3673,15 @@ static const char *get_ksymbol(struct module *mod, /* We ignore unnamed symbols: they're uninformative * and inserted at a whim. */ + if (*symname(mod, i) == '\0' + || is_arm_mapping_symbol(symname(mod, i))) + continue; + if (mod->symtab[i].st_value <= addr - && mod->symtab[i].st_value > mod->symtab[best].st_value - && *(mod->strtab + mod->symtab[i].st_name) != '\0' - && !is_arm_mapping_symbol(mod->strtab + mod->symtab[i].st_name)) + && mod->symtab[i].st_value > mod->symtab[best].st_value) best = i; if (mod->symtab[i].st_value > addr - && mod->symtab[i].st_value < nextval - && *(mod->strtab + mod->symtab[i].st_name) != '\0' - && !is_arm_mapping_symbol(mod->strtab + mod->symtab[i].st_name)) + && mod->symtab[i].st_value < nextval) nextval = mod->symtab[i].st_value; } @@ -3687,7 +3692,7 @@ static const char *get_ksymbol(struct module *mod, *size = nextval - mod->symtab[best].st_value; if (offset) *offset = addr - mod->symtab[best].st_value; - return mod->strtab + mod->symtab[best].st_name; + return symname(mod, best); } /* For kallsyms to ask for address resolution. NULL means not found. Careful @@ -3782,8 +3787,7 @@ int module_get_kallsym(unsigned int symnum, unsigned long *value, char *type, if (symnum < mod->num_symtab) { *value = mod->symtab[symnum].st_value; *type = mod->symtab[symnum].st_info; - strlcpy(name, mod->strtab + mod->symtab[symnum].st_name, - KSYM_NAME_LEN); + strlcpy(name, symname(mod, symnum), KSYM_NAME_LEN); strlcpy(module_name, mod->name, MODULE_NAME_LEN); *exported = is_exported(name, *value, mod); preempt_enable(); @@ -3800,7 +3804,7 @@ static unsigned long mod_find_symname(struct module *mod, const char *name) unsigned int i; for (i = 0; i < mod->num_symtab; i++) - if (strcmp(name, mod->strtab+mod->symtab[i].st_name) == 0 && + if (strcmp(name, symname(mod, i)) == 0 && mod->symtab[i].st_info != 'U') return mod->symtab[i].st_value; return 0; @@ -3844,7 +3848,7 @@ int module_kallsyms_on_each_symbol(int (*fn)(void *, const char *, if (mod->state == MODULE_STATE_UNFORMED) continue; for (i = 0; i < mod->num_symtab; i++) { - ret = fn(data, mod->strtab + mod->symtab[i].st_name, + ret = fn(data, symname(mod, i), mod, mod->symtab[i].st_value); if (ret != 0) return ret; diff --git a/kernel/ptrace.c b/kernel/ptrace.c index b760bae64..3189e51db 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -219,6 +219,14 @@ static int ptrace_has_cap(struct user_namespace *ns, unsigned int mode) static int __ptrace_may_access(struct task_struct *task, unsigned int mode) { const struct cred *cred = current_cred(), *tcred; + int dumpable = 0; + kuid_t caller_uid; + kgid_t caller_gid; + + if (!(mode & PTRACE_MODE_FSCREDS) == !(mode & PTRACE_MODE_REALCREDS)) { + WARN(1, "denying ptrace access check without PTRACE_MODE_*CREDS\n"); + return -EPERM; + } /* May we inspect the given task? * This check is used both for attaching with ptrace @@ -228,18 +236,33 @@ static int __ptrace_may_access(struct task_struct *task, unsigned int mode) * because setting up the necessary parent/child relationship * or halting the specified task is impossible. */ - int dumpable = 0; + /* Don't let security modules deny introspection */ if (same_thread_group(task, current)) return 0; rcu_read_lock(); + if (mode & PTRACE_MODE_FSCREDS) { + caller_uid = cred->fsuid; + caller_gid = cred->fsgid; + } else { + /* + * Using the euid would make more sense here, but something + * in userland might rely on the old behavior, and this + * shouldn't be a security problem since + * PTRACE_MODE_REALCREDS implies that the caller explicitly + * used a syscall that requests access to another process + * (and not a filesystem syscall to procfs). + */ + caller_uid = cred->uid; + caller_gid = cred->gid; + } tcred = __task_cred(task); - if (uid_eq(cred->uid, tcred->euid) && - uid_eq(cred->uid, tcred->suid) && - uid_eq(cred->uid, tcred->uid) && - gid_eq(cred->gid, tcred->egid) && - gid_eq(cred->gid, tcred->sgid) && - gid_eq(cred->gid, tcred->gid)) + if (uid_eq(caller_uid, tcred->euid) && + uid_eq(caller_uid, tcred->suid) && + uid_eq(caller_uid, tcred->uid) && + gid_eq(caller_gid, tcred->egid) && + gid_eq(caller_gid, tcred->sgid) && + gid_eq(caller_gid, tcred->gid)) goto ok; if (ptrace_has_cap(tcred->user_ns, mode)) goto ok; @@ -306,7 +329,7 @@ static int ptrace_attach(struct task_struct *task, long request, goto out; task_lock(task); - retval = __ptrace_may_access(task, PTRACE_MODE_ATTACH); + retval = __ptrace_may_access(task, PTRACE_MODE_ATTACH_REALCREDS); task_unlock(task); if (retval) goto unlock_creds; diff --git a/kernel/sys.c b/kernel/sys.c index 6af9212ab..78947de6f 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -1853,11 +1853,13 @@ static int prctl_set_mm_map(int opt, const void __user *addr, unsigned long data user_auxv[AT_VECTOR_SIZE - 1] = AT_NULL; } - if (prctl_map.exe_fd != (u32)-1) + if (prctl_map.exe_fd != (u32)-1) { error = prctl_set_mm_exe_file(mm, prctl_map.exe_fd); - down_read(&mm->mmap_sem); - if (error) - goto out; + if (error) + return error; + } + + down_write(&mm->mmap_sem); /* * We don't validate if these members are pointing to @@ -1894,10 +1896,8 @@ static int prctl_set_mm_map(int opt, const void __user *addr, unsigned long data if (prctl_map.auxv_size) memcpy(mm->saved_auxv, user_auxv, sizeof(user_auxv)); - error = 0; -out: - up_read(&mm->mmap_sem); - return error; + up_write(&mm->mmap_sem); + return 0; } #endif /* CONFIG_CHECKPOINT_RESTORE */ @@ -1963,7 +1963,7 @@ static int prctl_set_mm(int opt, unsigned long addr, error = -EINVAL; - down_read(&mm->mmap_sem); + down_write(&mm->mmap_sem); vma = find_vma(mm, addr); prctl_map.start_code = mm->start_code; @@ -2056,7 +2056,7 @@ static int prctl_set_mm(int opt, unsigned long addr, error = 0; out: - up_read(&mm->mmap_sem); + up_write(&mm->mmap_sem); return error; } diff --git a/kernel/time/itimer.c b/kernel/time/itimer.c index 8d262b467..1d5c7204d 100644 --- a/kernel/time/itimer.c +++ b/kernel/time/itimer.c @@ -26,7 +26,7 @@ */ static struct timeval itimer_get_remtime(struct hrtimer *timer) { - ktime_t rem = hrtimer_get_remaining(timer); + ktime_t rem = __hrtimer_get_remaining(timer, true); /* * Racy but safe: if the itimer expires after the above diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c index 31d11ac9f..f2826c35e 100644 --- a/kernel/time/posix-timers.c +++ b/kernel/time/posix-timers.c @@ -760,7 +760,7 @@ common_timer_get(struct k_itimer *timr, struct itimerspec *cur_setting) (timr->it_sigev_notify & ~SIGEV_THREAD_ID) == SIGEV_NONE)) timr->it_overrun += (unsigned int) hrtimer_forward(timer, now, iv); - remaining = ktime_sub(hrtimer_get_expires(timer), now); + remaining = __hrtimer_expires_remaining_adjusted(timer, now); /* Return 0 only, when the timer is expired and not pending */ if (remaining.tv64 <= 0) { /* diff --git a/lib/dma-debug.c b/lib/dma-debug.c index d34bd24c2..4a1515f4b 100644 --- a/lib/dma-debug.c +++ b/lib/dma-debug.c @@ -1181,7 +1181,7 @@ static inline bool overlap(void *addr, unsigned long len, void *start, void *end static void check_for_illegal_area(struct device *dev, void *addr, unsigned long len) { - if (overlap(addr, len, _text, _etext) || + if (overlap(addr, len, _stext, _etext) || overlap(addr, len, __start_rodata, __end_rodata)) err_printk(dev, NULL, "DMA-API: device driver maps memory from kernel text or rodata [addr=%p] [len=%lu]\n", addr, len); } diff --git a/lib/dump_stack.c b/lib/dump_stack.c index 6745c6230..c30d07e99 100644 --- a/lib/dump_stack.c +++ b/lib/dump_stack.c @@ -25,6 +25,7 @@ static atomic_t dump_lock = ATOMIC_INIT(-1); asmlinkage __visible void dump_stack(void) { + unsigned long flags; int was_locked; int old; int cpu; @@ -33,9 +34,8 @@ asmlinkage __visible void dump_stack(void) * Permit this cpu to perform nested stack dumps while serialising * against other CPUs */ - preempt_disable(); - retry: + local_irq_save(flags); cpu = smp_processor_id(); old = atomic_cmpxchg(&dump_lock, -1, cpu); if (old == -1) { @@ -43,6 +43,7 @@ retry: } else if (old == cpu) { was_locked = 1; } else { + local_irq_restore(flags); cpu_relax(); goto retry; } @@ -52,7 +53,7 @@ retry: if (!was_locked) atomic_set(&dump_lock, -1); - preempt_enable(); + local_irq_restore(flags); } #else asmlinkage __visible void dump_stack(void) diff --git a/lib/klist.c b/lib/klist.c index d74cf7a29..0507fa5d8 100644 --- a/lib/klist.c +++ b/lib/klist.c @@ -282,9 +282,9 @@ void klist_iter_init_node(struct klist *k, struct klist_iter *i, struct klist_node *n) { i->i_klist = k; - i->i_cur = n; - if (n) - kref_get(&n->n_ref); + i->i_cur = NULL; + if (n && kref_get_unless_zero(&n->n_ref)) + i->i_cur = n; } EXPORT_SYMBOL_GPL(klist_iter_init_node); diff --git a/lib/radix-tree.c b/lib/radix-tree.c index fcf5d9857..6b79e9026 100644 --- a/lib/radix-tree.c +++ b/lib/radix-tree.c @@ -1019,9 +1019,13 @@ radix_tree_gang_lookup(struct radix_tree_root *root, void **results, return 0; radix_tree_for_each_slot(slot, root, &iter, first_index) { - results[ret] = indirect_to_ptr(rcu_dereference_raw(*slot)); + results[ret] = rcu_dereference_raw(*slot); if (!results[ret]) continue; + if (radix_tree_is_indirect_ptr(results[ret])) { + slot = radix_tree_iter_retry(&iter); + continue; + } if (++ret == max_items) break; } @@ -1098,9 +1102,13 @@ radix_tree_gang_lookup_tag(struct radix_tree_root *root, void **results, return 0; radix_tree_for_each_tagged(slot, root, &iter, first_index, tag) { - results[ret] = indirect_to_ptr(rcu_dereference_raw(*slot)); + results[ret] = rcu_dereference_raw(*slot); if (!results[ret]) continue; + if (radix_tree_is_indirect_ptr(results[ret])) { + slot = radix_tree_iter_retry(&iter); + continue; + } if (++ret == max_items) break; } diff --git a/lib/string_helpers.c b/lib/string_helpers.c index 5939f63d9..5c88204b6 100644 --- a/lib/string_helpers.c +++ b/lib/string_helpers.c @@ -43,50 +43,73 @@ void string_get_size(u64 size, u64 blk_size, const enum string_size_units units, [STRING_UNITS_10] = 1000, [STRING_UNITS_2] = 1024, }; - int i, j; - u32 remainder = 0, sf_cap, exp; + static const unsigned int rounding[] = { 500, 50, 5 }; + int i = 0, j; + u32 remainder = 0, sf_cap; char tmp[8]; const char *unit; tmp[0] = '\0'; - i = 0; - if (!size) + + if (blk_size == 0) + size = 0; + if (size == 0) goto out; - while (blk_size >= divisor[units]) { - remainder = do_div(blk_size, divisor[units]); + /* This is Napier's algorithm. Reduce the original block size to + * + * coefficient * divisor[units]^i + * + * we do the reduction so both coefficients are just under 32 bits so + * that multiplying them together won't overflow 64 bits and we keep + * as much precision as possible in the numbers. + * + * Note: it's safe to throw away the remainders here because all the + * precision is in the coefficients. + */ + while (blk_size >> 32) { + do_div(blk_size, divisor[units]); i++; } - exp = divisor[units] / (u32)blk_size; - /* - * size must be strictly greater than exp here to ensure that remainder - * is greater than divisor[units] coming out of the if below. - */ - if (size > exp) { - remainder = do_div(size, divisor[units]); - remainder *= blk_size; + while (size >> 32) { + do_div(size, divisor[units]); i++; - } else { - remainder *= size; } + /* now perform the actual multiplication keeping i as the sum of the + * two logarithms */ size *= blk_size; - size += remainder / divisor[units]; - remainder %= divisor[units]; + /* and logarithmically reduce it until it's just under the divisor */ while (size >= divisor[units]) { remainder = do_div(size, divisor[units]); i++; } + /* work out in j how many digits of precision we need from the + * remainder */ sf_cap = size; for (j = 0; sf_cap*10 < 1000; j++) sf_cap *= 10; - if (j) { + if (units == STRING_UNITS_2) { + /* express the remainder as a decimal. It's currently the + * numerator of a fraction whose denominator is + * divisor[units], which is 1 << 10 for STRING_UNITS_2 */ remainder *= 1000; - remainder /= divisor[units]; + remainder >>= 10; + } + + /* add a 5 to the digit below what will be printed to ensure + * an arithmetical round up and carry it through to size */ + remainder += rounding[j]; + if (remainder >= 1000) { + remainder -= 1000; + size += 1; + } + + if (j) { snprintf(tmp, sizeof(tmp), ".%03u", remainder); tmp[j+1] = '\0'; } diff --git a/mm/memcontrol.c b/mm/memcontrol.c index fc1062096..ee6acd279 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -3522,16 +3522,17 @@ static void __mem_cgroup_usage_unregister_event(struct mem_cgroup *memcg, swap_buffers: /* Swap primary and spare array */ thresholds->spare = thresholds->primary; - /* If all events are unregistered, free the spare array */ - if (!new) { - kfree(thresholds->spare); - thresholds->spare = NULL; - } rcu_assign_pointer(thresholds->primary, new); /* To be sure that nobody uses thresholds */ synchronize_rcu(); + + /* If all events are unregistered, free the spare array */ + if (!new) { + kfree(thresholds->spare); + thresholds->spare = NULL; + } unlock: mutex_unlock(&memcg->thresholds_lock); } diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 8424b6471..750b7893e 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1572,7 +1572,7 @@ static int get_any_page(struct page *page, unsigned long pfn, int flags) * Did it turn free? */ ret = __get_any_page(page, pfn, 0); - if (!PageLRU(page)) { + if (ret == 1 && !PageLRU(page)) { /* Drop page reference which is from __get_any_page() */ put_hwpoison_page(page); pr_info("soft_offline: %#lx: unknown non LRU page type %lx\n", diff --git a/mm/mlock.c b/mm/mlock.c index 339d9e094..d6006b146 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -172,7 +172,7 @@ static void __munlock_isolation_failed(struct page *page) */ unsigned int munlock_vma_page(struct page *page) { - unsigned int nr_pages; + int nr_pages; struct zone *zone = page_zone(page); /* For try_to_munlock() and to serialize with page migration */ @@ -42,7 +42,6 @@ #include <linux/memory.h> #include <linux/printk.h> #include <linux/userfaultfd_k.h> -#include <linux/ksm.h> #include <asm/uaccess.h> #include <asm/cacheflush.h> @@ -443,12 +442,16 @@ static void validate_mm(struct mm_struct *mm) struct vm_area_struct *vma = mm->mmap; while (vma) { + struct anon_vma *anon_vma = vma->anon_vma; struct anon_vma_chain *avc; - vma_lock_anon_vma(vma); - list_for_each_entry(avc, &vma->anon_vma_chain, same_vma) - anon_vma_interval_tree_verify(avc); - vma_unlock_anon_vma(vma); + if (anon_vma) { + anon_vma_lock_read(anon_vma); + list_for_each_entry(avc, &vma->anon_vma_chain, same_vma) + anon_vma_interval_tree_verify(avc); + anon_vma_unlock_read(anon_vma); + } + highest_address = vma->vm_end; vma = vma->vm_next; i++; @@ -2168,32 +2171,27 @@ static int acct_stack_growth(struct vm_area_struct *vma, unsigned long size, uns int expand_upwards(struct vm_area_struct *vma, unsigned long address) { struct mm_struct *mm = vma->vm_mm; - int error; + int error = 0; if (!(vma->vm_flags & VM_GROWSUP)) return -EFAULT; - /* - * We must make sure the anon_vma is allocated - * so that the anon_vma locking is not a noop. - */ + /* Guard against wrapping around to address 0. */ + if (address < PAGE_ALIGN(address+4)) + address = PAGE_ALIGN(address+4); + else + return -ENOMEM; + + /* We must make sure the anon_vma is allocated. */ if (unlikely(anon_vma_prepare(vma))) return -ENOMEM; - vma_lock_anon_vma(vma); /* * vma->vm_start/vm_end cannot change under us because the caller * is required to hold the mmap_sem in read mode. We need the * anon_vma lock to serialize against concurrent expand_stacks. - * Also guard against wrapping around to address 0. */ - if (address < PAGE_ALIGN(address+4)) - address = PAGE_ALIGN(address+4); - else { - vma_unlock_anon_vma(vma); - return -ENOMEM; - } - error = 0; + anon_vma_lock_write(vma->anon_vma); /* Somebody else might have raced and expanded it already */ if (address > vma->vm_end) { @@ -2211,7 +2209,7 @@ int expand_upwards(struct vm_area_struct *vma, unsigned long address) * updates, but we only hold a shared mmap_sem * lock here, so we need to protect against * concurrent vma expansions. - * vma_lock_anon_vma() doesn't help here, as + * anon_vma_lock_write() doesn't help here, as * we don't guarantee that all growable vmas * in a mm share the same root anon vma. * So, we reuse mm->page_table_lock to guard @@ -2235,7 +2233,7 @@ int expand_upwards(struct vm_area_struct *vma, unsigned long address) } } } - vma_unlock_anon_vma(vma); + anon_vma_unlock_write(vma->anon_vma); khugepaged_enter_vma_merge(vma, vma->vm_flags); validate_mm(mm); return error; @@ -2251,25 +2249,21 @@ int expand_downwards(struct vm_area_struct *vma, struct mm_struct *mm = vma->vm_mm; int error; - /* - * We must make sure the anon_vma is allocated - * so that the anon_vma locking is not a noop. - */ - if (unlikely(anon_vma_prepare(vma))) - return -ENOMEM; - address &= PAGE_MASK; error = security_mmap_addr(address); if (error) return error; - vma_lock_anon_vma(vma); + /* We must make sure the anon_vma is allocated. */ + if (unlikely(anon_vma_prepare(vma))) + return -ENOMEM; /* * vma->vm_start/vm_end cannot change under us because the caller * is required to hold the mmap_sem in read mode. We need the * anon_vma lock to serialize against concurrent expand_stacks. */ + anon_vma_lock_write(vma->anon_vma); /* Somebody else might have raced and expanded it already */ if (address < vma->vm_start) { @@ -2287,7 +2281,7 @@ int expand_downwards(struct vm_area_struct *vma, * updates, but we only hold a shared mmap_sem * lock here, so we need to protect against * concurrent vma expansions. - * vma_lock_anon_vma() doesn't help here, as + * anon_vma_lock_write() doesn't help here, as * we don't guarantee that all growable vmas * in a mm share the same root anon vma. * So, we reuse mm->page_table_lock to guard @@ -2309,7 +2303,7 @@ int expand_downwards(struct vm_area_struct *vma, } } } - vma_unlock_anon_vma(vma); + anon_vma_unlock_write(vma->anon_vma); khugepaged_enter_vma_merge(vma, vma->vm_flags); validate_mm(mm); return error; @@ -2695,12 +2689,29 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size, if (!vma || !(vma->vm_flags & VM_SHARED)) goto out; - if (start < vma->vm_start || start + size > vma->vm_end) + if (start < vma->vm_start) goto out; - if (pgoff == linear_page_index(vma, start)) { - ret = 0; - goto out; + if (start + size > vma->vm_end) { + struct vm_area_struct *next; + + for (next = vma->vm_next; next; next = next->vm_next) { + /* hole between vmas ? */ + if (next->vm_start != next->vm_prev->vm_end) + goto out; + + if (next->vm_file != vma->vm_file) + goto out; + + if (next->vm_flags != vma->vm_flags) + goto out; + + if (start + size <= next->vm_end) + break; + } + + if (!next) + goto out; } prot |= vma->vm_flags & VM_READ ? PROT_READ : 0; @@ -2710,9 +2721,16 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size, flags &= MAP_NONBLOCK; flags |= MAP_SHARED | MAP_FIXED | MAP_POPULATE; if (vma->vm_flags & VM_LOCKED) { + struct vm_area_struct *tmp; flags |= MAP_LOCKED; + /* drop PG_Mlocked flag for over-mapped range */ - munlock_vma_pages_range(vma, start, start + size); + for (tmp = vma; tmp->vm_start >= start + size; + tmp = tmp->vm_next) { + munlock_vma_pages_range(tmp, + max(tmp->vm_start, start), + min(tmp->vm_end, start + size)); + } } vma_get_file(vma); diff --git a/mm/pgtable-generic.c b/mm/pgtable-generic.c index 7d3db0247..1ba58213a 100644 --- a/mm/pgtable-generic.c +++ b/mm/pgtable-generic.c @@ -210,7 +210,9 @@ pmd_t pmdp_collapse_flush(struct vm_area_struct *vma, unsigned long address, VM_BUG_ON(address & ~HPAGE_PMD_MASK); VM_BUG_ON(pmd_trans_huge(*pmdp)); pmd = pmdp_huge_get_and_clear(vma->vm_mm, address, pmdp); - flush_pmd_tlb_range(vma, address, address + HPAGE_PMD_SIZE); + + /* collapse entails shooting down ptes not pmd */ + flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE); return pmd; } #endif diff --git a/mm/process_vm_access.c b/mm/process_vm_access.c index e88d07164..5d453e58d 100644 --- a/mm/process_vm_access.c +++ b/mm/process_vm_access.c @@ -194,7 +194,7 @@ static ssize_t process_vm_rw_core(pid_t pid, struct iov_iter *iter, goto free_proc_pages; } - mm = mm_access(task, PTRACE_MODE_ATTACH); + mm = mm_access(task, PTRACE_MODE_ATTACH_REALCREDS); if (!mm || IS_ERR(mm)) { rc = IS_ERR(mm) ? PTR_ERR(mm) : -ESRCH; /* diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 2ffaf6a79..027c9ef8a 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -398,7 +398,6 @@ static int xs_sendpages(struct socket *sock, struct sockaddr *addr, int addrlen, if (unlikely(!sock)) return -ENOTSOCK; - clear_bit(SOCKWQ_ASYNC_NOSPACE, &sock->flags); if (base != 0) { addr = NULL; addrlen = 0; @@ -442,7 +441,6 @@ static void xs_nospace_callback(struct rpc_task *task) struct sock_xprt *transport = container_of(task->tk_rqstp->rq_xprt, struct sock_xprt, xprt); transport->inet->sk_write_pending--; - clear_bit(SOCKWQ_ASYNC_NOSPACE, &transport->sock->flags); } /** @@ -467,20 +465,11 @@ static int xs_nospace(struct rpc_task *task) /* Don't race with disconnect */ if (xprt_connected(xprt)) { - if (test_bit(SOCKWQ_ASYNC_NOSPACE, &transport->sock->flags)) { - /* - * Notify TCP that we're limited by the application - * window size - */ - set_bit(SOCK_NOSPACE, &transport->sock->flags); - sk->sk_write_pending++; - /* ...and wait for more buffer space */ - xprt_wait_for_buffer_space(task, xs_nospace_callback); - } - } else { - clear_bit(SOCKWQ_ASYNC_NOSPACE, &transport->sock->flags); + /* wait for more buffer space */ + sk->sk_write_pending++; + xprt_wait_for_buffer_space(task, xs_nospace_callback); + } else ret = -ENOTCONN; - } spin_unlock_bh(&xprt->transport_lock); @@ -616,9 +605,6 @@ process_status: case -EAGAIN: status = xs_nospace(task); break; - default: - dprintk("RPC: sendmsg returned unrecognized error %d\n", - -status); case -ENETUNREACH: case -ENOBUFS: case -EPIPE: @@ -626,7 +612,10 @@ process_status: case -EPERM: /* When the server has died, an ICMP port unreachable message * prompts ECONNREFUSED. */ - clear_bit(SOCKWQ_ASYNC_NOSPACE, &transport->sock->flags); + break; + default: + dprintk("RPC: sendmsg returned unrecognized error %d\n", + -status); } return status; @@ -706,16 +695,16 @@ static int xs_tcp_send_request(struct rpc_task *task) case -EAGAIN: status = xs_nospace(task); break; - default: - dprintk("RPC: sendmsg returned unrecognized error %d\n", - -status); case -ECONNRESET: case -ECONNREFUSED: case -ENOTCONN: case -EADDRINUSE: case -ENOBUFS: case -EPIPE: - clear_bit(SOCKWQ_ASYNC_NOSPACE, &transport->sock->flags); + break; + default: + dprintk("RPC: sendmsg returned unrecognized error %d\n", + -status); } return status; @@ -1609,19 +1598,23 @@ static void xs_tcp_state_change(struct sock *sk) static void xs_write_space(struct sock *sk) { - struct socket *sock; + struct socket_wq *wq; struct rpc_xprt *xprt; - if (unlikely(!(sock = sk->sk_socket))) + if (!sk->sk_socket) return; - clear_bit(SOCK_NOSPACE, &sock->flags); + clear_bit(SOCK_NOSPACE, &sk->sk_socket->flags); if (unlikely(!(xprt = xprt_from_sock(sk)))) return; - if (test_and_clear_bit(SOCKWQ_ASYNC_NOSPACE, &sock->flags) == 0) - return; + rcu_read_lock(); + wq = rcu_dereference(sk->sk_wq); + if (!wq || test_and_clear_bit(SOCKWQ_ASYNC_NOSPACE, &wq->flags) == 0) + goto out; xprt_write_space(xprt); +out: + rcu_read_unlock(); } /** diff --git a/scripts/bloat-o-meter b/scripts/bloat-o-meter index 23e78dcd1..38b64f487 100755 --- a/scripts/bloat-o-meter +++ b/scripts/bloat-o-meter @@ -58,8 +58,8 @@ for name in common: delta.sort() delta.reverse() -print "add/remove: %s/%s grow/shrink: %s/%s up/down: %s/%s (%s)" % \ - (add, remove, grow, shrink, up, -down, up-down) -print "%-40s %7s %7s %+7s" % ("function", "old", "new", "delta") +print("add/remove: %s/%s grow/shrink: %s/%s up/down: %s/%s (%s)" % \ + (add, remove, grow, shrink, up, -down, up-down)) +print("%-40s %7s %7s %+7s" % ("function", "old", "new", "delta")) for d, n in delta: - if d: print "%-40s %7s %7s %+7d" % (n, old.get(n,"-"), new.get(n,"-"), d) + if d: print("%-40s %7s %7s %+7d" % (n, old.get(n,"-"), new.get(n,"-"), d)) diff --git a/security/commoncap.c b/security/commoncap.c index 987ff5f8f..bf8241483 100644 --- a/security/commoncap.c +++ b/security/commoncap.c @@ -137,12 +137,17 @@ int cap_ptrace_access_check(struct task_struct *child, unsigned int mode) { int ret = 0; const struct cred *cred, *child_cred; + const kernel_cap_t *caller_caps; rcu_read_lock(); cred = current_cred(); child_cred = __task_cred(child); + if (mode & PTRACE_MODE_FSCREDS) + caller_caps = &cred->cap_effective; + else + caller_caps = &cred->cap_permitted; if (cred->user_ns == child_cred->user_ns && - cap_issubset(child_cred->cap_permitted, cred->cap_permitted)) + cap_issubset(child_cred->cap_permitted, *caller_caps)) goto out; if (ns_capable(child_cred->user_ns, CAP_SYS_PTRACE)) goto out; diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c index a8b27cdc2..4ba64fd49 100644 --- a/sound/core/pcm_native.c +++ b/sound/core/pcm_native.c @@ -74,6 +74,18 @@ static int snd_pcm_open(struct file *file, struct snd_pcm *pcm, int stream); static DEFINE_RWLOCK(snd_pcm_link_rwlock); static DECLARE_RWSEM(snd_pcm_link_rwsem); +/* Writer in rwsem may block readers even during its waiting in queue, + * and this may lead to a deadlock when the code path takes read sem + * twice (e.g. one in snd_pcm_action_nonatomic() and another in + * snd_pcm_stream_lock()). As a (suboptimal) workaround, let writer to + * spin until it gets the lock. + */ +static inline void down_write_nonblock(struct rw_semaphore *lock) +{ + while (!down_write_trylock(lock)) + cond_resched(); +} + /** * snd_pcm_stream_lock - Lock the PCM stream * @substream: PCM substream @@ -1813,7 +1825,7 @@ static int snd_pcm_link(struct snd_pcm_substream *substream, int fd) res = -ENOMEM; goto _nolock; } - down_write(&snd_pcm_link_rwsem); + down_write_nonblock(&snd_pcm_link_rwsem); write_lock_irq(&snd_pcm_link_rwlock); if (substream->runtime->status->state == SNDRV_PCM_STATE_OPEN || substream->runtime->status->state != substream1->runtime->status->state || @@ -1860,7 +1872,7 @@ static int snd_pcm_unlink(struct snd_pcm_substream *substream) struct snd_pcm_substream *s; int res = 0; - down_write(&snd_pcm_link_rwsem); + down_write_nonblock(&snd_pcm_link_rwsem); write_lock_irq(&snd_pcm_link_rwlock); if (!snd_pcm_stream_linked(substream)) { res = -EALREADY; diff --git a/sound/core/seq/seq_memory.c b/sound/core/seq/seq_memory.c index 801076687..c850345c4 100644 --- a/sound/core/seq/seq_memory.c +++ b/sound/core/seq/seq_memory.c @@ -383,15 +383,20 @@ int snd_seq_pool_init(struct snd_seq_pool *pool) if (snd_BUG_ON(!pool)) return -EINVAL; - if (pool->ptr) /* should be atomic? */ - return 0; - pool->ptr = vmalloc(sizeof(struct snd_seq_event_cell) * pool->size); - if (!pool->ptr) + cellptr = vmalloc(sizeof(struct snd_seq_event_cell) * pool->size); + if (!cellptr) return -ENOMEM; /* add new cells to the free cell list */ spin_lock_irqsave(&pool->lock, flags); + if (pool->ptr) { + spin_unlock_irqrestore(&pool->lock, flags); + vfree(cellptr); + return 0; + } + + pool->ptr = cellptr; pool->free = NULL; for (cell = 0; cell < pool->size; cell++) { diff --git a/sound/core/seq/seq_ports.c b/sound/core/seq/seq_ports.c index 921fb2bd8..fe686ee41 100644 --- a/sound/core/seq/seq_ports.c +++ b/sound/core/seq/seq_ports.c @@ -535,19 +535,22 @@ static void delete_and_unsubscribe_port(struct snd_seq_client *client, bool is_src, bool ack) { struct snd_seq_port_subs_info *grp; + struct list_head *list; + bool empty; grp = is_src ? &port->c_src : &port->c_dest; + list = is_src ? &subs->src_list : &subs->dest_list; down_write(&grp->list_mutex); write_lock_irq(&grp->list_lock); - if (is_src) - list_del(&subs->src_list); - else - list_del(&subs->dest_list); + empty = list_empty(list); + if (!empty) + list_del_init(list); grp->exclusive = 0; write_unlock_irq(&grp->list_lock); up_write(&grp->list_mutex); - unsubscribe_port(client, port, grp, &subs->info, ack); + if (!empty) + unsubscribe_port(client, port, grp, &subs->info, ack); } /* connect two ports */ diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index 02a86ba5b..2c13298e8 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -2143,10 +2143,10 @@ static void azx_remove(struct pci_dev *pci) struct hda_intel *hda; if (card) { - /* flush the pending probing work */ + /* cancel the pending probing work */ chip = card->private_data; hda = container_of(chip, struct hda_intel, chip); - flush_work(&hda->probe_work); + cancel_work_sync(&hda->probe_work); snd_card_free(card); } diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c index 2a912df67..68276f35e 100644 --- a/tools/lib/traceevent/event-parse.c +++ b/tools/lib/traceevent/event-parse.c @@ -4968,13 +4968,12 @@ static void pretty_print(struct trace_seq *s, void *data, int size, struct event sizeof(long) != 8) { char *p; - ls = 2; /* make %l into %ll */ - p = strchr(format, 'l'); - if (p) + if (ls == 1 && (p = strchr(format, 'l'))) memmove(p+1, p, strlen(p)+1); else if (strcmp(format, "%p") == 0) strcpy(format, "0x%llx"); + ls = 2; } switch (ls) { case -2: diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 6fc8cd753..b48e87693 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -399,6 +399,9 @@ static void tracepoint_error(struct parse_events_error *e, int err, { char help[BUFSIZ]; + if (!e) + return; + /* * We get error directly from syscall errno ( > 0), * or from encoded pointer's error ( < 0). diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index c35ffdd36..468de95bc 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -972,7 +972,7 @@ static struct machine *machines__find_for_cpumode(struct machines *machines, machine = machines__find(machines, pid); if (!machine) - machine = machines__find(machines, DEFAULT_GUEST_KERNEL_ID); + machine = machines__findnew(machines, DEFAULT_GUEST_KERNEL_ID); return machine; } diff --git a/virt/kvm/arm/arch_timer.c b/virt/kvm/arm/arch_timer.c index 69bca185c..ea6064696 100644 --- a/virt/kvm/arm/arch_timer.c +++ b/virt/kvm/arm/arch_timer.c @@ -143,7 +143,7 @@ static void kvm_timer_update_irq(struct kvm_vcpu *vcpu, bool new_level) * Check if there was a change in the timer state (should we raise or lower * the line level to the GIC). */ -static void kvm_timer_update_state(struct kvm_vcpu *vcpu) +static int kvm_timer_update_state(struct kvm_vcpu *vcpu) { struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu; @@ -154,10 +154,12 @@ static void kvm_timer_update_state(struct kvm_vcpu *vcpu) * until we call this function from kvm_timer_flush_hwstate. */ if (!vgic_initialized(vcpu->kvm)) - return; + return -ENODEV; if (kvm_timer_should_fire(vcpu) != timer->irq.level) kvm_timer_update_irq(vcpu, !timer->irq.level); + + return 0; } /* @@ -218,7 +220,8 @@ void kvm_timer_flush_hwstate(struct kvm_vcpu *vcpu) bool phys_active; int ret; - kvm_timer_update_state(vcpu); + if (kvm_timer_update_state(vcpu)) + return; /* * If we enter the guest with the virtual input level to the VGIC |