diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 988a0d2535b2..5b4753e602de 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -5462,6 +5462,14 @@ as generic guest with no PV drivers. Currently support XEN HVM, KVM, HYPER_V and VMWARE guest. + xen.event_eoi_delay= [XEN] + How long to delay EOI handling in case of event + storms (jiffies). Default is 10. + + xen.event_loop_timeout= [XEN] + After which time (jiffies) the event handling loop + should start to delay EOI handling. Default is 2. + xirc2ps_cs= [NET,PCMCIA] Format: <irq>,<irq_mask>,<io>,<full_duplex>,<do_sound>,<lockup_hack>[,<irq2>[,<irq3>[,<irq4>]]] diff --git a/Documentation/media/uapi/v4l/colorspaces-defs.rst b/Documentation/media/uapi/v4l/colorspaces-defs.rst index e122bbe3d799..aabb08130354 100644 --- a/Documentation/media/uapi/v4l/colorspaces-defs.rst +++ b/Documentation/media/uapi/v4l/colorspaces-defs.rst @@ -36,8 +36,7 @@ whole range, 0-255, dividing the angular value by 1.41. The enum :c:type:`v4l2_hsv_encoding` specifies which encoding is used. .. note:: The default R'G'B' quantization is full range for all - colorspaces except for BT.2020 which uses limited range R'G'B' - quantization. + colorspaces. HSV formats are always full range. .. tabularcolumns:: |p{6.7cm}|p{10.8cm}| @@ -169,8 +168,8 @@ whole range, 0-255, dividing the angular value by 1.41. The enum - Details * - ``V4L2_QUANTIZATION_DEFAULT`` - Use the default quantization encoding as defined by the - colorspace. This is always full range for R'G'B' (except for the - BT.2020 colorspace) and HSV. It is usually limited range for Y'CbCr. + colorspace. This is always full range for R'G'B' and HSV. + It is usually limited range for Y'CbCr. * - ``V4L2_QUANTIZATION_FULL_RANGE`` - Use the full range quantization encoding. I.e. the range [0…1] is mapped to [0…255] (with possible clipping to [1…254] to avoid the @@ -180,4 +179,4 @@ whole range, 0-255, dividing the angular value by 1.41. The enum * - ``V4L2_QUANTIZATION_LIM_RANGE`` - Use the limited range quantization encoding. I.e. the range [0…1] is mapped to [16…235]. Cb and Cr are mapped from [-0.5…0.5] to - [16…240]. + [16…240]. Limited Range cannot be used with HSV. diff --git a/Documentation/media/uapi/v4l/colorspaces-details.rst b/Documentation/media/uapi/v4l/colorspaces-details.rst index 8b0ba3668101..fd0cf57691d8 100644 --- a/Documentation/media/uapi/v4l/colorspaces-details.rst +++ b/Documentation/media/uapi/v4l/colorspaces-details.rst @@ -377,9 +377,8 @@ Colorspace BT.2020 (V4L2_COLORSPACE_BT2020) The :ref:`itu2020` standard defines the colorspace used by Ultra-high definition television (UHDTV). The default transfer function is ``V4L2_XFER_FUNC_709``. The default Y'CbCr encoding is -``V4L2_YCBCR_ENC_BT2020``. The default R'G'B' quantization is limited -range (!), and so is the default Y'CbCr quantization. The chromaticities -of the primary colors and the white reference are: +``V4L2_YCBCR_ENC_BT2020``. The default Y'CbCr quantization is limited range. +The chromaticities of the primary colors and the white reference are: diff --git a/Makefile b/Makefile index 3be5a9c352b9..d38d0cab8e9a 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 5 PATCHLEVEL = 4 -SUBLEVEL = 74 +SUBLEVEL = 75 EXTRAVERSION = NAME = Kleptomaniac Octopus diff --git a/arch/Kconfig b/arch/Kconfig index 238dccfa7691..84653a823d3b 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -405,6 +405,13 @@ config MMU_GATHER_NO_RANGE config HAVE_MMU_GATHER_NO_GATHER bool +config ARCH_WANT_IRQS_OFF_ACTIVATE_MM + bool + help + Temporary select until all architectures can be converted to have + irqs disabled over activate_mm. Architectures that do IPI based TLB + shootdowns should enable this. + config ARCH_HAVE_NMI_SAFE_CMPXCHG bool diff --git a/arch/arc/boot/dts/axc001.dtsi b/arch/arc/boot/dts/axc001.dtsi index 6ec1fcdfc0d7..92247288d056 100644 --- a/arch/arc/boot/dts/axc001.dtsi +++ b/arch/arc/boot/dts/axc001.dtsi @@ -85,7 +85,7 @@ * avoid duplicating the MB dtsi file given that IRQ from * this intc to cpu intc are different for axs101 and axs103 */ - mb_intc: dw-apb-ictl@e0012000 { + mb_intc: interrupt-controller@e0012000 { #interrupt-cells = <1>; compatible = "snps,dw-apb-ictl"; reg = < 0x0 0xe0012000 0x0 0x200 >; diff --git a/arch/arc/boot/dts/axc003.dtsi b/arch/arc/boot/dts/axc003.dtsi index ac8e1b463a70..cd1edcf4f95e 100644 --- a/arch/arc/boot/dts/axc003.dtsi +++ b/arch/arc/boot/dts/axc003.dtsi @@ -129,7 +129,7 @@ * avoid duplicating the MB dtsi file given that IRQ from * this intc to cpu intc are different for axs101 and axs103 */ - mb_intc: dw-apb-ictl@e0012000 { + mb_intc: interrupt-controller@e0012000 { #interrupt-cells = <1>; compatible = "snps,dw-apb-ictl"; reg = < 0x0 0xe0012000 0x0 0x200 >; diff --git a/arch/arc/boot/dts/axc003_idu.dtsi b/arch/arc/boot/dts/axc003_idu.dtsi index 9da21e7fd246..70779386ca79 100644 --- a/arch/arc/boot/dts/axc003_idu.dtsi +++ b/arch/arc/boot/dts/axc003_idu.dtsi @@ -135,7 +135,7 @@ * avoid duplicating the MB dtsi file given that IRQ from * this intc to cpu intc are different for axs101 and axs103 */ - mb_intc: dw-apb-ictl@e0012000 { + mb_intc: interrupt-controller@e0012000 { #interrupt-cells = <1>; compatible = "snps,dw-apb-ictl"; reg = < 0x0 0xe0012000 0x0 0x200 >; diff --git a/arch/arc/boot/dts/vdk_axc003.dtsi b/arch/arc/boot/dts/vdk_axc003.dtsi index f8be7ba8dad4..c21d0eb07bf6 100644 --- a/arch/arc/boot/dts/vdk_axc003.dtsi +++ b/arch/arc/boot/dts/vdk_axc003.dtsi @@ -46,7 +46,7 @@ }; - mb_intc: dw-apb-ictl@e0012000 { + mb_intc: interrupt-controller@e0012000 { #interrupt-cells = <1>; compatible = "snps,dw-apb-ictl"; reg = < 0xe0012000 0x200 >; diff --git a/arch/arc/boot/dts/vdk_axc003_idu.dtsi b/arch/arc/boot/dts/vdk_axc003_idu.dtsi index 0afa3e53a4e3..4d348853ac7c 100644 --- a/arch/arc/boot/dts/vdk_axc003_idu.dtsi +++ b/arch/arc/boot/dts/vdk_axc003_idu.dtsi @@ -54,7 +54,7 @@ }; - mb_intc: dw-apb-ictl@e0012000 { + mb_intc: interrupt-controller@e0012000 { #interrupt-cells = <1>; compatible = "snps,dw-apb-ictl"; reg = < 0xe0012000 0x200 >; diff --git a/arch/arc/kernel/perf_event.c b/arch/arc/kernel/perf_event.c index 79849f37e782..145722f80c9b 100644 --- a/arch/arc/kernel/perf_event.c +++ b/arch/arc/kernel/perf_event.c @@ -562,7 +562,7 @@ static int arc_pmu_device_probe(struct platform_device *pdev) { struct arc_reg_pct_build pct_bcr; struct arc_reg_cc_build cc_bcr; - int i, has_interrupts, irq; + int i, has_interrupts, irq = -1; int counter_size; /* in bits */ union cc_name { @@ -637,19 +637,28 @@ static int arc_pmu_device_probe(struct platform_device *pdev) .attr_groups = arc_pmu->attr_groups, }; - if (has_interrupts && (irq = platform_get_irq(pdev, 0) >= 0)) { + if (has_interrupts) { + irq = platform_get_irq(pdev, 0); + if (irq >= 0) { + int ret; - arc_pmu->irq = irq; + arc_pmu->irq = irq; - /* intc map function ensures irq_set_percpu_devid() called */ - request_percpu_irq(irq, arc_pmu_intr, "ARC perf counters", - this_cpu_ptr(&arc_pmu_cpu)); + /* intc map function ensures irq_set_percpu_devid() called */ + ret = request_percpu_irq(irq, arc_pmu_intr, "ARC perf counters", + this_cpu_ptr(&arc_pmu_cpu)); + + if (!ret) + on_each_cpu(arc_cpu_pmu_irq_init, &irq, 1); + else + irq = -1; + } - on_each_cpu(arc_cpu_pmu_irq_init, &irq, 1); - } else { - arc_pmu->pmu.capabilities |= PERF_PMU_CAP_NO_INTERRUPT; } + if (irq == -1) + arc_pmu->pmu.capabilities |= PERF_PMU_CAP_NO_INTERRUPT; + /* * perf parser doesn't really like '-' symbol in events name, so let's * use '_' in arc pct name as it goes to kernel PMU event prefix. diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 05c9bbfe444d..9aa88715f196 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -507,8 +507,10 @@ config ARCH_S3C24XX select HAVE_S3C2410_WATCHDOG if WATCHDOG select HAVE_S3C_RTC if RTC_CLASS select NEED_MACH_IO_H + select S3C2410_WATCHDOG select SAMSUNG_ATAGS select USE_OF + select WATCHDOG help Samsung S3C2410, S3C2412, S3C2413, S3C2416, S3C2440, S3C2442, S3C2443 and S3C2450 SoCs based systems, such as the Simtec Electronics BAST diff --git a/arch/arm/boot/dts/mt7623n-bananapi-bpi-r2.dts b/arch/arm/boot/dts/mt7623n-bananapi-bpi-r2.dts index 2b760f90f38c..5375c6699843 100644 --- a/arch/arm/boot/dts/mt7623n-bananapi-bpi-r2.dts +++ b/arch/arm/boot/dts/mt7623n-bananapi-bpi-r2.dts @@ -192,6 +192,7 @@ fixed-link { speed = <1000>; full-duplex; + pause; }; }; }; diff --git a/arch/arm/boot/dts/omap4.dtsi b/arch/arm/boot/dts/omap4.dtsi index e5506ab669fc..904852006b9b 100644 --- a/arch/arm/boot/dts/omap4.dtsi +++ b/arch/arm/boot/dts/omap4.dtsi @@ -328,7 +328,7 @@ status = "disabled"; }; - target-module@56000000 { + sgx_module: target-module@56000000 { compatible = "ti,sysc-omap4", "ti,sysc"; reg = <0x5600fe00 0x4>, <0x5600fe10 0x4>; diff --git a/arch/arm/boot/dts/omap443x.dtsi b/arch/arm/boot/dts/omap443x.dtsi index cbcdcb4e7d1c..86b9caf461df 100644 --- a/arch/arm/boot/dts/omap443x.dtsi +++ b/arch/arm/boot/dts/omap443x.dtsi @@ -74,3 +74,13 @@ }; /include/ "omap443x-clocks.dtsi" + +/* + * Use dpll_per for sgx at 153.6MHz like droid4 stock v3.0.8 Android kernel + */ +&sgx_module { + assigned-clocks = <&l3_gfx_clkctrl OMAP4_GPU_CLKCTRL 24>, + <&dpll_per_m7x2_ck>; + assigned-clock-rates = <0>, <153600000>; + assigned-clock-parents = <&dpll_per_m7x2_ck>; +}; diff --git a/arch/arm/boot/dts/s5pv210.dtsi b/arch/arm/boot/dts/s5pv210.dtsi index 2ad642f51fd9..61822afa30ab 100644 --- a/arch/arm/boot/dts/s5pv210.dtsi +++ b/arch/arm/boot/dts/s5pv210.dtsi @@ -52,34 +52,26 @@ }; }; + xxti: oscillator-0 { + compatible = "fixed-clock"; + clock-frequency = <0>; + clock-output-names = "xxti"; + #clock-cells = <0>; + }; + + xusbxti: oscillator-1 { + compatible = "fixed-clock"; + clock-frequency = <0>; + clock-output-names = "xusbxti"; + #clock-cells = <0>; + }; + soc { compatible = "simple-bus"; #address-cells = <1>; #size-cells = <1>; ranges; - external-clocks { - compatible = "simple-bus"; - #address-cells = <1>; - #size-cells = <0>; - - xxti: oscillator@0 { - compatible = "fixed-clock"; - reg = <0>; - clock-frequency = <0>; - clock-output-names = "xxti"; - #clock-cells = <0>; - }; - - xusbxti: oscillator@1 { - compatible = "fixed-clock"; - reg = <1>; - clock-frequency = <0>; - clock-output-names = "xusbxti"; - #clock-cells = <0>; - }; - }; - onenand: onenand@b0600000 { compatible = "samsung,s5pv210-onenand"; reg = <0xb0600000 0x2000>, @@ -100,19 +92,16 @@ }; clocks: clock-controller@e0100000 { - compatible = "samsung,s5pv210-clock", "simple-bus"; + compatible = "samsung,s5pv210-clock"; reg = <0xe0100000 0x10000>; clock-names = "xxti", "xusbxti"; clocks = <&xxti>, <&xusbxti>; #clock-cells = <1>; - #address-cells = <1>; - #size-cells = <1>; - ranges; + }; - pmu_syscon: syscon@e0108000 { - compatible = "samsung-s5pv210-pmu", "syscon"; - reg = <0xe0108000 0x8000>; - }; + pmu_syscon: syscon@e0108000 { + compatible = "samsung-s5pv210-pmu", "syscon"; + reg = <0xe0108000 0x8000>; }; pinctrl0: pinctrl@e0200000 { @@ -128,35 +117,28 @@ }; }; - amba { - #address-cells = <1>; - #size-cells = <1>; - compatible = "simple-bus"; - ranges; - - pdma0: dma@e0900000 { - compatible = "arm,pl330", "arm,primecell"; - reg = <0xe0900000 0x1000>; - interrupt-parent = <&vic0>; - interrupts = <19>; - clocks = <&clocks CLK_PDMA0>; - clock-names = "apb_pclk"; - #dma-cells = <1>; - #dma-channels = <8>; - #dma-requests = <32>; - }; + pdma0: dma@e0900000 { + compatible = "arm,pl330", "arm,primecell"; + reg = <0xe0900000 0x1000>; + interrupt-parent = <&vic0>; + interrupts = <19>; + clocks = <&clocks CLK_PDMA0>; + clock-names = "apb_pclk"; + #dma-cells = <1>; + #dma-channels = <8>; + #dma-requests = <32>; + }; - pdma1: dma@e0a00000 { - compatible = "arm,pl330", "arm,primecell"; - reg = <0xe0a00000 0x1000>; - interrupt-parent = <&vic0>; - interrupts = <20>; - clocks = <&clocks CLK_PDMA1>; - clock-names = "apb_pclk"; - #dma-cells = <1>; - #dma-channels = <8>; - #dma-requests = <32>; - }; + pdma1: dma@e0a00000 { + compatible = "arm,pl330", "arm,primecell"; + reg = <0xe0a00000 0x1000>; + interrupt-parent = <&vic0>; + interrupts = <20>; + clocks = <&clocks CLK_PDMA1>; + clock-names = "apb_pclk"; + #dma-cells = <1>; + #dma-channels = <8>; + #dma-requests = <32>; }; spi0: spi@e1300000 { @@ -229,43 +211,36 @@ status = "disabled"; }; - audio-subsystem { - compatible = "samsung,s5pv210-audss", "simple-bus"; - #address-cells = <1>; - #size-cells = <1>; - ranges; - - clk_audss: clock-controller@eee10000 { - compatible = "samsung,s5pv210-audss-clock"; - reg = <0xeee10000 0x1000>; - clock-names = "hclk", "xxti", - "fout_epll", - "sclk_audio0"; - clocks = <&clocks DOUT_HCLKP>, <&xxti>, - <&clocks FOUT_EPLL>, - <&clocks SCLK_AUDIO0>; - #clock-cells = <1>; - }; + clk_audss: clock-controller@eee10000 { + compatible = "samsung,s5pv210-audss-clock"; + reg = <0xeee10000 0x1000>; + clock-names = "hclk", "xxti", + "fout_epll", + "sclk_audio0"; + clocks = <&clocks DOUT_HCLKP>, <&xxti>, + <&clocks FOUT_EPLL>, + <&clocks SCLK_AUDIO0>; + #clock-cells = <1>; + }; - i2s0: i2s@eee30000 { - compatible = "samsung,s5pv210-i2s"; - reg = <0xeee30000 0x1000>; - interrupt-parent = <&vic2>; - interrupts = <16>; - dma-names = "rx", "tx", "tx-sec"; - dmas = <&pdma1 9>, <&pdma1 10>, <&pdma1 11>; - clock-names = "iis", - "i2s_opclk0", - "i2s_opclk1"; - clocks = <&clk_audss CLK_I2S>, - <&clk_audss CLK_I2S>, - <&clk_audss CLK_DOUT_AUD_BUS>; - samsung,idma-addr = <0xc0010000>; - pinctrl-names = "default"; - pinctrl-0 = <&i2s0_bus>; - #sound-dai-cells = <0>; - status = "disabled"; - }; + i2s0: i2s@eee30000 { + compatible = "samsung,s5pv210-i2s"; + reg = <0xeee30000 0x1000>; + interrupt-parent = <&vic2>; + interrupts = <16>; + dma-names = "rx", "tx", "tx-sec"; + dmas = <&pdma1 9>, <&pdma1 10>, <&pdma1 11>; + clock-names = "iis", + "i2s_opclk0", + "i2s_opclk1"; + clocks = <&clk_audss CLK_I2S>, + <&clk_audss CLK_I2S>, + <&clk_audss CLK_DOUT_AUD_BUS>; + samsung,idma-addr = <0xc0010000>; + pinctrl-names = "default"; + pinctrl-0 = <&i2s0_bus>; + #sound-dai-cells = <0>; + status = "disabled"; }; i2s1: i2s@e2100000 { diff --git a/arch/arm/kernel/hw_breakpoint.c b/arch/arm/kernel/hw_breakpoint.c index 5f95e4b911a0..7021ef0b4e71 100644 --- a/arch/arm/kernel/hw_breakpoint.c +++ b/arch/arm/kernel/hw_breakpoint.c @@ -680,6 +680,40 @@ static void disable_single_step(struct perf_event *bp) arch_install_hw_breakpoint(bp); } +/* + * Arm32 hardware does not always report a watchpoint hit address that matches + * one of the watchpoints set. It can also report an address "near" the + * watchpoint if a single instruction access both watched and unwatched + * addresses. There is no straight-forward way, short of disassembling the + * offending instruction, to map that address back to the watchpoint. This + * function computes the distance of the memory access from the watchpoint as a + * heuristic for the likelyhood that a given access triggered the watchpoint. + * + * See this same function in the arm64 platform code, which has the same + * problem. + * + * The function returns the distance of the address from the bytes watched by + * the watchpoint. In case of an exact match, it returns 0. + */ +static u32 get_distance_from_watchpoint(unsigned long addr, u32 val, + struct arch_hw_breakpoint_ctrl *ctrl) +{ + u32 wp_low, wp_high; + u32 lens, lene; + + lens = __ffs(ctrl->len); + lene = __fls(ctrl->len); + + wp_low = val + lens; + wp_high = val + lene; + if (addr < wp_low) + return wp_low - addr; + else if (addr > wp_high) + return addr - wp_high; + else + return 0; +} + static int watchpoint_fault_on_uaccess(struct pt_regs *regs, struct arch_hw_breakpoint *info) { @@ -689,23 +723,25 @@ static int watchpoint_fault_on_uaccess(struct pt_regs *regs, static void watchpoint_handler(unsigned long addr, unsigned int fsr, struct pt_regs *regs) { - int i, access; - u32 val, ctrl_reg, alignment_mask; + int i, access, closest_match = 0; + u32 min_dist = -1, dist; + u32 val, ctrl_reg; struct perf_event *wp, **slots; struct arch_hw_breakpoint *info; struct arch_hw_breakpoint_ctrl ctrl; slots = this_cpu_ptr(wp_on_reg); + /* + * Find all watchpoints that match the reported address. If no exact + * match is found. Attribute the hit to the closest watchpoint. + */ + rcu_read_lock(); for (i = 0; i < core_num_wrps; ++i) { - rcu_read_lock(); - wp = slots[i]; - if (wp == NULL) - goto unlock; + continue; - info = counter_arch_bp(wp); /* * The DFAR is an unknown value on debug architectures prior * to 7.1. Since we only allow a single watchpoint on these @@ -714,33 +750,31 @@ static void watchpoint_handler(unsigned long addr, unsigned int fsr, */ if (debug_arch < ARM_DEBUG_ARCH_V7_1) { BUG_ON(i > 0); + info = counter_arch_bp(wp); info->trigger = wp->attr.bp_addr; } else { - if (info->ctrl.len == ARM_BREAKPOINT_LEN_8) - alignment_mask = 0x7; - else - alignment_mask = 0x3; - - /* Check if the watchpoint value matches. */ - val = read_wb_reg(ARM_BASE_WVR + i); - if (val != (addr & ~alignment_mask)) - goto unlock; - - /* Possible match, check the byte address select. */ - ctrl_reg = read_wb_reg(ARM_BASE_WCR + i); - decode_ctrl_reg(ctrl_reg, &ctrl); - if (!((1 << (addr & alignment_mask)) & ctrl.len)) - goto unlock; - /* Check that the access type matches. */ if (debug_exception_updates_fsr()) { access = (fsr & ARM_FSR_ACCESS_MASK) ? HW_BREAKPOINT_W : HW_BREAKPOINT_R; if (!(access & hw_breakpoint_type(wp))) - goto unlock; + continue; } + val = read_wb_reg(ARM_BASE_WVR + i); + ctrl_reg = read_wb_reg(ARM_BASE_WCR + i); + decode_ctrl_reg(ctrl_reg, &ctrl); + dist = get_distance_from_watchpoint(addr, val, &ctrl); + if (dist < min_dist) { + min_dist = dist; + closest_match = i; + } + /* Is this an exact match? */ + if (dist != 0) + continue; + /* We have a winner. */ + info = counter_arch_bp(wp); info->trigger = addr; } @@ -762,13 +796,23 @@ static void watchpoint_handler(unsigned long addr, unsigned int fsr, * we can single-step over the watchpoint trigger. */ if (!is_default_overflow_handler(wp)) - goto unlock; - + continue; step: enable_single_step(wp, instruction_pointer(regs)); -unlock: - rcu_read_unlock(); } + + if (min_dist > 0 && min_dist != -1) { + /* No exact match found. */ + wp = slots[closest_match]; + info = counter_arch_bp(wp); + info->trigger = addr; + pr_debug("watchpoint fired: address = 0x%x\n", info->trigger); + perf_bp_event(wp, regs); + if (is_default_overflow_handler(wp)) + enable_single_step(wp, instruction_pointer(regs)); + } + + rcu_read_unlock(); } static void watchpoint_single_step_handler(unsigned long pc) diff --git a/arch/arm/plat-samsung/Kconfig b/arch/arm/plat-samsung/Kconfig index 301e572651c0..790c87ee7271 100644 --- a/arch/arm/plat-samsung/Kconfig +++ b/arch/arm/plat-samsung/Kconfig @@ -241,6 +241,7 @@ config SAMSUNG_PM_DEBUG depends on PM && DEBUG_KERNEL depends on PLAT_S3C24XX || ARCH_S3C64XX || ARCH_S5PV210 depends on DEBUG_EXYNOS_UART || DEBUG_S3C24XX_UART || DEBUG_S3C2410_UART + depends on DEBUG_LL && MMU help Say Y here if you want verbose debugging from the PM Suspend and Resume code. See <file:Documentation/arm/samsung-s3c24xx/suspend.rst> diff --git a/arch/arm64/Kconfig.platforms b/arch/arm64/Kconfig.platforms index 16d761475a86..9dccf4db319b 100644 --- a/arch/arm64/Kconfig.platforms +++ b/arch/arm64/Kconfig.platforms @@ -54,6 +54,7 @@ config ARCH_BCM_IPROC config ARCH_BERLIN bool "Marvell Berlin SoC Family" select DW_APB_ICTL + select DW_APB_TIMER_OF select GPIOLIB select PINCTRL help diff --git a/arch/arm64/boot/dts/renesas/ulcb.dtsi b/arch/arm64/boot/dts/renesas/ulcb.dtsi index 3ef89171538f..d8fccf3d4987 100644 --- a/arch/arm64/boot/dts/renesas/ulcb.dtsi +++ b/arch/arm64/boot/dts/renesas/ulcb.dtsi @@ -470,6 +470,7 @@ mmc-hs200-1_8v; mmc-hs400-1_8v; non-removable; + full-pwr-cycle-in-suspend; status = "okay"; }; diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index d719c6b4dd81..7140701f65f9 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -209,6 +209,7 @@ enum vcpu_sysreg { #define cp14_DBGWCR0 (DBGWCR0_EL1 * 2) #define cp14_DBGWVR0 (DBGWVR0_EL1 * 2) #define cp14_DBGDCCINT (MDCCINT_EL1 * 2) +#define cp14_DBGVCR (DBGVCR32_EL2 * 2) #define NR_COPRO_REGS (NR_SYS_REGS * 2) diff --git a/arch/arm64/include/asm/numa.h b/arch/arm64/include/asm/numa.h index 626ad01e83bf..dd870390d639 100644 --- a/arch/arm64/include/asm/numa.h +++ b/arch/arm64/include/asm/numa.h @@ -25,6 +25,9 @@ const struct cpumask *cpumask_of_node(int node); /* Returns a pointer to the cpumask of CPUs on Node 'node'. */ static inline const struct cpumask *cpumask_of_node(int node) { + if (node == NUMA_NO_NODE) + return cpu_all_mask; + return node_to_cpumask_map[node]; } #endif diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c index fa9528dfd0ce..113903db666c 100644 --- a/arch/arm64/kernel/topology.c +++ b/arch/arm64/kernel/topology.c @@ -35,21 +35,23 @@ void store_cpu_topology(unsigned int cpuid) if (mpidr & MPIDR_UP_BITMASK) return; - /* Create cpu topology mapping based on MPIDR. */ - if (mpidr & MPIDR_MT_BITMASK) { - /* Multiprocessor system : Multi-threads per core */ - cpuid_topo->thread_id = MPIDR_AFFINITY_LEVEL(mpidr, 0); - cpuid_topo->core_id = MPIDR_AFFINITY_LEVEL(mpidr, 1); - cpuid_topo->package_id = MPIDR_AFFINITY_LEVEL(mpidr, 2) | - MPIDR_AFFINITY_LEVEL(mpidr, 3) << 8; - } else { - /* Multiprocessor system : Single-thread per core */ - cpuid_topo->thread_id = -1; - cpuid_topo->core_id = MPIDR_AFFINITY_LEVEL(mpidr, 0); - cpuid_topo->package_id = MPIDR_AFFINITY_LEVEL(mpidr, 1) | - MPIDR_AFFINITY_LEVEL(mpidr, 2) << 8 | - MPIDR_AFFINITY_LEVEL(mpidr, 3) << 16; - } + /* + * This would be the place to create cpu topology based on MPIDR. + * + * However, it cannot be trusted to depict the actual topology; some + * pieces of the architecture enforce an artificial cap on Aff0 values + * (e.g. GICv3's ICC_SGI1R_EL1 limits it to 15), leading to an + * artificial cycling of Aff1, Aff2 and Aff3 values. IOW, these end up + * having absolutely no relationship to the actual underlying system + * topology, and cannot be reasonably used as core / package ID. + * + * If the MT bit is set, Aff0 *could* be used to define a thread ID, but + * we still wouldn't be able to obtain a sane core ID. This means we + * need to entirely ignore MPIDR for any topology deduction. + */ + cpuid_topo->thread_id = -1; + cpuid_topo->core_id = cpuid; + cpuid_topo->package_id = cpu_to_node(cpuid); pr_debug("CPU%u: cluster %d core %d thread %d mpidr %#016llx\n", cpuid, cpuid_topo->package_id, cpuid_topo->core_id, diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index d43f44b3377e..0ed7598dfa6a 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -1746,9 +1746,9 @@ static const struct sys_reg_desc cp14_regs[] = { { Op1( 0), CRn( 0), CRm( 1), Op2( 0), trap_raz_wi }, DBG_BCR_BVR_WCR_WVR(1), /* DBGDCCINT */ - { Op1( 0), CRn( 0), CRm( 2), Op2( 0), trap_debug32 }, + { Op1( 0), CRn( 0), CRm( 2), Op2( 0), trap_debug32, NULL, cp14_DBGDCCINT }, /* DBGDSCRext */ - { Op1( 0), CRn( 0), CRm( 2), Op2( 2), trap_debug32 }, + { Op1( 0), CRn( 0), CRm( 2), Op2( 2), trap_debug32, NULL, cp14_DBGDSCRext }, DBG_BCR_BVR_WCR_WVR(2), /* DBGDTR[RT]Xint */ { Op1( 0), CRn( 0), CRm( 3), Op2( 0), trap_raz_wi }, @@ -1763,7 +1763,7 @@ static const struct sys_reg_desc cp14_regs[] = { { Op1( 0), CRn( 0), CRm( 6), Op2( 2), trap_raz_wi }, DBG_BCR_BVR_WCR_WVR(6), /* DBGVCR */ - { Op1( 0), CRn( 0), CRm( 7), Op2( 0), trap_debug32 }, + { Op1( 0), CRn( 0), CRm( 7), Op2( 0), trap_debug32, NULL, cp14_DBGVCR }, DBG_BCR_BVR_WCR_WVR(7), DBG_BCR_BVR_WCR_WVR(8), DBG_BCR_BVR_WCR_WVR(9), diff --git a/arch/arm64/mm/numa.c b/arch/arm64/mm/numa.c index 4decf1659700..53ebb4babf3a 100644 --- a/arch/arm64/mm/numa.c +++ b/arch/arm64/mm/numa.c @@ -46,7 +46,11 @@ EXPORT_SYMBOL(node_to_cpumask_map); */ const struct cpumask *cpumask_of_node(int node) { - if (WARN_ON(node >= nr_node_ids)) + + if (node == NUMA_NO_NODE) + return cpu_all_mask; + + if (WARN_ON(node < 0 || node >= nr_node_ids)) return cpu_none_mask; if (WARN_ON(node_to_cpumask_map[node] == NULL)) diff --git a/arch/ia64/kernel/Makefile b/arch/ia64/kernel/Makefile index 1a8df6669eee..18d6008b151f 100644 --- a/arch/ia64/kernel/Makefile +++ b/arch/ia64/kernel/Makefile @@ -41,7 +41,7 @@ obj-y += esi_stub.o # must be in kernel proper endif obj-$(CONFIG_INTEL_IOMMU) += pci-dma.o -obj-$(CONFIG_BINFMT_ELF) += elfcore.o +obj-$(CONFIG_ELF_CORE) += elfcore.o # fp_emulate() expects f2-f5,f16-f31 to contain the user-level state. CFLAGS_traps.o += -mfixed-range=f2-f5,f16-f31 diff --git a/arch/ia64/kernel/kprobes.c b/arch/ia64/kernel/kprobes.c index b8356edbde65..b3dc39050c1a 100644 --- a/arch/ia64/kernel/kprobes.c +++ b/arch/ia64/kernel/kprobes.c @@ -396,83 +396,9 @@ static void kretprobe_trampoline(void) { } -/* - * At this point the target function has been tricked into - * returning into our trampoline. Lookup the associated instance - * and then: - * - call the handler function - * - cleanup by marking the instance as unused - * - long jump back to the original return address - */ int __kprobes trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs) { - struct kretprobe_instance *ri = NULL; - struct hlist_head *head, empty_rp; - struct hlist_node *tmp; - unsigned long flags, orig_ret_address = 0; - unsigned long trampoline_address = - ((struct fnptr *)kretprobe_trampoline)->ip; - - INIT_HLIST_HEAD(&empty_rp); - kretprobe_hash_lock(current, &head, &flags); - - /* - * It is possible to have multiple instances associated with a given - * task either because an multiple functions in the call path - * have a return probe installed on them, and/or more than one return - * return probe was registered for a target function. - * - * We can handle this because: - * - instances are always inserted at the head of the list - * - when multiple return probes are registered for the same - * function, the first instance's ret_addr will point to the - * real return address, and all the rest will point to - * kretprobe_trampoline - */ - hlist_for_each_entry_safe(ri, tmp, head, hlist) { - if (ri->task != current) - /* another task is sharing our hash bucket */ - continue; - - orig_ret_address = (unsigned long)ri->ret_addr; - if (orig_ret_address != trampoline_address) - /* - * This is the real return address. Any other - * instances associated with this task are for - * other calls deeper on the call stack - */ - break; - } - - regs->cr_iip = orig_ret_address; - - hlist_for_each_entry_safe(ri, tmp, head, hlist) { - if (ri->task != current) - /* another task is sharing our hash bucket */ - continue; - - if (ri->rp && ri->rp->handler) - ri->rp->handler(ri, regs); - - orig_ret_address = (unsigned long)ri->ret_addr; - recycle_rp_inst(ri, &empty_rp); - - if (orig_ret_address != trampoline_address) - /* - * This is the real return address. Any other - * instances associated with this task are for - * other calls deeper on the call stack - */ - break; - } - kretprobe_assert(ri, orig_ret_address, trampoline_address); - - kretprobe_hash_unlock(current, &flags); - - hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) { - hlist_del(&ri->hlist); - kfree(ri); - } + regs->cr_iip = __kretprobe_trampoline_handler(regs, kretprobe_trampoline, NULL); /* * By returning a non-zero value, we are telling * kprobe_handler() that we don't want the post_handler @@ -485,6 +411,7 @@ void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri, struct pt_regs *regs) { ri->ret_addr = (kprobe_opcode_t *)regs->b0; + ri->fp = NULL; /* Replace the return addr with trampoline addr */ regs->b0 = ((struct fnptr *)kretprobe_trampoline)->ip; diff --git a/arch/mips/dec/setup.c b/arch/mips/dec/setup.c index 61a0bf13e308..1fc8dffa8d1d 100644 --- a/arch/mips/dec/setup.c +++ b/arch/mips/dec/setup.c @@ -6,7 +6,7 @@ * for more details. * * Copyright (C) 1998 Harald Koerfgen - * Copyright (C) 2000, 2001, 2002, 2003, 2005 Maciej W. Rozycki + * Copyright (C) 2000, 2001, 2002, 2003, 2005, 2020 Maciej W. Rozycki */ #include <linux/console.h> #include <linux/export.h> @@ -15,6 +15,7 @@ #include <linux/ioport.h> #include <linux/irq.h> #include <linux/irqnr.h> +#include <linux/memblock.h> #include <linux/param.h> #include <linux/percpu-defs.h> #include <linux/sched.h> @@ -22,6 +23,7 @@ #include <linux/types.h> #include <linux/pm.h> +#include <asm/addrspace.h> #include <asm/bootinfo.h> #include <asm/cpu.h> #include <asm/cpu-features.h> @@ -29,7 +31,9 @@ #include <asm/irq.h> #include <asm/irq_cpu.h> #include <asm/mipsregs.h> +#include <asm/page.h> #include <asm/reboot.h> +#include <asm/sections.h> #include <asm/time.h> #include <asm/traps.h> #include <asm/wbflush.h> @@ -166,6 +170,9 @@ void __init plat_mem_setup(void) ioport_resource.start = ~0UL; ioport_resource.end = 0UL; + + /* Stay away from the firmware working memory area for now. */ + memblock_reserve(PHYS_OFFSET, __pa_symbol(&_text) - PHYS_OFFSET); } /* diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index ad620637cbd1..cb285e474c88 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -147,6 +147,7 @@ config PPC select ARCH_USE_BUILTIN_BSWAP select ARCH_USE_CMPXCHG_LOCKREF if PPC64 select ARCH_WANT_IPC_PARSE_VERSION + select ARCH_WANT_IRQS_OFF_ACTIVATE_MM select ARCH_WEAK_RELEASE_ACQUIRE select BINFMT_ELF select BUILDTIME_EXTABLE_SORT @@ -1023,6 +1024,19 @@ config FSL_RIO Include support for RapidIO controller on Freescale embedded processors (MPC8548, MPC8641, etc). +config PPC_RTAS_FILTER + bool "Enable filtering of RTAS syscalls" + default y + depends on PPC_RTAS + help + The RTAS syscall API has security issues that could be used to + compromise system integrity. This option enforces restrictions on the + RTAS calls and arguments passed by userspace programs to mitigate + these issues. + + Say Y unless you know what you are doing and the filter is causing + problems for you. + endmenu config NONSTATIC_KERNEL diff --git a/arch/powerpc/include/asm/drmem.h b/arch/powerpc/include/asm/drmem.h index bea7a2405ba5..ee61542c6c3d 100644 --- a/arch/powerpc/include/asm/drmem.h +++ b/arch/powerpc/include/asm/drmem.h @@ -20,7 +20,7 @@ struct drmem_lmb { struct drmem_lmb_info { struct drmem_lmb *lmbs; int n_lmbs; - u32 lmb_size; + u64 lmb_size; }; extern struct drmem_lmb_info *drmem_info; @@ -79,7 +79,7 @@ struct of_drconf_cell_v2 { #define DRCONF_MEM_AI_INVALID 0x00000040 #define DRCONF_MEM_RESERVED 0x00000080 -static inline u32 drmem_lmb_size(void) +static inline u64 drmem_lmb_size(void) { return drmem_info->lmb_size; } diff --git a/arch/powerpc/include/asm/mmu_context.h b/arch/powerpc/include/asm/mmu_context.h index 58efca934311..f132b418a8c7 100644 --- a/arch/powerpc/include/asm/mmu_context.h +++ b/arch/powerpc/include/asm/mmu_context.h @@ -216,7 +216,7 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, */ static inline void activate_mm(struct mm_struct *prev, struct mm_struct *next) { - switch_mm(prev, next, current); + switch_mm_irqs_off(prev, next, current); } /* We don't currently use enter_lazy_tlb() for anything */ diff --git a/arch/powerpc/kernel/head_32.S b/arch/powerpc/kernel/head_32.S index 4a24f8f026c7..5e2f2fd78b94 100644 --- a/arch/powerpc/kernel/head_32.S +++ b/arch/powerpc/kernel/head_32.S @@ -843,7 +843,7 @@ BEGIN_MMU_FTR_SECTION END_MMU_FTR_SECTION_IFSET(MMU_FTR_USE_HIGH_BATS) blr -load_segment_registers: +_GLOBAL(load_segment_registers) li r0, NUM_USER_SEGMENTS /* load up user segment register values */ mtctr r0 /* for context 0 */ li r3, 0 /* Kp = 0, Ks = 0, VSID = 0 */ diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c index 01210593d60c..c62ff66d44ad 100644 --- a/arch/powerpc/kernel/rtas.c +++ b/arch/powerpc/kernel/rtas.c @@ -940,6 +940,147 @@ struct pseries_errorlog *get_pseries_errorlog(struct rtas_error_log *log, return NULL; } +#ifdef CONFIG_PPC_RTAS_FILTER + +/* + * The sys_rtas syscall, as originally designed, allows root to pass + * arbitrary physical addresses to RTAS calls. A number of RTAS calls + * can be abused to write to arbitrary memory and do other things that + * are potentially harmful to system integrity, and thus should only + * be used inside the kernel and not exposed to userspace. + * + * All known legitimate users of the sys_rtas syscall will only ever + * pass addresses that fall within the RMO buffer, and use a known + * subset of RTAS calls. + * + * Accordingly, we filter RTAS requests to check that the call is + * permitted, and that provided pointers fall within the RMO buffer. + * The rtas_filters list contains an entry for each permitted call, + * with the indexes of the parameters which are expected to contain + * addresses and sizes of buffers allocated inside the RMO buffer. + */ +struct rtas_filter { + const char *name; + int token; + /* Indexes into the args buffer, -1 if not used */ + int buf_idx1; + int size_idx1; + int buf_idx2; + int size_idx2; + + int fixed_size; +}; + +static struct rtas_filter rtas_filters[] __ro_after_init = { + { "ibm,activate-firmware", -1, -1, -1, -1, -1 }, + { "ibm,configure-connector", -1, 0, -1, 1, -1, 4096 }, /* Special cased */ + { "display-character", -1, -1, -1, -1, -1 }, + { "ibm,display-message", -1, 0, -1, -1, -1 }, + { "ibm,errinjct", -1, 2, -1, -1, -1, 1024 }, + { "ibm,close-errinjct", -1, -1, -1, -1, -1 }, + { "ibm,open-errinct", -1, -1, -1, -1, -1 }, + { "ibm,get-config-addr-info2", -1, -1, -1, -1, -1 }, + { "ibm,get-dynamic-sensor-state", -1, 1, -1, -1, -1 }, + { "ibm,get-indices", -1, 2, 3, -1, -1 }, + { "get-power-level", -1, -1, -1, -1, -1 }, + { "get-sensor-state", -1, -1, -1, -1, -1 }, + { "ibm,get-system-parameter", -1, 1, 2, -1, -1 }, + { "get-time-of-day", -1, -1, -1, -1, -1 }, + { "ibm,get-vpd", -1, 0, -1, 1, 2 }, + { "ibm,lpar-perftools", -1, 2, 3, -1, -1 }, + { "ibm,platform-dump", -1, 4, 5, -1, -1 }, + { "ibm,read-slot-reset-state", -1, -1, -1, -1, -1 }, + { "ibm,scan-log-dump", -1, 0, 1, -1, -1 }, + { "ibm,set-dynamic-indicator", -1, 2, -1, -1, -1 }, + { "ibm,set-eeh-option", -1, -1, -1, -1, -1 }, + { "set-indicator", -1, -1, -1, -1, -1 }, + { "set-power-level", -1, -1, -1, -1, -1 }, + { "set-time-for-power-on", -1, -1, -1, -1, -1 }, + { "ibm,set-system-parameter", -1, 1, -1, -1, -1 }, + { "set-time-of-day", -1, -1, -1, -1, -1 }, + { "ibm,suspend-me", -1, -1, -1, -1, -1 }, + { "ibm,update-nodes", -1, 0, -1, -1, -1, 4096 }, + { "ibm,update-properties", -1, 0, -1, -1, -1, 4096 }, + { "ibm,physical-attestation", -1, 0, 1, -1, -1 }, +}; + +static bool in_rmo_buf(u32 base, u32 end) +{ + return base >= rtas_rmo_buf && + base < (rtas_rmo_buf + RTAS_RMOBUF_MAX) && + base <= end && + end >= rtas_rmo_buf && + end < (rtas_rmo_buf + RTAS_RMOBUF_MAX); +} + +static bool block_rtas_call(int token, int nargs, + struct rtas_args *args) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(rtas_filters); i++) { + struct rtas_filter *f = &rtas_filters[i]; + u32 base, size, end; + + if (token != f->token) + continue; + + if (f->buf_idx1 != -1) { + base = be32_to_cpu(args->args[f->buf_idx1]); + if (f->size_idx1 != -1) + size = be32_to_cpu(args->args[f->size_idx1]); + else if (f->fixed_size) + size = f->fixed_size; + else + size = 1; + + end = base + size - 1; + if (!in_rmo_buf(base, end)) + goto err; + } + + if (f->buf_idx2 != -1) { + base = be32_to_cpu(args->args[f->buf_idx2]); + if (f->size_idx2 != -1) + size = be32_to_cpu(args->args[f->size_idx2]); + else if (f->fixed_size) + size = f->fixed_size; + else + size = 1; + end = base + size - 1; + + /* + * Special case for ibm,configure-connector where the + * address can be 0 + */ + if (!strcmp(f->name, "ibm,configure-connector") && + base == 0) + return false; + + if (!in_rmo_buf(base, end)) + goto err; + } + + return false; + } + +err: + pr_err_ratelimited("sys_rtas: RTAS call blocked - exploit attempt?\n"); + pr_err_ratelimited("sys_rtas: token=0x%x, nargs=%d (called by %s)\n", + token, nargs, current->comm); + return true; +} + +#else + +static bool block_rtas_call(int token, int nargs, + struct rtas_args *args) +{ + return false; +} + +#endif /* CONFIG_PPC_RTAS_FILTER */ + /* We assume to be passed big endian arguments */ SYSCALL_DEFINE1(rtas, struct rtas_args __user *, uargs) { @@ -977,6 +1118,9 @@ SYSCALL_DEFINE1(rtas, struct rtas_args __user *, uargs) args.rets = &args.args[nargs]; memset(args.rets, 0, nret * sizeof(rtas_arg_t)); + if (block_rtas_call(token, nargs, &args)) + return -EINVAL; + /* Need to handle ibm,suspend_me call specially */ if (token == ibm_suspend_me_token) { @@ -1038,6 +1182,9 @@ void __init rtas_initialize(void) unsigned long rtas_region = RTAS_INSTANTIATE_MAX; u32 base, size, entry; int no_base, no_size, no_entry; +#ifdef CONFIG_PPC_RTAS_FILTER + int i; +#endif /* Get RTAS dev node and fill up our "rtas" structure with infos * about it. @@ -1077,6 +1224,12 @@ void __init rtas_initialize(void) #ifdef CONFIG_RTAS_ERROR_LOGGING rtas_last_error_token = rtas_token("rtas-last-error"); #endif + +#ifdef CONFIG_PPC_RTAS_FILTER + for (i = 0; i < ARRAY_SIZE(rtas_filters); i++) { + rtas_filters[i].token = rtas_token(rtas_filters[i].name); + } +#endif } int __init early_init_dt_scan_rtas(unsigned long node, diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c index 80a676da11cb..f08ca604a394 100644 --- a/arch/powerpc/kernel/sysfs.c +++ b/arch/powerpc/kernel/sysfs.c @@ -31,29 +31,27 @@ static DEFINE_PER_CPU(struct cpu, cpu_devices); -/* - * SMT snooze delay stuff, 64-bit only for now - */ - #ifdef CONFIG_PPC64 -/* Time in microseconds we delay before sleeping in the idle loop */ -static DEFINE_PER_CPU(long, smt_snooze_delay) = { 100 }; +/* + * Snooze delay has not been hooked up since 3fa8cad82b94 ("powerpc/pseries/cpuidle: + * smt-snooze-delay cleanup.") and has been broken even longer. As was foretold in + * 2014: + * + * "ppc64_util currently utilises it. Once we fix ppc64_util, propose to clean + * up the kernel code." + * + * powerpc-utils stopped using it as of 1.3.8. At some point in the future this + * code should be removed. + */ static ssize_t store_smt_snooze_delay(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { - struct cpu *cpu = container_of(dev, struct cpu, dev); - ssize_t ret; - long snooze; - - ret = sscanf(buf, "%ld", &snooze); - if (ret != 1) - return -EINVAL; - - per_cpu(smt_snooze_delay, cpu->dev.id) = snooze; + pr_warn_once("%s (%d) stored to unsupported smt_snooze_delay, which has no effect.\n", + current->comm, current->pid); return count; } @@ -61,9 +59,9 @@ static ssize_t show_smt_snooze_delay(struct device *dev, struct device_attribute *attr, char *buf) { - struct cpu *cpu = container_of(dev, struct cpu, dev); - - return sprintf(buf, "%ld\n", per_cpu(smt_snooze_delay, cpu->dev.id)); + pr_warn_once("%s (%d) read from unsupported smt_snooze_delay\n", + current->comm, current->pid); + return sprintf(buf, "100\n"); } static DEVICE_ATTR(smt_snooze_delay, 0644, show_smt_snooze_delay, @@ -71,16 +69,10 @@ static DEVICE_ATTR(smt_snooze_delay, 0644, show_smt_snooze_delay, static int __init setup_smt_snooze_delay(char *str) { - unsigned int cpu; - long snooze; - if (!cpu_has_feature(CPU_FTR_SMT)) return 1; - snooze = simple_strtol(str, NULL, 10); - for_each_possible_cpu(cpu) - per_cpu(smt_snooze_delay, cpu) = snooze; - + pr_warn("smt-snooze-delay command line option has no effect\n"); return 1; } __setup("smt-snooze-delay=", setup_smt_snooze_delay); diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index 9432fc6af28a..206032c9b545 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -877,7 +877,7 @@ static void p9_hmi_special_emu(struct pt_regs *regs) { unsigned int ra, rb, t, i, sel, instr, rc; const void __user *addr; - u8 vbuf[16], *vdst; + u8 vbuf[16] __aligned(16), *vdst; unsigned long ea, msr, msr_mask; bool swap; diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index e2183fed947d..dd9b19b1f459 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -5191,6 +5191,12 @@ static long kvm_arch_vm_ioctl_hv(struct file *filp, case KVM_PPC_ALLOCATE_HTAB: { u32 htab_order; + /* If we're a nested hypervisor, we currently only support radix */ + if (kvmhv_on_pseries()) { + r = -EOPNOTSUPP; + break; + } + r = -EFAULT; if (get_user(htab_order, (u32 __user *)argp)) break; diff --git a/arch/powerpc/platforms/powermac/sleep.S b/arch/powerpc/platforms/powermac/sleep.S index bd6085b470b7..935dcac4c02d 100644 --- a/arch/powerpc/platforms/powermac/sleep.S +++ b/arch/powerpc/platforms/powermac/sleep.S @@ -293,14 +293,7 @@ grackle_wake_up: * we do any r1 memory access as we are not sure they * are in a sane state above the first 256Mb region */ - li r0,16 /* load up segment register values */ - mtctr r0 /* for context 0 */ - lis r3,0x2000 /* Ku = 1, VSID = 0 */ - li r4,0 -3: mtsrin r3,r4 - addi r3,r3,0x111 /* increment VSID */ - addis r4,r4,0x1000 /* address of next segment */ - bdnz 3b + bl load_segment_registers sync isync diff --git a/arch/powerpc/platforms/powernv/opal-elog.c b/arch/powerpc/platforms/powernv/opal-elog.c index 62ef7ad995da..5e33b1fc67c2 100644 --- a/arch/powerpc/platforms/powernv/opal-elog.c +++ b/arch/powerpc/platforms/powernv/opal-elog.c @@ -179,14 +179,14 @@ static ssize_t raw_attr_read(struct file *filep, struct kobject *kobj, return count; } -static struct elog_obj *create_elog_obj(uint64_t id, size_t size, uint64_t type) +static void create_elog_obj(uint64_t id, size_t size, uint64_t type) { struct elog_obj *elog; int rc; elog = kzalloc(sizeof(*elog), GFP_KERNEL); if (!elog) - return NULL; + return; elog->kobj.kset = elog_kset; @@ -219,18 +219,37 @@ static struct elog_obj *create_elog_obj(uint64_t id, size_t size, uint64_t type) rc = kobject_add(&elog->kobj, NULL, "0x%llx", id); if (rc) { kobject_put(&elog->kobj); - return NULL; + return; } + /* + * As soon as the sysfs file for this elog is created/activated there is + * a chance the opal_errd daemon (or any userspace) might read and + * acknowledge the elog before kobject_uevent() is called. If that + * happens then there is a potential race between + * elog_ack_store->kobject_put() and kobject_uevent() which leads to a + * use-after-free of a kernfs object resulting in a kernel crash. + * + * To avoid that, we need to take a reference on behalf of the bin file, + * so that our reference remains valid while we call kobject_uevent(). + * We then drop our reference before exiting the function, leaving the + * bin file to drop the last reference (if it hasn't already). + */ + + /* Take a reference for the bin file */ + kobject_get(&elog->kobj); rc = sysfs_create_bin_file(&elog->kobj, &elog->raw_attr); - if (rc) { + if (rc == 0) { + kobject_uevent(&elog->kobj, KOBJ_ADD); + } else { + /* Drop the reference taken for the bin file */ kobject_put(&elog->kobj); - return NULL; } - kobject_uevent(&elog->kobj, KOBJ_ADD); + /* Drop our reference */ + kobject_put(&elog->kobj); - return elog; + return; } static irqreturn_t elog_event(int irq, void *data) diff --git a/arch/powerpc/platforms/powernv/smp.c b/arch/powerpc/platforms/powernv/smp.c index b2ba3e95bda7..bbf361f23ae8 100644 --- a/arch/powerpc/platforms/powernv/smp.c +++ b/arch/powerpc/platforms/powernv/smp.c @@ -43,7 +43,7 @@ #include <asm/udbg.h> #define DBG(fmt...) udbg_printf(fmt) #else -#define DBG(fmt...) +#define DBG(fmt...) do { } while (0) #endif static void pnv_smp_setup_cpu(int cpu) diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c index 66b32f46702d..f364909d0c08 100644 --- a/arch/powerpc/platforms/pseries/hotplug-memory.c +++ b/arch/powerpc/platforms/pseries/hotplug-memory.c @@ -279,7 +279,7 @@ static int dlpar_offline_lmb(struct drmem_lmb *lmb) return dlpar_change_lmb_state(lmb, false); } -static int pseries_remove_memblock(unsigned long base, unsigned int memblock_size) +static int pseries_remove_memblock(unsigned long base, unsigned long memblock_size) { unsigned long block_sz, start_pfn; int sections_per_block; @@ -310,10 +310,11 @@ static int pseries_remove_memblock(unsigned long base, unsigned int memblock_siz static int pseries_remove_mem_node(struct device_node *np) { - const __be32 *regs; + const __be32 *prop; unsigned long base; - unsigned int lmb_size; + unsigned long lmb_size; int ret = -EINVAL; + int addr_cells, size_cells; /* * Check to see if we are actually removing memory @@ -324,12 +325,19 @@ static int pseries_remove_mem_node(struct device_node *np) /* * Find the base address and size of the memblock */ - regs = of_get_property(np, "reg", NULL); - if (!regs) + prop = of_get_property(np, "reg", NULL); + if (!prop) return ret; - base = be64_to_cpu(*(unsigned long *)regs); - lmb_size = be32_to_cpu(regs[3]); + addr_cells = of_n_addr_cells(np); + size_cells = of_n_size_cells(np); + + /* + * "reg" property represents (addr,size) tuple. + */ + base = of_read_number(prop, addr_cells); + prop += addr_cells; + lmb_size = of_read_number(prop, size_cells); pseries_remove_memblock(base, lmb_size); return 0; @@ -620,7 +628,7 @@ static int dlpar_memory_remove_by_ic(u32 lmbs_to_remove, u32 drc_index) #else static inline int pseries_remove_memblock(unsigned long base, - unsigned int memblock_size) + unsigned long memblock_size) { return -EOPNOTSUPP; } @@ -953,10 +961,11 @@ int dlpar_memory(struct pseries_hp_errorlog *hp_elog) static int pseries_add_mem_node(struct device_node *np) { - const __be32 *regs; + const __be32 *prop; unsigned long base; - unsigned int lmb_size; + unsigned long lmb_size; int ret = -EINVAL; + int addr_cells, size_cells; /* * Check to see if we are actually adding memory @@ -967,12 +976,18 @@ static int pseries_add_mem_node(struct device_node *np) /* * Find the base and size of the memblock */ - regs = of_get_property(np, "reg", NULL); - if (!regs) + prop = of_get_property(np, "reg", NULL); + if (!prop) return ret; - base = be64_to_cpu(*(unsigned long *)regs); - lmb_size = be32_to_cpu(regs[3]); + addr_cells = of_n_addr_cells(np); + size_cells = of_n_size_cells(np); + /* + * "reg" property represents (addr,size) tuple. + */ + base = of_read_number(prop, addr_cells); + prop += addr_cells; + lmb_size = of_read_number(prop, size_cells); /* * Update memory region to represent the memory add diff --git a/arch/riscv/include/uapi/asm/auxvec.h b/arch/riscv/include/uapi/asm/auxvec.h index d86cb17bbabe..22e0ae888406 100644 --- a/arch/riscv/include/uapi/asm/auxvec.h +++ b/arch/riscv/include/uapi/asm/auxvec.h @@ -10,4 +10,7 @@ /* vDSO location */ #define AT_SYSINFO_EHDR 33 +/* entries in ARCH_DLINFO */ +#define AT_VECTOR_SIZE_ARCH 1 + #endif /* _UAPI_ASM_RISCV_AUXVEC_H */ diff --git a/arch/s390/boot/head.S b/arch/s390/boot/head.S index 4b86a8d3c121..e6bf5f40bff3 100644 --- a/arch/s390/boot/head.S +++ b/arch/s390/boot/head.S @@ -360,22 +360,23 @@ ENTRY(startup_kdump) # the save area and does disabled wait with a faulty address. # ENTRY(startup_pgm_check_handler) - stmg %r0,%r15,__LC_SAVE_AREA_SYNC - la %r1,4095 - stctg %c0,%c15,__LC_CREGS_SAVE_AREA-4095(%r1) - mvc __LC_GPREGS_SAVE_AREA-4095(128,%r1),__LC_SAVE_AREA_SYNC - mvc __LC_PSW_SAVE_AREA-4095(16,%r1),__LC_PGM_OLD_PSW + stmg %r8,%r15,__LC_SAVE_AREA_SYNC + la %r8,4095 + stctg %c0,%c15,__LC_CREGS_SAVE_AREA-4095(%r8) + stmg %r0,%r7,__LC_GPREGS_SAVE_AREA-4095(%r8) + mvc __LC_GPREGS_SAVE_AREA-4095+64(64,%r8),__LC_SAVE_AREA_SYNC + mvc __LC_PSW_SAVE_AREA-4095(16,%r8),__LC_PGM_OLD_PSW mvc __LC_RETURN_PSW(16),__LC_PGM_OLD_PSW ni __LC_RETURN_PSW,0xfc # remove IO and EX bits ni __LC_RETURN_PSW+1,0xfb # remove MCHK bit oi __LC_RETURN_PSW+1,0x2 # set wait state bit - larl %r2,.Lold_psw_disabled_wait - stg %r2,__LC_PGM_NEW_PSW+8 - l %r15,.Ldump_info_stack-.Lold_psw_disabled_wait(%r2) + larl %r9,.Lold_psw_disabled_wait + stg %r9,__LC_PGM_NEW_PSW+8 + l %r15,.Ldump_info_stack-.Lold_psw_disabled_wait(%r9) brasl %r14,print_pgm_check_info .Lold_psw_disabled_wait: - la %r1,4095 - lmg %r0,%r15,__LC_GPREGS_SAVE_AREA-4095(%r1) + la %r8,4095 + lmg %r0,%r15,__LC_GPREGS_SAVE_AREA-4095(%r8) lpswe __LC_RETURN_PSW # disabled wait .Ldump_info_stack: .long 0x5000 + PAGE_SIZE - STACK_FRAME_OVERHEAD diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c index 8ea9db599d38..11c32b228f51 100644 --- a/arch/s390/kernel/time.c +++ b/arch/s390/kernel/time.c @@ -354,8 +354,9 @@ static DEFINE_PER_CPU(atomic_t, clock_sync_word); static DEFINE_MUTEX(clock_sync_mutex); static unsigned long clock_sync_flags; -#define CLOCK_SYNC_HAS_STP 0 -#define CLOCK_SYNC_STP 1 +#define CLOCK_SYNC_HAS_STP 0 +#define CLOCK_SYNC_STP 1 +#define CLOCK_SYNC_STPINFO_VALID 2 /* * The get_clock function for the physical clock. It will get the current @@ -592,6 +593,22 @@ void stp_queue_work(void) queue_work(time_sync_wq, &stp_work); } +static int __store_stpinfo(void) +{ + int rc = chsc_sstpi(stp_page, &stp_info, sizeof(struct stp_sstpi)); + + if (rc) + clear_bit(CLOCK_SYNC_STPINFO_VALID, &clock_sync_flags); + else + set_bit(CLOCK_SYNC_STPINFO_VALID, &clock_sync_flags); + return rc; +} + +static int stpinfo_valid(void) +{ + return stp_online && test_bit(CLOCK_SYNC_STPINFO_VALID, &clock_sync_flags); +} + static int stp_sync_clock(void *data) { struct clock_sync_data *sync = data; @@ -613,8 +630,7 @@ static int stp_sync_clock(void *data) if (rc == 0) { sync->clock_delta = clock_delta; clock_sync_global(clock_delta); - rc = chsc_sstpi(stp_page, &stp_info, - sizeof(struct stp_sstpi)); + rc = __store_stpinfo(); if (rc == 0 && stp_info.tmd != 2) rc = -EAGAIN; } @@ -659,7 +675,7 @@ static void stp_work_fn(struct work_struct *work) if (rc) goto out_unlock; - rc = chsc_sstpi(stp_page, &stp_info, sizeof(struct stp_sstpi)); + rc = __store_stpinfo(); if (rc || stp_info.c == 0) goto out_unlock; @@ -696,10 +712,14 @@ static ssize_t stp_ctn_id_show(struct device *dev, struct device_attribute *attr, char *buf) { - if (!stp_online) - return -ENODATA; - return sprintf(buf, "%016llx\n", - *(unsigned long long *) stp_info.ctnid); + ssize_t ret = -ENODATA; + + mutex_lock(&stp_work_mutex); + if (stpinfo_valid()) + ret = sprintf(buf, "%016llx\n", + *(unsigned long long *) stp_info.ctnid); + mutex_unlock(&stp_work_mutex); + return ret; } static DEVICE_ATTR(ctn_id, 0400, stp_ctn_id_show, NULL); @@ -708,9 +728,13 @@ static ssize_t stp_ctn_type_show(struct device *dev, struct device_attribute *attr, char *buf) { - if (!stp_online) - return -ENODATA; - return sprintf(buf, "%i\n", stp_info.ctn); + ssize_t ret = -ENODATA; + + mutex_lock(&stp_work_mutex); + if (stpinfo_valid()) + ret = sprintf(buf, "%i\n", stp_info.ctn); + mutex_unlock(&stp_work_mutex); + return ret; } static DEVICE_ATTR(ctn_type, 0400, stp_ctn_type_show, NULL); @@ -719,9 +743,13 @@ static ssize_t stp_dst_offset_show(struct device *dev, struct device_attribute *attr, char *buf) { - if (!stp_online || !(stp_info.vbits & 0x2000)) - return -ENODATA; - return sprintf(buf, "%i\n", (int)(s16) stp_info.dsto); + ssize_t ret = -ENODATA; + + mutex_lock(&stp_work_mutex); + if (stpinfo_valid() && (stp_info.vbits & 0x2000)) + ret = sprintf(buf, "%i\n", (int)(s16) stp_info.dsto); + mutex_unlock(&stp_work_mutex); + return ret; } static DEVICE_ATTR(dst_offset, 0400, stp_dst_offset_show, NULL); @@ -730,9 +758,13 @@ static ssize_t stp_leap_seconds_show(struct device *dev, struct device_attribute *attr, char *buf) { - if (!stp_online || !(stp_info.vbits & 0x8000)) - return -ENODATA; - return sprintf(buf, "%i\n", (int)(s16) stp_info.leaps); + ssize_t ret = -ENODATA; + + mutex_lock(&stp_work_mutex); + if (stpinfo_valid() && (stp_info.vbits & 0x8000)) + ret = sprintf(buf, "%i\n", (int)(s16) stp_info.leaps); + mutex_unlock(&stp_work_mutex); + return ret; } static DEVICE_ATTR(leap_seconds, 0400, stp_leap_seconds_show, NULL); @@ -741,9 +773,13 @@ static ssize_t stp_stratum_show(struct device *dev, struct device_attribute *attr, char *buf) { - if (!stp_online) - return -ENODATA; - return sprintf(buf, "%i\n", (int)(s16) stp_info.stratum); + ssize_t ret = -ENODATA; + + mutex_lock(&stp_work_mutex); + if (stpinfo_valid()) + ret = sprintf(buf, "%i\n", (int)(s16) stp_info.stratum); + mutex_unlock(&stp_work_mutex); + return ret; } static DEVICE_ATTR(stratum, 0400, stp_stratum_show, NULL); @@ -752,9 +788,13 @@ static ssize_t stp_time_offset_show(struct device *dev, struct device_attribute *attr, char *buf) { - if (!stp_online || !(stp_info.vbits & 0x0800)) - return -ENODATA; - return sprintf(buf, "%i\n", (int) stp_info.tto); + ssize_t ret = -ENODATA; + + mutex_lock(&stp_work_mutex); + if (stpinfo_valid() && (stp_info.vbits & 0x0800)) + ret = sprintf(buf, "%i\n", (int) stp_info.tto); + mutex_unlock(&stp_work_mutex); + return ret; } static DEVICE_ATTR(time_offset, 0400, stp_time_offset_show, NULL); @@ -763,9 +803,13 @@ static ssize_t stp_time_zone_offset_show(struct device *dev, struct device_attribute *attr, char *buf) { - if (!stp_online || !(stp_info.vbits & 0x4000)) - return -ENODATA; - return sprintf(buf, "%i\n", (int)(s16) stp_info.tzo); + ssize_t ret = -ENODATA; + + mutex_lock(&stp_work_mutex); + if (stpinfo_valid() && (stp_info.vbits & 0x4000)) + ret = sprintf(buf, "%i\n", (int)(s16) stp_info.tzo); + mutex_unlock(&stp_work_mutex); + return ret; } static DEVICE_ATTR(time_zone_offset, 0400, @@ -775,9 +819,13 @@ static ssize_t stp_timing_mode_show(struct device *dev, struct device_attribute *attr, char *buf) { - if (!stp_online) - return -ENODATA; - return sprintf(buf, "%i\n", stp_info.tmd); + ssize_t ret = -ENODATA; + + mutex_lock(&stp_work_mutex); + if (stpinfo_valid()) + ret = sprintf(buf, "%i\n", stp_info.tmd); + mutex_unlock(&stp_work_mutex); + return ret; } static DEVICE_ATTR(timing_mode, 0400, stp_timing_mode_show, NULL); @@ -786,9 +834,13 @@ static ssize_t stp_timing_state_show(struct device *dev, struct device_attribute *attr, char *buf) { - if (!stp_online) - return -ENODATA; - return sprintf(buf, "%i\n", stp_info.tst); + ssize_t ret = -ENODATA; + + mutex_lock(&stp_work_mutex); + if (stpinfo_valid()) + ret = sprintf(buf, "%i\n", stp_info.tst); + mutex_unlock(&stp_work_mutex); + return ret; } static DEVICE_ATTR(timing_state, 0400, stp_timing_state_show, NULL); diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c index a8275fea4b70..aa81c25b44cf 100644 --- a/arch/sparc/kernel/smp_64.c +++ b/arch/sparc/kernel/smp_64.c @@ -1039,38 +1039,9 @@ void smp_fetch_global_pmu(void) * are flush_tlb_*() routines, and these run after flush_cache_*() * which performs the flushw. * - * The SMP TLB coherency scheme we use works as follows: - * - * 1) mm->cpu_vm_mask is a bit mask of which cpus an address - * space has (potentially) executed on, this is the heuristic - * we use to avoid doing cross calls. - * - * Also, for flushing from kswapd and also for clones, we - * use cpu_vm_mask as the list of cpus to make run the TLB. - * - * 2) TLB context numbers are shared globally across all processors - * in the system, this allows us to play several games to avoid - * cross calls. - * - * One invariant is that when a cpu switches to a process, and - * that processes tsk->active_mm->cpu_vm_mask does not have the - * current cpu's bit set, that tlb context is flushed locally. - * - * If the address space is non-shared (ie. mm->count == 1) we avoid - * cross calls when we want to flush the currently running process's - * tlb state. This is done by clearing all cpu bits except the current - * processor's in current->mm->cpu_vm_mask and performing the - * flush locally only. This will force any subsequent cpus which run - * this task to flush the context from the local tlb if the process - * migrates to another cpu (again). - * - * 3) For shared address spaces (threads) and swapping we bite the - * bullet for most cases and perform the cross call (but only to - * the cpus listed in cpu_vm_mask). - * - * The performance gain from "optimizing" away the cross call for threads is - * questionable (in theory the big win for threads is the massive sharing of - * address space state across processors). + * mm->cpu_vm_mask is a bit mask of which cpus an address + * space has (potentially) executed on, this is the heuristic + * we use to limit cross calls. */ /* This currently is only used by the hugetlb arch pre-fault @@ -1080,18 +1051,13 @@ void smp_fetch_global_pmu(void) void smp_flush_tlb_mm(struct mm_struct *mm) { u32 ctx = CTX_HWBITS(mm->context); - int cpu = get_cpu(); - if (atomic_read(&mm->mm_users) == 1) { - cpumask_copy(mm_cpumask(mm), cpumask_of(cpu)); - goto local_flush_and_out; - } + get_cpu(); smp_cross_call_masked(&xcall_flush_tlb_mm, ctx, 0, 0, mm_cpumask(mm)); -local_flush_and_out: __flush_tlb_mm(ctx, SECONDARY_CONTEXT); put_cpu(); @@ -1114,17 +1080,15 @@ void smp_flush_tlb_pending(struct mm_struct *mm, unsigned long nr, unsigned long { u32 ctx = CTX_HWBITS(mm->context); struct tlb_pending_info info; - int cpu = get_cpu(); + + get_cpu(); info.ctx = ctx; info.nr = nr; info.vaddrs = vaddrs; - if (mm == current->mm && atomic_read(&mm->mm_users) == 1) - cpumask_copy(mm_cpumask(mm), cpumask_of(cpu)); - else - smp_call_function_many(mm_cpumask(mm), tlb_pending_func, - &info, 1); + smp_call_function_many(mm_cpumask(mm), tlb_pending_func, + &info, 1); __flush_tlb_pending(ctx, nr, vaddrs); @@ -1134,14 +1098,13 @@ void smp_flush_tlb_pending(struct mm_struct *mm, unsigned long nr, unsigned long void smp_flush_tlb_page(struct mm_struct *mm, unsigned long vaddr) { unsigned long context = CTX_HWBITS(mm->context); - int cpu = get_cpu(); - if (mm == current->mm && atomic_read(&mm->mm_users) == 1) - cpumask_copy(mm_cpumask(mm), cpumask_of(cpu)); - else - smp_cross_call_masked(&xcall_flush_tlb_page, - context, vaddr, 0, - mm_cpumask(mm)); + get_cpu(); + + smp_cross_call_masked(&xcall_flush_tlb_page, + context, vaddr, 0, + mm_cpumask(mm)); + __flush_tlb_page(context, vaddr); put_cpu(); diff --git a/arch/um/kernel/sigio.c b/arch/um/kernel/sigio.c index 10c99e058fca..d1cffc2a7f21 100644 --- a/arch/um/kernel/sigio.c +++ b/arch/um/kernel/sigio.c @@ -35,14 +35,14 @@ int write_sigio_irq(int fd) } /* These are called from os-Linux/sigio.c to protect its pollfds arrays. */ -static DEFINE_SPINLOCK(sigio_spinlock); +static DEFINE_MUTEX(sigio_mutex); void sigio_lock(void) { - spin_lock(&sigio_spinlock); + mutex_lock(&sigio_mutex); } void sigio_unlock(void) { - spin_unlock(&sigio_spinlock); + mutex_unlock(&sigio_mutex); } diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c index a023cbe21230..39169885adfa 100644 --- a/arch/x86/events/amd/ibs.c +++ b/arch/x86/events/amd/ibs.c @@ -335,11 +335,15 @@ static u64 get_ibs_op_count(u64 config) { u64 count = 0; + /* + * If the internal 27-bit counter rolled over, the count is MaxCnt + * and the lower 7 bits of CurCnt are randomized. + * Otherwise CurCnt has the full 27-bit current counter value. + */ if (config & IBS_OP_VAL) - count += (config & IBS_OP_MAX_CNT) << 4; /* cnt rolled over */ - - if (ibs_caps & IBS_CAPS_RDWROPCNT) - count += (config & IBS_OP_CUR_CNT) >> 32; + count = (config & IBS_OP_MAX_CNT) << 4; + else if (ibs_caps & IBS_CAPS_RDWROPCNT) + count = (config & IBS_OP_CUR_CNT) >> 32; return count; } @@ -632,18 +636,24 @@ static int perf_ibs_handle_irq(struct perf_ibs *perf_ibs, struct pt_regs *iregs) perf_ibs->offset_max, offset + 1); } while (offset < offset_max); + /* + * Read IbsBrTarget, IbsOpData4, and IbsExtdCtl separately + * depending on their availability. + * Can't add to offset_max as they are staggered + */ if (event->attr.sample_type & PERF_SAMPLE_RAW) { - /* - * Read IbsBrTarget and IbsOpData4 separately - * depending on their availability. - * Can't add to offset_max as they are staggered - */ - if (ibs_caps & IBS_CAPS_BRNTRGT) { - rdmsrl(MSR_AMD64_IBSBRTARGET, *buf++); - size++; + if (perf_ibs == &perf_ibs_op) { + if (ibs_caps & IBS_CAPS_BRNTRGT) { + rdmsrl(MSR_AMD64_IBSBRTARGET, *buf++); + size++; + } + if (ibs_caps & IBS_CAPS_OPDATA4) { + rdmsrl(MSR_AMD64_IBSOPDATA4, *buf++); + size++; + } } - if (ibs_caps & IBS_CAPS_OPDATA4) { - rdmsrl(MSR_AMD64_IBSOPDATA4, *buf++); + if (perf_ibs == &perf_ibs_fetch && (ibs_caps & IBS_CAPS_FETCHCTLEXTD)) { + rdmsrl(MSR_AMD64_ICIBSEXTDCTL, *buf++); size++; } } diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 0461ab257df6..c4def9077747 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -243,7 +243,7 @@ static struct extra_reg intel_skl_extra_regs[] __read_mostly = { static struct event_constraint intel_icl_event_constraints[] = { FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */ - INTEL_UEVENT_CONSTRAINT(0x1c0, 0), /* INST_RETIRED.PREC_DIST */ + FIXED_EVENT_CONSTRAINT(0x01c0, 0), /* INST_RETIRED.PREC_DIST */ FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */ FIXED_EVENT_CONSTRAINT(0x0300, 2), /* CPU_CLK_UNHALTED.REF */ FIXED_EVENT_CONSTRAINT(0x0400, 3), /* SLOTS */ diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 391812e0384e..f312b6f6ac48 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -432,6 +432,7 @@ #define MSR_AMD64_IBSOP_REG_MASK ((1UL<<MSR_AMD64_IBSOP_REG_COUNT)-1) #define MSR_AMD64_IBSCTL 0xc001103a #define MSR_AMD64_IBSBRTARGET 0xc001103b +#define MSR_AMD64_ICIBSEXTDCTL 0xc001103c #define MSR_AMD64_IBSOPDATA4 0xc001103d #define MSR_AMD64_IBS_REG_COUNT_MAX 8 /* includes MSR_AMD64_IBSBRTARGET */ #define MSR_AMD64_SEV 0xc0010131 diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c index 187a86e0e753..f29f015a5e7f 100644 --- a/arch/x86/kernel/unwind_orc.c +++ b/arch/x86/kernel/unwind_orc.c @@ -311,19 +311,12 @@ EXPORT_SYMBOL_GPL(unwind_get_return_address); unsigned long *unwind_get_return_address_ptr(struct unwind_state *state) { - struct task_struct *task = state->task; - if (unwind_done(state)) return NULL; if (state->regs) return &state->regs->ip; - if (task != current && state->sp == task->thread.sp) { - struct inactive_task_frame *frame = (void *)task->thread.sp; - return &frame->ret_addr; - } - if (state->sp) return (unsigned long *)state->sp - 1; @@ -653,7 +646,7 @@ void __unwind_start(struct unwind_state *state, struct task_struct *task, } else { struct inactive_task_frame *frame = (void *)task->thread.sp; - state->sp = task->thread.sp; + state->sp = task->thread.sp + sizeof(*frame); state->bp = READ_ONCE_NOCHECK(frame->bp); state->ip = READ_ONCE_NOCHECK(frame->ret_addr); state->signal = (void *)state->ip == ret_from_fork; diff --git a/drivers/acpi/acpi_dbg.c b/drivers/acpi/acpi_dbg.c index 7a265c2171c0..cc4b509bad94 100644 --- a/drivers/acpi/acpi_dbg.c +++ b/drivers/acpi/acpi_dbg.c @@ -749,6 +749,9 @@ int __init acpi_aml_init(void) { int ret; + if (acpi_disabled) + return -ENODEV; + /* Initialize AML IO interface */ mutex_init(&acpi_aml_io.lock); init_waitqueue_head(&acpi_aml_io.wait); diff --git a/drivers/acpi/acpi_extlog.c b/drivers/acpi/acpi_extlog.c index 8596a106a933..91d0b0fc392b 100644 --- a/drivers/acpi/acpi_extlog.c +++ b/drivers/acpi/acpi_extlog.c @@ -223,9 +223,9 @@ static int __init extlog_init(void) u64 cap; int rc; - rdmsrl(MSR_IA32_MCG_CAP, cap); - - if (!(cap & MCG_ELOG_P) || !extlog_get_l1addr()) + if (rdmsrl_safe(MSR_IA32_MCG_CAP, &cap) || + !(cap & MCG_ELOG_P) || + !extlog_get_l1addr()) return -ENODEV; if (edac_get_report_status() == EDAC_REPORTING_FORCE) { diff --git a/drivers/acpi/button.c b/drivers/acpi/button.c index 985afc62da82..690bfe67e643 100644 --- a/drivers/acpi/button.c +++ b/drivers/acpi/button.c @@ -136,6 +136,7 @@ struct acpi_button { int last_state; ktime_t last_time; bool suspended; + bool lid_state_initialized; }; static BLOCKING_NOTIFIER_HEAD(acpi_lid_notifier); @@ -391,6 +392,8 @@ static int acpi_lid_update_state(struct acpi_device *device, static void acpi_lid_initialize_state(struct acpi_device *device) { + struct acpi_button *button = acpi_driver_data(device); + switch (lid_init_state) { case ACPI_BUTTON_LID_INIT_OPEN: (void)acpi_lid_notify_state(device, 1); @@ -402,13 +405,14 @@ static void acpi_lid_initialize_state(struct acpi_device *device) default: break; } + + button->lid_state_initialized = true; } static void acpi_button_notify(struct acpi_device *device, u32 event) { struct acpi_button *button = acpi_driver_data(device); struct input_dev *input; - int users; switch (event) { case ACPI_FIXED_HARDWARE_EVENT: @@ -417,10 +421,7 @@ static void acpi_button_notify(struct acpi_device *device, u32 event) case ACPI_BUTTON_NOTIFY_STATUS: input = button->input; if (button->type == ACPI_BUTTON_TYPE_LID) { - mutex_lock(&button->input->mutex); - users = button->input->users; - mutex_unlock(&button->input->mutex); - if (users) + if (button->lid_state_initialized) acpi_lid_update_state(device, true); } else { int keycode; @@ -465,7 +466,7 @@ static int acpi_button_resume(struct device *dev) struct acpi_button *button = acpi_driver_data(device); button->suspended = false; - if (button->type == ACPI_BUTTON_TYPE_LID && button->input->users) { + if (button->type == ACPI_BUTTON_TYPE_LID) { button->last_state = !!acpi_lid_evaluate_state(device); button->last_time = ktime_get(); acpi_lid_initialize_state(device); diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c index 1ec55345252b..c64001e789ed 100644 --- a/drivers/acpi/ec.c +++ b/drivers/acpi/ec.c @@ -1968,20 +1968,16 @@ bool acpi_ec_dispatch_gpe(void) if (acpi_any_gpe_status_set(first_ec->gpe)) return true; - if (ec_no_wakeup) - return false; - /* * Dispatch the EC GPE in-band, but do not report wakeup in any case * to allow the caller to process events properly after that. */ ret = acpi_dispatch_gpe(NULL, first_ec->gpe); - if (ret == ACPI_INTERRUPT_HANDLED) { + if (ret == ACPI_INTERRUPT_HANDLED) pm_pr_dbg("EC GPE dispatched\n"); - /* Flush the event and query workqueues. */ - acpi_ec_flush_work(); - } + /* Flush the event and query workqueues. */ + acpi_ec_flush_work(); return false; } diff --git a/drivers/acpi/hmat/hmat.c b/drivers/acpi/hmat/hmat.c index 8b0de8a3c647..0f1c939b7e90 100644 --- a/drivers/acpi/hmat/hmat.c +++ b/drivers/acpi/hmat/hmat.c @@ -403,7 +403,8 @@ static int __init hmat_parse_proximity_domain(union acpi_subtable_headers *heade pr_info("HMAT: Memory Flags:%04x Processor Domain:%d Memory Domain:%d\n", p->flags, p->processor_PD, p->memory_PD); - if (p->flags & ACPI_HMAT_MEMORY_PD_VALID && hmat_revision == 1) { + if ((hmat_revision == 1 && p->flags & ACPI_HMAT_MEMORY_PD_VALID) || + hmat_revision > 1) { target = find_mem_target(p->memory_PD); if (!target) { pr_debug("HMAT: Memory Domain missing from SRAT\n"); diff --git a/drivers/acpi/numa.c b/drivers/acpi/numa.c index eadbf90e65d1..85e01752fbe4 100644 --- a/drivers/acpi/numa.c +++ b/drivers/acpi/numa.c @@ -31,7 +31,7 @@ int acpi_numa __initdata; int pxm_to_node(int pxm) { - if (pxm < 0) + if (pxm < 0 || pxm >= MAX_PXM_DOMAINS || numa_off) return NUMA_NO_NODE; return pxm_to_node_map[pxm]; } diff --git a/drivers/acpi/video_detect.c b/drivers/acpi/video_detect.c index 5bcb4c01ec5f..55af78b55c51 100644 --- a/drivers/acpi/video_detect.c +++ b/drivers/acpi/video_detect.c @@ -282,6 +282,15 @@ static const struct dmi_system_id video_detect_dmi_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "530U4E/540U4E"), }, }, + /* https://bugs.launchpad.net/bugs/1894667 */ + { + .callback = video_detect_force_video, + .ident = "HP 635 Notebook", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"), + DMI_MATCH(DMI_PRODUCT_NAME, "HP 635 Notebook PC"), + }, + }, /* Non win8 machines which need native backlight nevertheless */ { diff --git a/drivers/ata/sata_nv.c b/drivers/ata/sata_nv.c index 18b147c182b9..0514aa7e80e3 100644 --- a/drivers/ata/sata_nv.c +++ b/drivers/ata/sata_nv.c @@ -2100,7 +2100,7 @@ static int nv_swncq_sdbfis(struct ata_port *ap) pp->dhfis_bits &= ~done_mask; pp->dmafis_bits &= ~done_mask; pp->sdbfis_bits |= done_mask; - ata_qc_complete_multiple(ap, ap->qc_active ^ done_mask); + ata_qc_complete_multiple(ap, ata_qc_get_active(ap) ^ done_mask); if (!ap->qc_active) { DPRINTK("over\n"); diff --git a/drivers/base/core.c b/drivers/base/core.c index 94df2ba1bbed..0fde3e9e63ee 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -3400,6 +3400,7 @@ static inline bool fwnode_is_primary(struct fwnode_handle *fwnode) */ void set_primary_fwnode(struct device *dev, struct fwnode_handle *fwnode) { + struct device *parent = dev->parent; struct fwnode_handle *fn = dev->fwnode; if (fwnode) { @@ -3414,7 +3415,8 @@ void set_primary_fwnode(struct device *dev, struct fwnode_handle *fwnode) } else { if (fwnode_is_primary(fn)) { dev->fwnode = fn->secondary; - fn->secondary = NULL; + if (!(parent && fn == parent->fwnode)) + fn->secondary = ERR_PTR(-ENODEV); } else { dev->fwnode = NULL; } diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c index 48616f358854..4244e22e4b40 100644 --- a/drivers/base/power/runtime.c +++ b/drivers/base/power/runtime.c @@ -291,8 +291,7 @@ static int rpm_get_suppliers(struct device *dev) device_links_read_lock_held()) { int retval; - if (!(link->flags & DL_FLAG_PM_RUNTIME) || - READ_ONCE(link->status) == DL_STATE_SUPPLIER_UNBIND) + if (!(link->flags & DL_FLAG_PM_RUNTIME)) continue; retval = pm_runtime_get_sync(link->supplier); @@ -312,8 +311,6 @@ static void rpm_put_suppliers(struct device *dev) list_for_each_entry_rcu(link, &dev->links.suppliers, c_node, device_links_read_lock_held()) { - if (READ_ONCE(link->status) == DL_STATE_SUPPLIER_UNBIND) - continue; while (refcount_dec_not_one(&link->rpm_active)) pm_runtime_put(link->supplier); diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 7c577cabb9c3..742f8160b6e2 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -787,9 +787,9 @@ static void recv_work(struct work_struct *work) blk_mq_complete_request(blk_mq_rq_from_pdu(cmd)); } + nbd_config_put(nbd); atomic_dec(&config->recv_threads); wake_up(&config->recv_wq); - nbd_config_put(nbd); kfree(args); } diff --git a/drivers/block/xen-blkback/blkback.c b/drivers/block/xen-blkback/blkback.c index 3666afa639d1..b18f0162cb9c 100644 --- a/drivers/block/xen-blkback/blkback.c +++ b/drivers/block/xen-blkback/blkback.c @@ -202,7 +202,7 @@ static inline void shrink_free_pagepool(struct xen_blkif_ring *ring, int num) #define vaddr(page) ((unsigned long)pfn_to_kaddr(page_to_pfn(page))) -static int do_block_io_op(struct xen_blkif_ring *ring); +static int do_block_io_op(struct xen_blkif_ring *ring, unsigned int *eoi_flags); static int dispatch_rw_block_io(struct xen_blkif_ring *ring, struct blkif_request *req, struct pending_req *pending_req); @@ -615,6 +615,8 @@ int xen_blkif_schedule(void *arg) struct xen_vbd *vbd = &blkif->vbd; unsigned long timeout; int ret; + bool do_eoi; + unsigned int eoi_flags = XEN_EOI_FLAG_SPURIOUS; set_freezable(); while (!kthread_should_stop()) { @@ -639,16 +641,23 @@ int xen_blkif_schedule(void *arg) if (timeout == 0) goto purge_gnt_list; + do_eoi = ring->waiting_reqs; + ring->waiting_reqs = 0; smp_mb(); /* clear flag *before* checking for work */ - ret = do_block_io_op(ring); + ret = do_block_io_op(ring, &eoi_flags); if (ret > 0) ring->waiting_reqs = 1; if (ret == -EACCES) wait_event_interruptible(ring->shutdown_wq, kthread_should_stop()); + if (do_eoi && !ring->waiting_reqs) { + xen_irq_lateeoi(ring->irq, eoi_flags); + eoi_flags |= XEN_EOI_FLAG_SPURIOUS; + } + purge_gnt_list: if (blkif->vbd.feature_gnt_persistent && time_after(jiffies, ring->next_lru)) { @@ -1121,7 +1130,7 @@ static void end_block_io_op(struct bio *bio) * and transmute it to the block API to hand it over to the proper block disk. */ static int -__do_block_io_op(struct xen_blkif_ring *ring) +__do_block_io_op(struct xen_blkif_ring *ring, unsigned int *eoi_flags) { union blkif_back_rings *blk_rings = &ring->blk_rings; struct blkif_request req; @@ -1144,6 +1153,9 @@ __do_block_io_op(struct xen_blkif_ring *ring) if (RING_REQUEST_CONS_OVERFLOW(&blk_rings->common, rc)) break; + /* We've seen a request, so clear spurious eoi flag. */ + *eoi_flags &= ~XEN_EOI_FLAG_SPURIOUS; + if (kthread_should_stop()) { more_to_do = 1; break; @@ -1202,13 +1214,13 @@ __do_block_io_op(struct xen_blkif_ring *ring) } static int -do_block_io_op(struct xen_blkif_ring *ring) +do_block_io_op(struct xen_blkif_ring *ring, unsigned int *eoi_flags) { union blkif_back_rings *blk_rings = &ring->blk_rings; int more_to_do; do { - more_to_do = __do_block_io_op(ring); + more_to_do = __do_block_io_op(ring, eoi_flags); if (more_to_do) break; diff --git a/drivers/block/xen-blkback/xenbus.c b/drivers/block/xen-blkback/xenbus.c index c4cd68116e7f..192ca58cc3c7 100644 --- a/drivers/block/xen-blkback/xenbus.c +++ b/drivers/block/xen-blkback/xenbus.c @@ -229,9 +229,8 @@ static int xen_blkif_map(struct xen_blkif_ring *ring, grant_ref_t *gref, BUG(); } - err = bind_interdomain_evtchn_to_irqhandler(blkif->domid, evtchn, - xen_blkif_be_int, 0, - "blkif-backend", ring); + err = bind_interdomain_evtchn_to_irqhandler_lateeoi(blkif->domid, + evtchn, xen_blkif_be_int, 0, "blkif-backend", ring); if (err < 0) { xenbus_unmap_ring_vfree(blkif->be->dev, ring->blk_ring); ring->blk_rings.common.sring = NULL; diff --git a/drivers/bus/fsl-mc/mc-io.c b/drivers/bus/fsl-mc/mc-io.c index d9629fc13a15..0a4a387b615d 100644 --- a/drivers/bus/fsl-mc/mc-io.c +++ b/drivers/bus/fsl-mc/mc-io.c @@ -129,7 +129,12 @@ int __must_check fsl_create_mc_io(struct device *dev, */ void fsl_destroy_mc_io(struct fsl_mc_io *mc_io) { - struct fsl_mc_device *dpmcp_dev = mc_io->dpmcp_dev; + struct fsl_mc_device *dpmcp_dev; + + if (!mc_io) + return; + + dpmcp_dev = mc_io->dpmcp_dev; if (dpmcp_dev) fsl_mc_io_unset_dpmcp(mc_io); diff --git a/drivers/clk/ti/clockdomain.c b/drivers/clk/ti/clockdomain.c index 423a99b9f10c..8d0dea188a28 100644 --- a/drivers/clk/ti/clockdomain.c +++ b/drivers/clk/ti/clockdomain.c @@ -146,10 +146,12 @@ static void __init of_ti_clockdomain_setup(struct device_node *node) if (!omap2_clk_is_hw_omap(clk_hw)) { pr_warn("can't setup clkdm for basic clk %s\n", __clk_get_name(clk)); + clk_put(clk); continue; } to_clk_hw_omap(clk_hw)->clkdm_name = clkdm_name; omap2_init_clk_clkdm(clk_hw); + clk_put(clk); } } diff --git a/drivers/cpufreq/acpi-cpufreq.c b/drivers/cpufreq/acpi-cpufreq.c index d6f7df33ab8c..4195834a4591 100644 --- a/drivers/cpufreq/acpi-cpufreq.c +++ b/drivers/cpufreq/acpi-cpufreq.c @@ -688,7 +688,8 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy) cpumask_copy(policy->cpus, topology_core_cpumask(cpu)); } - if (check_amd_hwpstate_cpu(cpu) && !acpi_pstate_strict) { + if (check_amd_hwpstate_cpu(cpu) && boot_cpu_data.x86 < 0x19 && + !acpi_pstate_strict) { cpumask_clear(policy->cpus); cpumask_set_cpu(cpu, policy->cpus); cpumask_copy(data->freqdomain_cpus, diff --git a/drivers/cpufreq/sti-cpufreq.c b/drivers/cpufreq/sti-cpufreq.c index 8f16bbb164b8..2855b7878a20 100644 --- a/drivers/cpufreq/sti-cpufreq.c +++ b/drivers/cpufreq/sti-cpufreq.c @@ -141,7 +141,8 @@ static const struct reg_field sti_stih407_dvfs_regfields[DVFS_MAX_REGFIELDS] = { static const struct reg_field *sti_cpufreq_match(void) { if (of_machine_is_compatible("st,stih407") || - of_machine_is_compatible("st,stih410")) + of_machine_is_compatible("st,stih410") || + of_machine_is_compatible("st,stih418")) return sti_stih407_dvfs_regfields; return NULL; @@ -258,7 +259,8 @@ static int sti_cpufreq_init(void) int ret; if ((!of_machine_is_compatible("st,stih407")) && - (!of_machine_is_compatible("st,stih410"))) + (!of_machine_is_compatible("st,stih410")) && + (!of_machine_is_compatible("st,stih418"))) return -ENODEV; ddata.cpu = get_cpu_device(0); diff --git a/drivers/dma/dma-jz4780.c b/drivers/dma/dma-jz4780.c index 0ecb724b394f..e27043427653 100644 --- a/drivers/dma/dma-jz4780.c +++ b/drivers/dma/dma-jz4780.c @@ -639,11 +639,11 @@ static enum dma_status jz4780_dma_tx_status(struct dma_chan *chan, unsigned long flags; unsigned long residue = 0; + spin_lock_irqsave(&jzchan->vchan.lock, flags); + status = dma_cookie_status(chan, cookie, txstate); if ((status == DMA_COMPLETE) || (txstate == NULL)) - return status; - - spin_lock_irqsave(&jzchan->vchan.lock, flags); + goto out_unlock_irqrestore; vdesc = vchan_find_desc(&jzchan->vchan, cookie); if (vdesc) { @@ -660,6 +660,7 @@ static enum dma_status jz4780_dma_tx_status(struct dma_chan *chan, && jzchan->desc->status & (JZ_DMA_DCS_AR | JZ_DMA_DCS_HLT)) status = DMA_ERROR; +out_unlock_irqrestore: spin_unlock_irqrestore(&jzchan->vchan.lock, flags); return status; } diff --git a/drivers/extcon/extcon-ptn5150.c b/drivers/extcon/extcon-ptn5150.c index d1c997599390..5f5252752644 100644 --- a/drivers/extcon/extcon-ptn5150.c +++ b/drivers/extcon/extcon-ptn5150.c @@ -127,7 +127,7 @@ static void ptn5150_irq_work(struct work_struct *work) case PTN5150_DFP_ATTACHED: extcon_set_state_sync(info->edev, EXTCON_USB_HOST, false); - gpiod_set_value(info->vbus_gpiod, 0); + gpiod_set_value_cansleep(info->vbus_gpiod, 0); extcon_set_state_sync(info->edev, EXTCON_USB, true); break; @@ -138,9 +138,9 @@ static void ptn5150_irq_work(struct work_struct *work) PTN5150_REG_CC_VBUS_DETECTION_MASK) >> PTN5150_REG_CC_VBUS_DETECTION_SHIFT); if (vbus) - gpiod_set_value(info->vbus_gpiod, 0); + gpiod_set_value_cansleep(info->vbus_gpiod, 0); else - gpiod_set_value(info->vbus_gpiod, 1); + gpiod_set_value_cansleep(info->vbus_gpiod, 1); extcon_set_state_sync(info->edev, EXTCON_USB_HOST, true); @@ -156,7 +156,7 @@ static void ptn5150_irq_work(struct work_struct *work) EXTCON_USB_HOST, false); extcon_set_state_sync(info->edev, EXTCON_USB, false); - gpiod_set_value(info->vbus_gpiod, 0); + gpiod_set_value_cansleep(info->vbus_gpiod, 0); } } diff --git a/drivers/firmware/arm_scmi/base.c b/drivers/firmware/arm_scmi/base.c index f804e8af6521..f986ee8919f0 100644 --- a/drivers/firmware/arm_scmi/base.c +++ b/drivers/firmware/arm_scmi/base.c @@ -173,6 +173,8 @@ static int scmi_base_implementation_list_get(const struct scmi_handle *handle, protocols_imp[tot_num_ret + loop] = *(list + loop); tot_num_ret += loop_num_ret; + + scmi_reset_rx_to_maxsz(handle, t); } while (loop_num_ret); scmi_xfer_put(handle, t); diff --git a/drivers/firmware/arm_scmi/clock.c b/drivers/firmware/arm_scmi/clock.c index 32526a793f3a..38400a8d0ca8 100644 --- a/drivers/firmware/arm_scmi/clock.c +++ b/drivers/firmware/arm_scmi/clock.c @@ -177,6 +177,8 @@ scmi_clock_describe_rates_get(const struct scmi_handle *handle, u32 clk_id, } tot_rate_cnt += num_returned; + + scmi_reset_rx_to_maxsz(handle, t); /* * check for both returned and remaining to avoid infinite * loop due to buggy firmware diff --git a/drivers/firmware/arm_scmi/common.h b/drivers/firmware/arm_scmi/common.h index 5237c2ff79fe..9a680b9af9e5 100644 --- a/drivers/firmware/arm_scmi/common.h +++ b/drivers/firmware/arm_scmi/common.h @@ -103,6 +103,8 @@ int scmi_do_xfer_with_response(const struct scmi_handle *h, struct scmi_xfer *xfer); int scmi_xfer_get_init(const struct scmi_handle *h, u8 msg_id, u8 prot_id, size_t tx_size, size_t rx_size, struct scmi_xfer **p); +void scmi_reset_rx_to_maxsz(const struct scmi_handle *handle, + struct scmi_xfer *xfer); int scmi_handle_put(const struct scmi_handle *handle); struct scmi_handle *scmi_handle_get(struct device *dev); void scmi_set_handle(struct scmi_device *scmi_dev); diff --git a/drivers/firmware/arm_scmi/driver.c b/drivers/firmware/arm_scmi/driver.c index 3eb0382491ce..11078199abed 100644 --- a/drivers/firmware/arm_scmi/driver.c +++ b/drivers/firmware/arm_scmi/driver.c @@ -481,6 +481,14 @@ int scmi_do_xfer(const struct scmi_handle *handle, struct scmi_xfer *xfer) return ret; } +void scmi_reset_rx_to_maxsz(const struct scmi_handle *handle, + struct scmi_xfer *xfer) +{ + struct scmi_info *info = handle_to_scmi_info(handle); + + xfer->rx.len = info->desc->max_msg_size; +} + #define SCMI_MAX_RESPONSE_TIMEOUT (2 * MSEC_PER_SEC) /** diff --git a/drivers/firmware/arm_scmi/perf.c b/drivers/firmware/arm_scmi/perf.c index 601af4edad5e..129a2887e964 100644 --- a/drivers/firmware/arm_scmi/perf.c +++ b/drivers/firmware/arm_scmi/perf.c @@ -281,6 +281,8 @@ scmi_perf_describe_levels_get(const struct scmi_handle *handle, u32 domain, } tot_opp_cnt += num_returned; + + scmi_reset_rx_to_maxsz(handle, t); /* * check for both returned and remaining to avoid infinite * loop due to buggy firmware diff --git a/drivers/firmware/arm_scmi/reset.c b/drivers/firmware/arm_scmi/reset.c index ab42c21c5517..6d223f345b6c 100644 --- a/drivers/firmware/arm_scmi/reset.c +++ b/drivers/firmware/arm_scmi/reset.c @@ -35,9 +35,7 @@ struct scmi_msg_reset_domain_reset { #define EXPLICIT_RESET_ASSERT BIT(1) #define ASYNCHRONOUS_RESET BIT(2) __le32 reset_state; -#define ARCH_RESET_TYPE BIT(31) -#define COLD_RESET_STATE BIT(0) -#define ARCH_COLD_RESET (ARCH_RESET_TYPE | COLD_RESET_STATE) +#define ARCH_COLD_RESET 0 }; struct reset_dom_info { diff --git a/drivers/firmware/arm_scmi/sensors.c b/drivers/firmware/arm_scmi/sensors.c index a400ea805fc2..931208bc48f1 100644 --- a/drivers/firmware/arm_scmi/sensors.c +++ b/drivers/firmware/arm_scmi/sensors.c @@ -154,6 +154,8 @@ static int scmi_sensor_description_get(const struct scmi_handle *handle, } desc_index += num_returned; + + scmi_reset_rx_to_maxsz(handle, t); /* * check for both returned and remaining to avoid infinite * loop due to buggy firmware diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 4105fbf57167..29141bff4b57 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -3890,7 +3890,7 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev, amdgpu_device_lock_adev(tmp_adev, false); r = amdgpu_device_pre_asic_reset(tmp_adev, - NULL, + (tmp_adev == adev) ? job : NULL, &need_full_reset); /*TODO Should we stop ?*/ if (r) { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c index 5fa5158d18ee..9d61d1b7a569 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c @@ -561,6 +561,7 @@ int amdgpu_gem_va_ioctl(struct drm_device *dev, void *data, struct ww_acquire_ctx ticket; struct list_head list, duplicates; uint64_t va_flags; + uint64_t vm_size; int r = 0; if (args->va_address < AMDGPU_VA_RESERVED_SIZE) { @@ -581,6 +582,15 @@ int amdgpu_gem_va_ioctl(struct drm_device *dev, void *data, args->va_address &= AMDGPU_GMC_HOLE_MASK; + vm_size = adev->vm_manager.max_pfn * AMDGPU_GPU_PAGE_SIZE; + vm_size -= AMDGPU_VA_RESERVED_SIZE; + if (args->va_address + args->map_size > vm_size) { + dev_dbg(&dev->pdev->dev, + "va_address 0x%llx is in top reserved area 0x%llx\n", + args->va_address + args->map_size, vm_size); + return -EINVAL; + } + if ((args->flags & ~valid_flags) && (args->flags & ~prt_flags)) { dev_dbg(&dev->pdev->dev, "invalid flags combination 0x%08X\n", args->flags); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h index 2eda3a8c330d..4a64825b53cb 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h @@ -105,8 +105,8 @@ struct amdgpu_bo_list_entry; #define AMDGPU_MMHUB_0 1 #define AMDGPU_MMHUB_1 2 -/* hardcode that limit for now */ -#define AMDGPU_VA_RESERVED_SIZE (1ULL << 20) +/* Reserve 2MB at top/bottom of address space for kernel use */ +#define AMDGPU_VA_RESERVED_SIZE (2ULL << 20) /* max vmids dedicated for process */ #define AMDGPU_VM_MAX_RESERVED_VMID 1 diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v10.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v10.c index 72e4d61ac752..ad0593342333 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v10.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v10.c @@ -58,8 +58,9 @@ static int update_qpd_v10(struct device_queue_manager *dqm, /* check if sh_mem_config register already configured */ if (qpd->sh_mem_config == 0) { qpd->sh_mem_config = - SH_MEM_ALIGNMENT_MODE_UNALIGNED << - SH_MEM_CONFIG__ALIGNMENT_MODE__SHIFT; + (SH_MEM_ALIGNMENT_MODE_UNALIGNED << + SH_MEM_CONFIG__ALIGNMENT_MODE__SHIFT) | + (3 << SH_MEM_CONFIG__INITIAL_INST_PREFETCH__SHIFT); #if 0 /* TODO: * This shouldn't be an issue with Navi10. Verify. diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index 7c5808503173..d2dd387c95d8 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -3956,6 +3956,13 @@ static void amdgpu_dm_connector_destroy(struct drm_connector *connector) struct amdgpu_device *adev = connector->dev->dev_private; struct amdgpu_display_manager *dm = &adev->dm; + /* + * Call only if mst_mgr was iniitalized before since it's not done + * for all connector types. + */ + if (aconnector->mst_mgr.dev) + drm_dp_mst_topology_mgr_destroy(&aconnector->mst_mgr); + #if defined(CONFIG_BACKLIGHT_CLASS_DEVICE) ||\ defined(CONFIG_BACKLIGHT_CLASS_DEVICE_MODULE) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link.c b/drivers/gpu/drm/amd/display/dc/core/dc_link.c index 3efee7b3378a..47cefc05fd3f 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c @@ -2268,7 +2268,7 @@ enum dc_status dc_link_validate_mode_timing( /* A hack to avoid failing any modes for EDID override feature on * topology change such as lower quality cable for DP or different dongle */ - if (link->remote_sinks[0]) + if (link->remote_sinks[0] && link->remote_sinks[0]->sink_signal == SIGNAL_TYPE_VIRTUAL) return DC_OK; /* Passive Dongle */ diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.c index ddf66046616d..6718777c826d 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.c @@ -898,10 +898,10 @@ void enc1_stream_encoder_dp_blank( */ REG_UPDATE(DP_VID_STREAM_CNTL, DP_VID_STREAM_DIS_DEFER, 2); /* Larger delay to wait until VBLANK - use max retry of - * 10us*5000=50ms. This covers 41.7ms of minimum 24 Hz mode + + * 10us*10200=102ms. This covers 100.0ms of minimum 10 Hz mode + * a little more because we may not trust delay accuracy. */ - max_retries = DP_BLANK_MAX_RETRY * 250; + max_retries = DP_BLANK_MAX_RETRY * 501; /* disable DP stream */ REG_UPDATE(DP_VID_STREAM_CNTL, DP_VID_STREAM_ENABLE, 0); diff --git a/drivers/gpu/drm/amd/display/dc/gpio/gpio_base.c b/drivers/gpu/drm/amd/display/dc/gpio/gpio_base.c index f8f85490e77e..8a6fb58d0199 100644 --- a/drivers/gpu/drm/amd/display/dc/gpio/gpio_base.c +++ b/drivers/gpu/drm/amd/display/dc/gpio/gpio_base.c @@ -63,13 +63,13 @@ enum gpio_result dal_gpio_open_ex( enum gpio_mode mode) { if (gpio->pin) { - ASSERT_CRITICAL(false); + BREAK_TO_DEBUGGER(); return GPIO_RESULT_ALREADY_OPENED; } // No action if allocation failed during gpio construct if (!gpio->hw_container.ddc) { - ASSERT_CRITICAL(false); + BREAK_TO_DEBUGGER(); return GPIO_RESULT_NON_SPECIFIC_ERROR; } gpio->mode = mode; diff --git a/drivers/gpu/drm/amd/display/dc/os_types.h b/drivers/gpu/drm/amd/display/dc/os_types.h index 30ec80ac6fc8..8da322582b68 100644 --- a/drivers/gpu/drm/amd/display/dc/os_types.h +++ b/drivers/gpu/drm/amd/display/dc/os_types.h @@ -57,7 +57,7 @@ * general debug capabilities * */ -#if defined(CONFIG_HAVE_KGDB) || defined(CONFIG_KGDB) +#if defined(CONFIG_DEBUG_KERNEL_DC) && (defined(CONFIG_HAVE_KGDB) || defined(CONFIG_KGDB)) #define ASSERT_CRITICAL(expr) do { \ if (WARN_ON(!(expr))) { \ kgdb_breakpoint(); \ diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c index 1b55f037ba4a..35e6cbe805eb 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c @@ -2864,7 +2864,7 @@ static int smu7_vblank_too_short(struct pp_hwmgr *hwmgr, if (hwmgr->is_kicker) switch_limit_us = data->is_memory_gddr5 ? 450 : 150; else - switch_limit_us = data->is_memory_gddr5 ? 190 : 150; + switch_limit_us = data->is_memory_gddr5 ? 200 : 150; break; case CHIP_VEGAM: switch_limit_us = 30; diff --git a/drivers/gpu/drm/bridge/megachips-stdpxxxx-ge-b850v3-fw.c b/drivers/gpu/drm/bridge/megachips-stdpxxxx-ge-b850v3-fw.c index 6e81e5db57f2..b050fd1f3d20 100644 --- a/drivers/gpu/drm/bridge/megachips-stdpxxxx-ge-b850v3-fw.c +++ b/drivers/gpu/drm/bridge/megachips-stdpxxxx-ge-b850v3-fw.c @@ -295,8 +295,12 @@ static int stdp4028_ge_b850v3_fw_probe(struct i2c_client *stdp4028_i2c, const struct i2c_device_id *id) { struct device *dev = &stdp4028_i2c->dev; + int ret; + + ret = ge_b850v3_lvds_init(dev); - ge_b850v3_lvds_init(dev); + if (ret) + return ret; ge_b850v3_lvds_ptr->stdp4028_i2c = stdp4028_i2c; i2c_set_clientdata(stdp4028_i2c, ge_b850v3_lvds_ptr); @@ -354,8 +358,12 @@ static int stdp2690_ge_b850v3_fw_probe(struct i2c_client *stdp2690_i2c, const struct i2c_device_id *id) { struct device *dev = &stdp2690_i2c->dev; + int ret; + + ret = ge_b850v3_lvds_init(dev); - ge_b850v3_lvds_init(dev); + if (ret) + return ret; ge_b850v3_lvds_ptr->stdp2690_i2c = stdp2690_i2c; i2c_set_clientdata(stdp2690_i2c, ge_b850v3_lvds_ptr); diff --git a/drivers/gpu/drm/bridge/synopsys/dw-mipi-dsi.c b/drivers/gpu/drm/bridge/synopsys/dw-mipi-dsi.c index 675442bfc1bd..77384c49fb8d 100644 --- a/drivers/gpu/drm/bridge/synopsys/dw-mipi-dsi.c +++ b/drivers/gpu/drm/bridge/synopsys/dw-mipi-dsi.c @@ -365,7 +365,6 @@ static void dw_mipi_message_config(struct dw_mipi_dsi *dsi, if (lpm) val |= CMD_MODE_ALL_LP; - dsi_write(dsi, DSI_LPCLK_CTRL, lpm ? 0 : PHY_TXREQUESTCLKHS); dsi_write(dsi, DSI_CMD_MODE_CFG, val); } @@ -541,16 +540,22 @@ static void dw_mipi_dsi_video_mode_config(struct dw_mipi_dsi *dsi) static void dw_mipi_dsi_set_mode(struct dw_mipi_dsi *dsi, unsigned long mode_flags) { + u32 val; + dsi_write(dsi, DSI_PWR_UP, RESET); if (mode_flags & MIPI_DSI_MODE_VIDEO) { dsi_write(dsi, DSI_MODE_CFG, ENABLE_VIDEO_MODE); dw_mipi_dsi_video_mode_config(dsi); - dsi_write(dsi, DSI_LPCLK_CTRL, PHY_TXREQUESTCLKHS); } else { dsi_write(dsi, DSI_MODE_CFG, ENABLE_CMD_MODE); } + val = PHY_TXREQUESTCLKHS; + if (dsi->mode_flags & MIPI_DSI_CLOCK_NON_CONTINUOUS) + val |= AUTO_CLKLANE_CTRL; + dsi_write(dsi, DSI_LPCLK_CTRL, val); + dsi_write(dsi, DSI_PWR_UP, POWERUP); } diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 89b6112bd66b..126a0eb6e054 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -33,6 +33,8 @@ #include <uapi/drm/i915_drm.h> #include <uapi/drm/drm_fourcc.h> +#include <asm/hypervisor.h> + #include <linux/io-mapping.h> #include <linux/i2c.h> #include <linux/i2c-algo-bit.h> @@ -2197,7 +2199,9 @@ static inline bool intel_vtd_active(void) if (intel_iommu_gfx_mapped) return true; #endif - return false; + + /* Running as a guest, we assume the host is enforcing VT'd */ + return !hypervisor_is_type(X86_HYPER_NATIVE); } static inline bool intel_scanout_needs_vtd_wa(struct drm_i915_private *dev_priv) diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c index 3ce8ad7603c7..3ffcbaa13878 100644 --- a/drivers/gpu/drm/ttm/ttm_bo.c +++ b/drivers/gpu/drm/ttm/ttm_bo.c @@ -761,7 +761,7 @@ bool ttm_bo_eviction_valuable(struct ttm_buffer_object *bo, /* Don't evict this BO if it's outside of the * requested placement range */ - if (place->fpfn >= (bo->mem.start + bo->mem.size) || + if (place->fpfn >= (bo->mem.start + bo->mem.num_pages) || (place->lpfn && place->lpfn <= bo->mem.start)) return false; diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c index 1c96809b51c9..b74acbd5997b 100644 --- a/drivers/hid/wacom_wac.c +++ b/drivers/hid/wacom_wac.c @@ -2773,7 +2773,9 @@ static int wacom_wac_collection(struct hid_device *hdev, struct hid_report *repo if (report->type != HID_INPUT_REPORT) return -1; - if (WACOM_PEN_FIELD(field) && wacom->wacom_wac.pen_input) + if (WACOM_PAD_FIELD(field)) + return 0; + else if (WACOM_PEN_FIELD(field) && wacom->wacom_wac.pen_input) wacom_wac_pen_report(hdev, report); else if (WACOM_FINGER_FIELD(field) && wacom->wacom_wac.touch_input) wacom_wac_finger_report(hdev, report); diff --git a/drivers/hwtracing/coresight/coresight-priv.h b/drivers/hwtracing/coresight/coresight-priv.h index 82e563cdc879..dfd24b85a577 100644 --- a/drivers/hwtracing/coresight/coresight-priv.h +++ b/drivers/hwtracing/coresight/coresight-priv.h @@ -147,7 +147,8 @@ static inline void coresight_write_reg_pair(void __iomem *addr, u64 val, void coresight_disable_path(struct list_head *path); int coresight_enable_path(struct list_head *path, u32 mode, void *sink_data); struct coresight_device *coresight_get_sink(struct list_head *path); -struct coresight_device *coresight_get_enabled_sink(bool reset); +struct coresight_device * +coresight_get_enabled_sink(struct coresight_device *source); struct coresight_device *coresight_get_sink_by_id(u32 id); struct list_head *coresight_build_path(struct coresight_device *csdev, struct coresight_device *sink); diff --git a/drivers/hwtracing/coresight/coresight.c b/drivers/hwtracing/coresight/coresight.c index 0bbce0d29158..90ecd04a2f20 100644 --- a/drivers/hwtracing/coresight/coresight.c +++ b/drivers/hwtracing/coresight/coresight.c @@ -481,50 +481,46 @@ struct coresight_device *coresight_get_sink(struct list_head *path) return csdev; } -static int coresight_enabled_sink(struct device *dev, const void *data) +static struct coresight_device * +coresight_find_enabled_sink(struct coresight_device *csdev) { - const bool *reset = data; - struct coresight_device *csdev = to_coresight_device(dev); + int i; + struct coresight_device *sink; if ((csdev->type == CORESIGHT_DEV_TYPE_SINK || csdev->type == CORESIGHT_DEV_TYPE_LINKSINK) && - csdev->activated) { - /* - * Now that we have a handle on the sink for this session, - * disable the sysFS "enable_sink" flag so that possible - * concurrent perf session that wish to use another sink don't - * trip on it. Doing so has no ramification for the current - * session. - */ - if (*reset) - csdev->activated = false; + csdev->activated) + return csdev; - return 1; + /* + * Recursively explore each port found on this element. + */ + for (i = 0; i < csdev->pdata->nr_outport; i++) { + struct coresight_device *child_dev; + + child_dev = csdev->pdata->conns[i].child_dev; + if (child_dev) + sink = coresight_find_enabled_sink(child_dev); + if (sink) + return sink; } - return 0; + return NULL; } /** - * coresight_get_enabled_sink - returns the first enabled sink found on the bus - * @deactivate: Whether the 'enable_sink' flag should be reset + * coresight_get_enabled_sink - returns the first enabled sink using + * connection based search starting from the source reference * - * When operated from perf the deactivate parameter should be set to 'true'. - * That way the "enabled_sink" flag of the sink that was selected can be reset, - * allowing for other concurrent perf sessions to choose a different sink. - * - * When operated from sysFS users have full control and as such the deactivate - * parameter should be set to 'false', hence mandating users to explicitly - * clear the flag. + * @source: Coresight source device reference */ -struct coresight_device *coresight_get_enabled_sink(bool deactivate) +struct coresight_device * +coresight_get_enabled_sink(struct coresight_device *source) { - struct device *dev = NULL; - - dev = bus_find_device(&coresight_bustype, NULL, &deactivate, - coresight_enabled_sink); + if (!source) + return NULL; - return dev ? to_coresight_device(dev) : NULL; + return coresight_find_enabled_sink(source); } static int coresight_sink_by_id(struct device *dev, const void *data) @@ -764,11 +760,7 @@ int coresight_enable(struct coresight_device *csdev) goto out; } - /* - * Search for a valid sink for this session but don't reset the - * "enable_sink" flag in sysFS. Users get to do that explicitly. - */ - sink = coresight_get_enabled_sink(false); + sink = coresight_get_enabled_sink(csdev); if (!sink) { ret = -EINVAL; goto out; diff --git a/drivers/i2c/busses/i2c-imx.c b/drivers/i2c/busses/i2c-imx.c index a3b61336fe55..9543c9816eed 100644 --- a/drivers/i2c/busses/i2c-imx.c +++ b/drivers/i2c/busses/i2c-imx.c @@ -1112,14 +1112,6 @@ static int i2c_imx_probe(struct platform_device *pdev) return ret; } - /* Request IRQ */ - ret = devm_request_irq(&pdev->dev, irq, i2c_imx_isr, IRQF_SHARED, - pdev->name, i2c_imx); - if (ret) { - dev_err(&pdev->dev, "can't claim irq %d\n", irq); - goto clk_disable; - } - /* Init queue */ init_waitqueue_head(&i2c_imx->queue); @@ -1138,6 +1130,14 @@ static int i2c_imx_probe(struct platform_device *pdev) if (ret < 0) goto rpm_disable; + /* Request IRQ */ + ret = request_threaded_irq(irq, i2c_imx_isr, NULL, IRQF_SHARED, + pdev->name, i2c_imx); + if (ret) { + dev_err(&pdev->dev, "can't claim irq %d\n", irq); + goto rpm_disable; + } + /* Set up clock divider */ i2c_imx->bitrate = IMX_I2C_BIT_RATE; ret = of_property_read_u32(pdev->dev.of_node, @@ -1180,13 +1180,12 @@ static int i2c_imx_probe(struct platform_device *pdev) clk_notifier_unregister: clk_notifier_unregister(i2c_imx->clk, &i2c_imx->clk_change_nb); + free_irq(irq, i2c_imx); rpm_disable: pm_runtime_put_noidle(&pdev->dev); pm_runtime_disable(&pdev->dev); pm_runtime_set_suspended(&pdev->dev); pm_runtime_dont_use_autosuspend(&pdev->dev); - -clk_disable: clk_disable_unprepare(i2c_imx->clk); return ret; } @@ -1194,7 +1193,7 @@ static int i2c_imx_probe(struct platform_device *pdev) static int i2c_imx_remove(struct platform_device *pdev) { struct imx_i2c_struct *i2c_imx = platform_get_drvdata(pdev); - int ret; + int irq, ret; ret = pm_runtime_get_sync(&pdev->dev); if (ret < 0) @@ -1214,6 +1213,9 @@ static int i2c_imx_remove(struct platform_device *pdev) imx_i2c_write_reg(0, i2c_imx, IMX_I2C_I2SR); clk_notifier_unregister(i2c_imx->clk, &i2c_imx->clk_change_nb); + irq = platform_get_irq(pdev, 0); + if (irq >= 0) + free_irq(irq, i2c_imx); clk_disable_unprepare(i2c_imx->clk); pm_runtime_put_noidle(&pdev->dev); diff --git a/drivers/iio/adc/rcar-gyroadc.c b/drivers/iio/adc/rcar-gyroadc.c index c37f201294b2..b1fb1fd763fc 100644 --- a/drivers/iio/adc/rcar-gyroadc.c +++ b/drivers/iio/adc/rcar-gyroadc.c @@ -357,7 +357,7 @@ static int rcar_gyroadc_parse_subdevs(struct iio_dev *indio_dev) num_channels = ARRAY_SIZE(rcar_gyroadc_iio_channels_3); break; default: - return -EINVAL; + goto err_e_inval; } /* @@ -374,7 +374,7 @@ static int rcar_gyroadc_parse_subdevs(struct iio_dev *indio_dev) dev_err(dev, "Failed to get child reg property of ADC \"%pOFn\".\n", child); - return ret; + goto err_of_node_put; } /* Channel number is too high. */ @@ -382,7 +382,7 @@ static int rcar_gyroadc_parse_subdevs(struct iio_dev *indio_dev) dev_err(dev, "Only %i channels supported with %pOFn, but reg = <%i>.\n", num_channels, child, reg); - return -EINVAL; + goto err_e_inval; } } @@ -391,7 +391,7 @@ static int rcar_gyroadc_parse_subdevs(struct iio_dev *indio_dev) dev_err(dev, "Channel %i uses different ADC mode than the rest.\n", reg); - return -EINVAL; + goto err_e_inval; } /* Channel is valid, grab the regulator. */ @@ -401,7 +401,8 @@ static int rcar_gyroadc_parse_subdevs(struct iio_dev *indio_dev) if (IS_ERR(vref)) { dev_dbg(dev, "Channel %i 'vref' supply not connected.\n", reg); - return PTR_ERR(vref); + ret = PTR_ERR(vref); + goto err_of_node_put; } priv->vref[reg] = vref; @@ -425,8 +426,10 @@ static int rcar_gyroadc_parse_subdevs(struct iio_dev *indio_dev) * attached to the GyroADC at a time, so if we found it, * we can stop parsing here. */ - if (childmode == RCAR_GYROADC_MODE_SELECT_1_MB88101A) + if (childmode == RCAR_GYROADC_MODE_SELECT_1_MB88101A) { + of_node_put(child); break; + } } if (first) { @@ -435,6 +438,12 @@ static int rcar_gyroadc_parse_subdevs(struct iio_dev *indio_dev) } return 0; + +err_e_inval: + ret = -EINVAL; +err_of_node_put: + of_node_put(child); + return ret; } static void rcar_gyroadc_deinit_supplies(struct iio_dev *indio_dev) diff --git a/drivers/iio/adc/ti-adc0832.c b/drivers/iio/adc/ti-adc0832.c index 6ea39f4bbb37..55abd2fd2ccc 100644 --- a/drivers/iio/adc/ti-adc0832.c +++ b/drivers/iio/adc/ti-adc0832.c @@ -28,6 +28,12 @@ struct adc0832 { struct regulator *reg; struct mutex lock; u8 mux_bits; + /* + * Max size needed: 16x 1 byte ADC data + 8 bytes timestamp + * May be shorter if not all channels are enabled subject + * to the timestamp remaining 8 byte aligned. + */ + u8 data[24] __aligned(8); u8 tx_buf[2] ____cacheline_aligned; u8 rx_buf[2]; @@ -199,7 +205,6 @@ static irqreturn_t adc0832_trigger_handler(int irq, void *p) struct iio_poll_func *pf = p; struct iio_dev *indio_dev = pf->indio_dev; struct adc0832 *adc = iio_priv(indio_dev); - u8 data[24] = { }; /* 16x 1 byte ADC data + 8 bytes timestamp */ int scan_index; int i = 0; @@ -217,10 +222,10 @@ static irqreturn_t adc0832_trigger_handler(int irq, void *p) goto out; } - data[i] = ret; + adc->data[i] = ret; i++; } - iio_push_to_buffers_with_timestamp(indio_dev, data, + iio_push_to_buffers_with_timestamp(indio_dev, adc->data, iio_get_time_ns(indio_dev)); out: mutex_unlock(&adc->lock); diff --git a/drivers/iio/adc/ti-adc12138.c b/drivers/iio/adc/ti-adc12138.c index 68a9dcb8faa2..db476482cc75 100644 --- a/drivers/iio/adc/ti-adc12138.c +++ b/drivers/iio/adc/ti-adc12138.c @@ -47,6 +47,12 @@ struct adc12138 { struct completion complete; /* The number of cclk periods for the S/H's acquisition time */ unsigned int acquisition_time; + /* + * Maximum size needed: 16x 2 bytes ADC data + 8 bytes timestamp. + * Less may be need if not all channels are enabled, as long as + * the 8 byte alignment of the timestamp is maintained. + */ + __be16 data[20] __aligned(8); u8 tx_buf[2] ____cacheline_aligned; u8 rx_buf[2]; @@ -329,7 +335,6 @@ static irqreturn_t adc12138_trigger_handler(int irq, void *p) struct iio_poll_func *pf = p; struct iio_dev *indio_dev = pf->indio_dev; struct adc12138 *adc = iio_priv(indio_dev); - __be16 data[20] = { }; /* 16x 2 bytes ADC data + 8 bytes timestamp */ __be16 trash; int ret; int scan_index; @@ -345,7 +350,7 @@ static irqreturn_t adc12138_trigger_handler(int irq, void *p) reinit_completion(&adc->complete); ret = adc12138_start_and_read_conv(adc, scan_chan, - i ? &data[i - 1] : &trash); + i ? &adc->data[i - 1] : &trash); if (ret) { dev_warn(&adc->spi->dev, "failed to start conversion\n"); @@ -362,7 +367,7 @@ static irqreturn_t adc12138_trigger_handler(int irq, void *p) } if (i) { - ret = adc12138_read_conv_data(adc, &data[i - 1]); + ret = adc12138_read_conv_data(adc, &adc->data[i - 1]); if (ret) { dev_warn(&adc->spi->dev, "failed to get conversion data\n"); @@ -370,7 +375,7 @@ static irqreturn_t adc12138_trigger_handler(int irq, void *p) } } - iio_push_to_buffers_with_timestamp(indio_dev, data, + iio_push_to_buffers_with_timestamp(indio_dev, adc->data, iio_get_time_ns(indio_dev)); out: mutex_unlock(&adc->lock); diff --git a/drivers/iio/gyro/itg3200_buffer.c b/drivers/iio/gyro/itg3200_buffer.c index d3fbe9d86467..1c3c1bd53374 100644 --- a/drivers/iio/gyro/itg3200_buffer.c +++ b/drivers/iio/gyro/itg3200_buffer.c @@ -46,13 +46,20 @@ static irqreturn_t itg3200_trigger_handler(int irq, void *p) struct iio_poll_func *pf = p; struct iio_dev *indio_dev = pf->indio_dev; struct itg3200 *st = iio_priv(indio_dev); - __be16 buf[ITG3200_SCAN_ELEMENTS + sizeof(s64)/sizeof(u16)]; - - int ret = itg3200_read_all_channels(st->i2c, buf); + /* + * Ensure correct alignment and padding including for the + * timestamp that may be inserted. + */ + struct { + __be16 buf[ITG3200_SCAN_ELEMENTS]; + s64 ts __aligned(8); + } scan; + + int ret = itg3200_read_all_channels(st->i2c, scan.buf); if (ret < 0) goto error_ret; - iio_push_to_buffers_with_timestamp(indio_dev, buf, pf->timestamp); + iio_push_to_buffers_with_timestamp(indio_dev, &scan, pf->timestamp); iio_trigger_notify_done(indio_dev->trig); diff --git a/drivers/iio/light/si1145.c b/drivers/iio/light/si1145.c index 982bba0c54e7..cb40345e7b51 100644 --- a/drivers/iio/light/si1145.c +++ b/drivers/iio/light/si1145.c @@ -169,6 +169,7 @@ struct si1145_part_info { * @part_info: Part information * @trig: Pointer to iio trigger * @meas_rate: Value of MEAS_RATE register. Only set in HW in auto mode + * @buffer: Used to pack data read from sensor. */ struct si1145_data { struct i2c_client *client; @@ -180,6 +181,14 @@ struct si1145_data { bool autonomous; struct iio_trigger *trig; int meas_rate; + /* + * Ensure timestamp will be naturally aligned if present. + * Maximum buffer size (may be only partly used if not all + * channels are enabled): + * 6*2 bytes channels data + 4 bytes alignment + + * 8 bytes timestamp + */ + u8 buffer[24] __aligned(8); }; /** @@ -441,12 +450,6 @@ static irqreturn_t si1145_trigger_handler(int irq, void *private) struct iio_poll_func *pf = private; struct iio_dev *indio_dev = pf->indio_dev; struct si1145_data *data = iio_priv(indio_dev); - /* - * Maximum buffer size: - * 6*2 bytes channels data + 4 bytes alignment + - * 8 bytes timestamp - */ - u8 buffer[24]; int i, j = 0; int ret; u8 irq_status = 0; @@ -479,7 +482,7 @@ static irqreturn_t si1145_trigger_handler(int irq, void *private) ret = i2c_smbus_read_i2c_block_data_or_emulated( data->client, indio_dev->channels[i].address, - sizeof(u16) * run, &buffer[j]); + sizeof(u16) * run, &data->buffer[j]); if (ret < 0) goto done; j += run * sizeof(u16); @@ -494,7 +497,7 @@ static irqreturn_t si1145_trigger_handler(int irq, void *private) goto done; } - iio_push_to_buffers_with_timestamp(indio_dev, buffer, + iio_push_to_buffers_with_timestamp(indio_dev, data->buffer, iio_get_time_ns(indio_dev)); done: diff --git a/drivers/infiniband/hw/qedr/qedr_iw_cm.c b/drivers/infiniband/hw/qedr/qedr_iw_cm.c index e521f3c3dbbf..653ddf30973e 100644 --- a/drivers/infiniband/hw/qedr/qedr_iw_cm.c +++ b/drivers/infiniband/hw/qedr/qedr_iw_cm.c @@ -727,6 +727,7 @@ int qedr_iw_destroy_listen(struct iw_cm_id *cm_id) listener->qed_handle); cm_id->rem_ref(cm_id); + kfree(listener); return rc; } diff --git a/drivers/input/serio/hil_mlc.c b/drivers/input/serio/hil_mlc.c index e1423f7648d6..4c039e4125d9 100644 --- a/drivers/input/serio/hil_mlc.c +++ b/drivers/input/serio/hil_mlc.c @@ -74,7 +74,7 @@ EXPORT_SYMBOL(hil_mlc_unregister); static LIST_HEAD(hil_mlcs); static DEFINE_RWLOCK(hil_mlcs_lock); static struct timer_list hil_mlcs_kicker; -static int hil_mlcs_probe; +static int hil_mlcs_probe, hil_mlc_stop; static void hil_mlcs_process(unsigned long unused); static DECLARE_TASKLET_DISABLED(hil_mlcs_tasklet, hil_mlcs_process, 0); @@ -702,9 +702,13 @@ static int hilse_donode(hil_mlc *mlc) if (!mlc->ostarted) { mlc->ostarted = 1; mlc->opacket = pack; - mlc->out(mlc); + rc = mlc->out(mlc); nextidx = HILSEN_DOZE; write_unlock_irqrestore(&mlc->lock, flags); + if (rc) { + hil_mlc_stop = 1; + return 1; + } break; } mlc->ostarted = 0; @@ -715,8 +719,13 @@ static int hilse_donode(hil_mlc *mlc) case HILSE_CTS: write_lock_irqsave(&mlc->lock, flags); - nextidx = mlc->cts(mlc) ? node->bad : node->good; + rc = mlc->cts(mlc); + nextidx = rc ? node->bad : node->good; write_unlock_irqrestore(&mlc->lock, flags); + if (rc) { + hil_mlc_stop = 1; + return 1; + } break; default: @@ -780,6 +789,12 @@ static void hil_mlcs_process(unsigned long unused) static void hil_mlcs_timer(struct timer_list *unused) { + if (hil_mlc_stop) { + /* could not send packet - stop immediately. */ + pr_warn(PREFIX "HIL seems stuck - Disabling HIL MLC.\n"); + return; + } + hil_mlcs_probe = 1; tasklet_schedule(&hil_mlcs_tasklet); /* Re-insert the periodic task. */ diff --git a/drivers/input/serio/hp_sdc_mlc.c b/drivers/input/serio/hp_sdc_mlc.c index 232d30c825bd..3e85e9039374 100644 --- a/drivers/input/serio/hp_sdc_mlc.c +++ b/drivers/input/serio/hp_sdc_mlc.c @@ -210,7 +210,7 @@ static int hp_sdc_mlc_cts(hil_mlc *mlc) priv->tseq[2] = 1; priv->tseq[3] = 0; priv->tseq[4] = 0; - __hp_sdc_enqueue_transaction(&priv->trans); + return __hp_sdc_enqueue_transaction(&priv->trans); busy: return 1; done: @@ -219,7 +219,7 @@ static int hp_sdc_mlc_cts(hil_mlc *mlc) return 0; } -static void hp_sdc_mlc_out(hil_mlc *mlc) +static int hp_sdc_mlc_out(hil_mlc *mlc) { struct hp_sdc_mlc_priv_s *priv; @@ -234,7 +234,7 @@ static void hp_sdc_mlc_out(hil_mlc *mlc) do_data: if (priv->emtestmode) { up(&mlc->osem); - return; + return 0; } /* Shouldn't be sending commands when loop may be busy */ BUG_ON(down_trylock(&mlc->csem)); @@ -296,7 +296,7 @@ static void hp_sdc_mlc_out(hil_mlc *mlc) BUG_ON(down_trylock(&mlc->csem)); } enqueue: - hp_sdc_enqueue_transaction(&priv->trans); + return hp_sdc_enqueue_transaction(&priv->trans); } static int __init hp_sdc_mlc_init(void) diff --git a/drivers/leds/leds-bcm6328.c b/drivers/leds/leds-bcm6328.c index c50d34e2b098..de932755bcb3 100644 --- a/drivers/leds/leds-bcm6328.c +++ b/drivers/leds/leds-bcm6328.c @@ -332,7 +332,7 @@ static int bcm6328_led(struct device *dev, struct device_node *nc, u32 reg, led->cdev.brightness_set = bcm6328_led_set; led->cdev.blink_set = bcm6328_blink_set; - rc = led_classdev_register(dev, &led->cdev); + rc = devm_led_classdev_register(dev, &led->cdev); if (rc < 0) return rc; diff --git a/drivers/leds/leds-bcm6358.c b/drivers/leds/leds-bcm6358.c index aec285fd21c0..dbb8953334d9 100644 --- a/drivers/leds/leds-bcm6358.c +++ b/drivers/leds/leds-bcm6358.c @@ -137,7 +137,7 @@ static int bcm6358_led(struct device *dev, struct device_node *nc, u32 reg, led->cdev.brightness_set = bcm6358_led_set; - rc = led_classdev_register(dev, &led->cdev); + rc = devm_led_classdev_register(dev, &led->cdev); if (rc < 0) return rc; diff --git a/drivers/md/md-bitmap.c b/drivers/md/md-bitmap.c index 7227d03dbbea..0a6c200e3dcb 100644 --- a/drivers/md/md-bitmap.c +++ b/drivers/md/md-bitmap.c @@ -1372,7 +1372,7 @@ __acquires(bitmap->lock) if (bitmap->bp[page].hijacked || bitmap->bp[page].map == NULL) csize = ((sector_t)1) << (bitmap->chunkshift + - PAGE_COUNTER_SHIFT - 1); + PAGE_COUNTER_SHIFT); else csize = ((sector_t)1) << bitmap->chunkshift; *blocks = csize - (offset & (csize - 1)); diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 02acd5d5a848..08a7f97750f7 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -2407,8 +2407,6 @@ static int resize_stripes(struct r5conf *conf, int newsize) } else err = -ENOMEM; - mutex_unlock(&conf->cache_size_mutex); - conf->slab_cache = sc; conf->active_name = 1-conf->active_name; @@ -2431,6 +2429,8 @@ static int resize_stripes(struct r5conf *conf, int newsize) if (!err) conf->pool_size = newsize; + mutex_unlock(&conf->cache_size_mutex); + return err; } diff --git a/drivers/media/i2c/imx274.c b/drivers/media/i2c/imx274.c index 6011cec5e351..e6aa9f32b6a8 100644 --- a/drivers/media/i2c/imx274.c +++ b/drivers/media/i2c/imx274.c @@ -1235,6 +1235,8 @@ static int imx274_s_frame_interval(struct v4l2_subdev *sd, ret = imx274_set_frame_interval(imx274, fi->interval); if (!ret) { + fi->interval = imx274->frame_interval; + /* * exposure time range is decided by frame interval * need to update it after frame interval changes @@ -1730,9 +1732,9 @@ static int imx274_set_frame_interval(struct stimx274 *priv, __func__, frame_interval.numerator, frame_interval.denominator); - if (frame_interval.numerator == 0) { - err = -EINVAL; - goto fail; + if (frame_interval.numerator == 0 || frame_interval.denominator == 0) { + frame_interval.denominator = IMX274_DEF_FRAME_RATE; + frame_interval.numerator = 1; } req_frame_rate = (u32)(frame_interval.denominator diff --git a/drivers/media/pci/tw5864/tw5864-video.c b/drivers/media/pci/tw5864/tw5864-video.c index 09732eed7eb4..656142c7a2cc 100644 --- a/drivers/media/pci/tw5864/tw5864-video.c +++ b/drivers/media/pci/tw5864/tw5864-video.c @@ -767,6 +767,9 @@ static int tw5864_enum_frameintervals(struct file *file, void *priv, fintv->type = V4L2_FRMIVAL_TYPE_STEPWISE; ret = tw5864_frameinterval_get(input, &frameinterval); + if (ret) + return ret; + fintv->stepwise.step = frameinterval; fintv->stepwise.min = frameinterval; fintv->stepwise.max = frameinterval; @@ -785,6 +788,9 @@ static int tw5864_g_parm(struct file *file, void *priv, cp->capability = V4L2_CAP_TIMEPERFRAME; ret = tw5864_frameinterval_get(input, &cp->timeperframe); + if (ret) + return ret; + cp->timeperframe.numerator *= input->frame_interval; cp->capturemode = 0; cp->readbuffers = 2; diff --git a/drivers/media/platform/mtk-jpeg/mtk_jpeg_core.c b/drivers/media/platform/mtk-jpeg/mtk_jpeg_core.c index ee802fc3bcdf..9fa1bc5514f3 100644 --- a/drivers/media/platform/mtk-jpeg/mtk_jpeg_core.c +++ b/drivers/media/platform/mtk-jpeg/mtk_jpeg_core.c @@ -571,6 +571,13 @@ static int mtk_jpeg_queue_setup(struct vb2_queue *q, if (!q_data) return -EINVAL; + if (*num_planes) { + for (i = 0; i < *num_planes; i++) + if (sizes[i] < q_data->sizeimage[i]) + return -EINVAL; + return 0; + } + *num_planes = q_data->fmt->colplanes; for (i = 0; i < q_data->fmt->colplanes; i++) { sizes[i] = q_data->sizeimage[i]; diff --git a/drivers/media/usb/uvc/uvc_ctrl.c b/drivers/media/usb/uvc/uvc_ctrl.c index a30a8a731eda..36abe47997b0 100644 --- a/drivers/media/usb/uvc/uvc_ctrl.c +++ b/drivers/media/usb/uvc/uvc_ctrl.c @@ -1848,30 +1848,35 @@ int uvc_xu_ctrl_query(struct uvc_video_chain *chain, { struct uvc_entity *entity; struct uvc_control *ctrl; - unsigned int i, found = 0; + unsigned int i; + bool found; u32 reqflags; u16 size; u8 *data = NULL; int ret; /* Find the extension unit. */ + found = false; list_for_each_entry(entity, &chain->entities, chain) { if (UVC_ENTITY_TYPE(entity) == UVC_VC_EXTENSION_UNIT && - entity->id == xqry->unit) + entity->id == xqry->unit) { + found = true; break; + } } - if (entity->id != xqry->unit) { + if (!found) { uvc_trace(UVC_TRACE_CONTROL, "Extension unit %u not found.\n", xqry->unit); return -ENOENT; } /* Find the control and perform delayed initialization if needed. */ + found = false; for (i = 0; i < entity->ncontrols; ++i) { ctrl = &entity->controls[i]; if (ctrl->index == xqry->selector - 1) { - found = 1; + found = true; break; } } @@ -2028,13 +2033,6 @@ static int uvc_ctrl_add_info(struct uvc_device *dev, struct uvc_control *ctrl, goto done; } - /* - * Retrieve control flags from the device. Ignore errors and work with - * default flag values from the uvc_ctrl array when the device doesn't - * properly implement GET_INFO on standard controls. - */ - uvc_ctrl_get_flags(dev, ctrl, &ctrl->info); - ctrl->initialized = 1; uvc_trace(UVC_TRACE_CONTROL, "Added control %pUl/%u to device %s " @@ -2257,6 +2255,13 @@ static void uvc_ctrl_init_ctrl(struct uvc_device *dev, struct uvc_control *ctrl) if (uvc_entity_match_guid(ctrl->entity, info->entity) && ctrl->index == info->index) { uvc_ctrl_add_info(dev, ctrl, info); + /* + * Retrieve control flags from the device. Ignore errors + * and work with default flag values from the uvc_ctrl + * array when the device doesn't properly implement + * GET_INFO on standard controls. + */ + uvc_ctrl_get_flags(dev, ctrl, &ctrl->info); break; } } diff --git a/drivers/memory/emif.c b/drivers/memory/emif.c index 402c6bc8e621..af296b6fcbbd 100644 --- a/drivers/memory/emif.c +++ b/drivers/memory/emif.c @@ -163,35 +163,12 @@ static const struct file_operations emif_mr4_fops = { static int __init_or_module emif_debugfs_init(struct emif_data *emif) { - struct dentry *dentry; - int ret; - - dentry = debugfs_create_dir(dev_name(emif->dev), NULL); - if (!dentry) { - ret = -ENOMEM; - goto err0; - } - emif->debugfs_root = dentry; - - dentry = debugfs_create_file("regcache_dump", S_IRUGO, - emif->debugfs_root, emif, &emif_regdump_fops); - if (!dentry) { - ret = -ENOMEM; - goto err1; - } - - dentry = debugfs_create_file("mr4", S_IRUGO, - emif->debugfs_root, emif, &emif_mr4_fops); - if (!dentry) { - ret = -ENOMEM; - goto err1; - } - + emif->debugfs_root = debugfs_create_dir(dev_name(emif->dev), NULL); + debugfs_create_file("regcache_dump", S_IRUGO, emif->debugfs_root, emif, + &emif_regdump_fops); + debugfs_create_file("mr4", S_IRUGO, emif->debugfs_root, emif, + &emif_mr4_fops); return 0; -err1: - debugfs_remove_recursive(emif->debugfs_root); -err0: - return ret; } static void __exit emif_debugfs_exit(struct emif_data *emif) diff --git a/drivers/message/fusion/mptscsih.c b/drivers/message/fusion/mptscsih.c index 1491561d2e5c..4bc43d8eeb9e 100644 --- a/drivers/message/fusion/mptscsih.c +++ b/drivers/message/fusion/mptscsih.c @@ -1176,8 +1176,10 @@ mptscsih_remove(struct pci_dev *pdev) MPT_SCSI_HOST *hd; int sz1; - if((hd = shost_priv(host)) == NULL) - return; + if (host == NULL) + hd = NULL; + else + hd = shost_priv(host); mptscsih_shutdown(pdev); @@ -1193,14 +1195,15 @@ mptscsih_remove(struct pci_dev *pdev) "Free'd ScsiLookup (%d) memory\n", ioc->name, sz1)); - kfree(hd->info_kbuf); + if (hd) + kfree(hd->info_kbuf); /* NULL the Scsi_Host pointer */ ioc->sh = NULL; - scsi_host_put(host); - + if (host) + scsi_host_put(host); mpt_detach(pdev); } diff --git a/drivers/mmc/host/sdhci-acpi.c b/drivers/mmc/host/sdhci-acpi.c index b2d924c5e82e..0dc8eafdc81d 100644 --- a/drivers/mmc/host/sdhci-acpi.c +++ b/drivers/mmc/host/sdhci-acpi.c @@ -658,6 +658,43 @@ static int sdhci_acpi_emmc_amd_probe_slot(struct platform_device *pdev, (host->mmc->caps & MMC_CAP_1_8V_DDR)) host->mmc->caps2 = MMC_CAP2_HS400_1_8V; + /* + * There are two types of presets out in the wild: + * 1) Default/broken presets. + * These presets have two sets of problems: + * a) The clock divisor for SDR12, SDR25, and SDR50 is too small. + * This results in clock frequencies that are 2x higher than + * acceptable. i.e., SDR12 = 25 MHz, SDR25 = 50 MHz, SDR50 = + * 100 MHz.x + * b) The HS200 and HS400 driver strengths don't match. + * By default, the SDR104 preset register has a driver strength of + * A, but the (internal) HS400 preset register has a driver + * strength of B. As part of initializing HS400, HS200 tuning + * needs to be performed. Having different driver strengths + * between tuning and operation is wrong. It results in different + * rise/fall times that lead to incorrect sampling. + * 2) Firmware with properly initialized presets. + * These presets have proper clock divisors. i.e., SDR12 => 12MHz, + * SDR25 => 25 MHz, SDR50 => 50 MHz. Additionally the HS200 and + * HS400 preset driver strengths match. + * + * Enabling presets for HS400 doesn't work for the following reasons: + * 1) sdhci_set_ios has a hard coded list of timings that are used + * to determine if presets should be enabled. + * 2) sdhci_get_preset_value is using a non-standard register to + * read out HS400 presets. The AMD controller doesn't support this + * non-standard register. In fact, it doesn't expose the HS400 + * preset register anywhere in the SDHCI memory map. This results + * in reading a garbage value and using the wrong presets. + * + * Since HS400 and HS200 presets must be identical, we could + * instead use the the SDR104 preset register. + * + * If the above issues are resolved we could remove this quirk for + * firmware that that has valid presets (i.e., SDR12 <= 12 MHz). + */ + host->quirks2 |= SDHCI_QUIRK2_PRESET_VALUE_BROKEN; + host->mmc_host_ops.select_drive_strength = amd_select_drive_strength; host->mmc_host_ops.set_ios = amd_set_ios; host->mmc_host_ops.execute_tuning = amd_sdhci_execute_tuning; diff --git a/drivers/mmc/host/sdhci-of-esdhc.c b/drivers/mmc/host/sdhci-of-esdhc.c index 66ad46d0ba88..64196c1b1c8f 100644 --- a/drivers/mmc/host/sdhci-of-esdhc.c +++ b/drivers/mmc/host/sdhci-of-esdhc.c @@ -1004,6 +1004,17 @@ static int esdhc_execute_tuning(struct mmc_host *mmc, u32 opcode) esdhc_tuning_block_enable(host, true); + /* + * The eSDHC controller takes the data timeout value into account + * during tuning. If the SD card is too slow sending the response, the + * timer will expire and a "Buffer Read Ready" interrupt without data + * is triggered. This leads to tuning errors. + * + * Just set the timeout to the maximum value because the core will + * already take care of it in sdhci_send_tuning(). + */ + sdhci_writeb(host, 0xe, SDHCI_TIMEOUT_CONTROL); + hs400_tuning = host->flags & SDHCI_HS400_TUNING; do { diff --git a/drivers/mmc/host/sdhci-pci-core.c b/drivers/mmc/host/sdhci-pci-core.c index 91d0cb08238c..ddea4621cda1 100644 --- a/drivers/mmc/host/sdhci-pci-core.c +++ b/drivers/mmc/host/sdhci-pci-core.c @@ -24,6 +24,8 @@ #include <linux/iopoll.h> #include <linux/gpio.h> #include <linux/pm_runtime.h> +#include <linux/pm_qos.h> +#include <linux/debugfs.h> #include <linux/mmc/slot-gpio.h> #include <linux/mmc/sdhci-pci-data.h> #include <linux/acpi.h> @@ -520,6 +522,8 @@ struct intel_host { bool rpm_retune_ok; u32 glk_rx_ctrl1; u32 glk_tun_val; + u32 active_ltr; + u32 idle_ltr; }; static const guid_t intel_dsm_guid = @@ -764,6 +768,108 @@ static int intel_execute_tuning(struct mmc_host *mmc, u32 opcode) return 0; } +#define INTEL_ACTIVELTR 0x804 +#define INTEL_IDLELTR 0x808 + +#define INTEL_LTR_REQ BIT(15) +#define INTEL_LTR_SCALE_MASK GENMASK(11, 10) +#define INTEL_LTR_SCALE_1US (2 << 10) +#define INTEL_LTR_SCALE_32US (3 << 10) +#define INTEL_LTR_VALUE_MASK GENMASK(9, 0) + +static void intel_cache_ltr(struct sdhci_pci_slot *slot) +{ + struct intel_host *intel_host = sdhci_pci_priv(slot); + struct sdhci_host *host = slot->host; + + intel_host->active_ltr = readl(host->ioaddr + INTEL_ACTIVELTR); + intel_host->idle_ltr = readl(host->ioaddr + INTEL_IDLELTR); +} + +static void intel_ltr_set(struct device *dev, s32 val) +{ + struct sdhci_pci_chip *chip = dev_get_drvdata(dev); + struct sdhci_pci_slot *slot = chip->slots[0]; + struct intel_host *intel_host = sdhci_pci_priv(slot); + struct sdhci_host *host = slot->host; + u32 ltr; + + pm_runtime_get_sync(dev); + + /* + * Program latency tolerance (LTR) accordingly what has been asked + * by the PM QoS layer or disable it in case we were passed + * negative value or PM_QOS_LATENCY_ANY. + */ + ltr = readl(host->ioaddr + INTEL_ACTIVELTR); + + if (val == PM_QOS_LATENCY_ANY || val < 0) { + ltr &= ~INTEL_LTR_REQ; + } else { + ltr |= INTEL_LTR_REQ; + ltr &= ~INTEL_LTR_SCALE_MASK; + ltr &= ~INTEL_LTR_VALUE_MASK; + + if (val > INTEL_LTR_VALUE_MASK) { + val >>= 5; + if (val > INTEL_LTR_VALUE_MASK) + val = INTEL_LTR_VALUE_MASK; + ltr |= INTEL_LTR_SCALE_32US | val; + } else { + ltr |= INTEL_LTR_SCALE_1US | val; + } + } + + if (ltr == intel_host->active_ltr) + goto out; + + writel(ltr, host->ioaddr + INTEL_ACTIVELTR); + writel(ltr, host->ioaddr + INTEL_IDLELTR); + + /* Cache the values into lpss structure */ + intel_cache_ltr(slot); +out: + pm_runtime_put_autosuspend(dev); +} + +static bool intel_use_ltr(struct sdhci_pci_chip *chip) +{ + switch (chip->pdev->device) { + case PCI_DEVICE_ID_INTEL_BYT_EMMC: + case PCI_DEVICE_ID_INTEL_BYT_EMMC2: + case PCI_DEVICE_ID_INTEL_BYT_SDIO: + case PCI_DEVICE_ID_INTEL_BYT_SD: + case PCI_DEVICE_ID_INTEL_BSW_EMMC: + case PCI_DEVICE_ID_INTEL_BSW_SDIO: + case PCI_DEVICE_ID_INTEL_BSW_SD: + return false; + default: + return true; + } +} + +static void intel_ltr_expose(struct sdhci_pci_chip *chip) +{ + struct device *dev = &chip->pdev->dev; + + if (!intel_use_ltr(chip)) + return; + + dev->power.set_latency_tolerance = intel_ltr_set; + dev_pm_qos_expose_latency_tolerance(dev); +} + +static void intel_ltr_hide(struct sdhci_pci_chip *chip) +{ + struct device *dev = &chip->pdev->dev; + + if (!intel_use_ltr(chip)) + return; + + dev_pm_qos_hide_latency_tolerance(dev); + dev->power.set_latency_tolerance = NULL; +} + static void byt_probe_slot(struct sdhci_pci_slot *slot) { struct mmc_host_ops *ops = &slot->host->mmc_host_ops; @@ -778,6 +884,43 @@ static void byt_probe_slot(struct sdhci_pci_slot *slot) ops->start_signal_voltage_switch = intel_start_signal_voltage_switch; device_property_read_u32(dev, "max-frequency", &mmc->f_max); + + if (!mmc->slotno) { + slot->chip->slots[mmc->slotno] = slot; + intel_ltr_expose(slot->chip); + } +} + +static void byt_add_debugfs(struct sdhci_pci_slot *slot) +{ + struct intel_host *intel_host = sdhci_pci_priv(slot); + struct mmc_host *mmc = slot->host->mmc; + struct dentry *dir = mmc->debugfs_root; + + if (!intel_use_ltr(slot->chip)) + return; + + debugfs_create_x32("active_ltr", 0444, dir, &intel_host->active_ltr); + debugfs_create_x32("idle_ltr", 0444, dir, &intel_host->idle_ltr); + + intel_cache_ltr(slot); +} + +static int byt_add_host(struct sdhci_pci_slot *slot) +{ + int ret = sdhci_add_host(slot->host); + + if (!ret) + byt_add_debugfs(slot); + return ret; +} + +static void byt_remove_slot(struct sdhci_pci_slot *slot, int dead) +{ + struct mmc_host *mmc = slot->host->mmc; + + if (!mmc->slotno) + intel_ltr_hide(slot->chip); } static int byt_emmc_probe_slot(struct sdhci_pci_slot *slot) @@ -859,6 +1002,8 @@ static int glk_emmc_add_host(struct sdhci_pci_slot *slot) if (ret) goto cleanup; + byt_add_debugfs(slot); + return 0; cleanup: @@ -1036,6 +1181,8 @@ static const struct sdhci_pci_fixes sdhci_intel_byt_emmc = { #endif .allow_runtime_pm = true, .probe_slot = byt_emmc_probe_slot, + .add_host = byt_add_host, + .remove_slot = byt_remove_slot, .quirks = SDHCI_QUIRK_NO_ENDATTR_IN_NOPDESC | SDHCI_QUIRK_NO_LED, .quirks2 = SDHCI_QUIRK2_PRESET_VALUE_BROKEN | @@ -1049,6 +1196,7 @@ static const struct sdhci_pci_fixes sdhci_intel_glk_emmc = { .allow_runtime_pm = true, .probe_slot = glk_emmc_probe_slot, .add_host = glk_emmc_add_host, + .remove_slot = byt_remove_slot, #ifdef CONFIG_PM_SLEEP .suspend = sdhci_cqhci_suspend, .resume = sdhci_cqhci_resume, @@ -1079,6 +1227,8 @@ static const struct sdhci_pci_fixes sdhci_ni_byt_sdio = { SDHCI_QUIRK2_PRESET_VALUE_BROKEN, .allow_runtime_pm = true, .probe_slot = ni_byt_sdio_probe_slot, + .add_host = byt_add_host, + .remove_slot = byt_remove_slot, .ops = &sdhci_intel_byt_ops, .priv_size = sizeof(struct intel_host), }; @@ -1096,6 +1246,8 @@ static const struct sdhci_pci_fixes sdhci_intel_byt_sdio = { SDHCI_QUIRK2_PRESET_VALUE_BROKEN, .allow_runtime_pm = true, .probe_slot = byt_sdio_probe_slot, + .add_host = byt_add_host, + .remove_slot = byt_remove_slot, .ops = &sdhci_intel_byt_ops, .priv_size = sizeof(struct intel_host), }; @@ -1115,6 +1267,8 @@ static const struct sdhci_pci_fixes sdhci_intel_byt_sd = { .allow_runtime_pm = true, .own_cd_for_runtime_pm = true, .probe_slot = byt_sd_probe_slot, + .add_host = byt_add_host, + .remove_slot = byt_remove_slot, .ops = &sdhci_intel_byt_ops, .priv_size = sizeof(struct intel_host), }; diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c index 136f9737713d..a1aeb2e10564 100644 --- a/drivers/mmc/host/sdhci.c +++ b/drivers/mmc/host/sdhci.c @@ -1162,9 +1162,11 @@ static inline void sdhci_auto_cmd_select(struct sdhci_host *host, /* * In case of Version 4.10 or later, use of 'Auto CMD Auto * Select' is recommended rather than use of 'Auto CMD12 - * Enable' or 'Auto CMD23 Enable'. + * Enable' or 'Auto CMD23 Enable'. We require Version 4 Mode + * here because some controllers (e.g sdhci-of-dwmshc) expect it. */ - if (host->version >= SDHCI_SPEC_410 && (use_cmd12 || use_cmd23)) { + if (host->version >= SDHCI_SPEC_410 && host->v4_mode && + (use_cmd12 || use_cmd23)) { *mode |= SDHCI_TRNS_AUTO_SEL; ctrl2 = sdhci_readw(host, SDHCI_HOST_CONTROL2); diff --git a/drivers/mmc/host/via-sdmmc.c b/drivers/mmc/host/via-sdmmc.c index 8d96ecba1b55..d12a068b0f9e 100644 --- a/drivers/mmc/host/via-sdmmc.c +++ b/drivers/mmc/host/via-sdmmc.c @@ -1259,11 +1259,14 @@ static void via_init_sdc_pm(struct via_crdr_mmc_host *host) static int via_sd_suspend(struct pci_dev *pcidev, pm_message_t state) { struct via_crdr_mmc_host *host; + unsigned long flags; host = pci_get_drvdata(pcidev); + spin_lock_irqsave(&host->lock, flags); via_save_pcictrlreg(host); via_save_sdcreg(host); + spin_unlock_irqrestore(&host->lock, flags); pci_save_state(pcidev); pci_enable_wake(pcidev, pci_choose_state(pcidev, state), 0); diff --git a/drivers/mtd/ubi/wl.c b/drivers/mtd/ubi/wl.c index 5d77a38dba54..7def041bbe48 100644 --- a/drivers/mtd/ubi/wl.c +++ b/drivers/mtd/ubi/wl.c @@ -1629,6 +1629,19 @@ int ubi_thread(void *u) !ubi->thread_enabled || ubi_dbg_is_bgt_disabled(ubi)) { set_current_state(TASK_INTERRUPTIBLE); spin_unlock(&ubi->wl_lock); + + /* + * Check kthread_should_stop() after we set the task + * state to guarantee that we either see the stop bit + * and exit or the task state is reset to runnable such + * that it's not scheduled out indefinitely and detects + * the stop bit at kthread_should_stop(). + */ + if (kthread_should_stop()) { + set_current_state(TASK_RUNNING); + break; + } + schedule(); continue; } diff --git a/drivers/net/can/flexcan.c b/drivers/net/can/flexcan.c index aaa7ed1dc97e..d59c6c87164f 100644 --- a/drivers/net/can/flexcan.c +++ b/drivers/net/can/flexcan.c @@ -1703,8 +1703,6 @@ static int __maybe_unused flexcan_suspend(struct device *device) err = flexcan_chip_disable(priv); if (err) return err; - - err = pm_runtime_force_suspend(device); } netif_stop_queue(dev); netif_device_detach(dev); @@ -1730,10 +1728,6 @@ static int __maybe_unused flexcan_resume(struct device *device) if (err) return err; } else { - err = pm_runtime_force_resume(device); - if (err) - return err; - err = flexcan_chip_enable(priv); } } @@ -1764,8 +1758,16 @@ static int __maybe_unused flexcan_noirq_suspend(struct device *device) struct net_device *dev = dev_get_drvdata(device); struct flexcan_priv *priv = netdev_priv(dev); - if (netif_running(dev) && device_may_wakeup(device)) - flexcan_enable_wakeup_irq(priv, true); + if (netif_running(dev)) { + int err; + + if (device_may_wakeup(device)) + flexcan_enable_wakeup_irq(priv, true); + + err = pm_runtime_force_suspend(device); + if (err) + return err; + } return 0; } @@ -1775,8 +1777,16 @@ static int __maybe_unused flexcan_noirq_resume(struct device *device) struct net_device *dev = dev_get_drvdata(device); struct flexcan_priv *priv = netdev_priv(dev); - if (netif_running(dev) && device_may_wakeup(device)) - flexcan_enable_wakeup_irq(priv, false); + if (netif_running(dev)) { + int err; + + err = pm_runtime_force_resume(device); + if (err) + return err; + + if (device_may_wakeup(device)) + flexcan_enable_wakeup_irq(priv, false); + } return 0; } diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index cdd3764760ed..6f777e9b4b93 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -8375,6 +8375,11 @@ static void bnxt_report_link(struct bnxt *bp) u16 fec; netif_carrier_on(bp->dev); + speed = bnxt_fw_to_ethtool_speed(bp->link_info.link_speed); + if (speed == SPEED_UNKNOWN) { + netdev_info(bp->dev, "NIC Link is Up, speed unknown\n"); + return; + } if (bp->link_info.duplex == BNXT_LINK_DUPLEX_FULL) duplex = "full"; else @@ -8387,7 +8392,6 @@ static void bnxt_report_link(struct bnxt *bp) flow_ctrl = "ON - receive"; else flow_ctrl = "none"; - speed = bnxt_fw_to_ethtool_speed(bp->link_info.link_speed); netdev_info(bp->dev, "NIC Link is Up, %u Mbps %s duplex, Flow control: %s\n", speed, duplex, flow_ctrl); if (bp->flags & BNXT_FLAG_EEE_CAP) diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c index 7277706847b1..8f0eec9fb17b 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core.c @@ -493,6 +493,9 @@ static void mlxsw_emad_transmit_retry(struct mlxsw_core *mlxsw_core, err = mlxsw_emad_transmit(trans->core, trans); if (err == 0) return; + + if (!atomic_dec_and_test(&trans->active)) + return; } else { err = -EIO; } diff --git a/drivers/net/wan/hdlc_fr.c b/drivers/net/wan/hdlc_fr.c index d6cfd51613ed..3a44dad87602 100644 --- a/drivers/net/wan/hdlc_fr.c +++ b/drivers/net/wan/hdlc_fr.c @@ -273,63 +273,69 @@ static inline struct net_device **get_dev_p(struct pvc_device *pvc, static int fr_hard_header(struct sk_buff **skb_p, u16 dlci) { - u16 head_len; struct sk_buff *skb = *skb_p; - switch (skb->protocol) { - case cpu_to_be16(NLPID_CCITT_ANSI_LMI): - head_len = 4; - skb_push(skb, head_len); - skb->data[3] = NLPID_CCITT_ANSI_LMI; - break; - - case cpu_to_be16(NLPID_CISCO_LMI): - head_len = 4; - skb_push(skb, head_len); - skb->data[3] = NLPID_CISCO_LMI; - break; - - case cpu_to_be16(ETH_P_IP): - head_len = 4; - skb_push(skb, head_len); - skb->data[3] = NLPID_IP; - break; - - case cpu_to_be16(ETH_P_IPV6): - head_len = 4; - skb_push(skb, head_len); - skb->data[3] = NLPID_IPV6; - break; - - case cpu_to_be16(ETH_P_802_3): - head_len = 10; - if (skb_headroom(skb) < head_len) { - struct sk_buff *skb2 = skb_realloc_headroom(skb, - head_len); + if (!skb->dev) { /* Control packets */ + switch (dlci) { + case LMI_CCITT_ANSI_DLCI: + skb_push(skb, 4); + skb->data[3] = NLPID_CCITT_ANSI_LMI; + break; + + case LMI_CISCO_DLCI: + skb_push(skb, 4); + skb->data[3] = NLPID_CISCO_LMI; + break; + + default: + return -EINVAL; + } + + } else if (skb->dev->type == ARPHRD_DLCI) { + switch (skb->protocol) { + case htons(ETH_P_IP): + skb_push(skb, 4); + skb->data[3] = NLPID_IP; + break; + + case htons(ETH_P_IPV6): + skb_push(skb, 4); + skb->data[3] = NLPID_IPV6; + break; + + default: + skb_push(skb, 10); + skb->data[3] = FR_PAD; + skb->data[4] = NLPID_SNAP; + /* OUI 00-00-00 indicates an Ethertype follows */ + skb->data[5] = 0x00; + skb->data[6] = 0x00; + skb->data[7] = 0x00; + /* This should be an Ethertype: */ + *(__be16 *)(skb->data + 8) = skb->protocol; + } + + } else if (skb->dev->type == ARPHRD_ETHER) { + if (skb_headroom(skb) < 10) { + struct sk_buff *skb2 = skb_realloc_headroom(skb, 10); if (!skb2) return -ENOBUFS; dev_kfree_skb(skb); skb = *skb_p = skb2; } - skb_push(skb, head_len); + skb_push(skb, 10); skb->data[3] = FR_PAD; skb->data[4] = NLPID_SNAP; - skb->data[5] = FR_PAD; + /* OUI 00-80-C2 stands for the 802.1 organization */ + skb->data[5] = 0x00; skb->data[6] = 0x80; skb->data[7] = 0xC2; + /* PID 00-07 stands for Ethernet frames without FCS */ skb->data[8] = 0x00; - skb->data[9] = 0x07; /* bridged Ethernet frame w/out FCS */ - break; + skb->data[9] = 0x07; - default: - head_len = 10; - skb_push(skb, head_len); - skb->data[3] = FR_PAD; - skb->data[4] = NLPID_SNAP; - skb->data[5] = FR_PAD; - skb->data[6] = FR_PAD; - skb->data[7] = FR_PAD; - *(__be16*)(skb->data + 8) = skb->protocol; + } else { + return -EINVAL; } dlci_to_q922(skb->data, dlci); @@ -425,8 +431,8 @@ static netdev_tx_t pvc_xmit(struct sk_buff *skb, struct net_device *dev) skb_put(skb, pad); memset(skb->data + len, 0, pad); } - skb->protocol = cpu_to_be16(ETH_P_802_3); } + skb->dev = dev; if (!fr_hard_header(&skb, pvc->dlci)) { dev->stats.tx_bytes += skb->len; dev->stats.tx_packets++; @@ -494,10 +500,8 @@ static void fr_lmi_send(struct net_device *dev, int fullrep) memset(skb->data, 0, len); skb_reserve(skb, 4); if (lmi == LMI_CISCO) { - skb->protocol = cpu_to_be16(NLPID_CISCO_LMI); fr_hard_header(&skb, LMI_CISCO_DLCI); } else { - skb->protocol = cpu_to_be16(NLPID_CCITT_ANSI_LMI); fr_hard_header(&skb, LMI_CCITT_ANSI_DLCI); } data = skb_tail_pointer(skb); diff --git a/drivers/net/wireless/ath/ath10k/htt_rx.c b/drivers/net/wireless/ath/ath10k/htt_rx.c index 8ca0a808a644..04095f91d301 100644 --- a/drivers/net/wireless/ath/ath10k/htt_rx.c +++ b/drivers/net/wireless/ath/ath10k/htt_rx.c @@ -949,6 +949,7 @@ static void ath10k_htt_rx_h_rates(struct ath10k *ar, u8 preamble = 0; u8 group_id; u32 info1, info2, info3; + u32 stbc, nsts_su; info1 = __le32_to_cpu(rxd->ppdu_start.info1); info2 = __le32_to_cpu(rxd->ppdu_start.info2); @@ -993,11 +994,16 @@ static void ath10k_htt_rx_h_rates(struct ath10k *ar, */ bw = info2 & 3; sgi = info3 & 1; + stbc = (info2 >> 3) & 1; group_id = (info2 >> 4) & 0x3F; if (GROUP_ID_IS_SU_MIMO(group_id)) { mcs = (info3 >> 4) & 0x0F; - nss = ((info2 >> 10) & 0x07) + 1; + nsts_su = ((info2 >> 10) & 0x07); + if (stbc) + nss = (nsts_su >> 2) + 1; + else + nss = (nsts_su + 1); } else { /* Hardware doesn't decode VHT-SIG-B into Rx descriptor * so it's impossible to decode MCS. Also since diff --git a/drivers/net/wireless/ath/ath10k/sdio.c b/drivers/net/wireless/ath/ath10k/sdio.c index 8fe626deadeb..24b1927a0751 100644 --- a/drivers/net/wireless/ath/ath10k/sdio.c +++ b/drivers/net/wireless/ath/ath10k/sdio.c @@ -550,6 +550,10 @@ static int ath10k_sdio_mbox_rx_alloc(struct ath10k *ar, le16_to_cpu(htc_hdr->len), ATH10K_HTC_MBOX_MAX_PAYLOAD_LENGTH); ret = -ENOMEM; + + queue_work(ar->workqueue, &ar->restart_work); + ath10k_warn(ar, "exceeds length, start recovery\n"); + goto err; } diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fweh.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fweh.c index 79c8a858b6d6..a30fcfbf2ee7 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fweh.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fweh.c @@ -304,10 +304,12 @@ void brcmf_fweh_detach(struct brcmf_pub *drvr) { struct brcmf_fweh_info *fweh = &drvr->fweh; - /* cancel the worker */ - cancel_work_sync(&fweh->event_work); - WARN_ON(!list_empty(&fweh->event_q)); - memset(fweh->evt_handler, 0, sizeof(fweh->evt_handler)); + /* cancel the worker if initialized */ + if (fweh->event_work.func) { + cancel_work_sync(&fweh->event_work); + WARN_ON(!list_empty(&fweh->event_q)); + memset(fweh->evt_handler, 0, sizeof(fweh->evt_handler)); + } } /** diff --git a/drivers/net/xen-netback/common.h b/drivers/net/xen-netback/common.h index 05847eb91a1b..32fe131ba366 100644 --- a/drivers/net/xen-netback/common.h +++ b/drivers/net/xen-netback/common.h @@ -140,6 +140,20 @@ struct xenvif_queue { /* Per-queue data for xenvif */ char name[QUEUE_NAME_SIZE]; /* DEVNAME-qN */ struct xenvif *vif; /* Parent VIF */ + /* + * TX/RX common EOI handling. + * When feature-split-event-channels = 0, interrupt handler sets + * NETBK_COMMON_EOI, otherwise NETBK_RX_EOI and NETBK_TX_EOI are set + * by the RX and TX interrupt handlers. + * RX and TX handler threads will issue an EOI when either + * NETBK_COMMON_EOI or their specific bits (NETBK_RX_EOI or + * NETBK_TX_EOI) are set and they will reset those bits. + */ + atomic_t eoi_pending; +#define NETBK_RX_EOI 0x01 +#define NETBK_TX_EOI 0x02 +#define NETBK_COMMON_EOI 0x04 + /* Use NAPI for guest TX */ struct napi_struct napi; /* When feature-split-event-channels = 0, tx_irq = rx_irq. */ @@ -375,6 +389,7 @@ int xenvif_dealloc_kthread(void *data); irqreturn_t xenvif_ctrl_irq_fn(int irq, void *data); +bool xenvif_have_rx_work(struct xenvif_queue *queue, bool test_kthread); void xenvif_rx_action(struct xenvif_queue *queue); void xenvif_rx_queue_tail(struct xenvif_queue *queue, struct sk_buff *skb); diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c index 103ed00775eb..e889488b84a0 100644 --- a/drivers/net/xen-netback/interface.c +++ b/drivers/net/xen-netback/interface.c @@ -77,12 +77,28 @@ int xenvif_schedulable(struct xenvif *vif) !vif->disabled; } +static bool xenvif_handle_tx_interrupt(struct xenvif_queue *queue) +{ + bool rc; + + rc = RING_HAS_UNCONSUMED_REQUESTS(&queue->tx); + if (rc) + napi_schedule(&queue->napi); + return rc; +} + static irqreturn_t xenvif_tx_interrupt(int irq, void *dev_id) { struct xenvif_queue *queue = dev_id; + int old; - if (RING_HAS_UNCONSUMED_REQUESTS(&queue->tx)) - napi_schedule(&queue->napi); + old = atomic_fetch_or(NETBK_TX_EOI, &queue->eoi_pending); + WARN(old & NETBK_TX_EOI, "Interrupt while EOI pending\n"); + + if (!xenvif_handle_tx_interrupt(queue)) { + atomic_andnot(NETBK_TX_EOI, &queue->eoi_pending); + xen_irq_lateeoi(irq, XEN_EOI_FLAG_SPURIOUS); + } return IRQ_HANDLED; } @@ -116,19 +132,46 @@ static int xenvif_poll(struct napi_struct *napi, int budget) return work_done; } +static bool xenvif_handle_rx_interrupt(struct xenvif_queue *queue) +{ + bool rc; + + rc = xenvif_have_rx_work(queue, false); + if (rc) + xenvif_kick_thread(queue); + return rc; +} + static irqreturn_t xenvif_rx_interrupt(int irq, void *dev_id) { struct xenvif_queue *queue = dev_id; + int old; - xenvif_kick_thread(queue); + old = atomic_fetch_or(NETBK_RX_EOI, &queue->eoi_pending); + WARN(old & NETBK_RX_EOI, "Interrupt while EOI pending\n"); + + if (!xenvif_handle_rx_interrupt(queue)) { + atomic_andnot(NETBK_RX_EOI, &queue->eoi_pending); + xen_irq_lateeoi(irq, XEN_EOI_FLAG_SPURIOUS); + } return IRQ_HANDLED; } irqreturn_t xenvif_interrupt(int irq, void *dev_id) { - xenvif_tx_interrupt(irq, dev_id); - xenvif_rx_interrupt(irq, dev_id); + struct xenvif_queue *queue = dev_id; + int old; + + old = atomic_fetch_or(NETBK_COMMON_EOI, &queue->eoi_pending); + WARN(old, "Interrupt while EOI pending\n"); + + /* Use bitwise or as we need to call both functions. */ + if ((!xenvif_handle_tx_interrupt(queue) | + !xenvif_handle_rx_interrupt(queue))) { + atomic_andnot(NETBK_COMMON_EOI, &queue->eoi_pending); + xen_irq_lateeoi(irq, XEN_EOI_FLAG_SPURIOUS); + } return IRQ_HANDLED; } @@ -595,7 +638,7 @@ int xenvif_connect_ctrl(struct xenvif *vif, grant_ref_t ring_ref, shared = (struct xen_netif_ctrl_sring *)addr; BACK_RING_INIT(&vif->ctrl, shared, XEN_PAGE_SIZE); - err = bind_interdomain_evtchn_to_irq(vif->domid, evtchn); + err = bind_interdomain_evtchn_to_irq_lateeoi(vif->domid, evtchn); if (err < 0) goto err_unmap; @@ -653,7 +696,7 @@ int xenvif_connect_data(struct xenvif_queue *queue, if (tx_evtchn == rx_evtchn) { /* feature-split-event-channels == 0 */ - err = bind_interdomain_evtchn_to_irqhandler( + err = bind_interdomain_evtchn_to_irqhandler_lateeoi( queue->vif->domid, tx_evtchn, xenvif_interrupt, 0, queue->name, queue); if (err < 0) @@ -664,7 +707,7 @@ int xenvif_connect_data(struct xenvif_queue *queue, /* feature-split-event-channels == 1 */ snprintf(queue->tx_irq_name, sizeof(queue->tx_irq_name), "%s-tx", queue->name); - err = bind_interdomain_evtchn_to_irqhandler( + err = bind_interdomain_evtchn_to_irqhandler_lateeoi( queue->vif->domid, tx_evtchn, xenvif_tx_interrupt, 0, queue->tx_irq_name, queue); if (err < 0) @@ -674,7 +717,7 @@ int xenvif_connect_data(struct xenvif_queue *queue, snprintf(queue->rx_irq_name, sizeof(queue->rx_irq_name), "%s-rx", queue->name); - err = bind_interdomain_evtchn_to_irqhandler( + err = bind_interdomain_evtchn_to_irqhandler_lateeoi( queue->vif->domid, rx_evtchn, xenvif_rx_interrupt, 0, queue->rx_irq_name, queue); if (err < 0) diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c index 0020b2e8c279..fa1ac0abc924 100644 --- a/drivers/net/xen-netback/netback.c +++ b/drivers/net/xen-netback/netback.c @@ -162,6 +162,10 @@ void xenvif_napi_schedule_or_enable_events(struct xenvif_queue *queue) if (more_to_do) napi_schedule(&queue->napi); + else if (atomic_fetch_andnot(NETBK_TX_EOI | NETBK_COMMON_EOI, + &queue->eoi_pending) & + (NETBK_TX_EOI | NETBK_COMMON_EOI)) + xen_irq_lateeoi(queue->tx_irq, 0); } static void tx_add_credit(struct xenvif_queue *queue) @@ -1622,9 +1626,14 @@ static bool xenvif_ctrl_work_todo(struct xenvif *vif) irqreturn_t xenvif_ctrl_irq_fn(int irq, void *data) { struct xenvif *vif = data; + unsigned int eoi_flag = XEN_EOI_FLAG_SPURIOUS; - while (xenvif_ctrl_work_todo(vif)) + while (xenvif_ctrl_work_todo(vif)) { xenvif_ctrl_action(vif); + eoi_flag = 0; + } + + xen_irq_lateeoi(irq, eoi_flag); return IRQ_HANDLED; } diff --git a/drivers/net/xen-netback/rx.c b/drivers/net/xen-netback/rx.c index ef5887037b22..9b62f65b630e 100644 --- a/drivers/net/xen-netback/rx.c +++ b/drivers/net/xen-netback/rx.c @@ -490,13 +490,13 @@ static bool xenvif_rx_queue_ready(struct xenvif_queue *queue) return queue->stalled && prod - cons >= 1; } -static bool xenvif_have_rx_work(struct xenvif_queue *queue) +bool xenvif_have_rx_work(struct xenvif_queue *queue, bool test_kthread) { return xenvif_rx_ring_slots_available(queue) || (queue->vif->stall_timeout && (xenvif_rx_queue_stalled(queue) || xenvif_rx_queue_ready(queue))) || - kthread_should_stop() || + (test_kthread && kthread_should_stop()) || queue->vif->disabled; } @@ -527,15 +527,20 @@ static void xenvif_wait_for_rx_work(struct xenvif_queue *queue) { DEFINE_WAIT(wait); - if (xenvif_have_rx_work(queue)) + if (xenvif_have_rx_work(queue, true)) return; for (;;) { long ret; prepare_to_wait(&queue->wq, &wait, TASK_INTERRUPTIBLE); - if (xenvif_have_rx_work(queue)) + if (xenvif_have_rx_work(queue, true)) break; + if (atomic_fetch_andnot(NETBK_RX_EOI | NETBK_COMMON_EOI, + &queue->eoi_pending) & + (NETBK_RX_EOI | NETBK_COMMON_EOI)) + xen_irq_lateeoi(queue->rx_irq, 0); + ret = schedule_timeout(xenvif_rx_queue_timeout(queue)); if (!ret) break; diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index abe4fe496d05..a41ee9feab8e 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -1679,7 +1679,6 @@ static int nvme_rdma_cm_handler(struct rdma_cm_id *cm_id, complete(&queue->cm_done); return 0; case RDMA_CM_EVENT_REJECTED: - nvme_rdma_destroy_queue_ib(queue); cm_error = nvme_rdma_conn_rejected(queue, ev); break; case RDMA_CM_EVENT_ROUTE_ERROR: diff --git a/drivers/pci/pci-acpi.c b/drivers/pci/pci-acpi.c index 0c02d500158f..3f40f951a6cd 100644 --- a/drivers/pci/pci-acpi.c +++ b/drivers/pci/pci-acpi.c @@ -944,6 +944,16 @@ static bool acpi_pci_bridge_d3(struct pci_dev *dev) if (!dev->is_hotplug_bridge) return false; + /* Assume D3 support if the bridge is power-manageable by ACPI. */ + adev = ACPI_COMPANION(&dev->dev); + if (!adev && !pci_dev_is_added(dev)) { + adev = acpi_pci_find_companion(&dev->dev); + ACPI_COMPANION_SET(&dev->dev, adev); + } + + if (adev && acpi_device_power_manageable(adev)) + return true; + /* * Look for a special _DSD property for the root port and if it * is set we know the hierarchy behind it supports D3 just fine. diff --git a/drivers/power/supply/bq27xxx_battery.c b/drivers/power/supply/bq27xxx_battery.c index 664e50103eaa..aff0a0a5e7f8 100644 --- a/drivers/power/supply/bq27xxx_battery.c +++ b/drivers/power/supply/bq27xxx_battery.c @@ -1678,8 +1678,6 @@ static int bq27xxx_battery_status(struct bq27xxx_device_info *di, status = POWER_SUPPLY_STATUS_FULL; else if (di->cache.flags & BQ27000_FLAG_CHGS) status = POWER_SUPPLY_STATUS_CHARGING; - else if (power_supply_am_i_supplied(di->bat) > 0) - status = POWER_SUPPLY_STATUS_NOT_CHARGING; else status = POWER_SUPPLY_STATUS_DISCHARGING; } else { @@ -1691,6 +1689,10 @@ static int bq27xxx_battery_status(struct bq27xxx_device_info *di, status = POWER_SUPPLY_STATUS_CHARGING; } + if ((status == POWER_SUPPLY_STATUS_DISCHARGING) && + (power_supply_am_i_supplied(di->bat) > 0)) + status = POWER_SUPPLY_STATUS_NOT_CHARGING; + val->intval = status; return 0; diff --git a/drivers/power/supply/test_power.c b/drivers/power/supply/test_power.c index c3cad2b6daba..1139ca725195 100644 --- a/drivers/power/supply/test_power.c +++ b/drivers/power/supply/test_power.c @@ -341,6 +341,7 @@ static int param_set_ac_online(const char *key, const struct kernel_param *kp) static int param_get_ac_online(char *buffer, const struct kernel_param *kp) { strcpy(buffer, map_get_key(map_ac_online, ac_online, "unknown")); + strcat(buffer, "\n"); return strlen(buffer); } @@ -354,6 +355,7 @@ static int param_set_usb_online(const char *key, const struct kernel_param *kp) static int param_get_usb_online(char *buffer, const struct kernel_param *kp) { strcpy(buffer, map_get_key(map_ac_online, usb_online, "unknown")); + strcat(buffer, "\n"); return strlen(buffer); } @@ -368,6 +370,7 @@ static int param_set_battery_status(const char *key, static int param_get_battery_status(char *buffer, const struct kernel_param *kp) { strcpy(buffer, map_get_key(map_status, battery_status, "unknown")); + strcat(buffer, "\n"); return strlen(buffer); } @@ -382,6 +385,7 @@ static int param_set_battery_health(const char *key, static int param_get_battery_health(char *buffer, const struct kernel_param *kp) { strcpy(buffer, map_get_key(map_health, battery_health, "unknown")); + strcat(buffer, "\n"); return strlen(buffer); } @@ -397,6 +401,7 @@ static int param_get_battery_present(char *buffer, const struct kernel_param *kp) { strcpy(buffer, map_get_key(map_present, battery_present, "unknown")); + strcat(buffer, "\n"); return strlen(buffer); } @@ -414,6 +419,7 @@ static int param_get_battery_technology(char *buffer, { strcpy(buffer, map_get_key(map_technology, battery_technology, "unknown")); + strcat(buffer, "\n"); return strlen(buffer); } diff --git a/drivers/rpmsg/qcom_glink_native.c b/drivers/rpmsg/qcom_glink_native.c index 1995f5b3ea67..d5114abcde19 100644 --- a/drivers/rpmsg/qcom_glink_native.c +++ b/drivers/rpmsg/qcom_glink_native.c @@ -970,7 +970,7 @@ static int qcom_glink_rx_open_ack(struct qcom_glink *glink, unsigned int lcid) return -EINVAL; } - complete(&channel->open_ack); + complete_all(&channel->open_ack); return 0; } @@ -1178,7 +1178,7 @@ static int qcom_glink_announce_create(struct rpmsg_device *rpdev) __be32 *val = defaults; int size; - if (glink->intentless) + if (glink->intentless || !completion_done(&channel->open_ack)) return 0; prop = of_find_property(np, "qcom,intents", NULL); @@ -1413,7 +1413,7 @@ static int qcom_glink_rx_open(struct qcom_glink *glink, unsigned int rcid, channel->rcid = ret; spin_unlock_irqrestore(&glink->idr_lock, flags); - complete(&channel->open_req); + complete_all(&channel->open_req); if (create_device) { rpdev = kzalloc(sizeof(*rpdev), GFP_KERNEL); diff --git a/drivers/rtc/rtc-rx8010.c b/drivers/rtc/rtc-rx8010.c index 8102469e27c0..0c436aea0da4 100644 --- a/drivers/rtc/rtc-rx8010.c +++ b/drivers/rtc/rtc-rx8010.c @@ -424,16 +424,26 @@ static int rx8010_ioctl(struct device *dev, unsigned int cmd, unsigned long arg) } } -static struct rtc_class_ops rx8010_rtc_ops = { +static const struct rtc_class_ops rx8010_rtc_ops_default = { .read_time = rx8010_get_time, .set_time = rx8010_set_time, .ioctl = rx8010_ioctl, }; +static const struct rtc_class_ops rx8010_rtc_ops_alarm = { + .read_time = rx8010_get_time, + .set_time = rx8010_set_time, + .ioctl = rx8010_ioctl, + .read_alarm = rx8010_read_alarm, + .set_alarm = rx8010_set_alarm, + .alarm_irq_enable = rx8010_alarm_irq_enable, +}; + static int rx8010_probe(struct i2c_client *client, const struct i2c_device_id *id) { struct i2c_adapter *adapter = client->adapter; + const struct rtc_class_ops *rtc_ops; struct rx8010_data *rx8010; int err = 0; @@ -464,16 +474,16 @@ static int rx8010_probe(struct i2c_client *client, if (err) { dev_err(&client->dev, "unable to request IRQ\n"); - client->irq = 0; - } else { - rx8010_rtc_ops.read_alarm = rx8010_read_alarm; - rx8010_rtc_ops.set_alarm = rx8010_set_alarm; - rx8010_rtc_ops.alarm_irq_enable = rx8010_alarm_irq_enable; + return err; } + + rtc_ops = &rx8010_rtc_ops_alarm; + } else { + rtc_ops = &rx8010_rtc_ops_default; } rx8010->rtc = devm_rtc_device_register(&client->dev, client->name, - &rx8010_rtc_ops, THIS_MODULE); + rtc_ops, THIS_MODULE); if (IS_ERR(rx8010->rtc)) { dev_err(&client->dev, "unable to register the class device\n"); diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c index d84d95cac2a1..412009e2b948 100644 --- a/drivers/scsi/qla2xxx/qla_target.c +++ b/drivers/scsi/qla2xxx/qla_target.c @@ -1230,14 +1230,15 @@ void qlt_schedule_sess_for_deletion(struct fc_port *sess) case DSC_DELETE_PEND: return; case DSC_DELETED: - if (tgt && tgt->tgt_stop && (tgt->sess_count == 0)) - wake_up_all(&tgt->waitQ); - if (sess->vha->fcport_count == 0) - wake_up_all(&sess->vha->fcport_waitQ); - if (!sess->plogi_link[QLT_PLOGI_LINK_SAME_WWN] && - !sess->plogi_link[QLT_PLOGI_LINK_CONFLICT]) + !sess->plogi_link[QLT_PLOGI_LINK_CONFLICT]) { + if (tgt && tgt->tgt_stop && tgt->sess_count == 0) + wake_up_all(&tgt->waitQ); + + if (sess->vha->fcport_count == 0) + wake_up_all(&sess->vha->fcport_waitQ); return; + } break; case DSC_UPD_FCPORT: /* diff --git a/drivers/spi/spi-sprd.c b/drivers/spi/spi-sprd.c index fa597e27be17..e60aff990395 100644 --- a/drivers/spi/spi-sprd.c +++ b/drivers/spi/spi-sprd.c @@ -563,11 +563,11 @@ static int sprd_spi_dma_request(struct sprd_spi *ss) ss->dma.dma_chan[SPRD_SPI_TX] = dma_request_chan(ss->dev, "tx_chn"); if (IS_ERR_OR_NULL(ss->dma.dma_chan[SPRD_SPI_TX])) { + dma_release_channel(ss->dma.dma_chan[SPRD_SPI_RX]); if (PTR_ERR(ss->dma.dma_chan[SPRD_SPI_TX]) == -EPROBE_DEFER) return PTR_ERR(ss->dma.dma_chan[SPRD_SPI_TX]); dev_err(ss->dev, "request TX DMA channel failed!\n"); - dma_release_channel(ss->dma.dma_chan[SPRD_SPI_RX]); return PTR_ERR(ss->dma.dma_chan[SPRD_SPI_TX]); } diff --git a/drivers/staging/comedi/drivers/cb_pcidas.c b/drivers/staging/comedi/drivers/cb_pcidas.c index 02ae00c95313..1893c70de0b9 100644 --- a/drivers/staging/comedi/drivers/cb_pcidas.c +++ b/drivers/staging/comedi/drivers/cb_pcidas.c @@ -1342,6 +1342,7 @@ static int cb_pcidas_auto_attach(struct comedi_device *dev, if (dev->irq && board->has_ao_fifo) { dev->write_subdev = s; s->subdev_flags |= SDF_CMD_WRITE; + s->len_chanlist = s->n_chan; s->do_cmdtest = cb_pcidas_ao_cmdtest; s->do_cmd = cb_pcidas_ao_cmd; s->cancel = cb_pcidas_ao_cancel; diff --git a/drivers/staging/fieldbus/anybuss/arcx-anybus.c b/drivers/staging/fieldbus/anybuss/arcx-anybus.c index 2ecffa42e561..fbe693816f07 100644 --- a/drivers/staging/fieldbus/anybuss/arcx-anybus.c +++ b/drivers/staging/fieldbus/anybuss/arcx-anybus.c @@ -297,7 +297,7 @@ static int controller_probe(struct platform_device *pdev) regulator = devm_regulator_register(dev, &can_power_desc, &config); if (IS_ERR(regulator)) { err = PTR_ERR(regulator); - goto out_reset; + goto out_ida; } /* make controller info visible to userspace */ cd->class_dev = kzalloc(sizeof(*cd->class_dev), GFP_KERNEL); diff --git a/drivers/staging/octeon/ethernet-mdio.c b/drivers/staging/octeon/ethernet-mdio.c index ffac0c4b3f5c..022c71e69a23 100644 --- a/drivers/staging/octeon/ethernet-mdio.c +++ b/drivers/staging/octeon/ethernet-mdio.c @@ -147,12 +147,6 @@ int cvm_oct_phy_setup_device(struct net_device *dev) phy_node = of_parse_phandle(priv->of_node, "phy-handle", 0); if (!phy_node && of_phy_is_fixed_link(priv->of_node)) { - int rc; - - rc = of_phy_register_fixed_link(priv->of_node); - if (rc) - return rc; - phy_node = of_node_get(priv->of_node); } if (!phy_node) diff --git a/drivers/staging/octeon/ethernet-rx.c b/drivers/staging/octeon/ethernet-rx.c index 0e65955c746b..9a242d68a26b 100644 --- a/drivers/staging/octeon/ethernet-rx.c +++ b/drivers/staging/octeon/ethernet-rx.c @@ -69,15 +69,17 @@ static inline int cvm_oct_check_rcv_error(cvmx_wqe_t *work) else port = work->word1.cn38xx.ipprt; - if ((work->word2.snoip.err_code == 10) && (work->word1.len <= 64)) { + if ((work->word2.snoip.err_code == 10) && (work->word1.len <= 64)) /* * Ignore length errors on min size packets. Some * equipment incorrectly pads packets to 64+4FCS * instead of 60+4FCS. Note these packets still get * counted as frame errors. */ - } else if (work->word2.snoip.err_code == 5 || - work->word2.snoip.err_code == 7) { + return 0; + + if (work->word2.snoip.err_code == 5 || + work->word2.snoip.err_code == 7) { /* * We received a packet with either an alignment error * or a FCS error. This may be signalling that we are @@ -108,7 +110,10 @@ static inline int cvm_oct_check_rcv_error(cvmx_wqe_t *work) /* Port received 0xd5 preamble */ work->packet_ptr.s.addr += i + 1; work->word1.len -= i + 5; - } else if ((*ptr & 0xf) == 0xd) { + return 0; + } + + if ((*ptr & 0xf) == 0xd) { /* Port received 0xd preamble */ work->packet_ptr.s.addr += i; work->word1.len -= i + 4; @@ -118,21 +123,20 @@ static inline int cvm_oct_check_rcv_error(cvmx_wqe_t *work) ((*(ptr + 1) & 0xf) << 4); ptr++; } - } else { - printk_ratelimited("Port %d unknown preamble, packet dropped\n", - port); - cvm_oct_free_work(work); - return 1; + return 0; } + + printk_ratelimited("Port %d unknown preamble, packet dropped\n", + port); + cvm_oct_free_work(work); + return 1; } - } else { - printk_ratelimited("Port %d receive error code %d, packet dropped\n", - port, work->word2.snoip.err_code); - cvm_oct_free_work(work); - return 1; } - return 0; + printk_ratelimited("Port %d receive error code %d, packet dropped\n", + port, work->word2.snoip.err_code); + cvm_oct_free_work(work); + return 1; } static void copy_segments_to_skb(cvmx_wqe_t *work, struct sk_buff *skb) diff --git a/drivers/staging/octeon/ethernet.c b/drivers/staging/octeon/ethernet.c index cf8e9a23ebf9..77b7c1fd9d78 100644 --- a/drivers/staging/octeon/ethernet.c +++ b/drivers/staging/octeon/ethernet.c @@ -13,6 +13,7 @@ #include <linux/phy.h> #include <linux/slab.h> #include <linux/interrupt.h> +#include <linux/of_mdio.h> #include <linux/of_net.h> #include <linux/if_ether.h> #include <linux/if_vlan.h> @@ -894,6 +895,14 @@ static int cvm_oct_probe(struct platform_device *pdev) break; } + if (priv->of_node && of_phy_is_fixed_link(priv->of_node)) { + if (of_phy_register_fixed_link(priv->of_node)) { + netdev_err(dev, "Failed to register fixed link for interface %d, port %d\n", + interface, priv->port); + dev->netdev_ops = NULL; + } + } + if (!dev->netdev_ops) { free_netdev(dev); } else if (register_netdev(dev) < 0) { diff --git a/drivers/tty/vt/keyboard.c b/drivers/tty/vt/keyboard.c index 568b2171f335..b6e78fdbfdff 100644 --- a/drivers/tty/vt/keyboard.c +++ b/drivers/tty/vt/keyboard.c @@ -742,8 +742,13 @@ static void k_fn(struct vc_data *vc, unsigned char value, char up_flag) return; if ((unsigned)value < ARRAY_SIZE(func_table)) { + unsigned long flags; + + spin_lock_irqsave(&func_buf_lock, flags); if (func_table[value]) puts_queue(vc, func_table[value]); + spin_unlock_irqrestore(&func_buf_lock, flags); + } else pr_err("k_fn called with value=%d\n", value); } @@ -1990,13 +1995,11 @@ int vt_do_kdsk_ioctl(int cmd, struct kbentry __user *user_kbe, int perm, #undef s #undef v -/* FIXME: This one needs untangling and locking */ +/* FIXME: This one needs untangling */ int vt_do_kdgkb_ioctl(int cmd, struct kbsentry __user *user_kdgkb, int perm) { struct kbsentry *kbs; - char *p; u_char *q; - u_char __user *up; int sz, fnw_sz; int delta; char *first_free, *fj, *fnw; @@ -2022,23 +2025,19 @@ int vt_do_kdgkb_ioctl(int cmd, struct kbsentry __user *user_kdgkb, int perm) i = kbs->kb_func; switch (cmd) { - case KDGKBSENT: - sz = sizeof(kbs->kb_string) - 1; /* sz should have been - a struct member */ - up = user_kdgkb->kb_string; - p = func_table[i]; - if(p) - for ( ; *p && sz; p++, sz--) - if (put_user(*p, up++)) { - ret = -EFAULT; - goto reterr; - } - if (put_user('\0', up)) { - ret = -EFAULT; - goto reterr; - } - kfree(kbs); - return ((p && *p) ? -EOVERFLOW : 0); + case KDGKBSENT: { + /* size should have been a struct member */ + ssize_t len = sizeof(user_kdgkb->kb_string); + + spin_lock_irqsave(&func_buf_lock, flags); + len = strlcpy(kbs->kb_string, func_table[i] ? : "", len); + spin_unlock_irqrestore(&func_buf_lock, flags); + + ret = copy_to_user(user_kdgkb->kb_string, kbs->kb_string, + len + 1) ? -EFAULT : 0; + + goto reterr; + } case KDSKBSENT: if (!perm) { ret = -EPERM; diff --git a/drivers/tty/vt/vt_ioctl.c b/drivers/tty/vt/vt_ioctl.c index cbc85c995d92..4f51be17427c 100644 --- a/drivers/tty/vt/vt_ioctl.c +++ b/drivers/tty/vt/vt_ioctl.c @@ -244,7 +244,7 @@ int vt_waitactive(int n) static inline int -do_fontx_ioctl(int cmd, struct consolefontdesc __user *user_cfd, int perm, struct console_font_op *op) +do_fontx_ioctl(struct vc_data *vc, int cmd, struct consolefontdesc __user *user_cfd, int perm, struct console_font_op *op) { struct consolefontdesc cfdarg; int i; @@ -262,15 +262,16 @@ do_fontx_ioctl(int cmd, struct consolefontdesc __user *user_cfd, int perm, struc op->height = cfdarg.charheight; op->charcount = cfdarg.charcount; op->data = cfdarg.chardata; - return con_font_op(vc_cons[fg_console].d, op); - case GIO_FONTX: { + return con_font_op(vc, op); + + case GIO_FONTX: op->op = KD_FONT_OP_GET; op->flags = KD_FONT_FLAG_OLD; op->width = 8; op->height = cfdarg.charheight; op->charcount = cfdarg.charcount; op->data = cfdarg.chardata; - i = con_font_op(vc_cons[fg_console].d, op); + i = con_font_op(vc, op); if (i) return i; cfdarg.charheight = op->height; @@ -278,7 +279,6 @@ do_fontx_ioctl(int cmd, struct consolefontdesc __user *user_cfd, int perm, struc if (copy_to_user(user_cfd, &cfdarg, sizeof(struct consolefontdesc))) return -EFAULT; return 0; - } } return -EINVAL; } @@ -924,7 +924,7 @@ int vt_ioctl(struct tty_struct *tty, op.height = 0; op.charcount = 256; op.data = up; - ret = con_font_op(vc_cons[fg_console].d, &op); + ret = con_font_op(vc, &op); break; } @@ -935,7 +935,7 @@ int vt_ioctl(struct tty_struct *tty, op.height = 32; op.charcount = 256; op.data = up; - ret = con_font_op(vc_cons[fg_console].d, &op); + ret = con_font_op(vc, &op); break; } @@ -952,7 +952,7 @@ int vt_ioctl(struct tty_struct *tty, case PIO_FONTX: case GIO_FONTX: - ret = do_fontx_ioctl(cmd, up, perm, &op); + ret = do_fontx_ioctl(vc, cmd, up, perm, &op); break; case PIO_FONTRESET: @@ -969,11 +969,11 @@ int vt_ioctl(struct tty_struct *tty, { op.op = KD_FONT_OP_SET_DEFAULT; op.data = NULL; - ret = con_font_op(vc_cons[fg_console].d, &op); + ret = con_font_op(vc, &op); if (ret) break; console_lock(); - con_set_default_unimap(vc_cons[fg_console].d); + con_set_default_unimap(vc); console_unlock(); break; } @@ -1100,8 +1100,9 @@ struct compat_consolefontdesc { }; static inline int -compat_fontx_ioctl(int cmd, struct compat_consolefontdesc __user *user_cfd, - int perm, struct console_font_op *op) +compat_fontx_ioctl(struct vc_data *vc, int cmd, + struct compat_consolefontdesc __user *user_cfd, + int perm, struct console_font_op *op) { struct compat_consolefontdesc cfdarg; int i; @@ -1119,7 +1120,8 @@ compat_fontx_ioctl(int cmd, struct compat_consolefontdesc __user *user_cfd, op->height = cfdarg.charheight; op->charcount = cfdarg.charcount; op->data = compat_ptr(cfdarg.chardata); - return con_font_op(vc_cons[fg_console].d, op); + return con_font_op(vc, op); + case GIO_FONTX: op->op = KD_FONT_OP_GET; op->flags = KD_FONT_FLAG_OLD; @@ -1127,7 +1129,7 @@ compat_fontx_ioctl(int cmd, struct compat_consolefontdesc __user *user_cfd, op->height = cfdarg.charheight; op->charcount = cfdarg.charcount; op->data = compat_ptr(cfdarg.chardata); - i = con_font_op(vc_cons[fg_console].d, op); + i = con_font_op(vc, op); if (i) return i; cfdarg.charheight = op->height; @@ -1217,7 +1219,7 @@ long vt_compat_ioctl(struct tty_struct *tty, */ case PIO_FONTX: case GIO_FONTX: - return compat_fontx_ioctl(cmd, up, perm, &op); + return compat_fontx_ioctl(vc, cmd, up, perm, &op); case KDFONTOP: return compat_kdfontop_ioctl(up, perm, &op, vc); diff --git a/drivers/uio/uio.c b/drivers/uio/uio.c index a57698985f9c..8313f81968d5 100644 --- a/drivers/uio/uio.c +++ b/drivers/uio/uio.c @@ -1010,8 +1010,6 @@ void uio_unregister_device(struct uio_info *info) idev = info->uio_dev; - uio_free_minor(idev); - mutex_lock(&idev->info_lock); uio_dev_del_attributes(idev); @@ -1026,6 +1024,8 @@ void uio_unregister_device(struct uio_info *info) device_unregister(&idev->dev); + uio_free_minor(idev); + return; } EXPORT_SYMBOL_GPL(uio_unregister_device); diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c index 808722b8294a..ed99d98172f4 100644 --- a/drivers/usb/class/cdc-acm.c +++ b/drivers/usb/class/cdc-acm.c @@ -507,6 +507,7 @@ static void acm_read_bulk_callback(struct urb *urb) "%s - cooling babbling device\n", __func__); usb_mark_last_busy(acm->dev); set_bit(rb->index, &acm->urbs_in_error_delay); + set_bit(ACM_ERROR_DELAY, &acm->flags); cooldown = true; break; default: @@ -532,7 +533,7 @@ static void acm_read_bulk_callback(struct urb *urb) if (stopped || stalled || cooldown) { if (stalled) - schedule_work(&acm->work); + schedule_delayed_work(&acm->dwork, 0); else if (cooldown) schedule_delayed_work(&acm->dwork, HZ / 2); return; @@ -562,13 +563,13 @@ static void acm_write_bulk(struct urb *urb) acm_write_done(acm, wb); spin_unlock_irqrestore(&acm->write_lock, flags); set_bit(EVENT_TTY_WAKEUP, &acm->flags); - schedule_work(&acm->work); + schedule_delayed_work(&acm->dwork, 0); } static void acm_softint(struct work_struct *work) { int i; - struct acm *acm = container_of(work, struct acm, work); + struct acm *acm = container_of(work, struct acm, dwork.work); if (test_bit(EVENT_RX_STALL, &acm->flags)) { smp_mb(); /* against acm_suspend() */ @@ -584,7 +585,7 @@ static void acm_softint(struct work_struct *work) if (test_and_clear_bit(ACM_ERROR_DELAY, &acm->flags)) { for (i = 0; i < acm->rx_buflimit; i++) if (test_and_clear_bit(i, &acm->urbs_in_error_delay)) - acm_submit_read_urb(acm, i, GFP_NOIO); + acm_submit_read_urb(acm, i, GFP_KERNEL); } if (test_and_clear_bit(EVENT_TTY_WAKEUP, &acm->flags)) @@ -1364,7 +1365,6 @@ static int acm_probe(struct usb_interface *intf, acm->ctrlsize = ctrlsize; acm->readsize = readsize; acm->rx_buflimit = num_rx_buf; - INIT_WORK(&acm->work, acm_softint); INIT_DELAYED_WORK(&acm->dwork, acm_softint); init_waitqueue_head(&acm->wioctl); spin_lock_init(&acm->write_lock); @@ -1574,7 +1574,6 @@ static void acm_disconnect(struct usb_interface *intf) } acm_kill_urbs(acm); - cancel_work_sync(&acm->work); cancel_delayed_work_sync(&acm->dwork); tty_unregister_device(acm_tty_driver, acm->minor); @@ -1617,7 +1616,6 @@ static int acm_suspend(struct usb_interface *intf, pm_message_t message) return 0; acm_kill_urbs(acm); - cancel_work_sync(&acm->work); cancel_delayed_work_sync(&acm->dwork); acm->urbs_in_error_delay = 0; diff --git a/drivers/usb/class/cdc-acm.h b/drivers/usb/class/cdc-acm.h index cd5e9d8ab237..b95ff769072e 100644 --- a/drivers/usb/class/cdc-acm.h +++ b/drivers/usb/class/cdc-acm.h @@ -112,8 +112,7 @@ struct acm { # define ACM_ERROR_DELAY 3 unsigned long urbs_in_error_delay; /* these need to be restarted after a delay */ struct usb_cdc_line_coding line; /* bits, stop, parity */ - struct work_struct work; /* work queue entry for various purposes*/ - struct delayed_work dwork; /* for cool downs needed in error recovery */ + struct delayed_work dwork; /* work queue entry for various purposes */ unsigned int ctrlin; /* input control lines (DCD, DSR, RI, break, overruns) */ unsigned int ctrlout; /* output control lines (DTR, RTS) */ struct async_icount iocount; /* counters for control line changes */ diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c index 4cbf29539006..440dbf55ddf7 100644 --- a/drivers/usb/dwc3/core.c +++ b/drivers/usb/dwc3/core.c @@ -1535,6 +1535,17 @@ static int dwc3_probe(struct platform_device *pdev) err5: dwc3_event_buffers_cleanup(dwc); + + usb_phy_shutdown(dwc->usb2_phy); + usb_phy_shutdown(dwc->usb3_phy); + phy_exit(dwc->usb2_generic_phy); + phy_exit(dwc->usb3_generic_phy); + + usb_phy_set_suspend(dwc->usb2_phy, 1); + usb_phy_set_suspend(dwc->usb3_phy, 1); + phy_power_off(dwc->usb2_generic_phy); + phy_power_off(dwc->usb3_generic_phy); + dwc3_ulpi_exit(dwc); err4: @@ -1570,9 +1581,9 @@ static int dwc3_remove(struct platform_device *pdev) dwc3_core_exit(dwc); dwc3_ulpi_exit(dwc); - pm_runtime_put_sync(&pdev->dev); - pm_runtime_allow(&pdev->dev); pm_runtime_disable(&pdev->dev); + pm_runtime_put_noidle(&pdev->dev); + pm_runtime_set_suspended(&pdev->dev); dwc3_free_event_buffers(dwc); dwc3_free_scratch_buffers(dwc); diff --git a/drivers/usb/dwc3/core.h b/drivers/usb/dwc3/core.h index 4dfbffa944de..c848f9164f92 100644 --- a/drivers/usb/dwc3/core.h +++ b/drivers/usb/dwc3/core.h @@ -700,6 +700,7 @@ struct dwc3_ep { #define DWC3_EP_END_TRANSFER_PENDING BIT(4) #define DWC3_EP_PENDING_REQUEST BIT(5) #define DWC3_EP_DELAY_START BIT(6) +#define DWC3_EP_PENDING_CLEAR_STALL BIT(11) /* This last one is specific to EP0 */ #define DWC3_EP0_DIR_IN BIT(31) diff --git a/drivers/usb/dwc3/dwc3-pci.c b/drivers/usb/dwc3/dwc3-pci.c index 139474c3e77b..ba88039449e0 100644 --- a/drivers/usb/dwc3/dwc3-pci.c +++ b/drivers/usb/dwc3/dwc3-pci.c @@ -147,7 +147,8 @@ static int dwc3_pci_quirks(struct dwc3_pci *dwc) if (pdev->vendor == PCI_VENDOR_ID_INTEL) { if (pdev->device == PCI_DEVICE_ID_INTEL_BXT || - pdev->device == PCI_DEVICE_ID_INTEL_BXT_M) { + pdev->device == PCI_DEVICE_ID_INTEL_BXT_M || + pdev->device == PCI_DEVICE_ID_INTEL_EHLLP) { guid_parse(PCI_INTEL_BXT_DSM_GUID, &dwc->guid); dwc->has_dsm_for_pm = true; } diff --git a/drivers/usb/dwc3/ep0.c b/drivers/usb/dwc3/ep0.c index 6dee4dabc0a4..991cab9a7491 100644 --- a/drivers/usb/dwc3/ep0.c +++ b/drivers/usb/dwc3/ep0.c @@ -524,6 +524,11 @@ static int dwc3_ep0_handle_endpoint(struct dwc3 *dwc, ret = __dwc3_gadget_ep_set_halt(dep, set, true); if (ret) return -EINVAL; + + /* ClearFeature(Halt) may need delayed status */ + if (!set && (dep->flags & DWC3_EP_END_TRANSFER_PENDING)) + return USB_GADGET_DELAYED_STATUS; + break; default: return -EINVAL; @@ -942,12 +947,16 @@ static void dwc3_ep0_xfer_complete(struct dwc3 *dwc, static void __dwc3_ep0_do_control_data(struct dwc3 *dwc, struct dwc3_ep *dep, struct dwc3_request *req) { + unsigned int trb_length = 0; int ret; req->direction = !!dep->number; if (req->request.length == 0) { - dwc3_ep0_prepare_one_trb(dep, dwc->ep0_trb_addr, 0, + if (!req->direction) + trb_length = dep->endpoint.maxpacket; + + dwc3_ep0_prepare_one_trb(dep, dwc->bounce_addr, trb_length, DWC3_TRBCTL_CONTROL_DATA, false); ret = dwc3_ep0_start_trans(dep); } else if (!IS_ALIGNED(req->request.length, dep->endpoint.maxpacket) @@ -994,9 +1003,12 @@ static void __dwc3_ep0_do_control_data(struct dwc3 *dwc, req->trb = &dwc->ep0_trb[dep->trb_enqueue - 1]; + if (!req->direction) + trb_length = dep->endpoint.maxpacket; + /* Now prepare one extra TRB to align transfer size */ dwc3_ep0_prepare_one_trb(dep, dwc->bounce_addr, - 0, DWC3_TRBCTL_CONTROL_DATA, + trb_length, DWC3_TRBCTL_CONTROL_DATA, false); ret = dwc3_ep0_start_trans(dep); } else { @@ -1042,6 +1054,17 @@ static void dwc3_ep0_do_control_status(struct dwc3 *dwc, __dwc3_ep0_do_control_status(dwc, dep); } +void dwc3_ep0_send_delayed_status(struct dwc3 *dwc) +{ + unsigned int direction = !dwc->ep0_expect_in; + + if (dwc->ep0state != EP0_STATUS_PHASE) + return; + + dwc->delayed_status = false; + __dwc3_ep0_do_control_status(dwc, dwc->eps[direction]); +} + static void dwc3_ep0_end_control_data(struct dwc3 *dwc, struct dwc3_ep *dep) { struct dwc3_gadget_ep_cmd_params params; diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index 809103254fc6..1d65de84464d 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -1057,6 +1057,8 @@ static void dwc3_prepare_one_trb_sg(struct dwc3_ep *dep, struct scatterlist *s; int i; unsigned int length = req->request.length; + unsigned int maxp = usb_endpoint_maxp(dep->endpoint.desc); + unsigned int rem = length % maxp; unsigned int remaining = req->request.num_mapped_sgs - req->num_queued_sgs; @@ -1068,8 +1070,6 @@ static void dwc3_prepare_one_trb_sg(struct dwc3_ep *dep, length -= sg_dma_len(s); for_each_sg(sg, s, remaining, i) { - unsigned int maxp = usb_endpoint_maxp(dep->endpoint.desc); - unsigned int rem = length % maxp; unsigned int trb_length; unsigned chain = true; @@ -1521,8 +1521,13 @@ static int __dwc3_gadget_ep_queue(struct dwc3_ep *dep, struct dwc3_request *req) list_add_tail(&req->list, &dep->pending_list); req->status = DWC3_REQUEST_STATUS_QUEUED; - /* Start the transfer only after the END_TRANSFER is completed */ - if (dep->flags & DWC3_EP_END_TRANSFER_PENDING) { + /* + * Start the transfer only after the END_TRANSFER is completed + * and endpoint STALL is cleared. + */ + if ((dep->flags & DWC3_EP_END_TRANSFER_PENDING) || + (dep->flags & DWC3_EP_WEDGE) || + (dep->flags & DWC3_EP_STALL)) { dep->flags |= DWC3_EP_DELAY_START; return 0; } @@ -1714,6 +1719,18 @@ int __dwc3_gadget_ep_set_halt(struct dwc3_ep *dep, int value, int protocol) return 0; } + dwc3_stop_active_transfer(dep, true, true); + + list_for_each_entry_safe(req, tmp, &dep->started_list, list) + dwc3_gadget_move_cancelled_request(req); + + if (dep->flags & DWC3_EP_END_TRANSFER_PENDING) { + dep->flags |= DWC3_EP_PENDING_CLEAR_STALL; + return 0; + } + + dwc3_gadget_ep_cleanup_cancelled_requests(dep); + ret = dwc3_send_clear_stall_ep_cmd(dep); if (ret) { dev_err(dwc->dev, "failed to clear STALL on %s\n", @@ -1723,18 +1740,11 @@ int __dwc3_gadget_ep_set_halt(struct dwc3_ep *dep, int value, int protocol) dep->flags &= ~(DWC3_EP_STALL | DWC3_EP_WEDGE); - dwc3_stop_active_transfer(dep, true, true); + if ((dep->flags & DWC3_EP_DELAY_START) && + !usb_endpoint_xfer_isoc(dep->endpoint.desc)) + __dwc3_gadget_kick_transfer(dep); - list_for_each_entry_safe(req, tmp, &dep->started_list, list) - dwc3_gadget_move_cancelled_request(req); - - list_for_each_entry_safe(req, tmp, &dep->pending_list, list) - dwc3_gadget_move_cancelled_request(req); - - if (!(dep->flags & DWC3_EP_END_TRANSFER_PENDING)) { - dep->flags &= ~DWC3_EP_DELAY_START; - dwc3_gadget_ep_cleanup_cancelled_requests(dep); - } + dep->flags &= ~DWC3_EP_DELAY_START; } return ret; @@ -2761,6 +2771,26 @@ static void dwc3_endpoint_interrupt(struct dwc3 *dwc, dep->flags &= ~DWC3_EP_END_TRANSFER_PENDING; dep->flags &= ~DWC3_EP_TRANSFER_STARTED; dwc3_gadget_ep_cleanup_cancelled_requests(dep); + + if (dep->flags & DWC3_EP_PENDING_CLEAR_STALL) { + struct dwc3 *dwc = dep->dwc; + + dep->flags &= ~DWC3_EP_PENDING_CLEAR_STALL; + if (dwc3_send_clear_stall_ep_cmd(dep)) { + struct usb_ep *ep0 = &dwc->eps[0]->endpoint; + + dev_err(dwc->dev, "failed to clear STALL on %s\n", + dep->name); + if (dwc->delayed_status) + __dwc3_gadget_ep0_set_halt(ep0, 1); + return; + } + + dep->flags &= ~(DWC3_EP_STALL | DWC3_EP_WEDGE); + if (dwc->delayed_status) + dwc3_ep0_send_delayed_status(dwc); + } + if ((dep->flags & DWC3_EP_DELAY_START) && !usb_endpoint_xfer_isoc(dep->endpoint.desc)) __dwc3_gadget_kick_transfer(dep); diff --git a/drivers/usb/dwc3/gadget.h b/drivers/usb/dwc3/gadget.h index 5faf4d1249e0..f207e59c7d03 100644 --- a/drivers/usb/dwc3/gadget.h +++ b/drivers/usb/dwc3/gadget.h @@ -111,6 +111,7 @@ int dwc3_gadget_ep0_set_halt(struct usb_ep *ep, int value); int dwc3_gadget_ep0_queue(struct usb_ep *ep, struct usb_request *request, gfp_t gfp_flags); int __dwc3_gadget_ep_set_halt(struct dwc3_ep *dep, int value, int protocol); +void dwc3_ep0_send_delayed_status(struct dwc3 *dwc); /** * dwc3_gadget_ep_get_transfer_index - Gets transfer index from HW diff --git a/drivers/usb/host/fsl-mph-dr-of.c b/drivers/usb/host/fsl-mph-dr-of.c index ae8f60f6e6a5..44a7e58a26e3 100644 --- a/drivers/usb/host/fsl-mph-dr-of.c +++ b/drivers/usb/host/fsl-mph-dr-of.c @@ -94,10 +94,13 @@ static struct platform_device *fsl_usb2_device_register( pdev->dev.coherent_dma_mask = ofdev->dev.coherent_dma_mask; - if (!pdev->dev.dma_mask) + if (!pdev->dev.dma_mask) { pdev->dev.dma_mask = &ofdev->dev.coherent_dma_mask; - else - dma_set_mask(&pdev->dev, DMA_BIT_MASK(32)); + } else { + retval = dma_set_mask(&pdev->dev, DMA_BIT_MASK(32)); + if (retval) + goto error; + } retval = platform_device_add_data(pdev, pdata, sizeof(*pdata)); if (retval) diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c index bbd616324faa..3c90c14390d6 100644 --- a/drivers/usb/host/xhci-pci.c +++ b/drivers/usb/host/xhci-pci.c @@ -21,6 +21,8 @@ #define SSIC_PORT_CFG2_OFFSET 0x30 #define PROG_DONE (1 << 30) #define SSIC_PORT_UNUSED (1 << 31) +#define SPARSE_DISABLE_BIT 17 +#define SPARSE_CNTL_ENABLE 0xC12C /* Device for a quirk */ #define PCI_VENDOR_ID_FRESCO_LOGIC 0x1b73 @@ -149,6 +151,9 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci) (pdev->device == 0x15e0 || pdev->device == 0x15e1)) xhci->quirks |= XHCI_SNPS_BROKEN_SUSPEND; + if (pdev->vendor == PCI_VENDOR_ID_AMD && pdev->device == 0x15e5) + xhci->quirks |= XHCI_DISABLE_SPARSE; + if (pdev->vendor == PCI_VENDOR_ID_AMD) xhci->quirks |= XHCI_TRUST_TX_LENGTH; @@ -467,6 +472,15 @@ static void xhci_pme_quirk(struct usb_hcd *hcd) readl(reg); } +static void xhci_sparse_control_quirk(struct usb_hcd *hcd) +{ + u32 reg; + + reg = readl(hcd->regs + SPARSE_CNTL_ENABLE); + reg &= ~BIT(SPARSE_DISABLE_BIT); + writel(reg, hcd->regs + SPARSE_CNTL_ENABLE); +} + static int xhci_pci_suspend(struct usb_hcd *hcd, bool do_wakeup) { struct xhci_hcd *xhci = hcd_to_xhci(hcd); @@ -486,6 +500,9 @@ static int xhci_pci_suspend(struct usb_hcd *hcd, bool do_wakeup) if (xhci->quirks & XHCI_SSIC_PORT_UNUSED) xhci_ssic_port_unused_quirk(hcd, true); + if (xhci->quirks & XHCI_DISABLE_SPARSE) + xhci_sparse_control_quirk(hcd); + ret = xhci_suspend(xhci, do_wakeup); if (ret && (xhci->quirks & XHCI_SSIC_PORT_UNUSED)) xhci_ssic_port_unused_quirk(hcd, false); diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c index 0d10ede581cb..7123ab44671b 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -982,12 +982,15 @@ int xhci_suspend(struct xhci_hcd *xhci, bool do_wakeup) xhci->shared_hcd->state != HC_STATE_SUSPENDED) return -EINVAL; - xhci_dbc_suspend(xhci); - /* Clear root port wake on bits if wakeup not allowed. */ if (!do_wakeup) xhci_disable_port_wake_on_bits(xhci); + if (!HCD_HW_ACCESSIBLE(hcd)) + return 0; + + xhci_dbc_suspend(xhci); + /* Don't poll the roothubs on bus suspend. */ xhci_dbg(xhci, "%s: stopping port polling.\n", __func__); clear_bit(HCD_FLAG_POLL_RH, &hcd->flags); diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h index c656b41b57b5..b483317bcb17 100644 --- a/drivers/usb/host/xhci.h +++ b/drivers/usb/host/xhci.h @@ -1873,6 +1873,7 @@ struct xhci_hcd { #define XHCI_DEFAULT_PM_RUNTIME_ALLOW BIT_ULL(33) #define XHCI_RESET_PLL_ON_DISCONNECT BIT_ULL(34) #define XHCI_SNPS_BROKEN_SUSPEND BIT_ULL(35) +#define XHCI_DISABLE_SPARSE BIT_ULL(38) unsigned int num_active_eps; unsigned int limit_active_eps; diff --git a/drivers/usb/misc/adutux.c b/drivers/usb/misc/adutux.c index d8d157c4c271..96495fcd952a 100644 --- a/drivers/usb/misc/adutux.c +++ b/drivers/usb/misc/adutux.c @@ -209,6 +209,7 @@ static void adu_interrupt_out_callback(struct urb *urb) if (status != 0) { if ((status != -ENOENT) && + (status != -ESHUTDOWN) && (status != -ECONNRESET)) { dev_dbg(&dev->udev->dev, "%s :nonzero status received: %d\n", __func__, diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c index 355a2c7fac0b..5bb84cb4876a 100644 --- a/drivers/usb/typec/tcpm/tcpm.c +++ b/drivers/usb/typec/tcpm/tcpm.c @@ -2723,12 +2723,12 @@ static void tcpm_reset_port(struct tcpm_port *port) static void tcpm_detach(struct tcpm_port *port) { - if (!port->attached) - return; - if (tcpm_port_is_disconnected(port)) port->hard_reset_count = 0; + if (!port->attached) + return; + tcpm_reset_port(port); } @@ -3482,7 +3482,7 @@ static void run_state_machine(struct tcpm_port *port) */ tcpm_set_pwr_role(port, TYPEC_SOURCE); tcpm_pd_send_control(port, PD_CTRL_PS_RDY); - tcpm_set_state(port, SRC_STARTUP, 0); + tcpm_set_state(port, SRC_STARTUP, PD_T_SWAP_SRC_START); break; case VCONN_SWAP_ACCEPT: diff --git a/drivers/vhost/vringh.c b/drivers/vhost/vringh.c index a0a2d74967ef..026a37ee4177 100644 --- a/drivers/vhost/vringh.c +++ b/drivers/vhost/vringh.c @@ -274,13 +274,14 @@ __vringh_iov(struct vringh *vrh, u16 i, desc_max = vrh->vring.num; up_next = -1; + /* You must want something! */ + if (WARN_ON(!riov && !wiov)) + return -EINVAL; + if (riov) riov->i = riov->used = 0; - else if (wiov) + if (wiov) wiov->i = wiov->used = 0; - else - /* You must want something! */ - BUG(); for (;;) { void *addr; diff --git a/drivers/video/fbdev/pvr2fb.c b/drivers/video/fbdev/pvr2fb.c index 0a3b2b7c7891..c916e9161443 100644 --- a/drivers/video/fbdev/pvr2fb.c +++ b/drivers/video/fbdev/pvr2fb.c @@ -1016,6 +1016,8 @@ static int __init pvr2fb_setup(char *options) if (!options || !*options) return 0; + cable_arg[0] = output_arg[0] = 0; + while ((this_opt = strsep(&options, ","))) { if (!*this_opt) continue; diff --git a/drivers/w1/masters/mxc_w1.c b/drivers/w1/masters/mxc_w1.c index 1ca880e01476..090cbbf9e1e2 100644 --- a/drivers/w1/masters/mxc_w1.c +++ b/drivers/w1/masters/mxc_w1.c @@ -7,7 +7,7 @@ #include <linux/clk.h> #include <linux/delay.h> #include <linux/io.h> -#include <linux/jiffies.h> +#include <linux/ktime.h> #include <linux/module.h> #include <linux/mod_devicetable.h> #include <linux/platform_device.h> @@ -40,12 +40,12 @@ struct mxc_w1_device { static u8 mxc_w1_ds2_reset_bus(void *data) { struct mxc_w1_device *dev = data; - unsigned long timeout; + ktime_t timeout; writeb(MXC_W1_CONTROL_RPP, dev->regs + MXC_W1_CONTROL); /* Wait for reset sequence 511+512us, use 1500us for sure */ - timeout = jiffies + usecs_to_jiffies(1500); + timeout = ktime_add_us(ktime_get(), 1500); udelay(511 + 512); @@ -55,7 +55,7 @@ static u8 mxc_w1_ds2_reset_bus(void *data) /* PST bit is valid after the RPP bit is self-cleared */ if (!(ctrl & MXC_W1_CONTROL_RPP)) return !(ctrl & MXC_W1_CONTROL_PST); - } while (time_is_after_jiffies(timeout)); + } while (ktime_before(ktime_get(), timeout)); return 1; } @@ -68,12 +68,12 @@ static u8 mxc_w1_ds2_reset_bus(void *data) static u8 mxc_w1_ds2_touch_bit(void *data, u8 bit) { struct mxc_w1_device *dev = data; - unsigned long timeout; + ktime_t timeout; writeb(MXC_W1_CONTROL_WR(bit), dev->regs + MXC_W1_CONTROL); /* Wait for read/write bit (60us, Max 120us), use 200us for sure */ - timeout = jiffies + usecs_to_jiffies(200); + timeout = ktime_add_us(ktime_get(), 200); udelay(60); @@ -83,7 +83,7 @@ static u8 mxc_w1_ds2_touch_bit(void *data, u8 bit) /* RDST bit is valid after the WR1/RD bit is self-cleared */ if (!(ctrl & MXC_W1_CONTROL_WR(bit))) return !!(ctrl & MXC_W1_CONTROL_RDST); - } while (time_is_after_jiffies(timeout)); + } while (ktime_before(ktime_get(), timeout)); return 0; } diff --git a/drivers/watchdog/rdc321x_wdt.c b/drivers/watchdog/rdc321x_wdt.c index 2e608ae6cbc7..e0efbc583198 100644 --- a/drivers/watchdog/rdc321x_wdt.c +++ b/drivers/watchdog/rdc321x_wdt.c @@ -230,6 +230,8 @@ static int rdc321x_wdt_probe(struct platform_device *pdev) rdc321x_wdt_device.sb_pdev = pdata->sb_pdev; rdc321x_wdt_device.base_reg = r->start; + rdc321x_wdt_device.queue = 0; + rdc321x_wdt_device.default_ticks = ticks; err = misc_register(&rdc321x_wdt_misc); if (err < 0) { @@ -244,14 +246,11 @@ static int rdc321x_wdt_probe(struct platform_device *pdev) rdc321x_wdt_device.base_reg, RDC_WDT_RST); init_completion(&rdc321x_wdt_device.stop); - rdc321x_wdt_device.queue = 0; clear_bit(0, &rdc321x_wdt_device.inuse); timer_setup(&rdc321x_wdt_device.timer, rdc321x_wdt_trigger, 0); - rdc321x_wdt_device.default_ticks = ticks; - dev_info(&pdev->dev, "watchdog init success\n"); return 0; diff --git a/drivers/xen/events/events_2l.c b/drivers/xen/events/events_2l.c index 8edef51c92e5..f026624898e7 100644 --- a/drivers/xen/events/events_2l.c +++ b/drivers/xen/events/events_2l.c @@ -91,6 +91,8 @@ static void evtchn_2l_unmask(unsigned port) BUG_ON(!irqs_disabled()); + smp_wmb(); /* All writes before unmask must be visible. */ + if (unlikely((cpu != cpu_from_evtchn(port)))) do_hypercall = 1; else { @@ -159,7 +161,7 @@ static inline xen_ulong_t active_evtchns(unsigned int cpu, * a bitset of words which contain pending event bits. The second * level is a bitset of pending events themselves. */ -static void evtchn_2l_handle_events(unsigned cpu) +static void evtchn_2l_handle_events(unsigned cpu, struct evtchn_loop_ctrl *ctrl) { int irq; xen_ulong_t pending_words; @@ -240,10 +242,7 @@ static void evtchn_2l_handle_events(unsigned cpu) /* Process port. */ port = (word_idx * BITS_PER_EVTCHN_WORD) + bit_idx; - irq = get_evtchn_to_irq(port); - - if (irq != -1) - generic_handle_irq(irq); + handle_irq_for_port(port, ctrl); bit_idx = (bit_idx + 1) % BITS_PER_EVTCHN_WORD; diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c index e402620b8920..26df84c45db4 100644 --- a/drivers/xen/events/events_base.c +++ b/drivers/xen/events/events_base.c @@ -33,6 +33,10 @@ #include <linux/slab.h> #include <linux/irqnr.h> #include <linux/pci.h> +#include <linux/spinlock.h> +#include <linux/cpuhotplug.h> +#include <linux/atomic.h> +#include <linux/ktime.h> #ifdef CONFIG_X86 #include <asm/desc.h> @@ -62,6 +66,15 @@ #include "events_internal.h" +#undef MODULE_PARAM_PREFIX +#define MODULE_PARAM_PREFIX "xen." + +static uint __read_mostly event_loop_timeout = 2; +module_param(event_loop_timeout, uint, 0644); + +static uint __read_mostly event_eoi_delay = 10; +module_param(event_eoi_delay, uint, 0644); + const struct evtchn_ops *evtchn_ops; /* @@ -70,6 +83,24 @@ const struct evtchn_ops *evtchn_ops; */ static DEFINE_MUTEX(irq_mapping_update_lock); +/* + * Lock protecting event handling loop against removing event channels. + * Adding of event channels is no issue as the associated IRQ becomes active + * only after everything is setup (before request_[threaded_]irq() the handler + * can't be entered for an event, as the event channel will be unmasked only + * then). + */ +static DEFINE_RWLOCK(evtchn_rwlock); + +/* + * Lock hierarchy: + * + * irq_mapping_update_lock + * evtchn_rwlock + * IRQ-desc lock + * percpu eoi_list_lock + */ + static LIST_HEAD(xen_irq_list_head); /* IRQ <-> VIRQ mapping. */ @@ -94,17 +125,20 @@ static bool (*pirq_needs_eoi)(unsigned irq); static struct irq_info *legacy_info_ptrs[NR_IRQS_LEGACY]; static struct irq_chip xen_dynamic_chip; +static struct irq_chip xen_lateeoi_chip; static struct irq_chip xen_percpu_chip; static struct irq_chip xen_pirq_chip; static void enable_dynirq(struct irq_data *data); static void disable_dynirq(struct irq_data *data); +static DEFINE_PER_CPU(unsigned int, irq_epoch); + static void clear_evtchn_to_irq_row(unsigned row) { unsigned col; for (col = 0; col < EVTCHN_PER_ROW; col++) - evtchn_to_irq[row][col] = -1; + WRITE_ONCE(evtchn_to_irq[row][col], -1); } static void clear_evtchn_to_irq_all(void) @@ -141,7 +175,7 @@ static int set_evtchn_to_irq(unsigned evtchn, unsigned irq) clear_evtchn_to_irq_row(row); } - evtchn_to_irq[row][col] = irq; + WRITE_ONCE(evtchn_to_irq[row][col], irq); return 0; } @@ -151,7 +185,7 @@ int get_evtchn_to_irq(unsigned evtchn) return -1; if (evtchn_to_irq[EVTCHN_ROW(evtchn)] == NULL) return -1; - return evtchn_to_irq[EVTCHN_ROW(evtchn)][EVTCHN_COL(evtchn)]; + return READ_ONCE(evtchn_to_irq[EVTCHN_ROW(evtchn)][EVTCHN_COL(evtchn)]); } /* Get info for IRQ */ @@ -260,10 +294,14 @@ static void xen_irq_info_cleanup(struct irq_info *info) */ unsigned int evtchn_from_irq(unsigned irq) { - if (WARN(irq >= nr_irqs, "Invalid irq %d!\n", irq)) + const struct irq_info *info = NULL; + + if (likely(irq < nr_irqs)) + info = info_for_irq(irq); + if (!info) return 0; - return info_for_irq(irq)->evtchn; + return info->evtchn; } unsigned irq_from_evtchn(unsigned int evtchn) @@ -374,9 +412,157 @@ void notify_remote_via_irq(int irq) } EXPORT_SYMBOL_GPL(notify_remote_via_irq); +struct lateeoi_work { + struct delayed_work delayed; + spinlock_t eoi_list_lock; + struct list_head eoi_list; +}; + +static DEFINE_PER_CPU(struct lateeoi_work, lateeoi); + +static void lateeoi_list_del(struct irq_info *info) +{ + struct lateeoi_work *eoi = &per_cpu(lateeoi, info->eoi_cpu); + unsigned long flags; + + spin_lock_irqsave(&eoi->eoi_list_lock, flags); + list_del_init(&info->eoi_list); + spin_unlock_irqrestore(&eoi->eoi_list_lock, flags); +} + +static void lateeoi_list_add(struct irq_info *info) +{ + struct lateeoi_work *eoi = &per_cpu(lateeoi, info->eoi_cpu); + struct irq_info *elem; + u64 now = get_jiffies_64(); + unsigned long delay; + unsigned long flags; + + if (now < info->eoi_time) + delay = info->eoi_time - now; + else + delay = 1; + + spin_lock_irqsave(&eoi->eoi_list_lock, flags); + + if (list_empty(&eoi->eoi_list)) { + list_add(&info->eoi_list, &eoi->eoi_list); + mod_delayed_work_on(info->eoi_cpu, system_wq, + &eoi->delayed, delay); + } else { + list_for_each_entry_reverse(elem, &eoi->eoi_list, eoi_list) { + if (elem->eoi_time <= info->eoi_time) + break; + } + list_add(&info->eoi_list, &elem->eoi_list); + } + + spin_unlock_irqrestore(&eoi->eoi_list_lock, flags); +} + +static void xen_irq_lateeoi_locked(struct irq_info *info, bool spurious) +{ + evtchn_port_t evtchn; + unsigned int cpu; + unsigned int delay = 0; + + evtchn = info->evtchn; + if (!VALID_EVTCHN(evtchn) || !list_empty(&info->eoi_list)) + return; + + if (spurious) { + if ((1 << info->spurious_cnt) < (HZ << 2)) + info->spurious_cnt++; + if (info->spurious_cnt > 1) { + delay = 1 << (info->spurious_cnt - 2); + if (delay > HZ) + delay = HZ; + if (!info->eoi_time) + info->eoi_cpu = smp_processor_id(); + info->eoi_time = get_jiffies_64() + delay; + } + } else { + info->spurious_cnt = 0; + } + + cpu = info->eoi_cpu; + if (info->eoi_time && + (info->irq_epoch == per_cpu(irq_epoch, cpu) || delay)) { + lateeoi_list_add(info); + return; + } + + info->eoi_time = 0; + unmask_evtchn(evtchn); +} + +static void xen_irq_lateeoi_worker(struct work_struct *work) +{ + struct lateeoi_work *eoi; + struct irq_info *info; + u64 now = get_jiffies_64(); + unsigned long flags; + + eoi = container_of(to_delayed_work(work), struct lateeoi_work, delayed); + + read_lock_irqsave(&evtchn_rwlock, flags); + + while (true) { + spin_lock(&eoi->eoi_list_lock); + + info = list_first_entry_or_null(&eoi->eoi_list, struct irq_info, + eoi_list); + + if (info == NULL || now < info->eoi_time) { + spin_unlock(&eoi->eoi_list_lock); + break; + } + + list_del_init(&info->eoi_list); + + spin_unlock(&eoi->eoi_list_lock); + + info->eoi_time = 0; + + xen_irq_lateeoi_locked(info, false); + } + + if (info) + mod_delayed_work_on(info->eoi_cpu, system_wq, + &eoi->delayed, info->eoi_time - now); + + read_unlock_irqrestore(&evtchn_rwlock, flags); +} + +static void xen_cpu_init_eoi(unsigned int cpu) +{ + struct lateeoi_work *eoi = &per_cpu(lateeoi, cpu); + + INIT_DELAYED_WORK(&eoi->delayed, xen_irq_lateeoi_worker); + spin_lock_init(&eoi->eoi_list_lock); + INIT_LIST_HEAD(&eoi->eoi_list); +} + +void xen_irq_lateeoi(unsigned int irq, unsigned int eoi_flags) +{ + struct irq_info *info; + unsigned long flags; + + read_lock_irqsave(&evtchn_rwlock, flags); + + info = info_for_irq(irq); + + if (info) + xen_irq_lateeoi_locked(info, eoi_flags & XEN_EOI_FLAG_SPURIOUS); + + read_unlock_irqrestore(&evtchn_rwlock, flags); +} +EXPORT_SYMBOL_GPL(xen_irq_lateeoi); + static void xen_irq_init(unsigned irq) { struct irq_info *info; + #ifdef CONFIG_SMP /* By default all event channels notify CPU#0. */ cpumask_copy(irq_get_affinity_mask(irq), cpumask_of(0)); @@ -391,6 +577,7 @@ static void xen_irq_init(unsigned irq) set_info_for_irq(irq, info); + INIT_LIST_HEAD(&info->eoi_list); list_add_tail(&info->list, &xen_irq_list_head); } @@ -439,16 +626,24 @@ static int __must_check xen_allocate_irq_gsi(unsigned gsi) static void xen_free_irq(unsigned irq) { struct irq_info *info = info_for_irq(irq); + unsigned long flags; if (WARN_ON(!info)) return; + write_lock_irqsave(&evtchn_rwlock, flags); + + if (!list_empty(&info->eoi_list)) + lateeoi_list_del(info); + list_del(&info->list); set_info_for_irq(irq, NULL); WARN_ON(info->refcnt > 0); + write_unlock_irqrestore(&evtchn_rwlock, flags); + kfree(info); /* Legacy IRQ descriptors are managed by the arch. */ @@ -840,7 +1035,7 @@ int xen_pirq_from_irq(unsigned irq) } EXPORT_SYMBOL_GPL(xen_pirq_from_irq); -int bind_evtchn_to_irq(unsigned int evtchn) +static int bind_evtchn_to_irq_chip(evtchn_port_t evtchn, struct irq_chip *chip) { int irq; int ret; @@ -857,7 +1052,7 @@ int bind_evtchn_to_irq(unsigned int evtchn) if (irq < 0) goto out; - irq_set_chip_and_handler_name(irq, &xen_dynamic_chip, + irq_set_chip_and_handler_name(irq, chip, handle_edge_irq, "event"); ret = xen_irq_info_evtchn_setup(irq, evtchn); @@ -878,8 +1073,19 @@ int bind_evtchn_to_irq(unsigned int evtchn) return irq; } + +int bind_evtchn_to_irq(evtchn_port_t evtchn) +{ + return bind_evtchn_to_irq_chip(evtchn, &xen_dynamic_chip); +} EXPORT_SYMBOL_GPL(bind_evtchn_to_irq); +int bind_evtchn_to_irq_lateeoi(evtchn_port_t evtchn) +{ + return bind_evtchn_to_irq_chip(evtchn, &xen_lateeoi_chip); +} +EXPORT_SYMBOL_GPL(bind_evtchn_to_irq_lateeoi); + static int bind_ipi_to_irq(unsigned int ipi, unsigned int cpu) { struct evtchn_bind_ipi bind_ipi; @@ -921,8 +1127,9 @@ static int bind_ipi_to_irq(unsigned int ipi, unsigned int cpu) return irq; } -int bind_interdomain_evtchn_to_irq(unsigned int remote_domain, - unsigned int remote_port) +static int bind_interdomain_evtchn_to_irq_chip(unsigned int remote_domain, + evtchn_port_t remote_port, + struct irq_chip *chip) { struct evtchn_bind_interdomain bind_interdomain; int err; @@ -933,10 +1140,26 @@ int bind_interdomain_evtchn_to_irq(unsigned int remote_domain, err = HYPERVISOR_event_channel_op(EVTCHNOP_bind_interdomain, &bind_interdomain); - return err ? : bind_evtchn_to_irq(bind_interdomain.local_port); + return err ? : bind_evtchn_to_irq_chip(bind_interdomain.local_port, + chip); +} + +int bind_interdomain_evtchn_to_irq(unsigned int remote_domain, + evtchn_port_t remote_port) +{ + return bind_interdomain_evtchn_to_irq_chip(remote_domain, remote_port, + &xen_dynamic_chip); } EXPORT_SYMBOL_GPL(bind_interdomain_evtchn_to_irq); +int bind_interdomain_evtchn_to_irq_lateeoi(unsigned int remote_domain, + evtchn_port_t remote_port) +{ + return bind_interdomain_evtchn_to_irq_chip(remote_domain, remote_port, + &xen_lateeoi_chip); +} +EXPORT_SYMBOL_GPL(bind_interdomain_evtchn_to_irq_lateeoi); + static int find_virq(unsigned int virq, unsigned int cpu) { struct evtchn_status status; @@ -1032,14 +1255,15 @@ static void unbind_from_irq(unsigned int irq) mutex_unlock(&irq_mapping_update_lock); } -int bind_evtchn_to_irqhandler(unsigned int evtchn, - irq_handler_t handler, - unsigned long irqflags, - const char *devname, void *dev_id) +static int bind_evtchn_to_irqhandler_chip(evtchn_port_t evtchn, + irq_handler_t handler, + unsigned long irqflags, + const char *devname, void *dev_id, + struct irq_chip *chip) { int irq, retval; - irq = bind_evtchn_to_irq(evtchn); + irq = bind_evtchn_to_irq_chip(evtchn, chip); if (irq < 0) return irq; retval = request_irq(irq, handler, irqflags, devname, dev_id); @@ -1050,18 +1274,38 @@ int bind_evtchn_to_irqhandler(unsigned int evtchn, return irq; } + +int bind_evtchn_to_irqhandler(evtchn_port_t evtchn, + irq_handler_t handler, + unsigned long irqflags, + const char *devname, void *dev_id) +{ + return bind_evtchn_to_irqhandler_chip(evtchn, handler, irqflags, + devname, dev_id, + &xen_dynamic_chip); +} EXPORT_SYMBOL_GPL(bind_evtchn_to_irqhandler); -int bind_interdomain_evtchn_to_irqhandler(unsigned int remote_domain, - unsigned int remote_port, - irq_handler_t handler, - unsigned long irqflags, - const char *devname, - void *dev_id) +int bind_evtchn_to_irqhandler_lateeoi(evtchn_port_t evtchn, + irq_handler_t handler, + unsigned long irqflags, + const char *devname, void *dev_id) +{ + return bind_evtchn_to_irqhandler_chip(evtchn, handler, irqflags, + devname, dev_id, + &xen_lateeoi_chip); +} +EXPORT_SYMBOL_GPL(bind_evtchn_to_irqhandler_lateeoi); + +static int bind_interdomain_evtchn_to_irqhandler_chip( + unsigned int remote_domain, evtchn_port_t remote_port, + irq_handler_t handler, unsigned long irqflags, + const char *devname, void *dev_id, struct irq_chip *chip) { int irq, retval; - irq = bind_interdomain_evtchn_to_irq(remote_domain, remote_port); + irq = bind_interdomain_evtchn_to_irq_chip(remote_domain, remote_port, + chip); if (irq < 0) return irq; @@ -1073,8 +1317,33 @@ int bind_interdomain_evtchn_to_irqhandler(unsigned int remote_domain, return irq; } + +int bind_interdomain_evtchn_to_irqhandler(unsigned int remote_domain, + evtchn_port_t remote_port, + irq_handler_t handler, + unsigned long irqflags, + const char *devname, + void *dev_id) +{ + return bind_interdomain_evtchn_to_irqhandler_chip(remote_domain, + remote_port, handler, irqflags, devname, + dev_id, &xen_dynamic_chip); +} EXPORT_SYMBOL_GPL(bind_interdomain_evtchn_to_irqhandler); +int bind_interdomain_evtchn_to_irqhandler_lateeoi(unsigned int remote_domain, + evtchn_port_t remote_port, + irq_handler_t handler, + unsigned long irqflags, + const char *devname, + void *dev_id) +{ + return bind_interdomain_evtchn_to_irqhandler_chip(remote_domain, + remote_port, handler, irqflags, devname, + dev_id, &xen_lateeoi_chip); +} +EXPORT_SYMBOL_GPL(bind_interdomain_evtchn_to_irqhandler_lateeoi); + int bind_virq_to_irqhandler(unsigned int virq, unsigned int cpu, irq_handler_t handler, unsigned long irqflags, const char *devname, void *dev_id) @@ -1187,7 +1456,7 @@ int evtchn_get(unsigned int evtchn) goto done; err = -EINVAL; - if (info->refcnt <= 0) + if (info->refcnt <= 0 || info->refcnt == SHRT_MAX) goto done; info->refcnt++; @@ -1226,6 +1495,54 @@ void xen_send_IPI_one(unsigned int cpu, enum ipi_vector vector) notify_remote_via_irq(irq); } +struct evtchn_loop_ctrl { + ktime_t timeout; + unsigned count; + bool defer_eoi; +}; + +void handle_irq_for_port(evtchn_port_t port, struct evtchn_loop_ctrl *ctrl) +{ + int irq; + struct irq_info *info; + + irq = get_evtchn_to_irq(port); + if (irq == -1) + return; + + /* + * Check for timeout every 256 events. + * We are setting the timeout value only after the first 256 + * events in order to not hurt the common case of few loop + * iterations. The 256 is basically an arbitrary value. + * + * In case we are hitting the timeout we need to defer all further + * EOIs in order to ensure to leave the event handling loop rather + * sooner than later. + */ + if (!ctrl->defer_eoi && !(++ctrl->count & 0xff)) { + ktime_t kt = ktime_get(); + + if (!ctrl->timeout) { + kt = ktime_add_ms(kt, + jiffies_to_msecs(event_loop_timeout)); + ctrl->timeout = kt; + } else if (kt > ctrl->timeout) { + ctrl->defer_eoi = true; + } + } + + info = info_for_irq(irq); + + if (ctrl->defer_eoi) { + info->eoi_cpu = smp_processor_id(); + info->irq_epoch = __this_cpu_read(irq_epoch); + info->eoi_time = get_jiffies_64() + event_eoi_delay; + } + + generic_handle_irq(irq); +} + static DEFINE_PER_CPU(unsigned, xed_nesting_count); static void __xen_evtchn_do_upcall(void) @@ -1233,6 +1550,9 @@ static void __xen_evtchn_do_upcall(void) struct vcpu_info *vcpu_info = __this_cpu_read(xen_vcpu); int cpu = get_cpu(); unsigned count; + struct evtchn_loop_ctrl ctrl = { 0 }; + + read_lock(&evtchn_rwlock); do { vcpu_info->evtchn_upcall_pending = 0; @@ -1240,7 +1560,7 @@ static void __xen_evtchn_do_upcall(void) if (__this_cpu_inc_return(xed_nesting_count) - 1) goto out; - xen_evtchn_handle_events(cpu); + xen_evtchn_handle_events(cpu, &ctrl); BUG_ON(!irqs_disabled()); @@ -1249,6 +1569,14 @@ static void __xen_evtchn_do_upcall(void) } while (count != 1 || vcpu_info->evtchn_upcall_pending); out: + read_unlock(&evtchn_rwlock); + + /* + * Increment irq_epoch only now to defer EOIs only for + * xen_irq_lateeoi() invocations occurring from inside the loop + * above. + */ + __this_cpu_inc(irq_epoch); put_cpu(); } @@ -1615,6 +1943,21 @@ static struct irq_chip xen_dynamic_chip __read_mostly = { .irq_retrigger = retrigger_dynirq, }; +static struct irq_chip xen_lateeoi_chip __read_mostly = { + /* The chip name needs to contain "xen-dyn" for irqbalance to work. */ + .name = "xen-dyn-lateeoi", + + .irq_disable = disable_dynirq, + .irq_mask = disable_dynirq, + .irq_unmask = enable_dynirq, + + .irq_ack = mask_ack_dynirq, + .irq_mask_ack = mask_ack_dynirq, + + .irq_set_affinity = set_affinity_irq, + .irq_retrigger = retrigger_dynirq, +}; + static struct irq_chip xen_pirq_chip __read_mostly = { .name = "xen-pirq", @@ -1681,12 +2024,31 @@ void xen_callback_vector(void) void xen_callback_vector(void) {} #endif -#undef MODULE_PARAM_PREFIX -#define MODULE_PARAM_PREFIX "xen." - static bool fifo_events = true; module_param(fifo_events, bool, 0); +static int xen_evtchn_cpu_prepare(unsigned int cpu) +{ + int ret = 0; + + xen_cpu_init_eoi(cpu); + + if (evtchn_ops->percpu_init) + ret = evtchn_ops->percpu_init(cpu); + + return ret; +} + +static int xen_evtchn_cpu_dead(unsigned int cpu) +{ + int ret = 0; + + if (evtchn_ops->percpu_deinit) + ret = evtchn_ops->percpu_deinit(cpu); + + return ret; +} + void __init xen_init_IRQ(void) { int ret = -EINVAL; @@ -1697,6 +2059,12 @@ void __init xen_init_IRQ(void) if (ret < 0) xen_evtchn_2l_init(); + xen_cpu_init_eoi(smp_processor_id()); + + cpuhp_setup_state_nocalls(CPUHP_XEN_EVTCHN_PREPARE, + "xen/evtchn:prepare", + xen_evtchn_cpu_prepare, xen_evtchn_cpu_dead); + evtchn_to_irq = kcalloc(EVTCHN_ROW(xen_evtchn_max_channels()), sizeof(*evtchn_to_irq), GFP_KERNEL); BUG_ON(!evtchn_to_irq); diff --git a/drivers/xen/events/events_fifo.c b/drivers/xen/events/events_fifo.c index 76b318e88382..33462521bfd0 100644 --- a/drivers/xen/events/events_fifo.c +++ b/drivers/xen/events/events_fifo.c @@ -227,19 +227,25 @@ static bool evtchn_fifo_is_masked(unsigned port) return sync_test_bit(EVTCHN_FIFO_BIT(MASKED, word), BM(word)); } /* - * Clear MASKED, spinning if BUSY is set. + * Clear MASKED if not PENDING, spinning if BUSY is set. + * Return true if mask was cleared. */ -static void clear_masked(volatile event_word_t *word) +static bool clear_masked_cond(volatile event_word_t *word) { event_word_t new, old, w; w = *word; do { + if (w & (1 << EVTCHN_FIFO_PENDING)) + return false; + old = w & ~(1 << EVTCHN_FIFO_BUSY); new = old & ~(1 << EVTCHN_FIFO_MASKED); w = sync_cmpxchg(word, old, new); } while (w != old); + + return true; } static void evtchn_fifo_unmask(unsigned port) @@ -248,8 +254,7 @@ static void evtchn_fifo_unmask(unsigned port) BUG_ON(!irqs_disabled()); - clear_masked(word); - if (evtchn_fifo_is_pending(port)) { + if (!clear_masked_cond(word)) { struct evtchn_unmask unmask = { .port = port }; (void)HYPERVISOR_event_channel_op(EVTCHNOP_unmask, &unmask); } @@ -270,19 +275,9 @@ static uint32_t clear_linked(volatile event_word_t *word) return w & EVTCHN_FIFO_LINK_MASK; } -static void handle_irq_for_port(unsigned port) -{ - int irq; - - irq = get_evtchn_to_irq(port); - if (irq != -1) - generic_handle_irq(irq); -} - -static void consume_one_event(unsigned cpu, +static void consume_one_event(unsigned cpu, struct evtchn_loop_ctrl *ctrl, struct evtchn_fifo_control_block *control_block, - unsigned priority, unsigned long *ready, - bool drop) + unsigned priority, unsigned long *ready) { struct evtchn_fifo_queue *q = &per_cpu(cpu_queue, cpu); uint32_t head; @@ -315,16 +310,17 @@ static void consume_one_event(unsigned cpu, clear_bit(priority, ready); if (evtchn_fifo_is_pending(port) && !evtchn_fifo_is_masked(port)) { - if (unlikely(drop)) + if (unlikely(!ctrl)) pr_warn("Dropping pending event for port %u\n", port); else - handle_irq_for_port(port); + handle_irq_for_port(port, ctrl); } q->head[priority] = head; } -static void __evtchn_fifo_handle_events(unsigned cpu, bool drop) +static void __evtchn_fifo_handle_events(unsigned cpu, + struct evtchn_loop_ctrl *ctrl) { struct evtchn_fifo_control_block *control_block; unsigned long ready; @@ -336,14 +332,15 @@ static void __evtchn_fifo_handle_events(unsigned cpu, bool drop) while (ready) { q = find_first_bit(&ready, EVTCHN_FIFO_MAX_QUEUES); - consume_one_event(cpu, control_block, q, &ready, drop); + consume_one_event(cpu, ctrl, control_block, q, &ready); ready |= xchg(&control_block->ready, 0); } } -static void evtchn_fifo_handle_events(unsigned cpu) +static void evtchn_fifo_handle_events(unsigned cpu, + struct evtchn_loop_ctrl *ctrl) { - __evtchn_fifo_handle_events(cpu, false); + __evtchn_fifo_handle_events(cpu, ctrl); } static void evtchn_fifo_resume(void) @@ -380,21 +377,6 @@ static void evtchn_fifo_resume(void) event_array_pages = 0; } -static const struct evtchn_ops evtchn_ops_fifo = { - .max_channels = evtchn_fifo_max_channels, - .nr_channels = evtchn_fifo_nr_channels, - .setup = evtchn_fifo_setup, - .bind_to_cpu = evtchn_fifo_bind_to_cpu, - .clear_pending = evtchn_fifo_clear_pending, - .set_pending = evtchn_fifo_set_pending, - .is_pending = evtchn_fifo_is_pending, - .test_and_set_mask = evtchn_fifo_test_and_set_mask, - .mask = evtchn_fifo_mask, - .unmask = evtchn_fifo_unmask, - .handle_events = evtchn_fifo_handle_events, - .resume = evtchn_fifo_resume, -}; - static int evtchn_fifo_alloc_control_block(unsigned cpu) { void *control_block = NULL; @@ -417,19 +399,36 @@ static int evtchn_fifo_alloc_control_block(unsigned cpu) return ret; } -static int xen_evtchn_cpu_prepare(unsigned int cpu) +static int evtchn_fifo_percpu_init(unsigned int cpu) { if (!per_cpu(cpu_control_block, cpu)) return evtchn_fifo_alloc_control_block(cpu); return 0; } -static int xen_evtchn_cpu_dead(unsigned int cpu) +static int evtchn_fifo_percpu_deinit(unsigned int cpu) { - __evtchn_fifo_handle_events(cpu, true); + __evtchn_fifo_handle_events(cpu, NULL); return 0; } +static const struct evtchn_ops evtchn_ops_fifo = { + .max_channels = evtchn_fifo_max_channels, + .nr_channels = evtchn_fifo_nr_channels, + .setup = evtchn_fifo_setup, + .bind_to_cpu = evtchn_fifo_bind_to_cpu, + .clear_pending = evtchn_fifo_clear_pending, + .set_pending = evtchn_fifo_set_pending, + .is_pending = evtchn_fifo_is_pending, + .test_and_set_mask = evtchn_fifo_test_and_set_mask, + .mask = evtchn_fifo_mask, + .unmask = evtchn_fifo_unmask, + .handle_events = evtchn_fifo_handle_events, + .resume = evtchn_fifo_resume, + .percpu_init = evtchn_fifo_percpu_init, + .percpu_deinit = evtchn_fifo_percpu_deinit, +}; + int __init xen_evtchn_fifo_init(void) { int cpu = smp_processor_id(); @@ -443,9 +442,5 @@ int __init xen_evtchn_fifo_init(void) evtchn_ops = &evtchn_ops_fifo; - cpuhp_setup_state_nocalls(CPUHP_XEN_EVTCHN_PREPARE, - "xen/evtchn:prepare", - xen_evtchn_cpu_prepare, xen_evtchn_cpu_dead); - return ret; } diff --git a/drivers/xen/events/events_internal.h b/drivers/xen/events/events_internal.h index 82938cff6c7a..a35c8c7ac606 100644 --- a/drivers/xen/events/events_internal.h +++ b/drivers/xen/events/events_internal.h @@ -30,11 +30,16 @@ enum xen_irq_type { */ struct irq_info { struct list_head list; - int refcnt; + struct list_head eoi_list; + short refcnt; + short spurious_cnt; enum xen_irq_type type; /* type */ unsigned irq; unsigned int evtchn; /* event channel */ unsigned short cpu; /* cpu bound */ + unsigned short eoi_cpu; /* EOI must happen on this cpu */ + unsigned int irq_epoch; /* If eoi_cpu valid: irq_epoch of event */ + u64 eoi_time; /* Time in jiffies when to EOI. */ union { unsigned short virq; @@ -53,6 +58,8 @@ struct irq_info { #define PIRQ_SHAREABLE (1 << 1) #define PIRQ_MSI_GROUP (1 << 2) +struct evtchn_loop_ctrl; + struct evtchn_ops { unsigned (*max_channels)(void); unsigned (*nr_channels)(void); @@ -67,14 +74,18 @@ struct evtchn_ops { void (*mask)(unsigned port); void (*unmask)(unsigned port); - void (*handle_events)(unsigned cpu); + void (*handle_events)(unsigned cpu, struct evtchn_loop_ctrl *ctrl); void (*resume)(void); + + int (*percpu_init)(unsigned int cpu); + int (*percpu_deinit)(unsigned int cpu); }; extern const struct evtchn_ops *evtchn_ops; extern int **evtchn_to_irq; int get_evtchn_to_irq(unsigned int evtchn); +void handle_irq_for_port(evtchn_port_t port, struct evtchn_loop_ctrl *ctrl); struct irq_info *info_for_irq(unsigned irq); unsigned cpu_from_irq(unsigned irq); @@ -132,9 +143,10 @@ static inline void unmask_evtchn(unsigned port) return evtchn_ops->unmask(port); } -static inline void xen_evtchn_handle_events(unsigned cpu) +static inline void xen_evtchn_handle_events(unsigned cpu, + struct evtchn_loop_ctrl *ctrl) { - return evtchn_ops->handle_events(cpu); + return evtchn_ops->handle_events(cpu, ctrl); } static inline void xen_evtchn_resume(void) diff --git a/drivers/xen/evtchn.c b/drivers/xen/evtchn.c index 052b55a14ebc..a43930191e20 100644 --- a/drivers/xen/evtchn.c +++ b/drivers/xen/evtchn.c @@ -166,7 +166,6 @@ static irqreturn_t evtchn_interrupt(int irq, void *data) "Interrupt for port %d, but apparently not enabled; per-user %p\n", evtchn->port, u); - disable_irq_nosync(irq); evtchn->enabled = false; spin_lock(&u->ring_prod_lock); @@ -292,7 +291,7 @@ static ssize_t evtchn_write(struct file *file, const char __user *buf, evtchn = find_evtchn(u, port); if (evtchn && !evtchn->enabled) { evtchn->enabled = true; - enable_irq(irq_from_evtchn(port)); + xen_irq_lateeoi(irq_from_evtchn(port), 0); } } @@ -392,8 +391,8 @@ static int evtchn_bind_to_user(struct per_user_data *u, int port) if (rc < 0) goto err; - rc = bind_evtchn_to_irqhandler(port, evtchn_interrupt, 0, - u->name, evtchn); + rc = bind_evtchn_to_irqhandler_lateeoi(port, evtchn_interrupt, 0, + u->name, evtchn); if (rc < 0) goto err; diff --git a/drivers/xen/pvcalls-back.c b/drivers/xen/pvcalls-back.c index ffe9bd843922..9439de2ca0e4 100644 --- a/drivers/xen/pvcalls-back.c +++ b/drivers/xen/pvcalls-back.c @@ -66,6 +66,7 @@ struct sock_mapping { atomic_t write; atomic_t io; atomic_t release; + atomic_t eoi; void (*saved_data_ready)(struct sock *sk); struct pvcalls_ioworker ioworker; }; @@ -87,7 +88,7 @@ static int pvcalls_back_release_active(struct xenbus_device *dev, struct pvcalls_fedata *fedata, struct sock_mapping *map); -static void pvcalls_conn_back_read(void *opaque) +static bool pvcalls_conn_back_read(void *opaque) { struct sock_mapping *map = (struct sock_mapping *)opaque; struct msghdr msg; @@ -107,17 +108,17 @@ static void pvcalls_conn_back_read(void *opaque) virt_mb(); if (error) - return; + return false; size = pvcalls_queued(prod, cons, array_size); if (size >= array_size) - return; + return false; spin_lock_irqsave(&map->sock->sk->sk_receive_queue.lock, flags); if (skb_queue_empty(&map->sock->sk->sk_receive_queue)) { atomic_set(&map->read, 0); spin_unlock_irqrestore(&map->sock->sk->sk_receive_queue.lock, flags); - return; + return true; } spin_unlock_irqrestore(&map->sock->sk->sk_receive_queue.lock, flags); wanted = array_size - size; @@ -141,7 +142,7 @@ static void pvcalls_conn_back_read(void *opaque) ret = inet_recvmsg(map->sock, &msg, wanted, MSG_DONTWAIT); WARN_ON(ret > wanted); if (ret == -EAGAIN) /* shouldn't happen */ - return; + return true; if (!ret) ret = -ENOTCONN; spin_lock_irqsave(&map->sock->sk->sk_receive_queue.lock, flags); @@ -160,10 +161,10 @@ static void pvcalls_conn_back_read(void *opaque) virt_wmb(); notify_remote_via_irq(map->irq); - return; + return true; } -static void pvcalls_conn_back_write(struct sock_mapping *map) +static bool pvcalls_conn_back_write(struct sock_mapping *map) { struct pvcalls_data_intf *intf = map->ring; struct pvcalls_data *data = &map->data; @@ -180,7 +181,7 @@ static void pvcalls_conn_back_write(struct sock_mapping *map) array_size = XEN_FLEX_RING_SIZE(map->ring_order); size = pvcalls_queued(prod, cons, array_size); if (size == 0) - return; + return false; memset(&msg, 0, sizeof(msg)); msg.msg_flags |= MSG_DONTWAIT; @@ -198,12 +199,11 @@ static void pvcalls_conn_back_write(struct sock_mapping *map) atomic_set(&map->write, 0); ret = inet_sendmsg(map->sock, &msg, size); - if (ret == -EAGAIN || (ret >= 0 && ret < size)) { + if (ret == -EAGAIN) { atomic_inc(&map->write); atomic_inc(&map->io); + return true; } - if (ret == -EAGAIN) - return; /* write the data, then update the indexes */ virt_wmb(); @@ -216,9 +216,13 @@ static void pvcalls_conn_back_write(struct sock_mapping *map) } /* update the indexes, then notify the other end */ virt_wmb(); - if (prod != cons + ret) + if (prod != cons + ret) { atomic_inc(&map->write); + atomic_inc(&map->io); + } notify_remote_via_irq(map->irq); + + return true; } static void pvcalls_back_ioworker(struct work_struct *work) @@ -227,6 +231,7 @@ static void pvcalls_back_ioworker(struct work_struct *work) struct pvcalls_ioworker, register_work); struct sock_mapping *map = container_of(ioworker, struct sock_mapping, ioworker); + unsigned int eoi_flags = XEN_EOI_FLAG_SPURIOUS; while (atomic_read(&map->io) > 0) { if (atomic_read(&map->release) > 0) { @@ -234,10 +239,18 @@ static void pvcalls_back_ioworker(struct work_struct *work) return; } - if (atomic_read(&map->read) > 0) - pvcalls_conn_back_read(map); - if (atomic_read(&map->write) > 0) - pvcalls_conn_back_write(map); + if (atomic_read(&map->read) > 0 && + pvcalls_conn_back_read(map)) + eoi_flags = 0; + if (atomic_read(&map->write) > 0 && + pvcalls_conn_back_write(map)) + eoi_flags = 0; + + if (atomic_read(&map->eoi) > 0 && !atomic_read(&map->write)) { + atomic_set(&map->eoi, 0); + xen_irq_lateeoi(map->irq, eoi_flags); + eoi_flags = XEN_EOI_FLAG_SPURIOUS; + } atomic_dec(&map->io); } @@ -334,12 +347,9 @@ static struct sock_mapping *pvcalls_new_active_socket( goto out; map->bytes = page; - ret = bind_interdomain_evtchn_to_irqhandler(fedata->dev->otherend_id, - evtchn, - pvcalls_back_conn_event, - 0, - "pvcalls-backend", - map); + ret = bind_interdomain_evtchn_to_irqhandler_lateeoi( + fedata->dev->otherend_id, evtchn, + pvcalls_back_conn_event, 0, "pvcalls-backend", map); if (ret < 0) goto out; map->irq = ret; @@ -873,15 +883,18 @@ static irqreturn_t pvcalls_back_event(int irq, void *dev_id) { struct xenbus_device *dev = dev_id; struct pvcalls_fedata *fedata = NULL; + unsigned int eoi_flags = XEN_EOI_FLAG_SPURIOUS; - if (dev == NULL) - return IRQ_HANDLED; + if (dev) { + fedata = dev_get_drvdata(&dev->dev); + if (fedata) { + pvcalls_back_work(fedata); + eoi_flags = 0; + } + } - fedata = dev_get_drvdata(&dev->dev); - if (fedata == NULL) - return IRQ_HANDLED; + xen_irq_lateeoi(irq, eoi_flags); - pvcalls_back_work(fedata); return IRQ_HANDLED; } @@ -891,12 +904,15 @@ static irqreturn_t pvcalls_back_conn_event(int irq, void *sock_map) struct pvcalls_ioworker *iow; if (map == NULL || map->sock == NULL || map->sock->sk == NULL || - map->sock->sk->sk_user_data != map) + map->sock->sk->sk_user_data != map) { + xen_irq_lateeoi(irq, 0); return IRQ_HANDLED; + } iow = &map->ioworker; atomic_inc(&map->write); + atomic_inc(&map->eoi); atomic_inc(&map->io); queue_work(iow->wq, &iow->register_work); @@ -931,7 +947,7 @@ static int backend_connect(struct xenbus_device *dev) goto error; } - err = bind_interdomain_evtchn_to_irq(dev->otherend_id, evtchn); + err = bind_interdomain_evtchn_to_irq_lateeoi(dev->otherend_id, evtchn); if (err < 0) goto error; fedata->irq = err; diff --git a/drivers/xen/xen-pciback/pci_stub.c b/drivers/xen/xen-pciback/pci_stub.c index 097410a7cdb7..adf3aae2939f 100644 --- a/drivers/xen/xen-pciback/pci_stub.c +++ b/drivers/xen/xen-pciback/pci_stub.c @@ -733,10 +733,17 @@ static pci_ers_result_t common_process(struct pcistub_device *psdev, wmb(); notify_remote_via_irq(pdev->evtchn_irq); + /* Enable IRQ to signal "request done". */ + xen_pcibk_lateeoi(pdev, 0); + ret = wait_event_timeout(xen_pcibk_aer_wait_queue, !(test_bit(_XEN_PCIB_active, (unsigned long *) &sh_info->flags)), 300*HZ); + /* Enable IRQ for pcifront request if not already active. */ + if (!test_bit(_PDEVF_op_active, &pdev->flags)) + xen_pcibk_lateeoi(pdev, 0); + if (!ret) { if (test_bit(_XEN_PCIB_active, (unsigned long *)&sh_info->flags)) { @@ -750,13 +757,6 @@ static pci_ers_result_t common_process(struct pcistub_device *psdev, } clear_bit(_PCIB_op_pending, (unsigned long *)&pdev->flags); - if (test_bit(_XEN_PCIF_active, - (unsigned long *)&sh_info->flags)) { - dev_dbg(&psdev->dev->dev, - "schedule pci_conf service in " DRV_NAME "\n"); - xen_pcibk_test_and_schedule_op(psdev->pdev); - } - res = (pci_ers_result_t)aer_op->err; return res; } diff --git a/drivers/xen/xen-pciback/pciback.h b/drivers/xen/xen-pciback/pciback.h index 263c059bff90..235cdfe13494 100644 --- a/drivers/xen/xen-pciback/pciback.h +++ b/drivers/xen/xen-pciback/pciback.h @@ -14,6 +14,7 @@ #include <linux/spinlock.h> #include <linux/workqueue.h> #include <linux/atomic.h> +#include <xen/events.h> #include <xen/interface/io/pciif.h> #define DRV_NAME "xen-pciback" @@ -27,6 +28,8 @@ struct pci_dev_entry { #define PDEVF_op_active (1<<(_PDEVF_op_active)) #define _PCIB_op_pending (1) #define PCIB_op_pending (1<<(_PCIB_op_pending)) +#define _EOI_pending (2) +#define EOI_pending (1<<(_EOI_pending)) struct xen_pcibk_device { void *pci_dev_data; @@ -182,12 +185,17 @@ static inline void xen_pcibk_release_devices(struct xen_pcibk_device *pdev) irqreturn_t xen_pcibk_handle_event(int irq, void *dev_id); void xen_pcibk_do_op(struct work_struct *data); +static inline void xen_pcibk_lateeoi(struct xen_pcibk_device *pdev, + unsigned int eoi_flag) +{ + if (test_and_clear_bit(_EOI_pending, &pdev->flags)) + xen_irq_lateeoi(pdev->evtchn_irq, eoi_flag); +} + int xen_pcibk_xenbus_register(void); void xen_pcibk_xenbus_unregister(void); extern int verbose_request; - -void xen_pcibk_test_and_schedule_op(struct xen_pcibk_device *pdev); #endif /* Handles shared IRQs that can to device domain and control domain. */ diff --git a/drivers/xen/xen-pciback/pciback_ops.c b/drivers/xen/xen-pciback/pciback_ops.c index 787966f44589..c4ed2c634ca7 100644 --- a/drivers/xen/xen-pciback/pciback_ops.c +++ b/drivers/xen/xen-pciback/pciback_ops.c @@ -297,26 +297,41 @@ int xen_pcibk_disable_msix(struct xen_pcibk_device *pdev, return 0; } #endif + +static inline bool xen_pcibk_test_op_pending(struct xen_pcibk_device *pdev) +{ + return test_bit(_XEN_PCIF_active, + (unsigned long *)&pdev->sh_info->flags) && + !test_and_set_bit(_PDEVF_op_active, &pdev->flags); +} + /* * Now the same evtchn is used for both pcifront conf_read_write request * as well as pcie aer front end ack. We use a new work_queue to schedule * xen_pcibk conf_read_write service for avoiding confict with aer_core * do_recovery job which also use the system default work_queue */ -void xen_pcibk_test_and_schedule_op(struct xen_pcibk_device *pdev) +static void xen_pcibk_test_and_schedule_op(struct xen_pcibk_device *pdev) { + bool eoi = true; + /* Check that frontend is requesting an operation and that we are not * already processing a request */ - if (test_bit(_XEN_PCIF_active, (unsigned long *)&pdev->sh_info->flags) - && !test_and_set_bit(_PDEVF_op_active, &pdev->flags)) { + if (xen_pcibk_test_op_pending(pdev)) { schedule_work(&pdev->op_work); + eoi = false; } /*_XEN_PCIB_active should have been cleared by pcifront. And also make sure xen_pcibk is waiting for ack by checking _PCIB_op_pending*/ if (!test_bit(_XEN_PCIB_active, (unsigned long *)&pdev->sh_info->flags) && test_bit(_PCIB_op_pending, &pdev->flags)) { wake_up(&xen_pcibk_aer_wait_queue); + eoi = false; } + + /* EOI if there was nothing to do. */ + if (eoi) + xen_pcibk_lateeoi(pdev, XEN_EOI_FLAG_SPURIOUS); } /* Performing the configuration space reads/writes must not be done in atomic @@ -324,10 +339,8 @@ void xen_pcibk_test_and_schedule_op(struct xen_pcibk_device *pdev) * use of semaphores). This function is intended to be called from a work * queue in process context taking a struct xen_pcibk_device as a parameter */ -void xen_pcibk_do_op(struct work_struct *data) +static void xen_pcibk_do_one_op(struct xen_pcibk_device *pdev) { - struct xen_pcibk_device *pdev = - container_of(data, struct xen_pcibk_device, op_work); struct pci_dev *dev; struct xen_pcibk_dev_data *dev_data = NULL; struct xen_pci_op *op = &pdev->op; @@ -400,16 +413,31 @@ void xen_pcibk_do_op(struct work_struct *data) smp_mb__before_atomic(); /* /after/ clearing PCIF_active */ clear_bit(_PDEVF_op_active, &pdev->flags); smp_mb__after_atomic(); /* /before/ final check for work */ +} - /* Check to see if the driver domain tried to start another request in - * between clearing _XEN_PCIF_active and clearing _PDEVF_op_active. - */ - xen_pcibk_test_and_schedule_op(pdev); +void xen_pcibk_do_op(struct work_struct *data) +{ + struct xen_pcibk_device *pdev = + container_of(data, struct xen_pcibk_device, op_work); + + do { + xen_pcibk_do_one_op(pdev); + } while (xen_pcibk_test_op_pending(pdev)); + + xen_pcibk_lateeoi(pdev, 0); } irqreturn_t xen_pcibk_handle_event(int irq, void *dev_id) { struct xen_pcibk_device *pdev = dev_id; + bool eoi; + + /* IRQs might come in before pdev->evtchn_irq is written. */ + if (unlikely(pdev->evtchn_irq != irq)) + pdev->evtchn_irq = irq; + + eoi = test_and_set_bit(_EOI_pending, &pdev->flags); + WARN(eoi, "IRQ while EOI pending\n"); xen_pcibk_test_and_schedule_op(pdev); diff --git a/drivers/xen/xen-pciback/xenbus.c b/drivers/xen/xen-pciback/xenbus.c index 833b2d2c4318..e7a670235965 100644 --- a/drivers/xen/xen-pciback/xenbus.c +++ b/drivers/xen/xen-pciback/xenbus.c @@ -123,7 +123,7 @@ static int xen_pcibk_do_attach(struct xen_pcibk_device *pdev, int gnt_ref, pdev->sh_info = vaddr; - err = bind_interdomain_evtchn_to_irqhandler( + err = bind_interdomain_evtchn_to_irqhandler_lateeoi( pdev->xdev->otherend_id, remote_evtchn, xen_pcibk_handle_event, 0, DRV_NAME, pdev); if (err < 0) { diff --git a/drivers/xen/xen-scsiback.c b/drivers/xen/xen-scsiback.c index ba0942e481bc..33d6499d8472 100644 --- a/drivers/xen/xen-scsiback.c +++ b/drivers/xen/xen-scsiback.c @@ -91,7 +91,6 @@ struct vscsibk_info { unsigned int irq; struct vscsiif_back_ring ring; - int ring_error; spinlock_t ring_lock; atomic_t nr_unreplied_reqs; @@ -722,7 +721,8 @@ static struct vscsibk_pend *prepare_pending_reqs(struct vscsibk_info *info, return pending_req; } -static int scsiback_do_cmd_fn(struct vscsibk_info *info) +static int scsiback_do_cmd_fn(struct vscsibk_info *info, + unsigned int *eoi_flags) { struct vscsiif_back_ring *ring = &info->ring; struct vscsiif_request ring_req; @@ -739,11 +739,12 @@ static int scsiback_do_cmd_fn(struct vscsibk_info *info) rc = ring->rsp_prod_pvt; pr_warn("Dom%d provided bogus ring requests (%#x - %#x = %u). Halting ring processing\n", info->domid, rp, rc, rp - rc); - info->ring_error = 1; - return 0; + return -EINVAL; } while ((rc != rp)) { + *eoi_flags &= ~XEN_EOI_FLAG_SPURIOUS; + if (RING_REQUEST_CONS_OVERFLOW(ring, rc)) break; @@ -802,13 +803,16 @@ static int scsiback_do_cmd_fn(struct vscsibk_info *info) static irqreturn_t scsiback_irq_fn(int irq, void *dev_id) { struct vscsibk_info *info = dev_id; + int rc; + unsigned int eoi_flags = XEN_EOI_FLAG_SPURIOUS; - if (info->ring_error) - return IRQ_HANDLED; - - while (scsiback_do_cmd_fn(info)) + while ((rc = scsiback_do_cmd_fn(info, &eoi_flags)) > 0) cond_resched(); + /* In case of a ring error we keep the event channel masked. */ + if (!rc) + xen_irq_lateeoi(irq, eoi_flags); + return IRQ_HANDLED; } @@ -829,7 +833,7 @@ static int scsiback_init_sring(struct vscsibk_info *info, grant_ref_t ring_ref, sring = (struct vscsiif_sring *)area; BACK_RING_INIT(&info->ring, sring, PAGE_SIZE); - err = bind_interdomain_evtchn_to_irq(info->domid, evtchn); + err = bind_interdomain_evtchn_to_irq_lateeoi(info->domid, evtchn); if (err < 0) goto unmap_page; @@ -1252,7 +1256,6 @@ static int scsiback_probe(struct xenbus_device *dev, info->domid = dev->otherend_id; spin_lock_init(&info->ring_lock); - info->ring_error = 0; atomic_set(&info->nr_unreplied_reqs, 0); init_waitqueue_head(&info->waiting_to_free); info->dev = dev; diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c index fe7f0bd2048e..ee9cabac1204 100644 --- a/fs/9p/vfs_file.c +++ b/fs/9p/vfs_file.c @@ -609,9 +609,9 @@ static void v9fs_mmap_vm_close(struct vm_area_struct *vma) struct writeback_control wbc = { .nr_to_write = LONG_MAX, .sync_mode = WB_SYNC_ALL, - .range_start = vma->vm_pgoff * PAGE_SIZE, + .range_start = (loff_t)vma->vm_pgoff * PAGE_SIZE, /* absolute end, byte at end included */ - .range_end = vma->vm_pgoff * PAGE_SIZE + + .range_end = (loff_t)vma->vm_pgoff * PAGE_SIZE + (vma->vm_end - vma->vm_start - 1), }; diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index c05127f50637..e25133a9e9df 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -1103,6 +1103,8 @@ static noinline int __btrfs_cow_block(struct btrfs_trans_handle *trans, ret = update_ref_for_cow(trans, root, buf, cow, &last_ref); if (ret) { + btrfs_tree_unlock(cow); + free_extent_buffer(cow); btrfs_abort_transaction(trans, ret); return ret; } @@ -1110,6 +1112,8 @@ static noinline int __btrfs_cow_block(struct btrfs_trans_handle *trans, if (test_bit(BTRFS_ROOT_REF_COWS, &root->state)) { ret = btrfs_reloc_cow_block(trans, root, buf, cow); if (ret) { + btrfs_tree_unlock(cow); + free_extent_buffer(cow); btrfs_abort_transaction(trans, ret); return ret; } @@ -1142,6 +1146,8 @@ static noinline int __btrfs_cow_block(struct btrfs_trans_handle *trans, if (last_ref) { ret = tree_mod_log_free_eb(buf); if (ret) { + btrfs_tree_unlock(cow); + free_extent_buffer(cow); btrfs_abort_transaction(trans, ret); return ret; } diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 23b4f38e2392..27128164fac9 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -3404,6 +3404,8 @@ struct reada_control *btrfs_reada_add(struct btrfs_root *root, int btrfs_reada_wait(void *handle); void btrfs_reada_detach(void *handle); int btree_readahead_hook(struct extent_buffer *eb, int err); +void btrfs_reada_remove_dev(struct btrfs_device *dev); +void btrfs_reada_undo_remove_dev(struct btrfs_device *dev); static inline int is_fstree(u64 rootid) { diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c index a34ee9c2f315..bef62b01824d 100644 --- a/fs/btrfs/delayed-inode.c +++ b/fs/btrfs/delayed-inode.c @@ -627,8 +627,7 @@ static int btrfs_delayed_inode_reserve_metadata( */ if (!src_rsv || (!trans->bytes_reserved && src_rsv->type != BTRFS_BLOCK_RSV_DELALLOC)) { - ret = btrfs_qgroup_reserve_meta_prealloc(root, - fs_info->nodesize, true); + ret = btrfs_qgroup_reserve_meta_prealloc(root, num_bytes, true); if (ret < 0) return ret; ret = btrfs_block_rsv_add(root, dst_rsv, num_bytes, diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c index 196bd241e701..96843934dcbb 100644 --- a/fs/btrfs/dev-replace.c +++ b/fs/btrfs/dev-replace.c @@ -190,7 +190,7 @@ static int btrfs_init_dev_replace_tgtdev(struct btrfs_fs_info *fs_info, int ret = 0; *device_out = NULL; - if (fs_info->fs_devices->seeding) { + if (srcdev->fs_devices->seeding) { btrfs_err(fs_info, "the filesystem is a seed filesystem!"); return -EINVAL; } @@ -631,6 +631,9 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info, } btrfs_wait_ordered_roots(fs_info, U64_MAX, 0, (u64)-1); + if (!scrub_ret) + btrfs_reada_remove_dev(src_device); + /* * We have to use this loop approach because at this point src_device * has to be available for transaction commit to complete, yet new @@ -639,6 +642,7 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info, while (1) { trans = btrfs_start_transaction(root, 0); if (IS_ERR(trans)) { + btrfs_reada_undo_remove_dev(src_device); mutex_unlock(&dev_replace->lock_finishing_cancel_unmount); return PTR_ERR(trans); } @@ -689,6 +693,7 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info, up_write(&dev_replace->rwsem); mutex_unlock(&fs_info->chunk_mutex); mutex_unlock(&fs_info->fs_devices->device_list_mutex); + btrfs_reada_undo_remove_dev(src_device); btrfs_rm_dev_replace_blocked(fs_info); if (tgt_device) btrfs_destroy_dev_replace_tgtdev(tgt_device); diff --git a/fs/btrfs/reada.c b/fs/btrfs/reada.c index 1feaeadc8cf5..2656dc8de99c 100644 --- a/fs/btrfs/reada.c +++ b/fs/btrfs/reada.c @@ -421,6 +421,9 @@ static struct reada_extent *reada_find_extent(struct btrfs_fs_info *fs_info, if (!dev->bdev) continue; + if (test_bit(BTRFS_DEV_STATE_NO_READA, &dev->dev_state)) + continue; + if (dev_replace_is_ongoing && dev == fs_info->dev_replace.tgtdev) { /* @@ -445,6 +448,8 @@ static struct reada_extent *reada_find_extent(struct btrfs_fs_info *fs_info, } have_zone = 1; } + if (!have_zone) + radix_tree_delete(&fs_info->reada_tree, index); spin_unlock(&fs_info->reada_lock); up_read(&fs_info->dev_replace.rwsem); @@ -1012,3 +1017,45 @@ void btrfs_reada_detach(void *handle) kref_put(&rc->refcnt, reada_control_release); } + +/* + * Before removing a device (device replace or device remove ioctls), call this + * function to wait for all existing readahead requests on the device and to + * make sure no one queues more readahead requests for the device. + * + * Must be called without holding neither the device list mutex nor the device + * replace semaphore, otherwise it will deadlock. + */ +void btrfs_reada_remove_dev(struct btrfs_device *dev) +{ + struct btrfs_fs_info *fs_info = dev->fs_info; + + /* Serialize with readahead extent creation at reada_find_extent(). */ + spin_lock(&fs_info->reada_lock); + set_bit(BTRFS_DEV_STATE_NO_READA, &dev->dev_state); + spin_unlock(&fs_info->reada_lock); + + /* + * There might be readahead requests added to the radix trees which + * were not yet added to the readahead work queue. We need to start + * them and wait for their completion, otherwise we can end up with + * use-after-free problems when dropping the last reference on the + * readahead extents and their zones, as they need to access the + * device structure. + */ + reada_start_machine(fs_info); + btrfs_flush_workqueue(fs_info->readahead_workers); +} + +/* + * If when removing a device (device replace or device remove ioctls) an error + * happens after calling btrfs_reada_remove_dev(), call this to undo what that + * function did. This is safe to call even if btrfs_reada_remove_dev() was not + * called before. + */ +void btrfs_reada_undo_remove_dev(struct btrfs_device *dev) +{ + spin_lock(&dev->fs_info->reada_lock); + clear_bit(BTRFS_DEV_STATE_NO_READA, &dev->dev_state); + spin_unlock(&dev->fs_info->reada_lock); +} diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index b0e5dfb9be7a..88940f494428 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -3812,6 +3812,72 @@ static int update_ref_path(struct send_ctx *sctx, struct recorded_ref *ref) return 0; } +/* + * When processing the new references for an inode we may orphanize an existing + * directory inode because its old name conflicts with one of the new references + * of the current inode. Later, when processing another new reference of our + * inode, we might need to orphanize another inode, but the path we have in the + * reference reflects the pre-orphanization name of the directory we previously + * orphanized. For example: + * + * parent snapshot looks like: + * + * . (ino 256) + * |----- f1 (ino 257) + * |----- f2 (ino 258) + * |----- d1/ (ino 259) + * |----- d2/ (ino 260) + * + * send snapshot looks like: + * + * . (ino 256) + * |----- d1 (ino 258) + * |----- f2/ (ino 259) + * |----- f2_link/ (ino 260) + * | |----- f1 (ino 257) + * | + * |----- d2 (ino 258) + * + * When processing inode 257 we compute the name for inode 259 as "d1", and we + * cache it in the name cache. Later when we start processing inode 258, when + * collecting all its new references we set a full path of "d1/d2" for its new + * reference with name "d2". When we start processing the new references we + * start by processing the new reference with name "d1", and this results in + * orphanizing inode 259, since its old reference causes a conflict. Then we + * move on the next new reference, with name "d2", and we find out we must + * orphanize inode 260, as its old reference conflicts with ours - but for the + * orphanization we use a source path corresponding to the path we stored in the + * new reference, which is "d1/d2" and not "o259-6-0/d2" - this makes the + * receiver fail since the path component "d1/" no longer exists, it was renamed + * to "o259-6-0/" when processing the previous new reference. So in this case we + * must recompute the path in the new reference and use it for the new + * orphanization operation. + */ +static int refresh_ref_path(struct send_ctx *sctx, struct recorded_ref *ref) +{ + char *name; + int ret; + + name = kmemdup(ref->name, ref->name_len, GFP_KERNEL); + if (!name) + return -ENOMEM; + + fs_path_reset(ref->full_path); + ret = get_cur_path(sctx, ref->dir, ref->dir_gen, ref->full_path); + if (ret < 0) + goto out; + + ret = fs_path_add(ref->full_path, name, ref->name_len); + if (ret < 0) + goto out; + + /* Update the reference's base name pointer. */ + set_ref_path(ref, ref->full_path); +out: + kfree(name); + return ret; +} + /* * This does all the move/link/unlink/rmdir magic. */ @@ -3880,52 +3946,56 @@ static int process_recorded_refs(struct send_ctx *sctx, int *pending_move) goto out; } + /* + * Before doing any rename and link operations, do a first pass on the + * new references to orphanize any unprocessed inodes that may have a + * reference that conflicts with one of the new references of the current + * inode. This needs to happen first because a new reference may conflict + * with the old reference of a parent directory, so we must make sure + * that the path used for link and rename commands don't use an + * orphanized name when an ancestor was not yet orphanized. + * + * Example: + * + * Parent snapshot: + * + * . (ino 256) + * |----- testdir/ (ino 259) + * | |----- a (ino 257) + * | + * |----- b (ino 258) + * + * Send snapshot: + * + * . (ino 256) + * |----- testdir_2/ (ino 259) + * | |----- a (ino 260) + * | + * |----- testdir (ino 257) + * |----- b (ino 257) + * |----- b2 (ino 258) + * + * Processing the new reference for inode 257 with name "b" may happen + * before processing the new reference with name "testdir". If so, we + * must make sure that by the time we send a link command to create the + * hard link "b", inode 259 was already orphanized, since the generated + * path in "valid_path" already contains the orphanized name for 259. + * We are processing inode 257, so only later when processing 259 we do + * the rename operation to change its temporary (orphanized) name to + * "testdir_2". + */ list_for_each_entry(cur, &sctx->new_refs, list) { - /* - * We may have refs where the parent directory does not exist - * yet. This happens if the parent directories inum is higher - * than the current inum. To handle this case, we create the - * parent directory out of order. But we need to check if this - * did already happen before due to other refs in the same dir. - */ ret = get_cur_inode_state(sctx, cur->dir, cur->dir_gen); if (ret < 0) goto out; - if (ret == inode_state_will_create) { - ret = 0; - /* - * First check if any of the current inodes refs did - * already create the dir. - */ - list_for_each_entry(cur2, &sctx->new_refs, list) { - if (cur == cur2) - break; - if (cur2->dir == cur->dir) { - ret = 1; - break; - } - } - - /* - * If that did not happen, check if a previous inode - * did already create the dir. - */ - if (!ret) - ret = did_create_dir(sctx, cur->dir); - if (ret < 0) - goto out; - if (!ret) { - ret = send_create_inode(sctx, cur->dir); - if (ret < 0) - goto out; - } - } + if (ret == inode_state_will_create) + continue; /* - * Check if this new ref would overwrite the first ref of - * another unprocessed inode. If yes, orphanize the - * overwritten inode. If we find an overwritten ref that is - * not the first ref, simply unlink it. + * Check if this new ref would overwrite the first ref of another + * unprocessed inode. If yes, orphanize the overwritten inode. + * If we find an overwritten ref that is not the first ref, + * simply unlink it. */ ret = will_overwrite_ref(sctx, cur->dir, cur->dir_gen, cur->name, cur->name_len, @@ -3942,6 +4012,12 @@ static int process_recorded_refs(struct send_ctx *sctx, int *pending_move) struct name_cache_entry *nce; struct waiting_dir_move *wdm; + if (orphanized_dir) { + ret = refresh_ref_path(sctx, cur); + if (ret < 0) + goto out; + } + ret = orphanize_inode(sctx, ow_inode, ow_gen, cur->full_path); if (ret < 0) @@ -4004,6 +4080,49 @@ static int process_recorded_refs(struct send_ctx *sctx, int *pending_move) } } + } + + list_for_each_entry(cur, &sctx->new_refs, list) { + /* + * We may have refs where the parent directory does not exist + * yet. This happens if the parent directories inum is higher + * than the current inum. To handle this case, we create the + * parent directory out of order. But we need to check if this + * did already happen before due to other refs in the same dir. + */ + ret = get_cur_inode_state(sctx, cur->dir, cur->dir_gen); + if (ret < 0) + goto out; + if (ret == inode_state_will_create) { + ret = 0; + /* + * First check if any of the current inodes refs did + * already create the dir. + */ + list_for_each_entry(cur2, &sctx->new_refs, list) { + if (cur == cur2) + break; + if (cur2->dir == cur->dir) { + ret = 1; + break; + } + } + + /* + * If that did not happen, check if a previous inode + * did already create the dir. + */ + if (!ret) + ret = did_create_dir(sctx, cur->dir); + if (ret < 0) + goto out; + if (!ret) { + ret = send_create_inode(sctx, cur->dir); + if (ret < 0) + goto out; + } + } + if (S_ISDIR(sctx->cur_inode_mode) && sctx->parent_root) { ret = wait_for_dest_dir_move(sctx, cur, is_orphan); if (ret < 0) @@ -7233,7 +7352,7 @@ long btrfs_ioctl_send(struct file *mnt_file, struct btrfs_ioctl_send_args *arg) alloc_size = sizeof(struct clone_root) * (arg->clone_sources_count + 1); - sctx->clone_roots = kzalloc(alloc_size, GFP_KERNEL); + sctx->clone_roots = kvzalloc(alloc_size, GFP_KERNEL); if (!sctx->clone_roots) { ret = -ENOMEM; goto out; diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c index 84b8d6ebf98f..48e46323d519 100644 --- a/fs/btrfs/tree-checker.c +++ b/fs/btrfs/tree-checker.c @@ -577,18 +577,36 @@ int btrfs_check_chunk_valid(struct extent_buffer *leaf, u64 type; u64 features; bool mixed = false; + int raid_index; + int nparity; + int ncopies; length = btrfs_chunk_length(leaf, chunk); stripe_len = btrfs_chunk_stripe_len(leaf, chunk); num_stripes = btrfs_chunk_num_stripes(leaf, chunk); sub_stripes = btrfs_chunk_sub_stripes(leaf, chunk); type = btrfs_chunk_type(leaf, chunk); + raid_index = btrfs_bg_flags_to_raid_index(type); + ncopies = btrfs_raid_array[raid_index].ncopies; + nparity = btrfs_raid_array[raid_index].nparity; if (!num_stripes) { chunk_err(leaf, chunk, logical, "invalid chunk num_stripes, have %u", num_stripes); return -EUCLEAN; } + if (num_stripes < ncopies) { + chunk_err(leaf, chunk, logical, + "invalid chunk num_stripes < ncopies, have %u < %d", + num_stripes, ncopies); + return -EUCLEAN; + } + if (nparity && num_stripes == nparity) { + chunk_err(leaf, chunk, logical, + "invalid chunk num_stripes == nparity, have %u == %d", + num_stripes, nparity); + return -EUCLEAN; + } if (!IS_ALIGNED(logical, fs_info->sectorsize)) { chunk_err(leaf, chunk, logical, "invalid chunk logical, have %llu should aligned to %u", @@ -869,7 +887,7 @@ static int check_root_item(struct extent_buffer *leaf, struct btrfs_key *key, int slot) { struct btrfs_fs_info *fs_info = leaf->fs_info; - struct btrfs_root_item ri; + struct btrfs_root_item ri = { 0 }; const u64 valid_root_flags = BTRFS_ROOT_SUBVOL_RDONLY | BTRFS_ROOT_SUBVOL_DEAD; @@ -889,14 +907,21 @@ static int check_root_item(struct extent_buffer *leaf, struct btrfs_key *key, return -EUCLEAN; } - if (btrfs_item_size_nr(leaf, slot) != sizeof(ri)) { + if (btrfs_item_size_nr(leaf, slot) != sizeof(ri) && + btrfs_item_size_nr(leaf, slot) != btrfs_legacy_root_item_size()) { generic_err(leaf, slot, - "invalid root item size, have %u expect %zu", - btrfs_item_size_nr(leaf, slot), sizeof(ri)); + "invalid root item size, have %u expect %zu or %u", + btrfs_item_size_nr(leaf, slot), sizeof(ri), + btrfs_legacy_root_item_size()); } + /* + * For legacy root item, the members starting at generation_v2 will be + * all filled with 0. + * And since we allow geneartion_v2 as 0, it will still pass the check. + */ read_extent_buffer(leaf, &ri, btrfs_item_ptr_offset(leaf, slot), - sizeof(ri)); + btrfs_item_size_nr(leaf, slot)); /* Generation related */ if (btrfs_root_generation(&ri) > diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 7042b84edc89..de53e5166997 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -3639,6 +3639,7 @@ static noinline int log_dir_items(struct btrfs_trans_handle *trans, * search and this search we'll not find the key again and can just * bail. */ +search: ret = btrfs_search_slot(NULL, root, &min_key, path, 0, 0); if (ret != 0) goto done; @@ -3658,6 +3659,13 @@ static noinline int log_dir_items(struct btrfs_trans_handle *trans, if (min_key.objectid != ino || min_key.type != key_type) goto done; + + if (need_resched()) { + btrfs_release_path(path); + cond_resched(); + goto search; + } + ret = overwrite_item(trans, log, dst_path, src, i, &min_key); if (ret) { diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index e798caee978e..58910a0a3e4a 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -1123,16 +1123,18 @@ static noinline struct btrfs_device *device_list_add(const char *path, bdput(path_bdev); mutex_unlock(&fs_devices->device_list_mutex); btrfs_warn_in_rcu(device->fs_info, - "duplicate device fsid:devid for %pU:%llu old:%s new:%s", - disk_super->fsid, devid, - rcu_str_deref(device->name), path); + "duplicate device %s devid %llu generation %llu scanned by %s (%d)", + path, devid, found_transid, + current->comm, + task_pid_nr(current)); return ERR_PTR(-EEXIST); } bdput(path_bdev); btrfs_info_in_rcu(device->fs_info, - "device fsid %pU devid %llu moved old:%s new:%s", - disk_super->fsid, devid, - rcu_str_deref(device->name), path); + "devid %llu device path %s changed to %s scanned by %s (%d)", + devid, rcu_str_deref(device->name), + path, current->comm, + task_pid_nr(current)); } name = rcu_string_strdup(path, GFP_NOFS); @@ -2206,6 +2208,8 @@ int btrfs_rm_device(struct btrfs_fs_info *fs_info, const char *device_path, mutex_unlock(&uuid_mutex); ret = btrfs_shrink_device(device, 0); + if (!ret) + btrfs_reada_remove_dev(device); mutex_lock(&uuid_mutex); if (ret) goto error_undo; @@ -2292,6 +2296,7 @@ int btrfs_rm_device(struct btrfs_fs_info *fs_info, const char *device_path, return ret; error_undo: + btrfs_reada_undo_remove_dev(device); if (test_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state)) { mutex_lock(&fs_info->chunk_mutex); list_add(&device->dev_alloc_list, diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h index 5acf5c507ec2..aa6a6d7b2978 100644 --- a/fs/btrfs/volumes.h +++ b/fs/btrfs/volumes.h @@ -56,6 +56,7 @@ struct btrfs_io_geometry { #define BTRFS_DEV_STATE_MISSING (2) #define BTRFS_DEV_STATE_REPLACE_TGT (3) #define BTRFS_DEV_STATE_FLUSH_SENT (4) +#define BTRFS_DEV_STATE_NO_READA (5) struct btrfs_device { struct list_head dev_list; /* device_list_mutex */ diff --git a/fs/buffer.c b/fs/buffer.c index 22d8ac4a8c40..0d7bd7712076 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -2739,16 +2739,6 @@ int nobh_writepage(struct page *page, get_block_t *get_block, /* Is the page fully outside i_size? (truncate in progress) */ offset = i_size & (PAGE_SIZE-1); if (page->index >= end_index+1 || !offset) { - /* - * The page may have dirty, unmapped buffers. For example, - * they may have been added in ext3_writepage(). Make them - * freeable here, so the page does not leak. - */ -#if 0 - /* Not really sure about this - do we need this ? */ - if (page->mapping->a_ops->invalidatepage) - page->mapping->a_ops->invalidatepage(page, offset); -#endif unlock_page(page); return 0; /* don't care */ } @@ -2943,12 +2933,6 @@ int block_write_full_page(struct page *page, get_block_t *get_block, /* Is the page fully outside i_size? (truncate in progress) */ offset = i_size & (PAGE_SIZE-1); if (page->index >= end_index+1 || !offset) { - /* - * The page may have dirty, unmapped buffers. For example, - * they may have been added in ext3_writepage(). Make them - * freeable here, so the page does not leak. - */ - do_invalidatepage(page, 0, PAGE_SIZE); unlock_page(page); return 0; /* don't care */ } diff --git a/fs/cachefiles/rdwr.c b/fs/cachefiles/rdwr.c index ad057ed2b30b..bd5fe8d00d00 100644 --- a/fs/cachefiles/rdwr.c +++ b/fs/cachefiles/rdwr.c @@ -121,7 +121,7 @@ static int cachefiles_read_reissue(struct cachefiles_object *object, _debug("reissue read"); ret = bmapping->a_ops->readpage(NULL, backpage); if (ret < 0) - goto unlock_discard; + goto discard; } /* but the page may have been read before the monitor was installed, so @@ -138,6 +138,7 @@ static int cachefiles_read_reissue(struct cachefiles_object *object, unlock_discard: unlock_page(backpage); +discard: spin_lock_irq(&object->work_lock); list_del(&monitor->op_link); spin_unlock_irq(&object->work_lock); diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index 7ab616601141..a02e845eb0fb 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -1427,7 +1427,7 @@ static vm_fault_t ceph_filemap_fault(struct vm_fault *vmf) struct ceph_inode_info *ci = ceph_inode(inode); struct ceph_file_info *fi = vma->vm_file->private_data; struct page *pinned_page = NULL; - loff_t off = vmf->pgoff << PAGE_SHIFT; + loff_t off = (loff_t)vmf->pgoff << PAGE_SHIFT; int want, got, err; sigset_t oldset; vm_fault_t ret = VM_FAULT_SIGBUS; diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index 17df90b5f57a..fd9e289f3e72 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -2614,13 +2614,18 @@ cifs_setattr(struct dentry *direntry, struct iattr *attrs) { struct cifs_sb_info *cifs_sb = CIFS_SB(direntry->d_sb); struct cifs_tcon *pTcon = cifs_sb_master_tcon(cifs_sb); + int rc, retries = 0; - if (pTcon->unix_ext) - return cifs_setattr_unix(direntry, attrs); - - return cifs_setattr_nounix(direntry, attrs); + do { + if (pTcon->unix_ext) + rc = cifs_setattr_unix(direntry, attrs); + else + rc = cifs_setattr_nounix(direntry, attrs); + retries++; + } while (is_retryable_error(rc) && retries < 2); /* BB: add cifs_setattr_legacy for really old servers */ + return rc; } #if 0 diff --git a/fs/exec.c b/fs/exec.c index de833553ae27..2441eb1a1e2d 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1044,11 +1044,24 @@ static int exec_mmap(struct mm_struct *mm) } task_lock(tsk); - active_mm = tsk->active_mm; membarrier_exec_mmap(mm); - tsk->mm = mm; + + local_irq_disable(); + active_mm = tsk->active_mm; tsk->active_mm = mm; + tsk->mm = mm; + /* + * This prevents preemption while active_mm is being loaded and + * it and mm are being updated, which could cause problems for + * lazy tlb mm refcounting when these are updated by context + * switches. Not all architectures can handle irqs off over + * activate_mm yet. + */ + if (!IS_ENABLED(CONFIG_ARCH_WANT_IRQS_OFF_ACTIVATE_MM)) + local_irq_enable(); activate_mm(active_mm, mm); + if (IS_ENABLED(CONFIG_ARCH_WANT_IRQS_OFF_ACTIVATE_MM)) + local_irq_enable(); tsk->mm->vmacache_seqnum = 0; vmacache_flush(tsk); task_unlock(tsk); diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 95a8a04c77dd..cbd028a31daf 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -5271,6 +5271,12 @@ static int ext4_do_update_inode(handle_t *handle, if (ext4_test_inode_state(inode, EXT4_STATE_NEW)) memset(raw_inode, 0, EXT4_SB(inode->i_sb)->s_inode_size); + err = ext4_inode_blocks_set(handle, raw_inode, ei); + if (err) { + spin_unlock(&ei->i_raw_lock); + goto out_brelse; + } + raw_inode->i_mode = cpu_to_le16(inode->i_mode); i_uid = i_uid_read(inode); i_gid = i_gid_read(inode); @@ -5304,11 +5310,6 @@ static int ext4_do_update_inode(handle_t *handle, EXT4_INODE_SET_XTIME(i_atime, inode, raw_inode); EXT4_EINODE_SET_XTIME(i_crtime, ei, raw_inode); - err = ext4_inode_blocks_set(handle, raw_inode, ei); - if (err) { - spin_unlock(&ei->i_raw_lock); - goto out_brelse; - } raw_inode->i_dtime = cpu_to_le32(ei->i_dtime); raw_inode->i_flags = cpu_to_le32(ei->i_flags & 0xFFFFFFFF); if (likely(!test_opt2(inode->i_sb, HURD_COMPAT))) diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index 080e25f6ef56..ad1d4c8faf44 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -861,8 +861,10 @@ static int add_new_gdb(handle_t *handle, struct inode *inode, BUFFER_TRACE(dind, "get_write_access"); err = ext4_journal_get_write_access(handle, dind); - if (unlikely(err)) + if (unlikely(err)) { ext4_std_error(sb, err); + goto errout; + } /* ext4_reserve_inode_write() gets a reference on the iloc */ err = ext4_reserve_inode_write(handle, inode, &iloc); diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 4aae7e3e89a1..6a260cc8bce6 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -4684,6 +4684,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) failed_mount8: ext4_unregister_sysfs(sb); + kobject_put(&sbi->s_kobj); failed_mount7: ext4_unregister_li_request(sb); failed_mount6: @@ -5856,6 +5857,11 @@ static int ext4_quota_on(struct super_block *sb, int type, int format_id, /* Quotafile not on the same filesystem? */ if (path->dentry->d_sb != sb) return -EXDEV; + + /* Quota already enabled for this file? */ + if (IS_NOQUOTA(d_inode(path->dentry))) + return -EBUSY; + /* Journaling quota? */ if (EXT4_SB(sb)->s_qf_names[type]) { /* Quotafile not in fs root? */ diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c index bbd07fe8a492..c966ccc44c15 100644 --- a/fs/f2fs/checkpoint.c +++ b/fs/f2fs/checkpoint.c @@ -108,7 +108,7 @@ struct page *f2fs_get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index) return __get_meta_page(sbi, index, true); } -struct page *f2fs_get_meta_page_nofail(struct f2fs_sb_info *sbi, pgoff_t index) +struct page *f2fs_get_meta_page_retry(struct f2fs_sb_info *sbi, pgoff_t index) { struct page *page; int count = 0; @@ -243,6 +243,8 @@ int f2fs_ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages, blkno * NAT_ENTRY_PER_BLOCK); break; case META_SIT: + if (unlikely(blkno >= TOTAL_SEGS(sbi))) + goto out; /* get sit block addr */ fio.new_blkaddr = current_sit_addr(sbi, blkno * SIT_ENTRY_PER_BLOCK); @@ -1044,8 +1046,12 @@ int f2fs_sync_dirty_inodes(struct f2fs_sb_info *sbi, enum inode_type type) get_pages(sbi, is_dir ? F2FS_DIRTY_DENTS : F2FS_DIRTY_DATA)); retry: - if (unlikely(f2fs_cp_error(sbi))) + if (unlikely(f2fs_cp_error(sbi))) { + trace_f2fs_sync_dirty_inodes_exit(sbi->sb, is_dir, + get_pages(sbi, is_dir ? + F2FS_DIRTY_DENTS : F2FS_DIRTY_DATA)); return -EIO; + } spin_lock(&sbi->inode_lock[type]); diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c index e9af46dc06f7..78d041f9775a 100644 --- a/fs/f2fs/dir.c +++ b/fs/f2fs/dir.c @@ -303,16 +303,15 @@ struct f2fs_dir_entry *__f2fs_find_entry(struct inode *dir, unsigned int max_depth; unsigned int level; + *res_page = NULL; + if (f2fs_has_inline_dentry(dir)) { - *res_page = NULL; de = f2fs_find_in_inline_dir(dir, fname, res_page); goto out; } - if (npages == 0) { - *res_page = NULL; + if (npages == 0) goto out; - } max_depth = F2FS_I(dir)->i_current_depth; if (unlikely(max_depth > MAX_DIR_HASH_DEPTH)) { @@ -323,7 +322,6 @@ struct f2fs_dir_entry *__f2fs_find_entry(struct inode *dir, } for (level = 0; level < max_depth; level++) { - *res_page = NULL; de = find_in_level(dir, level, fname, res_page); if (de || IS_ERR(*res_page)) break; diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index b3b7e63394be..63440abe58c4 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -3149,7 +3149,7 @@ enum rw_hint f2fs_io_type_to_rw_hint(struct f2fs_sb_info *sbi, void f2fs_stop_checkpoint(struct f2fs_sb_info *sbi, bool end_io); struct page *f2fs_grab_meta_page(struct f2fs_sb_info *sbi, pgoff_t index); struct page *f2fs_get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index); -struct page *f2fs_get_meta_page_nofail(struct f2fs_sb_info *sbi, pgoff_t index); +struct page *f2fs_get_meta_page_retry(struct f2fs_sb_info *sbi, pgoff_t index); struct page *f2fs_get_tmp_page(struct f2fs_sb_info *sbi, pgoff_t index); bool f2fs_is_valid_blkaddr(struct f2fs_sb_info *sbi, block_t blkaddr, int type); diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index ed12e9668184..2a4a382f28fe 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -109,7 +109,7 @@ static void clear_node_page_dirty(struct page *page) static struct page *get_current_nat_page(struct f2fs_sb_info *sbi, nid_t nid) { - return f2fs_get_meta_page_nofail(sbi, current_nat_addr(sbi, nid)); + return f2fs_get_meta_page(sbi, current_nat_addr(sbi, nid)); } static struct page *get_next_nat_page(struct f2fs_sb_info *sbi, nid_t nid) diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index 7d8578401267..5ba677f85533 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -2310,7 +2310,9 @@ int f2fs_npages_for_summary_flush(struct f2fs_sb_info *sbi, bool for_ra) */ struct page *f2fs_get_sum_page(struct f2fs_sb_info *sbi, unsigned int segno) { - return f2fs_get_meta_page_nofail(sbi, GET_SUM_BLOCK(sbi, segno)); + if (unlikely(f2fs_cp_error(sbi))) + return ERR_PTR(-EIO); + return f2fs_get_meta_page_retry(sbi, GET_SUM_BLOCK(sbi, segno)); } void f2fs_update_meta_page(struct f2fs_sb_info *sbi, @@ -2582,7 +2584,11 @@ static void change_curseg(struct f2fs_sb_info *sbi, int type) __next_free_blkoff(sbi, curseg, 0); sum_page = f2fs_get_sum_page(sbi, new_segno); - f2fs_bug_on(sbi, IS_ERR(sum_page)); + if (IS_ERR(sum_page)) { + /* GC won't be able to use stale summary pages by cp_error */ + memset(curseg->sum_blk, 0, SUM_ENTRY_SIZE); + return; + } sum_node = (struct f2fs_summary_block *)page_address(sum_page); memcpy(curseg->sum_blk, sum_node, SUM_ENTRY_SIZE); f2fs_put_page(sum_page, 1); @@ -3713,7 +3719,7 @@ int f2fs_lookup_journal_in_cursum(struct f2fs_journal *journal, int type, static struct page *get_current_sit_page(struct f2fs_sb_info *sbi, unsigned int segno) { - return f2fs_get_meta_page_nofail(sbi, current_sit_addr(sbi, segno)); + return f2fs_get_meta_page(sbi, current_sit_addr(sbi, segno)); } static struct page *get_next_sit_page(struct f2fs_sb_info *sbi, diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h index 5f89c515f5bb..33a6b074209d 100644 --- a/fs/gfs2/incore.h +++ b/fs/gfs2/incore.h @@ -694,6 +694,7 @@ struct gfs2_sbd { struct super_block *sd_vfs; struct gfs2_pcpu_lkstats __percpu *sd_lkstats; struct kobject sd_kobj; + struct completion sd_kobj_unregister; unsigned long sd_flags; /* SDF_... */ struct gfs2_sb_host sd_sb; diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c index e0c55765b06d..29b27d769860 100644 --- a/fs/gfs2/ops_fstype.c +++ b/fs/gfs2/ops_fstype.c @@ -169,15 +169,19 @@ static int gfs2_check_sb(struct gfs2_sbd *sdp, int silent) return -EINVAL; } - /* If format numbers match exactly, we're done. */ - - if (sb->sb_fs_format == GFS2_FORMAT_FS && - sb->sb_multihost_format == GFS2_FORMAT_MULTI) - return 0; + if (sb->sb_fs_format != GFS2_FORMAT_FS || + sb->sb_multihost_format != GFS2_FORMAT_MULTI) { + fs_warn(sdp, "Unknown on-disk format, unable to mount\n"); + return -EINVAL; + } - fs_warn(sdp, "Unknown on-disk format, unable to mount\n"); + if (sb->sb_bsize < 512 || sb->sb_bsize > PAGE_SIZE || + (sb->sb_bsize & (sb->sb_bsize - 1))) { + pr_warn("Invalid superblock size\n"); + return -EINVAL; + } - return -EINVAL; + return 0; } static void end_bio_io_page(struct bio *bio) @@ -1094,26 +1098,14 @@ static int gfs2_fill_super(struct super_block *sb, struct fs_context *fc) } error = init_names(sdp, silent); - if (error) { - /* In this case, we haven't initialized sysfs, so we have to - manually free the sdp. */ - free_sbd(sdp); - sb->s_fs_info = NULL; - return error; - } + if (error) + goto fail_free; snprintf(sdp->sd_fsname, sizeof(sdp->sd_fsname), "%s", sdp->sd_table_name); error = gfs2_sys_fs_add(sdp); - /* - * If we hit an error here, gfs2_sys_fs_add will have called function - * kobject_put which causes the sysfs usage count to go to zero, which - * causes sysfs to call function gfs2_sbd_release, which frees sdp. - * Subsequent error paths here will call gfs2_sys_fs_del, which also - * kobject_put to free sdp. - */ if (error) - return error; + goto fail_free; gfs2_create_debugfs_file(sdp); @@ -1210,9 +1202,9 @@ static int gfs2_fill_super(struct super_block *sb, struct fs_context *fc) gfs2_lm_unmount(sdp); fail_debug: gfs2_delete_debugfs_file(sdp); - /* gfs2_sys_fs_del must be the last thing we do, since it causes - * sysfs to call function gfs2_sbd_release, which frees sdp. */ gfs2_sys_fs_del(sdp); +fail_free: + free_sbd(sdp); sb->s_fs_info = NULL; return error; } diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c index 5fa1eec4fb4f..5935ce5ae563 100644 --- a/fs/gfs2/super.c +++ b/fs/gfs2/super.c @@ -695,6 +695,7 @@ static void gfs2_put_super(struct super_block *sb) /* At this point, we're through participating in the lockspace */ gfs2_sys_fs_del(sdp); + free_sbd(sdp); } /** diff --git a/fs/gfs2/sys.c b/fs/gfs2/sys.c index dd15b8e4af2c..1c6e52dc878e 100644 --- a/fs/gfs2/sys.c +++ b/fs/gfs2/sys.c @@ -302,7 +302,7 @@ static void gfs2_sbd_release(struct kobject *kobj) { struct gfs2_sbd *sdp = container_of(kobj, struct gfs2_sbd, sd_kobj); - free_sbd(sdp); + complete(&sdp->sd_kobj_unregister); } static struct kobj_type gfs2_ktype = { @@ -652,6 +652,7 @@ int gfs2_sys_fs_add(struct gfs2_sbd *sdp) sprintf(ro, "RDONLY=%d", sb_rdonly(sb)); sprintf(spectator, "SPECTATOR=%d", sdp->sd_args.ar_spectator ? 1 : 0); + init_completion(&sdp->sd_kobj_unregister); sdp->sd_kobj.kset = gfs2_kset; error = kobject_init_and_add(&sdp->sd_kobj, &gfs2_ktype, NULL, "%s", sdp->sd_table_name); @@ -682,6 +683,7 @@ int gfs2_sys_fs_add(struct gfs2_sbd *sdp) fail_reg: fs_err(sdp, "error %d adding sysfs files\n", error); kobject_put(&sdp->sd_kobj); + wait_for_completion(&sdp->sd_kobj_unregister); sb->s_fs_info = NULL; return error; } @@ -692,6 +694,7 @@ void gfs2_sys_fs_del(struct gfs2_sbd *sdp) sysfs_remove_group(&sdp->sd_kobj, &tune_group); sysfs_remove_group(&sdp->sd_kobj, &lock_module_group); kobject_put(&sdp->sd_kobj); + wait_for_completion(&sdp->sd_kobj_unregister); } static int gfs2_uevent(struct kset *kset, struct kobject *kobj, diff --git a/fs/nfs/namespace.c b/fs/nfs/namespace.c index 9287eb666322..2db17fdf516b 100644 --- a/fs/nfs/namespace.c +++ b/fs/nfs/namespace.c @@ -31,9 +31,9 @@ int nfs_mountpoint_expiry_timeout = 500 * HZ; /* * nfs_path - reconstruct the path given an arbitrary dentry * @base - used to return pointer to the end of devname part of path - * @dentry - pointer to dentry + * @dentry_in - pointer to dentry * @buffer - result buffer - * @buflen - length of buffer + * @buflen_in - length of buffer * @flags - options (see below) * * Helper function for constructing the server pathname @@ -48,15 +48,19 @@ int nfs_mountpoint_expiry_timeout = 500 * HZ; * the original device (export) name * (if unset, the original name is returned verbatim) */ -char *nfs_path(char **p, struct dentry *dentry, char *buffer, ssize_t buflen, - unsigned flags) +char *nfs_path(char **p, struct dentry *dentry_in, char *buffer, + ssize_t buflen_in, unsigned flags) { char *end; int namelen; unsigned seq; const char *base; + struct dentry *dentry; + ssize_t buflen; rename_retry: + buflen = buflen_in; + dentry = dentry_in; end = buffer+buflen; *--end = '\0'; buflen--; diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h index bb322d9de313..c4a98cbda6dd 100644 --- a/fs/nfs/nfs4_fs.h +++ b/fs/nfs/nfs4_fs.h @@ -570,6 +570,14 @@ static inline bool nfs4_stateid_is_newer(const nfs4_stateid *s1, const nfs4_stat return (s32)(be32_to_cpu(s1->seqid) - be32_to_cpu(s2->seqid)) > 0; } +static inline bool nfs4_stateid_is_next(const nfs4_stateid *s1, const nfs4_stateid *s2) +{ + u32 seq1 = be32_to_cpu(s1->seqid); + u32 seq2 = be32_to_cpu(s2->seqid); + + return seq2 == seq1 + 1U || (seq2 == 1U && seq1 == 0xffffffffU); +} + static inline void nfs4_stateid_seqid_inc(nfs4_stateid *s1) { u32 seqid = be32_to_cpu(s1->seqid); diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c index 534b6fd70ffd..6b31cb5f9c9d 100644 --- a/fs/nfs/nfs4file.c +++ b/fs/nfs/nfs4file.c @@ -138,7 +138,8 @@ static ssize_t __nfs4_copy_file_range(struct file *file_in, loff_t pos_in, /* Only offload copy if superblock is the same */ if (file_inode(file_in)->i_sb != file_inode(file_out)->i_sb) return -EXDEV; - if (!nfs_server_capable(file_inode(file_out), NFS_CAP_COPY)) + if (!nfs_server_capable(file_inode(file_out), NFS_CAP_COPY) || + !nfs_server_capable(file_inode(file_in), NFS_CAP_COPY)) return -EOPNOTSUPP; if (file_inode(file_in) == file_inode(file_out)) return -EOPNOTSUPP; diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 00435556db0c..ddc900df461c 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -1515,19 +1515,6 @@ static void nfs_state_log_update_open_stateid(struct nfs4_state *state) wake_up_all(&state->waitq); } -static void nfs_state_log_out_of_order_open_stateid(struct nfs4_state *state, - const nfs4_stateid *stateid) -{ - u32 state_seqid = be32_to_cpu(state->open_stateid.seqid); - u32 stateid_seqid = be32_to_cpu(stateid->seqid); - - if (stateid_seqid == state_seqid + 1U || - (stateid_seqid == 1U && state_seqid == 0xffffffffU)) - nfs_state_log_update_open_stateid(state); - else - set_bit(NFS_STATE_CHANGE_WAIT, &state->flags); -} - static void nfs_test_and_clear_all_open_stateid(struct nfs4_state *state) { struct nfs_client *clp = state->owner->so_server->nfs_client; @@ -1553,21 +1540,19 @@ static void nfs_test_and_clear_all_open_stateid(struct nfs4_state *state) * i.e. The stateid seqids have to be initialised to 1, and * are then incremented on every state transition. */ -static bool nfs_need_update_open_stateid(struct nfs4_state *state, +static bool nfs_stateid_is_sequential(struct nfs4_state *state, const nfs4_stateid *stateid) { - if (test_bit(NFS_OPEN_STATE, &state->flags) == 0 || - !nfs4_stateid_match_other(stateid, &state->open_stateid)) { + if (test_bit(NFS_OPEN_STATE, &state->flags)) { + /* The common case - we're updating to a new sequence number */ + if (nfs4_stateid_match_other(stateid, &state->open_stateid) && + nfs4_stateid_is_next(&state->open_stateid, stateid)) { + return true; + } + } else { + /* This is the first OPEN in this generation */ if (stateid->seqid == cpu_to_be32(1)) - nfs_state_log_update_open_stateid(state); - else - set_bit(NFS_STATE_CHANGE_WAIT, &state->flags); - return true; - } - - if (nfs4_stateid_is_newer(stateid, &state->open_stateid)) { - nfs_state_log_out_of_order_open_stateid(state, stateid); - return true; + return true; } return false; } @@ -1641,16 +1626,16 @@ static void nfs_set_open_stateid_locked(struct nfs4_state *state, int status = 0; for (;;) { - if (!nfs_need_update_open_stateid(state, stateid)) - return; - if (!test_bit(NFS_STATE_CHANGE_WAIT, &state->flags)) + if (nfs_stateid_is_sequential(state, stateid)) break; + if (status) break; /* Rely on seqids for serialisation with NFSv4.0 */ if (!nfs4_has_session(NFS_SERVER(state->inode)->nfs_client)) break; + set_bit(NFS_STATE_CHANGE_WAIT, &state->flags); prepare_to_wait(&state->waitq, &wait, TASK_KILLABLE); /* * Ensure we process the state changes in the same order @@ -1661,6 +1646,7 @@ static void nfs_set_open_stateid_locked(struct nfs4_state *state, spin_unlock(&state->owner->so_lock); rcu_read_unlock(); trace_nfs4_open_stateid_update_wait(state->inode, stateid, 0); + if (!signal_pending(current)) { if (schedule_timeout(5*HZ) == 0) status = -EAGAIN; @@ -3397,7 +3383,8 @@ static bool nfs4_refresh_open_old_stateid(nfs4_stateid *dst, __be32 seqid_open; u32 dst_seqid; bool ret; - int seq; + int seq, status = -EAGAIN; + DEFINE_WAIT(wait); for (;;) { ret = false; @@ -3409,15 +3396,41 @@ static bool nfs4_refresh_open_old_stateid(nfs4_stateid *dst, continue; break; } + + write_seqlock(&state->seqlock); seqid_open = state->open_stateid.seqid; - if (read_seqretry(&state->seqlock, seq)) - continue; dst_seqid = be32_to_cpu(dst->seqid); - if ((s32)(dst_seqid - be32_to_cpu(seqid_open)) >= 0) - dst->seqid = cpu_to_be32(dst_seqid + 1); - else + + /* Did another OPEN bump the state's seqid? try again: */ + if ((s32)(be32_to_cpu(seqid_open) - dst_seqid) > 0) { dst->seqid = seqid_open; + write_sequnlock(&state->seqlock); + ret = true; + break; + } + + /* server says we're behind but we haven't seen the update yet */ + set_bit(NFS_STATE_CHANGE_WAIT, &state->flags); + prepare_to_wait(&state->waitq, &wait, TASK_KILLABLE); + write_sequnlock(&state->seqlock); + trace_nfs4_close_stateid_update_wait(state->inode, dst, 0); + + if (signal_pending(current)) + status = -EINTR; + else + if (schedule_timeout(5*HZ) != 0) + status = 0; + + finish_wait(&state->waitq, &wait); + + if (!status) + continue; + if (status == -EINTR) + break; + + /* we slept the whole 5 seconds, we must have lost a seqid */ + dst->seqid = cpu_to_be32(dst_seqid + 1); ret = true; break; } @@ -7846,9 +7859,11 @@ int nfs4_proc_secinfo(struct inode *dir, const struct qstr *name, * both PNFS and NON_PNFS flags set, and not having one of NON_PNFS, PNFS, or * DS flags set. */ -static int nfs4_check_cl_exchange_flags(u32 flags) +static int nfs4_check_cl_exchange_flags(u32 flags, u32 version) { - if (flags & ~EXCHGID4_FLAG_MASK_R) + if (version >= 2 && (flags & ~EXCHGID4_2_FLAG_MASK_R)) + goto out_inval; + else if (version < 2 && (flags & ~EXCHGID4_FLAG_MASK_R)) goto out_inval; if ((flags & EXCHGID4_FLAG_USE_PNFS_MDS) && (flags & EXCHGID4_FLAG_USE_NON_PNFS)) @@ -8261,7 +8276,8 @@ static int _nfs4_proc_exchange_id(struct nfs_client *clp, const struct cred *cre if (status != 0) goto out; - status = nfs4_check_cl_exchange_flags(resp->flags); + status = nfs4_check_cl_exchange_flags(resp->flags, + clp->cl_mvops->minor_version); if (status != 0) goto out; diff --git a/fs/nfs/nfs4trace.h b/fs/nfs/nfs4trace.h index 9398c0b6e0a3..2295a934a154 100644 --- a/fs/nfs/nfs4trace.h +++ b/fs/nfs/nfs4trace.h @@ -1291,6 +1291,7 @@ DEFINE_NFS4_INODE_STATEID_EVENT(nfs4_setattr); DEFINE_NFS4_INODE_STATEID_EVENT(nfs4_delegreturn); DEFINE_NFS4_INODE_STATEID_EVENT(nfs4_open_stateid_update); DEFINE_NFS4_INODE_STATEID_EVENT(nfs4_open_stateid_update_wait); +DEFINE_NFS4_INODE_STATEID_EVENT(nfs4_close_stateid_update_wait); DECLARE_EVENT_CLASS(nfs4_getattr_event, TP_PROTO( diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c index c83ddac22f38..754c763374dd 100644 --- a/fs/nfsd/nfsproc.c +++ b/fs/nfsd/nfsproc.c @@ -118,6 +118,13 @@ nfsd_proc_setattr(struct svc_rqst *rqstp) return nfsd_return_attrs(nfserr, resp); } +/* Obsolete, replaced by MNTPROC_MNT. */ +static __be32 +nfsd_proc_root(struct svc_rqst *rqstp) +{ + return nfs_ok; +} + /* * Look up a path name component * Note: the dentry in the resp->fh may be negative if the file @@ -203,6 +210,13 @@ nfsd_proc_read(struct svc_rqst *rqstp) return fh_getattr(&resp->fh, &resp->stat); } +/* Reserved */ +static __be32 +nfsd_proc_writecache(struct svc_rqst *rqstp) +{ + return nfs_ok; +} + /* * Write data to a file * N.B. After this call resp->fh needs an fh_put @@ -617,6 +631,7 @@ static const struct svc_procedure nfsd_procedures2[18] = { .pc_xdrressize = ST+AT, }, [NFSPROC_ROOT] = { + .pc_func = nfsd_proc_root, .pc_decode = nfssvc_decode_void, .pc_encode = nfssvc_encode_void, .pc_argsize = sizeof(struct nfsd_void), @@ -654,6 +669,7 @@ static const struct svc_procedure nfsd_procedures2[18] = { .pc_xdrressize = ST+AT+1+NFSSVC_MAXBLKSIZE_V2/4, }, [NFSPROC_WRITECACHE] = { + .pc_func = nfsd_proc_writecache, .pc_decode = nfssvc_decode_void, .pc_encode = nfssvc_encode_void, .pc_argsize = sizeof(struct nfsd_void), diff --git a/fs/ubifs/debug.c b/fs/ubifs/debug.c index e4b52783819d..992b74f9c941 100644 --- a/fs/ubifs/debug.c +++ b/fs/ubifs/debug.c @@ -1123,6 +1123,7 @@ int dbg_check_dir(struct ubifs_info *c, const struct inode *dir) err = PTR_ERR(dent); if (err == -ENOENT) break; + kfree(pdent); return err; } diff --git a/fs/ubifs/journal.c b/fs/ubifs/journal.c index 5f2ac5ef0891..f78c3e3ef931 100644 --- a/fs/ubifs/journal.c +++ b/fs/ubifs/journal.c @@ -894,6 +894,7 @@ int ubifs_jnl_write_inode(struct ubifs_info *c, const struct inode *inode) if (err == -ENOENT) break; + kfree(pxent); goto out_release; } @@ -906,6 +907,7 @@ int ubifs_jnl_write_inode(struct ubifs_info *c, const struct inode *inode) ubifs_err(c, "dead directory entry '%s', error %d", xent->name, err); ubifs_ro_mode(c, err); + kfree(pxent); kfree(xent); goto out_release; } @@ -936,8 +938,6 @@ int ubifs_jnl_write_inode(struct ubifs_info *c, const struct inode *inode) inode->i_ino); release_head(c, BASEHD); - ubifs_add_auth_dirt(c, lnum); - if (last_reference) { err = ubifs_tnc_remove_ino(c, inode->i_ino); if (err) @@ -947,6 +947,8 @@ int ubifs_jnl_write_inode(struct ubifs_info *c, const struct inode *inode) } else { union ubifs_key key; + ubifs_add_auth_dirt(c, lnum); + ino_key_init(c, &key, inode->i_ino); err = ubifs_tnc_add(c, &key, lnum, offs, ilen, hash); } diff --git a/fs/ubifs/orphan.c b/fs/ubifs/orphan.c index 283f9eb48410..b0117878b3a0 100644 --- a/fs/ubifs/orphan.c +++ b/fs/ubifs/orphan.c @@ -173,6 +173,7 @@ int ubifs_add_orphan(struct ubifs_info *c, ino_t inum) err = PTR_ERR(xent); if (err == -ENOENT) break; + kfree(pxent); return err; } @@ -182,6 +183,7 @@ int ubifs_add_orphan(struct ubifs_info *c, ino_t inum) xattr_orphan = orphan_add(c, xattr_inum, orphan); if (IS_ERR(xattr_orphan)) { + kfree(pxent); kfree(xent); return PTR_ERR(xattr_orphan); } diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c index 7fc2f3f07c16..e49bd69dfc1c 100644 --- a/fs/ubifs/super.c +++ b/fs/ubifs/super.c @@ -1092,14 +1092,20 @@ static int ubifs_parse_options(struct ubifs_info *c, char *options, break; } case Opt_auth_key: - c->auth_key_name = kstrdup(args[0].from, GFP_KERNEL); - if (!c->auth_key_name) - return -ENOMEM; + if (!is_remount) { + c->auth_key_name = kstrdup(args[0].from, + GFP_KERNEL); + if (!c->auth_key_name) + return -ENOMEM; + } break; case Opt_auth_hash_name: - c->auth_hash_name = kstrdup(args[0].from, GFP_KERNEL); - if (!c->auth_hash_name) - return -ENOMEM; + if (!is_remount) { + c->auth_hash_name = kstrdup(args[0].from, + GFP_KERNEL); + if (!c->auth_hash_name) + return -ENOMEM; + } break; case Opt_ignore: break; @@ -1123,6 +1129,18 @@ static int ubifs_parse_options(struct ubifs_info *c, char *options, return 0; } +/* + * ubifs_release_options - release mount parameters which have been dumped. + * @c: UBIFS file-system description object + */ +static void ubifs_release_options(struct ubifs_info *c) +{ + kfree(c->auth_key_name); + c->auth_key_name = NULL; + kfree(c->auth_hash_name); + c->auth_hash_name = NULL; +} + /** * destroy_journal - destroy journal data structures. * @c: UBIFS file-system description object @@ -1295,7 +1313,7 @@ static int mount_ubifs(struct ubifs_info *c) err = ubifs_read_superblock(c); if (err) - goto out_free; + goto out_auth; c->probing = 0; @@ -1307,18 +1325,18 @@ static int mount_ubifs(struct ubifs_info *c) ubifs_err(c, "'compressor \"%s\" is not compiled in", ubifs_compr_name(c, c->default_compr)); err = -ENOTSUPP; - goto out_free; + goto out_auth; } err = init_constants_sb(c); if (err) - goto out_free; + goto out_auth; sz = ALIGN(c->max_idx_node_sz, c->min_io_size) * 2; c->cbuf = kmalloc(sz, GFP_NOFS); if (!c->cbuf) { err = -ENOMEM; - goto out_free; + goto out_auth; } err = alloc_wbufs(c); @@ -1593,6 +1611,8 @@ static int mount_ubifs(struct ubifs_info *c) free_wbufs(c); out_cbuf: kfree(c->cbuf); +out_auth: + ubifs_exit_authentication(c); out_free: kfree(c->write_reserve_buf); kfree(c->bu.buf); @@ -1632,8 +1652,7 @@ static void ubifs_umount(struct ubifs_info *c) ubifs_lpt_free(c, 0); ubifs_exit_authentication(c); - kfree(c->auth_key_name); - kfree(c->auth_hash_name); + ubifs_release_options(c); kfree(c->cbuf); kfree(c->rcvrd_mst_node); kfree(c->mst_node); @@ -2201,6 +2220,7 @@ static int ubifs_fill_super(struct super_block *sb, void *data, int silent) out_unlock: mutex_unlock(&c->umount_mutex); out_close: + ubifs_release_options(c); ubi_close_volume(c->ubi); out: return err; diff --git a/fs/ubifs/tnc.c b/fs/ubifs/tnc.c index e8e7b0e9532e..33742ee3945b 100644 --- a/fs/ubifs/tnc.c +++ b/fs/ubifs/tnc.c @@ -2885,6 +2885,7 @@ int ubifs_tnc_remove_ino(struct ubifs_info *c, ino_t inum) err = PTR_ERR(xent); if (err == -ENOENT) break; + kfree(pxent); return err; } @@ -2898,6 +2899,7 @@ int ubifs_tnc_remove_ino(struct ubifs_info *c, ino_t inum) fname_len(&nm) = le16_to_cpu(xent->nlen); err = ubifs_tnc_remove_nm(c, &key1, &nm); if (err) { + kfree(pxent); kfree(xent); return err; } @@ -2906,6 +2908,7 @@ int ubifs_tnc_remove_ino(struct ubifs_info *c, ino_t inum) highest_ino_key(c, &key2, xattr_inum); err = ubifs_tnc_remove_range(c, &key1, &key2); if (err) { + kfree(pxent); kfree(xent); return err; } diff --git a/fs/ubifs/xattr.c b/fs/ubifs/xattr.c index 9aefbb60074f..a0b9b349efe6 100644 --- a/fs/ubifs/xattr.c +++ b/fs/ubifs/xattr.c @@ -522,6 +522,7 @@ int ubifs_purge_xattrs(struct inode *host) xent->name, err); ubifs_ro_mode(c, err); kfree(pxent); + kfree(xent); return err; } @@ -531,6 +532,7 @@ int ubifs_purge_xattrs(struct inode *host) err = remove_xattr(c, host, xino, &nm); if (err) { kfree(pxent); + kfree(xent); iput(xino); ubifs_err(c, "cannot remove xattr, error %d", err); return err; diff --git a/fs/udf/super.c b/fs/udf/super.c index a0cd766b41cd..4aba4878ed96 100644 --- a/fs/udf/super.c +++ b/fs/udf/super.c @@ -1703,7 +1703,8 @@ static noinline int udf_process_sequence( "Pointers (max %u supported)\n", UDF_MAX_TD_NESTING); brelse(bh); - return -EIO; + ret = -EIO; + goto out; } vdp = (struct volDescPtr *)bh->b_data; @@ -1723,7 +1724,8 @@ static noinline int udf_process_sequence( curr = get_volume_descriptor_record(ident, bh, &data); if (IS_ERR(curr)) { brelse(bh); - return PTR_ERR(curr); + ret = PTR_ERR(curr); + goto out; } /* Descriptor we don't care about? */ if (!curr) @@ -1745,28 +1747,31 @@ static noinline int udf_process_sequence( */ if (!data.vds[VDS_POS_PRIMARY_VOL_DESC].block) { udf_err(sb, "Primary Volume Descriptor not found!\n"); - return -EAGAIN; + ret = -EAGAIN; + goto out; } ret = udf_load_pvoldesc(sb, data.vds[VDS_POS_PRIMARY_VOL_DESC].block); if (ret < 0) - return ret; + goto out; if (data.vds[VDS_POS_LOGICAL_VOL_DESC].block) { ret = udf_load_logicalvol(sb, data.vds[VDS_POS_LOGICAL_VOL_DESC].block, fileset); if (ret < 0) - return ret; + goto out; } /* Now handle prevailing Partition Descriptors */ for (i = 0; i < data.num_part_descs; i++) { ret = udf_load_partdesc(sb, data.part_descs_loc[i].rec.block); if (ret < 0) - return ret; + goto out; } - - return 0; + ret = 0; +out: + kfree(data.part_descs_loc); + return ret; } /* diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index f8db3fe616df..c114d24be619 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -4985,20 +4985,25 @@ xfs_bmap_del_extent_real( flags = XFS_ILOG_CORE; if (whichfork == XFS_DATA_FORK && XFS_IS_REALTIME_INODE(ip)) { - xfs_fsblock_t bno; xfs_filblks_t len; xfs_extlen_t mod; - bno = div_u64_rem(del->br_startblock, mp->m_sb.sb_rextsize, - &mod); - ASSERT(mod == 0); len = div_u64_rem(del->br_blockcount, mp->m_sb.sb_rextsize, &mod); ASSERT(mod == 0); - error = xfs_rtfree_extent(tp, bno, (xfs_extlen_t)len); - if (error) - goto done; + if (!(bflags & XFS_BMAPI_REMAP)) { + xfs_fsblock_t bno; + + bno = div_u64_rem(del->br_startblock, + mp->m_sb.sb_rextsize, &mod); + ASSERT(mod == 0); + + error = xfs_rtfree_extent(tp, bno, (xfs_extlen_t)len); + if (error) + goto done; + } + do_fx = 0; nblks = len * mp->m_sb.sb_rextsize; qfield = XFS_TRANS_DQ_RTBCOUNT; diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c index b58366937082..6d5ddc4e5135 100644 --- a/fs/xfs/xfs_rtalloc.c +++ b/fs/xfs/xfs_rtalloc.c @@ -1021,10 +1021,13 @@ xfs_growfs_rt( xfs_ilock(mp->m_rbmip, XFS_ILOCK_EXCL); xfs_trans_ijoin(tp, mp->m_rbmip, XFS_ILOCK_EXCL); /* - * Update the bitmap inode's size. + * Update the bitmap inode's size ondisk and incore. We need + * to update the incore size so that inode inactivation won't + * punch what it thinks are "posteof" blocks. */ mp->m_rbmip->i_d.di_size = nsbp->sb_rbmblocks * nsbp->sb_blocksize; + i_size_write(VFS_I(mp->m_rbmip), mp->m_rbmip->i_d.di_size); xfs_trans_log_inode(tp, mp->m_rbmip, XFS_ILOG_CORE); /* * Get the summary inode into the transaction. @@ -1032,9 +1035,12 @@ xfs_growfs_rt( xfs_ilock(mp->m_rsumip, XFS_ILOCK_EXCL); xfs_trans_ijoin(tp, mp->m_rsumip, XFS_ILOCK_EXCL); /* - * Update the summary inode's size. + * Update the summary inode's size. We need to update the + * incore size so that inode inactivation won't punch what it + * thinks are "posteof" blocks. */ mp->m_rsumip->i_d.di_size = nmp->m_rsumsize; + i_size_write(VFS_I(mp->m_rsumip), mp->m_rsumip->i_d.di_size); xfs_trans_log_inode(tp, mp->m_rsumip, XFS_ILOG_CORE); /* * Copy summary data from old to new sizes. diff --git a/include/linux/hil_mlc.h b/include/linux/hil_mlc.h index 774f7d3b8f6a..369221fd5518 100644 --- a/include/linux/hil_mlc.h +++ b/include/linux/hil_mlc.h @@ -103,7 +103,7 @@ struct hilse_node { /* Methods for back-end drivers, e.g. hp_sdc_mlc */ typedef int (hil_mlc_cts) (hil_mlc *mlc); -typedef void (hil_mlc_out) (hil_mlc *mlc); +typedef int (hil_mlc_out) (hil_mlc *mlc); typedef int (hil_mlc_in) (hil_mlc *mlc, suseconds_t timeout); struct hil_mlc_devinfo { diff --git a/include/linux/usb/pd.h b/include/linux/usb/pd.h index 145c38e351c2..6655ce32feff 100644 --- a/include/linux/usb/pd.h +++ b/include/linux/usb/pd.h @@ -442,6 +442,7 @@ static inline unsigned int rdo_max_power(u32 rdo) #define PD_T_ERROR_RECOVERY 100 /* minimum 25 is insufficient */ #define PD_T_SRCSWAPSTDBY 625 /* Maximum of 650ms */ #define PD_T_NEWSRC 250 /* Maximum of 275ms */ +#define PD_T_SWAP_SRC_START 20 /* Minimum of 20ms */ #define PD_T_DRP_TRY 100 /* 75 - 150 ms */ #define PD_T_DRP_TRYWAIT 600 /* 400 - 800 ms */ diff --git a/include/uapi/linux/btrfs_tree.h b/include/uapi/linux/btrfs_tree.h index b65c7ee75bc7..035e59eef05b 100644 --- a/include/uapi/linux/btrfs_tree.h +++ b/include/uapi/linux/btrfs_tree.h @@ -4,6 +4,11 @@ #include <linux/btrfs.h> #include <linux/types.h> +#ifdef __KERNEL__ +#include <linux/stddef.h> +#else +#include <stddef.h> +#endif /* * This header contains the structure definitions and constants used @@ -650,6 +655,15 @@ struct btrfs_root_item { __le64 reserved[8]; /* for future */ } __attribute__ ((__packed__)); +/* + * Btrfs root item used to be smaller than current size. The old format ends + * at where member generation_v2 is. + */ +static inline __u32 btrfs_legacy_root_item_size(void) +{ + return offsetof(struct btrfs_root_item, generation_v2); +} + /* * this is used for both forward and backward root refs */ diff --git a/include/uapi/linux/nfs4.h b/include/uapi/linux/nfs4.h index 8572930cf5b0..54a78529c8b3 100644 --- a/include/uapi/linux/nfs4.h +++ b/include/uapi/linux/nfs4.h @@ -136,6 +136,8 @@ #define EXCHGID4_FLAG_UPD_CONFIRMED_REC_A 0x40000000 #define EXCHGID4_FLAG_CONFIRMED_R 0x80000000 + +#define EXCHGID4_FLAG_SUPP_FENCE_OPS 0x00000004 /* * Since the validity of these bits depends on whether * they're set in the argument or response, have separate @@ -143,6 +145,7 @@ */ #define EXCHGID4_FLAG_MASK_A 0x40070103 #define EXCHGID4_FLAG_MASK_R 0x80070103 +#define EXCHGID4_2_FLAG_MASK_R 0x80070107 #define SEQ4_STATUS_CB_PATH_DOWN 0x00000001 #define SEQ4_STATUS_CB_GSS_CONTEXTS_EXPIRING 0x00000002 diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index 530638dffd93..3210b3c82a4a 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -371,9 +371,9 @@ enum v4l2_hsv_encoding { enum v4l2_quantization { /* - * The default for R'G'B' quantization is always full range, except - * for the BT2020 colorspace. For Y'CbCr the quantization is always - * limited range, except for COLORSPACE_JPEG: this is full range. + * The default for R'G'B' quantization is always full range. + * For Y'CbCr the quantization is always limited range, except + * for COLORSPACE_JPEG: this is full range. */ V4L2_QUANTIZATION_DEFAULT = 0, V4L2_QUANTIZATION_FULL_RANGE = 1, @@ -382,14 +382,13 @@ enum v4l2_quantization { /* * Determine how QUANTIZATION_DEFAULT should map to a proper quantization. - * This depends on whether the image is RGB or not, the colorspace and the - * Y'CbCr encoding. + * This depends on whether the image is RGB or not, the colorspace. + * The Y'CbCr encoding is not used anymore, but is still there for backwards + * compatibility. */ #define V4L2_MAP_QUANTIZATION_DEFAULT(is_rgb_or_hsv, colsp, ycbcr_enc) \ - (((is_rgb_or_hsv) && (colsp) == V4L2_COLORSPACE_BT2020) ? \ - V4L2_QUANTIZATION_LIM_RANGE : \ - (((is_rgb_or_hsv) || (colsp) == V4L2_COLORSPACE_JPEG) ? \ - V4L2_QUANTIZATION_FULL_RANGE : V4L2_QUANTIZATION_LIM_RANGE)) + (((is_rgb_or_hsv) || (colsp) == V4L2_COLORSPACE_JPEG) ? \ + V4L2_QUANTIZATION_FULL_RANGE : V4L2_QUANTIZATION_LIM_RANGE) /* * Deprecated names for opRGB colorspace (IEC 61966-2-5) diff --git a/include/xen/events.h b/include/xen/events.h index c0e6a0598397..31952308a6d5 100644 --- a/include/xen/events.h +++ b/include/xen/events.h @@ -14,11 +14,16 @@ unsigned xen_evtchn_nr_channels(void); -int bind_evtchn_to_irq(unsigned int evtchn); -int bind_evtchn_to_irqhandler(unsigned int evtchn, +int bind_evtchn_to_irq(evtchn_port_t evtchn); +int bind_evtchn_to_irq_lateeoi(evtchn_port_t evtchn); +int bind_evtchn_to_irqhandler(evtchn_port_t evtchn, irq_handler_t handler, unsigned long irqflags, const char *devname, void *dev_id); +int bind_evtchn_to_irqhandler_lateeoi(evtchn_port_t evtchn, + irq_handler_t handler, + unsigned long irqflags, const char *devname, + void *dev_id); int bind_virq_to_irq(unsigned int virq, unsigned int cpu, bool percpu); int bind_virq_to_irqhandler(unsigned int virq, unsigned int cpu, irq_handler_t handler, @@ -31,13 +36,21 @@ int bind_ipi_to_irqhandler(enum ipi_vector ipi, const char *devname, void *dev_id); int bind_interdomain_evtchn_to_irq(unsigned int remote_domain, - unsigned int remote_port); + evtchn_port_t remote_port); +int bind_interdomain_evtchn_to_irq_lateeoi(unsigned int remote_domain, + evtchn_port_t remote_port); int bind_interdomain_evtchn_to_irqhandler(unsigned int remote_domain, - unsigned int remote_port, + evtchn_port_t remote_port, irq_handler_t handler, unsigned long irqflags, const char *devname, void *dev_id); +int bind_interdomain_evtchn_to_irqhandler_lateeoi(unsigned int remote_domain, + evtchn_port_t remote_port, + irq_handler_t handler, + unsigned long irqflags, + const char *devname, + void *dev_id); /* * Common unbind function for all event sources. Takes IRQ to unbind from. @@ -46,6 +59,14 @@ int bind_interdomain_evtchn_to_irqhandler(unsigned int remote_domain, */ void unbind_from_irqhandler(unsigned int irq, void *dev_id); +/* + * Send late EOI for an IRQ bound to an event channel via one of the *_lateeoi + * functions above. + */ +void xen_irq_lateeoi(unsigned int irq, unsigned int eoi_flags); +/* Signal an event was spurious, i.e. there was no action resulting from it. */ +#define XEN_EOI_FLAG_SPURIOUS 0x00000001 + #define XEN_IRQ_PRIORITY_MAX EVTCHN_FIFO_PRIORITY_MAX #define XEN_IRQ_PRIORITY_DEFAULT EVTCHN_FIFO_PRIORITY_DEFAULT #define XEN_IRQ_PRIORITY_MIN EVTCHN_FIFO_PRIORITY_MIN diff --git a/init/Kconfig b/init/Kconfig index 6db3e310a5e4..96fc45d1b686 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -594,7 +594,8 @@ config IKHEADERS config LOG_BUF_SHIFT int "Kernel log buffer size (16 => 64KB, 17 => 128KB)" - range 12 25 + range 12 25 if !H8300 + range 12 19 if H8300 default 17 depends on PRINTK help diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 507474f79195..a67bfa803d98 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -4427,6 +4427,10 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, dst, reg_type_str[ptr_reg->type]); return -EACCES; case CONST_PTR_TO_MAP: + /* smin_val represents the known value */ + if (known && smin_val == 0 && opcode == BPF_ADD) + break; + /* fall-through */ case PTR_TO_PACKET_END: case PTR_TO_SOCKET: case PTR_TO_SOCKET_OR_NULL: diff --git a/kernel/debug/debug_core.c b/kernel/debug/debug_core.c index 2222f3225e53..097ab02989f9 100644 --- a/kernel/debug/debug_core.c +++ b/kernel/debug/debug_core.c @@ -96,14 +96,6 @@ int dbg_switch_cpu; /* Use kdb or gdbserver mode */ int dbg_kdb_mode = 1; -static int __init opt_kgdb_con(char *str) -{ - kgdb_use_con = 1; - return 0; -} - -early_param("kgdbcon", opt_kgdb_con); - module_param(kgdb_use_con, int, 0644); module_param(kgdbreboot, int, 0644); @@ -876,6 +868,20 @@ static struct console kgdbcons = { .index = -1, }; +static int __init opt_kgdb_con(char *str) +{ + kgdb_use_con = 1; + + if (kgdb_io_module_registered && !kgdb_con_registered) { + register_console(&kgdbcons); + kgdb_con_registered = 1; + } + + return 0; +} + +early_param("kgdbcon", opt_kgdb_con); + #ifdef CONFIG_MAGIC_SYSRQ static void sysrq_handle_dbg(int key) { diff --git a/kernel/futex.c b/kernel/futex.c index 5660c02b01b0..17fba7a986e0 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -1594,8 +1594,10 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_pi_state *pi_ */ newval = FUTEX_WAITERS | task_pid_vnr(new_owner); - if (unlikely(should_fail_futex(true))) + if (unlikely(should_fail_futex(true))) { ret = -EFAULT; + goto out_unlock; + } ret = cmpxchg_futex_value_locked(&curval, uaddr, uval, newval); if (!ret && (curval != uval)) { diff --git a/kernel/seccomp.c b/kernel/seccomp.c index e0fd97235653..0d991e9626f6 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -1219,13 +1219,7 @@ static const struct file_operations seccomp_notify_ops = { static struct file *init_listener(struct seccomp_filter *filter) { - struct file *ret = ERR_PTR(-EBUSY); - struct seccomp_filter *cur; - - for (cur = current->seccomp.filter; cur; cur = cur->prev) { - if (cur->notif) - goto out; - } + struct file *ret; ret = ERR_PTR(-ENOMEM); filter->notif = kzalloc(sizeof(*(filter->notif)), GFP_KERNEL); @@ -1252,6 +1246,31 @@ static struct file *init_listener(struct seccomp_filter *filter) return ret; } +/* + * Does @new_child have a listener while an ancestor also has a listener? + * If so, we'll want to reject this filter. + * This only has to be tested for the current process, even in the TSYNC case, + * because TSYNC installs @child with the same parent on all threads. + * Note that @new_child is not hooked up to its parent at this point yet, so + * we use current->seccomp.filter. + */ +static bool has_duplicate_listener(struct seccomp_filter *new_child) +{ + struct seccomp_filter *cur; + + /* must be protected against concurrent TSYNC */ + lockdep_assert_held(¤t->sighand->siglock); + + if (!new_child->notif) + return false; + for (cur = current->seccomp.filter; cur; cur = cur->prev) { + if (cur->notif) + return true; + } + + return false; +} + /** * seccomp_set_mode_filter: internal function for setting seccomp filter * @flags: flags to change filter behavior @@ -1321,6 +1340,11 @@ static long seccomp_set_mode_filter(unsigned int flags, if (!seccomp_may_assign_mode(seccomp_mode)) goto out; + if (has_duplicate_listener(prepared)) { + ret = -EBUSY; + goto out; + } + ret = seccomp_attach_filter(flags, prepared); if (ret) goto out; diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 9a2581fe7ed5..67cdb401c6ce 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -1717,18 +1717,18 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size, { struct ring_buffer_per_cpu *cpu_buffer; unsigned long nr_pages; - int cpu, err = 0; + int cpu, err; /* * Always succeed at resizing a non-existent buffer: */ if (!buffer) - return size; + return 0; /* Make sure the requested buffer exists */ if (cpu_id != RING_BUFFER_ALL_CPUS && !cpumask_test_cpu(cpu_id, buffer->cpumask)) - return size; + return 0; nr_pages = DIV_ROUND_UP(size, BUF_PAGE_SIZE); @@ -1868,7 +1868,7 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size, } mutex_unlock(&buffer->mutex); - return size; + return 0; out_err: for_each_buffer_cpu(buffer, cpu) { diff --git a/lib/scatterlist.c b/lib/scatterlist.c index 5813072bc589..29346184fcf2 100644 --- a/lib/scatterlist.c +++ b/lib/scatterlist.c @@ -514,7 +514,7 @@ struct scatterlist *sgl_alloc_order(unsigned long long length, elem_len = min_t(u64, length, PAGE_SIZE << order); page = alloc_pages(gfp, order); if (!page) { - sgl_free(sgl); + sgl_free_order(sgl, order); return NULL; } diff --git a/net/9p/trans_fd.c b/net/9p/trans_fd.c index 12ecacf0c55f..60eb9a2b209b 100644 --- a/net/9p/trans_fd.c +++ b/net/9p/trans_fd.c @@ -1023,7 +1023,7 @@ p9_fd_create_unix(struct p9_client *client, const char *addr, char *args) csocket = NULL; - if (addr == NULL) + if (!addr || !strlen(addr)) return -EINVAL; if (strlen(addr) >= UNIX_PATH_MAX) { diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index 3d2e9f944e0f..49726c378aab 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -3007,6 +3007,11 @@ static void con_fault(struct ceph_connection *con) ceph_msg_put(con->in_msg); con->in_msg = NULL; } + if (con->out_msg) { + BUG_ON(con->out_msg->con != con); + ceph_msg_put(con->out_msg); + con->out_msg = NULL; + } /* Requeue anything that hasn't been acked */ list_splice_init(&con->out_sent, &con->out_queue); diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index 41df4c507193..a6fee86f400e 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -1503,10 +1503,13 @@ xprt_transmit(struct rpc_task *task) { struct rpc_rqst *next, *req = task->tk_rqstp; struct rpc_xprt *xprt = req->rq_xprt; - int status; + int counter, status; spin_lock(&xprt->queue_lock); + counter = 0; while (!list_empty(&xprt->xmit_queue)) { + if (++counter == 20) + break; next = list_first_entry(&xprt->xmit_queue, struct rpc_rqst, rq_xmit); xprt_pin_rqst(next); @@ -1514,7 +1517,6 @@ xprt_transmit(struct rpc_task *task) status = xprt_request_transmit(next, task); if (status == -EBADMSG && next != req) status = 0; - cond_resched(); spin_lock(&xprt->queue_lock); xprt_unpin_rqst(next); if (status == 0) { diff --git a/samples/bpf/xdpsock_user.c b/samples/bpf/xdpsock_user.c index df011ac33402..79d1005ff2ee 100644 --- a/samples/bpf/xdpsock_user.c +++ b/samples/bpf/xdpsock_user.c @@ -677,6 +677,7 @@ static void l2fwd(struct xsk_socket_info *xsk, struct pollfd *fds) while (ret != rcvd) { if (ret < 0) exit_with_error(-ret); + complete_tx_l2fwd(xsk, fds); if (xsk_ring_prod__needs_wakeup(&xsk->tx)) kick_tx(xsk); ret = xsk_ring_prod__reserve(&xsk->tx, rcvd, &idx_tx); diff --git a/tools/perf/util/print_binary.c b/tools/perf/util/print_binary.c index 599a1543871d..13fdc51c61d9 100644 --- a/tools/perf/util/print_binary.c +++ b/tools/perf/util/print_binary.c @@ -50,7 +50,7 @@ int is_printable_array(char *p, unsigned int len) len--; - for (i = 0; i < len; i++) { + for (i = 0; i < len && p[i]; i++) { if (!isprint(p[i]) && !isspace(p[i])) return 0; } diff --git a/tools/testing/selftests/bpf/progs/test_sysctl_prog.c b/tools/testing/selftests/bpf/progs/test_sysctl_prog.c index 5cbbff416998..4396faf33394 100644 --- a/tools/testing/selftests/bpf/progs/test_sysctl_prog.c +++ b/tools/testing/selftests/bpf/progs/test_sysctl_prog.c @@ -19,11 +19,11 @@ #define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0])) #endif +const char tcp_mem_name[] = "net/ipv4/tcp_mem"; static __always_inline int is_tcp_mem(struct bpf_sysctl *ctx) { - char tcp_mem_name[] = "net/ipv4/tcp_mem"; unsigned char i; - char name[64]; + char name[sizeof(tcp_mem_name)]; int ret; memset(name, 0, sizeof(name)); diff --git a/tools/testing/selftests/x86/fsgsbase.c b/tools/testing/selftests/x86/fsgsbase.c index 15a329da59fa..757bdb218a66 100644 --- a/tools/testing/selftests/x86/fsgsbase.c +++ b/tools/testing/selftests/x86/fsgsbase.c @@ -442,6 +442,68 @@ static void test_unexpected_base(void) #define USER_REGS_OFFSET(r) offsetof(struct user_regs_struct, r) +static void test_ptrace_write_gs_read_base(void) +{ + int status; + pid_t child = fork(); + + if (child < 0) + err(1, "fork"); + + if (child == 0) { + printf("[RUN]\tPTRACE_POKE GS, read GSBASE back\n"); + + printf("[RUN]\tARCH_SET_GS to 1\n"); + if (syscall(SYS_arch_prctl, ARCH_SET_GS, 1) != 0) + err(1, "ARCH_SET_GS"); + + if (ptrace(PTRACE_TRACEME, 0, NULL, NULL) != 0) + err(1, "PTRACE_TRACEME"); + + raise(SIGTRAP); + _exit(0); + } + + wait(&status); + + if (WSTOPSIG(status) == SIGTRAP) { + unsigned long base; + unsigned long gs_offset = USER_REGS_OFFSET(gs); + unsigned long base_offset = USER_REGS_OFFSET(gs_base); + + /* Read the initial base. It should be 1. */ + base = ptrace(PTRACE_PEEKUSER, child, base_offset, NULL); + if (base == 1) { + printf("[OK]\tGSBASE started at 1\n"); + } else { + nerrs++; + printf("[FAIL]\tGSBASE started at 0x%lx\n", base); + } + + printf("[RUN]\tSet GS = 0x7, read GSBASE\n"); + + /* Poke an LDT selector into GS. */ + if (ptrace(PTRACE_POKEUSER, child, gs_offset, 0x7) != 0) + err(1, "PTRACE_POKEUSER"); + + /* And read the base. */ + base = ptrace(PTRACE_PEEKUSER, child, base_offset, NULL); + + if (base == 0 || base == 1) { + printf("[OK]\tGSBASE reads as 0x%lx with invalid GS\n", base); + } else { + nerrs++; + printf("[FAIL]\tGSBASE=0x%lx (should be 0 or 1)\n", base); + } + } + + ptrace(PTRACE_CONT, child, NULL, NULL); + + wait(&status); + if (!WIFEXITED(status)) + printf("[WARN]\tChild didn't exit cleanly.\n"); +} + static void test_ptrace_write_gsbase(void) { int status; @@ -499,6 +561,9 @@ static void test_ptrace_write_gsbase(void) END: ptrace(PTRACE_CONT, child, NULL, NULL); + wait(&status); + if (!WIFEXITED(status)) + printf("[WARN]\tChild didn't exit cleanly.\n"); } int main() @@ -508,6 +573,9 @@ int main() shared_scratch = mmap(NULL, 4096, PROT_READ | PROT_WRITE, MAP_ANONYMOUS | MAP_SHARED, -1, 0); + /* Do these tests before we have an LDT. */ + test_ptrace_write_gs_read_base(); + /* Probe FSGSBASE */ sethandler(SIGILL, sigill, 0); if (sigsetjmp(jmpbuf, 1) == 0) {