diff options
503 files changed, 5434 insertions, 2529 deletions
diff --git a/Documentation/ABI/testing/sysfs-bus-nvdimm b/Documentation/ABI/testing/sysfs-bus-nvdimm index 64eb8f4c6a41..46dafd8482b9 100644 --- a/Documentation/ABI/testing/sysfs-bus-nvdimm +++ b/Documentation/ABI/testing/sysfs-bus-nvdimm @@ -48,7 +48,8 @@ What: /sys/bus/nd/devices/nmemX/cxl/id Date: November 2022 KernelVersion: 6.2 Contact: Dave Jiang <dave.jiang@intel.com> -Description: (RO) Show the id (serial) of the device. This is CXL specific. +Description: (RO) Show the id (serial) of the device, formatted as an + unsigned 64-bit decimal value. This is CXL specific. What: /sys/bus/nd/devices/nmemX/cxl/provider Date: November 2022 diff --git a/Documentation/admin-guide/blockdev/zoned_loop.rst b/Documentation/admin-guide/blockdev/zoned_loop.rst index 64dcfde7450a..ae0eff616990 100644 --- a/Documentation/admin-guide/blockdev/zoned_loop.rst +++ b/Documentation/admin-guide/blockdev/zoned_loop.rst @@ -30,11 +30,10 @@ indicates the position of the write pointer of the zone. When resetting a sequential zone, its backing file size is truncated to zero. Conversely, for a zone finish operation, the backing file is truncated to the -zone size. With this, the maximum capacity of a zloop zoned block device created -can be larger configured to be larger than the storage space available on the -backing file system. Of course, for such configuration, writing more data than -the storage space available on the backing file system will result in write -errors. +zone capacity. With this, a zloop zoned block device can be configured with a +larger capacity than the storage space available on the backing file system. Of +course, for such configuration, writing more data than the storage space +available on the backing file system will result in write errors. The zoned loop block device driver implements a complete zone transition state machine. That is, zones can be empty, implicitly opened, explicitly opened, @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 6 PATCHLEVEL = 18 -SUBLEVEL = 49 +SUBLEVEL = 50 EXTRAVERSION = NAME = Baby Opossum Posse diff --git a/arch/alpha/include/uapi/asm/fpu.h b/arch/alpha/include/uapi/asm/fpu.h index cea9eafa056f..d28dc36786e2 100644 --- a/arch/alpha/include/uapi/asm/fpu.h +++ b/arch/alpha/include/uapi/asm/fpu.h @@ -101,7 +101,12 @@ ieee_swcr_to_fpcr(unsigned long sw) | IEEE_TRAP_ENABLE_OVF)) << 48; fp |= (~sw & (IEEE_TRAP_ENABLE_UNF | IEEE_TRAP_ENABLE_INE)) << 57; fp |= (sw & IEEE_MAP_UMZ ? FPCR_UNDZ | FPCR_UNFD : 0); - fp |= (~sw & IEEE_TRAP_ENABLE_DNO) << 41; + /* + * Disable denormal operand traps only when denormal inputs are to be + * flushed to zero. Otherwise they must keep trapping, so that /S + * instructions reach the kernel emulation handler. + */ + fp |= (sw & IEEE_MAP_DMZ ? FPCR_DNOD : 0); return fp; } @@ -116,7 +121,6 @@ ieee_fpcr_to_swcr(unsigned long fp) | IEEE_TRAP_ENABLE_OVF); sw |= (~fp >> 57) & (IEEE_TRAP_ENABLE_UNF | IEEE_TRAP_ENABLE_INE); sw |= (fp >> 47) & IEEE_MAP_UMZ; - sw |= (~fp >> 41) & IEEE_TRAP_ENABLE_DNO; return sw; } diff --git a/arch/alpha/kernel/pci-sysfs.c b/arch/alpha/kernel/pci-sysfs.c index 21833d1c867d..2e9870ee21c6 100644 --- a/arch/alpha/kernel/pci-sysfs.c +++ b/arch/alpha/kernel/pci-sysfs.c @@ -364,17 +364,17 @@ int pci_legacy_write(struct pci_bus *bus, loff_t port, u32 val, size_t size) switch(size) { case 1: - outb(port, val); + outb(val, port); return 1; case 2: if (port & 1) return -EINVAL; - outw(port, val); + outw(val, port); return 2; case 4: if (port & 3) return -EINVAL; - outl(port, val); + outl(val, port); return 4; } return -EINVAL; diff --git a/arch/alpha/kernel/sys_marvel.c b/arch/alpha/kernel/sys_marvel.c index 1f99b03effc2..a37707e05e34 100644 --- a/arch/alpha/kernel/sys_marvel.c +++ b/arch/alpha/kernel/sys_marvel.c @@ -263,6 +263,18 @@ init_io7_irqs(struct io7 *io7, */ printk(" Interrupts reported to CPU at PE %u\n", boot_cpuid); + /* Set up the lsi irqs. */ + for (i = 0; i < 128; ++i) { + irq_set_chip_and_handler(base + i, lsi_ops, handle_level_irq); + irq_set_status_flags(base + i, IRQ_LEVEL); + } + + /* Set up the msi irqs. */ + for (i = 128; i < (128 + 512); ++i) { + irq_set_chip_and_handler(base + i, msi_ops, handle_level_irq); + irq_set_status_flags(base + i, IRQ_LEVEL); + } + raw_spin_lock(&io7->irq_lock); /* set up the error irqs */ @@ -272,12 +284,6 @@ init_io7_irqs(struct io7 *io7, io7_redirect_irq(io7, &io7->csrs->STV_CTL.csr, boot_cpuid); io7_redirect_irq(io7, &io7->csrs->HEI_CTL.csr, boot_cpuid); - /* Set up the lsi irqs. */ - for (i = 0; i < 128; ++i) { - irq_set_chip_and_handler(base + i, lsi_ops, handle_level_irq); - irq_set_status_flags(i, IRQ_LEVEL); - } - /* Disable the implemented irqs in hardware. */ for (i = 0; i < 0x60; ++i) init_one_io7_lsi(io7, i, boot_cpuid); @@ -285,13 +291,6 @@ init_io7_irqs(struct io7 *io7, init_one_io7_lsi(io7, 0x74, boot_cpuid); init_one_io7_lsi(io7, 0x75, boot_cpuid); - - /* Set up the msi irqs. */ - for (i = 128; i < (128 + 512); ++i) { - irq_set_chip_and_handler(base + i, msi_ops, handle_level_irq); - irq_set_status_flags(i, IRQ_LEVEL); - } - for (i = 0; i < 16; ++i) init_one_io7_msi(io7, i, boot_cpuid); diff --git a/arch/alpha/kernel/traps.c b/arch/alpha/kernel/traps.c index 7004397937cf..7cd20e5f9ee0 100644 --- a/arch/alpha/kernel/traps.c +++ b/arch/alpha/kernel/traps.c @@ -166,12 +166,12 @@ static long dummy_emul(void) { return 0; } long (*alpha_fp_emul_imprecise)(struct pt_regs *regs, unsigned long writemask) = (void *)dummy_emul; EXPORT_SYMBOL_GPL(alpha_fp_emul_imprecise); -long (*alpha_fp_emul) (unsigned long pc) +long (*alpha_fp_emul) (unsigned long pc, unsigned long summary) = (void *)dummy_emul; EXPORT_SYMBOL_GPL(alpha_fp_emul); #else long alpha_fp_emul_imprecise(struct pt_regs *regs, unsigned long writemask); -long alpha_fp_emul (unsigned long pc); +long alpha_fp_emul (unsigned long pc, unsigned long summary); #endif asmlinkage void @@ -185,7 +185,7 @@ do_entArith(unsigned long summary, unsigned long write_mask, emulate the instruction. If the processor supports precise exceptions, we don't have to search. */ if (!amask(AMASK_PRECISE_TRAP)) - si_code = alpha_fp_emul(regs->pc - 4); + si_code = alpha_fp_emul(regs->pc - 4, summary); else si_code = alpha_fp_emul_imprecise(regs, write_mask); if (si_code == 0) diff --git a/arch/alpha/math-emu/math.c b/arch/alpha/math-emu/math.c index 68d420bfd3c0..e3f2df3729e3 100644 --- a/arch/alpha/math-emu/math.c +++ b/arch/alpha/math-emu/math.c @@ -52,13 +52,13 @@ MODULE_DESCRIPTION("FP Software completion module"); MODULE_LICENSE("GPL v2"); extern long (*alpha_fp_emul_imprecise)(struct pt_regs *, unsigned long); -extern long (*alpha_fp_emul) (unsigned long pc); +extern long (*alpha_fp_emul) (unsigned long pc, unsigned long summary); static long (*save_emul_imprecise)(struct pt_regs *, unsigned long); -static long (*save_emul) (unsigned long pc); +static long (*save_emul) (unsigned long pc, unsigned long summary); long do_alpha_fp_emul_imprecise(struct pt_regs *, unsigned long); -long do_alpha_fp_emul(unsigned long); +long do_alpha_fp_emul(unsigned long, unsigned long); static int alpha_fp_emul_init_module(void) { @@ -86,7 +86,22 @@ module_exit(alpha_fp_emul_cleanup_module); /* - * Emulate the floating point instruction at address PC. Returns -1 if the + * Exception bits of the exception summary register (EXC_SUM). Bit 0 is the + * software completion bit; bits 1 through 5 report the exceptions the + * hardware attributed to the trapping instruction, and lie at the same + * positions as the corresponding IEEE_TRAP_ENABLE_* bits. + */ +#define EXC_SUM_INV (1UL << 1) +#define EXC_SUM_DZE (1UL << 2) +#define EXC_SUM_OVF (1UL << 3) +#define EXC_SUM_UNF (1UL << 4) +#define EXC_SUM_INE (1UL << 5) +#define EXC_SUM_MASK (EXC_SUM_INV | EXC_SUM_DZE | EXC_SUM_OVF \ + | EXC_SUM_UNF | EXC_SUM_INE) + +/* + * Emulate the floating point instruction at address PC. SUMMARY is the + * exception summary register the trap was delivered with. Returns -1 if the * instruction to be emulated is illegal (such as with the opDEC trap), else * the SI_CODE for a SIGFPE signal, else 0 if everything's ok. * @@ -95,7 +110,7 @@ module_exit(alpha_fp_emul_cleanup_module); * stick the result of the operation into the appropriate register. */ long -alpha_fp_emul (unsigned long pc) +alpha_fp_emul (unsigned long pc, unsigned long summary) { FP_DECL_EX; FP_DECL_S(SA); FP_DECL_S(SB); FP_DECL_S(SR); @@ -300,12 +315,56 @@ done: swcr |= (_fex << IEEE_STATUS_TO_EXCSUM_SHIFT); current_thread_info()->ieee_state |= (_fex << IEEE_STATUS_TO_EXCSUM_SHIFT); + } - /* Update hardware control register. */ - fpcr &= (~FPCR_MASK | FPCR_DYN_MASK); - fpcr |= ieee_swcr_to_fpcr(swcr); - wrfpcr(fpcr); + /* + * EV6 records exception status bits in the FPCR before delivering the + * software completion trap, and swcr_update_status() above merged them + * into SWCR. Some can be wrong for the instruction we just emulated: + * a CVTTS of a value exactly representable as a subnormal sets FPCR_UNF + * even though the result is exact. Clear the exceptions the trap + * reported but that soft-fp did not raise. + */ + if (implver() == IMPLVER_EV6) { + unsigned long spurious = summary & EXC_SUM_MASK; + + if (spurious & (EXC_SUM_UNF | EXC_SUM_OVF)) { + /* + * EXC_SUM reports only the underflow or overflow, + * but the hardware sets INE alongside it in the FPCR. + */ + spurious |= EXC_SUM_INE; + } else if (!spurious) { + /* + * No exception reported, so this was a denormal + * operand trap, for which INE and UNF can be + * fabricated as well. + */ + spurious = EXC_SUM_INE | EXC_SUM_UNF; + } + /* + * Never clear an exception software has confirmed. Every + * instruction that genuinely raises one traps for software + * completion and is recorded in ieee_state above, so a bit + * found there -- including one just set from _fex -- belongs + * to this or an earlier instruction and must survive. + */ + spurious &= ~(current_thread_info()->ieee_state + >> IEEE_STATUS_TO_EXCSUM_SHIFT); + + swcr &= ~(spurious << IEEE_STATUS_TO_EXCSUM_SHIFT); + } + + /* + * Update hardware control register. This has to happen even when + * soft-fp raised nothing, to clear any fabricated bits. + */ + fpcr &= (~FPCR_MASK | FPCR_DYN_MASK); + fpcr |= ieee_swcr_to_fpcr(swcr); + wrfpcr(fpcr); + + if (_fex) { /* Do we generate a signal? */ _fex = _fex & swcr & IEEE_TRAP_ENABLE_MASK; si_code = 0; @@ -387,9 +446,16 @@ alpha_fp_emul_imprecise (struct pt_regs *regs, unsigned long write_mask) break; } if (!write_mask) { - /* Re-execute insns in the trap-shadow. */ + /* + * Re-execute insns in the trap-shadow. Pass no + * exception summary: it describes the trap, which + * was taken anywhere in the shadow, and so is not + * attribution for this instruction. Nothing is + * lost, since only EV6 -- which traps precisely and + * never comes this way -- needs it. + */ regs->pc = trigger_pc + 4; - si_code = alpha_fp_emul(trigger_pc); + si_code = alpha_fp_emul(trigger_pc, 0); goto egress; } trigger_pc -= 4; diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index e481254e3645..b4ef6a27e8ce 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -96,7 +96,7 @@ config ARM select HAVE_ARCH_TRACEHOOK select HAVE_ARCH_TRANSPARENT_HUGEPAGE if ARM_LPAE select HAVE_ARM_SMCCC if CPU_V7 - select HAVE_EBPF_JIT if !CPU_ENDIAN_BE32 + select HAVE_EBPF_JIT if !CPU_ENDIAN_BE32 && !CPU_32v3 select HAVE_CONTEXT_TRACKING_USER select HAVE_C_RECORDMCOUNT select HAVE_BUILDTIME_MCOUNT_SORT diff --git a/arch/arm64/boot/dts/qcom/sm6115-fxtec-pro1x.dts b/arch/arm64/boot/dts/qcom/sm6115-fxtec-pro1x.dts index ad347ccd1975..fb5b9f10c8a7 100644 --- a/arch/arm64/boot/dts/qcom/sm6115-fxtec-pro1x.dts +++ b/arch/arm64/boot/dts/qcom/sm6115-fxtec-pro1x.dts @@ -151,7 +151,7 @@ interrupts-extended = <&tlmm 80 IRQ_TYPE_LEVEL_LOW>; - irq-gpios = <&tlmm 80 IRQ_TYPE_LEVEL_LOW>; + irq-gpios = <&tlmm 80 GPIO_ACTIVE_LOW>; reset-gpios = <&tlmm 71 GPIO_ACTIVE_HIGH>; AVDD28-supply = <&ts_vdd_supply>; VDDIO-supply = <&ts_vddio_supply>; diff --git a/arch/arm64/boot/dts/qcom/x1-dell-thena.dtsi b/arch/arm64/boot/dts/qcom/x1-dell-thena.dtsi index aee3fafbe7fc..58a5fe65ae38 100644 --- a/arch/arm64/boot/dts/qcom/x1-dell-thena.dtsi +++ b/arch/arm64/boot/dts/qcom/x1-dell-thena.dtsi @@ -589,6 +589,7 @@ regulator-min-microvolt = <1200000>; regulator-max-microvolt = <1200000>; regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>; + regulator-always-on; }; vreg_l13b_3p0: ldo13 { @@ -610,6 +611,7 @@ regulator-min-microvolt = <1800000>; regulator-max-microvolt = <1800000>; regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>; + regulator-always-on; }; }; diff --git a/arch/arm64/boot/dts/rockchip/px30-cobra.dtsi b/arch/arm64/boot/dts/rockchip/px30-cobra.dtsi index add917af5de7..f14f9eca7d34 100644 --- a/arch/arm64/boot/dts/rockchip/px30-cobra.dtsi +++ b/arch/arm64/boot/dts/rockchip/px30-cobra.dtsi @@ -35,7 +35,7 @@ compatible = "mmc-pwrseq-emmc"; pinctrl-0 = <&emmc_reset>; pinctrl-names = "default"; - reset-gpios = <&gpio1 RK_PB3 GPIO_ACTIVE_HIGH>; + reset-gpios = <&gpio1 RK_PB3 GPIO_ACTIVE_LOW>; }; gpio-leds { diff --git a/arch/arm64/boot/dts/rockchip/px30-pp1516.dtsi b/arch/arm64/boot/dts/rockchip/px30-pp1516.dtsi index 192791993f05..02200de695d3 100644 --- a/arch/arm64/boot/dts/rockchip/px30-pp1516.dtsi +++ b/arch/arm64/boot/dts/rockchip/px30-pp1516.dtsi @@ -33,7 +33,7 @@ compatible = "mmc-pwrseq-emmc"; pinctrl-0 = <&emmc_reset>; pinctrl-names = "default"; - reset-gpios = <&gpio1 RK_PB3 GPIO_ACTIVE_HIGH>; + reset-gpios = <&gpio1 RK_PB3 GPIO_ACTIVE_LOW>; }; gpio-leds { diff --git a/arch/arm64/boot/dts/rockchip/px30-ringneck.dtsi b/arch/arm64/boot/dts/rockchip/px30-ringneck.dtsi index 973b4c5880e2..29794216592d 100644 --- a/arch/arm64/boot/dts/rockchip/px30-ringneck.dtsi +++ b/arch/arm64/boot/dts/rockchip/px30-ringneck.dtsi @@ -26,7 +26,7 @@ compatible = "mmc-pwrseq-emmc"; pinctrl-0 = <&emmc_reset>; pinctrl-names = "default"; - reset-gpios = <&gpio1 RK_PB3 GPIO_ACTIVE_HIGH>; + reset-gpios = <&gpio1 RK_PB3 GPIO_ACTIVE_LOW>; }; leds { diff --git a/arch/arm64/boot/dts/rockchip/rk3399-pinephone-pro.dts b/arch/arm64/boot/dts/rockchip/rk3399-pinephone-pro.dts index 5de964d369b0..c224f76c1383 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-pinephone-pro.dts +++ b/arch/arm64/boot/dts/rockchip/rk3399-pinephone-pro.dts @@ -689,12 +689,6 @@ }; }; - wifi { - wifi_host_wake_l: wifi-host-wake-l { - rockchip,pins = <4 RK_PD0 RK_FUNC_GPIO &pcfg_pull_none>; - }; - }; - wireless-bluetooth { bt_wake_pin: bt-wake-pin { rockchip,pins = <2 RK_PD2 RK_FUNC_GPIO &pcfg_pull_none>; @@ -721,19 +715,7 @@ pinctrl-names = "default"; pinctrl-0 = <&sdio0_bus4 &sdio0_cmd &sdio0_clk>; sd-uhs-sdr104; - #address-cells = <1>; - #size-cells = <0>; status = "okay"; - - brcmf: wifi@1 { - compatible = "brcm,bcm4329-fmac"; - reg = <1>; - interrupt-parent = <&gpio4>; - interrupts = <RK_PD0 IRQ_TYPE_LEVEL_HIGH>; - interrupt-names = "host-wake"; - pinctrl-names = "default"; - pinctrl-0 = <&wifi_host_wake_l>; - }; }; &pwm0 { diff --git a/arch/arm64/boot/dts/rockchip/rk3399-roc-pc-plus.dts b/arch/arm64/boot/dts/rockchip/rk3399-roc-pc-plus.dts index 8e3858cf988c..27465cceca9a 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-roc-pc-plus.dts +++ b/arch/arm64/boot/dts/rockchip/rk3399-roc-pc-plus.dts @@ -132,6 +132,18 @@ <3 RK_PD7 1 &pcfg_pull_none>; }; +&i2s0_8ch_bus_bclk_off { + rockchip,pins = + <3 RK_PD0 RK_FUNC_GPIO &pcfg_pull_none>, + <3 RK_PD1 1 &pcfg_pull_none>, + <3 RK_PD2 1 &pcfg_pull_none>, + <3 RK_PD3 1 &pcfg_pull_none>, + <3 RK_PD4 1 &pcfg_pull_none>, + <3 RK_PD5 1 &pcfg_pull_none>, + <3 RK_PD6 1 &pcfg_pull_none>, + <3 RK_PD7 1 &pcfg_pull_none>; +}; + &i2s1 { pinctrl-names = "default"; pinctrl-0 = <&i2s_8ch_mclk_pin>, <&i2s1_2ch_bus>; diff --git a/arch/arm64/boot/dts/rockchip/rk3588s-roc-pc.dts b/arch/arm64/boot/dts/rockchip/rk3588s-roc-pc.dts index 7e179862da6e..26c431de6d96 100644 --- a/arch/arm64/boot/dts/rockchip/rk3588s-roc-pc.dts +++ b/arch/arm64/boot/dts/rockchip/rk3588s-roc-pc.dts @@ -23,16 +23,19 @@ compatible = "simple-audio-card"; pinctrl-names = "default"; pinctrl-0 = <&hp_detect>; + simple-audio-card,aux-devs = <&headphones_amp>; simple-audio-card,name = "rockchip,es8388"; - simple-audio-card,bitclock-master = <&masterdai>; + simple-audio-card,bitclock-master = <&cpudai>; simple-audio-card,format = "i2s"; - simple-audio-card,frame-master = <&masterdai>; + simple-audio-card,frame-master = <&cpudai>; simple-audio-card,hp-det-gpios = <&gpio1 RK_PA6 GPIO_ACTIVE_LOW>; simple-audio-card,mclk-fs = <256>; simple-audio-card,pin-switches = "Headphones"; simple-audio-card,routing = - "Headphones", "LOUT1", - "Headphones", "ROUT1", + "Headphones", "Headphone Amp OUTL", + "Headphones", "Headphone Amp OUTR", + "Headphone Amp INL", "LOUT2", + "Headphone Amp INR", "ROUT2", "LINPUT1", "Microphone Jack", "RINPUT1", "Microphone Jack", "LINPUT2", "Onboard Microphone", @@ -47,11 +50,17 @@ system-clock-frequency = <12288000>; }; - simple-audio-card,cpu { + cpudai: simple-audio-card,cpu { sound-dai = <&i2s0_8ch>; }; }; + headphones_amp: audio-amplifier-headphones { + compatible = "simple-audio-amplifier"; + enable-gpios = <&gpio1 RK_PA4 GPIO_ACTIVE_HIGH>; + sound-name-prefix = "Headphone Amp"; + }; + chosen { stdout-path = "serial2:1500000n8"; }; @@ -323,12 +332,12 @@ es8388: audio-codec@11 { compatible = "everest,es8388", "everest,es8328"; reg = <0x11>; - clocks = <&cru I2S1_8CH_MCLKOUT>; + clocks = <&cru I2S0_8CH_MCLKOUT>; AVDD-supply = <&vcc_3v3_s0>; DVDD-supply = <&vcc_1v8_s0>; HPVDD-supply = <&vcc_3v3_s0>; PVDD-supply = <&vcc_3v3_s0>; - assigned-clocks = <&cru I2S1_8CH_MCLKOUT>; + assigned-clocks = <&cru I2S0_8CH_MCLKOUT>; assigned-clock-rates = <12288000>; #sound-dai-cells = <0>; }; diff --git a/arch/arm64/kernel/compat_alignment.c b/arch/arm64/kernel/compat_alignment.c index b68e1d328d4c..9b58d0aa38d2 100644 --- a/arch/arm64/kernel/compat_alignment.c +++ b/arch/arm64/kernel/compat_alignment.c @@ -114,8 +114,8 @@ do_alignment_ldrdstrd(unsigned long addr, u32 instr, struct pt_regs *regs) static int do_alignment_ldmstm(unsigned long addr, u32 instr, struct pt_regs *regs) { - unsigned int rd, rn, nr_regs, regbits; - unsigned long eaddr, newaddr; + unsigned int rd, rn, regbits; + unsigned long eaddr, newaddr, nr_regs; unsigned int val; /* count the number of registers in the mask to be transferred */ diff --git a/arch/arm64/kernel/proton-pack.c b/arch/arm64/kernel/proton-pack.c index b3801f532b10..5138002d72f1 100644 --- a/arch/arm64/kernel/proton-pack.c +++ b/arch/arm64/kernel/proton-pack.c @@ -1022,6 +1022,11 @@ static int __init parse_spectre_bhb_param(char *str) } early_param("nospectre_bhb", parse_spectre_bhb_param); +static bool spectre_bhb_mitigations_off(void) +{ + return __nospectre_bhb || cpu_mitigations_off(); +} + void spectre_bhb_enable_mitigation(const struct arm64_cpu_capabilities *entry) { bp_hardening_cb_t cpu_cb; @@ -1035,6 +1040,8 @@ void spectre_bhb_enable_mitigation(const struct arm64_cpu_capabilities *entry) /* No point mitigating Spectre-BHB alone. */ } else if (!IS_ENABLED(CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY)) { /* Do nothing */ + } else if (spectre_bhb_mitigations_off()) { + /* Mitigation disabled on the command line */ } else if (supports_ecbhb(SCOPE_LOCAL_CPU)) { state = SPECTRE_MITIGATED; set_bit(BHB_HW, &system_bhb_mitigations); @@ -1200,6 +1207,6 @@ void spectre_print_disabled_mitigations(void) if (spectre_v4_mitigations_off()) pr_info("spectre-v4 %s", spectre_disabled_suffix); - if (__nospectre_bhb || cpu_mitigations_off()) + if (spectre_bhb_mitigations_off()) pr_info("spectre-bhb %s", spectre_disabled_suffix); } diff --git a/arch/openrisc/kernel/entry.S b/arch/openrisc/kernel/entry.S index c7e90b09645e..18e68680471e 100644 --- a/arch/openrisc/kernel/entry.S +++ b/arch/openrisc/kernel/entry.S @@ -1223,15 +1223,50 @@ _no_syscall_trace: * */ +/* Keep this literal; hi()/lo() can't use the UL-suffixed TASK_SIZE. */ +#define OR1K_ATOMIC_ADDR_LIMIT 0x7ffffffc + ENTRY(sys_or1k_atomic) /* FIXME: This ignores r3 and always does an XCHG */ + + /* Check both user pointers before accessing them. */ + l.movhi r13,hi(OR1K_ATOMIC_ADDR_LIMIT) + l.ori r13,r13,lo(OR1K_ATOMIC_ADDR_LIMIT) + l.sfgtu r4,r13 + l.bf 9f + l.nop + l.sfgtu r5,r13 + l.bf 9f + l.nop + DISABLE_INTERRUPTS(r17,r19) - l.lwz r29,0(r4) - l.lwz r27,0(r5) - l.sw 0(r4),r27 - l.sw 0(r5),r29 +10: l.lwz r29,0(r4) +11: l.lwz r27,0(r5) +12: l.sw 0(r4),r27 +13: l.sw 0(r5),r29 ENABLE_INTERRUPTS(r17) l.jr r9 l.or r11,r0,r0 + /* + * Either pointer was outside user space, or turned out to be + * unmapped/inaccessible when we actually touched it. + */ +9: l.jr r9 + l.addi r11,r0,-EFAULT + + .section .fixup, "ax" +14: + ENABLE_INTERRUPTS(r17) + l.j 9b + l.nop + .previous + + .section __ex_table, "a" + .long 10b, 14b + .long 11b, 14b + .long 12b, 14b + .long 13b, 14b + .previous + /* ============================================================[ EOF ]=== */ diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c index eac84d687b53..c493692adc69 100644 --- a/arch/powerpc/kernel/pci-common.c +++ b/arch/powerpc/kernel/pci-common.c @@ -626,19 +626,14 @@ int pci_legacy_write(struct pci_bus *bus, loff_t port, u32 val, size_t size) return -ENXIO; addr = hose->io_base_virt + port; - /* WARNING: The generic code is idiotic. It gets passed a pointer - * to what can be a 1, 2 or 4 byte quantity and always reads that - * as a u32, which means that we have to correct the location of - * the data read within those 32 bits for size 1 and 2 - */ switch(size) { case 1: - out_8(addr, val >> 24); + out_8(addr, val); return 1; case 2: if (port & 1) return -EINVAL; - out_le16(addr, val >> 16); + out_le16(addr, val); return 2; case 4: if (port & 3) diff --git a/arch/powerpc/platforms/powermac/low_i2c.c b/arch/powerpc/platforms/powermac/low_i2c.c index 02474e27df9b..5eff89a6859e 100644 --- a/arch/powerpc/platforms/powermac/low_i2c.c +++ b/arch/powerpc/platforms/powermac/low_i2c.c @@ -1505,7 +1505,7 @@ static int __init pmac_i2c_create_platform_devices(void) if (bus->platform_dev == NULL) return -ENOMEM; bus->platform_dev->dev.platform_data = bus; - bus->platform_dev->dev.of_node = bus->busnode; + bus->platform_dev->dev.of_node = of_node_get(bus->busnode); platform_device_add(bus->platform_dev); } diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c index eec333dd2e59..4bcb6f222065 100644 --- a/arch/powerpc/platforms/pseries/iommu.c +++ b/arch/powerpc/platforms/pseries/iommu.c @@ -812,18 +812,11 @@ static struct device_node *pci_dma_find(struct device_node *dn, /* parse DMA window property. During normal system boot, only default * DMA window is passed in OF. But, for kdump, a dedicated adapter might - * have both default and DDW in FDT. In this scenario, DDW takes precedence - * over default window. + * have both default and DDW in FDT. In this scenario, default window + * takes precedence over DDW. For a dedicated adapter, default window will + * potentially have more unused TCEs. */ - if (ddw_win) { - struct dynamic_dma_window_prop *p; - - p = (struct dynamic_dma_window_prop *)ddw_prop; - prop->liobn = p->liobn; - prop->dma_base = p->dma_base; - prop->tce_shift = p->tce_shift; - prop->window_shift = p->window_shift; - } else if (default_win) { + if (default_win) { unsigned long offset, size, liobn; of_parse_dma_window(rdn, default_prop, &liobn, &offset, &size); @@ -832,6 +825,14 @@ static struct device_node *pci_dma_find(struct device_node *dn, prop->dma_base = cpu_to_be64(offset); prop->tce_shift = cpu_to_be32(IOMMU_PAGE_SHIFT_4K); prop->window_shift = cpu_to_be32(order_base_2(size)); + } else { + struct dynamic_dma_window_prop *p; + + p = (struct dynamic_dma_window_prop *)ddw_prop; + prop->liobn = p->liobn; + prop->dma_base = p->dma_base; + prop->tce_shift = p->tce_shift; + prop->window_shift = p->window_shift; } return rdn; diff --git a/arch/riscv/include/asm/acpi.h b/arch/riscv/include/asm/acpi.h index 6e13695120bc..a4b9e60f747c 100644 --- a/arch/riscv/include/asm/acpi.h +++ b/arch/riscv/include/asm/acpi.h @@ -12,6 +12,8 @@ #ifndef _ASM_ACPI_H #define _ASM_ACPI_H +#include <linux/cpuidle.h> + /* Basic configuration for ACPI */ #ifdef CONFIG_ACPI @@ -71,6 +73,23 @@ int acpi_get_riscv_isa(struct acpi_table_header *table, void acpi_get_cbo_block_size(struct acpi_table_header *table, u32 *cbom_size, u32 *cboz_size, u32 *cbop_size); + +/* + * RISC-V Functional Fixed Hardware Specification Version v1.0.1, + * Chapter 3.1.2, Table 4: Arch. Context Lost Flags + */ +#define RISCV_LPI_HART_TIMER_CTXT_LOST BIT(0) + +static inline unsigned int arch_get_idle_state_flags(u32 arch_flags) +{ + if (arch_flags & RISCV_LPI_HART_TIMER_CTXT_LOST) + return CPUIDLE_FLAG_TIMER_STOP; + + return 0; +} + +#define arch_get_idle_state_flags arch_get_idle_state_flags + #else static inline void acpi_init_rintc_map(void) { } static inline struct acpi_madt_rintc *acpi_cpu_get_madt_rintc(int cpu) diff --git a/arch/riscv/kernel/unaligned_access_speed.c b/arch/riscv/kernel/unaligned_access_speed.c index 78fc74a41678..f111a30d480c 100644 --- a/arch/riscv/kernel/unaligned_access_speed.c +++ b/arch/riscv/kernel/unaligned_access_speed.c @@ -6,7 +6,6 @@ #include <linux/cpu.h> #include <linux/cpumask.h> #include <linux/jump_label.h> -#include <linux/kthread.h> #include <linux/mm.h> #include <linux/smp.h> #include <linux/types.h> @@ -375,18 +374,9 @@ free: __free_pages(page, MISALIGNED_BUFFER_ORDER); } -/* Measure unaligned access speed on all CPUs present at boot in parallel. */ -static int vec_check_unaligned_access_speed_all_cpus(void *unused __always_unused) -{ - schedule_on_each_cpu(check_vector_unaligned_access); - riscv_hwprobe_complete_async_probe(); - - return 0; -} #else /* CONFIG_RISCV_PROBE_VECTOR_UNALIGNED_ACCESS */ -static int vec_check_unaligned_access_speed_all_cpus(void *unused __always_unused) +static void check_vector_unaligned_access(struct work_struct *work __always_unused) { - return 0; } #endif @@ -474,12 +464,7 @@ static int __init check_unaligned_access_all_cpus(void) per_cpu(vector_misaligned_access, cpu) = unaligned_vector_speed_param; } else if (!check_vector_unaligned_access_emulated_all_cpus() && IS_ENABLED(CONFIG_RISCV_PROBE_VECTOR_UNALIGNED_ACCESS)) { - riscv_hwprobe_register_async_probe(); - if (IS_ERR(kthread_run(vec_check_unaligned_access_speed_all_cpus, - NULL, "vec_check_unaligned_access_speed_all_cpus"))) { - pr_warn("Failed to create vec_unalign_check kthread\n"); - riscv_hwprobe_complete_async_probe(); - } + schedule_on_each_cpu(check_vector_unaligned_access); } /* diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c index fbe21b1db3ee..d866562cae38 100644 --- a/arch/s390/kernel/perf_cpum_cf.c +++ b/arch/s390/kernel/perf_cpum_cf.c @@ -111,6 +111,7 @@ struct cpu_cf_ptr { static struct cpu_cf_root { /* Anchor to per CPU data */ refcount_t refcnt; /* Overall active events */ + unsigned int tskctx; /* Users tracking all CPUs (cpu == -1) */ struct cpu_cf_ptr __percpu *cfptr; } cpu_cf_root; @@ -119,13 +120,15 @@ static struct cpu_cf_root { /* Anchor to per CPU data */ * user space in task context with perf_event_open() and close() * system calls. * - * This mutex serializes functions cpum_cf_alloc_cpu() called at event - * initialization via cpumf_pmu_event_init() and function cpum_cf_free_cpu() - * called at event removal via call back function hw_perf_event_destroy() - * when the event is deleted. They are serialized to enforce correct - * bookkeeping of pointer and reference counts anchored by - * struct cpu_cf_root and the access to cpu_cf_root::refcnt and the - * per CPU pointers stored in cpu_cf_root::cfptr. + * This mutex serializes the allocation and removal of the per CPU counter + * data via cpum_cf_alloc_cpu() and cpum_cf_free_cpu(). They are called with + * this mutex held at event initialization via cpumf_pmu_event_init(), at + * event removal via call back function hw_perf_event_destroy() when the + * event is deleted, and from the CPU hotplug prepare/dead callbacks. The + * mutex enforces correct bookkeeping of pointer and reference counts + * anchored by struct cpu_cf_root and protects the access to + * cpu_cf_root::refcnt, cpu_cf_root::tskctx and the per CPU pointers + * stored in cpu_cf_root::cfptr. */ static DEFINE_MUTEX(pmc_reserve_mutex); @@ -168,12 +171,14 @@ static void cpum_cf_reset_cpu(void *flags) } /* Free per CPU data when the last event is removed. */ -static void cpum_cf_free_root(void) +static void cpum_cf_free_root(unsigned int num) { - if (!refcount_dec_and_test(&cpu_cf_root.refcnt)) + struct cpu_cf_ptr __percpu *p = cpu_cf_root.cfptr; + + if (!refcount_sub_and_test(num, &cpu_cf_root.refcnt)) return; - free_percpu(cpu_cf_root.cfptr); cpu_cf_root.cfptr = NULL; + free_percpu(p); irq_subclass_unregister(IRQ_SUBCLASS_MEASUREMENT_ALERT); on_each_cpu(cpum_cf_reset_cpu, NULL, 1); debug_sprintf_event(cf_dbg, 4, "%s root.refcnt %u cfptr %d\n", @@ -187,17 +192,17 @@ static void cpum_cf_free_root(void) * CPUs possible, which might be larger than the number of CPUs currently * online. */ -static int cpum_cf_alloc_root(void) +static int cpum_cf_alloc_root(unsigned int num) { int rc = 0; - if (refcount_inc_not_zero(&cpu_cf_root.refcnt)) + if (refcount_add_not_zero(num, &cpu_cf_root.refcnt)) return rc; /* The memory is already zeroed. */ cpu_cf_root.cfptr = alloc_percpu(struct cpu_cf_ptr); if (cpu_cf_root.cfptr) { - refcount_set(&cpu_cf_root.refcnt, 1); + refcount_set(&cpu_cf_root.refcnt, num); on_each_cpu(cpum_cf_reset_cpu, NULL, 1); irq_subclass_register(IRQ_SUBCLASS_MEASUREMENT_ALERT); } else { @@ -207,20 +212,23 @@ static int cpum_cf_alloc_root(void) return rc; } -/* Free CPU counter data structure for a PMU */ -static void cpum_cf_free_cpu(int cpu) +/* + * Remove num references to the CPU counter data structure of a PMU. + * Called with pmc_reserve_mutex held. + */ +static void cpum_cf_free_cpu(int cpu, unsigned int num) { struct cpu_cf_events *cpuhw; struct cpu_cf_ptr *p; - mutex_lock(&pmc_reserve_mutex); + lockdep_assert_held(&pmc_reserve_mutex); /* * When invoked via CPU hotplug handler, there might be no events * installed or that particular CPU might not have an * event installed. This anchor pointer can be NULL! */ if (!cpu_cf_root.cfptr) - goto out; + return; p = per_cpu_ptr(cpu_cf_root.cfptr, cpu); cpuhw = p->cpucf; /* @@ -228,28 +236,29 @@ static void cpum_cf_free_cpu(int cpu) * installed on that CPU, but on different CPUs. */ if (!cpuhw) - goto out; + return; - if (refcount_dec_and_test(&cpuhw->refcnt)) { - kfree(cpuhw); + if (refcount_sub_and_test(num, &cpuhw->refcnt)) { p->cpucf = NULL; + kfree(cpuhw); } - cpum_cf_free_root(); -out: - mutex_unlock(&pmc_reserve_mutex); + cpum_cf_free_root(num); } -/* Allocate CPU counter data structure for a PMU. Called under mutex lock. */ -static int cpum_cf_alloc_cpu(int cpu) +/* + * Add num references to the CPU counter data structure of a PMU and + * allocate it when necessary. Called with pmc_reserve_mutex held. + */ +static int cpum_cf_alloc_cpu(int cpu, unsigned int num) { struct cpu_cf_events *cpuhw; struct cpu_cf_ptr *p; int rc; - mutex_lock(&pmc_reserve_mutex); - rc = cpum_cf_alloc_root(); + lockdep_assert_held(&pmc_reserve_mutex); + rc = cpum_cf_alloc_root(num); if (rc) - goto unlock; + return rc; p = per_cpu_ptr(cpu_cf_root.cfptr, cpu); cpuhw = p->cpucf; @@ -257,12 +266,12 @@ static int cpum_cf_alloc_cpu(int cpu) cpuhw = kzalloc(sizeof(*cpuhw), GFP_KERNEL); if (cpuhw) { p->cpucf = cpuhw; - refcount_set(&cpuhw->refcnt, 1); + refcount_set(&cpuhw->refcnt, num); } else { rc = -ENOMEM; } } else { - refcount_inc(&cpuhw->refcnt); + refcount_add(num, &cpuhw->refcnt); } if (rc) { /* @@ -270,10 +279,8 @@ static int cpum_cf_alloc_cpu(int cpu) * cpu_cf_event in not created, its destroy() function is not * invoked. Adjust the reference counter for the anchor. */ - cpum_cf_free_root(); + cpum_cf_free_root(num); } -unlock: - mutex_unlock(&pmc_reserve_mutex); return rc; } @@ -285,39 +292,70 @@ unlock: * perf_event_open() with task context and /dev/hwctr interface. * If cpu is non-zero install event on this CPU only. This setup handles * perf_event_open() with CPU context. + * Users with cpu == -1 are counted in cpu_cf_root::tskctx. The CPU hotplug + * prepare and dead callbacks use this count to install and remove the per + * CPU counter data on a new or dying CPU. */ -static int cpum_cf_alloc(int cpu) +static int cpum_cf_alloc_cpuslocked(int cpu) { cpumask_var_t mask; int rc; + lockdep_assert_cpus_held(); if (cpu == -1) { if (!zalloc_cpumask_var(&mask, GFP_KERNEL)) return -ENOMEM; + mutex_lock(&pmc_reserve_mutex); for_each_online_cpu(cpu) { - rc = cpum_cf_alloc_cpu(cpu); + rc = cpum_cf_alloc_cpu(cpu, 1); if (rc) { for_each_cpu(cpu, mask) - cpum_cf_free_cpu(cpu); + cpum_cf_free_cpu(cpu, 1); break; } cpumask_set_cpu(cpu, mask); } + if (!rc) + cpu_cf_root.tskctx++; + mutex_unlock(&pmc_reserve_mutex); free_cpumask_var(mask); } else { - rc = cpum_cf_alloc_cpu(cpu); + mutex_lock(&pmc_reserve_mutex); + rc = cpum_cf_alloc_cpu(cpu, 1); + mutex_unlock(&pmc_reserve_mutex); } return rc; } -static void cpum_cf_free(int cpu) +static int cpum_cf_alloc(int cpu) +{ + int rc; + + cpus_read_lock(); + rc = cpum_cf_alloc_cpuslocked(cpu); + cpus_read_unlock(); + return rc; +} + +static void cpum_cf_free_cpuslocked(int cpu) { + lockdep_assert_cpus_held(); + mutex_lock(&pmc_reserve_mutex); if (cpu == -1) { + cpu_cf_root.tskctx--; for_each_online_cpu(cpu) - cpum_cf_free_cpu(cpu); + cpum_cf_free_cpu(cpu, 1); } else { - cpum_cf_free_cpu(cpu); + cpum_cf_free_cpu(cpu, 1); } + mutex_unlock(&pmc_reserve_mutex); +} + +static void cpum_cf_free(int cpu) +{ + cpus_read_lock(); + cpum_cf_free_cpuslocked(cpu); + cpus_read_unlock(); } #define CF_DIAG_CTRSET_DEF 0xfeef /* Counter set header mark */ @@ -1091,53 +1129,67 @@ static refcount_t cfset_opencnt = REFCOUNT_INIT(0); /* Access count */ static DEFINE_MUTEX(cfset_ctrset_mutex); /* - * CPU hotplug handles only /dev/hwctr device. - * For perf_event_open() the CPU hotplug handling is done on kernel common - * code: + * CPU hotplug handling: + * + * cpum_cf_prepare_cpu() and cpum_cf_dead_cpu() run while the new or dying + * CPU is offline. They create and remove the per CPU counter data for all + * users tracking every CPU (cpu == -1), that is perf_event_open() events + * with task context and /dev/hwctr device sessions. Each such user holds + * one reference to the per CPU counter data of each CPU. Therefore install + * and remove one reference per user, tracked in cpu_cf_root::tskctx. This + * guarantees the per CPU counter data exists before the new CPU executes + * its first task and is removed only after the dying CPU is gone. + * + * cpum_cf_online_cpu() and cpum_cf_offline_cpu() run while the new or + * dying CPU is online. They handle only the counter set state of open + * /dev/hwctr device sessions on that CPU. For perf_event_open() events + * nothing is done: * - CPU add: Nothing is done since a file descriptor can not be created * and returned to the user. * - CPU delete: Handled by common code via pmu_disable(), pmu_stop() and - * pmu_delete(). The event itself is removed when the file descriptor is - * closed. + * pmu_delete(). During task exit processing of grouped perf events + * triggered by CPU hotplug processing, pmu_disable() is called as part + * of perf context removal process. The event itself is removed when the + * event file descriptor is closed. */ +static int cpum_cf_prepare_cpu(unsigned int cpu) +{ + int rc = 0; + + mutex_lock(&pmc_reserve_mutex); + if (cpu_cf_root.tskctx) + rc = cpum_cf_alloc_cpu(cpu, cpu_cf_root.tskctx); + mutex_unlock(&pmc_reserve_mutex); + return rc; +} + +static int cpum_cf_dead_cpu(unsigned int cpu) +{ + mutex_lock(&pmc_reserve_mutex); + if (cpu_cf_root.tskctx) + cpum_cf_free_cpu(cpu, cpu_cf_root.tskctx); + mutex_unlock(&pmc_reserve_mutex); + return 0; +} + static int cfset_online_cpu(unsigned int cpu); static int cpum_cf_online_cpu(unsigned int cpu) { - int rc = 0; - - /* - * Ignore notification for perf_event_open(). - * Handle only /dev/hwctr device sessions. - */ mutex_lock(&cfset_ctrset_mutex); - if (refcount_read(&cfset_opencnt)) { - rc = cpum_cf_alloc_cpu(cpu); - if (!rc) - cfset_online_cpu(cpu); - } + if (refcount_read(&cfset_opencnt)) + cfset_online_cpu(cpu); mutex_unlock(&cfset_ctrset_mutex); - return rc; + return 0; } static int cfset_offline_cpu(unsigned int cpu); static int cpum_cf_offline_cpu(unsigned int cpu) { - /* - * During task exit processing of grouped perf events triggered by CPU - * hotplug processing, pmu_disable() is called as part of perf context - * removal process. Therefore do not trigger event removal now for - * perf_event_open() created events. Perf common code triggers event - * destruction when the event file descriptor is closed. - * - * Handle only /dev/hwctr device sessions. - */ mutex_lock(&cfset_ctrset_mutex); - if (refcount_read(&cfset_opencnt)) { + if (refcount_read(&cfset_opencnt)) cfset_offline_cpu(cpu); - cpum_cf_free_cpu(cpu); - } mutex_unlock(&cfset_ctrset_mutex); return 0; } @@ -1184,7 +1236,7 @@ static void cpumf_measurement_alert(struct ext_code ext_code, static int cfset_init(void); static int __init cpumf_pmu_init(void) { - int rc; + int state, rc; /* Extract counter measurement facility information */ if (!cpum_cf_avail() || qctri(&cpumf_ctr_info)) @@ -1226,11 +1278,24 @@ static int __init cpumf_pmu_init(void) cfset_init(); } + rc = cpuhp_setup_state(CPUHP_BP_PREPARE_DYN, + "perf/s390/cf:prepare", + cpum_cf_prepare_cpu, cpum_cf_dead_cpu); + if (rc < 0) + goto out3; + state = rc; + rc = cpuhp_setup_state(CPUHP_AP_PERF_S390_CF_ONLINE, "perf/s390/cf:online", cpum_cf_online_cpu, cpum_cf_offline_cpu); - return rc; + if (rc < 0) + goto out4; + return 0; +out4: + cpuhp_remove_state(state); +out3: + perf_pmu_unregister(&cpumf_pmu); out2: debug_unregister_view(cf_dbg, &debug_sprintf_view); debug_unregister(cf_dbg); @@ -1386,6 +1451,7 @@ static void cfset_all_stop(struct cfset_request *req) */ static int cfset_release(struct inode *inode, struct file *file) { + cpus_read_lock(); mutex_lock(&cfset_ctrset_mutex); /* Open followed by close/exit has no private_data */ if (file->private_data) { @@ -1396,9 +1462,10 @@ static int cfset_release(struct inode *inode, struct file *file) } if (refcount_dec_and_test(&cfset_opencnt)) { /* Last close */ on_each_cpu(cfset_release_cpu, NULL, 1); - cpum_cf_free(-1); + cpum_cf_free_cpuslocked(-1); } mutex_unlock(&cfset_ctrset_mutex); + cpus_read_unlock(); return 0; } @@ -1417,15 +1484,17 @@ static int cfset_open(struct inode *inode, struct file *file) return -EPERM; file->private_data = NULL; + cpus_read_lock(); mutex_lock(&cfset_ctrset_mutex); if (!refcount_inc_not_zero(&cfset_opencnt)) { /* First open */ - rc = cpum_cf_alloc(-1); + rc = cpum_cf_alloc_cpuslocked(-1); if (!rc) { cfset_session_init(); refcount_set(&cfset_opencnt, 1); } } mutex_unlock(&cfset_ctrset_mutex); + cpus_read_unlock(); /* nonseekable_open() never fails */ return rc ?: nonseekable_open(inode, file); diff --git a/arch/x86/coco/tdx/tdx.c b/arch/x86/coco/tdx/tdx.c index 7b2833705d47..fcb9ec936d05 100644 --- a/arch/x86/coco/tdx/tdx.c +++ b/arch/x86/coco/tdx/tdx.c @@ -693,8 +693,8 @@ static bool handle_in(struct pt_regs *regs, int size, int port) .r13 = PORT_READ, .r14 = port, }; - u64 mask = GENMASK(BITS_PER_BYTE * size, 0); bool success; + u64 val; /* * Emulate the I/O read via hypercall. More info about ABI can be found @@ -702,18 +702,16 @@ static bool handle_in(struct pt_regs *regs, int size, int port) * "TDG.VP.VMCALL<Instruction.IO>". */ success = !__tdx_hypercall(&args); + val = success ? args.r11 : 0; - /* Update part of the register affected by the emulated instruction */ - regs->ax &= ~mask; - if (success) - regs->ax |= args.r11 & mask; + insn_assign_reg(®s->ax, val, size); return success; } static bool handle_out(struct pt_regs *regs, int size, int port) { - u64 mask = GENMASK(BITS_PER_BYTE * size, 0); + u64 mask = GENMASK(BITS_PER_BYTE * size - 1, 0); /* * Emulate the I/O write via hypercall. More info about ABI can be found diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c index e228e564b15e..8301a589d9a6 100644 --- a/arch/x86/events/intel/uncore.c +++ b/arch/x86/events/intel/uncore.c @@ -67,6 +67,7 @@ int uncore_die_to_segment(int die) return bus ? pci_domain_nr(bus) : -EINVAL; } +/* Note: This API can only be used when NUMA information is available. */ int uncore_device_to_die(struct pci_dev *dev) { int node = pcibus_to_node(dev->bus); diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c index a338ee01bb24..0182785cad1f 100644 --- a/arch/x86/events/intel/uncore_snbep.c +++ b/arch/x86/events/intel/uncore_snbep.c @@ -1475,13 +1475,7 @@ static int snbep_pci2phy_map_init(int devid, int nodeid_loc, int idmap_loc, bool } map->pbus_to_dieid[bus] = die_id = uncore_device_to_die(ubox_dev); - raw_spin_unlock(&pci2phy_map_lock); - - if (WARN_ON_ONCE(die_id == -1)) { - err = -EINVAL; - break; - } } } @@ -6533,7 +6527,7 @@ static void spr_update_device_location(int type_id) while ((dev = pci_get_device(PCI_VENDOR_ID_INTEL, device, dev)) != NULL) { - die = uncore_device_to_die(dev); + die = uncore_pcibus_to_dieid(dev->bus); if (die < 0) continue; @@ -6557,6 +6551,11 @@ static void spr_update_device_location(int type_id) int spr_uncore_pci_init(void) { + int ret = snbep_pci2phy_map_init(0x3250, SKX_CPUNODEID, SKX_GIDNIDMAP, true); + + if (ret) + return ret; + /* * The discovery table of UPI on some SPR variant is broken, * which impacts the detection of both UPI and M3UPI uncore PMON. diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h index db70832232d4..3e78bb76153c 100644 --- a/arch/x86/include/asm/barrier.h +++ b/arch/x86/include/asm/barrier.h @@ -17,7 +17,7 @@ #define rmb() asm volatile(ALTERNATIVE("lock addl $0,-4(%%esp)", "lfence", \ X86_FEATURE_XMM2) ::: "memory", "cc") #define wmb() asm volatile(ALTERNATIVE("lock addl $0,-4(%%esp)", "sfence", \ - X86_FEATURE_XMM2) ::: "memory", "cc") + X86_FEATURE_XMM) ::: "memory", "cc") #else #define __mb() asm volatile("mfence":::"memory") #define __rmb() asm volatile("lfence":::"memory") diff --git a/arch/x86/include/asm/insn-eval.h b/arch/x86/include/asm/insn-eval.h index 54368a43abf6..b1e6c47113aa 100644 --- a/arch/x86/include/asm/insn-eval.h +++ b/arch/x86/include/asm/insn-eval.h @@ -9,6 +9,7 @@ #include <linux/compiler.h> #include <linux/bug.h> #include <linux/err.h> +#include <asm/insn.h> #include <asm/ptrace.h> #define INSN_CODE_SEG_ADDR_SZ(params) ((params >> 4) & 0xf) @@ -44,4 +45,39 @@ enum insn_mmio_type { enum insn_mmio_type insn_decode_mmio(struct insn *insn, int *bytes); +/* + * Write @val into *@reg following the x86 rules for writes to + * general-purpose registers (Intel SDM Vol. 1, "General-Purpose + * Registers in 64-Bit Mode"): an 8- or 16-bit write leaves the rest of + * the register untouched, a 32-bit write zero-extends the result into + * the upper 32 bits, and a 64-bit write replaces the whole register. + * + * @bytes is the width of the write, not a property of the instruction: + * an instruction that, say, sign-extends a 32-bit immediate into a + * 64-bit register does a 64-bit write here. + * + * @reg need not be 8-byte aligned: KVM's instruction emulator offsets + * the pointer by one byte to address the high-byte registers (AH, CH, + * DH, BH). Use narrow stores for the sub-word cases so the access + * width matches @bytes and the adjacent bytes are left alone. + */ +static inline void insn_assign_reg(unsigned long *reg, u64 val, int bytes) +{ + switch (bytes) { + case 1: + *(u8 *)reg = (u8)val; + break; + case 2: + *(u16 *)reg = (u16)val; + break; + case 4: + /* A 32-bit write zero-extends into the upper 32 bits. */ + *reg = (u32)val; + break; + case 8: + *reg = val; + break; + } +} + #endif /* _ASM_X86_INSN_EVAL_H */ diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 4e3da5b497b8..9dbf3623e79e 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -24,6 +24,7 @@ #include "kvm_emulate.h" #include <linux/stringify.h> #include <asm/debugreg.h> +#include <asm/insn-eval.h> #include <asm/nospec-branch.h> #include <asm/ibt.h> #include <asm/text-patching.h> @@ -436,25 +437,6 @@ static void assign_masked(ulong *dest, ulong src, ulong mask) *dest = (*dest & ~mask) | (src & mask); } -static void assign_register(unsigned long *reg, u64 val, int bytes) -{ - /* The 4-byte case *is* correct: in 64-bit mode we zero-extend. */ - switch (bytes) { - case 1: - *(u8 *)reg = (u8)val; - break; - case 2: - *(u16 *)reg = (u16)val; - break; - case 4: - *reg = (u32)val; - break; /* 64b: zero-extend */ - case 8: - *reg = val; - break; - } -} - static inline unsigned long ad_mask(struct x86_emulate_ctxt *ctxt) { return (1UL << (ctxt->ad_bytes << 3)) - 1; @@ -502,7 +484,7 @@ register_address_increment(struct x86_emulate_ctxt *ctxt, int reg, int inc) { ulong *preg = reg_rmw(ctxt, reg); - assign_register(preg, *preg + inc, ctxt->ad_bytes); + insn_assign_reg(preg, *preg + inc, ctxt->ad_bytes); } static void rsp_increment(struct x86_emulate_ctxt *ctxt, int inc) @@ -1756,7 +1738,7 @@ static int load_segment_descriptor(struct x86_emulate_ctxt *ctxt, static void write_register_operand(struct operand *op) { - return assign_register(op->addr.reg, op->val, op->bytes); + return insn_assign_reg(op->addr.reg, op->val, op->bytes); } static int writeback(struct x86_emulate_ctxt *ctxt, struct operand *op) @@ -1989,7 +1971,7 @@ static int em_popa(struct x86_emulate_ctxt *ctxt) rc = emulate_pop(ctxt, &val, ctxt->op_bytes); if (rc != X86EMUL_CONTINUE) break; - assign_register(reg_rmw(ctxt, reg), val, ctxt->op_bytes); + insn_assign_reg(reg_rmw(ctxt, reg), val, ctxt->op_bytes); --reg; } return rc; diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index c3798cab3b7d..88a1bbfa918f 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -1756,7 +1756,7 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, u8 *rw_image EMIT_mov(dst_reg, src_reg); #ifdef CONFIG_SMP /* add <dst>, gs:[<off>] */ - EMIT2(0x65, add_1mod(0x48, dst_reg)); + EMIT2(0x65, add_2mod(0x48, 0, dst_reg)); EMIT3(0x03, add_2reg(0x04, 0, dst_reg), 0x25); EMIT((u32)(unsigned long)&this_cpu_off, 4); #endif diff --git a/block/genhd.c b/block/genhd.c index b00fa6baf4ff..28e5aea2418e 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -681,6 +681,7 @@ static bool __blk_mark_disk_dead(struct gendisk *disk) */ void blk_mark_disk_dead(struct gendisk *disk) { + blk_queue_flag_set(QUEUE_FLAG_DYING, disk->queue); __blk_mark_disk_dead(disk); blk_report_disk_dead(disk, true); } diff --git a/drivers/accel/rocket/rocket_job.c b/drivers/accel/rocket/rocket_job.c index acd606160dc9..b374d7ee54b6 100644 --- a/drivers/accel/rocket/rocket_job.c +++ b/drivers/accel/rocket/rocket_job.c @@ -8,6 +8,7 @@ #include <drm/drm_gem.h> #include <drm/rocket_accel.h> #include <linux/interrupt.h> +#include <linux/overflow.h> #include <linux/iommu.h> #include <linux/platform_device.h> #include <linux/pm_runtime.h> @@ -102,6 +103,7 @@ rocket_copy_tasks(struct drm_device *dev, fail: kvfree(rjob->tasks); + rjob->tasks = NULL; return ret; } @@ -188,14 +190,19 @@ static int rocket_job_push(struct rocket_job *job) struct rocket_device *rdev = job->rdev; struct drm_gem_object **bos; struct ww_acquire_ctx acquire_ctx; + u32 bo_count; int ret = 0; - bos = kvmalloc_array(job->in_bo_count + job->out_bo_count, sizeof(void *), - GFP_KERNEL); + if (check_add_overflow(job->in_bo_count, job->out_bo_count, &bo_count)) + return -EINVAL; + + bos = kvmalloc_array(bo_count, sizeof(*bos), GFP_KERNEL); + if (!bos) + return -ENOMEM; memcpy(bos, job->in_bos, job->in_bo_count * sizeof(void *)); memcpy(&bos[job->in_bo_count], job->out_bos, job->out_bo_count * sizeof(void *)); - ret = drm_gem_lock_reservations(bos, job->in_bo_count + job->out_bo_count, &acquire_ctx); + ret = drm_gem_lock_reservations(bos, bo_count, &acquire_ctx); if (ret) goto err; @@ -220,7 +227,7 @@ static int rocket_job_push(struct rocket_job *job) rocket_attach_object_fences(job->out_bos, job->out_bo_count, job->inference_done_fence); err_unlock: - drm_gem_unlock_reservations(bos, job->in_bo_count + job->out_bo_count, &acquire_ctx); + drm_gem_unlock_reservations(bos, bo_count, &acquire_ctx); err: kvfree(bos); @@ -310,13 +317,13 @@ static struct dma_fence *rocket_job_run(struct drm_sched_job *sched_job) dma_fence_put(job->done_fence); job->done_fence = dma_fence_get(fence); - ret = pm_runtime_get_sync(core->dev); + ret = pm_runtime_resume_and_get(core->dev); if (ret < 0) - return fence; + goto err_put_fences; ret = iommu_attach_group(job->domain->domain, core->iommu_group); if (ret < 0) - return fence; + goto err_put_pm; scoped_guard(mutex, &core->job_lock) { core->in_flight_job = job; @@ -324,6 +331,14 @@ static struct dma_fence *rocket_job_run(struct drm_sched_job *sched_job) } return fence; + +err_put_pm: + pm_runtime_put(core->dev); +err_put_fences: + dma_fence_put(job->done_fence); + job->done_fence = NULL; + dma_fence_put(fence); + return ERR_PTR(ret); } static void rocket_job_handle_irq(struct rocket_core *core) @@ -550,6 +565,7 @@ static int rocket_ioctl_submit_job(struct drm_device *dev, struct drm_file *file kref_init(&rjob->refcount); rjob->rdev = rdev; + rjob->domain = rocket_iommu_domain_get(file_priv); ret = drm_sched_job_init(&rjob->base, &file_priv->sched_entity, @@ -575,8 +591,6 @@ static int rocket_ioctl_submit_job(struct drm_device *dev, struct drm_file *file rjob->out_bo_count = job->out_bo_handle_count; - rjob->domain = rocket_iommu_domain_get(file_priv); - ret = rocket_job_push(rjob); if (ret) goto out_cleanup_job; diff --git a/drivers/acpi/apei/erst.c b/drivers/acpi/apei/erst.c index bf65e3461531..15ab797641cf 100644 --- a/drivers/acpi/apei/erst.c +++ b/drivers/acpi/apei/erst.c @@ -108,7 +108,7 @@ static inline u64 erst_get_timeout(void) if (erst_erange.attr & ERST_RANGE_SLOW) { timeout = ((erst_erange.timings & ERST_EXEC_TIMING_MAX_MASK) >> - ERST_EXEC_TIMING_MAX_SHIFT) * NSEC_PER_MSEC; + ERST_EXEC_TIMING_MAX_SHIFT) * NSEC_PER_USEC; if (timeout < FIRMWARE_TIMEOUT) timeout = FIRMWARE_TIMEOUT; } diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c index fc96a5e234f0..5b52455d86e0 100644 --- a/drivers/acpi/apei/ghes.c +++ b/drivers/acpi/apei/ghes.c @@ -581,7 +581,7 @@ static bool ghes_handle_arm_hw_error(struct acpi_hest_generic_data *gdata, return false; p = (char *)(err + 1); - length -= sizeof(err); + length -= sizeof(*err); for (i = 0; i < err->err_info_num; i++) { struct cper_arm_err_info *err_info; @@ -736,7 +736,7 @@ static DEFINE_KFIFO(cxl_cper_prot_err_fifo, struct cxl_cper_prot_err_work_data, CXL_CPER_PROT_ERR_FIFO_DEPTH); /* Synchronize schedule_work() with cxl_cper_prot_err_work changes */ -static DEFINE_SPINLOCK(cxl_cper_prot_err_work_lock); +static DEFINE_RAW_SPINLOCK(cxl_cper_prot_err_work_lock); struct work_struct *cxl_cper_prot_err_work; static void cxl_cper_post_prot_err(struct cxl_cper_sec_prot_err *prot_err, @@ -749,7 +749,7 @@ static void cxl_cper_post_prot_err(struct cxl_cper_sec_prot_err *prot_err, if (cxl_cper_sec_prot_err_valid(prot_err)) return; - guard(spinlock_irqsave)(&cxl_cper_prot_err_work_lock); + guard(raw_spinlock_irqsave)(&cxl_cper_prot_err_work_lock); if (!cxl_cper_prot_err_work) return; @@ -787,10 +787,11 @@ static void cxl_cper_post_prot_err(struct cxl_cper_sec_prot_err *prot_err, int cxl_cper_register_prot_err_work(struct work_struct *work) { - if (cxl_cper_prot_err_work) - return -EINVAL; + guard(raw_spinlock_irqsave)(&cxl_cper_prot_err_work_lock); - guard(spinlock)(&cxl_cper_prot_err_work_lock); + if (WARN_ONCE(cxl_cper_prot_err_work, + "CPER-CXL kfifo consumer already registered\n")) + return -EINVAL; cxl_cper_prot_err_work = work; return 0; } @@ -798,11 +799,18 @@ EXPORT_SYMBOL_NS_GPL(cxl_cper_register_prot_err_work, "CXL"); int cxl_cper_unregister_prot_err_work(struct work_struct *work) { - if (cxl_cper_prot_err_work != work) - return -EINVAL; + scoped_guard(raw_spinlock_irqsave, &cxl_cper_prot_err_work_lock) { + if (WARN_ONCE(cxl_cper_prot_err_work != work, + "CPER-CXL kfifo consumer mismatch on unregister\n")) + return -EINVAL; + cxl_cper_prot_err_work = NULL; + } + + cancel_work_sync(work); + + /* Discard stale entries so they are not replayed on next module load */ + kfifo_reset(&cxl_cper_prot_err_fifo); - guard(spinlock)(&cxl_cper_prot_err_work_lock); - cxl_cper_prot_err_work = NULL; return 0; } EXPORT_SYMBOL_NS_GPL(cxl_cper_unregister_prot_err_work, "CXL"); @@ -818,7 +826,7 @@ EXPORT_SYMBOL_NS_GPL(cxl_cper_prot_err_kfifo_get, "CXL"); DEFINE_KFIFO(cxl_cper_fifo, struct cxl_cper_work_data, CXL_CPER_FIFO_DEPTH); /* Synchronize schedule_work() with cxl_cper_work changes */ -static DEFINE_SPINLOCK(cxl_cper_work_lock); +static DEFINE_RAW_SPINLOCK(cxl_cper_work_lock); struct work_struct *cxl_cper_work; static void cxl_cper_post_event(enum cxl_event_type event_type, @@ -838,7 +846,7 @@ static void cxl_cper_post_event(enum cxl_event_type event_type, return; } - guard(spinlock_irqsave)(&cxl_cper_work_lock); + guard(raw_spinlock_irqsave)(&cxl_cper_work_lock); if (!cxl_cper_work) return; @@ -856,10 +864,11 @@ static void cxl_cper_post_event(enum cxl_event_type event_type, int cxl_cper_register_work(struct work_struct *work) { - if (cxl_cper_work) + guard(raw_spinlock_irqsave)(&cxl_cper_work_lock); + if (WARN_ONCE(cxl_cper_work, + "CXL CPER kfifo consumer already registered\n")) return -EINVAL; - guard(spinlock)(&cxl_cper_work_lock); cxl_cper_work = work; return 0; } @@ -867,11 +876,18 @@ EXPORT_SYMBOL_NS_GPL(cxl_cper_register_work, "CXL"); int cxl_cper_unregister_work(struct work_struct *work) { - if (cxl_cper_work != work) - return -EINVAL; + scoped_guard(raw_spinlock_irqsave, &cxl_cper_work_lock) { + if (WARN_ONCE(cxl_cper_work != work, + "CXL CPER kfifo consumer mismatch on unregister\n")) + return -EINVAL; + cxl_cper_work = NULL; + } + + cancel_work_sync(work); + + /* Discard stale entries so they are not replayed on next module load */ + kfifo_reset(&cxl_cper_fifo); - guard(spinlock)(&cxl_cper_work_lock); - cxl_cper_work = NULL; return 0; } EXPORT_SYMBOL_NS_GPL(cxl_cper_unregister_work, "CXL"); diff --git a/drivers/acpi/pfr_update.c b/drivers/acpi/pfr_update.c index 6283105bb0e8..9afd2c52fdbd 100644 --- a/drivers/acpi/pfr_update.c +++ b/drivers/acpi/pfr_update.c @@ -120,7 +120,7 @@ static int query_capability(struct pfru_update_cap_info *cap_hdr, struct pfru_device *pfru_dev) { acpi_handle handle = ACPI_HANDLE(pfru_dev->parent_dev); - union acpi_object *out_obj; + union acpi_object *out_obj, *elem; int ret = -EINVAL; out_obj = acpi_evaluate_dsm_typed(handle, &pfru_guid, @@ -150,7 +150,9 @@ static int query_capability(struct pfru_update_cap_info *cap_hdr, goto free_acpi_buffer; } - cap_hdr->status = out_obj->package.elements[CAP_STATUS_IDX].integer.value; + elem = out_obj->package.elements; + + cap_hdr->status = elem[CAP_STATUS_IDX].integer.value; if (cap_hdr->status != DSM_SUCCEED) { ret = -EBUSY; dev_dbg(pfru_dev->parent_dev, "Query cap Error Status:%d\n", @@ -158,29 +160,30 @@ static int query_capability(struct pfru_update_cap_info *cap_hdr, goto free_acpi_buffer; } - cap_hdr->update_cap = out_obj->package.elements[CAP_UPDATE_IDX].integer.value; + if (elem[CAP_CODE_TYPE_IDX].buffer.length > sizeof(cap_hdr->code_type) || + elem[CAP_DRV_TYPE_IDX].buffer.length > sizeof(cap_hdr->drv_type) || + elem[CAP_PLAT_ID_IDX].buffer.length > sizeof(cap_hdr->platform_id) || + elem[CAP_OEM_ID_IDX].buffer.length > sizeof(cap_hdr->oem_id)) + goto free_acpi_buffer; + + cap_hdr->update_cap = elem[CAP_UPDATE_IDX].integer.value; memcpy(&cap_hdr->code_type, - out_obj->package.elements[CAP_CODE_TYPE_IDX].buffer.pointer, - out_obj->package.elements[CAP_CODE_TYPE_IDX].buffer.length); - cap_hdr->fw_version = - out_obj->package.elements[CAP_FW_VER_IDX].integer.value; - cap_hdr->code_rt_version = - out_obj->package.elements[CAP_CODE_RT_VER_IDX].integer.value; + elem[CAP_CODE_TYPE_IDX].buffer.pointer, + elem[CAP_CODE_TYPE_IDX].buffer.length); + cap_hdr->fw_version = elem[CAP_FW_VER_IDX].integer.value; + cap_hdr->code_rt_version = elem[CAP_CODE_RT_VER_IDX].integer.value; memcpy(&cap_hdr->drv_type, - out_obj->package.elements[CAP_DRV_TYPE_IDX].buffer.pointer, - out_obj->package.elements[CAP_DRV_TYPE_IDX].buffer.length); - cap_hdr->drv_rt_version = - out_obj->package.elements[CAP_DRV_RT_VER_IDX].integer.value; - cap_hdr->drv_svn = - out_obj->package.elements[CAP_DRV_SVN_IDX].integer.value; + elem[CAP_DRV_TYPE_IDX].buffer.pointer, + elem[CAP_DRV_TYPE_IDX].buffer.length); + cap_hdr->drv_rt_version = elem[CAP_DRV_RT_VER_IDX].integer.value; + cap_hdr->drv_svn = elem[CAP_DRV_SVN_IDX].integer.value; memcpy(&cap_hdr->platform_id, - out_obj->package.elements[CAP_PLAT_ID_IDX].buffer.pointer, - out_obj->package.elements[CAP_PLAT_ID_IDX].buffer.length); + elem[CAP_PLAT_ID_IDX].buffer.pointer, + elem[CAP_PLAT_ID_IDX].buffer.length); memcpy(&cap_hdr->oem_id, - out_obj->package.elements[CAP_OEM_ID_IDX].buffer.pointer, - out_obj->package.elements[CAP_OEM_ID_IDX].buffer.length); - cap_hdr->oem_info_len = - out_obj->package.elements[CAP_OEM_INFO_IDX].buffer.length; + elem[CAP_OEM_ID_IDX].buffer.pointer, + elem[CAP_OEM_ID_IDX].buffer.length); + cap_hdr->oem_info_len = elem[CAP_OEM_INFO_IDX].buffer.length; ret = 0; diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index 55299f28b123..8df501fa8def 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -3534,17 +3534,13 @@ static unsigned int ata_scsi_pass_thru(struct ata_queued_cmd *qc) static size_t ata_format_dsm_trim_descr(struct scsi_cmnd *cmd, u32 trmax, u64 sector, u32 count) { - struct scsi_device *sdp = cmd->device; - size_t len = sdp->sector_size; + size_t len = ATA_SECT_SIZE; size_t r; __le64 *buf; u32 i = 0; unsigned long flags; - WARN_ON(len > ATA_SCSI_RBUF_SIZE); - - if (len > ATA_SCSI_RBUF_SIZE) - len = ATA_SCSI_RBUF_SIZE; + BUILD_BUG_ON(ATA_SECT_SIZE > ATA_SCSI_RBUF_SIZE); spin_lock_irqsave(&ata_scsi_rbuf_lock, flags); buf = ((void *)ata_scsi_rbuf); @@ -3579,13 +3575,11 @@ static unsigned int ata_scsi_write_same_xlat(struct ata_queued_cmd *qc) { struct ata_taskfile *tf = &qc->tf; struct scsi_cmnd *scmd = qc->scsicmd; - struct scsi_device *sdp = scmd->device; - size_t len = sdp->sector_size; struct ata_device *dev = qc->dev; const u8 *cdb = scmd->cmnd; u64 block; u32 n_block; - const u32 trmax = len >> 3; + const u32 trmax = ATA_MAX_TRIM_RNUM; u32 size; u16 fp; u8 bp = 0xff; @@ -3629,13 +3623,13 @@ static unsigned int ata_scsi_write_same_xlat(struct ata_queued_cmd *qc) goto invalid_param_len; /* - * size must match sector size in bytes - * For DATA SET MANAGEMENT TRIM in ACS-2 nsect (aka count) - * is defined as number of 512 byte blocks to be transferred. + * The TRIM descriptor is a single 512-byte page, which is the maximum + * WRITE SAME length advertised in the Block Limits VPD page. For DATA + * SET MANAGEMENT TRIM the COUNT field (aka nsect) is the number of + * 512-byte blocks to be transferred. */ - size = ata_format_dsm_trim_descr(scmd, trmax, block, n_block); - if (size != len) + if (size != ATA_SECT_SIZE) goto invalid_param_len; if (ata_ncq_enabled(dev) && ata_fpdma_dsm_supported(dev)) { @@ -3661,6 +3655,12 @@ static unsigned int ata_scsi_write_same_xlat(struct ata_queued_cmd *qc) ATA_TFLAG_WRITE; ata_qc_set_pc_nbytes(qc); + /* + * The DSM TRIM payload is a single 512-byte page, which may be smaller + * than the WRITE SAME data-out buffer (one logical block); only + * transfer that page so the length matches the COUNT field. + */ + qc->nbytes = size; return 0; diff --git a/drivers/auxdisplay/charlcd.c b/drivers/auxdisplay/charlcd.c index 09020bb8ad15..ae2692ec3963 100644 --- a/drivers/auxdisplay/charlcd.c +++ b/drivers/auxdisplay/charlcd.c @@ -595,6 +595,16 @@ static int charlcd_init(struct charlcd *lcd) return 0; } +static void charlcd_deinit(struct charlcd *lcd) +{ + struct charlcd_priv *priv = charlcd_to_priv(lcd); + + if (lcd->ops->backlight) { + cancel_delayed_work_sync(&priv->bl_work); + lcd->ops->backlight(lcd, CHARLCD_OFF); + } +} + struct charlcd *charlcd_alloc(unsigned int drvdata_size) { struct charlcd_priv *priv; @@ -654,8 +664,10 @@ int charlcd_register(struct charlcd *lcd) return ret; ret = misc_register(&charlcd_dev); - if (ret) + if (ret) { + charlcd_deinit(lcd); return ret; + } the_charlcd = lcd; register_reboot_notifier(&panel_notifier); @@ -665,16 +677,11 @@ EXPORT_SYMBOL_GPL(charlcd_register); int charlcd_unregister(struct charlcd *lcd) { - struct charlcd_priv *priv = charlcd_to_priv(lcd); - unregister_reboot_notifier(&panel_notifier); charlcd_puts(lcd, "\x0cLCD driver unloaded.\x1b[Lc\x1b[Lb\x1b[L-"); misc_deregister(&charlcd_dev); the_charlcd = NULL; - if (lcd->ops->backlight) { - cancel_delayed_work_sync(&priv->bl_work); - priv->lcd.ops->backlight(&priv->lcd, CHARLCD_OFF); - } + charlcd_deinit(lcd); return 0; } diff --git a/drivers/base/arch_numa.c b/drivers/base/arch_numa.c index c99f2ab105e5..a36c939b8e90 100644 --- a/drivers/base/arch_numa.c +++ b/drivers/base/arch_numa.c @@ -105,6 +105,18 @@ static void __init setup_node_to_cpumask_map(void) if (nr_node_ids == MAX_NUMNODES) setup_nr_node_ids(); + /* + * This check should never be true but it makes it clear to compilers + * that node_to_cpumask_map is bound by nr_node_ids, avoiding false + * positive fortify warnings when accessing node_to_cpumask_map in the + * for loop below. + */ + if (unlikely(nr_node_ids > MAX_NUMNODES)) { + pr_err("nr_node_ids (%u) is larger than MAX_NUMNODES (%u)\n", + nr_node_ids, MAX_NUMNODES); + return; + } + /* allocate and clear the mapping */ for (node = 0; node < nr_node_ids; node++) { alloc_bootmem_cpumask_var(&node_to_cpumask_map[node]); diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c index 13c2c48e587f..12e12e16047f 100644 --- a/drivers/base/power/main.c +++ b/drivers/base/power/main.c @@ -2161,6 +2161,7 @@ unlock: if (ret < 0) { suspend_report_result(dev, callback, ret); + pm_runtime_unblock(dev); pm_runtime_put(dev); return ret; } diff --git a/drivers/base/property.c b/drivers/base/property.c index b2dc2bd7e5ac..bdaaf833aa26 100644 --- a/drivers/base/property.c +++ b/drivers/base/property.c @@ -797,18 +797,31 @@ struct fwnode_handle * fwnode_get_next_child_node(const struct fwnode_handle *fwnode, struct fwnode_handle *child) { + const struct fwnode_handle *parent; + struct fwnode_handle *child_parent __free(fwnode_handle) = NULL; struct fwnode_handle *next; - if (IS_ERR_OR_NULL(fwnode)) + /* + * If this function is in a loop and the previous iteration returned + * an child from fwnode->secondary, then we need to use the secondary + * as parent rather than @fwnode. + */ + if (child) { + child_parent = fwnode_get_parent(child); + parent = child_parent; + } else { + parent = fwnode; + } + if (IS_ERR_OR_NULL(parent)) return NULL; /* Try to find a child in primary fwnode */ - next = fwnode_call_ptr_op(fwnode, get_next_child_node, child); + next = fwnode_call_ptr_op(parent, get_next_child_node, child); if (next) return next; /* When no more children in primary, continue with secondary */ - return fwnode_call_ptr_op(fwnode->secondary, get_next_child_node, child); + return fwnode_get_next_child_node(parent->secondary, NULL); } EXPORT_SYMBOL_GPL(fwnode_get_next_child_node); diff --git a/drivers/block/zloop.c b/drivers/block/zloop.c index 26364e43aeb3..45088c163286 100644 --- a/drivers/block/zloop.c +++ b/drivers/block/zloop.c @@ -319,7 +319,8 @@ static int zloop_finish_zone(struct zloop_device *zlo, unsigned int zone_no) zone->cond == BLK_ZONE_COND_FULL) goto unlock; - if (vfs_truncate(&zone->file->f_path, zlo->zone_size << SECTOR_SHIFT)) { + if (vfs_truncate(&zone->file->f_path, + zlo->zone_capacity << SECTOR_SHIFT)) { set_bit(ZLOOP_ZONE_SEQ_ERROR, &zone->flags); ret = -EIO; goto unlock; diff --git a/drivers/block/zram/backend_deflate.c b/drivers/block/zram/backend_deflate.c index b75016e0e654..fd438dcdfad6 100644 --- a/drivers/block/zram/backend_deflate.c +++ b/drivers/block/zram/backend_deflate.c @@ -24,8 +24,16 @@ static int deflate_setup_params(struct zcomp_params *params) { if (params->level == ZCOMP_PARAM_NOT_SET) params->level = Z_DEFAULT_COMPRESSION; - if (params->deflate.winbits == ZCOMP_PARAM_NOT_SET) + if (params->deflate.winbits == ZCOMP_PARAM_NOT_SET) { params->deflate.winbits = DEFLATE_DEF_WINBITS; + } else { + s32 wb = params->deflate.winbits; + + if ((wb < -15 || wb > -9) && (wb < 9 || wb > 15)) { + pr_err("invalid deflate winbits: %d\n", wb); + return -EINVAL; + } + } return 0; } diff --git a/drivers/bluetooth/btrtl.c b/drivers/bluetooth/btrtl.c index cb1c321910e2..a62eae7276d6 100644 --- a/drivers/bluetooth/btrtl.c +++ b/drivers/bluetooth/btrtl.c @@ -1331,19 +1331,6 @@ void btrtl_set_quirks(struct hci_dev *hdev, struct btrtl_device_info *btrtl_dev) if (!btrtl_dev->ic_info) return; - switch (btrtl_dev->project_id) { - case CHIP_ID_8761B: - /* RTL8761B/BU reports HCI version 5.1 but does not support - * the LE Extended Scan commands (Opcode 0x2042), causing - * repeated -EBUSY failures when BlueZ attempts extended - * scanning while a connection is active. - */ - hci_set_quirk(hdev, HCI_QUIRK_BROKEN_EXT_SCAN); - break; - default: - break; - } - switch (btrtl_dev->ic_info->lmp_subver) { case RTL_ROM_LMP_8703B: /* 8723CS reports two pages for local ext features, diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index ea9df7dc2316..a869fd15bc89 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -67,6 +67,7 @@ static struct usb_driver btusb_driver; #define BTUSB_INTEL_NO_WBS_SUPPORT BIT(26) #define BTUSB_ACTIONS_SEMI BIT(27) #define BTUSB_BARROT BIT(28) +#define BTUSB_BROKEN_EXT_SCAN BIT(29) static const struct usb_device_id btusb_table[] = { /* Generic Bluetooth USB device */ @@ -608,6 +609,10 @@ static const struct usb_device_id quirks_table[] = { { USB_DEVICE(0x0489, 0xe130), .driver_info = BTUSB_REALTEK | BTUSB_WIDEBAND_SPEECH }, + /* Realtek 8761BU Bluetooth devices */ + { USB_DEVICE(0x0bda, 0xa728), .driver_info = BTUSB_REALTEK | + BTUSB_BROKEN_EXT_SCAN }, + /* Realtek Bluetooth devices */ { USB_VENDOR_AND_INTERFACE_INFO(0x0bda, 0xe0, 0x01, 0x01), .driver_info = BTUSB_REALTEK }, @@ -805,6 +810,12 @@ static const struct usb_device_id quirks_table[] = { { USB_DEVICE(0x37ad, 0x0600), .driver_info = BTUSB_REALTEK | BTUSB_WIDEBAND_SPEECH }, + /* Additional Realtek 8761CU Bluetooth devices */ + { USB_DEVICE(0x0b05, 0x1bef), .driver_info = BTUSB_REALTEK | + BTUSB_WIDEBAND_SPEECH }, + { USB_DEVICE(0x0b05, 0x1d70), .driver_info = BTUSB_REALTEK | + BTUSB_WIDEBAND_SPEECH }, + /* Additional Realtek 8821AE Bluetooth devices */ { USB_DEVICE(0x0b05, 0x17dc), .driver_info = BTUSB_REALTEK }, { USB_DEVICE(0x13d3, 0x3414), .driver_info = BTUSB_REALTEK }, @@ -4319,6 +4330,9 @@ static int btusb_probe(struct usb_interface *intf, if (id->driver_info & BTUSB_INVALID_LE_STATES) hci_set_quirk(hdev, HCI_QUIRK_BROKEN_LE_STATES); + if (id->driver_info & BTUSB_BROKEN_EXT_SCAN) + hci_set_quirk(hdev, HCI_QUIRK_BROKEN_EXT_SCAN); + if (id->driver_info & BTUSB_DIGIANSWER) { data->cmdreq_type = USB_TYPE_VENDOR; hci_set_quirk(hdev, HCI_QUIRK_RESET_ON_CLOSE); diff --git a/drivers/bluetooth/hci_bcm.c b/drivers/bluetooth/hci_bcm.c index fff845ed44e3..0a54a7cf2bde 100644 --- a/drivers/bluetooth/hci_bcm.c +++ b/drivers/bluetooth/hci_bcm.c @@ -548,6 +548,7 @@ static int bcm_close(struct hci_uart *hu) if (IS_ENABLED(CONFIG_PM) && bdev->irq_acquired) { devm_free_irq(bdev->dev, bdev->irq, bdev); device_init_wakeup(bdev->dev, false); + pm_runtime_dont_use_autosuspend(bdev->dev); pm_runtime_disable(bdev->dev); } diff --git a/drivers/bluetooth/hci_bcm4377.c b/drivers/bluetooth/hci_bcm4377.c index 45e6d84224ee..1d41401f3dba 100644 --- a/drivers/bluetooth/hci_bcm4377.c +++ b/drivers/bluetooth/hci_bcm4377.c @@ -2486,6 +2486,7 @@ static const struct bcm4377_hw bcm4377_hw_variants[] = { .has_bar0_core2_window2 = true, .broken_mws_transport_config = true, .broken_le_coded = true, + .broken_le_ext_adv_report_phy = true, .send_calibration = bcm4378_send_calibration, .send_ptb = bcm4378_send_ptb, }, diff --git a/drivers/bluetooth/hci_h5.c b/drivers/bluetooth/hci_h5.c index d0d4420c1a0f..9da2be1f3cc9 100644 --- a/drivers/bluetooth/hci_h5.c +++ b/drivers/bluetooth/hci_h5.c @@ -987,8 +987,10 @@ static void h5_btrtl_open(struct h5 *h5) static void h5_btrtl_close(struct h5 *h5) { - if (!test_bit(H5_WAKEUP_DISABLE, &h5->flags)) + if (!test_bit(H5_WAKEUP_DISABLE, &h5->flags)) { + pm_runtime_dont_use_autosuspend(&h5->hu->serdev->dev); pm_runtime_disable(&h5->hu->serdev->dev); + } gpiod_set_value_cansleep(h5->device_wake_gpio, 0); gpiod_set_value_cansleep(h5->enable_gpio, 0); diff --git a/drivers/bluetooth/hci_intel.c b/drivers/bluetooth/hci_intel.c index 1d6e09508f1f..4d52b1d3d8fe 100644 --- a/drivers/bluetooth/hci_intel.c +++ b/drivers/bluetooth/hci_intel.c @@ -348,6 +348,7 @@ static int intel_set_power(struct hci_uart *hu, bool powered) devm_free_irq(&idev->pdev->dev, idev->irq, idev); device_wakeup_disable(&idev->pdev->dev); + pm_runtime_dont_use_autosuspend(&idev->pdev->dev); pm_runtime_disable(&idev->pdev->dev); } } diff --git a/drivers/bluetooth/hci_ldisc.c b/drivers/bluetooth/hci_ldisc.c index c27413a371c2..55e0dceee54a 100644 --- a/drivers/bluetooth/hci_ldisc.c +++ b/drivers/bluetooth/hci_ldisc.c @@ -451,7 +451,7 @@ static int hci_uart_setup(struct hci_dev *hdev) if (IS_ERR(skb)) { BT_ERR("%s: Reading local version information failed (%ld)", hdev->name, PTR_ERR(skb)); - return 0; + return PTR_ERR(skb); } if (skb->len != sizeof(*ver)) { diff --git a/drivers/bluetooth/hci_serdev.c b/drivers/bluetooth/hci_serdev.c index 593d9cefbbf9..d2eaf2f12aa2 100644 --- a/drivers/bluetooth/hci_serdev.c +++ b/drivers/bluetooth/hci_serdev.c @@ -221,7 +221,7 @@ static int hci_uart_setup(struct hci_dev *hdev) if (IS_ERR(skb)) { bt_dev_err(hdev, "Reading local version info failed (%ld)", PTR_ERR(skb)); - return 0; + return PTR_ERR(skb); } if (skb->len != sizeof(*ver)) diff --git a/drivers/cdx/cdx.c b/drivers/cdx/cdx.c index 9d6d24f49938..a066e0105c77 100644 --- a/drivers/cdx/cdx.c +++ b/drivers/cdx/cdx.c @@ -745,7 +745,6 @@ static int cdx_create_res_attr(struct cdx_device *cdx_dev, int num) sysfs_bin_attr_init(res_attr); - cdx_dev->res_attr[num] = res_attr; sprintf(res_attr_name, "resource%d", num); res_attr->mmap = cdx_mmap_resource; @@ -754,8 +753,12 @@ static int cdx_create_res_attr(struct cdx_device *cdx_dev, int num) res_attr->size = cdx_resource_len(cdx_dev, num); res_attr->private = (void *)(unsigned long)num; ret = sysfs_create_bin_file(&cdx_dev->dev.kobj, res_attr); - if (ret) + if (ret) { kfree(res_attr); + return ret; + } + + cdx_dev->res_attr[num] = res_attr; return ret; } diff --git a/drivers/char/hw_random/stm32-rng.c b/drivers/char/hw_random/stm32-rng.c index 9a8c00586ab0..f5bfe54c01dc 100644 --- a/drivers/char/hw_random/stm32-rng.c +++ b/drivers/char/hw_random/stm32-rng.c @@ -368,11 +368,6 @@ static int stm32_rng_init(struct hwrng *rng) return 0; } -static void stm32_rng_remove(struct platform_device *ofdev) -{ - pm_runtime_disable(&ofdev->dev); -} - static int __maybe_unused stm32_rng_runtime_suspend(struct device *dev) { struct stm32_rng_private *priv = dev_get_drvdata(dev); @@ -590,7 +585,9 @@ static int stm32_rng_probe(struct platform_device *ofdev) pm_runtime_set_autosuspend_delay(dev, 100); pm_runtime_use_autosuspend(dev); - pm_runtime_enable(dev); + ret = devm_pm_runtime_enable(dev); + if (ret) + return ret; return devm_hwrng_register(dev, &priv->rng); } @@ -602,7 +599,6 @@ static struct platform_driver stm32_rng_driver = { .of_match_table = stm32_rng_match, }, .probe = stm32_rng_probe, - .remove = stm32_rng_remove, }; module_platform_driver(stm32_rng_driver); diff --git a/drivers/char/ipmi/ipmb_dev_int.c b/drivers/char/ipmi/ipmb_dev_int.c index ee2bdc7ed0da..bc0564d87867 100644 --- a/drivers/char/ipmi/ipmb_dev_int.c +++ b/drivers/char/ipmi/ipmb_dev_int.c @@ -141,13 +141,14 @@ static ssize_t ipmb_write(struct file *file, const char __user *buf, u8 msg[MAX_MSG_LEN]; ssize_t ret; - if (count > sizeof(msg)) + if (!count || count > sizeof(msg)) return -EINVAL; if (copy_from_user(&msg, buf, count)) return -EFAULT; - if (count < msg[0]) + if (msg[IPMB_MSG_LEN_IDX] < IPMB_REQUEST_LEN_MIN || + count < (size_t)msg[IPMB_MSG_LEN_IDX] + 1) return -EINVAL; rq_sa = GET_7BIT_ADDR(msg[RQ_SA_8BIT_IDX]); diff --git a/drivers/char/ipmi/ipmi_msghandler.c b/drivers/char/ipmi/ipmi_msghandler.c index 51f76d755f98..0247079db185 100644 --- a/drivers/char/ipmi/ipmi_msghandler.c +++ b/drivers/char/ipmi/ipmi_msghandler.c @@ -1393,6 +1393,7 @@ static void _ipmi_destroy_user(struct ipmi_user *user) } } mutex_unlock(&intf->cmd_rcvrs_mutex); + synchronize_rcu(); while (rcvrs) { rcvr = rcvrs; rcvrs = rcvr->next; @@ -3740,6 +3741,7 @@ int ipmi_add_smi(struct module *owner, sysfs_attr_init(&intf->maintenance_mode_devattr.attr); rv = device_create_file(intf->si_dev, &intf->maintenance_mode_devattr); if (rv) { + device_remove_file(intf->si_dev, &intf->nr_msgs_devattr); device_remove_file(intf->si_dev, &intf->nr_users_devattr); goto out_err_bmc_reg; } @@ -3757,12 +3759,14 @@ int ipmi_add_smi(struct module *owner, out_err_bmc_reg: ipmi_bmc_unregister(intf); out_err_started: + intf->in_shutdown = true; if (intf->handlers->shutdown) intf->handlers->shutdown(intf->send_info); out_err: list_del(&intf->link); mutex_unlock(&ipmi_interfaces_mutex); mutex_unlock(&smi_watchers_mutex); + cancel_work_sync(&intf->smi_work); kref_put(&intf->refcount, intf_free); return rv; diff --git a/drivers/char/tpm/tpm_i2c_nuvoton.c b/drivers/char/tpm/tpm_i2c_nuvoton.c index d44903b29929..aa3673002f3a 100644 --- a/drivers/char/tpm/tpm_i2c_nuvoton.c +++ b/drivers/char/tpm/tpm_i2c_nuvoton.c @@ -182,8 +182,10 @@ static int i2c_nuvoton_wait_for_stat(struct tpm_chip *chip, u8 mask, u8 value, timeout); if (rc > 0) return 0; - /* At this point we know that the SINT pin is asserted, so we - * do not need to do i2c_nuvoton_check_status */ + + disable_irq(priv->irq); + if (rc < 0) + return rc; } else { unsigned long ten_msec, stop; bool status_valid; diff --git a/drivers/clocksource/timer-nxp-pit.c b/drivers/clocksource/timer-nxp-pit.c index d1740f18f718..2cf3b4ca6e1f 100644 --- a/drivers/clocksource/timer-nxp-pit.c +++ b/drivers/clocksource/timer-nxp-pit.c @@ -328,8 +328,10 @@ static int pit_timer_init(struct device_node *np) if (pit_instances == max_pit_instances) { ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "PIT timer:starting", pit_clockevent_starting_cpu, NULL); - if (ret < 0) + if (ret < 0) { + pit_clockevent_per_cpu_exit(pit, pit_instances); goto out_pit_clocksource_unregister; + } } return 0; diff --git a/drivers/clocksource/timer-sun4i.c b/drivers/clocksource/timer-sun4i.c index 7bdcc60ad43c..c2d04ab7cf2d 100644 --- a/drivers/clocksource/timer-sun4i.c +++ b/drivers/clocksource/timer-sun4i.c @@ -208,7 +208,7 @@ static int __init sun4i_timer_init(struct device_node *node) sun4i_timer_clear_interrupt(timer_of_base(&to)); clockevents_config_and_register(&to.clkevt, timer_of_rate(&to), - TIMER_SYNC_TICKS, 0xffffffff); + TIMER_SYNC_TICKS + 1, 0xffffffff); /* Enable timer0 interrupt */ val = readl(timer_of_base(&to) + TIMER_IRQ_EN_REG); diff --git a/drivers/crypto/allwinner/Kconfig b/drivers/crypto/allwinner/Kconfig index 06ea0e9fe6f2..d86ae005fbe2 100644 --- a/drivers/crypto/allwinner/Kconfig +++ b/drivers/crypto/allwinner/Kconfig @@ -70,14 +70,6 @@ config CRYPTO_DEV_SUN8I_CE_HASH help Say y to enable support for hash algorithms. -config CRYPTO_DEV_SUN8I_CE_PRNG - bool "Support for Allwinner Crypto Engine PRNG" - depends on CRYPTO_DEV_SUN8I_CE - select CRYPTO_RNG - help - Select this option if you want to provide kernel-side support for - the Pseudo-Random Number Generator found in the Crypto Engine. - config CRYPTO_DEV_SUN8I_CE_TRNG bool "Support for Allwinner Crypto Engine TRNG" depends on CRYPTO_DEV_SUN8I_CE @@ -113,14 +105,6 @@ config CRYPTO_DEV_SUN8I_SS_DEBUG This will create /sys/kernel/debug/sun8i-ss/stats for displaying the number of requests per flow and per algorithm. -config CRYPTO_DEV_SUN8I_SS_PRNG - bool "Support for Allwinner Security System PRNG" - depends on CRYPTO_DEV_SUN8I_SS - select CRYPTO_RNG - help - Select this option if you want to provide kernel-side support for - the Pseudo-Random Number Generator found in the Security System. - config CRYPTO_DEV_SUN8I_SS_HASH bool "Enable support for hash on sun8i-ss" depends on CRYPTO_DEV_SUN8I_SS diff --git a/drivers/crypto/allwinner/sun8i-ce/Makefile b/drivers/crypto/allwinner/sun8i-ce/Makefile index 0842eb2d9408..ea708b427e2e 100644 --- a/drivers/crypto/allwinner/sun8i-ce/Makefile +++ b/drivers/crypto/allwinner/sun8i-ce/Makefile @@ -1,5 +1,4 @@ obj-$(CONFIG_CRYPTO_DEV_SUN8I_CE) += sun8i-ce.o sun8i-ce-y += sun8i-ce-core.o sun8i-ce-cipher.o sun8i-ce-$(CONFIG_CRYPTO_DEV_SUN8I_CE_HASH) += sun8i-ce-hash.o -sun8i-ce-$(CONFIG_CRYPTO_DEV_SUN8I_CE_PRNG) += sun8i-ce-prng.o sun8i-ce-$(CONFIG_CRYPTO_DEV_SUN8I_CE_TRNG) += sun8i-ce-trng.o diff --git a/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-core.c b/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-core.c index c16bb6ce6ee3..ef6f601c6259 100644 --- a/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-core.c +++ b/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-core.c @@ -12,7 +12,6 @@ #include <crypto/engine.h> #include <crypto/internal/hash.h> -#include <crypto/internal/rng.h> #include <crypto/internal/skcipher.h> #include <linux/clk.h> #include <linux/delay.h> @@ -49,7 +48,6 @@ static const struct ce_variant ce_h3_variant = { { "mod", 50000000, 0 }, }, .esr = ESR_H3, - .prng = CE_ALG_PRNG, .trng = CE_ID_NOTSUPP, }; @@ -66,7 +64,6 @@ static const struct ce_variant ce_h5_variant = { { "mod", 300000000, 0 }, }, .esr = ESR_H5, - .prng = CE_ALG_PRNG, .trng = CE_ID_NOTSUPP, }; @@ -80,7 +77,6 @@ static const struct ce_variant ce_h6_variant = { }, .cipher_t_dlen_in_bytes = true, .hash_t_dlen_in_bits = true, - .prng_t_dlen_in_bytes = true, .trng_t_dlen_in_bytes = true, .ce_clks = { { "bus", 0, 200000000 }, @@ -88,7 +84,6 @@ static const struct ce_variant ce_h6_variant = { { "ram", 0, 400000000 }, }, .esr = ESR_H6, - .prng = CE_ALG_PRNG_V2, .trng = CE_ALG_TRNG_V2, }; @@ -102,7 +97,6 @@ static const struct ce_variant ce_h616_variant = { }, .cipher_t_dlen_in_bytes = true, .hash_t_dlen_in_bits = true, - .prng_t_dlen_in_bytes = true, .trng_t_dlen_in_bytes = true, .needs_word_addresses = true, .ce_clks = { @@ -112,7 +106,6 @@ static const struct ce_variant ce_h616_variant = { { "trng", 0, 0 }, }, .esr = ESR_H6, - .prng = CE_ALG_PRNG_V2, .trng = CE_ALG_TRNG_V2, }; @@ -129,7 +122,6 @@ static const struct ce_variant ce_a64_variant = { { "mod", 300000000, 0 }, }, .esr = ESR_A64, - .prng = CE_ALG_PRNG, .trng = CE_ID_NOTSUPP, }; @@ -148,7 +140,6 @@ static const struct ce_variant ce_d1_variant = { { "trng", 0, 0 }, }, .esr = ESR_D1, - .prng = CE_ALG_PRNG, .trng = CE_ALG_TRNG, }; @@ -165,7 +156,6 @@ static const struct ce_variant ce_r40_variant = { { "mod", 300000000, 0 }, }, .esr = ESR_R40, - .prng = CE_ALG_PRNG, .trng = CE_ID_NOTSUPP, }; @@ -614,25 +604,6 @@ static struct sun8i_ce_alg_template ce_algs[] = { }, }, #endif -#ifdef CONFIG_CRYPTO_DEV_SUN8I_CE_PRNG -{ - .type = CRYPTO_ALG_TYPE_RNG, - .alg.rng = { - .base = { - .cra_name = "stdrng", - .cra_driver_name = "sun8i-ce-prng", - .cra_priority = 300, - .cra_ctxsize = sizeof(struct sun8i_ce_rng_tfm_ctx), - .cra_module = THIS_MODULE, - .cra_init = sun8i_ce_prng_init, - .cra_exit = sun8i_ce_prng_exit, - }, - .generate = sun8i_ce_prng_generate, - .seed = sun8i_ce_prng_seed, - .seedsize = PRNG_SEED_SIZE, - } -}, -#endif }; static int sun8i_ce_debugfs_show(struct seq_file *seq, void *v) @@ -692,12 +663,6 @@ static int sun8i_ce_debugfs_show(struct seq_file *seq, void *v) seq_printf(seq, "\tFallback due to SG numbers: %lu\n", ce_algs[i].stat_fb_maxsg); break; - case CRYPTO_ALG_TYPE_RNG: - seq_printf(seq, "%s %s reqs=%lu bytes=%lu\n", - ce_algs[i].alg.rng.base.cra_driver_name, - ce_algs[i].alg.rng.base.cra_name, - ce_algs[i].stat_req, ce_algs[i].stat_bytes); - break; } } #if defined(CONFIG_CRYPTO_DEV_SUN8I_CE_TRNG) && \ @@ -925,23 +890,6 @@ static int sun8i_ce_register_algs(struct sun8i_ce_dev *ce) return err; } break; - case CRYPTO_ALG_TYPE_RNG: - if (ce->variant->prng == CE_ID_NOTSUPP) { - dev_info(ce->dev, - "DEBUG: Algo of %s not supported\n", - ce_algs[i].alg.rng.base.cra_name); - ce_algs[i].ce = NULL; - break; - } - dev_info(ce->dev, "Register %s\n", - ce_algs[i].alg.rng.base.cra_name); - err = crypto_register_rng(&ce_algs[i].alg.rng); - if (err) { - dev_err(ce->dev, "Fail to register %s\n", - ce_algs[i].alg.rng.base.cra_name); - ce_algs[i].ce = NULL; - } - break; default: ce_algs[i].ce = NULL; dev_err(ce->dev, "ERROR: tried to register an unknown algo\n"); @@ -968,11 +916,6 @@ static void sun8i_ce_unregister_algs(struct sun8i_ce_dev *ce) ce_algs[i].alg.hash.base.halg.base.cra_name); crypto_engine_unregister_ahash(&ce_algs[i].alg.hash); break; - case CRYPTO_ALG_TYPE_RNG: - dev_info(ce->dev, "Unregister %d %s\n", i, - ce_algs[i].alg.rng.base.cra_name); - crypto_unregister_rng(&ce_algs[i].alg.rng); - break; } } } diff --git a/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-prng.c b/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-prng.c deleted file mode 100644 index d0a1ac66738b..000000000000 --- a/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-prng.c +++ /dev/null @@ -1,159 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * sun8i-ce-prng.c - hardware cryptographic offloader for - * Allwinner H3/A64/H5/H2+/H6/R40 SoC - * - * Copyright (C) 2015-2020 Corentin Labbe <clabbe@baylibre.com> - * - * This file handle the PRNG - * - * You could find a link for the datasheet in Documentation/arch/arm/sunxi.rst - */ -#include "sun8i-ce.h" -#include <linux/dma-mapping.h> -#include <linux/pm_runtime.h> -#include <crypto/internal/rng.h> - -int sun8i_ce_prng_init(struct crypto_tfm *tfm) -{ - struct sun8i_ce_rng_tfm_ctx *ctx = crypto_tfm_ctx(tfm); - - memset(ctx, 0, sizeof(struct sun8i_ce_rng_tfm_ctx)); - return 0; -} - -void sun8i_ce_prng_exit(struct crypto_tfm *tfm) -{ - struct sun8i_ce_rng_tfm_ctx *ctx = crypto_tfm_ctx(tfm); - - kfree_sensitive(ctx->seed); - ctx->seed = NULL; - ctx->slen = 0; -} - -int sun8i_ce_prng_seed(struct crypto_rng *tfm, const u8 *seed, - unsigned int slen) -{ - struct sun8i_ce_rng_tfm_ctx *ctx = crypto_rng_ctx(tfm); - - if (ctx->seed && ctx->slen != slen) { - kfree_sensitive(ctx->seed); - ctx->slen = 0; - ctx->seed = NULL; - } - if (!ctx->seed) - ctx->seed = kmalloc(slen, GFP_KERNEL | GFP_DMA); - if (!ctx->seed) - return -ENOMEM; - - memcpy(ctx->seed, seed, slen); - ctx->slen = slen; - - return 0; -} - -int sun8i_ce_prng_generate(struct crypto_rng *tfm, const u8 *src, - unsigned int slen, u8 *dst, unsigned int dlen) -{ - struct sun8i_ce_rng_tfm_ctx *ctx = crypto_rng_ctx(tfm); - struct rng_alg *alg = crypto_rng_alg(tfm); - struct sun8i_ce_alg_template *algt; - struct sun8i_ce_dev *ce; - dma_addr_t dma_iv, dma_dst; - int err = 0; - int flow = 3; - unsigned int todo; - struct sun8i_ce_flow *chan; - struct ce_task *cet; - u32 common, sym; - void *d; - - algt = container_of(alg, struct sun8i_ce_alg_template, alg.rng); - ce = algt->ce; - - if (ctx->slen == 0) { - dev_err(ce->dev, "not seeded\n"); - return -EINVAL; - } - - /* we want dlen + seedsize rounded up to a multiple of PRNG_DATA_SIZE */ - todo = dlen + ctx->slen + PRNG_DATA_SIZE * 2; - todo -= todo % PRNG_DATA_SIZE; - - d = kzalloc(todo, GFP_KERNEL | GFP_DMA); - if (!d) { - err = -ENOMEM; - goto err_mem; - } - - dev_dbg(ce->dev, "%s PRNG slen=%u dlen=%u todo=%u multi=%u\n", __func__, - slen, dlen, todo, todo / PRNG_DATA_SIZE); - -#ifdef CONFIG_CRYPTO_DEV_SUN8I_CE_DEBUG - algt->stat_req++; - algt->stat_bytes += todo; -#endif - - dma_iv = dma_map_single(ce->dev, ctx->seed, ctx->slen, DMA_TO_DEVICE); - if (dma_mapping_error(ce->dev, dma_iv)) { - dev_err(ce->dev, "Cannot DMA MAP IV\n"); - err = -EFAULT; - goto err_iv; - } - - dma_dst = dma_map_single(ce->dev, d, todo, DMA_FROM_DEVICE); - if (dma_mapping_error(ce->dev, dma_dst)) { - dev_err(ce->dev, "Cannot DMA MAP DST\n"); - err = -EFAULT; - goto err_dst; - } - - err = pm_runtime_resume_and_get(ce->dev); - if (err < 0) - goto err_pm; - - mutex_lock(&ce->rnglock); - chan = &ce->chanlist[flow]; - - cet = &chan->tl[0]; - memset(cet, 0, sizeof(struct ce_task)); - - cet->t_id = cpu_to_le32(flow); - common = ce->variant->prng | CE_COMM_INT; - cet->t_common_ctl = cpu_to_le32(common); - - /* recent CE (H6) need length in bytes, in word otherwise */ - if (ce->variant->prng_t_dlen_in_bytes) - cet->t_dlen = cpu_to_le32(todo); - else - cet->t_dlen = cpu_to_le32(todo / 4); - - sym = PRNG_LD; - cet->t_sym_ctl = cpu_to_le32(sym); - cet->t_asym_ctl = 0; - - cet->t_key = desc_addr_val_le32(ce, dma_iv); - cet->t_iv = desc_addr_val_le32(ce, dma_iv); - - cet->t_dst[0].addr = desc_addr_val_le32(ce, dma_dst); - cet->t_dst[0].len = cpu_to_le32(todo / 4); - - err = sun8i_ce_run_task(ce, 3, "PRNG"); - mutex_unlock(&ce->rnglock); - - pm_runtime_put(ce->dev); - -err_pm: - dma_unmap_single(ce->dev, dma_dst, todo, DMA_FROM_DEVICE); -err_dst: - dma_unmap_single(ce->dev, dma_iv, ctx->slen, DMA_TO_DEVICE); - - if (!err) { - memcpy(dst, d, dlen); - memcpy(ctx->seed, d + dlen, ctx->slen); - } -err_iv: - kfree_sensitive(d); -err_mem: - return err; -} diff --git a/drivers/crypto/allwinner/sun8i-ce/sun8i-ce.h b/drivers/crypto/allwinner/sun8i-ce/sun8i-ce.h index 71f5a0cd3d45..468d99bf5bf6 100644 --- a/drivers/crypto/allwinner/sun8i-ce/sun8i-ce.h +++ b/drivers/crypto/allwinner/sun8i-ce/sun8i-ce.h @@ -15,7 +15,6 @@ #include <linux/hw_random.h> #include <crypto/internal/hash.h> #include <crypto/md5.h> -#include <crypto/rng.h> #include <crypto/sha1.h> #include <crypto/sha2.h> @@ -58,9 +57,7 @@ #define CE_ALG_SHA384 20 #define CE_ALG_SHA512 21 #define CE_ALG_TRNG 48 -#define CE_ALG_PRNG 49 #define CE_ALG_TRNG_V2 0x1c -#define CE_ALG_PRNG_V2 0x1d /* Used in ce_variant */ #define CE_ID_NOTSUPP 0xFF @@ -96,10 +93,6 @@ #define ESR_H6 4 #define ESR_D1 5 -#define PRNG_DATA_SIZE (160 / 8) -#define PRNG_SEED_SIZE DIV_ROUND_UP(175, 8) -#define PRNG_LD BIT(17) - #define CE_DIE_ID_SHIFT 16 #define CE_DIE_ID_MASK 0x07 @@ -136,13 +129,10 @@ struct ce_clock { * bytes or words * @hash_t_dlen_in_bytes: Does the request size for hash is in * bits or words - * @prng_t_dlen_in_bytes: Does the request size for PRNG is in - * bytes or words * @trng_t_dlen_in_bytes: Does the request size for TRNG is in * bytes or words * @ce_clks: list of clocks needed by this variant * @esr: The type of error register - * @prng: The CE_ALG_XXX value for the PRNG * @trng: The CE_ALG_XXX value for the TRNG */ struct ce_variant { @@ -151,12 +141,10 @@ struct ce_variant { u32 op_mode[CE_ID_OP_MAX]; bool cipher_t_dlen_in_bytes; bool hash_t_dlen_in_bits; - bool prng_t_dlen_in_bytes; bool trng_t_dlen_in_bytes; bool needs_word_addresses; struct ce_clock ce_clks[CE_MAX_CLOCKS]; int esr; - unsigned char prng; unsigned char trng; }; @@ -328,16 +316,6 @@ struct sun8i_ce_hash_reqctx { }; /* - * struct sun8i_ce_prng_ctx - context for PRNG TFM - * @seed: The seed to use - * @slen: The size of the seed - */ -struct sun8i_ce_rng_tfm_ctx { - void *seed; - unsigned int slen; -}; - -/* * struct sun8i_ce_alg_template - crypto_alg template * @type: the CRYPTO_ALG_TYPE for this template * @ce_algo_id: the CE_ID for this template @@ -357,7 +335,6 @@ struct sun8i_ce_alg_template { union { struct skcipher_engine_alg skcipher; struct ahash_engine_alg hash; - struct rng_alg rng; } alg; unsigned long stat_req; unsigned long stat_fb; @@ -398,11 +375,5 @@ int sun8i_ce_hash_finup(struct ahash_request *areq); int sun8i_ce_hash_digest(struct ahash_request *areq); int sun8i_ce_hash_run(struct crypto_engine *engine, void *breq); -int sun8i_ce_prng_generate(struct crypto_rng *tfm, const u8 *src, - unsigned int slen, u8 *dst, unsigned int dlen); -int sun8i_ce_prng_seed(struct crypto_rng *tfm, const u8 *seed, unsigned int slen); -void sun8i_ce_prng_exit(struct crypto_tfm *tfm); -int sun8i_ce_prng_init(struct crypto_tfm *tfm); - int sun8i_ce_hwrng_register(struct sun8i_ce_dev *ce); void sun8i_ce_hwrng_unregister(struct sun8i_ce_dev *ce); diff --git a/drivers/crypto/allwinner/sun8i-ss/Makefile b/drivers/crypto/allwinner/sun8i-ss/Makefile index aabfd893c817..2d6458a42e58 100644 --- a/drivers/crypto/allwinner/sun8i-ss/Makefile +++ b/drivers/crypto/allwinner/sun8i-ss/Makefile @@ -1,4 +1,3 @@ obj-$(CONFIG_CRYPTO_DEV_SUN8I_SS) += sun8i-ss.o sun8i-ss-y += sun8i-ss-core.o sun8i-ss-cipher.o -sun8i-ss-$(CONFIG_CRYPTO_DEV_SUN8I_SS_PRNG) += sun8i-ss-prng.o sun8i-ss-$(CONFIG_CRYPTO_DEV_SUN8I_SS_HASH) += sun8i-ss-hash.o diff --git a/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-core.c b/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-core.c index f45685707e0d..119cc15509d1 100644 --- a/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-core.c +++ b/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-core.c @@ -11,7 +11,6 @@ */ #include <crypto/engine.h> -#include <crypto/internal/rng.h> #include <crypto/internal/skcipher.h> #include <linux/clk.h> #include <linux/delay.h> @@ -283,25 +282,6 @@ static struct sun8i_ss_alg_template ss_algs[] = { .do_one_request = sun8i_ss_handle_cipher_request, }, }, -#ifdef CONFIG_CRYPTO_DEV_SUN8I_SS_PRNG -{ - .type = CRYPTO_ALG_TYPE_RNG, - .alg.rng = { - .base = { - .cra_name = "stdrng", - .cra_driver_name = "sun8i-ss-prng", - .cra_priority = 300, - .cra_ctxsize = sizeof(struct sun8i_ss_rng_tfm_ctx), - .cra_module = THIS_MODULE, - .cra_init = sun8i_ss_prng_init, - .cra_exit = sun8i_ss_prng_exit, - }, - .generate = sun8i_ss_prng_generate, - .seed = sun8i_ss_prng_seed, - .seedsize = PRNG_SEED_SIZE, - } -}, -#endif #ifdef CONFIG_CRYPTO_DEV_SUN8I_SS_HASH { .type = CRYPTO_ALG_TYPE_AHASH, .ss_algo_id = SS_ID_HASH_MD5, @@ -501,12 +481,6 @@ static int sun8i_ss_debugfs_show(struct seq_file *seq, void *v) seq_printf(seq, "\tFallback due to SG numbers: %lu\n", ss_algs[i].stat_fb_sgnum); break; - case CRYPTO_ALG_TYPE_RNG: - seq_printf(seq, "%s %s reqs=%lu tsize=%lu\n", - ss_algs[i].alg.rng.base.cra_driver_name, - ss_algs[i].alg.rng.base.cra_name, - ss_algs[i].stat_req, ss_algs[i].stat_bytes); - break; case CRYPTO_ALG_TYPE_AHASH: seq_printf(seq, "%s %s reqs=%lu fallback=%lu\n", ss_algs[i].alg.hash.base.halg.base.cra_driver_name, @@ -707,14 +681,6 @@ static int sun8i_ss_register_algs(struct sun8i_ss_dev *ss) return err; } break; - case CRYPTO_ALG_TYPE_RNG: - err = crypto_register_rng(&ss_algs[i].alg.rng); - if (err) { - dev_err(ss->dev, "Fail to register %s\n", - ss_algs[i].alg.rng.base.cra_name); - ss_algs[i].ss = NULL; - } - break; case CRYPTO_ALG_TYPE_AHASH: id = ss_algs[i].ss_algo_id; ss_method = ss->variant->alg_hash[id]; @@ -756,11 +722,6 @@ static void sun8i_ss_unregister_algs(struct sun8i_ss_dev *ss) ss_algs[i].alg.skcipher.base.base.cra_name); crypto_engine_unregister_skcipher(&ss_algs[i].alg.skcipher); break; - case CRYPTO_ALG_TYPE_RNG: - dev_info(ss->dev, "Unregister %d %s\n", i, - ss_algs[i].alg.rng.base.cra_name); - crypto_unregister_rng(&ss_algs[i].alg.rng); - break; case CRYPTO_ALG_TYPE_AHASH: dev_info(ss->dev, "Unregister %d %s\n", i, ss_algs[i].alg.hash.base.halg.base.cra_name); diff --git a/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-prng.c b/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-prng.c deleted file mode 100644 index a923cfc6553f..000000000000 --- a/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-prng.c +++ /dev/null @@ -1,177 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * sun8i-ss-prng.c - hardware cryptographic offloader for - * Allwinner A80/A83T SoC - * - * Copyright (C) 2015-2020 Corentin Labbe <clabbe@baylibre.com> - * - * This file handle the PRNG found in the SS - * - * You could find a link for the datasheet in Documentation/arch/arm/sunxi.rst - */ -#include "sun8i-ss.h" -#include <linux/dma-mapping.h> -#include <linux/kernel.h> -#include <linux/mm.h> -#include <linux/pm_runtime.h> -#include <crypto/internal/rng.h> - -int sun8i_ss_prng_seed(struct crypto_rng *tfm, const u8 *seed, - unsigned int slen) -{ - struct sun8i_ss_rng_tfm_ctx *ctx = crypto_rng_ctx(tfm); - - if (ctx->seed && ctx->slen != slen) { - kfree_sensitive(ctx->seed); - ctx->slen = 0; - ctx->seed = NULL; - } - if (!ctx->seed) - ctx->seed = kmalloc(slen, GFP_KERNEL); - if (!ctx->seed) - return -ENOMEM; - - memcpy(ctx->seed, seed, slen); - ctx->slen = slen; - - return 0; -} - -int sun8i_ss_prng_init(struct crypto_tfm *tfm) -{ - struct sun8i_ss_rng_tfm_ctx *ctx = crypto_tfm_ctx(tfm); - - memset(ctx, 0, sizeof(struct sun8i_ss_rng_tfm_ctx)); - return 0; -} - -void sun8i_ss_prng_exit(struct crypto_tfm *tfm) -{ - struct sun8i_ss_rng_tfm_ctx *ctx = crypto_tfm_ctx(tfm); - - kfree_sensitive(ctx->seed); - ctx->seed = NULL; - ctx->slen = 0; -} - -int sun8i_ss_prng_generate(struct crypto_rng *tfm, const u8 *src, - unsigned int slen, u8 *dst, unsigned int dlen) -{ - struct sun8i_ss_rng_tfm_ctx *ctx = crypto_rng_ctx(tfm); - struct rng_alg *alg = crypto_rng_alg(tfm); - struct sun8i_ss_alg_template *algt; - unsigned int todo_with_padding; - struct sun8i_ss_dev *ss; - dma_addr_t dma_iv, dma_dst; - unsigned int todo; - int err = 0; - int flow; - void *d; - u32 v; - - algt = container_of(alg, struct sun8i_ss_alg_template, alg.rng); - ss = algt->ss; - - if (ctx->slen == 0) { - dev_err(ss->dev, "The PRNG is not seeded\n"); - return -EINVAL; - } - - /* The SS does not give an updated seed, so we need to get a new one. - * So we will ask for an extra PRNG_SEED_SIZE data. - * We want dlen + seedsize rounded up to a multiple of PRNG_DATA_SIZE - */ - todo = dlen + PRNG_SEED_SIZE + PRNG_DATA_SIZE; - todo -= todo % PRNG_DATA_SIZE; - - todo_with_padding = ALIGN(todo, dma_get_cache_alignment()); - if (todo_with_padding < todo || todo < dlen) - return -EOVERFLOW; - - d = kzalloc(todo_with_padding, GFP_KERNEL); - if (!d) - return -ENOMEM; - - flow = sun8i_ss_get_engine_number(ss); - -#ifdef CONFIG_CRYPTO_DEV_SUN8I_SS_DEBUG - algt->stat_req++; - algt->stat_bytes += todo; -#endif - - v = SS_ALG_PRNG | SS_PRNG_CONTINUE | SS_START; - if (flow) - v |= SS_FLOW1; - else - v |= SS_FLOW0; - - dma_iv = dma_map_single(ss->dev, ctx->seed, ctx->slen, DMA_TO_DEVICE); - if (dma_mapping_error(ss->dev, dma_iv)) { - dev_err(ss->dev, "Cannot DMA MAP IV\n"); - err = -EFAULT; - goto err_free; - } - - dma_dst = dma_map_single(ss->dev, d, todo, DMA_FROM_DEVICE); - if (dma_mapping_error(ss->dev, dma_dst)) { - dev_err(ss->dev, "Cannot DMA MAP DST\n"); - err = -EFAULT; - goto err_iv; - } - - err = pm_runtime_resume_and_get(ss->dev); - if (err < 0) - goto err_pm; - err = 0; - - mutex_lock(&ss->mlock); - writel(dma_iv, ss->base + SS_IV_ADR_REG); - /* the PRNG act badly (failing rngtest) without SS_KEY_ADR_REG set */ - writel(dma_iv, ss->base + SS_KEY_ADR_REG); - writel(dma_dst, ss->base + SS_DST_ADR_REG); - writel(todo / 4, ss->base + SS_LEN_ADR_REG); - - reinit_completion(&ss->flows[flow].complete); - ss->flows[flow].status = 0; - /* Be sure all data is written before enabling the task */ - wmb(); - - writel(v, ss->base + SS_CTL_REG); - - wait_for_completion_interruptible_timeout(&ss->flows[flow].complete, - msecs_to_jiffies(todo)); - if (ss->flows[flow].status == 0) { - dev_err(ss->dev, "DMA timeout for PRNG (size=%u)\n", todo); - err = -EFAULT; - } - /* Since cipher and hash use the linux/cryptoengine and that we have - * a cryptoengine per flow, we are sure that they will issue only one - * request per flow. - * Since the cryptoengine wait for completion before submitting a new - * one, the mlock could be left just after the final writel. - * But cryptoengine cannot handle crypto_rng, so we need to be sure - * nothing will use our flow. - * The easiest way is to grab mlock until the hardware end our requests. - * We could have used a per flow lock, but this would increase - * complexity. - * The drawback is that no request could be handled for the other flow. - */ - mutex_unlock(&ss->mlock); - - pm_runtime_put(ss->dev); - -err_pm: - dma_unmap_single(ss->dev, dma_dst, todo, DMA_FROM_DEVICE); -err_iv: - dma_unmap_single(ss->dev, dma_iv, ctx->slen, DMA_TO_DEVICE); - - if (!err) { - memcpy(dst, d, dlen); - /* Update seed */ - memcpy(ctx->seed, d + dlen, ctx->slen); - } -err_free: - kfree_sensitive(d); - - return err; -} diff --git a/drivers/crypto/allwinner/sun8i-ss/sun8i-ss.h b/drivers/crypto/allwinner/sun8i-ss/sun8i-ss.h index ae66eb45fb24..9ec6c2ad5699 100644 --- a/drivers/crypto/allwinner/sun8i-ss/sun8i-ss.h +++ b/drivers/crypto/allwinner/sun8i-ss/sun8i-ss.h @@ -8,7 +8,6 @@ #include <crypto/aes.h> #include <crypto/des.h> #include <crypto/engine.h> -#include <crypto/rng.h> #include <crypto/skcipher.h> #include <linux/atomic.h> #include <linux/debugfs.h> @@ -27,7 +26,6 @@ #define SS_ALG_DES (1 << 2) #define SS_ALG_3DES (2 << 2) #define SS_ALG_MD5 (3 << 2) -#define SS_ALG_PRNG (4 << 2) #define SS_ALG_SHA1 (6 << 2) #define SS_ALG_SHA224 (7 << 2) #define SS_ALG_SHA256 (8 << 2) @@ -68,8 +66,6 @@ #define SS_FLOW0 BIT(30) #define SS_FLOW1 BIT(31) -#define SS_PRNG_CONTINUE BIT(18) - #define MAX_SG 8 #define MAXFLOW 2 @@ -79,9 +75,6 @@ #define SS_DIE_ID_SHIFT 20 #define SS_DIE_ID_MASK 0x07 -#define PRNG_DATA_SIZE (160 / 8) -#define PRNG_SEED_SIZE DIV_ROUND_UP(175, 8) - #define MAX_PAD_SIZE 4096 /* @@ -214,16 +207,6 @@ struct sun8i_cipher_tfm_ctx { }; /* - * struct sun8i_ss_prng_ctx - context for PRNG TFM - * @seed: The seed to use - * @slen: The size of the seed - */ -struct sun8i_ss_rng_tfm_ctx { - void *seed; - unsigned int slen; -}; - -/* * struct sun8i_ss_hash_tfm_ctx - context for an ahash TFM * @fallback_tfm: pointer to the fallback TFM * @ss: pointer to the private data of driver handling this TFM @@ -272,7 +255,6 @@ struct sun8i_ss_alg_template { struct sun8i_ss_dev *ss; union { struct skcipher_engine_alg skcipher; - struct rng_alg rng; struct ahash_engine_alg hash; } alg; unsigned long stat_req; @@ -298,11 +280,6 @@ int sun8i_ss_skencrypt(struct skcipher_request *areq); int sun8i_ss_get_engine_number(struct sun8i_ss_dev *ss); int sun8i_ss_run_task(struct sun8i_ss_dev *ss, struct sun8i_cipher_req_ctx *rctx, const char *name); -int sun8i_ss_prng_generate(struct crypto_rng *tfm, const u8 *src, - unsigned int slen, u8 *dst, unsigned int dlen); -int sun8i_ss_prng_seed(struct crypto_rng *tfm, const u8 *seed, unsigned int slen); -int sun8i_ss_prng_init(struct crypto_tfm *tfm); -void sun8i_ss_prng_exit(struct crypto_tfm *tfm); int sun8i_ss_hash_init_tfm(struct crypto_ahash *tfm); void sun8i_ss_hash_exit_tfm(struct crypto_ahash *tfm); diff --git a/drivers/cxl/core/features.c b/drivers/cxl/core/features.c index c3cb2060bbea..7b0eeb0788d3 100644 --- a/drivers/cxl/core/features.c +++ b/drivers/cxl/core/features.c @@ -649,7 +649,13 @@ static void *cxlctl_fw_rpc(struct fwctl_uctx *uctx, enum fwctl_rpc_scope scope, struct cxl_memdev *cxlmd = fwctl_to_memdev(fwctl_dev); struct cxl_features_state *cxlfs = to_cxlfs(cxlmd->cxlds); const struct fwctl_rpc_cxl *rpc_in = in; - u16 opcode = rpc_in->opcode; + u16 opcode; + + if (in_len < sizeof(rpc_in->hdr) || + rpc_in->op_size > in_len - sizeof(rpc_in->hdr)) + return ERR_PTR(-EINVAL); + + opcode = rpc_in->opcode; if (!cxlctl_validate_hw_command(cxlfs, rpc_in, scope, opcode)) return ERR_PTR(-EINVAL); diff --git a/drivers/cxl/core/pmem.c b/drivers/cxl/core/pmem.c index e3a8b8d81333..a62d84818f93 100644 --- a/drivers/cxl/core/pmem.c +++ b/drivers/cxl/core/pmem.c @@ -219,12 +219,14 @@ static struct cxl_nvdimm *cxl_nvdimm_alloc(struct cxl_nvdimm_bridge *cxl_nvb, dev->bus = &cxl_bus_type; dev->type = &cxl_nvdimm_type; /* - * A "%llx" string is 17-bytes vs dimm_id that is max - * NVDIMM_KEY_DESC_LEN + * dev_id is the nvdimm dimm_id used for security key lookup. + * It must match id_show(), which emits the CXL serial as an + * unsigned decimal. A u64 decimal string is at most 20 digits + * plus NUL. */ - BUILD_BUG_ON(sizeof(cxl_nvd->dev_id) < 17 || + BUILD_BUG_ON(sizeof(cxl_nvd->dev_id) < 21 || sizeof(cxl_nvd->dev_id) > NVDIMM_KEY_DESC_LEN); - sprintf(cxl_nvd->dev_id, "%llx", cxlmd->cxlds->serial); + sprintf(cxl_nvd->dev_id, "%llu", cxlmd->cxlds->serial); return cxl_nvd; } diff --git a/drivers/cxl/core/ras.c b/drivers/cxl/core/ras.c index 7056a79bff4d..f2d99865c6df 100644 --- a/drivers/cxl/core/ras.c +++ b/drivers/cxl/core/ras.c @@ -136,7 +136,6 @@ int cxl_ras_init(void) void cxl_ras_exit(void) { cxl_cper_unregister_prot_err_work(&cxl_cper_prot_err_work); - cancel_work_sync(&cxl_cper_prot_err_work); } static void cxl_dport_map_ras(struct cxl_dport *dport) diff --git a/drivers/cxl/cxl.h b/drivers/cxl/cxl.h index a5b00c3b0444..1f00a07f9c33 100644 --- a/drivers/cxl/cxl.h +++ b/drivers/cxl/cxl.h @@ -563,7 +563,8 @@ struct cxl_nvdimm_bridge { struct nvdimm_bus_descriptor nd_desc; }; -#define CXL_DEV_ID_LEN 19 +/* Holds a u64 serial as a decimal string: up to 20 digits + NUL */ +#define CXL_DEV_ID_LEN 21 enum { CXL_NVD_F_INVALIDATED = 0, diff --git a/drivers/cxl/pci.c b/drivers/cxl/pci.c index c78d7d88744b..2c42ab75e56a 100644 --- a/drivers/cxl/pci.c +++ b/drivers/cxl/pci.c @@ -1198,7 +1198,6 @@ static int __init cxl_pci_driver_init(void) static void __exit cxl_pci_driver_exit(void) { cxl_cper_unregister_work(&cxl_cper_work); - cancel_work_sync(&cxl_cper_work); pci_unregister_driver(&cxl_pci_driver); } diff --git a/drivers/cxl/pmem.c b/drivers/cxl/pmem.c index 3432fd83b1e2..255ecfd67ca1 100644 --- a/drivers/cxl/pmem.c +++ b/drivers/cxl/pmem.c @@ -52,7 +52,7 @@ static ssize_t id_show(struct device *dev, struct device_attribute *attr, char * struct cxl_nvdimm *cxl_nvd = nvdimm_provider_data(nvdimm); struct cxl_dev_state *cxlds = cxl_nvd->cxlmd->cxlds; - return sysfs_emit(buf, "%lld\n", cxlds->serial); + return sysfs_emit(buf, "%llu\n", cxlds->serial); } static DEVICE_ATTR_RO(id); diff --git a/drivers/fpga/altera-cvp.c b/drivers/fpga/altera-cvp.c index 5af0bd33890c..e2a2307a41ee 100644 --- a/drivers/fpga/altera-cvp.c +++ b/drivers/fpga/altera-cvp.c @@ -16,6 +16,7 @@ #include <linux/module.h> #include <linux/pci.h> #include <linux/sizes.h> +#include <linux/string.h> #define CVP_BAR 0 /* BAR used for data transfer in memory mode */ #define CVP_DUMMY_WR 244 /* dummy writes to clear CvP state machine */ @@ -264,7 +265,7 @@ static int altera_cvp_v2_wait_for_credit(struct fpga_manager *mgr, static int altera_cvp_send_block(struct altera_cvp_conf *conf, const u32 *data, size_t len) { - u32 mask, words = len / sizeof(u32); + u32 words = len / sizeof(u32); int i, remainder; for (i = 0; i < words; i++) @@ -273,9 +274,10 @@ static int altera_cvp_send_block(struct altera_cvp_conf *conf, /* write up to 3 trailing bytes, if any */ remainder = len % sizeof(u32); if (remainder) { - mask = BIT(remainder * 8) - 1; - if (mask) - conf->write_data(conf, *data & mask); + u32 word = 0; + + memcpy(&word, data, remainder); + conf->write_data(conf, word); } return 0; diff --git a/drivers/fpga/stratix10-soc.c b/drivers/fpga/stratix10-soc.c index 0a295ccf1644..b8ec2e6f615f 100644 --- a/drivers/fpga/stratix10-soc.c +++ b/drivers/fpga/stratix10-soc.c @@ -195,20 +195,18 @@ static int s10_ops_write_init(struct fpga_manager *mgr, ret = s10_svc_send_msg(priv, COMMAND_RECONFIG, &ctype, sizeof(ctype)); if (ret < 0) - goto init_done; + goto init_error; - ret = wait_for_completion_timeout( - &priv->status_return_completion, S10_RECONFIG_TIMEOUT); - if (!ret) { + if (!wait_for_completion_timeout(&priv->status_return_completion, + S10_RECONFIG_TIMEOUT)) { dev_err(dev, "timeout waiting for RECONFIG_REQUEST\n"); ret = -ETIMEDOUT; - goto init_done; + goto init_error; } - ret = 0; if (!test_and_clear_bit(SVC_STATUS_OK, &priv->status)) { ret = -ETIMEDOUT; - goto init_done; + goto init_error; } /* Allocate buffers from the service layer's pool. */ @@ -217,14 +215,16 @@ static int s10_ops_write_init(struct fpga_manager *mgr, if (IS_ERR(kbuf)) { s10_free_buffers(mgr); ret = PTR_ERR(kbuf); - goto init_done; + goto init_error; } priv->svc_bufs[i].buf = kbuf; priv->svc_bufs[i].lock = 0; } -init_done: + return 0; + +init_error: stratix10_svc_done(priv->chan); return ret; } @@ -342,6 +342,9 @@ static int s10_ops_write(struct fpga_manager *mgr, const char *buf, if (!s10_free_buffers(mgr)) dev_err(dev, "%s not all buffers were freed\n", __func__); + if (ret < 0) + stratix10_svc_done(priv->chan); + return ret; } 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 fd5a6c6532a1..deac90c49d63 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -7327,29 +7327,68 @@ finish: return stream; } +/* + * Apple Studio Display exposes two SST DP links for a 2x1 tiled panel. + * The primary tile advertises the full 5120x2880 mode (with DSC on the + * bandwidth-sufficient link) while the secondary carries a per-tile + * 2560x2880 timing on a insufficient bandwidth link. Hide the secondary + * connector from userspace so compositors configure a single 5K stream + * on the primary link only. + */ +static bool amdgpu_dm_hide_secondary_tile_from_userspace(struct drm_connector *connector) +{ + struct amdgpu_dm_connector *aconnector = to_amdgpu_dm_connector(connector); + + if (!aconnector->dc_sink) + return false; + + if (!aconnector->dc_sink->edid_caps.panel_patch.disable_second_tile) + return false; + + drm_edid_connector_update(connector, aconnector->drm_edid); + + if (!connector->has_tile) + return false; + + if (!connector->tile_h_loc && !connector->tile_v_loc) + return false; + + drm_dbg_kms(connector->dev, + "[CONNECTOR:%d:%s] hiding secondary Apple Studio Display tile from userspace\n", + connector->base.id, connector->name); + + return true; +} + +/** + * amdgpu_dm_connector_detect() - Detect whether a DRM connector is connected to a display + * + * A connector is considered connected when it has a sink that is not NULL. + * For connectors that support HPD (hotplug detection), the connection is + * handled in the HPD interrupt. + * + * Notes: + * 1. This interface is NOT called in context of HPD irq. + * 2. This interface *is called* in context of user-mode ioctl. Which + * makes it a bad place for *any* MST-related activity. + */ static enum drm_connector_status amdgpu_dm_connector_detect(struct drm_connector *connector, bool force) { - bool connected; struct amdgpu_dm_connector *aconnector = to_amdgpu_dm_connector(connector); - /* - * Notes: - * 1. This interface is NOT called in context of HPD irq. - * 2. This interface *is called* in context of user-mode ioctl. Which - * makes it a bad place for *any* MST-related activity. - */ + update_subconnector_property(aconnector); - if (aconnector->base.force == DRM_FORCE_UNSPECIFIED && - !aconnector->fake_enable) - connected = (aconnector->dc_sink != NULL); - else - connected = (aconnector->base.force == DRM_FORCE_ON || - aconnector->base.force == DRM_FORCE_ON_DIGITAL); + if (aconnector->base.force == DRM_FORCE_ON || + aconnector->base.force == DRM_FORCE_ON_DIGITAL) + return connector_status_connected; + else if (aconnector->base.force == DRM_FORCE_OFF) + return connector_status_disconnected; - update_subconnector_property(aconnector); + if (amdgpu_dm_hide_secondary_tile_from_userspace(connector)) + return connector_status_disconnected; - return (connected ? connector_status_connected : + return (aconnector->dc_sink ? connector_status_connected : connector_status_disconnected); } @@ -8501,6 +8540,47 @@ static void amdgpu_dm_connector_add_common_modes(struct drm_encoder *encoder, } } +/* + * The Apple Studio Display primary tile advertises both the full 5120x2880 + * mode and the per-tile 2560x2880 timing. As the secondary tile is hidden from + * userspace (see amdgpu_dm_hide_secondary_tile_from_userspace()), drop the + * per-tile timing from the primary connector so compositors only pick the full + * 5K mode. + */ +static void amdgpu_dm_prune_primary_tile_modes(struct drm_connector *connector) +{ + struct amdgpu_dm_connector *aconnector = to_amdgpu_dm_connector(connector); + struct drm_display_mode *mode, *t; + + if (!aconnector->dc_sink) + return; + + if (!aconnector->dc_sink->edid_caps.panel_patch.disable_second_tile) + return; + + if (!connector->has_tile) + return; + + /* Only prune the per-tile timing from the primary tile. */ + if (connector->tile_h_loc || connector->tile_v_loc) + return; + + list_for_each_entry_safe(mode, t, &connector->probed_modes, head) { + if (mode->hdisplay != connector->tile_h_size || + mode->vdisplay != connector->tile_v_size) + continue; + + drm_dbg_kms(connector->dev, + "[CONNECTOR:%d:%s] pruning per-tile %dx%d timing from primary Apple Studio Display tile\n", + connector->base.id, connector->name, + mode->hdisplay, mode->vdisplay); + + list_del(&mode->head); + drm_mode_destroy(connector->dev, mode); + aconnector->num_modes--; + } +} + static void amdgpu_set_panel_orientation(struct drm_connector *connector) { struct drm_encoder *encoder; @@ -8543,6 +8623,8 @@ static void amdgpu_dm_connector_ddc_get_modes(struct drm_connector *connector, amdgpu_dm_connector->num_modes = drm_edid_connector_add_modes(connector); + amdgpu_dm_prune_primary_tile_modes(connector); + /* sorting the probed modes before calling function * amdgpu_dm_get_native_mode() since EDID can have * more than one preferred mode. The modes that are diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c index d0f770dd0a95..25923b00667a 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c @@ -56,8 +56,11 @@ static u32 edid_extract_panel_id(struct edid *edid) (u32)EDID_PRODUCT_ID(edid); } -static void apply_edid_quirks(struct drm_device *dev, struct edid *edid, struct dc_edid_caps *edid_caps) +static void apply_edid_quirks(struct dc_link *link, struct edid *edid, + struct dc_edid_caps *edid_caps) { + struct amdgpu_dm_connector *aconnector = link->priv; + struct drm_device *dev = aconnector->base.dev; uint32_t panel_id = edid_extract_panel_id(edid); switch (panel_id) { @@ -87,6 +90,22 @@ static void apply_edid_quirks(struct drm_device *dev, struct edid *edid, struct drm_dbg_driver(dev, "Disabling VSC on monitor with panel id %X\n", panel_id); edid_caps->panel_patch.disable_colorimetry = true; break; + /* Workaround for monitors that get corrupted by the PHY SSC reduction */ + case drm_edid_encode_panel_id('D', 'E', 'L', 0x4147): + drm_dbg_driver(dev, "Skip PHY SSC reduction on panel id %X\n", panel_id); + link->wa_flags.skip_phy_ssc_reduction = true; + break; + /* + * Workaround for Apple Studio Display which exposes a 2x1 tiled panel + * over two SST DP links. Hide the secondary tile from userspace so + * compositors drive a single 5K stream on the primary link only. + */ + case drm_edid_encode_panel_id('A', 'P', 'P', 0xAE3A): + case drm_edid_encode_panel_id('A', 'P', 'P', 0xAE42): + case drm_edid_encode_panel_id('A', 'P', 'P', 0xAE46): + drm_dbg_driver(dev, "Hiding secondary tile on panel id %X\n", panel_id); + edid_caps->panel_patch.disable_second_tile = true; + break; default: return; } @@ -108,7 +127,6 @@ enum dc_edid_status dm_helpers_parse_edid_caps( { struct amdgpu_dm_connector *aconnector = link->priv; struct drm_connector *connector = &aconnector->base; - struct drm_device *dev = connector->dev; struct edid *edid_buf = edid ? (struct edid *) edid->raw_edid : NULL; struct cea_sad *sads; int sad_count = -1; @@ -138,7 +156,7 @@ enum dc_edid_status dm_helpers_parse_edid_caps( edid_caps->edid_hdmi = connector->display_info.is_hdmi; - apply_edid_quirks(dev, edid_buf, edid_caps); + apply_edid_quirks(link, edid_buf, edid_caps); sad_count = drm_edid_to_sad((struct edid *) edid->raw_edid, &sads); if (sad_count <= 0) diff --git a/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c b/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c index 6518d5639d66..04bc014906f8 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c +++ b/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c @@ -949,7 +949,10 @@ void dc_dmub_srv_log_diagnostic_data(struct dc_dmub_srv *dc_dmub_srv) { uint32_t i; - if (!dc_dmub_srv || !dc_dmub_srv->dmub) { + if (!dc_dmub_srv) + return; + + if (!dc_dmub_srv->dmub) { DC_LOG_ERROR("%s: invalid parameters.", __func__); return; } @@ -1146,7 +1149,10 @@ void dc_dmub_srv_enable_dpia_trace(const struct dc *dc) { struct dc_dmub_srv *dc_dmub_srv = dc->ctx->dmub_srv; - if (!dc_dmub_srv || !dc_dmub_srv->dmub) { + if (!dc_dmub_srv) + return; + + if (!dc_dmub_srv->dmub) { DC_LOG_ERROR("%s: invalid parameters.", __func__); return; } diff --git a/drivers/gpu/drm/amd/display/dc/dc_types.h b/drivers/gpu/drm/amd/display/dc/dc_types.h index b5aa03a3e39c..ff06a1dae5c6 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_types.h +++ b/drivers/gpu/drm/amd/display/dc/dc_types.h @@ -178,6 +178,7 @@ struct dc_panel_patch { unsigned int skip_audio_sab_check; unsigned int mst_start_top_delay; unsigned int remove_sink_ext_caps; + bool disable_second_tile; unsigned int disable_colorimetry; uint8_t blankstream_before_otg_off; bool oled_optimize_display_on; diff --git a/drivers/gpu/drm/nouveau/nouveau_gem.c b/drivers/gpu/drm/nouveau/nouveau_gem.c index f6cfb6ea4885..80e2bde9915f 100644 --- a/drivers/gpu/drm/nouveau/nouveau_gem.c +++ b/drivers/gpu/drm/nouveau/nouveau_gem.c @@ -313,11 +313,20 @@ nouveau_gem_info(struct drm_file *file_priv, struct drm_gem_object *gem, rep->offset = nvbo->offset; if (vmm->vmm.object.oclass >= NVIF_CLASS_VMM_NV50 && !nouveau_cli_uvmm(cli)) { + int ret; + + ret = ttm_bo_reserve(&nvbo->bo, false, false, NULL); + if (ret) + return ret; + vma = nouveau_vma_find(nvbo, vmm); - if (!vma) + if (!vma) { + ttm_bo_unreserve(&nvbo->bo); return -EINVAL; + } rep->offset = vma->addr; + ttm_bo_unreserve(&nvbo->bo); } else rep->offset = 0; diff --git a/drivers/hid/hid-apple.c b/drivers/hid/hid-apple.c index cb1bd6dca835..924dab47849e 100644 --- a/drivers/hid/hid-apple.c +++ b/drivers/hid/hid-apple.c @@ -91,6 +91,9 @@ struct apple_sc_backlight { struct hid_device *hdev; }; +/* T2 VHCI re-enumerates the internal keyboard across system resume. */ +static int apple_backlight_resume_brightness = -1; + struct apple_backlight_config_report { u8 report_id; u8 version; @@ -823,6 +826,7 @@ static int apple_backlight_led_set(struct led_classdev *led_cdev, static int apple_backlight_init(struct hid_device *hdev) { int ret; + int brightness; struct apple_sc *asc = hid_get_drvdata(hdev); struct apple_backlight_config_report *rep; @@ -858,13 +862,20 @@ static int apple_backlight_init(struct hid_device *hdev) asc->backlight->cdev.name = "apple::kbd_backlight"; asc->backlight->cdev.max_brightness = rep->backlight_on_max; asc->backlight->cdev.brightness_set_blocking = apple_backlight_led_set; - asc->backlight->cdev.flags = LED_CORE_SUSPENDRESUME; + /* VHCI re-enumeration restores the cached brightness in the next probe. */ + + brightness = READ_ONCE(apple_backlight_resume_brightness); + if (brightness < 0) + brightness = LED_OFF; + else + brightness = min_t(int, brightness, rep->backlight_on_max); - ret = apple_backlight_set(hdev, 0, 0); + ret = apple_backlight_set(hdev, brightness, 0); if (ret < 0) { hid_err(hdev, "backlight set request failed: %d\n", ret); goto cleanup_and_exit; } + asc->backlight->cdev.brightness = brightness; ret = devm_led_classdev_register(&hdev->dev, &asc->backlight->cdev); @@ -997,6 +1008,9 @@ static void apple_remove(struct hid_device *hdev) if (asc->quirks & APPLE_RDESC_BATTERY) timer_delete_sync(&asc->battery_timer); + if (asc->backlight) + WRITE_ONCE(apple_backlight_resume_brightness, + asc->backlight->cdev.brightness); hid_hw_stop(hdev); } diff --git a/drivers/hid/hid-corsair-void.c b/drivers/hid/hid-corsair-void.c index 5e9a5b8f7f16..071a663a6c26 100644 --- a/drivers/hid/hid-corsair-void.c +++ b/drivers/hid/hid-corsair-void.c @@ -92,6 +92,9 @@ #define CORSAIR_VOID_STATUS_REPORT_ID 0x64 #define CORSAIR_VOID_FIRMWARE_REPORT_ID 0x66 +#define CORSAIR_VOID_STATUS_REPORT_SIZE 5 +#define CORSAIR_VOID_FIRMWARE_REPORT_SIZE 5 + #define CORSAIR_VOID_USB_SIDETONE_REQUEST 0x1 #define CORSAIR_VOID_USB_SIDETONE_REQUEST_TYPE 0x21 #define CORSAIR_VOID_USB_SIDETONE_VALUE 0x200 @@ -742,6 +745,13 @@ static int corsair_void_raw_event(struct hid_device *hid_dev, /* Description of packets are documented at the top of this file */ if (hid_report->id == CORSAIR_VOID_STATUS_REPORT_ID) { + if (size < CORSAIR_VOID_STATUS_REPORT_SIZE) { + hid_warn_ratelimited(hid_dev, + "unexpected status report of size %d", + size); + return 1; + } + drvdata->mic_up = FIELD_GET(CORSAIR_VOID_MIC_MASK, data[2]); drvdata->connected = (data[3] == CORSAIR_VOID_WIRELESS_CONNECTED) || drvdata->is_wired; @@ -750,6 +760,13 @@ static int corsair_void_raw_event(struct hid_device *hid_dev, FIELD_GET(CORSAIR_VOID_CAPACITY_MASK, data[2]), data[3], data[4]); } else if (hid_report->id == CORSAIR_VOID_FIRMWARE_REPORT_ID) { + if (size < CORSAIR_VOID_FIRMWARE_REPORT_SIZE) { + hid_warn_ratelimited(hid_dev, + "unexpected firmware report of size %d", + size); + return 1; + } + drvdata->fw_receiver_major = data[1]; drvdata->fw_receiver_minor = data[2]; drvdata->fw_headset_major = data[3]; diff --git a/drivers/hid/hid-mcp2221.c b/drivers/hid/hid-mcp2221.c index ef3b5c77c38e..faebe95b4eb0 100644 --- a/drivers/hid/hid-mcp2221.c +++ b/drivers/hid/hid-mcp2221.c @@ -851,6 +851,9 @@ static int mcp2221_raw_event(struct hid_device *hdev, u8 *buf; struct mcp2221 *mcp = hid_get_drvdata(hdev); + if (size < 4) + return 0; + switch (data[0]) { case MCP2221_I2C_WR_DATA: @@ -912,6 +915,10 @@ static int mcp2221_raw_event(struct hid_device *hdev, mcp->status = -EINVAL; break; } + if (4 + data[3] > size) { + mcp->status = -EINVAL; + break; + } buf = mcp->rxbuf; memcpy(&buf[mcp->rxbuf_idx], &data[4], data[3]); mcp->rxbuf_idx = mcp->rxbuf_idx + data[3]; @@ -1035,6 +1042,8 @@ static void mcp2221_hid_unregister(void *ptr) { struct hid_device *hdev = ptr; + if (hdev->io_started) + hid_device_io_stop(hdev); hid_hw_close(hdev); hid_hw_stop(hdev); } diff --git a/drivers/hid/hid-picolcd_debugfs.c b/drivers/hid/hid-picolcd_debugfs.c index d01176da8896..0d325d69e64b 100644 --- a/drivers/hid/hid-picolcd_debugfs.c +++ b/drivers/hid/hid-picolcd_debugfs.c @@ -98,6 +98,15 @@ static ssize_t picolcd_debug_eeprom_read(struct file *f, char __user *u, ret = resp->raw_data[2]; if (ret > s) ret = s; + /* + * raw_data[2] is a device-supplied length; also clamp it to + * what picolcd_raw_event() actually stored (raw_size), or a + * hostile device overruns the raw_data[] buffer. + */ + if (ret > resp->raw_size - 3) + ret = resp->raw_size - 3; + if (ret < 0) + ret = 0; if (copy_to_user(u, resp->raw_data+3, ret)) ret = -EFAULT; else diff --git a/drivers/hid/hid-roccat.c b/drivers/hid/hid-roccat.c index e413662f7508..e54b6a8a92ef 100644 --- a/drivers/hid/hid-roccat.c +++ b/drivers/hid/hid-roccat.c @@ -70,6 +70,15 @@ static struct roccat_device *devices[ROCCAT_MAX_DEVICES]; /* protects modifications of devices array */ static DEFINE_MUTEX(devices_lock); +static void roccat_free_device(struct roccat_device *device) +{ + int i; + + for (i = 0; i < ROCCAT_CBUF_SIZE; i++) + kfree(device->cbuf[i].value); + kfree(device); +} + static ssize_t roccat_read(struct file *file, char __user *buffer, size_t count, loff_t *ppos) { @@ -226,7 +235,7 @@ static int roccat_release(struct inode *inode, struct file *file) hid_hw_power(device->hid, PM_HINT_NORMAL); hid_hw_close(device->hid); } else { - kfree(device); + roccat_free_device(device); } } @@ -374,7 +383,7 @@ void roccat_disconnect(int minor) hid_hw_close(device->hid); wake_up_interruptible(&device->wait); } else { - kfree(device); + roccat_free_device(device); } } EXPORT_SYMBOL_GPL(roccat_disconnect); diff --git a/drivers/hid/hid-sensor-custom.c b/drivers/hid/hid-sensor-custom.c index 957311e7b638..0b97d61df0c8 100644 --- a/drivers/hid/hid-sensor-custom.c +++ b/drivers/hid/hid-sensor-custom.c @@ -609,7 +609,7 @@ static int hid_sensor_custom_add_attributes(struct hid_sensor_custom &sensor_inst->fields[i]. hid_custom_attribute_group); if (ret) - break; + goto err_remove_groups; /* For power or report field store indexes */ if (sensor_inst->fields[i].attribute.attrib_id == @@ -621,6 +621,13 @@ static int hid_sensor_custom_add_attributes(struct hid_sensor_custom } return ret; + +err_remove_groups: + while (--i >= 0) + sysfs_remove_group(&sensor_inst->pdev->dev.kobj, + &sensor_inst->fields[i].hid_custom_attribute_group); + kfree(sensor_inst->fields); + return ret; } static void hid_sensor_custom_remove_attributes(struct hid_sensor_custom * diff --git a/drivers/hid/hid-sensor-hub.c b/drivers/hid/hid-sensor-hub.c index 1b725c879650..faeb9c4536f5 100644 --- a/drivers/hid/hid-sensor-hub.c +++ b/drivers/hid/hid-sensor-hub.c @@ -239,12 +239,17 @@ int sensor_hub_get_feature(struct hid_sensor_hub_device *hsdev, u32 report_id, u32 field_index, int buffer_size, void *buffer) { struct hid_report *report; + struct hid_field *field; struct sensor_hub_data *data = hid_get_drvdata(hsdev->hdev); - int report_size; + size_t field_size; + size_t report_size; + size_t copied = 0; + size_t to_copy; int ret = 0; - u8 *val_ptr; - int buffer_index = 0; - int i; + unsigned int i; + + if (!buffer || buffer_size <= 0) + return -EINVAL; memset(buffer, 0, buffer_size); @@ -258,26 +263,29 @@ int sensor_hub_get_feature(struct hid_sensor_hub_device *hsdev, u32 report_id, hid_hw_request(hsdev->hdev, report, HID_REQ_GET_REPORT); hid_hw_wait(hsdev->hdev); + field = report->field[field_index]; + /* calculate number of bytes required to read this field */ - report_size = DIV_ROUND_UP(report->field[field_index]->report_size, - 8) * - report->field[field_index]->report_count; - if (!report_size) { + field_size = DIV_ROUND_UP(field->report_size, 8); + /* HID core stores each parsed report value in a __s32 slot. */ + if (!field_size || field_size > sizeof(field->value[0])) { + ret = -EINVAL; + goto done_proc; + } + if (field->report_count > SIZE_MAX / field_size) { ret = -EINVAL; goto done_proc; } - ret = min(report_size, buffer_size); - val_ptr = (u8 *)report->field[field_index]->value; - for (i = 0; i < report->field[field_index]->report_count; ++i) { - if (buffer_index >= ret) - break; + report_size = field_size * field->report_count; + report_size = min_t(size_t, report_size, buffer_size); - memcpy(&((u8 *)buffer)[buffer_index], val_ptr, - report->field[field_index]->report_size / 8); - val_ptr += sizeof(__s32); - buffer_index += (report->field[field_index]->report_size / 8); + for (i = 0; i < field->report_count && copied < report_size; ++i) { + to_copy = min(field_size, report_size - copied); + memcpy(&((u8 *)buffer)[copied], &field->value[i], to_copy); + copied += to_copy; } + ret = copied; done_proc: mutex_unlock(&data->mutex); diff --git a/drivers/hid/hid-sony.c b/drivers/hid/hid-sony.c index b966e4044238..22db29add44e 100644 --- a/drivers/hid/hid-sony.c +++ b/drivers/hid/hid-sony.c @@ -2164,7 +2164,9 @@ static void sony_remove(struct hid_device *hdev) struct sony_sc *sc = hid_get_drvdata(hdev); if (sc->quirks & (GHL_GUITAR_PS3WIIU | GHL_GUITAR_PS4)) { - timer_delete_sync(&sc->ghl_poke_timer); + /* poison, not kill: a pending timer must not re-submit during teardown */ + usb_poison_urb(sc->ghl_urb); + timer_shutdown_sync(&sc->ghl_poke_timer); usb_free_urb(sc->ghl_urb); } diff --git a/drivers/hid/hid-universal-pidff.c b/drivers/hid/hid-universal-pidff.c index 549dac555d40..60180467a0bf 100644 --- a/drivers/hid/hid-universal-pidff.c +++ b/drivers/hid/hid-universal-pidff.c @@ -104,12 +104,14 @@ static int universal_pidff_probe(struct hid_device *hdev, error = init_function(hdev, id->driver_data); if (error) { hid_warn(hdev, "Error initialising force feedback\n"); - goto err; + goto err_stop; } hid_info(hdev, "Universal pidff driver loaded successfully!"); return 0; +err_stop: + hid_hw_stop(hdev); err: return error; } diff --git a/drivers/hid/intel-thc-hid/intel-quicki2c/pci-quicki2c.c b/drivers/hid/intel-thc-hid/intel-quicki2c/pci-quicki2c.c index 0156ab391778..c6ba6886072a 100644 --- a/drivers/hid/intel-thc-hid/intel-quicki2c/pci-quicki2c.c +++ b/drivers/hid/intel-thc-hid/intel-quicki2c/pci-quicki2c.c @@ -771,6 +771,7 @@ static void quicki2c_remove(struct pci_dev *pdev) quicki2c_hid_remove(qcdev); quicki2c_dma_deinit(qcdev); + pm_runtime_dont_use_autosuspend(qcdev->dev); pm_runtime_get_noresume(qcdev->dev); quicki2c_dev_deinit(qcdev); diff --git a/drivers/hid/intel-thc-hid/intel-quickspi/pci-quickspi.c b/drivers/hid/intel-thc-hid/intel-quickspi/pci-quickspi.c index f0830a56d556..1c96d1d85845 100644 --- a/drivers/hid/intel-thc-hid/intel-quickspi/pci-quickspi.c +++ b/drivers/hid/intel-thc-hid/intel-quickspi/pci-quickspi.c @@ -556,7 +556,14 @@ static int quickspi_alloc_report_buf(struct quickspi_device *qsdev) max_report_len = max(le16_to_cpu(qsdev->dev_desc.max_output_len), le16_to_cpu(qsdev->dev_desc.max_input_len)); - qsdev->report_buf = devm_kzalloc(qsdev->dev, max_report_len, GFP_KERNEL); + /* + * write_cmd_to_txdma() writes the output report header ahead of the + * content in this buffer, so it has to hold both. + */ + qsdev->report_buf_size = HIDSPI_OUTPUT_REPORT_SIZE(max_report_len); + + qsdev->report_buf = devm_kzalloc(qsdev->dev, qsdev->report_buf_size, + GFP_KERNEL); if (!qsdev->report_buf) return -ENOMEM; @@ -715,6 +722,7 @@ static void quickspi_remove(struct pci_dev *pdev) quickspi_hid_remove(qsdev); quickspi_dma_deinit(qsdev); + pm_runtime_dont_use_autosuspend(qsdev->dev); pm_runtime_get_noresume(qsdev->dev); quickspi_dev_deinit(qsdev); diff --git a/drivers/hid/intel-thc-hid/intel-quickspi/quickspi-dev.h b/drivers/hid/intel-thc-hid/intel-quickspi/quickspi-dev.h index bf5e18f5a5f4..0ed964bfe3dd 100644 --- a/drivers/hid/intel-thc-hid/intel-quickspi/quickspi-dev.h +++ b/drivers/hid/intel-thc-hid/intel-quickspi/quickspi-dev.h @@ -157,6 +157,7 @@ struct quickspi_device { u8 *report_descriptor; u8 *input_buf; u8 *report_buf; + u32 report_buf_size; u32 report_len; wait_queue_head_t reset_ack_wq; diff --git a/drivers/hid/intel-thc-hid/intel-quickspi/quickspi-hid.c b/drivers/hid/intel-thc-hid/intel-quickspi/quickspi-hid.c index ad52e402c28a..9df948f94d5a 100644 --- a/drivers/hid/intel-thc-hid/intel-quickspi/quickspi-hid.c +++ b/drivers/hid/intel-thc-hid/intel-quickspi/quickspi-hid.c @@ -61,7 +61,7 @@ static int quickspi_hid_raw_request(struct hid_device *hid, switch (reqtype) { case HID_REQ_GET_REPORT: - ret = quickspi_get_report(qsdev, rtype, reportnum, buf); + ret = quickspi_get_report(qsdev, rtype, reportnum, buf, len); break; case HID_REQ_SET_REPORT: ret = quickspi_set_report(qsdev, rtype, reportnum, buf, len); diff --git a/drivers/hid/intel-thc-hid/intel-quickspi/quickspi-protocol.c b/drivers/hid/intel-thc-hid/intel-quickspi/quickspi-protocol.c index cb19057f1191..847c5ec55569 100644 --- a/drivers/hid/intel-thc-hid/intel-quickspi/quickspi-protocol.c +++ b/drivers/hid/intel-thc-hid/intel-quickspi/quickspi-protocol.c @@ -30,6 +30,9 @@ static int write_cmd_to_txdma(struct quickspi_device *qsdev, write_buf = (struct output_report *)qsdev->report_buf; + if (HIDSPI_OUTPUT_REPORT_SIZE(report_buf_len) > qsdev->report_buf_size) + return -EINVAL; + write_buf->output_hdr.report_type = report_type; write_buf->output_hdr.content_len = cpu_to_le16(report_buf_len); write_buf->output_hdr.content_id = report_id; @@ -342,10 +345,12 @@ int reset_tic(struct quickspi_device *qsdev) } int quickspi_get_report(struct quickspi_device *qsdev, - u8 report_type, unsigned int report_id, void *buf) + u8 report_type, unsigned int report_id, void *buf, + u32 buf_len) { int rep_type; int ret; + u32 report_len; if (report_type == HID_INPUT_REPORT) { rep_type = GET_INPUT_REPORT; @@ -372,9 +377,17 @@ int quickspi_get_report(struct quickspi_device *qsdev, } qsdev->get_report_cmpl = false; - memcpy(buf, qsdev->report_buf, qsdev->report_len); + /* quickspi_handle_input_data() updates this from IRQ context. */ + report_len = READ_ONCE(qsdev->report_len); + if (report_len > buf_len) { + dev_err_once(qsdev->dev, "Get report response too big, %u vs %u\n", + report_len, buf_len); + return -EINVAL; + } + + memcpy(buf, qsdev->report_buf, report_len); - return qsdev->report_len; + return report_len; } int quickspi_set_report(struct quickspi_device *qsdev, diff --git a/drivers/hid/intel-thc-hid/intel-quickspi/quickspi-protocol.h b/drivers/hid/intel-thc-hid/intel-quickspi/quickspi-protocol.h index 775e29c1ed13..8a2338bee808 100644 --- a/drivers/hid/intel-thc-hid/intel-quickspi/quickspi-protocol.h +++ b/drivers/hid/intel-thc-hid/intel-quickspi/quickspi-protocol.h @@ -12,7 +12,7 @@ struct quickspi_device; void quickspi_handle_input_data(struct quickspi_device *qsdev, u32 buf_len); int quickspi_get_report(struct quickspi_device *qsdev, u8 report_type, - unsigned int report_id, void *buf); + unsigned int report_id, void *buf, u32 buf_len); int quickspi_set_report(struct quickspi_device *qsdev, u8 report_type, unsigned int report_id, void *buf, u32 buf_len); int quickspi_get_report_descriptor(struct quickspi_device *qsdev); diff --git a/drivers/hsi/controllers/omap_ssi_core.c b/drivers/hsi/controllers/omap_ssi_core.c index eeacc427fd65..47826315d7d6 100644 --- a/drivers/hsi/controllers/omap_ssi_core.c +++ b/drivers/hsi/controllers/omap_ssi_core.c @@ -502,6 +502,12 @@ static int ssi_probe(struct platform_device *pd) pm_runtime_enable(&pd->dev); + ssi->device.dma_mask = &ssi->device.coherent_dma_mask; + + err = dma_set_mask_and_coherent(&ssi->device, DMA_BIT_MASK(32)); + if (err) + goto out2; + err = ssi_hw_init(ssi); if (err < 0) goto out2; diff --git a/drivers/hwmon/max6621.c b/drivers/hwmon/max6621.c index a7066f3a0bb4..3690f2ffe5fc 100644 --- a/drivers/hwmon/max6621.c +++ b/drivers/hwmon/max6621.c @@ -17,8 +17,8 @@ #define MAX6621_DRV_NAME "max6621" #define MAX6621_TEMP_INPUT_REG_NUM 9 -#define MAX6621_TEMP_INPUT_MIN -127000 -#define MAX6621_TEMP_INPUT_MAX 128000 +#define MAX6621_TEMP_INPUT_MIN -128000 +#define MAX6621_TEMP_INPUT_MAX 127000 #define MAX6621_TEMP_ALERT_CHAN_SHIFT 1 #define MAX6621_TEMP_S0D0_REG 0x00 @@ -239,7 +239,7 @@ max6621_read(struct device *dev, enum hwmon_sensor_types type, u32 attr, if (ret) return ret; - *val = (regval >> MAX6621_REG_TEMP_SHIFT) * + *val = ((s16)regval >> MAX6621_REG_TEMP_SHIFT) * 1000L; break; @@ -254,7 +254,7 @@ max6621_read(struct device *dev, enum hwmon_sensor_types type, u32 attr, if (ret) return ret; - *val = regval * 1000L; + *val = (s16)regval * 1000L; break; case hwmon_temp_crit_alarm: diff --git a/drivers/hwtracing/coresight/coresight-etm3x-sysfs.c b/drivers/hwtracing/coresight/coresight-etm3x-sysfs.c index 762109307b86..b3c67e96a82a 100644 --- a/drivers/hwtracing/coresight/coresight-etm3x-sysfs.c +++ b/drivers/hwtracing/coresight/coresight-etm3x-sysfs.c @@ -717,26 +717,19 @@ static DEVICE_ATTR_RW(cntr_rld_event); static ssize_t cntr_val_show(struct device *dev, struct device_attribute *attr, char *buf) { - int i, ret = 0; u32 val; struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent); struct etm_config *config = &drvdata->config; if (!coresight_get_mode(drvdata->csdev)) { spin_lock(&drvdata->spinlock); - for (i = 0; i < drvdata->nr_cntr; i++) - ret += sprintf(buf, "counter %d: %x\n", - i, config->cntr_val[i]); + val = config->cntr_val[config->cntr_idx]; spin_unlock(&drvdata->spinlock); - return ret; - } - - for (i = 0; i < drvdata->nr_cntr; i++) { - val = etm_readl(drvdata, ETMCNTVRn(i)); - ret += sprintf(buf, "counter %d: %x\n", i, val); + } else { + val = etm_readl(drvdata, ETMCNTVRn(config->cntr_idx)); } - return ret; + return sysfs_emit(buf, "%#x\n", val); } static ssize_t cntr_val_store(struct device *dev, diff --git a/drivers/hwtracing/ptt/hisi_ptt.c b/drivers/hwtracing/ptt/hisi_ptt.c index 3090479a2979..3c3e9fa93418 100644 --- a/drivers/hwtracing/ptt/hisi_ptt.c +++ b/drivers/hwtracing/ptt/hisi_ptt.c @@ -171,13 +171,13 @@ static bool hisi_ptt_wait_trace_hw_idle(struct hisi_ptt *hisi_ptt) HISI_PTT_WAIT_TRACE_TIMEOUT_US); } -static void hisi_ptt_wait_dma_reset_done(struct hisi_ptt *hisi_ptt) +static bool hisi_ptt_wait_dma_reset_done(struct hisi_ptt *hisi_ptt) { u32 val; - readl_poll_timeout_atomic(hisi_ptt->iobase + HISI_PTT_TRACE_WR_STS, - val, !val, HISI_PTT_RESET_POLL_INTERVAL_US, - HISI_PTT_RESET_TIMEOUT_US); + return !readl_poll_timeout_atomic(hisi_ptt->iobase + HISI_PTT_TRACE_WR_STS, + val, !val, HISI_PTT_RESET_POLL_INTERVAL_US, + HISI_PTT_RESET_TIMEOUT_US); } static void hisi_ptt_trace_end(struct hisi_ptt *hisi_ptt) @@ -202,14 +202,18 @@ static int hisi_ptt_trace_start(struct hisi_ptt *hisi_ptt) return -EBUSY; } - ctrl->started = true; - /* Reset the DMA before start tracing */ val = readl(hisi_ptt->iobase + HISI_PTT_TRACE_CTRL); val |= HISI_PTT_TRACE_CTRL_RST; writel(val, hisi_ptt->iobase + HISI_PTT_TRACE_CTRL); - hisi_ptt_wait_dma_reset_done(hisi_ptt); + if (!hisi_ptt_wait_dma_reset_done(hisi_ptt)) { + pci_err(hisi_ptt->pdev, "timed out waiting for DMA reset\n"); + val = readl(hisi_ptt->iobase + HISI_PTT_TRACE_CTRL); + val &= ~HISI_PTT_TRACE_CTRL_RST; + writel(val, hisi_ptt->iobase + HISI_PTT_TRACE_CTRL); + return -ETIMEDOUT; + } val = readl(hisi_ptt->iobase + HISI_PTT_TRACE_CTRL); val &= ~HISI_PTT_TRACE_CTRL_RST; @@ -234,6 +238,8 @@ static int hisi_ptt_trace_start(struct hisi_ptt *hisi_ptt) if (!hisi_ptt->trace_ctrl.is_port) val |= HISI_PTT_TRACE_CTRL_FILTER_MODE; + ctrl->started = true; + /* Start the Trace */ val |= HISI_PTT_TRACE_CTRL_EN; writel(val, hisi_ptt->iobase + HISI_PTT_TRACE_CTRL); diff --git a/drivers/i2c/busses/i2c-mxs.c b/drivers/i2c/busses/i2c-mxs.c index 08c9091a1e35..72c80107c11a 100644 --- a/drivers/i2c/busses/i2c-mxs.c +++ b/drivers/i2c/busses/i2c-mxs.c @@ -831,7 +831,7 @@ static int mxs_i2c_probe(struct platform_device *pdev) } /* Setup the DMA */ - i2c->dmach = dma_request_chan(dev, "rx-tx"); + i2c->dmach = devm_dma_request_chan(dev, "rx-tx"); if (IS_ERR(i2c->dmach)) { return dev_err_probe(dev, PTR_ERR(i2c->dmach), "Failed to request dma\n"); @@ -869,9 +869,6 @@ static void mxs_i2c_remove(struct platform_device *pdev) i2c_del_adapter(&i2c->adapter); - if (i2c->dmach) - dma_release_channel(i2c->dmach); - writel(MXS_I2C_CTRL0_SFTRST, i2c->regs + MXS_I2C_CTRL0_SET); } diff --git a/drivers/i3c/master.c b/drivers/i3c/master.c index 588395e7a770..41452a27262d 100644 --- a/drivers/i3c/master.c +++ b/drivers/i3c/master.c @@ -2808,11 +2808,12 @@ static void i3c_master_unregister_i3c_devs(struct i3c_master_controller *master) if (!i3cdev->dev) continue; - i3cdev->dev->desc = NULL; - if (device_is_registered(&i3cdev->dev->dev)) + if (device_is_registered(&i3cdev->dev->dev)) { + get_device(&i3cdev->dev->dev); device_unregister(&i3cdev->dev->dev); - else - put_device(&i3cdev->dev->dev); + } + i3cdev->dev->desc = NULL; + put_device(&i3cdev->dev->dev); i3cdev->dev = NULL; } } diff --git a/drivers/i3c/master/adi-i3c-master.c b/drivers/i3c/master/adi-i3c-master.c index d329faf4b3f9..f0c2ddb2f4b2 100644 --- a/drivers/i3c/master/adi-i3c-master.c +++ b/drivers/i3c/master/adi-i3c-master.c @@ -967,17 +967,9 @@ static int adi_i3c_master_probe(struct platform_device *pdev) writel(0x00, master->regs + REG_ENABLE); writel(0x00, master->regs + REG_IRQ_MASK); - ret = devm_request_irq(&pdev->dev, irq, adi_i3c_master_irq, 0, - dev_name(&pdev->dev), master); - if (ret) - return ret; - platform_set_drvdata(pdev, master); master->free_rr_slots = GENMASK(ADI_MAX_DEVS, 1); - - writel(REG_IRQ_PENDING_CMDR, master->regs + REG_IRQ_MASK); - spin_lock_init(&master->ibi.lock); master->ibi.num_slots = 15; master->ibi.slots = devm_kcalloc(&pdev->dev, master->ibi.num_slots, @@ -989,6 +981,13 @@ static int adi_i3c_master_probe(struct platform_device *pdev) spin_lock_init(&master->xferqueue.lock); INIT_LIST_HEAD(&master->xferqueue.list); + ret = devm_request_irq(&pdev->dev, irq, adi_i3c_master_irq, 0, + dev_name(&pdev->dev), master); + if (ret) + return ret; + + writel(REG_IRQ_PENDING_CMDR, master->regs + REG_IRQ_MASK); + return i3c_master_register(&master->base, &pdev->dev, &adi_i3c_master_ops, false); } diff --git a/drivers/i3c/master/renesas-i3c.c b/drivers/i3c/master/renesas-i3c.c index 5b1bf5a0266c..b6c4dfc51fe5 100644 --- a/drivers/i3c/master/renesas-i3c.c +++ b/drivers/i3c/master/renesas-i3c.c @@ -428,6 +428,21 @@ static void renesas_i3c_enqueue_xfer(struct renesas_i3c *i3c, struct renesas_i3c } } +static void renesas_i3c_irqs_mask_and_clear_locked(struct renesas_i3c *i3c) +{ + /* Disable all the interrupts. */ + renesas_writel(i3c->regs, BIE, 0); + renesas_writel(i3c->regs, NTIE, 0); + + /* Clear normal transfer status flags. */ + renesas_writel(i3c->regs, NTST, 0); + + /* Clear bus status flags. */ + renesas_writel(i3c->regs, BST, 0); + /* Read back registers to confirm writes have fully propagated. */ + renesas_readl(i3c->regs, BST); +} + static void renesas_i3c_wait_xfer(struct renesas_i3c *i3c, struct renesas_i3c_xfer *xfer) { unsigned long time_left; @@ -878,10 +893,26 @@ static int renesas_i3c_reattach_i3c_dev(struct i3c_dev_desc *dev, struct i3c_master_controller *m = i3c_dev_get_master(dev); struct renesas_i3c *i3c = to_renesas_i3c(m); struct renesas_i3c_i2c_dev_data *data = i3c_dev_get_master_data(dev); + int pos; + + pos = renesas_i3c_get_free_pos(i3c); + + if (data->index > pos && pos >= 0) { + renesas_writel(i3c->regs, DATBAS(data->index), 0); + i3c->addrs[data->index] = 0; + i3c->free_pos |= BIT(data->index); + + data->index = pos; + i3c->free_pos &= ~BIT(data->index); + } i3c->addrs[data->index] = dev->info.dyn_addr ? dev->info.dyn_addr : dev->info.static_addr; + renesas_writel(i3c->regs, DATBAS(data->index), + DATBAS_DVSTAD(dev->info.static_addr) | + datbas_dvdyad_with_parity(i3c->addrs[data->index])); + return 0; } @@ -891,6 +922,8 @@ static void renesas_i3c_detach_i3c_dev(struct i3c_dev_desc *dev) struct i3c_master_controller *m = i3c_dev_get_master(dev); struct renesas_i3c *i3c = to_renesas_i3c(m); + renesas_writel(i3c->regs, DATBAS(data->index), 0); + i3c_dev_set_master_data(dev, NULL); i3c->addrs[data->index] = 0; i3c->free_pos |= BIT(data->index); @@ -1000,6 +1033,11 @@ static irqreturn_t renesas_i3c_tx_isr(int irq, void *data) scoped_guard(spinlock, &i3c->xferqueue.lock) { xfer = i3c->xferqueue.cur; + if (!xfer) { + renesas_i3c_irqs_mask_and_clear_locked(i3c); + return IRQ_HANDLED; + } + cmd = xfer->cmds; if (xfer->is_i2c_xfer) { @@ -1040,6 +1078,11 @@ static irqreturn_t renesas_i3c_resp_isr(int irq, void *data) scoped_guard(spinlock, &i3c->xferqueue.lock) { xfer = i3c->xferqueue.cur; + if (!xfer) { + renesas_i3c_irqs_mask_and_clear_locked(i3c); + return IRQ_HANDLED; + } + cmd = xfer->cmds; /* Clear the Respone Queue Full status flag*/ @@ -1124,6 +1167,11 @@ static irqreturn_t renesas_i3c_tend_isr(int irq, void *data) scoped_guard(spinlock, &i3c->xferqueue.lock) { xfer = i3c->xferqueue.cur; + if (!xfer) { + renesas_i3c_irqs_mask_and_clear_locked(i3c); + return IRQ_HANDLED; + } + cmd = xfer->cmds; if (xfer->is_i2c_xfer) { @@ -1170,6 +1218,11 @@ static irqreturn_t renesas_i3c_rx_isr(int irq, void *data) scoped_guard(spinlock, &i3c->xferqueue.lock) { xfer = i3c->xferqueue.cur; + if (!xfer) { + renesas_i3c_irqs_mask_and_clear_locked(i3c); + return IRQ_HANDLED; + } + cmd = xfer->cmds; if (xfer->is_i2c_xfer) { @@ -1220,15 +1273,13 @@ static irqreturn_t renesas_i3c_stop_isr(int irq, void *data) struct renesas_i3c_xfer *xfer; scoped_guard(spinlock, &i3c->xferqueue.lock) { - xfer = i3c->xferqueue.cur; - - /* read back registers to confirm writes have fully propagated */ - renesas_writel(i3c->regs, BST, 0); - renesas_readl(i3c->regs, BST); - renesas_writel(i3c->regs, BIE, 0); - renesas_clear_bit(i3c->regs, NTST, NTST_TDBEF0 | NTST_RDBFF0); + renesas_i3c_irqs_mask_and_clear_locked(i3c); renesas_clear_bit(i3c->regs, SCSTRCTL, SCSTRCTL_RWE); + xfer = i3c->xferqueue.cur; + if (!xfer) + return IRQ_HANDLED; + xfer->ret = 0; complete(&xfer->comp); } @@ -1245,6 +1296,11 @@ static irqreturn_t renesas_i3c_start_isr(int irq, void *data) scoped_guard(spinlock, &i3c->xferqueue.lock) { xfer = i3c->xferqueue.cur; + if (!xfer) { + renesas_i3c_irqs_mask_and_clear_locked(i3c); + return IRQ_HANDLED; + } + cmd = xfer->cmds; if (xfer->is_i2c_xfer) { diff --git a/drivers/i3c/master/svc-i3c-master.c b/drivers/i3c/master/svc-i3c-master.c index d33f4c765497..b6a697173e19 100644 --- a/drivers/i3c/master/svc-i3c-master.c +++ b/drivers/i3c/master/svc-i3c-master.c @@ -418,14 +418,22 @@ static int svc_i3c_master_handle_ibi(struct svc_i3c_master *master, buf = slot->data; while (SVC_I3C_MSTATUS_RXPEND(readl(master->regs + SVC_I3C_MSTATUS)) && - slot->len < SVC_I3C_FIFO_SIZE) { + slot->len < dev->ibi->max_payload_len) { mdatactrl = readl(master->regs + SVC_I3C_MDATACTRL); count = SVC_I3C_MDATACTRL_RXCOUNT(mdatactrl); + count = min(count, dev->ibi->max_payload_len - slot->len); readsb(master->regs + SVC_I3C_MRDATAB, buf, count); slot->len += count; buf += count; } + /* + * The device may have sent more than the requested payload. Drop the + * extra bytes so they do not leak into the next transfer. + */ + if (SVC_I3C_MSTATUS_RXPEND(readl(master->regs + SVC_I3C_MSTATUS))) + writel(SVC_I3C_MDATACTRL_FLUSHRB, master->regs + SVC_I3C_MDATACTRL); + master->ibi.tbq_slot = slot; return 0; diff --git a/drivers/infiniband/core/ucma.c b/drivers/infiniband/core/ucma.c index f86ece701db6..5d76879218ad 100644 --- a/drivers/infiniband/core/ucma.c +++ b/drivers/infiniband/core/ucma.c @@ -1404,7 +1404,10 @@ static int ucma_set_ib_path(struct ucma_context *ctx, memset(&event, 0, sizeof event); event.event = RDMA_CM_EVENT_ROUTE_RESOLVED; - return ucma_event_handler(ctx->cm_id, &event); + rdma_lock_handler(ctx->cm_id); + ret = ucma_event_handler(ctx->cm_id, &event); + rdma_unlock_handler(ctx->cm_id); + return ret; } static int ucma_set_option_ib(struct ucma_context *ctx, int optname, @@ -1776,6 +1779,13 @@ static ssize_t ucma_write_cm_event(struct ucma_file *file, goto out; } + rdma_lock_handler(ctx->cm_id); + if (!ctx->uid) { + kfree(uevent); + ret = -EINVAL; + goto err_unlock; + } + uevent->ctx = ctx; uevent->resp.uid = ctx->uid; uevent->resp.id = ctx->id; @@ -1789,6 +1799,8 @@ static ssize_t ucma_write_cm_event(struct ucma_file *file, mutex_unlock(&ctx->file->mut); wake_up_interruptible(&ctx->file->poll_wait); +err_unlock: + rdma_unlock_handler(ctx->cm_id); out: ucma_put_ctx(ctx); return ret; diff --git a/drivers/infiniband/core/uverbs_std_types_mr.c b/drivers/infiniband/core/uverbs_std_types_mr.c index 570b9656801d..0c72f801e0d3 100644 --- a/drivers/infiniband/core/uverbs_std_types_mr.c +++ b/drivers/infiniband/core/uverbs_std_types_mr.c @@ -364,7 +364,8 @@ static int UVERBS_HANDLER(UVERBS_METHOD_REG_MR)( dmah, attrs); else mr = pd->device->ops.reg_user_mr(pd, addr, length, iova, - access_flags, dmah, NULL); + access_flags, dmah, + &attrs->driver_udata); if (IS_ERR(mr)) return PTR_ERR(mr); @@ -527,7 +528,8 @@ DECLARE_UVERBS_NAMED_METHOD( UA_MANDATORY), UVERBS_ATTR_PTR_OUT(UVERBS_ATTR_REG_MR_RESP_RKEY, UVERBS_ATTR_TYPE(u32), - UA_MANDATORY)); + UA_MANDATORY), + UVERBS_ATTR_UHW()); DECLARE_UVERBS_NAMED_METHOD_DESTROY( UVERBS_METHOD_MR_DESTROY, diff --git a/drivers/infiniband/hw/cxgb4/device.c b/drivers/infiniband/hw/cxgb4/device.c index d892f55febe2..d03936d007b0 100644 --- a/drivers/infiniband/hw/cxgb4/device.c +++ b/drivers/infiniband/hw/cxgb4/device.c @@ -952,6 +952,12 @@ void c4iw_dealloc(struct uld_ctx *ctx) static void c4iw_remove(struct uld_ctx *ctx) { pr_debug("c4iw_dev %p\n", ctx->dev); + + /* c4iw_register_device() may still be using ctx->dev. */ + cancel_work_sync(&ctx->reg_work); + if (!ctx->dev) + return; + debugfs_remove_recursive(ctx->dev->debugfs_root); c4iw_unregister_device(ctx->dev); c4iw_dealloc(ctx); diff --git a/drivers/infiniband/hw/ionic/ionic_lif_cfg.c b/drivers/infiniband/hw/ionic/ionic_lif_cfg.c index f3cd281c3a2f..45846dc2e89b 100644 --- a/drivers/infiniband/hw/ionic/ionic_lif_cfg.c +++ b/drivers/infiniband/hw/ionic/ionic_lif_cfg.c @@ -70,7 +70,7 @@ void ionic_fill_lif_cfg(struct ionic_lif *lif, struct ionic_lif_cfg *cfg) * eq_count is tunable; see ionic_eq_count */ cfg->aq_count = le32_to_cpu(ident->rdma.aq_qtype.qid_count); - cfg->eq_count = le32_to_cpu(ident->rdma.eq_qtype.qid_count); + cfg->eq_count = lif->ionic->neqs_per_lif; cfg->cq_count = le32_to_cpu(ident->rdma.cq_qtype.qid_count); cfg->qp_count = le32_to_cpu(ident->rdma.sq_qtype.qid_count); cfg->dbid_count = le32_to_cpu(lif->ionic->ident.dev.ndbpgs_per_lif); diff --git a/drivers/interconnect/core.c b/drivers/interconnect/core.c index 6cc979b26151..cb99cb13089a 100644 --- a/drivers/interconnect/core.c +++ b/drivers/interconnect/core.c @@ -528,7 +528,7 @@ struct icc_path *of_icc_get_by_index(struct device *dev, int idx) path->name = kasprintf(GFP_KERNEL, "%s-%s", src_data->node->name, dst_data->node->name); if (!path->name) { - kfree(path); + icc_put(path); path = ERR_PTR(-ENOMEM); } @@ -626,8 +626,9 @@ struct icc_path *icc_get(struct device *dev, const char *src, const char *dst) path->name = kasprintf(GFP_KERNEL, "%s-%s", src_node->name, dst_node->name); if (!path->name) { - kfree(path); - path = ERR_PTR(-ENOMEM); + mutex_unlock(&icc_lock); + icc_put(path); + return ERR_PTR(-ENOMEM); } out: mutex_unlock(&icc_lock); diff --git a/drivers/iommu/amd/ppr.c b/drivers/iommu/amd/ppr.c index 1f8d2823bea4..80369ca1e316 100644 --- a/drivers/iommu/amd/ppr.c +++ b/drivers/iommu/amd/ppr.c @@ -151,7 +151,7 @@ static void iommu_call_iopf_notifier(struct amd_iommu *iommu, u64 *raw) /* Submit event */ iommu_report_device_fault(&pdev->dev, &event); - + pci_dev_put(pdev); return; out: @@ -159,6 +159,7 @@ out: amd_iommu_complete_ppr(&pdev->dev, PPR_PASID(raw[0]), IOMMU_PAGE_RESP_FAILURE, PPR_TAG(raw[0]) & 0x1FF); + pci_dev_put(pdev); } void amd_iommu_poll_ppr_log(struct amd_iommu *iommu) diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c index 7d18c6f9328a..daf8b87fdf08 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c @@ -3837,6 +3837,20 @@ int arm_smmu_cmdq_init(struct arm_smmu_device *smmu, return 0; } +static void arm_smmu_free_iopf_action(void *data) +{ + struct iopf_queue *queue = data; + + iopf_queue_free(queue); +} + +static void arm_smmu_destroy_vmid_map(void *data) +{ + struct ida *ida = data; + + ida_destroy(ida); +} + static int arm_smmu_init_queues(struct arm_smmu_device *smmu) { int ret; @@ -3864,6 +3878,11 @@ static int arm_smmu_init_queues(struct arm_smmu_device *smmu) smmu->evtq.iopf = iopf_queue_alloc(dev_name(smmu->dev)); if (!smmu->evtq.iopf) return -ENOMEM; + ret = devm_add_action_or_reset(smmu->dev, + arm_smmu_free_iopf_action, + smmu->evtq.iopf); + if (ret) + return ret; } /* priq */ @@ -3942,7 +3961,8 @@ static int arm_smmu_init_strtab(struct arm_smmu_device *smmu) ida_init(&smmu->vmid_map); - return 0; + return devm_add_action_or_reset(smmu->dev, arm_smmu_destroy_vmid_map, + &smmu->vmid_map); } static int arm_smmu_init_structures(struct arm_smmu_device *smmu) @@ -4155,6 +4175,13 @@ static int arm_smmu_device_disable(struct arm_smmu_device *smmu) return ret; } +static void arm_smmu_disable_action(void *data) +{ + struct arm_smmu_device *smmu = data; + + arm_smmu_device_disable(smmu); +} + static void arm_smmu_write_strtab(struct arm_smmu_device *smmu) { struct arm_smmu_strtab_cfg *cfg = &smmu->strtab_cfg; @@ -4878,7 +4905,7 @@ static int arm_smmu_device_probe(struct platform_device *pdev) /* Initialise in-memory data structures */ ret = arm_smmu_init_structures(smmu); if (ret) - goto err_free_iopf; + return ret; /* Record our private device structure */ platform_set_drvdata(pdev, smmu); @@ -4888,30 +4915,30 @@ static int arm_smmu_device_probe(struct platform_device *pdev) /* Reset the device */ ret = arm_smmu_device_reset(smmu); + if (ret) { + arm_smmu_device_disable(smmu); + return ret; + } + + /* Register last so it unwinds first, while the CMDQ is still up. */ + ret = devm_add_action_or_reset(smmu->dev, arm_smmu_disable_action, smmu); if (ret) - goto err_disable; + return ret; /* And we're up. Go go go! */ ret = iommu_device_sysfs_add(&smmu->iommu, dev, NULL, "smmu3.%pa", &ioaddr); if (ret) - goto err_disable; + return ret; ret = iommu_device_register(&smmu->iommu, &arm_smmu_ops, dev); if (ret) { dev_err(dev, "Failed to register iommu\n"); - goto err_free_sysfs; + iommu_device_sysfs_remove(&smmu->iommu); + return ret; } return 0; - -err_free_sysfs: - iommu_device_sysfs_remove(&smmu->iommu); -err_disable: - arm_smmu_device_disable(smmu); -err_free_iopf: - iopf_queue_free(smmu->evtq.iopf); - return ret; } static void arm_smmu_device_remove(struct platform_device *pdev) @@ -4920,9 +4947,6 @@ static void arm_smmu_device_remove(struct platform_device *pdev) iommu_device_unregister(&smmu->iommu); iommu_device_sysfs_remove(&smmu->iommu); - arm_smmu_device_disable(smmu); - iopf_queue_free(smmu->evtq.iopf); - ida_destroy(&smmu->vmid_map); } static void arm_smmu_device_shutdown(struct platform_device *pdev) diff --git a/drivers/iommu/arm/arm-smmu-v3/tegra241-cmdqv.c b/drivers/iommu/arm/arm-smmu-v3/tegra241-cmdqv.c index 2f0f9a2f74d9..cee489855311 100644 --- a/drivers/iommu/arm/arm-smmu-v3/tegra241-cmdqv.c +++ b/drivers/iommu/arm/arm-smmu-v3/tegra241-cmdqv.c @@ -58,6 +58,8 @@ #define VINTF_ENABLED BIT(0) #define TEGRA241_VINTF_SID_MATCH(s) (0x0040 + 0x4*(s)) +#define VINTF_SID_MATCH_VIRT_SID GENMASK(20, 1) +#define VINTF_SID_MATCH_ENABLE BIT(0) #define TEGRA241_VINTF_SID_REPLACE(s) (0x0080 + 0x4*(s)) #define TEGRA241_VINTF_LVCMDQ_ERR_MAP_64(m) \ @@ -1249,7 +1251,7 @@ static int tegra241_vintf_init_vsid(struct iommufd_vdevice *vdev) u64 virt_sid = vdev->virt_id; int sidx; - if (virt_sid > UINT_MAX) + if (virt_sid > FIELD_MAX(VINTF_SID_MATCH_VIRT_SID)) return -EINVAL; WARN_ON_ONCE(master->num_streams != 1); @@ -1261,7 +1263,9 @@ static int tegra241_vintf_init_vsid(struct iommufd_vdevice *vdev) return sidx; writel(stream->id, REG_VINTF(vintf, SID_REPLACE(sidx))); - writel(virt_sid << 1 | 0x1, REG_VINTF(vintf, SID_MATCH(sidx))); + writel(FIELD_PREP(VINTF_SID_MATCH_VIRT_SID, virt_sid) | + VINTF_SID_MATCH_ENABLE, + REG_VINTF(vintf, SID_MATCH(sidx))); dev_dbg(vintf->cmdqv->dev, "VINTF%u: allocated SID_REPLACE%d for pSID=%x, vSID=%x\n", vintf->idx, sidx, stream->id, (u32)virt_sid); diff --git a/drivers/iommu/intel/dmar.c b/drivers/iommu/intel/dmar.c index 6938800e9884..f4bdc5ffa9d9 100644 --- a/drivers/iommu/intel/dmar.c +++ b/drivers/iommu/intel/dmar.c @@ -915,6 +915,18 @@ dmar_validate_one_drhd(struct acpi_dmar_header *entry, void *arg) return 0; } +static bool dmar_required(void) +{ + /* tboot supersedes any user/platform opt */ + if (!intel_iommu_tboot_noforce && tboot_enabled()) + return true; + + if (!no_iommu && (!dmar_disabled || dmar_platform_optin())) + return true; + + return false; +} + void __init detect_intel_iommu(void) { int ret; @@ -928,8 +940,7 @@ void __init detect_intel_iommu(void) if (!ret) ret = dmar_walk_dmar_table((struct acpi_table_dmar *)dmar_tbl, &validate_drhd_cb); - if (!ret && !no_iommu && !iommu_detected && - (!dmar_disabled || dmar_platform_optin())) { + if (!ret && !iommu_detected && dmar_required()) { iommu_detected = 1; /* Make sure ACS will be enabled */ pci_request_acs(); diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index 8b38c65f403b..aec1a05d48d0 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -64,7 +64,7 @@ static int rwbf_quirk; * (used when kernel is launched w/ TXT) */ static int force_on = 0; -static int intel_iommu_tboot_noforce; +int intel_iommu_tboot_noforce; static int no_platform_optin; #define ROOT_ENTRY_NR (VTD_PAGE_SIZE/sizeof(struct root_entry)) @@ -2956,10 +2956,11 @@ static bool has_external_pci(void) static int __init platform_optin_force_iommu(void) { - if (!dmar_platform_optin() || no_platform_optin || !has_external_pci()) + if (no_iommu || !dmar_platform_optin() || no_platform_optin || + !has_external_pci()) return 0; - if (no_iommu || dmar_disabled) + if (dmar_disabled) pr_info("Intel-IOMMU force enabled due to platform opt in\n"); /* @@ -2970,7 +2971,6 @@ static int __init platform_optin_force_iommu(void) iommu_set_default_passthrough(false); dmar_disabled = 0; - no_iommu = 0; return 1; } diff --git a/drivers/iommu/intel/iommu.h b/drivers/iommu/intel/iommu.h index 6b11081e690f..8e2df00e881c 100644 --- a/drivers/iommu/intel/iommu.h +++ b/drivers/iommu/intel/iommu.h @@ -1434,6 +1434,7 @@ static inline bool ecmd_has_pmu_essential(struct intel_iommu *iommu) extern int dmar_disabled; extern int intel_iommu_enabled; +extern int intel_iommu_tboot_noforce; #else static inline int iommu_calculate_agaw(struct intel_iommu *iommu) { @@ -1446,6 +1447,7 @@ static inline int iommu_calculate_max_sagaw(struct intel_iommu *iommu) #define dmar_disabled (1) #define intel_iommu_enabled (0) #define intel_iommu_sm (0) +#define intel_iommu_tboot_noforce (0) #endif static inline const char *decode_prq_descriptor(char *str, size_t size, diff --git a/drivers/iommu/iommu-sva.c b/drivers/iommu/iommu-sva.c index fd735aaae9e3..838563fc4431 100644 --- a/drivers/iommu/iommu-sva.c +++ b/drivers/iommu/iommu-sva.c @@ -145,8 +145,8 @@ struct iommu_sva *iommu_sva_bind_device(struct device *dev, struct mm_struct *mm list_add(&domain->next, &iommu_mm->sva_domains); out: refcount_set(&handle->users, 1); - mutex_unlock(&iommu_sva_lock); handle->dev = dev; + mutex_unlock(&iommu_sva_lock); return handle; out_free_domain: diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index 59244c744eab..1547f3587a4e 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -360,7 +360,7 @@ int iommu_mock_device_add(struct device *dev, struct iommu_device *iommu) rc = device_add(dev); if (rc) - iommu_fwspec_free(dev); + dev_iommu_free(dev); return rc; } EXPORT_SYMBOL_GPL(iommu_mock_device_add); diff --git a/drivers/iommu/iommufd/device.c b/drivers/iommu/iommufd/device.c index 5c7ead633edd..c40515bf5017 100644 --- a/drivers/iommu/iommufd/device.c +++ b/drivers/iommu/iommufd/device.c @@ -1307,8 +1307,8 @@ void iommufd_access_notify_unmap(struct io_pagetable *iopt, unsigned long iova, xa_lock(&ioas->iopt.access_list); xa_for_each(&ioas->iopt.access_list, index, access) { - if (!iommufd_lock_obj(&access->obj) || - iommufd_access_is_internal(access)) + if (iommufd_access_is_internal(access) || + !iommufd_lock_obj(&access->obj)) continue; xa_unlock(&ioas->iopt.access_list); diff --git a/drivers/iommu/iommufd/ioas.c b/drivers/iommu/iommufd/ioas.c index cb1d2248393a..164612195905 100644 --- a/drivers/iommu/iommufd/ioas.c +++ b/drivers/iommu/iommufd/ioas.c @@ -433,6 +433,8 @@ static int iommufd_take_all_iova_rwsem(struct iommufd_ctx *ictx, rc = xa_err(xa_store(ioas_list, index, ioas, GFP_KERNEL)); if (rc) { + up_write(&ioas->iopt.iova_rwsem); + refcount_dec(&ioas->obj.users); iommufd_release_all_iova_rwsem(ictx, ioas_list); return rc; } diff --git a/drivers/iommu/iommufd/selftest.c b/drivers/iommu/iommufd/selftest.c index 8fd27f65d623..35c42ff4355a 100644 --- a/drivers/iommu/iommufd/selftest.c +++ b/drivers/iommu/iommufd/selftest.c @@ -183,6 +183,7 @@ struct mock_dev { struct device dev; struct mock_viommu *viommu; struct rw_semaphore viommu_rwsem; + struct rw_semaphore iopf_rwsem; unsigned long flags; unsigned long vdev_id; int id; @@ -1101,6 +1102,7 @@ static struct mock_dev *mock_dev_create(unsigned long dev_flags) return ERR_PTR(-ENOMEM); init_rwsem(&mdev->viommu_rwsem); + init_rwsem(&mdev->iopf_rwsem); device_initialize(&mdev->dev); mdev->flags = dev_flags; mdev->dev.release = mock_dev_release; @@ -1126,7 +1128,9 @@ static struct mock_dev *mock_dev_create(unsigned long dev_flags) goto err_put; } + down_write(&mdev->iopf_rwsem); rc = iommu_mock_device_add(&mdev->dev, &mock_iommu.iommu_dev); + up_write(&mdev->iopf_rwsem); if (rc) goto err_put; return mdev; @@ -1181,7 +1185,9 @@ static int iommufd_test_mock_domain(struct iommufd_ucmd *ucmd, } sobj->idev.idev = idev; + down_write(&sobj->idev.mock_dev->iopf_rwsem); rc = iommufd_device_attach(idev, IOMMU_NO_PASID, &pt_id); + up_write(&sobj->idev.mock_dev->iopf_rwsem); if (rc) goto out_unbind; @@ -1196,7 +1202,9 @@ static int iommufd_test_mock_domain(struct iommufd_ucmd *ucmd, return 0; out_detach: + down_write(&sobj->idev.mock_dev->iopf_rwsem); iommufd_device_detach(idev, IOMMU_NO_PASID); + up_write(&sobj->idev.mock_dev->iopf_rwsem); out_unbind: iommufd_device_unbind(idev); out_mdev: @@ -1240,7 +1248,9 @@ static int iommufd_test_mock_domain_replace(struct iommufd_ucmd *ucmd, if (IS_ERR(sobj)) return PTR_ERR(sobj); + down_write(&sobj->idev.mock_dev->iopf_rwsem); rc = iommufd_device_replace(sobj->idev.idev, IOMMU_NO_PASID, &pt_id); + up_write(&sobj->idev.mock_dev->iopf_rwsem); if (rc) goto out_sobj; @@ -1852,10 +1862,16 @@ static int iommufd_test_trigger_iopf(struct iommufd_ucmd *ucmd, { struct iopf_fault event = {}; struct iommufd_device *idev; + struct mock_dev *mdev; idev = iommufd_get_device(ucmd, cmd->trigger_iopf.dev_id); if (IS_ERR(idev)) return PTR_ERR(idev); + if (!iommufd_selftest_is_mock_dev(idev->dev)) { + iommufd_put_object(ucmd->ictx, &idev->obj); + return -EINVAL; + } + mdev = to_mock_dev(idev->dev); event.fault.prm.flags = IOMMU_FAULT_PAGE_REQUEST_LAST_PAGE; if (cmd->trigger_iopf.pasid != IOMMU_NO_PASID) @@ -1866,7 +1882,9 @@ static int iommufd_test_trigger_iopf(struct iommufd_ucmd *ucmd, event.fault.prm.grpid = cmd->trigger_iopf.grpid; event.fault.prm.perm = cmd->trigger_iopf.perm; + down_read(&mdev->iopf_rwsem); iommu_report_device_fault(idev->dev, &event); + up_read(&mdev->iopf_rwsem); iommufd_put_object(ucmd->ictx, &idev->obj); return 0; @@ -1974,14 +1992,19 @@ static int iommufd_test_pasid_attach(struct iommufd_ucmd *ucmd, if (IS_ERR(sobj)) return PTR_ERR(sobj); + down_write(&sobj->idev.mock_dev->iopf_rwsem); rc = iommufd_device_attach(sobj->idev.idev, cmd->pasid_attach.pasid, &cmd->pasid_attach.pt_id); + up_write(&sobj->idev.mock_dev->iopf_rwsem); if (rc) goto out_sobj; rc = iommufd_ucmd_respond(ucmd, sizeof(*cmd)); - if (rc) + if (rc) { + down_write(&sobj->idev.mock_dev->iopf_rwsem); iommufd_device_detach(sobj->idev.idev, cmd->pasid_attach.pasid); + up_write(&sobj->idev.mock_dev->iopf_rwsem); + } out_sobj: iommufd_put_object(ucmd->ictx, &sobj->obj); @@ -1998,8 +2021,10 @@ static int iommufd_test_pasid_replace(struct iommufd_ucmd *ucmd, if (IS_ERR(sobj)) return PTR_ERR(sobj); + down_write(&sobj->idev.mock_dev->iopf_rwsem); rc = iommufd_device_replace(sobj->idev.idev, cmd->pasid_attach.pasid, &cmd->pasid_attach.pt_id); + up_write(&sobj->idev.mock_dev->iopf_rwsem); if (rc) goto out_sobj; @@ -2019,7 +2044,9 @@ static int iommufd_test_pasid_detach(struct iommufd_ucmd *ucmd, if (IS_ERR(sobj)) return PTR_ERR(sobj); + down_write(&sobj->idev.mock_dev->iopf_rwsem); iommufd_device_detach(sobj->idev.idev, cmd->pasid_detach.pasid); + up_write(&sobj->idev.mock_dev->iopf_rwsem); iommufd_put_object(ucmd->ictx, &sobj->obj); return 0; } @@ -2030,7 +2057,9 @@ void iommufd_selftest_destroy(struct iommufd_object *obj) switch (sobj->type) { case TYPE_IDEV: + down_write(&sobj->idev.mock_dev->iopf_rwsem); iommufd_device_detach(sobj->idev.idev, IOMMU_NO_PASID); + up_write(&sobj->idev.mock_dev->iopf_rwsem); iommufd_device_unbind(sobj->idev.idev); mock_dev_destroy(sobj->idev.mock_dev); break; diff --git a/drivers/iommu/msm_iommu.c b/drivers/iommu/msm_iommu.c index 43a61ba021a5..d5e2fc9b0111 100644 --- a/drivers/iommu/msm_iommu.c +++ b/drivers/iommu/msm_iommu.c @@ -783,19 +783,25 @@ static int msm_iommu_probe(struct platform_device *pdev) "msm-smmu.%pa", &ioaddr); if (ret) { pr_err("Could not add msm-smmu at %pa to sysfs\n", &ioaddr); - return ret; + goto err_remove_list; } ret = iommu_device_register(&iommu->iommu, &msm_iommu_ops, &pdev->dev); if (ret) { pr_err("Could not register msm-smmu at %pa\n", &ioaddr); - return ret; + goto err_remove_sysfs; } pr_info("device mapped at %p, irq %d with %d ctx banks\n", iommu->base, iommu->irq, iommu->ncb); return ret; + +err_remove_sysfs: + iommu_device_sysfs_remove(&iommu->iommu); +err_remove_list: + list_del(&iommu->dev_node); + return ret; } static const struct of_device_id msm_iommu_dt_match[] = { diff --git a/drivers/mailbox/qcom-ipcc.c b/drivers/mailbox/qcom-ipcc.c index d957d989c0ce..dead907aa7a2 100644 --- a/drivers/mailbox/qcom-ipcc.c +++ b/drivers/mailbox/qcom-ipcc.c @@ -167,7 +167,7 @@ static struct mbox_chan *qcom_ipcc_mbox_xlate(struct mbox_controller *mbox, { struct qcom_ipcc *ipcc = to_qcom_ipcc(mbox); struct qcom_ipcc_chan_info *mchan; - struct mbox_chan *chan; + struct mbox_chan *chan, *free_chan = NULL; struct device *dev; int chan_id; @@ -180,16 +180,21 @@ static struct mbox_chan *qcom_ipcc_mbox_xlate(struct mbox_controller *mbox, chan = &ipcc->chans[chan_id]; mchan = chan->con_priv; - if (!mchan) - break; - else if (mchan->client_id == ph->args[0] && - mchan->signal_id == ph->args[1]) + if (!mchan) { + /* Keep scanning past holes to reject duplicate channel requests. */ + if (!free_chan) + free_chan = chan; + } else if (mchan->client_id == ph->args[0] && + mchan->signal_id == ph->args[1]) { return ERR_PTR(-EBUSY); + } } - if (chan_id >= mbox->num_chans) + if (!free_chan) return ERR_PTR(-EBUSY); + chan = free_chan; + mchan = devm_kzalloc(dev, sizeof(*mchan), GFP_KERNEL); if (!mchan) return ERR_PTR(-ENOMEM); diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c index b7cbe5874094..59e5d8aa42b7 100644 --- a/drivers/md/dm-bufio.c +++ b/drivers/md/dm-bufio.c @@ -1282,11 +1282,11 @@ static void free_buffer(struct dm_buffer *b) * dm-io completion routine. It just calls b->bio.bi_end_io, pretending * that the request was handled directly with bio interface. */ -static void dmio_complete(unsigned long error, void *context) +static void dmio_complete(unsigned long error, unsigned long unsup, void *context) { struct dm_buffer *b = context; - b->end_io(b, unlikely(error != 0) ? BLK_STS_IOERR : 0); + b->end_io(b, unlikely(error != 0) ? BLK_STS_IOERR : unlikely(unsup != 0) ? BLK_STS_NOTSUPP : 0); } static void use_dmio(struct dm_buffer *b, enum req_op op, sector_t sector, @@ -1314,7 +1314,7 @@ static void use_dmio(struct dm_buffer *b, enum req_op op, sector_t sector, io_req.mem.ptr.vma = (char *)b->data + offset; } - r = dm_io(&io_req, 1, ®ion, NULL, ioprio); + r = dm_io(&io_req, 1, ®ion, NULL, NULL, ioprio); if (unlikely(r)) b->end_io(b, errno_to_blk_status(r)); } @@ -2197,7 +2197,7 @@ int dm_bufio_issue_flush(struct dm_bufio_client *c) if (WARN_ON_ONCE(dm_bufio_in_request())) return -EINVAL; - return dm_io(&io_req, 1, &io_reg, NULL, IOPRIO_DEFAULT); + return dm_io(&io_req, 1, &io_reg, NULL, NULL, IOPRIO_DEFAULT); } EXPORT_SYMBOL_GPL(dm_bufio_issue_flush); @@ -2223,7 +2223,7 @@ int dm_bufio_issue_discard(struct dm_bufio_client *c, sector_t block, sector_t c if (WARN_ON_ONCE(dm_bufio_in_request())) return -EINVAL; /* discards are optional */ - return dm_io(&io_req, 1, &io_reg, NULL, IOPRIO_DEFAULT); + return dm_io(&io_req, 1, &io_reg, NULL, NULL, IOPRIO_DEFAULT); } EXPORT_SYMBOL_GPL(dm_bufio_issue_discard); diff --git a/drivers/md/dm-era-target.c b/drivers/md/dm-era-target.c index 883d1549cfc0..6f87e2c4e7da 100644 --- a/drivers/md/dm-era-target.c +++ b/drivers/md/dm-era-target.c @@ -1034,6 +1034,7 @@ static int metadata_checkpoint(struct era_metadata *md) static int metadata_take_snap(struct era_metadata *md) { int r, inc; + dm_block_t location; struct dm_block *clone; if (md->metadata_snap != SUPERBLOCK_LOCATION) { @@ -1071,7 +1072,9 @@ static int metadata_take_snap(struct era_metadata *md) r = dm_sm_inc_block(md->sm, md->writeset_tree_root); if (r) { DMERR("%s: couldn't inc writeset tree root", __func__); + location = dm_block_location(clone); dm_tm_unlock(md->tm, clone); + dm_sm_dec_block(md->sm, location); return r; } @@ -1079,7 +1082,9 @@ static int metadata_take_snap(struct era_metadata *md) if (r) { DMERR("%s: couldn't inc era tree root", __func__); dm_sm_dec_block(md->sm, md->writeset_tree_root); + location = dm_block_location(clone); dm_tm_unlock(md->tm, clone); + dm_sm_dec_block(md->sm, location); return r; } diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c index cd602b39481d..46a815f20b09 100644 --- a/drivers/md/dm-integrity.c +++ b/drivers/md/dm-integrity.c @@ -561,7 +561,7 @@ static int sync_rw_sb(struct dm_integrity_c *ic, blk_opf_t opf) } } - r = dm_io(&io_req, 1, &io_loc, NULL, IOPRIO_DEFAULT); + r = dm_io(&io_req, 1, &io_loc, NULL, NULL, IOPRIO_DEFAULT); if (unlikely(r)) return r; @@ -1034,12 +1034,14 @@ static void encrypt_journal(struct dm_integrity_c *ic, bool encrypt, unsigned in return crypt_journal(ic, encrypt, section, n_sections, comp); } -static void complete_journal_io(unsigned long error, void *context) +static void complete_journal_io(unsigned long error, unsigned long unsup, void *context) { struct journal_completion *comp = context; if (unlikely(error != 0)) dm_integrity_io_error(comp->ic, "writing journal", -EIO); + else if (unlikely(unsup != 0)) + dm_integrity_io_error(comp->ic, "writing journal", -EOPNOTSUPP); complete_journal_op(comp); } @@ -1054,7 +1056,7 @@ static void rw_journal_sectors(struct dm_integrity_c *ic, blk_opf_t opf, if (unlikely(dm_integrity_failed(ic))) { if (comp) - complete_journal_io(-1UL, comp); + complete_journal_io(-1UL, -1UL, comp); return; } @@ -1079,13 +1081,13 @@ static void rw_journal_sectors(struct dm_integrity_c *ic, blk_opf_t opf, io_loc.sector = ic->start + SB_SECTORS + sector; io_loc.count = n_sectors; - r = dm_io(&io_req, 1, &io_loc, NULL, IOPRIO_DEFAULT); + r = dm_io(&io_req, 1, &io_loc, NULL, NULL, IOPRIO_DEFAULT); if (unlikely(r)) { dm_integrity_io_error(ic, (opf & REQ_OP_MASK) == REQ_OP_READ ? "reading journal" : "writing journal", r); if (comp) { WARN_ONCE(1, "asynchronous dm_io failed: %d", r); - complete_journal_io(-1UL, comp); + complete_journal_io(-1UL, -1UL, comp); } } } @@ -1176,7 +1178,7 @@ static void copy_from_journal(struct dm_integrity_c *ic, unsigned int section, u BUG_ON((target | n_sectors | offset) & (unsigned int)(ic->sectors_per_block - 1)); if (unlikely(dm_integrity_failed(ic))) { - fn(-1UL, data); + fn(-1UL, -1UL, data); return; } @@ -1196,10 +1198,10 @@ static void copy_from_journal(struct dm_integrity_c *ic, unsigned int section, u io_loc.sector = target; io_loc.count = n_sectors; - r = dm_io(&io_req, 1, &io_loc, NULL, IOPRIO_DEFAULT); + r = dm_io(&io_req, 1, &io_loc, NULL, NULL, IOPRIO_DEFAULT); if (unlikely(r)) { WARN_ONCE(1, "asynchronous dm_io failed: %d", r); - fn(-1UL, data); + fn(-1UL, -1UL, data); } } @@ -1492,12 +1494,14 @@ struct flush_request { struct completion comp; }; -static void flush_notify(unsigned long error, void *fr_) +static void flush_notify(unsigned long error, unsigned long unsup, void *fr_) { struct flush_request *fr = fr_; if (unlikely(error != 0)) dm_integrity_io_error(fr->ic, "flushing disk cache", -EIO); + else if (unlikely(unsup != 0)) + dm_integrity_io_error(fr->ic, "flushing disk cache", -EOPNOTSUPP); complete(&fr->comp); } @@ -1520,7 +1524,7 @@ static void dm_integrity_flush_buffers(struct dm_integrity_c *ic, bool flush_dat fr.io_reg.count = 0; fr.ic = ic; init_completion(&fr.comp); - r = dm_io(&fr.io_req, 1, &fr.io_reg, NULL, IOPRIO_DEFAULT); + r = dm_io(&fr.io_req, 1, &fr.io_reg, NULL, NULL, IOPRIO_DEFAULT); BUG_ON(r); } @@ -1836,7 +1840,7 @@ static noinline void integrity_recheck(struct dm_integrity_io *dio, char *checks buffer_offset = (sector - io_loc.sector) << SECTOR_SHIFT; io_loc.count = round_up(io_loc.count, alignment); - r = dm_io(&io_req, 1, &io_loc, NULL, IOPRIO_DEFAULT); + r = dm_io(&io_req, 1, &io_loc, NULL, NULL, IOPRIO_DEFAULT); if (unlikely(r)) { dio->bi_status = errno_to_blk_status(r); goto free_ret; @@ -2889,7 +2893,7 @@ release_flush_bios: } } -static void complete_copy_from_journal(unsigned long error, void *context) +static void complete_copy_from_journal(unsigned long error, unsigned long unsup, void *context) { struct journal_io *io = context; struct journal_completion *comp = io->comp; @@ -2899,6 +2903,8 @@ static void complete_copy_from_journal(unsigned long error, void *context) mempool_free(io, &ic->journal_io_mempool); if (unlikely(error != 0)) dm_integrity_io_error(ic, "copying from journal", -EIO); + else if (unlikely(unsup != 0)) + dm_integrity_io_error(ic, "copying from journal", -EOPNOTSUPP); complete_journal_op(comp); } @@ -3214,7 +3220,7 @@ next_chunk: io_loc.sector = get_data_sector(ic, area, offset); io_loc.count = n_sectors; - r = dm_io(&io_req, 1, &io_loc, NULL, IOPRIO_DEFAULT); + r = dm_io(&io_req, 1, &io_loc, NULL, NULL, IOPRIO_DEFAULT); if (unlikely(r)) { dm_integrity_io_error(ic, "reading data", r); goto err; diff --git a/drivers/md/dm-io.c b/drivers/md/dm-io.c index c37668790577..c6684e63ceb0 100644 --- a/drivers/md/dm-io.c +++ b/drivers/md/dm-io.c @@ -33,6 +33,7 @@ struct dm_io_client { */ struct io { unsigned long error_bits; + unsigned long unsup_bits; atomic_t count; struct dm_io_client *client; io_notify_fn callback; @@ -119,6 +120,7 @@ static void retrieve_io_and_region_from_bio(struct bio *bio, struct io **io, static void complete_io(struct io *io) { unsigned long error_bits = io->error_bits; + unsigned long unsup_bits = io->unsup_bits; io_notify_fn fn = io->callback; void *context = io->context; @@ -127,13 +129,17 @@ static void complete_io(struct io *io) io->vma_invalidate_size); mempool_free(io, &io->client->pool); - fn(error_bits, context); + fn(error_bits, unsup_bits, context); } static void dec_count(struct io *io, unsigned int region, blk_status_t error) { - if (error) - set_bit(region, &io->error_bits); + if (unlikely(error)) { + if (error == BLK_STS_NOTSUPP || error == BLK_STS_INVAL) + set_bit(region, &io->unsup_bits); + else + set_bit(region, &io->error_bits); + } if (atomic_dec_and_test(&io->count)) complete_io(io); @@ -170,12 +176,11 @@ struct dpages { struct page **p, unsigned long *len, unsigned int *offset); void (*next_page)(struct dpages *dp); - union { - unsigned int context_u; - struct bvec_iter context_bi; - }; + unsigned int context_u; void *context_ptr; + struct bio *orig_bio; + void *vma_invalidate_address; unsigned long vma_invalidate_size; }; @@ -211,44 +216,6 @@ static void list_dp_init(struct dpages *dp, struct page_list *pl, unsigned int o } /* - * Functions for getting the pages from a bvec. - */ -static void bio_get_page(struct dpages *dp, struct page **p, - unsigned long *len, unsigned int *offset) -{ - struct bio_vec bvec = bvec_iter_bvec((struct bio_vec *)dp->context_ptr, - dp->context_bi); - - *p = bvec.bv_page; - *len = bvec.bv_len; - *offset = bvec.bv_offset; - - /* avoid figuring it out again in bio_next_page() */ - dp->context_bi.bi_sector = (sector_t)bvec.bv_len; -} - -static void bio_next_page(struct dpages *dp) -{ - unsigned int len = (unsigned int)dp->context_bi.bi_sector; - - bvec_iter_advance((struct bio_vec *)dp->context_ptr, - &dp->context_bi, len); -} - -static void bio_dp_init(struct dpages *dp, struct bio *bio) -{ - dp->get_page = bio_get_page; - dp->next_page = bio_next_page; - - /* - * We just use bvec iterator to retrieve pages, so it is ok to - * access the bvec table directly here - */ - dp->context_ptr = bio->bi_io_vec; - dp->context_bi = bio->bi_iter; -} - -/* * Functions for getting the pages from a VMA. */ static void vm_get_page(struct dpages *dp, @@ -332,6 +299,21 @@ static void do_region(const blk_opf_t opf, unsigned int region, return; } + if (dp->orig_bio) { + bio = bio_alloc_clone(where->bdev, dp->orig_bio, GFP_NOIO, + &io->client->bios); + bio->bi_iter.bi_sector = where->sector; + bio->bi_iter.bi_size = where->count << SECTOR_SHIFT; + bio->bi_opf = opf; + bio->bi_end_io = endio; + bio->bi_ioprio = ioprio; + store_io_and_region_in_bio(bio, io, region); + + atomic_inc(&io->count); + submit_bio(bio); + return; + } + /* * where->count may be zero if op holds a flush and we need to * send a zero-sized flush. @@ -418,6 +400,7 @@ static void async_io(struct dm_io_client *client, unsigned int num_regions, io = mempool_alloc(&client->pool, GFP_NOIO); io->error_bits = 0; + io->unsup_bits = 0; atomic_set(&io->count, 1); /* see dispatch_io() */ io->client = client; io->callback = fn; @@ -431,20 +414,23 @@ static void async_io(struct dm_io_client *client, unsigned int num_regions, struct sync_io { unsigned long error_bits; + unsigned long unsup_bits; struct completion wait; }; -static void sync_io_complete(unsigned long error, void *context) +static void sync_io_complete(unsigned long error, unsigned long unsup, void *context) { struct sync_io *sio = context; sio->error_bits = error; + sio->unsup_bits = unsup; complete(&sio->wait); } static int sync_io(struct dm_io_client *client, unsigned int num_regions, struct dm_io_region *where, blk_opf_t opf, struct dpages *dp, - unsigned long *error_bits, unsigned short ioprio) + unsigned long *error_bits, unsigned long *unsup_bits, + unsigned short ioprio) { struct sync_io sio; @@ -457,8 +443,10 @@ static int sync_io(struct dm_io_client *client, unsigned int num_regions, if (error_bits) *error_bits = sio.error_bits; + if (unsup_bits) + *unsup_bits = sio.unsup_bits; - return sio.error_bits ? -EIO : 0; + return sio.error_bits ? -EIO : sio.unsup_bits ? -EOPNOTSUPP : 0; } static int dp_init(struct dm_io_request *io_req, struct dpages *dp, @@ -468,6 +456,7 @@ static int dp_init(struct dm_io_request *io_req, struct dpages *dp, dp->vma_invalidate_address = NULL; dp->vma_invalidate_size = 0; + dp->orig_bio = NULL; switch (io_req->mem.type) { case DM_IO_PAGE_LIST: @@ -475,7 +464,11 @@ static int dp_init(struct dm_io_request *io_req, struct dpages *dp, break; case DM_IO_BIO: - bio_dp_init(dp, io_req->mem.ptr.bio); + /* + * The destination bios clone this bio's biovec directly, so + * there are no per-page accessors to set up here. + */ + dp->orig_bio = io_req->mem.ptr.bio; break; case DM_IO_VMA: @@ -500,7 +493,7 @@ static int dp_init(struct dm_io_request *io_req, struct dpages *dp, int dm_io(struct dm_io_request *io_req, unsigned int num_regions, struct dm_io_region *where, unsigned long *sync_error_bits, - unsigned short ioprio) + unsigned long *sync_unsup_bits, unsigned short ioprio) { int r; struct dpages dp; @@ -516,7 +509,8 @@ int dm_io(struct dm_io_request *io_req, unsigned int num_regions, if (!io_req->notify.fn) return sync_io(io_req->client, num_regions, where, - io_req->bi_opf, &dp, sync_error_bits, ioprio); + io_req->bi_opf, &dp, sync_error_bits, + sync_unsup_bits, ioprio); async_io(io_req->client, num_regions, where, io_req->bi_opf, &dp, io_req->notify.fn, io_req->notify.context, ioprio); diff --git a/drivers/md/dm-kcopyd.c b/drivers/md/dm-kcopyd.c index cec9a60227b6..7eecce8711ce 100644 --- a/drivers/md/dm-kcopyd.c +++ b/drivers/md/dm-kcopyd.c @@ -517,16 +517,16 @@ static int run_complete_job(struct kcopyd_job *job) return 0; } -static void complete_io(unsigned long error, void *context) +static void complete_io(unsigned long error, unsigned long unsup, void *context) { struct kcopyd_job *job = context; struct dm_kcopyd_client *kc = job->kc; io_job_finish(kc->throttle); - if (error) { + if (unlikely((error | unsup) != 0)) { if (op_is_write(job->op)) - job->write_err |= error; + job->write_err |= error | unsup; else job->read_err = 1; @@ -578,9 +578,9 @@ static int run_io_job(struct kcopyd_job *job) io_job_start(job->kc->throttle); if (job->op == REQ_OP_READ) - r = dm_io(&io_req, 1, &job->source, NULL, IOPRIO_DEFAULT); + r = dm_io(&io_req, 1, &job->source, NULL, NULL, IOPRIO_DEFAULT); else - r = dm_io(&io_req, job->num_dests, job->dests, NULL, IOPRIO_DEFAULT); + r = dm_io(&io_req, job->num_dests, job->dests, NULL, NULL, IOPRIO_DEFAULT); return r; } diff --git a/drivers/md/dm-log-userspace-base.c b/drivers/md/dm-log-userspace-base.c index 607436804a8b..40e21bec4792 100644 --- a/drivers/md/dm-log-userspace-base.c +++ b/drivers/md/dm-log-userspace-base.c @@ -139,6 +139,7 @@ static int build_constructor_string(struct dm_target *ti, str_size += strlen(argv[i]) + 1; /* +1 for space between args */ str_size += 20; /* Max number of chars in a printed u64 number */ + str_size++; /* For NUL-terminator */ str = kzalloc(str_size, GFP_KERNEL); if (!str) { diff --git a/drivers/md/dm-log.c b/drivers/md/dm-log.c index c8a1f9b6385f..38b686a7a487 100644 --- a/drivers/md/dm-log.c +++ b/drivers/md/dm-log.c @@ -300,7 +300,7 @@ static int rw_header(struct log_c *lc, enum req_op op) { lc->io_req.bi_opf = op; - return dm_io(&lc->io_req, 1, &lc->header_location, NULL, IOPRIO_DEFAULT); + return dm_io(&lc->io_req, 1, &lc->header_location, NULL, NULL, IOPRIO_DEFAULT); } static int flush_header(struct log_c *lc) @@ -313,7 +313,7 @@ static int flush_header(struct log_c *lc) lc->io_req.bi_opf = REQ_OP_WRITE | REQ_PREFLUSH; - return dm_io(&lc->io_req, 1, &null_location, NULL, IOPRIO_DEFAULT); + return dm_io(&lc->io_req, 1, &null_location, NULL, NULL, IOPRIO_DEFAULT); } static int read_header(struct log_c *log) diff --git a/drivers/md/dm-pcache/cache.c b/drivers/md/dm-pcache/cache.c index 534bf07b794f..887157fde68d 100644 --- a/drivers/md/dm-pcache/cache.c +++ b/drivers/md/dm-pcache/cache.c @@ -119,6 +119,10 @@ int cache_pos_decode(struct pcache_cache *cache, return -EIO; pos->cache_seg = &cache->segments[latest.cache_seg_id]; + + if (latest.seg_off >= pos->cache_seg->segment.data_size) + return -EIO; + pos->seg_off = latest.seg_off; *seq = latest.header.seq; *index = (latest_addr - pos_onmedia); @@ -246,6 +250,13 @@ static int get_seg_id(struct pcache_cache *cache, } else { *seg_id = cache->cache_info.seg_id; } + + if (*seg_id >= cache_dev->seg_num) { + pcache_dev_err(pcache, "invalid segment id %u from cache device (seg_num %u)\n", + *seg_id, cache_dev->seg_num); + ret = -EIO; + goto err; + } } return 0; err: @@ -261,6 +272,13 @@ static int cache_segs_init(struct pcache_cache *cache) int ret; u32 i; + if (cache_info->n_segs > cache->cache_dev->seg_num) { + pcache_dev_err(CACHE_TO_PCACHE(cache), + "cache_info n_segs %u exceeds cache device segments %u\n", + cache_info->n_segs, cache->cache_dev->seg_num); + return -EIO; + } + for (i = 0; i < cache_info->n_segs; i++) { ret = get_seg_id(cache, prev_cache_seg, new_cache, &seg_id); if (ret) diff --git a/drivers/md/dm-pcache/cache.h b/drivers/md/dm-pcache/cache.h index 27613b56be54..afc112b79496 100644 --- a/drivers/md/dm-pcache/cache.h +++ b/drivers/md/dm-pcache/cache.h @@ -491,6 +491,27 @@ static inline u32 cache_key_data_crc(struct pcache_cache_key *key) return crc32c(PCACHE_CRC_SEED, data, key->len); } +/** + * kset_onmedia_valid - Validate a kset header read from the cache device. + * @kset_onmedia: Pointer to the kset copied from on-media metadata. + * + * The magic and CRC are attacker-computable (fixed public seed). A non-last + * kset stores key_num keys inline, and cache_kset_crc() and the replay loop + * read struct_size(.., data, key_num) bytes from a buffer sized for + * PCACHE_KSET_KEYS_MAX keys, so key_num must be bounded before any such use. + */ +static inline bool kset_onmedia_valid(struct pcache_cache_kset_onmedia *kset_onmedia) +{ + if (kset_onmedia->magic != PCACHE_KSET_MAGIC) + return false; + + if (!(kset_onmedia->flags & PCACHE_KSET_FLAGS_LAST) && + kset_onmedia->key_num > PCACHE_KSET_KEYS_MAX) + return false; + + return true; +} + static inline u32 cache_kset_crc(struct pcache_cache_kset_onmedia *kset_onmedia) { u32 crc_size; diff --git a/drivers/md/dm-pcache/cache_dev.c b/drivers/md/dm-pcache/cache_dev.c index ece689e6ce59..f0259353ee39 100644 --- a/drivers/md/dm-pcache/cache_dev.c +++ b/drivers/md/dm-pcache/cache_dev.c @@ -242,6 +242,8 @@ int cache_dev_start(struct dm_pcache *pcache) struct pcache_cache_dev *cache_dev = &pcache->cache_dev; struct pcache_sb sb; bool format = false; + u32 seg_num; + u64 max_segs; int ret; mutex_init(&cache_dev->seg_lock); @@ -269,7 +271,25 @@ int cache_dev_start(struct dm_pcache *pcache) goto dax_release; cache_dev->sb_flags = le32_to_cpu(sb.flags); - ret = cache_dev_init(cache_dev, le32_to_cpu(sb.seg_num)); + + /* + * seg_num is read from the crc32c-only superblock, so whoever supplies + * the cache device controls it. It is the ceiling every later on-media + * segment id is validated against, so bound it against what the device + * physically holds before it is trusted, or a forged seg_num lets a + * segment id address past the DAX mapping. + */ + seg_num = le32_to_cpu(sb.seg_num); + max_segs = (bdev_nr_bytes(cache_dev->dm_dev->bdev) - PCACHE_SEGMENTS_OFF) / + PCACHE_SEG_SIZE; + if (seg_num == 0 || seg_num > max_segs || seg_num > PCACHE_CACHE_SEGS_MAX) { + pcache_dev_err(pcache, "invalid seg_num %u from cache device (device holds %llu, max %u)\n", + seg_num, max_segs, (u32)PCACHE_CACHE_SEGS_MAX); + ret = -EIO; + goto dax_release; + } + + ret = cache_dev_init(cache_dev, seg_num); if (ret) goto dax_release; diff --git a/drivers/md/dm-pcache/cache_gc.c b/drivers/md/dm-pcache/cache_gc.c index 94f8b276a021..3088cfef951b 100644 --- a/drivers/md/dm-pcache/cache_gc.c +++ b/drivers/md/dm-pcache/cache_gc.c @@ -37,18 +37,18 @@ static bool need_gc(struct pcache_cache *cache, struct pcache_cache_pos *dirty_t kset_onmedia = (struct pcache_cache_kset_onmedia *)cache->gc_kset_onmedia_buf; - to_copy = min(PCACHE_KSET_ONMEDIA_SIZE_MAX, PCACHE_SEG_SIZE - key_tail->seg_off); + to_copy = min(PCACHE_KSET_ONMEDIA_SIZE_MAX, cache_seg_remain(key_tail)); ret = copy_mc_to_kernel(kset_onmedia, key_addr, to_copy); if (ret) { pcache_dev_err(pcache, "error to read kset: %d", ret); return false; } - /* Check if kset_onmedia is corrupted */ - if (kset_onmedia->magic != PCACHE_KSET_MAGIC) { - pcache_dev_debug(pcache, "gc error: magic is not as expected. key_tail: %u:%u magic: %llx, expected: %llx\n", + /* Reject a corrupted or out-of-bounds kset before reading its keys */ + if (!kset_onmedia_valid(kset_onmedia)) { + pcache_dev_debug(pcache, "gc error: invalid kset. key_tail: %u:%u magic: %llx, key_num: %u\n", key_tail->cache_seg->cache_seg_id, key_tail->seg_off, - kset_onmedia->magic, PCACHE_KSET_MAGIC); + kset_onmedia->magic, kset_onmedia->key_num); return false; } diff --git a/drivers/md/dm-pcache/cache_key.c b/drivers/md/dm-pcache/cache_key.c index 2b77e121f89b..a3bb1f95afb9 100644 --- a/drivers/md/dm-pcache/cache_key.c +++ b/drivers/md/dm-pcache/cache_key.c @@ -97,6 +97,14 @@ int cache_key_decode(struct pcache_cache *cache, key->cache_pos.cache_seg = &cache->segments[key_onmedia->cache_seg_id]; key->cache_pos.seg_off = key_onmedia->cache_seg_off; + if ((u64)key->cache_pos.seg_off + key->len > + key->cache_pos.cache_seg->segment.data_size) { + pcache_dev_err(pcache, "key seg_off %u + len %u exceeds segment data size %u\n", + key->cache_pos.seg_off, key->len, + key->cache_pos.cache_seg->segment.data_size); + return -EIO; + } + key->seg_gen = key_onmedia->seg_gen; key->flags = key_onmedia->flags; @@ -728,18 +736,17 @@ static int kset_replay(struct pcache_cache *cache, struct pcache_cache_kset_onme goto err; } - __set_bit(key->cache_pos.cache_seg->cache_seg_id, cache->seg_map); - /* Check if the segment generation is valid for insertion. */ if (key->seg_gen < key->cache_pos.cache_seg->gen) { cache_key_put(key); - } else { - cache_subtree = get_subtree(&cache->req_key_tree, key->off); - spin_lock(&cache_subtree->tree_lock); - cache_key_insert(&cache->req_key_tree, key, true); - spin_unlock(&cache_subtree->tree_lock); + continue; } + __set_bit(key->cache_pos.cache_seg->cache_seg_id, cache->seg_map); + cache_subtree = get_subtree(&cache->req_key_tree, key->off); + spin_lock(&cache_subtree->tree_lock); + cache_key_insert(&cache->req_key_tree, key, true); + spin_unlock(&cache_subtree->tree_lock); cache_seg_get(key->cache_pos.cache_seg); } @@ -754,7 +761,7 @@ int cache_replay(struct pcache_cache *cache) struct pcache_cache_pos pos_tail; struct pcache_cache_pos *pos; struct pcache_cache_kset_onmedia *kset_onmedia; - u32 to_copy, count = 0; + u32 to_copy, count = 0, last_hops = 0; int ret = 0; kset_onmedia = kzalloc(PCACHE_KSET_ONMEDIA_SIZE_MAX, GFP_KERNEL); @@ -771,14 +778,14 @@ int cache_replay(struct pcache_cache *cache) __set_bit(pos->cache_seg->cache_seg_id, cache->seg_map); while (true) { - to_copy = min(PCACHE_KSET_ONMEDIA_SIZE_MAX, PCACHE_SEG_SIZE - pos->seg_off); + to_copy = min(PCACHE_KSET_ONMEDIA_SIZE_MAX, cache_seg_remain(pos)); ret = copy_mc_to_kernel(kset_onmedia, cache_pos_addr(pos), to_copy); if (ret) { ret = -EIO; goto out; } - if (kset_onmedia->magic != PCACHE_KSET_MAGIC || + if (!kset_onmedia_valid(kset_onmedia) || kset_onmedia->crc != cache_kset_crc(kset_onmedia)) { break; } @@ -789,6 +796,11 @@ int cache_replay(struct pcache_cache *cache) pcache_dev_debug(pcache, "last kset replay, next: %u\n", kset_onmedia->next_cache_seg_id); + if (++last_hops > cache->n_segs) { + ret = -EIO; + goto out; + } + next_seg = &cache->segments[kset_onmedia->next_cache_seg_id]; pos->cache_seg = next_seg; diff --git a/drivers/md/dm-pcache/cache_segment.c b/drivers/md/dm-pcache/cache_segment.c index 9d92e2b067ed..c698ebbc626d 100644 --- a/drivers/md/dm-pcache/cache_segment.c +++ b/drivers/md/dm-pcache/cache_segment.c @@ -243,8 +243,16 @@ struct pcache_cache_segment *get_cache_segment(struct pcache_cache *cache) spin_lock(&cache->seg_map_lock); again: - seg_id = find_next_zero_bit(cache->seg_map, cache->n_segs, cache->last_cache_seg); - if (seg_id == cache->n_segs) { + /* + * Only allocate initialized segments. cache_segs_init() initializes + * cache_info.n_segs of the cache->n_segs device segments; a forged + * smaller cache_info.n_segs leaves the rest as zeroed structs whose data + * pointer is NULL. Bounding the search to cache_info.n_segs keeps such a + * segment from reaching cache_kset_close(), which writes through it. + */ + seg_id = find_next_zero_bit(cache->seg_map, cache->cache_info.n_segs, + cache->last_cache_seg); + if (seg_id == cache->cache_info.n_segs) { /* reset the hint of ->last_cache_seg and retry */ if (cache->last_cache_seg) { cache->last_cache_seg = 0; diff --git a/drivers/md/dm-pcache/cache_writeback.c b/drivers/md/dm-pcache/cache_writeback.c index 87a82b3fe836..3df8687e2382 100644 --- a/drivers/md/dm-pcache/cache_writeback.c +++ b/drivers/md/dm-pcache/cache_writeback.c @@ -48,18 +48,18 @@ static inline bool is_cache_clean(struct pcache_cache *cache, struct pcache_cach addr = cache_pos_addr(dirty_tail); kset_onmedia = (struct pcache_cache_kset_onmedia *)cache->wb_kset_onmedia_buf; - to_copy = min(PCACHE_KSET_ONMEDIA_SIZE_MAX, PCACHE_SEG_SIZE - dirty_tail->seg_off); + to_copy = min(PCACHE_KSET_ONMEDIA_SIZE_MAX, cache_seg_remain(dirty_tail)); ret = copy_mc_to_kernel(kset_onmedia, addr, to_copy); if (ret) { pcache_dev_err(pcache, "error to read kset: %d", ret); return true; } - /* Check if the magic number matches the expected value */ - if (kset_onmedia->magic != PCACHE_KSET_MAGIC) { - pcache_dev_debug(pcache, "dirty_tail: %u:%u magic: %llx, not expected: %llx\n", + /* Reject a corrupted or out-of-bounds kset before reading its keys */ + if (!kset_onmedia_valid(kset_onmedia)) { + pcache_dev_debug(pcache, "dirty_tail: %u:%u invalid kset magic: %llx, key_num: %u\n", dirty_tail->cache_seg->cache_seg_id, dirty_tail->seg_off, - kset_onmedia->magic, PCACHE_KSET_MAGIC); + kset_onmedia->magic, kset_onmedia->key_num); return true; } diff --git a/drivers/md/dm-pcache/dm_pcache.c b/drivers/md/dm-pcache/dm_pcache.c index 87bcc1c515a6..f6da50b57c67 100644 --- a/drivers/md/dm-pcache/dm_pcache.c +++ b/drivers/md/dm-pcache/dm_pcache.c @@ -439,13 +439,13 @@ static int dm_pcache_message(struct dm_target *ti, unsigned int argc, char **argv, char *result, unsigned int maxlen) { struct dm_pcache *pcache = ti->private; - unsigned long val; + u8 val; if (argc != 2) goto err; if (!strcasecmp(argv[0], "gc_percent")) { - if (kstrtoul(argv[1], 10, &val)) + if (kstrtou8(argv[1], 10, &val)) goto err; return pcache_cache_set_gc_percent(&pcache->cache, val); diff --git a/drivers/md/dm-raid1.c b/drivers/md/dm-raid1.c index d9ec783a37dd..9b66863991d1 100644 --- a/drivers/md/dm-raid1.c +++ b/drivers/md/dm-raid1.c @@ -258,7 +258,7 @@ out: static int mirror_flush(struct dm_target *ti) { struct mirror_set *ms = ti->private; - unsigned long error_bits; + unsigned long error_bits, unsup_bits; unsigned int i; struct dm_io_region io[MAX_NR_MIRRORS]; @@ -277,8 +277,8 @@ static int mirror_flush(struct dm_target *ti) } error_bits = -1; - dm_io(&io_req, ms->nr_mirrors, io, &error_bits, IOPRIO_DEFAULT); - if (unlikely(error_bits != 0)) { + dm_io(&io_req, ms->nr_mirrors, io, &error_bits, &unsup_bits, IOPRIO_DEFAULT); + if (unlikely((error_bits | unsup_bits) != 0)) { for (i = 0; i < ms->nr_mirrors; i++) if (test_bit(i, &error_bits)) fail_mirror(ms->mirror + i, @@ -511,7 +511,7 @@ static void hold_bio(struct mirror_set *ms, struct bio *bio) * Reads *--------------------------------------------------------------- */ -static void read_callback(unsigned long error, void *context) +static void read_callback(unsigned long error, unsigned long unsup, void *context) { struct bio *bio = context; struct mirror *m; @@ -520,6 +520,8 @@ static void read_callback(unsigned long error, void *context) bio_set_m(bio, NULL); if (likely(!error)) { + if (unlikely(unsup != 0)) + bio->bi_status = BLK_STS_INVAL; bio_endio(bio); return; } @@ -553,7 +555,7 @@ static void read_async_bio(struct mirror *m, struct bio *bio) map_region(&io, m, bio); bio_set_m(bio, m); - BUG_ON(dm_io(&io_req, 1, &io, NULL, IOPRIO_DEFAULT)); + BUG_ON(dm_io(&io_req, 1, &io, NULL, NULL, IOPRIO_DEFAULT)); } static inline int region_in_sync(struct mirror_set *ms, region_t region, @@ -600,7 +602,7 @@ static void do_reads(struct mirror_set *ms, struct bio_list *reads) * NOSYNC: increment pending, just write to the default mirror *--------------------------------------------------------------------- */ -static void write_callback(unsigned long error, void *context) +static void write_callback(unsigned long error, unsigned long unsup, void *context) { unsigned int i; struct bio *bio = context; @@ -617,7 +619,7 @@ static void write_callback(unsigned long error, void *context) * This way we handle both writes to SYNC and NOSYNC * regions with the same code. */ - if (likely(!error)) { + if (likely(!(error | unsup))) { bio_endio(bio); return; } @@ -632,6 +634,12 @@ static void write_callback(unsigned long error, void *context) return; } + if (!error && unsup) { + bio->bi_status = BLK_STS_INVAL; + bio_endio(bio); + return; + } + for (i = 0; i < ms->nr_mirrors; i++) if (test_bit(i, &error)) fail_mirror(ms->mirror + i, DM_RAID1_WRITE_ERROR); @@ -680,7 +688,7 @@ static void do_write(struct mirror_set *ms, struct bio *bio) */ bio_set_m(bio, get_default_mirror(ms)); - BUG_ON(dm_io(&io_req, ms->nr_mirrors, io, NULL, IOPRIO_DEFAULT)); + BUG_ON(dm_io(&io_req, ms->nr_mirrors, io, NULL, NULL, IOPRIO_DEFAULT)); } static void do_writes(struct mirror_set *ms, struct bio_list *writes) @@ -1262,7 +1270,7 @@ static int mirror_end_io(struct dm_target *ti, struct bio *bio, return DM_ENDIO_DONE; } - if (*error == BLK_STS_NOTSUPP) + if (*error == BLK_STS_NOTSUPP || *error == BLK_STS_INVAL) goto out; if (bio->bi_opf & REQ_RAHEAD) diff --git a/drivers/md/dm-snap-persistent.c b/drivers/md/dm-snap-persistent.c index 0e13d60bfdd1..0dc429eb2692 100644 --- a/drivers/md/dm-snap-persistent.c +++ b/drivers/md/dm-snap-persistent.c @@ -223,7 +223,7 @@ static void do_metadata(struct work_struct *work) { struct mdata_req *req = container_of(work, struct mdata_req, work); - req->result = dm_io(req->io_req, 1, req->where, NULL, IOPRIO_DEFAULT); + req->result = dm_io(req->io_req, 1, req->where, NULL, NULL, IOPRIO_DEFAULT); } /* @@ -247,7 +247,7 @@ static int chunk_io(struct pstore *ps, void *area, chunk_t chunk, blk_opf_t opf, struct mdata_req req; if (!metadata) - return dm_io(&io_req, 1, &where, NULL, IOPRIO_DEFAULT); + return dm_io(&io_req, 1, &where, NULL, NULL, IOPRIO_DEFAULT); req.where = &where; req.io_req = &io_req; diff --git a/drivers/md/dm-stats.c b/drivers/md/dm-stats.c index dbff4922e068..8019eeb4cc91 100644 --- a/drivers/md/dm-stats.c +++ b/drivers/md/dm-stats.c @@ -178,8 +178,10 @@ static void dm_stat_free(struct rcu_head *head) kfree(s->program_id); kfree(s->aux_data); for_each_possible_cpu(cpu) { - dm_kvfree(s->stat_percpu[cpu][0].histogram, s->histogram_alloc_size); - dm_kvfree(s->stat_percpu[cpu], s->percpu_alloc_size); + if (s->stat_percpu[cpu]) { + dm_kvfree(s->stat_percpu[cpu][0].histogram, s->histogram_alloc_size); + dm_kvfree(s->stat_percpu[cpu], s->percpu_alloc_size); + } } dm_kvfree(s->stat_shared[0].tmp.histogram, s->histogram_alloc_size); dm_kvfree(s, s->shared_alloc_size); diff --git a/drivers/md/dm-switch.c b/drivers/md/dm-switch.c index 50a52ca50b34..65d169ffa753 100644 --- a/drivers/md/dm-switch.c +++ b/drivers/md/dm-switch.c @@ -184,7 +184,7 @@ static void switch_region_table_write(struct switch_ctx *sctx, unsigned long reg pte = sctx->region_table[region_index]; pte &= ~((((region_table_slot_t)1 << sctx->region_table_entry_bits) - 1) << bit); pte |= (region_table_slot_t)value << bit; - sctx->region_table[region_index] = pte; + WRITE_ONCE(sctx->region_table[region_index], pte); } /* diff --git a/drivers/md/dm-verity-target.c b/drivers/md/dm-verity-target.c index 40c0664fa034..2c754144e929 100644 --- a/drivers/md/dm-verity-target.c +++ b/drivers/md/dm-verity-target.c @@ -379,7 +379,7 @@ static noinline int verity_recheck(struct dm_verity *v, struct dm_verity_io *io, io_loc.bdev = v->data_dev->bdev; io_loc.sector = cur_block << (v->data_dev_block_bits - SECTOR_SHIFT); io_loc.count = 1 << (v->data_dev_block_bits - SECTOR_SHIFT); - r = dm_io(&io_req, 1, &io_loc, NULL, IOPRIO_DEFAULT); + r = dm_io(&io_req, 1, &io_loc, NULL, NULL, IOPRIO_DEFAULT); if (unlikely(r)) goto free_ret; diff --git a/drivers/md/dm-writecache.c b/drivers/md/dm-writecache.c index af54e289bceb..34148aa4df79 100644 --- a/drivers/md/dm-writecache.c +++ b/drivers/md/dm-writecache.c @@ -474,12 +474,14 @@ struct io_notify { atomic_t count; }; -static void writecache_notify_io(unsigned long error, void *context) +static void writecache_notify_io(unsigned long error, unsigned long unsup, void *context) { struct io_notify *endio = context; if (unlikely(error != 0)) writecache_error(endio->wc, -EIO, "error writing metadata"); + else if (unlikely(unsup != 0)) + writecache_error(endio->wc, -EOPNOTSUPP, "error writing metadata"); BUG_ON(atomic_read(&endio->count) <= 0); if (atomic_dec_and_test(&endio->count)) complete(&endio->c); @@ -530,11 +532,11 @@ static void ssd_commit_flushed(struct dm_writecache *wc, bool wait_for_ios) req.notify.context = &endio; /* writing via async dm-io (implied by notify.fn above) won't return an error */ - (void) dm_io(&req, 1, ®ion, NULL, IOPRIO_DEFAULT); + (void) dm_io(&req, 1, ®ion, NULL, NULL, IOPRIO_DEFAULT); i = j; } - writecache_notify_io(0, &endio); + writecache_notify_io(0, 0, &endio); wait_for_completion_io(&endio.c); if (wait_for_ios) @@ -567,7 +569,7 @@ static void ssd_commit_superblock(struct dm_writecache *wc) req.notify.fn = NULL; req.notify.context = NULL; - r = dm_io(&req, 1, ®ion, NULL, IOPRIO_DEFAULT); + r = dm_io(&req, 1, ®ion, NULL, NULL, IOPRIO_DEFAULT); if (unlikely(r)) writecache_error(wc, r, "error writing superblock"); } @@ -595,7 +597,7 @@ static void writecache_disk_flush(struct dm_writecache *wc, struct dm_dev *dev) req.client = wc->dm_io; req.notify.fn = NULL; - r = dm_io(&req, 1, ®ion, NULL, IOPRIO_DEFAULT); + r = dm_io(&req, 1, ®ion, NULL, NULL, IOPRIO_DEFAULT); if (unlikely(r)) writecache_error(wc, r, "error flushing metadata: %d", r); } @@ -989,7 +991,7 @@ static int writecache_read_metadata(struct dm_writecache *wc, sector_t n_sectors req.client = wc->dm_io; req.notify.fn = NULL; - return dm_io(&req, 1, ®ion, NULL, IOPRIO_DEFAULT); + return dm_io(&req, 1, ®ion, NULL, NULL, IOPRIO_DEFAULT); } static void writecache_resume(struct dm_target *ti) diff --git a/drivers/md/md.c b/drivers/md/md.c index 0d60c211e7c0..5304e920dbcc 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -1917,6 +1917,13 @@ static int super_1_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor_ rdev->bb_page, REQ_OP_READ, true)) return -EIO; bbp = (__le64 *)page_address(rdev->bb_page); + + /* check for badblocks api. */ + if (sb->bblog_shift >= BITS_PER_TYPE(sector_t)) { + pr_err("md: %pg: bogus bblog_shift %u for badblocks.\n", + rdev->bdev, sb->bblog_shift); + return -EINVAL; + } rdev->badblocks.shift = sb->bblog_shift; for (i = 0 ; i < (sectors << (9-3)) ; i++, bbp++) { u64 bb = le64_to_cpu(*bbp); diff --git a/drivers/md/persistent-data/dm-array.c b/drivers/md/persistent-data/dm-array.c index 8f8792e55806..961fa3c1439a 100644 --- a/drivers/md/persistent-data/dm-array.c +++ b/drivers/md/persistent-data/dm-array.c @@ -38,6 +38,14 @@ struct array_block { */ #define CSUM_XOR 595846735 +/* + * Each array block can hold this many values. + */ +static uint32_t calc_max_entries(size_t value_size, size_t size_of_block) +{ + return (size_of_block - sizeof(struct array_block)) / value_size; +} + static void array_block_prepare_for_write(const struct dm_block_validator *v, struct dm_block *b, size_t size_of_block) @@ -55,6 +63,7 @@ static int array_block_check(const struct dm_block_validator *v, size_t size_of_block) { struct array_block *bh_le = dm_block_data(b); + uint32_t nr_entries, max_entries, value_size; __le32 csum_disk; if (dm_block_location(b) != le64_to_cpu(bh_le->blocknr)) { @@ -74,6 +83,26 @@ static int array_block_check(const struct dm_block_validator *v, return -EILSEQ; } + nr_entries = le32_to_cpu(bh_le->nr_entries); + max_entries = le32_to_cpu(bh_le->max_entries); + value_size = le32_to_cpu(bh_le->value_size); + + if (!value_size) { + DMERR_LIMIT("%s failed: value_size is zero", __func__); + return -EILSEQ; + } + + if (max_entries != calc_max_entries(value_size, size_of_block)) { + DMERR_LIMIT("%s failed: max_entries %u invalid for value_size %u", + __func__, max_entries, value_size); + return -EILSEQ; + } + + if (nr_entries > max_entries) { + DMERR_LIMIT("%s failed: too many entries", __func__); + return -EILSEQ; + } + return 0; } @@ -139,14 +168,6 @@ static void dec_ablock_entries(struct dm_array_info *info, struct array_block *a } /* - * Each array block can hold this many values. - */ -static uint32_t calc_max_entries(size_t value_size, size_t size_of_block) -{ - return (size_of_block - sizeof(struct array_block)) / value_size; -} - -/* * Allocate a new array block. The caller will need to unlock block. */ static int alloc_ablock(struct dm_array_info *info, size_t size_of_block, @@ -225,6 +246,14 @@ static int get_ablock(struct dm_array_info *info, dm_block_t b, return r; *ab = dm_block_data(*block); + if (le32_to_cpu((*ab)->value_size) != info->value_type.size) { + DMERR_LIMIT("%s failed: value_size %u != wanted %u", __func__, + le32_to_cpu((*ab)->value_size), + info->value_type.size); + dm_tm_unlock(info->btree_info.tm, *block); + return -EILSEQ; + } + return 0; } @@ -287,6 +316,14 @@ static int __shadow_ablock(struct dm_array_info *info, dm_block_t b, return r; *ab = dm_block_data(*block); + if (le32_to_cpu((*ab)->value_size) != info->value_type.size) { + DMERR_LIMIT("%s failed: value_size %u != wanted %u", __func__, + le32_to_cpu((*ab)->value_size), + info->value_type.size); + dm_tm_unlock(info->btree_info.tm, *block); + return -EILSEQ; + } + if (inc) inc_ablock_entries(info, *ab); diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index d6b174454b1a..1ae9a587a959 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -3384,7 +3384,7 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr, struct md_rdev *rdev = conf->mirrors[j].rdev; if (rdev == NULL || test_bit(Faulty, &rdev->flags)) { - still_degraded = false; + still_degraded = true; break; } } diff --git a/drivers/media/cec/platform/stm32/stm32-cec.c b/drivers/media/cec/platform/stm32/stm32-cec.c index 1ec0cece0a5b..8c2fc232202d 100644 --- a/drivers/media/cec/platform/stm32/stm32-cec.c +++ b/drivers/media/cec/platform/stm32/stm32-cec.c @@ -132,7 +132,8 @@ static void stm32_rx_done(struct stm32_cec *cec, u32 status) u32 val; regmap_read(cec->regmap, CEC_RXDR, &val); - cec->rx_msg.msg[cec->rx_msg.len++] = val & 0xFF; + if (cec->rx_msg.len < CEC_MAX_MSG_SIZE) + cec->rx_msg.msg[cec->rx_msg.len++] = val & 0xFF; } if (cec->irq_status & RXEND) { diff --git a/drivers/media/test-drivers/vicodec/vicodec-core.c b/drivers/media/test-drivers/vicodec/vicodec-core.c index a3df3a33237e..654da27b1140 100644 --- a/drivers/media/test-drivers/vicodec/vicodec-core.c +++ b/drivers/media/test-drivers/vicodec/vicodec-core.c @@ -63,11 +63,11 @@ struct pixfmt_info { }; static const struct v4l2_fwht_pixfmt_info pixfmt_fwht = { - V4L2_PIX_FMT_FWHT, 0, 3, 1, 1, 1, 1, 1, 0, 1 + V4L2_PIX_FMT_FWHT, 0, 4, 1, 1, 1, 1, 1, 0, 1 }; static const struct v4l2_fwht_pixfmt_info pixfmt_stateless_fwht = { - V4L2_PIX_FMT_FWHT_STATELESS, 0, 3, 1, 1, 1, 1, 1, 0, 1 + V4L2_PIX_FMT_FWHT_STATELESS, 0, 4, 1, 1, 1, 1, 1, 0, 1 }; static void vicodec_dev_release(struct device *dev) diff --git a/drivers/media/v4l2-core/v4l2-dev.c b/drivers/media/v4l2-core/v4l2-dev.c index 10a126e50c1c..406915afcb2f 100644 --- a/drivers/media/v4l2-core/v4l2-dev.c +++ b/drivers/media/v4l2-core/v4l2-dev.c @@ -1066,25 +1066,25 @@ int __video_register_device(struct video_device *vdev, vdev->dev.class = &video_class; vdev->dev.devt = MKDEV(VIDEO_MAJOR, vdev->minor); vdev->dev.parent = vdev->dev_parent; - vdev->dev.release = v4l2_device_release; dev_set_name(&vdev->dev, "%s%d", name_base, vdev->num); - - /* Increase v4l2_device refcount */ - v4l2_device_get(vdev->v4l2_dev); - mutex_lock(&videodev_lock); ret = device_register(&vdev->dev); if (ret < 0) { mutex_unlock(&videodev_lock); pr_err("%s: device_register failed\n", __func__); - put_device(&vdev->dev); - return ret; + goto cleanup; } + /* Register the release callback that will be called when the last + reference to the device goes away. */ + vdev->dev.release = v4l2_device_release; if (nr != -1 && nr != vdev->num && warn_if_nr_in_use) pr_warn("%s: requested %s%d, got %s\n", __func__, name_base, nr, video_device_node_name(vdev)); + /* Increase v4l2_device refcount */ + v4l2_device_get(vdev->v4l2_dev); + /* Part 5: Register the entity. */ ret = video_register_media_controller(vdev); diff --git a/drivers/mfd/cgbc-core.c b/drivers/mfd/cgbc-core.c index 4782ff1114a9..33a32063050f 100644 --- a/drivers/mfd/cgbc-core.c +++ b/drivers/mfd/cgbc-core.c @@ -363,9 +363,9 @@ static void cgbc_remove(struct platform_device *pdev) { struct cgbc_device_data *cgbc = platform_get_drvdata(pdev); - cgbc_session_release(cgbc); - mfd_remove_devices(&pdev->dev); + + cgbc_session_release(cgbc); } static struct platform_driver cgbc_driver = { diff --git a/drivers/mfd/sm501.c b/drivers/mfd/sm501.c index c56f5005eb91..35bcb856595d 100644 --- a/drivers/mfd/sm501.c +++ b/drivers/mfd/sm501.c @@ -1627,6 +1627,7 @@ static void sm501_pci_remove(struct pci_dev *dev) release_mem_region(sm->io_res->start, 0x100); pci_disable_device(dev); + kfree(sm); } static void sm501_plat_remove(struct platform_device *dev) @@ -1637,6 +1638,7 @@ static void sm501_plat_remove(struct platform_device *dev) iounmap(sm->regs); release_mem_region(sm->io_res->start, 0x100); + kfree(sm); } static const struct pci_device_id sm501_pci_tbl[] = { diff --git a/drivers/misc/nsm.c b/drivers/misc/nsm.c index 3960506eb7ab..c3b474450d15 100644 --- a/drivers/misc/nsm.c +++ b/drivers/misc/nsm.c @@ -243,7 +243,7 @@ static int nsm_sendrecv_msg_locked(struct nsm *nsm) goto cleanup; } - msg->resp.len = len; + msg->resp.len = min_t(unsigned int, len, sizeof(msg->resp.data)); rc = 0; diff --git a/drivers/mmc/host/via-sdmmc.c b/drivers/mmc/host/via-sdmmc.c index c628b3bbfd7a..cf7b74835aa3 100644 --- a/drivers/mmc/host/via-sdmmc.c +++ b/drivers/mmc/host/via-sdmmc.c @@ -1154,10 +1154,16 @@ static int via_sd_probe(struct pci_dev *pcidev, ret = mmc_add_host(mmc); if (ret) - goto unmap; + goto free_irq; return 0; +free_irq: + writeb(0x0, sdhost->pcictrl_mmiobase + VIA_CRDR_PCIINTCTRL); + free_irq(pcidev->irq, sdhost); + cancel_work_sync(&sdhost->carddet_work); + /* carddet_work may re-enable the interrupt via via_reset_pcictrl(). */ + writeb(0x0, sdhost->pcictrl_mmiobase + VIA_CRDR_PCIINTCTRL); unmap: iounmap(sdhost->mmiobase); release: @@ -1200,6 +1206,10 @@ static void via_sd_remove(struct pci_dev *pcidev) free_irq(pcidev->irq, sdhost); + cancel_work_sync(&sdhost->carddet_work); + /* carddet_work may re-enable the interrupt via via_reset_pcictrl(). */ + writeb(0x0, sdhost->pcictrl_mmiobase + VIA_CRDR_PCIINTCTRL); + timer_delete_sync(&sdhost->timer); cancel_work_sync(&sdhost->finish_bh_work); diff --git a/drivers/net/dsa/realtek/rtl83xx.c b/drivers/net/dsa/realtek/rtl83xx.c index 2b9bd4462714..0df45c758beb 100644 --- a/drivers/net/dsa/realtek/rtl83xx.c +++ b/drivers/net/dsa/realtek/rtl83xx.c @@ -309,7 +309,7 @@ void rtl83xx_reset_assert(struct realtek_priv *priv) "Failed to assert the switch reset control: %pe\n", ERR_PTR(ret)); - gpiod_set_value(priv->reset, true); + gpiod_set_value_cansleep(priv->reset, true); } void rtl83xx_reset_deassert(struct realtek_priv *priv) @@ -322,7 +322,7 @@ void rtl83xx_reset_deassert(struct realtek_priv *priv) "Failed to deassert the switch reset control: %pe\n", ERR_PTR(ret)); - gpiod_set_value(priv->reset, false); + gpiod_set_value_cansleep(priv->reset, false); } MODULE_AUTHOR("Luiz Angelo Daros de Luca <luizluca@gmail.com>"); diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c index 8e6eec828d48..c4ea14f8fbe9 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c @@ -13474,10 +13474,13 @@ static int bnx2x_init_firmware(struct bnx2x *bp) iro_alloc_err: kfree(bp->init_ops_offsets); + bp->init_ops_offsets = NULL; init_offsets_alloc_err: kfree(bp->init_ops); + bp->init_ops = NULL; init_ops_alloc_err: kfree(bp->init_data); + bp->init_data = NULL; request_firmware_exit: release_firmware(bp->firmware); bp->firmware = NULL; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 29e52df2502e..186fc98a555d 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -499,11 +499,8 @@ static netdev_tx_t bnxt_start_xmit(struct sk_buff *skb, struct net_device *dev) if (skb_shinfo(skb)->nr_frags > TX_MAX_FRAGS) { netdev_warn_once(dev, "SKB has too many (%d) fragments, max supported is %d. SKB will be linearized.\n", skb_shinfo(skb)->nr_frags, TX_MAX_FRAGS); - if (skb_linearize(skb)) { - dev_kfree_skb_any(skb); - dev_core_stats_tx_dropped_inc(dev); - return NETDEV_TX_OK; - } + if (skb_linearize(skb)) + goto tx_free; } #endif free_size = bnxt_tx_avail(bp, txr); diff --git a/drivers/net/ethernet/ibm/emac/mal.c b/drivers/net/ethernet/ibm/emac/mal.c index 7d70056e9008..a423496421e9 100644 --- a/drivers/net/ethernet/ibm/emac/mal.c +++ b/drivers/net/ethernet/ibm/emac/mal.c @@ -35,6 +35,7 @@ int mal_register_commac(struct mal_instance *mal, struct mal_commac *commac) { unsigned long flags; + netdev_lock(mal->napi.dev); spin_lock_irqsave(&mal->lock, flags); MAL_DBG(mal, "reg(%08x, %08x)" NL, @@ -44,18 +45,20 @@ int mal_register_commac(struct mal_instance *mal, struct mal_commac *commac) if ((mal->tx_chan_mask & commac->tx_chan_mask) || (mal->rx_chan_mask & commac->rx_chan_mask)) { spin_unlock_irqrestore(&mal->lock, flags); + netdev_unlock(mal->napi.dev); printk(KERN_WARNING "mal%d: COMMAC channels conflict!\n", mal->index); return -EBUSY; } if (list_empty(&mal->list)) - napi_enable(&mal->napi); + napi_enable_locked(&mal->napi); mal->tx_chan_mask |= commac->tx_chan_mask; mal->rx_chan_mask |= commac->rx_chan_mask; list_add(&commac->list, &mal->list); spin_unlock_irqrestore(&mal->lock, flags); + netdev_unlock(mal->napi.dev); return 0; } @@ -64,7 +67,9 @@ void mal_unregister_commac(struct mal_instance *mal, struct mal_commac *commac) { unsigned long flags; + bool disable_napi; + netdev_lock(mal->napi.dev); spin_lock_irqsave(&mal->lock, flags); MAL_DBG(mal, "unreg(%08x, %08x)" NL, @@ -73,10 +78,12 @@ void mal_unregister_commac(struct mal_instance *mal, mal->tx_chan_mask &= ~commac->tx_chan_mask; mal->rx_chan_mask &= ~commac->rx_chan_mask; list_del_init(&commac->list); - if (list_empty(&mal->list)) - napi_disable(&mal->napi); + disable_napi = list_empty(&mal->list); spin_unlock_irqrestore(&mal->lock, flags); + if (disable_napi) + napi_disable_locked(&mal->napi); + netdev_unlock(mal->napi.dev); } int mal_set_rcbs(struct mal_instance *mal, int channel, unsigned long size) diff --git a/drivers/net/ethernet/nvidia/forcedeth.c b/drivers/net/ethernet/nvidia/forcedeth.c index c09fb7694fac..01eb1c75f2da 100644 --- a/drivers/net/ethernet/nvidia/forcedeth.c +++ b/drivers/net/ethernet/nvidia/forcedeth.c @@ -6221,7 +6221,7 @@ static int nv_suspend(struct device *device) netif_device_detach(dev); /* save non-pci configuration space */ - for (i = 0; i <= np->register_size/sizeof(u32); i++) + for (i = 0; i < np->register_size/sizeof(u32); i++) np->saved_config_space[i] = readl(base + i*sizeof(u32)); return 0; @@ -6236,7 +6236,7 @@ static int nv_resume(struct device *device) int i, rc = 0; /* restore non-pci configuration space */ - for (i = 0; i <= np->register_size/sizeof(u32); i++) + for (i = 0; i < np->register_size/sizeof(u32); i++) writel(np->saved_config_space[i], base+i*sizeof(u32)); if (np->driver_data & DEV_NEED_MSI_FIX) diff --git a/drivers/net/ethernet/qlogic/qede/qede.h b/drivers/net/ethernet/qlogic/qede/qede.h index 042a75f34060..0e7a0c2c1765 100644 --- a/drivers/net/ethernet/qlogic/qede/qede.h +++ b/drivers/net/ethernet/qlogic/qede/qede.h @@ -303,10 +303,10 @@ enum qede_agg_state { }; struct qede_agg_info { - /* rx_buf is a data buffer that can be placed / consumed from rx bd - * chain. It has two purposes: We will preallocate the data buffer - * for each aggregation when we open the interface and will place this - * buffer on the rx-bd-ring when we receive TPA_START. We don't want + /* buffer is used to retain the Rx consumer descriptor when a TPA + * session starts. If the SKB allocation fails during TPA_START, + * we use this saved buffer to safely recycle the physical page + * back into the rx-bd-ring via qede_reuse_page(). We don't want * to be in a state where allocation fails, as we can't reuse the * consumer buffer in the rx-chain since FW may still be writing to it * (since header needs to be modified for TPA). diff --git a/drivers/net/ethernet/qlogic/qede/qede_fp.c b/drivers/net/ethernet/qlogic/qede/qede_fp.c index c11e0d8f98aa..a02624f6d6d5 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_fp.c +++ b/drivers/net/ethernet/qlogic/qede/qede_fp.c @@ -850,6 +850,7 @@ static void qede_tpa_start(struct qede_dev *edev, pad, false); tpa_info->buffer.page_offset = sw_rx_data_cons->page_offset; tpa_info->buffer.mapping = sw_rx_data_cons->mapping; + tpa_info->buffer.data = sw_rx_data_cons->data; if (unlikely(!tpa_info->skb)) { DP_NOTICE(edev, "Failed to allocate SKB for gro\n"); diff --git a/drivers/net/ethernet/renesas/ravb.h b/drivers/net/ethernet/renesas/ravb.h index 7b48060c250b..330379c4f405 100644 --- a/drivers/net/ethernet/renesas/ravb.h +++ b/drivers/net/ethernet/renesas/ravb.h @@ -1039,6 +1039,7 @@ struct ravb_ptp_perout { struct ravb_ptp { struct ptp_clock *clock; struct ptp_clock_info info; + int phc_index; u32 default_addend; u32 current_addend; int extts[N_EXT_TS]; @@ -1133,6 +1134,8 @@ struct ravb_private { int msg_enable; int speed; int emac_irq; + int err_irq; + int mgmt_irq; unsigned no_avb_link:1; unsigned avb_link_active_low:1; diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index e2d7ce1a85e8..cd0d65cd699a 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -1757,7 +1757,7 @@ static int ravb_get_ts_info(struct net_device *ndev, (1 << HWTSTAMP_FILTER_NONE) | (1 << HWTSTAMP_FILTER_PTP_V2_L2_EVENT) | (1 << HWTSTAMP_FILTER_ALL); - info->phc_index = ptp_clock_index(priv->ptp.clock); + info->phc_index = READ_ONCE(priv->ptp.phc_index); } return 0; @@ -2896,11 +2896,13 @@ static int ravb_setup_irqs(struct ravb_private *priv) return error; if (info->err_mgmt_irqs) { - error = ravb_setup_irq(priv, "err_a", "err_a", NULL, ravb_multi_interrupt); + error = ravb_setup_irq(priv, "err_a", "err_a", &priv->err_irq, + ravb_multi_interrupt); if (error) return error; - error = ravb_setup_irq(priv, "mgmt_a", "mgmt_a", NULL, ravb_multi_interrupt); + error = ravb_setup_irq(priv, "mgmt_a", "mgmt_a", &priv->mgmt_irq, + ravb_multi_interrupt); if (error) return error; } @@ -2963,6 +2965,7 @@ static int ravb_probe(struct platform_device *pdev) priv->rstc = rstc; priv->ndev = ndev; priv->pdev = pdev; + priv->ptp.phc_index = -1; priv->num_tx_ring[RAVB_BE] = BE_TX_RING_SIZE; priv->num_rx_ring[RAVB_BE] = BE_RX_RING_SIZE; if (info->nc_queues) { diff --git a/drivers/net/ethernet/renesas/ravb_ptp.c b/drivers/net/ethernet/renesas/ravb_ptp.c index 226c6c0ab945..43218bc15b15 100644 --- a/drivers/net/ethernet/renesas/ravb_ptp.c +++ b/drivers/net/ethernet/renesas/ravb_ptp.c @@ -289,16 +289,17 @@ static const struct ptp_clock_info ravb_ptp_info = { void ravb_ptp_interrupt(struct net_device *ndev) { struct ravb_private *priv = netdev_priv(ndev); + struct ptp_clock *clock = READ_ONCE(priv->ptp.clock); u32 gis = ravb_read(ndev, GIS); gis &= ravb_read(ndev, GIC); - if (gis & GIS_PTCF) { + if ((gis & GIS_PTCF) && clock) { struct ptp_clock_event event; event.type = PTP_CLOCK_EXTTS; event.index = 0; event.timestamp = ravb_read(ndev, GCPT); - ptp_clock_event(priv->ptp.clock, &event); + ptp_clock_event(clock, &event); } if (gis & GIS_PTMF) { struct ravb_ptp_perout *perout = priv->ptp.perout; @@ -315,6 +316,7 @@ void ravb_ptp_interrupt(struct net_device *ndev) void ravb_ptp_init(struct net_device *ndev, struct platform_device *pdev) { struct ravb_private *priv = netdev_priv(ndev); + struct ptp_clock *clock; unsigned long flags; priv->ptp.info = ravb_ptp_info; @@ -327,15 +329,45 @@ void ravb_ptp_init(struct net_device *ndev, struct platform_device *pdev) ravb_modify(ndev, GCCR, GCCR_TCSS, GCCR_TCSS_ADJGPTP); spin_unlock_irqrestore(&priv->lock, flags); - priv->ptp.clock = ptp_clock_register(&priv->ptp.info, &pdev->dev); + clock = ptp_clock_register(&priv->ptp.info, &pdev->dev); + if (IS_ERR(clock)) { + netdev_err(ndev, "failed to register PTP clock: %pe\n", clock); + clock = NULL; + } + + WRITE_ONCE(priv->ptp.clock, clock); + if (clock) + WRITE_ONCE(priv->ptp.phc_index, ptp_clock_index(clock)); +} + +static void ravb_ptp_disable(struct net_device *ndev) +{ + ravb_write(ndev, 0, GIC); + ravb_write(ndev, 0, GIS); +} + +static void ravb_ptp_sync_irqs(struct net_device *ndev) +{ + struct ravb_private *priv = netdev_priv(ndev); + + synchronize_irq(ndev->irq); + if (priv->info->err_mgmt_irqs) { + synchronize_irq(priv->err_irq); + synchronize_irq(priv->mgmt_irq); + } } void ravb_ptp_stop(struct net_device *ndev) { struct ravb_private *priv = netdev_priv(ndev); + struct ptp_clock *clock; - ravb_write(ndev, 0, GIC); - ravb_write(ndev, 0, GIS); + WRITE_ONCE(priv->ptp.phc_index, -1); + clock = xchg(&priv->ptp.clock, NULL); + + ravb_ptp_disable(ndev); + ravb_ptp_sync_irqs(ndev); - ptp_clock_unregister(priv->ptp.clock); + if (clock) + ptp_clock_unregister(clock); } diff --git a/drivers/net/ipa/ipa_modem.c b/drivers/net/ipa/ipa_modem.c index 8fe0d0e1a00f..bd54fd6bd380 100644 --- a/drivers/net/ipa/ipa_modem.c +++ b/drivers/net/ipa/ipa_modem.c @@ -269,13 +269,29 @@ void ipa_modem_suspend(struct net_device *netdev) * the modem. We can't enable the queue directly in ipa_modem_resume() * because transmits restart the instant the queue is awakened; but the * device power state won't be ACTIVE until *after* ipa_modem_resume() - * returns. + * returns. A transmit restarted before that would stop the queue + * again and get -EINPROGRESS from pm_runtime_get(), and with this + * work having already run, nothing would ever wake the queue again. + * So wait for the resume to complete before waking the queue. */ static void ipa_modem_wake_queue_work(struct work_struct *work) { struct ipa_priv *priv = container_of(work, struct ipa_priv, work); + struct device *dev = priv->ipa->dev; + int ret; + + ret = pm_runtime_get_sync(dev); + /* Wake the queue even if the device could not be resumed, so + * that pending packets are dropped by the transmit path rather + * than stranded behind a stopped queue. + */ netif_wake_queue(priv->tx->netdev); + + if (ret < 0) + pm_runtime_put_noidle(dev); + else + (void)pm_runtime_put_autosuspend(dev); } /** ipa_modem_resume() - resume callback for runtime_pm diff --git a/drivers/net/ntb_netdev.c b/drivers/net/ntb_netdev.c index b72d0bfd7c2a..6b107e0f2cce 100644 --- a/drivers/net/ntb_netdev.c +++ b/drivers/net/ntb_netdev.c @@ -135,6 +135,9 @@ static void ntb_netdev_rx_handler(struct ntb_transport_qp *qp, void *qp_data, goto enqueue_again; } + ndev->stats.rx_packets++; + ndev->stats.rx_bytes += len; + new_skb = netdev_alloc_skb(ndev, ndev->mtu + ETH_HLEN); if (!new_skb) { ndev->stats.rx_dropped++; @@ -146,13 +149,7 @@ static void ntb_netdev_rx_handler(struct ntb_transport_qp *qp, void *qp_data, skb->ip_summed = CHECKSUM_NONE; skb_record_rx_queue(skb, q->qid); - if (netif_rx(skb) == NET_RX_DROP) { - ndev->stats.rx_errors++; - ndev->stats.rx_dropped++; - } else { - ndev->stats.rx_packets++; - ndev->stats.rx_bytes += len; - } + netif_rx(skb); skb = new_skb; @@ -187,8 +184,10 @@ static int __ntb_netdev_maybe_stop_tx(struct net_device *netdev, static int ntb_netdev_maybe_stop_tx(struct net_device *ndev, struct ntb_netdev_queue *q, int size) { - if (__netif_subqueue_stopped(ndev, q->qid) || - (ntb_transport_tx_free_entry(q->qp) >= size)) + if (__netif_subqueue_stopped(ndev, q->qid)) + return -EBUSY; + + if (ntb_transport_tx_free_entry(q->qp) >= size) return 0; return __ntb_netdev_maybe_stop_tx(ndev, q, size); @@ -237,21 +236,30 @@ static netdev_tx_t ntb_netdev_start_xmit(struct sk_buff *skb, q = &dev->queues[qid]; - ntb_netdev_maybe_stop_tx(ndev, q, tx_stop); + if (unlikely(ntb_netdev_maybe_stop_tx(ndev, q, tx_stop))) + return NETDEV_TX_BUSY; rc = ntb_transport_tx_enqueue(q->qp, skb, skb->data, skb->len); - if (rc) - goto err; + if (rc) { + if (rc == -EAGAIN || rc == -EBUSY) { + netif_stop_subqueue(ndev, q->qid); + mod_timer(&q->tx_timer, + jiffies + usecs_to_jiffies(tx_time)); + return NETDEV_TX_BUSY; + } + + goto drop; + } /* check for next submit */ ntb_netdev_maybe_stop_tx(ndev, q, tx_stop); return NETDEV_TX_OK; -err: +drop: + dev_kfree_skb_any(skb); ndev->stats.tx_dropped++; - ndev->stats.tx_errors++; - return NETDEV_TX_BUSY; + return NETDEV_TX_OK; } static void ntb_netdev_tx_timer(struct timer_list *t) diff --git a/drivers/net/ovpn/main.c b/drivers/net/ovpn/main.c index 0262926449f2..c18ed8690baf 100644 --- a/drivers/net/ovpn/main.c +++ b/drivers/net/ovpn/main.c @@ -12,6 +12,7 @@ #include <linux/module.h> #include <linux/netdevice.h> #include <linux/inetdevice.h> +#include <linux/workqueue.h> #include <net/gro_cells.h> #include <net/ip.h> #include <net/rtnetlink.h> @@ -26,6 +27,9 @@ #include "tcp.h" #include "udp.h" +/* module-owned workqueue on which all ovpn-specific work is queued */ +struct workqueue_struct *ovpn_wq; + static void ovpn_priv_free(struct net_device *net) { struct ovpn_priv *ovpn = netdev_priv(net); @@ -264,10 +268,16 @@ static int __init ovpn_init(void) ovpn_tcp_init(); + ovpn_wq = alloc_workqueue("ovpn", WQ_PERCPU, 0); + if (!ovpn_wq) { + pr_err("ovpn: cannot allocate workqueue\n"); + return -ENOMEM; + } + err = rtnl_link_register(&ovpn_link_ops); if (err) { pr_err("ovpn: can't register rtnl link ops: %d\n", err); - return err; + goto destroy_wq; } err = ovpn_nl_register(); @@ -280,6 +290,9 @@ static int __init ovpn_init(void) unreg_rtnl: rtnl_link_unregister(&ovpn_link_ops); +destroy_wq: + destroy_workqueue(ovpn_wq); + ovpn_wq = NULL; return err; } @@ -288,7 +301,11 @@ static __exit void ovpn_cleanup(void) ovpn_nl_unregister(); rtnl_link_unregister(&ovpn_link_ops); + flush_workqueue(ovpn_wq); rcu_barrier(); + + destroy_workqueue(ovpn_wq); + ovpn_wq = NULL; } module_init(ovpn_init); diff --git a/drivers/net/ovpn/ovpnpriv.h b/drivers/net/ovpn/ovpnpriv.h index 5898f6adada7..84499140e4bd 100644 --- a/drivers/net/ovpn/ovpnpriv.h +++ b/drivers/net/ovpn/ovpnpriv.h @@ -15,6 +15,10 @@ #include <uapi/linux/if_link.h> #include <uapi/linux/ovpn.h> +struct workqueue_struct; + +extern struct workqueue_struct *ovpn_wq; + /** * struct ovpn_peer_collection - container of peers for MultiPeer mode * @by_id: table of peers index by ID diff --git a/drivers/net/ovpn/peer.c b/drivers/net/ovpn/peer.c index 412ef09abd5e..6b9f5f12fc5a 100644 --- a/drivers/net/ovpn/peer.c +++ b/drivers/net/ovpn/peer.c @@ -62,7 +62,7 @@ void ovpn_peer_keepalive_set(struct ovpn_peer *peer, u32 interval, u32 timeout) /* now that interval and timeout have been changed, kick * off the worker so that the next delay can be recomputed */ - mod_delayed_work(system_wq, &peer->ovpn->keepalive_work, 0); + mod_delayed_work(ovpn_wq, &peer->ovpn->keepalive_work, 0); } /** @@ -1366,7 +1366,7 @@ static time64_t ovpn_peer_keepalive_work_single(struct ovpn_peer *peer, peer->id); if (WARN_ON(!ovpn_peer_hold(peer))) return 0; - if (!schedule_work(&peer->keepalive_work)) + if (!queue_work(ovpn_wq, &peer->keepalive_work)) ovpn_peer_put(peer); } @@ -1458,8 +1458,8 @@ void ovpn_peer_keepalive_work(struct work_struct *work) netdev_dbg(ovpn->dev, "scheduling keepalive work: now=%llu next_run=%llu delta=%llu\n", next_run, now, next_run - now); - schedule_delayed_work(&ovpn->keepalive_work, - (next_run - now) * HZ); + queue_delayed_work(ovpn_wq, &ovpn->keepalive_work, + (next_run - now) * HZ); } unlock_ovpn(ovpn, &release_list); } diff --git a/drivers/net/ovpn/tcp.c b/drivers/net/ovpn/tcp.c index 0af14055c39a..8fe8a8e750a4 100644 --- a/drivers/net/ovpn/tcp.c +++ b/drivers/net/ovpn/tcp.c @@ -151,7 +151,7 @@ err: /* take reference for deferred peer deletion. should never fail */ if (WARN_ON(!ovpn_peer_hold(peer))) goto err_nopeer; - if (!schedule_work(&peer->tcp.defer_del_work)) + if (!queue_work(ovpn_wq, &peer->tcp.defer_del_work)) ovpn_peer_put(peer); ovpn_dev_dstats_rx_dropped(peer->ovpn->dev); err_nopeer: @@ -284,13 +284,12 @@ static void ovpn_tcp_send_sock(struct ovpn_peer *peer, struct sock *sk) * stream therefore we abort the connection */ ovpn_peer_hold(peer); - if (!schedule_work(&peer->tcp.defer_del_work)) + if (!queue_work(ovpn_wq, &peer->tcp.defer_del_work)) ovpn_peer_put(peer); /* we bail out immediately and keep tx_in_progress set * to true. This way we prevent more TX attempts - * which would lead to more invocations of - * schedule_work() + * which would lead to more invocations of queue_work() */ return; } @@ -487,7 +486,7 @@ static void ovpn_tcp_write_space(struct sock *sk) rcu_read_lock(); sock = rcu_dereference_sk_user_data(sk); if (likely(sock && sock->peer)) { - schedule_work(&sock->tcp_tx_work); + queue_work(ovpn_wq, &sock->tcp_tx_work); sock->peer->tcp.sk_cb.sk_write_space(sk); } rcu_read_unlock(); diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index 1b7fc17bf391..848b6ec9bd85 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -959,7 +959,7 @@ static unsigned int phylink_inband_caps(struct phylink *pl, return 0; pcs = pl->mac_ops->mac_select_pcs(pl->config, interface); - if (!pcs) + if (IS_ERR_OR_NULL(pcs)) return 0; return phylink_pcs_inband_caps(pcs, interface); diff --git a/drivers/net/slip/slip.c b/drivers/net/slip/slip.c index bc84e2cc0502..59daf095cad6 100644 --- a/drivers/net/slip/slip.c +++ b/drivers/net/slip/slip.c @@ -628,9 +628,15 @@ static void sl_uninit(struct net_device *dev) struct slip *sl = netdev_priv(dev); sl_free_bufs(sl); + /* Drop the slip_devs[] entry here rather than from the destructor: + * ndo_uninit runs under RTNL, so it cannot race sl_sync(). + */ + slip_devs[dev->base_addr] = NULL; } -/* Hook the destructor so we can free slip devices at the right point in time */ +/* Only for the slip_open() error path: register_netdevice() can fail before + * ndo_init, and then ndo_uninit is not called either. + */ static void sl_free_netdev(struct net_device *dev) { int i = dev->base_addr; @@ -657,7 +663,6 @@ static void sl_setup(struct net_device *dev) { dev->netdev_ops = &sl_netdev_ops; dev->needs_free_netdev = true; - dev->priv_destructor = sl_free_netdev; dev->hard_header_len = 0; dev->addr_len = 0; @@ -908,7 +913,7 @@ static void slip_close(struct tty_struct *tty) #endif /* Flush network side */ unregister_netdev(sl->dev); - /* This will complete via sl_free_netdev */ + /* sl_uninit() has dropped the slip_devs[] entry by now */ } static void slip_hangup(struct tty_struct *tty) diff --git a/drivers/net/thunderbolt/main.c b/drivers/net/thunderbolt/main.c index ceaba08cd378..7bb9aa20fab9 100644 --- a/drivers/net/thunderbolt/main.c +++ b/drivers/net/thunderbolt/main.c @@ -629,6 +629,14 @@ static int tbnet_alloc_tx_buffers(struct tbnet *net) return 0; } +static void tbnet_connect_failed(struct tbnet *net) +{ + /* Leave login_received set: only the peer can make it true again. */ + mutex_lock(&net->connection_lock); + net->login_sent = false; + mutex_unlock(&net->connection_lock); +} + static void tbnet_connected_work(struct work_struct *work) { struct tbnet *net = container_of(work, typeof(*net), connected_work); @@ -650,6 +658,9 @@ static void tbnet_connected_work(struct work_struct *work) ret = tb_xdomain_alloc_in_hopid(net->xd, net->remote_transmit_path); if (ret != net->remote_transmit_path) { netdev_err(net->dev, "failed to allocate Rx HopID\n"); + if (ret >= 0) + tb_xdomain_release_in_hopid(net->xd, ret); + tbnet_connect_failed(net); return; } @@ -694,6 +705,7 @@ err_stop_rings: tb_ring_stop(net->rx_ring.ring); tb_ring_stop(net->tx_ring.ring); tb_xdomain_release_in_hopid(net->xd, net->remote_transmit_path); + tbnet_connect_failed(net); } static void tbnet_login_work(struct work_struct *work) diff --git a/drivers/net/tun.c b/drivers/net/tun.c index d27c3229465a..172273ae6575 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -1105,11 +1105,16 @@ static netdev_features_t tun_net_fix_features(struct net_device *dev, static void tun_set_headroom(struct net_device *dev, int new_hr) { struct tun_struct *tun = netdev_priv(dev); + size_t max_headroom; - if (new_hr < NET_SKB_PAD) - new_hr = NET_SKB_PAD; + max_headroom = min_t(size_t, SKB_MAX_HEAD(0), U16_MAX - 1); - tun->align = new_hr; + if ((tun->flags & TUN_TYPE_MASK) == IFF_TAP) + max_headroom -= ETH_HLEN + NET_IP_ALIGN; + else + max_headroom -= 1; + + tun->align = clamp_t(int, new_hr, NET_SKB_PAD, max_headroom); } static void @@ -1820,7 +1825,13 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile, switch (tun->flags & TUN_TYPE_MASK) { case IFF_TUN: if (tun->flags & IFF_NO_PI) { - u8 ip_version = skb->len ? (skb->data[0] >> 4) : 0; + u8 ip_version; + + if (!pskb_may_pull(skb, 1)) { + err = -EINVAL; + goto drop; + } + ip_version = skb->data[0] >> 4; switch (ip_version) { case 4: @@ -1840,7 +1851,7 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile, skb->dev = tun->dev; break; case IFF_TAP: - if (frags && !pskb_may_pull(skb, ETH_HLEN)) { + if (!pskb_may_pull(skb, ETH_HLEN)) { err = -ENOMEM; drop_reason = SKB_DROP_REASON_HDR_TRUNC; goto drop; diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 05acac10cd2b..c6d9ea259c0b 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -1360,6 +1360,7 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x1bbb, 0x0203, 2)}, /* Alcatel L800MA */ {QMI_FIXED_INTF(0x2357, 0x0201, 4)}, /* TP-LINK HSUPA Modem MA180 */ {QMI_FIXED_INTF(0x2357, 0x9000, 4)}, /* TP-LINK MA260 */ + {QMI_QUIRK_SET_DTR(0x1bc7, 0x0991, 0)}, /* Telit FE990D50 */ {QMI_QUIRK_SET_DTR(0x1bc7, 0x1031, 3)}, /* Telit LE910C1-EUX */ {QMI_QUIRK_SET_DTR(0x1bc7, 0x1034, 2)}, /* Telit LE910C4-WWX */ {QMI_QUIRK_SET_DTR(0x1bc7, 0x1037, 4)}, /* Telit LE910C4-WWX */ diff --git a/drivers/net/wireless/ath/ath11k/mac.c b/drivers/net/wireless/ath/ath11k/mac.c index f142c17aa9aa..4794caa9f7ea 100644 --- a/drivers/net/wireless/ath/ath11k/mac.c +++ b/drivers/net/wireless/ath/ath11k/mac.c @@ -1557,12 +1557,15 @@ static int ath11k_mac_setup_bcn_tmpl_ema(struct ath11k_vif *arvif, if (!beacons || !beacons->cnt) { ath11k_warn(arvif->ar->ab, "failed to get ema beacon templates from mac80211\n"); - return -EPERM; + ret = -EPERM; + goto free; } if (tx_arvif == arvif) { - if (ath11k_mac_set_vif_params(tx_arvif, beacons->bcn[0].skb)) - return -EINVAL; + if (ath11k_mac_set_vif_params(tx_arvif, beacons->bcn[0].skb)) { + ret = -EINVAL; + goto free; + } } else { arvif->wpaie_present = tx_arvif->wpaie_present; } @@ -1589,11 +1592,11 @@ static int ath11k_mac_setup_bcn_tmpl_ema(struct ath11k_vif *arvif, } } - ieee80211_beacon_free_ema_list(beacons); - if (tx_arvif != arvif && !nontx_vif_params_set) - return -EINVAL; /* Profile not found in the beacons */ + ret = -EINVAL; /* Profile not found in the beacons */ +free: + ieee80211_beacon_free_ema_list(beacons); return ret; } @@ -1622,19 +1625,22 @@ static int ath11k_mac_setup_bcn_tmpl_mbssid(struct ath11k_vif *arvif, } if (tx_arvif == arvif) { - if (ath11k_mac_set_vif_params(tx_arvif, bcn)) - return -EINVAL; + if (ath11k_mac_set_vif_params(tx_arvif, bcn)) { + ret = -EINVAL; + goto free; + } } else if (!ath11k_mac_set_nontx_vif_params(tx_arvif, arvif, bcn)) { - return -EINVAL; + ret = -EINVAL; + goto free; } ret = ath11k_wmi_bcn_tmpl(ar, arvif->vdev_id, &offs, bcn, 0); - kfree_skb(bcn); - if (ret) ath11k_warn(ab, "failed to submit beacon template command: %d\n", ret); +free: + kfree_skb(bcn); return ret; } diff --git a/drivers/net/wireless/ath/ath6kl/cfg80211.c b/drivers/net/wireless/ath/ath6kl/cfg80211.c index 88f0197fc041..e4f87018f164 100644 --- a/drivers/net/wireless/ath/ath6kl/cfg80211.c +++ b/drivers/net/wireless/ath/ath6kl/cfg80211.c @@ -753,6 +753,11 @@ void ath6kl_cfg80211_connect_event(struct ath6kl_vif *vif, u16 channel, u8 *assoc_resp_ie = assoc_info + beacon_ie_len + assoc_req_len + assoc_resp_ie_offset; + if (assoc_req_len < assoc_req_ie_offset) + assoc_req_len = assoc_req_ie_offset; + if (assoc_resp_len < assoc_resp_ie_offset) + assoc_resp_len = assoc_resp_ie_offset; + assoc_req_len -= assoc_req_ie_offset; assoc_resp_len -= assoc_resp_ie_offset; diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c index 936df04504ec..5beceea8f76b 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c @@ -1827,17 +1827,18 @@ gotpkt: if (bus->rxctl) { brcmf_err("last control frame is being processed.\n"); spin_unlock_bh(&bus->rxctl_lock); - vfree(buf); goto done; } bus->rxctl = buf + doff; bus->rxctl_orig = buf; bus->rxlen = len - doff; spin_unlock_bh(&bus->rxctl_lock); + buf = NULL; done: /* Awake any waiters */ brcmf_sdio_dcmd_resp_wake(bus); + vfree(buf); } /* Pad read to blocksize for efficiency */ diff --git a/drivers/net/wireless/intel/iwlwifi/dvm/main.c b/drivers/net/wireless/intel/iwlwifi/dvm/main.c index 2b4dbebc71c2..72dc0d8dc9b9 100644 --- a/drivers/net/wireless/intel/iwlwifi/dvm/main.c +++ b/drivers/net/wireless/intel/iwlwifi/dvm/main.c @@ -1511,10 +1511,10 @@ out_destroy_workqueue: priv->workqueue = NULL; out_uninit_drv: iwl_uninit_drv(priv); -out_free_eeprom_blob: - kfree(priv->eeprom_blob); out_free_eeprom: kfree(priv->nvm_data); +out_free_eeprom_blob: + kfree(priv->eeprom_blob); out_leave_trans: iwl_trans_op_mode_leave(priv->trans); out_free_hw: diff --git a/drivers/net/wireless/marvell/mwifiex/sta_ioctl.c b/drivers/net/wireless/marvell/mwifiex/sta_ioctl.c index 358de94eeb5e..b8267a5ebcfb 100644 --- a/drivers/net/wireless/marvell/mwifiex/sta_ioctl.c +++ b/drivers/net/wireless/marvell/mwifiex/sta_ioctl.c @@ -57,6 +57,18 @@ int mwifiex_wait_queue_complete(struct mwifiex_adapter *adapter, mwifiex_dbg(adapter, ERROR, "cmd_wait_q terminated: %d\n", status); mwifiex_cancel_all_pending_cmd(adapter); + + /* The command response path writes through cmd_node->data_buf. + * On an interrupted wait, the caller can return and release a + * stack-allocated data_buf before a late firmware response is + * processed. Detach the caller-owned buffer from the current + * command so a late response cannot corrupt freed stack memory. + */ + spin_lock_bh(&adapter->mwifiex_cmd_lock); + if (adapter->curr_cmd == cmd_queued) + adapter->curr_cmd->data_buf = NULL; + spin_unlock_bh(&adapter->mwifiex_cmd_lock); + return status; } diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/main.c b/drivers/net/wireless/mediatek/mt76/mt7615/main.c index 87a2e5163699..25936fb309fb 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7615/main.c +++ b/drivers/net/wireless/mediatek/mt76/mt7615/main.c @@ -1239,11 +1239,12 @@ static int mt7615_suspend(struct ieee80211_hw *hw, cancel_delayed_work_sync(&dev->pm.ps_work); mt76_connac_free_pending_tx_skbs(&dev->pm, NULL); + cancel_delayed_work_sync(&phy->scan_work); + cancel_delayed_work_sync(&phy->mt76->mac_work); + mt7615_mutex_acquire(dev); clear_bit(MT76_STATE_RUNNING, &phy->mt76->state); - cancel_delayed_work_sync(&phy->scan_work); - cancel_delayed_work_sync(&phy->mt76->mac_work); set_bit(MT76_STATE_SUSPEND, &phy->mt76->state); ieee80211_iterate_active_interfaces(hw, diff --git a/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c b/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c index 2aa7b711c774..46e337307c3d 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c +++ b/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c @@ -1295,8 +1295,10 @@ int mt76_connac_mcu_sta_ba(struct mt76_dev *dev, struct mt76_vif_link *mvif, wtbl_hdr); ret = mt76_connac_mcu_sta_wed_update(dev, skb); - if (ret) + if (ret) { + dev_kfree_skb(skb); return ret; + } ret = mt76_mcu_skb_send_msg(dev, skb, cmd, true); if (ret) @@ -1309,8 +1311,10 @@ int mt76_connac_mcu_sta_ba(struct mt76_dev *dev, struct mt76_vif_link *mvif, mt76_connac_mcu_sta_ba_tlv(skb, params, enable, tx); ret = mt76_connac_mcu_sta_wed_update(dev, skb); - if (ret) + if (ret) { + dev_kfree_skb(skb); return ret; + } return mt76_mcu_skb_send_msg(dev, skb, cmd, true); } @@ -2766,12 +2770,16 @@ int mt76_connac_mcu_add_key(struct mt76_dev *dev, struct ieee80211_vif *vif, return PTR_ERR(skb); ret = mt76_connac_mcu_sta_key_tlv(sta_key_conf, skb, key, cmd); - if (ret) + if (ret) { + dev_kfree_skb(skb); return ret; + } ret = mt76_connac_mcu_sta_wed_update(dev, skb); - if (ret) + if (ret) { + dev_kfree_skb(skb); return ret; + } return mt76_mcu_skb_send_msg(dev, skb, mcu_cmd, true); } diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c index f60e2eaea2af..1646b9ba2980 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c +++ b/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c @@ -1773,8 +1773,10 @@ int mt7915_mcu_add_sta(struct mt7915_dev *dev, struct ieee80211_vif *vif, } out: ret = mt76_connac_mcu_sta_wed_update(&dev->mt76, skb); - if (ret) + if (ret) { + dev_kfree_skb(skb); return ret; + } return mt76_mcu_skb_send_msg(&dev->mt76, skb, MCU_EXT_CMD(STA_REC_UPDATE), true); @@ -2915,8 +2917,15 @@ int mt7915_mcu_get_eeprom(struct mt7915_dev *dev, u32 offset, u8 *read_buf) return ret; res = (struct mt7915_mcu_eeprom_info *)skb->data; - if (!buf) - buf = dev->mt76.eeprom.data + le32_to_cpu(res->addr); + if (!buf) { + u32 addr = le32_to_cpu(res->addr); + + if (addr > dev->mt76.eeprom.size - MT7915_EEPROM_BLOCK_SIZE) { + dev_kfree_skb(skb); + return -EINVAL; + } + buf = dev->mt76.eeprom.data + addr; + } memcpy(buf, res->data, MT7915_EEPROM_BLOCK_SIZE); dev_kfree_skb(skb); diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/mac.c b/drivers/net/wireless/mediatek/mt76/mt7925/mac.c index 18f99d6570ad..f9980b5f4532 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7925/mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt7925/mac.c @@ -1312,6 +1312,7 @@ void mt7925_mac_reset_work(struct work_struct *work) cancel_delayed_work_sync(&dev->mphy.mac_work); cancel_delayed_work_sync(&pm->ps_work); + cancel_delayed_work_sync(&dev->mlo_pm_work); cancel_work_sync(&pm->wake_work); for (i = 0; i < 10; i++) { diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/main.c b/drivers/net/wireless/mediatek/mt76/mt7925/main.c index 910713e62e14..8ef0d981adc9 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7925/main.c +++ b/drivers/net/wireless/mediatek/mt76/mt7925/main.c @@ -1502,6 +1502,7 @@ static int mt7925_suspend(struct ieee80211_hw *hw, cancel_delayed_work_sync(&phy->mt76->mac_work); cancel_delayed_work_sync(&dev->pm.ps_work); + cancel_delayed_work_sync(&dev->mlo_pm_work); mt76_connac_free_pending_tx_skbs(&dev->pm, NULL); mt792x_mutex_acquire(dev); @@ -2180,10 +2181,19 @@ static void mt7925_rfkill_poll(struct ieee80211_hw *hw) wiphy_rfkill_set_hw_state(hw->wiphy, ret == 0); } +static void mt7925_stop(struct ieee80211_hw *hw, bool suspend) +{ + struct mt792x_dev *dev = mt792x_hw_dev(hw); + + cancel_delayed_work_sync(&dev->mlo_pm_work); + + mt792x_stop(hw, suspend); +} + const struct ieee80211_ops mt7925_ops = { .tx = mt792x_tx, .start = mt7925_start, - .stop = mt792x_stop, + .stop = mt7925_stop, .add_interface = mt7925_add_interface, .remove_interface = mt792x_remove_interface, .config = mt7925_config, diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c index 647efa963db4..bc19e800b41c 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c +++ b/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c @@ -1290,8 +1290,10 @@ int mt7925_mcu_add_key(struct mt76_dev *dev, struct ieee80211_vif *vif, return PTR_ERR(skb); ret = mt7925_mcu_sta_key_tlv(wcid, sta_key_conf, skb, key, cmd, msta); - if (ret) + if (ret) { + dev_kfree_skb(skb); return ret; + } return mt76_mcu_skb_send_msg(dev, skb, mcu_cmd, true); } diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/pci.c b/drivers/net/wireless/mediatek/mt76/mt7925/pci.c index d6732f50784c..7972111d53a4 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7925/pci.c +++ b/drivers/net/wireless/mediatek/mt76/mt7925/pci.c @@ -41,6 +41,7 @@ static void mt7925e_unregister_device(struct mt792x_dev *dev) mt76_for_each_q_rx(&dev->mt76, i) napi_disable(&dev->mt76.napi[i]); cancel_delayed_work_sync(&pm->ps_work); + cancel_delayed_work_sync(&dev->mlo_pm_work); cancel_work_sync(&pm->wake_work); cancel_work_sync(&dev->reset_work); @@ -454,6 +455,7 @@ static int mt7925_pci_suspend(struct device *device) dev->hif_resumed = false; flush_work(&dev->reset_work); cancel_delayed_work_sync(&pm->ps_work); + cancel_delayed_work_sync(&dev->mlo_pm_work); cancel_work_sync(&pm->wake_work); mt7925_roc_abort_sync(dev); diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/usb.c b/drivers/net/wireless/mediatek/mt76/mt7925/usb.c index bf040f34e4b9..16ab139b6748 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7925/usb.c +++ b/drivers/net/wireless/mediatek/mt76/mt7925/usb.c @@ -251,6 +251,7 @@ static int mt7925u_suspend(struct usb_interface *intf, pm_message_t state) pm->suspended = true; dev->hif_resumed = false; flush_work(&dev->reset_work); + cancel_delayed_work_sync(&dev->mlo_pm_work); mt76_connac_mcu_set_hif_suspend(&dev->mt76, true, false); ret = wait_event_timeout(dev->wait, diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/eeprom.c b/drivers/net/wireless/mediatek/mt76/mt7996/eeprom.c index da3231c9aa11..11e0a28113a2 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7996/eeprom.c +++ b/drivers/net/wireless/mediatek/mt76/mt7996/eeprom.c @@ -148,6 +148,12 @@ mt7996_eeprom_check_or_use_default(struct mt7996_dev *dev, bool use_default) goto out; } + if (fw->size < MT7996_EEPROM_SIZE) { + dev_err(dev->mt76.dev, "Invalid default bin size\n"); + ret = -EINVAL; + goto out; + } + if (!use_default && mt7996_eeprom_variant_valid(dev, fw->data)) goto out; diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c index 29f599a7ad01..e55bb232bdeb 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c @@ -1279,6 +1279,30 @@ mt7996_tx_check_aggr(struct ieee80211_link_sta *link_sta, } static void +mt7996_txp_skb_unmap(struct mt76_dev *mdev, struct mt76_txwi_cache *t) +{ + u8 *txwi_ptr = mt76_get_txwi_ptr(mdev, t); + __le32 *txwi = (__le32 *)txwi_ptr; + __le32 *txp; + dma_addr_t addr; + u32 val; + + if (!(le32_to_cpu(txwi[7]) & MT_TXD7_MAC_TXD)) { + mt76_connac_txp_skb_unmap(mdev, t); + return; + } + + txp = (__le32 *)(txwi_ptr + MT_TXD_SIZE); + val = le32_to_cpu(txp[3]); + addr = le32_to_cpu(txp[2]); +#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT + addr |= (dma_addr_t)FIELD_GET(MT_TXP3_DMA_ADDR_H, val) << 32; +#endif + dma_unmap_single(mdev->dma_dev, addr, FIELD_GET(MT_TXP_BUF_LEN, val), + DMA_TO_DEVICE); +} + +static void mt7996_txwi_free(struct mt7996_dev *dev, struct mt76_txwi_cache *t, struct ieee80211_link_sta *link_sta, struct mt76_wcid *wcid, struct list_head *free_list) @@ -1287,7 +1311,7 @@ mt7996_txwi_free(struct mt7996_dev *dev, struct mt76_txwi_cache *t, __le32 *txwi; u16 wcid_idx; - mt76_connac_txp_skb_unmap(mdev, t); + mt7996_txp_skb_unmap(mdev, t); if (!t->skb) goto out; diff --git a/drivers/net/wireless/realtek/rtl818x/rtl8180/dev.c b/drivers/net/wireless/realtek/rtl818x/rtl8180/dev.c index 070c0431c482..4a5989172a5e 100644 --- a/drivers/net/wireless/realtek/rtl818x/rtl8180/dev.c +++ b/drivers/net/wireless/realtek/rtl818x/rtl8180/dev.c @@ -1652,7 +1652,7 @@ static void rtl8180_eeprom_register_write(struct eeprom_93cx6 *eeprom) static void rtl8180_eeprom_read(struct rtl8180_priv *priv) { - struct eeprom_93cx6 eeprom; + struct eeprom_93cx6 eeprom = {}; int eeprom_cck_table_adr; u16 eeprom_val; int i; diff --git a/drivers/net/wireless/realtek/rtl818x/rtl8187/dev.c b/drivers/net/wireless/realtek/rtl818x/rtl8187/dev.c index 7aa2da0cd63c..98174bb3cf2a 100644 --- a/drivers/net/wireless/realtek/rtl818x/rtl8187/dev.c +++ b/drivers/net/wireless/realtek/rtl818x/rtl8187/dev.c @@ -1445,7 +1445,7 @@ static int rtl8187_probe(struct usb_interface *intf, struct usb_device *udev = interface_to_usbdev(intf); struct ieee80211_hw *dev; struct rtl8187_priv *priv; - struct eeprom_93cx6 eeprom; + struct eeprom_93cx6 eeprom = {}; struct ieee80211_channel *channel; const char *chip_name; u16 txpwr, reg; diff --git a/drivers/net/wireless/realtek/rtl8xxxu/core.c b/drivers/net/wireless/realtek/rtl8xxxu/core.c index 25e5fd48b8e2..f8bd9bfe74ba 100644 --- a/drivers/net/wireless/realtek/rtl8xxxu/core.c +++ b/drivers/net/wireless/realtek/rtl8xxxu/core.c @@ -5885,14 +5885,19 @@ static void rtl8xxxu_queue_rx_urb(struct rtl8xxxu_priv *priv, { struct sk_buff *skb; unsigned long flags; - int pending = 0; spin_lock_irqsave(&priv->rx_urb_lock, flags); if (!priv->shutdown) { list_add_tail(&rx_urb->list, &priv->rx_urb_pending_list); priv->rx_urb_pending_count++; - pending = priv->rx_urb_pending_count; + /* + * Arm the worker under rx_urb_lock so this is atomic with the + * shutdown check: moving it out of the lock would let a + * completion arm the work after rtl8xxxu_stop() canceled it. + */ + if (priv->rx_urb_pending_count > RTL8XXXU_RX_URB_PENDING_WATER) + schedule_work(&priv->rx_urb_wq); } else { skb = (struct sk_buff *)rx_urb->urb.context; dev_kfree_skb_irq(skb); @@ -5900,9 +5905,6 @@ static void rtl8xxxu_queue_rx_urb(struct rtl8xxxu_priv *priv, } spin_unlock_irqrestore(&priv->rx_urb_lock, flags); - - if (pending > RTL8XXXU_RX_URB_PENDING_WATER) - schedule_work(&priv->rx_urb_wq); } static void rtl8xxxu_rx_urb_work(struct work_struct *work) @@ -7550,6 +7552,13 @@ static void rtl8xxxu_stop(struct ieee80211_hw *hw, bool suspend) priv->shutdown = true; spin_unlock_irqrestore(&priv->rx_urb_lock, flags); + /* + * Cancel before killing rx_anchor: the worker re-anchors every URB + * it drained via rtl8xxxu_submit_rx_urb(), so a worker still running + * after the kill could submit a URB that escapes it. + */ + cancel_work_sync(&priv->rx_urb_wq); + usb_kill_anchored_urbs(&priv->rx_anchor); usb_kill_anchored_urbs(&priv->tx_anchor); if (priv->usb_interrupts) diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192du/sw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192du/sw.c index cc699efa9c79..a7824ba346e6 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8192du/sw.c +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192du/sw.c @@ -147,8 +147,10 @@ static int rtl92du_init_sw_vars(struct ieee80211_hw *hw) /* for firmware buf */ rtlpriv->rtlhal.pfirmware = kmalloc(0x8000, GFP_KERNEL); - if (!rtlpriv->rtlhal.pfirmware) - return -ENOMEM; + if (!rtlpriv->rtlhal.pfirmware) { + err = -ENOMEM; + goto error; + } rtlpriv->max_fw_size = 0x8000; pr_info("Driver for Realtek RTL8192DU WLAN interface\n"); @@ -162,10 +164,14 @@ static int rtl92du_init_sw_vars(struct ieee80211_hw *hw) pr_err("Failed to request firmware!\n"); kfree(rtlpriv->rtlhal.pfirmware); rtlpriv->rtlhal.pfirmware = NULL; - return err; + goto error; } return 0; + +error: + rtl92du_deinit_shared_data(hw); + return err; } static void rtl92du_deinit_sw_vars(struct ieee80211_hw *hw) diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192du/trx.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192du/trx.c index 743ce0cfffe6..c608c51f1b78 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8192du/trx.c +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192du/trx.c @@ -106,7 +106,8 @@ void rtl92du_tx_fill_desc(struct ieee80211_hw *hw, if (sta) { sta_entry = (struct rtl_sta_info *)sta->drv_priv; tid = ieee80211_get_tid(hdr); - agg_state = sta_entry->tids[tid].agg.agg_state; + if (tid < MAX_TID_COUNT) + agg_state = sta_entry->tids[tid].agg.agg_state; ampdu_density = sta->deflink.ht_cap.ampdu_density; } diff --git a/drivers/net/wireless/realtek/rtw88/pci.c b/drivers/net/wireless/realtek/rtw88/pci.c index eae54f50485c..8bdac965d6ff 100644 --- a/drivers/net/wireless/realtek/rtw88/pci.c +++ b/drivers/net/wireless/realtek/rtw88/pci.c @@ -1799,7 +1799,7 @@ int rtw_pci_probe(struct pci_dev *pdev, ret = rtw_pci_napi_init(rtwdev); if (ret) { rtw_err(rtwdev, "failed to setup NAPI\n"); - goto err_pci_declaim; + goto err_destroy_rsrc; } ret = rtw_chip_info_setup(rtwdev); @@ -1831,6 +1831,8 @@ int rtw_pci_probe(struct pci_dev *pdev, err_destroy_pci: rtw_pci_napi_deinit(rtwdev); + +err_destroy_rsrc: rtw_pci_destroy(rtwdev, pdev); err_pci_declaim: diff --git a/drivers/net/wireless/realtek/rtw88/tx.c b/drivers/net/wireless/realtek/rtw88/tx.c index 9e24741b2cb1..611dade1b1eb 100644 --- a/drivers/net/wireless/realtek/rtw88/tx.c +++ b/drivers/net/wireless/realtek/rtw88/tx.c @@ -619,6 +619,7 @@ static int rtw_txq_push_skb(struct rtw_dev *rtwdev, ret = rtw_hci_tx_write(rtwdev, &pkt_info, skb); if (ret) { rtw_err(rtwdev, "failed to write TX skb to HCI\n"); + ieee80211_free_txskb(rtwdev->hw, skb); return ret; } return 0; diff --git a/drivers/ntb/ntb_transport.c b/drivers/ntb/ntb_transport.c index 2cee3c1729c3..aea63fab2ea3 100644 --- a/drivers/ntb/ntb_transport.c +++ b/drivers/ntb/ntb_transport.c @@ -1755,9 +1755,16 @@ static void ntb_transport_rxc_db(unsigned long data) static void ntb_tx_copy_callback(void *data, const struct dmaengine_result *res) { + struct ntb_payload_header __iomem *hdr; struct ntb_queue_entry *entry = data; - struct ntb_transport_qp *qp = entry->qp; - struct ntb_payload_header __iomem *hdr = entry->tx_hdr; + struct ntb_transport_qp *qp; + unsigned int len; + void *cb_data; + + qp = entry->qp; + hdr = entry->tx_hdr; + cb_data = entry->cb_data; + len = entry->len; /* we need to check DMA results if we are using DMA */ if (res) { @@ -1797,15 +1804,13 @@ static void ntb_tx_copy_callback(void *data, * "link down" or similar. Since no payload is being sent in these * cases, there is nothing to add to the completion queue. */ - if (entry->len > 0) { - qp->tx_bytes += entry->len; - - if (qp->tx_handler) - qp->tx_handler(qp, qp->cb_data, entry->cb_data, - entry->len); - } + if (len > 0) + qp->tx_bytes += len; ntb_list_add(&qp->ntb_tx_free_q_lock, &entry->entry, &qp->tx_free_q); + + if (len > 0 && qp->tx_handler) + qp->tx_handler(qp, qp->cb_data, cb_data, len); } static void ntb_memcpy_tx(struct ntb_queue_entry *entry, void __iomem *offset) @@ -1930,15 +1935,6 @@ static int ntb_process_tx(struct ntb_transport_qp *qp, return -EAGAIN; } - if (entry->len > qp->tx_max_frame - sizeof(struct ntb_payload_header)) { - if (qp->tx_handler) - qp->tx_handler(qp, qp->cb_data, NULL, -EIO); - - ntb_list_add(&qp->ntb_tx_free_q_lock, &entry->entry, - &qp->tx_free_q); - return 0; - } - ntb_async_tx(qp, entry); qp->tx_index++; @@ -2310,9 +2306,11 @@ int ntb_transport_tx_enqueue(struct ntb_transport_qp *qp, void *cb, void *data, if (!qp || !len) return -EINVAL; - /* If the qp link is down already, just ignore. */ if (!qp->link_is_up) - return 0; + return -ENOLINK; + + if (len > qp->tx_max_frame - sizeof(struct ntb_payload_header)) + return -EMSGSIZE; entry = ntb_list_rm(&qp->ntb_tx_free_q_lock, &qp->tx_free_q); if (!entry) { diff --git a/drivers/nvdimm/label.c b/drivers/nvdimm/label.c index 04f4a049599a..584a9c27ce4b 100644 --- a/drivers/nvdimm/label.c +++ b/drivers/nvdimm/label.c @@ -202,7 +202,7 @@ static int __nd_label_validate(struct nvdimm_drvdata *ndd) } nslot = __le32_to_cpu(nsindex[i]->nslot); - if (nslot * sizeof_namespace_label(ndd) + if ((u64)nslot * sizeof_namespace_label(ndd) + 2 * sizeof_namespace_index(ndd) > ndd->nsarea.config_size) { dev_dbg(dev, "nsindex%d nslot: %u invalid, config_size: %#x\n", diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 24a5ca35aeb2..d7199fc97f18 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -5120,7 +5120,7 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev, BUILD_BUG_ON(NVME_DSM_MAX_RANGES * sizeof(struct nvme_dsm_range) > PAGE_SIZE); - ctrl->discard_page = alloc_page(GFP_KERNEL); + ctrl->discard_page = alloc_page(GFP_KERNEL | __GFP_ZERO); if (!ctrl->discard_page) { ret = -ENOMEM; goto out; diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index bf78faf1a4ff..101a3667559d 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -2316,7 +2316,7 @@ nvme_fc_create_hw_io_queues(struct nvme_fc_ctrl *ctrl, u16 qsize) return 0; delete_queues: - for (; i > 0; i--) + for (--i; i > 0; i--) __nvme_fc_delete_hw_queue(ctrl, &ctrl->queues[i], i); return ret; } diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 489583393b84..0a46c60583d7 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -2161,6 +2161,7 @@ static int nvme_pci_configure_admin_queue(struct nvme_dev *dev) result = queue_request_irq(nvmeq); if (result) { dev->online_queues--; + nvme_disable_ctrl(&dev->ctrl, false); return result; } diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c index 04c074ae8f7b..da826e96a4cc 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -117,6 +117,7 @@ struct nvme_tcp_request { struct bio *curr_bio; struct iov_iter iter; + u32 data_recvd; /* send state */ size_t offset; @@ -621,6 +622,29 @@ static void nvme_tcp_error_recovery(struct nvme_ctrl *ctrl) queue_work(nvme_reset_wq, &to_tcp_ctrl(ctrl)->err_work); } +/* + * NVMe has no short read: a read that completes successfully must + * have transferred everything it asked for. + */ +static bool nvme_tcp_data_in_short(struct nvme_tcp_queue *queue, + struct request *rq) +{ + struct nvme_tcp_request *req = blk_mq_rq_to_pdu(rq); + + if (le16_to_cpu(req->status) >> 1) + return false; + if (req_op(rq) != REQ_OP_READ || !req->data_len) + return false; + if (likely(req->data_recvd == req->data_len)) + return false; + + dev_err(queue->ctrl->ctrl.device, + "queue %d tag %#x short data-in: got %u of %u\n", + nvme_tcp_queue_id(queue), rq->tag, + req->data_recvd, req->data_len); + return true; +} + static int nvme_tcp_process_nvme_cqe(struct nvme_tcp_queue *queue, struct nvme_completion *cqe) { @@ -640,6 +664,9 @@ static int nvme_tcp_process_nvme_cqe(struct nvme_tcp_queue *queue, if (req->status == cpu_to_le16(NVME_SC_SUCCESS)) req->status = cqe->status; + if (unlikely(nvme_tcp_data_in_short(queue, rq))) + return -EPROTO; + if (!nvme_try_complete_req(rq, req->status, cqe->result)) nvme_complete_rq(rq); queue->nr_cqe++; @@ -650,6 +677,7 @@ static int nvme_tcp_process_nvme_cqe(struct nvme_tcp_queue *queue, static int nvme_tcp_handle_c2h_data(struct nvme_tcp_queue *queue, struct nvme_tcp_data_pdu *pdu) { + struct nvme_tcp_request *req; struct request *rq; rq = nvme_find_rq(nvme_tcp_tagset(queue), pdu->command_id); @@ -660,7 +688,8 @@ static int nvme_tcp_handle_c2h_data(struct nvme_tcp_queue *queue, return -ENOENT; } - if (!blk_rq_payload_bytes(rq)) { + req = blk_mq_rq_to_pdu(rq); + if (!blk_rq_payload_bytes(rq) || !req->curr_bio || !req->data_len) { dev_err(queue->ctrl->ctrl.device, "queue %d tag %#x unexpected data\n", nvme_tcp_queue_id(queue), rq->tag); @@ -754,6 +783,13 @@ static int nvme_tcp_handle_r2t(struct nvme_tcp_queue *queue, } req = blk_mq_rq_to_pdu(rq); + if (unlikely(rq_data_dir(rq) != WRITE)) { + dev_err(queue->ctrl->ctrl.device, + "req %d unexpected r2t for a non-write command\n", + rq->tag); + return -EPROTO; + } + if (unlikely(!r2t_length)) { dev_err(queue->ctrl->ctrl.device, "req %d r2t len is %u, probably a bug...\n", @@ -962,6 +998,7 @@ static int nvme_tcp_recv_data(struct nvme_tcp_queue *queue, struct sk_buff *skb, *len -= recv_len; *offset += recv_len; queue->data_remaining -= recv_len; + req->data_recvd += recv_len; } if (!queue->data_remaining) { @@ -970,6 +1007,8 @@ static int nvme_tcp_recv_data(struct nvme_tcp_queue *queue, struct sk_buff *skb, queue->ddgst_remaining = NVME_TCP_DIGEST_LENGTH; } else { if (pdu->hdr.flags & NVME_TCP_F_DATA_SUCCESS) { + if (unlikely(nvme_tcp_data_in_short(queue, rq))) + return -EPROTO; nvme_tcp_end_request(rq, le16_to_cpu(req->status)); queue->nr_cqe++; @@ -1018,6 +1057,9 @@ static int nvme_tcp_recv_ddgst(struct nvme_tcp_queue *queue, pdu->command_id); struct nvme_tcp_request *req = blk_mq_rq_to_pdu(rq); + if (unlikely(nvme_tcp_data_in_short(queue, rq))) + return -EPROTO; + nvme_tcp_end_request(rq, le16_to_cpu(req->status)); queue->nr_cqe++; } @@ -2720,6 +2762,7 @@ static blk_status_t nvme_tcp_setup_cmd_pdu(struct nvme_ns *ns, req->status = cpu_to_le16(NVME_SC_SUCCESS); req->offset = 0; req->data_sent = 0; + req->data_recvd = 0; req->pdu_len = 0; req->pdu_sent = 0; req->h2cdata_left = 0; diff --git a/drivers/of/base.c b/drivers/of/base.c index 6620bf07b79b..25529235c1a6 100644 --- a/drivers/of/base.c +++ b/drivers/of/base.c @@ -1891,7 +1891,7 @@ void of_alias_scan(void * (*dt_alloc)(u64 size, u64 align)) /* walk the alias backwards to extract the id and work out * the 'stem' string */ - while (isdigit(*(end-1)) && end > start) + while (end > start && isdigit(*(end - 1))) end--; len = end - start; diff --git a/drivers/pci/controller/dwc/pci-meson.c b/drivers/pci/controller/dwc/pci-meson.c index 225d887cd0a3..e3fe61ef862b 100644 --- a/drivers/pci/controller/dwc/pci-meson.c +++ b/drivers/pci/controller/dwc/pci-meson.c @@ -402,7 +402,7 @@ static int meson_pcie_probe(struct platform_device *pdev) return PTR_ERR(mp->phy); } - mp->reset_gpio = devm_gpiod_get(dev, "reset", GPIOD_OUT_LOW); + mp->reset_gpio = devm_gpiod_get(dev, "reset", GPIOD_OUT_HIGH); if (IS_ERR(mp->reset_gpio)) { dev_err(dev, "get reset gpio failed\n"); return PTR_ERR(mp->reset_gpio); diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c index 28b157297487..fff5df771d5b 100644 --- a/drivers/pci/controller/pci-hyperv.c +++ b/drivers/pci/controller/pci-hyperv.c @@ -2120,6 +2120,7 @@ static bool hv_pcie_init_dev_msi_info(struct device *dev, struct irq_domain *dom info->ops->msi_prepare = hv_msi_prepare; chip->irq_set_affinity = irq_chip_set_affinity_parent; + chip->irq_retrigger = irq_chip_retrigger_hierarchy; if (IS_ENABLED(CONFIG_X86)) chip->flags |= IRQCHIP_MOVE_DEFERRED; diff --git a/drivers/pci/controller/plda/pcie-plda-host.c b/drivers/pci/controller/plda/pcie-plda-host.c index 3c2f68383010..dea3d443434c 100644 --- a/drivers/pci/controller/plda/pcie-plda-host.c +++ b/drivers/pci/controller/plda/pcie-plda-host.c @@ -419,6 +419,8 @@ static int plda_pcie_init_irq_domains(struct plda_pcie_rp *port) return plda_allocate_msi_domains(port); } +static void plda_pcie_irq_domain_deinit(struct plda_pcie_rp *pcie); + int plda_init_interrupts(struct platform_device *pdev, struct plda_pcie_rp *port, const struct plda_event *event) @@ -440,14 +442,17 @@ int plda_init_interrupts(struct platform_device *pdev, } port->irq = platform_get_irq(pdev, 0); - if (port->irq < 0) - return -ENODEV; + if (port->irq < 0) { + ret = -ENODEV; + goto err_irq_domain_deinit; + } for_each_set_bit(i, &port->events_bitmap, port->num_events) { event_irq = irq_create_mapping(port->event_domain, i); if (!event_irq) { dev_err(dev, "failed to map hwirq %d\n", i); - return -ENXIO; + ret = -ENXIO; + goto err_irq_domain_deinit; } if (event->request_event_irq) @@ -459,7 +464,7 @@ int plda_init_interrupts(struct platform_device *pdev, if (ret) { dev_err(dev, "failed to request IRQ %d\n", event_irq); - return ret; + goto err_irq_domain_deinit; } } @@ -467,7 +472,8 @@ int plda_init_interrupts(struct platform_device *pdev, event->intx_event); if (!port->intx_irq) { dev_err(dev, "failed to map INTx interrupt\n"); - return -ENXIO; + ret = -ENXIO; + goto err_irq_domain_deinit; } /* Plug the INTx chained handler */ @@ -475,8 +481,11 @@ int plda_init_interrupts(struct platform_device *pdev, port->msi_irq = irq_create_mapping(port->event_domain, event->msi_event); - if (!port->msi_irq) - return -ENXIO; + if (!port->msi_irq) { + dev_err(dev, "failed to map MSI interrupt\n"); + ret = -ENXIO; + goto err_irq_domain_deinit; + } /* Plug the MSI chained handler */ irq_set_chained_handler_and_data(port->msi_irq, plda_handle_msi, port); @@ -485,6 +494,11 @@ int plda_init_interrupts(struct platform_device *pdev, irq_set_chained_handler_and_data(port->irq, plda_handle_event, port); return 0; + +err_irq_domain_deinit: + plda_pcie_irq_domain_deinit(port); + + return ret; } EXPORT_SYMBOL_GPL(plda_init_interrupts); @@ -559,9 +573,27 @@ EXPORT_SYMBOL_GPL(plda_pcie_setup_iomems); static void plda_pcie_irq_domain_deinit(struct plda_pcie_rp *pcie) { - irq_set_chained_handler_and_data(pcie->irq, NULL, NULL); - irq_set_chained_handler_and_data(pcie->msi_irq, NULL, NULL); - irq_set_chained_handler_and_data(pcie->intx_irq, NULL, NULL); + u32 i, event_irq; + + if (pcie->irq > 0) + irq_set_chained_handler_and_data(pcie->irq, NULL, NULL); + if (pcie->msi_irq > 0) + irq_set_chained_handler_and_data(pcie->msi_irq, NULL, NULL); + if (pcie->intx_irq > 0) + irq_set_chained_handler_and_data(pcie->intx_irq, NULL, NULL); + + for_each_set_bit(i, &pcie->events_bitmap, pcie->num_events) { + event_irq = irq_find_mapping(pcie->event_domain, i); + if (event_irq) { + devm_free_irq(pcie->dev, event_irq, pcie); + irq_dispose_mapping(event_irq); + } + } + + if (pcie->intx_irq) + irq_dispose_mapping(pcie->intx_irq); + if (pcie->msi_irq) + irq_dispose_mapping(pcie->msi_irq); irq_domain_remove(pcie->msi.dev_domain); diff --git a/drivers/pci/msi/msi.c b/drivers/pci/msi/msi.c index 34d664139f48..7e2332869306 100644 --- a/drivers/pci/msi/msi.c +++ b/drivers/pci/msi/msi.c @@ -860,6 +860,7 @@ void __pci_restore_msix_state(struct pci_dev *dev) { struct msi_desc *entry; bool write_msg; + u16 cmd; if (!dev->msix_enabled) return; @@ -869,6 +870,14 @@ void __pci_restore_msix_state(struct pci_dev *dev) pci_msix_clear_and_set_ctrl(dev, 0, PCI_MSIX_FLAGS_ENABLE | PCI_MSIX_FLAGS_MASKALL); + /* + * The restored device state may not have Memory Space enabled. + * Since the MSI-X Table and PBA are in Memory Space, enable it + * while restoring them. + */ + pci_read_config_word(dev, PCI_COMMAND, &cmd); + pci_write_config_word(dev, PCI_COMMAND, cmd | PCI_COMMAND_MEMORY); + write_msg = arch_restore_msi_irqs(dev); scoped_guard (msi_descs_lock, &dev->dev) { @@ -879,6 +888,7 @@ void __pci_restore_msix_state(struct pci_dev *dev) } } + pci_write_config_word(dev, PCI_COMMAND, cmd); pci_msix_clear_and_set_ctrl(dev, PCI_MSIX_FLAGS_MASKALL, 0); } diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c index edb9bc34c0c5..f3b7f4e410a4 100644 --- a/drivers/pci/pci-sysfs.c +++ b/drivers/pci/pci-sysfs.c @@ -723,7 +723,7 @@ static ssize_t pci_read_config(struct file *filp, struct kobject *kobj, else if (dev->hdr_type == PCI_HEADER_TYPE_CARDBUS) size = 128; - if (off > size) + if (off >= size) return 0; if (off + count > size) { size -= off; @@ -804,7 +804,7 @@ static ssize_t pci_write_config(struct file *filp, struct kobject *kobj, add_taint(TAINT_USER, LOCKDEP_STILL_OK); } - if (off > dev->cfg_size) + if (off >= dev->cfg_size) return 0; if (off + count > dev->cfg_size) { size = dev->cfg_size - off; @@ -906,12 +906,30 @@ static ssize_t pci_read_legacy_io(struct file *filp, struct kobject *kobj, char *buf, loff_t off, size_t count) { struct pci_bus *bus = to_pci_bus(kobj_to_dev(kobj)); + u32 val = 0; + int ret; /* Only support 1, 2 or 4 byte accesses */ if (count != 1 && count != 2 && count != 4) return -EINVAL; - return pci_legacy_read(bus, off, (u32 *)buf, count); + ret = pci_legacy_read(bus, off, &val, count); + if (ret < 0) + return ret; + + switch (count) { + case 1: + buf[0] = *(u8 *)&val; + break; + case 2: + put_unaligned_le16(*(u16 *)&val, buf); + break; + case 4: + put_unaligned_le32(val, buf); + break; + } + + return ret; } /** @@ -931,12 +949,24 @@ static ssize_t pci_write_legacy_io(struct file *filp, struct kobject *kobj, char *buf, loff_t off, size_t count) { struct pci_bus *bus = to_pci_bus(kobj_to_dev(kobj)); + u32 val; - /* Only support 1, 2 or 4 byte accesses */ - if (count != 1 && count != 2 && count != 4) + /* Only support 1, 2 or 4 byte accesses. */ + switch (count) { + case 1: + val = *(u8 *)buf; + break; + case 2: + val = get_unaligned_le16(buf); + break; + case 4: + val = get_unaligned_le32(buf); + break; + default: return -EINVAL; + } - return pci_legacy_write(bus, off, *(u32 *)buf, count); + return pci_legacy_write(bus, off, val, count); } /** diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c index 85f1f0cf62d6..9f90abe3e88e 100644 --- a/drivers/pci/pcie/aer.c +++ b/drivers/pci/pcie/aer.c @@ -427,23 +427,32 @@ void pci_aer_exit(struct pci_dev *dev) #define AER_AGENT_REQUESTER 1 #define AER_AGENT_COMPLETER 2 #define AER_AGENT_TRANSMITTER 3 +#define AER_AGENT_COMPONENT 4 #define AER_AGENT_REQUESTER_MASK(t) ((t == AER_CORRECTABLE) ? \ - 0 : (PCI_ERR_UNC_COMP_TIME|PCI_ERR_UNC_UNSUP)) + 0 : PCI_ERR_UNC_COMP_TIME) #define AER_AGENT_COMPLETER_MASK(t) ((t == AER_CORRECTABLE) ? \ 0 : PCI_ERR_UNC_COMP_ABORT) #define AER_AGENT_TRANSMITTER_MASK(t) ((t == AER_CORRECTABLE) ? \ - (PCI_ERR_COR_REP_ROLL|PCI_ERR_COR_REP_TIMER) : 0) + (PCI_ERR_COR_REP_ROLL|PCI_ERR_COR_REP_TIMER) : \ + (PCI_ERR_UNC_POISON_BLK|PCI_ERR_UNC_ATOMEG| \ + PCI_ERR_UNC_DMWR_BLK|PCI_ERR_UNC_XLAT_BLK| \ + PCI_ERR_UNC_TLPPRE)) +#define AER_AGENT_COMPONENT_MASK(t) ((t == AER_CORRECTABLE) ? \ + (PCI_ERR_COR_INTERNAL|PCI_ERR_COR_LOG_OVER) : \ + (PCI_ERR_UNC_INTN|PCI_ERR_UNC_SURPDN)) #define AER_GET_AGENT(t, e) \ ((e & AER_AGENT_COMPLETER_MASK(t)) ? AER_AGENT_COMPLETER : \ (e & AER_AGENT_REQUESTER_MASK(t)) ? AER_AGENT_REQUESTER : \ (e & AER_AGENT_TRANSMITTER_MASK(t)) ? AER_AGENT_TRANSMITTER : \ + (e & AER_AGENT_COMPONENT_MASK(t)) ? AER_AGENT_COMPONENT : \ AER_AGENT_RECEIVER) #define AER_PHYSICAL_LAYER_ERROR 0 #define AER_DATA_LINK_LAYER_ERROR 1 #define AER_TRANSACTION_LAYER_ERROR 2 +#define AER_GENERAL_ERROR 3 #define AER_PHYSICAL_LAYER_ERROR_MASK(t) ((t == AER_CORRECTABLE) ? \ PCI_ERR_COR_RCVR : 0) @@ -451,11 +460,14 @@ void pci_aer_exit(struct pci_dev *dev) (PCI_ERR_COR_BAD_TLP| \ PCI_ERR_COR_BAD_DLLP| \ PCI_ERR_COR_REP_ROLL| \ - PCI_ERR_COR_REP_TIMER) : PCI_ERR_UNC_DLP) + PCI_ERR_COR_REP_TIMER) : (PCI_ERR_UNC_DLP|PCI_ERR_UNC_SURPDN)) +#define AER_GENERAL_ERROR_MASK(t) ((t == AER_CORRECTABLE) ? \ + (PCI_ERR_COR_INTERNAL|PCI_ERR_COR_LOG_OVER) : PCI_ERR_UNC_INTN) #define AER_GET_LAYER_ERROR(t, e) \ ((e & AER_PHYSICAL_LAYER_ERROR_MASK(t)) ? AER_PHYSICAL_LAYER_ERROR : \ (e & AER_DATA_LINK_LAYER_ERROR_MASK(t)) ? AER_DATA_LINK_LAYER_ERROR : \ + (e & AER_GENERAL_ERROR_MASK(t)) ? AER_GENERAL_ERROR : \ AER_TRANSACTION_LAYER_ERROR) /* @@ -470,7 +482,8 @@ static const char * const aer_error_severity_string[] = { static const char *aer_error_layer[] = { "Physical Layer", "Data Link Layer", - "Transaction Layer" + "Transaction Layer", + "General", }; static const char *aer_correctable_error_string[] = { @@ -547,7 +560,8 @@ static const char *aer_agent_string[] = { "Receiver ID", "Requester ID", "Completer ID", - "Transmitter ID" + "Transmitter ID", + "Component ID", }; #define aer_stats_dev_attr(name, stats_array, strings_array, \ @@ -938,7 +952,8 @@ void pci_print_aer(struct pci_dev *dev, int aer_severity, status = aer->uncor_status; mask = aer->uncor_mask; info.level = KERN_ERR; - tlp_header_valid = tlp_header_logged(status, aer->cap_control); + tlp_header_valid = tlp_header_logged(status & ~mask, + aer->cap_control); } info.status = status; @@ -1427,7 +1442,7 @@ int aer_get_device_error_info(struct aer_err_info *info, int i) pci_read_config_dword(dev, aer + PCI_ERR_CAP, &aercc); info->first_error = PCI_ERR_CAP_FEP(aercc); - if (tlp_header_logged(info->status, aercc)) { + if (tlp_header_logged(info->status & ~info->mask, aercc)) { info->tlp_header_valid = 1; pcie_read_tlp_log(dev, aer + PCI_ERR_HEADER_LOG, aer + PCI_ERR_PREFIX_LOG, diff --git a/drivers/pci/proc.c b/drivers/pci/proc.c index 9348a0fb8084..005e5b455164 100644 --- a/drivers/pci/proc.c +++ b/drivers/pci/proc.c @@ -14,6 +14,8 @@ #include <linux/capability.h> #include <linux/uaccess.h> #include <linux/security.h> +#include <linux/panic.h> +#include <linux/sched.h> #include <asm/byteorder.h> #include "pci.h" @@ -38,13 +40,16 @@ static ssize_t proc_bus_pci_read(struct file *file, char __user *buf, * undefined locations (think of Intel PIIX4 as a typical example). */ - if (capable(CAP_SYS_ADMIN)) + if (file_ns_capable(file, &init_user_ns, CAP_SYS_ADMIN)) size = dev->cfg_size; else if (dev->hdr_type == PCI_HEADER_TYPE_CARDBUS) size = 128; else size = 64; + if (!nbytes) + return 0; + if (pos >= size) return 0; if (nbytes >= size) @@ -121,6 +126,15 @@ static ssize_t proc_bus_pci_write(struct file *file, const char __user *buf, if (ret) return ret; + if (!nbytes) + return 0; + + if (resource_is_exclusive(&dev->driver_exclusive_resource, pos, nbytes)) { + pci_warn_once(dev, "%s: Unexpected write to kernel-exclusive config offset %x", + current->comm, pos); + add_taint(TAINT_USER, LOCKDEP_STILL_OK); + } + if (pos >= size) return 0; if (nbytes >= size) diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index f6001be94955..af58057665d9 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -2506,6 +2506,9 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x10f1, quirk_disable_aspm_l0s); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x10f4, quirk_disable_aspm_l0s); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x1508, quirk_disable_aspm_l0s); +/* Realtek RTS525A generates a Replay Timer Timeout storm when L0s is enabled. */ +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_REALTEK, 0x525a, quirk_disable_aspm_l0s); + static void quirk_disable_aspm_l0s_l1(struct pci_dev *dev) { pcie_aspm_remove_cap(dev, @@ -5331,7 +5334,7 @@ static void pci_quirk_enable_intel_rp_mpc_acs(struct pci_dev *dev) if (!(mpc & INTEL_MPC_REG_IRBNCE)) { pci_info(dev, "Enabling MPC IRBNCE\n"); mpc |= INTEL_MPC_REG_IRBNCE; - pci_write_config_word(dev, INTEL_MPC_REG, mpc); + pci_write_config_dword(dev, INTEL_MPC_REG, mpc); } } @@ -6210,6 +6213,10 @@ DECLARE_PCI_FIXUP_ENABLE(PCI_VENDOR_ID_PERICOM, 0xb404, pci_fixup_pericom_acs_store_forward); DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_PERICOM, 0xb404, pci_fixup_pericom_acs_store_forward); +DECLARE_PCI_FIXUP_ENABLE(PCI_VENDOR_ID_PERICOM, 0x2608, + pci_fixup_pericom_acs_store_forward); +DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_PERICOM, 0x2608, + pci_fixup_pericom_acs_store_forward); static void nvidia_ion_ahci_fixup(struct pci_dev *pdev) { diff --git a/drivers/phy/freescale/phy-fsl-imx8mq-usb.c b/drivers/phy/freescale/phy-fsl-imx8mq-usb.c index 8e7b6e10e1f0..b4f602965c99 100644 --- a/drivers/phy/freescale/phy-fsl-imx8mq-usb.c +++ b/drivers/phy/freescale/phy-fsl-imx8mq-usb.c @@ -166,9 +166,9 @@ static struct typec_switch_dev *tca_blk_get_typec_switch(struct platform_device return sw; } -static void tca_blk_put_typec_switch(struct typec_switch_dev *sw) +static void tca_blk_put_typec_switch(void *data) { - typec_switch_unregister(sw); + typec_switch_unregister(data); } static void tca_blk_orientation_set(struct tca_blk *tca, @@ -241,6 +241,7 @@ static struct tca_blk *imx95_usb_phy_get_tca(struct platform_device *pdev, struct device *dev = &pdev->dev; struct resource *res; struct tca_blk *tca; + int ret; res = platform_get_resource(pdev, IORESOURCE_MEM, 1); if (!res) @@ -259,17 +260,11 @@ static struct tca_blk *imx95_usb_phy_get_tca(struct platform_device *pdev, tca->orientation = TYPEC_ORIENTATION_NORMAL; tca->sw = tca_blk_get_typec_switch(pdev, imx_phy); - return tca; -} - -static void imx95_usb_phy_put_tca(struct imx8mq_usb_phy *imx_phy) -{ - struct tca_blk *tca = imx_phy->tca; - - if (!tca) - return; + ret = devm_add_action_or_reset(&pdev->dev, tca_blk_put_typec_switch, tca->sw); + if (ret) + return ERR_PTR(ret); - tca_blk_put_typec_switch(tca->sw); + return tca; } static u32 phy_tx_vref_tune_from_property(u32 percent) @@ -702,9 +697,7 @@ static int imx8mq_usb_phy_probe(struct platform_device *pdev) static void imx8mq_usb_phy_remove(struct platform_device *pdev) { - struct imx8mq_usb_phy *imx_phy = platform_get_drvdata(pdev); - imx95_usb_phy_put_tca(imx_phy); } static struct platform_driver imx8mq_usb_phy_driver = { diff --git a/drivers/phy/rockchip/phy-rockchip-samsung-dcphy.c b/drivers/phy/rockchip/phy-rockchip-samsung-dcphy.c index 4508a3147272..d4e49db6feed 100644 --- a/drivers/phy/rockchip/phy-rockchip-samsung-dcphy.c +++ b/drivers/phy/rockchip/phy-rockchip-samsung-dcphy.c @@ -1525,7 +1525,7 @@ static const struct regmap_config samsung_mipi_dcphy_regmap_config = { .reg_bits = 32, .val_bits = 32, .reg_stride = 4, - .max_register = 0x10000, + .max_register = 0xfffc, }; static struct phy *samsung_mipi_dcphy_xlate(struct device *dev, diff --git a/drivers/platform/chrome/cros_ec_sensorhub_ring.c b/drivers/platform/chrome/cros_ec_sensorhub_ring.c index 1205219515d6..302d037b90a1 100644 --- a/drivers/platform/chrome/cros_ec_sensorhub_ring.c +++ b/drivers/platform/chrome/cros_ec_sensorhub_ring.c @@ -464,6 +464,21 @@ cros_ec_sensor_ring_process_event(struct cros_ec_sensorhub *sensorhub, fifo_timestamp, *current_timestamp, now); + + /* + * A standalone timestamp event typically has a sensor_num of + * 0xff. Return early here to prevent it from hitting the + * bounds check below and spamming the logs. + */ + return false; + } + + /* Skip event if sensor_num from EC is out of bounds. */ + if (in->sensor_num >= sensorhub->sensor_num) { + dev_warn_ratelimited(sensorhub->dev, + "Invalid sensor number %u from EC\n", + in->sensor_num); + return false; } if (in->flags & MOTIONSENSE_SENSOR_FLAG_ODR) { @@ -491,10 +506,6 @@ cros_ec_sensor_ring_process_event(struct cros_ec_sensorhub *sensorhub, return true; } - if (in->flags & MOTIONSENSE_SENSOR_FLAG_TIMESTAMP) - /* If we just have a timestamp, skip this entry. */ - return false; - /* Regular sample */ out->sensor_id = in->sensor_num; trace_cros_ec_sensorhub_data(in->sensor_num, diff --git a/drivers/platform/x86/amd/pmc/mp1_stb.c b/drivers/platform/x86/amd/pmc/mp1_stb.c index 3b9b9f30faa3..1a06425f596d 100644 --- a/drivers/platform/x86/amd/pmc/mp1_stb.c +++ b/drivers/platform/x86/amd/pmc/mp1_stb.c @@ -289,7 +289,7 @@ int amd_stb_s2d_init(struct amd_pmc_dev *dev) u32 phys_addr_low, phys_addr_hi; u64 stb_phys_addr; u32 size = 0; - int ret; + int ret = 0; if (!enable_stb) return 0; @@ -306,27 +306,42 @@ int amd_stb_s2d_init(struct amd_pmc_dev *dev) /* Spill to DRAM feature uses separate SMU message port */ dev->msg_port = MSG_PORT_S2D; - amd_pmc_send_cmd(dev, S2D_TELEMETRY_SIZE, &size, dev->stb_arg.s2d_msg_id, true); - if (size != S2D_TELEMETRY_BYTES_MAX) - return -EIO; + ret = amd_pmc_send_cmd(dev, S2D_TELEMETRY_SIZE, &size, dev->stb_arg.s2d_msg_id, true); + if (ret) + goto out; + if (size != S2D_TELEMETRY_BYTES_MAX) { + ret = -EIO; + goto out; + } - /* Get DRAM size */ - ret = amd_pmc_send_cmd(dev, S2D_DRAM_SIZE, &dev->dram_size, dev->stb_arg.s2d_msg_id, true); - if (ret || !dev->dram_size) + /* Get DRAM size; fall back to the default if the query fails */ + if (amd_pmc_send_cmd(dev, S2D_DRAM_SIZE, &dev->dram_size, dev->stb_arg.s2d_msg_id, true) || + !dev->dram_size) dev->dram_size = S2D_TELEMETRY_DRAMBYTES_MAX; /* Get STB DRAM address */ - amd_pmc_send_cmd(dev, S2D_PHYS_ADDR_LOW, &phys_addr_low, dev->stb_arg.s2d_msg_id, true); - amd_pmc_send_cmd(dev, S2D_PHYS_ADDR_HIGH, &phys_addr_hi, dev->stb_arg.s2d_msg_id, true); + ret = amd_pmc_send_cmd(dev, S2D_PHYS_ADDR_LOW, &phys_addr_low, + dev->stb_arg.s2d_msg_id, true); + if (ret) + goto out; + ret = amd_pmc_send_cmd(dev, S2D_PHYS_ADDR_HIGH, &phys_addr_hi, + dev->stb_arg.s2d_msg_id, true); + if (ret) + goto out; stb_phys_addr = ((u64)phys_addr_hi << 32 | phys_addr_low); - - /* Clear msg_port for other SMU operation */ - dev->msg_port = MSG_PORT_PMC; + if (!stb_phys_addr) { + dev_err(dev->dev, "S2D phys addr query returned invalid address\n"); + ret = -ENXIO; + goto out; + } dev->stb_virt_addr = devm_ioremap(dev->dev, stb_phys_addr, dev->dram_size); if (!dev->stb_virt_addr) - return -ENOMEM; + ret = -ENOMEM; - return 0; +out: + /* Restore the default message port for subsequent SMU operations */ + dev->msg_port = MSG_PORT_PMC; + return ret; } diff --git a/drivers/platform/x86/amd/pmc/pmc.c b/drivers/platform/x86/amd/pmc/pmc.c index 2cd77a44c7e7..000f876e27eb 100644 --- a/drivers/platform/x86/amd/pmc/pmc.c +++ b/drivers/platform/x86/amd/pmc/pmc.c @@ -870,13 +870,17 @@ static int amd_pmc_probe(struct platform_device *pdev) amd_pmc_dbgfs_register(dev); err = amd_stb_s2d_init(dev); if (err) - goto err_pci_dev_put; + goto err_dbgfs_unregister; if (IS_ENABLED(CONFIG_AMD_MP2_STB)) amd_mp2_stb_init(dev); pm_report_max_hw_sleep(U64_MAX); return 0; +err_dbgfs_unregister: + amd_pmc_dbgfs_unregister(dev); + if (IS_ENABLED(CONFIG_SUSPEND)) + acpi_unregister_lps0_dev(&amd_pmc_s2idle_dev_ops); err_pci_dev_put: pci_dev_put(rdev); return err; diff --git a/drivers/platform/x86/dell/dell-wmi-sysman/biosattr-interface.c b/drivers/platform/x86/dell/dell-wmi-sysman/biosattr-interface.c index c2dd2de6bc20..fea97d6c3bf0 100644 --- a/drivers/platform/x86/dell/dell-wmi-sysman/biosattr-interface.c +++ b/drivers/platform/x86/dell/dell-wmi-sysman/biosattr-interface.c @@ -84,7 +84,6 @@ int set_attribute(const char *a_name, const char *a_value) if (ret < 0) goto out; - print_hex_dump_bytes("set attribute data: ", DUMP_PREFIX_NONE, buffer, buffer_size); ret = call_biosattributes_interface(wmi_priv.bios_attr_wdev, buffer, buffer_size, SETATTRIBUTE_METHOD_ID); diff --git a/drivers/platform/x86/hp/hp-bioscfg/bioscfg.c b/drivers/platform/x86/hp/hp-bioscfg/bioscfg.c index 51e8977d3eb4..274bdecce685 100644 --- a/drivers/platform/x86/hp/hp-bioscfg/bioscfg.c +++ b/drivers/platform/x86/hp/hp-bioscfg/bioscfg.c @@ -85,7 +85,7 @@ int hp_get_string_from_buffer(u8 **buffer, u32 *buffer_size, char *dst, u32 dst_ * bytes. */ conv_dst_size = size; - if (size > dst_size) + if (size >= dst_size) conv_dst_size = dst_size - 1; /* @@ -661,12 +661,17 @@ static int hp_init_bios_package_attribute(enum hp_wmi_data_type attr_type, int ret = 0; /* Take action appropriate to each ACPI TYPE */ - if (obj->package.count < min_elements) { - pr_err("ACPI-package does not have enough elements: %d < %d\n", - obj->package.count, min_elements); + if (obj->package.count < COMMON_ELEM_CNT) { + pr_err("ACPI-package is missing common elements: %d < %d\n", + obj->package.count, COMMON_ELEM_CNT); goto pack_attr_exit; } + if (obj->package.count < min_elements) { + pr_warn("ACPI-package has fewer elements than expected: %d < %d, parsing available elements\n", + obj->package.count, min_elements); + } + elements = obj->package.elements; /* sanity checking */ @@ -731,26 +736,31 @@ static int hp_init_bios_package_attribute(enum hp_wmi_data_type attr_type, switch (attr_type) { case HPWMI_STRING_TYPE: ret = hp_populate_string_package_data(elements, + obj->package.count, instance_id, attr_name_kobj); break; case HPWMI_INTEGER_TYPE: ret = hp_populate_integer_package_data(elements, + obj->package.count, instance_id, attr_name_kobj); break; case HPWMI_ENUMERATION_TYPE: ret = hp_populate_enumeration_package_data(elements, + obj->package.count, instance_id, attr_name_kobj); break; case HPWMI_ORDERED_LIST_TYPE: ret = hp_populate_ordered_list_package_data(elements, + obj->package.count, instance_id, attr_name_kobj); break; case HPWMI_PASSWORD_TYPE: ret = hp_populate_password_package_data(elements, + obj->package.count, instance_id, attr_name_kobj); break; diff --git a/drivers/platform/x86/hp/hp-bioscfg/bioscfg.h b/drivers/platform/x86/hp/hp-bioscfg/bioscfg.h index f1eec0e4ba07..ac57d6eab4c3 100644 --- a/drivers/platform/x86/hp/hp-bioscfg/bioscfg.h +++ b/drivers/platform/x86/hp/hp-bioscfg/bioscfg.h @@ -279,6 +279,9 @@ enum hp_wmi_data_elements { PSWD_ENCODINGS = 13, PSWD_IS_SET = 14, PSWD_ELEM_CNT = 15, + + /* Minimum elements shared by all attribute types (NAME..SECURITY_LEVEL) */ + COMMON_ELEM_CNT = SECURITY_LEVEL + 1, }; #define GET_INSTANCE_ID(type) \ @@ -401,6 +404,7 @@ int hp_populate_string_buffer_data(u8 *buffer_ptr, u32 *buffer_size, int hp_alloc_string_data(void); void hp_exit_string_attributes(void); int hp_populate_string_package_data(union acpi_object *str_obj, + int str_obj_count, int instance_id, struct kobject *attr_name_kobj); @@ -411,6 +415,7 @@ int hp_populate_integer_buffer_data(u8 *buffer_ptr, u32 *buffer_size, int hp_alloc_integer_data(void); void hp_exit_integer_attributes(void); int hp_populate_integer_package_data(union acpi_object *integer_obj, + int integer_obj_count, int instance_id, struct kobject *attr_name_kobj); @@ -421,6 +426,7 @@ int hp_populate_enumeration_buffer_data(u8 *buffer_ptr, u32 *buffer_size, int hp_alloc_enumeration_data(void); void hp_exit_enumeration_attributes(void); int hp_populate_enumeration_package_data(union acpi_object *enum_obj, + int enum_obj_count, int instance_id, struct kobject *attr_name_kobj); @@ -432,6 +438,7 @@ int hp_populate_ordered_list_buffer_data(u8 *buffer_ptr, int hp_alloc_ordered_list_data(void); void hp_exit_ordered_list_attributes(void); int hp_populate_ordered_list_package_data(union acpi_object *order_obj, + int order_obj_count, int instance_id, struct kobject *attr_name_kobj); @@ -440,6 +447,7 @@ int hp_populate_password_buffer_data(u8 *buffer_ptr, u32 *buffer_size, int instance_id, struct kobject *attr_name_kobj); int hp_populate_password_package_data(union acpi_object *password_obj, + int password_obj_count, int instance_id, struct kobject *attr_name_kobj); int hp_alloc_password_data(void); diff --git a/drivers/platform/x86/hp/hp-bioscfg/enum-attributes.c b/drivers/platform/x86/hp/hp-bioscfg/enum-attributes.c index af4d1920d488..446dd18d2cee 100644 --- a/drivers/platform/x86/hp/hp-bioscfg/enum-attributes.c +++ b/drivers/platform/x86/hp/hp-bioscfg/enum-attributes.c @@ -163,10 +163,11 @@ static int hp_populate_enumeration_elements_from_package(union acpi_object *enum /* Check that both expected and read object type match */ if (expected_enum_types[eloc] != enum_obj[elem].type) { - pr_err("Error expected type %d for elem %d, but got type %d instead\n", - expected_enum_types[eloc], elem, enum_obj[elem].type); + pr_warn("Unexpected element type at elem %d: expected %d, got %d, skipping\n", + elem, expected_enum_types[eloc], enum_obj[elem].type); kfree(str_value); - return -EIO; + str_value = NULL; + continue; } /* Assign appropriate element value to corresponding field */ @@ -227,6 +228,8 @@ static int hp_populate_enumeration_elements_from_package(union acpi_object *enum kfree(str_value); str_value = NULL; } + if (size) + elem += size - 1; break; case SECURITY_LEVEL: @@ -280,6 +283,8 @@ static int hp_populate_enumeration_elements_from_package(union acpi_object *enum kfree(str_value); str_value = NULL; } + if (size) + elem += (size < MAX_VALUES_SIZE ? size : MAX_VALUES_SIZE) - 1; break; default: pr_warn("Invalid element: %d found in Enumeration attribute or data may be malformed\n", elem); @@ -300,10 +305,12 @@ exit_enumeration_package: * Populate all properties of an instance under enumeration attribute * * @enum_obj: ACPI object with enumeration data + * @enum_obj_count: Number of elements in @enum_obj * @instance_id: The instance to enumerate * @attr_name_kobj: The parent kernel object */ int hp_populate_enumeration_package_data(union acpi_object *enum_obj, + int enum_obj_count, int instance_id, struct kobject *attr_name_kobj) { @@ -312,7 +319,7 @@ int hp_populate_enumeration_package_data(union acpi_object *enum_obj, enum_data->attr_name_kobj = attr_name_kobj; hp_populate_enumeration_elements_from_package(enum_obj, - enum_obj->package.count, + enum_obj_count, instance_id); hp_update_attribute_permissions(enum_data->common.is_readonly, &enumeration_current_val); diff --git a/drivers/platform/x86/hp/hp-bioscfg/int-attributes.c b/drivers/platform/x86/hp/hp-bioscfg/int-attributes.c index 63b1fda2be4e..5577f571d7c0 100644 --- a/drivers/platform/x86/hp/hp-bioscfg/int-attributes.c +++ b/drivers/platform/x86/hp/hp-bioscfg/int-attributes.c @@ -243,6 +243,8 @@ static int hp_populate_integer_elements_from_package(union acpi_object *integer_ kfree(str_value); str_value = NULL; } + if (size) + elem += size - 1; break; case SECURITY_LEVEL: @@ -275,10 +277,12 @@ exit_integer_package: * Populate all properties of an instance under integer attribute * * @integer_obj: ACPI object with integer data + * @integer_obj_count: Number of elements in @integer_obj * @instance_id: The instance to enumerate * @attr_name_kobj: The parent kernel object */ int hp_populate_integer_package_data(union acpi_object *integer_obj, + int integer_obj_count, int instance_id, struct kobject *attr_name_kobj) { @@ -286,7 +290,7 @@ int hp_populate_integer_package_data(union acpi_object *integer_obj, integer_data->attr_name_kobj = attr_name_kobj; hp_populate_integer_elements_from_package(integer_obj, - integer_obj->package.count, + integer_obj_count, instance_id); hp_update_attribute_permissions(integer_data->common.is_readonly, &integer_current_val); diff --git a/drivers/platform/x86/hp/hp-bioscfg/order-list-attributes.c b/drivers/platform/x86/hp/hp-bioscfg/order-list-attributes.c index 6a31f47ce3f5..db5513d86e00 100644 --- a/drivers/platform/x86/hp/hp-bioscfg/order-list-attributes.c +++ b/drivers/platform/x86/hp/hp-bioscfg/order-list-attributes.c @@ -146,7 +146,7 @@ static int hp_populate_ordered_list_elements_from_package(union acpi_object *ord if (!order_obj) return -EINVAL; - for (elem = 1, eloc = 1; eloc < ORD_ELEM_CNT; elem++, eloc++) { + for (elem = 1, eloc = 1; eloc < ORD_ELEM_CNT && elem < order_obj_count; elem++, eloc++) { switch (order_obj[elem].type) { case ACPI_TYPE_STRING: @@ -233,6 +233,8 @@ static int hp_populate_ordered_list_elements_from_package(union acpi_object *ord kfree(str_value); str_value = NULL; } + if (size) + elem += size - 1; break; case SECURITY_LEVEL: @@ -262,7 +264,9 @@ static int hp_populate_ordered_list_elements_from_package(union acpi_object *ord * Ordered list data is stored in hex and comma separated format * Convert the data and split it to show each element */ - ret = hp_convert_hexstr_to_str(str_value, value_len, &tmpstr, &tmp_len); + ret = hp_convert_hexstr_to_str(order_obj[elem].string.pointer, + order_obj[elem].string.length, + &tmpstr, &tmp_len); if (ret) goto exit_list; @@ -299,10 +303,12 @@ exit_list: * Populate all properties of an instance under ordered_list attribute * * @order_obj: ACPI object with ordered_list data + * @order_obj_count: Number of elements in @order_obj * @instance_id: The instance to enumerate * @attr_name_kobj: The parent kernel object */ -int hp_populate_ordered_list_package_data(union acpi_object *order_obj, int instance_id, +int hp_populate_ordered_list_package_data(union acpi_object *order_obj, int order_obj_count, + int instance_id, struct kobject *attr_name_kobj) { struct ordered_list_data *ordered_list_data = &bioscfg_drv.ordered_list_data[instance_id]; @@ -310,7 +316,7 @@ int hp_populate_ordered_list_package_data(union acpi_object *order_obj, int inst ordered_list_data->attr_name_kobj = attr_name_kobj; hp_populate_ordered_list_elements_from_package(order_obj, - order_obj->package.count, + order_obj_count, instance_id); hp_update_attribute_permissions(ordered_list_data->common.is_readonly, &ordered_list_current_val); diff --git a/drivers/platform/x86/hp/hp-bioscfg/passwdobj-attributes.c b/drivers/platform/x86/hp/hp-bioscfg/passwdobj-attributes.c index ec79d9d50377..3c7fbb1a87e2 100644 --- a/drivers/platform/x86/hp/hp-bioscfg/passwdobj-attributes.c +++ b/drivers/platform/x86/hp/hp-bioscfg/passwdobj-attributes.c @@ -66,7 +66,7 @@ static int validate_password_input(int instance_id, const char *buf) struct password_data *password_data = &bioscfg_drv.password_data[instance_id]; length = strlen(buf); - if (buf[length - 1] == '\n') + if (length > 0 && buf[length - 1] == '\n') length--; if (length > MAX_PASSWD_SIZE) @@ -123,7 +123,7 @@ static ssize_t new_password_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { - return store_password_instance(kobj, buf, count, true); + return store_password_instance(kobj, buf, count, false); } static struct kobj_attribute password_new_password = __ATTR_WO(new_password); @@ -321,6 +321,8 @@ static int hp_populate_password_elements_from_package(union acpi_object *passwor str_value = NULL; } + if (size) + elem += size - 1; break; case SECURITY_LEVEL: password_data->common.security_level = int_value; @@ -362,6 +364,8 @@ static int hp_populate_password_elements_from_package(union acpi_object *passwor str_value = NULL; } + if (size) + elem += size - 1; break; case PSWD_IS_SET: password_data->is_enabled = int_value; @@ -385,10 +389,12 @@ exit_package: * Populate all properties for an instance under password attribute * * @password_obj: ACPI object with password data + * @password_obj_count: Number of elements in @password_obj * @instance_id: The instance to enumerate * @attr_name_kobj: The parent kernel object */ -int hp_populate_password_package_data(union acpi_object *password_obj, int instance_id, +int hp_populate_password_package_data(union acpi_object *password_obj, int password_obj_count, + int instance_id, struct kobject *attr_name_kobj) { struct password_data *password_data = &bioscfg_drv.password_data[instance_id]; @@ -396,7 +402,7 @@ int hp_populate_password_package_data(union acpi_object *password_obj, int insta password_data->attr_name_kobj = attr_name_kobj; hp_populate_password_elements_from_package(password_obj, - password_obj->package.count, + password_obj_count, instance_id); hp_friendly_user_name_update(password_data->common.path, diff --git a/drivers/platform/x86/hp/hp-bioscfg/spmobj-attributes.c b/drivers/platform/x86/hp/hp-bioscfg/spmobj-attributes.c index 2b00a14792e9..4d94e48c1a4c 100644 --- a/drivers/platform/x86/hp/hp-bioscfg/spmobj-attributes.c +++ b/drivers/platform/x86/hp/hp-bioscfg/spmobj-attributes.c @@ -238,7 +238,7 @@ static ssize_t sk_store(struct kobject *kobj, ret = hp_wmi_perform_query(HPWMI_SECUREPLATFORM_SET_SK, HPWMI_SECUREPLATFORM, (void *)bioscfg_drv.spm_data.signing_key, - count, 0); + length, 0); if (!ret) { bioscfg_drv.spm_data.mechanism = SIGNING_KEY; @@ -274,7 +274,7 @@ static ssize_t kek_store(struct kobject *kobj, ret = hp_wmi_perform_query(HPWMI_SECUREPLATFORM_SET_KEK, HPWMI_SECUREPLATFORM, (void *)bioscfg_drv.spm_data.endorsement_key, - count, 0); + length, 0); if (!ret) { bioscfg_drv.spm_data.mechanism = ENDORSEMENT_KEY; diff --git a/drivers/platform/x86/hp/hp-bioscfg/string-attributes.c b/drivers/platform/x86/hp/hp-bioscfg/string-attributes.c index 7b885d25650c..4e3d1fe90310 100644 --- a/drivers/platform/x86/hp/hp-bioscfg/string-attributes.c +++ b/drivers/platform/x86/hp/hp-bioscfg/string-attributes.c @@ -233,6 +233,8 @@ static int hp_populate_string_elements_from_package(union acpi_object *string_ob kfree(str_value); str_value = NULL; } + if (size) + elem += size - 1; break; case SECURITY_LEVEL: @@ -263,10 +265,12 @@ exit_string_package: * Populate all properties of an instance under string attribute * * @string_obj: ACPI object with string data + * @string_obj_count: Number of elements in @string_obj * @instance_id: The instance to enumerate * @attr_name_kobj: The parent kernel object */ int hp_populate_string_package_data(union acpi_object *string_obj, + int string_obj_count, int instance_id, struct kobject *attr_name_kobj) { @@ -275,7 +279,7 @@ int hp_populate_string_package_data(union acpi_object *string_obj, string_data->attr_name_kobj = attr_name_kobj; hp_populate_string_elements_from_package(string_obj, - string_obj->package.count, + string_obj_count, instance_id); hp_update_attribute_permissions(string_data->common.is_readonly, diff --git a/drivers/platform/x86/intel/ishtp_eclite.c b/drivers/platform/x86/intel/ishtp_eclite.c index 93ac8b2dbf38..bca7e217878b 100644 --- a/drivers/platform/x86/intel/ishtp_eclite.c +++ b/drivers/platform/x86/intel/ishtp_eclite.c @@ -600,13 +600,16 @@ static int ecl_ishtp_cl_probe(struct ishtp_cl_device *cl_device) rv = acpi_opregion_init(opr_dev); if (rv) { dev_err(cl_data_to_dev(opr_dev), "ACPI opregion init failed\n"); - goto err_exit; + goto err_put; } /* Reprobe devices depending on ECLite - battery, fan, etc. */ acpi_dev_clear_dependencies(opr_dev->adev); return 0; + +err_put: + acpi_dev_put(opr_dev->adev); err_exit: ishtp_set_connection_state(ecl_ishtp_cl, ISHTP_CL_DISCONNECTING); ishtp_cl_disconnect(ecl_ishtp_cl); diff --git a/drivers/platform/x86/intel/speed_select_if/isst_tpmi_core.c b/drivers/platform/x86/intel/speed_select_if/isst_tpmi_core.c index b11d62c934b3..2e2e168d301c 100644 --- a/drivers/platform/x86/intel/speed_select_if/isst_tpmi_core.c +++ b/drivers/platform/x86/intel/speed_select_if/isst_tpmi_core.c @@ -336,8 +336,11 @@ static int sst_add_perf_profiles(struct auxiliary_device *auxdev, int i; pd_info->perf_levels = devm_kcalloc(dev, levels, sizeof(struct perf_level), GFP_KERNEL); - if (!pd_info->perf_levels) - return 0; + if (!pd_info->perf_levels) { + pd_info->pp_header.allowed_level_mask = 0; + pd_info->pp_header.level_en_mask = 0; + return -ENOMEM; + } pd_info->ratio_unit = pd_info->pp_header.ratio_unit; pd_info->avx_levels = SST_MAX_AVX_LEVELS; @@ -367,7 +370,7 @@ static int sst_add_perf_profiles(struct auxiliary_device *auxdev, static int sst_main(struct auxiliary_device *auxdev, struct tpmi_per_power_domain_info *pd_info) { struct device *dev = &auxdev->dev; - int i, mask, levels; + int i, ret, mask, levels; *((u64 *)&pd_info->sst_header) = readq(pd_info->sst_base); pd_info->sst_header.cp_offset *= 8; @@ -399,8 +402,12 @@ static int sst_main(struct auxiliary_device *auxdev, struct tpmi_per_power_domai levels = i; mask <<= 1; } + + ret = sst_add_perf_profiles(auxdev, pd_info, levels + 1); + if (ret) + return ret; + pd_info->max_level = levels; - sst_add_perf_profiles(auxdev, pd_info, levels + 1); return 0; } @@ -599,6 +606,9 @@ static bool disable_dynamic_sst_features(void) #define SST_CP_PRIORITY_TYPE_START 1 #define SST_CP_PRIORITY_TYPE_WIDTH 1 +#define SST_CP_MAX_ENABLE 1 +#define SST_CP_MAX_PRIORITY_TYPE 1 + static long isst_if_core_power_state(void __user *argp) { struct tpmi_per_power_domain_info *power_domain_info; @@ -618,6 +628,10 @@ static long isst_if_core_power_state(void __user *argp) if (power_domain_info->write_blocked) return -EPERM; + if (core_power.enable > SST_CP_MAX_ENABLE || + core_power.priority_type > SST_CP_MAX_PRIORITY_TYPE) + return -EINVAL; + _write_cp_info("cp_enable", core_power.enable, SST_CP_CONTROL_OFFSET, SST_CP_ENABLE_START, SST_CP_ENABLE_WIDTH, SST_MUL_FACTOR_NONE) _write_cp_info("cp_prio_type", core_power.priority_type, SST_CP_CONTROL_OFFSET, @@ -649,6 +663,11 @@ static long isst_if_core_power_state(void __user *argp) #define SST_CLOS_CONFIG_MAX_START 16 #define SST_CLOS_CONFIG_MAX_WIDTH 8 +#define SST_MAX_CLOS 3 + +#define SST_MAX_FREQ 0xff +#define SST_CLOS_MAX_PRIORITY 0x0f + static long isst_if_clos_param(void __user *argp) { struct tpmi_per_power_domain_info *power_domain_info; @@ -657,6 +676,9 @@ static long isst_if_clos_param(void __user *argp) if (copy_from_user(&clos_param, argp, sizeof(clos_param))) return -EFAULT; + if (clos_param.clos > SST_MAX_CLOS) + return -EINVAL; + power_domain_info = get_instance(clos_param.socket_id, clos_param.power_domain_id); if (!power_domain_info) return -EINVAL; @@ -665,6 +687,15 @@ static long isst_if_clos_param(void __user *argp) if (power_domain_info->write_blocked) return -EPERM; + if (!in_range(clos_param.min_freq_mhz / SST_MUL_FACTOR_FREQ, 0, SST_MAX_FREQ + 1)) + return -EINVAL; + + if (!in_range(clos_param.max_freq_mhz / SST_MUL_FACTOR_FREQ, 0, SST_MAX_FREQ + 1)) + return -EINVAL; + + if (!in_range(clos_param.prop_prio, 0, SST_CLOS_MAX_PRIORITY + 1)) + return -EINVAL; + _write_cp_info("clos.min_freq", clos_param.min_freq_mhz, (SST_CLOS_CONFIG_0_OFFSET + clos_param.clos * SST_REG_SIZE), SST_CLOS_CONFIG_MIN_START, SST_CLOS_CONFIG_MIN_WIDTH, @@ -703,6 +734,8 @@ static long isst_if_clos_param(void __user *argp) #define SST_CLOS_ASSOC_CPUS_PER_REG 16 #define SST_CLOS_ASSOC_BITS_PER_CPU 4 +#define SST_CLOS_ASSOC_MAX_LOGICAL_CPU 63 + static long isst_if_clos_assoc(void __user *argp) { struct isst_if_clos_assoc_cmds assoc_cmds; @@ -729,7 +762,13 @@ static long isst_if_clos_assoc(void __user *argp) if (copy_from_user(&clos_assoc, ptr, sizeof(clos_assoc))) return -EFAULT; - if (clos_assoc.socket_id > topology_max_packages()) + if (clos_assoc.clos > SST_MAX_CLOS) + return -EINVAL; + + if (clos_assoc.socket_id >= topology_max_packages()) + return -EINVAL; + + if (clos_assoc.logical_cpu > SST_CLOS_ASSOC_MAX_LOGICAL_CPU) return -EINVAL; cpu = clos_assoc.logical_cpu; @@ -747,6 +786,8 @@ static long isst_if_clos_assoc(void __user *argp) pkg_id = clos_assoc.socket_id; sst_inst = isst_common.sst_inst[pkg_id]; + if (!sst_inst) + return -EINVAL; punit_id = map_partition_power_domain_id(sst_inst, punit_id, &part); if (punit_id < 0) @@ -844,6 +885,7 @@ static long isst_if_clos_assoc(void __user *argp) #define SST_PP_FEATURE_STATE_START 8 #define SST_PP_FEATURE_STATE_WIDTH 8 +#define SST_PP_FEATURE_STATE_VALID_MASK GENMASK(1, 0) #define SST_BF_FEATURE_SUPPORTED_START 12 #define SST_BF_FEATURE_SUPPORTED_WIDTH 1 @@ -876,7 +918,7 @@ static int isst_if_get_perf_level(void __user *argp) SST_PP_FEATURE_STATE_START, SST_PP_FEATURE_STATE_WIDTH, SST_MUL_FACTOR_NONE) perf_level.enabled = !!(power_domain_info->sst_header.cap_mask & BIT(1)); - level_mask = perf_level.level_mask; + level_mask = perf_level.level_mask & power_domain_info->pp_header.level_en_mask; perf_level.sst_bf_support = 0; for_each_set_bit(level, &level_mask, BITS_PER_BYTE) { /* @@ -994,6 +1036,9 @@ static int isst_if_set_perf_feature(void __user *argp) if (power_domain_info->write_blocked) return -EPERM; + if (perf_feature.feature & ~SST_PP_FEATURE_STATE_VALID_MASK) + return -EINVAL; + _write_pp_info("perf_feature", perf_feature.feature, SST_PP_CONTROL_OFFSET, SST_PP_FEATURE_STATE_START, SST_PP_FEATURE_STATE_WIDTH, SST_MUL_FACTOR_NONE) @@ -1260,6 +1305,12 @@ static int isst_if_get_perf_level_mask(void __user *argp) if (!power_domain_info) return -EINVAL; + if (cpumask.level > power_domain_info->max_level) + return -EINVAL; + + if (!(power_domain_info->pp_header.level_en_mask & BIT(cpumask.level))) + return -EINVAL; + _read_pp_level_info("mask", mask, cpumask.level, SST_PP_INFO_2_OFFSET, SST_PP_RSLVD_CORE_MASK_START, SST_PP_RSLVD_CORE_MASK_WIDTH, SST_MUL_FACTOR_NONE) @@ -1305,6 +1356,9 @@ static int isst_if_get_base_freq_info(void __user *argp) if (base_freq.level > power_domain_info->max_level) return -EINVAL; + if (!(power_domain_info->pp_header.level_en_mask & BIT(base_freq.level))) + return -EINVAL; + _read_bf_level_info("p1_high", base_freq.high_base_freq_mhz, base_freq.level, SST_BF_INFO_0_OFFSET, SST_BF_P1_HIGH_START, SST_BF_P1_HIGH_WIDTH, SST_MUL_FACTOR_FREQ) @@ -1341,6 +1395,12 @@ static int isst_if_get_base_freq_mask(void __user *argp) if (!power_domain_info) return -EINVAL; + if (cpumask.level > power_domain_info->max_level) + return -EINVAL; + + if (!(power_domain_info->pp_header.level_en_mask & BIT(cpumask.level))) + return -EINVAL; + _read_bf_level_info("BF-cpumask", mask, cpumask.level, SST_BF_INFO_1_OFFSET, P1_HI_CORE_MASK_START, P1_HI_CORE_MASK_WIDTH, SST_MUL_FACTOR_NONE) @@ -1369,6 +1429,8 @@ static int isst_if_get_tpmi_instance_count(void __user *argp) return -EINVAL; sst_inst = isst_common.sst_inst[tpmi_inst.socket_id]; + if (!sst_inst) + return -EINVAL; tpmi_inst.count = isst_instance_count(sst_inst); @@ -1436,6 +1498,9 @@ static int isst_if_get_turbo_freq_info(void __user *argp) if (turbo_freq.level > power_domain_info->max_level) return -EINVAL; + if (!(power_domain_info->pp_header.level_en_mask & BIT(turbo_freq.level))) + return -EINVAL; + turbo_freq.max_buckets = TRL_MAX_BUCKETS; turbo_freq.max_trl_levels = TRL_MAX_LEVELS; turbo_freq.max_clip_freqs = SST_TF_MAX_LP_CLIP_RATIOS; diff --git a/drivers/platform/x86/lenovo/think-lmi.c b/drivers/platform/x86/lenovo/think-lmi.c index 540b472b1bf3..a56cca9d6598 100644 --- a/drivers/platform/x86/lenovo/think-lmi.c +++ b/drivers/platform/x86/lenovo/think-lmi.c @@ -438,14 +438,13 @@ static ssize_t current_password_store(struct kobject *kobj, struct tlmi_pwd_setting *setting = to_tlmi_pwd_setting(kobj); size_t pwdlen; - pwdlen = strlen(buf); + /* Strip newline; setting password won't work if one is present. */ + pwdlen = strchrnul(buf, '\n') - buf; /* pwdlen == 0 is allowed to clear the password */ if (pwdlen && ((pwdlen < setting->minlen) || (pwdlen > setting->maxlen))) return -EINVAL; - strscpy(setting->password, buf, setting->maxlen); - /* Strip out CR if one is present, setting password won't work if it is present */ - strreplace(setting->password, '\n', '\0'); + strscpy(setting->password, buf, pwdlen + 1); return count; } @@ -741,6 +740,8 @@ static ssize_t certificate_thumbprint_show(struct kobject *kobj, struct kobj_att return -EOPNOTSUPP; for (i = 0; i < ARRAY_SIZE(thumbtypes); i++) { + ssize_t ret; + if (tlmi_priv.pwdcfg.core.password_mode >= TLMI_PWDCFG_MODE_MULTICERT) { /* Format: 'SVC | SMC, Thumbtype' */ wmistr = kasprintf(GFP_KERNEL, "%s,%s", @@ -752,8 +753,12 @@ static ssize_t certificate_thumbprint_show(struct kobject *kobj, struct kobj_att } if (!wmistr) return -ENOMEM; - count += cert_thumbprint(buf, wmistr, count); + + ret = cert_thumbprint(buf, wmistr, count); kfree(wmistr); + if (ret < 0) + return ret; + count = ret; } return count; @@ -1452,6 +1457,10 @@ static void tlmi_release_attr(void) /* Free up any saved signatures */ kfree(tlmi_priv.pwd_admin->signature); kfree(tlmi_priv.pwd_admin->save_signature); + if (tlmi_priv.pwd_system) { + kfree(tlmi_priv.pwd_system->signature); + kfree(tlmi_priv.pwd_system->save_signature); + } /* Authentication structures */ list_for_each_entry_safe(pos, n, &tlmi_priv.authentication_kset->list, entry) diff --git a/drivers/platform/x86/lenovo/wmi-helpers.c b/drivers/platform/x86/lenovo/wmi-helpers.c index f6fef6296251..910e024a5c82 100644 --- a/drivers/platform/x86/lenovo/wmi-helpers.c +++ b/drivers/platform/x86/lenovo/wmi-helpers.c @@ -45,7 +45,6 @@ int lwmi_dev_evaluate_int(struct wmi_device *wdev, u8 instance, u32 method_id, unsigned char *buf, size_t size, u32 *retval) { struct acpi_buffer output = { ACPI_ALLOCATE_BUFFER, NULL }; - union acpi_object *ret_obj __free(kfree) = NULL; struct acpi_buffer input = { size, buf }; acpi_status status; @@ -54,8 +53,9 @@ int lwmi_dev_evaluate_int(struct wmi_device *wdev, u8 instance, u32 method_id, if (ACPI_FAILURE(status)) return -EIO; + union acpi_object *ret_obj __free(kfree) = output.pointer; + if (retval) { - ret_obj = output.pointer; if (!ret_obj) return -ENODATA; diff --git a/drivers/platform/x86/lenovo/ymc.c b/drivers/platform/x86/lenovo/ymc.c index 470d53e3c9d2..c71d92f896ec 100644 --- a/drivers/platform/x86/lenovo/ymc.c +++ b/drivers/platform/x86/lenovo/ymc.c @@ -8,6 +8,8 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/acpi.h> +#include <linux/bitfield.h> +#include <linux/bits.h> #include <linux/dmi.h> #include <linux/input.h> #include <linux/input/sparse-keymap.h> @@ -20,6 +22,8 @@ #define LENOVO_YMC_QUERY_INSTANCE 0 #define LENOVO_YMC_QUERY_METHOD 0x01 +#define LENOVO_YMC_STATE_MASK GENMASK(7, 0) + static bool force; module_param(force, bool, 0444); MODULE_PARM_DESC(force, "Force loading on boards without a convertible DMI chassis-type"); @@ -85,7 +89,9 @@ static void lenovo_ymc_notify(struct wmi_device *wdev, union acpi_object *data) "WMI event data is not an integer\n"); goto free_obj; } - code = obj->integer.value; + + /* strip upper bits (e.g. 0x50000) on newer devices */ + code = FIELD_GET(LENOVO_YMC_STATE_MASK, obj->integer.value); if (!sparse_keymap_report_event(priv->input_dev, code, 1, true)) dev_warn(&wdev->dev, "Unknown key %d pressed\n", code); diff --git a/drivers/power/supply/bq24257_charger.c b/drivers/power/supply/bq24257_charger.c index 766eecb35694..097b51271ba9 100644 --- a/drivers/power/supply/bq24257_charger.c +++ b/drivers/power/supply/bq24257_charger.c @@ -18,6 +18,7 @@ #include <linux/gpio/consumer.h> #include <linux/interrupt.h> #include <linux/delay.h> +#include <linux/devm-helpers.h> #include <linux/acpi.h> #include <linux/of.h> @@ -1003,10 +1004,6 @@ static int bq24257_probe(struct i2c_client *client) if (bq->info->chip == BQ24250) bq->iilimit_autoset_enable = false; - if (bq->iilimit_autoset_enable) - INIT_DELAYED_WORK(&bq->iilimit_setup_work, - bq24257_iilimit_setup_work); - /* * The BQ24250 doesn't have a dedicated Power Good (PG) pin so let's * not probe for it and instead use a SW-based approach to determine @@ -1047,6 +1044,14 @@ static int bq24257_probe(struct i2c_client *client) return ret; } + if (bq->iilimit_autoset_enable) { + ret = devm_delayed_work_autocancel(dev, + &bq->iilimit_setup_work, + bq24257_iilimit_setup_work); + if (ret) + return ret; + } + ret = devm_request_threaded_irq(dev, client->irq, NULL, bq24257_irq_handler_thread, IRQF_TRIGGER_FALLING | @@ -1064,9 +1069,6 @@ static void bq24257_remove(struct i2c_client *client) { struct bq24257_device *bq = i2c_get_clientdata(client); - if (bq->iilimit_autoset_enable) - cancel_delayed_work_sync(&bq->iilimit_setup_work); - bq24257_field_write(bq, F_RESET, 1); /* reset to defaults */ } diff --git a/drivers/power/supply/bq256xx_charger.c b/drivers/power/supply/bq256xx_charger.c index d3de4f8b80db..8cdd45ddd05b 100644 --- a/drivers/power/supply/bq256xx_charger.c +++ b/drivers/power/supply/bq256xx_charger.c @@ -897,6 +897,8 @@ static void bq256xx_charger_reset(void *data) if (!IS_ERR_OR_NULL(bq->usb3_phy)) usb_unregister_notifier(bq->usb3_phy, &bq->usb_nb); + + cancel_work_sync(&bq->usb_work); } static int bq256xx_set_charger_property(struct power_supply *psy, @@ -1722,24 +1724,12 @@ static int bq256xx_probe(struct i2c_client *client) return ret; } - ret = devm_add_action_or_reset(dev, bq256xx_charger_reset, bq); - if (ret) - return ret; + INIT_WORK(&bq->usb_work, bq256xx_usb_work); + bq->usb_nb.notifier_call = bq256xx_usb_notifier; /* OTG reporting */ bq->usb2_phy = devm_usb_get_phy(dev, USB_PHY_TYPE_USB2); - if (!IS_ERR_OR_NULL(bq->usb2_phy)) { - INIT_WORK(&bq->usb_work, bq256xx_usb_work); - bq->usb_nb.notifier_call = bq256xx_usb_notifier; - usb_register_notifier(bq->usb2_phy, &bq->usb_nb); - } - bq->usb3_phy = devm_usb_get_phy(dev, USB_PHY_TYPE_USB3); - if (!IS_ERR_OR_NULL(bq->usb3_phy)) { - INIT_WORK(&bq->usb_work, bq256xx_usb_work); - bq->usb_nb.notifier_call = bq256xx_usb_notifier; - usb_register_notifier(bq->usb3_phy, &bq->usb_nb); - } ret = bq256xx_power_supply_init(bq, &psy_cfg, dev); if (ret) { @@ -1747,6 +1737,17 @@ static int bq256xx_probe(struct i2c_client *client) return ret; } + /* Register after the power supplies so devm runs it first. */ + ret = devm_add_action_or_reset(dev, bq256xx_charger_reset, bq); + if (ret) + return ret; + + if (!IS_ERR_OR_NULL(bq->usb2_phy)) + usb_register_notifier(bq->usb2_phy, &bq->usb_nb); + + if (!IS_ERR_OR_NULL(bq->usb3_phy)) + usb_register_notifier(bq->usb3_phy, &bq->usb_nb); + if (client->irq) { ret = devm_request_threaded_irq(dev, client->irq, NULL, bq256xx_irq_handler_thread, diff --git a/drivers/power/supply/bq25890_charger.c b/drivers/power/supply/bq25890_charger.c index f246ec871d5c..305318b21e5c 100644 --- a/drivers/power/supply/bq25890_charger.c +++ b/drivers/power/supply/bq25890_charger.c @@ -1389,6 +1389,14 @@ static int bq25890_fw_read_u32_props(struct bq25890_device *bq) return 0; } +static void bq25890_release_secondary_chrg(void *data) +{ + struct bq25890_device *bq = data; + + power_supply_put(bq->secondary_chrg); + bq->secondary_chrg = NULL; +} + static int bq25890_fw_probe(struct bq25890_device *bq) { int ret; @@ -1401,6 +1409,10 @@ static int bq25890_fw_probe(struct bq25890_device *bq) bq->secondary_chrg = power_supply_get_by_name(str); if (!bq->secondary_chrg) return -EPROBE_DEFER; + + ret = devm_add_action_or_reset(bq->dev, bq25890_release_secondary_chrg, bq); + if (ret) + return ret; } /* Optional, left at 0 if property is not present */ diff --git a/drivers/power/supply/charger-manager.c b/drivers/power/supply/charger-manager.c index c3644018b6bb..70af1a4ce110 100644 --- a/drivers/power/supply/charger-manager.c +++ b/drivers/power/supply/charger-manager.c @@ -1018,6 +1018,29 @@ static int charger_extcon_init(struct charger_manager *cm, return 0; } +static int charger_manager_get_regulators(struct charger_manager *cm) +{ + struct charger_desc *desc = cm->desc; + struct charger_regulator *charger; + int i, ret; + + for (i = 0; i < desc->num_charger_regulators; i++) { + charger = &desc->charger_regulators[i]; + charger->consumer = regulator_get(cm->dev, + charger->regulator_name); + if (IS_ERR(charger->consumer)) { + dev_err(cm->dev, "Cannot find charger(%s)\n", + charger->regulator_name); + ret = PTR_ERR(charger->consumer); + while (i-- > 0) + regulator_put(desc->charger_regulators[i].consumer); + return ret; + } + charger->cm = cm; + } + return 0; +} + /** * charger_manager_register_extcon - Register extcon device to receive state * of charger cable. @@ -1040,15 +1063,6 @@ static int charger_manager_register_extcon(struct charger_manager *cm) for (i = 0; i < desc->num_charger_regulators; i++) { charger = &desc->charger_regulators[i]; - charger->consumer = regulator_get(cm->dev, - charger->regulator_name); - if (IS_ERR(charger->consumer)) { - dev_err(cm->dev, "Cannot find charger(%s)\n", - charger->regulator_name); - return PTR_ERR(charger->consumer); - } - charger->cm = cm; - for (j = 0; j < charger->num_cables; j++) { struct charger_cable *cable = &charger->cables[j]; @@ -1584,13 +1598,23 @@ static int charger_manager_probe(struct platform_device *pdev) } psy_cfg.attr_grp = desc->sysfs_groups; + /* + * Acquire charger regulators before exposing the sysfs entries, so + * userspace cannot reach externally_control before the regulators + * (and charger->cm) are available. Mirrors the order in remove(). + */ + ret = charger_manager_get_regulators(cm); + if (ret < 0) + return ret; + cm->charger_psy = power_supply_register(&pdev->dev, &cm->charger_psy_desc, &psy_cfg); if (IS_ERR(cm->charger_psy)) { dev_err(&pdev->dev, "Cannot register charger-manager with name \"%s\"\n", cm->charger_psy_desc.name); - return PTR_ERR(cm->charger_psy); + ret = PTR_ERR(cm->charger_psy); + goto err_regulator; } /* Register extcon device for charger cable */ @@ -1624,11 +1648,11 @@ static int charger_manager_probe(struct platform_device *pdev) return 0; err_reg_extcon: + power_supply_unregister(cm->charger_psy); +err_regulator: for (i = 0; i < desc->num_charger_regulators; i++) regulator_put(desc->charger_regulators[i].consumer); - power_supply_unregister(cm->charger_psy); - return ret; } @@ -1646,12 +1670,12 @@ static void charger_manager_remove(struct platform_device *pdev) cancel_work_sync(&setup_polling); cancel_delayed_work_sync(&cm_monitor_work); - for (i = 0 ; i < desc->num_charger_regulators ; i++) - regulator_put(desc->charger_regulators[i].consumer); + try_charger_enable(cm, false); power_supply_unregister(cm->charger_psy); - try_charger_enable(cm, false); + for (i = 0 ; i < desc->num_charger_regulators ; i++) + regulator_put(desc->charger_regulators[i].consumer); } static const struct platform_device_id charger_manager_id[] = { diff --git a/drivers/power/supply/cros_usbpd-charger.c b/drivers/power/supply/cros_usbpd-charger.c index 47d3f58aa15c..93f61da8d596 100644 --- a/drivers/power/supply/cros_usbpd-charger.c +++ b/drivers/power/supply/cros_usbpd-charger.c @@ -125,6 +125,11 @@ static int cros_usbpd_charger_get_num_ports(struct charger_data *charger) if (ret < 0) return ret; + if (resp.port_count > EC_USB_PD_MAX_PORTS) { + dev_warn(charger->dev, "Charge port count out of bounds\n"); + return EC_USB_PD_MAX_PORTS; + } + return resp.port_count; } @@ -138,6 +143,11 @@ static int cros_usbpd_charger_get_usbpd_num_ports(struct charger_data *charger) if (ret < 0) return ret; + if (resp.num_ports > EC_USB_PD_MAX_PORTS) { + dev_warn(charger->dev, "USB PD port count out of bounds\n"); + return EC_USB_PD_MAX_PORTS; + } + return resp.num_ports; } @@ -589,10 +599,13 @@ static int cros_usbpd_charger_probe(struct platform_device *pd) /* * Sanity checks on the number of ports: - * there should be at most 1 dedicated port + * there should be at most 1 dedicated port, and the count must + * not exceed the maximum number of supported ports + * (EC_USB_PD_MAX_PORTS). */ if (charger->num_charger_ports < charger->num_usbpd_ports || - charger->num_charger_ports > (charger->num_usbpd_ports + 1)) { + charger->num_charger_ports > (charger->num_usbpd_ports + 1) || + charger->num_charger_ports > EC_USB_PD_MAX_PORTS) { dev_err(dev, "Unexpected number of charge port count\n"); ret = -EPROTO; goto fail_nowarn; diff --git a/drivers/power/supply/lp8727_charger.c b/drivers/power/supply/lp8727_charger.c index 4186fcd37512..e81bb393340c 100644 --- a/drivers/power/supply/lp8727_charger.c +++ b/drivers/power/supply/lp8727_charger.c @@ -280,10 +280,10 @@ static int lp8727_setup_irq(struct lp8727_chg *pchg) static void lp8727_release_irq(struct lp8727_chg *pchg) { - cancel_delayed_work_sync(&pchg->work); - if (pchg->irq) free_irq(pchg->irq, pchg); + + cancel_delayed_work_sync(&pchg->work); } static enum power_supply_property lp8727_charger_prop[] = { diff --git a/drivers/power/supply/lp8788-charger.c b/drivers/power/supply/lp8788-charger.c index f0a680c155c4..1bc2c150fb91 100644 --- a/drivers/power/supply/lp8788-charger.c +++ b/drivers/power/supply/lp8788-charger.c @@ -710,8 +710,8 @@ static void lp8788_charger_remove(struct platform_device *pdev) { struct lp8788_charger *pchg = platform_get_drvdata(pdev); - flush_work(&pchg->charger_work); lp8788_irq_unregister(pdev, pchg); + cancel_work_sync(&pchg->charger_work); } static struct platform_driver lp8788_charger_driver = { diff --git a/drivers/power/supply/max17040_battery.c b/drivers/power/supply/max17040_battery.c index f4748adec092..0d95ff5cc892 100644 --- a/drivers/power/supply/max17040_battery.c +++ b/drivers/power/supply/max17040_battery.c @@ -192,8 +192,11 @@ static int max17040_raw_vcell_to_uvolts(struct max17040_chip *chip, u16 vcell) static int max17040_get_vcell(struct max17040_chip *chip) { u32 vcell; + int ret; - regmap_read(chip->regmap, MAX17040_VCELL, &vcell); + ret = regmap_read(chip->regmap, MAX17040_VCELL, &vcell); + if (ret) + return ret; return max17040_raw_vcell_to_uvolts(chip, vcell); } @@ -201,8 +204,11 @@ static int max17040_get_vcell(struct max17040_chip *chip) static int max17040_get_soc(struct max17040_chip *chip) { u32 soc; + int ret; - regmap_read(chip->regmap, MAX17040_SOC, &soc); + ret = regmap_read(chip->regmap, MAX17040_SOC, &soc); + if (ret) + return ret; return soc >> (chip->quirk_double_soc ? 9 : 8); } @@ -261,7 +267,11 @@ static int max17040_get_of_data(struct max17040_chip *chip) static void max17040_check_changes(struct max17040_chip *chip) { - chip->soc = max17040_get_soc(chip); + int soc; + + soc = max17040_get_soc(chip); + if (soc >= 0) + chip->soc = soc; } static void max17040_queue_work(struct max17040_chip *chip) @@ -396,10 +406,16 @@ static int max17040_get_property(struct power_supply *psy, val->intval = max17040_get_online(chip); break; case POWER_SUPPLY_PROP_VOLTAGE_NOW: - val->intval = max17040_get_vcell(chip); + ret = max17040_get_vcell(chip); + if (ret < 0) + return ret; + val->intval = ret; break; case POWER_SUPPLY_PROP_CAPACITY: - val->intval = max17040_get_soc(chip); + ret = max17040_get_soc(chip); + if (ret < 0) + return ret; + val->intval = ret; break; case POWER_SUPPLY_PROP_CAPACITY_ALERT_MIN: val->intval = chip->low_soc_alert; @@ -458,16 +474,12 @@ static const struct power_supply_desc max17040_battery_desc = { static int max17040_probe(struct i2c_client *client) { const struct i2c_device_id *id = i2c_client_get_device_id(client); - struct i2c_adapter *adapter = client->adapter; struct power_supply_config psy_cfg = {}; struct max17040_chip *chip; enum chip_id chip_id; bool enable_irq = false; int ret; - if (!i2c_check_functionality(adapter, I2C_FUNC_SMBUS_BYTE)) - return -EIO; - chip = devm_kzalloc(&client->dev, sizeof(*chip), GFP_KERNEL); if (!chip) return -ENOMEM; @@ -568,7 +580,7 @@ static int max17040_suspend(struct device *dev) // disable soc alert to prevent wakeup max17040_set_soc_alert(chip, 0); else - cancel_delayed_work(&chip->work); + cancel_delayed_work_sync(&chip->work); if (client->irq && device_may_wakeup(dev)) enable_irq_wake(client->irq); diff --git a/drivers/power/supply/qcom_battmgr.c b/drivers/power/supply/qcom_battmgr.c index ff77dba29a3e..7454ec0e9963 100644 --- a/drivers/power/supply/qcom_battmgr.c +++ b/drivers/power/supply/qcom_battmgr.c @@ -5,6 +5,7 @@ * Copyright (c) Qualcomm Technologies, Inc. and/or its subsidiaries. */ #include <linux/auxiliary_bus.h> +#include <linux/devm-helpers.h> #include <linux/module.h> #include <linux/mutex.h> #include <linux/nvmem-consumer.h> @@ -1235,7 +1236,7 @@ static void qcom_battmgr_sc8280xp_strcpy(char *dest, const char *src) memcpy(dest, src + 1, len); dest[len] = '\0'; } else { - memcpy(dest, src, BATTMGR_STRING_LEN); + strscpy(dest, src, BATTMGR_STRING_LEN); } } @@ -1650,7 +1651,6 @@ static int qcom_battmgr_probe(struct auxiliary_device *adev, psy_cfg_supply.supplied_to = qcom_battmgr_battery; psy_cfg_supply.num_supplicants = 1; - INIT_WORK(&battmgr->enable_work, qcom_battmgr_enable_worker); mutex_init(&battmgr->lock); init_completion(&battmgr->ack); @@ -1713,6 +1713,11 @@ static int qcom_battmgr_probe(struct auxiliary_device *adev, "failed to register wireless charing power supply\n"); } + ret = devm_work_autocancel(dev, &battmgr->enable_work, + qcom_battmgr_enable_worker); + if (ret) + return ret; + battmgr->client = devm_pmic_glink_client_alloc(dev, PMIC_GLINK_OWNER_BATTMGR, qcom_battmgr_callback, qcom_battmgr_pdr_notify, diff --git a/drivers/power/supply/rt9455_charger.c b/drivers/power/supply/rt9455_charger.c index 5130d2395e88..710d510f9809 100644 --- a/drivers/power/supply/rt9455_charger.c +++ b/drivers/power/supply/rt9455_charger.c @@ -1582,6 +1582,19 @@ static const struct regmap_config rt9455_regmap_config = { .cache_type = REGCACHE_MAPLE, }; +static void rt9455_cancel_all_delayed_works(void *data) +{ + struct rt9455_info *info = data; + + /* + * Both pwr_rdy_work and batt_presence_work can queue + * max_charging_time_work, so cancel them first. + */ + cancel_delayed_work_sync(&info->pwr_rdy_work); + cancel_delayed_work_sync(&info->batt_presence_work); + cancel_delayed_work_sync(&info->max_charging_time_work); +} + static int rt9455_probe(struct i2c_client *client) { struct i2c_adapter *adapter = client->adapter; @@ -1672,6 +1685,10 @@ static int rt9455_probe(struct i2c_client *client) goto put_usb_notifier; } + ret = devm_add_action_or_reset(dev, rt9455_cancel_all_delayed_works, info); + if (ret) + goto put_usb_notifier; + ret = devm_request_threaded_irq(dev, client->irq, NULL, rt9455_irq_handler_thread, IRQF_TRIGGER_LOW | IRQF_ONESHOT, @@ -1712,10 +1729,6 @@ static void rt9455_remove(struct i2c_client *client) if (info->nb.notifier_call) usb_unregister_notifier(info->usb_phy, &info->nb); #endif - - cancel_delayed_work_sync(&info->pwr_rdy_work); - cancel_delayed_work_sync(&info->max_charging_time_work); - cancel_delayed_work_sync(&info->batt_presence_work); } static const struct i2c_device_id rt9455_i2c_id_table[] = { diff --git a/drivers/power/supply/twl4030_charger.c b/drivers/power/supply/twl4030_charger.c index 04216b2bfb6c..e5b4d72720de 100644 --- a/drivers/power/supply/twl4030_charger.c +++ b/drivers/power/supply/twl4030_charger.c @@ -14,6 +14,7 @@ #include <linux/err.h> #include <linux/of.h> #include <linux/platform_device.h> +#include <linux/devm-helpers.h> #include <linux/interrupt.h> #include <linux/mfd/twl.h> #include <linux/power_supply.h> @@ -1002,8 +1003,15 @@ static int twl4030_bci_probe(struct platform_device *pdev) platform_set_drvdata(pdev, bci); - INIT_WORK(&bci->work, twl4030_bci_usb_work); - INIT_DELAYED_WORK(&bci->current_worker, twl4030_current_worker); + ret = devm_delayed_work_autocancel(&pdev->dev, &bci->current_worker, + twl4030_current_worker); + if (ret) + return ret; + + ret = devm_work_autocancel(&pdev->dev, &bci->work, + twl4030_bci_usb_work); + if (ret) + return ret; bci->channel_vac = devm_iio_channel_get(&pdev->dev, "vac"); if (IS_ERR(bci->channel_vac)) { diff --git a/drivers/power/supply/ucs1002_power.c b/drivers/power/supply/ucs1002_power.c index fe94435340de..da49de82c082 100644 --- a/drivers/power/supply/ucs1002_power.c +++ b/drivers/power/supply/ucs1002_power.c @@ -12,6 +12,7 @@ #include <linux/kernel.h> #include <linux/kthread.h> #include <linux/device.h> +#include <linux/devm-helpers.h> #include <linux/module.h> #include <linux/of.h> #include <linux/of_irq.h> @@ -641,7 +642,10 @@ static int ucs1002_probe(struct i2c_client *client) } info->health = POWER_SUPPLY_HEALTH_GOOD; - INIT_DELAYED_WORK(&info->health_poll, ucs1002_health_poll); + ret = devm_delayed_work_autocancel(dev, &info->health_poll, + ucs1002_health_poll); + if (ret) + return ret; if (irq_a_det > 0) { ret = devm_request_threaded_irq(dev, irq_a_det, NULL, diff --git a/drivers/ptp/ptp_vmclock.c b/drivers/ptp/ptp_vmclock.c index 83114695dbb5..8edc2880c609 100644 --- a/drivers/ptp/ptp_vmclock.c +++ b/drivers/ptp/ptp_vmclock.c @@ -371,6 +371,12 @@ static int vmclock_miscdev_mmap(struct file *fp, struct vm_area_struct *vma) */ vm_flags_clear(vma, VM_MAYWRITE); + /* + * Restrict the read-only mapping so it cannot be upgraded to + * writable later with mprotect(). + */ + vm_flags_clear(vma, VM_MAYWRITE); + if (vma->vm_end - vma->vm_start != PAGE_SIZE || vma->vm_pgoff) return -EINVAL; diff --git a/drivers/rapidio/devices/rio_mport_cdev.c b/drivers/rapidio/devices/rio_mport_cdev.c index 995cfeca972b..c3fa45b26c1b 100644 --- a/drivers/rapidio/devices/rio_mport_cdev.c +++ b/drivers/rapidio/devices/rio_mport_cdev.c @@ -564,9 +564,13 @@ static void dma_req_free(struct kref *ref) } if (req->map) { - mutex_lock(&req->map->md->buf_mutex); - kref_put(&req->map->ref, mport_release_mapping); - mutex_unlock(&req->map->md->buf_mutex); + struct rio_mport_mapping *map = req->map; + struct mport_dev *md = map->md; + + mutex_lock(&md->buf_mutex); + req->map = NULL; + kref_put(&map->ref, mport_release_mapping); + mutex_unlock(&md->buf_mutex); } kref_put(&priv->dma_ref, mport_release_dma); diff --git a/drivers/regulator/as3722-regulator.c b/drivers/regulator/as3722-regulator.c index da378bfdba40..85e2aaa1a06b 100644 --- a/drivers/regulator/as3722-regulator.c +++ b/drivers/regulator/as3722-regulator.c @@ -600,7 +600,6 @@ static int as3722_get_regulator_dt_data(struct platform_device *pdev, ret = of_regulator_match(&pdev->dev, np, as3722_regulator_matches, ARRAY_SIZE(as3722_regulator_matches)); - of_node_put(np); if (ret < 0) { dev_err(&pdev->dev, "Parsing of regulator node failed: %d\n", ret); diff --git a/drivers/regulator/max8998.c b/drivers/regulator/max8998.c index 254a77887f66..52ab2208675b 100644 --- a/drivers/regulator/max8998.c +++ b/drivers/regulator/max8998.c @@ -582,7 +582,6 @@ static int max8998_pmic_dt_parse_pdata(struct max8998_dev *iodev, } pdata->num_regulators = rdata - pdata->regulators; - of_node_put(reg_np); of_node_put(regulators_np); pdata->buck_voltage_lock = of_property_read_bool(pmic_np, "max8998,pmic-buck-voltage-lock"); diff --git a/drivers/regulator/qcom-refgen-regulator.c b/drivers/regulator/qcom-refgen-regulator.c index 299ac3c8c3bc..6a3795469927 100644 --- a/drivers/regulator/qcom-refgen-regulator.c +++ b/drivers/regulator/qcom-refgen-regulator.c @@ -66,7 +66,7 @@ static const struct regulator_desc sdm845_refgen_desc = { .enable_time = 5, .name = "refgen", .owner = THIS_MODULE, - .type = REGULATOR_VOLTAGE, + .type = REGULATOR_CURRENT, .ops = &(const struct regulator_ops) { .enable = qcom_sdm845_refgen_enable, .disable = qcom_sdm845_refgen_disable, @@ -82,7 +82,7 @@ static const struct regulator_desc sm8250_refgen_desc = { .enable_time = 5, .name = "refgen", .owner = THIS_MODULE, - .type = REGULATOR_VOLTAGE, + .type = REGULATOR_CURRENT, .ops = &(const struct regulator_ops) { .enable = regulator_enable_regmap, .disable = regulator_disable_regmap, diff --git a/drivers/remoteproc/mtk_scp.c b/drivers/remoteproc/mtk_scp.c index eb8908ea3bab..b3613802730c 100644 --- a/drivers/remoteproc/mtk_scp.c +++ b/drivers/remoteproc/mtk_scp.c @@ -35,6 +35,7 @@ struct mtk_scp *scp_get(struct platform_device *pdev) struct device *dev = &pdev->dev; struct device_node *scp_node; struct platform_device *scp_pdev; + struct mtk_scp *scp; scp_node = of_parse_phandle(dev->of_node, "mediatek,scp", 0); if (!scp_node) { @@ -50,7 +51,13 @@ struct mtk_scp *scp_get(struct platform_device *pdev) return NULL; } - return platform_get_drvdata(scp_pdev); + scp = platform_get_drvdata(scp_pdev); + if (!scp) { + put_device(&scp_pdev->dev); + return NULL; + } + + return scp; } EXPORT_SYMBOL_GPL(scp_get); diff --git a/drivers/rpmsg/qcom_glink_smem.c b/drivers/rpmsg/qcom_glink_smem.c index 7a982c60a8dd..17c885f4ed50 100644 --- a/drivers/rpmsg/qcom_glink_smem.c +++ b/drivers/rpmsg/qcom_glink_smem.c @@ -103,6 +103,13 @@ static void glink_smem_rx_peek(struct qcom_glink_pipe *np, if (tail >= pipe->native.length) tail -= pipe->native.length; + /* + * Order the availability (head) read in glink_smem_rx_avail() + * against the FIFO payload read below, so APPS never consumes + * stale data the remote has not yet published. + */ + rmb(); + len = min_t(size_t, count, pipe->native.length - tail); if (len) memcpy_fromio(data, pipe->fifo + tail, len); diff --git a/drivers/s390/block/dasd.c b/drivers/s390/block/dasd.c index 7765e40f7cea..e7845c8ccc9f 100644 --- a/drivers/s390/block/dasd.c +++ b/drivers/s390/block/dasd.c @@ -1746,8 +1746,10 @@ void dasd_int_handler(struct ccw_device *cdev, unsigned long intparm, return; } if (rq_data_dir(req) == READ) { - device->discipline->ese_read(cqr, irb); - cqr->status = DASD_CQR_SUCCESS; + if (device->discipline->ese_read(cqr, irb)) + cqr->status = DASD_CQR_ERROR; + else + cqr->status = DASD_CQR_SUCCESS; cqr->stopclk = now; dasd_device_clear_timer(device); dasd_schedule_device_bh(device); diff --git a/drivers/s390/block/dasd_eckd.c b/drivers/s390/block/dasd_eckd.c index 9dfa14eb09d2..8947fbd2797a 100644 --- a/drivers/s390/block/dasd_eckd.c +++ b/drivers/s390/block/dasd_eckd.c @@ -1493,6 +1493,8 @@ static void dasd_eckd_reset_path(struct dasd_device *device, __u8 pm) struct dasd_eckd_private *private = device->private; unsigned long flags; + if (!private) + return; if (!private->fcx_max_data) private->fcx_max_data = get_fcx_max_data(device); spin_lock_irqsave(get_ccwdev_lock(device->cdev), flags); @@ -1648,6 +1650,9 @@ static int dasd_eckd_is_ese(struct dasd_device *device) { struct dasd_eckd_private *private = device->private; + if (!private) + return 0; + return private->vsq.vol_info.ese; } @@ -1655,6 +1660,9 @@ static int dasd_eckd_ext_pool_id(struct dasd_device *device) { struct dasd_eckd_private *private = device->private; + if (!private) + return 0; + return private->vsq.extent_pool_id; } @@ -1668,6 +1676,9 @@ static int dasd_eckd_space_configured(struct dasd_device *device) struct dasd_eckd_private *private = device->private; int rc; + if (!private) + return 0; + rc = dasd_eckd_read_vol_info(device); return rc ? : private->vsq.space_configured; @@ -1682,6 +1693,9 @@ static int dasd_eckd_space_allocated(struct dasd_device *device) struct dasd_eckd_private *private = device->private; int rc; + if (!private) + return 0; + rc = dasd_eckd_read_vol_info(device); return rc ? : private->vsq.space_allocated; @@ -1691,6 +1705,9 @@ static int dasd_eckd_logical_capacity(struct dasd_device *device) { struct dasd_eckd_private *private = device->private; + if (!private) + return 0; + return private->vsq.logical_capacity; } @@ -1833,7 +1850,11 @@ static int dasd_eckd_read_ext_pool_info(struct dasd_device *device) static int dasd_eckd_ext_size(struct dasd_device *device) { struct dasd_eckd_private *private = device->private; - struct dasd_ext_pool_sum eps = private->eps; + struct dasd_ext_pool_sum eps; + + if (!private) + return 0; + eps = private->eps; if (!eps.flags.extent_size_valid) return 0; @@ -1849,6 +1870,9 @@ static int dasd_eckd_ext_pool_warn_thrshld(struct dasd_device *device) { struct dasd_eckd_private *private = device->private; + if (!private) + return 0; + return private->eps.warn_thrshld; } @@ -1856,6 +1880,9 @@ static int dasd_eckd_ext_pool_cap_at_warnlevel(struct dasd_device *device) { struct dasd_eckd_private *private = device->private; + if (!private) + return 0; + return private->eps.flags.capacity_at_warnlevel; } @@ -1866,6 +1893,9 @@ static int dasd_eckd_ext_pool_oos(struct dasd_device *device) { struct dasd_eckd_private *private = device->private; + if (!private) + return 0; + return private->eps.flags.pool_oos; } @@ -5949,8 +5979,11 @@ static int dasd_eckd_query_host_access(struct dasd_device *device, struct ccw1 *ccw; int rc; + if (!private) + return -ENODEV; + /* not available for HYPER PAV alias devices */ - if (!device->block && private->lcu->pav == HYPER_PAV) + if (!device->block && private->lcu && private->lcu->pav == HYPER_PAV) return -EOPNOTSUPP; /* may not be supported by the storage server */ @@ -6815,6 +6848,9 @@ static int dasd_eckd_hpf_enabled(struct dasd_device *device) { struct dasd_eckd_private *private = device->private; + if (!private) + return 0; + return private->fcx_max_data ? 1 : 0; } diff --git a/drivers/s390/block/dasd_erp.c b/drivers/s390/block/dasd_erp.c index 89d7516b9ec8..468f0b2cc342 100644 --- a/drivers/s390/block/dasd_erp.c +++ b/drivers/s390/block/dasd_erp.c @@ -123,6 +123,7 @@ struct dasd_ccw_req *dasd_default_erp_postaction(struct dasd_ccw_req *cqr) int success; unsigned long startclk, stopclk; struct dasd_device *startdev; + unsigned int proc_bytes; BUG_ON(cqr->refers == NULL || cqr->function == NULL); @@ -130,6 +131,7 @@ struct dasd_ccw_req *dasd_default_erp_postaction(struct dasd_ccw_req *cqr) startclk = cqr->startclk; stopclk = cqr->stopclk; startdev = cqr->startdev; + proc_bytes = cqr->proc_bytes; /* free all ERPs - but NOT the original cqr */ while (cqr->refers != NULL) { @@ -147,6 +149,7 @@ struct dasd_ccw_req *dasd_default_erp_postaction(struct dasd_ccw_req *cqr) cqr->startclk = startclk; cqr->stopclk = stopclk; cqr->startdev = startdev; + cqr->proc_bytes = proc_bytes; if (success) cqr->status = DASD_CQR_DONE; else { diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index 3f7ba6d3987f..31e1d74143df 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -1184,8 +1184,10 @@ blk_status_t scsi_alloc_sgtables(struct scsi_cmnd *cmd) if (blk_rq_bytes(rq) & rq->q->limits.dma_pad_mask) { unsigned int pad_len = (rq->q->limits.dma_pad_mask & ~blk_rq_bytes(rq)) + 1; + unsigned int data_len = last_sg->length; last_sg->length += pad_len; + sg_zero_buffer(last_sg, 1, pad_len, data_len); cmd->extra_len += pad_len; } diff --git a/drivers/staging/greybus/hid.c b/drivers/staging/greybus/hid.c index afa78c96ede8..96154d8c5f38 100644 --- a/drivers/staging/greybus/hid.c +++ b/drivers/staging/greybus/hid.c @@ -256,7 +256,7 @@ static int __gb_hid_output_raw_report(struct hid_device *hid, __u8 *buf, if (report_id && ret >= 0) ret++; /* add report_id to the number of transferred bytes */ - return 0; + return ret; } static int gb_hid_raw_request(struct hid_device *hid, unsigned char reportnum, diff --git a/drivers/staging/media/ipu7/ipu7-isys.c b/drivers/staging/media/ipu7/ipu7-isys.c index cb2f49f3e0fa..bf262c01a2b8 100644 --- a/drivers/staging/media/ipu7/ipu7-isys.c +++ b/drivers/staging/media/ipu7/ipu7-isys.c @@ -773,6 +773,7 @@ static int isys_probe(struct auxiliary_device *auxdev, return 0; out_cleanup: + isys_notifier_cleanup(isys); isys_unregister_devices(isys); out_cleanup_fw: ipu7_fw_isys_release(isys); diff --git a/drivers/staging/media/tegra-video/vi.c b/drivers/staging/media/tegra-video/vi.c index 46f169346782..f5d7ba4cdd6e 100644 --- a/drivers/staging/media/tegra-video/vi.c +++ b/drivers/staging/media/tegra-video/vi.c @@ -1260,6 +1260,7 @@ static int tegra_vi_channels_alloc(struct tegra_vi *vi) struct device_node *parent; struct v4l2_fwnode_endpoint v4l2_ep = { .bus_type = 0 }; unsigned int lanes; + int err; int ret = 0; ports = of_get_child_by_name(node, "ports"); @@ -1270,8 +1271,8 @@ static int tegra_vi_channels_alloc(struct tegra_vi *vi) if (!of_node_name_eq(port, "port")) continue; - ret = of_property_read_u32(port, "reg", &port_num); - if (ret < 0) + err = of_property_read_u32(port, "reg", &port_num); + if (err < 0) continue; if (port_num > vi->soc->vi_max_channels) { @@ -1292,10 +1293,10 @@ static int tegra_vi_channels_alloc(struct tegra_vi *vi) ep = of_graph_get_endpoint_by_regs(parent, 0, 0); of_node_put(parent); - ret = v4l2_fwnode_endpoint_parse(of_fwnode_handle(ep), + err = v4l2_fwnode_endpoint_parse(of_fwnode_handle(ep), &v4l2_ep); of_node_put(ep); - if (ret) + if (err) continue; lanes = v4l2_ep.bus.mipi_csi2.num_data_lanes; diff --git a/drivers/staging/media/tegra-video/vip.c b/drivers/staging/media/tegra-video/vip.c index 5ec717f3afd5..eb0381c10d2b 100644 --- a/drivers/staging/media/tegra-video/vip.c +++ b/drivers/staging/media/tegra-video/vip.c @@ -126,7 +126,7 @@ static int tegra_vip_channel_of_parse(struct tegra_vip *vip) if (!ep) { err = -EINVAL; dev_err_probe(dev, err, "%pOF: error getting endpoint node\n", np); - goto err_node_put; + return err; } fwh = of_fwnode_handle(ep); @@ -134,14 +134,14 @@ static int tegra_vip_channel_of_parse(struct tegra_vip *vip) of_node_put(ep); if (err) { dev_err_probe(dev, err, "%pOF: failed to parse v4l2 endpoint\n", np); - goto err_node_put; + return err; } num_pads = of_graph_get_endpoint_count(np); if (num_pads != TEGRA_VIP_PADS_NUM) { err = -EINVAL; dev_err_probe(dev, err, "%pOF: need 2 pads, got %d\n", np, num_pads); - goto err_node_put; + return err; } vip->chan.of_node = of_node_get(np); @@ -149,10 +149,6 @@ static int tegra_vip_channel_of_parse(struct tegra_vip *vip) vip->chan.pads[TEGRA_VIP_PAD_SOURCE].flags = MEDIA_PAD_FL_SOURCE; return 0; - -err_node_put: - of_node_put(np); - return err; } static int tegra_vip_channel_init(struct tegra_vip *vip) diff --git a/drivers/tty/serial/imx.c b/drivers/tty/serial/imx.c index 90e2ea1e8afe..1f2b4c12eead 100644 --- a/drivers/tty/serial/imx.c +++ b/drivers/tty/serial/imx.c @@ -22,6 +22,7 @@ #include <linux/clk.h> #include <linux/delay.h> #include <linux/ktime.h> +#include <linux/mutex.h> #include <linux/pinctrl/consumer.h> #include <linux/rational.h> #include <linux/slab.h> @@ -2079,6 +2080,9 @@ static const struct uart_ops imx_uart_pops = { static struct imx_port *imx_uart_ports[UART_NR]; +/* Held across uart_add/remove_one_port(); console callbacks must not take it. */ +static DEFINE_MUTEX(imx_uart_ports_lock); + #if IS_ENABLED(CONFIG_SERIAL_IMX_CONSOLE) static void imx_uart_console_putchar(struct uart_port *port, unsigned char ch) { @@ -2631,11 +2635,19 @@ static int imx_uart_probe(struct platform_device *pdev) } } - imx_uart_ports[sport->port.line] = sport; - platform_set_drvdata(pdev, sport); - ret = uart_add_one_port(&imx_uart_uart_driver, &sport->port); + scoped_guard(mutex, &imx_uart_ports_lock) { + if (imx_uart_ports[sport->port.line]) { + ret = -EBUSY; + } else { + imx_uart_ports[sport->port.line] = sport; + ret = uart_add_one_port(&imx_uart_uart_driver, + &sport->port); + if (ret) + imx_uart_ports[sport->port.line] = NULL; + } + } err_clk: clk_disable_unprepare(sport->clk_ipg); @@ -2647,7 +2659,9 @@ static void imx_uart_remove(struct platform_device *pdev) { struct imx_port *sport = platform_get_drvdata(pdev); + guard(mutex)(&imx_uart_ports_lock); uart_remove_one_port(&imx_uart_uart_driver, &sport->port); + imx_uart_ports[sport->port.line] = NULL; } static void imx_uart_restore_context(struct imx_port *sport) diff --git a/drivers/usb/dwc2/gadget.c b/drivers/usb/dwc2/gadget.c index a6c2b8de3908..8282de6df011 100644 --- a/drivers/usb/dwc2/gadget.c +++ b/drivers/usb/dwc2/gadget.c @@ -4680,6 +4680,7 @@ static int dwc2_hsotg_pullup(struct usb_gadget *gadget, int is_on) { struct dwc2_hsotg *hsotg = to_hsotg(gadget); unsigned long flags; + int ret = 0; dev_dbg(hsotg->dev, "%s: is_on: %d op_state: %d\n", __func__, is_on, hsotg->op_state); @@ -4691,6 +4692,13 @@ static int dwc2_hsotg_pullup(struct usb_gadget *gadget, int is_on) } spin_lock_irqsave(&hsotg->lock, flags); + if (hsotg->in_ppd) { + ret = dwc2_exit_partial_power_down(hsotg, 0, true); + if (ret) { + dev_err(hsotg->dev, "exit partial_power_down failed\n"); + goto exit; + } + } if (is_on) { hsotg->enabled = 1; dwc2_hsotg_core_init_disconnected(hsotg, false); @@ -4704,9 +4712,10 @@ static int dwc2_hsotg_pullup(struct usb_gadget *gadget, int is_on) } hsotg->gadget.speed = USB_SPEED_UNKNOWN; +exit: spin_unlock_irqrestore(&hsotg->lock, flags); - return 0; + return ret; } static int dwc2_hsotg_vbus_session(struct usb_gadget *gadget, int is_active) diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index ea8487d4bbb3..a2c735276909 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -3497,6 +3497,7 @@ static void dwc3_gadget_free_endpoints(struct dwc3 *dwc) } dwc3_debugfs_remove_endpoint_dir(dep); + cancel_delayed_work_sync(&dep->nostream_work); kfree(dep); } } diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c index 311606097718..15e8ca3a616b 100644 --- a/drivers/usb/gadget/function/f_fs.c +++ b/drivers/usb/gadget/function/f_fs.c @@ -549,6 +549,7 @@ static ssize_t ffs_ep0_read(struct file *file, char __user *buf, if (ffs_setup_state_clear_cancelled(ffs) == FFS_SETUP_CANCELLED) return -EIDRM; +retry: /* Acquire mutex */ ret = ffs_mutex_lock(&ffs->mutex, file->f_flags & O_NONBLOCK); if (ret < 0) @@ -583,10 +584,15 @@ static ssize_t ffs_ep0_read(struct file *file, char __user *buf, break; } - if (wait_event_interruptible_exclusive_locked_irq(ffs->ev.waitq, - ffs->ev.count)) { - ret = -EINTR; - break; + if (!ffs->ev.count) { + spin_unlock_irq(&ffs->ev.waitq.lock); + mutex_unlock(&ffs->mutex); + + if (wait_event_interruptible_exclusive(ffs->ev.waitq, + ffs->ev.count)) + return -EINTR; + + goto retry; } /* unlocks spinlock */ diff --git a/drivers/usb/gadget/function/f_midi2.c b/drivers/usb/gadget/function/f_midi2.c index de16b02d857e..0199d95ff803 100644 --- a/drivers/usb/gadget/function/f_midi2.c +++ b/drivers/usb/gadget/function/f_midi2.c @@ -2474,6 +2474,7 @@ static void f_midi2_ep_opts_release(struct config_item *item) { struct f_midi2_ep_opts *opts = to_f_midi2_ep_opts(item); + configfs_remove_default_groups(&opts->group); kfree(opts->info.ep_name); kfree(opts->info.product_id); kfree(opts); @@ -2640,6 +2641,7 @@ static void f_midi2_free_inst(struct usb_function_instance *f) opts = container_of(f, struct f_midi2_opts, func_inst); + configfs_remove_default_groups(&opts->func_inst.group); kfree(opts->info.iface_name); kfree(opts); } diff --git a/drivers/usb/gadget/function/f_tcm.c b/drivers/usb/gadget/function/f_tcm.c index 09d72bb4f855..02c5d9cfda45 100644 --- a/drivers/usb/gadget/function/f_tcm.c +++ b/drivers/usb/gadget/function/f_tcm.c @@ -1674,19 +1674,25 @@ static struct se_portal_group *usbg_make_tpg(struct se_wwn *wwn, opts = container_of(tpg_instances[i].func_inst, struct f_tcm_opts, func_inst); - mutex_lock(&opts->dep_lock); - if (!opts->ready) - goto unlock_dep; + if (!READ_ONCE(opts->ready)) + goto unlock_inst; if (opts->has_dep) { if (!try_module_get(opts->dependent)) - goto unlock_dep; + goto unlock_inst; } else { + /* + * configfs_depend_item_unlocked() may acquire the configfs + * root inode lock when the target belongs to a different + * subsystem. Calling it under dep_lock would create a + * circular dependency: + * dep_lock -> configfs inode lock -> su_mutex -> dep_lock + */ ret = configfs_depend_item_unlocked( wwn->wwn_group.cg_subsys, &opts->func_inst.group.cg_item); if (ret) - goto unlock_dep; + goto unlock_inst; } tpg = kzalloc(sizeof(struct usbg_tpg), GFP_KERNEL); @@ -1713,7 +1719,6 @@ static struct se_portal_group *usbg_make_tpg(struct se_wwn *wwn, tpg_instances[i].tpg = tpg; tpg->fi = tpg_instances[i].func_inst; - mutex_unlock(&opts->dep_lock); mutex_unlock(&tpg_instances_lock); return &tpg->se_tpg; @@ -1726,8 +1731,6 @@ unref_dep: module_put(opts->dependent); else configfs_undepend_item_unlocked(&opts->func_inst.group.cg_item); -unlock_dep: - mutex_unlock(&opts->dep_lock); unlock_inst: mutex_unlock(&tpg_instances_lock); @@ -2664,9 +2667,7 @@ static int tcm_set_name(struct usb_function_instance *f, const char *name) pr_debug("tcm: Activating %s\n", name); - mutex_lock(&opts->dep_lock); - opts->ready = true; - mutex_unlock(&opts->dep_lock); + WRITE_ONCE(opts->ready, true); return 0; } diff --git a/drivers/usb/gadget/function/f_uvc.c b/drivers/usb/gadget/function/f_uvc.c index 72601e15563c..ab77e6bf001a 100644 --- a/drivers/usb/gadget/function/f_uvc.c +++ b/drivers/usb/gadget/function/f_uvc.c @@ -889,9 +889,12 @@ error_unlock: v4l2_error: v4l2_device_unregister(&uvc->v4l2_dev); error: - if (uvc->control_req) + if (uvc->control_req) { usb_ep_free_request(cdev->gadget->ep0, uvc->control_req); + uvc->control_req = NULL; + } kfree(uvc->control_buf); + uvc->control_buf = NULL; usb_free_all_descriptors(f); return ret; @@ -1075,7 +1078,9 @@ static void uvc_function_unbind(struct usb_configuration *c, uvc->vdev_release_done = NULL; usb_ep_free_request(cdev->gadget->ep0, uvc->control_req); + uvc->control_req = NULL; kfree(uvc->control_buf); + uvc->control_buf = NULL; usb_free_all_descriptors(f); } diff --git a/drivers/usb/gadget/function/u_audio.c b/drivers/usb/gadget/function/u_audio.c index ca8dbec65f73..24c673dcbbd7 100644 --- a/drivers/usb/gadget/function/u_audio.c +++ b/drivers/usb/gadget/function/u_audio.c @@ -1177,6 +1177,20 @@ static struct snd_kcontrol_new u_audio_controls[] = { }, }; +static void u_audio_card_free(struct snd_card *card) +{ + struct snd_uac_chip *uac = card->private_data; + + if (!uac) + return; + + kfree(uac->p_prm.reqs); + kfree(uac->c_prm.reqs); + kfree(uac->p_prm.rbuf); + kfree(uac->c_prm.rbuf); + kfree(uac); +} + int g_audio_setup(struct g_audio *g_audio, const char *pcm_name, const char *card_name) { @@ -1258,6 +1272,8 @@ int g_audio_setup(struct g_audio *g_audio, const char *pcm_name, goto fail; uac->card = card; + card->private_data = uac; + card->private_free = u_audio_card_free; /* * Create first PCM device @@ -1426,6 +1442,8 @@ int g_audio_setup(struct g_audio *g_audio, const char *pcm_name, snd_fail: snd_card_free(card); + return err; + fail: kfree(uac->p_prm.reqs); kfree(uac->c_prm.reqs); @@ -1451,12 +1469,6 @@ void g_audio_cleanup(struct g_audio *g_audio) card = uac->card; if (card) snd_card_free_when_closed(card); - - kfree(uac->p_prm.reqs); - kfree(uac->c_prm.reqs); - kfree(uac->p_prm.rbuf); - kfree(uac->c_prm.rbuf); - kfree(uac); } EXPORT_SYMBOL_GPL(g_audio_cleanup); diff --git a/drivers/usb/gadget/function/uvc_video.c b/drivers/usb/gadget/function/uvc_video.c index f24746e72877..dd9105a8ef78 100644 --- a/drivers/usb/gadget/function/uvc_video.c +++ b/drivers/usb/gadget/function/uvc_video.c @@ -821,7 +821,7 @@ int uvcg_video_init(struct uvc_video *video, struct uvc_device *uvc) /* Allocate a kthread for asynchronous hw submit handler. */ video->kworker = kthread_run_worker(0, "UVCG"); if (IS_ERR(video->kworker)) { - uvcg_err(&video->uvc->func, "failed to create UVCG kworker\n"); + uvcg_err(&uvc->func, "failed to create UVCG kworker\n"); return PTR_ERR(video->kworker); } diff --git a/drivers/usb/gadget/udc/at91_udc.c b/drivers/usb/gadget/udc/at91_udc.c index 42b94d858e37..005152798000 100644 --- a/drivers/usb/gadget/udc/at91_udc.c +++ b/drivers/usb/gadget/udc/at91_udc.c @@ -1794,6 +1794,19 @@ static void at91udc_of_init(struct at91_udc *udc, struct device_node *np) udc->caps = match->data; } +/* + * The work handler re-arms this timer, so shut the timer down before + * draining the work; otherwise it restarts the polling cycle. + */ +static void at91_udc_shutdown_vbus_timer(struct at91_udc *udc) +{ + if (!(udc->board.vbus_pin && udc->board.vbus_polled)) + return; + + timer_shutdown_sync(&udc->vbus_timer); + cancel_work_sync(&udc->vbus_timer_work); +} + static int at91udc_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; @@ -1907,7 +1920,7 @@ static int at91udc_probe(struct platform_device *pdev) } retval = usb_add_gadget_udc(dev, &udc->gadget); if (retval) - goto err_unprepare_iclk; + goto err_shutdown_vbus; dev_set_drvdata(dev, udc); device_init_wakeup(dev, 1); create_debug_file(udc); @@ -1915,6 +1928,8 @@ static int at91udc_probe(struct platform_device *pdev) INFO("%s version %s\n", driver_name, DRIVER_VERSION); return 0; +err_shutdown_vbus: + at91_udc_shutdown_vbus_timer(udc); err_unprepare_iclk: clk_unprepare(udc->iclk); err_unprepare_fclk: @@ -1933,6 +1948,9 @@ static void at91udc_remove(struct platform_device *pdev) DBG("remove\n"); usb_del_gadget_udc(&udc->gadget); + + at91_udc_shutdown_vbus_timer(udc); + if (udc->driver) { dev_err(&pdev->dev, "Driver still in use but removing anyhow\n"); diff --git a/drivers/usb/gadget/udc/snps_udc_plat.c b/drivers/usb/gadget/udc/snps_udc_plat.c index db842a6de643..0ee3ed185d9c 100644 --- a/drivers/usb/gadget/udc/snps_udc_plat.c +++ b/drivers/usb/gadget/udc/snps_udc_plat.c @@ -159,10 +159,9 @@ static int udc_plat_probe(struct platform_device *pdev) if (of_property_present(dev->of_node, "extcon")) { udc->edev = extcon_get_edev_by_phandle(dev, 0); if (IS_ERR(udc->edev)) { - if (PTR_ERR(udc->edev) == -EPROBE_DEFER) - return -EPROBE_DEFER; - dev_err(dev, "Invalid or missing extcon\n"); ret = PTR_ERR(udc->edev); + if (ret != -EPROBE_DEFER) + dev_err(dev, "Invalid or missing extcon\n"); goto exit_phy; } diff --git a/drivers/usb/phy/phy-fsl-usb.c b/drivers/usb/phy/phy-fsl-usb.c index e266a47c4d48..1c405e5dc32c 100644 --- a/drivers/usb/phy/phy-fsl-usb.c +++ b/drivers/usb/phy/phy-fsl-usb.c @@ -46,7 +46,7 @@ static const char driver_name[] = "fsl-usb2-otg"; -const pm_message_t otg_suspend_state = { +static const pm_message_t otg_suspend_state = { .event = 1, }; @@ -57,11 +57,11 @@ static struct fsl_otg *fsl_otg_dev; static int srp_wait_done; /* FSM timers */ -struct fsl_otg_timer *a_wait_vrise_tmr, *a_wait_bcon_tmr, *a_aidl_bdis_tmr, +static struct fsl_otg_timer *a_wait_vrise_tmr, *a_wait_bcon_tmr, *a_aidl_bdis_tmr, *b_ase0_brst_tmr, *b_se0_srp_tmr; /* Driver specific timers */ -struct fsl_otg_timer *b_data_pulse_tmr, *b_vbus_pulse_tmr, *b_srp_fail_tmr, +static struct fsl_otg_timer *b_data_pulse_tmr, *b_vbus_pulse_tmr, *b_srp_fail_tmr, *b_srp_wait_tmr, *a_wait_enum_tmr; static struct list_head active_timers; @@ -102,7 +102,7 @@ static void (*_fsl_writel)(u32 v, unsigned __iomem *p); #define fsl_writel(val, addr) writel(val, addr) #endif /* CONFIG_PPC32 */ -int write_ulpi(u8 addr, u8 data) +static int write_ulpi(u8 addr, u8 data) { u32 temp; @@ -115,7 +115,7 @@ int write_ulpi(u8 addr, u8 data) /* Operations that will be called from OTG Finite State Machine */ /* Charge vbus for vbus pulsing in SRP */ -void fsl_otg_chrg_vbus(struct otg_fsm *fsm, int on) +static void fsl_otg_chrg_vbus(struct otg_fsm *fsm, int on) { u32 tmp; @@ -133,7 +133,7 @@ void fsl_otg_chrg_vbus(struct otg_fsm *fsm, int on) } /* Discharge vbus through a resistor to ground */ -void fsl_otg_dischrg_vbus(int on) +static void fsl_otg_dischrg_vbus(int on) { u32 tmp; @@ -151,7 +151,7 @@ void fsl_otg_dischrg_vbus(int on) } /* A-device driver vbus, controlled through PP bit in PORTSC */ -void fsl_otg_drv_vbus(struct otg_fsm *fsm, int on) +static void fsl_otg_drv_vbus(struct otg_fsm *fsm, int on) { u32 tmp; @@ -169,7 +169,7 @@ void fsl_otg_drv_vbus(struct otg_fsm *fsm, int on) * Pull-up D+, signalling connect by periperal. Also used in * data-line pulsing in SRP */ -void fsl_otg_loc_conn(struct otg_fsm *fsm, int on) +static void fsl_otg_loc_conn(struct otg_fsm *fsm, int on) { u32 tmp; @@ -188,7 +188,7 @@ void fsl_otg_loc_conn(struct otg_fsm *fsm, int on) * port. In host mode, controller will automatically send SOF. * Suspend will block the data on the port. */ -void fsl_otg_loc_sof(struct otg_fsm *fsm, int on) +static void fsl_otg_loc_sof(struct otg_fsm *fsm, int on) { u32 tmp; @@ -203,7 +203,7 @@ void fsl_otg_loc_sof(struct otg_fsm *fsm, int on) } /* Start SRP pulsing by data-line pulsing, followed with v-bus pulsing. */ -void fsl_otg_start_pulse(struct otg_fsm *fsm) +static void fsl_otg_start_pulse(struct otg_fsm *fsm) { u32 tmp; @@ -219,7 +219,7 @@ void fsl_otg_start_pulse(struct otg_fsm *fsm) fsl_otg_add_timer(fsm, b_data_pulse_tmr); } -void b_data_pulse_end(unsigned long foo) +static void b_data_pulse_end(unsigned long foo) { #ifdef HA_DATA_PULSE #else @@ -230,7 +230,7 @@ void b_data_pulse_end(unsigned long foo) fsl_otg_pulse_vbus(); } -void fsl_otg_pulse_vbus(void) +static void fsl_otg_pulse_vbus(void) { srp_wait_done = 0; fsl_otg_chrg_vbus(&fsl_otg_dev->fsm, 1); @@ -238,7 +238,7 @@ void fsl_otg_pulse_vbus(void) fsl_otg_add_timer(&fsl_otg_dev->fsm, b_vbus_pulse_tmr); } -void b_vbus_pulse_end(unsigned long foo) +static void b_vbus_pulse_end(unsigned long foo) { fsl_otg_chrg_vbus(&fsl_otg_dev->fsm, 0); @@ -251,7 +251,7 @@ void b_vbus_pulse_end(unsigned long foo) fsl_otg_add_timer(&fsl_otg_dev->fsm, b_srp_wait_tmr); } -void b_srp_end(unsigned long foo) +static void b_srp_end(unsigned long foo) { fsl_otg_dischrg_vbus(0); srp_wait_done = 1; @@ -266,7 +266,7 @@ void b_srp_end(unsigned long foo) * a_host will start by SRP. It needs to set b_hnp_enable before * actually suspending to start HNP */ -void a_wait_enum(unsigned long foo) +static void a_wait_enum(unsigned long foo) { VDBG("a_wait_enum timeout\n"); if (!fsl_otg_dev->phy.otg->host->b_hnp_enable) @@ -276,13 +276,13 @@ void a_wait_enum(unsigned long foo) } /* The timeout callback function to set time out bit */ -void set_tmout(unsigned long indicator) +static void set_tmout(unsigned long indicator) { *(int *)indicator = 1; } /* Initialize timers */ -int fsl_otg_init_timers(struct otg_fsm *fsm) +static int fsl_otg_init_timers(struct otg_fsm *fsm) { /* FSM used timers */ a_wait_vrise_tmr = otg_timer_initializer(&set_tmout, TA_WAIT_VRISE, @@ -339,7 +339,7 @@ int fsl_otg_init_timers(struct otg_fsm *fsm) } /* Uninitialize timers */ -void fsl_otg_uninit_timers(void) +static void fsl_otg_uninit_timers(void) { /* FSM used timers */ kfree(a_wait_vrise_tmr); @@ -391,7 +391,7 @@ static struct fsl_otg_timer *fsl_otg_get_timer(enum otg_fsm_timer t) } /* Add timer to timer list */ -void fsl_otg_add_timer(struct otg_fsm *fsm, void *gtimer) +static void fsl_otg_add_timer(struct otg_fsm *fsm, void *gtimer) { struct fsl_otg_timer *timer = gtimer; struct fsl_otg_timer *tmp_timer; @@ -421,7 +421,7 @@ static void fsl_otg_fsm_add_timer(struct otg_fsm *fsm, enum otg_fsm_timer t) } /* Remove timer from the timer list; clear timeout status */ -void fsl_otg_del_timer(struct otg_fsm *fsm, void *gtimer) +static void fsl_otg_del_timer(struct otg_fsm *fsm, void *gtimer) { struct fsl_otg_timer *timer = gtimer; struct fsl_otg_timer *tmp_timer, *del_tmp; @@ -443,7 +443,7 @@ static void fsl_otg_fsm_del_timer(struct otg_fsm *fsm, enum otg_fsm_timer t) } /* Reset controller, not reset the bus */ -void otg_reset_controller(void) +static void otg_reset_controller(void) { u32 command; @@ -455,7 +455,7 @@ void otg_reset_controller(void) } /* Call suspend/resume routines in host driver */ -int fsl_otg_start_host(struct otg_fsm *fsm, int on) +static int fsl_otg_start_host(struct otg_fsm *fsm, int on) { struct usb_otg *otg = fsm->otg; struct device *dev; @@ -522,7 +522,7 @@ end: * Call suspend and resume function in udc driver * to stop and start udc driver. */ -int fsl_otg_start_gadget(struct otg_fsm *fsm, int on) +static int fsl_otg_start_gadget(struct otg_fsm *fsm, int on) { struct usb_otg *otg = fsm->otg; struct device *dev; @@ -704,7 +704,7 @@ static int fsl_otg_start_hnp(struct usb_otg *otg) * intact. It needs to have knowledge of some USB interrupts * such as port change. */ -irqreturn_t fsl_otg_isr(int irq, void *dev_id) +static irqreturn_t fsl_otg_isr(int irq, void *dev_id) { struct otg_fsm *fsm = &((struct fsl_otg *)dev_id)->fsm; struct usb_otg *otg = ((struct fsl_otg *)dev_id)->phy.otg; @@ -830,7 +830,7 @@ err: } /* OTG Initialization */ -int usb_otg_start(struct platform_device *pdev) +static int usb_otg_start(struct platform_device *pdev) { struct fsl_otg *p_otg; struct usb_phy *otg_trans = usb_get_phy(USB_PHY_TYPE_USB2); @@ -1002,7 +1002,7 @@ static void fsl_otg_remove(struct platform_device *pdev) pdata->exit(pdev); } -struct platform_driver fsl_otg_driver = { +static struct platform_driver fsl_otg_driver = { .probe = fsl_otg_probe, .remove = fsl_otg_remove, .driver = { diff --git a/drivers/usb/phy/phy-fsl-usb.h b/drivers/usb/phy/phy-fsl-usb.h index d70341ae5a92..cc841c4e4762 100644 --- a/drivers/usb/phy/phy-fsl-usb.h +++ b/drivers/usb/phy/phy-fsl-usb.h @@ -373,6 +373,6 @@ struct fsl_otg_config { #define FSL_OTG_NAME "fsl-usb2-otg" -void fsl_otg_add_timer(struct otg_fsm *fsm, void *timer); -void fsl_otg_del_timer(struct otg_fsm *fsm, void *timer); -void fsl_otg_pulse_vbus(void); +static void fsl_otg_add_timer(struct otg_fsm *fsm, void *timer); +static void fsl_otg_del_timer(struct otg_fsm *fsm, void *timer); +static void fsl_otg_pulse_vbus(void); diff --git a/drivers/usb/typec/altmodes/thunderbolt.c b/drivers/usb/typec/altmodes/thunderbolt.c index d09dd09cf1c3..1f4dab8d6264 100644 --- a/drivers/usb/typec/altmodes/thunderbolt.c +++ b/drivers/usb/typec/altmodes/thunderbolt.c @@ -303,6 +303,8 @@ static void tbt_altmode_remove(struct typec_altmode *alt) { struct tbt_altmode *tbt = typec_altmode_get_drvdata(alt); + disable_work_sync(&tbt->work); + for (int i = TYPEC_PLUG_SOP_PP; i >= 0; --i) { if (tbt->plug[i]) typec_altmode_put_plug(tbt->plug[i]); diff --git a/drivers/usb/typec/tcpm/tcpci.c b/drivers/usb/typec/tcpm/tcpci.c index 2a951c585e92..3be5d3f58c50 100644 --- a/drivers/usb/typec/tcpm/tcpci.c +++ b/drivers/usb/typec/tcpm/tcpci.c @@ -37,6 +37,7 @@ struct tcpci { struct regmap *regmap; unsigned int alert_mask; + unsigned int rx_type_mask; bool controls_vbus; @@ -485,6 +486,8 @@ static int tcpci_set_pd_rx(struct tcpc_dev *tcpc, bool enable) if (tcpci->data->cable_comm_capable) reg |= TCPC_RX_DETECT_SOP1; } + + tcpci->rx_type_mask = reg; ret = regmap_write(tcpci->regmap, TCPC_RX_DETECT, reg); if (ret < 0) return ret; @@ -746,6 +749,7 @@ process_status: if (status & TCPC_ALERT_RX_STATUS) { struct pd_message msg; unsigned int cnt, payload_cnt; + enum tcpm_transmit_type rx_type; u16 header; regmap_read(tcpci->regmap, TCPC_RX_BYTE_CNT, &cnt); @@ -770,10 +774,16 @@ process_status: regmap_raw_read(tcpci->regmap, TCPC_RX_DATA, &msg.payload, payload_cnt); + ret = regmap_read(tcpci->regmap, TCPC_RX_BUF_FRAME_TYPE, &rx_type); + if (ret) + return ret; + /* Read complete, clear RX status alert bit */ tcpci_write16(tcpci, TCPC_ALERT, TCPC_ALERT_RX_STATUS); - tcpm_pd_receive(tcpci->port, &msg, TCPC_TX_SOP); + rx_type &= TCPC_RX_BUF_FRAME_TYPE_MASK; + if (tcpci->rx_type_mask & BIT(rx_type)) + tcpm_pd_receive(tcpci->port, &msg, rx_type); } if (tcpci->data->vbus_vsafe0v && (status & TCPC_ALERT_EXTENDED_STATUS)) { diff --git a/drivers/usb/typec/ucsi/ucsi.c b/drivers/usb/typec/ucsi/ucsi.c index 0d1062191951..85e2e7fcd02c 100644 --- a/drivers/usb/typec/ucsi/ucsi.c +++ b/drivers/usb/typec/ucsi/ucsi.c @@ -78,7 +78,8 @@ int ucsi_sync_control_common(struct ucsi *ucsi, u64 command, u32 *cci, if (ret) goto out_clear_bit; - if (!wait_for_completion_timeout(&ucsi->complete, 5 * HZ)) + if (!wait_for_completion_timeout(&ucsi->complete, + msecs_to_jiffies(UCSI_TIMEOUT_MS))) ret = -ETIMEDOUT; out_clear_bit: diff --git a/drivers/video/fbdev/omap2/omapfb/displays/panel-dsi-cm.c b/drivers/video/fbdev/omap2/omapfb/displays/panel-dsi-cm.c index 1d75f27c6b80..ce1d4d5f4034 100644 --- a/drivers/video/fbdev/omap2/omapfb/displays/panel-dsi-cm.c +++ b/drivers/video/fbdev/omap2/omapfb/displays/panel-dsi-cm.c @@ -1151,14 +1151,14 @@ static int dsicm_probe(struct platform_device *pdev) dssdev->caps = OMAP_DSS_DISPLAY_CAP_MANUAL_UPDATE | OMAP_DSS_DISPLAY_CAP_TEAR_ELIM; + mutex_init(&ddata->lock); + r = omapdss_register_display(dssdev); if (r) { dev_err(dev, "Failed to register panel\n"); goto err_reg; } - mutex_init(&ddata->lock); - atomic_set(&ddata->do_update, 0); ddata->reset_gpio = devm_gpiod_get(&pdev->dev, "reset", GPIOD_OUT_LOW); diff --git a/drivers/video/fbdev/pvr2fb.c b/drivers/video/fbdev/pvr2fb.c index 0b8d23c12b77..d3459a56beef 100644 --- a/drivers/video/fbdev/pvr2fb.c +++ b/drivers/video/fbdev/pvr2fb.c @@ -639,7 +639,7 @@ static irqreturn_t __maybe_unused pvr2fb_interrupt(int irq, void *dev_id) } #ifdef CONFIG_PVR2_DMA -static ssize_t pvr2fb_write(struct fb_info *info, const char *buf, +static ssize_t pvr2fb_write(struct fb_info *info, const char __user *buf, size_t count, loff_t *ppos) { unsigned long dst, start, end, len; @@ -1078,7 +1078,7 @@ static struct pvr2_board { #ifdef CONFIG_PCI { pvr2fb_pci_init, pvr2fb_pci_exit, "PCI PVR2" }, #endif - { 0, }, + { }, }; static int __init pvr2fb_init(void) diff --git a/drivers/video/fbdev/ssd1307fb.c b/drivers/video/fbdev/ssd1307fb.c index 83dd31fa1fab..0df3ac694f4e 100644 --- a/drivers/video/fbdev/ssd1307fb.c +++ b/drivers/video/fbdev/ssd1307fb.c @@ -14,6 +14,7 @@ #include <linux/module.h> #include <linux/property.h> #include <linux/pwm.h> +#include <linux/spinlock.h> #include <linux/uaccess.h> #include <linux/regulator/consumer.h> @@ -72,6 +73,13 @@ struct ssd1307fb_par { struct i2c_client *client; u32 height; struct fb_info *info; + /* Pending damage, with exclusive x2/y2, protected by damage_lock. */ + spinlock_t damage_lock; + bool damage_pending; + u32 damage_x1; + u32 damage_x2; + u32 damage_y1; + u32 damage_y2; u8 lookup_table[4]; u32 page_offset; u32 col_offset; @@ -302,19 +310,49 @@ static int ssd1307fb_blank(int blank_mode, struct fb_info *info) return ssd1307fb_write_cmd(par->client, SSD1307FB_DISPLAY_ON); } +static void ssd1307fb_schedule_damage(struct fb_info *info, u32 x, u32 y, + u32 width, u32 height) +{ + struct ssd1307fb_par *par = info->par; + unsigned long flags; + u32 x2, y2; + + if (!width || !height || x >= par->width || y >= par->height) + return; + + x2 = x + min(width, par->width - x); + y2 = y + min(height, par->height - y); + + spin_lock_irqsave(&par->damage_lock, flags); + if (par->damage_pending) { + par->damage_x1 = min(par->damage_x1, x); + par->damage_y1 = min(par->damage_y1, y); + par->damage_x2 = max(par->damage_x2, x2); + par->damage_y2 = max(par->damage_y2, y2); + } else { + par->damage_x1 = x; + par->damage_y1 = y; + par->damage_x2 = x2; + par->damage_y2 = y2; + par->damage_pending = true; + } + spin_unlock_irqrestore(&par->damage_lock, flags); + + /* Advance an already-pending mmap update as well. */ + mod_delayed_work(system_wq, &info->deferred_work, 0); +} + static void ssd1307fb_defio_damage_range(struct fb_info *info, off_t off, size_t len) { struct ssd1307fb_par *par = info->par; - ssd1307fb_update_display(par); + ssd1307fb_schedule_damage(info, 0, 0, par->width, par->height); } static void ssd1307fb_defio_damage_area(struct fb_info *info, u32 x, u32 y, u32 width, u32 height) { - struct ssd1307fb_par *par = info->par; - - ssd1307fb_update_rect(par, x, y, width, height); + ssd1307fb_schedule_damage(info, x, y, width, height); } FB_GEN_DEFAULT_DEFERRED_SYSMEM_OPS(ssd1307fb, @@ -329,7 +367,30 @@ static const struct fb_ops ssd1307fb_ops = { static void ssd1307fb_deferred_io(struct fb_info *info, struct list_head *pagereflist) { - ssd1307fb_update_display(info->par); + struct ssd1307fb_par *par = info->par; + unsigned long flags; + u32 x, y, width, height; + + spin_lock_irqsave(&par->damage_lock, flags); + if (!list_empty(pagereflist)) { + x = 0; + y = 0; + width = par->width; + height = par->height; + par->damage_pending = false; + } else if (par->damage_pending) { + x = par->damage_x1; + y = par->damage_y1; + width = par->damage_x2 - par->damage_x1; + height = par->damage_y2 - par->damage_y1; + par->damage_pending = false; + } else { + spin_unlock_irqrestore(&par->damage_lock, flags); + return; + } + spin_unlock_irqrestore(&par->damage_lock, flags); + + ssd1307fb_update_rect(par, x, y, width, height); } static int ssd1307fb_init(struct ssd1307fb_par *par) @@ -601,6 +662,7 @@ static int ssd1307fb_probe(struct i2c_client *client) par = info->par; par->info = info; par->client = client; + spin_lock_init(&par->damage_lock); par->device_info = device_get_match_data(dev); diff --git a/drivers/video/fbdev/uvesafb.c b/drivers/video/fbdev/uvesafb.c index b806da0538bc..8330d80fb394 100644 --- a/drivers/video/fbdev/uvesafb.c +++ b/drivers/video/fbdev/uvesafb.c @@ -1910,6 +1910,8 @@ static int uvesafb_init(void) err = 0; } } + if (err) + cn_del_callback(&uvesafb_cn_id); return err; } diff --git a/drivers/video/sticore.c b/drivers/video/sticore.c index 88a1758616e0..91382628515b 100644 --- a/drivers/video/sticore.c +++ b/drivers/video/sticore.c @@ -325,7 +325,7 @@ static void sti_rom_copy(unsigned long base, unsigned long count, void *dest) -static char default_sti_path[21] __read_mostly; +static char default_sti_path[32] __read_mostly; #ifndef MODULE static int __init sti_setup(char *str) @@ -1148,6 +1148,26 @@ static void sti_init_roms(void) pr_info("STI GSC/PCI core graphics driver " STI_DRIVERVERSION "\n"); + /* + * Find default console by hardware path which is either stored in + * console entry in stable storage or alternatively from console path + * in PAGE0 used by BCH and PDC. + */ + if (!default_sti_path[0]) { + struct pdc_module_path conspath; + struct device *dev = NULL; + + if (pdc_stable_read(0x60, &conspath, sizeof(conspath)) == PDC_OK) + dev = hwpath_to_device(&conspath.path); + if (!dev) + dev = hwpath_to_device(&PAGE0->mem_cons.dp.path); + if (dev && dev_is_pci(dev)) + print_pci_hwpath(to_pci_dev(dev), default_sti_path); + else if (dev && !dev_is_pci(dev)) + print_pa_hwpath(to_parisc_device(dev), default_sti_path); + pr_debug("default graphic card: %s\n", default_sti_path); + } + /* Register drivers for native & PCI cards */ register_parisc_driver(&pa_sti_driver); WARN_ON(pci_register_driver(&pci_sti_driver)); diff --git a/drivers/w1/slaves/w1_ds28e17.c b/drivers/w1/slaves/w1_ds28e17.c index 5738cbce1a37..d98a1719d6b3 100644 --- a/drivers/w1/slaves/w1_ds28e17.c +++ b/drivers/w1/slaves/w1_ds28e17.c @@ -389,6 +389,10 @@ static int w1_f19_i2c_master_transfer(struct i2c_adapter *adapter, * another simple read in that case. */ if (msgs[i+1].flags & I2C_M_RECV_LEN) { + if (msgs[i+1].buf[0] > I2C_SMBUS_BLOCK_MAX) { + i = -EPROTO; + goto error; + } result = w1_f19_i2c_read(sl, msgs[i+1].addr, &(msgs[i+1].buf[1]), msgs[i+1].buf[0]); if (result < 0) { @@ -415,6 +419,10 @@ static int w1_f19_i2c_master_transfer(struct i2c_adapter *adapter, * another simple read in that case. */ if (msgs[i].flags & I2C_M_RECV_LEN) { + if (msgs[i].buf[0] > I2C_SMBUS_BLOCK_MAX) { + i = -EPROTO; + goto error; + } result = w1_f19_i2c_read(sl, msgs[i].addr, &(msgs[i].buf[1]), diff --git a/fs/backing-file.c b/fs/backing-file.c index e049a627d78f..6f16e23f7046 100644 --- a/fs/backing-file.c +++ b/fs/backing-file.c @@ -34,7 +34,7 @@ struct file *backing_file_open(const struct file *user_file, int flags, const struct path *real_path, const struct cred *cred) { - const struct path *user_path = &user_file->f_path; + const struct path *user_path = file_user_path(user_file); struct file *f; int error; diff --git a/fs/btrfs/direct-io.c b/fs/btrfs/direct-io.c index 3091132190b6..5f2a99e68335 100644 --- a/fs/btrfs/direct-io.c +++ b/fs/btrfs/direct-io.c @@ -281,17 +281,24 @@ static int btrfs_get_blocks_direct_write(struct extent_map **map, em2 = btrfs_create_dio_extent(BTRFS_I(inode), dio_data, start, &file_extent, type); btrfs_dec_nocow_writers(bg); - if (type == BTRFS_ORDERED_PREALLOC) { - btrfs_free_extent_map(em); - *map = em2; - em = em2; - } - if (IS_ERR(em2)) { ret = PTR_ERR(em2); + btrfs_free_extent_map(em); + *map = NULL; goto out; } + /* + * True NOCOW writes don't need to create a new extent map, + * while PREALLOC writes must replace the existing one. + */ + if (em2) { + ASSERT(type == BTRFS_ORDERED_PREALLOC); + btrfs_free_extent_map(em); + *map = em2; + em = em2; + } + dio_data->nocow_done = true; } else { /* Our caller expects us to free the input extent map. */ diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 2f1c5f5e2e72..b702f625c753 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -330,14 +330,21 @@ int btrfs_fileattr_set(struct mnt_idmap *idmap, inode_flags |= BTRFS_INODE_NODATACOW; } } else { - /* - * Revert back under same assumptions as above - */ - if (S_ISREG(inode->vfs_inode.i_mode)) { - if (inode->vfs_inode.i_size == 0) - inode_flags &= ~(BTRFS_INODE_NODATACOW | - BTRFS_INODE_NODATASUM); - } else { + /* We can only change NODATACOW for zero-sized regular file. */ + if (S_ISREG(inode->vfs_inode.i_mode) && (inode->vfs_inode.i_size == 0)) { + inode_flags &= ~BTRFS_INODE_NODATACOW; + /* + * There is currently no way to change NODATASUM flag + * through fileattr API. If we unconditionally keep the + * current NODATASUM flag, chattr +C then chattr -C will + * keep the NODATASUM flag, and no way to remove that + * flag. + * + * So respect the current mount option for NODATASUM flag. + */ + if (!btrfs_test_opt(fs_info, NODATASUM)) + inode_flags &= ~BTRFS_INODE_NODATASUM; + } else if (!S_ISREG(inode->vfs_inode.i_mode)) { inode_flags &= ~BTRFS_INODE_NODATACOW; } } diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index 80e5de6736e8..37f20f401b0e 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -4056,6 +4056,24 @@ static noinline_for_stack int mark_garbage_root(struct btrfs_root *root) return ret; } +static void release_recovered_fs_roots(struct list_head *roots, bool drop_reloc_refs) +{ + struct btrfs_root *root; + struct btrfs_root *next; + + list_for_each_entry_safe(root, next, roots, reloc_dirty_list) { + list_del_init(&root->reloc_dirty_list); + if (drop_reloc_refs) { + struct btrfs_root *reloc_root = root->reloc_root; + + ASSERT(reloc_root); + root->reloc_root = NULL; + btrfs_put_root(reloc_root); + } + btrfs_put_root(root); + } +} + /* * recover relocation interrupted by system crash. * @@ -4065,6 +4083,7 @@ static noinline_for_stack int mark_garbage_root(struct btrfs_root *root) int btrfs_recover_relocation(struct btrfs_fs_info *fs_info) { LIST_HEAD(reloc_roots); + LIST_HEAD(recovered_roots); struct btrfs_key key; struct btrfs_root *fs_root; struct btrfs_root *reloc_root; @@ -4176,7 +4195,7 @@ int btrfs_recover_relocation(struct btrfs_fs_info *fs_info) ret = PTR_ERR(fs_root); list_add_tail(&reloc_root->root_list, &reloc_roots); btrfs_end_transaction(trans); - goto out_unset; + goto out_drop_reloc_refs; } ret = __add_reloc_root(reloc_root); @@ -4185,15 +4204,17 @@ int btrfs_recover_relocation(struct btrfs_fs_info *fs_info) list_add_tail(&reloc_root->root_list, &reloc_roots); btrfs_put_root(fs_root); btrfs_end_transaction(trans); - goto out_unset; + goto out_drop_reloc_refs; } + ASSERT(list_empty(&fs_root->reloc_dirty_list)); fs_root->reloc_root = btrfs_grab_root(reloc_root); - btrfs_put_root(fs_root); + list_add_tail(&fs_root->reloc_dirty_list, &recovered_roots); } ret = btrfs_commit_transaction(trans); if (ret) - goto out_unset; + goto out_drop_reloc_refs; + release_recovered_fs_roots(&recovered_roots, false); merge_reloc_roots(rc); @@ -4209,6 +4230,8 @@ out_clean: ret2 = clean_dirty_subvols(rc); if (ret2 < 0 && !ret) ret = ret2; +out_drop_reloc_refs: + release_recovered_fs_roots(&recovered_roots, true); out_unset: unset_reloc_control(rc); reloc_chunk_end(fs_info); diff --git a/fs/buffer.c b/fs/buffer.c index b6b477ff7b75..261f521dbc58 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -2199,6 +2199,7 @@ void block_commit_write(struct folio *folio, size_t from, size_t to) { size_t block_start, block_end; bool partial = false; + bool uptodate = folio_test_uptodate(folio); unsigned blocksize; struct buffer_head *bh, *head; @@ -2221,6 +2222,8 @@ void block_commit_write(struct folio *folio, size_t from, size_t to) clear_buffer_new(bh); block_start = block_end; + if (uptodate && block_start >= to) + break; bh = bh->b_this_page; } while (bh != head); diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index ea31c892a1fb..faa3de95caff 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -1421,6 +1421,16 @@ void ceph_shift_unused_folios_left(struct folio_batch *fbatch) fbatch->nr = n; } +static void ceph_undo_wrbuffer_claim(struct inode *inode, struct folio *folio) +{ + struct ceph_snap_context *snapc = folio_detach_private(folio); + + if (!snapc) + return; + ceph_put_wrbuffer_cap_refs(ceph_inode(inode), 1, snapc); + ceph_put_snap_context(snapc); +} + static int ceph_submit_write(struct address_space *mapping, struct writeback_control *wbc, @@ -1484,6 +1494,7 @@ new_request: if (!page) continue; + ceph_undo_wrbuffer_claim(inode, page_folio(page)); redirty_page_for_writepage(wbc, page); unlock_page(page); } diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index 07e3236e0f97..94d59d58ea3a 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -2585,9 +2585,14 @@ static void __kick_flushing_caps(struct ceph_mds_client *mdsc, } } - list_for_each_entry(cf, &ci->i_cap_flush_list, i_list) { - if (cf->tid < first_tid) + cf = list_first_entry(&ci->i_cap_flush_list, struct ceph_cap_flush, i_list); + while (&cf->i_list != &ci->i_cap_flush_list) { + struct ceph_cap_flush *next; + + if (cf->tid < first_tid) { + cf = list_next_entry(cf, i_list); continue; + } cap = ci->i_auth_cap; if (!(cap && cap->session == session)) { @@ -2597,6 +2602,7 @@ static void __kick_flushing_caps(struct ceph_mds_client *mdsc, } first_tid = cf->tid + 1; + next = list_next_entry(cf, i_list); if (!cf->is_capsnap) { struct cap_msg_args arg; @@ -2637,6 +2643,7 @@ static void __kick_flushing_caps(struct ceph_mds_client *mdsc, } spin_lock(&ci->i_ceph_lock); + cf = next; } } diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c index c30510bdae3a..e4577a80da58 100644 --- a/fs/ceph/dir.c +++ b/fs/ceph/dir.c @@ -1763,11 +1763,11 @@ static int __dir_lease_check(const struct dentry *dentry, if (ret > 0) { if (time_before(jiffies, di->time + lwc->dir_lease_ttl)) return STOP; + if (!lwc->expire_dir_lease) + return KEEP; /* Move dentry to tail of dir lease list if we don't want * to delete it. So dentries in the list are checked in a * round robin manner */ - if (!lwc->expire_dir_lease) - return TOUCH; if (dentry->d_lockref.count > 0 || (di->flags & CEPH_DENTRY_REFERENCED)) return TOUCH; @@ -1794,7 +1794,7 @@ int ceph_trim_dentries(struct ceph_mds_client *mdsc) lwc.dir_lease = false; lwc.nr_to_scan = CEPH_CAPS_PER_RELEASE * 2; freed = __dentry_leases_walk(mdsc, &lwc); - if (!lwc.nr_to_scan) /* more invalid leases */ + if (freed > 0 && !lwc.nr_to_scan) /* more invalid leases */ return -EAGAIN; if (lwc.nr_to_scan < CEPH_CAPS_PER_RELEASE) @@ -1804,6 +1804,10 @@ int ceph_trim_dentries(struct ceph_mds_client *mdsc) lwc.expire_dir_lease = freed < count; lwc.dir_lease_ttl = mdsc->fsc->mount_options->caps_wanted_delay_max * HZ; freed +=__dentry_leases_walk(mdsc, &lwc); + if (freed == 0 && count == 0) + /* no progress possible currently, retry futile */ + return 0; + if (!lwc.nr_to_scan) /* more to check */ return -EAGAIN; diff --git a/fs/ceph/export.c b/fs/ceph/export.c index b2f2af104679..debb9634b9e3 100644 --- a/fs/ceph/export.c +++ b/fs/ceph/export.c @@ -442,6 +442,16 @@ static struct dentry *ceph_fh_to_parent(struct super_block *sb, return dentry; } +static int ceph_export_copy_name(char *name, const char *src, u32 len) +{ + if (len > NAME_MAX) + return -ENAMETOOLONG; + + memcpy(name, src, len); + name[len] = '\0'; + return 0; +} + static int __get_snap_name(struct dentry *parent, char *name, struct dentry *child) { @@ -513,9 +523,8 @@ static int __get_snap_name(struct dentry *parent, char *name, BUG_ON(!rde->inode.in); if (ceph_snap(inode) == le64_to_cpu(rde->inode.in->snapid)) { - memcpy(name, rde->name, rde->name_len); - name[rde->name_len] = '\0'; - err = 0; + err = ceph_export_copy_name(name, rde->name, + rde->name_len); goto out; } } @@ -580,8 +589,8 @@ static int ceph_get_name(struct dentry *parent, char *name, rinfo = &req->r_reply_info; if (!IS_ENCRYPTED(dir)) { - memcpy(name, rinfo->dname, rinfo->dname_len); - name[rinfo->dname_len] = 0; + err = ceph_export_copy_name(name, rinfo->dname, + rinfo->dname_len); } else { struct fscrypt_str oname = FSTR_INIT(NULL, 0); struct ceph_fname fname = { .dir = dir, @@ -595,10 +604,9 @@ static int ceph_get_name(struct dentry *parent, char *name, goto out; err = ceph_fname_to_usr(&fname, NULL, &oname, NULL); - if (!err) { - memcpy(name, oname.name, oname.len); - name[oname.len] = 0; - } + if (!err) + err = ceph_export_copy_name(name, oname.name, + oname.len); ceph_fname_free_buffer(dir, &oname); } out: diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 049b2d414fe9..7752564bd77a 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -4269,7 +4269,9 @@ static void handle_session(struct ceph_mds_session *session, pr_err_client(cl, "No memory for path\n"); goto fail; } - ceph_decode_copy(&p, cap_auths[i].match.path, _len); + ceph_decode_copy_safe(&p, end, + cap_auths[i].match.path, + _len, bad); /* Remove the tailing '/' */ while (_len && cap_auths[i].match.path[_len - 1] == '/') { @@ -4286,7 +4288,9 @@ static void handle_session(struct ceph_mds_session *session, pr_err_client(cl, "No memory for fs_name\n"); goto fail; } - ceph_decode_copy(&p, cap_auths[i].match.fs_name, _len); + ceph_decode_copy_safe(&p, end, + cap_auths[i].match.fs_name, + _len, bad); } ceph_decode_8_safe(&p, end, cap_auths[i].match.root_squash, bad); diff --git a/fs/ceph/mdsmap.c b/fs/ceph/mdsmap.c index 97ecf272a37d..c91c0e2e118b 100644 --- a/fs/ceph/mdsmap.c +++ b/fs/ceph/mdsmap.c @@ -3,6 +3,7 @@ #include <linux/bug.h> #include <linux/err.h> +#include <linux/overflow.h> #include <linux/random.h> #include <linux/slab.h> #include <linux/types.h> @@ -126,6 +127,7 @@ struct ceph_mdsmap *ceph_mdsmap_decode(struct ceph_mds_client *mdsc, void **p, u8 mdsmap_v; u16 mdsmap_ev; u32 target; + size_t export_targets_len; m = kzalloc(sizeof(*m), GFP_NOFS); if (!m) @@ -224,8 +226,11 @@ struct ceph_mdsmap *ceph_mdsmap_decode(struct ceph_mds_client *mdsc, void **p, *p += namelen; if (info_v >= 2) { ceph_decode_32_safe(p, end, num_export_targets, bad); + export_targets_len = size_mul(num_export_targets, + sizeof(u32)); + ceph_decode_need(p, end, export_targets_len, bad); pexport_targets = *p; - *p += num_export_targets * sizeof(u32); + *p += export_targets_len; } else { num_export_targets = 0; } @@ -264,6 +269,10 @@ struct ceph_mdsmap *ceph_mdsmap_decode(struct ceph_mds_client *mdsc, void **p, goto nomem; for (j = 0; j < num_export_targets; j++) { target = ceph_decode_32(&pexport_targets); + if (target >= CEPH_MAX_MDS) { + err = -EIO; + goto corrupt; + } info->export_targets[j] = target; } } else { diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c index caf0fe4d2b1b..cc73b0874ce4 100644 --- a/fs/ceph/xattr.c +++ b/fs/ceph/xattr.c @@ -850,6 +850,7 @@ start: name = p; p += len; ceph_decode_32_safe(&p, end, len, bad); + ceph_decode_need(&p, end, len, bad); val = p; p += len; diff --git a/fs/ecryptfs/crypto.c b/fs/ecryptfs/crypto.c index 69536cacdea8..70c204c995a7 100644 --- a/fs/ecryptfs/crypto.c +++ b/fs/ecryptfs/crypto.c @@ -1285,7 +1285,7 @@ static int ecryptfs_read_headers_virt(char *page_virt, } else set_default_header_data(crypt_stat); rc = ecryptfs_parse_packet_set(crypt_stat, (page_virt + offset), - ecryptfs_dentry); + PAGE_SIZE - offset, ecryptfs_dentry); out: return rc; } diff --git a/fs/ecryptfs/ecryptfs_kernel.h b/fs/ecryptfs/ecryptfs_kernel.h index 9e6ab0b41337..5be8c31653fa 100644 --- a/fs/ecryptfs/ecryptfs_kernel.h +++ b/fs/ecryptfs/ecryptfs_kernel.h @@ -585,7 +585,8 @@ int ecryptfs_generate_key_packet_set(char *dest_base, size_t *len, size_t max); int ecryptfs_parse_packet_set(struct ecryptfs_crypt_stat *crypt_stat, - unsigned char *src, struct dentry *ecryptfs_dentry); + unsigned char *src, size_t src_size, + struct dentry *ecryptfs_dentry); int ecryptfs_truncate(struct dentry *dentry, loff_t new_length); ssize_t ecryptfs_getxattr_lower(struct dentry *lower_dentry, struct inode *lower_inode, diff --git a/fs/ecryptfs/keystore.c b/fs/ecryptfs/keystore.c index 7f9f68c00ef6..970e37510394 100644 --- a/fs/ecryptfs/keystore.c +++ b/fs/ecryptfs/keystore.c @@ -937,6 +937,12 @@ ecryptfs_parse_tag_70_packet(char **filename, size_t *filename_size, "rc = [%d]\n", __func__, rc); goto out; } + if (s->parsed_tag_70_packet_size < (ECRYPTFS_SIG_SIZE + 2)) { + ecryptfs_printk(KERN_WARNING, "Invalid packet size [%zd]\n", + s->parsed_tag_70_packet_size); + rc = -EINVAL; + goto out; + } s->block_aligned_filename_size = (s->parsed_tag_70_packet_size - ECRYPTFS_SIG_SIZE - 1); if ((1 + s->packet_size_len + s->parsed_tag_70_packet_size) @@ -1424,10 +1430,20 @@ parse_tag_3_packet(struct ecryptfs_crypt_stat *crypt_stat, } (*new_auth_tok)->session_key.encrypted_key_size = (body_size - (ECRYPTFS_SALT_SIZE + 5)); + /* + * Although encrypted_key_size is copied into the + * encrypted_key[ECRYPTFS_MAX_ENCRYPTED_KEY_BYTES] buffer here, + * it later bounds operations on a smaller buffer: + * decrypt_passphrase_encrypted_session_key() sets decrypted_key_size = + * encrypted_key_size and decrypts into + * decrypted_key[ECRYPTFS_MAX_KEY_BYTES], then memcpy's into + * crypt_stat->key[ECRYPTFS_MAX_KEY_BYTES]. Limit to + * ECRYPTFS_MAX_KEY_BYTES to protect those smaller buffers. + */ if ((*new_auth_tok)->session_key.encrypted_key_size - > ECRYPTFS_MAX_ENCRYPTED_KEY_BYTES) { + > ECRYPTFS_MAX_KEY_BYTES) { printk(KERN_WARNING "Tag 3 packet contains key larger " - "than ECRYPTFS_MAX_ENCRYPTED_KEY_BYTES\n"); + "than ECRYPTFS_MAX_KEY_BYTES\n"); rc = -EINVAL; goto out_free; } @@ -1576,7 +1592,7 @@ parse_tag_11_packet(unsigned char *data, unsigned char *contents, } (*packet_size) += length_size; (*tag_11_contents_size) = (body_size - 14); - if (unlikely((*packet_size) + body_size + 1 > max_packet_size)) { + if (unlikely((*packet_size) + body_size > max_packet_size)) { printk(KERN_ERR "Packet size exceeds max\n"); rc = -EINVAL; goto out; @@ -1743,6 +1759,7 @@ out: * ecryptfs_parse_packet_set * @crypt_stat: The cryptographic context * @src: Virtual address of region of memory containing the packets + * @src_size: Size of the packet set buffer * @ecryptfs_dentry: The eCryptfs dentry associated with the packet set * * Get crypt_stat to have the file's session key if the requisite key @@ -1753,7 +1770,7 @@ out: * conditions. */ int ecryptfs_parse_packet_set(struct ecryptfs_crypt_stat *crypt_stat, - unsigned char *src, + unsigned char *src, size_t src_size, struct dentry *ecryptfs_dentry) { size_t i = 0; @@ -1777,7 +1794,11 @@ int ecryptfs_parse_packet_set(struct ecryptfs_crypt_stat *crypt_stat, * added the our &auth_tok_list */ next_packet_is_auth_tok_packet = 1; while (next_packet_is_auth_tok_packet) { - size_t max_packet_size = ((PAGE_SIZE - 8) - i); + size_t max_packet_size; + + if (i >= src_size) + break; + max_packet_size = src_size - i; switch (src[i]) { case ECRYPTFS_TAG_3_PACKET_TYPE: @@ -1792,12 +1813,16 @@ int ecryptfs_parse_packet_set(struct ecryptfs_crypt_stat *crypt_stat, goto out_wipe_list; } i += packet_size; + if (i > src_size) { + rc = -EIO; + goto out_wipe_list; + } rc = parse_tag_11_packet((unsigned char *)&src[i], sig_tmp_space, ECRYPTFS_SIG_SIZE, &tag_11_contents_size, &tag_11_packet_size, - max_packet_size); + src_size - i); if (rc) { ecryptfs_printk(KERN_ERR, "No valid " "(ecryptfs-specific) literal " @@ -1809,6 +1834,10 @@ int ecryptfs_parse_packet_set(struct ecryptfs_crypt_stat *crypt_stat, goto out_wipe_list; } i += tag_11_packet_size; + if (i > src_size) { + rc = -EIO; + goto out_wipe_list; + } if (ECRYPTFS_SIG_SIZE != tag_11_contents_size) { ecryptfs_printk(KERN_ERR, "Expected " "signature of size [%d]; " @@ -1836,6 +1865,10 @@ int ecryptfs_parse_packet_set(struct ecryptfs_crypt_stat *crypt_stat, goto out_wipe_list; } i += packet_size; + if (i > src_size) { + rc = -EIO; + goto out_wipe_list; + } crypt_stat->flags |= ECRYPTFS_ENCRYPTED; break; case ECRYPTFS_TAG_11_PACKET_TYPE: diff --git a/fs/ecryptfs/messaging.c b/fs/ecryptfs/messaging.c index 6318f3500e5c..75c35b559b37 100644 --- a/fs/ecryptfs/messaging.c +++ b/fs/ecryptfs/messaging.c @@ -165,6 +165,7 @@ int ecryptfs_exorcise_daemon(struct ecryptfs_daemon *daemon) mutex_unlock(&daemon->mux); goto out; } + mutex_lock(&ecryptfs_msg_ctx_lists_mux); list_for_each_entry_safe(msg_ctx, msg_ctx_tmp, &daemon->msg_ctx_out_queue, daemon_out_list) { list_del(&msg_ctx->daemon_out_list); @@ -173,6 +174,7 @@ int ecryptfs_exorcise_daemon(struct ecryptfs_daemon *daemon) "the out queue of a dying daemon\n", __func__); ecryptfs_msg_ctx_alloc_to_free(msg_ctx); } + mutex_unlock(&ecryptfs_msg_ctx_lists_mux); hlist_del(&daemon->euid_chain); mutex_unlock(&daemon->mux); kfree_sensitive(daemon); @@ -283,9 +285,16 @@ ecryptfs_send_message_locked(char *data, int data_len, u8 msg_type, mutex_unlock(&ecryptfs_msg_ctx_lists_mux); rc = ecryptfs_send_miscdev(data, data_len, *msg_ctx, msg_type, 0, daemon); - if (rc) + if (rc) { printk(KERN_ERR "%s: Error attempting to send message to " "userspace daemon; rc = [%d]\n", __func__, rc); + mutex_lock(&ecryptfs_msg_ctx_lists_mux); + mutex_lock(&(*msg_ctx)->mux); + ecryptfs_msg_ctx_alloc_to_free(*msg_ctx); + mutex_unlock(&(*msg_ctx)->mux); + mutex_unlock(&ecryptfs_msg_ctx_lists_mux); + *msg_ctx = NULL; + } out: return rc; } diff --git a/fs/ecryptfs/miscdev.c b/fs/ecryptfs/miscdev.c index 4e62c3cef70f..23baa55d390f 100644 --- a/fs/ecryptfs/miscdev.c +++ b/fs/ecryptfs/miscdev.c @@ -357,7 +357,7 @@ ecryptfs_miscdev_write(struct file *file, const char __user *buf, u32 seq; size_t packet_size, packet_size_length; char *data; - unsigned char packet_size_peek[ECRYPTFS_MAX_PKT_LEN_SIZE]; + unsigned char packet_size_peek[ECRYPTFS_MAX_PKT_LEN_SIZE] = { }; ssize_t rc; if (count == 0) { @@ -373,7 +373,8 @@ ecryptfs_miscdev_write(struct file *file, const char __user *buf, } if (copy_from_user(packet_size_peek, &buf[PKT_LEN_OFFSET], - sizeof(packet_size_peek))) { + min_t(size_t, count - PKT_LEN_OFFSET, + sizeof(packet_size_peek)))) { printk(KERN_WARNING "%s: Error while inspecting packet size\n", __func__); return -EFAULT; diff --git a/fs/ecryptfs/super.c b/fs/ecryptfs/super.c index e7b7f426fecf..0e2108219a6f 100644 --- a/fs/ecryptfs/super.c +++ b/fs/ecryptfs/super.c @@ -153,6 +153,13 @@ static int ecryptfs_show_options(struct seq_file *m, struct dentry *root) if (mount_crypt_stat->global_default_cipher_key_size) seq_printf(m, ",ecryptfs_key_bytes=%zd", mount_crypt_stat->global_default_cipher_key_size); + if (mount_crypt_stat->flags & ECRYPTFS_GLOBAL_ENCRYPT_FILENAMES) { + seq_printf(m, ",ecryptfs_fn_cipher=%s", + mount_crypt_stat->global_default_fn_cipher_name); + if (mount_crypt_stat->global_default_fn_cipher_key_bytes) + seq_printf(m, ",ecryptfs_fn_key_bytes=%zd", + mount_crypt_stat->global_default_fn_cipher_key_bytes); + } if (mount_crypt_stat->flags & ECRYPTFS_PLAINTEXT_PASSTHROUGH_ENABLED) seq_printf(m, ",ecryptfs_passthrough"); if (mount_crypt_stat->flags & ECRYPTFS_XATTR_METADATA_ENABLED) diff --git a/fs/efivarfs/super.c b/fs/efivarfs/super.c index 6de97565d5f7..ca5004774c0b 100644 --- a/fs/efivarfs/super.c +++ b/fs/efivarfs/super.c @@ -89,12 +89,30 @@ static int efivarfs_statfs(struct dentry *dentry, struct kstatfs *buf) /* Some UEFI firmware does not implement QueryVariableInfo() */ storage_space = remaining_space = 0; if (efi_rt_services_supported(EFI_RT_SUPPORTED_QUERY_VARIABLE_INFO)) { - status = efivar_query_variable_info(attr, &storage_space, - &remaining_space, - &max_variable_size); - if (status != EFI_SUCCESS && status != EFI_UNSUPPORTED) - pr_warn_ratelimited("query_variable_info() failed: 0x%lx\n", - status); + static DEFINE_RATELIMIT_STATE(_rs, 2 * HZ, 5); + static u64 storage, remaining; + static DEFINE_SPINLOCK(lock); + + if (!__ratelimit(&_rs)) { + ratelimit_set_flags(&_rs, RATELIMIT_MSG_ON_RELEASE); + + spin_lock(&lock); + storage_space = storage; + remaining_space = remaining; + spin_unlock(&lock); + } else { + status = efivar_query_variable_info(attr, &storage_space, + &remaining_space, + &max_variable_size); + if (status != EFI_SUCCESS && status != EFI_UNSUPPORTED) + pr_warn("query_variable_info() failed: 0x%lx\n", + status); + + spin_lock(&lock); + storage = storage_space; + remaining = remaining_space; + spin_unlock(&lock); + } } /* diff --git a/fs/fat/misc.c b/fs/fat/misc.c index 950da09f0961..5c45603bf77e 100644 --- a/fs/fat/misc.c +++ b/fs/fat/misc.c @@ -133,7 +133,11 @@ int fat_chain_add(struct inode *inode, int new_dclus, int nr_cluster) ret = fat_ent_read(inode, &fatent, last); if (ret >= 0) { int wait = inode_needs_sync(inode); + int old = ret; + ret = fat_ent_write(inode, &fatent, new_dclus, wait); + if (ret < 0) + fat_ent_write(inode, &fatent, old, wait); fatent_brelse(&fatent); } if (ret < 0) diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index 77c3982bca3d..e5559d28031b 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -580,7 +580,7 @@ static void request_wait_answer(struct fuse_req *req) if (req->args->abort_on_kill) { fuse_abort_conn(fc); - return; + goto wait_for_finish; } if (test_bit(FR_URING, &req->flags)) @@ -591,6 +591,7 @@ static void request_wait_answer(struct fuse_req *req) return; } +wait_for_finish: /* * Either request is already in userspace, or it was forced. * Wait it out. diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c index 6dbfb9cb07d7..d0a89ca1a4e4 100644 --- a/fs/jbd2/checkpoint.c +++ b/fs/jbd2/checkpoint.c @@ -358,15 +358,16 @@ int jbd2_cleanup_journal_tail(journal_t *journal) /* * journal_shrink_one_cp_list * - * Find all the written-back checkpoint buffers in the given list - * and try to release them. If the whole transaction is released, set - * the 'released' parameter. Return the number of released checkpointed - * buffers. + * Find written-back checkpoint buffers in the given list and try to release + * them. If 'nr_to_scan' is set, scan at most that many buffers. If the whole + * transaction is released, set the 'released' parameter. Return the number of + * released checkpointed buffers. * * Called with j_list_lock held. */ static unsigned long journal_shrink_one_cp_list(struct journal_head *jh, enum jbd2_shrink_type type, + unsigned long *nr_to_scan, bool *released) { struct journal_head *last_jh; @@ -375,13 +376,15 @@ static unsigned long journal_shrink_one_cp_list(struct journal_head *jh, int ret; *released = false; - if (!jh) + if (!jh || (nr_to_scan && !*nr_to_scan)) return 0; last_jh = jh->b_cpprev; do { jh = next_jh; next_jh = jh->b_cpnext; + if (nr_to_scan) + (*nr_to_scan)--; if (type == JBD2_SHRINK_DESTROY) { ret = __jbd2_journal_remove_checkpoint(jh); @@ -389,7 +392,7 @@ static unsigned long journal_shrink_one_cp_list(struct journal_head *jh, ret = jbd2_journal_try_remove_checkpoint(jh); if (ret < 0) { if (type == JBD2_SHRINK_BUSY_SKIP) - continue; + goto next; break; } } @@ -400,9 +403,10 @@ static unsigned long journal_shrink_one_cp_list(struct journal_head *jh, break; } +next: if (need_resched()) break; - } while (jh != last_jh); + } while (jh != last_jh && (!nr_to_scan || *nr_to_scan)); return nr_freed; } @@ -424,7 +428,6 @@ unsigned long jbd2_journal_shrink_checkpoint_list(journal_t *journal, tid_t first_tid = 0, last_tid = 0, next_tid = 0; tid_t tid = 0; unsigned long nr_freed = 0; - unsigned long freed; bool first_set = false; again: @@ -457,10 +460,9 @@ again: next_transaction = transaction->t_cpnext; tid = transaction->t_tid; - freed = journal_shrink_one_cp_list(transaction->t_checkpoint_list, - JBD2_SHRINK_BUSY_SKIP, &released); - nr_freed += freed; - (*nr_to_scan) -= min(*nr_to_scan, freed); + nr_freed += journal_shrink_one_cp_list(transaction->t_checkpoint_list, + JBD2_SHRINK_BUSY_SKIP, + nr_to_scan, &released); if (*nr_to_scan == 0) break; if (need_resched() || spin_needbreak(&journal->j_list_lock)) @@ -516,7 +518,7 @@ void __jbd2_journal_clean_checkpoint_list(journal_t *journal, transaction = next_transaction; next_transaction = transaction->t_cpnext; journal_shrink_one_cp_list(transaction->t_checkpoint_list, - type, &released); + type, NULL, &released); /* * This function only frees up some memory if possible so we * dont have an obligation to finish processing. Bail out if diff --git a/fs/lockd/clntproc.c b/fs/lockd/clntproc.c index cebcc283b7ce..8728b53cf2e8 100644 --- a/fs/lockd/clntproc.c +++ b/fs/lockd/clntproc.c @@ -487,9 +487,12 @@ static const struct file_lock_operations nlmclnt_lock_ops = { static void nlmclnt_locks_init_private(struct file_lock *fl, struct nlm_host *host) { fl->fl_u.nfs_fl.state = 0; + fl->fl_ops = NULL; fl->fl_u.nfs_fl.owner = nlmclnt_find_lockowner(host, fl->c.flc_owner); INIT_LIST_HEAD(&fl->fl_u.nfs_fl.list); + if (!fl->fl_u.nfs_fl.owner) + return; fl->fl_ops = &nlmclnt_lock_ops; } diff --git a/fs/lockd/svcsubs.c b/fs/lockd/svcsubs.c index d11beea76ddb..91a4c22c86ff 100644 --- a/fs/lockd/svcsubs.c +++ b/fs/lockd/svcsubs.c @@ -301,12 +301,10 @@ nlm_file_inuse(struct nlm_file *file) return 0; } -static void nlm_close_files(struct nlm_file *file) +static void nlm_file_release(struct nlm_file *file) { - if (file->f_file[O_RDONLY]) - nlmsvc_ops->fclose(file->f_file[O_RDONLY]); - if (file->f_file[O_WRONLY]) - nlmsvc_ops->fclose(file->f_file[O_WRONLY]); + if (!nlm_file_inuse(file)) + nlm_delete_file(file); } /* @@ -316,32 +314,41 @@ static int nlm_traverse_files(void *data, nlm_host_match_fn_t match, int (*is_failover_file)(void *data, struct nlm_file *file)) { - struct hlist_node *next; - struct nlm_file *file; + struct nlm_file *file, *next; int i, ret = 0; mutex_lock(&nlm_file_mutex); for (i = 0; i < FILE_NRHASH; i++) { - hlist_for_each_entry_safe(file, next, &nlm_files[i], f_list) { - if (is_failover_file && !is_failover_file(data, file)) - continue; + file = hlist_entry_safe(nlm_files[i].first, + struct nlm_file, f_list); + if (file) file->f_count++; - mutex_unlock(&nlm_file_mutex); - - /* Traverse locks, blocks and shares of this file - * and update file->f_locks count */ - if (nlm_inspect_file(data, file, match)) - ret = 1; + while (file) { + /* + * Pin the next neighbour before we drop the mutex + * for nlm_inspect_file(); a concurrent + * nlm_release_file() under the same mutex would + * otherwise be free to unlink and kfree it during + * the unlock window, leaving us to dereference a + * freed slab when we walked to next afterwards. + */ + next = hlist_entry_safe(file->f_list.next, + struct nlm_file, f_list); + if (next) + next->f_count++; + + if (!is_failover_file || is_failover_file(data, file)) { + mutex_unlock(&nlm_file_mutex); + + if (nlm_inspect_file(data, file, match)) + ret = 1; + + mutex_lock(&nlm_file_mutex); + } - mutex_lock(&nlm_file_mutex); file->f_count--; - /* No more references to this file. Let go of it. */ - if (list_empty(&file->f_blocks) && !file->f_locks - && !file->f_shares && !file->f_count) { - hlist_del(&file->f_list); - nlm_close_files(file); - kfree(file); - } + nlm_file_release(file); + file = next; } } mutex_unlock(&nlm_file_mutex); diff --git a/fs/netfs/read_retry.c b/fs/netfs/read_retry.c index 999177426141..f59a70f3a086 100644 --- a/fs/netfs/read_retry.c +++ b/fs/netfs/read_retry.c @@ -175,7 +175,9 @@ static void netfs_retry_read_subrequests(struct netfs_io_request *rreq) list_for_each_entry_safe_from(subreq, tmp, &stream->subrequests, rreq_link) { trace_netfs_sreq(subreq, netfs_sreq_trace_superfluous); + spin_lock(&rreq->lock); list_del(&subreq->rreq_link); + spin_unlock(&rreq->lock); netfs_put_subrequest(subreq, netfs_sreq_trace_put_done); if (subreq == to) break; @@ -203,8 +205,10 @@ static void netfs_retry_read_subrequests(struct netfs_io_request *rreq) refcount_read(&subreq->ref), netfs_sreq_trace_new); + spin_lock(&rreq->lock); list_add(&subreq->rreq_link, &to->rreq_link); - to = list_next_entry(to, rreq_link); + spin_unlock(&rreq->lock); + to = subreq; trace_netfs_sreq(subreq, netfs_sreq_trace_retry); stream->sreq_max_len = umin(len, rreq->rsize); diff --git a/fs/netfs/write_retry.c b/fs/netfs/write_retry.c index 29489a23a220..32735abfa03f 100644 --- a/fs/netfs/write_retry.c +++ b/fs/netfs/write_retry.c @@ -130,7 +130,9 @@ static void netfs_retry_write_stream(struct netfs_io_request *wreq, list_for_each_entry_safe_from(subreq, tmp, &stream->subrequests, rreq_link) { trace_netfs_sreq(subreq, netfs_sreq_trace_discard); + spin_lock(&wreq->lock); list_del(&subreq->rreq_link); + spin_unlock(&wreq->lock); netfs_put_subrequest(subreq, netfs_sreq_trace_put_done); if (subreq == to) break; @@ -153,8 +155,10 @@ static void netfs_retry_write_stream(struct netfs_io_request *wreq, netfs_sreq_trace_new); trace_netfs_sreq(subreq, netfs_sreq_trace_split); + spin_lock(&wreq->lock); list_add(&subreq->rreq_link, &to->rreq_link); - to = list_next_entry(to, rreq_link); + spin_unlock(&wreq->lock); + to = subreq; trace_netfs_sreq(subreq, netfs_sreq_trace_retry); stream->sreq_max_len = len; diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c index 495cace1e564..8f7ed5c1549e 100644 --- a/fs/nfs/nfs4client.c +++ b/fs/nfs/nfs4client.c @@ -1095,20 +1095,22 @@ static int nfs4_server_common_setup(struct nfs_server *server, return error; /* data servers support only a subset of NFSv4.1 */ - if (is_ds_only_client(server->nfs_client)) - return -EPROTONOSUPPORT; + if (is_ds_only_client(server->nfs_client)) { + error = -EPROTONOSUPPORT; + goto out_free_delegation_hash; + } /* We must ensure the session is initialised first */ error = nfs4_init_session(server->nfs_client); if (error < 0) - return error; + goto out_free_delegation_hash; nfs_server_set_init_caps(server); /* Probe the root fh to retrieve its FSID and filehandle */ error = nfs4_get_rootfh(server, mntfh, auth_probe); if (error < 0) - return error; + goto out_free_delegation_hash; dprintk("Server FSID: %llx:%llx\n", (unsigned long long) server->fsid.major, @@ -1117,7 +1119,7 @@ static int nfs4_server_common_setup(struct nfs_server *server, error = nfs_probe_server(server, mntfh); if (error < 0) - return error; + goto out_free_delegation_hash; nfs4_session_limit_rwsize(server); nfs4_session_limit_xasize(server); @@ -1129,6 +1131,11 @@ static int nfs4_server_common_setup(struct nfs_server *server, server->mount_time = jiffies; server->destroy = nfs4_destroy_server; return 0; + +out_free_delegation_hash: + kfree(server->delegation_hash_table); + server->delegation_hash_table = NULL; + return error; } /* diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index f84086437f53..57067589786f 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -1389,7 +1389,7 @@ pnfs_layout_need_return(struct pnfs_layout_hdr *lo) return false; return pnfs_mark_layout_stateid_return(lo, &lo->plh_return_segs, lo->plh_return_iomode, - lo->plh_return_seq) != EBUSY; + lo->plh_return_seq) != -EBUSY; } static void pnfs_layoutreturn_before_put_layout_hdr(struct pnfs_layout_hdr *lo) @@ -2631,6 +2631,7 @@ out_forget: spin_unlock(&ino->i_lock); lseg->pls_layout = lo; NFS_SERVER(ino)->pnfs_curr_ld->free_lseg(lseg); + pnfs_free_lseg_list(&free_me); return ERR_PTR(-EAGAIN); } diff --git a/fs/nfs_common/nfslocalio.c b/fs/nfs_common/nfslocalio.c index dd715cdb6c04..85aa03a7b020 100644 --- a/fs/nfs_common/nfslocalio.c +++ b/fs/nfs_common/nfslocalio.c @@ -292,8 +292,22 @@ struct nfsd_file *nfs_open_local_fh(nfs_uuid_t *uuid, localio = nfs_to->nfsd_open_local_fh(net, uuid->dom, rpc_clnt, cred, nfs_fh, pnf, fmode); if (!IS_ERR(localio) && nfs_uuid_add_file(uuid, nfl) < 0) { - /* Delete the cached file when racing with nfs_uuid_put() */ + /* + * Delete the cached file when racing with nfs_uuid_put(). + * Since nfl->nfs_uuid was never published via + * rcu_assign_pointer(), nfs_close_local_fh() will early-return + * and cannot clean up after us. Drop the slot's file ref and + * its paired net ref, then drop the caller-owned nfsd_file ref + * (+1) and the entry-time nfsd_net ref carried via nf->nf_net, + * and return -ENXIO so the caller never dereferences the + * now-cleared localio. + */ + struct nfsd_file __rcu *tmp = + (struct nfsd_file __force __rcu *)localio; + nfs_to_nfsd_file_put_local(pnf); + nfs_to_nfsd_file_put_local(&tmp); + localio = ERR_PTR(-ENXIO); } nfs_to_nfsd_net_put(net); diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c index a238b6725008..06df1edc8e4b 100644 --- a/fs/nfsd/filecache.c +++ b/fs/nfsd/filecache.c @@ -327,8 +327,11 @@ static void nfsd_file_lru_add(struct nfsd_file *nf) refcount_inc(&nf->nf_ref); if (list_lru_add_obj(&nfsd_file_lru, &nf->nf_lru)) trace_nfsd_file_lru_add(nf); - else - WARN_ON(1); + else { + refcount_dec(&nf->nf_ref); + WARN_ON_ONCE(1); + return; + } nfsd_file_schedule_laundrette(); } @@ -471,11 +474,20 @@ void nfsd_file_net_dispose(struct nfsd_net *nn) for (i = 0; i < 8 && !list_empty(&l->freeme); i++) list_move(l->freeme.next, &dispose); spin_unlock(&l->lock); - if (!list_empty(&l->freeme)) - /* Wake up another thread to share the work + if (!list_empty(&l->freeme)) { + /* + * Wake up another thread to share the work * *before* doing any actual disposing. + * + * The filecache laundrette is shut down after + * the nn->nfsd_serv pointer is cleared, but + * before the svc_serv is freed. */ - svc_wake_up(nn->nfsd_serv); + struct svc_serv *serv = nn->nfsd_serv; + + if (serv) + svc_wake_up(serv); + } nfsd_file_dispose_list(&dispose); } } diff --git a/fs/nfsd/flexfilelayoutxdr.c b/fs/nfsd/flexfilelayoutxdr.c index f9f7e38cba13..374e52d3064a 100644 --- a/fs/nfsd/flexfilelayoutxdr.c +++ b/fs/nfsd/flexfilelayoutxdr.c @@ -30,19 +30,24 @@ nfsd4_ff_encode_layoutget(struct xdr_stream *xdr, struct ff_idmap uid; struct ff_idmap gid; - fh_len = 4 + fl->fh.size; + fh_len = 4 + xdr_align_size(fl->fh.size); uid.len = sprintf(uid.buf, "%u", from_kuid(&init_user_ns, fl->uid)); gid.len = sprintf(gid.buf, "%u", from_kgid(&init_user_ns, fl->gid)); - /* 8 + len for recording the length, name, and padding */ - ds_len = 20 + sizeof(stateid_opaque_t) + 4 + fh_len + - 8 + uid.len + 8 + gid.len; + /* data server entry: deviceid + efficiency + stateid + fh list + + * user + group + flags + stats_collect_hint + */ + ds_len = 16 + 4 + 4 + sizeof(stateid_opaque_t) + 4 + fh_len + + 4 + xdr_align_size(uid.len) + + 4 + xdr_align_size(gid.len) + + 4 + 4; + /* mirror: ds_count + ds */ mirror_len = 4 + ds_len; - /* The layout segment */ - len = 20 + mirror_len; + /* stripe_unit + mirror_count + mirror */ + len = 12 + mirror_len; p = xdr_reserve_space(xdr, sizeof(__be32) + len); if (!p) @@ -94,7 +99,8 @@ nfsd4_ff_encode_getdeviceinfo(struct xdr_stream *xdr, } /* len + padding for two strings */ - addr_len = 16 + da->netaddr.netid_len + da->netaddr.addr_len; + addr_len = 8 + xdr_align_size(da->netaddr.netid_len) + + xdr_align_size(da->netaddr.addr_len); ver_len = 20; len = 4 + ver_len + 4 + addr_len; diff --git a/fs/nfsd/localio.c b/fs/nfsd/localio.c index be710d809a3b..c3eb0557b3e1 100644 --- a/fs/nfsd/localio.c +++ b/fs/nfsd/localio.c @@ -97,11 +97,15 @@ nfsd_open_local_fh(struct net *net, struct auth_domain *dom, } nfsd_file_get(localio); again: + rcu_read_lock(); new = unrcu_pointer(cmpxchg(pnf, NULL, RCU_INITIALIZER(localio))); if (new) { /* Some other thread installed an nfsd_file */ - if (nfsd_file_get(new) == NULL) + if (nfsd_file_get(new) == NULL) { + rcu_read_unlock(); goto again; + } + rcu_read_unlock(); /* * Drop the ref we were going to install (both file and * net) and the one we were going to return (only file). @@ -110,6 +114,8 @@ nfsd_open_local_fh(struct net *net, struct auth_domain *dom, nfsd_net_put(net); nfsd_file_put(localio); localio = new; + } else { + rcu_read_unlock(); } } else nfsd_net_put(net); diff --git a/fs/nfsd/nfs2acl.c b/fs/nfsd/nfs2acl.c index 76305b86c1a9..2998640f259d 100644 --- a/fs/nfsd/nfs2acl.c +++ b/fs/nfsd/nfs2acl.c @@ -115,14 +115,19 @@ static __be32 nfsacld_proc_setacl(struct svc_rqst *rqstp) inode_lock(inode); - error = set_posix_acl(&nop_mnt_idmap, fh->fh_dentry, ACL_TYPE_ACCESS, - argp->acl_access); - if (error) - goto out_drop_lock; - error = set_posix_acl(&nop_mnt_idmap, fh->fh_dentry, ACL_TYPE_DEFAULT, - argp->acl_default); - if (error) - goto out_drop_lock; + error = 0; + if (argp->mask & NFS_ACL) { + error = set_posix_acl(&nop_mnt_idmap, fh->fh_dentry, + ACL_TYPE_ACCESS, argp->acl_access); + if (error) + goto out_drop_lock; + } + if (argp->mask & NFS_DFACL) { + error = set_posix_acl(&nop_mnt_idmap, fh->fh_dentry, + ACL_TYPE_DEFAULT, argp->acl_default); + if (error) + goto out_drop_lock; + } inode_unlock(inode); @@ -248,22 +253,21 @@ nfsaclsvc_encode_getaclres(struct svc_rqst *rqstp, struct xdr_stream *xdr) if (!svcxdr_encode_stat(xdr, resp->status)) return false; - - if (dentry == NULL || d_really_is_negative(dentry)) - return true; - inode = d_inode(dentry); - - if (!svcxdr_encode_fattr(rqstp, xdr, &resp->fh, &resp->stat)) - return false; - if (xdr_stream_encode_u32(xdr, resp->mask) < 0) - return false; - - if (!nfs_stream_encode_acl(xdr, inode, resp->acl_access, - resp->mask & NFS_ACL, 0)) - return false; - if (!nfs_stream_encode_acl(xdr, inode, resp->acl_default, - resp->mask & NFS_DFACL, NFS_ACL_DEFAULT)) - return false; + switch (resp->status) { + case nfs_ok: + inode = d_inode(dentry); + if (!svcxdr_encode_fattr(rqstp, xdr, &resp->fh, &resp->stat)) + return false; + if (xdr_stream_encode_u32(xdr, resp->mask) < 0) + return false; + if (!nfs_stream_encode_acl(xdr, inode, resp->acl_access, + resp->mask & NFS_ACL, 0)) + return false; + if (!nfs_stream_encode_acl(xdr, inode, resp->acl_default, + resp->mask & NFS_DFACL, NFS_ACL_DEFAULT)) + return false; + break; + } return true; } diff --git a/fs/nfsd/nfs3acl.c b/fs/nfsd/nfs3acl.c index e87731380be8..a87f9d7f32be 100644 --- a/fs/nfsd/nfs3acl.c +++ b/fs/nfsd/nfs3acl.c @@ -105,12 +105,17 @@ static __be32 nfsd3_proc_setacl(struct svc_rqst *rqstp) inode_lock(inode); - error = set_posix_acl(&nop_mnt_idmap, fh->fh_dentry, ACL_TYPE_ACCESS, - argp->acl_access); - if (error) - goto out_drop_lock; - error = set_posix_acl(&nop_mnt_idmap, fh->fh_dentry, ACL_TYPE_DEFAULT, - argp->acl_default); + error = 0; + if (argp->mask & NFS_ACL) { + error = set_posix_acl(&nop_mnt_idmap, fh->fh_dentry, + ACL_TYPE_ACCESS, argp->acl_access); + if (error) + goto out_drop_lock; + } + if (argp->mask & NFS_DFACL) { + error = set_posix_acl(&nop_mnt_idmap, fh->fh_dentry, + ACL_TYPE_DEFAULT, argp->acl_default); + } out_drop_lock: inode_unlock(inode); diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c index b6d03e1ef5f7..fbf573c31719 100644 --- a/fs/nfsd/nfs3proc.c +++ b/fs/nfsd/nfs3proc.c @@ -29,6 +29,25 @@ static int nfs3_ftypes[] = { S_IFIFO, /* NF3FIFO */ }; +/* + * Reject a client-supplied atime or mtime whose nanoseconds field is out + * of range. Such a value is well-formed on the wire but is not a valid + * timespec64, and storing it verbatim can corrupt on-disk timestamps. + * tv_nsec is a long, so it is cast to unsigned long (the same width) to + * catch both an over-large value and one that became negative when an + * out-of-range u32 wire nseconds was assigned to a 32-bit long. + */ +static bool nfsd3_time_in_range(const struct iattr *iap) +{ + if ((iap->ia_valid & ATTR_ATIME_SET) && + (unsigned long)iap->ia_atime.tv_nsec >= NSEC_PER_SEC) + return false; + if ((iap->ia_valid & ATTR_MTIME_SET) && + (unsigned long)iap->ia_mtime.tv_nsec >= NSEC_PER_SEC) + return false; + return true; +} + static __be32 nfsd3_map_status(__be32 status) { switch (status) { @@ -101,9 +120,14 @@ nfsd3_proc_setattr(struct svc_rqst *rqstp) SVCFH_fmt(&argp->fh)); fh_copy(&resp->fh, &argp->fh); + if (!nfsd3_time_in_range(&argp->attrs)) { + resp->status = nfserr_inval; + goto out; + } if (argp->check_guard) guardtime = &argp->guardtime; resp->status = nfsd_setattr(rqstp, &resp->fh, &attrs, guardtime); +out: resp->status = nfsd3_map_status(resp->status); return rpc_success; } @@ -265,6 +289,8 @@ nfsd3_create_file(struct svc_rqst *rqstp, struct svc_fh *fhp, trace_nfsd_vfs_create(rqstp, fhp, S_IFREG, argp->name, argp->len); + if (!nfsd3_time_in_range(iap)) + return nfserr_inval; if (isdotent(argp->name, argp->len)) return nfserr_exist; if (!(iap->ia_valid & ATTR_MODE)) @@ -404,8 +430,13 @@ nfsd3_proc_mkdir(struct svc_rqst *rqstp) argp->attrs.ia_valid &= ~ATTR_SIZE; fh_copy(&resp->dirfh, &argp->fh); fh_init(&resp->fh, NFS3_FHSIZE); + if (!nfsd3_time_in_range(&argp->attrs)) { + resp->status = nfserr_inval; + goto out; + } resp->status = nfsd_create(rqstp, &resp->dirfh, argp->name, argp->len, &attrs, S_IFDIR, 0, &resp->fh); +out: resp->status = nfsd3_map_status(resp->status); return rpc_success; } @@ -419,6 +450,10 @@ nfsd3_proc_symlink(struct svc_rqst *rqstp) .na_iattr = &argp->attrs, }; + if (!nfsd3_time_in_range(&argp->attrs)) { + resp->status = nfserr_inval; + goto out; + } if (argp->tlen == 0) { resp->status = nfserr_inval; goto out; @@ -475,6 +510,11 @@ nfsd3_proc_mknod(struct svc_rqst *rqstp) goto out; } + if (!nfsd3_time_in_range(&argp->attrs)) { + resp->status = nfserr_inval; + goto out; + } + type = nfs3_ftypes[argp->ftype]; resp->status = nfsd_create(rqstp, &resp->dirfh, argp->name, argp->len, &attrs, type, rdev, &resp->fh); diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c index e00b2aea8da2..441a55c25148 100644 --- a/fs/nfsd/nfs4callback.c +++ b/fs/nfsd/nfs4callback.c @@ -108,6 +108,8 @@ static int decode_cb_fattr4(struct xdr_stream *xdr, uint32_t *bitmap, if (!xdrgen_decode_fattr4_time_deleg_access(xdr, &access)) return -EIO; + if (access.nseconds >= NSEC_PER_SEC) + return -EIO; fattr->ncf_cb_atime.tv_sec = access.seconds; fattr->ncf_cb_atime.tv_nsec = access.nseconds; @@ -117,6 +119,8 @@ static int decode_cb_fattr4(struct xdr_stream *xdr, uint32_t *bitmap, if (!xdrgen_decode_fattr4_time_deleg_modify(xdr, &modify)) return -EIO; + if (modify.nseconds >= NSEC_PER_SEC) + return -EIO; fattr->ncf_cb_mtime.tv_sec = modify.seconds; fattr->ncf_cb_mtime.tv_nsec = modify.nseconds; @@ -456,13 +460,20 @@ static void encode_cb_sequence4args(struct xdr_stream *xdr, const struct nfsd4_callback *cb, struct nfs4_cb_compound_hdr *hdr) { - struct nfsd4_session *session = cb->cb_clp->cl_cb_session; + struct nfsd4_session *session; struct nfsd4_referring_call_list *rcl; __be32 *p; if (hdr->minorversion == 0) return; + rcu_read_lock(); + session = rcu_dereference(cb->cb_clp->cl_cb_session); + if (!session) { + rcu_read_unlock(); + return; + } + encode_nfs_cb_opnum4(xdr, OP_CB_SEQUENCE); encode_sessionid4(xdr, session); @@ -478,6 +489,7 @@ static void encode_cb_sequence4args(struct xdr_stream *xdr, encode_referring_call_list4(xdr, rcl); hdr->nops++; + rcu_read_unlock(); } static void update_cb_slot_table(struct nfsd4_session *ses, u32 target) @@ -529,21 +541,32 @@ static void update_cb_slot_table(struct nfsd4_session *ses, u32 target) static int decode_cb_sequence4resok(struct xdr_stream *xdr, struct nfsd4_callback *cb) { - struct nfsd4_session *session = cb->cb_clp->cl_cb_session; + struct nfsd4_session *session; int status = -ESERVERFAULT; __be32 *p; u32 seqid, slotid, target; + rcu_read_lock(); + session = rcu_dereference(cb->cb_clp->cl_cb_session); + if (!session) { + rcu_read_unlock(); + cb->cb_seq_status = -NFS4ERR_BADSESSION; + return -NFS4ERR_BADSESSION; + } + /* * If the server returns different values for sessionID, slotID or * sequence number, the server is looney tunes. */ p = xdr_inline_decode(xdr, NFS4_MAX_SESSIONID_LEN + 4 + 4 + 4 + 4); - if (unlikely(p == NULL)) + if (unlikely(p == NULL)) { + rcu_read_unlock(); goto out_overflow; + } if (memcmp(p, session->se_sessionid.data, NFS4_MAX_SESSIONID_LEN)) { dprintk("NFS: %s Invalid session id\n", __func__); + rcu_read_unlock(); goto out; } p += XDR_QUADLEN(NFS4_MAX_SESSIONID_LEN); @@ -551,12 +574,14 @@ static int decode_cb_sequence4resok(struct xdr_stream *xdr, seqid = be32_to_cpup(p++); if (seqid != session->se_cb_seq_nr[cb->cb_held_slot]) { dprintk("NFS: %s Invalid sequence number\n", __func__); + rcu_read_unlock(); goto out; } slotid = be32_to_cpup(p++); if (slotid != cb->cb_held_slot) { dprintk("NFS: %s Invalid slotid\n", __func__); + rcu_read_unlock(); goto out; } @@ -564,6 +589,7 @@ static int decode_cb_sequence4resok(struct xdr_stream *xdr, target = be32_to_cpup(p++); update_cb_slot_table(session, target); + rcu_read_unlock(); status = 0; out: cb->cb_seq_status = status; @@ -1174,9 +1200,8 @@ static int setup_callback_client(struct nfs4_client *clp, struct nfs4_cb_conn *c } else { if (!conn->cb_xprt || !ses) return -EINVAL; - clp->cl_cb_session = ses; args.bc_xprt = conn->cb_xprt; - args.prognumber = clp->cl_cb_session->se_cb_prog; + args.prognumber = ses->se_cb_prog; args.protocol = conn->cb_xprt->xpt_class->xcl_ident | XPRT_TRANSPORT_BC; args.authflavor = ses->se_cb_sec.flavor; @@ -1194,8 +1219,10 @@ static int setup_callback_client(struct nfs4_client *clp, struct nfs4_cb_conn *c return -ENOMEM; } - if (clp->cl_minorversion != 0) + if (clp->cl_minorversion != 0) { clp->cl_cb_conn.cb_xprt = conn->cb_xprt; + rcu_assign_pointer(clp->cl_cb_session, ses); + } clp->cl_cb_client = client; clp->cl_cb_cred = cred; rcu_read_lock(); @@ -1302,18 +1329,33 @@ static int grab_slot(struct nfsd4_session *ses) static bool nfsd41_cb_get_slot(struct nfsd4_callback *cb, struct rpc_task *task) { struct nfs4_client *clp = cb->cb_clp; - struct nfsd4_session *ses = clp->cl_cb_session; + struct nfsd4_session *ses; if (cb->cb_held_slot >= 0) return true; + + rcu_read_lock(); + ses = rcu_dereference(clp->cl_cb_session); + if (!ses) { + rcu_read_unlock(); + rpc_sleep_on(&clp->cl_cb_waitq, task, NULL); + return false; + } cb->cb_held_slot = grab_slot(ses); if (cb->cb_held_slot < 0) { + rcu_read_unlock(); rpc_sleep_on(&clp->cl_cb_waitq, task, NULL); /* Race breaker */ - cb->cb_held_slot = grab_slot(ses); + rcu_read_lock(); + ses = rcu_dereference(clp->cl_cb_session); + if (ses) + cb->cb_held_slot = grab_slot(ses); + rcu_read_unlock(); if (cb->cb_held_slot < 0) return false; rpc_wake_up_queued_task(&clp->cl_cb_waitq, task); + } else { + rcu_read_unlock(); } return true; } @@ -1321,12 +1363,17 @@ static bool nfsd41_cb_get_slot(struct nfsd4_callback *cb, struct rpc_task *task) static void nfsd41_cb_release_slot(struct nfsd4_callback *cb) { struct nfs4_client *clp = cb->cb_clp; - struct nfsd4_session *ses = clp->cl_cb_session; + struct nfsd4_session *ses; if (cb->cb_held_slot >= 0) { - spin_lock(&ses->se_lock); - ses->se_cb_slot_avail |= BIT(cb->cb_held_slot); - spin_unlock(&ses->se_lock); + rcu_read_lock(); + ses = rcu_dereference(clp->cl_cb_session); + if (ses) { + spin_lock(&ses->se_lock); + ses->se_cb_slot_avail |= BIT(cb->cb_held_slot); + spin_unlock(&ses->se_lock); + } + rcu_read_unlock(); cb->cb_held_slot = -1; rpc_wake_up_next(&clp->cl_cb_waitq); } @@ -1458,22 +1505,35 @@ static void nfsd4_cb_prepare(struct rpc_task *task, void *calldata) trace_nfsd_cb_rpc_prepare(clp); cb->cb_seq_status = 1; cb->cb_status = 0; - if (minorversion && !nfsd41_cb_get_slot(cb, task)) - return; + if (minorversion) { + if (!rcu_access_pointer(clp->cl_cb_session)) { + rpc_exit(task, -EIO); + return; + } + if (!nfsd41_cb_get_slot(cb, task)) + return; + } rpc_call_start(task); } /* Returns true if CB_COMPOUND processing should continue */ static bool nfsd4_cb_sequence_done(struct rpc_task *task, struct nfsd4_callback *cb) { - struct nfsd4_session *session = cb->cb_clp->cl_cb_session; + struct nfsd4_session *session; bool ret = false; if (cb->cb_held_slot < 0) goto requeue; + rcu_read_lock(); + session = rcu_dereference(cb->cb_clp->cl_cb_session); + if (!session) { + rcu_read_unlock(); + goto requeue; + } + /* This is the operation status code for CB_SEQUENCE */ - trace_nfsd_cb_seq_status(task, cb); + trace_nfsd_cb_seq_status(task, cb, session); switch (cb->cb_seq_status) { case 0: /* @@ -1505,12 +1565,16 @@ static bool nfsd4_cb_sequence_done(struct rpc_task *task, struct nfsd4_callback fallthrough; case -NFS4ERR_BADSESSION: nfsd4_mark_cb_fault(cb->cb_clp); + rcu_read_unlock(); goto requeue; case -NFS4ERR_DELAY: cb->cb_seq_status = 1; - if (RPC_SIGNALLED(task) || !rpc_restart_call(task)) + if (RPC_SIGNALLED(task) || !rpc_restart_call(task)) { + rcu_read_unlock(); goto requeue; + } rpc_delay(task, 2 * HZ); + rcu_read_unlock(); return false; case -NFS4ERR_SEQ_MISORDERED: case -NFS4ERR_BADSLOT: @@ -1522,11 +1586,13 @@ static bool nfsd4_cb_sequence_done(struct rpc_task *task, struct nfsd4_callback */ nfsd4_mark_cb_fault(cb->cb_clp); cb->cb_held_slot = -1; + rcu_read_unlock(); goto retry_nowait; default: nfsd4_mark_cb_fault(cb->cb_clp); } - trace_nfsd_cb_free_slot(task, cb); + trace_nfsd_cb_free_slot(task, cb, session); + rcu_read_unlock(); nfsd41_cb_release_slot(cb); return ret; retry_nowait: @@ -1648,7 +1714,15 @@ static struct nfsd4_conn * __nfsd4_find_backchannel(struct nfs4_client *clp) * Note there isn't a lot of locking in this code; instead we depend on * the fact that it is run from clp->cl_callback_wq, which won't run two * work items at once. So, for example, clp->cl_callback_wq handles all - * access of cl_cb_client and all calls to rpc_create or rpc_shutdown_client. + * access of cl_cb_client, and all calls to rpc_create or + * rpc_shutdown_client. + * + * cl_cb_session is written only from cl_callback_wq (via + * rcu_assign_pointer) and read from rpciod under rcu_read_lock (via + * rcu_dereference) by encode_cb_sequence4args(), decode_cb_sequence4resok(), + * nfsd4_cb_sequence_done(), and the cb-slot helpers. Sessions are freed + * with kfree_rcu() so that rpciod readers in an RCU read-side critical + * section never dereference a freed session. */ static void nfsd4_process_cb_update(struct nfsd4_callback *cb) { @@ -1700,6 +1774,7 @@ static void nfsd4_process_cb_update(struct nfsd4_callback *cb) nfsd4_mark_cb_down(clp); if (c) svc_xprt_put(c->cn_xprt); + rcu_assign_pointer(clp->cl_cb_session, ses); return; } } diff --git a/fs/nfsd/nfs4layouts.c b/fs/nfsd/nfs4layouts.c index 62762e43f810..2121ef26e7a9 100644 --- a/fs/nfsd/nfs4layouts.c +++ b/fs/nfsd/nfs4layouts.c @@ -249,11 +249,17 @@ nfsd4_alloc_layout_stateid(struct nfsd4_compound_state *cstate, nfsd4_init_cb(&ls->ls_recall, clp, &nfsd4_cb_layout_ops, NFSPROC4_CLNT_CB_LAYOUT); - if (parent->sc_type == SC_TYPE_DELEG) + if (parent->sc_type == SC_TYPE_DELEG) { + spin_lock(&fp->fi_lock); ls->ls_file = nfsd_file_get(fp->fi_deleg_file); - else + spin_unlock(&fp->fi_lock); + } else { ls->ls_file = find_any_file(fp); - BUG_ON(!ls->ls_file); + } + if (!ls->ls_file) { + nfs4_put_stid(stp); + return NULL; + } if (nfsd4_layout_setlease(ls)) { nfs4_put_stid(stp); diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index 98086d217aa2..82f3d379d639 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -1196,7 +1196,7 @@ nfsd4_setattr(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, if (deleg_attrs) { status = nfserr_bad_stateid; - if (st->sc_type & SC_TYPE_DELEG) { + if (st && (st->sc_type & SC_TYPE_DELEG)) { struct nfs4_delegation *dp = delegstateid(st); /* Only for *_ATTRS_DELEG flavors */ @@ -1805,6 +1805,7 @@ static ssize_t _nfsd_copy_file_range(struct nfsd4_copy *copy, /* See RFC 7862 p.67: */ if (bytes_total == 0) bytes_total = ULLONG_MAX; + since = READ_ONCE(dst->f_wb_err); do { /* Only async copies can be stopped here */ if (kthread_should_stop()) @@ -1820,13 +1821,14 @@ static ssize_t _nfsd_copy_file_range(struct nfsd4_copy *copy, } while (bytes_total > 0 && nfsd4_copy_is_async(copy)); /* for a non-zero asynchronous copy do a commit of data */ if (nfsd4_copy_is_async(copy) && copy->cp_res.wr_bytes_written > 0) { - since = READ_ONCE(dst->f_wb_err); end = copy->cp_dst_pos + copy->cp_res.wr_bytes_written - 1; status = vfs_fsync_range(dst, copy->cp_dst_pos, end, 0); if (!status) status = filemap_check_wb_err(dst->f_mapping, since); if (!status) set_bit(NFSD4_COPY_F_COMMITTED, ©->cp_flags); + else if (status != -EAGAIN && status != -ESTALE) + nfsd_reset_write_verifier(copy->cp_nn); } return bytes_copied; } @@ -1985,16 +1987,14 @@ nfsd4_copy(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, } status = nfsd4_setup_inter_ssc(rqstp, cstate, copy); if (status) { - trace_nfsd_copy_done(copy, status); - return nfserr_offload_denied; + status = nfserr_offload_denied; + goto out; } } else { trace_nfsd_copy_intra(copy); status = nfsd4_setup_intra_ssc(rqstp, cstate, copy); - if (status) { - trace_nfsd_copy_done(copy, status); - return status; - } + if (status) + goto out; } memcpy(©->fh, &cstate->current_fh.fh_handle, @@ -2014,11 +2014,12 @@ nfsd4_copy(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, async_copy->cp_src = kmalloc(sizeof(*async_copy->cp_src), GFP_KERNEL); if (!async_copy->cp_src) goto out_dec_async_copy_err; - if (!nfs4_init_copy_state(nn, copy)) + dup_copy_fields(copy, async_copy); + + if (!nfs4_init_copy_state(nn, async_copy)) goto out_dec_async_copy_err; - memcpy(&result->cb_stateid, ©->cp_stateid.cs_stid, + memcpy(&result->cb_stateid, &async_copy->cp_stateid.cs_stid, sizeof(result->cb_stateid)); - dup_copy_fields(copy, async_copy); if ((READ_ONCE(copy->nf_dst->nf_file->f_mode) & FMODE_NOCMTIME) != 0) async_copy->attr_update = true; @@ -2124,7 +2125,6 @@ nfsd4_copy_notify(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); struct nfs4_stid *stid = NULL; struct nfs4_cpntf_state *cps; - struct nfs4_client *clp = cstate->clp; status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh, &cn->cpn_src_stateid, RD_STATE, NULL, @@ -2138,12 +2138,14 @@ nfsd4_copy_notify(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, cn->cpn_lease_time.tv_nsec = 0; status = nfserrno(-ENOMEM); + /* + * The returned cps is published and fully initialized, and carries an + * extra reference for us; drop it once we are done with it. + */ cps = nfs4_alloc_init_cpntf_state(nn, stid); if (!cps) goto out; memcpy(&cn->cpn_cnr_stateid, &cps->cp_stateid.cs_stid, sizeof(stateid_t)); - memcpy(&cps->cp_p_stateid, &stid->sc_stateid, sizeof(stateid_t)); - memcpy(&cps->cp_p_clid, &clp->cl_clientid, sizeof(clientid_t)); /* For now, only return one server address in cpn_src, the * address used by the client to connect to this server. @@ -2152,10 +2154,11 @@ nfsd4_copy_notify(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, status = nfsd4_set_netaddr((struct sockaddr *)&rqstp->rq_daddr, &cn->cpn_src->u.nl4_addr); WARN_ON_ONCE(status); - if (status) { - nfs4_put_cpntf_state(nn, cps); - goto out; - } + /* + * Drop our extra reference. The membership reference keeps the entry + * alive for a later inter-server READ, or until the laundromat reaps it. + */ + nfs4_put_cpntf_state(nn, cps); out: nfs4_put_stid(stid); return status; @@ -2929,9 +2932,22 @@ nfsd4_proc_compound(struct svc_rqst *rqstp) op->status = nfsd4_open_omfg(rqstp, cstate, op); goto encode_op; } - if (!current_fh->fh_dentry && - !HAS_FH_FLAG(current_fh, NFSD4_FH_FOREIGN)) { - if (!(op->opdesc->op_flags & ALLOWED_WITHOUT_FH)) { + if (!current_fh->fh_dentry) { + if (HAS_FH_FLAG(current_fh, NFSD4_FH_FOREIGN)) { + /* + * FOREIGN fh from inter-SSC PUTFH: only + * SAVEFH may proceed with a NULL fh_dentry. + * Per RFC 7862 S15.2.3, validation of a + * foreign fh is deferred to the operation + * that consumes it, and NFS4ERR_STALE is + * returned at that point. + */ + if (op->opnum != OP_SAVEFH && + !(op->opdesc->op_flags & ALLOWED_WITHOUT_FH)) { + op->status = nfserr_stale; + goto encode_op; + } + } else if (!(op->opdesc->op_flags & ALLOWED_WITHOUT_FH)) { op->status = nfserr_nofilehandle; goto encode_op; } @@ -3317,7 +3333,7 @@ static u32 nfsd4_get_dir_delegation_rsize(const struct svc_rqst *rqstp, op_encode_stateid_maxsz + 2 /* gddr_notification */ + 2 /* gddr_child_attributes */ + - 2 /* gddr_dir_attributes */); + 2 /* gddr_dir_attributes */) * sizeof(__be32); } #ifdef CONFIG_NFSD_PNFS diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index c9d9a7d46e7b..48715a55df8f 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -944,7 +944,7 @@ out_free: * Create a unique stateid_t to represent each COPY. */ static int nfs4_init_cp_state(struct nfsd_net *nn, copy_stateid_t *stid, - unsigned char cs_type) + unsigned char cs_type, struct nfs4_stid *p_stid) { int new_id; @@ -954,19 +954,34 @@ static int nfs4_init_cp_state(struct nfsd_net *nn, copy_stateid_t *stid, idr_preload(GFP_KERNEL); spin_lock(&nn->s2s_cp_lock); new_id = idr_alloc_cyclic(&nn->s2s_cp_stateids, stid, 0, 0, GFP_NOWAIT); - stid->cs_stid.si_opaque.so_id = new_id; - stid->cs_stid.si_generation = 1; + if (new_id >= 0) { + stid->cs_stid.si_opaque.so_id = new_id; + stid->cs_stid.si_generation = 1; + /* + * Set cs_type and link onto sc_cp_list under the same lock + * that installed the IDR entry, so a concurrent + * manage_cpntf_state() sees either no entry or a fully + * linked cp_list. + */ + stid->cs_type = cs_type; + if (p_stid) { + struct nfs4_cpntf_state *cps = + container_of(stid, struct nfs4_cpntf_state, + cp_stateid); + + list_add(&cps->cp_list, &p_stid->sc_cp_list); + } + } spin_unlock(&nn->s2s_cp_lock); idr_preload_end(); if (new_id < 0) return 0; - stid->cs_type = cs_type; return 1; } int nfs4_init_copy_state(struct nfsd_net *nn, struct nfsd4_copy *copy) { - return nfs4_init_cp_state(nn, ©->cp_stateid, NFS4_COPY_STID); + return nfs4_init_cp_state(nn, ©->cp_stateid, NFS4_COPY_STID, NULL); } struct nfs4_cpntf_state *nfs4_alloc_init_cpntf_state(struct nfsd_net *nn, @@ -977,13 +992,21 @@ struct nfs4_cpntf_state *nfs4_alloc_init_cpntf_state(struct nfsd_net *nn, cps = kzalloc(sizeof(struct nfs4_cpntf_state), GFP_KERNEL); if (!cps) return NULL; + /* So a stale list_del_init() before linking is a no-op. */ + INIT_LIST_HEAD(&cps->cp_list); cps->cpntf_time = ktime_get_boottime_seconds(); - refcount_set(&cps->cp_stateid.cs_count, 1); - if (!nfs4_init_cp_state(nn, &cps->cp_stateid, NFS4_COPYNOTIFY_STID)) + /* + * Fully initialize the entry before nfs4_init_cp_state() publishes it, + * since a concurrent OFFLOAD_CANCEL could then free it. Take an extra + * reference for the caller (dropped with nfs4_put_cpntf_state()). + */ + memcpy(&cps->cp_p_stateid, &p_stid->sc_stateid, sizeof(stateid_t)); + memcpy(&cps->cp_p_clid, &p_stid->sc_client->cl_clientid, + sizeof(clientid_t)); + refcount_set(&cps->cp_stateid.cs_count, 2); + if (!nfs4_init_cp_state(nn, &cps->cp_stateid, NFS4_COPYNOTIFY_STID, + p_stid)) goto out_free; - spin_lock(&nn->s2s_cp_lock); - list_add(&cps->cp_list, &p_stid->sc_cp_list); - spin_unlock(&nn->s2s_cp_lock); return cps; out_free: kfree(cps); @@ -1003,18 +1026,66 @@ void nfs4_free_copy_state(struct nfsd4_copy *copy) spin_unlock(&nn->s2s_cp_lock); } +/* + * Drop the parent's reference on an already-unlinked cpntf entry. If a + * concurrent holder still owns a reference, its nfs4_put_cpntf_state() does + * the final free. + * + * nn->s2s_cp_lock must be held. + */ +static void put_cpntf_state_unlinked_locked(struct nfs4_cpntf_state *cps) +{ + WARN_ON_ONCE(cps->cp_stateid.cs_type != NFS4_COPYNOTIFY_STID); + WARN_ON_ONCE(!list_empty(&cps->cp_list)); + + if (refcount_dec_and_test(&cps->cp_stateid.cs_count)) + kfree(cps); +} + +/* + * Unhash from the IDR and sc_cp_list. Gated on list_empty() to avoid + * evicting a recycled so_id. + */ +static void nfsd4_unhash_cpntf_state(struct nfsd_net *nn, struct nfs4_cpntf_state *cps) +{ + lockdep_assert_held(&nn->s2s_cp_lock); + + if (!list_empty(&cps->cp_list)) { + list_del_init(&cps->cp_list); + idr_remove(&nn->s2s_cp_stateids, cps->cp_stateid.cs_stid.si_opaque.so_id); + } +} + +/* + * Revoke a copy-notify stateid: unlink it from the IDR and sc_cp_list first + * so no new finder can discover it, then drop the membership reference. Every + * revoke path (cancel, laundromat, drain) must use this rather than + * _free_cpntf_state_locked(), which unlinks only at refcount zero and so could + * let a second revoke free the entry under a concurrent reader. + * + * nn->s2s_cp_lock must be held. + */ +static void revoke_cpntf_state_locked(struct nfsd_net *nn, + struct nfs4_cpntf_state *cps) +{ + nfsd4_unhash_cpntf_state(nn, cps); + put_cpntf_state_unlinked_locked(cps); +} + static void nfs4_free_cpntf_statelist(struct net *net, struct nfs4_stid *stid) { - struct nfs4_cpntf_state *cps; + struct nfs4_cpntf_state *cps, *tmp; struct nfsd_net *nn; nn = net_generic(net, nfsd_net_id); spin_lock(&nn->s2s_cp_lock); - while (!list_empty(&stid->sc_cp_list)) { - cps = list_first_entry(&stid->sc_cp_list, - struct nfs4_cpntf_state, cp_list); - _free_cpntf_state_locked(nn, cps); - } + /* + * Revoke unlinks each entry before dropping the parent's reference, so + * the drain terminates in one pass per entry regardless of cs_count; a + * concurrent holder does the final kfree via nfs4_put_cpntf_state(). + */ + list_for_each_entry_safe(cps, tmp, &stid->sc_cp_list, cp_list) + revoke_cpntf_state_locked(nn, cps); spin_unlock(&nn->s2s_cp_lock); } @@ -2185,7 +2256,7 @@ static void __free_session(struct nfsd4_session *ses) { free_session_slots(ses, 0); xa_destroy(&ses->se_slots); - kfree(ses); + kfree_rcu(ses, rcu_head); } static void free_session(struct nfsd4_session *ses) @@ -2522,14 +2593,24 @@ __destroy_client(struct nfs4_client *clp) release_openowner(oo); } for (i = 0; i < OWNER_HASH_SIZE; i++) { - struct nfs4_stateowner *so, *tmp; + struct nfs4_stateowner *so; - list_for_each_entry_safe(so, tmp, &clp->cl_ownerstr_hashtbl[i], - so_strhash) { + spin_lock(&clp->cl_lock); + while (!list_empty(&clp->cl_ownerstr_hashtbl[i])) { + so = list_first_entry(&clp->cl_ownerstr_hashtbl[i], + struct nfs4_stateowner, so_strhash); /* Should be no openowners at this point */ WARN_ON_ONCE(so->so_is_open_owner); + nfs4_get_stateowner(so); + unhash_lockowner_locked(lockowner(so)); + spin_unlock(&clp->cl_lock); + remove_blocked_locks(lockowner(so)); + nfs4_put_stateowner(so); + + spin_lock(&clp->cl_lock); } + spin_unlock(&clp->cl_lock); } nfsd4_return_all_client_layouts(clp); nfsd4_shutdown_copy(clp); @@ -3292,7 +3373,7 @@ static struct nfs4_client *create_client(struct xdr_netobj name, clp->cl_time = ktime_get_boottime_seconds(); copy_verf(clp, verf); memcpy(&clp->cl_addr, sa, sizeof(struct sockaddr_storage)); - clp->cl_cb_session = NULL; + RCU_INIT_POINTER(clp->cl_cb_session, NULL); clp->net = net; clp->cl_nfsd_dentry = nfsd_client_mkdir( nn, &clp->cl_nfsdfs, @@ -4396,6 +4477,19 @@ static void nfsd4_construct_sequence_response(struct nfsd4_session *session, seq->status_flags |= SEQ4_STATUS_ADMIN_STATE_REVOKED; } +static bool nfsd4_slots_inuse(struct nfsd4_session *ses, int from) +{ + int i; + + for (i = from; i < ses->se_fchannel.maxreqs; i++) { + struct nfsd4_slot *slot = xa_load(&ses->se_slots, i); + + if (slot->sl_flags & NFSD4_SLOT_INUSE) + return true; + } + return false; +} + __be32 nfsd4_sequence(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) @@ -4475,7 +4569,9 @@ nfsd4_sequence(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, if (session->se_target_maxslots < session->se_fchannel.maxreqs && slot->sl_generation == session->se_slot_gen && - seq->maxslots <= session->se_target_maxslots) + seq->maxslots <= session->se_target_maxslots && + seq->slotid < session->se_target_maxslots && + !nfsd4_slots_inuse(session, session->se_target_maxslots)) /* Client acknowledged our reduce maxreqs */ free_session_slots(session, session->se_target_maxslots); @@ -5072,6 +5168,7 @@ static void nfsd4_drop_revoked_stid(struct nfs4_stid *s) case SC_TYPE_DELEG: dp = delegstateid(s); list_del_init(&dp->dl_recall_lru); + s->sc_status |= SC_STATUS_FREED; spin_unlock(&cl->cl_lock); nfs4_put_stid(s); break; @@ -5515,8 +5612,10 @@ static void nfsd_break_one_deleg(struct nfs4_delegation *dp) refcount_inc(&dp->dl_stid.sc_count); queued = nfsd4_run_cb(&dp->dl_recall); WARN_ON_ONCE(!queued); - if (!queued) + if (!queued) { refcount_dec(&dp->dl_stid.sc_count); + clear_bit(NFSD4_CALLBACK_RUNNING, &dp->dl_recall.cb_flags); + } } /* Called from break_lease() with flc_lock held. */ @@ -6738,30 +6837,36 @@ static void nfsd4_ssc_shutdown_umount(struct nfsd_net *nn) static void nfsd4_ssc_expire_umount(struct nfsd_net *nn) { bool do_wakeup = false; - struct nfsd4_ssc_umount_item *ni = NULL; - struct nfsd4_ssc_umount_item *tmp; + struct nfsd4_ssc_umount_item *ni; +restart: spin_lock(&nn->nfsd_ssc_lock); - list_for_each_entry_safe(ni, tmp, &nn->nfsd_ssc_mount_list, nsui_list) { - if (time_after(jiffies, ni->nsui_expire)) { - if (refcount_read(&ni->nsui_refcnt) > 1) - continue; + list_for_each_entry(ni, &nn->nfsd_ssc_mount_list, nsui_list) { + if (!time_after(jiffies, ni->nsui_expire)) + break; + if (refcount_read(&ni->nsui_refcnt) > 1) + continue; - /* mark being unmount */ - ni->nsui_busy = true; - spin_unlock(&nn->nfsd_ssc_lock); - mntput(ni->nsui_vfsmount); - spin_lock(&nn->nfsd_ssc_lock); + /* Prevent concurrent setup during unmount */ + ni->nsui_busy = true; + spin_unlock(&nn->nfsd_ssc_lock); + mntput(ni->nsui_vfsmount); + spin_lock(&nn->nfsd_ssc_lock); - /* waiters need to start from begin of list */ - list_del(&ni->nsui_list); - kfree(ni); + /* Force concurrent scanners to restart */ + list_del(&ni->nsui_list); + kfree(ni); - /* wakeup ssc_connect waiters */ - do_wakeup = true; - continue; - } - break; + /* wakeup ssc_connect waiters */ + do_wakeup = true; + /* + * Concurrent nfsd4_ssc_cancel_dul() can free any item + * on the list under nfsd_ssc_lock while mntput() runs + * above. Restart from the head; the list is short and + * the expire worker is periodic, so this is cheap. + */ + spin_unlock(&nn->nfsd_ssc_lock); + goto restart; } if (do_wakeup) wake_up_all(&nn->nfsd_ssc_waitq); @@ -6911,16 +7016,22 @@ retry: if (atomic_read(&clp->cl_admin_revoked) == 0) continue; + if (is_client_expired(clp)) + continue; spin_lock(&clp->cl_lock); idr_for_each_entry_ul(&clp->cl_stateids, stid, tmp, id) if (stid->sc_status & SC_STATUS_ADMIN_REVOKED) { refcount_inc(&stid->sc_count); + atomic_inc(&clp->cl_rpc_users); spin_unlock(&nn->client_lock); /* this function drops ->cl_lock */ nfsd4_drop_revoked_stid(stid); nfs4_put_stid(stid); spin_lock(&nn->client_lock); + if (atomic_dec_and_test(&clp->cl_rpc_users) && + is_client_expired(clp)) + wake_up_all(&expiry_wq); goto retry; } spin_unlock(&clp->cl_lock); @@ -6955,7 +7066,7 @@ nfs4_laundromat(struct nfsd_net *nn) cps = container_of(cps_t, struct nfs4_cpntf_state, cp_stateid); if (cps->cp_stateid.cs_type == NFS4_COPYNOTIFY_STID && state_expired(<, cps->cpntf_time)) - _free_cpntf_state_locked(nn, cps); + revoke_cpntf_state_locked(nn, cps); } spin_unlock(&nn->s2s_cp_lock); nfsd4_async_copy_reaper(nn); @@ -7074,12 +7185,12 @@ deleg_reaper(struct nfsd_net *nn) continue; if (atomic_read(&clp->cl_delegs_in_recall)) continue; - if (test_and_set_bit(NFSD4_CALLBACK_RUNNING, &clp->cl_ra->ra_cb.cb_flags)) - continue; if (ktime_get_boottime_seconds() - clp->cl_ra_time < 5) continue; if (clp->cl_cb_state != NFSD4_CB_UP) continue; + if (test_and_set_bit(NFSD4_CALLBACK_RUNNING, &clp->cl_ra->ra_cb.cb_flags)) + continue; /* release in nfsd4_cb_recall_any_release */ kref_get(&clp->cl_nfsdfs.cl_ref); @@ -7342,16 +7453,14 @@ nfs4_check_file(struct svc_rqst *rqstp, struct svc_fh *fhp, struct nfs4_stid *s, out: return status; } -static void -_free_cpntf_state_locked(struct nfsd_net *nn, struct nfs4_cpntf_state *cps) + +static void _free_cpntf_state_locked(struct nfsd_net *nn, struct nfs4_cpntf_state *cps) { WARN_ON_ONCE(cps->cp_stateid.cs_type != NFS4_COPYNOTIFY_STID); - if (!refcount_dec_and_test(&cps->cp_stateid.cs_count)) - return; - list_del(&cps->cp_list); - idr_remove(&nn->s2s_cp_stateids, - cps->cp_stateid.cs_stid.si_opaque.so_id); - kfree(cps); + if (refcount_dec_and_test(&cps->cp_stateid.cs_count)) { + nfsd4_unhash_cpntf_state(nn, cps); + kfree(cps); + } } /* * A READ from an inter server to server COPY will have a @@ -7376,10 +7485,20 @@ __be32 manage_cpntf_state(struct nfsd_net *nn, stateid_t *st, state = NULL; goto unlock; } - if (!clp) + if (!clp) { refcount_inc(&state->cp_stateid.cs_count); - else - _free_cpntf_state_locked(nn, state); + } else if (memcmp(&clp->cl_clientid, &state->cp_p_clid, + sizeof(clientid_t))) { + /* + * OFFLOAD_CANCEL: only the creating client may cancel. + * so_id is guessable, so without this check any client + * could free another's cpntf state. + */ + state = NULL; + goto unlock; + } else { + revoke_cpntf_state_locked(nn, state); + } } unlock: spin_unlock(&nn->s2s_cp_lock); @@ -7666,7 +7785,7 @@ retry: return status; stp = openlockstateid(s); if (nfsd4_cstate_assign_replay(cstate, stp->st_stateowner) == -EAGAIN) { - nfs4_put_stateowner(stp->st_stateowner); + nfs4_put_stid(&stp->st_stid); goto retry; } @@ -7914,6 +8033,10 @@ nfsd4_delegreturn(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, if (status) goto put_stateid; + status = nfs4_check_fh(&cstate->current_fh, &dp->dl_stid); + if (status) + goto put_stateid; + trace_nfsd_deleg_return(stateid); destroy_delegation(dp); smp_mb__after_atomic(); @@ -8381,6 +8504,9 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, status = nfserr_no_grace; if (!locks_in_grace(net) && lock->lk_reclaim) goto out; + if (lock->lk_reclaim && + test_bit(NFSD4_CLIENT_RECLAIM_COMPLETE, &cstate->clp->cl_flags)) + goto out; if (lock->lk_reclaim) flags |= FL_RECLAIM; @@ -8417,10 +8543,11 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, goto out; } - if (lock->lk_type & (NFS4_READW_LT | NFS4_WRITEW_LT) && - nfsd4_has_session(cstate) && - locks_can_async_lock(nf->nf_file->f_op)) - flags |= FL_SLEEP; + if ((lock->lk_type == NFS4_READW_LT || + lock->lk_type == NFS4_WRITEW_LT) && + nfsd4_has_session(cstate) && + locks_can_async_lock(nf->nf_file->f_op)) + flags |= FL_SLEEP; nbl = find_or_allocate_block(lock_sop, &fp->fi_fhandle, nn); if (!nbl) { diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 1e158881c1af..9f49e3c9e752 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -526,6 +526,8 @@ nfsd4_decode_fattr4(struct nfsd4_compoundargs *argp, u32 *bmval, u32 bmlen, if (!xdrgen_decode_fattr4_time_deleg_access(argp->xdr, &access)) return nfserr_bad_xdr; + if (access.nseconds >= NSEC_PER_SEC) + return nfserr_inval; iattr->ia_atime.tv_sec = access.seconds; iattr->ia_atime.tv_nsec = access.nseconds; iattr->ia_valid |= ATTR_ATIME | ATTR_ATIME_SET | ATTR_DELEG; @@ -535,6 +537,8 @@ nfsd4_decode_fattr4(struct nfsd4_compoundargs *argp, u32 *bmval, u32 bmlen, if (!xdrgen_decode_fattr4_time_deleg_modify(argp->xdr, &modify)) return nfserr_bad_xdr; + if (modify.nseconds >= NSEC_PER_SEC) + return nfserr_inval; iattr->ia_mtime.tv_sec = modify.seconds; iattr->ia_mtime.tv_nsec = modify.nseconds; iattr->ia_ctime.tv_sec = modify.seconds; @@ -822,6 +826,10 @@ nfsd4_decode_create(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) case NF4LNK: if (xdr_stream_decode_u32(argp->xdr, &create->cr_datalen) < 0) return nfserr_bad_xdr; + if (create->cr_datalen == 0) + return nfserr_inval; + if (create->cr_datalen > NFS4_MAXPATHLEN) + return nfserr_nametoolong; p = xdr_inline_decode(argp->xdr, create->cr_datalen); if (!p) return nfserr_bad_xdr; @@ -1969,6 +1977,7 @@ static __be32 nfsd4_decode_nl4_server(struct nfsd4_compoundargs *argp, { struct nfs42_netaddr *naddr; __be32 *p; + u32 str_len; if (xdr_stream_decode_u32(argp->xdr, &ns->nl4_type) < 0) return nfserr_bad_xdr; @@ -1998,6 +2007,18 @@ static __be32 nfsd4_decode_nl4_server(struct nfsd4_compoundargs *argp, return nfserr_bad_xdr; memcpy(naddr->addr, p, naddr->addr_len); break; + case NL4_NAME: + case NL4_URL: + /* + * Well-formed XDR, but only NL4_NETADDR is supported. Consume + * the utf8str_cis to keep the stream aligned, then return + * NFS4ERR_NOTSUPP rather than the misleading NFS4ERR_BADXDR. + */ + if (xdr_stream_decode_u32(argp->xdr, &str_len) < 0) + return nfserr_bad_xdr; + if (!xdr_inline_decode(argp->xdr, str_len)) + return nfserr_bad_xdr; + return nfserr_notsupp; default: return nfserr_bad_xdr; } @@ -5984,9 +6005,12 @@ void nfsd4_release_compoundargs(struct svc_rqst *rqstp) { struct nfsd4_compoundargs *args = rqstp->rq_argp; + args->opcnt = 0; if (args->ops != args->iops) { - vfree(args->ops); + void *old_ops = args->ops; + args->ops = args->iops; + kvfree_rcu_mightsleep(old_ops); } while (args->to_free) { struct svcxdr_tmpbuf *tb = args->to_free; diff --git a/fs/nfsd/nfscache.c b/fs/nfsd/nfscache.c index ab13ee9c7fd8..ed1748a6d319 100644 --- a/fs/nfsd/nfscache.c +++ b/fs/nfsd/nfscache.c @@ -200,14 +200,14 @@ int nfsd_reply_cache_init(struct nfsd_net *nn) nn->nfsd_reply_cache_shrinker->seeks = 1; nn->nfsd_reply_cache_shrinker->private_data = nn; - shrinker_register(nn->nfsd_reply_cache_shrinker); - for (i = 0; i < hashsize; i++) { INIT_LIST_HEAD(&nn->drc_hashtbl[i].lru_head); spin_lock_init(&nn->drc_hashtbl[i].cache_lock); } nn->drc_hashsize = hashsize; + shrinker_register(nn->nfsd_reply_cache_shrinker); + return 0; out_shrinker: kvfree(nn->drc_hashtbl); @@ -275,7 +275,7 @@ nfsd_prune_bucket_locked(struct nfsd_net *nn, struct nfsd_drc_bucket *b, nfsd_cacherep_unlink_locked(nn, b, rp); list_add(&rp->c_lru, dispose); - if (max && ++freed > max) + if (max && ++freed >= max) break; } } diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index 1da5c40d6722..b3281318cf77 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -1431,7 +1431,7 @@ static int nfsd_genl_rpc_status_compose_msg(struct sk_buff *skb, nla_put_s64(skb, NFSD_A_RPC_STATUS_SERVICE_TIME, ktime_to_us(genl_rqstp->rq_stime), NFSD_A_RPC_STATUS_PAD)) - return -ENOBUFS; + goto out_cancel; switch (genl_rqstp->rq_saddr.sa_family) { case AF_INET: { @@ -1447,7 +1447,7 @@ static int nfsd_genl_rpc_status_compose_msg(struct sk_buff *skb, s_in->sin_port) || nla_put_be16(skb, NFSD_A_RPC_STATUS_DPORT, d_in->sin_port)) - return -ENOBUFS; + goto out_cancel; break; } case AF_INET6: { @@ -1463,7 +1463,7 @@ static int nfsd_genl_rpc_status_compose_msg(struct sk_buff *skb, s_in->sin6_port) || nla_put_be16(skb, NFSD_A_RPC_STATUS_DPORT, d_in->sin6_port)) - return -ENOBUFS; + goto out_cancel; break; } } @@ -1471,10 +1471,14 @@ static int nfsd_genl_rpc_status_compose_msg(struct sk_buff *skb, for (i = 0; i < genl_rqstp->rq_opcnt; i++) if (nla_put_u32(skb, NFSD_A_RPC_STATUS_COMPOUND_OPS, genl_rqstp->rq_opnum[i])) - return -ENOBUFS; + goto out_cancel; genlmsg_end(skb, hdr); return 0; + +out_cancel: + genlmsg_cancel(skb, hdr); + return -ENOBUFS; } /** @@ -1502,10 +1506,20 @@ int nfsd_nl_rpc_status_get_dumpit(struct sk_buff *skb, for (i = 0; i < nn->nfsd_serv->sv_nrpools; i++) { struct svc_rqst *rqstp; + long thread_skip = 0; if (i < cb->args[0]) /* already consumed */ continue; + /* + * The saved thread index only applies to the pool the dump + * was resumed in. Subsequent pools must start from thread 0, + * otherwise their first cb->args[1] threads are silently + * skipped. + */ + if (i == cb->args[0]) + thread_skip = cb->args[1]; + rqstp_index = 0; list_for_each_entry_rcu(rqstp, &nn->nfsd_serv->sv_pools[i].sp_all_threads, @@ -1513,7 +1527,7 @@ int nfsd_nl_rpc_status_get_dumpit(struct sk_buff *skb, struct nfsd_genl_rqstp genl_rqstp; unsigned int status_counter; - if (rqstp_index++ < cb->args[1]) /* already consumed */ + if (rqstp_index++ < thread_skip) /* already consumed */ continue; /* * Acquire rq_status_counter before parsing the rqst @@ -1555,17 +1569,26 @@ int nfsd_nl_rpc_status_get_dumpit(struct sk_buff *skb, #endif /* CONFIG_NFSD_V4 */ /* - * Acquire rq_status_counter before reporting the rqst - * fields to the user. + * Read-side load-load fence: order the field reads + * above before the counter re-read below, mirroring + * the smp_rmb() in the standard seqcount retry. The + * begin-side smp_load_acquire() above pairs with the + * smp_store_release() in nfsd_dispatch(). */ - if (smp_load_acquire(&rqstp->rq_status_counter) != - status_counter) + smp_rmb(); + if (READ_ONCE(rqstp->rq_status_counter) != status_counter) continue; ret = nfsd_genl_rpc_status_compose_msg(skb, cb, &genl_rqstp); - if (ret) + if (ret) { + if (skb->len) { + cb->args[0] = i; + cb->args[1] = rqstp_index - 1; + ret = skb->len; + } goto out; + } } } @@ -1876,6 +1899,60 @@ err_free_msg: } /** + * nfsd_nl_validate_listeners - sanity-check the listener list from userland + * @info: netlink metadata and command arguments + * + * Walk every NFSD_A_SERVER_SOCK_ADDR attribute and confirm that each entry + * is well-formed: it parses against the policy, carries both an address and + * a transport name, and the address is long enough for its family. Doing + * this up front lets the callers below assume every entry is valid and + * guarantees we make no changes when the request is malformed. + * + * Return: 0 if every entry is valid, or a negative errno otherwise. + */ +static int nfsd_nl_validate_listeners(struct genl_info *info) +{ + const struct nlattr *attr; + int rem; + + nlmsg_for_each_attr_type(attr, NFSD_A_SERVER_SOCK_ADDR, info->nlhdr, + GENL_HDRLEN, rem) { + struct nlattr *tb[NFSD_A_SOCK_MAX + 1]; + struct sockaddr *sa; + int err; + + err = nla_parse_nested(tb, NFSD_A_SOCK_MAX, attr, + nfsd_sock_nl_policy, info->extack); + if (err < 0) + return err; + + if (!tb[NFSD_A_SOCK_ADDR] || !tb[NFSD_A_SOCK_TRANSPORT_NAME]) + return -EINVAL; + + sa = nla_data(tb[NFSD_A_SOCK_ADDR]); + if (nla_len(tb[NFSD_A_SOCK_ADDR]) < sizeof(sa->sa_family)) + return -EINVAL; + + switch (sa->sa_family) { + case AF_INET: + if (nla_len(tb[NFSD_A_SOCK_ADDR]) < + sizeof(struct sockaddr_in)) + return -EINVAL; + break; + case AF_INET6: + if (nla_len(tb[NFSD_A_SOCK_ADDR]) < + sizeof(struct sockaddr_in6)) + return -EINVAL; + break; + default: + return -EAFNOSUPPORT; + } + } + + return 0; +} + +/** * nfsd_nl_listener_set_doit - set the nfs running sockets * @skb: reply buffer * @info: netlink metadata and command arguments @@ -1893,6 +1970,15 @@ int nfsd_nl_listener_set_doit(struct sk_buff *skb, struct genl_info *info) bool delete = false; int err, rem; + /* + * Validate the entire listener list before making any changes, so a + * malformed request fails cleanly without creating a serv or touching + * the existing listeners. + */ + err = nfsd_nl_validate_listeners(info); + if (err) + return err; + mutex_lock(&nfsd_mutex); err = nfsd_create_serv(net); @@ -1919,16 +2005,11 @@ int nfsd_nl_listener_set_doit(struct sk_buff *skb, struct genl_info *info) const char *xcl_name; struct sockaddr *sa; + /* validated up front in nfsd_nl_validate_listeners() */ if (nla_parse_nested(tb, NFSD_A_SOCK_MAX, attr, nfsd_sock_nl_policy, info->extack) < 0) continue; - if (!tb[NFSD_A_SOCK_ADDR] || !tb[NFSD_A_SOCK_TRANSPORT_NAME]) - continue; - - if (nla_len(tb[NFSD_A_SOCK_ADDR]) < sizeof(*sa)) - continue; - xcl_name = nla_data(tb[NFSD_A_SOCK_TRANSPORT_NAME]); sa = nla_data(tb[NFSD_A_SOCK_ADDR]); @@ -1980,16 +2061,11 @@ int nfsd_nl_listener_set_doit(struct sk_buff *skb, struct genl_info *info) struct sockaddr *sa; int ret; + /* validated up front in nfsd_nl_validate_listeners() */ if (nla_parse_nested(tb, NFSD_A_SOCK_MAX, attr, nfsd_sock_nl_policy, info->extack) < 0) continue; - if (!tb[NFSD_A_SOCK_ADDR] || !tb[NFSD_A_SOCK_TRANSPORT_NAME]) - continue; - - if (nla_len(tb[NFSD_A_SOCK_ADDR]) < sizeof(*sa)) - continue; - xcl_name = nla_data(tb[NFSD_A_SOCK_TRANSPORT_NAME]); sa = nla_data(tb[NFSD_A_SOCK_ADDR]); @@ -2250,11 +2326,12 @@ static int __init init_nfsd(void) { int retval; - nfsd_debugfs_init(); - retval = nfsd4_init_slabs(); if (retval) return retval; + + nfsd_debugfs_init(); + retval = nfsd4_init_pnfs(); if (retval) goto out_free_slabs; @@ -2299,8 +2376,8 @@ out_free_lockd: out_free_pnfs: nfsd4_exit_pnfs(); out_free_slabs: - nfsd4_free_slabs(); nfsd_debugfs_exit(); + nfsd4_free_slabs(); return retval; } @@ -2315,9 +2392,9 @@ static void __exit exit_nfsd(void) unregister_pernet_subsys(&nfsd_net_ops); nfsd_drc_slab_free(); nfsd_lockd_shutdown(); - nfsd4_free_slabs(); nfsd4_exit_pnfs(); nfsd_debugfs_exit(); + nfsd4_free_slabs(); } MODULE_AUTHOR("Olaf Kirch <okir@monad.swb.de>"); diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c index ed85dd43da18..3ab4b1b6e235 100644 --- a/fs/nfsd/nfsfh.c +++ b/fs/nfsd/nfsfh.c @@ -69,10 +69,8 @@ nfsd_mode_check(struct dentry *dentry, umode_t requested) if (requested == 0) /* the caller doesn't care */ return nfs_ok; if (mode == requested) { - if (mode == S_IFDIR && !d_can_lookup(dentry)) { - WARN_ON_ONCE(1); + if (mode == S_IFDIR && !d_can_lookup(dentry)) return nfserr_notdir; - } return nfs_ok; } if (mode == S_IFLNK) { @@ -279,15 +277,19 @@ static __be32 nfsd_set_fh_dentry(struct svc_rqst *rqstp, struct net *net, if (dentry->d_sb->s_export_op->flags & EXPORT_OP_NOWCC) fhp->fh_no_wcc = true; fhp->fh_64bit_cookies = true; - if (exp->ex_flags & NFSEXP_V4ROOT) + if (exp->ex_flags & NFSEXP_V4ROOT) { + dput(dentry); goto out; + } break; case NFS_FHSIZE: fhp->fh_no_wcc = true; if (EX_WGATHER(exp)) fhp->fh_use_wgather = true; - if (exp->ex_flags & NFSEXP_V4ROOT) + if (exp->ex_flags & NFSEXP_V4ROOT) { + dput(dentry); goto out; + } } fhp->fh_dentry = dentry; diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c index 906a67257890..35f409b65552 100644 --- a/fs/nfsd/nfsproc.c +++ b/fs/nfsd/nfsproc.c @@ -82,6 +82,7 @@ nfsd_proc_setattr(struct svc_rqst *rqstp) .na_iattr = iap, }; struct svc_fh *fhp; + int hosterr; dprintk("nfsd: SETATTR %s, valid=%x, size=%ld\n", SVCFH_fmt(&argp->fh), @@ -117,6 +118,12 @@ nfsd_proc_setattr(struct svc_rqst *rqstp) if (resp->status != nfs_ok) goto out; + hosterr = fh_want_write(fhp); + if (hosterr) { + resp->status = nfserrno(hosterr); + goto out; + } + if (delta < 0) delta = -delta; if (delta < MAX_TOUCH_TIME_ERROR && diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index fcb47f344e32..242b8c7b6e0f 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -835,7 +835,7 @@ nfsd_acl_init_request(struct svc_rqst *rqstp, ret->mismatch.lovers = NFSD_ACL_NRVERS; for (i = NFSD_ACL_MINVERS; i < NFSD_ACL_NRVERS; i++) { - if (nfsd_support_acl_version(rqstp->rq_vers) && + if (nfsd_support_acl_version(i) && nfsd_vers(nn, i, NFSD_TEST)) { ret->mismatch.lovers = i; break; @@ -845,7 +845,7 @@ nfsd_acl_init_request(struct svc_rqst *rqstp, return rpc_prog_unavail; ret->mismatch.hivers = NFSD_ACL_MINVERS; for (i = NFSD_ACL_NRVERS - 1; i >= NFSD_ACL_MINVERS; i--) { - if (nfsd_support_acl_version(rqstp->rq_vers) && + if (nfsd_support_acl_version(i) && nfsd_vers(nn, i, NFSD_TEST)) { ret->mismatch.hivers = i; break; diff --git a/fs/nfsd/nfsxdr.c b/fs/nfsd/nfsxdr.c index fc262ceafca9..e7e309594f84 100644 --- a/fs/nfsd/nfsxdr.c +++ b/fs/nfsd/nfsxdr.c @@ -10,6 +10,16 @@ #include "auth.h" /* + * Sun convention: a sattr time-useconds field of one full second (an + * otherwise out-of-range value) means "set this time to the current + * server time." It's needed to make permissions checks for the "touch" + * program across NFSv2 mounts work correctly. See description of + * sattr in section 6.1 of "NFS Illustrated" by Brent Callaghan, + * Addison-Wesley, ISBN 0-201-32750-5 + */ +#define NFS2_SATTR_SET_TO_SERVER_TIME (1000000) + +/* * Mapping of S_IF* types to NFS file types */ static const u32 nfs_ftypes[] = { @@ -172,27 +182,29 @@ svcxdr_decode_sattr(struct svc_rqst *rqstp, struct xdr_stream *xdr, tmp1 = be32_to_cpup(p++); tmp2 = be32_to_cpup(p++); if (tmp1 != (u32)-1 && tmp2 != (u32)-1) { + /* + * Range test here to prevent the multiplication from + * wrapping to a valid (but incorrect) value on 32-bit + * platforms. + */ + if (tmp2 > NFS2_SATTR_SET_TO_SERVER_TIME) + return false; iap->ia_valid |= ATTR_ATIME | ATTR_ATIME_SET; iap->ia_atime.tv_sec = tmp1; iap->ia_atime.tv_nsec = tmp2 * NSEC_PER_USEC; + if (tmp2 == NFS2_SATTR_SET_TO_SERVER_TIME) + iap->ia_valid &= ~ATTR_ATIME_SET; } tmp1 = be32_to_cpup(p++); tmp2 = be32_to_cpup(p++); if (tmp1 != (u32)-1 && tmp2 != (u32)-1) { + if (tmp2 > NFS2_SATTR_SET_TO_SERVER_TIME) + return false; iap->ia_valid |= ATTR_MTIME | ATTR_MTIME_SET; iap->ia_mtime.tv_sec = tmp1; iap->ia_mtime.tv_nsec = tmp2 * NSEC_PER_USEC; - /* - * Passing the invalid value useconds=1000000 for mtime - * is a Sun convention for "set both mtime and atime to - * current server time". It's needed to make permissions - * checks for the "touch" program across v2 mounts to - * Solaris and Irix boxes work correctly. See description of - * sattr in section 6.1 of "NFS Illustrated" by - * Brent Callaghan, Addison-Wesley, ISBN 0-201-32750-5 - */ - if (tmp2 == 1000000) + if (tmp2 == NFS2_SATTR_SET_TO_SERVER_TIME) iap->ia_valid &= ~(ATTR_ATIME_SET|ATTR_MTIME_SET); } diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h index 2eed2c5b3cd0..ea414f3adad5 100644 --- a/fs/nfsd/state.h +++ b/fs/nfsd/state.h @@ -383,6 +383,7 @@ struct nfsd4_session { u16 se_slot_gen; bool se_dead; u32 se_target_maxslots; + struct rcu_head rcu_head; }; /* formatted contents of nfs4_sessionid */ @@ -494,7 +495,7 @@ struct nfs4_client { #define NFSD4_CB_FAULT 3 int cl_cb_state; struct nfsd4_callback cl_cb_null; - struct nfsd4_session *cl_cb_session; + struct nfsd4_session __rcu *cl_cb_session; /* for all client information that callback code might need: */ spinlock_t cl_lock; diff --git a/fs/nfsd/trace.h b/fs/nfsd/trace.h index 6e2c8e2aab10..ba48d3963e9f 100644 --- a/fs/nfsd/trace.h +++ b/fs/nfsd/trace.h @@ -236,7 +236,7 @@ TRACE_EVENT_CONDITION(nfsd_fh_verify, TP_CONDITION(rqstp != NULL), TP_STRUCT__entry( __field(unsigned int, netns_ino) - __sockaddr(server, rqstp->rq_xprt->xpt_remotelen) + __sockaddr(server, rqstp->rq_xprt->xpt_locallen) __sockaddr(client, rqstp->rq_xprt->xpt_remotelen) __field(u32, xid) __field(u32, fh_hash) @@ -275,7 +275,7 @@ TRACE_EVENT_CONDITION(nfsd_fh_verify_err, TP_CONDITION(rqstp != NULL && error), TP_STRUCT__entry( __field(unsigned int, netns_ino) - __sockaddr(server, rqstp->rq_xprt->xpt_remotelen) + __sockaddr(server, rqstp->rq_xprt->xpt_locallen) __sockaddr(client, rqstp->rq_xprt->xpt_remotelen) __field(u32, xid) __field(u32, fh_hash) @@ -1688,9 +1688,10 @@ DEFINE_NFSD_CB_LIFETIME_EVENT(bc_shutdown); TRACE_EVENT(nfsd_cb_seq_status, TP_PROTO( const struct rpc_task *task, - const struct nfsd4_callback *cb + const struct nfsd4_callback *cb, + const struct nfsd4_session *session ), - TP_ARGS(task, cb), + TP_ARGS(task, cb, session), TP_STRUCT__entry( __field(unsigned int, task_id) __field(unsigned int, client_id) @@ -1702,8 +1703,6 @@ TRACE_EVENT(nfsd_cb_seq_status, __field(int, seq_status) ), TP_fast_assign( - const struct nfs4_client *clp = cb->cb_clp; - const struct nfsd4_session *session = clp->cl_cb_session; const struct nfsd4_sessionid *sid = (struct nfsd4_sessionid *)&session->se_sessionid; @@ -1729,9 +1728,10 @@ TRACE_EVENT(nfsd_cb_seq_status, TRACE_EVENT(nfsd_cb_free_slot, TP_PROTO( const struct rpc_task *task, - const struct nfsd4_callback *cb + const struct nfsd4_callback *cb, + const struct nfsd4_session *session ), - TP_ARGS(task, cb), + TP_ARGS(task, cb, session), TP_STRUCT__entry( __field(unsigned int, task_id) __field(unsigned int, client_id) @@ -1742,8 +1742,6 @@ TRACE_EVENT(nfsd_cb_free_slot, __field(u32, slot_seqno) ), TP_fast_assign( - const struct nfs4_client *clp = cb->cb_clp; - const struct nfsd4_session *session = clp->cl_cb_session; const struct nfsd4_sessionid *sid = (struct nfsd4_sessionid *)&session->se_sessionid; diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index ba882a4ea9cb..53b55ee4e00e 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -136,8 +136,10 @@ nfsd_cross_mnt(struct svc_rqst *rqstp, struct dentry **dpp, follow_flags = LOOKUP_AUTOMOUNT; err = follow_down(&path, follow_flags); - if (err < 0) + if (err < 0) { + path_put(&path); goto out; + } if (path.mnt == exp->ex_path.mnt && path.dentry == dentry && nfsd_mountpoint(dentry, exp) == 2) { /* This is only a mountpoint in some other namespace */ @@ -418,21 +420,22 @@ nfsd_sanitize_attrs(struct inode *inode, struct iattr *iap) } static __be32 -nfsd_get_write_access(struct svc_rqst *rqstp, struct svc_fh *fhp, - struct iattr *iap) +nfsd_may_truncate(struct svc_rqst *rqstp, struct svc_fh *fhp, + struct iattr *iap) { struct inode *inode = d_inode(fhp->fh_dentry); - if (iap->ia_size < inode->i_size) { - __be32 err; + if (iap->ia_size >= i_size_read(inode)) + return nfs_ok; - err = nfsd_permission(&rqstp->rq_cred, - fhp->fh_export, fhp->fh_dentry, - NFSD_MAY_TRUNC | NFSD_MAY_OWNER_OVERRIDE); - if (err) - return err; - } - return nfserrno(get_write_access(inode)); + return nfsd_permission(&rqstp->rq_cred, fhp->fh_export, fhp->fh_dentry, + NFSD_MAY_TRUNC | NFSD_MAY_OWNER_OVERRIDE); +} + +static __be32 +nfsd_get_write_access(struct svc_fh *fhp) +{ + return nfserrno(get_write_access(d_inode(fhp->fh_dentry))); } static int __nfsd_setattr(struct dentry *dentry, struct iattr *iap) @@ -559,12 +562,17 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, * setattr call. */ if (size_change) { - err = nfsd_get_write_access(rqstp, fhp, iap); + err = nfsd_get_write_access(fhp); if (err) return err; } inode_lock(inode); + if (size_change) { + err = nfsd_may_truncate(rqstp, fhp, iap); + if (err) + goto out_unlock; + } err = fh_fill_pre_attrs(fhp); if (err) goto out_unlock; diff --git a/fs/nilfs2/bmap.c b/fs/nilfs2/bmap.c index ccc1a7aa52d2..efa01f5b35df 100644 --- a/fs/nilfs2/bmap.c +++ b/fs/nilfs2/bmap.c @@ -175,7 +175,7 @@ static int nilfs_bmap_do_delete(struct nilfs_bmap *bmap, __u64 key) return ret; } - return bmap->b_ops->bop_delete(bmap, key); + return bmap->b_ops->bop_delete(bmap, key, false); } /** diff --git a/fs/nilfs2/bmap.h b/fs/nilfs2/bmap.h index 4656df392722..a72f3c308a5d 100644 --- a/fs/nilfs2/bmap.h +++ b/fs/nilfs2/bmap.h @@ -63,7 +63,7 @@ struct nilfs_bmap_operations { int (*bop_lookup_contig)(const struct nilfs_bmap *, __u64, __u64 *, unsigned int); int (*bop_insert)(struct nilfs_bmap *, __u64, __u64); - int (*bop_delete)(struct nilfs_bmap *, __u64); + int (*bop_delete)(struct nilfs_bmap *bmap, __u64 key, bool deform); void (*bop_clear)(struct nilfs_bmap *); int (*bop_propagate)(struct nilfs_bmap *, struct buffer_head *); diff --git a/fs/nilfs2/btree.c b/fs/nilfs2/btree.c index dd0c8e560ef6..a47ee0ad57f7 100644 --- a/fs/nilfs2/btree.c +++ b/fs/nilfs2/btree.c @@ -1425,6 +1425,28 @@ static void nilfs_btree_shrink(struct nilfs_bmap *btree, path[level].bp_bh = NULL; } +/** + * nilfs_btree_discard - discard the last node for the mapping transformation + * @btree: bmap struct of btree + * @path: array of nilfs_btree_path struct + * @level: level of the B-tree node being operated on + * @keyp: argument for passing a key (unused) + * @ptrp: argument for passing a pointer (unused) + */ +static void nilfs_btree_discard(struct nilfs_bmap *btree, + struct nilfs_btree_path *path, int level, + __u64 *keyp, __u64 *ptrp) +{ + struct nilfs_btree_node *root = nilfs_btree_get_root(btree); + + nilfs_btree_node_delete(root, 0, NULL, NULL, + NILFS_BTREE_ROOT_NCHILDREN_MAX); + nilfs_btree_node_set_level(root, level); + + nilfs_btnode_delete(path[level].bp_bh); + path[level].bp_bh = NULL; +} + static void nilfs_btree_nop(struct nilfs_bmap *btree, struct nilfs_btree_path *path, int level, __u64 *keyp, __u64 *ptrp) @@ -1435,7 +1457,7 @@ static int nilfs_btree_prepare_delete(struct nilfs_bmap *btree, struct nilfs_btree_path *path, int *levelp, struct nilfs_bmap_stats *stats, - struct inode *dat) + struct inode *dat, bool deform) { struct buffer_head *bh; struct nilfs_btree_node *node, *parent, *sib; @@ -1522,15 +1544,17 @@ static int nilfs_btree_prepare_delete(struct nilfs_bmap *btree, if (nilfs_btree_node_get_nchildren(node) - 1 <= NILFS_BTREE_ROOT_NCHILDREN_MAX) { path[level].bp_op = nilfs_btree_shrink; - stats->bs_nblocks += 2; - level++; - path[level].bp_op = nilfs_btree_nop; - goto shrink_root_child; + } else if (deform) { + path[level].bp_op = nilfs_btree_discard; } else { path[level].bp_op = nilfs_btree_do_delete; stats->bs_nblocks++; goto out; } + stats->bs_nblocks += 2; + level++; + path[level].bp_op = nilfs_btree_nop; + goto shrink_root_child; } } @@ -1581,7 +1605,7 @@ static void nilfs_btree_commit_delete(struct nilfs_bmap *btree, nilfs_bmap_set_dirty(btree); } -static int nilfs_btree_delete(struct nilfs_bmap *btree, __u64 key) +static int nilfs_btree_delete(struct nilfs_bmap *btree, __u64 key, bool deform) { struct nilfs_btree_path *path; @@ -1601,7 +1625,8 @@ static int nilfs_btree_delete(struct nilfs_bmap *btree, __u64 key) dat = NILFS_BMAP_USE_VBN(btree) ? nilfs_bmap_get_dat(btree) : NULL; - ret = nilfs_btree_prepare_delete(btree, path, &level, &stats, dat); + ret = nilfs_btree_prepare_delete(btree, path, &level, &stats, dat, + deform); if (ret < 0) goto out; nilfs_btree_commit_delete(btree, path, level, dat); diff --git a/fs/nilfs2/direct.c b/fs/nilfs2/direct.c index 2d8dc6b35b54..834ce02f2afb 100644 --- a/fs/nilfs2/direct.c +++ b/fs/nilfs2/direct.c @@ -144,7 +144,7 @@ static int nilfs_direct_insert(struct nilfs_bmap *bmap, __u64 key, __u64 ptr) return ret; } -static int nilfs_direct_delete(struct nilfs_bmap *bmap, __u64 key) +static int nilfs_direct_delete(struct nilfs_bmap *bmap, __u64 key, bool deform) { union nilfs_bmap_ptr_req req; struct inode *dat; @@ -234,7 +234,7 @@ int nilfs_direct_delete_and_convert(struct nilfs_bmap *bmap, /* no need to allocate any resource for conversion */ /* delete */ - ret = bmap->b_ops->bop_delete(bmap, key); + ret = bmap->b_ops->bop_delete(bmap, key, true); if (ret < 0) return ret; diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c index bfe884d624e7..cf57eabfed45 100644 --- a/fs/notify/fanotify/fanotify.c +++ b/fs/notify/fanotify/fanotify.c @@ -602,8 +602,7 @@ static struct fanotify_event *fanotify_alloc_perm_event(const void *data, pevent->hdr.len = 0; pevent->state = FAN_EVENT_INIT; pevent->path = *path; - /* NULL ppos means no range info */ - pevent->ppos = range ? &range->pos : NULL; + pevent->pos = range ? range->pos : FANOTIFY_NO_RANGE; pevent->count = range ? range->count : 0; path_get(path); diff --git a/fs/notify/fanotify/fanotify.h b/fs/notify/fanotify/fanotify.h index 39e60218df7c..eb2ba71d5c81 100644 --- a/fs/notify/fanotify/fanotify.h +++ b/fs/notify/fanotify/fanotify.h @@ -427,6 +427,8 @@ FANOTIFY_ME(struct fanotify_event *event) return container_of(event, struct fanotify_mnt_event, fae); } +#define FANOTIFY_NO_RANGE ((loff_t)-1) + /* * Structure for permission fanotify events. It gets allocated and freed in * fanotify_handle_event() since we wait there for user response. When the @@ -437,7 +439,7 @@ FANOTIFY_ME(struct fanotify_event *event) struct fanotify_perm_event { struct fanotify_event fae; struct path path; - const loff_t *ppos; /* optional file range info */ + loff_t pos; /* FANOTIFY_NO_RANGE if unavailable */ size_t count; u32 response; /* userspace answer to the event */ unsigned short state; /* state of the event */ @@ -467,7 +469,7 @@ static inline bool fanotify_event_has_access_range(struct fanotify_event *event) if (!(event->mask & FANOTIFY_PRE_CONTENT_EVENTS)) return false; - return FANOTIFY_PERM(event)->ppos; + return FANOTIFY_PERM(event)->pos != FANOTIFY_NO_RANGE; } static inline struct fanotify_event *FANOTIFY_E(struct fsnotify_event *fse) diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index 5c30f4d8c7c1..c1ce663952c8 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -674,12 +674,9 @@ static size_t copy_range_info_to_user(struct fanotify_event *event, if (WARN_ON_ONCE(info_len > count)) return -EFAULT; - if (WARN_ON_ONCE(!pevent->ppos)) - return -EINVAL; - info.hdr.info_type = FAN_EVENT_INFO_TYPE_RANGE; info.hdr.len = info_len; - info.offset = *(pevent->ppos); + info.offset = pevent->pos; info.count = pevent->count; if (copy_to_user(buf, &info, info_len)) diff --git a/fs/nsfs.c b/fs/nsfs.c index e2f9a725883c..4dee1e728569 100644 --- a/fs/nsfs.c +++ b/fs/nsfs.c @@ -566,7 +566,7 @@ static struct dentry *nsfs_fh_to_dentry(struct super_block *sb, struct fid *fh, return ERR_PTR(-EOPNOTSUPP); } - if (owning_ns && !ns_capable(owning_ns, CAP_SYS_ADMIN)) { + if (owning_ns && !may_see_all_namespaces()) { ns->ops->put(ns); return ERR_PTR(-EPERM); } diff --git a/fs/ntfs3/frecord.c b/fs/ntfs3/frecord.c index e904c5da9192..3a458975181c 100644 --- a/fs/ntfs3/frecord.c +++ b/fs/ntfs3/frecord.c @@ -2652,6 +2652,15 @@ int ni_read_frame(struct ntfs_inode *ni, u64 frame_vbo, struct page **pages, err = unc_size; else if (!unc_size || unc_size > frame_size) err = -EINVAL; + else if (unc_size < frame_size) { + /* + * Partial decompress: zero the [unc_size, frame_size) + * tail. decompress_lznt() leaves it untouched, so + * without this the freshly vmapped pages would expose + * uninitialized kernel memory to userspace. + */ + memset(frame_mem + unc_size, 0, frame_size - unc_size); + } } if (!err && valid_size < frame_vbo + frame_size) { size_t ok = valid_size - frame_vbo; diff --git a/fs/ntfs3/fslog.c b/fs/ntfs3/fslog.c index a0503a334423..5437dc78209e 100644 --- a/fs/ntfs3/fslog.c +++ b/fs/ntfs3/fslog.c @@ -648,6 +648,14 @@ static inline void *enum_rstbl(struct RESTART_TABLE *t, void *c) } /* + * dp_range_ok - true if [j, j + count) fits in a page_lcns[cap] array. + */ +static inline bool dp_range_ok(size_t j, u32 count, u32 cap) +{ + return j < cap && count <= cap - j; +} + +/* * find_dp - Search for a @vcn in Dirty Page Table. */ static inline struct DIR_PAGE_ENTRY *find_dp(struct RESTART_TABLE *dptbl, @@ -789,6 +797,20 @@ static bool check_rstbl(const struct RESTART_TABLE *rt, size_t bytes) return true; } +static bool check_dp_table(const struct RESTART_TABLE *dptbl) +{ + u32 rsize = le16_to_cpu(dptbl->size); + struct DIR_PAGE_ENTRY *dp = NULL; + + while ((dp = enum_rstbl((struct RESTART_TABLE *)dptbl, dp))) { + if (struct_size(dp, page_lcns, le32_to_cpu(dp->lcns_follow)) > + rsize) + return false; + } + + return true; +} + /* * free_rsttbl_idx - Free a previously allocated index a Restart Table. */ @@ -4280,6 +4302,11 @@ check_dirty_page_table: goto out; } + if (!check_dp_table(rt)) { + err = -EINVAL; + goto out; + } + dptbl = kmemdup(rt, t32, GFP_NOFS); if (!dptbl) { err = -ENOMEM; @@ -5072,6 +5099,13 @@ find_dirty_page: /* Shorten length by any Lcns which were deleted. */ saved_len = dlen; + if (!dp_range_ok(le64_to_cpu(lrh->target_vcn) - le64_to_cpu(dp->vcn), + le16_to_cpu(lrh->lcns_follow), + le32_to_cpu(dp->lcns_follow))) { + err = -EINVAL; + goto out; + } + for (i = le16_to_cpu(lrh->lcns_follow); i; i--) { size_t j; u32 alen, voff; diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c index 724350925aff..798d76f479d0 100644 --- a/fs/ocfs2/cluster/heartbeat.c +++ b/fs/ocfs2/cluster/heartbeat.c @@ -43,6 +43,14 @@ static DECLARE_RWSEM(o2hb_callback_sem); * whenever any of the threads sees activity from the node in its region. */ static DEFINE_SPINLOCK(o2hb_live_lock); +/* + * Serializes region pin/unpin dependency management (o2hb_dependent_users + * and the o2nm_depend_item()/o2nm_undepend_item() calls). o2hb_region_pin() + * has to drop o2hb_live_lock across the sleeping o2nm_depend_item(), so the + * spinlock alone can no longer keep pin and unpin mutually exclusive; this + * mutex, taken outside o2hb_live_lock, does. + */ +static DEFINE_MUTEX(o2hb_dependency_mutex); static struct list_head o2hb_live_slots[O2NM_MAX_NODES]; static unsigned long o2hb_live_node_bitmap[BITS_TO_LONGS(O2NM_MAX_NODES)]; static LIST_HEAD(o2hb_node_events); @@ -138,7 +146,7 @@ static unsigned int o2hb_dependent_users; * In global heartbeat mode, we pin/unpin all o2hb regions. This solution * works for both file system and userdlm domains. */ -static int o2hb_region_pin(const char *region_uuid); +static int o2hb_region_pin(const char *region_uuid, bool from_callback); static void o2hb_region_unpin(const char *region_uuid); /* Only sets a new threshold if there are no active regions. @@ -2115,6 +2123,7 @@ static void o2hb_heartbeat_group_drop_item(struct config_group *group, * If global heartbeat active and there are dependent users, * pin all regions if quorum region count <= CUT_OFF */ + mutex_lock(&o2hb_dependency_mutex); spin_lock(&o2hb_live_lock); if (!o2hb_dependent_users) @@ -2122,10 +2131,11 @@ static void o2hb_heartbeat_group_drop_item(struct config_group *group, if (bitmap_weight(o2hb_quorum_region_bitmap, O2NM_MAX_REGIONS) <= O2HB_PIN_CUT_OFF) - o2hb_region_pin(NULL); + o2hb_region_pin(NULL, true); unlock: spin_unlock(&o2hb_live_lock); + mutex_unlock(&o2hb_dependency_mutex); } static ssize_t o2hb_heartbeat_group_dead_threshold_show(struct config_item *item, @@ -2263,48 +2273,113 @@ EXPORT_SYMBOL_GPL(o2hb_setup_callback); * In local, we only pin the matching region. In global we pin all the active * regions. */ -static int o2hb_region_pin(const char *region_uuid) +static int o2hb_region_pin(const char *region_uuid, bool from_callback) { - int ret = 0, found = 0; - struct o2hb_region *reg; + int ret = 0, found; + struct o2hb_region *reg, *pinned; char *uuid; assert_spin_locked(&o2hb_live_lock); - list_for_each_entry(reg, &o2hb_all_regions, hr_all_item) { - if (reg->hr_item_dropped) - continue; + do { + found = 0; + pinned = NULL; - uuid = config_item_name(®->hr_item); + list_for_each_entry(reg, &o2hb_all_regions, hr_all_item) { + if (reg->hr_item_dropped) + continue; - /* local heartbeat */ - if (region_uuid) { - if (strcmp(region_uuid, uuid)) + uuid = config_item_name(®->hr_item); + + /* local heartbeat */ + if (region_uuid) { + if (strcmp(region_uuid, uuid)) + continue; + found = 1; + } + + if (reg->hr_item_pinned || reg->hr_item_dropped) { + if (found) + break; continue; - found = 1; + } + + /* + * Found a region that needs pinning. Take a reference + * so it stays alive while we drop the lock below. + */ + pinned = reg; + config_item_get(®->hr_item); + break; } - if (reg->hr_item_pinned || reg->hr_item_dropped) - goto skip_pin; + if (!pinned) + break; + + uuid = config_item_name(&pinned->hr_item); + + /* + * o2nm_depend_item() -> configfs_depend_item() can sleep (it + * takes the configfs root inode rwsem), so it must not run + * under o2hb_live_lock. Drop the lock across it; @pinned is + * kept alive by the reference taken above. The region list may + * change while unlocked, so we rescan from the top afterwards. + */ + spin_unlock(&o2hb_live_lock); /* Ignore ENOENT only for local hb (userdlm domain) */ - ret = o2nm_depend_item(®->hr_item); + if (from_callback) + ret = o2nm_depend_item_unlocked(&pinned->hr_item); + else + ret = o2nm_depend_item(&pinned->hr_item); + + spin_lock(&o2hb_live_lock); if (!ret) { - mlog(ML_CLUSTER, "Pin region %s\n", uuid); - reg->hr_item_pinned = 1; - } else { - if (ret == -ENOENT && found) - ret = 0; - else { - mlog(ML_ERROR, "Pin region %s fails with %d\n", - uuid, ret); + /* + * o2hb_live_lock was dropped across o2nm_depend_item(). + * o2hb_set_quorum_device() runs in the heartbeat thread + * without o2hb_dependency_mutex, so for global heartbeat + * it may have crossed O2HB_PIN_CUT_OFF and unpinned the + * regions while we slept. If that happened this pin is + * no longer wanted; undo it and stop rather than + * resurrecting it on the rescan below. + */ + if (!region_uuid && + bitmap_weight(o2hb_quorum_region_bitmap, + O2NM_MAX_REGIONS) > O2HB_PIN_CUT_OFF) { + o2nm_undepend_item(&pinned->hr_item); + spin_unlock(&o2hb_live_lock); + config_item_put(&pinned->hr_item); + spin_lock(&o2hb_live_lock); break; } + mlog(ML_CLUSTER, "Pin region %s\n", uuid); + pinned->hr_item_pinned = 1; + } else if (ret == -ENOENT && (found || !region_uuid)) { + /* + * For local hb (found): ignore ENOENT from userdlm + * domains as before. For global hb (!region_uuid): + * the region may have been detached from configfs + * while the lock was dropped — skip it and continue + * pinning the remaining regions. + */ + ret = 0; + } else { + mlog(ML_ERROR, "Pin region %s fails with %d\n", + uuid, ret); } -skip_pin: - if (found) - break; - } + + /* + * config_item_put() may drop the last reference and run + * o2hb_region_release(), which also grabs o2hb_live_lock and + * can sleep, so it must happen with the lock released. + */ + spin_unlock(&o2hb_live_lock); + config_item_put(&pinned->hr_item); + spin_lock(&o2hb_live_lock); + + /* local hb pins a single matching region */ + } while (!ret && !region_uuid); return ret; } @@ -2349,12 +2424,13 @@ static int o2hb_region_inc_user(const char *region_uuid) { int ret = 0; + mutex_lock(&o2hb_dependency_mutex); spin_lock(&o2hb_live_lock); /* local heartbeat */ if (!o2hb_global_heartbeat_active()) { - ret = o2hb_region_pin(region_uuid); - goto unlock; + ret = o2hb_region_pin(region_uuid, false); + goto unlock; } /* @@ -2366,16 +2442,23 @@ static int o2hb_region_inc_user(const char *region_uuid) goto unlock; if (bitmap_weight(o2hb_quorum_region_bitmap, - O2NM_MAX_REGIONS) <= O2HB_PIN_CUT_OFF) - ret = o2hb_region_pin(NULL); + O2NM_MAX_REGIONS) <= O2HB_PIN_CUT_OFF) { + ret = o2hb_region_pin(NULL, false); + if (ret) { + o2hb_region_unpin(NULL); + o2hb_dependent_users--; + } + } unlock: spin_unlock(&o2hb_live_lock); + mutex_unlock(&o2hb_dependency_mutex); return ret; } static void o2hb_region_dec_user(const char *region_uuid) { + mutex_lock(&o2hb_dependency_mutex); spin_lock(&o2hb_live_lock); /* local heartbeat */ @@ -2394,6 +2477,7 @@ static void o2hb_region_dec_user(const char *region_uuid) unlock: spin_unlock(&o2hb_live_lock); + mutex_unlock(&o2hb_dependency_mutex); } int o2hb_register_callback(const char *region_uuid, diff --git a/fs/ocfs2/cluster/nodemanager.c b/fs/ocfs2/cluster/nodemanager.c index 2f61d39e4e50..5fffbed779da 100644 --- a/fs/ocfs2/cluster/nodemanager.c +++ b/fs/ocfs2/cluster/nodemanager.c @@ -776,6 +776,12 @@ int o2nm_depend_item(struct config_item *item) return configfs_depend_item(&o2nm_cluster_group.cs_subsys, item); } +int o2nm_depend_item_unlocked(struct config_item *item) +{ + return configfs_depend_item_unlocked(&o2nm_cluster_group.cs_subsys, + item); +} + void o2nm_undepend_item(struct config_item *item) { configfs_undepend_item(item); diff --git a/fs/ocfs2/cluster/nodemanager.h b/fs/ocfs2/cluster/nodemanager.h index 3490e77a952d..2f72f56996bd 100644 --- a/fs/ocfs2/cluster/nodemanager.h +++ b/fs/ocfs2/cluster/nodemanager.h @@ -64,6 +64,7 @@ void o2nm_node_get(struct o2nm_node *node); void o2nm_node_put(struct o2nm_node *node); int o2nm_depend_item(struct config_item *item); +int o2nm_depend_item_unlocked(struct config_item *item); void o2nm_undepend_item(struct config_item *item); int o2nm_depend_this_node(void); void o2nm_undepend_this_node(void); diff --git a/fs/ocfs2/dir.c b/fs/ocfs2/dir.c index 8c9c4825f984..c0fec28e62c8 100644 --- a/fs/ocfs2/dir.c +++ b/fs/ocfs2/dir.c @@ -1888,7 +1888,7 @@ static int ocfs2_dir_foreach_blk_el(struct inode *inode, i += le16_to_cpu(de->rec_len); } offset = i; - ctx->pos = (ctx->pos & ~(sb->s_blocksize - 1)) + ctx->pos = (ctx->pos & ~((loff_t)sb->s_blocksize - 1)) | offset; *f_version = inode_query_iversion(inode); } diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c index 4145e06d2c08..4ab8c48582b1 100644 --- a/fs/ocfs2/dlm/dlmmaster.c +++ b/fs/ocfs2/dlm/dlmmaster.c @@ -3101,6 +3101,12 @@ int dlm_migrate_request_handler(struct o2net_msg *msg, u32 len, void *data, name = migrate->name; namelen = migrate->namelen; + if (namelen > DLM_LOCKID_NAME_MAX) { + mlog(ML_ERROR, "%s: invalid name length %u in migrate request\n", + dlm->name, namelen); + ret = -EINVAL; + goto leave; + } hash = dlm_lockid_hash(name, namelen); /* preallocate.. if this fails, abort */ diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c index 843ee02bd85f..2379225f0ee6 100644 --- a/fs/ocfs2/dlm/dlmrecovery.c +++ b/fs/ocfs2/dlm/dlmrecovery.c @@ -1357,6 +1357,15 @@ int dlm_mig_lockres_handler(struct o2net_msg *msg, u32 len, void *data, if (!dlm_grab(dlm)) return -EINVAL; + if (mres->lockname_len > DLM_LOCKID_NAME_MAX || + mres->num_locks > DLM_MAX_MIGRATABLE_LOCKS || + be16_to_cpu(msg->data_len) < struct_size(mres, ml, mres->num_locks)) { + mlog(ML_ERROR, "%s: invalid lockres migration message from %u\n", + dlm->name, mres->master); + dlm_put(dlm); + return -EINVAL; + } + if (!dlm_joined(dlm)) { mlog(ML_ERROR, "Domain %s not joined! " "lockres %.*s, master %u\n", diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c index 267b50e8e42e..54a030e6779d 100644 --- a/fs/ocfs2/refcounttree.c +++ b/fs/ocfs2/refcounttree.c @@ -116,6 +116,33 @@ static int ocfs2_validate_refcount_block(struct super_block *sb, le32_to_cpu(rb->rf_fs_generation)); goto out; } + + /* + * rf_records (rl_count/rl_used/rl_recs[]) is only meaningful when + * this block is not an interior tree block (OCFS2_REFCOUNT_TREE_FL); + * in that case the same union bytes hold an extent list (rf_list) + * instead, which is validated by ocfs2_validate_extent_block(). + */ + if (!(le32_to_cpu(rb->rf_flags) & OCFS2_REFCOUNT_TREE_FL)) { + if (le16_to_cpu(rb->rf_records.rl_count) != + ocfs2_refcount_recs_per_rb(sb)) { + rc = ocfs2_error(sb, + "Refcount block #%llu has an invalid rl_count of %u\n", + (unsigned long long)bh->b_blocknr, + le16_to_cpu(rb->rf_records.rl_count)); + goto out; + } + + if (le16_to_cpu(rb->rf_records.rl_used) > + le16_to_cpu(rb->rf_records.rl_count)) { + rc = ocfs2_error(sb, + "Refcount block #%llu has an invalid rl_used of %u (rl_count %u)\n", + (unsigned long long)bh->b_blocknr, + le16_to_cpu(rb->rf_records.rl_used), + le16_to_cpu(rb->rf_records.rl_count)); + goto out; + } + } out: return rc; } @@ -3355,10 +3382,9 @@ static int ocfs2_replace_cow(struct ocfs2_cow_context *context) cow_start += num_clusters; } - if (ocfs2_dealloc_has_cluster(&context->dealloc)) { + if (ocfs2_dealloc_has_cluster(&context->dealloc)) ocfs2_schedule_truncate_log_flush(osb, 1); - ocfs2_run_deallocs(osb, &context->dealloc); - } + ocfs2_run_deallocs(osb, &context->dealloc); return ret; } @@ -3841,10 +3867,9 @@ unlock: ocfs2_unlock_refcount_tree(osb, ref_tree, 1); brelse(ref_root_bh); - if (!ret && ocfs2_dealloc_has_cluster(&dealloc)) { + if (!ret && ocfs2_dealloc_has_cluster(&dealloc)) ocfs2_schedule_truncate_log_flush(osb, 1); - ocfs2_run_deallocs(osb, &dealloc); - } + ocfs2_run_deallocs(osb, &dealloc); out: /* * Empty the extent map so that we may get the right extent @@ -4130,10 +4155,9 @@ out_unlock_refcount: ocfs2_unlock_refcount_tree(osb, ref_tree, 1); brelse(ref_root_bh); out: - if (ocfs2_dealloc_has_cluster(&dealloc)) { + if (ocfs2_dealloc_has_cluster(&dealloc)) ocfs2_schedule_truncate_log_flush(osb, 1); - ocfs2_run_deallocs(osb, &dealloc); - } + ocfs2_run_deallocs(osb, &dealloc); return ret; } @@ -4686,10 +4710,9 @@ loff_t ocfs2_reflink_remap_blocks(struct inode *s_inode, } out: - if (ocfs2_dealloc_has_cluster(&dealloc)) { + if (ocfs2_dealloc_has_cluster(&dealloc)) ocfs2_schedule_truncate_log_flush(osb, 1); - ocfs2_run_deallocs(osb, &dealloc); - } + ocfs2_run_deallocs(osb, &dealloc); return ret; } diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c index fa49a768b0a1..cd9c8d4dd9f7 100644 --- a/fs/ocfs2/xattr.c +++ b/fs/ocfs2/xattr.c @@ -7187,10 +7187,9 @@ out_unlock: ref_tree, 1); brelse(ref_root_bh); - if (ocfs2_dealloc_has_cluster(&dealloc)) { + if (ocfs2_dealloc_has_cluster(&dealloc)) ocfs2_schedule_truncate_log_flush(OCFS2_SB(old_inode->i_sb), 1); - ocfs2_run_deallocs(OCFS2_SB(old_inode->i_sb), &dealloc); - } + ocfs2_run_deallocs(OCFS2_SB(old_inode->i_sb), &dealloc); out: return ret; diff --git a/fs/orangefs/devorangefs-req.c b/fs/orangefs/devorangefs-req.c index 33ee8cb32f83..e5c60da7e677 100644 --- a/fs/orangefs/devorangefs-req.c +++ b/fs/orangefs/devorangefs-req.c @@ -474,6 +474,7 @@ static ssize_t orangefs_devreq_write_iter(struct kiocb *iocb, op->downcall.trailer_size, iter)) { gossip_err("%s: failed to copy trailer.\n", __func__); vfree(op->downcall.trailer_buf); + op->downcall.trailer_buf = NULL; goto Efault; } diff --git a/fs/orangefs/orangefs-debugfs.c b/fs/orangefs/orangefs-debugfs.c index 79267b3419f2..4b7e6c52d4a3 100644 --- a/fs/orangefs/orangefs-debugfs.c +++ b/fs/orangefs/orangefs-debugfs.c @@ -569,6 +569,7 @@ static int orangefs_prepare_cdm_array(char *debug_array_string) cds_delimiter = strchr(cds_head, '\n'); *cds_delimiter = '\0'; + cds_head = skip_spaces(cds_head); keyword_len = strcspn(cds_head, " "); cdm_array[i].keyword = kzalloc(keyword_len + 1, GFP_KERNEL); diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 6dc16295e307..5c3d966b70f2 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -1073,10 +1073,12 @@ static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr, bool present = false; struct folio *folio; + if (pmd_none(*pmd)) + return; if (pmd_present(*pmd)) { page = vm_normal_page_pmd(vma, addr, *pmd); present = true; - } else if (unlikely(thp_migration_supported() && is_swap_pmd(*pmd))) { + } else if (unlikely(thp_migration_supported())) { swp_entry_t entry = pmd_to_swp_entry(*pmd); if (is_pfn_swap_entry(entry)) @@ -2004,6 +2006,9 @@ static int pagemap_pmd_range_thp(pmd_t *pmdp, unsigned long addr, if (vma->vm_flags & VM_SOFTDIRTY) flags |= PM_SOFT_DIRTY; + if (pmd_none(pmd)) + goto populate_pagemap; + if (pmd_present(pmd)) { page = pmd_page(pmd); @@ -2014,7 +2019,7 @@ static int pagemap_pmd_range_thp(pmd_t *pmdp, unsigned long addr, flags |= PM_UFFD_WP; if (pm->show_pfn) frame = pmd_pfn(pmd) + idx; - } else if (thp_migration_supported() && is_swap_pmd(pmd)) { + } else if (thp_migration_supported()) { swp_entry_t entry = pmd_to_swp_entry(pmd); unsigned long offset; @@ -2041,6 +2046,7 @@ static int pagemap_pmd_range_thp(pmd_t *pmdp, unsigned long addr, flags |= PM_FILE; } +populate_pagemap: for (; addr != end; addr += PAGE_SIZE, idx++) { u64 cur_flags = flags; pagemap_entry_t pme; @@ -2411,6 +2417,9 @@ static unsigned long pagemap_thp_category(struct pagemap_scan_private *p, { unsigned long categories = PAGE_IS_HUGE; + if (pmd_none(pmd)) + return categories; + if (pmd_present(pmd)) { struct page *page; @@ -2428,7 +2437,7 @@ static unsigned long pagemap_thp_category(struct pagemap_scan_private *p, categories |= PAGE_IS_PFNZERO; if (pmd_soft_dirty(pmd)) categories |= PAGE_IS_SOFT_DIRTY; - } else if (is_swap_pmd(pmd)) { + } else { swp_entry_t swp; categories |= PAGE_IS_SWAPPED; diff --git a/fs/smb/client/cifsfs.c b/fs/smb/client/cifsfs.c index 9059c2efbcc0..5ad6a9b3bb56 100644 --- a/fs/smb/client/cifsfs.c +++ b/fs/smb/client/cifsfs.c @@ -1364,8 +1364,19 @@ static loff_t cifs_remap_file_range(struct file *src_file, loff_t off, */ lock_two_nondirectories(target_inode, src_inode); - if (len == 0) - len = src_inode->i_size - off; + if (len == 0) { + loff_t src_size = i_size_read(src_inode); + + if (off > src_size) { + rc = -EINVAL; + goto unlock; + } + len = src_size - off; + if (!len) { + rc = 0; + goto unlock; + } + } cifs_dbg(FYI, "clone range\n"); diff --git a/fs/smb/client/dfs_cache.c b/fs/smb/client/dfs_cache.c index f2ad0ccd08a7..9072b5e80122 100644 --- a/fs/smb/client/dfs_cache.c +++ b/fs/smb/client/dfs_cache.c @@ -122,6 +122,8 @@ static inline void free_tgts(struct cache_entry *ce) kfree(t->name); kfree(t); } + + WRITE_ONCE(ce->tgthint, NULL); } static inline void flush_cache_ent(struct cache_entry *ce) @@ -869,13 +871,22 @@ int dfs_cache_find(const unsigned int xid, struct cifs_ses *ses, const struct nl goto out_free_path; } - if (ref) - rc = setup_referral(path, ce, ref, get_tgt_name(ce)); - else + if (ref) { + char *target = get_tgt_name(ce); + + if (IS_ERR(target)) { + rc = PTR_ERR(target); + goto out_unlock; + } + rc = setup_referral(path, ce, ref, target); + } else { rc = 0; + } + if (!rc && tgt_list) rc = get_targets(ce, tgt_list); +out_unlock: up_read(&htable_rw_lock); out_free_path: @@ -915,10 +926,17 @@ int dfs_cache_noreq_find(const char *path, struct dfs_info3_param *ref, goto out_unlock; } - if (ref) - rc = setup_referral(path, ce, ref, get_tgt_name(ce)); - else + if (ref) { + char *target = get_tgt_name(ce); + + if (IS_ERR(target)) { + rc = PTR_ERR(target); + goto out_unlock; + } + rc = setup_referral(path, ce, ref, target); + } else { rc = 0; + } if (!rc && tgt_list) rc = get_targets(ce, tgt_list); @@ -959,7 +977,8 @@ void dfs_cache_noreq_update_tgthint(const char *path, const struct dfs_cache_tgt t = READ_ONCE(ce->tgthint); - if (unlikely(!strcasecmp(it->it_name, t->name))) + /* Check 't' in case ce->tgthint was cleared by free_tgts() */ + if (t && unlikely(!strcasecmp(it->it_name, t->name))) goto out_unlock; list_for_each_entry(t, &ce->tlist, list) { diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c index a34457d5143e..2914b751970c 100644 --- a/fs/smb/client/file.c +++ b/fs/smb/client/file.c @@ -994,6 +994,7 @@ static int cifs_do_truncate(const unsigned int xid, struct dentry *dentry) if (!rc) { netfs_resize_file(&cinode->netfs, 0, true); cifs_setsize(inode, 0); + cifs_invalidate_cache(inode, 0); } } if (cfile) diff --git a/fs/smb/client/inode.c b/fs/smb/client/inode.c index c9e955d0d799..4ce3def36843 100644 --- a/fs/smb/client/inode.c +++ b/fs/smb/client/inode.c @@ -3080,6 +3080,7 @@ int cifs_file_set_size(const unsigned int xid, struct dentry *dentry, size, false); cifs_dbg(FYI, "%s: set_file_size: rc = %d\n", __func__, rc); cifsFileInfo_put(open_file); + tcon = NULL; } } diff --git a/fs/smb/client/smb1ops.c b/fs/smb/client/smb1ops.c index ca8f3dd7ff63..848e06c51009 100644 --- a/fs/smb/client/smb1ops.c +++ b/fs/smb/client/smb1ops.c @@ -727,7 +727,7 @@ static int cifs_query_path_info(const unsigned int xid, ea->ea_value_length = cpu_to_le16(SMB2_WSL_XATTR_DEV_SIZE); memcpy(&ea->ea_data[0], SMB2_WSL_XATTR_DEV, SMB2_WSL_XATTR_NAME_LEN + 1); data->wsl.eas_len += ALIGN(sizeof(*ea) + SMB2_WSL_XATTR_NAME_LEN + 1 + - SMB2_WSL_XATTR_MODE_SIZE, 4); + SMB2_WSL_XATTR_DEV_SIZE, 4); rc = 0; } else if (rc >= 0) { /* It is an error if EA $LXDEV has wrong size. */ diff --git a/fs/smb/client/smb2file.c b/fs/smb/client/smb2file.c index 9bab3c57b3a4..8110f4e3f0a4 100644 --- a/fs/smb/client/smb2file.c +++ b/fs/smb/client/smb2file.c @@ -61,7 +61,10 @@ static struct smb2_symlink_err_rsp *symlink_data(const struct kvec *iov) cifs_dbg(FYI, "%s: skipping unhandled error context: 0x%x\n", __func__, le32_to_cpu(p->ErrorId)); - len = ALIGN(le32_to_cpu(p->ErrorDataLength), 8); + len = le32_to_cpu(p->ErrorDataLength); + if (len > end - ((u8 *)p + sizeof(*p))) + return ERR_PTR(-EINVAL); + len = ALIGN(len, 8); if (len > end - ((u8 *)p + sizeof(*p))) return ERR_PTR(-EINVAL); diff --git a/fs/tracefs/event_inode.c b/fs/tracefs/event_inode.c index ad182f9fbb48..a7b082a665bd 100644 --- a/fs/tracefs/event_inode.c +++ b/fs/tracefs/event_inode.c @@ -436,6 +436,8 @@ static inline struct eventfs_inode *init_ei(struct eventfs_inode *ei, const char if (!ei->name) return NULL; kref_init(&ei->kref); + INIT_LIST_HEAD(&ei->children); + INIT_LIST_HEAD(&ei->list); return ei; } @@ -727,8 +729,6 @@ struct eventfs_inode *eventfs_create_dir(const char *name, struct eventfs_inode ei->entries = entries; ei->nr_entries = size; ei->data = data; - INIT_LIST_HEAD(&ei->children); - INIT_LIST_HEAD(&ei->list); mutex_lock(&eventfs_mutex); if (!parent->is_freed) @@ -801,9 +801,6 @@ struct eventfs_inode *eventfs_create_events_dir(const char *name, struct dentry ei->attr.uid = uid; ei->attr.gid = gid; - INIT_LIST_HEAD(&ei->children); - INIT_LIST_HEAD(&ei->list); - ti = get_tracefs(inode); ti->flags |= TRACEFS_EVENT_INODE; ti->private = ei; diff --git a/fs/ubifs/auth.c b/fs/ubifs/auth.c index a4a0158f712d..1f770795ee70 100644 --- a/fs/ubifs/auth.c +++ b/fs/ubifs/auth.c @@ -217,7 +217,7 @@ int ubifs_sb_verify_signature(struct ubifs_info *c, signode = snod->node; - if (le32_to_cpu(signode->len) > snod->len + sizeof(struct ubifs_sig_node)) { + if (le32_to_cpu(signode->len) > snod->len - sizeof(struct ubifs_sig_node)) { ubifs_err(c, "invalid signature len %d", le32_to_cpu(signode->len)); err = -EINVAL; goto out_destroy; diff --git a/fs/udf/inode.c b/fs/udf/inode.c index a79d73f28aa7..3a184ded12ad 100644 --- a/fs/udf/inode.c +++ b/fs/udf/inode.c @@ -532,7 +532,7 @@ static int udf_do_extend_file(struct inode *inode, sb->s_blocksize - 1) & ~(sb->s_blocksize - 1)); iinfo->i_lenExtents = (iinfo->i_lenExtents + sb->s_blocksize - 1) & - ~(sb->s_blocksize - 1); + ~((u64)sb->s_blocksize - 1); } add = 0; diff --git a/fs/udf/partition.c b/fs/udf/partition.c index 2b85c9501bed..ad8dcedca263 100644 --- a/fs/udf/partition.c +++ b/fs/udf/partition.c @@ -55,7 +55,7 @@ uint32_t udf_get_pblock_virt15(struct super_block *sb, uint32_t block, map = &sbi->s_partmaps[partition]; vdata = &map->s_type_specific.s_virtual; - if (block > vdata->s_num_entries) { + if (block >= vdata->s_num_entries) { udf_debug("Trying to access block beyond end of VAT (%u max %u)\n", block, vdata->s_num_entries); return 0xFFFFFFFF; diff --git a/include/linux/compaction.h b/include/linux/compaction.h index 173d9c07a895..ff2d5fb29161 100644 --- a/include/linux/compaction.h +++ b/include/linux/compaction.h @@ -56,6 +56,7 @@ enum compact_result { }; struct alloc_context; /* in mm/internal.h */ +struct capture_control; /* in mm/internal.h */ /* * Number of free order-0 pages that should be available above given watermark @@ -92,7 +93,7 @@ extern int fragmentation_index(struct zone *zone, unsigned int order); extern enum compact_result try_to_compact_pages(gfp_t gfp_mask, unsigned int order, unsigned int alloc_flags, const struct alloc_context *ac, enum compact_priority prio, - struct page **page); + struct capture_control *capc); extern void reset_isolation_suitable(pg_data_t *pgdat); extern bool compaction_suitable(struct zone *zone, int order, unsigned long watermark, int highest_zoneidx); diff --git a/include/linux/dm-io.h b/include/linux/dm-io.h index 7b2968612b7e..674683894064 100644 --- a/include/linux/dm-io.h +++ b/include/linux/dm-io.h @@ -27,7 +27,7 @@ struct page_list { struct page *page; }; -typedef void (*io_notify_fn)(unsigned int long error, void *context); +typedef void (*io_notify_fn)(unsigned long int error, unsigned long int unsup, void *context); enum dm_io_mem_type { DM_IO_PAGE_LIST,/* Page list */ @@ -80,8 +80,8 @@ void dm_io_client_destroy(struct dm_io_client *client); * error occurred doing io to the corresponding region. */ int dm_io(struct dm_io_request *io_req, unsigned int num_regions, - struct dm_io_region *region, unsigned int long *sync_error_bits, - unsigned short ioprio); + struct dm_io_region *region, unsigned long int *sync_error_bits, + unsigned long int *sync_unsup_bits, unsigned short ioprio); #endif /* __KERNEL__ */ #endif /* _LINUX_DM_IO_H */ diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index a3f6cdf8a2b6..d09604498fa4 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -1277,6 +1277,8 @@ static inline void hugetlb_count_sub(long l, struct mm_struct *mm) { } +pte_t huge_ptep_get(struct mm_struct *mm, unsigned long addr, pte_t *ptep); + static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { diff --git a/include/linux/list.h b/include/linux/list.h index 00ea8e5fb88b..0121e2f88f89 100644 --- a/include/linux/list.h +++ b/include/linux/list.h @@ -150,10 +150,13 @@ static inline bool __list_del_entry_valid(struct list_head *entry) * * This is only for internal list manipulation where we know * the prev/next entries already! + * + * Must be inlined to ensure it can be safely called + * with initdata arguments. */ -static inline void __list_add(struct list_head *new, - struct list_head *prev, - struct list_head *next) +static __always_inline void __list_add(struct list_head *new, + struct list_head *prev, + struct list_head *next) { if (!__list_add_valid(new, prev, next)) return; @@ -171,8 +174,12 @@ static inline void __list_add(struct list_head *new, * * Insert a new entry after the specified head. * This is good for implementing stacks. + * + * Must be inlined to ensure it can be safely called + * with initdata arguments. */ -static inline void list_add(struct list_head *new, struct list_head *head) +static __always_inline void list_add(struct list_head *new, + struct list_head *head) { __list_add(new, head, head->next); } diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 8b1045c51e0a..f9c552744b71 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -285,6 +285,8 @@ typedef struct { unsigned long val; } swp_entry_t; +typedef swp_entry_t softleaf_t; + #if defined(CONFIG_MEMCG) || defined(CONFIG_SLAB_OBJ_EXT) /* We have some extra room after the refcount in tail pages. */ #define NR_PAGES_IN_LARGE_FOLIO diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index c13f759374be..7be5b78b2bff 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2145,6 +2145,7 @@ struct net_device { unsigned long state; unsigned int flags; unsigned short hard_header_len; + enum netdev_stat_type pcpu_stat_type:8; netdev_features_t features; struct inet6_dev __rcu *ip6_ptr; __cacheline_group_end(net_device_read_txrx); @@ -2396,8 +2397,6 @@ struct net_device { void *ml_priv; enum netdev_ml_priv_type ml_priv_type; - enum netdev_stat_type pcpu_stat_type:8; - #if IS_ENABLED(CONFIG_GARP) struct garp_port __rcu *garp_port; #endif diff --git a/include/linux/sunrpc/svc_rdma_pcl.h b/include/linux/sunrpc/svc_rdma_pcl.h index 7516ad0fae80..655681cf8fed 100644 --- a/include/linux/sunrpc/svc_rdma_pcl.h +++ b/include/linux/sunrpc/svc_rdma_pcl.h @@ -97,7 +97,7 @@ pcl_next_chunk(const struct svc_rdma_pcl *pcl, struct svc_rdma_chunk *chunk) */ #define pcl_for_each_segment(pos, chunk) \ for (pos = &(chunk)->ch_segments[0]; \ - pos <= &(chunk)->ch_segments[(chunk)->ch_segcount - 1]; \ + pos < &(chunk)->ch_segments[(chunk)->ch_segcount]; \ pos++) /** diff --git a/include/linux/swapops.h b/include/linux/swapops.h index 57aad87e46a6..1966b4890d46 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -120,6 +120,8 @@ static inline unsigned long swp_offset_pfn(swp_entry_t entry) return swp_offset(entry) & SWP_PFN_MASK; } +#define softleaf_to_pfn swp_offset_pfn + /* check whether a pte points to a swap entry */ static inline int is_swap_pte(pte_t pte) { @@ -139,6 +141,8 @@ static inline swp_entry_t pte_to_swp_entry(pte_t pte) return swp_entry(__swp_type(arch_entry), __swp_offset(arch_entry)); } +#define softleaf_from_pte pte_to_swp_entry + /* * Convert the arch-independent representation of a swp_entry_t into the * arch-dependent pte representation. @@ -572,7 +576,13 @@ static inline pmd_t swp_entry_to_pmd(swp_entry_t entry) static inline int pmd_is_migration_entry(pmd_t pmd) { - return is_swap_pmd(pmd) && is_migration_entry(pmd_to_swp_entry(pmd)); + swp_entry_t entry; + + if (pmd_present(pmd)) + return 0; + + entry = pmd_to_swp_entry(pmd); + return is_migration_entry(entry); } #else /* CONFIG_ARCH_ENABLE_THP_MIGRATION */ static inline int set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw, diff --git a/include/linux/usb/tcpci.h b/include/linux/usb/tcpci.h index f7f5cfbdef12..9b46a6bc762c 100644 --- a/include/linux/usb/tcpci.h +++ b/include/linux/usb/tcpci.h @@ -144,6 +144,7 @@ #define TCPC_RX_BUF_FRAME_TYPE 0x31 #define TCPC_RX_BUF_FRAME_TYPE_SOP 0 #define TCPC_RX_BUF_FRAME_TYPE_SOP1 1 +#define TCPC_RX_BUF_FRAME_TYPE_MASK GENMASK(2, 0) #define TCPC_RX_HDR 0x32 #define TCPC_RX_DATA 0x34 /* through 0x4f */ diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index 253ed3930f6e..85e3455cea25 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -629,8 +629,7 @@ struct metadata_dst *iptunnel_metadata_reply(struct metadata_dst *md, int skb_tunnel_check_pmtu(struct sk_buff *skb, struct dst_entry *encap_dst, int headroom, bool reply); -static inline void ip_tunnel_adj_headroom(struct net_device *dev, - unsigned int headroom) +static inline unsigned int ip_tunnel_limit_headroom(unsigned int headroom) { /* we must cap headroom to some upperlimit, else pskb_expand_head * will overflow header offsets in skb_headers_offset_update(). @@ -640,6 +639,14 @@ static inline void ip_tunnel_adj_headroom(struct net_device *dev, if (headroom > max_allowed) headroom = max_allowed; + return headroom; +} + +static inline void ip_tunnel_adj_headroom(struct net_device *dev, + unsigned int headroom) +{ + headroom = ip_tunnel_limit_headroom(headroom); + if (headroom > READ_ONCE(dev->needed_headroom)) WRITE_ONCE(dev->needed_headroom, headroom); } @@ -665,13 +672,29 @@ static inline int iptunnel_pull_offloads(struct sk_buff *skb) static inline void iptunnel_xmit_stats(struct net_device *dev, int pkt_len) { if (pkt_len > 0) { - struct pcpu_sw_netstats *tstats = get_cpu_ptr(dev->tstats); - - u64_stats_update_begin(&tstats->syncp); - u64_stats_add(&tstats->tx_bytes, pkt_len); - u64_stats_inc(&tstats->tx_packets); - u64_stats_update_end(&tstats->syncp); - put_cpu_ptr(tstats); + if (dev->pcpu_stat_type == NETDEV_PCPU_STAT_DSTATS) { + struct pcpu_dstats *dstats = get_cpu_ptr(dev->dstats); + + u64_stats_update_begin(&dstats->syncp); + u64_stats_add(&dstats->tx_bytes, pkt_len); + u64_stats_inc(&dstats->tx_packets); + u64_stats_update_end(&dstats->syncp); + put_cpu_ptr(dstats); + return; + } + if (dev->pcpu_stat_type == NETDEV_PCPU_STAT_TSTATS) { + struct pcpu_sw_netstats *tstats = get_cpu_ptr(dev->tstats); + + u64_stats_update_begin(&tstats->syncp); + u64_stats_add(&tstats->tx_bytes, pkt_len); + u64_stats_inc(&tstats->tx_packets); + u64_stats_update_end(&tstats->syncp); + put_cpu_ptr(tstats); + return; + } + pr_err_once("iptunnel_xmit_stats pcpu_stat_type=%d\n", + dev->pcpu_stat_type); + WARN_ON_ONCE(1); return; } diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index 4bbba29f7341..e2191b158ac4 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -2064,7 +2064,7 @@ struct sctp_association { force_delay:1; __u8 strreset_enable; - __u8 strreset_outstanding; /* request param count on the fly */ + __u8 strreset_outstanding; /* request param bitmask on the fly */ __u32 strreset_outseq; /* Update after receiving response */ __u32 strreset_inseq; /* Update after receiving request */ diff --git a/include/uapi/linux/landlock.h b/include/uapi/linux/landlock.h index f030adc462ee..bb81293c6010 100644 --- a/include/uapi/linux/landlock.h +++ b/include/uapi/linux/landlock.h @@ -237,6 +237,7 @@ struct landlock_net_port_attr { * device. * - %LANDLOCK_ACCESS_FS_MAKE_DIR: Create (or rename) a directory. * - %LANDLOCK_ACCESS_FS_MAKE_REG: Create (or rename or link) a regular file. + * This also guards the creation of whiteout objects as used in OverlayFS. * - %LANDLOCK_ACCESS_FS_MAKE_SOCK: Create (or rename or link) a UNIX domain * socket. * - %LANDLOCK_ACCESS_FS_MAKE_FIFO: Create (or rename or link) a named pipe. diff --git a/io_uring/query.c b/io_uring/query.c index cf02893ba911..e0b42e07eb08 100644 --- a/io_uring/query.c +++ b/io_uring/query.c @@ -36,6 +36,9 @@ static int io_handle_query_entry(struct io_ring_ctx *ctx, if (copy_from_user(&hdr, uhdr, sizeof(hdr))) return -EFAULT; + /* copy_struct_to_user() zeros up to usize bytes */ + if (hdr.size > PAGE_SIZE) + return -E2BIG; usize = hdr.size; hdr.size = min(hdr.size, IO_MAX_QUERY_SIZE); udata = u64_to_user_ptr(hdr.query_data); diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c index f9de58df00fe..d01903b9f965 100644 --- a/kernel/auditfilter.c +++ b/kernel/auditfilter.c @@ -1025,7 +1025,6 @@ static inline int audit_add_rule(struct audit_entry *entry) int audit_del_rule(struct audit_entry *entry) { struct audit_entry *e; - struct audit_tree *tree = entry->rule.tree; struct list_head *list; int ret = 0; #ifdef CONFIG_AUDITSYSCALL @@ -1073,9 +1072,6 @@ int audit_del_rule(struct audit_entry *entry) out: mutex_unlock(&audit_filter_mutex); - if (tree) - audit_put_tree(tree); /* that's the temporary one */ - return ret; } @@ -1160,6 +1156,8 @@ int audit_rule_change(int type, int seq, void *data, size_t datasz) } if (err || type == AUDIT_DEL_RULE) { + if (type == AUDIT_DEL_RULE && entry->rule.tree) + audit_put_tree(entry->rule.tree); if (entry->rule.exe) audit_remove_mark(entry->rule.exe); audit_free_rule(entry); diff --git a/kernel/bpf/bloom_filter.c b/kernel/bpf/bloom_filter.c index 35e1ddca74d2..3f55f28fd589 100644 --- a/kernel/bpf/bloom_filter.c +++ b/kernel/bpf/bloom_filter.c @@ -41,7 +41,7 @@ static long bloom_map_peek_elem(struct bpf_map *map, void *value) for (i = 0; i < bloom->nr_hash_funcs; i++) { h = hash(bloom, value, map->value_size, i); - if (!test_bit(h, bloom->bitset)) + if (!test_bit(h % BITS_PER_LONG, bloom->bitset + BIT_WORD(h))) return -ENOENT; } @@ -57,9 +57,13 @@ static long bloom_map_push_elem(struct bpf_map *map, void *value, u64 flags) if (flags != BPF_ANY) return -EINVAL; + /* + * On 32-bit architectures, hashes larger than INT_MAX would be + * treated as negative by set_bit(). + */ for (i = 0; i < bloom->nr_hash_funcs; i++) { h = hash(bloom, value, map->value_size, i); - set_bit(h, bloom->bitset); + set_bit(h % BITS_PER_LONG, bloom->bitset + BIT_WORD(h)); } return 0; @@ -94,9 +98,10 @@ static int bloom_map_alloc_check(union bpf_attr *attr) static struct bpf_map *bloom_map_alloc(union bpf_attr *attr) { - u32 bitset_bytes, bitset_mask, nr_hash_funcs, nr_bits; + u32 bitset_mask, nr_hash_funcs, nr_bits; int numa_node = bpf_map_attr_numa_node(attr); struct bpf_bloom_filter *bloom; + u64 bitset_bytes; if (attr->key_size != 0 || attr->value_size == 0 || attr->max_entries == 0 || @@ -127,22 +132,16 @@ static struct bpf_map *bloom_map_alloc(union bpf_attr *attr) if (check_mul_overflow(attr->max_entries, nr_hash_funcs, &nr_bits) || check_mul_overflow(nr_bits / 5, (u32)7, &nr_bits) || nr_bits > (1UL << 31)) { - /* The bit array size is 2^32 bits but to avoid overflowing the - * u32, we use U32_MAX, which will round up to the equivalent - * number of bytes - */ - bitset_bytes = BITS_TO_BYTES(U32_MAX); bitset_mask = U32_MAX; } else { if (nr_bits <= BITS_PER_LONG) nr_bits = BITS_PER_LONG; else nr_bits = roundup_pow_of_two(nr_bits); - bitset_bytes = BITS_TO_BYTES(nr_bits); bitset_mask = nr_bits - 1; } - bitset_bytes = roundup(bitset_bytes, sizeof(unsigned long)); + bitset_bytes = BITS_TO_LONGS((u64)bitset_mask + 1) * sizeof(unsigned long); bloom = bpf_map_area_alloc(sizeof(*bloom) + bitset_bytes, numa_node); if (!bloom) diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index 2365541c81dd..13f4f696a7c0 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -460,6 +460,7 @@ static long __bpf_get_stack(struct pt_regs *regs, struct task_struct *task, max_depth = stack_map_calculate_max_depth(size, elem_size, flags); + preempt_disable(); if (may_fault) rcu_read_lock(); /* need RCU for perf's callchain below */ @@ -476,6 +477,7 @@ static long __bpf_get_stack(struct pt_regs *regs, struct task_struct *task, if (unlikely(!trace) || trace->nr < skip) { if (may_fault) rcu_read_unlock(); + preempt_enable(); goto err_fault; } @@ -496,6 +498,7 @@ static long __bpf_get_stack(struct pt_regs *regs, struct task_struct *task, /* trace/ips should not be dereferenced after this point */ if (may_fault) rcu_read_unlock(); + preempt_enable(); if (user_build_id) stack_map_get_build_id_offset(buf, trace_nr, user, may_fault); diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 459ed144542c..dcecf8806856 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -611,6 +611,13 @@ static bool is_atomic_load_insn(const struct bpf_insn *insn) insn->imm == BPF_LOAD_ACQ; } +static bool is_atomic_fetch_insn(const struct bpf_insn *insn) +{ + return BPF_CLASS(insn->code) == BPF_STX && + BPF_MODE(insn->code) == BPF_ATOMIC && + (insn->imm & BPF_FETCH); +} + static int __get_spi(s32 off) { return (-off - 1) / BPF_REG_SIZE; @@ -4323,10 +4330,24 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx, * dreg still needs precision before this insn */ } - } else if (class == BPF_LDX || is_atomic_load_insn(insn)) { - if (!bt_is_reg_set(bt, dreg)) + } else if (class == BPF_LDX || + is_atomic_load_insn(insn) || + is_atomic_fetch_insn(insn)) { + u32 load_reg = dreg; + + /* + * Atomic fetch operation writes the old value into + * a register (sreg or r0) and if it was tracked for + * precision, propagate to the stack slot like we do + * in regular ldx. + */ + if (is_atomic_fetch_insn(insn)) + load_reg = insn->imm == BPF_CMPXCHG ? + BPF_REG_0 : sreg; + + if (!bt_is_reg_set(bt, load_reg)) return 0; - bt_clear_reg(bt, dreg); + bt_clear_reg(bt, load_reg); /* scalars can only be spilled into stack w/o losing precision. * Load from any other memory can be zero extended. diff --git a/kernel/module/kallsyms.c b/kernel/module/kallsyms.c index 0fc11e45df9b..f23126d804b2 100644 --- a/kernel/module/kallsyms.c +++ b/kernel/module/kallsyms.c @@ -258,17 +258,25 @@ static const char *find_kallsyms_symbol(struct module *mod, unsigned int i, best = 0; unsigned long nextval, bestval; struct mod_kallsyms *kallsyms = rcu_dereference(mod->kallsyms); - struct module_memory *mod_mem; + struct module_memory *mod_mem = NULL; - /* At worse, next value is at end of module */ - if (within_module_init(addr, mod)) - mod_mem = &mod->mem[MOD_INIT_TEXT]; - else - mod_mem = &mod->mem[MOD_TEXT]; + for_each_mod_mem_type(type) { +#ifndef CONFIG_KALLSYMS_ALL + if (!mod_mem_type_is_text(type)) + continue; +#endif + if (within_module_mem_type(addr, mod, type)) { + mod_mem = &mod->mem[type]; + break; + } + } - nextval = (unsigned long)mod_mem->base + mod_mem->size; + if (!mod_mem) + return NULL; - bestval = kallsyms_symbol_value(&kallsyms->symtab[best]); + /* Initialize bounds within memory region the address belongs to. */ + nextval = (unsigned long)mod_mem->base + mod_mem->size; + bestval = (unsigned long)mod_mem->base - 1; /* * Scan for closest preceding symbol, and next symbol. (ELF diff --git a/kernel/module/main.c b/kernel/module/main.c index 3745cd02c847..d34187b02d14 100644 --- a/kernel/module/main.c +++ b/kernel/module/main.c @@ -1958,6 +1958,7 @@ static int elf_validity_cache_sechdrs(struct load_info *info) * Specifically checks: * * * Section name table index is inbounds of section headers + * * Section name table type is SHT_STRTAB * * Section name table is not empty * * Section name table is NUL terminated * * All section name offsets are inbounds of the section @@ -1985,6 +1986,11 @@ static int elf_validity_cache_secstrings(struct load_info *info) strhdr = &info->sechdrs[info->hdr->e_shstrndx]; + if (strhdr->sh_type != SHT_STRTAB) { + pr_err("Invalid ELF section name table type: %u\n", strhdr->sh_type); + return -ENOEXEC; + } + /* * The section name table must be NUL-terminated, as required * by the spec. This makes strcmp and pr_* calls that access @@ -2151,7 +2157,7 @@ static int elf_validity_cache_index_sym(struct load_info *info) * Must have &load_info->index.sym populated. * * Looks at the symbol table's associated string table, makes sure it is - * in-bounds, and caches it. + * in-bounds and of type SHT_STRTAB, and caches it. * * Return: %0 if valid, %-ENOEXEC on failure. */ @@ -2165,6 +2171,12 @@ static int elf_validity_cache_index_str(struct load_info *info) return -ENOEXEC; } + if (info->sechdrs[str_idx].sh_type != SHT_STRTAB) { + pr_err("Invalid ELF symbol string table type: %u\n", + info->sechdrs[str_idx].sh_type); + return -ENOEXEC; + } + info->index.str = str_idx; return 0; } diff --git a/kernel/params.c b/kernel/params.c index 8942884e21c4..10ae7aac16d7 100644 --- a/kernel/params.c +++ b/kernel/params.c @@ -261,6 +261,7 @@ EXPORT_SYMBOL_GPL(param_set_uint_minmax); int param_set_charp(const char *val, const struct kernel_param *kp) { + char *tmp; size_t len, maxlen = 1024; len = strnlen(val, maxlen + 1); @@ -269,19 +270,20 @@ int param_set_charp(const char *val, const struct kernel_param *kp) return -ENOSPC; } - maybe_kfree_parameter(*(char **)kp->arg); - /* * This is a hack. We can't kmalloc() in early boot, and we * don't need to; this mangled commandline is preserved. */ if (slab_is_available()) { - *(char **)kp->arg = kmalloc_parameter(len + 1); - if (!*(char **)kp->arg) + tmp = kmalloc_parameter(len + 1); + if (!tmp) return -ENOMEM; - strcpy(*(char **)kp->arg, val); + memcpy(tmp, val, len + 1); } else - *(const char **)kp->arg = val; + tmp = (char *)val; + + maybe_kfree_parameter(*(char **)kp->arg); + *(char **)kp->arg = tmp; return 0; } diff --git a/kernel/pid.c b/kernel/pid.c index 6a7769749ee6..9dfc327394f1 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -715,29 +715,6 @@ static struct ctl_table_root pid_table_root = { .set_ownership = pid_table_root_set_ownership, }; -static int proc_do_cad_pid(const struct ctl_table *table, int write, void *buffer, - size_t *lenp, loff_t *ppos) -{ - struct pid *new_pid; - pid_t tmp_pid; - int r; - struct ctl_table tmp_table = *table; - - tmp_pid = pid_vnr(cad_pid); - tmp_table.data = &tmp_pid; - - r = proc_dointvec(&tmp_table, write, buffer, lenp, ppos); - if (r || !write) - return r; - - new_pid = find_get_pid(tmp_pid); - if (!new_pid) - return -ESRCH; - - put_pid(xchg(&cad_pid, new_pid)); - return 0; -} - static const struct ctl_table pid_table[] = { { .procname = "pid_max", @@ -748,14 +725,6 @@ static const struct ctl_table pid_table[] = { .extra1 = &pid_max_min, .extra2 = &pid_max_max, }, -#ifdef CONFIG_PROC_SYSCTL - { - .procname = "cad_pid", - .maxlen = sizeof(int), - .mode = 0600, - .proc_handler = proc_do_cad_pid, - }, -#endif }; #endif diff --git a/kernel/reboot.c b/kernel/reboot.c index ec087827c85c..972cc11c9157 100644 --- a/kernel/reboot.c +++ b/kernel/reboot.c @@ -1366,6 +1366,29 @@ static struct attribute *reboot_attrs[] = { }; #ifdef CONFIG_SYSCTL +static int proc_do_cad_pid(const struct ctl_table *table, int write, void *buffer, + size_t *lenp, loff_t *ppos) +{ + struct ctl_table tmp_table = *table; + struct pid *new_pid; + pid_t tmp_pid; + int r; + + tmp_pid = pid_vnr(cad_pid); + tmp_table.data = &tmp_pid; + + r = proc_dointvec(&tmp_table, write, buffer, lenp, ppos); + if (r || !write) + return r; + + new_pid = find_get_pid(tmp_pid); + if (!new_pid) + return -ESRCH; + + put_pid(xchg(&cad_pid, new_pid)); + return 0; +} + static const struct ctl_table kern_reboot_table[] = { { .procname = "poweroff_cmd", @@ -1381,6 +1404,12 @@ static const struct ctl_table kern_reboot_table[] = { .mode = 0644, .proc_handler = proc_dointvec, }, + { + .procname = "cad_pid", + .maxlen = sizeof(int), + .mode = 0600, + .proc_handler = proc_do_cad_pid, + }, }; static void __init kernel_reboot_sysctls_init(void) diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c index 5d8fc382c4a1..374b65940d03 100644 --- a/kernel/sched/cpufreq_schedutil.c +++ b/kernel/sched/cpufreq_schedutil.c @@ -61,6 +61,17 @@ static DEFINE_PER_CPU(struct sugov_cpu, sugov_cpu); /************************ Governor internals ***********************/ +static void sugov_update_rate_limit_us(struct sugov_policy *sg_policy) +{ + /* + * Cast rate_limit_us before multiplication to force 64-bit arithmetic. + * Otherwise, on 32-bit platforms, both operands are converted to + * 32-bit unsigned long and the multiplication may overflow. + */ + sg_policy->freq_update_delay_ns = + (s64)sg_policy->tunables->rate_limit_us * NSEC_PER_USEC; +} + static bool sugov_should_update_freq(struct sugov_policy *sg_policy, u64 time) { s64 delta_ns; @@ -606,7 +617,7 @@ rate_limit_us_store(struct gov_attr_set *attr_set, const char *buf, size_t count tunables->rate_limit_us = rate_limit_us; list_for_each_entry(sg_policy, &attr_set->policy_list, tunables_hook) - sg_policy->freq_update_delay_ns = rate_limit_us * NSEC_PER_USEC; + sugov_update_rate_limit_us(sg_policy); return count; } @@ -848,7 +859,7 @@ static int sugov_start(struct cpufreq_policy *policy) void (*uu)(struct update_util_data *data, u64 time, unsigned int flags); unsigned int cpu; - sg_policy->freq_update_delay_ns = sg_policy->tunables->rate_limit_us * NSEC_PER_USEC; + sugov_update_rate_limit_us(sg_policy); sg_policy->last_freq_update_time = 0; sg_policy->next_freq = 0; sg_policy->work_in_progress = false; diff --git a/kernel/signal.c b/kernel/signal.c index e1843b71efff..34ba75bd749a 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -1183,6 +1183,7 @@ static inline bool has_si_pid_and_uid(struct kernel_siginfo *info) int send_signal_locked(int sig, struct kernel_siginfo *info, struct task_struct *t, enum pid_type type) { + struct kernel_siginfo rewritten; /* Should SIGKILL or SIGSTOP be received by a pid namespace init? */ bool force = false; @@ -1196,6 +1197,9 @@ int send_signal_locked(int sig, struct kernel_siginfo *info, /* SIGKILL and SIGSTOP is special or has ids */ struct user_namespace *t_user_ns; + rewritten = *info; + info = &rewritten; + rcu_read_lock(); t_user_ns = task_cred_xxx(t, user_ns); if (current_user_ns() != t_user_ns) { diff --git a/kernel/taskstats.c b/kernel/taskstats.c index 2cd0172d0516..05a905e64fa1 100644 --- a/kernel/taskstats.c +++ b/kernel/taskstats.c @@ -368,10 +368,9 @@ static int parse(struct nlattr *na, struct cpumask *mask) return -E2BIG; if (len < 1) return -EINVAL; - data = kmalloc(len, GFP_KERNEL); + data = nla_strdup(na, GFP_KERNEL); if (!data) return -ENOMEM; - nla_strscpy(data, na, len); ret = cpulist_parse(data, mask); kfree(data); return ret; diff --git a/kernel/time/itimer.c b/kernel/time/itimer.c index 7c6110e964e7..03a32dffc56c 100644 --- a/kernel/time/itimer.c +++ b/kernel/time/itimer.c @@ -100,7 +100,7 @@ static int do_getitimer(int which, struct itimerspec64 *value) static int put_itimerval(struct __kernel_old_itimerval __user *o, const struct itimerspec64 *i) { - struct __kernel_old_itimerval v; + struct __kernel_old_itimerval v = {}; v.it_interval.tv_sec = i->it_interval.tv_sec; v.it_interval.tv_usec = i->it_interval.tv_nsec / NSEC_PER_USEC; diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 889a8de3fc20..06184f304c6a 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -2693,10 +2693,12 @@ static int __do_adjtimex(struct tk_data *tkd, struct __kernel_timex *txc, return ret; add_device_randomness(txc, sizeof(*txc)); - if (!aux_clock) + if (!aux_clock) { ktime_get_real_ts64(&ts); - else - tk_get_aux_ts64(tkd->timekeeper.id, &ts); + } else { + if (!tk_get_aux_ts64(tkd->timekeeper.id, &ts)) + return -ENODEV; + } add_device_randomness(&ts, sizeof(ts)); diff --git a/kernel/time/timer.c b/kernel/time/timer.c index d5ebb1d927ea..97a7bd5a8e3b 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -2491,6 +2491,7 @@ static void migrate_timer_list(struct timer_base *new_base, struct hlist_head *h timer = hlist_entry(head->first, struct timer_list, entry); detach_timer(timer, false); timer->flags = (timer->flags & ~TIMER_BASEMASK) | cpu; + debug_timer_activate(timer); internal_add_timer(new_base, timer); } } diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 9ea034b55158..5936389188bd 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -396,6 +396,17 @@ static __always_inline unsigned int rb_page_commit(struct buffer_page *bpage) return local_read(&bpage->page->commit); } +/** + * rb_page_capacity - Get the capacity of a buffer page + * @bpage: The buffer page + * + * Return: The maximum size available for events in the given buffer page. + */ +static __always_inline unsigned int rb_page_capacity(struct buffer_page *bpage) +{ + return (PAGE_SIZE << bpage->order) - BUF_PAGE_HDR_SIZE; +} + static void free_buffer_page(struct buffer_page *bpage) { /* Range pages are not to be freed */ @@ -595,11 +606,42 @@ struct trace_buffer { struct ring_buffer_meta *meta; - unsigned int subbuf_size; unsigned int subbuf_order; unsigned int max_data_size; }; +static __always_inline unsigned int rb_subbuf_size(struct trace_buffer *buffer) +{ + return PAGE_SIZE << buffer->subbuf_order; +} + +/** + * rb_subbuf_capacity - Get the capacity of a subbuffer + * @buffer: A trace buffer + * + * Unsafe to use without holding trace_buffer::mutex or with resizing enabled. + * Consider rb_page_capacity() instead. + * + * Return: The maximum size available for events in a trace buffer subbuffer. + */ +static __always_inline unsigned int rb_subbuf_capacity(struct trace_buffer *buffer) +{ + return rb_subbuf_size(buffer) - BUF_PAGE_HDR_SIZE; +} + +/** + * rb_subbuf_start - Get the start address of a subbuffer + * @buffer: A trace buffer + * @addr: An address of an event on a subbuffer + * + * Return: The start of the subbuffer for where @addr sits + */ +static __always_inline +unsigned long rb_subbuf_start(struct trace_buffer *buffer, unsigned long addr) +{ + return addr & ~((unsigned long)(rb_subbuf_size(buffer) - 1)); +} + struct ring_buffer_iter { struct ring_buffer_per_cpu *cpu_buffer; unsigned long head; @@ -639,7 +681,7 @@ int ring_buffer_print_page_header(struct trace_buffer *buffer, struct trace_seq trace_seq_printf(s, "\tfield: char data;\t" "offset:%u;\tsize:%u;\tsigned:%u;\n", (unsigned int)offsetof(typeof(field), data), - (unsigned int)buffer->subbuf_size, + (unsigned int)rb_subbuf_capacity(buffer), (unsigned int)is_signed_type(char)); return !trace_seq_has_overflowed(s); @@ -1628,7 +1670,7 @@ rb_range_align_subbuf(unsigned long addr, int subbuf_size, int nr_subbufs) */ static void *rb_range_meta(struct trace_buffer *buffer, int nr_pages, int cpu) { - int subbuf_size = buffer->subbuf_size + BUF_PAGE_HDR_SIZE; + int subbuf_size = rb_subbuf_size(buffer); struct ring_buffer_cpu_meta *meta; struct ring_buffer_meta *bmeta; unsigned long ptr; @@ -2302,8 +2344,8 @@ static int __rb_allocate_pages(struct ring_buffer_per_cpu *cpu_buffer, bpage->range = 1; bpage->id = i + 1; } else { - int order = cpu_buffer->buffer->subbuf_order; - bpage->page = alloc_cpu_data(cpu_buffer->cpu, order); + bpage->page = alloc_cpu_data(cpu_buffer->cpu, + cpu_buffer->buffer->subbuf_order); if (!bpage->page) goto free_pages; } @@ -2402,8 +2444,7 @@ rb_allocate_cpu_buffer(struct trace_buffer *buffer, long nr_pages, int cpu) atomic_inc(&cpu_buffer->resize_disabled); } else { - int order = cpu_buffer->buffer->subbuf_order; - bpage->page = alloc_cpu_data(cpu, order); + bpage->page = alloc_cpu_data(cpu, bpage->order); if (!bpage->page) goto fail_free_reader; } @@ -2473,7 +2514,7 @@ static void rb_free_cpu_buffer(struct ring_buffer_per_cpu *cpu_buffer) free_buffer_page(bpage); } - free_page((unsigned long)cpu_buffer->free_page); + free_pages((unsigned long)cpu_buffer->free_page, cpu_buffer->buffer->subbuf_order); kfree(cpu_buffer); } @@ -2512,10 +2553,9 @@ static struct trace_buffer *alloc_buffer(unsigned long size, unsigned flags, buffer->subbuf_order = order; subbuf_size = (PAGE_SIZE << order); - buffer->subbuf_size = subbuf_size - BUF_PAGE_HDR_SIZE; /* Max payload is buffer page size - header (8bytes) */ - buffer->max_data_size = buffer->subbuf_size - (sizeof(u32) * 2); + buffer->max_data_size = rb_subbuf_capacity(buffer) - (sizeof(u32) * 2); buffer->flags = flags; buffer->clock = trace_clock_local; @@ -2588,9 +2628,8 @@ static struct trace_buffer *alloc_buffer(unsigned long size, unsigned flags, rb_range_meta_init(buffer, nr_pages, scratch_size); } else { - /* need at least two pages */ - nr_pages = DIV_ROUND_UP(size, buffer->subbuf_size); + nr_pages = DIV_ROUND_UP(size, rb_subbuf_capacity(buffer)); if (nr_pages < 2) nr_pages = 2; } @@ -2963,7 +3002,7 @@ static void update_pages_handler(struct work_struct *work) * @size: the new size. * @cpu_id: the cpu buffer to resize * - * Minimum size is 2 * buffer->subbuf_size. + * Minimum size is 2 * rb_subbuf_capacity(buffer). * * Returns 0 on success and < 0 on failure. */ @@ -2985,12 +3024,6 @@ int ring_buffer_resize(struct trace_buffer *buffer, unsigned long size, !cpumask_test_cpu(cpu_id, buffer->cpumask)) return 0; - nr_pages = DIV_ROUND_UP(size, buffer->subbuf_size); - - /* we need a minimum of two pages */ - if (nr_pages < 2) - nr_pages = 2; - /* * Keep CPUs from coming online while resizing to synchronize * with new per CPU buffers being created. @@ -3001,6 +3034,12 @@ int ring_buffer_resize(struct trace_buffer *buffer, unsigned long size, mutex_lock(&buffer->mutex); atomic_inc(&buffer->resizing); + nr_pages = DIV_ROUND_UP(size, rb_subbuf_capacity(buffer)); + + /* we need a minimum of two pages */ + if (nr_pages < 2) + nr_pages = 2; + if (cpu_id == RING_BUFFER_ALL_CPUS) { /* * Don't succeed if resizing is disabled, as a reader might be @@ -3279,7 +3318,7 @@ rb_event_index(struct ring_buffer_per_cpu *cpu_buffer, struct ring_buffer_event { unsigned long addr = (unsigned long)event; - addr &= (PAGE_SIZE << cpu_buffer->buffer->subbuf_order) - 1; + addr &= (unsigned long)rb_subbuf_size(cpu_buffer->buffer) - 1; return addr - BUF_PAGE_HDR_SIZE; } @@ -3518,8 +3557,8 @@ static inline void rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer, unsigned long tail, struct rb_event_info *info) { - unsigned long bsize = READ_ONCE(cpu_buffer->buffer->subbuf_size); struct buffer_page *tail_page = info->tail_page; + unsigned long bsize = rb_page_capacity(tail_page); struct ring_buffer_event *event; unsigned long length = info->length; @@ -3871,8 +3910,7 @@ rb_try_to_discard(struct ring_buffer_per_cpu *cpu_buffer, new_index = rb_event_index(cpu_buffer, event); old_index = new_index + rb_event_ts_length(event); - addr = (unsigned long)event; - addr &= ~((PAGE_SIZE << cpu_buffer->buffer->subbuf_order) - 1); + addr = rb_subbuf_start(cpu_buffer->buffer, (unsigned long)event); bpage = READ_ONCE(cpu_buffer->tail_page); @@ -4519,7 +4557,7 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer, tail = write - info->length; /* See if we shot pass the end of this buffer page */ - if (unlikely(write > cpu_buffer->buffer->subbuf_size)) { + if (unlikely(write > rb_page_capacity(tail_page))) { check_buffer(cpu_buffer, info, CHECK_FULL_PAGE); return rb_move_tail(cpu_buffer, tail, info); } @@ -4764,7 +4802,7 @@ rb_decrement_entry(struct ring_buffer_per_cpu *cpu_buffer, struct buffer_page *bpage = cpu_buffer->commit_page; struct buffer_page *start; - addr &= ~((PAGE_SIZE << cpu_buffer->buffer->subbuf_order) - 1); + addr = rb_subbuf_start(cpu_buffer->buffer, addr); /* Do the likely case first */ if (likely(bpage->page == (void *)addr)) { @@ -5441,7 +5479,6 @@ static struct buffer_page * rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer) { struct buffer_page *reader = NULL; - unsigned long bsize = READ_ONCE(cpu_buffer->buffer->subbuf_size); unsigned long overwrite; unsigned long flags; int nr_loops = 0; @@ -5580,7 +5617,7 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer) #define USECS_WAIT 1000000 for (nr_loops = 0; nr_loops < USECS_WAIT; nr_loops++) { /* If the write is past the end of page, a writer is still updating it */ - if (likely(!reader || rb_page_write(reader) <= bsize)) + if (likely(!reader || rb_page_write(reader) <= rb_page_capacity(reader))) break; udelay(1); @@ -6002,36 +6039,44 @@ EXPORT_SYMBOL_GPL(ring_buffer_consume); struct ring_buffer_iter * ring_buffer_read_start(struct trace_buffer *buffer, int cpu, gfp_t flags) { + struct ring_buffer_iter *iter __free(kfree) = kzalloc_obj(*iter, flags); struct ring_buffer_per_cpu *cpu_buffer; - struct ring_buffer_iter *iter; - - if (!cpumask_test_cpu(cpu, buffer->cpumask)) - return NULL; - iter = kzalloc(sizeof(*iter), flags); if (!iter) return NULL; - /* Holds the entire event: data and meta data */ - iter->event_size = buffer->subbuf_size; - iter->event = kmalloc(iter->event_size, flags); - if (!iter->event) { - kfree(iter); + if (!cpumask_test_cpu(cpu, buffer->cpumask)) return NULL; - } cpu_buffer = buffer->buffers[cpu]; - iter->cpu_buffer = cpu_buffer; + /* + * Only KDB is using GFP_ATOMIC, for the others, lock the buffer to + * prevent concurrent resizing. + */ + if (gfpflags_allow_blocking(flags)) + mutex_lock(&buffer->mutex); atomic_inc(&cpu_buffer->resize_disabled); + if (gfpflags_allow_blocking(flags)) + mutex_unlock(&buffer->mutex); + + /* Holds the entire event: data and meta data. */ + iter->event_size = rb_page_capacity(READ_ONCE(cpu_buffer->reader_page)); + iter->event = kmalloc(iter->event_size, flags); + if (!iter->event) { + atomic_dec(&cpu_buffer->resize_disabled); + return NULL; + } + iter->cpu_buffer = cpu_buffer; + guard(raw_spinlock_irqsave)(&cpu_buffer->reader_lock); arch_spin_lock(&cpu_buffer->lock); rb_iter_reset(iter); arch_spin_unlock(&cpu_buffer->lock); - return iter; + return_ptr(iter); } EXPORT_SYMBOL_GPL(ring_buffer_read_start); @@ -6085,7 +6130,7 @@ unsigned long ring_buffer_size(struct trace_buffer *buffer, int cpu) if (!cpumask_test_cpu(cpu, buffer->cpumask)) return 0; - return buffer->subbuf_size * buffer->buffers[cpu]->nr_pages; + return rb_subbuf_capacity(buffer) * buffer->buffers[cpu]->nr_pages; } EXPORT_SYMBOL_GPL(ring_buffer_size); @@ -6536,7 +6581,7 @@ ring_buffer_alloc_read_page(struct trace_buffer *buffer, int cpu) if (bpage->data) { rb_init_page(bpage->data); } else { - bpage->data = alloc_cpu_data(cpu, cpu_buffer->buffer->subbuf_order); + bpage->data = alloc_cpu_data(cpu, bpage->order); if (!bpage->data) { kfree(bpage); return ERR_PTR(-ENOMEM); @@ -6655,15 +6700,15 @@ int ring_buffer_read_page(struct trace_buffer *buffer, if (!data_page || !data_page->data) return -1; - if (data_page->order != buffer->subbuf_order) - return -1; - bpage = data_page->data; if (!bpage) return -1; guard(raw_spinlock_irqsave)(&cpu_buffer->reader_lock); + if (data_page->order != cpu_buffer->reader_page->order) + return -1; + reader = rb_get_reader_page(cpu_buffer); if (!reader) return -1; @@ -6778,7 +6823,7 @@ int ring_buffer_read_page(struct trace_buffer *buffer, /* If there is room at the end of the page to save the * missed events, then record it there. */ - if (buffer->subbuf_size - commit >= sizeof(missed_events)) { + if (rb_page_capacity(reader) - commit >= sizeof(missed_events)) { memcpy(&bpage->data[commit], &missed_events, sizeof(missed_events)); local_add(RB_MISSED_STORED, &bpage->commit); @@ -6790,8 +6835,8 @@ int ring_buffer_read_page(struct trace_buffer *buffer, /* * This page may be off to user land. Zero it out here. */ - if (commit < buffer->subbuf_size) - memset(&bpage->data[commit], 0, buffer->subbuf_size - commit); + if (commit < rb_page_capacity(reader)) + memset(&bpage->data[commit], 0, rb_page_capacity(reader) - commit); return read; } @@ -6817,7 +6862,7 @@ EXPORT_SYMBOL_GPL(ring_buffer_read_page_data); */ int ring_buffer_subbuf_size_get(struct trace_buffer *buffer) { - return buffer->subbuf_size + BUF_PAGE_HDR_SIZE; + return rb_subbuf_size(buffer); } EXPORT_SYMBOL_GPL(ring_buffer_subbuf_size_get); @@ -6862,7 +6907,8 @@ int ring_buffer_subbuf_order_set(struct trace_buffer *buffer, int order) { struct ring_buffer_per_cpu *cpu_buffer; struct buffer_page *bpage, *tmp; - int old_order, old_size; + unsigned int old_capacity; + int old_order; int nr_pages; int psize; int err; @@ -6871,9 +6917,6 @@ int ring_buffer_subbuf_order_set(struct trace_buffer *buffer, int order) if (!buffer || order < 0) return -EINVAL; - if (buffer->subbuf_order == order) - return 0; - psize = (1 << order) * PAGE_SIZE; if (psize <= BUF_PAGE_HDR_SIZE) return -EINVAL; @@ -6882,18 +6925,21 @@ int ring_buffer_subbuf_order_set(struct trace_buffer *buffer, int order) if (psize > RB_WRITE_MASK + 1) return -EINVAL; - old_order = buffer->subbuf_order; - old_size = buffer->subbuf_size; - /* prevent another thread from changing buffer sizes */ guard(mutex)(&buffer->mutex); + + old_order = buffer->subbuf_order; + if (old_order == order) + return 0; + + old_capacity = rb_subbuf_capacity(buffer); + atomic_inc(&buffer->record_disabled); /* Make sure all commits have finished */ synchronize_rcu(); buffer->subbuf_order = order; - buffer->subbuf_size = psize - BUF_PAGE_HDR_SIZE; /* Make sure all new buffers are allocated, before deleting the old ones */ for_each_buffer_cpu(buffer, cpu) { @@ -6909,8 +6955,8 @@ int ring_buffer_subbuf_order_set(struct trace_buffer *buffer, int order) } /* Update the number of pages to match the new size */ - nr_pages = old_size * buffer->buffers[cpu]->nr_pages; - nr_pages = DIV_ROUND_UP(nr_pages, buffer->subbuf_size); + nr_pages = old_capacity * buffer->buffers[cpu]->nr_pages; + nr_pages = DIV_ROUND_UP(nr_pages, rb_subbuf_capacity(buffer)); /* we need a minimum of two pages */ if (nr_pages < 2) @@ -6973,8 +7019,10 @@ int ring_buffer_subbuf_order_set(struct trace_buffer *buffer, int order) cpu_buffer->nr_pages = cpu_buffer->nr_pages_to_update; cpu_buffer->nr_pages_to_update = 0; + arch_spin_lock(&cpu_buffer->lock); old_free_data_page = cpu_buffer->free_page; cpu_buffer->free_page = NULL; + arch_spin_unlock(&cpu_buffer->lock); rb_head_page_activate(cpu_buffer); @@ -6996,7 +7044,6 @@ int ring_buffer_subbuf_order_set(struct trace_buffer *buffer, int order) error: buffer->subbuf_order = old_order; - buffer->subbuf_size = old_size; atomic_dec(&buffer->record_disabled); @@ -7074,7 +7121,7 @@ static void rb_setup_ids_meta_page(struct ring_buffer_per_cpu *cpu_buffer, meta->meta_struct_len = sizeof(*meta); meta->nr_subbufs = nr_subbufs; - meta->subbuf_size = cpu_buffer->buffer->subbuf_size + BUF_PAGE_HDR_SIZE; + meta->subbuf_size = rb_subbuf_size(cpu_buffer->buffer); meta->meta_page_size = meta->subbuf_size; rb_update_meta_page(cpu_buffer); @@ -7436,7 +7483,7 @@ consume: * missed events, then record it there. */ commit = rb_page_size(reader); - if (buffer->subbuf_size - commit >= sizeof(missed_events)) { + if (rb_subbuf_capacity(buffer) - commit >= sizeof(missed_events)) { memcpy(&bpage->data[commit], &missed_events, sizeof(missed_events)); local_add(RB_MISSED_STORED, &bpage->commit); @@ -7468,7 +7515,7 @@ consume: out: /* Some archs do not have data cache coherency between kernel and user-space */ flush_kernel_vmap_range(cpu_buffer->reader_page->page, - buffer->subbuf_size + BUF_PAGE_HDR_SIZE); + rb_subbuf_size(buffer)); rb_update_meta_page(cpu_buffer); diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 914d6baa1bf9..e62772a76671 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -9699,6 +9699,8 @@ buffer_subbuf_size_write(struct file *filp, const char __user *ubuf, /* Do not allow tracing while changing the order of the ring buffer */ tracing_stop_tr(tr); + trace_access_lock(RING_BUFFER_ALL_CPUS); + old_order = ring_buffer_subbuf_order_get(tr->array_buffer.buffer); if (old_order == order) goto out; @@ -9738,6 +9740,7 @@ buffer_subbuf_size_write(struct file *filp, const char __user *ubuf, #endif (*ppos)++; out: + trace_access_unlock(RING_BUFFER_ALL_CPUS); if (ret) cnt = ret; tracing_start_tr(tr); @@ -11172,7 +11175,8 @@ __init static void enable_instances(void) tr = trace_array_create_systems(name, NULL, addr, size); if (IS_ERR(tr)) { - pr_warn("Tracing: Failed to create instance buffer %s\n", curr_str); + pr_warn("Tracing: Failed to create instance buffer '%s' (%ld)\n", name, + PTR_ERR(tr)); continue; } diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index c184d1a7387a..0f96eb95ad38 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -4729,6 +4729,8 @@ static __init void event_test_stuff(void) struct task_struct *test_thread; test_thread = kthread_run(event_test_thread, NULL, "test-events"); + if (WARN_ON(IS_ERR(test_thread))) + return; msleep(1); kthread_stop(test_thread); } diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index cf2a4388845d..1799c22ff9f2 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -6613,8 +6613,10 @@ static int hist_register_trigger(char *glob, tracing_set_filter_buffering(file->tr, true); } - if (named_data) + if (named_data) { + remove_hist_vars(hist_data); destroy_hist_data(hist_data); + } out: return ret; } diff --git a/kernel/trace/trace_events_user.c b/kernel/trace/trace_events_user.c index 8e839370f713..d4fe566991cb 100644 --- a/kernel/trace/trace_events_user.c +++ b/kernel/trace/trace_events_user.c @@ -868,6 +868,9 @@ void user_event_mm_dup(struct task_struct *t, struct user_event_mm *old_mm) struct user_event_mm *mm = user_event_mm_alloc(t); struct user_event_enabler *enabler; + /* On failure, do not free parent's copy */ + t->user_event_mm = NULL; + if (!mm) return; diff --git a/lib/ucs2_string.c b/lib/ucs2_string.c index dfb4f2358cab..ca5c615d5bef 100644 --- a/lib/ucs2_string.c +++ b/lib/ucs2_string.c @@ -8,7 +8,7 @@ ucs2_strnlen(const ucs2_char_t *s, size_t maxlength) { unsigned long length = 0; - while (*s++ != 0 && length < maxlength) + while (length < maxlength && *s++ != 0) length++; return length; } diff --git a/lib/xarray.c b/lib/xarray.c index 9a8b4916540c..bfe7bef80f34 100644 --- a/lib/xarray.c +++ b/lib/xarray.c @@ -1053,6 +1053,9 @@ void xas_split_alloc(struct xa_state *xas, void *entry, unsigned int order, if (xas->xa_shift + XA_CHUNK_SHIFT > order) return; + if (xas->xa->xa_flags & XA_FLAGS_ACCOUNT) + gfp |= __GFP_ACCOUNT; + do { struct xa_node *node; diff --git a/mm/compaction.c b/mm/compaction.c index 6769a9d6f16a..7bb638df5db9 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -1364,12 +1364,44 @@ static bool suitable_migration_source(struct compact_control *cc, if (pageblock_skip_persistent(page)) return false; - if ((cc->mode != MIGRATE_ASYNC) || !cc->direct_compaction) + /* + * Background compaction produces blocks for the zone at + * large, with no particular allocation context. Allow all + * block types, including CMA. + */ + if (!cc->direct_compaction) return true; block_mt = get_pageblock_migratetype(page); - if (cc->migratetype == MIGRATE_MOVABLE) + /* + * CMA pages can only be taken by ALLOC_CMA requests. For anybody + * else, vacating a CMA block consumes free pages the caller + * could have used, and produces free pages it cannot. + */ + if (is_migrate_cma(block_mt) && !(cc->alloc_flags & ALLOC_CMA)) + return false; + + /* + * Per default, scans are restricted to blocks compatible with + * the request, to prevent cross-contamination. Once + * compaction priority escalates to synchronous scans, though, + * scan all blocks to try to make forward progress. For + * movable request, this likely helps little: there shouldn't + * be many migratable pages inside non-movable blocks besides + * allocator fallbacks. For non-movable requests, this helps a + * lot, as they can finally scan movable blocks. + */ + if (cc->mode != MIGRATE_ASYNC) + return true; + + /* + * Prevent <pageblock_order unmovable/reclaimable requests from + * polluting movable blocks through fallbacks. Whole-block production + * (directly requested, or defrag_mode) is exempt as the allocator + * claims and converts these. + */ + if (cc->migratetype == MIGRATE_MOVABLE || cc->order >= pageblock_order) return is_migrate_movable(block_mt); else return block_mt == cc->migratetype; @@ -1957,12 +1989,12 @@ static unsigned long fast_find_migrateblock(struct compact_control *cc) return pfn; /* - * Only allow kcompactd and direct requests for movable pages to - * quickly clear out a MOVABLE pageblock for allocation. This - * reduces the risk that a large movable pageblock is freed for - * an unmovable/reclaimable small allocation. + * Prevent <pageblock_order unmovable/reclaimable requests from + * polluting movable blocks through fallbacks. Whole-block production + * is exempt as the allocator claims and converts these. */ - if (cc->direct_compaction && cc->migratetype != MIGRATE_MOVABLE) + if (cc->direct_compaction && cc->migratetype != MIGRATE_MOVABLE && + cc->order < pageblock_order) return pfn; /* @@ -2748,9 +2780,8 @@ out: static enum compact_result compact_zone_order(struct zone *zone, int order, gfp_t gfp_mask, enum compact_priority prio, unsigned int alloc_flags, int highest_zoneidx, - struct page **capture) + struct capture_control *capc) { - enum compact_result ret; struct compact_control cc = { .order = order, .search_order = order, @@ -2765,54 +2796,24 @@ static enum compact_result compact_zone_order(struct zone *zone, int order, .ignore_skip_hint = (prio == MIN_COMPACT_PRIORITY), .ignore_block_suitable = (prio == MIN_COMPACT_PRIORITY) }; - struct capture_control capc = { - .cc = &cc, - .page = NULL, - }; - /* - * Make sure the structs are really initialized before we expose the - * capture control, in case we are interrupted and the interrupt handler - * frees a page. - */ - barrier(); - WRITE_ONCE(current->capture_control, &capc); - - ret = compact_zone(&cc, &capc); - - /* - * Make sure we hide capture control first before we read the captured - * page pointer, otherwise an interrupt could free and capture a page - * and we would leak it. - */ - WRITE_ONCE(current->capture_control, NULL); - *capture = READ_ONCE(capc.page); - /* - * Technically, it is also possible that compaction is skipped but - * the page is still captured out of luck(IRQ came and freed the page). - * Returning COMPACT_SUCCESS in such cases helps in properly accounting - * the COMPACT[STALL|FAIL] when compaction is skipped. - */ - if (*capture) - ret = COMPACT_SUCCESS; - - return ret; + return compact_zone(&cc, capc); } /** * try_to_compact_pages - Direct compact to satisfy a high-order allocation * @gfp_mask: The GFP mask of the current allocation - * @order: The order of the current allocation + * @order: The order to try to make available * @alloc_flags: The allocation flags of the current allocation * @ac: The context of current allocation * @prio: Determines how hard direct compaction should try to succeed - * @capture: Pointer to free page created by compaction will be stored here + * @capc: Free page capture bypassing the freelist * * This is the main entry point for direct page compaction. */ enum compact_result try_to_compact_pages(gfp_t gfp_mask, unsigned int order, unsigned int alloc_flags, const struct alloc_context *ac, - enum compact_priority prio, struct page **capture) + enum compact_priority prio, struct capture_control *capc) { struct zoneref *z; struct zone *zone; @@ -2839,8 +2840,17 @@ enum compact_result try_to_compact_pages(gfp_t gfp_mask, unsigned int order, continue; } + WRITE_ONCE(capc->zone, zone); + status = compact_zone_order(zone, order, gfp_mask, prio, - alloc_flags, ac->highest_zoneidx, capture); + alloc_flags, ac->highest_zoneidx, capc); + + WRITE_ONCE(capc->zone, NULL); + + /* Stop if a page has been captured */ + if (READ_ONCE(capc->page)) + status = COMPACT_SUCCESS; + rc = max(status, rc); /* The allocation should succeed, stop compacting */ @@ -2273,6 +2273,7 @@ static unsigned long collect_longterm_unpinnable_folios( for (folio = pofs_get_folio(pofs, i); folio; folio = pofs_next_folio(folio, pofs, &i)) { + const int pin_refs = folio_has_pincount(folio) ? 1 : GUP_PIN_COUNTING_BIAS; if (folio_is_longterm_pinnable(folio)) continue; @@ -2287,15 +2288,20 @@ static unsigned long collect_longterm_unpinnable_folios( continue; } + /* + * We drain not only to make the folio_isolate_lru() succeed, + * but also to remove any other folio references from LRU + * caches. + */ if (drained == 0 && folio_may_be_lru_cached(folio) && folio_ref_count(folio) != - folio_expected_ref_count(folio) + 1) { + folio_expected_ref_count(folio) + pin_refs) { lru_add_drain(); drained = 1; } if (drained == 1 && folio_may_be_lru_cached(folio) && folio_ref_count(folio) != - folio_expected_ref_count(folio) + 1) { + folio_expected_ref_count(folio) + pin_refs) { lru_add_drain_all(); drained = 2; } diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 227aeffae8ee..8564a92d83f0 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2293,9 +2293,11 @@ static pmd_t move_soft_dirty_pmd(pmd_t pmd) static pmd_t clear_uffd_wp_pmd(pmd_t pmd) { + if (pmd_none(pmd)) + return pmd; if (pmd_present(pmd)) pmd = pmd_clear_uffd_wp(pmd); - else if (is_swap_pmd(pmd)) + else pmd = pmd_swp_clear_uffd_wp(pmd); return pmd; diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 5515870b5b15..e9f4cbf50a2b 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -5876,6 +5876,7 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, bool adjust_reservation; unsigned long last_addr_mask; + i_mmap_assert_write_locked(vma->vm_file->f_mapping); WARN_ON(!is_vm_hugetlb_page(vma)); BUG_ON(start & ~huge_page_mask(h)); BUG_ON(end & ~huge_page_mask(h)); @@ -5967,7 +5968,10 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, /* * Restore the reservation for anonymous page, otherwise the - * backing page could be stolen by someone. + * backing page could be stolen by someone. Restore only on the + * last unmap, otherwise the owner could empty its resv map + * while the folio is still mapped by a child. Note that holding + * i_mmap_lock_write is needed to check the number of mappings. * If there we are freeing a surplus, do not set the restore * reservation bit. */ @@ -5975,7 +5979,7 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, spin_lock_irq(&hugetlb_lock); if (!h->surplus_huge_pages && __vma_private_lock(vma) && - folio_test_anon(folio)) { + !folio_mapped(folio) && folio_test_anon(folio)) { folio_set_hugetlb_restore_reserve(folio); /* Reservation to be adjusted after the spin lock */ adjust_reservation = true; diff --git a/mm/internal.h b/mm/internal.h index f5c0d927924d..ef42eee87c7b 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -908,7 +908,15 @@ struct compact_control { * immediately when one is created during the free path. */ struct capture_control { - struct compact_control *cc; + struct zone *zone; + int migratetype; + /* + * Allocation request order. May differ from the compaction + * order: defrag_mode promotes sub-block allocations to + * pageblock-order compaction; capture still matches at the + * original allocation order so prep_new_page() is consistent. + */ + int order; struct page *page; }; diff --git a/mm/kasan/quarantine.c b/mm/kasan/quarantine.c index 6958aa713c67..16f4e67beee8 100644 --- a/mm/kasan/quarantine.c +++ b/mm/kasan/quarantine.c @@ -355,7 +355,12 @@ void kasan_quarantine_remove_cache(struct kmem_cache *cache) */ on_each_cpu(per_cpu_remove_cache, cache, 1); - for_each_online_cpu(cpu) { + /* + * A CPU can go offline after on_each_cpu() returns, leaving cache + * objects on that CPU's shrink list. Scan all possible CPUs to + * drain those lists. + */ + for_each_possible_cpu(cpu) { sq = per_cpu_ptr(&shrink_qlist, cpu); raw_spin_lock_irqsave(&sq->lock, flags); qlist_move_cache(&sq->qlist, &to_free, cache); diff --git a/mm/kmemleak.c b/mm/kmemleak.c index 415b154fdf38..452f3714f337 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -1690,6 +1690,42 @@ unlock_put: } /* + * Scan all task kernel stacks, rescheduling between tasks. Each task is looked + * up and pinned within its own RCU read-side section, so no lock is held across + * the scan and the walk cannot trip the soft lockup watchdog. + */ +static void kmemleak_scan_task_stacks(void) +{ + struct pid *pid; + int nr = 1; + + do { + struct task_struct *p = NULL; + + rcu_read_lock(); + pid = find_ge_pid(nr, &init_pid_ns); + if (pid) { + nr = pid_nr(pid) + 1; + p = pid_task(pid, PIDTYPE_PID); + if (p) + get_task_struct(p); + } + rcu_read_unlock(); + + if (p) { + void *stack = try_get_task_stack(p); + + if (stack) { + scan_block(stack, stack + THREAD_SIZE, NULL); + put_task_stack(p); + } + put_task_struct(p); + } + cond_resched(); + } while (pid && !scan_should_stop()); +} + +/* * Scan data sections and all the referenced memory blocks allocated via the * kernel's standard allocators. This function must be called with the * scan_mutex held. @@ -1780,19 +1816,8 @@ static void kmemleak_scan(void) /* * Scanning the task stacks (may introduce false negatives). */ - if (kmemleak_stack_scan) { - struct task_struct *p, *g; - - rcu_read_lock(); - for_each_process_thread(g, p) { - void *stack = try_get_task_stack(p); - if (stack) { - scan_block(stack, stack + THREAD_SIZE, NULL); - put_task_stack(p); - } - } - rcu_read_unlock(); - } + if (kmemleak_stack_scan) + kmemleak_scan_task_stacks(); /* * Scan the objects already referenced from the sections scanned diff --git a/mm/memcontrol-v1.c b/mm/memcontrol-v1.c index 6eed14bff742..74d3a4d78ec6 100644 --- a/mm/memcontrol-v1.c +++ b/mm/memcontrol-v1.c @@ -1139,13 +1139,13 @@ static ssize_t memcg_write_event_control(struct kernfs_open_file *of, event->unregister_event = mem_cgroup_usage_unregister_event; } else if (!strcmp(name, "memory.oom_control")) { pr_warn_once("oom_control is deprecated and will be removed. " - "Please report your usecase to linux-mm-@kvack.org" + "Please report your usecase to linux-mm@kvack.org" " if you depend on this functionality.\n"); event->register_event = mem_cgroup_oom_register_event; event->unregister_event = mem_cgroup_oom_unregister_event; } else if (!strcmp(name, "memory.pressure_level")) { pr_warn_once("pressure_level is deprecated and will be removed. " - "Please report your usecase to linux-mm-@kvack.org " + "Please report your usecase to linux-mm@kvack.org " "if you depend on this functionality.\n"); event->register_event = vmpressure_register_event; event->unregister_event = vmpressure_unregister_event; @@ -1982,7 +1982,7 @@ static int mem_cgroup_oom_control_write(struct cgroup_subsys_state *css, struct mem_cgroup *memcg = mem_cgroup_from_css(css); pr_warn_once("oom_control is deprecated and will be removed. " - "Please report your usecase to linux-mm-@kvack.org if you " + "Please report your usecase to linux-mm@kvack.org if you " "depend on this functionality.\n"); /* cannot set to root cgroup and only 0 and 1 are allowed */ diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 752d98fd3921..898821793349 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -3809,9 +3809,11 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css) page_counter_init(&memcg->swap, &parent->swap, false); #ifdef CONFIG_MEMCG_V1 memcg->memory.track_failcnt = !memcg_on_dfl; + memcg->memsw.track_failcnt = !memcg_on_dfl; WRITE_ONCE(memcg->oom_kill_disable, READ_ONCE(parent->oom_kill_disable)); page_counter_init(&memcg->kmem, &parent->kmem, false); page_counter_init(&memcg->tcpmem, &parent->tcpmem, false); + memcg->tcpmem.track_failcnt = !memcg_on_dfl; #endif } else { init_memcg_stats(); @@ -4028,6 +4030,7 @@ static void flush_nmi_stats(struct mem_cgroup *memcg, struct mem_cgroup *parent, int index = memcg_stats_index(MEMCG_KMEM); memcg->vmstats->state[index] += kmem; + memcg->vmstats->state_local[index] += kmem; if (parent) parent->vmstats->state_pending[index] += kmem; } @@ -4045,9 +4048,11 @@ static void flush_nmi_stats(struct mem_cgroup *memcg, struct mem_cgroup *parent, int index = memcg_stats_index(NR_SLAB_RECLAIMABLE_B); lstats->state[index] += slab; + lstats->state_local[index] += slab; if (plstats) plstats->state_pending[index] += slab; memcg->vmstats->state[index] += slab; + memcg->vmstats->state_local[index] += slab; if (parent) parent->vmstats->state_pending[index] += slab; } @@ -4056,9 +4061,11 @@ static void flush_nmi_stats(struct mem_cgroup *memcg, struct mem_cgroup *parent, int index = memcg_stats_index(NR_SLAB_UNRECLAIMABLE_B); lstats->state[index] += slab; + lstats->state_local[index] += slab; if (plstats) plstats->state_pending[index] += slab; memcg->vmstats->state[index] += slab; + memcg->vmstats->state_local[index] += slab; if (parent) parent->vmstats->state_pending[index] += slab; } @@ -4378,6 +4385,9 @@ static ssize_t memory_high_write(struct kernfs_open_file *of, unsigned long nr_pages = page_counter_read(&memcg->memory); unsigned long reclaimed; + if (high != READ_ONCE(memcg->memory.high)) + break; + if (nr_pages <= high) break; @@ -4429,6 +4439,9 @@ static ssize_t memory_max_write(struct kernfs_open_file *of, for (;;) { unsigned long nr_pages = page_counter_read(&memcg->memory); + if (max != READ_ONCE(memcg->memory.max)) + break; + if (nr_pages <= max) break; diff --git a/mm/memory.c b/mm/memory.c index 6b4cdb8bd8db..72793ec63107 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -6320,34 +6320,39 @@ retry_pud: if (pmd_none(*vmf.pmd) && thp_vma_allowable_order(vma, vm_flags, TVA_PAGEFAULT, PMD_ORDER)) { ret = create_huge_pmd(&vmf); - if (!(ret & VM_FAULT_FALLBACK)) + if (ret & VM_FAULT_FALLBACK) + goto fallback; + else return ret; - } else { - vmf.orig_pmd = pmdp_get_lockless(vmf.pmd); + } - if (unlikely(is_swap_pmd(vmf.orig_pmd))) { - VM_BUG_ON(thp_migration_supported() && - !pmd_is_migration_entry(vmf.orig_pmd)); - if (pmd_is_migration_entry(vmf.orig_pmd)) - pmd_migration_entry_wait(mm, vmf.pmd); - return 0; - } - if (pmd_trans_huge(vmf.orig_pmd)) { - if (pmd_protnone(vmf.orig_pmd) && vma_is_accessible(vma)) - return do_huge_pmd_numa_page(&vmf); + vmf.orig_pmd = pmdp_get_lockless(vmf.pmd); + if (pmd_none(vmf.orig_pmd)) + goto fallback; - if ((flags & (FAULT_FLAG_WRITE|FAULT_FLAG_UNSHARE)) && - !pmd_write(vmf.orig_pmd)) { - ret = wp_huge_pmd(&vmf); - if (!(ret & VM_FAULT_FALLBACK)) - return ret; - } else { - huge_pmd_set_accessed(&vmf); - return 0; - } + if (unlikely(!pmd_present(vmf.orig_pmd))) { + VM_BUG_ON(thp_migration_supported() && + !pmd_is_migration_entry(vmf.orig_pmd)); + if (pmd_is_migration_entry(vmf.orig_pmd)) + pmd_migration_entry_wait(mm, vmf.pmd); + return 0; + } + if (pmd_trans_huge(vmf.orig_pmd)) { + if (pmd_protnone(vmf.orig_pmd) && vma_is_accessible(vma)) + return do_huge_pmd_numa_page(&vmf); + + if ((flags & (FAULT_FLAG_WRITE|FAULT_FLAG_UNSHARE)) && + !pmd_write(vmf.orig_pmd)) { + ret = wp_huge_pmd(&vmf); + if (!(ret & VM_FAULT_FALLBACK)) + return ret; + } else { + huge_pmd_set_accessed(&vmf); + return 0; } } +fallback: return handle_pte_fault(&vmf); } diff --git a/mm/mempolicy.c b/mm/mempolicy.c index b4aa4f2cb8ec..d18cee845354 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -1989,24 +1989,15 @@ struct mempolicy *get_vma_policy(struct vm_area_struct *vma, bool vma_policy_mof(struct vm_area_struct *vma) { struct mempolicy *pol; + pgoff_t ilx; + bool mof; - if (vma->vm_ops && vma->vm_ops->get_policy) { - bool ret = false; - pgoff_t ilx; /* ignored here */ - - pol = vma->vm_ops->get_policy(vma, vma->vm_start, &ilx); - if (pol && (pol->flags & MPOL_F_MOF)) - ret = true; - mpol_cond_put(pol); - - return ret; - } - - pol = vma->vm_policy; + pol = __get_vma_policy(vma, vma->vm_start, &ilx); if (!pol) pol = get_task_policy(current); - - return pol->flags & MPOL_F_MOF; + mof = pol->flags & MPOL_F_MOF; + mpol_cond_put(pol); + return mof; } bool apply_policy_zone(struct mempolicy *policy, enum zone_type zone) diff --git a/mm/migrate.c b/mm/migrate.c index e66d9cc67dda..d03b5d265e71 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -1821,7 +1821,7 @@ static int migrate_pages_batch(struct list_head *from, is_thp = folio_test_pmd_mappable(folio); nr_pages = folio_nr_pages(folio); - cond_resched(); + cond_resched_tasks_rcu_qs(); /* * The rare folio on the deferred split list should diff --git a/mm/mm_init.c b/mm/mm_init.c index d2d915984611..922493a35a28 100644 --- a/mm/mm_init.c +++ b/mm/mm_init.c @@ -2238,10 +2238,13 @@ bool __init deferred_grow_zone(struct zone *zone, unsigned int order) } /* - * There were no pages to initialize and free which means the zone's - * memory map is completely initialized. + * The loop only tests spfn before entering an iteration, so on exit it + * may point up to a section past the end of the zone. When it does, + * the rest of the zone has already been handed to + * deferred_init_memmap_chunk() and nothing is left to initialize. */ - pgdat->first_deferred_pfn = nr_pages ? spfn : ULONG_MAX; + pgdat->first_deferred_pfn = + spfn < zone_end_pfn(zone) ? spfn : ULONG_MAX; pgdat_resize_unlock(pgdat, &flags); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 775e02b797a3..af37e0c2d6f8 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -763,14 +763,14 @@ static inline struct capture_control *task_capc(struct zone *zone) return unlikely(capc) && !(current->flags & PF_KTHREAD) && !capc->page && - capc->cc->zone == zone ? capc : NULL; + capc->zone == zone ? capc : NULL; } static inline bool compaction_capture(struct capture_control *capc, struct page *page, int order, int migratetype) { - if (!capc || order != capc->cc->order) + if (!capc || order != capc->order) return false; /* Do not accidentally pollute CMA or isolated regions*/ @@ -786,12 +786,12 @@ compaction_capture(struct capture_control *capc, struct page *page, * have trouble finding a high-order free page. */ if (order < pageblock_order && migratetype == MIGRATE_MOVABLE && - capc->cc->migratetype != MIGRATE_MOVABLE) + capc->migratetype != MIGRATE_MOVABLE) return false; - if (migratetype != capc->cc->migratetype) - trace_mm_page_alloc_extfrag(page, capc->cc->order, order, - capc->cc->migratetype, migratetype); + if (migratetype != capc->migratetype) + trace_mm_page_alloc_extfrag(page, capc->order, order, + capc->migratetype, migratetype); capc->page = page; return true; @@ -4132,18 +4132,67 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, struct page *page = NULL; unsigned long pflags; unsigned int noreclaim_flag; + struct capture_control capc = { + .zone = NULL, + .migratetype = ac->migratetype, + .order = order, + .page = NULL, + }; + int compact_order = order; - if (!order) + /* + * If fallbacks are not permitted (defrag_mode), we either + * need to reclaim space in a block of matching type, or clear + * out an entire block to allow __rmqueue_claim() to convert. + * + * Reclaim by itself is primarily freeing space in movable + * blocks, since that's where the LRU pages live. So this + * works for movable requests, but not for others. + * + * For those, promote the order to help make blocks, instead + * of spinning in reclaim alone unproductively. + */ + if ((alloc_flags & ALLOC_NOFRAGMENT) && ac->migratetype != MIGRATE_MOVABLE) + compact_order = max(order, pageblock_order); + + if (!compact_order) return NULL; psi_memstall_enter(&pflags); delayacct_compact_start(); + fs_reclaim_acquire(gfp_mask); noreclaim_flag = memalloc_noreclaim_save(); - *compact_result = try_to_compact_pages(gfp_mask, order, alloc_flags, ac, - prio, &page); + /* + * Make sure the structs are really initialized before we expose the + * capture control, in case we are interrupted and the interrupt handler + * frees a page. + */ + barrier(); + WRITE_ONCE(current->capture_control, &capc); + + *compact_result = try_to_compact_pages(gfp_mask, compact_order, + alloc_flags, ac, prio, &capc); + + /* + * Make sure we hide capture control first before we read the captured + * page pointer, otherwise an interrupt could free and capture a page + * and we would leak it. + */ + WRITE_ONCE(current->capture_control, NULL); + page = READ_ONCE(capc.page); + + /* + * Technically, it is also possible that compaction is skipped but + * the page is still captured out of luck(IRQ came and freed the page). + * Returning COMPACT_SUCCESS in such cases helps in properly accounting + * the COMPACT[STALL|FAIL] when compaction is skipped. + */ + if (page) + *compact_result = COMPACT_SUCCESS; memalloc_noreclaim_restore(noreclaim_flag); + fs_reclaim_release(gfp_mask); psi_memstall_leave(&pflags); delayacct_compact_end(); @@ -4167,7 +4216,7 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, struct zone *zone = page_zone(page); zone->compact_blockskip_flush = false; - compaction_defer_reset(zone, order, true); + compaction_defer_reset(zone, compact_order, true); count_vm_event(COMPACTSUCCESS); return page; } @@ -4404,9 +4453,14 @@ __alloc_pages_direct_reclaim(gfp_t gfp_mask, unsigned int order, struct page *page = NULL; unsigned long pflags; bool drained = false; + int reclaim_order = order; + + /* Match the slowpath compaction promotion in __alloc_pages_direct_compact */ + if ((alloc_flags & ALLOC_NOFRAGMENT) && ac->migratetype != MIGRATE_MOVABLE) + reclaim_order = max(order, pageblock_order); psi_memstall_enter(&pflags); - *did_some_progress = __perform_reclaim(gfp_mask, order, ac); + *did_some_progress = __perform_reclaim(gfp_mask, reclaim_order, ac); if (unlikely(!(*did_some_progress))) goto out; diff --git a/mm/page_table_check.c b/mm/page_table_check.c index 0a5ab62c9c59..91c4dacc41fb 100644 --- a/mm/page_table_check.c +++ b/mm/page_table_check.c @@ -223,10 +223,14 @@ EXPORT_SYMBOL(__page_table_check_ptes_set); static inline void page_table_check_pmd_flags(pmd_t pmd) { - if (pmd_present(pmd) && pmd_uffd_wp(pmd)) - WARN_ON_ONCE(pmd_write(pmd)); - else if (is_swap_pmd(pmd) && pmd_swp_uffd_wp(pmd)) - WARN_ON_ONCE(swap_cached_writable(pmd_to_swp_entry(pmd))); + if (pmd_present(pmd)) { + if (pmd_uffd_wp(pmd)) + WARN_ON_ONCE(pmd_write(pmd)); + } else if (pmd_swp_uffd_wp(pmd)) { + swp_entry_t entry = pmd_to_swp_entry(pmd); + + WARN_ON_ONCE(swap_cached_writable(entry)); + } } void __page_table_check_pmds_set(struct mm_struct *mm, pmd_t *pmdp, pmd_t pmd, diff --git a/mm/pagewalk.c b/mm/pagewalk.c index ca6c51598aed..47befc414adc 100644 --- a/mm/pagewalk.c +++ b/mm/pagewalk.c @@ -127,6 +127,7 @@ static int walk_pmd_range(pud_t *pud, unsigned long addr, unsigned long end, pmd = pmd_offset(pud, addr); do { again: + walk->action = ACTION_SUBTREE; next = pmd_addr_end(addr, end); if (pmd_none(*pmd)) { if (has_install) @@ -139,8 +140,6 @@ again: continue; } - walk->action = ACTION_SUBTREE; - /* * This implies that each ->pmd_entry() handler * needs to know about pmd_trans_huge() pmds @@ -197,6 +196,7 @@ static int walk_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end, pud = pud_offset(p4d, addr); do { again: + walk->action = ACTION_SUBTREE; next = pud_addr_end(addr, end); if (pud_none(*pud)) { if (has_install) @@ -209,8 +209,6 @@ static int walk_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end, continue; } - walk->action = ACTION_SUBTREE; - if (ops->pud_entry) err = ops->pud_entry(pud, addr, next, walk); if (err) diff --git a/mm/rmap.c b/mm/rmap.c index 4c78c7109909..4348b35db465 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1983,20 +1983,26 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma, /* Unexpected PMD-mapped THP? */ VM_BUG_ON_FOLIO(!pvmw.pte, folio); - /* - * Handle PFN swap PTEs, such as device-exclusive ones, that - * actually map pages. - */ - pteval = ptep_get(pvmw.pte); + address = pvmw.address; + if (folio_test_hugetlb(folio)) { + pteval = huge_ptep_get(mm, address, pvmw.pte); + } else { + pteval = ptep_get(pvmw.pte); + } if (likely(pte_present(pteval))) { pfn = pte_pfn(pteval); } else { - pfn = swp_offset_pfn(pte_to_swp_entry(pteval)); + /* + * Handle PFN swap PTEs, such as device-exclusive ones, + * that actually map pages. + */ + const softleaf_t entry = softleaf_from_pte(pteval); + + pfn = softleaf_to_pfn(entry); VM_WARN_ON_FOLIO(folio_test_hugetlb(folio), folio); } subpage = folio_page(folio, pfn - folio_pfn(folio)); - address = pvmw.address; anon_exclusive = folio_test_anon(folio) && PageAnonExclusive(subpage); diff --git a/mm/swapfile.c b/mm/swapfile.c index 841cf1ab8330..cf33c3b2c31f 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -1613,11 +1613,11 @@ struct swap_info_struct *get_swap_device(swp_entry_t entry) return si; bad_nofile: - pr_err("%s: %s%08lx\n", __func__, Bad_file, entry.val); + pr_err_ratelimited("%s: %s%08lx\n", __func__, Bad_file, entry.val); out: return NULL; put_out: - pr_err("%s: %s%08lx\n", __func__, Bad_offset, entry.val); + pr_err_ratelimited("%s: %s%08lx\n", __func__, Bad_offset, entry.val); percpu_ref_put(&si->users); return NULL; } @@ -3753,7 +3753,7 @@ static int __swap_duplicate(swp_entry_t entry, unsigned char usage, int nr) si = swap_entry_to_info(entry); if (WARN_ON_ONCE(!si)) { - pr_err("%s%08lx\n", Bad_file, entry.val); + pr_err_ratelimited("%s%08lx\n", Bad_file, entry.val); return -EINVAL; } diff --git a/mm/vmscan.c b/mm/vmscan.c index 95b1179a14e7..05027b320eda 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -201,6 +201,13 @@ struct scan_control { */ int vm_swappiness = 60; +static int sc_swappiness(struct scan_control *sc, struct mem_cgroup *memcg) +{ + if (sc->proactive && sc->proactive_swappiness) + return *sc->proactive_swappiness; + return mem_cgroup_swappiness(memcg); +} + #ifdef CONFIG_MEMCG /* Returns true for reclaim through cgroup limits or cgroup interfaces. */ @@ -241,13 +248,6 @@ static bool writeback_throttling_sane(struct scan_control *sc) #endif return false; } - -static int sc_swappiness(struct scan_control *sc, struct mem_cgroup *memcg) -{ - if (sc->proactive && sc->proactive_swappiness) - return *sc->proactive_swappiness; - return mem_cgroup_swappiness(memcg); -} #else static bool cgroup_reclaim(struct scan_control *sc) { @@ -263,11 +263,6 @@ static bool writeback_throttling_sane(struct scan_control *sc) { return true; } - -static int sc_swappiness(struct scan_control *sc, struct mem_cgroup *memcg) -{ - return READ_ONCE(vm_swappiness); -} #endif /* for_each_managed_zone_pgdat - helper macro to iterate over all managed zones in a pgdat up to @@ -5864,7 +5859,7 @@ static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc) } } - cond_resched(); + cond_resched_tasks_rcu_qs(); if (nr_reclaimed < nr_to_reclaim || proportional_reclaim) continue; diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c index bb1f1e124dc0..3564b37f1fce 100644 --- a/mm/zsmalloc.c +++ b/mm/zsmalloc.c @@ -508,6 +508,11 @@ static int get_size_class_index(int size) return min_t(int, ZS_SIZE_CLASSES - 1, idx); } +static struct size_class *lookup_size_class(struct zs_pool *pool, size_t size) +{ + return pool->size_class[get_size_class_index(size + ZS_HANDLE_SIZE)]; +} + static inline void class_stat_add(struct size_class *class, int type, unsigned long cnt) { @@ -1052,7 +1057,7 @@ unsigned int zs_lookup_class_index(struct zs_pool *pool, unsigned int size) { struct size_class *class; - class = pool->size_class[get_size_class_index(size)]; + class = lookup_size_class(pool, size); return class->index; } @@ -1279,9 +1284,7 @@ unsigned long zs_malloc(struct zs_pool *pool, size_t size, gfp_t gfp, if (!handle) return (unsigned long)ERR_PTR(-ENOMEM); - /* extra space in chunk to keep the handle */ - size += ZS_HANDLE_SIZE; - class = pool->size_class[get_size_class_index(size)]; + class = lookup_size_class(pool, size); /* class->lock effectively protects the zpage migration */ spin_lock(&class->lock); diff --git a/mm/zswap.c b/mm/zswap.c index 12fb0e395412..18249dd96ef8 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -1375,11 +1375,12 @@ static void shrink_worker(struct work_struct *w) } while (memcg && !mem_cgroup_tryget_online(memcg)); spin_unlock(&zswap_shrink_lock); - if (!memcg) { - /* - * Continue shrinking without incrementing failures if - * we found candidate memcgs in the last tree walk. - */ + /* + * A NULL memcg ends a full hierarchy pass (except when memcg is + * disabled, where it is always NULL: fall through to the root LRU). + * Count a failure only if the last pass found no candidates. + */ + if (!memcg && !mem_cgroup_disabled()) { if (!attempts && ++failures == MAX_RECLAIM_RETRIES) break; @@ -1398,7 +1399,7 @@ static void shrink_worker(struct work_struct *w) * and failures. */ if (ret == -ENOENT) - continue; + goto resched; ++attempts; if (ret && ++failures == MAX_RECLAIM_RETRIES) diff --git a/net/bluetooth/eir.c b/net/bluetooth/eir.c index 1de5f9df6eec..a55696820b22 100644 --- a/net/bluetooth/eir.c +++ b/net/bluetooth/eir.c @@ -369,6 +369,7 @@ u8 eir_create_scan_rsp(struct hci_dev *hdev, u8 instance, u8 *ptr) void *eir_get_service_data(u8 *eir, size_t eir_len, u16 uuid, size_t *len) { + const u8 *eir_end = eir + eir_len; size_t dlen; while ((eir = eir_get_data(eir, eir_len, EIR_SERVICE_DATA, &dlen))) { @@ -381,7 +382,7 @@ void *eir_get_service_data(u8 *eir, size_t eir_len, u16 uuid, size_t *len) } eir += dlen; - eir_len -= dlen; + eir_len = eir_end - eir; } return NULL; diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index e630d6369a0c..eb91dc9fbe86 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -1298,7 +1298,8 @@ static void hci_le_conn_failed(struct hci_conn *conn, u8 status) /* Enable advertising in case this was a failed connection * attempt as a peripheral. */ - hci_enable_advertising(hdev); + if (conn->role == HCI_ROLE_SLAVE) + hci_enable_advertising(hdev); } /* This function requires the caller holds hdev->lock */ diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index a1d7e7985f76..f63f993226d5 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -4130,7 +4130,7 @@ static int hci_send_cmd_sync(struct hci_dev *hdev, struct sk_buff *skb) if (READ_ONCE(hdev->req_status) == HCI_REQ_PEND && !hci_dev_test_and_set_flag(hdev, HCI_CMD_PENDING)) { kfree_skb(hdev->req_skb); - hdev->req_skb = skb_clone(hdev->sent_cmd, GFP_KERNEL); + hdev->req_skb = skb_get(hdev->sent_cmd); } return err; diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 3c66262c1f4d..031ee997bb92 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -5665,10 +5665,11 @@ static void le_conn_complete_evt(struct hci_dev *hdev, u8 status, hci_dev_lock(hdev); - /* All controllers implicitly stop advertising in the event of a - * connection, so ensure that the state bit is cleared. + /* Advertising stops when a connection is created. On a failed + * connection it keeps running, so leave the state bit alone. */ - hci_dev_clear_flag(hdev, HCI_LE_ADV); + if (!status) + hci_dev_clear_flag(hdev, HCI_LE_ADV); /* Check for existing connection: * diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c index 5c7cd2a38d51..27261f8e904e 100644 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@ -5300,6 +5300,7 @@ int hci_dev_open_sync(struct hci_dev *hdev) if (hdev->req_skb) { kfree_skb(hdev->req_skb); hdev->req_skb = NULL; + hci_dev_clear_flag(hdev, HCI_CMD_PENDING); } clear_bit(HCI_RUNNING, &hdev->flags); @@ -5484,6 +5485,7 @@ int hci_dev_close_sync(struct hci_dev *hdev) if (hdev->req_skb) { kfree_skb(hdev->req_skb); hdev->req_skb = NULL; + hci_dev_clear_flag(hdev, HCI_CMD_PENDING); } clear_bit(HCI_RUNNING, &hdev->flags); diff --git a/net/bluetooth/iso.c b/net/bluetooth/iso.c index 022978f4ffd6..03260e1e265c 100644 --- a/net/bluetooth/iso.c +++ b/net/bluetooth/iso.c @@ -2148,6 +2148,14 @@ static void iso_conn_ready(struct iso_conn *conn) lock_sock(parent); + /* The listener may have been closed concurrently. */ + if (parent->sk_state != BT_LISTEN || + sock_flag(parent, SOCK_ZAPPED)) { + release_sock(parent); + sock_put(parent); + return; + } + sk = iso_sock_alloc(sock_net(parent), NULL, BTPROTO_ISO, GFP_ATOMIC, 0); if (!sk) { diff --git a/net/bluetooth/rfcomm/core.c b/net/bluetooth/rfcomm/core.c index fe5ea8db2188..bdc9a7cd9405 100644 --- a/net/bluetooth/rfcomm/core.c +++ b/net/bluetooth/rfcomm/core.c @@ -2208,9 +2208,13 @@ static void rfcomm_security_cfm(struct hci_conn *conn, u8 status, u8 encrypt) BT_DBG("conn %p status 0x%02x encrypt 0x%02x", conn, status, encrypt); + rfcomm_lock(); + s = rfcomm_session_get(&conn->hdev->bdaddr, &conn->dst); - if (!s) + if (!s) { + rfcomm_unlock(); return; + } list_for_each_entry_safe(d, n, &s->dlcs, list) { if (test_and_clear_bit(RFCOMM_SEC_PENDING, &d->flags)) { @@ -2242,6 +2246,8 @@ static void rfcomm_security_cfm(struct hci_conn *conn, u8 status, u8 encrypt) set_bit(RFCOMM_AUTH_REJECT, &d->flags); } + rfcomm_unlock(); + rfcomm_schedule(); } diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index 7108a3153a16..46b2c2ae7778 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -6,6 +6,7 @@ #include <linux/err.h> #include <linux/highmem.h> #include <linux/mm.h> +#include <linux/overflow.h> #include <linux/pagemap.h> #include <linux/slab.h> #include <linux/uaccess.h> @@ -5805,6 +5806,31 @@ static inline void convert_extent_map(struct ceph_sparse_read *sr) } #endif +static bool sparse_extent_map_valid(struct ceph_sparse_read *sr) +{ + u64 req_end, pos; + int i; + + if (check_add_overflow(sr->sr_req_off, sr->sr_req_len, &req_end)) + return false; + + pos = sr->sr_req_off; + for (i = 0; i < sr->sr_count; i++) { + struct ceph_sparse_extent *ext = &sr->sr_extent[i]; + u64 end; + + if (ext->off < pos) + return false; + if (check_add_overflow(ext->off, ext->len, &end)) + return false; + if (end > req_end) + return false; + pos = end; + } + + return true; +} + static int osd_sparse_read(struct ceph_connection *con, struct ceph_msg_data_cursor *cursor, char **pbuf) @@ -5856,6 +5882,10 @@ next_op: fallthrough; case CEPH_SPARSE_READ_DATA_LEN: convert_extent_map(sr); + if (!sparse_extent_map_valid(sr)) { + pr_warn_ratelimited("invalid sparse extent map\n"); + return -EREMOTEIO; + } ret = sizeof(sr->sr_datalen); *pbuf = (char *)&sr->sr_datalen; sr->sr_state = CEPH_SPARSE_READ_DATA_PRE; diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c index ff06ba2965cf..68bd45852fc3 100644 --- a/net/ceph/osdmap.c +++ b/net/ceph/osdmap.c @@ -519,6 +519,8 @@ static struct crush_map *crush_decode(void *pbyval, void *end) ceph_decode_need(p, end, 4*sizeof(u32), bad); b->id = ceph_decode_32(p); + if (b->id != -1 - i) + goto bad; b->type = ceph_decode_16(p); if (b->type == 0) goto bad; diff --git a/net/core/skbuff.c b/net/core/skbuff.c index e75baa72a22e..31c2c5a97a35 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -1373,10 +1373,13 @@ EXPORT_SYMBOL(skb_dump); * * Report xmit error if a device callback is tracking this skb. * skb must be freed afterwards. + * + * Does nothing for a cloned skb: the zerocopy state lives in + * skb_shinfo(), which the clones share. */ void skb_tx_error(struct sk_buff *skb) { - if (skb) { + if (skb && !skb_cloned(skb)) { skb_zcopy_downgrade_managed(skb); skb_zcopy_clear(skb, true); } diff --git a/net/core/xdp.c b/net/core/xdp.c index 1948ef4a41aa..7a28900c52c6 100644 --- a/net/core/xdp.c +++ b/net/core/xdp.c @@ -585,7 +585,7 @@ struct xdp_frame *xdp_convert_zc_to_xdp_frame(struct xdp_buff *xdp) xdp->data - xdp->data_meta; totsize = xdp->data_end - xdp->data + metasize; - if (sizeof(*xdpf) + totsize > PAGE_SIZE) + if (sizeof(*xdpf) + totsize > SKB_WITH_OVERHEAD(PAGE_SIZE)) return NULL; page = dev_alloc_page(); @@ -602,7 +602,7 @@ struct xdp_frame *xdp_convert_zc_to_xdp_frame(struct xdp_buff *xdp) xdpf->data = addr + metasize; xdpf->len = totsize - metasize; - xdpf->headroom = 0; + xdpf->headroom = metasize; xdpf->metasize = metasize; xdpf->frame_sz = PAGE_SIZE; xdpf->mem_type = MEM_TYPE_PAGE_ORDER0; diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index 50d0f5fe4e4c..e9da39010f8b 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -317,7 +317,7 @@ static int ip_tunnel_bind_dev(struct net_device *dev) mtu = min(tdev->mtu, IP_MAX_MTU); } - dev->needed_headroom = t_hlen + hlen; + dev->needed_headroom = ip_tunnel_limit_headroom(t_hlen + hlen); mtu -= t_hlen + (dev->type == ARPHRD_ETHER ? dev->hard_header_len : 0); if (mtu < IPV4_MIN_MTU) diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index 94e974c201f0..4c2447d770e4 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -248,7 +248,7 @@ static int ipip_tunnel_rcv(struct sk_buff *skb, u8 ipproto) tun_dst = ip_tun_rx_dst(skb, flags, 0, 0); if (!tun_dst) - return 0; + goto drop; ip_tunnel_md_udp_encap(skb, &tun_dst->u.tun_info); } skb_reset_mac_header(skb); diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index ca9eaee4c2ef..f5b6e895b096 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -2168,6 +2168,9 @@ int ip_mr_input(struct sk_buff *skb) if (IPCB(skb)->flags & IPSKB_FORWARDED) goto dont_forward; + if (!local) + skb_orphan(skb); + mrt = ipmr_rt_fib_lookup(net, skb); if (IS_ERR(mrt)) { kfree_skb(skb); diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c index fbc0df2daed3..15fb42ca5eed 100644 --- a/net/ipv6/exthdrs.c +++ b/net/ipv6/exthdrs.c @@ -371,23 +371,16 @@ static void seg6_update_csum(struct sk_buff *skb) (__be32 *)addr); } -static int ipv6_srh_rcv(struct sk_buff *skb) +static int ipv6_srh_rcv(struct sk_buff *skb, struct inet6_dev *idev) { struct inet6_skb_parm *opt = IP6CB(skb); struct net *net = dev_net(skb->dev); struct ipv6_sr_hdr *hdr; - struct inet6_dev *idev; struct in6_addr *addr; int accept_seg6; hdr = (struct ipv6_sr_hdr *)skb_transport_header(skb); - idev = __in6_dev_get(skb->dev); - if (!idev) { - kfree_skb(skb); - return -1; - } - accept_seg6 = min(READ_ONCE(net->ipv6.devconf_all->seg6_enabled), READ_ONCE(idev->cnf.seg6_enabled)); @@ -488,12 +481,11 @@ looped_back: return -1; } -static int ipv6_rpl_srh_rcv(struct sk_buff *skb) +static int ipv6_rpl_srh_rcv(struct sk_buff *skb, struct inet6_dev *idev) { struct ipv6_rpl_sr_hdr *hdr, *ohdr, *chdr; struct inet6_skb_parm *opt = IP6CB(skb); struct net *net = dev_net(skb->dev); - struct inet6_dev *idev; struct ipv6hdr *oldhdr; unsigned int chdr_len; unsigned char *buf; @@ -502,8 +494,6 @@ static int ipv6_rpl_srh_rcv(struct sk_buff *skb) u64 n = 0; u32 r; - idev = __in6_dev_get(skb->dev); - accept_rpl_seg = min(READ_ONCE(net->ipv6.devconf_all->rpl_seg_enabled), READ_ONCE(idev->cnf.rpl_seg_enabled)); if (!accept_rpl_seg) { @@ -692,10 +682,14 @@ static int ipv6_rthdr_rcv(struct sk_buff *skb) switch (hdr->type) { case IPV6_SRCRT_TYPE_4: /* segment routing */ - return ipv6_srh_rcv(skb); + if (!idev) + goto disabled; + return ipv6_srh_rcv(skb, idev); case IPV6_SRCRT_TYPE_3: /* rpl segment routing */ - return ipv6_rpl_srh_rcv(skb); + if (!idev) + goto disabled; + return ipv6_rpl_srh_rcv(skb, idev); default: break; } @@ -840,6 +834,10 @@ unknown_rh: icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, (&hdr->type) - skb_network_header(skb)); return -1; + +disabled: + kfree_skb_reason(skb, SKB_DROP_REASON_IPV6DISABLED); + return -1; } static const struct inet6_protocol rthdr_protocol = { diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 58b473c157c8..e2463bcfc504 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -1136,13 +1136,11 @@ static void ip6gre_tnl_link_config_route(struct ip6_tnl *t, int set_mtu, return; if (rt->dst.dev) { - unsigned short dst_len = rt->dst.dev->hard_header_len + - t_hlen; + unsigned int headroom; - if (t->dev->header_ops) - dev->hard_header_len = dst_len; - else - dev->needed_headroom = dst_len; + headroom = rt->dst.dev->hard_header_len + t_hlen; + headroom = ip_tunnel_limit_headroom(headroom); + dev->needed_headroom = headroom; if (set_mtu) { int mtu = rt->dst.dev->mtu - t_hlen; @@ -1170,8 +1168,8 @@ static int ip6gre_calc_hlen(struct ip6_tnl *tunnel) t_hlen = tunnel->hlen + sizeof(struct ipv6hdr); - if (tunnel->dev->header_ops) - tunnel->dev->hard_header_len = LL_MAX_HEADER + t_hlen; + if (tunnel->dev->header_ops && tunnel->dev->type == ARPHRD_IP6GRE) + tunnel->dev->hard_header_len = t_hlen; else tunnel->dev->needed_headroom = LL_MAX_HEADER + t_hlen; diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c index 168ec07e31cc..b59b2b119a1c 100644 --- a/net/ipv6/ip6_input.c +++ b/net/ipv6/ip6_input.c @@ -577,6 +577,7 @@ int ip6_mc_input(struct sk_buff *skb) if (deliver) { skb2 = skb_clone(skb, GFP_ATOMIC); } else { + skb_orphan(skb); skb2 = skb; skb = NULL; } diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 757c37092be7..22c12045f2c3 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1228,19 +1228,8 @@ route_lookup: */ max_headroom += LL_RESERVED_SPACE(tdev); - if (skb_headroom(skb) < max_headroom || skb_shared(skb) || - (skb_cloned(skb) && !skb_clone_writable(skb, 0))) { - struct sk_buff *new_skb; - - new_skb = skb_realloc_headroom(skb, max_headroom); - if (!new_skb) - goto tx_err_dst_release; - - if (skb->sk) - skb_set_owner_w(new_skb, skb->sk); - consume_skb(skb); - skb = new_skb; - } + if (skb_cow_head(skb, max_headroom)) + goto tx_err_dst_release; if (t->parms.collect_md) { if (t->encap.type != TUNNEL_ENCAP_NONE) @@ -1517,8 +1506,11 @@ static void ip6_tnl_link_config(struct ip6_tnl *t) tdev = __dev_get_by_index(t->net, p->link); if (tdev) { - dev->needed_headroom = tdev->hard_header_len + - tdev->needed_headroom + t_hlen; + unsigned int headroom; + + headroom = tdev->hard_header_len + tdev->needed_headroom; + headroom += t_hlen; + dev->needed_headroom = ip_tunnel_limit_headroom(headroom); mtu = min_t(unsigned int, tdev->mtu, IP6_MAX_MTU); mtu = mtu - t_hlen; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 5894f7dd4d4d..cce5ea6fe7a0 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -6017,7 +6017,7 @@ static int rt6_nh_dump_exceptions(struct fib6_nh *nh, void *arg) return 0; for (i = 0; i < FIB6_EXCEPTION_BUCKET_SIZE; i++) { - hlist_for_each_entry(rt6_ex, &bucket->chain, hlist) { + hlist_for_each_entry_rcu(rt6_ex, &bucket->chain, hlist) { if (w->skip) { w->skip--; continue; diff --git a/net/ipv6/seg6_local.c b/net/ipv6/seg6_local.c index 95ea0b62729a..7b5212220185 100644 --- a/net/ipv6/seg6_local.c +++ b/net/ipv6/seg6_local.c @@ -261,6 +261,15 @@ static bool decap_and_validate(struct sk_buff *skb, int proto) memset(IPCB(skb), 0, sizeof(*IPCB(skb))); IPCB(skb)->iif = iif; + } else if (proto == IPPROTO_IPV6) { + bool l3slave = ipv6_l3mdev_skb(IP6CB(skb)->flags); + int iif = IP6CB(skb)->iif; + + memset(IP6CB(skb), 0, sizeof(*IP6CB(skb))); + IP6CB(skb)->iif = iif; + IP6CB(skb)->nhoff = offsetof(struct ipv6hdr, nexthdr); + if (l3slave) + IP6CB(skb)->flags |= IP6SKB_L3SLAVE; } return true; diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index c03df1682a63..f4d6370340d0 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -1128,7 +1128,7 @@ static void ipip6_tunnel_bind_dev(struct net_device *dev) WRITE_ONCE(dev->mtu, mtu); hlen = tdev->hard_header_len + tdev->needed_headroom; } - dev->needed_headroom = t_hlen + hlen; + dev->needed_headroom = ip_tunnel_limit_headroom(t_hlen + hlen); } static void ipip6_tunnel_update(struct ip_tunnel *t, diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index 7f5a5aa0cfdc..bd5838e65c31 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -2079,6 +2079,8 @@ static int afiucv_hs_rcv(struct sk_buff *skb, struct net_device *dev, sk = NULL; read_lock(&iucv_sk_list.lock); sk_for_each(sk, &iucv_sk_list.head) { + if (iucv_sk(sk)->hs_dev != dev) + continue; if (trans_hdr->flags == AF_IUCV_FLAG_SYN) { if ((!memcmp(&iucv_sk(sk)->src_name, trans_hdr->destAppName, 8)) && diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c index 59457c0c14aa..fbdd3d055dbc 100644 --- a/net/l2tp/l2tp_netlink.c +++ b/net/l2tp/l2tp_netlink.c @@ -248,8 +248,8 @@ static int l2tp_nl_cmd_tunnel_create(struct sk_buff *skb, struct genl_info *info kfree(tunnel); goto out; } - ret = l2tp_tunnel_notify(&l2tp_nl_family, info, tunnel, - L2TP_CMD_TUNNEL_CREATE); + l2tp_tunnel_notify(&l2tp_nl_family, info, tunnel, + L2TP_CMD_TUNNEL_CREATE); l2tp_tunnel_put(tunnel); out: @@ -305,8 +305,8 @@ static int l2tp_nl_cmd_tunnel_modify(struct sk_buff *skb, struct genl_info *info goto out; } - ret = l2tp_tunnel_notify(&l2tp_nl_family, info, - tunnel, L2TP_CMD_TUNNEL_MODIFY); + l2tp_tunnel_notify(&l2tp_nl_family, info, + tunnel, L2TP_CMD_TUNNEL_MODIFY); l2tp_tunnel_put(tunnel); @@ -645,8 +645,8 @@ static int l2tp_nl_cmd_session_create(struct sk_buff *skb, struct genl_info *inf session = l2tp_session_get(net, tunnel->sock, tunnel->version, tunnel_id, session_id); if (session) { - ret = l2tp_session_notify(&l2tp_nl_family, info, session, - L2TP_CMD_SESSION_CREATE); + l2tp_session_notify(&l2tp_nl_family, info, session, + L2TP_CMD_SESSION_CREATE); l2tp_session_put(session); } } @@ -710,8 +710,8 @@ static int l2tp_nl_cmd_session_modify(struct sk_buff *skb, struct genl_info *inf if (info->attrs[L2TP_ATTR_RECV_TIMEOUT]) session->reorder_timeout = nla_get_msecs(info->attrs[L2TP_ATTR_RECV_TIMEOUT]); - ret = l2tp_session_notify(&l2tp_nl_family, info, - session, L2TP_CMD_SESSION_MODIFY); + l2tp_session_notify(&l2tp_nl_family, info, + session, L2TP_CMD_SESSION_MODIFY); l2tp_session_put(session); diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c index f9b8c4d0f049..608c43a4602d 100644 --- a/net/mpls/af_mpls.c +++ b/net/mpls/af_mpls.c @@ -198,6 +198,7 @@ static u32 mpls_multipath_hash(struct mpls_route *rt, struct sk_buff *skb) if (pskb_may_pull(skb, mpls_hdr_len + sizeof(struct iphdr))) { const struct iphdr *v4hdr; + hdr = mpls_hdr(skb) + label_index; v4hdr = (const struct iphdr *)(hdr + 1); if (v4hdr->version == 4) { hash = jhash_3words(ntohl(v4hdr->saddr), @@ -208,6 +209,7 @@ static u32 mpls_multipath_hash(struct mpls_route *rt, struct sk_buff *skb) sizeof(struct ipv6hdr))) { const struct ipv6hdr *v6hdr; + hdr = mpls_hdr(skb) + label_index; v6hdr = (const struct ipv6hdr *)(hdr + 1); hash = __ipv6_addr_jhash(&v6hdr->saddr, hash); hash = __ipv6_addr_jhash(&v6hdr->daddr, hash); diff --git a/net/mptcp/syncookies.c b/net/mptcp/syncookies.c index 7f22526346a7..b5cac5701122 100644 --- a/net/mptcp/syncookies.c +++ b/net/mptcp/syncookies.c @@ -118,6 +118,7 @@ bool mptcp_token_join_cookie_init_state(struct mptcp_subflow_request_sock *subfl subflow_req->local_nonce = e->local_nonce; subflow_req->backup = e->backup; subflow_req->remote_id = e->join_id; + subflow_req->local_id = e->local_id; subflow_req->token = e->token; subflow_req->msk = msk; spin_unlock_bh(&join_entry_locks[i]); diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index f63c8ac74e4a..fb68aa17e479 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -2003,6 +2003,7 @@ int ovs_ct_init(struct net *net) { unsigned int n_bits = sizeof(struct ovs_key_ct_labels) * BITS_PER_BYTE; struct ovs_net *ovs_net = net_generic(net, ovs_net_id); + int err = 0; if (nf_connlabels_get(net, n_bits - 1)) { ovs_net->xt_label = false; @@ -2012,10 +2013,11 @@ int ovs_ct_init(struct net *net) } #if IS_ENABLED(CONFIG_NETFILTER_CONNCOUNT) - return ovs_ct_limit_init(net, ovs_net); -#else - return 0; + err = ovs_ct_limit_init(net, ovs_net); + if (err && ovs_net->xt_label) + nf_connlabels_put(net); #endif + return err; } void ovs_ct_exit(struct net *net) diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index b407644b652f..1c032d4a6665 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -285,6 +285,7 @@ void ovs_dp_process_packet(struct sk_buff *skb, struct sw_flow_key *key) consume_skb(skb); break; default: + skb_tx_error(skb); kfree_skb(skb); break; } @@ -601,8 +602,6 @@ static int queue_userspace_packet(struct datapath *dp, struct sk_buff *skb, err = genlmsg_unicast(ovs_dp_get_net(dp), user_skb, upcall_info->portid); user_skb = NULL; out: - if (err) - skb_tx_error(skb); consume_skb(user_skb); consume_skb(nskb); @@ -1473,33 +1472,34 @@ static int ovs_flow_cmd_del(struct sk_buff *skb, struct genl_info *info) goto unlock; } - ovs_flow_tbl_remove(&dp->table, flow); - ovs_unlock(); - - reply = ovs_flow_cmd_alloc_info((const struct sw_flow_actions __force *) flow->sf_acts, + reply = ovs_flow_cmd_alloc_info(ovsl_dereference(flow->sf_acts), &flow->id, info, false, ufid_flags); - if (likely(reply)) { - if (!IS_ERR(reply)) { - rcu_read_lock(); /*To keep RCU checker happy. */ - err = ovs_flow_cmd_fill_info(flow, ovs_header->dp_ifindex, - reply, info->snd_portid, - info->snd_seq, 0, - OVS_FLOW_CMD_DEL, - ufid_flags); - rcu_read_unlock(); - if (WARN_ON_ONCE(err < 0)) { - kfree_skb(reply); - goto out_free; - } + if (IS_ERR(reply)) { + netlink_set_err(sock_net(skb->sk)->genl_sock, 0, 0, + PTR_ERR(reply)); + reply = NULL; + } - ovs_notify(&dp_flow_genl_family, reply, info); - } else { - netlink_set_err(sock_net(skb->sk)->genl_sock, 0, 0, - PTR_ERR(reply)); + if (likely(reply)) { + err = ovs_flow_cmd_fill_info(flow, ovs_header->dp_ifindex, + reply, info->snd_portid, + info->snd_seq, 0, + OVS_FLOW_CMD_DEL, ufid_flags); + if (WARN_ON_ONCE(err < 0)) { + kfree_skb(reply); + reply = NULL; } } + /* Removal has to happen after ovs_flow_cmd_fill_info(), as it uses + * the flow->mask that can be scheduled to be freed by the + * ovs_flow_tbl_remove() and we're not holding the RCU read lock. + */ + ovs_flow_tbl_remove(&dp->table, flow); + ovs_unlock(); + + if (likely(reply)) + ovs_notify(&dp_flow_genl_family, reply, info); -out_free: ovs_flow_free(flow, true); return 0; unlock: diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 34573c9b8a5e..a753945f860c 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -1259,7 +1259,7 @@ static void transition_one_qdisc(struct net_device *dev, rcu_assign_pointer(dev_queue->qdisc, new_qdisc); if (need_watchdog_p) { - WRITE_ONCE(dev_queue->trans_start, 0); + WRITE_ONCE(dev_queue->trans_start, jiffies); *need_watchdog_p = 1; } } diff --git a/net/sctp/inqueue.c b/net/sctp/inqueue.c index a024c0843247..5f988b3a8814 100644 --- a/net/sctp/inqueue.c +++ b/net/sctp/inqueue.c @@ -71,8 +71,11 @@ void sctp_inq_free(struct sctp_inq *queue) */ void sctp_inq_push(struct sctp_inq *q, struct sctp_chunk *chunk) { - /* Directly call the packet handling routine. */ - if (chunk->rcvr->dead) { + /* Directly call the packet handling routine. Drop the chunk if the + * receiver or the transport it was looked up on is gone. + */ + if (chunk->rcvr->dead || + (chunk->transport && chunk->transport->dead)) { sctp_chunk_free(chunk); return; } diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c index 424f10a6fdba..94716406d602 100644 --- a/net/sctp/sm_sideeffect.c +++ b/net/sctp/sm_sideeffect.c @@ -1332,6 +1332,10 @@ static int sctp_cmd_interpreter(enum sctp_event_type event_type, sctp_outq_uncork(&asoc->outqueue, gfp); local_cork = 0; } + /* No chunk left in this packet may use this asoc. */ + if (event_type == SCTP_EVENT_T_CHUNK && + chunk->asoc == asoc) + chunk->pdiscard = 1; /* Delete the current association. */ sctp_cmd_delete_tcb(commands, asoc); asoc = NULL; diff --git a/net/sctp/stream.c b/net/sctp/stream.c index 9addcfad467f..8826dd60e59e 100644 --- a/net/sctp/stream.c +++ b/net/sctp/stream.c @@ -22,6 +22,15 @@ #include <net/sctp/sm.h> #include <net/sctp/stream_sched.h> +#define SCTP_STRRESET_MASK(type) \ + BIT(ntohs(type) - ntohs(SCTP_PARAM_RESET_OUT_REQUEST)) +#define SCTP_STRRESET_TEST(asoc, type) \ + ((asoc)->strreset_outstanding & SCTP_STRRESET_MASK(type)) +#define SCTP_STRRESET_SET(asoc, type) \ + ((asoc)->strreset_outstanding |= SCTP_STRRESET_MASK(type)) +#define SCTP_STRRESET_CLEAR(asoc, type) \ + ((asoc)->strreset_outstanding &= ~SCTP_STRRESET_MASK(type)) + static void sctp_stream_shrink_out(struct sctp_stream *stream, __u16 outcnt) { struct sctp_association *asoc; @@ -372,7 +381,10 @@ int sctp_send_reset_streams(struct sctp_association *asoc, goto out; } - asoc->strreset_outstanding = out + in; + if (out) + SCTP_STRRESET_SET(asoc, SCTP_PARAM_RESET_OUT_REQUEST); + if (in) + SCTP_STRRESET_SET(asoc, SCTP_PARAM_RESET_IN_REQUEST); out: return retval; @@ -417,7 +429,7 @@ int sctp_send_reset_assoc(struct sctp_association *asoc) return retval; } - asoc->strreset_outstanding = 1; + SCTP_STRRESET_SET(asoc, SCTP_PARAM_RESET_TSN_REQUEST); return 0; } @@ -474,7 +486,10 @@ int sctp_send_add_streams(struct sctp_association *asoc, goto out; } - asoc->strreset_outstanding = !!out + !!in; + if (out) + SCTP_STRRESET_SET(asoc, SCTP_PARAM_RESET_ADD_OUT_STREAMS); + if (in) + SCTP_STRRESET_SET(asoc, SCTP_PARAM_RESET_ADD_IN_STREAMS); out: return retval; @@ -482,13 +497,13 @@ out: static struct sctp_paramhdr *sctp_chunk_lookup_strreset_param( struct sctp_association *asoc, __be32 resp_seq, - __be16 type) + __be16 type, bool match_seq) { struct sctp_chunk *chunk = asoc->strreset_chunk; struct sctp_reconf_chunk *hdr; union sctp_params param; - if (!chunk) + if (!chunk || !chunk->transport) return NULL; hdr = (struct sctp_reconf_chunk *)chunk->chunk_hdr; @@ -499,7 +514,7 @@ static struct sctp_paramhdr *sctp_chunk_lookup_strreset_param( */ struct sctp_strreset_tsnreq *req = param.v; - if ((!resp_seq || req->request_seq == resp_seq) && + if ((!match_seq || req->request_seq == resp_seq) && (!type || type == req->param_hdr.type)) return param.v; } @@ -564,13 +579,14 @@ struct sctp_chunk *sctp_process_strreset_outreq( if (asoc->strreset_chunk) { if (!sctp_chunk_lookup_strreset_param( asoc, outreq->response_seq, - SCTP_PARAM_RESET_IN_REQUEST)) { + SCTP_PARAM_RESET_IN_REQUEST, true) || + !SCTP_STRRESET_TEST(asoc, SCTP_PARAM_RESET_IN_REQUEST)) { /* same process with outstanding isn't 0 */ result = SCTP_STRRESET_ERR_IN_PROGRESS; goto out; } - asoc->strreset_outstanding--; + SCTP_STRRESET_CLEAR(asoc, SCTP_PARAM_RESET_IN_REQUEST); asoc->strreset_outseq++; if (!asoc->strreset_outstanding) { @@ -669,7 +685,7 @@ struct sctp_chunk *sctp_process_strreset_inreq( SCTP_SO(stream, i)->state = SCTP_STREAM_CLOSED; asoc->strreset_chunk = chunk; - asoc->strreset_outstanding = 1; + SCTP_STRRESET_SET(asoc, SCTP_PARAM_RESET_OUT_REQUEST); sctp_chunk_hold(asoc->strreset_chunk); result = SCTP_STRRESET_PERFORMED; @@ -816,13 +832,14 @@ struct sctp_chunk *sctp_process_strreset_addstrm_out( if (asoc->strreset_chunk) { if (!sctp_chunk_lookup_strreset_param( - asoc, 0, SCTP_PARAM_RESET_ADD_IN_STREAMS)) { + asoc, 0, SCTP_PARAM_RESET_ADD_IN_STREAMS, false) || + !SCTP_STRRESET_TEST(asoc, SCTP_PARAM_RESET_ADD_IN_STREAMS)) { /* same process with outstanding isn't 0 */ result = SCTP_STRRESET_ERR_IN_PROGRESS; goto out; } - asoc->strreset_outstanding--; + SCTP_STRRESET_CLEAR(asoc, SCTP_PARAM_RESET_ADD_IN_STREAMS); asoc->strreset_outseq++; if (!asoc->strreset_outstanding) { @@ -899,7 +916,7 @@ struct sctp_chunk *sctp_process_strreset_addstrm_in( goto out; asoc->strreset_chunk = chunk; - asoc->strreset_outstanding = 1; + SCTP_STRRESET_SET(asoc, SCTP_PARAM_RESET_ADD_OUT_STREAMS); sctp_chunk_hold(asoc->strreset_chunk); stream->outcnt = outcnt; @@ -927,8 +944,9 @@ struct sctp_chunk *sctp_process_strreset_resp( struct sctp_paramhdr *req; __u32 result; - req = sctp_chunk_lookup_strreset_param(asoc, resp->response_seq, 0); - if (!req) + req = sctp_chunk_lookup_strreset_param(asoc, resp->response_seq, 0, + true); + if (!req || !SCTP_STRRESET_TEST(asoc, req->type)) return NULL; result = ntohl(resp->result); @@ -1078,7 +1096,7 @@ struct sctp_chunk *sctp_process_strreset_resp( nums, 0, GFP_ATOMIC); } - asoc->strreset_outstanding--; + SCTP_STRRESET_CLEAR(asoc, req->type); asoc->strreset_outseq++; /* remove everything for this reconf request */ diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index bc7b4a33b726..6057a7d9718b 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -3237,7 +3237,8 @@ int smc_ioctl(struct socket *sock, unsigned int cmd, return -EINVAL; } if (smc->sk.sk_state == SMC_INIT || - smc->sk.sk_state == SMC_CLOSED) + smc->sk.sk_state == SMC_CLOSED || + !READ_ONCE(smc->conn.sndbuf_desc)) answ = 0; else answ = smc->conn.sndbuf_desc->len - diff --git a/net/smc/smc.h b/net/smc/smc.h index ea45467c1140..1425fd756d34 100644 --- a/net/smc/smc.h +++ b/net/smc/smc.h @@ -277,9 +277,9 @@ struct smc_connection { * 0 for SMC-R, 32 for SMC-D */ u64 peer_token; /* SMC-D token of peer */ - u8 killed : 1; /* abnormal termination */ - u8 freed : 1; /* normal termination */ - u8 out_of_sync : 1; /* out of sync with peer */ + u8 killed; /* abnormal termination */ + u8 freed; /* normal termination */ + u8 out_of_sync; /* out of sync with peer */ }; struct smc_sock { /* smc sock container */ diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index 5df4838a6386..34fa809e9504 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -1134,13 +1134,13 @@ again: read_unlock_bh(&lgr->conns_lock); /* pre-fetch buffer outside of send_lock, might sleep */ rc = smc_cdc_get_free_slot(conn, to_lnk, &wr_buf, NULL, &pend); - if (rc) - goto err_out; - /* avoid race with smcr_tx_sndbuf_nonempty() */ - spin_lock_bh(&conn->send_lock); - smc_switch_link_and_count(conn, to_lnk); - rc = smc_switch_cursor(smc, pend, wr_buf); - spin_unlock_bh(&conn->send_lock); + if (!rc) { + /* avoid race with smcr_tx_sndbuf_nonempty() */ + spin_lock_bh(&conn->send_lock); + smc_switch_link_and_count(conn, to_lnk); + rc = smc_switch_cursor(smc, pend, wr_buf); + spin_unlock_bh(&conn->send_lock); + } sock_put(&smc->sk); if (rc) goto err_out; @@ -1195,14 +1195,16 @@ static void smcd_buf_detach(struct smc_connection *conn) { struct smcd_dev *smcd = conn->lgr->smcd; u64 peer_token = conn->peer_token; + struct smc_buf_desc *buf_desc; if (!conn->sndbuf_desc) return; smc_ism_detach_dmb(smcd, peer_token); - kfree(conn->sndbuf_desc); + buf_desc = conn->sndbuf_desc; conn->sndbuf_desc = NULL; + kfree(buf_desc); } static void smc_buf_unuse(struct smc_connection *conn, @@ -1254,11 +1256,10 @@ void smc_conn_free(struct smc_connection *conn) goto lgr_put; if (lgr->is_smcd) { - if (!list_empty(&lgr->list)) - smc_ism_unset_conn(conn); + smc_ism_unset_conn(conn); + tasklet_kill(&conn->rx_tsklet); if (smc_ism_support_dmb_nocopy(lgr->smcd)) smcd_buf_detach(conn); - tasklet_kill(&conn->rx_tsklet); } else { smc_cdc_wait_pend_tx_wr(conn); if (current_work() != &conn->abort_work) @@ -1511,12 +1512,12 @@ static void smc_conn_kill(struct smc_connection *conn, bool soft) smc_sk_wake_ups(smc); if (conn->lgr->is_smcd) { smc_ism_unset_conn(conn); - if (smc_ism_support_dmb_nocopy(conn->lgr->smcd)) - smcd_buf_detach(conn); if (soft) tasklet_kill(&conn->rx_tsklet); else tasklet_unlock_wait(&conn->rx_tsklet); + if (smc_ism_support_dmb_nocopy(conn->lgr->smcd)) + smcd_buf_detach(conn); } else { smc_cdc_wait_pend_tx_wr(conn); } diff --git a/net/smc/smc_llc.c b/net/smc/smc_llc.c index 28873ec06e3c..51937265203c 100644 --- a/net/smc/smc_llc.c +++ b/net/smc/smc_llc.c @@ -157,6 +157,7 @@ struct smc_llc_msg_confirm_rkey { /* type 0x06 */ }; #define SMC_LLC_DEL_RKEY_MAX 8 +#define SMC_LLC_DEL_RKEY_V2_INLINE 9 #define SMC_LLC_FLAG_RKEY_RETRY 0x10 #define SMC_LLC_FLAG_RKEY_NEG 0x20 @@ -177,6 +178,15 @@ struct smc_llc_msg_delete_rkey_v2 { /* type 0x29 */ __be32 rkey[]; }; +/* the leading rkeys of a DELETE_RKEY_V2 fit into union smc_llc_msg */ +struct smc_llc_msg_delete_rkey_v2_inline { /* type 0x29 */ + struct smc_llc_hdr hd; + u8 num_rkeys; + u8 num_inval_rkeys; + u8 reserved[2]; + __be32 rkey[SMC_LLC_DEL_RKEY_V2_INLINE]; +}; + union smc_llc_msg { struct smc_llc_msg_confirm_link confirm_link; struct smc_llc_msg_add_link add_link; @@ -186,6 +196,7 @@ union smc_llc_msg { struct smc_llc_msg_confirm_rkey confirm_rkey; struct smc_llc_msg_delete_rkey delete_rkey; + struct smc_llc_msg_delete_rkey_v2_inline delete_rkey_v2; struct smc_llc_msg_test_link test_link; struct { @@ -194,15 +205,25 @@ union smc_llc_msg { } raw; }; +static_assert(SMC_LLC_DEL_RKEY_V2_INLINE == + (sizeof(union smc_llc_msg) - + offsetof(struct smc_llc_msg_delete_rkey_v2, rkey)) / + sizeof(__be32)); +static_assert(offsetof(struct smc_llc_msg_delete_rkey_v2_inline, rkey) == + offsetof(struct smc_llc_msg_delete_rkey_v2, rkey)); + #define SMC_LLC_FLAG_RESP 0x80 struct smc_llc_qentry { struct list_head list; struct smc_link *link; + u16 body_len; union smc_llc_msg msg; + u8 body[] __counted_by(body_len); }; -static void smc_llc_enqueue(struct smc_link *link, union smc_llc_msg *llc); +static void smc_llc_enqueue(struct smc_link *link, union smc_llc_msg *llc, + u32 byte_len); struct smc_llc_qentry *smc_llc_flow_qentry_clr(struct smc_llc_flow *flow) { @@ -998,15 +1019,20 @@ static int smc_llc_cli_conf_link(struct smc_link *link, static void smc_llc_save_add_link_rkeys(struct smc_link *link, struct smc_link *link_new, - u8 *llc_msg) + struct smc_llc_qentry *qentry) { + const u32 rt_off = offsetof(struct smc_llc_msg_add_link_v2_ext, rt); struct smc_llc_msg_add_link_v2_ext *ext; struct smc_link_group *lgr = link->lgr; int max, i; - ext = (struct smc_llc_msg_add_link_v2_ext *)(llc_msg + - SMC_WR_TX_SIZE); + /* the rkey count itself is only there if enough bytes arrived */ + if (qentry->body_len < rt_off) + return; + ext = (struct smc_llc_msg_add_link_v2_ext *)qentry->body; max = min_t(u8, ext->num_rkeys, SMC_LLC_RKEYS_PER_MSG_V2); + max = min_t(u32, max, (qentry->body_len - rt_off) / + sizeof(ext->rt[0])); down_write(&lgr->rmbs_lock); for (i = 0; i < max; i++) { smc_rtoken_set(lgr, link->link_idx, link_new->link_idx, @@ -1099,9 +1125,7 @@ int smc_llc_cli_add_link(struct smc_link *link, struct smc_llc_qentry *qentry) if (rc) goto out_clear_lnk; if (lgr->smc_version == SMC_V2) { - u8 *llc_msg = smc_link_shared_v2_rxbuf(link) ? - (u8 *)lgr->wr_rx_buf_v2 : (u8 *)llc; - smc_llc_save_add_link_rkeys(link, lnk_new, llc_msg); + smc_llc_save_add_link_rkeys(link, lnk_new, qentry); } else { rc = smc_llc_cli_rkey_exchange(link, lnk_new); if (rc) { @@ -1481,7 +1505,7 @@ int smc_llc_srv_add_link(struct smc_link *link, } add_llc = &qentry->msg.add_link; if (add_llc->hd.flags & SMC_LLC_FLAG_ADD_LNK_REJ) { - smc_llc_flow_qentry_del(&lgr->llc_flow_lcl); + smc_llc_flow_qentry_clr(&lgr->llc_flow_lcl); rc = -ENOLINK; goto out_err; } @@ -1492,7 +1516,8 @@ int smc_llc_srv_add_link(struct smc_link *link, lgr_new_t = SMC_LGR_ASYMMETRIC_PEER; } smc_llc_save_add_link_info(link_new, add_llc); - smc_llc_flow_qentry_del(&lgr->llc_flow_lcl); + /* add_llc still points into qentry, so only detach it here */ + smc_llc_flow_qentry_clr(&lgr->llc_flow_lcl); rc = smc_ib_ready_link(link_new); if (rc) @@ -1501,9 +1526,7 @@ int smc_llc_srv_add_link(struct smc_link *link, if (rc) goto out_err; if (lgr->smc_version == SMC_V2) { - u8 *llc_msg = smc_link_shared_v2_rxbuf(link) ? - (u8 *)lgr->wr_rx_buf_v2 : (u8 *)add_llc; - smc_llc_save_add_link_rkeys(link, link_new, llc_msg); + smc_llc_save_add_link_rkeys(link, link_new, qentry); } else { rc = smc_llc_srv_rkey_exchange(link, link_new); if (rc) @@ -1512,14 +1535,14 @@ int smc_llc_srv_add_link(struct smc_link *link, rc = smc_llc_srv_conf_link(link, link_new, lgr_new_t); if (rc) goto out_err; - kfree(ini); - return 0; + goto out; out_err: if (link_new) { link_new->state = SMC_LNK_INACTIVE; smcr_link_clear(link_new, false); } out: + kfree(qentry); kfree(ini); if (send_req_add_link_resp) smc_llc_send_req_add_link_response(req_qentry); @@ -1552,7 +1575,8 @@ void smc_llc_add_link_local(struct smc_link *link) add_llc.hd.common.llc_type = SMC_LLC_ADD_LINK; smc_llc_init_msg_hdr(&add_llc.hd, link->lgr, sizeof(add_llc)); /* no dev and port needed */ - smc_llc_enqueue(link, (union smc_llc_msg *)&add_llc); + smc_llc_enqueue(link, (union smc_llc_msg *)&add_llc, + sizeof(union smc_llc_msg)); } /* worker to process an add link message */ @@ -1588,7 +1612,8 @@ void smc_llc_srv_delete_link_local(struct smc_link *link, u8 del_link_id) del_llc.link_num = del_link_id; del_llc.reason = htonl(SMC_LLC_DEL_LOST_PATH); del_llc.hd.flags |= SMC_LLC_FLAG_DEL_LINK_ORDERLY; - smc_llc_enqueue(link, (union smc_llc_msg *)&del_llc); + smc_llc_enqueue(link, (union smc_llc_msg *)&del_llc, + sizeof(union smc_llc_msg)); } static void smc_llc_process_cli_delete_link(struct smc_link_group *lgr) @@ -1810,19 +1835,28 @@ static void smc_llc_rmt_delete_rkey(struct smc_link_group *lgr) link = qentry->link; if (lgr->smc_version == SMC_V2) { - struct smc_llc_msg_delete_rkey_v2 *llcv2; + struct smc_llc_msg_delete_rkey_v2_inline *llcv2; - if (smc_link_shared_v2_rxbuf(link)) { - memcpy(lgr->wr_rx_buf_v2, llc, sizeof(*llc)); - llcv2 = (struct smc_llc_msg_delete_rkey_v2 *)lgr->wr_rx_buf_v2; - } else { - llcv2 = (struct smc_llc_msg_delete_rkey_v2 *)llc; - } + /* The leading SMC_LLC_DEL_RKEY_V2_INLINE rkeys are declared in + * the message itself, any further ones were received into + * qentry->body. + */ + llcv2 = &qentry->msg.delete_rkey_v2; llcv2->num_inval_rkeys = 0; max = min_t(u8, llcv2->num_rkeys, SMC_LLC_RKEYS_PER_MSG_V2); + max = min_t(u32, max, SMC_LLC_DEL_RKEY_V2_INLINE + + qentry->body_len / sizeof(__be32)); for (i = 0; i < max; i++) { - if (smc_rtoken_delete(link, llcv2->rkey[i])) + __be32 rkey; + + if (i < SMC_LLC_DEL_RKEY_V2_INLINE) + rkey = llcv2->rkey[i]; + else + memcpy(&rkey, qentry->body + + (i - SMC_LLC_DEL_RKEY_V2_INLINE) * + sizeof(rkey), sizeof(rkey)); + if (smc_rtoken_delete(link, rkey)) llcv2->num_inval_rkeys++; } memset(&llc->rkey[0], 0, sizeof(llc->rkey)); @@ -2064,18 +2098,52 @@ assign: wake_up(&link->lgr->llc_msg_waiter); } -static void smc_llc_enqueue(struct smc_link *link, union smc_llc_msg *llc) +/* the longest tail either reader of qentry->body can use */ +static u32 smc_llc_max_body_len(union smc_llc_msg *llc) +{ + switch (llc->raw.hdr.common.llc_type) { + case SMC_LLC_ADD_LINK: + return offsetof(struct smc_llc_msg_add_link_v2_ext, rt) + + SMC_LLC_RKEYS_PER_MSG_V2 * + sizeof(struct smc_llc_msg_add_link_cont_rt); + case SMC_LLC_DELETE_RKEY: + return (SMC_LLC_RKEYS_PER_MSG_V2 - + SMC_LLC_DEL_RKEY_V2_INLINE) * sizeof(__be32); + default: + return 0; + } +} + +static void smc_llc_enqueue(struct smc_link *link, union smc_llc_msg *llc, + u32 byte_len) { struct smc_link_group *lgr = link->lgr; struct smc_llc_qentry *qentry; unsigned long flags; + u16 body_len = 0; + + /* V2 messages can be longer than the inline union smc_llc_msg. Carry + * the remainder in the qentry itself, so that its lifetime and its + * length match the message the peer actually sent. + */ + if (lgr->smc_version == SMC_V2 && byte_len > SMC_WR_TX_SIZE) + body_len = min_t(u32, byte_len, SMC_WR_BUF_V2_SIZE) - + SMC_WR_TX_SIZE; + body_len = min_t(u32, body_len, smc_llc_max_body_len(llc)); - qentry = kmalloc(sizeof(*qentry), GFP_ATOMIC); + qentry = kmalloc_flex(*qentry, body, body_len, GFP_ATOMIC); if (!qentry) return; + qentry->body_len = body_len; qentry->link = link; INIT_LIST_HEAD(&qentry->list); memcpy(&qentry->msg, llc, sizeof(union smc_llc_msg)); + if (body_len) { + u8 *src = smc_link_shared_v2_rxbuf(link) ? + (u8 *)lgr->wr_rx_buf_v2 : (u8 *)llc; + + memcpy(qentry->body, src + SMC_WR_TX_SIZE, body_len); + } /* process responses immediately */ if ((llc->raw.hdr.flags & SMC_LLC_FLAG_RESP) && @@ -2107,7 +2175,7 @@ static void smc_llc_rx_handler(struct ib_wc *wc, void *buf) return; /* invalid message */ } - smc_llc_enqueue(link, llc); + smc_llc_enqueue(link, llc, wc->byte_len); } /***************************** worker, utils *********************************/ diff --git a/net/smc/smc_rx.c b/net/smc/smc_rx.c index 09b839725953..24524dfd5518 100644 --- a/net/smc/smc_rx.c +++ b/net/smc/smc_rx.c @@ -115,16 +115,15 @@ static void smc_rx_pipe_buf_release(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { struct smc_spd_priv *priv = (struct smc_spd_priv *)buf->private; + struct smc_connection *conn = &priv->smc->conn; struct smc_sock *smc = priv->smc; - struct smc_connection *conn; struct sock *sk = &smc->sk; - if (sk->sk_state == SMC_CLOSED || - sk->sk_state == SMC_PEERFINCLOSEWAIT || - sk->sk_state == SMC_APPFINCLOSEWAIT) - goto out; - conn = &smc->conn; lock_sock(sk); + if (conn->freed) { + release_sock(sk); + goto out; + } smc_rx_update_cons(smc, priv->len); release_sock(sk); if (atomic_sub_and_test(priv->len, &conn->splice_pending)) diff --git a/net/smc/smc_tx.h b/net/smc/smc_tx.h index a59f370b8b43..610a945aefd6 100644 --- a/net/smc/smc_tx.h +++ b/net/smc/smc_tx.h @@ -20,11 +20,15 @@ static inline int smc_tx_prepared_sends(struct smc_connection *conn) { + struct smc_buf_desc *sndbuf_desc = READ_ONCE(conn->sndbuf_desc); union smc_host_cursor sent, prep; + if (!sndbuf_desc) + return 0; + smc_curs_copy(&sent, &conn->tx_curs_sent, conn); smc_curs_copy(&prep, &conn->tx_curs_prep, conn); - return smc_curs_diff(conn->sndbuf_desc->len, &sent, &prep); + return smc_curs_diff(sndbuf_desc->len, &sent, &prep); } void smc_tx_pending(struct smc_connection *conn); diff --git a/net/smc/smc_wr.c b/net/smc/smc_wr.c index b04a21b8c511..4624817137be 100644 --- a/net/smc/smc_wr.c +++ b/net/smc/smc_wr.c @@ -602,9 +602,9 @@ static void smc_wr_init_sge(struct smc_link *lnk) /* With SMC-Rv2 there can be messages larger than SMC_WR_TX_SIZE. * Each ib_recv_wr gets 2 sges, the second one is a spillover buffer - * and the same buffer for all sges. When a larger message arrived then - * the content of the first small sge is copied to the beginning of - * the larger spillover buffer, allowing easy data mapping. + * and the same buffer for all sges. The spillover sge starts at + * SMC_WR_TX_SIZE, so the leading bytes of that buffer are never + * written. */ for (i = 0; i < lnk->wr_rx_cnt; i++) { int x = i * lnk->wr_rx_sge_cnt; diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c index bb3c3db2713b..6e40544fe2c0 100644 --- a/net/sunrpc/auth_gss/auth_gss.c +++ b/net/sunrpc/auth_gss/auth_gss.c @@ -2074,7 +2074,11 @@ gss_unwrap_resp_priv(struct rpc_task *task, struct rpc_cred *cred, goto unwrap_failed; opaque_len = be32_to_cpup(p++); offset = (u8 *)(p) - (u8 *)head->iov_base; - if (offset + opaque_len > rcv_buf->len) + if (offset > rcv_buf->len) + goto unwrap_failed; + if (opaque_len > rcv_buf->len - offset) + goto unwrap_failed; + if (opaque_len <= GSS_KRB5_TOK_HDR_LEN) goto unwrap_failed; maj_stat = gss_unwrap(ctx->gc_gss_ctx, offset, diff --git a/net/sunrpc/auth_gss/gss_krb5_wrap.c b/net/sunrpc/auth_gss/gss_krb5_wrap.c index b3e1738ff6bf..71b406d00472 100644 --- a/net/sunrpc/auth_gss/gss_krb5_wrap.c +++ b/net/sunrpc/auth_gss/gss_krb5_wrap.c @@ -74,6 +74,8 @@ static void _rotate_left(struct xdr_buf *buf, unsigned int shift) int shifted = 0; int this_shift; + if (!buf->len) + return; shift %= buf->len; while (shifted < shift) { this_shift = min(shift - shifted, LOCAL_BUF_LEN); @@ -86,6 +88,8 @@ static void rotate_left(u32 base, struct xdr_buf *buf, unsigned int shift) { struct xdr_buf subbuf; + if (buf->len <= base) + return; xdr_buf_subsegment(buf, &subbuf, base, buf->len - base); _rotate_left(&subbuf, shift); } @@ -155,6 +159,9 @@ gss_krb5_unwrap_v2(struct krb5_ctx *kctx, int offset, int len, dprintk("RPC: %s\n", __func__); + if (len - offset <= GSS_KRB5_TOK_HDR_LEN) + return GSS_S_DEFECTIVE_TOKEN; + ptr = buf->head[0].iov_base + offset; if (be16_to_cpu(*((__be16 *)ptr)) != KG2_TOK_WRAP) @@ -221,14 +228,16 @@ gss_krb5_unwrap_v2(struct krb5_ctx *kctx, int offset, int len, * head buffer space rather than that actually occupied. */ movelen = min_t(unsigned int, buf->head[0].iov_len, len); + if (movelen < offset + GSS_KRB5_TOK_HDR_LEN + headskip) + return GSS_S_DEFECTIVE_TOKEN; movelen -= offset + GSS_KRB5_TOK_HDR_LEN + headskip; - BUG_ON(offset + GSS_KRB5_TOK_HDR_LEN + headskip + movelen > - buf->head[0].iov_len); memmove(ptr, ptr + GSS_KRB5_TOK_HDR_LEN + headskip, movelen); buf->head[0].iov_len -= GSS_KRB5_TOK_HDR_LEN + headskip; buf->len = len - (GSS_KRB5_TOK_HDR_LEN + headskip); /* Trim off the trailing "extra count" and checksum blob */ + if (ec + GSS_KRB5_TOK_HDR_LEN + tailskip > buf->len - offset) + return GSS_S_DEFECTIVE_TOKEN; xdr_buf_trim(buf, ec + GSS_KRB5_TOK_HDR_LEN + tailskip); *align = XDR_QUADLEN(GSS_KRB5_TOK_HDR_LEN + headskip); diff --git a/net/sunrpc/auth_gss/gss_rpc_upcall.c b/net/sunrpc/auth_gss/gss_rpc_upcall.c index f549e4c05def..711857ac688a 100644 --- a/net/sunrpc/auth_gss/gss_rpc_upcall.c +++ b/net/sunrpc/auth_gss/gss_rpc_upcall.c @@ -121,12 +121,6 @@ out: return result; } -void init_gssp_clnt(struct sunrpc_net *sn) -{ - mutex_init(&sn->gssp_lock); - sn->gssp_clnt = NULL; -} - int set_gssp_clnt(struct net *net) { struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); diff --git a/net/sunrpc/auth_gss/gss_rpc_upcall.h b/net/sunrpc/auth_gss/gss_rpc_upcall.h index 31e96344167e..b3c2b2b90798 100644 --- a/net/sunrpc/auth_gss/gss_rpc_upcall.h +++ b/net/sunrpc/auth_gss/gss_rpc_upcall.h @@ -29,7 +29,6 @@ int gssp_accept_sec_context_upcall(struct net *net, struct gssp_upcall_data *data); void gssp_free_upcall_data(struct gssp_upcall_data *data); -void init_gssp_clnt(struct sunrpc_net *); int set_gssp_clnt(struct net *); void clear_gssp_clnt(struct sunrpc_net *); diff --git a/net/sunrpc/auth_gss/gss_rpc_xdr.c b/net/sunrpc/auth_gss/gss_rpc_xdr.c index f320c0a8e604..3837e0a33d49 100644 --- a/net/sunrpc/auth_gss/gss_rpc_xdr.c +++ b/net/sunrpc/auth_gss/gss_rpc_xdr.c @@ -230,6 +230,7 @@ static int gssx_dec_option_array(struct xdr_stream *xdr, struct gssx_option_array *oa) { struct svc_cred *creds; + bool creds_decoded = false; u32 count, i; __be32 *p; int err; @@ -280,9 +281,14 @@ static int gssx_dec_option_array(struct xdr_stream *xdr, if (length == sizeof(CREDS_VALUE) && memcmp(p, CREDS_VALUE, sizeof(CREDS_VALUE)) == 0) { /* We have creds here. parse them */ + if (creds_decoded) { + err = -EINVAL; + goto free_creds; + } err = gssx_dec_linux_creds(xdr, creds); if (err) goto free_creds; + creds_decoded = true; oa->data[0].value.len = 1; /* presence */ } else { /* consume uninteresting buffer */ diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c index e2f0df8cdaa6..f7f885ab0a4b 100644 --- a/net/sunrpc/auth_gss/svcauth_gss.c +++ b/net/sunrpc/auth_gss/svcauth_gss.c @@ -949,6 +949,8 @@ svcauth_gss_unwrap_priv(struct svc_rqst *rqstp, u32 seq, struct gss_ctx *ctx) } if (len > xdr_stream_remaining(xdr)) goto unwrap_failed; + if (len <= GSS_KRB5_TOK_HDR_LEN) + goto unwrap_failed; offset = xdr_stream_pos(xdr); saved_len = buf->len; @@ -1466,7 +1468,6 @@ static int create_use_gss_proxy_proc_entry(struct net *net) &use_gss_proxy_proc_ops, net); if (!*p) return -ENOMEM; - init_gssp_clnt(sn); return 0; } @@ -1573,6 +1574,9 @@ svcauth_gss_decode_credbody(struct xdr_stream *xdr, u32 body_len; __be32 *p; + /* Early-return paths leave deterministic state, not stale residue. */ + memset(gc, 0, sizeof(*gc)); + p = xdr_inline_decode(xdr, XDR_UNIT); if (!p) return false; @@ -1942,6 +1946,8 @@ svcauth_gss_release(struct svc_rqst *rqstp) if (!gsd) goto out; + if (rqstp->rq_auth_stat != rpc_auth_ok) + goto out; gc = &gsd->clcred; if (gc->gc_proc != RPC_GSS_PROC_DATA) goto out; diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c index 6f6e0d4928af..fda19596566f 100644 --- a/net/sunrpc/cache.c +++ b/net/sunrpc/cache.c @@ -423,10 +423,9 @@ void sunrpc_destroy_cache_detail(struct cache_detail *cd) list_del_init(&cd->others); spin_unlock(&cd->hash_lock); spin_unlock(&cache_list_lock); - if (list_empty(&cache_list)) { - /* module must be being unloaded so its safe to kill the worker */ - cancel_delayed_work_sync(&cache_cleaner); - } + cancel_delayed_work_sync(&cache_cleaner); + if (!list_empty(&cache_list)) + queue_delayed_work(system_power_efficient_wq, &cache_cleaner, 0); } EXPORT_SYMBOL_GPL(sunrpc_destroy_cache_detail); diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index a142e20ce7e7..07de0efaf37d 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -96,7 +96,10 @@ static void rpc_unregister_client(struct rpc_clnt *clnt) static void __rpc_clnt_remove_pipedir(struct rpc_clnt *clnt) { - rpc_remove_client_dir(clnt); + if (clnt->pipefs_sb) { + rpc_remove_client_dir(clnt); + clnt->pipefs_sb = NULL; + } } static void rpc_clnt_remove_pipedir(struct rpc_clnt *clnt) @@ -177,19 +180,28 @@ static int rpc_clnt_skip_event(struct rpc_clnt *clnt, unsigned long event) } static int __rpc_clnt_handle_event(struct rpc_clnt *clnt, unsigned long event, - struct super_block *sb) + struct super_block *sb) { + int err = 0; + switch (event) { case RPC_PIPEFS_MOUNT: - return rpc_setup_pipedir_sb(sb, clnt); + clnt->pipefs_sb = sb; + err = rpc_setup_pipedir_sb(sb, clnt); + if (err) + clnt->pipefs_sb = NULL; + break; case RPC_PIPEFS_UMOUNT: - __rpc_clnt_remove_pipedir(clnt); + if (clnt->pipefs_sb == sb) { + __rpc_clnt_remove_pipedir(clnt); + clnt->pipefs_sb = NULL; + } break; default: printk(KERN_ERR "%s: unknown event: %ld\n", __func__, event); return -ENOTSUPP; } - return 0; + return err; } static int __rpc_pipefs_event(struct rpc_clnt *clnt, unsigned long event, diff --git a/net/sunrpc/sunrpc_syms.c b/net/sunrpc/sunrpc_syms.c index bab6cab29405..04109278fda6 100644 --- a/net/sunrpc/sunrpc_syms.c +++ b/net/sunrpc/sunrpc_syms.c @@ -54,6 +54,7 @@ static __net_init int sunrpc_init_net(struct net *net) INIT_LIST_HEAD(&sn->all_clients); spin_lock_init(&sn->rpc_client_lock); spin_lock_init(&sn->rpcb_clnt_lock); + mutex_init(&sn->gssp_lock); return 0; err_pipefs: diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index 1f4bf5b290e4..1c7410488236 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -352,7 +352,7 @@ static int svc_pool_map_get_node(unsigned int pidx) if (m->mode == SVC_POOL_PERNODE) return m->pool_to[pidx]; } - return numa_mem_id(); + return NUMA_NO_NODE; } /* * Set the given thread's cpus_allowed mask so that it @@ -402,6 +402,7 @@ struct svc_pool *svc_pool_for_cpu(struct svc_serv *serv) struct svc_pool_map *m = &svc_pool_map; int cpu = raw_smp_processor_id(); unsigned int pidx = 0; + unsigned int i; if (serv->sv_nrpools <= 1) return serv->sv_pools; @@ -414,8 +415,34 @@ struct svc_pool *svc_pool_for_cpu(struct svc_serv *serv) pidx = m->to_pool[cpu_to_node(cpu)]; break; } + pidx %= serv->sv_nrpools; + + /* + * It's possible to have a pool with no threads. Userland can just set + * things up this way directly. Also, when threads are autodistributed + * they are spread evenly across the pools, but when there are fewer + * threads than pools some pools can end up with none. + * + * A transport enqueued on a threadless pool would never be picked up, + * since each thread only services its own pool. Fall back to the next + * populated pool, trading NUMA locality for a guarantee that the + * transport is serviced. + */ + for (i = 0; i < serv->sv_nrpools; i++) { + struct svc_pool *pool = &serv->sv_pools[pidx]; + + /* This is set under the service mutex and rarely ever + * changes. A data race here is harmless. + */ + if (data_race(pool->sp_nrthreads)) + return pool; + + if (++pidx >= serv->sv_nrpools) + pidx = 0; + } - return &serv->sv_pools[pidx % serv->sv_nrpools]; + /* No pool has any threads; nothing can service the transport. */ + return &serv->sv_pools[pidx]; } static int svc_rpcb_setup(struct svc_serv *serv, struct net *net) @@ -476,6 +503,35 @@ __svc_init_bc(struct svc_serv *serv) } #endif +static int svc_pool_init_counters(struct svc_pool *pool) +{ + int err; + + err = percpu_counter_init(&pool->sp_messages_arrived, 0, GFP_KERNEL); + if (err) + return err; + err = percpu_counter_init(&pool->sp_sockets_queued, 0, GFP_KERNEL); + if (err) + goto err_sockets; + err = percpu_counter_init(&pool->sp_threads_woken, 0, GFP_KERNEL); + if (err) + goto err_threads; + return 0; + +err_threads: + percpu_counter_destroy(&pool->sp_sockets_queued); +err_sockets: + percpu_counter_destroy(&pool->sp_messages_arrived); + return err; +} + +static void svc_pool_destroy_counters(struct svc_pool *pool) +{ + percpu_counter_destroy(&pool->sp_messages_arrived); + percpu_counter_destroy(&pool->sp_sockets_queued); + percpu_counter_destroy(&pool->sp_threads_woken); +} + /* * Create an RPC service */ @@ -541,12 +597,18 @@ __svc_create(struct svc_program *prog, int nprogs, struct svc_stat *stats, INIT_LIST_HEAD(&pool->sp_all_threads); init_llist_head(&pool->sp_idle_threads); - percpu_counter_init(&pool->sp_messages_arrived, 0, GFP_KERNEL); - percpu_counter_init(&pool->sp_sockets_queued, 0, GFP_KERNEL); - percpu_counter_init(&pool->sp_threads_woken, 0, GFP_KERNEL); + if (svc_pool_init_counters(pool)) + goto out_err; } return serv; + +out_err: + while (i--) + svc_pool_destroy_counters(&serv->sv_pools[i]); + kfree(serv->sv_pools); + kfree(serv); + return NULL; } /** @@ -625,9 +687,7 @@ svc_destroy(struct svc_serv **servp) for (i = 0; i < serv->sv_nrpools; i++) { struct svc_pool *pool = &serv->sv_pools[i]; - percpu_counter_destroy(&pool->sp_messages_arrived); - percpu_counter_destroy(&pool->sp_sockets_queued); - percpu_counter_destroy(&pool->sp_threads_woken); + svc_pool_destroy_counters(pool); } kfree(serv->sv_pools); kfree(serv); @@ -663,6 +723,15 @@ svc_release_buffer(struct svc_rqst *rqstp) kfree(rqstp->rq_pages); } +static void svc_rqst_free_rcu(struct rcu_head *head) +{ + struct svc_rqst *rqstp = container_of(head, struct svc_rqst, rq_rcu_head); + + kfree(rqstp->rq_resp); + kfree(rqstp->rq_argp); + kfree(rqstp); +} + static void svc_rqst_free(struct svc_rqst *rqstp) { @@ -671,10 +740,8 @@ svc_rqst_free(struct svc_rqst *rqstp) svc_release_buffer(rqstp); if (rqstp->rq_scratch_folio) folio_put(rqstp->rq_scratch_folio); - kfree(rqstp->rq_resp); - kfree(rqstp->rq_argp); kfree(rqstp->rq_auth_data); - kfree_rcu(rqstp, rq_rcu_head); + call_rcu(&rqstp->rq_rcu_head, svc_rqst_free_rcu); } static struct svc_rqst * @@ -691,7 +758,9 @@ svc_prepare_thread(struct svc_serv *serv, struct svc_pool *pool, int node) rqstp->rq_server = serv; rqstp->rq_pool = pool; - rqstp->rq_scratch_folio = __folio_alloc_node(GFP_KERNEL, 0, node); + rqstp->rq_scratch_folio = __folio_alloc_node(GFP_KERNEL, 0, + node == NUMA_NO_NODE ? + numa_mem_id() : node); if (!rqstp->rq_scratch_folio) goto out_enomem; diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c index fb4dab207000..d3cd543ff80a 100644 --- a/net/sunrpc/xdr.c +++ b/net/sunrpc/xdr.c @@ -2049,7 +2049,7 @@ void xdr_buf_trim(struct xdr_buf *buf, unsigned int len) trim -= cur; } fix_len: - buf->len -= (len - trim); + buf->len -= min_t(unsigned int, buf->len, len - trim); } EXPORT_SYMBOL_GPL(xdr_buf_trim); diff --git a/net/sunrpc/xprtrdma/ib_client.c b/net/sunrpc/xprtrdma/ib_client.c index 28c68b5f6823..cfc24e21d260 100644 --- a/net/sunrpc/xprtrdma/ib_client.c +++ b/net/sunrpc/xprtrdma/ib_client.c @@ -51,7 +51,11 @@ static struct rpcrdma_device *rpcrdma_get_client_data(struct ib_device *device) * to be invoked when the device is removed, unless this notification * is unregistered first. * - * On failure, a negative errno is returned. + * On failure, a negative errno is returned. rn->rn_done is left + * NULL on every failure path (it is assigned only after xa_alloc + * and kref_get have both succeeded), so the @rn may safely be + * passed to rpcrdma_rn_unregister() without a separate + * registered/unregistered flag in the caller. */ int rpcrdma_rn_register(struct ib_device *device, struct rpcrdma_notification *rn, @@ -83,6 +87,10 @@ static void rpcrdma_rn_release(struct kref *kref) * rpcrdma_rn_unregister - stop device removal notifications * @device: monitored device * @rn: notification object that no longer wishes to be notified + * + * It is safe to call this on an @rn whose registration never + * completed or failed; rn_done == NULL is treated as + * never-registered and the call is a no-op. */ void rpcrdma_rn_unregister(struct ib_device *device, struct rpcrdma_notification *rn) @@ -92,6 +100,20 @@ void rpcrdma_rn_unregister(struct ib_device *device, if (!rd) return; + /* + * rn_done is the registration sentinel: rpcrdma_rn_register + * assigns it last, after xa_alloc and kref_get have both + * succeeded. A NULL rn_done means this notification was + * never registered (or its registration failed) or has + * already been unregistered, and the call is a no-op. + * Without this guard, rn_index == 0 from a kzalloc'd + * parent would erase another caller's slot 0 and underflow + * rd_kref. + */ + if (!rn->rn_done) + return; + rn->rn_done = NULL; + trace_rpcrdma_client_unregister(device, rn); xa_erase(&rd->rd_xa, rn->rn_index); kref_put(&rd->rd_kref, rpcrdma_rn_release); diff --git a/net/sunrpc/xprtrdma/svc_rdma_pcl.c b/net/sunrpc/xprtrdma/svc_rdma_pcl.c index b63cfeaa2923..a1c61311714d 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_pcl.c +++ b/net/sunrpc/xprtrdma/svc_rdma_pcl.c @@ -213,7 +213,6 @@ bool pcl_alloc_write(struct svc_rdma_recv_ctxt *rctxt, chunk = pcl_alloc_chunk(segcount, 0); if (!chunk) return false; - list_add_tail(&chunk->ch_list, &pcl->cl_chunks); for (j = 0; j < segcount; j++) { segment = &chunk->ch_segments[j]; @@ -225,6 +224,7 @@ bool pcl_alloc_write(struct svc_rdma_recv_ctxt *rctxt, chunk->ch_length += segment->rs_length; chunk->ch_segcount++; } + list_add_tail(&chunk->ch_list, &pcl->cl_chunks); } return true; } diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c index e7e4a39ca6c6..68a0aa627455 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c +++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c @@ -498,10 +498,13 @@ static bool xdr_check_write_chunk(struct svc_rdma_recv_ctxt *rctxt) return false; /* Before trusting the segcount value enough to use it in - * a computation, perform a simple range check. This is an - * arbitrary but sensible limit (ie, not architectural). + * a computation, perform a simple range check. A zero + * segcount describes no remote buffer and is rejected so + * downstream consumers never see a degenerate ch_segcount==0 + * chunk. The upper bound is an arbitrary but sensible limit + * (ie, not architectural). */ - if (unlikely(segcount > rctxt->rc_maxpages)) + if (segcount == 0 || unlikely(segcount > rctxt->rc_maxpages)) return false; p = xdr_inline_decode(&rctxt->rc_stream, diff --git a/net/sunrpc/xprtrdma/svc_rdma_rw.c b/net/sunrpc/xprtrdma/svc_rdma_rw.c index 310de7a80be5..b3700c1478ea 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_rw.c +++ b/net/sunrpc/xprtrdma/svc_rdma_rw.c @@ -817,7 +817,7 @@ static int svc_rdma_build_read_chunk(struct svc_rqst *rqstp, * svc_rdma_copy_inline_range - Copy part of the inline content into pages * @rqstp: RPC transaction context * @head: context for ongoing I/O - * @offset: offset into the Receive buffer of region to copy + * @offset: offset into the inline content of region to copy * @remaining: length of region to copy * * Take a page at a time from rqstp->rq_pages and copy the inline @@ -834,9 +834,13 @@ static int svc_rdma_copy_inline_range(struct svc_rqst *rqstp, unsigned int offset, unsigned int remaining) { - unsigned char *dst, *src = head->rc_recv_buf; + unsigned char *dst, *src = head->rc_saved_arg.head[0].iov_base; + unsigned int inline_len = head->rc_saved_arg.head[0].iov_len; unsigned int page_no, numpages; + if (offset > inline_len || remaining > inline_len - offset) + return -EINVAL; + numpages = PAGE_ALIGN(head->rc_pageoff + remaining) >> PAGE_SHIFT; for (page_no = 0; page_no < numpages; page_no++) { unsigned int page_len; @@ -887,9 +891,10 @@ svc_rdma_read_multiple_chunks(struct svc_rqst *rqstp, { const struct svc_rdma_pcl *pcl = &head->rc_read_pcl; struct svc_rdma_chunk *chunk, *next; - unsigned int start, length; + unsigned int inline_len, start, length; int ret; + inline_len = head->rc_saved_arg.head[0].iov_len; start = 0; chunk = pcl_first_chunk(pcl); length = chunk->ch_position; @@ -907,6 +912,8 @@ svc_rdma_read_multiple_chunks(struct svc_rqst *rqstp, break; start += length; + if (head->rc_readbytes > next->ch_position) + return -EINVAL; length = next->ch_position - head->rc_readbytes; ret = svc_rdma_copy_inline_range(rqstp, head, start, length); if (ret < 0) @@ -914,7 +921,9 @@ svc_rdma_read_multiple_chunks(struct svc_rqst *rqstp, } start += length; - length = head->rc_byte_len - start; + if (start > inline_len) + return -EINVAL; + length = inline_len - start; return svc_rdma_copy_inline_range(rqstp, head, start, length); } @@ -939,8 +948,12 @@ svc_rdma_read_multiple_chunks(struct svc_rqst *rqstp, static int svc_rdma_read_data_item(struct svc_rqst *rqstp, struct svc_rdma_recv_ctxt *head) { - return svc_rdma_build_read_chunk(rqstp, head, - pcl_first_chunk(&head->rc_read_pcl)); + struct svc_rdma_chunk *chunk = pcl_first_chunk(&head->rc_read_pcl); + + if (chunk->ch_position > head->rc_saved_arg.head[0].iov_len) + return -EINVAL; + + return svc_rdma_build_read_chunk(rqstp, head, chunk); } /** @@ -966,17 +979,20 @@ static int svc_rdma_read_chunk_range(struct svc_rqst *rqstp, const struct svc_rdma_segment *segment; int ret; + if (!length) + return 0; + ret = -EINVAL; pcl_for_each_segment(segment, chunk) { struct svc_rdma_segment dummy; - if (offset > segment->rs_length) { + if (offset >= segment->rs_length) { offset -= segment->rs_length; continue; } dummy.rs_handle = segment->rs_handle; - dummy.rs_length = min_t(u32, length, segment->rs_length) - offset; + dummy.rs_length = min_t(u32, length, segment->rs_length - offset); dummy.rs_offset = segment->rs_offset + offset; ret = svc_rdma_build_read_segment(rqstp, head, &dummy); @@ -985,6 +1001,8 @@ static int svc_rdma_read_chunk_range(struct svc_rqst *rqstp, head->rc_readbytes += dummy.rs_length; length -= dummy.rs_length; + if (!length) + break; offset = 0; } return ret; @@ -1009,14 +1027,17 @@ static int svc_rdma_read_call_chunk(struct svc_rqst *rqstp, pcl_first_chunk(&head->rc_call_pcl); const struct svc_rdma_pcl *pcl = &head->rc_read_pcl; struct svc_rdma_chunk *chunk, *next; - unsigned int start, length; + unsigned int call_len, start, length; int ret; if (pcl_is_empty(pcl)) return svc_rdma_build_read_chunk(rqstp, head, call_chunk); + call_len = call_chunk->ch_length; start = 0; chunk = pcl_first_chunk(pcl); + if (chunk->ch_position > call_len) + return -EINVAL; length = chunk->ch_position; ret = svc_rdma_read_chunk_range(rqstp, head, call_chunk, start, length); @@ -1033,6 +1054,10 @@ static int svc_rdma_read_call_chunk(struct svc_rqst *rqstp, break; start += length; + if (next->ch_position > call_len) + return -EINVAL; + if (head->rc_readbytes > next->ch_position) + return -EINVAL; length = next->ch_position - head->rc_readbytes; ret = svc_rdma_read_chunk_range(rqstp, head, call_chunk, start, length); @@ -1041,7 +1066,9 @@ static int svc_rdma_read_call_chunk(struct svc_rqst *rqstp, } start += length; - length = call_chunk->ch_length - start; + if (start > call_len) + return -EINVAL; + length = call_len - start; return svc_rdma_read_chunk_range(rqstp, head, call_chunk, start, length); } diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c index 914cd263c2f1..082db5cea213 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c +++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c @@ -700,20 +700,21 @@ static int svc_rdma_xb_count_sges(const struct xdr_buf *xdr, } /** - * svc_rdma_pull_up_needed - Determine whether to use pull-up + * svc_rdma_check_pull_up - Determine whether to use pull-up * @rdma: controlling transport * @sctxt: send_ctxt for the Send WR * @write_pcl: Write chunk list provided by client * @xdr: xdr_buf containing RPC message to transmit * * Returns: - * %true if pull-up must be used - * %false otherwise + * %1 if pull-up must be used + * %0 if pull-up is not needed + * %-E2BIG if the reply is too large to be pulled up */ -static bool svc_rdma_pull_up_needed(const struct svcxprt_rdma *rdma, - const struct svc_rdma_send_ctxt *sctxt, - const struct svc_rdma_pcl *write_pcl, - const struct xdr_buf *xdr) +static int svc_rdma_check_pull_up(const struct svcxprt_rdma *rdma, + const struct svc_rdma_send_ctxt *sctxt, + const struct svc_rdma_pcl *write_pcl, + const struct xdr_buf *xdr) { /* Resources needed for the transport header */ struct svc_rdma_pullup_data args = { @@ -725,11 +726,22 @@ static bool svc_rdma_pull_up_needed(const struct svcxprt_rdma *rdma, ret = pcl_process_nonpayloads(write_pcl, xdr, svc_rdma_xb_count_sges, &args); if (ret < 0) - return false; + return 0; if (args.pd_length < RPCRDMA_PULLUP_THRESH) - return true; - return args.pd_num_sges >= rdma->sc_max_send_sges; + return 1; + if (args.pd_num_sges < rdma->sc_max_send_sges) + return 0; + + /* + * The reply has too many SGEs to Send inline, so it has to be + * linearized into sc_xprt_buf. That buffer holds only + * sc_max_req_size bytes, so a larger reply cannot be pulled up. + * RFC 8166 Section 4.5.3 requires responding with ERR_CHUNK. + */ + if (args.pd_length > rdma->sc_max_req_size) + return -E2BIG; + return 1; } /** @@ -785,7 +797,7 @@ static int svc_rdma_xb_linearize(const struct xdr_buf *xdr, * Assemble the elements of @xdr into the transport header buffer. * * Assumptions: - * pull_up_needed has determined that @xdr will fit in the buffer. + * check_pull_up has determined that @xdr will fit in the buffer. * * Returns: * %0 if pull-up was successful @@ -820,6 +832,7 @@ static int svc_rdma_pull_up_reply_msg(const struct svcxprt_rdma *rdma, * * Returns: * %0 if DMA mapping was successful. + * %-E2BIG if the reply is too large to be pulled up * %-EMSGSIZE if a buffer manipulation problem occurred * %-EIO if DMA mapping failed * @@ -835,6 +848,7 @@ int svc_rdma_map_reply_msg(struct svcxprt_rdma *rdma, .md_rdma = rdma, .md_ctxt = sctxt, }; + int ret; /* Set up the (persistently-mapped) transport header SGE. */ sctxt->sc_send_wr.num_sge = 1; @@ -849,7 +863,10 @@ int svc_rdma_map_reply_msg(struct svcxprt_rdma *rdma, /* For pull-up, svc_rdma_send() will sync the transport header. * No additional DMA mapping is necessary. */ - if (svc_rdma_pull_up_needed(rdma, sctxt, write_pcl, xdr)) + ret = svc_rdma_check_pull_up(rdma, sctxt, write_pcl, xdr); + if (ret < 0) + return ret; + if (ret) return svc_rdma_pull_up_reply_msg(rdma, sctxt, write_pcl, xdr); return pcl_process_nonpayloads(write_pcl, xdr, @@ -1033,7 +1050,7 @@ int svc_rdma_sendto(struct svc_rqst *rqstp) &rctxt->rc_reply_pcl, sctxt, &rqstp->rq_res); if (ret < 0) - goto reply_chunk; + goto send_err; rc_size = ret; } @@ -1054,10 +1071,10 @@ int svc_rdma_sendto(struct svc_rqst *rqstp) ret = svc_rdma_send_reply_msg(rdma, sctxt, rctxt, rqstp); if (ret < 0) - goto put_ctxt; + goto send_err; return 0; -reply_chunk: +send_err: if (ret != -E2BIG && ret != -EINVAL) goto put_ctxt; diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c index 12857381e861..c8d994272f6f 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_transport.c +++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c @@ -43,6 +43,7 @@ */ #include <linux/interrupt.h> +#include <linux/module.h> #include <linux/sched.h> #include <linux/slab.h> #include <linux/spinlock.h> @@ -226,12 +227,16 @@ svc_rdma_parse_connect_private(struct svcxprt_rdma *newxprt, * structure for the listening endpoint. * * This function creates a new xprt for the new connection and enqueues it on - * the accept queue for the listent xprt. When the listen thread is kicked, it + * the accept queue for the listen xprt. When the listen thread is kicked, it * will call the recvfrom method on the listen xprt which will accept the new * connection. + * + * Return values: + * %0: Do not destroy @new_cma_id + * %1: Destroy @new_cma_id (allocation failure) */ -static void handle_connect_req(struct rdma_cm_id *new_cma_id, - struct rdma_conn_param *param) +static int handle_connect_req(struct rdma_cm_id *new_cma_id, + struct rdma_conn_param *param) { struct svcxprt_rdma *listen_xprt = new_cma_id->context; struct svcxprt_rdma *newxprt; @@ -241,7 +246,7 @@ static void handle_connect_req(struct rdma_cm_id *new_cma_id, listen_xprt->sc_xprt.xpt_net, ibdev_to_node(new_cma_id->device)); if (!newxprt) - return; + return 1; newxprt->sc_cm_id = new_cma_id; new_cma_id->context = newxprt; svc_rdma_parse_connect_private(newxprt, param); @@ -275,6 +280,7 @@ static void handle_connect_req(struct rdma_cm_id *new_cma_id, set_bit(XPT_CONN, &listen_xprt->sc_xprt.xpt_flags); svc_xprt_enqueue(&listen_xprt->sc_xprt); + return 0; } /** @@ -298,8 +304,7 @@ static int svc_rdma_listen_handler(struct rdma_cm_id *cma_id, switch (event->event) { case RDMA_CM_EVENT_CONNECT_REQUEST: - handle_connect_req(cma_id, &event->param.conn); - break; + return handle_connect_req(cma_id, &event->param.conn); case RDMA_CM_EVENT_ADDR_CHANGE: listen_id = svc_rdma_create_listen_id(cma_rdma->xpt_net, sap, cma_xprt); @@ -576,13 +581,26 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt) return &newxprt->sc_xprt; errout: - /* Take a reference in case the DTO handler runs */ - svc_xprt_get(&newxprt->sc_xprt); - if (newxprt->sc_qp && !IS_ERR(newxprt->sc_qp)) - ib_destroy_qp(newxprt->sc_qp); - rdma_destroy_id(newxprt->sc_cm_id); - rpcrdma_rn_unregister(dev, &newxprt->sc_rn); - /* This call to put will destroy the transport */ + /* + * Drop the kref_init birth reference. svc_xprt_free will + * dispatch xpo_free = svc_rdma_free, which tears down sc_qp, + * sc_sq_cq, sc_rq_cq, and sc_pd under existing IS_ERR/NULL + * guards, and sc_rn under the rn_done sentinel guard inside + * rpcrdma_rn_unregister. + * + * sc_cm_id is destroyed unconditionally by svc_rdma_free; that + * is safe here because sc_cm_id is non-NULL by caller invariant + * on every path that reaches this errout: handle_connect_req + * installs newxprt->sc_cm_id before queueing the new xprt for + * accept, and svc_rdma_accept has already dereferenced it above + * the first goto errout. + * + * svc_handle_xprt() drops its pre-acquired module reference when + * ->xpo_accept() returns NULL. Take a replacement reference before + * freeing @newxprt, because svc_xprt_free() drops the module + * reference associated with @newxprt. + */ + __module_get(newxprt->sc_xprt.xpt_class->xcl_owner); svc_xprt_put(&newxprt->sc_xprt); return NULL; } diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 6b64c6c49494..a4422cbd3254 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -2647,7 +2647,17 @@ static int xs_tls_handshake_sync(struct rpc_xprt *lower_xprt, struct xprtsec_par rc = wait_for_completion_interruptible_timeout(&lower_transport->handshake_done, XS_TLS_HANDSHAKE_TO); if (rc <= 0) { - tls_handshake_cancel(sk); + if (!tls_handshake_cancel(sk)) { + /* + * Cancellation lost to handshake_complete(): the + * callback still owns its xprt reference and is in + * flight. Wait for it to finish before returning. + */ + wait_for_completion(&lower_transport->handshake_done); + if (rc == 0) + rc = -ETIMEDOUT; + goto out; + } if (rc == 0) rc = -ETIMEDOUT; goto out_put_xprt; diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c index 698cec8cbdab..8b56ff4bdf4d 100644 --- a/net/vmw_vsock/virtio_transport.c +++ b/net/vmw_vsock/virtio_transport.c @@ -848,10 +848,10 @@ static void virtio_vsock_remove(struct virtio_device *vdev) /* Other works can be queued before 'config->del_vqs()', so we flush * all works before to free the vsock object to avoid use after free. */ - flush_work(&vsock->rx_work); flush_work(&vsock->tx_work); flush_work(&vsock->event_work); flush_work(&vsock->send_pkt_work); + flush_work(&vsock->rx_work); mutex_unlock(&the_virtio_vsock_mutex); diff --git a/rust/kernel/bug.rs b/rust/kernel/bug.rs index 36aef43e5ebe..13ac693e7811 100644 --- a/rust/kernel/bug.rs +++ b/rust/kernel/bug.rs @@ -8,6 +8,7 @@ #[macro_export] #[doc(hidden)] +#[cfg(not(testlib))] #[cfg(all(CONFIG_BUG, not(CONFIG_UML), not(CONFIG_LOONGARCH), not(CONFIG_ARM)))] #[cfg(CONFIG_DEBUG_BUGVERBOSE)] macro_rules! warn_flags { @@ -47,6 +48,7 @@ macro_rules! warn_flags { #[macro_export] #[doc(hidden)] +#[cfg(not(testlib))] #[cfg(all(CONFIG_BUG, not(CONFIG_UML), not(CONFIG_LOONGARCH), not(CONFIG_ARM)))] #[cfg(not(CONFIG_DEBUG_BUGVERBOSE))] macro_rules! warn_flags { @@ -73,6 +75,7 @@ macro_rules! warn_flags { #[macro_export] #[doc(hidden)] +#[cfg(not(testlib))] #[cfg(all(CONFIG_BUG, CONFIG_UML))] macro_rules! warn_flags { ($flags:expr) => { @@ -91,6 +94,7 @@ macro_rules! warn_flags { #[macro_export] #[doc(hidden)] +#[cfg(not(testlib))] #[cfg(all(CONFIG_BUG, any(CONFIG_LOONGARCH, CONFIG_ARM)))] macro_rules! warn_flags { ($flags:expr) => { @@ -101,7 +105,7 @@ macro_rules! warn_flags { #[macro_export] #[doc(hidden)] -#[cfg(not(CONFIG_BUG))] +#[cfg(any(testlib, not(CONFIG_BUG)))] macro_rules! warn_flags { ($flags:expr) => {}; } diff --git a/rust/kernel/list.rs b/rust/kernel/list.rs index 7355bbac16a7..fb4ed721d1f6 100644 --- a/rust/kernel/list.rs +++ b/rust/kernel/list.rs @@ -233,7 +233,7 @@ pub use self::arc_field::{define_list_arc_field_getter, ListArcField}; /// assert_eq!(list.iter().count(), 3); /// } /// -/// // Pop the items from the list using `pop_front()` and verify the content. +/// // Pop the items from the list using `pop_back()` and verify the content. /// { /// assert_eq!(list.pop_back().ok_or(EINVAL)?.value.foo(), ("a", 15)); /// assert_eq!(list.pop_back().ok_or(EINVAL)?.value.foo(), ("a", 32)); diff --git a/rust/kernel/time.rs b/rust/kernel/time.rs index c1e83aed2b46..0c944d89f0bc 100644 --- a/rust/kernel/time.rs +++ b/rust/kernel/time.rs @@ -421,22 +421,25 @@ impl Delta { /// to the value in the [`Delta`]. #[inline] pub fn as_micros_ceil(self) -> i64 { + // Only positive values need to be rounded up: truncating division already + // rounds towards zero, i.e. up, for negative values. + // + // The usual `(nanos + d - 1) / d` is not used because the addition overflows + // once `nanos` exceeds `i64::MAX - (d - 1)`; saturating the addition instead + // would drop the rounding bias and return a result one unit too small. let n = self.as_nanos(); - let n = if n >= 0 { - n.saturating_add(NSEC_PER_USEC - 1) - } else { - n - }; + + let (n, add) = if n > 0 { (n - 1, 1) } else { (n, 0) }; #[cfg(CONFIG_64BIT)] { - n / NSEC_PER_USEC + n / NSEC_PER_USEC + add } #[cfg(not(CONFIG_64BIT))] // SAFETY: It is always safe to call `ktime_to_us()` with any value. unsafe { - bindings::ktime_to_us(n) + bindings::ktime_to_us(n) + add } } diff --git a/scripts/rust_is_available.sh b/scripts/rust_is_available.sh index d2323de0692c..82be88d44c18 100755 --- a/scripts/rust_is_available.sh +++ b/scripts/rust_is_available.sh @@ -242,6 +242,20 @@ if [ "$bindgen_libclang_cversion" -ge 1900100 ] && fi fi +if [ "$bindgen_libclang_cversion" -ge 2200000 ] && + [ "$rust_bindings_generator_cversion" -lt 7201 ]; then + # Distributions may have patched the issue. + if ! "$BINDGEN" $(dirname $0)/rust_is_available_bindgen_libclang_22.h | grep -q 'pub foo'; then + echo >&2 "***" + echo >&2 "*** Rust bindings generator '$BINDGEN' < 0.72.1 together with libclang >= 22" + echo >&2 "*** may not work due to a bug (https://github.com/rust-lang/rust-bindgen/pull/3278)." + echo >&2 "*** Your bindgen version: $rust_bindings_generator_version" + echo >&2 "*** Your libclang version: $bindgen_libclang_version" + echo >&2 "***" + warning=1 + fi +fi + # If the C compiler is Clang, then we can also check whether its version # matches the `libclang` version used by the Rust bindings generator. # diff --git a/scripts/rust_is_available_bindgen_libclang_22.h b/scripts/rust_is_available_bindgen_libclang_22.h new file mode 100644 index 000000000000..6b33544c14a8 --- /dev/null +++ b/scripts/rust_is_available_bindgen_libclang_22.h @@ -0,0 +1,5 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +struct S; +struct S { + int foo; +}; diff --git a/scripts/rust_is_available_test.py b/scripts/rust_is_available_test.py index 4fcc319dea84..a5fadef98132 100755 --- a/scripts/rust_is_available_test.py +++ b/scripts/rust_is_available_test.py @@ -54,7 +54,7 @@ else: """) @classmethod - def generate_bindgen(cls, version_stdout, libclang_stderr, version_0_66_patched=False, libclang_concat_patched=False): + def generate_bindgen(cls, version_stdout, libclang_stderr, version_0_66_patched=False, libclang_concat_patched=False, libclang_22_patched=False): if libclang_stderr is None: libclang_case = f"raise SystemExit({cls.bindgen_default_bindgen_libclang_failure_exit_code})" else: @@ -70,6 +70,11 @@ else: else: libclang_concat_case = "pass" + if libclang_22_patched: + libclang_22_case = "print('pub foo: ::std::os::raw::c_int,')" + else: + libclang_22_case = "pass" + return cls.generate_executable(f"""#!/usr/bin/env python3 import sys if "rust_is_available_bindgen_libclang.h" in " ".join(sys.argv): @@ -78,6 +83,8 @@ elif "rust_is_available_bindgen_0_66.h" in " ".join(sys.argv): {version_0_66_case} elif "rust_is_available_bindgen_libclang_concat.h" in " ".join(sys.argv): {libclang_concat_case} +elif "rust_is_available_bindgen_libclang_22.h" in " ".join(sys.argv): + {libclang_22_case} else: print({repr(version_stdout)}) """) @@ -300,6 +307,27 @@ else: bindgen = self.generate_bindgen(f"bindgen {bindgen_version}", libclang_stderr, libclang_concat_patched=True) result = self.run_script(self.Expected.SUCCESS, { "BINDGEN": bindgen, "CC": cc }) + def test_bindgen_bad_libclang_22(self): + for (bindgen_version, libclang_version, expected_not_patched) in ( + ("0.71.1", "21.1.0", self.Expected.SUCCESS), + ("0.71.1", "22.0.0", self.Expected.SUCCESS_WITH_WARNINGS), + ("0.71.1", "22.1.0", self.Expected.SUCCESS_WITH_WARNINGS), + + ("0.72.0", "22.0.0", self.Expected.SUCCESS_WITH_WARNINGS), + + ("0.72.1", "22.0.0", self.Expected.SUCCESS), + ): + with self.subTest(bindgen_version=bindgen_version, libclang_version=libclang_version): + cc = self.generate_clang(f"clang version {libclang_version}") + libclang_stderr = f"scripts/rust_is_available_bindgen_libclang.h:2:9: warning: clang version {libclang_version} [-W#pragma-messages], err: false" + bindgen = self.generate_bindgen(f"bindgen {bindgen_version}", libclang_stderr) + result = self.run_script(expected_not_patched, { "BINDGEN": bindgen, "CC": cc }) + if expected_not_patched == self.Expected.SUCCESS_WITH_WARNINGS: + self.assertIn(f"Rust bindings generator '{bindgen}' < 0.72.1 together with libclang >= 22", result.stderr) + + bindgen = self.generate_bindgen(f"bindgen {bindgen_version}", libclang_stderr, libclang_22_patched=True) + result = self.run_script(self.Expected.SUCCESS, { "BINDGEN": bindgen, "CC": cc }) + def test_clang_matches_bindgen_libclang_different_bindgen(self): bindgen = self.generate_bindgen_libclang("scripts/rust_is_available_bindgen_libclang.h:2:9: warning: clang version 999.0.0 [-W#pragma-messages], err: false") result = self.run_script(self.Expected.SUCCESS_WITH_WARNINGS, { "BINDGEN": bindgen }) diff --git a/security/apparmor/include/cred.h b/security/apparmor/include/cred.h index b028e4c13b6f..d37f33f0eec8 100644 --- a/security/apparmor/include/cred.h +++ b/security/apparmor/include/cred.h @@ -184,13 +184,9 @@ static inline struct aa_label *begin_current_label_crit_section(void) { struct aa_label *label = aa_current_raw_label(); - might_sleep(); - if (label_is_stale(label)) { label = aa_get_newest_label(label); - if (aa_replace_current_label(label) == 0) - /* task cred will keep the reference */ - aa_put_label(label); + aa_schedule_stale_label_replacement(); } return label; diff --git a/security/apparmor/include/label.h b/security/apparmor/include/label.h index 335f21930702..574be681f83e 100644 --- a/security/apparmor/include/label.h +++ b/security/apparmor/include/label.h @@ -23,7 +23,7 @@ struct aa_ruleset; #define LOCAL_VEC_ENTRIES 8 #define DEFINE_VEC(T, V) \ - struct aa_ ## T *(_ ## V ## _localtmp)[LOCAL_VEC_ENTRIES]; \ + struct aa_ ## T *(_ ## V ## _localtmp)[LOCAL_VEC_ENTRIES + 1]; \ struct aa_ ## T **(V) #define vec_setup(T, V, N, GFP) \ @@ -31,10 +31,10 @@ struct aa_ruleset; if ((N) <= LOCAL_VEC_ENTRIES) { \ typeof(N) i; \ (V) = (_ ## V ## _localtmp); \ - for (i = 0; i < (N); i++) \ + for (i = 0; i <= (N); i++) \ (V)[i] = NULL; \ } else \ - (V) = kzalloc(sizeof(struct aa_ ## T *) * (N), (GFP)); \ + (V) = kzalloc_objs(struct aa_ ## T *, (N) + 1, (GFP)); \ (V) ? 0 : -ENOMEM; \ }) diff --git a/security/apparmor/include/task.h b/security/apparmor/include/task.h index b1aaaf60fa8b..6f26758ca10f 100644 --- a/security/apparmor/include/task.h +++ b/security/apparmor/include/task.h @@ -21,15 +21,22 @@ static inline struct aa_task_ctx *task_ctx(struct task_struct *task) * @onexec: profile to transition to on next exec (MAY BE NULL) * @previous: profile the task may return to (MAY BE NULL) * @token: magic value the task must know for returning to @previous_profile + * @label_replacement_tw: for aa_schedule_stale_label_replacement() + * @label_replacement_pending: is @label_replacement_tw pending? + * + * When changing this, check if aa_dup_task_ctx() needs to be updated. */ struct aa_task_ctx { struct aa_label *nnp; struct aa_label *onexec; struct aa_label *previous; u64 token; + struct callback_head label_replacement_tw; + bool label_replacement_pending; }; int aa_replace_current_label(struct aa_label *label); +void aa_schedule_stale_label_replacement(void); void aa_set_current_onexec(struct aa_label *label, bool stack); int aa_set_current_hat(struct aa_label *label, u64 token); int aa_restore_previous_label(u64 cookie); @@ -56,10 +63,10 @@ static inline void aa_free_task_ctx(struct aa_task_ctx *ctx) static inline void aa_dup_task_ctx(struct aa_task_ctx *new, const struct aa_task_ctx *old) { - *new = *old; - aa_get_label(new->nnp); - aa_get_label(new->previous); - aa_get_label(new->onexec); + new->nnp = aa_get_label(old->nnp); + new->onexec = aa_get_label(old->onexec); + new->previous = aa_get_label(old->previous); + new->token = old->token; } /** diff --git a/security/apparmor/task.c b/security/apparmor/task.c index c9bc9cc69475..f9519baa4e60 100644 --- a/security/apparmor/task.c +++ b/security/apparmor/task.c @@ -14,6 +14,7 @@ #include <linux/gfp.h> #include <linux/ptrace.h> +#include <linux/task_work.h> #include "include/audit.h" #include "include/cred.h" @@ -88,6 +89,32 @@ int aa_replace_current_label(struct aa_label *label) return 0; } +static void aa_replace_stale_label_tw_func(struct callback_head *tw) +{ + struct aa_task_ctx *ctx = task_ctx(current); + struct aa_label *label; + + ctx->label_replacement_pending = false; + label = aa_current_raw_label(); + if (!label_is_stale(label)) + return; + label = aa_get_newest_label(label); + aa_replace_current_label(label); + aa_put_label(label); +} + +/* replace the current task's stale label on syscall return */ +void aa_schedule_stale_label_replacement(void) +{ + struct aa_task_ctx *ctx = task_ctx(current); + + if (ctx->label_replacement_pending) + return; + init_task_work(&ctx->label_replacement_tw, aa_replace_stale_label_tw_func); + if (task_work_add(current, &ctx->label_replacement_tw, TWA_RESUME) == 0) + ctx->label_replacement_pending = true; +} + /** * aa_set_current_onexec - set the tasks change_profile to happen onexec diff --git a/security/keys/trusted-keys/trusted_tpm1.c b/security/keys/trusted-keys/trusted_tpm1.c index 636acb66a4f6..ea6717da7cba 100644 --- a/security/keys/trusted-keys/trusted_tpm1.c +++ b/security/keys/trusted-keys/trusted_tpm1.c @@ -981,9 +981,9 @@ err_put: static void trusted_tpm_exit(void) { if (chip) { + unregister_key_type(&key_type_trusted); put_device(&chip->dev); kfree(digests); - unregister_key_type(&key_type_trusted); } } diff --git a/security/landlock/errata/abi-1.h b/security/landlock/errata/abi-1.h index e8a2bff2e5b6..80930957e84d 100644 --- a/security/landlock/errata/abi-1.h +++ b/security/landlock/errata/abi-1.h @@ -14,3 +14,26 @@ * actions. */ LANDLOCK_ERRATUM(3) + +/** + * DOC: erratum_4 + * + * Erratum 4: Creation of whiteout objects + * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + * + * This fix changes the access rights required for the creation of whiteout + * objects through :manpage:`mknod(2)`, :manpage:`renameat2(2)`, or + * :manpage:`link(2)`. Creating whiteout objects is now guarded by + * ``LANDLOCK_ACCESS_FS_MAKE_REG`` instead of ``LANDLOCK_ACCESS_FS_MAKE_CHAR``. + * + * Whiteout objects are used in OverlayFS to mark the absence of a file in an + * upper file system. Despite being created with ``S_IFCHR``, whiteout objects + * do not count as character devices. + * + * Impact: + * + * Sandboxed programs that create OverlayFS whiteouts (such as fuse-overlayfs) + * now require ``LANDLOCK_ACCESS_FS_MAKE_REG`` instead of + * ``LANDLOCK_ACCESS_FS_MAKE_CHAR``. + */ +LANDLOCK_ERRATUM(4) diff --git a/security/landlock/fs.c b/security/landlock/fs.c index 4f8dfeadbbe2..d741ed3e5568 100644 --- a/security/landlock/fs.c +++ b/security/landlock/fs.c @@ -20,6 +20,7 @@ #include <linux/falloc.h> #include <linux/fs.h> #include <linux/init.h> +#include <linux/kdev_t.h> #include <linux/kernel.h> #include <linux/limits.h> #include <linux/list.h> @@ -985,7 +986,8 @@ static int current_check_access_path(const struct path *const path, return -EACCES; } -static __attribute_const__ access_mask_t get_mode_access(const umode_t mode) +static __attribute_const__ access_mask_t get_mode_access(const umode_t mode, + const dev_t dev) { switch (mode & S_IFMT) { case S_IFLNK: @@ -993,6 +995,9 @@ static __attribute_const__ access_mask_t get_mode_access(const umode_t mode) case S_IFDIR: return LANDLOCK_ACCESS_FS_MAKE_DIR; case S_IFCHR: + /* Whiteout objects are guarded with MAKE_REG. */ + if (dev == WHITEOUT_DEV) + return LANDLOCK_ACCESS_FS_MAKE_REG; return LANDLOCK_ACCESS_FS_MAKE_CHAR; case S_IFBLK: return LANDLOCK_ACCESS_FS_MAKE_BLOCK; @@ -1009,6 +1014,13 @@ static __attribute_const__ access_mask_t get_mode_access(const umode_t mode) } } +static access_mask_t get_dentry_access(const struct dentry *const dentry) +{ + const struct inode *const inode = d_backing_inode(dentry); + + return get_mode_access(inode->i_mode, inode->i_rdev); +} + static access_mask_t maybe_remove(const struct dentry *const dentry) { if (d_is_negative(dentry)) @@ -1098,6 +1110,7 @@ static bool collect_domain_accesses( * @new_dentry: Destination file or directory. * @removable: Sets to true if it is a rename operation. * @exchange: Sets to true if it is a rename operation with RENAME_EXCHANGE. + * @whiteout: Sets to true if it is a rename operation with RENAME_WHITEOUT. * * Because of its unprivileged constraints, Landlock relies on file hierarchies * (and not only inodes) to tie access rights to files. Being able to link or @@ -1146,7 +1159,8 @@ static bool collect_domain_accesses( static int current_check_refer_path(struct dentry *const old_dentry, const struct path *const new_dir, struct dentry *const new_dentry, - const bool removable, const bool exchange) + const bool removable, const bool exchange, + const bool whiteout) { const struct landlock_cred_security *const subject = landlock_get_applicable_subject(current_cred(), any_fs, NULL); @@ -1166,18 +1180,25 @@ static int current_check_refer_path(struct dentry *const old_dentry, if (exchange) { if (unlikely(d_is_negative(new_dentry))) return -ENOENT; - access_request_parent1 = - get_mode_access(d_backing_inode(new_dentry)->i_mode); + access_request_parent1 = get_dentry_access(new_dentry); } else { access_request_parent1 = 0; } - access_request_parent2 = - get_mode_access(d_backing_inode(old_dentry)->i_mode); + access_request_parent2 = get_dentry_access(old_dentry); if (removable) { access_request_parent1 |= maybe_remove(old_dentry); access_request_parent2 |= maybe_remove(new_dentry); } + /* + * In case of renameat2(2) with RENAME_WHITEOUT, a whiteout object is + * created in the source location, so we require an additional access + * right there. + */ + if (whiteout) + access_request_parent1 |= + get_mode_access(S_IFCHR | WHITEOUT_MODE, WHITEOUT_DEV); + /* The mount points are the same for old and new paths, cf. EXDEV. */ if (old_dentry->d_parent == new_dir->dentry) { /* @@ -1527,7 +1548,7 @@ static int hook_path_link(struct dentry *const old_dentry, struct dentry *const new_dentry) { return current_check_refer_path(old_dentry, new_dir, new_dentry, false, - false); + false, false); } static int hook_path_rename(const struct path *const old_dir, @@ -1538,7 +1559,8 @@ static int hook_path_rename(const struct path *const old_dir, { /* old_dir refers to old_dentry->d_parent and new_dir->mnt */ return current_check_refer_path(old_dentry, new_dir, new_dentry, true, - !!(flags & RENAME_EXCHANGE)); + !!(flags & RENAME_EXCHANGE), + !!(flags & RENAME_WHITEOUT)); } static int hook_path_mkdir(const struct path *const dir, @@ -1551,7 +1573,8 @@ static int hook_path_mknod(const struct path *const dir, struct dentry *const dentry, const umode_t mode, const unsigned int dev) { - return current_check_access_path(dir, get_mode_access(mode)); + return current_check_access_path( + dir, get_mode_access(mode, new_decode_dev(dev))); } static int hook_path_symlink(const struct path *const dir, diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c index 7fd8a60b8be9..0d984fdf211a 100644 --- a/security/smack/smack_lsm.c +++ b/security/smack/smack_lsm.c @@ -1969,7 +1969,7 @@ static int smack_file_send_sigiotask(struct task_struct *tsk, { struct smack_known **blob; struct smack_known *skp; - struct smack_known *tkp = smk_of_task(smack_cred(tsk->cred)); + struct smack_known *tkp = smk_of_task_struct_obj(tsk); const struct cred *tcred; struct file *file; int rc; diff --git a/sound/core/ump_convert.c b/sound/core/ump_convert.c index 0fe13d031656..85cc67de6330 100644 --- a/sound/core/ump_convert.c +++ b/sound/core/ump_convert.c @@ -258,6 +258,7 @@ static int cvt_legacy_sysex_to_ump(struct ump_cvt_to_ump *cvt, else status = UMP_SYSEX_STATUS_CONTINUE; *data = ump_compose(UMP_MSG_TYPE_DATA, group, status, cvt->len); + data[1] = 0; offset = 8; for (i = 0; i < cvt->len; i++) { *data |= cvt->buf[i] << offset; diff --git a/sound/drivers/aloop.c b/sound/drivers/aloop.c index 3f8488716a08..d08027681c37 100644 --- a/sound/drivers/aloop.c +++ b/sound/drivers/aloop.c @@ -1805,6 +1805,12 @@ static int loopback_probe(struct platform_device *devptr) int dev = devptr->id; int err; + if (dev < 0 || dev >= SNDRV_CARDS) { + dev_warn(&devptr->dev, + "Invalid card index %d, using default 0\n", dev); + dev = 0; + } + err = snd_devm_card_new(&devptr->dev, index[dev], id[dev], THIS_MODULE, sizeof(struct loopback), &card); if (err < 0) diff --git a/sound/drivers/mpu401/mpu401.c b/sound/drivers/mpu401/mpu401.c index d3f9424088d4..e1550e02d264 100644 --- a/sound/drivers/mpu401/mpu401.c +++ b/sound/drivers/mpu401/mpu401.c @@ -89,6 +89,12 @@ static int snd_mpu401_probe(struct platform_device *devptr) int err; struct snd_card *card; + if (dev < 0 || dev >= SNDRV_CARDS) { + dev_warn(&devptr->dev, + "Invalid card index %d, using default 0\n", dev); + dev = 0; + } + if (port[dev] == SNDRV_AUTO_PORT) { dev_err(&devptr->dev, "specify port\n"); return -EINVAL; diff --git a/sound/drivers/mts64.c b/sound/drivers/mts64.c index fe50b48c10e7..017e478bd21f 100644 --- a/sound/drivers/mts64.c +++ b/sound/drivers/mts64.c @@ -900,6 +900,12 @@ static int snd_mts64_probe(struct platform_device *pdev) p = platform_get_drvdata(pdev); platform_set_drvdata(pdev, NULL); + if (dev < 0) { + dev_warn(&pdev->dev, + "Invalid card index %d, using default 0\n", dev); + dev = 0; + } + if (dev >= SNDRV_CARDS) return -ENODEV; if (!enable[dev]) diff --git a/sound/drivers/portman2x4.c b/sound/drivers/portman2x4.c index b903a138fc2a..fc7aa7ceb5a5 100644 --- a/sound/drivers/portman2x4.c +++ b/sound/drivers/portman2x4.c @@ -697,6 +697,12 @@ static int snd_portman_probe(struct platform_device *pdev) p = platform_get_drvdata(pdev); platform_set_drvdata(pdev, NULL); + if (dev < 0) { + dev_warn(&pdev->dev, + "Invalid card index %d, using default 0\n", dev); + dev = 0; + } + if (dev >= SNDRV_CARDS) return -ENODEV; if (!enable[dev]) diff --git a/sound/drivers/serial-u16550.c b/sound/drivers/serial-u16550.c index 3c28961091b1..cc9c325df910 100644 --- a/sound/drivers/serial-u16550.c +++ b/sound/drivers/serial-u16550.c @@ -846,6 +846,12 @@ static int snd_serial_probe(struct platform_device *devptr) int err; int dev = devptr->id; + if (dev < 0 || dev >= SNDRV_CARDS) { + dev_warn(&devptr->dev, + "Invalid card index %d, using default 0\n", dev); + dev = 0; + } + switch (adaptor[dev]) { case SNDRV_SERIAL_SOUNDCANVAS: ins[dev] = 1; diff --git a/sound/drivers/virmidi.c b/sound/drivers/virmidi.c index a204f42d1026..70e16105f1c4 100644 --- a/sound/drivers/virmidi.c +++ b/sound/drivers/virmidi.c @@ -75,6 +75,12 @@ static int snd_virmidi_probe(struct platform_device *devptr) int idx, err; int dev = devptr->id; + if (dev < 0 || dev >= SNDRV_CARDS) { + dev_warn(&devptr->dev, + "Invalid card index %d, using default 0\n", dev); + dev = 0; + } + err = snd_devm_card_new(&devptr->dev, index[dev], id[dev], THIS_MODULE, sizeof(struct snd_card_virmidi), &card); if (err < 0) diff --git a/sound/hda/codecs/realtek/alc269.c b/sound/hda/codecs/realtek/alc269.c index e79997b34302..2e2e90d03787 100644 --- a/sound/hda/codecs/realtek/alc269.c +++ b/sound/hda/codecs/realtek/alc269.c @@ -7014,6 +7014,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8dfc, "HP EliteBook 645 G12", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8dfd, "HP EliteBook 6 G1a 16", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), SND_PCI_QUIRK(0x103c, 0x8dfe, "HP EliteBook 665 G12", ALC236_FIXUP_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8e0d, "HP EliteBook 6 G1a 14 (AD3Q9ET#UUG)", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), SND_PCI_QUIRK(0x103c, 0x8e11, "HP Trekker", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x103c, 0x8e12, "HP Trekker", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x103c, 0x8e13, "HP Trekker", ALC287_FIXUP_CS35L41_I2C_2), @@ -7464,6 +7465,10 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x38a8, "Y780P AMD VECO dual", ALC287_FIXUP_TAS2781_I2C), SND_PCI_QUIRK(0x17aa, 0x38a9, "Thinkbook 16P", ALC287_FIXUP_MG_RTKC_CSAMP_CS35L41_I2C_THINKPAD), SND_PCI_QUIRK(0x17aa, 0x38ab, "Thinkbook 16P", ALC287_FIXUP_MG_RTKC_CSAMP_CS35L41_I2C_THINKPAD), + /* Lenovo Yoga Slim 7 14AKP10 shares PCI SSID 17aa:38b4 with Legion Slim 7 + * 16IRH8; use codec SSID to distinguish them + */ + HDA_CODEC_QUIRK(0x17aa, 0x391a, "Lenovo Yoga Slim 7 14AKP10", ALC287_FIXUP_YOGA9_14IAP7_BASS_SPK_PIN), SND_PCI_QUIRK(0x17aa, 0x38b4, "Legion Slim 7 16IRH8", ALC287_FIXUP_CS35L41_I2C_2), HDA_CODEC_QUIRK(0x17aa, 0x391c, "Lenovo Yoga 7 2-in-1 14AKP10", ALC287_FIXUP_YOGA9_14IAP7_BASS_SPK_PIN), HDA_CODEC_QUIRK(0x17aa, 0x391d, "Lenovo Yoga 7 2-in-1 16AKP10", ALC287_FIXUP_YOGA9_14IAP7_BASS_SPK_PIN), @@ -7498,7 +7503,6 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x390d, "Lenovo Yoga Pro 7 14ASP10", ALC287_FIXUP_YOGA9_14IAP7_BASS_SPK_PIN), SND_PCI_QUIRK(0x17aa, 0x3911, "Lenovo Yoga Pro 7 14IAH10", ALC287_FIXUP_YOGA9_14IAP7_BASS_SPK_PIN), SND_PCI_QUIRK(0x17aa, 0x3913, "Lenovo 145", ALC236_FIXUP_LENOVO_INV_DMIC), - SND_PCI_QUIRK(0x17aa, 0x391a, "Lenovo Yoga Slim 7 14AKP10", ALC287_FIXUP_YOGA9_14IAP7_BASS_SPK_PIN), SND_PCI_QUIRK(0x17aa, 0x391f, "Yoga S990-16 pro Quad YC Quad", ALC287_FIXUP_TXNW2781_I2C), SND_PCI_QUIRK(0x17aa, 0x3920, "Yoga S990-16 pro Quad VECO Quad", ALC287_FIXUP_TXNW2781_I2C), SND_PCI_QUIRK(0x17aa, 0x3929, "Thinkbook 13x Gen 5", ALC287_FIXUP_MG_RTKC_CSAMP_CS35L41_I2C_THINKPAD), @@ -7563,6 +7567,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1d05, 0x3031, "TongFang X6AR55xU", ALC2XX_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x1d05, 0x3033, "TongFang X6SP45xU", ALC2XX_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x1d05, 0x3034, "TongFang X6KK45xU", ALC2XX_FIXUP_HEADSET_MIC), + SND_PCI_QUIRK(0x1d05, 0x30ba, "TongFang XxAF5xxx", ALC2XX_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x1d17, 0x3288, "Haier Boyue G42", ALC269VC_FIXUP_ACER_VCOPPERBOX_PINS), SND_PCI_QUIRK(0x1d72, 0x1602, "RedmiBook", ALC255_FIXUP_XIAOMI_HEADSET_MIC), SND_PCI_QUIRK(0x1d72, 0x1701, "XiaomiNotebook Pro", ALC298_FIXUP_DELL1_MIC_NO_PRESENCE), diff --git a/sound/hda/core/ext/stream.c b/sound/hda/core/ext/stream.c index b4759198e51d..f6d80f95333b 100644 --- a/sound/hda/core/ext/stream.c +++ b/sound/hda/core/ext/stream.c @@ -211,8 +211,8 @@ void snd_hdac_ext_stream_reset(struct hdac_ext_stream *hext_stream) break; udelay(3); } while (--timeout); - val &= ~AZX_PPLCCTL_STRST; - writel(val, hext_stream->pplc_addr + AZX_REG_PPLCCTL); + snd_hdac_updatel(hext_stream->pplc_addr, AZX_REG_PPLCCTL, + AZX_PPLCCTL_STRST, 0); udelay(3); timeout = 50; diff --git a/sound/pci/pcxhr/pcxhr.c b/sound/pci/pcxhr/pcxhr.c index 83066d08367e..7b37b2aa76a6 100644 --- a/sound/pci/pcxhr/pcxhr.c +++ b/sound/pci/pcxhr/pcxhr.c @@ -1532,6 +1532,13 @@ static int pcxhr_probe(struct pci_dev *pci, mgr->pci = pci; mgr->irq = -1; + /* ISR lock */ + mutex_init(&mgr->lock); + mutex_init(&mgr->msg_lock); + + /* init setup mutex*/ + mutex_init(&mgr->setup_mutex); + if (request_threaded_irq(pci->irq, pcxhr_interrupt, pcxhr_threaded_irq, IRQF_SHARED, KBUILD_MODNAME, mgr)) { @@ -1545,13 +1552,6 @@ static int pcxhr_probe(struct pci_dev *pci, "Digigram at 0x%lx & 0x%lx, 0x%lx irq %i", mgr->port[0], mgr->port[1], mgr->port[2], mgr->irq); - /* ISR lock */ - mutex_init(&mgr->lock); - mutex_init(&mgr->msg_lock); - - /* init setup mutex*/ - mutex_init(&mgr->setup_mutex); - mgr->prmh = kmalloc(sizeof(*mgr->prmh) + sizeof(u32) * (PCXHR_SIZE_MAX_LONG_STATUS - PCXHR_SIZE_MAX_STATUS), diff --git a/sound/soc/amd/yc/acp6x-mach.c b/sound/soc/amd/yc/acp6x-mach.c index d9f145b634f3..df845260f570 100644 --- a/sound/soc/amd/yc/acp6x-mach.c +++ b/sound/soc/amd/yc/acp6x-mach.c @@ -749,6 +749,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = { .driver_data = &acp6x_card, .matches = { DMI_MATCH(DMI_BOARD_VENDOR, "Micro-Star International Co., Ltd."), + DMI_MATCH(DMI_PRODUCT_NAME, "Thin A15 B7UC"), + } + }, + { + .driver_data = &acp6x_card, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "Micro-Star International Co., Ltd."), DMI_MATCH(DMI_PRODUCT_NAME, "Thin A15 B7VE"), } }, diff --git a/sound/usb/6fire/comm.c b/sound/usb/6fire/comm.c index 49629d4bb327..bcfb34db37d9 100644 --- a/sound/usb/6fire/comm.c +++ b/sound/usb/6fire/comm.c @@ -36,11 +36,14 @@ static void usb6fire_comm_receiver_handler(struct urb *urb) struct midi_runtime *midi_rt = rt->chip->midi; if (!urb->status) { - if (rt->receiver_buffer[0] == 0x10) /* midi in event */ + u8 len = rt->receiver_buffer[1]; + + if (rt->receiver_buffer[0] == 0x10 && /* midi in event */ + len <= COMM_RECEIVER_BUFSIZE - 2 && + urb->actual_length >= len + 2) if (midi_rt) midi_rt->in_received(midi_rt, - rt->receiver_buffer + 2, - rt->receiver_buffer[1]); + rt->receiver_buffer + 2, len); } if (!rt->chip->shutdown) { diff --git a/sound/usb/bcd2000/bcd2000.c b/sound/usb/bcd2000/bcd2000.c index bebb48cb9abc..c5c542d17ccc 100644 --- a/sound/usb/bcd2000/bcd2000.c +++ b/sound/usb/bcd2000/bcd2000.c @@ -134,6 +134,9 @@ static void bcd2000_midi_send(struct bcd2000 *bcd2k) if (!midi_out_substream) return; + if (!bcd2k->midi_out_urb) + return; + /* copy command prefix bytes */ memcpy(bcd2k->midi_out_buf, device_cmd_prefix, sizeof(device_cmd_prefix)); @@ -178,7 +181,7 @@ static int bcd2000_midi_output_close(struct snd_rawmidi_substream *substream) { struct bcd2000 *bcd2k = substream->rmidi->private_data; - if (bcd2k->midi_out_active) { + if (bcd2k->midi_out_active && bcd2k->midi_out_urb) { usb_kill_urb(bcd2k->midi_out_urb); bcd2k->midi_out_active = 0; } @@ -348,11 +351,13 @@ static int bcd2000_init_midi(struct bcd2000 *bcd2k) static void bcd2000_free_usb_related_resources(struct bcd2000 *bcd2k, struct usb_interface *interface) { - usb_kill_urb(bcd2k->midi_out_urb); - usb_kill_urb(bcd2k->midi_in_urb); + usb_poison_urb(bcd2k->midi_out_urb); + usb_poison_urb(bcd2k->midi_in_urb); usb_free_urb(bcd2k->midi_out_urb); usb_free_urb(bcd2k->midi_in_urb); + bcd2k->midi_out_urb = NULL; + bcd2k->midi_in_urb = NULL; if (bcd2k->intf) { usb_set_intfdata(bcd2k->intf, NULL); diff --git a/tools/include/linux/compiler.h b/tools/include/linux/compiler.h index f40bd2b04c29..f2f54b038168 100644 --- a/tools/include/linux/compiler.h +++ b/tools/include/linux/compiler.h @@ -119,7 +119,7 @@ #define __read_mostly #ifndef __attribute_const__ -# define __attribute_const__ +# define __attribute_const__ __attribute__ ((__const__)) #endif #ifndef __maybe_unused diff --git a/tools/testing/selftests/mm/run_vmtests.sh b/tools/testing/selftests/mm/run_vmtests.sh index 1edb2d785d93..0a6bc35190a1 100755 --- a/tools/testing/selftests/mm/run_vmtests.sh +++ b/tools/testing/selftests/mm/run_vmtests.sh @@ -370,7 +370,7 @@ CATEGORY="compaction" run_test ./compaction_test if command -v sudo &> /dev/null && sudo -u nobody ls ./on-fault-limit >/dev/null; then - CATEGORY="mlock" run_test sudo -u nobody ./on-fault-limit + CATEGORY="mlock" run_test sudo -u nobody sh -c ./on-fault-limit else echo "# SKIP ./on-fault-limit" fi |