diff --git a/Documentation/RCU/Design/Requirements/Requirements.rst b/Documentation/RCU/Design/Requirements/Requirements.rst index a0f8164c8513..49387d823619 100644 --- a/Documentation/RCU/Design/Requirements/Requirements.rst +++ b/Documentation/RCU/Design/Requirements/Requirements.rst @@ -1858,7 +1858,7 @@ unloaded. After a given module has been unloaded, any attempt to call one of its functions results in a segmentation fault. The module-unload functions must therefore cancel any delayed calls to loadable-module functions, for example, any outstanding mod_timer() must be dealt -with via del_timer_sync() or similar. +with via timer_shutdown_sync() or similar. Unfortunately, there is no way to cancel an RCU callback; once you invoke call_rcu(), the callback function is eventually going to be diff --git a/Documentation/core-api/local_ops.rst b/Documentation/core-api/local_ops.rst index 2ac3f9f29845..0b42ceaaf3c4 100644 --- a/Documentation/core-api/local_ops.rst +++ b/Documentation/core-api/local_ops.rst @@ -191,7 +191,7 @@ Here is a sample module which implements a basic per cpu counter using static void __exit test_exit(void) { - del_timer_sync(&test_timer); + timer_shutdown_sync(&test_timer); } module_init(test_init); diff --git a/Documentation/devicetree/bindings/interrupt-controller/intel,ce4100-ioapic.txt b/Documentation/devicetree/bindings/interrupt-controller/intel,ce4100-ioapic.txt deleted file mode 100644 index 7d19f494f19a..000000000000 --- a/Documentation/devicetree/bindings/interrupt-controller/intel,ce4100-ioapic.txt +++ /dev/null @@ -1,26 +0,0 @@ -Interrupt chips ---------------- - -* Intel I/O Advanced Programmable Interrupt Controller (IO APIC) - - Required properties: - -------------------- - compatible = "intel,ce4100-ioapic"; - #interrupt-cells = <2>; - - Device's interrupt property: - - interrupts =

; - - The first number (P) represents the interrupt pin which is wired to the - IO APIC. The second number (S) represents the sense of interrupt which - should be configured and can be one of: - 0 - Edge Rising - 1 - Level Low - 2 - Level High - 3 - Edge Falling - -* Local APIC - Required property: - - compatible = "intel,ce4100-lapic"; diff --git a/Documentation/devicetree/bindings/interrupt-controller/intel,ce4100-ioapic.yaml b/Documentation/devicetree/bindings/interrupt-controller/intel,ce4100-ioapic.yaml new file mode 100644 index 000000000000..39ab8cdd19b4 --- /dev/null +++ b/Documentation/devicetree/bindings/interrupt-controller/intel,ce4100-ioapic.yaml @@ -0,0 +1,60 @@ +# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) +%YAML 1.2 +--- +$id: "http://devicetree.org/schemas/interrupt-controller/intel,ce4100-ioapic.yaml#" +$schema: "http://devicetree.org/meta-schemas/core.yaml#" + +title: Intel I/O Advanced Programmable Interrupt Controller (IO APIC) + +maintainers: + - Rahul Tanwar + +description: | + Intel's Advanced Programmable Interrupt Controller (APIC) is a + family of interrupt controllers. The APIC is a split + architecture design, with a local component (LAPIC) integrated + into the processor itself and an external I/O APIC. Local APIC + (lapic) receives interrupts from the processor's interrupt pins, + from internal sources and from an external I/O APIC (ioapic). + And it sends these to the processor core for handling. + See [1] Chapter 8 for more details. + + Many of the Intel's generic devices like hpet, ioapic, lapic have + the ce4100 name in their compatible property names because they + first appeared in CE4100 SoC. + + This schema defines bindings for I/O APIC interrupt controller. + + [1] https://pdos.csail.mit.edu/6.828/2008/readings/ia32/IA32-3A.pdf + +properties: + compatible: + const: intel,ce4100-ioapic + + reg: + maxItems: 1 + + interrupt-controller: true + + '#interrupt-cells': + const: 2 + + interrupts: + maxItems: 1 + +required: + - compatible + - reg + - interrupt-controller + - '#interrupt-cells' + +additionalProperties: false + +examples: + - | + ioapic1: interrupt-controller@fec00000 { + compatible = "intel,ce4100-ioapic"; + reg = <0xfec00000 0x1000>; + interrupt-controller; + #interrupt-cells = <2>; + }; diff --git a/Documentation/devicetree/bindings/interrupt-controller/intel,ce4100-lapic.yaml b/Documentation/devicetree/bindings/interrupt-controller/intel,ce4100-lapic.yaml new file mode 100644 index 000000000000..d2d0145cb889 --- /dev/null +++ b/Documentation/devicetree/bindings/interrupt-controller/intel,ce4100-lapic.yaml @@ -0,0 +1,71 @@ +# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) +%YAML 1.2 +--- +$id: "http://devicetree.org/schemas/interrupt-controller/intel,ce4100-lapic.yaml#" +$schema: "http://devicetree.org/meta-schemas/core.yaml#" + +title: Intel Local Advanced Programmable Interrupt Controller (LAPIC) + +maintainers: + - Rahul Tanwar + +description: | + Intel's Advanced Programmable Interrupt Controller (APIC) is a + family of interrupt controllers. The APIC is a split + architecture design, with a local component (LAPIC) integrated + into the processor itself and an external I/O APIC. Local APIC + (lapic) receives interrupts from the processor's interrupt pins, + from internal sources and from an external I/O APIC (ioapic). + And it sends these to the processor core for handling. + See [1] Chapter 8 for more details. + + Many of the Intel's generic devices like hpet, ioapic, lapic have + the ce4100 name in their compatible property names because they + first appeared in CE4100 SoC. + + This schema defines bindings for local APIC interrupt controller. + + [1] https://pdos.csail.mit.edu/6.828/2008/readings/ia32/IA32-3A.pdf + +properties: + compatible: + const: intel,ce4100-lapic + + reg: + maxItems: 1 + + interrupt-controller: true + + '#interrupt-cells': + const: 2 + + intel,virtual-wire-mode: + description: Intel defines a few possible interrupt delivery + modes. With respect to boot/init time, mainly two interrupt + delivery modes are possible. + PIC Mode - Legacy external 8259 compliant PIC interrupt controller. + Virtual Wire Mode - use lapic as virtual wire interrupt delivery mode. + For ACPI or MPS spec compliant systems, it is figured out by some read + only bit field/s available in their respective defined data structures. + For OF based systems, it is by default set to PIC mode. + But if this optional boolean property is set, then the interrupt delivery + mode is configured to virtual wire compatibility mode. + type: boolean + +required: + - compatible + - reg + - interrupt-controller + - '#interrupt-cells' + +additionalProperties: false + +examples: + - | + lapic0: interrupt-controller@fee00000 { + compatible = "intel,ce4100-lapic"; + reg = <0xfee00000 0x1000>; + interrupt-controller; + #interrupt-cells = <2>; + intel,virtual-wire-mode; + }; diff --git a/Documentation/devicetree/bindings/timer/nuvoton,npcm7xx-timer.yaml b/Documentation/devicetree/bindings/timer/nuvoton,npcm7xx-timer.yaml index 737af78ad70c..d53e1bb98b8a 100644 --- a/Documentation/devicetree/bindings/timer/nuvoton,npcm7xx-timer.yaml +++ b/Documentation/devicetree/bindings/timer/nuvoton,npcm7xx-timer.yaml @@ -25,7 +25,13 @@ properties: - description: The timer interrupt of timer 0 clocks: - maxItems: 1 + items: + - description: The reference clock for timer 0 + - description: The reference clock for timer 1 + - description: The reference clock for timer 2 + - description: The reference clock for timer 3 + - description: The reference clock for timer 4 + minItems: 1 required: - compatible diff --git a/Documentation/devicetree/bindings/timer/renesas,cmt.yaml b/Documentation/devicetree/bindings/timer/renesas,cmt.yaml index bde6c9b66bf4..a0be1755ea28 100644 --- a/Documentation/devicetree/bindings/timer/renesas,cmt.yaml +++ b/Documentation/devicetree/bindings/timer/renesas,cmt.yaml @@ -102,12 +102,14 @@ properties: - enum: - renesas,r8a779a0-cmt0 # 32-bit CMT0 on R-Car V3U - renesas,r8a779f0-cmt0 # 32-bit CMT0 on R-Car S4-8 + - renesas,r8a779g0-cmt0 # 32-bit CMT0 on R-Car V4H - const: renesas,rcar-gen4-cmt0 # 32-bit CMT0 on R-Car Gen4 - items: - enum: - renesas,r8a779a0-cmt1 # 48-bit CMT on R-Car V3U - renesas,r8a779f0-cmt1 # 48-bit CMT on R-Car S4-8 + - renesas,r8a779g0-cmt1 # 48-bit CMT on R-Car V4H - const: renesas,rcar-gen4-cmt1 # 48-bit CMT on R-Car Gen4 reg: diff --git a/Documentation/devicetree/bindings/timer/renesas,tmu.yaml b/Documentation/devicetree/bindings/timer/renesas,tmu.yaml index 60f4c059bcff..a67e427a9e7e 100644 --- a/Documentation/devicetree/bindings/timer/renesas,tmu.yaml +++ b/Documentation/devicetree/bindings/timer/renesas,tmu.yaml @@ -38,6 +38,7 @@ properties: - renesas,tmu-r8a77995 # R-Car D3 - renesas,tmu-r8a779a0 # R-Car V3U - renesas,tmu-r8a779f0 # R-Car S4-8 + - renesas,tmu-r8a779g0 # R-Car V4H - const: renesas,tmu reg: diff --git a/Documentation/devicetree/bindings/timer/rockchip,rk-timer.yaml b/Documentation/devicetree/bindings/timer/rockchip,rk-timer.yaml index dc3bc1e62fe9..b61ed1a431bb 100644 --- a/Documentation/devicetree/bindings/timer/rockchip,rk-timer.yaml +++ b/Documentation/devicetree/bindings/timer/rockchip,rk-timer.yaml @@ -18,6 +18,7 @@ properties: - enum: - rockchip,rv1108-timer - rockchip,rk3036-timer + - rockchip,rk3128-timer - rockchip,rk3188-timer - rockchip,rk3228-timer - rockchip,rk3229-timer diff --git a/Documentation/kernel-hacking/locking.rst b/Documentation/kernel-hacking/locking.rst index 6805ae6e86e6..c756786e17ae 100644 --- a/Documentation/kernel-hacking/locking.rst +++ b/Documentation/kernel-hacking/locking.rst @@ -967,7 +967,7 @@ you might do the following:: while (list) { struct foo *next = list->next; - del_timer(&list->timer); + timer_delete(&list->timer); kfree(list); list = next; } @@ -981,7 +981,7 @@ the lock after we spin_unlock_bh(), and then try to free the element (which has already been freed!). This can be avoided by checking the result of -del_timer(): if it returns 1, the timer has been deleted. +timer_delete(): if it returns 1, the timer has been deleted. If 0, it means (in this case) that it is currently running, so we can do:: @@ -990,7 +990,7 @@ do:: while (list) { struct foo *next = list->next; - if (!del_timer(&list->timer)) { + if (!timer_delete(&list->timer)) { /* Give timer a chance to delete this */ spin_unlock_bh(&list_lock); goto retry; @@ -1005,9 +1005,12 @@ do:: Another common problem is deleting timers which restart themselves (by calling add_timer() at the end of their timer function). Because this is a fairly common case which is prone to races, you should -use del_timer_sync() (``include/linux/timer.h``) to -handle this case. It returns the number of times the timer had to be -deleted before we finally stopped it from adding itself back in. +use timer_delete_sync() (``include/linux/timer.h``) to handle this case. + +Before freeing a timer, timer_shutdown() or timer_shutdown_sync() should be +called which will keep it from being rearmed. Any subsequent attempt to +rearm the timer will be silently ignored by the core code. + Locking Speed ============= @@ -1335,7 +1338,7 @@ lock. - kfree() -- add_timer() and del_timer() +- add_timer() and timer_delete() Mutex API reference =================== diff --git a/Documentation/timers/hrtimers.rst b/Documentation/timers/hrtimers.rst index c1c20a693e8f..7ac448908d1f 100644 --- a/Documentation/timers/hrtimers.rst +++ b/Documentation/timers/hrtimers.rst @@ -118,7 +118,7 @@ existing timer wheel code, as it is mature and well suited. Sharing code was not really a win, due to the different data structures. Also, the hrtimer functions now have clearer behavior and clearer names - such as hrtimer_try_to_cancel() and hrtimer_cancel() [which are roughly -equivalent to del_timer() and del_timer_sync()] - so there's no direct +equivalent to timer_delete() and timer_delete_sync()] - so there's no direct 1:1 mapping between them on the algorithmic level, and thus no real potential for code sharing either. diff --git a/Documentation/translations/it_IT/kernel-hacking/locking.rst b/Documentation/translations/it_IT/kernel-hacking/locking.rst index 51af37f2d621..b8ecf41273c5 100644 --- a/Documentation/translations/it_IT/kernel-hacking/locking.rst +++ b/Documentation/translations/it_IT/kernel-hacking/locking.rst @@ -990,7 +990,7 @@ potreste fare come segue:: while (list) { struct foo *next = list->next; - del_timer(&list->timer); + timer_delete(&list->timer); kfree(list); list = next; } @@ -1003,7 +1003,7 @@ e prenderà il *lock* solo dopo spin_unlock_bh(), e cercherà di eliminare il suo oggetto (che però è già stato eliminato). Questo può essere evitato controllando il valore di ritorno di -del_timer(): se ritorna 1, il temporizzatore è stato già +timer_delete(): se ritorna 1, il temporizzatore è stato già rimosso. Se 0, significa (in questo caso) che il temporizzatore è in esecuzione, quindi possiamo fare come segue:: @@ -1012,7 +1012,7 @@ esecuzione, quindi possiamo fare come segue:: while (list) { struct foo *next = list->next; - if (!del_timer(&list->timer)) { + if (!timer_delete(&list->timer)) { /* Give timer a chance to delete this */ spin_unlock_bh(&list_lock); goto retry; @@ -1026,10 +1026,8 @@ esecuzione, quindi possiamo fare come segue:: Un altro problema è l'eliminazione dei temporizzatori che si riavviano da soli (chiamando add_timer() alla fine della loro esecuzione). Dato che questo è un problema abbastanza comune con una propensione -alle corse critiche, dovreste usare del_timer_sync() -(``include/linux/timer.h``) per gestire questo caso. Questa ritorna il -numero di volte che il temporizzatore è stato interrotto prima che -fosse in grado di fermarlo senza che si riavviasse. +alle corse critiche, dovreste usare timer_delete_sync() +(``include/linux/timer.h``) per gestire questo caso. Velocità della sincronizzazione =============================== @@ -1374,7 +1372,7 @@ contesto, o trattenendo un qualsiasi *lock*. - kfree() -- add_timer() e del_timer() +- add_timer() e timer_delete() Riferimento per l'API dei Mutex =============================== diff --git a/Documentation/translations/zh_CN/core-api/local_ops.rst b/Documentation/translations/zh_CN/core-api/local_ops.rst index 41e4525038e8..eb5423f60f17 100644 --- a/Documentation/translations/zh_CN/core-api/local_ops.rst +++ b/Documentation/translations/zh_CN/core-api/local_ops.rst @@ -185,7 +185,7 @@ UP之间没有不同的行为，在你的架构的 ``local.h`` 中包括 ``asm-g static void __exit test_exit(void) { - del_timer_sync(&test_timer); + timer_shutdown_sync(&test_timer); } module_init(test_init); diff --git a/Documentation/x86/boot.rst b/Documentation/x86/boot.rst index 894a19897005..240d084782a6 100644 --- a/Documentation/x86/boot.rst +++ b/Documentation/x86/boot.rst @@ -455,6 +455,7 @@ Protocol: 2.00+ 11 Minimal Linux Bootloader 12 OVMF UEFI virtualization stack + 13 barebox == ======================================= Please contact if you need a bootloader ID value assigned. diff --git a/arch/arm/mach-spear/time.c b/arch/arm/mach-spear/time.c index e979e2197f8e..5371c824786d 100644 --- a/arch/arm/mach-spear/time.c +++ b/arch/arm/mach-spear/time.c @@ -90,7 +90,7 @@ static void __init spear_clocksource_init(void) 200, 16, clocksource_mmio_readw_up); } -static inline void timer_shutdown(struct clock_event_device *evt) +static inline void spear_timer_shutdown(struct clock_event_device *evt) { u16 val = readw(gpt_base + CR(CLKEVT)); @@ -101,7 +101,7 @@ static inline void timer_shutdown(struct clock_event_device *evt) static int spear_shutdown(struct clock_event_device *evt) { - timer_shutdown(evt); + spear_timer_shutdown(evt); return 0; } @@ -111,7 +111,7 @@ static int spear_set_oneshot(struct clock_event_device *evt) u16 val; /* stop the timer */ - timer_shutdown(evt); + spear_timer_shutdown(evt); val = readw(gpt_base + CR(CLKEVT)); val |= CTRL_ONE_SHOT; @@ -126,7 +126,7 @@ static int spear_set_periodic(struct clock_event_device *evt) u16 val; /* stop the timer */ - timer_shutdown(evt); + spear_timer_shutdown(evt); period = clk_get_rate(gpt_clk) / HZ; period >>= CTRL_PRESCALER16; diff --git a/arch/arm64/kernel/vdso.c b/arch/arm64/kernel/vdso.c index 99ae81ab91a7..e59a32aa0c49 100644 --- a/arch/arm64/kernel/vdso.c +++ b/arch/arm64/kernel/vdso.c @@ -151,28 +151,6 @@ int vdso_join_timens(struct task_struct *task, struct time_namespace *ns) mmap_read_unlock(mm); return 0; } - -static struct page *find_timens_vvar_page(struct vm_area_struct *vma) -{ - if (likely(vma->vm_mm == current->mm)) - return current->nsproxy->time_ns->vvar_page; - - /* - * VM_PFNMAP | VM_IO protect .fault() handler from being called - * through interfaces like /proc/$pid/mem or - * process_vm_{readv,writev}() as long as there's no .access() - * in special_mapping_vmops. - * For more details check_vma_flags() and __access_remote_vm() - */ - WARN(1, "vvar_page accessed remotely"); - - return NULL; -} -#else -static struct page *find_timens_vvar_page(struct vm_area_struct *vma) -{ - return NULL; -} #endif static vm_fault_t vvar_fault(const struct vm_special_mapping *sm, diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c index 4abc01949702..507f8228f983 100644 --- a/arch/powerpc/kernel/vdso.c +++ b/arch/powerpc/kernel/vdso.c @@ -129,28 +129,6 @@ int vdso_join_timens(struct task_struct *task, struct time_namespace *ns) return 0; } - -static struct page *find_timens_vvar_page(struct vm_area_struct *vma) -{ - if (likely(vma->vm_mm == current->mm)) - return current->nsproxy->time_ns->vvar_page; - - /* - * VM_PFNMAP | VM_IO protect .fault() handler from being called - * through interfaces like /proc/$pid/mem or - * process_vm_{readv,writev}() as long as there's no .access() - * in special_mapping_vmops. - * For more details check_vma_flags() and __access_remote_vm() - */ - WARN(1, "vvar_page accessed remotely"); - - return NULL; -} -#else -static struct page *find_timens_vvar_page(struct vm_area_struct *vma) -{ - return NULL; -} #endif static vm_fault_t vvar_fault(const struct vm_special_mapping *sm, diff --git a/arch/riscv/kernel/vdso.c b/arch/riscv/kernel/vdso.c index 123d05255fcf..e410275918ac 100644 --- a/arch/riscv/kernel/vdso.c +++ b/arch/riscv/kernel/vdso.c @@ -137,28 +137,6 @@ int vdso_join_timens(struct task_struct *task, struct time_namespace *ns) mmap_read_unlock(mm); return 0; } - -static struct page *find_timens_vvar_page(struct vm_area_struct *vma) -{ - if (likely(vma->vm_mm == current->mm)) - return current->nsproxy->time_ns->vvar_page; - - /* - * VM_PFNMAP | VM_IO protect .fault() handler from being called - * through interfaces like /proc/$pid/mem or - * process_vm_{readv,writev}() as long as there's no .access() - * in special_mapping_vmops. - * For more details check_vma_flags() and __access_remote_vm() - */ - WARN(1, "vvar_page accessed remotely"); - - return NULL; -} -#else -static struct page *find_timens_vvar_page(struct vm_area_struct *vma) -{ - return NULL; -} #endif static vm_fault_t vvar_fault(const struct vm_special_mapping *sm, diff --git a/arch/s390/kernel/vdso.c b/arch/s390/kernel/vdso.c index 3105ca5bd470..d6df7169c01f 100644 --- a/arch/s390/kernel/vdso.c +++ b/arch/s390/kernel/vdso.c @@ -44,21 +44,6 @@ struct vdso_data *arch_get_vdso_data(void *vvar_page) return (struct vdso_data *)(vvar_page); } -static struct page *find_timens_vvar_page(struct vm_area_struct *vma) -{ - if (likely(vma->vm_mm == current->mm)) - return current->nsproxy->time_ns->vvar_page; - /* - * VM_PFNMAP | VM_IO protect .fault() handler from being called - * through interfaces like /proc/$pid/mem or - * process_vm_{readv,writev}() as long as there's no .access() - * in special_mapping_vmops(). - * For more details check_vma_flags() and __access_remote_vm() - */ - WARN(1, "vvar_page accessed remotely"); - return NULL; -} - /* * The VVAR page layout depends on whether a task belongs to the root or * non-root time namespace. Whenever a task changes its namespace, the VVAR @@ -84,11 +69,6 @@ int vdso_join_timens(struct task_struct *task, struct time_namespace *ns) mmap_read_unlock(mm); return 0; } -#else -static inline struct page *find_timens_vvar_page(struct vm_area_struct *vma) -{ - return NULL; -} #endif static vm_fault_t vvar_fault(const struct vm_special_mapping *sm, diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index e2eebb193ee0..68a2a04c02e5 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -463,8 +463,8 @@ config X86_X2APIC Some Intel systems circa 2022 and later are locked into x2APIC mode and can not fall back to the legacy APIC modes if SGX or TDX are - enabled in the BIOS. They will be unable to boot without enabling - this option. + enabled in the BIOS. They will boot with very reduced functionality + without enabling this option. If you don't know what to do here, say N. diff --git a/arch/x86/boot/compressed/kaslr.c b/arch/x86/boot/compressed/kaslr.c index e476bcbd9b42..454757fbdfe5 100644 --- a/arch/x86/boot/compressed/kaslr.c +++ b/arch/x86/boot/compressed/kaslr.c @@ -668,7 +668,7 @@ static bool process_mem_region(struct mem_vector *region, } } #endif - return 0; + return false; } #ifdef CONFIG_EFI diff --git a/arch/x86/boot/string.c b/arch/x86/boot/string.c index 8a3fff9128bb..1c8541ae3b3a 100644 --- a/arch/x86/boot/string.c +++ b/arch/x86/boot/string.c @@ -350,7 +350,7 @@ static int _kstrtoul(const char *s, unsigned int base, unsigned long *res) } /** - * kstrtoul - convert a string to an unsigned long + * boot_kstrtoul - convert a string to an unsigned long * @s: The start of the string. The string must be null-terminated, and may also * include a single newline before its terminating null. The first character * may also be a plus sign, but not a minus sign. diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S index 4dd19819053a..59b93901660d 100644 --- a/arch/x86/entry/entry_64_compat.S +++ b/arch/x86/entry/entry_64_compat.S @@ -61,7 +61,7 @@ SYM_CODE_START(entry_SYSENTER_compat) movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp /* Construct struct pt_regs on stack */ - pushq $__USER32_DS /* pt_regs->ss */ + pushq $__USER_DS /* pt_regs->ss */ pushq $0 /* pt_regs->sp = 0 (placeholder) */ /* @@ -197,7 +197,7 @@ SYM_INNER_LABEL(entry_SYSCALL_compat_safe_stack, SYM_L_GLOBAL) ANNOTATE_NOENDBR /* Construct struct pt_regs on stack */ - pushq $__USER32_DS /* pt_regs->ss */ + pushq $__USER_DS /* pt_regs->ss */ pushq %r8 /* pt_regs->sp */ pushq %r11 /* pt_regs->flags */ pushq $__USER32_CS /* pt_regs->cs */ diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c index 6976416b2c9f..3c6b488b2f11 100644 --- a/arch/x86/entry/vdso/vma.c +++ b/arch/x86/entry/vdso/vma.c @@ -98,24 +98,6 @@ static int vdso_mremap(const struct vm_special_mapping *sm, } #ifdef CONFIG_TIME_NS -static struct page *find_timens_vvar_page(struct vm_area_struct *vma) -{ - if (likely(vma->vm_mm == current->mm)) - return current->nsproxy->time_ns->vvar_page; - - /* - * VM_PFNMAP | VM_IO protect .fault() handler from being called - * through interfaces like /proc/$pid/mem or - * process_vm_{readv,writev}() as long as there's no .access() - * in special_mapping_vmops(). - * For more details check_vma_flags() and __access_remote_vm() - */ - - WARN(1, "vvar_page accessed remotely"); - - return NULL; -} - /* * The vvar page layout depends on whether a task belongs to the root or * non-root time namespace. Whenever a task changes its namespace, the VVAR @@ -140,11 +122,6 @@ int vdso_join_timens(struct task_struct *task, struct time_namespace *ns) return 0; } -#else -static inline struct page *find_timens_vvar_page(struct vm_area_struct *vma) -{ - return NULL; -} #endif static vm_fault_t vvar_fault(const struct vm_special_mapping *sm, diff --git a/arch/x86/ia32/Makefile b/arch/x86/ia32/Makefile index e481056698de..333556a86b2a 100644 --- a/arch/x86/ia32/Makefile +++ b/arch/x86/ia32/Makefile @@ -3,7 +3,5 @@ # Makefile for the ia32 kernel emulation subsystem. # -obj-$(CONFIG_IA32_EMULATION) := ia32_signal.o - audit-class-$(CONFIG_AUDIT) := audit.o obj-$(CONFIG_IA32_EMULATION) += $(audit-class-y) diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h index 3415321c8240..3216da7074ba 100644 --- a/arch/x86/include/asm/apic.h +++ b/arch/x86/include/asm/apic.h @@ -249,7 +249,6 @@ static inline u64 native_x2apic_icr_read(void) extern int x2apic_mode; extern int x2apic_phys; extern void __init x2apic_set_max_apicid(u32 apicid); -extern void __init check_x2apic(void); extern void x2apic_setup(void); static inline int x2apic_enabled(void) { @@ -258,13 +257,13 @@ static inline int x2apic_enabled(void) #define x2apic_supported() (boot_cpu_has(X86_FEATURE_X2APIC)) #else /* !CONFIG_X86_X2APIC */ -static inline void check_x2apic(void) { } static inline void x2apic_setup(void) { } static inline int x2apic_enabled(void) { return 0; } #define x2apic_mode (0) #define x2apic_supported() (0) #endif /* !CONFIG_X86_X2APIC */ +extern void __init check_x2apic(void); struct irq_data; diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h index cb0ff1055ab1..be8b58da63b9 100644 --- a/arch/x86/include/asm/elf.h +++ b/arch/x86/include/asm/elf.h @@ -152,10 +152,6 @@ do { \ (elf_check_arch_ia32(x) || \ (IS_ENABLED(CONFIG_X86_X32_ABI) && (x)->e_machine == EM_X86_64)) -#if __USER32_DS != __USER_DS -# error "The following code assumes __USER32_DS == __USER_DS" -#endif - static inline void elf_common_init(struct thread_struct *t, struct pt_regs *regs, const u16 ds) { diff --git a/arch/x86/include/asm/fpu/signal.h b/arch/x86/include/asm/fpu/signal.h index e1c9df9102a5..611fa41711af 100644 --- a/arch/x86/include/asm/fpu/signal.h +++ b/arch/x86/include/asm/fpu/signal.h @@ -13,16 +13,9 @@ #ifdef CONFIG_X86_64 # include # include -struct ksignal; -int ia32_setup_rt_frame(int sig, struct ksignal *ksig, - compat_sigset_t *set, struct pt_regs *regs); -int ia32_setup_frame(int sig, struct ksignal *ksig, - compat_sigset_t *set, struct pt_regs *regs); #else # define user_i387_ia32_struct user_i387_struct # define user32_fxsr_struct user_fxsr_struct -# define ia32_setup_frame __setup_frame -# define ia32_setup_rt_frame __setup_rt_frame #endif extern void convert_from_fxsr(struct user_i387_ia32_struct *env, diff --git a/arch/x86/include/asm/segment.h b/arch/x86/include/asm/segment.h index 2e7890dd58a4..c390a672d560 100644 --- a/arch/x86/include/asm/segment.h +++ b/arch/x86/include/asm/segment.h @@ -135,6 +135,7 @@ #define __KERNEL_DS (GDT_ENTRY_KERNEL_DS*8) #define __USER_DS (GDT_ENTRY_DEFAULT_USER_DS*8 + 3) #define __USER_CS (GDT_ENTRY_DEFAULT_USER_CS*8 + 3) +#define __USER32_CS __USER_CS #define __ESPFIX_SS (GDT_ENTRY_ESPFIX_SS*8) /* segment for calling fn: */ @@ -210,7 +211,6 @@ #define __KERNEL_DS (GDT_ENTRY_KERNEL_DS*8) #define __USER32_CS (GDT_ENTRY_DEFAULT_USER32_CS*8 + 3) #define __USER_DS (GDT_ENTRY_DEFAULT_USER_DS*8 + 3) -#define __USER32_DS __USER_DS #define __USER_CS (GDT_ENTRY_DEFAULT_USER_CS*8 + 3) #define __CPUNODE_SEG (GDT_ENTRY_CPUNODE*8 + 3) diff --git a/arch/x86/include/asm/sighandling.h b/arch/x86/include/asm/sighandling.h index 65e667279e0f..e770c4fc47f4 100644 --- a/arch/x86/include/asm/sighandling.h +++ b/arch/x86/include/asm/sighandling.h @@ -15,4 +15,13 @@ void signal_fault(struct pt_regs *regs, void __user *frame, char *where); +void __user * +get_sigframe(struct ksignal *ksig, struct pt_regs *regs, size_t frame_size, + void __user **fpstate); + +int ia32_setup_frame(struct ksignal *ksig, struct pt_regs *regs); +int ia32_setup_rt_frame(struct ksignal *ksig, struct pt_regs *regs); +int x64_setup_rt_frame(struct ksignal *ksig, struct pt_regs *regs); +int x32_setup_rt_frame(struct ksignal *ksig, struct pt_regs *regs); + #endif /* _ASM_X86_SIGHANDLING_H */ diff --git a/arch/x86/include/asm/signal.h b/arch/x86/include/asm/signal.h index 2dfb5fea13af..4a4043ca6493 100644 --- a/arch/x86/include/asm/signal.h +++ b/arch/x86/include/asm/signal.h @@ -28,11 +28,6 @@ typedef struct { #define SA_IA32_ABI 0x02000000u #define SA_X32_ABI 0x01000000u -#ifndef CONFIG_COMPAT -#define compat_sigset_t compat_sigset_t -typedef sigset_t compat_sigset_t; -#endif - #endif /* __ASSEMBLY__ */ #include #ifndef __ASSEMBLY__ diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index f901658d9f7c..cceaafdd2d84 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -44,7 +44,7 @@ obj-y += head_$(BITS).o obj-y += head$(BITS).o obj-y += ebda.o obj-y += platform-quirks.o -obj-y += process_$(BITS).o signal.o +obj-y += process_$(BITS).o signal.o signal_$(BITS).o obj-$(CONFIG_COMPAT) += signal_compat.o obj-y += traps.o idt.o irq.o irq_$(BITS).o dumpstack_$(BITS).o obj-y += time.o ioport.o dumpstack.o nmi.o @@ -54,7 +54,7 @@ obj-$(CONFIG_JUMP_LABEL) += jump_label.o obj-$(CONFIG_IRQ_WORK) += irq_work.o obj-y += probe_roms.o obj-$(CONFIG_X86_32) += sys_ia32.o -obj-$(CONFIG_IA32_EMULATION) += sys_ia32.o +obj-$(CONFIG_IA32_EMULATION) += sys_ia32.o signal_32.o obj-$(CONFIG_X86_64) += sys_x86_64.o obj-$(CONFIG_X86_ESPFIX64) += espfix_64.o obj-$(CONFIG_SYSFS) += ksysfs.o diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index beaf9fc44e2f..a9bea860e22a 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -1608,7 +1608,7 @@ static void text_poke_loc_init(struct text_poke_loc *tp, void *addr, default: BUG_ON(len != insn.length); - }; + } switch (tp->opcode) { diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index c6876d3ea4b1..20d9a604da7c 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -1931,16 +1931,19 @@ void __init check_x2apic(void) } } #else /* CONFIG_X86_X2APIC */ -static int __init validate_x2apic(void) +void __init check_x2apic(void) { if (!apic_is_x2apic_enabled()) - return 0; + return; /* - * Checkme: Can we simply turn off x2apic here instead of panic? + * Checkme: Can we simply turn off x2APIC here instead of disabling the APIC? */ - panic("BIOS has enabled x2apic but kernel doesn't support x2apic, please disable x2apic in BIOS.\n"); + pr_err("Kernel does not support x2APIC, please recompile with CONFIG_X86_X2APIC.\n"); + pr_err("Disabling APIC, expect reduced performance and functionality.\n"); + + disable_apic = 1; + setup_clear_cpu_cap(X86_FEATURE_APIC); } -early_initcall(validate_x2apic); static inline void try_to_enable_x2apic(int remap_mode) { } static inline void __x2apic_enable(void) { } diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c index 5cd51f25f446..28da5dd83fc0 100644 --- a/arch/x86/kernel/devicetree.c +++ b/arch/x86/kernel/devicetree.c @@ -31,11 +31,6 @@ char __initdata cmd_line[COMMAND_LINE_SIZE]; int __initdata of_ioapic; -void __init early_init_dt_add_memory_arch(u64 base, u64 size) -{ - BUG(); -} - void __init add_dtb(u64 data) { initial_dtb = data + offsetof(struct setup_data, data); @@ -167,7 +162,14 @@ static void __init dtb_lapic_setup(void) return; } smp_found_config = 1; - pic_mode = 1; + if (of_property_read_bool(dn, "intel,virtual-wire-mode")) { + pr_info("Virtual Wire compatibility mode.\n"); + pic_mode = 0; + } else { + pr_info("IMCR and PIC compatibility mode.\n"); + pic_mode = 1; + } + register_lapic_address(lapic_addr); } @@ -248,7 +250,7 @@ static void __init dtb_add_ioapic(struct device_node *dn) ret = of_address_to_resource(dn, 0, &r); if (ret) { - printk(KERN_ERR "Can't obtain address from device node %pOF.\n", dn); + pr_err("Can't obtain address from device node %pOF.\n", dn); return; } mp_register_ioapic(++ioapic_id, r.start, gsi_top, &cfg); @@ -265,7 +267,7 @@ static void __init dtb_ioapic_setup(void) of_ioapic = 1; return; } - printk(KERN_ERR "Error: No information about IO-APIC in OF.\n"); + pr_err("Error: No information about IO-APIC in OF.\n"); } #else static void __init dtb_ioapic_setup(void) {} diff --git a/arch/x86/kernel/espfix_64.c b/arch/x86/kernel/espfix_64.c index 9417d5aa7305..16f9814c9be0 100644 --- a/arch/x86/kernel/espfix_64.c +++ b/arch/x86/kernel/espfix_64.c @@ -94,17 +94,7 @@ static inline unsigned long espfix_base_addr(unsigned int cpu) static void init_espfix_random(void) { - unsigned long rand; - - /* - * This is run before the entropy pools are initialized, - * but this is hopefully better than nothing. - */ - if (!arch_get_random_longs(&rand, 1)) { - /* The constant is an arbitrary large prime */ - rand = rdtsc(); - rand *= 0xc345c6b72fd16123UL; - } + unsigned long rand = get_random_long(); slot_random = rand % ESPFIX_STACKS_PER_PAGE; page_random = (rand / ESPFIX_STACKS_PER_PAGE) diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index 9b7acc9c7874..67c8ed99144b 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -260,16 +260,6 @@ SYM_FUNC_START(startup_32_smp) /* Shift the stack pointer to a virtual address */ addl $__PAGE_OFFSET, %esp -/* - * start system 32-bit setup. We need to re-do some of the things done - * in 16-bit mode for the "real" operations. - */ - movl setup_once_ref,%eax - andl %eax,%eax - jz 1f # Did we do this already? - call *%eax -1: - /* * Check if it is 486 */ @@ -331,18 +321,7 @@ SYM_FUNC_END(startup_32_smp) #include "verify_cpu.S" -/* - * setup_once - * - * The setup work we only want to run on the BSP. - * - * Warning: %esi is live across this function. - */ __INIT -setup_once: - andl $0,setup_once_ref /* Once is enough, thanks */ - RET - SYM_FUNC_START(early_idt_handler_array) # 36(%esp) %eflags # 32(%esp) %cs @@ -458,7 +437,6 @@ SYM_DATA(early_recursion_flag, .long 0) __REFDATA .align 4 SYM_DATA(initial_code, .long i386_start_kernel) -SYM_DATA(setup_once_ref, .long setup_once) #ifdef CONFIG_PAGE_TABLE_ISOLATION #define PGD_ALIGN (2 * PAGE_SIZE) diff --git a/arch/x86/kernel/i8259.c b/arch/x86/kernel/i8259.c index 15aefa3f3e18..3aa5304200c5 100644 --- a/arch/x86/kernel/i8259.c +++ b/arch/x86/kernel/i8259.c @@ -407,7 +407,7 @@ struct legacy_pic null_legacy_pic = { .make_irq = legacy_pic_uint_noop, }; -struct legacy_pic default_legacy_pic = { +static struct legacy_pic default_legacy_pic = { .nr_legacy_irqs = NR_IRQS_LEGACY, .chip = &i8259A_chip, .mask = mask_8259A_irq, diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index 37c12fb92906..dfaa270a7cc9 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -44,16 +44,35 @@ #include "tls.h" -enum x86_regset { - REGSET_GENERAL, - REGSET_FP, - REGSET_XFP, - REGSET_IOPERM64 = REGSET_XFP, - REGSET_XSTATE, - REGSET_TLS, - REGSET_IOPERM32, +enum x86_regset_32 { + REGSET32_GENERAL, + REGSET32_FP, + REGSET32_XFP, + REGSET32_XSTATE, + REGSET32_TLS, + REGSET32_IOPERM, }; +enum x86_regset_64 { + REGSET64_GENERAL, + REGSET64_FP, + REGSET64_IOPERM, + REGSET64_XSTATE, +}; + +#define REGSET_GENERAL \ +({ \ + BUILD_BUG_ON((int)REGSET32_GENERAL != (int)REGSET64_GENERAL); \ + REGSET32_GENERAL; \ +}) + +#define REGSET_FP \ +({ \ + BUILD_BUG_ON((int)REGSET32_FP != (int)REGSET64_FP); \ + REGSET32_FP; \ +}) + + struct pt_regs_offset { const char *name; int offset; @@ -788,13 +807,13 @@ long arch_ptrace(struct task_struct *child, long request, #ifdef CONFIG_X86_32 case PTRACE_GETFPXREGS: /* Get the child extended FPU state. */ return copy_regset_to_user(child, &user_x86_32_view, - REGSET_XFP, + REGSET32_XFP, 0, sizeof(struct user_fxsr_struct), datap) ? -EIO : 0; case PTRACE_SETFPXREGS: /* Set the child extended FPU state. */ return copy_regset_from_user(child, &user_x86_32_view, - REGSET_XFP, + REGSET32_XFP, 0, sizeof(struct user_fxsr_struct), datap) ? -EIO : 0; #endif @@ -1086,13 +1105,13 @@ static long ia32_arch_ptrace(struct task_struct *child, compat_long_t request, case PTRACE_GETFPXREGS: /* Get the child extended FPU state. */ return copy_regset_to_user(child, &user_x86_32_view, - REGSET_XFP, 0, + REGSET32_XFP, 0, sizeof(struct user32_fxsr_struct), datap); case PTRACE_SETFPXREGS: /* Set the child extended FPU state. */ return copy_regset_from_user(child, &user_x86_32_view, - REGSET_XFP, 0, + REGSET32_XFP, 0, sizeof(struct user32_fxsr_struct), datap); @@ -1215,29 +1234,38 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request, #ifdef CONFIG_X86_64 static struct user_regset x86_64_regsets[] __ro_after_init = { - [REGSET_GENERAL] = { - .core_note_type = NT_PRSTATUS, - .n = sizeof(struct user_regs_struct) / sizeof(long), - .size = sizeof(long), .align = sizeof(long), - .regset_get = genregs_get, .set = genregs_set + [REGSET64_GENERAL] = { + .core_note_type = NT_PRSTATUS, + .n = sizeof(struct user_regs_struct) / sizeof(long), + .size = sizeof(long), + .align = sizeof(long), + .regset_get = genregs_get, + .set = genregs_set }, - [REGSET_FP] = { - .core_note_type = NT_PRFPREG, - .n = sizeof(struct fxregs_state) / sizeof(long), - .size = sizeof(long), .align = sizeof(long), - .active = regset_xregset_fpregs_active, .regset_get = xfpregs_get, .set = xfpregs_set + [REGSET64_FP] = { + .core_note_type = NT_PRFPREG, + .n = sizeof(struct fxregs_state) / sizeof(long), + .size = sizeof(long), + .align = sizeof(long), + .active = regset_xregset_fpregs_active, + .regset_get = xfpregs_get, + .set = xfpregs_set }, - [REGSET_XSTATE] = { - .core_note_type = NT_X86_XSTATE, - .size = sizeof(u64), .align = sizeof(u64), - .active = xstateregs_active, .regset_get = xstateregs_get, - .set = xstateregs_set + [REGSET64_XSTATE] = { + .core_note_type = NT_X86_XSTATE, + .size = sizeof(u64), + .align = sizeof(u64), + .active = xstateregs_active, + .regset_get = xstateregs_get, + .set = xstateregs_set }, - [REGSET_IOPERM64] = { - .core_note_type = NT_386_IOPERM, - .n = IO_BITMAP_LONGS, - .size = sizeof(long), .align = sizeof(long), - .active = ioperm_active, .regset_get = ioperm_get + [REGSET64_IOPERM] = { + .core_note_type = NT_386_IOPERM, + .n = IO_BITMAP_LONGS, + .size = sizeof(long), + .align = sizeof(long), + .active = ioperm_active, + .regset_get = ioperm_get }, }; @@ -1256,43 +1284,57 @@ static const struct user_regset_view user_x86_64_view = { #if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION static struct user_regset x86_32_regsets[] __ro_after_init = { - [REGSET_GENERAL] = { - .core_note_type = NT_PRSTATUS, - .n = sizeof(struct user_regs_struct32) / sizeof(u32), - .size = sizeof(u32), .align = sizeof(u32), - .regset_get = genregs32_get, .set = genregs32_set + [REGSET32_GENERAL] = { + .core_note_type = NT_PRSTATUS, + .n = sizeof(struct user_regs_struct32) / sizeof(u32), + .size = sizeof(u32), + .align = sizeof(u32), + .regset_get = genregs32_get, + .set = genregs32_set }, - [REGSET_FP] = { - .core_note_type = NT_PRFPREG, - .n = sizeof(struct user_i387_ia32_struct) / sizeof(u32), - .size = sizeof(u32), .align = sizeof(u32), - .active = regset_fpregs_active, .regset_get = fpregs_get, .set = fpregs_set + [REGSET32_FP] = { + .core_note_type = NT_PRFPREG, + .n = sizeof(struct user_i387_ia32_struct) / sizeof(u32), + .size = sizeof(u32), + .align = sizeof(u32), + .active = regset_fpregs_active, + .regset_get = fpregs_get, + .set = fpregs_set }, - [REGSET_XFP] = { - .core_note_type = NT_PRXFPREG, - .n = sizeof(struct fxregs_state) / sizeof(u32), - .size = sizeof(u32), .align = sizeof(u32), - .active = regset_xregset_fpregs_active, .regset_get = xfpregs_get, .set = xfpregs_set + [REGSET32_XFP] = { + .core_note_type = NT_PRXFPREG, + .n = sizeof(struct fxregs_state) / sizeof(u32), + .size = sizeof(u32), + .align = sizeof(u32), + .active = regset_xregset_fpregs_active, + .regset_get = xfpregs_get, + .set = xfpregs_set }, - [REGSET_XSTATE] = { - .core_note_type = NT_X86_XSTATE, - .size = sizeof(u64), .align = sizeof(u64), - .active = xstateregs_active, .regset_get = xstateregs_get, - .set = xstateregs_set + [REGSET32_XSTATE] = { + .core_note_type = NT_X86_XSTATE, + .size = sizeof(u64), + .align = sizeof(u64), + .active = xstateregs_active, + .regset_get = xstateregs_get, + .set = xstateregs_set }, - [REGSET_TLS] = { - .core_note_type = NT_386_TLS, - .n = GDT_ENTRY_TLS_ENTRIES, .bias = GDT_ENTRY_TLS_MIN, - .size = sizeof(struct user_desc), - .align = sizeof(struct user_desc), - .active = regset_tls_active, - .regset_get = regset_tls_get, .set = regset_tls_set + [REGSET32_TLS] = { + .core_note_type = NT_386_TLS, + .n = GDT_ENTRY_TLS_ENTRIES, + .bias = GDT_ENTRY_TLS_MIN, + .size = sizeof(struct user_desc), + .align = sizeof(struct user_desc), + .active = regset_tls_active, + .regset_get = regset_tls_get, + .set = regset_tls_set }, - [REGSET_IOPERM32] = { - .core_note_type = NT_386_IOPERM, - .n = IO_BITMAP_BYTES / sizeof(u32), - .size = sizeof(u32), .align = sizeof(u32), - .active = ioperm_active, .regset_get = ioperm_get + [REGSET32_IOPERM] = { + .core_note_type = NT_386_IOPERM, + .n = IO_BITMAP_BYTES / sizeof(u32), + .size = sizeof(u32), + .align = sizeof(u32), + .active = ioperm_active, + .regset_get = ioperm_get }, }; @@ -1311,10 +1353,10 @@ u64 xstate_fx_sw_bytes[USER_XSTATE_FX_SW_WORDS]; void __init update_regset_xstate_info(unsigned int size, u64 xstate_mask) { #ifdef CONFIG_X86_64 - x86_64_regsets[REGSET_XSTATE].n = size / sizeof(u64); + x86_64_regsets[REGSET64_XSTATE].n = size / sizeof(u64); #endif #if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION - x86_32_regsets[REGSET_XSTATE].n = size / sizeof(u64); + x86_32_regsets[REGSET32_XSTATE].n = size / sizeof(u64); #endif xstate_fx_sw_bytes[USER_XSTATE_XCR0_WORD] = xstate_mask; } diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index 9c7265b524c7..1504eb8d25aa 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -37,179 +37,26 @@ #include #include -#ifdef CONFIG_X86_64 -#include -#include -#include -#include -#endif /* CONFIG_X86_64 */ - #include #include #include -#ifdef CONFIG_X86_64 -/* - * If regs->ss will cause an IRET fault, change it. Otherwise leave it - * alone. Using this generally makes no sense unless - * user_64bit_mode(regs) would return true. - */ -static void force_valid_ss(struct pt_regs *regs) +static inline int is_ia32_compat_frame(struct ksignal *ksig) { - u32 ar; - asm volatile ("lar %[old_ss], %[ar]\n\t" - "jz 1f\n\t" /* If invalid: */ - "xorl %[ar], %[ar]\n\t" /* set ar = 0 */ - "1:" - : [ar] "=r" (ar) - : [old_ss] "rm" ((u16)regs->ss)); - - /* - * For a valid 64-bit user context, we need DPL 3, type - * read-write data or read-write exp-down data, and S and P - * set. We can't use VERW because VERW doesn't check the - * P bit. - */ - ar &= AR_DPL_MASK | AR_S | AR_P | AR_TYPE_MASK; - if (ar != (AR_DPL3 | AR_S | AR_P | AR_TYPE_RWDATA) && - ar != (AR_DPL3 | AR_S | AR_P | AR_TYPE_RWDATA_EXPDOWN)) - regs->ss = __USER_DS; -} -# define CONTEXT_COPY_SIZE offsetof(struct sigcontext, reserved1) -#else -# define CONTEXT_COPY_SIZE sizeof(struct sigcontext) -#endif - -static bool restore_sigcontext(struct pt_regs *regs, - struct sigcontext __user *usc, - unsigned long uc_flags) -{ - struct sigcontext sc; - - /* Always make any pending restarted system calls return -EINTR */ - current->restart_block.fn = do_no_restart_syscall; - - if (copy_from_user(&sc, usc, CONTEXT_COPY_SIZE)) - return false; - -#ifdef CONFIG_X86_32 - loadsegment(gs, sc.gs); - regs->fs = sc.fs; - regs->es = sc.es; - regs->ds = sc.ds; -#endif /* CONFIG_X86_32 */ - - regs->bx = sc.bx; - regs->cx = sc.cx; - regs->dx = sc.dx; - regs->si = sc.si; - regs->di = sc.di; - regs->bp = sc.bp; - regs->ax = sc.ax; - regs->sp = sc.sp; - regs->ip = sc.ip; - -#ifdef CONFIG_X86_64 - regs->r8 = sc.r8; - regs->r9 = sc.r9; - regs->r10 = sc.r10; - regs->r11 = sc.r11; - regs->r12 = sc.r12; - regs->r13 = sc.r13; - regs->r14 = sc.r14; - regs->r15 = sc.r15; -#endif /* CONFIG_X86_64 */ - - /* Get CS/SS and force CPL3 */ - regs->cs = sc.cs | 0x03; - regs->ss = sc.ss | 0x03; - - regs->flags = (regs->flags & ~FIX_EFLAGS) | (sc.flags & FIX_EFLAGS); - /* disable syscall checks */ - regs->orig_ax = -1; - -#ifdef CONFIG_X86_64 - /* - * Fix up SS if needed for the benefit of old DOSEMU and - * CRIU. - */ - if (unlikely(!(uc_flags & UC_STRICT_RESTORE_SS) && user_64bit_mode(regs))) - force_valid_ss(regs); -#endif - - return fpu__restore_sig((void __user *)sc.fpstate, - IS_ENABLED(CONFIG_X86_32)); + return IS_ENABLED(CONFIG_IA32_EMULATION) && + ksig->ka.sa.sa_flags & SA_IA32_ABI; } -static __always_inline int -__unsafe_setup_sigcontext(struct sigcontext __user *sc, void __user *fpstate, - struct pt_regs *regs, unsigned long mask) +static inline int is_ia32_frame(struct ksignal *ksig) { -#ifdef CONFIG_X86_32 - unsigned int gs; - savesegment(gs, gs); - - unsafe_put_user(gs, (unsigned int __user *)&sc->gs, Efault); - unsafe_put_user(regs->fs, (unsigned int __user *)&sc->fs, Efault); - unsafe_put_user(regs->es, (unsigned int __user *)&sc->es, Efault); - unsafe_put_user(regs->ds, (unsigned int __user *)&sc->ds, Efault); -#endif /* CONFIG_X86_32 */ - - unsafe_put_user(regs->di, &sc->di, Efault); - unsafe_put_user(regs->si, &sc->si, Efault); - unsafe_put_user(regs->bp, &sc->bp, Efault); - unsafe_put_user(regs->sp, &sc->sp, Efault); - unsafe_put_user(regs->bx, &sc->bx, Efault); - unsafe_put_user(regs->dx, &sc->dx, Efault); - unsafe_put_user(regs->cx, &sc->cx, Efault); - unsafe_put_user(regs->ax, &sc->ax, Efault); -#ifdef CONFIG_X86_64 - unsafe_put_user(regs->r8, &sc->r8, Efault); - unsafe_put_user(regs->r9, &sc->r9, Efault); - unsafe_put_user(regs->r10, &sc->r10, Efault); - unsafe_put_user(regs->r11, &sc->r11, Efault); - unsafe_put_user(regs->r12, &sc->r12, Efault); - unsafe_put_user(regs->r13, &sc->r13, Efault); - unsafe_put_user(regs->r14, &sc->r14, Efault); - unsafe_put_user(regs->r15, &sc->r15, Efault); -#endif /* CONFIG_X86_64 */ - - unsafe_put_user(current->thread.trap_nr, &sc->trapno, Efault); - unsafe_put_user(current->thread.error_code, &sc->err, Efault); - unsafe_put_user(regs->ip, &sc->ip, Efault); -#ifdef CONFIG_X86_32 - unsafe_put_user(regs->cs, (unsigned int __user *)&sc->cs, Efault); - unsafe_put_user(regs->flags, &sc->flags, Efault); - unsafe_put_user(regs->sp, &sc->sp_at_signal, Efault); - unsafe_put_user(regs->ss, (unsigned int __user *)&sc->ss, Efault); -#else /* !CONFIG_X86_32 */ - unsafe_put_user(regs->flags, &sc->flags, Efault); - unsafe_put_user(regs->cs, &sc->cs, Efault); - unsafe_put_user(0, &sc->gs, Efault); - unsafe_put_user(0, &sc->fs, Efault); - unsafe_put_user(regs->ss, &sc->ss, Efault); -#endif /* CONFIG_X86_32 */ - - unsafe_put_user(fpstate, (unsigned long __user *)&sc->fpstate, Efault); - - /* non-iBCS2 extensions.. */ - unsafe_put_user(mask, &sc->oldmask, Efault); - unsafe_put_user(current->thread.cr2, &sc->cr2, Efault); - return 0; -Efault: - return -EFAULT; + return IS_ENABLED(CONFIG_X86_32) || is_ia32_compat_frame(ksig); } -#define unsafe_put_sigcontext(sc, fp, regs, set, label) \ -do { \ - if (__unsafe_setup_sigcontext(sc, fp, regs, set->sig[0])) \ - goto label; \ -} while(0); - -#define unsafe_put_sigmask(set, frame, label) \ - unsafe_put_user(*(__u64 *)(set), \ - (__u64 __user *)&(frame)->uc.uc_sigmask, \ - label) +static inline int is_x32_frame(struct ksignal *ksig) +{ + return IS_ENABLED(CONFIG_X86_X32_ABI) && + ksig->ka.sa.sa_flags & SA_X32_ABI; +} /* * Set up a signal frame. @@ -223,24 +70,12 @@ do { \ /* * Determine which stack to use.. */ -static unsigned long align_sigframe(unsigned long sp) -{ -#ifdef CONFIG_X86_32 - /* - * Align the stack pointer according to the i386 ABI, - * i.e. so that on function entry ((sp + 4) & 15) == 0. - */ - sp = ((sp + 4) & -FRAME_ALIGNMENT) - 4; -#else /* !CONFIG_X86_32 */ - sp = round_down(sp, FRAME_ALIGNMENT) - 8; -#endif - return sp; -} - -static void __user * -get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size, +void __user * +get_sigframe(struct ksignal *ksig, struct pt_regs *regs, size_t frame_size, void __user **fpstate) { + struct k_sigaction *ka = &ksig->ka; + int ia32_frame = is_ia32_frame(ksig); /* Default to using normal stack */ bool nested_altstack = on_sig_stack(regs->sp); bool entering_altstack = false; @@ -249,7 +84,7 @@ get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size, unsigned long buf_fx = 0; /* redzone */ - if (IS_ENABLED(CONFIG_X86_64)) + if (!ia32_frame) sp -= 128; /* This is the X/Open sanctioned signal stack switching. */ @@ -263,7 +98,7 @@ get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size, sp = current->sas_ss_sp + current->sas_ss_size; entering_altstack = true; } - } else if (IS_ENABLED(CONFIG_X86_32) && + } else if (ia32_frame && !nested_altstack && regs->ss != __USER_DS && !(ka->sa.sa_flags & SA_RESTORER) && @@ -273,11 +108,19 @@ get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size, entering_altstack = true; } - sp = fpu__alloc_mathframe(sp, IS_ENABLED(CONFIG_X86_32), - &buf_fx, &math_size); + sp = fpu__alloc_mathframe(sp, ia32_frame, &buf_fx, &math_size); *fpstate = (void __user *)sp; - sp = align_sigframe(sp - frame_size); + sp -= frame_size; + + if (ia32_frame) + /* + * Align the stack pointer according to the i386 ABI, + * i.e. so that on function entry ((sp + 4) & 15) == 0. + */ + sp = ((sp + 4) & -FRAME_ALIGNMENT) - 4; + else + sp = round_down(sp, FRAME_ALIGNMENT) - 8; /* * If we are on the alternate signal stack and would overflow it, don't. @@ -300,391 +143,6 @@ get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size, return (void __user *)sp; } -#ifdef CONFIG_X86_32 -static const struct { - u16 poplmovl; - u32 val; - u16 int80; -} __attribute__((packed)) retcode = { - 0xb858, /* popl %eax; movl $..., %eax */ - __NR_sigreturn, - 0x80cd, /* int $0x80 */ -}; - -static const struct { - u8 movl; - u32 val; - u16 int80; - u8 pad; -} __attribute__((packed)) rt_retcode = { - 0xb8, /* movl $..., %eax */ - __NR_rt_sigreturn, - 0x80cd, /* int $0x80 */ - 0 -}; - -static int -__setup_frame(int sig, struct ksignal *ksig, sigset_t *set, - struct pt_regs *regs) -{ - struct sigframe __user *frame; - void __user *restorer; - void __user *fp = NULL; - - frame = get_sigframe(&ksig->ka, regs, sizeof(*frame), &fp); - - if (!user_access_begin(frame, sizeof(*frame))) - return -EFAULT; - - unsafe_put_user(sig, &frame->sig, Efault); - unsafe_put_sigcontext(&frame->sc, fp, regs, set, Efault); - unsafe_put_user(set->sig[1], &frame->extramask[0], Efault); - if (current->mm->context.vdso) - restorer = current->mm->context.vdso + - vdso_image_32.sym___kernel_sigreturn; - else - restorer = &frame->retcode; - if (ksig->ka.sa.sa_flags & SA_RESTORER) - restorer = ksig->ka.sa.sa_restorer; - - /* Set up to return from userspace. */ - unsafe_put_user(restorer, &frame->pretcode, Efault); - - /* - * This is popl %eax ; movl $__NR_sigreturn, %eax ; int $0x80 - * - * WE DO NOT USE IT ANY MORE! It's only left here for historical - * reasons and because gdb uses it as a signature to notice - * signal handler stack frames. - */ - unsafe_put_user(*((u64 *)&retcode), (u64 *)frame->retcode, Efault); - user_access_end(); - - /* Set up registers for signal handler */ - regs->sp = (unsigned long)frame; - regs->ip = (unsigned long)ksig->ka.sa.sa_handler; - regs->ax = (unsigned long)sig; - regs->dx = 0; - regs->cx = 0; - - regs->ds = __USER_DS; - regs->es = __USER_DS; - regs->ss = __USER_DS; - regs->cs = __USER_CS; - - return 0; - -Efault: - user_access_end(); - return -EFAULT; -} - -static int __setup_rt_frame(int sig, struct ksignal *ksig, - sigset_t *set, struct pt_regs *regs) -{ - struct rt_sigframe __user *frame; - void __user *restorer; - void __user *fp = NULL; - - frame = get_sigframe(&ksig->ka, regs, sizeof(*frame), &fp); - - if (!user_access_begin(frame, sizeof(*frame))) - return -EFAULT; - - unsafe_put_user(sig, &frame->sig, Efault); - unsafe_put_user(&frame->info, &frame->pinfo, Efault); - unsafe_put_user(&frame->uc, &frame->puc, Efault); - - /* Create the ucontext. */ - if (static_cpu_has(X86_FEATURE_XSAVE)) - unsafe_put_user(UC_FP_XSTATE, &frame->uc.uc_flags, Efault); - else - unsafe_put_user(0, &frame->uc.uc_flags, Efault); - unsafe_put_user(0, &frame->uc.uc_link, Efault); - unsafe_save_altstack(&frame->uc.uc_stack, regs->sp, Efault); - - /* Set up to return from userspace. */ - restorer = current->mm->context.vdso + - vdso_image_32.sym___kernel_rt_sigreturn; - if (ksig->ka.sa.sa_flags & SA_RESTORER) - restorer = ksig->ka.sa.sa_restorer; - unsafe_put_user(restorer, &frame->pretcode, Efault); - - /* - * This is movl $__NR_rt_sigreturn, %ax ; int $0x80 - * - * WE DO NOT USE IT ANY MORE! It's only left here for historical - * reasons and because gdb uses it as a signature to notice - * signal handler stack frames. - */ - unsafe_put_user(*((u64 *)&rt_retcode), (u64 *)frame->retcode, Efault); - unsafe_put_sigcontext(&frame->uc.uc_mcontext, fp, regs, set, Efault); - unsafe_put_sigmask(set, frame, Efault); - user_access_end(); - - if (copy_siginfo_to_user(&frame->info, &ksig->info)) - return -EFAULT; - - /* Set up registers for signal handler */ - regs->sp = (unsigned long)frame; - regs->ip = (unsigned long)ksig->ka.sa.sa_handler; - regs->ax = (unsigned long)sig; - regs->dx = (unsigned long)&frame->info; - regs->cx = (unsigned long)&frame->uc; - - regs->ds = __USER_DS; - regs->es = __USER_DS; - regs->ss = __USER_DS; - regs->cs = __USER_CS; - - return 0; -Efault: - user_access_end(); - return -EFAULT; -} -#else /* !CONFIG_X86_32 */ -static unsigned long frame_uc_flags(struct pt_regs *regs) -{ - unsigned long flags; - - if (boot_cpu_has(X86_FEATURE_XSAVE)) - flags = UC_FP_XSTATE | UC_SIGCONTEXT_SS; - else - flags = UC_SIGCONTEXT_SS; - - if (likely(user_64bit_mode(regs))) - flags |= UC_STRICT_RESTORE_SS; - - return flags; -} - -static int __setup_rt_frame(int sig, struct ksignal *ksig, - sigset_t *set, struct pt_regs *regs) -{ - struct rt_sigframe __user *frame; - void __user *fp = NULL; - unsigned long uc_flags; - - /* x86-64 should always use SA_RESTORER. */ - if (!(ksig->ka.sa.sa_flags & SA_RESTORER)) - return -EFAULT; - - frame = get_sigframe(&ksig->ka, regs, sizeof(struct rt_sigframe), &fp); - uc_flags = frame_uc_flags(regs); - - if (!user_access_begin(frame, sizeof(*frame))) - return -EFAULT; - - /* Create the ucontext. */ - unsafe_put_user(uc_flags, &frame->uc.uc_flags, Efault); - unsafe_put_user(0, &frame->uc.uc_link, Efault); - unsafe_save_altstack(&frame->uc.uc_stack, regs->sp, Efault); - - /* Set up to return from userspace. If provided, use a stub - already in userspace. */ - unsafe_put_user(ksig->ka.sa.sa_restorer, &frame->pretcode, Efault); - unsafe_put_sigcontext(&frame->uc.uc_mcontext, fp, regs, set, Efault); - unsafe_put_sigmask(set, frame, Efault); - user_access_end(); - - if (ksig->ka.sa.sa_flags & SA_SIGINFO) { - if (copy_siginfo_to_user(&frame->info, &ksig->info)) - return -EFAULT; - } - - /* Set up registers for signal handler */ - regs->di = sig; - /* In case the signal handler was declared without prototypes */ - regs->ax = 0; - - /* This also works for non SA_SIGINFO handlers because they expect the - next argument after the signal number on the stack. */ - regs->si = (unsigned long)&frame->info; - regs->dx = (unsigned long)&frame->uc; - regs->ip = (unsigned long) ksig->ka.sa.sa_handler; - - regs->sp = (unsigned long)frame; - - /* - * Set up the CS and SS registers to run signal handlers in - * 64-bit mode, even if the handler happens to be interrupting - * 32-bit or 16-bit code. - * - * SS is subtle. In 64-bit mode, we don't need any particular - * SS descriptor, but we do need SS to be valid. It's possible - * that the old SS is entirely bogus -- this can happen if the - * signal we're trying to deliver is #GP or #SS caused by a bad - * SS value. We also have a compatibility issue here: DOSEMU - * relies on the contents of the SS register indicating the - * SS value at the time of the signal, even though that code in - * DOSEMU predates sigreturn's ability to restore SS. (DOSEMU - * avoids relying on sigreturn to restore SS; instead it uses - * a trampoline.) So we do our best: if the old SS was valid, - * we keep it. Otherwise we replace it. - */ - regs->cs = __USER_CS; - - if (unlikely(regs->ss != __USER_DS)) - force_valid_ss(regs); - - return 0; - -Efault: - user_access_end(); - return -EFAULT; -} -#endif /* CONFIG_X86_32 */ - -#ifdef CONFIG_X86_X32_ABI -static int x32_copy_siginfo_to_user(struct compat_siginfo __user *to, - const struct kernel_siginfo *from) -{ - struct compat_siginfo new; - - copy_siginfo_to_external32(&new, from); - if (from->si_signo == SIGCHLD) { - new._sifields._sigchld_x32._utime = from->si_utime; - new._sifields._sigchld_x32._stime = from->si_stime; - } - if (copy_to_user(to, &new, sizeof(struct compat_siginfo))) - return -EFAULT; - return 0; -} - -int copy_siginfo_to_user32(struct compat_siginfo __user *to, - const struct kernel_siginfo *from) -{ - if (in_x32_syscall()) - return x32_copy_siginfo_to_user(to, from); - return __copy_siginfo_to_user32(to, from); -} -#endif /* CONFIG_X86_X32_ABI */ - -static int x32_setup_rt_frame(struct ksignal *ksig, - compat_sigset_t *set, - struct pt_regs *regs) -{ -#ifdef CONFIG_X86_X32_ABI - struct rt_sigframe_x32 __user *frame; - unsigned long uc_flags; - void __user *restorer; - void __user *fp = NULL; - - if (!(ksig->ka.sa.sa_flags & SA_RESTORER)) - return -EFAULT; - - frame = get_sigframe(&ksig->ka, regs, sizeof(*frame), &fp); - - uc_flags = frame_uc_flags(regs); - - if (!user_access_begin(frame, sizeof(*frame))) - return -EFAULT; - - /* Create the ucontext. */ - unsafe_put_user(uc_flags, &frame->uc.uc_flags, Efault); - unsafe_put_user(0, &frame->uc.uc_link, Efault); - unsafe_compat_save_altstack(&frame->uc.uc_stack, regs->sp, Efault); - unsafe_put_user(0, &frame->uc.uc__pad0, Efault); - restorer = ksig->ka.sa.sa_restorer; - unsafe_put_user(restorer, (unsigned long __user *)&frame->pretcode, Efault); - unsafe_put_sigcontext(&frame->uc.uc_mcontext, fp, regs, set, Efault); - unsafe_put_sigmask(set, frame, Efault); - user_access_end(); - - if (ksig->ka.sa.sa_flags & SA_SIGINFO) { - if (x32_copy_siginfo_to_user(&frame->info, &ksig->info)) - return -EFAULT; - } - - /* Set up registers for signal handler */ - regs->sp = (unsigned long) frame; - regs->ip = (unsigned long) ksig->ka.sa.sa_handler; - - /* We use the x32 calling convention here... */ - regs->di = ksig->sig; - regs->si = (unsigned long) &frame->info; - regs->dx = (unsigned long) &frame->uc; - - loadsegment(ds, __USER_DS); - loadsegment(es, __USER_DS); - - regs->cs = __USER_CS; - regs->ss = __USER_DS; -#endif /* CONFIG_X86_X32_ABI */ - - return 0; -#ifdef CONFIG_X86_X32_ABI -Efault: - user_access_end(); - return -EFAULT; -#endif -} - -/* - * Do a signal return; undo the signal stack. - */ -#ifdef CONFIG_X86_32 -SYSCALL_DEFINE0(sigreturn) -{ - struct pt_regs *regs = current_pt_regs(); - struct sigframe __user *frame; - sigset_t set; - - frame = (struct sigframe __user *)(regs->sp - 8); - - if (!access_ok(frame, sizeof(*frame))) - goto badframe; - if (__get_user(set.sig[0], &frame->sc.oldmask) || - __get_user(set.sig[1], &frame->extramask[0])) - goto badframe; - - set_current_blocked(&set); - - /* - * x86_32 has no uc_flags bits relevant to restore_sigcontext. - * Save a few cycles by skipping the __get_user. - */ - if (!restore_sigcontext(regs, &frame->sc, 0)) - goto badframe; - return regs->ax; - -badframe: - signal_fault(regs, frame, "sigreturn"); - - return 0; -} -#endif /* CONFIG_X86_32 */ - -SYSCALL_DEFINE0(rt_sigreturn) -{ - struct pt_regs *regs = current_pt_regs(); - struct rt_sigframe __user *frame; - sigset_t set; - unsigned long uc_flags; - - frame = (struct rt_sigframe __user *)(regs->sp - sizeof(long)); - if (!access_ok(frame, sizeof(*frame))) - goto badframe; - if (__get_user(*(__u64 *)&set, (__u64 __user *)&frame->uc.uc_sigmask)) - goto badframe; - if (__get_user(uc_flags, &frame->uc.uc_flags)) - goto badframe; - - set_current_blocked(&set); - - if (!restore_sigcontext(regs, &frame->uc.uc_mcontext, uc_flags)) - goto badframe; - - if (restore_altstack(&frame->uc.uc_stack)) - goto badframe; - - return regs->ax; - -badframe: - signal_fault(regs, frame, "rt_sigreturn"); - return 0; -} - /* * There are four different struct types for signal frame: sigframe_ia32, * rt_sigframe_ia32, rt_sigframe_x32, and rt_sigframe. Use the worst case @@ -743,43 +201,22 @@ unsigned long get_sigframe_size(void) return max_frame_size; } -static inline int is_ia32_compat_frame(struct ksignal *ksig) -{ - return IS_ENABLED(CONFIG_IA32_EMULATION) && - ksig->ka.sa.sa_flags & SA_IA32_ABI; -} - -static inline int is_ia32_frame(struct ksignal *ksig) -{ - return IS_ENABLED(CONFIG_X86_32) || is_ia32_compat_frame(ksig); -} - -static inline int is_x32_frame(struct ksignal *ksig) -{ - return IS_ENABLED(CONFIG_X86_X32_ABI) && - ksig->ka.sa.sa_flags & SA_X32_ABI; -} - static int setup_rt_frame(struct ksignal *ksig, struct pt_regs *regs) { - int usig = ksig->sig; - sigset_t *set = sigmask_to_save(); - compat_sigset_t *cset = (compat_sigset_t *) set; - /* Perform fixup for the pre-signal frame. */ rseq_signal_deliver(ksig, regs); /* Set up the stack frame */ if (is_ia32_frame(ksig)) { if (ksig->ka.sa.sa_flags & SA_SIGINFO) - return ia32_setup_rt_frame(usig, ksig, cset, regs); + return ia32_setup_rt_frame(ksig, regs); else - return ia32_setup_frame(usig, ksig, cset, regs); + return ia32_setup_frame(ksig, regs); } else if (is_x32_frame(ksig)) { - return x32_setup_rt_frame(ksig, cset, regs); + return x32_setup_rt_frame(ksig, regs); } else { - return __setup_rt_frame(ksig->sig, ksig, set, regs); + return x64_setup_rt_frame(ksig, regs); } } @@ -969,36 +406,3 @@ bool sigaltstack_size_valid(size_t ss_size) return true; } #endif /* CONFIG_DYNAMIC_SIGFRAME */ - -#ifdef CONFIG_X86_X32_ABI -COMPAT_SYSCALL_DEFINE0(x32_rt_sigreturn) -{ - struct pt_regs *regs = current_pt_regs(); - struct rt_sigframe_x32 __user *frame; - sigset_t set; - unsigned long uc_flags; - - frame = (struct rt_sigframe_x32 __user *)(regs->sp - 8); - - if (!access_ok(frame, sizeof(*frame))) - goto badframe; - if (__get_user(set.sig[0], (__u64 __user *)&frame->uc.uc_sigmask)) - goto badframe; - if (__get_user(uc_flags, &frame->uc.uc_flags)) - goto badframe; - - set_current_blocked(&set); - - if (!restore_sigcontext(regs, &frame->uc.uc_mcontext, uc_flags)) - goto badframe; - - if (compat_restore_altstack(&frame->uc.uc_stack)) - goto badframe; - - return regs->ax; - -badframe: - signal_fault(regs, frame, "x32 rt_sigreturn"); - return 0; -} -#endif diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/kernel/signal_32.c similarity index 82% rename from arch/x86/ia32/ia32_signal.c rename to arch/x86/kernel/signal_32.c index c9c3859322fa..2553136cf39b 100644 --- a/arch/x86/ia32/ia32_signal.c +++ b/arch/x86/kernel/signal_32.c @@ -1,7 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 /* - * linux/arch/x86_64/ia32/ia32_signal.c - * * Copyright (C) 1991, 1992 Linus Torvalds * * 1997-11-28 Modified for POSIX.1b signals by Richard Henderson @@ -26,7 +24,6 @@ #include #include #include -#include #include #include #include @@ -35,6 +32,9 @@ #include #include +#ifdef CONFIG_IA32_EMULATION +#include + static inline void reload_segments(struct sigcontext_32 *sc) { unsigned int cur; @@ -53,6 +53,21 @@ static inline void reload_segments(struct sigcontext_32 *sc) loadsegment(es, sc->es | 0x03); } +#define sigset32_t compat_sigset_t +#define restore_altstack32 compat_restore_altstack +#define unsafe_save_altstack32 unsafe_compat_save_altstack + +#else + +#define sigset32_t sigset_t +#define __NR_ia32_sigreturn __NR_sigreturn +#define __NR_ia32_rt_sigreturn __NR_rt_sigreturn +#define restore_altstack32 restore_altstack +#define unsafe_save_altstack32 unsafe_save_altstack +#define __copy_siginfo_to_user32 copy_siginfo_to_user + +#endif + /* * Do a signal return; undo the signal stack. */ @@ -86,6 +101,7 @@ static bool ia32_restore_sigcontext(struct pt_regs *regs, /* disable syscall checks */ regs->orig_ax = -1; +#ifdef CONFIG_IA32_EMULATION /* * Reload fs and gs if they have changed in the signal * handler. This does not handle long fs/gs base changes in @@ -93,10 +109,17 @@ static bool ia32_restore_sigcontext(struct pt_regs *regs, * normal case. */ reload_segments(&sc); +#else + loadsegment(gs, sc.gs); + regs->fs = sc.fs; + regs->es = sc.es; + regs->ds = sc.ds; +#endif + return fpu__restore_sig(compat_ptr(sc.fpstate), 1); } -COMPAT_SYSCALL_DEFINE0(sigreturn) +SYSCALL32_DEFINE0(sigreturn) { struct pt_regs *regs = current_pt_regs(); struct sigframe_ia32 __user *frame = (struct sigframe_ia32 __user *)(regs->sp-8); @@ -119,7 +142,7 @@ badframe: return 0; } -COMPAT_SYSCALL_DEFINE0(rt_sigreturn) +SYSCALL32_DEFINE0(rt_sigreturn) { struct pt_regs *regs = current_pt_regs(); struct rt_sigframe_ia32 __user *frame; @@ -129,7 +152,7 @@ COMPAT_SYSCALL_DEFINE0(rt_sigreturn) if (!access_ok(frame, sizeof(*frame))) goto badframe; - if (__get_user(set.sig[0], (__u64 __user *)&frame->uc.uc_sigmask)) + if (__get_user(*(__u64 *)&set, (__u64 __user *)&frame->uc.uc_sigmask)) goto badframe; set_current_blocked(&set); @@ -137,7 +160,7 @@ COMPAT_SYSCALL_DEFINE0(rt_sigreturn) if (!ia32_restore_sigcontext(regs, &frame->uc.uc_mcontext)) goto badframe; - if (compat_restore_altstack(&frame->uc.uc_stack)) + if (restore_altstack32(&frame->uc.uc_stack)) goto badframe; return regs->ax; @@ -159,9 +182,15 @@ __unsafe_setup_sigcontext32(struct sigcontext_32 __user *sc, struct pt_regs *regs, unsigned int mask) { unsafe_put_user(get_user_seg(gs), (unsigned int __user *)&sc->gs, Efault); +#ifdef CONFIG_IA32_EMULATION unsafe_put_user(get_user_seg(fs), (unsigned int __user *)&sc->fs, Efault); unsafe_put_user(get_user_seg(ds), (unsigned int __user *)&sc->ds, Efault); unsafe_put_user(get_user_seg(es), (unsigned int __user *)&sc->es, Efault); +#else + unsafe_put_user(regs->fs, (unsigned int __user *)&sc->fs, Efault); + unsafe_put_user(regs->es, (unsigned int __user *)&sc->es, Efault); + unsafe_put_user(regs->ds, (unsigned int __user *)&sc->ds, Efault); +#endif unsafe_put_user(regs->di, &sc->di, Efault); unsafe_put_user(regs->si, &sc->si, Efault); @@ -196,43 +225,9 @@ do { \ goto label; \ } while(0) -/* - * Determine which stack to use.. - */ -static void __user *get_sigframe(struct ksignal *ksig, struct pt_regs *regs, - size_t frame_size, - void __user **fpstate) -{ - unsigned long sp, fx_aligned, math_size; - - /* Default to using normal stack */ - sp = regs->sp; - - /* This is the X/Open sanctioned signal stack switching. */ - if (ksig->ka.sa.sa_flags & SA_ONSTACK) - sp = sigsp(sp, ksig); - /* This is the legacy signal stack switching. */ - else if (regs->ss != __USER32_DS && - !(ksig->ka.sa.sa_flags & SA_RESTORER) && - ksig->ka.sa.sa_restorer) - sp = (unsigned long) ksig->ka.sa.sa_restorer; - - sp = fpu__alloc_mathframe(sp, 1, &fx_aligned, &math_size); - *fpstate = (struct _fpstate_32 __user *) sp; - if (!copy_fpstate_to_sigframe(*fpstate, (void __user *)fx_aligned, - math_size)) - return (void __user *) -1L; - - sp -= frame_size; - /* Align the stack pointer according to the i386 ABI, - * i.e. so that on function entry ((sp + 4) & 15) == 0. */ - sp = ((sp + 4) & -16ul) - 4; - return (void __user *) sp; -} - -int ia32_setup_frame(int sig, struct ksignal *ksig, - compat_sigset_t *set, struct pt_regs *regs) +int ia32_setup_frame(struct ksignal *ksig, struct pt_regs *regs) { + sigset32_t *set = (sigset32_t *) sigmask_to_save(); struct sigframe_ia32 __user *frame; void __user *restorer; void __user *fp = NULL; @@ -264,7 +259,7 @@ int ia32_setup_frame(int sig, struct ksignal *ksig, if (!user_access_begin(frame, sizeof(*frame))) return -EFAULT; - unsafe_put_user(sig, &frame->sig, Efault); + unsafe_put_user(ksig->sig, &frame->sig, Efault); unsafe_put_sigcontext32(&frame->sc, fp, regs, set, Efault); unsafe_put_user(set->sig[1], &frame->extramask[0], Efault); unsafe_put_user(ptr_to_compat(restorer), &frame->pretcode, Efault); @@ -280,15 +275,20 @@ int ia32_setup_frame(int sig, struct ksignal *ksig, regs->ip = (unsigned long) ksig->ka.sa.sa_handler; /* Make -mregparm=3 work */ - regs->ax = sig; + regs->ax = ksig->sig; regs->dx = 0; regs->cx = 0; - loadsegment(ds, __USER32_DS); - loadsegment(es, __USER32_DS); +#ifdef CONFIG_IA32_EMULATION + loadsegment(ds, __USER_DS); + loadsegment(es, __USER_DS); +#else + regs->ds = __USER_DS; + regs->es = __USER_DS; +#endif regs->cs = __USER32_CS; - regs->ss = __USER32_DS; + regs->ss = __USER_DS; return 0; Efault: @@ -296,9 +296,9 @@ Efault: return -EFAULT; } -int ia32_setup_rt_frame(int sig, struct ksignal *ksig, - compat_sigset_t *set, struct pt_regs *regs) +int ia32_setup_rt_frame(struct ksignal *ksig, struct pt_regs *regs) { + sigset32_t *set = (sigset32_t *) sigmask_to_save(); struct rt_sigframe_ia32 __user *frame; void __user *restorer; void __user *fp = NULL; @@ -321,7 +321,7 @@ int ia32_setup_rt_frame(int sig, struct ksignal *ksig, if (!user_access_begin(frame, sizeof(*frame))) return -EFAULT; - unsafe_put_user(sig, &frame->sig, Efault); + unsafe_put_user(ksig->sig, &frame->sig, Efault); unsafe_put_user(ptr_to_compat(&frame->info), &frame->pinfo, Efault); unsafe_put_user(ptr_to_compat(&frame->uc), &frame->puc, Efault); @@ -331,7 +331,7 @@ int ia32_setup_rt_frame(int sig, struct ksignal *ksig, else unsafe_put_user(0, &frame->uc.uc_flags, Efault); unsafe_put_user(0, &frame->uc.uc_link, Efault); - unsafe_compat_save_altstack(&frame->uc.uc_stack, regs->sp, Efault); + unsafe_save_altstack32(&frame->uc.uc_stack, regs->sp, Efault); if (ksig->ka.sa.sa_flags & SA_RESTORER) restorer = ksig->ka.sa.sa_restorer; @@ -357,15 +357,20 @@ int ia32_setup_rt_frame(int sig, struct ksignal *ksig, regs->ip = (unsigned long) ksig->ka.sa.sa_handler; /* Make -mregparm=3 work */ - regs->ax = sig; + regs->ax = ksig->sig; regs->dx = (unsigned long) &frame->info; regs->cx = (unsigned long) &frame->uc; - loadsegment(ds, __USER32_DS); - loadsegment(es, __USER32_DS); +#ifdef CONFIG_IA32_EMULATION + loadsegment(ds, __USER_DS); + loadsegment(es, __USER_DS); +#else + regs->ds = __USER_DS; + regs->es = __USER_DS; +#endif regs->cs = __USER32_CS; - regs->ss = __USER32_DS; + regs->ss = __USER_DS; return 0; Efault: diff --git a/arch/x86/kernel/signal_64.c b/arch/x86/kernel/signal_64.c new file mode 100644 index 000000000000..ff9c55064223 --- /dev/null +++ b/arch/x86/kernel/signal_64.c @@ -0,0 +1,383 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 1991, 1992 Linus Torvalds + * Copyright (C) 2000, 2001, 2002 Andi Kleen SuSE Labs + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include +#include +#include +#include +#include + +#include +#include +#include + +#include +#include +#include + +/* + * If regs->ss will cause an IRET fault, change it. Otherwise leave it + * alone. Using this generally makes no sense unless + * user_64bit_mode(regs) would return true. + */ +static void force_valid_ss(struct pt_regs *regs) +{ + u32 ar; + asm volatile ("lar %[old_ss], %[ar]\n\t" + "jz 1f\n\t" /* If invalid: */ + "xorl %[ar], %[ar]\n\t" /* set ar = 0 */ + "1:" + : [ar] "=r" (ar) + : [old_ss] "rm" ((u16)regs->ss)); + + /* + * For a valid 64-bit user context, we need DPL 3, type + * read-write data or read-write exp-down data, and S and P + * set. We can't use VERW because VERW doesn't check the + * P bit. + */ + ar &= AR_DPL_MASK | AR_S | AR_P | AR_TYPE_MASK; + if (ar != (AR_DPL3 | AR_S | AR_P | AR_TYPE_RWDATA) && + ar != (AR_DPL3 | AR_S | AR_P | AR_TYPE_RWDATA_EXPDOWN)) + regs->ss = __USER_DS; +} + +static bool restore_sigcontext(struct pt_regs *regs, + struct sigcontext __user *usc, + unsigned long uc_flags) +{ + struct sigcontext sc; + + /* Always make any pending restarted system calls return -EINTR */ + current->restart_block.fn = do_no_restart_syscall; + + if (copy_from_user(&sc, usc, offsetof(struct sigcontext, reserved1))) + return false; + + regs->bx = sc.bx; + regs->cx = sc.cx; + regs->dx = sc.dx; + regs->si = sc.si; + regs->di = sc.di; + regs->bp = sc.bp; + regs->ax = sc.ax; + regs->sp = sc.sp; + regs->ip = sc.ip; + regs->r8 = sc.r8; + regs->r9 = sc.r9; + regs->r10 = sc.r10; + regs->r11 = sc.r11; + regs->r12 = sc.r12; + regs->r13 = sc.r13; + regs->r14 = sc.r14; + regs->r15 = sc.r15; + + /* Get CS/SS and force CPL3 */ + regs->cs = sc.cs | 0x03; + regs->ss = sc.ss | 0x03; + + regs->flags = (regs->flags & ~FIX_EFLAGS) | (sc.flags & FIX_EFLAGS); + /* disable syscall checks */ + regs->orig_ax = -1; + + /* + * Fix up SS if needed for the benefit of old DOSEMU and + * CRIU. + */ + if (unlikely(!(uc_flags & UC_STRICT_RESTORE_SS) && user_64bit_mode(regs))) + force_valid_ss(regs); + + return fpu__restore_sig((void __user *)sc.fpstate, 0); +} + +static __always_inline int +__unsafe_setup_sigcontext(struct sigcontext __user *sc, void __user *fpstate, + struct pt_regs *regs, unsigned long mask) +{ + unsafe_put_user(regs->di, &sc->di, Efault); + unsafe_put_user(regs->si, &sc->si, Efault); + unsafe_put_user(regs->bp, &sc->bp, Efault); + unsafe_put_user(regs->sp, &sc->sp, Efault); + unsafe_put_user(regs->bx, &sc->bx, Efault); + unsafe_put_user(regs->dx, &sc->dx, Efault); + unsafe_put_user(regs->cx, &sc->cx, Efault); + unsafe_put_user(regs->ax, &sc->ax, Efault); + unsafe_put_user(regs->r8, &sc->r8, Efault); + unsafe_put_user(regs->r9, &sc->r9, Efault); + unsafe_put_user(regs->r10, &sc->r10, Efault); + unsafe_put_user(regs->r11, &sc->r11, Efault); + unsafe_put_user(regs->r12, &sc->r12, Efault); + unsafe_put_user(regs->r13, &sc->r13, Efault); + unsafe_put_user(regs->r14, &sc->r14, Efault); + unsafe_put_user(regs->r15, &sc->r15, Efault); + + unsafe_put_user(current->thread.trap_nr, &sc->trapno, Efault); + unsafe_put_user(current->thread.error_code, &sc->err, Efault); + unsafe_put_user(regs->ip, &sc->ip, Efault); + unsafe_put_user(regs->flags, &sc->flags, Efault); + unsafe_put_user(regs->cs, &sc->cs, Efault); + unsafe_put_user(0, &sc->gs, Efault); + unsafe_put_user(0, &sc->fs, Efault); + unsafe_put_user(regs->ss, &sc->ss, Efault); + + unsafe_put_user(fpstate, (unsigned long __user *)&sc->fpstate, Efault); + + /* non-iBCS2 extensions.. */ + unsafe_put_user(mask, &sc->oldmask, Efault); + unsafe_put_user(current->thread.cr2, &sc->cr2, Efault); + return 0; +Efault: + return -EFAULT; +} + +#define unsafe_put_sigcontext(sc, fp, regs, set, label) \ +do { \ + if (__unsafe_setup_sigcontext(sc, fp, regs, set->sig[0])) \ + goto label; \ +} while(0); + +#define unsafe_put_sigmask(set, frame, label) \ + unsafe_put_user(*(__u64 *)(set), \ + (__u64 __user *)&(frame)->uc.uc_sigmask, \ + label) + +static unsigned long frame_uc_flags(struct pt_regs *regs) +{ + unsigned long flags; + + if (boot_cpu_has(X86_FEATURE_XSAVE)) + flags = UC_FP_XSTATE | UC_SIGCONTEXT_SS; + else + flags = UC_SIGCONTEXT_SS; + + if (likely(user_64bit_mode(regs))) + flags |= UC_STRICT_RESTORE_SS; + + return flags; +} + +int x64_setup_rt_frame(struct ksignal *ksig, struct pt_regs *regs) +{ + sigset_t *set = sigmask_to_save(); + struct rt_sigframe __user *frame; + void __user *fp = NULL; + unsigned long uc_flags; + + /* x86-64 should always use SA_RESTORER. */ + if (!(ksig->ka.sa.sa_flags & SA_RESTORER)) + return -EFAULT; + + frame = get_sigframe(ksig, regs, sizeof(struct rt_sigframe), &fp); + uc_flags = frame_uc_flags(regs); + + if (!user_access_begin(frame, sizeof(*frame))) + return -EFAULT; + + /* Create the ucontext. */ + unsafe_put_user(uc_flags, &frame->uc.uc_flags, Efault); + unsafe_put_user(0, &frame->uc.uc_link, Efault); + unsafe_save_altstack(&frame->uc.uc_stack, regs->sp, Efault); + + /* Set up to return from userspace. If provided, use a stub + already in userspace. */ + unsafe_put_user(ksig->ka.sa.sa_restorer, &frame->pretcode, Efault); + unsafe_put_sigcontext(&frame->uc.uc_mcontext, fp, regs, set, Efault); + unsafe_put_sigmask(set, frame, Efault); + user_access_end(); + + if (ksig->ka.sa.sa_flags & SA_SIGINFO) { + if (copy_siginfo_to_user(&frame->info, &ksig->info)) + return -EFAULT; + } + + /* Set up registers for signal handler */ + regs->di = ksig->sig; + /* In case the signal handler was declared without prototypes */ + regs->ax = 0; + + /* This also works for non SA_SIGINFO handlers because they expect the + next argument after the signal number on the stack. */ + regs->si = (unsigned long)&frame->info; + regs->dx = (unsigned long)&frame->uc; + regs->ip = (unsigned long) ksig->ka.sa.sa_handler; + + regs->sp = (unsigned long)frame; + + /* + * Set up the CS and SS registers to run signal handlers in + * 64-bit mode, even if the handler happens to be interrupting + * 32-bit or 16-bit code. + * + * SS is subtle. In 64-bit mode, we don't need any particular + * SS descriptor, but we do need SS to be valid. It's possible + * that the old SS is entirely bogus -- this can happen if the + * signal we're trying to deliver is #GP or #SS caused by a bad + * SS value. We also have a compatibility issue here: DOSEMU + * relies on the contents of the SS register indicating the + * SS value at the time of the signal, even though that code in + * DOSEMU predates sigreturn's ability to restore SS. (DOSEMU + * avoids relying on sigreturn to restore SS; instead it uses + * a trampoline.) So we do our best: if the old SS was valid, + * we keep it. Otherwise we replace it. + */ + regs->cs = __USER_CS; + + if (unlikely(regs->ss != __USER_DS)) + force_valid_ss(regs); + + return 0; + +Efault: + user_access_end(); + return -EFAULT; +} + +/* + * Do a signal return; undo the signal stack. + */ +SYSCALL_DEFINE0(rt_sigreturn) +{ + struct pt_regs *regs = current_pt_regs(); + struct rt_sigframe __user *frame; + sigset_t set; + unsigned long uc_flags; + + frame = (struct rt_sigframe __user *)(regs->sp - sizeof(long)); + if (!access_ok(frame, sizeof(*frame))) + goto badframe; + if (__get_user(*(__u64 *)&set, (__u64 __user *)&frame->uc.uc_sigmask)) + goto badframe; + if (__get_user(uc_flags, &frame->uc.uc_flags)) + goto badframe; + + set_current_blocked(&set); + + if (!restore_sigcontext(regs, &frame->uc.uc_mcontext, uc_flags)) + goto badframe; + + if (restore_altstack(&frame->uc.uc_stack)) + goto badframe; + + return regs->ax; + +badframe: + signal_fault(regs, frame, "rt_sigreturn"); + return 0; +} + +#ifdef CONFIG_X86_X32_ABI +static int x32_copy_siginfo_to_user(struct compat_siginfo __user *to, + const struct kernel_siginfo *from) +{ + struct compat_siginfo new; + + copy_siginfo_to_external32(&new, from); + if (from->si_signo == SIGCHLD) { + new._sifields._sigchld_x32._utime = from->si_utime; + new._sifields._sigchld_x32._stime = from->si_stime; + } + if (copy_to_user(to, &new, sizeof(struct compat_siginfo))) + return -EFAULT; + return 0; +} + +int copy_siginfo_to_user32(struct compat_siginfo __user *to, + const struct kernel_siginfo *from) +{ + if (in_x32_syscall()) + return x32_copy_siginfo_to_user(to, from); + return __copy_siginfo_to_user32(to, from); +} + +int x32_setup_rt_frame(struct ksignal *ksig, struct pt_regs *regs) +{ + compat_sigset_t *set = (compat_sigset_t *) sigmask_to_save(); + struct rt_sigframe_x32 __user *frame; + unsigned long uc_flags; + void __user *restorer; + void __user *fp = NULL; + + if (!(ksig->ka.sa.sa_flags & SA_RESTORER)) + return -EFAULT; + + frame = get_sigframe(ksig, regs, sizeof(*frame), &fp); + + uc_flags = frame_uc_flags(regs); + + if (!user_access_begin(frame, sizeof(*frame))) + return -EFAULT; + + /* Create the ucontext. */ + unsafe_put_user(uc_flags, &frame->uc.uc_flags, Efault); + unsafe_put_user(0, &frame->uc.uc_link, Efault); + unsafe_compat_save_altstack(&frame->uc.uc_stack, regs->sp, Efault); + unsafe_put_user(0, &frame->uc.uc__pad0, Efault); + restorer = ksig->ka.sa.sa_restorer; + unsafe_put_user(restorer, (unsigned long __user *)&frame->pretcode, Efault); + unsafe_put_sigcontext(&frame->uc.uc_mcontext, fp, regs, set, Efault); + unsafe_put_sigmask(set, frame, Efault); + user_access_end(); + + if (ksig->ka.sa.sa_flags & SA_SIGINFO) { + if (x32_copy_siginfo_to_user(&frame->info, &ksig->info)) + return -EFAULT; + } + + /* Set up registers for signal handler */ + regs->sp = (unsigned long) frame; + regs->ip = (unsigned long) ksig->ka.sa.sa_handler; + + /* We use the x32 calling convention here... */ + regs->di = ksig->sig; + regs->si = (unsigned long) &frame->info; + regs->dx = (unsigned long) &frame->uc; + + loadsegment(ds, __USER_DS); + loadsegment(es, __USER_DS); + + regs->cs = __USER_CS; + regs->ss = __USER_DS; + + return 0; + +Efault: + user_access_end(); + return -EFAULT; +} + +COMPAT_SYSCALL_DEFINE0(x32_rt_sigreturn) +{ + struct pt_regs *regs = current_pt_regs(); + struct rt_sigframe_x32 __user *frame; + sigset_t set; + unsigned long uc_flags; + + frame = (struct rt_sigframe_x32 __user *)(regs->sp - 8); + + if (!access_ok(frame, sizeof(*frame))) + goto badframe; + if (__get_user(set.sig[0], (__u64 __user *)&frame->uc.uc_sigmask)) + goto badframe; + if (__get_user(uc_flags, &frame->uc.uc_flags)) + goto badframe; + + set_current_blocked(&set); + + if (!restore_sigcontext(regs, &frame->uc.uc_mcontext, uc_flags)) + goto badframe; + + if (compat_restore_altstack(&frame->uc.uc_stack)) + goto badframe; + + return regs->ax; + +badframe: + signal_fault(regs, frame, "x32 rt_sigreturn"); + return 0; +} +#endif /* CONFIG_X86_X32_ABI */ diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index d3fdec706f1d..d1e1679f32cf 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -68,13 +68,13 @@ #ifdef CONFIG_X86_64 #include -#include #else #include #include -#include #endif +#include + DECLARE_BITMAP(system_vectors, NR_VECTORS); static inline void cond_local_irq_enable(struct pt_regs *regs) diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index cafacb2e58cc..a78e73da4a74 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -51,7 +51,7 @@ int tsc_clocksource_reliable; static u32 art_to_tsc_numerator; static u32 art_to_tsc_denominator; static u64 art_to_tsc_offset; -struct clocksource *art_related_clocksource; +static struct clocksource *art_related_clocksource; struct cyc2ns { struct cyc2ns_data data[2]; /* 0 + 2*16 = 32 */ diff --git a/arch/x86/xen/xen-asm.S b/arch/x86/xen/xen-asm.S index 6b4fdf6b9542..4a184f6e4e4d 100644 --- a/arch/x86/xen/xen-asm.S +++ b/arch/x86/xen/xen-asm.S @@ -262,10 +262,10 @@ SYM_CODE_START(xen_entry_SYSCALL_compat) /* * Neither Xen nor the kernel really knows what the old SS and - * CS were. The kernel expects __USER32_DS and __USER32_CS, so + * CS were. The kernel expects __USER_DS and __USER32_CS, so * report those values even though Xen will guess its own values. */ - movq $__USER32_DS, 4*8(%rsp) + movq $__USER_DS, 4*8(%rsp) movq $__USER32_CS, 1*8(%rsp) jmp entry_SYSCALL_compat_after_hwframe @@ -284,10 +284,10 @@ SYM_CODE_START(xen_entry_SYSENTER_compat) /* * Neither Xen nor the kernel really knows what the old SS and - * CS were. The kernel expects __USER32_DS and __USER32_CS, so + * CS were. The kernel expects __USER_DS and __USER32_CS, so * report those values even though Xen will guess its own values. */ - movq $__USER32_DS, 4*8(%rsp) + movq $__USER_DS, 4*8(%rsp) movq $__USER32_CS, 1*8(%rsp) jmp entry_SYSENTER_compat_after_hwframe diff --git a/drivers/bluetooth/hci_qca.c b/drivers/bluetooth/hci_qca.c index 8df11016fd51..ba8be8e1bebd 100644 --- a/drivers/bluetooth/hci_qca.c +++ b/drivers/bluetooth/hci_qca.c @@ -696,9 +696,15 @@ static int qca_close(struct hci_uart *hu) skb_queue_purge(&qca->tx_wait_q); skb_queue_purge(&qca->txq); skb_queue_purge(&qca->rx_memdump_q); + /* + * Shut the timers down so they can't be rearmed when + * destroy_workqueue() drains pending work which in turn might try + * to arm a timer. After shutdown rearm attempts are silently + * ignored by the timer core code. + */ + timer_shutdown_sync(&qca->tx_idle_timer); + timer_shutdown_sync(&qca->wake_retrans_timer); destroy_workqueue(qca->workqueue); - del_timer_sync(&qca->tx_idle_timer); - del_timer_sync(&qca->wake_retrans_timer); qca->hu = NULL; kfree_skb(qca->rx_skb); diff --git a/drivers/char/tpm/tpm-dev-common.c b/drivers/char/tpm/tpm-dev-common.c index dc4c0a0a5129..30b4c288c1bb 100644 --- a/drivers/char/tpm/tpm-dev-common.c +++ b/drivers/char/tpm/tpm-dev-common.c @@ -155,7 +155,7 @@ ssize_t tpm_common_read(struct file *file, char __user *buf, out: if (!priv->response_length) { *off = 0; - del_singleshot_timer_sync(&priv->user_read_timer); + del_timer_sync(&priv->user_read_timer); flush_work(&priv->timeout_work); } mutex_unlock(&priv->buffer_mutex); @@ -262,7 +262,7 @@ __poll_t tpm_common_poll(struct file *file, poll_table *wait) void tpm_common_release(struct file *file, struct file_priv *priv) { flush_work(&priv->async_work); - del_singleshot_timer_sync(&priv->user_read_timer); + del_timer_sync(&priv->user_read_timer); flush_work(&priv->timeout_work); file->private_data = NULL; priv->response_length = 0; diff --git a/drivers/clocksource/arm_arch_timer.c b/drivers/clocksource/arm_arch_timer.c index 933bb960490d..e09d4427f604 100644 --- a/drivers/clocksource/arm_arch_timer.c +++ b/drivers/clocksource/arm_arch_timer.c @@ -18,6 +18,7 @@ #include #include #include +#include #include #include #include @@ -97,7 +98,7 @@ static bool evtstrm_enable __ro_after_init = IS_ENABLED(CONFIG_ARM_ARCH_TIMER_EV static int __init early_evtstrm_cfg(char *buf) { - return strtobool(buf, &evtstrm_enable); + return kstrtobool(buf, &evtstrm_enable); } early_param("clocksource.arm_arch_timer.evtstrm", early_evtstrm_cfg); @@ -687,8 +688,8 @@ static irqreturn_t arch_timer_handler_virt_mem(int irq, void *dev_id) return timer_handler(ARCH_TIMER_MEM_VIRT_ACCESS, evt); } -static __always_inline int timer_shutdown(const int access, - struct clock_event_device *clk) +static __always_inline int arch_timer_shutdown(const int access, + struct clock_event_device *clk) { unsigned long ctrl; @@ -701,22 +702,22 @@ static __always_inline int timer_shutdown(const int access, static int arch_timer_shutdown_virt(struct clock_event_device *clk) { - return timer_shutdown(ARCH_TIMER_VIRT_ACCESS, clk); + return arch_timer_shutdown(ARCH_TIMER_VIRT_ACCESS, clk); } static int arch_timer_shutdown_phys(struct clock_event_device *clk) { - return timer_shutdown(ARCH_TIMER_PHYS_ACCESS, clk); + return arch_timer_shutdown(ARCH_TIMER_PHYS_ACCESS, clk); } static int arch_timer_shutdown_virt_mem(struct clock_event_device *clk) { - return timer_shutdown(ARCH_TIMER_MEM_VIRT_ACCESS, clk); + return arch_timer_shutdown(ARCH_TIMER_MEM_VIRT_ACCESS, clk); } static int arch_timer_shutdown_phys_mem(struct clock_event_device *clk) { - return timer_shutdown(ARCH_TIMER_MEM_PHYS_ACCESS, clk); + return arch_timer_shutdown(ARCH_TIMER_MEM_PHYS_ACCESS, clk); } static __always_inline void set_next_event(const int access, unsigned long evt, diff --git a/drivers/clocksource/ingenic-ost.c b/drivers/clocksource/ingenic-ost.c index 06d25754e606..9f7c280a1336 100644 --- a/drivers/clocksource/ingenic-ost.c +++ b/drivers/clocksource/ingenic-ost.c @@ -141,7 +141,7 @@ static int __init ingenic_ost_probe(struct platform_device *pdev) return 0; } -static int __maybe_unused ingenic_ost_suspend(struct device *dev) +static int ingenic_ost_suspend(struct device *dev) { struct ingenic_ost *ost = dev_get_drvdata(dev); @@ -150,14 +150,14 @@ static int __maybe_unused ingenic_ost_suspend(struct device *dev) return 0; } -static int __maybe_unused ingenic_ost_resume(struct device *dev) +static int ingenic_ost_resume(struct device *dev) { struct ingenic_ost *ost = dev_get_drvdata(dev); return clk_enable(ost->clk); } -static const struct dev_pm_ops __maybe_unused ingenic_ost_pm_ops = { +static const struct dev_pm_ops ingenic_ost_pm_ops = { /* _noirq: We want the OST clock to be gated last / ungated first */ .suspend_noirq = ingenic_ost_suspend, .resume_noirq = ingenic_ost_resume, @@ -181,9 +181,7 @@ static const struct of_device_id ingenic_ost_of_match[] = { static struct platform_driver ingenic_ost_driver = { .driver = { .name = "ingenic-ost", -#ifdef CONFIG_PM_SUSPEND - .pm = &ingenic_ost_pm_ops, -#endif + .pm = pm_sleep_ptr(&ingenic_ost_pm_ops), .of_match_table = ingenic_ost_of_match, }, }; diff --git a/drivers/clocksource/sh_cmt.c b/drivers/clocksource/sh_cmt.c index 64dcb082d4cf..7b952aa52c0b 100644 --- a/drivers/clocksource/sh_cmt.c +++ b/drivers/clocksource/sh_cmt.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #include #include @@ -116,6 +117,7 @@ struct sh_cmt_device { void __iomem *mapbase; struct clk *clk; unsigned long rate; + unsigned int reg_delay; raw_spinlock_t lock; /* Protect the shared start/stop register */ @@ -247,10 +249,17 @@ static inline u32 sh_cmt_read_cmstr(struct sh_cmt_channel *ch) static inline void sh_cmt_write_cmstr(struct sh_cmt_channel *ch, u32 value) { - if (ch->iostart) - ch->cmt->info->write_control(ch->iostart, 0, value); - else - ch->cmt->info->write_control(ch->cmt->mapbase, 0, value); + u32 old_value = sh_cmt_read_cmstr(ch); + + if (value != old_value) { + if (ch->iostart) { + ch->cmt->info->write_control(ch->iostart, 0, value); + udelay(ch->cmt->reg_delay); + } else { + ch->cmt->info->write_control(ch->cmt->mapbase, 0, value); + udelay(ch->cmt->reg_delay); + } + } } static inline u32 sh_cmt_read_cmcsr(struct sh_cmt_channel *ch) @@ -260,7 +269,12 @@ static inline u32 sh_cmt_read_cmcsr(struct sh_cmt_channel *ch) static inline void sh_cmt_write_cmcsr(struct sh_cmt_channel *ch, u32 value) { - ch->cmt->info->write_control(ch->ioctrl, CMCSR, value); + u32 old_value = sh_cmt_read_cmcsr(ch); + + if (value != old_value) { + ch->cmt->info->write_control(ch->ioctrl, CMCSR, value); + udelay(ch->cmt->reg_delay); + } } static inline u32 sh_cmt_read_cmcnt(struct sh_cmt_channel *ch) @@ -268,14 +282,33 @@ static inline u32 sh_cmt_read_cmcnt(struct sh_cmt_channel *ch) return ch->cmt->info->read_count(ch->ioctrl, CMCNT); } -static inline void sh_cmt_write_cmcnt(struct sh_cmt_channel *ch, u32 value) +static inline int sh_cmt_write_cmcnt(struct sh_cmt_channel *ch, u32 value) { + /* Tests showed that we need to wait 3 clocks here */ + unsigned int cmcnt_delay = DIV_ROUND_UP(3 * ch->cmt->reg_delay, 2); + u32 reg; + + if (ch->cmt->info->model > SH_CMT_16BIT) { + int ret = read_poll_timeout_atomic(sh_cmt_read_cmcsr, reg, + !(reg & SH_CMT32_CMCSR_WRFLG), + 1, cmcnt_delay, false, ch); + if (ret < 0) + return ret; + } + ch->cmt->info->write_count(ch->ioctrl, CMCNT, value); + udelay(cmcnt_delay); + return 0; } static inline void sh_cmt_write_cmcor(struct sh_cmt_channel *ch, u32 value) { - ch->cmt->info->write_count(ch->ioctrl, CMCOR, value); + u32 old_value = ch->cmt->info->read_count(ch->ioctrl, CMCOR); + + if (value != old_value) { + ch->cmt->info->write_count(ch->ioctrl, CMCOR, value); + udelay(ch->cmt->reg_delay); + } } static u32 sh_cmt_get_counter(struct sh_cmt_channel *ch, u32 *has_wrapped) @@ -319,7 +352,7 @@ static void sh_cmt_start_stop_ch(struct sh_cmt_channel *ch, int start) static int sh_cmt_enable(struct sh_cmt_channel *ch) { - int k, ret; + int ret; dev_pm_syscore_device(&ch->cmt->pdev->dev, true); @@ -347,26 +380,9 @@ static int sh_cmt_enable(struct sh_cmt_channel *ch) } sh_cmt_write_cmcor(ch, 0xffffffff); - sh_cmt_write_cmcnt(ch, 0); + ret = sh_cmt_write_cmcnt(ch, 0); - /* - * According to the sh73a0 user's manual, as CMCNT can be operated - * only by the RCLK (Pseudo 32 kHz), there's one restriction on - * modifying CMCNT register; two RCLK cycles are necessary before - * this register is either read or any modification of the value - * it holds is reflected in the LSI's actual operation. - * - * While at it, we're supposed to clear out the CMCNT as of this - * moment, so make sure it's processed properly here. This will - * take RCLKx2 at maximum. - */ - for (k = 0; k < 100; k++) { - if (!sh_cmt_read_cmcnt(ch)) - break; - udelay(1); - } - - if (sh_cmt_read_cmcnt(ch)) { + if (ret || sh_cmt_read_cmcnt(ch)) { dev_err(&ch->cmt->pdev->dev, "ch%u: cannot clear CMCNT\n", ch->index); ret = -ETIMEDOUT; @@ -995,8 +1011,8 @@ MODULE_DEVICE_TABLE(of, sh_cmt_of_table); static int sh_cmt_setup(struct sh_cmt_device *cmt, struct platform_device *pdev) { - unsigned int mask; - unsigned int i; + unsigned int mask, i; + unsigned long rate; int ret; cmt->pdev = pdev; @@ -1032,10 +1048,16 @@ static int sh_cmt_setup(struct sh_cmt_device *cmt, struct platform_device *pdev) if (ret < 0) goto err_clk_unprepare; - if (cmt->info->width == 16) - cmt->rate = clk_get_rate(cmt->clk) / 512; - else - cmt->rate = clk_get_rate(cmt->clk) / 8; + rate = clk_get_rate(cmt->clk); + if (!rate) { + ret = -EINVAL; + goto err_clk_disable; + } + + /* We shall wait 2 input clks after register writes */ + if (cmt->info->model >= SH_CMT_48BIT) + cmt->reg_delay = DIV_ROUND_UP(2UL * USEC_PER_SEC, rate); + cmt->rate = rate / (cmt->info->width == 16 ? 512 : 8); /* Map the memory resource(s). */ ret = sh_cmt_map_memory(cmt); diff --git a/drivers/clocksource/timer-npcm7xx.c b/drivers/clocksource/timer-npcm7xx.c index a00520cbb660..9af30af5f989 100644 --- a/drivers/clocksource/timer-npcm7xx.c +++ b/drivers/clocksource/timer-npcm7xx.c @@ -188,6 +188,7 @@ static void __init npcm7xx_clocksource_init(void) static int __init npcm7xx_timer_init(struct device_node *np) { + struct clk *clk; int ret; ret = timer_of_init(np, &npcm7xx_to); @@ -199,6 +200,15 @@ static int __init npcm7xx_timer_init(struct device_node *np) npcm7xx_to.of_clk.rate = npcm7xx_to.of_clk.rate / (NPCM7XX_Tx_MIN_PRESCALE + 1); + /* Enable the clock for timer1, if it exists */ + clk = of_clk_get(np, 1); + if (clk) { + if (!IS_ERR(clk)) + clk_prepare_enable(clk); + else + pr_warn("%pOF: Failed to get clock for timer1: %pe", np, clk); + } + npcm7xx_clocksource_init(); npcm7xx_clockevents_init(); diff --git a/drivers/clocksource/timer-sp804.c b/drivers/clocksource/timer-sp804.c index e6a87f4af2b5..cd1916c05325 100644 --- a/drivers/clocksource/timer-sp804.c +++ b/drivers/clocksource/timer-sp804.c @@ -155,14 +155,14 @@ static irqreturn_t sp804_timer_interrupt(int irq, void *dev_id) return IRQ_HANDLED; } -static inline void timer_shutdown(struct clock_event_device *evt) +static inline void evt_timer_shutdown(struct clock_event_device *evt) { writel(0, common_clkevt->ctrl); } static int sp804_shutdown(struct clock_event_device *evt) { - timer_shutdown(evt); + evt_timer_shutdown(evt); return 0; } @@ -171,7 +171,7 @@ static int sp804_set_periodic(struct clock_event_device *evt) unsigned long ctrl = TIMER_CTRL_32BIT | TIMER_CTRL_IE | TIMER_CTRL_PERIODIC | TIMER_CTRL_ENABLE; - timer_shutdown(evt); + evt_timer_shutdown(evt); writel(common_clkevt->reload, common_clkevt->load); writel(ctrl, common_clkevt->ctrl); return 0; diff --git a/drivers/clocksource/timer-ti-dm-systimer.c b/drivers/clocksource/timer-ti-dm-systimer.c index 2737407ff069..632523c1232f 100644 --- a/drivers/clocksource/timer-ti-dm-systimer.c +++ b/drivers/clocksource/timer-ti-dm-systimer.c @@ -345,8 +345,10 @@ static int __init dmtimer_systimer_init_clock(struct dmtimer_systimer *t, return error; r = clk_get_rate(clock); - if (!r) + if (!r) { + clk_disable_unprepare(clock); return -ENODEV; + } if (is_ick) t->ick = clock; diff --git a/drivers/clocksource/timer-ti-dm.c b/drivers/clocksource/timer-ti-dm.c index cad29ded3a48..b24b903a8822 100644 --- a/drivers/clocksource/timer-ti-dm.c +++ b/drivers/clocksource/timer-ti-dm.c @@ -633,6 +633,8 @@ static struct omap_dm_timer *omap_dm_timer_request_by_node(struct device_node *n static int omap_dm_timer_free(struct omap_dm_timer *cookie) { struct dmtimer *timer; + struct device *dev; + int rc; timer = to_dmtimer(cookie); if (unlikely(!timer)) @@ -640,10 +642,21 @@ static int omap_dm_timer_free(struct omap_dm_timer *cookie) WARN_ON(!timer->reserved); timer->reserved = 0; + + dev = &timer->pdev->dev; + rc = pm_runtime_resume_and_get(dev); + if (rc) + return rc; + + /* Clear timer configuration */ + dmtimer_write(timer, OMAP_TIMER_CTRL_REG, 0); + + pm_runtime_put_sync(dev); + return 0; } -int omap_dm_timer_get_irq(struct omap_dm_timer *cookie) +static int omap_dm_timer_get_irq(struct omap_dm_timer *cookie) { struct dmtimer *timer = to_dmtimer(cookie); if (timer) @@ -1135,6 +1148,10 @@ static int omap_dm_timer_probe(struct platform_device *pdev) goto err_disable; } __omap_dm_timer_init_regs(timer); + + /* Clear timer configuration */ + dmtimer_write(timer, OMAP_TIMER_CTRL_REG, 0); + pm_runtime_put(dev); } @@ -1258,7 +1275,7 @@ static struct platform_driver omap_dm_timer_driver = { .remove = omap_dm_timer_remove, .driver = { .name = "omap_timer", - .of_match_table = of_match_ptr(omap_timer_match), + .of_match_table = omap_timer_match, .pm = &omap_dm_timer_pm_ops, }, }; diff --git a/drivers/staging/wlan-ng/hfa384x_usb.c b/drivers/staging/wlan-ng/hfa384x_usb.c index 02fdef7a16c8..c7cd54171d99 100644 --- a/drivers/staging/wlan-ng/hfa384x_usb.c +++ b/drivers/staging/wlan-ng/hfa384x_usb.c @@ -1116,8 +1116,8 @@ cleanup: if (ctlx == get_active_ctlx(hw)) { spin_unlock_irqrestore(&hw->ctlxq.lock, flags); - del_singleshot_timer_sync(&hw->reqtimer); - del_singleshot_timer_sync(&hw->resptimer); + del_timer_sync(&hw->reqtimer); + del_timer_sync(&hw->resptimer); hw->req_timer_done = 1; hw->resp_timer_done = 1; usb_kill_urb(&hw->ctlx_urb); diff --git a/drivers/staging/wlan-ng/prism2usb.c b/drivers/staging/wlan-ng/prism2usb.c index e13da7fadfff..c13f1699e5a2 100644 --- a/drivers/staging/wlan-ng/prism2usb.c +++ b/drivers/staging/wlan-ng/prism2usb.c @@ -170,9 +170,9 @@ static void prism2sta_disconnect_usb(struct usb_interface *interface) */ prism2sta_ifstate(wlandev, P80211ENUM_ifstate_disable); - del_singleshot_timer_sync(&hw->throttle); - del_singleshot_timer_sync(&hw->reqtimer); - del_singleshot_timer_sync(&hw->resptimer); + del_timer_sync(&hw->throttle); + del_timer_sync(&hw->reqtimer); + del_timer_sync(&hw->resptimer); /* Unlink all the URBs. This "removes the wheels" * from the entire CTLX handling mechanism. diff --git a/include/clocksource/timer-ti-dm.h b/include/clocksource/timer-ti-dm.h index 77eceeae708c..dcc1712f75e7 100644 --- a/include/clocksource/timer-ti-dm.h +++ b/include/clocksource/timer-ti-dm.h @@ -62,8 +62,6 @@ struct omap_dm_timer { }; -int omap_dm_timer_get_irq(struct omap_dm_timer *timer); - u32 omap_dm_timer_modify_idlect_mask(u32 inputmask); /* diff --git a/include/linux/compat.h b/include/linux/compat.h index 594357881b0b..44b1736c95b5 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -126,11 +126,9 @@ struct compat_tms { #define _COMPAT_NSIG_WORDS (_COMPAT_NSIG / _COMPAT_NSIG_BPW) -#ifndef compat_sigset_t typedef struct { compat_sigset_word sig[_COMPAT_NSIG_WORDS]; } compat_sigset_t; -#endif int set_compat_user_sigmask(const compat_sigset_t __user *umask, size_t sigsetsize); diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index a34b0f9a9972..33a0ee3bcb2e 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -264,6 +264,7 @@ static inline int is_syscall_trace_event(struct trace_event_call *tp_event) #define SC_VAL64(type, name) ((type) name##_hi << 32 | name##_lo) #ifdef CONFIG_COMPAT +#define SYSCALL32_DEFINE0 COMPAT_SYSCALL_DEFINE0 #define SYSCALL32_DEFINE1 COMPAT_SYSCALL_DEFINE1 #define SYSCALL32_DEFINE2 COMPAT_SYSCALL_DEFINE2 #define SYSCALL32_DEFINE3 COMPAT_SYSCALL_DEFINE3 @@ -271,6 +272,7 @@ static inline int is_syscall_trace_event(struct trace_event_call *tp_event) #define SYSCALL32_DEFINE5 COMPAT_SYSCALL_DEFINE5 #define SYSCALL32_DEFINE6 COMPAT_SYSCALL_DEFINE6 #else +#define SYSCALL32_DEFINE0 SYSCALL_DEFINE0 #define SYSCALL32_DEFINE1 SYSCALL_DEFINE1 #define SYSCALL32_DEFINE2 SYSCALL_DEFINE2 #define SYSCALL32_DEFINE3 SYSCALL_DEFINE3 diff --git a/include/linux/time_namespace.h b/include/linux/time_namespace.h index 3146f1c056c9..bb9d3f5542f8 100644 --- a/include/linux/time_namespace.h +++ b/include/linux/time_namespace.h @@ -45,6 +45,7 @@ struct time_namespace *copy_time_ns(unsigned long flags, void free_time_ns(struct time_namespace *ns); void timens_on_fork(struct nsproxy *nsproxy, struct task_struct *tsk); struct vdso_data *arch_get_vdso_data(void *vvar_page); +struct page *find_timens_vvar_page(struct vm_area_struct *vma); static inline void put_time_ns(struct time_namespace *ns) { @@ -141,6 +142,11 @@ static inline void timens_on_fork(struct nsproxy *nsproxy, return; } +static inline struct page *find_timens_vvar_page(struct vm_area_struct *vma) +{ + return NULL; +} + static inline void timens_add_monotonic(struct timespec64 *ts) { } static inline void timens_add_boottime(struct timespec64 *ts) { } diff --git a/include/linux/timer.h b/include/linux/timer.h index 648f00105f58..9162f275819a 100644 --- a/include/linux/timer.h +++ b/include/linux/timer.h @@ -169,7 +169,6 @@ static inline int timer_pending(const struct timer_list * timer) } extern void add_timer_on(struct timer_list *timer, int cpu); -extern int del_timer(struct timer_list * timer); extern int mod_timer(struct timer_list *timer, unsigned long expires); extern int mod_timer_pending(struct timer_list *timer, unsigned long expires); extern int timer_reduce(struct timer_list *timer, unsigned long expires); @@ -183,14 +182,36 @@ extern int timer_reduce(struct timer_list *timer, unsigned long expires); extern void add_timer(struct timer_list *timer); extern int try_to_del_timer_sync(struct timer_list *timer); +extern int timer_delete_sync(struct timer_list *timer); +extern int timer_delete(struct timer_list *timer); +extern int timer_shutdown_sync(struct timer_list *timer); +extern int timer_shutdown(struct timer_list *timer); -#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT) - extern int del_timer_sync(struct timer_list *timer); -#else -# define del_timer_sync(t) del_timer(t) -#endif +/** + * del_timer_sync - Delete a pending timer and wait for a running callback + * @timer: The timer to be deleted + * + * See timer_delete_sync() for detailed explanation. + * + * Do not use in new code. Use timer_delete_sync() instead. + */ +static inline int del_timer_sync(struct timer_list *timer) +{ + return timer_delete_sync(timer); +} -#define del_singleshot_timer_sync(t) del_timer_sync(t) +/** + * del_timer - Delete a pending timer + * @timer: The timer to be deleted + * + * See timer_delete() for detailed explanation. + * + * Do not use in new code. Use timer_delete() instead. + */ +static inline int del_timer(struct timer_list *timer) +{ + return timer_delete(timer); +} extern void init_timers(void); struct hrtimer; diff --git a/include/linux/timerqueue.h b/include/linux/timerqueue.h index 93884086f392..adc80e29168e 100644 --- a/include/linux/timerqueue.h +++ b/include/linux/timerqueue.h @@ -35,7 +35,7 @@ struct timerqueue_node *timerqueue_getnext(struct timerqueue_head *head) { struct rb_node *leftmost = rb_first_cached(&head->rb_root); - return rb_entry(leftmost, struct timerqueue_node, node); + return rb_entry_safe(leftmost, struct timerqueue_node, node); } static inline void timerqueue_init(struct timerqueue_node *node) diff --git a/kernel/cpu.c b/kernel/cpu.c index bbad5e375d3b..6c0a92ca6bb5 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -663,21 +663,51 @@ static bool cpuhp_next_state(bool bringup, return true; } -static int cpuhp_invoke_callback_range(bool bringup, - unsigned int cpu, - struct cpuhp_cpu_state *st, - enum cpuhp_state target) +static int __cpuhp_invoke_callback_range(bool bringup, + unsigned int cpu, + struct cpuhp_cpu_state *st, + enum cpuhp_state target, + bool nofail) { enum cpuhp_state state; - int err = 0; + int ret = 0; while (cpuhp_next_state(bringup, &state, st, target)) { + int err; + err = cpuhp_invoke_callback(cpu, state, bringup, NULL, NULL); - if (err) + if (!err) + continue; + + if (nofail) { + pr_warn("CPU %u %s state %s (%d) failed (%d)\n", + cpu, bringup ? "UP" : "DOWN", + cpuhp_get_step(st->state)->name, + st->state, err); + ret = -1; + } else { + ret = err; break; + } } - return err; + return ret; +} + +static inline int cpuhp_invoke_callback_range(bool bringup, + unsigned int cpu, + struct cpuhp_cpu_state *st, + enum cpuhp_state target) +{ + return __cpuhp_invoke_callback_range(bringup, cpu, st, target, false); +} + +static inline void cpuhp_invoke_callback_range_nofail(bool bringup, + unsigned int cpu, + struct cpuhp_cpu_state *st, + enum cpuhp_state target) +{ + __cpuhp_invoke_callback_range(bringup, cpu, st, target, true); } static inline bool can_rollback_cpu(struct cpuhp_cpu_state *st) @@ -999,7 +1029,6 @@ static int take_cpu_down(void *_param) struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state); enum cpuhp_state target = max((int)st->target, CPUHP_AP_OFFLINE); int err, cpu = smp_processor_id(); - int ret; /* Ensure this CPU doesn't handle any more interrupts. */ err = __cpu_disable(); @@ -1012,13 +1041,10 @@ static int take_cpu_down(void *_param) */ WARN_ON(st->state != (CPUHP_TEARDOWN_CPU - 1)); - /* Invoke the former CPU_DYING callbacks */ - ret = cpuhp_invoke_callback_range(false, cpu, st, target); - /* - * DYING must not fail! + * Invoke the former CPU_DYING callbacks. DYING must not fail! */ - WARN_ON_ONCE(ret); + cpuhp_invoke_callback_range_nofail(false, cpu, st, target); /* Give up timekeeping duties */ tick_handover_do_timer(); @@ -1296,16 +1322,14 @@ void notify_cpu_starting(unsigned int cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); enum cpuhp_state target = min((int)st->target, CPUHP_AP_ONLINE); - int ret; rcu_cpu_starting(cpu); /* Enables RCU usage on this CPU. */ cpumask_set_cpu(cpu, &cpus_booted_once_mask); - ret = cpuhp_invoke_callback_range(true, cpu, st, target); /* * STARTING must not fail! */ - WARN_ON_ONCE(ret); + cpuhp_invoke_callback_range_nofail(true, cpu, st, target); } /* @@ -2326,8 +2350,10 @@ static ssize_t target_store(struct device *dev, struct device_attribute *attr, if (st->state < target) ret = cpu_up(dev->id, target); - else + else if (st->state > target) ret = cpu_down(dev->id, target); + else if (WARN_ON(st->target != target)) + st->target = target; out: unlock_device_hotplug(); return ret ? ret : count; @@ -2688,6 +2714,7 @@ void __init boot_cpu_hotplug_init(void) cpumask_set_cpu(smp_processor_id(), &cpus_booted_once_mask); #endif this_cpu_write(cpuhp_state.state, CPUHP_ONLINE); + this_cpu_write(cpuhp_state.target, CPUHP_ONLINE); } /* diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c index 5d85014d59b5..960143b183cd 100644 --- a/kernel/time/clockevents.c +++ b/kernel/time/clockevents.c @@ -76,7 +76,7 @@ static u64 cev_delta2ns(unsigned long latch, struct clock_event_device *evt, } /** - * clockevents_delta2ns - Convert a latch value (device ticks) to nanoseconds + * clockevent_delta2ns - Convert a latch value (device ticks) to nanoseconds * @latch: value to convert * @evt: pointer to clock event device descriptor * diff --git a/kernel/time/namespace.c b/kernel/time/namespace.c index aec832801c26..0775b9ec952a 100644 --- a/kernel/time/namespace.c +++ b/kernel/time/namespace.c @@ -192,6 +192,24 @@ static void timens_setup_vdso_data(struct vdso_data *vdata, offset[CLOCK_BOOTTIME_ALARM] = boottime; } +struct page *find_timens_vvar_page(struct vm_area_struct *vma) +{ + if (likely(vma->vm_mm == current->mm)) + return current->nsproxy->time_ns->vvar_page; + + /* + * VM_PFNMAP | VM_IO protect .fault() handler from being called + * through interfaces like /proc/$pid/mem or + * process_vm_{readv,writev}() as long as there's no .access() + * in special_mapping_vmops(). + * For more details check_vma_flags() and __access_remote_vm() + */ + + WARN(1, "vvar_page accessed remotely"); + + return NULL; +} + /* * Protects possibly multiple offsets writers racing each other * and tasks entering the namespace. diff --git a/kernel/time/timer.c b/kernel/time/timer.c index 717fcb9fb14a..63a8ce7177dd 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -1017,7 +1017,7 @@ __mod_timer(struct timer_list *timer, unsigned long expires, unsigned int option unsigned int idx = UINT_MAX; int ret = 0; - BUG_ON(!timer->function); + debug_assert_init(timer); /* * This is a common optimization triggered by the networking code - if @@ -1044,6 +1044,14 @@ __mod_timer(struct timer_list *timer, unsigned long expires, unsigned int option * dequeue/enqueue dance. */ base = lock_timer_base(timer, &flags); + /* + * Has @timer been shutdown? This needs to be evaluated + * while holding base lock to prevent a race against the + * shutdown code. + */ + if (!timer->function) + goto out_unlock; + forward_timer_base(base); if (timer_pending(timer) && (options & MOD_TIMER_REDUCE) && @@ -1070,6 +1078,14 @@ __mod_timer(struct timer_list *timer, unsigned long expires, unsigned int option } } else { base = lock_timer_base(timer, &flags); + /* + * Has @timer been shutdown? This needs to be evaluated + * while holding base lock to prevent a race against the + * shutdown code. + */ + if (!timer->function) + goto out_unlock; + forward_timer_base(base); } @@ -1083,7 +1099,7 @@ __mod_timer(struct timer_list *timer, unsigned long expires, unsigned int option /* * We are trying to schedule the timer on the new base. * However we can't change timer's base while it is running, - * otherwise del_timer_sync() can't detect that the timer's + * otherwise timer_delete_sync() can't detect that the timer's * handler yet has not finished. This also guarantees that the * timer is serialized wrt itself. */ @@ -1121,14 +1137,20 @@ out_unlock: } /** - * mod_timer_pending - modify a pending timer's timeout - * @timer: the pending timer to be modified - * @expires: new timeout in jiffies + * mod_timer_pending - Modify a pending timer's timeout + * @timer: The pending timer to be modified + * @expires: New absolute timeout in jiffies * - * mod_timer_pending() is the same for pending timers as mod_timer(), - * but will not re-activate and modify already deleted timers. + * mod_timer_pending() is the same for pending timers as mod_timer(), but + * will not activate inactive timers. * - * It is useful for unserialized use of timers. + * If @timer->function == NULL then the start operation is silently + * discarded. + * + * Return: + * * %0 - The timer was inactive and not modified or was in + * shutdown state and the operation was discarded + * * %1 - The timer was active and requeued to expire at @expires */ int mod_timer_pending(struct timer_list *timer, unsigned long expires) { @@ -1137,24 +1159,31 @@ int mod_timer_pending(struct timer_list *timer, unsigned long expires) EXPORT_SYMBOL(mod_timer_pending); /** - * mod_timer - modify a timer's timeout - * @timer: the timer to be modified - * @expires: new timeout in jiffies - * - * mod_timer() is a more efficient way to update the expire field of an - * active timer (if the timer is inactive it will be activated) + * mod_timer - Modify a timer's timeout + * @timer: The timer to be modified + * @expires: New absolute timeout in jiffies * * mod_timer(timer, expires) is equivalent to: * * del_timer(timer); timer->expires = expires; add_timer(timer); * + * mod_timer() is more efficient than the above open coded sequence. In + * case that the timer is inactive, the del_timer() part is a NOP. The + * timer is in any case activated with the new expiry time @expires. + * * Note that if there are multiple unserialized concurrent users of the * same timer, then mod_timer() is the only safe way to modify the timeout, * since add_timer() cannot modify an already running timer. * - * The function returns whether it has modified a pending timer or not. - * (ie. mod_timer() of an inactive timer returns 0, mod_timer() of an - * active timer returns 1.) + * If @timer->function == NULL then the start operation is silently + * discarded. In this case the return value is 0 and meaningless. + * + * Return: + * * %0 - The timer was inactive and started or was in shutdown + * state and the operation was discarded + * * %1 - The timer was active and requeued to expire at @expires or + * the timer was active and not modified because @expires did + * not change the effective expiry time */ int mod_timer(struct timer_list *timer, unsigned long expires) { @@ -1165,11 +1194,22 @@ EXPORT_SYMBOL(mod_timer); /** * timer_reduce - Modify a timer's timeout if it would reduce the timeout * @timer: The timer to be modified - * @expires: New timeout in jiffies + * @expires: New absolute timeout in jiffies * * timer_reduce() is very similar to mod_timer(), except that it will only - * modify a running timer if that would reduce the expiration time (it will - * start a timer that isn't running). + * modify an enqueued timer if that would reduce the expiration time. If + * @timer is not enqueued it starts the timer. + * + * If @timer->function == NULL then the start operation is silently + * discarded. + * + * Return: + * * %0 - The timer was inactive and started or was in shutdown + * state and the operation was discarded + * * %1 - The timer was active and requeued to expire at @expires or + * the timer was active and not modified because @expires + * did not change the effective expiry time such that the + * timer would expire earlier than already scheduled */ int timer_reduce(struct timer_list *timer, unsigned long expires) { @@ -1178,39 +1218,51 @@ int timer_reduce(struct timer_list *timer, unsigned long expires) EXPORT_SYMBOL(timer_reduce); /** - * add_timer - start a timer - * @timer: the timer to be added + * add_timer - Start a timer + * @timer: The timer to be started * - * The kernel will do a ->function(@timer) callback from the - * timer interrupt at the ->expires point in the future. The - * current time is 'jiffies'. + * Start @timer to expire at @timer->expires in the future. @timer->expires + * is the absolute expiry time measured in 'jiffies'. When the timer expires + * timer->function(timer) will be invoked from soft interrupt context. * - * The timer's ->expires, ->function fields must be set prior calling this - * function. + * The @timer->expires and @timer->function fields must be set prior + * to calling this function. * - * Timers with an ->expires field in the past will be executed in the next - * timer tick. + * If @timer->function == NULL then the start operation is silently + * discarded. + * + * If @timer->expires is already in the past @timer will be queued to + * expire at the next timer tick. + * + * This can only operate on an inactive timer. Attempts to invoke this on + * an active timer are rejected with a warning. */ void add_timer(struct timer_list *timer) { - BUG_ON(timer_pending(timer)); + if (WARN_ON_ONCE(timer_pending(timer))) + return; __mod_timer(timer, timer->expires, MOD_TIMER_NOTPENDING); } EXPORT_SYMBOL(add_timer); /** - * add_timer_on - start a timer on a particular CPU - * @timer: the timer to be added - * @cpu: the CPU to start it on + * add_timer_on - Start a timer on a particular CPU + * @timer: The timer to be started + * @cpu: The CPU to start it on * - * This is not very scalable on SMP. Double adds are not possible. + * Same as add_timer() except that it starts the timer on the given CPU. + * + * See add_timer() for further details. */ void add_timer_on(struct timer_list *timer, int cpu) { struct timer_base *new_base, *base; unsigned long flags; - BUG_ON(timer_pending(timer) || !timer->function); + debug_assert_init(timer); + + if (WARN_ON_ONCE(timer_pending(timer))) + return; new_base = get_timer_cpu_base(timer->flags, cpu); @@ -1220,6 +1272,13 @@ void add_timer_on(struct timer_list *timer, int cpu) * wrong base locked. See lock_timer_base(). */ base = lock_timer_base(timer, &flags); + /* + * Has @timer been shutdown? This needs to be evaluated while + * holding base lock to prevent a race against the shutdown code. + */ + if (!timer->function) + goto out_unlock; + if (base != new_base) { timer->flags |= TIMER_MIGRATING; @@ -1233,22 +1292,27 @@ void add_timer_on(struct timer_list *timer, int cpu) debug_timer_activate(timer); internal_add_timer(base, timer); +out_unlock: raw_spin_unlock_irqrestore(&base->lock, flags); } EXPORT_SYMBOL_GPL(add_timer_on); /** - * del_timer - deactivate a timer. - * @timer: the timer to be deactivated + * __timer_delete - Internal function: Deactivate a timer + * @timer: The timer to be deactivated + * @shutdown: If true, this indicates that the timer is about to be + * shutdown permanently. * - * del_timer() deactivates a timer - this works on both active and inactive - * timers. + * If @shutdown is true then @timer->function is set to NULL under the + * timer base lock which prevents further rearming of the time. In that + * case any attempt to rearm @timer after this function returns will be + * silently ignored. * - * The function returns whether it has deactivated a pending timer or not. - * (ie. del_timer() of an inactive timer returns 0, del_timer() of an - * active timer returns 1.) + * Return: + * * %0 - The timer was not pending + * * %1 - The timer was pending and deactivated */ -int del_timer(struct timer_list *timer) +static int __timer_delete(struct timer_list *timer, bool shutdown) { struct timer_base *base; unsigned long flags; @@ -1256,24 +1320,90 @@ int del_timer(struct timer_list *timer) debug_assert_init(timer); - if (timer_pending(timer)) { + /* + * If @shutdown is set then the lock has to be taken whether the + * timer is pending or not to protect against a concurrent rearm + * which might hit between the lockless pending check and the lock + * aquisition. By taking the lock it is ensured that such a newly + * enqueued timer is dequeued and cannot end up with + * timer->function == NULL in the expiry code. + * + * If timer->function is currently executed, then this makes sure + * that the callback cannot requeue the timer. + */ + if (timer_pending(timer) || shutdown) { base = lock_timer_base(timer, &flags); ret = detach_if_pending(timer, base, true); + if (shutdown) + timer->function = NULL; raw_spin_unlock_irqrestore(&base->lock, flags); } return ret; } -EXPORT_SYMBOL(del_timer); /** - * try_to_del_timer_sync - Try to deactivate a timer - * @timer: timer to delete + * timer_delete - Deactivate a timer + * @timer: The timer to be deactivated * - * This function tries to deactivate a timer. Upon successful (ret >= 0) - * exit the timer is not queued and the handler is not running on any CPU. + * The function only deactivates a pending timer, but contrary to + * timer_delete_sync() it does not take into account whether the timer's + * callback function is concurrently executed on a different CPU or not. + * It neither prevents rearming of the timer. If @timer can be rearmed + * concurrently then the return value of this function is meaningless. + * + * Return: + * * %0 - The timer was not pending + * * %1 - The timer was pending and deactivated */ -int try_to_del_timer_sync(struct timer_list *timer) +int timer_delete(struct timer_list *timer) +{ + return __timer_delete(timer, false); +} +EXPORT_SYMBOL(timer_delete); + +/** + * timer_shutdown - Deactivate a timer and prevent rearming + * @timer: The timer to be deactivated + * + * The function does not wait for an eventually running timer callback on a + * different CPU but it prevents rearming of the timer. Any attempt to arm + * @timer after this function returns will be silently ignored. + * + * This function is useful for teardown code and should only be used when + * timer_shutdown_sync() cannot be invoked due to locking or context constraints. + * + * Return: + * * %0 - The timer was not pending + * * %1 - The timer was pending + */ +int timer_shutdown(struct timer_list *timer) +{ + return __timer_delete(timer, true); +} +EXPORT_SYMBOL_GPL(timer_shutdown); + +/** + * __try_to_del_timer_sync - Internal function: Try to deactivate a timer + * @timer: Timer to deactivate + * @shutdown: If true, this indicates that the timer is about to be + * shutdown permanently. + * + * If @shutdown is true then @timer->function is set to NULL under the + * timer base lock which prevents further rearming of the timer. Any + * attempt to rearm @timer after this function returns will be silently + * ignored. + * + * This function cannot guarantee that the timer cannot be rearmed + * right after dropping the base lock if @shutdown is false. That + * needs to be prevented by the calling code if necessary. + * + * Return: + * * %0 - The timer was not pending + * * %1 - The timer was pending and deactivated + * * %-1 - The timer callback function is running on a different CPU + */ +static int __try_to_del_timer_sync(struct timer_list *timer, bool shutdown) { struct timer_base *base; unsigned long flags; @@ -1285,11 +1415,34 @@ int try_to_del_timer_sync(struct timer_list *timer) if (base->running_timer != timer) ret = detach_if_pending(timer, base, true); + if (shutdown) + timer->function = NULL; raw_spin_unlock_irqrestore(&base->lock, flags); return ret; } + +/** + * try_to_del_timer_sync - Try to deactivate a timer + * @timer: Timer to deactivate + * + * This function tries to deactivate a timer. On success the timer is not + * queued and the timer callback function is not running on any CPU. + * + * This function does not guarantee that the timer cannot be rearmed right + * after dropping the base lock. That needs to be prevented by the calling + * code if necessary. + * + * Return: + * * %0 - The timer was not pending + * * %1 - The timer was pending and deactivated + * * %-1 - The timer callback function is running on a different CPU + */ +int try_to_del_timer_sync(struct timer_list *timer) +{ + return __try_to_del_timer_sync(timer, false); +} EXPORT_SYMBOL(try_to_del_timer_sync); #ifdef CONFIG_PREEMPT_RT @@ -1365,44 +1518,29 @@ static inline void timer_sync_wait_running(struct timer_base *base) { } static inline void del_timer_wait_running(struct timer_list *timer) { } #endif -#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT) /** - * del_timer_sync - deactivate a timer and wait for the handler to finish. - * @timer: the timer to be deactivated + * __timer_delete_sync - Internal function: Deactivate a timer and wait + * for the handler to finish. + * @timer: The timer to be deactivated + * @shutdown: If true, @timer->function will be set to NULL under the + * timer base lock which prevents rearming of @timer * - * This function only differs from del_timer() on SMP: besides deactivating - * the timer it also makes sure the handler has finished executing on other - * CPUs. + * If @shutdown is not set the timer can be rearmed later. If the timer can + * be rearmed concurrently, i.e. after dropping the base lock then the + * return value is meaningless. * - * Synchronization rules: Callers must prevent restarting of the timer, - * otherwise this function is meaningless. It must not be called from - * interrupt contexts unless the timer is an irqsafe one. The caller must - * not hold locks which would prevent completion of the timer's - * handler. The timer's handler must not call add_timer_on(). Upon exit the - * timer is not queued and the handler is not running on any CPU. + * If @shutdown is set then @timer->function is set to NULL under timer + * base lock which prevents rearming of the timer. Any attempt to rearm + * a shutdown timer is silently ignored. * - * Note: For !irqsafe timers, you must not hold locks that are held in - * interrupt context while calling this function. Even if the lock has - * nothing to do with the timer in question. Here's why:: + * If the timer should be reused after shutdown it has to be initialized + * again. * - * CPU0 CPU1 - * ---- ---- - * - * call_timer_fn(); - * base->running_timer = mytimer; - * spin_lock_irq(somelock); - * - * spin_lock(somelock); - * del_timer_sync(mytimer); - * while (base->running_timer == mytimer); - * - * Now del_timer_sync() will never return and never release somelock. - * The interrupt on the other CPU is waiting to grab somelock but - * it has interrupted the softirq that CPU0 is waiting to finish. - * - * The function returns whether it has deactivated a pending timer or not. + * Return: + * * %0 - The timer was not pending + * * %1 - The timer was pending and deactivated */ -int del_timer_sync(struct timer_list *timer) +static int __timer_delete_sync(struct timer_list *timer, bool shutdown) { int ret; @@ -1422,7 +1560,7 @@ int del_timer_sync(struct timer_list *timer) * don't use it in hardirq context, because it * could lead to deadlock. */ - WARN_ON(in_irq() && !(timer->flags & TIMER_IRQSAFE)); + WARN_ON(in_hardirq() && !(timer->flags & TIMER_IRQSAFE)); /* * Must be able to sleep on PREEMPT_RT because of the slowpath in @@ -1432,7 +1570,7 @@ int del_timer_sync(struct timer_list *timer) lockdep_assert_preemption_enabled(); do { - ret = try_to_del_timer_sync(timer); + ret = __try_to_del_timer_sync(timer, shutdown); if (unlikely(ret < 0)) { del_timer_wait_running(timer); @@ -1442,8 +1580,96 @@ int del_timer_sync(struct timer_list *timer) return ret; } -EXPORT_SYMBOL(del_timer_sync); -#endif + +/** + * timer_delete_sync - Deactivate a timer and wait for the handler to finish. + * @timer: The timer to be deactivated + * + * Synchronization rules: Callers must prevent restarting of the timer, + * otherwise this function is meaningless. It must not be called from + * interrupt contexts unless the timer is an irqsafe one. The caller must + * not hold locks which would prevent completion of the timer's callback + * function. The timer's handler must not call add_timer_on(). Upon exit + * the timer is not queued and the handler is not running on any CPU. + * + * For !irqsafe timers, the caller must not hold locks that are held in + * interrupt context. Even if the lock has nothing to do with the timer in + * question. Here's why:: + * + * CPU0 CPU1 + * ---- ---- + * + * call_timer_fn(); + * base->running_timer = mytimer; + * spin_lock_irq(somelock); + * + * spin_lock(somelock); + * timer_delete_sync(mytimer); + * while (base->running_timer == mytimer); + * + * Now timer_delete_sync() will never return and never release somelock. + * The interrupt on the other CPU is waiting to grab somelock but it has + * interrupted the softirq that CPU0 is waiting to finish. + * + * This function cannot guarantee that the timer is not rearmed again by + * some concurrent or preempting code, right after it dropped the base + * lock. If there is the possibility of a concurrent rearm then the return + * value of the function is meaningless. + * + * If such a guarantee is needed, e.g. for teardown situations then use + * timer_shutdown_sync() instead. + * + * Return: + * * %0 - The timer was not pending + * * %1 - The timer was pending and deactivated + */ +int timer_delete_sync(struct timer_list *timer) +{ + return __timer_delete_sync(timer, false); +} +EXPORT_SYMBOL(timer_delete_sync); + +/** + * timer_shutdown_sync - Shutdown a timer and prevent rearming + * @timer: The timer to be shutdown + * + * When the function returns it is guaranteed that: + * - @timer is not queued + * - The callback function of @timer is not running + * - @timer cannot be enqueued again. Any attempt to rearm + * @timer is silently ignored. + * + * See timer_delete_sync() for synchronization rules. + * + * This function is useful for final teardown of an infrastructure where + * the timer is subject to a circular dependency problem. + * + * A common pattern for this is a timer and a workqueue where the timer can + * schedule work and work can arm the timer. On shutdown the workqueue must + * be destroyed and the timer must be prevented from rearming. Unless the + * code has conditionals like 'if (mything->in_shutdown)' to prevent that + * there is no way to get this correct with timer_delete_sync(). + * + * timer_shutdown_sync() is solving the problem. The correct ordering of + * calls in this case is: + * + * timer_shutdown_sync(&mything->timer); + * workqueue_destroy(&mything->workqueue); + * + * After this 'mything' can be safely freed. + * + * This obviously implies that the timer is not required to be functional + * for the rest of the shutdown operation. + * + * Return: + * * %0 - The timer was not pending + * * %1 - The timer was pending + */ +int timer_shutdown_sync(struct timer_list *timer) +{ + return __timer_delete_sync(timer, true); +} +EXPORT_SYMBOL_GPL(timer_shutdown_sync); static void call_timer_fn(struct timer_list *timer, void (*fn)(struct timer_list *), @@ -1465,8 +1691,8 @@ static void call_timer_fn(struct timer_list *timer, #endif /* * Couple the lock chain with the lock chain at - * del_timer_sync() by acquiring the lock_map around the fn() - * call here and in del_timer_sync(). + * timer_delete_sync() by acquiring the lock_map around the fn() + * call here and in timer_delete_sync(). */ lock_map_acquire(&lockdep_map); @@ -1509,6 +1735,12 @@ static void expire_timers(struct timer_base *base, struct hlist_head *head) fn = timer->function; + if (WARN_ON_ONCE(!fn)) { + /* Should never happen. Emphasis on should! */ + base->running_timer = NULL; + continue; + } + if (timer->flags & TIMER_IRQSAFE) { raw_spin_unlock(&base->lock); call_timer_fn(timer, fn, baseclk); @@ -1933,7 +2165,7 @@ signed long __sched schedule_timeout(signed long timeout) timer_setup_on_stack(&timer.timer, process_timeout, 0); __mod_timer(&timer.timer, expire, MOD_TIMER_NOTPENDING); schedule(); - del_singleshot_timer_sync(&timer.timer); + del_timer_sync(&timer.timer); /* Remove the timer from the object tracker */ destroy_timer_on_stack(&timer.timer); @@ -2017,8 +2249,6 @@ int timers_dead_cpu(unsigned int cpu) struct timer_base *new_base; int b, i; - BUG_ON(cpu_online(cpu)); - for (b = 0; b < NR_BASES; b++) { old_base = per_cpu_ptr(&timer_bases[b], cpu); new_base = get_cpu_ptr(&timer_bases[b]); @@ -2035,7 +2265,8 @@ int timers_dead_cpu(unsigned int cpu) */ forward_timer_base(new_base); - BUG_ON(old_base->running_timer); + WARN_ON_ONCE(old_base->running_timer); + old_base->running_timer = NULL; for (i = 0; i < WHEEL_SIZE; i++) migrate_timer_list(new_base, old_base->vectors + i); diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index 656cec208371..ab453ede54f0 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -1164,7 +1164,7 @@ xprt_request_enqueue_receive(struct rpc_task *task) spin_unlock(&xprt->queue_lock); /* Turn off autodisconnect */ - del_singleshot_timer_sync(&xprt->timer); + del_timer_sync(&xprt->timer); return 0; }