diff options
105 files changed, 881 insertions, 513 deletions
diff --git a/Documentation/admin-guide/pm/intel_pstate.rst b/Documentation/admin-guide/pm/intel_pstate.rst index 7adef969ffee..cdd1a9a7f9a2 100644 --- a/Documentation/admin-guide/pm/intel_pstate.rst +++ b/Documentation/admin-guide/pm/intel_pstate.rst @@ -564,8 +564,8 @@ Energy-Performance Preference (EPP) knob (if supported) or its Energy-Performance Bias (EPB) knob. It is also possible to write a positive integer value between 0 to 255, if the EPP feature is present. If the EPP feature is not present, writing integer value to this attribute is not -supported. In this case, user can use - "/sys/devices/system/cpu/cpu*/power/energy_perf_bias" interface. +supported. In this case, user can use the +"/sys/devices/system/cpu/cpu*/power/energy_perf_bias" interface. [Note that tasks may by migrated from one CPU to another by the scheduler's load-balancing algorithm and if different energy vs performance hints are diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile index b45f0124cc16..130569f90c54 100644 --- a/arch/arm64/Makefile +++ b/arch/arm64/Makefile @@ -82,8 +82,8 @@ endif # compiler to generate them and consequently to break the single image contract # we pass it only to the assembler. This option is utilized only in case of non # integrated assemblers. -ifneq ($(CONFIG_AS_HAS_ARMV8_4), y) -branch-prot-flags-$(CONFIG_AS_HAS_PAC) += -Wa,-march=armv8.3-a +ifeq ($(CONFIG_AS_HAS_PAC), y) +asm-arch := armv8.3-a endif endif @@ -91,7 +91,12 @@ KBUILD_CFLAGS += $(branch-prot-flags-y) ifeq ($(CONFIG_AS_HAS_ARMV8_4), y) # make sure to pass the newest target architecture to -march. -KBUILD_CFLAGS += -Wa,-march=armv8.4-a +asm-arch := armv8.4-a +endif + +ifdef asm-arch +KBUILD_CFLAGS += -Wa,-march=$(asm-arch) \ + -DARM64_ASM_ARCH='"$(asm-arch)"' endif ifeq ($(CONFIG_SHADOW_CALL_STACK), y) @@ -165,7 +170,8 @@ zinstall install: PHONY += vdso_install vdso_install: $(Q)$(MAKE) $(build)=arch/arm64/kernel/vdso $@ - $(Q)$(MAKE) $(build)=arch/arm64/kernel/vdso32 $@ + $(if $(CONFIG_COMPAT_VDSO), \ + $(Q)$(MAKE) $(build)=arch/arm64/kernel/vdso32 $@) # We use MRPROPER_FILES and CLEAN_FILES now archclean: diff --git a/arch/arm64/include/asm/compiler.h b/arch/arm64/include/asm/compiler.h index 51a7ce87cdfe..6fb2e6bcc392 100644 --- a/arch/arm64/include/asm/compiler.h +++ b/arch/arm64/include/asm/compiler.h @@ -2,6 +2,12 @@ #ifndef __ASM_COMPILER_H #define __ASM_COMPILER_H +#ifdef ARM64_ASM_ARCH +#define ARM64_ASM_PREAMBLE ".arch " ARM64_ASM_ARCH "\n" +#else +#define ARM64_ASM_PREAMBLE +#endif + /* * The EL0/EL1 pointer bits used by a pointer authentication code. * This is dependent on TBI0/TBI1 being enabled, or bits 63:56 would also apply. diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h index 51c1d9918999..1da8e3dc4455 100644 --- a/arch/arm64/include/asm/kvm_arm.h +++ b/arch/arm64/include/asm/kvm_arm.h @@ -71,11 +71,12 @@ * IMO: Override CPSR.I and enable signaling with VI * FMO: Override CPSR.F and enable signaling with VF * SWIO: Turn set/way invalidates into set/way clean+invalidate + * PTW: Take a stage2 fault if a stage1 walk steps in device memory */ #define HCR_GUEST_FLAGS (HCR_TSC | HCR_TSW | HCR_TWE | HCR_TWI | HCR_VM | \ HCR_BSU_IS | HCR_FB | HCR_TAC | \ HCR_AMO | HCR_SWIO | HCR_TIDCP | HCR_RW | HCR_TLOR | \ - HCR_FMO | HCR_IMO) + HCR_FMO | HCR_IMO | HCR_PTW ) #define HCR_VIRT_EXCP_MASK (HCR_VSE | HCR_VI | HCR_VF) #define HCR_HOST_NVHE_FLAGS (HCR_RW | HCR_API | HCR_APK) #define HCR_HOST_VHE_FLAGS (HCR_RW | HCR_TGE | HCR_E2H) diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h index fb1a922b31ba..6f98fbd0ac81 100644 --- a/arch/arm64/include/asm/kvm_asm.h +++ b/arch/arm64/include/asm/kvm_asm.h @@ -169,6 +169,34 @@ extern char __smccc_workaround_1_smc[__SMCCC_WORKAROUND_1_SMC_SZ]; *__hyp_this_cpu_ptr(sym); \ }) +#define __KVM_EXTABLE(from, to) \ + " .pushsection __kvm_ex_table, \"a\"\n" \ + " .align 3\n" \ + " .long (" #from " - .), (" #to " - .)\n" \ + " .popsection\n" + + +#define __kvm_at(at_op, addr) \ +( { \ + int __kvm_at_err = 0; \ + u64 spsr, elr; \ + asm volatile( \ + " mrs %1, spsr_el2\n" \ + " mrs %2, elr_el2\n" \ + "1: at "at_op", %3\n" \ + " isb\n" \ + " b 9f\n" \ + "2: msr spsr_el2, %1\n" \ + " msr elr_el2, %2\n" \ + " mov %w0, %4\n" \ + "9:\n" \ + __KVM_EXTABLE(1b, 2b) \ + : "+r" (__kvm_at_err), "=&r" (spsr), "=&r" (elr) \ + : "r" (addr), "i" (-EFAULT)); \ + __kvm_at_err; \ +} ) + + #else /* __ASSEMBLY__ */ .macro hyp_adr_this_cpu reg, sym, tmp @@ -193,6 +221,21 @@ extern char __smccc_workaround_1_smc[__SMCCC_WORKAROUND_1_SMC_SZ]; ldr \vcpu, [\ctxt, #HOST_CONTEXT_VCPU] .endm +/* + * KVM extable for unexpected exceptions. + * In the same format _asm_extable, but output to a different section so that + * it can be mapped to EL2. The KVM version is not sorted. The caller must + * ensure: + * x18 has the hypervisor value to allow any Shadow-Call-Stack instrumented + * code to write to it, and that SPSR_EL2 and ELR_EL2 are restored by the fixup. + */ +.macro _kvm_extable, from, to + .pushsection __kvm_ex_table, "a" + .align 3 + .long (\from - .), (\to - .) + .popsection +.endm + #endif #endif /* __ARM_KVM_ASM_H__ */ diff --git a/arch/arm64/include/asm/tlbflush.h b/arch/arm64/include/asm/tlbflush.h index d493174415db..cc3f5a33ff9c 100644 --- a/arch/arm64/include/asm/tlbflush.h +++ b/arch/arm64/include/asm/tlbflush.h @@ -28,14 +28,16 @@ * not. The macros handles invoking the asm with or without the * register argument as appropriate. */ -#define __TLBI_0(op, arg) asm ("tlbi " #op "\n" \ +#define __TLBI_0(op, arg) asm (ARM64_ASM_PREAMBLE \ + "tlbi " #op "\n" \ ALTERNATIVE("nop\n nop", \ "dsb ish\n tlbi " #op, \ ARM64_WORKAROUND_REPEAT_TLBI, \ CONFIG_ARM64_WORKAROUND_REPEAT_TLBI) \ : : ) -#define __TLBI_1(op, arg) asm ("tlbi " #op ", %0\n" \ +#define __TLBI_1(op, arg) asm (ARM64_ASM_PREAMBLE \ + "tlbi " #op ", %0\n" \ ALTERNATIVE("nop\n nop", \ "dsb ish\n tlbi " #op ", %0", \ ARM64_WORKAROUND_REPEAT_TLBI, \ diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c index 1886a02c3f50..d0076c2159e6 100644 --- a/arch/arm64/kernel/cpuinfo.c +++ b/arch/arm64/kernel/cpuinfo.c @@ -327,7 +327,6 @@ static void cpuinfo_detect_icache_policy(struct cpuinfo_arm64 *info) set_bit(ICACHEF_VPIPT, &__icache_flags); break; default: - fallthrough; case ICACHE_POLICY_VIPT: /* Assume aliasing */ set_bit(ICACHEF_ALIASING, &__icache_flags); diff --git a/arch/arm64/kernel/image-vars.h b/arch/arm64/kernel/image-vars.h index 9e897c500237..8982b68289b7 100644 --- a/arch/arm64/kernel/image-vars.h +++ b/arch/arm64/kernel/image-vars.h @@ -103,6 +103,10 @@ KVM_NVHE_ALIAS(vgic_v3_cpuif_trap); KVM_NVHE_ALIAS(gic_pmr_sync); #endif +/* EL2 exception handling */ +KVM_NVHE_ALIAS(__start___kvm_ex_table); +KVM_NVHE_ALIAS(__stop___kvm_ex_table); + #endif /* CONFIG_KVM */ #endif /* __ARM64_KERNEL_IMAGE_VARS_H */ diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S index ec8e894684a7..7cba7623fcec 100644 --- a/arch/arm64/kernel/vmlinux.lds.S +++ b/arch/arm64/kernel/vmlinux.lds.S @@ -20,6 +20,13 @@ ENTRY(_text) jiffies = jiffies_64; + +#define HYPERVISOR_EXTABLE \ + . = ALIGN(SZ_8); \ + __start___kvm_ex_table = .; \ + *(__kvm_ex_table) \ + __stop___kvm_ex_table = .; + #define HYPERVISOR_TEXT \ /* \ * Align to 4 KB so that \ @@ -35,6 +42,7 @@ jiffies = jiffies_64; __hyp_idmap_text_end = .; \ __hyp_text_start = .; \ *(.hyp.text) \ + HYPERVISOR_EXTABLE \ __hyp_text_end = .; #define IDMAP_TEXT \ diff --git a/arch/arm64/kvm/hyp/entry.S b/arch/arm64/kvm/hyp/entry.S index ee32a7743389..76e7eaf4675e 100644 --- a/arch/arm64/kvm/hyp/entry.S +++ b/arch/arm64/kvm/hyp/entry.S @@ -196,20 +196,23 @@ alternative_endif // This is our single instruction exception window. A pending // SError is guaranteed to occur at the earliest when we unmask // it, and at the latest just after the ISB. - .global abort_guest_exit_start abort_guest_exit_start: isb - .global abort_guest_exit_end abort_guest_exit_end: msr daifset, #4 // Mask aborts + ret + + _kvm_extable abort_guest_exit_start, 9997f + _kvm_extable abort_guest_exit_end, 9997f +9997: + msr daifset, #4 // Mask aborts + mov x0, #(1 << ARM_EXIT_WITH_SERROR_BIT) - // If the exception took place, restore the EL1 exception - // context so that we can report some information. - // Merge the exception code with the SError pending bit. - tbz x0, #ARM_EXIT_WITH_SERROR_BIT, 1f + // restore the EL1 exception context so that we can report some + // information. Merge the exception code with the SError pending bit. msr elr_el2, x2 msr esr_el2, x3 msr spsr_el2, x4 diff --git a/arch/arm64/kvm/hyp/hyp-entry.S b/arch/arm64/kvm/hyp/hyp-entry.S index 689fccbc9de7..46b4dab933d0 100644 --- a/arch/arm64/kvm/hyp/hyp-entry.S +++ b/arch/arm64/kvm/hyp/hyp-entry.S @@ -15,6 +15,30 @@ #include <asm/kvm_mmu.h> #include <asm/mmu.h> +.macro save_caller_saved_regs_vect + /* x0 and x1 were saved in the vector entry */ + stp x2, x3, [sp, #-16]! + stp x4, x5, [sp, #-16]! + stp x6, x7, [sp, #-16]! + stp x8, x9, [sp, #-16]! + stp x10, x11, [sp, #-16]! + stp x12, x13, [sp, #-16]! + stp x14, x15, [sp, #-16]! + stp x16, x17, [sp, #-16]! +.endm + +.macro restore_caller_saved_regs_vect + ldp x16, x17, [sp], #16 + ldp x14, x15, [sp], #16 + ldp x12, x13, [sp], #16 + ldp x10, x11, [sp], #16 + ldp x8, x9, [sp], #16 + ldp x6, x7, [sp], #16 + ldp x4, x5, [sp], #16 + ldp x2, x3, [sp], #16 + ldp x0, x1, [sp], #16 +.endm + .text .macro do_el2_call @@ -143,13 +167,19 @@ el1_error: b __guest_exit el2_sync: - /* Check for illegal exception return, otherwise panic */ + /* Check for illegal exception return */ mrs x0, spsr_el2 + tbnz x0, #20, 1f - /* if this was something else, then panic! */ - tst x0, #PSR_IL_BIT - b.eq __hyp_panic + save_caller_saved_regs_vect + stp x29, x30, [sp, #-16]! + bl kvm_unexpected_el2_exception + ldp x29, x30, [sp], #16 + restore_caller_saved_regs_vect + eret + +1: /* Let's attempt a recovery from the illegal exception return */ get_vcpu_ptr x1, x0 mov x0, #ARM_EXCEPTION_IL @@ -157,27 +187,14 @@ el2_sync: el2_error: - ldp x0, x1, [sp], #16 + save_caller_saved_regs_vect + stp x29, x30, [sp, #-16]! + + bl kvm_unexpected_el2_exception + + ldp x29, x30, [sp], #16 + restore_caller_saved_regs_vect - /* - * Only two possibilities: - * 1) Either we come from the exit path, having just unmasked - * PSTATE.A: change the return code to an EL2 fault, and - * carry on, as we're already in a sane state to handle it. - * 2) Or we come from anywhere else, and that's a bug: we panic. - * - * For (1), x0 contains the original return code and x1 doesn't - * contain anything meaningful at that stage. We can reuse them - * as temp registers. - * For (2), who cares? - */ - mrs x0, elr_el2 - adr x1, abort_guest_exit_start - cmp x0, x1 - adr x1, abort_guest_exit_end - ccmp x0, x1, #4, ne - b.ne __hyp_panic - mov x0, #(1 << ARM_EXIT_WITH_SERROR_BIT) eret sb diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h index 426ef65601dd..5b6b8fa00f0a 100644 --- a/arch/arm64/kvm/hyp/include/hyp/switch.h +++ b/arch/arm64/kvm/hyp/include/hyp/switch.h @@ -17,6 +17,7 @@ #include <asm/barrier.h> #include <asm/cpufeature.h> +#include <asm/extable.h> #include <asm/kprobes.h> #include <asm/kvm_asm.h> #include <asm/kvm_emulate.h> @@ -29,6 +30,9 @@ extern const char __hyp_panic_string[]; +extern struct exception_table_entry __start___kvm_ex_table; +extern struct exception_table_entry __stop___kvm_ex_table; + /* Check whether the FP regs were dirtied while in the host-side run loop: */ static inline bool update_fp_enabled(struct kvm_vcpu *vcpu) { @@ -142,10 +146,10 @@ static inline bool __translate_far_to_hpfar(u64 far, u64 *hpfar) * saved the guest context yet, and we may return early... */ par = read_sysreg(par_el1); - asm volatile("at s1e1r, %0" : : "r" (far)); - isb(); - - tmp = read_sysreg(par_el1); + if (!__kvm_at("s1e1r", far)) + tmp = read_sysreg(par_el1); + else + tmp = SYS_PAR_EL1_F; /* back to the guest */ write_sysreg(par, par_el1); if (unlikely(tmp & SYS_PAR_EL1_F)) @@ -508,4 +512,31 @@ static inline void __set_host_arch_workaround_state(struct kvm_vcpu *vcpu) #endif } +static inline void __kvm_unexpected_el2_exception(void) +{ + unsigned long addr, fixup; + struct kvm_cpu_context *host_ctxt; + struct exception_table_entry *entry, *end; + unsigned long elr_el2 = read_sysreg(elr_el2); + + entry = hyp_symbol_addr(__start___kvm_ex_table); + end = hyp_symbol_addr(__stop___kvm_ex_table); + host_ctxt = &__hyp_this_cpu_ptr(kvm_host_data)->host_ctxt; + + while (entry < end) { + addr = (unsigned long)&entry->insn + entry->insn; + fixup = (unsigned long)&entry->fixup + entry->fixup; + + if (addr != elr_el2) { + entry++; + continue; + } + + write_sysreg(fixup, elr_el2); + return; + } + + hyp_panic(host_ctxt); +} + #endif /* __ARM64_KVM_HYP_SWITCH_H__ */ diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c index 341be2f2f312..0970442d2dbc 100644 --- a/arch/arm64/kvm/hyp/nvhe/switch.c +++ b/arch/arm64/kvm/hyp/nvhe/switch.c @@ -270,3 +270,8 @@ void __noreturn hyp_panic(struct kvm_cpu_context *host_ctxt) read_sysreg(hpfar_el2), par, vcpu); unreachable(); } + +asmlinkage void kvm_unexpected_el2_exception(void) +{ + return __kvm_unexpected_el2_exception(); +} diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c index c52d714e0d75..c1da4f86ccac 100644 --- a/arch/arm64/kvm/hyp/vhe/switch.c +++ b/arch/arm64/kvm/hyp/vhe/switch.c @@ -217,3 +217,8 @@ void __noreturn hyp_panic(struct kvm_cpu_context *host_ctxt) __hyp_call_panic(spsr, elr, par, host_ctxt); unreachable(); } + +asmlinkage void kvm_unexpected_el2_exception(void) +{ + return __kvm_unexpected_el2_exception(); +} diff --git a/arch/s390/include/asm/percpu.h b/arch/s390/include/asm/percpu.h index 50b4ce8cddfd..918f0ba4f4d2 100644 --- a/arch/s390/include/asm/percpu.h +++ b/arch/s390/include/asm/percpu.h @@ -29,7 +29,7 @@ typedef typeof(pcp) pcp_op_T__; \ pcp_op_T__ old__, new__, prev__; \ pcp_op_T__ *ptr__; \ - preempt_disable(); \ + preempt_disable_notrace(); \ ptr__ = raw_cpu_ptr(&(pcp)); \ prev__ = *ptr__; \ do { \ @@ -37,7 +37,7 @@ new__ = old__ op (val); \ prev__ = cmpxchg(ptr__, old__, new__); \ } while (prev__ != old__); \ - preempt_enable(); \ + preempt_enable_notrace(); \ new__; \ }) @@ -68,7 +68,7 @@ typedef typeof(pcp) pcp_op_T__; \ pcp_op_T__ val__ = (val); \ pcp_op_T__ old__, *ptr__; \ - preempt_disable(); \ + preempt_disable_notrace(); \ ptr__ = raw_cpu_ptr(&(pcp)); \ if (__builtin_constant_p(val__) && \ ((szcast)val__ > -129) && ((szcast)val__ < 128)) { \ @@ -84,7 +84,7 @@ : [val__] "d" (val__) \ : "cc"); \ } \ - preempt_enable(); \ + preempt_enable_notrace(); \ } #define this_cpu_add_4(pcp, val) arch_this_cpu_add(pcp, val, "laa", "asi", int) @@ -95,14 +95,14 @@ typedef typeof(pcp) pcp_op_T__; \ pcp_op_T__ val__ = (val); \ pcp_op_T__ old__, *ptr__; \ - preempt_disable(); \ + preempt_disable_notrace(); \ ptr__ = raw_cpu_ptr(&(pcp)); \ asm volatile( \ op " %[old__],%[val__],%[ptr__]\n" \ : [old__] "=d" (old__), [ptr__] "+Q" (*ptr__) \ : [val__] "d" (val__) \ : "cc"); \ - preempt_enable(); \ + preempt_enable_notrace(); \ old__ + val__; \ }) @@ -114,14 +114,14 @@ typedef typeof(pcp) pcp_op_T__; \ pcp_op_T__ val__ = (val); \ pcp_op_T__ old__, *ptr__; \ - preempt_disable(); \ + preempt_disable_notrace(); \ ptr__ = raw_cpu_ptr(&(pcp)); \ asm volatile( \ op " %[old__],%[val__],%[ptr__]\n" \ : [old__] "=d" (old__), [ptr__] "+Q" (*ptr__) \ : [val__] "d" (val__) \ : "cc"); \ - preempt_enable(); \ + preempt_enable_notrace(); \ } #define this_cpu_and_4(pcp, val) arch_this_cpu_to_op(pcp, val, "lan") @@ -136,10 +136,10 @@ typedef typeof(pcp) pcp_op_T__; \ pcp_op_T__ ret__; \ pcp_op_T__ *ptr__; \ - preempt_disable(); \ + preempt_disable_notrace(); \ ptr__ = raw_cpu_ptr(&(pcp)); \ ret__ = cmpxchg(ptr__, oval, nval); \ - preempt_enable(); \ + preempt_enable_notrace(); \ ret__; \ }) @@ -152,10 +152,10 @@ ({ \ typeof(pcp) *ptr__; \ typeof(pcp) ret__; \ - preempt_disable(); \ + preempt_disable_notrace(); \ ptr__ = raw_cpu_ptr(&(pcp)); \ ret__ = xchg(ptr__, nval); \ - preempt_enable(); \ + preempt_enable_notrace(); \ ret__; \ }) @@ -171,11 +171,11 @@ typeof(pcp1) *p1__; \ typeof(pcp2) *p2__; \ int ret__; \ - preempt_disable(); \ + preempt_disable_notrace(); \ p1__ = raw_cpu_ptr(&(pcp1)); \ p2__ = raw_cpu_ptr(&(pcp2)); \ ret__ = __cmpxchg_double(p1__, p2__, o1__, o2__, n1__, n2__); \ - preempt_enable(); \ + preempt_enable_notrace(); \ ret__; \ }) diff --git a/arch/s390/mm/vmem.c b/arch/s390/mm/vmem.c index 1aed1a4dfc2d..eddf71c22875 100644 --- a/arch/s390/mm/vmem.c +++ b/arch/s390/mm/vmem.c @@ -402,6 +402,7 @@ static int modify_p4d_table(pgd_t *pgd, unsigned long addr, unsigned long end, pud = vmem_crst_alloc(_REGION3_ENTRY_EMPTY); if (!pud) goto out; + p4d_populate(&init_mm, p4d, pud); } ret = modify_pud_table(p4d, addr, next, add, direct); if (ret) diff --git a/drivers/acpi/acpi_apd.c b/drivers/acpi/acpi_apd.c index 4c348377a39d..806b8ce05624 100644 --- a/drivers/acpi/acpi_apd.c +++ b/drivers/acpi/acpi_apd.c @@ -99,8 +99,8 @@ static int fch_misc_setup(struct apd_private_data *pdata) if (ret < 0) return -ENOENT; - acpi_dev_get_property(adev, "is-rv", ACPI_TYPE_INTEGER, &obj); - clk_data->is_rv = obj->integer.value; + if (!acpi_dev_get_property(adev, "is-rv", ACPI_TYPE_INTEGER, &obj)) + clk_data->is_rv = obj->integer.value; list_for_each_entry(rentry, &resource_list, node) { clk_data->base = devm_ioremap(&adev->dev, rentry->res->start, diff --git a/drivers/acpi/osl.c b/drivers/acpi/osl.c index 6ad8cb05f672..4a0b07792233 100644 --- a/drivers/acpi/osl.c +++ b/drivers/acpi/osl.c @@ -350,7 +350,7 @@ void __iomem __ref pg_off = round_down(phys, PAGE_SIZE); pg_sz = round_up(phys + size, PAGE_SIZE) - pg_off; - virt = acpi_map(pg_off, pg_sz); + virt = acpi_map(phys, size); if (!virt) { mutex_unlock(&acpi_ioremap_lock); kfree(map); @@ -358,7 +358,7 @@ void __iomem __ref } INIT_LIST_HEAD(&map->list); - map->virt = virt; + map->virt = (void __iomem __force *)((unsigned long)virt & PAGE_MASK); map->phys = pg_off; map->size = pg_sz; map->track.refcount = 1; @@ -1575,11 +1575,26 @@ static acpi_status acpi_deactivate_mem_region(acpi_handle handle, u32 level, acpi_status acpi_release_memory(acpi_handle handle, struct resource *res, u32 level) { + acpi_status status; + if (!(res->flags & IORESOURCE_MEM)) return AE_TYPE; - return acpi_walk_namespace(ACPI_TYPE_REGION, handle, level, - acpi_deactivate_mem_region, NULL, res, NULL); + status = acpi_walk_namespace(ACPI_TYPE_REGION, handle, level, + acpi_deactivate_mem_region, NULL, + res, NULL); + if (ACPI_FAILURE(status)) + return status; + + /* + * Wait for all of the mappings queued up for removal by + * acpi_deactivate_mem_region() to actually go away. + */ + synchronize_rcu(); + rcu_barrier(); + flush_scheduled_work(); + + return AE_OK; } EXPORT_SYMBOL_GPL(acpi_release_memory); diff --git a/drivers/base/core.c b/drivers/base/core.c index ac1046a382bc..f6f620aa9408 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -4264,9 +4264,9 @@ static inline bool fwnode_is_primary(struct fwnode_handle *fwnode) */ void set_primary_fwnode(struct device *dev, struct fwnode_handle *fwnode) { - if (fwnode) { - struct fwnode_handle *fn = dev->fwnode; + struct fwnode_handle *fn = dev->fwnode; + if (fwnode) { if (fwnode_is_primary(fn)) fn = fn->secondary; @@ -4276,8 +4276,12 @@ void set_primary_fwnode(struct device *dev, struct fwnode_handle *fwnode) } dev->fwnode = fwnode; } else { - dev->fwnode = fwnode_is_primary(dev->fwnode) ? - dev->fwnode->secondary : NULL; + if (fwnode_is_primary(fn)) { + dev->fwnode = fn->secondary; + fn->secondary = NULL; + } else { + dev->fwnode = NULL; + } } } EXPORT_SYMBOL_GPL(set_primary_fwnode); diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c index 9dd85bea4026..205a06752ca9 100644 --- a/drivers/base/power/main.c +++ b/drivers/base/power/main.c @@ -1606,13 +1606,17 @@ static int __device_suspend(struct device *dev, pm_message_t state, bool async) } /* - * If a device configured to wake up the system from sleep states - * has been suspended at run time and there's a resume request pending - * for it, this is equivalent to the device signaling wakeup, so the - * system suspend operation should be aborted. + * Wait for possible runtime PM transitions of the device in progress + * to complete and if there's a runtime resume request pending for it, + * resume it before proceeding with invoking the system-wide suspend + * callbacks for it. + * + * If the system-wide suspend callbacks below change the configuration + * of the device, they must disable runtime PM for it or otherwise + * ensure that its runtime-resume callbacks will not be confused by that + * change in case they are invoked going forward. */ - if (pm_runtime_barrier(dev) && device_may_wakeup(dev)) - pm_wakeup_event(dev, 0); + pm_runtime_barrier(dev); if (pm_wakeup_pending()) { dev->power.direct_complete = false; diff --git a/drivers/block/loop.c b/drivers/block/loop.c index 5a9915101362..d3394191e168 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -1114,8 +1114,6 @@ static int loop_configure(struct loop_device *lo, fmode_t mode, mapping = file->f_mapping; inode = mapping->host; - size = get_loop_size(lo, file); - if ((config->info.lo_flags & ~LOOP_CONFIGURE_SETTABLE_FLAGS) != 0) { error = -EINVAL; goto out_unlock; @@ -1165,6 +1163,8 @@ static int loop_configure(struct loop_device *lo, fmode_t mode, loop_update_rotational(lo); loop_update_dio(lo); loop_sysfs_init(lo); + + size = get_loop_size(lo, file); loop_set_size(lo, size); set_blocksize(bdev, S_ISBLK(inode->i_mode) ? diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 3ff4054d6834..edf8b632e3d2 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -1363,6 +1363,8 @@ static void nbd_set_cmd_timeout(struct nbd_device *nbd, u64 timeout) nbd->tag_set.timeout = timeout * HZ; if (timeout) blk_queue_rq_timeout(nbd->disk->queue, timeout * HZ); + else + blk_queue_rq_timeout(nbd->disk->queue, 30 * HZ); } /* Must be called with config_lock held */ diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 02ab56b2a0d8..47aa90f9a7c2 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -703,8 +703,7 @@ static ssize_t show_scaling_cur_freq(struct cpufreq_policy *policy, char *buf) freq = arch_freq_get_on_cpu(policy->cpu); if (freq) ret = sprintf(buf, "%u\n", freq); - else if (cpufreq_driver && cpufreq_driver->setpolicy && - cpufreq_driver->get) + else if (cpufreq_driver->setpolicy && cpufreq_driver->get) ret = sprintf(buf, "%u\n", cpufreq_driver->get(policy->cpu)); else ret = sprintf(buf, "%u\n", policy->cur); diff --git a/drivers/cpufreq/tegra194-cpufreq.c b/drivers/cpufreq/tegra194-cpufreq.c index bae527e507e0..e1d931c457a7 100644 --- a/drivers/cpufreq/tegra194-cpufreq.c +++ b/drivers/cpufreq/tegra194-cpufreq.c @@ -56,9 +56,11 @@ struct read_counters_work { static struct workqueue_struct *read_counters_wq; -static enum cluster get_cpu_cluster(u8 cpu) +static void get_cpu_cluster(void *cluster) { - return MPIDR_AFFINITY_LEVEL(cpu_logical_map(cpu), 1); + u64 mpidr = read_cpuid_mpidr() & MPIDR_HWID_BITMASK; + + *((uint32_t *)cluster) = MPIDR_AFFINITY_LEVEL(mpidr, 1); } /* @@ -186,8 +188,10 @@ static unsigned int tegra194_get_speed(u32 cpu) static int tegra194_cpufreq_init(struct cpufreq_policy *policy) { struct tegra194_cpufreq_data *data = cpufreq_get_driver_data(); - int cl = get_cpu_cluster(policy->cpu); u32 cpu; + u32 cl; + + smp_call_function_single(policy->cpu, get_cpu_cluster, &cl, true); if (cl >= data->num_clusters) return -EINVAL; diff --git a/drivers/dma/fsldma.h b/drivers/dma/fsldma.h index 56f18ae99233..308bed0a560a 100644 --- a/drivers/dma/fsldma.h +++ b/drivers/dma/fsldma.h @@ -205,10 +205,10 @@ struct fsldma_chan { #else static u64 fsl_ioread64(const u64 __iomem *addr) { - u32 fsl_addr = lower_32_bits(addr); - u64 fsl_addr_hi = (u64)in_le32((u32 *)(fsl_addr + 1)) << 32; + u32 val_lo = in_le32((u32 __iomem *)addr); + u32 val_hi = in_le32((u32 __iomem *)addr + 1); - return fsl_addr_hi | in_le32((u32 *)fsl_addr); + return ((u64)val_hi << 32) + val_lo; } static void fsl_iowrite64(u64 val, u64 __iomem *addr) @@ -219,10 +219,10 @@ static void fsl_iowrite64(u64 val, u64 __iomem *addr) static u64 fsl_ioread64be(const u64 __iomem *addr) { - u32 fsl_addr = lower_32_bits(addr); - u64 fsl_addr_hi = (u64)in_be32((u32 *)fsl_addr) << 32; + u32 val_hi = in_be32((u32 __iomem *)addr); + u32 val_lo = in_be32((u32 __iomem *)addr + 1); - return fsl_addr_hi | in_be32((u32 *)(fsl_addr + 1)); + return ((u64)val_hi << 32) + val_lo; } static void fsl_iowrite64be(u64 val, u64 __iomem *addr) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c index 0047da06041f..414548064648 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c @@ -179,6 +179,7 @@ int amdgpu_driver_load_kms(struct drm_device *dev, unsigned long flags) case CHIP_VEGA20: case CHIP_ARCTURUS: case CHIP_SIENNA_CICHLID: + case CHIP_NAVY_FLOUNDER: /* enable runpm if runpm=1 */ if (amdgpu_runtime_pm > 0) adev->runpm = true; @@ -678,8 +679,12 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file * in the bitfields */ if (se_num == AMDGPU_INFO_MMR_SE_INDEX_MASK) se_num = 0xffffffff; + else if (se_num >= AMDGPU_GFX_MAX_SE) + return -EINVAL; if (sh_num == AMDGPU_INFO_MMR_SH_INDEX_MASK) sh_num = 0xffffffff; + else if (sh_num >= AMDGPU_GFX_MAX_SH_PER_SE) + return -EINVAL; if (info->read_mmr_reg.count > 128) return -EINVAL; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c index 7fe564275457..d8c6520ff74a 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c @@ -522,8 +522,7 @@ static int psp_asd_load(struct psp_context *psp) * add workaround to bypass it for sriov now. * TODO: add version check to make it common */ - if (amdgpu_sriov_vf(psp->adev) || - (psp->adev->asic_type == CHIP_NAVY_FLOUNDER)) + if (amdgpu_sriov_vf(psp->adev) || !psp->asd_fw) return 0; cmd = kzalloc(sizeof(struct psp_gfx_cmd_resp), GFP_KERNEL); diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c index 65997ffaed45..037a187aa42f 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c @@ -7263,10 +7263,8 @@ static void gfx_v10_0_update_medium_grain_clock_gating(struct amdgpu_device *ade def = data = RREG32_SOC15(GC, 0, mmRLC_CGTT_MGCG_OVERRIDE); data &= ~(RLC_CGTT_MGCG_OVERRIDE__GRBM_CGTT_SCLK_OVERRIDE_MASK | RLC_CGTT_MGCG_OVERRIDE__GFXIP_MGCG_OVERRIDE_MASK | - RLC_CGTT_MGCG_OVERRIDE__GFXIP_MGLS_OVERRIDE_MASK); - - /* only for Vega10 & Raven1 */ - data |= RLC_CGTT_MGCG_OVERRIDE__RLC_CGTT_SCLK_OVERRIDE_MASK; + RLC_CGTT_MGCG_OVERRIDE__GFXIP_MGLS_OVERRIDE_MASK | + RLC_CGTT_MGCG_OVERRIDE__ENABLE_CGTS_LEGACY_MASK); if (def != data) WREG32_SOC15(GC, 0, mmRLC_CGTT_MGCG_OVERRIDE, data); diff --git a/drivers/gpu/drm/amd/amdgpu/nv.c b/drivers/gpu/drm/amd/amdgpu/nv.c index da8024c2826e..ca11253e787c 100644 --- a/drivers/gpu/drm/amd/amdgpu/nv.c +++ b/drivers/gpu/drm/amd/amdgpu/nv.c @@ -364,6 +364,7 @@ nv_asic_reset_method(struct amdgpu_device *adev) switch (adev->asic_type) { case CHIP_SIENNA_CICHLID: + case CHIP_NAVY_FLOUNDER: return AMD_RESET_METHOD_MODE1; default: if (smu_baco_is_support(smu)) 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 df9338257ae0..b51c527a3f0d 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -2834,12 +2834,18 @@ static int amdgpu_dm_mode_config_init(struct amdgpu_device *adev) &dm_atomic_state_funcs); r = amdgpu_display_modeset_create_props(adev); - if (r) + if (r) { + dc_release_state(state->context); + kfree(state); return r; + } r = amdgpu_dm_audio_init(adev); - if (r) + if (r) { + dc_release_state(state->context); + kfree(state); return r; + } return 0; } @@ -2856,6 +2862,8 @@ static void amdgpu_dm_update_backlight_caps(struct amdgpu_display_manager *dm) #if defined(CONFIG_ACPI) struct amdgpu_dm_backlight_caps caps; + memset(&caps, 0, sizeof(caps)); + if (dm->backlight_caps.caps_valid) return; @@ -2894,51 +2902,50 @@ static int set_backlight_via_aux(struct dc_link *link, uint32_t brightness) return rc ? 0 : 1; } -static u32 convert_brightness(const struct amdgpu_dm_backlight_caps *caps, - const uint32_t user_brightness) +static int get_brightness_range(const struct amdgpu_dm_backlight_caps *caps, + unsigned *min, unsigned *max) { - u32 min, max, conversion_pace; - u32 brightness = user_brightness; - if (!caps) - goto out; + return 0; - if (!caps->aux_support) { - max = caps->max_input_signal; - min = caps->min_input_signal; - /* - * The brightness input is in the range 0-255 - * It needs to be rescaled to be between the - * requested min and max input signal - * It also needs to be scaled up by 0x101 to - * match the DC interface which has a range of - * 0 to 0xffff - */ - conversion_pace = 0x101; - brightness = - user_brightness - * conversion_pace - * (max - min) - / AMDGPU_MAX_BL_LEVEL - + min * conversion_pace; + if (caps->aux_support) { + // Firmware limits are in nits, DC API wants millinits. + *max = 1000 * caps->aux_max_input_signal; + *min = 1000 * caps->aux_min_input_signal; } else { - /* TODO - * We are doing a linear interpolation here, which is OK but - * does not provide the optimal result. We probably want - * something close to the Perceptual Quantizer (PQ) curve. - */ - max = caps->aux_max_input_signal; - min = caps->aux_min_input_signal; - - brightness = (AMDGPU_MAX_BL_LEVEL - user_brightness) * min - + user_brightness * max; - // Multiple the value by 1000 since we use millinits - brightness *= 1000; - brightness = DIV_ROUND_CLOSEST(brightness, AMDGPU_MAX_BL_LEVEL); + // Firmware limits are 8-bit, PWM control is 16-bit. + *max = 0x101 * caps->max_input_signal; + *min = 0x101 * caps->min_input_signal; } + return 1; +} -out: - return brightness; +static u32 convert_brightness_from_user(const struct amdgpu_dm_backlight_caps *caps, + uint32_t brightness) +{ + unsigned min, max; + + if (!get_brightness_range(caps, &min, &max)) + return brightness; + + // Rescale 0..255 to min..max + return min + DIV_ROUND_CLOSEST((max - min) * brightness, + AMDGPU_MAX_BL_LEVEL); +} + +static u32 convert_brightness_to_user(const struct amdgpu_dm_backlight_caps *caps, + uint32_t brightness) +{ + unsigned min, max; + + if (!get_brightness_range(caps, &min, &max)) + return brightness; + + if (brightness < min) + return 0; + // Rescale min..max to 0..255 + return DIV_ROUND_CLOSEST(AMDGPU_MAX_BL_LEVEL * (brightness - min), + max - min); } static int amdgpu_dm_backlight_update_status(struct backlight_device *bd) @@ -2954,7 +2961,7 @@ static int amdgpu_dm_backlight_update_status(struct backlight_device *bd) link = (struct dc_link *)dm->backlight_link; - brightness = convert_brightness(&caps, bd->props.brightness); + brightness = convert_brightness_from_user(&caps, bd->props.brightness); // Change brightness based on AUX property if (caps.aux_support) return set_backlight_via_aux(link, brightness); @@ -2971,7 +2978,7 @@ static int amdgpu_dm_backlight_get_brightness(struct backlight_device *bd) if (ret == DC_ERROR_UNEXPECTED) return bd->props.brightness; - return ret; + return convert_brightness_to_user(&dm->backlight_caps, ret); } static const struct backlight_ops amdgpu_dm_backlight_ops = { diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c index e85b58f0f416..336aaa09be46 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c @@ -67,7 +67,7 @@ static ssize_t dm_dp_aux_transfer(struct drm_dp_aux *aux, result = dc_link_aux_transfer_raw(TO_DM_AUX(aux)->ddc_service, &payload, &operation_result); - if (payload.write) + if (payload.write && result >= 0) result = msg->size; if (result < 0) diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c index c664404a75d4..543afa34d87a 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c @@ -94,6 +94,15 @@ int rn_get_active_display_cnt_wa( return display_count; } +void rn_set_low_power_state(struct clk_mgr *clk_mgr_base) +{ + struct clk_mgr_internal *clk_mgr = TO_CLK_MGR_INTERNAL(clk_mgr_base); + + rn_vbios_smu_set_dcn_low_power_state(clk_mgr, DCN_PWR_STATE_LOW_POWER); + /* update power state */ + clk_mgr_base->clks.pwr_state = DCN_PWR_STATE_LOW_POWER; +} + void rn_update_clocks(struct clk_mgr *clk_mgr_base, struct dc_state *context, bool safe_to_lower) @@ -516,6 +525,7 @@ static struct clk_mgr_funcs dcn21_funcs = { .init_clocks = rn_init_clocks, .enable_pme_wa = rn_enable_pme_wa, .are_clock_states_equal = rn_are_clock_states_equal, + .set_low_power_state = rn_set_low_power_state, .notify_wm_ranges = rn_notify_wm_ranges, .notify_link_rate_change = rn_notify_link_rate_change, }; 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 117d8aaf2a9b..437d1a7a16fe 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c @@ -763,6 +763,7 @@ static bool detect_dp(struct dc_link *link, sink_caps->signal = dp_passive_dongle_detection(link->ddc, sink_caps, audio_support); + link->dpcd_caps.dongle_type = sink_caps->dongle_type; } return true; @@ -3286,10 +3287,10 @@ void core_link_disable_stream(struct pipe_ctx *pipe_ctx) core_link_set_avmute(pipe_ctx, true); } - dc->hwss.blank_stream(pipe_ctx); #if defined(CONFIG_DRM_AMD_DC_HDCP) update_psp_stream_config(pipe_ctx, true); #endif + dc->hwss.blank_stream(pipe_ctx); if (pipe_ctx->stream->signal == SIGNAL_TYPE_DISPLAY_PORT_MST) deallocate_mst_payload(pipe_ctx); diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c index 9bc03f26efda..b2be6ad5101d 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c @@ -4409,9 +4409,9 @@ bool dc_link_get_backlight_level_nits(struct dc_link *link, link->connector_signal != SIGNAL_TYPE_DISPLAY_PORT)) return false; - if (!core_link_read_dpcd(link, DP_SOURCE_BACKLIGHT_CURRENT_PEAK, + if (core_link_read_dpcd(link, DP_SOURCE_BACKLIGHT_CURRENT_PEAK, dpcd_backlight_get.raw, - sizeof(union dpcd_source_backlight_get))) + sizeof(union dpcd_source_backlight_get)) != DC_OK) return false; *backlight_millinits_avg = @@ -4450,9 +4450,9 @@ bool dc_link_read_default_bl_aux(struct dc_link *link, uint32_t *backlight_milli link->connector_signal != SIGNAL_TYPE_DISPLAY_PORT)) return false; - if (!core_link_read_dpcd(link, DP_SOURCE_BACKLIGHT_LEVEL, + if (core_link_read_dpcd(link, DP_SOURCE_BACKLIGHT_LEVEL, (uint8_t *) backlight_millinits, - sizeof(uint32_t))) + sizeof(uint32_t)) != DC_OK) return false; return true; diff --git a/drivers/gpu/drm/amd/display/dc/dc_stream.h b/drivers/gpu/drm/amd/display/dc/dc_stream.h index 633442bc7ef2..d9888f316da6 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_stream.h +++ b/drivers/gpu/drm/amd/display/dc/dc_stream.h @@ -233,7 +233,7 @@ struct dc_stream_state { union stream_update_flags update_flags; }; -#define ABM_LEVEL_IMMEDIATE_DISABLE 0xFFFFFFFF +#define ABM_LEVEL_IMMEDIATE_DISABLE 255 struct dc_stream_update { struct dc_stream_state *stream; diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c index a643927e272b..fa643ec5a876 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c @@ -1450,33 +1450,42 @@ void dcn10_init_hw(struct dc *dc) void dcn10_power_down_on_boot(struct dc *dc) { int i = 0; + struct dc_link *edp_link; - if (dc->config.power_down_display_on_boot) { - struct dc_link *edp_link = get_edp_link(dc); - - if (edp_link && - edp_link->link_enc->funcs->is_dig_enabled && - edp_link->link_enc->funcs->is_dig_enabled(edp_link->link_enc) && - dc->hwseq->funcs.edp_backlight_control && - dc->hwss.power_down && - dc->hwss.edp_power_control) { - dc->hwseq->funcs.edp_backlight_control(edp_link, false); - dc->hwss.power_down(dc); - dc->hwss.edp_power_control(edp_link, false); - } else { - for (i = 0; i < dc->link_count; i++) { - struct dc_link *link = dc->links[i]; - - if (link->link_enc->funcs->is_dig_enabled && - link->link_enc->funcs->is_dig_enabled(link->link_enc) && - dc->hwss.power_down) { - dc->hwss.power_down(dc); - break; - } + if (!dc->config.power_down_display_on_boot) + return; + + edp_link = get_edp_link(dc); + if (edp_link && + edp_link->link_enc->funcs->is_dig_enabled && + edp_link->link_enc->funcs->is_dig_enabled(edp_link->link_enc) && + dc->hwseq->funcs.edp_backlight_control && + dc->hwss.power_down && + dc->hwss.edp_power_control) { + dc->hwseq->funcs.edp_backlight_control(edp_link, false); + dc->hwss.power_down(dc); + dc->hwss.edp_power_control(edp_link, false); + } else { + for (i = 0; i < dc->link_count; i++) { + struct dc_link *link = dc->links[i]; + if (link->link_enc->funcs->is_dig_enabled && + link->link_enc->funcs->is_dig_enabled(link->link_enc) && + dc->hwss.power_down) { + dc->hwss.power_down(dc); + break; } + } } + + /* + * Call update_clocks with empty context + * to send DISPLAY_OFF + * Otherwise DISPLAY_OFF may not be asserted + */ + if (dc->clk_mgr->funcs->set_low_power_state) + dc->clk_mgr->funcs->set_low_power_state(dc->clk_mgr); } void dcn10_reset_hw_ctx_wrap( diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c index 17d5cb422025..8939541ad7af 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c @@ -1213,6 +1213,7 @@ static enum dc_status dcn10_validate_global(struct dc *dc, struct dc_state *cont bool video_large = false; bool desktop_large = false; bool dcc_disabled = false; + bool mpo_enabled = false; for (i = 0; i < context->stream_count; i++) { if (context->stream_status[i].plane_count == 0) @@ -1221,6 +1222,9 @@ static enum dc_status dcn10_validate_global(struct dc *dc, struct dc_state *cont if (context->stream_status[i].plane_count > 2) return DC_FAIL_UNSUPPORTED_1; + if (context->stream_status[i].plane_count > 1) + mpo_enabled = true; + for (j = 0; j < context->stream_status[i].plane_count; j++) { struct dc_plane_state *plane = context->stream_status[i].plane_states[j]; @@ -1244,6 +1248,10 @@ static enum dc_status dcn10_validate_global(struct dc *dc, struct dc_state *cont } } + /* Disable MPO in multi-display configurations. */ + if (context->stream_count > 1 && mpo_enabled) + return DC_FAIL_UNSUPPORTED_1; + /* * Workaround: On DCN10 there is UMC issue that causes underflow when * playing 4k video on 4k desktop with video downscaled and single channel diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr.h b/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr.h index 5994d2a33c40..947d6106f341 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr.h @@ -230,6 +230,8 @@ struct clk_mgr_funcs { int (*get_dp_ref_clk_frequency)(struct clk_mgr *clk_mgr); + void (*set_low_power_state)(struct clk_mgr *clk_mgr); + void (*init_clocks)(struct clk_mgr *clk_mgr); void (*enable_pme_wa) (struct clk_mgr *clk_mgr); diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c index c9cfe90a2947..9ee8cf8267c8 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c @@ -204,8 +204,7 @@ static int smu10_set_min_deep_sleep_dcefclk(struct pp_hwmgr *hwmgr, uint32_t clo { struct smu10_hwmgr *smu10_data = (struct smu10_hwmgr *)(hwmgr->backend); - if (smu10_data->need_min_deep_sleep_dcefclk && - smu10_data->deep_sleep_dcefclk != clock) { + if (clock && smu10_data->deep_sleep_dcefclk != clock) { smu10_data->deep_sleep_dcefclk = clock; smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_SetMinDeepSleepDcefclk, @@ -219,8 +218,7 @@ static int smu10_set_hard_min_dcefclk_by_freq(struct pp_hwmgr *hwmgr, uint32_t c { struct smu10_hwmgr *smu10_data = (struct smu10_hwmgr *)(hwmgr->backend); - if (smu10_data->dcf_actual_hard_min_freq && - smu10_data->dcf_actual_hard_min_freq != clock) { + if (clock && smu10_data->dcf_actual_hard_min_freq != clock) { smu10_data->dcf_actual_hard_min_freq = clock; smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_SetHardMinDcefclkByFreq, @@ -234,8 +232,7 @@ static int smu10_set_hard_min_fclk_by_freq(struct pp_hwmgr *hwmgr, uint32_t cloc { struct smu10_hwmgr *smu10_data = (struct smu10_hwmgr *)(hwmgr->backend); - if (smu10_data->f_actual_hard_min_freq && - smu10_data->f_actual_hard_min_freq != clock) { + if (clock && smu10_data->f_actual_hard_min_freq != clock) { smu10_data->f_actual_hard_min_freq = clock; smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_SetHardMinFclkByFreq, diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_thermal.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_thermal.c index 468bdd6f6697..d572ba4ec9b1 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_thermal.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_thermal.c @@ -363,17 +363,19 @@ int vega10_thermal_get_temperature(struct pp_hwmgr *hwmgr) static int vega10_thermal_set_temperature_range(struct pp_hwmgr *hwmgr, struct PP_TemperatureRange *range) { + struct phm_ppt_v2_information *pp_table_info = + (struct phm_ppt_v2_information *)(hwmgr->pptable); + struct phm_tdp_table *tdp_table = pp_table_info->tdp_table; struct amdgpu_device *adev = hwmgr->adev; - int low = VEGA10_THERMAL_MINIMUM_ALERT_TEMP * - PP_TEMPERATURE_UNITS_PER_CENTIGRADES; - int high = VEGA10_THERMAL_MAXIMUM_ALERT_TEMP * - PP_TEMPERATURE_UNITS_PER_CENTIGRADES; + int low = VEGA10_THERMAL_MINIMUM_ALERT_TEMP; + int high = VEGA10_THERMAL_MAXIMUM_ALERT_TEMP; uint32_t val; - if (low < range->min) - low = range->min; - if (high > range->max) - high = range->max; + /* compare them in unit celsius degree */ + if (low < range->min / PP_TEMPERATURE_UNITS_PER_CENTIGRADES) + low = range->min / PP_TEMPERATURE_UNITS_PER_CENTIGRADES; + if (high > tdp_table->usSoftwareShutdownTemp) + high = tdp_table->usSoftwareShutdownTemp; if (low > high) return -EINVAL; @@ -382,8 +384,8 @@ static int vega10_thermal_set_temperature_range(struct pp_hwmgr *hwmgr, val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, MAX_IH_CREDIT, 5); val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, THERM_IH_HW_ENA, 1); - val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, DIG_THERM_INTH, (high / PP_TEMPERATURE_UNITS_PER_CENTIGRADES)); - val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, DIG_THERM_INTL, (low / PP_TEMPERATURE_UNITS_PER_CENTIGRADES)); + val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, DIG_THERM_INTH, high); + val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, DIG_THERM_INTL, low); val &= (~THM_THERMAL_INT_CTRL__THERM_TRIGGER_MASK_MASK) & (~THM_THERMAL_INT_CTRL__THERM_INTH_MASK_MASK) & (~THM_THERMAL_INT_CTRL__THERM_INTL_MASK_MASK); diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_thermal.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_thermal.c index c15b9756025d..7ace439dcde7 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_thermal.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_thermal.c @@ -170,17 +170,18 @@ int vega12_thermal_get_temperature(struct pp_hwmgr *hwmgr) static int vega12_thermal_set_temperature_range(struct pp_hwmgr *hwmgr, struct PP_TemperatureRange *range) { + struct phm_ppt_v3_information *pptable_information = + (struct phm_ppt_v3_information *)hwmgr->pptable; struct amdgpu_device *adev = hwmgr->adev; - int low = VEGA12_THERMAL_MINIMUM_ALERT_TEMP * - PP_TEMPERATURE_UNITS_PER_CENTIGRADES; - int high = VEGA12_THERMAL_MAXIMUM_ALERT_TEMP * - PP_TEMPERATURE_UNITS_PER_CENTIGRADES; + int low = VEGA12_THERMAL_MINIMUM_ALERT_TEMP; + int high = VEGA12_THERMAL_MAXIMUM_ALERT_TEMP; uint32_t val; - if (low < range->min) - low = range->min; - if (high > range->max) - high = range->max; + /* compare them in unit celsius degree */ + if (low < range->min / PP_TEMPERATURE_UNITS_PER_CENTIGRADES) + low = range->min / PP_TEMPERATURE_UNITS_PER_CENTIGRADES; + if (high > pptable_information->us_software_shutdown_temp) + high = pptable_information->us_software_shutdown_temp; if (low > high) return -EINVAL; @@ -189,8 +190,8 @@ static int vega12_thermal_set_temperature_range(struct pp_hwmgr *hwmgr, val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, MAX_IH_CREDIT, 5); val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, THERM_IH_HW_ENA, 1); - val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, DIG_THERM_INTH, (high / PP_TEMPERATURE_UNITS_PER_CENTIGRADES)); - val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, DIG_THERM_INTL, (low / PP_TEMPERATURE_UNITS_PER_CENTIGRADES)); + val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, DIG_THERM_INTH, high); + val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, DIG_THERM_INTL, low); val = val & (~THM_THERMAL_INT_CTRL__THERM_TRIGGER_MASK_MASK); WREG32_SOC15(THM, 0, mmTHM_THERMAL_INT_CTRL, val); diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_thermal.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_thermal.c index 7add2f60f49c..364162ddaa9c 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_thermal.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_thermal.c @@ -240,17 +240,18 @@ int vega20_thermal_get_temperature(struct pp_hwmgr *hwmgr) static int vega20_thermal_set_temperature_range(struct pp_hwmgr *hwmgr, struct PP_TemperatureRange *range) { + struct phm_ppt_v3_information *pptable_information = + (struct phm_ppt_v3_information *)hwmgr->pptable; struct amdgpu_device *adev = hwmgr->adev; - int low = VEGA20_THERMAL_MINIMUM_ALERT_TEMP * - PP_TEMPERATURE_UNITS_PER_CENTIGRADES; - int high = VEGA20_THERMAL_MAXIMUM_ALERT_TEMP * - PP_TEMPERATURE_UNITS_PER_CENTIGRADES; + int low = VEGA20_THERMAL_MINIMUM_ALERT_TEMP; + int high = VEGA20_THERMAL_MAXIMUM_ALERT_TEMP; uint32_t val; - if (low < range->min) - low = range->min; - if (high > range->max) - high = range->max; + /* compare them in unit celsius degree */ + if (low < range->min / PP_TEMPERATURE_UNITS_PER_CENTIGRADES) + low = range->min / PP_TEMPERATURE_UNITS_PER_CENTIGRADES; + if (high > pptable_information->us_software_shutdown_temp) + high = pptable_information->us_software_shutdown_temp; if (low > high) return -EINVAL; @@ -259,8 +260,8 @@ static int vega20_thermal_set_temperature_range(struct pp_hwmgr *hwmgr, val = CGS_REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, MAX_IH_CREDIT, 5); val = CGS_REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, THERM_IH_HW_ENA, 1); - val = CGS_REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, DIG_THERM_INTH, (high / PP_TEMPERATURE_UNITS_PER_CENTIGRADES)); - val = CGS_REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, DIG_THERM_INTL, (low / PP_TEMPERATURE_UNITS_PER_CENTIGRADES)); + val = CGS_REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, DIG_THERM_INTH, high); + val = CGS_REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, DIG_THERM_INTL, low); val = val & (~THM_THERMAL_INT_CTRL__THERM_TRIGGER_MASK_MASK); WREG32_SOC15(THM, 0, mmTHM_THERMAL_INT_CTRL, val); diff --git a/drivers/gpu/drm/amd/powerplay/sienna_cichlid_ppt.c b/drivers/gpu/drm/amd/powerplay/sienna_cichlid_ppt.c index 3865dbed5f93..638760839c15 100644 --- a/drivers/gpu/drm/amd/powerplay/sienna_cichlid_ppt.c +++ b/drivers/gpu/drm/amd/powerplay/sienna_cichlid_ppt.c @@ -95,6 +95,7 @@ static struct cmn2asic_msg_mapping sienna_cichlid_message_map[SMU_MSG_MAX_COUNT] MSG_MAP(TransferTableSmu2Dram, PPSMC_MSG_TransferTableSmu2Dram, 0), MSG_MAP(TransferTableDram2Smu, PPSMC_MSG_TransferTableDram2Smu, 0), MSG_MAP(UseDefaultPPTable, PPSMC_MSG_UseDefaultPPTable, 0), + MSG_MAP(RunDcBtc, PPSMC_MSG_RunDcBtc, 0), MSG_MAP(EnterBaco, PPSMC_MSG_EnterBaco, 0), MSG_MAP(SetSoftMinByFreq, PPSMC_MSG_SetSoftMinByFreq, 0), MSG_MAP(SetSoftMaxByFreq, PPSMC_MSG_SetSoftMaxByFreq, 0), @@ -775,7 +776,7 @@ static int sienna_cichlid_dpm_set_vcn_enable(struct smu_context *smu, bool enabl ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_PowerUpVcn, 0, NULL); if (ret) return ret; - if (adev->asic_type == CHIP_SIENNA_CICHLID) { + if (adev->vcn.num_vcn_inst > 1) { ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_PowerUpVcn, 0x10000, NULL); if (ret) @@ -787,7 +788,7 @@ static int sienna_cichlid_dpm_set_vcn_enable(struct smu_context *smu, bool enabl ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_PowerDownVcn, 0, NULL); if (ret) return ret; - if (adev->asic_type == CHIP_SIENNA_CICHLID) { + if (adev->vcn.num_vcn_inst > 1) { ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_PowerDownVcn, 0x10000, NULL); if (ret) @@ -1732,6 +1733,11 @@ static int sienna_cichlid_get_dpm_ultimate_freq(struct smu_context *smu, return ret; } +static int sienna_cichlid_run_btc(struct smu_context *smu) +{ + return smu_cmn_send_smc_msg(smu, SMU_MSG_RunDcBtc, NULL); +} + static bool sienna_cichlid_is_baco_supported(struct smu_context *smu) { struct amdgpu_device *adev = smu->adev; @@ -2719,6 +2725,7 @@ static const struct pptable_funcs sienna_cichlid_ppt_funcs = { .mode1_reset = smu_v11_0_mode1_reset, .get_dpm_ultimate_freq = sienna_cichlid_get_dpm_ultimate_freq, .set_soft_freq_limited_range = smu_v11_0_set_soft_freq_limited_range, + .run_btc = sienna_cichlid_run_btc, .get_pp_feature_mask = smu_cmn_get_pp_feature_mask, .set_pp_feature_mask = smu_cmn_set_pp_feature_mask, }; diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c index f68c69a45752..9e1ad493e689 100644 --- a/drivers/gpu/drm/drm_atomic_helper.c +++ b/drivers/gpu/drm/drm_atomic_helper.c @@ -34,6 +34,7 @@ #include <drm/drm_bridge.h> #include <drm/drm_damage_helper.h> #include <drm/drm_device.h> +#include <drm/drm_drv.h> #include <drm/drm_plane_helper.h> #include <drm/drm_print.h> #include <drm/drm_self_refresh_helper.h> @@ -3106,7 +3107,7 @@ void drm_atomic_helper_shutdown(struct drm_device *dev) if (ret) DRM_ERROR("Disabling all crtc's during unload failed with %i\n", ret); - DRM_MODESET_LOCK_ALL_END(ctx, ret); + DRM_MODESET_LOCK_ALL_END(dev, ctx, ret); } EXPORT_SYMBOL(drm_atomic_helper_shutdown); @@ -3246,7 +3247,7 @@ struct drm_atomic_state *drm_atomic_helper_suspend(struct drm_device *dev) } unlock: - DRM_MODESET_LOCK_ALL_END(ctx, err); + DRM_MODESET_LOCK_ALL_END(dev, ctx, err); if (err) return ERR_PTR(err); @@ -3327,7 +3328,7 @@ int drm_atomic_helper_resume(struct drm_device *dev, err = drm_atomic_helper_commit_duplicated_state(state, &ctx); - DRM_MODESET_LOCK_ALL_END(ctx, err); + DRM_MODESET_LOCK_ALL_END(dev, ctx, err); drm_atomic_state_put(state); return err; diff --git a/drivers/gpu/drm/drm_color_mgmt.c b/drivers/gpu/drm/drm_color_mgmt.c index c93123ff7c21..138ff34b31db 100644 --- a/drivers/gpu/drm/drm_color_mgmt.c +++ b/drivers/gpu/drm/drm_color_mgmt.c @@ -294,7 +294,7 @@ int drm_mode_gamma_set_ioctl(struct drm_device *dev, crtc->gamma_size, &ctx); out: - DRM_MODESET_LOCK_ALL_END(ctx, ret); + DRM_MODESET_LOCK_ALL_END(dev, ctx, ret); return ret; } diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c index 283bcc4362ca..aecdd7ea26dc 100644 --- a/drivers/gpu/drm/drm_crtc.c +++ b/drivers/gpu/drm/drm_crtc.c @@ -588,7 +588,6 @@ int drm_mode_setcrtc(struct drm_device *dev, void *data, if (crtc_req->mode_valid && !drm_lease_held(file_priv, plane->base.id)) return -EACCES; - mutex_lock(&crtc->dev->mode_config.mutex); DRM_MODESET_LOCK_ALL_BEGIN(dev, ctx, DRM_MODESET_ACQUIRE_INTERRUPTIBLE, ret); @@ -756,8 +755,7 @@ out: fb = NULL; mode = NULL; - DRM_MODESET_LOCK_ALL_END(ctx, ret); - mutex_unlock(&crtc->dev->mode_config.mutex); + DRM_MODESET_LOCK_ALL_END(dev, ctx, ret); return ret; } diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c index b23cb2fec3f3..67dd72ea200e 100644 --- a/drivers/gpu/drm/drm_dp_mst_topology.c +++ b/drivers/gpu/drm/drm_dp_mst_topology.c @@ -5040,8 +5040,8 @@ int drm_dp_mst_add_affected_dsc_crtcs(struct drm_atomic_state *state, struct drm crtc = conn_state->crtc; - if (WARN_ON(!crtc)) - return -EINVAL; + if (!crtc) + continue; if (!drm_dp_mst_dsc_aux_for_port(pos->port)) continue; diff --git a/drivers/gpu/drm/drm_mode_object.c b/drivers/gpu/drm/drm_mode_object.c index 901b078abf40..db05f386a709 100644 --- a/drivers/gpu/drm/drm_mode_object.c +++ b/drivers/gpu/drm/drm_mode_object.c @@ -428,7 +428,7 @@ int drm_mode_obj_get_properties_ioctl(struct drm_device *dev, void *data, out_unref: drm_mode_object_put(obj); out: - DRM_MODESET_LOCK_ALL_END(ctx, ret); + DRM_MODESET_LOCK_ALL_END(dev, ctx, ret); return ret; } @@ -470,7 +470,7 @@ static int set_property_legacy(struct drm_mode_object *obj, break; } drm_property_change_valid_put(prop, ref); - DRM_MODESET_LOCK_ALL_END(ctx, ret); + DRM_MODESET_LOCK_ALL_END(dev, ctx, ret); return ret; } diff --git a/drivers/gpu/drm/drm_plane.c b/drivers/gpu/drm/drm_plane.c index b7b90b3a2e38..affe1cfed009 100644 --- a/drivers/gpu/drm/drm_plane.c +++ b/drivers/gpu/drm/drm_plane.c @@ -792,7 +792,7 @@ static int setplane_internal(struct drm_plane *plane, crtc_x, crtc_y, crtc_w, crtc_h, src_x, src_y, src_w, src_h, &ctx); - DRM_MODESET_LOCK_ALL_END(ctx, ret); + DRM_MODESET_LOCK_ALL_END(plane->dev, ctx, ret); return ret; } diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c index d5a4cd85a0f6..c6404b8d067f 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c @@ -337,9 +337,16 @@ static void etnaviv_hw_identify(struct etnaviv_gpu *gpu) gpu->identity.model = gpu_read(gpu, VIVS_HI_CHIP_MODEL); gpu->identity.revision = gpu_read(gpu, VIVS_HI_CHIP_REV); - gpu->identity.product_id = gpu_read(gpu, VIVS_HI_CHIP_PRODUCT_ID); gpu->identity.customer_id = gpu_read(gpu, VIVS_HI_CHIP_CUSTOMER_ID); - gpu->identity.eco_id = gpu_read(gpu, VIVS_HI_CHIP_ECO_ID); + + /* + * Reading these two registers on GC600 rev 0x19 result in a + * unhandled fault: external abort on non-linefetch + */ + if (!etnaviv_is_model_rev(gpu, GC600, 0x19)) { + gpu->identity.product_id = gpu_read(gpu, VIVS_HI_CHIP_PRODUCT_ID); + gpu->identity.eco_id = gpu_read(gpu, VIVS_HI_CHIP_ECO_ID); + } /* * !!!! HACK ALERT !!!! diff --git a/drivers/gpu/drm/etnaviv/etnaviv_sched.c b/drivers/gpu/drm/etnaviv/etnaviv_sched.c index 4e3e95dce6d8..cd46c882269c 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_sched.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_sched.c @@ -89,12 +89,15 @@ static void etnaviv_sched_timedout_job(struct drm_sched_job *sched_job) u32 dma_addr; int change; + /* block scheduler */ + drm_sched_stop(&gpu->sched, sched_job); + /* * If the GPU managed to complete this jobs fence, the timout is * spurious. Bail out. */ if (dma_fence_is_signaled(submit->out_fence)) - return; + goto out_no_timeout; /* * If the GPU is still making forward progress on the front-end (which @@ -105,12 +108,9 @@ static void etnaviv_sched_timedout_job(struct drm_sched_job *sched_job) change = dma_addr - gpu->hangcheck_dma_addr; if (change < 0 || change > 16) { gpu->hangcheck_dma_addr = dma_addr; - return; + goto out_no_timeout; } - /* block scheduler */ - drm_sched_stop(&gpu->sched, sched_job); - if(sched_job) drm_sched_increase_karma(sched_job); @@ -120,6 +120,7 @@ static void etnaviv_sched_timedout_job(struct drm_sched_job *sched_job) drm_sched_resubmit_jobs(&gpu->sched); +out_no_timeout: /* restart scheduler after GPU is usable again */ drm_sched_start(&gpu->sched, true); } diff --git a/drivers/gpu/drm/exynos/exynos_drm_fbdev.c b/drivers/gpu/drm/exynos/exynos_drm_fbdev.c index 56a2b47e1af7..5147f5929be7 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_fbdev.c +++ b/drivers/gpu/drm/exynos/exynos_drm_fbdev.c @@ -92,7 +92,7 @@ static int exynos_drm_fbdev_update(struct drm_fb_helper *helper, offset = fbi->var.xoffset * fb->format->cpp[0]; offset += fbi->var.yoffset * fb->pitches[0]; - fbi->screen_base = exynos_gem->kvaddr + offset; + fbi->screen_buffer = exynos_gem->kvaddr + offset; fbi->screen_size = size; fbi->fix.smem_len = size; diff --git a/drivers/gpu/drm/exynos/exynos_drm_gem.h b/drivers/gpu/drm/exynos/exynos_drm_gem.h index 7445748288da..74e926abeff0 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_gem.h +++ b/drivers/gpu/drm/exynos/exynos_drm_gem.h @@ -40,7 +40,7 @@ struct exynos_drm_gem { unsigned int flags; unsigned long size; void *cookie; - void __iomem *kvaddr; + void *kvaddr; dma_addr_t dma_addr; unsigned long dma_attrs; struct sg_table *sgt; diff --git a/drivers/gpu/drm/i915/i915_cmd_parser.c b/drivers/gpu/drm/i915/i915_cmd_parser.c index 372354d33f55..5ac4a999f05a 100644 --- a/drivers/gpu/drm/i915/i915_cmd_parser.c +++ b/drivers/gpu/drm/i915/i915_cmd_parser.c @@ -1204,6 +1204,12 @@ static u32 *copy_batch(struct drm_i915_gem_object *dst_obj, return dst; } +static inline bool cmd_desc_is(const struct drm_i915_cmd_descriptor * const desc, + const u32 cmd) +{ + return desc->cmd.value == (cmd & desc->cmd.mask); +} + static bool check_cmd(const struct intel_engine_cs *engine, const struct drm_i915_cmd_descriptor *desc, const u32 *cmd, u32 length) @@ -1242,19 +1248,19 @@ static bool check_cmd(const struct intel_engine_cs *engine, * allowed mask/value pair given in the whitelist entry. */ if (reg->mask) { - if (desc->cmd.value == MI_LOAD_REGISTER_MEM) { + if (cmd_desc_is(desc, MI_LOAD_REGISTER_MEM)) { DRM_DEBUG("CMD: Rejected LRM to masked register 0x%08X\n", reg_addr); return false; } - if (desc->cmd.value == MI_LOAD_REGISTER_REG) { + if (cmd_desc_is(desc, MI_LOAD_REGISTER_REG)) { DRM_DEBUG("CMD: Rejected LRR to masked register 0x%08X\n", reg_addr); return false; } - if (desc->cmd.value == MI_LOAD_REGISTER_IMM(1) && + if (cmd_desc_is(desc, MI_LOAD_REGISTER_IMM(1)) && (offset + 2 > length || (cmd[offset + 1] & reg->mask) != reg->value)) { DRM_DEBUG("CMD: Rejected LRI to masked register 0x%08X\n", @@ -1478,7 +1484,7 @@ int intel_engine_cmd_parser(struct intel_engine_cs *engine, break; } - if (desc->cmd.value == MI_BATCH_BUFFER_START) { + if (cmd_desc_is(desc, MI_BATCH_BUFFER_START)) { ret = check_bbstart(cmd, offset, length, batch_length, batch_addr, shadow_addr, jump_whitelist); diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c index 4c9bda19cbc4..e1c7bcd1b1eb 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c @@ -133,7 +133,7 @@ void a6xx_gmu_set_freq(struct msm_gpu *gpu, struct dev_pm_opp *opp) if (!gmu->legacy) { a6xx_hfi_set_freq(gmu, perf_index); - icc_set_bw(gpu->icc_path, 0, MBps_to_icc(7216)); + dev_pm_opp_set_bw(&gpu->pdev->dev, opp); pm_runtime_put(gmu->dev); return; } @@ -157,11 +157,7 @@ void a6xx_gmu_set_freq(struct msm_gpu *gpu, struct dev_pm_opp *opp) if (ret) dev_err(gmu->dev, "GMU set GPU frequency error: %d\n", ret); - /* - * Eventually we will want to scale the path vote with the frequency but - * for now leave it at max so that the performance is nominal. - */ - icc_set_bw(gpu->icc_path, 0, MBps_to_icc(7216)); + dev_pm_opp_set_bw(&gpu->pdev->dev, opp); pm_runtime_put(gmu->dev); } @@ -204,6 +200,16 @@ static int a6xx_gmu_start(struct a6xx_gmu *gmu) { int ret; u32 val; + u32 mask, reset_val; + + val = gmu_read(gmu, REG_A6XX_GMU_CM3_DTCM_START + 0xff8); + if (val <= 0x20010004) { + mask = 0xffffffff; + reset_val = 0xbabeface; + } else { + mask = 0x1ff; + reset_val = 0x100; + } gmu_write(gmu, REG_A6XX_GMU_CM3_SYSRESET, 1); @@ -215,7 +221,7 @@ static int a6xx_gmu_start(struct a6xx_gmu *gmu) gmu_write(gmu, REG_A6XX_GMU_CM3_SYSRESET, 0); ret = gmu_poll_timeout(gmu, REG_A6XX_GMU_CM3_FW_INIT_RESULT, val, - val == 0xbabeface, 100, 10000); + (val & mask) == reset_val, 100, 10000); if (ret) DRM_DEV_ERROR(gmu->dev, "GMU firmware initialization timed out\n"); @@ -845,10 +851,24 @@ static void a6xx_gmu_set_initial_freq(struct msm_gpu *gpu, struct a6xx_gmu *gmu) if (IS_ERR_OR_NULL(gpu_opp)) return; + gmu->freq = 0; /* so a6xx_gmu_set_freq() doesn't exit early */ a6xx_gmu_set_freq(gpu, gpu_opp); dev_pm_opp_put(gpu_opp); } +static void a6xx_gmu_set_initial_bw(struct msm_gpu *gpu, struct a6xx_gmu *gmu) +{ + struct dev_pm_opp *gpu_opp; + unsigned long gpu_freq = gmu->gpu_freqs[gmu->current_perf_index]; + + gpu_opp = dev_pm_opp_find_freq_exact(&gpu->pdev->dev, gpu_freq, true); + if (IS_ERR_OR_NULL(gpu_opp)) + return; + + dev_pm_opp_set_bw(&gpu->pdev->dev, gpu_opp); + dev_pm_opp_put(gpu_opp); +} + int a6xx_gmu_resume(struct a6xx_gpu *a6xx_gpu) { struct adreno_gpu *adreno_gpu = &a6xx_gpu->base; @@ -882,7 +902,7 @@ int a6xx_gmu_resume(struct a6xx_gpu *a6xx_gpu) } /* Set the bus quota to a reasonable value for boot */ - icc_set_bw(gpu->icc_path, 0, MBps_to_icc(3072)); + a6xx_gmu_set_initial_bw(gpu, gmu); /* Enable the GMU interrupt */ gmu_write(gmu, REG_A6XX_GMU_AO_HOST_INTERRUPT_CLR, ~0); @@ -1051,7 +1071,7 @@ int a6xx_gmu_stop(struct a6xx_gpu *a6xx_gpu) a6xx_gmu_shutdown(gmu); /* Remove the bus vote */ - icc_set_bw(gpu->icc_path, 0, 0); + dev_pm_opp_set_bw(&gpu->pdev->dev, NULL); /* * Make sure the GX domain is off before turning off the GMU (CX) diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c index 959656ad6987..b12f5b4a1bea 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c @@ -938,7 +938,8 @@ struct msm_gpu_state *a6xx_gpu_state_get(struct msm_gpu *gpu) msm_gem_kernel_put(dumper.bo, gpu->aspace, true); } - a6xx_get_debugbus(gpu, a6xx_state); + if (snapshot_debugbus) + a6xx_get_debugbus(gpu, a6xx_state); return &a6xx_state->base; } diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h index 846fd5b54c23..2fb58b7098e4 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h @@ -372,7 +372,7 @@ static const struct a6xx_indexed_registers { u32 data; u32 count; } a6xx_indexed_reglist[] = { - { "CP_SEQ_STAT", REG_A6XX_CP_SQE_STAT_ADDR, + { "CP_SQE_STAT", REG_A6XX_CP_SQE_STAT_ADDR, REG_A6XX_CP_SQE_STAT_DATA, 0x33 }, { "CP_DRAW_STATE", REG_A6XX_CP_DRAW_STATE_ADDR, REG_A6XX_CP_DRAW_STATE_DATA, 0x100 }, diff --git a/drivers/gpu/drm/msm/adreno/adreno_device.c b/drivers/gpu/drm/msm/adreno/adreno_device.c index 4e84f3c76f4f..9eeb46bf2a5d 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_device.c +++ b/drivers/gpu/drm/msm/adreno/adreno_device.c @@ -14,6 +14,10 @@ bool hang_debug = false; MODULE_PARM_DESC(hang_debug, "Dump registers when hang is detected (can be slow!)"); module_param_named(hang_debug, hang_debug, bool, 0600); +bool snapshot_debugbus = false; +MODULE_PARM_DESC(snapshot_debugbus, "Include debugbus sections in GPU devcoredump (if not fused off)"); +module_param_named(snapshot_debugbus, snapshot_debugbus, bool, 0600); + static const struct adreno_info gpulist[] = { { .rev = ADRENO_REV(2, 0, 0, 0), diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c index bb0b09790157..288141fe4c58 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c +++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c @@ -396,7 +396,7 @@ int adreno_hw_init(struct msm_gpu *gpu) ring->next = ring->start; /* reset completed fence seqno: */ - ring->memptrs->fence = ring->seqno; + ring->memptrs->fence = ring->fctx->completed_fence; ring->memptrs->rptr = 0; } diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.h b/drivers/gpu/drm/msm/adreno/adreno_gpu.h index 99bb468f5f24..e55abae365b5 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_gpu.h +++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.h @@ -21,6 +21,8 @@ #define REG_SKIP ~0 #define REG_ADRENO_SKIP(_offset) [_offset] = REG_SKIP +extern bool snapshot_debugbus; + /** * adreno_regs: List of registers that are used in across all * 3D devices. Each device type has different offset value for the same diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c index f272a8d0f95b..c2729f71e2fa 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c @@ -827,7 +827,7 @@ static void dpu_crtc_enable(struct drm_crtc *crtc, { struct dpu_crtc *dpu_crtc; struct drm_encoder *encoder; - bool request_bandwidth; + bool request_bandwidth = false; if (!crtc) { DPU_ERROR("invalid crtc\n"); diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c index a97f6d2e5a08..bd6def436c65 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c @@ -599,7 +599,10 @@ static int dpu_encoder_virt_atomic_check( dpu_kms = to_dpu_kms(priv->kms); mode = &crtc_state->mode; adj_mode = &crtc_state->adjusted_mode; - global_state = dpu_kms_get_existing_global_state(dpu_kms); + global_state = dpu_kms_get_global_state(crtc_state->state); + if (IS_ERR(global_state)) + return PTR_ERR(global_state); + trace_dpu_enc_atomic_check(DRMID(drm_enc)); /* perform atomic check on the first physical encoder (master) */ @@ -625,12 +628,15 @@ static int dpu_encoder_virt_atomic_check( /* Reserve dynamic resources now. */ if (!ret) { /* - * Avoid reserving resources when mode set is pending. Topology - * info may not be available to complete reservation. + * Release and Allocate resources on every modeset + * Dont allocate when active is false. */ if (drm_atomic_crtc_needs_modeset(crtc_state)) { - ret = dpu_rm_reserve(&dpu_kms->rm, global_state, - drm_enc, crtc_state, topology); + dpu_rm_release(global_state, drm_enc); + + if (!crtc_state->active_changed || crtc_state->active) + ret = dpu_rm_reserve(&dpu_kms->rm, global_state, + drm_enc, crtc_state, topology); } } @@ -1181,7 +1187,6 @@ static void dpu_encoder_virt_disable(struct drm_encoder *drm_enc) struct dpu_encoder_virt *dpu_enc = NULL; struct msm_drm_private *priv; struct dpu_kms *dpu_kms; - struct dpu_global_state *global_state; int i = 0; if (!drm_enc) { @@ -1200,7 +1205,6 @@ static void dpu_encoder_virt_disable(struct drm_encoder *drm_enc) priv = drm_enc->dev->dev_private; dpu_kms = to_dpu_kms(priv->kms); - global_state = dpu_kms_get_existing_global_state(dpu_kms); trace_dpu_enc_disable(DRMID(drm_enc)); @@ -1230,8 +1234,6 @@ static void dpu_encoder_virt_disable(struct drm_encoder *drm_enc) DPU_DEBUG_ENC(dpu_enc, "encoder disabled\n"); - dpu_rm_release(global_state, drm_enc); - mutex_unlock(&dpu_enc->enc_lock); } diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c index 33f6c56f01ed..29e373d2e7b5 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c @@ -866,9 +866,9 @@ static int dpu_plane_atomic_check(struct drm_plane *plane, crtc_state = drm_atomic_get_new_crtc_state(state->state, state->crtc); - min_scale = FRAC_16_16(1, pdpu->pipe_sblk->maxdwnscale); + min_scale = FRAC_16_16(1, pdpu->pipe_sblk->maxupscale); ret = drm_atomic_helper_check_plane_state(state, crtc_state, min_scale, - pdpu->pipe_sblk->maxupscale << 16, + pdpu->pipe_sblk->maxdwnscale << 16, true, true); if (ret) { DPU_DEBUG_PLANE(pdpu, "Check plane state failed (%d)\n", ret); diff --git a/drivers/gpu/drm/msm/msm_atomic.c b/drivers/gpu/drm/msm/msm_atomic.c index 5ccfad794c6a..561bfa48841c 100644 --- a/drivers/gpu/drm/msm/msm_atomic.c +++ b/drivers/gpu/drm/msm/msm_atomic.c @@ -27,6 +27,34 @@ int msm_atomic_prepare_fb(struct drm_plane *plane, return msm_framebuffer_prepare(new_state->fb, kms->aspace); } +/* + * Helpers to control vblanks while we flush.. basically just to ensure + * that vblank accounting is switched on, so we get valid seqn/timestamp + * on pageflip events (if requested) + */ + +static void vblank_get(struct msm_kms *kms, unsigned crtc_mask) +{ + struct drm_crtc *crtc; + + for_each_crtc_mask(kms->dev, crtc, crtc_mask) { + if (!crtc->state->active) + continue; + drm_crtc_vblank_get(crtc); + } +} + +static void vblank_put(struct msm_kms *kms, unsigned crtc_mask) +{ + struct drm_crtc *crtc; + + for_each_crtc_mask(kms->dev, crtc, crtc_mask) { + if (!crtc->state->active) + continue; + drm_crtc_vblank_put(crtc); + } +} + static void msm_atomic_async_commit(struct msm_kms *kms, int crtc_idx) { unsigned crtc_mask = BIT(crtc_idx); @@ -44,6 +72,8 @@ static void msm_atomic_async_commit(struct msm_kms *kms, int crtc_idx) kms->funcs->enable_commit(kms); + vblank_get(kms, crtc_mask); + /* * Flush hardware updates: */ @@ -58,6 +88,8 @@ static void msm_atomic_async_commit(struct msm_kms *kms, int crtc_idx) kms->funcs->wait_flush(kms, crtc_mask); trace_msm_atomic_wait_flush_finish(crtc_mask); + vblank_put(kms, crtc_mask); + mutex_lock(&kms->commit_lock); kms->funcs->complete_commit(kms, crtc_mask); mutex_unlock(&kms->commit_lock); @@ -221,6 +253,8 @@ void msm_atomic_commit_tail(struct drm_atomic_state *state) */ kms->pending_crtc_mask &= ~crtc_mask; + vblank_get(kms, crtc_mask); + /* * Flush hardware updates: */ @@ -235,6 +269,8 @@ void msm_atomic_commit_tail(struct drm_atomic_state *state) kms->funcs->wait_flush(kms, crtc_mask); trace_msm_atomic_wait_flush_finish(crtc_mask); + vblank_put(kms, crtc_mask); + mutex_lock(&kms->commit_lock); kms->funcs->complete_commit(kms, crtc_mask); mutex_unlock(&kms->commit_lock); diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c index 7d641c7e3514..79333842f70a 100644 --- a/drivers/gpu/drm/msm/msm_drv.c +++ b/drivers/gpu/drm/msm/msm_drv.c @@ -1320,6 +1320,13 @@ static int msm_pdev_remove(struct platform_device *pdev) return 0; } +static void msm_pdev_shutdown(struct platform_device *pdev) +{ + struct drm_device *drm = platform_get_drvdata(pdev); + + drm_atomic_helper_shutdown(drm); +} + static const struct of_device_id dt_match[] = { { .compatible = "qcom,mdp4", .data = (void *)KMS_MDP4 }, { .compatible = "qcom,mdss", .data = (void *)KMS_MDP5 }, @@ -1332,6 +1339,7 @@ MODULE_DEVICE_TABLE(of, dt_match); static struct platform_driver msm_platform_driver = { .probe = msm_pdev_probe, .remove = msm_pdev_remove, + .shutdown = msm_pdev_shutdown, .driver = { .name = "msm", .of_match_table = dt_match, diff --git a/drivers/gpu/drm/msm/msm_ringbuffer.c b/drivers/gpu/drm/msm/msm_ringbuffer.c index e397c44cc011..39ecb5a18431 100644 --- a/drivers/gpu/drm/msm/msm_ringbuffer.c +++ b/drivers/gpu/drm/msm/msm_ringbuffer.c @@ -27,7 +27,8 @@ struct msm_ringbuffer *msm_ringbuffer_new(struct msm_gpu *gpu, int id, ring->id = id; ring->start = msm_gem_kernel_new(gpu->dev, MSM_GPU_RINGBUFFER_SZ, - MSM_BO_WC, gpu->aspace, &ring->bo, &ring->iova); + MSM_BO_WC | MSM_BO_GPU_READONLY, gpu->aspace, &ring->bo, + &ring->iova); if (IS_ERR(ring->start)) { ret = PTR_ERR(ring->start); diff --git a/drivers/gpu/drm/omapdrm/omap_crtc.c b/drivers/gpu/drm/omapdrm/omap_crtc.c index 6d40914675da..328a4a74f534 100644 --- a/drivers/gpu/drm/omapdrm/omap_crtc.c +++ b/drivers/gpu/drm/omapdrm/omap_crtc.c @@ -451,11 +451,12 @@ static void omap_crtc_atomic_enable(struct drm_crtc *crtc, if (omap_state->manually_updated) return; - spin_lock_irq(&crtc->dev->event_lock); drm_crtc_vblank_on(crtc); + ret = drm_crtc_vblank_get(crtc); WARN_ON(ret != 0); + spin_lock_irq(&crtc->dev->event_lock); omap_crtc_arm_event(crtc); spin_unlock_irq(&crtc->dev->event_lock); } diff --git a/drivers/hwmon/applesmc.c b/drivers/hwmon/applesmc.c index 316618409315..a18887990f4a 100644 --- a/drivers/hwmon/applesmc.c +++ b/drivers/hwmon/applesmc.c @@ -753,15 +753,18 @@ static ssize_t applesmc_light_show(struct device *dev, } ret = applesmc_read_key(LIGHT_SENSOR_LEFT_KEY, buffer, data_length); + if (ret) + goto out; /* newer macbooks report a single 10-bit bigendian value */ if (data_length == 10) { left = be16_to_cpu(*(__be16 *)(buffer + 6)) >> 2; goto out; } left = buffer[2]; + + ret = applesmc_read_key(LIGHT_SENSOR_RIGHT_KEY, buffer, data_length); if (ret) goto out; - ret = applesmc_read_key(LIGHT_SENSOR_RIGHT_KEY, buffer, data_length); right = buffer[2]; out: @@ -810,12 +813,11 @@ static ssize_t applesmc_show_fan_speed(struct device *dev, to_index(attr)); ret = applesmc_read_key(newkey, buffer, 2); - speed = ((buffer[0] << 8 | buffer[1]) >> 2); - if (ret) return ret; - else - return snprintf(sysfsbuf, PAGE_SIZE, "%u\n", speed); + + speed = ((buffer[0] << 8 | buffer[1]) >> 2); + return snprintf(sysfsbuf, PAGE_SIZE, "%u\n", speed); } static ssize_t applesmc_store_fan_speed(struct device *dev, @@ -851,12 +853,11 @@ static ssize_t applesmc_show_fan_manual(struct device *dev, u8 buffer[2]; ret = applesmc_read_key(FANS_MANUAL, buffer, 2); - manual = ((buffer[0] << 8 | buffer[1]) >> to_index(attr)) & 0x01; - if (ret) return ret; - else - return snprintf(sysfsbuf, PAGE_SIZE, "%d\n", manual); + + manual = ((buffer[0] << 8 | buffer[1]) >> to_index(attr)) & 0x01; + return snprintf(sysfsbuf, PAGE_SIZE, "%d\n", manual); } static ssize_t applesmc_store_fan_manual(struct device *dev, @@ -872,10 +873,11 @@ static ssize_t applesmc_store_fan_manual(struct device *dev, return -EINVAL; ret = applesmc_read_key(FANS_MANUAL, buffer, 2); - val = (buffer[0] << 8 | buffer[1]); if (ret) goto out; + val = (buffer[0] << 8 | buffer[1]); + if (input) val = val | (0x01 << to_index(attr)); else @@ -951,13 +953,12 @@ static ssize_t applesmc_key_count_show(struct device *dev, u32 count; ret = applesmc_read_key(KEY_COUNT_KEY, buffer, 4); - count = ((u32)buffer[0]<<24) + ((u32)buffer[1]<<16) + - ((u32)buffer[2]<<8) + buffer[3]; - if (ret) return ret; - else - return snprintf(sysfsbuf, PAGE_SIZE, "%d\n", count); + + count = ((u32)buffer[0]<<24) + ((u32)buffer[1]<<16) + + ((u32)buffer[2]<<8) + buffer[3]; + return snprintf(sysfsbuf, PAGE_SIZE, "%d\n", count); } static ssize_t applesmc_key_at_index_read_show(struct device *dev, diff --git a/drivers/hwmon/gsc-hwmon.c b/drivers/hwmon/gsc-hwmon.c index 3dfe2ca2f8c8..c6d4567f3952 100644 --- a/drivers/hwmon/gsc-hwmon.c +++ b/drivers/hwmon/gsc-hwmon.c @@ -172,6 +172,7 @@ gsc_hwmon_read(struct device *dev, enum hwmon_sensor_types type, u32 attr, case mode_temperature: if (tmp > 0x8000) tmp -= 0xffff; + tmp *= 100; /* convert to millidegrees celsius */ break; case mode_voltage_raw: tmp = clamp_val(tmp, 0, BIT(GSC_HWMON_RESOLUTION)); diff --git a/drivers/hwmon/nct7904.c b/drivers/hwmon/nct7904.c index b0425694f702..242ff8bee78d 100644 --- a/drivers/hwmon/nct7904.c +++ b/drivers/hwmon/nct7904.c @@ -231,7 +231,7 @@ static int nct7904_read_fan(struct device *dev, u32 attr, int channel, if (ret < 0) return ret; cnt = ((ret & 0xff00) >> 3) | (ret & 0x1f); - if (cnt == 0x1fff) + if (cnt == 0 || cnt == 0x1fff) rpm = 0; else rpm = 1350000 / cnt; @@ -243,7 +243,7 @@ static int nct7904_read_fan(struct device *dev, u32 attr, int channel, if (ret < 0) return ret; cnt = ((ret & 0xff00) >> 3) | (ret & 0x1f); - if (cnt == 0x1fff) + if (cnt == 0 || cnt == 0x1fff) rpm = 0; else rpm = 1350000 / cnt; diff --git a/drivers/hwmon/pmbus/isl68137.c b/drivers/hwmon/pmbus/isl68137.c index 0c622711ef7e..58aa95a3c010 100644 --- a/drivers/hwmon/pmbus/isl68137.c +++ b/drivers/hwmon/pmbus/isl68137.c @@ -67,6 +67,7 @@ enum variants { raa_dmpvr1_2rail, raa_dmpvr2_1rail, raa_dmpvr2_2rail, + raa_dmpvr2_2rail_nontc, raa_dmpvr2_3rail, raa_dmpvr2_hv, }; @@ -241,6 +242,10 @@ static int isl68137_probe(struct i2c_client *client, info->pages = 1; info->read_word_data = raa_dmpvr2_read_word_data; break; + case raa_dmpvr2_2rail_nontc: + info->func[0] &= ~PMBUS_HAVE_TEMP; + info->func[1] &= ~PMBUS_HAVE_TEMP; + fallthrough; case raa_dmpvr2_2rail: info->pages = 2; info->read_word_data = raa_dmpvr2_read_word_data; @@ -304,7 +309,7 @@ static const struct i2c_device_id raa_dmpvr_id[] = { {"raa228000", raa_dmpvr2_hv}, {"raa228004", raa_dmpvr2_hv}, {"raa228006", raa_dmpvr2_hv}, - {"raa228228", raa_dmpvr2_2rail}, + {"raa228228", raa_dmpvr2_2rail_nontc}, {"raa229001", raa_dmpvr2_2rail}, {"raa229004", raa_dmpvr2_2rail}, {} diff --git a/drivers/i2c/busses/i2c-bcm-iproc.c b/drivers/i2c/busses/i2c-bcm-iproc.c index 688e92818821..d8295b1c379d 100644 --- a/drivers/i2c/busses/i2c-bcm-iproc.c +++ b/drivers/i2c/busses/i2c-bcm-iproc.c @@ -720,7 +720,7 @@ static int bcm_iproc_i2c_xfer_internal(struct bcm_iproc_i2c_dev *iproc_i2c, /* mark the last byte */ if (!process_call && (i == msg->len - 1)) - val |= 1 << M_TX_WR_STATUS_SHIFT; + val |= BIT(M_TX_WR_STATUS_SHIFT); iproc_i2c_wr_reg(iproc_i2c, M_TX_OFFSET, val); } @@ -738,7 +738,7 @@ static int bcm_iproc_i2c_xfer_internal(struct bcm_iproc_i2c_dev *iproc_i2c, */ addr = i2c_8bit_addr_from_msg(msg); /* mark it the last byte out */ - val = addr | (1 << M_TX_WR_STATUS_SHIFT); + val = addr | BIT(M_TX_WR_STATUS_SHIFT); iproc_i2c_wr_reg(iproc_i2c, M_TX_OFFSET, val); } diff --git a/drivers/i2c/busses/i2c-rcar.c b/drivers/i2c/busses/i2c-rcar.c index 9e883474db8c..c7c543483b08 100644 --- a/drivers/i2c/busses/i2c-rcar.c +++ b/drivers/i2c/busses/i2c-rcar.c @@ -590,6 +590,7 @@ static bool rcar_i2c_slave_irq(struct rcar_i2c_priv *priv) /* master sent stop */ if (ssr_filtered & SSR) { i2c_slave_event(priv->slave, I2C_SLAVE_STOP, &value); + rcar_i2c_write(priv, ICSCR, SIE | SDBS); /* clear our NACK */ rcar_i2c_write(priv, ICSIER, SAR); rcar_i2c_write(priv, ICSSR, ~SSR & 0xff); } diff --git a/drivers/i2c/i2c-core-acpi.c b/drivers/i2c/i2c-core-acpi.c index 2ade99b105b9..e627d7b2790f 100644 --- a/drivers/i2c/i2c-core-acpi.c +++ b/drivers/i2c/i2c-core-acpi.c @@ -276,16 +276,6 @@ void i2c_acpi_register_devices(struct i2c_adapter *adap) dev_warn(&adap->dev, "failed to enumerate I2C slaves\n"); } -const struct acpi_device_id * -i2c_acpi_match_device(const struct acpi_device_id *matches, - struct i2c_client *client) -{ - if (!(client && matches)) - return NULL; - - return acpi_match_device(matches, &client->dev); -} - static const struct acpi_device_id i2c_acpi_force_400khz_device_ids[] = { /* * These Silead touchscreen controllers only work at 400KHz, for diff --git a/drivers/i2c/i2c-core-base.c b/drivers/i2c/i2c-core-base.c index 34a9609f256d..5ec082e2039d 100644 --- a/drivers/i2c/i2c-core-base.c +++ b/drivers/i2c/i2c-core-base.c @@ -480,7 +480,7 @@ static int i2c_device_probe(struct device *dev) * or ACPI ID table is supplied for the probing device. */ if (!driver->id_table && - !i2c_acpi_match_device(dev->driver->acpi_match_table, client) && + !acpi_driver_match_device(dev, dev->driver) && !i2c_of_match_device(dev->driver->of_match_table, client)) { status = -ENODEV; goto put_sync_adapter; diff --git a/drivers/i2c/i2c-core.h b/drivers/i2c/i2c-core.h index 94ff1693b391..8ce261167a2d 100644 --- a/drivers/i2c/i2c-core.h +++ b/drivers/i2c/i2c-core.h @@ -59,20 +59,11 @@ static inline int __i2c_check_suspended(struct i2c_adapter *adap) } #ifdef CONFIG_ACPI -const struct acpi_device_id * -i2c_acpi_match_device(const struct acpi_device_id *matches, - struct i2c_client *client); void i2c_acpi_register_devices(struct i2c_adapter *adap); int i2c_acpi_get_irq(struct i2c_client *client); #else /* CONFIG_ACPI */ static inline void i2c_acpi_register_devices(struct i2c_adapter *adap) { } -static inline const struct acpi_device_id * -i2c_acpi_match_device(const struct acpi_device_id *matches, - struct i2c_client *client) -{ - return NULL; -} static inline int i2c_acpi_get_irq(struct i2c_client *client) { diff --git a/drivers/iio/dac/dpot-dac.c b/drivers/iio/dac/dpot-dac.c index be61c3b01e8b..1a9609eda5c5 100644 --- a/drivers/iio/dac/dpot-dac.c +++ b/drivers/iio/dac/dpot-dac.c @@ -74,10 +74,11 @@ static int dpot_dac_read_raw(struct iio_dev *indio_dev, case IIO_VAL_INT: /* * Convert integer scale to fractional scale by - * setting the denominator (val2) to one, and... + * setting the denominator (val2) to one... */ *val2 = 1; ret = IIO_VAL_FRACTIONAL; + /* ...and fall through. Say it again for GCC. */ fallthrough; case IIO_VAL_FRACTIONAL: *val *= regulator_get_voltage(dac->vref) / 1000; diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 8b743657b957..225380efd1e2 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -6514,9 +6514,12 @@ raid5_store_stripe_size(struct mddev *mddev, const char *page, size_t len) /* * The value should not be bigger than PAGE_SIZE. It requires to - * be multiple of DEFAULT_STRIPE_SIZE. + * be multiple of DEFAULT_STRIPE_SIZE and the value should be power + * of two. */ - if (new % DEFAULT_STRIPE_SIZE != 0 || new > PAGE_SIZE || new == 0) + if (new % DEFAULT_STRIPE_SIZE != 0 || + new > PAGE_SIZE || new == 0 || + new != roundup_pow_of_two(new)) return -EINVAL; err = mddev_lock(mddev); diff --git a/drivers/media/usb/dvb-usb/dib0700_devices.c b/drivers/media/usb/dvb-usb/dib0700_devices.c index a6ae46567a31..52e648e2713a 100644 --- a/drivers/media/usb/dvb-usb/dib0700_devices.c +++ b/drivers/media/usb/dvb-usb/dib0700_devices.c @@ -1659,14 +1659,14 @@ static int dib8096_set_param_override(struct dvb_frontend *fe) switch (band) { default: - deb_info("Warning : Rf frequency (%iHz) is not in the supported range, using VHF switch ", fe->dtv_property_cache.frequency); + deb_info("Warning : Rf frequency (%iHz) is not in the supported range, using VHF switch ", fe->dtv_property_cache.frequency); fallthrough; case BAND_VHF: - state->dib8000_ops.set_gpio(fe, 3, 0, 1); - break; + state->dib8000_ops.set_gpio(fe, 3, 0, 1); + break; case BAND_UHF: - state->dib8000_ops.set_gpio(fe, 3, 0, 0); - break; + state->dib8000_ops.set_gpio(fe, 3, 0, 0); + break; } ret = state->set_param_save(fe); diff --git a/drivers/mfd/mfd-core.c b/drivers/mfd/mfd-core.c index c3651f06684f..fc00aaccb5f7 100644 --- a/drivers/mfd/mfd-core.c +++ b/drivers/mfd/mfd-core.c @@ -126,10 +126,6 @@ static int mfd_match_of_node_to_dev(struct platform_device *pdev, const __be32 *reg; u64 of_node_addr; - /* Skip devices 'disabled' by Device Tree */ - if (!of_device_is_available(np)) - return -ENODEV; - /* Skip if OF node has previously been allocated to a device */ list_for_each_entry(of_entry, &mfd_of_node_list, list) if (of_entry->np == np) @@ -212,6 +208,12 @@ static int mfd_add_device(struct device *parent, int id, if (IS_ENABLED(CONFIG_OF) && parent->of_node && cell->of_compatible) { for_each_child_of_node(parent->of_node, np) { if (of_device_is_compatible(np, cell->of_compatible)) { + /* Ignore 'disabled' devices error free */ + if (!of_device_is_available(np)) { + ret = 0; + goto fail_alias; + } + ret = mfd_match_of_node_to_dev(pdev, np, cell); if (ret == -EAGAIN) continue; @@ -370,8 +372,6 @@ static int mfd_remove_devices_fn(struct device *dev, void *data) regulator_bulk_unregister_supply_alias(dev, cell->parent_supplies, cell->num_parent_supplies); - kfree(cell); - platform_device_unregister(pdev); return 0; } diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c index 140c7bf33a98..90b8f56fbadb 100644 --- a/drivers/xen/events/events_base.c +++ b/drivers/xen/events/events_base.c @@ -156,7 +156,7 @@ int get_evtchn_to_irq(evtchn_port_t evtchn) /* Get info for IRQ */ struct irq_info *info_for_irq(unsigned irq) { - return irq_get_handler_data(irq); + return irq_get_chip_data(irq); } /* Constructors for packed IRQ information. */ @@ -377,7 +377,7 @@ static void xen_irq_init(unsigned irq) info->type = IRQT_UNBOUND; info->refcnt = -1; - irq_set_handler_data(irq, info); + irq_set_chip_data(irq, info); list_add_tail(&info->list, &xen_irq_list_head); } @@ -426,14 +426,14 @@ static int __must_check xen_allocate_irq_gsi(unsigned gsi) static void xen_free_irq(unsigned irq) { - struct irq_info *info = irq_get_handler_data(irq); + struct irq_info *info = irq_get_chip_data(irq); if (WARN_ON(!info)) return; list_del(&info->list); - irq_set_handler_data(irq, NULL); + irq_set_chip_data(irq, NULL); WARN_ON(info->refcnt > 0); @@ -603,7 +603,7 @@ EXPORT_SYMBOL_GPL(xen_irq_from_gsi); static void __unbind_from_irq(unsigned int irq) { evtchn_port_t evtchn = evtchn_from_irq(irq); - struct irq_info *info = irq_get_handler_data(irq); + struct irq_info *info = irq_get_chip_data(irq); if (info->refcnt > 0) { info->refcnt--; @@ -1108,7 +1108,7 @@ int bind_ipi_to_irqhandler(enum ipi_vector ipi, void unbind_from_irqhandler(unsigned int irq, void *dev_id) { - struct irq_info *info = irq_get_handler_data(irq); + struct irq_info *info = irq_get_chip_data(irq); if (WARN_ON(!info)) return; @@ -1142,7 +1142,7 @@ int evtchn_make_refcounted(evtchn_port_t evtchn) if (irq == -1) return -ENOENT; - info = irq_get_handler_data(irq); + info = irq_get_chip_data(irq); if (!info) return -ENOENT; @@ -1170,7 +1170,7 @@ int evtchn_get(evtchn_port_t evtchn) if (irq == -1) goto done; - info = irq_get_handler_data(irq); + info = irq_get_chip_data(irq); if (!info) goto done; diff --git a/drivers/xen/xenbus/xenbus_client.c b/drivers/xen/xenbus/xenbus_client.c index 786fbb7d8be0..907bcbb93afb 100644 --- a/drivers/xen/xenbus/xenbus_client.c +++ b/drivers/xen/xenbus/xenbus_client.c @@ -379,8 +379,14 @@ int xenbus_grant_ring(struct xenbus_device *dev, void *vaddr, int i, j; for (i = 0; i < nr_pages; i++) { - err = gnttab_grant_foreign_access(dev->otherend_id, - virt_to_gfn(vaddr), 0); + unsigned long gfn; + + if (is_vmalloc_addr(vaddr)) + gfn = pfn_to_gfn(vmalloc_to_pfn(vaddr)); + else + gfn = virt_to_gfn(vaddr); + + err = gnttab_grant_foreign_access(dev->otherend_id, gfn, 0); if (err < 0) { xenbus_dev_fatal(dev, err, "granting access to ring page"); diff --git a/fs/afs/flock.c b/fs/afs/flock.c index eff82a6839e4..cb3054c7843e 100644 --- a/fs/afs/flock.c +++ b/fs/afs/flock.c @@ -376,7 +376,6 @@ again: spin_unlock(&vnode->lock); return; - fallthrough; default: /* Looks like a lock request was withdrawn. */ spin_unlock(&vnode->lock); diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index 55ccccf77cea..034b3f4fdd3a 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -887,8 +887,8 @@ int __ceph_caps_issued_mask(struct ceph_inode_info *ci, int mask, int touch) int have = ci->i_snap_caps; if ((have & mask) == mask) { - dout("__ceph_caps_issued_mask ino 0x%lx snap issued %s" - " (mask %s)\n", ci->vfs_inode.i_ino, + dout("__ceph_caps_issued_mask ino 0x%llx snap issued %s" + " (mask %s)\n", ceph_ino(&ci->vfs_inode), ceph_cap_string(have), ceph_cap_string(mask)); return 1; @@ -899,8 +899,8 @@ int __ceph_caps_issued_mask(struct ceph_inode_info *ci, int mask, int touch) if (!__cap_is_valid(cap)) continue; if ((cap->issued & mask) == mask) { - dout("__ceph_caps_issued_mask ino 0x%lx cap %p issued %s" - " (mask %s)\n", ci->vfs_inode.i_ino, cap, + dout("__ceph_caps_issued_mask ino 0x%llx cap %p issued %s" + " (mask %s)\n", ceph_ino(&ci->vfs_inode), cap, ceph_cap_string(cap->issued), ceph_cap_string(mask)); if (touch) @@ -911,8 +911,8 @@ int __ceph_caps_issued_mask(struct ceph_inode_info *ci, int mask, int touch) /* does a combination of caps satisfy mask? */ have |= cap->issued; if ((have & mask) == mask) { - dout("__ceph_caps_issued_mask ino 0x%lx combo issued %s" - " (mask %s)\n", ci->vfs_inode.i_ino, + dout("__ceph_caps_issued_mask ino 0x%llx combo issued %s" + " (mask %s)\n", ceph_ino(&ci->vfs_inode), ceph_cap_string(cap->issued), ceph_cap_string(mask)); if (touch) { @@ -2872,7 +2872,7 @@ int ceph_get_caps(struct file *filp, int need, int want, struct cap_wait cw; DEFINE_WAIT_FUNC(wait, woken_wake_function); - cw.ino = inode->i_ino; + cw.ino = ceph_ino(inode); cw.tgid = current->tgid; cw.need = need; cw.want = want; diff --git a/fs/ceph/debugfs.c b/fs/ceph/debugfs.c index 97539b497e4c..3e3fcda9b276 100644 --- a/fs/ceph/debugfs.c +++ b/fs/ceph/debugfs.c @@ -202,7 +202,7 @@ static int caps_show_cb(struct inode *inode, struct ceph_cap *cap, void *p) { struct seq_file *s = p; - seq_printf(s, "0x%-17lx%-17s%-17s\n", inode->i_ino, + seq_printf(s, "0x%-17llx%-17s%-17s\n", ceph_ino(inode), ceph_cap_string(cap->issued), ceph_cap_string(cap->implemented)); return 0; @@ -247,7 +247,7 @@ static int caps_show(struct seq_file *s, void *p) spin_lock(&mdsc->caps_list_lock); list_for_each_entry(cw, &mdsc->cap_wait_list, list) { - seq_printf(s, "%-13d0x%-17lx%-17s%-17s\n", cw->tgid, cw->ino, + seq_printf(s, "%-13d0x%-17llx%-17s%-17s\n", cw->tgid, cw->ino, ceph_cap_string(cw->need), ceph_cap_string(cw->want)); } diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c index 9ff9d10a60ff..d72e4a12bb69 100644 --- a/fs/ceph/dir.c +++ b/fs/ceph/dir.c @@ -259,9 +259,7 @@ static int __dcache_readdir(struct file *file, struct dir_context *ctx, dentry, dentry, d_inode(dentry)); ctx->pos = di->offset; if (!dir_emit(ctx, dentry->d_name.name, - dentry->d_name.len, - ceph_translate_ino(dentry->d_sb, - d_inode(dentry)->i_ino), + dentry->d_name.len, ceph_present_inode(d_inode(dentry)), d_inode(dentry)->i_mode >> 12)) { dput(dentry); err = 0; @@ -324,18 +322,21 @@ static int ceph_readdir(struct file *file, struct dir_context *ctx) /* always start with . and .. */ if (ctx->pos == 0) { dout("readdir off 0 -> '.'\n"); - if (!dir_emit(ctx, ".", 1, - ceph_translate_ino(inode->i_sb, inode->i_ino), + if (!dir_emit(ctx, ".", 1, ceph_present_inode(inode), inode->i_mode >> 12)) return 0; ctx->pos = 1; } if (ctx->pos == 1) { - ino_t ino = parent_ino(file->f_path.dentry); + u64 ino; + struct dentry *dentry = file->f_path.dentry; + + spin_lock(&dentry->d_lock); + ino = ceph_present_inode(dentry->d_parent->d_inode); + spin_unlock(&dentry->d_lock); + dout("readdir off 1 -> '..'\n"); - if (!dir_emit(ctx, "..", 2, - ceph_translate_ino(inode->i_sb, ino), - inode->i_mode >> 12)) + if (!dir_emit(ctx, "..", 2, ino, inode->i_mode >> 12)) return 0; ctx->pos = 2; } @@ -507,9 +508,6 @@ more: } for (; i < rinfo->dir_nr; i++) { struct ceph_mds_reply_dir_entry *rde = rinfo->dir_entries + i; - struct ceph_vino vino; - ino_t ino; - u32 ftype; BUG_ON(rde->offset < ctx->pos); @@ -519,13 +517,10 @@ more: rde->name_len, rde->name, &rde->inode.in); BUG_ON(!rde->inode.in); - ftype = le32_to_cpu(rde->inode.in->mode) >> 12; - vino.ino = le64_to_cpu(rde->inode.in->ino); - vino.snap = le64_to_cpu(rde->inode.in->snapid); - ino = ceph_vino_to_ino(vino); if (!dir_emit(ctx, rde->name, rde->name_len, - ceph_translate_ino(inode->i_sb, ino), ftype)) { + ceph_present_ino(inode->i_sb, le64_to_cpu(rde->inode.in->ino)), + le32_to_cpu(rde->inode.in->mode) >> 12)) { dout("filldir stopping us...\n"); return 0; } @@ -1161,7 +1156,7 @@ retry: if (try_async && op == CEPH_MDS_OP_UNLINK && (req->r_dir_caps = get_caps_for_async_unlink(dir, dentry))) { - dout("async unlink on %lu/%.*s caps=%s", dir->i_ino, + dout("async unlink on %llu/%.*s caps=%s", ceph_ino(dir), dentry->d_name.len, dentry->d_name.name, ceph_cap_string(req->r_dir_caps)); set_bit(CEPH_MDS_R_ASYNC, &req->r_req_flags); diff --git a/fs/ceph/file.c b/fs/ceph/file.c index 30cd00265181..3f4c993dfc6f 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -630,8 +630,8 @@ static int ceph_finish_async_create(struct inode *dir, struct dentry *dentry, } else { struct dentry *dn; - dout("%s d_adding new inode 0x%llx to 0x%lx/%s\n", __func__, - vino.ino, dir->i_ino, dentry->d_name.name); + dout("%s d_adding new inode 0x%llx to 0x%llx/%s\n", __func__, + vino.ino, ceph_ino(dir), dentry->d_name.name); ceph_dir_clear_ordered(dir); ceph_init_inode_acls(inode, as_ctx); if (inode->i_state & I_NEW) { @@ -2507,6 +2507,7 @@ const struct file_operations ceph_file_fops = { .mmap = ceph_mmap, .fsync = ceph_fsync, .lock = ceph_lock, + .setlease = simple_nosetlease, .flock = ceph_flock, .splice_read = generic_file_splice_read, .splice_write = iter_file_splice_write, diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index 357c937699d5..d163fa96cb40 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -41,8 +41,10 @@ static void ceph_inode_work(struct work_struct *work); */ static int ceph_set_ino_cb(struct inode *inode, void *data) { - ceph_inode(inode)->i_vino = *(struct ceph_vino *)data; - inode->i_ino = ceph_vino_to_ino(*(struct ceph_vino *)data); + struct ceph_inode_info *ci = ceph_inode(inode); + + ci->i_vino = *(struct ceph_vino *)data; + inode->i_ino = ceph_vino_to_ino_t(ci->i_vino); inode_set_iversion_raw(inode, 0); return 0; } @@ -50,17 +52,14 @@ static int ceph_set_ino_cb(struct inode *inode, void *data) struct inode *ceph_get_inode(struct super_block *sb, struct ceph_vino vino) { struct inode *inode; - ino_t t = ceph_vino_to_ino(vino); - inode = iget5_locked(sb, t, ceph_ino_compare, ceph_set_ino_cb, &vino); + inode = iget5_locked(sb, (unsigned long)vino.ino, ceph_ino_compare, + ceph_set_ino_cb, &vino); if (!inode) return ERR_PTR(-ENOMEM); - if (inode->i_state & I_NEW) - dout("get_inode created new inode %p %llx.%llx ino %llx\n", - inode, ceph_vinop(inode), (u64)inode->i_ino); - dout("get_inode on %lu=%llx.%llx got %p\n", inode->i_ino, vino.ino, - vino.snap, inode); + dout("get_inode on %llu=%llx.%llx got %p new %d\n", ceph_present_inode(inode), + ceph_vinop(inode), inode, !!(inode->i_state & I_NEW)); return inode; } @@ -2378,7 +2377,7 @@ int ceph_getattr(const struct path *path, struct kstat *stat, } generic_fillattr(inode, stat); - stat->ino = ceph_translate_ino(inode->i_sb, inode->i_ino); + stat->ino = ceph_present_inode(inode); /* * btime on newly-allocated inodes is 0, so if this is still set to diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h index bc9e95937d7c..658800605bfb 100644 --- a/fs/ceph/mds_client.h +++ b/fs/ceph/mds_client.h @@ -372,7 +372,7 @@ struct ceph_quotarealm_inode { struct cap_wait { struct list_head list; - unsigned long ino; + u64 ino; pid_t tgid; int need; int want; diff --git a/fs/ceph/quota.c b/fs/ceph/quota.c index 198ddde5c1e6..cc2c4d40b022 100644 --- a/fs/ceph/quota.c +++ b/fs/ceph/quota.c @@ -23,12 +23,12 @@ static inline bool ceph_has_realms_with_quotas(struct inode *inode) { struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc; struct super_block *sb = mdsc->fsc->sb; + struct inode *root = d_inode(sb->s_root); if (atomic64_read(&mdsc->quotarealms_count) > 0) return true; /* if root is the real CephFS root, we don't have quota realms */ - if (sb->s_root->d_inode && - (sb->s_root->d_inode->i_ino == CEPH_INO_ROOT)) + if (root && ceph_ino(root) == CEPH_INO_ROOT) return false; /* otherwise, we can't know for sure */ return true; diff --git a/fs/ceph/super.h b/fs/ceph/super.h index 4c3c964b1c54..a3995ebe0623 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -457,15 +457,7 @@ ceph_vino(const struct inode *inode) return ceph_inode(inode)->i_vino; } -/* - * ino_t is <64 bits on many architectures, blech. - * - * i_ino (kernel inode) st_ino (userspace) - * i386 32 32 - * x86_64+ino32 64 32 - * x86_64 64 64 - */ -static inline u32 ceph_ino_to_ino32(__u64 vino) +static inline u32 ceph_ino_to_ino32(u64 vino) { u32 ino = vino & 0xffffffff; ino ^= vino >> 32; @@ -475,34 +467,17 @@ static inline u32 ceph_ino_to_ino32(__u64 vino) } /* - * kernel i_ino value + * Inode numbers in cephfs are 64 bits, but inode->i_ino is 32-bits on + * some arches. We generally do not use this value inside the ceph driver, but + * we do want to set it to something, so that generic vfs code has an + * appropriate value for tracepoints and the like. */ -static inline ino_t ceph_vino_to_ino(struct ceph_vino vino) +static inline ino_t ceph_vino_to_ino_t(struct ceph_vino vino) { -#if BITS_PER_LONG == 32 - return ceph_ino_to_ino32(vino.ino); -#else + if (sizeof(ino_t) == sizeof(u32)) + return ceph_ino_to_ino32(vino.ino); return (ino_t)vino.ino; -#endif -} - -/* - * user-visible ino (stat, filldir) - */ -#if BITS_PER_LONG == 32 -static inline ino_t ceph_translate_ino(struct super_block *sb, ino_t ino) -{ - return ino; -} -#else -static inline ino_t ceph_translate_ino(struct super_block *sb, ino_t ino) -{ - if (ceph_test_mount_opt(ceph_sb_to_client(sb), INO32)) - ino = ceph_ino_to_ino32(ino); - return ino; } -#endif - /* for printf-style formatting */ #define ceph_vinop(i) ceph_inode(i)->i_vino.ino, ceph_inode(i)->i_vino.snap @@ -511,11 +486,34 @@ static inline u64 ceph_ino(struct inode *inode) { return ceph_inode(inode)->i_vino.ino; } + static inline u64 ceph_snap(struct inode *inode) { return ceph_inode(inode)->i_vino.snap; } +/** + * ceph_present_ino - format an inode number for presentation to userland + * @sb: superblock where the inode lives + * @ino: inode number to (possibly) convert + * + * If the user mounted with the ino32 option, then the 64-bit value needs + * to be converted to something that can fit inside 32 bits. Note that + * internal kernel code never uses this value, so this is entirely for + * userland consumption. + */ +static inline u64 ceph_present_ino(struct super_block *sb, u64 ino) +{ + if (unlikely(ceph_test_mount_opt(ceph_sb_to_client(sb), INO32))) + return ceph_ino_to_ino32(ino); + return ino; +} + +static inline u64 ceph_present_inode(struct inode *inode) +{ + return ceph_present_ino(inode->i_sb, ceph_ino(inode)); +} + static inline int ceph_ino_compare(struct inode *inode, void *data) { struct ceph_vino *pvino = (struct ceph_vino *)data; @@ -524,11 +522,16 @@ static inline int ceph_ino_compare(struct inode *inode, void *data) ci->i_vino.snap == pvino->snap; } + static inline struct inode *ceph_find_inode(struct super_block *sb, struct ceph_vino vino) { - ino_t t = ceph_vino_to_ino(vino); - return ilookup5(sb, t, ceph_ino_compare, &vino); + /* + * NB: The hashval will be run through the fs/inode.c hash function + * anyway, so there is no need to squash the inode number down to + * 32-bits first. Just use low-order bits on arches with 32-bit long. + */ + return ilookup5(sb, (unsigned long)vino.ino, ceph_ino_compare, &vino); } diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 3a196d81f594..bf596467c234 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -4901,7 +4901,7 @@ static void __ext4_update_other_inode_time(struct super_block *sb, (inode->i_state & I_DIRTY_TIME)) { struct ext4_inode_info *ei = EXT4_I(inode); - inode->i_state &= ~(I_DIRTY_TIME | I_DIRTY_TIME_EXPIRED); + inode->i_state &= ~I_DIRTY_TIME; spin_unlock(&inode->i_lock); spin_lock(&ei->i_raw_lock); diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index a605c3dddabc..149227160ff0 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -42,7 +42,6 @@ struct wb_writeback_work { long nr_pages; struct super_block *sb; - unsigned long *older_than_this; enum writeback_sync_modes sync_mode; unsigned int tagged_writepages:1; unsigned int for_kupdate:1; @@ -144,7 +143,9 @@ static void inode_io_list_del_locked(struct inode *inode, struct bdi_writeback *wb) { assert_spin_locked(&wb->list_lock); + assert_spin_locked(&inode->i_lock); + inode->i_state &= ~I_SYNC_QUEUED; list_del_init(&inode->i_io_list); wb_io_lists_depopulated(wb); } @@ -1122,7 +1123,9 @@ void inode_io_list_del(struct inode *inode) struct bdi_writeback *wb; wb = inode_to_wb_and_lock_list(inode); + spin_lock(&inode->i_lock); inode_io_list_del_locked(inode, wb); + spin_unlock(&inode->i_lock); spin_unlock(&wb->list_lock); } EXPORT_SYMBOL(inode_io_list_del); @@ -1172,8 +1175,10 @@ void sb_clear_inode_writeback(struct inode *inode) * the case then the inode must have been redirtied while it was being written * out and we don't reset its dirtied_when. */ -static void redirty_tail(struct inode *inode, struct bdi_writeback *wb) +static void redirty_tail_locked(struct inode *inode, struct bdi_writeback *wb) { + assert_spin_locked(&inode->i_lock); + if (!list_empty(&wb->b_dirty)) { struct inode *tail; @@ -1182,6 +1187,14 @@ static void redirty_tail(struct inode *inode, struct bdi_writeback *wb) inode->dirtied_when = jiffies; } inode_io_list_move_locked(inode, wb, &wb->b_dirty); + inode->i_state &= ~I_SYNC_QUEUED; +} + +static void redirty_tail(struct inode *inode, struct bdi_writeback *wb) +{ + spin_lock(&inode->i_lock); + redirty_tail_locked(inode, wb); + spin_unlock(&inode->i_lock); } /* @@ -1220,16 +1233,13 @@ static bool inode_dirtied_after(struct inode *inode, unsigned long t) #define EXPIRE_DIRTY_ATIME 0x0001 /* - * Move expired (dirtied before work->older_than_this) dirty inodes from + * Move expired (dirtied before dirtied_before) dirty inodes from * @delaying_queue to @dispatch_queue. */ static int move_expired_inodes(struct list_head *delaying_queue, struct list_head *dispatch_queue, - int flags, - struct wb_writeback_work *work) + unsigned long dirtied_before) { - unsigned long *older_than_this = NULL; - unsigned long expire_time; LIST_HEAD(tmp); struct list_head *pos, *node; struct super_block *sb = NULL; @@ -1237,21 +1247,15 @@ static int move_expired_inodes(struct list_head *delaying_queue, int do_sb_sort = 0; int moved = 0; - if ((flags & EXPIRE_DIRTY_ATIME) == 0) - older_than_this = work->older_than_this; - else if (!work->for_sync) { - expire_time = jiffies - (dirtytime_expire_interval * HZ); - older_than_this = &expire_time; - } while (!list_empty(delaying_queue)) { inode = wb_inode(delaying_queue->prev); - if (older_than_this && - inode_dirtied_after(inode, *older_than_this)) + if (inode_dirtied_after(inode, dirtied_before)) break; list_move(&inode->i_io_list, &tmp); moved++; - if (flags & EXPIRE_DIRTY_ATIME) - set_bit(__I_DIRTY_TIME_EXPIRED, &inode->i_state); + spin_lock(&inode->i_lock); + inode->i_state |= I_SYNC_QUEUED; + spin_unlock(&inode->i_lock); if (sb_is_blkdev_sb(inode->i_sb)) continue; if (sb && sb != inode->i_sb) @@ -1289,18 +1293,22 @@ out: * | * +--> dequeue for IO */ -static void queue_io(struct bdi_writeback *wb, struct wb_writeback_work *work) +static void queue_io(struct bdi_writeback *wb, struct wb_writeback_work *work, + unsigned long dirtied_before) { int moved; + unsigned long time_expire_jif = dirtied_before; assert_spin_locked(&wb->list_lock); list_splice_init(&wb->b_more_io, &wb->b_io); - moved = move_expired_inodes(&wb->b_dirty, &wb->b_io, 0, work); + moved = move_expired_inodes(&wb->b_dirty, &wb->b_io, dirtied_before); + if (!work->for_sync) + time_expire_jif = jiffies - dirtytime_expire_interval * HZ; moved += move_expired_inodes(&wb->b_dirty_time, &wb->b_io, - EXPIRE_DIRTY_ATIME, work); + time_expire_jif); if (moved) wb_io_lists_populated(wb); - trace_writeback_queue_io(wb, work, moved); + trace_writeback_queue_io(wb, work, dirtied_before, moved); } static int write_inode(struct inode *inode, struct writeback_control *wbc) @@ -1394,7 +1402,7 @@ static void requeue_inode(struct inode *inode, struct bdi_writeback *wb, * writeback is not making progress due to locked * buffers. Skip this inode for now. */ - redirty_tail(inode, wb); + redirty_tail_locked(inode, wb); return; } @@ -1414,7 +1422,7 @@ static void requeue_inode(struct inode *inode, struct bdi_writeback *wb, * retrying writeback of the dirty page/inode * that cannot be performed immediately. */ - redirty_tail(inode, wb); + redirty_tail_locked(inode, wb); } } else if (inode->i_state & I_DIRTY) { /* @@ -1422,10 +1430,11 @@ static void requeue_inode(struct inode *inode, struct bdi_writeback *wb, * such as delayed allocation during submission or metadata * updates after data IO completion. */ - redirty_tail(inode, wb); + redirty_tail_locked(inode, wb); } else if (inode->i_state & I_DIRTY_TIME) { inode->dirtied_when = jiffies; inode_io_list_move_locked(inode, wb, &wb->b_dirty_time); + inode->i_state &= ~I_SYNC_QUEUED; } else { /* The inode is clean. Remove from writeback lists. */ inode_io_list_del_locked(inode, wb); @@ -1472,18 +1481,14 @@ __writeback_single_inode(struct inode *inode, struct writeback_control *wbc) spin_lock(&inode->i_lock); dirty = inode->i_state & I_DIRTY; - if (inode->i_state & I_DIRTY_TIME) { - if ((dirty & I_DIRTY_INODE) || - wbc->sync_mode == WB_SYNC_ALL || - unlikely(inode->i_state & I_DIRTY_TIME_EXPIRED) || - unlikely(time_after(jiffies, - (inode->dirtied_time_when + - dirtytime_expire_interval * HZ)))) { - dirty |= I_DIRTY_TIME | I_DIRTY_TIME_EXPIRED; - trace_writeback_lazytime(inode); - } - } else - inode->i_state &= ~I_DIRTY_TIME_EXPIRED; + if ((inode->i_state & I_DIRTY_TIME) && + ((dirty & I_DIRTY_INODE) || + wbc->sync_mode == WB_SYNC_ALL || wbc->for_sync || + time_after(jiffies, inode->dirtied_time_when + + dirtytime_expire_interval * HZ))) { + dirty |= I_DIRTY_TIME; + trace_writeback_lazytime(inode); + } inode->i_state &= ~dirty; /* @@ -1669,8 +1674,8 @@ static long writeback_sb_inodes(struct super_block *sb, */ spin_lock(&inode->i_lock); if (inode->i_state & (I_NEW | I_FREEING | I_WILL_FREE)) { + redirty_tail_locked(inode, wb); spin_unlock(&inode->i_lock); - redirty_tail(inode, wb); continue; } if ((inode->i_state & I_SYNC) && wbc.sync_mode != WB_SYNC_ALL) { @@ -1811,7 +1816,7 @@ static long writeback_inodes_wb(struct bdi_writeback *wb, long nr_pages, blk_start_plug(&plug); spin_lock(&wb->list_lock); if (list_empty(&wb->b_io)) - queue_io(wb, &work); + queue_io(wb, &work, jiffies); __writeback_inodes_wb(wb, &work); spin_unlock(&wb->list_lock); blk_finish_plug(&plug); @@ -1831,7 +1836,7 @@ static long writeback_inodes_wb(struct bdi_writeback *wb, long nr_pages, * takes longer than a dirty_writeback_interval interval, then leave a * one-second gap. * - * older_than_this takes precedence over nr_to_write. So we'll only write back + * dirtied_before takes precedence over nr_to_write. So we'll only write back * all dirty pages if they are all attached to "old" mappings. */ static long wb_writeback(struct bdi_writeback *wb, @@ -1839,14 +1844,11 @@ static long wb_writeback(struct bdi_writeback *wb, { unsigned long wb_start = jiffies; long nr_pages = work->nr_pages; - unsigned long oldest_jif; + unsigned long dirtied_before = jiffies; struct inode *inode; long progress; struct blk_plug plug; - oldest_jif = jiffies; - work->older_than_this = &oldest_jif; - blk_start_plug(&plug); spin_lock(&wb->list_lock); for (;;) { @@ -1880,14 +1882,14 @@ static long wb_writeback(struct bdi_writeback *wb, * safe. */ if (work->for_kupdate) { - oldest_jif = jiffies - + dirtied_before = jiffies - msecs_to_jiffies(dirty_expire_interval * 10); } else if (work->for_background) - oldest_jif = jiffies; + dirtied_before = jiffies; trace_writeback_start(wb, work); if (list_empty(&wb->b_io)) - queue_io(wb, work); + queue_io(wb, work, dirtied_before); if (work->sb) progress = writeback_sb_inodes(work->sb, wb, work); else @@ -2289,11 +2291,12 @@ void __mark_inode_dirty(struct inode *inode, int flags) inode->i_state |= flags; /* - * If the inode is being synced, just update its dirty state. - * The unlocker will place the inode on the appropriate - * superblock list, based upon its state. + * If the inode is queued for writeback by flush worker, just + * update its dirty state. Once the flush worker is done with + * the inode it will place it on the appropriate superblock + * list, based upon its state. */ - if (inode->i_state & I_SYNC) + if (inode->i_state & I_SYNC_QUEUED) goto out_unlock_inode; /* diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c index a58333e3980d..3763c9ff1406 100644 --- a/fs/gfs2/log.c +++ b/fs/gfs2/log.c @@ -902,6 +902,36 @@ static void empty_ail1_list(struct gfs2_sbd *sdp) } /** + * drain_bd - drain the buf and databuf queue for a failed transaction + * @tr: the transaction to drain + * + * When this is called, we're taking an error exit for a log write that failed + * but since we bypassed the after_commit functions, we need to remove the + * items from the buf and databuf queue. + */ +static void trans_drain(struct gfs2_trans *tr) +{ + struct gfs2_bufdata *bd; + struct list_head *head; + + if (!tr) + return; + + head = &tr->tr_buf; + while (!list_empty(head)) { + bd = list_first_entry(head, struct gfs2_bufdata, bd_list); + list_del_init(&bd->bd_list); + kmem_cache_free(gfs2_bufdata_cachep, bd); + } + head = &tr->tr_databuf; + while (!list_empty(head)) { + bd = list_first_entry(head, struct gfs2_bufdata, bd_list); + list_del_init(&bd->bd_list); + kmem_cache_free(gfs2_bufdata_cachep, bd); + } +} + +/** * gfs2_log_flush - flush incore transaction(s) * @sdp: the filesystem * @gl: The glock structure to flush. If NULL, flush the whole incore log @@ -1005,6 +1035,7 @@ void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl, u32 flags) out: if (gfs2_withdrawn(sdp)) { + trans_drain(tr); /** * If the tr_list is empty, we're withdrawing during a log * flush that targets a transaction, but the transaction was diff --git a/fs/gfs2/trans.c b/fs/gfs2/trans.c index e1c7eb6eb00a..6d4bf7ea7b3b 100644 --- a/fs/gfs2/trans.c +++ b/fs/gfs2/trans.c @@ -67,6 +67,7 @@ int gfs2_trans_begin(struct gfs2_sbd *sdp, unsigned int blocks, tr->tr_reserved += gfs2_struct2blk(sdp, revokes); INIT_LIST_HEAD(&tr->tr_databuf); INIT_LIST_HEAD(&tr->tr_buf); + INIT_LIST_HEAD(&tr->tr_list); INIT_LIST_HEAD(&tr->tr_ail1_list); INIT_LIST_HEAD(&tr->tr_ail2_list); diff --git a/fs/io-wq.c b/fs/io-wq.c index e92c4724480c..414beb543883 100644 --- a/fs/io-wq.c +++ b/fs/io-wq.c @@ -925,6 +925,24 @@ static bool io_wq_worker_cancel(struct io_worker *worker, void *data) return match->nr_running && !match->cancel_all; } +static inline void io_wqe_remove_pending(struct io_wqe *wqe, + struct io_wq_work *work, + struct io_wq_work_node *prev) +{ + unsigned int hash = io_get_work_hash(work); + struct io_wq_work *prev_work = NULL; + + if (io_wq_is_hashed(work) && work == wqe->hash_tail[hash]) { + if (prev) + prev_work = container_of(prev, struct io_wq_work, list); + if (prev_work && io_get_work_hash(prev_work) == hash) + wqe->hash_tail[hash] = prev_work; + else + wqe->hash_tail[hash] = NULL; + } + wq_list_del(&wqe->work_list, &work->list, prev); +} + static void io_wqe_cancel_pending_work(struct io_wqe *wqe, struct io_cb_cancel_data *match) { @@ -938,8 +956,7 @@ retry: work = container_of(node, struct io_wq_work, list); if (!match->fn(work, match->data)) continue; - - wq_list_del(&wqe->work_list, node, prev); + io_wqe_remove_pending(wqe, work, prev); spin_unlock_irqrestore(&wqe->lock, flags); io_run_cancel(work, wqe); match->nr_pending++; diff --git a/fs/io_uring.c b/fs/io_uring.c index 8a53af8e5fe2..ce69bd9b0838 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -1150,7 +1150,7 @@ static void io_prep_async_work(struct io_kiocb *req) io_req_init_async(req); if (req->flags & REQ_F_ISREG) { - if (def->hash_reg_file) + if (def->hash_reg_file || (req->ctx->flags & IORING_SETUP_IOPOLL)) io_wq_hash_work(&req->work, file_inode(req->file)); } else { if (def->unbound_nonreg_file) @@ -1746,7 +1746,8 @@ static struct io_kiocb *io_req_find_next(struct io_kiocb *req) return __io_req_find_next(req); } -static int io_req_task_work_add(struct io_kiocb *req, struct callback_head *cb) +static int io_req_task_work_add(struct io_kiocb *req, struct callback_head *cb, + bool twa_signal_ok) { struct task_struct *tsk = req->task; struct io_ring_ctx *ctx = req->ctx; @@ -1759,7 +1760,7 @@ static int io_req_task_work_add(struct io_kiocb *req, struct callback_head *cb) * will do the job. */ notify = 0; - if (!(ctx->flags & IORING_SETUP_SQPOLL)) + if (!(ctx->flags & IORING_SETUP_SQPOLL) && twa_signal_ok) notify = TWA_SIGNAL; ret = task_work_add(tsk, cb, notify); @@ -1819,7 +1820,7 @@ static void io_req_task_queue(struct io_kiocb *req) init_task_work(&req->task_work, io_req_task_submit); percpu_ref_get(&req->ctx->refs); - ret = io_req_task_work_add(req, &req->task_work); + ret = io_req_task_work_add(req, &req->task_work, true); if (unlikely(ret)) { struct task_struct *tsk; @@ -2048,6 +2049,7 @@ static void io_iopoll_complete(struct io_ring_ctx *ctx, unsigned int *nr_events, req = list_first_entry(done, struct io_kiocb, inflight_entry); if (READ_ONCE(req->result) == -EAGAIN) { + req->result = 0; req->iopoll_completed = 0; list_move_tail(&req->inflight_entry, &again); continue; @@ -2293,22 +2295,6 @@ end_req: io_req_complete(req, ret); return false; } - -static void io_rw_resubmit(struct callback_head *cb) -{ - struct io_kiocb *req = container_of(cb, struct io_kiocb, task_work); - struct io_ring_ctx *ctx = req->ctx; - int err; - - err = io_sq_thread_acquire_mm(ctx, req); - - if (io_resubmit_prep(req, err)) { - refcount_inc(&req->refs); - io_queue_async_work(req); - } - - percpu_ref_put(&ctx->refs); -} #endif static bool io_rw_reissue(struct io_kiocb *req, long res) @@ -2319,12 +2305,14 @@ static bool io_rw_reissue(struct io_kiocb *req, long res) if ((res != -EAGAIN && res != -EOPNOTSUPP) || io_wq_current_is_worker()) return false; - init_task_work(&req->task_work, io_rw_resubmit); - percpu_ref_get(&req->ctx->refs); + ret = io_sq_thread_acquire_mm(req->ctx, req); - ret = io_req_task_work_add(req, &req->task_work); - if (!ret) + if (io_resubmit_prep(req, ret)) { + refcount_inc(&req->refs); + io_queue_async_work(req); return true; + } + #endif return false; } @@ -2865,6 +2853,11 @@ static ssize_t io_import_iovec(int rw, struct io_kiocb *req, return iov_iter_count(&req->io->rw.iter); } +static inline loff_t *io_kiocb_ppos(struct kiocb *kiocb) +{ + return kiocb->ki_filp->f_mode & FMODE_STREAM ? NULL : &kiocb->ki_pos; +} + /* * For files that don't have ->read_iter() and ->write_iter(), handle them * by looping over ->read() or ->write() manually. @@ -2900,10 +2893,10 @@ static ssize_t loop_rw_iter(int rw, struct file *file, struct kiocb *kiocb, if (rw == READ) { nr = file->f_op->read(file, iovec.iov_base, - iovec.iov_len, &kiocb->ki_pos); + iovec.iov_len, io_kiocb_ppos(kiocb)); } else { nr = file->f_op->write(file, iovec.iov_base, - iovec.iov_len, &kiocb->ki_pos); + iovec.iov_len, io_kiocb_ppos(kiocb)); } if (iov_iter_is_bvec(iter)) @@ -3044,7 +3037,7 @@ static int io_async_buf_func(struct wait_queue_entry *wait, unsigned mode, /* submit ref gets dropped, acquire a new one */ refcount_inc(&req->refs); - ret = io_req_task_work_add(req, &req->task_work); + ret = io_req_task_work_add(req, &req->task_work, true); if (unlikely(ret)) { struct task_struct *tsk; @@ -3125,6 +3118,7 @@ static int io_read(struct io_kiocb *req, bool force_nonblock, ret = io_import_iovec(READ, req, &iovec, iter, !force_nonblock); if (ret < 0) return ret; + iov_count = iov_iter_count(iter); io_size = ret; req->result = io_size; ret = 0; @@ -3137,8 +3131,7 @@ static int io_read(struct io_kiocb *req, bool force_nonblock, if (force_nonblock && !io_file_supports_async(req->file, READ)) goto copy_iov; - iov_count = iov_iter_count(iter); - ret = rw_verify_area(READ, req->file, &kiocb->ki_pos, iov_count); + ret = rw_verify_area(READ, req->file, io_kiocb_ppos(kiocb), iov_count); if (unlikely(ret)) goto out_free; @@ -3150,14 +3143,18 @@ static int io_read(struct io_kiocb *req, bool force_nonblock, ret = 0; goto out_free; } else if (ret == -EAGAIN) { - if (!force_nonblock) + /* IOPOLL retry should happen for io-wq threads */ + if (!force_nonblock && !(req->ctx->flags & IORING_SETUP_IOPOLL)) goto done; + /* some cases will consume bytes even on error returns */ + iov_iter_revert(iter, iov_count - iov_iter_count(iter)); ret = io_setup_async_rw(req, iovec, inline_vecs, iter, false); if (ret) goto out_free; return -EAGAIN; } else if (ret < 0) { - goto out_free; + /* make sure -ERESTARTSYS -> -EINTR is done */ + goto done; } /* read it all, or we did blocking attempt. no retry. */ @@ -3241,6 +3238,7 @@ static int io_write(struct io_kiocb *req, bool force_nonblock, ret = io_import_iovec(WRITE, req, &iovec, iter, !force_nonblock); if (ret < 0) return ret; + iov_count = iov_iter_count(iter); io_size = ret; req->result = io_size; @@ -3257,8 +3255,7 @@ static int io_write(struct io_kiocb *req, bool force_nonblock, (req->flags & REQ_F_ISREG)) goto copy_iov; - iov_count = iov_iter_count(iter); - ret = rw_verify_area(WRITE, req->file, &kiocb->ki_pos, iov_count); + ret = rw_verify_area(WRITE, req->file, io_kiocb_ppos(kiocb), iov_count); if (unlikely(ret)) goto out_free; @@ -3291,9 +3288,14 @@ static int io_write(struct io_kiocb *req, bool force_nonblock, if (ret2 == -EOPNOTSUPP && (kiocb->ki_flags & IOCB_NOWAIT)) ret2 = -EAGAIN; if (!force_nonblock || ret2 != -EAGAIN) { + /* IOPOLL retry should happen for io-wq threads */ + if ((req->ctx->flags & IORING_SETUP_IOPOLL) && ret2 == -EAGAIN) + goto copy_iov; kiocb_done(kiocb, ret2, cs); } else { copy_iov: + /* some cases will consume bytes even on error returns */ + iov_iter_revert(iter, iov_count - iov_iter_count(iter)); ret = io_setup_async_rw(req, iovec, inline_vecs, iter, false); if (!ret) return -EAGAIN; @@ -4566,6 +4568,7 @@ struct io_poll_table { static int __io_async_wake(struct io_kiocb *req, struct io_poll_iocb *poll, __poll_t mask, task_work_func_t func) { + bool twa_signal_ok; int ret; /* for instances that support it check for an event match first: */ @@ -4581,12 +4584,20 @@ static int __io_async_wake(struct io_kiocb *req, struct io_poll_iocb *poll, percpu_ref_get(&req->ctx->refs); /* + * If we using the signalfd wait_queue_head for this wakeup, then + * it's not safe to use TWA_SIGNAL as we could be recursing on the + * tsk->sighand->siglock on doing the wakeup. Should not be needed + * either, as the normal wakeup will suffice. + */ + twa_signal_ok = (poll->head != &req->task->sighand->signalfd_wqh); + + /* * If this fails, then the task is exiting. When a task exits, the * work gets canceled, so just cancel this request as well instead * of executing it. We can't safely execute it anyway, as we may not * have the needed state needed for it anyway. */ - ret = io_req_task_work_add(req, &req->task_work); + ret = io_req_task_work_add(req, &req->task_work, twa_signal_ok); if (unlikely(ret)) { struct task_struct *tsk; @@ -4875,12 +4886,20 @@ static bool io_arm_poll_handler(struct io_kiocb *req) struct async_poll *apoll; struct io_poll_table ipt; __poll_t mask, ret; + int rw; if (!req->file || !file_can_poll(req->file)) return false; if (req->flags & REQ_F_POLLED) return false; - if (!def->pollin && !def->pollout) + if (def->pollin) + rw = READ; + else if (def->pollout) + rw = WRITE; + else + return false; + /* if we can't nonblock try, then no point in arming a poll handler */ + if (!io_file_supports_async(req->file, rw)) return false; apoll = kmalloc(sizeof(*apoll), GFP_ATOMIC); @@ -7433,9 +7452,6 @@ static int io_sq_offload_start(struct io_ring_ctx *ctx, { int ret; - mmgrab(current->mm); - ctx->sqo_mm = current->mm; - if (ctx->flags & IORING_SETUP_SQPOLL) { ret = -EPERM; if (!capable(CAP_SYS_ADMIN)) @@ -7480,10 +7496,6 @@ static int io_sq_offload_start(struct io_ring_ctx *ctx, return 0; err: io_finish_async(ctx); - if (ctx->sqo_mm) { - mmdrop(ctx->sqo_mm); - ctx->sqo_mm = NULL; - } return ret; } @@ -8533,6 +8545,9 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p, ctx->user = user; ctx->creds = get_current_cred(); + mmgrab(current->mm); + ctx->sqo_mm = current->mm; + /* * Account memory _before_ installing the file descriptor. Once * the descriptor is installed, it can get closed at any time. Also diff --git a/fs/xfs/libxfs/xfs_trans_inode.c b/fs/xfs/libxfs/xfs_trans_inode.c index e15129647e00..b7e222befb08 100644 --- a/fs/xfs/libxfs/xfs_trans_inode.c +++ b/fs/xfs/libxfs/xfs_trans_inode.c @@ -110,9 +110,9 @@ xfs_trans_log_inode( * to log the timestamps, or will clear already cleared fields in the * worst case. */ - if (inode->i_state & (I_DIRTY_TIME | I_DIRTY_TIME_EXPIRED)) { + if (inode->i_state & I_DIRTY_TIME) { spin_lock(&inode->i_lock); - inode->i_state &= ~(I_DIRTY_TIME | I_DIRTY_TIME_EXPIRED); + inode->i_state &= ~I_DIRTY_TIME; spin_unlock(&inode->i_lock); } diff --git a/include/drm/drm_modeset_lock.h b/include/drm/drm_modeset_lock.h index 4fc9a43ac45a..aafd07388eb7 100644 --- a/include/drm/drm_modeset_lock.h +++ b/include/drm/drm_modeset_lock.h @@ -164,6 +164,8 @@ int drm_modeset_lock_all_ctx(struct drm_device *dev, * is 0, so no error checking is necessary */ #define DRM_MODESET_LOCK_ALL_BEGIN(dev, ctx, flags, ret) \ + if (!drm_drv_uses_atomic_modeset(dev)) \ + mutex_lock(&dev->mode_config.mutex); \ drm_modeset_acquire_init(&ctx, flags); \ modeset_lock_retry: \ ret = drm_modeset_lock_all_ctx(dev, &ctx); \ @@ -172,6 +174,7 @@ modeset_lock_retry: \ /** * DRM_MODESET_LOCK_ALL_END - Helper to release and cleanup modeset locks + * @dev: drm device * @ctx: local modeset acquire context, will be dereferenced * @ret: local ret/err/etc variable to track error status * @@ -188,7 +191,7 @@ modeset_lock_retry: \ * to that failure. In both of these cases the code between BEGIN/END will not * be run, so the failure will reflect the inability to grab the locks. */ -#define DRM_MODESET_LOCK_ALL_END(ctx, ret) \ +#define DRM_MODESET_LOCK_ALL_END(dev, ctx, ret) \ modeset_lock_fail: \ if (ret == -EDEADLK) { \ ret = drm_modeset_backoff(&ctx); \ @@ -196,6 +199,8 @@ modeset_lock_fail: \ goto modeset_lock_retry; \ } \ drm_modeset_drop_locks(&ctx); \ - drm_modeset_acquire_fini(&ctx); + drm_modeset_acquire_fini(&ctx); \ + if (!drm_drv_uses_atomic_modeset(dev)) \ + mutex_unlock(&dev->mode_config.mutex); #endif /* DRM_MODESET_LOCK_H_ */ diff --git a/include/linux/ceph/ceph_features.h b/include/linux/ceph/ceph_features.h index fcd84e8d88f4..999636d53cf2 100644 --- a/include/linux/ceph/ceph_features.h +++ b/include/linux/ceph/ceph_features.h @@ -11,14 +11,14 @@ #define CEPH_FEATURE_INCARNATION_2 (1ull<<57) // CEPH_FEATURE_SERVER_JEWEL #define DEFINE_CEPH_FEATURE(bit, incarnation, name) \ - static const uint64_t CEPH_FEATURE_##name = (1ULL<<bit); \ - static const uint64_t CEPH_FEATUREMASK_##name = \ + static const uint64_t __maybe_unused CEPH_FEATURE_##name = (1ULL<<bit); \ + static const uint64_t __maybe_unused CEPH_FEATUREMASK_##name = \ (1ULL<<bit | CEPH_FEATURE_INCARNATION_##incarnation); /* this bit is ignored but still advertised by release *when* */ #define DEFINE_CEPH_FEATURE_DEPRECATED(bit, incarnation, name, when) \ - static const uint64_t DEPRECATED_CEPH_FEATURE_##name = (1ULL<<bit); \ - static const uint64_t DEPRECATED_CEPH_FEATUREMASK_##name = \ + static const uint64_t __maybe_unused DEPRECATED_CEPH_FEATURE_##name = (1ULL<<bit); \ + static const uint64_t __maybe_unused DEPRECATED_CEPH_FEATUREMASK_##name = \ (1ULL<<bit | CEPH_FEATURE_INCARNATION_##incarnation); /* diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 8f141d4c859c..a911e5d06845 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -956,8 +956,8 @@ static inline int cpufreq_frequency_table_target(struct cpufreq_policy *policy, case CPUFREQ_RELATION_C: return cpufreq_table_find_index_c(policy, target_freq); default: - pr_err("%s: Invalid relation: %d\n", __func__, relation); - return -EINVAL; + WARN_ON_ONCE(1); + return 0; } } diff --git a/include/linux/fs.h b/include/linux/fs.h index e019ea2f1347..7519ae003a08 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2132,6 +2132,10 @@ static inline void kiocb_clone(struct kiocb *kiocb, struct kiocb *kiocb_src, * * I_DONTCACHE Evict inode as soon as it is not used anymore. * + * I_SYNC_QUEUED Inode is queued in b_io or b_more_io writeback lists. + * Used to detect that mark_inode_dirty() should not move + * inode between dirty lists. + * * Q: What is the difference between I_WILL_FREE and I_FREEING? */ #define I_DIRTY_SYNC (1 << 0) @@ -2149,12 +2153,11 @@ static inline void kiocb_clone(struct kiocb *kiocb, struct kiocb *kiocb_src, #define I_DIO_WAKEUP (1 << __I_DIO_WAKEUP) #define I_LINKABLE (1 << 10) #define I_DIRTY_TIME (1 << 11) -#define __I_DIRTY_TIME_EXPIRED 12 -#define I_DIRTY_TIME_EXPIRED (1 << __I_DIRTY_TIME_EXPIRED) #define I_WB_SWITCH (1 << 13) #define I_OVL_INUSE (1 << 14) #define I_CREATING (1 << 15) #define I_DONTCACHE (1 << 16) +#define I_SYNC_QUEUED (1 << 17) #define I_DIRTY_INODE (I_DIRTY_SYNC | I_DIRTY_DATASYNC) #define I_DIRTY (I_DIRTY_INODE | I_DIRTY_PAGES) diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 500def620d8f..c25b8e41c0ea 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -186,7 +186,7 @@ * lower_32_bits - return bits 0-31 of a number * @n: the number we're accessing */ -#define lower_32_bits(n) ((u32)(n)) +#define lower_32_bits(n) ((u32)((n) & 0xffffffff)) struct completion; struct pt_regs; diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h index 10f5d1fa7347..e7cbccc7c14c 100644 --- a/include/trace/events/writeback.h +++ b/include/trace/events/writeback.h @@ -20,7 +20,6 @@ {I_CLEAR, "I_CLEAR"}, \ {I_SYNC, "I_SYNC"}, \ {I_DIRTY_TIME, "I_DIRTY_TIME"}, \ - {I_DIRTY_TIME_EXPIRED, "I_DIRTY_TIME_EXPIRED"}, \ {I_REFERENCED, "I_REFERENCED"} \ ) @@ -498,8 +497,9 @@ DEFINE_WBC_EVENT(wbc_writepage); TRACE_EVENT(writeback_queue_io, TP_PROTO(struct bdi_writeback *wb, struct wb_writeback_work *work, + unsigned long dirtied_before, int moved), - TP_ARGS(wb, work, moved), + TP_ARGS(wb, work, dirtied_before, moved), TP_STRUCT__entry( __array(char, name, 32) __field(unsigned long, older) @@ -509,19 +509,17 @@ TRACE_EVENT(writeback_queue_io, __field(ino_t, cgroup_ino) ), TP_fast_assign( - unsigned long *older_than_this = work->older_than_this; strscpy_pad(__entry->name, bdi_dev_name(wb->bdi), 32); - __entry->older = older_than_this ? *older_than_this : 0; - __entry->age = older_than_this ? - (jiffies - *older_than_this) * 1000 / HZ : -1; + __entry->older = dirtied_before; + __entry->age = (jiffies - dirtied_before) * 1000 / HZ; __entry->moved = moved; __entry->reason = work->reason; __entry->cgroup_ino = __trace_wb_assign_cgroup(wb); ), TP_printk("bdi %s: older=%lu age=%ld enqueue=%d reason=%s cgroup_ino=%lu", __entry->name, - __entry->older, /* older_than_this in jiffies */ - __entry->age, /* older_than_this in relative milliseconds */ + __entry->older, /* dirtied_before in jiffies */ + __entry->age, /* dirtied_before in relative milliseconds */ __entry->moved, __print_symbolic(__entry->reason, WB_WORK_REASON), (unsigned long)__entry->cgroup_ino diff --git a/include/xen/arm/page.h b/include/xen/arm/page.h index d7f6af50e200..39df751d0dc4 100644 --- a/include/xen/arm/page.h +++ b/include/xen/arm/page.h @@ -76,7 +76,11 @@ static inline unsigned long bfn_to_pfn(unsigned long bfn) #define bfn_to_local_pfn(bfn) bfn_to_pfn(bfn) /* VIRT <-> GUEST conversion */ -#define virt_to_gfn(v) (pfn_to_gfn(virt_to_phys(v) >> XEN_PAGE_SHIFT)) +#define virt_to_gfn(v) \ + ({ \ + WARN_ON_ONCE(!virt_addr_valid(v)); \ + pfn_to_gfn(virt_to_phys(v) >> XEN_PAGE_SHIFT); \ + }) #define gfn_to_virt(m) (__va(gfn_to_pfn(m) << XEN_PAGE_SHIFT)) /* Only used in PV code. But ARM guests are always HVM. */ |