diff --git a/Documentation/devicetree/bindings/sound/wm8994.txt b/Documentation/devicetree/bindings/sound/wm8994.txt index 68cccc4653ba..367b58ce1bb9 100644 --- a/Documentation/devicetree/bindings/sound/wm8994.txt +++ b/Documentation/devicetree/bindings/sound/wm8994.txt @@ -14,9 +14,15 @@ Required properties: - #gpio-cells : Must be 2. The first cell is the pin number and the second cell is used to specify optional parameters (currently unused). - - AVDD2-supply, DBVDD1-supply, DBVDD2-supply, DBVDD3-supply, CPVDD-supply, - SPKVDD1-supply, SPKVDD2-supply : power supplies for the device, as covered - in Documentation/devicetree/bindings/regulator/regulator.txt + - power supplies for the device, as covered in + Documentation/devicetree/bindings/regulator/regulator.txt, depending + on compatible: + - for wlf,wm1811 and wlf,wm8958: + AVDD1-supply, AVDD2-supply, DBVDD1-supply, DBVDD2-supply, DBVDD3-supply, + DCVDD-supply, CPVDD-supply, SPKVDD1-supply, SPKVDD2-supply + - for wlf,wm8994: + AVDD1-supply, AVDD2-supply, DBVDD-supply, DCVDD-supply, CPVDD-supply, + SPKVDD1-supply, SPKVDD2-supply Optional properties: @@ -73,11 +79,11 @@ wm8994: codec@1a { lineout1-se; + AVDD1-supply = <®ulator>; AVDD2-supply = <®ulator>; CPVDD-supply = <®ulator>; - DBVDD1-supply = <®ulator>; - DBVDD2-supply = <®ulator>; - DBVDD3-supply = <®ulator>; + DBVDD-supply = <®ulator>; + DCVDD-supply = <®ulator>; SPKVDD1-supply = <®ulator>; SPKVDD2-supply = <®ulator>; }; diff --git a/Documentation/driver-api/libata.rst b/Documentation/driver-api/libata.rst index 70e180e6b93d..9f3e5dc31184 100644 --- a/Documentation/driver-api/libata.rst +++ b/Documentation/driver-api/libata.rst @@ -250,7 +250,7 @@ High-level taskfile hooks :: - void (*qc_prep) (struct ata_queued_cmd *qc); + enum ata_completion_errors (*qc_prep) (struct ata_queued_cmd *qc); int (*qc_issue) (struct ata_queued_cmd *qc); diff --git a/Makefile b/Makefile index acb2499d9b05..adf384710677 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 5 PATCHLEVEL = 4 -SUBLEVEL = 68 +SUBLEVEL = 69 EXTRAVERSION = NAME = Kleptomaniac Octopus diff --git a/arch/arm/include/asm/kvm_emulate.h b/arch/arm/include/asm/kvm_emulate.h index cbde9fa15792..c1747fcb86d3 100644 --- a/arch/arm/include/asm/kvm_emulate.h +++ b/arch/arm/include/asm/kvm_emulate.h @@ -204,7 +204,7 @@ static inline int kvm_vcpu_dabt_get_rd(struct kvm_vcpu *vcpu) return (kvm_vcpu_get_hsr(vcpu) & HSR_SRT_MASK) >> HSR_SRT_SHIFT; } -static inline bool kvm_vcpu_dabt_iss1tw(struct kvm_vcpu *vcpu) +static inline bool kvm_vcpu_abt_iss1tw(const struct kvm_vcpu *vcpu) { return kvm_vcpu_get_hsr(vcpu) & HSR_DABT_S1PTW; } @@ -236,16 +236,21 @@ static inline bool kvm_vcpu_trap_il_is32bit(struct kvm_vcpu *vcpu) return kvm_vcpu_get_hsr(vcpu) & HSR_IL; } -static inline u8 kvm_vcpu_trap_get_class(struct kvm_vcpu *vcpu) +static inline u8 kvm_vcpu_trap_get_class(const struct kvm_vcpu *vcpu) { return kvm_vcpu_get_hsr(vcpu) >> HSR_EC_SHIFT; } -static inline bool kvm_vcpu_trap_is_iabt(struct kvm_vcpu *vcpu) +static inline bool kvm_vcpu_trap_is_iabt(const struct kvm_vcpu *vcpu) { return kvm_vcpu_trap_get_class(vcpu) == HSR_EC_IABT; } +static inline bool kvm_vcpu_trap_is_exec_fault(const struct kvm_vcpu *vcpu) +{ + return kvm_vcpu_trap_is_iabt(vcpu) && !kvm_vcpu_abt_iss1tw(vcpu); +} + static inline u8 kvm_vcpu_trap_get_fault(struct kvm_vcpu *vcpu) { return kvm_vcpu_get_hsr(vcpu) & HSR_FSC; diff --git a/arch/arm/kernel/stacktrace.c b/arch/arm/kernel/stacktrace.c index a082f6e4f0f4..76ea4178a55c 100644 --- a/arch/arm/kernel/stacktrace.c +++ b/arch/arm/kernel/stacktrace.c @@ -116,6 +116,8 @@ static int save_trace(struct stackframe *frame, void *d) return 0; regs = (struct pt_regs *)frame->sp; + if ((unsigned long)®s[1] > ALIGN(frame->sp, THREAD_SIZE)) + return 0; trace->entries[trace->nr_entries++] = regs->ARM_pc; diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c index c053abd1fb53..97a512551b21 100644 --- a/arch/arm/kernel/traps.c +++ b/arch/arm/kernel/traps.c @@ -64,14 +64,16 @@ static void dump_mem(const char *, const char *, unsigned long, unsigned long); void dump_backtrace_entry(unsigned long where, unsigned long from, unsigned long frame) { + unsigned long end = frame + 4 + sizeof(struct pt_regs); + #ifdef CONFIG_KALLSYMS printk("[<%08lx>] (%ps) from [<%08lx>] (%pS)\n", where, (void *)where, from, (void *)from); #else printk("Function entered at [<%08lx>] from [<%08lx>]\n", where, from); #endif - if (in_entry_text(from)) - dump_mem("", "Exception stack", frame + 4, frame + 4 + sizeof(struct pt_regs)); + if (in_entry_text(from) && end <= ALIGN(frame, THREAD_SIZE)) + dump_mem("", "Exception stack", frame + 4, end); } void dump_backtrace_stm(u32 *stack, u32 instruction) diff --git a/arch/arm/mach-omap2/cpuidle34xx.c b/arch/arm/mach-omap2/cpuidle34xx.c index 532a3e4b98c6..090a8aafb25e 100644 --- a/arch/arm/mach-omap2/cpuidle34xx.c +++ b/arch/arm/mach-omap2/cpuidle34xx.c @@ -109,6 +109,7 @@ static int omap3_enter_idle(struct cpuidle_device *dev, int index) { struct omap3_idle_statedata *cx = &omap3_idle_data[index]; + int error; if (omap_irq_pending() || need_resched()) goto return_sleep_time; @@ -125,8 +126,11 @@ static int omap3_enter_idle(struct cpuidle_device *dev, * Call idle CPU PM enter notifier chain so that * VFP context is saved. */ - if (cx->mpu_state == PWRDM_POWER_OFF) - cpu_pm_enter(); + if (cx->mpu_state == PWRDM_POWER_OFF) { + error = cpu_pm_enter(); + if (error) + goto out_clkdm_set; + } /* Execute ARM wfi */ omap_sram_idle(); @@ -139,6 +143,7 @@ static int omap3_enter_idle(struct cpuidle_device *dev, pwrdm_read_prev_pwrst(mpu_pd) == PWRDM_POWER_OFF) cpu_pm_exit(); +out_clkdm_set: /* Re-allow idle for C1 */ if (cx->flags & OMAP_CPUIDLE_CX_NO_CLKDM_IDLE) clkdm_allow_idle(mpu_pd->pwrdm_clkdms[0]); diff --git a/arch/arm/mach-omap2/cpuidle44xx.c b/arch/arm/mach-omap2/cpuidle44xx.c index fe75d4fa6073..6f5f89711f25 100644 --- a/arch/arm/mach-omap2/cpuidle44xx.c +++ b/arch/arm/mach-omap2/cpuidle44xx.c @@ -122,6 +122,7 @@ static int omap_enter_idle_coupled(struct cpuidle_device *dev, { struct idle_statedata *cx = state_ptr + index; u32 mpuss_can_lose_context = 0; + int error; /* * CPU0 has to wait and stay ON until CPU1 is OFF state. @@ -159,7 +160,9 @@ static int omap_enter_idle_coupled(struct cpuidle_device *dev, * Call idle CPU PM enter notifier chain so that * VFP and per CPU interrupt context is saved. */ - cpu_pm_enter(); + error = cpu_pm_enter(); + if (error) + goto cpu_pm_out; if (dev->cpu == 0) { pwrdm_set_logic_retst(mpu_pd, cx->mpu_logic_state); @@ -169,13 +172,17 @@ static int omap_enter_idle_coupled(struct cpuidle_device *dev, * Call idle CPU cluster PM enter notifier chain * to save GIC and wakeupgen context. */ - if (mpuss_can_lose_context) - cpu_cluster_pm_enter(); + if (mpuss_can_lose_context) { + error = cpu_cluster_pm_enter(); + if (error) + goto cpu_cluster_pm_out; + } } omap4_enter_lowpower(dev->cpu, cx->cpu_state); cpu_done[dev->cpu] = true; +cpu_cluster_pm_out: /* Wakeup CPU1 only if it is not offlined */ if (dev->cpu == 0 && cpumask_test_cpu(1, cpu_online_mask)) { @@ -197,12 +204,6 @@ static int omap_enter_idle_coupled(struct cpuidle_device *dev, } } - /* - * Call idle CPU PM exit notifier chain to restore - * VFP and per CPU IRQ context. - */ - cpu_pm_exit(); - /* * Call idle CPU cluster PM exit notifier chain * to restore GIC and wakeupgen context. @@ -210,6 +211,13 @@ static int omap_enter_idle_coupled(struct cpuidle_device *dev, if (dev->cpu == 0 && mpuss_can_lose_context) cpu_cluster_pm_exit(); + /* + * Call idle CPU PM exit notifier chain to restore + * VFP and per CPU IRQ context. + */ + cpu_pm_exit(); + +cpu_pm_out: tick_broadcast_exit(); fail: diff --git a/arch/arm/mach-omap2/pm34xx.c b/arch/arm/mach-omap2/pm34xx.c index 54254fc92c2e..fa66534a7ae2 100644 --- a/arch/arm/mach-omap2/pm34xx.c +++ b/arch/arm/mach-omap2/pm34xx.c @@ -194,6 +194,7 @@ void omap_sram_idle(void) int per_next_state = PWRDM_POWER_ON; int core_next_state = PWRDM_POWER_ON; u32 sdrc_pwr = 0; + int error; mpu_next_state = pwrdm_read_next_pwrst(mpu_pwrdm); switch (mpu_next_state) { @@ -222,8 +223,11 @@ void omap_sram_idle(void) pwrdm_pre_transition(NULL); /* PER */ - if (per_next_state == PWRDM_POWER_OFF) - cpu_cluster_pm_enter(); + if (per_next_state == PWRDM_POWER_OFF) { + error = cpu_cluster_pm_enter(); + if (error) + return; + } /* CORE */ if (core_next_state < PWRDM_POWER_ON) { diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h index f47081b40523..f65ff6b90f4a 100644 --- a/arch/arm64/include/asm/kvm_emulate.h +++ b/arch/arm64/include/asm/kvm_emulate.h @@ -299,7 +299,7 @@ static inline int kvm_vcpu_dabt_get_rd(const struct kvm_vcpu *vcpu) return (kvm_vcpu_get_hsr(vcpu) & ESR_ELx_SRT_MASK) >> ESR_ELx_SRT_SHIFT; } -static inline bool kvm_vcpu_dabt_iss1tw(const struct kvm_vcpu *vcpu) +static __always_inline bool kvm_vcpu_abt_iss1tw(const struct kvm_vcpu *vcpu) { return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_S1PTW); } @@ -307,7 +307,7 @@ static inline bool kvm_vcpu_dabt_iss1tw(const struct kvm_vcpu *vcpu) static inline bool kvm_vcpu_dabt_iswrite(const struct kvm_vcpu *vcpu) { return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_WNR) || - kvm_vcpu_dabt_iss1tw(vcpu); /* AF/DBM update */ + kvm_vcpu_abt_iss1tw(vcpu); /* AF/DBM update */ } static inline bool kvm_vcpu_dabt_is_cm(const struct kvm_vcpu *vcpu) @@ -336,6 +336,11 @@ static inline bool kvm_vcpu_trap_is_iabt(const struct kvm_vcpu *vcpu) return kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_IABT_LOW; } +static inline bool kvm_vcpu_trap_is_exec_fault(const struct kvm_vcpu *vcpu) +{ + return kvm_vcpu_trap_is_iabt(vcpu) && !kvm_vcpu_abt_iss1tw(vcpu); +} + static inline u8 kvm_vcpu_trap_get_fault(const struct kvm_vcpu *vcpu) { return kvm_vcpu_get_hsr(vcpu) & ESR_ELx_FSC; @@ -373,6 +378,9 @@ static inline int kvm_vcpu_sys_get_rt(struct kvm_vcpu *vcpu) static inline bool kvm_is_write_fault(struct kvm_vcpu *vcpu) { + if (kvm_vcpu_abt_iss1tw(vcpu)) + return true; + if (kvm_vcpu_trap_is_iabt(vcpu)) return false; diff --git a/arch/arm64/include/asm/sections.h b/arch/arm64/include/asm/sections.h index 788ae971f11c..25a73aab438f 100644 --- a/arch/arm64/include/asm/sections.h +++ b/arch/arm64/include/asm/sections.h @@ -15,6 +15,7 @@ extern char __hyp_text_start[], __hyp_text_end[]; extern char __idmap_text_start[], __idmap_text_end[]; extern char __initdata_begin[], __initdata_end[]; extern char __inittext_begin[], __inittext_end[]; +extern char __exittext_begin[], __exittext_end[]; extern char __irqentry_text_start[], __irqentry_text_end[]; extern char __mmuoff_data_start[], __mmuoff_data_end[]; extern char __entry_tramp_text_start[], __entry_tramp_text_end[]; diff --git a/arch/arm64/kernel/acpi.c b/arch/arm64/kernel/acpi.c index a100483b47c4..46ec402e97ed 100644 --- a/arch/arm64/kernel/acpi.c +++ b/arch/arm64/kernel/acpi.c @@ -19,6 +19,7 @@ #include <linux/init.h> #include <linux/irq.h> #include <linux/irqdomain.h> +#include <linux/irq_work.h> #include <linux/memblock.h> #include <linux/of_fdt.h> #include <linux/smp.h> @@ -269,6 +270,7 @@ pgprot_t __acpi_get_mem_attribute(phys_addr_t addr) int apei_claim_sea(struct pt_regs *regs) { int err = -ENOENT; + bool return_to_irqs_enabled; unsigned long current_flags; if (!IS_ENABLED(CONFIG_ACPI_APEI_GHES)) @@ -276,6 +278,12 @@ int apei_claim_sea(struct pt_regs *regs) current_flags = local_daif_save_flags(); + /* current_flags isn't useful here as daif doesn't tell us about pNMI */ + return_to_irqs_enabled = !irqs_disabled_flags(arch_local_save_flags()); + + if (regs) + return_to_irqs_enabled = interrupts_enabled(regs); + /* * SEA can interrupt SError, mask it and describe this as an NMI so * that APEI defers the handling. @@ -284,6 +292,23 @@ int apei_claim_sea(struct pt_regs *regs) nmi_enter(); err = ghes_notify_sea(); nmi_exit(); + + /* + * APEI NMI-like notifications are deferred to irq_work. Unless + * we interrupted irqs-masked code, we can do that now. + */ + if (!err) { + if (return_to_irqs_enabled) { + local_daif_restore(DAIF_PROCCTX_NOIRQ); + __irq_enter(); + irq_work_run(); + __irq_exit(); + } else { + pr_warn_ratelimited("APEI work queued but not completed"); + err = -EINPROGRESS; + } + } + local_daif_restore(current_flags); return err; diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index f400cb29b811..f2ec84540414 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -160,11 +160,10 @@ static const struct arm64_ftr_bits ftr_id_aa64pfr0[] = { ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_GIC_SHIFT, 4, 0), S_ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_ASIMD_SHIFT, 4, ID_AA64PFR0_ASIMD_NI), S_ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_FP_SHIFT, 4, ID_AA64PFR0_FP_NI), - /* Linux doesn't care about the EL3 */ ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL3_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL2_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL1_SHIFT, 4, ID_AA64PFR0_EL1_64BIT_ONLY), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL0_SHIFT, 4, ID_AA64PFR0_EL0_64BIT_ONLY), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL2_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL1_SHIFT, 4, ID_AA64PFR0_EL1_64BIT_ONLY), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL0_SHIFT, 4, ID_AA64PFR0_EL0_64BIT_ONLY), ARM64_FTR_END, }; @@ -320,7 +319,7 @@ static const struct arm64_ftr_bits ftr_id_pfr0[] = { }; static const struct arm64_ftr_bits ftr_id_dfr0[] = { - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 28, 4, 0), + /* [31:28] TraceFilt */ S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 24, 4, 0xf), /* PerfMon */ ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 20, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 16, 4, 0), @@ -719,9 +718,6 @@ void update_cpu_features(int cpu, taint |= check_update_ftr_reg(SYS_ID_AA64MMFR2_EL1, cpu, info->reg_id_aa64mmfr2, boot->reg_id_aa64mmfr2); - /* - * EL3 is not our concern. - */ taint |= check_update_ftr_reg(SYS_ID_AA64PFR0_EL1, cpu, info->reg_id_aa64pfr0, boot->reg_id_aa64pfr0); taint |= check_update_ftr_reg(SYS_ID_AA64PFR1_EL1, cpu, diff --git a/arch/arm64/kernel/insn.c b/arch/arm64/kernel/insn.c index a612da533ea2..53bcf5386907 100644 --- a/arch/arm64/kernel/insn.c +++ b/arch/arm64/kernel/insn.c @@ -21,6 +21,7 @@ #include <asm/fixmap.h> #include <asm/insn.h> #include <asm/kprobes.h> +#include <asm/sections.h> #define AARCH64_INSN_SF_BIT BIT(31) #define AARCH64_INSN_N_BIT BIT(22) @@ -78,16 +79,29 @@ bool aarch64_insn_is_branch_imm(u32 insn) static DEFINE_RAW_SPINLOCK(patch_lock); +static bool is_exit_text(unsigned long addr) +{ + /* discarded with init text/data */ + return system_state < SYSTEM_RUNNING && + addr >= (unsigned long)__exittext_begin && + addr < (unsigned long)__exittext_end; +} + +static bool is_image_text(unsigned long addr) +{ + return core_kernel_text(addr) || is_exit_text(addr); +} + static void __kprobes *patch_map(void *addr, int fixmap) { unsigned long uintaddr = (uintptr_t) addr; - bool module = !core_kernel_text(uintaddr); + bool image = is_image_text(uintaddr); struct page *page; - if (module && IS_ENABLED(CONFIG_STRICT_MODULE_RWX)) - page = vmalloc_to_page(addr); - else if (!module) + if (image) page = phys_to_page(__pa_symbol(addr)); + else if (IS_ENABLED(CONFIG_STRICT_MODULE_RWX)) + page = vmalloc_to_page(addr); else return addr; diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S index 4f77de8ce138..0bab37b1acbe 100644 --- a/arch/arm64/kernel/vmlinux.lds.S +++ b/arch/arm64/kernel/vmlinux.lds.S @@ -170,9 +170,12 @@ SECTIONS __inittext_begin = .; INIT_TEXT_SECTION(8) + + __exittext_begin = .; .exit.text : { ARM_EXIT_KEEP(EXIT_TEXT) } + __exittext_end = .; . = ALIGN(4); .altinstructions : { diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c index 65660b614474..84964983198e 100644 --- a/arch/arm64/kvm/hyp/switch.c +++ b/arch/arm64/kvm/hyp/switch.c @@ -496,7 +496,7 @@ static bool __hyp_text fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code) kvm_vcpu_trap_get_fault_type(vcpu) == FSC_FAULT && kvm_vcpu_dabt_isvalid(vcpu) && !kvm_vcpu_dabt_isextabt(vcpu) && - !kvm_vcpu_dabt_iss1tw(vcpu); + !kvm_vcpu_abt_iss1tw(vcpu); if (valid) { int ret = __vgic_v2_perform_cpuif_access(vcpu); diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index d26e6cd28953..2a7339aeb1ad 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -654,11 +654,13 @@ static int do_sea(unsigned long addr, unsigned int esr, struct pt_regs *regs) inf = esr_to_fault_info(esr); - /* - * Return value ignored as we rely on signal merging. - * Future patches will make this more robust. - */ - apei_claim_sea(regs); + if (user_mode(regs) && apei_claim_sea(regs) == 0) { + /* + * APEI claimed this as a firmware-first notification. + * Some processing deferred to task_work before ret_to_user(). + */ + return 0; + } if (esr & ESR_ELx_FnV) siaddr = NULL; diff --git a/arch/m68k/q40/config.c b/arch/m68k/q40/config.c index e63eb5f06999..f31890078197 100644 --- a/arch/m68k/q40/config.c +++ b/arch/m68k/q40/config.c @@ -264,6 +264,7 @@ static int q40_get_rtc_pll(struct rtc_pll_info *pll) { int tmp = Q40_RTC_CTRL; + pll->pll_ctrl = 0; pll->pll_value = tmp & Q40_RTC_PLL_MASK; if (tmp & Q40_RTC_PLL_SIGN) pll->pll_value = -pll->pll_value; diff --git a/arch/mips/include/asm/cpu-type.h b/arch/mips/include/asm/cpu-type.h index 7bbb66760a07..1809c408736b 100644 --- a/arch/mips/include/asm/cpu-type.h +++ b/arch/mips/include/asm/cpu-type.h @@ -47,6 +47,7 @@ static inline int __pure __get_cpu_type(const int cpu_type) case CPU_34K: case CPU_1004K: case CPU_74K: + case CPU_1074K: case CPU_M14KC: case CPU_M14KEC: case CPU_INTERAPTIV: diff --git a/arch/powerpc/include/asm/kvm_asm.h b/arch/powerpc/include/asm/kvm_asm.h index 635fb154b33f..a3633560493b 100644 --- a/arch/powerpc/include/asm/kvm_asm.h +++ b/arch/powerpc/include/asm/kvm_asm.h @@ -150,4 +150,7 @@ #define KVM_INST_FETCH_FAILED -1 +/* Extract PO and XOP opcode fields */ +#define PO_XOP_OPCODE_MASK 0xfc0007fe + #endif /* __POWERPC_KVM_ASM_H__ */ diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index dc0780f930d5..59260eb96291 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -19,6 +19,7 @@ CFLAGS_btext.o += $(DISABLE_LATENT_ENTROPY_PLUGIN) CFLAGS_prom.o += $(DISABLE_LATENT_ENTROPY_PLUGIN) CFLAGS_prom_init.o += $(call cc-option, -fno-stack-protector) +CFLAGS_prom_init.o += -DDISABLE_BRANCH_PROFILING ifdef CONFIG_FUNCTION_TRACER # Do not trace early boot code @@ -36,7 +37,6 @@ KASAN_SANITIZE_btext.o := n ifdef CONFIG_KASAN CFLAGS_early_32.o += -DDISABLE_BRANCH_PROFILING CFLAGS_cputable.o += -DDISABLE_BRANCH_PROFILING -CFLAGS_prom_init.o += -DDISABLE_BRANCH_PROFILING CFLAGS_btext.o += -DDISABLE_BRANCH_PROFILING endif diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c index bc8a551013be..c35069294ecf 100644 --- a/arch/powerpc/kernel/eeh.c +++ b/arch/powerpc/kernel/eeh.c @@ -503,7 +503,7 @@ int eeh_dev_check_failure(struct eeh_dev *edev) rc = 1; if (pe->state & EEH_PE_ISOLATED) { pe->check_count++; - if (pe->check_count % EEH_MAX_FAILS == 0) { + if (pe->check_count == EEH_MAX_FAILS) { dn = pci_device_to_OF_node(dev); if (dn) location = of_get_property(dn, "ibm,loc-code", diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index 014ff0701f24..9432fc6af28a 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -510,11 +510,11 @@ void system_reset_exception(struct pt_regs *regs) #ifdef CONFIG_PPC_BOOK3S_64 BUG_ON(get_paca()->in_nmi == 0); if (get_paca()->in_nmi > 1) - nmi_panic(regs, "Unrecoverable nested System Reset"); + die("Unrecoverable nested System Reset", regs, SIGABRT); #endif /* Must die if the interrupt is not recoverable */ if (!(regs->msr & MSR_RI)) - nmi_panic(regs, "Unrecoverable System Reset"); + die("Unrecoverable System Reset", regs, SIGABRT); if (saved_hsrrs) { mtspr(SPRN_HSRR0, hsrr0); @@ -858,7 +858,7 @@ void machine_check_exception(struct pt_regs *regs) /* Must die if the interrupt is not recoverable */ if (!(regs->msr & MSR_RI)) - nmi_panic(regs, "Unrecoverable Machine check"); + die("Unrecoverable Machine check", regs, SIGBUS); return; diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c index da8375437d16..9d7344835469 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_radix.c +++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c @@ -1104,6 +1104,11 @@ void kvmppc_radix_flush_memslot(struct kvm *kvm, kvm->arch.lpid); gpa += PAGE_SIZE; } + /* + * Increase the mmu notifier sequence number to prevent any page + * fault that read the memslot earlier from writing a PTE. + */ + kvm->mmu_notifier_seq++; spin_unlock(&kvm->mmu_lock); } diff --git a/arch/powerpc/kvm/book3s_hv_tm.c b/arch/powerpc/kvm/book3s_hv_tm.c index 0db937497169..cc90b8b82329 100644 --- a/arch/powerpc/kvm/book3s_hv_tm.c +++ b/arch/powerpc/kvm/book3s_hv_tm.c @@ -3,6 +3,8 @@ * Copyright 2017 Paul Mackerras, IBM Corp. <paulus@xxxxxxxxxxx> */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/kvm_host.h> #include <asm/kvm_ppc.h> @@ -44,7 +46,18 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu) u64 newmsr, bescr; int ra, rs; - switch (instr & 0xfc0007ff) { + /* + * rfid, rfebb, and mtmsrd encode bit 31 = 0 since it's a reserved bit + * in these instructions, so masking bit 31 out doesn't change these + * instructions. For treclaim., tsr., and trechkpt. instructions if bit + * 31 = 0 then they are per ISA invalid forms, however P9 UM, in section + * 4.6.10 Book II Invalid Forms, informs specifically that ignoring bit + * 31 is an acceptable way to handle these invalid forms that have + * bit 31 = 0. Moreover, for emulation purposes both forms (w/ and wo/ + * bit 31 set) can generate a softpatch interrupt. Hence both forms + * are handled below for these instructions so they behave the same way. + */ + switch (instr & PO_XOP_OPCODE_MASK) { case PPC_INST_RFID: /* XXX do we need to check for PR=0 here? */ newmsr = vcpu->arch.shregs.srr1; @@ -105,7 +118,8 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu) vcpu->arch.shregs.msr = newmsr; return RESUME_GUEST; - case PPC_INST_TSR: + /* ignore bit 31, see comment above */ + case (PPC_INST_TSR & PO_XOP_OPCODE_MASK): /* check for PR=1 and arch 2.06 bit set in PCR */ if ((msr & MSR_PR) && (vcpu->arch.vcore->pcr & PCR_ARCH_206)) { /* generate an illegal instruction interrupt */ @@ -140,7 +154,8 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu) vcpu->arch.shregs.msr = msr; return RESUME_GUEST; - case PPC_INST_TRECLAIM: + /* ignore bit 31, see comment above */ + case (PPC_INST_TRECLAIM & PO_XOP_OPCODE_MASK): /* check for TM disabled in the HFSCR or MSR */ if (!(vcpu->arch.hfscr & HFSCR_TM)) { /* generate an illegal instruction interrupt */ @@ -176,7 +191,8 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu) vcpu->arch.shregs.msr &= ~MSR_TS_MASK; return RESUME_GUEST; - case PPC_INST_TRECHKPT: + /* ignore bit 31, see comment above */ + case (PPC_INST_TRECHKPT & PO_XOP_OPCODE_MASK): /* XXX do we need to check for PR=0 here? */ /* check for TM disabled in the HFSCR or MSR */ if (!(vcpu->arch.hfscr & HFSCR_TM)) { @@ -208,6 +224,8 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu) } /* What should we do here? We didn't recognize the instruction */ - WARN_ON_ONCE(1); + kvmppc_core_queue_program(vcpu, SRR1_PROGILL); + pr_warn_ratelimited("Unrecognized TM-related instruction %#x for emulation", instr); + return RESUME_GUEST; } diff --git a/arch/powerpc/kvm/book3s_hv_tm_builtin.c b/arch/powerpc/kvm/book3s_hv_tm_builtin.c index 217246279dfa..fad931f224ef 100644 --- a/arch/powerpc/kvm/book3s_hv_tm_builtin.c +++ b/arch/powerpc/kvm/book3s_hv_tm_builtin.c @@ -23,7 +23,18 @@ int kvmhv_p9_tm_emulation_early(struct kvm_vcpu *vcpu) u64 newmsr, msr, bescr; int rs; - switch (instr & 0xfc0007ff) { + /* + * rfid, rfebb, and mtmsrd encode bit 31 = 0 since it's a reserved bit + * in these instructions, so masking bit 31 out doesn't change these + * instructions. For the tsr. instruction if bit 31 = 0 then it is per + * ISA an invalid form, however P9 UM, in section 4.6.10 Book II Invalid + * Forms, informs specifically that ignoring bit 31 is an acceptable way + * to handle TM-related invalid forms that have bit 31 = 0. Moreover, + * for emulation purposes both forms (w/ and wo/ bit 31 set) can + * generate a softpatch interrupt. Hence both forms are handled below + * for tsr. to make them behave the same way. + */ + switch (instr & PO_XOP_OPCODE_MASK) { case PPC_INST_RFID: /* XXX do we need to check for PR=0 here? */ newmsr = vcpu->arch.shregs.srr1; @@ -73,7 +84,8 @@ int kvmhv_p9_tm_emulation_early(struct kvm_vcpu *vcpu) vcpu->arch.shregs.msr = newmsr; return 1; - case PPC_INST_TSR: + /* ignore bit 31, see comment above */ + case (PPC_INST_TSR & PO_XOP_OPCODE_MASK): /* we know the MSR has the TS field = S (0b01) here */ msr = vcpu->arch.shregs.msr; /* check for PR=1 and arch 2.06 bit set in PCR */ diff --git a/arch/powerpc/mm/book3s64/iommu_api.c b/arch/powerpc/mm/book3s64/iommu_api.c index 56cc84520577..ef164851738b 100644 --- a/arch/powerpc/mm/book3s64/iommu_api.c +++ b/arch/powerpc/mm/book3s64/iommu_api.c @@ -121,24 +121,6 @@ static long mm_iommu_do_alloc(struct mm_struct *mm, unsigned long ua, goto free_exit; } - pageshift = PAGE_SHIFT; - for (i = 0; i < entries; ++i) { - struct page *page = mem->hpages[i]; - - /* - * Allow to use larger than 64k IOMMU pages. Only do that - * if we are backed by hugetlb. - */ - if ((mem->pageshift > PAGE_SHIFT) && PageHuge(page)) - pageshift = page_shift(compound_head(page)); - mem->pageshift = min(mem->pageshift, pageshift); - /* - * We don't need struct page reference any more, switch - * to physical address. - */ - mem->hpas[i] = page_to_pfn(page) << PAGE_SHIFT; - } - good_exit: atomic64_set(&mem->mapped, 1); mem->used = 1; @@ -158,6 +140,27 @@ static long mm_iommu_do_alloc(struct mm_struct *mm, unsigned long ua, } } + if (mem->dev_hpa == MM_IOMMU_TABLE_INVALID_HPA) { + /* + * Allow to use larger than 64k IOMMU pages. Only do that + * if we are backed by hugetlb. Skip device memory as it is not + * backed with page structs. + */ + pageshift = PAGE_SHIFT; + for (i = 0; i < entries; ++i) { + struct page *page = mem->hpages[i]; + + if ((mem->pageshift > PAGE_SHIFT) && PageHuge(page)) + pageshift = page_shift(compound_head(page)); + mem->pageshift = min(mem->pageshift, pageshift); + /* + * We don't need struct page reference any more, switch + * to physical address. + */ + mem->hpas[i] = page_to_pfn(page) << PAGE_SHIFT; + } + } + list_add_rcu(&mem->next, &mm->context.iommu_group_mem_list); mutex_unlock(&mem_list_mutex); diff --git a/arch/powerpc/perf/imc-pmu.c b/arch/powerpc/perf/imc-pmu.c index cb50a9e1fd2d..eb82dda884e5 100644 --- a/arch/powerpc/perf/imc-pmu.c +++ b/arch/powerpc/perf/imc-pmu.c @@ -44,6 +44,16 @@ static DEFINE_PER_CPU(u64 *, trace_imc_mem); static struct imc_pmu_ref *trace_imc_refc; static int trace_imc_mem_size; +/* + * Global data structure used to avoid races between thread, + * core and trace-imc + */ +static struct imc_pmu_ref imc_global_refc = { + .lock = __MUTEX_INITIALIZER(imc_global_refc.lock), + .id = 0, + .refc = 0, +}; + static struct imc_pmu *imc_event_to_pmu(struct perf_event *event) { return container_of(event->pmu, struct imc_pmu, pmu); @@ -698,6 +708,16 @@ static int ppc_core_imc_cpu_offline(unsigned int cpu) return -EINVAL; ref->refc = 0; + /* + * Reduce the global reference count, if this is the + * last cpu in this core and core-imc event running + * in this cpu. + */ + mutex_lock(&imc_global_refc.lock); + if (imc_global_refc.id == IMC_DOMAIN_CORE) + imc_global_refc.refc--; + + mutex_unlock(&imc_global_refc.lock); } return 0; } @@ -710,6 +730,23 @@ static int core_imc_pmu_cpumask_init(void) ppc_core_imc_cpu_offline); } +static void reset_global_refc(struct perf_event *event) +{ + mutex_lock(&imc_global_refc.lock); + imc_global_refc.refc--; + + /* + * If no other thread is running any + * event for this domain(thread/core/trace), + * set the global id to zero. + */ + if (imc_global_refc.refc <= 0) { + imc_global_refc.refc = 0; + imc_global_refc.id = 0; + } + mutex_unlock(&imc_global_refc.lock); +} + static void core_imc_counters_release(struct perf_event *event) { int rc, core_id; @@ -759,6 +796,8 @@ static void core_imc_counters_release(struct perf_event *event) ref->refc = 0; } mutex_unlock(&ref->lock); + + reset_global_refc(event); } static int core_imc_event_init(struct perf_event *event) @@ -819,6 +858,29 @@ static int core_imc_event_init(struct perf_event *event) ++ref->refc; mutex_unlock(&ref->lock); + /* + * Since the system can run either in accumulation or trace-mode + * of IMC at a time, core-imc events are allowed only if no other + * trace/thread imc events are enabled/monitored. + * + * Take the global lock, and check the refc.id + * to know whether any other trace/thread imc + * events are running. + */ + mutex_lock(&imc_global_refc.lock); + if (imc_global_refc.id == 0 || imc_global_refc.id == IMC_DOMAIN_CORE) { + /* + * No other trace/thread imc events are running in + * the system, so set the refc.id to core-imc. + */ + imc_global_refc.id = IMC_DOMAIN_CORE; + imc_global_refc.refc++; + } else { + mutex_unlock(&imc_global_refc.lock); + return -EBUSY; + } + mutex_unlock(&imc_global_refc.lock); + event->hw.event_base = (u64)pcmi->vbase + (config & IMC_EVENT_OFFSET_MASK); event->destroy = core_imc_counters_release; return 0; @@ -877,7 +939,23 @@ static int ppc_thread_imc_cpu_online(unsigned int cpu) static int ppc_thread_imc_cpu_offline(unsigned int cpu) { - mtspr(SPRN_LDBAR, 0); + /* + * Set the bit 0 of LDBAR to zero. + * + * If bit 0 of LDBAR is unset, it will stop posting + * the counter data to memory. + * For thread-imc, bit 0 of LDBAR will be set to 1 in the + * event_add function. So reset this bit here, to stop the updates + * to memory in the cpu_offline path. + */ + mtspr(SPRN_LDBAR, (mfspr(SPRN_LDBAR) & (~(1UL << 63)))); + + /* Reduce the refc if thread-imc event running on this cpu */ + mutex_lock(&imc_global_refc.lock); + if (imc_global_refc.id == IMC_DOMAIN_THREAD) + imc_global_refc.refc--; + mutex_unlock(&imc_global_refc.lock); + return 0; } @@ -916,7 +994,22 @@ static int thread_imc_event_init(struct perf_event *event) if (!target) return -EINVAL; + mutex_lock(&imc_global_refc.lock); + /* + * Check if any other trace/core imc events are running in the + * system, if not set the global id to thread-imc. + */ + if (imc_global_refc.id == 0 || imc_global_refc.id == IMC_DOMAIN_THREAD) { + imc_global_refc.id = IMC_DOMAIN_THREAD; + imc_global_refc.refc++; + } else { + mutex_unlock(&imc_global_refc.lock); + return -EBUSY; + } + mutex_unlock(&imc_global_refc.lock); + event->pmu->task_ctx_nr = perf_sw_context; + event->destroy = reset_global_refc; return 0; } @@ -1063,10 +1156,12 @@ static void thread_imc_event_del(struct perf_event *event, int flags) int core_id; struct imc_pmu_ref *ref; - mtspr(SPRN_LDBAR, 0); - core_id = smp_processor_id() / threads_per_core; ref = &core_imc_refc[core_id]; + if (!ref) { + pr_debug("imc: Failed to get event reference count\n"); + return; + } mutex_lock(&ref->lock); ref->refc--; @@ -1082,6 +1177,10 @@ static void thread_imc_event_del(struct perf_event *event, int flags) ref->refc = 0; } mutex_unlock(&ref->lock); + + /* Set bit 0 of LDBAR to zero, to stop posting updates to memory */ + mtspr(SPRN_LDBAR, (mfspr(SPRN_LDBAR) & (~(1UL << 63)))); + /* * Take a snapshot and calculate the delta and update * the event counter values. @@ -1133,7 +1232,18 @@ static int ppc_trace_imc_cpu_online(unsigned int cpu) static int ppc_trace_imc_cpu_offline(unsigned int cpu) { - mtspr(SPRN_LDBAR, 0); + /* + * No need to set bit 0 of LDBAR to zero, as + * it is set to zero for imc trace-mode + * + * Reduce the refc if any trace-imc event running + * on this cpu. + */ + mutex_lock(&imc_global_refc.lock); + if (imc_global_refc.id == IMC_DOMAIN_TRACE) + imc_global_refc.refc--; + mutex_unlock(&imc_global_refc.lock); + return 0; } @@ -1226,15 +1336,14 @@ static int trace_imc_event_add(struct perf_event *event, int flags) local_mem = get_trace_imc_event_base_addr(); ldbar_value = ((u64)local_mem & THREAD_IMC_LDBAR_MASK) | TRACE_IMC_ENABLE; - if (core_imc_refc) - ref = &core_imc_refc[core_id]; + /* trace-imc reference count */ + if (trace_imc_refc) + ref = &trace_imc_refc[core_id]; if (!ref) { - /* If core-imc is not enabled, use trace-imc reference count */ - if (trace_imc_refc) - ref = &trace_imc_refc[core_id]; - if (!ref) - return -EINVAL; + pr_debug("imc: Failed to get the event reference count\n"); + return -EINVAL; } + mtspr(SPRN_LDBAR, ldbar_value); mutex_lock(&ref->lock); if (ref->refc == 0) { @@ -1242,13 +1351,11 @@ static int trace_imc_event_add(struct perf_event *event, int flags) get_hard_smp_processor_id(smp_processor_id()))) { mutex_unlock(&ref->lock); pr_err("trace-imc: Unable to start the counters for core %d\n", core_id); - mtspr(SPRN_LDBAR, 0); return -EINVAL; } } ++ref->refc; mutex_unlock(&ref->lock); - return 0; } @@ -1274,16 +1381,13 @@ static void trace_imc_event_del(struct perf_event *event, int flags) int core_id = smp_processor_id() / threads_per_core; struct imc_pmu_ref *ref = NULL; - if (core_imc_refc) - ref = &core_imc_refc[core_id]; + if (trace_imc_refc) + ref = &trace_imc_refc[core_id]; if (!ref) { - /* If core-imc is not enabled, use trace-imc reference count */ - if (trace_imc_refc) - ref = &trace_imc_refc[core_id]; - if (!ref) - return; + pr_debug("imc: Failed to get event reference count\n"); + return; } - mtspr(SPRN_LDBAR, 0); + mutex_lock(&ref->lock); ref->refc--; if (ref->refc == 0) { @@ -1297,6 +1401,7 @@ static void trace_imc_event_del(struct perf_event *event, int flags) ref->refc = 0; } mutex_unlock(&ref->lock); + trace_imc_event_stop(event, flags); } @@ -1314,10 +1419,30 @@ static int trace_imc_event_init(struct perf_event *event) if (event->attr.sample_period == 0) return -ENOENT; + /* + * Take the global lock, and make sure + * no other thread is running any core/thread imc + * events + */ + mutex_lock(&imc_global_refc.lock); + if (imc_global_refc.id == 0 || imc_global_refc.id == IMC_DOMAIN_TRACE) { + /* + * No core/thread imc events are running in the + * system, so set the refc.id to trace-imc. + */ + imc_global_refc.id = IMC_DOMAIN_TRACE; + imc_global_refc.refc++; + } else { + mutex_unlock(&imc_global_refc.lock); + return -EBUSY; + } + mutex_unlock(&imc_global_refc.lock); + event->hw.idx = -1; target = event->hw.target; event->pmu->task_ctx_nr = perf_hw_context; + event->destroy = reset_global_refc; return 0; } @@ -1429,10 +1554,10 @@ static void cleanup_all_core_imc_memory(void) static void thread_imc_ldbar_disable(void *dummy) { /* - * By Zeroing LDBAR, we disable thread-imc - * updates. + * By setting 0th bit of LDBAR to zero, we disable thread-imc + * updates to memory. */ - mtspr(SPRN_LDBAR, 0); + mtspr(SPRN_LDBAR, (mfspr(SPRN_LDBAR) & (~(1UL << 63)))); } void thread_imc_disable(void) diff --git a/arch/riscv/include/asm/ftrace.h b/arch/riscv/include/asm/ftrace.h index c6dcc5291f97..02fbc175142e 100644 --- a/arch/riscv/include/asm/ftrace.h +++ b/arch/riscv/include/asm/ftrace.h @@ -63,4 +63,11 @@ do { \ * Let auipc+jalr be the basic *mcount unit*, so we make it 8 bytes here. */ #define MCOUNT_INSN_SIZE 8 + +#ifndef __ASSEMBLY__ +struct dyn_ftrace; +int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec); +#define ftrace_init_nop ftrace_init_nop +#endif + #endif diff --git a/arch/riscv/kernel/ftrace.c b/arch/riscv/kernel/ftrace.c index c40fdcdeb950..291c579e1245 100644 --- a/arch/riscv/kernel/ftrace.c +++ b/arch/riscv/kernel/ftrace.c @@ -88,6 +88,25 @@ int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, return __ftrace_modify_call(rec->ip, addr, false); } + +/* + * This is called early on, and isn't wrapped by + * ftrace_arch_code_modify_{prepare,post_process}() and therefor doesn't hold + * text_mutex, which triggers a lockdep failure. SMP isn't running so we could + * just directly poke the text, but it's simpler to just take the lock + * ourselves. + */ +int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec) +{ + int out; + + ftrace_arch_code_modify_prepare(); + out = ftrace_make_nop(mod, rec, MCOUNT_ADDR); + ftrace_arch_code_modify_post_process(); + + return out; +} + int ftrace_update_ftrace_func(ftrace_func_t func) { int ret = __ftrace_modify_call((unsigned long)&ftrace_call, diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index 34a655ad7123..5ce586948d92 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -1247,26 +1247,46 @@ static inline pgd_t *pgd_offset_raw(pgd_t *pgd, unsigned long address) #define pgd_offset(mm, address) pgd_offset_raw(READ_ONCE((mm)->pgd), address) #define pgd_offset_k(address) pgd_offset(&init_mm, address) -static inline p4d_t *p4d_offset(pgd_t *pgd, unsigned long address) +static inline p4d_t *p4d_offset_lockless(pgd_t *pgdp, pgd_t pgd, unsigned long address) { - if ((pgd_val(*pgd) & _REGION_ENTRY_TYPE_MASK) >= _REGION_ENTRY_TYPE_R1) - return (p4d_t *) pgd_deref(*pgd) + p4d_index(address); - return (p4d_t *) pgd; + if ((pgd_val(pgd) & _REGION_ENTRY_TYPE_MASK) >= _REGION_ENTRY_TYPE_R1) + return (p4d_t *) pgd_deref(pgd) + p4d_index(address); + return (p4d_t *) pgdp; } +#define p4d_offset_lockless p4d_offset_lockless -static inline pud_t *pud_offset(p4d_t *p4d, unsigned long address) +static inline p4d_t *p4d_offset(pgd_t *pgdp, unsigned long address) { - if ((p4d_val(*p4d) & _REGION_ENTRY_TYPE_MASK) >= _REGION_ENTRY_TYPE_R2) - return (pud_t *) p4d_deref(*p4d) + pud_index(address); - return (pud_t *) p4d; + return p4d_offset_lockless(pgdp, *pgdp, address); } -static inline pmd_t *pmd_offset(pud_t *pud, unsigned long address) +static inline pud_t *pud_offset_lockless(p4d_t *p4dp, p4d_t p4d, unsigned long address) { - if ((pud_val(*pud) & _REGION_ENTRY_TYPE_MASK) >= _REGION_ENTRY_TYPE_R3) - return (pmd_t *) pud_deref(*pud) + pmd_index(address); - return (pmd_t *) pud; + if ((p4d_val(p4d) & _REGION_ENTRY_TYPE_MASK) >= _REGION_ENTRY_TYPE_R2) + return (pud_t *) p4d_deref(p4d) + pud_index(address); + return (pud_t *) p4dp; } +#define pud_offset_lockless pud_offset_lockless + +static inline pud_t *pud_offset(p4d_t *p4dp, unsigned long address) +{ + return pud_offset_lockless(p4dp, *p4dp, address); +} +#define pud_offset pud_offset + +static inline pmd_t *pmd_offset_lockless(pud_t *pudp, pud_t pud, unsigned long address) +{ + if ((pud_val(pud) & _REGION_ENTRY_TYPE_MASK) >= _REGION_ENTRY_TYPE_R3) + return (pmd_t *) pud_deref(pud) + pmd_index(address); + return (pmd_t *) pudp; +} +#define pmd_offset_lockless pmd_offset_lockless + +static inline pmd_t *pmd_offset(pud_t *pudp, unsigned long address) +{ + return pmd_offset_lockless(pudp, *pudp, address); +} +#define pmd_offset pmd_offset static inline pte_t *pte_offset(pmd_t *pmd, unsigned long address) { diff --git a/arch/s390/include/asm/stacktrace.h b/arch/s390/include/asm/stacktrace.h index 0ae4bbf7779c..3679d224fd3c 100644 --- a/arch/s390/include/asm/stacktrace.h +++ b/arch/s390/include/asm/stacktrace.h @@ -111,4 +111,15 @@ struct stack_frame { r2; \ }) +#define CALL_ON_STACK_NORETURN(fn, stack) \ +({ \ + asm volatile( \ + " la 15,0(%[_stack])\n" \ + " xc %[_bc](8,15),%[_bc](15)\n" \ + " brasl 14,%[_fn]\n" \ + ::[_bc] "i" (offsetof(struct stack_frame, back_chain)), \ + [_stack] "a" (stack), [_fn] "X" (fn)); \ + BUG(); \ +}) + #endif /* _ASM_S390_STACKTRACE_H */ diff --git a/arch/s390/kernel/irq.c b/arch/s390/kernel/irq.c index 8371855042dc..da550cb8b31b 100644 --- a/arch/s390/kernel/irq.c +++ b/arch/s390/kernel/irq.c @@ -294,11 +294,6 @@ static irqreturn_t do_ext_interrupt(int irq, void *dummy) return IRQ_HANDLED; } -static struct irqaction external_interrupt = { - .name = "EXT", - .handler = do_ext_interrupt, -}; - void __init init_ext_interrupts(void) { int idx; @@ -308,7 +303,8 @@ void __init init_ext_interrupts(void) irq_set_chip_and_handler(EXT_INTERRUPT, &dummy_irq_chip, handle_percpu_irq); - setup_irq(EXT_INTERRUPT, &external_interrupt); + if (request_irq(EXT_INTERRUPT, do_ext_interrupt, 0, "EXT", NULL)) + panic("Failed to register EXT interrupt\n"); } static DEFINE_SPINLOCK(irq_subclass_lock); diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c index 229e1e2f8253..996e447ead3a 100644 --- a/arch/s390/kernel/perf_cpum_sf.c +++ b/arch/s390/kernel/perf_cpum_sf.c @@ -1429,8 +1429,8 @@ static int aux_output_begin(struct perf_output_handle *handle, idx = aux->empty_mark + 1; for (i = 0; i < range_scan; i++, idx++) { te = aux_sdb_trailer(aux, idx); - te->flags = te->flags & ~SDB_TE_BUFFER_FULL_MASK; - te->flags = te->flags & ~SDB_TE_ALERT_REQ_MASK; + te->flags &= ~(SDB_TE_BUFFER_FULL_MASK | + SDB_TE_ALERT_REQ_MASK); te->overflow = 0; } /* Save the position of empty SDBs */ @@ -1477,8 +1477,7 @@ static bool aux_set_alert(struct aux_buffer *aux, unsigned long alert_index, te = aux_sdb_trailer(aux, alert_index); do { orig_flags = te->flags; - orig_overflow = te->overflow; - *overflow = orig_overflow; + *overflow = orig_overflow = te->overflow; if (orig_flags & SDB_TE_BUFFER_FULL_MASK) { /* * SDB is already set by hardware. @@ -1712,7 +1711,7 @@ static void *aux_buffer_setup(struct perf_event *event, void **pages, } /* Allocate aux_buffer struct for the event */ - aux = kmalloc(sizeof(struct aux_buffer), GFP_KERNEL); + aux = kzalloc(sizeof(struct aux_buffer), GFP_KERNEL); if (!aux) goto no_aux; sfb = &aux->sfb; diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index 07b2b61a0289..61c02a162d37 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -356,7 +356,6 @@ early_initcall(async_stack_realloc); void __init arch_call_rest_init(void) { - struct stack_frame *frame; unsigned long stack; stack = stack_alloc(); @@ -369,13 +368,7 @@ void __init arch_call_rest_init(void) set_task_stack_end_magic(current); stack += STACK_INIT_OFFSET; S390_lowcore.kernel_stack = stack; - frame = (struct stack_frame *) stack; - memset(frame, 0, sizeof(*frame)); - /* Branch to rest_init on the new stack, never returns */ - asm volatile( - " la 15,0(%[_frame])\n" - " jg rest_init\n" - : : [_frame] "a" (frame)); + CALL_ON_STACK_NORETURN(rest_init, stack); } static void __init setup_lowcore_dat_off(void) @@ -634,7 +627,7 @@ static struct notifier_block kdump_mem_nb = { /* * Make sure that the area behind memory_end is protected */ -static void reserve_memory_end(void) +static void __init reserve_memory_end(void) { if (memory_end_set) memblock_reserve(memory_end, ULONG_MAX); @@ -643,7 +636,7 @@ static void reserve_memory_end(void) /* * Make sure that oldmem, where the dump is stored, is protected */ -static void reserve_oldmem(void) +static void __init reserve_oldmem(void) { #ifdef CONFIG_CRASH_DUMP if (OLDMEM_BASE) @@ -655,7 +648,7 @@ static void reserve_oldmem(void) /* * Make sure that oldmem, where the dump is stored, is protected */ -static void remove_oldmem(void) +static void __init remove_oldmem(void) { #ifdef CONFIG_CRASH_DUMP if (OLDMEM_BASE) diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c index 66bf050d785c..ad426cc656e5 100644 --- a/arch/s390/kernel/smp.c +++ b/arch/s390/kernel/smp.c @@ -878,7 +878,7 @@ static void __no_sanitize_address smp_start_secondary(void *cpuvoid) S390_lowcore.restart_source = -1UL; __ctl_load(S390_lowcore.cregs_save_area, 0, 15); __load_psw_mask(PSW_KERNEL_BITS | PSW_MASK_DAT); - CALL_ON_STACK(smp_init_secondary, S390_lowcore.kernel_stack, 0); + CALL_ON_STACK_NORETURN(smp_init_secondary, S390_lowcore.kernel_stack); } /* Upping and downing of CPUs */ diff --git a/arch/x86/include/asm/crash.h b/arch/x86/include/asm/crash.h index ef5638f641f2..88eadd08ad70 100644 --- a/arch/x86/include/asm/crash.h +++ b/arch/x86/include/asm/crash.h @@ -10,4 +10,10 @@ int crash_setup_memmap_entries(struct kimage *image, struct boot_params *params); void crash_smp_send_stop(void); +#ifdef CONFIG_KEXEC_CORE +void __init crash_reserve_low_1M(void); +#else +static inline void __init crash_reserve_low_1M(void) { } +#endif + #endif /* _ASM_X86_CRASH_H */ diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index 5c24a7b35166..b222a3595946 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -320,7 +320,7 @@ DECLARE_STATIC_KEY_FALSE(mds_idle_clear); * combination with microcode which triggers a CPU buffer flush when the * instruction is executed. */ -static inline void mds_clear_cpu_buffers(void) +static __always_inline void mds_clear_cpu_buffers(void) { static const u16 ds = __KERNEL_DS; @@ -341,7 +341,7 @@ static inline void mds_clear_cpu_buffers(void) * * Clear CPU buffers if the corresponding static key is enabled */ -static inline void mds_user_clear_cpu_buffers(void) +static __always_inline void mds_user_clear_cpu_buffers(void) { if (static_branch_likely(&mds_user_clear)) mds_clear_cpu_buffers(); diff --git a/arch/x86/include/asm/pkeys.h b/arch/x86/include/asm/pkeys.h index 19b137f1b3be..2ff9b98812b7 100644 --- a/arch/x86/include/asm/pkeys.h +++ b/arch/x86/include/asm/pkeys.h @@ -4,6 +4,11 @@ #define ARCH_DEFAULT_PKEY 0 +/* + * If more than 16 keys are ever supported, a thorough audit + * will be necessary to ensure that the types that store key + * numbers and masks have sufficient capacity. + */ #define arch_max_pkey() (boot_cpu_has(X86_FEATURE_OSPKE) ? 16 : 1) extern int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index ea6d9da9b094..4b6301946f45 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -2256,6 +2256,7 @@ static inline void __init check_timer(void) legacy_pic->init(0); legacy_pic->make_irq(0); apic_write(APIC_LVT0, APIC_DM_EXTINT); + legacy_pic->unmask(0); unlock_ExtINT_logic(); diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c index eb651fbde92a..ff25a2ea271c 100644 --- a/arch/x86/kernel/crash.c +++ b/arch/x86/kernel/crash.c @@ -24,6 +24,7 @@ #include <linux/export.h> #include <linux/slab.h> #include <linux/vmalloc.h> +#include <linux/memblock.h> #include <asm/processor.h> #include <asm/hardirq.h> @@ -39,6 +40,7 @@ #include <asm/virtext.h> #include <asm/intel_pt.h> #include <asm/crash.h> +#include <asm/cmdline.h> /* Used while preparing memory map entries for second kernel */ struct crash_memmap_data { @@ -68,6 +70,19 @@ static inline void cpu_crash_vmclear_loaded_vmcss(void) rcu_read_unlock(); } +/* + * When the crashkernel option is specified, only use the low + * 1M for the real mode trampoline. + */ +void __init crash_reserve_low_1M(void) +{ + if (cmdline_find_option(boot_command_line, "crashkernel", NULL, 0) < 0) + return; + + memblock_reserve(0, 1<<20); + pr_info("Reserving the low 1M of memory for crashkernel\n"); +} + #if defined(CONFIG_SMP) && defined(CONFIG_X86_LOCAL_APIC) static void kdump_nmi_callback(int cpu, struct pt_regs *regs) diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index 755eb26cbec0..735d1f1bbabc 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -895,8 +895,6 @@ const void *get_xsave_field_ptr(int xfeature_nr) #ifdef CONFIG_ARCH_HAS_PKEYS -#define NR_VALID_PKRU_BITS (CONFIG_NR_PROTECTION_KEYS * 2) -#define PKRU_VALID_MASK (NR_VALID_PKRU_BITS - 1) /* * This will go out and modify PKRU register to set the access * rights for @pkey to @init_val. @@ -915,6 +913,13 @@ int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, if (!boot_cpu_has(X86_FEATURE_OSPKE)) return -EINVAL; + /* + * This code should only be called with valid 'pkey' + * values originating from in-kernel users. Complain + * if a bad value is observed. + */ + WARN_ON_ONCE(pkey >= arch_max_pkey()); + /* Set the bits we need in PKRU: */ if (init_val & PKEY_DISABLE_ACCESS) new_pkru_bits |= PKRU_AD_BIT; diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 128d3ad46e96..cc7823e7ef96 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -5836,6 +5836,8 @@ int x86_emulate_insn(struct x86_emulate_ctxt *ctxt) } ctxt->eip = ctxt->_eip; + if (ctxt->mode != X86EMUL_MODE_PROT64) + ctxt->eip = (u32)ctxt->_eip; done: if (rc == X86EMUL_PROPAGATE_FAULT) { diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 6920f1d3b66f..9f793c9649cd 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -1684,7 +1684,7 @@ static void start_sw_period(struct kvm_lapic *apic) hrtimer_start(&apic->lapic_timer.timer, apic->lapic_timer.target_expiration, - HRTIMER_MODE_ABS); + HRTIMER_MODE_ABS_HARD); } bool kvm_lapic_hv_timer_in_use(struct kvm_vcpu *vcpu) diff --git a/arch/x86/kvm/mmutrace.h b/arch/x86/kvm/mmutrace.h index 3c6522b84ff1..ffcd96fc02d0 100644 --- a/arch/x86/kvm/mmutrace.h +++ b/arch/x86/kvm/mmutrace.h @@ -339,7 +339,7 @@ TRACE_EVENT( /* These depend on page entry type, so compute them now. */ __field(bool, r) __field(bool, x) - __field(u8, u) + __field(signed char, u) ), TP_fast_assign( diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 3243a80ea32c..b58495fde2e8 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -787,9 +787,6 @@ static int skip_emulated_instruction(struct kvm_vcpu *vcpu) if (!kvm_emulate_instruction(vcpu, EMULTYPE_SKIP)) return 0; } else { - if (svm->next_rip - kvm_rip_read(vcpu) > MAX_INST_SIZE) - pr_err("%s: ip 0x%lx next 0x%llx\n", - __func__, kvm_rip_read(vcpu), svm->next_rip); kvm_rip_write(vcpu, svm->next_rip); } svm_set_interrupt_shadow(vcpu, 0); @@ -3970,6 +3967,12 @@ static int iret_interception(struct vcpu_svm *svm) return 1; } +static int invd_interception(struct vcpu_svm *svm) +{ + /* Treat an INVD instruction as a NOP and just skip it. */ + return kvm_skip_emulated_instruction(&svm->vcpu); +} + static int invlpg_interception(struct vcpu_svm *svm) { if (!static_cpu_has(X86_FEATURE_DECODEASSISTS)) @@ -4822,7 +4825,7 @@ static int (*const svm_exit_handlers[])(struct vcpu_svm *svm) = { [SVM_EXIT_RDPMC] = rdpmc_interception, [SVM_EXIT_CPUID] = cpuid_interception, [SVM_EXIT_IRET] = iret_interception, - [SVM_EXIT_INVD] = emulate_on_interception, + [SVM_EXIT_INVD] = invd_interception, [SVM_EXIT_PAUSE] = pause_interception, [SVM_EXIT_HLT] = halt_interception, [SVM_EXIT_INVLPG] = invlpg_interception, diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index a1e62dda5607..2a1ed3aae100 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -1130,6 +1130,10 @@ void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu) vmx->guest_msrs[i].mask); } + + if (vmx->nested.need_vmcs12_to_shadow_sync) + nested_sync_vmcs12_to_shadow(vcpu); + if (vmx->guest_state_loaded) return; @@ -1537,7 +1541,7 @@ static int vmx_rtit_ctl_check(struct kvm_vcpu *vcpu, u64 data) static int skip_emulated_instruction(struct kvm_vcpu *vcpu) { - unsigned long rip; + unsigned long rip, orig_rip; /* * Using VMCS.VM_EXIT_INSTRUCTION_LEN on EPT misconfig depends on @@ -1549,8 +1553,17 @@ static int skip_emulated_instruction(struct kvm_vcpu *vcpu) */ if (!static_cpu_has(X86_FEATURE_HYPERVISOR) || to_vmx(vcpu)->exit_reason != EXIT_REASON_EPT_MISCONFIG) { - rip = kvm_rip_read(vcpu); - rip += vmcs_read32(VM_EXIT_INSTRUCTION_LEN); + orig_rip = kvm_rip_read(vcpu); + rip = orig_rip + vmcs_read32(VM_EXIT_INSTRUCTION_LEN); +#ifdef CONFIG_X86_64 + /* + * We need to mask out the high 32 bits of RIP if not in 64-bit + * mode, but just finding out that we are in 64-bit mode is + * quite expensive. Only do it if there was a carry. + */ + if (unlikely(((rip ^ orig_rip) >> 31) == 3) && !is_64_bit_mode(vcpu)) + rip = (u32)rip; +#endif kvm_rip_write(vcpu, rip); } else { if (!kvm_emulate_instruction(vcpu, EMULTYPE_SKIP)) @@ -6486,8 +6499,11 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu) vmcs_write32(PLE_WINDOW, vmx->ple_window); } - if (vmx->nested.need_vmcs12_to_shadow_sync) - nested_sync_vmcs12_to_shadow(vcpu); + /* + * We did this in prepare_switch_to_guest, because it needs to + * be within srcu_read_lock. + */ + WARN_ON_ONCE(vmx->nested.need_vmcs12_to_shadow_sync); if (test_bit(VCPU_REGS_RSP, (unsigned long *)&vcpu->arch.regs_dirty)) vmcs_writel(GUEST_RSP, vcpu->arch.regs[VCPU_REGS_RSP]); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 8920ee7b2881..12e83297ea02 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -973,6 +973,7 @@ int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) unsigned long old_cr4 = kvm_read_cr4(vcpu); unsigned long pdptr_bits = X86_CR4_PGE | X86_CR4_PSE | X86_CR4_PAE | X86_CR4_SMEP; + unsigned long mmu_role_bits = pdptr_bits | X86_CR4_SMAP | X86_CR4_PKE; if (kvm_valid_cr4(vcpu, cr4)) return 1; @@ -1000,7 +1001,7 @@ int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) if (kvm_x86_ops->set_cr4(vcpu, cr4)) return 1; - if (((cr4 ^ old_cr4) & pdptr_bits) || + if (((cr4 ^ old_cr4) & mmu_role_bits) || (!(cr4 & X86_CR4_PCIDE) && (old_cr4 & X86_CR4_PCIDE))) kvm_mmu_reset_context(vcpu); @@ -5050,10 +5051,13 @@ long kvm_arch_vm_ioctl(struct file *filp, r = -EFAULT; if (copy_from_user(&u.ps, argp, sizeof(u.ps))) goto out; + mutex_lock(&kvm->lock); r = -ENXIO; if (!kvm->arch.vpit) - goto out; + goto set_pit_out; r = kvm_vm_ioctl_set_pit(kvm, &u.ps); +set_pit_out: + mutex_unlock(&kvm->lock); break; } case KVM_GET_PIT2: { @@ -5073,10 +5077,13 @@ long kvm_arch_vm_ioctl(struct file *filp, r = -EFAULT; if (copy_from_user(&u.ps2, argp, sizeof(u.ps2))) goto out; + mutex_lock(&kvm->lock); r = -ENXIO; if (!kvm->arch.vpit) - goto out; + goto set_pit2_out; r = kvm_vm_ioctl_set_pit2(kvm, &u.ps2); +set_pit2_out: + mutex_unlock(&kvm->lock); break; } case KVM_REINJECT_CONTROL: { diff --git a/arch/x86/lib/usercopy_64.c b/arch/x86/lib/usercopy_64.c index b0dfac3d3df7..1847e993ac63 100644 --- a/arch/x86/lib/usercopy_64.c +++ b/arch/x86/lib/usercopy_64.c @@ -120,7 +120,7 @@ long __copy_user_flushcache(void *dst, const void __user *src, unsigned size) */ if (size < 8) { if (!IS_ALIGNED(dest, 4) || size != 4) - clean_cache_range(dst, 1); + clean_cache_range(dst, size); } else { if (!IS_ALIGNED(dest, 8)) { dest = ALIGN(dest, boot_cpu_data.x86_clflush_size); diff --git a/arch/x86/realmode/init.c b/arch/x86/realmode/init.c index 7dce39c8c034..262f83cad355 100644 --- a/arch/x86/realmode/init.c +++ b/arch/x86/realmode/init.c @@ -8,6 +8,7 @@ #include <asm/pgtable.h> #include <asm/realmode.h> #include <asm/tlbflush.h> +#include <asm/crash.h> struct real_mode_header *real_mode_header; u32 *trampoline_cr4_features; @@ -34,6 +35,7 @@ void __init reserve_real_mode(void) memblock_reserve(mem, size); set_real_mode_mem(mem); + crash_reserve_low_1M(); } static void __init setup_real_mode(void) diff --git a/arch/xtensa/kernel/entry.S b/arch/xtensa/kernel/entry.S index 59671603c9c6..1f07876ea2ed 100644 --- a/arch/xtensa/kernel/entry.S +++ b/arch/xtensa/kernel/entry.S @@ -1897,6 +1897,7 @@ ENTRY(system_call) mov a6, a2 call4 do_syscall_trace_enter + beqz a6, .Lsyscall_exit l32i a7, a2, PT_SYSCALL 1: @@ -1911,8 +1912,6 @@ ENTRY(system_call) addx4 a4, a7, a4 l32i a4, a4, 0 - movi a5, sys_ni_syscall; - beq a4, a5, 1f /* Load args: arg0 - arg5 are passed via regs. */ @@ -1932,6 +1931,7 @@ ENTRY(system_call) s32i a6, a2, PT_AREG2 bnez a3, 1f +.Lsyscall_exit: abi_ret(4) 1: diff --git a/arch/xtensa/kernel/ptrace.c b/arch/xtensa/kernel/ptrace.c index b964f0b2d886..145742d70a9f 100644 --- a/arch/xtensa/kernel/ptrace.c +++ b/arch/xtensa/kernel/ptrace.c @@ -542,14 +542,28 @@ long arch_ptrace(struct task_struct *child, long request, return ret; } -void do_syscall_trace_enter(struct pt_regs *regs) +void do_syscall_trace_leave(struct pt_regs *regs); +int do_syscall_trace_enter(struct pt_regs *regs) { + if (regs->syscall == NO_SYSCALL) + regs->areg[2] = -ENOSYS; + if (test_thread_flag(TIF_SYSCALL_TRACE) && - tracehook_report_syscall_entry(regs)) + tracehook_report_syscall_entry(regs)) { + regs->areg[2] = -ENOSYS; regs->syscall = NO_SYSCALL; + return 0; + } + + if (regs->syscall == NO_SYSCALL) { + do_syscall_trace_leave(regs); + return 0; + } if (test_thread_flag(TIF_SYSCALL_TRACEPOINT)) trace_sys_enter(regs, syscall_get_nr(current, regs)); + + return 1; } void do_syscall_trace_leave(struct pt_regs *regs) diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c index 57eacdcbf820..1ec55345252b 100644 --- a/drivers/acpi/ec.c +++ b/drivers/acpi/ec.c @@ -1043,29 +1043,21 @@ void acpi_ec_unblock_transactions(void) /* -------------------------------------------------------------------------- Event Management -------------------------------------------------------------------------- */ -static struct acpi_ec_query_handler * -acpi_ec_get_query_handler(struct acpi_ec_query_handler *handler) -{ - if (handler) - kref_get(&handler->kref); - return handler; -} - static struct acpi_ec_query_handler * acpi_ec_get_query_handler_by_value(struct acpi_ec *ec, u8 value) { struct acpi_ec_query_handler *handler; - bool found = false; mutex_lock(&ec->mutex); list_for_each_entry(handler, &ec->list, node) { if (value == handler->query_bit) { - found = true; - break; + kref_get(&handler->kref); + mutex_unlock(&ec->mutex); + return handler; } } mutex_unlock(&ec->mutex); - return found ? acpi_ec_get_query_handler(handler) : NULL; + return NULL; } static void acpi_ec_query_handler_release(struct kref *kref) diff --git a/drivers/ata/acard-ahci.c b/drivers/ata/acard-ahci.c index 753985c01517..46dc54d18f0b 100644 --- a/drivers/ata/acard-ahci.c +++ b/drivers/ata/acard-ahci.c @@ -56,7 +56,7 @@ struct acard_sg { __le32 size; /* bit 31 (EOT) max==0x10000 (64k) */ }; -static void acard_ahci_qc_prep(struct ata_queued_cmd *qc); +static enum ata_completion_errors acard_ahci_qc_prep(struct ata_queued_cmd *qc); static bool acard_ahci_qc_fill_rtf(struct ata_queued_cmd *qc); static int acard_ahci_port_start(struct ata_port *ap); static int acard_ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent); @@ -210,7 +210,7 @@ static unsigned int acard_ahci_fill_sg(struct ata_queued_cmd *qc, void *cmd_tbl) return si; } -static void acard_ahci_qc_prep(struct ata_queued_cmd *qc) +static enum ata_completion_errors acard_ahci_qc_prep(struct ata_queued_cmd *qc) { struct ata_port *ap = qc->ap; struct ahci_port_priv *pp = ap->private_data; @@ -248,6 +248,8 @@ static void acard_ahci_qc_prep(struct ata_queued_cmd *qc) opts |= AHCI_CMD_ATAPI | AHCI_CMD_PREFETCH; ahci_fill_cmd_slot(pp, qc->hw_tag, opts); + + return AC_ERR_OK; } static bool acard_ahci_qc_fill_rtf(struct ata_queued_cmd *qc) diff --git a/drivers/ata/libahci.c b/drivers/ata/libahci.c index bff369d9a1a7..ea5bf5f4cbed 100644 --- a/drivers/ata/libahci.c +++ b/drivers/ata/libahci.c @@ -57,7 +57,7 @@ static int ahci_scr_write(struct ata_link *link, unsigned int sc_reg, u32 val); static bool ahci_qc_fill_rtf(struct ata_queued_cmd *qc); static int ahci_port_start(struct ata_port *ap); static void ahci_port_stop(struct ata_port *ap); -static void ahci_qc_prep(struct ata_queued_cmd *qc); +static enum ata_completion_errors ahci_qc_prep(struct ata_queued_cmd *qc); static int ahci_pmp_qc_defer(struct ata_queued_cmd *qc); static void ahci_freeze(struct ata_port *ap); static void ahci_thaw(struct ata_port *ap); @@ -1624,7 +1624,7 @@ static int ahci_pmp_qc_defer(struct ata_queued_cmd *qc) return sata_pmp_qc_defer_cmd_switch(qc); } -static void ahci_qc_prep(struct ata_queued_cmd *qc) +static enum ata_completion_errors ahci_qc_prep(struct ata_queued_cmd *qc) { struct ata_port *ap = qc->ap; struct ahci_port_priv *pp = ap->private_data; @@ -1660,6 +1660,8 @@ static void ahci_qc_prep(struct ata_queued_cmd *qc) opts |= AHCI_CMD_ATAPI | AHCI_CMD_PREFETCH; ahci_fill_cmd_slot(pp, qc->hw_tag, opts); + + return AC_ERR_OK; } static void ahci_fbs_dec_intr(struct ata_port *ap) diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index 066b37963ad5..f67b3fb33d57 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -4978,7 +4978,10 @@ int ata_std_qc_defer(struct ata_queued_cmd *qc) return ATA_DEFER_LINK; } -void ata_noop_qc_prep(struct ata_queued_cmd *qc) { } +enum ata_completion_errors ata_noop_qc_prep(struct ata_queued_cmd *qc) +{ + return AC_ERR_OK; +} /** * ata_sg_init - Associate command with scatter-gather table. @@ -5465,7 +5468,9 @@ void ata_qc_issue(struct ata_queued_cmd *qc) return; } - ap->ops->qc_prep(qc); + qc->err_mask |= ap->ops->qc_prep(qc); + if (unlikely(qc->err_mask)) + goto err; trace_ata_qc_issue(qc); qc->err_mask |= ap->ops->qc_issue(qc); if (unlikely(qc->err_mask)) diff --git a/drivers/ata/libata-sff.c b/drivers/ata/libata-sff.c index 4ed682da52ae..038db94216a9 100644 --- a/drivers/ata/libata-sff.c +++ b/drivers/ata/libata-sff.c @@ -2679,12 +2679,14 @@ static void ata_bmdma_fill_sg_dumb(struct ata_queued_cmd *qc) * LOCKING: * spin_lock_irqsave(host lock) */ -void ata_bmdma_qc_prep(struct ata_queued_cmd *qc) +enum ata_completion_errors ata_bmdma_qc_prep(struct ata_queued_cmd *qc) { if (!(qc->flags & ATA_QCFLAG_DMAMAP)) - return; + return AC_ERR_OK; ata_bmdma_fill_sg(qc); + + return AC_ERR_OK; } EXPORT_SYMBOL_GPL(ata_bmdma_qc_prep); @@ -2697,12 +2699,14 @@ EXPORT_SYMBOL_GPL(ata_bmdma_qc_prep); * LOCKING: * spin_lock_irqsave(host lock) */ -void ata_bmdma_dumb_qc_prep(struct ata_queued_cmd *qc) +enum ata_completion_errors ata_bmdma_dumb_qc_prep(struct ata_queued_cmd *qc) { if (!(qc->flags & ATA_QCFLAG_DMAMAP)) - return; + return AC_ERR_OK; ata_bmdma_fill_sg_dumb(qc); + + return AC_ERR_OK; } EXPORT_SYMBOL_GPL(ata_bmdma_dumb_qc_prep); diff --git a/drivers/ata/pata_macio.c b/drivers/ata/pata_macio.c index 57f2ec71cfc3..1bfd0154dad5 100644 --- a/drivers/ata/pata_macio.c +++ b/drivers/ata/pata_macio.c @@ -510,7 +510,7 @@ static int pata_macio_cable_detect(struct ata_port *ap) return ATA_CBL_PATA40; } -static void pata_macio_qc_prep(struct ata_queued_cmd *qc) +static enum ata_completion_errors pata_macio_qc_prep(struct ata_queued_cmd *qc) { unsigned int write = (qc->tf.flags & ATA_TFLAG_WRITE); struct ata_port *ap = qc->ap; @@ -523,7 +523,7 @@ static void pata_macio_qc_prep(struct ata_queued_cmd *qc) __func__, qc, qc->flags, write, qc->dev->devno); if (!(qc->flags & ATA_QCFLAG_DMAMAP)) - return; + return AC_ERR_OK; table = (struct dbdma_cmd *) priv->dma_table_cpu; @@ -568,6 +568,8 @@ static void pata_macio_qc_prep(struct ata_queued_cmd *qc) table->command = cpu_to_le16(DBDMA_STOP); dev_dbgdma(priv->dev, "%s: %d DMA list entries\n", __func__, pi); + + return AC_ERR_OK; } diff --git a/drivers/ata/pata_pxa.c b/drivers/ata/pata_pxa.c index 4afcb8e63e21..41430f79663c 100644 --- a/drivers/ata/pata_pxa.c +++ b/drivers/ata/pata_pxa.c @@ -44,25 +44,27 @@ static void pxa_ata_dma_irq(void *d) /* * Prepare taskfile for submission. */ -static void pxa_qc_prep(struct ata_queued_cmd *qc) +static enum ata_completion_errors pxa_qc_prep(struct ata_queued_cmd *qc) { struct pata_pxa_data *pd = qc->ap->private_data; struct dma_async_tx_descriptor *tx; enum dma_transfer_direction dir; if (!(qc->flags & ATA_QCFLAG_DMAMAP)) - return; + return AC_ERR_OK; dir = (qc->dma_dir == DMA_TO_DEVICE ? DMA_MEM_TO_DEV : DMA_DEV_TO_MEM); tx = dmaengine_prep_slave_sg(pd->dma_chan, qc->sg, qc->n_elem, dir, DMA_PREP_INTERRUPT); if (!tx) { ata_dev_err(qc->dev, "prep_slave_sg() failed\n"); - return; + return AC_ERR_OK; } tx->callback = pxa_ata_dma_irq; tx->callback_param = pd; pd->dma_cookie = dmaengine_submit(tx); + + return AC_ERR_OK; } /* diff --git a/drivers/ata/pdc_adma.c b/drivers/ata/pdc_adma.c index cb490531b62e..5db55e1e2a61 100644 --- a/drivers/ata/pdc_adma.c +++ b/drivers/ata/pdc_adma.c @@ -116,7 +116,7 @@ static int adma_ata_init_one(struct pci_dev *pdev, const struct pci_device_id *ent); static int adma_port_start(struct ata_port *ap); static void adma_port_stop(struct ata_port *ap); -static void adma_qc_prep(struct ata_queued_cmd *qc); +static enum ata_completion_errors adma_qc_prep(struct ata_queued_cmd *qc); static unsigned int adma_qc_issue(struct ata_queued_cmd *qc); static int adma_check_atapi_dma(struct ata_queued_cmd *qc); static void adma_freeze(struct ata_port *ap); @@ -295,7 +295,7 @@ static int adma_fill_sg(struct ata_queued_cmd *qc) return i; } -static void adma_qc_prep(struct ata_queued_cmd *qc) +static enum ata_completion_errors adma_qc_prep(struct ata_queued_cmd *qc) { struct adma_port_priv *pp = qc->ap->private_data; u8 *buf = pp->pkt; @@ -306,7 +306,7 @@ static void adma_qc_prep(struct ata_queued_cmd *qc) adma_enter_reg_mode(qc->ap); if (qc->tf.protocol != ATA_PROT_DMA) - return; + return AC_ERR_OK; buf[i++] = 0; /* Response flags */ buf[i++] = 0; /* reserved */ @@ -371,6 +371,7 @@ static void adma_qc_prep(struct ata_queued_cmd *qc) printk("%s\n", obuf); } #endif + return AC_ERR_OK; } static inline void adma_packet_start(struct ata_queued_cmd *qc) diff --git a/drivers/ata/sata_fsl.c b/drivers/ata/sata_fsl.c index ca6c706e9c25..d55ee244d693 100644 --- a/drivers/ata/sata_fsl.c +++ b/drivers/ata/sata_fsl.c @@ -502,7 +502,7 @@ static unsigned int sata_fsl_fill_sg(struct ata_queued_cmd *qc, void *cmd_desc, return num_prde; } -static void sata_fsl_qc_prep(struct ata_queued_cmd *qc) +static enum ata_completion_errors sata_fsl_qc_prep(struct ata_queued_cmd *qc) { struct ata_port *ap = qc->ap; struct sata_fsl_port_priv *pp = ap->private_data; @@ -548,6 +548,8 @@ static void sata_fsl_qc_prep(struct ata_queued_cmd *qc) VPRINTK("SATA FSL : xx_qc_prep, di = 0x%x, ttl = %d, num_prde = %d\n", desc_info, ttl_dwords, num_prde); + + return AC_ERR_OK; } static unsigned int sata_fsl_qc_issue(struct ata_queued_cmd *qc) diff --git a/drivers/ata/sata_inic162x.c b/drivers/ata/sata_inic162x.c index 7f99e23bff88..a6b76cc12a66 100644 --- a/drivers/ata/sata_inic162x.c +++ b/drivers/ata/sata_inic162x.c @@ -478,7 +478,7 @@ static void inic_fill_sg(struct inic_prd *prd, struct ata_queued_cmd *qc) prd[-1].flags |= PRD_END; } -static void inic_qc_prep(struct ata_queued_cmd *qc) +static enum ata_completion_errors inic_qc_prep(struct ata_queued_cmd *qc) { struct inic_port_priv *pp = qc->ap->private_data; struct inic_pkt *pkt = pp->pkt; @@ -538,6 +538,8 @@ static void inic_qc_prep(struct ata_queued_cmd *qc) inic_fill_sg(prd, qc); pp->cpb_tbl[0] = pp->pkt_dma; + + return AC_ERR_OK; } static unsigned int inic_qc_issue(struct ata_queued_cmd *qc) diff --git a/drivers/ata/sata_mv.c b/drivers/ata/sata_mv.c index bde695a32097..d7228f8e9297 100644 --- a/drivers/ata/sata_mv.c +++ b/drivers/ata/sata_mv.c @@ -592,8 +592,8 @@ static int mv5_scr_write(struct ata_link *link, unsigned int sc_reg_in, u32 val) static int mv_port_start(struct ata_port *ap); static void mv_port_stop(struct ata_port *ap); static int mv_qc_defer(struct ata_queued_cmd *qc); -static void mv_qc_prep(struct ata_queued_cmd *qc); -static void mv_qc_prep_iie(struct ata_queued_cmd *qc); +static enum ata_completion_errors mv_qc_prep(struct ata_queued_cmd *qc); +static enum ata_completion_errors mv_qc_prep_iie(struct ata_queued_cmd *qc); static unsigned int mv_qc_issue(struct ata_queued_cmd *qc); static int mv_hardreset(struct ata_link *link, unsigned int *class, unsigned long deadline); @@ -2031,7 +2031,7 @@ static void mv_rw_multi_errata_sata24(struct ata_queued_cmd *qc) * LOCKING: * Inherited from caller. */ -static void mv_qc_prep(struct ata_queued_cmd *qc) +static enum ata_completion_errors mv_qc_prep(struct ata_queued_cmd *qc) { struct ata_port *ap = qc->ap; struct mv_port_priv *pp = ap->private_data; @@ -2043,15 +2043,15 @@ static void mv_qc_prep(struct ata_queued_cmd *qc) switch (tf->protocol) { case ATA_PROT_DMA: if (tf->command == ATA_CMD_DSM) - return; + return AC_ERR_OK; /* fall-thru */ case ATA_PROT_NCQ: break; /* continue below */ case ATA_PROT_PIO: mv_rw_multi_errata_sata24(qc); - return; + return AC_ERR_OK; default: - return; + return AC_ERR_OK; } /* Fill in command request block @@ -2098,12 +2098,10 @@ static void mv_qc_prep(struct ata_queued_cmd *qc) * non-NCQ mode are: [RW] STREAM DMA and W DMA FUA EXT, none * of which are defined/used by Linux. If we get here, this * driver needs work. - * - * FIXME: modify libata to give qc_prep a return value and - * return error here. */ - BUG_ON(tf->command); - break; + ata_port_err(ap, "%s: unsupported command: %.2x\n", __func__, + tf->command); + return AC_ERR_INVALID; } mv_crqb_pack_cmd(cw++, tf->nsect, ATA_REG_NSECT, 0); mv_crqb_pack_cmd(cw++, tf->hob_lbal, ATA_REG_LBAL, 0); @@ -2116,8 +2114,10 @@ static void mv_qc_prep(struct ata_queued_cmd *qc) mv_crqb_pack_cmd(cw++, tf->command, ATA_REG_CMD, 1); /* last */ if (!(qc->flags & ATA_QCFLAG_DMAMAP)) - return; + return AC_ERR_OK; mv_fill_sg(qc); + + return AC_ERR_OK; } /** @@ -2132,7 +2132,7 @@ static void mv_qc_prep(struct ata_queued_cmd *qc) * LOCKING: * Inherited from caller. */ -static void mv_qc_prep_iie(struct ata_queued_cmd *qc) +static enum ata_completion_errors mv_qc_prep_iie(struct ata_queued_cmd *qc) { struct ata_port *ap = qc->ap; struct mv_port_priv *pp = ap->private_data; @@ -2143,9 +2143,9 @@ static void mv_qc_prep_iie(struct ata_queued_cmd *qc) if ((tf->protocol != ATA_PROT_DMA) && (tf->protocol != ATA_PROT_NCQ)) - return; + return AC_ERR_OK; if (tf->command == ATA_CMD_DSM) - return; /* use bmdma for this */ + return AC_ERR_OK; /* use bmdma for this */ /* Fill in Gen IIE command request block */ if (!(tf->flags & ATA_TFLAG_WRITE)) @@ -2186,8 +2186,10 @@ static void mv_qc_prep_iie(struct ata_queued_cmd *qc) ); if (!(qc->flags & ATA_QCFLAG_DMAMAP)) - return; + return AC_ERR_OK; mv_fill_sg(qc); + + return AC_ERR_OK; } /** diff --git a/drivers/ata/sata_nv.c b/drivers/ata/sata_nv.c index 7510303111fa..18b147c182b9 100644 --- a/drivers/ata/sata_nv.c +++ b/drivers/ata/sata_nv.c @@ -297,7 +297,7 @@ static void nv_ck804_freeze(struct ata_port *ap); static void nv_ck804_thaw(struct ata_port *ap); static int nv_adma_slave_config(struct scsi_device *sdev); static int nv_adma_check_atapi_dma(struct ata_queued_cmd *qc); -static void nv_adma_qc_prep(struct ata_queued_cmd *qc); +static enum ata_completion_errors nv_adma_qc_prep(struct ata_queued_cmd *qc); static unsigned int nv_adma_qc_issue(struct ata_queued_cmd *qc); static irqreturn_t nv_adma_interrupt(int irq, void *dev_instance); static void nv_adma_irq_clear(struct ata_port *ap); @@ -319,7 +319,7 @@ static void nv_mcp55_freeze(struct ata_port *ap); static void nv_swncq_error_handler(struct ata_port *ap); static int nv_swncq_slave_config(struct scsi_device *sdev); static int nv_swncq_port_start(struct ata_port *ap); -static void nv_swncq_qc_prep(struct ata_queued_cmd *qc); +static enum ata_completion_errors nv_swncq_qc_prep(struct ata_queued_cmd *qc); static void nv_swncq_fill_sg(struct ata_queued_cmd *qc); static unsigned int nv_swncq_qc_issue(struct ata_queued_cmd *qc); static void nv_swncq_irq_clear(struct ata_port *ap, u16 fis); @@ -1344,7 +1344,7 @@ static int nv_adma_use_reg_mode(struct ata_queued_cmd *qc) return 1; } -static void nv_adma_qc_prep(struct ata_queued_cmd *qc) +static enum ata_completion_errors nv_adma_qc_prep(struct ata_queued_cmd *qc) { struct nv_adma_port_priv *pp = qc->ap->private_data; struct nv_adma_cpb *cpb = &pp->cpb[qc->hw_tag]; @@ -1356,7 +1356,7 @@ static void nv_adma_qc_prep(struct ata_queued_cmd *qc) (qc->flags & ATA_QCFLAG_DMAMAP)); nv_adma_register_mode(qc->ap); ata_bmdma_qc_prep(qc); - return; + return AC_ERR_OK; } cpb->resp_flags = NV_CPB_RESP_DONE; @@ -1388,6 +1388,8 @@ static void nv_adma_qc_prep(struct ata_queued_cmd *qc) cpb->ctl_flags = ctl_flags; wmb(); cpb->resp_flags = 0; + + return AC_ERR_OK; } static unsigned int nv_adma_qc_issue(struct ata_queued_cmd *qc) @@ -1950,17 +1952,19 @@ static int nv_swncq_port_start(struct ata_port *ap) return 0; } -static void nv_swncq_qc_prep(struct ata_queued_cmd *qc) +static enum ata_completion_errors nv_swncq_qc_prep(struct ata_queued_cmd *qc) { if (qc->tf.protocol != ATA_PROT_NCQ) { ata_bmdma_qc_prep(qc); - return; + return AC_ERR_OK; } if (!(qc->flags & ATA_QCFLAG_DMAMAP)) - return; + return AC_ERR_OK; nv_swncq_fill_sg(qc); + + return AC_ERR_OK; } static void nv_swncq_fill_sg(struct ata_queued_cmd *qc) diff --git a/drivers/ata/sata_promise.c b/drivers/ata/sata_promise.c index 5fd464765ddc..c451d7d1c817 100644 --- a/drivers/ata/sata_promise.c +++ b/drivers/ata/sata_promise.c @@ -139,7 +139,7 @@ static int pdc_sata_scr_write(struct ata_link *link, unsigned int sc_reg, u32 va static int pdc_ata_init_one(struct pci_dev *pdev, const struct pci_device_id *ent); static int pdc_common_port_start(struct ata_port *ap); static int pdc_sata_port_start(struct ata_port *ap); -static void pdc_qc_prep(struct ata_queued_cmd *qc); +static enum ata_completion_errors pdc_qc_prep(struct ata_queued_cmd *qc); static void pdc_tf_load_mmio(struct ata_port *ap, const struct ata_taskfile *tf); static void pdc_exec_command_mmio(struct ata_port *ap, const struct ata_taskfile *tf); static int pdc_check_atapi_dma(struct ata_queued_cmd *qc); @@ -633,7 +633,7 @@ static void pdc_fill_sg(struct ata_queued_cmd *qc) prd[idx - 1].flags_len |= cpu_to_le32(ATA_PRD_EOT); } -static void pdc_qc_prep(struct ata_queued_cmd *qc) +static enum ata_completion_errors pdc_qc_prep(struct ata_queued_cmd *qc) { struct pdc_port_priv *pp = qc->ap->private_data; unsigned int i; @@ -665,6 +665,8 @@ static void pdc_qc_prep(struct ata_queued_cmd *qc) default: break; } + + return AC_ERR_OK; } static int pdc_is_sataii_tx4(unsigned long flags) diff --git a/drivers/ata/sata_qstor.c b/drivers/ata/sata_qstor.c index c53c5a47204d..ef00ab644afb 100644 --- a/drivers/ata/sata_qstor.c +++ b/drivers/ata/sata_qstor.c @@ -100,7 +100,7 @@ static int qs_scr_write(struct ata_link *link, unsigned int sc_reg, u32 val); static int qs_ata_init_one(struct pci_dev *pdev, const struct pci_device_id *ent); static int qs_port_start(struct ata_port *ap); static void qs_host_stop(struct ata_host *host); -static void qs_qc_prep(struct ata_queued_cmd *qc); +static enum ata_completion_errors qs_qc_prep(struct ata_queued_cmd *qc); static unsigned int qs_qc_issue(struct ata_queued_cmd *qc); static int qs_check_atapi_dma(struct ata_queued_cmd *qc); static void qs_freeze(struct ata_port *ap); @@ -260,7 +260,7 @@ static unsigned int qs_fill_sg(struct ata_queued_cmd *qc) return si; } -static void qs_qc_prep(struct ata_queued_cmd *qc) +static enum ata_completion_errors qs_qc_prep(struct ata_queued_cmd *qc) { struct qs_port_priv *pp = qc->ap->private_data; u8 dflags = QS_DF_PORD, *buf = pp->pkt; @@ -272,7 +272,7 @@ static void qs_qc_prep(struct ata_queued_cmd *qc) qs_enter_reg_mode(qc->ap); if (qc->tf.protocol != ATA_PROT_DMA) - return; + return AC_ERR_OK; nelem = qs_fill_sg(qc); @@ -295,6 +295,8 @@ static void qs_qc_prep(struct ata_queued_cmd *qc) /* frame information structure (FIS) */ ata_tf_to_fis(&qc->tf, 0, 1, &buf[32]); + + return AC_ERR_OK; } static inline void qs_packet_start(struct ata_queued_cmd *qc) diff --git a/drivers/ata/sata_rcar.c b/drivers/ata/sata_rcar.c index c35b7b993133..141ac600b64c 100644 --- a/drivers/ata/sata_rcar.c +++ b/drivers/ata/sata_rcar.c @@ -550,12 +550,14 @@ static void sata_rcar_bmdma_fill_sg(struct ata_queued_cmd *qc) prd[si - 1].addr |= cpu_to_le32(SATA_RCAR_DTEND); } -static void sata_rcar_qc_prep(struct ata_queued_cmd *qc) +static enum ata_completion_errors sata_rcar_qc_prep(struct ata_queued_cmd *qc) { if (!(qc->flags & ATA_QCFLAG_DMAMAP)) - return; + return AC_ERR_OK; sata_rcar_bmdma_fill_sg(qc); + + return AC_ERR_OK; } static void sata_rcar_bmdma_setup(struct ata_queued_cmd *qc) diff --git a/drivers/ata/sata_sil.c b/drivers/ata/sata_sil.c index e6fbae2f645a..75321f1ceba5 100644 --- a/drivers/ata/sata_sil.c +++ b/drivers/ata/sata_sil.c @@ -103,7 +103,7 @@ static void sil_dev_config(struct ata_device *dev); static int sil_scr_read(struct ata_link *link, unsigned int sc_reg, u32 *val); static int sil_scr_write(struct ata_link *link, unsigned int sc_reg, u32 val); static int sil_set_mode(struct ata_link *link, struct ata_device **r_failed); -static void sil_qc_prep(struct ata_queued_cmd *qc); +static enum ata_completion_errors sil_qc_prep(struct ata_queued_cmd *qc); static void sil_bmdma_setup(struct ata_queued_cmd *qc); static void sil_bmdma_start(struct ata_queued_cmd *qc); static void sil_bmdma_stop(struct ata_queued_cmd *qc); @@ -317,12 +317,14 @@ static void sil_fill_sg(struct ata_queued_cmd *qc) last_prd->flags_len |= cpu_to_le32(ATA_PRD_EOT); } -static void sil_qc_prep(struct ata_queued_cmd *qc) +static enum ata_completion_errors sil_qc_prep(struct ata_queued_cmd *qc) { if (!(qc->flags & ATA_QCFLAG_DMAMAP)) - return; + return AC_ERR_OK; sil_fill_sg(qc); + + return AC_ERR_OK; } static unsigned char sil_get_device_cache_line(struct pci_dev *pdev) diff --git a/drivers/ata/sata_sil24.c b/drivers/ata/sata_sil24.c index 7bef82de53ca..560070d4f1d0 100644 --- a/drivers/ata/sata_sil24.c +++ b/drivers/ata/sata_sil24.c @@ -326,7 +326,7 @@ static void sil24_dev_config(struct ata_device *dev); static int sil24_scr_read(struct ata_link *link, unsigned sc_reg, u32 *val); static int sil24_scr_write(struct ata_link *link, unsigned sc_reg, u32 val); static int sil24_qc_defer(struct ata_queued_cmd *qc); -static void sil24_qc_prep(struct ata_queued_cmd *qc); +static enum ata_completion_errors sil24_qc_prep(struct ata_queued_cmd *qc); static unsigned int sil24_qc_issue(struct ata_queued_cmd *qc); static bool sil24_qc_fill_rtf(struct ata_queued_cmd *qc); static void sil24_pmp_attach(struct ata_port *ap); @@ -830,7 +830,7 @@ static int sil24_qc_defer(struct ata_queued_cmd *qc) return ata_std_qc_defer(qc); } -static void sil24_qc_prep(struct ata_queued_cmd *qc) +static enum ata_completion_errors sil24_qc_prep(struct ata_queued_cmd *qc) { struct ata_port *ap = qc->ap; struct sil24_port_priv *pp = ap->private_data; @@ -874,6 +874,8 @@ static void sil24_qc_prep(struct ata_queued_cmd *qc) if (qc->flags & ATA_QCFLAG_DMAMAP) sil24_fill_sg(qc, sge); + + return AC_ERR_OK; } static unsigned int sil24_qc_issue(struct ata_queued_cmd *qc) diff --git a/drivers/ata/sata_sx4.c b/drivers/ata/sata_sx4.c index 2277ba0c9c7f..2c7b30c5ea3d 100644 --- a/drivers/ata/sata_sx4.c +++ b/drivers/ata/sata_sx4.c @@ -202,7 +202,7 @@ static void pdc_error_handler(struct ata_port *ap); static void pdc_freeze(struct ata_port *ap); static void pdc_thaw(struct ata_port *ap); static int pdc_port_start(struct ata_port *ap); -static void pdc20621_qc_prep(struct ata_queued_cmd *qc); +static enum ata_completion_errors pdc20621_qc_prep(struct ata_queued_cmd *qc); static void pdc_tf_load_mmio(struct ata_port *ap, const struct ata_taskfile *tf); static void pdc_exec_command_mmio(struct ata_port *ap, const struct ata_taskfile *tf); static unsigned int pdc20621_dimm_init(struct ata_host *host); @@ -530,7 +530,7 @@ static void pdc20621_nodata_prep(struct ata_queued_cmd *qc) VPRINTK("ata pkt buf ofs %u, mmio copied\n", i); } -static void pdc20621_qc_prep(struct ata_queued_cmd *qc) +static enum ata_completion_errors pdc20621_qc_prep(struct ata_queued_cmd *qc) { switch (qc->tf.protocol) { case ATA_PROT_DMA: @@ -542,6 +542,8 @@ static void pdc20621_qc_prep(struct ata_queued_cmd *qc) default: break; } + + return AC_ERR_OK; } static void __pdc20621_push_hdma(struct ata_queued_cmd *qc, diff --git a/drivers/atm/eni.c b/drivers/atm/eni.c index 9d0d65efcd94..bedaebd5a495 100644 --- a/drivers/atm/eni.c +++ b/drivers/atm/eni.c @@ -2245,7 +2245,7 @@ static int eni_init_one(struct pci_dev *pci_dev, rc = dma_set_mask_and_coherent(&pci_dev->dev, DMA_BIT_MASK(32)); if (rc < 0) - goto out; + goto err_disable; rc = -ENOMEM; eni_dev = kmalloc(sizeof(struct eni_dev), GFP_KERNEL); diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c index 1eb81f113786..83e26fd188cc 100644 --- a/drivers/base/arch_topology.c +++ b/drivers/base/arch_topology.c @@ -270,7 +270,7 @@ static int __init get_cpu_for_node(struct device_node *node) static int __init parse_core(struct device_node *core, int package_id, int core_id) { - char name[10]; + char name[20]; bool leaf = true; int i = 0; int cpu; @@ -317,7 +317,7 @@ static int __init parse_core(struct device_node *core, int package_id, static int __init parse_cluster(struct device_node *cluster, int depth) { - char name[10]; + char name[20]; bool leaf = true; bool has_cores = false; struct device_node *c; diff --git a/drivers/base/regmap/internal.h b/drivers/base/regmap/internal.h index 3d80c4b43f72..d7c01b70e43d 100644 --- a/drivers/base/regmap/internal.h +++ b/drivers/base/regmap/internal.h @@ -259,7 +259,7 @@ bool regcache_set_val(struct regmap *map, void *base, unsigned int idx, int regcache_lookup_reg(struct regmap *map, unsigned int reg); int _regmap_raw_write(struct regmap *map, unsigned int reg, - const void *val, size_t val_len); + const void *val, size_t val_len, bool noinc); void regmap_async_complete_cb(struct regmap_async *async, int ret); diff --git a/drivers/base/regmap/regcache.c b/drivers/base/regmap/regcache.c index a93cafd7be4f..7f4b3b62492c 100644 --- a/drivers/base/regmap/regcache.c +++ b/drivers/base/regmap/regcache.c @@ -717,7 +717,7 @@ static int regcache_sync_block_raw_flush(struct regmap *map, const void **data, map->cache_bypass = true; - ret = _regmap_raw_write(map, base, *data, count * val_bytes); + ret = _regmap_raw_write(map, base, *data, count * val_bytes, false); if (ret) dev_err(map->dev, "Unable to sync registers %#x-%#x. %d\n", base, cur - map->reg_stride, ret); diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c index 927ebde1607b..e0893f1b1452 100644 --- a/drivers/base/regmap/regmap.c +++ b/drivers/base/regmap/regmap.c @@ -1468,7 +1468,7 @@ static void regmap_set_work_buf_flag_mask(struct regmap *map, int max_bytes, } static int _regmap_raw_write_impl(struct regmap *map, unsigned int reg, - const void *val, size_t val_len) + const void *val, size_t val_len, bool noinc) { struct regmap_range_node *range; unsigned long flags; @@ -1527,7 +1527,7 @@ static int _regmap_raw_write_impl(struct regmap *map, unsigned int reg, win_residue, val_len / map->format.val_bytes); ret = _regmap_raw_write_impl(map, reg, val, win_residue * - map->format.val_bytes); + map->format.val_bytes, noinc); if (ret != 0) return ret; @@ -1541,7 +1541,7 @@ static int _regmap_raw_write_impl(struct regmap *map, unsigned int reg, win_residue = range->window_len - win_offset; } - ret = _regmap_select_page(map, ®, range, val_num); + ret = _regmap_select_page(map, ®, range, noinc ? 1 : val_num); if (ret != 0) return ret; } @@ -1749,7 +1749,8 @@ static int _regmap_bus_raw_write(void *context, unsigned int reg, map->work_buf + map->format.reg_bytes + map->format.pad_bytes, - map->format.val_bytes); + map->format.val_bytes, + false); } static inline void *_regmap_map_get_context(struct regmap *map) @@ -1843,7 +1844,7 @@ int regmap_write_async(struct regmap *map, unsigned int reg, unsigned int val) EXPORT_SYMBOL_GPL(regmap_write_async); int _regmap_raw_write(struct regmap *map, unsigned int reg, - const void *val, size_t val_len) + const void *val, size_t val_len, bool noinc) { size_t val_bytes = map->format.val_bytes; size_t val_count = val_len / val_bytes; @@ -1864,7 +1865,7 @@ int _regmap_raw_write(struct regmap *map, unsigned int reg, /* Write as many bytes as possible with chunk_size */ for (i = 0; i < chunk_count; i++) { - ret = _regmap_raw_write_impl(map, reg, val, chunk_bytes); + ret = _regmap_raw_write_impl(map, reg, val, chunk_bytes, noinc); if (ret) return ret; @@ -1875,7 +1876,7 @@ int _regmap_raw_write(struct regmap *map, unsigned int reg, /* Write remaining bytes */ if (val_len) - ret = _regmap_raw_write_impl(map, reg, val, val_len); + ret = _regmap_raw_write_impl(map, reg, val, val_len, noinc); return ret; } @@ -1908,7 +1909,7 @@ int regmap_raw_write(struct regmap *map, unsigned int reg, map->lock(map->lock_arg); - ret = _regmap_raw_write(map, reg, val, val_len); + ret = _regmap_raw_write(map, reg, val, val_len, false); map->unlock(map->lock_arg); @@ -1966,7 +1967,7 @@ int regmap_noinc_write(struct regmap *map, unsigned int reg, write_len = map->max_raw_write; else write_len = val_len; - ret = _regmap_raw_write(map, reg, val, write_len); + ret = _regmap_raw_write(map, reg, val, write_len, true); if (ret) goto out_unlock; val = ((u8 *)val) + write_len; @@ -2443,7 +2444,7 @@ int regmap_raw_write_async(struct regmap *map, unsigned int reg, map->async = true; - ret = _regmap_raw_write(map, reg, val, val_len); + ret = _regmap_raw_write(map, reg, val, val_len, false); map->async = false; @@ -2454,7 +2455,7 @@ int regmap_raw_write_async(struct regmap *map, unsigned int reg, EXPORT_SYMBOL_GPL(regmap_raw_write_async); static int _regmap_raw_read(struct regmap *map, unsigned int reg, void *val, - unsigned int val_len) + unsigned int val_len, bool noinc) { struct regmap_range_node *range; int ret; @@ -2467,7 +2468,7 @@ static int _regmap_raw_read(struct regmap *map, unsigned int reg, void *val, range = _regmap_range_lookup(map, reg); if (range) { ret = _regmap_select_page(map, ®, range, - val_len / map->format.val_bytes); + noinc ? 1 : val_len / map->format.val_bytes); if (ret != 0) return ret; } @@ -2505,7 +2506,7 @@ static int _regmap_bus_read(void *context, unsigned int reg, if (!map->format.parse_val) return -EINVAL; - ret = _regmap_raw_read(map, reg, work_val, map->format.val_bytes); + ret = _regmap_raw_read(map, reg, work_val, map->format.val_bytes, false); if (ret == 0) *val = map->format.parse_val(work_val); @@ -2621,7 +2622,7 @@ int regmap_raw_read(struct regmap *map, unsigned int reg, void *val, /* Read bytes that fit into whole chunks */ for (i = 0; i < chunk_count; i++) { - ret = _regmap_raw_read(map, reg, val, chunk_bytes); + ret = _regmap_raw_read(map, reg, val, chunk_bytes, false); if (ret != 0) goto out; @@ -2632,7 +2633,7 @@ int regmap_raw_read(struct regmap *map, unsigned int reg, void *val, /* Read remaining bytes */ if (val_len) { - ret = _regmap_raw_read(map, reg, val, val_len); + ret = _regmap_raw_read(map, reg, val, val_len, false); if (ret != 0) goto out; } @@ -2707,7 +2708,7 @@ int regmap_noinc_read(struct regmap *map, unsigned int reg, read_len = map->max_raw_read; else read_len = val_len; - ret = _regmap_raw_read(map, reg, val, read_len); + ret = _regmap_raw_read(map, reg, val, read_len, true); if (ret) goto out_unlock; val = ((u8 *)val) + read_len; diff --git a/drivers/bluetooth/btrtl.c b/drivers/bluetooth/btrtl.c index bf3c02be6930..0dfaf90a31b0 100644 --- a/drivers/bluetooth/btrtl.c +++ b/drivers/bluetooth/btrtl.c @@ -370,11 +370,11 @@ static int rtlbt_parse_firmware(struct hci_dev *hdev, * the end. */ len = patch_length; - buf = kmemdup(btrtl_dev->fw_data + patch_offset, patch_length, - GFP_KERNEL); + buf = kvmalloc(patch_length, GFP_KERNEL); if (!buf) return -ENOMEM; + memcpy(buf, btrtl_dev->fw_data + patch_offset, patch_length - 4); memcpy(buf + patch_length - 4, &epatch_info->fw_version, 4); *_buf = buf; @@ -460,8 +460,10 @@ static int rtl_load_file(struct hci_dev *hdev, const char *name, u8 **buff) if (ret < 0) return ret; ret = fw->size; - *buff = kmemdup(fw->data, ret, GFP_KERNEL); - if (!*buff) + *buff = kvmalloc(fw->size, GFP_KERNEL); + if (*buff) + memcpy(*buff, fw->data, ret); + else ret = -ENOMEM; release_firmware(fw); @@ -499,14 +501,14 @@ static int btrtl_setup_rtl8723b(struct hci_dev *hdev, goto out; if (btrtl_dev->cfg_len > 0) { - tbuff = kzalloc(ret + btrtl_dev->cfg_len, GFP_KERNEL); + tbuff = kvzalloc(ret + btrtl_dev->cfg_len, GFP_KERNEL); if (!tbuff) { ret = -ENOMEM; goto out; } memcpy(tbuff, fw_data, ret); - kfree(fw_data); + kvfree(fw_data); memcpy(tbuff + ret, btrtl_dev->cfg_data, btrtl_dev->cfg_len); ret += btrtl_dev->cfg_len; @@ -519,14 +521,14 @@ static int btrtl_setup_rtl8723b(struct hci_dev *hdev, ret = rtl_download_firmware(hdev, fw_data, ret); out: - kfree(fw_data); + kvfree(fw_data); return ret; } void btrtl_free(struct btrtl_device_info *btrtl_dev) { - kfree(btrtl_dev->fw_data); - kfree(btrtl_dev->cfg_data); + kvfree(btrtl_dev->fw_data); + kvfree(btrtl_dev->cfg_data); kfree(btrtl_dev); } EXPORT_SYMBOL_GPL(btrtl_free); diff --git a/drivers/bus/hisi_lpc.c b/drivers/bus/hisi_lpc.c index 20c957185af2..2e9252d37a18 100644 --- a/drivers/bus/hisi_lpc.c +++ b/drivers/bus/hisi_lpc.c @@ -358,6 +358,26 @@ static int hisi_lpc_acpi_xlat_io_res(struct acpi_device *adev, return 0; } +/* + * Released firmware describes the IO port max address as 0x3fff, which is + * the max host bus address. Fixup to a proper range. This will probably + * never be fixed in firmware. + */ +static void hisi_lpc_acpi_fixup_child_resource(struct device *hostdev, + struct resource *r) +{ + if (r->end != 0x3fff) + return; + + if (r->start == 0xe4) + r->end = 0xe4 + 0x04 - 1; + else if (r->start == 0x2f8) + r->end = 0x2f8 + 0x08 - 1; + else + dev_warn(hostdev, "unrecognised resource %pR to fixup, ignoring\n", + r); +} + /* * hisi_lpc_acpi_set_io_res - set the resources for a child * @child: the device node to be updated the I/O resource @@ -419,8 +439,11 @@ static int hisi_lpc_acpi_set_io_res(struct device *child, return -ENOMEM; } count = 0; - list_for_each_entry(rentry, &resource_list, node) - resources[count++] = *rentry->res; + list_for_each_entry(rentry, &resource_list, node) { + resources[count] = *rentry->res; + hisi_lpc_acpi_fixup_child_resource(hostdev, &resources[count]); + count++; + } acpi_dev_free_resource_list(&resource_list); diff --git a/drivers/char/ipmi/bt-bmc.c b/drivers/char/ipmi/bt-bmc.c index 40b9927c072c..89a8faa9b6cf 100644 --- a/drivers/char/ipmi/bt-bmc.c +++ b/drivers/char/ipmi/bt-bmc.c @@ -399,15 +399,15 @@ static int bt_bmc_config_irq(struct bt_bmc *bt_bmc, struct device *dev = &pdev->dev; int rc; - bt_bmc->irq = platform_get_irq(pdev, 0); - if (!bt_bmc->irq) - return -ENODEV; + bt_bmc->irq = platform_get_irq_optional(pdev, 0); + if (bt_bmc->irq < 0) + return bt_bmc->irq; rc = devm_request_irq(dev, bt_bmc->irq, bt_bmc_irq, IRQF_SHARED, DEVICE_NAME, bt_bmc); if (rc < 0) { dev_warn(dev, "Unable to request IRQ %d\n", bt_bmc->irq); - bt_bmc->irq = 0; + bt_bmc->irq = rc; return rc; } @@ -479,7 +479,7 @@ static int bt_bmc_probe(struct platform_device *pdev) bt_bmc_config_irq(bt_bmc, pdev); - if (bt_bmc->irq) { + if (bt_bmc->irq >= 0) { dev_info(dev, "Using IRQ %d\n", bt_bmc->irq); } else { dev_info(dev, "No IRQ; using timer\n"); @@ -505,7 +505,7 @@ static int bt_bmc_remove(struct platform_device *pdev) struct bt_bmc *bt_bmc = dev_get_drvdata(&pdev->dev); misc_deregister(&bt_bmc->miscdev); - if (!bt_bmc->irq) + if (bt_bmc->irq < 0) del_timer_sync(&bt_bmc->poll_timer); return 0; } diff --git a/drivers/char/random.c b/drivers/char/random.c index e877c20e0ee0..75a8f7f57269 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -1223,14 +1223,14 @@ static void add_timer_randomness(struct timer_rand_state *state, unsigned num) * We take into account the first, second and third-order deltas * in order to make our estimate. */ - delta = sample.jiffies - state->last_time; - state->last_time = sample.jiffies; + delta = sample.jiffies - READ_ONCE(state->last_time); + WRITE_ONCE(state->last_time, sample.jiffies); - delta2 = delta - state->last_delta; - state->last_delta = delta; + delta2 = delta - READ_ONCE(state->last_delta); + WRITE_ONCE(state->last_delta, delta); - delta3 = delta2 - state->last_delta2; - state->last_delta2 = delta2; + delta3 = delta2 - READ_ONCE(state->last_delta2); + WRITE_ONCE(state->last_delta2, delta2); if (delta < 0) delta = -delta; diff --git a/drivers/char/tlclk.c b/drivers/char/tlclk.c index 6d81bb3bb503..896a3550fba9 100644 --- a/drivers/char/tlclk.c +++ b/drivers/char/tlclk.c @@ -777,17 +777,21 @@ static int __init tlclk_init(void) { int ret; + telclk_interrupt = (inb(TLCLK_REG7) & 0x0f); + + alarm_events = kzalloc( sizeof(struct tlclk_alarms), GFP_KERNEL); + if (!alarm_events) { + ret = -ENOMEM; + goto out1; + } + ret = register_chrdev(tlclk_major, "telco_clock", &tlclk_fops); if (ret < 0) { printk(KERN_ERR "tlclk: can't get major %d.\n", tlclk_major); + kfree(alarm_events); return ret; } tlclk_major = ret; - alarm_events = kzalloc( sizeof(struct tlclk_alarms), GFP_KERNEL); - if (!alarm_events) { - ret = -ENOMEM; - goto out1; - } /* Read telecom clock IRQ number (Set by BIOS) */ if (!request_region(TLCLK_BASE, 8, "telco_clock")) { @@ -796,7 +800,6 @@ static int __init tlclk_init(void) ret = -EBUSY; goto out2; } - telclk_interrupt = (inb(TLCLK_REG7) & 0x0f); if (0x0F == telclk_interrupt ) { /* not MCPBL0010 ? */ printk(KERN_ERR "telclk_interrupt = 0x%x non-mcpbl0010 hw.\n", @@ -837,8 +840,8 @@ static int __init tlclk_init(void) release_region(TLCLK_BASE, 8); out2: kfree(alarm_events); -out1: unregister_chrdev(tlclk_major, "telco_clock"); +out1: return ret; } diff --git a/drivers/char/tpm/tpm_crb.c b/drivers/char/tpm/tpm_crb.c index e59f1f91d7f3..a9dcf31eadd2 100644 --- a/drivers/char/tpm/tpm_crb.c +++ b/drivers/char/tpm/tpm_crb.c @@ -22,6 +22,7 @@ #include "tpm.h" #define ACPI_SIG_TPM2 "TPM2" +#define TPM_CRB_MAX_RESOURCES 3 static const guid_t crb_acpi_start_guid = GUID_INIT(0x6BBF6CAB, 0x5463, 0x4714, @@ -91,7 +92,6 @@ enum crb_status { struct crb_priv { u32 sm; const char *hid; - void __iomem *iobase; struct crb_regs_head __iomem *regs_h; struct crb_regs_tail __iomem *regs_t; u8 __iomem *cmd; @@ -434,21 +434,27 @@ static const struct tpm_class_ops tpm_crb = { static int crb_check_resource(struct acpi_resource *ares, void *data) { - struct resource *io_res = data; + struct resource *iores_array = data; struct resource_win win; struct resource *res = &(win.res); + int i; if (acpi_dev_resource_memory(ares, res) || acpi_dev_resource_address_space(ares, &win)) { - *io_res = *res; - io_res->name = NULL; + for (i = 0; i < TPM_CRB_MAX_RESOURCES + 1; ++i) { + if (resource_type(iores_array + i) != IORESOURCE_MEM) { + iores_array[i] = *res; + iores_array[i].name = NULL; + break; + } + } } return 1; } -static void __iomem *crb_map_res(struct device *dev, struct crb_priv *priv, - struct resource *io_res, u64 start, u32 size) +static void __iomem *crb_map_res(struct device *dev, struct resource *iores, + void __iomem **iobase_ptr, u64 start, u32 size) { struct resource new_res = { .start = start, @@ -460,10 +466,16 @@ static void __iomem *crb_map_res(struct device *dev, struct crb_priv *priv, if (start != new_res.start) return (void __iomem *) ERR_PTR(-EINVAL); - if (!resource_contains(io_res, &new_res)) + if (!iores) return devm_ioremap_resource(dev, &new_res); - return priv->iobase + (new_res.start - io_res->start); + if (!*iobase_ptr) { + *iobase_ptr = devm_ioremap_resource(dev, iores); + if (IS_ERR(*iobase_ptr)) + return *iobase_ptr; + } + + return *iobase_ptr + (new_res.start - iores->start); } /* @@ -490,9 +502,13 @@ static u64 crb_fixup_cmd_size(struct device *dev, struct resource *io_res, static int crb_map_io(struct acpi_device *device, struct crb_priv *priv, struct acpi_table_tpm2 *buf) { - struct list_head resources; - struct resource io_res; + struct list_head acpi_resource_list; + struct resource iores_array[TPM_CRB_MAX_RESOURCES + 1] = { {0} }; + void __iomem *iobase_array[TPM_CRB_MAX_RESOURCES] = {NULL}; struct device *dev = &device->dev; + struct resource *iores; + void __iomem **iobase_ptr; + int i; u32 pa_high, pa_low; u64 cmd_pa; u32 cmd_size; @@ -501,21 +517,41 @@ static int crb_map_io(struct acpi_device *device, struct crb_priv *priv, u32 rsp_size; int ret; - INIT_LIST_HEAD(&resources); - ret = acpi_dev_get_resources(device, &resources, crb_check_resource, - &io_res); + INIT_LIST_HEAD(&acpi_resource_list); + ret = acpi_dev_get_resources(device, &acpi_resource_list, + crb_check_resource, iores_array); if (ret < 0) return ret; - acpi_dev_free_resource_list(&resources); + acpi_dev_free_resource_list(&acpi_resource_list); - if (resource_type(&io_res) != IORESOURCE_MEM) { + if (resource_type(iores_array) != IORESOURCE_MEM) { dev_err(dev, FW_BUG "TPM2 ACPI table does not define a memory resource\n"); return -EINVAL; + } else if (resource_type(iores_array + TPM_CRB_MAX_RESOURCES) == + IORESOURCE_MEM) { + dev_warn(dev, "TPM2 ACPI table defines too many memory resources\n"); + memset(iores_array + TPM_CRB_MAX_RESOURCES, + 0, sizeof(*iores_array)); + iores_array[TPM_CRB_MAX_RESOURCES].flags = 0; } - priv->iobase = devm_ioremap_resource(dev, &io_res); - if (IS_ERR(priv->iobase)) - return PTR_ERR(priv->iobase); + iores = NULL; + iobase_ptr = NULL; + for (i = 0; resource_type(iores_array + i) == IORESOURCE_MEM; ++i) { + if (buf->control_address >= iores_array[i].start && + buf->control_address + sizeof(struct crb_regs_tail) - 1 <= + iores_array[i].end) { + iores = iores_array + i; + iobase_ptr = iobase_array + i; + break; + } + } + + priv->regs_t = crb_map_res(dev, iores, iobase_ptr, buf->control_address, + sizeof(struct crb_regs_tail)); + + if (IS_ERR(priv->regs_t)) + return PTR_ERR(priv->regs_t); /* The ACPI IO region starts at the head area and continues to include * the control area, as one nice sane region except for some older @@ -523,9 +559,10 @@ static int crb_map_io(struct acpi_device *device, struct crb_priv *priv, */ if ((priv->sm == ACPI_TPM2_COMMAND_BUFFER) || (priv->sm == ACPI_TPM2_MEMORY_MAPPED)) { - if (buf->control_address == io_res.start + + if (iores && + buf->control_address == iores->start + sizeof(*priv->regs_h)) - priv->regs_h = priv->iobase; + priv->regs_h = *iobase_ptr; else dev_warn(dev, FW_BUG "Bad ACPI memory layout"); } @@ -534,13 +571,6 @@ static int crb_map_io(struct acpi_device *device, struct crb_priv *priv, if (ret) return ret; - priv->regs_t = crb_map_res(dev, priv, &io_res, buf->control_address, - sizeof(struct crb_regs_tail)); - if (IS_ERR(priv->regs_t)) { - ret = PTR_ERR(priv->regs_t); - goto out_relinquish_locality; - } - /* * PTT HW bug w/a: wake up the device to access * possibly not retained registers. @@ -552,13 +582,26 @@ static int crb_map_io(struct acpi_device *device, struct crb_priv *priv, pa_high = ioread32(&priv->regs_t->ctrl_cmd_pa_high); pa_low = ioread32(&priv->regs_t->ctrl_cmd_pa_low); cmd_pa = ((u64)pa_high << 32) | pa_low; - cmd_size = crb_fixup_cmd_size(dev, &io_res, cmd_pa, - ioread32(&priv->regs_t->ctrl_cmd_size)); + cmd_size = ioread32(&priv->regs_t->ctrl_cmd_size); + + iores = NULL; + iobase_ptr = NULL; + for (i = 0; iores_array[i].end; ++i) { + if (cmd_pa >= iores_array[i].start && + cmd_pa <= iores_array[i].end) { + iores = iores_array + i; + iobase_ptr = iobase_array + i; + break; + } + } + + if (iores) + cmd_size = crb_fixup_cmd_size(dev, iores, cmd_pa, cmd_size); dev_dbg(dev, "cmd_hi = %X cmd_low = %X cmd_size %X\n", pa_high, pa_low, cmd_size); - priv->cmd = crb_map_res(dev, priv, &io_res, cmd_pa, cmd_size); + priv->cmd = crb_map_res(dev, iores, iobase_ptr, cmd_pa, cmd_size); if (IS_ERR(priv->cmd)) { ret = PTR_ERR(priv->cmd); goto out; @@ -566,11 +609,25 @@ static int crb_map_io(struct acpi_device *device, struct crb_priv *priv, memcpy_fromio(&__rsp_pa, &priv->regs_t->ctrl_rsp_pa, 8); rsp_pa = le64_to_cpu(__rsp_pa); - rsp_size = crb_fixup_cmd_size(dev, &io_res, rsp_pa, - ioread32(&priv->regs_t->ctrl_rsp_size)); + rsp_size = ioread32(&priv->regs_t->ctrl_rsp_size); + + iores = NULL; + iobase_ptr = NULL; + for (i = 0; resource_type(iores_array + i) == IORESOURCE_MEM; ++i) { + if (rsp_pa >= iores_array[i].start && + rsp_pa <= iores_array[i].end) { + iores = iores_array + i; + iobase_ptr = iobase_array + i; + break; + } + } + + if (iores) + rsp_size = crb_fixup_cmd_size(dev, iores, rsp_pa, rsp_size); if (cmd_pa != rsp_pa) { - priv->rsp = crb_map_res(dev, priv, &io_res, rsp_pa, rsp_size); + priv->rsp = crb_map_res(dev, iores, iobase_ptr, + rsp_pa, rsp_size); ret = PTR_ERR_OR_ZERO(priv->rsp); goto out; } diff --git a/drivers/char/tpm/tpm_ibmvtpm.c b/drivers/char/tpm/tpm_ibmvtpm.c index e82013d587b4..64428dbed992 100644 --- a/drivers/char/tpm/tpm_ibmvtpm.c +++ b/drivers/char/tpm/tpm_ibmvtpm.c @@ -581,6 +581,7 @@ static irqreturn_t ibmvtpm_interrupt(int irq, void *vtpm_instance) */ while ((crq = ibmvtpm_crq_get_next(ibmvtpm)) != NULL) { ibmvtpm_crq_process(crq, ibmvtpm); + wake_up_interruptible(&ibmvtpm->crq_queue.wq); crq->valid = 0; smp_wmb(); } @@ -628,6 +629,7 @@ static int tpm_ibmvtpm_probe(struct vio_dev *vio_dev, } crq_q->num_entry = CRQ_RES_BUF_SIZE / sizeof(*crq_q->crq_addr); + init_waitqueue_head(&crq_q->wq); ibmvtpm->crq_dma_handle = dma_map_single(dev, crq_q->crq_addr, CRQ_RES_BUF_SIZE, DMA_BIDIRECTIONAL); @@ -680,6 +682,13 @@ static int tpm_ibmvtpm_probe(struct vio_dev *vio_dev, if (rc) goto init_irq_cleanup; + if (!wait_event_timeout(ibmvtpm->crq_queue.wq, + ibmvtpm->rtce_buf != NULL, + HZ)) { + dev_err(dev, "CRQ response timed out\n"); + goto init_irq_cleanup; + } + return tpm_chip_register(chip); init_irq_cleanup: do { diff --git a/drivers/char/tpm/tpm_ibmvtpm.h b/drivers/char/tpm/tpm_ibmvtpm.h index 7983f1a33267..b92aa7d3e93e 100644 --- a/drivers/char/tpm/tpm_ibmvtpm.h +++ b/drivers/char/tpm/tpm_ibmvtpm.h @@ -26,6 +26,7 @@ struct ibmvtpm_crq_queue { struct ibmvtpm_crq *crq_addr; u32 index; u32 num_entry; + wait_queue_head_t wq; }; struct ibmvtpm_dev { diff --git a/drivers/clk/imx/clk-pfdv2.c b/drivers/clk/imx/clk-pfdv2.c index a03bbed662c6..2a46b9b61b46 100644 --- a/drivers/clk/imx/clk-pfdv2.c +++ b/drivers/clk/imx/clk-pfdv2.c @@ -139,6 +139,12 @@ static int clk_pfdv2_set_rate(struct clk_hw *hw, unsigned long rate, u32 val; u8 frac; + if (!rate) + return -EINVAL; + + /* PFD can NOT change rate without gating */ + WARN_ON(clk_pfdv2_is_enabled(hw)); + tmp = tmp * 18 + rate / 2; do_div(tmp, rate); frac = tmp; diff --git a/drivers/clk/socfpga/clk-pll-s10.c b/drivers/clk/socfpga/clk-pll-s10.c index 4705eb544f01..8d7b1d0c4664 100644 --- a/drivers/clk/socfpga/clk-pll-s10.c +++ b/drivers/clk/socfpga/clk-pll-s10.c @@ -39,7 +39,9 @@ static unsigned long clk_pll_recalc_rate(struct clk_hw *hwclk, /* read VCO1 reg for numerator and denominator */ reg = readl(socfpgaclk->hw.reg); refdiv = (reg & SOCFPGA_PLL_REFDIV_MASK) >> SOCFPGA_PLL_REFDIV_SHIFT; - vco_freq = (unsigned long long)parent_rate / refdiv; + + vco_freq = parent_rate; + do_div(vco_freq, refdiv); /* Read mdiv and fdiv from the fdbck register */ reg = readl(socfpgaclk->hw.reg + 0x4); diff --git a/drivers/clk/ti/adpll.c b/drivers/clk/ti/adpll.c index fdfb90058504..bb2f2836dab2 100644 --- a/drivers/clk/ti/adpll.c +++ b/drivers/clk/ti/adpll.c @@ -194,15 +194,8 @@ static const char *ti_adpll_clk_get_name(struct ti_adpll_data *d, if (err) return NULL; } else { - const char *base_name = "adpll"; - char *buf; - - buf = devm_kzalloc(d->dev, 8 + 1 + strlen(base_name) + 1 + - strlen(postfix), GFP_KERNEL); - if (!buf) - return NULL; - sprintf(buf, "%08lx.%s.%s", d->pa, base_name, postfix); - name = buf; + name = devm_kasprintf(d->dev, GFP_KERNEL, "%08lx.adpll.%s", + d->pa, postfix); } return name; diff --git a/drivers/clocksource/h8300_timer8.c b/drivers/clocksource/h8300_timer8.c index 1d740a8c42ab..47114c2a7cb5 100644 --- a/drivers/clocksource/h8300_timer8.c +++ b/drivers/clocksource/h8300_timer8.c @@ -169,7 +169,7 @@ static int __init h8300_8timer_init(struct device_node *node) return PTR_ERR(clk); } - ret = ENXIO; + ret = -ENXIO; base = of_iomap(node, 0); if (!base) { pr_err("failed to map registers for clockevent\n"); diff --git a/drivers/cpufreq/powernv-cpufreq.c b/drivers/cpufreq/powernv-cpufreq.c index 1806b1da4366..3a2f022f6bde 100644 --- a/drivers/cpufreq/powernv-cpufreq.c +++ b/drivers/cpufreq/powernv-cpufreq.c @@ -902,6 +902,7 @@ static struct notifier_block powernv_cpufreq_reboot_nb = { void powernv_cpufreq_work_fn(struct work_struct *work) { struct chip *chip = container_of(work, struct chip, throttle); + struct cpufreq_policy *policy; unsigned int cpu; cpumask_t mask; @@ -916,12 +917,14 @@ void powernv_cpufreq_work_fn(struct work_struct *work) chip->restore = false; for_each_cpu(cpu, &mask) { int index; - struct cpufreq_policy policy; - cpufreq_get_policy(&policy, cpu); - index = cpufreq_table_find_index_c(&policy, policy.cur); - powernv_cpufreq_target_index(&policy, index); - cpumask_andnot(&mask, &mask, policy.cpus); + policy = cpufreq_cpu_get(cpu); + if (!policy) + continue; + index = cpufreq_table_find_index_c(policy, policy->cur); + powernv_cpufreq_target_index(policy, index); + cpumask_andnot(&mask, &mask, policy->cpus); + cpufreq_cpu_put(policy); } out: put_online_cpus(); diff --git a/drivers/crypto/chelsio/chcr_algo.c b/drivers/crypto/chelsio/chcr_algo.c index fe2eadc0ce83..2d30ed5a2674 100644 --- a/drivers/crypto/chelsio/chcr_algo.c +++ b/drivers/crypto/chelsio/chcr_algo.c @@ -2480,8 +2480,9 @@ int chcr_aead_dma_map(struct device *dev, else reqctx->b0_dma = 0; if (req->src == req->dst) { - error = dma_map_sg(dev, req->src, sg_nents(req->src), - DMA_BIDIRECTIONAL); + error = dma_map_sg(dev, req->src, + sg_nents_for_len(req->src, dst_size), + DMA_BIDIRECTIONAL); if (!error) goto err; } else { diff --git a/drivers/crypto/chelsio/chtls/chtls_io.c b/drivers/crypto/chelsio/chtls/chtls_io.c index ce1f1d5d7cd5..c403d6b64e08 100644 --- a/drivers/crypto/chelsio/chtls/chtls_io.c +++ b/drivers/crypto/chelsio/chtls/chtls_io.c @@ -1437,7 +1437,7 @@ static int chtls_pt_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, csk->wr_max_credits)) sk->sk_write_space(sk); - if (copied >= target && !sk->sk_backlog.tail) + if (copied >= target && !READ_ONCE(sk->sk_backlog.tail)) break; if (copied) { @@ -1470,7 +1470,7 @@ static int chtls_pt_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, break; } } - if (sk->sk_backlog.tail) { + if (READ_ONCE(sk->sk_backlog.tail)) { release_sock(sk); lock_sock(sk); chtls_cleanup_rbuf(sk, copied); @@ -1615,7 +1615,7 @@ static int peekmsg(struct sock *sk, struct msghdr *msg, break; } - if (sk->sk_backlog.tail) { + if (READ_ONCE(sk->sk_backlog.tail)) { /* Do not sleep, just process backlog. */ release_sock(sk); lock_sock(sk); @@ -1743,7 +1743,7 @@ int chtls_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, csk->wr_max_credits)) sk->sk_write_space(sk); - if (copied >= target && !sk->sk_backlog.tail) + if (copied >= target && !READ_ONCE(sk->sk_backlog.tail)) break; if (copied) { @@ -1774,7 +1774,7 @@ int chtls_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, } } - if (sk->sk_backlog.tail) { + if (READ_ONCE(sk->sk_backlog.tail)) { release_sock(sk); lock_sock(sk); chtls_cleanup_rbuf(sk, copied); diff --git a/drivers/dax/bus.c b/drivers/dax/bus.c index 8fafbeab510a..eccdda1f7b71 100644 --- a/drivers/dax/bus.c +++ b/drivers/dax/bus.c @@ -227,7 +227,7 @@ static void dax_region_unregister(void *region) struct dax_region *alloc_dax_region(struct device *parent, int region_id, struct resource *res, int target_node, unsigned int align, - unsigned long pfn_flags) + unsigned long long pfn_flags) { struct dax_region *dax_region; diff --git a/drivers/dax/bus.h b/drivers/dax/bus.h index 8619e3299943..9e4eba67e8b9 100644 --- a/drivers/dax/bus.h +++ b/drivers/dax/bus.h @@ -11,7 +11,7 @@ struct dax_region; void dax_region_put(struct dax_region *dax_region); struct dax_region *alloc_dax_region(struct device *parent, int region_id, struct resource *res, int target_node, unsigned int align, - unsigned long flags); + unsigned long long flags); enum dev_dax_subsys { DEV_DAX_BUS, diff --git a/drivers/dax/dax-private.h b/drivers/dax/dax-private.h index 6ccca3b890d6..3107ce80e809 100644 --- a/drivers/dax/dax-private.h +++ b/drivers/dax/dax-private.h @@ -32,7 +32,7 @@ struct dax_region { struct device *dev; unsigned int align; struct resource res; - unsigned long pfn_flags; + unsigned long long pfn_flags; }; /** diff --git a/drivers/devfreq/tegra30-devfreq.c b/drivers/devfreq/tegra30-devfreq.c index a6ba75f4106d..e273011c83fb 100644 --- a/drivers/devfreq/tegra30-devfreq.c +++ b/drivers/devfreq/tegra30-devfreq.c @@ -68,6 +68,8 @@ #define KHZ 1000 +#define KHZ_MAX (ULONG_MAX / KHZ) + /* Assume that the bus is saturated if the utilization is 25% */ #define BUS_SATURATION_RATIO 25 @@ -169,7 +171,7 @@ struct tegra_actmon_emc_ratio { }; static struct tegra_actmon_emc_ratio actmon_emc_ratios[] = { - { 1400000, ULONG_MAX }, + { 1400000, KHZ_MAX }, { 1200000, 750000 }, { 1100000, 600000 }, { 1000000, 500000 }, diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c index eba7e3fe769c..f6df6ef1b0fb 100644 --- a/drivers/dma-buf/dma-buf.c +++ b/drivers/dma-buf/dma-buf.c @@ -59,6 +59,8 @@ static void dma_buf_release(struct dentry *dentry) struct dma_buf *dmabuf; dmabuf = dentry->d_fsdata; + if (unlikely(!dmabuf)) + return; BUG_ON(dmabuf->vmapping_counter); diff --git a/drivers/dma-buf/dma-fence.c b/drivers/dma-buf/dma-fence.c index 2c136aee3e79..052a41e2451c 100644 --- a/drivers/dma-buf/dma-fence.c +++ b/drivers/dma-buf/dma-fence.c @@ -273,6 +273,30 @@ void dma_fence_free(struct dma_fence *fence) } EXPORT_SYMBOL(dma_fence_free); +static bool __dma_fence_enable_signaling(struct dma_fence *fence) +{ + bool was_set; + + lockdep_assert_held(fence->lock); + + was_set = test_and_set_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT, + &fence->flags); + + if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags)) + return false; + + if (!was_set && fence->ops->enable_signaling) { + trace_dma_fence_enable_signal(fence); + + if (!fence->ops->enable_signaling(fence)) { + dma_fence_signal_locked(fence); + return false; + } + } + + return true; +} + /** * dma_fence_enable_sw_signaling - enable signaling on fence * @fence: the fence to enable @@ -285,19 +309,12 @@ void dma_fence_enable_sw_signaling(struct dma_fence *fence) { unsigned long flags; - if (!test_and_set_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT, - &fence->flags) && - !test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags) && - fence->ops->enable_signaling) { - trace_dma_fence_enable_signal(fence); - - spin_lock_irqsave(fence->lock, flags); - - if (!fence->ops->enable_signaling(fence)) - dma_fence_signal_locked(fence); + if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags)) + return; - spin_unlock_irqrestore(fence->lock, flags); - } + spin_lock_irqsave(fence->lock, flags); + __dma_fence_enable_signaling(fence); + spin_unlock_irqrestore(fence->lock, flags); } EXPORT_SYMBOL(dma_fence_enable_sw_signaling); @@ -331,7 +348,6 @@ int dma_fence_add_callback(struct dma_fence *fence, struct dma_fence_cb *cb, { unsigned long flags; int ret = 0; - bool was_set; if (WARN_ON(!fence || !func)) return -EINVAL; @@ -343,25 +359,14 @@ int dma_fence_add_callback(struct dma_fence *fence, struct dma_fence_cb *cb, spin_lock_irqsave(fence->lock, flags); - was_set = test_and_set_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT, - &fence->flags); - - if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags)) - ret = -ENOENT; - else if (!was_set && fence->ops->enable_signaling) { - trace_dma_fence_enable_signal(fence); - - if (!fence->ops->enable_signaling(fence)) { - dma_fence_signal_locked(fence); - ret = -ENOENT; - } - } - - if (!ret) { + if (__dma_fence_enable_signaling(fence)) { cb->func = func; list_add_tail(&cb->node, &fence->cb_list); - } else + } else { INIT_LIST_HEAD(&cb->node); + ret = -ENOENT; + } + spin_unlock_irqrestore(fence->lock, flags); return ret; @@ -461,7 +466,6 @@ dma_fence_default_wait(struct dma_fence *fence, bool intr, signed long timeout) struct default_wait_cb cb; unsigned long flags; signed long ret = timeout ? timeout : 1; - bool was_set; if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags)) return ret; @@ -473,21 +477,9 @@ dma_fence_default_wait(struct dma_fence *fence, bool intr, signed long timeout) goto out; } - was_set = test_and_set_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT, - &fence->flags); - - if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags)) + if (!__dma_fence_enable_signaling(fence)) goto out; - if (!was_set && fence->ops->enable_signaling) { - trace_dma_fence_enable_signal(fence); - - if (!fence->ops->enable_signaling(fence)) { - dma_fence_signal_locked(fence); - goto out; - } - } - if (!timeout) { ret = 0; goto out; diff --git a/drivers/dma/mediatek/mtk-hsdma.c b/drivers/dma/mediatek/mtk-hsdma.c index 1a2028e1c29e..4c58da742143 100644 --- a/drivers/dma/mediatek/mtk-hsdma.c +++ b/drivers/dma/mediatek/mtk-hsdma.c @@ -997,7 +997,7 @@ static int mtk_hsdma_probe(struct platform_device *pdev) if (err) { dev_err(&pdev->dev, "request_irq failed with err %d\n", err); - goto err_unregister; + goto err_free; } platform_set_drvdata(pdev, hsdma); @@ -1006,6 +1006,8 @@ static int mtk_hsdma_probe(struct platform_device *pdev) return 0; +err_free: + of_dma_controller_free(pdev->dev.of_node); err_unregister: dma_async_device_unregister(dd); diff --git a/drivers/dma/stm32-dma.c b/drivers/dma/stm32-dma.c index 5989b0893521..6c5771de32c6 100644 --- a/drivers/dma/stm32-dma.c +++ b/drivers/dma/stm32-dma.c @@ -488,8 +488,10 @@ static int stm32_dma_terminate_all(struct dma_chan *c) spin_lock_irqsave(&chan->vchan.lock, flags); - if (chan->busy) { - stm32_dma_stop(chan); + if (chan->desc) { + vchan_terminate_vdesc(&chan->desc->vdesc); + if (chan->busy) + stm32_dma_stop(chan); chan->desc = NULL; } @@ -545,6 +547,8 @@ static void stm32_dma_start_transfer(struct stm32_dma_chan *chan) if (!vdesc) return; + list_del(&vdesc->node); + chan->desc = to_stm32_dma_desc(vdesc); chan->next_sg = 0; } @@ -622,7 +626,6 @@ static void stm32_dma_handle_chan_done(struct stm32_dma_chan *chan) } else { chan->busy = false; if (chan->next_sg == chan->desc->num_sgs) { - list_del(&chan->desc->vdesc.node); vchan_cookie_complete(&chan->desc->vdesc); chan->desc = NULL; } diff --git a/drivers/dma/stm32-mdma.c b/drivers/dma/stm32-mdma.c index 5838311cf990..ee1cbf3be75d 100644 --- a/drivers/dma/stm32-mdma.c +++ b/drivers/dma/stm32-mdma.c @@ -1127,6 +1127,8 @@ static void stm32_mdma_start_transfer(struct stm32_mdma_chan *chan) return; } + list_del(&vdesc->node); + chan->desc = to_stm32_mdma_desc(vdesc); hwdesc = chan->desc->node[0].hwdesc; chan->curr_hwdesc = 0; @@ -1242,8 +1244,10 @@ static int stm32_mdma_terminate_all(struct dma_chan *c) LIST_HEAD(head); spin_lock_irqsave(&chan->vchan.lock, flags); - if (chan->busy) { - stm32_mdma_stop(chan); + if (chan->desc) { + vchan_terminate_vdesc(&chan->desc->vdesc); + if (chan->busy) + stm32_mdma_stop(chan); chan->desc = NULL; } vchan_get_all_descriptors(&chan->vchan, &head); @@ -1331,7 +1335,6 @@ static enum dma_status stm32_mdma_tx_status(struct dma_chan *c, static void stm32_mdma_xfer_end(struct stm32_mdma_chan *chan) { - list_del(&chan->desc->vdesc.node); vchan_cookie_complete(&chan->desc->vdesc); chan->desc = NULL; chan->busy = false; diff --git a/drivers/dma/tegra20-apb-dma.c b/drivers/dma/tegra20-apb-dma.c index 4a750e29bfb5..3fe27dbde5b2 100644 --- a/drivers/dma/tegra20-apb-dma.c +++ b/drivers/dma/tegra20-apb-dma.c @@ -1287,8 +1287,7 @@ static void tegra_dma_free_chan_resources(struct dma_chan *dc) dev_dbg(tdc2dev(tdc), "Freeing channel %d\n", tdc->id); - if (tdc->busy) - tegra_dma_terminate_all(dc); + tegra_dma_terminate_all(dc); spin_lock_irqsave(&tdc->lock, flags); list_splice_init(&tdc->pending_sg_req, &sg_req_list); diff --git a/drivers/dma/xilinx/zynqmp_dma.c b/drivers/dma/xilinx/zynqmp_dma.c index 9c845c07b107..d47749a35863 100644 --- a/drivers/dma/xilinx/zynqmp_dma.c +++ b/drivers/dma/xilinx/zynqmp_dma.c @@ -123,10 +123,12 @@ /* Max transfer size per descriptor */ #define ZYNQMP_DMA_MAX_TRANS_LEN 0x40000000 +/* Max burst lengths */ +#define ZYNQMP_DMA_MAX_DST_BURST_LEN 32768U +#define ZYNQMP_DMA_MAX_SRC_BURST_LEN 32768U + /* Reset values for data attributes */ #define ZYNQMP_DMA_AXCACHE_VAL 0xF -#define ZYNQMP_DMA_ARLEN_RST_VAL 0xF -#define ZYNQMP_DMA_AWLEN_RST_VAL 0xF #define ZYNQMP_DMA_SRC_ISSUE_RST_VAL 0x1F @@ -534,17 +536,19 @@ static void zynqmp_dma_handle_ovfl_int(struct zynqmp_dma_chan *chan, u32 status) static void zynqmp_dma_config(struct zynqmp_dma_chan *chan) { - u32 val; + u32 val, burst_val; val = readl(chan->regs + ZYNQMP_DMA_CTRL0); val |= ZYNQMP_DMA_POINT_TYPE_SG; writel(val, chan->regs + ZYNQMP_DMA_CTRL0); val = readl(chan->regs + ZYNQMP_DMA_DATA_ATTR); + burst_val = __ilog2_u32(chan->src_burst_len); val = (val & ~ZYNQMP_DMA_ARLEN) | - (chan->src_burst_len << ZYNQMP_DMA_ARLEN_OFST); + ((burst_val << ZYNQMP_DMA_ARLEN_OFST) & ZYNQMP_DMA_ARLEN); + burst_val = __ilog2_u32(chan->dst_burst_len); val = (val & ~ZYNQMP_DMA_AWLEN) | - (chan->dst_burst_len << ZYNQMP_DMA_AWLEN_OFST); + ((burst_val << ZYNQMP_DMA_AWLEN_OFST) & ZYNQMP_DMA_AWLEN); writel(val, chan->regs + ZYNQMP_DMA_DATA_ATTR); } @@ -560,8 +564,10 @@ static int zynqmp_dma_device_config(struct dma_chan *dchan, { struct zynqmp_dma_chan *chan = to_chan(dchan); - chan->src_burst_len = config->src_maxburst; - chan->dst_burst_len = config->dst_maxburst; + chan->src_burst_len = clamp(config->src_maxburst, 1U, + ZYNQMP_DMA_MAX_SRC_BURST_LEN); + chan->dst_burst_len = clamp(config->dst_maxburst, 1U, + ZYNQMP_DMA_MAX_DST_BURST_LEN); return 0; } @@ -887,8 +893,8 @@ static int zynqmp_dma_chan_probe(struct zynqmp_dma_device *zdev, return PTR_ERR(chan->regs); chan->bus_width = ZYNQMP_DMA_BUS_WIDTH_64; - chan->dst_burst_len = ZYNQMP_DMA_AWLEN_RST_VAL; - chan->src_burst_len = ZYNQMP_DMA_ARLEN_RST_VAL; + chan->dst_burst_len = ZYNQMP_DMA_MAX_DST_BURST_LEN; + chan->src_burst_len = ZYNQMP_DMA_MAX_SRC_BURST_LEN; err = of_property_read_u32(node, "xlnx,bus-width", &chan->bus_width); if (err < 0) { dev_err(&pdev->dev, "missing xlnx,bus-width property\n"); diff --git a/drivers/edac/ghes_edac.c b/drivers/edac/ghes_edac.c index 523dd56a798c..0031819402d0 100644 --- a/drivers/edac/ghes_edac.c +++ b/drivers/edac/ghes_edac.c @@ -488,6 +488,7 @@ int ghes_edac_register(struct ghes *ghes, struct device *dev) if (!force_load && idx < 0) return -ENODEV; } else { + force_load = true; idx = 0; } @@ -586,6 +587,9 @@ void ghes_edac_unregister(struct ghes *ghes) struct mem_ctl_info *mci; unsigned long flags; + if (!force_load) + return; + mutex_lock(&ghes_reg_mutex); if (!refcount_dec_and_test(&ghes_refcount)) diff --git a/drivers/firmware/arm_sdei.c b/drivers/firmware/arm_sdei.c index eb2df89d4924..e497785cd99f 100644 --- a/drivers/firmware/arm_sdei.c +++ b/drivers/firmware/arm_sdei.c @@ -412,14 +412,19 @@ int sdei_event_enable(u32 event_num) return -ENOENT; } - spin_lock(&sdei_list_lock); - event->reenable = true; - spin_unlock(&sdei_list_lock); + cpus_read_lock(); if (event->type == SDEI_EVENT_TYPE_SHARED) err = sdei_api_event_enable(event->event_num); else err = sdei_do_cross_call(_local_event_enable, event); + + if (!err) { + spin_lock(&sdei_list_lock); + event->reenable = true; + spin_unlock(&sdei_list_lock); + } + cpus_read_unlock(); mutex_unlock(&sdei_events_lock); return err; @@ -621,21 +626,18 @@ int sdei_event_register(u32 event_num, sdei_event_callback *cb, void *arg) break; } - spin_lock(&sdei_list_lock); - event->reregister = true; - spin_unlock(&sdei_list_lock); - + cpus_read_lock(); err = _sdei_event_register(event); if (err) { - spin_lock(&sdei_list_lock); - event->reregister = false; - event->reenable = false; - spin_unlock(&sdei_list_lock); - sdei_event_destroy(event); pr_warn("Failed to register event %u: %d\n", event_num, err); + } else { + spin_lock(&sdei_list_lock); + event->reregister = true; + spin_unlock(&sdei_list_lock); } + cpus_read_unlock(); } while (0); mutex_unlock(&sdei_events_lock); diff --git a/drivers/gpio/gpio-rcar.c b/drivers/gpio/gpio-rcar.c index 187984d26f47..f0b6c68e848e 100644 --- a/drivers/gpio/gpio-rcar.c +++ b/drivers/gpio/gpio-rcar.c @@ -250,8 +250,10 @@ static int gpio_rcar_request(struct gpio_chip *chip, unsigned offset) int error; error = pm_runtime_get_sync(p->dev); - if (error < 0) + if (error < 0) { + pm_runtime_put(p->dev); return error; + } error = pinctrl_gpio_request(chip->base + offset); if (error) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c index d10f483f5e27..ce30d4e8bf25 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c @@ -644,6 +644,9 @@ static int kgd_hqd_destroy(struct kgd_dev *kgd, void *mqd, uint32_t temp; struct v10_compute_mqd *m = get_mqd(mqd); + if (amdgpu_sriov_vf(adev) && adev->in_gpu_reset) + return 0; + #if 0 unsigned long flags; int retry; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c index e262f2ac07a3..92754cfb9808 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c @@ -540,6 +540,9 @@ int kgd_gfx_v9_hqd_destroy(struct kgd_dev *kgd, void *mqd, uint32_t temp; struct v9_mqd *m = get_mqd(mqd); + if (amdgpu_sriov_vf(adev) && adev->in_gpu_reset) + return 0; + if (adev->in_gpu_reset) return -EIO; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c index edb561baf8b9..f3fa271e3394 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c @@ -1247,15 +1247,15 @@ int amdgpu_amdkfd_gpuvm_free_memory_of_gpu( * be freed anyway */ - /* No more MMU notifiers */ - amdgpu_mn_unregister(mem->bo); - /* Make sure restore workers don't access the BO any more */ bo_list_entry = &mem->validate_list; mutex_lock(&process_info->lock); list_del(&bo_list_entry->head); mutex_unlock(&process_info->lock); + /* No more MMU notifiers */ + amdgpu_mn_unregister(mem->bo); + ret = reserve_bo_and_cond_vms(mem, NULL, BO_VM_ALL, &ctx); if (unlikely(ret)) return ret; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c index 50dff69a0f6e..b1172d93c99c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c @@ -192,30 +192,35 @@ static bool amdgpu_read_bios_from_rom(struct amdgpu_device *adev) static bool amdgpu_read_platform_bios(struct amdgpu_device *adev) { - uint8_t __iomem *bios; - size_t size; + phys_addr_t rom = adev->pdev->rom; + size_t romlen = adev->pdev->romlen; + void __iomem *bios; adev->bios = NULL; - bios = pci_platform_rom(adev->pdev, &size); - if (!bios) { + if (!rom || romlen == 0) return false; - } - adev->bios = kzalloc(size, GFP_KERNEL); - if (adev->bios == NULL) + adev->bios = kzalloc(romlen, GFP_KERNEL); + if (!adev->bios) return false; - memcpy_fromio(adev->bios, bios, size); + bios = ioremap(rom, romlen); + if (!bios) + goto free_bios; - if (!check_atom_bios(adev->bios, size)) { - kfree(adev->bios); - return false; - } + memcpy_fromio(adev->bios, bios, romlen); + iounmap(bios); - adev->bios_size = size; + if (!check_atom_bios(adev->bios, romlen)) + goto free_bios; + + adev->bios_size = romlen; return true; +free_bios: + kfree(adev->bios); + return false; } #ifdef CONFIG_ACPI diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 5e1dce424154..4105fbf57167 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -3466,6 +3466,8 @@ static int amdgpu_device_reset_sriov(struct amdgpu_device *adev, if (r) return r; + amdgpu_amdkfd_pre_reset(adev); + /* Resume IP prior to SMC */ r = amdgpu_device_ip_reinit_early_sriov(adev); if (r) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.c index c8793e6cc3c5..6373bfb47d55 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.c @@ -124,13 +124,12 @@ int amdgpu_gfx_rlc_init_sr(struct amdgpu_device *adev, u32 dws) */ int amdgpu_gfx_rlc_init_csb(struct amdgpu_device *adev) { - volatile u32 *dst_ptr; u32 dws; int r; /* allocate clear state block */ adev->gfx.rlc.clear_state_size = dws = adev->gfx.rlc.funcs->get_csb_size(adev); - r = amdgpu_bo_create_reserved(adev, dws * 4, PAGE_SIZE, + r = amdgpu_bo_create_kernel(adev, dws * 4, PAGE_SIZE, AMDGPU_GEM_DOMAIN_VRAM, &adev->gfx.rlc.clear_state_obj, &adev->gfx.rlc.clear_state_gpu_addr, @@ -141,13 +140,6 @@ int amdgpu_gfx_rlc_init_csb(struct amdgpu_device *adev) return r; } - /* set up the cs buffer */ - dst_ptr = adev->gfx.rlc.cs_ptr; - adev->gfx.rlc.funcs->get_csb_buffer(adev, dst_ptr); - amdgpu_bo_kunmap(adev->gfx.rlc.clear_state_obj); - amdgpu_bo_unpin(adev->gfx.rlc.clear_state_obj); - amdgpu_bo_unreserve(adev->gfx.rlc.clear_state_obj); - return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/atom.c b/drivers/gpu/drm/amd/amdgpu/atom.c index dd30f4e61a8c..cae426c7c086 100644 --- a/drivers/gpu/drm/amd/amdgpu/atom.c +++ b/drivers/gpu/drm/amd/amdgpu/atom.c @@ -744,8 +744,8 @@ static void atom_op_jump(atom_exec_context *ctx, int *ptr, int arg) cjiffies = jiffies; if (time_after(cjiffies, ctx->last_jump_jiffies)) { cjiffies -= ctx->last_jump_jiffies; - if ((jiffies_to_msecs(cjiffies) > 5000)) { - DRM_ERROR("atombios stuck in loop for more than 5secs aborting\n"); + if ((jiffies_to_msecs(cjiffies) > 10000)) { + DRM_ERROR("atombios stuck in loop for more than 10secs aborting\n"); ctx->abort = true; } } else { diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c index 19876c90be0e..d17edc850427 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c @@ -993,39 +993,6 @@ static int gfx_v10_0_rlc_init(struct amdgpu_device *adev) return 0; } -static int gfx_v10_0_csb_vram_pin(struct amdgpu_device *adev) -{ - int r; - - r = amdgpu_bo_reserve(adev->gfx.rlc.clear_state_obj, false); - if (unlikely(r != 0)) - return r; - - r = amdgpu_bo_pin(adev->gfx.rlc.clear_state_obj, - AMDGPU_GEM_DOMAIN_VRAM); - if (!r) - adev->gfx.rlc.clear_state_gpu_addr = - amdgpu_bo_gpu_offset(adev->gfx.rlc.clear_state_obj); - - amdgpu_bo_unreserve(adev->gfx.rlc.clear_state_obj); - - return r; -} - -static void gfx_v10_0_csb_vram_unpin(struct amdgpu_device *adev) -{ - int r; - - if (!adev->gfx.rlc.clear_state_obj) - return; - - r = amdgpu_bo_reserve(adev->gfx.rlc.clear_state_obj, true); - if (likely(r == 0)) { - amdgpu_bo_unpin(adev->gfx.rlc.clear_state_obj); - amdgpu_bo_unreserve(adev->gfx.rlc.clear_state_obj); - } -} - static void gfx_v10_0_mec_fini(struct amdgpu_device *adev) { amdgpu_bo_free_kernel(&adev->gfx.mec.hpd_eop_obj, NULL, NULL); @@ -1787,25 +1754,7 @@ static void gfx_v10_0_enable_gui_idle_interrupt(struct amdgpu_device *adev, static int gfx_v10_0_init_csb(struct amdgpu_device *adev) { - int r; - - if (adev->in_gpu_reset) { - r = amdgpu_bo_reserve(adev->gfx.rlc.clear_state_obj, false); - if (r) - return r; - - r = amdgpu_bo_kmap(adev->gfx.rlc.clear_state_obj, - (void **)&adev->gfx.rlc.cs_ptr); - if (!r) { - adev->gfx.rlc.funcs->get_csb_buffer(adev, - adev->gfx.rlc.cs_ptr); - amdgpu_bo_kunmap(adev->gfx.rlc.clear_state_obj); - } - - amdgpu_bo_unreserve(adev->gfx.rlc.clear_state_obj); - if (r) - return r; - } + adev->gfx.rlc.funcs->get_csb_buffer(adev, adev->gfx.rlc.cs_ptr); /* csib */ WREG32_SOC15(GC, 0, mmRLC_CSIB_ADDR_HI, @@ -3774,10 +3723,6 @@ static int gfx_v10_0_hw_init(void *handle) int r; struct amdgpu_device *adev = (struct amdgpu_device *)handle; - r = gfx_v10_0_csb_vram_pin(adev); - if (r) - return r; - if (!amdgpu_emu_mode) gfx_v10_0_init_golden_registers(adev); @@ -3865,7 +3810,6 @@ static int gfx_v10_0_hw_fini(void *handle) } gfx_v10_0_cp_enable(adev, false); gfx_v10_0_enable_gui_idle_interrupt(adev, false); - gfx_v10_0_csb_vram_unpin(adev); return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c index 791ba398f007..d92e92e5d50b 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c @@ -4554,6 +4554,8 @@ static int gfx_v7_0_hw_init(void *handle) gfx_v7_0_constants_init(adev); + /* init CSB */ + adev->gfx.rlc.funcs->get_csb_buffer(adev, adev->gfx.rlc.cs_ptr); /* init rlc */ r = adev->gfx.rlc.funcs->resume(adev); if (r) diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c index cc88ba76a8d4..467ed7fca884 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c @@ -1321,39 +1321,6 @@ static int gfx_v8_0_rlc_init(struct amdgpu_device *adev) return 0; } -static int gfx_v8_0_csb_vram_pin(struct amdgpu_device *adev) -{ - int r; - - r = amdgpu_bo_reserve(adev->gfx.rlc.clear_state_obj, false); - if (unlikely(r != 0)) - return r; - - r = amdgpu_bo_pin(adev->gfx.rlc.clear_state_obj, - AMDGPU_GEM_DOMAIN_VRAM); - if (!r) - adev->gfx.rlc.clear_state_gpu_addr = - amdgpu_bo_gpu_offset(adev->gfx.rlc.clear_state_obj); - - amdgpu_bo_unreserve(adev->gfx.rlc.clear_state_obj); - - return r; -} - -static void gfx_v8_0_csb_vram_unpin(struct amdgpu_device *adev) -{ - int r; - - if (!adev->gfx.rlc.clear_state_obj) - return; - - r = amdgpu_bo_reserve(adev->gfx.rlc.clear_state_obj, true); - if (likely(r == 0)) { - amdgpu_bo_unpin(adev->gfx.rlc.clear_state_obj); - amdgpu_bo_unreserve(adev->gfx.rlc.clear_state_obj); - } -} - static void gfx_v8_0_mec_fini(struct amdgpu_device *adev) { amdgpu_bo_free_kernel(&adev->gfx.mec.hpd_eop_obj, NULL, NULL); @@ -3917,6 +3884,7 @@ static void gfx_v8_0_enable_gui_idle_interrupt(struct amdgpu_device *adev, static void gfx_v8_0_init_csb(struct amdgpu_device *adev) { + adev->gfx.rlc.funcs->get_csb_buffer(adev, adev->gfx.rlc.cs_ptr); /* csib */ WREG32(mmRLC_CSIB_ADDR_HI, adev->gfx.rlc.clear_state_gpu_addr >> 32); @@ -4837,10 +4805,6 @@ static int gfx_v8_0_hw_init(void *handle) gfx_v8_0_init_golden_registers(adev); gfx_v8_0_constants_init(adev); - r = gfx_v8_0_csb_vram_pin(adev); - if (r) - return r; - r = adev->gfx.rlc.funcs->resume(adev); if (r) return r; @@ -4958,8 +4922,6 @@ static int gfx_v8_0_hw_fini(void *handle) pr_err("rlc is busy, skip halt rlc\n"); amdgpu_gfx_rlc_exit_safe_mode(adev); - gfx_v8_0_csb_vram_unpin(adev); - return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c index 6004fdacc866..90dcc7afc9c4 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c @@ -1675,39 +1675,6 @@ static int gfx_v9_0_rlc_init(struct amdgpu_device *adev) return 0; } -static int gfx_v9_0_csb_vram_pin(struct amdgpu_device *adev) -{ - int r; - - r = amdgpu_bo_reserve(adev->gfx.rlc.clear_state_obj, false); - if (unlikely(r != 0)) - return r; - - r = amdgpu_bo_pin(adev->gfx.rlc.clear_state_obj, - AMDGPU_GEM_DOMAIN_VRAM); - if (!r) - adev->gfx.rlc.clear_state_gpu_addr = - amdgpu_bo_gpu_offset(adev->gfx.rlc.clear_state_obj); - - amdgpu_bo_unreserve(adev->gfx.rlc.clear_state_obj); - - return r; -} - -static void gfx_v9_0_csb_vram_unpin(struct amdgpu_device *adev) -{ - int r; - - if (!adev->gfx.rlc.clear_state_obj) - return; - - r = amdgpu_bo_reserve(adev->gfx.rlc.clear_state_obj, true); - if (likely(r == 0)) { - amdgpu_bo_unpin(adev->gfx.rlc.clear_state_obj); - amdgpu_bo_unreserve(adev->gfx.rlc.clear_state_obj); - } -} - static void gfx_v9_0_mec_fini(struct amdgpu_device *adev) { amdgpu_bo_free_kernel(&adev->gfx.mec.hpd_eop_obj, NULL, NULL); @@ -2596,6 +2563,7 @@ static void gfx_v9_0_enable_gui_idle_interrupt(struct amdgpu_device *adev, static void gfx_v9_0_init_csb(struct amdgpu_device *adev) { + adev->gfx.rlc.funcs->get_csb_buffer(adev, adev->gfx.rlc.cs_ptr); /* csib */ WREG32_RLC(SOC15_REG_OFFSET(GC, 0, mmRLC_CSIB_ADDR_HI), adev->gfx.rlc.clear_state_gpu_addr >> 32); @@ -3888,10 +3856,6 @@ static int gfx_v9_0_hw_init(void *handle) gfx_v9_0_constants_init(adev); - r = gfx_v9_0_csb_vram_pin(adev); - if (r) - return r; - r = adev->gfx.rlc.funcs->resume(adev); if (r) return r; @@ -3977,8 +3941,6 @@ static int gfx_v9_0_hw_fini(void *handle) gfx_v9_0_cp_enable(adev, false); adev->gfx.rlc.funcs->stop(adev); - gfx_v9_0_csb_vram_unpin(adev); - return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c index 36ad0c0e8efb..cd2cbe760e88 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c @@ -1026,6 +1026,10 @@ static int vcn_v2_0_start_dpg_mode(struct amdgpu_device *adev, bool indirect) tmp = REG_SET_FIELD(tmp, UVD_RBC_RB_CNTL, RB_RPTR_WR_EN, 1); WREG32_SOC15(UVD, 0, mmUVD_RBC_RB_CNTL, tmp); + /* Stall DPG before WPTR/RPTR reset */ + WREG32_P(SOC15_REG_OFFSET(UVD, 0, mmUVD_POWER_STATUS), + UVD_POWER_STATUS__STALL_DPG_POWER_UP_MASK, + ~UVD_POWER_STATUS__STALL_DPG_POWER_UP_MASK); /* set the write pointer delay */ WREG32_SOC15(UVD, 0, mmUVD_RBC_RB_WPTR_CNTL, 0); @@ -1048,6 +1052,9 @@ static int vcn_v2_0_start_dpg_mode(struct amdgpu_device *adev, bool indirect) WREG32_SOC15(UVD, 0, mmUVD_RBC_RB_WPTR, lower_32_bits(ring->wptr)); + /* Unstall DPG */ + WREG32_P(SOC15_REG_OFFSET(UVD, 0, mmUVD_POWER_STATUS), + 0, ~UVD_POWER_STATUS__STALL_DPG_POWER_UP_MASK); return 0; } @@ -1357,8 +1364,13 @@ static int vcn_v2_0_pause_dpg_mode(struct amdgpu_device *adev, UVD_DPG_PAUSE__NJ_PAUSE_DPG_ACK_MASK, UVD_DPG_PAUSE__NJ_PAUSE_DPG_ACK_MASK, ret_code); + /* Stall DPG before WPTR/RPTR reset */ + WREG32_P(SOC15_REG_OFFSET(UVD, 0, mmUVD_POWER_STATUS), + UVD_POWER_STATUS__STALL_DPG_POWER_UP_MASK, + ~UVD_POWER_STATUS__STALL_DPG_POWER_UP_MASK); /* Restore */ ring = &adev->vcn.inst->ring_enc[0]; + ring->wptr = 0; WREG32_SOC15(UVD, 0, mmUVD_RB_BASE_LO, ring->gpu_addr); WREG32_SOC15(UVD, 0, mmUVD_RB_BASE_HI, upper_32_bits(ring->gpu_addr)); WREG32_SOC15(UVD, 0, mmUVD_RB_SIZE, ring->ring_size / 4); @@ -1366,6 +1378,7 @@ static int vcn_v2_0_pause_dpg_mode(struct amdgpu_device *adev, WREG32_SOC15(UVD, 0, mmUVD_RB_WPTR, lower_32_bits(ring->wptr)); ring = &adev->vcn.inst->ring_enc[1]; + ring->wptr = 0; WREG32_SOC15(UVD, 0, mmUVD_RB_BASE_LO2, ring->gpu_addr); WREG32_SOC15(UVD, 0, mmUVD_RB_BASE_HI2, upper_32_bits(ring->gpu_addr)); WREG32_SOC15(UVD, 0, mmUVD_RB_SIZE2, ring->ring_size / 4); @@ -1374,6 +1387,9 @@ static int vcn_v2_0_pause_dpg_mode(struct amdgpu_device *adev, WREG32_SOC15(UVD, 0, mmUVD_RBC_RB_WPTR, RREG32_SOC15(UVD, 0, mmUVD_SCRATCH2) & 0x7FFFFFFF); + /* Unstall DPG */ + WREG32_P(SOC15_REG_OFFSET(UVD, 0, mmUVD_POWER_STATUS), + 0, ~UVD_POWER_STATUS__STALL_DPG_POWER_UP_MASK); SOC15_WAIT_ON_RREG(UVD, 0, mmUVD_POWER_STATUS, UVD_PGFSM_CONFIG__UVDM_UVDU_PWR_ON, diff --git a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h index 901fe3590165..d3400da6ab64 100644 --- a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h +++ b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h @@ -905,7 +905,7 @@ static const uint32_t cwsr_trap_gfx10_hex[] = { 0x7a5d0000, 0x807c817c, 0x807aff7a, 0x00000080, 0xbf0a717c, 0xbf85fff8, - 0xbf820141, 0xbef4037e, + 0xbf820142, 0xbef4037e, 0x8775ff7f, 0x0000ffff, 0x8875ff75, 0x00040000, 0xbef60380, 0xbef703ff, @@ -967,7 +967,7 @@ static const uint32_t cwsr_trap_gfx10_hex[] = { 0x725d0000, 0xe0304080, 0x725d0100, 0xe0304100, 0x725d0200, 0xe0304180, - 0x725d0300, 0xbf820031, + 0x725d0300, 0xbf820032, 0xbef603ff, 0x01000000, 0xbef20378, 0x8078ff78, 0x00000400, 0xbefc0384, @@ -992,83 +992,84 @@ static const uint32_t cwsr_trap_gfx10_hex[] = { 0x725d0000, 0xe0304100, 0x725d0100, 0xe0304200, 0x725d0200, 0xe0304300, - 0x725d0300, 0xb9782a05, - 0x80788178, 0x907c9973, - 0x877c817c, 0xbf06817c, - 0xbf850002, 0x8f788978, - 0xbf820001, 0x8f788a78, - 0xb9721e06, 0x8f728a72, - 0x80787278, 0x8078ff78, - 0x00000200, 0x80f8ff78, - 0x00000050, 0xbef603ff, - 0x01000000, 0xbefc03ff, - 0x0000006c, 0x80f89078, - 0xf429003a, 0xf0000000, - 0xbf8cc07f, 0x80fc847c, - 0xbf800000, 0xbe803100, - 0xbe823102, 0x80f8a078, - 0xf42d003a, 0xf0000000, - 0xbf8cc07f, 0x80fc887c, - 0xbf800000, 0xbe803100, - 0xbe823102, 0xbe843104, - 0xbe863106, 0x80f8c078, - 0xf431003a, 0xf0000000, - 0xbf8cc07f, 0x80fc907c, - 0xbf800000, 0xbe803100, - 0xbe823102, 0xbe843104, - 0xbe863106, 0xbe883108, - 0xbe8a310a, 0xbe8c310c, - 0xbe8e310e, 0xbf06807c, - 0xbf84fff0, 0xb9782a05, - 0x80788178, 0x907c9973, - 0x877c817c, 0xbf06817c, - 0xbf850002, 0x8f788978, - 0xbf820001, 0x8f788a78, - 0xb9721e06, 0x8f728a72, - 0x80787278, 0x8078ff78, - 0x00000200, 0xbef603ff, - 0x01000000, 0xf4211bfa, + 0x725d0300, 0xbf8c3f70, + 0xb9782a05, 0x80788178, + 0x907c9973, 0x877c817c, + 0xbf06817c, 0xbf850002, + 0x8f788978, 0xbf820001, + 0x8f788a78, 0xb9721e06, + 0x8f728a72, 0x80787278, + 0x8078ff78, 0x00000200, + 0x80f8ff78, 0x00000050, + 0xbef603ff, 0x01000000, + 0xbefc03ff, 0x0000006c, + 0x80f89078, 0xf429003a, + 0xf0000000, 0xbf8cc07f, + 0x80fc847c, 0xbf800000, + 0xbe803100, 0xbe823102, + 0x80f8a078, 0xf42d003a, + 0xf0000000, 0xbf8cc07f, + 0x80fc887c, 0xbf800000, + 0xbe803100, 0xbe823102, + 0xbe843104, 0xbe863106, + 0x80f8c078, 0xf431003a, + 0xf0000000, 0xbf8cc07f, + 0x80fc907c, 0xbf800000, + 0xbe803100, 0xbe823102, + 0xbe843104, 0xbe863106, + 0xbe883108, 0xbe8a310a, + 0xbe8c310c, 0xbe8e310e, + 0xbf06807c, 0xbf84fff0, + 0xb9782a05, 0x80788178, + 0x907c9973, 0x877c817c, + 0xbf06817c, 0xbf850002, + 0x8f788978, 0xbf820001, + 0x8f788a78, 0xb9721e06, + 0x8f728a72, 0x80787278, + 0x8078ff78, 0x00000200, + 0xbef603ff, 0x01000000, + 0xf4211bfa, 0xf0000000, + 0x80788478, 0xf4211b3a, 0xf0000000, 0x80788478, - 0xf4211b3a, 0xf0000000, - 0x80788478, 0xf4211b7a, + 0xf4211b7a, 0xf0000000, + 0x80788478, 0xf4211eba, 0xf0000000, 0x80788478, - 0xf4211eba, 0xf0000000, - 0x80788478, 0xf4211efa, + 0xf4211efa, 0xf0000000, + 0x80788478, 0xf4211c3a, 0xf0000000, 0x80788478, - 0xf4211c3a, 0xf0000000, - 0x80788478, 0xf4211c7a, + 0xf4211c7a, 0xf0000000, + 0x80788478, 0xf4211e7a, 0xf0000000, 0x80788478, - 0xf4211e7a, 0xf0000000, - 0x80788478, 0xf4211cfa, + 0xf4211cfa, 0xf0000000, + 0x80788478, 0xf4211bba, 0xf0000000, 0x80788478, + 0xbf8cc07f, 0xb9eef814, 0xf4211bba, 0xf0000000, 0x80788478, 0xbf8cc07f, - 0xb9eef814, 0xf4211bba, - 0xf0000000, 0x80788478, - 0xbf8cc07f, 0xb9eef815, - 0xbef2036d, 0x876dff72, - 0x0000ffff, 0xbefc036f, - 0xbefe037a, 0xbeff037b, - 0x876f71ff, 0x000003ff, - 0xb9ef4803, 0xb9f9f816, - 0x876f71ff, 0xfffff800, - 0x906f8b6f, 0xb9efa2c3, - 0xb9f3f801, 0x876fff72, - 0xfc000000, 0x906f9a6f, - 0x8f6f906f, 0xbef30380, + 0xb9eef815, 0xbef2036d, + 0x876dff72, 0x0000ffff, + 0xbefc036f, 0xbefe037a, + 0xbeff037b, 0x876f71ff, + 0x000003ff, 0xb9ef4803, + 0xb9f9f816, 0x876f71ff, + 0xfffff800, 0x906f8b6f, + 0xb9efa2c3, 0xb9f3f801, + 0x876fff72, 0xfc000000, + 0x906f9a6f, 0x8f6f906f, + 0xbef30380, 0x88736f73, + 0x876fff72, 0x02000000, + 0x906f996f, 0x8f6f8f6f, 0x88736f73, 0x876fff72, - 0x02000000, 0x906f996f, - 0x8f6f8f6f, 0x88736f73, - 0x876fff72, 0x01000000, - 0x906f986f, 0x8f6f996f, - 0x88736f73, 0x876fff70, - 0x00800000, 0x906f976f, - 0xb9f3f807, 0x87fe7e7e, - 0x87ea6a6a, 0xb9f0f802, - 0xbf8a0000, 0xbe80226c, - 0xbf810000, 0xbf9f0000, + 0x01000000, 0x906f986f, + 0x8f6f996f, 0x88736f73, + 0x876fff70, 0x00800000, + 0x906f976f, 0xb9f3f807, + 0x87fe7e7e, 0x87ea6a6a, + 0xb9f0f802, 0xbf8a0000, + 0xbe80226c, 0xbf810000, 0xbf9f0000, 0xbf9f0000, 0xbf9f0000, 0xbf9f0000, + 0xbf9f0000, 0x00000000, }; static const uint32_t cwsr_trap_arcturus_hex[] = { 0xbf820001, 0xbf8202c4, diff --git a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx10.asm b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx10.asm index cdaa523ce6be..4433bda2ce25 100644 --- a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx10.asm +++ b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx10.asm @@ -758,6 +758,7 @@ L_RESTORE_V0: buffer_load_dword v1, v0, s_restore_buf_rsrc0, s_restore_mem_offset_save slc:1 glc:1 offset:256 buffer_load_dword v2, v0, s_restore_buf_rsrc0, s_restore_mem_offset_save slc:1 glc:1 offset:256*2 buffer_load_dword v3, v0, s_restore_buf_rsrc0, s_restore_mem_offset_save slc:1 glc:1 offset:256*3 + s_waitcnt vmcnt(0) /* restore SGPRs */ //will be 2+8+16*6 diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c index a2ed9c257cb0..e9a278440079 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c @@ -1075,6 +1075,8 @@ static int stop_cpsch(struct device_queue_manager *dqm) unmap_queues_cpsch(dqm, KFD_UNMAP_QUEUES_FILTER_ALL_QUEUES, 0); dqm_unlock(dqm); + pm_release_ib(&dqm->packets); + kfd_gtt_sa_free(dqm->dev, dqm->fence_mem); pm_uninit(&dqm->packets); 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 60e50181f6d3..2384aa018993 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -4299,19 +4299,6 @@ static void dm_crtc_helper_disable(struct drm_crtc *crtc) { } -static bool does_crtc_have_active_cursor(struct drm_crtc_state *new_crtc_state) -{ - struct drm_device *dev = new_crtc_state->crtc->dev; - struct drm_plane *plane; - - drm_for_each_plane_mask(plane, dev, new_crtc_state->plane_mask) { - if (plane->type == DRM_PLANE_TYPE_CURSOR) - return true; - } - - return false; -} - static int count_crtc_active_planes(struct drm_crtc_state *new_crtc_state) { struct drm_atomic_state *state = new_crtc_state->state; @@ -4391,19 +4378,20 @@ static int dm_crtc_helper_atomic_check(struct drm_crtc *crtc, return ret; } - /* In some use cases, like reset, no stream is attached */ - if (!dm_crtc_state->stream) - return 0; - /* - * We want at least one hardware plane enabled to use - * the stream with a cursor enabled. + * We require the primary plane to be enabled whenever the CRTC is, otherwise + * drm_mode_cursor_universal may end up trying to enable the cursor plane while all other + * planes are disabled, which is not supported by the hardware. And there is legacy + * userspace which stops using the HW cursor altogether in response to the resulting EINVAL. */ - if (state->enable && state->active && - does_crtc_have_active_cursor(state) && - dm_crtc_state->active_planes == 0) + if (state->enable && + !(state->plane_mask & drm_plane_mask(crtc->primary))) return -EINVAL; + /* In some use cases, like reset, no stream is attached */ + if (!dm_crtc_state->stream) + return 0; + if (dc_validate_stream(dc, dm_crtc_state->stream) == DC_OK) return 0; diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c index b43bb7f90e4e..2233d293a707 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c @@ -210,6 +210,8 @@ static int __set_legacy_tf(struct dc_transfer_func *func, res = mod_color_calculate_regamma_params(func, gamma, true, has_rom, NULL); + dc_gamma_release(&gamma); + return res ? 0 : -ENOMEM; } diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link.c b/drivers/gpu/drm/amd/display/dc/core/dc_link.c index 5bf12a446e95..3efee7b3378a 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c @@ -1733,8 +1733,7 @@ static void write_i2c_retimer_setting( slave_address, buffer[0], buffer[1], i2c_success?1:0); if (!i2c_success) - /* Write failure */ - ASSERT(i2c_success); + goto i2c_write_fail; /* Based on DP159 specs, APPLY_RX_TX_CHANGE bit in 0x0A * needs to be set to 1 on every 0xA-0xC write. @@ -1752,8 +1751,7 @@ static void write_i2c_retimer_setting( pipe_ctx->stream->link->ddc, slave_address, &offset, 1, &value, 1); if (!i2c_success) - /* Write failure */ - ASSERT(i2c_success); + goto i2c_write_fail; } buffer[0] = offset; @@ -1765,8 +1763,7 @@ static void write_i2c_retimer_setting( offset = 0x%x, reg_val = 0x%x, i2c_success = %d\n", slave_address, buffer[0], buffer[1], i2c_success?1:0); if (!i2c_success) - /* Write failure */ - ASSERT(i2c_success); + goto i2c_write_fail; } } } @@ -1786,8 +1783,7 @@ static void write_i2c_retimer_setting( slave_address, buffer[0], buffer[1], i2c_success?1:0); if (!i2c_success) - /* Write failure */ - ASSERT(i2c_success); + goto i2c_write_fail; /* Based on DP159 specs, APPLY_RX_TX_CHANGE bit in 0x0A * needs to be set to 1 on every 0xA-0xC write. @@ -1805,8 +1801,7 @@ static void write_i2c_retimer_setting( pipe_ctx->stream->link->ddc, slave_address, &offset, 1, &value, 1); if (!i2c_success) - /* Write failure */ - ASSERT(i2c_success); + goto i2c_write_fail; } buffer[0] = offset; @@ -1818,8 +1813,7 @@ static void write_i2c_retimer_setting( offset = 0x%x, reg_val = 0x%x, i2c_success = %d\n", slave_address, buffer[0], buffer[1], i2c_success?1:0); if (!i2c_success) - /* Write failure */ - ASSERT(i2c_success); + goto i2c_write_fail; } } } @@ -1837,8 +1831,7 @@ static void write_i2c_retimer_setting( offset = 0x%x, reg_val = 0x%x, i2c_success = %d\n", slave_address, buffer[0], buffer[1], i2c_success?1:0); if (!i2c_success) - /* Write failure */ - ASSERT(i2c_success); + goto i2c_write_fail; /* Write offset 0x00 to 0x23 */ buffer[0] = 0x00; @@ -1849,8 +1842,7 @@ static void write_i2c_retimer_setting( offset = 0x%x, reg_val = 0x%x, i2c_success = %d\n", slave_address, buffer[0], buffer[1], i2c_success?1:0); if (!i2c_success) - /* Write failure */ - ASSERT(i2c_success); + goto i2c_write_fail; /* Write offset 0xff to 0x00 */ buffer[0] = 0xff; @@ -1861,10 +1853,14 @@ static void write_i2c_retimer_setting( offset = 0x%x, reg_val = 0x%x, i2c_success = %d\n", slave_address, buffer[0], buffer[1], i2c_success?1:0); if (!i2c_success) - /* Write failure */ - ASSERT(i2c_success); + goto i2c_write_fail; } + + return; + +i2c_write_fail: + DC_LOG_DEBUG("Set retimer failed"); } static void write_i2c_default_retimer_setting( @@ -1889,8 +1885,7 @@ static void write_i2c_default_retimer_setting( offset = 0x%x, reg_val = 0x%x, i2c_success = %d\n", slave_address, buffer[0], buffer[1], i2c_success?1:0); if (!i2c_success) - /* Write failure */ - ASSERT(i2c_success); + goto i2c_write_fail; /* Write offset 0x0A to 0x17 */ buffer[0] = 0x0A; @@ -1901,8 +1896,7 @@ static void write_i2c_default_retimer_setting( offset = 0x%x, reg_val = 0x%x, i2c_success = %d\n", slave_address, buffer[0], buffer[1], i2c_success?1:0); if (!i2c_success) - /* Write failure */ - ASSERT(i2c_success); + goto i2c_write_fail; /* Write offset 0x0B to 0xDA or 0xD8 */ buffer[0] = 0x0B; @@ -1913,8 +1907,7 @@ static void write_i2c_default_retimer_setting( offset = 0x%x, reg_val = 0x%x, i2c_success = %d\n", slave_address, buffer[0], buffer[1], i2c_success?1:0); if (!i2c_success) - /* Write failure */ - ASSERT(i2c_success); + goto i2c_write_fail; /* Write offset 0x0A to 0x17 */ buffer[0] = 0x0A; @@ -1925,8 +1918,7 @@ static void write_i2c_default_retimer_setting( offset = 0x%x, reg_val= 0x%x, i2c_success = %d\n", slave_address, buffer[0], buffer[1], i2c_success?1:0); if (!i2c_success) - /* Write failure */ - ASSERT(i2c_success); + goto i2c_write_fail; /* Write offset 0x0C to 0x1D or 0x91 */ buffer[0] = 0x0C; @@ -1937,8 +1929,7 @@ static void write_i2c_default_retimer_setting( offset = 0x%x, reg_val = 0x%x, i2c_success = %d\n", slave_address, buffer[0], buffer[1], i2c_success?1:0); if (!i2c_success) - /* Write failure */ - ASSERT(i2c_success); + goto i2c_write_fail; /* Write offset 0x0A to 0x17 */ buffer[0] = 0x0A; @@ -1949,8 +1940,7 @@ static void write_i2c_default_retimer_setting( offset = 0x%x, reg_val = 0x%x, i2c_success = %d\n", slave_address, buffer[0], buffer[1], i2c_success?1:0); if (!i2c_success) - /* Write failure */ - ASSERT(i2c_success); + goto i2c_write_fail; if (is_vga_mode) { @@ -1965,8 +1955,7 @@ static void write_i2c_default_retimer_setting( offset = 0x%x, reg_val = 0x%x, i2c_success = %d\n", slave_address, buffer[0], buffer[1], i2c_success?1:0); if (!i2c_success) - /* Write failure */ - ASSERT(i2c_success); + goto i2c_write_fail; /* Write offset 0x00 to 0x23 */ buffer[0] = 0x00; @@ -1977,8 +1966,7 @@ static void write_i2c_default_retimer_setting( offset = 0x%x, reg_val= 0x%x, i2c_success = %d\n", slave_address, buffer[0], buffer[1], i2c_success?1:0); if (!i2c_success) - /* Write failure */ - ASSERT(i2c_success); + goto i2c_write_fail; /* Write offset 0xff to 0x00 */ buffer[0] = 0xff; @@ -1989,9 +1977,13 @@ static void write_i2c_default_retimer_setting( offset = 0x%x, reg_val= 0x%x, i2c_success = %d end here\n", slave_address, buffer[0], buffer[1], i2c_success?1:0); if (!i2c_success) - /* Write failure */ - ASSERT(i2c_success); + goto i2c_write_fail; } + + return; + +i2c_write_fail: + DC_LOG_DEBUG("Set default retimer failed"); } static void write_i2c_redriver_setting( @@ -2020,8 +2012,7 @@ static void write_i2c_redriver_setting( slave_address, buffer[3], buffer[4], buffer[5], buffer[6], i2c_success?1:0); if (!i2c_success) - /* Write failure */ - ASSERT(i2c_success); + DC_LOG_DEBUG("Set redriver failed"); } static void enable_link_hdmi(struct pipe_ctx *pipe_ctx) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c index 51991bf26a93..4c90d68db230 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c @@ -126,22 +126,16 @@ struct aux_payloads { struct vector payloads; }; -static struct i2c_payloads *dal_ddc_i2c_payloads_create(struct dc_context *ctx, uint32_t count) +static bool dal_ddc_i2c_payloads_create( + struct dc_context *ctx, + struct i2c_payloads *payloads, + uint32_t count) { - struct i2c_payloads *payloads; - - payloads = kzalloc(sizeof(struct i2c_payloads), GFP_KERNEL); - - if (!payloads) - return NULL; - if (dal_vector_construct( &payloads->payloads, ctx, count, sizeof(struct i2c_payload))) - return payloads; - - kfree(payloads); - return NULL; + return true; + return false; } static struct i2c_payload *dal_ddc_i2c_payloads_get(struct i2c_payloads *p) @@ -154,14 +148,12 @@ static uint32_t dal_ddc_i2c_payloads_get_count(struct i2c_payloads *p) return p->payloads.count; } -static void dal_ddc_i2c_payloads_destroy(struct i2c_payloads **p) +static void dal_ddc_i2c_payloads_destroy(struct i2c_payloads *p) { - if (!p || !*p) + if (!p) return; - dal_vector_destruct(&(*p)->payloads); - kfree(*p); - *p = NULL; + dal_vector_destruct(&p->payloads); } #define DDC_MIN(a, b) (((a) < (b)) ? (a) : (b)) @@ -521,9 +513,13 @@ bool dal_ddc_service_query_ddc_data( uint32_t payloads_num = write_payloads + read_payloads; + if (write_size > EDID_SEGMENT_SIZE || read_size > EDID_SEGMENT_SIZE) return false; + if (!payloads_num) + return false; + /*TODO: len of payload data for i2c and aux is uint8!!!!, * but we want to read 256 over i2c!!!!*/ if (dal_ddc_service_is_in_aux_transaction_mode(ddc)) { @@ -556,23 +552,25 @@ bool dal_ddc_service_query_ddc_data( ret = dc_link_aux_transfer_with_retries(ddc, &read_payload); } else { - struct i2c_payloads *payloads = - dal_ddc_i2c_payloads_create(ddc->ctx, payloads_num); + struct i2c_command command = {0}; + struct i2c_payloads payloads; + + if (!dal_ddc_i2c_payloads_create(ddc->ctx, &payloads, payloads_num)) + return false; - struct i2c_command command = { - .payloads = dal_ddc_i2c_payloads_get(payloads), - .number_of_payloads = 0, - .engine = DDC_I2C_COMMAND_ENGINE, - .speed = ddc->ctx->dc->caps.i2c_speed_in_khz }; + command.payloads = dal_ddc_i2c_payloads_get(&payloads); + command.number_of_payloads = 0; + command.engine = DDC_I2C_COMMAND_ENGINE; + command.speed = ddc->ctx->dc->caps.i2c_speed_in_khz; dal_ddc_i2c_payloads_add( - payloads, address, write_size, write_buf, true); + &payloads, address, write_size, write_buf, true); dal_ddc_i2c_payloads_add( - payloads, address, read_size, read_buf, false); + &payloads, address, read_size, read_buf, false); command.number_of_payloads = - dal_ddc_i2c_payloads_get_count(payloads); + dal_ddc_i2c_payloads_get_count(&payloads); ret = dm_helpers_submit_i2c( ddc->ctx, diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_hwss.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_hwss.c index a519dbc5ecb6..5641a9477d29 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link_hwss.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_hwss.c @@ -400,6 +400,7 @@ void dp_set_dsc_on_stream(struct pipe_ctx *pipe_ctx, bool enable) dsc_cfg.pic_height = stream->timing.v_addressable + stream->timing.v_border_top + stream->timing.v_border_bottom; dsc_cfg.pixel_encoding = stream->timing.pixel_encoding; dsc_cfg.color_depth = stream->timing.display_color_depth; + dsc_cfg.is_odm = pipe_ctx->next_odm_pipe ? true : false; dsc_cfg.dc_dsc_cfg = stream->timing.dsc_cfg; ASSERT(dsc_cfg.dc_dsc_cfg.num_slices_h % opp_cnt == 0); dsc_cfg.dc_dsc_cfg.num_slices_h /= opp_cnt; @@ -496,11 +497,15 @@ bool dp_set_dsc_pps_sdp(struct pipe_ctx *pipe_ctx, bool enable) struct dsc_config dsc_cfg; uint8_t dsc_packed_pps[128]; + memset(&dsc_cfg, 0, sizeof(dsc_cfg)); + memset(dsc_packed_pps, 0, 128); + /* Enable DSC hw block */ dsc_cfg.pic_width = stream->timing.h_addressable + stream->timing.h_border_left + stream->timing.h_border_right; dsc_cfg.pic_height = stream->timing.v_addressable + stream->timing.v_border_top + stream->timing.v_border_bottom; dsc_cfg.pixel_encoding = stream->timing.pixel_encoding; dsc_cfg.color_depth = stream->timing.display_color_depth; + dsc_cfg.is_odm = pipe_ctx->next_odm_pipe ? true : false; dsc_cfg.dc_dsc_cfg = stream->timing.dsc_cfg; DC_LOG_DSC(" "); diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dccg.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dccg.c index 16476ed25536..206436632275 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dccg.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dccg.c @@ -119,32 +119,6 @@ void dccg2_get_dccg_ref_freq(struct dccg *dccg, void dccg2_init(struct dccg *dccg) { - struct dcn_dccg *dccg_dcn = TO_DCN_DCCG(dccg); - - // Fallthrough intentional to program all available dpp_dto's - switch (dccg_dcn->base.ctx->dc->res_pool->pipe_count) { - case 6: - REG_UPDATE(DPPCLK_DTO_CTRL, DPPCLK_DTO_DB_EN[5], 1); - /* Fall through */ - case 5: - REG_UPDATE(DPPCLK_DTO_CTRL, DPPCLK_DTO_DB_EN[4], 1); - /* Fall through */ - case 4: - REG_UPDATE(DPPCLK_DTO_CTRL, DPPCLK_DTO_DB_EN[3], 1); - /* Fall through */ - case 3: - REG_UPDATE(DPPCLK_DTO_CTRL, DPPCLK_DTO_DB_EN[2], 1); - /* Fall through */ - case 2: - REG_UPDATE(DPPCLK_DTO_CTRL, DPPCLK_DTO_DB_EN[1], 1); - /* Fall through */ - case 1: - REG_UPDATE(DPPCLK_DTO_CTRL, DPPCLK_DTO_DB_EN[0], 1); - break; - default: - ASSERT(false); - break; - } } static const struct dccg_funcs dccg2_funcs = { diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dsc.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dsc.c index 1b419407af94..5c45c39662fb 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dsc.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dsc.c @@ -207,6 +207,9 @@ static bool dsc2_get_packed_pps(struct display_stream_compressor *dsc, const str struct dsc_reg_values dsc_reg_vals; struct dsc_optc_config dsc_optc_cfg; + memset(&dsc_reg_vals, 0, sizeof(dsc_reg_vals)); + memset(&dsc_optc_cfg, 0, sizeof(dsc_optc_cfg)); + DC_LOG_DSC("Getting packed DSC PPS for DSC Config:"); dsc_config_log(dsc, dsc_cfg); DC_LOG_DSC("DSC Picture Parameter Set (PPS):"); @@ -348,6 +351,7 @@ static bool dsc_prepare_config(const struct dsc_config *dsc_cfg, struct dsc_reg_ dsc_reg_vals->pps.block_pred_enable = dsc_cfg->dc_dsc_cfg.block_pred_enable; dsc_reg_vals->pps.line_buf_depth = dsc_cfg->dc_dsc_cfg.linebuf_depth; dsc_reg_vals->alternate_ich_encoding_en = dsc_reg_vals->pps.dsc_version_minor == 1 ? 0 : 1; + dsc_reg_vals->ich_reset_at_eol = (dsc_cfg->is_odm || dsc_reg_vals->num_slices_h > 1) ? 0xF : 0; // TODO: in addition to validating slice height (pic height must be divisible by slice height), // see what happens when the same condition doesn't apply for slice_width/pic_width. @@ -510,7 +514,6 @@ static void dsc_update_from_dsc_parameters(struct dsc_reg_values *reg_vals, cons reg_vals->pps.rc_buf_thresh[i] = reg_vals->pps.rc_buf_thresh[i] >> 6; reg_vals->rc_buffer_model_size = dsc_params->rc_buffer_model_size; - reg_vals->ich_reset_at_eol = reg_vals->num_slices_h == 1 ? 0 : 0xf; } static void dsc_write_to_registers(struct display_stream_compressor *dsc, const struct dsc_reg_values *reg_vals) diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c index 05b98eadc289..08062de3fbeb 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c @@ -340,8 +340,8 @@ struct _vcs_dpi_soc_bounding_box_st dcn2_0_nv14_soc = { }, }, .num_states = 5, - .sr_exit_time_us = 8.6, - .sr_enter_plus_exit_time_us = 10.9, + .sr_exit_time_us = 11.6, + .sr_enter_plus_exit_time_us = 13.9, .urgent_latency_us = 4.0, .urgent_latency_pixel_data_only_us = 4.0, .urgent_latency_pixel_mixed_with_vm_data_us = 4.0, @@ -2275,6 +2275,7 @@ static bool dcn20_validate_dsc(struct dc *dc, struct dc_state *new_ctx) + stream->timing.v_border_bottom; dsc_cfg.pixel_encoding = stream->timing.pixel_encoding; dsc_cfg.color_depth = stream->timing.display_color_depth; + dsc_cfg.is_odm = pipe_ctx->next_odm_pipe ? true : false; dsc_cfg.dc_dsc_cfg = stream->timing.dsc_cfg; dsc_cfg.dc_dsc_cfg.num_slices_h /= opp_cnt; diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubp.c b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubp.c index a00af513aa2b..c8f77bd0ce8a 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubp.c +++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubp.c @@ -73,32 +73,47 @@ void apply_DEDCN21_142_wa_for_hostvm_deadline( struct _vcs_dpi_display_dlg_regs_st *dlg_attr) { struct dcn21_hubp *hubp21 = TO_DCN21_HUBP(hubp); - uint32_t cur_value; + uint32_t refcyc_per_vm_group_vblank; + uint32_t refcyc_per_vm_req_vblank; + uint32_t refcyc_per_vm_group_flip; + uint32_t refcyc_per_vm_req_flip; + const uint32_t uninitialized_hw_default = 0; - REG_GET(VBLANK_PARAMETERS_5, REFCYC_PER_VM_GROUP_VBLANK, &cur_value); - if (cur_value > dlg_attr->refcyc_per_vm_group_vblank) + REG_GET(VBLANK_PARAMETERS_5, + REFCYC_PER_VM_GROUP_VBLANK, &refcyc_per_vm_group_vblank); + + if (refcyc_per_vm_group_vblank == uninitialized_hw_default || + refcyc_per_vm_group_vblank > dlg_attr->refcyc_per_vm_group_vblank) REG_SET(VBLANK_PARAMETERS_5, 0, REFCYC_PER_VM_GROUP_VBLANK, dlg_attr->refcyc_per_vm_group_vblank); REG_GET(VBLANK_PARAMETERS_6, - REFCYC_PER_VM_REQ_VBLANK, - &cur_value); - if (cur_value > dlg_attr->refcyc_per_vm_req_vblank) + REFCYC_PER_VM_REQ_VBLANK, &refcyc_per_vm_req_vblank); + + if (refcyc_per_vm_req_vblank == uninitialized_hw_default || + refcyc_per_vm_req_vblank > dlg_attr->refcyc_per_vm_req_vblank) REG_SET(VBLANK_PARAMETERS_6, 0, REFCYC_PER_VM_REQ_VBLANK, dlg_attr->refcyc_per_vm_req_vblank); - REG_GET(FLIP_PARAMETERS_3, REFCYC_PER_VM_GROUP_FLIP, &cur_value); - if (cur_value > dlg_attr->refcyc_per_vm_group_flip) + REG_GET(FLIP_PARAMETERS_3, + REFCYC_PER_VM_GROUP_FLIP, &refcyc_per_vm_group_flip); + + if (refcyc_per_vm_group_flip == uninitialized_hw_default || + refcyc_per_vm_group_flip > dlg_attr->refcyc_per_vm_group_flip) REG_SET(FLIP_PARAMETERS_3, 0, REFCYC_PER_VM_GROUP_FLIP, dlg_attr->refcyc_per_vm_group_flip); - REG_GET(FLIP_PARAMETERS_4, REFCYC_PER_VM_REQ_FLIP, &cur_value); - if (cur_value > dlg_attr->refcyc_per_vm_req_flip) + REG_GET(FLIP_PARAMETERS_4, + REFCYC_PER_VM_REQ_FLIP, &refcyc_per_vm_req_flip); + + if (refcyc_per_vm_req_flip == uninitialized_hw_default || + refcyc_per_vm_req_flip > dlg_attr->refcyc_per_vm_req_flip) REG_SET(FLIP_PARAMETERS_4, 0, REFCYC_PER_VM_REQ_FLIP, dlg_attr->refcyc_per_vm_req_flip); REG_SET(FLIP_PARAMETERS_5, 0, REFCYC_PER_PTE_GROUP_FLIP_C, dlg_attr->refcyc_per_pte_group_flip_c); + REG_SET(FLIP_PARAMETERS_6, 0, REFCYC_PER_META_CHUNK_FLIP_C, dlg_attr->refcyc_per_meta_chunk_flip_c); } diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/dsc.h b/drivers/gpu/drm/amd/display/dc/inc/hw/dsc.h index 1ddb1c6fa149..75ecfdc5d5cd 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw/dsc.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw/dsc.h @@ -36,6 +36,7 @@ struct dsc_config { uint32_t pic_height; enum dc_pixel_encoding pixel_encoding; enum dc_color_depth color_depth; /* Bits per component */ + bool is_odm; struct dc_dsc_config dc_dsc_cfg; }; diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c index 3a2a1dc9a786..1b55f037ba4a 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c @@ -3987,6 +3987,13 @@ static int smu7_set_power_state_tasks(struct pp_hwmgr *hwmgr, const void *input) "Failed to populate and upload SCLK MCLK DPM levels!", result = tmp_result); + /* + * If a custom pp table is loaded, set DPMTABLE_OD_UPDATE_VDDC flag. + * That effectively disables AVFS feature. + */ + if (hwmgr->hardcode_pp_table != NULL) + data->need_update_smu7_dpm_table |= DPMTABLE_OD_UPDATE_VDDC; + tmp_result = smu7_update_avfs(hwmgr); PP_ASSERT_WITH_CODE((0 == tmp_result), "Failed to update avfs voltages!", diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c index beacfffbdc3e..ecbc9daea57e 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c @@ -3691,6 +3691,13 @@ static int vega10_set_power_state_tasks(struct pp_hwmgr *hwmgr, PP_ASSERT_WITH_CODE(!result, "Failed to upload PPtable!", return result); + /* + * If a custom pp table is loaded, set DPMTABLE_OD_UPDATE_VDDC flag. + * That effectively disables AVFS feature. + */ + if(hwmgr->hardcode_pp_table != NULL) + data->need_update_dpm_table |= DPMTABLE_OD_UPDATE_VDDC; + vega10_update_avfs(hwmgr); /* diff --git a/drivers/gpu/drm/exynos/exynos_drm_dsi.c b/drivers/gpu/drm/exynos/exynos_drm_dsi.c index 8ed94c994800..b83acd696774 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_dsi.c +++ b/drivers/gpu/drm/exynos/exynos_drm_dsi.c @@ -1741,10 +1741,6 @@ static int exynos_dsi_probe(struct platform_device *pdev) dsi->dev = dev; dsi->driver_data = of_device_get_match_data(dev); - ret = exynos_dsi_parse_dt(dsi); - if (ret) - return ret; - dsi->supplies[0].supply = "vddcore"; dsi->supplies[1].supply = "vddio"; ret = devm_regulator_bulk_get(dev, ARRAY_SIZE(dsi->supplies), @@ -1805,11 +1801,25 @@ static int exynos_dsi_probe(struct platform_device *pdev) return ret; } + ret = exynos_dsi_parse_dt(dsi); + if (ret) + return ret; + platform_set_drvdata(pdev, &dsi->encoder); pm_runtime_enable(dev); - return component_add(dev, &exynos_dsi_component_ops); + ret = component_add(dev, &exynos_dsi_component_ops); + if (ret) + goto err_disable_runtime; + + return 0; + +err_disable_runtime: + pm_runtime_disable(dev); + of_node_put(dsi->in_bridge_node); + + return ret; } static int exynos_dsi_remove(struct platform_device *pdev) diff --git a/drivers/gpu/drm/gma500/cdv_intel_display.c b/drivers/gpu/drm/gma500/cdv_intel_display.c index f56852a503e8..8b784947ed3b 100644 --- a/drivers/gpu/drm/gma500/cdv_intel_display.c +++ b/drivers/gpu/drm/gma500/cdv_intel_display.c @@ -405,6 +405,8 @@ static bool cdv_intel_find_dp_pll(const struct gma_limit_t *limit, struct gma_crtc *gma_crtc = to_gma_crtc(crtc); struct gma_clock_t clock; + memset(&clock, 0, sizeof(clock)); + switch (refclk) { case 27000: if (target < 200000) { diff --git a/drivers/gpu/drm/mcde/mcde_display.c b/drivers/gpu/drm/mcde/mcde_display.c index 751454ae3cd1..28ed50628501 100644 --- a/drivers/gpu/drm/mcde/mcde_display.c +++ b/drivers/gpu/drm/mcde/mcde_display.c @@ -946,6 +946,7 @@ static void mcde_display_disable(struct drm_simple_display_pipe *pipe) struct drm_crtc *crtc = &pipe->crtc; struct drm_device *drm = crtc->dev; struct mcde *mcde = drm->dev_private; + struct drm_pending_vblank_event *event; if (mcde->te_sync) drm_crtc_vblank_off(crtc); @@ -953,6 +954,15 @@ static void mcde_display_disable(struct drm_simple_display_pipe *pipe) /* Disable FIFO A flow */ mcde_disable_fifo(mcde, MCDE_FIFO_A, true); + event = crtc->state->event; + if (event) { + crtc->state->event = NULL; + + spin_lock_irq(&crtc->dev->event_lock); + drm_crtc_send_vblank_event(crtc, event); + spin_unlock_irq(&crtc->dev->event_lock); + } + dev_info(drm->dev, "MCDE display is disabled\n"); } diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c index 24b55103bfe0..c8fb21cc0d6f 100644 --- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c @@ -1414,18 +1414,31 @@ static const struct adreno_gpu_funcs funcs = { static void check_speed_bin(struct device *dev) { struct nvmem_cell *cell; - u32 bin, val; + u32 val; + + /* + * If the OPP table specifies a opp-supported-hw property then we have + * to set something with dev_pm_opp_set_supported_hw() or the table + * doesn't get populated so pick an arbitrary value that should + * ensure the default frequencies are selected but not conflict with any + * actual bins + */ + val = 0x80; cell = nvmem_cell_get(dev, "speed_bin"); - /* If a nvmem cell isn't defined, nothing to do */ - if (IS_ERR(cell)) - return; + if (!IS_ERR(cell)) { + void *buf = nvmem_cell_read(cell, NULL); + + if (!IS_ERR(buf)) { + u8 bin = *((u8 *) buf); - bin = *((u32 *) nvmem_cell_read(cell, NULL)); - nvmem_cell_put(cell); + val = (1 << bin); + kfree(buf); + } - val = (1 << bin); + nvmem_cell_put(cell); + } dev_pm_opp_set_supported_hw(dev, &val, 1); } diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c index 4558d66761b3..108632a1f243 100644 --- a/drivers/gpu/drm/msm/msm_drv.c +++ b/drivers/gpu/drm/msm/msm_drv.c @@ -444,8 +444,10 @@ static int msm_drm_init(struct device *dev, struct drm_driver *drv) if (!dev->dma_parms) { dev->dma_parms = devm_kzalloc(dev, sizeof(*dev->dma_parms), GFP_KERNEL); - if (!dev->dma_parms) - return -ENOMEM; + if (!dev->dma_parms) { + ret = -ENOMEM; + goto err_msm_uninit; + } } dma_set_max_seg_size(dev, DMA_BIT_MASK(32)); diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.c b/drivers/gpu/drm/nouveau/dispnv50/disp.c index 419a02260bfa..ee2b1e1199e0 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/disp.c +++ b/drivers/gpu/drm/nouveau/dispnv50/disp.c @@ -1032,8 +1032,10 @@ nv50_mstc_detect(struct drm_connector *connector, bool force) return connector_status_disconnected; ret = pm_runtime_get_sync(connector->dev->dev); - if (ret < 0 && ret != -EACCES) + if (ret < 0 && ret != -EACCES) { + pm_runtime_put_autosuspend(connector->dev->dev); return connector_status_disconnected; + } conn_status = drm_dp_mst_detect_port(connector, mstc->port->mgr, mstc->port); diff --git a/drivers/gpu/drm/nouveau/nouveau_debugfs.c b/drivers/gpu/drm/nouveau/nouveau_debugfs.c index 5c314f135dd1..3b13feca970f 100644 --- a/drivers/gpu/drm/nouveau/nouveau_debugfs.c +++ b/drivers/gpu/drm/nouveau/nouveau_debugfs.c @@ -183,8 +183,11 @@ nouveau_debugfs_pstate_set(struct file *file, const char __user *ubuf, } ret = pm_runtime_get_sync(drm->dev); - if (ret < 0 && ret != -EACCES) + if (ret < 0 && ret != -EACCES) { + pm_runtime_put_autosuspend(drm->dev); return ret; + } + ret = nvif_mthd(ctrl, NVIF_CONTROL_PSTATE_USER, &args, sizeof(args)); pm_runtime_put_autosuspend(drm->dev); if (ret < 0) diff --git a/drivers/gpu/drm/nouveau/nouveau_gem.c b/drivers/gpu/drm/nouveau/nouveau_gem.c index fbfe25422774..7d39d4949ee7 100644 --- a/drivers/gpu/drm/nouveau/nouveau_gem.c +++ b/drivers/gpu/drm/nouveau/nouveau_gem.c @@ -78,8 +78,10 @@ nouveau_gem_object_open(struct drm_gem_object *gem, struct drm_file *file_priv) return ret; ret = pm_runtime_get_sync(dev); - if (ret < 0 && ret != -EACCES) + if (ret < 0 && ret != -EACCES) { + pm_runtime_put_autosuspend(dev); goto out; + } ret = nouveau_vma_new(nvbo, vmm, &vma); pm_runtime_mark_last_busy(dev); diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadowpci.c b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadowpci.c index 9b91da09dc5f..8d9812a51ef6 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadowpci.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadowpci.c @@ -101,9 +101,13 @@ platform_init(struct nvkm_bios *bios, const char *name) else return ERR_PTR(-ENODEV); + if (!pdev->rom || pdev->romlen == 0) + return ERR_PTR(-ENODEV); + if ((priv = kmalloc(sizeof(*priv), GFP_KERNEL))) { + priv->size = pdev->romlen; if (ret = -ENODEV, - (priv->rom = pci_platform_rom(pdev, &priv->size))) + (priv->rom = ioremap(pdev->rom, pdev->romlen))) return priv; kfree(priv); } @@ -111,11 +115,20 @@ platform_init(struct nvkm_bios *bios, const char *name) return ERR_PTR(ret); } +static void +platform_fini(void *data) +{ + struct priv *priv = data; + + iounmap(priv->rom); + kfree(priv); +} + const struct nvbios_source nvbios_platform = { .name = "PLATFORM", .init = platform_init, - .fini = (void(*)(void *))kfree, + .fini = platform_fini, .read = pcirom_read, .rw = true, }; diff --git a/drivers/gpu/drm/omapdrm/dss/dss.c b/drivers/gpu/drm/omapdrm/dss/dss.c index 4bdd63b57100..ac93dae2a9c8 100644 --- a/drivers/gpu/drm/omapdrm/dss/dss.c +++ b/drivers/gpu/drm/omapdrm/dss/dss.c @@ -1151,46 +1151,38 @@ static const struct dss_features dra7xx_dss_feats = { .has_lcd_clk_src = true, }; -static int dss_init_ports(struct dss_device *dss) +static void __dss_uninit_ports(struct dss_device *dss, unsigned int num_ports) { struct platform_device *pdev = dss->pdev; struct device_node *parent = pdev->dev.of_node; struct device_node *port; unsigned int i; - int r; - for (i = 0; i < dss->feat->num_ports; i++) { + for (i = 0; i < num_ports; i++) { port = of_graph_get_port_by_id(parent, i); if (!port) continue; switch (dss->feat->ports[i]) { case OMAP_DISPLAY_TYPE_DPI: - r = dpi_init_port(dss, pdev, port, dss->feat->model); - if (r) - return r; + dpi_uninit_port(port); break; - case OMAP_DISPLAY_TYPE_SDI: - r = sdi_init_port(dss, pdev, port); - if (r) - return r; + sdi_uninit_port(port); break; - default: break; } } - - return 0; } -static void dss_uninit_ports(struct dss_device *dss) +static int dss_init_ports(struct dss_device *dss) { struct platform_device *pdev = dss->pdev; struct device_node *parent = pdev->dev.of_node; struct device_node *port; - int i; + unsigned int i; + int r; for (i = 0; i < dss->feat->num_ports; i++) { port = of_graph_get_port_by_id(parent, i); @@ -1199,15 +1191,32 @@ static void dss_uninit_ports(struct dss_device *dss) switch (dss->feat->ports[i]) { case OMAP_DISPLAY_TYPE_DPI: - dpi_uninit_port(port); + r = dpi_init_port(dss, pdev, port, dss->feat->model); + if (r) + goto error; break; + case OMAP_DISPLAY_TYPE_SDI: - sdi_uninit_port(port); + r = sdi_init_port(dss, pdev, port); + if (r) + goto error; break; + default: break; } } + + return 0; + +error: + __dss_uninit_ports(dss, i); + return r; +} + +static void dss_uninit_ports(struct dss_device *dss) +{ + __dss_uninit_ports(dss, dss->feat->num_ports); } static int dss_video_pll_probe(struct dss_device *dss) diff --git a/drivers/gpu/drm/omapdrm/dss/omapdss-boot-init.c b/drivers/gpu/drm/omapdrm/dss/omapdss-boot-init.c index 31502857f013..ce67891eedd4 100644 --- a/drivers/gpu/drm/omapdrm/dss/omapdss-boot-init.c +++ b/drivers/gpu/drm/omapdrm/dss/omapdss-boot-init.c @@ -192,7 +192,7 @@ static int __init omapdss_boot_init(void) dss = of_find_matching_node(NULL, omapdss_of_match); if (dss == NULL || !of_device_is_available(dss)) - return 0; + goto put_node; omapdss_walk_device(dss, true); @@ -217,6 +217,8 @@ static int __init omapdss_boot_init(void) kfree(n); } +put_node: + of_node_put(dss); return 0; } diff --git a/drivers/gpu/drm/radeon/radeon_bios.c b/drivers/gpu/drm/radeon/radeon_bios.c index 4d1490fbb075..756a50e8aff2 100644 --- a/drivers/gpu/drm/radeon/radeon_bios.c +++ b/drivers/gpu/drm/radeon/radeon_bios.c @@ -108,25 +108,33 @@ static bool radeon_read_bios(struct radeon_device *rdev) static bool radeon_read_platform_bios(struct radeon_device *rdev) { - uint8_t __iomem *bios; - size_t size; + phys_addr_t rom = rdev->pdev->rom; + size_t romlen = rdev->pdev->romlen; + void __iomem *bios; rdev->bios = NULL; - bios = pci_platform_rom(rdev->pdev, &size); - if (!bios) { + if (!rom || romlen == 0) return false; - } - if (size == 0 || bios[0] != 0x55 || bios[1] != 0xaa) { + rdev->bios = kzalloc(romlen, GFP_KERNEL); + if (!rdev->bios) return false; - } - rdev->bios = kmemdup(bios, size, GFP_KERNEL); - if (rdev->bios == NULL) { - return false; - } + + bios = ioremap(rom, romlen); + if (!bios) + goto free_bios; + + memcpy_fromio(rdev->bios, bios, romlen); + iounmap(bios); + + if (rdev->bios[0] != 0x55 || rdev->bios[1] != 0xaa) + goto free_bios; return true; +free_bios: + kfree(rdev->bios); + return false; } #ifdef CONFIG_ACPI diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c index 30c5ddd6d081..134e9106ebac 100644 --- a/drivers/gpu/drm/scheduler/sched_main.c +++ b/drivers/gpu/drm/scheduler/sched_main.c @@ -284,10 +284,21 @@ static void drm_sched_job_timedout(struct work_struct *work) unsigned long flags; sched = container_of(work, struct drm_gpu_scheduler, work_tdr.work); + + /* Protects against concurrent deletion in drm_sched_get_cleanup_job */ + spin_lock_irqsave(&sched->job_list_lock, flags); job = list_first_entry_or_null(&sched->ring_mirror_list, struct drm_sched_job, node); if (job) { + /* + * Remove the bad job so it cannot be freed by concurrent + * drm_sched_cleanup_jobs. It will be reinserted back after sched->thread + * is parked at which point it's safe. + */ + list_del_init(&job->node); + spin_unlock_irqrestore(&sched->job_list_lock, flags); + job->sched->ops->timedout_job(job); /* @@ -298,6 +309,8 @@ static void drm_sched_job_timedout(struct work_struct *work) job->sched->ops->free_job(job); sched->free_guilty = false; } + } else { + spin_unlock_irqrestore(&sched->job_list_lock, flags); } spin_lock_irqsave(&sched->job_list_lock, flags); @@ -369,6 +382,20 @@ void drm_sched_stop(struct drm_gpu_scheduler *sched, struct drm_sched_job *bad) kthread_park(sched->thread); + /* + * Reinsert back the bad job here - now it's safe as + * drm_sched_get_cleanup_job cannot race against us and release the + * bad job at this point - we parked (waited for) any in progress + * (earlier) cleanups and drm_sched_get_cleanup_job will not be called + * now until the scheduler thread is unparked. + */ + if (bad && bad->sched == sched) + /* + * Add at the head of the queue to reflect it was the earliest + * job extracted. + */ + list_add(&bad->node, &sched->ring_mirror_list); + /* * Iterate the job list from later to earlier one and either deactive * their HW callbacks or remove them from mirror list if they already diff --git a/drivers/gpu/drm/sun4i/sun8i_csc.h b/drivers/gpu/drm/sun4i/sun8i_csc.h index f42441b1b14d..a55a38ad849c 100644 --- a/drivers/gpu/drm/sun4i/sun8i_csc.h +++ b/drivers/gpu/drm/sun4i/sun8i_csc.h @@ -12,7 +12,7 @@ struct sun8i_mixer; /* VI channel CSC units offsets */ #define CCSC00_OFFSET 0xAA050 -#define CCSC01_OFFSET 0xFA000 +#define CCSC01_OFFSET 0xFA050 #define CCSC10_OFFSET 0xA0000 #define CCSC11_OFFSET 0xF0000 diff --git a/drivers/gpu/drm/vc4/vc4_hdmi.c b/drivers/gpu/drm/vc4/vc4_hdmi.c index d5f5ba410524..54435b72b761 100644 --- a/drivers/gpu/drm/vc4/vc4_hdmi.c +++ b/drivers/gpu/drm/vc4/vc4_hdmi.c @@ -1125,6 +1125,7 @@ static int vc4_hdmi_audio_init(struct vc4_hdmi *hdmi) card->num_links = 1; card->name = "vc4-hdmi"; card->dev = dev; + card->owner = THIS_MODULE; /* * Be careful, snd_soc_register_card() calls dev_set_drvdata() and diff --git a/drivers/hwtracing/coresight/coresight-etm4x.c b/drivers/hwtracing/coresight/coresight-etm4x.c index a128b5063f46..83dccdeef906 100644 --- a/drivers/hwtracing/coresight/coresight-etm4x.c +++ b/drivers/hwtracing/coresight/coresight-etm4x.c @@ -1184,6 +1184,7 @@ static int etm4_probe(struct amba_device *adev, const struct amba_id *id) return 0; err_arch_supported: + etmdrvdata[drvdata->cpu] = NULL; if (--etm4_count == 0) { cpuhp_remove_state_nocalls(CPUHP_AP_ARM_CORESIGHT_STARTING); if (hp_online) diff --git a/drivers/hwtracing/intel_th/intel_th.h b/drivers/hwtracing/intel_th/intel_th.h index 6f4f5486fe6d..5fe694708b7a 100644 --- a/drivers/hwtracing/intel_th/intel_th.h +++ b/drivers/hwtracing/intel_th/intel_th.h @@ -47,11 +47,13 @@ struct intel_th_output { /** * struct intel_th_drvdata - describes hardware capabilities and quirks * @tscu_enable: device needs SW to enable time stamping unit + * @multi_is_broken: device has multiblock mode is broken * @has_mintctl: device has interrupt control (MINTCTL) register * @host_mode_only: device can only operate in 'host debugger' mode */ struct intel_th_drvdata { unsigned int tscu_enable : 1, + multi_is_broken : 1, has_mintctl : 1, host_mode_only : 1; }; diff --git a/drivers/hwtracing/intel_th/msu.c b/drivers/hwtracing/intel_th/msu.c index 255f8f41c8ff..3cd2489d398c 100644 --- a/drivers/hwtracing/intel_th/msu.c +++ b/drivers/hwtracing/intel_th/msu.c @@ -157,7 +157,8 @@ struct msc { /* config */ unsigned int enabled : 1, wrap : 1, - do_irq : 1; + do_irq : 1, + multi_is_broken : 1; unsigned int mode; unsigned int burst_len; unsigned int index; @@ -1665,7 +1666,7 @@ static int intel_th_msc_init(struct msc *msc) { atomic_set(&msc->user_count, -1); - msc->mode = MSC_MODE_MULTI; + msc->mode = msc->multi_is_broken ? MSC_MODE_SINGLE : MSC_MODE_MULTI; mutex_init(&msc->buf_mutex); INIT_LIST_HEAD(&msc->win_list); INIT_LIST_HEAD(&msc->iter_list); @@ -1877,6 +1878,9 @@ mode_store(struct device *dev, struct device_attribute *attr, const char *buf, return -EINVAL; found: + if (i == MSC_MODE_MULTI && msc->multi_is_broken) + return -EOPNOTSUPP; + mutex_lock(&msc->buf_mutex); ret = 0; @@ -2083,6 +2087,9 @@ static int intel_th_msc_probe(struct intel_th_device *thdev) if (!res) msc->do_irq = 1; + if (INTEL_TH_CAP(to_intel_th(thdev), multi_is_broken)) + msc->multi_is_broken = 1; + msc->index = thdev->id; msc->thdev = thdev; diff --git a/drivers/hwtracing/intel_th/pci.c b/drivers/hwtracing/intel_th/pci.c index 0d26484d6795..21fdf0b93516 100644 --- a/drivers/hwtracing/intel_th/pci.c +++ b/drivers/hwtracing/intel_th/pci.c @@ -120,6 +120,10 @@ static void intel_th_pci_remove(struct pci_dev *pdev) pci_free_irq_vectors(pdev); } +static const struct intel_th_drvdata intel_th_1x_multi_is_broken = { + .multi_is_broken = 1, +}; + static const struct intel_th_drvdata intel_th_2x = { .tscu_enable = 1, .has_mintctl = 1, @@ -152,7 +156,7 @@ static const struct pci_device_id intel_th_pci_id_table[] = { { /* Kaby Lake PCH-H */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xa2a6), - .driver_data = (kernel_ulong_t)0, + .driver_data = (kernel_ulong_t)&intel_th_1x_multi_is_broken, }, { /* Denverton */ @@ -207,7 +211,7 @@ static const struct pci_device_id intel_th_pci_id_table[] = { { /* Comet Lake PCH-V */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xa3a6), - .driver_data = (kernel_ulong_t)&intel_th_2x, + .driver_data = (kernel_ulong_t)&intel_th_1x_multi_is_broken, }, { /* Ice Lake NNPI */ diff --git a/drivers/i2c/busses/i2c-aspeed.c b/drivers/i2c/busses/i2c-aspeed.c index dad6e432de89..bdcc3c9d0abe 100644 --- a/drivers/i2c/busses/i2c-aspeed.c +++ b/drivers/i2c/busses/i2c-aspeed.c @@ -69,6 +69,7 @@ * These share bit definitions, so use the same values for the enable & * status bits. */ +#define ASPEED_I2CD_INTR_RECV_MASK 0xf000ffff #define ASPEED_I2CD_INTR_SDA_DL_TIMEOUT BIT(14) #define ASPEED_I2CD_INTR_BUS_RECOVER_DONE BIT(13) #define ASPEED_I2CD_INTR_SLAVE_MATCH BIT(7) @@ -604,6 +605,7 @@ static irqreturn_t aspeed_i2c_bus_irq(int irq, void *dev_id) writel(irq_received & ~ASPEED_I2CD_INTR_RX_DONE, bus->base + ASPEED_I2C_INTR_STS_REG); readl(bus->base + ASPEED_I2C_INTR_STS_REG); + irq_received &= ASPEED_I2CD_INTR_RECV_MASK; irq_remaining = irq_received; #if IS_ENABLED(CONFIG_I2C_SLAVE) diff --git a/drivers/i2c/busses/i2c-tegra.c b/drivers/i2c/busses/i2c-tegra.c index 331f7cca9bab..db94e96aed77 100644 --- a/drivers/i2c/busses/i2c-tegra.c +++ b/drivers/i2c/busses/i2c-tegra.c @@ -16,6 +16,7 @@ #include <linux/interrupt.h> #include <linux/io.h> #include <linux/iopoll.h> +#include <linux/irq.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/of_device.h> @@ -230,7 +231,6 @@ struct tegra_i2c_hw_feature { * @base_phys: physical base address of the I2C controller * @cont_id: I2C controller ID, used for packet header * @irq: IRQ number of transfer complete interrupt - * @irq_disabled: used to track whether or not the interrupt is enabled * @is_dvc: identifies the DVC I2C controller, has a different register layout * @msg_complete: transfer completion notifier * @msg_err: error code for completed message @@ -240,7 +240,6 @@ struct tegra_i2c_hw_feature { * @bus_clk_rate: current I2C bus clock rate * @clk_divisor_non_hs_mode: clock divider for non-high-speed modes * @is_multimaster_mode: track if I2C controller is in multi-master mode - * @xfer_lock: lock to serialize transfer submission and processing * @tx_dma_chan: DMA transmit channel * @rx_dma_chan: DMA receive channel * @dma_phys: handle to DMA resources @@ -260,7 +259,6 @@ struct tegra_i2c_dev { phys_addr_t base_phys; int cont_id; int irq; - bool irq_disabled; int is_dvc; struct completion msg_complete; int msg_err; @@ -270,8 +268,6 @@ struct tegra_i2c_dev { u32 bus_clk_rate; u16 clk_divisor_non_hs_mode; bool is_multimaster_mode; - /* xfer_lock: lock to serialize transfer submission and processing */ - spinlock_t xfer_lock; struct dma_chan *tx_dma_chan; struct dma_chan *rx_dma_chan; dma_addr_t dma_phys; @@ -790,11 +786,6 @@ static int tegra_i2c_init(struct tegra_i2c_dev *i2c_dev, bool clk_reinit) if (err) return err; - if (i2c_dev->irq_disabled) { - i2c_dev->irq_disabled = false; - enable_irq(i2c_dev->irq); - } - return 0; } @@ -825,18 +816,12 @@ static irqreturn_t tegra_i2c_isr(int irq, void *dev_id) status = i2c_readl(i2c_dev, I2C_INT_STATUS); - spin_lock(&i2c_dev->xfer_lock); if (status == 0) { dev_warn(i2c_dev->dev, "irq status 0 %08x %08x %08x\n", i2c_readl(i2c_dev, I2C_PACKET_TRANSFER_STATUS), i2c_readl(i2c_dev, I2C_STATUS), i2c_readl(i2c_dev, I2C_CNFG)); i2c_dev->msg_err |= I2C_ERR_UNKNOWN_INTERRUPT; - - if (!i2c_dev->irq_disabled) { - disable_irq_nosync(i2c_dev->irq); - i2c_dev->irq_disabled = true; - } goto err; } @@ -925,7 +910,6 @@ static irqreturn_t tegra_i2c_isr(int irq, void *dev_id) complete(&i2c_dev->msg_complete); done: - spin_unlock(&i2c_dev->xfer_lock); return IRQ_HANDLED; } @@ -999,6 +983,30 @@ static void tegra_i2c_config_fifo_trig(struct tegra_i2c_dev *i2c_dev, i2c_writel(i2c_dev, val, reg); } +static unsigned long +tegra_i2c_wait_completion_timeout(struct tegra_i2c_dev *i2c_dev, + struct completion *complete, + unsigned int timeout_ms) +{ + unsigned long ret; + + enable_irq(i2c_dev->irq); + ret = wait_for_completion_timeout(complete, + msecs_to_jiffies(timeout_ms)); + disable_irq(i2c_dev->irq); + + /* + * There is a chance that completion may happen after IRQ + * synchronization, which is done by disable_irq(). + */ + if (ret == 0 && completion_done(complete)) { + dev_warn(i2c_dev->dev, "completion done after timeout\n"); + ret = 1; + } + + return ret; +} + static int tegra_i2c_issue_bus_clear(struct i2c_adapter *adap) { struct tegra_i2c_dev *i2c_dev = i2c_get_adapdata(adap); @@ -1020,8 +1028,8 @@ static int tegra_i2c_issue_bus_clear(struct i2c_adapter *adap) i2c_writel(i2c_dev, reg, I2C_BUS_CLEAR_CNFG); tegra_i2c_unmask_irq(i2c_dev, I2C_INT_BUS_CLR_DONE); - time_left = wait_for_completion_timeout(&i2c_dev->msg_complete, - msecs_to_jiffies(50)); + time_left = tegra_i2c_wait_completion_timeout( + i2c_dev, &i2c_dev->msg_complete, 50); if (time_left == 0) { dev_err(i2c_dev->dev, "timed out for bus clear\n"); return -ETIMEDOUT; @@ -1044,7 +1052,6 @@ static int tegra_i2c_xfer_msg(struct tegra_i2c_dev *i2c_dev, u32 packet_header; u32 int_mask; unsigned long time_left; - unsigned long flags; size_t xfer_size; u32 *buffer = NULL; int err = 0; @@ -1075,7 +1082,6 @@ static int tegra_i2c_xfer_msg(struct tegra_i2c_dev *i2c_dev, */ xfer_time += DIV_ROUND_CLOSEST(((xfer_size * 9) + 2) * MSEC_PER_SEC, i2c_dev->bus_clk_rate); - spin_lock_irqsave(&i2c_dev->xfer_lock, flags); int_mask = I2C_INT_NO_ACK | I2C_INT_ARBITRATION_LOST; tegra_i2c_unmask_irq(i2c_dev, int_mask); @@ -1090,7 +1096,7 @@ static int tegra_i2c_xfer_msg(struct tegra_i2c_dev *i2c_dev, dev_err(i2c_dev->dev, "starting RX DMA failed, err %d\n", err); - goto unlock; + return err; } } else { @@ -1149,7 +1155,7 @@ static int tegra_i2c_xfer_msg(struct tegra_i2c_dev *i2c_dev, dev_err(i2c_dev->dev, "starting TX DMA failed, err %d\n", err); - goto unlock; + return err; } } else { tegra_i2c_fill_tx_fifo(i2c_dev); @@ -1169,15 +1175,10 @@ static int tegra_i2c_xfer_msg(struct tegra_i2c_dev *i2c_dev, dev_dbg(i2c_dev->dev, "unmasked irq: %02x\n", i2c_readl(i2c_dev, I2C_INT_MASK)); -unlock: - spin_unlock_irqrestore(&i2c_dev->xfer_lock, flags); - if (dma) { - if (err) - return err; + time_left = tegra_i2c_wait_completion_timeout( + i2c_dev, &i2c_dev->dma_complete, xfer_time); - time_left = wait_for_completion_timeout(&i2c_dev->dma_complete, - msecs_to_jiffies(xfer_time)); if (time_left == 0) { dev_err(i2c_dev->dev, "DMA transfer timeout\n"); dmaengine_terminate_sync(i2c_dev->msg_read ? @@ -1202,13 +1203,13 @@ static int tegra_i2c_xfer_msg(struct tegra_i2c_dev *i2c_dev, i2c_dev->tx_dma_chan); } - time_left = wait_for_completion_timeout(&i2c_dev->msg_complete, - msecs_to_jiffies(xfer_time)); + time_left = tegra_i2c_wait_completion_timeout( + i2c_dev, &i2c_dev->msg_complete, xfer_time); + tegra_i2c_mask_irq(i2c_dev, int_mask); if (time_left == 0) { dev_err(i2c_dev->dev, "i2c transfer timed out\n"); - tegra_i2c_init(i2c_dev, true); return -ETIMEDOUT; } @@ -1568,7 +1569,6 @@ static int tegra_i2c_probe(struct platform_device *pdev) I2C_PACKET_HEADER_SIZE; init_completion(&i2c_dev->msg_complete); init_completion(&i2c_dev->dma_complete); - spin_lock_init(&i2c_dev->xfer_lock); if (!i2c_dev->hw->has_single_clk_source) { fast_clk = devm_clk_get(&pdev->dev, "fast-clk"); @@ -1644,6 +1644,8 @@ static int tegra_i2c_probe(struct platform_device *pdev) goto release_dma; } + irq_set_status_flags(i2c_dev->irq, IRQ_NOAUTOEN); + ret = devm_request_irq(&pdev->dev, i2c_dev->irq, tegra_i2c_isr, 0, dev_name(&pdev->dev), i2c_dev); if (ret) { @@ -1719,10 +1721,14 @@ static int tegra_i2c_remove(struct platform_device *pdev) static int __maybe_unused tegra_i2c_suspend(struct device *dev) { struct tegra_i2c_dev *i2c_dev = dev_get_drvdata(dev); + int err = 0; i2c_mark_adapter_suspended(&i2c_dev->adapter); - return 0; + if (!pm_runtime_status_suspended(dev)) + err = tegra_i2c_runtime_suspend(dev); + + return err; } static int __maybe_unused tegra_i2c_resume(struct device *dev) @@ -1730,6 +1736,10 @@ static int __maybe_unused tegra_i2c_resume(struct device *dev) struct tegra_i2c_dev *i2c_dev = dev_get_drvdata(dev); int err; + /* + * We need to ensure that clocks are enabled so that registers can be + * restored in tegra_i2c_init(). + */ err = tegra_i2c_runtime_resume(dev); if (err) return err; @@ -1738,9 +1748,16 @@ static int __maybe_unused tegra_i2c_resume(struct device *dev) if (err) return err; - err = tegra_i2c_runtime_suspend(dev); - if (err) - return err; + /* + * In case we are runtime suspended, disable clocks again so that we + * don't unbalance the clock reference counts during the next runtime + * resume transition. + */ + if (pm_runtime_status_suspended(dev)) { + err = tegra_i2c_runtime_suspend(dev); + if (err) + return err; + } i2c_mark_adapter_resumed(&i2c_dev->adapter); diff --git a/drivers/i2c/i2c-core-base.c b/drivers/i2c/i2c-core-base.c index def62d5b42ca..2dfe2ffcf882 100644 --- a/drivers/i2c/i2c-core-base.c +++ b/drivers/i2c/i2c-core-base.c @@ -1385,8 +1385,8 @@ static int i2c_register_adapter(struct i2c_adapter *adap) /* create pre-declared device nodes */ of_i2c_register_devices(adap); - i2c_acpi_register_devices(adap); i2c_acpi_install_space_handler(adap); + i2c_acpi_register_devices(adap); if (adap->nr < __i2c_first_dynamic_bus_num) i2c_scan_static_board_info(adap); diff --git a/drivers/infiniband/core/cm.c b/drivers/infiniband/core/cm.c index 09af96ec41dd..c1d6a068f50f 100644 --- a/drivers/infiniband/core/cm.c +++ b/drivers/infiniband/core/cm.c @@ -1092,14 +1092,22 @@ static void cm_destroy_id(struct ib_cm_id *cm_id, int err) break; } - spin_lock_irq(&cm.lock); + spin_lock_irq(&cm_id_priv->lock); + spin_lock(&cm.lock); + /* Required for cleanup paths related cm_req_handler() */ + if (cm_id_priv->timewait_info) { + cm_cleanup_timewait(cm_id_priv->timewait_info); + kfree(cm_id_priv->timewait_info); + cm_id_priv->timewait_info = NULL; + } if (!list_empty(&cm_id_priv->altr_list) && (!cm_id_priv->altr_send_port_not_ready)) list_del(&cm_id_priv->altr_list); if (!list_empty(&cm_id_priv->prim_list) && (!cm_id_priv->prim_send_port_not_ready)) list_del(&cm_id_priv->prim_list); - spin_unlock_irq(&cm.lock); + spin_unlock(&cm.lock); + spin_unlock_irq(&cm_id_priv->lock); cm_free_id(cm_id->local_id); cm_deref_id(cm_id_priv); @@ -1416,7 +1424,7 @@ int ib_send_cm_req(struct ib_cm_id *cm_id, /* Verify that we're not in timewait. */ cm_id_priv = container_of(cm_id, struct cm_id_private, id); spin_lock_irqsave(&cm_id_priv->lock, flags); - if (cm_id->state != IB_CM_IDLE) { + if (cm_id->state != IB_CM_IDLE || WARN_ON(cm_id_priv->timewait_info)) { spin_unlock_irqrestore(&cm_id_priv->lock, flags); ret = -EINVAL; goto out; @@ -1434,12 +1442,12 @@ int ib_send_cm_req(struct ib_cm_id *cm_id, param->ppath_sgid_attr, &cm_id_priv->av, cm_id_priv); if (ret) - goto error1; + goto out; if (param->alternate_path) { ret = cm_init_av_by_path(param->alternate_path, NULL, &cm_id_priv->alt_av, cm_id_priv); if (ret) - goto error1; + goto out; } cm_id->service_id = param->service_id; cm_id->service_mask = ~cpu_to_be64(0); @@ -1457,7 +1465,7 @@ int ib_send_cm_req(struct ib_cm_id *cm_id, ret = cm_alloc_msg(cm_id_priv, &cm_id_priv->msg); if (ret) - goto error1; + goto out; req_msg = (struct cm_req_msg *) cm_id_priv->msg->mad; cm_format_req(req_msg, cm_id_priv, param); @@ -1480,7 +1488,6 @@ int ib_send_cm_req(struct ib_cm_id *cm_id, return 0; error2: cm_free_msg(cm_id_priv->msg); -error1: kfree(cm_id_priv->timewait_info); out: return ret; } EXPORT_SYMBOL(ib_send_cm_req); @@ -1965,7 +1972,7 @@ static int cm_req_handler(struct cm_work *work) pr_debug("%s: local_id %d, no listen_cm_id_priv\n", __func__, be32_to_cpu(cm_id->local_id)); ret = -EINVAL; - goto free_timeinfo; + goto destroy; } cm_id_priv->id.cm_handler = listen_cm_id_priv->id.cm_handler; @@ -2050,8 +2057,6 @@ static int cm_req_handler(struct cm_work *work) rejected: atomic_dec(&cm_id_priv->refcount); cm_deref_id(listen_cm_id_priv); -free_timeinfo: - kfree(cm_id_priv->timewait_info); destroy: ib_destroy_cm_id(cm_id); return ret; diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c index 6b4e7235d2f5..30e08bcc9afb 100644 --- a/drivers/infiniband/hw/cxgb4/cm.c +++ b/drivers/infiniband/hw/cxgb4/cm.c @@ -3382,7 +3382,7 @@ int c4iw_connect(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param) if (raddr->sin_addr.s_addr == htonl(INADDR_ANY)) { err = pick_local_ipaddrs(dev, cm_id); if (err) - goto fail2; + goto fail3; } /* find a route */ @@ -3404,7 +3404,7 @@ int c4iw_connect(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param) if (ipv6_addr_type(&raddr6->sin6_addr) == IPV6_ADDR_ANY) { err = pick_local_ip6addrs(dev, cm_id); if (err) - goto fail2; + goto fail3; } /* find a route */ diff --git a/drivers/infiniband/hw/i40iw/i40iw_cm.c b/drivers/infiniband/hw/i40iw/i40iw_cm.c index b1df93b69df4..fa7a5ff498c7 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_cm.c +++ b/drivers/infiniband/hw/i40iw/i40iw_cm.c @@ -2074,9 +2074,9 @@ static int i40iw_addr_resolve_neigh_ipv6(struct i40iw_device *iwdev, dst = i40iw_get_dst_ipv6(&src_addr, &dst_addr); if (!dst || dst->error) { if (dst) { - dst_release(dst); i40iw_pr_err("ip6_route_output returned dst->error = %d\n", dst->error); + dst_release(dst); } return rc; } diff --git a/drivers/infiniband/hw/qedr/qedr_iw_cm.c b/drivers/infiniband/hw/qedr/qedr_iw_cm.c index a7a926b7b562..6dea49e11f5f 100644 --- a/drivers/infiniband/hw/qedr/qedr_iw_cm.c +++ b/drivers/infiniband/hw/qedr/qedr_iw_cm.c @@ -490,10 +490,10 @@ qedr_addr6_resolve(struct qedr_dev *dev, if ((!dst) || dst->error) { if (dst) { - dst_release(dst); DP_ERR(dev, "ip6_route_output returned dst->error = %d\n", dst->error); + dst_release(dst); } return -EINVAL; } diff --git a/drivers/infiniband/sw/rxe/rxe.c b/drivers/infiniband/sw/rxe/rxe.c index 70c4ea438664..de5f3efe9fcb 100644 --- a/drivers/infiniband/sw/rxe/rxe.c +++ b/drivers/infiniband/sw/rxe/rxe.c @@ -118,6 +118,8 @@ static void rxe_init_device_param(struct rxe_dev *rxe) rxe->attr.max_fast_reg_page_list_len = RXE_MAX_FMR_PAGE_LIST_LEN; rxe->attr.max_pkeys = RXE_MAX_PKEYS; rxe->attr.local_ca_ack_delay = RXE_LOCAL_CA_ACK_DELAY; + addrconf_addr_eui48((unsigned char *)&rxe->attr.sys_image_guid, + rxe->ndev->dev_addr); rxe->max_ucontext = RXE_MAX_UCONTEXT; } diff --git a/drivers/infiniband/sw/rxe/rxe_qp.c b/drivers/infiniband/sw/rxe/rxe_qp.c index e2c6d1cedf41..f85273883794 100644 --- a/drivers/infiniband/sw/rxe/rxe_qp.c +++ b/drivers/infiniband/sw/rxe/rxe_qp.c @@ -592,15 +592,16 @@ int rxe_qp_from_attr(struct rxe_qp *qp, struct ib_qp_attr *attr, int mask, int err; if (mask & IB_QP_MAX_QP_RD_ATOMIC) { - int max_rd_atomic = __roundup_pow_of_two(attr->max_rd_atomic); + int max_rd_atomic = attr->max_rd_atomic ? + roundup_pow_of_two(attr->max_rd_atomic) : 0; qp->attr.max_rd_atomic = max_rd_atomic; atomic_set(&qp->req.rd_atomic, max_rd_atomic); } if (mask & IB_QP_MAX_DEST_RD_ATOMIC) { - int max_dest_rd_atomic = - __roundup_pow_of_two(attr->max_dest_rd_atomic); + int max_dest_rd_atomic = attr->max_dest_rd_atomic ? + roundup_pow_of_two(attr->max_dest_rd_atomic) : 0; qp->attr.max_dest_rd_atomic = max_dest_rd_atomic; diff --git a/drivers/infiniband/ulp/iser/iser_memory.c b/drivers/infiniband/ulp/iser/iser_memory.c index 2cc89a9b9e9b..ea8e611397a3 100644 --- a/drivers/infiniband/ulp/iser/iser_memory.c +++ b/drivers/infiniband/ulp/iser/iser_memory.c @@ -292,12 +292,27 @@ void iser_unreg_mem_fastreg(struct iscsi_iser_task *iser_task, { struct iser_device *device = iser_task->iser_conn->ib_conn.device; struct iser_mem_reg *reg = &iser_task->rdma_reg[cmd_dir]; + struct iser_fr_desc *desc; + struct ib_mr_status mr_status; - if (!reg->mem_h) + desc = reg->mem_h; + if (!desc) return; - device->reg_ops->reg_desc_put(&iser_task->iser_conn->ib_conn, - reg->mem_h); + /* + * The signature MR cannot be invalidated and reused without checking. + * libiscsi calls the check_protection transport handler only if + * SCSI-Response is received. And the signature MR is not checked if + * the task is completed for some other reason like a timeout or error + * handling. That's why we must check the signature MR here before + * putting it to the free pool. + */ + if (unlikely(desc->sig_protected)) { + desc->sig_protected = false; + ib_check_mr_status(desc->rsc.sig_mr, IB_MR_CHECK_SIG_STATUS, + &mr_status); + } + device->reg_ops->reg_desc_put(&iser_task->iser_conn->ib_conn, desc); reg->mem_h = NULL; } diff --git a/drivers/leds/leds-mlxreg.c b/drivers/leds/leds-mlxreg.c index cabe379071a7..82aea1cd0c12 100644 --- a/drivers/leds/leds-mlxreg.c +++ b/drivers/leds/leds-mlxreg.c @@ -228,8 +228,8 @@ static int mlxreg_led_config(struct mlxreg_led_priv_data *priv) brightness = LED_OFF; led_data->base_color = MLXREG_LED_GREEN_SOLID; } - sprintf(led_data->led_cdev_name, "%s:%s", "mlxreg", - data->label); + snprintf(led_data->led_cdev_name, sizeof(led_data->led_cdev_name), + "mlxreg:%s", data->label); led_cdev->name = led_data->led_cdev_name; led_cdev->brightness = brightness; led_cdev->max_brightness = LED_ON; diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h index 217c838a1b40..859567ad3db4 100644 --- a/drivers/md/bcache/bcache.h +++ b/drivers/md/bcache/bcache.h @@ -585,6 +585,7 @@ struct cache_set { */ wait_queue_head_t btree_cache_wait; struct task_struct *btree_cache_alloc_lock; + spinlock_t btree_cannibalize_lock; /* * When we free a btree node, we increment the gen of the bucket the diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c index 46556bde032e..8d06105fc9ff 100644 --- a/drivers/md/bcache/btree.c +++ b/drivers/md/bcache/btree.c @@ -886,15 +886,17 @@ static struct btree *mca_find(struct cache_set *c, struct bkey *k) static int mca_cannibalize_lock(struct cache_set *c, struct btree_op *op) { - struct task_struct *old; - - old = cmpxchg(&c->btree_cache_alloc_lock, NULL, current); - if (old && old != current) { + spin_lock(&c->btree_cannibalize_lock); + if (likely(c->btree_cache_alloc_lock == NULL)) { + c->btree_cache_alloc_lock = current; + } else if (c->btree_cache_alloc_lock != current) { if (op) prepare_to_wait(&c->btree_cache_wait, &op->wait, TASK_UNINTERRUPTIBLE); + spin_unlock(&c->btree_cannibalize_lock); return -EINTR; } + spin_unlock(&c->btree_cannibalize_lock); return 0; } @@ -929,10 +931,12 @@ static struct btree *mca_cannibalize(struct cache_set *c, struct btree_op *op, */ static void bch_cannibalize_unlock(struct cache_set *c) { + spin_lock(&c->btree_cannibalize_lock); if (c->btree_cache_alloc_lock == current) { c->btree_cache_alloc_lock = NULL; wake_up(&c->btree_cache_wait); } + spin_unlock(&c->btree_cannibalize_lock); } static struct btree *mca_alloc(struct cache_set *c, struct btree_op *op, diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c index 2cbfcd99b7ee..63f5ce18311b 100644 --- a/drivers/md/bcache/super.c +++ b/drivers/md/bcache/super.c @@ -1798,6 +1798,7 @@ struct cache_set *bch_cache_set_alloc(struct cache_sb *sb) sema_init(&c->sb_write_mutex, 1); mutex_init(&c->bucket_lock); init_waitqueue_head(&c->btree_cache_wait); + spin_lock_init(&c->btree_cannibalize_lock); init_waitqueue_head(&c->bucket_wait); init_waitqueue_head(&c->gc_wait); sema_init(&c->uuid_write_mutex, 1); diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index edc366075913..13ad79112661 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -922,21 +922,15 @@ bool dm_table_supports_dax(struct dm_table *t, static bool dm_table_does_not_support_partial_completion(struct dm_table *t); -struct verify_rq_based_data { - unsigned sq_count; - unsigned mq_count; -}; - -static int device_is_rq_based(struct dm_target *ti, struct dm_dev *dev, - sector_t start, sector_t len, void *data) +static int device_is_rq_stackable(struct dm_target *ti, struct dm_dev *dev, + sector_t start, sector_t len, void *data) { - struct request_queue *q = bdev_get_queue(dev->bdev); - struct verify_rq_based_data *v = data; + struct block_device *bdev = dev->bdev; + struct request_queue *q = bdev_get_queue(bdev); - if (queue_is_mq(q)) - v->mq_count++; - else - v->sq_count++; + /* request-based cannot stack on partitions! */ + if (bdev != bdev->bd_contains) + return false; return queue_is_mq(q); } @@ -945,7 +939,6 @@ static int dm_table_determine_type(struct dm_table *t) { unsigned i; unsigned bio_based = 0, request_based = 0, hybrid = 0; - struct verify_rq_based_data v = {.sq_count = 0, .mq_count = 0}; struct dm_target *tgt; struct list_head *devices = dm_table_get_devices(t); enum dm_queue_mode live_md_type = dm_get_md_type(t->md); @@ -1049,14 +1042,10 @@ static int dm_table_determine_type(struct dm_table *t) /* Non-request-stackable devices can't be used for request-based dm */ if (!tgt->type->iterate_devices || - !tgt->type->iterate_devices(tgt, device_is_rq_based, &v)) { + !tgt->type->iterate_devices(tgt, device_is_rq_stackable, NULL)) { DMERR("table load rejected: including non-request-stackable devices"); return -EINVAL; } - if (v.sq_count > 0) { - DMERR("table load rejected: not all devices are blk-mq request-stackable"); - return -EINVAL; - } return 0; } diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 63d59e2ed158..667db23f10ee 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -1720,23 +1720,6 @@ static blk_qc_t __process_bio(struct mapped_device *md, struct dm_table *map, return ret; } -static void dm_queue_split(struct mapped_device *md, struct dm_target *ti, struct bio **bio) -{ - unsigned len, sector_count; - - sector_count = bio_sectors(*bio); - len = min_t(sector_t, max_io_len((*bio)->bi_iter.bi_sector, ti), sector_count); - - if (sector_count > len) { - struct bio *split = bio_split(*bio, len, GFP_NOIO, &md->queue->bio_split); - - bio_chain(split, *bio); - trace_block_split(md->queue, split, (*bio)->bi_iter.bi_sector); - generic_make_request(*bio); - *bio = split; - } -} - static blk_qc_t dm_process_bio(struct mapped_device *md, struct dm_table *map, struct bio *bio) { @@ -1764,14 +1747,12 @@ static blk_qc_t dm_process_bio(struct mapped_device *md, if (current->bio_list) { if (is_abnormal_io(bio)) blk_queue_split(md->queue, &bio); - else - dm_queue_split(md, ti, &bio); + /* regular IO is split by __split_and_process_bio */ } if (dm_get_md_type(md) == DM_TYPE_NVME_BIO_BASED) return __process_bio(md, map, bio, ti); - else - return __split_and_process_bio(md, map, bio); + return __split_and_process_bio(md, map, bio); } static blk_qc_t dm_make_request(struct request_queue *q, struct bio *bio) diff --git a/drivers/media/dvb-frontends/tda10071.c b/drivers/media/dvb-frontends/tda10071.c index 1953b00b3e48..685c0ac71819 100644 --- a/drivers/media/dvb-frontends/tda10071.c +++ b/drivers/media/dvb-frontends/tda10071.c @@ -470,10 +470,11 @@ static int tda10071_read_status(struct dvb_frontend *fe, enum fe_status *status) goto error; if (dev->delivery_system == SYS_DVBS) { - dev->dvbv3_ber = buf[0] << 24 | buf[1] << 16 | - buf[2] << 8 | buf[3] << 0; - dev->post_bit_error += buf[0] << 24 | buf[1] << 16 | - buf[2] << 8 | buf[3] << 0; + u32 bit_error = buf[0] << 24 | buf[1] << 16 | + buf[2] << 8 | buf[3] << 0; + + dev->dvbv3_ber = bit_error; + dev->post_bit_error += bit_error; c->post_bit_error.stat[0].scale = FE_SCALE_COUNTER; c->post_bit_error.stat[0].uvalue = dev->post_bit_error; dev->block_error += buf[4] << 8 | buf[5] << 0; diff --git a/drivers/media/i2c/smiapp/smiapp-core.c b/drivers/media/i2c/smiapp/smiapp-core.c index 42805dfbffeb..06edbe8749c6 100644 --- a/drivers/media/i2c/smiapp/smiapp-core.c +++ b/drivers/media/i2c/smiapp/smiapp-core.c @@ -2327,11 +2327,12 @@ smiapp_sysfs_nvm_read(struct device *dev, struct device_attribute *attr, if (rval < 0) { if (rval != -EBUSY && rval != -EAGAIN) pm_runtime_set_active(&client->dev); - pm_runtime_put(&client->dev); + pm_runtime_put_noidle(&client->dev); return -ENODEV; } if (smiapp_read_nvm(sensor, sensor->nvm)) { + pm_runtime_put(&client->dev); dev_err(&client->dev, "nvm read failed\n"); return -ENODEV; } diff --git a/drivers/media/mc/mc-device.c b/drivers/media/mc/mc-device.c index e19df5165e78..da8088351135 100644 --- a/drivers/media/mc/mc-device.c +++ b/drivers/media/mc/mc-device.c @@ -575,6 +575,38 @@ static void media_device_release(struct media_devnode *devnode) dev_dbg(devnode->parent, "Media device released\n"); } +static void __media_device_unregister_entity(struct media_entity *entity) +{ + struct media_device *mdev = entity->graph_obj.mdev; + struct media_link *link, *tmp; + struct media_interface *intf; + unsigned int i; + + ida_free(&mdev->entity_internal_idx, entity->internal_idx); + + /* Remove all interface links pointing to this entity */ + list_for_each_entry(intf, &mdev->interfaces, graph_obj.list) { + list_for_each_entry_safe(link, tmp, &intf->links, list) { + if (link->entity == entity) + __media_remove_intf_link(link); + } + } + + /* Remove all data links that belong to this entity */ + __media_entity_remove_links(entity); + + /* Remove all pads that belong to this entity */ + for (i = 0; i < entity->num_pads; i++) + media_gobj_destroy(&entity->pads[i].graph_obj); + + /* Remove the entity */ + media_gobj_destroy(&entity->graph_obj); + + /* invoke entity_notify callbacks to handle entity removal?? */ + + entity->graph_obj.mdev = NULL; +} + /** * media_device_register_entity - Register an entity with a media device * @mdev: The media device @@ -632,6 +664,7 @@ int __must_check media_device_register_entity(struct media_device *mdev, */ ret = media_graph_walk_init(&new, mdev); if (ret) { + __media_device_unregister_entity(entity); mutex_unlock(&mdev->graph_mutex); return ret; } @@ -644,38 +677,6 @@ int __must_check media_device_register_entity(struct media_device *mdev, } EXPORT_SYMBOL_GPL(media_device_register_entity); -static void __media_device_unregister_entity(struct media_entity *entity) -{ - struct media_device *mdev = entity->graph_obj.mdev; - struct media_link *link, *tmp; - struct media_interface *intf; - unsigned int i; - - ida_free(&mdev->entity_internal_idx, entity->internal_idx); - - /* Remove all interface links pointing to this entity */ - list_for_each_entry(intf, &mdev->interfaces, graph_obj.list) { - list_for_each_entry_safe(link, tmp, &intf->links, list) { - if (link->entity == entity) - __media_remove_intf_link(link); - } - } - - /* Remove all data links that belong to this entity */ - __media_entity_remove_links(entity); - - /* Remove all pads that belong to this entity */ - for (i = 0; i < entity->num_pads; i++) - media_gobj_destroy(&entity->pads[i].graph_obj); - - /* Remove the entity */ - media_gobj_destroy(&entity->graph_obj); - - /* invoke entity_notify callbacks to handle entity removal?? */ - - entity->graph_obj.mdev = NULL; -} - void media_device_unregister_entity(struct media_entity *entity) { struct media_device *mdev = entity->graph_obj.mdev; diff --git a/drivers/media/platform/qcom/venus/vdec.c b/drivers/media/platform/qcom/venus/vdec.c index 59ae7a1e63bc..05b80a66e80e 100644 --- a/drivers/media/platform/qcom/venus/vdec.c +++ b/drivers/media/platform/qcom/venus/vdec.c @@ -987,13 +987,14 @@ static int vdec_stop_capture(struct venus_inst *inst) ret = hfi_session_flush(inst, HFI_FLUSH_OUTPUT); vdec_cancel_dst_buffers(inst); inst->codec_state = VENUS_DEC_STATE_CAPTURE_SETUP; - INIT_LIST_HEAD(&inst->registeredbufs); venus_helper_free_dpb_bufs(inst); break; default: - return 0; + break; } + INIT_LIST_HEAD(&inst->registeredbufs); + return ret; } diff --git a/drivers/media/platform/ti-vpe/cal.c b/drivers/media/platform/ti-vpe/cal.c index 955a49b8e9c0..f06408009a9c 100644 --- a/drivers/media/platform/ti-vpe/cal.c +++ b/drivers/media/platform/ti-vpe/cal.c @@ -678,12 +678,13 @@ static void pix_proc_config(struct cal_ctx *ctx) } static void cal_wr_dma_config(struct cal_ctx *ctx, - unsigned int width) + unsigned int width, unsigned int height) { u32 val; val = reg_read(ctx->dev, CAL_WR_DMA_CTRL(ctx->csi2_port)); set_field(&val, ctx->csi2_port, CAL_WR_DMA_CTRL_CPORT_MASK); + set_field(&val, height, CAL_WR_DMA_CTRL_YSIZE_MASK); set_field(&val, CAL_WR_DMA_CTRL_DTAG_PIX_DAT, CAL_WR_DMA_CTRL_DTAG_MASK); set_field(&val, CAL_WR_DMA_CTRL_MODE_CONST, @@ -1306,7 +1307,8 @@ static int cal_start_streaming(struct vb2_queue *vq, unsigned int count) csi2_lane_config(ctx); csi2_ctx_config(ctx); pix_proc_config(ctx); - cal_wr_dma_config(ctx, ctx->v_fmt.fmt.pix.bytesperline); + cal_wr_dma_config(ctx, ctx->v_fmt.fmt.pix.bytesperline, + ctx->v_fmt.fmt.pix.height); cal_wr_dma_addr(ctx, addr); csi2_ppi_enable(ctx); diff --git a/drivers/media/usb/go7007/go7007-usb.c b/drivers/media/usb/go7007/go7007-usb.c index ff2aa057c1fb..f889c9d740cd 100644 --- a/drivers/media/usb/go7007/go7007-usb.c +++ b/drivers/media/usb/go7007/go7007-usb.c @@ -1044,6 +1044,7 @@ static int go7007_usb_probe(struct usb_interface *intf, struct go7007_usb *usb; const struct go7007_usb_board *board; struct usb_device *usbdev = interface_to_usbdev(intf); + struct usb_host_endpoint *ep; unsigned num_i2c_devs; char *name; int video_pipe, i, v_urb_len; @@ -1140,7 +1141,8 @@ static int go7007_usb_probe(struct usb_interface *intf, if (usb->intr_urb->transfer_buffer == NULL) goto allocfail; - if (go->board_id == GO7007_BOARDID_SENSORAY_2250) + ep = usb->usbdev->ep_in[4]; + if (usb_endpoint_type(&ep->desc) == USB_ENDPOINT_XFER_BULK) usb_fill_bulk_urb(usb->intr_urb, usb->usbdev, usb_rcvbulkpipe(usb->usbdev, 4), usb->intr_urb->transfer_buffer, 2*sizeof(u16), diff --git a/drivers/mfd/mfd-core.c b/drivers/mfd/mfd-core.c index 23276a80e3b4..96d02b6f06fd 100644 --- a/drivers/mfd/mfd-core.c +++ b/drivers/mfd/mfd-core.c @@ -28,6 +28,11 @@ int mfd_cell_enable(struct platform_device *pdev) const struct mfd_cell *cell = mfd_get_cell(pdev); int err = 0; + if (!cell->enable) { + dev_dbg(&pdev->dev, "No .enable() call-back registered\n"); + return 0; + } + /* only call enable hook if the cell wasn't previously enabled */ if (atomic_inc_return(cell->usage_count) == 1) err = cell->enable(pdev); @@ -45,6 +50,11 @@ int mfd_cell_disable(struct platform_device *pdev) const struct mfd_cell *cell = mfd_get_cell(pdev); int err = 0; + if (!cell->disable) { + dev_dbg(&pdev->dev, "No .disable() call-back registered\n"); + return 0; + } + /* only disable if no other clients are using it */ if (atomic_dec_return(cell->usage_count) == 0) err = cell->disable(pdev); diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c index b7159e243323..de14b5845f52 100644 --- a/drivers/mmc/core/mmc.c +++ b/drivers/mmc/core/mmc.c @@ -297,7 +297,7 @@ static void mmc_manage_enhanced_area(struct mmc_card *card, u8 *ext_csd) } } -static void mmc_part_add(struct mmc_card *card, unsigned int size, +static void mmc_part_add(struct mmc_card *card, u64 size, unsigned int part_cfg, char *name, int idx, bool ro, int area_type) { @@ -313,7 +313,7 @@ static void mmc_manage_gp_partitions(struct mmc_card *card, u8 *ext_csd) { int idx; u8 hc_erase_grp_sz, hc_wp_grp_sz; - unsigned int part_size; + u64 part_size; /* * General purpose partition feature support -- @@ -343,8 +343,7 @@ static void mmc_manage_gp_partitions(struct mmc_card *card, u8 *ext_csd) (ext_csd[EXT_CSD_GP_SIZE_MULT + idx * 3 + 1] << 8) + ext_csd[EXT_CSD_GP_SIZE_MULT + idx * 3]; - part_size *= (size_t)(hc_erase_grp_sz * - hc_wp_grp_sz); + part_size *= (hc_erase_grp_sz * hc_wp_grp_sz); mmc_part_add(card, part_size << 19, EXT_CSD_PART_CONFIG_ACC_GP0 + idx, "gp%d", idx, false, @@ -362,7 +361,7 @@ static void mmc_manage_gp_partitions(struct mmc_card *card, u8 *ext_csd) static int mmc_decode_ext_csd(struct mmc_card *card, u8 *ext_csd) { int err = 0, idx; - unsigned int part_size; + u64 part_size; struct device_node *np; bool broken_hpi = false; diff --git a/drivers/mtd/chips/cfi_cmdset_0002.c b/drivers/mtd/chips/cfi_cmdset_0002.c index a4f2d8cdca12..c8b9ab40a102 100644 --- a/drivers/mtd/chips/cfi_cmdset_0002.c +++ b/drivers/mtd/chips/cfi_cmdset_0002.c @@ -794,7 +794,6 @@ static struct mtd_info *cfi_amdstd_setup(struct mtd_info *mtd) kfree(mtd->eraseregions); kfree(mtd); kfree(cfi->cmdset_priv); - kfree(cfi->cfiq); return NULL; } diff --git a/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c b/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c index b9d5d55a5edb..ef89947ee319 100644 --- a/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c +++ b/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c @@ -540,8 +540,10 @@ static int bch_set_geometry(struct gpmi_nand_data *this) return ret; ret = pm_runtime_get_sync(this->dev); - if (ret < 0) + if (ret < 0) { + pm_runtime_put_autosuspend(this->dev); return ret; + } /* * Due to erratum #2847 of the MX23, the BCH cannot be soft reset on this diff --git a/drivers/mtd/nand/raw/omap_elm.c b/drivers/mtd/nand/raw/omap_elm.c index 5502ffbdd1e6..6e0e31eab7cc 100644 --- a/drivers/mtd/nand/raw/omap_elm.c +++ b/drivers/mtd/nand/raw/omap_elm.c @@ -411,6 +411,7 @@ static int elm_probe(struct platform_device *pdev) pm_runtime_enable(&pdev->dev); if (pm_runtime_get_sync(&pdev->dev) < 0) { ret = -EINVAL; + pm_runtime_put_sync(&pdev->dev); pm_runtime_disable(&pdev->dev); dev_err(&pdev->dev, "can't enable clock\n"); return ret; diff --git a/drivers/mtd/parsers/cmdlinepart.c b/drivers/mtd/parsers/cmdlinepart.c index c86f2db8c882..0625b25620ca 100644 --- a/drivers/mtd/parsers/cmdlinepart.c +++ b/drivers/mtd/parsers/cmdlinepart.c @@ -218,12 +218,29 @@ static int mtdpart_setup_real(char *s) struct cmdline_mtd_partition *this_mtd; struct mtd_partition *parts; int mtd_id_len, num_parts; - char *p, *mtd_id; + char *p, *mtd_id, *semicol; + + /* + * Replace the first ';' by a NULL char so strrchr can work + * properly. + */ + semicol = strchr(s, ';'); + if (semicol) + *semicol = '\0'; mtd_id = s; - /* fetch <mtd-id> */ - p = strchr(s, ':'); + /* + * fetch <mtd-id>. We use strrchr to ignore all ':' that could + * be present in the MTD name, only the last one is interpreted + * as an <mtd-id>/<part-definition> separator. + */ + p = strrchr(s, ':'); + + /* Restore the ';' now. */ + if (semicol) + *semicol = ';'; + if (!p) { pr_err("no mtd-id\n"); return -EINVAL; diff --git a/drivers/mtd/ubi/fastmap-wl.c b/drivers/mtd/ubi/fastmap-wl.c index c44c8470247e..b486250923c5 100644 --- a/drivers/mtd/ubi/fastmap-wl.c +++ b/drivers/mtd/ubi/fastmap-wl.c @@ -39,6 +39,13 @@ static struct ubi_wl_entry *find_anchor_wl_entry(struct rb_root *root) return victim; } +static inline void return_unused_peb(struct ubi_device *ubi, + struct ubi_wl_entry *e) +{ + wl_tree_add(e, &ubi->free); + ubi->free_count++; +} + /** * return_unused_pool_pebs - returns unused PEB to the free tree. * @ubi: UBI device description object @@ -52,23 +59,10 @@ static void return_unused_pool_pebs(struct ubi_device *ubi, for (i = pool->used; i < pool->size; i++) { e = ubi->lookuptbl[pool->pebs[i]]; - wl_tree_add(e, &ubi->free); - ubi->free_count++; + return_unused_peb(ubi, e); } } -static int anchor_pebs_available(struct rb_root *root) -{ - struct rb_node *p; - struct ubi_wl_entry *e; - - ubi_rb_for_each_entry(p, e, root, u.rb) - if (e->pnum < UBI_FM_MAX_START) - return 1; - - return 0; -} - /** * ubi_wl_get_fm_peb - find a physical erase block with a given maximal number. * @ubi: UBI device description object @@ -277,8 +271,26 @@ static struct ubi_wl_entry *get_peb_for_wl(struct ubi_device *ubi) int ubi_ensure_anchor_pebs(struct ubi_device *ubi) { struct ubi_work *wrk; + struct ubi_wl_entry *anchor; spin_lock(&ubi->wl_lock); + + /* Do we already have an anchor? */ + if (ubi->fm_anchor) { + spin_unlock(&ubi->wl_lock); + return 0; + } + + /* See if we can find an anchor PEB on the list of free PEBs */ + anchor = ubi_wl_get_fm_peb(ubi, 1); + if (anchor) { + ubi->fm_anchor = anchor; + spin_unlock(&ubi->wl_lock); + return 0; + } + + /* No luck, trigger wear leveling to produce a new anchor PEB */ + ubi->fm_do_produce_anchor = 1; if (ubi->wl_scheduled) { spin_unlock(&ubi->wl_lock); return 0; @@ -294,7 +306,6 @@ int ubi_ensure_anchor_pebs(struct ubi_device *ubi) return -ENOMEM; } - wrk->anchor = 1; wrk->func = &wear_leveling_worker; __schedule_ubi_work(ubi, wrk); return 0; @@ -356,6 +367,11 @@ static void ubi_fastmap_close(struct ubi_device *ubi) return_unused_pool_pebs(ubi, &ubi->fm_pool); return_unused_pool_pebs(ubi, &ubi->fm_wl_pool); + if (ubi->fm_anchor) { + return_unused_peb(ubi, ubi->fm_anchor); + ubi->fm_anchor = NULL; + } + if (ubi->fm) { for (i = 0; i < ubi->fm->used_blocks; i++) kfree(ubi->fm->e[i]); diff --git a/drivers/mtd/ubi/fastmap.c b/drivers/mtd/ubi/fastmap.c index 604772fc4a96..53f448e7433a 100644 --- a/drivers/mtd/ubi/fastmap.c +++ b/drivers/mtd/ubi/fastmap.c @@ -1543,14 +1543,6 @@ int ubi_update_fastmap(struct ubi_device *ubi) return 0; } - ret = ubi_ensure_anchor_pebs(ubi); - if (ret) { - up_write(&ubi->fm_eba_sem); - up_write(&ubi->work_sem); - up_write(&ubi->fm_protect); - return ret; - } - new_fm = kzalloc(sizeof(*new_fm), GFP_KERNEL); if (!new_fm) { up_write(&ubi->fm_eba_sem); @@ -1621,7 +1613,8 @@ int ubi_update_fastmap(struct ubi_device *ubi) } spin_lock(&ubi->wl_lock); - tmp_e = ubi_wl_get_fm_peb(ubi, 1); + tmp_e = ubi->fm_anchor; + ubi->fm_anchor = NULL; spin_unlock(&ubi->wl_lock); if (old_fm) { @@ -1673,6 +1666,9 @@ int ubi_update_fastmap(struct ubi_device *ubi) up_write(&ubi->work_sem); up_write(&ubi->fm_protect); kfree(old_fm); + + ubi_ensure_anchor_pebs(ubi); + return ret; err: diff --git a/drivers/mtd/ubi/ubi.h b/drivers/mtd/ubi/ubi.h index 721b6aa7936c..a173eb707bdd 100644 --- a/drivers/mtd/ubi/ubi.h +++ b/drivers/mtd/ubi/ubi.h @@ -491,6 +491,8 @@ struct ubi_debug_info { * @fm_work: fastmap work queue * @fm_work_scheduled: non-zero if fastmap work was scheduled * @fast_attach: non-zero if UBI was attached by fastmap + * @fm_anchor: The next anchor PEB to use for fastmap + * @fm_do_produce_anchor: If true produce an anchor PEB in wl * * @used: RB-tree of used physical eraseblocks * @erroneous: RB-tree of erroneous used physical eraseblocks @@ -599,6 +601,8 @@ struct ubi_device { struct work_struct fm_work; int fm_work_scheduled; int fast_attach; + struct ubi_wl_entry *fm_anchor; + int fm_do_produce_anchor; /* Wear-leveling sub-system's stuff */ struct rb_root used; @@ -789,7 +793,6 @@ struct ubi_attach_info { * @vol_id: the volume ID on which this erasure is being performed * @lnum: the logical eraseblock number * @torture: if the physical eraseblock has to be tortured - * @anchor: produce a anchor PEB to by used by fastmap * * The @func pointer points to the worker function. If the @shutdown argument is * not zero, the worker has to free the resources and exit immediately as the @@ -805,7 +808,6 @@ struct ubi_work { int vol_id; int lnum; int torture; - int anchor; }; #include "debug.h" diff --git a/drivers/mtd/ubi/wl.c b/drivers/mtd/ubi/wl.c index 3fcdefe2714d..5d77a38dba54 100644 --- a/drivers/mtd/ubi/wl.c +++ b/drivers/mtd/ubi/wl.c @@ -339,13 +339,6 @@ static struct ubi_wl_entry *find_wl_entry(struct ubi_device *ubi, } } - /* If no fastmap has been written and this WL entry can be used - * as anchor PEB, hold it back and return the second best WL entry - * such that fastmap can use the anchor PEB later. */ - if (prev_e && !ubi->fm_disabled && - !ubi->fm && e->pnum < UBI_FM_MAX_START) - return prev_e; - return e; } @@ -656,9 +649,6 @@ static int wear_leveling_worker(struct ubi_device *ubi, struct ubi_work *wrk, { int err, scrubbing = 0, torture = 0, protect = 0, erroneous = 0; int erase = 0, keep = 0, vol_id = -1, lnum = -1; -#ifdef CONFIG_MTD_UBI_FASTMAP - int anchor = wrk->anchor; -#endif struct ubi_wl_entry *e1, *e2; struct ubi_vid_io_buf *vidb; struct ubi_vid_hdr *vid_hdr; @@ -698,11 +688,7 @@ static int wear_leveling_worker(struct ubi_device *ubi, struct ubi_work *wrk, } #ifdef CONFIG_MTD_UBI_FASTMAP - /* Check whether we need to produce an anchor PEB */ - if (!anchor) - anchor = !anchor_pebs_available(&ubi->free); - - if (anchor) { + if (ubi->fm_do_produce_anchor) { e1 = find_anchor_wl_entry(&ubi->used); if (!e1) goto out_cancel; @@ -719,6 +705,7 @@ static int wear_leveling_worker(struct ubi_device *ubi, struct ubi_work *wrk, self_check_in_wl_tree(ubi, e1, &ubi->used); rb_erase(&e1->u.rb, &ubi->used); dbg_wl("anchor-move PEB %d to PEB %d", e1->pnum, e2->pnum); + ubi->fm_do_produce_anchor = 0; } else if (!ubi->scrub.rb_node) { #else if (!ubi->scrub.rb_node) { @@ -1051,7 +1038,6 @@ static int ensure_wear_leveling(struct ubi_device *ubi, int nested) goto out_cancel; } - wrk->anchor = 0; wrk->func = &wear_leveling_worker; if (nested) __schedule_ubi_work(ubi, wrk); @@ -1093,8 +1079,15 @@ static int __erase_worker(struct ubi_device *ubi, struct ubi_work *wl_wrk) err = sync_erase(ubi, e, wl_wrk->torture); if (!err) { spin_lock(&ubi->wl_lock); - wl_tree_add(e, &ubi->free); - ubi->free_count++; + + if (!ubi->fm_anchor && e->pnum < UBI_FM_MAX_START) { + ubi->fm_anchor = e; + ubi->fm_do_produce_anchor = 0; + } else { + wl_tree_add(e, &ubi->free); + ubi->free_count++; + } + spin_unlock(&ubi->wl_lock); /* @@ -1882,6 +1875,9 @@ int ubi_wl_init(struct ubi_device *ubi, struct ubi_attach_info *ai) if (err) goto out_free; +#ifdef CONFIG_MTD_UBI_FASTMAP + ubi_ensure_anchor_pebs(ubi); +#endif return 0; out_free: diff --git a/drivers/mtd/ubi/wl.h b/drivers/mtd/ubi/wl.h index a9e2d669acd8..c93a53293786 100644 --- a/drivers/mtd/ubi/wl.h +++ b/drivers/mtd/ubi/wl.h @@ -2,7 +2,6 @@ #ifndef UBI_WL_H #define UBI_WL_H #ifdef CONFIG_MTD_UBI_FASTMAP -static int anchor_pebs_available(struct rb_root *root); static void update_fastmap_work_fn(struct work_struct *wrk); static struct ubi_wl_entry *find_anchor_wl_entry(struct rb_root *root); static struct ubi_wl_entry *get_peb_for_wl(struct ubi_device *ubi); diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c index 7a248cc1055a..7af7cc7c8669 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c @@ -2654,8 +2654,10 @@ static int setup_dpni(struct fsl_mc_device *ls_dev) priv->cls_rules = devm_kzalloc(dev, sizeof(struct dpaa2_eth_cls_rule) * dpaa2_eth_fs_count(priv), GFP_KERNEL); - if (!priv->cls_rules) + if (!priv->cls_rules) { + err = -ENOMEM; goto close; + } return 0; diff --git a/drivers/net/ethernet/intel/e1000/e1000_main.c b/drivers/net/ethernet/intel/e1000/e1000_main.c index f93ed70709c6..a2ee28e487a6 100644 --- a/drivers/net/ethernet/intel/e1000/e1000_main.c +++ b/drivers/net/ethernet/intel/e1000/e1000_main.c @@ -542,8 +542,13 @@ void e1000_reinit_locked(struct e1000_adapter *adapter) WARN_ON(in_interrupt()); while (test_and_set_bit(__E1000_RESETTING, &adapter->flags)) msleep(1); - e1000_down(adapter); - e1000_up(adapter); + + /* only run the task if not already down */ + if (!test_bit(__E1000_DOWN, &adapter->flags)) { + e1000_down(adapter); + e1000_up(adapter); + } + clear_bit(__E1000_RESETTING, &adapter->flags); } @@ -1433,10 +1438,15 @@ int e1000_close(struct net_device *netdev) struct e1000_hw *hw = &adapter->hw; int count = E1000_CHECK_RESET_COUNT; - while (test_bit(__E1000_RESETTING, &adapter->flags) && count--) + while (test_and_set_bit(__E1000_RESETTING, &adapter->flags) && count--) usleep_range(10000, 20000); - WARN_ON(test_bit(__E1000_RESETTING, &adapter->flags)); + WARN_ON(count < 0); + + /* signal that we're down so that the reset task will no longer run */ + set_bit(__E1000_DOWN, &adapter->flags); + clear_bit(__E1000_RESETTING, &adapter->flags); + e1000_down(adapter); e1000_power_down_phy(adapter); e1000_free_irq(adapter); diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index 34124c213d27..222ae76809aa 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -3077,9 +3077,6 @@ static int iavf_delete_clsflower(struct iavf_adapter *adapter, static int iavf_setup_tc_cls_flower(struct iavf_adapter *adapter, struct flow_cls_offload *cls_flower) { - if (cls_flower->common.chain_index) - return -EOPNOTSUPP; - switch (cls_flower->command) { case FLOW_CLS_REPLACE: return iavf_configure_clsflower(adapter, cls_flower); @@ -3103,6 +3100,11 @@ static int iavf_setup_tc_cls_flower(struct iavf_adapter *adapter, static int iavf_setup_tc_block_cb(enum tc_setup_type type, void *type_data, void *cb_priv) { + struct iavf_adapter *adapter = cb_priv; + + if (!tc_cls_can_offload_and_chain0(adapter->netdev, type_data)) + return -EOPNOTSUPP; + switch (type) { case TC_SETUP_CLSFLOWER: return iavf_setup_tc_cls_flower(cb_priv, type_data); diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c index 62673e27af0e..fc9ff985a62b 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c @@ -2635,14 +2635,14 @@ ice_set_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring) netdev_info(netdev, "Changing Tx descriptor count from %d to %d\n", vsi->tx_rings[0]->count, new_tx_cnt); - tx_rings = devm_kcalloc(&pf->pdev->dev, vsi->alloc_txq, + tx_rings = devm_kcalloc(&pf->pdev->dev, vsi->num_txq, sizeof(*tx_rings), GFP_KERNEL); if (!tx_rings) { err = -ENOMEM; goto done; } - for (i = 0; i < vsi->alloc_txq; i++) { + ice_for_each_txq(vsi, i) { /* clone ring and setup updated count */ tx_rings[i] = *vsi->tx_rings[i]; tx_rings[i].count = new_tx_cnt; @@ -2667,14 +2667,14 @@ ice_set_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring) netdev_info(netdev, "Changing Rx descriptor count from %d to %d\n", vsi->rx_rings[0]->count, new_rx_cnt); - rx_rings = devm_kcalloc(&pf->pdev->dev, vsi->alloc_rxq, + rx_rings = devm_kcalloc(&pf->pdev->dev, vsi->num_rxq, sizeof(*rx_rings), GFP_KERNEL); if (!rx_rings) { err = -ENOMEM; goto done; } - for (i = 0; i < vsi->alloc_rxq; i++) { + ice_for_each_rxq(vsi, i) { /* clone ring and setup updated count */ rx_rings[i] = *vsi->rx_rings[i]; rx_rings[i].count = new_rx_cnt; @@ -2712,7 +2712,7 @@ ice_set_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring) ice_down(vsi); if (tx_rings) { - for (i = 0; i < vsi->alloc_txq; i++) { + ice_for_each_txq(vsi, i) { ice_free_tx_ring(vsi->tx_rings[i]); *vsi->tx_rings[i] = tx_rings[i]; } @@ -2720,7 +2720,7 @@ ice_set_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring) } if (rx_rings) { - for (i = 0; i < vsi->alloc_rxq; i++) { + ice_for_each_rxq(vsi, i) { ice_free_rx_ring(vsi->rx_rings[i]); /* copy the real tail offset */ rx_rings[i].tail = vsi->rx_rings[i]->tail; @@ -2744,7 +2744,7 @@ ice_set_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring) free_tx: /* error cleanup if the Rx allocations failed after getting Tx */ if (tx_rings) { - for (i = 0; i < vsi->alloc_txq; i++) + ice_for_each_txq(vsi, i) ice_free_tx_ring(&tx_rings[i]); devm_kfree(&pf->pdev->dev, tx_rings); } diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev.c b/drivers/net/ethernet/qlogic/qed/qed_dev.c index 4456ce5325a7..a923c6553270 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_dev.c +++ b/drivers/net/ethernet/qlogic/qed/qed_dev.c @@ -4142,7 +4142,8 @@ static int qed_hw_get_nvm_info(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) cdev->mf_bits = BIT(QED_MF_LLH_MAC_CLSS) | BIT(QED_MF_LLH_PROTO_CLSS) | BIT(QED_MF_LL2_NON_UNICAST) | - BIT(QED_MF_INTER_PF_SWITCH); + BIT(QED_MF_INTER_PF_SWITCH) | + BIT(QED_MF_DISABLE_ARFS); break; case NVM_CFG1_GLOB_MF_MODE_DEFAULT: cdev->mf_bits = BIT(QED_MF_LLH_MAC_CLSS) | @@ -4155,6 +4156,14 @@ static int qed_hw_get_nvm_info(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) DP_INFO(p_hwfn, "Multi function mode is 0x%lx\n", cdev->mf_bits); + + /* In CMT the PF is unknown when the GFS block processes the + * packet. Therefore cannot use searcher as it has a per PF + * database, and thus ARFS must be disabled. + * + */ + if (QED_IS_CMT(cdev)) + cdev->mf_bits |= BIT(QED_MF_DISABLE_ARFS); } DP_INFO(p_hwfn, "Multi function mode is 0x%lx\n", diff --git a/drivers/net/ethernet/qlogic/qed/qed_l2.c b/drivers/net/ethernet/qlogic/qed/qed_l2.c index 1a5fc2ae351c..8a73482cb7a8 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_l2.c +++ b/drivers/net/ethernet/qlogic/qed/qed_l2.c @@ -2001,6 +2001,9 @@ void qed_arfs_mode_configure(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, struct qed_arfs_config_params *p_cfg_params) { + if (test_bit(QED_MF_DISABLE_ARFS, &p_hwfn->cdev->mf_bits)) + return; + if (p_cfg_params->mode != QED_FILTER_CONFIG_MODE_DISABLE) { qed_gft_config(p_hwfn, p_ptt, p_hwfn->rel_pf_id, p_cfg_params->tcp, diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c index e72f9f1d2e94..bc1f5b36b5bf 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_main.c +++ b/drivers/net/ethernet/qlogic/qed/qed_main.c @@ -280,6 +280,8 @@ int qed_fill_dev_info(struct qed_dev *cdev, dev_info->fw_eng = FW_ENGINEERING_VERSION; dev_info->b_inter_pf_switch = test_bit(QED_MF_INTER_PF_SWITCH, &cdev->mf_bits); + if (!test_bit(QED_MF_DISABLE_ARFS, &cdev->mf_bits)) + dev_info->b_arfs_capable = true; dev_info->tx_switching = true; if (hw_info->b_wol_support == QED_WOL_SUPPORT_PME) diff --git a/drivers/net/ethernet/qlogic/qed/qed_sriov.c b/drivers/net/ethernet/qlogic/qed/qed_sriov.c index dcb5c917f373..fb9c3ca5d36c 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_sriov.c +++ b/drivers/net/ethernet/qlogic/qed/qed_sriov.c @@ -96,6 +96,7 @@ static int qed_sp_vf_start(struct qed_hwfn *p_hwfn, struct qed_vf_info *p_vf) p_ramrod->personality = PERSONALITY_ETH; break; case QED_PCI_ETH_ROCE: + case QED_PCI_ETH_IWARP: p_ramrod->personality = PERSONALITY_RDMA_AND_ETH; break; default: diff --git a/drivers/net/ethernet/qlogic/qede/qede_filter.c b/drivers/net/ethernet/qlogic/qede/qede_filter.c index c8bdbf057d5a..5041994bf03f 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_filter.c +++ b/drivers/net/ethernet/qlogic/qede/qede_filter.c @@ -336,6 +336,9 @@ int qede_alloc_arfs(struct qede_dev *edev) { int i; + if (!edev->dev_info.common.b_arfs_capable) + return -EINVAL; + edev->arfs = vzalloc(sizeof(*edev->arfs)); if (!edev->arfs) return -ENOMEM; diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c index 2c3d654c8454..ce3e62e73e4c 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_main.c +++ b/drivers/net/ethernet/qlogic/qede/qede_main.c @@ -770,7 +770,7 @@ static void qede_init_ndev(struct qede_dev *edev) NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_HW_TC; - if (!IS_VF(edev) && edev->dev_info.common.num_hwfns == 1) + if (edev->dev_info.common.b_arfs_capable) hw_features |= NETIF_F_NTUPLE; if (edev->dev_info.common.vxlan_enable || @@ -2211,7 +2211,7 @@ static void qede_unload(struct qede_dev *edev, enum qede_unload_mode mode, qede_vlan_mark_nonconfigured(edev); edev->ops->fastpath_stop(edev->cdev); - if (!IS_VF(edev) && edev->dev_info.common.num_hwfns == 1) { + if (edev->dev_info.common.b_arfs_capable) { qede_poll_for_freeing_arfs_filters(edev); qede_free_arfs(edev); } @@ -2278,10 +2278,9 @@ static int qede_load(struct qede_dev *edev, enum qede_load_mode mode, if (rc) goto err2; - if (!IS_VF(edev) && edev->dev_info.common.num_hwfns == 1) { - rc = qede_alloc_arfs(edev); - if (rc) - DP_NOTICE(edev, "aRFS memory allocation failed\n"); + if (qede_alloc_arfs(edev)) { + edev->ndev->features &= ~NETIF_F_NTUPLE; + edev->dev_info.common.b_arfs_capable = false; } qede_napi_add_enable(edev); diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index 6fa9852e3f97..903212ad9bb2 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -6256,8 +6256,7 @@ static irqreturn_t rtl8169_interrupt(int irq, void *dev_instance) if (unlikely(status & RxFIFOOver && tp->mac_version == RTL_GIGA_MAC_VER_11)) { netif_stop_queue(tp->dev); - /* XXX - Hack alert. See rtl_task(). */ - set_bit(RTL_FLAG_TASK_RESET_PENDING, tp->wk.flags); + rtl_schedule_task(tp, RTL_FLAG_TASK_RESET_PENDING); } rtl_irq_disable(tp); diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet.h b/drivers/net/ethernet/xilinx/xilinx_axienet.h index 2dacfc85b3ba..04e51af32178 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet.h +++ b/drivers/net/ethernet/xilinx/xilinx_axienet.h @@ -435,7 +435,7 @@ struct axienet_local { void __iomem *regs; void __iomem *dma_regs; - struct tasklet_struct dma_err_tasklet; + struct work_struct dma_err_task; int tx_irq; int rx_irq; diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c index 479325eeaf8a..bb6e52f3bdf9 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c +++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c @@ -437,9 +437,10 @@ static void axienet_setoptions(struct net_device *ndev, u32 options) lp->options |= options; } -static void __axienet_device_reset(struct axienet_local *lp) +static int __axienet_device_reset(struct axienet_local *lp) { u32 timeout; + /* Reset Axi DMA. This would reset Axi Ethernet core as well. The reset * process of Axi DMA takes a while to complete as all pending * commands/transfers will be flushed or completed during this @@ -455,9 +456,11 @@ static void __axienet_device_reset(struct axienet_local *lp) if (--timeout == 0) { netdev_err(lp->ndev, "%s: DMA reset timeout!\n", __func__); - break; + return -ETIMEDOUT; } } + + return 0; } /** @@ -470,13 +473,17 @@ static void __axienet_device_reset(struct axienet_local *lp) * areconnected to Axi Ethernet reset lines, this in turn resets the Axi * Ethernet core. No separate hardware reset is done for the Axi Ethernet * core. + * Returns 0 on success or a negative error number otherwise. */ -static void axienet_device_reset(struct net_device *ndev) +static int axienet_device_reset(struct net_device *ndev) { u32 axienet_status; struct axienet_local *lp = netdev_priv(ndev); + int ret; - __axienet_device_reset(lp); + ret = __axienet_device_reset(lp); + if (ret) + return ret; lp->max_frm_size = XAE_MAX_VLAN_FRAME_SIZE; lp->options |= XAE_OPTION_VLAN; @@ -491,9 +498,11 @@ static void axienet_device_reset(struct net_device *ndev) lp->options |= XAE_OPTION_JUMBO; } - if (axienet_dma_bd_init(ndev)) { + ret = axienet_dma_bd_init(ndev); + if (ret) { netdev_err(ndev, "%s: descriptor allocation failed\n", __func__); + return ret; } axienet_status = axienet_ior(lp, XAE_RCW1_OFFSET); @@ -518,6 +527,8 @@ static void axienet_device_reset(struct net_device *ndev) axienet_setoptions(ndev, lp->options); netif_trans_update(ndev); + + return 0; } /** @@ -806,7 +817,7 @@ static irqreturn_t axienet_tx_irq(int irq, void *_ndev) /* Write to the Rx channel control register */ axienet_dma_out32(lp, XAXIDMA_RX_CR_OFFSET, cr); - tasklet_schedule(&lp->dma_err_tasklet); + schedule_work(&lp->dma_err_task); axienet_dma_out32(lp, XAXIDMA_TX_SR_OFFSET, status); } out: @@ -855,7 +866,7 @@ static irqreturn_t axienet_rx_irq(int irq, void *_ndev) /* write to the Rx channel control register */ axienet_dma_out32(lp, XAXIDMA_RX_CR_OFFSET, cr); - tasklet_schedule(&lp->dma_err_tasklet); + schedule_work(&lp->dma_err_task); axienet_dma_out32(lp, XAXIDMA_RX_SR_OFFSET, status); } out: @@ -891,7 +902,7 @@ static irqreturn_t axienet_eth_irq(int irq, void *_ndev) return IRQ_HANDLED; } -static void axienet_dma_err_handler(unsigned long data); +static void axienet_dma_err_handler(struct work_struct *work); /** * axienet_open - Driver open routine. @@ -921,8 +932,9 @@ static int axienet_open(struct net_device *ndev) */ mutex_lock(&lp->mii_bus->mdio_lock); axienet_mdio_disable(lp); - axienet_device_reset(ndev); - ret = axienet_mdio_enable(lp); + ret = axienet_device_reset(ndev); + if (ret == 0) + ret = axienet_mdio_enable(lp); mutex_unlock(&lp->mii_bus->mdio_lock); if (ret < 0) return ret; @@ -935,9 +947,8 @@ static int axienet_open(struct net_device *ndev) phylink_start(lp->phylink); - /* Enable tasklets for Axi DMA error handling */ - tasklet_init(&lp->dma_err_tasklet, axienet_dma_err_handler, - (unsigned long) lp); + /* Enable worker thread for Axi DMA error handling */ + INIT_WORK(&lp->dma_err_task, axienet_dma_err_handler); /* Enable interrupts for Axi DMA Tx */ ret = request_irq(lp->tx_irq, axienet_tx_irq, IRQF_SHARED, @@ -966,7 +977,7 @@ static int axienet_open(struct net_device *ndev) err_tx_irq: phylink_stop(lp->phylink); phylink_disconnect_phy(lp->phylink); - tasklet_kill(&lp->dma_err_tasklet); + cancel_work_sync(&lp->dma_err_task); dev_err(lp->dev, "request_irq() failed\n"); return ret; } @@ -1025,7 +1036,7 @@ static int axienet_stop(struct net_device *ndev) axienet_mdio_enable(lp); mutex_unlock(&lp->mii_bus->mdio_lock); - tasklet_kill(&lp->dma_err_tasklet); + cancel_work_sync(&lp->dma_err_task); if (lp->eth_irq > 0) free_irq(lp->eth_irq, ndev); @@ -1505,17 +1516,18 @@ static const struct phylink_mac_ops axienet_phylink_ops = { }; /** - * axienet_dma_err_handler - Tasklet handler for Axi DMA Error - * @data: Data passed + * axienet_dma_err_handler - Work queue task for Axi DMA Error + * @work: pointer to work_struct * * Resets the Axi DMA and Axi Ethernet devices, and reconfigures the * Tx/Rx BDs. */ -static void axienet_dma_err_handler(unsigned long data) +static void axienet_dma_err_handler(struct work_struct *work) { u32 axienet_status; u32 cr, i; - struct axienet_local *lp = (struct axienet_local *) data; + struct axienet_local *lp = container_of(work, struct axienet_local, + dma_err_task); struct net_device *ndev = lp->ndev; struct axidma_bd *cur_p; diff --git a/drivers/net/ieee802154/adf7242.c b/drivers/net/ieee802154/adf7242.c index 8dbccec6ac86..5945ac5f38ee 100644 --- a/drivers/net/ieee802154/adf7242.c +++ b/drivers/net/ieee802154/adf7242.c @@ -882,7 +882,9 @@ static int adf7242_rx(struct adf7242_local *lp) int ret; u8 lqi, len_u8, *data; - adf7242_read_reg(lp, 0, &len_u8); + ret = adf7242_read_reg(lp, 0, &len_u8); + if (ret) + return ret; len = len_u8; diff --git a/drivers/net/ieee802154/ca8210.c b/drivers/net/ieee802154/ca8210.c index 430c93786153..25dbea302fb6 100644 --- a/drivers/net/ieee802154/ca8210.c +++ b/drivers/net/ieee802154/ca8210.c @@ -2924,6 +2924,7 @@ static int ca8210_dev_com_init(struct ca8210_priv *priv) ); if (!priv->irq_workqueue) { dev_crit(&priv->spi->dev, "alloc of irq_workqueue failed!\n"); + destroy_workqueue(priv->mlme_workqueue); return -ENOMEM; } diff --git a/drivers/net/wireless/ath/ar5523/ar5523.c b/drivers/net/wireless/ath/ar5523/ar5523.c index da2d179430ca..4c57e79e5779 100644 --- a/drivers/net/wireless/ath/ar5523/ar5523.c +++ b/drivers/net/wireless/ath/ar5523/ar5523.c @@ -1770,6 +1770,8 @@ static const struct usb_device_id ar5523_id_table[] = { AR5523_DEVICE_UX(0x0846, 0x4300), /* Netgear / WG111U */ AR5523_DEVICE_UG(0x0846, 0x4250), /* Netgear / WG111T */ AR5523_DEVICE_UG(0x0846, 0x5f00), /* Netgear / WPN111 */ + AR5523_DEVICE_UG(0x083a, 0x4506), /* SMC / EZ Connect + SMCWUSBT-G2 */ AR5523_DEVICE_UG(0x157e, 0x3006), /* Umedia / AR5523_1 */ AR5523_DEVICE_UX(0x157e, 0x3205), /* Umedia / AR5523_2 */ AR5523_DEVICE_UG(0x157e, 0x3006), /* Umedia / TEW444UBEU */ diff --git a/drivers/net/wireless/ath/ath10k/debug.c b/drivers/net/wireless/ath/ath10k/debug.c index bd2b5628f850..04c50a26a4f4 100644 --- a/drivers/net/wireless/ath/ath10k/debug.c +++ b/drivers/net/wireless/ath/ath10k/debug.c @@ -1516,7 +1516,7 @@ static void ath10k_tpc_stats_print(struct ath10k_tpc_stats *tpc_stats, *len += scnprintf(buf + *len, buf_len - *len, "No. Preamble Rate_code "); - for (i = 0; i < WMI_TPC_TX_N_CHAIN; i++) + for (i = 0; i < tpc_stats->num_tx_chain; i++) *len += scnprintf(buf + *len, buf_len - *len, "tpc_value%d ", i); @@ -2532,6 +2532,7 @@ void ath10k_debug_destroy(struct ath10k *ar) ath10k_debug_fw_stats_reset(ar); kfree(ar->debug.tpc_stats); + kfree(ar->debug.tpc_stats_final); } int ath10k_debug_register(struct ath10k *ar) diff --git a/drivers/net/wireless/ath/ath10k/sdio.c b/drivers/net/wireless/ath/ath10k/sdio.c index 9870d2d095c8..8fe626deadeb 100644 --- a/drivers/net/wireless/ath/ath10k/sdio.c +++ b/drivers/net/wireless/ath/ath10k/sdio.c @@ -1582,23 +1582,33 @@ static int ath10k_sdio_hif_diag_read(struct ath10k *ar, u32 address, void *buf, size_t buf_len) { int ret; + void *mem; + + mem = kzalloc(buf_len, GFP_KERNEL); + if (!mem) + return -ENOMEM; /* set window register to start read cycle */ ret = ath10k_sdio_write32(ar, MBOX_WINDOW_READ_ADDR_ADDRESS, address); if (ret) { ath10k_warn(ar, "failed to set mbox window read address: %d", ret); - return ret; + goto out; } /* read the data */ - ret = ath10k_sdio_read(ar, MBOX_WINDOW_DATA_ADDRESS, buf, buf_len); + ret = ath10k_sdio_read(ar, MBOX_WINDOW_DATA_ADDRESS, mem, buf_len); if (ret) { ath10k_warn(ar, "failed to read from mbox window data address: %d\n", ret); - return ret; + goto out; } - return 0; + memcpy(buf, mem, buf_len); + +out: + kfree(mem); + + return ret; } static int ath10k_sdio_hif_diag_read32(struct ath10k *ar, u32 address, diff --git a/drivers/net/wireless/ath/ath10k/wmi.c b/drivers/net/wireless/ath/ath10k/wmi.c index 90f1197a6ad8..2675174cc4fe 100644 --- a/drivers/net/wireless/ath/ath10k/wmi.c +++ b/drivers/net/wireless/ath/ath10k/wmi.c @@ -4668,16 +4668,13 @@ static void ath10k_tpc_config_disp_tables(struct ath10k *ar, } pream_idx = 0; - for (i = 0; i < __le32_to_cpu(ev->rate_max); i++) { + for (i = 0; i < tpc_stats->rate_max; i++) { memset(tpc_value, 0, sizeof(tpc_value)); memset(buff, 0, sizeof(buff)); if (i == pream_table[pream_idx]) pream_idx++; - for (j = 0; j < WMI_TPC_TX_N_CHAIN; j++) { - if (j >= __le32_to_cpu(ev->num_tx_chain)) - break; - + for (j = 0; j < tpc_stats->num_tx_chain; j++) { tpc[j] = ath10k_tpc_config_get_rate(ar, ev, i, j + 1, rate_code[i], type); @@ -4790,7 +4787,7 @@ void ath10k_wmi_tpc_config_get_rate_code(u8 *rate_code, u16 *pream_table, void ath10k_wmi_event_pdev_tpc_config(struct ath10k *ar, struct sk_buff *skb) { - u32 num_tx_chain; + u32 num_tx_chain, rate_max; u8 rate_code[WMI_TPC_RATE_MAX]; u16 pream_table[WMI_TPC_PREAM_TABLE_MAX]; struct wmi_pdev_tpc_config_event *ev; @@ -4806,6 +4803,13 @@ void ath10k_wmi_event_pdev_tpc_config(struct ath10k *ar, struct sk_buff *skb) return; } + rate_max = __le32_to_cpu(ev->rate_max); + if (rate_max > WMI_TPC_RATE_MAX) { + ath10k_warn(ar, "number of rate is %d greater than TPC configured rate %d\n", + rate_max, WMI_TPC_RATE_MAX); + rate_max = WMI_TPC_RATE_MAX; + } + tpc_stats = kzalloc(sizeof(*tpc_stats), GFP_ATOMIC); if (!tpc_stats) return; @@ -4822,8 +4826,8 @@ void ath10k_wmi_event_pdev_tpc_config(struct ath10k *ar, struct sk_buff *skb) __le32_to_cpu(ev->twice_antenna_reduction); tpc_stats->power_limit = __le32_to_cpu(ev->power_limit); tpc_stats->twice_max_rd_power = __le32_to_cpu(ev->twice_max_rd_power); - tpc_stats->num_tx_chain = __le32_to_cpu(ev->num_tx_chain); - tpc_stats->rate_max = __le32_to_cpu(ev->rate_max); + tpc_stats->num_tx_chain = num_tx_chain; + tpc_stats->rate_max = rate_max; ath10k_tpc_config_disp_tables(ar, ev, tpc_stats, rate_code, pream_table, @@ -5018,16 +5022,13 @@ ath10k_wmi_tpc_stats_final_disp_tables(struct ath10k *ar, } pream_idx = 0; - for (i = 0; i < __le32_to_cpu(ev->rate_max); i++) { + for (i = 0; i < tpc_stats->rate_max; i++) { memset(tpc_value, 0, sizeof(tpc_value)); memset(buff, 0, sizeof(buff)); if (i == pream_table[pream_idx]) pream_idx++; - for (j = 0; j < WMI_TPC_TX_N_CHAIN; j++) { - if (j >= __le32_to_cpu(ev->num_tx_chain)) - break; - + for (j = 0; j < tpc_stats->num_tx_chain; j++) { tpc[j] = ath10k_wmi_tpc_final_get_rate(ar, ev, i, j + 1, rate_code[i], type, pream_idx); @@ -5043,7 +5044,7 @@ ath10k_wmi_tpc_stats_final_disp_tables(struct ath10k *ar, void ath10k_wmi_event_tpc_final_table(struct ath10k *ar, struct sk_buff *skb) { - u32 num_tx_chain; + u32 num_tx_chain, rate_max; u8 rate_code[WMI_TPC_FINAL_RATE_MAX]; u16 pream_table[WMI_TPC_PREAM_TABLE_MAX]; struct wmi_pdev_tpc_final_table_event *ev; @@ -5051,12 +5052,24 @@ void ath10k_wmi_event_tpc_final_table(struct ath10k *ar, struct sk_buff *skb) ev = (struct wmi_pdev_tpc_final_table_event *)skb->data; + num_tx_chain = __le32_to_cpu(ev->num_tx_chain); + if (num_tx_chain > WMI_TPC_TX_N_CHAIN) { + ath10k_warn(ar, "number of tx chain is %d greater than TPC final configured tx chain %d\n", + num_tx_chain, WMI_TPC_TX_N_CHAIN); + return; + } + + rate_max = __le32_to_cpu(ev->rate_max); + if (rate_max > WMI_TPC_FINAL_RATE_MAX) { + ath10k_warn(ar, "number of rate is %d greater than TPC final configured rate %d\n", + rate_max, WMI_TPC_FINAL_RATE_MAX); + rate_max = WMI_TPC_FINAL_RATE_MAX; + } + tpc_stats = kzalloc(sizeof(*tpc_stats), GFP_ATOMIC); if (!tpc_stats) return; - num_tx_chain = __le32_to_cpu(ev->num_tx_chain); - ath10k_wmi_tpc_config_get_rate_code(rate_code, pream_table, num_tx_chain); @@ -5069,8 +5082,8 @@ void ath10k_wmi_event_tpc_final_table(struct ath10k *ar, struct sk_buff *skb) __le32_to_cpu(ev->twice_antenna_reduction); tpc_stats->power_limit = __le32_to_cpu(ev->power_limit); tpc_stats->twice_max_rd_power = __le32_to_cpu(ev->twice_max_rd_power); - tpc_stats->num_tx_chain = __le32_to_cpu(ev->num_tx_chain); - tpc_stats->rate_max = __le32_to_cpu(ev->rate_max); + tpc_stats->num_tx_chain = num_tx_chain; + tpc_stats->rate_max = rate_max; ath10k_wmi_tpc_stats_final_disp_tables(ar, ev, tpc_stats, rate_code, pream_table, diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwsignal.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwsignal.c index eadc64454839..3d36b6ee158b 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwsignal.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwsignal.c @@ -2149,8 +2149,7 @@ int brcmf_fws_process_skb(struct brcmf_if *ifp, struct sk_buff *skb) brcmf_fws_enq(fws, BRCMF_FWS_SKBSTATE_DELAYED, fifo, skb); brcmf_fws_schedule_deq(fws); } else { - bphy_err(drvr, "drop skb: no hanger slot\n"); - brcmf_txfinalize(ifp, skb, false); + bphy_err(drvr, "no hanger slot available\n"); rc = -ENOMEM; } brcmf_fws_unlock(fws); diff --git a/drivers/net/wireless/marvell/mwifiex/fw.h b/drivers/net/wireless/marvell/mwifiex/fw.h index 1fb76d2f5d3f..8b9d0809daf6 100644 --- a/drivers/net/wireless/marvell/mwifiex/fw.h +++ b/drivers/net/wireless/marvell/mwifiex/fw.h @@ -953,7 +953,7 @@ struct mwifiex_tkip_param { struct mwifiex_aes_param { u8 pn[WPA_PN_SIZE]; __le16 key_len; - u8 key[WLAN_KEY_LEN_CCMP]; + u8 key[WLAN_KEY_LEN_CCMP_256]; } __packed; struct mwifiex_wapi_param { diff --git a/drivers/net/wireless/marvell/mwifiex/sta_cmdresp.c b/drivers/net/wireless/marvell/mwifiex/sta_cmdresp.c index 7ae2c34f65db..4eaa493e3325 100644 --- a/drivers/net/wireless/marvell/mwifiex/sta_cmdresp.c +++ b/drivers/net/wireless/marvell/mwifiex/sta_cmdresp.c @@ -619,7 +619,7 @@ static int mwifiex_ret_802_11_key_material_v2(struct mwifiex_private *priv, key_v2 = &resp->params.key_material_v2; len = le16_to_cpu(key_v2->key_param_set.key_params.aes.key_len); - if (len > WLAN_KEY_LEN_CCMP) + if (len > sizeof(key_v2->key_param_set.key_params.aes.key)) return -EINVAL; if (le16_to_cpu(key_v2->action) == HostCmd_ACT_GEN_SET) { @@ -635,7 +635,7 @@ static int mwifiex_ret_802_11_key_material_v2(struct mwifiex_private *priv, return 0; memset(priv->aes_key_v2.key_param_set.key_params.aes.key, 0, - WLAN_KEY_LEN_CCMP); + sizeof(key_v2->key_param_set.key_params.aes.key)); priv->aes_key_v2.key_param_set.key_params.aes.key_len = cpu_to_le16(len); memcpy(priv->aes_key_v2.key_param_set.key_params.aes.key, diff --git a/drivers/net/wireless/mediatek/mt76/agg-rx.c b/drivers/net/wireless/mediatek/mt76/agg-rx.c index cbff0dfc9631..f8441fd65400 100644 --- a/drivers/net/wireless/mediatek/mt76/agg-rx.c +++ b/drivers/net/wireless/mediatek/mt76/agg-rx.c @@ -268,6 +268,7 @@ static void mt76_rx_aggr_shutdown(struct mt76_dev *dev, struct mt76_rx_tid *tid) if (!skb) continue; + tid->reorder_buf[i] = NULL; tid->nframes--; dev_kfree_skb(skb); } diff --git a/drivers/net/wireless/mediatek/mt76/dma.c b/drivers/net/wireless/mediatek/mt76/dma.c index 6249a46c1976..026d996612fb 100644 --- a/drivers/net/wireless/mediatek/mt76/dma.c +++ b/drivers/net/wireless/mediatek/mt76/dma.c @@ -261,10 +261,13 @@ mt76_dma_tx_queue_skb_raw(struct mt76_dev *dev, enum mt76_txq_id qid, struct mt76_queue_buf buf; dma_addr_t addr; + if (q->queued + 1 >= q->ndesc - 1) + goto error; + addr = dma_map_single(dev->dev, skb->data, skb->len, DMA_TO_DEVICE); if (unlikely(dma_mapping_error(dev->dev, addr))) - return -ENOMEM; + goto error; buf.addr = addr; buf.len = skb->len; @@ -275,6 +278,10 @@ mt76_dma_tx_queue_skb_raw(struct mt76_dev *dev, enum mt76_txq_id qid, spin_unlock_bh(&q->lock); return 0; + +error: + dev_kfree_skb(skb); + return -ENOMEM; } static int diff --git a/drivers/net/wireless/mediatek/mt76/mac80211.c b/drivers/net/wireless/mediatek/mt76/mac80211.c index 1a2c143b34d0..8bd191347b9f 100644 --- a/drivers/net/wireless/mediatek/mt76/mac80211.c +++ b/drivers/net/wireless/mediatek/mt76/mac80211.c @@ -105,7 +105,15 @@ static int mt76_led_init(struct mt76_dev *dev) dev->led_al = of_property_read_bool(np, "led-active-low"); } - return devm_led_classdev_register(dev->dev, &dev->led_cdev); + return led_classdev_register(dev->dev, &dev->led_cdev); +} + +static void mt76_led_cleanup(struct mt76_dev *dev) +{ + if (!dev->led_cdev.brightness_set && !dev->led_cdev.blink_set) + return; + + led_classdev_unregister(&dev->led_cdev); } static void mt76_init_stream_cap(struct mt76_dev *dev, @@ -360,6 +368,8 @@ void mt76_unregister_device(struct mt76_dev *dev) { struct ieee80211_hw *hw = dev->hw; + if (IS_ENABLED(CONFIG_MT76_LEDS)) + mt76_led_cleanup(dev); mt76_tx_status_check(dev, NULL, true); ieee80211_unregister_hw(hw); } diff --git a/drivers/net/wireless/mediatek/mt76/mt7603/main.c b/drivers/net/wireless/mediatek/mt76/mt7603/main.c index 25d5b1608bc9..0a5695c3d924 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7603/main.c +++ b/drivers/net/wireless/mediatek/mt76/mt7603/main.c @@ -561,6 +561,7 @@ mt7603_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, mtxq = (struct mt76_txq *)txq->drv_priv; + mutex_lock(&dev->mt76.mutex); switch (action) { case IEEE80211_AMPDU_RX_START: mt76_rx_aggr_start(&dev->mt76, &msta->wcid, tid, ssn, @@ -590,6 +591,7 @@ mt7603_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, ieee80211_stop_tx_ba_cb_irqsafe(vif, sta->addr, tid); break; } + mutex_unlock(&dev->mt76.mutex); return 0; } diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/main.c b/drivers/net/wireless/mediatek/mt76/mt7615/main.c index 87c748715b5d..38183aef0eb9 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7615/main.c +++ b/drivers/net/wireless/mediatek/mt76/mt7615/main.c @@ -455,6 +455,7 @@ mt7615_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, mtxq = (struct mt76_txq *)txq->drv_priv; + mutex_lock(&dev->mt76.mutex); switch (action) { case IEEE80211_AMPDU_RX_START: mt76_rx_aggr_start(&dev->mt76, &msta->wcid, tid, ssn, @@ -485,6 +486,7 @@ mt7615_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, ieee80211_stop_tx_ba_cb_irqsafe(vif, sta->addr, tid); break; } + mutex_unlock(&dev->mt76.mutex); return 0; } diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_util.c b/drivers/net/wireless/mediatek/mt76/mt76x02_util.c index aec73a0295e8..de0d6f21c621 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x02_util.c +++ b/drivers/net/wireless/mediatek/mt76/mt76x02_util.c @@ -371,6 +371,7 @@ int mt76x02_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, mtxq = (struct mt76_txq *)txq->drv_priv; + mutex_lock(&dev->mt76.mutex); switch (action) { case IEEE80211_AMPDU_RX_START: mt76_rx_aggr_start(&dev->mt76, &msta->wcid, tid, @@ -400,6 +401,7 @@ int mt76x02_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, ieee80211_stop_tx_ba_cb_irqsafe(vif, sta->addr, tid); break; } + mutex_unlock(&dev->mt76.mutex); return 0; } diff --git a/drivers/net/wireless/ti/wlcore/main.c b/drivers/net/wireless/ti/wlcore/main.c index 547ad538d8b6..5f74cf821068 100644 --- a/drivers/net/wireless/ti/wlcore/main.c +++ b/drivers/net/wireless/ti/wlcore/main.c @@ -3658,8 +3658,10 @@ void wlcore_regdomain_config(struct wl1271 *wl) goto out; ret = pm_runtime_get_sync(wl->dev); - if (ret < 0) + if (ret < 0) { + pm_runtime_put_autosuspend(wl->dev); goto out; + } ret = wlcore_cmd_regdomain_config_locked(wl); if (ret < 0) { diff --git a/drivers/net/wireless/ti/wlcore/tx.c b/drivers/net/wireless/ti/wlcore/tx.c index 90e56d4c3df3..e20e18cd04ae 100644 --- a/drivers/net/wireless/ti/wlcore/tx.c +++ b/drivers/net/wireless/ti/wlcore/tx.c @@ -863,6 +863,7 @@ void wl1271_tx_work(struct work_struct *work) ret = wlcore_tx_work_locked(wl); if (ret < 0) { + pm_runtime_put_noidle(wl->dev); wl12xx_queue_recovery_work(wl); goto out; } diff --git a/drivers/nvme/host/Kconfig b/drivers/nvme/host/Kconfig index 2b36f052bfb9..7b3f6555e67b 100644 --- a/drivers/nvme/host/Kconfig +++ b/drivers/nvme/host/Kconfig @@ -64,6 +64,7 @@ config NVME_TCP depends on INET depends on BLK_DEV_NVME select NVME_FABRICS + select CRYPTO select CRYPTO_CRC32C help This provides support for the NVMe over Fabrics protocol using diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 2d2673d360ff..2cd32901d95c 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -288,11 +288,8 @@ void nvme_complete_rq(struct request *req) nvme_req(req)->ctrl->comp_seen = true; if (unlikely(status != BLK_STS_OK && nvme_req_needs_retry(req))) { - if ((req->cmd_flags & REQ_NVME_MPATH) && - blk_path_error(status)) { - nvme_failover_req(req); + if ((req->cmd_flags & REQ_NVME_MPATH) && nvme_failover_req(req)) return; - } if (!blk_queue_dying(req->q)) { nvme_retry_req(req); @@ -1867,7 +1864,7 @@ static void __nvme_revalidate_disk(struct gendisk *disk, struct nvme_id_ns *id) if (ns->head->disk) { nvme_update_disk_info(ns->head->disk, ns, id); blk_queue_stack_limits(ns->head->disk->queue, ns->queue); - revalidate_disk(ns->head->disk); + nvme_mpath_update_disk_size(ns->head->disk); } #endif } @@ -3200,6 +3197,10 @@ static ssize_t nvme_sysfs_delete(struct device *dev, { struct nvme_ctrl *ctrl = dev_get_drvdata(dev); + /* Can't delete non-created controllers */ + if (!ctrl->created) + return -EBUSY; + if (device_remove_file_self(dev, attr)) nvme_delete_ctrl_sync(ctrl); return count; @@ -3995,6 +3996,7 @@ void nvme_start_ctrl(struct nvme_ctrl *ctrl) nvme_queue_scan(ctrl); nvme_start_queues(ctrl); } + ctrl->created = true; } EXPORT_SYMBOL_GPL(nvme_start_ctrl); @@ -4085,6 +4087,7 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev, if (ret) goto out_release_instance; + nvme_get_ctrl(ctrl); cdev_init(&ctrl->cdev, &nvme_dev_fops); ctrl->cdev.owner = ops->module; ret = cdev_device_add(&ctrl->cdev, ctrl->device); @@ -4103,6 +4106,7 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev, return 0; out_free_name: + nvme_put_ctrl(ctrl); kfree_const(ctrl->device->kobj.name); out_release_instance: ida_simple_remove(&nvme_instance_ida, ctrl->instance); diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index dae050d1f814..da801a14cd13 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -3171,10 +3171,7 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts, goto fail_ctrl; } - nvme_get_ctrl(&ctrl->ctrl); - if (!queue_delayed_work(nvme_wq, &ctrl->connect_work, 0)) { - nvme_put_ctrl(&ctrl->ctrl); dev_err(ctrl->ctrl.device, "NVME-FC{%d}: failed to schedule initial connect\n", ctrl->cnum); @@ -3199,6 +3196,7 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts, /* initiate nvme ctrl ref counting teardown */ nvme_uninit_ctrl(&ctrl->ctrl); + nvme_put_ctrl(&ctrl->ctrl); /* Remove core ctrl ref. */ nvme_put_ctrl(&ctrl->ctrl); diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c index 0a458f788088..3968f89f7855 100644 --- a/drivers/nvme/host/multipath.c +++ b/drivers/nvme/host/multipath.c @@ -65,17 +65,12 @@ void nvme_set_disk_name(char *disk_name, struct nvme_ns *ns, } } -void nvme_failover_req(struct request *req) +bool nvme_failover_req(struct request *req) { struct nvme_ns *ns = req->q->queuedata; u16 status = nvme_req(req)->status; unsigned long flags; - spin_lock_irqsave(&ns->head->requeue_lock, flags); - blk_steal_bios(&ns->head->requeue_list, req); - spin_unlock_irqrestore(&ns->head->requeue_lock, flags); - blk_mq_end_request(req, 0); - switch (status & 0x7ff) { case NVME_SC_ANA_TRANSITION: case NVME_SC_ANA_INACCESSIBLE: @@ -104,15 +99,17 @@ void nvme_failover_req(struct request *req) nvme_mpath_clear_current_path(ns); break; default: - /* - * Reset the controller for any non-ANA error as we don't know - * what caused the error. - */ - nvme_reset_ctrl(ns->ctrl); - break; + /* This was a non-ANA error so follow the normal error path. */ + return false; } + spin_lock_irqsave(&ns->head->requeue_lock, flags); + blk_steal_bios(&ns->head->requeue_list, req); + spin_unlock_irqrestore(&ns->head->requeue_lock, flags); + blk_mq_end_request(req, 0); + kblockd_schedule_work(&ns->head->requeue_work); + return true; } void nvme_kick_requeue_lists(struct nvme_ctrl *ctrl) diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index 2bd9f7c3084f..b7117fb09dd0 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -253,6 +253,7 @@ struct nvme_ctrl { struct nvme_command ka_cmd; struct work_struct fw_act_work; unsigned long events; + bool created; #ifdef CONFIG_NVME_MULTIPATH /* asymmetric namespace access: */ @@ -530,7 +531,7 @@ void nvme_mpath_wait_freeze(struct nvme_subsystem *subsys); void nvme_mpath_start_freeze(struct nvme_subsystem *subsys); void nvme_set_disk_name(char *disk_name, struct nvme_ns *ns, struct nvme_ctrl *ctrl, int *flags); -void nvme_failover_req(struct request *req); +bool nvme_failover_req(struct request *req); void nvme_kick_requeue_lists(struct nvme_ctrl *ctrl); int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl,struct nvme_ns_head *head); void nvme_mpath_add_disk(struct nvme_ns *ns, struct nvme_id_ns *id); @@ -560,6 +561,16 @@ static inline void nvme_trace_bio_complete(struct request *req, req->bio, status); } +static inline void nvme_mpath_update_disk_size(struct gendisk *disk) +{ + struct block_device *bdev = bdget_disk(disk, 0); + + if (bdev) { + bd_set_size(bdev, get_capacity(disk) << SECTOR_SHIFT); + bdput(bdev); + } +} + extern struct device_attribute dev_attr_ana_grpid; extern struct device_attribute dev_attr_ana_state; extern struct device_attribute subsys_attr_iopolicy; @@ -579,8 +590,9 @@ static inline void nvme_set_disk_name(char *disk_name, struct nvme_ns *ns, sprintf(disk_name, "nvme%dn%d", ctrl->instance, ns->head->instance); } -static inline void nvme_failover_req(struct request *req) +static inline bool nvme_failover_req(struct request *req) { + return false; } static inline void nvme_kick_requeue_lists(struct nvme_ctrl *ctrl) { @@ -634,6 +646,9 @@ static inline void nvme_mpath_wait_freeze(struct nvme_subsystem *subsys) static inline void nvme_mpath_start_freeze(struct nvme_subsystem *subsys) { } +static inline void nvme_mpath_update_disk_size(struct gendisk *disk) +{ +} #endif /* CONFIG_NVME_MULTIPATH */ #ifdef CONFIG_NVM diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index a91433bdf5de..75f26d2ec642 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -2850,7 +2850,6 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id) dev_info(dev->ctrl.device, "pci function %s\n", dev_name(&pdev->dev)); nvme_reset_ctrl(&dev->ctrl); - nvme_get_ctrl(&dev->ctrl); async_schedule(nvme_async_probe, dev); return 0; diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index f9444272f861..abe4fe496d05 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -2088,8 +2088,6 @@ static struct nvme_ctrl *nvme_rdma_create_ctrl(struct device *dev, dev_info(ctrl->ctrl.device, "new ctrl: NQN \"%s\", addr %pISpcs\n", ctrl->ctrl.opts->subsysnqn, &ctrl->addr); - nvme_get_ctrl(&ctrl->ctrl); - mutex_lock(&nvme_rdma_ctrl_mutex); list_add_tail(&ctrl->list, &nvme_rdma_ctrl_list); mutex_unlock(&nvme_rdma_ctrl_mutex); @@ -2099,6 +2097,7 @@ static struct nvme_ctrl *nvme_rdma_create_ctrl(struct device *dev, out_uninit_ctrl: nvme_uninit_ctrl(&ctrl->ctrl); nvme_put_ctrl(&ctrl->ctrl); + nvme_put_ctrl(&ctrl->ctrl); if (ret > 0) ret = -EIO; return ERR_PTR(ret); diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c index c782005ee99f..6d7a813e7183 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -2404,8 +2404,6 @@ static struct nvme_ctrl *nvme_tcp_create_ctrl(struct device *dev, dev_info(ctrl->ctrl.device, "new ctrl: NQN \"%s\", addr %pISp\n", ctrl->ctrl.opts->subsysnqn, &ctrl->addr); - nvme_get_ctrl(&ctrl->ctrl); - mutex_lock(&nvme_tcp_ctrl_mutex); list_add_tail(&ctrl->list, &nvme_tcp_ctrl_list); mutex_unlock(&nvme_tcp_ctrl_mutex); @@ -2415,6 +2413,7 @@ static struct nvme_ctrl *nvme_tcp_create_ctrl(struct device *dev, out_uninit_ctrl: nvme_uninit_ctrl(&ctrl->ctrl); nvme_put_ctrl(&ctrl->ctrl); + nvme_put_ctrl(&ctrl->ctrl); if (ret > 0) ret = -EIO; return ERR_PTR(ret); diff --git a/drivers/nvme/target/loop.c b/drivers/nvme/target/loop.c index 11f5aea97d1b..82b87a4c50f6 100644 --- a/drivers/nvme/target/loop.c +++ b/drivers/nvme/target/loop.c @@ -619,8 +619,6 @@ static struct nvme_ctrl *nvme_loop_create_ctrl(struct device *dev, dev_info(ctrl->ctrl.device, "new ctrl: \"%s\"\n", ctrl->ctrl.opts->subsysnqn); - nvme_get_ctrl(&ctrl->ctrl); - changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE); WARN_ON_ONCE(!changed); @@ -638,6 +636,7 @@ static struct nvme_ctrl *nvme_loop_create_ctrl(struct device *dev, kfree(ctrl->queues); out_uninit_ctrl: nvme_uninit_ctrl(&ctrl->ctrl); + nvme_put_ctrl(&ctrl->ctrl); out_put_ctrl: nvme_put_ctrl(&ctrl->ctrl); if (ret > 0) diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c index 36d906a7f70d..b5314164479e 100644 --- a/drivers/nvme/target/rdma.c +++ b/drivers/nvme/target/rdma.c @@ -75,6 +75,7 @@ enum nvmet_rdma_queue_state { struct nvmet_rdma_queue { struct rdma_cm_id *cm_id; + struct ib_qp *qp; struct nvmet_port *port; struct ib_cq *cq; atomic_t sq_wr_avail; @@ -464,7 +465,7 @@ static int nvmet_rdma_post_recv(struct nvmet_rdma_device *ndev, if (ndev->srq) ret = ib_post_srq_recv(ndev->srq, &cmd->wr, NULL); else - ret = ib_post_recv(cmd->queue->cm_id->qp, &cmd->wr, NULL); + ret = ib_post_recv(cmd->queue->qp, &cmd->wr, NULL); if (unlikely(ret)) pr_err("post_recv cmd failed\n"); @@ -503,7 +504,7 @@ static void nvmet_rdma_release_rsp(struct nvmet_rdma_rsp *rsp) atomic_add(1 + rsp->n_rdma, &queue->sq_wr_avail); if (rsp->n_rdma) { - rdma_rw_ctx_destroy(&rsp->rw, queue->cm_id->qp, + rdma_rw_ctx_destroy(&rsp->rw, queue->qp, queue->cm_id->port_num, rsp->req.sg, rsp->req.sg_cnt, nvmet_data_dir(&rsp->req)); } @@ -587,7 +588,7 @@ static void nvmet_rdma_read_data_done(struct ib_cq *cq, struct ib_wc *wc) WARN_ON(rsp->n_rdma <= 0); atomic_add(rsp->n_rdma, &queue->sq_wr_avail); - rdma_rw_ctx_destroy(&rsp->rw, queue->cm_id->qp, + rdma_rw_ctx_destroy(&rsp->rw, queue->qp, queue->cm_id->port_num, rsp->req.sg, rsp->req.sg_cnt, nvmet_data_dir(&rsp->req)); rsp->n_rdma = 0; @@ -742,7 +743,7 @@ static bool nvmet_rdma_execute_command(struct nvmet_rdma_rsp *rsp) } if (nvmet_rdma_need_data_in(rsp)) { - if (rdma_rw_ctx_post(&rsp->rw, queue->cm_id->qp, + if (rdma_rw_ctx_post(&rsp->rw, queue->qp, queue->cm_id->port_num, &rsp->read_cqe, NULL)) nvmet_req_complete(&rsp->req, NVME_SC_DATA_XFER_ERROR); } else { @@ -1025,6 +1026,7 @@ static int nvmet_rdma_create_queue_ib(struct nvmet_rdma_queue *queue) pr_err("failed to create_qp ret= %d\n", ret); goto err_destroy_cq; } + queue->qp = queue->cm_id->qp; atomic_set(&queue->sq_wr_avail, qp_attr.cap.max_send_wr); @@ -1053,11 +1055,10 @@ static int nvmet_rdma_create_queue_ib(struct nvmet_rdma_queue *queue) static void nvmet_rdma_destroy_queue_ib(struct nvmet_rdma_queue *queue) { - struct ib_qp *qp = queue->cm_id->qp; - - ib_drain_qp(qp); - rdma_destroy_id(queue->cm_id); - ib_destroy_qp(qp); + ib_drain_qp(queue->qp); + if (queue->cm_id) + rdma_destroy_id(queue->cm_id); + ib_destroy_qp(queue->qp); ib_free_cq(queue->cq); } @@ -1291,9 +1292,12 @@ static int nvmet_rdma_queue_connect(struct rdma_cm_id *cm_id, ret = nvmet_rdma_cm_accept(cm_id, queue, &event->param.conn); if (ret) { - schedule_work(&queue->release_work); - /* Destroying rdma_cm id is not needed here */ - return 0; + /* + * Don't destroy the cm_id in free path, as we implicitly + * destroy the cm_id here with non-zero ret code. + */ + queue->cm_id = NULL; + goto free_queue; } mutex_lock(&nvmet_rdma_queue_mutex); @@ -1302,6 +1306,8 @@ static int nvmet_rdma_queue_connect(struct rdma_cm_id *cm_id, return 0; +free_queue: + nvmet_rdma_free_queue(queue); put_device: kref_put(&ndev->ref, nvmet_rdma_free_dev); diff --git a/drivers/opp/core.c b/drivers/opp/core.c index 7b057c32e11b..29dfaa591f8b 100644 --- a/drivers/opp/core.c +++ b/drivers/opp/core.c @@ -990,7 +990,6 @@ static struct opp_table *_allocate_opp_table(struct device *dev, int index) BLOCKING_INIT_NOTIFIER_HEAD(&opp_table->head); INIT_LIST_HEAD(&opp_table->opp_list); kref_init(&opp_table->kref); - kref_init(&opp_table->list_kref); /* Secure the device table modification */ list_add(&opp_table->node, &opp_tables); @@ -1074,33 +1073,6 @@ static void _opp_table_kref_release(struct kref *kref) mutex_unlock(&opp_table_lock); } -void _opp_remove_all_static(struct opp_table *opp_table) -{ - struct dev_pm_opp *opp, *tmp; - - list_for_each_entry_safe(opp, tmp, &opp_table->opp_list, node) { - if (!opp->dynamic) - dev_pm_opp_put(opp); - } - - opp_table->parsed_static_opps = false; -} - -static void _opp_table_list_kref_release(struct kref *kref) -{ - struct opp_table *opp_table = container_of(kref, struct opp_table, - list_kref); - - _opp_remove_all_static(opp_table); - mutex_unlock(&opp_table_lock); -} - -void _put_opp_list_kref(struct opp_table *opp_table) -{ - kref_put_mutex(&opp_table->list_kref, _opp_table_list_kref_release, - &opp_table_lock); -} - void dev_pm_opp_put_opp_table(struct opp_table *opp_table) { kref_put_mutex(&opp_table->kref, _opp_table_kref_release, @@ -1204,6 +1176,24 @@ void dev_pm_opp_remove(struct device *dev, unsigned long freq) } EXPORT_SYMBOL_GPL(dev_pm_opp_remove); +void _opp_remove_all_static(struct opp_table *opp_table) +{ + struct dev_pm_opp *opp, *tmp; + + mutex_lock(&opp_table->lock); + + if (!opp_table->parsed_static_opps || --opp_table->parsed_static_opps) + goto unlock; + + list_for_each_entry_safe(opp, tmp, &opp_table->opp_list, node) { + if (!opp->dynamic) + dev_pm_opp_put_unlocked(opp); + } + +unlock: + mutex_unlock(&opp_table->lock); +} + /** * dev_pm_opp_remove_all_dynamic() - Remove all dynamically created OPPs * @dev: device for which we do this operation @@ -2209,7 +2199,7 @@ void _dev_pm_opp_find_and_remove_table(struct device *dev) return; } - _put_opp_list_kref(opp_table); + _opp_remove_all_static(opp_table); /* Drop reference taken by _find_opp_table() */ dev_pm_opp_put_opp_table(opp_table); diff --git a/drivers/opp/of.c b/drivers/opp/of.c index 1e5fcdee043c..249738e1e0b7 100644 --- a/drivers/opp/of.c +++ b/drivers/opp/of.c @@ -658,17 +658,15 @@ static int _of_add_opp_table_v2(struct device *dev, struct opp_table *opp_table) struct dev_pm_opp *opp; /* OPP table is already initialized for the device */ + mutex_lock(&opp_table->lock); if (opp_table->parsed_static_opps) { - kref_get(&opp_table->list_kref); + opp_table->parsed_static_opps++; + mutex_unlock(&opp_table->lock); return 0; } - /* - * Re-initialize list_kref every time we add static OPPs to the OPP - * table as the reference count may be 0 after the last tie static OPPs - * were removed. - */ - kref_init(&opp_table->list_kref); + opp_table->parsed_static_opps = 1; + mutex_unlock(&opp_table->lock); /* We have opp-table node now, iterate over it and add OPPs */ for_each_available_child_of_node(opp_table->np, np) { @@ -678,7 +676,7 @@ static int _of_add_opp_table_v2(struct device *dev, struct opp_table *opp_table) dev_err(dev, "%s: Failed to add OPP, %d\n", __func__, ret); of_node_put(np); - goto put_list_kref; + goto remove_static_opp; } else if (opp) { count++; } @@ -687,7 +685,7 @@ static int _of_add_opp_table_v2(struct device *dev, struct opp_table *opp_table) /* There should be one of more OPP defined */ if (WARN_ON(!count)) { ret = -ENOENT; - goto put_list_kref; + goto remove_static_opp; } list_for_each_entry(opp, &opp_table->opp_list, node) @@ -698,18 +696,16 @@ static int _of_add_opp_table_v2(struct device *dev, struct opp_table *opp_table) dev_err(dev, "Not all nodes have performance state set (%d: %d)\n", count, pstate_count); ret = -ENOENT; - goto put_list_kref; + goto remove_static_opp; } if (pstate_count) opp_table->genpd_performance_state = true; - opp_table->parsed_static_opps = true; - return 0; -put_list_kref: - _put_opp_list_kref(opp_table); +remove_static_opp: + _opp_remove_all_static(opp_table); return ret; } @@ -737,6 +733,10 @@ static int _of_add_opp_table_v1(struct device *dev, struct opp_table *opp_table) return -EINVAL; } + mutex_lock(&opp_table->lock); + opp_table->parsed_static_opps = 1; + mutex_unlock(&opp_table->lock); + val = prop->value; while (nr) { unsigned long freq = be32_to_cpup(val++) * 1000; @@ -746,7 +746,7 @@ static int _of_add_opp_table_v1(struct device *dev, struct opp_table *opp_table) if (ret) { dev_err(dev, "%s: Failed to add OPP %ld (%d)\n", __func__, freq, ret); - _put_opp_list_kref(opp_table); + _opp_remove_all_static(opp_table); return ret; } nr -= 2; diff --git a/drivers/opp/opp.h b/drivers/opp/opp.h index 01a500e2c40a..d14e27102730 100644 --- a/drivers/opp/opp.h +++ b/drivers/opp/opp.h @@ -127,11 +127,10 @@ enum opp_table_access { * @dev_list: list of devices that share these OPPs * @opp_list: table of opps * @kref: for reference count of the table. - * @list_kref: for reference count of the OPP list. * @lock: mutex protecting the opp_list and dev_list. * @np: struct device_node pointer for opp's DT node. * @clock_latency_ns_max: Max clock latency in nanoseconds. - * @parsed_static_opps: True if OPPs are initialized from DT. + * @parsed_static_opps: Count of devices for which OPPs are initialized from DT. * @shared_opp: OPP is shared between multiple devices. * @suspend_opp: Pointer to OPP to be used during device suspend. * @genpd_virt_dev_lock: Mutex protecting the genpd virtual device pointers. @@ -167,7 +166,6 @@ struct opp_table { struct list_head dev_list; struct list_head opp_list; struct kref kref; - struct kref list_kref; struct mutex lock; struct device_node *np; @@ -176,7 +174,7 @@ struct opp_table { /* For backward compatibility with v1 bindings */ unsigned int voltage_tolerance_v1; - bool parsed_static_opps; + unsigned int parsed_static_opps; enum opp_table_access shared_opp; struct dev_pm_opp *suspend_opp; diff --git a/drivers/pci/controller/dwc/pcie-tegra194.c b/drivers/pci/controller/dwc/pcie-tegra194.c index f89f5acee72d..c06b05ab9f78 100644 --- a/drivers/pci/controller/dwc/pcie-tegra194.c +++ b/drivers/pci/controller/dwc/pcie-tegra194.c @@ -1395,7 +1395,7 @@ static int tegra_pcie_config_rp(struct tegra_pcie_dw *pcie) ret = pinctrl_pm_select_default_state(dev); if (ret < 0) { dev_err(dev, "Failed to configure sideband pins: %d\n", ret); - goto fail_pinctrl; + goto fail_pm_get_sync; } tegra_pcie_init_controller(pcie); @@ -1422,9 +1422,8 @@ static int tegra_pcie_config_rp(struct tegra_pcie_dw *pcie) fail_host_init: tegra_pcie_deinit_controller(pcie); -fail_pinctrl: - pm_runtime_put_sync(dev); fail_pm_get_sync: + pm_runtime_put_sync(dev); pm_runtime_disable(dev); return ret; } diff --git a/drivers/pci/controller/pci-tegra.c b/drivers/pci/controller/pci-tegra.c index b71e753419c2..cfa3c83d6cc7 100644 --- a/drivers/pci/controller/pci-tegra.c +++ b/drivers/pci/controller/pci-tegra.c @@ -2768,7 +2768,7 @@ static int tegra_pcie_probe(struct platform_device *pdev) err = pm_runtime_get_sync(pcie->dev); if (err < 0) { dev_err(dev, "fail to enable pcie controller: %d\n", err); - goto teardown_msi; + goto pm_runtime_put; } err = tegra_pcie_request_resources(pcie); @@ -2808,7 +2808,6 @@ static int tegra_pcie_probe(struct platform_device *pdev) pm_runtime_put: pm_runtime_put_sync(pcie->dev); pm_runtime_disable(pcie->dev); -teardown_msi: tegra_pcie_msi_teardown(pcie); put_resources: tegra_pcie_put_resources(pcie); diff --git a/drivers/pci/hotplug/pciehp_hpc.c b/drivers/pci/hotplug/pciehp_hpc.c index 356786a3b7f4..88b996764ff9 100644 --- a/drivers/pci/hotplug/pciehp_hpc.c +++ b/drivers/pci/hotplug/pciehp_hpc.c @@ -529,7 +529,7 @@ static irqreturn_t pciehp_isr(int irq, void *dev_id) struct controller *ctrl = (struct controller *)dev_id; struct pci_dev *pdev = ctrl_dev(ctrl); struct device *parent = pdev->dev.parent; - u16 status, events; + u16 status, events = 0; /* * Interrupts only occur in D3hot or shallower and only if enabled @@ -554,6 +554,7 @@ static irqreturn_t pciehp_isr(int irq, void *dev_id) } } +read_status: pcie_capability_read_word(pdev, PCI_EXP_SLTSTA, &status); if (status == (u16) ~0) { ctrl_info(ctrl, "%s: no response from device\n", __func__); @@ -566,24 +567,37 @@ static irqreturn_t pciehp_isr(int irq, void *dev_id) * Slot Status contains plain status bits as well as event * notification bits; right now we only want the event bits. */ - events = status & (PCI_EXP_SLTSTA_ABP | PCI_EXP_SLTSTA_PFD | - PCI_EXP_SLTSTA_PDC | PCI_EXP_SLTSTA_CC | - PCI_EXP_SLTSTA_DLLSC); + status &= PCI_EXP_SLTSTA_ABP | PCI_EXP_SLTSTA_PFD | + PCI_EXP_SLTSTA_PDC | PCI_EXP_SLTSTA_CC | + PCI_EXP_SLTSTA_DLLSC; /* * If we've already reported a power fault, don't report it again * until we've done something to handle it. */ if (ctrl->power_fault_detected) - events &= ~PCI_EXP_SLTSTA_PFD; + status &= ~PCI_EXP_SLTSTA_PFD; + events |= status; if (!events) { if (parent) pm_runtime_put(parent); return IRQ_NONE; } - pcie_capability_write_word(pdev, PCI_EXP_SLTSTA, events); + if (status) { + pcie_capability_write_word(pdev, PCI_EXP_SLTSTA, events); + + /* + * In MSI mode, all event bits must be zero before the port + * will send a new interrupt (PCIe Base Spec r5.0 sec 6.7.3.4). + * So re-read the Slot Status register in case a bit was set + * between read and write. + */ + if (pci_dev_msi_enabled(pdev) && !pciehp_poll_mode) + goto read_status; + } + ctrl_dbg(ctrl, "pending interrupts %#06x from Slot Status\n", events); if (parent) pm_runtime_put(parent); diff --git a/drivers/pci/iov.c b/drivers/pci/iov.c index deec9f9e0b61..9c116cbaa95d 100644 --- a/drivers/pci/iov.c +++ b/drivers/pci/iov.c @@ -253,8 +253,14 @@ static ssize_t sriov_numvfs_show(struct device *dev, char *buf) { struct pci_dev *pdev = to_pci_dev(dev); + u16 num_vfs; + + /* Serialize vs sriov_numvfs_store() so readers see valid num_VFs */ + device_lock(&pdev->dev); + num_vfs = pdev->sriov->num_VFs; + device_unlock(&pdev->dev); - return sprintf(buf, "%u\n", pdev->sriov->num_VFs); + return sprintf(buf, "%u\n", num_vfs); } /* diff --git a/drivers/pci/rom.c b/drivers/pci/rom.c index 137bf0cee897..8fc9a4e911e3 100644 --- a/drivers/pci/rom.c +++ b/drivers/pci/rom.c @@ -195,20 +195,3 @@ void pci_unmap_rom(struct pci_dev *pdev, void __iomem *rom) pci_disable_rom(pdev); } EXPORT_SYMBOL(pci_unmap_rom); - -/** - * pci_platform_rom - provides a pointer to any ROM image provided by the - * platform - * @pdev: pointer to pci device struct - * @size: pointer to receive size of pci window over ROM - */ -void __iomem *pci_platform_rom(struct pci_dev *pdev, size_t *size) -{ - if (pdev->rom && pdev->romlen) { - *size = pdev->romlen; - return phys_to_virt((phys_addr_t)pdev->rom); - } - - return NULL; -} -EXPORT_SYMBOL(pci_platform_rom); diff --git a/drivers/pci/setup-bus.c b/drivers/pci/setup-bus.c index 5356630e0e48..44f4866d95d8 100644 --- a/drivers/pci/setup-bus.c +++ b/drivers/pci/setup-bus.c @@ -752,24 +752,32 @@ static void pci_bridge_check_ranges(struct pci_bus *bus) } /* - * Helper function for sizing routines: find first available bus resource - * of a given type. Note: we intentionally skip the bus resources which - * have already been assigned (that is, have non-NULL parent resource). + * Helper function for sizing routines. Assigned resources have non-NULL + * parent resource. + * + * Return first unassigned resource of the correct type. If there is none, + * return first assigned resource of the correct type. If none of the + * above, return NULL. + * + * Returning an assigned resource of the correct type allows the caller to + * distinguish between already assigned and no resource of the correct type. */ -static struct resource *find_free_bus_resource(struct pci_bus *bus, - unsigned long type_mask, - unsigned long type) +static struct resource *find_bus_resource_of_type(struct pci_bus *bus, + unsigned long type_mask, + unsigned long type) { + struct resource *r, *r_assigned = NULL; int i; - struct resource *r; pci_bus_for_each_resource(bus, r, i) { if (r == &ioport_resource || r == &iomem_resource) continue; if (r && (r->flags & type_mask) == type && !r->parent) return r; + if (r && (r->flags & type_mask) == type && !r_assigned) + r_assigned = r; } - return NULL; + return r_assigned; } static resource_size_t calculate_iosize(resource_size_t size, @@ -866,8 +874,8 @@ static void pbus_size_io(struct pci_bus *bus, resource_size_t min_size, struct list_head *realloc_head) { struct pci_dev *dev; - struct resource *b_res = find_free_bus_resource(bus, IORESOURCE_IO, - IORESOURCE_IO); + struct resource *b_res = find_bus_resource_of_type(bus, IORESOURCE_IO, + IORESOURCE_IO); resource_size_t size = 0, size0 = 0, size1 = 0; resource_size_t children_add_size = 0; resource_size_t min_align, align; @@ -875,6 +883,10 @@ static void pbus_size_io(struct pci_bus *bus, resource_size_t min_size, if (!b_res) return; + /* If resource is already assigned, nothing more to do */ + if (b_res->parent) + return; + min_align = window_alignment(bus, IORESOURCE_IO); list_for_each_entry(dev, &bus->devices, bus_list) { int i; @@ -978,7 +990,7 @@ static int pbus_size_mem(struct pci_bus *bus, unsigned long mask, resource_size_t min_align, align, size, size0, size1; resource_size_t aligns[18]; /* Alignments from 1MB to 128GB */ int order, max_order; - struct resource *b_res = find_free_bus_resource(bus, + struct resource *b_res = find_bus_resource_of_type(bus, mask | IORESOURCE_PREFETCH, type); resource_size_t children_add_size = 0; resource_size_t children_add_align = 0; @@ -987,6 +999,10 @@ static int pbus_size_mem(struct pci_bus *bus, unsigned long mask, if (!b_res) return -ENOSPC; + /* If resource is already assigned, nothing more to do */ + if (b_res->parent) + return 0; + memset(aligns, 0, sizeof(aligns)); max_order = 0; size = 0; diff --git a/drivers/phy/samsung/phy-s5pv210-usb2.c b/drivers/phy/samsung/phy-s5pv210-usb2.c index 56a5083fe6f9..32be62e49804 100644 --- a/drivers/phy/samsung/phy-s5pv210-usb2.c +++ b/drivers/phy/samsung/phy-s5pv210-usb2.c @@ -139,6 +139,10 @@ static void s5pv210_phy_pwr(struct samsung_usb2_phy_instance *inst, bool on) udelay(10); rst &= ~rstbits; writel(rst, drv->reg_phy + S5PV210_UPHYRST); + /* The following delay is necessary for the reset sequence to be + * completed + */ + udelay(80); } else { pwr = readl(drv->reg_phy + S5PV210_UPHYPWR); pwr |= phypwr; diff --git a/drivers/power/supply/max17040_battery.c b/drivers/power/supply/max17040_battery.c index 62499018e68b..2e845045a3fc 100644 --- a/drivers/power/supply/max17040_battery.c +++ b/drivers/power/supply/max17040_battery.c @@ -105,7 +105,7 @@ static void max17040_get_vcell(struct i2c_client *client) vcell = max17040_read_reg(client, MAX17040_VCELL); - chip->vcell = vcell; + chip->vcell = (vcell >> 4) * 1250; } static void max17040_get_soc(struct i2c_client *client) diff --git a/drivers/rapidio/devices/rio_mport_cdev.c b/drivers/rapidio/devices/rio_mport_cdev.c index 10af330153b5..0b85a80ae7ef 100644 --- a/drivers/rapidio/devices/rio_mport_cdev.c +++ b/drivers/rapidio/devices/rio_mport_cdev.c @@ -2384,13 +2384,6 @@ static struct mport_dev *mport_cdev_add(struct rio_mport *mport) cdev_init(&md->cdev, &mport_fops); md->cdev.owner = THIS_MODULE; - ret = cdev_device_add(&md->cdev, &md->dev); - if (ret) { - rmcd_error("Failed to register mport %d (err=%d)", - mport->id, ret); - goto err_cdev; - } - INIT_LIST_HEAD(&md->doorbells); spin_lock_init(&md->db_lock); INIT_LIST_HEAD(&md->portwrites); @@ -2410,6 +2403,13 @@ static struct mport_dev *mport_cdev_add(struct rio_mport *mport) #else md->properties.transfer_mode |= RIO_TRANSFER_MODE_TRANSFER; #endif + + ret = cdev_device_add(&md->cdev, &md->dev); + if (ret) { + rmcd_error("Failed to register mport %d (err=%d)", + mport->id, ret); + goto err_cdev; + } ret = rio_query_mport(mport, &attr); if (!ret) { md->properties.flags = attr.flags; diff --git a/drivers/regulator/axp20x-regulator.c b/drivers/regulator/axp20x-regulator.c index 16f0c8570036..7075f42b9fcf 100644 --- a/drivers/regulator/axp20x-regulator.c +++ b/drivers/regulator/axp20x-regulator.c @@ -42,8 +42,9 @@ #define AXP20X_DCDC2_V_OUT_MASK GENMASK(5, 0) #define AXP20X_DCDC3_V_OUT_MASK GENMASK(7, 0) -#define AXP20X_LDO24_V_OUT_MASK GENMASK(7, 4) +#define AXP20X_LDO2_V_OUT_MASK GENMASK(7, 4) #define AXP20X_LDO3_V_OUT_MASK GENMASK(6, 0) +#define AXP20X_LDO4_V_OUT_MASK GENMASK(3, 0) #define AXP20X_LDO5_V_OUT_MASK GENMASK(7, 4) #define AXP20X_PWR_OUT_EXTEN_MASK BIT_MASK(0) @@ -544,14 +545,14 @@ static const struct regulator_desc axp20x_regulators[] = { AXP20X_PWR_OUT_CTRL, AXP20X_PWR_OUT_DCDC3_MASK), AXP_DESC_FIXED(AXP20X, LDO1, "ldo1", "acin", 1300), AXP_DESC(AXP20X, LDO2, "ldo2", "ldo24in", 1800, 3300, 100, - AXP20X_LDO24_V_OUT, AXP20X_LDO24_V_OUT_MASK, + AXP20X_LDO24_V_OUT, AXP20X_LDO2_V_OUT_MASK, AXP20X_PWR_OUT_CTRL, AXP20X_PWR_OUT_LDO2_MASK), AXP_DESC(AXP20X, LDO3, "ldo3", "ldo3in", 700, 3500, 25, AXP20X_LDO3_V_OUT, AXP20X_LDO3_V_OUT_MASK, AXP20X_PWR_OUT_CTRL, AXP20X_PWR_OUT_LDO3_MASK), AXP_DESC_RANGES(AXP20X, LDO4, "ldo4", "ldo24in", axp20x_ldo4_ranges, AXP20X_LDO4_V_OUT_NUM_VOLTAGES, - AXP20X_LDO24_V_OUT, AXP20X_LDO24_V_OUT_MASK, + AXP20X_LDO24_V_OUT, AXP20X_LDO4_V_OUT_MASK, AXP20X_PWR_OUT_CTRL, AXP20X_PWR_OUT_LDO4_MASK), AXP_DESC_IO(AXP20X, LDO5, "ldo5", "ldo5in", 1800, 3300, 100, AXP20X_LDO5_V_OUT, AXP20X_LDO5_V_OUT_MASK, diff --git a/drivers/rtc/rtc-ds1374.c b/drivers/rtc/rtc-ds1374.c index 367497914c10..28eb96cbaf98 100644 --- a/drivers/rtc/rtc-ds1374.c +++ b/drivers/rtc/rtc-ds1374.c @@ -620,6 +620,10 @@ static int ds1374_probe(struct i2c_client *client, if (!ds1374) return -ENOMEM; + ds1374->rtc = devm_rtc_allocate_device(&client->dev); + if (IS_ERR(ds1374->rtc)) + return PTR_ERR(ds1374->rtc); + ds1374->client = client; i2c_set_clientdata(client, ds1374); @@ -641,12 +645,11 @@ static int ds1374_probe(struct i2c_client *client, device_set_wakeup_capable(&client->dev, 1); } - ds1374->rtc = devm_rtc_device_register(&client->dev, client->name, - &ds1374_rtc_ops, THIS_MODULE); - if (IS_ERR(ds1374->rtc)) { - dev_err(&client->dev, "unable to register the class device\n"); - return PTR_ERR(ds1374->rtc); - } + ds1374->rtc->ops = &ds1374_rtc_ops; + + ret = rtc_register_device(ds1374->rtc); + if (ret) + return ret; #ifdef CONFIG_RTC_DRV_DS1374_WDT save_client = client; diff --git a/drivers/rtc/rtc-sa1100.c b/drivers/rtc/rtc-sa1100.c index 86fa723b3b76..795273269d58 100644 --- a/drivers/rtc/rtc-sa1100.c +++ b/drivers/rtc/rtc-sa1100.c @@ -182,7 +182,6 @@ static const struct rtc_class_ops sa1100_rtc_ops = { int sa1100_rtc_init(struct platform_device *pdev, struct sa1100_rtc *info) { - struct rtc_device *rtc; int ret; spin_lock_init(&info->lock); @@ -211,15 +210,14 @@ int sa1100_rtc_init(struct platform_device *pdev, struct sa1100_rtc *info) writel_relaxed(0, info->rcnr); } - rtc = devm_rtc_device_register(&pdev->dev, pdev->name, &sa1100_rtc_ops, - THIS_MODULE); - if (IS_ERR(rtc)) { + info->rtc->ops = &sa1100_rtc_ops; + info->rtc->max_user_freq = RTC_FREQ; + + ret = rtc_register_device(info->rtc); + if (ret) { clk_disable_unprepare(info->clk); - return PTR_ERR(rtc); + return ret; } - info->rtc = rtc; - - rtc->max_user_freq = RTC_FREQ; /* Fix for a nasty initialization problem the in SA11xx RTSR register. * See also the comments in sa1100_rtc_interrupt(). @@ -268,6 +266,10 @@ static int sa1100_rtc_probe(struct platform_device *pdev) info->irq_1hz = irq_1hz; info->irq_alarm = irq_alarm; + info->rtc = devm_rtc_allocate_device(&pdev->dev); + if (IS_ERR(info->rtc)) + return PTR_ERR(info->rtc); + ret = devm_request_irq(&pdev->dev, irq_1hz, sa1100_rtc_interrupt, 0, "rtc 1Hz", &pdev->dev); if (ret) { diff --git a/drivers/s390/block/dasd_fba.c b/drivers/s390/block/dasd_fba.c index cbb770824226..1a44e321b54e 100644 --- a/drivers/s390/block/dasd_fba.c +++ b/drivers/s390/block/dasd_fba.c @@ -40,6 +40,7 @@ MODULE_LICENSE("GPL"); static struct dasd_discipline dasd_fba_discipline; +static void *dasd_fba_zero_page; struct dasd_fba_private { struct dasd_fba_characteristics rdc_data; @@ -270,7 +271,7 @@ static void ccw_write_zero(struct ccw1 *ccw, int count) ccw->cmd_code = DASD_FBA_CCW_WRITE; ccw->flags |= CCW_FLAG_SLI; ccw->count = count; - ccw->cda = (__u32) (addr_t) page_to_phys(ZERO_PAGE(0)); + ccw->cda = (__u32) (addr_t) dasd_fba_zero_page; } /* @@ -830,6 +831,11 @@ dasd_fba_init(void) int ret; ASCEBC(dasd_fba_discipline.ebcname, 4); + + dasd_fba_zero_page = (void *)get_zeroed_page(GFP_KERNEL | GFP_DMA); + if (!dasd_fba_zero_page) + return -ENOMEM; + ret = ccw_driver_register(&dasd_fba_driver); if (!ret) wait_for_device_probe(); @@ -841,6 +847,7 @@ static void __exit dasd_fba_cleanup(void) { ccw_driver_unregister(&dasd_fba_driver); + free_page((unsigned long)dasd_fba_zero_page); } module_init(dasd_fba_init); diff --git a/drivers/s390/cio/airq.c b/drivers/s390/cio/airq.c index 427b2e24a8ce..cb466ed7eb5e 100644 --- a/drivers/s390/cio/airq.c +++ b/drivers/s390/cio/airq.c @@ -105,16 +105,12 @@ static irqreturn_t do_airq_interrupt(int irq, void *dummy) return IRQ_HANDLED; } -static struct irqaction airq_interrupt = { - .name = "AIO", - .handler = do_airq_interrupt, -}; - void __init init_airq_interrupts(void) { irq_set_chip_and_handler(THIN_INTERRUPT, &dummy_irq_chip, handle_percpu_irq); - setup_irq(THIN_INTERRUPT, &airq_interrupt); + if (request_irq(THIN_INTERRUPT, do_airq_interrupt, 0, "AIO", NULL)) + panic("Failed to register AIO interrupt\n"); } static inline unsigned long iv_size(unsigned long bits) diff --git a/drivers/s390/cio/cio.c b/drivers/s390/cio/cio.c index 18f5458f90e8..6d716db2a46a 100644 --- a/drivers/s390/cio/cio.c +++ b/drivers/s390/cio/cio.c @@ -563,16 +563,12 @@ static irqreturn_t do_cio_interrupt(int irq, void *dummy) return IRQ_HANDLED; } -static struct irqaction io_interrupt = { - .name = "I/O", - .handler = do_cio_interrupt, -}; - void __init init_cio_interrupts(void) { irq_set_chip_and_handler(IO_INTERRUPT, &dummy_irq_chip, handle_percpu_irq); - setup_irq(IO_INTERRUPT, &io_interrupt); + if (request_irq(IO_INTERRUPT, do_cio_interrupt, 0, "I/O", NULL)) + panic("Failed to register I/O interrupt\n"); } #ifdef CONFIG_CCW_CONSOLE diff --git a/drivers/s390/crypto/zcrypt_api.c b/drivers/s390/crypto/zcrypt_api.c index 7fa0262e91af..ec41a8a76398 100644 --- a/drivers/s390/crypto/zcrypt_api.c +++ b/drivers/s390/crypto/zcrypt_api.c @@ -1419,7 +1419,8 @@ static long zcrypt_unlocked_ioctl(struct file *filp, unsigned int cmd, if (!reqcnt) return -ENOMEM; zcrypt_perdev_reqcnt(reqcnt, AP_DEVICES); - if (copy_to_user((int __user *) arg, reqcnt, sizeof(reqcnt))) + if (copy_to_user((int __user *) arg, reqcnt, + sizeof(u32) * AP_DEVICES)) rc = -EFAULT; kfree(reqcnt); return rc; diff --git a/drivers/scsi/aacraid/aachba.c b/drivers/scsi/aacraid/aachba.c index 0ed3f806ace5..2388143d59f5 100644 --- a/drivers/scsi/aacraid/aachba.c +++ b/drivers/scsi/aacraid/aachba.c @@ -2467,13 +2467,13 @@ static int aac_read(struct scsi_cmnd * scsicmd) scsicmd->result = DID_OK << 16 | COMMAND_COMPLETE << 8 | SAM_STAT_CHECK_CONDITION; set_sense(&dev->fsa_dev[cid].sense_data, - HARDWARE_ERROR, SENCODE_INTERNAL_TARGET_FAILURE, + ILLEGAL_REQUEST, SENCODE_LBA_OUT_OF_RANGE, ASENCODE_INTERNAL_TARGET_FAILURE, 0, 0); memcpy(scsicmd->sense_buffer, &dev->fsa_dev[cid].sense_data, min_t(size_t, sizeof(dev->fsa_dev[cid].sense_data), SCSI_SENSE_BUFFERSIZE)); scsicmd->scsi_done(scsicmd); - return 1; + return 0; } dprintk((KERN_DEBUG "aac_read[cpu %d]: lba = %llu, t = %ld.\n", @@ -2559,13 +2559,13 @@ static int aac_write(struct scsi_cmnd * scsicmd) scsicmd->result = DID_OK << 16 | COMMAND_COMPLETE << 8 | SAM_STAT_CHECK_CONDITION; set_sense(&dev->fsa_dev[cid].sense_data, - HARDWARE_ERROR, SENCODE_INTERNAL_TARGET_FAILURE, + ILLEGAL_REQUEST, SENCODE_LBA_OUT_OF_RANGE, ASENCODE_INTERNAL_TARGET_FAILURE, 0, 0); memcpy(scsicmd->sense_buffer, &dev->fsa_dev[cid].sense_data, min_t(size_t, sizeof(dev->fsa_dev[cid].sense_data), SCSI_SENSE_BUFFERSIZE)); scsicmd->scsi_done(scsicmd); - return 1; + return 0; } dprintk((KERN_DEBUG "aac_write[cpu %d]: lba = %llu, t = %ld.\n", diff --git a/drivers/scsi/aacraid/commsup.c b/drivers/scsi/aacraid/commsup.c index 2142a649e865..90fb17c5dd69 100644 --- a/drivers/scsi/aacraid/commsup.c +++ b/drivers/scsi/aacraid/commsup.c @@ -728,7 +728,7 @@ int aac_hba_send(u8 command, struct fib *fibptr, fib_callback callback, hbacmd->request_id = cpu_to_le32((((u32)(fibptr - dev->fibs)) << 2) + 1); fibptr->flags |= FIB_CONTEXT_FLAG_SCSI_CMD; - } else if (command != HBA_IU_TYPE_SCSI_TM_REQ) + } else return -EINVAL; diff --git a/drivers/scsi/aacraid/linit.c b/drivers/scsi/aacraid/linit.c index 4a858789e6c5..1035f947f1bc 100644 --- a/drivers/scsi/aacraid/linit.c +++ b/drivers/scsi/aacraid/linit.c @@ -723,7 +723,11 @@ static int aac_eh_abort(struct scsi_cmnd* cmd) status = aac_hba_send(HBA_IU_TYPE_SCSI_TM_REQ, fib, (fib_callback) aac_hba_callback, (void *) cmd); - + if (status != -EINPROGRESS) { + aac_fib_complete(fib); + aac_fib_free(fib); + return ret; + } /* Wait up to 15 secs for completion */ for (count = 0; count < 15; ++count) { if (cmd->SCp.sent_command) { @@ -902,11 +906,11 @@ static int aac_eh_dev_reset(struct scsi_cmnd *cmd) info = &aac->hba_map[bus][cid]; - if (info->devtype != AAC_DEVTYPE_NATIVE_RAW && - info->reset_state > 0) + if (!(info->devtype == AAC_DEVTYPE_NATIVE_RAW && + !(info->reset_state > 0))) return FAILED; - pr_err("%s: Host adapter reset request. SCSI hang ?\n", + pr_err("%s: Host device reset request. SCSI hang ?\n", AAC_DRIVERNAME); fib = aac_fib_alloc(aac); @@ -921,7 +925,12 @@ static int aac_eh_dev_reset(struct scsi_cmnd *cmd) status = aac_hba_send(command, fib, (fib_callback) aac_tmf_callback, (void *) info); - + if (status != -EINPROGRESS) { + info->reset_state = 0; + aac_fib_complete(fib); + aac_fib_free(fib); + return ret; + } /* Wait up to 15 seconds for completion */ for (count = 0; count < 15; ++count) { if (info->reset_state == 0) { @@ -960,11 +969,11 @@ static int aac_eh_target_reset(struct scsi_cmnd *cmd) info = &aac->hba_map[bus][cid]; - if (info->devtype != AAC_DEVTYPE_NATIVE_RAW && - info->reset_state > 0) + if (!(info->devtype == AAC_DEVTYPE_NATIVE_RAW && + !(info->reset_state > 0))) return FAILED; - pr_err("%s: Host adapter reset request. SCSI hang ?\n", + pr_err("%s: Host target reset request. SCSI hang ?\n", AAC_DRIVERNAME); fib = aac_fib_alloc(aac); @@ -981,6 +990,13 @@ static int aac_eh_target_reset(struct scsi_cmnd *cmd) (fib_callback) aac_tmf_callback, (void *) info); + if (status != -EINPROGRESS) { + info->reset_state = 0; + aac_fib_complete(fib); + aac_fib_free(fib); + return ret; + } + /* Wait up to 15 seconds for completion */ for (count = 0; count < 15; ++count) { if (info->reset_state <= 0) { @@ -1033,7 +1049,7 @@ static int aac_eh_bus_reset(struct scsi_cmnd* cmd) } } - pr_err("%s: Host adapter reset request. SCSI hang ?\n", AAC_DRIVERNAME); + pr_err("%s: Host bus reset request. SCSI hang ?\n", AAC_DRIVERNAME); /* * Check the health of the controller @@ -1591,7 +1607,7 @@ static int aac_probe_one(struct pci_dev *pdev, const struct pci_device_id *id) struct Scsi_Host *shost; struct aac_dev *aac; struct list_head *insert = &aac_devices; - int error = -ENODEV; + int error; int unique_id = 0; u64 dmamask; int mask_bits = 0; @@ -1616,7 +1632,6 @@ static int aac_probe_one(struct pci_dev *pdev, const struct pci_device_id *id) error = pci_enable_device(pdev); if (error) goto out; - error = -ENODEV; if (!(aac_drivers[index].quirks & AAC_QUIRK_SRC)) { error = pci_set_dma_mask(pdev, DMA_BIT_MASK(32)); @@ -1648,8 +1663,10 @@ static int aac_probe_one(struct pci_dev *pdev, const struct pci_device_id *id) pci_set_master(pdev); shost = scsi_host_alloc(&aac_driver_template, sizeof(struct aac_dev)); - if (!shost) + if (!shost) { + error = -ENOMEM; goto out_disable_pdev; + } shost->irq = pdev->irq; shost->unique_id = unique_id; @@ -1674,8 +1691,11 @@ static int aac_probe_one(struct pci_dev *pdev, const struct pci_device_id *id) aac->fibs = kcalloc(shost->can_queue + AAC_NUM_MGT_FIB, sizeof(struct fib), GFP_KERNEL); - if (!aac->fibs) + if (!aac->fibs) { + error = -ENOMEM; goto out_free_host; + } + spin_lock_init(&aac->fib_lock); mutex_init(&aac->ioctl_mutex); diff --git a/drivers/scsi/cxlflash/main.c b/drivers/scsi/cxlflash/main.c index 93ef97af22df..67d681c53c29 100644 --- a/drivers/scsi/cxlflash/main.c +++ b/drivers/scsi/cxlflash/main.c @@ -3746,6 +3746,7 @@ static int cxlflash_probe(struct pci_dev *pdev, cfg->afu_cookie = cfg->ops->create_afu(pdev); if (unlikely(!cfg->afu_cookie)) { dev_err(dev, "%s: create_afu failed\n", __func__); + rc = -ENOMEM; goto out_remove; } diff --git a/drivers/scsi/fnic/fnic_scsi.c b/drivers/scsi/fnic/fnic_scsi.c index e3f5c91d5e4f..b60795893994 100644 --- a/drivers/scsi/fnic/fnic_scsi.c +++ b/drivers/scsi/fnic/fnic_scsi.c @@ -1027,7 +1027,8 @@ static void fnic_fcpio_icmnd_cmpl_handler(struct fnic *fnic, atomic64_inc(&fnic_stats->io_stats.io_completions); - io_duration_time = jiffies_to_msecs(jiffies) - jiffies_to_msecs(io_req->start_time); + io_duration_time = jiffies_to_msecs(jiffies) - + jiffies_to_msecs(start_time); if(io_duration_time <= 10) atomic64_inc(&fnic_stats->io_stats.io_btw_0_to_10_msec); diff --git a/drivers/scsi/hpsa.c b/drivers/scsi/hpsa.c index 216e557f703e..e67cb4561aac 100644 --- a/drivers/scsi/hpsa.c +++ b/drivers/scsi/hpsa.c @@ -504,6 +504,12 @@ static ssize_t host_store_rescan(struct device *dev, return count; } +static void hpsa_turn_off_ioaccel_for_device(struct hpsa_scsi_dev_t *device) +{ + device->offload_enabled = 0; + device->offload_to_be_enabled = 0; +} + static ssize_t host_show_firmware_revision(struct device *dev, struct device_attribute *attr, char *buf) { @@ -1738,8 +1744,7 @@ static void hpsa_figure_phys_disk_ptrs(struct ctlr_info *h, __func__, h->scsi_host->host_no, logical_drive->bus, logical_drive->target, logical_drive->lun); - logical_drive->offload_enabled = 0; - logical_drive->offload_to_be_enabled = 0; + hpsa_turn_off_ioaccel_for_device(logical_drive); logical_drive->queue_depth = 8; } } @@ -2499,8 +2504,7 @@ static void process_ioaccel2_completion(struct ctlr_info *h, IOACCEL2_SERV_RESPONSE_FAILURE) { if (c2->error_data.status == IOACCEL2_STATUS_SR_IOACCEL_DISABLED) { - dev->offload_enabled = 0; - dev->offload_to_be_enabled = 0; + hpsa_turn_off_ioaccel_for_device(dev); } if (dev->in_reset) { @@ -3670,10 +3674,17 @@ static void hpsa_get_ioaccel_status(struct ctlr_info *h, this_device->offload_config = !!(ioaccel_status & OFFLOAD_CONFIGURED_BIT); if (this_device->offload_config) { - this_device->offload_to_be_enabled = + bool offload_enabled = !!(ioaccel_status & OFFLOAD_ENABLED_BIT); - if (hpsa_get_raid_map(h, scsi3addr, this_device)) - this_device->offload_to_be_enabled = 0; + /* + * Check to see if offload can be enabled. + */ + if (offload_enabled) { + rc = hpsa_get_raid_map(h, scsi3addr, this_device); + if (rc) /* could not load raid_map */ + goto out; + this_device->offload_to_be_enabled = 1; + } } out: @@ -3996,8 +4007,7 @@ static int hpsa_update_device_info(struct ctlr_info *h, } else { this_device->raid_level = RAID_UNKNOWN; this_device->offload_config = 0; - this_device->offload_enabled = 0; - this_device->offload_to_be_enabled = 0; + hpsa_turn_off_ioaccel_for_device(this_device); this_device->hba_ioaccel_enabled = 0; this_device->volume_offline = 0; this_device->queue_depth = h->nr_cmds; @@ -5230,8 +5240,12 @@ static int hpsa_scsi_ioaccel_raid_map(struct ctlr_info *h, /* Handles load balance across RAID 1 members. * (2-drive R1 and R10 with even # of drives.) * Appropriate for SSDs, not optimal for HDDs + * Ensure we have the correct raid_map. */ - BUG_ON(le16_to_cpu(map->layout_map_count) != 2); + if (le16_to_cpu(map->layout_map_count) != 2) { + hpsa_turn_off_ioaccel_for_device(dev); + return IO_ACCEL_INELIGIBLE; + } if (dev->offload_to_mirror) map_index += le16_to_cpu(map->data_disks_per_row); dev->offload_to_mirror = !dev->offload_to_mirror; @@ -5239,8 +5253,12 @@ static int hpsa_scsi_ioaccel_raid_map(struct ctlr_info *h, case HPSA_RAID_ADM: /* Handles N-way mirrors (R1-ADM) * and R10 with # of drives divisible by 3.) + * Ensure we have the correct raid_map. */ - BUG_ON(le16_to_cpu(map->layout_map_count) != 3); + if (le16_to_cpu(map->layout_map_count) != 3) { + hpsa_turn_off_ioaccel_for_device(dev); + return IO_ACCEL_INELIGIBLE; + } offload_to_mirror = dev->offload_to_mirror; raid_map_helper(map, offload_to_mirror, @@ -5265,7 +5283,10 @@ static int hpsa_scsi_ioaccel_raid_map(struct ctlr_info *h, r5or6_blocks_per_row = le16_to_cpu(map->strip_size) * le16_to_cpu(map->data_disks_per_row); - BUG_ON(r5or6_blocks_per_row == 0); + if (r5or6_blocks_per_row == 0) { + hpsa_turn_off_ioaccel_for_device(dev); + return IO_ACCEL_INELIGIBLE; + } stripesize = r5or6_blocks_per_row * le16_to_cpu(map->layout_map_count); #if BITS_PER_LONG == 32 @@ -8285,7 +8306,7 @@ static int detect_controller_lockup(struct ctlr_info *h) * * Called from monitor controller worker (hpsa_event_monitor_worker) * - * A Volume (or Volumes that comprise an Array set may be undergoing a + * A Volume (or Volumes that comprise an Array set) may be undergoing a * transformation, so we will be turning off ioaccel for all volumes that * make up the Array. */ @@ -8308,6 +8329,9 @@ static void hpsa_set_ioaccel_status(struct ctlr_info *h) * Run through current device list used during I/O requests. */ for (i = 0; i < h->ndevices; i++) { + int offload_to_be_enabled = 0; + int offload_config = 0; + device = h->dev[i]; if (!device) @@ -8325,25 +8349,35 @@ static void hpsa_set_ioaccel_status(struct ctlr_info *h) continue; ioaccel_status = buf[IOACCEL_STATUS_BYTE]; - device->offload_config = + + /* + * Check if offload is still configured on + */ + offload_config = !!(ioaccel_status & OFFLOAD_CONFIGURED_BIT); - if (device->offload_config) - device->offload_to_be_enabled = + /* + * If offload is configured on, check to see if ioaccel + * needs to be enabled. + */ + if (offload_config) + offload_to_be_enabled = !!(ioaccel_status & OFFLOAD_ENABLED_BIT); + /* + * If ioaccel is to be re-enabled, re-enable later during the + * scan operation so the driver can get a fresh raidmap + * before turning ioaccel back on. + */ + if (offload_to_be_enabled) + continue; + /* * Immediately turn off ioaccel for any volume the * controller tells us to. Some of the reasons could be: * transformation - change to the LVs of an Array. * degraded volume - component failure - * - * If ioaccel is to be re-enabled, re-enable later during the - * scan operation so the driver can get a fresh raidmap - * before turning ioaccel back on. - * */ - if (!device->offload_to_be_enabled) - device->offload_enabled = 0; + hpsa_turn_off_ioaccel_for_device(device); } kfree(buf); diff --git a/drivers/scsi/libfc/fc_rport.c b/drivers/scsi/libfc/fc_rport.c index 6bb8917b99a1..64500417c22e 100644 --- a/drivers/scsi/libfc/fc_rport.c +++ b/drivers/scsi/libfc/fc_rport.c @@ -133,8 +133,10 @@ struct fc_rport_priv *fc_rport_create(struct fc_lport *lport, u32 port_id) lockdep_assert_held(&lport->disc.disc_mutex); rdata = fc_rport_lookup(lport, port_id); - if (rdata) + if (rdata) { + kref_put(&rdata->kref, fc_rport_destroy); return rdata; + } if (lport->rport_priv_size > 0) rport_priv_size = lport->rport_priv_size; @@ -481,10 +483,11 @@ static void fc_rport_enter_delete(struct fc_rport_priv *rdata, fc_rport_state_enter(rdata, RPORT_ST_DELETE); - kref_get(&rdata->kref); - if (rdata->event == RPORT_EV_NONE && - !queue_work(rport_event_queue, &rdata->event_work)) - kref_put(&rdata->kref, fc_rport_destroy); + if (rdata->event == RPORT_EV_NONE) { + kref_get(&rdata->kref); + if (!queue_work(rport_event_queue, &rdata->event_work)) + kref_put(&rdata->kref, fc_rport_destroy); + } rdata->event = event; } diff --git a/drivers/scsi/lpfc/lpfc_attr.c b/drivers/scsi/lpfc/lpfc_attr.c index 25aa7a53d255..bb973901b672 100644 --- a/drivers/scsi/lpfc/lpfc_attr.c +++ b/drivers/scsi/lpfc/lpfc_attr.c @@ -176,7 +176,6 @@ lpfc_nvme_info_show(struct device *dev, struct device_attribute *attr, int i; int len = 0; char tmp[LPFC_MAX_NVME_INFO_TMP_LEN] = {0}; - unsigned long iflags = 0; if (!(vport->cfg_enable_fc4_type & LPFC_ENABLE_NVME)) { len = scnprintf(buf, PAGE_SIZE, "NVME Disabled\n"); @@ -347,7 +346,6 @@ lpfc_nvme_info_show(struct device *dev, struct device_attribute *attr, if (strlcat(buf, "\nNVME Initiator Enabled\n", PAGE_SIZE) >= PAGE_SIZE) goto buffer_done; - rcu_read_lock(); scnprintf(tmp, sizeof(tmp), "XRI Dist lpfc%d Total %d IO %d ELS %d\n", phba->brd_no, @@ -355,7 +353,7 @@ lpfc_nvme_info_show(struct device *dev, struct device_attribute *attr, phba->sli4_hba.io_xri_max, lpfc_sli4_get_els_iocb_cnt(phba)); if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE) - goto rcu_unlock_buf_done; + goto buffer_done; /* Port state is only one of two values for now. */ if (localport->port_id) @@ -371,15 +369,17 @@ lpfc_nvme_info_show(struct device *dev, struct device_attribute *attr, wwn_to_u64(vport->fc_nodename.u.wwn), localport->port_id, statep); if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE) - goto rcu_unlock_buf_done; + goto buffer_done; + + spin_lock_irq(shost->host_lock); list_for_each_entry(ndlp, &vport->fc_nodes, nlp_listp) { nrport = NULL; - spin_lock_irqsave(&vport->phba->hbalock, iflags); + spin_lock(&vport->phba->hbalock); rport = lpfc_ndlp_get_nrport(ndlp); if (rport) nrport = rport->remoteport; - spin_unlock_irqrestore(&vport->phba->hbalock, iflags); + spin_unlock(&vport->phba->hbalock); if (!nrport) continue; @@ -398,39 +398,39 @@ lpfc_nvme_info_show(struct device *dev, struct device_attribute *attr, /* Tab in to show lport ownership. */ if (strlcat(buf, "NVME RPORT ", PAGE_SIZE) >= PAGE_SIZE) - goto rcu_unlock_buf_done; + goto unlock_buf_done; if (phba->brd_no >= 10) { if (strlcat(buf, " ", PAGE_SIZE) >= PAGE_SIZE) - goto rcu_unlock_buf_done; + goto unlock_buf_done; } scnprintf(tmp, sizeof(tmp), "WWPN x%llx ", nrport->port_name); if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE) - goto rcu_unlock_buf_done; + goto unlock_buf_done; scnprintf(tmp, sizeof(tmp), "WWNN x%llx ", nrport->node_name); if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE) - goto rcu_unlock_buf_done; + goto unlock_buf_done; scnprintf(tmp, sizeof(tmp), "DID x%06x ", nrport->port_id); if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE) - goto rcu_unlock_buf_done; + goto unlock_buf_done; /* An NVME rport can have multiple roles. */ if (nrport->port_role & FC_PORT_ROLE_NVME_INITIATOR) { if (strlcat(buf, "INITIATOR ", PAGE_SIZE) >= PAGE_SIZE) - goto rcu_unlock_buf_done; + goto unlock_buf_done; } if (nrport->port_role & FC_PORT_ROLE_NVME_TARGET) { if (strlcat(buf, "TARGET ", PAGE_SIZE) >= PAGE_SIZE) - goto rcu_unlock_buf_done; + goto unlock_buf_done; } if (nrport->port_role & FC_PORT_ROLE_NVME_DISCOVERY) { if (strlcat(buf, "DISCSRVC ", PAGE_SIZE) >= PAGE_SIZE) - goto rcu_unlock_buf_done; + goto unlock_buf_done; } if (nrport->port_role & ~(FC_PORT_ROLE_NVME_INITIATOR | FC_PORT_ROLE_NVME_TARGET | @@ -438,14 +438,14 @@ lpfc_nvme_info_show(struct device *dev, struct device_attribute *attr, scnprintf(tmp, sizeof(tmp), "UNKNOWN ROLE x%x", nrport->port_role); if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE) - goto rcu_unlock_buf_done; + goto unlock_buf_done; } scnprintf(tmp, sizeof(tmp), "%s\n", statep); if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE) - goto rcu_unlock_buf_done; + goto unlock_buf_done; } - rcu_read_unlock(); + spin_unlock_irq(shost->host_lock); if (!lport) goto buffer_done; @@ -505,11 +505,11 @@ lpfc_nvme_info_show(struct device *dev, struct device_attribute *attr, atomic_read(&lport->cmpl_fcp_err)); strlcat(buf, tmp, PAGE_SIZE); - /* RCU is already unlocked. */ + /* host_lock is already unlocked. */ goto buffer_done; - rcu_unlock_buf_done: - rcu_read_unlock(); + unlock_buf_done: + spin_unlock_irq(shost->host_lock); buffer_done: len = strnlen(buf, PAGE_SIZE); diff --git a/drivers/scsi/lpfc/lpfc_ct.c b/drivers/scsi/lpfc/lpfc_ct.c index 4a09f21cb235..e672fa9e842c 100644 --- a/drivers/scsi/lpfc/lpfc_ct.c +++ b/drivers/scsi/lpfc/lpfc_ct.c @@ -2056,8 +2056,8 @@ lpfc_fdmi_hba_attr_wwnn(struct lpfc_vport *vport, struct lpfc_fdmi_attr_def *ad) struct lpfc_fdmi_attr_entry *ae; uint32_t size; - ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; - memset(ae, 0, sizeof(struct lpfc_name)); + ae = &ad->AttrValue; + memset(ae, 0, sizeof(*ae)); memcpy(&ae->un.AttrWWN, &vport->fc_sparam.nodeName, sizeof(struct lpfc_name)); @@ -2073,8 +2073,8 @@ lpfc_fdmi_hba_attr_manufacturer(struct lpfc_vport *vport, struct lpfc_fdmi_attr_entry *ae; uint32_t len, size; - ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; - memset(ae, 0, 256); + ae = &ad->AttrValue; + memset(ae, 0, sizeof(*ae)); /* This string MUST be consistent with other FC platforms * supported by Broadcom. @@ -2098,8 +2098,8 @@ lpfc_fdmi_hba_attr_sn(struct lpfc_vport *vport, struct lpfc_fdmi_attr_def *ad) struct lpfc_fdmi_attr_entry *ae; uint32_t len, size; - ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; - memset(ae, 0, 256); + ae = &ad->AttrValue; + memset(ae, 0, sizeof(*ae)); strncpy(ae->un.AttrString, phba->SerialNumber, sizeof(ae->un.AttrString)); @@ -2120,8 +2120,8 @@ lpfc_fdmi_hba_attr_model(struct lpfc_vport *vport, struct lpfc_fdmi_attr_entry *ae; uint32_t len, size; - ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; - memset(ae, 0, 256); + ae = &ad->AttrValue; + memset(ae, 0, sizeof(*ae)); strncpy(ae->un.AttrString, phba->ModelName, sizeof(ae->un.AttrString)); @@ -2141,8 +2141,8 @@ lpfc_fdmi_hba_attr_description(struct lpfc_vport *vport, struct lpfc_fdmi_attr_entry *ae; uint32_t len, size; - ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; - memset(ae, 0, 256); + ae = &ad->AttrValue; + memset(ae, 0, sizeof(*ae)); strncpy(ae->un.AttrString, phba->ModelDesc, sizeof(ae->un.AttrString)); @@ -2164,8 +2164,8 @@ lpfc_fdmi_hba_attr_hdw_ver(struct lpfc_vport *vport, struct lpfc_fdmi_attr_entry *ae; uint32_t i, j, incr, size; - ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; - memset(ae, 0, 256); + ae = &ad->AttrValue; + memset(ae, 0, sizeof(*ae)); /* Convert JEDEC ID to ascii for hardware version */ incr = vp->rev.biuRev; @@ -2194,8 +2194,8 @@ lpfc_fdmi_hba_attr_drvr_ver(struct lpfc_vport *vport, struct lpfc_fdmi_attr_entry *ae; uint32_t len, size; - ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; - memset(ae, 0, 256); + ae = &ad->AttrValue; + memset(ae, 0, sizeof(*ae)); strncpy(ae->un.AttrString, lpfc_release_version, sizeof(ae->un.AttrString)); @@ -2216,8 +2216,8 @@ lpfc_fdmi_hba_attr_rom_ver(struct lpfc_vport *vport, struct lpfc_fdmi_attr_entry *ae; uint32_t len, size; - ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; - memset(ae, 0, 256); + ae = &ad->AttrValue; + memset(ae, 0, sizeof(*ae)); if (phba->sli_rev == LPFC_SLI_REV4) lpfc_decode_firmware_rev(phba, ae->un.AttrString, 1); @@ -2241,8 +2241,8 @@ lpfc_fdmi_hba_attr_fmw_ver(struct lpfc_vport *vport, struct lpfc_fdmi_attr_entry *ae; uint32_t len, size; - ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; - memset(ae, 0, 256); + ae = &ad->AttrValue; + memset(ae, 0, sizeof(*ae)); lpfc_decode_firmware_rev(phba, ae->un.AttrString, 1); len = strnlen(ae->un.AttrString, @@ -2261,8 +2261,8 @@ lpfc_fdmi_hba_attr_os_ver(struct lpfc_vport *vport, struct lpfc_fdmi_attr_entry *ae; uint32_t len, size; - ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; - memset(ae, 0, 256); + ae = &ad->AttrValue; + memset(ae, 0, sizeof(*ae)); snprintf(ae->un.AttrString, sizeof(ae->un.AttrString), "%s %s %s", init_utsname()->sysname, @@ -2284,7 +2284,7 @@ lpfc_fdmi_hba_attr_ct_len(struct lpfc_vport *vport, struct lpfc_fdmi_attr_entry *ae; uint32_t size; - ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; + ae = &ad->AttrValue; ae->un.AttrInt = cpu_to_be32(LPFC_MAX_CT_SIZE); size = FOURBYTES + sizeof(uint32_t); @@ -2300,8 +2300,8 @@ lpfc_fdmi_hba_attr_symbolic_name(struct lpfc_vport *vport, struct lpfc_fdmi_attr_entry *ae; uint32_t len, size; - ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; - memset(ae, 0, 256); + ae = &ad->AttrValue; + memset(ae, 0, sizeof(*ae)); len = lpfc_vport_symbolic_node_name(vport, ae->un.AttrString, 256); @@ -2319,7 +2319,7 @@ lpfc_fdmi_hba_attr_vendor_info(struct lpfc_vport *vport, struct lpfc_fdmi_attr_entry *ae; uint32_t size; - ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; + ae = &ad->AttrValue; /* Nothing is defined for this currently */ ae->un.AttrInt = cpu_to_be32(0); @@ -2336,7 +2336,7 @@ lpfc_fdmi_hba_attr_num_ports(struct lpfc_vport *vport, struct lpfc_fdmi_attr_entry *ae; uint32_t size; - ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; + ae = &ad->AttrValue; /* Each driver instance corresponds to a single port */ ae->un.AttrInt = cpu_to_be32(1); @@ -2353,8 +2353,8 @@ lpfc_fdmi_hba_attr_fabric_wwnn(struct lpfc_vport *vport, struct lpfc_fdmi_attr_entry *ae; uint32_t size; - ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; - memset(ae, 0, sizeof(struct lpfc_name)); + ae = &ad->AttrValue; + memset(ae, 0, sizeof(*ae)); memcpy(&ae->un.AttrWWN, &vport->fabric_nodename, sizeof(struct lpfc_name)); @@ -2372,8 +2372,8 @@ lpfc_fdmi_hba_attr_bios_ver(struct lpfc_vport *vport, struct lpfc_fdmi_attr_entry *ae; uint32_t len, size; - ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; - memset(ae, 0, 256); + ae = &ad->AttrValue; + memset(ae, 0, sizeof(*ae)); strlcat(ae->un.AttrString, phba->BIOSVersion, sizeof(ae->un.AttrString)); @@ -2393,7 +2393,7 @@ lpfc_fdmi_hba_attr_bios_state(struct lpfc_vport *vport, struct lpfc_fdmi_attr_entry *ae; uint32_t size; - ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; + ae = &ad->AttrValue; /* Driver doesn't have access to this information */ ae->un.AttrInt = cpu_to_be32(0); @@ -2410,8 +2410,8 @@ lpfc_fdmi_hba_attr_vendor_id(struct lpfc_vport *vport, struct lpfc_fdmi_attr_entry *ae; uint32_t len, size; - ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; - memset(ae, 0, 256); + ae = &ad->AttrValue; + memset(ae, 0, sizeof(*ae)); strncpy(ae->un.AttrString, "EMULEX", sizeof(ae->un.AttrString)); @@ -2433,8 +2433,8 @@ lpfc_fdmi_port_attr_fc4type(struct lpfc_vport *vport, struct lpfc_fdmi_attr_entry *ae; uint32_t size; - ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; - memset(ae, 0, 32); + ae = &ad->AttrValue; + memset(ae, 0, sizeof(*ae)); ae->un.AttrTypes[3] = 0x02; /* Type 0x1 - ELS */ ae->un.AttrTypes[2] = 0x01; /* Type 0x8 - FCP */ @@ -2459,7 +2459,7 @@ lpfc_fdmi_port_attr_support_speed(struct lpfc_vport *vport, struct lpfc_fdmi_attr_entry *ae; uint32_t size; - ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; + ae = &ad->AttrValue; ae->un.AttrInt = 0; if (!(phba->hba_flag & HBA_FCOE_MODE)) { @@ -2513,7 +2513,7 @@ lpfc_fdmi_port_attr_speed(struct lpfc_vport *vport, struct lpfc_fdmi_attr_entry *ae; uint32_t size; - ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; + ae = &ad->AttrValue; if (!(phba->hba_flag & HBA_FCOE_MODE)) { switch (phba->fc_linkspeed) { @@ -2583,7 +2583,7 @@ lpfc_fdmi_port_attr_max_frame(struct lpfc_vport *vport, struct lpfc_fdmi_attr_entry *ae; uint32_t size; - ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; + ae = &ad->AttrValue; hsp = (struct serv_parm *)&vport->fc_sparam; ae->un.AttrInt = (((uint32_t) hsp->cmn.bbRcvSizeMsb & 0x0F) << 8) | @@ -2603,8 +2603,8 @@ lpfc_fdmi_port_attr_os_devname(struct lpfc_vport *vport, struct lpfc_fdmi_attr_entry *ae; uint32_t len, size; - ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; - memset(ae, 0, 256); + ae = &ad->AttrValue; + memset(ae, 0, sizeof(*ae)); snprintf(ae->un.AttrString, sizeof(ae->un.AttrString), "/sys/class/scsi_host/host%d", shost->host_no); @@ -2624,8 +2624,8 @@ lpfc_fdmi_port_attr_host_name(struct lpfc_vport *vport, struct lpfc_fdmi_attr_entry *ae; uint32_t len, size; - ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; - memset(ae, 0, 256); + ae = &ad->AttrValue; + memset(ae, 0, sizeof(*ae)); scnprintf(ae->un.AttrString, sizeof(ae->un.AttrString), "%s", vport->phba->os_host_name); @@ -2645,8 +2645,8 @@ lpfc_fdmi_port_attr_wwnn(struct lpfc_vport *vport, struct lpfc_fdmi_attr_entry *ae; uint32_t size; - ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; - memset(ae, 0, sizeof(struct lpfc_name)); + ae = &ad->AttrValue; + memset(ae, 0, sizeof(*ae)); memcpy(&ae->un.AttrWWN, &vport->fc_sparam.nodeName, sizeof(struct lpfc_name)); @@ -2663,8 +2663,8 @@ lpfc_fdmi_port_attr_wwpn(struct lpfc_vport *vport, struct lpfc_fdmi_attr_entry *ae; uint32_t size; - ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; - memset(ae, 0, sizeof(struct lpfc_name)); + ae = &ad->AttrValue; + memset(ae, 0, sizeof(*ae)); memcpy(&ae->un.AttrWWN, &vport->fc_sparam.portName, sizeof(struct lpfc_name)); @@ -2681,8 +2681,8 @@ lpfc_fdmi_port_attr_symbolic_name(struct lpfc_vport *vport, struct lpfc_fdmi_attr_entry *ae; uint32_t len, size; - ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; - memset(ae, 0, 256); + ae = &ad->AttrValue; + memset(ae, 0, sizeof(*ae)); len = lpfc_vport_symbolic_port_name(vport, ae->un.AttrString, 256); len += (len & 3) ? (4 - (len & 3)) : 4; @@ -2700,7 +2700,7 @@ lpfc_fdmi_port_attr_port_type(struct lpfc_vport *vport, struct lpfc_fdmi_attr_entry *ae; uint32_t size; - ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; + ae = &ad->AttrValue; if (phba->fc_topology == LPFC_TOPOLOGY_LOOP) ae->un.AttrInt = cpu_to_be32(LPFC_FDMI_PORTTYPE_NLPORT); else @@ -2718,7 +2718,7 @@ lpfc_fdmi_port_attr_class(struct lpfc_vport *vport, struct lpfc_fdmi_attr_entry *ae; uint32_t size; - ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; + ae = &ad->AttrValue; ae->un.AttrInt = cpu_to_be32(FC_COS_CLASS2 | FC_COS_CLASS3); size = FOURBYTES + sizeof(uint32_t); ad->AttrLen = cpu_to_be16(size); @@ -2733,8 +2733,8 @@ lpfc_fdmi_port_attr_fabric_wwpn(struct lpfc_vport *vport, struct lpfc_fdmi_attr_entry *ae; uint32_t size; - ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; - memset(ae, 0, sizeof(struct lpfc_name)); + ae = &ad->AttrValue; + memset(ae, 0, sizeof(*ae)); memcpy(&ae->un.AttrWWN, &vport->fabric_portname, sizeof(struct lpfc_name)); @@ -2751,8 +2751,8 @@ lpfc_fdmi_port_attr_active_fc4type(struct lpfc_vport *vport, struct lpfc_fdmi_attr_entry *ae; uint32_t size; - ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; - memset(ae, 0, 32); + ae = &ad->AttrValue; + memset(ae, 0, sizeof(*ae)); ae->un.AttrTypes[3] = 0x02; /* Type 0x1 - ELS */ ae->un.AttrTypes[2] = 0x01; /* Type 0x8 - FCP */ @@ -2775,7 +2775,7 @@ lpfc_fdmi_port_attr_port_state(struct lpfc_vport *vport, struct lpfc_fdmi_attr_entry *ae; uint32_t size; - ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; + ae = &ad->AttrValue; /* Link Up - operational */ ae->un.AttrInt = cpu_to_be32(LPFC_FDMI_PORTSTATE_ONLINE); size = FOURBYTES + sizeof(uint32_t); @@ -2791,7 +2791,7 @@ lpfc_fdmi_port_attr_num_disc(struct lpfc_vport *vport, struct lpfc_fdmi_attr_entry *ae; uint32_t size; - ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; + ae = &ad->AttrValue; vport->fdmi_num_disc = lpfc_find_map_node(vport); ae->un.AttrInt = cpu_to_be32(vport->fdmi_num_disc); size = FOURBYTES + sizeof(uint32_t); @@ -2807,7 +2807,7 @@ lpfc_fdmi_port_attr_nportid(struct lpfc_vport *vport, struct lpfc_fdmi_attr_entry *ae; uint32_t size; - ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; + ae = &ad->AttrValue; ae->un.AttrInt = cpu_to_be32(vport->fc_myDID); size = FOURBYTES + sizeof(uint32_t); ad->AttrLen = cpu_to_be16(size); @@ -2822,8 +2822,8 @@ lpfc_fdmi_smart_attr_service(struct lpfc_vport *vport, struct lpfc_fdmi_attr_entry *ae; uint32_t len, size; - ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; - memset(ae, 0, 256); + ae = &ad->AttrValue; + memset(ae, 0, sizeof(*ae)); strncpy(ae->un.AttrString, "Smart SAN Initiator", sizeof(ae->un.AttrString)); @@ -2843,8 +2843,8 @@ lpfc_fdmi_smart_attr_guid(struct lpfc_vport *vport, struct lpfc_fdmi_attr_entry *ae; uint32_t size; - ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; - memset(ae, 0, 256); + ae = &ad->AttrValue; + memset(ae, 0, sizeof(*ae)); memcpy(&ae->un.AttrString, &vport->fc_sparam.nodeName, sizeof(struct lpfc_name)); @@ -2864,8 +2864,8 @@ lpfc_fdmi_smart_attr_version(struct lpfc_vport *vport, struct lpfc_fdmi_attr_entry *ae; uint32_t len, size; - ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; - memset(ae, 0, 256); + ae = &ad->AttrValue; + memset(ae, 0, sizeof(*ae)); strncpy(ae->un.AttrString, "Smart SAN Version 2.0", sizeof(ae->un.AttrString)); @@ -2886,8 +2886,8 @@ lpfc_fdmi_smart_attr_model(struct lpfc_vport *vport, struct lpfc_fdmi_attr_entry *ae; uint32_t len, size; - ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; - memset(ae, 0, 256); + ae = &ad->AttrValue; + memset(ae, 0, sizeof(*ae)); strncpy(ae->un.AttrString, phba->ModelName, sizeof(ae->un.AttrString)); @@ -2906,7 +2906,7 @@ lpfc_fdmi_smart_attr_port_info(struct lpfc_vport *vport, struct lpfc_fdmi_attr_entry *ae; uint32_t size; - ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; + ae = &ad->AttrValue; /* SRIOV (type 3) is not supported */ if (vport->vpi) @@ -2926,7 +2926,7 @@ lpfc_fdmi_smart_attr_qos(struct lpfc_vport *vport, struct lpfc_fdmi_attr_entry *ae; uint32_t size; - ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; + ae = &ad->AttrValue; ae->un.AttrInt = cpu_to_be32(0); size = FOURBYTES + sizeof(uint32_t); ad->AttrLen = cpu_to_be16(size); @@ -2941,7 +2941,7 @@ lpfc_fdmi_smart_attr_security(struct lpfc_vport *vport, struct lpfc_fdmi_attr_entry *ae; uint32_t size; - ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; + ae = &ad->AttrValue; ae->un.AttrInt = cpu_to_be32(1); size = FOURBYTES + sizeof(uint32_t); ad->AttrLen = cpu_to_be16(size); @@ -3089,7 +3089,8 @@ lpfc_fdmi_cmd(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp, /* Registered Port List */ /* One entry (port) per adapter */ rh->rpl.EntryCnt = cpu_to_be32(1); - memcpy(&rh->rpl.pe, &phba->pport->fc_sparam.portName, + memcpy(&rh->rpl.pe.PortName, + &phba->pport->fc_sparam.portName, sizeof(struct lpfc_name)); /* point to the HBA attribute block */ diff --git a/drivers/scsi/lpfc/lpfc_hbadisc.c b/drivers/scsi/lpfc/lpfc_hbadisc.c index 799db8a785c2..0dc1d56ff470 100644 --- a/drivers/scsi/lpfc/lpfc_hbadisc.c +++ b/drivers/scsi/lpfc/lpfc_hbadisc.c @@ -73,6 +73,7 @@ static void lpfc_disc_timeout_handler(struct lpfc_vport *); static void lpfc_disc_flush_list(struct lpfc_vport *vport); static void lpfc_unregister_fcfi_cmpl(struct lpfc_hba *, LPFC_MBOXQ_t *); static int lpfc_fcf_inuse(struct lpfc_hba *); +static void lpfc_mbx_cmpl_read_sparam(struct lpfc_hba *, LPFC_MBOXQ_t *); void lpfc_terminate_rport_io(struct fc_rport *rport) @@ -1134,11 +1135,13 @@ lpfc_mbx_cmpl_clear_la(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb) return; } - void lpfc_mbx_cmpl_local_config_link(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb) { struct lpfc_vport *vport = pmb->vport; + LPFC_MBOXQ_t *sparam_mb; + struct lpfc_dmabuf *sparam_mp; + int rc; if (pmb->u.mb.mbxStatus) goto out; @@ -1163,12 +1166,42 @@ lpfc_mbx_cmpl_local_config_link(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb) } /* Start discovery by sending a FLOGI. port_state is identically - * LPFC_FLOGI while waiting for FLOGI cmpl. Check if sending - * the FLOGI is being deferred till after MBX_READ_SPARAM completes. + * LPFC_FLOGI while waiting for FLOGI cmpl. */ if (vport->port_state != LPFC_FLOGI) { - if (!(phba->hba_flag & HBA_DEFER_FLOGI)) + /* Issue MBX_READ_SPARAM to update CSPs before FLOGI if + * bb-credit recovery is in place. + */ + if (phba->bbcredit_support && phba->cfg_enable_bbcr && + !(phba->link_flag & LS_LOOPBACK_MODE)) { + sparam_mb = mempool_alloc(phba->mbox_mem_pool, + GFP_KERNEL); + if (!sparam_mb) + goto sparam_out; + + rc = lpfc_read_sparam(phba, sparam_mb, 0); + if (rc) { + mempool_free(sparam_mb, phba->mbox_mem_pool); + goto sparam_out; + } + sparam_mb->vport = vport; + sparam_mb->mbox_cmpl = lpfc_mbx_cmpl_read_sparam; + rc = lpfc_sli_issue_mbox(phba, sparam_mb, MBX_NOWAIT); + if (rc == MBX_NOT_FINISHED) { + sparam_mp = (struct lpfc_dmabuf *) + sparam_mb->ctx_buf; + lpfc_mbuf_free(phba, sparam_mp->virt, + sparam_mp->phys); + kfree(sparam_mp); + sparam_mb->ctx_buf = NULL; + mempool_free(sparam_mb, phba->mbox_mem_pool); + goto sparam_out; + } + + phba->hba_flag |= HBA_DEFER_FLOGI; + } else { lpfc_initial_flogi(vport); + } } else { if (vport->fc_flag & FC_PT2PT) lpfc_disc_start(vport); @@ -1180,6 +1213,7 @@ lpfc_mbx_cmpl_local_config_link(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb) "0306 CONFIG_LINK mbxStatus error x%x " "HBA state x%x\n", pmb->u.mb.mbxStatus, vport->port_state); +sparam_out: mempool_free(pmb, phba->mbox_mem_pool); lpfc_linkdown(phba); @@ -3237,21 +3271,6 @@ lpfc_mbx_process_link_up(struct lpfc_hba *phba, struct lpfc_mbx_read_top *la) lpfc_linkup(phba); sparam_mbox = NULL; - if (!(phba->hba_flag & HBA_FCOE_MODE)) { - cfglink_mbox = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL); - if (!cfglink_mbox) - goto out; - vport->port_state = LPFC_LOCAL_CFG_LINK; - lpfc_config_link(phba, cfglink_mbox); - cfglink_mbox->vport = vport; - cfglink_mbox->mbox_cmpl = lpfc_mbx_cmpl_local_config_link; - rc = lpfc_sli_issue_mbox(phba, cfglink_mbox, MBX_NOWAIT); - if (rc == MBX_NOT_FINISHED) { - mempool_free(cfglink_mbox, phba->mbox_mem_pool); - goto out; - } - } - sparam_mbox = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL); if (!sparam_mbox) goto out; @@ -3272,7 +3291,20 @@ lpfc_mbx_process_link_up(struct lpfc_hba *phba, struct lpfc_mbx_read_top *la) goto out; } - if (phba->hba_flag & HBA_FCOE_MODE) { + if (!(phba->hba_flag & HBA_FCOE_MODE)) { + cfglink_mbox = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL); + if (!cfglink_mbox) + goto out; + vport->port_state = LPFC_LOCAL_CFG_LINK; + lpfc_config_link(phba, cfglink_mbox); + cfglink_mbox->vport = vport; + cfglink_mbox->mbox_cmpl = lpfc_mbx_cmpl_local_config_link; + rc = lpfc_sli_issue_mbox(phba, cfglink_mbox, MBX_NOWAIT); + if (rc == MBX_NOT_FINISHED) { + mempool_free(cfglink_mbox, phba->mbox_mem_pool); + goto out; + } + } else { vport->port_state = LPFC_VPORT_UNKNOWN; /* * Add the driver's default FCF record at FCF index 0 now. This @@ -3329,10 +3361,6 @@ lpfc_mbx_process_link_up(struct lpfc_hba *phba, struct lpfc_mbx_read_top *la) } /* Reset FCF roundrobin bmask for new discovery */ lpfc_sli4_clear_fcf_rr_bmask(phba); - } else { - if (phba->bbcredit_support && phba->cfg_enable_bbcr && - !(phba->link_flag & LS_LOOPBACK_MODE)) - phba->hba_flag |= HBA_DEFER_FLOGI; } /* Prepare for LINK up registrations */ diff --git a/drivers/scsi/lpfc/lpfc_hw.h b/drivers/scsi/lpfc/lpfc_hw.h index 436cdc8c5ef4..b5642c872593 100644 --- a/drivers/scsi/lpfc/lpfc_hw.h +++ b/drivers/scsi/lpfc/lpfc_hw.h @@ -1340,25 +1340,8 @@ struct fc_rdp_res_frame { /* lpfc_sli_ct_request defines the CT_IU preamble for FDMI commands */ #define SLI_CT_FDMI_Subtypes 0x10 /* Management Service Subtype */ -/* - * Registered Port List Format - */ -struct lpfc_fdmi_reg_port_list { - uint32_t EntryCnt; - uint32_t pe; /* Variable-length array */ -}; - - /* Definitions for HBA / Port attribute entries */ -struct lpfc_fdmi_attr_def { /* Defined in TLV format */ - /* Structure is in Big Endian format */ - uint32_t AttrType:16; - uint32_t AttrLen:16; - uint32_t AttrValue; /* Marks start of Value (ATTRIBUTE_ENTRY) */ -}; - - /* Attribute Entry */ struct lpfc_fdmi_attr_entry { union { @@ -1369,7 +1352,13 @@ struct lpfc_fdmi_attr_entry { } un; }; -#define LPFC_FDMI_MAX_AE_SIZE sizeof(struct lpfc_fdmi_attr_entry) +struct lpfc_fdmi_attr_def { /* Defined in TLV format */ + /* Structure is in Big Endian format */ + uint32_t AttrType:16; + uint32_t AttrLen:16; + /* Marks start of Value (ATTRIBUTE_ENTRY) */ + struct lpfc_fdmi_attr_entry AttrValue; +} __packed; /* * HBA Attribute Block @@ -1393,13 +1382,20 @@ struct lpfc_fdmi_hba_ident { struct lpfc_name PortName; }; +/* + * Registered Port List Format + */ +struct lpfc_fdmi_reg_port_list { + uint32_t EntryCnt; + struct lpfc_fdmi_port_entry pe; +} __packed; + /* * Register HBA(RHBA) */ struct lpfc_fdmi_reg_hba { struct lpfc_fdmi_hba_ident hi; - struct lpfc_fdmi_reg_port_list rpl; /* variable-length array */ -/* struct lpfc_fdmi_attr_block ab; */ + struct lpfc_fdmi_reg_port_list rpl; }; /* diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c index 95abffd9ad10..d4c83eca0ad2 100644 --- a/drivers/scsi/lpfc/lpfc_init.c +++ b/drivers/scsi/lpfc/lpfc_init.c @@ -9124,6 +9124,7 @@ lpfc_sli4_release_hdwq(struct lpfc_hba *phba) /* Free the CQ/WQ corresponding to the Hardware Queue */ lpfc_sli4_queue_free(hdwq[idx].io_cq); lpfc_sli4_queue_free(hdwq[idx].io_wq); + hdwq[idx].hba_eq = NULL; hdwq[idx].io_cq = NULL; hdwq[idx].io_wq = NULL; if (phba->cfg_xpsgl && !phba->nvmet_support) diff --git a/drivers/scsi/lpfc/lpfc_nportdisc.c b/drivers/scsi/lpfc/lpfc_nportdisc.c index 696171382558..590a49e84762 100644 --- a/drivers/scsi/lpfc/lpfc_nportdisc.c +++ b/drivers/scsi/lpfc/lpfc_nportdisc.c @@ -279,6 +279,109 @@ lpfc_els_abort(struct lpfc_hba *phba, struct lpfc_nodelist *ndlp) lpfc_cancel_retry_delay_tmo(phba->pport, ndlp); } +/* lpfc_defer_pt2pt_acc - Complete SLI3 pt2pt processing on link up + * @phba: pointer to lpfc hba data structure. + * @link_mbox: pointer to CONFIG_LINK mailbox object + * + * This routine is only called if we are SLI3, direct connect pt2pt + * mode and the remote NPort issues the PLOGI after link up. + */ +void +lpfc_defer_pt2pt_acc(struct lpfc_hba *phba, LPFC_MBOXQ_t *link_mbox) +{ + LPFC_MBOXQ_t *login_mbox; + MAILBOX_t *mb = &link_mbox->u.mb; + struct lpfc_iocbq *save_iocb; + struct lpfc_nodelist *ndlp; + int rc; + + ndlp = link_mbox->ctx_ndlp; + login_mbox = link_mbox->context3; + save_iocb = login_mbox->context3; + link_mbox->context3 = NULL; + login_mbox->context3 = NULL; + + /* Check for CONFIG_LINK error */ + if (mb->mbxStatus) { + lpfc_printf_log(phba, KERN_ERR, LOG_DISCOVERY, + "4575 CONFIG_LINK fails pt2pt discovery: %x\n", + mb->mbxStatus); + mempool_free(login_mbox, phba->mbox_mem_pool); + mempool_free(link_mbox, phba->mbox_mem_pool); + kfree(save_iocb); + return; + } + + /* Now that CONFIG_LINK completed, and our SID is configured, + * we can now proceed with sending the PLOGI ACC. + */ + rc = lpfc_els_rsp_acc(link_mbox->vport, ELS_CMD_PLOGI, + save_iocb, ndlp, login_mbox); + if (rc) { + lpfc_printf_log(phba, KERN_ERR, LOG_DISCOVERY, + "4576 PLOGI ACC fails pt2pt discovery: %x\n", + rc); + mempool_free(login_mbox, phba->mbox_mem_pool); + } + + mempool_free(link_mbox, phba->mbox_mem_pool); + kfree(save_iocb); +} + +/** + * lpfc_defer_tgt_acc - Progress SLI4 target rcv PLOGI handler + * @phba: Pointer to HBA context object. + * @pmb: Pointer to mailbox object. + * + * This function provides the unreg rpi mailbox completion handler for a tgt. + * The routine frees the memory resources associated with the completed + * mailbox command and transmits the ELS ACC. + * + * This routine is only called if we are SLI4, acting in target + * mode and the remote NPort issues the PLOGI after link up. + **/ +void +lpfc_defer_acc_rsp(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb) +{ + struct lpfc_vport *vport = pmb->vport; + struct lpfc_nodelist *ndlp = pmb->ctx_ndlp; + LPFC_MBOXQ_t *mbox = pmb->context3; + struct lpfc_iocbq *piocb = NULL; + int rc; + + if (mbox) { + pmb->context3 = NULL; + piocb = mbox->context3; + mbox->context3 = NULL; + } + + /* + * Complete the unreg rpi mbx request, and update flags. + * This will also restart any deferred events. + */ + lpfc_nlp_get(ndlp); + lpfc_sli4_unreg_rpi_cmpl_clr(phba, pmb); + + if (!piocb) { + lpfc_printf_vlog(vport, KERN_ERR, LOG_DISCOVERY | LOG_ELS, + "4578 PLOGI ACC fail\n"); + if (mbox) + mempool_free(mbox, phba->mbox_mem_pool); + goto out; + } + + rc = lpfc_els_rsp_acc(vport, ELS_CMD_PLOGI, piocb, ndlp, mbox); + if (rc) { + lpfc_printf_vlog(vport, KERN_ERR, LOG_DISCOVERY | LOG_ELS, + "4579 PLOGI ACC fail %x\n", rc); + if (mbox) + mempool_free(mbox, phba->mbox_mem_pool); + } + kfree(piocb); +out: + lpfc_nlp_put(ndlp); +} + static int lpfc_rcv_plogi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp, struct lpfc_iocbq *cmdiocb) @@ -291,10 +394,13 @@ lpfc_rcv_plogi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp, IOCB_t *icmd; struct serv_parm *sp; uint32_t ed_tov; - LPFC_MBOXQ_t *mbox; + LPFC_MBOXQ_t *link_mbox; + LPFC_MBOXQ_t *login_mbox; + struct lpfc_iocbq *save_iocb; struct ls_rjt stat; uint32_t vid, flag; - int rc; + u16 rpi; + int rc, defer_acc; memset(&stat, 0, sizeof (struct ls_rjt)); pcmd = (struct lpfc_dmabuf *) cmdiocb->context2; @@ -343,6 +449,7 @@ lpfc_rcv_plogi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp, else ndlp->nlp_fcp_info |= CLASS3; + defer_acc = 0; ndlp->nlp_class_sup = 0; if (sp->cls1.classValid) ndlp->nlp_class_sup |= FC_COS_CLASS1; @@ -354,7 +461,6 @@ lpfc_rcv_plogi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp, ndlp->nlp_class_sup |= FC_COS_CLASS4; ndlp->nlp_maxframe = ((sp->cmn.bbRcvSizeMsb & 0x0F) << 8) | sp->cmn.bbRcvSizeLsb; - /* if already logged in, do implicit logout */ switch (ndlp->nlp_state) { case NLP_STE_NPR_NODE: @@ -396,6 +502,10 @@ lpfc_rcv_plogi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp, ndlp->nlp_fcp_info &= ~NLP_FCP_2_DEVICE; ndlp->nlp_flag &= ~NLP_FIRSTBURST; + login_mbox = NULL; + link_mbox = NULL; + save_iocb = NULL; + /* Check for Nport to NPort pt2pt protocol */ if ((vport->fc_flag & FC_PT2PT) && !(vport->fc_flag & FC_PT2PT_PLOGI)) { @@ -423,17 +533,22 @@ lpfc_rcv_plogi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp, if (phba->sli_rev == LPFC_SLI_REV4) lpfc_issue_reg_vfi(vport); else { - mbox = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL); - if (mbox == NULL) + defer_acc = 1; + link_mbox = mempool_alloc(phba->mbox_mem_pool, + GFP_KERNEL); + if (!link_mbox) goto out; - lpfc_config_link(phba, mbox); - mbox->mbox_cmpl = lpfc_sli_def_mbox_cmpl; - mbox->vport = vport; - rc = lpfc_sli_issue_mbox(phba, mbox, MBX_NOWAIT); - if (rc == MBX_NOT_FINISHED) { - mempool_free(mbox, phba->mbox_mem_pool); + lpfc_config_link(phba, link_mbox); + link_mbox->mbox_cmpl = lpfc_defer_pt2pt_acc; + link_mbox->vport = vport; + link_mbox->ctx_ndlp = ndlp; + + save_iocb = kzalloc(sizeof(*save_iocb), GFP_KERNEL); + if (!save_iocb) goto out; - } + /* Save info from cmd IOCB used in rsp */ + memcpy((uint8_t *)save_iocb, (uint8_t *)cmdiocb, + sizeof(struct lpfc_iocbq)); } lpfc_can_disctmo(vport); @@ -448,30 +563,57 @@ lpfc_rcv_plogi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp, ndlp->nlp_flag |= NLP_SUPPRESS_RSP; } - mbox = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL); - if (!mbox) + login_mbox = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL); + if (!login_mbox) goto out; /* Registering an existing RPI behaves differently for SLI3 vs SLI4 */ - if (phba->sli_rev == LPFC_SLI_REV4) + if (phba->nvmet_support && !defer_acc) { + link_mbox = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL); + if (!link_mbox) + goto out; + + /* As unique identifiers such as iotag would be overwritten + * with those from the cmdiocb, allocate separate temporary + * storage for the copy. + */ + save_iocb = kzalloc(sizeof(*save_iocb), GFP_KERNEL); + if (!save_iocb) + goto out; + + /* Unreg RPI is required for SLI4. */ + rpi = phba->sli4_hba.rpi_ids[ndlp->nlp_rpi]; + lpfc_unreg_login(phba, vport->vpi, rpi, link_mbox); + link_mbox->vport = vport; + link_mbox->ctx_ndlp = ndlp; + link_mbox->mbox_cmpl = lpfc_defer_acc_rsp; + + if (((ndlp->nlp_DID & Fabric_DID_MASK) != Fabric_DID_MASK) && + (!(vport->fc_flag & FC_OFFLINE_MODE))) + ndlp->nlp_flag |= NLP_UNREG_INP; + + /* Save info from cmd IOCB used in rsp */ + memcpy(save_iocb, cmdiocb, sizeof(*save_iocb)); + + /* Delay sending ACC till unreg RPI completes. */ + defer_acc = 1; + } else if (phba->sli_rev == LPFC_SLI_REV4) lpfc_unreg_rpi(vport, ndlp); rc = lpfc_reg_rpi(phba, vport->vpi, icmd->un.rcvels.remoteID, - (uint8_t *) sp, mbox, ndlp->nlp_rpi); - if (rc) { - mempool_free(mbox, phba->mbox_mem_pool); + (uint8_t *)sp, login_mbox, ndlp->nlp_rpi); + if (rc) goto out; - } /* ACC PLOGI rsp command needs to execute first, - * queue this mbox command to be processed later. + * queue this login_mbox command to be processed later. */ - mbox->mbox_cmpl = lpfc_mbx_cmpl_reg_login; + login_mbox->mbox_cmpl = lpfc_mbx_cmpl_reg_login; /* - * mbox->ctx_ndlp = lpfc_nlp_get(ndlp) deferred until mailbox + * login_mbox->ctx_ndlp = lpfc_nlp_get(ndlp) deferred until mailbox * command issued in lpfc_cmpl_els_acc(). */ - mbox->vport = vport; + login_mbox->vport = vport; spin_lock_irq(shost->host_lock); ndlp->nlp_flag |= (NLP_ACC_REGLOGIN | NLP_RCV_PLOGI); spin_unlock_irq(shost->host_lock); @@ -495,6 +637,9 @@ lpfc_rcv_plogi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp, if ((vport->port_type == LPFC_NPIV_PORT && vport->cfg_restrict_login)) { + /* no deferred ACC */ + kfree(save_iocb); + /* In order to preserve RPIs, we want to cleanup * the default RPI the firmware created to rcv * this ELS request. The only way to do this is @@ -506,16 +651,50 @@ lpfc_rcv_plogi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp, stat.un.b.lsRjtRsnCode = LSRJT_INVALID_CMD; stat.un.b.lsRjtRsnCodeExp = LSEXP_NOTHING_MORE; rc = lpfc_els_rsp_reject(vport, stat.un.lsRjtError, cmdiocb, - ndlp, mbox); + ndlp, login_mbox); if (rc) - mempool_free(mbox, phba->mbox_mem_pool); + mempool_free(login_mbox, phba->mbox_mem_pool); return 1; } - rc = lpfc_els_rsp_acc(vport, ELS_CMD_PLOGI, cmdiocb, ndlp, mbox); + if (defer_acc) { + /* So the order here should be: + * SLI3 pt2pt + * Issue CONFIG_LINK mbox + * CONFIG_LINK cmpl + * SLI4 tgt + * Issue UNREG RPI mbx + * UNREG RPI cmpl + * Issue PLOGI ACC + * PLOGI ACC cmpl + * Issue REG_LOGIN mbox + */ + + /* Save the REG_LOGIN mbox for and rcv IOCB copy later */ + link_mbox->context3 = login_mbox; + login_mbox->context3 = save_iocb; + + /* Start the ball rolling by issuing CONFIG_LINK here */ + rc = lpfc_sli_issue_mbox(phba, link_mbox, MBX_NOWAIT); + if (rc == MBX_NOT_FINISHED) + goto out; + return 1; + } + + rc = lpfc_els_rsp_acc(vport, ELS_CMD_PLOGI, cmdiocb, ndlp, login_mbox); if (rc) - mempool_free(mbox, phba->mbox_mem_pool); + mempool_free(login_mbox, phba->mbox_mem_pool); return 1; out: + if (defer_acc) + lpfc_printf_log(phba, KERN_ERR, LOG_DISCOVERY, + "4577 discovery failure: %p %p %p\n", + save_iocb, link_mbox, login_mbox); + kfree(save_iocb); + if (link_mbox) + mempool_free(link_mbox, phba->mbox_mem_pool); + if (login_mbox) + mempool_free(login_mbox, phba->mbox_mem_pool); + stat.un.b.lsRjtRsnCode = LSRJT_UNABLE_TPC; stat.un.b.lsRjtRsnCodeExp = LSEXP_OUT_OF_RESOURCE; lpfc_els_rsp_reject(vport, stat.un.lsRjtError, cmdiocb, ndlp, NULL); diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c index a951e1c8165e..e2877d2b3cc0 100644 --- a/drivers/scsi/lpfc/lpfc_sli.c +++ b/drivers/scsi/lpfc/lpfc_sli.c @@ -17866,6 +17866,10 @@ lpfc_prep_seq(struct lpfc_vport *vport, struct hbq_dmabuf *seq_dmabuf) list_add_tail(&iocbq->list, &first_iocbq->list); } } + /* Free the sequence's header buffer */ + if (!first_iocbq) + lpfc_in_buf_free(vport->phba, &seq_dmabuf->dbuf); + return first_iocbq; } diff --git a/drivers/scsi/mpt3sas/mpt3sas_ctl.c b/drivers/scsi/mpt3sas/mpt3sas_ctl.c index d5a62fea8fe3..bae7cf70ee17 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_ctl.c +++ b/drivers/scsi/mpt3sas/mpt3sas_ctl.c @@ -3717,12 +3717,6 @@ mpt3sas_ctl_exit(ushort hbas_to_enumerate) for (i = 0; i < MPI2_DIAG_BUF_TYPE_COUNT; i++) { if (!ioc->diag_buffer[i]) continue; - if (!(ioc->diag_buffer_status[i] & - MPT3_DIAG_BUFFER_IS_REGISTERED)) - continue; - if ((ioc->diag_buffer_status[i] & - MPT3_DIAG_BUFFER_IS_RELEASED)) - continue; dma_free_coherent(&ioc->pdev->dev, ioc->diag_buffer_sz[i], ioc->diag_buffer[i], diff --git a/drivers/scsi/pm8001/pm8001_sas.c b/drivers/scsi/pm8001/pm8001_sas.c index 027bf5b2981b..36f5bab09f73 100644 --- a/drivers/scsi/pm8001/pm8001_sas.c +++ b/drivers/scsi/pm8001/pm8001_sas.c @@ -1202,8 +1202,8 @@ int pm8001_abort_task(struct sas_task *task) pm8001_dev = dev->lldd_dev; pm8001_ha = pm8001_find_ha_by_dev(dev); phy_id = pm8001_dev->attached_phy; - rc = pm8001_find_tag(task, &tag); - if (rc == 0) { + ret = pm8001_find_tag(task, &tag); + if (ret == 0) { pm8001_printk("no tag for task:%p\n", task); return TMF_RESP_FUNC_FAILED; } @@ -1241,26 +1241,50 @@ int pm8001_abort_task(struct sas_task *task) /* 2. Send Phy Control Hard Reset */ reinit_completion(&completion); + phy->port_reset_status = PORT_RESET_TMO; phy->reset_success = false; phy->enable_completion = &completion; phy->reset_completion = &completion_reset; ret = PM8001_CHIP_DISP->phy_ctl_req(pm8001_ha, phy_id, PHY_HARD_RESET); - if (ret) - goto out; - PM8001_MSG_DBG(pm8001_ha, - pm8001_printk("Waiting for local phy ctl\n")); - wait_for_completion(&completion); - if (!phy->reset_success) + if (ret) { + phy->enable_completion = NULL; + phy->reset_completion = NULL; goto out; + } - /* 3. Wait for Port Reset complete / Port reset TMO */ + /* In the case of the reset timeout/fail we still + * abort the command at the firmware. The assumption + * here is that the drive is off doing something so + * that it's not processing requests, and we want to + * avoid getting a completion for this and either + * leaking the task in libsas or losing the race and + * getting a double free. + */ PM8001_MSG_DBG(pm8001_ha, + pm8001_printk("Waiting for local phy ctl\n")); + ret = wait_for_completion_timeout(&completion, + PM8001_TASK_TIMEOUT * HZ); + if (!ret || !phy->reset_success) { + phy->enable_completion = NULL; + phy->reset_completion = NULL; + } else { + /* 3. Wait for Port Reset complete or + * Port reset TMO + */ + PM8001_MSG_DBG(pm8001_ha, pm8001_printk("Waiting for Port reset\n")); - wait_for_completion(&completion_reset); - if (phy->port_reset_status) { - pm8001_dev_gone_notify(dev); - goto out; + ret = wait_for_completion_timeout( + &completion_reset, + PM8001_TASK_TIMEOUT * HZ); + if (!ret) + phy->reset_completion = NULL; + WARN_ON(phy->port_reset_status == + PORT_RESET_TMO); + if (phy->port_reset_status == PORT_RESET_TMO) { + pm8001_dev_gone_notify(dev); + goto out; + } } /* diff --git a/drivers/scsi/qedi/qedi_iscsi.c b/drivers/scsi/qedi/qedi_iscsi.c index 0f57c8073406..0f2622a48311 100644 --- a/drivers/scsi/qedi/qedi_iscsi.c +++ b/drivers/scsi/qedi/qedi_iscsi.c @@ -1062,6 +1062,9 @@ static void qedi_ep_disconnect(struct iscsi_endpoint *ep) break; } + if (!abrt_conn) + wait_delay += qedi->pf_params.iscsi_pf_params.two_msl_timer; + qedi_ep->state = EP_STATE_DISCONN_START; ret = qedi_ops->destroy_conn(qedi->cdev, qedi_ep->handle, abrt_conn); if (ret) { diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c index ac4c47fc5f4c..62d2ee825c97 100644 --- a/drivers/scsi/qla2xxx/qla_init.c +++ b/drivers/scsi/qla2xxx/qla_init.c @@ -1002,7 +1002,7 @@ static void qla24xx_async_gnl_sp_done(srb_t *sp, int res) set_bit(loop_id, vha->hw->loop_id_map); wwn = wwn_to_u64(e->port_name); - ql_dbg(ql_dbg_disc + ql_dbg_verbose, vha, 0x20e8, + ql_dbg(ql_dbg_disc, vha, 0x20e8, "%s %8phC %02x:%02x:%02x CLS %x/%x lid %x \n", __func__, (void *)&wwn, e->port_id[2], e->port_id[1], e->port_id[0], e->current_login_state, e->last_login_state, @@ -1061,6 +1061,16 @@ static void qla24xx_async_gnl_sp_done(srb_t *sp, int res) spin_lock_irqsave(&vha->hw->tgt.sess_lock, flags); vha->gnl.sent = 0; + if (!list_empty(&vha->gnl.fcports)) { + /* retrigger gnl */ + list_for_each_entry_safe(fcport, tf, &vha->gnl.fcports, + gnl_entry) { + list_del_init(&fcport->gnl_entry); + fcport->flags &= ~(FCF_ASYNC_SENT | FCF_ASYNC_ACTIVE); + if (qla24xx_post_gnl_work(vha, fcport) == QLA_SUCCESS) + break; + } + } spin_unlock_irqrestore(&vha->hw->tgt.sess_lock, flags); sp->free(sp); @@ -1901,33 +1911,13 @@ qla24xx_handle_prli_done_event(struct scsi_qla_host *vha, struct event_arg *ea) "%s %d %8phC post fc4 prli\n", __func__, __LINE__, ea->fcport->port_name); ea->fcport->fc4f_nvme = 0; - qla24xx_post_prli_work(vha, ea->fcport); return; } - /* at this point both PRLI NVME & PRLI FCP failed */ - if (N2N_TOPO(vha->hw)) { - if (ea->fcport->n2n_link_reset_cnt < 3) { - ea->fcport->n2n_link_reset_cnt++; - /* - * remote port is not sending Plogi. Reset - * link to kick start his state machine - */ - set_bit(N2N_LINK_RESET, &vha->dpc_flags); - } else { - ql_log(ql_log_warn, vha, 0x2119, - "%s %d %8phC Unable to reconnect\n", - __func__, __LINE__, ea->fcport->port_name); - } - } else { - /* - * switch connect. login failed. Take connection - * down and allow relogin to retrigger - */ - ea->fcport->flags &= ~FCF_ASYNC_SENT; - ea->fcport->keep_nport_handle = 0; - qlt_schedule_sess_for_deletion(ea->fcport); - } + ea->fcport->flags &= ~FCF_ASYNC_SENT; + ea->fcport->keep_nport_handle = 0; + ea->fcport->logout_on_delete = 1; + qlt_schedule_sess_for_deletion(ea->fcport); break; } } @@ -1995,7 +1985,7 @@ qla24xx_handle_plogi_done_event(struct scsi_qla_host *vha, struct event_arg *ea) qla24xx_post_prli_work(vha, ea->fcport); } else { ql_dbg(ql_dbg_disc, vha, 0x20ea, - "%s %d %8phC LoopID 0x%x in use with %06x. post gnl\n", + "%s %d %8phC LoopID 0x%x in use with %06x. post gpdb\n", __func__, __LINE__, ea->fcport->port_name, ea->fcport->loop_id, ea->fcport->d_id.b24); @@ -2066,6 +2056,7 @@ qla24xx_handle_plogi_done_event(struct scsi_qla_host *vha, struct event_arg *ea) set_bit(lid, vha->hw->loop_id_map); ea->fcport->loop_id = lid; ea->fcport->keep_nport_handle = 0; + ea->fcport->logout_on_delete = 1; qlt_schedule_sess_for_deletion(ea->fcport); } break; diff --git a/drivers/scsi/qla2xxx/qla_iocb.c b/drivers/scsi/qla2xxx/qla_iocb.c index bdf1994251b9..aed4ce66e6cf 100644 --- a/drivers/scsi/qla2xxx/qla_iocb.c +++ b/drivers/scsi/qla2xxx/qla_iocb.c @@ -2749,6 +2749,10 @@ static void qla2x00_els_dcmd2_sp_done(srb_t *sp, int res) struct scsi_qla_host *vha = sp->vha; struct event_arg ea; struct qla_work_evt *e; + struct fc_port *conflict_fcport; + port_id_t cid; /* conflict Nport id */ + u32 *fw_status = sp->u.iocb_cmd.u.els_plogi.fw_status; + u16 lid; ql_dbg(ql_dbg_disc, vha, 0x3072, "%s ELS done rc %d hdl=%x, portid=%06x %8phC\n", @@ -2760,14 +2764,102 @@ static void qla2x00_els_dcmd2_sp_done(srb_t *sp, int res) if (sp->flags & SRB_WAKEUP_ON_COMP) complete(&lio->u.els_plogi.comp); else { - if (res) { - set_bit(RELOGIN_NEEDED, &vha->dpc_flags); - } else { + switch (fw_status[0]) { + case CS_DATA_UNDERRUN: + case CS_COMPLETE: memset(&ea, 0, sizeof(ea)); ea.fcport = fcport; ea.data[0] = MBS_COMMAND_COMPLETE; ea.sp = sp; qla24xx_handle_plogi_done_event(vha, &ea); + break; + + case CS_IOCB_ERROR: + switch (fw_status[1]) { + case LSC_SCODE_PORTID_USED: + lid = fw_status[2] & 0xffff; + qlt_find_sess_invalidate_other(vha, + wwn_to_u64(fcport->port_name), + fcport->d_id, lid, &conflict_fcport); + if (conflict_fcport) { + /* + * Another fcport shares the same + * loop_id & nport id; conflict + * fcport needs to finish cleanup + * before this fcport can proceed + * to login. + */ + conflict_fcport->conflict = fcport; + fcport->login_pause = 1; + ql_dbg(ql_dbg_disc, vha, 0x20ed, + "%s %d %8phC pid %06x inuse with lid %#x post gidpn\n", + __func__, __LINE__, + fcport->port_name, + fcport->d_id.b24, lid); + } else { + ql_dbg(ql_dbg_disc, vha, 0x20ed, + "%s %d %8phC pid %06x inuse with lid %#x sched del\n", + __func__, __LINE__, + fcport->port_name, + fcport->d_id.b24, lid); + qla2x00_clear_loop_id(fcport); + set_bit(lid, vha->hw->loop_id_map); + fcport->loop_id = lid; + fcport->keep_nport_handle = 0; + qlt_schedule_sess_for_deletion(fcport); + } + break; + + case LSC_SCODE_NPORT_USED: + cid.b.domain = (fw_status[2] >> 16) & 0xff; + cid.b.area = (fw_status[2] >> 8) & 0xff; + cid.b.al_pa = fw_status[2] & 0xff; + cid.b.rsvd_1 = 0; + + ql_dbg(ql_dbg_disc, vha, 0x20ec, + "%s %d %8phC lid %#x in use with pid %06x post gnl\n", + __func__, __LINE__, fcport->port_name, + fcport->loop_id, cid.b24); + set_bit(fcport->loop_id, + vha->hw->loop_id_map); + fcport->loop_id = FC_NO_LOOP_ID; + qla24xx_post_gnl_work(vha, fcport); + break; + + case LSC_SCODE_NOXCB: + vha->hw->exch_starvation++; + if (vha->hw->exch_starvation > 5) { + ql_log(ql_log_warn, vha, 0xd046, + "Exchange starvation. Resetting RISC\n"); + vha->hw->exch_starvation = 0; + set_bit(ISP_ABORT_NEEDED, + &vha->dpc_flags); + qla2xxx_wake_dpc(vha); + } + /* fall through */ + default: + ql_dbg(ql_dbg_disc, vha, 0x20eb, + "%s %8phC cmd error fw_status 0x%x 0x%x 0x%x\n", + __func__, sp->fcport->port_name, + fw_status[0], fw_status[1], fw_status[2]); + + fcport->flags &= ~FCF_ASYNC_SENT; + fcport->disc_state = DSC_LOGIN_FAILED; + set_bit(RELOGIN_NEEDED, &vha->dpc_flags); + break; + } + break; + + default: + ql_dbg(ql_dbg_disc, vha, 0x20eb, + "%s %8phC cmd error 2 fw_status 0x%x 0x%x 0x%x\n", + __func__, sp->fcport->port_name, + fw_status[0], fw_status[1], fw_status[2]); + + sp->fcport->flags &= ~FCF_ASYNC_SENT; + sp->fcport->disc_state = DSC_LOGIN_FAILED; + set_bit(RELOGIN_NEEDED, &vha->dpc_flags); + break; } e = qla2x00_alloc_work(vha, QLA_EVT_UNMAP); @@ -2801,11 +2893,12 @@ qla24xx_els_dcmd2_iocb(scsi_qla_host_t *vha, int els_opcode, return -ENOMEM; } + fcport->flags |= FCF_ASYNC_SENT; + fcport->disc_state = DSC_LOGIN_PEND; elsio = &sp->u.iocb_cmd; ql_dbg(ql_dbg_io, vha, 0x3073, "Enter: PLOGI portid=%06x\n", fcport->d_id.b24); - fcport->flags |= FCF_ASYNC_SENT; sp->type = SRB_ELS_DCMD; sp->name = "ELS_DCMD"; sp->fcport = fcport; diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c index b75e6e4d58c0..a7acc266cec0 100644 --- a/drivers/scsi/qla2xxx/qla_target.c +++ b/drivers/scsi/qla2xxx/qla_target.c @@ -957,7 +957,7 @@ void qlt_free_session_done(struct work_struct *work) struct qlt_plogi_ack_t *own = sess->plogi_link[QLT_PLOGI_LINK_SAME_WWN]; - ql_dbg(ql_dbg_tgt_mgt, vha, 0xf084, + ql_dbg(ql_dbg_disc, vha, 0xf084, "%s: se_sess %p / sess %p from port %8phC loop_id %#04x" " s_id %02x:%02x:%02x logout %d keep %d els_logo %d\n", __func__, sess->se_sess, sess, sess->port_name, sess->loop_id, @@ -1024,7 +1024,7 @@ void qlt_free_session_done(struct work_struct *work) while (!READ_ONCE(sess->logout_completed)) { if (!traced) { - ql_dbg(ql_dbg_tgt_mgt, vha, 0xf086, + ql_dbg(ql_dbg_disc, vha, 0xf086, "%s: waiting for sess %p logout\n", __func__, sess); traced = true; @@ -1045,6 +1045,10 @@ void qlt_free_session_done(struct work_struct *work) (struct imm_ntfy_from_isp *)sess->iocb, SRB_NACK_LOGO); } + spin_lock_irqsave(&vha->work_lock, flags); + sess->flags &= ~FCF_ASYNC_SENT; + spin_unlock_irqrestore(&vha->work_lock, flags); + spin_lock_irqsave(&ha->tgt.sess_lock, flags); if (sess->se_sess) { sess->se_sess = NULL; @@ -1108,7 +1112,7 @@ void qlt_free_session_done(struct work_struct *work) spin_unlock_irqrestore(&ha->tgt.sess_lock, flags); sess->free_pending = 0; - ql_dbg(ql_dbg_tgt_mgt, vha, 0xf001, + ql_dbg(ql_dbg_disc, vha, 0xf001, "Unregistration of sess %p %8phC finished fcp_cnt %d\n", sess, sess->port_name, vha->fcport_count); @@ -1151,6 +1155,11 @@ void qlt_unreg_sess(struct fc_port *sess) return; } sess->free_pending = 1; + /* + * Use FCF_ASYNC_SENT flag to block other cmds used in sess + * management from being sent. + */ + sess->flags |= FCF_ASYNC_SENT; spin_unlock_irqrestore(&sess->vha->work_lock, flags); if (sess->se_sess) @@ -4580,7 +4589,7 @@ qlt_find_sess_invalidate_other(scsi_qla_host_t *vha, uint64_t wwn, /* find other sess with nport_id collision */ if (port_id.b24 == other_sess->d_id.b24) { if (loop_id != other_sess->loop_id) { - ql_dbg(ql_dbg_tgt_tmr, vha, 0x1000c, + ql_dbg(ql_dbg_disc, vha, 0x1000c, "Invalidating sess %p loop_id %d wwn %llx.\n", other_sess, other_sess->loop_id, other_wwn); @@ -4596,7 +4605,7 @@ qlt_find_sess_invalidate_other(scsi_qla_host_t *vha, uint64_t wwn, * Another wwn used to have our s_id/loop_id * kill the session, but don't free the loop_id */ - ql_dbg(ql_dbg_tgt_tmr, vha, 0xf01b, + ql_dbg(ql_dbg_disc, vha, 0xf01b, "Invalidating sess %p loop_id %d wwn %llx.\n", other_sess, other_sess->loop_id, other_wwn); @@ -4611,7 +4620,7 @@ qlt_find_sess_invalidate_other(scsi_qla_host_t *vha, uint64_t wwn, /* find other sess with nport handle collision */ if ((loop_id == other_sess->loop_id) && (loop_id != FC_NO_LOOP_ID)) { - ql_dbg(ql_dbg_tgt_tmr, vha, 0x1000d, + ql_dbg(ql_dbg_disc, vha, 0x1000d, "Invalidating sess %p loop_id %d wwn %llx.\n", other_sess, other_sess->loop_id, other_wwn); diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c index 5e502e160554..d538b3d4f74a 100644 --- a/drivers/scsi/ufs/ufshcd.c +++ b/drivers/scsi/ufs/ufshcd.c @@ -334,27 +334,27 @@ static void ufshcd_add_command_trace(struct ufs_hba *hba, u8 opcode = 0; u32 intr, doorbell; struct ufshcd_lrb *lrbp = &hba->lrb[tag]; + struct scsi_cmnd *cmd = lrbp->cmd; int transfer_len = -1; if (!trace_ufshcd_command_enabled()) { /* trace UPIU W/O tracing command */ - if (lrbp->cmd) + if (cmd) ufshcd_add_cmd_upiu_trace(hba, tag, str); return; } - if (lrbp->cmd) { /* data phase exists */ + if (cmd) { /* data phase exists */ /* trace UPIU also */ ufshcd_add_cmd_upiu_trace(hba, tag, str); - opcode = (u8)(*lrbp->cmd->cmnd); + opcode = cmd->cmnd[0]; if ((opcode == READ_10) || (opcode == WRITE_10)) { /* * Currently we only fully trace read(10) and write(10) * commands */ - if (lrbp->cmd->request && lrbp->cmd->request->bio) - lba = - lrbp->cmd->request->bio->bi_iter.bi_sector; + if (cmd->request && cmd->request->bio) + lba = cmd->request->bio->bi_iter.bi_sector; transfer_len = be32_to_cpu( lrbp->ucd_req_ptr->sc.exp_data_transfer_len); } @@ -1888,12 +1888,12 @@ void ufshcd_send_command(struct ufs_hba *hba, unsigned int task_tag) { hba->lrb[task_tag].issue_time_stamp = ktime_get(); hba->lrb[task_tag].compl_time_stamp = ktime_set(0, 0); + ufshcd_add_command_trace(hba, task_tag, "send"); ufshcd_clk_scaling_start_busy(hba); __set_bit(task_tag, &hba->outstanding_reqs); ufshcd_writel(hba, 1 << task_tag, REG_UTP_TRANSFER_REQ_DOOR_BELL); /* Make sure that doorbell is committed immediately */ wmb(); - ufshcd_add_command_trace(hba, task_tag, "send"); } /** diff --git a/drivers/soundwire/bus.c b/drivers/soundwire/bus.c index fc53dbe57f85..a90963812357 100644 --- a/drivers/soundwire/bus.c +++ b/drivers/soundwire/bus.c @@ -113,6 +113,8 @@ static int sdw_delete_slave(struct device *dev, void *data) struct sdw_slave *slave = dev_to_sdw_dev(dev); struct sdw_bus *bus = slave->bus; + pm_runtime_disable(dev); + sdw_slave_debugfs_exit(slave); mutex_lock(&bus->bus_lock); diff --git a/drivers/soundwire/cadence_master.c b/drivers/soundwire/cadence_master.c index 502ed4ec8f07..e3d06330d125 100644 --- a/drivers/soundwire/cadence_master.c +++ b/drivers/soundwire/cadence_master.c @@ -231,6 +231,22 @@ static int cdns_clear_bit(struct sdw_cdns *cdns, int offset, u32 value) return -EAGAIN; } +/* + * all changes to the MCP_CONFIG, MCP_CONTROL, MCP_CMDCTRL and MCP_PHYCTRL + * need to be confirmed with a write to MCP_CONFIG_UPDATE + */ +static int cdns_update_config(struct sdw_cdns *cdns) +{ + int ret; + + ret = cdns_clear_bit(cdns, CDNS_MCP_CONFIG_UPDATE, + CDNS_MCP_CONFIG_UPDATE_BIT); + if (ret < 0) + dev_err(cdns->dev, "Config update timedout\n"); + + return ret; +} + /* * debugfs */ @@ -752,7 +768,38 @@ EXPORT_SYMBOL(sdw_cdns_thread); /* * init routines */ -static int _cdns_enable_interrupt(struct sdw_cdns *cdns) + +/** + * sdw_cdns_exit_reset() - Program reset parameters and start bus operations + * @cdns: Cadence instance + */ +int sdw_cdns_exit_reset(struct sdw_cdns *cdns) +{ + /* program maximum length reset to be safe */ + cdns_updatel(cdns, CDNS_MCP_CONTROL, + CDNS_MCP_CONTROL_RST_DELAY, + CDNS_MCP_CONTROL_RST_DELAY); + + /* use hardware generated reset */ + cdns_updatel(cdns, CDNS_MCP_CONTROL, + CDNS_MCP_CONTROL_HW_RST, + CDNS_MCP_CONTROL_HW_RST); + + /* enable bus operations with clock and data */ + cdns_updatel(cdns, CDNS_MCP_CONFIG, + CDNS_MCP_CONFIG_OP, + CDNS_MCP_CONFIG_OP_NORMAL); + + /* commit changes */ + return cdns_update_config(cdns); +} +EXPORT_SYMBOL(sdw_cdns_exit_reset); + +/** + * sdw_cdns_enable_interrupt() - Enable SDW interrupts and update config + * @cdns: Cadence instance + */ +int sdw_cdns_enable_interrupt(struct sdw_cdns *cdns) { u32 mask; @@ -784,24 +831,8 @@ static int _cdns_enable_interrupt(struct sdw_cdns *cdns) cdns_writel(cdns, CDNS_MCP_INTMASK, mask); - return 0; -} - -/** - * sdw_cdns_enable_interrupt() - Enable SDW interrupts and update config - * @cdns: Cadence instance - */ -int sdw_cdns_enable_interrupt(struct sdw_cdns *cdns) -{ - int ret; - - _cdns_enable_interrupt(cdns); - ret = cdns_clear_bit(cdns, CDNS_MCP_CONFIG_UPDATE, - CDNS_MCP_CONFIG_UPDATE_BIT); - if (ret < 0) - dev_err(cdns->dev, "Config update timedout\n"); - - return ret; + /* commit changes */ + return cdns_update_config(cdns); } EXPORT_SYMBOL(sdw_cdns_enable_interrupt); @@ -975,6 +1006,10 @@ int sdw_cdns_init(struct sdw_cdns *cdns) cdns_writel(cdns, CDNS_MCP_SSP_CTRL0, CDNS_DEFAULT_SSP_INTERVAL); cdns_writel(cdns, CDNS_MCP_SSP_CTRL1, CDNS_DEFAULT_SSP_INTERVAL); + /* flush command FIFOs */ + cdns_updatel(cdns, CDNS_MCP_CONTROL, CDNS_MCP_CONTROL_CMD_RST, + CDNS_MCP_CONTROL_CMD_RST); + /* Set cmd accept mode */ cdns_updatel(cdns, CDNS_MCP_CONTROL, CDNS_MCP_CONTROL_CMD_ACCEPT, CDNS_MCP_CONTROL_CMD_ACCEPT); @@ -997,13 +1032,10 @@ int sdw_cdns_init(struct sdw_cdns *cdns) /* Set cmd mode for Tx and Rx cmds */ val &= ~CDNS_MCP_CONFIG_CMD; - /* Set operation to normal */ - val &= ~CDNS_MCP_CONFIG_OP; - val |= CDNS_MCP_CONFIG_OP_NORMAL; - cdns_writel(cdns, CDNS_MCP_CONFIG, val); - return 0; + /* commit changes */ + return cdns_update_config(cdns); } EXPORT_SYMBOL(sdw_cdns_init); diff --git a/drivers/soundwire/cadence_master.h b/drivers/soundwire/cadence_master.h index 0b72b7094735..1a67728c5000 100644 --- a/drivers/soundwire/cadence_master.h +++ b/drivers/soundwire/cadence_master.h @@ -161,6 +161,7 @@ irqreturn_t sdw_cdns_thread(int irq, void *dev_id); int sdw_cdns_init(struct sdw_cdns *cdns); int sdw_cdns_pdi_init(struct sdw_cdns *cdns, struct sdw_cdns_stream_config config); +int sdw_cdns_exit_reset(struct sdw_cdns *cdns); int sdw_cdns_enable_interrupt(struct sdw_cdns *cdns); #ifdef CONFIG_DEBUG_FS diff --git a/drivers/soundwire/intel.c b/drivers/soundwire/intel.c index 243af8198d1c..a2da04946f0b 100644 --- a/drivers/soundwire/intel.c +++ b/drivers/soundwire/intel.c @@ -1050,8 +1050,6 @@ static int intel_probe(struct platform_device *pdev) if (ret) goto err_init; - ret = sdw_cdns_enable_interrupt(&sdw->cdns); - /* Read the PDI config and initialize cadence PDI */ intel_pdi_init(sdw, &config); ret = sdw_cdns_pdi_init(&sdw->cdns, config); @@ -1069,6 +1067,18 @@ static int intel_probe(struct platform_device *pdev) goto err_init; } + ret = sdw_cdns_enable_interrupt(&sdw->cdns); + if (ret < 0) { + dev_err(sdw->cdns.dev, "cannot enable interrupts\n"); + goto err_init; + } + + ret = sdw_cdns_exit_reset(&sdw->cdns); + if (ret < 0) { + dev_err(sdw->cdns.dev, "unable to exit bus reset sequence\n"); + goto err_init; + } + /* Register DAIs */ ret = intel_register_dai(sdw); if (ret) { diff --git a/drivers/staging/media/imx/imx-media-capture.c b/drivers/staging/media/imx/imx-media-capture.c index 46576e32581f..d151cd6d3188 100644 --- a/drivers/staging/media/imx/imx-media-capture.c +++ b/drivers/staging/media/imx/imx-media-capture.c @@ -785,7 +785,7 @@ int imx_media_capture_device_register(struct imx_media_video_dev *vdev) /* setup default format */ fmt_src.pad = priv->src_sd_pad; fmt_src.which = V4L2_SUBDEV_FORMAT_ACTIVE; - v4l2_subdev_call(sd, pad, get_fmt, NULL, &fmt_src); + ret = v4l2_subdev_call(sd, pad, get_fmt, NULL, &fmt_src); if (ret) { v4l2_err(sd, "failed to get src_sd format\n"); goto unreg; diff --git a/drivers/staging/rtl8188eu/core/rtw_recv.c b/drivers/staging/rtl8188eu/core/rtw_recv.c index d4278361e002..a036ef104198 100644 --- a/drivers/staging/rtl8188eu/core/rtw_recv.c +++ b/drivers/staging/rtl8188eu/core/rtw_recv.c @@ -1525,21 +1525,14 @@ static int amsdu_to_msdu(struct adapter *padapter, struct recv_frame *prframe) /* Allocate new skb for releasing to upper layer */ sub_skb = dev_alloc_skb(nSubframe_Length + 12); - if (sub_skb) { - skb_reserve(sub_skb, 12); - skb_put_data(sub_skb, pdata, nSubframe_Length); - } else { - sub_skb = skb_clone(prframe->pkt, GFP_ATOMIC); - if (sub_skb) { - sub_skb->data = pdata; - sub_skb->len = nSubframe_Length; - skb_set_tail_pointer(sub_skb, nSubframe_Length); - } else { - DBG_88E("skb_clone() Fail!!! , nr_subframes=%d\n", nr_subframes); - break; - } + if (!sub_skb) { + DBG_88E("dev_alloc_skb() Fail!!! , nr_subframes=%d\n", nr_subframes); + break; } + skb_reserve(sub_skb, 12); + skb_put_data(sub_skb, pdata, nSubframe_Length); + subframes[nr_subframes++] = sub_skb; if (nr_subframes >= MAX_SUBFRAME_COUNT) { diff --git a/drivers/thermal/rcar_thermal.c b/drivers/thermal/rcar_thermal.c index d0873de718da..43f0cd2bd0ae 100644 --- a/drivers/thermal/rcar_thermal.c +++ b/drivers/thermal/rcar_thermal.c @@ -526,8 +526,10 @@ static int rcar_thermal_probe(struct platform_device *pdev) res = platform_get_resource(pdev, IORESOURCE_MEM, mres++); common->base = devm_ioremap_resource(dev, res); - if (IS_ERR(common->base)) - return PTR_ERR(common->base); + if (IS_ERR(common->base)) { + ret = PTR_ERR(common->base); + goto error_unregister; + } idle = 0; /* polling delay is not needed */ } diff --git a/drivers/tty/serial/8250/8250_omap.c b/drivers/tty/serial/8250/8250_omap.c index 836e736ae188..f2c6d9d3bb28 100644 --- a/drivers/tty/serial/8250/8250_omap.c +++ b/drivers/tty/serial/8250/8250_omap.c @@ -790,7 +790,10 @@ static void __dma_rx_do_complete(struct uart_8250_port *p) dmaengine_tx_status(dma->rxchan, dma->rx_cookie, &state); count = dma->rx_size - state.residue; - + if (count < dma->rx_size) + dmaengine_terminate_async(dma->rxchan); + if (!count) + goto unlock; ret = tty_insert_flip_string(tty_port, dma->rx_buf, count); p->port.icount.rx += ret; @@ -852,7 +855,6 @@ static void omap_8250_rx_dma_flush(struct uart_8250_port *p) spin_unlock_irqrestore(&priv->rx_dma_lock, flags); __dma_rx_do_complete(p); - dmaengine_terminate_all(dma->rxchan); } static int omap_8250_rx_dma(struct uart_8250_port *p) @@ -1234,6 +1236,7 @@ static int omap8250_probe(struct platform_device *pdev) spin_lock_init(&priv->rx_dma_lock); device_init_wakeup(&pdev->dev, true); + pm_runtime_enable(&pdev->dev); pm_runtime_use_autosuspend(&pdev->dev); /* @@ -1247,7 +1250,6 @@ static int omap8250_probe(struct platform_device *pdev) pm_runtime_set_autosuspend_delay(&pdev->dev, -1); pm_runtime_irq_safe(&pdev->dev); - pm_runtime_enable(&pdev->dev); pm_runtime_get_sync(&pdev->dev); diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c index 90f09ed6e5ad..5b673077639b 100644 --- a/drivers/tty/serial/8250/8250_port.c +++ b/drivers/tty/serial/8250/8250_port.c @@ -1816,6 +1816,7 @@ int serial8250_handle_irq(struct uart_port *port, unsigned int iir) unsigned char status; unsigned long flags; struct uart_8250_port *up = up_to_u8250p(port); + bool skip_rx = false; if (iir & UART_IIR_NO_INT) return 0; @@ -1824,7 +1825,20 @@ int serial8250_handle_irq(struct uart_port *port, unsigned int iir) status = serial_port_in(port, UART_LSR); - if (status & (UART_LSR_DR | UART_LSR_BI)) { + /* + * If port is stopped and there are no error conditions in the + * FIFO, then don't drain the FIFO, as this may lead to TTY buffer + * overflow. Not servicing, RX FIFO would trigger auto HW flow + * control when FIFO occupancy reaches preset threshold, thus + * halting RX. This only works when auto HW flow control is + * available. + */ + if (!(status & (UART_LSR_FIFOE | UART_LSR_BRK_ERROR_BITS)) && + (port->status & (UPSTAT_AUTOCTS | UPSTAT_AUTORTS)) && + !(port->read_status_mask & UART_LSR_DR)) + skip_rx = true; + + if (status & (UART_LSR_DR | UART_LSR_BI) && !skip_rx) { if (!up->dma || handle_rx_dma(up, iir)) status = serial8250_rx_chars(up, status); } diff --git a/drivers/tty/serial/samsung.c b/drivers/tty/serial/samsung.c index 71f99e921759..c7683beb3412 100644 --- a/drivers/tty/serial/samsung.c +++ b/drivers/tty/serial/samsung.c @@ -1187,14 +1187,14 @@ static unsigned int s3c24xx_serial_getclk(struct s3c24xx_uart_port *ourport, struct s3c24xx_uart_info *info = ourport->info; struct clk *clk; unsigned long rate; - unsigned int cnt, baud, quot, clk_sel, best_quot = 0; + unsigned int cnt, baud, quot, best_quot = 0; char clkname[MAX_CLK_NAME_LENGTH]; int calc_deviation, deviation = (1 << 30) - 1; - clk_sel = (ourport->cfg->clk_sel) ? ourport->cfg->clk_sel : - ourport->info->def_clk_sel; for (cnt = 0; cnt < info->num_clks; cnt++) { - if (!(clk_sel & (1 << cnt))) + /* Keep selected clock if provided */ + if (ourport->cfg->clk_sel && + !(ourport->cfg->clk_sel & (1 << cnt))) continue; sprintf(clkname, "clk_uart_baud%d", cnt); diff --git a/drivers/tty/serial/sifive.c b/drivers/tty/serial/sifive.c index 38133eba83a8..b4343c6aa651 100644 --- a/drivers/tty/serial/sifive.c +++ b/drivers/tty/serial/sifive.c @@ -618,10 +618,10 @@ static void sifive_serial_shutdown(struct uart_port *port) * * On the V0 SoC, the UART IP block is derived from the CPU clock source * after a synchronous divide-by-two divider, so any CPU clock rate change - * requires the UART baud rate to be updated. This presumably could corrupt any - * serial word currently being transmitted or received. It would probably - * be better to stop receives and transmits, then complete the baud rate - * change, then re-enable them. + * requires the UART baud rate to be updated. This presumably corrupts any + * serial word currently being transmitted or received. In order to avoid + * corrupting the output data stream, we drain the transmit queue before + * allowing the clock's rate to be changed. */ static int sifive_serial_clk_notifier(struct notifier_block *nb, unsigned long event, void *data) @@ -629,6 +629,26 @@ static int sifive_serial_clk_notifier(struct notifier_block *nb, struct clk_notifier_data *cnd = data; struct sifive_serial_port *ssp = notifier_to_sifive_serial_port(nb); + if (event == PRE_RATE_CHANGE) { + /* + * The TX watermark is always set to 1 by this driver, which + * means that the TX busy bit will lower when there are 0 bytes + * left in the TX queue -- in other words, when the TX FIFO is + * empty. + */ + __ssp_wait_for_xmitr(ssp); + /* + * On the cycle the TX FIFO goes empty there is still a full + * UART frame left to be transmitted in the shift register. + * The UART provides no way for software to directly determine + * when that last frame has been transmitted, so we just sleep + * here instead. As we're not tracking the number of stop bits + * they're just worst cased here. The rest of the serial + * framing parameters aren't configurable by software. + */ + udelay(DIV_ROUND_UP(12 * 1000 * 1000, ssp->baud_rate)); + } + if (event == POST_RATE_CHANGE && ssp->clkin_rate != cnd->new_rate) { ssp->clkin_rate = cnd->new_rate; __ssp_update_div(ssp); diff --git a/drivers/tty/serial/xilinx_uartps.c b/drivers/tty/serial/xilinx_uartps.c index 8948970f795e..9359c80fbb9f 100644 --- a/drivers/tty/serial/xilinx_uartps.c +++ b/drivers/tty/serial/xilinx_uartps.c @@ -1248,6 +1248,7 @@ static int cdns_uart_console_setup(struct console *co, char *options) int bits = 8; int parity = 'n'; int flow = 'n'; + unsigned long time_out; if (!port->membase) { pr_debug("console on " CDNS_UART_TTY_NAME "%i not present\n", @@ -1258,6 +1259,13 @@ static int cdns_uart_console_setup(struct console *co, char *options) if (options) uart_parse_options(options, &baud, &parity, &bits, &flow); + /* Wait for tx_empty before setting up the console */ + time_out = jiffies + usecs_to_jiffies(TX_TIMEOUT); + + while (time_before(jiffies, time_out) && + cdns_uart_tx_empty(port) != TIOCSER_TEMT) + cpu_relax(); + return uart_set_options(port, co, baud, parity, bits, flow); } diff --git a/drivers/tty/vcc.c b/drivers/tty/vcc.c index d2a1e1228c82..9ffd42e333b8 100644 --- a/drivers/tty/vcc.c +++ b/drivers/tty/vcc.c @@ -605,6 +605,7 @@ static int vcc_probe(struct vio_dev *vdev, const struct vio_device_id *id) port->index = vcc_table_add(port); if (port->index == -1) { pr_err("VCC: no more TTY indices left for allocation\n"); + rv = -ENOMEM; goto free_ldc; } diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index 422554434251..809103254fc6 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -270,7 +270,7 @@ int dwc3_send_gadget_ep_cmd(struct dwc3_ep *dep, unsigned cmd, { const struct usb_endpoint_descriptor *desc = dep->endpoint.desc; struct dwc3 *dwc = dep->dwc; - u32 timeout = 1000; + u32 timeout = 5000; u32 saved_config = 0; u32 reg; diff --git a/drivers/usb/host/ehci-mv.c b/drivers/usb/host/ehci-mv.c index 66ec1fdf9fe7..b6f196f5e252 100644 --- a/drivers/usb/host/ehci-mv.c +++ b/drivers/usb/host/ehci-mv.c @@ -156,12 +156,10 @@ static int mv_ehci_probe(struct platform_device *pdev) hcd->rsrc_len = resource_size(r); hcd->regs = ehci_mv->op_regs; - hcd->irq = platform_get_irq(pdev, 0); - if (!hcd->irq) { - dev_err(&pdev->dev, "Cannot get irq."); - retval = -ENODEV; + retval = platform_get_irq(pdev, 0); + if (retval < 0) goto err_disable_clk; - } + hcd->irq = retval; ehci = hcd_to_ehci(hcd); ehci->caps = (struct ehci_caps *) ehci_mv->cap_regs; diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c index 0d16f9806655..a72fd5309b09 100644 --- a/drivers/vfio/pci/vfio_pci.c +++ b/drivers/vfio/pci/vfio_pci.c @@ -474,6 +474,19 @@ static void vfio_pci_release(void *device_data) if (!(--vdev->refcnt)) { vfio_spapr_pci_eeh_release(vdev->pdev); vfio_pci_disable(vdev); + mutex_lock(&vdev->igate); + if (vdev->err_trigger) { + eventfd_ctx_put(vdev->err_trigger); + vdev->err_trigger = NULL; + } + mutex_unlock(&vdev->igate); + + mutex_lock(&vdev->igate); + if (vdev->req_trigger) { + eventfd_ctx_put(vdev->req_trigger); + vdev->req_trigger = NULL; + } + mutex_unlock(&vdev->igate); } mutex_unlock(&vdev->reflck->lock); diff --git a/fs/block_dev.c b/fs/block_dev.c index 2dc9c73a4cb2..79272cdbe827 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -1857,6 +1857,16 @@ static void __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part) struct gendisk *disk = bdev->bd_disk; struct block_device *victim = NULL; + /* + * Sync early if it looks like we're the last one. If someone else + * opens the block device between now and the decrement of bd_openers + * then we did a sync that we didn't need to, but that's not the end + * of the world and we want to avoid long (could be several minute) + * syncs while holding the mutex. + */ + if (bdev->bd_openers == 1) + sync_blockdev(bdev); + mutex_lock_nested(&bdev->bd_mutex, for_part); if (for_part) bdev->bd_part_count--; diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index dd6fb2ee8040..cd65ef7c7c3f 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -649,16 +649,15 @@ static int btree_readpage_end_io_hook(struct btrfs_io_bio *io_bio, goto err; if (memcmp_extent_buffer(eb, result, 0, csum_size)) { - u32 val; - u32 found = 0; - - memcpy(&found, result, csum_size); + u8 val[BTRFS_CSUM_SIZE] = { 0 }; read_extent_buffer(eb, &val, 0, csum_size); btrfs_warn_rl(fs_info, - "%s checksum verify failed on %llu wanted %x found %x level %d", + "%s checksum verify failed on %llu wanted " CSUM_FMT " found " CSUM_FMT " level %d", fs_info->sb->s_id, eb->start, - val, found, btrfs_header_level(eb)); + CSUM_FMT_VALUE(csum_size, val), + CSUM_FMT_VALUE(csum_size, result), + btrfs_header_level(eb)); ret = -EUCLEAN; goto err; } diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 31c1ed554d26..7658f3193175 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -5428,8 +5428,6 @@ int btrfs_drop_snapshot(struct btrfs_root *root, */ if (!for_reloc && !root_dropped) btrfs_add_dead_root(root); - if (err && err != -EAGAIN) - btrfs_handle_fs_error(fs_info, err, NULL); return err; } diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 9ac40991a640..182e93a5b11d 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -8586,14 +8586,64 @@ static inline blk_status_t btrfs_submit_dio_bio(struct bio *bio, return ret; } -static int btrfs_submit_direct_hook(struct btrfs_dio_private *dip) +/* + * If this succeeds, the btrfs_dio_private is responsible for cleaning up locked + * or ordered extents whether or not we submit any bios. + */ +static struct btrfs_dio_private *btrfs_create_dio_private(struct bio *dio_bio, + struct inode *inode, + loff_t file_offset) { - struct inode *inode = dip->inode; + const bool write = (bio_op(dio_bio) == REQ_OP_WRITE); + struct btrfs_dio_private *dip; + struct bio *bio; + + dip = kzalloc(sizeof(*dip), GFP_NOFS); + if (!dip) + return NULL; + + bio = btrfs_bio_clone(dio_bio); + bio->bi_private = dip; + btrfs_io_bio(bio)->logical = file_offset; + + dip->private = dio_bio->bi_private; + dip->inode = inode; + dip->logical_offset = file_offset; + dip->bytes = dio_bio->bi_iter.bi_size; + dip->disk_bytenr = (u64)dio_bio->bi_iter.bi_sector << 9; + dip->orig_bio = bio; + dip->dio_bio = dio_bio; + atomic_set(&dip->pending_bios, 1); + + if (write) { + struct btrfs_dio_data *dio_data = current->journal_info; + + /* + * Setting range start and end to the same value means that + * no cleanup will happen in btrfs_direct_IO + */ + dio_data->unsubmitted_oe_range_end = dip->logical_offset + + dip->bytes; + dio_data->unsubmitted_oe_range_start = + dio_data->unsubmitted_oe_range_end; + + bio->bi_end_io = btrfs_endio_direct_write; + } else { + bio->bi_end_io = btrfs_endio_direct_read; + dip->subio_endio = btrfs_subio_endio_read; + } + return dip; +} + +static void btrfs_submit_direct(struct bio *dio_bio, struct inode *inode, + loff_t file_offset) +{ + const bool write = (bio_op(dio_bio) == REQ_OP_WRITE); struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + struct btrfs_dio_private *dip; struct bio *bio; - struct bio *orig_bio = dip->orig_bio; - u64 start_sector = orig_bio->bi_iter.bi_sector; - u64 file_offset = dip->logical_offset; + struct bio *orig_bio; + u64 start_sector; int async_submit = 0; u64 submit_len; int clone_offset = 0; @@ -8602,11 +8652,24 @@ static int btrfs_submit_direct_hook(struct btrfs_dio_private *dip) blk_status_t status; struct btrfs_io_geometry geom; + dip = btrfs_create_dio_private(dio_bio, inode, file_offset); + if (!dip) { + if (!write) { + unlock_extent(&BTRFS_I(inode)->io_tree, file_offset, + file_offset + dio_bio->bi_iter.bi_size - 1); + } + dio_bio->bi_status = BLK_STS_RESOURCE; + dio_end_io(dio_bio); + return; + } + + orig_bio = dip->orig_bio; + start_sector = orig_bio->bi_iter.bi_sector; submit_len = orig_bio->bi_iter.bi_size; ret = btrfs_get_io_geometry(fs_info, btrfs_op(orig_bio), start_sector << 9, submit_len, &geom); if (ret) - return -EIO; + goto out_err; if (geom.len >= submit_len) { bio = orig_bio; @@ -8669,7 +8732,7 @@ static int btrfs_submit_direct_hook(struct btrfs_dio_private *dip) submit: status = btrfs_submit_dio_bio(bio, inode, file_offset, async_submit); if (!status) - return 0; + return; if (bio != orig_bio) bio_put(bio); @@ -8683,107 +8746,6 @@ static int btrfs_submit_direct_hook(struct btrfs_dio_private *dip) */ if (atomic_dec_and_test(&dip->pending_bios)) bio_io_error(dip->orig_bio); - - /* bio_end_io() will handle error, so we needn't return it */ - return 0; -} - -static void btrfs_submit_direct(struct bio *dio_bio, struct inode *inode, - loff_t file_offset) -{ - struct btrfs_dio_private *dip = NULL; - struct bio *bio = NULL; - struct btrfs_io_bio *io_bio; - bool write = (bio_op(dio_bio) == REQ_OP_WRITE); - int ret = 0; - - bio = btrfs_bio_clone(dio_bio); - - dip = kzalloc(sizeof(*dip), GFP_NOFS); - if (!dip) { - ret = -ENOMEM; - goto free_ordered; - } - - dip->private = dio_bio->bi_private; - dip->inode = inode; - dip->logical_offset = file_offset; - dip->bytes = dio_bio->bi_iter.bi_size; - dip->disk_bytenr = (u64)dio_bio->bi_iter.bi_sector << 9; - bio->bi_private = dip; - dip->orig_bio = bio; - dip->dio_bio = dio_bio; - atomic_set(&dip->pending_bios, 1); - io_bio = btrfs_io_bio(bio); - io_bio->logical = file_offset; - - if (write) { - bio->bi_end_io = btrfs_endio_direct_write; - } else { - bio->bi_end_io = btrfs_endio_direct_read; - dip->subio_endio = btrfs_subio_endio_read; - } - - /* - * Reset the range for unsubmitted ordered extents (to a 0 length range) - * even if we fail to submit a bio, because in such case we do the - * corresponding error handling below and it must not be done a second - * time by btrfs_direct_IO(). - */ - if (write) { - struct btrfs_dio_data *dio_data = current->journal_info; - - dio_data->unsubmitted_oe_range_end = dip->logical_offset + - dip->bytes; - dio_data->unsubmitted_oe_range_start = - dio_data->unsubmitted_oe_range_end; - } - - ret = btrfs_submit_direct_hook(dip); - if (!ret) - return; - - btrfs_io_bio_free_csum(io_bio); - -free_ordered: - /* - * If we arrived here it means either we failed to submit the dip - * or we either failed to clone the dio_bio or failed to allocate the - * dip. If we cloned the dio_bio and allocated the dip, we can just - * call bio_endio against our io_bio so that we get proper resource - * cleanup if we fail to submit the dip, otherwise, we must do the - * same as btrfs_endio_direct_[write|read] because we can't call these - * callbacks - they require an allocated dip and a clone of dio_bio. - */ - if (bio && dip) { - bio_io_error(bio); - /* - * The end io callbacks free our dip, do the final put on bio - * and all the cleanup and final put for dio_bio (through - * dio_end_io()). - */ - dip = NULL; - bio = NULL; - } else { - if (write) - __endio_write_update_ordered(inode, - file_offset, - dio_bio->bi_iter.bi_size, - false); - else - unlock_extent(&BTRFS_I(inode)->io_tree, file_offset, - file_offset + dio_bio->bi_iter.bi_size - 1); - - dio_bio->bi_status = BLK_STS_IOERR; - /* - * Releases and cleans up our dio_bio, no need to bio_put() - * nor bio_endio()/bio_io_error() against dio_bio. - */ - dio_end_io(dio_bio); - } - if (bio) - bio_put(bio); - kfree(dip); } static ssize_t check_direct_IO(struct btrfs_fs_info *fs_info, @@ -9082,20 +9044,17 @@ static void btrfs_invalidatepage(struct page *page, unsigned int offset, /* * Qgroup reserved space handler * Page here will be either - * 1) Already written to disk - * In this case, its reserved space is released from data rsv map - * and will be freed by delayed_ref handler finally. - * So even we call qgroup_free_data(), it won't decrease reserved - * space. - * 2) Not written to disk - * This means the reserved space should be freed here. However, - * if a truncate invalidates the page (by clearing PageDirty) - * and the page is accounted for while allocating extent - * in btrfs_check_data_free_space() we let delayed_ref to - * free the entire extent. + * 1) Already written to disk or ordered extent already submitted + * Then its QGROUP_RESERVED bit in io_tree is already cleaned. + * Qgroup will be handled by its qgroup_record then. + * btrfs_qgroup_free_data() call will do nothing here. + * + * 2) Not written to disk yet + * Then btrfs_qgroup_free_data() call will clear the QGROUP_RESERVED + * bit of its io_tree, and free the qgroup reserved data space. + * Since the IO will never happen for this page. */ - if (PageDirty(page)) - btrfs_qgroup_free_data(inode, NULL, page_start, PAGE_SIZE); + btrfs_qgroup_free_data(inode, NULL, page_start, PAGE_SIZE); if (!inode_evicting) { clear_extent_bit(tree, page_start, page_end, EXTENT_LOCKED | EXTENT_DELALLOC | EXTENT_DELALLOC_NEW | diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index af3605a0bf2e..1bc57f7b91cf 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -1468,6 +1468,9 @@ int btrfs_init_reloc_root(struct btrfs_trans_handle *trans, int clear_rsv = 0; int ret; + if (!rc) + return 0; + /* * The subvolume has reloc tree but the swap is finished, no need to * create/update the dead reloc tree @@ -1475,13 +1478,25 @@ int btrfs_init_reloc_root(struct btrfs_trans_handle *trans, if (reloc_root_is_dead(root)) return 0; + /* + * This is subtle but important. We do not do + * record_root_in_transaction for reloc roots, instead we record their + * corresponding fs root, and then here we update the last trans for the + * reloc root. This means that we have to do this for the entire life + * of the reloc root, regardless of which stage of the relocation we are + * in. + */ if (root->reloc_root) { reloc_root = root->reloc_root; reloc_root->last_trans = trans->transid; return 0; } - if (!rc || !rc->create_reloc_tree || + /* + * We are merging reloc roots, we do not need new reloc trees. Also + * reloc trees never need their own reloc tree. + */ + if (!rc->create_reloc_tree || root->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID) return 0; @@ -2336,6 +2351,18 @@ static noinline_for_stack int merge_reloc_root(struct reloc_control *rc, trans = NULL; goto out; } + + /* + * At this point we no longer have a reloc_control, so we can't + * depend on btrfs_init_reloc_root to update our last_trans. + * + * But that's ok, we started the trans handle on our + * corresponding fs_root, which means it's been added to the + * dirty list. At commit time we'll still call + * btrfs_update_reloc_root() and update our root item + * appropriately. + */ + reloc_root->last_trans = trans->transid; trans->block_rsv = rc->block_rsv; replaced = 0; @@ -4342,6 +4369,18 @@ static struct reloc_control *alloc_reloc_control(struct btrfs_fs_info *fs_info) return rc; } +static void free_reloc_control(struct reloc_control *rc) +{ + struct mapping_node *node, *tmp; + + free_reloc_roots(&rc->reloc_roots); + rbtree_postorder_for_each_entry_safe(node, tmp, + &rc->reloc_root_tree.rb_root, rb_node) + kfree(node); + + kfree(rc); +} + /* * Print the block group being relocated */ @@ -4474,7 +4513,7 @@ int btrfs_relocate_block_group(struct btrfs_fs_info *fs_info, u64 group_start) btrfs_dec_block_group_ro(rc->block_group); iput(rc->data_inode); btrfs_put_block_group(rc->block_group); - kfree(rc); + free_reloc_control(rc); return err; } @@ -4647,7 +4686,7 @@ int btrfs_recover_relocation(struct btrfs_root *root) err = ret; out_unset: unset_reloc_control(rc); - kfree(rc); + free_reloc_control(rc); out: if (!list_empty(&reloc_roots)) free_reloc_roots(&reloc_roots); diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c index 91ea38506fbb..84b8d6ebf98f 100644 --- a/fs/btrfs/tree-checker.c +++ b/fs/btrfs/tree-checker.c @@ -674,6 +674,44 @@ int btrfs_check_chunk_valid(struct extent_buffer *leaf, return 0; } +/* + * Enhanced version of chunk item checker. + * + * The common btrfs_check_chunk_valid() doesn't check item size since it needs + * to work on super block sys_chunk_array which doesn't have full item ptr. + */ +static int check_leaf_chunk_item(struct extent_buffer *leaf, + struct btrfs_chunk *chunk, + struct btrfs_key *key, int slot) +{ + int num_stripes; + + if (btrfs_item_size_nr(leaf, slot) < sizeof(struct btrfs_chunk)) { + chunk_err(leaf, chunk, key->offset, + "invalid chunk item size: have %u expect [%zu, %u)", + btrfs_item_size_nr(leaf, slot), + sizeof(struct btrfs_chunk), + BTRFS_LEAF_DATA_SIZE(leaf->fs_info)); + return -EUCLEAN; + } + + num_stripes = btrfs_chunk_num_stripes(leaf, chunk); + /* Let btrfs_check_chunk_valid() handle this error type */ + if (num_stripes == 0) + goto out; + + if (btrfs_chunk_item_size(num_stripes) != + btrfs_item_size_nr(leaf, slot)) { + chunk_err(leaf, chunk, key->offset, + "invalid chunk item size: have %u expect %lu", + btrfs_item_size_nr(leaf, slot), + btrfs_chunk_item_size(num_stripes)); + return -EUCLEAN; + } +out: + return btrfs_check_chunk_valid(leaf, chunk, key->offset); +} + __printf(3, 4) __cold static void dev_item_err(const struct extent_buffer *eb, int slot, @@ -1265,7 +1303,7 @@ static int check_leaf_item(struct extent_buffer *leaf, break; case BTRFS_CHUNK_ITEM_KEY: chunk = btrfs_item_ptr(leaf, slot, struct btrfs_chunk); - ret = btrfs_check_chunk_valid(leaf, chunk, key->offset); + ret = check_leaf_chunk_item(leaf, chunk, key, slot); break; case BTRFS_DEV_ITEM_KEY: ret = check_dev_item(leaf, key, slot); diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index b2695919435e..af563d73d252 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -2013,12 +2013,24 @@ void ceph_check_caps(struct ceph_inode_info *ci, int flags, if (mutex_trylock(&session->s_mutex) == 0) { dout("inverting session/ino locks on %p\n", session); + session = ceph_get_mds_session(session); spin_unlock(&ci->i_ceph_lock); if (took_snap_rwsem) { up_read(&mdsc->snap_rwsem); took_snap_rwsem = 0; } - mutex_lock(&session->s_mutex); + if (session) { + mutex_lock(&session->s_mutex); + ceph_put_mds_session(session); + } else { + /* + * Because we take the reference while + * holding the i_ceph_lock, it should + * never be NULL. Throw a warning if it + * ever is. + */ + WARN_ON_ONCE(true); + } goto retry; } } diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index c07407586ce8..660a878e20ef 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -754,8 +754,11 @@ static int fill_inode(struct inode *inode, struct page *locked_page, info_caps = le32_to_cpu(info->cap.caps); /* prealloc new cap struct */ - if (info_caps && ceph_snap(inode) == CEPH_NOSNAP) + if (info_caps && ceph_snap(inode) == CEPH_NOSNAP) { new_cap = ceph_get_cap(mdsc, caps_reservation); + if (!new_cap) + return -ENOMEM; + } /* * prealloc xattr data, if it looks like we'll need it. only diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index f9cbdfc1591b..b16c994414ab 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -268,8 +268,9 @@ struct smb_version_operations { int (*check_message)(char *, unsigned int, struct TCP_Server_Info *); bool (*is_oplock_break)(char *, struct TCP_Server_Info *); int (*handle_cancelled_mid)(char *, struct TCP_Server_Info *); - void (*downgrade_oplock)(struct TCP_Server_Info *, - struct cifsInodeInfo *, bool); + void (*downgrade_oplock)(struct TCP_Server_Info *server, + struct cifsInodeInfo *cinode, __u32 oplock, + unsigned int epoch, bool *purge_cache); /* process transaction2 response */ bool (*check_trans2)(struct mid_q_entry *, struct TCP_Server_Info *, char *, int); @@ -1261,6 +1262,8 @@ struct cifsFileInfo { unsigned int f_flags; bool invalidHandle:1; /* file closed via session abend */ bool oplock_break_cancelled:1; + unsigned int oplock_epoch; /* epoch from the lease break */ + __u32 oplock_level; /* oplock/lease level from the lease break */ int count; spinlock_t file_info_lock; /* protects four flag/count fields above */ struct mutex fh_mutex; /* prevents reopen race after dead ses*/ @@ -1408,7 +1411,7 @@ struct cifsInodeInfo { unsigned int epoch; /* used to track lease state changes */ #define CIFS_INODE_PENDING_OPLOCK_BREAK (0) /* oplock break in progress */ #define CIFS_INODE_PENDING_WRITERS (1) /* Writes in progress */ -#define CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2 (2) /* Downgrade oplock to L2 */ +#define CIFS_INODE_FLAG_UNUSED (2) /* Unused flag */ #define CIFS_INO_DELETE_PENDING (3) /* delete pending on server */ #define CIFS_INO_INVALID_MAPPING (4) /* pagecache is invalid */ #define CIFS_INO_LOCK (5) /* lock bit for synchronization */ diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 4959dbe740f7..31d578739341 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -4269,7 +4269,8 @@ readpages_get_pages(struct address_space *mapping, struct list_head *page_list, break; __SetPageLocked(page); - if (add_to_page_cache_locked(page, mapping, page->index, gfp)) { + rc = add_to_page_cache_locked(page, mapping, page->index, gfp); + if (rc) { __ClearPageLocked(page); break; } @@ -4285,6 +4286,7 @@ static int cifs_readpages(struct file *file, struct address_space *mapping, struct list_head *page_list, unsigned num_pages) { int rc; + int err = 0; struct list_head tmplist; struct cifsFileInfo *open_file = file->private_data; struct cifs_sb_info *cifs_sb = CIFS_FILE_SB(file); @@ -4329,7 +4331,7 @@ static int cifs_readpages(struct file *file, struct address_space *mapping, * the order of declining indexes. When we put the pages in * the rdata->pages, then we want them in increasing order. */ - while (!list_empty(page_list)) { + while (!list_empty(page_list) && !err) { unsigned int i, nr_pages, bytes, rsize; loff_t offset; struct page *page, *tpage; @@ -4362,9 +4364,10 @@ static int cifs_readpages(struct file *file, struct address_space *mapping, return 0; } - rc = readpages_get_pages(mapping, page_list, rsize, &tmplist, + nr_pages = 0; + err = readpages_get_pages(mapping, page_list, rsize, &tmplist, &nr_pages, &offset, &bytes); - if (rc) { + if (!nr_pages) { add_credits_and_wake_if(server, credits, 0); break; } @@ -4675,12 +4678,13 @@ void cifs_oplock_break(struct work_struct *work) struct cifs_tcon *tcon = tlink_tcon(cfile->tlink); struct TCP_Server_Info *server = tcon->ses->server; int rc = 0; + bool purge_cache = false; wait_on_bit(&cinode->flags, CIFS_INODE_PENDING_WRITERS, TASK_UNINTERRUPTIBLE); - server->ops->downgrade_oplock(server, cinode, - test_bit(CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2, &cinode->flags)); + server->ops->downgrade_oplock(server, cinode, cfile->oplock_level, + cfile->oplock_epoch, &purge_cache); if (!CIFS_CACHE_WRITE(cinode) && CIFS_CACHE_READ(cinode) && cifs_has_mand_locks(cinode)) { @@ -4695,18 +4699,21 @@ void cifs_oplock_break(struct work_struct *work) else break_lease(inode, O_WRONLY); rc = filemap_fdatawrite(inode->i_mapping); - if (!CIFS_CACHE_READ(cinode)) { + if (!CIFS_CACHE_READ(cinode) || purge_cache) { rc = filemap_fdatawait(inode->i_mapping); mapping_set_error(inode->i_mapping, rc); cifs_zap_mapping(inode); } cifs_dbg(FYI, "Oplock flush inode %p rc %d\n", inode, rc); + if (CIFS_CACHE_WRITE(cinode)) + goto oplock_break_ack; } rc = cifs_push_locks(cfile); if (rc) cifs_dbg(VFS, "Push locks rc = %d\n", rc); +oplock_break_ack: /* * releasing stale oplock after recent reconnect of smb session using * a now incorrect file handle is not a data integrity issue but do diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c index 5ad83bdb9bea..40ca394fd5de 100644 --- a/fs/cifs/misc.c +++ b/fs/cifs/misc.c @@ -488,21 +488,10 @@ is_valid_oplock_break(char *buffer, struct TCP_Server_Info *srv) set_bit(CIFS_INODE_PENDING_OPLOCK_BREAK, &pCifsInode->flags); - /* - * Set flag if the server downgrades the oplock - * to L2 else clear. - */ - if (pSMB->OplockLevel) - set_bit( - CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2, - &pCifsInode->flags); - else - clear_bit( - CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2, - &pCifsInode->flags); - - cifs_queue_oplock_break(netfile); + netfile->oplock_epoch = 0; + netfile->oplock_level = pSMB->OplockLevel; netfile->oplock_break_cancelled = false; + cifs_queue_oplock_break(netfile); spin_unlock(&tcon->open_file_lock); spin_unlock(&cifs_tcp_ses_lock); diff --git a/fs/cifs/smb1ops.c b/fs/cifs/smb1ops.c index 195766221a7a..e523c05a4487 100644 --- a/fs/cifs/smb1ops.c +++ b/fs/cifs/smb1ops.c @@ -369,12 +369,10 @@ coalesce_t2(char *second_buf, struct smb_hdr *target_hdr) static void cifs_downgrade_oplock(struct TCP_Server_Info *server, - struct cifsInodeInfo *cinode, bool set_level2) + struct cifsInodeInfo *cinode, __u32 oplock, + unsigned int epoch, bool *purge_cache) { - if (set_level2) - cifs_set_oplock_level(cinode, OPLOCK_READ); - else - cifs_set_oplock_level(cinode, 0); + cifs_set_oplock_level(cinode, oplock); } static bool diff --git a/fs/cifs/smb2misc.c b/fs/cifs/smb2misc.c index 2fc96f7923ee..7d875a47d022 100644 --- a/fs/cifs/smb2misc.c +++ b/fs/cifs/smb2misc.c @@ -550,7 +550,7 @@ smb2_tcon_has_lease(struct cifs_tcon *tcon, struct smb2_lease_break *rsp) cifs_dbg(FYI, "found in the open list\n"); cifs_dbg(FYI, "lease key match, lease break 0x%x\n", - le32_to_cpu(rsp->NewLeaseState)); + lease_state); if (ack_req) cfile->oplock_break_cancelled = false; @@ -559,17 +559,8 @@ smb2_tcon_has_lease(struct cifs_tcon *tcon, struct smb2_lease_break *rsp) set_bit(CIFS_INODE_PENDING_OPLOCK_BREAK, &cinode->flags); - /* - * Set or clear flags depending on the lease state being READ. - * HANDLE caching flag should be added when the client starts - * to defer closing remote file handles with HANDLE leases. - */ - if (lease_state & SMB2_LEASE_READ_CACHING_HE) - set_bit(CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2, - &cinode->flags); - else - clear_bit(CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2, - &cinode->flags); + cfile->oplock_epoch = le16_to_cpu(rsp->Epoch); + cfile->oplock_level = lease_state; cifs_queue_oplock_break(cfile); return true; @@ -599,7 +590,7 @@ smb2_tcon_find_pending_open_lease(struct cifs_tcon *tcon, cifs_dbg(FYI, "found in the pending open list\n"); cifs_dbg(FYI, "lease key match, lease break 0x%x\n", - le32_to_cpu(rsp->NewLeaseState)); + lease_state); open->oplock = lease_state; } @@ -732,18 +723,9 @@ smb2_is_valid_oplock_break(char *buffer, struct TCP_Server_Info *server) set_bit(CIFS_INODE_PENDING_OPLOCK_BREAK, &cinode->flags); - /* - * Set flag if the server downgrades the oplock - * to L2 else clear. - */ - if (rsp->OplockLevel) - set_bit( - CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2, - &cinode->flags); - else - clear_bit( - CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2, - &cinode->flags); + cfile->oplock_epoch = 0; + cfile->oplock_level = rsp->OplockLevel; + spin_unlock(&cfile->file_info_lock); cifs_queue_oplock_break(cfile); diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index 7ccbfc656478..64ad466695c5 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -1565,35 +1565,32 @@ smb2_ioctl_query_info(const unsigned int xid, if (le32_to_cpu(io_rsp->OutputCount) < qi.input_buffer_length) qi.input_buffer_length = le32_to_cpu(io_rsp->OutputCount); if (qi.input_buffer_length > 0 && - le32_to_cpu(io_rsp->OutputOffset) + qi.input_buffer_length > rsp_iov[1].iov_len) { - rc = -EFAULT; - goto iqinf_exit; - } - if (copy_to_user(&pqi->input_buffer_length, &qi.input_buffer_length, - sizeof(qi.input_buffer_length))) { - rc = -EFAULT; - goto iqinf_exit; - } + le32_to_cpu(io_rsp->OutputOffset) + qi.input_buffer_length + > rsp_iov[1].iov_len) + goto e_fault; + + if (copy_to_user(&pqi->input_buffer_length, + &qi.input_buffer_length, + sizeof(qi.input_buffer_length))) + goto e_fault; + if (copy_to_user((void __user *)pqi + sizeof(struct smb_query_info), (const void *)io_rsp + le32_to_cpu(io_rsp->OutputOffset), - qi.input_buffer_length)) { - rc = -EFAULT; - goto iqinf_exit; - } + qi.input_buffer_length)) + goto e_fault; } else { pqi = (struct smb_query_info __user *)arg; qi_rsp = (struct smb2_query_info_rsp *)rsp_iov[1].iov_base; if (le32_to_cpu(qi_rsp->OutputBufferLength) < qi.input_buffer_length) qi.input_buffer_length = le32_to_cpu(qi_rsp->OutputBufferLength); - if (copy_to_user(&pqi->input_buffer_length, &qi.input_buffer_length, - sizeof(qi.input_buffer_length))) { - rc = -EFAULT; - goto iqinf_exit; - } - if (copy_to_user(pqi + 1, qi_rsp->Buffer, qi.input_buffer_length)) { - rc = -EFAULT; - goto iqinf_exit; - } + if (copy_to_user(&pqi->input_buffer_length, + &qi.input_buffer_length, + sizeof(qi.input_buffer_length))) + goto e_fault; + + if (copy_to_user(pqi + 1, qi_rsp->Buffer, + qi.input_buffer_length)) + goto e_fault; } iqinf_exit: @@ -1609,6 +1606,10 @@ smb2_ioctl_query_info(const unsigned int xid, free_rsp_buf(resp_buftype[1], rsp_iov[1].iov_base); free_rsp_buf(resp_buftype[2], rsp_iov[2].iov_base); return rc; + +e_fault: + rc = -EFAULT; + goto iqinf_exit; } static ssize_t @@ -3331,22 +3332,38 @@ static long smb3_fallocate(struct file *file, struct cifs_tcon *tcon, int mode, static void smb2_downgrade_oplock(struct TCP_Server_Info *server, - struct cifsInodeInfo *cinode, bool set_level2) + struct cifsInodeInfo *cinode, __u32 oplock, + unsigned int epoch, bool *purge_cache) { - if (set_level2) - server->ops->set_oplock_level(cinode, SMB2_OPLOCK_LEVEL_II, - 0, NULL); - else - server->ops->set_oplock_level(cinode, 0, 0, NULL); + server->ops->set_oplock_level(cinode, oplock, 0, NULL); } static void -smb21_downgrade_oplock(struct TCP_Server_Info *server, - struct cifsInodeInfo *cinode, bool set_level2) +smb21_set_oplock_level(struct cifsInodeInfo *cinode, __u32 oplock, + unsigned int epoch, bool *purge_cache); + +static void +smb3_downgrade_oplock(struct TCP_Server_Info *server, + struct cifsInodeInfo *cinode, __u32 oplock, + unsigned int epoch, bool *purge_cache) { - server->ops->set_oplock_level(cinode, - set_level2 ? SMB2_LEASE_READ_CACHING_HE : - 0, 0, NULL); + unsigned int old_state = cinode->oplock; + unsigned int old_epoch = cinode->epoch; + unsigned int new_state; + + if (epoch > old_epoch) { + smb21_set_oplock_level(cinode, oplock, 0, NULL); + cinode->epoch = epoch; + } + + new_state = cinode->oplock; + *purge_cache = false; + + if ((old_state & CIFS_CACHE_READ_FLG) != 0 && + (new_state & CIFS_CACHE_READ_FLG) == 0) + *purge_cache = true; + else if (old_state == new_state && (epoch - old_epoch > 1)) + *purge_cache = true; } static void @@ -4606,7 +4623,7 @@ struct smb_version_operations smb21_operations = { .print_stats = smb2_print_stats, .is_oplock_break = smb2_is_valid_oplock_break, .handle_cancelled_mid = smb2_handle_cancelled_mid, - .downgrade_oplock = smb21_downgrade_oplock, + .downgrade_oplock = smb2_downgrade_oplock, .need_neg = smb2_need_neg, .negotiate = smb2_negotiate, .negotiate_wsize = smb2_negotiate_wsize, @@ -4706,7 +4723,7 @@ struct smb_version_operations smb30_operations = { .dump_share_caps = smb2_dump_share_caps, .is_oplock_break = smb2_is_valid_oplock_break, .handle_cancelled_mid = smb2_handle_cancelled_mid, - .downgrade_oplock = smb21_downgrade_oplock, + .downgrade_oplock = smb3_downgrade_oplock, .need_neg = smb2_need_neg, .negotiate = smb2_negotiate, .negotiate_wsize = smb3_negotiate_wsize, @@ -4814,7 +4831,7 @@ struct smb_version_operations smb311_operations = { .dump_share_caps = smb2_dump_share_caps, .is_oplock_break = smb2_is_valid_oplock_break, .handle_cancelled_mid = smb2_handle_cancelled_mid, - .downgrade_oplock = smb21_downgrade_oplock, + .downgrade_oplock = smb3_downgrade_oplock, .need_neg = smb2_need_neg, .negotiate = smb2_negotiate, .negotiate_wsize = smb3_negotiate_wsize, diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h index 0abfde6d0b05..f264e1d36fe1 100644 --- a/fs/cifs/smb2pdu.h +++ b/fs/cifs/smb2pdu.h @@ -1386,7 +1386,7 @@ struct smb2_oplock_break { struct smb2_lease_break { struct smb2_sync_hdr sync_hdr; __le16 StructureSize; /* Must be 44 */ - __le16 Reserved; + __le16 Epoch; __le32 Flags; __u8 LeaseKey[16]; __le32 CurrentLeaseState; diff --git a/fs/dcache.c b/fs/dcache.c index e88cf0554e65..b2a7f1765f0b 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -903,17 +903,19 @@ struct dentry *dget_parent(struct dentry *dentry) { int gotref; struct dentry *ret; + unsigned seq; /* * Do optimistic parent lookup without any * locking. */ rcu_read_lock(); + seq = raw_seqcount_begin(&dentry->d_seq); ret = READ_ONCE(dentry->d_parent); gotref = lockref_get_not_zero(&ret->d_lockref); rcu_read_unlock(); if (likely(gotref)) { - if (likely(ret == READ_ONCE(dentry->d_parent))) + if (!read_seqcount_retry(&dentry->d_seq, seq)) return ret; dput(ret); } diff --git a/fs/exec.c b/fs/exec.c index d62cd1d71098..de833553ae27 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1007,16 +1007,26 @@ ssize_t read_code(struct file *file, unsigned long addr, loff_t pos, size_t len) } EXPORT_SYMBOL(read_code); +/* + * Maps the mm_struct mm into the current task struct. + * On success, this function returns with the mutex + * exec_update_mutex locked. + */ static int exec_mmap(struct mm_struct *mm) { struct task_struct *tsk; struct mm_struct *old_mm, *active_mm; + int ret; /* Notify parent that we're no longer interested in the old VM */ tsk = current; old_mm = current->mm; exec_mm_release(tsk, old_mm); + ret = mutex_lock_killable(&tsk->signal->exec_update_mutex); + if (ret) + return ret; + if (old_mm) { sync_mm_rss(old_mm); /* @@ -1028,9 +1038,11 @@ static int exec_mmap(struct mm_struct *mm) down_read(&old_mm->mmap_sem); if (unlikely(old_mm->core_state)) { up_read(&old_mm->mmap_sem); + mutex_unlock(&tsk->signal->exec_update_mutex); return -EINTR; } } + task_lock(tsk); active_mm = tsk->active_mm; membarrier_exec_mmap(mm); @@ -1285,11 +1297,12 @@ int flush_old_exec(struct linux_binprm * bprm) goto out; /* - * After clearing bprm->mm (to mark that current is using the - * prepared mm now), we have nothing left of the original + * After setting bprm->called_exec_mmap (to mark that current is + * using the prepared mm now), we have nothing left of the original * process. If anything from here on returns an error, the check * in search_binary_handler() will SEGV current. */ + bprm->called_exec_mmap = 1; bprm->mm = NULL; set_fs(USER_DS); @@ -1423,6 +1436,8 @@ static void free_bprm(struct linux_binprm *bprm) { free_arg_pages(bprm); if (bprm->cred) { + if (bprm->called_exec_mmap) + mutex_unlock(¤t->signal->exec_update_mutex); mutex_unlock(¤t->signal->cred_guard_mutex); abort_creds(bprm->cred); } @@ -1472,6 +1487,7 @@ void install_exec_creds(struct linux_binprm *bprm) * credentials; any time after this it may be unlocked. */ security_bprm_committed_creds(bprm); + mutex_unlock(¤t->signal->exec_update_mutex); mutex_unlock(¤t->signal->cred_guard_mutex); } EXPORT_SYMBOL(install_exec_creds); @@ -1663,7 +1679,7 @@ int search_binary_handler(struct linux_binprm *bprm) read_lock(&binfmt_lock); put_binfmt(fmt); - if (retval < 0 && !bprm->mm) { + if (retval < 0 && bprm->called_exec_mmap) { /* we got to flush_old_exec() and failed after it */ read_unlock(&binfmt_lock); force_sigsegv(SIGSEGV); diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index a284d99a1ee5..95a8a04c77dd 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -5315,7 +5315,7 @@ static int ext4_do_update_inode(handle_t *handle, raw_inode->i_file_acl_high = cpu_to_le16(ei->i_file_acl >> 32); raw_inode->i_file_acl_lo = cpu_to_le32(ei->i_file_acl); - if (ei->i_disksize != ext4_isize(inode->i_sb, raw_inode)) { + if (READ_ONCE(ei->i_disksize) != ext4_isize(inode->i_sb, raw_inode)) { ext4_isize_set(raw_inode, ei->i_disksize); need_datasync = 1; } diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index e1782b2e2e2d..e5d43d2ee474 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -1901,8 +1901,15 @@ void ext4_mb_simple_scan_group(struct ext4_allocation_context *ac, BUG_ON(buddy == NULL); k = mb_find_next_zero_bit(buddy, max, 0); - BUG_ON(k >= max); - + if (k >= max) { + ext4_grp_locked_error(ac->ac_sb, e4b->bd_group, 0, 0, + "%d free clusters of order %d. But found 0", + grp->bb_counters[i], i); + ext4_mark_group_bitmap_corrupted(ac->ac_sb, + e4b->bd_group, + EXT4_GROUP_INFO_BBITMAP_CORRUPT); + break; + } ac->ac_found++; ac->ac_b_ex.fe_len = 1 << i; diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c index e611d768efde..a78aa5480454 100644 --- a/fs/f2fs/gc.c +++ b/fs/f2fs/gc.c @@ -1012,8 +1012,14 @@ static int gc_data_segment(struct f2fs_sb_info *sbi, struct f2fs_summary *sum, block_t start_bidx; nid_t nid = le32_to_cpu(entry->nid); - /* stop BG_GC if there is not enough free sections. */ - if (gc_type == BG_GC && has_not_enough_free_secs(sbi, 0, 0)) + /* + * stop BG_GC if there is not enough free sections. + * Or, stop GC if the segment becomes fully valid caused by + * race condition along with SSR block allocation. + */ + if ((gc_type == BG_GC && has_not_enough_free_secs(sbi, 0, 0)) || + get_valid_blocks(sbi, segno, false) == + sbi->blocks_per_seg) return submitted; if (check_valid_map(sbi, segno, off) == 0) diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index 8a67b933ccd4..ed12e9668184 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -2353,7 +2353,6 @@ static int __f2fs_build_free_nids(struct f2fs_sb_info *sbi, if (ret) { up_read(&nm_i->nat_tree_lock); - f2fs_bug_on(sbi, !mount); f2fs_err(sbi, "NAT is corrupt, run fsck to fix it"); return ret; } diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index 06dd38e76c62..f9022b702875 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -764,7 +764,6 @@ static int fuse_check_page(struct page *page) { if (page_mapcount(page) || page->mapping != NULL || - page_count(page) != 1 || (page->flags & PAGE_FLAGS_CHECK_AT_PREP & ~(1 << PG_locked | 1 << PG_referenced | diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 5dca643a257c..f58ab84b09fb 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -323,6 +323,8 @@ struct inode *fuse_iget(struct super_block *sb, u64 nodeid, int fuse_reverse_inval_inode(struct super_block *sb, u64 nodeid, loff_t offset, loff_t len) { + struct fuse_conn *fc = get_fuse_conn_super(sb); + struct fuse_inode *fi; struct inode *inode; pgoff_t pg_start; pgoff_t pg_end; @@ -331,6 +333,11 @@ int fuse_reverse_inval_inode(struct super_block *sb, u64 nodeid, if (!inode) return -ENOENT; + fi = get_fuse_inode(inode); + spin_lock(&fi->lock); + fi->attr_version = atomic64_inc_return(&fc->attr_version); + spin_unlock(&fi->lock); + fuse_invalidate_attr(inode); forget_all_cached_acls(inode); if (offset >= 0) { diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c index 8466166f22e3..988bb7b17ed8 100644 --- a/fs/gfs2/inode.c +++ b/fs/gfs2/inode.c @@ -712,7 +712,7 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry, error = gfs2_trans_begin(sdp, blocks, 0); if (error) - goto fail_gunlock2; + goto fail_free_inode; if (blocks > 1) { ip->i_eattr = ip->i_no_addr + 1; @@ -723,7 +723,7 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry, error = gfs2_glock_get(sdp, ip->i_no_addr, &gfs2_iopen_glops, CREATE, &io_gl); if (error) - goto fail_gunlock2; + goto fail_free_inode; BUG_ON(test_and_set_bit(GLF_INODE_CREATING, &io_gl->gl_flags)); @@ -732,7 +732,6 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry, goto fail_gunlock2; glock_set_object(ip->i_iopen_gh.gh_gl, ip); - gfs2_glock_put(io_gl); gfs2_set_iop(inode); insert_inode_hash(inode); @@ -765,6 +764,8 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry, mark_inode_dirty(inode); d_instantiate(dentry, inode); + /* After instantiate, errors should result in evict which will destroy + * both inode and iopen glocks properly. */ if (file) { file->f_mode |= FMODE_CREATED; error = finish_open(file, dentry, gfs2_open_common); @@ -772,15 +773,15 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry, gfs2_glock_dq_uninit(ghs); gfs2_glock_dq_uninit(ghs + 1); clear_bit(GLF_INODE_CREATING, &io_gl->gl_flags); + gfs2_glock_put(io_gl); return error; fail_gunlock3: glock_clear_object(io_gl, ip); gfs2_glock_dq_uninit(&ip->i_iopen_gh); - gfs2_glock_put(io_gl); fail_gunlock2: - if (io_gl) - clear_bit(GLF_INODE_CREATING, &io_gl->gl_flags); + clear_bit(GLF_INODE_CREATING, &io_gl->gl_flags); + gfs2_glock_put(io_gl); fail_free_inode: if (ip->i_gl) { glock_clear_object(ip->i_gl, ip); diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index e25901ae3ff4..a30ea7ecb790 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -1040,20 +1040,19 @@ vm_fault_t iomap_page_mkwrite(struct vm_fault *vmf, const struct iomap_ops *ops) lock_page(page); size = i_size_read(inode); - if ((page->mapping != inode->i_mapping) || - (page_offset(page) > size)) { + offset = page_offset(page); + if (page->mapping != inode->i_mapping || offset > size) { /* We overload EFAULT to mean page got truncated */ ret = -EFAULT; goto out_unlock; } /* page is wholly or partially inside EOF */ - if (((page->index + 1) << PAGE_SHIFT) > size) + if (offset > size - PAGE_SIZE) length = offset_in_page(size); else length = PAGE_SIZE; - offset = page_offset(page); while (length > 0) { ret = iomap_apply(inode, offset, length, IOMAP_WRITE | IOMAP_FAULT, ops, page, diff --git a/fs/nfs/nfstrace.h b/fs/nfs/nfstrace.h index 361cc10d6f95..c8081d2b4166 100644 --- a/fs/nfs/nfstrace.h +++ b/fs/nfs/nfstrace.h @@ -1147,7 +1147,12 @@ TRACE_EVENT(nfs_xdr_status, __field(unsigned int, task_id) __field(unsigned int, client_id) __field(u32, xid) + __field(int, version) __field(unsigned long, error) + __string(program, + xdr->rqst->rq_task->tk_client->cl_program->name) + __string(procedure, + xdr->rqst->rq_task->tk_msg.rpc_proc->p_name) ), TP_fast_assign( @@ -1157,13 +1162,19 @@ TRACE_EVENT(nfs_xdr_status, __entry->task_id = task->tk_pid; __entry->client_id = task->tk_client->cl_clid; __entry->xid = be32_to_cpu(rqstp->rq_xid); + __entry->version = task->tk_client->cl_vers; __entry->error = error; + __assign_str(program, + task->tk_client->cl_program->name) + __assign_str(procedure, task->tk_msg.rpc_proc->p_name) ), TP_printk( - "task:%u@%d xid=0x%08x error=%ld (%s)", + "task:%u@%d xid=0x%08x %sv%d %s error=%ld (%s)", __entry->task_id, __entry->client_id, __entry->xid, - -__entry->error, nfs_show_status(__entry->error) + __get_str(program), __entry->version, + __get_str(procedure), -__entry->error, + nfs_show_status(__entry->error) ) ); diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index b736912098ee..f4407dd426bf 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -133,47 +133,70 @@ nfs_async_iocounter_wait(struct rpc_task *task, struct nfs_lock_context *l_ctx) EXPORT_SYMBOL_GPL(nfs_async_iocounter_wait); /* - * nfs_page_group_lock - lock the head of the page group - * @req - request in group that is to be locked + * nfs_page_set_headlock - set the request PG_HEADLOCK + * @req: request that is to be locked * - * this lock must be held when traversing or modifying the page - * group list + * this lock must be held when modifying req->wb_head * * return 0 on success, < 0 on error */ int -nfs_page_group_lock(struct nfs_page *req) +nfs_page_set_headlock(struct nfs_page *req) { - struct nfs_page *head = req->wb_head; - - WARN_ON_ONCE(head != head->wb_head); - - if (!test_and_set_bit(PG_HEADLOCK, &head->wb_flags)) + if (!test_and_set_bit(PG_HEADLOCK, &req->wb_flags)) return 0; - set_bit(PG_CONTENDED1, &head->wb_flags); + set_bit(PG_CONTENDED1, &req->wb_flags); smp_mb__after_atomic(); - return wait_on_bit_lock(&head->wb_flags, PG_HEADLOCK, + return wait_on_bit_lock(&req->wb_flags, PG_HEADLOCK, TASK_UNINTERRUPTIBLE); } /* - * nfs_page_group_unlock - unlock the head of the page group - * @req - request in group that is to be unlocked + * nfs_page_clear_headlock - clear the request PG_HEADLOCK + * @req: request that is to be locked */ void -nfs_page_group_unlock(struct nfs_page *req) +nfs_page_clear_headlock(struct nfs_page *req) { - struct nfs_page *head = req->wb_head; - - WARN_ON_ONCE(head != head->wb_head); - smp_mb__before_atomic(); - clear_bit(PG_HEADLOCK, &head->wb_flags); + clear_bit(PG_HEADLOCK, &req->wb_flags); smp_mb__after_atomic(); - if (!test_bit(PG_CONTENDED1, &head->wb_flags)) + if (!test_bit(PG_CONTENDED1, &req->wb_flags)) return; - wake_up_bit(&head->wb_flags, PG_HEADLOCK); + wake_up_bit(&req->wb_flags, PG_HEADLOCK); +} + +/* + * nfs_page_group_lock - lock the head of the page group + * @req: request in group that is to be locked + * + * this lock must be held when traversing or modifying the page + * group list + * + * return 0 on success, < 0 on error + */ +int +nfs_page_group_lock(struct nfs_page *req) +{ + int ret; + + ret = nfs_page_set_headlock(req); + if (ret || req->wb_head == req) + return ret; + return nfs_page_set_headlock(req->wb_head); +} + +/* + * nfs_page_group_unlock - unlock the head of the page group + * @req: request in group that is to be unlocked + */ +void +nfs_page_group_unlock(struct nfs_page *req) +{ + if (req != req->wb_head) + nfs_page_clear_headlock(req->wb_head); + nfs_page_clear_headlock(req); } /* diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 58c8317dd7d8..613c3ef23e07 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -425,22 +425,28 @@ nfs_destroy_unlinked_subrequests(struct nfs_page *destroy_list, destroy_list = (subreq->wb_this_page == old_head) ? NULL : subreq->wb_this_page; + /* Note: lock subreq in order to change subreq->wb_head */ + nfs_page_set_headlock(subreq); WARN_ON_ONCE(old_head != subreq->wb_head); /* make sure old group is not used */ subreq->wb_this_page = subreq; + subreq->wb_head = subreq; clear_bit(PG_REMOVE, &subreq->wb_flags); /* Note: races with nfs_page_group_destroy() */ if (!kref_read(&subreq->wb_kref)) { /* Check if we raced with nfs_page_group_destroy() */ - if (test_and_clear_bit(PG_TEARDOWN, &subreq->wb_flags)) + if (test_and_clear_bit(PG_TEARDOWN, &subreq->wb_flags)) { + nfs_page_clear_headlock(subreq); nfs_free_request(subreq); + } else + nfs_page_clear_headlock(subreq); continue; } + nfs_page_clear_headlock(subreq); - subreq->wb_head = subreq; nfs_release_request(old_head); if (test_and_clear_bit(PG_INODE_REF, &subreq->wb_flags)) { diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c index 3007b8945d38..51c08ae79063 100644 --- a/fs/nfsd/filecache.c +++ b/fs/nfsd/filecache.c @@ -133,9 +133,13 @@ nfsd_file_mark_find_or_create(struct nfsd_file *nf) struct nfsd_file_mark, nfm_mark)); mutex_unlock(&nfsd_file_fsnotify_group->mark_mutex); - fsnotify_put_mark(mark); - if (likely(nfm)) + if (nfm) { + fsnotify_put_mark(mark); break; + } + /* Avoid soft lockup race with nfsd_file_mark_put() */ + fsnotify_destroy_mark(mark, nfsd_file_fsnotify_group); + fsnotify_put_mark(mark); } else mutex_unlock(&nfsd_file_fsnotify_group->mark_mutex); diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 68cf11660764..8cb2f744dde6 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -495,6 +495,8 @@ find_any_file(struct nfs4_file *f) { struct nfsd_file *ret; + if (!f) + return NULL; spin_lock(&f->fi_lock); ret = __nfs4_get_fd(f, O_RDWR); if (!ret) { @@ -1273,6 +1275,12 @@ static void nfs4_put_stateowner(struct nfs4_stateowner *sop) nfs4_free_stateowner(sop); } +static bool +nfs4_ol_stateid_unhashed(const struct nfs4_ol_stateid *stp) +{ + return list_empty(&stp->st_perfile); +} + static bool unhash_ol_stateid(struct nfs4_ol_stateid *stp) { struct nfs4_file *fp = stp->st_stid.sc_file; @@ -1343,9 +1351,11 @@ static bool unhash_lock_stateid(struct nfs4_ol_stateid *stp) { lockdep_assert_held(&stp->st_stid.sc_client->cl_lock); + if (!unhash_ol_stateid(stp)) + return false; list_del_init(&stp->st_locks); nfs4_unhash_stid(&stp->st_stid); - return unhash_ol_stateid(stp); + return true; } static void release_lock_stateid(struct nfs4_ol_stateid *stp) @@ -1410,13 +1420,12 @@ static void release_open_stateid_locks(struct nfs4_ol_stateid *open_stp, static bool unhash_open_stateid(struct nfs4_ol_stateid *stp, struct list_head *reaplist) { - bool unhashed; - lockdep_assert_held(&stp->st_stid.sc_client->cl_lock); - unhashed = unhash_ol_stateid(stp); + if (!unhash_ol_stateid(stp)) + return false; release_open_stateid_locks(stp, reaplist); - return unhashed; + return true; } static void release_open_stateid(struct nfs4_ol_stateid *stp) @@ -6267,21 +6276,21 @@ alloc_init_lock_stateowner(unsigned int strhashval, struct nfs4_client *clp, } static struct nfs4_ol_stateid * -find_lock_stateid(struct nfs4_lockowner *lo, struct nfs4_file *fp) +find_lock_stateid(const struct nfs4_lockowner *lo, + const struct nfs4_ol_stateid *ost) { struct nfs4_ol_stateid *lst; - struct nfs4_client *clp = lo->lo_owner.so_client; - lockdep_assert_held(&clp->cl_lock); + lockdep_assert_held(&ost->st_stid.sc_client->cl_lock); - list_for_each_entry(lst, &lo->lo_owner.so_stateids, st_perstateowner) { - if (lst->st_stid.sc_type != NFS4_LOCK_STID) - continue; - if (lst->st_stid.sc_file == fp) { - refcount_inc(&lst->st_stid.sc_count); - return lst; + /* If ost is not hashed, ost->st_locks will not be valid */ + if (!nfs4_ol_stateid_unhashed(ost)) + list_for_each_entry(lst, &ost->st_locks, st_locks) { + if (lst->st_stateowner == &lo->lo_owner) { + refcount_inc(&lst->st_stid.sc_count); + return lst; + } } - } return NULL; } @@ -6297,11 +6306,11 @@ init_lock_stateid(struct nfs4_ol_stateid *stp, struct nfs4_lockowner *lo, mutex_lock_nested(&stp->st_mutex, OPEN_STATEID_MUTEX); retry: spin_lock(&clp->cl_lock); - spin_lock(&fp->fi_lock); - retstp = find_lock_stateid(lo, fp); + if (nfs4_ol_stateid_unhashed(open_stp)) + goto out_close; + retstp = find_lock_stateid(lo, open_stp); if (retstp) - goto out_unlock; - + goto out_found; refcount_inc(&stp->st_stid.sc_count); stp->st_stid.sc_type = NFS4_LOCK_STID; stp->st_stateowner = nfs4_get_stateowner(&lo->lo_owner); @@ -6310,22 +6319,26 @@ init_lock_stateid(struct nfs4_ol_stateid *stp, struct nfs4_lockowner *lo, stp->st_access_bmap = 0; stp->st_deny_bmap = open_stp->st_deny_bmap; stp->st_openstp = open_stp; + spin_lock(&fp->fi_lock); list_add(&stp->st_locks, &open_stp->st_locks); list_add(&stp->st_perstateowner, &lo->lo_owner.so_stateids); list_add(&stp->st_perfile, &fp->fi_stateids); -out_unlock: spin_unlock(&fp->fi_lock); spin_unlock(&clp->cl_lock); - if (retstp) { - if (nfsd4_lock_ol_stateid(retstp) != nfs_ok) { - nfs4_put_stid(&retstp->st_stid); - goto retry; - } - /* To keep mutex tracking happy */ - mutex_unlock(&stp->st_mutex); - stp = retstp; - } return stp; +out_found: + spin_unlock(&clp->cl_lock); + if (nfsd4_lock_ol_stateid(retstp) != nfs_ok) { + nfs4_put_stid(&retstp->st_stid); + goto retry; + } + /* To keep mutex tracking happy */ + mutex_unlock(&stp->st_mutex); + return retstp; +out_close: + spin_unlock(&clp->cl_lock); + mutex_unlock(&stp->st_mutex); + return NULL; } static struct nfs4_ol_stateid * @@ -6340,7 +6353,7 @@ find_or_create_lock_stateid(struct nfs4_lockowner *lo, struct nfs4_file *fi, *new = false; spin_lock(&clp->cl_lock); - lst = find_lock_stateid(lo, fi); + lst = find_lock_stateid(lo, ost); spin_unlock(&clp->cl_lock); if (lst != NULL) { if (nfsd4_lock_ol_stateid(lst) == nfs_ok) diff --git a/fs/nfsd/trace.h b/fs/nfsd/trace.h index ffc78a0e28b2..b073bdc2e6e8 100644 --- a/fs/nfsd/trace.h +++ b/fs/nfsd/trace.h @@ -228,7 +228,7 @@ TRACE_EVENT(nfsd_file_acquire, TP_ARGS(rqstp, hash, inode, may_flags, nf, status), TP_STRUCT__entry( - __field(__be32, xid) + __field(u32, xid) __field(unsigned int, hash) __field(void *, inode) __field(unsigned int, may_flags) @@ -236,11 +236,11 @@ TRACE_EVENT(nfsd_file_acquire, __field(unsigned long, nf_flags) __field(unsigned char, nf_may) __field(struct file *, nf_file) - __field(__be32, status) + __field(u32, status) ), TP_fast_assign( - __entry->xid = rqstp->rq_xid; + __entry->xid = be32_to_cpu(rqstp->rq_xid); __entry->hash = hash; __entry->inode = inode; __entry->may_flags = may_flags; @@ -248,15 +248,15 @@ TRACE_EVENT(nfsd_file_acquire, __entry->nf_flags = nf ? nf->nf_flags : 0; __entry->nf_may = nf ? nf->nf_may : 0; __entry->nf_file = nf ? nf->nf_file : NULL; - __entry->status = status; + __entry->status = be32_to_cpu(status); ), TP_printk("xid=0x%x hash=0x%x inode=0x%p may_flags=%s ref=%d nf_flags=%s nf_may=%s nf_file=0x%p status=%u", - be32_to_cpu(__entry->xid), __entry->hash, __entry->inode, + __entry->xid, __entry->hash, __entry->inode, show_nf_may(__entry->may_flags), __entry->nf_ref, show_nf_flags(__entry->nf_flags), show_nf_may(__entry->nf_may), __entry->nf_file, - be32_to_cpu(__entry->status)) + __entry->status) ); DECLARE_EVENT_CLASS(nfsd_file_search_class, diff --git a/fs/proc/base.c b/fs/proc/base.c index ebea9501afb8..529d0c6ec6f9 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -403,11 +403,11 @@ static int proc_pid_wchan(struct seq_file *m, struct pid_namespace *ns, static int lock_trace(struct task_struct *task) { - int err = mutex_lock_killable(&task->signal->cred_guard_mutex); + int err = mutex_lock_killable(&task->signal->exec_update_mutex); if (err) return err; if (!ptrace_may_access(task, PTRACE_MODE_ATTACH_FSCREDS)) { - mutex_unlock(&task->signal->cred_guard_mutex); + mutex_unlock(&task->signal->exec_update_mutex); return -EPERM; } return 0; @@ -415,7 +415,7 @@ static int lock_trace(struct task_struct *task) static void unlock_trace(struct task_struct *task) { - mutex_unlock(&task->signal->cred_guard_mutex); + mutex_unlock(&task->signal->exec_update_mutex); } #ifdef CONFIG_STACKTRACE @@ -2770,7 +2770,7 @@ static int do_io_accounting(struct task_struct *task, struct seq_file *m, int wh unsigned long flags; int result; - result = mutex_lock_killable(&task->signal->cred_guard_mutex); + result = mutex_lock_killable(&task->signal->exec_update_mutex); if (result) return result; @@ -2806,7 +2806,7 @@ static int do_io_accounting(struct task_struct *task, struct seq_file *m, int wh result = 0; out_unlock: - mutex_unlock(&task->signal->cred_guard_mutex); + mutex_unlock(&task->signal->exec_update_mutex); return result; } diff --git a/fs/ubifs/io.c b/fs/ubifs/io.c index 8ceb51478800..7e4bfaf2871f 100644 --- a/fs/ubifs/io.c +++ b/fs/ubifs/io.c @@ -225,7 +225,7 @@ int ubifs_is_mapped(const struct ubifs_info *c, int lnum) int ubifs_check_node(const struct ubifs_info *c, const void *buf, int lnum, int offs, int quiet, int must_chk_crc) { - int err = -EINVAL, type, node_len; + int err = -EINVAL, type, node_len, dump_node = 1; uint32_t crc, node_crc, magic; const struct ubifs_ch *ch = buf; @@ -278,10 +278,22 @@ int ubifs_check_node(const struct ubifs_info *c, const void *buf, int lnum, out_len: if (!quiet) ubifs_err(c, "bad node length %d", node_len); + if (type == UBIFS_DATA_NODE && node_len > UBIFS_DATA_NODE_SZ) + dump_node = 0; out: if (!quiet) { ubifs_err(c, "bad node at LEB %d:%d", lnum, offs); - ubifs_dump_node(c, buf); + if (dump_node) { + ubifs_dump_node(c, buf); + } else { + int safe_len = min3(node_len, c->leb_size - offs, + (int)UBIFS_MAX_DATA_NODE_SZ); + pr_err("\tprevent out-of-bounds memory access\n"); + pr_err("\ttruncated data node length %d\n", safe_len); + pr_err("\tcorrupted data node:\n"); + print_hex_dump(KERN_ERR, "\t", DUMP_PREFIX_OFFSET, 32, 1, + buf, safe_len, 0); + } dump_stack(); } return err; diff --git a/fs/ubifs/journal.c b/fs/ubifs/journal.c index a6ae2428e4c9..5f2ac5ef0891 100644 --- a/fs/ubifs/journal.c +++ b/fs/ubifs/journal.c @@ -906,6 +906,7 @@ int ubifs_jnl_write_inode(struct ubifs_info *c, const struct inode *inode) ubifs_err(c, "dead directory entry '%s', error %d", xent->name, err); ubifs_ro_mode(c, err); + kfree(xent); goto out_release; } ubifs_assert(c, ubifs_inode(xino)->xattr); diff --git a/fs/ubifs/orphan.c b/fs/ubifs/orphan.c index 7dd740e3692d..283f9eb48410 100644 --- a/fs/ubifs/orphan.c +++ b/fs/ubifs/orphan.c @@ -157,7 +157,7 @@ int ubifs_add_orphan(struct ubifs_info *c, ino_t inum) int err = 0; ino_t xattr_inum; union ubifs_key key; - struct ubifs_dent_node *xent; + struct ubifs_dent_node *xent, *pxent = NULL; struct fscrypt_name nm = {0}; struct ubifs_orphan *xattr_orphan; struct ubifs_orphan *orphan; @@ -181,11 +181,16 @@ int ubifs_add_orphan(struct ubifs_info *c, ino_t inum) xattr_inum = le64_to_cpu(xent->inum); xattr_orphan = orphan_add(c, xattr_inum, orphan); - if (IS_ERR(xattr_orphan)) + if (IS_ERR(xattr_orphan)) { + kfree(xent); return PTR_ERR(xattr_orphan); + } + kfree(pxent); + pxent = xent; key_read(c, &xent->key, &key); } + kfree(pxent); return 0; } diff --git a/fs/xfs/libxfs/xfs_attr_leaf.c b/fs/xfs/libxfs/xfs_attr_leaf.c index 5472ed3ce694..de33efc9b4f9 100644 --- a/fs/xfs/libxfs/xfs_attr_leaf.c +++ b/fs/xfs/libxfs/xfs_attr_leaf.c @@ -453,13 +453,15 @@ xfs_attr_copy_value( * special case for dev/uuid inodes, they have fixed size data forks. */ int -xfs_attr_shortform_bytesfit(xfs_inode_t *dp, int bytes) +xfs_attr_shortform_bytesfit( + struct xfs_inode *dp, + int bytes) { - int offset; - int minforkoff; /* lower limit on valid forkoff locations */ - int maxforkoff; /* upper limit on valid forkoff locations */ - int dsize; - xfs_mount_t *mp = dp->i_mount; + struct xfs_mount *mp = dp->i_mount; + int64_t dsize; + int minforkoff; + int maxforkoff; + int offset; /* rounded down */ offset = (XFS_LITINO(mp, dp->i_d.di_version) - bytes) >> 3; @@ -525,7 +527,7 @@ xfs_attr_shortform_bytesfit(xfs_inode_t *dp, int bytes) * A data fork btree root must have space for at least * MINDBTPTRS key/ptr pairs if the data fork is small or empty. */ - minforkoff = max(dsize, XFS_BMDR_SPACE_CALC(MINDBTPTRS)); + minforkoff = max_t(int64_t, dsize, XFS_BMDR_SPACE_CALC(MINDBTPTRS)); minforkoff = roundup(minforkoff, 8) >> 3; /* attr fork btree root can have at least this many key/ptr pairs */ @@ -924,7 +926,7 @@ xfs_attr_shortform_verify( char *endp; struct xfs_ifork *ifp; int i; - int size; + int64_t size; ASSERT(ip->i_d.di_aformat == XFS_DINODE_FMT_LOCAL); ifp = XFS_IFORK_PTR(ip, XFS_ATTR_FORK); @@ -1449,7 +1451,9 @@ xfs_attr3_leaf_add_work( for (i = 0; i < XFS_ATTR_LEAF_MAPSIZE; i++) { if (ichdr->freemap[i].base == tmp) { ichdr->freemap[i].base += sizeof(xfs_attr_leaf_entry_t); - ichdr->freemap[i].size -= sizeof(xfs_attr_leaf_entry_t); + ichdr->freemap[i].size -= + min_t(uint16_t, ichdr->freemap[i].size, + sizeof(xfs_attr_leaf_entry_t)); } } ichdr->usedbytes += xfs_attr_leaf_entsize(leaf, args->index); diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index 19a600443b9e..f8db3fe616df 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -5376,16 +5376,17 @@ __xfs_bunmapi( } div_u64_rem(del.br_startblock, mp->m_sb.sb_rextsize, &mod); if (mod) { + xfs_extlen_t off = mp->m_sb.sb_rextsize - mod; + /* * Realtime extent is lined up at the end but not * at the front. We'll get rid of full extents if * we can. */ - mod = mp->m_sb.sb_rextsize - mod; - if (del.br_blockcount > mod) { - del.br_blockcount -= mod; - del.br_startoff += mod; - del.br_startblock += mod; + if (del.br_blockcount > off) { + del.br_blockcount -= off; + del.br_startoff += off; + del.br_startblock += off; } else if (del.br_startoff == start && (del.br_state == XFS_EXT_UNWRITTEN || tp->t_blk_res == 0)) { @@ -5403,6 +5404,7 @@ __xfs_bunmapi( continue; } else if (del.br_state == XFS_EXT_UNWRITTEN) { struct xfs_bmbt_irec prev; + xfs_fileoff_t unwrite_start; /* * This one is already unwritten. @@ -5416,12 +5418,13 @@ __xfs_bunmapi( ASSERT(!isnullstartblock(prev.br_startblock)); ASSERT(del.br_startblock == prev.br_startblock + prev.br_blockcount); - if (prev.br_startoff < start) { - mod = start - prev.br_startoff; - prev.br_blockcount -= mod; - prev.br_startblock += mod; - prev.br_startoff = start; - } + unwrite_start = max3(start, + del.br_startoff - mod, + prev.br_startoff); + mod = unwrite_start - prev.br_startoff; + prev.br_startoff = unwrite_start; + prev.br_startblock += mod; + prev.br_blockcount -= mod; prev.br_state = XFS_EXT_UNWRITTEN; error = xfs_bmap_add_extent_unwritten_real(tp, ip, whichfork, &icur, &cur, diff --git a/fs/xfs/libxfs/xfs_dir2_node.c b/fs/xfs/libxfs/xfs_dir2_node.c index 705c4f562758..99d5b2ed67f2 100644 --- a/fs/xfs/libxfs/xfs_dir2_node.c +++ b/fs/xfs/libxfs/xfs_dir2_node.c @@ -210,6 +210,7 @@ __xfs_dir3_free_read( if (fa) { xfs_verifier_error(*bpp, -EFSCORRUPTED, fa); xfs_trans_brelse(tp, *bpp); + *bpp = NULL; return -EFSCORRUPTED; } diff --git a/fs/xfs/libxfs/xfs_dir2_sf.c b/fs/xfs/libxfs/xfs_dir2_sf.c index 85f14fc2a8da..ae16ca7c422a 100644 --- a/fs/xfs/libxfs/xfs_dir2_sf.c +++ b/fs/xfs/libxfs/xfs_dir2_sf.c @@ -628,7 +628,7 @@ xfs_dir2_sf_verify( int i; int i8count; int offset; - int size; + int64_t size; int error; uint8_t filetype; diff --git a/fs/xfs/libxfs/xfs_iext_tree.c b/fs/xfs/libxfs/xfs_iext_tree.c index 7bc87408f1a0..52451809c478 100644 --- a/fs/xfs/libxfs/xfs_iext_tree.c +++ b/fs/xfs/libxfs/xfs_iext_tree.c @@ -596,7 +596,7 @@ xfs_iext_realloc_root( struct xfs_ifork *ifp, struct xfs_iext_cursor *cur) { - size_t new_size = ifp->if_bytes + sizeof(struct xfs_iext_rec); + int64_t new_size = ifp->if_bytes + sizeof(struct xfs_iext_rec); void *new; /* account for the prev/next pointers */ diff --git a/fs/xfs/libxfs/xfs_inode_fork.c b/fs/xfs/libxfs/xfs_inode_fork.c index c643beeb5a24..8fdd0424070e 100644 --- a/fs/xfs/libxfs/xfs_inode_fork.c +++ b/fs/xfs/libxfs/xfs_inode_fork.c @@ -129,7 +129,7 @@ xfs_init_local_fork( struct xfs_inode *ip, int whichfork, const void *data, - int size) + int64_t size) { struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork); int mem_size = size, real_size = 0; @@ -467,11 +467,11 @@ xfs_iroot_realloc( void xfs_idata_realloc( struct xfs_inode *ip, - int byte_diff, + int64_t byte_diff, int whichfork) { struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork); - int new_size = (int)ifp->if_bytes + byte_diff; + int64_t new_size = ifp->if_bytes + byte_diff; ASSERT(new_size >= 0); ASSERT(new_size <= XFS_IFORK_SIZE(ip, whichfork)); @@ -552,7 +552,7 @@ xfs_iextents_copy( struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork); struct xfs_iext_cursor icur; struct xfs_bmbt_irec rec; - int copied = 0; + int64_t copied = 0; ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL | XFS_ILOCK_SHARED)); ASSERT(ifp->if_bytes > 0); diff --git a/fs/xfs/libxfs/xfs_inode_fork.h b/fs/xfs/libxfs/xfs_inode_fork.h index 00c62ce170d0..7b845c052fb4 100644 --- a/fs/xfs/libxfs/xfs_inode_fork.h +++ b/fs/xfs/libxfs/xfs_inode_fork.h @@ -13,16 +13,16 @@ struct xfs_dinode; * File incore extent information, present for each of data & attr forks. */ struct xfs_ifork { - int if_bytes; /* bytes in if_u1 */ - unsigned int if_seq; /* fork mod counter */ + int64_t if_bytes; /* bytes in if_u1 */ struct xfs_btree_block *if_broot; /* file's incore btree root */ - short if_broot_bytes; /* bytes allocated for root */ - unsigned char if_flags; /* per-fork flags */ + unsigned int if_seq; /* fork mod counter */ int if_height; /* height of the extent tree */ union { void *if_root; /* extent tree root */ char *if_data; /* inline file data */ } if_u1; + short if_broot_bytes; /* bytes allocated for root */ + unsigned char if_flags; /* per-fork flags */ }; /* @@ -93,12 +93,14 @@ int xfs_iformat_fork(struct xfs_inode *, struct xfs_dinode *); void xfs_iflush_fork(struct xfs_inode *, struct xfs_dinode *, struct xfs_inode_log_item *, int); void xfs_idestroy_fork(struct xfs_inode *, int); -void xfs_idata_realloc(struct xfs_inode *, int, int); +void xfs_idata_realloc(struct xfs_inode *ip, int64_t byte_diff, + int whichfork); void xfs_iroot_realloc(struct xfs_inode *, int, int); int xfs_iread_extents(struct xfs_trans *, struct xfs_inode *, int); int xfs_iextents_copy(struct xfs_inode *, struct xfs_bmbt_rec *, int); -void xfs_init_local_fork(struct xfs_inode *, int, const void *, int); +void xfs_init_local_fork(struct xfs_inode *ip, int whichfork, + const void *data, int64_t size); xfs_extnum_t xfs_iext_count(struct xfs_ifork *ifp); void xfs_iext_insert(struct xfs_inode *, struct xfs_iext_cursor *cur, diff --git a/fs/xfs/libxfs/xfs_trans_resv.c b/fs/xfs/libxfs/xfs_trans_resv.c index d12bbd526e7c..b3584cd2cc16 100644 --- a/fs/xfs/libxfs/xfs_trans_resv.c +++ b/fs/xfs/libxfs/xfs_trans_resv.c @@ -196,6 +196,24 @@ xfs_calc_inode_chunk_res( return res; } +/* + * Per-extent log reservation for the btree changes involved in freeing or + * allocating a realtime extent. We have to be able to log as many rtbitmap + * blocks as needed to mark inuse MAXEXTLEN blocks' worth of realtime extents, + * as well as the realtime summary block. + */ +unsigned int +xfs_rtalloc_log_count( + struct xfs_mount *mp, + unsigned int num_ops) +{ + unsigned int blksz = XFS_FSB_TO_B(mp, 1); + unsigned int rtbmp_bytes; + + rtbmp_bytes = (MAXEXTLEN / mp->m_sb.sb_rextsize) / NBBY; + return (howmany(rtbmp_bytes, blksz) + 1) * num_ops; +} + /* * Various log reservation values. * @@ -218,13 +236,21 @@ xfs_calc_inode_chunk_res( /* * In a write transaction we can allocate a maximum of 2 - * extents. This gives: + * extents. This gives (t1): * the inode getting the new extents: inode size * the inode's bmap btree: max depth * block size * the agfs of the ags from which the extents are allocated: 2 * sector * the superblock free block counter: sector size * the allocation btrees: 2 exts * 2 trees * (2 * max depth - 1) * block size - * And the bmap_finish transaction can free bmap blocks in a join: + * Or, if we're writing to a realtime file (t2): + * the inode getting the new extents: inode size + * the inode's bmap btree: max depth * block size + * the agfs of the ags from which the extents are allocated: 2 * sector + * the superblock free block counter: sector size + * the realtime bitmap: ((MAXEXTLEN / rtextsize) / NBBY) bytes + * the realtime summary: 1 block + * the allocation btrees: 2 trees * (2 * max depth - 1) * block size + * And the bmap_finish transaction can free bmap blocks in a join (t3): * the agfs of the ags containing the blocks: 2 * sector size * the agfls of the ags containing the blocks: 2 * sector size * the super block free block counter: sector size @@ -234,40 +260,72 @@ STATIC uint xfs_calc_write_reservation( struct xfs_mount *mp) { - return XFS_DQUOT_LOGRES(mp) + - max((xfs_calc_inode_res(mp, 1) + + unsigned int t1, t2, t3; + unsigned int blksz = XFS_FSB_TO_B(mp, 1); + + t1 = xfs_calc_inode_res(mp, 1) + + xfs_calc_buf_res(XFS_BM_MAXLEVELS(mp, XFS_DATA_FORK), blksz) + + xfs_calc_buf_res(3, mp->m_sb.sb_sectsize) + + xfs_calc_buf_res(xfs_allocfree_log_count(mp, 2), blksz); + + if (xfs_sb_version_hasrealtime(&mp->m_sb)) { + t2 = xfs_calc_inode_res(mp, 1) + xfs_calc_buf_res(XFS_BM_MAXLEVELS(mp, XFS_DATA_FORK), - XFS_FSB_TO_B(mp, 1)) + + blksz) + xfs_calc_buf_res(3, mp->m_sb.sb_sectsize) + - xfs_calc_buf_res(xfs_allocfree_log_count(mp, 2), - XFS_FSB_TO_B(mp, 1))), - (xfs_calc_buf_res(5, mp->m_sb.sb_sectsize) + - xfs_calc_buf_res(xfs_allocfree_log_count(mp, 2), - XFS_FSB_TO_B(mp, 1)))); + xfs_calc_buf_res(xfs_rtalloc_log_count(mp, 1), blksz) + + xfs_calc_buf_res(xfs_allocfree_log_count(mp, 1), blksz); + } else { + t2 = 0; + } + + t3 = xfs_calc_buf_res(5, mp->m_sb.sb_sectsize) + + xfs_calc_buf_res(xfs_allocfree_log_count(mp, 2), blksz); + + return XFS_DQUOT_LOGRES(mp) + max3(t1, t2, t3); } /* - * In truncating a file we free up to two extents at once. We can modify: + * In truncating a file we free up to two extents at once. We can modify (t1): * the inode being truncated: inode size * the inode's bmap btree: (max depth + 1) * block size - * And the bmap_finish transaction can free the blocks and bmap blocks: + * And the bmap_finish transaction can free the blocks and bmap blocks (t2): * the agf for each of the ags: 4 * sector size * the agfl for each of the ags: 4 * sector size * the super block to reflect the freed blocks: sector size * worst case split in allocation btrees per extent assuming 4 extents: * 4 exts * 2 trees * (2 * max depth - 1) * block size + * Or, if it's a realtime file (t3): + * the agf for each of the ags: 2 * sector size + * the agfl for each of the ags: 2 * sector size + * the super block to reflect the freed blocks: sector size + * the realtime bitmap: 2 exts * ((MAXEXTLEN / rtextsize) / NBBY) bytes + * the realtime summary: 2 exts * 1 block + * worst case split in allocation btrees per extent assuming 2 extents: + * 2 exts * 2 trees * (2 * max depth - 1) * block size */ STATIC uint xfs_calc_itruncate_reservation( struct xfs_mount *mp) { - return XFS_DQUOT_LOGRES(mp) + - max((xfs_calc_inode_res(mp, 1) + - xfs_calc_buf_res(XFS_BM_MAXLEVELS(mp, XFS_DATA_FORK) + 1, - XFS_FSB_TO_B(mp, 1))), - (xfs_calc_buf_res(9, mp->m_sb.sb_sectsize) + - xfs_calc_buf_res(xfs_allocfree_log_count(mp, 4), - XFS_FSB_TO_B(mp, 1)))); + unsigned int t1, t2, t3; + unsigned int blksz = XFS_FSB_TO_B(mp, 1); + + t1 = xfs_calc_inode_res(mp, 1) + + xfs_calc_buf_res(XFS_BM_MAXLEVELS(mp, XFS_DATA_FORK) + 1, blksz); + + t2 = xfs_calc_buf_res(9, mp->m_sb.sb_sectsize) + + xfs_calc_buf_res(xfs_allocfree_log_count(mp, 4), blksz); + + if (xfs_sb_version_hasrealtime(&mp->m_sb)) { + t3 = xfs_calc_buf_res(5, mp->m_sb.sb_sectsize) + + xfs_calc_buf_res(xfs_rtalloc_log_count(mp, 2), blksz) + + xfs_calc_buf_res(xfs_allocfree_log_count(mp, 2), blksz); + } else { + t3 = 0; + } + + return XFS_DQUOT_LOGRES(mp) + max3(t1, t2, t3); } /* diff --git a/fs/xfs/scrub/dir.c b/fs/xfs/scrub/dir.c index 1e2e11721eb9..20eca2d8e7c7 100644 --- a/fs/xfs/scrub/dir.c +++ b/fs/xfs/scrub/dir.c @@ -152,6 +152,9 @@ xchk_dir_actor( xname.type = XFS_DIR3_FT_UNKNOWN; error = xfs_dir_lookup(sdc->sc->tp, ip, &xname, &lookup_ino, NULL); + /* ENOENT means the hash lookup failed and the dir is corrupt */ + if (error == -ENOENT) + error = -EFSCORRUPTED; if (!xchk_fblock_process_error(sdc->sc, XFS_DATA_FORK, offset, &error)) goto out; diff --git a/fs/xfs/scrub/scrub.c b/fs/xfs/scrub/scrub.c index 15c8c5f3f688..720bef577998 100644 --- a/fs/xfs/scrub/scrub.c +++ b/fs/xfs/scrub/scrub.c @@ -167,6 +167,7 @@ xchk_teardown( xfs_irele(sc->ip); sc->ip = NULL; } + sb_end_write(sc->mp->m_super); if (sc->flags & XCHK_REAPING_DISABLED) xchk_start_reaping(sc); if (sc->flags & XCHK_HAS_QUOTAOFFLOCK) { @@ -489,6 +490,14 @@ xfs_scrub_metadata( sc.ops = &meta_scrub_ops[sm->sm_type]; sc.sick_mask = xchk_health_mask_for_scrub_type(sm->sm_type); retry_op: + /* + * If freeze runs concurrently with a scrub, the freeze can be delayed + * indefinitely as we walk the filesystem and iterate over metadata + * buffers. Freeze quiesces the log (which waits for the buffer LRU to + * be emptied) and that won't happen while checking is running. + */ + sb_start_write(mp->m_super); + /* Set up for the operation. */ error = sc.ops->setup(&sc, ip); if (error) diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c index 0c71acc1b831..d6d78e127625 100644 --- a/fs/xfs/xfs_bmap_util.c +++ b/fs/xfs/xfs_bmap_util.c @@ -1039,6 +1039,7 @@ xfs_unmap_extent( goto out_unlock; } +/* Caller must first wait for the completion of any pending DIOs if required. */ int xfs_flush_unmap_range( struct xfs_inode *ip, @@ -1050,9 +1051,6 @@ xfs_flush_unmap_range( xfs_off_t rounding, start, end; int error; - /* wait for the completion of any pending DIOs */ - inode_dio_wait(inode); - rounding = max_t(xfs_off_t, 1 << mp->m_sb.sb_blocklog, PAGE_SIZE); start = round_down(offset, rounding); end = round_up(offset + len, rounding) - 1; @@ -1084,10 +1082,6 @@ xfs_free_file_space( if (len <= 0) /* if nothing being freed */ return 0; - error = xfs_flush_unmap_range(ip, offset, len); - if (error) - return error; - startoffset_fsb = XFS_B_TO_FSB(mp, offset); endoffset_fsb = XFS_B_TO_FSBT(mp, offset + len); diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 1e2176190c86..203065a64765 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -818,6 +818,36 @@ xfs_file_fallocate( if (error) goto out_unlock; + /* + * Must wait for all AIO to complete before we continue as AIO can + * change the file size on completion without holding any locks we + * currently hold. We must do this first because AIO can update both + * the on disk and in memory inode sizes, and the operations that follow + * require the in-memory size to be fully up-to-date. + */ + inode_dio_wait(inode); + + /* + * Now AIO and DIO has drained we flush and (if necessary) invalidate + * the cached range over the first operation we are about to run. + * + * We care about zero and collapse here because they both run a hole + * punch over the range first. Because that can zero data, and the range + * of invalidation for the shift operations is much larger, we still do + * the required flush for collapse in xfs_prepare_shift(). + * + * Insert has the same range requirements as collapse, and we extend the + * file first which can zero data. Hence insert has the same + * flush/invalidate requirements as collapse and so they are both + * handled at the right time by xfs_prepare_shift(). + */ + if (mode & (FALLOC_FL_PUNCH_HOLE | FALLOC_FL_ZERO_RANGE | + FALLOC_FL_COLLAPSE_RANGE)) { + error = xfs_flush_unmap_range(ip, offset, len); + if (error) + goto out_unlock; + } + if (mode & FALLOC_FL_PUNCH_HOLE) { error = xfs_free_file_space(ip, offset, len); if (error) diff --git a/fs/xfs/xfs_fsmap.c b/fs/xfs/xfs_fsmap.c index d082143feb5a..c13754e119be 100644 --- a/fs/xfs/xfs_fsmap.c +++ b/fs/xfs/xfs_fsmap.c @@ -895,6 +895,14 @@ xfs_getfsmap( info.format_arg = arg; info.head = head; + /* + * If fsmap runs concurrently with a scrub, the freeze can be delayed + * indefinitely as we walk the rmapbt and iterate over metadata + * buffers. Freeze quiesces the log (which waits for the buffer LRU to + * be emptied) and that won't happen while we're reading buffers. + */ + sb_start_write(mp->m_super); + /* For each device we support... */ for (i = 0; i < XFS_GETFSMAP_DEVS; i++) { /* Is this device within the range the user asked for? */ @@ -934,6 +942,7 @@ xfs_getfsmap( if (tp) xfs_trans_cancel(tp); + sb_end_write(mp->m_super); head->fmh_oflags = FMH_OF_DEV_T; return error; } diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index c93c4b7328ef..60c452631277 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -622,6 +622,7 @@ xfs_ioc_space( error = xfs_break_layouts(inode, &iolock, BREAK_UNMAP); if (error) goto out_unlock; + inode_dio_wait(inode); switch (bf->l_whence) { case 0: /*SEEK_SET*/ diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c index f4795fdb7389..b32a66452d44 100644 --- a/fs/xfs/xfs_trans.c +++ b/fs/xfs/xfs_trans.c @@ -306,6 +306,11 @@ xfs_trans_alloc( * * Note the zero-length reservation; this transaction MUST be cancelled * without any dirty data. + * + * Callers should obtain freeze protection to avoid two conflicts with fs + * freezing: (1) having active transactions trip the m_active_trans ASSERTs; + * and (2) grabbing buffers at the same time that freeze is trying to drain + * the buffer LRU list. */ int xfs_trans_alloc_empty( diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h index 818691846c90..6fd08cf04add 100644 --- a/include/asm-generic/pgtable.h +++ b/include/asm-generic/pgtable.h @@ -1171,6 +1171,16 @@ static inline bool arch_has_pfn_modify_check(void) #endif #endif +#ifndef p4d_offset_lockless +#define p4d_offset_lockless(pgdp, pgd, address) p4d_offset(&(pgd), address) +#endif +#ifndef pud_offset_lockless +#define pud_offset_lockless(p4dp, p4d, address) pud_offset(&(p4d), address) +#endif +#ifndef pmd_offset_lockless +#define pmd_offset_lockless(pudp, pud, address) pmd_offset(&(pud), address) +#endif + /* * On some architectures it depends on the mm if the p4d/pud or pmd * layer of the page table hierarchy is folded or not. diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h index b40fc633f3be..a345d9fed3d8 100644 --- a/include/linux/binfmts.h +++ b/include/linux/binfmts.h @@ -44,7 +44,13 @@ struct linux_binprm { * exec has happened. Used to sanitize execution environment * and to set AT_SECURE auxv for glibc. */ - secureexec:1; + secureexec:1, + /* + * Set by flush_old_exec, when exec_mmap has been called. + * This is past the point of no return, when the + * exec_update_mutex has been taken. + */ + called_exec_mmap:1; #ifdef __alpha__ unsigned int taso:1; #endif diff --git a/include/linux/debugfs.h b/include/linux/debugfs.h index 58424eb3b329..798f0b9b43ae 100644 --- a/include/linux/debugfs.h +++ b/include/linux/debugfs.h @@ -54,6 +54,8 @@ static const struct file_operations __fops = { \ .llseek = no_llseek, \ } +typedef struct vfsmount *(*debugfs_automount_t)(struct dentry *, void *); + #if defined(CONFIG_DEBUG_FS) struct dentry *debugfs_lookup(const char *name, struct dentry *parent); @@ -75,7 +77,6 @@ struct dentry *debugfs_create_dir(const char *name, struct dentry *parent); struct dentry *debugfs_create_symlink(const char *name, struct dentry *parent, const char *dest); -typedef struct vfsmount *(*debugfs_automount_t)(struct dentry *, void *); struct dentry *debugfs_create_automount(const char *name, struct dentry *parent, debugfs_automount_t f, @@ -203,7 +204,7 @@ static inline struct dentry *debugfs_create_symlink(const char *name, static inline struct dentry *debugfs_create_automount(const char *name, struct dentry *parent, - struct vfsmount *(*f)(void *), + debugfs_automount_t f, void *data) { return ERR_PTR(-ENODEV); diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index 645fd401c856..a60488867dd0 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -369,6 +369,8 @@ void unregister_kretprobes(struct kretprobe **rps, int num); void kprobe_flush_task(struct task_struct *tk); void recycle_rp_inst(struct kretprobe_instance *ri, struct hlist_head *head); +void kprobe_free_init_mem(void); + int disable_kprobe(struct kprobe *kp); int enable_kprobe(struct kprobe *kp); @@ -426,6 +428,9 @@ static inline void unregister_kretprobes(struct kretprobe **rps, int num) static inline void kprobe_flush_task(struct task_struct *tk) { } +static inline void kprobe_free_init_mem(void) +{ +} static inline int disable_kprobe(struct kprobe *kp) { return -ENOSYS; diff --git a/include/linux/libata.h b/include/linux/libata.h index e752368ea351..3c3d8d6b1618 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -486,6 +486,7 @@ enum hsm_task_states { }; enum ata_completion_errors { + AC_ERR_OK = 0, /* no error */ AC_ERR_DEV = (1 << 0), /* device reported error */ AC_ERR_HSM = (1 << 1), /* host state machine violation */ AC_ERR_TIMEOUT = (1 << 2), /* timeout */ @@ -895,9 +896,9 @@ struct ata_port_operations { /* * Command execution */ - int (*qc_defer)(struct ata_queued_cmd *qc); - int (*check_atapi_dma)(struct ata_queued_cmd *qc); - void (*qc_prep)(struct ata_queued_cmd *qc); + int (*qc_defer)(struct ata_queued_cmd *qc); + int (*check_atapi_dma)(struct ata_queued_cmd *qc); + enum ata_completion_errors (*qc_prep)(struct ata_queued_cmd *qc); unsigned int (*qc_issue)(struct ata_queued_cmd *qc); bool (*qc_fill_rtf)(struct ata_queued_cmd *qc); @@ -1165,7 +1166,7 @@ extern int ata_xfer_mode2shift(unsigned long xfer_mode); extern const char *ata_mode_string(unsigned long xfer_mask); extern unsigned long ata_id_xfermask(const u16 *id); extern int ata_std_qc_defer(struct ata_queued_cmd *qc); -extern void ata_noop_qc_prep(struct ata_queued_cmd *qc); +extern enum ata_completion_errors ata_noop_qc_prep(struct ata_queued_cmd *qc); extern void ata_sg_init(struct ata_queued_cmd *qc, struct scatterlist *sg, unsigned int n_elem); extern unsigned int ata_dev_classify(const struct ata_taskfile *tf); @@ -1899,9 +1900,9 @@ extern const struct ata_port_operations ata_bmdma_port_ops; .sg_tablesize = LIBATA_MAX_PRD, \ .dma_boundary = ATA_DMA_BOUNDARY -extern void ata_bmdma_qc_prep(struct ata_queued_cmd *qc); +extern enum ata_completion_errors ata_bmdma_qc_prep(struct ata_queued_cmd *qc); extern unsigned int ata_bmdma_qc_issue(struct ata_queued_cmd *qc); -extern void ata_bmdma_dumb_qc_prep(struct ata_queued_cmd *qc); +extern enum ata_completion_errors ata_bmdma_dumb_qc_prep(struct ata_queued_cmd *qc); extern unsigned int ata_bmdma_port_intr(struct ata_port *ap, struct ata_queued_cmd *qc); extern irqreturn_t ata_bmdma_interrupt(int irq, void *dev_instance); diff --git a/include/linux/mmc/card.h b/include/linux/mmc/card.h index e459b38ef33c..cf3780a6ccc4 100644 --- a/include/linux/mmc/card.h +++ b/include/linux/mmc/card.h @@ -226,7 +226,7 @@ struct mmc_queue_req; * MMC Physical partitions */ struct mmc_part { - unsigned int size; /* partition size (in bytes) */ + u64 size; /* partition size (in bytes) */ unsigned int part_cfg; /* partition type */ char name[MAX_MMC_PART_NAME_LEN]; bool force_ro; /* to make boot parts RO by default */ diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h index 0bbd587fac6a..7e9419d74b86 100644 --- a/include/linux/nfs_page.h +++ b/include/linux/nfs_page.h @@ -142,6 +142,8 @@ extern void nfs_unlock_and_release_request(struct nfs_page *); extern int nfs_page_group_lock(struct nfs_page *); extern void nfs_page_group_unlock(struct nfs_page *); extern bool nfs_page_group_sync_on_bit(struct nfs_page *, unsigned int); +extern int nfs_page_set_headlock(struct nfs_page *req); +extern void nfs_page_clear_headlock(struct nfs_page *req); extern bool nfs_async_iocounter_wait(struct rpc_task *, struct nfs_lock_context *); /* diff --git a/include/linux/pci.h b/include/linux/pci.h index f39f22f9ee47..e92bd9b32f36 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1216,7 +1216,6 @@ int pci_enable_rom(struct pci_dev *pdev); void pci_disable_rom(struct pci_dev *pdev); void __iomem __must_check *pci_map_rom(struct pci_dev *pdev, size_t *size); void pci_unmap_rom(struct pci_dev *pdev, void __iomem *rom); -void __iomem __must_check *pci_platform_rom(struct pci_dev *pdev, size_t *size); /* Power management related routines */ int pci_save_state(struct pci_dev *dev); diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index b5db1ee96d78..65a7355ed07b 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -637,6 +637,7 @@ struct qed_dev_info { #define QED_MFW_VERSION_3_OFFSET 24 u32 flash_size; + bool b_arfs_capable; bool b_inter_pf_switch; bool tx_switching; bool rdma_supported; diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index 88050259c466..a29df79540ce 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -224,7 +224,14 @@ struct signal_struct { struct mutex cred_guard_mutex; /* guard against foreign influences on * credential calculations - * (notably. ptrace) */ + * (notably. ptrace) + * Deprecated do not use in new code. + * Use exec_update_mutex instead. + */ + struct mutex exec_update_mutex; /* Held while task_struct is being + * updated during exec, and may have + * inconsistent permissions. + */ } __randomize_layout; /* diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h index bcf4cf26b8c8..a42a29952889 100644 --- a/include/linux/seqlock.h +++ b/include/linux/seqlock.h @@ -243,6 +243,13 @@ static inline void raw_write_seqcount_end(seqcount_t *s) * usual consistency guarantee. It is one wmb cheaper, because we can * collapse the two back-to-back wmb()s. * + * Note that, writes surrounding the barrier should be declared atomic (e.g. + * via WRITE_ONCE): a) to ensure the writes become visible to other threads + * atomically, avoiding compiler optimizations; b) to document which writes are + * meant to propagate to the reader critical section. This is necessary because + * neither writes before and after the barrier are enclosed in a seq-writer + * critical section that would ensure readers are aware of ongoing writes. + * * seqcount_t seq; * bool X = true, Y = false; * @@ -262,11 +269,11 @@ static inline void raw_write_seqcount_end(seqcount_t *s) * * void write(void) * { - * Y = true; + * WRITE_ONCE(Y, true); * * raw_write_seqcount_barrier(seq); * - * X = false; + * WRITE_ONCE(X, false); * } */ static inline void raw_write_seqcount_barrier(seqcount_t *s) diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index a62889c8bed7..68139cc2f3ca 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1816,6 +1816,18 @@ static inline __u32 skb_queue_len(const struct sk_buff_head *list_) return list_->qlen; } +/** + * skb_queue_len_lockless - get queue length + * @list_: list to measure + * + * Return the length of an &sk_buff queue. + * This variant can be used in lockless contexts. + */ +static inline __u32 skb_queue_len_lockless(const struct sk_buff_head *list_) +{ + return READ_ONCE(list_->qlen); +} + /** * __skb_queue_head_init - initialize non-spinlock portions of sk_buff_head * @list: queue to initialize @@ -2021,7 +2033,7 @@ static inline void __skb_unlink(struct sk_buff *skb, struct sk_buff_head *list) { struct sk_buff *next, *prev; - list->qlen--; + WRITE_ONCE(list->qlen, list->qlen - 1); next = skb->next; prev = skb->prev; skb->next = skb->prev = NULL; diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h index 26f282e5e082..77589ed787f5 100644 --- a/include/linux/sunrpc/svc_rdma.h +++ b/include/linux/sunrpc/svc_rdma.h @@ -154,9 +154,8 @@ struct svc_rdma_send_ctxt { }; /* svc_rdma_backchannel.c */ -extern int svc_rdma_handle_bc_reply(struct rpc_xprt *xprt, - __be32 *rdma_resp, - struct xdr_buf *rcvbuf); +extern void svc_rdma_handle_bc_reply(struct svc_rqst *rqstp, + struct svc_rdma_recv_ctxt *rctxt); /* svc_rdma_recvfrom.c */ extern void svc_rdma_recv_ctxts_destroy(struct svcxprt_rdma *rdma); diff --git a/include/net/sock.h b/include/net/sock.h index 6d9c1131fe5c..e6a48ebb22aa 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -909,11 +909,11 @@ static inline void __sk_add_backlog(struct sock *sk, struct sk_buff *skb) skb_dst_force(skb); if (!sk->sk_backlog.tail) - sk->sk_backlog.head = skb; + WRITE_ONCE(sk->sk_backlog.head, skb); else sk->sk_backlog.tail->next = skb; - sk->sk_backlog.tail = skb; + WRITE_ONCE(sk->sk_backlog.tail, skb); skb->next = NULL; } diff --git a/include/sound/hda_codec.h b/include/sound/hda_codec.h index 9a0393cf024c..65c056ce9112 100644 --- a/include/sound/hda_codec.h +++ b/include/sound/hda_codec.h @@ -494,6 +494,11 @@ void snd_hda_update_power_acct(struct hda_codec *codec); static inline void snd_hda_set_power_save(struct hda_bus *bus, int delay) {} #endif +static inline bool hda_codec_need_resume(struct hda_codec *codec) +{ + return !codec->relaxed_resume && codec->jacktbl.used; +} + #ifdef CONFIG_SND_HDA_PATCH_LOADER /* * patch firmware diff --git a/include/trace/events/sctp.h b/include/trace/events/sctp.h index 7475c7be165a..d4aac3436595 100644 --- a/include/trace/events/sctp.h +++ b/include/trace/events/sctp.h @@ -75,15 +75,6 @@ TRACE_EVENT(sctp_probe, __entry->pathmtu = asoc->pathmtu; __entry->rwnd = asoc->peer.rwnd; __entry->unack_data = asoc->unack_data; - - if (trace_sctp_probe_path_enabled()) { - struct sctp_transport *sp; - - list_for_each_entry(sp, &asoc->peer.transport_addr_list, - transports) { - trace_sctp_probe_path(sp, asoc); - } - } ), TP_printk("asoc=%#llx mark=%#x bind_port=%d peer_port=%d pathmtu=%d " diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h index ffa3c51dbb1a..28df77a948e5 100644 --- a/include/trace/events/sunrpc.h +++ b/include/trace/events/sunrpc.h @@ -165,6 +165,7 @@ DECLARE_EVENT_CLASS(rpc_task_running, DEFINE_RPC_RUNNING_EVENT(begin); DEFINE_RPC_RUNNING_EVENT(run_action); DEFINE_RPC_RUNNING_EVENT(complete); +DEFINE_RPC_RUNNING_EVENT(end); DECLARE_EVENT_CLASS(rpc_task_queued, diff --git a/init/init_task.c b/init/init_task.c index 9e5cbe5eab7b..bd403ed3e418 100644 --- a/init/init_task.c +++ b/init/init_task.c @@ -26,6 +26,7 @@ static struct signal_struct init_signals = { .multiprocess = HLIST_HEAD_INIT, .rlim = INIT_RLIMITS, .cred_guard_mutex = __MUTEX_INITIALIZER(init_signals.cred_guard_mutex), + .exec_update_mutex = __MUTEX_INITIALIZER(init_signals.exec_update_mutex), #ifdef CONFIG_POSIX_TIMERS .posix_timers = LIST_HEAD_INIT(init_signals.posix_timers), .cputimer = { diff --git a/init/main.c b/init/main.c index 8c7d6b8ee6bd..fef9e610b74b 100644 --- a/init/main.c +++ b/init/main.c @@ -32,6 +32,7 @@ #include <linux/nmi.h> #include <linux/percpu.h> #include <linux/kmod.h> +#include <linux/kprobes.h> #include <linux/vmalloc.h> #include <linux/kernel_stat.h> #include <linux/start_kernel.h> @@ -1111,6 +1112,7 @@ static int __ref kernel_init(void *unused) kernel_init_freeable(); /* need to finish all async __init code before freeing the memory */ async_synchronize_full(); + kprobe_free_init_mem(); ftrace_free_init_mem(); free_initmem(); mark_readonly(); diff --git a/kernel/Makefile b/kernel/Makefile index 42557f251fea..f2cc0d118a0b 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -115,6 +115,8 @@ obj-$(CONFIG_TORTURE_TEST) += torture.o obj-$(CONFIG_HAS_IOMEM) += iomem.o obj-$(CONFIG_RSEQ) += rseq.o +obj-$(CONFIG_SYSCTL_KUNIT_TEST) += sysctl-test.o + obj-$(CONFIG_GCC_PLUGIN_STACKLEAK) += stackleak.o KASAN_SANITIZE_stackleak.o := n KCOV_INSTRUMENT_stackleak.o := n diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c index 4508d5e0cf69..8a8fd732ff6d 100644 --- a/kernel/audit_watch.c +++ b/kernel/audit_watch.c @@ -302,8 +302,6 @@ static void audit_update_watch(struct audit_parent *parent, if (oentry->rule.exe) audit_remove_mark(oentry->rule.exe); - audit_watch_log_rule_change(r, owatch, "updated_rules"); - call_rcu(&oentry->rcu, audit_free_rule_rcu); } diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 039d64b1bfb7..728ffec52cf3 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -664,15 +664,7 @@ static void htab_elem_free_rcu(struct rcu_head *head) struct htab_elem *l = container_of(head, struct htab_elem, rcu); struct bpf_htab *htab = l->htab; - /* must increment bpf_prog_active to avoid kprobe+bpf triggering while - * we're calling kfree, otherwise deadlock is possible if kprobes - * are placed somewhere inside of slub - */ - preempt_disable(); - __this_cpu_inc(bpf_prog_active); htab_elem_free(htab, l); - __this_cpu_dec(bpf_prog_active); - preempt_enable(); } static void htab_put_fd_value(struct bpf_htab *htab, struct htab_elem *l) diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c index 218c09ff6a27..375d93eb71c7 100644 --- a/kernel/bpf/inode.c +++ b/kernel/bpf/inode.c @@ -205,10 +205,12 @@ static void *map_seq_next(struct seq_file *m, void *v, loff_t *pos) else prev_key = key; + rcu_read_lock(); if (map->ops->map_get_next_key(map, prev_key, key)) { map_iter(m)->done = true; - return NULL; + key = NULL; } + rcu_read_unlock(); return key; } diff --git a/kernel/events/core.c b/kernel/events/core.c index db1f5aa755f2..47646050efa0 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -1253,7 +1253,7 @@ static void put_ctx(struct perf_event_context *ctx) * function. * * Lock order: - * cred_guard_mutex + * exec_update_mutex * task_struct::perf_event_mutex * perf_event_context::mutex * perf_event::child_mutex; @@ -11002,14 +11002,14 @@ SYSCALL_DEFINE5(perf_event_open, } if (task) { - err = mutex_lock_interruptible(&task->signal->cred_guard_mutex); + err = mutex_lock_interruptible(&task->signal->exec_update_mutex); if (err) goto err_task; /* * Reuse ptrace permission checks for now. * - * We must hold cred_guard_mutex across this and any potential + * We must hold exec_update_mutex across this and any potential * perf_install_in_context() call for this new event to * serialize against exec() altering our credentials (and the * perf_event_exit_task() that could imply). @@ -11298,7 +11298,7 @@ SYSCALL_DEFINE5(perf_event_open, mutex_unlock(&ctx->mutex); if (task) { - mutex_unlock(&task->signal->cred_guard_mutex); + mutex_unlock(&task->signal->exec_update_mutex); put_task_struct(task); } @@ -11334,7 +11334,7 @@ SYSCALL_DEFINE5(perf_event_open, free_event(event); err_cred: if (task) - mutex_unlock(&task->signal->cred_guard_mutex); + mutex_unlock(&task->signal->exec_update_mutex); err_task: if (task) put_task_struct(task); @@ -11639,7 +11639,7 @@ static void perf_event_exit_task_context(struct task_struct *child, int ctxn) /* * When a child task exits, feed back event values to parent events. * - * Can be called with cred_guard_mutex held when called from + * Can be called with exec_update_mutex held when called from * install_exec_creds(). */ void perf_event_exit_task(struct task_struct *child) diff --git a/kernel/fork.c b/kernel/fork.c index 9180f4416dba..594272569a80 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1221,7 +1221,7 @@ struct mm_struct *mm_access(struct task_struct *task, unsigned int mode) struct mm_struct *mm; int err; - err = mutex_lock_killable(&task->signal->cred_guard_mutex); + err = mutex_lock_killable(&task->signal->exec_update_mutex); if (err) return ERR_PTR(err); @@ -1231,7 +1231,7 @@ struct mm_struct *mm_access(struct task_struct *task, unsigned int mode) mmput(mm); mm = ERR_PTR(-EACCES); } - mutex_unlock(&task->signal->cred_guard_mutex); + mutex_unlock(&task->signal->exec_update_mutex); return mm; } @@ -1586,6 +1586,7 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk) sig->oom_score_adj_min = current->signal->oom_score_adj_min; mutex_init(&sig->cred_guard_mutex); + mutex_init(&sig->exec_update_mutex); return 0; } diff --git a/kernel/kcmp.c b/kernel/kcmp.c index a0e3d7a0e8b8..b3ff9288c6cc 100644 --- a/kernel/kcmp.c +++ b/kernel/kcmp.c @@ -173,8 +173,8 @@ SYSCALL_DEFINE5(kcmp, pid_t, pid1, pid_t, pid2, int, type, /* * One should have enough rights to inspect task details. */ - ret = kcmp_lock(&task1->signal->cred_guard_mutex, - &task2->signal->cred_guard_mutex); + ret = kcmp_lock(&task1->signal->exec_update_mutex, + &task2->signal->exec_update_mutex); if (ret) goto err; if (!ptrace_may_access(task1, PTRACE_MODE_READ_REALCREDS) || @@ -229,8 +229,8 @@ SYSCALL_DEFINE5(kcmp, pid_t, pid1, pid_t, pid2, int, type, } err_unlock: - kcmp_unlock(&task1->signal->cred_guard_mutex, - &task2->signal->cred_guard_mutex); + kcmp_unlock(&task1->signal->exec_update_mutex, + &task2->signal->exec_update_mutex); err: put_task_struct(task1); put_task_struct(task2); diff --git a/kernel/kprobes.c b/kernel/kprobes.c index 5646f291eb70..283c8b01ce78 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -1076,9 +1076,20 @@ static int disarm_kprobe_ftrace(struct kprobe *p) ipmodify ? &kprobe_ipmodify_enabled : &kprobe_ftrace_enabled); } #else /* !CONFIG_KPROBES_ON_FTRACE */ -#define prepare_kprobe(p) arch_prepare_kprobe(p) -#define arm_kprobe_ftrace(p) (-ENODEV) -#define disarm_kprobe_ftrace(p) (-ENODEV) +static inline int prepare_kprobe(struct kprobe *p) +{ + return arch_prepare_kprobe(p); +} + +static inline int arm_kprobe_ftrace(struct kprobe *p) +{ + return -ENODEV; +} + +static inline int disarm_kprobe_ftrace(struct kprobe *p) +{ + return -ENODEV; +} #endif /* Arm a kprobe with text_mutex */ @@ -2110,9 +2121,10 @@ static void kill_kprobe(struct kprobe *p) /* * The module is going away. We should disarm the kprobe which - * is using ftrace. + * is using ftrace, because ftrace framework is still available at + * MODULE_STATE_GOING notification. */ - if (kprobe_ftrace(p)) + if (kprobe_ftrace(p) && !kprobe_disabled(p) && !kprobes_all_disarmed) disarm_kprobe_ftrace(p); } @@ -2308,6 +2320,28 @@ static struct notifier_block kprobe_module_nb = { extern unsigned long __start_kprobe_blacklist[]; extern unsigned long __stop_kprobe_blacklist[]; +void kprobe_free_init_mem(void) +{ + void *start = (void *)(&__init_begin); + void *end = (void *)(&__init_end); + struct hlist_head *head; + struct kprobe *p; + int i; + + mutex_lock(&kprobe_mutex); + + /* Kill all kprobes on initmem */ + for (i = 0; i < KPROBE_TABLE_SIZE; i++) { + head = &kprobe_table[i]; + hlist_for_each_entry(p, head, hlist) { + if (start <= (void *)p->addr && (void *)p->addr < end) + kill_kprobe(p); + } + } + + mutex_unlock(&kprobe_mutex); +} + static int __init init_kprobes(void) { int i, err = 0; diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index 9ab1a965c3b9..bca0f7f71cde 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -2302,18 +2302,6 @@ static int check_irq_usage(struct task_struct *curr, struct held_lock *prev, return 0; } -static void inc_chains(void) -{ - if (current->hardirq_context) - nr_hardirq_chains++; - else { - if (current->softirq_context) - nr_softirq_chains++; - else - nr_process_chains++; - } -} - #else static inline int check_irq_usage(struct task_struct *curr, @@ -2321,13 +2309,27 @@ static inline int check_irq_usage(struct task_struct *curr, { return 1; } +#endif /* CONFIG_TRACE_IRQFLAGS */ -static inline void inc_chains(void) +static void inc_chains(int irq_context) { - nr_process_chains++; + if (irq_context & LOCK_CHAIN_HARDIRQ_CONTEXT) + nr_hardirq_chains++; + else if (irq_context & LOCK_CHAIN_SOFTIRQ_CONTEXT) + nr_softirq_chains++; + else + nr_process_chains++; } -#endif /* CONFIG_TRACE_IRQFLAGS */ +static void dec_chains(int irq_context) +{ + if (irq_context & LOCK_CHAIN_HARDIRQ_CONTEXT) + nr_hardirq_chains--; + else if (irq_context & LOCK_CHAIN_SOFTIRQ_CONTEXT) + nr_softirq_chains--; + else + nr_process_chains--; +} static void print_deadlock_scenario(struct held_lock *nxt, struct held_lock *prv) @@ -2847,7 +2849,7 @@ static inline int add_chain_cache(struct task_struct *curr, hlist_add_head_rcu(&chain->entry, hash_head); debug_atomic_inc(chain_lookup_misses); - inc_chains(); + inc_chains(chain->irq_context); return 1; } @@ -3600,7 +3602,8 @@ mark_usage(struct task_struct *curr, struct held_lock *hlock, int check) static inline unsigned int task_irq_context(struct task_struct *task) { - return 2 * !!task->hardirq_context + !!task->softirq_context; + return LOCK_CHAIN_HARDIRQ_CONTEXT * !!task->hardirq_context + + LOCK_CHAIN_SOFTIRQ_CONTEXT * !!task->softirq_context; } static int separate_irq_context(struct task_struct *curr, @@ -4805,6 +4808,8 @@ static void remove_class_from_lock_chain(struct pending_free *pf, return; /* Overwrite the chain key for concurrent RCU readers. */ WRITE_ONCE(chain->chain_key, chain_key); + dec_chains(chain->irq_context); + /* * Note: calling hlist_del_rcu() from inside a * hlist_for_each_entry_rcu() loop is safe. @@ -4826,6 +4831,7 @@ static void remove_class_from_lock_chain(struct pending_free *pf, } *new_chain = *chain; hlist_add_head_rcu(&new_chain->entry, chainhashentry(chain_key)); + inc_chains(new_chain->irq_context); #endif } diff --git a/kernel/locking/lockdep_internals.h b/kernel/locking/lockdep_internals.h index 18d85aebbb57..a525368b8cf6 100644 --- a/kernel/locking/lockdep_internals.h +++ b/kernel/locking/lockdep_internals.h @@ -106,6 +106,12 @@ static const unsigned long LOCKF_USED_IN_IRQ_READ = #define STACK_TRACE_HASH_SIZE 16384 #endif +/* + * Bit definitions for lock_chain.irq_context + */ +#define LOCK_CHAIN_SOFTIRQ_CONTEXT (1 << 0) +#define LOCK_CHAIN_HARDIRQ_CONTEXT (1 << 1) + #define MAX_LOCKDEP_CHAINS (1UL << MAX_LOCKDEP_CHAINS_BITS) #define MAX_LOCKDEP_CHAIN_HLOCKS (MAX_LOCKDEP_CHAINS*5) diff --git a/kernel/notifier.c b/kernel/notifier.c index 157d7c29f720..f6d5ffe4e72e 100644 --- a/kernel/notifier.c +++ b/kernel/notifier.c @@ -23,7 +23,10 @@ static int notifier_chain_register(struct notifier_block **nl, struct notifier_block *n) { while ((*nl) != NULL) { - WARN_ONCE(((*nl) == n), "double register detected"); + if (unlikely((*nl) == n)) { + WARN(1, "double register detected"); + return 0; + } if (n->priority > (*nl)->priority) break; nl = &((*nl)->next); diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index 971197f5d8ee..5569ef6bc183 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -2193,6 +2193,9 @@ static int __init console_setup(char *str) char *s, *options, *brl_options = NULL; int idx; + if (str[0] == 0) + return 1; + if (_braille_console_setup(&str, &brl_options)) return 1; diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 352239c411a4..79ce22de4409 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -4199,7 +4199,8 @@ static inline void sched_submit_work(struct task_struct *tsk) * it wants to wake up a task to maintain concurrency. * As this function is called inside the schedule() context, * we disable preemption to avoid it calling schedule() again - * in the possible wakeup of a kworker. + * in the possible wakeup of a kworker and because wq_worker_sleeping() + * requires it. */ if (tsk->flags & PF_WQ_WORKER) { preempt_disable(); diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 20bf1f66733a..b02a83ff4068 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -4383,16 +4383,16 @@ static inline struct cfs_bandwidth *tg_cfs_bandwidth(struct task_group *tg) } /* returns 0 on failure to allocate runtime */ -static int assign_cfs_rq_runtime(struct cfs_rq *cfs_rq) +static int __assign_cfs_rq_runtime(struct cfs_bandwidth *cfs_b, + struct cfs_rq *cfs_rq, u64 target_runtime) { - struct task_group *tg = cfs_rq->tg; - struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(tg); - u64 amount = 0, min_amount; + u64 min_amount, amount = 0; + + lockdep_assert_held(&cfs_b->lock); /* note: this is a positive sum as runtime_remaining <= 0 */ - min_amount = sched_cfs_bandwidth_slice() - cfs_rq->runtime_remaining; + min_amount = target_runtime - cfs_rq->runtime_remaining; - raw_spin_lock(&cfs_b->lock); if (cfs_b->quota == RUNTIME_INF) amount = min_amount; else { @@ -4404,13 +4404,25 @@ static int assign_cfs_rq_runtime(struct cfs_rq *cfs_rq) cfs_b->idle = 0; } } - raw_spin_unlock(&cfs_b->lock); cfs_rq->runtime_remaining += amount; return cfs_rq->runtime_remaining > 0; } +/* returns 0 on failure to allocate runtime */ +static int assign_cfs_rq_runtime(struct cfs_rq *cfs_rq) +{ + struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg); + int ret; + + raw_spin_lock(&cfs_b->lock); + ret = __assign_cfs_rq_runtime(cfs_b, cfs_rq, sched_cfs_bandwidth_slice()); + raw_spin_unlock(&cfs_b->lock); + + return ret; +} + static void __account_cfs_rq_runtime(struct cfs_rq *cfs_rq, u64 delta_exec) { /* dock delta_exec before expiring quota (as it could span periods) */ @@ -4499,13 +4511,33 @@ static int tg_throttle_down(struct task_group *tg, void *data) return 0; } -static void throttle_cfs_rq(struct cfs_rq *cfs_rq) +static bool throttle_cfs_rq(struct cfs_rq *cfs_rq) { struct rq *rq = rq_of(cfs_rq); struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg); struct sched_entity *se; long task_delta, idle_task_delta, dequeue = 1; - bool empty; + + raw_spin_lock(&cfs_b->lock); + /* This will start the period timer if necessary */ + if (__assign_cfs_rq_runtime(cfs_b, cfs_rq, 1)) { + /* + * We have raced with bandwidth becoming available, and if we + * actually throttled the timer might not unthrottle us for an + * entire period. We additionally needed to make sure that any + * subsequent check_cfs_rq_runtime calls agree not to throttle + * us, as we may commit to do cfs put_prev+pick_next, so we ask + * for 1ns of runtime rather than just check cfs_b. + */ + dequeue = 0; + } else { + list_add_tail_rcu(&cfs_rq->throttled_list, + &cfs_b->throttled_cfs_rq); + } + raw_spin_unlock(&cfs_b->lock); + + if (!dequeue) + return false; /* Throttle no longer required. */ se = cfs_rq->tg->se[cpu_of(rq_of(cfs_rq))]; @@ -4534,29 +4566,13 @@ static void throttle_cfs_rq(struct cfs_rq *cfs_rq) if (!se) sub_nr_running(rq, task_delta); - cfs_rq->throttled = 1; - cfs_rq->throttled_clock = rq_clock(rq); - raw_spin_lock(&cfs_b->lock); - empty = list_empty(&cfs_b->throttled_cfs_rq); - - /* - * Add to the _head_ of the list, so that an already-started - * distribute_cfs_runtime will not see us. If disribute_cfs_runtime is - * not running add to the tail so that later runqueues don't get starved. - */ - if (cfs_b->distribute_running) - list_add_rcu(&cfs_rq->throttled_list, &cfs_b->throttled_cfs_rq); - else - list_add_tail_rcu(&cfs_rq->throttled_list, &cfs_b->throttled_cfs_rq); - /* - * If we're the first throttled task, make sure the bandwidth - * timer is running. + * Note: distribution will already see us throttled via the + * throttled-list. rq->lock protects completion. */ - if (empty) - start_cfs_bandwidth(cfs_b); - - raw_spin_unlock(&cfs_b->lock); + cfs_rq->throttled = 1; + cfs_rq->throttled_clock = rq_clock(rq); + return true; } void unthrottle_cfs_rq(struct cfs_rq *cfs_rq) @@ -4915,8 +4931,7 @@ static bool check_cfs_rq_runtime(struct cfs_rq *cfs_rq) if (cfs_rq_throttled(cfs_rq)) return true; - throttle_cfs_rq(cfs_rq); - return true; + return throttle_cfs_rq(cfs_rq); } static enum hrtimer_restart sched_cfs_slack_timer(struct hrtimer *timer) diff --git a/kernel/sys.c b/kernel/sys.c index a611d1d58c7d..3459a5ce0da0 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -1279,11 +1279,13 @@ SYSCALL_DEFINE1(uname, struct old_utsname __user *, name) SYSCALL_DEFINE1(olduname, struct oldold_utsname __user *, name) { - struct oldold_utsname tmp = {}; + struct oldold_utsname tmp; if (!name) return -EFAULT; + memset(&tmp, 0, sizeof(tmp)); + down_read(&uts_sem); memcpy(&tmp.sysname, &utsname()->sysname, __OLD_UTS_LEN); memcpy(&tmp.nodename, &utsname()->nodename, __OLD_UTS_LEN); diff --git a/kernel/sysctl-test.c b/kernel/sysctl-test.c new file mode 100644 index 000000000000..2a63241a8453 --- /dev/null +++ b/kernel/sysctl-test.c @@ -0,0 +1,392 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * KUnit test of proc sysctl. + */ + +#include <kunit/test.h> +#include <linux/sysctl.h> + +#define KUNIT_PROC_READ 0 +#define KUNIT_PROC_WRITE 1 + +static int i_zero; +static int i_one_hundred = 100; + +/* + * Test that proc_dointvec will not try to use a NULL .data field even when the + * length is non-zero. + */ +static void sysctl_test_api_dointvec_null_tbl_data(struct kunit *test) +{ + struct ctl_table null_data_table = { + .procname = "foo", + /* + * Here we are testing that proc_dointvec behaves correctly when + * we give it a NULL .data field. Normally this would point to a + * piece of memory where the value would be stored. + */ + .data = NULL, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + .extra1 = &i_zero, + .extra2 = &i_one_hundred, + }; + /* + * proc_dointvec expects a buffer in user space, so we allocate one. We + * also need to cast it to __user so sparse doesn't get mad. + */ + void __user *buffer = (void __user *)kunit_kzalloc(test, sizeof(int), + GFP_USER); + size_t len; + loff_t pos; + + /* + * We don't care what the starting length is since proc_dointvec should + * not try to read because .data is NULL. + */ + len = 1234; + KUNIT_EXPECT_EQ(test, 0, proc_dointvec(&null_data_table, + KUNIT_PROC_READ, buffer, &len, + &pos)); + KUNIT_EXPECT_EQ(test, (size_t)0, len); + + /* + * See above. + */ + len = 1234; + KUNIT_EXPECT_EQ(test, 0, proc_dointvec(&null_data_table, + KUNIT_PROC_WRITE, buffer, &len, + &pos)); + KUNIT_EXPECT_EQ(test, (size_t)0, len); +} + +/* + * Similar to the previous test, we create a struct ctrl_table that has a .data + * field that proc_dointvec cannot do anything with; however, this time it is + * because we tell proc_dointvec that the size is 0. + */ +static void sysctl_test_api_dointvec_table_maxlen_unset(struct kunit *test) +{ + int data = 0; + struct ctl_table data_maxlen_unset_table = { + .procname = "foo", + .data = &data, + /* + * So .data is no longer NULL, but we tell proc_dointvec its + * length is 0, so it still shouldn't try to use it. + */ + .maxlen = 0, + .mode = 0644, + .proc_handler = proc_dointvec, + .extra1 = &i_zero, + .extra2 = &i_one_hundred, + }; + void __user *buffer = (void __user *)kunit_kzalloc(test, sizeof(int), + GFP_USER); + size_t len; + loff_t pos; + + /* + * As before, we don't care what buffer length is because proc_dointvec + * cannot do anything because its internal .data buffer has zero length. + */ + len = 1234; + KUNIT_EXPECT_EQ(test, 0, proc_dointvec(&data_maxlen_unset_table, + KUNIT_PROC_READ, buffer, &len, + &pos)); + KUNIT_EXPECT_EQ(test, (size_t)0, len); + + /* + * See previous comment. + */ + len = 1234; + KUNIT_EXPECT_EQ(test, 0, proc_dointvec(&data_maxlen_unset_table, + KUNIT_PROC_WRITE, buffer, &len, + &pos)); + KUNIT_EXPECT_EQ(test, (size_t)0, len); +} + +/* + * Here we provide a valid struct ctl_table, but we try to read and write from + * it using a buffer of zero length, so it should still fail in a similar way as + * before. + */ +static void sysctl_test_api_dointvec_table_len_is_zero(struct kunit *test) +{ + int data = 0; + /* Good table. */ + struct ctl_table table = { + .procname = "foo", + .data = &data, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + .extra1 = &i_zero, + .extra2 = &i_one_hundred, + }; + void __user *buffer = (void __user *)kunit_kzalloc(test, sizeof(int), + GFP_USER); + /* + * However, now our read/write buffer has zero length. + */ + size_t len = 0; + loff_t pos; + + KUNIT_EXPECT_EQ(test, 0, proc_dointvec(&table, KUNIT_PROC_READ, buffer, + &len, &pos)); + KUNIT_EXPECT_EQ(test, (size_t)0, len); + + KUNIT_EXPECT_EQ(test, 0, proc_dointvec(&table, KUNIT_PROC_WRITE, buffer, + &len, &pos)); + KUNIT_EXPECT_EQ(test, (size_t)0, len); +} + +/* + * Test that proc_dointvec refuses to read when the file position is non-zero. + */ +static void sysctl_test_api_dointvec_table_read_but_position_set( + struct kunit *test) +{ + int data = 0; + /* Good table. */ + struct ctl_table table = { + .procname = "foo", + .data = &data, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + .extra1 = &i_zero, + .extra2 = &i_one_hundred, + }; + void __user *buffer = (void __user *)kunit_kzalloc(test, sizeof(int), + GFP_USER); + /* + * We don't care about our buffer length because we start off with a + * non-zero file position. + */ + size_t len = 1234; + /* + * proc_dointvec should refuse to read into the buffer since the file + * pos is non-zero. + */ + loff_t pos = 1; + + KUNIT_EXPECT_EQ(test, 0, proc_dointvec(&table, KUNIT_PROC_READ, buffer, + &len, &pos)); + KUNIT_EXPECT_EQ(test, (size_t)0, len); +} + +/* + * Test that we can read a two digit number in a sufficiently size buffer. + * Nothing fancy. + */ +static void sysctl_test_dointvec_read_happy_single_positive(struct kunit *test) +{ + int data = 0; + /* Good table. */ + struct ctl_table table = { + .procname = "foo", + .data = &data, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + .extra1 = &i_zero, + .extra2 = &i_one_hundred, + }; + size_t len = 4; + loff_t pos = 0; + char *buffer = kunit_kzalloc(test, len, GFP_USER); + char __user *user_buffer = (char __user *)buffer; + /* Store 13 in the data field. */ + *((int *)table.data) = 13; + + KUNIT_EXPECT_EQ(test, 0, proc_dointvec(&table, KUNIT_PROC_READ, + user_buffer, &len, &pos)); + KUNIT_ASSERT_EQ(test, (size_t)3, len); + buffer[len] = '\0'; + /* And we read 13 back out. */ + KUNIT_EXPECT_STREQ(test, "13\n", buffer); +} + +/* + * Same as previous test, just now with negative numbers. + */ +static void sysctl_test_dointvec_read_happy_single_negative(struct kunit *test) +{ + int data = 0; + /* Good table. */ + struct ctl_table table = { + .procname = "foo", + .data = &data, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + .extra1 = &i_zero, + .extra2 = &i_one_hundred, + }; + size_t len = 5; + loff_t pos = 0; + char *buffer = kunit_kzalloc(test, len, GFP_USER); + char __user *user_buffer = (char __user *)buffer; + *((int *)table.data) = -16; + + KUNIT_EXPECT_EQ(test, 0, proc_dointvec(&table, KUNIT_PROC_READ, + user_buffer, &len, &pos)); + KUNIT_ASSERT_EQ(test, (size_t)4, len); + buffer[len] = '\0'; + KUNIT_EXPECT_STREQ(test, "-16\n", (char *)buffer); +} + +/* + * Test that a simple positive write works. + */ +static void sysctl_test_dointvec_write_happy_single_positive(struct kunit *test) +{ + int data = 0; + /* Good table. */ + struct ctl_table table = { + .procname = "foo", + .data = &data, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + .extra1 = &i_zero, + .extra2 = &i_one_hundred, + }; + char input[] = "9"; + size_t len = sizeof(input) - 1; + loff_t pos = 0; + char *buffer = kunit_kzalloc(test, len, GFP_USER); + char __user *user_buffer = (char __user *)buffer; + + memcpy(buffer, input, len); + + KUNIT_EXPECT_EQ(test, 0, proc_dointvec(&table, KUNIT_PROC_WRITE, + user_buffer, &len, &pos)); + KUNIT_EXPECT_EQ(test, sizeof(input) - 1, len); + KUNIT_EXPECT_EQ(test, sizeof(input) - 1, (size_t)pos); + KUNIT_EXPECT_EQ(test, 9, *((int *)table.data)); +} + +/* + * Same as previous test, but now with negative numbers. + */ +static void sysctl_test_dointvec_write_happy_single_negative(struct kunit *test) +{ + int data = 0; + struct ctl_table table = { + .procname = "foo", + .data = &data, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + .extra1 = &i_zero, + .extra2 = &i_one_hundred, + }; + char input[] = "-9"; + size_t len = sizeof(input) - 1; + loff_t pos = 0; + char *buffer = kunit_kzalloc(test, len, GFP_USER); + char __user *user_buffer = (char __user *)buffer; + + memcpy(buffer, input, len); + + KUNIT_EXPECT_EQ(test, 0, proc_dointvec(&table, KUNIT_PROC_WRITE, + user_buffer, &len, &pos)); + KUNIT_EXPECT_EQ(test, sizeof(input) - 1, len); + KUNIT_EXPECT_EQ(test, sizeof(input) - 1, (size_t)pos); + KUNIT_EXPECT_EQ(test, -9, *((int *)table.data)); +} + +/* + * Test that writing a value smaller than the minimum possible value is not + * allowed. + */ +static void sysctl_test_api_dointvec_write_single_less_int_min( + struct kunit *test) +{ + int data = 0; + struct ctl_table table = { + .procname = "foo", + .data = &data, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + .extra1 = &i_zero, + .extra2 = &i_one_hundred, + }; + size_t max_len = 32, len = max_len; + loff_t pos = 0; + char *buffer = kunit_kzalloc(test, max_len, GFP_USER); + char __user *user_buffer = (char __user *)buffer; + unsigned long abs_of_less_than_min = (unsigned long)INT_MAX + - (INT_MAX + INT_MIN) + 1; + + /* + * We use this rigmarole to create a string that contains a value one + * less than the minimum accepted value. + */ + KUNIT_ASSERT_LT(test, + (size_t)snprintf(buffer, max_len, "-%lu", + abs_of_less_than_min), + max_len); + + KUNIT_EXPECT_EQ(test, -EINVAL, proc_dointvec(&table, KUNIT_PROC_WRITE, + user_buffer, &len, &pos)); + KUNIT_EXPECT_EQ(test, max_len, len); + KUNIT_EXPECT_EQ(test, 0, *((int *)table.data)); +} + +/* + * Test that writing the maximum possible value works. + */ +static void sysctl_test_api_dointvec_write_single_greater_int_max( + struct kunit *test) +{ + int data = 0; + struct ctl_table table = { + .procname = "foo", + .data = &data, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + .extra1 = &i_zero, + .extra2 = &i_one_hundred, + }; + size_t max_len = 32, len = max_len; + loff_t pos = 0; + char *buffer = kunit_kzalloc(test, max_len, GFP_USER); + char __user *user_buffer = (char __user *)buffer; + unsigned long greater_than_max = (unsigned long)INT_MAX + 1; + + KUNIT_ASSERT_GT(test, greater_than_max, (unsigned long)INT_MAX); + KUNIT_ASSERT_LT(test, (size_t)snprintf(buffer, max_len, "%lu", + greater_than_max), + max_len); + KUNIT_EXPECT_EQ(test, -EINVAL, proc_dointvec(&table, KUNIT_PROC_WRITE, + user_buffer, &len, &pos)); + KUNIT_ASSERT_EQ(test, max_len, len); + KUNIT_EXPECT_EQ(test, 0, *((int *)table.data)); +} + +static struct kunit_case sysctl_test_cases[] = { + KUNIT_CASE(sysctl_test_api_dointvec_null_tbl_data), + KUNIT_CASE(sysctl_test_api_dointvec_table_maxlen_unset), + KUNIT_CASE(sysctl_test_api_dointvec_table_len_is_zero), + KUNIT_CASE(sysctl_test_api_dointvec_table_read_but_position_set), + KUNIT_CASE(sysctl_test_dointvec_read_happy_single_positive), + KUNIT_CASE(sysctl_test_dointvec_read_happy_single_negative), + KUNIT_CASE(sysctl_test_dointvec_write_happy_single_positive), + KUNIT_CASE(sysctl_test_dointvec_write_happy_single_negative), + KUNIT_CASE(sysctl_test_api_dointvec_write_single_less_int_min), + KUNIT_CASE(sysctl_test_api_dointvec_write_single_greater_int_max), + {} +}; + +static struct kunit_suite sysctl_test_suite = { + .name = "sysctl_test", + .test_cases = sysctl_test_cases, +}; + +kunit_test_suite(sysctl_test_suite); diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index ca69290bee2a..4fc2af4367a7 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -1005,9 +1005,8 @@ static int scale64_check_overflow(u64 mult, u64 div, u64 *base) ((int)sizeof(u64)*8 - fls64(mult) < fls64(rem))) return -EOVERFLOW; tmp *= mult; - rem *= mult; - do_div(rem, div); + rem = div64_u64(rem * mult, div); *base = tmp + rem; return 0; } diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index f9c2bdbbd893..db8162b34ef6 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -3233,6 +3233,9 @@ int trace_array_printk(struct trace_array *tr, if (!(global_trace.trace_flags & TRACE_ITER_PRINTK)) return 0; + if (!tr) + return -ENOENT; + va_start(ap, fmt); ret = trace_array_vprintk(tr, ip, fmt, ap); va_end(ap); @@ -8502,17 +8505,26 @@ static int __remove_instance(struct trace_array *tr) return 0; } -int trace_array_destroy(struct trace_array *tr) +int trace_array_destroy(struct trace_array *this_tr) { + struct trace_array *tr; int ret; - if (!tr) + if (!this_tr) return -EINVAL; mutex_lock(&event_mutex); mutex_lock(&trace_types_lock); - ret = __remove_instance(tr); + ret = -ENODEV; + + /* Making sure trace array exists before destroying it. */ + list_for_each_entry(tr, &ftrace_trace_arrays, list) { + if (tr == this_tr) { + ret = __remove_instance(tr); + break; + } + } mutex_unlock(&trace_types_lock); mutex_unlock(&event_mutex); @@ -9134,7 +9146,7 @@ __init static int tracer_alloc_buffers(void) goto out_free_buffer_mask; /* Only allocate trace_printk buffers if a trace_printk exists */ - if (__stop___trace_bprintk_fmt != __start___trace_bprintk_fmt) + if (&__stop___trace_bprintk_fmt != &__start___trace_bprintk_fmt) /* Must be called before global_trace.buffer is allocated */ trace_printk_init_buffers(); diff --git a/kernel/trace/trace_entries.h b/kernel/trace/trace_entries.h index fc8e97328e54..78c146efb862 100644 --- a/kernel/trace/trace_entries.h +++ b/kernel/trace/trace_entries.h @@ -174,7 +174,7 @@ FTRACE_ENTRY(kernel_stack, stack_entry, F_STRUCT( __field( int, size ) - __dynamic_array(unsigned long, caller ) + __array( unsigned long, caller, FTRACE_STACK_ENTRIES ) ), F_printk("\t=> %ps\n\t=> %ps\n\t=> %ps\n" diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index ed9eb97b64b4..309b2b3c5349 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -793,6 +793,8 @@ int ftrace_set_clr_event(struct trace_array *tr, char *buf, int set) char *event = NULL, *sub = NULL, *match; int ret; + if (!tr) + return -ENOENT; /* * The buf format can be <subsystem>:<event-name> * *:<event-name> means any event by that name. diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index 8107574e8af9..a616b314fb7a 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -4770,7 +4770,6 @@ static int parse_var_defs(struct hist_trigger_data *hist_data) s = kstrdup(field_str, GFP_KERNEL); if (!s) { - kfree(hist_data->attrs->var_defs.name[n_vars]); ret = -ENOMEM; goto free; } diff --git a/kernel/trace/trace_preemptirq.c b/kernel/trace/trace_preemptirq.c index 4d8e99fdbbbe..26b06b09c9f6 100644 --- a/kernel/trace/trace_preemptirq.c +++ b/kernel/trace/trace_preemptirq.c @@ -63,14 +63,14 @@ NOKPROBE_SYMBOL(trace_hardirqs_on_caller); __visible void trace_hardirqs_off_caller(unsigned long caller_addr) { + lockdep_hardirqs_off(CALLER_ADDR0); + if (!this_cpu_read(tracing_irq_cpu)) { this_cpu_write(tracing_irq_cpu, 1); tracer_hardirqs_off(CALLER_ADDR0, caller_addr); if (!in_nmi()) trace_irq_disable_rcuidle(CALLER_ADDR0, caller_addr); } - - lockdep_hardirqs_off(CALLER_ADDR0); } EXPORT_SYMBOL(trace_hardirqs_off_caller); NOKPROBE_SYMBOL(trace_hardirqs_off_caller); diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 1a0c224af6fb..4aa268582a22 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -864,7 +864,8 @@ void wq_worker_running(struct task_struct *task) * @task: task going to sleep * * This function is called from schedule() when a busy worker is - * going to sleep. + * going to sleep. Preemption needs to be disabled to protect ->sleeping + * assignment. */ void wq_worker_sleeping(struct task_struct *task) { @@ -881,7 +882,8 @@ void wq_worker_sleeping(struct task_struct *task) pool = worker->pool; - if (WARN_ON_ONCE(worker->sleeping)) + /* Return if preempted before wq_worker_running() was reached */ + if (worker->sleeping) return; worker->sleeping = 1; diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 6118d99117da..ee00c6c8a373 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -1939,6 +1939,17 @@ config TEST_SYSCTL If unsure, say N. +config SYSCTL_KUNIT_TEST + bool "KUnit test for sysctl" + depends on KUNIT + help + This builds the proc sysctl unit test, which runs on boot. + Tests the API contract and implementation correctness of sysctl. + For more information on KUnit and unit tests in general please refer + to the KUnit documentation in Documentation/dev-tools/kunit/. + + If unsure, say N. + config TEST_UDELAY tristate "udelay test driver" help diff --git a/lib/string.c b/lib/string.c index 08ec58cc673b..abfaa05181e2 100644 --- a/lib/string.c +++ b/lib/string.c @@ -272,6 +272,30 @@ ssize_t strscpy_pad(char *dest, const char *src, size_t count) } EXPORT_SYMBOL(strscpy_pad); +/** + * stpcpy - copy a string from src to dest returning a pointer to the new end + * of dest, including src's %NUL-terminator. May overrun dest. + * @dest: pointer to end of string being copied into. Must be large enough + * to receive copy. + * @src: pointer to the beginning of string being copied from. Must not overlap + * dest. + * + * stpcpy differs from strcpy in a key way: the return value is a pointer + * to the new %NUL-terminating character in @dest. (For strcpy, the return + * value is a pointer to the start of @dest). This interface is considered + * unsafe as it doesn't perform bounds checking of the inputs. As such it's + * not recommended for usage. Instead, its definition is provided in case + * the compiler lowers other libcalls to stpcpy. + */ +char *stpcpy(char *__restrict__ dest, const char *__restrict__ src); +char *stpcpy(char *__restrict__ dest, const char *__restrict__ src) +{ + while ((*dest++ = *src++) != '\0') + /* nothing */; + return --dest; +} +EXPORT_SYMBOL(stpcpy); + #ifndef __HAVE_ARCH_STRCAT /** * strcat - Append one %NUL-terminated string to another diff --git a/mm/filemap.c b/mm/filemap.c index 18c1f5830074..51b2cb5aa503 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2845,6 +2845,14 @@ static struct page *do_read_cache_page(struct address_space *mapping, unlock_page(page); goto out; } + + /* + * A previous I/O error may have been due to temporary + * failures. + * Clear page error before actual read, PG_error will be + * set again if read page fails. + */ + ClearPageError(page); goto filler; out: diff --git a/mm/gup.c b/mm/gup.c index 4a8e969a6e59..3ef769529548 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -2184,13 +2184,13 @@ static int gup_huge_pgd(pgd_t orig, pgd_t *pgdp, unsigned long addr, return 1; } -static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end, +static int gup_pmd_range(pud_t *pudp, pud_t pud, unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { unsigned long next; pmd_t *pmdp; - pmdp = pmd_offset(&pud, addr); + pmdp = pmd_offset_lockless(pudp, pud, addr); do { pmd_t pmd = READ_ONCE(*pmdp); @@ -2227,13 +2227,13 @@ static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end, return 1; } -static int gup_pud_range(p4d_t p4d, unsigned long addr, unsigned long end, +static int gup_pud_range(p4d_t *p4dp, p4d_t p4d, unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { unsigned long next; pud_t *pudp; - pudp = pud_offset(&p4d, addr); + pudp = pud_offset_lockless(p4dp, p4d, addr); do { pud_t pud = READ_ONCE(*pudp); @@ -2248,20 +2248,20 @@ static int gup_pud_range(p4d_t p4d, unsigned long addr, unsigned long end, if (!gup_huge_pd(__hugepd(pud_val(pud)), addr, PUD_SHIFT, next, flags, pages, nr)) return 0; - } else if (!gup_pmd_range(pud, addr, next, flags, pages, nr)) + } else if (!gup_pmd_range(pudp, pud, addr, next, flags, pages, nr)) return 0; } while (pudp++, addr = next, addr != end); return 1; } -static int gup_p4d_range(pgd_t pgd, unsigned long addr, unsigned long end, +static int gup_p4d_range(pgd_t *pgdp, pgd_t pgd, unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { unsigned long next; p4d_t *p4dp; - p4dp = p4d_offset(&pgd, addr); + p4dp = p4d_offset_lockless(pgdp, pgd, addr); do { p4d_t p4d = READ_ONCE(*p4dp); @@ -2273,7 +2273,7 @@ static int gup_p4d_range(pgd_t pgd, unsigned long addr, unsigned long end, if (!gup_huge_pd(__hugepd(p4d_val(p4d)), addr, P4D_SHIFT, next, flags, pages, nr)) return 0; - } else if (!gup_pud_range(p4d, addr, next, flags, pages, nr)) + } else if (!gup_pud_range(p4dp, p4d, addr, next, flags, pages, nr)) return 0; } while (p4dp++, addr = next, addr != end); @@ -2301,7 +2301,7 @@ static void gup_pgd_range(unsigned long addr, unsigned long end, if (!gup_huge_pd(__hugepd(pgd_val(pgd)), addr, PGDIR_SHIFT, next, flags, pages, nr)) return; - } else if (!gup_p4d_range(pgd, addr, next, flags, pages, nr)) + } else if (!gup_p4d_range(pgdp, pgd, addr, next, flags, pages, nr)) return; } while (pgdp++, addr = next, addr != end); } diff --git a/mm/kmemleak.c b/mm/kmemleak.c index 244607663363..312942d78405 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -1947,7 +1947,7 @@ void __init kmemleak_init(void) create_object((unsigned long)__bss_start, __bss_stop - __bss_start, KMEMLEAK_GREY, GFP_ATOMIC); /* only register .data..ro_after_init if not within .data */ - if (__start_ro_after_init < _sdata || __end_ro_after_init > _edata) + if (&__start_ro_after_init < &_sdata || &__end_ro_after_init > &_edata) create_object((unsigned long)__start_ro_after_init, __end_ro_after_init - __start_ro_after_init, KMEMLEAK_GREY, GFP_ATOMIC); diff --git a/mm/madvise.c b/mm/madvise.c index 26f7954865ed..1107e99e498b 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -380,9 +380,9 @@ static int madvise_cold_or_pageout_pte_range(pmd_t *pmd, return 0; } +regular_page: if (pmd_trans_unstable(pmd)) return 0; -regular_page: #endif tlb_change_page_size(tlb, PAGE_SIZE); orig_pte = pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 402c8bc65e08..ca1632850fb7 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -5489,7 +5489,6 @@ static int mem_cgroup_move_account(struct page *page, { struct lruvec *from_vec, *to_vec; struct pglist_data *pgdat; - unsigned long flags; unsigned int nr_pages = compound ? hpage_nr_pages(page) : 1; int ret; bool anon; @@ -5516,18 +5515,13 @@ static int mem_cgroup_move_account(struct page *page, from_vec = mem_cgroup_lruvec(pgdat, from); to_vec = mem_cgroup_lruvec(pgdat, to); - spin_lock_irqsave(&from->move_lock, flags); + lock_page_memcg(page); if (!anon && page_mapped(page)) { __mod_lruvec_state(from_vec, NR_FILE_MAPPED, -nr_pages); __mod_lruvec_state(to_vec, NR_FILE_MAPPED, nr_pages); } - /* - * move_lock grabbed above and caller set from->moving_account, so - * mod_memcg_page_state will serialize updates to PageDirty. - * So mapping should be stable for dirty pages. - */ if (!anon && PageDirty(page)) { struct address_space *mapping = page_mapping(page); @@ -5543,15 +5537,23 @@ static int mem_cgroup_move_account(struct page *page, } /* + * All state has been migrated, let's switch to the new memcg. + * * It is safe to change page->mem_cgroup here because the page - * is referenced, charged, and isolated - we can't race with - * uncharging, charging, migration, or LRU putback. + * is referenced, charged, isolated, and locked: we can't race + * with (un)charging, migration, LRU putback, or anything else + * that would rely on a stable page->mem_cgroup. + * + * Note that lock_page_memcg is a memcg lock, not a page lock, + * to save space. As soon as we switch page->mem_cgroup to a + * new memcg that isn't locked, the above state can change + * concurrently again. Make sure we're truly done with it. */ + smp_mb(); - /* caller should have done css_get */ - page->mem_cgroup = to; + page->mem_cgroup = to; /* caller should have done css_get */ - spin_unlock_irqrestore(&from->move_lock, flags); + __unlock_page_memcg(from); ret = 0; diff --git a/mm/memory.c b/mm/memory.c index cb7c940cf800..2157bb28117a 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -118,6 +118,18 @@ int randomize_va_space __read_mostly = 2; #endif +#ifndef arch_faults_on_old_pte +static inline bool arch_faults_on_old_pte(void) +{ + /* + * Those arches which don't have hw access flag feature need to + * implement their own helper. By default, "true" means pagefault + * will be hit on old pte. + */ + return true; +} +#endif + static int __init disable_randmaps(char *s) { randomize_va_space = 0; @@ -2145,32 +2157,101 @@ static inline int pte_unmap_same(struct mm_struct *mm, pmd_t *pmd, return same; } -static inline void cow_user_page(struct page *dst, struct page *src, unsigned long va, struct vm_area_struct *vma) +static inline bool cow_user_page(struct page *dst, struct page *src, + struct vm_fault *vmf) { + bool ret; + void *kaddr; + void __user *uaddr; + bool locked = false; + struct vm_area_struct *vma = vmf->vma; + struct mm_struct *mm = vma->vm_mm; + unsigned long addr = vmf->address; + debug_dma_assert_idle(src); + if (likely(src)) { + copy_user_highpage(dst, src, addr, vma); + return true; + } + /* * If the source page was a PFN mapping, we don't have * a "struct page" for it. We do a best-effort copy by * just copying from the original user address. If that * fails, we just zero-fill it. Live with it. */ - if (unlikely(!src)) { - void *kaddr = kmap_atomic(dst); - void __user *uaddr = (void __user *)(va & PAGE_MASK); + kaddr = kmap_atomic(dst); + uaddr = (void __user *)(addr & PAGE_MASK); + + /* + * On architectures with software "accessed" bits, we would + * take a double page fault, so mark it accessed here. + */ + if (arch_faults_on_old_pte() && !pte_young(vmf->orig_pte)) { + pte_t entry; + + vmf->pte = pte_offset_map_lock(mm, vmf->pmd, addr, &vmf->ptl); + locked = true; + if (!likely(pte_same(*vmf->pte, vmf->orig_pte))) { + /* + * Other thread has already handled the fault + * and we don't need to do anything. If it's + * not the case, the fault will be triggered + * again on the same address. + */ + ret = false; + goto pte_unlock; + } + + entry = pte_mkyoung(vmf->orig_pte); + if (ptep_set_access_flags(vma, addr, vmf->pte, entry, 0)) + update_mmu_cache(vma, addr, vmf->pte); + } + + /* + * This really shouldn't fail, because the page is there + * in the page tables. But it might just be unreadable, + * in which case we just give up and fill the result with + * zeroes. + */ + if (__copy_from_user_inatomic(kaddr, uaddr, PAGE_SIZE)) { + if (locked) + goto warn; + + /* Re-validate under PTL if the page is still mapped */ + vmf->pte = pte_offset_map_lock(mm, vmf->pmd, addr, &vmf->ptl); + locked = true; + if (!likely(pte_same(*vmf->pte, vmf->orig_pte))) { + /* The PTE changed under us. Retry page fault. */ + ret = false; + goto pte_unlock; + } /* - * This really shouldn't fail, because the page is there - * in the page tables. But it might just be unreadable, - * in which case we just give up and fill the result with - * zeroes. + * The same page can be mapped back since last copy attampt. + * Try to copy again under PTL. */ - if (__copy_from_user_inatomic(kaddr, uaddr, PAGE_SIZE)) + if (__copy_from_user_inatomic(kaddr, uaddr, PAGE_SIZE)) { + /* + * Give a warn in case there can be some obscure + * use-case + */ +warn: + WARN_ON_ONCE(1); clear_page(kaddr); - kunmap_atomic(kaddr); - flush_dcache_page(dst); - } else - copy_user_highpage(dst, src, va, vma); + } + } + + ret = true; + +pte_unlock: + if (locked) + pte_unmap_unlock(vmf->pte, vmf->ptl); + kunmap_atomic(kaddr); + flush_dcache_page(dst); + + return ret; } static gfp_t __get_fault_gfp_mask(struct vm_area_struct *vma) @@ -2342,7 +2423,19 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf) vmf->address); if (!new_page) goto oom; - cow_user_page(new_page, old_page, vmf->address, vma); + + if (!cow_user_page(new_page, old_page, vmf)) { + /* + * COW failed, if the fault was solved by other, + * it's fine. If not, userspace would re-fault on + * the same address and we will handle the fault + * from the second attempt. + */ + put_page(new_page); + if (old_page) + put_page(old_page); + return 0; + } } if (mem_cgroup_try_charge_delay(new_page, mm, GFP_KERNEL, &memcg, false)) diff --git a/mm/mmap.c b/mm/mmap.c index a3584a90c55c..ba78f1f1b1bd 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -2126,6 +2126,7 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr, info.low_limit = mm->mmap_base; info.high_limit = mmap_end; info.align_mask = 0; + info.align_offset = 0; return vm_unmapped_area(&info); } #endif @@ -2167,6 +2168,7 @@ arch_get_unmapped_area_topdown(struct file *filp, unsigned long addr, info.low_limit = max(PAGE_SIZE, mmap_min_addr); info.high_limit = arch_get_mmap_base(addr, mm->mmap_base); info.align_mask = 0; + info.align_offset = 0; addr = vm_unmapped_area(&info); /* diff --git a/mm/pagewalk.c b/mm/pagewalk.c index d48c2a986ea3..4eb09e089881 100644 --- a/mm/pagewalk.c +++ b/mm/pagewalk.c @@ -16,9 +16,9 @@ static int walk_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, err = ops->pte_entry(pte, addr, addr + PAGE_SIZE, walk); if (err) break; - addr += PAGE_SIZE; - if (addr == end) + if (addr >= end - PAGE_SIZE) break; + addr += PAGE_SIZE; pte++; } diff --git a/mm/slub.c b/mm/slub.c index 822ba0724529..d69934eac9e9 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -533,15 +533,32 @@ static void print_section(char *level, char *text, u8 *addr, metadata_access_disable(); } +/* + * See comment in calculate_sizes(). + */ +static inline bool freeptr_outside_object(struct kmem_cache *s) +{ + return s->offset >= s->inuse; +} + +/* + * Return offset of the end of info block which is inuse + free pointer if + * not overlapping with object. + */ +static inline unsigned int get_info_end(struct kmem_cache *s) +{ + if (freeptr_outside_object(s)) + return s->inuse + sizeof(void *); + else + return s->inuse; +} + static struct track *get_track(struct kmem_cache *s, void *object, enum track_item alloc) { struct track *p; - if (s->offset) - p = object + s->offset + sizeof(void *); - else - p = object + s->inuse; + p = object + get_info_end(s); return p + alloc; } @@ -682,10 +699,7 @@ static void print_trailer(struct kmem_cache *s, struct page *page, u8 *p) print_section(KERN_ERR, "Redzone ", p + s->object_size, s->inuse - s->object_size); - if (s->offset) - off = s->offset + sizeof(void *); - else - off = s->inuse; + off = get_info_end(s); if (s->flags & SLAB_STORE_USER) off += 2 * sizeof(struct track); @@ -776,7 +790,7 @@ static int check_bytes_and_report(struct kmem_cache *s, struct page *page, * object address * Bytes of the object to be managed. * If the freepointer may overlay the object then the free - * pointer is the first word of the object. + * pointer is at the middle of the object. * * Poisoning uses 0x6b (POISON_FREE) and the last byte is * 0xa5 (POISON_END) @@ -810,11 +824,7 @@ static int check_bytes_and_report(struct kmem_cache *s, struct page *page, static int check_pad_bytes(struct kmem_cache *s, struct page *page, u8 *p) { - unsigned long off = s->inuse; /* The end of info */ - - if (s->offset) - /* Freepointer is placed after the object. */ - off += sizeof(void *); + unsigned long off = get_info_end(s); /* The end of info */ if (s->flags & SLAB_STORE_USER) /* We also have user information there */ @@ -900,7 +910,7 @@ static int check_object(struct kmem_cache *s, struct page *page, check_pad_bytes(s, page, p); } - if (!s->offset && val == SLUB_RED_ACTIVE) + if (!freeptr_outside_object(s) && val == SLUB_RED_ACTIVE) /* * Object and freepointer overlap. Cannot check * freepointer while object is allocated. @@ -3585,6 +3595,11 @@ static int calculate_sizes(struct kmem_cache *s, int forced_order) * * This is the case if we do RCU, have a constructor or * destructor or are poisoning the objects. + * + * The assumption that s->offset >= s->inuse means free + * pointer is outside of the object is used in the + * freeptr_outside_object() function. If that is no + * longer true, the function needs to be modified. */ s->offset = size; size += sizeof(void *); diff --git a/mm/swap_state.c b/mm/swap_state.c index 4ce014dc4571..7c434fcfff0d 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -511,10 +511,11 @@ static unsigned long swapin_nr_pages(unsigned long offset) return 1; hits = atomic_xchg(&swapin_readahead_hits, 0); - pages = __swapin_nr_pages(prev_offset, offset, hits, max_pages, + pages = __swapin_nr_pages(READ_ONCE(prev_offset), offset, hits, + max_pages, atomic_read(&last_readahead_pages)); if (!hits) - prev_offset = offset; + WRITE_ONCE(prev_offset, offset); atomic_set(&last_readahead_pages, pages); return pages; diff --git a/mm/swapfile.c b/mm/swapfile.c index 891a3ef48651..cf62bdb7b304 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -1038,7 +1038,7 @@ int get_swap_pages(int n_goal, swp_entry_t swp_entries[], int entry_size) goto nextsi; } if (size == SWAPFILE_CLUSTER) { - if (!(si->flags & SWP_FS)) + if (si->flags & SWP_BLKDEV) n_ret = swap_alloc_cluster(si, swp_entries); } else n_ret = scan_swap_map_slots(si, SWAP_HAS_CACHE, @@ -2132,7 +2132,7 @@ int try_to_unuse(unsigned int type, bool frontswap, swp_entry_t entry; unsigned int i; - if (!si->inuse_pages) + if (!READ_ONCE(si->inuse_pages)) return 0; if (!frontswap) @@ -2148,7 +2148,7 @@ int try_to_unuse(unsigned int type, bool frontswap, spin_lock(&mmlist_lock); p = &init_mm.mmlist; - while (si->inuse_pages && + while (READ_ONCE(si->inuse_pages) && !signal_pending(current) && (p = p->next) != &init_mm.mmlist) { @@ -2177,7 +2177,7 @@ int try_to_unuse(unsigned int type, bool frontswap, mmput(prev_mm); i = 0; - while (si->inuse_pages && + while (READ_ONCE(si->inuse_pages) && !signal_pending(current) && (i = find_next_to_unuse(si, i, frontswap)) != 0) { @@ -2219,7 +2219,7 @@ int try_to_unuse(unsigned int type, bool frontswap, * been preempted after get_swap_page(), temporarily hiding that swap. * It's easy and robust (though cpu-intensive) just to keep retrying. */ - if (si->inuse_pages) { + if (READ_ONCE(si->inuse_pages)) { if (!signal_pending(current)) goto retry; retval = -EINTR; @@ -2737,10 +2737,10 @@ static void *swap_next(struct seq_file *swap, void *v, loff_t *pos) else type = si->type + 1; + ++(*pos); for (; (si = swap_type_to_swap_info(type)); type++) { if (!(si->flags & SWP_USED) || !si->swap_map) continue; - ++*pos; return si; } diff --git a/mm/vmscan.c b/mm/vmscan.c index 6db9176d8c63..10feb872d9a4 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -3168,8 +3168,9 @@ static bool allow_direct_reclaim(pg_data_t *pgdat) /* kswapd must be awake if processes are being throttled */ if (!wmark_ok && waitqueue_active(&pgdat->kswapd_wait)) { - pgdat->kswapd_classzone_idx = min(pgdat->kswapd_classzone_idx, - (enum zone_type)ZONE_NORMAL); + if (READ_ONCE(pgdat->kswapd_classzone_idx) > ZONE_NORMAL) + WRITE_ONCE(pgdat->kswapd_classzone_idx, ZONE_NORMAL); + wake_up_interruptible(&pgdat->kswapd_wait); } @@ -3801,9 +3802,9 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx) static enum zone_type kswapd_classzone_idx(pg_data_t *pgdat, enum zone_type prev_classzone_idx) { - if (pgdat->kswapd_classzone_idx == MAX_NR_ZONES) - return prev_classzone_idx; - return pgdat->kswapd_classzone_idx; + enum zone_type curr_idx = READ_ONCE(pgdat->kswapd_classzone_idx); + + return curr_idx == MAX_NR_ZONES ? prev_classzone_idx : curr_idx; } static void kswapd_try_to_sleep(pg_data_t *pgdat, int alloc_order, int reclaim_order, @@ -3847,8 +3848,11 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int alloc_order, int reclaim_o * the previous request that slept prematurely. */ if (remaining) { - pgdat->kswapd_classzone_idx = kswapd_classzone_idx(pgdat, classzone_idx); - pgdat->kswapd_order = max(pgdat->kswapd_order, reclaim_order); + WRITE_ONCE(pgdat->kswapd_classzone_idx, + kswapd_classzone_idx(pgdat, classzone_idx)); + + if (READ_ONCE(pgdat->kswapd_order) < reclaim_order) + WRITE_ONCE(pgdat->kswapd_order, reclaim_order); } finish_wait(&pgdat->kswapd_wait, &wait); @@ -3925,12 +3929,12 @@ static int kswapd(void *p) tsk->flags |= PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD; set_freezable(); - pgdat->kswapd_order = 0; - pgdat->kswapd_classzone_idx = MAX_NR_ZONES; + WRITE_ONCE(pgdat->kswapd_order, 0); + WRITE_ONCE(pgdat->kswapd_classzone_idx, MAX_NR_ZONES); for ( ; ; ) { bool ret; - alloc_order = reclaim_order = pgdat->kswapd_order; + alloc_order = reclaim_order = READ_ONCE(pgdat->kswapd_order); classzone_idx = kswapd_classzone_idx(pgdat, classzone_idx); kswapd_try_sleep: @@ -3938,10 +3942,10 @@ static int kswapd(void *p) classzone_idx); /* Read the new order and classzone_idx */ - alloc_order = reclaim_order = pgdat->kswapd_order; + alloc_order = reclaim_order = READ_ONCE(pgdat->kswapd_order); classzone_idx = kswapd_classzone_idx(pgdat, classzone_idx); - pgdat->kswapd_order = 0; - pgdat->kswapd_classzone_idx = MAX_NR_ZONES; + WRITE_ONCE(pgdat->kswapd_order, 0); + WRITE_ONCE(pgdat->kswapd_classzone_idx, MAX_NR_ZONES); ret = try_to_freeze(); if (kthread_should_stop()) @@ -3985,20 +3989,23 @@ void wakeup_kswapd(struct zone *zone, gfp_t gfp_flags, int order, enum zone_type classzone_idx) { pg_data_t *pgdat; + enum zone_type curr_idx; if (!managed_zone(zone)) return; if (!cpuset_zone_allowed(zone, gfp_flags)) return; + pgdat = zone->zone_pgdat; + curr_idx = READ_ONCE(pgdat->kswapd_classzone_idx); + + if (curr_idx == MAX_NR_ZONES || curr_idx < classzone_idx) + WRITE_ONCE(pgdat->kswapd_classzone_idx, classzone_idx); + + if (READ_ONCE(pgdat->kswapd_order) < order) + WRITE_ONCE(pgdat->kswapd_order, order); - if (pgdat->kswapd_classzone_idx == MAX_NR_ZONES) - pgdat->kswapd_classzone_idx = classzone_idx; - else - pgdat->kswapd_classzone_idx = max(pgdat->kswapd_classzone_idx, - classzone_idx); - pgdat->kswapd_order = max(pgdat->kswapd_order, order); if (!waitqueue_active(&pgdat->kswapd_wait)) return; diff --git a/net/atm/lec.c b/net/atm/lec.c index 5a77c235a212..3625a04a6c70 100644 --- a/net/atm/lec.c +++ b/net/atm/lec.c @@ -1269,6 +1269,12 @@ static void lec_arp_clear_vccs(struct lec_arp_table *entry) entry->vcc = NULL; } if (entry->recv_vcc) { + struct atm_vcc *vcc = entry->recv_vcc; + struct lec_vcc_priv *vpriv = LEC_VCC_PRIV(vcc); + + kfree(vpriv); + vcc->user_back = NULL; + entry->recv_vcc->push = entry->old_recv_push; vcc_release_async(entry->recv_vcc, -EPIPE); entry->recv_vcc = NULL; diff --git a/net/atm/proc.c b/net/atm/proc.c index d79221fd4dae..c31896707313 100644 --- a/net/atm/proc.c +++ b/net/atm/proc.c @@ -134,8 +134,7 @@ static void vcc_seq_stop(struct seq_file *seq, void *v) static void *vcc_seq_next(struct seq_file *seq, void *v, loff_t *pos) { v = vcc_walk(seq, 1); - if (v) - (*pos)++; + (*pos)++; return v; } diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c index 5f6309ade1ea..a6b26ca5c697 100644 --- a/net/batman-adv/bridge_loop_avoidance.c +++ b/net/batman-adv/bridge_loop_avoidance.c @@ -25,6 +25,7 @@ #include <linux/lockdep.h> #include <linux/netdevice.h> #include <linux/netlink.h> +#include <linux/preempt.h> #include <linux/rculist.h> #include <linux/rcupdate.h> #include <linux/seq_file.h> @@ -83,11 +84,12 @@ static inline u32 batadv_choose_claim(const void *data, u32 size) */ static inline u32 batadv_choose_backbone_gw(const void *data, u32 size) { - const struct batadv_bla_claim *claim = (struct batadv_bla_claim *)data; + const struct batadv_bla_backbone_gw *gw; u32 hash = 0; - hash = jhash(&claim->addr, sizeof(claim->addr), hash); - hash = jhash(&claim->vid, sizeof(claim->vid), hash); + gw = (struct batadv_bla_backbone_gw *)data; + hash = jhash(&gw->orig, sizeof(gw->orig), hash); + hash = jhash(&gw->vid, sizeof(gw->vid), hash); return hash % size; } @@ -1579,13 +1581,16 @@ int batadv_bla_init(struct batadv_priv *bat_priv) } /** - * batadv_bla_check_bcast_duplist() - Check if a frame is in the broadcast dup. + * batadv_bla_check_duplist() - Check if a frame is in the broadcast dup. * @bat_priv: the bat priv with all the soft interface information - * @skb: contains the bcast_packet to be checked + * @skb: contains the multicast packet to be checked + * @payload_ptr: pointer to position inside the head buffer of the skb + * marking the start of the data to be CRC'ed + * @orig: originator mac address, NULL if unknown * - * check if it is on our broadcast list. Another gateway might - * have sent the same packet because it is connected to the same backbone, - * so we have to remove this duplicate. + * Check if it is on our broadcast list. Another gateway might have sent the + * same packet because it is connected to the same backbone, so we have to + * remove this duplicate. * * This is performed by checking the CRC, which will tell us * with a good chance that it is the same packet. If it is furthermore @@ -1594,19 +1599,17 @@ int batadv_bla_init(struct batadv_priv *bat_priv) * * Return: true if a packet is in the duplicate list, false otherwise. */ -bool batadv_bla_check_bcast_duplist(struct batadv_priv *bat_priv, - struct sk_buff *skb) +static bool batadv_bla_check_duplist(struct batadv_priv *bat_priv, + struct sk_buff *skb, u8 *payload_ptr, + const u8 *orig) { - int i, curr; - __be32 crc; - struct batadv_bcast_packet *bcast_packet; struct batadv_bcast_duplist_entry *entry; bool ret = false; - - bcast_packet = (struct batadv_bcast_packet *)skb->data; + int i, curr; + __be32 crc; /* calculate the crc ... */ - crc = batadv_skb_crc32(skb, (u8 *)(bcast_packet + 1)); + crc = batadv_skb_crc32(skb, payload_ptr); spin_lock_bh(&bat_priv->bla.bcast_duplist_lock); @@ -1625,8 +1628,21 @@ bool batadv_bla_check_bcast_duplist(struct batadv_priv *bat_priv, if (entry->crc != crc) continue; - if (batadv_compare_eth(entry->orig, bcast_packet->orig)) - continue; + /* are the originators both known and not anonymous? */ + if (orig && !is_zero_ether_addr(orig) && + !is_zero_ether_addr(entry->orig)) { + /* If known, check if the new frame came from + * the same originator: + * We are safe to take identical frames from the + * same orig, if known, as multiplications in + * the mesh are detected via the (orig, seqno) pair. + * So we can be a bit more liberal here and allow + * identical frames from the same orig which the source + * host might have sent multiple times on purpose. + */ + if (batadv_compare_eth(entry->orig, orig)) + continue; + } /* this entry seems to match: same crc, not too old, * and from another gw. therefore return true to forbid it. @@ -1642,7 +1658,14 @@ bool batadv_bla_check_bcast_duplist(struct batadv_priv *bat_priv, entry = &bat_priv->bla.bcast_duplist[curr]; entry->crc = crc; entry->entrytime = jiffies; - ether_addr_copy(entry->orig, bcast_packet->orig); + + /* known originator */ + if (orig) + ether_addr_copy(entry->orig, orig); + /* anonymous originator */ + else + eth_zero_addr(entry->orig); + bat_priv->bla.bcast_duplist_curr = curr; out: @@ -1651,6 +1674,48 @@ bool batadv_bla_check_bcast_duplist(struct batadv_priv *bat_priv, return ret; } +/** + * batadv_bla_check_ucast_duplist() - Check if a frame is in the broadcast dup. + * @bat_priv: the bat priv with all the soft interface information + * @skb: contains the multicast packet to be checked, decapsulated from a + * unicast_packet + * + * Check if it is on our broadcast list. Another gateway might have sent the + * same packet because it is connected to the same backbone, so we have to + * remove this duplicate. + * + * Return: true if a packet is in the duplicate list, false otherwise. + */ +static bool batadv_bla_check_ucast_duplist(struct batadv_priv *bat_priv, + struct sk_buff *skb) +{ + return batadv_bla_check_duplist(bat_priv, skb, (u8 *)skb->data, NULL); +} + +/** + * batadv_bla_check_bcast_duplist() - Check if a frame is in the broadcast dup. + * @bat_priv: the bat priv with all the soft interface information + * @skb: contains the bcast_packet to be checked + * + * Check if it is on our broadcast list. Another gateway might have sent the + * same packet because it is connected to the same backbone, so we have to + * remove this duplicate. + * + * Return: true if a packet is in the duplicate list, false otherwise. + */ +bool batadv_bla_check_bcast_duplist(struct batadv_priv *bat_priv, + struct sk_buff *skb) +{ + struct batadv_bcast_packet *bcast_packet; + u8 *payload_ptr; + + bcast_packet = (struct batadv_bcast_packet *)skb->data; + payload_ptr = (u8 *)(bcast_packet + 1); + + return batadv_bla_check_duplist(bat_priv, skb, payload_ptr, + bcast_packet->orig); +} + /** * batadv_bla_is_backbone_gw_orig() - Check if the originator is a gateway for * the VLAN identified by vid. @@ -1812,7 +1877,7 @@ batadv_bla_loopdetect_check(struct batadv_priv *bat_priv, struct sk_buff *skb, * @bat_priv: the bat priv with all the soft interface information * @skb: the frame to be checked * @vid: the VLAN ID of the frame - * @is_bcast: the packet came in a broadcast packet type. + * @packet_type: the batman packet type this frame came in * * batadv_bla_rx avoidance checks if: * * we have to race for a claim @@ -1824,7 +1889,7 @@ batadv_bla_loopdetect_check(struct batadv_priv *bat_priv, struct sk_buff *skb, * further process the skb. */ bool batadv_bla_rx(struct batadv_priv *bat_priv, struct sk_buff *skb, - unsigned short vid, bool is_bcast) + unsigned short vid, int packet_type) { struct batadv_bla_backbone_gw *backbone_gw; struct ethhdr *ethhdr; @@ -1846,9 +1911,32 @@ bool batadv_bla_rx(struct batadv_priv *bat_priv, struct sk_buff *skb, goto handled; if (unlikely(atomic_read(&bat_priv->bla.num_requests))) - /* don't allow broadcasts while requests are in flight */ - if (is_multicast_ether_addr(ethhdr->h_dest) && is_bcast) - goto handled; + /* don't allow multicast packets while requests are in flight */ + if (is_multicast_ether_addr(ethhdr->h_dest)) + /* Both broadcast flooding or multicast-via-unicasts + * delivery might send to multiple backbone gateways + * sharing the same LAN and therefore need to coordinate + * which backbone gateway forwards into the LAN, + * by claiming the payload source address. + * + * Broadcast flooding and multicast-via-unicasts + * delivery use the following two batman packet types. + * Note: explicitly exclude BATADV_UNICAST_4ADDR, + * as the DHCP gateway feature will send explicitly + * to only one BLA gateway, so the claiming process + * should be avoided there. + */ + if (packet_type == BATADV_BCAST || + packet_type == BATADV_UNICAST) + goto handled; + + /* potential duplicates from foreign BLA backbone gateways via + * multicast-in-unicast packets + */ + if (is_multicast_ether_addr(ethhdr->h_dest) && + packet_type == BATADV_UNICAST && + batadv_bla_check_ucast_duplist(bat_priv, skb)) + goto handled; ether_addr_copy(search_claim.addr, ethhdr->h_source); search_claim.vid = vid; @@ -1883,13 +1971,14 @@ bool batadv_bla_rx(struct batadv_priv *bat_priv, struct sk_buff *skb, goto allow; } - /* if it is a broadcast ... */ - if (is_multicast_ether_addr(ethhdr->h_dest) && is_bcast) { + /* if it is a multicast ... */ + if (is_multicast_ether_addr(ethhdr->h_dest) && + (packet_type == BATADV_BCAST || packet_type == BATADV_UNICAST)) { /* ... drop it. the responsible gateway is in charge. * - * We need to check is_bcast because with the gateway + * We need to check packet type because with the gateway * feature, broadcasts (like DHCP requests) may be sent - * using a unicast packet type. + * using a unicast 4 address packet type. See comment above. */ goto handled; } else { diff --git a/net/batman-adv/bridge_loop_avoidance.h b/net/batman-adv/bridge_loop_avoidance.h index 02b24a861a85..9370be015813 100644 --- a/net/batman-adv/bridge_loop_avoidance.h +++ b/net/batman-adv/bridge_loop_avoidance.h @@ -35,7 +35,7 @@ static inline bool batadv_bla_is_loopdetect_mac(const uint8_t *mac) #ifdef CONFIG_BATMAN_ADV_BLA bool batadv_bla_rx(struct batadv_priv *bat_priv, struct sk_buff *skb, - unsigned short vid, bool is_bcast); + unsigned short vid, int packet_type); bool batadv_bla_tx(struct batadv_priv *bat_priv, struct sk_buff *skb, unsigned short vid); bool batadv_bla_is_backbone_gw(struct sk_buff *skb, @@ -66,7 +66,7 @@ bool batadv_bla_check_claim(struct batadv_priv *bat_priv, u8 *addr, static inline bool batadv_bla_rx(struct batadv_priv *bat_priv, struct sk_buff *skb, unsigned short vid, - bool is_bcast) + int packet_type) { return false; } diff --git a/net/batman-adv/multicast.c b/net/batman-adv/multicast.c index 1d5bdf3a4b65..f5bf931252c4 100644 --- a/net/batman-adv/multicast.c +++ b/net/batman-adv/multicast.c @@ -51,6 +51,7 @@ #include <uapi/linux/batadv_packet.h> #include <uapi/linux/batman_adv.h> +#include "bridge_loop_avoidance.h" #include "hard-interface.h" #include "hash.h" #include "log.h" @@ -1434,6 +1435,35 @@ batadv_mcast_forw_mode(struct batadv_priv *bat_priv, struct sk_buff *skb, return BATADV_FORW_ALL; } +/** + * batadv_mcast_forw_send_orig() - send a multicast packet to an originator + * @bat_priv: the bat priv with all the soft interface information + * @skb: the multicast packet to send + * @vid: the vlan identifier + * @orig_node: the originator to send the packet to + * + * Return: NET_XMIT_DROP in case of error or NET_XMIT_SUCCESS otherwise. + */ +int batadv_mcast_forw_send_orig(struct batadv_priv *bat_priv, + struct sk_buff *skb, + unsigned short vid, + struct batadv_orig_node *orig_node) +{ + /* Avoid sending multicast-in-unicast packets to other BLA + * gateways - they already got the frame from the LAN side + * we share with them. + * TODO: Refactor to take BLA into account earlier, to avoid + * reducing the mcast_fanout count. + */ + if (batadv_bla_is_backbone_gw_orig(bat_priv, orig_node->orig, vid)) { + dev_kfree_skb(skb); + return NET_XMIT_SUCCESS; + } + + return batadv_send_skb_unicast(bat_priv, skb, BATADV_UNICAST, 0, + orig_node, vid); +} + /** * batadv_mcast_forw_tt() - forwards a packet to multicast listeners * @bat_priv: the bat priv with all the soft interface information @@ -1471,8 +1501,8 @@ batadv_mcast_forw_tt(struct batadv_priv *bat_priv, struct sk_buff *skb, break; } - batadv_send_skb_unicast(bat_priv, newskb, BATADV_UNICAST, 0, - orig_entry->orig_node, vid); + batadv_mcast_forw_send_orig(bat_priv, newskb, vid, + orig_entry->orig_node); } rcu_read_unlock(); @@ -1513,8 +1543,7 @@ batadv_mcast_forw_want_all_ipv4(struct batadv_priv *bat_priv, break; } - batadv_send_skb_unicast(bat_priv, newskb, BATADV_UNICAST, 0, - orig_node, vid); + batadv_mcast_forw_send_orig(bat_priv, newskb, vid, orig_node); } rcu_read_unlock(); return ret; @@ -1551,8 +1580,7 @@ batadv_mcast_forw_want_all_ipv6(struct batadv_priv *bat_priv, break; } - batadv_send_skb_unicast(bat_priv, newskb, BATADV_UNICAST, 0, - orig_node, vid); + batadv_mcast_forw_send_orig(bat_priv, newskb, vid, orig_node); } rcu_read_unlock(); return ret; @@ -1618,8 +1646,7 @@ batadv_mcast_forw_want_all_rtr4(struct batadv_priv *bat_priv, break; } - batadv_send_skb_unicast(bat_priv, newskb, BATADV_UNICAST, 0, - orig_node, vid); + batadv_mcast_forw_send_orig(bat_priv, newskb, vid, orig_node); } rcu_read_unlock(); return ret; @@ -1656,8 +1683,7 @@ batadv_mcast_forw_want_all_rtr6(struct batadv_priv *bat_priv, break; } - batadv_send_skb_unicast(bat_priv, newskb, BATADV_UNICAST, 0, - orig_node, vid); + batadv_mcast_forw_send_orig(bat_priv, newskb, vid, orig_node); } rcu_read_unlock(); return ret; diff --git a/net/batman-adv/multicast.h b/net/batman-adv/multicast.h index 5d9e2bb29c97..403929013ac4 100644 --- a/net/batman-adv/multicast.h +++ b/net/batman-adv/multicast.h @@ -46,6 +46,11 @@ enum batadv_forw_mode batadv_mcast_forw_mode(struct batadv_priv *bat_priv, struct sk_buff *skb, struct batadv_orig_node **mcast_single_orig); +int batadv_mcast_forw_send_orig(struct batadv_priv *bat_priv, + struct sk_buff *skb, + unsigned short vid, + struct batadv_orig_node *orig_node); + int batadv_mcast_forw_send(struct batadv_priv *bat_priv, struct sk_buff *skb, unsigned short vid); @@ -71,6 +76,16 @@ batadv_mcast_forw_mode(struct batadv_priv *bat_priv, struct sk_buff *skb, return BATADV_FORW_ALL; } +static inline int +batadv_mcast_forw_send_orig(struct batadv_priv *bat_priv, + struct sk_buff *skb, + unsigned short vid, + struct batadv_orig_node *orig_node) +{ + kfree_skb(skb); + return NET_XMIT_DROP; +} + static inline int batadv_mcast_forw_send(struct batadv_priv *bat_priv, struct sk_buff *skb, unsigned short vid) diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c index f0f864820dea..708e90cb18a6 100644 --- a/net/batman-adv/routing.c +++ b/net/batman-adv/routing.c @@ -826,6 +826,10 @@ static bool batadv_check_unicast_ttvn(struct batadv_priv *bat_priv, vid = batadv_get_vid(skb, hdr_len); ethhdr = (struct ethhdr *)(skb->data + hdr_len); + /* do not reroute multicast frames in a unicast header */ + if (is_multicast_ether_addr(ethhdr->h_dest)) + return true; + /* check if the destination client was served by this node and it is now * roaming. In this case, it means that the node has got a ROAM_ADV * message and that it knows the new destination in the mesh to re-route diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index 5ee8e9a100f9..7f209390069e 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -364,9 +364,8 @@ static netdev_tx_t batadv_interface_tx(struct sk_buff *skb, goto dropped; ret = batadv_send_skb_via_gw(bat_priv, skb, vid); } else if (mcast_single_orig) { - ret = batadv_send_skb_unicast(bat_priv, skb, - BATADV_UNICAST, 0, - mcast_single_orig, vid); + ret = batadv_mcast_forw_send_orig(bat_priv, skb, vid, + mcast_single_orig); } else if (forw_mode == BATADV_FORW_SOME) { ret = batadv_mcast_forw_send(bat_priv, skb, vid); } else { @@ -425,10 +424,10 @@ void batadv_interface_rx(struct net_device *soft_iface, struct vlan_ethhdr *vhdr; struct ethhdr *ethhdr; unsigned short vid; - bool is_bcast; + int packet_type; batadv_bcast_packet = (struct batadv_bcast_packet *)skb->data; - is_bcast = (batadv_bcast_packet->packet_type == BATADV_BCAST); + packet_type = batadv_bcast_packet->packet_type; skb_pull_rcsum(skb, hdr_size); skb_reset_mac_header(skb); @@ -471,7 +470,7 @@ void batadv_interface_rx(struct net_device *soft_iface, /* Let the bridge loop avoidance check the packet. If will * not handle it, we can safely push it up. */ - if (batadv_bla_rx(bat_priv, skb, vid, is_bcast)) + if (batadv_bla_rx(bat_priv, skb, vid, packet_type)) goto out; if (orig_node) diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 7bf6860fed78..fd436e5d7b54 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -41,12 +41,27 @@ /* Handle HCI Event packets */ -static void hci_cc_inquiry_cancel(struct hci_dev *hdev, struct sk_buff *skb) +static void hci_cc_inquiry_cancel(struct hci_dev *hdev, struct sk_buff *skb, + u8 *new_status) { __u8 status = *((__u8 *) skb->data); BT_DBG("%s status 0x%2.2x", hdev->name, status); + /* It is possible that we receive Inquiry Complete event right + * before we receive Inquiry Cancel Command Complete event, in + * which case the latter event should have status of Command + * Disallowed (0x0c). This should not be treated as error, since + * we actually achieve what Inquiry Cancel wants to achieve, + * which is to end the last Inquiry session. + */ + if (status == 0x0c && !test_bit(HCI_INQUIRY, &hdev->flags)) { + bt_dev_warn(hdev, "Ignoring error of Inquiry Cancel command"); + status = 0x00; + } + + *new_status = status; + if (status) return; @@ -3142,7 +3157,7 @@ static void hci_cmd_complete_evt(struct hci_dev *hdev, struct sk_buff *skb, switch (*opcode) { case HCI_OP_INQUIRY_CANCEL: - hci_cc_inquiry_cancel(hdev, skb); + hci_cc_inquiry_cancel(hdev, skb, status); break; case HCI_OP_PERIODIC_INQ: @@ -5853,6 +5868,11 @@ void hci_event_packet(struct hci_dev *hdev, struct sk_buff *skb) u8 status = 0, event = hdr->evt, req_evt = 0; u16 opcode = HCI_OP_NOP; + if (!event) { + bt_dev_warn(hdev, "Received unexpected HCI Event 00000000"); + goto done; + } + if (hdev->sent_cmd && bt_cb(hdev->sent_cmd)->hci.req_event == event) { struct hci_command_hdr *cmd_hdr = (void *) hdev->sent_cmd->data; opcode = __le16_to_cpu(cmd_hdr->opcode); @@ -6064,6 +6084,7 @@ void hci_event_packet(struct hci_dev *hdev, struct sk_buff *skb) req_complete_skb(hdev, status, opcode, orig_skb); } +done: kfree_skb(orig_skb); kfree_skb(skb); hdev->stat.evt_rx++; diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index a845786258a0..12a50e5a9f45 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -419,6 +419,9 @@ static void l2cap_chan_timeout(struct work_struct *work) BT_DBG("chan %p state %s", chan, state_to_string(chan->state)); mutex_lock(&conn->chan_lock); + /* __set_chan_timer() calls l2cap_chan_hold(chan) while scheduling + * this work. No need to call l2cap_chan_hold(chan) here again. + */ l2cap_chan_lock(chan); if (chan->state == BT_CONNECTED || chan->state == BT_CONFIG) @@ -431,12 +434,12 @@ static void l2cap_chan_timeout(struct work_struct *work) l2cap_chan_close(chan, reason); - l2cap_chan_unlock(chan); - chan->ops->close(chan); - mutex_unlock(&conn->chan_lock); + l2cap_chan_unlock(chan); l2cap_chan_put(chan); + + mutex_unlock(&conn->chan_lock); } struct l2cap_chan *l2cap_chan_create(void) @@ -1734,9 +1737,9 @@ static void l2cap_conn_del(struct hci_conn *hcon, int err) l2cap_chan_del(chan, err); - l2cap_chan_unlock(chan); - chan->ops->close(chan); + + l2cap_chan_unlock(chan); l2cap_chan_put(chan); } @@ -4131,7 +4134,8 @@ static inline int l2cap_config_req(struct l2cap_conn *conn, return 0; } - if (chan->state != BT_CONFIG && chan->state != BT_CONNECT2) { + if (chan->state != BT_CONFIG && chan->state != BT_CONNECT2 && + chan->state != BT_CONNECTED) { cmd_reject_invalid_cid(conn, cmd->ident, chan->scid, chan->dcid); goto unlock; @@ -4355,6 +4359,7 @@ static inline int l2cap_disconnect_req(struct l2cap_conn *conn, return 0; } + l2cap_chan_hold(chan); l2cap_chan_lock(chan); rsp.dcid = cpu_to_le16(chan->scid); @@ -4363,12 +4368,11 @@ static inline int l2cap_disconnect_req(struct l2cap_conn *conn, chan->ops->set_shutdown(chan); - l2cap_chan_hold(chan); l2cap_chan_del(chan, ECONNRESET); - l2cap_chan_unlock(chan); - chan->ops->close(chan); + + l2cap_chan_unlock(chan); l2cap_chan_put(chan); mutex_unlock(&conn->chan_lock); @@ -4400,20 +4404,21 @@ static inline int l2cap_disconnect_rsp(struct l2cap_conn *conn, return 0; } + l2cap_chan_hold(chan); l2cap_chan_lock(chan); if (chan->state != BT_DISCONN) { l2cap_chan_unlock(chan); + l2cap_chan_put(chan); mutex_unlock(&conn->chan_lock); return 0; } - l2cap_chan_hold(chan); l2cap_chan_del(chan, 0); - l2cap_chan_unlock(chan); - chan->ops->close(chan); + + l2cap_chan_unlock(chan); l2cap_chan_put(chan); mutex_unlock(&conn->chan_lock); diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index a7be8b59b3c2..390a9afab647 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -1042,7 +1042,7 @@ static int l2cap_sock_recvmsg(struct socket *sock, struct msghdr *msg, } /* Kill socket (only if zapped and orphan) - * Must be called on unlocked socket. + * Must be called on unlocked socket, with l2cap channel lock. */ static void l2cap_sock_kill(struct sock *sk) { @@ -1193,6 +1193,7 @@ static int l2cap_sock_release(struct socket *sock) { struct sock *sk = sock->sk; int err; + struct l2cap_chan *chan; BT_DBG("sock %p, sk %p", sock, sk); @@ -1202,9 +1203,17 @@ static int l2cap_sock_release(struct socket *sock) bt_sock_unlink(&l2cap_sk_list, sk); err = l2cap_sock_shutdown(sock, 2); + chan = l2cap_pi(sk)->chan; + + l2cap_chan_hold(chan); + l2cap_chan_lock(chan); sock_orphan(sk); l2cap_sock_kill(sk); + + l2cap_chan_unlock(chan); + l2cap_chan_put(chan); + return err; } @@ -1222,12 +1231,15 @@ static void l2cap_sock_cleanup_listen(struct sock *parent) BT_DBG("child chan %p state %s", chan, state_to_string(chan->state)); + l2cap_chan_hold(chan); l2cap_chan_lock(chan); + __clear_chan_timer(chan); l2cap_chan_close(chan, ECONNRESET); - l2cap_chan_unlock(chan); - l2cap_sock_kill(sk); + + l2cap_chan_unlock(chan); + l2cap_chan_put(chan); } } diff --git a/net/core/devlink.c b/net/core/devlink.c index 5667cae57072..26c8993a17ae 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -4823,6 +4823,7 @@ int devlink_health_report(struct devlink_health_reporter *reporter, { enum devlink_health_reporter_state prev_health_state; struct devlink *devlink = reporter->devlink; + unsigned long recover_ts_threshold; /* write a log message of the current error */ WARN_ON(!msg); @@ -4832,10 +4833,12 @@ int devlink_health_report(struct devlink_health_reporter *reporter, reporter->health_state = DEVLINK_HEALTH_REPORTER_STATE_ERROR; /* abort if the previous error wasn't recovered */ + recover_ts_threshold = reporter->last_recovery_ts + + msecs_to_jiffies(reporter->graceful_period); if (reporter->auto_recover && (prev_health_state != DEVLINK_HEALTH_REPORTER_STATE_HEALTHY || - jiffies - reporter->last_recovery_ts < - msecs_to_jiffies(reporter->graceful_period))) { + (reporter->last_recovery_ts && reporter->recovery_count && + time_is_after_jiffies(recover_ts_threshold)))) { trace_devlink_health_recover_aborted(devlink, reporter->ops->name, reporter->health_state, diff --git a/net/core/filter.c b/net/core/filter.c index cf2a68513bfd..c441f9961e91 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -6791,8 +6791,6 @@ static int bpf_gen_ld_abs(const struct bpf_insn *orig, bool indirect = BPF_MODE(orig->code) == BPF_IND; struct bpf_insn *insn = insn_buf; - /* We're guaranteed here that CTX is in R6. */ - *insn++ = BPF_MOV64_REG(BPF_REG_1, BPF_REG_CTX); if (!indirect) { *insn++ = BPF_MOV64_IMM(BPF_REG_2, orig->imm); } else { @@ -6800,6 +6798,8 @@ static int bpf_gen_ld_abs(const struct bpf_insn *orig, if (orig->imm) *insn++ = BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, orig->imm); } + /* We're guaranteed here that CTX is in R6. */ + *insn++ = BPF_MOV64_REG(BPF_REG_1, BPF_REG_CTX); switch (BPF_SIZE(orig->code)) { case BPF_B: diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 7b40d12f0c22..04953e5f2530 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -3290,6 +3290,7 @@ static void *neigh_stat_seq_next(struct seq_file *seq, void *v, loff_t *pos) *pos = cpu+1; return per_cpu_ptr(tbl->stats, cpu); } + (*pos)++; return NULL; } diff --git a/net/ipv4/route.c b/net/ipv4/route.c index aa77f989ba81..7a5f64cf1fdd 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -271,6 +271,7 @@ static void *rt_cpu_seq_next(struct seq_file *seq, void *v, loff_t *pos) *pos = cpu+1; return &per_cpu(rt_cache_stat, cpu); } + (*pos)++; return NULL; } diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 01ddfb4156e4..2ffa33b5ef40 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2053,7 +2053,7 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, /* Well, if we have backlog, try to process it now yet. */ - if (copied >= target && !sk->sk_backlog.tail) + if (copied >= target && !READ_ONCE(sk->sk_backlog.tail)) break; if (copied) { diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 96d80e50bf35..9ca6c32065ec 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -2479,14 +2479,13 @@ static void *ipv6_route_seq_next(struct seq_file *seq, void *v, loff_t *pos) struct net *net = seq_file_net(seq); struct ipv6_route_iter *iter = seq->private; + ++(*pos); if (!v) goto iter_table; n = rcu_dereference_bh(((struct fib6_info *)v)->fib6_next); - if (n) { - ++*pos; + if (n) return n; - } iter_table: ipv6_route_check_sernum(iter); @@ -2494,8 +2493,6 @@ static void *ipv6_route_seq_next(struct seq_file *seq, void *v, loff_t *pos) r = fib6_walk_continue(&iter->w); spin_unlock_bh(&iter->tbl->tb6_lock); if (r > 0) { - if (v) - ++*pos; return iter->w.leaf; } else if (r < 0) { fib6_walker_unlink(net, &iter->w); diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c index 5abb7f9b7ee5..fa0f3c1543ba 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -784,7 +784,7 @@ static int llc_ui_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, } /* Well, if we have backlog, try to process it now yet. */ - if (copied >= target && !sk->sk_backlog.tail) + if (copied >= target && !READ_ONCE(sk->sk_backlog.tail)) break; if (copied) { diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 30201aeb426c..f029e75ec815 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -3913,6 +3913,9 @@ void __ieee80211_subif_start_xmit(struct sk_buff *skb, skb->prev = NULL; skb->next = NULL; + if (skb->protocol == sdata->control_port_protocol) + ctrl_flags |= IEEE80211_TX_CTRL_SKIP_MPATH_LOOKUP; + skb = ieee80211_build_hdr(sdata, skb, info_flags, sta, ctrl_flags); if (IS_ERR(skb)) @@ -5096,7 +5099,8 @@ int ieee80211_tx_control_port(struct wiphy *wiphy, struct net_device *dev, return -EINVAL; if (proto == sdata->control_port_protocol) - ctrl_flags |= IEEE80211_TX_CTRL_PORT_CTRL_PROTO; + ctrl_flags |= IEEE80211_TX_CTRL_PORT_CTRL_PROTO | + IEEE80211_TX_CTRL_SKIP_MPATH_LOOKUP; if (unencrypted) flags = IEEE80211_TX_INTFL_DONT_ENCRYPT; diff --git a/net/mac802154/tx.c b/net/mac802154/tx.c index ab52811523e9..c829e4a75325 100644 --- a/net/mac802154/tx.c +++ b/net/mac802154/tx.c @@ -34,11 +34,11 @@ void ieee802154_xmit_worker(struct work_struct *work) if (res) goto err_tx; - ieee802154_xmit_complete(&local->hw, skb, false); - dev->stats.tx_packets++; dev->stats.tx_bytes += skb->len; + ieee802154_xmit_complete(&local->hw, skb, false); + return; err_tx: @@ -78,6 +78,8 @@ ieee802154_tx(struct ieee802154_local *local, struct sk_buff *skb) /* async is priority, otherwise sync is fallback */ if (local->ops->xmit_async) { + unsigned int len = skb->len; + ret = drv_xmit_async(local, skb); if (ret) { ieee802154_wake_queue(&local->hw); @@ -85,7 +87,7 @@ ieee802154_tx(struct ieee802154_local *local, struct sk_buff *skb) } dev->stats.tx_packets++; - dev->stats.tx_bytes += skb->len; + dev->stats.tx_bytes += len; } else { local->tx_skb = skb; queue_work(local->workqueue, &local->tx_work); diff --git a/net/netfilter/nf_conntrack_proto.c b/net/netfilter/nf_conntrack_proto.c index a0560d175a7f..aaf4293ddd45 100644 --- a/net/netfilter/nf_conntrack_proto.c +++ b/net/netfilter/nf_conntrack_proto.c @@ -565,6 +565,7 @@ static int nf_ct_netns_inet_get(struct net *net) int err; err = nf_ct_netns_do_get(net, NFPROTO_IPV4); +#if IS_ENABLED(CONFIG_IPV6) if (err < 0) goto err1; err = nf_ct_netns_do_get(net, NFPROTO_IPV6); @@ -575,6 +576,7 @@ static int nf_ct_netns_inet_get(struct net *net) err2: nf_ct_netns_put(net, NFPROTO_IPV4); err1: +#endif return err; } diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 2023650c2724..ff2d2b514506 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -456,7 +456,8 @@ static struct nft_table *nft_table_lookup(const struct net *net, if (nla == NULL) return ERR_PTR(-EINVAL); - list_for_each_entry_rcu(table, &net->nft.tables, list) { + list_for_each_entry_rcu(table, &net->nft.tables, list, + lockdep_is_held(&net->nft.commit_mutex)) { if (!nla_strcmp(nla, table->name) && table->family == family && nft_active_genmask(table, genmask)) diff --git a/net/openvswitch/meter.c b/net/openvswitch/meter.c index 3323b79ff548..541eea74ef7a 100644 --- a/net/openvswitch/meter.c +++ b/net/openvswitch/meter.c @@ -251,8 +251,8 @@ static struct dp_meter *dp_meter_create(struct nlattr **a) * * Start with a full bucket. */ - band->bucket = (band->burst_size + band->rate) * 1000; - band_max_delta_t = band->bucket / band->rate; + band->bucket = (band->burst_size + band->rate) * 1000ULL; + band_max_delta_t = div_u64(band->bucket, band->rate); if (band_max_delta_t > meter->max_delta_t) meter->max_delta_t = band_max_delta_t; band++; diff --git a/net/openvswitch/meter.h b/net/openvswitch/meter.h index f645913870bd..2e3fd6f1d7eb 100644 --- a/net/openvswitch/meter.h +++ b/net/openvswitch/meter.h @@ -23,7 +23,7 @@ struct dp_meter_band { u32 type; u32 rate; u32 burst_size; - u32 bucket; /* 1/1000 packets, or in bits */ + u64 bucket; /* 1/1000 packets, or in bits */ struct ovs_flow_stats stats; }; diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index 0dab62b67b9a..adceb226ffab 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -36,6 +36,7 @@ #include <net/sctp/sctp.h> #include <net/sctp/sm.h> #include <net/sctp/stream_sched.h> +#include <trace/events/sctp.h> /* Declare internal functions here. */ static int sctp_acked(struct sctp_sackhdr *sack, __u32 tsn); @@ -1238,6 +1239,11 @@ int sctp_outq_sack(struct sctp_outq *q, struct sctp_chunk *chunk) /* Grab the association's destination address list. */ transport_list = &asoc->peer.transport_addr_list; + /* SCTP path tracepoint for congestion control debugging. */ + list_for_each_entry(transport, transport_list, transports) { + trace_sctp_probe_path(transport, asoc); + } + sack_ctsn = ntohl(sack->cum_tsn_ack); gap_ack_blocks = ntohs(sack->num_gap_ack_blocks); asoc->stats.gapcnt += gap_ack_blocks; diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c index 987c4b1f0b17..53d8b82eda00 100644 --- a/net/sunrpc/sched.c +++ b/net/sunrpc/sched.c @@ -204,10 +204,6 @@ static void __rpc_add_wait_queue(struct rpc_wait_queue *queue, struct rpc_task *task, unsigned char queue_priority) { - WARN_ON_ONCE(RPC_IS_QUEUED(task)); - if (RPC_IS_QUEUED(task)) - return; - INIT_LIST_HEAD(&task->u.tk_wait.timer_list); if (RPC_IS_PRIORITY(queue)) __rpc_add_wait_queue_priority(queue, task, queue_priority); @@ -382,7 +378,7 @@ static void rpc_make_runnable(struct workqueue_struct *wq, * NB: An RPC task will only receive interrupt-driven events as long * as it's on a wait queue. */ -static void __rpc_sleep_on_priority(struct rpc_wait_queue *q, +static void __rpc_do_sleep_on_priority(struct rpc_wait_queue *q, struct rpc_task *task, unsigned char queue_priority) { @@ -395,12 +391,23 @@ static void __rpc_sleep_on_priority(struct rpc_wait_queue *q, } +static void __rpc_sleep_on_priority(struct rpc_wait_queue *q, + struct rpc_task *task, + unsigned char queue_priority) +{ + if (WARN_ON_ONCE(RPC_IS_QUEUED(task))) + return; + __rpc_do_sleep_on_priority(q, task, queue_priority); +} + static void __rpc_sleep_on_priority_timeout(struct rpc_wait_queue *q, struct rpc_task *task, unsigned long timeout, unsigned char queue_priority) { + if (WARN_ON_ONCE(RPC_IS_QUEUED(task))) + return; if (time_is_after_jiffies(timeout)) { - __rpc_sleep_on_priority(q, task, queue_priority); + __rpc_do_sleep_on_priority(q, task, queue_priority); __rpc_add_timer(q, task, timeout); } else task->tk_status = -ETIMEDOUT; @@ -824,6 +831,7 @@ rpc_reset_task_statistics(struct rpc_task *task) */ void rpc_exit_task(struct rpc_task *task) { + trace_rpc_task_end(task, task->tk_action); task->tk_action = NULL; if (task->tk_ops->rpc_count_stats) task->tk_ops->rpc_count_stats(task, task->tk_calldata); diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index dc74519286be..fe4cd0b4c412 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -104,8 +104,17 @@ void svc_unreg_xprt_class(struct svc_xprt_class *xcl) } EXPORT_SYMBOL_GPL(svc_unreg_xprt_class); -/* - * Format the transport list for printing +/** + * svc_print_xprts - Format the transport list for printing + * @buf: target buffer for formatted address + * @maxlen: length of target buffer + * + * Fills in @buf with a string containing a list of transport names, each name + * terminated with '\n'. If the buffer is too small, some entries may be + * missing, but it is guaranteed that all lines in the output buffer are + * complete. + * + * Returns positive length of the filled-in string. */ int svc_print_xprts(char *buf, int maxlen) { @@ -118,9 +127,9 @@ int svc_print_xprts(char *buf, int maxlen) list_for_each_entry(xcl, &svc_xprt_class_list, xcl_list) { int slen; - sprintf(tmpstr, "%s %d\n", xcl->xcl_name, xcl->xcl_max_payload); - slen = strlen(tmpstr); - if (len + slen > maxlen) + slen = snprintf(tmpstr, sizeof(tmpstr), "%s %d\n", + xcl->xcl_name, xcl->xcl_max_payload); + if (slen >= sizeof(tmpstr) || len + slen >= maxlen) break; len += slen; strcat(buf, tmpstr); diff --git a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c index cf80394b2db3..68d2dcf0a1be 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c +++ b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c @@ -15,26 +15,25 @@ #undef SVCRDMA_BACKCHANNEL_DEBUG /** - * svc_rdma_handle_bc_reply - Process incoming backchannel reply - * @xprt: controlling backchannel transport - * @rdma_resp: pointer to incoming transport header - * @rcvbuf: XDR buffer into which to decode the reply + * svc_rdma_handle_bc_reply - Process incoming backchannel Reply + * @rqstp: resources for handling the Reply + * @rctxt: Received message * - * Returns: - * %0 if @rcvbuf is filled in, xprt_complete_rqst called, - * %-EAGAIN if server should call ->recvfrom again. */ -int svc_rdma_handle_bc_reply(struct rpc_xprt *xprt, __be32 *rdma_resp, - struct xdr_buf *rcvbuf) +void svc_rdma_handle_bc_reply(struct svc_rqst *rqstp, + struct svc_rdma_recv_ctxt *rctxt) { + struct svc_xprt *sxprt = rqstp->rq_xprt; + struct rpc_xprt *xprt = sxprt->xpt_bc_xprt; struct rpcrdma_xprt *r_xprt = rpcx_to_rdmax(xprt); + struct xdr_buf *rcvbuf = &rqstp->rq_arg; struct kvec *dst, *src = &rcvbuf->head[0]; + __be32 *rdma_resp = rctxt->rc_recv_buf; struct rpc_rqst *req; u32 credits; size_t len; __be32 xid; __be32 *p; - int ret; p = (__be32 *)src->iov_base; len = src->iov_len; @@ -49,14 +48,10 @@ int svc_rdma_handle_bc_reply(struct rpc_xprt *xprt, __be32 *rdma_resp, __func__, (int)len, p); #endif - ret = -EAGAIN; - if (src->iov_len < 24) - goto out_shortreply; - spin_lock(&xprt->queue_lock); req = xprt_lookup_rqst(xprt, xid); if (!req) - goto out_notfound; + goto out_unlock; dst = &req->rq_private_buf.head[0]; memcpy(&req->rq_private_buf, &req->rq_rcv_buf, sizeof(struct xdr_buf)); @@ -77,25 +72,12 @@ int svc_rdma_handle_bc_reply(struct rpc_xprt *xprt, __be32 *rdma_resp, spin_unlock(&xprt->transport_lock); spin_lock(&xprt->queue_lock); - ret = 0; xprt_complete_rqst(req->rq_task, rcvbuf->len); xprt_unpin_rqst(req); rcvbuf->len = 0; out_unlock: spin_unlock(&xprt->queue_lock); -out: - return ret; - -out_shortreply: - dprintk("svcrdma: short bc reply: xprt=%p, len=%zu\n", - xprt, src->iov_len); - goto out; - -out_notfound: - dprintk("svcrdma: unrecognized bc reply: xprt=%p, xid=%08x\n", - xprt, be32_to_cpu(xid)); - goto out_unlock; } /* Send a backwards direction RPC call. @@ -252,6 +234,7 @@ xprt_rdma_bc_put(struct rpc_xprt *xprt) { dprintk("svcrdma: %s: xprt %p\n", __func__, xprt); + xprt_rdma_free_addresses(xprt); xprt_free(xprt); } diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c index d803d814a03a..fd5c1f1bb988 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c +++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c @@ -817,12 +817,9 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp) goto out_drop; rqstp->rq_xprt_hlen = ret; - if (svc_rdma_is_backchannel_reply(xprt, p)) { - ret = svc_rdma_handle_bc_reply(xprt->xpt_bc_xprt, p, - &rqstp->rq_arg); - svc_rdma_recv_ctxt_put(rdma_xprt, ctxt); - return ret; - } + if (svc_rdma_is_backchannel_reply(xprt, p)) + goto out_backchannel; + svc_rdma_get_inv_rkey(rdma_xprt, ctxt); p += rpcrdma_fixed_maxsz; @@ -852,6 +849,8 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp) svc_rdma_recv_ctxt_put(rdma_xprt, ctxt); return ret; +out_backchannel: + svc_rdma_handle_bc_reply(rqstp, ctxt); out_drop: svc_rdma_recv_ctxt_put(rdma_xprt, ctxt); return 0; diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 959155c3a160..66e8f89bce53 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -260,12 +260,12 @@ static void tipc_sk_respond(struct sock *sk, struct sk_buff *skb, int err) * * Caller must hold socket lock */ -static void tsk_rej_rx_queue(struct sock *sk) +static void tsk_rej_rx_queue(struct sock *sk, int error) { struct sk_buff *skb; while ((skb = __skb_dequeue(&sk->sk_receive_queue))) - tipc_sk_respond(sk, skb, TIPC_ERR_NO_PORT); + tipc_sk_respond(sk, skb, error); } static bool tipc_sk_connected(struct sock *sk) @@ -515,34 +515,45 @@ static void __tipc_shutdown(struct socket *sock, int error) /* Remove any pending SYN message */ __skb_queue_purge(&sk->sk_write_queue); - /* Reject all unreceived messages, except on an active connection - * (which disconnects locally & sends a 'FIN+' to peer). - */ - while ((skb = __skb_dequeue(&sk->sk_receive_queue)) != NULL) { - if (TIPC_SKB_CB(skb)->bytes_read) { - kfree_skb(skb); - continue; - } - if (!tipc_sk_type_connectionless(sk) && - sk->sk_state != TIPC_DISCONNECTING) { - tipc_set_sk_state(sk, TIPC_DISCONNECTING); - tipc_node_remove_conn(net, dnode, tsk->portid); - } - tipc_sk_respond(sk, skb, error); + /* Remove partially received buffer if any */ + skb = skb_peek(&sk->sk_receive_queue); + if (skb && TIPC_SKB_CB(skb)->bytes_read) { + __skb_unlink(skb, &sk->sk_receive_queue); + kfree_skb(skb); } - if (tipc_sk_type_connectionless(sk)) + /* Reject all unreceived messages if connectionless */ + if (tipc_sk_type_connectionless(sk)) { + tsk_rej_rx_queue(sk, error); return; + } - if (sk->sk_state != TIPC_DISCONNECTING) { + switch (sk->sk_state) { + case TIPC_CONNECTING: + case TIPC_ESTABLISHED: + tipc_set_sk_state(sk, TIPC_DISCONNECTING); + tipc_node_remove_conn(net, dnode, tsk->portid); + /* Send a FIN+/- to its peer */ + skb = __skb_dequeue(&sk->sk_receive_queue); + if (skb) { + __skb_queue_purge(&sk->sk_receive_queue); + tipc_sk_respond(sk, skb, error); + break; + } skb = tipc_msg_create(TIPC_CRITICAL_IMPORTANCE, TIPC_CONN_MSG, SHORT_H_SIZE, 0, dnode, tsk_own_node(tsk), tsk_peer_port(tsk), tsk->portid, error); if (skb) tipc_node_xmit_skb(net, skb, dnode, tsk->portid); - tipc_node_remove_conn(net, dnode, tsk->portid); - tipc_set_sk_state(sk, TIPC_DISCONNECTING); + break; + case TIPC_LISTEN: + /* Reject all SYN messages */ + tsk_rej_rx_queue(sk, error); + break; + default: + __skb_queue_purge(&sk->sk_receive_queue); + break; } } @@ -2564,7 +2575,7 @@ static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags, * Reject any stray messages received by new socket * before the socket lock was taken (very, very unlikely) */ - tsk_rej_rx_queue(new_sk); + tsk_rej_rx_queue(new_sk, TIPC_ERR_NO_PORT); /* Connect new socket to it's peer */ tipc_sk_finish_conn(new_tsock, msg_origport(msg), msg_orignode(msg)); diff --git a/net/tipc/topsrv.c b/net/tipc/topsrv.c index 73dbed0c4b6b..931c426673c0 100644 --- a/net/tipc/topsrv.c +++ b/net/tipc/topsrv.c @@ -400,7 +400,9 @@ static int tipc_conn_rcv_from_sock(struct tipc_conn *con) return -EWOULDBLOCK; if (ret == sizeof(s)) { read_lock_bh(&sk->sk_callback_lock); - ret = tipc_conn_rcv_sub(srv, con, &s); + /* RACE: the connection can be closed in the meantime */ + if (likely(connected(con))) + ret = tipc_conn_rcv_sub(srv, con, &s); read_unlock_bh(&sk->sk_callback_lock); if (!ret) return 0; diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index b3369d678f1a..ecadd9e482c4 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -189,11 +189,17 @@ static inline int unix_may_send(struct sock *sk, struct sock *osk) return unix_peer(osk) == NULL || unix_our_peer(sk, osk); } -static inline int unix_recvq_full(struct sock const *sk) +static inline int unix_recvq_full(const struct sock *sk) { return skb_queue_len(&sk->sk_receive_queue) > sk->sk_max_ack_backlog; } +static inline int unix_recvq_full_lockless(const struct sock *sk) +{ + return skb_queue_len_lockless(&sk->sk_receive_queue) > + READ_ONCE(sk->sk_max_ack_backlog); +} + struct sock *unix_peer_get(struct sock *s) { struct sock *peer; @@ -1724,7 +1730,8 @@ static int unix_dgram_sendmsg(struct socket *sock, struct msghdr *msg, * - unix_peer(sk) == sk by time of get but disconnected before lock */ if (other != sk && - unlikely(unix_peer(other) != sk && unix_recvq_full(other))) { + unlikely(unix_peer(other) != sk && + unix_recvq_full_lockless(other))) { if (timeo) { timeo = unix_wait_for_peer(other, timeo); diff --git a/net/wireless/Kconfig b/net/wireless/Kconfig index 63cf7131f601..211007c091d5 100644 --- a/net/wireless/Kconfig +++ b/net/wireless/Kconfig @@ -217,6 +217,7 @@ config LIB80211_CRYPT_WEP config LIB80211_CRYPT_CCMP tristate + select CRYPTO select CRYPTO_AES select CRYPTO_CCM diff --git a/security/device_cgroup.c b/security/device_cgroup.c index 725674f3276d..5d7bb91c6487 100644 --- a/security/device_cgroup.c +++ b/security/device_cgroup.c @@ -352,7 +352,8 @@ static bool match_exception_partial(struct list_head *exceptions, short type, { struct dev_exception_item *ex; - list_for_each_entry_rcu(ex, exceptions, list) { + list_for_each_entry_rcu(ex, exceptions, list, + lockdep_is_held(&devcgroup_mutex)) { if ((type & DEVCG_DEV_BLOCK) && !(ex->type & DEVCG_DEV_BLOCK)) continue; if ((type & DEVCG_DEV_CHAR) && !(ex->type & DEVCG_DEV_CHAR)) diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index 552e73d90fd2..212f48025db8 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -3156,6 +3156,9 @@ static int selinux_inode_setxattr(struct dentry *dentry, const char *name, return dentry_has_perm(current_cred(), dentry, FILE__SETATTR); } + if (!selinux_state.initialized) + return (inode_owner_or_capable(inode) ? 0 : -EPERM); + sbsec = inode->i_sb->s_security; if (!(sbsec->flags & SBLABEL_MNT)) return -EOPNOTSUPP; @@ -3239,6 +3242,15 @@ static void selinux_inode_post_setxattr(struct dentry *dentry, const char *name, return; } + if (!selinux_state.initialized) { + /* If we haven't even been initialized, then we can't validate + * against a policy, so leave the label as invalid. It may + * resolve to a valid label on the next revalidation try if + * we've since initialized. + */ + return; + } + rc = security_context_to_sid_force(&selinux_state, value, size, &newsid); if (rc) { diff --git a/security/selinux/selinuxfs.c b/security/selinux/selinuxfs.c index e6c7643c3fc0..e9eaff90cbcc 100644 --- a/security/selinux/selinuxfs.c +++ b/security/selinux/selinuxfs.c @@ -1508,6 +1508,7 @@ static struct avc_cache_stats *sel_avc_get_stat_idx(loff_t *idx) *idx = cpu + 1; return &per_cpu(avc_cache_stats, cpu); } + (*idx)++; return NULL; } diff --git a/sound/hda/hdac_bus.c b/sound/hda/hdac_bus.c index 8f19876244eb..53be2cac98e7 100644 --- a/sound/hda/hdac_bus.c +++ b/sound/hda/hdac_bus.c @@ -158,6 +158,7 @@ static void snd_hdac_bus_process_unsol_events(struct work_struct *work) struct hdac_driver *drv; unsigned int rp, caddr, res; + spin_lock_irq(&bus->reg_lock); while (bus->unsol_rp != bus->unsol_wp) { rp = (bus->unsol_rp + 1) % HDA_UNSOL_QUEUE_SIZE; bus->unsol_rp = rp; @@ -169,10 +170,13 @@ static void snd_hdac_bus_process_unsol_events(struct work_struct *work) codec = bus->caddr_tbl[caddr & 0x0f]; if (!codec || !codec->dev.driver) continue; + spin_unlock_irq(&bus->reg_lock); drv = drv_to_hdac_driver(codec->dev.driver); if (drv->unsol_event) drv->unsol_event(codec, res); + spin_lock_irq(&bus->reg_lock); } + spin_unlock_irq(&bus->reg_lock); } /** diff --git a/sound/hda/hdac_regmap.c b/sound/hda/hdac_regmap.c index 2596a881186f..49780399c284 100644 --- a/sound/hda/hdac_regmap.c +++ b/sound/hda/hdac_regmap.c @@ -363,7 +363,6 @@ static const struct regmap_config hda_regmap_cfg = { .reg_write = hda_reg_write, .use_single_read = true, .use_single_write = true, - .disable_locking = true, }; /** diff --git a/sound/pci/asihpi/hpioctl.c b/sound/pci/asihpi/hpioctl.c index 496dcde9715d..9790f5108a16 100644 --- a/sound/pci/asihpi/hpioctl.c +++ b/sound/pci/asihpi/hpioctl.c @@ -343,7 +343,7 @@ int asihpi_adapter_probe(struct pci_dev *pci_dev, struct hpi_message hm; struct hpi_response hr; struct hpi_adapter adapter; - struct hpi_pci pci; + struct hpi_pci pci = { 0 }; memset(&adapter, 0, sizeof(adapter)); @@ -499,7 +499,7 @@ int asihpi_adapter_probe(struct pci_dev *pci_dev, return 0; err: - for (idx = 0; idx < HPI_MAX_ADAPTER_MEM_SPACES; idx++) { + while (--idx >= 0) { if (pci.ap_mem_base[idx]) { iounmap(pci.ap_mem_base[idx]); pci.ap_mem_base[idx] = NULL; diff --git a/sound/pci/hda/hda_codec.c b/sound/pci/hda/hda_codec.c index 103011e7285a..6da296def283 100644 --- a/sound/pci/hda/hda_codec.c +++ b/sound/pci/hda/hda_codec.c @@ -641,8 +641,18 @@ static void hda_jackpoll_work(struct work_struct *work) struct hda_codec *codec = container_of(work, struct hda_codec, jackpoll_work.work); - snd_hda_jack_set_dirty_all(codec); - snd_hda_jack_poll_all(codec); + /* for non-polling trigger: we need nothing if already powered on */ + if (!codec->jackpoll_interval && snd_hdac_is_power_on(&codec->core)) + return; + + /* the power-up/down sequence triggers the runtime resume */ + snd_hda_power_up_pm(codec); + /* update jacks manually if polling is required, too */ + if (codec->jackpoll_interval) { + snd_hda_jack_set_dirty_all(codec); + snd_hda_jack_poll_all(codec); + } + snd_hda_power_down_pm(codec); if (!codec->jackpoll_interval) return; @@ -2958,18 +2968,14 @@ static int hda_codec_runtime_resume(struct device *dev) static int hda_codec_force_resume(struct device *dev) { struct hda_codec *codec = dev_to_hda_codec(dev); - bool forced_resume = !codec->relaxed_resume && codec->jacktbl.used; int ret; - /* The get/put pair below enforces the runtime resume even if the - * device hasn't been used at suspend time. This trick is needed to - * update the jack state change during the sleep. - */ - if (forced_resume) - pm_runtime_get_noresume(dev); ret = pm_runtime_force_resume(dev); - if (forced_resume) - pm_runtime_put(dev); + /* schedule jackpoll work for jack detection update */ + if (codec->jackpoll_interval || + (pm_runtime_suspended(dev) && hda_codec_need_resume(codec))) + schedule_delayed_work(&codec->jackpoll_work, + codec->jackpoll_interval); return ret; } diff --git a/sound/pci/hda/hda_controller.c b/sound/pci/hda/hda_controller.c index 76b507058cb4..5e6081750bd9 100644 --- a/sound/pci/hda/hda_controller.c +++ b/sound/pci/hda/hda_controller.c @@ -1159,16 +1159,23 @@ irqreturn_t azx_interrupt(int irq, void *dev_id) if (snd_hdac_bus_handle_stream_irq(bus, status, stream_update)) active = true; - /* clear rirb int */ status = azx_readb(chip, RIRBSTS); if (status & RIRB_INT_MASK) { + /* + * Clearing the interrupt status here ensures that no + * interrupt gets masked after the RIRB wp is read in + * snd_hdac_bus_update_rirb. This avoids a possible + * race condition where codec response in RIRB may + * remain unserviced by IRQ, eventually falling back + * to polling mode in azx_rirb_get_response. + */ + azx_writeb(chip, RIRBSTS, RIRB_INT_MASK); active = true; if (status & RIRB_INT_RESPONSE) { if (chip->driver_caps & AZX_DCAPS_CTX_WORKAROUND) udelay(80); snd_hdac_bus_update_rirb(bus); } - azx_writeb(chip, RIRBSTS, RIRB_INT_MASK); } } while (active && ++repeat < 10); diff --git a/sound/pci/hda/hda_controller.h b/sound/pci/hda/hda_controller.h index 82e26442724b..a356fb0e5773 100644 --- a/sound/pci/hda/hda_controller.h +++ b/sound/pci/hda/hda_controller.h @@ -41,7 +41,7 @@ /* 24 unused */ #define AZX_DCAPS_COUNT_LPIB_DELAY (1 << 25) /* Take LPIB as delay */ #define AZX_DCAPS_PM_RUNTIME (1 << 26) /* runtime PM support */ -/* 27 unused */ +#define AZX_DCAPS_SUSPEND_SPURIOUS_WAKEUP (1 << 27) /* Workaround for spurious wakeups after suspend */ #define AZX_DCAPS_CORBRP_SELF_CLEAR (1 << 28) /* CORBRP clears itself after reset */ #define AZX_DCAPS_NO_MSI64 (1 << 29) /* Stick to 32-bit MSIs */ #define AZX_DCAPS_SEPARATE_STREAM_TAG (1 << 30) /* capture and playback use separate stream tag */ diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index 7353d2ec359a..590ea262f2e2 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -295,7 +295,8 @@ enum { /* PCH for HSW/BDW; with runtime PM */ /* no i915 binding for this as HSW/BDW has another controller for HDMI */ #define AZX_DCAPS_INTEL_PCH \ - (AZX_DCAPS_INTEL_PCH_BASE | AZX_DCAPS_PM_RUNTIME) + (AZX_DCAPS_INTEL_PCH_BASE | AZX_DCAPS_PM_RUNTIME |\ + AZX_DCAPS_SUSPEND_SPURIOUS_WAKEUP) /* HSW HDMI */ #define AZX_DCAPS_INTEL_HASWELL \ @@ -1002,7 +1003,8 @@ static void __azx_runtime_resume(struct azx *chip, bool from_rt) if (status && from_rt) { list_for_each_codec(codec, &chip->bus) - if (status & (1 << codec->addr)) + if (!codec->relaxed_resume && + (status & (1 << codec->addr))) schedule_delayed_work(&codec->jackpoll_work, codec->jackpoll_interval); } @@ -1025,7 +1027,14 @@ static int azx_suspend(struct device *dev) chip = card->private_data; bus = azx_bus(chip); snd_power_change_state(card, SNDRV_CTL_POWER_D3hot); - __azx_runtime_suspend(chip); + /* An ugly workaround: direct call of __azx_runtime_suspend() and + * __azx_runtime_resume() for old Intel platforms that suffer from + * spurious wakeups after S3 suspend + */ + if (chip->driver_caps & AZX_DCAPS_SUSPEND_SPURIOUS_WAKEUP) + __azx_runtime_suspend(chip); + else + pm_runtime_force_suspend(dev); if (bus->irq >= 0) { free_irq(bus->irq, chip); bus->irq = -1; @@ -1052,7 +1061,11 @@ static int azx_resume(struct device *dev) chip->msi = 0; if (azx_acquire_irq(chip, 1) < 0) return -EIO; - __azx_runtime_resume(chip, false); + + if (chip->driver_caps & AZX_DCAPS_SUSPEND_SPURIOUS_WAKEUP) + __azx_runtime_resume(chip, false); + else + pm_runtime_force_resume(dev); snd_power_change_state(card, SNDRV_CTL_POWER_D0); trace_azx_resume(chip); @@ -1099,12 +1112,12 @@ static int azx_runtime_suspend(struct device *dev) if (!azx_is_pm_ready(card)) return 0; chip = card->private_data; - if (!azx_has_pm_runtime(chip)) - return 0; /* enable controller wake up event */ - azx_writew(chip, WAKEEN, azx_readw(chip, WAKEEN) | - STATESTS_INT_MASK); + if (snd_power_get_state(card) == SNDRV_CTL_POWER_D0) { + azx_writew(chip, WAKEEN, azx_readw(chip, WAKEEN) | + STATESTS_INT_MASK); + } __azx_runtime_suspend(chip); trace_azx_runtime_suspend(chip); @@ -1115,17 +1128,18 @@ static int azx_runtime_resume(struct device *dev) { struct snd_card *card = dev_get_drvdata(dev); struct azx *chip; + bool from_rt = snd_power_get_state(card) == SNDRV_CTL_POWER_D0; if (!azx_is_pm_ready(card)) return 0; chip = card->private_data; - if (!azx_has_pm_runtime(chip)) - return 0; - __azx_runtime_resume(chip, true); + __azx_runtime_resume(chip, from_rt); /* disable controller Wake Up event*/ - azx_writew(chip, WAKEEN, azx_readw(chip, WAKEEN) & - ~STATESTS_INT_MASK); + if (from_rt) { + azx_writew(chip, WAKEEN, azx_readw(chip, WAKEEN) & + ~STATESTS_INT_MASK); + } trace_azx_runtime_resume(chip); return 0; diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 54346ae47d11..4dfd714f718b 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -3418,7 +3418,11 @@ static void alc256_shutup(struct hda_codec *codec) /* 3k pull low control for Headset jack. */ /* NOTE: call this before clearing the pin, otherwise codec stalls */ - alc_update_coef_idx(codec, 0x46, 0, 3 << 12); + /* If disable 3k pulldown control for alc257, the Mic detection will not work correctly + * when booting with headset plugged. So skip setting it for the codec alc257 + */ + if (codec->core.vendor_id != 0x10ec0257) + alc_update_coef_idx(codec, 0x46, 0, 3 << 12); if (!spec->no_shutup_pins) snd_hda_codec_write(codec, hp_pin, 0, @@ -6032,6 +6036,7 @@ static void alc_fixup_thinkpad_acpi(struct hda_codec *codec, #include "hp_x360_helper.c" enum { + ALC269_FIXUP_GPIO2, ALC269_FIXUP_SONY_VAIO, ALC275_FIXUP_SONY_VAIO_GPIO2, ALC269_FIXUP_DELL_M101Z, @@ -6213,6 +6218,10 @@ enum { }; static const struct hda_fixup alc269_fixups[] = { + [ALC269_FIXUP_GPIO2] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc_fixup_gpio2, + }, [ALC269_FIXUP_SONY_VAIO] = { .type = HDA_FIXUP_PINCTLS, .v.pins = (const struct hda_pintbl[]) { @@ -7032,6 +7041,8 @@ static const struct hda_fixup alc269_fixups[] = { [ALC233_FIXUP_LENOVO_MULTI_CODECS] = { .type = HDA_FIXUP_FUNC, .v.func = alc233_alc662_fixup_lenovo_dual_codecs, + .chained = true, + .chain_id = ALC269_FIXUP_GPIO2 }, [ALC233_FIXUP_ACER_HEADSET_MIC] = { .type = HDA_FIXUP_VERBS, diff --git a/sound/soc/codecs/max98090.c b/sound/soc/codecs/max98090.c index 45da2b51543e..6b9d326e11b0 100644 --- a/sound/soc/codecs/max98090.c +++ b/sound/soc/codecs/max98090.c @@ -2112,10 +2112,16 @@ static void max98090_pll_work(struct max98090_priv *max98090) dev_info_ratelimited(component->dev, "PLL unlocked\n"); + /* + * As the datasheet suggested, the maximum PLL lock time should be + * 7 msec. The workaround resets the codec softly by toggling SHDN + * off and on if PLL failed to lock for 10 msec. Notably, there is + * no suggested hold time for SHDN off. + */ + /* Toggle shutdown OFF then ON */ snd_soc_component_update_bits(component, M98090_REG_DEVICE_SHUTDOWN, M98090_SHDNN_MASK, 0); - msleep(10); snd_soc_component_update_bits(component, M98090_REG_DEVICE_SHUTDOWN, M98090_SHDNN_MASK, M98090_SHDNN_MASK); diff --git a/sound/soc/codecs/pcm3168a.c b/sound/soc/codecs/pcm3168a.c index 88b75695fbf7..b37e5fbbd301 100644 --- a/sound/soc/codecs/pcm3168a.c +++ b/sound/soc/codecs/pcm3168a.c @@ -302,6 +302,13 @@ static int pcm3168a_set_dai_sysclk(struct snd_soc_dai *dai, struct pcm3168a_priv *pcm3168a = snd_soc_component_get_drvdata(dai->component); int ret; + /* + * Some sound card sets 0 Hz as reset, + * but it is impossible to set. Ignore it here + */ + if (freq == 0) + return 0; + if (freq > PCM3168A_MAX_SYSCLK) return -EINVAL; diff --git a/sound/soc/codecs/wm8994.c b/sound/soc/codecs/wm8994.c index d5fb7f5dd551..6dbab3fc6537 100644 --- a/sound/soc/codecs/wm8994.c +++ b/sound/soc/codecs/wm8994.c @@ -3372,6 +3372,8 @@ int wm8994_mic_detect(struct snd_soc_component *component, struct snd_soc_jack * return -EINVAL; } + pm_runtime_get_sync(component->dev); + switch (micbias) { case 1: micdet = &wm8994->micdet[0]; @@ -3419,6 +3421,8 @@ int wm8994_mic_detect(struct snd_soc_component *component, struct snd_soc_jack * snd_soc_dapm_sync(dapm); + pm_runtime_put(component->dev); + return 0; } EXPORT_SYMBOL_GPL(wm8994_mic_detect); @@ -3786,6 +3790,8 @@ int wm8958_mic_detect(struct snd_soc_component *component, struct snd_soc_jack * return -EINVAL; } + pm_runtime_get_sync(component->dev); + if (jack) { snd_soc_dapm_force_enable_pin(dapm, "CLK_SYS"); snd_soc_dapm_sync(dapm); @@ -3854,6 +3860,8 @@ int wm8958_mic_detect(struct snd_soc_component *component, struct snd_soc_jack * snd_soc_dapm_sync(dapm); } + pm_runtime_put(component->dev); + return 0; } EXPORT_SYMBOL_GPL(wm8958_mic_detect); @@ -4047,11 +4055,13 @@ static int wm8994_component_probe(struct snd_soc_component *component) wm8994->hubs.dcs_readback_mode = 2; break; } + wm8994->hubs.micd_scthr = true; break; case WM8958: wm8994->hubs.dcs_readback_mode = 1; wm8994->hubs.hp_startup_mode = 1; + wm8994->hubs.micd_scthr = true; switch (control->revision) { case 0: diff --git a/sound/soc/codecs/wm_hubs.c b/sound/soc/codecs/wm_hubs.c index e93af7edd8f7..dd421e2fe7b2 100644 --- a/sound/soc/codecs/wm_hubs.c +++ b/sound/soc/codecs/wm_hubs.c @@ -1223,6 +1223,9 @@ int wm_hubs_handle_analogue_pdata(struct snd_soc_component *component, snd_soc_component_update_bits(component, WM8993_ADDITIONAL_CONTROL, WM8993_LINEOUT2_FB, WM8993_LINEOUT2_FB); + if (!hubs->micd_scthr) + return 0; + snd_soc_component_update_bits(component, WM8993_MICBIAS, WM8993_JD_SCTHR_MASK | WM8993_JD_THR_MASK | WM8993_MICB1_LVL | WM8993_MICB2_LVL, diff --git a/sound/soc/codecs/wm_hubs.h b/sound/soc/codecs/wm_hubs.h index 4b8e5f0d6e32..988b29e63060 100644 --- a/sound/soc/codecs/wm_hubs.h +++ b/sound/soc/codecs/wm_hubs.h @@ -27,6 +27,7 @@ struct wm_hubs_data { int hp_startup_mode; int series_startup; int no_series_update; + bool micd_scthr; bool no_cache_dac_hp_direct; struct list_head dcs_cache; diff --git a/sound/soc/img/img-i2s-out.c b/sound/soc/img/img-i2s-out.c index 4b1853409633..9c4212f2f726 100644 --- a/sound/soc/img/img-i2s-out.c +++ b/sound/soc/img/img-i2s-out.c @@ -347,8 +347,10 @@ static int img_i2s_out_set_fmt(struct snd_soc_dai *dai, unsigned int fmt) chan_control_mask = IMG_I2S_OUT_CHAN_CTL_CLKT_MASK; ret = pm_runtime_get_sync(i2s->dev); - if (ret < 0) + if (ret < 0) { + pm_runtime_put_noidle(i2s->dev); return ret; + } img_i2s_out_disable(i2s); @@ -488,8 +490,10 @@ static int img_i2s_out_probe(struct platform_device *pdev) goto err_pm_disable; } ret = pm_runtime_get_sync(&pdev->dev); - if (ret < 0) + if (ret < 0) { + pm_runtime_put_noidle(&pdev->dev); goto err_suspend; + } reg = IMG_I2S_OUT_CTL_FRM_SIZE_MASK; img_i2s_out_writel(i2s, reg, IMG_I2S_OUT_CTL); diff --git a/sound/soc/intel/boards/bytcr_rt5640.c b/sound/soc/intel/boards/bytcr_rt5640.c index f7964d1ec486..6012367f6fe4 100644 --- a/sound/soc/intel/boards/bytcr_rt5640.c +++ b/sound/soc/intel/boards/bytcr_rt5640.c @@ -591,6 +591,16 @@ static const struct dmi_system_id byt_rt5640_quirk_table[] = { BYT_RT5640_SSP0_AIF1 | BYT_RT5640_MCLK_EN), }, + { /* MPMAN Converter 9, similar hw as the I.T.Works TW891 2-in-1 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "MPMAN"), + DMI_MATCH(DMI_PRODUCT_NAME, "Converter9"), + }, + .driver_data = (void *)(BYTCR_INPUT_DEFAULTS | + BYT_RT5640_MONO_SPEAKER | + BYT_RT5640_SSP0_AIF1 | + BYT_RT5640_MCLK_EN), + }, { /* MPMAN MPWIN895CL */ .matches = { diff --git a/sound/soc/kirkwood/kirkwood-dma.c b/sound/soc/kirkwood/kirkwood-dma.c index 6f69f314f2c2..d2d5c25bf550 100644 --- a/sound/soc/kirkwood/kirkwood-dma.c +++ b/sound/soc/kirkwood/kirkwood-dma.c @@ -132,7 +132,7 @@ static int kirkwood_dma_open(struct snd_pcm_substream *substream) err = request_irq(priv->irq, kirkwood_dma_irq, IRQF_SHARED, "kirkwood-i2s", priv); if (err) - return -EBUSY; + return err; /* * Enable Error interrupts. We're only ack'ing them but diff --git a/sound/soc/sof/ipc.c b/sound/soc/sof/ipc.c index e7b1a80e2a14..f38f651da224 100644 --- a/sound/soc/sof/ipc.c +++ b/sound/soc/sof/ipc.c @@ -215,15 +215,17 @@ static int tx_wait_done(struct snd_sof_ipc *ipc, struct snd_sof_ipc_msg *msg, snd_sof_trace_notify_for_error(ipc->sdev); ret = -ETIMEDOUT; } else { - /* copy the data returned from DSP */ ret = msg->reply_error; - if (msg->reply_size) - memcpy(reply_data, msg->reply_data, msg->reply_size); - if (ret < 0) + if (ret < 0) { dev_err(sdev->dev, "error: ipc error for 0x%x size %zu\n", hdr->cmd, msg->reply_size); - else + } else { ipc_log_header(sdev->dev, "ipc tx succeeded", hdr->cmd); + if (msg->reply_size) + /* copy the data returned from DSP */ + memcpy(reply_data, msg->reply_data, + msg->reply_size); + } } return ret; diff --git a/sound/usb/midi.c b/sound/usb/midi.c index 0cb4142b05f6..bc9068b616bb 100644 --- a/sound/usb/midi.c +++ b/sound/usb/midi.c @@ -1827,6 +1827,28 @@ static int snd_usbmidi_create_endpoints(struct snd_usb_midi *umidi, return 0; } +static struct usb_ms_endpoint_descriptor *find_usb_ms_endpoint_descriptor( + struct usb_host_endpoint *hostep) +{ + unsigned char *extra = hostep->extra; + int extralen = hostep->extralen; + + while (extralen > 3) { + struct usb_ms_endpoint_descriptor *ms_ep = + (struct usb_ms_endpoint_descriptor *)extra; + + if (ms_ep->bLength > 3 && + ms_ep->bDescriptorType == USB_DT_CS_ENDPOINT && + ms_ep->bDescriptorSubtype == UAC_MS_GENERAL) + return ms_ep; + if (!extra[0]) + break; + extralen -= extra[0]; + extra += extra[0]; + } + return NULL; +} + /* * Returns MIDIStreaming device capabilities. */ @@ -1864,11 +1886,8 @@ static int snd_usbmidi_get_ms_info(struct snd_usb_midi *umidi, ep = get_ep_desc(hostep); if (!usb_endpoint_xfer_bulk(ep) && !usb_endpoint_xfer_int(ep)) continue; - ms_ep = (struct usb_ms_endpoint_descriptor *)hostep->extra; - if (hostep->extralen < 4 || - ms_ep->bLength < 4 || - ms_ep->bDescriptorType != USB_DT_CS_ENDPOINT || - ms_ep->bDescriptorSubtype != UAC_MS_GENERAL) + ms_ep = find_usb_ms_endpoint_descriptor(hostep); + if (!ms_ep) continue; if (usb_endpoint_dir_out(ep)) { if (endpoints[epidx].out_ep) { diff --git a/sound/usb/mixer.c b/sound/usb/mixer.c index 9079c380228f..8aa96ed0b1b5 100644 --- a/sound/usb/mixer.c +++ b/sound/usb/mixer.c @@ -1684,6 +1684,16 @@ static void __build_feature_ctl(struct usb_mixer_interface *mixer, /* get min/max values */ get_min_max_with_quirks(cval, 0, kctl); + /* skip a bogus volume range */ + if (cval->max <= cval->min) { + usb_audio_dbg(mixer->chip, + "[%d] FU [%s] skipped due to invalid volume\n", + cval->head.id, kctl->id.name); + snd_ctl_free_one(kctl); + return; + } + + if (control == UAC_FU_VOLUME) { check_mapped_dB(map, cval); if (cval->dBmin < cval->dBmax || !cval->initialized) { diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index a756f50d9f07..cc75d9749e9f 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -1604,12 +1604,13 @@ void snd_usb_ctl_msg_quirk(struct usb_device *dev, unsigned int pipe, && (requesttype & USB_TYPE_MASK) == USB_TYPE_CLASS) msleep(20); - /* Zoom R16/24, Logitech H650e, Jabra 550a, Kingston HyperX needs a tiny - * delay here, otherwise requests like get/set frequency return as - * failed despite actually succeeding. + /* Zoom R16/24, Logitech H650e/H570e, Jabra 550a, Kingston HyperX + * needs a tiny delay here, otherwise requests like get/set + * frequency return as failed despite actually succeeding. */ if ((chip->usb_id == USB_ID(0x1686, 0x00dd) || chip->usb_id == USB_ID(0x046d, 0x0a46) || + chip->usb_id == USB_ID(0x046d, 0x0a56) || chip->usb_id == USB_ID(0x0b0e, 0x0349) || chip->usb_id == USB_ID(0x0951, 0x16ad)) && (requesttype & USB_TYPE_MASK) == USB_TYPE_CLASS) diff --git a/tools/gpio/gpio-hammer.c b/tools/gpio/gpio-hammer.c index 0e0060a6eb34..083399d276e4 100644 --- a/tools/gpio/gpio-hammer.c +++ b/tools/gpio/gpio-hammer.c @@ -135,7 +135,14 @@ int main(int argc, char **argv) device_name = optarg; break; case 'o': - lines[i] = strtoul(optarg, NULL, 10); + /* + * Avoid overflow. Do not immediately error, we want to + * be able to accurately report on the amount of times + * '-o' was given to give an accurate error message + */ + if (i < GPIOHANDLES_MAX) + lines[i] = strtoul(optarg, NULL, 10); + i++; break; case '?': @@ -143,6 +150,14 @@ int main(int argc, char **argv) return -1; } } + + if (i >= GPIOHANDLES_MAX) { + fprintf(stderr, + "Only %d occurences of '-o' are allowed, %d were found\n", + GPIOHANDLES_MAX, i + 1); + return -1; + } + nlines = i; if (!device_name || !nlines) { diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 48b234d8f251..1b7e748170e5 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -556,7 +556,7 @@ static int add_jump_destinations(struct objtool_file *file) insn->type != INSN_JUMP_UNCONDITIONAL) continue; - if (insn->ignore || insn->offset == FAKE_JUMP_OFFSET) + if (insn->offset == FAKE_JUMP_OFFSET) continue; rela = find_rela_by_dest_range(insn->sec, insn->offset, diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 468fc49420ce..ac2feddc75fd 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -351,7 +351,7 @@ static void process_interval(void) } init_stats(&walltime_nsecs_stats); - update_stats(&walltime_nsecs_stats, stat_config.interval * 1000000); + update_stats(&walltime_nsecs_stats, stat_config.interval * 1000000ULL); print_counters(&rs, 0, NULL); } diff --git a/tools/perf/pmu-events/jevents.c b/tools/perf/pmu-events/jevents.c index d36ae65ae333..f4a0d72246cb 100644 --- a/tools/perf/pmu-events/jevents.c +++ b/tools/perf/pmu-events/jevents.c @@ -1068,10 +1068,9 @@ static int process_one_file(const char *fpath, const struct stat *sb, */ int main(int argc, char *argv[]) { - int rc; + int rc, ret = 0; int maxfds; char ldirname[PATH_MAX]; - const char *arch; const char *output_file; const char *start_dirname; @@ -1142,7 +1141,8 @@ int main(int argc, char *argv[]) /* Make build fail */ fclose(eventsfp); free_arch_std_events(); - return 1; + ret = 1; + goto out_free_mapfile; } else if (rc) { goto empty_map; } @@ -1160,14 +1160,17 @@ int main(int argc, char *argv[]) /* Make build fail */ fclose(eventsfp); free_arch_std_events(); - return 1; + ret = 1; } - return 0; + + goto out_free_mapfile; empty_map: fclose(eventsfp); create_empty_mapping(output_file); free_arch_std_events(); - return 0; +out_free_mapfile: + free(mapfile); + return ret; } diff --git a/tools/perf/tests/shell/lib/probe_vfs_getname.sh b/tools/perf/tests/shell/lib/probe_vfs_getname.sh index 7cb99b433888..c2cc42daf924 100644 --- a/tools/perf/tests/shell/lib/probe_vfs_getname.sh +++ b/tools/perf/tests/shell/lib/probe_vfs_getname.sh @@ -14,7 +14,7 @@ add_probe_vfs_getname() { if [ $had_vfs_getname -eq 1 ] ; then line=$(perf probe -L getname_flags 2>&1 | egrep 'result.*=.*filename;' | sed -r 's/[[:space:]]+([[:digit:]]+)[[:space:]]+result->uptr.*/\1/') perf probe -q "vfs_getname=getname_flags:${line} pathname=result->name:string" || \ - perf probe $verbose "vfs_getname=getname_flags:${line} pathname=filename:string" + perf probe $verbose "vfs_getname=getname_flags:${line} pathname=filename:ustring" fi } diff --git a/tools/perf/tests/shell/record+zstd_comp_decomp.sh b/tools/perf/tests/shell/record+zstd_comp_decomp.sh index 63a91ec473bb..045723b3d992 100755 --- a/tools/perf/tests/shell/record+zstd_comp_decomp.sh +++ b/tools/perf/tests/shell/record+zstd_comp_decomp.sh @@ -12,7 +12,8 @@ skip_if_no_z_record() { collect_z_record() { echo "Collecting compressed record file:" - $perf_tool record -o $trace_file -g -z -F 5000 -- \ + [[ "$(uname -m)" != s390x ]] && gflag='-g' + $perf_tool record -o $trace_file $gflag -z -F 5000 -- \ dd count=500 if=/dev/urandom of=/dev/null } diff --git a/tools/perf/trace/beauty/arch_errno_names.sh b/tools/perf/trace/beauty/arch_errno_names.sh index 22c9fc900c84..f8c44a85650b 100755 --- a/tools/perf/trace/beauty/arch_errno_names.sh +++ b/tools/perf/trace/beauty/arch_errno_names.sh @@ -91,7 +91,7 @@ EoHEADER # in tools/perf/arch archlist="" for arch in $(find $toolsdir/arch -maxdepth 1 -mindepth 1 -type d -printf "%f\n" | grep -v x86 | sort); do - test -d arch/$arch && archlist="$archlist $arch" + test -d $toolsdir/perf/arch/$arch && archlist="$archlist $arch" done for arch in x86 $archlist generic; do diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c index a22c1114e880..324ec0456c83 100644 --- a/tools/perf/util/cpumap.c +++ b/tools/perf/util/cpumap.c @@ -299,7 +299,7 @@ static void set_max_cpu_num(void) /* get the highest possible cpu number for a sparse allocation */ ret = snprintf(path, PATH_MAX, "%s/devices/system/cpu/possible", mnt); - if (ret == PATH_MAX) { + if (ret >= PATH_MAX) { pr_err("sysfs path crossed PATH_MAX(%d) size\n", PATH_MAX); goto out; } @@ -310,7 +310,7 @@ static void set_max_cpu_num(void) /* get the highest present cpu number for a sparse allocation */ ret = snprintf(path, PATH_MAX, "%s/devices/system/cpu/present", mnt); - if (ret == PATH_MAX) { + if (ret >= PATH_MAX) { pr_err("sysfs path crossed PATH_MAX(%d) size\n", PATH_MAX); goto out; } @@ -338,7 +338,7 @@ static void set_max_node_num(void) /* get the highest possible cpu number for a sparse allocation */ ret = snprintf(path, PATH_MAX, "%s/devices/system/node/possible", mnt); - if (ret == PATH_MAX) { + if (ret >= PATH_MAX) { pr_err("sysfs path crossed PATH_MAX(%d) size\n", PATH_MAX); goto out; } @@ -423,7 +423,7 @@ int cpu__setup_cpunode_map(void) return 0; n = snprintf(path, PATH_MAX, "%s/devices/system/node", mnt); - if (n == PATH_MAX) { + if (n >= PATH_MAX) { pr_err("sysfs path crossed PATH_MAX(%d) size\n", PATH_MAX); return -1; } @@ -438,7 +438,7 @@ int cpu__setup_cpunode_map(void) continue; n = snprintf(buf, PATH_MAX, "%s/%s", path, dent1->d_name); - if (n == PATH_MAX) { + if (n >= PATH_MAX) { pr_err("sysfs path crossed PATH_MAX(%d) size\n", PATH_MAX); continue; } diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c index f5f855fff412..451eee24165e 100644 --- a/tools/perf/util/cs-etm.c +++ b/tools/perf/util/cs-etm.c @@ -363,6 +363,23 @@ struct cs_etm_packet_queue return NULL; } +static void cs_etm__packet_swap(struct cs_etm_auxtrace *etm, + struct cs_etm_traceid_queue *tidq) +{ + struct cs_etm_packet *tmp; + + if (etm->sample_branches || etm->synth_opts.last_branch || + etm->sample_instructions) { + /* + * Swap PACKET with PREV_PACKET: PACKET becomes PREV_PACKET for + * the next incoming packet. + */ + tmp = tidq->packet; + tidq->packet = tidq->prev_packet; + tidq->prev_packet = tmp; + } +} + static void cs_etm__packet_dump(const char *pkt_string) { const char *color = PERF_COLOR_BLUE; @@ -1340,12 +1357,14 @@ static int cs_etm__sample(struct cs_etm_queue *etmq, struct cs_etm_traceid_queue *tidq) { struct cs_etm_auxtrace *etm = etmq->etm; - struct cs_etm_packet *tmp; int ret; u8 trace_chan_id = tidq->trace_chan_id; - u64 instrs_executed = tidq->packet->instr_count; + u64 instrs_prev; + + /* Get instructions remainder from previous packet */ + instrs_prev = tidq->period_instructions; - tidq->period_instructions += instrs_executed; + tidq->period_instructions += tidq->packet->instr_count; /* * Record a branch when the last instruction in @@ -1363,26 +1382,76 @@ static int cs_etm__sample(struct cs_etm_queue *etmq, * TODO: allow period to be defined in cycles and clock time */ - /* Get number of instructions executed after the sample point */ - u64 instrs_over = tidq->period_instructions - - etm->instructions_sample_period; + /* + * Below diagram demonstrates the instruction samples + * generation flows: + * + * Instrs Instrs Instrs Instrs + * Sample(n) Sample(n+1) Sample(n+2) Sample(n+3) + * | | | | + * V V V V + * -------------------------------------------------- + * ^ ^ + * | | + * Period Period + * instructions(Pi) instructions(Pi') + * + * | | + * \---------------- -----------------/ + * V + * tidq->packet->instr_count + * + * Instrs Sample(n...) are the synthesised samples occurring + * every etm->instructions_sample_period instructions - as + * defined on the perf command line. Sample(n) is being the + * last sample before the current etm packet, n+1 to n+3 + * samples are generated from the current etm packet. + * + * tidq->packet->instr_count represents the number of + * instructions in the current etm packet. + * + * Period instructions (Pi) contains the the number of + * instructions executed after the sample point(n) from the + * previous etm packet. This will always be less than + * etm->instructions_sample_period. + * + * When generate new samples, it combines with two parts + * instructions, one is the tail of the old packet and another + * is the head of the new coming packet, to generate + * sample(n+1); sample(n+2) and sample(n+3) consume the + * instructions with sample period. After sample(n+3), the rest + * instructions will be used by later packet and it is assigned + * to tidq->period_instructions for next round calculation. + */ /* - * Calculate the address of the sampled instruction (-1 as - * sample is reported as though instruction has just been - * executed, but PC has not advanced to next instruction) + * Get the initial offset into the current packet instructions; + * entry conditions ensure that instrs_prev is less than + * etm->instructions_sample_period. */ - u64 offset = (instrs_executed - instrs_over - 1); - u64 addr = cs_etm__instr_addr(etmq, trace_chan_id, - tidq->packet, offset); + u64 offset = etm->instructions_sample_period - instrs_prev; + u64 addr; - ret = cs_etm__synth_instruction_sample( - etmq, tidq, addr, etm->instructions_sample_period); - if (ret) - return ret; + while (tidq->period_instructions >= + etm->instructions_sample_period) { + /* + * Calculate the address of the sampled instruction (-1 + * as sample is reported as though instruction has just + * been executed, but PC has not advanced to next + * instruction) + */ + addr = cs_etm__instr_addr(etmq, trace_chan_id, + tidq->packet, offset - 1); + ret = cs_etm__synth_instruction_sample( + etmq, tidq, addr, + etm->instructions_sample_period); + if (ret) + return ret; - /* Carry remaining instructions into next sample period */ - tidq->period_instructions = instrs_over; + offset += etm->instructions_sample_period; + tidq->period_instructions -= + etm->instructions_sample_period; + } } if (etm->sample_branches) { @@ -1404,15 +1473,7 @@ static int cs_etm__sample(struct cs_etm_queue *etmq, } } - if (etm->sample_branches || etm->synth_opts.last_branch) { - /* - * Swap PACKET with PREV_PACKET: PACKET becomes PREV_PACKET for - * the next incoming packet. - */ - tmp = tidq->packet; - tidq->packet = tidq->prev_packet; - tidq->prev_packet = tmp; - } + cs_etm__packet_swap(etm, tidq); return 0; } @@ -1441,7 +1502,6 @@ static int cs_etm__flush(struct cs_etm_queue *etmq, { int err = 0; struct cs_etm_auxtrace *etm = etmq->etm; - struct cs_etm_packet *tmp; /* Handle start tracing packet */ if (tidq->prev_packet->sample_type == CS_ETM_EMPTY) @@ -1476,15 +1536,7 @@ static int cs_etm__flush(struct cs_etm_queue *etmq, } swap_packet: - if (etm->sample_branches || etm->synth_opts.last_branch) { - /* - * Swap PACKET with PREV_PACKET: PACKET becomes PREV_PACKET for - * the next incoming packet. - */ - tmp = tidq->packet; - tidq->packet = tidq->prev_packet; - tidq->prev_packet = tmp; - } + cs_etm__packet_swap(etm, tidq); return err; } diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index a844715a352d..9dd9e3f4ef59 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -1254,6 +1254,9 @@ void perf_evsel__exit(struct evsel *evsel) perf_thread_map__put(evsel->core.threads); zfree(&evsel->group_name); zfree(&evsel->name); + zfree(&evsel->pmu_name); + zfree(&evsel->per_pkg_mask); + zfree(&evsel->metric_events); perf_evsel__object.fini(evsel); } @@ -2357,6 +2360,10 @@ bool perf_evsel__fallback(struct evsel *evsel, int err, char *new_name; const char *sep = ":"; + /* If event has exclude user then don't exclude kernel. */ + if (evsel->core.attr.exclude_user) + return false; + /* Is there already the separator in the name. */ if (strchr(name, '/') || strchr(name, ':')) diff --git a/tools/perf/util/mem2node.c b/tools/perf/util/mem2node.c index 797d86a1ab09..c84f5841c7ab 100644 --- a/tools/perf/util/mem2node.c +++ b/tools/perf/util/mem2node.c @@ -1,5 +1,6 @@ #include <errno.h> #include <inttypes.h> +#include <asm/bug.h> #include <linux/bitmap.h> #include <linux/kernel.h> #include <linux/zalloc.h> @@ -95,7 +96,7 @@ int mem2node__init(struct mem2node *map, struct perf_env *env) /* Cut unused entries, due to merging. */ tmp_entries = realloc(entries, sizeof(*entries) * j); - if (tmp_entries) + if (tmp_entries || WARN_ON_ONCE(j == 0)) entries = tmp_entries; for (i = 0; i < j; i++) { diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c index 940a6e7a6854..7753c3091478 100644 --- a/tools/perf/util/metricgroup.c +++ b/tools/perf/util/metricgroup.c @@ -174,6 +174,7 @@ static int metricgroup__setup_events(struct list_head *groups, if (!evsel) { pr_debug("Cannot resolve %s: %s\n", eg->metric_name, eg->metric_expr); + free(metric_events); continue; } for (i = 0; i < eg->idnum; i++) @@ -181,11 +182,13 @@ static int metricgroup__setup_events(struct list_head *groups, me = metricgroup__lookup(metric_events_list, evsel, true); if (!me) { ret = -ENOMEM; + free(metric_events); break; } expr = malloc(sizeof(struct metric_expr)); if (!expr) { ret = -ENOMEM; + free(metric_events); break; } expr->metric_expr = eg->metric_expr; diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 759a99f723fc..2d651c93b476 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -1344,7 +1344,7 @@ int parse_events_add_pmu(struct parse_events_state *parse_state, evsel = __add_event(list, &parse_state->idx, &attr, NULL, pmu, NULL, auto_merge_stats, NULL); if (evsel) { - evsel->pmu_name = name; + evsel->pmu_name = name ? strdup(name) : NULL; evsel->use_uncore_alias = use_uncore_alias; return 0; } else { @@ -1385,7 +1385,7 @@ int parse_events_add_pmu(struct parse_events_state *parse_state, evsel->snapshot = info.snapshot; evsel->metric_expr = info.metric_expr; evsel->metric_name = info.metric_name; - evsel->pmu_name = name; + evsel->pmu_name = name ? strdup(name) : NULL; evsel->use_uncore_alias = use_uncore_alias; evsel->percore = config_term_percore(&evsel->config_terms); } @@ -1505,12 +1505,11 @@ parse_events__set_leader_for_uncore_aliase(char *name, struct list_head *list, * event. That can be used to distinguish the leader from * other members, even they have the same event name. */ - if ((leader != evsel) && (leader->pmu_name == evsel->pmu_name)) { + if ((leader != evsel) && + !strcmp(leader->pmu_name, evsel->pmu_name)) { is_leader = false; continue; } - /* The name is always alias name */ - WARN_ON(strcmp(leader->name, evsel->name)); /* Store the leader event for each PMU */ leaders[nr_pmu++] = (uintptr_t) evsel; diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index 43d1d410854a..4027906fd3e3 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -2788,7 +2788,7 @@ static char *prefix_if_not_in(const char *pre, char *str) return str; if (asprintf(&n, "%s,%s", pre, str) < 0) - return NULL; + n = NULL; free(str); return n; diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index 66f4be1df573..2ec0a32da579 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -1449,6 +1449,7 @@ struct kcore_copy_info { u64 first_symbol; u64 last_symbol; u64 first_module; + u64 first_module_symbol; u64 last_module_symbol; size_t phnum; struct list_head phdrs; @@ -1525,6 +1526,8 @@ static int kcore_copy__process_kallsyms(void *arg, const char *name, char type, return 0; if (strchr(name, '[')) { + if (!kci->first_module_symbol || start < kci->first_module_symbol) + kci->first_module_symbol = start; if (start > kci->last_module_symbol) kci->last_module_symbol = start; return 0; @@ -1722,6 +1725,10 @@ static int kcore_copy__calc_maps(struct kcore_copy_info *kci, const char *dir, kci->etext += page_size; } + if (kci->first_module_symbol && + (!kci->first_module || kci->first_module_symbol < kci->first_module)) + kci->first_module = kci->first_module_symbol; + kci->first_module = round_down(kci->first_module, page_size); if (kci->last_module_symbol) { diff --git a/tools/power/x86/intel_pstate_tracer/intel_pstate_tracer.py b/tools/power/x86/intel_pstate_tracer/intel_pstate_tracer.py index 2d6d342b148f..1351975d0769 100755 --- a/tools/power/x86/intel_pstate_tracer/intel_pstate_tracer.py +++ b/tools/power/x86/intel_pstate_tracer/intel_pstate_tracer.py @@ -11,11 +11,11 @@ then this utility enables and collects trace data for a user specified interval and generates performance plots. Prerequisites: - Python version 2.7.x + Python version 2.7.x or higher gnuplot 5.0 or higher - gnuplot-py 1.8 + gnuplot-py 1.8 or higher (Most of the distributions have these required packages. They may be called - gnuplot-py, phython-gnuplot. ) + gnuplot-py, phython-gnuplot or phython3-gnuplot, gnuplot-nox, ... ) HWP (Hardware P-States are disabled) Kernel config for Linux trace is enabled @@ -181,7 +181,7 @@ def plot_pstate_cpu_with_sample(): g_plot('set xlabel "Samples"') g_plot('set ylabel "P-State"') g_plot('set title "{} : cpu pstate vs. sample : {:%F %H:%M}"'.format(testname, datetime.now())) - title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).replace('\n', ' ') + title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).decode('utf-8').replace('\n', ' ') plot_str = "plot for [i in title_list] i.'.csv' using {:d}:{:d} pt 7 ps 1 title i".format(C_SAMPLE, C_TO) g_plot('title_list = "{}"'.format(title_list)) g_plot(plot_str) @@ -198,7 +198,7 @@ def plot_pstate_cpu(): # the following command is really cool, but doesn't work with the CPU masking option because it aborts on the first missing file. # plot_str = 'plot for [i=0:*] file=sprintf("cpu%03d.csv",i) title_s=sprintf("cpu%03d",i) file using 16:7 pt 7 ps 1 title title_s' # - title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).replace('\n', ' ') + title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).decode('utf-8').replace('\n', ' ') plot_str = "plot for [i in title_list] i.'.csv' using {:d}:{:d} pt 7 ps 1 title i".format(C_ELAPSED, C_TO) g_plot('title_list = "{}"'.format(title_list)) g_plot(plot_str) @@ -212,7 +212,7 @@ def plot_load_cpu(): g_plot('set ylabel "CPU load (percent)"') g_plot('set title "{} : cpu loads : {:%F %H:%M}"'.format(testname, datetime.now())) - title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).replace('\n', ' ') + title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).decode('utf-8').replace('\n', ' ') plot_str = "plot for [i in title_list] i.'.csv' using {:d}:{:d} pt 7 ps 1 title i".format(C_ELAPSED, C_LOAD) g_plot('title_list = "{}"'.format(title_list)) g_plot(plot_str) @@ -226,7 +226,7 @@ def plot_frequency_cpu(): g_plot('set ylabel "CPU Frequency (GHz)"') g_plot('set title "{} : cpu frequencies : {:%F %H:%M}"'.format(testname, datetime.now())) - title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).replace('\n', ' ') + title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).decode('utf-8').replace('\n', ' ') plot_str = "plot for [i in title_list] i.'.csv' using {:d}:{:d} pt 7 ps 1 title i".format(C_ELAPSED, C_FREQ) g_plot('title_list = "{}"'.format(title_list)) g_plot(plot_str) @@ -241,7 +241,7 @@ def plot_duration_cpu(): g_plot('set ylabel "Timer Duration (MilliSeconds)"') g_plot('set title "{} : cpu durations : {:%F %H:%M}"'.format(testname, datetime.now())) - title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).replace('\n', ' ') + title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).decode('utf-8').replace('\n', ' ') plot_str = "plot for [i in title_list] i.'.csv' using {:d}:{:d} pt 7 ps 1 title i".format(C_ELAPSED, C_DURATION) g_plot('title_list = "{}"'.format(title_list)) g_plot(plot_str) @@ -255,7 +255,7 @@ def plot_scaled_cpu(): g_plot('set ylabel "Scaled Busy (Unitless)"') g_plot('set title "{} : cpu scaled busy : {:%F %H:%M}"'.format(testname, datetime.now())) - title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).replace('\n', ' ') + title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).decode('utf-8').replace('\n', ' ') plot_str = "plot for [i in title_list] i.'.csv' using {:d}:{:d} pt 7 ps 1 title i".format(C_ELAPSED, C_SCALED) g_plot('title_list = "{}"'.format(title_list)) g_plot(plot_str) @@ -269,7 +269,7 @@ def plot_boost_cpu(): g_plot('set ylabel "CPU IO Boost (percent)"') g_plot('set title "{} : cpu io boost : {:%F %H:%M}"'.format(testname, datetime.now())) - title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).replace('\n', ' ') + title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).decode('utf-8').replace('\n', ' ') plot_str = "plot for [i in title_list] i.'.csv' using {:d}:{:d} pt 7 ps 1 title i".format(C_ELAPSED, C_BOOST) g_plot('title_list = "{}"'.format(title_list)) g_plot(plot_str) @@ -283,7 +283,7 @@ def plot_ghz_cpu(): g_plot('set ylabel "TSC Frequency (GHz)"') g_plot('set title "{} : cpu TSC Frequencies (Sanity check calculation) : {:%F %H:%M}"'.format(testname, datetime.now())) - title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).replace('\n', ' ') + title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).decode('utf-8').replace('\n', ' ') plot_str = "plot for [i in title_list] i.'.csv' using {:d}:{:d} pt 7 ps 1 title i".format(C_ELAPSED, C_GHZ) g_plot('title_list = "{}"'.format(title_list)) g_plot(plot_str) diff --git a/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c b/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c index 2e233613d1fc..7fa4595d2b66 100644 --- a/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c +++ b/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c @@ -131,6 +131,7 @@ int bpf_testcb(struct bpf_sock_ops *skops) g.bytes_received = skops->bytes_received; g.bytes_acked = skops->bytes_acked; } + g.num_close_events++; bpf_map_update_elem(&global_map, &key, &g, BPF_ANY); } diff --git a/tools/testing/selftests/bpf/test_tcpbpf.h b/tools/testing/selftests/bpf/test_tcpbpf.h index 7bcfa6207005..6220b95cbd02 100644 --- a/tools/testing/selftests/bpf/test_tcpbpf.h +++ b/tools/testing/selftests/bpf/test_tcpbpf.h @@ -13,5 +13,6 @@ struct tcpbpf_globals { __u64 bytes_received; __u64 bytes_acked; __u32 num_listen; + __u32 num_close_events; }; #endif diff --git a/tools/testing/selftests/bpf/test_tcpbpf_user.c b/tools/testing/selftests/bpf/test_tcpbpf_user.c index 716b4e3be581..3ae127620463 100644 --- a/tools/testing/selftests/bpf/test_tcpbpf_user.c +++ b/tools/testing/selftests/bpf/test_tcpbpf_user.c @@ -16,6 +16,9 @@ #include "test_tcpbpf.h" +/* 3 comes from one listening socket + both ends of the connection */ +#define EXPECTED_CLOSE_EVENTS 3 + #define EXPECT_EQ(expected, actual, fmt) \ do { \ if ((expected) != (actual)) { \ @@ -23,13 +26,14 @@ " Actual: %" fmt "\n" \ " Expected: %" fmt "\n", \ (actual), (expected)); \ - goto err; \ + ret--; \ } \ } while (0) int verify_result(const struct tcpbpf_globals *result) { __u32 expected_events; + int ret = 0; expected_events = ((1 << BPF_SOCK_OPS_TIMEOUT_INIT) | (1 << BPF_SOCK_OPS_RWND_INIT) | @@ -48,15 +52,15 @@ int verify_result(const struct tcpbpf_globals *result) EXPECT_EQ(0x80, result->bad_cb_test_rv, PRIu32); EXPECT_EQ(0, result->good_cb_test_rv, PRIu32); EXPECT_EQ(1, result->num_listen, PRIu32); + EXPECT_EQ(EXPECTED_CLOSE_EVENTS, result->num_close_events, PRIu32); - return 0; -err: - return -1; + return ret; } int verify_sockopt_result(int sock_map_fd) { __u32 key = 0; + int ret = 0; int res; int rv; @@ -69,9 +73,7 @@ int verify_sockopt_result(int sock_map_fd) rv = bpf_map_lookup_elem(sock_map_fd, &key, &res); EXPECT_EQ(0, rv, "d"); EXPECT_EQ(1, res, "d"); - return 0; -err: - return -1; + return ret; } static int bpf_find_map(const char *test, struct bpf_object *obj, @@ -96,6 +98,7 @@ int main(int argc, char **argv) int error = EXIT_FAILURE; struct bpf_object *obj; int cg_fd = -1; + int retry = 10; __u32 key = 0; int rv; @@ -134,12 +137,20 @@ int main(int argc, char **argv) if (sock_map_fd < 0) goto err; +retry_lookup: rv = bpf_map_lookup_elem(map_fd, &key, &g); if (rv != 0) { printf("FAILED: bpf_map_lookup_elem returns %d\n", rv); goto err; } + if (g.num_close_events != EXPECTED_CLOSE_EVENTS && retry--) { + printf("Unexpected number of close events (%d), retrying!\n", + g.num_close_events); + usleep(100); + goto retry_lookup; + } + if (verify_result(&g)) { printf("FAILED: Wrong stats\n"); goto err; diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-glob.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-glob.tc index 27a54a17da65..f4e92afab14b 100644 --- a/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-glob.tc +++ b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-glob.tc @@ -30,7 +30,7 @@ ftrace_filter_check '*schedule*' '^.*schedule.*$' ftrace_filter_check 'schedule*' '^schedule.*$' # filter by *mid*end -ftrace_filter_check '*aw*lock' '.*aw.*lock$' +ftrace_filter_check '*pin*lock' '.*pin.*lock$' # filter by start*mid* ftrace_filter_check 'mutex*try*' '^mutex.*try.*' diff --git a/tools/testing/selftests/ptrace/Makefile b/tools/testing/selftests/ptrace/Makefile index c0b7f89f0930..2f1f532c39db 100644 --- a/tools/testing/selftests/ptrace/Makefile +++ b/tools/testing/selftests/ptrace/Makefile @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0-only -CFLAGS += -iquote../../../../include/uapi -Wall +CFLAGS += -std=c99 -pthread -iquote../../../../include/uapi -Wall -TEST_GEN_PROGS := get_syscall_info peeksiginfo +TEST_GEN_PROGS := get_syscall_info peeksiginfo vmaccess include ../lib.mk diff --git a/tools/testing/selftests/ptrace/vmaccess.c b/tools/testing/selftests/ptrace/vmaccess.c new file mode 100644 index 000000000000..4db327b44586 --- /dev/null +++ b/tools/testing/selftests/ptrace/vmaccess.c @@ -0,0 +1,86 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Copyright (c) 2020 Bernd Edlinger <bernd.edlinger@xxxxxxxxxx> + * All rights reserved. + * + * Check whether /proc/$pid/mem can be accessed without causing deadlocks + * when de_thread is blocked with ->cred_guard_mutex held. + */ + +#include "../kselftest_harness.h" +#include <stdio.h> +#include <fcntl.h> +#include <pthread.h> +#include <signal.h> +#include <unistd.h> +#include <sys/ptrace.h> + +static void *thread(void *arg) +{ + ptrace(PTRACE_TRACEME, 0, 0L, 0L); + return NULL; +} + +TEST(vmaccess) +{ + int f, pid = fork(); + char mm[64]; + + if (!pid) { + pthread_t pt; + + pthread_create(&pt, NULL, thread, NULL); + pthread_join(pt, NULL); + execlp("true", "true", NULL); + } + + sleep(1); + sprintf(mm, "/proc/%d/mem", pid); + f = open(mm, O_RDONLY); + ASSERT_GE(f, 0); + close(f); + f = kill(pid, SIGCONT); + ASSERT_EQ(f, 0); +} + +TEST(attach) +{ + int s, k, pid = fork(); + + if (!pid) { + pthread_t pt; + + pthread_create(&pt, NULL, thread, NULL); + pthread_join(pt, NULL); + execlp("sleep", "sleep", "2", NULL); + } + + sleep(1); + k = ptrace(PTRACE_ATTACH, pid, 0L, 0L); + ASSERT_EQ(errno, EAGAIN); + ASSERT_EQ(k, -1); + k = waitpid(-1, &s, WNOHANG); + ASSERT_NE(k, -1); + ASSERT_NE(k, 0); + ASSERT_NE(k, pid); + ASSERT_EQ(WIFEXITED(s), 1); + ASSERT_EQ(WEXITSTATUS(s), 0); + sleep(1); + k = ptrace(PTRACE_ATTACH, pid, 0L, 0L); + ASSERT_EQ(k, 0); + k = waitpid(-1, &s, 0); + ASSERT_EQ(k, pid); + ASSERT_EQ(WIFSTOPPED(s), 1); + ASSERT_EQ(WSTOPSIG(s), SIGSTOP); + k = ptrace(PTRACE_DETACH, pid, 0L, 0L); + ASSERT_EQ(k, 0); + k = waitpid(-1, &s, 0); + ASSERT_EQ(k, pid); + ASSERT_EQ(WIFEXITED(s), 1); + ASSERT_EQ(WEXITSTATUS(s), 0); + k = waitpid(-1, NULL, 0); + ASSERT_EQ(k, -1); + ASSERT_EQ(errno, ECHILD); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/x86/syscall_nt.c b/tools/testing/selftests/x86/syscall_nt.c index 02309a195041..a765f62ee766 100644 --- a/tools/testing/selftests/x86/syscall_nt.c +++ b/tools/testing/selftests/x86/syscall_nt.c @@ -59,6 +59,7 @@ static void do_it(unsigned long extraflags) set_eflags(get_eflags() | extraflags); syscall(SYS_getpid); flags = get_eflags(); + set_eflags(X86_EFLAGS_IF | X86_EFLAGS_FIXED); if ((flags & extraflags) == extraflags) { printf("[OK]\tThe syscall worked and flags are still set\n"); } else { diff --git a/virt/kvm/arm/mmio.c b/virt/kvm/arm/mmio.c index f274fabb4301..1e9ec878d56d 100644 --- a/virt/kvm/arm/mmio.c +++ b/virt/kvm/arm/mmio.c @@ -130,7 +130,7 @@ static int decode_hsr(struct kvm_vcpu *vcpu, bool *is_write, int *len) bool sign_extend; bool sixty_four; - if (kvm_vcpu_dabt_iss1tw(vcpu)) { + if (kvm_vcpu_abt_iss1tw(vcpu)) { /* page table accesses IO mem: tell guest to fix its TTBR */ kvm_inject_dabt(vcpu, kvm_vcpu_get_hfar(vcpu)); return 1; diff --git a/virt/kvm/arm/mmu.c b/virt/kvm/arm/mmu.c index 1e1c4f6a85c7..8700402f3000 100644 --- a/virt/kvm/arm/mmu.c +++ b/virt/kvm/arm/mmu.c @@ -1690,7 +1690,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, unsigned long vma_pagesize, flags = 0; write_fault = kvm_is_write_fault(vcpu); - exec_fault = kvm_vcpu_trap_is_iabt(vcpu); + exec_fault = kvm_vcpu_trap_is_exec_fault(vcpu); VM_BUG_ON(write_fault && exec_fault); if (fault_status == FSC_PERM && !write_fault && !exec_fault) { diff --git a/virt/kvm/arm/vgic/vgic-init.c b/virt/kvm/arm/vgic/vgic-init.c index 6f50c429196d..689910153889 100644 --- a/virt/kvm/arm/vgic/vgic-init.c +++ b/virt/kvm/arm/vgic/vgic-init.c @@ -177,6 +177,7 @@ static int kvm_vgic_dist_init(struct kvm *kvm, unsigned int nr_spis) break; default: kfree(dist->spis); + dist->spis = NULL; return -EINVAL; } } @@ -357,6 +358,12 @@ void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu) { struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; + /* + * Retire all pending LPIs on this vcpu anyway as we're + * going to destroy it. + */ + vgic_flush_pending_lpis(vcpu); + INIT_LIST_HEAD(&vgic_cpu->ap_list_head); } @@ -368,10 +375,10 @@ static void __kvm_vgic_destroy(struct kvm *kvm) vgic_debug_destroy(kvm); - kvm_vgic_dist_destroy(kvm); - kvm_for_each_vcpu(i, vcpu, kvm) kvm_vgic_vcpu_destroy(vcpu); + + kvm_vgic_dist_destroy(kvm); } void kvm_vgic_destroy(struct kvm *kvm) diff --git a/virt/kvm/arm/vgic/vgic-its.c b/virt/kvm/arm/vgic/vgic-its.c index f8ad7096555d..35be0e2a4639 100644 --- a/virt/kvm/arm/vgic/vgic-its.c +++ b/virt/kvm/arm/vgic/vgic-its.c @@ -96,14 +96,21 @@ static struct vgic_irq *vgic_add_lpi(struct kvm *kvm, u32 intid, * We "cache" the configuration table entries in our struct vgic_irq's. * However we only have those structs for mapped IRQs, so we read in * the respective config data from memory here upon mapping the LPI. + * + * Should any of these fail, behave as if we couldn't create the LPI + * by dropping the refcount and returning the error. */ ret = update_lpi_config(kvm, irq, NULL, false); - if (ret) + if (ret) { + vgic_put_irq(kvm, irq); return ERR_PTR(ret); + } ret = vgic_v3_lpi_sync_pending_status(kvm, irq); - if (ret) + if (ret) { + vgic_put_irq(kvm, irq); return ERR_PTR(ret); + } return irq; } diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 4eed7fd8db93..1dfa49d26de9 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -185,6 +185,7 @@ bool kvm_is_reserved_pfn(kvm_pfn_t pfn) */ if (pfn_valid(pfn)) return PageReserved(pfn_to_page(pfn)) && + !is_zero_pfn(pfn) && !kvm_is_zone_device_pfn(pfn); return true;