diff options
| author | Linux Build Service Account <lnxbuild@localhost> | 2018-03-07 09:16:31 -0800 |
|---|---|---|
| committer | Gerrit - the friendly Code Review server <code-review@localhost> | 2018-03-07 09:16:30 -0800 |
| commit | d30c02ed5bce2c101768121402000ee780fb8d71 (patch) | |
| tree | 7db60f7b333be05a3e667480ea15a0c06eacaa6a /arch | |
| parent | 40cb35870700b174f3e2db77c855920458a96c16 (diff) | |
| parent | 863577dd59f54becb161ecb1918169022bae6f36 (diff) | |
Merge "Merge android-4.4.116 (20ddb25) into msm-4.4"
Diffstat (limited to 'arch')
239 files changed, 6093 insertions, 1813 deletions
diff --git a/arch/Kconfig b/arch/Kconfig index ed2539c590bf..a29c6098fb98 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -536,6 +536,11 @@ config HAVE_ARCH_MMAP_RND_BITS - ARCH_MMAP_RND_BITS_MIN - ARCH_MMAP_RND_BITS_MAX +config HAVE_EXIT_THREAD + bool + help + An architecture implements exit_thread. + config ARCH_MMAP_RND_BITS_MIN int diff --git a/arch/alpha/kernel/pci_impl.h b/arch/alpha/kernel/pci_impl.h index 2b0ac429f5eb..412bb3c24f36 100644 --- a/arch/alpha/kernel/pci_impl.h +++ b/arch/alpha/kernel/pci_impl.h @@ -143,7 +143,8 @@ struct pci_iommu_arena }; #if defined(CONFIG_ALPHA_SRM) && \ - (defined(CONFIG_ALPHA_CIA) || defined(CONFIG_ALPHA_LCA)) + (defined(CONFIG_ALPHA_CIA) || defined(CONFIG_ALPHA_LCA) || \ + defined(CONFIG_ALPHA_AVANTI)) # define NEED_SRM_SAVE_RESTORE #else # undef NEED_SRM_SAVE_RESTORE diff --git a/arch/alpha/kernel/process.c b/arch/alpha/kernel/process.c index 84d13263ce46..60c17b9bf04d 100644 --- a/arch/alpha/kernel/process.c +++ b/arch/alpha/kernel/process.c @@ -210,14 +210,6 @@ start_thread(struct pt_regs * regs, unsigned long pc, unsigned long sp) } EXPORT_SYMBOL(start_thread); -/* - * Free current thread data structures etc.. - */ -void -exit_thread(void) -{ -} - void flush_thread(void) { @@ -273,12 +265,13 @@ copy_thread(unsigned long clone_flags, unsigned long usp, application calling fork. */ if (clone_flags & CLONE_SETTLS) childti->pcb.unique = regs->r20; + else + regs->r20 = 0; /* OSF/1 has some strange fork() semantics. */ childti->pcb.usp = usp ?: rdusp(); *childregs = *regs; childregs->r0 = 0; childregs->r19 = 0; childregs->r20 = 1; /* OSF/1 has some strange fork() semantics. */ - regs->r20 = 0; stack = ((struct switch_stack *) regs) - 1; *childstack = *stack; childstack->r26 = (unsigned long) ret_from_fork; diff --git a/arch/arc/kernel/process.c b/arch/arc/kernel/process.c index a3f750e76b68..b5db9e7fd649 100644 --- a/arch/arc/kernel/process.c +++ b/arch/arc/kernel/process.c @@ -183,13 +183,6 @@ void flush_thread(void) { } -/* - * Free any architecture-specific thread data structures, etc. - */ -void exit_thread(void) -{ -} - int dump_fpu(struct pt_regs *regs, elf_fpregset_t *fpu) { return 0; diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 22b546e0f845..162bd82dbf51 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -50,6 +50,7 @@ config ARM select HAVE_DMA_CONTIGUOUS if MMU select HAVE_DYNAMIC_FTRACE if (!XIP_KERNEL) && !CPU_ENDIAN_BE32 select HAVE_EFFICIENT_UNALIGNED_ACCESS if (CPU_V6 || CPU_V6K || CPU_V7) && MMU + select HAVE_EXIT_THREAD select HAVE_FTRACE_MCOUNT_RECORD if (!XIP_KERNEL) select HAVE_FUNCTION_GRAPH_TRACER if (!THUMB2_KERNEL) select HAVE_FUNCTION_TRACER if (!XIP_KERNEL) diff --git a/arch/arm/boot/compressed/string.c b/arch/arm/boot/compressed/string.c index 36e53ef9200f..689467448736 100644 --- a/arch/arm/boot/compressed/string.c +++ b/arch/arm/boot/compressed/string.c @@ -65,6 +65,15 @@ size_t strlen(const char *s) return sc - s; } +size_t strnlen(const char *s, size_t count) +{ + const char *sc; + + for (sc = s; count-- && *sc != '\0'; ++sc) + /* nothing */; + return sc - s; +} + int memcmp(const void *cs, const void *ct, size_t count) { const unsigned char *su1 = cs, *su2 = ct, *end = su1 + count; diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c index 0017b3edfea8..e06307ad1d1c 100644 --- a/arch/arm/kernel/process.c +++ b/arch/arm/kernel/process.c @@ -268,9 +268,9 @@ EXPORT_SYMBOL_GPL(thread_notify_head); /* * Free current thread data structures etc.. */ -void exit_thread(void) +void exit_thread(struct task_struct *tsk) { - thread_notify(THREAD_NOTIFY_EXIT, current_thread_info()); + thread_notify(THREAD_NOTIFY_EXIT, task_thread_info(tsk)); } void flush_thread(void) diff --git a/arch/arm/kvm/handle_exit.c b/arch/arm/kvm/handle_exit.c index f36b5b1acd1f..05b2f8294968 100644 --- a/arch/arm/kvm/handle_exit.c +++ b/arch/arm/kvm/handle_exit.c @@ -45,7 +45,7 @@ static int handle_hvc(struct kvm_vcpu *vcpu, struct kvm_run *run) ret = kvm_psci_call(vcpu); if (ret < 0) { - kvm_inject_undefined(vcpu); + vcpu_set_reg(vcpu, 0, ~0UL); return 1; } @@ -54,7 +54,16 @@ static int handle_hvc(struct kvm_vcpu *vcpu, struct kvm_run *run) static int handle_smc(struct kvm_vcpu *vcpu, struct kvm_run *run) { - kvm_inject_undefined(vcpu); + /* + * "If an SMC instruction executed at Non-secure EL1 is + * trapped to EL2 because HCR_EL2.TSC is 1, the exception is a + * Trap exception, not a Secure Monitor Call exception [...]" + * + * We need to advance the PC after the trap, as it would + * otherwise return to the same address... + */ + vcpu_set_reg(vcpu, 0, ~0UL); + kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu)); return 1; } diff --git a/arch/arm/vfp/vfpmodule.c b/arch/arm/vfp/vfpmodule.c index 2a61e4b04600..73085d3482ed 100644 --- a/arch/arm/vfp/vfpmodule.c +++ b/arch/arm/vfp/vfpmodule.c @@ -156,10 +156,6 @@ static void vfp_thread_copy(struct thread_info *thread) * - we could be preempted if tree preempt rcu is enabled, so * it is unsafe to use thread->cpu. * THREAD_NOTIFY_EXIT - * - the thread (v) will be running on the local CPU, so - * v === current_thread_info() - * - thread->cpu is the local CPU number at the time it is accessed, - * but may change at any time. * - we could be preempted if tree preempt rcu is enabled, so * it is unsafe to use thread->cpu. */ diff --git a/arch/arm64/kernel/image.h b/arch/arm64/kernel/image.h index f0be31f1dd45..86d444f9c2c1 100644 --- a/arch/arm64/kernel/image.h +++ b/arch/arm64/kernel/image.h @@ -100,6 +100,7 @@ __efistub_memcpy = KALLSYMS_HIDE(__pi_memcpy); __efistub_memmove = KALLSYMS_HIDE(__pi_memmove); __efistub_memset = KALLSYMS_HIDE(__pi_memset); __efistub_strlen = KALLSYMS_HIDE(__pi_strlen); +__efistub_strnlen = KALLSYMS_HIDE(__pi_strnlen); __efistub_strcmp = KALLSYMS_HIDE(__pi_strcmp); __efistub_strncmp = KALLSYMS_HIDE(__pi_strncmp); __efistub___flush_dcache_area = KALLSYMS_HIDE(__pi___flush_dcache_area); diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index 6df738c01f42..5dd9b572259f 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -274,13 +274,6 @@ void show_regs(struct pt_regs * regs) __show_regs(regs); } -/* - * Free current thread data structures etc.. - */ -void exit_thread(void) -{ -} - static void tls_thread_flush(void) { asm ("msr tpidr_el0, xzr"); diff --git a/arch/arm64/lib/strnlen.S b/arch/arm64/lib/strnlen.S index 2ca665711bf2..eae38da6e0bb 100644 --- a/arch/arm64/lib/strnlen.S +++ b/arch/arm64/lib/strnlen.S @@ -168,4 +168,4 @@ CPU_LE( lsr tmp2, tmp2, tmp4 ) /* Shift (tmp1 & 63). */ .Lhit_limit: mov len, limit ret -ENDPROC(strnlen) +ENDPIPROC(strnlen) diff --git a/arch/avr32/Kconfig b/arch/avr32/Kconfig index b6878eb64884..37d9c02be634 100644 --- a/arch/avr32/Kconfig +++ b/arch/avr32/Kconfig @@ -4,6 +4,7 @@ config AVR32 # that we usually don't need on AVR32. select EXPERT select HAVE_CLK + select HAVE_EXIT_THREAD select HAVE_OPROFILE select HAVE_KPROBES select VIRT_TO_BUS diff --git a/arch/avr32/kernel/process.c b/arch/avr32/kernel/process.c index 42a53e740a7e..68e5b9dac059 100644 --- a/arch/avr32/kernel/process.c +++ b/arch/avr32/kernel/process.c @@ -62,9 +62,9 @@ void machine_restart(char *cmd) /* * Free current thread data structures etc */ -void exit_thread(void) +void exit_thread(struct task_struct *tsk) { - ocd_disable(current); + ocd_disable(tsk); } void flush_thread(void) diff --git a/arch/blackfin/include/asm/processor.h b/arch/blackfin/include/asm/processor.h index 7acd46653df3..0c265aba94ad 100644 --- a/arch/blackfin/include/asm/processor.h +++ b/arch/blackfin/include/asm/processor.h @@ -76,13 +76,6 @@ static inline void release_thread(struct task_struct *dead_task) } /* - * Free current thread data structures etc.. - */ -static inline void exit_thread(void) -{ -} - -/* * Return saved PC of a blocked thread. */ #define thread_saved_pc(tsk) (tsk->thread.pc) diff --git a/arch/c6x/kernel/process.c b/arch/c6x/kernel/process.c index 3ae9f5a166a0..0ee7686a78f3 100644 --- a/arch/c6x/kernel/process.c +++ b/arch/c6x/kernel/process.c @@ -82,10 +82,6 @@ void flush_thread(void) { } -void exit_thread(void) -{ -} - /* * Do necessary setup to start up a newly executed thread. */ diff --git a/arch/cris/Kconfig b/arch/cris/Kconfig index e086f9e93728..088551086342 100644 --- a/arch/cris/Kconfig +++ b/arch/cris/Kconfig @@ -59,6 +59,7 @@ config CRIS select GENERIC_IOMAP select MODULES_USE_ELF_RELA select CLONE_BACKWARDS2 + select HAVE_EXIT_THREAD if ETRAX_ARCH_V32 select OLD_SIGSUSPEND select OLD_SIGACTION select ARCH_REQUIRE_GPIOLIB diff --git a/arch/cris/arch-v10/kernel/process.c b/arch/cris/arch-v10/kernel/process.c index 02b783457be0..96e5afef6b47 100644 --- a/arch/cris/arch-v10/kernel/process.c +++ b/arch/cris/arch-v10/kernel/process.c @@ -35,15 +35,6 @@ void default_idle(void) local_irq_enable(); } -/* - * Free current thread data structures etc.. - */ - -void exit_thread(void) -{ - /* Nothing needs to be done. */ -} - /* if the watchdog is enabled, we can simply disable interrupts and go * into an eternal loop, and the watchdog will reset the CPU after 0.1s * if on the other hand the watchdog wasn't enabled, we just enable it and wait diff --git a/arch/cris/arch-v32/kernel/process.c b/arch/cris/arch-v32/kernel/process.c index c7ce784a393c..4d1afa9f9fd3 100644 --- a/arch/cris/arch-v32/kernel/process.c +++ b/arch/cris/arch-v32/kernel/process.c @@ -33,9 +33,9 @@ void default_idle(void) */ extern void deconfigure_bp(long pid); -void exit_thread(void) +void exit_thread(struct task_struct *tsk) { - deconfigure_bp(current->pid); + deconfigure_bp(tsk->pid); } /* diff --git a/arch/frv/include/asm/processor.h b/arch/frv/include/asm/processor.h index ae8d423e79d9..73f0a79ad8e6 100644 --- a/arch/frv/include/asm/processor.h +++ b/arch/frv/include/asm/processor.h @@ -97,13 +97,6 @@ extern asmlinkage void *restore_user_regs(const struct user_context *target, ... #define forget_segments() do { } while (0) /* - * Free current thread data structures etc.. - */ -static inline void exit_thread(void) -{ -} - -/* * Return saved PC of a blocked thread. */ extern unsigned long thread_saved_pc(struct task_struct *tsk); diff --git a/arch/h8300/include/asm/processor.h b/arch/h8300/include/asm/processor.h index 54e3fd83c336..111df7397ac7 100644 --- a/arch/h8300/include/asm/processor.h +++ b/arch/h8300/include/asm/processor.h @@ -111,13 +111,6 @@ static inline void release_thread(struct task_struct *dead_task) } /* - * Free current thread data structures etc.. - */ -static inline void exit_thread(void) -{ -} - -/* * Return saved PC of a blocked thread. */ unsigned long thread_saved_pc(struct task_struct *tsk); diff --git a/arch/hexagon/kernel/process.c b/arch/hexagon/kernel/process.c index a9ebd471823a..d9edfd3fc52a 100644 --- a/arch/hexagon/kernel/process.c +++ b/arch/hexagon/kernel/process.c @@ -137,13 +137,6 @@ void release_thread(struct task_struct *dead_task) } /* - * Free any architecture-specific thread data structures, etc. - */ -void exit_thread(void) -{ -} - -/* * Some archs flush debug and FPU info here */ void flush_thread(void) diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig index 7091a367eeda..1678ea3fab79 100644 --- a/arch/ia64/Kconfig +++ b/arch/ia64/Kconfig @@ -18,6 +18,7 @@ config IA64 select ACPI_SYSTEM_POWER_STATES_SUPPORT if ACPI select ARCH_MIGHT_HAVE_ACPI_PDC if ACPI select HAVE_UNSTABLE_SCHED_CLOCK + select HAVE_EXIT_THREAD select HAVE_IDE select HAVE_OPROFILE select HAVE_KPROBES diff --git a/arch/ia64/kernel/perfmon.c b/arch/ia64/kernel/perfmon.c index 60e02f7747ff..c5d5955511d1 100644 --- a/arch/ia64/kernel/perfmon.c +++ b/arch/ia64/kernel/perfmon.c @@ -4543,8 +4543,8 @@ pfm_context_unload(pfm_context_t *ctx, void *arg, int count, struct pt_regs *reg /* - * called only from exit_thread(): task == current - * we come here only if current has a context attached (loaded or masked) + * called only from exit_thread() + * we come here only if the task has a context attached (loaded or masked) */ void pfm_exit_thread(struct task_struct *task) diff --git a/arch/ia64/kernel/process.c b/arch/ia64/kernel/process.c index b51514957620..aae6c4dc7ae7 100644 --- a/arch/ia64/kernel/process.c +++ b/arch/ia64/kernel/process.c @@ -570,22 +570,22 @@ flush_thread (void) } /* - * Clean up state associated with current thread. This is called when + * Clean up state associated with a thread. This is called when * the thread calls exit(). */ void -exit_thread (void) +exit_thread (struct task_struct *tsk) { - ia64_drop_fpu(current); + ia64_drop_fpu(tsk); #ifdef CONFIG_PERFMON /* if needed, stop monitoring and flush state to perfmon context */ - if (current->thread.pfm_context) - pfm_exit_thread(current); + if (tsk->thread.pfm_context) + pfm_exit_thread(tsk); /* free debug register resources */ - if (current->thread.flags & IA64_THREAD_DBG_VALID) - pfm_release_debug_registers(current); + if (tsk->thread.flags & IA64_THREAD_DBG_VALID) + pfm_release_debug_registers(tsk); #endif } diff --git a/arch/m32r/kernel/process.c b/arch/m32r/kernel/process.c index e69221d581d5..a88b1f01e91f 100644 --- a/arch/m32r/kernel/process.c +++ b/arch/m32r/kernel/process.c @@ -101,15 +101,6 @@ void show_regs(struct pt_regs * regs) #endif } -/* - * Free current thread data structures etc.. - */ -void exit_thread(void) -{ - /* Nothing to do. */ - DPRINTK("pid = %d\n", current->pid); -} - void flush_thread(void) { DPRINTK("pid = %d\n", current->pid); diff --git a/arch/m68k/include/asm/processor.h b/arch/m68k/include/asm/processor.h index 20dda1d4b860..a6ce2ec8d693 100644 --- a/arch/m68k/include/asm/processor.h +++ b/arch/m68k/include/asm/processor.h @@ -153,13 +153,6 @@ static inline void release_thread(struct task_struct *dead_task) { } -/* - * Free current thread data structures etc.. - */ -static inline void exit_thread(void) -{ -} - extern unsigned long thread_saved_pc(struct task_struct *tsk); unsigned long get_wchan(struct task_struct *p); diff --git a/arch/metag/Kconfig b/arch/metag/Kconfig index 0b389a81c43a..6fe012a001be 100644 --- a/arch/metag/Kconfig +++ b/arch/metag/Kconfig @@ -11,6 +11,7 @@ config METAG select HAVE_DEBUG_KMEMLEAK select HAVE_DEBUG_STACKOVERFLOW select HAVE_DYNAMIC_FTRACE + select HAVE_EXIT_THREAD select HAVE_FTRACE_MCOUNT_RECORD select HAVE_FUNCTION_TRACER select HAVE_KERNEL_BZIP2 diff --git a/arch/metag/include/asm/processor.h b/arch/metag/include/asm/processor.h index 0838ca699764..a0333ebcac35 100644 --- a/arch/metag/include/asm/processor.h +++ b/arch/metag/include/asm/processor.h @@ -134,8 +134,6 @@ static inline void release_thread(struct task_struct *dead_task) #define copy_segments(tsk, mm) do { } while (0) #define release_segments(mm) do { } while (0) -extern void exit_thread(void); - /* * Return saved PC of a blocked thread. */ diff --git a/arch/metag/kernel/process.c b/arch/metag/kernel/process.c index 7f546183a0f0..35062796edf2 100644 --- a/arch/metag/kernel/process.c +++ b/arch/metag/kernel/process.c @@ -345,10 +345,10 @@ void flush_thread(void) /* * Free current thread data structures etc. */ -void exit_thread(void) +void exit_thread(struct task_struct *tsk) { - clear_fpu(¤t->thread); - clear_dsp(¤t->thread); + clear_fpu(&tsk->thread); + clear_dsp(&tsk->thread); } /* TODO: figure out how to unwind the kernel stack here to figure out diff --git a/arch/microblaze/include/asm/processor.h b/arch/microblaze/include/asm/processor.h index 497a988d79c2..c38d0dd91134 100644 --- a/arch/microblaze/include/asm/processor.h +++ b/arch/microblaze/include/asm/processor.h @@ -70,11 +70,6 @@ static inline void release_thread(struct task_struct *dead_task) { } -/* Free all resources held by a thread. */ -static inline void exit_thread(void) -{ -} - extern unsigned long thread_saved_pc(struct task_struct *t); extern unsigned long get_wchan(struct task_struct *p); @@ -127,11 +122,6 @@ static inline void release_thread(struct task_struct *dead_task) { } -/* Free current thread data structures etc. */ -static inline void exit_thread(void) -{ -} - /* Return saved (kernel) PC of a blocked thread. */ # define thread_saved_pc(tsk) \ ((tsk)->thread.regs ? (tsk)->thread.regs->r15 : 0) diff --git a/arch/mips/Kbuild.platforms b/arch/mips/Kbuild.platforms index a96c81d1d22e..5631eaa8e54b 100644 --- a/arch/mips/Kbuild.platforms +++ b/arch/mips/Kbuild.platforms @@ -11,6 +11,7 @@ platforms += cavium-octeon platforms += cobalt platforms += dec platforms += emma +platforms += generic platforms += jazz platforms += jz4740 platforms += lantiq diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 8b0424abc84c..2c93e3b7d318 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -64,6 +64,8 @@ config MIPS select HAVE_IRQ_TIME_ACCOUNTING select GENERIC_TIME_VSYSCALL select ARCH_CLOCKSOURCE_DATA + select HANDLE_DOMAIN_IRQ + select HAVE_EXIT_THREAD menu "Machine selection" @@ -71,6 +73,57 @@ choice prompt "System type" default SGI_IP22 +config MIPS_GENERIC + bool "Generic board-agnostic MIPS kernel" + select BOOT_RAW + select BUILTIN_DTB + select CEVT_R4K + select CLKSRC_MIPS_GIC + select COMMON_CLK + select CPU_MIPSR2_IRQ_VI + select CPU_MIPSR2_IRQ_EI + select CSRC_R4K + select DMA_PERDEV_COHERENT + select HW_HAS_PCI + select IRQ_MIPS_CPU + select LIBFDT + select MIPS_CPU_SCACHE + select MIPS_GIC + select MIPS_L1_CACHE_SHIFT_7 + select NO_EXCEPT_FILL + select PCI_DRIVERS_GENERIC + select PINCTRL + select SMP_UP if SMP + select SYS_HAS_CPU_MIPS32_R1 + select SYS_HAS_CPU_MIPS32_R2 + select SYS_HAS_CPU_MIPS32_R6 + select SYS_HAS_CPU_MIPS64_R1 + select SYS_HAS_CPU_MIPS64_R2 + select SYS_HAS_CPU_MIPS64_R6 + select SYS_SUPPORTS_32BIT_KERNEL + select SYS_SUPPORTS_64BIT_KERNEL + select SYS_SUPPORTS_BIG_ENDIAN + select SYS_SUPPORTS_HIGHMEM + select SYS_SUPPORTS_LITTLE_ENDIAN + select SYS_SUPPORTS_MICROMIPS + select SYS_SUPPORTS_MIPS_CPS + select SYS_SUPPORTS_MIPS16 + select SYS_SUPPORTS_MULTITHREADING + select SYS_SUPPORTS_RELOCATABLE + select SYS_SUPPORTS_SMARTMIPS + select USB_EHCI_BIG_ENDIAN_DESC if BIG_ENDIAN + select USB_EHCI_BIG_ENDIAN_MMIO if BIG_ENDIAN + select USB_OHCI_BIG_ENDIAN_DESC if BIG_ENDIAN + select USB_OHCI_BIG_ENDIAN_MMIO if BIG_ENDIAN + select USB_UHCI_BIG_ENDIAN_DESC if BIG_ENDIAN + select USB_UHCI_BIG_ENDIAN_MMIO if BIG_ENDIAN + select USE_OF + help + Select this to build a kernel which aims to support multiple boards, + generally using a flattened device tree passed from the bootloader + using the boot protocol defined in the UHI (Unified Hosting + Interface) specification. + config MIPS_ALCHEMY bool "Alchemy processor based machines" select ARCH_PHYS_ADDR_T_64BIT @@ -977,6 +1030,7 @@ source "arch/mips/ath79/Kconfig" source "arch/mips/bcm47xx/Kconfig" source "arch/mips/bcm63xx/Kconfig" source "arch/mips/bmips/Kconfig" +source "arch/mips/generic/Kconfig" source "arch/mips/jazz/Kconfig" source "arch/mips/jz4740/Kconfig" source "arch/mips/lantiq/Kconfig" @@ -1086,6 +1140,10 @@ config DMA_MAYBE_COHERENT select DMA_NONCOHERENT bool +config DMA_PERDEV_COHERENT + bool + select DMA_MAYBE_COHERENT + config DMA_COHERENT bool @@ -1981,7 +2039,7 @@ config CPU_SUPPORTS_UNCACHED_ACCELERATED bool config MIPS_PGD_C0_CONTEXT bool - default y if 64BIT && CPU_MIPSR2 && !CPU_XLP + default y if 64BIT && (CPU_MIPSR2 || CPU_MIPSR6) && !CPU_XLP # # Set to y for ptrace access to watch registers. @@ -2270,7 +2328,7 @@ config MIPS_CMP config MIPS_CPS bool "MIPS Coherent Processing System support" - depends on SYS_SUPPORTS_MIPS_CPS && !CPU_MIPSR6 + depends on SYS_SUPPORTS_MIPS_CPS select MIPS_CM select MIPS_CPC select MIPS_CPS_PM if HOTPLUG_CPU @@ -2278,6 +2336,7 @@ config MIPS_CPS select SMP select SYNC_R4K if (CEVT_R4K || CSRC_R4K) select SYS_SUPPORTS_HOTPLUG_CPU + select SYS_SUPPORTS_SCHED_SMT if CPU_MIPSR6 select SYS_SUPPORTS_SMP select WEAK_ORDERING help diff --git a/arch/mips/Makefile b/arch/mips/Makefile index 252e347958f3..0e4516d631a6 100644 --- a/arch/mips/Makefile +++ b/arch/mips/Makefile @@ -138,7 +138,7 @@ cflags-$(CONFIG_CPU_MIPS32_R1) += $(call cc-option,-march=mips32,-mips32 -U_MIPS -Wa,-mips32 -Wa,--trap cflags-$(CONFIG_CPU_MIPS32_R2) += $(call cc-option,-march=mips32r2,-mips32r2 -U_MIPS_ISA -D_MIPS_ISA=_MIPS_ISA_MIPS32) \ -Wa,-mips32r2 -Wa,--trap -cflags-$(CONFIG_CPU_MIPS32_R6) += -march=mips32r6 -Wa,--trap +cflags-$(CONFIG_CPU_MIPS32_R6) += -march=mips32r6 -Wa,--trap -modd-spreg cflags-$(CONFIG_CPU_MIPS64_R1) += $(call cc-option,-march=mips64,-mips64 -U_MIPS_ISA -D_MIPS_ISA=_MIPS_ISA_MIPS64) \ -Wa,-mips64 -Wa,--trap cflags-$(CONFIG_CPU_MIPS64_R2) += $(call cc-option,-march=mips64r2,-mips64r2 -U_MIPS_ISA -D_MIPS_ISA=_MIPS_ISA_MIPS64) \ @@ -263,7 +263,14 @@ KBUILD_CPPFLAGS += -DVMLINUX_LOAD_ADDRESS=$(load-y) KBUILD_CPPFLAGS += -DDATAOFFSET=$(if $(dataoffset-y),$(dataoffset-y),0) bootvars-y = VMLINUX_LOAD_ADDRESS=$(load-y) \ - VMLINUX_ENTRY_ADDRESS=$(entry-y) + VMLINUX_ENTRY_ADDRESS=$(entry-y) \ + PLATFORM="$(platform-y)" +ifdef CONFIG_32BIT +bootvars-y += ADDR_BITS=32 +endif +ifdef CONFIG_64BIT +bootvars-y += ADDR_BITS=64 +endif LDFLAGS += -m $(ld-emul) @@ -303,6 +310,11 @@ boot-y += uImage.gz boot-y += uImage.lzma boot-y += uImage.lzo endif +boot-y += vmlinux.itb +boot-y += vmlinux.gz.itb +boot-y += vmlinux.bz2.itb +boot-y += vmlinux.lzma.itb +boot-y += vmlinux.lzo.itb # compressed boot image targets (arch/mips/boot/compressed/) bootz-y := vmlinuz @@ -413,4 +425,54 @@ define archhelp echo ' dtbs_install - Install dtbs to $(INSTALL_DTBS_PATH)' echo echo ' These will be default as appropriate for a configured platform.' + echo + echo ' If you are targeting a system supported by generic kernels you may' + echo ' configure the kernel for a given architecture target like so:' + echo + echo ' {micro32,32,64}{r1,r2,r6}{el,}_defconfig <BOARDS="list of boards">' + echo + echo ' Otherwise, the following default configurations are available:' endef + +generic_config_dir = $(srctree)/arch/$(ARCH)/configs/generic +generic_defconfigs := + +# +# If the user generates a generic kernel configuration without specifying a +# list of boards to include the config fragments for, default to including all +# available board config fragments. +# +ifeq ($(BOARDS),) +BOARDS = $(patsubst board-%.config,%,$(notdir $(wildcard $(generic_config_dir)/board-*.config))) +endif + +# +# Generic kernel configurations which merge generic_defconfig with the +# appropriate config fragments from arch/mips/configs/generic/, resulting in +# the ability to easily configure the kernel for a given architecture, +# endianness & set of boards without duplicating the needed configuration in +# hundreds of defconfig files. +# +define gen_generic_defconfigs +$(foreach bits,$(1),$(foreach rev,$(2),$(foreach endian,$(3), +target := $(bits)$(rev)$(filter el,$(endian))_defconfig +generic_defconfigs += $$(target) +$$(target): $(generic_config_dir)/$(bits)$(rev).config +$$(target): $(generic_config_dir)/$(endian).config +))) +endef + +$(eval $(call gen_generic_defconfigs,32 64,r1 r2 r6,eb el)) +$(eval $(call gen_generic_defconfigs,micro32,r2,eb el)) + +.PHONY: $(generic_defconfigs) +$(generic_defconfigs): + $(Q)$(CONFIG_SHELL) $(srctree)/scripts/kconfig/merge_config.sh \ + -m -O $(objtree) $(srctree)/arch/$(ARCH)/configs/generic_defconfig $^ \ + $(foreach board,$(BOARDS),$(generic_config_dir)/board-$(board).config) + $(Q)$(MAKE) olddefconfig + +# +# Prevent generic merge_config rules attempting to merge single fragments +# +$(generic_config_dir)/%.config: ; diff --git a/arch/mips/alchemy/common/dbdma.c b/arch/mips/alchemy/common/dbdma.c index 745695db5ba0..f2f264b5aafe 100644 --- a/arch/mips/alchemy/common/dbdma.c +++ b/arch/mips/alchemy/common/dbdma.c @@ -261,7 +261,7 @@ u32 au1xxx_dbdma_chan_alloc(u32 srcid, u32 destid, au1x_dma_chan_t *cp; /* - * We do the intialization on the first channel allocation. + * We do the initialization on the first channel allocation. * We have to wait because of the interrupt handler initialization * which can't be done successfully during board set up. */ @@ -964,7 +964,7 @@ u32 au1xxx_dbdma_put_dscr(u32 chanid, au1x_ddma_desc_t *dscr) dp->dscr_source1 = dscr->dscr_source1; dp->dscr_cmd1 = dscr->dscr_cmd1; nbytes = dscr->dscr_cmd1; - /* Allow the caller to specifiy if an interrupt is generated */ + /* Allow the caller to specify if an interrupt is generated */ dp->dscr_cmd0 &= ~DSCR_CMD0_IE; dp->dscr_cmd0 |= dscr->dscr_cmd0 | DSCR_CMD0_V; ctp->chan_ptr->ddma_dbell = 0; diff --git a/arch/mips/alchemy/common/setup.c b/arch/mips/alchemy/common/setup.c index 2902138b3e0f..7faaa6d593a7 100644 --- a/arch/mips/alchemy/common/setup.c +++ b/arch/mips/alchemy/common/setup.c @@ -48,17 +48,17 @@ void __init plat_mem_setup(void) clear_c0_config(1 << 19); /* Clear Config[OD] */ hw_coherentio = 0; - coherentio = 1; + coherentio = IO_COHERENCE_ENABLED; switch (alchemy_get_cputype()) { case ALCHEMY_CPU_AU1000: case ALCHEMY_CPU_AU1500: case ALCHEMY_CPU_AU1100: - coherentio = 0; + coherentio = IO_COHERENCE_DISABLED; break; case ALCHEMY_CPU_AU1200: /* Au1200 AB USB does not support coherent memory */ if (0 == (read_c0_prid() & PRID_REV_MASK)) - coherentio = 0; + coherentio = IO_COHERENCE_DISABLED; break; } diff --git a/arch/mips/bmips/setup.c b/arch/mips/bmips/setup.c index 5b16d2955fbb..a2a8344b8a64 100644 --- a/arch/mips/bmips/setup.c +++ b/arch/mips/bmips/setup.c @@ -149,8 +149,8 @@ void __init plat_mem_setup(void) /* intended to somewhat resemble ARM; see Documentation/arm/Booting */ if (fw_arg0 == 0 && fw_arg1 == 0xffffffff) dtb = phys_to_virt(fw_arg2); - else if (fw_arg0 == -2) /* UHI interface */ - dtb = (void *)fw_arg1; + else if (fw_passed_dtb) /* UHI interface */ + dtb = (void *)fw_passed_dtb; else if (__dtb_start != __dtb_end) dtb = (void *)__dtb_start; else diff --git a/arch/mips/boot/Makefile b/arch/mips/boot/Makefile index acb1988f354e..2728a9a9c7c5 100644 --- a/arch/mips/boot/Makefile +++ b/arch/mips/boot/Makefile @@ -100,3 +100,69 @@ $(obj)/uImage.lzo: $(obj)/vmlinux.bin.lzo FORCE $(obj)/uImage: $(obj)/uImage.$(suffix-y) @ln -sf $(notdir $<) $@ @echo ' Image $@ is ready' + +# +# Flattened Image Tree (.itb) images +# + +targets += vmlinux.itb +targets += vmlinux.gz.itb +targets += vmlinux.bz2.itb +targets += vmlinux.lzma.itb +targets += vmlinux.lzo.itb + +ifeq ($(ADDR_BITS),32) + itb_addr_cells = 1 +endif +ifeq ($(ADDR_BITS),64) + itb_addr_cells = 2 +endif + +quiet_cmd_cpp_its_S = ITS $@ + cmd_cpp_its_S = $(CPP) $(cpp_flags) -P -C -o $@ $< \ + -DKERNEL_NAME="\"Linux $(KERNELRELEASE)\"" \ + -DVMLINUX_BINARY="\"$(3)\"" \ + -DVMLINUX_COMPRESSION="\"$(2)\"" \ + -DVMLINUX_LOAD_ADDRESS=$(VMLINUX_LOAD_ADDRESS) \ + -DVMLINUX_ENTRY_ADDRESS=$(VMLINUX_ENTRY_ADDRESS) \ + -DADDR_BITS=$(ADDR_BITS) \ + -DADDR_CELLS=$(itb_addr_cells) + +$(obj)/vmlinux.its: $(srctree)/arch/mips/$(PLATFORM)/vmlinux.its.S FORCE + $(call if_changed_dep,cpp_its_S,none,vmlinux.bin) + +$(obj)/vmlinux.gz.its: $(srctree)/arch/mips/$(PLATFORM)/vmlinux.its.S FORCE + $(call if_changed_dep,cpp_its_S,gzip,vmlinux.bin.gz) + +$(obj)/vmlinux.bz2.its: $(srctree)/arch/mips/$(PLATFORM)/vmlinux.its.S FORCE + $(call if_changed_dep,cpp_its_S,bzip2,vmlinux.bin.bz2) + +$(obj)/vmlinux.lzma.its: $(srctree)/arch/mips/$(PLATFORM)/vmlinux.its.S FORCE + $(call if_changed_dep,cpp_its_S,lzma,vmlinux.bin.lzma) + +$(obj)/vmlinux.lzo.its: $(srctree)/arch/mips/$(PLATFORM)/vmlinux.its.S FORCE + $(call if_changed_dep,cpp_its_S,lzo,vmlinux.bin.lzo) + +quiet_cmd_itb-image = ITB $@ + cmd_itb-image = \ + env PATH="$(objtree)/scripts/dtc:$(PATH)" \ + $(CONFIG_SHELL) $(MKIMAGE) \ + -D "-I dts -O dtb -p 500 \ + --include $(objtree)/arch/mips \ + --warning no-unit_address_vs_reg" \ + -f $(2) $@ + +$(obj)/vmlinux.itb: $(obj)/vmlinux.its $(obj)/vmlinux.bin FORCE + $(call if_changed,itb-image,$<) + +$(obj)/vmlinux.gz.itb: $(obj)/vmlinux.gz.its $(obj)/vmlinux.bin.gz FORCE + $(call if_changed,itb-image,$<) + +$(obj)/vmlinux.bz2.itb: $(obj)/vmlinux.bz2.its $(obj)/vmlinux.bin.bz2 FORCE + $(call if_changed,itb-image,$<) + +$(obj)/vmlinux.lzma.itb: $(obj)/vmlinux.lzma.its $(obj)/vmlinux.bin.lzma FORCE + $(call if_changed,itb-image,$<) + +$(obj)/vmlinux.lzo.itb: $(obj)/vmlinux.lzo.its $(obj)/vmlinux.bin.lzo FORCE + $(call if_changed,itb-image,$<) diff --git a/arch/mips/cavium-octeon/executive/cvmx-interrupt-decodes.c b/arch/mips/cavium-octeon/executive/cvmx-interrupt-decodes.c index e59d1b79f24c..2f415d9d0f3c 100644 --- a/arch/mips/cavium-octeon/executive/cvmx-interrupt-decodes.c +++ b/arch/mips/cavium-octeon/executive/cvmx-interrupt-decodes.c @@ -68,7 +68,7 @@ void __cvmx_interrupt_gmxx_rxx_int_en_enable(int index, int block) gmx_rx_int_en.s.pause_drp = 1; /* Skipping gmx_rx_int_en.s.reserved_16_18 */ /*gmx_rx_int_en.s.ifgerr = 1; */ - /*gmx_rx_int_en.s.coldet = 1; // Collsion detect */ + /*gmx_rx_int_en.s.coldet = 1; // Collision detect */ /*gmx_rx_int_en.s.falerr = 1; // False carrier error or extend error after slottime */ /*gmx_rx_int_en.s.rsverr = 1; // RGMII reserved opcodes */ /*gmx_rx_int_en.s.pcterr = 1; // Bad Preamble / Protocol */ @@ -89,7 +89,7 @@ void __cvmx_interrupt_gmxx_rxx_int_en_enable(int index, int block) /*gmx_rx_int_en.s.phy_spd = 1; */ /*gmx_rx_int_en.s.phy_link = 1; */ /*gmx_rx_int_en.s.ifgerr = 1; */ - /*gmx_rx_int_en.s.coldet = 1; // Collsion detect */ + /*gmx_rx_int_en.s.coldet = 1; // Collision detect */ /*gmx_rx_int_en.s.falerr = 1; // False carrier error or extend error after slottime */ /*gmx_rx_int_en.s.rsverr = 1; // RGMII reserved opcodes */ /*gmx_rx_int_en.s.pcterr = 1; // Bad Preamble / Protocol */ @@ -112,7 +112,7 @@ void __cvmx_interrupt_gmxx_rxx_int_en_enable(int index, int block) /*gmx_rx_int_en.s.phy_spd = 1; */ /*gmx_rx_int_en.s.phy_link = 1; */ /*gmx_rx_int_en.s.ifgerr = 1; */ - /*gmx_rx_int_en.s.coldet = 1; // Collsion detect */ + /*gmx_rx_int_en.s.coldet = 1; // Collision detect */ /*gmx_rx_int_en.s.falerr = 1; // False carrier error or extend error after slottime */ /*gmx_rx_int_en.s.rsverr = 1; // RGMII reserved opcodes */ /*gmx_rx_int_en.s.pcterr = 1; // Bad Preamble / Protocol */ @@ -134,7 +134,7 @@ void __cvmx_interrupt_gmxx_rxx_int_en_enable(int index, int block) /*gmx_rx_int_en.s.phy_spd = 1; */ /*gmx_rx_int_en.s.phy_link = 1; */ /*gmx_rx_int_en.s.ifgerr = 1; */ - /*gmx_rx_int_en.s.coldet = 1; // Collsion detect */ + /*gmx_rx_int_en.s.coldet = 1; // Collision detect */ /*gmx_rx_int_en.s.falerr = 1; // False carrier error or extend error after slottime */ /*gmx_rx_int_en.s.rsverr = 1; // RGMII reserved opcodes */ /*gmx_rx_int_en.s.pcterr = 1; // Bad Preamble / Protocol */ @@ -156,7 +156,7 @@ void __cvmx_interrupt_gmxx_rxx_int_en_enable(int index, int block) /*gmx_rx_int_en.s.phy_spd = 1; */ /*gmx_rx_int_en.s.phy_link = 1; */ /*gmx_rx_int_en.s.ifgerr = 1; */ - /*gmx_rx_int_en.s.coldet = 1; // Collsion detect */ + /*gmx_rx_int_en.s.coldet = 1; // Collision detect */ /*gmx_rx_int_en.s.falerr = 1; // False carrier error or extend error after slottime */ /*gmx_rx_int_en.s.rsverr = 1; // RGMII reserved opcodes */ /*gmx_rx_int_en.s.pcterr = 1; // Bad Preamble / Protocol */ @@ -179,7 +179,7 @@ void __cvmx_interrupt_gmxx_rxx_int_en_enable(int index, int block) /*gmx_rx_int_en.s.phy_spd = 1; */ /*gmx_rx_int_en.s.phy_link = 1; */ /*gmx_rx_int_en.s.ifgerr = 1; */ - /*gmx_rx_int_en.s.coldet = 1; // Collsion detect */ + /*gmx_rx_int_en.s.coldet = 1; // Collision detect */ /*gmx_rx_int_en.s.falerr = 1; // False carrier error or extend error after slottime */ /*gmx_rx_int_en.s.rsverr = 1; // RGMII reserved opcodes */ /*gmx_rx_int_en.s.pcterr = 1; // Bad Preamble / Protocol */ @@ -209,7 +209,7 @@ void __cvmx_interrupt_gmxx_rxx_int_en_enable(int index, int block) gmx_rx_int_en.s.pause_drp = 1; /* Skipping gmx_rx_int_en.s.reserved_16_18 */ /*gmx_rx_int_en.s.ifgerr = 1; */ - /*gmx_rx_int_en.s.coldet = 1; // Collsion detect */ + /*gmx_rx_int_en.s.coldet = 1; // Collision detect */ /*gmx_rx_int_en.s.falerr = 1; // False carrier error or extend error after slottime */ /*gmx_rx_int_en.s.rsverr = 1; // RGMII reserved opcodes */ /*gmx_rx_int_en.s.pcterr = 1; // Bad Preamble / Protocol */ diff --git a/arch/mips/cavium-octeon/executive/cvmx-pko.c b/arch/mips/cavium-octeon/executive/cvmx-pko.c index 87be167a7a6a..676fab50dd2b 100644 --- a/arch/mips/cavium-octeon/executive/cvmx-pko.c +++ b/arch/mips/cavium-octeon/executive/cvmx-pko.c @@ -189,7 +189,7 @@ void cvmx_pko_initialize_global(void) /* * Set the size of the PKO command buffers to an odd number of * 64bit words. This allows the normal two word send to stay - * aligned and never span a comamnd word buffer. + * aligned and never span a command word buffer. */ config.u64 = 0; config.s.pool = CVMX_FPA_OUTPUT_BUFFER_POOL; diff --git a/arch/mips/cavium-octeon/smp.c b/arch/mips/cavium-octeon/smp.c index b7fa9ae28c36..42412ba0f3bf 100644 --- a/arch/mips/cavium-octeon/smp.c +++ b/arch/mips/cavium-octeon/smp.c @@ -331,7 +331,7 @@ static int octeon_update_boot_vector(unsigned int cpu) } if (!(avail_coremask & (1 << coreid))) { - /* core not available, assume, that catched by simple-executive */ + /* core not available, assume, that caught by simple-executive */ cvmx_write_csr(CVMX_CIU_PP_RST, 1 << coreid); cvmx_write_csr(CVMX_CIU_PP_RST, 0); } diff --git a/arch/mips/configs/generic/32r1.config b/arch/mips/configs/generic/32r1.config new file mode 100644 index 000000000000..a11cd8715519 --- /dev/null +++ b/arch/mips/configs/generic/32r1.config @@ -0,0 +1,2 @@ +CONFIG_CPU_MIPS32_R1=y +CONFIG_HIGHMEM=y diff --git a/arch/mips/configs/generic/32r2.config b/arch/mips/configs/generic/32r2.config new file mode 100644 index 000000000000..9570672d4f9f --- /dev/null +++ b/arch/mips/configs/generic/32r2.config @@ -0,0 +1,3 @@ +CONFIG_CPU_MIPS32_R2=y +CONFIG_MIPS_O32_FP64_SUPPORT=y +CONFIG_HIGHMEM=y diff --git a/arch/mips/configs/generic/32r6.config b/arch/mips/configs/generic/32r6.config new file mode 100644 index 000000000000..ca606e71f4d0 --- /dev/null +++ b/arch/mips/configs/generic/32r6.config @@ -0,0 +1,2 @@ +CONFIG_CPU_MIPS32_R6=y +CONFIG_HIGHMEM=y diff --git a/arch/mips/configs/generic/64r1.config b/arch/mips/configs/generic/64r1.config new file mode 100644 index 000000000000..7c1ea7e7bae3 --- /dev/null +++ b/arch/mips/configs/generic/64r1.config @@ -0,0 +1,4 @@ +CONFIG_CPU_MIPS64_R1=y +CONFIG_64BIT=y +CONFIG_MIPS32_O32=y +CONFIG_MIPS32_N32=y diff --git a/arch/mips/configs/generic/64r2.config b/arch/mips/configs/generic/64r2.config new file mode 100644 index 000000000000..b4d31ae8bfec --- /dev/null +++ b/arch/mips/configs/generic/64r2.config @@ -0,0 +1,5 @@ +CONFIG_CPU_MIPS64_R2=y +CONFIG_MIPS_O32_FP64_SUPPORT=y +CONFIG_64BIT=y +CONFIG_MIPS32_O32=y +CONFIG_MIPS32_N32=y diff --git a/arch/mips/configs/generic/64r6.config b/arch/mips/configs/generic/64r6.config new file mode 100644 index 000000000000..7cac0339c4d5 --- /dev/null +++ b/arch/mips/configs/generic/64r6.config @@ -0,0 +1,4 @@ +CONFIG_CPU_MIPS64_R6=y +CONFIG_64BIT=y +CONFIG_MIPS32_O32=y +CONFIG_MIPS32_N32=y diff --git a/arch/mips/configs/generic/board-ranchu.config b/arch/mips/configs/generic/board-ranchu.config new file mode 100644 index 000000000000..fee9ad4c5598 --- /dev/null +++ b/arch/mips/configs/generic/board-ranchu.config @@ -0,0 +1,30 @@ +CONFIG_VIRT_BOARD_RANCHU=y + +CONFIG_BATTERY_GOLDFISH=y +CONFIG_FB=y +CONFIG_FB_GOLDFISH=y +CONFIG_GOLDFISH=y +CONFIG_STAGING=y +CONFIG_GOLDFISH_AUDIO=y +CONFIG_GOLDFISH_PIC=y +CONFIG_GOLDFISH_PIPE=y +CONFIG_GOLDFISH_TTY=y +CONFIG_RTC_CLASS=y +CONFIG_RTC_DRV_GOLDFISH=y + +CONFIG_INPUT_EVDEV=y +CONFIG_INPUT_KEYBOARD=y +CONFIG_KEYBOARD_GOLDFISH_EVENTS=y + +CONFIG_MAGIC_SYSRQ=y +CONFIG_POWER_SUPPLY=y +CONFIG_POWER_RESET=y +CONFIG_POWER_RESET_SYSCON=y +CONFIG_POWER_RESET_SYSCON_POWEROFF=y + +CONFIG_VIRTIO_BLK=y +CONFIG_VIRTIO_CONSOLE=y +CONFIG_VIRTIO_MMIO=y +CONFIG_VIRTIO_MMIO_CMDLINE_DEVICES=y +CONFIG_NETDEVICES=y +CONFIG_VIRTIO_NET=y diff --git a/arch/mips/configs/generic/eb.config b/arch/mips/configs/generic/eb.config new file mode 100644 index 000000000000..c5cdc99a6530 --- /dev/null +++ b/arch/mips/configs/generic/eb.config @@ -0,0 +1 @@ +CONFIG_CPU_BIG_ENDIAN=y diff --git a/arch/mips/configs/generic/el.config b/arch/mips/configs/generic/el.config new file mode 100644 index 000000000000..ee43fdb3b8f4 --- /dev/null +++ b/arch/mips/configs/generic/el.config @@ -0,0 +1 @@ +CONFIG_CPU_LITTLE_ENDIAN=y diff --git a/arch/mips/configs/generic/micro32r2.config b/arch/mips/configs/generic/micro32r2.config new file mode 100644 index 000000000000..b701fe7aaa68 --- /dev/null +++ b/arch/mips/configs/generic/micro32r2.config @@ -0,0 +1,4 @@ +CONFIG_CPU_MIPS32_R2=y +CONFIG_CPU_MICROMIPS=y +CONFIG_MIPS_O32_FP64_SUPPORT=y +CONFIG_HIGHMEM=y diff --git a/arch/mips/configs/generic_defconfig b/arch/mips/configs/generic_defconfig new file mode 100644 index 000000000000..196c14d400b8 --- /dev/null +++ b/arch/mips/configs/generic_defconfig @@ -0,0 +1,96 @@ +CONFIG_MIPS_GENERIC=y +CONFIG_CPU_LITTLE_ENDIAN=y +CONFIG_MIPS_CPS=y +CONFIG_CPU_HAS_MSA=y +CONFIG_HIGHMEM=y +CONFIG_NR_CPUS=16 +CONFIG_MIPS_O32_FP64_SUPPORT=y +CONFIG_SYSVIPC=y +CONFIG_NO_HZ_IDLE=y +CONFIG_IKCONFIG=y +CONFIG_IKCONFIG_PROC=y +CONFIG_MEMCG=y +CONFIG_MEMCG_SWAP=y +CONFIG_BLK_CGROUP=y +CONFIG_CFS_BANDWIDTH=y +CONFIG_RT_GROUP_SCHED=y +CONFIG_CGROUP_PIDS=y +CONFIG_CGROUP_FREEZER=y +CONFIG_CPUSETS=y +CONFIG_CGROUP_DEVICE=y +CONFIG_CGROUP_CPUACCT=y +CONFIG_NAMESPACES=y +CONFIG_USER_NS=y +CONFIG_SCHED_AUTOGROUP=y +CONFIG_BLK_DEV_INITRD=y +CONFIG_BPF_SYSCALL=y +CONFIG_USERFAULTFD=y +CONFIG_EMBEDDED=y +# CONFIG_SLUB_DEBUG is not set +# CONFIG_COMPAT_BRK is not set +CONFIG_CC_STACKPROTECTOR_REGULAR=y +CONFIG_MODULES=y +CONFIG_MODULE_UNLOAD=y +CONFIG_TRIM_UNUSED_KSYMS=y +CONFIG_NET=y +CONFIG_PACKET=y +CONFIG_UNIX=y +CONFIG_INET=y +CONFIG_NETFILTER=y +# CONFIG_WIRELESS is not set +CONFIG_DEVTMPFS=y +CONFIG_DEVTMPFS_MOUNT=y +CONFIG_SCSI=y +# CONFIG_INPUT_MOUSEDEV is not set +# CONFIG_INPUT_KEYBOARD is not set +# CONFIG_INPUT_MOUSE is not set +# CONFIG_SERIO is not set +CONFIG_HW_RANDOM=y +# CONFIG_HWMON is not set +CONFIG_MFD_SYSCON=y +CONFIG_HID_A4TECH=y +CONFIG_HID_APPLE=y +CONFIG_HID_BELKIN=y +CONFIG_HID_CHERRY=y +CONFIG_HID_CHICONY=y +CONFIG_HID_CYPRESS=y +CONFIG_HID_EZKEY=y +CONFIG_HID_KENSINGTON=y +CONFIG_HID_LOGITECH=y +CONFIG_HID_MICROSOFT=y +CONFIG_HID_MONTEREY=y +# CONFIG_USB_SUPPORT is not set +# CONFIG_MIPS_PLATFORM_DEVICES is not set +# CONFIG_IOMMU_SUPPORT is not set +CONFIG_EXT4_FS=y +CONFIG_EXT4_FS_POSIX_ACL=y +CONFIG_EXT4_FS_SECURITY=y +CONFIG_EXT4_ENCRYPTION=y +CONFIG_FANOTIFY=y +CONFIG_FUSE_FS=y +CONFIG_CUSE=y +CONFIG_OVERLAY_FS=y +CONFIG_MSDOS_FS=y +CONFIG_VFAT_FS=y +CONFIG_TMPFS=y +CONFIG_TMPFS_POSIX_ACL=y +# CONFIG_MISC_FILESYSTEMS is not set +CONFIG_NFS_FS=y +CONFIG_NFS_V3_ACL=y +CONFIG_NFS_V4=y +CONFIG_NFS_V4_1=y +CONFIG_NFS_V4_2=y +CONFIG_PRINTK_TIME=y +CONFIG_DEBUG_INFO=y +CONFIG_DEBUG_INFO_REDUCED=y +CONFIG_DEBUG_FS=y +# CONFIG_SCHED_DEBUG is not set +# CONFIG_FTRACE is not set +CONFIG_CMDLINE_BOOL=y +CONFIG_CMDLINE="earlycon" +# CONFIG_XZ_DEC_X86 is not set +# CONFIG_XZ_DEC_POWERPC is not set +# CONFIG_XZ_DEC_IA64 is not set +# CONFIG_XZ_DEC_ARM is not set +# CONFIG_XZ_DEC_ARMTHUMB is not set +# CONFIG_XZ_DEC_SPARC is not set diff --git a/arch/mips/configs/ranchu32r5_defconfig b/arch/mips/configs/ranchu32r5_defconfig new file mode 100644 index 000000000000..62287a910a12 --- /dev/null +++ b/arch/mips/configs/ranchu32r5_defconfig @@ -0,0 +1,314 @@ +CONFIG_MIPS_GENERIC=y +CONFIG_VIRT_BOARD_RANCHU=y +CONFIG_CPU_LITTLE_ENDIAN=y +CONFIG_CPU_MIPS32_R2=y +CONFIG_MIPS_CPS=y +CONFIG_CPU_HAS_MSA=y +CONFIG_HIGHMEM=y +CONFIG_KSM=y +CONFIG_CMA=y +CONFIG_NR_CPUS=16 +CONFIG_PREEMPT=y +CONFIG_MIPS_O32_FP64_SUPPORT=y +# CONFIG_USELIB is not set +CONFIG_AUDIT=y +CONFIG_NO_HZ=y +CONFIG_HIGH_RES_TIMERS=y +CONFIG_TASKSTATS=y +CONFIG_TASK_DELAY_ACCT=y +CONFIG_TASK_XACCT=y +CONFIG_TASK_IO_ACCOUNTING=y +CONFIG_IKCONFIG=y +CONFIG_IKCONFIG_PROC=y +CONFIG_CGROUP_DEBUG=y +CONFIG_CGROUP_FREEZER=y +CONFIG_CGROUP_PIDS=y +CONFIG_CGROUP_DEVICE=y +CONFIG_CPUSETS=y +CONFIG_CGROUP_CPUACCT=y +CONFIG_MEMCG=y +CONFIG_MEMCG_SWAP=y +CONFIG_CFS_BANDWIDTH=y +CONFIG_RT_GROUP_SCHED=y +CONFIG_BLK_CGROUP=y +CONFIG_NAMESPACES=y +CONFIG_USER_NS=y +CONFIG_SCHED_AUTOGROUP=y +CONFIG_BLK_DEV_INITRD=y +CONFIG_KALLSYMS_ALL=y +CONFIG_BPF_SYSCALL=y +CONFIG_USERFAULTFD=y +CONFIG_EMBEDDED=y +CONFIG_PERF_EVENTS=y +# CONFIG_SLUB_DEBUG is not set +# CONFIG_COMPAT_BRK is not set +CONFIG_CC_STACKPROTECTOR_REGULAR=y +CONFIG_MODULES=y +CONFIG_MODULE_UNLOAD=y +CONFIG_MODVERSIONS=y +# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set +CONFIG_PM_AUTOSLEEP=y +CONFIG_PM_WAKELOCKS=y +CONFIG_PM_WAKELOCKS_LIMIT=0 +# CONFIG_PM_WAKELOCKS_GC is not set +CONFIG_PM_DEBUG=y +CONFIG_NET=y +CONFIG_PACKET=y +CONFIG_UNIX=y +CONFIG_XFRM_USER=y +CONFIG_NET_KEY=y +CONFIG_INET=y +CONFIG_IP_MULTICAST=y +CONFIG_IP_ADVANCED_ROUTER=y +CONFIG_IP_MULTIPLE_TABLES=y +CONFIG_INET_ESP=y +# CONFIG_INET_LRO is not set +CONFIG_INET_DIAG_DESTROY=y +CONFIG_IPV6_ROUTER_PREF=y +CONFIG_IPV6_ROUTE_INFO=y +CONFIG_IPV6_OPTIMISTIC_DAD=y +CONFIG_INET6_AH=y +CONFIG_INET6_ESP=y +CONFIG_INET6_IPCOMP=y +CONFIG_IPV6_MIP6=y +CONFIG_IPV6_MULTIPLE_TABLES=y +CONFIG_NETFILTER=y +CONFIG_NF_CONNTRACK=y +CONFIG_NF_CONNTRACK_SECMARK=y +CONFIG_NF_CONNTRACK_EVENTS=y +CONFIG_NF_CT_PROTO_DCCP=y +CONFIG_NF_CT_PROTO_SCTP=y +CONFIG_NF_CT_PROTO_UDPLITE=y +CONFIG_NF_CONNTRACK_AMANDA=y +CONFIG_NF_CONNTRACK_FTP=y +CONFIG_NF_CONNTRACK_H323=y +CONFIG_NF_CONNTRACK_IRC=y +CONFIG_NF_CONNTRACK_NETBIOS_NS=y +CONFIG_NF_CONNTRACK_PPTP=y +CONFIG_NF_CONNTRACK_SANE=y +CONFIG_NF_CONNTRACK_TFTP=y +CONFIG_NF_CT_NETLINK=y +CONFIG_NETFILTER_XT_TARGET_CLASSIFY=y +CONFIG_NETFILTER_XT_TARGET_CONNMARK=y +CONFIG_NETFILTER_XT_TARGET_CONNSECMARK=y +CONFIG_NETFILTER_XT_TARGET_IDLETIMER=y +CONFIG_NETFILTER_XT_TARGET_MARK=y +CONFIG_NETFILTER_XT_TARGET_NFLOG=y +CONFIG_NETFILTER_XT_TARGET_NFQUEUE=y +CONFIG_NETFILTER_XT_TARGET_TPROXY=y +CONFIG_NETFILTER_XT_TARGET_TRACE=y +CONFIG_NETFILTER_XT_TARGET_SECMARK=y +CONFIG_NETFILTER_XT_TARGET_TCPMSS=y +CONFIG_NETFILTER_XT_MATCH_COMMENT=y +CONFIG_NETFILTER_XT_MATCH_CONNLIMIT=y +CONFIG_NETFILTER_XT_MATCH_CONNMARK=y +CONFIG_NETFILTER_XT_MATCH_CONNTRACK=y +CONFIG_NETFILTER_XT_MATCH_HASHLIMIT=y +CONFIG_NETFILTER_XT_MATCH_HELPER=y +CONFIG_NETFILTER_XT_MATCH_IPRANGE=y +CONFIG_NETFILTER_XT_MATCH_LENGTH=y +CONFIG_NETFILTER_XT_MATCH_LIMIT=y +CONFIG_NETFILTER_XT_MATCH_MAC=y +CONFIG_NETFILTER_XT_MATCH_MARK=y +CONFIG_NETFILTER_XT_MATCH_POLICY=y +CONFIG_NETFILTER_XT_MATCH_PKTTYPE=y +CONFIG_NETFILTER_XT_MATCH_QUOTA=y +CONFIG_NETFILTER_XT_MATCH_SOCKET=y +CONFIG_NETFILTER_XT_MATCH_STATE=y +CONFIG_NETFILTER_XT_MATCH_STATISTIC=y +CONFIG_NETFILTER_XT_MATCH_STRING=y +CONFIG_NETFILTER_XT_MATCH_TIME=y +CONFIG_NETFILTER_XT_MATCH_U32=y +CONFIG_NF_CONNTRACK_IPV4=y +CONFIG_IP_NF_IPTABLES=y +CONFIG_IP_NF_MATCH_AH=y +CONFIG_IP_NF_MATCH_ECN=y +CONFIG_IP_NF_MATCH_TTL=y +CONFIG_IP_NF_FILTER=y +CONFIG_IP_NF_TARGET_REJECT=y +CONFIG_IP_NF_NAT=y +CONFIG_IP_NF_TARGET_MASQUERADE=y +CONFIG_IP_NF_TARGET_NETMAP=y +CONFIG_IP_NF_TARGET_REDIRECT=y +CONFIG_IP_NF_MANGLE=y +CONFIG_IP_NF_RAW=y +CONFIG_IP_NF_SECURITY=y +CONFIG_IP_NF_ARPTABLES=y +CONFIG_IP_NF_ARPFILTER=y +CONFIG_IP_NF_ARP_MANGLE=y +CONFIG_NF_CONNTRACK_IPV6=y +CONFIG_IP6_NF_IPTABLES=y +CONFIG_IP6_NF_FILTER=y +CONFIG_IP6_NF_TARGET_REJECT=y +CONFIG_IP6_NF_MANGLE=y +CONFIG_IP6_NF_RAW=y +CONFIG_NET_SCHED=y +CONFIG_NET_SCH_HTB=y +CONFIG_NET_CLS_U32=y +CONFIG_NET_EMATCH=y +CONFIG_NET_EMATCH_U32=y +CONFIG_NET_CLS_ACT=y +CONFIG_DNS_RESOLVER=y +CONFIG_CFG80211=y +CONFIG_DEVTMPFS=y +CONFIG_DEVTMPFS_MOUNT=y +CONFIG_DMA_CMA=y +CONFIG_BLK_DEV_LOOP=y +CONFIG_BLK_DEV_RAM=y +CONFIG_BLK_DEV_RAM_SIZE=8192 +CONFIG_VIRTIO_BLK=y +CONFIG_SCSI=y +CONFIG_MD=y +CONFIG_BLK_DEV_DM=y +CONFIG_DM_CRYPT=y +CONFIG_DM_UEVENT=y +CONFIG_DM_VERITY=y +CONFIG_DM_VERITY_FEC=y +CONFIG_NETDEVICES=y +CONFIG_TUN=y +CONFIG_VIRTIO_NET=y +CONFIG_PPP=y +CONFIG_PPP_BSDCOMP=y +CONFIG_PPP_DEFLATE=y +CONFIG_PPP_MPPE=y +# CONFIG_INPUT_MOUSEDEV is not set +CONFIG_INPUT_EVDEV=y +# CONFIG_KEYBOARD_ATKBD is not set +CONFIG_KEYBOARD_GOLDFISH_EVENTS=y +# CONFIG_INPUT_MOUSE is not set +CONFIG_INPUT_JOYSTICK=y +CONFIG_INPUT_TABLET=y +CONFIG_INPUT_MISC=y +CONFIG_INPUT_UINPUT=y +CONFIG_INPUT_GPIO=y +# CONFIG_SERIO_I8042 is not set +CONFIG_SERIO_LIBPS2=y +# CONFIG_VT is not set +# CONFIG_LEGACY_PTYS is not set +CONFIG_GOLDFISH_TTY=y +# CONFIG_DEVMEM is not set +# CONFIG_DEVKMEM is not set +CONFIG_VIRTIO_CONSOLE=y +CONFIG_HW_RANDOM=y +CONFIG_HW_RANDOM_VIRTIO=y +CONFIG_BATTERY_GOLDFISH=y +CONFIG_POWER_RESET=y +CONFIG_POWER_RESET_SYSCON=y +CONFIG_POWER_RESET_SYSCON_POWEROFF=y +# CONFIG_HWMON is not set +CONFIG_MEDIA_SUPPORT=y +CONFIG_FB=y +CONFIG_FB_GOLDFISH=y +CONFIG_BACKLIGHT_LCD_SUPPORT=y +CONFIG_SOUND=y +CONFIG_SND=y +CONFIG_HIDRAW=y +CONFIG_UHID=y +CONFIG_HID_A4TECH=y +CONFIG_HID_ACRUX=y +CONFIG_HID_ACRUX_FF=y +CONFIG_HID_APPLE=y +CONFIG_HID_BELKIN=y +CONFIG_HID_CHERRY=y +CONFIG_HID_CHICONY=y +CONFIG_HID_PRODIKEYS=y +CONFIG_HID_CYPRESS=y +CONFIG_HID_DRAGONRISE=y +CONFIG_DRAGONRISE_FF=y +CONFIG_HID_EMS_FF=y +CONFIG_HID_ELECOM=y +CONFIG_HID_EZKEY=y +CONFIG_HID_KEYTOUCH=y +CONFIG_HID_KYE=y +CONFIG_HID_WALTOP=y +CONFIG_HID_GYRATION=y +CONFIG_HID_TWINHAN=y +CONFIG_HID_KENSINGTON=y +CONFIG_HID_LCPOWER=y +CONFIG_HID_LOGITECH=y +CONFIG_HID_LOGITECH_DJ=y +CONFIG_LOGITECH_FF=y +CONFIG_LOGIRUMBLEPAD2_FF=y +CONFIG_LOGIG940_FF=y +# CONFIG_LOGIWHEELS_FF is not set +CONFIG_HID_MAGICMOUSE=y +CONFIG_HID_MICROSOFT=y +CONFIG_HID_MONTEREY=y +CONFIG_HID_MULTITOUCH=y +CONFIG_HID_ORTEK=y +CONFIG_HID_PANTHERLORD=y +CONFIG_PANTHERLORD_FF=y +CONFIG_HID_PETALYNX=y +CONFIG_HID_PICOLCD=y +CONFIG_HID_PRIMAX=y +CONFIG_HID_SAITEK=y +CONFIG_HID_SAMSUNG=y +CONFIG_HID_SPEEDLINK=y +CONFIG_HID_SUNPLUS=y +CONFIG_HID_GREENASIA=y +CONFIG_GREENASIA_FF=y +CONFIG_HID_SMARTJOYPLUS=y +CONFIG_SMARTJOYPLUS_FF=y +CONFIG_HID_TIVO=y +CONFIG_HID_TOPSEED=y +CONFIG_HID_THRUSTMASTER=y +CONFIG_HID_WACOM=y +CONFIG_HID_WIIMOTE=y +CONFIG_HID_ZEROPLUS=y +CONFIG_HID_ZYDACRON=y +# CONFIG_USB_SUPPORT is not set +CONFIG_RTC_CLASS=y +CONFIG_RTC_DRV_GOLDFISH=y +CONFIG_VIRTIO_MMIO=y +CONFIG_VIRTIO_MMIO_CMDLINE_DEVICES=y +CONFIG_STAGING=y +CONFIG_ASHMEM=y +CONFIG_ANDROID_LOW_MEMORY_KILLER=y +CONFIG_SYNC=y +CONFIG_ION=y +CONFIG_GOLDFISH_AUDIO=y +CONFIG_GOLDFISH_SYNC=y +# CONFIG_MIPS_PLATFORM_DEVICES is not set +CONFIG_GOLDFISH=y +CONFIG_GOLDFISH_PIPE=y +# CONFIG_IOMMU_SUPPORT is not set +CONFIG_GOLDFISH_PIC=y +CONFIG_ANDROID=y +CONFIG_ANDROID_BINDER_IPC=y +CONFIG_EXT4_FS=y +CONFIG_EXT4_FS_POSIX_ACL=y +CONFIG_EXT4_FS_SECURITY=y +CONFIG_EXT4_ENCRYPTION=y +CONFIG_FANOTIFY=y +CONFIG_QUOTA=y +CONFIG_QFMT_V2=y +CONFIG_FUSE_FS=y +CONFIG_CUSE=y +CONFIG_OVERLAY_FS=y +CONFIG_MSDOS_FS=y +CONFIG_VFAT_FS=y +CONFIG_TMPFS=y +CONFIG_TMPFS_POSIX_ACL=y +CONFIG_CONFIGFS_FS=y +CONFIG_SDCARD_FS=y +CONFIG_PRINTK_TIME=y +CONFIG_DEBUG_INFO=y +CONFIG_DEBUG_INFO_REDUCED=y +CONFIG_DEBUG_FS=y +CONFIG_MAGIC_SYSRQ=y +CONFIG_PANIC_TIMEOUT=5 +# CONFIG_SCHED_DEBUG is not set +CONFIG_SCHEDSTATS=y +CONFIG_TIMER_STATS=y +# CONFIG_FTRACE is not set +CONFIG_CMDLINE_BOOL=y +CONFIG_CMDLINE="earlycon" +CONFIG_SECURITY=y +CONFIG_SECURITY_NETWORK=y +CONFIG_SECURITY_SELINUX=y +# CONFIG_XZ_DEC_X86 is not set +# CONFIG_XZ_DEC_POWERPC is not set +# CONFIG_XZ_DEC_IA64 is not set +# CONFIG_XZ_DEC_ARM is not set +# CONFIG_XZ_DEC_ARMTHUMB is not set +# CONFIG_XZ_DEC_SPARC is not set diff --git a/arch/mips/configs/ranchu32r6_defconfig b/arch/mips/configs/ranchu32r6_defconfig new file mode 100644 index 000000000000..4df031b26a5d --- /dev/null +++ b/arch/mips/configs/ranchu32r6_defconfig @@ -0,0 +1,313 @@ +CONFIG_MIPS_GENERIC=y +CONFIG_VIRT_BOARD_RANCHU=y +CONFIG_CPU_LITTLE_ENDIAN=y +CONFIG_CPU_MIPS32_R6=y +CONFIG_MIPS_CPS=y +CONFIG_CPU_HAS_MSA=y +CONFIG_HIGHMEM=y +CONFIG_KSM=y +CONFIG_CMA=y +CONFIG_NR_CPUS=16 +CONFIG_PREEMPT=y +# CONFIG_USELIB is not set +CONFIG_AUDIT=y +CONFIG_NO_HZ=y +CONFIG_HIGH_RES_TIMERS=y +CONFIG_TASKSTATS=y +CONFIG_TASK_DELAY_ACCT=y +CONFIG_TASK_XACCT=y +CONFIG_TASK_IO_ACCOUNTING=y +CONFIG_IKCONFIG=y +CONFIG_IKCONFIG_PROC=y +CONFIG_CGROUP_DEBUG=y +CONFIG_CGROUP_FREEZER=y +CONFIG_CGROUP_PIDS=y +CONFIG_CGROUP_DEVICE=y +CONFIG_CPUSETS=y +CONFIG_CGROUP_CPUACCT=y +CONFIG_MEMCG=y +CONFIG_MEMCG_SWAP=y +CONFIG_CFS_BANDWIDTH=y +CONFIG_RT_GROUP_SCHED=y +CONFIG_BLK_CGROUP=y +CONFIG_NAMESPACES=y +CONFIG_USER_NS=y +CONFIG_SCHED_AUTOGROUP=y +CONFIG_BLK_DEV_INITRD=y +CONFIG_KALLSYMS_ALL=y +CONFIG_BPF_SYSCALL=y +CONFIG_USERFAULTFD=y +CONFIG_EMBEDDED=y +CONFIG_PERF_EVENTS=y +# CONFIG_SLUB_DEBUG is not set +# CONFIG_COMPAT_BRK is not set +CONFIG_CC_STACKPROTECTOR_REGULAR=y +CONFIG_MODULES=y +CONFIG_MODULE_UNLOAD=y +CONFIG_MODVERSIONS=y +# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set +CONFIG_PM_AUTOSLEEP=y +CONFIG_PM_WAKELOCKS=y +CONFIG_PM_WAKELOCKS_LIMIT=0 +# CONFIG_PM_WAKELOCKS_GC is not set +CONFIG_PM_DEBUG=y +CONFIG_NET=y +CONFIG_PACKET=y +CONFIG_UNIX=y +CONFIG_XFRM_USER=y +CONFIG_NET_KEY=y +CONFIG_INET=y +CONFIG_IP_MULTICAST=y +CONFIG_IP_ADVANCED_ROUTER=y +CONFIG_IP_MULTIPLE_TABLES=y +CONFIG_INET_ESP=y +# CONFIG_INET_LRO is not set +CONFIG_INET_DIAG_DESTROY=y +CONFIG_IPV6_ROUTER_PREF=y +CONFIG_IPV6_ROUTE_INFO=y +CONFIG_IPV6_OPTIMISTIC_DAD=y +CONFIG_INET6_AH=y +CONFIG_INET6_ESP=y +CONFIG_INET6_IPCOMP=y +CONFIG_IPV6_MIP6=y +CONFIG_IPV6_MULTIPLE_TABLES=y +CONFIG_NETFILTER=y +CONFIG_NF_CONNTRACK=y +CONFIG_NF_CONNTRACK_SECMARK=y +CONFIG_NF_CONNTRACK_EVENTS=y +CONFIG_NF_CT_PROTO_DCCP=y +CONFIG_NF_CT_PROTO_SCTP=y +CONFIG_NF_CT_PROTO_UDPLITE=y +CONFIG_NF_CONNTRACK_AMANDA=y +CONFIG_NF_CONNTRACK_FTP=y +CONFIG_NF_CONNTRACK_H323=y +CONFIG_NF_CONNTRACK_IRC=y +CONFIG_NF_CONNTRACK_NETBIOS_NS=y +CONFIG_NF_CONNTRACK_PPTP=y +CONFIG_NF_CONNTRACK_SANE=y +CONFIG_NF_CONNTRACK_TFTP=y +CONFIG_NF_CT_NETLINK=y +CONFIG_NETFILTER_XT_TARGET_CLASSIFY=y +CONFIG_NETFILTER_XT_TARGET_CONNMARK=y +CONFIG_NETFILTER_XT_TARGET_CONNSECMARK=y +CONFIG_NETFILTER_XT_TARGET_IDLETIMER=y +CONFIG_NETFILTER_XT_TARGET_MARK=y +CONFIG_NETFILTER_XT_TARGET_NFLOG=y +CONFIG_NETFILTER_XT_TARGET_NFQUEUE=y +CONFIG_NETFILTER_XT_TARGET_TPROXY=y +CONFIG_NETFILTER_XT_TARGET_TRACE=y +CONFIG_NETFILTER_XT_TARGET_SECMARK=y +CONFIG_NETFILTER_XT_TARGET_TCPMSS=y +CONFIG_NETFILTER_XT_MATCH_COMMENT=y +CONFIG_NETFILTER_XT_MATCH_CONNLIMIT=y +CONFIG_NETFILTER_XT_MATCH_CONNMARK=y +CONFIG_NETFILTER_XT_MATCH_CONNTRACK=y +CONFIG_NETFILTER_XT_MATCH_HASHLIMIT=y +CONFIG_NETFILTER_XT_MATCH_HELPER=y +CONFIG_NETFILTER_XT_MATCH_IPRANGE=y +CONFIG_NETFILTER_XT_MATCH_LENGTH=y +CONFIG_NETFILTER_XT_MATCH_LIMIT=y +CONFIG_NETFILTER_XT_MATCH_MAC=y +CONFIG_NETFILTER_XT_MATCH_MARK=y +CONFIG_NETFILTER_XT_MATCH_POLICY=y +CONFIG_NETFILTER_XT_MATCH_PKTTYPE=y +CONFIG_NETFILTER_XT_MATCH_QUOTA=y +CONFIG_NETFILTER_XT_MATCH_SOCKET=y +CONFIG_NETFILTER_XT_MATCH_STATE=y +CONFIG_NETFILTER_XT_MATCH_STATISTIC=y +CONFIG_NETFILTER_XT_MATCH_STRING=y +CONFIG_NETFILTER_XT_MATCH_TIME=y +CONFIG_NETFILTER_XT_MATCH_U32=y +CONFIG_NF_CONNTRACK_IPV4=y +CONFIG_IP_NF_IPTABLES=y +CONFIG_IP_NF_MATCH_AH=y +CONFIG_IP_NF_MATCH_ECN=y +CONFIG_IP_NF_MATCH_TTL=y +CONFIG_IP_NF_FILTER=y +CONFIG_IP_NF_TARGET_REJECT=y +CONFIG_IP_NF_NAT=y +CONFIG_IP_NF_TARGET_MASQUERADE=y +CONFIG_IP_NF_TARGET_NETMAP=y +CONFIG_IP_NF_TARGET_REDIRECT=y +CONFIG_IP_NF_MANGLE=y +CONFIG_IP_NF_RAW=y +CONFIG_IP_NF_SECURITY=y +CONFIG_IP_NF_ARPTABLES=y +CONFIG_IP_NF_ARPFILTER=y +CONFIG_IP_NF_ARP_MANGLE=y +CONFIG_NF_CONNTRACK_IPV6=y +CONFIG_IP6_NF_IPTABLES=y +CONFIG_IP6_NF_FILTER=y +CONFIG_IP6_NF_TARGET_REJECT=y +CONFIG_IP6_NF_MANGLE=y +CONFIG_IP6_NF_RAW=y +CONFIG_NET_SCHED=y +CONFIG_NET_SCH_HTB=y +CONFIG_NET_CLS_U32=y +CONFIG_NET_EMATCH=y +CONFIG_NET_EMATCH_U32=y +CONFIG_NET_CLS_ACT=y +CONFIG_DNS_RESOLVER=y +CONFIG_CFG80211=y +CONFIG_DEVTMPFS=y +CONFIG_DEVTMPFS_MOUNT=y +CONFIG_DMA_CMA=y +CONFIG_BLK_DEV_LOOP=y +CONFIG_BLK_DEV_RAM=y +CONFIG_BLK_DEV_RAM_SIZE=8192 +CONFIG_VIRTIO_BLK=y +CONFIG_SCSI=y +CONFIG_MD=y +CONFIG_BLK_DEV_DM=y +CONFIG_DM_CRYPT=y +CONFIG_DM_UEVENT=y +CONFIG_DM_VERITY=y +CONFIG_DM_VERITY_FEC=y +CONFIG_NETDEVICES=y +CONFIG_TUN=y +CONFIG_VIRTIO_NET=y +CONFIG_PPP=y +CONFIG_PPP_BSDCOMP=y +CONFIG_PPP_DEFLATE=y +CONFIG_PPP_MPPE=y +# CONFIG_INPUT_MOUSEDEV is not set +CONFIG_INPUT_EVDEV=y +# CONFIG_KEYBOARD_ATKBD is not set +CONFIG_KEYBOARD_GOLDFISH_EVENTS=y +# CONFIG_INPUT_MOUSE is not set +CONFIG_INPUT_JOYSTICK=y +CONFIG_INPUT_TABLET=y +CONFIG_INPUT_MISC=y +CONFIG_INPUT_UINPUT=y +CONFIG_INPUT_GPIO=y +# CONFIG_SERIO_I8042 is not set +CONFIG_SERIO_LIBPS2=y +# CONFIG_VT is not set +# CONFIG_LEGACY_PTYS is not set +CONFIG_GOLDFISH_TTY=y +# CONFIG_DEVMEM is not set +# CONFIG_DEVKMEM is not set +CONFIG_VIRTIO_CONSOLE=y +CONFIG_HW_RANDOM=y +CONFIG_HW_RANDOM_VIRTIO=y +CONFIG_BATTERY_GOLDFISH=y +CONFIG_POWER_RESET=y +CONFIG_POWER_RESET_SYSCON=y +CONFIG_POWER_RESET_SYSCON_POWEROFF=y +# CONFIG_HWMON is not set +CONFIG_MEDIA_SUPPORT=y +CONFIG_FB=y +CONFIG_FB_GOLDFISH=y +CONFIG_BACKLIGHT_LCD_SUPPORT=y +CONFIG_SOUND=y +CONFIG_SND=y +CONFIG_HIDRAW=y +CONFIG_UHID=y +CONFIG_HID_A4TECH=y +CONFIG_HID_ACRUX=y +CONFIG_HID_ACRUX_FF=y +CONFIG_HID_APPLE=y +CONFIG_HID_BELKIN=y +CONFIG_HID_CHERRY=y +CONFIG_HID_CHICONY=y +CONFIG_HID_PRODIKEYS=y +CONFIG_HID_CYPRESS=y +CONFIG_HID_DRAGONRISE=y +CONFIG_DRAGONRISE_FF=y +CONFIG_HID_EMS_FF=y +CONFIG_HID_ELECOM=y +CONFIG_HID_EZKEY=y +CONFIG_HID_KEYTOUCH=y +CONFIG_HID_KYE=y +CONFIG_HID_WALTOP=y +CONFIG_HID_GYRATION=y +CONFIG_HID_TWINHAN=y +CONFIG_HID_KENSINGTON=y +CONFIG_HID_LCPOWER=y +CONFIG_HID_LOGITECH=y +CONFIG_HID_LOGITECH_DJ=y +CONFIG_LOGITECH_FF=y +CONFIG_LOGIRUMBLEPAD2_FF=y +CONFIG_LOGIG940_FF=y +# CONFIG_LOGIWHEELS_FF is not set +CONFIG_HID_MAGICMOUSE=y +CONFIG_HID_MICROSOFT=y +CONFIG_HID_MONTEREY=y +CONFIG_HID_MULTITOUCH=y +CONFIG_HID_ORTEK=y +CONFIG_HID_PANTHERLORD=y +CONFIG_PANTHERLORD_FF=y +CONFIG_HID_PETALYNX=y +CONFIG_HID_PICOLCD=y +CONFIG_HID_PRIMAX=y +CONFIG_HID_SAITEK=y +CONFIG_HID_SAMSUNG=y +CONFIG_HID_SPEEDLINK=y +CONFIG_HID_SUNPLUS=y +CONFIG_HID_GREENASIA=y +CONFIG_GREENASIA_FF=y +CONFIG_HID_SMARTJOYPLUS=y +CONFIG_SMARTJOYPLUS_FF=y +CONFIG_HID_TIVO=y +CONFIG_HID_TOPSEED=y +CONFIG_HID_THRUSTMASTER=y +CONFIG_HID_WACOM=y +CONFIG_HID_WIIMOTE=y +CONFIG_HID_ZEROPLUS=y +CONFIG_HID_ZYDACRON=y +# CONFIG_USB_SUPPORT is not set +CONFIG_RTC_CLASS=y +CONFIG_RTC_DRV_GOLDFISH=y +CONFIG_VIRTIO_MMIO=y +CONFIG_VIRTIO_MMIO_CMDLINE_DEVICES=y +CONFIG_STAGING=y +CONFIG_ASHMEM=y +CONFIG_ANDROID_LOW_MEMORY_KILLER=y +CONFIG_SYNC=y +CONFIG_ION=y +CONFIG_GOLDFISH_AUDIO=y +CONFIG_GOLDFISH_SYNC=y +# CONFIG_MIPS_PLATFORM_DEVICES is not set +CONFIG_GOLDFISH=y +CONFIG_GOLDFISH_PIPE=y +# CONFIG_IOMMU_SUPPORT is not set +CONFIG_GOLDFISH_PIC=y +CONFIG_ANDROID=y +CONFIG_ANDROID_BINDER_IPC=y +CONFIG_EXT4_FS=y +CONFIG_EXT4_FS_POSIX_ACL=y +CONFIG_EXT4_FS_SECURITY=y +CONFIG_EXT4_ENCRYPTION=y +CONFIG_FANOTIFY=y +CONFIG_QUOTA=y +CONFIG_QFMT_V2=y +CONFIG_FUSE_FS=y +CONFIG_CUSE=y +CONFIG_OVERLAY_FS=y +CONFIG_MSDOS_FS=y +CONFIG_VFAT_FS=y +CONFIG_TMPFS=y +CONFIG_TMPFS_POSIX_ACL=y +CONFIG_CONFIGFS_FS=y +CONFIG_SDCARD_FS=y +CONFIG_PRINTK_TIME=y +CONFIG_DEBUG_INFO=y +CONFIG_DEBUG_INFO_REDUCED=y +CONFIG_DEBUG_FS=y +CONFIG_MAGIC_SYSRQ=y +CONFIG_PANIC_TIMEOUT=5 +# CONFIG_SCHED_DEBUG is not set +CONFIG_SCHEDSTATS=y +CONFIG_TIMER_STATS=y +# CONFIG_FTRACE is not set +CONFIG_CMDLINE_BOOL=y +CONFIG_CMDLINE="earlycon" +CONFIG_SECURITY=y +CONFIG_SECURITY_NETWORK=y +CONFIG_SECURITY_SELINUX=y +# CONFIG_XZ_DEC_X86 is not set +# CONFIG_XZ_DEC_POWERPC is not set +# CONFIG_XZ_DEC_IA64 is not set +# CONFIG_XZ_DEC_ARM is not set +# CONFIG_XZ_DEC_ARMTHUMB is not set +# CONFIG_XZ_DEC_SPARC is not set diff --git a/arch/mips/configs/ranchu64_defconfig b/arch/mips/configs/ranchu64_defconfig new file mode 100644 index 000000000000..35ff3534441c --- /dev/null +++ b/arch/mips/configs/ranchu64_defconfig @@ -0,0 +1,315 @@ +CONFIG_MIPS_GENERIC=y +CONFIG_VIRT_BOARD_RANCHU=y +CONFIG_CPU_LITTLE_ENDIAN=y +CONFIG_CPU_MIPS64_R6=y +CONFIG_64BIT=y +CONFIG_MIPS_CPS=y +CONFIG_CPU_HAS_MSA=y +CONFIG_KSM=y +CONFIG_CMA=y +CONFIG_NR_CPUS=16 +CONFIG_PREEMPT=y +# CONFIG_USELIB is not set +CONFIG_AUDIT=y +CONFIG_NO_HZ=y +CONFIG_HIGH_RES_TIMERS=y +CONFIG_TASKSTATS=y +CONFIG_TASK_DELAY_ACCT=y +CONFIG_TASK_XACCT=y +CONFIG_TASK_IO_ACCOUNTING=y +CONFIG_IKCONFIG=y +CONFIG_IKCONFIG_PROC=y +CONFIG_CGROUP_DEBUG=y +CONFIG_CGROUP_FREEZER=y +CONFIG_CGROUP_PIDS=y +CONFIG_CGROUP_DEVICE=y +CONFIG_CPUSETS=y +CONFIG_CGROUP_CPUACCT=y +CONFIG_MEMCG=y +CONFIG_MEMCG_SWAP=y +CONFIG_CFS_BANDWIDTH=y +CONFIG_RT_GROUP_SCHED=y +CONFIG_BLK_CGROUP=y +CONFIG_NAMESPACES=y +CONFIG_USER_NS=y +CONFIG_SCHED_AUTOGROUP=y +CONFIG_BLK_DEV_INITRD=y +CONFIG_KALLSYMS_ALL=y +CONFIG_BPF_SYSCALL=y +CONFIG_USERFAULTFD=y +CONFIG_EMBEDDED=y +CONFIG_PERF_EVENTS=y +# CONFIG_SLUB_DEBUG is not set +# CONFIG_COMPAT_BRK is not set +CONFIG_CC_STACKPROTECTOR_REGULAR=y +CONFIG_MODULES=y +CONFIG_MODULE_UNLOAD=y +CONFIG_MODVERSIONS=y +# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set +CONFIG_MIPS32_O32=y +CONFIG_MIPS32_N32=y +CONFIG_PM_AUTOSLEEP=y +CONFIG_PM_WAKELOCKS=y +CONFIG_PM_WAKELOCKS_LIMIT=0 +# CONFIG_PM_WAKELOCKS_GC is not set +CONFIG_PM_DEBUG=y +CONFIG_NET=y +CONFIG_PACKET=y +CONFIG_UNIX=y +CONFIG_XFRM_USER=y +CONFIG_NET_KEY=y +CONFIG_INET=y +CONFIG_IP_MULTICAST=y +CONFIG_IP_ADVANCED_ROUTER=y +CONFIG_IP_MULTIPLE_TABLES=y +CONFIG_INET_ESP=y +# CONFIG_INET_LRO is not set +CONFIG_INET_DIAG_DESTROY=y +CONFIG_IPV6_ROUTER_PREF=y +CONFIG_IPV6_ROUTE_INFO=y +CONFIG_IPV6_OPTIMISTIC_DAD=y +CONFIG_INET6_AH=y +CONFIG_INET6_ESP=y +CONFIG_INET6_IPCOMP=y +CONFIG_IPV6_MIP6=y +CONFIG_IPV6_MULTIPLE_TABLES=y +CONFIG_NETFILTER=y +CONFIG_NF_CONNTRACK=y +CONFIG_NF_CONNTRACK_SECMARK=y +CONFIG_NF_CONNTRACK_EVENTS=y +CONFIG_NF_CT_PROTO_DCCP=y +CONFIG_NF_CT_PROTO_SCTP=y +CONFIG_NF_CT_PROTO_UDPLITE=y +CONFIG_NF_CONNTRACK_AMANDA=y +CONFIG_NF_CONNTRACK_FTP=y +CONFIG_NF_CONNTRACK_H323=y +CONFIG_NF_CONNTRACK_IRC=y +CONFIG_NF_CONNTRACK_NETBIOS_NS=y +CONFIG_NF_CONNTRACK_PPTP=y +CONFIG_NF_CONNTRACK_SANE=y +CONFIG_NF_CONNTRACK_TFTP=y +CONFIG_NF_CT_NETLINK=y +CONFIG_NETFILTER_XT_TARGET_CLASSIFY=y +CONFIG_NETFILTER_XT_TARGET_CONNMARK=y +CONFIG_NETFILTER_XT_TARGET_CONNSECMARK=y +CONFIG_NETFILTER_XT_TARGET_IDLETIMER=y +CONFIG_NETFILTER_XT_TARGET_MARK=y +CONFIG_NETFILTER_XT_TARGET_NFLOG=y +CONFIG_NETFILTER_XT_TARGET_NFQUEUE=y +CONFIG_NETFILTER_XT_TARGET_TPROXY=y +CONFIG_NETFILTER_XT_TARGET_TRACE=y +CONFIG_NETFILTER_XT_TARGET_SECMARK=y +CONFIG_NETFILTER_XT_TARGET_TCPMSS=y +CONFIG_NETFILTER_XT_MATCH_COMMENT=y +CONFIG_NETFILTER_XT_MATCH_CONNLIMIT=y +CONFIG_NETFILTER_XT_MATCH_CONNMARK=y +CONFIG_NETFILTER_XT_MATCH_CONNTRACK=y +CONFIG_NETFILTER_XT_MATCH_HASHLIMIT=y +CONFIG_NETFILTER_XT_MATCH_HELPER=y +CONFIG_NETFILTER_XT_MATCH_IPRANGE=y +CONFIG_NETFILTER_XT_MATCH_LENGTH=y +CONFIG_NETFILTER_XT_MATCH_LIMIT=y +CONFIG_NETFILTER_XT_MATCH_MAC=y +CONFIG_NETFILTER_XT_MATCH_MARK=y +CONFIG_NETFILTER_XT_MATCH_POLICY=y +CONFIG_NETFILTER_XT_MATCH_PKTTYPE=y +CONFIG_NETFILTER_XT_MATCH_QUOTA=y +CONFIG_NETFILTER_XT_MATCH_SOCKET=y +CONFIG_NETFILTER_XT_MATCH_STATE=y +CONFIG_NETFILTER_XT_MATCH_STATISTIC=y +CONFIG_NETFILTER_XT_MATCH_STRING=y +CONFIG_NETFILTER_XT_MATCH_TIME=y +CONFIG_NETFILTER_XT_MATCH_U32=y +CONFIG_NF_CONNTRACK_IPV4=y +CONFIG_IP_NF_IPTABLES=y +CONFIG_IP_NF_MATCH_AH=y +CONFIG_IP_NF_MATCH_ECN=y +CONFIG_IP_NF_MATCH_TTL=y +CONFIG_IP_NF_FILTER=y +CONFIG_IP_NF_TARGET_REJECT=y +CONFIG_IP_NF_NAT=y +CONFIG_IP_NF_TARGET_MASQUERADE=y +CONFIG_IP_NF_TARGET_NETMAP=y +CONFIG_IP_NF_TARGET_REDIRECT=y +CONFIG_IP_NF_MANGLE=y +CONFIG_IP_NF_RAW=y +CONFIG_IP_NF_SECURITY=y +CONFIG_IP_NF_ARPTABLES=y +CONFIG_IP_NF_ARPFILTER=y +CONFIG_IP_NF_ARP_MANGLE=y +CONFIG_NF_CONNTRACK_IPV6=y +CONFIG_IP6_NF_IPTABLES=y +CONFIG_IP6_NF_FILTER=y +CONFIG_IP6_NF_TARGET_REJECT=y +CONFIG_IP6_NF_MANGLE=y +CONFIG_IP6_NF_RAW=y +CONFIG_NET_SCHED=y +CONFIG_NET_SCH_HTB=y +CONFIG_NET_CLS_U32=y +CONFIG_NET_EMATCH=y +CONFIG_NET_EMATCH_U32=y +CONFIG_NET_CLS_ACT=y +CONFIG_DNS_RESOLVER=y +CONFIG_CFG80211=y +CONFIG_DEVTMPFS=y +CONFIG_DEVTMPFS_MOUNT=y +CONFIG_DMA_CMA=y +CONFIG_BLK_DEV_LOOP=y +CONFIG_BLK_DEV_RAM=y +CONFIG_BLK_DEV_RAM_SIZE=8192 +CONFIG_VIRTIO_BLK=y +CONFIG_SCSI=y +CONFIG_MD=y +CONFIG_BLK_DEV_DM=y +CONFIG_DM_CRYPT=y +CONFIG_DM_UEVENT=y +CONFIG_DM_VERITY=y +CONFIG_DM_VERITY_FEC=y +CONFIG_NETDEVICES=y +CONFIG_TUN=y +CONFIG_VIRTIO_NET=y +CONFIG_PPP=y +CONFIG_PPP_BSDCOMP=y +CONFIG_PPP_DEFLATE=y +CONFIG_PPP_MPPE=y +# CONFIG_INPUT_MOUSEDEV is not set +CONFIG_INPUT_EVDEV=y +# CONFIG_KEYBOARD_ATKBD is not set +CONFIG_KEYBOARD_GOLDFISH_EVENTS=y +# CONFIG_INPUT_MOUSE is not set +CONFIG_INPUT_JOYSTICK=y +CONFIG_INPUT_TABLET=y +CONFIG_INPUT_MISC=y +CONFIG_INPUT_UINPUT=y +CONFIG_INPUT_GPIO=y +# CONFIG_SERIO_I8042 is not set +CONFIG_SERIO_LIBPS2=y +# CONFIG_VT is not set +# CONFIG_LEGACY_PTYS is not set +CONFIG_GOLDFISH_TTY=y +# CONFIG_DEVMEM is not set +# CONFIG_DEVKMEM is not set +CONFIG_VIRTIO_CONSOLE=y +CONFIG_HW_RANDOM=y +CONFIG_HW_RANDOM_VIRTIO=y +CONFIG_BATTERY_GOLDFISH=y +CONFIG_POWER_RESET=y +CONFIG_POWER_RESET_SYSCON=y +CONFIG_POWER_RESET_SYSCON_POWEROFF=y +# CONFIG_HWMON is not set +CONFIG_MEDIA_SUPPORT=y +CONFIG_FB=y +CONFIG_FB_GOLDFISH=y +CONFIG_BACKLIGHT_LCD_SUPPORT=y +CONFIG_SOUND=y +CONFIG_SND=y +CONFIG_HIDRAW=y +CONFIG_UHID=y +CONFIG_HID_A4TECH=y +CONFIG_HID_ACRUX=y +CONFIG_HID_ACRUX_FF=y +CONFIG_HID_APPLE=y +CONFIG_HID_BELKIN=y +CONFIG_HID_CHERRY=y +CONFIG_HID_CHICONY=y +CONFIG_HID_PRODIKEYS=y +CONFIG_HID_CYPRESS=y +CONFIG_HID_DRAGONRISE=y +CONFIG_DRAGONRISE_FF=y +CONFIG_HID_EMS_FF=y +CONFIG_HID_ELECOM=y +CONFIG_HID_EZKEY=y +CONFIG_HID_KEYTOUCH=y +CONFIG_HID_KYE=y +CONFIG_HID_WALTOP=y +CONFIG_HID_GYRATION=y +CONFIG_HID_TWINHAN=y +CONFIG_HID_KENSINGTON=y +CONFIG_HID_LCPOWER=y +CONFIG_HID_LOGITECH=y +CONFIG_HID_LOGITECH_DJ=y +CONFIG_LOGITECH_FF=y +CONFIG_LOGIRUMBLEPAD2_FF=y +CONFIG_LOGIG940_FF=y +# CONFIG_LOGIWHEELS_FF is not set +CONFIG_HID_MAGICMOUSE=y +CONFIG_HID_MICROSOFT=y +CONFIG_HID_MONTEREY=y +CONFIG_HID_MULTITOUCH=y +CONFIG_HID_ORTEK=y +CONFIG_HID_PANTHERLORD=y +CONFIG_PANTHERLORD_FF=y +CONFIG_HID_PETALYNX=y +CONFIG_HID_PICOLCD=y +CONFIG_HID_PRIMAX=y +CONFIG_HID_SAITEK=y +CONFIG_HID_SAMSUNG=y +CONFIG_HID_SPEEDLINK=y +CONFIG_HID_SUNPLUS=y +CONFIG_HID_GREENASIA=y +CONFIG_GREENASIA_FF=y +CONFIG_HID_SMARTJOYPLUS=y +CONFIG_SMARTJOYPLUS_FF=y +CONFIG_HID_TIVO=y +CONFIG_HID_TOPSEED=y +CONFIG_HID_THRUSTMASTER=y +CONFIG_HID_WACOM=y +CONFIG_HID_WIIMOTE=y +CONFIG_HID_ZEROPLUS=y +CONFIG_HID_ZYDACRON=y +# CONFIG_USB_SUPPORT is not set +CONFIG_RTC_CLASS=y +CONFIG_RTC_DRV_GOLDFISH=y +CONFIG_VIRTIO_MMIO=y +CONFIG_VIRTIO_MMIO_CMDLINE_DEVICES=y +CONFIG_STAGING=y +CONFIG_ASHMEM=y +CONFIG_ANDROID_LOW_MEMORY_KILLER=y +CONFIG_SYNC=y +CONFIG_ION=y +CONFIG_GOLDFISH_AUDIO=y +CONFIG_GOLDFISH_SYNC=y +# CONFIG_MIPS_PLATFORM_DEVICES is not set +CONFIG_GOLDFISH=y +CONFIG_GOLDFISH_PIPE=y +# CONFIG_IOMMU_SUPPORT is not set +CONFIG_GOLDFISH_PIC=y +CONFIG_ANDROID=y +CONFIG_ANDROID_BINDER_IPC=y +CONFIG_EXT4_FS=y +CONFIG_EXT4_FS_POSIX_ACL=y +CONFIG_EXT4_FS_SECURITY=y +CONFIG_EXT4_ENCRYPTION=y +CONFIG_FANOTIFY=y +CONFIG_QUOTA=y +CONFIG_QFMT_V2=y +CONFIG_FUSE_FS=y +CONFIG_CUSE=y +CONFIG_OVERLAY_FS=y +CONFIG_MSDOS_FS=y +CONFIG_VFAT_FS=y +CONFIG_TMPFS=y +CONFIG_TMPFS_POSIX_ACL=y +CONFIG_CONFIGFS_FS=y +CONFIG_SDCARD_FS=y +CONFIG_PRINTK_TIME=y +CONFIG_DEBUG_INFO=y +CONFIG_DEBUG_INFO_REDUCED=y +CONFIG_DEBUG_FS=y +CONFIG_MAGIC_SYSRQ=y +CONFIG_PANIC_TIMEOUT=5 +# CONFIG_SCHED_DEBUG is not set +CONFIG_SCHEDSTATS=y +CONFIG_TIMER_STATS=y +# CONFIG_FTRACE is not set +CONFIG_CMDLINE_BOOL=y +CONFIG_CMDLINE="earlycon" +CONFIG_SECURITY=y +CONFIG_SECURITY_NETWORK=y +CONFIG_SECURITY_SELINUX=y +# CONFIG_XZ_DEC_X86 is not set +# CONFIG_XZ_DEC_POWERPC is not set +# CONFIG_XZ_DEC_IA64 is not set +# CONFIG_XZ_DEC_ARM is not set +# CONFIG_XZ_DEC_ARMTHUMB is not set +# CONFIG_XZ_DEC_SPARC is not set diff --git a/arch/mips/configs/ranchu_defconfig b/arch/mips/configs/ranchu_defconfig new file mode 100644 index 000000000000..266a11b66c78 --- /dev/null +++ b/arch/mips/configs/ranchu_defconfig @@ -0,0 +1,312 @@ +CONFIG_MIPS_GENERIC=y +CONFIG_VIRT_BOARD_RANCHU=y +CONFIG_CPU_LITTLE_ENDIAN=y +CONFIG_MIPS_CPS=y +CONFIG_HIGHMEM=y +CONFIG_KSM=y +CONFIG_CMA=y +CONFIG_NR_CPUS=16 +CONFIG_PREEMPT=y +CONFIG_MIPS_O32_FP64_SUPPORT=y +# CONFIG_USELIB is not set +CONFIG_AUDIT=y +CONFIG_NO_HZ=y +CONFIG_HIGH_RES_TIMERS=y +CONFIG_TASKSTATS=y +CONFIG_TASK_DELAY_ACCT=y +CONFIG_TASK_XACCT=y +CONFIG_TASK_IO_ACCOUNTING=y +CONFIG_IKCONFIG=y +CONFIG_IKCONFIG_PROC=y +CONFIG_CGROUP_DEBUG=y +CONFIG_CGROUP_FREEZER=y +CONFIG_CGROUP_PIDS=y +CONFIG_CGROUP_DEVICE=y +CONFIG_CPUSETS=y +CONFIG_CGROUP_CPUACCT=y +CONFIG_MEMCG=y +CONFIG_MEMCG_SWAP=y +CONFIG_CFS_BANDWIDTH=y +CONFIG_RT_GROUP_SCHED=y +CONFIG_BLK_CGROUP=y +CONFIG_NAMESPACES=y +CONFIG_USER_NS=y +CONFIG_SCHED_AUTOGROUP=y +CONFIG_BLK_DEV_INITRD=y +CONFIG_KALLSYMS_ALL=y +CONFIG_BPF_SYSCALL=y +CONFIG_USERFAULTFD=y +CONFIG_EMBEDDED=y +CONFIG_PERF_EVENTS=y +# CONFIG_SLUB_DEBUG is not set +# CONFIG_COMPAT_BRK is not set +CONFIG_CC_STACKPROTECTOR_REGULAR=y +CONFIG_MODULES=y +CONFIG_MODULE_UNLOAD=y +CONFIG_MODVERSIONS=y +# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set +CONFIG_PM_AUTOSLEEP=y +CONFIG_PM_WAKELOCKS=y +CONFIG_PM_WAKELOCKS_LIMIT=0 +# CONFIG_PM_WAKELOCKS_GC is not set +CONFIG_PM_DEBUG=y +CONFIG_NET=y +CONFIG_PACKET=y +CONFIG_UNIX=y +CONFIG_XFRM_USER=y +CONFIG_NET_KEY=y +CONFIG_INET=y +CONFIG_IP_MULTICAST=y +CONFIG_IP_ADVANCED_ROUTER=y +CONFIG_IP_MULTIPLE_TABLES=y +CONFIG_INET_ESP=y +# CONFIG_INET_LRO is not set +CONFIG_INET_DIAG_DESTROY=y +CONFIG_IPV6_ROUTER_PREF=y +CONFIG_IPV6_ROUTE_INFO=y +CONFIG_IPV6_OPTIMISTIC_DAD=y +CONFIG_INET6_AH=y +CONFIG_INET6_ESP=y +CONFIG_INET6_IPCOMP=y +CONFIG_IPV6_MIP6=y +CONFIG_IPV6_MULTIPLE_TABLES=y +CONFIG_NETFILTER=y +CONFIG_NF_CONNTRACK=y +CONFIG_NF_CONNTRACK_SECMARK=y +CONFIG_NF_CONNTRACK_EVENTS=y +CONFIG_NF_CT_PROTO_DCCP=y +CONFIG_NF_CT_PROTO_SCTP=y +CONFIG_NF_CT_PROTO_UDPLITE=y +CONFIG_NF_CONNTRACK_AMANDA=y +CONFIG_NF_CONNTRACK_FTP=y +CONFIG_NF_CONNTRACK_H323=y +CONFIG_NF_CONNTRACK_IRC=y +CONFIG_NF_CONNTRACK_NETBIOS_NS=y +CONFIG_NF_CONNTRACK_PPTP=y +CONFIG_NF_CONNTRACK_SANE=y +CONFIG_NF_CONNTRACK_TFTP=y +CONFIG_NF_CT_NETLINK=y +CONFIG_NETFILTER_XT_TARGET_CLASSIFY=y +CONFIG_NETFILTER_XT_TARGET_CONNMARK=y +CONFIG_NETFILTER_XT_TARGET_CONNSECMARK=y +CONFIG_NETFILTER_XT_TARGET_IDLETIMER=y +CONFIG_NETFILTER_XT_TARGET_MARK=y +CONFIG_NETFILTER_XT_TARGET_NFLOG=y +CONFIG_NETFILTER_XT_TARGET_NFQUEUE=y +CONFIG_NETFILTER_XT_TARGET_TPROXY=y +CONFIG_NETFILTER_XT_TARGET_TRACE=y +CONFIG_NETFILTER_XT_TARGET_SECMARK=y +CONFIG_NETFILTER_XT_TARGET_TCPMSS=y +CONFIG_NETFILTER_XT_MATCH_COMMENT=y +CONFIG_NETFILTER_XT_MATCH_CONNLIMIT=y +CONFIG_NETFILTER_XT_MATCH_CONNMARK=y +CONFIG_NETFILTER_XT_MATCH_CONNTRACK=y +CONFIG_NETFILTER_XT_MATCH_HASHLIMIT=y +CONFIG_NETFILTER_XT_MATCH_HELPER=y +CONFIG_NETFILTER_XT_MATCH_IPRANGE=y +CONFIG_NETFILTER_XT_MATCH_LENGTH=y +CONFIG_NETFILTER_XT_MATCH_LIMIT=y +CONFIG_NETFILTER_XT_MATCH_MAC=y +CONFIG_NETFILTER_XT_MATCH_MARK=y +CONFIG_NETFILTER_XT_MATCH_POLICY=y +CONFIG_NETFILTER_XT_MATCH_PKTTYPE=y +CONFIG_NETFILTER_XT_MATCH_QUOTA=y +CONFIG_NETFILTER_XT_MATCH_SOCKET=y +CONFIG_NETFILTER_XT_MATCH_STATE=y +CONFIG_NETFILTER_XT_MATCH_STATISTIC=y +CONFIG_NETFILTER_XT_MATCH_STRING=y +CONFIG_NETFILTER_XT_MATCH_TIME=y +CONFIG_NETFILTER_XT_MATCH_U32=y +CONFIG_NF_CONNTRACK_IPV4=y +CONFIG_IP_NF_IPTABLES=y +CONFIG_IP_NF_MATCH_AH=y +CONFIG_IP_NF_MATCH_ECN=y +CONFIG_IP_NF_MATCH_TTL=y +CONFIG_IP_NF_FILTER=y +CONFIG_IP_NF_TARGET_REJECT=y +CONFIG_IP_NF_NAT=y +CONFIG_IP_NF_TARGET_MASQUERADE=y +CONFIG_IP_NF_TARGET_NETMAP=y +CONFIG_IP_NF_TARGET_REDIRECT=y +CONFIG_IP_NF_MANGLE=y +CONFIG_IP_NF_RAW=y +CONFIG_IP_NF_SECURITY=y +CONFIG_IP_NF_ARPTABLES=y +CONFIG_IP_NF_ARPFILTER=y +CONFIG_IP_NF_ARP_MANGLE=y +CONFIG_NF_CONNTRACK_IPV6=y +CONFIG_IP6_NF_IPTABLES=y +CONFIG_IP6_NF_FILTER=y +CONFIG_IP6_NF_TARGET_REJECT=y +CONFIG_IP6_NF_MANGLE=y +CONFIG_IP6_NF_RAW=y +CONFIG_NET_SCHED=y +CONFIG_NET_SCH_HTB=y +CONFIG_NET_CLS_U32=y +CONFIG_NET_EMATCH=y +CONFIG_NET_EMATCH_U32=y +CONFIG_NET_CLS_ACT=y +CONFIG_DNS_RESOLVER=y +CONFIG_CFG80211=y +CONFIG_DEVTMPFS=y +CONFIG_DEVTMPFS_MOUNT=y +CONFIG_DMA_CMA=y +CONFIG_BLK_DEV_LOOP=y +CONFIG_BLK_DEV_RAM=y +CONFIG_BLK_DEV_RAM_SIZE=8192 +CONFIG_VIRTIO_BLK=y +CONFIG_SCSI=y +CONFIG_MD=y +CONFIG_BLK_DEV_DM=y +CONFIG_DM_CRYPT=y +CONFIG_DM_UEVENT=y +CONFIG_DM_VERITY=y +CONFIG_DM_VERITY_FEC=y +CONFIG_NETDEVICES=y +CONFIG_TUN=y +CONFIG_VIRTIO_NET=y +CONFIG_PPP=y +CONFIG_PPP_BSDCOMP=y +CONFIG_PPP_DEFLATE=y +CONFIG_PPP_MPPE=y +# CONFIG_INPUT_MOUSEDEV is not set +CONFIG_INPUT_EVDEV=y +# CONFIG_KEYBOARD_ATKBD is not set +CONFIG_KEYBOARD_GOLDFISH_EVENTS=y +# CONFIG_INPUT_MOUSE is not set +CONFIG_INPUT_JOYSTICK=y +CONFIG_INPUT_TABLET=y +CONFIG_INPUT_MISC=y +CONFIG_INPUT_UINPUT=y +CONFIG_INPUT_GPIO=y +# CONFIG_SERIO_I8042 is not set +CONFIG_SERIO_LIBPS2=y +# CONFIG_VT is not set +# CONFIG_LEGACY_PTYS is not set +CONFIG_GOLDFISH_TTY=y +# CONFIG_DEVMEM is not set +# CONFIG_DEVKMEM is not set +CONFIG_VIRTIO_CONSOLE=y +CONFIG_HW_RANDOM=y +CONFIG_HW_RANDOM_VIRTIO=y +CONFIG_BATTERY_GOLDFISH=y +CONFIG_POWER_RESET=y +CONFIG_POWER_RESET_SYSCON=y +CONFIG_POWER_RESET_SYSCON_POWEROFF=y +# CONFIG_HWMON is not set +CONFIG_MEDIA_SUPPORT=y +CONFIG_FB=y +CONFIG_FB_GOLDFISH=y +CONFIG_BACKLIGHT_LCD_SUPPORT=y +CONFIG_SOUND=y +CONFIG_SND=y +CONFIG_HIDRAW=y +CONFIG_UHID=y +CONFIG_HID_A4TECH=y +CONFIG_HID_ACRUX=y +CONFIG_HID_ACRUX_FF=y +CONFIG_HID_APPLE=y +CONFIG_HID_BELKIN=y +CONFIG_HID_CHERRY=y +CONFIG_HID_CHICONY=y +CONFIG_HID_PRODIKEYS=y +CONFIG_HID_CYPRESS=y +CONFIG_HID_DRAGONRISE=y +CONFIG_DRAGONRISE_FF=y +CONFIG_HID_EMS_FF=y +CONFIG_HID_ELECOM=y +CONFIG_HID_EZKEY=y +CONFIG_HID_KEYTOUCH=y +CONFIG_HID_KYE=y +CONFIG_HID_WALTOP=y +CONFIG_HID_GYRATION=y +CONFIG_HID_TWINHAN=y +CONFIG_HID_KENSINGTON=y +CONFIG_HID_LCPOWER=y +CONFIG_HID_LOGITECH=y +CONFIG_HID_LOGITECH_DJ=y +CONFIG_LOGITECH_FF=y +CONFIG_LOGIRUMBLEPAD2_FF=y +CONFIG_LOGIG940_FF=y +# CONFIG_LOGIWHEELS_FF is not set +CONFIG_HID_MAGICMOUSE=y +CONFIG_HID_MICROSOFT=y +CONFIG_HID_MONTEREY=y +CONFIG_HID_MULTITOUCH=y +CONFIG_HID_ORTEK=y +CONFIG_HID_PANTHERLORD=y +CONFIG_PANTHERLORD_FF=y +CONFIG_HID_PETALYNX=y +CONFIG_HID_PICOLCD=y +CONFIG_HID_PRIMAX=y +CONFIG_HID_SAITEK=y +CONFIG_HID_SAMSUNG=y +CONFIG_HID_SPEEDLINK=y +CONFIG_HID_SUNPLUS=y +CONFIG_HID_GREENASIA=y +CONFIG_GREENASIA_FF=y +CONFIG_HID_SMARTJOYPLUS=y +CONFIG_SMARTJOYPLUS_FF=y +CONFIG_HID_TIVO=y +CONFIG_HID_TOPSEED=y +CONFIG_HID_THRUSTMASTER=y +CONFIG_HID_WACOM=y +CONFIG_HID_WIIMOTE=y +CONFIG_HID_ZEROPLUS=y +CONFIG_HID_ZYDACRON=y +# CONFIG_USB_SUPPORT is not set +CONFIG_RTC_CLASS=y +CONFIG_RTC_DRV_GOLDFISH=y +CONFIG_VIRTIO_MMIO=y +CONFIG_VIRTIO_MMIO_CMDLINE_DEVICES=y +CONFIG_STAGING=y +CONFIG_ASHMEM=y +CONFIG_ANDROID_LOW_MEMORY_KILLER=y +CONFIG_SYNC=y +CONFIG_ION=y +CONFIG_GOLDFISH_AUDIO=y +CONFIG_GOLDFISH_SYNC=y +# CONFIG_MIPS_PLATFORM_DEVICES is not set +CONFIG_GOLDFISH=y +CONFIG_GOLDFISH_PIPE=y +# CONFIG_IOMMU_SUPPORT is not set +CONFIG_GOLDFISH_PIC=y +CONFIG_ANDROID=y +CONFIG_ANDROID_BINDER_IPC=y +CONFIG_EXT4_FS=y +CONFIG_EXT4_FS_POSIX_ACL=y +CONFIG_EXT4_FS_SECURITY=y +CONFIG_EXT4_ENCRYPTION=y +CONFIG_FANOTIFY=y +CONFIG_QUOTA=y +CONFIG_QFMT_V2=y +CONFIG_FUSE_FS=y +CONFIG_CUSE=y +CONFIG_OVERLAY_FS=y +CONFIG_MSDOS_FS=y +CONFIG_VFAT_FS=y +CONFIG_TMPFS=y +CONFIG_TMPFS_POSIX_ACL=y +CONFIG_CONFIGFS_FS=y +CONFIG_SDCARD_FS=y +CONFIG_PRINTK_TIME=y +CONFIG_DEBUG_INFO=y +CONFIG_DEBUG_INFO_REDUCED=y +CONFIG_DEBUG_FS=y +CONFIG_MAGIC_SYSRQ=y +CONFIG_PANIC_TIMEOUT=5 +# CONFIG_SCHED_DEBUG is not set +CONFIG_SCHEDSTATS=y +CONFIG_TIMER_STATS=y +# CONFIG_FTRACE is not set +CONFIG_CMDLINE_BOOL=y +CONFIG_CMDLINE="earlycon noexec=on" +CONFIG_SECURITY=y +CONFIG_SECURITY_NETWORK=y +CONFIG_SECURITY_SELINUX=y +# CONFIG_XZ_DEC_X86 is not set +# CONFIG_XZ_DEC_POWERPC is not set +# CONFIG_XZ_DEC_IA64 is not set +# CONFIG_XZ_DEC_ARM is not set +# CONFIG_XZ_DEC_ARMTHUMB is not set +# CONFIG_XZ_DEC_SPARC is not set diff --git a/arch/mips/dec/int-handler.S b/arch/mips/dec/int-handler.S index 554d1da97743..1910223a9c02 100644 --- a/arch/mips/dec/int-handler.S +++ b/arch/mips/dec/int-handler.S @@ -5,7 +5,7 @@ * Written by Ralf Baechle and Andreas Busse, modified for DECstation * support by Paul Antoine and Harald Koerfgen. * - * completly rewritten: + * completely rewritten: * Copyright (C) 1998 Harald Koerfgen * * Rewritten extensively for controller-driven IRQ support diff --git a/arch/mips/fw/arc/memory.c b/arch/mips/fw/arc/memory.c index 5537b94572b2..0d75b5a0bad4 100644 --- a/arch/mips/fw/arc/memory.c +++ b/arch/mips/fw/arc/memory.c @@ -9,7 +9,7 @@ * PROM library functions for acquiring/using memory descriptors given to us * from the ARCS firmware. This is only used when CONFIG_ARC_MEMORY is set * because on some machines like SGI IP27 the ARC memory configuration data - * completly bogus and alternate easier to use mechanisms are available. + * completely bogus and alternate easier to use mechanisms are available. */ #include <linux/init.h> #include <linux/kernel.h> diff --git a/arch/mips/generic/Kconfig b/arch/mips/generic/Kconfig new file mode 100644 index 000000000000..80e1c72dfd50 --- /dev/null +++ b/arch/mips/generic/Kconfig @@ -0,0 +1,22 @@ +if MIPS_GENERIC + +config LEGACY_BOARDS + bool + help + Select this from your board if the board must use a legacy, non-UHI, + boot protocol. This will cause the kernel to scan through the list of + supported machines calling their detect functions in turn if the + kernel is booted without being provided with an FDT via the UHI + boot protocol. + +config VIRT_BOARD_RANCHU + bool "Support Ranchu platform for Android emulator" + help + This enables support for the platform used by Android emulator. + + Ranchu platform consists of a set of virtual devices. This platform + enables emulation of variety of virtual configurations while using + Android emulator. Android emulator is based on Qemu, and contains + the support for the same set of virtual devices. + +endif diff --git a/arch/mips/generic/Makefile b/arch/mips/generic/Makefile new file mode 100644 index 000000000000..bdaa5b22dc36 --- /dev/null +++ b/arch/mips/generic/Makefile @@ -0,0 +1,15 @@ +# +# Copyright (C) 2016 Imagination Technologies +# Author: Paul Burton <paul.burton@imgtec.com> +# +# This program is free software; you can redistribute it and/or modify it +# under the terms of the GNU General Public License as published by the +# Free Software Foundation; either version 2 of the License, or (at your +# option) any later version. +# + +obj-y += init.o +obj-y += irq.o +obj-y += proc.o + +obj-$(CONFIG_VIRT_BOARD_RANCHU) += board-ranchu.o diff --git a/arch/mips/generic/Platform b/arch/mips/generic/Platform new file mode 100644 index 000000000000..9a30d69e2281 --- /dev/null +++ b/arch/mips/generic/Platform @@ -0,0 +1,14 @@ +# +# Copyright (C) 2016 Imagination Technologies +# Author: Paul Burton <paul.burton@imgtec.com> +# +# This program is free software; you can redistribute it and/or modify it +# under the terms of the GNU General Public License as published by the +# Free Software Foundation; either version 2 of the License, or (at your +# option) any later version. +# + +platform-$(CONFIG_MIPS_GENERIC) += generic/ +cflags-$(CONFIG_MIPS_GENERIC) += -I$(srctree)/arch/mips/include/asm/mach-generic +load-$(CONFIG_MIPS_GENERIC) += 0xffffffff80100000 +all-$(CONFIG_MIPS_GENERIC) := vmlinux.gz.itb diff --git a/arch/mips/generic/board-ranchu.c b/arch/mips/generic/board-ranchu.c new file mode 100644 index 000000000000..ea451b89bb53 --- /dev/null +++ b/arch/mips/generic/board-ranchu.c @@ -0,0 +1,92 @@ +/* + * Support code for virtual Ranchu board for MIPS. + * + * Author: Miodrag Dinic <miodrag.dinic@mips.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + */ + +#include <linux/of_address.h> +#include <linux/types.h> + +#include <asm/machine.h> +#include <asm/mipsregs.h> +#include <asm/time.h> + +#define GOLDFISH_TIMER_LOW 0x00 +#define GOLDFISH_TIMER_HIGH 0x04 + +static __init u64 read_rtc_time(void __iomem *base) +{ + u32 time_low; + u32 time_high; + + /* + * Reading the low address latches the high value + * as well so there is no fear that we may read + * inaccurate high value. + */ + time_low = readl(base + GOLDFISH_TIMER_LOW); + time_high = readl(base + GOLDFISH_TIMER_HIGH); + + return ((u64)time_high << 32) | time_low; +} + +static __init unsigned int ranchu_measure_hpt_freq(void) +{ + u64 rtc_start, rtc_current, rtc_delta; + unsigned int start, count; + struct device_node *np; + void __iomem *rtc_base; + + np = of_find_compatible_node(NULL, NULL, "google,goldfish-rtc"); + if (!np) + panic("%s(): Failed to find 'google,goldfish-rtc' dt node!", + __func__); + + rtc_base = of_iomap(np, 0); + if (!rtc_base) + panic("%s(): Failed to ioremap Goldfish RTC base!", __func__); + + /* + * Poll the nanosecond resolution RTC for one + * second to calibrate the CPU frequency. + */ + rtc_start = read_rtc_time(rtc_base); + start = read_c0_count(); + + do { + rtc_current = read_rtc_time(rtc_base); + rtc_delta = rtc_current - rtc_start; + } while (rtc_delta < NSEC_PER_SEC); + + count = read_c0_count() - start; + + /* + * Make sure the frequency will be a round number. + * Without this correction, the returned value may vary + * between subsequent emulation executions. + * + * TODO: Set this value using device tree. + */ + count += 5000; + count -= count % 10000; + + iounmap(rtc_base); + + return count; +} + +static const struct of_device_id ranchu_of_match[] __initconst = { + { + .compatible = "mti,ranchu", + }, +}; + +MIPS_MACHINE(ranchu) = { + .matches = ranchu_of_match, + .measure_hpt_freq = ranchu_measure_hpt_freq, +}; diff --git a/arch/mips/generic/init.c b/arch/mips/generic/init.c new file mode 100644 index 000000000000..0ea73e845440 --- /dev/null +++ b/arch/mips/generic/init.c @@ -0,0 +1,176 @@ +/* + * Copyright (C) 2016 Imagination Technologies + * Author: Paul Burton <paul.burton@imgtec.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + */ + +#include <linux/clk.h> +#include <linux/clk-provider.h> +#include <linux/clocksource.h> +#include <linux/init.h> +#include <linux/irqchip.h> +#include <linux/of_fdt.h> +#include <linux/of_platform.h> + +#include <asm/fw/fw.h> +#include <asm/irq_cpu.h> +#include <asm/machine.h> +#include <asm/mips-cpc.h> +#include <asm/prom.h> +#include <asm/smp-ops.h> +#include <asm/time.h> + +static __initdata const void *fdt; +static __initdata const struct mips_machine *mach; +static __initdata const void *mach_match_data; + +void __init prom_init(void) +{ + const struct mips_machine *check_mach; + const struct of_device_id *match; + + if ((fw_arg0 == -2) && !fdt_check_header((void *)fw_arg1)) { + /* + * We booted using the UHI boot protocol, so we have been + * provided with the appropriate device tree for the board. + * Make use of it & search for any machine struct based upon + * the root compatible string. + */ + fdt = (void *)fw_arg1; + + for_each_mips_machine(check_mach) { + match = mips_machine_is_compatible(check_mach, fdt); + if (match) { + mach = check_mach; + mach_match_data = match->data; + break; + } + } + } else if (IS_ENABLED(CONFIG_LEGACY_BOARDS)) { + /* + * We weren't booted using the UHI boot protocol, but do + * support some number of boards with legacy boot protocols. + * Attempt to find the right one. + */ + for_each_mips_machine(check_mach) { + if (!check_mach->detect) + continue; + + if (!check_mach->detect()) + continue; + + mach = check_mach; + } + + /* + * If we don't recognise the machine then we can't continue, so + * die here. + */ + BUG_ON(!mach); + + /* Retrieve the machine's FDT */ + fdt = mach->fdt; + } + + BUG_ON(!fdt); +} + +void __init *plat_get_fdt(void) +{ + return (void *)fdt; +} + +void __init plat_mem_setup(void) +{ + if (mach && mach->fixup_fdt) + fdt = mach->fixup_fdt(fdt, mach_match_data); + + strlcpy(arcs_cmdline, boot_command_line, COMMAND_LINE_SIZE); + __dt_setup_arch((void *)fdt); +} + +void __init device_tree_init(void) +{ + int err; + + unflatten_and_copy_device_tree(); + mips_cpc_probe(); + + err = register_cps_smp_ops(); + if (err) + err = register_up_smp_ops(); +} + +void __init plat_time_init(void) +{ + struct device_node *np; + struct clk *clk; + + of_clk_init(NULL); + + if (!cpu_has_counter) { + mips_hpt_frequency = 0; + } else if (mach && mach->measure_hpt_freq) { + mips_hpt_frequency = mach->measure_hpt_freq(); + } else { + np = of_get_cpu_node(0, NULL); + if (!np) { + pr_err("Failed to get CPU node\n"); + return; + } + + clk = of_clk_get(np, 0); + if (IS_ERR(clk)) { + pr_err("Failed to get CPU clock: %ld\n", PTR_ERR(clk)); + return; + } + + mips_hpt_frequency = clk_get_rate(clk); + clk_put(clk); + + switch (boot_cpu_type()) { + case CPU_20KC: + case CPU_25KF: + /* The counter runs at the CPU clock rate */ + break; + default: + /* The counter runs at half the CPU clock rate */ + mips_hpt_frequency /= 2; + break; + } + } + + clocksource_probe(); +} + +void __init arch_init_irq(void) +{ + struct device_node *intc_node; + + intc_node = of_find_compatible_node(NULL, NULL, + "mti,cpu-interrupt-controller"); + if (!cpu_has_veic && !intc_node) + mips_cpu_irq_init(); + + irqchip_init(); +} + +static int __init publish_devices(void) +{ + if (!of_have_populated_dt()) + panic("Device-tree not present"); + + if (of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL)) + panic("Failed to populate DT"); + + return 0; +} +arch_initcall(publish_devices); + +void __init prom_free_prom_memory(void) +{ +} diff --git a/arch/mips/generic/irq.c b/arch/mips/generic/irq.c new file mode 100644 index 000000000000..14064bdd91dd --- /dev/null +++ b/arch/mips/generic/irq.c @@ -0,0 +1,64 @@ +/* + * Copyright (C) 2016 Imagination Technologies + * Author: Paul Burton <paul.burton@imgtec.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + */ + +#include <linux/clk.h> +#include <linux/clk-provider.h> +#include <linux/clocksource.h> +#include <linux/init.h> +#include <linux/irqchip/mips-gic.h> +#include <linux/types.h> + +#include <asm/irq.h> + +int get_c0_fdc_int(void) +{ + int mips_cpu_fdc_irq; + + if (cpu_has_veic) + panic("Unimplemented!"); + else if (gic_present) + mips_cpu_fdc_irq = gic_get_c0_fdc_int(); + else if (cp0_fdc_irq >= 0) + mips_cpu_fdc_irq = MIPS_CPU_IRQ_BASE + cp0_fdc_irq; + else + mips_cpu_fdc_irq = -1; + + return mips_cpu_fdc_irq; +} + +int get_c0_perfcount_int(void) +{ + int mips_cpu_perf_irq; + + if (cpu_has_veic) + panic("Unimplemented!"); + else if (gic_present) + mips_cpu_perf_irq = gic_get_c0_perfcount_int(); + else if (cp0_perfcount_irq >= 0) + mips_cpu_perf_irq = MIPS_CPU_IRQ_BASE + cp0_perfcount_irq; + else + mips_cpu_perf_irq = -1; + + return mips_cpu_perf_irq; +} + +unsigned int get_c0_compare_int(void) +{ + int mips_cpu_timer_irq; + + if (cpu_has_veic) + panic("Unimplemented!"); + else if (gic_present) + mips_cpu_timer_irq = gic_get_c0_compare_int(); + else + mips_cpu_timer_irq = MIPS_CPU_IRQ_BASE + cp0_compare_irq; + + return mips_cpu_timer_irq; +} diff --git a/arch/mips/generic/proc.c b/arch/mips/generic/proc.c new file mode 100644 index 000000000000..42b33250a4a2 --- /dev/null +++ b/arch/mips/generic/proc.c @@ -0,0 +1,29 @@ +/* + * Copyright (C) 2016 Imagination Technologies + * Author: Paul Burton <paul.burton@imgtec.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + */ + +#include <linux/of.h> + +#include <asm/bootinfo.h> + +const char *get_system_type(void) +{ + const char *str; + int err; + + err = of_property_read_string(of_root, "model", &str); + if (!err) + return str; + + err = of_property_read_string_index(of_root, "compatible", 0, &str); + if (!err) + return str; + + return "Unknown"; +} diff --git a/arch/mips/generic/vmlinux.its.S b/arch/mips/generic/vmlinux.its.S new file mode 100644 index 000000000000..f67fbf1c8541 --- /dev/null +++ b/arch/mips/generic/vmlinux.its.S @@ -0,0 +1,31 @@ +/dts-v1/; + +/ { + description = KERNEL_NAME; + #address-cells = <ADDR_CELLS>; + + images { + kernel@0 { + description = KERNEL_NAME; + data = /incbin/(VMLINUX_BINARY); + type = "kernel"; + arch = "mips"; + os = "linux"; + compression = VMLINUX_COMPRESSION; + load = /bits/ ADDR_BITS <VMLINUX_LOAD_ADDRESS>; + entry = /bits/ ADDR_BITS <VMLINUX_ENTRY_ADDRESS>; + hash@0 { + algo = "sha1"; + }; + }; + }; + + configurations { + default = "conf@default"; + + conf@default { + description = "Generic Linux kernel"; + kernel = "kernel@0"; + }; + }; +}; diff --git a/arch/mips/include/asm/bootinfo.h b/arch/mips/include/asm/bootinfo.h index b603804caac5..6effbf5c71ec 100644 --- a/arch/mips/include/asm/bootinfo.h +++ b/arch/mips/include/asm/bootinfo.h @@ -127,6 +127,10 @@ extern char arcs_cmdline[COMMAND_LINE_SIZE]; */ extern unsigned long fw_arg0, fw_arg1, fw_arg2, fw_arg3; +#ifdef CONFIG_USE_OF +extern unsigned long fw_passed_dtb; +#endif + /* * Platform memory detection hook called by setup_arch */ diff --git a/arch/mips/include/asm/cpu-features.h b/arch/mips/include/asm/cpu-features.h index d1e04c943f5f..57cdc5be9545 100644 --- a/arch/mips/include/asm/cpu-features.h +++ b/arch/mips/include/asm/cpu-features.h @@ -311,6 +311,10 @@ #define cpu_has_mipsmt (cpu_data[0].ases & MIPS_ASE_MIPSMT) #endif +#ifndef cpu_has_vp +#define cpu_has_vp (cpu_data[0].options & MIPS_CPU_VP) +#endif + #ifndef cpu_has_userlocal #define cpu_has_userlocal (cpu_data[0].options & MIPS_CPU_ULRI) #endif @@ -414,4 +418,11 @@ # define cpu_has_small_pages (cpu_data[0].options & MIPS_CPU_SP) #endif +#ifndef cpu_has_nan_legacy +#define cpu_has_nan_legacy (cpu_data[0].options & MIPS_CPU_NAN_LEGACY) +#endif +#ifndef cpu_has_nan_2008 +#define cpu_has_nan_2008 (cpu_data[0].options & MIPS_CPU_NAN_2008) +#endif + #endif /* __ASM_CPU_FEATURES_H */ diff --git a/arch/mips/include/asm/cpu-info.h b/arch/mips/include/asm/cpu-info.h index e7dc785a91ca..aa526c304115 100644 --- a/arch/mips/include/asm/cpu-info.h +++ b/arch/mips/include/asm/cpu-info.h @@ -68,7 +68,7 @@ struct cpuinfo_mips { #ifdef CONFIG_64BIT int vmbits; /* Virtual memory size in bits */ #endif -#ifdef CONFIG_MIPS_MT_SMP +#if defined(CONFIG_MIPS_MT_SMP) || defined(CONFIG_CPU_MIPSR6) /* * There is not necessarily a 1:1 mapping of VPE num to CPU number * in particular on multi-core systems. @@ -125,7 +125,7 @@ struct proc_cpuinfo_notifier_args { unsigned long n; }; -#ifdef CONFIG_MIPS_MT_SMP +#if defined(CONFIG_MIPS_MT_SMP) || defined(CONFIG_CPU_MIPSR6) # define cpu_vpe_id(cpuinfo) ((cpuinfo)->vpe_id) #else # define cpu_vpe_id(cpuinfo) ({ (void)cpuinfo; 0; }) diff --git a/arch/mips/include/asm/cpu.h b/arch/mips/include/asm/cpu.h index 82ad15f11049..82a26ed17515 100644 --- a/arch/mips/include/asm/cpu.h +++ b/arch/mips/include/asm/cpu.h @@ -386,6 +386,9 @@ enum cpu_type_enum { #define MIPS_CPU_BP_GHIST 0x8000000000ull /* R12K+ Branch Prediction Global History */ #define MIPS_CPU_SP 0x10000000000ull /* Small (1KB) page support */ #define MIPS_CPU_FTLB 0x20000000000ull /* CPU has Fixed-page-size TLB */ +#define MIPS_CPU_NAN_LEGACY 0x40000000000ull /* Legacy NaN implemented */ +#define MIPS_CPU_NAN_2008 0x80000000000ull /* 2008 NaN implemented */ +#define MIPS_CPU_VP 0x100000000000ull /* MIPSr6 Virtual Processors (multi-threading) */ /* * CPU ASE encodings diff --git a/arch/mips/include/asm/device.h b/arch/mips/include/asm/device.h index c94fafba9e62..21c2082a0dfb 100644 --- a/arch/mips/include/asm/device.h +++ b/arch/mips/include/asm/device.h @@ -11,6 +11,11 @@ struct dma_map_ops; struct dev_archdata { /* DMA operations on that device */ struct dma_map_ops *dma_ops; + +#ifdef CONFIG_DMA_PERDEV_COHERENT + /* Non-zero if DMA is coherent with CPU caches */ + bool dma_coherent; +#endif }; struct pdev_archdata { diff --git a/arch/mips/include/asm/dma-coherence.h b/arch/mips/include/asm/dma-coherence.h index bc5e85d579e6..72d0eab02afc 100644 --- a/arch/mips/include/asm/dma-coherence.h +++ b/arch/mips/include/asm/dma-coherence.h @@ -9,14 +9,22 @@ #ifndef __ASM_DMA_COHERENCE_H #define __ASM_DMA_COHERENCE_H -#ifdef CONFIG_DMA_MAYBE_COHERENT -extern int coherentio; +enum coherent_io_user_state { + IO_COHERENCE_DEFAULT, + IO_COHERENCE_ENABLED, + IO_COHERENCE_DISABLED, +}; + +#if defined(CONFIG_DMA_PERDEV_COHERENT) +/* Don't provide (hw_)coherentio to avoid misuse */ +#elif defined(CONFIG_DMA_MAYBE_COHERENT) +extern enum coherent_io_user_state coherentio; extern int hw_coherentio; #else #ifdef CONFIG_DMA_COHERENT -#define coherentio 1 +#define coherentio IO_COHERENCE_ENABLED #else -#define coherentio 0 +#define coherentio IO_COHERENCE_DISABLED #endif #define hw_coherentio 0 #endif /* CONFIG_DMA_MAYBE_COHERENT */ diff --git a/arch/mips/include/asm/dma-mapping.h b/arch/mips/include/asm/dma-mapping.h index e604f760c4a0..953236992be3 100644 --- a/arch/mips/include/asm/dma-mapping.h +++ b/arch/mips/include/asm/dma-mapping.h @@ -34,4 +34,14 @@ static inline void dma_mark_clean(void *addr, size_t size) {} extern void dma_cache_sync(struct device *dev, void *vaddr, size_t size, enum dma_data_direction direction); +#define arch_setup_dma_ops arch_setup_dma_ops +static inline void arch_setup_dma_ops(struct device *dev, u64 dma_base, + u64 size, const struct iommu_ops *iommu, + bool coherent) +{ +#ifdef CONFIG_DMA_PERDEV_COHERENT + dev->archdata.dma_coherent = coherent; +#endif +} + #endif /* _ASM_DMA_MAPPING_H */ diff --git a/arch/mips/include/asm/dsemul.h b/arch/mips/include/asm/dsemul.h new file mode 100644 index 000000000000..a6e067801f23 --- /dev/null +++ b/arch/mips/include/asm/dsemul.h @@ -0,0 +1,92 @@ +/* + * Copyright (C) 2016 Imagination Technologies + * Author: Paul Burton <paul.burton@imgtec.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + */ + +#ifndef __MIPS_ASM_DSEMUL_H__ +#define __MIPS_ASM_DSEMUL_H__ + +#include <asm/break.h> +#include <asm/inst.h> + +/* Break instruction with special math emu break code set */ +#define BREAK_MATH(micromips) (((micromips) ? 0x7 : 0xd) | (BRK_MEMU << 16)) + +/* When used as a frame index, indicates the lack of a frame */ +#define BD_EMUFRAME_NONE ((int)BIT(31)) + +struct mm_struct; +struct pt_regs; +struct task_struct; + +/** + * mips_dsemul() - 'Emulate' an instruction from a branch delay slot + * @regs: User thread register context. + * @ir: The instruction to be 'emulated'. + * @branch_pc: The PC of the branch instruction. + * @cont_pc: The PC to continue at following 'emulation'. + * + * Emulate or execute an arbitrary MIPS instruction within the context of + * the current user thread. This is used primarily to handle instructions + * in the delay slots of emulated branch instructions, for example FP + * branch instructions on systems without an FPU. + * + * Return: Zero on success, negative if ir is a NOP, signal number on failure. + */ +extern int mips_dsemul(struct pt_regs *regs, mips_instruction ir, + unsigned long branch_pc, unsigned long cont_pc); + +/** + * do_dsemulret() - Return from a delay slot 'emulation' frame + * @xcp: User thread register context. + * + * Call in response to the BRK_MEMU break instruction used to return to + * the kernel from branch delay slot 'emulation' frames following a call + * to mips_dsemul(). Restores the user thread PC to the value that was + * passed as the cpc parameter to mips_dsemul(). + * + * Return: True if an emulation frame was returned from, else false. + */ +extern bool do_dsemulret(struct pt_regs *xcp); + +/** + * dsemul_thread_cleanup() - Cleanup thread 'emulation' frame + * @tsk: The task structure associated with the thread + * + * If the thread @tsk has a branch delay slot 'emulation' frame + * allocated to it then free that frame. + * + * Return: True if a frame was freed, else false. + */ +extern bool dsemul_thread_cleanup(struct task_struct *tsk); + +/** + * dsemul_thread_rollback() - Rollback from an 'emulation' frame + * @regs: User thread register context. + * + * If the current thread, whose register context is represented by @regs, + * is executing within a delay slot 'emulation' frame then exit that + * frame. The PC will be rolled back to the branch if the instruction + * that was being 'emulated' has not yet executed, or advanced to the + * continuation PC if it has. + * + * Return: True if a frame was exited, else false. + */ +extern bool dsemul_thread_rollback(struct pt_regs *regs); + +/** + * dsemul_mm_cleanup() - Cleanup per-mm delay slot 'emulation' state + * @mm: The struct mm_struct to cleanup state for. + * + * Cleanup state for the given @mm, ensuring that any memory allocated + * for delay slot 'emulation' book-keeping is freed. This is to be called + * before @mm is freed in order to avoid memory leaks. + */ +extern void dsemul_mm_cleanup(struct mm_struct *mm); + +#endif /* __MIPS_ASM_DSEMUL_H__ */ diff --git a/arch/mips/include/asm/elf.h b/arch/mips/include/asm/elf.h index b01a6ff468e0..dc72fdc73719 100644 --- a/arch/mips/include/asm/elf.h +++ b/arch/mips/include/asm/elf.h @@ -12,7 +12,6 @@ #include <linux/fs.h> #include <uapi/linux/elf.h> -#include <asm/cpu-info.h> #include <asm/current.h> /* ELF header e_flags defines. */ @@ -44,6 +43,7 @@ #define EF_MIPS_OPTIONS_FIRST 0x00000080 #define EF_MIPS_32BITMODE 0x00000100 #define EF_MIPS_FP64 0x00000200 +#define EF_MIPS_NAN2008 0x00000400 #define EF_MIPS_ABI 0x0000f000 #define EF_MIPS_ARCH 0xf0000000 @@ -305,7 +305,7 @@ do { \ \ current->thread.abi = &mips_abi; \ \ - current->thread.fpu.fcr31 = boot_cpu_data.fpu_csr31; \ + mips_set_personality_nan(state); \ } while (0) #endif /* CONFIG_32BIT */ @@ -367,7 +367,7 @@ do { \ else \ current->thread.abi = &mips_abi; \ \ - current->thread.fpu.fcr31 = boot_cpu_data.fpu_csr31; \ + mips_set_personality_nan(state); \ \ p = personality(current->personality); \ if (p != PER_LINUX32 && p != PER_LINUX) \ @@ -432,6 +432,7 @@ extern int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp); struct arch_elf_state { + int nan_2008; int fp_abi; int interp_fp_abi; int overall_fp_mode; @@ -440,17 +441,26 @@ struct arch_elf_state { #define MIPS_ABI_FP_UNKNOWN (-1) /* Unknown FP ABI (kernel internal) */ #define INIT_ARCH_ELF_STATE { \ + .nan_2008 = -1, \ .fp_abi = MIPS_ABI_FP_UNKNOWN, \ .interp_fp_abi = MIPS_ABI_FP_UNKNOWN, \ .overall_fp_mode = -1, \ } +/* Whether to accept legacy-NaN and 2008-NaN user binaries. */ +extern bool mips_use_nan_legacy; +extern bool mips_use_nan_2008; + extern int arch_elf_pt_proc(void *ehdr, void *phdr, struct file *elf, bool is_interp, struct arch_elf_state *state); -extern int arch_check_elf(void *ehdr, bool has_interpreter, +extern int arch_check_elf(void *ehdr, bool has_interpreter, void *interp_ehdr, struct arch_elf_state *state); +extern void mips_set_personality_nan(struct arch_elf_state *state); extern void mips_set_personality_fp(struct arch_elf_state *state); +#define elf_read_implies_exec(ex, stk) mips_elf_read_implies_exec(&(ex), stk) +extern int mips_elf_read_implies_exec(void *elf_ex, int exstack); + #endif /* _ASM_ELF_H */ diff --git a/arch/mips/include/asm/fpu_emulator.h b/arch/mips/include/asm/fpu_emulator.h index 2f021cdfba4f..c7544dea523b 100644 --- a/arch/mips/include/asm/fpu_emulator.h +++ b/arch/mips/include/asm/fpu_emulator.h @@ -24,7 +24,7 @@ #define _ASM_FPU_EMULATOR_H #include <linux/sched.h> -#include <asm/break.h> +#include <asm/dsemul.h> #include <asm/thread_info.h> #include <asm/inst.h> #include <asm/local.h> @@ -36,6 +36,7 @@ struct mips_fpu_emulator_stats { unsigned long emulated; unsigned long loads; unsigned long stores; + unsigned long branches; unsigned long cp1ops; unsigned long cp1xops; unsigned long errors; @@ -45,6 +46,121 @@ struct mips_fpu_emulator_stats { unsigned long ieee754_zerodiv; unsigned long ieee754_invalidop; unsigned long ds_emul; + + unsigned long abs_s; + unsigned long abs_d; + unsigned long add_s; + unsigned long add_d; + unsigned long bc1eqz; + unsigned long bc1nez; + unsigned long ceil_w_s; + unsigned long ceil_w_d; + unsigned long ceil_l_s; + unsigned long ceil_l_d; + unsigned long class_s; + unsigned long class_d; + unsigned long cmp_af_s; + unsigned long cmp_af_d; + unsigned long cmp_eq_s; + unsigned long cmp_eq_d; + unsigned long cmp_le_s; + unsigned long cmp_le_d; + unsigned long cmp_lt_s; + unsigned long cmp_lt_d; + unsigned long cmp_ne_s; + unsigned long cmp_ne_d; + unsigned long cmp_or_s; + unsigned long cmp_or_d; + unsigned long cmp_ueq_s; + unsigned long cmp_ueq_d; + unsigned long cmp_ule_s; + unsigned long cmp_ule_d; + unsigned long cmp_ult_s; + unsigned long cmp_ult_d; + unsigned long cmp_un_s; + unsigned long cmp_un_d; + unsigned long cmp_une_s; + unsigned long cmp_une_d; + unsigned long cmp_saf_s; + unsigned long cmp_saf_d; + unsigned long cmp_seq_s; + unsigned long cmp_seq_d; + unsigned long cmp_sle_s; + unsigned long cmp_sle_d; + unsigned long cmp_slt_s; + unsigned long cmp_slt_d; + unsigned long cmp_sne_s; + unsigned long cmp_sne_d; + unsigned long cmp_sor_s; + unsigned long cmp_sor_d; + unsigned long cmp_sueq_s; + unsigned long cmp_sueq_d; + unsigned long cmp_sule_s; + unsigned long cmp_sule_d; + unsigned long cmp_sult_s; + unsigned long cmp_sult_d; + unsigned long cmp_sun_s; + unsigned long cmp_sun_d; + unsigned long cmp_sune_s; + unsigned long cmp_sune_d; + unsigned long cvt_d_l; + unsigned long cvt_d_s; + unsigned long cvt_d_w; + unsigned long cvt_l_s; + unsigned long cvt_l_d; + unsigned long cvt_s_d; + unsigned long cvt_s_l; + unsigned long cvt_s_w; + unsigned long cvt_w_s; + unsigned long cvt_w_d; + unsigned long div_s; + unsigned long div_d; + unsigned long floor_w_s; + unsigned long floor_w_d; + unsigned long floor_l_s; + unsigned long floor_l_d; + unsigned long maddf_s; + unsigned long maddf_d; + unsigned long max_s; + unsigned long max_d; + unsigned long maxa_s; + unsigned long maxa_d; + unsigned long min_s; + unsigned long min_d; + unsigned long mina_s; + unsigned long mina_d; + unsigned long mov_s; + unsigned long mov_d; + unsigned long msubf_s; + unsigned long msubf_d; + unsigned long mul_s; + unsigned long mul_d; + unsigned long neg_s; + unsigned long neg_d; + unsigned long recip_s; + unsigned long recip_d; + unsigned long rint_s; + unsigned long rint_d; + unsigned long round_w_s; + unsigned long round_w_d; + unsigned long round_l_s; + unsigned long round_l_d; + unsigned long rsqrt_s; + unsigned long rsqrt_d; + unsigned long sel_s; + unsigned long sel_d; + unsigned long seleqz_s; + unsigned long seleqz_d; + unsigned long selnez_s; + unsigned long selnez_d; + unsigned long sqrt_s; + unsigned long sqrt_d; + unsigned long sub_s; + unsigned long sub_d; + unsigned long trunc_w_s; + unsigned long trunc_w_d; + unsigned long trunc_l_s; + unsigned long trunc_l_d; }; DECLARE_PER_CPU(struct mips_fpu_emulator_stats, fpuemustats); @@ -60,27 +176,18 @@ do { \ #define MIPS_FPU_EMU_INC_STATS(M) do { } while (0) #endif /* CONFIG_DEBUG_FS */ -extern int mips_dsemul(struct pt_regs *regs, mips_instruction ir, - unsigned long cpc); -extern int do_dsemulret(struct pt_regs *xcp); extern int fpu_emulator_cop1Handler(struct pt_regs *xcp, struct mips_fpu_struct *ctx, int has_fpu, void *__user *fault_addr); +void force_fcr31_sig(unsigned long fcr31, void __user *fault_addr, + struct task_struct *tsk); int process_fpemu_return(int sig, void __user *fault_addr, unsigned long fcr31); +int isBranchInstr(struct pt_regs *regs, struct mm_decoded_insn dec_insn, + unsigned long *contpc); int mm_isBranchInstr(struct pt_regs *regs, struct mm_decoded_insn dec_insn, unsigned long *contpc); -/* - * Instruction inserted following the badinst to further tag the sequence - */ -#define BD_COOKIE 0x0000bd36 /* tne $0, $0 with baggage */ - -/* - * Break instruction with special math emu break code set - */ -#define BREAK_MATH (0x0000000d | (BRK_MEMU << 16)) - #define SIGNALLING_NAN 0x7ff800007ff80000LL static inline void fpu_emulator_init_fpu(void) @@ -92,4 +199,15 @@ static inline void fpu_emulator_init_fpu(void) set_fpr64(&t->thread.fpu.fpr[i], 0, SIGNALLING_NAN); } +/* + * Mask the FCSR Cause bits according to the Enable bits, observing + * that Unimplemented is always enabled. + */ +static inline unsigned long mask_fcr31_x(unsigned long fcr31) +{ + return fcr31 & (FPU_CSR_UNI_X | + ((fcr31 & FPU_CSR_ALL_E) << + (ffs(FPU_CSR_ALL_X) - ffs(FPU_CSR_ALL_E)))); +} + #endif /* _ASM_FPU_EMULATOR_H */ diff --git a/arch/mips/include/asm/irq_regs.h b/arch/mips/include/asm/irq_regs.h index 33bd2a06de57..8c48d6dd1d78 100644 --- a/arch/mips/include/asm/irq_regs.h +++ b/arch/mips/include/asm/irq_regs.h @@ -18,4 +18,14 @@ static inline struct pt_regs *get_irq_regs(void) return current_thread_info()->regs; } +static inline struct pt_regs *set_irq_regs(struct pt_regs *new_regs) +{ + struct pt_regs *old_regs; + + old_regs = get_irq_regs(); + current_thread_info()->regs = new_regs; + + return old_regs; +} + #endif /* __ASM_IRQ_REGS_H */ diff --git a/arch/mips/include/asm/mach-au1x00/au1xxx_dbdma.h b/arch/mips/include/asm/mach-au1x00/au1xxx_dbdma.h index ca8077afac4a..456ddba152c4 100644 --- a/arch/mips/include/asm/mach-au1x00/au1xxx_dbdma.h +++ b/arch/mips/include/asm/mach-au1x00/au1xxx_dbdma.h @@ -100,7 +100,7 @@ typedef volatile struct au1xxx_ddma_desc { u32 dscr_nxtptr; /* Next descriptor pointer (mostly) */ /* * First 32 bytes are HW specific!!! - * Lets have some SW data following -- make sure it's 32 bytes. + * Let's have some SW data following -- make sure it's 32 bytes. */ u32 sw_status; u32 sw_context; diff --git a/arch/mips/include/asm/mach-cavium-octeon/kernel-entry-init.h b/arch/mips/include/asm/mach-cavium-octeon/kernel-entry-init.h index cf92fe733995..c4873e8594ef 100644 --- a/arch/mips/include/asm/mach-cavium-octeon/kernel-entry-init.h +++ b/arch/mips/include/asm/mach-cavium-octeon/kernel-entry-init.h @@ -141,7 +141,7 @@ octeon_main_processor: .endm /* - * Do SMP slave processor setup necessary before we can savely execute C code. + * Do SMP slave processor setup necessary before we can safely execute C code. */ .macro smp_slave_setup .endm diff --git a/arch/mips/include/asm/mach-generic/dma-coherence.h b/arch/mips/include/asm/mach-generic/dma-coherence.h index 0f8a354fd468..61addb1677e9 100644 --- a/arch/mips/include/asm/mach-generic/dma-coherence.h +++ b/arch/mips/include/asm/mach-generic/dma-coherence.h @@ -49,7 +49,19 @@ static inline int plat_dma_supported(struct device *dev, u64 mask) static inline int plat_device_is_coherent(struct device *dev) { - return coherentio; +#ifdef CONFIG_DMA_PERDEV_COHERENT + return dev->archdata.dma_coherent; +#else + switch (coherentio) { + default: + case IO_COHERENCE_DEFAULT: + return hw_coherentio; + case IO_COHERENCE_ENABLED: + return 1; + case IO_COHERENCE_DISABLED: + return 0; + } +#endif } #ifndef plat_post_dma_flush diff --git a/arch/mips/include/asm/mach-generic/kernel-entry-init.h b/arch/mips/include/asm/mach-generic/kernel-entry-init.h index 13b0751b010a..a229297c880b 100644 --- a/arch/mips/include/asm/mach-generic/kernel-entry-init.h +++ b/arch/mips/include/asm/mach-generic/kernel-entry-init.h @@ -16,7 +16,7 @@ .endm /* - * Do SMP slave processor setup necessary before we can savely execute C code. + * Do SMP slave processor setup necessary before we can safely execute C code. */ .macro smp_slave_setup .endm diff --git a/arch/mips/include/asm/mach-ip27/irq.h b/arch/mips/include/asm/mach-ip27/irq.h index cf4384bfa846..b0b7261ff3ad 100644 --- a/arch/mips/include/asm/mach-ip27/irq.h +++ b/arch/mips/include/asm/mach-ip27/irq.h @@ -11,7 +11,7 @@ #define __ASM_MACH_IP27_IRQ_H /* - * A hardwired interrupt number is completly stupid for this system - a + * A hardwired interrupt number is completely stupid for this system - a * large configuration might have thousands if not tenthousands of * interrupts. */ diff --git a/arch/mips/include/asm/mach-ip27/kernel-entry-init.h b/arch/mips/include/asm/mach-ip27/kernel-entry-init.h index b087cb83da3a..f992c1db876b 100644 --- a/arch/mips/include/asm/mach-ip27/kernel-entry-init.h +++ b/arch/mips/include/asm/mach-ip27/kernel-entry-init.h @@ -81,7 +81,7 @@ .endm /* - * Do SMP slave processor setup necessary before we can savely execute C code. + * Do SMP slave processor setup necessary before we can safely execute C code. */ .macro smp_slave_setup GET_NASID_ASM t1 diff --git a/arch/mips/include/asm/mach-jz4740/gpio.h b/arch/mips/include/asm/mach-jz4740/gpio.h index bf8c3e1860e7..7c7708a23baa 100644 --- a/arch/mips/include/asm/mach-jz4740/gpio.h +++ b/arch/mips/include/asm/mach-jz4740/gpio.h @@ -27,7 +27,7 @@ enum jz_gpio_function { /* Usually a driver for a SoC component has to request several gpio pins and - configure them as funcion pins. + configure them as function pins. jz_gpio_bulk_request can be used to ease this process. Usually one would do something like: diff --git a/arch/mips/include/asm/mach-lantiq/falcon/lantiq_soc.h b/arch/mips/include/asm/mach-lantiq/falcon/lantiq_soc.h index 98d6a2f14aaf..642504188a5b 100644 --- a/arch/mips/include/asm/mach-lantiq/falcon/lantiq_soc.h +++ b/arch/mips/include/asm/mach-lantiq/falcon/lantiq_soc.h @@ -22,7 +22,7 @@ /* * during early_printk no ioremap possible at this early stage - * lets use KSEG1 instead + * let's use KSEG1 instead */ #define LTQ_ASC0_BASE_ADDR 0x1E100C00 #define LTQ_EARLY_ASC KSEG1ADDR(LTQ_ASC0_BASE_ADDR) diff --git a/arch/mips/include/asm/mach-lantiq/xway/lantiq_soc.h b/arch/mips/include/asm/mach-lantiq/xway/lantiq_soc.h index dd6005b75e0c..b230347a2b84 100644 --- a/arch/mips/include/asm/mach-lantiq/xway/lantiq_soc.h +++ b/arch/mips/include/asm/mach-lantiq/xway/lantiq_soc.h @@ -75,7 +75,7 @@ extern __iomem void *ltq_cgu_membase; /* * during early_printk no ioremap is possible - * lets use KSEG1 instead + * let's use KSEG1 instead */ #define LTQ_ASC1_BASE_ADDR 0x1E100C00 #define LTQ_EARLY_ASC KSEG1ADDR(LTQ_ASC1_BASE_ADDR) diff --git a/arch/mips/include/asm/machine.h b/arch/mips/include/asm/machine.h new file mode 100644 index 000000000000..6b444cd9526f --- /dev/null +++ b/arch/mips/include/asm/machine.h @@ -0,0 +1,63 @@ +/* + * Copyright (C) 2016 Imagination Technologies + * Author: Paul Burton <paul.burton@imgtec.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + */ + +#ifndef __MIPS_ASM_MACHINE_H__ +#define __MIPS_ASM_MACHINE_H__ + +#include <linux/libfdt.h> +#include <linux/of.h> + +struct mips_machine { + const struct of_device_id *matches; + const void *fdt; + bool (*detect)(void); + const void *(*fixup_fdt)(const void *fdt, const void *match_data); + unsigned int (*measure_hpt_freq)(void); +}; + +extern long __mips_machines_start; +extern long __mips_machines_end; + +#define MIPS_MACHINE(name) \ + static const struct mips_machine __mips_mach_##name \ + __used __section(.mips.machines.init) + +#define for_each_mips_machine(mach) \ + for ((mach) = (struct mips_machine *)&__mips_machines_start; \ + (mach) < (struct mips_machine *)&__mips_machines_end; \ + (mach)++) + +/** + * mips_machine_is_compatible() - check if a machine is compatible with an FDT + * @mach: the machine struct to check + * @fdt: the FDT to check for compatibility with + * + * Check whether the given machine @mach is compatible with the given flattened + * device tree @fdt, based upon the compatibility property of the root node. + * + * Return: the device id matched if any, else NULL + */ +static inline const struct of_device_id * +mips_machine_is_compatible(const struct mips_machine *mach, const void *fdt) +{ + const struct of_device_id *match; + + if (!mach->matches) + return NULL; + + for (match = mach->matches; match->compatible; match++) { + if (fdt_node_check_compatible(fdt, 0, match->compatible) == 0) + return match; + } + + return NULL; +} + +#endif /* __MIPS_ASM_MACHINE_H__ */ diff --git a/arch/mips/include/asm/mips-cm.h b/arch/mips/include/asm/mips-cm.h index b836ddec82b7..70ad1c759555 100644 --- a/arch/mips/include/asm/mips-cm.h +++ b/arch/mips/include/asm/mips-cm.h @@ -28,7 +28,7 @@ extern void __iomem *mips_cm_l2sync_base; * This function returns the physical base address of the Coherence Manager * global control block, or 0 if no Coherence Manager is present. It provides * a default implementation which reads the CMGCRBase register where available, - * and may be overriden by platforms which determine this address in a + * and may be overridden by platforms which determine this address in a * different way by defining a function with the same prototype except for the * name mips_cm_phys_base (without underscores). */ @@ -208,6 +208,7 @@ BUILD_CM_RW(l2_config, MIPS_CM_GCB_OFS + 0x130) BUILD_CM_RW(sys_config2, MIPS_CM_GCB_OFS + 0x150) BUILD_CM_RW(l2_pft_control, MIPS_CM_GCB_OFS + 0x300) BUILD_CM_RW(l2_pft_control_b, MIPS_CM_GCB_OFS + 0x308) +BUILD_CM_RW(bev_base, MIPS_CM_GCB_OFS + 0x680) /* Core Local & Core Other register accessor functions */ BUILD_CM_Cx_RW(reset_release, 0x00) @@ -457,7 +458,10 @@ static inline unsigned int mips_cm_max_vp_width(void) if (mips_cm_revision() >= CM_REV_CM3) return read_gcr_sys_config2() & CM_GCR_SYS_CONFIG2_MAXVPW_MSK; - return smp_num_siblings; + if (config_enabled(CONFIG_SMP)) + return smp_num_siblings; + + return 1; } /** diff --git a/arch/mips/include/asm/mips-cpc.h b/arch/mips/include/asm/mips-cpc.h index e09035239e53..8c519f9827a3 100644 --- a/arch/mips/include/asm/mips-cpc.h +++ b/arch/mips/include/asm/mips-cpc.h @@ -106,6 +106,9 @@ BUILD_CPC_R_(revision, MIPS_CPC_GCB_OFS + 0x20) BUILD_CPC_Cx_RW(cmd, 0x00) BUILD_CPC_Cx_RW(stat_conf, 0x08) BUILD_CPC_Cx_RW(other, 0x10) +BUILD_CPC_Cx_RW(vp_stop, 0x20) +BUILD_CPC_Cx_RW(vp_run, 0x28) +BUILD_CPC_Cx_RW(vp_running, 0x30) /* CPC_Cx_CMD register fields */ #define CPC_Cx_CMD_SHF 0 diff --git a/arch/mips/include/asm/mips-r2-to-r6-emul.h b/arch/mips/include/asm/mips-r2-to-r6-emul.h index 4b89f28047f7..20621e1ca238 100644 --- a/arch/mips/include/asm/mips-r2-to-r6-emul.h +++ b/arch/mips/include/asm/mips-r2-to-r6-emul.h @@ -52,7 +52,7 @@ do { \ __this_cpu_inc(mipsr2emustats.M); \ err = __get_user(nir, (u32 __user *)regs->cp0_epc); \ if (!err) { \ - if (nir == BREAK_MATH) \ + if (nir == BREAK_MATH(0)) \ __this_cpu_inc(mipsr2bdemustats.M); \ } \ preempt_enable(); \ @@ -79,7 +79,7 @@ struct r2_decoder_table { }; -extern void do_trap_or_bp(struct pt_regs *regs, unsigned int code, +extern void do_trap_or_bp(struct pt_regs *regs, unsigned int code, int si_code, const char *str); #ifndef CONFIG_MIPSR2_TO_R6_EMULATOR diff --git a/arch/mips/include/asm/mipsregs.h b/arch/mips/include/asm/mipsregs.h index e43aca183c99..c785da1d8660 100644 --- a/arch/mips/include/asm/mipsregs.h +++ b/arch/mips/include/asm/mipsregs.h @@ -589,6 +589,7 @@ #define MIPS_CONF5_MRP (_ULCAST_(1) << 3) #define MIPS_CONF5_LLB (_ULCAST_(1) << 4) #define MIPS_CONF5_MVH (_ULCAST_(1) << 5) +#define MIPS_CONF5_VP (_ULCAST_(1) << 7) #define MIPS_CONF5_FRE (_ULCAST_(1) << 8) #define MIPS_CONF5_UFE (_ULCAST_(1) << 9) #define MIPS_CONF5_MSAEN (_ULCAST_(1) << 27) diff --git a/arch/mips/include/asm/mmu.h b/arch/mips/include/asm/mmu.h index 1afa1f986df8..f6ba08d77931 100644 --- a/arch/mips/include/asm/mmu.h +++ b/arch/mips/include/asm/mmu.h @@ -2,11 +2,20 @@ #define __ASM_MMU_H #include <linux/atomic.h> +#include <linux/spinlock.h> +#include <linux/wait.h> typedef struct { unsigned long asid[NR_CPUS]; void *vdso; atomic_t fp_mode_switching; + + /* lock to be held whilst modifying fp_bd_emupage_allocmap */ + spinlock_t bd_emupage_lock; + /* bitmap tracking allocation of fp_bd_emupage */ + unsigned long *bd_emupage_allocmap; + /* wait queue for threads requiring an emuframe */ + wait_queue_head_t bd_emupage_queue; } mm_context_t; #endif /* __ASM_MMU_H */ diff --git a/arch/mips/include/asm/mmu_context.h b/arch/mips/include/asm/mmu_context.h index 45914b59824c..3a7761f88a16 100644 --- a/arch/mips/include/asm/mmu_context.h +++ b/arch/mips/include/asm/mmu_context.h @@ -16,6 +16,7 @@ #include <linux/smp.h> #include <linux/slab.h> #include <asm/cacheflush.h> +#include <asm/dsemul.h> #include <asm/hazards.h> #include <asm/tlbflush.h> #include <asm-generic/mm_hooks.h> @@ -133,6 +134,10 @@ init_new_context(struct task_struct *tsk, struct mm_struct *mm) atomic_set(&mm->context.fp_mode_switching, 0); + mm->context.bd_emupage_allocmap = NULL; + spin_lock_init(&mm->context.bd_emupage_lock); + init_waitqueue_head(&mm->context.bd_emupage_queue); + return 0; } @@ -167,6 +172,7 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, */ static inline void destroy_context(struct mm_struct *mm) { + dsemul_mm_cleanup(mm); } #define deactivate_mm(tsk, mm) do { } while (0) diff --git a/arch/mips/include/asm/octeon/cvmx-config.h b/arch/mips/include/asm/octeon/cvmx-config.h index f7dd17d0dc22..f4f1996e0fac 100644 --- a/arch/mips/include/asm/octeon/cvmx-config.h +++ b/arch/mips/include/asm/octeon/cvmx-config.h @@ -33,7 +33,7 @@ /* Packet buffers */ #define CVMX_FPA_PACKET_POOL (0) #define CVMX_FPA_PACKET_POOL_SIZE CVMX_FPA_POOL_0_SIZE -/* Work queue entrys */ +/* Work queue entries */ #define CVMX_FPA_WQE_POOL (1) #define CVMX_FPA_WQE_POOL_SIZE CVMX_FPA_POOL_1_SIZE /* PKO queue command buffers */ diff --git a/arch/mips/include/asm/octeon/cvmx.h b/arch/mips/include/asm/octeon/cvmx.h index 774bb45834cb..56e3436f1c21 100644 --- a/arch/mips/include/asm/octeon/cvmx.h +++ b/arch/mips/include/asm/octeon/cvmx.h @@ -189,7 +189,7 @@ static inline uint64_t cvmx_ptr_to_phys(void *ptr) static inline void *cvmx_phys_to_ptr(uint64_t physical_address) { if (sizeof(void *) == 8) { - /* Just set the top bit, avoiding any TLB uglyness */ + /* Just set the top bit, avoiding any TLB ugliness */ return CASTPTR(void, CVMX_ADD_SEG(CVMX_MIPS_SPACE_XKPHYS, physical_address)); diff --git a/arch/mips/include/asm/page.h b/arch/mips/include/asm/page.h index 21ed7150fec3..74cb004c2868 100644 --- a/arch/mips/include/asm/page.h +++ b/arch/mips/include/asm/page.h @@ -229,8 +229,10 @@ extern int __virt_addr_valid(const volatile void *kaddr); #define virt_addr_valid(kaddr) \ __virt_addr_valid((const volatile void *) (kaddr)) -#define VM_DATA_DEFAULT_FLAGS (VM_READ | VM_WRITE | VM_EXEC | \ - VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC) +#define VM_DATA_DEFAULT_FLAGS \ + (VM_READ | VM_WRITE | \ + ((current->personality & READ_IMPLIES_EXEC) ? VM_EXEC : 0) | \ + VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC) #define UNCAC_ADDR(addr) ((addr) - PAGE_OFFSET + UNCAC_BASE) #define CAC_ADDR(addr) ((addr) - UNCAC_BASE + PAGE_OFFSET) diff --git a/arch/mips/include/asm/pci/bridge.h b/arch/mips/include/asm/pci/bridge.h index 8d7a63b52ac7..3206245d1ed6 100644 --- a/arch/mips/include/asm/pci/bridge.h +++ b/arch/mips/include/asm/pci/bridge.h @@ -269,16 +269,16 @@ typedef struct bridge_err_cmdword_s { union { u32 cmd_word; struct { - u32 didn:4, /* Destination ID */ - sidn:4, /* Source ID */ - pactyp:4, /* Packet type */ - tnum:5, /* Trans Number */ - coh:1, /* Coh Transacti */ - ds:2, /* Data size */ - gbr:1, /* GBR enable */ - vbpm:1, /* VBPM message */ + u32 didn:4, /* Destination ID */ + sidn:4, /* Source ID */ + pactyp:4, /* Packet type */ + tnum:5, /* Trans Number */ + coh:1, /* Coh Transaction */ + ds:2, /* Data size */ + gbr:1, /* GBR enable */ + vbpm:1, /* VBPM message */ error:1, /* Error occurred */ - barr:1, /* Barrier op */ + barr:1, /* Barrier op */ rsvd:8; } berr_st; } berr_un; diff --git a/arch/mips/include/asm/processor.h b/arch/mips/include/asm/processor.h index 041153f5cf93..25eef1d60f27 100644 --- a/arch/mips/include/asm/processor.h +++ b/arch/mips/include/asm/processor.h @@ -11,12 +11,14 @@ #ifndef _ASM_PROCESSOR_H #define _ASM_PROCESSOR_H +#include <linux/atomic.h> #include <linux/cpumask.h> #include <linux/threads.h> #include <asm/cachectl.h> #include <asm/cpu.h> #include <asm/cpu-info.h> +#include <asm/dsemul.h> #include <asm/mipsregs.h> #include <asm/prefetch.h> @@ -74,7 +76,11 @@ extern unsigned int vced_count, vcei_count; #endif -#define STACK_TOP (TASK_SIZE & PAGE_MASK) +/* + * One page above the stack is used for branch delay slot "emulation". + * See dsemul.c for details. + */ +#define STACK_TOP ((TASK_SIZE & PAGE_MASK) - PAGE_SIZE) /* * This decides where the kernel will search for a free chunk of vm @@ -252,6 +258,12 @@ struct thread_struct { /* Saved fpu/fpu emulator stuff. */ struct mips_fpu_struct fpu FPU_ALIGN; + /* Assigned branch delay slot 'emulation' frame */ + atomic_t bd_emu_frame; + /* PC of the branch from a branch delay slot 'emulation' */ + unsigned long bd_emu_branch_pc; + /* PC to continue from following a branch delay slot 'emulation' */ + unsigned long bd_emu_cont_pc; #ifdef CONFIG_MIPS_MT_FPAFF /* Emulated instruction count */ unsigned long emulated_fp; @@ -319,6 +331,10 @@ struct thread_struct { * FPU affinity state (null if not FPAFF) \ */ \ FPAFF_INIT \ + /* Delay slot emulation */ \ + .bd_emu_frame = ATOMIC_INIT(BD_EMUFRAME_NONE), \ + .bd_emu_branch_pc = 0, \ + .bd_emu_cont_pc = 0, \ /* \ * Saved DSP stuff \ */ \ @@ -355,6 +371,10 @@ extern unsigned long thread_saved_pc(struct task_struct *tsk); */ extern void start_thread(struct pt_regs * regs, unsigned long pc, unsigned long sp); +static inline void flush_thread(void) +{ +} + unsigned long get_wchan(struct task_struct *p); #define __KSTK_TOS(tsk) ((unsigned long)task_stack_page(tsk) + \ diff --git a/arch/mips/include/asm/r4kcache.h b/arch/mips/include/asm/r4kcache.h index 38902bf97adc..667ca3c467b7 100644 --- a/arch/mips/include/asm/r4kcache.h +++ b/arch/mips/include/asm/r4kcache.h @@ -210,7 +210,11 @@ static inline void protected_writeback_dcache_line(unsigned long addr) static inline void protected_writeback_scache_line(unsigned long addr) { +#ifdef CONFIG_EVA + protected_cachee_op(Hit_Writeback_Inv_SD, addr); +#else protected_cache_op(Hit_Writeback_Inv_SD, addr); +#endif } /* diff --git a/arch/mips/include/asm/sgi/hpc3.h b/arch/mips/include/asm/sgi/hpc3.h index 59920b345942..4a9c99050c13 100644 --- a/arch/mips/include/asm/sgi/hpc3.h +++ b/arch/mips/include/asm/sgi/hpc3.h @@ -147,7 +147,7 @@ struct hpc3_ethregs { #define HPC3_EPCFG_P1 0x000f /* Cycles to spend in P1 state for PIO */ #define HPC3_EPCFG_P2 0x00f0 /* Cycles to spend in P2 state for PIO */ #define HPC3_EPCFG_P3 0x0f00 /* Cycles to spend in P3 state for PIO */ -#define HPC3_EPCFG_TST 0x1000 /* Diagnistic ram test feature bit */ +#define HPC3_EPCFG_TST 0x1000 /* Diagnostic ram test feature bit */ u32 _unused2[0x1000/4 - 8]; /* padding */ diff --git a/arch/mips/include/asm/sgiarcs.h b/arch/mips/include/asm/sgiarcs.h index 26ddfff28c8e..105a9479ac5f 100644 --- a/arch/mips/include/asm/sgiarcs.h +++ b/arch/mips/include/asm/sgiarcs.h @@ -144,7 +144,7 @@ struct linux_tinfo { struct linux_vdirent { ULONG namelen; unsigned char attr; - char fname[32]; /* XXX imperical, should be a define */ + char fname[32]; /* XXX empirical, should be a define */ }; /* Other stuff for files. */ @@ -179,7 +179,7 @@ struct linux_finfo { enum linux_devtypes dtype; unsigned long namelen; unsigned char attr; - char name[32]; /* XXX imperical, should be define */ + char name[32]; /* XXX empirical, should be define */ }; /* This describes the vector containing function pointers to the ARC diff --git a/arch/mips/include/asm/smp-cps.h b/arch/mips/include/asm/smp-cps.h index 326c16ebd589..2ae1f61a4a95 100644 --- a/arch/mips/include/asm/smp-cps.h +++ b/arch/mips/include/asm/smp-cps.h @@ -29,7 +29,7 @@ extern struct core_boot_config *mips_cps_core_bootcfg; extern void mips_cps_core_entry(void); extern void mips_cps_core_init(void); -extern struct vpe_boot_config *mips_cps_boot_vpes(void); +extern void mips_cps_boot_vpes(struct core_boot_config *cfg, unsigned vpe); extern void mips_cps_pm_save(void); extern void mips_cps_pm_restore(void); diff --git a/arch/mips/include/asm/sn/ioc3.h b/arch/mips/include/asm/sn/ioc3.h index e33f0363235b..feb385180f87 100644 --- a/arch/mips/include/asm/sn/ioc3.h +++ b/arch/mips/include/asm/sn/ioc3.h @@ -355,7 +355,7 @@ struct ioc3_etxd { #define SSCR_PAUSE_STATE 0x40000000 /* sets when PAUSE takes effect */ #define SSCR_RESET 0x80000000 /* reset DMA channels */ -/* all producer/comsumer pointers are the same bitfield */ +/* all producer/consumer pointers are the same bitfield */ #define PROD_CONS_PTR_4K 0x00000ff8 /* for 4K buffers */ #define PROD_CONS_PTR_1K 0x000003f8 /* for 1K buffers */ #define PROD_CONS_PTR_OFF 3 diff --git a/arch/mips/include/asm/sn/sn0/hubio.h b/arch/mips/include/asm/sn/sn0/hubio.h index 5998b13e9764..57ece90f8cf1 100644 --- a/arch/mips/include/asm/sn/sn0/hubio.h +++ b/arch/mips/include/asm/sn/sn0/hubio.h @@ -628,7 +628,7 @@ typedef union h1_icrbb_u { /* * Values for field imsgtype */ -#define IIO_ICRB_IMSGT_XTALK 0 /* Incoming Meessage from Xtalk */ +#define IIO_ICRB_IMSGT_XTALK 0 /* Incoming Message from Xtalk */ #define IIO_ICRB_IMSGT_BTE 1 /* Incoming message from BTE */ #define IIO_ICRB_IMSGT_SN0NET 2 /* Incoming message from SN0 net */ #define IIO_ICRB_IMSGT_CRB 3 /* Incoming message from CRB ??? */ diff --git a/arch/mips/include/asm/switch_to.h b/arch/mips/include/asm/switch_to.h index ebb5c0f2f90d..c0ae27971e31 100644 --- a/arch/mips/include/asm/switch_to.h +++ b/arch/mips/include/asm/switch_to.h @@ -76,6 +76,22 @@ do { if (cpu_has_rw_llb) { \ } while (0) /* + * Check FCSR for any unmasked exceptions pending set with `ptrace', + * clear them and send a signal. + */ +#define __sanitize_fcr31(next) \ +do { \ + unsigned long fcr31 = mask_fcr31_x(next->thread.fpu.fcr31); \ + void __user *pc; \ + \ + if (unlikely(fcr31)) { \ + pc = (void __user *)task_pt_regs(next)->cp0_epc; \ + next->thread.fpu.fcr31 &= ~fcr31; \ + force_fcr31_sig(fcr31, pc, next); \ + } \ +} while (0) + +/* * For newly created kernel threads switch_to() will return to * ret_from_kernel_thread, newly created user threads to ret_from_fork. * That is, everything following resume() will be skipped for new threads. @@ -85,6 +101,8 @@ do { if (cpu_has_rw_llb) { \ do { \ __mips_mt_fpaff_switch_to(prev); \ lose_fpu_inatomic(1, prev); \ + if (tsk_used_math(next)) \ + __sanitize_fcr31(next); \ if (cpu_has_dsp) { \ __save_dsp(prev); \ __restore_dsp(next); \ diff --git a/arch/mips/include/asm/uaccess.h b/arch/mips/include/asm/uaccess.h index c74c32ccc647..b6e20f3053f4 100644 --- a/arch/mips/include/asm/uaccess.h +++ b/arch/mips/include/asm/uaccess.h @@ -96,7 +96,7 @@ static inline bool eva_kernel_access(void) } /* - * Is a address valid? This does a straighforward calculation rather + * Is a address valid? This does a straightforward calculation rather * than tests. * * Address valid if: diff --git a/arch/mips/include/asm/vdso.h b/arch/mips/include/asm/vdso.h index 8f4ca5dd992b..b7cd6cf77b83 100644 --- a/arch/mips/include/asm/vdso.h +++ b/arch/mips/include/asm/vdso.h @@ -79,8 +79,8 @@ union mips_vdso_data { struct { u64 xtime_sec; u64 xtime_nsec; - u32 wall_to_mono_sec; - u32 wall_to_mono_nsec; + u64 wall_to_mono_sec; + u64 wall_to_mono_nsec; u32 seq_count; u32 cs_shift; u8 clock_mode; diff --git a/arch/mips/include/uapi/asm/inst.h b/arch/mips/include/uapi/asm/inst.h index 9b44d5a816fa..bd817e626da1 100644 --- a/arch/mips/include/uapi/asm/inst.h +++ b/arch/mips/include/uapi/asm/inst.h @@ -21,20 +21,20 @@ enum major_op { spec_op, bcond_op, j_op, jal_op, beq_op, bne_op, blez_op, bgtz_op, - addi_op, cbcond0_op = addi_op, addiu_op, slti_op, sltiu_op, + addi_op, pop10_op = addi_op, addiu_op, slti_op, sltiu_op, andi_op, ori_op, xori_op, lui_op, cop0_op, cop1_op, cop2_op, cop1x_op, beql_op, bnel_op, blezl_op, bgtzl_op, - daddi_op, cbcond1_op = daddi_op, daddiu_op, ldl_op, ldr_op, + daddi_op, pop30_op = daddi_op, daddiu_op, ldl_op, ldr_op, spec2_op, jalx_op, mdmx_op, msa_op = mdmx_op, spec3_op, lb_op, lh_op, lwl_op, lw_op, lbu_op, lhu_op, lwr_op, lwu_op, sb_op, sh_op, swl_op, sw_op, sdl_op, sdr_op, swr_op, cache_op, ll_op, lwc1_op, lwc2_op, bc6_op = lwc2_op, pref_op, - lld_op, ldc1_op, ldc2_op, beqzcjic_op = ldc2_op, ld_op, + lld_op, ldc1_op, ldc2_op, pop66_op = ldc2_op, ld_op, sc_op, swc1_op, swc2_op, balc6_op = swc2_op, major_3b_op, - scd_op, sdc1_op, sdc2_op, bnezcjialc_op = sdc2_op, sd_op + scd_op, sdc1_op, sdc2_op, pop76_op = sdc2_op, sd_op }; /* @@ -166,6 +166,7 @@ enum cop1_sdw_func { fceill_op = 0x0a, ffloorl_op = 0x0b, fround_op = 0x0c, ftrunc_op = 0x0d, fceil_op = 0x0e, ffloor_op = 0x0f, + fsel_op = 0x10, fmovc_op = 0x11, fmovz_op = 0x12, fmovn_op = 0x13, fseleqz_op = 0x14, frecip_op = 0x15, frsqrt_op = 0x16, @@ -644,6 +645,16 @@ struct msa_mi10_format { /* MSA MI10 */ ;)))))) }; +struct dsp_format { /* SPEC3 DSP format instructions */ + __BITFIELD_FIELD(unsigned int opcode : 6, + __BITFIELD_FIELD(unsigned int base : 5, + __BITFIELD_FIELD(unsigned int index : 5, + __BITFIELD_FIELD(unsigned int rd : 5, + __BITFIELD_FIELD(unsigned int op : 5, + __BITFIELD_FIELD(unsigned int func : 6, + ;)))))) +}; + struct spec3_format { /* SPEC3 */ __BITFIELD_FIELD(unsigned int opcode:6, __BITFIELD_FIELD(unsigned int rs:5, @@ -799,6 +810,13 @@ struct mm_x_format { /* Scaled indexed load format (microMIPS) */ ;))))) }; +struct mm_a_format { /* ADDIUPC format (microMIPS) */ + __BITFIELD_FIELD(unsigned int opcode : 6, + __BITFIELD_FIELD(unsigned int rs : 3, + __BITFIELD_FIELD(signed int simmediate : 23, + ;))) +}; + /* * microMIPS instruction formats (16-bit length) */ @@ -925,6 +943,7 @@ union mips_instruction { struct b_format b_format; struct ps_format ps_format; struct v_format v_format; + struct dsp_format dsp_format; struct spec3_format spec3_format; struct fb_format fb_format; struct fp0_format fp0_format; @@ -940,6 +959,7 @@ union mips_instruction { struct mm_i_format mm_i_format; struct mm_m_format mm_m_format; struct mm_x_format mm_x_format; + struct mm_a_format mm_a_format; struct mm_b0_format mm_b0_format; struct mm_b1_format mm_b1_format; struct mm16_m_format mm16_m_format ; diff --git a/arch/mips/kernel/binfmt_elfn32.c b/arch/mips/kernel/binfmt_elfn32.c index 1188e00bb120..9fd86df3fcfa 100644 --- a/arch/mips/kernel/binfmt_elfn32.c +++ b/arch/mips/kernel/binfmt_elfn32.c @@ -1,5 +1,6 @@ /* * Support for n32 Linux/MIPS ELF binaries. + * Author: Ralf Baechle (ralf@linux-mips.org) * * Copyright (C) 1999, 2001 Ralf Baechle * Copyright (C) 1999, 2001 Silicon Graphics, Inc. @@ -51,7 +52,6 @@ typedef elf_fpreg_t elf_fpregset_t[ELF_NFPREG]; #define ELF_ET_DYN_BASE (TASK32_SIZE / 3 * 2) #include <asm/processor.h> -#include <linux/module.h> #include <linux/elfcore.h> #include <linux/compat.h> #include <linux/math64.h> @@ -110,12 +110,6 @@ jiffies_to_compat_timeval(unsigned long jiffies, struct compat_timeval *value) #define ELF_CORE_EFLAGS EF_MIPS_ABI2 -MODULE_DESCRIPTION("Binary format loader for compatibility with n32 Linux/MIPS binaries"); -MODULE_AUTHOR("Ralf Baechle (ralf@linux-mips.org)"); - -#undef MODULE_DESCRIPTION -#undef MODULE_AUTHOR - #undef TASK_SIZE #define TASK_SIZE TASK_SIZE32 diff --git a/arch/mips/kernel/binfmt_elfo32.c b/arch/mips/kernel/binfmt_elfo32.c index 928767858b86..bccbc0123c13 100644 --- a/arch/mips/kernel/binfmt_elfo32.c +++ b/arch/mips/kernel/binfmt_elfo32.c @@ -1,5 +1,6 @@ /* * Support for o32 Linux/MIPS ELF binaries. + * Author: Ralf Baechle (ralf@linux-mips.org) * * Copyright (C) 1999, 2001 Ralf Baechle * Copyright (C) 1999, 2001 Silicon Graphics, Inc. @@ -72,7 +73,6 @@ typedef elf_fpreg_t elf_fpregset_t[ELF_NFPREG]; #include <asm/processor.h> -#include <linux/module.h> #include <linux/elfcore.h> #include <linux/compat.h> #include <linux/math64.h> @@ -129,12 +129,6 @@ jiffies_to_compat_timeval(unsigned long jiffies, struct compat_timeval *value) value->tv_usec = rem / NSEC_PER_USEC; } -MODULE_DESCRIPTION("Binary format loader for compatibility with o32 Linux/MIPS binaries"); -MODULE_AUTHOR("Ralf Baechle (ralf@linux-mips.org)"); - -#undef MODULE_DESCRIPTION -#undef MODULE_AUTHOR - #undef TASK_SIZE #define TASK_SIZE TASK_SIZE32 diff --git a/arch/mips/kernel/branch.c b/arch/mips/kernel/branch.c index 71e8f4c0b8da..56f166a48fbc 100644 --- a/arch/mips/kernel/branch.c +++ b/arch/mips/kernel/branch.c @@ -9,7 +9,7 @@ #include <linux/kernel.h> #include <linux/sched.h> #include <linux/signal.h> -#include <linux/module.h> +#include <linux/export.h> #include <asm/branch.h> #include <asm/cpu.h> #include <asm/cpu-features.h> @@ -479,7 +479,7 @@ int __compute_return_epc_for_insn(struct pt_regs *regs, /* * OK we are here either because we hit a NAL * instruction or because we are emulating an - * old bltzal{,l} one. Lets figure out what the + * old bltzal{,l} one. Let's figure out what the * case really is. */ if (!insn.i_format.rs) { @@ -511,7 +511,7 @@ int __compute_return_epc_for_insn(struct pt_regs *regs, /* * OK we are here either because we hit a BAL * instruction or because we are emulating an - * old bgezal{,l} one. Lets figure out what the + * old bgezal{,l} one. Let's figure out what the * case really is. */ if (!insn.i_format.rs) { @@ -799,7 +799,7 @@ int __compute_return_epc_for_insn(struct pt_regs *regs, epc += 4 + (insn.i_format.simmediate << 2); regs->cp0_epc = epc; break; - case beqzcjic_op: + case pop66_op: if (!cpu_has_mips_r6) { ret = -SIGILL; break; @@ -807,7 +807,7 @@ int __compute_return_epc_for_insn(struct pt_regs *regs, /* Compact branch: BEQZC || JIC */ regs->cp0_epc += 8; break; - case bnezcjialc_op: + case pop76_op: if (!cpu_has_mips_r6) { ret = -SIGILL; break; @@ -820,8 +820,8 @@ int __compute_return_epc_for_insn(struct pt_regs *regs, regs->cp0_epc += 8; break; #endif - case cbcond0_op: - case cbcond1_op: + case pop10_op: + case pop30_op: /* Only valid for MIPS R6 */ if (!cpu_has_mips_r6) { ret = -SIGILL; diff --git a/arch/mips/kernel/cps-vec.S b/arch/mips/kernel/cps-vec.S index ac81edd44563..6829ee25af60 100644 --- a/arch/mips/kernel/cps-vec.S +++ b/arch/mips/kernel/cps-vec.S @@ -18,9 +18,13 @@ #include <asm/mipsmtregs.h> #include <asm/pm.h> +#define GCR_CPC_BASE_OFS 0x0088 #define GCR_CL_COHERENCE_OFS 0x2008 #define GCR_CL_ID_OFS 0x2028 +#define CPC_CL_VC_STOP_OFS 0x2020 +#define CPC_CL_VC_RUN_OFS 0x2028 + .extern mips_cm_base .set noreorder @@ -60,6 +64,37 @@ nop .endm + /* + * Set dest to non-zero if the core supports MIPSr6 multithreading + * (ie. VPs), else zero. If MIPSr6 multithreading is not supported then + * branch to nomt. + */ + .macro has_vp dest, nomt + mfc0 \dest, CP0_CONFIG, 1 + bgez \dest, \nomt + mfc0 \dest, CP0_CONFIG, 2 + bgez \dest, \nomt + mfc0 \dest, CP0_CONFIG, 3 + bgez \dest, \nomt + mfc0 \dest, CP0_CONFIG, 4 + bgez \dest, \nomt + mfc0 \dest, CP0_CONFIG, 5 + andi \dest, \dest, MIPS_CONF5_VP + beqz \dest, \nomt + nop + .endm + + /* Calculate an uncached address for the CM GCRs */ + .macro cmgcrb dest + .set push + .set noat + MFC0 $1, CP0_CMGCRBASE + PTR_SLL $1, $1, 4 + PTR_LI \dest, UNCAC_BASE + PTR_ADDU \dest, \dest, $1 + .set pop + .endm + .section .text.cps-vec .balign 0x1000 @@ -90,120 +125,64 @@ not_nmi: li t0, ST0_CU1 | ST0_CU0 | ST0_BEV | STATUS_BITDEPS mtc0 t0, CP0_STATUS - /* - * Clear the bits used to index the caches. Note that the architecture - * dictates that writing to any of TagLo or TagHi selects 0 or 2 should - * be valid for all MIPS32 CPUs, even those for which said writes are - * unnecessary. - */ - mtc0 zero, CP0_TAGLO, 0 - mtc0 zero, CP0_TAGHI, 0 - mtc0 zero, CP0_TAGLO, 2 - mtc0 zero, CP0_TAGHI, 2 - ehb - - /* Primary cache configuration is indicated by Config1 */ - mfc0 v0, CP0_CONFIG, 1 - - /* Detect I-cache line size */ - _EXT t0, v0, MIPS_CONF1_IL_SHF, MIPS_CONF1_IL_SZ - beqz t0, icache_done - li t1, 2 - sllv t0, t1, t0 - - /* Detect I-cache size */ - _EXT t1, v0, MIPS_CONF1_IS_SHF, MIPS_CONF1_IS_SZ - xori t2, t1, 0x7 - beqz t2, 1f - li t3, 32 - addiu t1, t1, 1 - sllv t1, t3, t1 -1: /* At this point t1 == I-cache sets per way */ - _EXT t2, v0, MIPS_CONF1_IA_SHF, MIPS_CONF1_IA_SZ - addiu t2, t2, 1 - mul t1, t1, t0 - mul t1, t1, t2 - - li a0, CKSEG0 - PTR_ADD a1, a0, t1 -1: cache Index_Store_Tag_I, 0(a0) - PTR_ADD a0, a0, t0 - bne a0, a1, 1b + /* Skip cache & coherence setup if we're already coherent */ + cmgcrb v1 + lw s7, GCR_CL_COHERENCE_OFS(v1) + bnez s7, 1f nop -icache_done: - /* Detect D-cache line size */ - _EXT t0, v0, MIPS_CONF1_DL_SHF, MIPS_CONF1_DL_SZ - beqz t0, dcache_done - li t1, 2 - sllv t0, t1, t0 - - /* Detect D-cache size */ - _EXT t1, v0, MIPS_CONF1_DS_SHF, MIPS_CONF1_DS_SZ - xori t2, t1, 0x7 - beqz t2, 1f - li t3, 32 - addiu t1, t1, 1 - sllv t1, t3, t1 -1: /* At this point t1 == D-cache sets per way */ - _EXT t2, v0, MIPS_CONF1_DA_SHF, MIPS_CONF1_DA_SZ - addiu t2, t2, 1 - mul t1, t1, t0 - mul t1, t1, t2 + /* Initialize the L1 caches */ + jal mips_cps_cache_init + nop - li a0, CKSEG0 - PTR_ADDU a1, a0, t1 - PTR_SUBU a1, a1, t0 -1: cache Index_Store_Tag_D, 0(a0) - bne a0, a1, 1b - PTR_ADD a0, a0, t0 -dcache_done: + /* Enter the coherent domain */ + li t0, 0xff + sw t0, GCR_CL_COHERENCE_OFS(v1) + ehb /* Set Kseg0 CCA to that in s0 */ - mfc0 t0, CP0_CONFIG +1: mfc0 t0, CP0_CONFIG ori t0, 0x7 xori t0, 0x7 or t0, t0, s0 mtc0 t0, CP0_CONFIG ehb - /* Calculate an uncached address for the CM GCRs */ - MFC0 v1, CP0_CMGCRBASE - PTR_SLL v1, v1, 4 - PTR_LI t0, UNCAC_BASE - PTR_ADDU v1, v1, t0 - - /* Enter the coherent domain */ - li t0, 0xff - sw t0, GCR_CL_COHERENCE_OFS(v1) - ehb - /* Jump to kseg0 */ PTR_LA t0, 1f jr t0 nop /* - * We're up, cached & coherent. Perform any further required core-level - * initialisation. + * We're up, cached & coherent. Perform any EVA initialization necessary + * before we access memory. */ -1: jal mips_cps_core_init +1: eva_init + + /* Retrieve boot configuration pointers */ + jal mips_cps_get_bootcfg + nop + + /* Skip core-level init if we started up coherent */ + bnez s7, 1f nop - /* Do any EVA initialization if necessary */ - eva_init + /* Perform any further required core-level initialisation */ + jal mips_cps_core_init + nop /* * Boot any other VPEs within this core that should be online, and * deactivate this VPE if it should be offline. */ + move a1, t9 jal mips_cps_boot_vpes - nop + move a0, v0 /* Off we go! */ - PTR_L t1, VPEBOOTCFG_PC(v0) - PTR_L gp, VPEBOOTCFG_GP(v0) - PTR_L sp, VPEBOOTCFG_SP(v0) +1: PTR_L t1, VPEBOOTCFG_PC(v1) + PTR_L gp, VPEBOOTCFG_GP(v1) + PTR_L sp, VPEBOOTCFG_SP(v1) jr t1 nop END(mips_cps_core_entry) @@ -245,7 +224,6 @@ LEAF(excep_intex) .org 0x480 LEAF(excep_ejtag) - DUMP_EXCEP("EJTAG") PTR_LA k0, ejtag_debug_handler jr k0 nop @@ -323,22 +301,35 @@ LEAF(mips_cps_core_init) nop END(mips_cps_core_init) -LEAF(mips_cps_boot_vpes) - /* Retrieve CM base address */ - PTR_LA t0, mips_cm_base - PTR_L t0, 0(t0) - +/** + * mips_cps_get_bootcfg() - retrieve boot configuration pointers + * + * Returns: pointer to struct core_boot_config in v0, pointer to + * struct vpe_boot_config in v1, VPE ID in t9 + */ +LEAF(mips_cps_get_bootcfg) /* Calculate a pointer to this cores struct core_boot_config */ + cmgcrb t0 lw t0, GCR_CL_ID_OFS(t0) li t1, COREBOOTCFG_SIZE mul t0, t0, t1 PTR_LA t1, mips_cps_core_bootcfg PTR_L t1, 0(t1) - PTR_ADDU t0, t0, t1 + PTR_ADDU v0, t0, t1 /* Calculate this VPEs ID. If the core doesn't support MT use 0 */ li t9, 0 -#ifdef CONFIG_MIPS_MT_SMP +#if defined(CONFIG_CPU_MIPSR6) + has_vp ta2, 1f + + /* + * Assume non-contiguous numbering. Perhaps some day we'll need + * to handle contiguous VP numbering, but no such systems yet + * exist. + */ + mfc0 t9, $3, 1 + andi t9, t9, 0xff +#elif defined(CONFIG_MIPS_MT_SMP) has_mt ta2, 1f /* Find the number of VPEs present in the core */ @@ -362,22 +353,47 @@ LEAF(mips_cps_boot_vpes) 1: /* Calculate a pointer to this VPEs struct vpe_boot_config */ li t1, VPEBOOTCFG_SIZE - mul v0, t9, t1 - PTR_L ta3, COREBOOTCFG_VPECONFIG(t0) - PTR_ADDU v0, v0, ta3 - -#ifdef CONFIG_MIPS_MT_SMP + mul v1, t9, t1 + PTR_L ta3, COREBOOTCFG_VPECONFIG(v0) + PTR_ADDU v1, v1, ta3 - /* If the core doesn't support MT then return */ - bnez ta2, 1f - nop jr ra nop + END(mips_cps_get_bootcfg) + +LEAF(mips_cps_boot_vpes) + PTR_L ta2, COREBOOTCFG_VPEMASK(a0) + PTR_L ta3, COREBOOTCFG_VPECONFIG(a0) + +#if defined(CONFIG_CPU_MIPSR6) + + has_vp t0, 5f + + /* Find base address of CPC */ + cmgcrb t3 + PTR_L t1, GCR_CPC_BASE_OFS(t3) + PTR_LI t2, ~0x7fff + and t1, t1, t2 + PTR_LI t2, UNCAC_BASE + PTR_ADD t1, t1, t2 + + /* Start any other VPs that ought to be running */ + PTR_S ta2, CPC_CL_VC_RUN_OFS(t1) + + /* Ensure this VP stops running if it shouldn't be */ + not ta2 + PTR_S ta2, CPC_CL_VC_STOP_OFS(t1) + ehb + +#elif defined(CONFIG_MIPS_MT) .set push .set mt -1: /* Enter VPE configuration state */ + /* If the core doesn't support MT then return */ + has_mt t0, 5f + + /* Enter VPE configuration state */ dvpe PTR_LA t1, 1f jr.hb t1 @@ -388,7 +404,6 @@ LEAF(mips_cps_boot_vpes) ehb /* Loop through each VPE */ - PTR_L ta2, COREBOOTCFG_VPEMASK(t0) move t8, ta2 li ta1, 0 @@ -465,7 +480,7 @@ LEAF(mips_cps_boot_vpes) /* Check whether this VPE is meant to be running */ li t0, 1 - sll t0, t0, t9 + sll t0, t0, a1 and t0, t0, t8 bnez t0, 2f nop @@ -482,10 +497,84 @@ LEAF(mips_cps_boot_vpes) #endif /* CONFIG_MIPS_MT_SMP */ /* Return */ - jr ra +5: jr ra nop END(mips_cps_boot_vpes) +LEAF(mips_cps_cache_init) + /* + * Clear the bits used to index the caches. Note that the architecture + * dictates that writing to any of TagLo or TagHi selects 0 or 2 should + * be valid for all MIPS32 CPUs, even those for which said writes are + * unnecessary. + */ + mtc0 zero, CP0_TAGLO, 0 + mtc0 zero, CP0_TAGHI, 0 + mtc0 zero, CP0_TAGLO, 2 + mtc0 zero, CP0_TAGHI, 2 + ehb + + /* Primary cache configuration is indicated by Config1 */ + mfc0 v0, CP0_CONFIG, 1 + + /* Detect I-cache line size */ + _EXT t0, v0, MIPS_CONF1_IL_SHF, MIPS_CONF1_IL_SZ + beqz t0, icache_done + li t1, 2 + sllv t0, t1, t0 + + /* Detect I-cache size */ + _EXT t1, v0, MIPS_CONF1_IS_SHF, MIPS_CONF1_IS_SZ + xori t2, t1, 0x7 + beqz t2, 1f + li t3, 32 + addiu t1, t1, 1 + sllv t1, t3, t1 +1: /* At this point t1 == I-cache sets per way */ + _EXT t2, v0, MIPS_CONF1_IA_SHF, MIPS_CONF1_IA_SZ + addiu t2, t2, 1 + mul t1, t1, t0 + mul t1, t1, t2 + + li a0, CKSEG0 + PTR_ADD a1, a0, t1 +1: cache Index_Store_Tag_I, 0(a0) + PTR_ADD a0, a0, t0 + bne a0, a1, 1b + nop +icache_done: + + /* Detect D-cache line size */ + _EXT t0, v0, MIPS_CONF1_DL_SHF, MIPS_CONF1_DL_SZ + beqz t0, dcache_done + li t1, 2 + sllv t0, t1, t0 + + /* Detect D-cache size */ + _EXT t1, v0, MIPS_CONF1_DS_SHF, MIPS_CONF1_DS_SZ + xori t2, t1, 0x7 + beqz t2, 1f + li t3, 32 + addiu t1, t1, 1 + sllv t1, t3, t1 +1: /* At this point t1 == D-cache sets per way */ + _EXT t2, v0, MIPS_CONF1_DA_SHF, MIPS_CONF1_DA_SZ + addiu t2, t2, 1 + mul t1, t1, t0 + mul t1, t1, t2 + + li a0, CKSEG0 + PTR_ADDU a1, a0, t1 + PTR_SUBU a1, a1, t0 +1: cache Index_Store_Tag_D, 0(a0) + bne a0, a1, 1b + PTR_ADD a0, a0, t0 +dcache_done: + + jr ra + nop + END(mips_cps_cache_init) + #if defined(CONFIG_MIPS_CPS_PM) && defined(CONFIG_CPU_PM) /* Calculate a pointer to this CPUs struct mips_static_suspend_state */ diff --git a/arch/mips/kernel/cpu-probe.c b/arch/mips/kernel/cpu-probe.c index 6b9064499bd3..e38442d5cd6e 100644 --- a/arch/mips/kernel/cpu-probe.c +++ b/arch/mips/kernel/cpu-probe.c @@ -99,6 +99,161 @@ static inline void cpu_set_fpu_fcsr_mask(struct cpuinfo_mips *c) } /* + * Determine the IEEE 754 NaN encodings and ABS.fmt/NEG.fmt execution modes + * supported by FPU hardware. + */ +static void cpu_set_fpu_2008(struct cpuinfo_mips *c) +{ + if (c->isa_level & (MIPS_CPU_ISA_M32R1 | MIPS_CPU_ISA_M64R1 | + MIPS_CPU_ISA_M32R2 | MIPS_CPU_ISA_M64R2 | + MIPS_CPU_ISA_M32R6 | MIPS_CPU_ISA_M64R6)) { + unsigned long sr, fir, fcsr, fcsr0, fcsr1; + + sr = read_c0_status(); + __enable_fpu(FPU_AS_IS); + + fir = read_32bit_cp1_register(CP1_REVISION); + if (fir & MIPS_FPIR_HAS2008) { + fcsr = read_32bit_cp1_register(CP1_STATUS); + + fcsr0 = fcsr & ~(FPU_CSR_ABS2008 | FPU_CSR_NAN2008); + write_32bit_cp1_register(CP1_STATUS, fcsr0); + fcsr0 = read_32bit_cp1_register(CP1_STATUS); + + fcsr1 = fcsr | FPU_CSR_ABS2008 | FPU_CSR_NAN2008; + write_32bit_cp1_register(CP1_STATUS, fcsr1); + fcsr1 = read_32bit_cp1_register(CP1_STATUS); + + write_32bit_cp1_register(CP1_STATUS, fcsr); + + if (!(fcsr0 & FPU_CSR_NAN2008)) + c->options |= MIPS_CPU_NAN_LEGACY; + if (fcsr1 & FPU_CSR_NAN2008) + c->options |= MIPS_CPU_NAN_2008; + + if ((fcsr0 ^ fcsr1) & FPU_CSR_ABS2008) + c->fpu_msk31 &= ~FPU_CSR_ABS2008; + else + c->fpu_csr31 |= fcsr & FPU_CSR_ABS2008; + + if ((fcsr0 ^ fcsr1) & FPU_CSR_NAN2008) + c->fpu_msk31 &= ~FPU_CSR_NAN2008; + else + c->fpu_csr31 |= fcsr & FPU_CSR_NAN2008; + } else { + c->options |= MIPS_CPU_NAN_LEGACY; + } + + write_c0_status(sr); + } else { + c->options |= MIPS_CPU_NAN_LEGACY; + } +} + +/* + * IEEE 754 conformance mode to use. Affects the NaN encoding and the + * ABS.fmt/NEG.fmt execution mode. + */ +static enum { STRICT, LEGACY, STD2008, RELAXED } ieee754 = STRICT; + +/* + * Set the IEEE 754 NaN encodings and the ABS.fmt/NEG.fmt execution modes + * to support by the FPU emulator according to the IEEE 754 conformance + * mode selected. Note that "relaxed" straps the emulator so that it + * allows 2008-NaN binaries even for legacy processors. + */ +static void cpu_set_nofpu_2008(struct cpuinfo_mips *c) +{ + c->options &= ~(MIPS_CPU_NAN_2008 | MIPS_CPU_NAN_LEGACY); + c->fpu_csr31 &= ~(FPU_CSR_ABS2008 | FPU_CSR_NAN2008); + c->fpu_msk31 &= ~(FPU_CSR_ABS2008 | FPU_CSR_NAN2008); + + switch (ieee754) { + case STRICT: + if (c->isa_level & (MIPS_CPU_ISA_M32R1 | MIPS_CPU_ISA_M64R1 | + MIPS_CPU_ISA_M32R2 | MIPS_CPU_ISA_M64R2 | + MIPS_CPU_ISA_M32R6 | MIPS_CPU_ISA_M64R6)) { + c->options |= MIPS_CPU_NAN_2008 | MIPS_CPU_NAN_LEGACY; + } else { + c->options |= MIPS_CPU_NAN_LEGACY; + c->fpu_msk31 |= FPU_CSR_ABS2008 | FPU_CSR_NAN2008; + } + break; + case LEGACY: + c->options |= MIPS_CPU_NAN_LEGACY; + c->fpu_msk31 |= FPU_CSR_ABS2008 | FPU_CSR_NAN2008; + break; + case STD2008: + c->options |= MIPS_CPU_NAN_2008; + c->fpu_csr31 |= FPU_CSR_ABS2008 | FPU_CSR_NAN2008; + c->fpu_msk31 |= FPU_CSR_ABS2008 | FPU_CSR_NAN2008; + break; + case RELAXED: + c->options |= MIPS_CPU_NAN_2008 | MIPS_CPU_NAN_LEGACY; + break; + } +} + +/* + * Override the IEEE 754 NaN encoding and ABS.fmt/NEG.fmt execution mode + * according to the "ieee754=" parameter. + */ +static void cpu_set_nan_2008(struct cpuinfo_mips *c) +{ + switch (ieee754) { + case STRICT: + mips_use_nan_legacy = !!cpu_has_nan_legacy; + mips_use_nan_2008 = !!cpu_has_nan_2008; + break; + case LEGACY: + mips_use_nan_legacy = !!cpu_has_nan_legacy; + mips_use_nan_2008 = !cpu_has_nan_legacy; + break; + case STD2008: + mips_use_nan_legacy = !cpu_has_nan_2008; + mips_use_nan_2008 = !!cpu_has_nan_2008; + break; + case RELAXED: + mips_use_nan_legacy = true; + mips_use_nan_2008 = true; + break; + } +} + +/* + * IEEE 754 NaN encoding and ABS.fmt/NEG.fmt execution mode override + * settings: + * + * strict: accept binaries that request a NaN encoding supported by the FPU + * legacy: only accept legacy-NaN binaries + * 2008: only accept 2008-NaN binaries + * relaxed: accept any binaries regardless of whether supported by the FPU + */ +static int __init ieee754_setup(char *s) +{ + if (!s) + return -1; + else if (!strcmp(s, "strict")) + ieee754 = STRICT; + else if (!strcmp(s, "legacy")) + ieee754 = LEGACY; + else if (!strcmp(s, "2008")) + ieee754 = STD2008; + else if (!strcmp(s, "relaxed")) + ieee754 = RELAXED; + else + return -1; + + if (!(boot_cpu_data.options & MIPS_CPU_FPU)) + cpu_set_nofpu_2008(&boot_cpu_data); + cpu_set_nan_2008(&boot_cpu_data); + + return 0; +} + +early_param("ieee754", ieee754_setup); + +/* * Set the FIR feature flags for the FPU emulator. */ static void cpu_set_nofpu_id(struct cpuinfo_mips *c) @@ -113,6 +268,8 @@ static void cpu_set_nofpu_id(struct cpuinfo_mips *c) if (c->isa_level & (MIPS_CPU_ISA_M32R2 | MIPS_CPU_ISA_M64R2 | MIPS_CPU_ISA_M32R6 | MIPS_CPU_ISA_M64R6)) value |= MIPS_FPIR_F64 | MIPS_FPIR_L | MIPS_FPIR_W; + if (c->options & MIPS_CPU_NAN_2008) + value |= MIPS_FPIR_HAS2008; c->fpu_id = value; } @@ -137,6 +294,8 @@ static void cpu_set_fpu_opts(struct cpuinfo_mips *c) } cpu_set_fpu_fcsr_mask(c); + cpu_set_fpu_2008(c); + cpu_set_nan_2008(c); } /* @@ -147,6 +306,8 @@ static void cpu_set_nofpu_opts(struct cpuinfo_mips *c) c->options &= ~MIPS_CPU_FPU; c->fpu_msk31 = mips_nofpu_msk31; + cpu_set_nofpu_2008(c); + cpu_set_nan_2008(c); cpu_set_nofpu_id(c); } @@ -635,6 +796,8 @@ static inline unsigned int decode_config5(struct cpuinfo_mips *c) if (config5 & MIPS_CONF5_MVH) c->options |= MIPS_CPU_XPA; #endif + if (cpu_has_mips_r6 && (config5 & MIPS_CONF5_VP)) + c->options |= MIPS_CPU_VP; return config5 & MIPS_CONF_M; } diff --git a/arch/mips/kernel/elf.c b/arch/mips/kernel/elf.c index 3afffc30ee12..624e15dbd405 100644 --- a/arch/mips/kernel/elf.c +++ b/arch/mips/kernel/elf.c @@ -8,9 +8,18 @@ * option) any later version. */ +#include <linux/binfmts.h> #include <linux/elf.h> +#include <linux/export.h> #include <linux/sched.h> +#include <asm/cpu-features.h> +#include <asm/cpu-info.h> + +/* Whether to accept legacy-NaN and 2008-NaN user binaries. */ +bool mips_use_nan_legacy; +bool mips_use_nan_2008; + /* FPU modes */ enum { FP_FRE, @@ -68,15 +77,23 @@ static struct mode_req none_req = { true, true, false, true, true }; int arch_elf_pt_proc(void *_ehdr, void *_phdr, struct file *elf, bool is_interp, struct arch_elf_state *state) { - struct elf32_hdr *ehdr32 = _ehdr; + union { + struct elf32_hdr e32; + struct elf64_hdr e64; + } *ehdr = _ehdr; struct elf32_phdr *phdr32 = _phdr; struct elf64_phdr *phdr64 = _phdr; struct mips_elf_abiflags_v0 abiflags; + bool elf32; + u32 flags; int ret; - /* Lets see if this is an O32 ELF */ - if (ehdr32->e_ident[EI_CLASS] == ELFCLASS32) { - if (ehdr32->e_flags & EF_MIPS_FP64) { + elf32 = ehdr->e32.e_ident[EI_CLASS] == ELFCLASS32; + flags = elf32 ? ehdr->e32.e_flags : ehdr->e64.e_flags; + + /* Let's see if this is an O32 ELF */ + if (elf32) { + if (flags & EF_MIPS_FP64) { /* * Set MIPS_ABI_FP_OLD_64 for EF_MIPS_FP64. We will override it * later if needed @@ -120,13 +137,50 @@ int arch_elf_pt_proc(void *_ehdr, void *_phdr, struct file *elf, return 0; } -int arch_check_elf(void *_ehdr, bool has_interpreter, +int arch_check_elf(void *_ehdr, bool has_interpreter, void *_interp_ehdr, struct arch_elf_state *state) { - struct elf32_hdr *ehdr = _ehdr; + union { + struct elf32_hdr e32; + struct elf64_hdr e64; + } *ehdr = _ehdr; + union { + struct elf32_hdr e32; + struct elf64_hdr e64; + } *iehdr = _interp_ehdr; struct mode_req prog_req, interp_req; int fp_abi, interp_fp_abi, abi0, abi1, max_abi; - bool is_mips64; + bool elf32; + u32 flags; + + elf32 = ehdr->e32.e_ident[EI_CLASS] == ELFCLASS32; + flags = elf32 ? ehdr->e32.e_flags : ehdr->e64.e_flags; + + /* + * Determine the NaN personality, reject the binary if not allowed. + * Also ensure that any interpreter matches the executable. + */ + if (flags & EF_MIPS_NAN2008) { + if (mips_use_nan_2008) + state->nan_2008 = 1; + else + return -ENOEXEC; + } else { + if (mips_use_nan_legacy) + state->nan_2008 = 0; + else + return -ENOEXEC; + } + if (has_interpreter) { + bool ielf32; + u32 iflags; + + ielf32 = iehdr->e32.e_ident[EI_CLASS] == ELFCLASS32; + iflags = ielf32 ? iehdr->e32.e_flags : iehdr->e64.e_flags; + + if ((flags ^ iflags) & EF_MIPS_NAN2008) + return -ELIBBAD; + } if (!config_enabled(CONFIG_MIPS_O32_FP64_SUPPORT)) return 0; @@ -142,21 +196,18 @@ int arch_check_elf(void *_ehdr, bool has_interpreter, abi0 = abi1 = fp_abi; } - is_mips64 = (ehdr->e_ident[EI_CLASS] == ELFCLASS64) || - (ehdr->e_flags & EF_MIPS_ABI2); + if (elf32 && !(flags & EF_MIPS_ABI2)) { + /* Default to a mode capable of running code expecting FR=0 */ + state->overall_fp_mode = cpu_has_mips_r6 ? FP_FRE : FP_FR0; - if (is_mips64) { + /* Allow all ABIs we know about */ + max_abi = MIPS_ABI_FP_64A; + } else { /* MIPS64 code always uses FR=1, thus the default is easy */ state->overall_fp_mode = FP_FR1; /* Disallow access to the various FPXX & FP64 ABIs */ max_abi = MIPS_ABI_FP_SOFT; - } else { - /* Default to a mode capable of running code expecting FR=0 */ - state->overall_fp_mode = cpu_has_mips_r6 ? FP_FRE : FP_FR0; - - /* Allow all ABIs we know about */ - max_abi = MIPS_ABI_FP_64A; } if ((abi0 > max_abi && abi0 != MIPS_ABI_FP_UNKNOWN) || @@ -254,3 +305,91 @@ void mips_set_personality_fp(struct arch_elf_state *state) BUG(); } } + +/* + * Select the IEEE 754 NaN encoding and ABS.fmt/NEG.fmt execution mode + * in FCSR according to the ELF NaN personality. + */ +void mips_set_personality_nan(struct arch_elf_state *state) +{ + struct cpuinfo_mips *c = &boot_cpu_data; + struct task_struct *t = current; + + t->thread.fpu.fcr31 = c->fpu_csr31; + switch (state->nan_2008) { + case 0: + break; + case 1: + if (!(c->fpu_msk31 & FPU_CSR_NAN2008)) + t->thread.fpu.fcr31 |= FPU_CSR_NAN2008; + if (!(c->fpu_msk31 & FPU_CSR_ABS2008)) + t->thread.fpu.fcr31 |= FPU_CSR_ABS2008; + break; + default: + BUG(); + } +} + +static int noexec = EXSTACK_DEFAULT; + +/* + * kernel parameter: noexec=on|off + * + * Force indicating stack and heap as non-executable or + * executable regardless of PT_GNU_STACK entry or CPU XI + * (execute inhibit) support. Valid valuess are: on, off. + * + * noexec=on: force indicating non-executable + * stack and heap + * noexec=off: force indicating executable + * stack and heap + * + * If this parameter is omitted, stack and heap will be + * indicated non-executable or executable as they are + * actually set up, which depends on PT_GNU_STACK entry + * and possibly other factors (for instance, CPU XI + * support). + * + * NOTE: Using noexec=on on a system without CPU XI + * support is not recommended since there is no actual + * HW support that provide non-executable stack/heap. + * Use only for debugging purposes and not in a + * production environment. + */ +static int __init noexec_setup(char *str) +{ + if (!strcmp(str, "on")) + noexec = EXSTACK_DISABLE_X; + else if (!strcmp(str, "off")) + noexec = EXSTACK_ENABLE_X; + else + pr_err("Malformed noexec format! noexec=on|off\n"); + + return 1; +} +__setup("noexec=", noexec_setup); + +int mips_elf_read_implies_exec(void *elf_ex, int exstack) +{ + switch (noexec) { + case EXSTACK_DISABLE_X: + return 0; + case EXSTACK_ENABLE_X: + return 1; + default: + break; + } + + if (exstack != EXSTACK_DISABLE_X) { + /* The binary doesn't request a non-executable stack */ + return 1; + } + + if (!cpu_has_rixi) { + /* The CPU doesn't support non-executable memory */ + return 1; + } + + return 0; +} +EXPORT_SYMBOL(mips_elf_read_implies_exec); diff --git a/arch/mips/kernel/head.S b/arch/mips/kernel/head.S index 4e4cc5b9a771..462989e89ec9 100644 --- a/arch/mips/kernel/head.S +++ b/arch/mips/kernel/head.S @@ -94,21 +94,24 @@ NESTED(kernel_entry, 16, sp) # kernel entry point jr t0 0: +#ifdef CONFIG_USE_OF #ifdef CONFIG_MIPS_RAW_APPENDED_DTB - PTR_LA t0, __appended_dtb + PTR_LA t2, __appended_dtb #ifdef CONFIG_CPU_BIG_ENDIAN li t1, 0xd00dfeed #else li t1, 0xedfe0dd0 #endif - lw t2, (t0) - bne t1, t2, not_found - nop + lw t0, (t2) + beq t0, t1, dtb_found +#endif + li t1, -2 + beq a0, t1, dtb_found + move t2, a1 - move a1, t0 - PTR_LI a0, -2 -not_found: + li t2, 0 +dtb_found: #endif PTR_LA t0, __bss_start # clear .bss LONG_S zero, (t0) @@ -123,6 +126,10 @@ not_found: LONG_S a2, fw_arg2 LONG_S a3, fw_arg3 +#ifdef CONFIG_USE_OF + LONG_S t2, fw_passed_dtb +#endif + MTC0 zero, CP0_CONTEXT # clear context register PTR_LA $28, init_thread_union /* Set the SP after an empty pt_regs. */ diff --git a/arch/mips/kernel/linux32.c b/arch/mips/kernel/linux32.c index 0b29646bcee7..50fb62544df7 100644 --- a/arch/mips/kernel/linux32.c +++ b/arch/mips/kernel/linux32.c @@ -26,7 +26,6 @@ #include <linux/utsname.h> #include <linux/personality.h> #include <linux/dnotify.h> -#include <linux/module.h> #include <linux/binfmts.h> #include <linux/security.h> #include <linux/compat.h> diff --git a/arch/mips/kernel/mips-cm.c b/arch/mips/kernel/mips-cm.c index 1448c1f43d4e..36bd476d0760 100644 --- a/arch/mips/kernel/mips-cm.c +++ b/arch/mips/kernel/mips-cm.c @@ -24,7 +24,7 @@ static char *cm2_tr[8] = { "0x04", "cpc", "0x06", "0x07" }; -/* CM3 Tag ECC transation type */ +/* CM3 Tag ECC transaction type */ static char *cm3_tr[16] = { [0x0] = "ReqNoData", [0x1] = "0x1", @@ -265,15 +265,34 @@ void mips_cm_lock_other(unsigned int core, unsigned int vp) u32 val; preempt_disable(); - curr_core = current_cpu_data.core; - spin_lock_irqsave(&per_cpu(cm_core_lock, curr_core), - per_cpu(cm_core_lock_flags, curr_core)); if (mips_cm_revision() >= CM_REV_CM3) { val = core << CM3_GCR_Cx_OTHER_CORE_SHF; val |= vp << CM3_GCR_Cx_OTHER_VP_SHF; + + /* + * We need to disable interrupts in SMP systems in order to + * ensure that we don't interrupt the caller with code which + * may modify the redirect register. We do so here in a + * slightly obscure way by using a spin lock, since this has + * the neat property of also catching any nested uses of + * mips_cm_lock_other() leading to a deadlock or a nice warning + * with lockdep enabled. + */ + spin_lock_irqsave(this_cpu_ptr(&cm_core_lock), + *this_cpu_ptr(&cm_core_lock_flags)); } else { - BUG_ON(vp != 0); + WARN_ON(vp != 0); + + /* + * We only have a GCR_CL_OTHER per core in systems with + * CM 2.5 & older, so have to ensure other VP(E)s don't + * race with us. + */ + curr_core = current_cpu_data.core; + spin_lock_irqsave(&per_cpu(cm_core_lock, curr_core), + per_cpu(cm_core_lock_flags, curr_core)); + val = core << CM_GCR_Cx_OTHER_CORENUM_SHF; } @@ -288,10 +307,17 @@ void mips_cm_lock_other(unsigned int core, unsigned int vp) void mips_cm_unlock_other(void) { - unsigned curr_core = current_cpu_data.core; + unsigned int curr_core; + + if (mips_cm_revision() < CM_REV_CM3) { + curr_core = current_cpu_data.core; + spin_unlock_irqrestore(&per_cpu(cm_core_lock, curr_core), + per_cpu(cm_core_lock_flags, curr_core)); + } else { + spin_unlock_irqrestore(this_cpu_ptr(&cm_core_lock), + *this_cpu_ptr(&cm_core_lock_flags)); + } - spin_unlock_irqrestore(&per_cpu(cm_core_lock, curr_core), - per_cpu(cm_core_lock_flags, curr_core)); preempt_enable(); } diff --git a/arch/mips/kernel/mips-cpc.c b/arch/mips/kernel/mips-cpc.c index 566b8d2c092c..3491ee05737c 100644 --- a/arch/mips/kernel/mips-cpc.c +++ b/arch/mips/kernel/mips-cpc.c @@ -10,6 +10,8 @@ #include <linux/errno.h> #include <linux/percpu.h> +#include <linux/of.h> +#include <linux/of_address.h> #include <linux/spinlock.h> #include <asm/mips-cm.h> @@ -21,6 +23,22 @@ static DEFINE_PER_CPU_ALIGNED(spinlock_t, cpc_core_lock); static DEFINE_PER_CPU_ALIGNED(unsigned long, cpc_core_lock_flags); +phys_addr_t __weak mips_cpc_default_phys_base(void) +{ + struct device_node *cpc_node; + struct resource res; + int err; + + cpc_node = of_find_compatible_node(of_root, NULL, "mti,mips-cpc"); + if (cpc_node) { + err = of_address_to_resource(cpc_node, 0, &res); + if (!err) + return res.start; + } + + return 0; +} + /** * mips_cpc_phys_base - retrieve the physical base address of the CPC * @@ -43,8 +61,12 @@ static phys_addr_t mips_cpc_phys_base(void) if (cpc_base & CM_GCR_CPC_BASE_CPCEN_MSK) return cpc_base & CM_GCR_CPC_BASE_CPCBASE_MSK; - /* Otherwise, give it the default address & enable it */ + /* Otherwise, use the default address */ cpc_base = mips_cpc_default_phys_base(); + if (!cpc_base) + return cpc_base; + + /* Enable the CPC, mapped at the default address */ write_gcr_cpc_base(cpc_base | CM_GCR_CPC_BASE_CPCEN_MSK); return cpc_base; } diff --git a/arch/mips/kernel/mips-r2-to-r6-emul.c b/arch/mips/kernel/mips-r2-to-r6-emul.c index e3384065f5e7..d7fbcc56c66f 100644 --- a/arch/mips/kernel/mips-r2-to-r6-emul.c +++ b/arch/mips/kernel/mips-r2-to-r6-emul.c @@ -15,7 +15,6 @@ #include <linux/debugfs.h> #include <linux/init.h> #include <linux/kernel.h> -#include <linux/module.h> #include <linux/ptrace.h> #include <linux/seq_file.h> @@ -283,7 +282,7 @@ static int jr_func(struct pt_regs *regs, u32 ir) err = mipsr6_emul(regs, nir); if (err > 0) { regs->cp0_epc = nepc; - err = mips_dsemul(regs, nir, cepc); + err = mips_dsemul(regs, nir, epc, cepc); if (err == SIGILL) err = SIGEMT; MIPS_R2_STATS(dsemul); @@ -900,7 +899,7 @@ static inline int mipsr2_find_op_func(struct pt_regs *regs, u32 inst, * mipsr2_decoder: Decode and emulate a MIPS R2 instruction * @regs: Process register set * @inst: Instruction to decode and emulate - * @fcr31: Floating Point Control and Status Register returned + * @fcr31: Floating Point Control and Status Register Cause bits returned */ int mipsr2_decoder(struct pt_regs *regs, u32 inst, unsigned long *fcr31) { @@ -941,42 +940,42 @@ repeat: switch (rt) { case tgei_op: if ((long)regs->regs[rs] >= MIPSInst_SIMM(inst)) - do_trap_or_bp(regs, 0, "TGEI"); + do_trap_or_bp(regs, 0, 0, "TGEI"); MIPS_R2_STATS(traps); break; case tgeiu_op: if (regs->regs[rs] >= MIPSInst_UIMM(inst)) - do_trap_or_bp(regs, 0, "TGEIU"); + do_trap_or_bp(regs, 0, 0, "TGEIU"); MIPS_R2_STATS(traps); break; case tlti_op: if ((long)regs->regs[rs] < MIPSInst_SIMM(inst)) - do_trap_or_bp(regs, 0, "TLTI"); + do_trap_or_bp(regs, 0, 0, "TLTI"); MIPS_R2_STATS(traps); break; case tltiu_op: if (regs->regs[rs] < MIPSInst_UIMM(inst)) - do_trap_or_bp(regs, 0, "TLTIU"); + do_trap_or_bp(regs, 0, 0, "TLTIU"); MIPS_R2_STATS(traps); break; case teqi_op: if (regs->regs[rs] == MIPSInst_SIMM(inst)) - do_trap_or_bp(regs, 0, "TEQI"); + do_trap_or_bp(regs, 0, 0, "TEQI"); MIPS_R2_STATS(traps); break; case tnei_op: if (regs->regs[rs] != MIPSInst_SIMM(inst)) - do_trap_or_bp(regs, 0, "TNEI"); + do_trap_or_bp(regs, 0, 0, "TNEI"); MIPS_R2_STATS(traps); @@ -1033,7 +1032,7 @@ repeat: if (nir) { err = mipsr6_emul(regs, nir); if (err > 0) { - err = mips_dsemul(regs, nir, cpc); + err = mips_dsemul(regs, nir, epc, cpc); if (err == SIGILL) err = SIGEMT; MIPS_R2_STATS(dsemul); @@ -1082,7 +1081,7 @@ repeat: if (nir) { err = mipsr6_emul(regs, nir); if (err > 0) { - err = mips_dsemul(regs, nir, cpc); + err = mips_dsemul(regs, nir, epc, cpc); if (err == SIGILL) err = SIGEMT; MIPS_R2_STATS(dsemul); @@ -1097,10 +1096,20 @@ repeat: } break; - case beql_op: - case bnel_op: case blezl_op: case bgtzl_op: + /* + * For BLEZL and BGTZL, rt field must be set to 0. If this + * is not the case, this may be an encoding of a MIPS R6 + * instruction, so return to CPU execution if this occurs + */ + if (MIPSInst_RT(inst)) { + err = SIGILL; + break; + } + /* fall through */ + case beql_op: + case bnel_op: if (delay_slot(regs)) { err = SIGILL; break; @@ -1149,7 +1158,7 @@ repeat: if (nir) { err = mipsr6_emul(regs, nir); if (err > 0) { - err = mips_dsemul(regs, nir, cpc); + err = mips_dsemul(regs, nir, epc, cpc); if (err == SIGILL) err = SIGEMT; MIPS_R2_STATS(dsemul); @@ -1173,13 +1182,13 @@ fpu_emul: err = fpu_emulator_cop1Handler(regs, ¤t->thread.fpu, 0, &fault_addr); - *fcr31 = current->thread.fpu.fcr31; /* - * We can't allow the emulated instruction to leave any of - * the cause bits set in $fcr31. + * We can't allow the emulated instruction to leave any + * enabled Cause bits set in $fcr31. */ - current->thread.fpu.fcr31 &= ~FPU_CSR_ALL_X; + *fcr31 = res = mask_fcr31_x(current->thread.fpu.fcr31); + current->thread.fpu.fcr31 &= ~res; /* * this is a tricky issue - lose_fpu() uses LL/SC atomics @@ -2204,7 +2213,7 @@ fpu_emul: } /* - * Lets not return to userland just yet. It's constly and + * Let's not return to userland just yet. It's costly and * it's likely we have more R2 instructions to emulate */ if (!err && (pass++ < MIPS_R2_EMUL_TOTAL_PASS)) { @@ -2330,6 +2339,8 @@ static int mipsr2_stats_clear_show(struct seq_file *s, void *unused) __this_cpu_write((mipsr2bremustats).bgezl, 0); __this_cpu_write((mipsr2bremustats).bltzll, 0); __this_cpu_write((mipsr2bremustats).bgezll, 0); + __this_cpu_write((mipsr2bremustats).bltzall, 0); + __this_cpu_write((mipsr2bremustats).bgezall, 0); __this_cpu_write((mipsr2bremustats).bltzal, 0); __this_cpu_write((mipsr2bremustats).bgezal, 0); __this_cpu_write((mipsr2bremustats).beql, 0); diff --git a/arch/mips/kernel/perf_event_mipsxx.c b/arch/mips/kernel/perf_event_mipsxx.c index d7b8dd43147a..9bc1191b1ab0 100644 --- a/arch/mips/kernel/perf_event_mipsxx.c +++ b/arch/mips/kernel/perf_event_mipsxx.c @@ -530,7 +530,7 @@ static void mipspmu_enable(struct pmu *pmu) /* * MIPS performance counters can be per-TC. The control registers can - * not be directly accessed accross CPUs. Hence if we want to do global + * not be directly accessed across CPUs. Hence if we want to do global * control, we need cross CPU calls. on_each_cpu() can help us, but we * can not make sure this function is called with interrupts enabled. So * here we pause local counters and then grab a rwlock and leave the diff --git a/arch/mips/kernel/pm-cps.c b/arch/mips/kernel/pm-cps.c index 0b3e58a3189f..a3b602083149 100644 --- a/arch/mips/kernel/pm-cps.c +++ b/arch/mips/kernel/pm-cps.c @@ -223,11 +223,18 @@ static void __init cps_gen_cache_routine(u32 **pp, struct uasm_label **pl, uasm_build_label(pl, *pp, lbl); /* Generate the cache ops */ - for (i = 0; i < unroll_lines; i++) - uasm_i_cache(pp, op, i * cache->linesz, t0); + for (i = 0; i < unroll_lines; i++) { + if (cpu_has_mips_r6) { + uasm_i_cache(pp, op, 0, t0); + uasm_i_addiu(pp, t0, t0, cache->linesz); + } else { + uasm_i_cache(pp, op, i * cache->linesz, t0); + } + } - /* Update the base address */ - uasm_i_addiu(pp, t0, t0, unroll_lines * cache->linesz); + if (!cpu_has_mips_r6) + /* Update the base address */ + uasm_i_addiu(pp, t0, t0, unroll_lines * cache->linesz); /* Loop if we haven't reached the end address yet */ uasm_il_bne(pp, pr, t0, t1, lbl); @@ -264,14 +271,9 @@ static int __init cps_gen_flush_fsb(u32 **pp, struct uasm_label **pl, /* On older ones it's unavailable */ return -1; - /* CPUs which do not require the workaround */ - case CPU_P5600: - case CPU_I6400: - return 0; - default: - WARN_ONCE(1, "pm-cps: FSB flush unsupported for this CPU\n"); - return -1; + /* Assume that the CPU does not need this workaround */ + return 0; } /* @@ -471,7 +473,7 @@ static void * __init cps_gen_entry_code(unsigned cpu, enum cps_pm_state state) /* * Disable all but self interventions. The load from COHCTL is defined * by the interAptiv & proAptiv SUMs as ensuring that the operation - * resulting from the preceeding store is complete. + * resulting from the preceding store is complete. */ uasm_i_addiu(&p, t0, zero, 1 << cpu_data[cpu].core); uasm_i_sw(&p, t0, 0, r_pcohctl); diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c index fcbc4e57d765..fe61ce7ad9b1 100644 --- a/arch/mips/kernel/process.c +++ b/arch/mips/kernel/process.c @@ -30,6 +30,7 @@ #include <asm/asm.h> #include <asm/bootinfo.h> #include <asm/cpu.h> +#include <asm/dsemul.h> #include <asm/dsp.h> #include <asm/fpu.h> #include <asm/irq.h> @@ -64,22 +65,23 @@ void start_thread(struct pt_regs * regs, unsigned long pc, unsigned long sp) status = regs->cp0_status & ~(ST0_CU0|ST0_CU1|ST0_FR|KU_MASK); status |= KU_USER; regs->cp0_status = status; + lose_fpu(0); + clear_thread_flag(TIF_MSA_CTX_LIVE); clear_used_math(); - clear_fpu_owner(); + atomic_set(¤t->thread.bd_emu_frame, BD_EMUFRAME_NONE); init_dsp(); - clear_thread_flag(TIF_USEDMSA); - clear_thread_flag(TIF_MSA_CTX_LIVE); - disable_msa(); regs->cp0_epc = pc; regs->regs[29] = sp; } -void exit_thread(void) -{ -} - -void flush_thread(void) +void exit_thread(struct task_struct *tsk) { + /* + * User threads may have allocated a delay slot emulation frame. + * If so, clean up that allocation. + */ + if (!(current->flags & PF_KTHREAD)) + dsemul_thread_cleanup(tsk); } int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) @@ -168,6 +170,8 @@ int copy_thread(unsigned long clone_flags, unsigned long usp, clear_tsk_thread_flag(p, TIF_FPUBOUND); #endif /* CONFIG_MIPS_MT_FPAFF */ + atomic_set(&p->thread.bd_emu_frame, BD_EMUFRAME_NONE); + if (clone_flags & CLONE_SETTLS) ti->tp_value = regs->regs[7]; @@ -708,7 +712,7 @@ int mips_set_process_fp_mode(struct task_struct *task, unsigned int value) * allows us to only worry about whether an FP mode switch is in * progress when FP is first used in a tasks time slice. Pretty much all * of the mode switch overhead can thus be confined to cases where mode - * switches are actually occuring. That is, to here. However for the + * switches are actually occurring. That is, to here. However for the * thread performing the mode switch it may take a while... */ if (num_online_cpus() > 1) { diff --git a/arch/mips/kernel/ptrace.c b/arch/mips/kernel/ptrace.c index c3d2d2c05fdb..0f0030e7f6d9 100644 --- a/arch/mips/kernel/ptrace.c +++ b/arch/mips/kernel/ptrace.c @@ -79,16 +79,15 @@ void ptrace_disable(struct task_struct *child) } /* - * Poke at FCSR according to its mask. Don't set the cause bits as - * this is currently not handled correctly in FP context restoration - * and will cause an oops if a corresponding enable bit is set. + * Poke at FCSR according to its mask. Set the Cause bits even + * if a corresponding Enable bit is set. This will be noticed at + * the time the thread is switched to and SIGFPE thrown accordingly. */ static void ptrace_setfcr31(struct task_struct *child, u32 value) { u32 fcr31; u32 mask; - value &= ~FPU_CSR_ALL_X; fcr31 = child->thread.fpu.fcr31; mask = boot_cpu_data.fpu_msk31; child->thread.fpu.fcr31 = (value & ~mask) | (fcr31 & mask); diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c index 4f9f1ae49213..34fd37e5c898 100644 --- a/arch/mips/kernel/setup.c +++ b/arch/mips/kernel/setup.c @@ -597,6 +597,46 @@ static int __init early_parse_mem(char *p) } early_param("mem", early_parse_mem); +static int __init early_parse_memmap(char *p) +{ + char *oldp; + u64 start_at, mem_size; + + if (!p) + return -EINVAL; + + if (!strncmp(p, "exactmap", 8)) { + pr_err("\"memmap=exactmap\" invalid on MIPS\n"); + return 0; + } + + oldp = p; + mem_size = memparse(p, &p); + if (p == oldp) + return -EINVAL; + + if (*p == '@') { + start_at = memparse(p+1, &p); + add_memory_region(start_at, mem_size, BOOT_MEM_RAM); + } else if (*p == '#') { + pr_err("\"memmap=nn#ss\" (force ACPI data) invalid on MIPS\n"); + return -EINVAL; + } else if (*p == '$') { + start_at = memparse(p+1, &p); + add_memory_region(start_at, mem_size, BOOT_MEM_RESERVED); + } else { + pr_err("\"memmap\" invalid format!\n"); + return -EINVAL; + } + + if (*p == '\0') { + usermem = 1; + return 0; + } else + return -EINVAL; +} +early_param("memmap", early_parse_memmap); + #ifdef CONFIG_PROC_VMCORE unsigned long setup_elfcorehdr, setup_elfcorehdr_size; static int __init early_parse_elfcorehdr(char *p) @@ -857,6 +897,7 @@ static inline void prefill_possible_map(void) {} void __init setup_arch(char **cmdline_p) { cpu_probe(); + mips_cm_probe(); prom_init(); setup_early_fdc_console(); @@ -886,6 +927,10 @@ void __init setup_arch(char **cmdline_p) unsigned long kernelsp[NR_CPUS]; unsigned long fw_arg0, fw_arg1, fw_arg2, fw_arg3; +#ifdef CONFIG_USE_OF +unsigned long fw_passed_dtb; +#endif + #ifdef CONFIG_DEBUG_FS struct dentry *mips_debugfs_dir; static int __init debugfs_mips(void) diff --git a/arch/mips/kernel/signal.c b/arch/mips/kernel/signal.c index 9e35b6b26aa8..129be9703fe8 100644 --- a/arch/mips/kernel/signal.c +++ b/arch/mips/kernel/signal.c @@ -772,6 +772,14 @@ static void handle_signal(struct ksignal *ksig, struct pt_regs *regs) struct mips_abi *abi = current->thread.abi; void *vdso = current->mm->context.vdso; + /* + * If we were emulating a delay slot instruction, exit that frame such + * that addresses in the sigframe are as expected for userland and we + * don't have a problem if we reuse the thread's frame for an + * instruction within the signal handler. + */ + dsemul_thread_rollback(regs); + if (regs->regs[0]) { switch(regs->regs[2]) { case ERESTART_RESTARTBLOCK: diff --git a/arch/mips/kernel/smp-cps.c b/arch/mips/kernel/smp-cps.c index e04c8057b882..1b78309fb493 100644 --- a/arch/mips/kernel/smp-cps.c +++ b/arch/mips/kernel/smp-cps.c @@ -27,15 +27,27 @@ #include <asm/time.h> #include <asm/uasm.h> +static bool threads_disabled; static DECLARE_BITMAP(core_power, NR_CPUS); struct core_boot_config *mips_cps_core_bootcfg; +static int __init setup_nothreads(char *s) +{ + threads_disabled = true; + return 0; +} +early_param("nothreads", setup_nothreads); + static unsigned core_vpe_count(unsigned core) { unsigned cfg; - if (!config_enabled(CONFIG_MIPS_MT_SMP) || !cpu_has_mipsmt) + if (threads_disabled) + return 1; + + if ((!config_enabled(CONFIG_MIPS_MT_SMP) || !cpu_has_mipsmt) + && (!config_enabled(CONFIG_CPU_MIPSR6) || !cpu_has_vp)) return 1; mips_cm_lock_other(core, 0); @@ -47,11 +59,12 @@ static unsigned core_vpe_count(unsigned core) static void __init cps_smp_setup(void) { unsigned int ncores, nvpes, core_vpes; + unsigned long core_entry; int c, v; /* Detect & record VPE topology */ ncores = mips_cm_numcores(); - pr_info("VPE topology "); + pr_info("%s topology ", cpu_has_mips_r6 ? "VP" : "VPE"); for (c = nvpes = 0; c < ncores; c++) { core_vpes = core_vpe_count(c); pr_cont("%c%u", c ? ',' : '{', core_vpes); @@ -62,7 +75,7 @@ static void __init cps_smp_setup(void) for (v = 0; v < min_t(int, core_vpes, NR_CPUS - nvpes); v++) { cpu_data[nvpes + v].core = c; -#ifdef CONFIG_MIPS_MT_SMP +#if defined(CONFIG_MIPS_MT_SMP) || defined(CONFIG_CPU_MIPSR6) cpu_data[nvpes + v].vpe_id = v; #endif } @@ -91,6 +104,11 @@ static void __init cps_smp_setup(void) /* Make core 0 coherent with everything */ write_gcr_cl_coherence(0xff); + if (mips_cm_revision() >= CM_REV_CM3) { + core_entry = CKSEG1ADDR((unsigned long)mips_cps_core_entry); + write_gcr_bev_base(core_entry); + } + #ifdef CONFIG_MIPS_MT_FPAFF /* If we have an FPU, enroll ourselves in the FPU-full mask */ if (cpu_has_fpu) @@ -122,9 +140,11 @@ static void __init cps_prepare_cpus(unsigned int max_cpus) /* Warn the user if the CCA prevents multi-core */ ncores = mips_cm_numcores(); - if (cca_unsuitable && ncores > 1) { - pr_warn("Using only one core due to unsuitable CCA 0x%x\n", - cca); + if ((cca_unsuitable || cpu_has_dc_aliases) && ncores > 1) { + pr_warn("Using only one core due to %s%s%s\n", + cca_unsuitable ? "unsuitable CCA" : "", + (cca_unsuitable && cpu_has_dc_aliases) ? " & " : "", + cpu_has_dc_aliases ? "dcache aliasing" : ""); for_each_present_cpu(c) { if (cpu_data[c].core) @@ -210,6 +230,18 @@ static void boot_core(unsigned core) if (mips_cpc_present()) { /* Reset the core */ mips_cpc_lock_other(core); + + if (mips_cm_revision() >= CM_REV_CM3) { + /* Run VP0 following the reset */ + write_cpc_co_vp_run(0x1); + + /* + * Ensure that the VP_RUN register is written before the + * core leaves reset. + */ + wmb(); + } + write_cpc_co_cmd(CPC_Cx_CMD_RESET); timeout = 100; @@ -247,7 +279,10 @@ static void boot_core(unsigned core) static void remote_vpe_boot(void *dummy) { - mips_cps_boot_vpes(); + unsigned core = current_cpu_data.core; + struct core_boot_config *core_cfg = &mips_cps_core_bootcfg[core]; + + mips_cps_boot_vpes(core_cfg, cpu_vpe_id(¤t_cpu_data)); } static void cps_boot_secondary(int cpu, struct task_struct *idle) @@ -256,6 +291,7 @@ static void cps_boot_secondary(int cpu, struct task_struct *idle) unsigned vpe_id = cpu_vpe_id(&cpu_data[cpu]); struct core_boot_config *core_cfg = &mips_cps_core_bootcfg[core]; struct vpe_boot_config *vpe_cfg = &core_cfg->vpe_config[vpe_id]; + unsigned long core_entry; unsigned int remote; int err; @@ -273,6 +309,13 @@ static void cps_boot_secondary(int cpu, struct task_struct *idle) goto out; } + if (cpu_has_vp) { + mips_cm_lock_other(core, vpe_id); + core_entry = CKSEG1ADDR((unsigned long)mips_cps_core_entry); + write_gcr_co_reset_base(core_entry); + mips_cm_unlock_other(); + } + if (core != current_cpu_data.core) { /* Boot a VPE on another powered up core */ for (remote = 0; remote < NR_CPUS; remote++) { @@ -290,10 +333,10 @@ static void cps_boot_secondary(int cpu, struct task_struct *idle) goto out; } - BUG_ON(!cpu_has_mipsmt); + BUG_ON(!cpu_has_mipsmt && !cpu_has_vp); /* Boot a VPE on this core */ - mips_cps_boot_vpes(); + mips_cps_boot_vpes(core_cfg, vpe_id); out: preempt_enable(); } @@ -304,6 +347,17 @@ static void cps_init_secondary(void) if (cpu_has_mipsmt) dmt(); + if (mips_cm_revision() >= CM_REV_CM3) { + unsigned ident = gic_read_local_vp_id(); + + /* + * Ensure that our calculation of the VP ID matches up with + * what the GIC reports, otherwise we'll have configured + * interrupts incorrectly. + */ + BUG_ON(ident != mips_cm_vp_id(smp_processor_id())); + } + change_c0_status(ST0_IM, STATUSF_IP2 | STATUSF_IP3 | STATUSF_IP4 | STATUSF_IP5 | STATUSF_IP6 | STATUSF_IP7); } @@ -352,14 +406,16 @@ static enum { void play_dead(void) { - unsigned cpu, core; + unsigned int cpu, core, vpe_id; local_irq_disable(); idle_task_exit(); cpu = smp_processor_id(); cpu_death = CPU_DEATH_POWER; - if (cpu_has_mipsmt) { + pr_debug("CPU%d going offline\n", cpu); + + if (cpu_has_mipsmt || cpu_has_vp) { core = cpu_data[cpu].core; /* Look for another online VPE within the core */ @@ -380,10 +436,21 @@ void play_dead(void) complete(&cpu_death_chosen); if (cpu_death == CPU_DEATH_HALT) { - /* Halt this TC */ - write_c0_tchalt(TCHALT_H); - instruction_hazard(); + vpe_id = cpu_vpe_id(&cpu_data[cpu]); + + pr_debug("Halting core %d VP%d\n", core, vpe_id); + if (cpu_has_mipsmt) { + /* Halt this TC */ + write_c0_tchalt(TCHALT_H); + instruction_hazard(); + } else if (cpu_has_vp) { + write_cpc_cl_vp_stop(1 << vpe_id); + + /* Ensure that the VP_STOP register is written */ + wmb(); + } } else { + pr_debug("Gating power to core %d\n", core); /* Power down the core */ cps_pm_enter_state(CPS_PM_POWER_GATED); } @@ -410,6 +477,8 @@ static void wait_for_sibling_halt(void *ptr_cpu) static void cps_cpu_die(unsigned int cpu) { unsigned core = cpu_data[cpu].core; + unsigned int vpe_id = cpu_vpe_id(&cpu_data[cpu]); + ktime_t fail_time; unsigned stat; int err; @@ -437,14 +506,36 @@ static void cps_cpu_die(unsigned int cpu) * state, the latter happening when a JTAG probe is connected * in which case the CPC will refuse to power down the core. */ + fail_time = ktime_add_ms(ktime_get(), 2000); do { + mips_cm_lock_other(core, 0); mips_cpc_lock_other(core); stat = read_cpc_co_stat_conf(); stat &= CPC_Cx_STAT_CONF_SEQSTATE_MSK; mips_cpc_unlock_other(); - } while (stat != CPC_Cx_STAT_CONF_SEQSTATE_D0 && - stat != CPC_Cx_STAT_CONF_SEQSTATE_D2 && - stat != CPC_Cx_STAT_CONF_SEQSTATE_U2); + mips_cm_unlock_other(); + + if (stat == CPC_Cx_STAT_CONF_SEQSTATE_D0 || + stat == CPC_Cx_STAT_CONF_SEQSTATE_D2 || + stat == CPC_Cx_STAT_CONF_SEQSTATE_U2) + break; + + /* + * The core ought to have powered down, but didn't & + * now we don't really know what state it's in. It's + * likely that its _pwr_up pin has been wired to logic + * 1 & it powered back up as soon as we powered it + * down... + * + * The best we can do is warn the user & continue in + * the hope that the core is doing nothing harmful & + * might behave properly if we online it later. + */ + if (WARN(ktime_after(ktime_get(), fail_time), + "CPU%u hasn't powered down, seq. state %u\n", + cpu, stat >> CPC_Cx_STAT_CONF_SEQSTATE_SHF)) + break; + } while (1); /* Indicate the core is powered off */ bitmap_clear(core_power, core, 1); @@ -458,6 +549,12 @@ static void cps_cpu_die(unsigned int cpu) (void *)(unsigned long)cpu, 1); if (err) panic("Failed to call remote sibling CPU\n"); + } else if (cpu_has_vp) { + do { + mips_cm_lock_other(core, vpe_id); + stat = read_cpc_co_vp_running(); + mips_cm_unlock_other(); + } while (stat & (1 << vpe_id)); } } diff --git a/arch/mips/kernel/smp.c b/arch/mips/kernel/smp.c index 4af08c197177..1ef11f46db5a 100644 --- a/arch/mips/kernel/smp.c +++ b/arch/mips/kernel/smp.c @@ -25,7 +25,7 @@ #include <linux/smp.h> #include <linux/spinlock.h> #include <linux/threads.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/time.h> #include <linux/timex.h> #include <linux/sched.h> diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c index 31ca2edd7218..e23f4775b10b 100644 --- a/arch/mips/kernel/traps.c +++ b/arch/mips/kernel/traps.c @@ -56,6 +56,7 @@ #include <asm/pgtable.h> #include <asm/ptrace.h> #include <asm/sections.h> +#include <asm/siginfo.h> #include <asm/tlbdebug.h> #include <asm/traps.h> #include <asm/uaccess.h> @@ -705,6 +706,32 @@ asmlinkage void do_ov(struct pt_regs *regs) exception_exit(prev_state); } +/* + * Send SIGFPE according to FCSR Cause bits, which must have already + * been masked against Enable bits. This is impotant as Inexact can + * happen together with Overflow or Underflow, and `ptrace' can set + * any bits. + */ +void force_fcr31_sig(unsigned long fcr31, void __user *fault_addr, + struct task_struct *tsk) +{ + struct siginfo si = { .si_addr = fault_addr, .si_signo = SIGFPE }; + + if (fcr31 & FPU_CSR_INV_X) + si.si_code = FPE_FLTINV; + else if (fcr31 & FPU_CSR_DIV_X) + si.si_code = FPE_FLTDIV; + else if (fcr31 & FPU_CSR_OVF_X) + si.si_code = FPE_FLTOVF; + else if (fcr31 & FPU_CSR_UDF_X) + si.si_code = FPE_FLTUND; + else if (fcr31 & FPU_CSR_INE_X) + si.si_code = FPE_FLTRES; + else + si.si_code = __SI_FAULT; + force_sig_info(SIGFPE, &si, tsk); +} + int process_fpemu_return(int sig, void __user *fault_addr, unsigned long fcr31) { struct siginfo si = { 0 }; @@ -714,27 +741,7 @@ int process_fpemu_return(int sig, void __user *fault_addr, unsigned long fcr31) return 0; case SIGFPE: - si.si_addr = fault_addr; - si.si_signo = sig; - /* - * Inexact can happen together with Overflow or Underflow. - * Respect the mask to deliver the correct exception. - */ - fcr31 &= (fcr31 & FPU_CSR_ALL_E) << - (ffs(FPU_CSR_ALL_X) - ffs(FPU_CSR_ALL_E)); - if (fcr31 & FPU_CSR_INV_X) - si.si_code = FPE_FLTINV; - else if (fcr31 & FPU_CSR_DIV_X) - si.si_code = FPE_FLTDIV; - else if (fcr31 & FPU_CSR_OVF_X) - si.si_code = FPE_FLTOVF; - else if (fcr31 & FPU_CSR_UDF_X) - si.si_code = FPE_FLTUND; - else if (fcr31 & FPU_CSR_INE_X) - si.si_code = FPE_FLTRES; - else - si.si_code = __SI_FAULT; - force_sig_info(sig, &si, current); + force_fcr31_sig(fcr31, fault_addr, current); return 1; case SIGBUS: @@ -797,13 +804,13 @@ static int simulate_fp(struct pt_regs *regs, unsigned int opcode, /* Run the emulator */ sig = fpu_emulator_cop1Handler(regs, ¤t->thread.fpu, 1, &fault_addr); - fcr31 = current->thread.fpu.fcr31; /* - * We can't allow the emulated instruction to leave any of - * the cause bits set in $fcr31. + * We can't allow the emulated instruction to leave any + * enabled Cause bits set in $fcr31. */ - current->thread.fpu.fcr31 &= ~FPU_CSR_ALL_X; + fcr31 = mask_fcr31_x(current->thread.fpu.fcr31); + current->thread.fpu.fcr31 &= ~fcr31; /* Restore the hardware register state */ own_fpu(1); @@ -829,7 +836,7 @@ asmlinkage void do_fpe(struct pt_regs *regs, unsigned long fcr31) goto out; /* Clear FCSR.Cause before enabling interrupts */ - write_32bit_cp1_register(CP1_STATUS, fcr31 & ~FPU_CSR_ALL_X); + write_32bit_cp1_register(CP1_STATUS, fcr31 & ~mask_fcr31_x(fcr31)); local_irq_enable(); die_if_kernel("FP exception in kernel code", regs); @@ -851,13 +858,13 @@ asmlinkage void do_fpe(struct pt_regs *regs, unsigned long fcr31) /* Run the emulator */ sig = fpu_emulator_cop1Handler(regs, ¤t->thread.fpu, 1, &fault_addr); - fcr31 = current->thread.fpu.fcr31; /* - * We can't allow the emulated instruction to leave any of - * the cause bits set in $fcr31. + * We can't allow the emulated instruction to leave any + * enabled Cause bits set in $fcr31. */ - current->thread.fpu.fcr31 &= ~FPU_CSR_ALL_X; + fcr31 = mask_fcr31_x(current->thread.fpu.fcr31); + current->thread.fpu.fcr31 &= ~fcr31; /* Restore the hardware register state */ own_fpu(1); /* Using the FPU again. */ @@ -873,7 +880,7 @@ out: exception_exit(prev_state); } -void do_trap_or_bp(struct pt_regs *regs, unsigned int code, +void do_trap_or_bp(struct pt_regs *regs, unsigned int code, int si_code, const char *str) { siginfo_t info = { 0 }; @@ -930,7 +937,13 @@ void do_trap_or_bp(struct pt_regs *regs, unsigned int code, default: scnprintf(b, sizeof(b), "%s instruction in kernel code", str); die_if_kernel(b, regs); - force_sig(SIGTRAP, current); + if (si_code) { + info.si_signo = SIGTRAP; + info.si_code = si_code; + force_sig_info(SIGTRAP, &info, current); + } else { + force_sig(SIGTRAP, current); + } } } @@ -1014,7 +1027,7 @@ asmlinkage void do_bp(struct pt_regs *regs) break; } - do_trap_or_bp(regs, bcode, "Break"); + do_trap_or_bp(regs, bcode, TRAP_BRKPT, "Break"); out: set_fs(seg); @@ -1056,7 +1069,7 @@ asmlinkage void do_tr(struct pt_regs *regs) tcode = (opcode >> 6) & ((1 << 10) - 1); } - do_trap_or_bp(regs, tcode, "Trap"); + do_trap_or_bp(regs, tcode, 0, "Trap"); out: set_fs(seg); @@ -1430,13 +1443,13 @@ asmlinkage void do_cpu(struct pt_regs *regs) sig = fpu_emulator_cop1Handler(regs, ¤t->thread.fpu, 0, &fault_addr); - fcr31 = current->thread.fpu.fcr31; /* * We can't allow the emulated instruction to leave - * any of the cause bits set in $fcr31. + * any enabled Cause bits set in $fcr31. */ - current->thread.fpu.fcr31 &= ~FPU_CSR_ALL_X; + fcr31 = mask_fcr31_x(current->thread.fpu.fcr31); + current->thread.fpu.fcr31 &= ~fcr31; /* Send a signal if required. */ if (!process_fpemu_return(sig, fault_addr, fcr31) && !err) @@ -1507,6 +1520,7 @@ asmlinkage void do_mdmx(struct pt_regs *regs) */ asmlinkage void do_watch(struct pt_regs *regs) { + siginfo_t info = { .si_signo = SIGTRAP, .si_code = TRAP_HWBKPT }; enum ctx_state prev_state; u32 cause; @@ -1527,7 +1541,7 @@ asmlinkage void do_watch(struct pt_regs *regs) if (test_tsk_thread_flag(current, TIF_LOAD_WATCH)) { mips_read_watch_registers(); local_irq_enable(); - force_sig(SIGTRAP, current); + force_sig_info(SIGTRAP, &info, current); } else { mips_clear_watch_registers(); local_irq_enable(); @@ -2126,6 +2140,13 @@ void per_cpu_trap_init(bool is_boot_cpu) * o read IntCtl.IPFDC to determine the fast debug channel interrupt */ if (cpu_has_mips_r2_r6) { + /* + * We shouldn't trust a secondary core has a sane EBASE register + * so use the one calculated by the boot CPU. + */ + if (!is_boot_cpu) + write_c0_ebase(ebase); + cp0_compare_irq_shift = CAUSEB_TI - CAUSEB_IP; cp0_compare_irq = (read_c0_intctl() >> INTCTLB_IPTI) & 7; cp0_perfcount_irq = (read_c0_intctl() >> INTCTLB_IPPCI) & 7; @@ -2229,7 +2250,7 @@ void __init trap_init(void) /* * Copy the generic exception handlers to their final destination. - * This will be overriden later as suitable for a particular + * This will be overridden later as suitable for a particular * configuration. */ set_handler(0x180, &except_vec3_generic, 0x80); diff --git a/arch/mips/kernel/unaligned.c b/arch/mips/kernel/unaligned.c index 5c62065cbf22..0aa4bae4d4d4 100644 --- a/arch/mips/kernel/unaligned.c +++ b/arch/mips/kernel/unaligned.c @@ -939,88 +939,114 @@ static void emulate_load_store_insn(struct pt_regs *regs, * The remaining opcodes are the ones that are really of * interest. */ -#ifdef CONFIG_EVA case spec3_op: - /* - * we can land here only from kernel accessing user memory, - * so we need to "switch" the address limit to user space, so - * address check can work properly. - */ - seg = get_fs(); - set_fs(USER_DS); - switch (insn.spec3_format.func) { - case lhe_op: - if (!access_ok(VERIFY_READ, addr, 2)) { - set_fs(seg); - goto sigbus; - } - LoadHWE(addr, value, res); - if (res) { - set_fs(seg); - goto fault; - } - compute_return_epc(regs); - regs->regs[insn.spec3_format.rt] = value; - break; - case lwe_op: - if (!access_ok(VERIFY_READ, addr, 4)) { - set_fs(seg); - goto sigbus; + if (insn.dsp_format.func == lx_op) { + switch (insn.dsp_format.op) { + case lwx_op: + if (!access_ok(VERIFY_READ, addr, 4)) + goto sigbus; + LoadW(addr, value, res); + if (res) + goto fault; + compute_return_epc(regs); + regs->regs[insn.dsp_format.rd] = value; + break; + case lhx_op: + if (!access_ok(VERIFY_READ, addr, 2)) + goto sigbus; + LoadHW(addr, value, res); + if (res) + goto fault; + compute_return_epc(regs); + regs->regs[insn.dsp_format.rd] = value; + break; + default: + goto sigill; } + } +#ifdef CONFIG_EVA + else { + /* + * we can land here only from kernel accessing user + * memory, so we need to "switch" the address limit to + * user space, so that address check can work properly. + */ + seg = get_fs(); + set_fs(USER_DS); + switch (insn.spec3_format.func) { + case lhe_op: + if (!access_ok(VERIFY_READ, addr, 2)) { + set_fs(seg); + goto sigbus; + } + LoadHWE(addr, value, res); + if (res) { + set_fs(seg); + goto fault; + } + compute_return_epc(regs); + regs->regs[insn.spec3_format.rt] = value; + break; + case lwe_op: + if (!access_ok(VERIFY_READ, addr, 4)) { + set_fs(seg); + goto sigbus; + } LoadWE(addr, value, res); - if (res) { - set_fs(seg); - goto fault; - } - compute_return_epc(regs); - regs->regs[insn.spec3_format.rt] = value; - break; - case lhue_op: - if (!access_ok(VERIFY_READ, addr, 2)) { - set_fs(seg); - goto sigbus; - } - LoadHWUE(addr, value, res); - if (res) { - set_fs(seg); - goto fault; - } - compute_return_epc(regs); - regs->regs[insn.spec3_format.rt] = value; - break; - case she_op: - if (!access_ok(VERIFY_WRITE, addr, 2)) { - set_fs(seg); - goto sigbus; - } - compute_return_epc(regs); - value = regs->regs[insn.spec3_format.rt]; - StoreHWE(addr, value, res); - if (res) { - set_fs(seg); - goto fault; - } - break; - case swe_op: - if (!access_ok(VERIFY_WRITE, addr, 4)) { - set_fs(seg); - goto sigbus; - } - compute_return_epc(regs); - value = regs->regs[insn.spec3_format.rt]; - StoreWE(addr, value, res); - if (res) { + if (res) { + set_fs(seg); + goto fault; + } + compute_return_epc(regs); + regs->regs[insn.spec3_format.rt] = value; + break; + case lhue_op: + if (!access_ok(VERIFY_READ, addr, 2)) { + set_fs(seg); + goto sigbus; + } + LoadHWUE(addr, value, res); + if (res) { + set_fs(seg); + goto fault; + } + compute_return_epc(regs); + regs->regs[insn.spec3_format.rt] = value; + break; + case she_op: + if (!access_ok(VERIFY_WRITE, addr, 2)) { + set_fs(seg); + goto sigbus; + } + compute_return_epc(regs); + value = regs->regs[insn.spec3_format.rt]; + StoreHWE(addr, value, res); + if (res) { + set_fs(seg); + goto fault; + } + break; + case swe_op: + if (!access_ok(VERIFY_WRITE, addr, 4)) { + set_fs(seg); + goto sigbus; + } + compute_return_epc(regs); + value = regs->regs[insn.spec3_format.rt]; + StoreWE(addr, value, res); + if (res) { + set_fs(seg); + goto fault; + } + break; + default: set_fs(seg); - goto fault; + goto sigill; } - break; - default: set_fs(seg); - goto sigill; } - set_fs(seg); - break; #endif + break; case lh_op: if (!access_ok(VERIFY_READ, addr, 2)) goto sigbus; @@ -1191,6 +1217,7 @@ static void emulate_load_store_insn(struct pt_regs *regs, case ldc1_op: case swc1_op: case sdc1_op: + case cop1x_op: die_if_kernel("Unaligned FP access in kernel code", regs); BUG_ON(!used_math()); diff --git a/arch/mips/kernel/vdso.c b/arch/mips/kernel/vdso.c index 5649a9e429e0..3fcc833b316d 100644 --- a/arch/mips/kernel/vdso.c +++ b/arch/mips/kernel/vdso.c @@ -106,6 +106,16 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) down_write(&mm->mmap_sem); + /* Map delay slot emulation page */ + base = mmap_region(NULL, STACK_TOP, PAGE_SIZE, + VM_READ|VM_WRITE|VM_EXEC| + VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC, + 0); + if (IS_ERR_VALUE(base)) { + ret = base; + goto out; + } + /* * Determine total area size. This includes the VDSO data itself, the * data page, and the GIC user page if present. Always create a mapping diff --git a/arch/mips/kvm/tlb.c b/arch/mips/kvm/tlb.c index eff71c75dc27..75d056022c64 100644 --- a/arch/mips/kvm/tlb.c +++ b/arch/mips/kvm/tlb.c @@ -683,7 +683,7 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) kvm_debug("%s: vcpu %p, cpu: %d\n", __func__, vcpu, cpu); - /* Alocate new kernel and user ASIDs if needed */ + /* Allocate new kernel and user ASIDs if needed */ local_irq_save(flags); diff --git a/arch/mips/kvm/trap_emul.c b/arch/mips/kvm/trap_emul.c index 307cc4c98bdd..473aa4dff867 100644 --- a/arch/mips/kvm/trap_emul.c +++ b/arch/mips/kvm/trap_emul.c @@ -501,7 +501,7 @@ static int kvm_trap_emul_vcpu_setup(struct kvm_vcpu *vcpu) kvm_write_c0_guest_config7(cop0, (MIPS_CONF7_WII) | (1 << 10)); /* - * Setup IntCtl defaults, compatibilty mode for timer interrupts (HW5) + * Setup IntCtl defaults, compatibility mode for timer interrupts (HW5) */ kvm_write_c0_guest_intctl(cop0, 0xFC000000); diff --git a/arch/mips/math-emu/Makefile b/arch/mips/math-emu/Makefile index a19641d3ac23..e9f10b88b695 100644 --- a/arch/mips/math-emu/Makefile +++ b/arch/mips/math-emu/Makefile @@ -4,9 +4,11 @@ obj-y += cp1emu.o ieee754dp.o ieee754sp.o ieee754.o \ dp_div.o dp_mul.o dp_sub.o dp_add.o dp_fsp.o dp_cmp.o dp_simple.o \ - dp_tint.o dp_fint.o dp_maddf.o dp_msubf.o dp_2008class.o dp_fmin.o dp_fmax.o \ + dp_tint.o dp_fint.o dp_rint.o dp_maddf.o dp_2008class.o dp_fmin.o \ + dp_fmax.o \ sp_div.o sp_mul.o sp_sub.o sp_add.o sp_fdp.o sp_cmp.o sp_simple.o \ - sp_tint.o sp_fint.o sp_maddf.o sp_msubf.o sp_2008class.o sp_fmin.o sp_fmax.o \ + sp_tint.o sp_fint.o sp_rint.o sp_maddf.o sp_2008class.o sp_fmin.o \ + sp_fmax.o \ dsemul.o lib-y += ieee754d.o \ diff --git a/arch/mips/math-emu/cp1emu.c b/arch/mips/math-emu/cp1emu.c index 89d05de8040a..ebb5e3bfe12a 100644 --- a/arch/mips/math-emu/cp1emu.c +++ b/arch/mips/math-emu/cp1emu.c @@ -434,12 +434,14 @@ static int microMIPS32_to_MIPS32(union mips_instruction *insn_ptr) * a single subroutine should be used across both * modules. */ -static int isBranchInstr(struct pt_regs *regs, struct mm_decoded_insn dec_insn, - unsigned long *contpc) +int isBranchInstr(struct pt_regs *regs, struct mm_decoded_insn dec_insn, + unsigned long *contpc) { union mips_instruction insn = (union mips_instruction)dec_insn.insn; unsigned int fcr31; unsigned int bit = 0; + unsigned int bit0; + union fpureg *fpr; switch (insn.i_format.opcode) { case spec_op: @@ -450,7 +452,7 @@ static int isBranchInstr(struct pt_regs *regs, struct mm_decoded_insn dec_insn, regs->cp0_epc + dec_insn.pc_inc + dec_insn.next_pc_inc; } - /* Fall through */ + /* fall through */ case jr_op: /* For R6, JR already emulated in jalr_op */ if (NO_R6EMU && insn.r_format.func == jr_op) @@ -470,10 +472,11 @@ static int isBranchInstr(struct pt_regs *regs, struct mm_decoded_insn dec_insn, regs->regs[31] = regs->cp0_epc + dec_insn.pc_inc + dec_insn.next_pc_inc; - /* Fall through */ + /* fall through */ case bltzl_op: if (NO_R6EMU) break; + /* fall through */ case bltz_op: if ((long)regs->regs[insn.i_format.rs] < 0) *contpc = regs->cp0_epc + @@ -493,10 +496,11 @@ static int isBranchInstr(struct pt_regs *regs, struct mm_decoded_insn dec_insn, regs->regs[31] = regs->cp0_epc + dec_insn.pc_inc + dec_insn.next_pc_inc; - /* Fall through */ + /* fall through */ case bgezl_op: if (NO_R6EMU) break; + /* fall through */ case bgez_op: if ((long)regs->regs[insn.i_format.rs] >= 0) *contpc = regs->cp0_epc + @@ -511,11 +515,12 @@ static int isBranchInstr(struct pt_regs *regs, struct mm_decoded_insn dec_insn, break; case jalx_op: set_isa16_mode(bit); + /* fall through */ case jal_op: regs->regs[31] = regs->cp0_epc + dec_insn.pc_inc + dec_insn.next_pc_inc; - /* Fall through */ + /* fall through */ case j_op: *contpc = regs->cp0_epc + dec_insn.pc_inc; *contpc >>= 28; @@ -527,6 +532,7 @@ static int isBranchInstr(struct pt_regs *regs, struct mm_decoded_insn dec_insn, case beql_op: if (NO_R6EMU) break; + /* fall through */ case beq_op: if (regs->regs[insn.i_format.rs] == regs->regs[insn.i_format.rt]) @@ -541,6 +547,7 @@ static int isBranchInstr(struct pt_regs *regs, struct mm_decoded_insn dec_insn, case bnel_op: if (NO_R6EMU) break; + /* fall through */ case bne_op: if (regs->regs[insn.i_format.rs] != regs->regs[insn.i_format.rt]) @@ -555,6 +562,7 @@ static int isBranchInstr(struct pt_regs *regs, struct mm_decoded_insn dec_insn, case blezl_op: if (!insn.i_format.rt && NO_R6EMU) break; + /* fall through */ case blez_op: /* @@ -592,6 +600,7 @@ static int isBranchInstr(struct pt_regs *regs, struct mm_decoded_insn dec_insn, case bgtzl_op: if (!insn.i_format.rt && NO_R6EMU) break; + /* fall through */ case bgtz_op: /* * Compact branches for R6 for the @@ -627,8 +636,8 @@ static int isBranchInstr(struct pt_regs *regs, struct mm_decoded_insn dec_insn, dec_insn.pc_inc + dec_insn.next_pc_inc; return 1; - case cbcond0_op: - case cbcond1_op: + case pop10_op: + case pop30_op: if (!cpu_has_mips_r6) break; if (insn.i_format.rt && !insn.i_format.rs) @@ -683,14 +692,14 @@ static int isBranchInstr(struct pt_regs *regs, struct mm_decoded_insn dec_insn, dec_insn.next_pc_inc; return 1; - case beqzcjic_op: + case pop66_op: if (!cpu_has_mips_r6) break; *contpc = regs->cp0_epc + dec_insn.pc_inc + dec_insn.next_pc_inc; return 1; - case bnezcjialc_op: + case pop76_op: if (!cpu_has_mips_r6) break; if (!insn.i_format.rs) @@ -707,14 +716,14 @@ static int isBranchInstr(struct pt_regs *regs, struct mm_decoded_insn dec_insn, ((insn.i_format.rs == bc1eqz_op) || (insn.i_format.rs == bc1nez_op))) { bit = 0; + fpr = ¤t->thread.fpu.fpr[insn.i_format.rt]; + bit0 = get_fpr32(fpr, 0) & 0x1; switch (insn.i_format.rs) { case bc1eqz_op: - if (get_fpr32(¤t->thread.fpu.fpr[insn.i_format.rt], 0) & 0x1) - bit = 1; + bit = bit0 == 0; break; case bc1nez_op: - if (!(get_fpr32(¤t->thread.fpu.fpr[insn.i_format.rt], 0) & 0x1)) - bit = 1; + bit = bit0 != 0; break; } if (bit) @@ -728,7 +737,8 @@ static int isBranchInstr(struct pt_regs *regs, struct mm_decoded_insn dec_insn, return 1; } - /* R2/R6 compatible cop1 instruction. Fall through */ + /* R2/R6 compatible cop1 instruction */ + /* fall through */ case cop2_op: case cop1x_op: if (insn.i_format.rs == bc_op) { @@ -809,7 +819,7 @@ do { \ #define SITOREG(si, x) \ do { \ if (cop1_64bit(xcp) && !hybrid_fprs()) { \ - unsigned i; \ + unsigned int i; \ set_fpr32(&ctx->fpr[x], 0, si); \ for (i = 1; i < ARRAY_SIZE(ctx->fpr[x].val32); i++) \ set_fpr32(&ctx->fpr[x], i, 0); \ @@ -822,19 +832,19 @@ do { \ #define SITOHREG(si, x) \ do { \ - unsigned i; \ + unsigned int i; \ set_fpr32(&ctx->fpr[x], 1, si); \ for (i = 2; i < ARRAY_SIZE(ctx->fpr[x].val32); i++) \ set_fpr32(&ctx->fpr[x], i, 0); \ } while (0) #define DIFROMREG(di, x) \ - ((di) = get_fpr64(&ctx->fpr[(x) & ~(cop1_64bit(xcp) == 0)], 0)) + ((di) = get_fpr64(&ctx->fpr[(x) & ~(cop1_64bit(xcp) ^ 1)], 0)) #define DITOREG(di, x) \ do { \ - unsigned fpr, i; \ - fpr = (x) & ~(cop1_64bit(xcp) == 0); \ + unsigned int fpr, i; \ + fpr = (x) & ~(cop1_64bit(xcp) ^ 1); \ set_fpr64(&ctx->fpr[fpr], 0, di); \ for (i = 1; i < ARRAY_SIZE(ctx->fpr[x].val64); i++) \ set_fpr64(&ctx->fpr[fpr], i, 0); \ @@ -975,9 +985,10 @@ static int cop1Emulate(struct pt_regs *xcp, struct mips_fpu_struct *ctx, struct mm_decoded_insn dec_insn, void *__user *fault_addr) { unsigned long contpc = xcp->cp0_epc + dec_insn.pc_inc; - unsigned int cond, cbit; + unsigned int cond, cbit, bit0; mips_instruction ir; int likely, pc_inc; + union fpureg *fpr; u32 __user *wva; u64 __user *dva; u32 wval; @@ -1188,15 +1199,18 @@ emul: if (!cpu_has_mips_r6 || delay_slot(xcp)) return SIGILL; - cond = likely = 0; + likely = 0; + cond = 0; + fpr = ¤t->thread.fpu.fpr[MIPSInst_RT(ir)]; + bit0 = get_fpr32(fpr, 0) & 0x1; switch (MIPSInst_RS(ir)) { case bc1eqz_op: - if (get_fpr32(¤t->thread.fpu.fpr[MIPSInst_RT(ir)], 0) & 0x1) - cond = 1; + MIPS_FPU_EMU_INC_STATS(bc1eqz); + cond = bit0 == 0; break; case bc1nez_op: - if (!(get_fpr32(¤t->thread.fpu.fpr[MIPSInst_RT(ir)], 0) & 0x1)) - cond = 1; + MIPS_FPU_EMU_INC_STATS(bc1nez); + cond = bit0 != 0; break; } goto branch_common; @@ -1216,18 +1230,19 @@ emul: case bcfl_op: if (cpu_has_mips_2_3_4_5_r) likely = 1; - /* Fall through */ + /* fall through */ case bcf_op: cond = !cond; break; case bctl_op: if (cpu_has_mips_2_3_4_5_r) likely = 1; - /* Fall through */ + /* fall through */ case bct_op: break; } branch_common: + MIPS_FPU_EMU_INC_STATS(branches); set_delay_slot(xcp); if (cond) { /* @@ -1267,7 +1282,9 @@ branch_common: * instruction in the dslot. */ sig = mips_dsemul(xcp, ir, - contpc); + bcpc, contpc); + if (sig < 0) + break; if (sig) xcp->cp0_epc = bcpc; /* @@ -1320,7 +1337,9 @@ branch_common: * Single step the non-cp1 * instruction in the dslot */ - sig = mips_dsemul(xcp, ir, contpc); + sig = mips_dsemul(xcp, ir, bcpc, contpc); + if (sig < 0) + break; if (sig) xcp->cp0_epc = bcpc; /* SIGILL forces out of the emulation loop. */ @@ -1344,7 +1363,8 @@ branch_common: return SIGILL; /* a real fpu computation instruction */ - if ((sig = fpu_emu(xcp, ctx, ir))) + sig = fpu_emu(xcp, ctx, ir); + if (sig) return sig; } break; @@ -1457,7 +1477,7 @@ DEF3OP(nmsub, dp, ieee754dp_mul, ieee754dp_sub, ieee754dp_neg); static int fpux_emu(struct pt_regs *xcp, struct mips_fpu_struct *ctx, mips_instruction ir, void *__user *fault_addr) { - unsigned rcsr = 0; /* resulting csr */ + unsigned int rcsr = 0; /* resulting csr */ MIPS_FPU_EMU_INC_STATS(cp1xops); @@ -1653,10 +1673,10 @@ static int fpu_emu(struct pt_regs *xcp, struct mips_fpu_struct *ctx, mips_instruction ir) { int rfmt; /* resulting format */ - unsigned rcsr = 0; /* resulting csr */ + unsigned int rcsr = 0; /* resulting csr */ unsigned int oldrm; unsigned int cbit; - unsigned cond; + unsigned int cond; union { union ieee754dp d; union ieee754sp s; @@ -1672,20 +1692,24 @@ static int fpu_emu(struct pt_regs *xcp, struct mips_fpu_struct *ctx, union ieee754sp(*b) (union ieee754sp, union ieee754sp); union ieee754sp(*u) (union ieee754sp); } handler; - union ieee754sp fs, ft; + union ieee754sp fd, fs, ft; switch (MIPSInst_FUNC(ir)) { /* binary ops */ case fadd_op: + MIPS_FPU_EMU_INC_STATS(add_s); handler.b = ieee754sp_add; goto scopbop; case fsub_op: + MIPS_FPU_EMU_INC_STATS(sub_s); handler.b = ieee754sp_sub; goto scopbop; case fmul_op: + MIPS_FPU_EMU_INC_STATS(mul_s); handler.b = ieee754sp_mul; goto scopbop; case fdiv_op: + MIPS_FPU_EMU_INC_STATS(div_s); handler.b = ieee754sp_div; goto scopbop; @@ -1694,6 +1718,7 @@ static int fpu_emu(struct pt_regs *xcp, struct mips_fpu_struct *ctx, if (!cpu_has_mips_2_3_4_5_r) return SIGILL; + MIPS_FPU_EMU_INC_STATS(sqrt_s); handler.u = ieee754sp_sqrt; goto scopuop; @@ -1706,6 +1731,7 @@ static int fpu_emu(struct pt_regs *xcp, struct mips_fpu_struct *ctx, if (!cpu_has_mips_4_5_64_r2_r6) return SIGILL; + MIPS_FPU_EMU_INC_STATS(rsqrt_s); handler.u = fpemu_sp_rsqrt; goto scopuop; @@ -1713,6 +1739,7 @@ static int fpu_emu(struct pt_regs *xcp, struct mips_fpu_struct *ctx, if (!cpu_has_mips_4_5_64_r2_r6) return SIGILL; + MIPS_FPU_EMU_INC_STATS(recip_s); handler.u = fpemu_sp_recip; goto scopuop; @@ -1749,6 +1776,7 @@ static int fpu_emu(struct pt_regs *xcp, struct mips_fpu_struct *ctx, if (!cpu_has_mips_r6) return SIGILL; + MIPS_FPU_EMU_INC_STATS(seleqz_s); SPFROMREG(rv.s, MIPSInst_FT(ir)); if (rv.w & 0x1) rv.w = 0; @@ -1760,6 +1788,7 @@ static int fpu_emu(struct pt_regs *xcp, struct mips_fpu_struct *ctx, if (!cpu_has_mips_r6) return SIGILL; + MIPS_FPU_EMU_INC_STATS(selnez_s); SPFROMREG(rv.s, MIPSInst_FT(ir)); if (rv.w & 0x1) SPFROMREG(rv.s, MIPSInst_FS(ir)); @@ -1773,6 +1802,7 @@ static int fpu_emu(struct pt_regs *xcp, struct mips_fpu_struct *ctx, if (!cpu_has_mips_r6) return SIGILL; + MIPS_FPU_EMU_INC_STATS(maddf_s); SPFROMREG(ft, MIPSInst_FT(ir)); SPFROMREG(fs, MIPSInst_FS(ir)); SPFROMREG(fd, MIPSInst_FD(ir)); @@ -1786,6 +1816,7 @@ static int fpu_emu(struct pt_regs *xcp, struct mips_fpu_struct *ctx, if (!cpu_has_mips_r6) return SIGILL; + MIPS_FPU_EMU_INC_STATS(msubf_s); SPFROMREG(ft, MIPSInst_FT(ir)); SPFROMREG(fs, MIPSInst_FS(ir)); SPFROMREG(fd, MIPSInst_FD(ir)); @@ -1799,9 +1830,9 @@ static int fpu_emu(struct pt_regs *xcp, struct mips_fpu_struct *ctx, if (!cpu_has_mips_r6) return SIGILL; + MIPS_FPU_EMU_INC_STATS(rint_s); SPFROMREG(fs, MIPSInst_FS(ir)); - rv.l = ieee754sp_tlong(fs); - rv.s = ieee754sp_flong(rv.l); + rv.s = ieee754sp_rint(fs); goto copcsr; } @@ -1811,6 +1842,7 @@ static int fpu_emu(struct pt_regs *xcp, struct mips_fpu_struct *ctx, if (!cpu_has_mips_r6) return SIGILL; + MIPS_FPU_EMU_INC_STATS(class_s); SPFROMREG(fs, MIPSInst_FS(ir)); rv.w = ieee754sp_2008class(fs); rfmt = w_fmt; @@ -1823,6 +1855,7 @@ static int fpu_emu(struct pt_regs *xcp, struct mips_fpu_struct *ctx, if (!cpu_has_mips_r6) return SIGILL; + MIPS_FPU_EMU_INC_STATS(min_s); SPFROMREG(ft, MIPSInst_FT(ir)); SPFROMREG(fs, MIPSInst_FS(ir)); rv.s = ieee754sp_fmin(fs, ft); @@ -1835,6 +1868,7 @@ static int fpu_emu(struct pt_regs *xcp, struct mips_fpu_struct *ctx, if (!cpu_has_mips_r6) return SIGILL; + MIPS_FPU_EMU_INC_STATS(mina_s); SPFROMREG(ft, MIPSInst_FT(ir)); SPFROMREG(fs, MIPSInst_FS(ir)); rv.s = ieee754sp_fmina(fs, ft); @@ -1847,6 +1881,7 @@ static int fpu_emu(struct pt_regs *xcp, struct mips_fpu_struct *ctx, if (!cpu_has_mips_r6) return SIGILL; + MIPS_FPU_EMU_INC_STATS(max_s); SPFROMREG(ft, MIPSInst_FT(ir)); SPFROMREG(fs, MIPSInst_FS(ir)); rv.s = ieee754sp_fmax(fs, ft); @@ -1859,6 +1894,7 @@ static int fpu_emu(struct pt_regs *xcp, struct mips_fpu_struct *ctx, if (!cpu_has_mips_r6) return SIGILL; + MIPS_FPU_EMU_INC_STATS(maxa_s); SPFROMREG(ft, MIPSInst_FT(ir)); SPFROMREG(fs, MIPSInst_FS(ir)); rv.s = ieee754sp_fmaxa(fs, ft); @@ -1866,15 +1902,18 @@ static int fpu_emu(struct pt_regs *xcp, struct mips_fpu_struct *ctx, } case fabs_op: + MIPS_FPU_EMU_INC_STATS(abs_s); handler.u = ieee754sp_abs; goto scopuop; case fneg_op: + MIPS_FPU_EMU_INC_STATS(neg_s); handler.u = ieee754sp_neg; goto scopuop; case fmov_op: /* an easy one */ + MIPS_FPU_EMU_INC_STATS(mov_s); SPFROMREG(rv.s, MIPSInst_FS(ir)); goto copcsr; @@ -1917,12 +1956,14 @@ copcsr: return SIGILL; /* not defined */ case fcvtd_op: + MIPS_FPU_EMU_INC_STATS(cvt_d_s); SPFROMREG(fs, MIPSInst_FS(ir)); rv.d = ieee754dp_fsp(fs); rfmt = d_fmt; goto copcsr; case fcvtw_op: + MIPS_FPU_EMU_INC_STATS(cvt_w_s); SPFROMREG(fs, MIPSInst_FS(ir)); rv.w = ieee754sp_tint(fs); rfmt = w_fmt; @@ -1935,6 +1976,15 @@ copcsr: if (!cpu_has_mips_2_3_4_5_r) return SIGILL; + if (MIPSInst_FUNC(ir) == fceil_op) + MIPS_FPU_EMU_INC_STATS(ceil_w_s); + if (MIPSInst_FUNC(ir) == ffloor_op) + MIPS_FPU_EMU_INC_STATS(floor_w_s); + if (MIPSInst_FUNC(ir) == fround_op) + MIPS_FPU_EMU_INC_STATS(round_w_s); + if (MIPSInst_FUNC(ir) == ftrunc_op) + MIPS_FPU_EMU_INC_STATS(trunc_w_s); + oldrm = ieee754_csr.rm; SPFROMREG(fs, MIPSInst_FS(ir)); ieee754_csr.rm = MIPSInst_FUNC(ir); @@ -1943,10 +1993,23 @@ copcsr: rfmt = w_fmt; goto copcsr; + case fsel_op: + if (!cpu_has_mips_r6) + return SIGILL; + + MIPS_FPU_EMU_INC_STATS(sel_s); + SPFROMREG(fd, MIPSInst_FD(ir)); + if (fd.bits & 0x1) + SPFROMREG(rv.s, MIPSInst_FT(ir)); + else + SPFROMREG(rv.s, MIPSInst_FS(ir)); + break; + case fcvtl_op: if (!cpu_has_mips_3_4_5_64_r2_r6) return SIGILL; + MIPS_FPU_EMU_INC_STATS(cvt_l_s); SPFROMREG(fs, MIPSInst_FS(ir)); rv.l = ieee754sp_tlong(fs); rfmt = l_fmt; @@ -1959,6 +2022,15 @@ copcsr: if (!cpu_has_mips_3_4_5_64_r2_r6) return SIGILL; + if (MIPSInst_FUNC(ir) == fceill_op) + MIPS_FPU_EMU_INC_STATS(ceil_l_s); + if (MIPSInst_FUNC(ir) == ffloorl_op) + MIPS_FPU_EMU_INC_STATS(floor_l_s); + if (MIPSInst_FUNC(ir) == froundl_op) + MIPS_FPU_EMU_INC_STATS(round_l_s); + if (MIPSInst_FUNC(ir) == ftruncl_op) + MIPS_FPU_EMU_INC_STATS(trunc_l_s); + oldrm = ieee754_csr.rm; SPFROMREG(fs, MIPSInst_FS(ir)); ieee754_csr.rm = MIPSInst_FUNC(ir); @@ -1969,9 +2041,10 @@ copcsr: default: if (!NO_R6EMU && MIPSInst_FUNC(ir) >= fcmp_op) { - unsigned cmpop = MIPSInst_FUNC(ir) - fcmp_op; + unsigned int cmpop; union ieee754sp fs, ft; + cmpop = MIPSInst_FUNC(ir) - fcmp_op; SPFROMREG(fs, MIPSInst_FS(ir)); SPFROMREG(ft, MIPSInst_FT(ir)); rv.w = ieee754sp_cmp(fs, ft, @@ -1991,7 +2064,7 @@ copcsr: } case d_fmt: { - union ieee754dp fs, ft; + union ieee754dp fd, fs, ft; union { union ieee754dp(*b) (union ieee754dp, union ieee754dp); union ieee754dp(*u) (union ieee754dp); @@ -2000,15 +2073,19 @@ copcsr: switch (MIPSInst_FUNC(ir)) { /* binary ops */ case fadd_op: + MIPS_FPU_EMU_INC_STATS(add_d); handler.b = ieee754dp_add; goto dcopbop; case fsub_op: + MIPS_FPU_EMU_INC_STATS(sub_d); handler.b = ieee754dp_sub; goto dcopbop; case fmul_op: + MIPS_FPU_EMU_INC_STATS(mul_d); handler.b = ieee754dp_mul; goto dcopbop; case fdiv_op: + MIPS_FPU_EMU_INC_STATS(div_d); handler.b = ieee754dp_div; goto dcopbop; @@ -2017,6 +2094,7 @@ copcsr: if (!cpu_has_mips_2_3_4_5_r) return SIGILL; + MIPS_FPU_EMU_INC_STATS(sqrt_d); handler.u = ieee754dp_sqrt; goto dcopuop; /* @@ -2028,12 +2106,14 @@ copcsr: if (!cpu_has_mips_4_5_64_r2_r6) return SIGILL; + MIPS_FPU_EMU_INC_STATS(rsqrt_d); handler.u = fpemu_dp_rsqrt; goto dcopuop; case frecip_op: if (!cpu_has_mips_4_5_64_r2_r6) return SIGILL; + MIPS_FPU_EMU_INC_STATS(recip_d); handler.u = fpemu_dp_recip; goto dcopuop; case fmovc_op: @@ -2067,6 +2147,7 @@ copcsr: if (!cpu_has_mips_r6) return SIGILL; + MIPS_FPU_EMU_INC_STATS(seleqz_d); DPFROMREG(rv.d, MIPSInst_FT(ir)); if (rv.l & 0x1) rv.l = 0; @@ -2078,6 +2159,7 @@ copcsr: if (!cpu_has_mips_r6) return SIGILL; + MIPS_FPU_EMU_INC_STATS(selnez_d); DPFROMREG(rv.d, MIPSInst_FT(ir)); if (rv.l & 0x1) DPFROMREG(rv.d, MIPSInst_FS(ir)); @@ -2091,6 +2173,7 @@ copcsr: if (!cpu_has_mips_r6) return SIGILL; + MIPS_FPU_EMU_INC_STATS(maddf_d); DPFROMREG(ft, MIPSInst_FT(ir)); DPFROMREG(fs, MIPSInst_FS(ir)); DPFROMREG(fd, MIPSInst_FD(ir)); @@ -2104,6 +2187,7 @@ copcsr: if (!cpu_has_mips_r6) return SIGILL; + MIPS_FPU_EMU_INC_STATS(msubf_d); DPFROMREG(ft, MIPSInst_FT(ir)); DPFROMREG(fs, MIPSInst_FS(ir)); DPFROMREG(fd, MIPSInst_FD(ir)); @@ -2117,9 +2201,9 @@ copcsr: if (!cpu_has_mips_r6) return SIGILL; + MIPS_FPU_EMU_INC_STATS(rint_d); DPFROMREG(fs, MIPSInst_FS(ir)); - rv.l = ieee754dp_tlong(fs); - rv.d = ieee754dp_flong(rv.l); + rv.d = ieee754dp_rint(fs); goto copcsr; } @@ -2129,9 +2213,10 @@ copcsr: if (!cpu_has_mips_r6) return SIGILL; + MIPS_FPU_EMU_INC_STATS(class_d); DPFROMREG(fs, MIPSInst_FS(ir)); - rv.w = ieee754dp_2008class(fs); - rfmt = w_fmt; + rv.l = ieee754dp_2008class(fs); + rfmt = l_fmt; goto copcsr; } @@ -2141,6 +2226,7 @@ copcsr: if (!cpu_has_mips_r6) return SIGILL; + MIPS_FPU_EMU_INC_STATS(min_d); DPFROMREG(ft, MIPSInst_FT(ir)); DPFROMREG(fs, MIPSInst_FS(ir)); rv.d = ieee754dp_fmin(fs, ft); @@ -2153,6 +2239,7 @@ copcsr: if (!cpu_has_mips_r6) return SIGILL; + MIPS_FPU_EMU_INC_STATS(mina_d); DPFROMREG(ft, MIPSInst_FT(ir)); DPFROMREG(fs, MIPSInst_FS(ir)); rv.d = ieee754dp_fmina(fs, ft); @@ -2165,6 +2252,7 @@ copcsr: if (!cpu_has_mips_r6) return SIGILL; + MIPS_FPU_EMU_INC_STATS(max_d); DPFROMREG(ft, MIPSInst_FT(ir)); DPFROMREG(fs, MIPSInst_FS(ir)); rv.d = ieee754dp_fmax(fs, ft); @@ -2177,6 +2265,7 @@ copcsr: if (!cpu_has_mips_r6) return SIGILL; + MIPS_FPU_EMU_INC_STATS(maxa_d); DPFROMREG(ft, MIPSInst_FT(ir)); DPFROMREG(fs, MIPSInst_FS(ir)); rv.d = ieee754dp_fmaxa(fs, ft); @@ -2184,15 +2273,18 @@ copcsr: } case fabs_op: + MIPS_FPU_EMU_INC_STATS(abs_d); handler.u = ieee754dp_abs; goto dcopuop; case fneg_op: + MIPS_FPU_EMU_INC_STATS(neg_d); handler.u = ieee754dp_neg; goto dcopuop; case fmov_op: /* an easy one */ + MIPS_FPU_EMU_INC_STATS(mov_d); DPFROMREG(rv.d, MIPSInst_FS(ir)); goto copcsr; @@ -2212,6 +2304,7 @@ dcopuop: * unary conv ops */ case fcvts_op: + MIPS_FPU_EMU_INC_STATS(cvt_s_d); DPFROMREG(fs, MIPSInst_FS(ir)); rv.s = ieee754sp_fdp(fs); rfmt = s_fmt; @@ -2221,6 +2314,7 @@ dcopuop: return SIGILL; /* not defined */ case fcvtw_op: + MIPS_FPU_EMU_INC_STATS(cvt_w_d); DPFROMREG(fs, MIPSInst_FS(ir)); rv.w = ieee754dp_tint(fs); /* wrong */ rfmt = w_fmt; @@ -2233,6 +2327,15 @@ dcopuop: if (!cpu_has_mips_2_3_4_5_r) return SIGILL; + if (MIPSInst_FUNC(ir) == fceil_op) + MIPS_FPU_EMU_INC_STATS(ceil_w_d); + if (MIPSInst_FUNC(ir) == ffloor_op) + MIPS_FPU_EMU_INC_STATS(floor_w_d); + if (MIPSInst_FUNC(ir) == fround_op) + MIPS_FPU_EMU_INC_STATS(round_w_d); + if (MIPSInst_FUNC(ir) == ftrunc_op) + MIPS_FPU_EMU_INC_STATS(trunc_w_d); + oldrm = ieee754_csr.rm; DPFROMREG(fs, MIPSInst_FS(ir)); ieee754_csr.rm = MIPSInst_FUNC(ir); @@ -2241,10 +2344,23 @@ dcopuop: rfmt = w_fmt; goto copcsr; + case fsel_op: + if (!cpu_has_mips_r6) + return SIGILL; + + MIPS_FPU_EMU_INC_STATS(sel_d); + DPFROMREG(fd, MIPSInst_FD(ir)); + if (fd.bits & 0x1) + DPFROMREG(rv.d, MIPSInst_FT(ir)); + else + DPFROMREG(rv.d, MIPSInst_FS(ir)); + break; + case fcvtl_op: if (!cpu_has_mips_3_4_5_64_r2_r6) return SIGILL; + MIPS_FPU_EMU_INC_STATS(cvt_l_d); DPFROMREG(fs, MIPSInst_FS(ir)); rv.l = ieee754dp_tlong(fs); rfmt = l_fmt; @@ -2257,6 +2373,15 @@ dcopuop: if (!cpu_has_mips_3_4_5_64_r2_r6) return SIGILL; + if (MIPSInst_FUNC(ir) == fceill_op) + MIPS_FPU_EMU_INC_STATS(ceil_l_d); + if (MIPSInst_FUNC(ir) == ffloorl_op) + MIPS_FPU_EMU_INC_STATS(floor_l_d); + if (MIPSInst_FUNC(ir) == froundl_op) + MIPS_FPU_EMU_INC_STATS(round_l_d); + if (MIPSInst_FUNC(ir) == ftruncl_op) + MIPS_FPU_EMU_INC_STATS(trunc_l_d); + oldrm = ieee754_csr.rm; DPFROMREG(fs, MIPSInst_FS(ir)); ieee754_csr.rm = MIPSInst_FUNC(ir); @@ -2267,9 +2392,10 @@ dcopuop: default: if (!NO_R6EMU && MIPSInst_FUNC(ir) >= fcmp_op) { - unsigned cmpop = MIPSInst_FUNC(ir) - fcmp_op; + unsigned int cmpop; union ieee754dp fs, ft; + cmpop = MIPSInst_FUNC(ir) - fcmp_op; DPFROMREG(fs, MIPSInst_FS(ir)); DPFROMREG(ft, MIPSInst_FT(ir)); rv.w = ieee754dp_cmp(fs, ft, @@ -2298,12 +2424,14 @@ dcopuop: switch (MIPSInst_FUNC(ir)) { case fcvts_op: /* convert word to single precision real */ + MIPS_FPU_EMU_INC_STATS(cvt_s_w); SPFROMREG(fs, MIPSInst_FS(ir)); rv.s = ieee754sp_fint(fs.bits); rfmt = s_fmt; goto copcsr; case fcvtd_op: /* convert word to double precision real */ + MIPS_FPU_EMU_INC_STATS(cvt_d_w); SPFROMREG(fs, MIPSInst_FS(ir)); rv.d = ieee754dp_fint(fs.bits); rfmt = d_fmt; @@ -2323,6 +2451,90 @@ dcopuop: (MIPSInst_FUNC(ir) & 0x20)) return SIGILL; + if (!sig) { + if (!(MIPSInst_FUNC(ir) & PREDICATE_BIT)) { + switch (cmpop) { + case 0: + MIPS_FPU_EMU_INC_STATS(cmp_af_s); + break; + case 1: + MIPS_FPU_EMU_INC_STATS(cmp_un_s); + break; + case 2: + MIPS_FPU_EMU_INC_STATS(cmp_eq_s); + break; + case 3: + MIPS_FPU_EMU_INC_STATS(cmp_ueq_s); + break; + case 4: + MIPS_FPU_EMU_INC_STATS(cmp_lt_s); + break; + case 5: + MIPS_FPU_EMU_INC_STATS(cmp_ult_s); + break; + case 6: + MIPS_FPU_EMU_INC_STATS(cmp_le_s); + break; + case 7: + MIPS_FPU_EMU_INC_STATS(cmp_ule_s); + break; + } + } else { + switch (cmpop) { + case 1: + MIPS_FPU_EMU_INC_STATS(cmp_or_s); + break; + case 2: + MIPS_FPU_EMU_INC_STATS(cmp_une_s); + break; + case 3: + MIPS_FPU_EMU_INC_STATS(cmp_ne_s); + break; + } + } + } else { + if (!(MIPSInst_FUNC(ir) & PREDICATE_BIT)) { + switch (cmpop) { + case 0: + MIPS_FPU_EMU_INC_STATS(cmp_saf_s); + break; + case 1: + MIPS_FPU_EMU_INC_STATS(cmp_sun_s); + break; + case 2: + MIPS_FPU_EMU_INC_STATS(cmp_seq_s); + break; + case 3: + MIPS_FPU_EMU_INC_STATS(cmp_sueq_s); + break; + case 4: + MIPS_FPU_EMU_INC_STATS(cmp_slt_s); + break; + case 5: + MIPS_FPU_EMU_INC_STATS(cmp_sult_s); + break; + case 6: + MIPS_FPU_EMU_INC_STATS(cmp_sle_s); + break; + case 7: + MIPS_FPU_EMU_INC_STATS(cmp_sule_s); + break; + } + } else { + switch (cmpop) { + case 1: + MIPS_FPU_EMU_INC_STATS(cmp_sor_s); + break; + case 2: + MIPS_FPU_EMU_INC_STATS(cmp_sune_s); + break; + case 3: + MIPS_FPU_EMU_INC_STATS(cmp_sne_s); + break; + } + } + } + /* fmt is w_fmt for single precision so fix it */ rfmt = s_fmt; /* default to false */ @@ -2366,6 +2578,7 @@ dcopuop: break; } } + break; } case l_fmt: @@ -2378,11 +2591,13 @@ dcopuop: switch (MIPSInst_FUNC(ir)) { case fcvts_op: /* convert long to single precision real */ + MIPS_FPU_EMU_INC_STATS(cvt_s_l); rv.s = ieee754sp_flong(bits); rfmt = s_fmt; goto copcsr; case fcvtd_op: /* convert long to double precision real */ + MIPS_FPU_EMU_INC_STATS(cvt_d_l); rv.d = ieee754dp_flong(bits); rfmt = d_fmt; goto copcsr; @@ -2396,6 +2611,90 @@ dcopuop: (MIPSInst_FUNC(ir) & 0x20)) return SIGILL; + if (!sig) { + if (!(MIPSInst_FUNC(ir) & PREDICATE_BIT)) { + switch (cmpop) { + case 0: + MIPS_FPU_EMU_INC_STATS(cmp_af_d); + break; + case 1: + MIPS_FPU_EMU_INC_STATS(cmp_un_d); + break; + case 2: + MIPS_FPU_EMU_INC_STATS(cmp_eq_d); + break; + case 3: + MIPS_FPU_EMU_INC_STATS(cmp_ueq_d); + break; + case 4: + MIPS_FPU_EMU_INC_STATS(cmp_lt_d); + break; + case 5: + MIPS_FPU_EMU_INC_STATS(cmp_ult_d); + break; + case 6: + MIPS_FPU_EMU_INC_STATS(cmp_le_d); + break; + case 7: + MIPS_FPU_EMU_INC_STATS(cmp_ule_d); + break; + } + } else { + switch (cmpop) { + case 1: + MIPS_FPU_EMU_INC_STATS(cmp_or_d); + break; + case 2: + MIPS_FPU_EMU_INC_STATS(cmp_une_d); + break; + case 3: + MIPS_FPU_EMU_INC_STATS(cmp_ne_d); + break; + } + } + } else { + if (!(MIPSInst_FUNC(ir) & PREDICATE_BIT)) { + switch (cmpop) { + case 0: + MIPS_FPU_EMU_INC_STATS(cmp_saf_d); + break; + case 1: + MIPS_FPU_EMU_INC_STATS(cmp_sun_d); + break; + case 2: + MIPS_FPU_EMU_INC_STATS(cmp_seq_d); + break; + case 3: + MIPS_FPU_EMU_INC_STATS(cmp_sueq_d); + break; + case 4: + MIPS_FPU_EMU_INC_STATS(cmp_slt_d); + break; + case 5: + MIPS_FPU_EMU_INC_STATS(cmp_sult_d); + break; + case 6: + MIPS_FPU_EMU_INC_STATS(cmp_sle_d); + break; + case 7: + MIPS_FPU_EMU_INC_STATS(cmp_sule_d); + break; + } + } else { + switch (cmpop) { + case 1: + MIPS_FPU_EMU_INC_STATS(cmp_sor_d); + break; + case 2: + MIPS_FPU_EMU_INC_STATS(cmp_sune_d); + break; + case 3: + MIPS_FPU_EMU_INC_STATS(cmp_sne_d); + break; + } + } + } + /* fmt is l_fmt for double precision so fix it */ rfmt = d_fmt; /* default to false */ @@ -2439,6 +2738,8 @@ dcopuop: break; } } + break; + default: return SIGILL; } diff --git a/arch/mips/math-emu/dp_add.c b/arch/mips/math-emu/dp_add.c index 8954ef031f84..678de20e4cb1 100644 --- a/arch/mips/math-emu/dp_add.c +++ b/arch/mips/math-emu/dp_add.c @@ -104,8 +104,7 @@ union ieee754dp ieee754dp_add(union ieee754dp x, union ieee754dp y) case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM): DPDNORMX; - - /* FALL THROUGH */ + /* fall through */ case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_DNORM): DPDNORMY; diff --git a/arch/mips/math-emu/dp_div.c b/arch/mips/math-emu/dp_div.c index f4746f7c5f63..3063ae3ab3b9 100644 --- a/arch/mips/math-emu/dp_div.c +++ b/arch/mips/math-emu/dp_div.c @@ -103,6 +103,7 @@ union ieee754dp ieee754dp_div(union ieee754dp x, union ieee754dp y) case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM): DPDNORMX; + /* fall through */ case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_DNORM): DPDNORMY; diff --git a/arch/mips/math-emu/dp_fmax.c b/arch/mips/math-emu/dp_fmax.c index 5bec64f2884e..d1f984b40344 100644 --- a/arch/mips/math-emu/dp_fmax.c +++ b/arch/mips/math-emu/dp_fmax.c @@ -96,6 +96,7 @@ union ieee754dp ieee754dp_fmax(union ieee754dp x, union ieee754dp y) case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM): DPDNORMX; + /* fall through */ case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_DNORM): DPDNORMY; @@ -224,6 +225,7 @@ union ieee754dp ieee754dp_fmaxa(union ieee754dp x, union ieee754dp y) case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM): DPDNORMX; + /* fall through */ case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_DNORM): DPDNORMY; diff --git a/arch/mips/math-emu/dp_fmin.c b/arch/mips/math-emu/dp_fmin.c index a287b23818d8..f98b96135c8d 100644 --- a/arch/mips/math-emu/dp_fmin.c +++ b/arch/mips/math-emu/dp_fmin.c @@ -96,6 +96,7 @@ union ieee754dp ieee754dp_fmin(union ieee754dp x, union ieee754dp y) case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM): DPDNORMX; + /* fall through */ case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_DNORM): DPDNORMY; @@ -224,6 +225,7 @@ union ieee754dp ieee754dp_fmina(union ieee754dp x, union ieee754dp y) case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM): DPDNORMX; + /* fall through */ case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_DNORM): DPDNORMY; diff --git a/arch/mips/math-emu/dp_maddf.c b/arch/mips/math-emu/dp_maddf.c index 119eda9fa1ea..7ea2f8222026 100644 --- a/arch/mips/math-emu/dp_maddf.c +++ b/arch/mips/math-emu/dp_maddf.c @@ -14,83 +14,91 @@ #include "ieee754dp.h" -union ieee754dp ieee754dp_maddf(union ieee754dp z, union ieee754dp x, - union ieee754dp y) + +/* 128 bits shift right logical with rounding. */ +static void srl128(u64 *hptr, u64 *lptr, int count) +{ + u64 low; + + if (count >= 128) { + *lptr = *hptr != 0 || *lptr != 0; + *hptr = 0; + } else if (count >= 64) { + if (count == 64) { + *lptr = *hptr | (*lptr != 0); + } else { + low = *lptr; + *lptr = *hptr >> (count - 64); + *lptr |= (*hptr << (128 - count)) != 0 || low != 0; + } + *hptr = 0; + } else { + low = *lptr; + *lptr = low >> count | *hptr << (64 - count); + *lptr |= (low << (64 - count)) != 0; + *hptr = *hptr >> count; + } +} + +static union ieee754dp _dp_maddf(union ieee754dp z, union ieee754dp x, + union ieee754dp y, enum maddf_flags flags) { int re; int rs; - u64 rm; - unsigned lxm; - unsigned hxm; - unsigned lym; - unsigned hym; + unsigned int lxm; + unsigned int hxm; + unsigned int lym; + unsigned int hym; u64 lrm; u64 hrm; + u64 lzm; + u64 hzm; u64 t; u64 at; int s; COMPXDP; COMPYDP; - - u64 zm; int ze; int zs __maybe_unused; int zc; + COMPZDP; EXPLODEXDP; EXPLODEYDP; - EXPLODEDP(z, zc, zs, ze, zm) + EXPLODEZDP; FLUSHXDP; FLUSHYDP; - FLUSHDP(z, zc, zs, ze, zm); + FLUSHZDP; ieee754_clearcx(); - switch (zc) { - case IEEE754_CLASS_SNAN: - ieee754_setcx(IEEE754_INVALID_OPERATION); + /* + * Handle the cases when at least one of x, y or z is a NaN. + * Order of precedence is sNaN, qNaN and z, x, y. + */ + if (zc == IEEE754_CLASS_SNAN) return ieee754dp_nanxcpt(z); - case IEEE754_CLASS_DNORM: - DPDNORMx(zm, ze); - /* QNAN is handled separately below */ - } - - switch (CLPAIR(xc, yc)) { - case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_SNAN): - case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_SNAN): - case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_SNAN): - case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_SNAN): - case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_SNAN): - return ieee754dp_nanxcpt(y); - - case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_SNAN): - case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_QNAN): - case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_ZERO): - case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_NORM): - case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_DNORM): - case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_INF): + if (xc == IEEE754_CLASS_SNAN) return ieee754dp_nanxcpt(x); - - case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_QNAN): - case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_QNAN): - case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_QNAN): - case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_QNAN): + if (yc == IEEE754_CLASS_SNAN) + return ieee754dp_nanxcpt(y); + if (zc == IEEE754_CLASS_QNAN) + return z; + if (xc == IEEE754_CLASS_QNAN) + return x; + if (yc == IEEE754_CLASS_QNAN) return y; - case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN): - case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_ZERO): - case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_NORM): - case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_DNORM): - case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_INF): - return x; + if (zc == IEEE754_CLASS_DNORM) + DPDNORMZ; + /* ZERO z cases are handled separately below */ + switch (CLPAIR(xc, yc)) { /* * Infinity handling */ case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_ZERO): case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_INF): - if (zc == IEEE754_CLASS_QNAN) - return z; ieee754_setcx(IEEE754_INVALID_OPERATION); return ieee754dp_indef(); @@ -99,9 +107,27 @@ union ieee754dp ieee754dp_maddf(union ieee754dp z, union ieee754dp x, case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_NORM): case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_DNORM): case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_INF): - if (zc == IEEE754_CLASS_QNAN) - return z; - return ieee754dp_inf(xs ^ ys); + if ((zc == IEEE754_CLASS_INF) && + ((!(flags & MADDF_NEGATE_PRODUCT) && (zs != (xs ^ ys))) || + ((flags & MADDF_NEGATE_PRODUCT) && (zs == (xs ^ ys))))) { + /* + * Cases of addition of infinities with opposite signs + * or subtraction of infinities with same signs. + */ + ieee754_setcx(IEEE754_INVALID_OPERATION); + return ieee754dp_indef(); + } + /* + * z is here either not an infinity, or an infinity having the + * same sign as product (x*y) (in case of MADDF.D instruction) + * or product -(x*y) (in MSUBF.D case). The result must be an + * infinity, and its sign is determined only by the value of + * (flags & MADDF_NEGATE_PRODUCT) and the signs of x and y. + */ + if (flags & MADDF_NEGATE_PRODUCT) + return ieee754dp_inf(1 ^ (xs ^ ys)); + else + return ieee754dp_inf(xs ^ ys); case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_ZERO): case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_NORM): @@ -110,34 +136,45 @@ union ieee754dp ieee754dp_maddf(union ieee754dp z, union ieee754dp x, case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_ZERO): if (zc == IEEE754_CLASS_INF) return ieee754dp_inf(zs); - /* Multiplication is 0 so just return z */ + if (zc == IEEE754_CLASS_ZERO) { + /* Handle cases +0 + (-0) and similar ones. */ + if ((!(flags & MADDF_NEGATE_PRODUCT) + && (zs == (xs ^ ys))) || + ((flags & MADDF_NEGATE_PRODUCT) + && (zs != (xs ^ ys)))) + /* + * Cases of addition of zeros of equal signs + * or subtraction of zeroes of opposite signs. + * The sign of the resulting zero is in any + * such case determined only by the sign of z. + */ + return z; + + return ieee754dp_zero(ieee754_csr.rm == FPU_CSR_RD); + } + /* x*y is here 0, and z is not 0, so just return z */ return z; case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM): DPDNORMX; + /* fall through */ case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_DNORM): - if (zc == IEEE754_CLASS_QNAN) - return z; - else if (zc == IEEE754_CLASS_INF) + if (zc == IEEE754_CLASS_INF) return ieee754dp_inf(zs); DPDNORMY; break; case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_NORM): - if (zc == IEEE754_CLASS_QNAN) - return z; - else if (zc == IEEE754_CLASS_INF) + if (zc == IEEE754_CLASS_INF) return ieee754dp_inf(zs); DPDNORMX; break; case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_NORM): - if (zc == IEEE754_CLASS_QNAN) - return z; - else if (zc == IEEE754_CLASS_INF) + if (zc == IEEE754_CLASS_INF) return ieee754dp_inf(zs); - /* fall through to real computations */ + /* continue to real computations */ } /* Finally get to do some computation */ @@ -154,18 +191,17 @@ union ieee754dp ieee754dp_maddf(union ieee754dp z, union ieee754dp x, re = xe + ye; rs = xs ^ ys; + if (flags & MADDF_NEGATE_PRODUCT) + rs ^= 1; /* shunt to top of word */ xm <<= 64 - (DP_FBITS + 1); ym <<= 64 - (DP_FBITS + 1); /* - * Multiply 32 bits xm, ym to give high 32 bits rm with stickness. + * Multiply 64 bits xm and ym to give 128 bits result in hrm:lrm. */ - /* 32 * 32 => 64 */ -#define DPXMULT(x, y) ((u64)(x) * (u64)y) - lxm = xm; hxm = xm >> 32; lym = ym; @@ -190,76 +226,120 @@ union ieee754dp ieee754dp_maddf(union ieee754dp z, union ieee754dp x, hrm = hrm + (t >> 32); - rm = hrm | (lrm != 0); - - /* - * Sticky shift down to normal rounding precision. - */ - if ((s64) rm < 0) { - rm = (rm >> (64 - (DP_FBITS + 1 + 3))) | - ((rm << (DP_FBITS + 1 + 3)) != 0); - re++; - } else { - rm = (rm >> (64 - (DP_FBITS + 1 + 3 + 1))) | - ((rm << (DP_FBITS + 1 + 3 + 1)) != 0); + /* Put explicit bit at bit 126 if necessary */ + if ((int64_t)hrm < 0) { + lrm = (hrm << 63) | (lrm >> 1); + hrm = hrm >> 1; + re++; } - assert(rm & (DP_HIDDEN_BIT << 3)); - /* And now the addition */ - assert(zm & DP_HIDDEN_BIT); + assert(hrm & (1 << 62)); - /* - * Provide guard,round and stick bit space. - */ - zm <<= 3; + if (zc == IEEE754_CLASS_ZERO) { + /* + * Move explicit bit from bit 126 to bit 55 since the + * ieee754dp_format code expects the mantissa to be + * 56 bits wide (53 + 3 rounding bits). + */ + srl128(&hrm, &lrm, (126 - 55)); + return ieee754dp_format(rs, re, lrm); + } + + /* Move explicit bit from bit 52 to bit 126 */ + lzm = 0; + hzm = zm << 10; + assert(hzm & (1 << 62)); + /* Make the exponents the same */ if (ze > re) { /* * Have to shift y fraction right to align. */ s = ze - re; - rm = XDPSRS(rm, s); + srl128(&hrm, &lrm, s); re += s; } else if (re > ze) { /* * Have to shift x fraction right to align. */ s = re - ze; - zm = XDPSRS(zm, s); + srl128(&hzm, &lzm, s); ze += s; } assert(ze == re); assert(ze <= DP_EMAX); + /* Do the addition */ if (zs == rs) { /* - * Generate 28 bit result of adding two 27 bit numbers - * leaving result in xm, xs and xe. + * Generate 128 bit result by adding two 127 bit numbers + * leaving result in hzm:lzm, zs and ze. */ - zm = zm + rm; - - if (zm >> (DP_FBITS + 1 + 3)) { /* carry out */ - zm = XDPSRS1(zm); + hzm = hzm + hrm + (lzm > (lzm + lrm)); + lzm = lzm + lrm; + if ((int64_t)hzm < 0) { /* carry out */ + srl128(&hzm, &lzm, 1); ze++; } } else { - if (zm >= rm) { - zm = zm - rm; + if (hzm > hrm || (hzm == hrm && lzm >= lrm)) { + hzm = hzm - hrm - (lzm < lrm); + lzm = lzm - lrm; } else { - zm = rm - zm; + hzm = hrm - hzm - (lrm < lzm); + lzm = lrm - lzm; zs = rs; } - if (zm == 0) + if (lzm == 0 && hzm == 0) return ieee754dp_zero(ieee754_csr.rm == FPU_CSR_RD); /* - * Normalize to rounding precision. + * Put explicit bit at bit 126 if necessary. */ - while ((zm >> (DP_FBITS + 3)) == 0) { - zm <<= 1; - ze--; + if (hzm == 0) { + /* left shift by 63 or 64 bits */ + if ((int64_t)lzm < 0) { + /* MSB of lzm is the explicit bit */ + hzm = lzm >> 1; + lzm = lzm << 63; + ze -= 63; + } else { + hzm = lzm; + lzm = 0; + ze -= 64; + } + } + + t = 0; + while ((hzm >> (62 - t)) == 0) + t++; + + assert(t <= 62); + if (t) { + hzm = hzm << t | lzm >> (64 - t); + lzm = lzm << t; + ze -= t; } } - return ieee754dp_format(zs, ze, zm); + /* + * Move explicit bit from bit 126 to bit 55 since the + * ieee754dp_format code expects the mantissa to be + * 56 bits wide (53 + 3 rounding bits). + */ + srl128(&hzm, &lzm, (126 - 55)); + + return ieee754dp_format(zs, ze, lzm); +} + +union ieee754dp ieee754dp_maddf(union ieee754dp z, union ieee754dp x, + union ieee754dp y) +{ + return _dp_maddf(z, x, y, 0); +} + +union ieee754dp ieee754dp_msubf(union ieee754dp z, union ieee754dp x, + union ieee754dp y) +{ + return _dp_maddf(z, x, y, MADDF_NEGATE_PRODUCT); } diff --git a/arch/mips/math-emu/dp_msubf.c b/arch/mips/math-emu/dp_msubf.c deleted file mode 100644 index 12241262f856..000000000000 --- a/arch/mips/math-emu/dp_msubf.c +++ /dev/null @@ -1,269 +0,0 @@ -/* - * IEEE754 floating point arithmetic - * double precision: MSUB.f (Fused Multiply Subtract) - * MSUBF.fmt: FPR[fd] = FPR[fd] - (FPR[fs] x FPR[ft]) - * - * MIPS floating point support - * Copyright (C) 2015 Imagination Technologies, Ltd. - * Author: Markos Chandras <markos.chandras@imgtec.com> - * - * This program is free software; you can distribute it and/or modify it - * under the terms of the GNU General Public License as published by the - * Free Software Foundation; version 2 of the License. - */ - -#include "ieee754dp.h" - -union ieee754dp ieee754dp_msubf(union ieee754dp z, union ieee754dp x, - union ieee754dp y) -{ - int re; - int rs; - u64 rm; - unsigned lxm; - unsigned hxm; - unsigned lym; - unsigned hym; - u64 lrm; - u64 hrm; - u64 t; - u64 at; - int s; - - COMPXDP; - COMPYDP; - - u64 zm; int ze; int zs __maybe_unused; int zc; - - EXPLODEXDP; - EXPLODEYDP; - EXPLODEDP(z, zc, zs, ze, zm) - - FLUSHXDP; - FLUSHYDP; - FLUSHDP(z, zc, zs, ze, zm); - - ieee754_clearcx(); - - switch (zc) { - case IEEE754_CLASS_SNAN: - ieee754_setcx(IEEE754_INVALID_OPERATION); - return ieee754dp_nanxcpt(z); - case IEEE754_CLASS_DNORM: - DPDNORMx(zm, ze); - /* QNAN is handled separately below */ - } - - switch (CLPAIR(xc, yc)) { - case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_SNAN): - case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_SNAN): - case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_SNAN): - case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_SNAN): - case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_SNAN): - return ieee754dp_nanxcpt(y); - - case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_SNAN): - case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_QNAN): - case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_ZERO): - case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_NORM): - case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_DNORM): - case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_INF): - return ieee754dp_nanxcpt(x); - - case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_QNAN): - case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_QNAN): - case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_QNAN): - case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_QNAN): - return y; - - case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN): - case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_ZERO): - case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_NORM): - case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_DNORM): - case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_INF): - return x; - - - /* - * Infinity handling - */ - case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_ZERO): - case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_INF): - if (zc == IEEE754_CLASS_QNAN) - return z; - ieee754_setcx(IEEE754_INVALID_OPERATION); - return ieee754dp_indef(); - - case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_INF): - case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_INF): - case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_NORM): - case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_DNORM): - case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_INF): - if (zc == IEEE754_CLASS_QNAN) - return z; - return ieee754dp_inf(xs ^ ys); - - case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_ZERO): - case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_NORM): - case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_DNORM): - case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_ZERO): - case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_ZERO): - if (zc == IEEE754_CLASS_INF) - return ieee754dp_inf(zs); - /* Multiplication is 0 so just return z */ - return z; - - case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM): - DPDNORMX; - - case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_DNORM): - if (zc == IEEE754_CLASS_QNAN) - return z; - else if (zc == IEEE754_CLASS_INF) - return ieee754dp_inf(zs); - DPDNORMY; - break; - - case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_NORM): - if (zc == IEEE754_CLASS_QNAN) - return z; - else if (zc == IEEE754_CLASS_INF) - return ieee754dp_inf(zs); - DPDNORMX; - break; - - case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_NORM): - if (zc == IEEE754_CLASS_QNAN) - return z; - else if (zc == IEEE754_CLASS_INF) - return ieee754dp_inf(zs); - /* fall through to real computations */ - } - - /* Finally get to do some computation */ - - /* - * Do the multiplication bit first - * - * rm = xm * ym, re = xe + ye basically - * - * At this point xm and ym should have been normalized. - */ - assert(xm & DP_HIDDEN_BIT); - assert(ym & DP_HIDDEN_BIT); - - re = xe + ye; - rs = xs ^ ys; - - /* shunt to top of word */ - xm <<= 64 - (DP_FBITS + 1); - ym <<= 64 - (DP_FBITS + 1); - - /* - * Multiply 32 bits xm, ym to give high 32 bits rm with stickness. - */ - - /* 32 * 32 => 64 */ -#define DPXMULT(x, y) ((u64)(x) * (u64)y) - - lxm = xm; - hxm = xm >> 32; - lym = ym; - hym = ym >> 32; - - lrm = DPXMULT(lxm, lym); - hrm = DPXMULT(hxm, hym); - - t = DPXMULT(lxm, hym); - - at = lrm + (t << 32); - hrm += at < lrm; - lrm = at; - - hrm = hrm + (t >> 32); - - t = DPXMULT(hxm, lym); - - at = lrm + (t << 32); - hrm += at < lrm; - lrm = at; - - hrm = hrm + (t >> 32); - - rm = hrm | (lrm != 0); - - /* - * Sticky shift down to normal rounding precision. - */ - if ((s64) rm < 0) { - rm = (rm >> (64 - (DP_FBITS + 1 + 3))) | - ((rm << (DP_FBITS + 1 + 3)) != 0); - re++; - } else { - rm = (rm >> (64 - (DP_FBITS + 1 + 3 + 1))) | - ((rm << (DP_FBITS + 1 + 3 + 1)) != 0); - } - assert(rm & (DP_HIDDEN_BIT << 3)); - - /* And now the subtraction */ - - /* flip sign of r and handle as add */ - rs ^= 1; - - assert(zm & DP_HIDDEN_BIT); - - /* - * Provide guard,round and stick bit space. - */ - zm <<= 3; - - if (ze > re) { - /* - * Have to shift y fraction right to align. - */ - s = ze - re; - rm = XDPSRS(rm, s); - re += s; - } else if (re > ze) { - /* - * Have to shift x fraction right to align. - */ - s = re - ze; - zm = XDPSRS(zm, s); - ze += s; - } - assert(ze == re); - assert(ze <= DP_EMAX); - - if (zs == rs) { - /* - * Generate 28 bit result of adding two 27 bit numbers - * leaving result in xm, xs and xe. - */ - zm = zm + rm; - - if (zm >> (DP_FBITS + 1 + 3)) { /* carry out */ - zm = XDPSRS1(zm); - ze++; - } - } else { - if (zm >= rm) { - zm = zm - rm; - } else { - zm = rm - zm; - zs = rs; - } - if (zm == 0) - return ieee754dp_zero(ieee754_csr.rm == FPU_CSR_RD); - - /* - * Normalize to rounding precision. - */ - while ((zm >> (DP_FBITS + 3)) == 0) { - zm <<= 1; - ze--; - } - } - - return ieee754dp_format(zs, ze, zm); -} diff --git a/arch/mips/math-emu/dp_mul.c b/arch/mips/math-emu/dp_mul.c index d0901f03fa19..c34a6cdf1b25 100644 --- a/arch/mips/math-emu/dp_mul.c +++ b/arch/mips/math-emu/dp_mul.c @@ -26,10 +26,10 @@ union ieee754dp ieee754dp_mul(union ieee754dp x, union ieee754dp y) int re; int rs; u64 rm; - unsigned lxm; - unsigned hxm; - unsigned lym; - unsigned hym; + unsigned int lxm; + unsigned int hxm; + unsigned int lym; + unsigned int hym; u64 lrm; u64 hrm; u64 t; @@ -101,6 +101,7 @@ union ieee754dp ieee754dp_mul(union ieee754dp x, union ieee754dp y) case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM): DPDNORMX; + /* fall through */ case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_DNORM): DPDNORMY; @@ -125,12 +126,9 @@ union ieee754dp ieee754dp_mul(union ieee754dp x, union ieee754dp y) ym <<= 64 - (DP_FBITS + 1); /* - * Multiply 32 bits xm, ym to give high 32 bits rm with stickness. + * Multiply 64 bits xm, ym to give high 64 bits rm with stickness. */ - /* 32 * 32 => 64 */ -#define DPXMULT(x, y) ((u64)(x) * (u64)y) - lxm = xm; hxm = xm >> 32; lym = ym; @@ -163,7 +161,7 @@ union ieee754dp ieee754dp_mul(union ieee754dp x, union ieee754dp y) if ((s64) rm < 0) { rm = (rm >> (64 - (DP_FBITS + 1 + 3))) | ((rm << (DP_FBITS + 1 + 3)) != 0); - re++; + re++; } else { rm = (rm >> (64 - (DP_FBITS + 1 + 3 + 1))) | ((rm << (DP_FBITS + 1 + 3 + 1)) != 0); diff --git a/arch/mips/math-emu/dp_rint.c b/arch/mips/math-emu/dp_rint.c new file mode 100644 index 000000000000..c3b9077ff357 --- /dev/null +++ b/arch/mips/math-emu/dp_rint.c @@ -0,0 +1,89 @@ +/* IEEE754 floating point arithmetic + * double precision: common utilities + */ +/* + * MIPS floating point support + * Copyright (C) 1994-2000 Algorithmics Ltd. + * Copyright (C) 2017 Imagination Technologies, Ltd. + * Author: Aleksandar Markovic <aleksandar.markovic@imgtec.com> + * + * This program is free software; you can distribute it and/or modify it + * under the terms of the GNU General Public License (Version 2) as + * published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License + * for more details. + * + * You should have received a copy of the GNU General Public License along + * with this program. + */ + +#include "ieee754dp.h" + +union ieee754dp ieee754dp_rint(union ieee754dp x) +{ + union ieee754dp ret; + u64 residue; + int sticky; + int round; + int odd; + + COMPXDP; + + ieee754_clearcx(); + + EXPLODEXDP; + FLUSHXDP; + + if (xc == IEEE754_CLASS_SNAN) + return ieee754dp_nanxcpt(x); + + if ((xc == IEEE754_CLASS_QNAN) || + (xc == IEEE754_CLASS_INF) || + (xc == IEEE754_CLASS_ZERO)) + return x; + + if (xe >= DP_FBITS) + return x; + + if (xe < -1) { + residue = xm; + round = 0; + sticky = residue != 0; + xm = 0; + } else { + residue = xm << (64 - DP_FBITS + xe); + round = (residue >> 63) != 0; + sticky = (residue << 1) != 0; + xm >>= DP_FBITS - xe; + } + + odd = (xm & 0x1) != 0x0; + + switch (ieee754_csr.rm) { + case FPU_CSR_RN: /* toward nearest */ + if (round && (sticky || odd)) + xm++; + break; + case FPU_CSR_RZ: /* toward zero */ + break; + case FPU_CSR_RU: /* toward +infinity */ + if ((round || sticky) && !xs) + xm++; + break; + case FPU_CSR_RD: /* toward -infinity */ + if ((round || sticky) && xs) + xm++; + break; + } + + if (round || sticky) + ieee754_setcx(IEEE754_INEXACT); + + ret = ieee754dp_flong(xm); + DPSIGN(ret) = xs; + + return ret; +} diff --git a/arch/mips/math-emu/dp_simple.c b/arch/mips/math-emu/dp_simple.c index 926d56bf37f2..eb96485ed939 100644 --- a/arch/mips/math-emu/dp_simple.c +++ b/arch/mips/math-emu/dp_simple.c @@ -23,27 +23,39 @@ union ieee754dp ieee754dp_neg(union ieee754dp x) { - unsigned int oldrm; union ieee754dp y; - oldrm = ieee754_csr.rm; - ieee754_csr.rm = FPU_CSR_RD; - y = ieee754dp_sub(ieee754dp_zero(0), x); - ieee754_csr.rm = oldrm; + if (ieee754_csr.abs2008) { + y = x; + DPSIGN(y) = !DPSIGN(x); + } else { + unsigned int oldrm; + + oldrm = ieee754_csr.rm; + ieee754_csr.rm = FPU_CSR_RD; + y = ieee754dp_sub(ieee754dp_zero(0), x); + ieee754_csr.rm = oldrm; + } return y; } union ieee754dp ieee754dp_abs(union ieee754dp x) { - unsigned int oldrm; union ieee754dp y; - oldrm = ieee754_csr.rm; - ieee754_csr.rm = FPU_CSR_RD; - if (DPSIGN(x)) - y = ieee754dp_sub(ieee754dp_zero(0), x); - else - y = ieee754dp_add(ieee754dp_zero(0), x); - ieee754_csr.rm = oldrm; + if (ieee754_csr.abs2008) { + y = x; + DPSIGN(y) = 0; + } else { + unsigned int oldrm; + + oldrm = ieee754_csr.rm; + ieee754_csr.rm = FPU_CSR_RD; + if (DPSIGN(x)) + y = ieee754dp_sub(ieee754dp_zero(0), x); + else + y = ieee754dp_add(ieee754dp_zero(0), x); + ieee754_csr.rm = oldrm; + } return y; } diff --git a/arch/mips/math-emu/dp_sqrt.c b/arch/mips/math-emu/dp_sqrt.c index cd5bc083001e..1d26c92e5295 100644 --- a/arch/mips/math-emu/dp_sqrt.c +++ b/arch/mips/math-emu/dp_sqrt.c @@ -21,7 +21,7 @@ #include "ieee754dp.h" -static const unsigned table[] = { +static const unsigned int table[] = { 0, 1204, 3062, 5746, 9193, 13348, 18162, 23592, 29598, 36145, 43202, 50740, 58733, 67158, 75992, 85215, 83599, 71378, 60428, 50647, 41945, 34246, @@ -33,7 +33,7 @@ union ieee754dp ieee754dp_sqrt(union ieee754dp x) { struct _ieee754_csr oldcsr; union ieee754dp y, z, t; - unsigned scalx, yh; + unsigned int scalx, yh; COMPXDP; EXPLODEXDP; @@ -91,7 +91,8 @@ union ieee754dp ieee754dp_sqrt(union ieee754dp x) scalx -= 256; } - y = x = builddp(0, xe + DP_EBIAS, xm & ~DP_HIDDEN_BIT); + x = builddp(0, xe + DP_EBIAS, xm & ~DP_HIDDEN_BIT); + y = x; /* magic initial approximation to almost 8 sig. bits */ yh = y.bits >> 32; @@ -108,7 +109,8 @@ union ieee754dp ieee754dp_sqrt(union ieee754dp x) /* triple to almost 56 sig. bits: y ~= sqrt(x) to within 1 ulp */ /* t=y*y; z=t; pt[n0]+=0x00100000; t+=z; z=(x-z)*y; */ - z = t = ieee754dp_mul(y, y); + t = ieee754dp_mul(y, y); + z = t; t.bexp += 0x001; t = ieee754dp_add(t, z); z = ieee754dp_mul(ieee754dp_sub(x, z), y); @@ -140,7 +142,7 @@ union ieee754dp ieee754dp_sqrt(union ieee754dp x) switch (oldcsr.rm) { case FPU_CSR_RU: y.bits += 1; - /* drop through */ + /* fall through */ case FPU_CSR_RN: t.bits += 1; break; diff --git a/arch/mips/math-emu/dp_sub.c b/arch/mips/math-emu/dp_sub.c index fc17a781b9ae..3cc48b86519b 100644 --- a/arch/mips/math-emu/dp_sub.c +++ b/arch/mips/math-emu/dp_sub.c @@ -106,7 +106,7 @@ union ieee754dp ieee754dp_sub(union ieee754dp x, union ieee754dp y) case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM): DPDNORMX; - /* FALL THROUGH */ + /* fall through */ case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_DNORM): /* normalize ym,ye */ diff --git a/arch/mips/math-emu/dp_tint.c b/arch/mips/math-emu/dp_tint.c index 6ffc336c530e..f3985617ce31 100644 --- a/arch/mips/math-emu/dp_tint.c +++ b/arch/mips/math-emu/dp_tint.c @@ -38,10 +38,13 @@ int ieee754dp_tint(union ieee754dp x) switch (xc) { case IEEE754_CLASS_SNAN: case IEEE754_CLASS_QNAN: - case IEEE754_CLASS_INF: ieee754_setcx(IEEE754_INVALID_OPERATION); return ieee754si_indef(); + case IEEE754_CLASS_INF: + ieee754_setcx(IEEE754_INVALID_OPERATION); + return ieee754si_overflow(xs); + case IEEE754_CLASS_ZERO: return 0; @@ -53,7 +56,7 @@ int ieee754dp_tint(union ieee754dp x) /* Set invalid. We will only use overflow for floating point overflow */ ieee754_setcx(IEEE754_INVALID_OPERATION); - return ieee754si_indef(); + return ieee754si_overflow(xs); } /* oh gawd */ if (xe > DP_FBITS) { @@ -93,7 +96,7 @@ int ieee754dp_tint(union ieee754dp x) if ((xm >> 31) != 0 && (xs == 0 || xm != 0x80000000)) { /* This can happen after rounding */ ieee754_setcx(IEEE754_INVALID_OPERATION); - return ieee754si_indef(); + return ieee754si_overflow(xs); } if (round || sticky) ieee754_setcx(IEEE754_INEXACT); diff --git a/arch/mips/math-emu/dp_tlong.c b/arch/mips/math-emu/dp_tlong.c index 9cdc145b75e0..748fa10ed4cf 100644 --- a/arch/mips/math-emu/dp_tlong.c +++ b/arch/mips/math-emu/dp_tlong.c @@ -38,10 +38,13 @@ s64 ieee754dp_tlong(union ieee754dp x) switch (xc) { case IEEE754_CLASS_SNAN: case IEEE754_CLASS_QNAN: - case IEEE754_CLASS_INF: ieee754_setcx(IEEE754_INVALID_OPERATION); return ieee754di_indef(); + case IEEE754_CLASS_INF: + ieee754_setcx(IEEE754_INVALID_OPERATION); + return ieee754di_overflow(xs); + case IEEE754_CLASS_ZERO: return 0; @@ -56,7 +59,7 @@ s64 ieee754dp_tlong(union ieee754dp x) /* Set invalid. We will only use overflow for floating point overflow */ ieee754_setcx(IEEE754_INVALID_OPERATION); - return ieee754di_indef(); + return ieee754di_overflow(xs); } /* oh gawd */ if (xe > DP_FBITS) { @@ -97,7 +100,7 @@ s64 ieee754dp_tlong(union ieee754dp x) if ((xm >> 63) != 0) { /* This can happen after rounding */ ieee754_setcx(IEEE754_INVALID_OPERATION); - return ieee754di_indef(); + return ieee754di_overflow(xs); } if (round || sticky) ieee754_setcx(IEEE754_INEXACT); diff --git a/arch/mips/math-emu/dsemul.c b/arch/mips/math-emu/dsemul.c index cbb36c14b155..4a094f7acb3d 100644 --- a/arch/mips/math-emu/dsemul.c +++ b/arch/mips/math-emu/dsemul.c @@ -1,3 +1,6 @@ +#include <linux/err.h> +#include <linux/slab.h> + #include <asm/branch.h> #include <asm/cacheflush.h> #include <asm/fpu_emulator.h> @@ -5,158 +8,296 @@ #include <asm/mipsregs.h> #include <asm/uaccess.h> -#include "ieee754.h" - -/* - * Emulate the arbritrary instruction ir at xcp->cp0_epc. Required when - * we have to emulate the instruction in a COP1 branch delay slot. Do - * not change cp0_epc due to the instruction +/** + * struct emuframe - The 'emulation' frame structure + * @emul: The instruction to 'emulate'. + * @badinst: A break instruction to cause a return to the kernel. * - * According to the spec: - * 1) it shouldn't be a branch :-) - * 2) it can be a COP instruction :-( - * 3) if we are tring to run a protected memory space we must take - * special care on memory access instructions :-( - */ - -/* - * "Trampoline" return routine to catch exception following - * execution of delay-slot instruction execution. + * This structure defines the frames placed within the delay slot emulation + * page in response to a call to mips_dsemul(). Each thread may be allocated + * only one frame at any given time. The kernel stores within it the + * instruction to be 'emulated' followed by a break instruction, then + * executes the frame in user mode. The break causes a trap to the kernel + * which leads to do_dsemulret() being called unless the instruction in + * @emul causes a trap itself, is a branch, or a signal is delivered to + * the thread. In these cases the allocated frame will either be reused by + * a subsequent delay slot 'emulation', or be freed during signal delivery or + * upon thread exit. + * + * This approach is used because: + * + * - Actually emulating all instructions isn't feasible. We would need to + * be able to handle instructions from all revisions of the MIPS ISA, + * all ASEs & all vendor instruction set extensions. This would be a + * whole lot of work & continual maintenance burden as new instructions + * are introduced, and in the case of some vendor extensions may not + * even be possible. Thus we need to take the approach of actually + * executing the instruction. + * + * - We must execute the instruction within user context. If we were to + * execute the instruction in kernel mode then it would have access to + * kernel resources without very careful checks, leaving us with a + * high potential for security or stability issues to arise. + * + * - We used to place the frame on the users stack, but this requires + * that the stack be executable. This is bad for security so the + * per-process page is now used instead. + * + * - The instruction in @emul may be something entirely invalid for a + * delay slot. The user may (intentionally or otherwise) place a branch + * in a delay slot, or a kernel mode instruction, or something else + * which generates an exception. Thus we can't rely upon the break in + * @badinst always being hit. For this reason we track the index of the + * frame allocated to each thread, allowing us to clean it up at later + * points such as signal delivery or thread exit. + * + * - The user may generate a fake struct emuframe if they wish, invoking + * the BRK_MEMU break instruction themselves. We must therefore not + * trust that BRK_MEMU means there's actually a valid frame allocated + * to the thread, and must not allow the user to do anything they + * couldn't already. */ - struct emuframe { mips_instruction emul; mips_instruction badinst; - mips_instruction cookie; - unsigned long epc; }; -int mips_dsemul(struct pt_regs *regs, mips_instruction ir, unsigned long cpc) -{ - struct emuframe __user *fr; - int err; - - if ((get_isa16_mode(regs->cp0_epc) && ((ir >> 16) == MM_NOP16)) || - (ir == 0)) { - /* NOP is easy */ - regs->cp0_epc = cpc; - clear_delay_slot(regs); - return 0; - } +static const int emupage_frame_count = PAGE_SIZE / sizeof(struct emuframe); - pr_debug("dsemul %lx %lx\n", regs->cp0_epc, cpc); +static inline __user struct emuframe *dsemul_page(void) +{ + return (__user struct emuframe *)STACK_TOP; +} - /* - * The strategy is to push the instruction onto the user stack - * and put a trap after it which we can catch and jump to - * the required address any alternative apart from full - * instruction emulation!!. - * - * Algorithmics used a system call instruction, and - * borrowed that vector. MIPS/Linux version is a bit - * more heavyweight in the interests of portability and - * multiprocessor support. For Linux we generate a - * an unaligned access and force an address error exception. - * - * For embedded systems (stand-alone) we prefer to use a - * non-existing CP1 instruction. This prevents us from emulating - * branches, but gives us a cleaner interface to the exception - * handler (single entry point). - */ +static int alloc_emuframe(void) +{ + mm_context_t *mm_ctx = ¤t->mm->context; + int idx; - /* Ensure that the two instructions are in the same cache line */ - fr = (struct emuframe __user *) - ((regs->regs[29] - sizeof(struct emuframe)) & ~0x7); +retry: + spin_lock(&mm_ctx->bd_emupage_lock); - /* Verify that the stack pointer is not competely insane */ - if (unlikely(!access_ok(VERIFY_WRITE, fr, sizeof(struct emuframe)))) - return SIGBUS; + /* Ensure we have an allocation bitmap */ + if (!mm_ctx->bd_emupage_allocmap) { + mm_ctx->bd_emupage_allocmap = + kcalloc(BITS_TO_LONGS(emupage_frame_count), + sizeof(unsigned long), + GFP_ATOMIC); - if (get_isa16_mode(regs->cp0_epc)) { - err = __put_user(ir >> 16, (u16 __user *)(&fr->emul)); - err |= __put_user(ir & 0xffff, (u16 __user *)((long)(&fr->emul) + 2)); - err |= __put_user(BREAK_MATH >> 16, (u16 __user *)(&fr->badinst)); - err |= __put_user(BREAK_MATH & 0xffff, (u16 __user *)((long)(&fr->badinst) + 2)); - } else { - err = __put_user(ir, &fr->emul); - err |= __put_user((mips_instruction)BREAK_MATH, &fr->badinst); + if (!mm_ctx->bd_emupage_allocmap) { + idx = BD_EMUFRAME_NONE; + goto out_unlock; + } } - err |= __put_user((mips_instruction)BD_COOKIE, &fr->cookie); - err |= __put_user(cpc, &fr->epc); + /* Attempt to allocate a single bit/frame */ + idx = bitmap_find_free_region(mm_ctx->bd_emupage_allocmap, + emupage_frame_count, 0); + if (idx < 0) { + /* + * Failed to allocate a frame. We'll wait until one becomes + * available. We unlock the page so that other threads actually + * get the opportunity to free their frames, which means + * technically the result of bitmap_full may be incorrect. + * However the worst case is that we repeat all this and end up + * back here again. + */ + spin_unlock(&mm_ctx->bd_emupage_lock); + if (!wait_event_killable(mm_ctx->bd_emupage_queue, + !bitmap_full(mm_ctx->bd_emupage_allocmap, + emupage_frame_count))) + goto retry; - if (unlikely(err)) { - MIPS_FPU_EMU_INC_STATS(errors); - return SIGBUS; + /* Received a fatal signal - just give in */ + return BD_EMUFRAME_NONE; } - regs->cp0_epc = ((unsigned long) &fr->emul) | - get_isa16_mode(regs->cp0_epc); + /* Success! */ + pr_debug("allocate emuframe %d to %d\n", idx, current->pid); +out_unlock: + spin_unlock(&mm_ctx->bd_emupage_lock); + return idx; +} - flush_cache_sigtramp((unsigned long)&fr->emul); +static void free_emuframe(int idx, struct mm_struct *mm) +{ + mm_context_t *mm_ctx = &mm->context; - return 0; + spin_lock(&mm_ctx->bd_emupage_lock); + + pr_debug("free emuframe %d from %d\n", idx, current->pid); + bitmap_clear(mm_ctx->bd_emupage_allocmap, idx, 1); + + /* If some thread is waiting for a frame, now's its chance */ + wake_up(&mm_ctx->bd_emupage_queue); + + spin_unlock(&mm_ctx->bd_emupage_lock); +} + +static bool within_emuframe(struct pt_regs *regs) +{ + unsigned long base = (unsigned long)dsemul_page(); + + if (regs->cp0_epc < base) + return false; + if (regs->cp0_epc >= (base + PAGE_SIZE)) + return false; + + return true; +} + +bool dsemul_thread_cleanup(struct task_struct *tsk) +{ + int fr_idx; + + /* Clear any allocated frame, retrieving its index */ + fr_idx = atomic_xchg(&tsk->thread.bd_emu_frame, BD_EMUFRAME_NONE); + + /* If no frame was allocated, we're done */ + if (fr_idx == BD_EMUFRAME_NONE) + return false; + + task_lock(tsk); + + /* Free the frame that this thread had allocated */ + if (tsk->mm) + free_emuframe(fr_idx, tsk->mm); + + task_unlock(tsk); + return true; } -int do_dsemulret(struct pt_regs *xcp) +bool dsemul_thread_rollback(struct pt_regs *regs) { struct emuframe __user *fr; - unsigned long epc; - u32 insn, cookie; - int err = 0; - u16 instr[2]; + int fr_idx; - fr = (struct emuframe __user *) - (msk_isa16_mode(xcp->cp0_epc) - sizeof(mips_instruction)); + /* Do nothing if we're not executing from a frame */ + if (!within_emuframe(regs)) + return false; - /* - * If we can't even access the area, something is very wrong, but we'll - * leave that to the default handling - */ - if (!access_ok(VERIFY_READ, fr, sizeof(struct emuframe))) - return 0; + /* Find the frame being executed */ + fr_idx = atomic_read(¤t->thread.bd_emu_frame); + if (fr_idx == BD_EMUFRAME_NONE) + return false; + fr = &dsemul_page()[fr_idx]; /* - * Do some sanity checking on the stackframe: - * - * - Is the instruction pointed to by the EPC an BREAK_MATH? - * - Is the following memory word the BD_COOKIE? + * If the PC is at the emul instruction, roll back to the branch. If + * PC is at the badinst (break) instruction, we've already emulated the + * instruction so progress to the continue PC. If it's anything else + * then something is amiss & the user has branched into some other area + * of the emupage - we'll free the allocated frame anyway. */ - if (get_isa16_mode(xcp->cp0_epc)) { - err = __get_user(instr[0], (u16 __user *)(&fr->badinst)); - err |= __get_user(instr[1], (u16 __user *)((long)(&fr->badinst) + 2)); - insn = (instr[0] << 16) | instr[1]; + if (msk_isa16_mode(regs->cp0_epc) == (unsigned long)&fr->emul) + regs->cp0_epc = current->thread.bd_emu_branch_pc; + else if (msk_isa16_mode(regs->cp0_epc) == (unsigned long)&fr->badinst) + regs->cp0_epc = current->thread.bd_emu_cont_pc; + + atomic_set(¤t->thread.bd_emu_frame, BD_EMUFRAME_NONE); + free_emuframe(fr_idx, current->mm); + return true; +} + +void dsemul_mm_cleanup(struct mm_struct *mm) +{ + mm_context_t *mm_ctx = &mm->context; + + kfree(mm_ctx->bd_emupage_allocmap); +} + +int mips_dsemul(struct pt_regs *regs, mips_instruction ir, + unsigned long branch_pc, unsigned long cont_pc) +{ + int isa16 = get_isa16_mode(regs->cp0_epc); + mips_instruction break_math; + struct emuframe __user *fr; + int err, fr_idx; + + /* NOP is easy */ + if (ir == 0) + return -1; + + /* microMIPS instructions */ + if (isa16) { + union mips_instruction insn = { .word = ir }; + + /* NOP16 aka MOVE16 $0, $0 */ + if ((ir >> 16) == MM_NOP16) + return -1; + + /* ADDIUPC */ + if (insn.mm_a_format.opcode == mm_addiupc_op) { + unsigned int rs; + s32 v; + + rs = (((insn.mm_a_format.rs + 0xe) & 0xf) + 2); + v = regs->cp0_epc & ~3; + v += insn.mm_a_format.simmediate << 2; + regs->regs[rs] = (long)v; + return -1; + } + } + + pr_debug("dsemul 0x%08lx cont at 0x%08lx\n", regs->cp0_epc, cont_pc); + + /* Allocate a frame if we don't already have one */ + fr_idx = atomic_read(¤t->thread.bd_emu_frame); + if (fr_idx == BD_EMUFRAME_NONE) + fr_idx = alloc_emuframe(); + if (fr_idx == BD_EMUFRAME_NONE) + return SIGBUS; + fr = &dsemul_page()[fr_idx]; + + /* Retrieve the appropriately encoded break instruction */ + break_math = BREAK_MATH(isa16); + + /* Write the instructions to the frame */ + if (isa16) { + err = __put_user(ir >> 16, + (u16 __user *)(&fr->emul)); + err |= __put_user(ir & 0xffff, + (u16 __user *)((long)(&fr->emul) + 2)); + err |= __put_user(break_math >> 16, + (u16 __user *)(&fr->badinst)); + err |= __put_user(break_math & 0xffff, + (u16 __user *)((long)(&fr->badinst) + 2)); } else { - err = __get_user(insn, &fr->badinst); + err = __put_user(ir, &fr->emul); + err |= __put_user(break_math, &fr->badinst); } - err |= __get_user(cookie, &fr->cookie); - if (unlikely(err || (insn != BREAK_MATH) || (cookie != BD_COOKIE))) { + if (unlikely(err)) { MIPS_FPU_EMU_INC_STATS(errors); - return 0; + free_emuframe(fr_idx, current->mm); + return SIGBUS; } - /* - * At this point, we are satisfied that it's a BD emulation trap. Yes, - * a user might have deliberately put two malformed and useless - * instructions in a row in his program, in which case he's in for a - * nasty surprise - the next instruction will be treated as a - * continuation address! Alas, this seems to be the only way that we - * can handle signals, recursion, and longjmps() in the context of - * emulating the branch delay instruction. - */ + /* Record the PC of the branch, PC to continue from & frame index */ + current->thread.bd_emu_branch_pc = branch_pc; + current->thread.bd_emu_cont_pc = cont_pc; + atomic_set(¤t->thread.bd_emu_frame, fr_idx); - pr_debug("dsemulret\n"); + /* Change user register context to execute the frame */ + regs->cp0_epc = (unsigned long)&fr->emul | isa16; - if (__get_user(epc, &fr->epc)) { /* Saved EPC */ - /* This is not a good situation to be in */ - force_sig(SIGBUS, current); + /* Ensure the icache observes our newly written frame */ + flush_cache_sigtramp((unsigned long)&fr->emul); - return 0; + return 0; +} + +bool do_dsemulret(struct pt_regs *xcp) +{ + /* Cleanup the allocated frame, returning if there wasn't one */ + if (!dsemul_thread_cleanup(current)) { + MIPS_FPU_EMU_INC_STATS(errors); + return false; } /* Set EPC to return to post-branch instruction */ - xcp->cp0_epc = epc; + xcp->cp0_epc = current->thread.bd_emu_cont_pc; + pr_debug("dsemulret to 0x%08lx\n", xcp->cp0_epc); MIPS_FPU_EMU_INC_STATS(ds_emul); - return 1; + return true; } diff --git a/arch/mips/math-emu/ieee754.c b/arch/mips/math-emu/ieee754.c index 8e97acbbe22c..e16ae7b75dbb 100644 --- a/arch/mips/math-emu/ieee754.c +++ b/arch/mips/math-emu/ieee754.c @@ -59,7 +59,8 @@ const union ieee754dp __ieee754dp_spcvals[] = { DPCNST(1, 3, 0x4000000000000ULL), /* - 10.0 */ DPCNST(0, DP_EMAX + 1, 0x0000000000000ULL), /* + infinity */ DPCNST(1, DP_EMAX + 1, 0x0000000000000ULL), /* - infinity */ - DPCNST(0, DP_EMAX + 1, 0x7FFFFFFFFFFFFULL), /* + indef quiet Nan */ + DPCNST(0, DP_EMAX + 1, 0x7FFFFFFFFFFFFULL), /* + ind legacy qNaN */ + DPCNST(0, DP_EMAX + 1, 0x8000000000000ULL), /* + indef 2008 qNaN */ DPCNST(0, DP_EMAX, 0xFFFFFFFFFFFFFULL), /* + max */ DPCNST(1, DP_EMAX, 0xFFFFFFFFFFFFFULL), /* - max */ DPCNST(0, DP_EMIN, 0x0000000000000ULL), /* + min normal */ @@ -82,7 +83,8 @@ const union ieee754sp __ieee754sp_spcvals[] = { SPCNST(1, 3, 0x200000), /* - 10.0 */ SPCNST(0, SP_EMAX + 1, 0x000000), /* + infinity */ SPCNST(1, SP_EMAX + 1, 0x000000), /* - infinity */ - SPCNST(0, SP_EMAX + 1, 0x3FFFFF), /* + indef quiet Nan */ + SPCNST(0, SP_EMAX + 1, 0x3FFFFF), /* + indef legacy quiet NaN */ + SPCNST(0, SP_EMAX + 1, 0x400000), /* + indef 2008 quiet NaN */ SPCNST(0, SP_EMAX, 0x7FFFFF), /* + max normal */ SPCNST(1, SP_EMAX, 0x7FFFFF), /* - max normal */ SPCNST(0, SP_EMIN, 0x000000), /* + min normal */ diff --git a/arch/mips/math-emu/ieee754.h b/arch/mips/math-emu/ieee754.h index df94720714c7..e0eb7a965fdf 100644 --- a/arch/mips/math-emu/ieee754.h +++ b/arch/mips/math-emu/ieee754.h @@ -67,6 +67,7 @@ union ieee754sp ieee754sp_div(union ieee754sp x, union ieee754sp y); union ieee754sp ieee754sp_fint(int x); union ieee754sp ieee754sp_flong(s64 x); union ieee754sp ieee754sp_fdp(union ieee754dp x); +union ieee754sp ieee754sp_rint(union ieee754sp x); int ieee754sp_tint(union ieee754sp x); s64 ieee754sp_tlong(union ieee754sp x); @@ -101,6 +102,7 @@ union ieee754dp ieee754dp_neg(union ieee754dp x); union ieee754dp ieee754dp_fint(int x); union ieee754dp ieee754dp_flong(s64 x); union ieee754dp ieee754dp_fsp(union ieee754sp x); +union ieee754dp ieee754dp_rint(union ieee754dp x); int ieee754dp_tint(union ieee754dp x); s64 ieee754dp_tlong(union ieee754dp x); @@ -163,11 +165,12 @@ struct _ieee754_csr { }; #define ieee754_csr (*(struct _ieee754_csr *)(¤t->thread.fpu.fcr31)) -static inline unsigned ieee754_getrm(void) +static inline unsigned int ieee754_getrm(void) { return (ieee754_csr.rm); } -static inline unsigned ieee754_setrm(unsigned rm) + +static inline unsigned int ieee754_setrm(unsigned int rm) { return (ieee754_csr.rm = rm); } @@ -175,14 +178,14 @@ static inline unsigned ieee754_setrm(unsigned rm) /* * get current exceptions */ -static inline unsigned ieee754_getcx(void) +static inline unsigned int ieee754_getcx(void) { return (ieee754_csr.cx); } /* test for current exception condition */ -static inline int ieee754_cxtest(unsigned n) +static inline int ieee754_cxtest(unsigned int n) { return (ieee754_csr.cx & n); } @@ -190,21 +193,21 @@ static inline int ieee754_cxtest(unsigned n) /* * get sticky exceptions */ -static inline unsigned ieee754_getsx(void) +static inline unsigned int ieee754_getsx(void) { return (ieee754_csr.sx); } /* clear sticky conditions */ -static inline unsigned ieee754_clrsx(void) +static inline unsigned int ieee754_clrsx(void) { return (ieee754_csr.sx = 0); } /* test for sticky exception condition */ -static inline int ieee754_sxtest(unsigned n) +static inline int ieee754_sxtest(unsigned int n) { return (ieee754_csr.sx & n); } @@ -221,15 +224,16 @@ union ieee754dp ieee754dp_dump(char *s, union ieee754dp x); #define IEEE754_SPCVAL_NTEN 5 /* -10.0 */ #define IEEE754_SPCVAL_PINFINITY 6 /* +inf */ #define IEEE754_SPCVAL_NINFINITY 7 /* -inf */ -#define IEEE754_SPCVAL_INDEF 8 /* quiet NaN */ -#define IEEE754_SPCVAL_PMAX 9 /* +max norm */ -#define IEEE754_SPCVAL_NMAX 10 /* -max norm */ -#define IEEE754_SPCVAL_PMIN 11 /* +min norm */ -#define IEEE754_SPCVAL_NMIN 12 /* -min norm */ -#define IEEE754_SPCVAL_PMIND 13 /* +min denorm */ -#define IEEE754_SPCVAL_NMIND 14 /* -min denorm */ -#define IEEE754_SPCVAL_P1E31 15 /* + 1.0e31 */ -#define IEEE754_SPCVAL_P1E63 16 /* + 1.0e63 */ +#define IEEE754_SPCVAL_INDEF_LEG 8 /* legacy quiet NaN */ +#define IEEE754_SPCVAL_INDEF_2008 9 /* IEEE 754-2008 quiet NaN */ +#define IEEE754_SPCVAL_PMAX 10 /* +max norm */ +#define IEEE754_SPCVAL_NMAX 11 /* -max norm */ +#define IEEE754_SPCVAL_PMIN 12 /* +min norm */ +#define IEEE754_SPCVAL_NMIN 13 /* -min norm */ +#define IEEE754_SPCVAL_PMIND 14 /* +min denorm */ +#define IEEE754_SPCVAL_NMIND 15 /* -min denorm */ +#define IEEE754_SPCVAL_P1E31 16 /* + 1.0e31 */ +#define IEEE754_SPCVAL_P1E63 17 /* + 1.0e63 */ extern const union ieee754dp __ieee754dp_spcvals[]; extern const union ieee754sp __ieee754sp_spcvals[]; @@ -243,7 +247,8 @@ extern const union ieee754sp __ieee754sp_spcvals[]; #define ieee754dp_zero(sn) (ieee754dp_spcvals[IEEE754_SPCVAL_PZERO+(sn)]) #define ieee754dp_one(sn) (ieee754dp_spcvals[IEEE754_SPCVAL_PONE+(sn)]) #define ieee754dp_ten(sn) (ieee754dp_spcvals[IEEE754_SPCVAL_PTEN+(sn)]) -#define ieee754dp_indef() (ieee754dp_spcvals[IEEE754_SPCVAL_INDEF]) +#define ieee754dp_indef() (ieee754dp_spcvals[IEEE754_SPCVAL_INDEF_LEG + \ + ieee754_csr.nan2008]) #define ieee754dp_max(sn) (ieee754dp_spcvals[IEEE754_SPCVAL_PMAX+(sn)]) #define ieee754dp_min(sn) (ieee754dp_spcvals[IEEE754_SPCVAL_PMIN+(sn)]) #define ieee754dp_mind(sn) (ieee754dp_spcvals[IEEE754_SPCVAL_PMIND+(sn)]) @@ -254,7 +259,8 @@ extern const union ieee754sp __ieee754sp_spcvals[]; #define ieee754sp_zero(sn) (ieee754sp_spcvals[IEEE754_SPCVAL_PZERO+(sn)]) #define ieee754sp_one(sn) (ieee754sp_spcvals[IEEE754_SPCVAL_PONE+(sn)]) #define ieee754sp_ten(sn) (ieee754sp_spcvals[IEEE754_SPCVAL_PTEN+(sn)]) -#define ieee754sp_indef() (ieee754sp_spcvals[IEEE754_SPCVAL_INDEF]) +#define ieee754sp_indef() (ieee754sp_spcvals[IEEE754_SPCVAL_INDEF_LEG + \ + ieee754_csr.nan2008]) #define ieee754sp_max(sn) (ieee754sp_spcvals[IEEE754_SPCVAL_PMAX+(sn)]) #define ieee754sp_min(sn) (ieee754sp_spcvals[IEEE754_SPCVAL_PMIN+(sn)]) #define ieee754sp_mind(sn) (ieee754sp_spcvals[IEEE754_SPCVAL_PMIND+(sn)]) @@ -266,12 +272,25 @@ extern const union ieee754sp __ieee754sp_spcvals[]; */ static inline int ieee754si_indef(void) { - return INT_MAX; + return ieee754_csr.nan2008 ? 0 : INT_MAX; } static inline s64 ieee754di_indef(void) { - return S64_MAX; + return ieee754_csr.nan2008 ? 0 : S64_MAX; +} + +/* + * Overflow integer value + */ +static inline int ieee754si_overflow(int xs) +{ + return ieee754_csr.nan2008 && xs ? INT_MIN : INT_MAX; +} + +static inline s64 ieee754di_overflow(int xs) +{ + return ieee754_csr.nan2008 && xs ? S64_MIN : S64_MAX; } /* result types for xctx.rt */ diff --git a/arch/mips/math-emu/ieee754dp.c b/arch/mips/math-emu/ieee754dp.c index 522d843f2ffd..465a0342ed4c 100644 --- a/arch/mips/math-emu/ieee754dp.c +++ b/arch/mips/math-emu/ieee754dp.c @@ -37,8 +37,11 @@ static inline int ieee754dp_isnan(union ieee754dp x) static inline int ieee754dp_issnan(union ieee754dp x) { + int qbit; + assert(ieee754dp_isnan(x)); - return (DPMANT(x) & DP_MBIT(DP_FBITS - 1)) == DP_MBIT(DP_FBITS - 1); + qbit = (DPMANT(x) & DP_MBIT(DP_FBITS - 1)) == DP_MBIT(DP_FBITS - 1); + return ieee754_csr.nan2008 ^ qbit; } @@ -51,7 +54,15 @@ union ieee754dp __cold ieee754dp_nanxcpt(union ieee754dp r) assert(ieee754dp_issnan(r)); ieee754_setcx(IEEE754_INVALID_OPERATION); - return ieee754dp_indef(); + if (ieee754_csr.nan2008) { + DPMANT(r) |= DP_MBIT(DP_FBITS - 1); + } else { + DPMANT(r) &= ~DP_MBIT(DP_FBITS - 1); + if (!ieee754dp_isnan(r)) + DPMANT(r) |= DP_MBIT(DP_FBITS - 2); + } + + return r; } static u64 ieee754dp_get_rounding(int sn, u64 xm) @@ -89,7 +100,7 @@ union ieee754dp ieee754dp_format(int sn, int xe, u64 xm) { assert(xm); /* we don't gen exact zeros (probably should) */ - assert((xm >> (DP_FBITS + 1 + 3)) == 0); /* no execess */ + assert((xm >> (DP_FBITS + 1 + 3)) == 0); /* no excess */ assert(xm & (DP_HIDDEN_BIT << 3)); if (xe < DP_EMIN) { @@ -157,7 +168,7 @@ union ieee754dp ieee754dp_format(int sn, int xe, u64 xm) /* strip grs bits */ xm >>= 3; - assert((xm >> (DP_FBITS + 1)) == 0); /* no execess */ + assert((xm >> (DP_FBITS + 1)) == 0); /* no excess */ assert(xe >= DP_EMIN); if (xe > DP_EMAX) { @@ -190,7 +201,7 @@ union ieee754dp ieee754dp_format(int sn, int xe, u64 xm) ieee754_setcx(IEEE754_UNDERFLOW); return builddp(sn, DP_EMIN - 1 + DP_EBIAS, xm); } else { - assert((xm >> (DP_FBITS + 1)) == 0); /* no execess */ + assert((xm >> (DP_FBITS + 1)) == 0); /* no excess */ assert(xm & DP_HIDDEN_BIT); return builddp(sn, xe + DP_EBIAS, xm & ~DP_HIDDEN_BIT); diff --git a/arch/mips/math-emu/ieee754dp.h b/arch/mips/math-emu/ieee754dp.h index e2babd98fee3..a56707b75282 100644 --- a/arch/mips/math-emu/ieee754dp.h +++ b/arch/mips/math-emu/ieee754dp.h @@ -55,11 +55,15 @@ static inline int ieee754dp_finite(union ieee754dp x) #define XDPSRS1(v) \ (((v) >> 1) | ((v) & 1)) +/* 32bit * 32bit => 64bit unsigned integer multiplication */ +#define DPXMULT(x, y) ((u64)(x) * (u64)y) + /* convert denormal to normalized with extended exponent */ #define DPDNORMx(m,e) \ while ((m >> DP_FBITS) == 0) { m <<= 1; e--; } #define DPDNORMX DPDNORMx(xm, xe) #define DPDNORMY DPDNORMx(ym, ye) +#define DPDNORMZ DPDNORMx(zm, ze) static inline union ieee754dp builddp(int s, int bx, u64 m) { diff --git a/arch/mips/math-emu/ieee754int.h b/arch/mips/math-emu/ieee754int.h index 6383e2c5c1ad..06ac0e2ac7ac 100644 --- a/arch/mips/math-emu/ieee754int.h +++ b/arch/mips/math-emu/ieee754int.h @@ -26,6 +26,10 @@ #define CLPAIR(x, y) ((x)*6+(y)) +enum maddf_flags { + MADDF_NEGATE_PRODUCT = 1 << 0, +}; + static inline void ieee754_clearcx(void) { ieee754_csr.cx = 0; @@ -50,10 +54,13 @@ static inline int ieee754_class_nan(int xc) } #define COMPXSP \ - unsigned xm; int xe; int xs __maybe_unused; int xc + unsigned int xm; int xe; int xs __maybe_unused; int xc #define COMPYSP \ - unsigned ym; int ye; int ys; int yc + unsigned int ym; int ye; int ys; int yc + +#define COMPZSP \ + unsigned int zm; int ze; int zs; int zc #define EXPLODESP(v, vc, vs, ve, vm) \ { \ @@ -63,10 +70,10 @@ static inline int ieee754_class_nan(int xc) if (ve == SP_EMAX+1+SP_EBIAS) { \ if (vm == 0) \ vc = IEEE754_CLASS_INF; \ - else if (vm & SP_MBIT(SP_FBITS-1)) \ - vc = IEEE754_CLASS_SNAN; \ - else \ + else if (ieee754_csr.nan2008 ^ !(vm & SP_MBIT(SP_FBITS - 1))) \ vc = IEEE754_CLASS_QNAN; \ + else \ + vc = IEEE754_CLASS_SNAN; \ } else if (ve == SP_EMIN-1+SP_EBIAS) { \ if (vm) { \ ve = SP_EMIN; \ @@ -81,6 +88,7 @@ static inline int ieee754_class_nan(int xc) } #define EXPLODEXSP EXPLODESP(x, xc, xs, xe, xm) #define EXPLODEYSP EXPLODESP(y, yc, ys, ye, ym) +#define EXPLODEZSP EXPLODESP(z, zc, zs, ze, zm) #define COMPXDP \ @@ -89,6 +97,9 @@ static inline int ieee754_class_nan(int xc) #define COMPYDP \ u64 ym; int ye; int ys; int yc +#define COMPZDP \ + u64 zm; int ze; int zs; int zc + #define EXPLODEDP(v, vc, vs, ve, vm) \ { \ vm = DPMANT(v); \ @@ -97,10 +108,10 @@ static inline int ieee754_class_nan(int xc) if (ve == DP_EMAX+1+DP_EBIAS) { \ if (vm == 0) \ vc = IEEE754_CLASS_INF; \ - else if (vm & DP_MBIT(DP_FBITS-1)) \ - vc = IEEE754_CLASS_SNAN; \ - else \ + else if (ieee754_csr.nan2008 ^ !(vm & DP_MBIT(DP_FBITS - 1))) \ vc = IEEE754_CLASS_QNAN; \ + else \ + vc = IEEE754_CLASS_SNAN; \ } else if (ve == DP_EMIN-1+DP_EBIAS) { \ if (vm) { \ ve = DP_EMIN; \ @@ -115,6 +126,7 @@ static inline int ieee754_class_nan(int xc) } #define EXPLODEXDP EXPLODEDP(x, xc, xs, xe, xm) #define EXPLODEYDP EXPLODEDP(y, yc, ys, ye, ym) +#define EXPLODEZDP EXPLODEDP(z, zc, zs, ze, zm) #define FLUSHDP(v, vc, vs, ve, vm) \ if (vc==IEEE754_CLASS_DNORM) { \ @@ -140,7 +152,9 @@ static inline int ieee754_class_nan(int xc) #define FLUSHXDP FLUSHDP(x, xc, xs, xe, xm) #define FLUSHYDP FLUSHDP(y, yc, ys, ye, ym) +#define FLUSHZDP FLUSHDP(z, zc, zs, ze, zm) #define FLUSHXSP FLUSHSP(x, xc, xs, xe, xm) #define FLUSHYSP FLUSHSP(y, yc, ys, ye, ym) +#define FLUSHZSP FLUSHSP(z, zc, zs, ze, zm) #endif /* __IEEE754INT_H */ diff --git a/arch/mips/math-emu/ieee754sp.c b/arch/mips/math-emu/ieee754sp.c index ca8e35e33bf7..8423e4c5e415 100644 --- a/arch/mips/math-emu/ieee754sp.c +++ b/arch/mips/math-emu/ieee754sp.c @@ -37,8 +37,11 @@ static inline int ieee754sp_isnan(union ieee754sp x) static inline int ieee754sp_issnan(union ieee754sp x) { + int qbit; + assert(ieee754sp_isnan(x)); - return SPMANT(x) & SP_MBIT(SP_FBITS - 1); + qbit = (SPMANT(x) & SP_MBIT(SP_FBITS - 1)) == SP_MBIT(SP_FBITS - 1); + return ieee754_csr.nan2008 ^ qbit; } @@ -51,10 +54,18 @@ union ieee754sp __cold ieee754sp_nanxcpt(union ieee754sp r) assert(ieee754sp_issnan(r)); ieee754_setcx(IEEE754_INVALID_OPERATION); - return ieee754sp_indef(); + if (ieee754_csr.nan2008) { + SPMANT(r) |= SP_MBIT(SP_FBITS - 1); + } else { + SPMANT(r) &= ~SP_MBIT(SP_FBITS - 1); + if (!ieee754sp_isnan(r)) + SPMANT(r) |= SP_MBIT(SP_FBITS - 2); + } + + return r; } -static unsigned ieee754sp_get_rounding(int sn, unsigned xm) +static unsigned int ieee754sp_get_rounding(int sn, unsigned int xm) { /* inexact must round of 3 bits */ @@ -85,11 +96,11 @@ static unsigned ieee754sp_get_rounding(int sn, unsigned xm) * xe is an unbiased exponent * xm is 3bit extended precision value. */ -union ieee754sp ieee754sp_format(int sn, int xe, unsigned xm) +union ieee754sp ieee754sp_format(int sn, int xe, unsigned int xm) { assert(xm); /* we don't gen exact zeros (probably should) */ - assert((xm >> (SP_FBITS + 1 + 3)) == 0); /* no execess */ + assert((xm >> (SP_FBITS + 1 + 3)) == 0); /* no excess */ assert(xm & (SP_HIDDEN_BIT << 3)); if (xe < SP_EMIN) { @@ -130,7 +141,8 @@ union ieee754sp ieee754sp_format(int sn, int xe, unsigned xm) } else { /* sticky right shift es bits */ - SPXSRSXn(es); + xm = XSPSRS(xm, es); + xe += es; assert((xm & (SP_HIDDEN_BIT << 3)) == 0); assert(xe == SP_EMIN); } @@ -155,7 +167,7 @@ union ieee754sp ieee754sp_format(int sn, int xe, unsigned xm) /* strip grs bits */ xm >>= 3; - assert((xm >> (SP_FBITS + 1)) == 0); /* no execess */ + assert((xm >> (SP_FBITS + 1)) == 0); /* no excess */ assert(xe >= SP_EMIN); if (xe > SP_EMAX) { @@ -188,7 +200,7 @@ union ieee754sp ieee754sp_format(int sn, int xe, unsigned xm) ieee754_setcx(IEEE754_UNDERFLOW); return buildsp(sn, SP_EMIN - 1 + SP_EBIAS, xm); } else { - assert((xm >> (SP_FBITS + 1)) == 0); /* no execess */ + assert((xm >> (SP_FBITS + 1)) == 0); /* no excess */ assert(xm & SP_HIDDEN_BIT); return buildsp(sn, xe + SP_EBIAS, xm & ~SP_HIDDEN_BIT); diff --git a/arch/mips/math-emu/ieee754sp.h b/arch/mips/math-emu/ieee754sp.h index 374a3f00a589..8c5a63804873 100644 --- a/arch/mips/math-emu/ieee754sp.h +++ b/arch/mips/math-emu/ieee754sp.h @@ -45,28 +45,31 @@ static inline int ieee754sp_finite(union ieee754sp x) return SPBEXP(x) != SP_EMAX + 1 + SP_EBIAS; } +/* 64 bit right shift with rounding */ +#define XSPSRS64(v, rs) \ + (((rs) >= 64) ? ((v) != 0) : ((v) >> (rs)) | ((v) << (64-(rs)) != 0)) + /* 3bit extended single precision sticky right shift */ -#define SPXSRSXn(rs) \ - (xe += rs, \ - xm = (rs > (SP_FBITS+3))?1:((xm) >> (rs)) | ((xm) << (32-(rs)) != 0)) +#define XSPSRS(v, rs) \ + ((rs > (SP_FBITS+3))?1:((v) >> (rs)) | ((v) << (32-(rs)) != 0)) -#define SPXSRSX1() \ - (xe++, (xm = (xm >> 1) | (xm & 1))) +#define XSPSRS1(m) \ + ((m >> 1) | (m & 1)) -#define SPXSRSYn(rs) \ - (ye+=rs, \ - ym = (rs > (SP_FBITS+3))?1:((ym) >> (rs)) | ((ym) << (32-(rs)) != 0)) +#define SPXSRSX1() \ + (xe++, (xm = XSPSRS1(xm))) #define SPXSRSY1() \ - (ye++, (ym = (ym >> 1) | (ym & 1))) + (ye++, (ym = XSPSRS1(ym))) /* convert denormal to normalized with extended exponent */ #define SPDNORMx(m,e) \ while ((m >> SP_FBITS) == 0) { m <<= 1; e--; } #define SPDNORMX SPDNORMx(xm, xe) #define SPDNORMY SPDNORMx(ym, ye) +#define SPDNORMZ SPDNORMx(zm, ze) -static inline union ieee754sp buildsp(int s, int bx, unsigned m) +static inline union ieee754sp buildsp(int s, int bx, unsigned int m) { union ieee754sp r; diff --git a/arch/mips/math-emu/me-debugfs.c b/arch/mips/math-emu/me-debugfs.c index be650ed7db59..8c0ec154aecc 100644 --- a/arch/mips/math-emu/me-debugfs.c +++ b/arch/mips/math-emu/me-debugfs.c @@ -28,14 +28,190 @@ static int fpuemu_stat_get(void *data, u64 *val) } DEFINE_SIMPLE_ATTRIBUTE(fops_fpuemu_stat, fpuemu_stat_get, NULL, "%llu\n"); +/* + * Used to obtain names for a debugfs instruction counter, given field name + * in fpuemustats structure. For example, for input "cmp_sueq_d", the output + * would be "cmp.sueq.d". This is needed since dots are not allowed to be + * used in structure field names, and are, on the other hand, desired to be + * used in debugfs item names to be clearly associated to corresponding + * MIPS FPU instructions. + */ +static void adjust_instruction_counter_name(char *out_name, char *in_name) +{ + int i = 0; + + strcpy(out_name, in_name); + while (in_name[i] != '\0') { + if (out_name[i] == '_') + out_name[i] = '.'; + i++; + } +} + +static int fpuemustats_clear_show(struct seq_file *s, void *unused) +{ + __this_cpu_write((fpuemustats).emulated, 0); + __this_cpu_write((fpuemustats).loads, 0); + __this_cpu_write((fpuemustats).stores, 0); + __this_cpu_write((fpuemustats).branches, 0); + __this_cpu_write((fpuemustats).cp1ops, 0); + __this_cpu_write((fpuemustats).cp1xops, 0); + __this_cpu_write((fpuemustats).errors, 0); + __this_cpu_write((fpuemustats).ieee754_inexact, 0); + __this_cpu_write((fpuemustats).ieee754_underflow, 0); + __this_cpu_write((fpuemustats).ieee754_overflow, 0); + __this_cpu_write((fpuemustats).ieee754_zerodiv, 0); + __this_cpu_write((fpuemustats).ieee754_invalidop, 0); + __this_cpu_write((fpuemustats).ds_emul, 0); + + __this_cpu_write((fpuemustats).abs_s, 0); + __this_cpu_write((fpuemustats).abs_d, 0); + __this_cpu_write((fpuemustats).add_s, 0); + __this_cpu_write((fpuemustats).add_d, 0); + __this_cpu_write((fpuemustats).bc1eqz, 0); + __this_cpu_write((fpuemustats).bc1nez, 0); + __this_cpu_write((fpuemustats).ceil_w_s, 0); + __this_cpu_write((fpuemustats).ceil_w_d, 0); + __this_cpu_write((fpuemustats).ceil_l_s, 0); + __this_cpu_write((fpuemustats).ceil_l_d, 0); + __this_cpu_write((fpuemustats).class_s, 0); + __this_cpu_write((fpuemustats).class_d, 0); + __this_cpu_write((fpuemustats).cmp_af_s, 0); + __this_cpu_write((fpuemustats).cmp_af_d, 0); + __this_cpu_write((fpuemustats).cmp_eq_s, 0); + __this_cpu_write((fpuemustats).cmp_eq_d, 0); + __this_cpu_write((fpuemustats).cmp_le_s, 0); + __this_cpu_write((fpuemustats).cmp_le_d, 0); + __this_cpu_write((fpuemustats).cmp_lt_s, 0); + __this_cpu_write((fpuemustats).cmp_lt_d, 0); + __this_cpu_write((fpuemustats).cmp_ne_s, 0); + __this_cpu_write((fpuemustats).cmp_ne_d, 0); + __this_cpu_write((fpuemustats).cmp_or_s, 0); + __this_cpu_write((fpuemustats).cmp_or_d, 0); + __this_cpu_write((fpuemustats).cmp_ueq_s, 0); + __this_cpu_write((fpuemustats).cmp_ueq_d, 0); + __this_cpu_write((fpuemustats).cmp_ule_s, 0); + __this_cpu_write((fpuemustats).cmp_ule_d, 0); + __this_cpu_write((fpuemustats).cmp_ult_s, 0); + __this_cpu_write((fpuemustats).cmp_ult_d, 0); + __this_cpu_write((fpuemustats).cmp_un_s, 0); + __this_cpu_write((fpuemustats).cmp_un_d, 0); + __this_cpu_write((fpuemustats).cmp_une_s, 0); + __this_cpu_write((fpuemustats).cmp_une_d, 0); + __this_cpu_write((fpuemustats).cmp_saf_s, 0); + __this_cpu_write((fpuemustats).cmp_saf_d, 0); + __this_cpu_write((fpuemustats).cmp_seq_s, 0); + __this_cpu_write((fpuemustats).cmp_seq_d, 0); + __this_cpu_write((fpuemustats).cmp_sle_s, 0); + __this_cpu_write((fpuemustats).cmp_sle_d, 0); + __this_cpu_write((fpuemustats).cmp_slt_s, 0); + __this_cpu_write((fpuemustats).cmp_slt_d, 0); + __this_cpu_write((fpuemustats).cmp_sne_s, 0); + __this_cpu_write((fpuemustats).cmp_sne_d, 0); + __this_cpu_write((fpuemustats).cmp_sor_s, 0); + __this_cpu_write((fpuemustats).cmp_sor_d, 0); + __this_cpu_write((fpuemustats).cmp_sueq_s, 0); + __this_cpu_write((fpuemustats).cmp_sueq_d, 0); + __this_cpu_write((fpuemustats).cmp_sule_s, 0); + __this_cpu_write((fpuemustats).cmp_sule_d, 0); + __this_cpu_write((fpuemustats).cmp_sult_s, 0); + __this_cpu_write((fpuemustats).cmp_sult_d, 0); + __this_cpu_write((fpuemustats).cmp_sun_s, 0); + __this_cpu_write((fpuemustats).cmp_sun_d, 0); + __this_cpu_write((fpuemustats).cmp_sune_s, 0); + __this_cpu_write((fpuemustats).cmp_sune_d, 0); + __this_cpu_write((fpuemustats).cvt_d_l, 0); + __this_cpu_write((fpuemustats).cvt_d_s, 0); + __this_cpu_write((fpuemustats).cvt_d_w, 0); + __this_cpu_write((fpuemustats).cvt_l_s, 0); + __this_cpu_write((fpuemustats).cvt_l_d, 0); + __this_cpu_write((fpuemustats).cvt_s_d, 0); + __this_cpu_write((fpuemustats).cvt_s_l, 0); + __this_cpu_write((fpuemustats).cvt_s_w, 0); + __this_cpu_write((fpuemustats).cvt_w_s, 0); + __this_cpu_write((fpuemustats).cvt_w_d, 0); + __this_cpu_write((fpuemustats).div_s, 0); + __this_cpu_write((fpuemustats).div_d, 0); + __this_cpu_write((fpuemustats).floor_w_s, 0); + __this_cpu_write((fpuemustats).floor_w_d, 0); + __this_cpu_write((fpuemustats).floor_l_s, 0); + __this_cpu_write((fpuemustats).floor_l_d, 0); + __this_cpu_write((fpuemustats).maddf_s, 0); + __this_cpu_write((fpuemustats).maddf_d, 0); + __this_cpu_write((fpuemustats).max_s, 0); + __this_cpu_write((fpuemustats).max_d, 0); + __this_cpu_write((fpuemustats).maxa_s, 0); + __this_cpu_write((fpuemustats).maxa_d, 0); + __this_cpu_write((fpuemustats).min_s, 0); + __this_cpu_write((fpuemustats).min_d, 0); + __this_cpu_write((fpuemustats).mina_s, 0); + __this_cpu_write((fpuemustats).mina_d, 0); + __this_cpu_write((fpuemustats).mov_s, 0); + __this_cpu_write((fpuemustats).mov_d, 0); + __this_cpu_write((fpuemustats).msubf_s, 0); + __this_cpu_write((fpuemustats).msubf_d, 0); + __this_cpu_write((fpuemustats).mul_s, 0); + __this_cpu_write((fpuemustats).mul_d, 0); + __this_cpu_write((fpuemustats).neg_s, 0); + __this_cpu_write((fpuemustats).neg_d, 0); + __this_cpu_write((fpuemustats).recip_s, 0); + __this_cpu_write((fpuemustats).recip_d, 0); + __this_cpu_write((fpuemustats).rint_s, 0); + __this_cpu_write((fpuemustats).rint_d, 0); + __this_cpu_write((fpuemustats).round_w_s, 0); + __this_cpu_write((fpuemustats).round_w_d, 0); + __this_cpu_write((fpuemustats).round_l_s, 0); + __this_cpu_write((fpuemustats).round_l_d, 0); + __this_cpu_write((fpuemustats).rsqrt_s, 0); + __this_cpu_write((fpuemustats).rsqrt_d, 0); + __this_cpu_write((fpuemustats).sel_s, 0); + __this_cpu_write((fpuemustats).sel_d, 0); + __this_cpu_write((fpuemustats).seleqz_s, 0); + __this_cpu_write((fpuemustats).seleqz_d, 0); + __this_cpu_write((fpuemustats).selnez_s, 0); + __this_cpu_write((fpuemustats).selnez_d, 0); + __this_cpu_write((fpuemustats).sqrt_s, 0); + __this_cpu_write((fpuemustats).sqrt_d, 0); + __this_cpu_write((fpuemustats).sub_s, 0); + __this_cpu_write((fpuemustats).sub_d, 0); + __this_cpu_write((fpuemustats).trunc_w_s, 0); + __this_cpu_write((fpuemustats).trunc_w_d, 0); + __this_cpu_write((fpuemustats).trunc_l_s, 0); + __this_cpu_write((fpuemustats).trunc_l_d, 0); + + return 0; +} + +static int fpuemustats_clear_open(struct inode *inode, struct file *file) +{ + return single_open(file, fpuemustats_clear_show, inode->i_private); +} + +static const struct file_operations fpuemustats_clear_fops = { + .open = fpuemustats_clear_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + static int __init debugfs_fpuemu(void) { - struct dentry *d, *dir; + struct dentry *fpuemu_debugfs_base_dir; + struct dentry *fpuemu_debugfs_inst_dir; + struct dentry *d, *reset_file; if (!mips_debugfs_dir) return -ENODEV; - dir = debugfs_create_dir("fpuemustats", mips_debugfs_dir); - if (!dir) + + fpuemu_debugfs_base_dir = debugfs_create_dir("fpuemustats", + mips_debugfs_dir); + if (!fpuemu_debugfs_base_dir) + return -ENOMEM; + + reset_file = debugfs_create_file("fpuemustats_clear", 0444, + mips_debugfs_dir, NULL, + &fpuemustats_clear_fops); + if (!reset_file) return -ENOMEM; #define FPU_EMU_STAT_OFFSET(m) \ @@ -43,7 +219,7 @@ static int __init debugfs_fpuemu(void) #define FPU_STAT_CREATE(m) \ do { \ - d = debugfs_create_file(#m , S_IRUGO, dir, \ + d = debugfs_create_file(#m, 0444, fpuemu_debugfs_base_dir, \ (void *)FPU_EMU_STAT_OFFSET(m), \ &fops_fpuemu_stat); \ if (!d) \ @@ -53,6 +229,7 @@ do { \ FPU_STAT_CREATE(emulated); FPU_STAT_CREATE(loads); FPU_STAT_CREATE(stores); + FPU_STAT_CREATE(branches); FPU_STAT_CREATE(cp1ops); FPU_STAT_CREATE(cp1xops); FPU_STAT_CREATE(errors); @@ -63,6 +240,139 @@ do { \ FPU_STAT_CREATE(ieee754_invalidop); FPU_STAT_CREATE(ds_emul); + fpuemu_debugfs_inst_dir = debugfs_create_dir("instructions", + fpuemu_debugfs_base_dir); + if (!fpuemu_debugfs_inst_dir) + return -ENOMEM; + +#define FPU_STAT_CREATE_EX(m) \ +do { \ + char name[32]; \ + \ + adjust_instruction_counter_name(name, #m); \ + \ + d = debugfs_create_file(name, 0444, fpuemu_debugfs_inst_dir, \ + (void *)FPU_EMU_STAT_OFFSET(m), \ + &fops_fpuemu_stat); \ + if (!d) \ + return -ENOMEM; \ +} while (0) + + FPU_STAT_CREATE_EX(abs_s); + FPU_STAT_CREATE_EX(abs_d); + FPU_STAT_CREATE_EX(add_s); + FPU_STAT_CREATE_EX(add_d); + FPU_STAT_CREATE_EX(bc1eqz); + FPU_STAT_CREATE_EX(bc1nez); + FPU_STAT_CREATE_EX(ceil_w_s); + FPU_STAT_CREATE_EX(ceil_w_d); + FPU_STAT_CREATE_EX(ceil_l_s); + FPU_STAT_CREATE_EX(ceil_l_d); + FPU_STAT_CREATE_EX(class_s); + FPU_STAT_CREATE_EX(class_d); + FPU_STAT_CREATE_EX(cmp_af_s); + FPU_STAT_CREATE_EX(cmp_af_d); + FPU_STAT_CREATE_EX(cmp_eq_s); + FPU_STAT_CREATE_EX(cmp_eq_d); + FPU_STAT_CREATE_EX(cmp_le_s); + FPU_STAT_CREATE_EX(cmp_le_d); + FPU_STAT_CREATE_EX(cmp_lt_s); + FPU_STAT_CREATE_EX(cmp_lt_d); + FPU_STAT_CREATE_EX(cmp_ne_s); + FPU_STAT_CREATE_EX(cmp_ne_d); + FPU_STAT_CREATE_EX(cmp_or_s); + FPU_STAT_CREATE_EX(cmp_or_d); + FPU_STAT_CREATE_EX(cmp_ueq_s); + FPU_STAT_CREATE_EX(cmp_ueq_d); + FPU_STAT_CREATE_EX(cmp_ule_s); + FPU_STAT_CREATE_EX(cmp_ule_d); + FPU_STAT_CREATE_EX(cmp_ult_s); + FPU_STAT_CREATE_EX(cmp_ult_d); + FPU_STAT_CREATE_EX(cmp_un_s); + FPU_STAT_CREATE_EX(cmp_un_d); + FPU_STAT_CREATE_EX(cmp_une_s); + FPU_STAT_CREATE_EX(cmp_une_d); + FPU_STAT_CREATE_EX(cmp_saf_s); + FPU_STAT_CREATE_EX(cmp_saf_d); + FPU_STAT_CREATE_EX(cmp_seq_s); + FPU_STAT_CREATE_EX(cmp_seq_d); + FPU_STAT_CREATE_EX(cmp_sle_s); + FPU_STAT_CREATE_EX(cmp_sle_d); + FPU_STAT_CREATE_EX(cmp_slt_s); + FPU_STAT_CREATE_EX(cmp_slt_d); + FPU_STAT_CREATE_EX(cmp_sne_s); + FPU_STAT_CREATE_EX(cmp_sne_d); + FPU_STAT_CREATE_EX(cmp_sor_s); + FPU_STAT_CREATE_EX(cmp_sor_d); + FPU_STAT_CREATE_EX(cmp_sueq_s); + FPU_STAT_CREATE_EX(cmp_sueq_d); + FPU_STAT_CREATE_EX(cmp_sule_s); + FPU_STAT_CREATE_EX(cmp_sule_d); + FPU_STAT_CREATE_EX(cmp_sult_s); + FPU_STAT_CREATE_EX(cmp_sult_d); + FPU_STAT_CREATE_EX(cmp_sun_s); + FPU_STAT_CREATE_EX(cmp_sun_d); + FPU_STAT_CREATE_EX(cmp_sune_s); + FPU_STAT_CREATE_EX(cmp_sune_d); + FPU_STAT_CREATE_EX(cvt_d_l); + FPU_STAT_CREATE_EX(cvt_d_s); + FPU_STAT_CREATE_EX(cvt_d_w); + FPU_STAT_CREATE_EX(cvt_l_s); + FPU_STAT_CREATE_EX(cvt_l_d); + FPU_STAT_CREATE_EX(cvt_s_d); + FPU_STAT_CREATE_EX(cvt_s_l); + FPU_STAT_CREATE_EX(cvt_s_w); + FPU_STAT_CREATE_EX(cvt_w_s); + FPU_STAT_CREATE_EX(cvt_w_d); + FPU_STAT_CREATE_EX(div_s); + FPU_STAT_CREATE_EX(div_d); + FPU_STAT_CREATE_EX(floor_w_s); + FPU_STAT_CREATE_EX(floor_w_d); + FPU_STAT_CREATE_EX(floor_l_s); + FPU_STAT_CREATE_EX(floor_l_d); + FPU_STAT_CREATE_EX(maddf_s); + FPU_STAT_CREATE_EX(maddf_d); + FPU_STAT_CREATE_EX(max_s); + FPU_STAT_CREATE_EX(max_d); + FPU_STAT_CREATE_EX(maxa_s); + FPU_STAT_CREATE_EX(maxa_d); + FPU_STAT_CREATE_EX(min_s); + FPU_STAT_CREATE_EX(min_d); + FPU_STAT_CREATE_EX(mina_s); + FPU_STAT_CREATE_EX(mina_d); + FPU_STAT_CREATE_EX(mov_s); + FPU_STAT_CREATE_EX(mov_d); + FPU_STAT_CREATE_EX(msubf_s); + FPU_STAT_CREATE_EX(msubf_d); + FPU_STAT_CREATE_EX(mul_s); + FPU_STAT_CREATE_EX(mul_d); + FPU_STAT_CREATE_EX(neg_s); + FPU_STAT_CREATE_EX(neg_d); + FPU_STAT_CREATE_EX(recip_s); + FPU_STAT_CREATE_EX(recip_d); + FPU_STAT_CREATE_EX(rint_s); + FPU_STAT_CREATE_EX(rint_d); + FPU_STAT_CREATE_EX(round_w_s); + FPU_STAT_CREATE_EX(round_w_d); + FPU_STAT_CREATE_EX(round_l_s); + FPU_STAT_CREATE_EX(round_l_d); + FPU_STAT_CREATE_EX(rsqrt_s); + FPU_STAT_CREATE_EX(rsqrt_d); + FPU_STAT_CREATE_EX(sel_s); + FPU_STAT_CREATE_EX(sel_d); + FPU_STAT_CREATE_EX(seleqz_s); + FPU_STAT_CREATE_EX(seleqz_d); + FPU_STAT_CREATE_EX(selnez_s); + FPU_STAT_CREATE_EX(selnez_d); + FPU_STAT_CREATE_EX(sqrt_s); + FPU_STAT_CREATE_EX(sqrt_d); + FPU_STAT_CREATE_EX(sub_s); + FPU_STAT_CREATE_EX(sub_d); + FPU_STAT_CREATE_EX(trunc_w_s); + FPU_STAT_CREATE_EX(trunc_w_d); + FPU_STAT_CREATE_EX(trunc_l_s); + FPU_STAT_CREATE_EX(trunc_l_d); + return 0; } arch_initcall(debugfs_fpuemu); diff --git a/arch/mips/math-emu/sp_add.c b/arch/mips/math-emu/sp_add.c index f1c87b07d3b4..51dced9fbdaf 100644 --- a/arch/mips/math-emu/sp_add.c +++ b/arch/mips/math-emu/sp_add.c @@ -104,8 +104,7 @@ union ieee754sp ieee754sp_add(union ieee754sp x, union ieee754sp y) case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM): SPDNORMX; - - /* FALL THROUGH */ + /* fall through */ case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_DNORM): SPDNORMY; @@ -132,13 +131,15 @@ union ieee754sp ieee754sp_add(union ieee754sp x, union ieee754sp y) * Have to shift y fraction right to align. */ s = xe - ye; - SPXSRSYn(s); + ym = XSPSRS(ym, s); + ye += s; } else if (ye > xe) { /* * Have to shift x fraction right to align. */ s = ye - xe; - SPXSRSXn(s); + xm = XSPSRS(xm, s); + xe += s; } assert(xe == ye); assert(xe <= SP_EMAX); diff --git a/arch/mips/math-emu/sp_div.c b/arch/mips/math-emu/sp_div.c index 27f6db3a0a4c..5d2904960eb8 100644 --- a/arch/mips/math-emu/sp_div.c +++ b/arch/mips/math-emu/sp_div.c @@ -23,9 +23,9 @@ union ieee754sp ieee754sp_div(union ieee754sp x, union ieee754sp y) { - unsigned rm; + unsigned int rm; int re; - unsigned bm; + unsigned int bm; COMPXSP; COMPYSP; @@ -103,6 +103,7 @@ union ieee754sp ieee754sp_div(union ieee754sp x, union ieee754sp y) case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM): SPDNORMX; + /* fall through */ case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_DNORM): SPDNORMY; diff --git a/arch/mips/math-emu/sp_fdp.c b/arch/mips/math-emu/sp_fdp.c index 3797148893ad..36a50f9082d1 100644 --- a/arch/mips/math-emu/sp_fdp.c +++ b/arch/mips/math-emu/sp_fdp.c @@ -44,13 +44,17 @@ union ieee754sp ieee754sp_fdp(union ieee754dp x) switch (xc) { case IEEE754_CLASS_SNAN: - return ieee754sp_nanxcpt(ieee754sp_nan_fdp(xs, xm)); + x = ieee754dp_nanxcpt(x); + EXPLODEXDP; + /* fall through */ case IEEE754_CLASS_QNAN: y = ieee754sp_nan_fdp(xs, xm); - EXPLODEYSP; - if (!ieee754_class_nan(yc)) - y = ieee754sp_indef(); + if (!ieee754_csr.nan2008) { + EXPLODEYSP; + if (!ieee754_class_nan(yc)) + y = ieee754sp_indef(); + } return y; case IEEE754_CLASS_INF: diff --git a/arch/mips/math-emu/sp_fint.c b/arch/mips/math-emu/sp_fint.c index d5d8495b2cc4..1a35d12b6fc8 100644 --- a/arch/mips/math-emu/sp_fint.c +++ b/arch/mips/math-emu/sp_fint.c @@ -23,7 +23,7 @@ union ieee754sp ieee754sp_fint(int x) { - unsigned xm; + unsigned int xm; int xe; int xs; diff --git a/arch/mips/math-emu/sp_fmax.c b/arch/mips/math-emu/sp_fmax.c index 74a5a00d2f22..22019ed691df 100644 --- a/arch/mips/math-emu/sp_fmax.c +++ b/arch/mips/math-emu/sp_fmax.c @@ -96,6 +96,7 @@ union ieee754sp ieee754sp_fmax(union ieee754sp x, union ieee754sp y) case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM): SPDNORMX; + /* fall through */ case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_DNORM): SPDNORMY; @@ -224,6 +225,7 @@ union ieee754sp ieee754sp_fmaxa(union ieee754sp x, union ieee754sp y) case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM): SPDNORMX; + /* fall through */ case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_DNORM): SPDNORMY; diff --git a/arch/mips/math-emu/sp_fmin.c b/arch/mips/math-emu/sp_fmin.c index c51385f46b09..feaec3985cca 100644 --- a/arch/mips/math-emu/sp_fmin.c +++ b/arch/mips/math-emu/sp_fmin.c @@ -96,6 +96,7 @@ union ieee754sp ieee754sp_fmin(union ieee754sp x, union ieee754sp y) case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM): SPDNORMX; + /* fall through */ case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_DNORM): SPDNORMY; @@ -224,6 +225,7 @@ union ieee754sp ieee754sp_fmina(union ieee754sp x, union ieee754sp y) case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM): SPDNORMX; + /* fall through */ case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_DNORM): SPDNORMY; diff --git a/arch/mips/math-emu/sp_maddf.c b/arch/mips/math-emu/sp_maddf.c index dd1dd83e34eb..07ba675401e2 100644 --- a/arch/mips/math-emu/sp_maddf.c +++ b/arch/mips/math-emu/sp_maddf.c @@ -14,81 +14,60 @@ #include "ieee754sp.h" -union ieee754sp ieee754sp_maddf(union ieee754sp z, union ieee754sp x, - union ieee754sp y) + +static union ieee754sp _sp_maddf(union ieee754sp z, union ieee754sp x, + union ieee754sp y, enum maddf_flags flags) { int re; int rs; - unsigned rm; - unsigned short lxm; - unsigned short hxm; - unsigned short lym; - unsigned short hym; - unsigned lrm; - unsigned hrm; - unsigned t; - unsigned at; + unsigned int rm; + u64 rm64; + u64 zm64; int s; COMPXSP; COMPYSP; - u32 zm; int ze; int zs __maybe_unused; int zc; + COMPZSP; EXPLODEXSP; EXPLODEYSP; - EXPLODESP(z, zc, zs, ze, zm) + EXPLODEZSP; FLUSHXSP; FLUSHYSP; - FLUSHSP(z, zc, zs, ze, zm); + FLUSHZSP; ieee754_clearcx(); - switch (zc) { - case IEEE754_CLASS_SNAN: - ieee754_setcx(IEEE754_INVALID_OPERATION); + /* + * Handle the cases when at least one of x, y or z is a NaN. + * Order of precedence is sNaN, qNaN and z, x, y. + */ + if (zc == IEEE754_CLASS_SNAN) return ieee754sp_nanxcpt(z); - case IEEE754_CLASS_DNORM: - SPDNORMx(zm, ze); - /* QNAN is handled separately below */ - } - - switch (CLPAIR(xc, yc)) { - case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_SNAN): - case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_SNAN): - case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_SNAN): - case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_SNAN): - case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_SNAN): + if (xc == IEEE754_CLASS_SNAN) + return ieee754sp_nanxcpt(x); + if (yc == IEEE754_CLASS_SNAN) return ieee754sp_nanxcpt(y); + if (zc == IEEE754_CLASS_QNAN) + return z; + if (xc == IEEE754_CLASS_QNAN) + return x; + if (yc == IEEE754_CLASS_QNAN) + return y; - case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_SNAN): - case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_QNAN): - case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_ZERO): - case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_NORM): - case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_DNORM): - case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_INF): - return ieee754sp_nanxcpt(x); + if (zc == IEEE754_CLASS_DNORM) + SPDNORMZ; + /* ZERO z cases are handled separately below */ - case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_QNAN): - case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_QNAN): - case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_QNAN): - case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_QNAN): - return y; + switch (CLPAIR(xc, yc)) { - case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN): - case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_ZERO): - case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_NORM): - case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_DNORM): - case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_INF): - return x; /* * Infinity handling */ case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_ZERO): case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_INF): - if (zc == IEEE754_CLASS_QNAN) - return z; ieee754_setcx(IEEE754_INVALID_OPERATION); return ieee754sp_indef(); @@ -97,9 +76,27 @@ union ieee754sp ieee754sp_maddf(union ieee754sp z, union ieee754sp x, case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_NORM): case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_DNORM): case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_INF): - if (zc == IEEE754_CLASS_QNAN) - return z; - return ieee754sp_inf(xs ^ ys); + if ((zc == IEEE754_CLASS_INF) && + ((!(flags & MADDF_NEGATE_PRODUCT) && (zs != (xs ^ ys))) || + ((flags & MADDF_NEGATE_PRODUCT) && (zs == (xs ^ ys))))) { + /* + * Cases of addition of infinities with opposite signs + * or subtraction of infinities with same signs. + */ + ieee754_setcx(IEEE754_INVALID_OPERATION); + return ieee754sp_indef(); + } + /* + * z is here either not an infinity, or an infinity having the + * same sign as product (x*y) (in case of MADDF.D instruction) + * or product -(x*y) (in MSUBF.D case). The result must be an + * infinity, and its sign is determined only by the value of + * (flags & MADDF_NEGATE_PRODUCT) and the signs of x and y. + */ + if (flags & MADDF_NEGATE_PRODUCT) + return ieee754sp_inf(1 ^ (xs ^ ys)); + else + return ieee754sp_inf(xs ^ ys); case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_ZERO): case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_NORM): @@ -108,34 +105,45 @@ union ieee754sp ieee754sp_maddf(union ieee754sp z, union ieee754sp x, case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_ZERO): if (zc == IEEE754_CLASS_INF) return ieee754sp_inf(zs); - /* Multiplication is 0 so just return z */ + if (zc == IEEE754_CLASS_ZERO) { + /* Handle cases +0 + (-0) and similar ones. */ + if ((!(flags & MADDF_NEGATE_PRODUCT) + && (zs == (xs ^ ys))) || + ((flags & MADDF_NEGATE_PRODUCT) + && (zs != (xs ^ ys)))) + /* + * Cases of addition of zeros of equal signs + * or subtraction of zeroes of opposite signs. + * The sign of the resulting zero is in any + * such case determined only by the sign of z. + */ + return z; + + return ieee754sp_zero(ieee754_csr.rm == FPU_CSR_RD); + } + /* x*y is here 0, and z is not 0, so just return z */ return z; case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM): SPDNORMX; + /* fall through */ case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_DNORM): - if (zc == IEEE754_CLASS_QNAN) - return z; - else if (zc == IEEE754_CLASS_INF) + if (zc == IEEE754_CLASS_INF) return ieee754sp_inf(zs); SPDNORMY; break; case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_NORM): - if (zc == IEEE754_CLASS_QNAN) - return z; - else if (zc == IEEE754_CLASS_INF) + if (zc == IEEE754_CLASS_INF) return ieee754sp_inf(zs); SPDNORMX; break; case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_NORM): - if (zc == IEEE754_CLASS_QNAN) - return z; - else if (zc == IEEE754_CLASS_INF) + if (zc == IEEE754_CLASS_INF) return ieee754sp_inf(zs); - /* fall through to real computations */ + /* continue to real computations */ } /* Finally get to do some computation */ @@ -154,102 +162,104 @@ union ieee754sp ieee754sp_maddf(union ieee754sp z, union ieee754sp x, re = xe + ye; rs = xs ^ ys; + if (flags & MADDF_NEGATE_PRODUCT) + rs ^= 1; - /* shunt to top of word */ - xm <<= 32 - (SP_FBITS + 1); - ym <<= 32 - (SP_FBITS + 1); + /* Multiple 24 bit xm and ym to give 48 bit results */ + rm64 = (uint64_t)xm * ym; - /* - * Multiply 32 bits xm, ym to give high 32 bits rm with stickness. - */ - lxm = xm & 0xffff; - hxm = xm >> 16; - lym = ym & 0xffff; - hym = ym >> 16; + /* Shunt to top of word */ + rm64 = rm64 << 16; - lrm = lxm * lym; /* 16 * 16 => 32 */ - hrm = hxm * hym; /* 16 * 16 => 32 */ - - t = lxm * hym; /* 16 * 16 => 32 */ - at = lrm + (t << 16); - hrm += at < lrm; - lrm = at; - hrm = hrm + (t >> 16); - - t = hxm * lym; /* 16 * 16 => 32 */ - at = lrm + (t << 16); - hrm += at < lrm; - lrm = at; - hrm = hrm + (t >> 16); - - rm = hrm | (lrm != 0); - - /* - * Sticky shift down to normal rounding precision. - */ - if ((int) rm < 0) { - rm = (rm >> (32 - (SP_FBITS + 1 + 3))) | - ((rm << (SP_FBITS + 1 + 3)) != 0); + /* Put explicit bit at bit 62 if necessary */ + if ((int64_t) rm64 < 0) { + rm64 = rm64 >> 1; re++; - } else { - rm = (rm >> (32 - (SP_FBITS + 1 + 3 + 1))) | - ((rm << (SP_FBITS + 1 + 3 + 1)) != 0); } - assert(rm & (SP_HIDDEN_BIT << 3)); - /* And now the addition */ + assert(rm64 & (1 << 62)); - assert(zm & SP_HIDDEN_BIT); + if (zc == IEEE754_CLASS_ZERO) { + /* + * Move explicit bit from bit 62 to bit 26 since the + * ieee754sp_format code expects the mantissa to be + * 27 bits wide (24 + 3 rounding bits). + */ + rm = XSPSRS64(rm64, (62 - 26)); + return ieee754sp_format(rs, re, rm); + } - /* - * Provide guard,round and stick bit space. - */ - zm <<= 3; + /* Move explicit bit from bit 23 to bit 62 */ + zm64 = (uint64_t)zm << (62 - 23); + assert(zm64 & (1 << 62)); + /* Make the exponents the same */ if (ze > re) { /* - * Have to shift y fraction right to align. + * Have to shift r fraction right to align. */ s = ze - re; - SPXSRSYn(s); + rm64 = XSPSRS64(rm64, s); + re += s; } else if (re > ze) { /* - * Have to shift x fraction right to align. + * Have to shift z fraction right to align. */ s = re - ze; - SPXSRSYn(s); + zm64 = XSPSRS64(zm64, s); + ze += s; } assert(ze == re); assert(ze <= SP_EMAX); + /* Do the addition */ if (zs == rs) { /* - * Generate 28 bit result of adding two 27 bit numbers - * leaving result in zm, zs and ze. + * Generate 64 bit result by adding two 63 bit numbers + * leaving result in zm64, zs and ze. */ - zm = zm + rm; - - if (zm >> (SP_FBITS + 1 + 3)) { /* carry out */ - SPXSRSX1(); + zm64 = zm64 + rm64; + if ((int64_t)zm64 < 0) { /* carry out */ + zm64 = XSPSRS1(zm64); + ze++; } } else { - if (zm >= rm) { - zm = zm - rm; + if (zm64 >= rm64) { + zm64 = zm64 - rm64; } else { - zm = rm - zm; + zm64 = rm64 - zm64; zs = rs; } - if (zm == 0) + if (zm64 == 0) return ieee754sp_zero(ieee754_csr.rm == FPU_CSR_RD); /* - * Normalize in extended single precision + * Put explicit bit at bit 62 if necessary. */ - while ((zm >> (SP_MBITS + 3)) == 0) { - zm <<= 1; + while ((zm64 >> 62) == 0) { + zm64 <<= 1; ze--; } - } + + /* + * Move explicit bit from bit 62 to bit 26 since the + * ieee754sp_format code expects the mantissa to be + * 27 bits wide (24 + 3 rounding bits). + */ + zm = XSPSRS64(zm64, (62 - 26)); + return ieee754sp_format(zs, ze, zm); } + +union ieee754sp ieee754sp_maddf(union ieee754sp z, union ieee754sp x, + union ieee754sp y) +{ + return _sp_maddf(z, x, y, 0); +} + +union ieee754sp ieee754sp_msubf(union ieee754sp z, union ieee754sp x, + union ieee754sp y) +{ + return _sp_maddf(z, x, y, MADDF_NEGATE_PRODUCT); +} diff --git a/arch/mips/math-emu/sp_msubf.c b/arch/mips/math-emu/sp_msubf.c deleted file mode 100644 index 81c38b980d69..000000000000 --- a/arch/mips/math-emu/sp_msubf.c +++ /dev/null @@ -1,258 +0,0 @@ -/* - * IEEE754 floating point arithmetic - * single precision: MSUB.f (Fused Multiply Subtract) - * MSUBF.fmt: FPR[fd] = FPR[fd] - (FPR[fs] x FPR[ft]) - * - * MIPS floating point support - * Copyright (C) 2015 Imagination Technologies, Ltd. - * Author: Markos Chandras <markos.chandras@imgtec.com> - * - * This program is free software; you can distribute it and/or modify it - * under the terms of the GNU General Public License as published by the - * Free Software Foundation; version 2 of the License. - */ - -#include "ieee754sp.h" - -union ieee754sp ieee754sp_msubf(union ieee754sp z, union ieee754sp x, - union ieee754sp y) -{ - int re; - int rs; - unsigned rm; - unsigned short lxm; - unsigned short hxm; - unsigned short lym; - unsigned short hym; - unsigned lrm; - unsigned hrm; - unsigned t; - unsigned at; - int s; - - COMPXSP; - COMPYSP; - u32 zm; int ze; int zs __maybe_unused; int zc; - - EXPLODEXSP; - EXPLODEYSP; - EXPLODESP(z, zc, zs, ze, zm) - - FLUSHXSP; - FLUSHYSP; - FLUSHSP(z, zc, zs, ze, zm); - - ieee754_clearcx(); - - switch (zc) { - case IEEE754_CLASS_SNAN: - ieee754_setcx(IEEE754_INVALID_OPERATION); - return ieee754sp_nanxcpt(z); - case IEEE754_CLASS_DNORM: - SPDNORMx(zm, ze); - /* QNAN is handled separately below */ - } - - switch (CLPAIR(xc, yc)) { - case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_SNAN): - case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_SNAN): - case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_SNAN): - case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_SNAN): - case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_SNAN): - return ieee754sp_nanxcpt(y); - - case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_SNAN): - case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_QNAN): - case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_ZERO): - case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_NORM): - case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_DNORM): - case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_INF): - return ieee754sp_nanxcpt(x); - - case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_QNAN): - case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_QNAN): - case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_QNAN): - case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_QNAN): - return y; - - case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN): - case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_ZERO): - case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_NORM): - case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_DNORM): - case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_INF): - return x; - - /* - * Infinity handling - */ - case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_ZERO): - case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_INF): - if (zc == IEEE754_CLASS_QNAN) - return z; - ieee754_setcx(IEEE754_INVALID_OPERATION); - return ieee754sp_indef(); - - case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_INF): - case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_INF): - case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_NORM): - case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_DNORM): - case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_INF): - if (zc == IEEE754_CLASS_QNAN) - return z; - return ieee754sp_inf(xs ^ ys); - - case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_ZERO): - case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_NORM): - case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_DNORM): - case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_ZERO): - case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_ZERO): - if (zc == IEEE754_CLASS_INF) - return ieee754sp_inf(zs); - /* Multiplication is 0 so just return z */ - return z; - - case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM): - SPDNORMX; - - case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_DNORM): - if (zc == IEEE754_CLASS_QNAN) - return z; - else if (zc == IEEE754_CLASS_INF) - return ieee754sp_inf(zs); - SPDNORMY; - break; - - case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_NORM): - if (zc == IEEE754_CLASS_QNAN) - return z; - else if (zc == IEEE754_CLASS_INF) - return ieee754sp_inf(zs); - SPDNORMX; - break; - - case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_NORM): - if (zc == IEEE754_CLASS_QNAN) - return z; - else if (zc == IEEE754_CLASS_INF) - return ieee754sp_inf(zs); - /* fall through to real compuation */ - } - - /* Finally get to do some computation */ - - /* - * Do the multiplication bit first - * - * rm = xm * ym, re = xe + ye basically - * - * At this point xm and ym should have been normalized. - */ - - /* rm = xm * ym, re = xe+ye basically */ - assert(xm & SP_HIDDEN_BIT); - assert(ym & SP_HIDDEN_BIT); - - re = xe + ye; - rs = xs ^ ys; - - /* shunt to top of word */ - xm <<= 32 - (SP_FBITS + 1); - ym <<= 32 - (SP_FBITS + 1); - - /* - * Multiply 32 bits xm, ym to give high 32 bits rm with stickness. - */ - lxm = xm & 0xffff; - hxm = xm >> 16; - lym = ym & 0xffff; - hym = ym >> 16; - - lrm = lxm * lym; /* 16 * 16 => 32 */ - hrm = hxm * hym; /* 16 * 16 => 32 */ - - t = lxm * hym; /* 16 * 16 => 32 */ - at = lrm + (t << 16); - hrm += at < lrm; - lrm = at; - hrm = hrm + (t >> 16); - - t = hxm * lym; /* 16 * 16 => 32 */ - at = lrm + (t << 16); - hrm += at < lrm; - lrm = at; - hrm = hrm + (t >> 16); - - rm = hrm | (lrm != 0); - - /* - * Sticky shift down to normal rounding precision. - */ - if ((int) rm < 0) { - rm = (rm >> (32 - (SP_FBITS + 1 + 3))) | - ((rm << (SP_FBITS + 1 + 3)) != 0); - re++; - } else { - rm = (rm >> (32 - (SP_FBITS + 1 + 3 + 1))) | - ((rm << (SP_FBITS + 1 + 3 + 1)) != 0); - } - assert(rm & (SP_HIDDEN_BIT << 3)); - - /* And now the subtraction */ - - /* Flip sign of r and handle as add */ - rs ^= 1; - - assert(zm & SP_HIDDEN_BIT); - - /* - * Provide guard,round and stick bit space. - */ - zm <<= 3; - - if (ze > re) { - /* - * Have to shift y fraction right to align. - */ - s = ze - re; - SPXSRSYn(s); - } else if (re > ze) { - /* - * Have to shift x fraction right to align. - */ - s = re - ze; - SPXSRSYn(s); - } - assert(ze == re); - assert(ze <= SP_EMAX); - - if (zs == rs) { - /* - * Generate 28 bit result of adding two 27 bit numbers - * leaving result in zm, zs and ze. - */ - zm = zm + rm; - - if (zm >> (SP_FBITS + 1 + 3)) { /* carry out */ - SPXSRSX1(); /* shift preserving sticky */ - } - } else { - if (zm >= rm) { - zm = zm - rm; - } else { - zm = rm - zm; - zs = rs; - } - if (zm == 0) - return ieee754sp_zero(ieee754_csr.rm == FPU_CSR_RD); - - /* - * Normalize in extended single precision - */ - while ((zm >> (SP_MBITS + 3)) == 0) { - zm <<= 1; - ze--; - } - - } - return ieee754sp_format(zs, ze, zm); -} diff --git a/arch/mips/math-emu/sp_mul.c b/arch/mips/math-emu/sp_mul.c index d910c43a6f30..fde71e293ec4 100644 --- a/arch/mips/math-emu/sp_mul.c +++ b/arch/mips/math-emu/sp_mul.c @@ -25,15 +25,15 @@ union ieee754sp ieee754sp_mul(union ieee754sp x, union ieee754sp y) { int re; int rs; - unsigned rm; + unsigned int rm; unsigned short lxm; unsigned short hxm; unsigned short lym; unsigned short hym; - unsigned lrm; - unsigned hrm; - unsigned t; - unsigned at; + unsigned int lrm; + unsigned int hrm; + unsigned int t; + unsigned int at; COMPXSP; COMPYSP; @@ -101,6 +101,7 @@ union ieee754sp ieee754sp_mul(union ieee754sp x, union ieee754sp y) case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM): SPDNORMX; + /* fall through */ case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_DNORM): SPDNORMY; diff --git a/arch/mips/math-emu/sp_rint.c b/arch/mips/math-emu/sp_rint.c new file mode 100644 index 000000000000..70765b17e196 --- /dev/null +++ b/arch/mips/math-emu/sp_rint.c @@ -0,0 +1,90 @@ +/* IEEE754 floating point arithmetic + * single precision + */ +/* + * MIPS floating point support + * Copyright (C) 1994-2000 Algorithmics Ltd. + * Copyright (C) 2017 Imagination Technologies, Ltd. + * Author: Aleksandar Markovic <aleksandar.markovic@imgtec.com> + * + * This program is free software; you can distribute it and/or modify it + * under the terms of the GNU General Public License (Version 2) as + * published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License + * for more details. + * + * You should have received a copy of the GNU General Public License along + * with this program. + */ + +#include "ieee754sp.h" + +union ieee754sp ieee754sp_rint(union ieee754sp x) +{ + union ieee754sp ret; + u32 residue; + int sticky; + int round; + int odd; + + COMPXDP; /* <-- DP needed for 64-bit mantissa tmp */ + + ieee754_clearcx(); + + EXPLODEXSP; + FLUSHXSP; + + if (xc == IEEE754_CLASS_SNAN) + return ieee754sp_nanxcpt(x); + + if ((xc == IEEE754_CLASS_QNAN) || + (xc == IEEE754_CLASS_INF) || + (xc == IEEE754_CLASS_ZERO)) + return x; + + if (xe >= SP_FBITS) + return x; + + if (xe < -1) { + residue = xm; + round = 0; + sticky = residue != 0; + xm = 0; + } else { + residue = xm << (xe + 1); + residue <<= 31 - SP_FBITS; + round = (residue >> 31) != 0; + sticky = (residue << 1) != 0; + xm >>= SP_FBITS - xe; + } + + odd = (xm & 0x1) != 0x0; + + switch (ieee754_csr.rm) { + case FPU_CSR_RN: /* toward nearest */ + if (round && (sticky || odd)) + xm++; + break; + case FPU_CSR_RZ: /* toward zero */ + break; + case FPU_CSR_RU: /* toward +infinity */ + if ((round || sticky) && !xs) + xm++; + break; + case FPU_CSR_RD: /* toward -infinity */ + if ((round || sticky) && xs) + xm++; + break; + } + + if (round || sticky) + ieee754_setcx(IEEE754_INEXACT); + + ret = ieee754sp_flong(xm); + SPSIGN(ret) = xs; + + return ret; +} diff --git a/arch/mips/math-emu/sp_simple.c b/arch/mips/math-emu/sp_simple.c index c50e9451f2d2..756c9cf2dfd2 100644 --- a/arch/mips/math-emu/sp_simple.c +++ b/arch/mips/math-emu/sp_simple.c @@ -23,27 +23,39 @@ union ieee754sp ieee754sp_neg(union ieee754sp x) { - unsigned int oldrm; union ieee754sp y; - oldrm = ieee754_csr.rm; - ieee754_csr.rm = FPU_CSR_RD; - y = ieee754sp_sub(ieee754sp_zero(0), x); - ieee754_csr.rm = oldrm; + if (ieee754_csr.abs2008) { + y = x; + SPSIGN(y) = !SPSIGN(x); + } else { + unsigned int oldrm; + + oldrm = ieee754_csr.rm; + ieee754_csr.rm = FPU_CSR_RD; + y = ieee754sp_sub(ieee754sp_zero(0), x); + ieee754_csr.rm = oldrm; + } return y; } union ieee754sp ieee754sp_abs(union ieee754sp x) { - unsigned int oldrm; union ieee754sp y; - oldrm = ieee754_csr.rm; - ieee754_csr.rm = FPU_CSR_RD; - if (SPSIGN(x)) - y = ieee754sp_sub(ieee754sp_zero(0), x); - else - y = ieee754sp_add(ieee754sp_zero(0), x); - ieee754_csr.rm = oldrm; + if (ieee754_csr.abs2008) { + y = x; + SPSIGN(y) = 0; + } else { + unsigned int oldrm; + + oldrm = ieee754_csr.rm; + ieee754_csr.rm = FPU_CSR_RD; + if (SPSIGN(x)) + y = ieee754sp_sub(ieee754sp_zero(0), x); + else + y = ieee754sp_add(ieee754sp_zero(0), x); + ieee754_csr.rm = oldrm; + } return y; } diff --git a/arch/mips/math-emu/sp_sqrt.c b/arch/mips/math-emu/sp_sqrt.c index 67059c33a250..9cc83f012342 100644 --- a/arch/mips/math-emu/sp_sqrt.c +++ b/arch/mips/math-emu/sp_sqrt.c @@ -82,7 +82,8 @@ union ieee754sp ieee754sp_sqrt(union ieee754sp x) /* generate sqrt(x) bit by bit */ ix += ix; - q = s = 0; /* q = sqrt(x) */ + s = 0; + q = 0; /* q = sqrt(x) */ r = 0x01000000; /* r = moving bit from right to left */ while (r != 0) { diff --git a/arch/mips/math-emu/sp_sub.c b/arch/mips/math-emu/sp_sub.c index ec5f937a8b3e..9f2ff72c3d6b 100644 --- a/arch/mips/math-emu/sp_sub.c +++ b/arch/mips/math-emu/sp_sub.c @@ -106,6 +106,7 @@ union ieee754sp ieee754sp_sub(union ieee754sp x, union ieee754sp y) case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM): SPDNORMX; + /* fall through */ case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_DNORM): SPDNORMY; @@ -134,13 +135,15 @@ union ieee754sp ieee754sp_sub(union ieee754sp x, union ieee754sp y) * have to shift y fraction right to align */ s = xe - ye; - SPXSRSYn(s); + ym = XSPSRS(ym, s); + ye += s; } else if (ye > xe) { /* * have to shift x fraction right to align */ s = ye - xe; - SPXSRSXn(s); + xm = XSPSRS(xm, s); + xe += s; } assert(xe == ye); assert(xe <= SP_EMAX); diff --git a/arch/mips/math-emu/sp_tint.c b/arch/mips/math-emu/sp_tint.c index 091299a31798..f4b4cabfe2e1 100644 --- a/arch/mips/math-emu/sp_tint.c +++ b/arch/mips/math-emu/sp_tint.c @@ -38,10 +38,13 @@ int ieee754sp_tint(union ieee754sp x) switch (xc) { case IEEE754_CLASS_SNAN: case IEEE754_CLASS_QNAN: - case IEEE754_CLASS_INF: ieee754_setcx(IEEE754_INVALID_OPERATION); return ieee754si_indef(); + case IEEE754_CLASS_INF: + ieee754_setcx(IEEE754_INVALID_OPERATION); + return ieee754si_overflow(xs); + case IEEE754_CLASS_ZERO: return 0; @@ -56,7 +59,7 @@ int ieee754sp_tint(union ieee754sp x) /* Set invalid. We will only use overflow for floating point overflow */ ieee754_setcx(IEEE754_INVALID_OPERATION); - return ieee754si_indef(); + return ieee754si_overflow(xs); } /* oh gawd */ if (xe > SP_FBITS) { @@ -97,7 +100,7 @@ int ieee754sp_tint(union ieee754sp x) if ((xm >> 31) != 0) { /* This can happen after rounding */ ieee754_setcx(IEEE754_INVALID_OPERATION); - return ieee754si_indef(); + return ieee754si_overflow(xs); } if (round || sticky) ieee754_setcx(IEEE754_INEXACT); diff --git a/arch/mips/math-emu/sp_tlong.c b/arch/mips/math-emu/sp_tlong.c index 9f3c742c1cea..bca5ac995801 100644 --- a/arch/mips/math-emu/sp_tlong.c +++ b/arch/mips/math-emu/sp_tlong.c @@ -20,7 +20,6 @@ */ #include "ieee754sp.h" -#include "ieee754dp.h" s64 ieee754sp_tlong(union ieee754sp x) { @@ -39,10 +38,13 @@ s64 ieee754sp_tlong(union ieee754sp x) switch (xc) { case IEEE754_CLASS_SNAN: case IEEE754_CLASS_QNAN: - case IEEE754_CLASS_INF: ieee754_setcx(IEEE754_INVALID_OPERATION); return ieee754di_indef(); + case IEEE754_CLASS_INF: + ieee754_setcx(IEEE754_INVALID_OPERATION); + return ieee754di_overflow(xs); + case IEEE754_CLASS_ZERO: return 0; @@ -57,7 +59,7 @@ s64 ieee754sp_tlong(union ieee754sp x) /* Set invalid. We will only use overflow for floating point overflow */ ieee754_setcx(IEEE754_INVALID_OPERATION); - return ieee754di_indef(); + return ieee754di_overflow(xs); } /* oh gawd */ if (xe > SP_FBITS) { @@ -94,7 +96,7 @@ s64 ieee754sp_tlong(union ieee754sp x) if ((xm >> 63) != 0) { /* This can happen after rounding */ ieee754_setcx(IEEE754_INVALID_OPERATION); - return ieee754di_indef(); + return ieee754di_overflow(xs); } if (round || sticky) ieee754_setcx(IEEE754_INEXACT); diff --git a/arch/mips/mm/c-r4k.c b/arch/mips/mm/c-r4k.c index 5d3a25e1cfae..d66a61efb143 100644 --- a/arch/mips/mm/c-r4k.c +++ b/arch/mips/mm/c-r4k.c @@ -780,25 +780,72 @@ static void r4k_dma_cache_inv(unsigned long addr, unsigned long size) } #endif /* CONFIG_DMA_NONCOHERENT || CONFIG_DMA_MAYBE_COHERENT */ +struct flush_cache_sigtramp_args { + struct mm_struct *mm; + struct page *page; + unsigned long addr; +}; + /* * While we're protected against bad userland addresses we don't care * very much about what happens in that case. Usually a segmentation * fault will dump the process later on anyway ... */ -static void local_r4k_flush_cache_sigtramp(void * arg) +static void local_r4k_flush_cache_sigtramp(void *args) { + struct flush_cache_sigtramp_args *fcs_args = args; + unsigned long addr = fcs_args->addr; + struct page *page = fcs_args->page; + struct mm_struct *mm = fcs_args->mm; + int map_coherent = 0; + void *vaddr; + unsigned long ic_lsize = cpu_icache_line_size(); unsigned long dc_lsize = cpu_dcache_line_size(); unsigned long sc_lsize = cpu_scache_line_size(); - unsigned long addr = (unsigned long) arg; + + /* + * If owns no valid ASID yet, cannot possibly have gotten + * this page into the cache. + */ + if (!has_valid_asid(mm)) + return; + + if (mm == current->active_mm) { + vaddr = NULL; + } else { + /* + * Use kmap_coherent or kmap_atomic to do flushes for + * another ASID than the current one. + */ + map_coherent = (cpu_has_dc_aliases && + page_mapcount(page) && + !Page_dcache_dirty(page)); + if (map_coherent) + vaddr = kmap_coherent(page, addr); + else + vaddr = kmap_atomic(page); + addr = (unsigned long)vaddr + (addr & ~PAGE_MASK); + } R4600_HIT_CACHEOP_WAR_IMPL; if (dc_lsize) - protected_writeback_dcache_line(addr & ~(dc_lsize - 1)); + vaddr ? flush_dcache_line(addr & ~(dc_lsize - 1)) + : protected_writeback_dcache_line(addr & ~(dc_lsize - 1)); if (!cpu_icache_snoops_remote_store && scache_size) - protected_writeback_scache_line(addr & ~(sc_lsize - 1)); + vaddr ? flush_scache_line(addr & ~(sc_lsize - 1)) + : protected_writeback_scache_line(addr & ~(sc_lsize - 1)); if (ic_lsize) - protected_flush_icache_line(addr & ~(ic_lsize - 1)); + vaddr ? flush_icache_line(addr & ~(ic_lsize - 1)) + : protected_flush_icache_line(addr & ~(ic_lsize - 1)); + + if (vaddr) { + if (map_coherent) + kunmap_coherent(); + else + kunmap_atomic(vaddr); + } + if (MIPS4K_ICACHE_REFILL_WAR) { __asm__ __volatile__ ( ".set push\n\t" @@ -823,7 +870,23 @@ static void local_r4k_flush_cache_sigtramp(void * arg) static void r4k_flush_cache_sigtramp(unsigned long addr) { - r4k_on_each_cpu(local_r4k_flush_cache_sigtramp, (void *) addr); + struct flush_cache_sigtramp_args args; + int npages; + + down_read(¤t->mm->mmap_sem); + + npages = get_user_pages_fast(addr, 1, 0, &args.page); + if (npages < 1) + goto out; + + args.mm = current->mm; + args.addr = addr; + + r4k_on_each_cpu(local_r4k_flush_cache_sigtramp, &args); + + put_page(args.page); +out: + up_read(¤t->mm->mmap_sem); } static void r4k_flush_icache_all(void) @@ -1670,7 +1733,7 @@ void r4k_cache_init(void) * This code supports virtually indexed processors and will be * unnecessarily inefficient on physically indexed processors. */ - if (c->dcache.linesz) + if (c->dcache.linesz && cpu_has_dc_aliases) shm_align_mask = max_t( unsigned long, c->dcache.sets * c->dcache.linesz - 1, PAGE_SIZE - 1); @@ -1696,7 +1759,12 @@ void r4k_cache_init(void) local_flush_icache_range = local_r4k_flush_icache_range; #if defined(CONFIG_DMA_NONCOHERENT) || defined(CONFIG_DMA_MAYBE_COHERENT) - if (coherentio) { +# if defined(CONFIG_DMA_PERDEV_COHERENT) + if (0) { +# else + if ((coherentio == IO_COHERENCE_ENABLED) || + ((coherentio == IO_COHERENCE_DEFAULT) && hw_coherentio)) { +# endif _dma_cache_wback_inv = (void *)cache_noop; _dma_cache_wback = (void *)cache_noop; _dma_cache_inv = (void *)cache_noop; diff --git a/arch/mips/mm/dma-default.c b/arch/mips/mm/dma-default.c index 730d394ce5f0..3ae73ae45938 100644 --- a/arch/mips/mm/dma-default.c +++ b/arch/mips/mm/dma-default.c @@ -24,14 +24,15 @@ #include <dma-coherence.h> -#ifdef CONFIG_DMA_MAYBE_COHERENT -int coherentio = 0; /* User defined DMA coherency from command line. */ +#if defined(CONFIG_DMA_MAYBE_COHERENT) && !defined(CONFIG_DMA_PERDEV_COHERENT) +/* User defined DMA coherency from command line. */ +enum coherent_io_user_state coherentio = IO_COHERENCE_DEFAULT; EXPORT_SYMBOL_GPL(coherentio); int hw_coherentio = 0; /* Actual hardware supported DMA coherency setting. */ static int __init setcoherentio(char *str) { - coherentio = 1; + coherentio = IO_COHERENCE_ENABLED; pr_info("Hardware DMA cache coherency (command line)\n"); return 0; } @@ -39,7 +40,7 @@ early_param("coherentio", setcoherentio); static int __init setnocoherentio(char *str) { - coherentio = 0; + coherentio = IO_COHERENCE_DISABLED; pr_info("Software DMA cache coherency (command line)\n"); return 0; } @@ -159,8 +160,7 @@ static void *mips_dma_alloc_coherent(struct device *dev, size_t size, *dma_handle = plat_map_dma_mem(dev, ret, size); if (!plat_device_is_coherent(dev)) { dma_cache_wback_inv((unsigned long) ret, size); - if (!hw_coherentio) - ret = UNCAC_ADDR(ret); + ret = UNCAC_ADDR(ret); } return ret; @@ -188,7 +188,7 @@ static void mips_dma_free_coherent(struct device *dev, size_t size, void *vaddr, plat_unmap_dma_mem(dev, dma_handle, size, DMA_BIDIRECTIONAL); - if (!plat_device_is_coherent(dev) && !hw_coherentio) + if (!plat_device_is_coherent(dev)) addr = CAC_ADDR(addr); page = virt_to_page((void *) addr); @@ -208,7 +208,7 @@ static int mips_dma_mmap(struct device *dev, struct vm_area_struct *vma, unsigned long pfn; int ret = -ENXIO; - if (!plat_device_is_coherent(dev) && !hw_coherentio) + if (!plat_device_is_coherent(dev)) addr = CAC_ADDR(addr); pfn = page_to_pfn(virt_to_page((void *)addr)); diff --git a/arch/mips/mm/sc-ip22.c b/arch/mips/mm/sc-ip22.c index efaf364fe581..f293a97cb885 100644 --- a/arch/mips/mm/sc-ip22.c +++ b/arch/mips/mm/sc-ip22.c @@ -172,7 +172,7 @@ static inline int __init indy_sc_probe(void) return 1; } -/* XXX Check with wje if the Indy caches can differenciate between +/* XXX Check with wje if the Indy caches can differentiate between writeback + invalidate and just invalidate. */ static struct bcache_ops indy_sc_ops = { .bc_enable = indy_sc_enable, diff --git a/arch/mips/mm/sc-mips.c b/arch/mips/mm/sc-mips.c index ddb8154610cc..91dec32c77b7 100644 --- a/arch/mips/mm/sc-mips.c +++ b/arch/mips/mm/sc-mips.c @@ -186,10 +186,6 @@ static int __init mips_sc_probe_cm3(void) return 0; } -void __weak platform_early_l2_init(void) -{ -} - static inline int __init mips_sc_probe(void) { struct cpuinfo_mips *c = ¤t_cpu_data; @@ -199,12 +195,6 @@ static inline int __init mips_sc_probe(void) /* Mark as not present until probe completed */ c->scache.flags |= MIPS_CACHE_NOT_PRESENT; - /* - * Do we need some platform specific probing before - * we configure L2? - */ - platform_early_l2_init(); - if (mips_cm_revision() >= CM_REV_CM3) return mips_sc_probe_cm3(); diff --git a/arch/mips/mm/tlbex.c b/arch/mips/mm/tlbex.c index 63b7d6f82d24..b5a0234da765 100644 --- a/arch/mips/mm/tlbex.c +++ b/arch/mips/mm/tlbex.c @@ -12,7 +12,7 @@ * Copyright (C) 2011 MIPS Technologies, Inc. * * ... and the days got worse and worse and now you see - * I've gone completly out of my mind. + * I've gone completely out of my mind. * * They're coming to take me a away haha * they're coming to take me a away hoho hihi haha diff --git a/arch/mips/mti-malta/malta-init.c b/arch/mips/mti-malta/malta-init.c index 571148c5fd0b..dc2c5214809d 100644 --- a/arch/mips/mti-malta/malta-init.c +++ b/arch/mips/mti-malta/malta-init.c @@ -293,7 +293,6 @@ mips_pci_controller: console_config(); #endif /* Early detection of CMP support */ - mips_cm_probe(); mips_cpc_probe(); if (!register_cps_smp_ops()) @@ -304,10 +303,3 @@ mips_pci_controller: return; register_up_smp_ops(); } - -void platform_early_l2_init(void) -{ - /* L2 configuration lives in the CM3 */ - if (mips_cm_revision() >= CM_REV_CM3) - mips_cm_probe(); -} diff --git a/arch/mips/mti-malta/malta-setup.c b/arch/mips/mti-malta/malta-setup.c index 36b09b2ea972..363c9a34e57e 100644 --- a/arch/mips/mti-malta/malta-setup.c +++ b/arch/mips/mti-malta/malta-setup.c @@ -154,12 +154,12 @@ static void __init plat_setup_iocoherency(void) * coherency instead. */ if (plat_enable_iocoherency()) { - if (coherentio == 0) + if (coherentio == IO_COHERENCE_DISABLED) pr_info("Hardware DMA cache coherency disabled\n"); else pr_info("Hardware DMA cache coherency enabled\n"); } else { - if (coherentio == 1) + if (coherentio == IO_COHERENCE_ENABLED) pr_info("Hardware DMA cache coherency unsupported, but enabled from command line!\n"); else pr_info("Software DMA cache coherency enabled\n"); diff --git a/arch/mips/pci/pci-alchemy.c b/arch/mips/pci/pci-alchemy.c index 28952637a862..f945ee85dcaf 100644 --- a/arch/mips/pci/pci-alchemy.c +++ b/arch/mips/pci/pci-alchemy.c @@ -429,7 +429,8 @@ static int alchemy_pci_probe(struct platform_device *pdev) /* Au1500 revisions older than AD have borked coherent PCI */ if ((alchemy_get_cputype() == ALCHEMY_CPU_AU1500) && - (read_c0_prid() < 0x01030202) && !coherentio) { + (read_c0_prid() < 0x01030202) && + (coherentio == IO_COHERENCE_DISABLED)) { val = __raw_readl(ctx->regs + PCI_REG_CONFIG); val |= PCI_CONFIG_NC; __raw_writel(val, ctx->regs + PCI_REG_CONFIG); diff --git a/arch/mips/sgi-ip27/ip27-memory.c b/arch/mips/sgi-ip27/ip27-memory.c index 8d0eb2643248..f1f88291451e 100644 --- a/arch/mips/sgi-ip27/ip27-memory.c +++ b/arch/mips/sgi-ip27/ip27-memory.c @@ -7,7 +7,7 @@ * Copyright (C) 2000 by Silicon Graphics, Inc. * Copyright (C) 2004 by Christoph Hellwig * - * On SGI IP27 the ARC memory configuration data is completly bogus but + * On SGI IP27 the ARC memory configuration data is completely bogus but * alternate easier to use mechanisms are available. */ #include <linux/init.h> diff --git a/arch/mips/sgi-ip27/ip27-nmi.c b/arch/mips/sgi-ip27/ip27-nmi.c index a2358b44420c..cfceaea92724 100644 --- a/arch/mips/sgi-ip27/ip27-nmi.c +++ b/arch/mips/sgi-ip27/ip27-nmi.c @@ -23,7 +23,7 @@ typedef unsigned long machreg_t; static arch_spinlock_t nmi_lock = __ARCH_SPIN_LOCK_UNLOCKED; /* - * Lets see what else we need to do here. Set up sp, gp? + * Let's see what else we need to do here. Set up sp, gp? */ void nmi_dump(void) { diff --git a/arch/mips/sgi-ip27/ip27-xtalk.c b/arch/mips/sgi-ip27/ip27-xtalk.c index 20f582a2137a..4fe5678ba74d 100644 --- a/arch/mips/sgi-ip27/ip27-xtalk.c +++ b/arch/mips/sgi-ip27/ip27-xtalk.c @@ -67,7 +67,7 @@ static int xbow_probe(nasid_t nasid) return -ENODEV; /* - * Okay, here's a xbow. Lets arbitrate and find + * Okay, here's a xbow. Let's arbitrate and find * out if we should initialize it. Set enabled * hub connected at highest or lowest widget as * master. diff --git a/arch/mips/sni/rm200.c b/arch/mips/sni/rm200.c index a046b302623e..160b88000b4b 100644 --- a/arch/mips/sni/rm200.c +++ b/arch/mips/sni/rm200.c @@ -263,7 +263,7 @@ spurious_8259A_irq: static int spurious_irq_mask; /* * At this point we can be sure the IRQ is spurious, - * lets ACK and report it. [once per IRQ] + * let's ACK and report it. [once per IRQ] */ if (!(spurious_irq_mask & irqmask)) { printk(KERN_DEBUG diff --git a/arch/mips/vdso/gettimeofday.c b/arch/mips/vdso/gettimeofday.c index ce89c9e294f9..e2690d7ca4dd 100644 --- a/arch/mips/vdso/gettimeofday.c +++ b/arch/mips/vdso/gettimeofday.c @@ -20,6 +20,48 @@ #include <asm/unistd.h> #include <asm/vdso.h> +#ifdef CONFIG_MIPS_CLOCK_VSYSCALL + +static __always_inline long gettimeofday_fallback(struct timeval *_tv, + struct timezone *_tz) +{ + register struct timezone *tz asm("a1") = _tz; + register struct timeval *tv asm("a0") = _tv; + register long ret asm("v0"); + register long nr asm("v0") = __NR_gettimeofday; + register long error asm("a3"); + + asm volatile( + " syscall\n" + : "=r" (ret), "=r" (error) + : "r" (tv), "r" (tz), "r" (nr) + : "$1", "$3", "$8", "$9", "$10", "$11", "$12", "$13", + "$14", "$15", "$24", "$25", "hi", "lo", "memory"); + + return error ? -ret : ret; +} + +#endif + +static __always_inline long clock_gettime_fallback(clockid_t _clkid, + struct timespec *_ts) +{ + register struct timespec *ts asm("a1") = _ts; + register clockid_t clkid asm("a0") = _clkid; + register long ret asm("v0"); + register long nr asm("v0") = __NR_clock_gettime; + register long error asm("a3"); + + asm volatile( + " syscall\n" + : "=r" (ret), "=r" (error) + : "r" (clkid), "r" (ts), "r" (nr) + : "$1", "$3", "$8", "$9", "$10", "$11", "$12", "$13", + "$14", "$15", "$24", "$25", "hi", "lo", "memory"); + + return error ? -ret : ret; +} + static __always_inline int do_realtime_coarse(struct timespec *ts, const union mips_vdso_data *data) { @@ -39,8 +81,8 @@ static __always_inline int do_monotonic_coarse(struct timespec *ts, const union mips_vdso_data *data) { u32 start_seq; - u32 to_mono_sec; - u32 to_mono_nsec; + u64 to_mono_sec; + u64 to_mono_nsec; do { start_seq = vdso_data_read_begin(data); @@ -148,8 +190,8 @@ static __always_inline int do_monotonic(struct timespec *ts, { u32 start_seq; u64 ns; - u32 to_mono_sec; - u32 to_mono_nsec; + u64 to_mono_sec; + u64 to_mono_nsec; do { start_seq = vdso_data_read_begin(data); @@ -187,7 +229,7 @@ int __vdso_gettimeofday(struct timeval *tv, struct timezone *tz) ret = do_realtime(&ts, data); if (ret) - return ret; + return gettimeofday_fallback(tv, tz); if (tv) { tv->tv_sec = ts.tv_sec; @@ -202,12 +244,12 @@ int __vdso_gettimeofday(struct timeval *tv, struct timezone *tz) return 0; } -#endif /* CONFIG_CLKSRC_MIPS_GIC */ +#endif /* CONFIG_MIPS_CLOCK_VSYSCALL */ int __vdso_clock_gettime(clockid_t clkid, struct timespec *ts) { const union mips_vdso_data *data = get_vdso_data(); - int ret; + int ret = -1; switch (clkid) { case CLOCK_REALTIME_COARSE: @@ -223,10 +265,11 @@ int __vdso_clock_gettime(clockid_t clkid, struct timespec *ts) ret = do_monotonic(ts, data); break; default: - ret = -ENOSYS; break; } - /* If we return -ENOSYS libc should fall back to a syscall. */ + if (ret) + ret = clock_gettime_fallback(clkid, ts); + return ret; } diff --git a/arch/mn10300/Kconfig b/arch/mn10300/Kconfig index 78ae5552fdb8..e5f4a197a7ea 100644 --- a/arch/mn10300/Kconfig +++ b/arch/mn10300/Kconfig @@ -1,5 +1,6 @@ config MN10300 def_bool y + select HAVE_EXIT_THREAD select HAVE_OPROFILE select HAVE_UID16 select GENERIC_IRQ_SHOW diff --git a/arch/mn10300/include/asm/fpu.h b/arch/mn10300/include/asm/fpu.h index 738ff72659d5..a47e995d45f3 100644 --- a/arch/mn10300/include/asm/fpu.h +++ b/arch/mn10300/include/asm/fpu.h @@ -76,11 +76,9 @@ static inline void unlazy_fpu(struct task_struct *tsk) preempt_enable(); } -static inline void exit_fpu(void) +static inline void exit_fpu(struct task_struct *tsk) { #ifdef CONFIG_LAZY_SAVE_FPU - struct task_struct *tsk = current; - preempt_disable(); if (fpu_state_owner == tsk) fpu_state_owner = NULL; @@ -123,7 +121,7 @@ static inline void fpu_init_state(void) {} static inline void fpu_save(struct fpu_state_struct *s) {} static inline void fpu_kill_state(struct task_struct *tsk) {} static inline void unlazy_fpu(struct task_struct *tsk) {} -static inline void exit_fpu(void) {} +static inline void exit_fpu(struct task_struct *tsk) {} static inline void flush_fpu(void) {} static inline int fpu_setup_sigcontext(struct fpucontext *buf) { return 0; } static inline int fpu_restore_sigcontext(struct fpucontext *buf) { return 0; } diff --git a/arch/mn10300/kernel/process.c b/arch/mn10300/kernel/process.c index 3707da583d05..cbede4e88dee 100644 --- a/arch/mn10300/kernel/process.c +++ b/arch/mn10300/kernel/process.c @@ -103,9 +103,9 @@ void show_regs(struct pt_regs *regs) /* * free current thread data structures etc.. */ -void exit_thread(void) +void exit_thread(struct task_struct *tsk) { - exit_fpu(); + exit_fpu(tsk); } void flush_thread(void) diff --git a/arch/mn10300/mm/misalignment.c b/arch/mn10300/mm/misalignment.c index b9920b1edd5a..70cef54dc40f 100644 --- a/arch/mn10300/mm/misalignment.c +++ b/arch/mn10300/mm/misalignment.c @@ -437,7 +437,7 @@ transfer_failed: info.si_signo = SIGSEGV; info.si_errno = 0; - info.si_code = 0; + info.si_code = SEGV_MAPERR; info.si_addr = (void *) regs->pc; force_sig_info(SIGSEGV, &info, current); return; diff --git a/arch/nios2/include/asm/processor.h b/arch/nios2/include/asm/processor.h index c2ba45c159c7..1c953f0cadbf 100644 --- a/arch/nios2/include/asm/processor.h +++ b/arch/nios2/include/asm/processor.h @@ -75,11 +75,6 @@ static inline void release_thread(struct task_struct *dead_task) { } -/* Free current thread data structures etc.. */ -static inline void exit_thread(void) -{ -} - /* Return saved PC of a blocked thread. */ #define thread_saved_pc(tsk) ((tsk)->thread.kregs->ea) diff --git a/arch/openrisc/include/asm/processor.h b/arch/openrisc/include/asm/processor.h index 4d235e3d2534..70334c9f7d24 100644 --- a/arch/openrisc/include/asm/processor.h +++ b/arch/openrisc/include/asm/processor.h @@ -85,15 +85,6 @@ void release_thread(struct task_struct *); unsigned long get_wchan(struct task_struct *p); /* - * Free current thread data structures etc.. - */ - -extern inline void exit_thread(void) -{ - /* Nothing needs to be done. */ -} - -/* * Return saved PC of a blocked thread. For now, this is the "user" PC */ extern unsigned long thread_saved_pc(struct task_struct *t); diff --git a/arch/openrisc/kernel/traps.c b/arch/openrisc/kernel/traps.c index 3d3f6062f49c..605a284922fb 100644 --- a/arch/openrisc/kernel/traps.c +++ b/arch/openrisc/kernel/traps.c @@ -302,12 +302,12 @@ asmlinkage void do_unaligned_access(struct pt_regs *regs, unsigned long address) siginfo_t info; if (user_mode(regs)) { - /* Send a SIGSEGV */ - info.si_signo = SIGSEGV; + /* Send a SIGBUS */ + info.si_signo = SIGBUS; info.si_errno = 0; - /* info.si_code has been set above */ - info.si_addr = (void *)address; - force_sig_info(SIGSEGV, &info, current); + info.si_code = BUS_ADRALN; + info.si_addr = (void __user *)address; + force_sig_info(SIGBUS, &info, current); } else { printk("KERNEL: Unaligned Access 0x%.8lx\n", address); show_registers(regs); diff --git a/arch/parisc/kernel/process.c b/arch/parisc/kernel/process.c index 809905a811ed..40639439d8b3 100644 --- a/arch/parisc/kernel/process.c +++ b/arch/parisc/kernel/process.c @@ -144,13 +144,6 @@ void machine_power_off(void) void (*pm_power_off)(void) = machine_power_off; EXPORT_SYMBOL(pm_power_off); -/* - * Free current thread data structures etc.. - */ -void exit_thread(void) -{ -} - void flush_thread(void) { /* Only needs to handle fpu stuff or perf monitors. diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index c628f47a9052..f3a47e9962c9 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -113,6 +113,7 @@ config PPC select HAVE_MEMBLOCK_NODE_MAP select HAVE_DMA_ATTRS select HAVE_DMA_API_DEBUG + select HAVE_EXIT_THREAD select HAVE_OPROFILE select HAVE_DEBUG_KMEMLEAK select ARCH_HAS_SG_CHAIN @@ -129,13 +130,14 @@ config PPC select IRQ_FORCED_THREADING select HAVE_RCU_TABLE_FREE if SMP select HAVE_SYSCALL_TRACEPOINTS - select HAVE_BPF_JIT + select HAVE_BPF_JIT if CPU_BIG_ENDIAN select HAVE_ARCH_JUMP_LABEL select ARCH_HAVE_NMI_SAFE_CMPXCHG select ARCH_HAS_GCOV_PROFILE_ALL select GENERIC_SMP_IDLE_THREAD select GENERIC_CMOS_UPDATE select GENERIC_TIME_VSYSCALL_OLD + select GENERIC_CPU_VULNERABILITIES if PPC_BOOK3S_64 select GENERIC_CLOCKEVENTS select GENERIC_CLOCKEVENTS_BROADCAST if SMP select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST diff --git a/arch/powerpc/include/asm/exception-64e.h b/arch/powerpc/include/asm/exception-64e.h index a703452d67b6..555e22d5e07f 100644 --- a/arch/powerpc/include/asm/exception-64e.h +++ b/arch/powerpc/include/asm/exception-64e.h @@ -209,5 +209,11 @@ exc_##label##_book3e: ori r3,r3,vector_offset@l; \ mtspr SPRN_IVOR##vector_number,r3; +#define RFI_TO_KERNEL \ + rfi + +#define RFI_TO_USER \ + rfi + #endif /* _ASM_POWERPC_EXCEPTION_64E_H */ diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h index 77f52b26dad6..9bddbec441b8 100644 --- a/arch/powerpc/include/asm/exception-64s.h +++ b/arch/powerpc/include/asm/exception-64s.h @@ -50,6 +50,59 @@ #define EX_PPR 88 /* SMT thread status register (priority) */ #define EX_CTR 96 +/* + * Macros for annotating the expected destination of (h)rfid + * + * The nop instructions allow us to insert one or more instructions to flush the + * L1-D cache when returning to userspace or a guest. + */ +#define RFI_FLUSH_SLOT \ + RFI_FLUSH_FIXUP_SECTION; \ + nop; \ + nop; \ + nop + +#define RFI_TO_KERNEL \ + rfid + +#define RFI_TO_USER \ + RFI_FLUSH_SLOT; \ + rfid; \ + b rfi_flush_fallback + +#define RFI_TO_USER_OR_KERNEL \ + RFI_FLUSH_SLOT; \ + rfid; \ + b rfi_flush_fallback + +#define RFI_TO_GUEST \ + RFI_FLUSH_SLOT; \ + rfid; \ + b rfi_flush_fallback + +#define HRFI_TO_KERNEL \ + hrfid + +#define HRFI_TO_USER \ + RFI_FLUSH_SLOT; \ + hrfid; \ + b hrfi_flush_fallback + +#define HRFI_TO_USER_OR_KERNEL \ + RFI_FLUSH_SLOT; \ + hrfid; \ + b hrfi_flush_fallback + +#define HRFI_TO_GUEST \ + RFI_FLUSH_SLOT; \ + hrfid; \ + b hrfi_flush_fallback + +#define HRFI_TO_UNKNOWN \ + RFI_FLUSH_SLOT; \ + hrfid; \ + b hrfi_flush_fallback + #ifdef CONFIG_RELOCATABLE #define __EXCEPTION_RELON_PROLOG_PSERIES_1(label, h) \ ld r12,PACAKBASE(r13); /* get high part of &label */ \ @@ -191,7 +244,7 @@ END_FTR_SECTION_NESTED(ftr,ftr,943) mtspr SPRN_##h##SRR0,r12; \ mfspr r12,SPRN_##h##SRR1; /* and SRR1 */ \ mtspr SPRN_##h##SRR1,r10; \ - h##rfid; \ + h##RFI_TO_KERNEL; \ b . /* prevent speculative execution */ #define EXCEPTION_PROLOG_PSERIES_1(label, h) \ __EXCEPTION_PROLOG_PSERIES_1(label, h) diff --git a/arch/powerpc/include/asm/feature-fixups.h b/arch/powerpc/include/asm/feature-fixups.h index 9a67a38bf7b9..7068bafbb2d6 100644 --- a/arch/powerpc/include/asm/feature-fixups.h +++ b/arch/powerpc/include/asm/feature-fixups.h @@ -184,4 +184,19 @@ label##3: \ FTR_ENTRY_OFFSET label##1b-label##3b; \ .popsection; +#define RFI_FLUSH_FIXUP_SECTION \ +951: \ + .pushsection __rfi_flush_fixup,"a"; \ + .align 2; \ +952: \ + FTR_ENTRY_OFFSET 951b-952b; \ + .popsection; + + +#ifndef __ASSEMBLY__ + +extern long __start___rfi_flush_fixup, __stop___rfi_flush_fixup; + +#endif + #endif /* __ASM_POWERPC_FEATURE_FIXUPS_H */ diff --git a/arch/powerpc/include/asm/hvcall.h b/arch/powerpc/include/asm/hvcall.h index 85bc8c0d257b..449bbb87c257 100644 --- a/arch/powerpc/include/asm/hvcall.h +++ b/arch/powerpc/include/asm/hvcall.h @@ -239,6 +239,7 @@ #define H_GET_HCA_INFO 0x1B8 #define H_GET_PERF_COUNT 0x1BC #define H_MANAGE_TRACE 0x1C0 +#define H_GET_CPU_CHARACTERISTICS 0x1C8 #define H_FREE_LOGICAL_LAN_BUFFER 0x1D4 #define H_QUERY_INT_STATE 0x1E4 #define H_POLL_PENDING 0x1D8 @@ -285,7 +286,19 @@ #define H_SET_MODE_RESOURCE_ADDR_TRANS_MODE 3 #define H_SET_MODE_RESOURCE_LE 4 +/* H_GET_CPU_CHARACTERISTICS return values */ +#define H_CPU_CHAR_SPEC_BAR_ORI31 (1ull << 63) // IBM bit 0 +#define H_CPU_CHAR_BCCTRL_SERIALISED (1ull << 62) // IBM bit 1 +#define H_CPU_CHAR_L1D_FLUSH_ORI30 (1ull << 61) // IBM bit 2 +#define H_CPU_CHAR_L1D_FLUSH_TRIG2 (1ull << 60) // IBM bit 3 +#define H_CPU_CHAR_L1D_THREAD_PRIV (1ull << 59) // IBM bit 4 + +#define H_CPU_BEHAV_FAVOUR_SECURITY (1ull << 63) // IBM bit 0 +#define H_CPU_BEHAV_L1D_FLUSH_PR (1ull << 62) // IBM bit 1 +#define H_CPU_BEHAV_BNDS_CHK_SPEC_BAR (1ull << 61) // IBM bit 2 + #ifndef __ASSEMBLY__ +#include <linux/types.h> /** * plpar_hcall_norets: - Make a pseries hypervisor call with no return arguments @@ -423,6 +436,11 @@ extern long pseries_big_endian_exceptions(void); #endif /* CONFIG_PPC_PSERIES */ +struct h_cpu_char_result { + u64 character; + u64 behaviour; +}; + #endif /* __ASSEMBLY__ */ #endif /* __KERNEL__ */ #endif /* _ASM_POWERPC_HVCALL_H */ diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h index 70bd4381f8e6..45e2aefece16 100644 --- a/arch/powerpc/include/asm/paca.h +++ b/arch/powerpc/include/asm/paca.h @@ -192,6 +192,16 @@ struct paca_struct { #endif struct kvmppc_host_state kvm_hstate; #endif +#ifdef CONFIG_PPC_BOOK3S_64 + /* + * rfi fallback flush must be in its own cacheline to prevent + * other paca data leaking into the L1d + */ + u64 exrfi[13] __aligned(0x80); + void *rfi_flush_fallback_area; + u64 l1d_flush_congruence; + u64 l1d_flush_sets; +#endif }; extern struct paca_struct *paca; diff --git a/arch/powerpc/include/asm/plpar_wrappers.h b/arch/powerpc/include/asm/plpar_wrappers.h index 67859edbf8fd..6e05cb397a5c 100644 --- a/arch/powerpc/include/asm/plpar_wrappers.h +++ b/arch/powerpc/include/asm/plpar_wrappers.h @@ -323,4 +323,18 @@ static inline long plapr_set_watchpoint0(unsigned long dawr0, unsigned long dawr return plpar_set_mode(0, H_SET_MODE_RESOURCE_SET_DAWR, dawr0, dawrx0); } +static inline long plpar_get_cpu_characteristics(struct h_cpu_char_result *p) +{ + unsigned long retbuf[PLPAR_HCALL_BUFSIZE]; + long rc; + + rc = plpar_hcall(H_GET_CPU_CHARACTERISTICS, retbuf); + if (rc == H_SUCCESS) { + p->character = retbuf[0]; + p->behaviour = retbuf[1]; + } + + return rc; +} + #endif /* _ASM_POWERPC_PLPAR_WRAPPERS_H */ diff --git a/arch/powerpc/include/asm/ppc_asm.h b/arch/powerpc/include/asm/ppc_asm.h index dd0fc18d8103..160bb2311bbb 100644 --- a/arch/powerpc/include/asm/ppc_asm.h +++ b/arch/powerpc/include/asm/ppc_asm.h @@ -224,6 +224,16 @@ name: \ .globl name; \ name: +#define _KPROBE_TOC(name) \ + .section ".kprobes.text","a"; \ + .align 2 ; \ + .type name,@function; \ + .globl name; \ +name: \ +0: addis r2,r12,(.TOC.-0b)@ha; \ + addi r2,r2,(.TOC.-0b)@l; \ + .localentry name,.-name + #define DOTSYM(a) a #else @@ -261,6 +271,8 @@ name: \ .type GLUE(.,name),@function; \ GLUE(.,name): +#define _KPROBE_TOC(n) _KPROBE(n) + #define DOTSYM(a) GLUE(.,a) #endif diff --git a/arch/powerpc/include/asm/setup.h b/arch/powerpc/include/asm/setup.h index e9d384cbd021..7916b56f2e60 100644 --- a/arch/powerpc/include/asm/setup.h +++ b/arch/powerpc/include/asm/setup.h @@ -26,6 +26,19 @@ void initmem_init(void); void setup_panic(void); #define ARCH_PANIC_TIMEOUT 180 +void rfi_flush_enable(bool enable); + +/* These are bit flags */ +enum l1d_flush_type { + L1D_FLUSH_NONE = 0x1, + L1D_FLUSH_FALLBACK = 0x2, + L1D_FLUSH_ORI = 0x4, + L1D_FLUSH_MTTRIG = 0x8, +}; + +void __init setup_rfi_flush(enum l1d_flush_type, bool enable); +void do_rfi_flush_fixups(enum l1d_flush_type types); + #endif /* !__ASSEMBLY__ */ #endif /* _ASM_POWERPC_SETUP_H */ diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index 40da69163d51..d92705e3a0c1 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -243,6 +243,10 @@ int main(void) #ifdef CONFIG_PPC_BOOK3S_64 DEFINE(PACAMCEMERGSP, offsetof(struct paca_struct, mc_emergency_sp)); DEFINE(PACA_IN_MCE, offsetof(struct paca_struct, in_mce)); + DEFINE(PACA_RFI_FLUSH_FALLBACK_AREA, offsetof(struct paca_struct, rfi_flush_fallback_area)); + DEFINE(PACA_EXRFI, offsetof(struct paca_struct, exrfi)); + DEFINE(PACA_L1D_FLUSH_CONGRUENCE, offsetof(struct paca_struct, l1d_flush_congruence)); + DEFINE(PACA_L1D_FLUSH_SETS, offsetof(struct paca_struct, l1d_flush_sets)); #endif DEFINE(PACAHWCPUID, offsetof(struct paca_struct, hw_cpu_id)); DEFINE(PACAKEXECSTATE, offsetof(struct paca_struct, kexec_state)); diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index f6fd0332c3a2..2837232bbffb 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -36,6 +36,11 @@ #include <asm/hw_irq.h> #include <asm/context_tracking.h> #include <asm/tm.h> +#ifdef CONFIG_PPC_BOOK3S +#include <asm/exception-64s.h> +#else +#include <asm/exception-64e.h> +#endif /* * System calls. @@ -225,13 +230,23 @@ END_FTR_SECTION_IFCLR(CPU_FTR_STCX_CHECKS_ADDRESS) ACCOUNT_CPU_USER_EXIT(r11, r12) HMT_MEDIUM_LOW_HAS_PPR ld r13,GPR13(r1) /* only restore r13 if returning to usermode */ + ld r2,GPR2(r1) + ld r1,GPR1(r1) + mtlr r4 + mtcr r5 + mtspr SPRN_SRR0,r7 + mtspr SPRN_SRR1,r8 + RFI_TO_USER + b . /* prevent speculative execution */ + + /* exit to kernel */ 1: ld r2,GPR2(r1) ld r1,GPR1(r1) mtlr r4 mtcr r5 mtspr SPRN_SRR0,r7 mtspr SPRN_SRR1,r8 - RFI + RFI_TO_KERNEL b . /* prevent speculative execution */ syscall_error: @@ -353,8 +368,7 @@ tabort_syscall: mtmsrd r10, 1 mtspr SPRN_SRR0, r11 mtspr SPRN_SRR1, r12 - - rfid + RFI_TO_USER b . /* prevent speculative execution */ #endif @@ -887,7 +901,7 @@ BEGIN_FTR_SECTION END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) ACCOUNT_CPU_USER_EXIT(r2, r4) REST_GPR(13, r1) -1: + mtspr SPRN_SRR1,r3 ld r2,_CCR(r1) @@ -900,8 +914,22 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) ld r3,GPR3(r1) ld r4,GPR4(r1) ld r1,GPR1(r1) + RFI_TO_USER + b . /* prevent speculative execution */ - rfid +1: mtspr SPRN_SRR1,r3 + + ld r2,_CCR(r1) + mtcrf 0xFF,r2 + ld r2,_NIP(r1) + mtspr SPRN_SRR0,r2 + + ld r0,GPR0(r1) + ld r2,GPR2(r1) + ld r3,GPR3(r1) + ld r4,GPR4(r1) + ld r1,GPR1(r1) + RFI_TO_KERNEL b . /* prevent speculative execution */ #endif /* CONFIG_PPC_BOOK3E */ @@ -1077,7 +1105,7 @@ _GLOBAL(enter_rtas) mtspr SPRN_SRR0,r5 mtspr SPRN_SRR1,r6 - rfid + RFI_TO_KERNEL b . /* prevent speculative execution */ rtas_return_loc: @@ -1102,7 +1130,7 @@ rtas_return_loc: mtspr SPRN_SRR0,r3 mtspr SPRN_SRR1,r4 - rfid + RFI_TO_KERNEL b . /* prevent speculative execution */ .align 3 @@ -1173,7 +1201,7 @@ _GLOBAL(enter_prom) LOAD_REG_IMMEDIATE(r12, MSR_SF | MSR_ISF | MSR_LE) andc r11,r11,r12 mtsrr1 r11 - rfid + RFI_TO_KERNEL #endif /* CONFIG_PPC_BOOK3E */ 1: /* Return from OF */ diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index b81ccc5fb32d..938a30fef031 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -46,7 +46,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_REAL_LE) \ mtspr SPRN_SRR0,r10 ; \ ld r10,PACAKMSR(r13) ; \ mtspr SPRN_SRR1,r10 ; \ - rfid ; \ + RFI_TO_KERNEL ; \ b . ; /* prevent speculative execution */ #define SYSCALL_PSERIES_3 \ @@ -54,7 +54,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_REAL_LE) \ 1: mfspr r12,SPRN_SRR1 ; \ xori r12,r12,MSR_LE ; \ mtspr SPRN_SRR1,r12 ; \ - rfid ; /* return to userspace */ \ + RFI_TO_USER ; /* return to userspace */ \ b . ; /* prevent speculative execution */ #if defined(CONFIG_RELOCATABLE) @@ -507,7 +507,7 @@ BEGIN_FTR_SECTION LOAD_HANDLER(r12, machine_check_handle_early) 1: mtspr SPRN_SRR0,r12 mtspr SPRN_SRR1,r11 - rfid + RFI_TO_KERNEL b . /* prevent speculative execution */ 2: /* Stack overflow. Stay on emergency stack and panic. @@ -601,7 +601,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_CFAR) ld r11,PACA_EXGEN+EX_R11(r13) ld r12,PACA_EXGEN+EX_R12(r13) ld r13,PACA_EXGEN+EX_R13(r13) - HRFID + HRFI_TO_UNKNOWN b . #endif @@ -666,7 +666,7 @@ masked_##_H##interrupt: \ ld r10,PACA_EXGEN+EX_R10(r13); \ ld r11,PACA_EXGEN+EX_R11(r13); \ GET_SCRATCH0(r13); \ - ##_H##rfid; \ + ##_H##RFI_TO_KERNEL; \ b . MASKED_INTERRUPT() @@ -756,7 +756,7 @@ kvmppc_skip_interrupt: addi r13, r13, 4 mtspr SPRN_SRR0, r13 GET_SCRATCH0(r13) - rfid + RFI_TO_KERNEL b . kvmppc_skip_Hinterrupt: @@ -768,7 +768,7 @@ kvmppc_skip_Hinterrupt: addi r13, r13, 4 mtspr SPRN_HSRR0, r13 GET_SCRATCH0(r13) - hrfid + HRFI_TO_KERNEL b . #endif @@ -1439,7 +1439,7 @@ machine_check_handle_early: li r3,MSR_ME andc r10,r10,r3 /* Turn off MSR_ME */ mtspr SPRN_SRR1,r10 - rfid + RFI_TO_KERNEL b . 2: /* @@ -1457,7 +1457,7 @@ machine_check_handle_early: */ bl machine_check_queue_event MACHINE_CHECK_HANDLER_WINDUP - rfid + RFI_TO_USER_OR_KERNEL 9: /* Deliver the machine check to host kernel in V mode. */ MACHINE_CHECK_HANDLER_WINDUP @@ -1503,6 +1503,8 @@ slb_miss_realmode: andi. r10,r12,MSR_RI /* check for unrecoverable exception */ beq- 2f + andi. r10,r12,MSR_PR /* check for user mode (PR != 0) */ + bne 1f .machine push .machine "power4" @@ -1516,7 +1518,23 @@ slb_miss_realmode: ld r11,PACA_EXSLB+EX_R11(r13) ld r12,PACA_EXSLB+EX_R12(r13) ld r13,PACA_EXSLB+EX_R13(r13) - rfid + RFI_TO_KERNEL + b . /* prevent speculative execution */ + +1: +.machine push +.machine "power4" + mtcrf 0x80,r9 + mtcrf 0x01,r9 /* slb_allocate uses cr0 and cr7 */ +.machine pop + + RESTORE_PPR_PACA(PACA_EXSLB, r9) + ld r9,PACA_EXSLB+EX_R9(r13) + ld r10,PACA_EXSLB+EX_R10(r13) + ld r11,PACA_EXSLB+EX_R11(r13) + ld r12,PACA_EXSLB+EX_R12(r13) + ld r13,PACA_EXSLB+EX_R13(r13) + RFI_TO_USER b . /* prevent speculative execution */ 2: mfspr r11,SPRN_SRR0 @@ -1525,7 +1543,7 @@ slb_miss_realmode: mtspr SPRN_SRR0,r10 ld r10,PACAKMSR(r13) mtspr SPRN_SRR1,r10 - rfid + RFI_TO_KERNEL b . unrecov_slb: @@ -1546,6 +1564,92 @@ power4_fixup_nap: blr #endif + .globl rfi_flush_fallback +rfi_flush_fallback: + SET_SCRATCH0(r13); + GET_PACA(r13); + std r9,PACA_EXRFI+EX_R9(r13) + std r10,PACA_EXRFI+EX_R10(r13) + std r11,PACA_EXRFI+EX_R11(r13) + std r12,PACA_EXRFI+EX_R12(r13) + std r8,PACA_EXRFI+EX_R13(r13) + mfctr r9 + ld r10,PACA_RFI_FLUSH_FALLBACK_AREA(r13) + ld r11,PACA_L1D_FLUSH_SETS(r13) + ld r12,PACA_L1D_FLUSH_CONGRUENCE(r13) + /* + * The load adresses are at staggered offsets within cachelines, + * which suits some pipelines better (on others it should not + * hurt). + */ + addi r12,r12,8 + mtctr r11 + DCBT_STOP_ALL_STREAM_IDS(r11) /* Stop prefetch streams */ + + /* order ld/st prior to dcbt stop all streams with flushing */ + sync +1: li r8,0 + .rept 8 /* 8-way set associative */ + ldx r11,r10,r8 + add r8,r8,r12 + xor r11,r11,r11 // Ensure r11 is 0 even if fallback area is not + add r8,r8,r11 // Add 0, this creates a dependency on the ldx + .endr + addi r10,r10,128 /* 128 byte cache line */ + bdnz 1b + + mtctr r9 + ld r9,PACA_EXRFI+EX_R9(r13) + ld r10,PACA_EXRFI+EX_R10(r13) + ld r11,PACA_EXRFI+EX_R11(r13) + ld r12,PACA_EXRFI+EX_R12(r13) + ld r8,PACA_EXRFI+EX_R13(r13) + GET_SCRATCH0(r13); + rfid + + .globl hrfi_flush_fallback +hrfi_flush_fallback: + SET_SCRATCH0(r13); + GET_PACA(r13); + std r9,PACA_EXRFI+EX_R9(r13) + std r10,PACA_EXRFI+EX_R10(r13) + std r11,PACA_EXRFI+EX_R11(r13) + std r12,PACA_EXRFI+EX_R12(r13) + std r8,PACA_EXRFI+EX_R13(r13) + mfctr r9 + ld r10,PACA_RFI_FLUSH_FALLBACK_AREA(r13) + ld r11,PACA_L1D_FLUSH_SETS(r13) + ld r12,PACA_L1D_FLUSH_CONGRUENCE(r13) + /* + * The load adresses are at staggered offsets within cachelines, + * which suits some pipelines better (on others it should not + * hurt). + */ + addi r12,r12,8 + mtctr r11 + DCBT_STOP_ALL_STREAM_IDS(r11) /* Stop prefetch streams */ + + /* order ld/st prior to dcbt stop all streams with flushing */ + sync +1: li r8,0 + .rept 8 /* 8-way set associative */ + ldx r11,r10,r8 + add r8,r8,r12 + xor r11,r11,r11 // Ensure r11 is 0 even if fallback area is not + add r8,r8,r11 // Add 0, this creates a dependency on the ldx + .endr + addi r10,r10,128 /* 128 byte cache line */ + bdnz 1b + + mtctr r9 + ld r9,PACA_EXRFI+EX_R9(r13) + ld r10,PACA_EXRFI+EX_R10(r13) + ld r11,PACA_EXRFI+EX_R11(r13) + ld r12,PACA_EXRFI+EX_R12(r13) + ld r8,PACA_EXRFI+EX_R13(r13) + GET_SCRATCH0(r13); + hrfid + /* * Hash table stuff */ diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S index db475d41b57a..107588295b39 100644 --- a/arch/powerpc/kernel/misc_64.S +++ b/arch/powerpc/kernel/misc_64.S @@ -66,7 +66,7 @@ PPC64_CACHES: * flush all bytes from start through stop-1 inclusive */ -_KPROBE(flush_icache_range) +_KPROBE_TOC(flush_icache_range) BEGIN_FTR_SECTION PURGE_PREFETCHED_INS blr @@ -117,7 +117,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE) * * flush all bytes from start to stop-1 inclusive */ -_GLOBAL(flush_dcache_range) +_GLOBAL_TOC(flush_dcache_range) /* * Flush the data cache to memory @@ -701,31 +701,3 @@ _GLOBAL(kexec_sequence) li r5,0 blr /* image->start(physid, image->start, 0); */ #endif /* CONFIG_KEXEC */ - -#ifdef CONFIG_MODULES -#if defined(_CALL_ELF) && _CALL_ELF == 2 - -#ifdef CONFIG_MODVERSIONS -.weak __crc_TOC. -.section "___kcrctab+TOC.","a" -.globl __kcrctab_TOC. -__kcrctab_TOC.: - .llong __crc_TOC. -#endif - -/* - * Export a fake .TOC. since both modpost and depmod will complain otherwise. - * Both modpost and depmod strip the leading . so we do the same here. - */ -.section "__ksymtab_strings","a" -__kstrtab_TOC.: - .asciz "TOC." - -.section "___ksymtab+TOC.","a" -/* This symbol name is important: it's used by modpost to find exported syms */ -.globl __ksymtab_TOC. -__ksymtab_TOC.: - .llong 0 /* .value */ - .llong __kstrtab_TOC. -#endif /* ELFv2 */ -#endif /* MODULES */ diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c index e4f7d4eed20c..08b7a40de5f8 100644 --- a/arch/powerpc/kernel/module_64.c +++ b/arch/powerpc/kernel/module_64.c @@ -326,7 +326,10 @@ static void dedotify_versions(struct modversion_info *vers, } } -/* Undefined symbols which refer to .funcname, hack to funcname (or .TOC.) */ +/* + * Undefined symbols which refer to .funcname, hack to funcname. Make .TOC. + * seem to be defined (value set later). + */ static void dedotify(Elf64_Sym *syms, unsigned int numsyms, char *strtab) { unsigned int i; @@ -334,8 +337,11 @@ static void dedotify(Elf64_Sym *syms, unsigned int numsyms, char *strtab) for (i = 1; i < numsyms; i++) { if (syms[i].st_shndx == SHN_UNDEF) { char *name = strtab + syms[i].st_name; - if (name[0] == '.') + if (name[0] == '.') { + if (strcmp(name+1, "TOC.") == 0) + syms[i].st_shndx = SHN_ABS; syms[i].st_name++; + } } } } @@ -351,7 +357,7 @@ static Elf64_Sym *find_dot_toc(Elf64_Shdr *sechdrs, numsyms = sechdrs[symindex].sh_size / sizeof(Elf64_Sym); for (i = 1; i < numsyms; i++) { - if (syms[i].st_shndx == SHN_UNDEF + if (syms[i].st_shndx == SHN_ABS && strcmp(strtab + syms[i].st_name, "TOC.") == 0) return &syms[i]; } diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index b7abf3cd2a67..ef5f566f3977 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -209,7 +209,8 @@ void enable_kernel_vsx(void) WARN_ON(preemptible()); #ifdef CONFIG_SMP - if (current->thread.regs && (current->thread.regs->msr & MSR_VSX)) + if (current->thread.regs && + (current->thread.regs->msr & (MSR_VSX|MSR_VEC|MSR_FP))) giveup_vsx(current); else giveup_vsx(NULL); /* just enable vsx for kernel - force */ @@ -231,7 +232,7 @@ void flush_vsx_to_thread(struct task_struct *tsk) { if (tsk->thread.regs) { preempt_disable(); - if (tsk->thread.regs->msr & MSR_VSX) { + if (tsk->thread.regs->msr & (MSR_VSX|MSR_VEC|MSR_FP)) { #ifdef CONFIG_SMP BUG_ON(tsk != current); #endif diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index a20823210ac0..df4a87eb8da4 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -38,6 +38,7 @@ #include <linux/hugetlb.h> #include <linux/memory.h> #include <linux/nmi.h> +#include <linux/debugfs.h> #include <asm/io.h> #include <asm/kdump.h> @@ -834,4 +835,142 @@ static int __init disable_hardlockup_detector(void) return 0; } early_initcall(disable_hardlockup_detector); + +#ifdef CONFIG_PPC_BOOK3S_64 +static enum l1d_flush_type enabled_flush_types; +static void *l1d_flush_fallback_area; +static bool no_rfi_flush; +bool rfi_flush; + +static int __init handle_no_rfi_flush(char *p) +{ + pr_info("rfi-flush: disabled on command line."); + no_rfi_flush = true; + return 0; +} +early_param("no_rfi_flush", handle_no_rfi_flush); + +/* + * The RFI flush is not KPTI, but because users will see doco that says to use + * nopti we hijack that option here to also disable the RFI flush. + */ +static int __init handle_no_pti(char *p) +{ + pr_info("rfi-flush: disabling due to 'nopti' on command line.\n"); + handle_no_rfi_flush(NULL); + return 0; +} +early_param("nopti", handle_no_pti); + +static void do_nothing(void *unused) +{ + /* + * We don't need to do the flush explicitly, just enter+exit kernel is + * sufficient, the RFI exit handlers will do the right thing. + */ +} + +void rfi_flush_enable(bool enable) +{ + if (rfi_flush == enable) + return; + + if (enable) { + do_rfi_flush_fixups(enabled_flush_types); + on_each_cpu(do_nothing, NULL, 1); + } else + do_rfi_flush_fixups(L1D_FLUSH_NONE); + + rfi_flush = enable; +} + +static void init_fallback_flush(void) +{ + u64 l1d_size, limit; + int cpu; + + l1d_size = ppc64_caches.dsize; + limit = min(safe_stack_limit(), ppc64_rma_size); + + /* + * Align to L1d size, and size it at 2x L1d size, to catch possible + * hardware prefetch runoff. We don't have a recipe for load patterns to + * reliably avoid the prefetcher. + */ + l1d_flush_fallback_area = __va(memblock_alloc_base(l1d_size * 2, l1d_size, limit)); + memset(l1d_flush_fallback_area, 0, l1d_size * 2); + + for_each_possible_cpu(cpu) { + /* + * The fallback flush is currently coded for 8-way + * associativity. Different associativity is possible, but it + * will be treated as 8-way and may not evict the lines as + * effectively. + * + * 128 byte lines are mandatory. + */ + u64 c = l1d_size / 8; + + paca[cpu].rfi_flush_fallback_area = l1d_flush_fallback_area; + paca[cpu].l1d_flush_congruence = c; + paca[cpu].l1d_flush_sets = c / 128; + } +} + +void __init setup_rfi_flush(enum l1d_flush_type types, bool enable) +{ + if (types & L1D_FLUSH_FALLBACK) { + pr_info("rfi-flush: Using fallback displacement flush\n"); + init_fallback_flush(); + } + + if (types & L1D_FLUSH_ORI) + pr_info("rfi-flush: Using ori type flush\n"); + + if (types & L1D_FLUSH_MTTRIG) + pr_info("rfi-flush: Using mttrig type flush\n"); + + enabled_flush_types = types; + + if (!no_rfi_flush) + rfi_flush_enable(enable); +} + +#ifdef CONFIG_DEBUG_FS +static int rfi_flush_set(void *data, u64 val) +{ + if (val == 1) + rfi_flush_enable(true); + else if (val == 0) + rfi_flush_enable(false); + else + return -EINVAL; + + return 0; +} + +static int rfi_flush_get(void *data, u64 *val) +{ + *val = rfi_flush ? 1 : 0; + return 0; +} + +DEFINE_SIMPLE_ATTRIBUTE(fops_rfi_flush, rfi_flush_get, rfi_flush_set, "%llu\n"); + +static __init int rfi_flush_debugfs_init(void) +{ + debugfs_create_file("rfi_flush", 0600, powerpc_debugfs_root, NULL, &fops_rfi_flush); + return 0; +} +device_initcall(rfi_flush_debugfs_init); +#endif + +ssize_t cpu_show_meltdown(struct device *dev, struct device_attribute *attr, char *buf) +{ + if (rfi_flush) + return sprintf(buf, "Mitigation: RFI Flush\n"); + + return sprintf(buf, "Vulnerable\n"); +} +#endif /* CONFIG_PPC_BOOK3S_64 */ #endif diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S index 2dd91f79de05..30f90e8f5dd6 100644 --- a/arch/powerpc/kernel/vmlinux.lds.S +++ b/arch/powerpc/kernel/vmlinux.lds.S @@ -73,6 +73,15 @@ SECTIONS /* Read-only data */ RODATA +#ifdef CONFIG_PPC64 + . = ALIGN(8); + __rfi_flush_fixup : AT(ADDR(__rfi_flush_fixup) - LOAD_OFFSET) { + __start___rfi_flush_fixup = .; + *(__rfi_flush_fixup) + __stop___rfi_flush_fixup = .; + } +#endif + EXCEPTION_TABLE(0) NOTES :kernel :notes diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index ffab9269bfe4..4463718ae614 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -64,7 +64,7 @@ _GLOBAL_TOC(kvmppc_hv_entry_trampoline) mtmsrd r0,1 /* clear RI in MSR */ mtsrr0 r5 mtsrr1 r6 - RFI + RFI_TO_KERNEL kvmppc_call_hv_entry: ld r4, HSTATE_KVM_VCPU(r13) @@ -170,7 +170,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) mtsrr0 r8 mtsrr1 r7 beq cr1, 13f /* machine check */ - RFI + RFI_TO_KERNEL /* On POWER7, we have external interrupts set to use HSRR0/1 */ 11: mtspr SPRN_HSRR0, r8 @@ -965,8 +965,7 @@ BEGIN_FTR_SECTION END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) ld r0, VCPU_GPR(R0)(r4) ld r4, VCPU_GPR(R4)(r4) - - hrfid + HRFI_TO_GUEST b . secondary_too_late: diff --git a/arch/powerpc/kvm/book3s_rmhandlers.S b/arch/powerpc/kvm/book3s_rmhandlers.S index 16c4d88ba27d..a328f99a887c 100644 --- a/arch/powerpc/kvm/book3s_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_rmhandlers.S @@ -46,6 +46,9 @@ #define FUNC(name) name +#define RFI_TO_KERNEL RFI +#define RFI_TO_GUEST RFI + .macro INTERRUPT_TRAMPOLINE intno .global kvmppc_trampoline_\intno @@ -141,7 +144,7 @@ kvmppc_handler_skip_ins: GET_SCRATCH0(r13) /* And get back into the code */ - RFI + RFI_TO_KERNEL #endif /* @@ -164,6 +167,6 @@ _GLOBAL_TOC(kvmppc_entry_trampoline) ori r5, r5, MSR_EE mtsrr0 r7 mtsrr1 r6 - RFI + RFI_TO_KERNEL #include "book3s_segment.S" diff --git a/arch/powerpc/kvm/book3s_segment.S b/arch/powerpc/kvm/book3s_segment.S index ca8f174289bb..7c982956d709 100644 --- a/arch/powerpc/kvm/book3s_segment.S +++ b/arch/powerpc/kvm/book3s_segment.S @@ -156,7 +156,7 @@ no_dcbz32_on: PPC_LL r9, SVCPU_R9(r3) PPC_LL r3, (SVCPU_R3)(r3) - RFI + RFI_TO_GUEST kvmppc_handler_trampoline_enter_end: @@ -389,5 +389,5 @@ END_FTR_SECTION_IFSET(CPU_FTR_HVMODE) cmpwi r12, BOOK3S_INTERRUPT_DOORBELL beqa BOOK3S_INTERRUPT_DOORBELL - RFI + RFI_TO_KERNEL kvmppc_handler_trampoline_exit_end: diff --git a/arch/powerpc/lib/feature-fixups.c b/arch/powerpc/lib/feature-fixups.c index 7ce3870d7ddd..a18d648d31a6 100644 --- a/arch/powerpc/lib/feature-fixups.c +++ b/arch/powerpc/lib/feature-fixups.c @@ -20,6 +20,7 @@ #include <asm/code-patching.h> #include <asm/page.h> #include <asm/sections.h> +#include <asm/setup.h> struct fixup_entry { @@ -113,6 +114,47 @@ void do_feature_fixups(unsigned long value, void *fixup_start, void *fixup_end) } } +#ifdef CONFIG_PPC_BOOK3S_64 +void do_rfi_flush_fixups(enum l1d_flush_type types) +{ + unsigned int instrs[3], *dest; + long *start, *end; + int i; + + start = PTRRELOC(&__start___rfi_flush_fixup), + end = PTRRELOC(&__stop___rfi_flush_fixup); + + instrs[0] = 0x60000000; /* nop */ + instrs[1] = 0x60000000; /* nop */ + instrs[2] = 0x60000000; /* nop */ + + if (types & L1D_FLUSH_FALLBACK) + /* b .+16 to fallback flush */ + instrs[0] = 0x48000010; + + i = 0; + if (types & L1D_FLUSH_ORI) { + instrs[i++] = 0x63ff0000; /* ori 31,31,0 speculation barrier */ + instrs[i++] = 0x63de0000; /* ori 30,30,0 L1d flush*/ + } + + if (types & L1D_FLUSH_MTTRIG) + instrs[i++] = 0x7c12dba6; /* mtspr TRIG2,r0 (SPR #882) */ + + for (i = 0; start < end; start++, i++) { + dest = (void *)start + *start; + + pr_devel("patching dest %lx\n", (unsigned long)dest); + + patch_instruction(dest, instrs[0]); + patch_instruction(dest + 1, instrs[1]); + patch_instruction(dest + 2, instrs[2]); + } + + printk(KERN_DEBUG "rfi-flush: patched %d locations\n", i); +} +#endif /* CONFIG_PPC_BOOK3S_64 */ + void do_lwsync_fixups(unsigned long value, void *fixup_start, void *fixup_end) { long *start, *end; diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c index f48afc06ba14..30c6b3b7be90 100644 --- a/arch/powerpc/platforms/powernv/setup.c +++ b/arch/powerpc/platforms/powernv/setup.c @@ -35,13 +35,63 @@ #include <asm/opal.h> #include <asm/kexec.h> #include <asm/smp.h> +#include <asm/tm.h> +#include <asm/setup.h> #include "powernv.h" +static void pnv_setup_rfi_flush(void) +{ + struct device_node *np, *fw_features; + enum l1d_flush_type type; + int enable; + + /* Default to fallback in case fw-features are not available */ + type = L1D_FLUSH_FALLBACK; + enable = 1; + + np = of_find_node_by_name(NULL, "ibm,opal"); + fw_features = of_get_child_by_name(np, "fw-features"); + of_node_put(np); + + if (fw_features) { + np = of_get_child_by_name(fw_features, "inst-l1d-flush-trig2"); + if (np && of_property_read_bool(np, "enabled")) + type = L1D_FLUSH_MTTRIG; + + of_node_put(np); + + np = of_get_child_by_name(fw_features, "inst-l1d-flush-ori30,30,0"); + if (np && of_property_read_bool(np, "enabled")) + type = L1D_FLUSH_ORI; + + of_node_put(np); + + /* Enable unless firmware says NOT to */ + enable = 2; + np = of_get_child_by_name(fw_features, "needs-l1d-flush-msr-hv-1-to-0"); + if (np && of_property_read_bool(np, "disabled")) + enable--; + + of_node_put(np); + + np = of_get_child_by_name(fw_features, "needs-l1d-flush-msr-pr-0-to-1"); + if (np && of_property_read_bool(np, "disabled")) + enable--; + + of_node_put(np); + of_node_put(fw_features); + } + + setup_rfi_flush(type, enable > 0); +} + static void __init pnv_setup_arch(void) { set_arch_panic_timeout(10, ARCH_PANIC_TIMEOUT); + pnv_setup_rfi_flush(); + /* Initialize SMP */ pnv_smp_init(); diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index 36df46eaba24..dd2545fc9947 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -499,6 +499,39 @@ static void __init find_and_init_phbs(void) of_pci_check_probe_only(); } +static void pseries_setup_rfi_flush(void) +{ + struct h_cpu_char_result result; + enum l1d_flush_type types; + bool enable; + long rc; + + /* Enable by default */ + enable = true; + + rc = plpar_get_cpu_characteristics(&result); + if (rc == H_SUCCESS) { + types = L1D_FLUSH_NONE; + + if (result.character & H_CPU_CHAR_L1D_FLUSH_TRIG2) + types |= L1D_FLUSH_MTTRIG; + if (result.character & H_CPU_CHAR_L1D_FLUSH_ORI30) + types |= L1D_FLUSH_ORI; + + /* Use fallback if nothing set in hcall */ + if (types == L1D_FLUSH_NONE) + types = L1D_FLUSH_FALLBACK; + + if (!(result.behaviour & H_CPU_BEHAV_L1D_FLUSH_PR)) + enable = false; + } else { + /* Default to fallback if case hcall is not available */ + types = L1D_FLUSH_FALLBACK; + } + + setup_rfi_flush(types, enable); +} + static void __init pSeries_setup_arch(void) { set_arch_panic_timeout(10, ARCH_PANIC_TIMEOUT); @@ -515,7 +548,9 @@ static void __init pSeries_setup_arch(void) fwnmi_init(); - /* By default, only probe PCI (can be overriden by rtas_pci) */ + pseries_setup_rfi_flush(); + + /* By default, only probe PCI (can be overridden by rtas_pci) */ pci_add_flags(PCI_PROBE_ONLY); /* Find and initialize PCI host bridges */ diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c index 7bc4e4c5d5b8..d1653cc64550 100644 --- a/arch/s390/kernel/process.c +++ b/arch/s390/kernel/process.c @@ -67,13 +67,6 @@ unsigned long thread_saved_pc(struct task_struct *tsk) extern void kernel_thread_starter(void); -/* - * Free current thread data structures etc.. - */ -void exit_thread(void) -{ -} - void flush_thread(void) { } diff --git a/arch/score/kernel/process.c b/arch/score/kernel/process.c index a1519ad3d49d..aae9480706c2 100644 --- a/arch/score/kernel/process.c +++ b/arch/score/kernel/process.c @@ -56,8 +56,6 @@ void start_thread(struct pt_regs *regs, unsigned long pc, unsigned long sp) regs->regs[0] = sp; } -void exit_thread(void) {} - /* * When a process does an "exec", machine state like FPU and debug * registers need to be reset. This is a hook function for that. diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig index d514df7e04dd..0bc9282d37d2 100644 --- a/arch/sh/Kconfig +++ b/arch/sh/Kconfig @@ -71,6 +71,7 @@ config SUPERH32 config SUPERH64 def_bool ARCH = "sh64" + select HAVE_EXIT_THREAD select KALLSYMS config ARCH_DEFCONFIG diff --git a/arch/sh/kernel/process_32.c b/arch/sh/kernel/process_32.c index 2885fc9d9dcd..ee12e9451874 100644 --- a/arch/sh/kernel/process_32.c +++ b/arch/sh/kernel/process_32.c @@ -76,13 +76,6 @@ void start_thread(struct pt_regs *regs, unsigned long new_pc, } EXPORT_SYMBOL(start_thread); -/* - * Free current thread data structures etc.. - */ -void exit_thread(void) -{ -} - void flush_thread(void) { struct task_struct *tsk = current; diff --git a/arch/sh/kernel/process_64.c b/arch/sh/kernel/process_64.c index e2062e643341..9d3e9916555d 100644 --- a/arch/sh/kernel/process_64.c +++ b/arch/sh/kernel/process_64.c @@ -288,7 +288,7 @@ void show_regs(struct pt_regs *regs) /* * Free current thread data structures etc.. */ -void exit_thread(void) +void exit_thread(struct task_struct *tsk) { /* * See arch/sparc/kernel/process.c for the precedent for doing @@ -307,9 +307,8 @@ void exit_thread(void) * which it would get safely nulled. */ #ifdef CONFIG_SH_FPU - if (last_task_used_math == current) { + if (last_task_used_math == tsk) last_task_used_math = NULL; - } #endif } diff --git a/arch/sh/kernel/traps_32.c b/arch/sh/kernel/traps_32.c index ff639342a8be..c5b997757988 100644 --- a/arch/sh/kernel/traps_32.c +++ b/arch/sh/kernel/traps_32.c @@ -607,7 +607,8 @@ asmlinkage void do_divide_error(unsigned long r4) break; } - force_sig_info(SIGFPE, &info, current); + info.si_signo = SIGFPE; + force_sig_info(info.si_signo, &info, current); } #endif diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index 1cf6a15102d8..a1eb588fd46f 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -20,6 +20,7 @@ config SPARC select HAVE_OPROFILE select HAVE_ARCH_KGDB if !SMP || SPARC64 select HAVE_ARCH_TRACEHOOK + select HAVE_EXIT_THREAD select SYSCTL_EXCEPTION_TRACE select ARCH_WANT_OPTIONAL_GPIOLIB select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE diff --git a/arch/sparc/kernel/process_32.c b/arch/sparc/kernel/process_32.c index c5113c7ce2fd..b7780a5bef11 100644 --- a/arch/sparc/kernel/process_32.c +++ b/arch/sparc/kernel/process_32.c @@ -184,21 +184,21 @@ unsigned long thread_saved_pc(struct task_struct *tsk) /* * Free current thread data structures etc.. */ -void exit_thread(void) +void exit_thread(struct task_struct *tsk) { #ifndef CONFIG_SMP - if(last_task_used_math == current) { + if (last_task_used_math == tsk) { #else - if (test_thread_flag(TIF_USEDFPU)) { + if (test_ti_thread_flag(task_thread_info(tsk), TIF_USEDFPU)) { #endif /* Keep process from leaving FPU in a bogon state. */ put_psr(get_psr() | PSR_EF); - fpsave(¤t->thread.float_regs[0], ¤t->thread.fsr, - ¤t->thread.fpqueue[0], ¤t->thread.fpqdepth); + fpsave(&tsk->thread.float_regs[0], &tsk->thread.fsr, + &tsk->thread.fpqueue[0], &tsk->thread.fpqdepth); #ifndef CONFIG_SMP last_task_used_math = NULL; #else - clear_thread_flag(TIF_USEDFPU); + clear_ti_thread_flag(task_thread_info(tsk), TIF_USEDFPU); #endif } } diff --git a/arch/sparc/kernel/process_64.c b/arch/sparc/kernel/process_64.c index 46a59643bb1c..7c3fc5886038 100644 --- a/arch/sparc/kernel/process_64.c +++ b/arch/sparc/kernel/process_64.c @@ -417,9 +417,9 @@ unsigned long thread_saved_pc(struct task_struct *tsk) } /* Free current thread data structures etc.. */ -void exit_thread(void) +void exit_thread(struct task_struct *tsk) { - struct thread_info *t = current_thread_info(); + struct thread_info *t = task_thread_info(tsk); if (t->utraps) { if (t->utraps[0] < 2) diff --git a/arch/tile/Kconfig b/arch/tile/Kconfig index 8ec7a4599c08..09d4656f1492 100644 --- a/arch/tile/Kconfig +++ b/arch/tile/Kconfig @@ -3,6 +3,7 @@ config TILE def_bool y + select HAVE_EXIT_THREAD select HAVE_PERF_EVENTS select USE_PMC if PERF_EVENTS select HAVE_DMA_ATTRS diff --git a/arch/tile/kernel/process.c b/arch/tile/kernel/process.c index a97ab1a69a90..c5f3c1a20507 100644 --- a/arch/tile/kernel/process.c +++ b/arch/tile/kernel/process.c @@ -539,7 +539,7 @@ void flush_thread(void) /* * Free current thread data structures etc.. */ -void exit_thread(void) +void exit_thread(struct task_struct *tsk) { #ifdef CONFIG_HARDWALL /* @@ -548,7 +548,7 @@ void exit_thread(void) * the last reference to a hardwall fd, it would already have * been released and deactivated at this point.) */ - hardwall_deactivate_all(current); + hardwall_deactivate_all(tsk); #endif } diff --git a/arch/um/kernel/process.c b/arch/um/kernel/process.c index 48af59aae129..0b04711f1f18 100644 --- a/arch/um/kernel/process.c +++ b/arch/um/kernel/process.c @@ -103,10 +103,6 @@ void interrupt_end(void) tracehook_notify_resume(regs); } -void exit_thread(void) -{ -} - int get_current_pid(void) { return task_pid_nr(current); diff --git a/arch/unicore32/kernel/process.c b/arch/unicore32/kernel/process.c index b008e9961465..00299c927852 100644 --- a/arch/unicore32/kernel/process.c +++ b/arch/unicore32/kernel/process.c @@ -201,13 +201,6 @@ void show_regs(struct pt_regs *regs) __backtrace(); } -/* - * Free current thread data structures etc.. - */ -void exit_thread(void) -{ -} - void flush_thread(void) { struct thread_info *thread = current_thread_info(); diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index ddc3abdf437e..2e1ae5f0c369 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -108,6 +108,7 @@ config X86 select HAVE_DYNAMIC_FTRACE select HAVE_DYNAMIC_FTRACE_WITH_REGS select HAVE_EFFICIENT_UNALIGNED_ACCESS + select HAVE_EXIT_THREAD select HAVE_FENTRY if X86_64 select HAVE_FTRACE_MCOUNT_RECORD select HAVE_FUNCTION_GRAPH_FP_TEST diff --git a/arch/x86/crypto/poly1305_glue.c b/arch/x86/crypto/poly1305_glue.c index 4264a3d59589..7c064887b783 100644 --- a/arch/x86/crypto/poly1305_glue.c +++ b/arch/x86/crypto/poly1305_glue.c @@ -164,7 +164,6 @@ static struct shash_alg alg = { .init = poly1305_simd_init, .update = poly1305_simd_update, .final = crypto_poly1305_final, - .setkey = crypto_poly1305_setkey, .descsize = sizeof(struct poly1305_simd_desc_ctx), .base = { .cra_name = "poly1305", diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h index 817f67209568..858f8c354cea 100644 --- a/arch/x86/include/asm/asm.h +++ b/arch/x86/include/asm/asm.h @@ -11,10 +11,12 @@ # define __ASM_FORM_COMMA(x) " " #x "," #endif -#ifdef CONFIG_X86_32 +#ifndef __x86_64__ +/* 32 bit */ # define __ASM_SEL(a,b) __ASM_FORM(a) # define __ASM_SEL_RAW(a,b) __ASM_FORM_RAW(a) #else +/* 64 bit */ # define __ASM_SEL(a,b) __ASM_FORM(b) # define __ASM_SEL_RAW(a,b) __ASM_FORM_RAW(b) #endif diff --git a/arch/x86/include/asm/vsyscall.h b/arch/x86/include/asm/vsyscall.h index 9ee85066f407..62210da19a92 100644 --- a/arch/x86/include/asm/vsyscall.h +++ b/arch/x86/include/asm/vsyscall.h @@ -13,7 +13,6 @@ extern void map_vsyscall(void); */ extern bool emulate_vsyscall(struct pt_regs *regs, unsigned long address); extern bool vsyscall_enabled(void); -extern unsigned long vsyscall_pgprot; #else static inline void map_vsyscall(void) {} static inline bool emulate_vsyscall(struct pt_regs *regs, unsigned long address) @@ -22,5 +21,6 @@ static inline bool emulate_vsyscall(struct pt_regs *regs, unsigned long address) } static inline bool vsyscall_enabled(void) { return false; } #endif +extern unsigned long vsyscall_pgprot; #endif /* _ASM_X86_VSYSCALL_H */ diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index b3e94ef461fd..ce5f8a2e7ae6 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -44,7 +44,7 @@ static struct microcode_ops *microcode_ops; -static bool dis_ucode_ldr; +static bool dis_ucode_ldr = true; static int __init disable_loader(char *str) { @@ -81,6 +81,7 @@ struct cpu_info_ctx { static bool __init check_loader_disabled_bsp(void) { + u32 a, b, c, d; #ifdef CONFIG_X86_32 const char *cmdline = (const char *)__pa_nodebug(boot_command_line); const char *opt = "dis_ucode_ldr"; @@ -93,8 +94,20 @@ static bool __init check_loader_disabled_bsp(void) bool *res = &dis_ucode_ldr; #endif - if (cmdline_find_option_bool(cmdline, option)) - *res = true; + a = 1; + c = 0; + native_cpuid(&a, &b, &c, &d); + + /* + * CPUID(1).ECX[31]: reserved for hypervisor use. This is still not + * completely accurate as xen pv guests don't see that CPUID bit set but + * that's good enough as they don't land on the BSP path anyway. + */ + if (c & BIT(31)) + return *res; + + if (cmdline_find_option_bool(cmdline, option) <= 0) + *res = false; return *res; } @@ -122,9 +135,7 @@ void __init load_ucode_bsp(void) { int vendor; unsigned int family; - - if (check_loader_disabled_bsp()) - return; + bool intel = true; if (!have_cpuid_p()) return; @@ -134,16 +145,27 @@ void __init load_ucode_bsp(void) switch (vendor) { case X86_VENDOR_INTEL: - if (family >= 6) - load_ucode_intel_bsp(); + if (family < 6) + return; break; + case X86_VENDOR_AMD: - if (family >= 0x10) - load_ucode_amd_bsp(family); + if (family < 0x10) + return; + intel = false; break; + default: - break; + return; } + + if (check_loader_disabled_bsp()) + return; + + if (intel) + load_ucode_intel_bsp(); + else + load_ucode_amd_bsp(family); } static bool check_loader_disabled_ap(void) @@ -162,9 +184,6 @@ void load_ucode_ap(void) if (check_loader_disabled_ap()) return; - if (!have_cpuid_p()) - return; - vendor = x86_vendor(); family = x86_family(); diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index c1b21d61b769..2754dad26839 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -81,10 +81,9 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) /* * Free current thread data structures etc.. */ -void exit_thread(void) +void exit_thread(struct task_struct *tsk) { - struct task_struct *me = current; - struct thread_struct *t = &me->thread; + struct thread_struct *t = &tsk->thread; unsigned long *bp = t->io_bitmap_ptr; struct fpu *fpu = &t->fpu; diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index f8d785aa2e96..2a1a8737015b 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -4595,14 +4595,15 @@ static int vmx_deliver_nested_posted_interrupt(struct kvm_vcpu *vcpu, if (is_guest_mode(vcpu) && vector == vmx->nested.posted_intr_nv) { - /* the PIR and ON have been set by L1. */ - kvm_vcpu_trigger_posted_interrupt(vcpu); /* * If a posted intr is not recognized by hardware, * we will accomplish it in the next vmentry. */ vmx->nested.pi_pending = true; kvm_make_request(KVM_REQ_EVENT, vcpu); + /* the PIR and ON have been set by L1. */ + if (!kvm_vcpu_trigger_posted_interrupt(vcpu)) + kvm_vcpu_kick(vcpu); return 0; } return -1; diff --git a/arch/x86/mm/kaiser.c b/arch/x86/mm/kaiser.c index 2298434f7bdb..7a72e32e4806 100644 --- a/arch/x86/mm/kaiser.c +++ b/arch/x86/mm/kaiser.c @@ -363,7 +363,7 @@ void __init kaiser_init(void) kaiser_add_user_map_ptrs_early(__entry_text_start, __entry_text_end, __PAGE_KERNEL_RX); -#if defined(CONFIG_FUNCTION_GRAPH_TRACER) || defined(CONFIG_KASAN) +#ifdef CONFIG_FUNCTION_GRAPH_TRACER kaiser_add_user_map_ptrs_early(__irqentry_text_start, __irqentry_text_end, __PAGE_KERNEL_RX); diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig index 82044f732323..bdad9be4a729 100644 --- a/arch/xtensa/Kconfig +++ b/arch/xtensa/Kconfig @@ -16,6 +16,7 @@ config XTENSA select GENERIC_SCHED_CLOCK select HAVE_DMA_API_DEBUG select HAVE_DMA_ATTRS + select HAVE_EXIT_THREAD select HAVE_FUNCTION_TRACER select HAVE_FUTEX_CMPXCHG if !MMU select HAVE_IRQ_TIME_ACCOUNTING diff --git a/arch/xtensa/include/asm/futex.h b/arch/xtensa/include/asm/futex.h index b39531babec0..72bfc1cbc2b5 100644 --- a/arch/xtensa/include/asm/futex.h +++ b/arch/xtensa/include/asm/futex.h @@ -109,7 +109,6 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, u32 oldval, u32 newval) { int ret = 0; - u32 prev; if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32))) return -EFAULT; @@ -120,26 +119,24 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, __asm__ __volatile__ ( " # futex_atomic_cmpxchg_inatomic\n" - "1: l32i %1, %3, 0\n" - " mov %0, %5\n" - " wsr %1, scompare1\n" - "2: s32c1i %0, %3, 0\n" - "3:\n" + " wsr %5, scompare1\n" + "1: s32c1i %1, %4, 0\n" + " s32i %1, %6, 0\n" + "2:\n" " .section .fixup,\"ax\"\n" " .align 4\n" - "4: .long 3b\n" - "5: l32r %1, 4b\n" - " movi %0, %6\n" + "3: .long 2b\n" + "4: l32r %1, 3b\n" + " movi %0, %7\n" " jx %1\n" " .previous\n" " .section __ex_table,\"a\"\n" - " .long 1b,5b,2b,5b\n" + " .long 1b,4b\n" " .previous\n" - : "+r" (ret), "=&r" (prev), "+m" (*uaddr) - : "r" (uaddr), "r" (oldval), "r" (newval), "I" (-EFAULT) + : "+r" (ret), "+r" (newval), "+m" (*uaddr), "+m" (*uval) + : "r" (uaddr), "r" (oldval), "r" (uval), "I" (-EFAULT) : "memory"); - *uval = prev; return ret; } diff --git a/arch/xtensa/kernel/process.c b/arch/xtensa/kernel/process.c index 1c85323f01d7..17a378c15a15 100644 --- a/arch/xtensa/kernel/process.c +++ b/arch/xtensa/kernel/process.c @@ -113,10 +113,10 @@ void arch_cpu_idle(void) /* * This is called when the thread calls exit(). */ -void exit_thread(void) +void exit_thread(struct task_struct *tsk) { #if XTENSA_HAVE_COPROCESSORS - coprocessor_release_all(current_thread_info()); + coprocessor_release_all(task_thread_info(tsk)); #endif } |