diff options
Diffstat (limited to 'arch/powerpc')
86 files changed, 1354 insertions, 680 deletions
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index f7c8f9972f61..6189238e69f8 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -184,7 +184,7 @@ config PPC select HAVE_FUNCTION_GRAPH_TRACER select HAVE_FUNCTION_TRACER select HAVE_GCC_PLUGINS - select HAVE_GENERIC_RCU_GUP + select HAVE_GENERIC_GUP select HAVE_HW_BREAKPOINT if PERF_EVENTS && (PPC_BOOK3S || PPC_8xx) select HAVE_IDE select HAVE_IOREMAP_PROT @@ -380,22 +380,6 @@ source "arch/powerpc/platforms/Kconfig" menu "Kernel options" -config PPC_DT_CPU_FTRS - bool "Device-tree based CPU feature discovery & setup" - depends on PPC_BOOK3S_64 - default n - help - This enables code to use a new device tree binding for describing CPU - compatibility and features. Saying Y here will attempt to use the new - binding if the firmware provides it. Currently only the skiboot - firmware provides this binding. - If you're not sure say Y. - -config PPC_CPUFEATURES_ENABLE_UNKNOWN - bool "cpufeatures pass through unknown features to guest/userspace" - depends on PPC_DT_CPU_FTRS - default y - config HIGHMEM bool "High memory support" depends on PPC32 @@ -1215,11 +1199,6 @@ source "arch/powerpc/Kconfig.debug" source "security/Kconfig" -config KEYS_COMPAT - bool - depends on COMPAT && KEYS - default y - source "crypto/Kconfig" config PPC_LIB_RHEAP diff --git a/arch/powerpc/boot/dts/fsl/kmcent2.dts b/arch/powerpc/boot/dts/fsl/kmcent2.dts index 47afa438602e..5922c1ea0e96 100644 --- a/arch/powerpc/boot/dts/fsl/kmcent2.dts +++ b/arch/powerpc/boot/dts/fsl/kmcent2.dts @@ -293,9 +293,7 @@ compatible = "fsl,ucc-hdlc"; rx-clock-name = "clk9"; tx-clock-name = "clk9"; - fsl,tx-timeslot-mask = <0xfffffffe>; - fsl,rx-timeslot-mask = <0xfffffffe>; - fsl,siram-entry-id = <0>; + fsl,hdlc-bus; }; }; }; diff --git a/arch/powerpc/boot/dts/include/dt-bindings b/arch/powerpc/boot/dts/include/dt-bindings deleted file mode 120000 index 08c00e4972fa..000000000000 --- a/arch/powerpc/boot/dts/include/dt-bindings +++ /dev/null @@ -1 +0,0 @@ -../../../../../include/dt-bindings
\ No newline at end of file diff --git a/arch/powerpc/include/asm/book3s/64/hash-4k.h b/arch/powerpc/include/asm/book3s/64/hash-4k.h index b4b5e6b671ca..0c4e470571ca 100644 --- a/arch/powerpc/include/asm/book3s/64/hash-4k.h +++ b/arch/powerpc/include/asm/book3s/64/hash-4k.h @@ -8,7 +8,7 @@ #define H_PTE_INDEX_SIZE 9 #define H_PMD_INDEX_SIZE 7 #define H_PUD_INDEX_SIZE 9 -#define H_PGD_INDEX_SIZE 12 +#define H_PGD_INDEX_SIZE 9 #ifndef __ASSEMBLY__ #define H_PTE_TABLE_SIZE (sizeof(pte_t) << H_PTE_INDEX_SIZE) diff --git a/arch/powerpc/include/asm/book3s/64/hugetlb.h b/arch/powerpc/include/asm/book3s/64/hugetlb.h index 6666cd366596..5c28bd6f2ae1 100644 --- a/arch/powerpc/include/asm/book3s/64/hugetlb.h +++ b/arch/powerpc/include/asm/book3s/64/hugetlb.h @@ -50,4 +50,14 @@ static inline pte_t arch_make_huge_pte(pte_t entry, struct vm_area_struct *vma, else return entry; } + +#ifdef CONFIG_ARCH_HAS_GIGANTIC_PAGE +static inline bool gigantic_page_supported(void) +{ + if (radix_enabled()) + return true; + return false; +} +#endif + #endif diff --git a/arch/powerpc/include/asm/bug.h b/arch/powerpc/include/asm/bug.h index f2c562a0a427..0151af6c2a50 100644 --- a/arch/powerpc/include/asm/bug.h +++ b/arch/powerpc/include/asm/bug.h @@ -104,7 +104,7 @@ "1: "PPC_TLNEI" %4,0\n" \ _EMIT_BUG_ENTRY \ : : "i" (__FILE__), "i" (__LINE__), \ - "i" (BUGFLAG_TAINT(TAINT_WARN)), \ + "i" (BUGFLAG_WARNING|BUGFLAG_TAINT(TAINT_WARN)),\ "i" (sizeof(struct bug_entry)), \ "r" (__ret_warn_on)); \ } \ diff --git a/arch/powerpc/include/asm/compat.h b/arch/powerpc/include/asm/compat.h index 4f2df589ec1d..f256e1d14a14 100644 --- a/arch/powerpc/include/asm/compat.h +++ b/arch/powerpc/include/asm/compat.h @@ -109,7 +109,6 @@ struct compat_statfs { int f_spare[4]; }; -#define COMPAT_RLIM_OLD_INFINITY 0x7fffffff #define COMPAT_RLIM_INFINITY 0xffffffff typedef u32 compat_old_sigset_t; diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h index c2d509584a98..d02ad93bf708 100644 --- a/arch/powerpc/include/asm/cputable.h +++ b/arch/powerpc/include/asm/cputable.h @@ -214,7 +214,6 @@ enum { #define CPU_FTR_DAWR LONG_ASM_CONST(0x0400000000000000) #define CPU_FTR_DABRX LONG_ASM_CONST(0x0800000000000000) #define CPU_FTR_PMAO_BUG LONG_ASM_CONST(0x1000000000000000) -#define CPU_FTR_SUBCORE LONG_ASM_CONST(0x2000000000000000) #define CPU_FTR_POWER9_DD1 LONG_ASM_CONST(0x4000000000000000) #ifndef __ASSEMBLY__ @@ -463,7 +462,7 @@ enum { CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \ CPU_FTR_ICSWX | CPU_FTR_CFAR | CPU_FTR_HVMODE | CPU_FTR_VMX_COPY | \ CPU_FTR_DBELL | CPU_FTR_HAS_PPR | CPU_FTR_DAWR | \ - CPU_FTR_ARCH_207S | CPU_FTR_TM_COMP | CPU_FTR_SUBCORE) + CPU_FTR_ARCH_207S | CPU_FTR_TM_COMP) #define CPU_FTRS_POWER8E (CPU_FTRS_POWER8 | CPU_FTR_PMAO_BUG) #define CPU_FTRS_POWER8_DD1 (CPU_FTRS_POWER8 & ~CPU_FTR_DBELL) #define CPU_FTRS_POWER9 (CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \ diff --git a/arch/powerpc/include/asm/dma-mapping.h b/arch/powerpc/include/asm/dma-mapping.h index 181a095468e4..eaece3d3e225 100644 --- a/arch/powerpc/include/asm/dma-mapping.h +++ b/arch/powerpc/include/asm/dma-mapping.h @@ -17,10 +17,6 @@ #include <asm/io.h> #include <asm/swiotlb.h> -#ifdef CONFIG_PPC64 -#define DMA_ERROR_CODE (~(dma_addr_t)0x0) -#endif - /* Some dma direct funcs must be visible for use in other dma_ops */ extern void *__dma_direct_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t flag, @@ -116,7 +112,6 @@ static inline void set_dma_offset(struct device *dev, dma_addr_t off) #define HAVE_ARCH_DMA_SET_MASK 1 extern int dma_set_mask(struct device *dev, u64 dma_mask); -extern int __dma_set_mask(struct device *dev, u64 dma_mask); extern u64 __dma_get_required_mask(struct device *dev); static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size) diff --git a/arch/powerpc/include/asm/hvcall.h b/arch/powerpc/include/asm/hvcall.h index d73755fafbb0..57d38b504ff7 100644 --- a/arch/powerpc/include/asm/hvcall.h +++ b/arch/powerpc/include/asm/hvcall.h @@ -295,6 +295,8 @@ #define H_DISABLE_ALL_VIO_INTS 0x0A #define H_DISABLE_VIO_INTERRUPT 0x0B #define H_ENABLE_VIO_INTERRUPT 0x0C +#define H_GET_SESSION_TOKEN 0x19 +#define H_SESSION_ERR_DETECTED 0x1A /* Platform specific hcalls, used by KVM */ diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h index 8a8ce220d7d0..20febe0b7f32 100644 --- a/arch/powerpc/include/asm/iommu.h +++ b/arch/powerpc/include/asm/iommu.h @@ -139,6 +139,8 @@ struct scatterlist; #ifdef CONFIG_PPC64 +#define IOMMU_MAPPING_ERROR (~(dma_addr_t)0x0) + static inline void set_iommu_table_base(struct device *dev, struct iommu_table *base) { @@ -238,6 +240,8 @@ static inline int __init tce_iommu_bus_notifier_init(void) } #endif /* !CONFIG_IOMMU_API */ +int dma_iommu_mapping_error(struct device *dev, dma_addr_t dma_addr); + #else static inline void *get_iommu_table_base(struct device *dev) diff --git a/arch/powerpc/include/asm/kprobes.h b/arch/powerpc/include/asm/kprobes.h index a83821f33ea3..8814a7249ceb 100644 --- a/arch/powerpc/include/asm/kprobes.h +++ b/arch/powerpc/include/asm/kprobes.h @@ -103,6 +103,7 @@ extern int kprobe_exceptions_notify(struct notifier_block *self, extern int kprobe_fault_handler(struct pt_regs *regs, int trapnr); extern int kprobe_handler(struct pt_regs *regs); extern int kprobe_post_handler(struct pt_regs *regs); +extern int is_current_kprobe_addr(unsigned long addr); #ifdef CONFIG_KPROBES_ON_FTRACE extern int skip_singlestep(struct kprobe *p, struct pt_regs *regs, struct kprobe_ctlblk *kcb); diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h index 2bf35017ffc0..b8d5b8e35244 100644 --- a/arch/powerpc/include/asm/kvm_book3s.h +++ b/arch/powerpc/include/asm/kvm_book3s.h @@ -86,7 +86,6 @@ struct kvmppc_vcore { u16 last_cpu; u8 vcore_state; u8 in_guest; - struct kvmppc_vcore *master_vcore; struct kvm_vcpu *runnable_threads[MAX_SMT_THREADS]; struct list_head preempt_list; spinlock_t lock; diff --git a/arch/powerpc/include/asm/kvm_book3s_asm.h b/arch/powerpc/include/asm/kvm_book3s_asm.h index b148496ffe36..7cea76f11c26 100644 --- a/arch/powerpc/include/asm/kvm_book3s_asm.h +++ b/arch/powerpc/include/asm/kvm_book3s_asm.h @@ -81,7 +81,7 @@ struct kvm_split_mode { u8 subcore_size; u8 do_nap; u8 napped[MAX_SMT_THREADS]; - struct kvmppc_vcore *master_vcs[MAX_SUBCORES]; + struct kvmppc_vcore *vc[MAX_SUBCORES]; }; /* diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index 9c51ac4b8f36..8b3f1238d07f 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -35,6 +35,7 @@ #include <asm/page.h> #include <asm/cacheflush.h> #include <asm/hvcall.h> +#include <asm/mce.h> #define KVM_MAX_VCPUS NR_CPUS #define KVM_MAX_VCORES NR_CPUS @@ -52,8 +53,8 @@ #define KVM_IRQCHIP_NUM_PINS 256 /* PPC-specific vcpu->requests bit members */ -#define KVM_REQ_WATCHDOG 8 -#define KVM_REQ_EPR_EXIT 9 +#define KVM_REQ_WATCHDOG KVM_ARCH_REQ(0) +#define KVM_REQ_EPR_EXIT KVM_ARCH_REQ(1) #include <linux/mmu_notifier.h> @@ -267,6 +268,8 @@ struct kvm_resize_hpt; struct kvm_arch { unsigned int lpid; + unsigned int smt_mode; /* # vcpus per virtual core */ + unsigned int emul_smt_mode; /* emualted SMT mode, on P9 */ #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE unsigned int tlb_sets; struct kvm_hpt_info hpt; @@ -285,6 +288,7 @@ struct kvm_arch { cpumask_t need_tlb_flush; cpumask_t cpu_in_guest; u8 radix; + u8 fwnmi_enabled; pgd_t *pgtable; u64 process_table; struct dentry *debugfs_dir; @@ -566,6 +570,7 @@ struct kvm_vcpu_arch { ulong wort; ulong tid; ulong psscr; + ulong hfscr; ulong shadow_srr1; #endif u32 vrsave; /* also USPRG0 */ @@ -579,7 +584,7 @@ struct kvm_vcpu_arch { ulong mcsrr0; ulong mcsrr1; ulong mcsr; - u32 dec; + ulong dec; #ifdef CONFIG_BOOKE u32 decar; #endif @@ -710,6 +715,7 @@ struct kvm_vcpu_arch { unsigned long pending_exceptions; u8 ceded; u8 prodded; + u8 doorbell_request; u32 last_inst; struct swait_queue_head *wqp; @@ -722,6 +728,7 @@ struct kvm_vcpu_arch { int prev_cpu; bool timer_running; wait_queue_head_t cpu_run; + struct machine_check_event mce_evt; /* Valid if trap == 0x200 */ struct kvm_vcpu_arch_shared *shared; #if defined(CONFIG_PPC_BOOK3S_64) && defined(CONFIG_KVM_BOOK3S_PR_POSSIBLE) diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h index e0d88c38602b..ba5fadd6f3c9 100644 --- a/arch/powerpc/include/asm/kvm_ppc.h +++ b/arch/powerpc/include/asm/kvm_ppc.h @@ -315,6 +315,8 @@ struct kvmppc_ops { struct irq_bypass_producer *); int (*configure_mmu)(struct kvm *kvm, struct kvm_ppc_mmuv3_cfg *cfg); int (*get_rmmu_info)(struct kvm *kvm, struct kvm_ppc_rmmu_info *info); + int (*set_smt_mode)(struct kvm *kvm, unsigned long mode, + unsigned long flags); }; extern struct kvmppc_ops *kvmppc_hv_ops; diff --git a/arch/powerpc/include/asm/module.h b/arch/powerpc/include/asm/module.h index 53885512b8d3..6c0132c7212f 100644 --- a/arch/powerpc/include/asm/module.h +++ b/arch/powerpc/include/asm/module.h @@ -14,6 +14,10 @@ #include <asm-generic/module.h> +#ifdef CC_USING_MPROFILE_KERNEL +#define MODULE_ARCH_VERMAGIC "mprofile-kernel" +#endif + #ifndef __powerpc64__ /* * Thanks to Paul M for explaining this. diff --git a/arch/powerpc/include/asm/page.h b/arch/powerpc/include/asm/page.h index 2a32483c7b6c..8da5d4c1cab2 100644 --- a/arch/powerpc/include/asm/page.h +++ b/arch/powerpc/include/asm/page.h @@ -132,7 +132,19 @@ extern long long virt_phys_offset; #define virt_to_pfn(kaddr) (__pa(kaddr) >> PAGE_SHIFT) #define virt_to_page(kaddr) pfn_to_page(virt_to_pfn(kaddr)) #define pfn_to_kaddr(pfn) __va((pfn) << PAGE_SHIFT) + +#ifdef CONFIG_PPC_BOOK3S_64 +/* + * On hash the vmalloc and other regions alias to the kernel region when passed + * through __pa(), which virt_to_pfn() uses. That means virt_addr_valid() can + * return true for some vmalloc addresses, which is incorrect. So explicitly + * check that the address is in the kernel region. + */ +#define virt_addr_valid(kaddr) (REGION_ID(kaddr) == KERNEL_REGION_ID && \ + pfn_valid(virt_to_pfn(kaddr))) +#else #define virt_addr_valid(kaddr) pfn_valid(virt_to_pfn(kaddr)) +#endif /* * On Book-E parts we need __va to parse the device tree and we can't diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h index 3a8d278e7421..1a9b45198c06 100644 --- a/arch/powerpc/include/asm/ppc-opcode.h +++ b/arch/powerpc/include/asm/ppc-opcode.h @@ -103,6 +103,8 @@ #define OP_31_XOP_STBUX 247 #define OP_31_XOP_LHZX 279 #define OP_31_XOP_LHZUX 311 +#define OP_31_XOP_MSGSNDP 142 +#define OP_31_XOP_MSGCLRP 174 #define OP_31_XOP_MFSPR 339 #define OP_31_XOP_LWAX 341 #define OP_31_XOP_LHAX 343 diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h index a2123f291ab0..1189d04f3bd1 100644 --- a/arch/powerpc/include/asm/processor.h +++ b/arch/powerpc/include/asm/processor.h @@ -110,13 +110,18 @@ void release_thread(struct task_struct *); #define TASK_SIZE_128TB (0x0000800000000000UL) #define TASK_SIZE_512TB (0x0002000000000000UL) -#ifdef CONFIG_PPC_BOOK3S_64 +/* + * For now 512TB is only supported with book3s and 64K linux page size. + */ +#if defined(CONFIG_PPC_BOOK3S_64) && defined(CONFIG_PPC_64K_PAGES) /* * Max value currently used: */ -#define TASK_SIZE_USER64 TASK_SIZE_512TB +#define TASK_SIZE_USER64 TASK_SIZE_512TB +#define DEFAULT_MAP_WINDOW_USER64 TASK_SIZE_128TB #else -#define TASK_SIZE_USER64 TASK_SIZE_64TB +#define TASK_SIZE_USER64 TASK_SIZE_64TB +#define DEFAULT_MAP_WINDOW_USER64 TASK_SIZE_64TB #endif /* @@ -132,7 +137,7 @@ void release_thread(struct task_struct *); * space during mmap's. */ #define TASK_UNMAPPED_BASE_USER32 (PAGE_ALIGN(TASK_SIZE_USER32 / 4)) -#define TASK_UNMAPPED_BASE_USER64 (PAGE_ALIGN(TASK_SIZE_128TB / 4)) +#define TASK_UNMAPPED_BASE_USER64 (PAGE_ALIGN(DEFAULT_MAP_WINDOW_USER64 / 4)) #define TASK_UNMAPPED_BASE ((is_32bit_task()) ? \ TASK_UNMAPPED_BASE_USER32 : TASK_UNMAPPED_BASE_USER64 ) @@ -143,21 +148,15 @@ void release_thread(struct task_struct *); * with 128TB and conditionally enable upto 512TB */ #ifdef CONFIG_PPC_BOOK3S_64 -#define DEFAULT_MAP_WINDOW ((is_32bit_task()) ? \ - TASK_SIZE_USER32 : TASK_SIZE_128TB) +#define DEFAULT_MAP_WINDOW ((is_32bit_task()) ? \ + TASK_SIZE_USER32 : DEFAULT_MAP_WINDOW_USER64) #else #define DEFAULT_MAP_WINDOW TASK_SIZE #endif #ifdef __powerpc64__ -#ifdef CONFIG_PPC_BOOK3S_64 -/* Limit stack to 128TB */ -#define STACK_TOP_USER64 TASK_SIZE_128TB -#else -#define STACK_TOP_USER64 TASK_SIZE_USER64 -#endif - +#define STACK_TOP_USER64 DEFAULT_MAP_WINDOW_USER64 #define STACK_TOP_USER32 TASK_SIZE_USER32 #define STACK_TOP (is_32bit_task() ? \ @@ -379,12 +378,6 @@ struct thread_struct { } #endif -/* - * Return saved PC of a blocked thread. For now, this is the "user" PC - */ -#define thread_saved_pc(tsk) \ - ((tsk)->thread.regs? (tsk)->thread.regs->nip: 0) - #define task_pt_regs(tsk) ((struct pt_regs *)(tsk)->thread.regs) unsigned long get_wchan(struct task_struct *p); diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h index 8b3b46b7b0f2..dc4e15937ccf 100644 --- a/arch/powerpc/include/asm/topology.h +++ b/arch/powerpc/include/asm/topology.h @@ -43,9 +43,24 @@ extern void __init dump_numa_cpu_topology(void); extern int sysfs_add_device_to_node(struct device *dev, int nid); extern void sysfs_remove_device_from_node(struct device *dev, int nid); +extern int numa_update_cpu_topology(bool cpus_locked); +static inline int early_cpu_to_node(int cpu) +{ + int nid; + + nid = numa_cpu_lookup_table[cpu]; + + /* + * Fall back to node 0 if nid is unset (it should be, except bugs). + * This allows callers to safely do NODE_DATA(early_cpu_to_node(cpu)). + */ + return (nid < 0) ? 0 : nid; +} #else +static inline int early_cpu_to_node(int cpu) { return 0; } + static inline void dump_numa_cpu_topology(void) {} static inline int sysfs_add_device_to_node(struct device *dev, int nid) @@ -57,6 +72,11 @@ static inline void sysfs_remove_device_from_node(struct device *dev, int nid) { } + +static inline int numa_update_cpu_topology(bool cpus_locked) +{ + return 0; +} #endif /* CONFIG_NUMA */ #if defined(CONFIG_NUMA) && defined(CONFIG_PPC_SPLPAR) diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h index 5c0d8a8cdae5..4cf57f2126e6 100644 --- a/arch/powerpc/include/asm/uaccess.h +++ b/arch/powerpc/include/asm/uaccess.h @@ -267,13 +267,7 @@ do { \ extern unsigned long __copy_tofrom_user(void __user *to, const void __user *from, unsigned long size); -#ifndef __powerpc64__ - -#define INLINE_COPY_FROM_USER -#define INLINE_COPY_TO_USER - -#else /* __powerpc64__ */ - +#ifdef __powerpc64__ static inline unsigned long raw_copy_in_user(void __user *to, const void __user *from, unsigned long n) { @@ -346,7 +340,6 @@ static inline unsigned long clear_user(void __user *addr, unsigned long size) } extern long strncpy_from_user(char *dst, const char __user *src, long count); -extern __must_check long strlen_user(const char __user *str); extern __must_check long strnlen_user(const char __user *str, long n); #endif /* _ARCH_POWERPC_UACCESS_H */ diff --git a/arch/powerpc/include/asm/xive.h b/arch/powerpc/include/asm/xive.h index c8a822acf962..c23ff4389ca2 100644 --- a/arch/powerpc/include/asm/xive.h +++ b/arch/powerpc/include/asm/xive.h @@ -94,11 +94,13 @@ struct xive_q { * store at 0 and some ESBs support doing a trigger via a * separate trigger page. */ -#define XIVE_ESB_GET 0x800 -#define XIVE_ESB_SET_PQ_00 0xc00 -#define XIVE_ESB_SET_PQ_01 0xd00 -#define XIVE_ESB_SET_PQ_10 0xe00 -#define XIVE_ESB_SET_PQ_11 0xf00 +#define XIVE_ESB_STORE_EOI 0x400 /* Store */ +#define XIVE_ESB_LOAD_EOI 0x000 /* Load */ +#define XIVE_ESB_GET 0x800 /* Load */ +#define XIVE_ESB_SET_PQ_00 0xc00 /* Load */ +#define XIVE_ESB_SET_PQ_01 0xd00 /* Load */ +#define XIVE_ESB_SET_PQ_10 0xe00 /* Load */ +#define XIVE_ESB_SET_PQ_11 0xf00 /* Load */ #define XIVE_ESB_VAL_P 0x2 #define XIVE_ESB_VAL_Q 0x1 diff --git a/arch/powerpc/include/uapi/asm/cputable.h b/arch/powerpc/include/uapi/asm/cputable.h index 3e7ce86d5c13..4d877144f377 100644 --- a/arch/powerpc/include/uapi/asm/cputable.h +++ b/arch/powerpc/include/uapi/asm/cputable.h @@ -46,6 +46,8 @@ #define PPC_FEATURE2_HTM_NOSC 0x01000000 #define PPC_FEATURE2_ARCH_3_00 0x00800000 /* ISA 3.00 */ #define PPC_FEATURE2_HAS_IEEE128 0x00400000 /* VSX IEEE Binary Float 128-bit */ +#define PPC_FEATURE2_DARN 0x00200000 /* darn random number insn */ +#define PPC_FEATURE2_SCV 0x00100000 /* scv syscall */ /* * IMPORTANT! diff --git a/arch/powerpc/include/uapi/asm/ioctls.h b/arch/powerpc/include/uapi/asm/ioctls.h index 49a25796a61a..bfd609a3e928 100644 --- a/arch/powerpc/include/uapi/asm/ioctls.h +++ b/arch/powerpc/include/uapi/asm/ioctls.h @@ -100,6 +100,7 @@ #define TIOCGPKT _IOR('T', 0x38, int) /* Get packet mode state */ #define TIOCGPTLCK _IOR('T', 0x39, int) /* Get Pty lock state */ #define TIOCGEXCL _IOR('T', 0x40, int) /* Get exclusive mode state */ +#define TIOCGPTPEER _IOR('T', 0x41, int) /* Safely open the slave */ #define TIOCSERCONFIG 0x5453 #define TIOCSERGWILD 0x5454 diff --git a/arch/powerpc/include/uapi/asm/kvm.h b/arch/powerpc/include/uapi/asm/kvm.h index 07fbeb927834..8cf8f0c96906 100644 --- a/arch/powerpc/include/uapi/asm/kvm.h +++ b/arch/powerpc/include/uapi/asm/kvm.h @@ -60,6 +60,12 @@ struct kvm_regs { #define KVM_SREGS_E_FSL_PIDn (1 << 0) /* PID1/PID2 */ +/* flags for kvm_run.flags */ +#define KVM_RUN_PPC_NMI_DISP_MASK (3 << 0) +#define KVM_RUN_PPC_NMI_DISP_FULLY_RECOV (1 << 0) +#define KVM_RUN_PPC_NMI_DISP_LIMITED_RECOV (2 << 0) +#define KVM_RUN_PPC_NMI_DISP_NOT_RECOV (3 << 0) + /* * Feature bits indicate which sections of the sregs struct are valid, * both in KVM_GET_SREGS and KVM_SET_SREGS. On KVM_SET_SREGS, registers diff --git a/arch/powerpc/include/uapi/asm/socket.h b/arch/powerpc/include/uapi/asm/socket.h index 58e2ec0310fc..3c590c7c42c0 100644 --- a/arch/powerpc/include/uapi/asm/socket.h +++ b/arch/powerpc/include/uapi/asm/socket.h @@ -8,28 +8,6 @@ * 2 of the License, or (at your option) any later version. */ -#include <asm/sockios.h> - -/* For setsockopt(2) */ -#define SOL_SOCKET 1 - -#define SO_DEBUG 1 -#define SO_REUSEADDR 2 -#define SO_TYPE 3 -#define SO_ERROR 4 -#define SO_DONTROUTE 5 -#define SO_BROADCAST 6 -#define SO_SNDBUF 7 -#define SO_RCVBUF 8 -#define SO_SNDBUFFORCE 32 -#define SO_RCVBUFFORCE 33 -#define SO_KEEPALIVE 9 -#define SO_OOBINLINE 10 -#define SO_NO_CHECK 11 -#define SO_PRIORITY 12 -#define SO_LINGER 13 -#define SO_BSDCOMPAT 14 -#define SO_REUSEPORT 15 #define SO_RCVLOWAT 16 #define SO_SNDLOWAT 17 #define SO_RCVTIMEO 18 @@ -37,72 +15,6 @@ #define SO_PASSCRED 20 #define SO_PEERCRED 21 -/* Security levels - as per NRL IPv6 - don't actually do anything */ -#define SO_SECURITY_AUTHENTICATION 22 -#define SO_SECURITY_ENCRYPTION_TRANSPORT 23 -#define SO_SECURITY_ENCRYPTION_NETWORK 24 - -#define SO_BINDTODEVICE 25 - -/* Socket filtering */ -#define SO_ATTACH_FILTER 26 -#define SO_DETACH_FILTER 27 -#define SO_GET_FILTER SO_ATTACH_FILTER - -#define SO_PEERNAME 28 -#define SO_TIMESTAMP 29 -#define SCM_TIMESTAMP SO_TIMESTAMP - -#define SO_ACCEPTCONN 30 - -#define SO_PEERSEC 31 -#define SO_PASSSEC 34 -#define SO_TIMESTAMPNS 35 -#define SCM_TIMESTAMPNS SO_TIMESTAMPNS - -#define SO_MARK 36 - -#define SO_TIMESTAMPING 37 -#define SCM_TIMESTAMPING SO_TIMESTAMPING - -#define SO_PROTOCOL 38 -#define SO_DOMAIN 39 - -#define SO_RXQ_OVFL 40 - -#define SO_WIFI_STATUS 41 -#define SCM_WIFI_STATUS SO_WIFI_STATUS -#define SO_PEEK_OFF 42 - -/* Instruct lower device to use last 4-bytes of skb data as FCS */ -#define SO_NOFCS 43 - -#define SO_LOCK_FILTER 44 - -#define SO_SELECT_ERR_QUEUE 45 - -#define SO_BUSY_POLL 46 - -#define SO_MAX_PACING_RATE 47 - -#define SO_BPF_EXTENSIONS 48 - -#define SO_INCOMING_CPU 49 - -#define SO_ATTACH_BPF 50 -#define SO_DETACH_BPF SO_DETACH_FILTER - -#define SO_ATTACH_REUSEPORT_CBPF 51 -#define SO_ATTACH_REUSEPORT_EBPF 52 - -#define SO_CNX_ADVICE 53 - -#define SCM_TIMESTAMPING_OPT_STATS 54 - -#define SO_MEMINFO 55 - -#define SO_INCOMING_NAPI_ID 56 - -#define SO_COOKIE 57 +#include <asm-generic/socket.h> #endif /* _ASM_POWERPC_SOCKET_H */ diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index 709e23425317..ae8e89e0d083 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -485,6 +485,7 @@ int main(void) OFFSET(KVM_ENABLED_HCALLS, kvm, arch.enabled_hcalls); OFFSET(KVM_VRMA_SLB_V, kvm, arch.vrma_slb_v); OFFSET(KVM_RADIX, kvm, arch.radix); + OFFSET(KVM_FWNMI, kvm, arch.fwnmi_enabled); OFFSET(VCPU_DSISR, kvm_vcpu, arch.shregs.dsisr); OFFSET(VCPU_DAR, kvm_vcpu, arch.shregs.dar); OFFSET(VCPU_VPA, kvm_vcpu, arch.vpa.pinned_addr); @@ -513,6 +514,7 @@ int main(void) OFFSET(VCPU_PENDING_EXC, kvm_vcpu, arch.pending_exceptions); OFFSET(VCPU_CEDED, kvm_vcpu, arch.ceded); OFFSET(VCPU_PRODDED, kvm_vcpu, arch.prodded); + OFFSET(VCPU_DBELL_REQ, kvm_vcpu, arch.doorbell_request); OFFSET(VCPU_MMCR, kvm_vcpu, arch.mmcr); OFFSET(VCPU_PMC, kvm_vcpu, arch.pmc); OFFSET(VCPU_SPMC, kvm_vcpu, arch.spmc); @@ -542,6 +544,7 @@ int main(void) OFFSET(VCPU_WORT, kvm_vcpu, arch.wort); OFFSET(VCPU_TID, kvm_vcpu, arch.tid); OFFSET(VCPU_PSSCR, kvm_vcpu, arch.psscr); + OFFSET(VCPU_HFSCR, kvm_vcpu, arch.hfscr); OFFSET(VCORE_ENTRY_EXIT, kvmppc_vcore, entry_exit_map); OFFSET(VCORE_IN_GUEST, kvmppc_vcore, in_guest); OFFSET(VCORE_NAPPING_THREADS, kvmppc_vcore, napping_threads); diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c index 9b3e88b1a9c8..6f849832a669 100644 --- a/arch/powerpc/kernel/cputable.c +++ b/arch/powerpc/kernel/cputable.c @@ -124,7 +124,8 @@ extern void __restore_cpu_e6500(void); #define COMMON_USER_POWER9 COMMON_USER_POWER8 #define COMMON_USER2_POWER9 (COMMON_USER2_POWER8 | \ PPC_FEATURE2_ARCH_3_00 | \ - PPC_FEATURE2_HAS_IEEE128) + PPC_FEATURE2_HAS_IEEE128 | \ + PPC_FEATURE2_DARN ) #ifdef CONFIG_PPC_BOOK3E_64 #define COMMON_USER_BOOKE (COMMON_USER_PPC64 | PPC_FEATURE_BOOKE) diff --git a/arch/powerpc/kernel/dma-iommu.c b/arch/powerpc/kernel/dma-iommu.c index fb7cbaa37658..8f7abf9baa63 100644 --- a/arch/powerpc/kernel/dma-iommu.c +++ b/arch/powerpc/kernel/dma-iommu.c @@ -105,6 +105,11 @@ static u64 dma_iommu_get_required_mask(struct device *dev) return mask; } +int dma_iommu_mapping_error(struct device *dev, dma_addr_t dma_addr) +{ + return dma_addr == IOMMU_MAPPING_ERROR; +} + struct dma_map_ops dma_iommu_ops = { .alloc = dma_iommu_alloc_coherent, .free = dma_iommu_free_coherent, @@ -115,5 +120,6 @@ struct dma_map_ops dma_iommu_ops = { .map_page = dma_iommu_map_page, .unmap_page = dma_iommu_unmap_page, .get_required_mask = dma_iommu_get_required_mask, + .mapping_error = dma_iommu_mapping_error, }; EXPORT_SYMBOL(dma_iommu_ops); diff --git a/arch/powerpc/kernel/dma.c b/arch/powerpc/kernel/dma.c index 41c749586bd2..4194bbbbdb10 100644 --- a/arch/powerpc/kernel/dma.c +++ b/arch/powerpc/kernel/dma.c @@ -314,18 +314,6 @@ EXPORT_SYMBOL(dma_set_coherent_mask); #define PREALLOC_DMA_DEBUG_ENTRIES (1 << 16) -int __dma_set_mask(struct device *dev, u64 dma_mask) -{ - const struct dma_map_ops *dma_ops = get_dma_ops(dev); - - if ((dma_ops != NULL) && (dma_ops->set_dma_mask != NULL)) - return dma_ops->set_dma_mask(dev, dma_mask); - if (!dev->dma_mask || !dma_supported(dev, dma_mask)) - return -EIO; - *dev->dma_mask = dma_mask; - return 0; -} - int dma_set_mask(struct device *dev, u64 dma_mask) { if (ppc_md.dma_set_mask) @@ -338,7 +326,10 @@ int dma_set_mask(struct device *dev, u64 dma_mask) return phb->controller_ops.dma_set_mask(pdev, dma_mask); } - return __dma_set_mask(dev, dma_mask); + if (!dev->dma_mask || !dma_supported(dev, dma_mask)) + return -EIO; + *dev->dma_mask = dma_mask; + return 0; } EXPORT_SYMBOL(dma_set_mask); diff --git a/arch/powerpc/kernel/dt_cpu_ftrs.c b/arch/powerpc/kernel/dt_cpu_ftrs.c index fcc7588a96d6..4c7656dc4e04 100644 --- a/arch/powerpc/kernel/dt_cpu_ftrs.c +++ b/arch/powerpc/kernel/dt_cpu_ftrs.c @@ -8,6 +8,7 @@ #include <linux/export.h> #include <linux/init.h> #include <linux/jump_label.h> +#include <linux/libfdt.h> #include <linux/memblock.h> #include <linux/printk.h> #include <linux/sched.h> @@ -642,7 +643,6 @@ static struct dt_cpu_feature_match __initdata {"processor-control-facility", feat_enable_dbell, CPU_FTR_DBELL}, {"processor-control-facility-v3", feat_enable_dbell, CPU_FTR_DBELL}, {"processor-utilization-of-resources-register", feat_enable_purr, 0}, - {"subcore", feat_enable, CPU_FTR_SUBCORE}, {"no-execute", feat_enable, 0}, {"strong-access-ordering", feat_enable, CPU_FTR_SAO}, {"cache-inhibited-large-page", feat_enable_large_ci, 0}, @@ -671,12 +671,24 @@ static struct dt_cpu_feature_match __initdata {"wait-v3", feat_enable, 0}, }; -/* XXX: how to configure this? Default + boot time? */ -#ifdef CONFIG_PPC_CPUFEATURES_ENABLE_UNKNOWN -#define CPU_FEATURE_ENABLE_UNKNOWN 1 -#else -#define CPU_FEATURE_ENABLE_UNKNOWN 0 -#endif +static bool __initdata using_dt_cpu_ftrs; +static bool __initdata enable_unknown = true; + +static int __init dt_cpu_ftrs_parse(char *str) +{ + if (!str) + return 0; + + if (!strcmp(str, "off")) + using_dt_cpu_ftrs = false; + else if (!strcmp(str, "known")) + enable_unknown = false; + else + return 1; + + return 0; +} +early_param("dt_cpu_ftrs", dt_cpu_ftrs_parse); static void __init cpufeatures_setup_start(u32 isa) { @@ -707,7 +719,7 @@ static bool __init cpufeatures_process_feature(struct dt_cpu_feature *f) } } - if (!known && CPU_FEATURE_ENABLE_UNKNOWN) { + if (!known && enable_unknown) { if (!feat_try_enable_unknown(f)) { pr_info("not enabling: %s (unknown and unsupported by kernel)\n", f->name); @@ -756,6 +768,26 @@ static void __init cpufeatures_setup_finished(void) cur_cpu_spec->cpu_features, cur_cpu_spec->mmu_features); } +static int __init disabled_on_cmdline(void) +{ + unsigned long root, chosen; + const char *p; + + root = of_get_flat_dt_root(); + chosen = of_get_flat_dt_subnode_by_name(root, "chosen"); + if (chosen == -FDT_ERR_NOTFOUND) + return false; + + p = of_get_flat_dt_prop(chosen, "bootargs", NULL); + if (!p) + return false; + + if (strstr(p, "dt_cpu_ftrs=off")) + return true; + + return false; +} + static int __init fdt_find_cpu_features(unsigned long node, const char *uname, int depth, void *data) { @@ -766,8 +798,6 @@ static int __init fdt_find_cpu_features(unsigned long node, const char *uname, return 0; } -static bool __initdata using_dt_cpu_ftrs = false; - bool __init dt_cpu_ftrs_in_use(void) { return using_dt_cpu_ftrs; @@ -775,6 +805,8 @@ bool __init dt_cpu_ftrs_in_use(void) bool __init dt_cpu_ftrs_init(void *fdt) { + using_dt_cpu_ftrs = false; + /* Setup and verify the FDT, if it fails we just bail */ if (!early_init_dt_verify(fdt)) return false; @@ -782,6 +814,9 @@ bool __init dt_cpu_ftrs_init(void *fdt) if (!of_scan_flat_dt(fdt_find_cpu_features, NULL)) return false; + if (disabled_on_cmdline()) + return false; + cpufeatures_setup_cpu(); using_dt_cpu_ftrs = true; @@ -1027,5 +1062,8 @@ static int __init dt_cpu_ftrs_scan_callback(unsigned long node, const char void __init dt_cpu_ftrs_scan(void) { + if (!using_dt_cpu_ftrs) + return; + of_scan_flat_dt(dt_cpu_ftrs_scan_callback, NULL); } diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index ae418b85c17c..b886795060fd 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -1411,10 +1411,8 @@ USE_TEXT_SECTION() .balign IFETCH_ALIGN_BYTES do_hash_page: #ifdef CONFIG_PPC_STD_MMU_64 - andis. r0,r4,0xa410 /* weird error? */ + andis. r0,r4,0xa450 /* weird error? */ bne- handle_page_fault /* if not, try to insert a HPTE */ - andis. r0,r4,DSISR_DABRMATCH@h - bne- handle_dabr_fault CURRENT_THREAD_INFO(r11, r1) lwz r0,TI_PREEMPT(r11) /* If we're in an "NMI" */ andis. r0,r0,NMI_MASK@h /* (i.e. an irq when soft-disabled) */ @@ -1438,11 +1436,16 @@ do_hash_page: /* Error */ blt- 13f + + /* Reload DSISR into r4 for the DABR check below */ + ld r4,_DSISR(r1) #endif /* CONFIG_PPC_STD_MMU_64 */ /* Here we have a page fault that hash_page can't handle. */ handle_page_fault: -11: ld r4,_DAR(r1) +11: andis. r0,r4,DSISR_DABRMATCH@h + bne- handle_dabr_fault + ld r4,_DAR(r1) ld r5,_DSISR(r1) addi r3,r1,STACK_FRAME_OVERHEAD bl do_page_fault diff --git a/arch/powerpc/kernel/idle_book3s.S b/arch/powerpc/kernel/idle_book3s.S index 07d4e0ad60db..4898d676dcae 100644 --- a/arch/powerpc/kernel/idle_book3s.S +++ b/arch/powerpc/kernel/idle_book3s.S @@ -416,7 +416,7 @@ power9_dd1_recover_paca: * which needs to be restored from the stack. */ li r3, 1 - stb r0,PACA_NAPSTATELOST(r13) + stb r3,PACA_NAPSTATELOST(r13) blr /* diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c index f2b724cd9e64..233ca3fe4754 100644 --- a/arch/powerpc/kernel/iommu.c +++ b/arch/powerpc/kernel/iommu.c @@ -198,11 +198,11 @@ static unsigned long iommu_range_alloc(struct device *dev, if (unlikely(npages == 0)) { if (printk_ratelimit()) WARN_ON(1); - return DMA_ERROR_CODE; + return IOMMU_MAPPING_ERROR; } if (should_fail_iommu(dev)) - return DMA_ERROR_CODE; + return IOMMU_MAPPING_ERROR; /* * We don't need to disable preemption here because any CPU can @@ -278,7 +278,7 @@ again: } else { /* Give up */ spin_unlock_irqrestore(&(pool->lock), flags); - return DMA_ERROR_CODE; + return IOMMU_MAPPING_ERROR; } } @@ -310,13 +310,13 @@ static dma_addr_t iommu_alloc(struct device *dev, struct iommu_table *tbl, unsigned long attrs) { unsigned long entry; - dma_addr_t ret = DMA_ERROR_CODE; + dma_addr_t ret = IOMMU_MAPPING_ERROR; int build_fail; entry = iommu_range_alloc(dev, tbl, npages, NULL, mask, align_order); - if (unlikely(entry == DMA_ERROR_CODE)) - return DMA_ERROR_CODE; + if (unlikely(entry == IOMMU_MAPPING_ERROR)) + return IOMMU_MAPPING_ERROR; entry += tbl->it_offset; /* Offset into real TCE table */ ret = entry << tbl->it_page_shift; /* Set the return dma address */ @@ -328,12 +328,12 @@ static dma_addr_t iommu_alloc(struct device *dev, struct iommu_table *tbl, /* tbl->it_ops->set() only returns non-zero for transient errors. * Clean up the table bitmap in this case and return - * DMA_ERROR_CODE. For all other errors the functionality is + * IOMMU_MAPPING_ERROR. For all other errors the functionality is * not altered. */ if (unlikely(build_fail)) { __iommu_free(tbl, ret, npages); - return DMA_ERROR_CODE; + return IOMMU_MAPPING_ERROR; } /* Flush/invalidate TLB caches if necessary */ @@ -478,7 +478,7 @@ int ppc_iommu_map_sg(struct device *dev, struct iommu_table *tbl, DBG(" - vaddr: %lx, size: %lx\n", vaddr, slen); /* Handle failure */ - if (unlikely(entry == DMA_ERROR_CODE)) { + if (unlikely(entry == IOMMU_MAPPING_ERROR)) { if (!(attrs & DMA_ATTR_NO_WARN) && printk_ratelimit()) dev_info(dev, "iommu_alloc failed, tbl %p " @@ -545,7 +545,7 @@ int ppc_iommu_map_sg(struct device *dev, struct iommu_table *tbl, */ if (outcount < incount) { outs = sg_next(outs); - outs->dma_address = DMA_ERROR_CODE; + outs->dma_address = IOMMU_MAPPING_ERROR; outs->dma_length = 0; } @@ -563,7 +563,7 @@ int ppc_iommu_map_sg(struct device *dev, struct iommu_table *tbl, npages = iommu_num_pages(s->dma_address, s->dma_length, IOMMU_PAGE_SIZE(tbl)); __iommu_free(tbl, vaddr, npages); - s->dma_address = DMA_ERROR_CODE; + s->dma_address = IOMMU_MAPPING_ERROR; s->dma_length = 0; } if (s == outs) @@ -777,7 +777,7 @@ dma_addr_t iommu_map_page(struct device *dev, struct iommu_table *tbl, unsigned long mask, enum dma_data_direction direction, unsigned long attrs) { - dma_addr_t dma_handle = DMA_ERROR_CODE; + dma_addr_t dma_handle = IOMMU_MAPPING_ERROR; void *vaddr; unsigned long uaddr; unsigned int npages, align; @@ -797,7 +797,7 @@ dma_addr_t iommu_map_page(struct device *dev, struct iommu_table *tbl, dma_handle = iommu_alloc(dev, tbl, vaddr, npages, direction, mask >> tbl->it_page_shift, align, attrs); - if (dma_handle == DMA_ERROR_CODE) { + if (dma_handle == IOMMU_MAPPING_ERROR) { if (!(attrs & DMA_ATTR_NO_WARN) && printk_ratelimit()) { dev_info(dev, "iommu_alloc failed, tbl %p " @@ -869,7 +869,7 @@ void *iommu_alloc_coherent(struct device *dev, struct iommu_table *tbl, io_order = get_iommu_order(size, tbl); mapping = iommu_alloc(dev, tbl, ret, nio_pages, DMA_BIDIRECTIONAL, mask >> tbl->it_page_shift, io_order, 0); - if (mapping == DMA_ERROR_CODE) { + if (mapping == IOMMU_MAPPING_ERROR) { free_pages((unsigned long)ret, order); return NULL; } diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c index 160ae0fa7d0d..01addfb0ed0a 100644 --- a/arch/powerpc/kernel/kprobes.c +++ b/arch/powerpc/kernel/kprobes.c @@ -43,6 +43,12 @@ DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk); struct kretprobe_blackpoint kretprobe_blacklist[] = {{NULL, NULL}}; +int is_current_kprobe_addr(unsigned long addr) +{ + struct kprobe *p = kprobe_running(); + return (p && (unsigned long)p->addr == addr) ? 1 : 0; +} + bool arch_within_kprobe_blacklist(unsigned long addr) { return (addr >= (unsigned long)__kprobes_text_start && @@ -305,16 +311,17 @@ int kprobe_handler(struct pt_regs *regs) save_previous_kprobe(kcb); set_current_kprobe(p, regs, kcb); kprobes_inc_nmissed_count(p); - prepare_singlestep(p, regs); kcb->kprobe_status = KPROBE_REENTER; if (p->ainsn.boostable >= 0) { ret = try_to_emulate(p, regs); if (ret > 0) { restore_previous_kprobe(kcb); + preempt_enable_no_resched(); return 1; } } + prepare_singlestep(p, regs); return 1; } else { if (*addr != BREAKPOINT_INSTRUCTION) { @@ -616,6 +623,15 @@ int setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs) regs->gpr[2] = (unsigned long)(((func_descr_t *)jp->entry)->toc); #endif + /* + * jprobes use jprobe_return() which skips the normal return + * path of the function, and this messes up the accounting of the + * function graph tracer. + * + * Pause function graph tracing while performing the jprobe function. + */ + pause_graph_tracing(); + return 1; } NOKPROBE_SYMBOL(setjmp_pre_handler); @@ -641,6 +657,8 @@ int longjmp_break_handler(struct kprobe *p, struct pt_regs *regs) * saved regs... */ memcpy(regs, &kcb->jprobe_saved_regs, sizeof(struct pt_regs)); + /* It's OK to start function graph tracing again */ + unpause_graph_tracing(); preempt_enable_no_resched(); return 1; } diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c index 5f9eada3519b..a9bfa49f3698 100644 --- a/arch/powerpc/kernel/mce.c +++ b/arch/powerpc/kernel/mce.c @@ -405,6 +405,7 @@ void machine_check_print_event_info(struct machine_check_event *evt, break; } } +EXPORT_SYMBOL_GPL(machine_check_print_event_info); uint64_t get_mce_fault_addr(struct machine_check_event *evt) { diff --git a/arch/powerpc/kernel/nvram_64.c b/arch/powerpc/kernel/nvram_64.c index eae61b044e9e..496d6393bd41 100644 --- a/arch/powerpc/kernel/nvram_64.c +++ b/arch/powerpc/kernel/nvram_64.c @@ -792,21 +792,17 @@ static ssize_t dev_nvram_write(struct file *file, const char __user *buf, count = min_t(size_t, count, size - *ppos); count = min(count, PAGE_SIZE); - ret = -ENOMEM; - tmp = kmalloc(count, GFP_KERNEL); - if (!tmp) - goto out; - - ret = -EFAULT; - if (copy_from_user(tmp, buf, count)) + tmp = memdup_user(buf, count); + if (IS_ERR(tmp)) { + ret = PTR_ERR(tmp); goto out; + } ret = ppc_md.nvram_write(tmp, count, ppos); -out: kfree(tmp); +out: return ret; - } static long dev_nvram_ioctl(struct file *file, unsigned int cmd, diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index d645da302bf2..2ad725ef4368 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -864,6 +864,25 @@ static void tm_reclaim_thread(struct thread_struct *thr, if (!MSR_TM_SUSPENDED(mfmsr())) return; + /* + * If we are in a transaction and FP is off then we can't have + * used FP inside that transaction. Hence the checkpointed + * state is the same as the live state. We need to copy the + * live state to the checkpointed state so that when the + * transaction is restored, the checkpointed state is correct + * and the aborted transaction sees the correct state. We use + * ckpt_regs.msr here as that's what tm_reclaim will use to + * determine if it's going to write the checkpointed state or + * not. So either this will write the checkpointed registers, + * or reclaim will. Similarly for VMX. + */ + if ((thr->ckpt_regs.msr & MSR_FP) == 0) + memcpy(&thr->ckfp_state, &thr->fp_state, + sizeof(struct thread_fp_state)); + if ((thr->ckpt_regs.msr & MSR_VEC) == 0) + memcpy(&thr->ckvr_state, &thr->vr_state, + sizeof(struct thread_vr_state)); + giveup_all(container_of(thr, struct task_struct, thread)); tm_reclaim(thr, thr->ckpt_regs.msr, cause); @@ -1647,6 +1666,7 @@ void start_thread(struct pt_regs *regs, unsigned long start, unsigned long sp) #ifdef CONFIG_VSX current->thread.used_vsr = 0; #endif + current->thread.load_fp = 0; memset(¤t->thread.fp_state, 0, sizeof(current->thread.fp_state)); current->thread.fp_save_area = NULL; #ifdef CONFIG_ALTIVEC @@ -1655,6 +1675,7 @@ void start_thread(struct pt_regs *regs, unsigned long start, unsigned long sp) current->thread.vr_save_area = NULL; current->thread.vrsave = 0; current->thread.used_vr = 0; + current->thread.load_vec = 0; #endif /* CONFIG_ALTIVEC */ #ifdef CONFIG_SPE memset(current->thread.evr, 0, sizeof(current->thread.evr)); @@ -1666,6 +1687,7 @@ void start_thread(struct pt_regs *regs, unsigned long start, unsigned long sp) current->thread.tm_tfhar = 0; current->thread.tm_texasr = 0; current->thread.tm_tfiar = 0; + current->thread.load_tm = 0; #endif /* CONFIG_PPC_TRANSACTIONAL_MEM */ } EXPORT_SYMBOL(start_thread); diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c index 40c4887c27b6..f83056297441 100644 --- a/arch/powerpc/kernel/prom.c +++ b/arch/powerpc/kernel/prom.c @@ -161,7 +161,9 @@ static struct ibm_pa_feature { { .pabyte = 0, .pabit = 3, .cpu_features = CPU_FTR_CTRL }, { .pabyte = 0, .pabit = 6, .cpu_features = CPU_FTR_NOEXECUTE }, { .pabyte = 1, .pabit = 2, .mmu_features = MMU_FTR_CI_LARGE_PAGE }, +#ifdef CONFIG_PPC_RADIX_MMU { .pabyte = 40, .pabit = 0, .mmu_features = MMU_FTR_TYPE_RADIX }, +#endif { .pabyte = 1, .pabit = 1, .invert = 1, .cpu_features = CPU_FTR_NODSISRALIGN }, { .pabyte = 5, .pabit = 0, .cpu_features = CPU_FTR_REAL_LE, .cpu_user_ftrs = PPC_FEATURE_TRUE_LE }, diff --git a/arch/powerpc/kernel/rtasd.c b/arch/powerpc/kernel/rtasd.c index 3650732639ed..0f0b1b2f3b60 100644 --- a/arch/powerpc/kernel/rtasd.c +++ b/arch/powerpc/kernel/rtasd.c @@ -283,7 +283,7 @@ static void prrn_work_fn(struct work_struct *work) * the RTAS event. */ pseries_devicetree_update(-prrn_update_scope); - arch_update_cpu_topology(); + numa_update_cpu_topology(false); } static DECLARE_WORK(prrn_work, prrn_work_fn); diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index 71dcda91755d..857129acf960 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -928,7 +928,7 @@ void __init setup_arch(char **cmdline_p) #ifdef CONFIG_PPC_MM_SLICES #ifdef CONFIG_PPC64 - init_mm.context.addr_limit = TASK_SIZE_128TB; + init_mm.context.addr_limit = DEFAULT_MAP_WINDOW_USER64; #else #error "context.addr_limit not initialized." #endif diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index f35ff9dea4fb..4640f6d64f8b 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -616,6 +616,24 @@ void __init exc_lvl_early_init(void) #endif /* + * Emergency stacks are used for a range of things, from asynchronous + * NMIs (system reset, machine check) to synchronous, process context. + * We set preempt_count to zero, even though that isn't necessarily correct. To + * get the right value we'd need to copy it from the previous thread_info, but + * doing that might fault causing more problems. + * TODO: what to do with accounting? + */ +static void emerg_stack_init_thread_info(struct thread_info *ti, int cpu) +{ + ti->task = NULL; + ti->cpu = cpu; + ti->preempt_count = 0; + ti->local_flags = 0; + ti->flags = 0; + klp_init_thread_info(ti); +} + +/* * Stack space used when we detect a bad kernel stack pointer, and * early in SMP boots before relocation is enabled. Exclusive emergency * stack for machine checks. @@ -633,24 +651,31 @@ void __init emergency_stack_init(void) * Since we use these as temporary stacks during secondary CPU * bringup, we need to get at them in real mode. This means they * must also be within the RMO region. + * + * The IRQ stacks allocated elsewhere in this file are zeroed and + * initialized in kernel/irq.c. These are initialized here in order + * to have emergency stacks available as early as possible. */ limit = min(safe_stack_limit(), ppc64_rma_size); for_each_possible_cpu(i) { struct thread_info *ti; ti = __va(memblock_alloc_base(THREAD_SIZE, THREAD_SIZE, limit)); - klp_init_thread_info(ti); + memset(ti, 0, THREAD_SIZE); + emerg_stack_init_thread_info(ti, i); paca[i].emergency_sp = (void *)ti + THREAD_SIZE; #ifdef CONFIG_PPC_BOOK3S_64 /* emergency stack for NMI exception handling. */ ti = __va(memblock_alloc_base(THREAD_SIZE, THREAD_SIZE, limit)); - klp_init_thread_info(ti); + memset(ti, 0, THREAD_SIZE); + emerg_stack_init_thread_info(ti, i); paca[i].nmi_emergency_sp = (void *)ti + THREAD_SIZE; /* emergency stack for machine check exception handling. */ ti = __va(memblock_alloc_base(THREAD_SIZE, THREAD_SIZE, limit)); - klp_init_thread_info(ti); + memset(ti, 0, THREAD_SIZE); + emerg_stack_init_thread_info(ti, i); paca[i].mc_emergency_sp = (void *)ti + THREAD_SIZE; #endif } @@ -661,7 +686,7 @@ void __init emergency_stack_init(void) static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size, size_t align) { - return __alloc_bootmem_node(NODE_DATA(cpu_to_node(cpu)), size, align, + return __alloc_bootmem_node(NODE_DATA(early_cpu_to_node(cpu)), size, align, __pa(MAX_DMA_ADDRESS)); } @@ -672,7 +697,7 @@ static void __init pcpu_fc_free(void *ptr, size_t size) static int pcpu_cpu_distance(unsigned int from, unsigned int to) { - if (cpu_to_node(from) == cpu_to_node(to)) + if (early_cpu_to_node(from) == early_cpu_to_node(to)) return LOCAL_DISTANCE; else return REMOTE_DISTANCE; diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index df2a41647d8e..1069f74fca47 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -97,7 +97,7 @@ int smp_generic_cpu_bootable(unsigned int nr) /* Special case - we inhibit secondary thread startup * during boot if the user requests it. */ - if (system_state == SYSTEM_BOOTING && cpu_has_feature(CPU_FTR_SMT)) { + if (system_state < SYSTEM_RUNNING && cpu_has_feature(CPU_FTR_SMT)) { if (!smt_enabled_at_boot && cpu_thread_in_core(nr) != 0) return 0; if (smt_enabled_at_boot diff --git a/arch/powerpc/kernel/trace/ftrace_64_mprofile.S b/arch/powerpc/kernel/trace/ftrace_64_mprofile.S index 7c933a99f5d5..c98e90b4ea7b 100644 --- a/arch/powerpc/kernel/trace/ftrace_64_mprofile.S +++ b/arch/powerpc/kernel/trace/ftrace_64_mprofile.S @@ -45,10 +45,14 @@ _GLOBAL(ftrace_caller) stdu r1,-SWITCH_FRAME_SIZE(r1) /* Save all gprs to pt_regs */ - SAVE_8GPRS(0,r1) - SAVE_8GPRS(8,r1) - SAVE_8GPRS(16,r1) - SAVE_8GPRS(24,r1) + SAVE_GPR(0, r1) + SAVE_10GPRS(2, r1) + SAVE_10GPRS(12, r1) + SAVE_10GPRS(22, r1) + + /* Save previous stack pointer (r1) */ + addi r8, r1, SWITCH_FRAME_SIZE + std r8, GPR1(r1) /* Load special regs for save below */ mfmsr r8 @@ -95,18 +99,44 @@ ftrace_call: bl ftrace_stub nop - /* Load ctr with the possibly modified NIP */ - ld r3, _NIP(r1) - mtctr r3 + /* Load the possibly modified NIP */ + ld r15, _NIP(r1) + #ifdef CONFIG_LIVEPATCH - cmpd r14,r3 /* has NIP been altered? */ + cmpd r14, r15 /* has NIP been altered? */ +#endif + +#if defined(CONFIG_LIVEPATCH) && defined(CONFIG_KPROBES_ON_FTRACE) + /* NIP has not been altered, skip over further checks */ + beq 1f + + /* Check if there is an active kprobe on us */ + subi r3, r14, 4 + bl is_current_kprobe_addr + nop + + /* + * If r3 == 1, then this is a kprobe/jprobe. + * else, this is livepatched function. + * + * The conditional branch for livepatch_handler below will use the + * result of this comparison. For kprobe/jprobe, we just need to branch to + * the new NIP, not call livepatch_handler. The branch below is bne, so we + * want CR0[EQ] to be true if this is a kprobe/jprobe. Which means we want + * CR0[EQ] = (r3 == 1). + */ + cmpdi r3, 1 +1: #endif + /* Load CTR with the possibly modified NIP */ + mtctr r15 + /* Restore gprs */ - REST_8GPRS(0,r1) - REST_8GPRS(8,r1) - REST_8GPRS(16,r1) - REST_8GPRS(24,r1) + REST_GPR(0,r1) + REST_10GPRS(2,r1) + REST_10GPRS(12,r1) + REST_10GPRS(22,r1) /* Restore possibly modified LR */ ld r0, _LINK(r1) @@ -119,7 +149,10 @@ ftrace_call: addi r1, r1, SWITCH_FRAME_SIZE #ifdef CONFIG_LIVEPATCH - /* Based on the cmpd above, if the NIP was altered handle livepatch */ + /* + * Based on the cmpd or cmpdi above, if the NIP was altered and we're + * not on a kprobe/jprobe, then handle livepatch. + */ bne- livepatch_handler #endif diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig index 24de532c1736..0c52cb5d43f5 100644 --- a/arch/powerpc/kvm/Kconfig +++ b/arch/powerpc/kvm/Kconfig @@ -67,7 +67,7 @@ config KVM_BOOK3S_64 select KVM_BOOK3S_64_HANDLER select KVM select KVM_BOOK3S_PR_POSSIBLE if !KVM_BOOK3S_HV_POSSIBLE - select SPAPR_TCE_IOMMU if IOMMU_SUPPORT + select SPAPR_TCE_IOMMU if IOMMU_SUPPORT && (PPC_SERIES || PPC_POWERNV) ---help--- Support running unmodified book3s_64 and book3s_32 guest kernels in virtual machines on book3s_64 host processors. diff --git a/arch/powerpc/kvm/Makefile b/arch/powerpc/kvm/Makefile index d91a2604c496..381a6ec0ff3b 100644 --- a/arch/powerpc/kvm/Makefile +++ b/arch/powerpc/kvm/Makefile @@ -46,7 +46,7 @@ kvm-e500mc-objs := \ e500_emulate.o kvm-objs-$(CONFIG_KVM_E500MC) := $(kvm-e500mc-objs) -kvm-book3s_64-builtin-objs-$(CONFIG_KVM_BOOK3S_64_HANDLER) := \ +kvm-book3s_64-builtin-objs-$(CONFIG_SPAPR_TCE_IOMMU) := \ book3s_64_vio_hv.o kvm-pr-y := \ @@ -90,11 +90,11 @@ kvm-book3s_64-objs-$(CONFIG_KVM_XICS) += \ book3s_xics.o kvm-book3s_64-objs-$(CONFIG_KVM_XIVE) += book3s_xive.o +kvm-book3s_64-objs-$(CONFIG_SPAPR_TCE_IOMMU) += book3s_64_vio.o kvm-book3s_64-module-objs := \ $(common-objs-y) \ book3s.o \ - book3s_64_vio.o \ book3s_rtas.o \ $(kvm-book3s_64-objs-y) diff --git a/arch/powerpc/kvm/book3s_64_vio_hv.c b/arch/powerpc/kvm/book3s_64_vio_hv.c index eda0a8f6fae8..3adfd2f5301c 100644 --- a/arch/powerpc/kvm/book3s_64_vio_hv.c +++ b/arch/powerpc/kvm/book3s_64_vio_hv.c @@ -301,6 +301,10 @@ long kvmppc_rm_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn, /* udbg_printf("H_PUT_TCE(): liobn=0x%lx ioba=0x%lx, tce=0x%lx\n", */ /* liobn, ioba, tce); */ + /* For radix, we might be in virtual mode, so punt */ + if (kvm_is_radix(vcpu->kvm)) + return H_TOO_HARD; + stt = kvmppc_find_table(vcpu->kvm, liobn); if (!stt) return H_TOO_HARD; @@ -381,6 +385,10 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu, bool prereg = false; struct kvmppc_spapr_tce_iommu_table *stit; + /* For radix, we might be in virtual mode, so punt */ + if (kvm_is_radix(vcpu->kvm)) + return H_TOO_HARD; + stt = kvmppc_find_table(vcpu->kvm, liobn); if (!stt) return H_TOO_HARD; @@ -491,6 +499,10 @@ long kvmppc_rm_h_stuff_tce(struct kvm_vcpu *vcpu, long i, ret; struct kvmppc_spapr_tce_iommu_table *stit; + /* For radix, we might be in virtual mode, so punt */ + if (kvm_is_radix(vcpu->kvm)) + return H_TOO_HARD; + stt = kvmppc_find_table(vcpu->kvm, liobn); if (!stt) return H_TOO_HARD; @@ -527,6 +539,7 @@ long kvmppc_rm_h_stuff_tce(struct kvm_vcpu *vcpu, return H_SUCCESS; } +/* This can be called in either virtual mode or real mode */ long kvmppc_h_get_tce(struct kvm_vcpu *vcpu, unsigned long liobn, unsigned long ioba) { diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index 42b7a4fd57d9..0b436df746fc 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -46,6 +46,8 @@ #include <linux/of.h> #include <asm/reg.h> +#include <asm/ppc-opcode.h> +#include <asm/disassemble.h> #include <asm/cputable.h> #include <asm/cacheflush.h> #include <asm/tlbflush.h> @@ -645,6 +647,7 @@ static void kvmppc_create_dtl_entry(struct kvm_vcpu *vcpu, unsigned long stolen; unsigned long core_stolen; u64 now; + unsigned long flags; dt = vcpu->arch.dtl_ptr; vpa = vcpu->arch.vpa.pinned_addr; @@ -652,10 +655,10 @@ static void kvmppc_create_dtl_entry(struct kvm_vcpu *vcpu, core_stolen = vcore_stolen_time(vc, now); stolen = core_stolen - vcpu->arch.stolen_logged; vcpu->arch.stolen_logged = core_stolen; - spin_lock_irq(&vcpu->arch.tbacct_lock); + spin_lock_irqsave(&vcpu->arch.tbacct_lock, flags); stolen += vcpu->arch.busy_stolen; vcpu->arch.busy_stolen = 0; - spin_unlock_irq(&vcpu->arch.tbacct_lock); + spin_unlock_irqrestore(&vcpu->arch.tbacct_lock, flags); if (!dt || !vpa) return; memset(dt, 0, sizeof(struct dtl_entry)); @@ -675,6 +678,26 @@ static void kvmppc_create_dtl_entry(struct kvm_vcpu *vcpu, vcpu->arch.dtl.dirty = true; } +/* See if there is a doorbell interrupt pending for a vcpu */ +static bool kvmppc_doorbell_pending(struct kvm_vcpu *vcpu) +{ + int thr; + struct kvmppc_vcore *vc; + + if (vcpu->arch.doorbell_request) + return true; + /* + * Ensure that the read of vcore->dpdes comes after the read + * of vcpu->doorbell_request. This barrier matches the + * lwsync in book3s_hv_rmhandlers.S just before the + * fast_guest_return label. + */ + smp_rmb(); + vc = vcpu->arch.vcore; + thr = vcpu->vcpu_id - vc->first_vcpuid; + return !!(vc->dpdes & (1 << thr)); +} + static bool kvmppc_power8_compatible(struct kvm_vcpu *vcpu) { if (vcpu->arch.vcore->arch_compat >= PVR_ARCH_207) @@ -926,6 +949,101 @@ static int kvmppc_emulate_debug_inst(struct kvm_run *run, } } +static void do_nothing(void *x) +{ +} + +static unsigned long kvmppc_read_dpdes(struct kvm_vcpu *vcpu) +{ + int thr, cpu, pcpu, nthreads; + struct kvm_vcpu *v; + unsigned long dpdes; + + nthreads = vcpu->kvm->arch.emul_smt_mode; + dpdes = 0; + cpu = vcpu->vcpu_id & ~(nthreads - 1); + for (thr = 0; thr < nthreads; ++thr, ++cpu) { + v = kvmppc_find_vcpu(vcpu->kvm, cpu); + if (!v) + continue; + /* + * If the vcpu is currently running on a physical cpu thread, + * interrupt it in order to pull it out of the guest briefly, + * which will update its vcore->dpdes value. + */ + pcpu = READ_ONCE(v->cpu); + if (pcpu >= 0) + smp_call_function_single(pcpu, do_nothing, NULL, 1); + if (kvmppc_doorbell_pending(v)) + dpdes |= 1 << thr; + } + return dpdes; +} + +/* + * On POWER9, emulate doorbell-related instructions in order to + * give the guest the illusion of running on a multi-threaded core. + * The instructions emulated are msgsndp, msgclrp, mfspr TIR, + * and mfspr DPDES. + */ +static int kvmppc_emulate_doorbell_instr(struct kvm_vcpu *vcpu) +{ + u32 inst, rb, thr; + unsigned long arg; + struct kvm *kvm = vcpu->kvm; + struct kvm_vcpu *tvcpu; + + if (!cpu_has_feature(CPU_FTR_ARCH_300)) + return EMULATE_FAIL; + if (kvmppc_get_last_inst(vcpu, INST_GENERIC, &inst) != EMULATE_DONE) + return RESUME_GUEST; + if (get_op(inst) != 31) + return EMULATE_FAIL; + rb = get_rb(inst); + thr = vcpu->vcpu_id & (kvm->arch.emul_smt_mode - 1); + switch (get_xop(inst)) { + case OP_31_XOP_MSGSNDP: + arg = kvmppc_get_gpr(vcpu, rb); + if (((arg >> 27) & 0xf) != PPC_DBELL_SERVER) + break; + arg &= 0x3f; + if (arg >= kvm->arch.emul_smt_mode) + break; + tvcpu = kvmppc_find_vcpu(kvm, vcpu->vcpu_id - thr + arg); + if (!tvcpu) + break; + if (!tvcpu->arch.doorbell_request) { + tvcpu->arch.doorbell_request = 1; + kvmppc_fast_vcpu_kick_hv(tvcpu); + } + break; + case OP_31_XOP_MSGCLRP: + arg = kvmppc_get_gpr(vcpu, rb); + if (((arg >> 27) & 0xf) != PPC_DBELL_SERVER) + break; + vcpu->arch.vcore->dpdes = 0; + vcpu->arch.doorbell_request = 0; + break; + case OP_31_XOP_MFSPR: + switch (get_sprn(inst)) { + case SPRN_TIR: + arg = thr; + break; + case SPRN_DPDES: + arg = kvmppc_read_dpdes(vcpu); + break; + default: + return EMULATE_FAIL; + } + kvmppc_set_gpr(vcpu, get_rt(inst), arg); + break; + default: + return EMULATE_FAIL; + } + kvmppc_set_pc(vcpu, kvmppc_get_pc(vcpu) + 4); + return RESUME_GUEST; +} + static int kvmppc_handle_exit_hv(struct kvm_run *run, struct kvm_vcpu *vcpu, struct task_struct *tsk) { @@ -971,15 +1089,20 @@ static int kvmppc_handle_exit_hv(struct kvm_run *run, struct kvm_vcpu *vcpu, r = RESUME_GUEST; break; case BOOK3S_INTERRUPT_MACHINE_CHECK: - /* - * Deliver a machine check interrupt to the guest. - * We have to do this, even if the host has handled the - * machine check, because machine checks use SRR0/1 and - * the interrupt might have trashed guest state in them. - */ - kvmppc_book3s_queue_irqprio(vcpu, - BOOK3S_INTERRUPT_MACHINE_CHECK); - r = RESUME_GUEST; + /* Exit to guest with KVM_EXIT_NMI as exit reason */ + run->exit_reason = KVM_EXIT_NMI; + run->hw.hardware_exit_reason = vcpu->arch.trap; + /* Clear out the old NMI status from run->flags */ + run->flags &= ~KVM_RUN_PPC_NMI_DISP_MASK; + /* Now set the NMI status */ + if (vcpu->arch.mce_evt.disposition == MCE_DISPOSITION_RECOVERED) + run->flags |= KVM_RUN_PPC_NMI_DISP_FULLY_RECOV; + else + run->flags |= KVM_RUN_PPC_NMI_DISP_NOT_RECOV; + + r = RESUME_HOST; + /* Print the MCE event to host console. */ + machine_check_print_event_info(&vcpu->arch.mce_evt, false); break; case BOOK3S_INTERRUPT_PROGRAM: { @@ -1048,12 +1171,19 @@ static int kvmppc_handle_exit_hv(struct kvm_run *run, struct kvm_vcpu *vcpu, break; /* * This occurs if the guest (kernel or userspace), does something that - * is prohibited by HFSCR. We just generate a program interrupt to - * the guest. + * is prohibited by HFSCR. + * On POWER9, this could be a doorbell instruction that we need + * to emulate. + * Otherwise, we just generate a program interrupt to the guest. */ case BOOK3S_INTERRUPT_H_FAC_UNAVAIL: - kvmppc_core_queue_program(vcpu, SRR1_PROGILL); - r = RESUME_GUEST; + r = EMULATE_FAIL; + if ((vcpu->arch.hfscr >> 56) == FSCR_MSGP_LG) + r = kvmppc_emulate_doorbell_instr(vcpu); + if (r == EMULATE_FAIL) { + kvmppc_core_queue_program(vcpu, SRR1_PROGILL); + r = RESUME_GUEST; + } break; case BOOK3S_INTERRUPT_HV_RM_HARD: r = RESUME_PASSTHROUGH; @@ -1143,6 +1273,12 @@ static void kvmppc_set_lpcr(struct kvm_vcpu *vcpu, u64 new_lpcr, mask = LPCR_DPFD | LPCR_ILE | LPCR_TC; if (cpu_has_feature(CPU_FTR_ARCH_207S)) mask |= LPCR_AIL; + /* + * On POWER9, allow userspace to enable large decrementer for the + * guest, whether or not the host has it enabled. + */ + if (cpu_has_feature(CPU_FTR_ARCH_300)) + mask |= LPCR_LD; /* Broken 32-bit version of LPCR must not clear top bits */ if (preserve_top32) @@ -1486,6 +1622,14 @@ static int kvmppc_set_one_reg_hv(struct kvm_vcpu *vcpu, u64 id, r = set_vpa(vcpu, &vcpu->arch.dtl, addr, len); break; case KVM_REG_PPC_TB_OFFSET: + /* + * POWER9 DD1 has an erratum where writing TBU40 causes + * the timebase to lose ticks. So we don't let the + * timebase offset be changed on P9 DD1. (It is + * initialized to zero.) + */ + if (cpu_has_feature(CPU_FTR_POWER9_DD1)) + break; /* round up to multiple of 2^24 */ vcpu->arch.vcore->tb_offset = ALIGN(set_reg_val(id, *val), 1UL << 24); @@ -1603,7 +1747,7 @@ static struct kvmppc_vcore *kvmppc_vcore_create(struct kvm *kvm, int core) init_swait_queue_head(&vcore->wq); vcore->preempt_tb = TB_NIL; vcore->lpcr = kvm->arch.lpcr; - vcore->first_vcpuid = core * threads_per_vcore(); + vcore->first_vcpuid = core * kvm->arch.smt_mode; vcore->kvm = kvm; INIT_LIST_HEAD(&vcore->preempt_list); @@ -1762,14 +1906,10 @@ static struct kvm_vcpu *kvmppc_core_vcpu_create_hv(struct kvm *kvm, unsigned int id) { struct kvm_vcpu *vcpu; - int err = -EINVAL; + int err; int core; struct kvmppc_vcore *vcore; - core = id / threads_per_vcore(); - if (core >= KVM_MAX_VCORES) - goto out; - err = -ENOMEM; vcpu = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL); if (!vcpu) @@ -1800,6 +1940,20 @@ static struct kvm_vcpu *kvmppc_core_vcpu_create_hv(struct kvm *kvm, vcpu->arch.busy_preempt = TB_NIL; vcpu->arch.intr_msr = MSR_SF | MSR_ME; + /* + * Set the default HFSCR for the guest from the host value. + * This value is only used on POWER9. + * On POWER9 DD1, TM doesn't work, so we make sure to + * prevent the guest from using it. + * On POWER9, we want to virtualize the doorbell facility, so we + * turn off the HFSCR bit, which causes those instructions to trap. + */ + vcpu->arch.hfscr = mfspr(SPRN_HFSCR); + if (!cpu_has_feature(CPU_FTR_TM)) + vcpu->arch.hfscr &= ~HFSCR_TM; + if (cpu_has_feature(CPU_FTR_ARCH_300)) + vcpu->arch.hfscr &= ~HFSCR_MSGP; + kvmppc_mmu_book3s_hv_init(vcpu); vcpu->arch.state = KVMPPC_VCPU_NOTREADY; @@ -1807,11 +1961,17 @@ static struct kvm_vcpu *kvmppc_core_vcpu_create_hv(struct kvm *kvm, init_waitqueue_head(&vcpu->arch.cpu_run); mutex_lock(&kvm->lock); - vcore = kvm->arch.vcores[core]; - if (!vcore) { - vcore = kvmppc_vcore_create(kvm, core); - kvm->arch.vcores[core] = vcore; - kvm->arch.online_vcores++; + vcore = NULL; + err = -EINVAL; + core = id / kvm->arch.smt_mode; + if (core < KVM_MAX_VCORES) { + vcore = kvm->arch.vcores[core]; + if (!vcore) { + err = -ENOMEM; + vcore = kvmppc_vcore_create(kvm, core); + kvm->arch.vcores[core] = vcore; + kvm->arch.online_vcores++; + } } mutex_unlock(&kvm->lock); @@ -1839,6 +1999,43 @@ out: return ERR_PTR(err); } +static int kvmhv_set_smt_mode(struct kvm *kvm, unsigned long smt_mode, + unsigned long flags) +{ + int err; + int esmt = 0; + + if (flags) + return -EINVAL; + if (smt_mode > MAX_SMT_THREADS || !is_power_of_2(smt_mode)) + return -EINVAL; + if (!cpu_has_feature(CPU_FTR_ARCH_300)) { + /* + * On POWER8 (or POWER7), the threading mode is "strict", + * so we pack smt_mode vcpus per vcore. + */ + if (smt_mode > threads_per_subcore) + return -EINVAL; + } else { + /* + * On POWER9, the threading mode is "loose", + * so each vcpu gets its own vcore. + */ + esmt = smt_mode; + smt_mode = 1; + } + mutex_lock(&kvm->lock); + err = -EBUSY; + if (!kvm->arch.online_vcores) { + kvm->arch.smt_mode = smt_mode; + kvm->arch.emul_smt_mode = esmt; + err = 0; + } + mutex_unlock(&kvm->lock); + + return err; +} + static void unpin_vpa(struct kvm *kvm, struct kvmppc_vpa *vpa) { if (vpa->pinned_addr) @@ -1889,7 +2086,7 @@ static void kvmppc_end_cede(struct kvm_vcpu *vcpu) } } -extern void __kvmppc_vcore_entry(void); +extern int __kvmppc_vcore_entry(void); static void kvmppc_remove_runnable(struct kvmppc_vcore *vc, struct kvm_vcpu *vcpu) @@ -1954,10 +2151,6 @@ static void kvmppc_release_hwthread(int cpu) tpaca->kvm_hstate.kvm_split_mode = NULL; } -static void do_nothing(void *x) -{ -} - static void radix_flush_cpu(struct kvm *kvm, int cpu, struct kvm_vcpu *vcpu) { int i; @@ -1975,11 +2168,35 @@ static void radix_flush_cpu(struct kvm *kvm, int cpu, struct kvm_vcpu *vcpu) smp_call_function_single(cpu + i, do_nothing, NULL, 1); } +static void kvmppc_prepare_radix_vcpu(struct kvm_vcpu *vcpu, int pcpu) +{ + struct kvm *kvm = vcpu->kvm; + + /* + * With radix, the guest can do TLB invalidations itself, + * and it could choose to use the local form (tlbiel) if + * it is invalidating a translation that has only ever been + * used on one vcpu. However, that doesn't mean it has + * only ever been used on one physical cpu, since vcpus + * can move around between pcpus. To cope with this, when + * a vcpu moves from one pcpu to another, we need to tell + * any vcpus running on the same core as this vcpu previously + * ran to flush the TLB. The TLB is shared between threads, + * so we use a single bit in .need_tlb_flush for all 4 threads. + */ + if (vcpu->arch.prev_cpu != pcpu) { + if (vcpu->arch.prev_cpu >= 0 && + cpu_first_thread_sibling(vcpu->arch.prev_cpu) != + cpu_first_thread_sibling(pcpu)) + radix_flush_cpu(kvm, vcpu->arch.prev_cpu, vcpu); + vcpu->arch.prev_cpu = pcpu; + } +} + static void kvmppc_start_thread(struct kvm_vcpu *vcpu, struct kvmppc_vcore *vc) { int cpu; struct paca_struct *tpaca; - struct kvmppc_vcore *mvc = vc->master_vcore; struct kvm *kvm = vc->kvm; cpu = vc->pcpu; @@ -1989,36 +2206,16 @@ static void kvmppc_start_thread(struct kvm_vcpu *vcpu, struct kvmppc_vcore *vc) vcpu->arch.timer_running = 0; } cpu += vcpu->arch.ptid; - vcpu->cpu = mvc->pcpu; + vcpu->cpu = vc->pcpu; vcpu->arch.thread_cpu = cpu; - - /* - * With radix, the guest can do TLB invalidations itself, - * and it could choose to use the local form (tlbiel) if - * it is invalidating a translation that has only ever been - * used on one vcpu. However, that doesn't mean it has - * only ever been used on one physical cpu, since vcpus - * can move around between pcpus. To cope with this, when - * a vcpu moves from one pcpu to another, we need to tell - * any vcpus running on the same core as this vcpu previously - * ran to flush the TLB. The TLB is shared between threads, - * so we use a single bit in .need_tlb_flush for all 4 threads. - */ - if (kvm_is_radix(kvm) && vcpu->arch.prev_cpu != cpu) { - if (vcpu->arch.prev_cpu >= 0 && - cpu_first_thread_sibling(vcpu->arch.prev_cpu) != - cpu_first_thread_sibling(cpu)) - radix_flush_cpu(kvm, vcpu->arch.prev_cpu, vcpu); - vcpu->arch.prev_cpu = cpu; - } cpumask_set_cpu(cpu, &kvm->arch.cpu_in_guest); } tpaca = &paca[cpu]; tpaca->kvm_hstate.kvm_vcpu = vcpu; - tpaca->kvm_hstate.ptid = cpu - mvc->pcpu; + tpaca->kvm_hstate.ptid = cpu - vc->pcpu; /* Order stores to hstate.kvm_vcpu etc. before store to kvm_vcore */ smp_wmb(); - tpaca->kvm_hstate.kvm_vcore = mvc; + tpaca->kvm_hstate.kvm_vcore = vc; if (cpu != smp_processor_id()) kvmppc_ipi_thread(cpu); } @@ -2147,8 +2344,7 @@ struct core_info { int max_subcore_threads; int total_threads; int subcore_threads[MAX_SUBCORES]; - struct kvm *subcore_vm[MAX_SUBCORES]; - struct list_head vcs[MAX_SUBCORES]; + struct kvmppc_vcore *vc[MAX_SUBCORES]; }; /* @@ -2159,17 +2355,12 @@ static int subcore_thread_map[MAX_SUBCORES] = { 0, 4, 2, 6 }; static void init_core_info(struct core_info *cip, struct kvmppc_vcore *vc) { - int sub; - memset(cip, 0, sizeof(*cip)); cip->n_subcores = 1; cip->max_subcore_threads = vc->num_threads; cip->total_threads = vc->num_threads; cip->subcore_threads[0] = vc->num_threads; - cip->subcore_vm[0] = vc->kvm; - for (sub = 0; sub < MAX_SUBCORES; ++sub) - INIT_LIST_HEAD(&cip->vcs[sub]); - list_add_tail(&vc->preempt_list, &cip->vcs[0]); + cip->vc[0] = vc; } static bool subcore_config_ok(int n_subcores, int n_threads) @@ -2189,9 +2380,8 @@ static bool subcore_config_ok(int n_subcores, int n_threads) return n_subcores * roundup_pow_of_two(n_threads) <= MAX_SMT_THREADS; } -static void init_master_vcore(struct kvmppc_vcore *vc) +static void init_vcore_to_run(struct kvmppc_vcore *vc) { - vc->master_vcore = vc; vc->entry_exit_map = 0; vc->in_guest = 0; vc->napping_threads = 0; @@ -2216,9 +2406,9 @@ static bool can_dynamic_split(struct kvmppc_vcore *vc, struct core_info *cip) ++cip->n_subcores; cip->total_threads += vc->num_threads; cip->subcore_threads[sub] = vc->num_threads; - cip->subcore_vm[sub] = vc->kvm; - init_master_vcore(vc); - list_move_tail(&vc->preempt_list, &cip->vcs[sub]); + cip->vc[sub] = vc; + init_vcore_to_run(vc); + list_del_init(&vc->preempt_list); return true; } @@ -2286,6 +2476,18 @@ static void collect_piggybacks(struct core_info *cip, int target_threads) spin_unlock(&lp->lock); } +static bool recheck_signals(struct core_info *cip) +{ + int sub, i; + struct kvm_vcpu *vcpu; + + for (sub = 0; sub < cip->n_subcores; ++sub) + for_each_runnable_thread(i, vcpu, cip->vc[sub]) + if (signal_pending(vcpu->arch.run_task)) + return true; + return false; +} + static void post_guest_process(struct kvmppc_vcore *vc, bool is_master) { int still_running = 0, i; @@ -2323,7 +2525,6 @@ static void post_guest_process(struct kvmppc_vcore *vc, bool is_master) wake_up(&vcpu->arch.cpu_run); } } - list_del_init(&vc->preempt_list); if (!is_master) { if (still_running > 0) { kvmppc_vcore_preempt(vc); @@ -2385,6 +2586,21 @@ static inline int kvmppc_set_host_core(unsigned int cpu) return 0; } +static void set_irq_happened(int trap) +{ + switch (trap) { + case BOOK3S_INTERRUPT_EXTERNAL: + local_paca->irq_happened |= PACA_IRQ_EE; + break; + case BOOK3S_INTERRUPT_H_DOORBELL: + local_paca->irq_happened |= PACA_IRQ_DBELL; + break; + case BOOK3S_INTERRUPT_HMI: + local_paca->irq_happened |= PACA_IRQ_HMI; + break; + } +} + /* * Run a set of guest threads on a physical core. * Called with vc->lock held. @@ -2395,7 +2611,7 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc) int i; int srcu_idx; struct core_info core_info; - struct kvmppc_vcore *pvc, *vcnext; + struct kvmppc_vcore *pvc; struct kvm_split_mode split_info, *sip; int split, subcore_size, active; int sub; @@ -2404,6 +2620,7 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc) int pcpu, thr; int target_threads; int controlled_threads; + int trap; /* * Remove from the list any threads that have a signal pending @@ -2418,7 +2635,7 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc) /* * Initialize *vc. */ - init_master_vcore(vc); + init_vcore_to_run(vc); vc->preempt_tb = TB_NIL; /* @@ -2455,6 +2672,43 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc) if (vc->num_threads < target_threads) collect_piggybacks(&core_info, target_threads); + /* + * On radix, arrange for TLB flushing if necessary. + * This has to be done before disabling interrupts since + * it uses smp_call_function(). + */ + pcpu = smp_processor_id(); + if (kvm_is_radix(vc->kvm)) { + for (sub = 0; sub < core_info.n_subcores; ++sub) + for_each_runnable_thread(i, vcpu, core_info.vc[sub]) + kvmppc_prepare_radix_vcpu(vcpu, pcpu); + } + + /* + * Hard-disable interrupts, and check resched flag and signals. + * If we need to reschedule or deliver a signal, clean up + * and return without going into the guest(s). + */ + local_irq_disable(); + hard_irq_disable(); + if (lazy_irq_pending() || need_resched() || + recheck_signals(&core_info)) { + local_irq_enable(); + vc->vcore_state = VCORE_INACTIVE; + /* Unlock all except the primary vcore */ + for (sub = 1; sub < core_info.n_subcores; ++sub) { + pvc = core_info.vc[sub]; + /* Put back on to the preempted vcores list */ + kvmppc_vcore_preempt(pvc); + spin_unlock(&pvc->lock); + } + for (i = 0; i < controlled_threads; ++i) + kvmppc_release_hwthread(pcpu + i); + return; + } + + kvmppc_clear_host_core(pcpu); + /* Decide on micro-threading (split-core) mode */ subcore_size = threads_per_subcore; cmd_bit = stat_bit = 0; @@ -2478,13 +2732,10 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc) split_info.ldbar = mfspr(SPRN_LDBAR); split_info.subcore_size = subcore_size; for (sub = 0; sub < core_info.n_subcores; ++sub) - split_info.master_vcs[sub] = - list_first_entry(&core_info.vcs[sub], - struct kvmppc_vcore, preempt_list); + split_info.vc[sub] = core_info.vc[sub]; /* order writes to split_info before kvm_split_mode pointer */ smp_wmb(); } - pcpu = smp_processor_id(); for (thr = 0; thr < controlled_threads; ++thr) paca[pcpu + thr].kvm_hstate.kvm_split_mode = sip; @@ -2504,32 +2755,29 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc) } } - kvmppc_clear_host_core(pcpu); - /* Start all the threads */ active = 0; for (sub = 0; sub < core_info.n_subcores; ++sub) { thr = subcore_thread_map[sub]; thr0_done = false; active |= 1 << thr; - list_for_each_entry(pvc, &core_info.vcs[sub], preempt_list) { - pvc->pcpu = pcpu + thr; - for_each_runnable_thread(i, vcpu, pvc) { - kvmppc_start_thread(vcpu, pvc); - kvmppc_create_dtl_entry(vcpu, pvc); - trace_kvm_guest_enter(vcpu); - if (!vcpu->arch.ptid) - thr0_done = true; - active |= 1 << (thr + vcpu->arch.ptid); - } - /* - * We need to start the first thread of each subcore - * even if it doesn't have a vcpu. - */ - if (pvc->master_vcore == pvc && !thr0_done) - kvmppc_start_thread(NULL, pvc); - thr += pvc->num_threads; + pvc = core_info.vc[sub]; + pvc->pcpu = pcpu + thr; + for_each_runnable_thread(i, vcpu, pvc) { + kvmppc_start_thread(vcpu, pvc); + kvmppc_create_dtl_entry(vcpu, pvc); + trace_kvm_guest_enter(vcpu); + if (!vcpu->arch.ptid) + thr0_done = true; + active |= 1 << (thr + vcpu->arch.ptid); } + /* + * We need to start the first thread of each subcore + * even if it doesn't have a vcpu. + */ + if (!thr0_done) + kvmppc_start_thread(NULL, pvc); + thr += pvc->num_threads; } /* @@ -2556,17 +2804,27 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc) trace_kvmppc_run_core(vc, 0); for (sub = 0; sub < core_info.n_subcores; ++sub) - list_for_each_entry(pvc, &core_info.vcs[sub], preempt_list) - spin_unlock(&pvc->lock); + spin_unlock(&core_info.vc[sub]->lock); + + /* + * Interrupts will be enabled once we get into the guest, + * so tell lockdep that we're about to enable interrupts. + */ + trace_hardirqs_on(); guest_enter(); srcu_idx = srcu_read_lock(&vc->kvm->srcu); - __kvmppc_vcore_entry(); + trap = __kvmppc_vcore_entry(); srcu_read_unlock(&vc->kvm->srcu, srcu_idx); + guest_exit(); + + trace_hardirqs_off(); + set_irq_happened(trap); + spin_lock(&vc->lock); /* prevent other vcpu threads from doing kvmppc_start_thread() now */ vc->vcore_state = VCORE_EXITING; @@ -2594,6 +2852,10 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc) split_info.do_nap = 0; } + kvmppc_set_host_core(pcpu); + + local_irq_enable(); + /* Let secondaries go back to the offline loop */ for (i = 0; i < controlled_threads; ++i) { kvmppc_release_hwthread(pcpu + i); @@ -2602,18 +2864,15 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc) cpumask_clear_cpu(pcpu + i, &vc->kvm->arch.cpu_in_guest); } - kvmppc_set_host_core(pcpu); - spin_unlock(&vc->lock); /* make sure updates to secondary vcpu structs are visible now */ smp_mb(); - guest_exit(); - for (sub = 0; sub < core_info.n_subcores; ++sub) - list_for_each_entry_safe(pvc, vcnext, &core_info.vcs[sub], - preempt_list) - post_guest_process(pvc, pvc == vc); + for (sub = 0; sub < core_info.n_subcores; ++sub) { + pvc = core_info.vc[sub]; + post_guest_process(pvc, pvc == vc); + } spin_lock(&vc->lock); preempt_enable(); @@ -2658,6 +2917,30 @@ static void shrink_halt_poll_ns(struct kvmppc_vcore *vc) vc->halt_poll_ns /= halt_poll_ns_shrink; } +#ifdef CONFIG_KVM_XICS +static inline bool xive_interrupt_pending(struct kvm_vcpu *vcpu) +{ + if (!xive_enabled()) + return false; + return vcpu->arch.xive_saved_state.pipr < + vcpu->arch.xive_saved_state.cppr; +} +#else +static inline bool xive_interrupt_pending(struct kvm_vcpu *vcpu) +{ + return false; +} +#endif /* CONFIG_KVM_XICS */ + +static bool kvmppc_vcpu_woken(struct kvm_vcpu *vcpu) +{ + if (vcpu->arch.pending_exceptions || vcpu->arch.prodded || + kvmppc_doorbell_pending(vcpu) || xive_interrupt_pending(vcpu)) + return true; + + return false; +} + /* * Check to see if any of the runnable vcpus on the vcore have pending * exceptions or are no longer ceded @@ -2668,8 +2951,7 @@ static int kvmppc_vcore_check_block(struct kvmppc_vcore *vc) int i; for_each_runnable_thread(i, vcpu, vc) { - if (vcpu->arch.pending_exceptions || !vcpu->arch.ceded || - vcpu->arch.prodded) + if (!vcpu->arch.ceded || kvmppc_vcpu_woken(vcpu)) return 1; } @@ -2811,15 +3093,14 @@ static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) */ if (!signal_pending(current)) { if (vc->vcore_state == VCORE_PIGGYBACK) { - struct kvmppc_vcore *mvc = vc->master_vcore; - if (spin_trylock(&mvc->lock)) { - if (mvc->vcore_state == VCORE_RUNNING && - !VCORE_IS_EXITING(mvc)) { + if (spin_trylock(&vc->lock)) { + if (vc->vcore_state == VCORE_RUNNING && + !VCORE_IS_EXITING(vc)) { kvmppc_create_dtl_entry(vcpu, vc); kvmppc_start_thread(vcpu, vc); trace_kvm_guest_enter(vcpu); } - spin_unlock(&mvc->lock); + spin_unlock(&vc->lock); } } else if (vc->vcore_state == VCORE_RUNNING && !VCORE_IS_EXITING(vc)) { @@ -2855,7 +3136,7 @@ static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) break; n_ceded = 0; for_each_runnable_thread(i, v, vc) { - if (!v->arch.pending_exceptions && !v->arch.prodded) + if (!kvmppc_vcpu_woken(v)) n_ceded += v->arch.ceded; else v->arch.ceded = 0; @@ -2907,12 +3188,36 @@ static int kvmppc_vcpu_run_hv(struct kvm_run *run, struct kvm_vcpu *vcpu) { int r; int srcu_idx; + unsigned long ebb_regs[3] = {}; /* shut up GCC */ + unsigned long user_tar = 0; + unsigned int user_vrsave; if (!vcpu->arch.sane) { run->exit_reason = KVM_EXIT_INTERNAL_ERROR; return -EINVAL; } + /* + * Don't allow entry with a suspended transaction, because + * the guest entry/exit code will lose it. + * If the guest has TM enabled, save away their TM-related SPRs + * (they will get restored by the TM unavailable interrupt). + */ +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + if (cpu_has_feature(CPU_FTR_TM) && current->thread.regs && + (current->thread.regs->msr & MSR_TM)) { + if (MSR_TM_ACTIVE(current->thread.regs->msr)) { + run->exit_reason = KVM_EXIT_FAIL_ENTRY; + run->fail_entry.hardware_entry_failure_reason = 0; + return -EINVAL; + } + current->thread.tm_tfhar = mfspr(SPRN_TFHAR); + current->thread.tm_tfiar = mfspr(SPRN_TFIAR); + current->thread.tm_texasr = mfspr(SPRN_TEXASR); + current->thread.regs->msr &= ~MSR_TM; + } +#endif + kvmppc_core_prepare_to_enter(vcpu); /* No need to go into the guest when all we'll do is come back out */ @@ -2934,6 +3239,15 @@ static int kvmppc_vcpu_run_hv(struct kvm_run *run, struct kvm_vcpu *vcpu) flush_all_to_thread(current); + /* Save userspace EBB and other register values */ + if (cpu_has_feature(CPU_FTR_ARCH_207S)) { + ebb_regs[0] = mfspr(SPRN_EBBHR); + ebb_regs[1] = mfspr(SPRN_EBBRR); + ebb_regs[2] = mfspr(SPRN_BESCR); + user_tar = mfspr(SPRN_TAR); + } + user_vrsave = mfspr(SPRN_VRSAVE); + vcpu->arch.wqp = &vcpu->arch.vcore->wq; vcpu->arch.pgdir = current->mm->pgd; vcpu->arch.state = KVMPPC_VCPU_BUSY_IN_HOST; @@ -2960,6 +3274,16 @@ static int kvmppc_vcpu_run_hv(struct kvm_run *run, struct kvm_vcpu *vcpu) } } while (is_kvmppc_resume_guest(r)); + /* Restore userspace EBB and other register values */ + if (cpu_has_feature(CPU_FTR_ARCH_207S)) { + mtspr(SPRN_EBBHR, ebb_regs[0]); + mtspr(SPRN_EBBRR, ebb_regs[1]); + mtspr(SPRN_BESCR, ebb_regs[2]); + mtspr(SPRN_TAR, user_tar); + mtspr(SPRN_FSCR, current->thread.fscr); + } + mtspr(SPRN_VRSAVE, user_vrsave); + out: vcpu->arch.state = KVMPPC_VCPU_NOTREADY; atomic_dec(&vcpu->kvm->arch.vcpus_running); @@ -3317,7 +3641,7 @@ void kvmppc_alloc_host_rm_ops(void) return; } - get_online_cpus(); + cpus_read_lock(); for (cpu = 0; cpu < nr_cpu_ids; cpu += threads_per_core) { if (!cpu_online(cpu)) @@ -3339,17 +3663,17 @@ void kvmppc_alloc_host_rm_ops(void) l_ops = (unsigned long) ops; if (cmpxchg64((unsigned long *)&kvmppc_host_rm_ops_hv, 0, l_ops)) { - put_online_cpus(); + cpus_read_unlock(); kfree(ops->rm_core); kfree(ops); return; } - cpuhp_setup_state_nocalls(CPUHP_KVM_PPC_BOOK3S_PREPARE, - "ppc/kvm_book3s:prepare", - kvmppc_set_host_core, - kvmppc_clear_host_core); - put_online_cpus(); + cpuhp_setup_state_nocalls_cpuslocked(CPUHP_KVM_PPC_BOOK3S_PREPARE, + "ppc/kvm_book3s:prepare", + kvmppc_set_host_core, + kvmppc_clear_host_core); + cpus_read_unlock(); } void kvmppc_free_host_rm_ops(void) @@ -3468,6 +3792,19 @@ static int kvmppc_core_init_vm_hv(struct kvm *kvm) kvm_hv_vm_activated(); /* + * Initialize smt_mode depending on processor. + * POWER8 and earlier have to use "strict" threading, where + * all vCPUs in a vcore have to run on the same (sub)core, + * whereas on POWER9 the threads can each run a different + * guest. + */ + if (!cpu_has_feature(CPU_FTR_ARCH_300)) + kvm->arch.smt_mode = threads_per_subcore; + else + kvm->arch.smt_mode = 1; + kvm->arch.emul_smt_mode = 1; + + /* * Create a debugfs directory for the VM */ snprintf(buf, sizeof(buf), "vm%d", current->pid); @@ -3896,6 +4233,7 @@ static struct kvmppc_ops kvm_ops_hv = { #endif .configure_mmu = kvmhv_configure_mmu, .get_rmmu_info = kvmhv_get_rmmu_info, + .set_smt_mode = kvmhv_set_smt_mode, }; static int kvm_init_subcore_bitmap(void) diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c index 88a65923c649..90644db9d38e 100644 --- a/arch/powerpc/kvm/book3s_hv_builtin.c +++ b/arch/powerpc/kvm/book3s_hv_builtin.c @@ -207,7 +207,14 @@ EXPORT_SYMBOL_GPL(kvmppc_hwrng_present); long kvmppc_h_random(struct kvm_vcpu *vcpu) { - if (powernv_get_random_real_mode(&vcpu->arch.gpr[4])) + int r; + + /* Only need to do the expensive mfmsr() on radix */ + if (kvm_is_radix(vcpu->kvm) && (mfmsr() & MSR_IR)) + r = powernv_get_random_long(&vcpu->arch.gpr[4]); + else + r = powernv_get_random_real_mode(&vcpu->arch.gpr[4]); + if (r) return H_SUCCESS; return H_HARDWARE; @@ -300,7 +307,7 @@ void kvmhv_commence_exit(int trap) return; for (i = 0; i < MAX_SUBCORES; ++i) { - vc = sip->master_vcs[i]; + vc = sip->vc[i]; if (!vc) break; do { diff --git a/arch/powerpc/kvm/book3s_hv_interrupts.S b/arch/powerpc/kvm/book3s_hv_interrupts.S index 0fdc4a28970b..dc54373c8780 100644 --- a/arch/powerpc/kvm/book3s_hv_interrupts.S +++ b/arch/powerpc/kvm/book3s_hv_interrupts.S @@ -61,13 +61,6 @@ BEGIN_FTR_SECTION std r3, HSTATE_DABR(r13) END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S) - /* Hard-disable interrupts */ - mfmsr r10 - std r10, HSTATE_HOST_MSR(r13) - rldicl r10,r10,48,1 - rotldi r10,r10,16 - mtmsrd r10,1 - /* Save host PMU registers */ BEGIN_FTR_SECTION /* Work around P8 PMAE bug */ @@ -121,10 +114,20 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) * Put whatever is in the decrementer into the * hypervisor decrementer. */ +BEGIN_FTR_SECTION + ld r5, HSTATE_KVM_VCORE(r13) + ld r6, VCORE_KVM(r5) + ld r9, KVM_HOST_LPCR(r6) + andis. r9, r9, LPCR_LD@h +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300) mfspr r8,SPRN_DEC mftb r7 - mtspr SPRN_HDEC,r8 +BEGIN_FTR_SECTION + /* On POWER9, don't sign-extend if host LPCR[LD] bit is set */ + bne 32f +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300) extsw r8,r8 +32: mtspr SPRN_HDEC,r8 add r8,r8,r7 std r8,HSTATE_DECEXP(r13) @@ -143,6 +146,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) * * R1 = host R1 * R2 = host R2 + * R3 = trap number on this thread * R12 = exit handler id * R13 = PACA */ diff --git a/arch/powerpc/kvm/book3s_hv_ras.c b/arch/powerpc/kvm/book3s_hv_ras.c index 7ef0993214f3..c356f9a40b24 100644 --- a/arch/powerpc/kvm/book3s_hv_ras.c +++ b/arch/powerpc/kvm/book3s_hv_ras.c @@ -130,12 +130,28 @@ static long kvmppc_realmode_mc_power7(struct kvm_vcpu *vcpu) out: /* + * For guest that supports FWNMI capability, hook the MCE event into + * vcpu structure. We are going to exit the guest with KVM_EXIT_NMI + * exit reason. On our way to exit we will pull this event from vcpu + * structure and print it from thread 0 of the core/subcore. + * + * For guest that does not support FWNMI capability (old QEMU): * We are now going enter guest either through machine check * interrupt (for unhandled errors) or will continue from * current HSRR0 (for handled errors) in guest. Hence * queue up the event so that we can log it from host console later. */ - machine_check_queue_event(); + if (vcpu->kvm->arch.fwnmi_enabled) { + /* + * Hook up the mce event on to vcpu structure. + * First clear the old event. + */ + memset(&vcpu->arch.mce_evt, 0, sizeof(vcpu->arch.mce_evt)); + if (get_mce_event(&mce_evt, MCE_EVENT_RELEASE)) { + vcpu->arch.mce_evt = mce_evt; + } + } else + machine_check_queue_event(); return handled; } diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index bdb3f76ceb6b..6ea4b53f4b16 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -32,12 +32,30 @@ #include <asm/opal.h> #include <asm/xive-regs.h> +/* Sign-extend HDEC if not on POWER9 */ +#define EXTEND_HDEC(reg) \ +BEGIN_FTR_SECTION; \ + extsw reg, reg; \ +END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300) + #define VCPU_GPRS_TM(reg) (((reg) * ULONG_SIZE) + VCPU_GPR_TM) /* Values in HSTATE_NAPPING(r13) */ #define NAPPING_CEDE 1 #define NAPPING_NOVCPU 2 +/* Stack frame offsets for kvmppc_hv_entry */ +#define SFS 160 +#define STACK_SLOT_TRAP (SFS-4) +#define STACK_SLOT_TID (SFS-16) +#define STACK_SLOT_PSSCR (SFS-24) +#define STACK_SLOT_PID (SFS-32) +#define STACK_SLOT_IAMR (SFS-40) +#define STACK_SLOT_CIABR (SFS-48) +#define STACK_SLOT_DAWR (SFS-56) +#define STACK_SLOT_DAWRX (SFS-64) +#define STACK_SLOT_HFSCR (SFS-72) + /* * Call kvmppc_hv_entry in real mode. * Must be called with interrupts hard-disabled. @@ -51,6 +69,7 @@ _GLOBAL_TOC(kvmppc_hv_entry_trampoline) std r0, PPC_LR_STKOFF(r1) stdu r1, -112(r1) mfmsr r10 + std r10, HSTATE_HOST_MSR(r13) LOAD_REG_ADDR(r5, kvmppc_call_hv_entry) li r0,MSR_RI andc r0,r10,r0 @@ -135,20 +154,21 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) stb r0, HSTATE_HWTHREAD_REQ(r13) /* - * For external and machine check interrupts, we need - * to call the Linux handler to process the interrupt. - * We do that by jumping to absolute address 0x500 for - * external interrupts, or the machine_check_fwnmi label - * for machine checks (since firmware might have patched - * the vector area at 0x200). The [h]rfid at the end of the - * handler will return to the book3s_hv_interrupts.S code. - * For other interrupts we do the rfid to get back - * to the book3s_hv_interrupts.S code here. + * For external interrupts we need to call the Linux + * handler to process the interrupt. We do that by jumping + * to absolute address 0x500 for external interrupts. + * The [h]rfid at the end of the handler will return to + * the book3s_hv_interrupts.S code. For other interrupts + * we do the rfid to get back to the book3s_hv_interrupts.S + * code here. */ ld r8, 112+PPC_LR_STKOFF(r1) addi r1, r1, 112 ld r7, HSTATE_HOST_MSR(r13) + /* Return the trap number on this thread as the return value */ + mr r3, r12 + /* * If we came back from the guest via a relocation-on interrupt, * we will be in virtual mode at this point, which makes it a @@ -158,62 +178,25 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) andi. r0, r0, MSR_IR /* in real mode? */ bne .Lvirt_return - cmpwi cr1, r12, BOOK3S_INTERRUPT_MACHINE_CHECK - cmpwi r12, BOOK3S_INTERRUPT_EXTERNAL - beq 11f - cmpwi r12, BOOK3S_INTERRUPT_H_DOORBELL - beq 15f /* Invoke the H_DOORBELL handler */ - cmpwi cr2, r12, BOOK3S_INTERRUPT_HMI - beq cr2, 14f /* HMI check */ - - /* RFI into the highmem handler, or branch to interrupt handler */ + /* RFI into the highmem handler */ mfmsr r6 li r0, MSR_RI andc r6, r6, r0 mtmsrd r6, 1 /* Clear RI in MSR */ mtsrr0 r8 mtsrr1 r7 - beq cr1, 13f /* machine check */ RFI - /* On POWER7, we have external interrupts set to use HSRR0/1 */ -11: mtspr SPRN_HSRR0, r8 - mtspr SPRN_HSRR1, r7 - ba 0x500 - -13: b machine_check_fwnmi - -14: mtspr SPRN_HSRR0, r8 - mtspr SPRN_HSRR1, r7 - b hmi_exception_after_realmode - -15: mtspr SPRN_HSRR0, r8 - mtspr SPRN_HSRR1, r7 - ba 0xe80 - - /* Virtual-mode return - can't get here for HMI or machine check */ + /* Virtual-mode return */ .Lvirt_return: - cmpwi r12, BOOK3S_INTERRUPT_EXTERNAL - beq 16f - cmpwi r12, BOOK3S_INTERRUPT_H_DOORBELL - beq 17f - andi. r0, r7, MSR_EE /* were interrupts hard-enabled? */ - beq 18f - mtmsrd r7, 1 /* if so then re-enable them */ -18: mtlr r8 + mtlr r8 blr -16: mtspr SPRN_HSRR0, r8 /* jump to reloc-on external vector */ - mtspr SPRN_HSRR1, r7 - b exc_virt_0x4500_hardware_interrupt - -17: mtspr SPRN_HSRR0, r8 - mtspr SPRN_HSRR1, r7 - b exc_virt_0x4e80_h_doorbell - kvmppc_primary_no_guest: /* We handle this much like a ceded vcpu */ /* put the HDEC into the DEC, since HDEC interrupts don't wake us */ + /* HDEC may be larger than DEC for arch >= v3.00, but since the */ + /* HDEC value came from DEC in the first place, it will fit */ mfspr r3, SPRN_HDEC mtspr SPRN_DEC, r3 /* @@ -295,8 +278,9 @@ kvm_novcpu_wakeup: /* See if our timeslice has expired (HDEC is negative) */ mfspr r0, SPRN_HDEC + EXTEND_HDEC(r0) li r12, BOOK3S_INTERRUPT_HV_DECREMENTER - cmpwi r0, 0 + cmpdi r0, 0 blt kvm_novcpu_exit /* Got an IPI but other vcpus aren't yet exiting, must be a latecomer */ @@ -319,10 +303,10 @@ kvm_novcpu_exit: bl kvmhv_accumulate_time #endif 13: mr r3, r12 - stw r12, 112-4(r1) + stw r12, STACK_SLOT_TRAP(r1) bl kvmhv_commence_exit nop - lwz r12, 112-4(r1) + lwz r12, STACK_SLOT_TRAP(r1) b kvmhv_switch_to_host /* @@ -390,8 +374,8 @@ kvm_secondary_got_guest: lbz r4, HSTATE_PTID(r13) cmpwi r4, 0 bne 63f - lis r6, 0x7fff - ori r6, r6, 0xffff + LOAD_REG_ADDR(r6, decrementer_max) + ld r6, 0(r6) mtspr SPRN_HDEC, r6 /* and set per-LPAR registers, if doing dynamic micro-threading */ ld r6, HSTATE_SPLIT_MODE(r13) @@ -545,11 +529,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) * * *****************************************************************************/ -/* Stack frame offsets */ -#define STACK_SLOT_TID (112-16) -#define STACK_SLOT_PSSCR (112-24) -#define STACK_SLOT_PID (112-32) - .global kvmppc_hv_entry kvmppc_hv_entry: @@ -565,7 +544,7 @@ kvmppc_hv_entry: */ mflr r0 std r0, PPC_LR_STKOFF(r1) - stdu r1, -112(r1) + stdu r1, -SFS(r1) /* Save R1 in the PACA */ std r1, HSTATE_HOST_R1(r13) @@ -749,10 +728,22 @@ BEGIN_FTR_SECTION mfspr r5, SPRN_TIDR mfspr r6, SPRN_PSSCR mfspr r7, SPRN_PID + mfspr r8, SPRN_IAMR std r5, STACK_SLOT_TID(r1) std r6, STACK_SLOT_PSSCR(r1) std r7, STACK_SLOT_PID(r1) + std r8, STACK_SLOT_IAMR(r1) + mfspr r5, SPRN_HFSCR + std r5, STACK_SLOT_HFSCR(r1) END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300) +BEGIN_FTR_SECTION + mfspr r5, SPRN_CIABR + mfspr r6, SPRN_DAWR + mfspr r7, SPRN_DAWRX + std r5, STACK_SLOT_CIABR(r1) + std r6, STACK_SLOT_DAWR(r1) + std r7, STACK_SLOT_DAWRX(r1) +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) BEGIN_FTR_SECTION /* Set partition DABR */ @@ -895,8 +886,10 @@ FTR_SECTION_ELSE ld r5, VCPU_TID(r4) ld r6, VCPU_PSSCR(r4) oris r6, r6, PSSCR_EC@h /* This makes stop trap to HV */ + ld r7, VCPU_HFSCR(r4) mtspr SPRN_TIDR, r5 mtspr SPRN_PSSCR, r6 + mtspr SPRN_HFSCR, r7 ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_300) 8: @@ -911,7 +904,7 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_300) mftb r7 subf r3,r7,r8 mtspr SPRN_DEC,r3 - stw r3,VCPU_DEC(r4) + std r3,VCPU_DEC(r4) ld r5, VCPU_SPRG0(r4) ld r6, VCPU_SPRG1(r4) @@ -968,7 +961,8 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_300) /* Check if HDEC expires soon */ mfspr r3, SPRN_HDEC - cmpwi r3, 512 /* 1 microsecond */ + EXTEND_HDEC(r3) + cmpdi r3, 512 /* 1 microsecond */ blt hdec_soon #ifdef CONFIG_KVM_XICS @@ -1022,7 +1016,13 @@ kvmppc_cede_reentry: /* r4 = vcpu, r13 = paca */ li r0, BOOK3S_INTERRUPT_EXTERNAL bne cr1, 12f mfspr r0, SPRN_DEC - cmpwi r0, 0 +BEGIN_FTR_SECTION + /* On POWER9 check whether the guest has large decrementer enabled */ + andis. r8, r8, LPCR_LD@h + bne 15f +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300) + extsw r0, r0 +15: cmpdi r0, 0 li r0, BOOK3S_INTERRUPT_DECREMENTER bge 5f @@ -1032,6 +1032,23 @@ kvmppc_cede_reentry: /* r4 = vcpu, r13 = paca */ mr r9, r4 bl kvmppc_msr_interrupt 5: +BEGIN_FTR_SECTION + b fast_guest_return +END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300) + /* On POWER9, check for pending doorbell requests */ + lbz r0, VCPU_DBELL_REQ(r4) + cmpwi r0, 0 + beq fast_guest_return + ld r5, HSTATE_KVM_VCORE(r13) + /* Set DPDES register so the CPU will take a doorbell interrupt */ + li r0, 1 + mtspr SPRN_DPDES, r0 + std r0, VCORE_DPDES(r5) + /* Make sure other cpus see vcore->dpdes set before dbell req clear */ + lwsync + /* Clear the pending doorbell request */ + li r0, 0 + stb r0, VCPU_DBELL_REQ(r4) /* * Required state: @@ -1206,6 +1223,15 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) stw r12,VCPU_TRAP(r9) + /* + * Now that we have saved away SRR0/1 and HSRR0/1, + * interrupts are recoverable in principle, so set MSR_RI. + * This becomes important for relocation-on interrupts from + * the guest, which we can get in radix mode on POWER9. + */ + li r0, MSR_RI + mtmsrd r0, 1 + #ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING addi r3, r9, VCPU_TB_RMINTR mr r4, r9 @@ -1262,6 +1288,13 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) beq 4f b guest_exit_cont 3: + /* If it's a hypervisor facility unavailable interrupt, save HFSCR */ + cmpwi r12, BOOK3S_INTERRUPT_H_FAC_UNAVAIL + bne 14f + mfspr r3, SPRN_HFSCR + std r3, VCPU_HFSCR(r9) + b guest_exit_cont +14: /* External interrupt ? */ cmpwi r12, BOOK3S_INTERRUPT_EXTERNAL bne+ guest_exit_cont @@ -1449,12 +1482,18 @@ mc_cont: mtspr SPRN_SPURR,r4 /* Save DEC */ + ld r3, HSTATE_KVM_VCORE(r13) mfspr r5,SPRN_DEC mftb r6 + /* On P9, if the guest has large decr enabled, don't sign extend */ +BEGIN_FTR_SECTION + ld r4, VCORE_LPCR(r3) + andis. r4, r4, LPCR_LD@h + bne 16f +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300) extsw r5,r5 - add r5,r5,r6 +16: add r5,r5,r6 /* r5 is a guest timebase value here, convert to host TB */ - ld r3,HSTATE_KVM_VCORE(r13) ld r4,VCORE_TB_OFFSET(r3) subf r5,r4,r5 std r5,VCPU_DEC_EXPIRES(r9) @@ -1499,17 +1538,19 @@ FTR_SECTION_ELSE rldicl r6, r6, 4, 50 /* r6 &= PSSCR_GUEST_VIS */ rotldi r6, r6, 60 std r6, VCPU_PSSCR(r9) + /* Restore host HFSCR value */ + ld r7, STACK_SLOT_HFSCR(r1) + mtspr SPRN_HFSCR, r7 ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_300) /* * Restore various registers to 0, where non-zero values * set by the guest could disrupt the host. */ li r0, 0 - mtspr SPRN_IAMR, r0 - mtspr SPRN_CIABR, r0 - mtspr SPRN_DAWRX, r0 + mtspr SPRN_PSPB, r0 mtspr SPRN_WORT, r0 BEGIN_FTR_SECTION + mtspr SPRN_IAMR, r0 mtspr SPRN_TCSCR, r0 /* Set MMCRS to 1<<31 to freeze and disable the SPMC counters */ li r0, 1 @@ -1525,6 +1566,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300) std r6,VCPU_UAMOR(r9) li r6,0 mtspr SPRN_AMR,r6 + mtspr SPRN_UAMOR, r6 /* Switch DSCR back to host value */ mfspr r8, SPRN_DSCR @@ -1670,12 +1712,22 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) /* Restore host values of some registers */ BEGIN_FTR_SECTION + ld r5, STACK_SLOT_CIABR(r1) + ld r6, STACK_SLOT_DAWR(r1) + ld r7, STACK_SLOT_DAWRX(r1) + mtspr SPRN_CIABR, r5 + mtspr SPRN_DAWR, r6 + mtspr SPRN_DAWRX, r7 +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) +BEGIN_FTR_SECTION ld r5, STACK_SLOT_TID(r1) ld r6, STACK_SLOT_PSSCR(r1) ld r7, STACK_SLOT_PID(r1) + ld r8, STACK_SLOT_IAMR(r1) mtspr SPRN_TIDR, r5 mtspr SPRN_PSSCR, r6 mtspr SPRN_PID, r7 + mtspr SPRN_IAMR, r8 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300) BEGIN_FTR_SECTION PPC_INVALIDATE_ERAT @@ -1819,8 +1871,8 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_TYPE_RADIX) li r0, KVM_GUEST_MODE_NONE stb r0, HSTATE_IN_GUEST(r13) - ld r0, 112+PPC_LR_STKOFF(r1) - addi r1, r1, 112 + ld r0, SFS+PPC_LR_STKOFF(r1) + addi r1, r1, SFS mtlr r0 blr @@ -2366,12 +2418,20 @@ END_FTR_SECTION_IFSET(CPU_FTR_TM) mfspr r3, SPRN_DEC mfspr r4, SPRN_HDEC mftb r5 - cmpw r3, r4 +BEGIN_FTR_SECTION + /* On P9 check whether the guest has large decrementer mode enabled */ + ld r6, HSTATE_KVM_VCORE(r13) + ld r6, VCORE_LPCR(r6) + andis. r6, r6, LPCR_LD@h + bne 68f +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300) + extsw r3, r3 +68: EXTEND_HDEC(r4) + cmpd r3, r4 ble 67f mtspr SPRN_DEC, r4 67: /* save expiry time of guest decrementer */ - extsw r3, r3 add r3, r3, r5 ld r4, HSTATE_KVM_VCPU(r13) ld r5, HSTATE_KVM_VCORE(r13) @@ -2552,22 +2612,32 @@ machine_check_realmode: ld r9, HSTATE_KVM_VCPU(r13) li r12, BOOK3S_INTERRUPT_MACHINE_CHECK /* - * Deliver unhandled/fatal (e.g. UE) MCE errors to guest through - * machine check interrupt (set HSRR0 to 0x200). And for handled - * errors (no-fatal), just go back to guest execution with current - * HSRR0 instead of exiting guest. This new approach will inject - * machine check to guest for fatal error causing guest to crash. - * - * The old code used to return to host for unhandled errors which - * was causing guest to hang with soft lockups inside guest and - * makes it difficult to recover guest instance. + * For the guest that is FWNMI capable, deliver all the MCE errors + * (handled/unhandled) by exiting the guest with KVM_EXIT_NMI exit + * reason. This new approach injects machine check errors in guest + * address space to guest with additional information in the form + * of RTAS event, thus enabling guest kernel to suitably handle + * such errors. * + * For the guest that is not FWNMI capable (old QEMU) fallback + * to old behaviour for backward compatibility: + * Deliver unhandled/fatal (e.g. UE) MCE errors to guest either + * through machine check interrupt (set HSRR0 to 0x200). + * For handled errors (no-fatal), just go back to guest execution + * with current HSRR0. * if we receive machine check with MSR(RI=0) then deliver it to * guest as machine check causing guest to crash. */ ld r11, VCPU_MSR(r9) rldicl. r0, r11, 64-MSR_HV_LG, 63 /* check if it happened in HV mode */ bne mc_cont /* if so, exit to host */ + /* Check if guest is capable of handling NMI exit */ + ld r10, VCPU_KVM(r9) + lbz r10, KVM_FWNMI(r10) + cmpdi r10, 1 /* FWNMI capable? */ + beq mc_cont /* if so, exit with KVM_EXIT_NMI. */ + + /* if not, fall through for backward compatibility. */ andi. r10, r11, MSR_RI /* check for unrecoverable exception */ beq 1f /* Deliver a machine check to guest */ ld r10, VCPU_PC(r9) diff --git a/arch/powerpc/kvm/book3s_pr_papr.c b/arch/powerpc/kvm/book3s_pr_papr.c index bcbeeb62dd13..8a4205fa774f 100644 --- a/arch/powerpc/kvm/book3s_pr_papr.c +++ b/arch/powerpc/kvm/book3s_pr_papr.c @@ -50,7 +50,9 @@ static int kvmppc_h_pr_enter(struct kvm_vcpu *vcpu) pteg_addr = get_pteg_addr(vcpu, pte_index); mutex_lock(&vcpu->kvm->arch.hpt_mutex); - copy_from_user(pteg, (void __user *)pteg_addr, sizeof(pteg)); + ret = H_FUNCTION; + if (copy_from_user(pteg, (void __user *)pteg_addr, sizeof(pteg))) + goto done; hpte = pteg; ret = H_PTEG_FULL; @@ -71,7 +73,9 @@ static int kvmppc_h_pr_enter(struct kvm_vcpu *vcpu) hpte[0] = cpu_to_be64(kvmppc_get_gpr(vcpu, 6)); hpte[1] = cpu_to_be64(kvmppc_get_gpr(vcpu, 7)); pteg_addr += i * HPTE_SIZE; - copy_to_user((void __user *)pteg_addr, hpte, HPTE_SIZE); + ret = H_FUNCTION; + if (copy_to_user((void __user *)pteg_addr, hpte, HPTE_SIZE)) + goto done; kvmppc_set_gpr(vcpu, 4, pte_index | i); ret = H_SUCCESS; @@ -93,7 +97,9 @@ static int kvmppc_h_pr_remove(struct kvm_vcpu *vcpu) pteg = get_pteg_addr(vcpu, pte_index); mutex_lock(&vcpu->kvm->arch.hpt_mutex); - copy_from_user(pte, (void __user *)pteg, sizeof(pte)); + ret = H_FUNCTION; + if (copy_from_user(pte, (void __user *)pteg, sizeof(pte))) + goto done; pte[0] = be64_to_cpu((__force __be64)pte[0]); pte[1] = be64_to_cpu((__force __be64)pte[1]); @@ -103,7 +109,9 @@ static int kvmppc_h_pr_remove(struct kvm_vcpu *vcpu) ((flags & H_ANDCOND) && (pte[0] & avpn) != 0)) goto done; - copy_to_user((void __user *)pteg, &v, sizeof(v)); + ret = H_FUNCTION; + if (copy_to_user((void __user *)pteg, &v, sizeof(v))) + goto done; rb = compute_tlbie_rb(pte[0], pte[1], pte_index); vcpu->arch.mmu.tlbie(vcpu, rb, rb & 1 ? true : false); @@ -171,7 +179,10 @@ static int kvmppc_h_pr_bulk_remove(struct kvm_vcpu *vcpu) } pteg = get_pteg_addr(vcpu, tsh & H_BULK_REMOVE_PTEX); - copy_from_user(pte, (void __user *)pteg, sizeof(pte)); + if (copy_from_user(pte, (void __user *)pteg, sizeof(pte))) { + ret = H_FUNCTION; + break; + } pte[0] = be64_to_cpu((__force __be64)pte[0]); pte[1] = be64_to_cpu((__force __be64)pte[1]); @@ -184,7 +195,10 @@ static int kvmppc_h_pr_bulk_remove(struct kvm_vcpu *vcpu) tsh |= H_BULK_REMOVE_NOT_FOUND; } else { /* Splat the pteg in (userland) hpt */ - copy_to_user((void __user *)pteg, &v, sizeof(v)); + if (copy_to_user((void __user *)pteg, &v, sizeof(v))) { + ret = H_FUNCTION; + break; + } rb = compute_tlbie_rb(pte[0], pte[1], tsh & H_BULK_REMOVE_PTEX); @@ -211,7 +225,9 @@ static int kvmppc_h_pr_protect(struct kvm_vcpu *vcpu) pteg = get_pteg_addr(vcpu, pte_index); mutex_lock(&vcpu->kvm->arch.hpt_mutex); - copy_from_user(pte, (void __user *)pteg, sizeof(pte)); + ret = H_FUNCTION; + if (copy_from_user(pte, (void __user *)pteg, sizeof(pte))) + goto done; pte[0] = be64_to_cpu((__force __be64)pte[0]); pte[1] = be64_to_cpu((__force __be64)pte[1]); @@ -234,7 +250,9 @@ static int kvmppc_h_pr_protect(struct kvm_vcpu *vcpu) vcpu->arch.mmu.tlbie(vcpu, rb, rb & 1 ? true : false); pte[0] = (__force u64)cpu_to_be64(pte[0]); pte[1] = (__force u64)cpu_to_be64(pte[1]); - copy_to_user((void __user *)pteg, pte, sizeof(pte)); + ret = H_FUNCTION; + if (copy_to_user((void __user *)pteg, pte, sizeof(pte))) + goto done; ret = H_SUCCESS; done: @@ -244,36 +262,37 @@ static int kvmppc_h_pr_protect(struct kvm_vcpu *vcpu) return EMULATE_DONE; } -static int kvmppc_h_pr_put_tce(struct kvm_vcpu *vcpu) +static int kvmppc_h_pr_logical_ci_load(struct kvm_vcpu *vcpu) { - unsigned long liobn = kvmppc_get_gpr(vcpu, 4); - unsigned long ioba = kvmppc_get_gpr(vcpu, 5); - unsigned long tce = kvmppc_get_gpr(vcpu, 6); long rc; - rc = kvmppc_h_put_tce(vcpu, liobn, ioba, tce); + rc = kvmppc_h_logical_ci_load(vcpu); if (rc == H_TOO_HARD) return EMULATE_FAIL; kvmppc_set_gpr(vcpu, 3, rc); return EMULATE_DONE; } -static int kvmppc_h_pr_logical_ci_load(struct kvm_vcpu *vcpu) +static int kvmppc_h_pr_logical_ci_store(struct kvm_vcpu *vcpu) { long rc; - rc = kvmppc_h_logical_ci_load(vcpu); + rc = kvmppc_h_logical_ci_store(vcpu); if (rc == H_TOO_HARD) return EMULATE_FAIL; kvmppc_set_gpr(vcpu, 3, rc); return EMULATE_DONE; } -static int kvmppc_h_pr_logical_ci_store(struct kvm_vcpu *vcpu) +#ifdef CONFIG_SPAPR_TCE_IOMMU +static int kvmppc_h_pr_put_tce(struct kvm_vcpu *vcpu) { + unsigned long liobn = kvmppc_get_gpr(vcpu, 4); + unsigned long ioba = kvmppc_get_gpr(vcpu, 5); + unsigned long tce = kvmppc_get_gpr(vcpu, 6); long rc; - rc = kvmppc_h_logical_ci_store(vcpu); + rc = kvmppc_h_put_tce(vcpu, liobn, ioba, tce); if (rc == H_TOO_HARD) return EMULATE_FAIL; kvmppc_set_gpr(vcpu, 3, rc); @@ -311,6 +330,23 @@ static int kvmppc_h_pr_stuff_tce(struct kvm_vcpu *vcpu) return EMULATE_DONE; } +#else /* CONFIG_SPAPR_TCE_IOMMU */ +static int kvmppc_h_pr_put_tce(struct kvm_vcpu *vcpu) +{ + return EMULATE_FAIL; +} + +static int kvmppc_h_pr_put_tce_indirect(struct kvm_vcpu *vcpu) +{ + return EMULATE_FAIL; +} + +static int kvmppc_h_pr_stuff_tce(struct kvm_vcpu *vcpu) +{ + return EMULATE_FAIL; +} +#endif /* CONFIG_SPAPR_TCE_IOMMU */ + static int kvmppc_h_pr_xics_hcall(struct kvm_vcpu *vcpu, u32 cmd) { long rc = kvmppc_xics_hcall(vcpu, cmd); diff --git a/arch/powerpc/kvm/book3s_xive.c b/arch/powerpc/kvm/book3s_xive.c index ffe1da95033a..08b200a0bbce 100644 --- a/arch/powerpc/kvm/book3s_xive.c +++ b/arch/powerpc/kvm/book3s_xive.c @@ -1257,8 +1257,8 @@ static void xive_pre_save_scan(struct kvmppc_xive *xive) if (!xc) continue; for (j = 0; j < KVMPPC_XIVE_Q_COUNT; j++) { - if (xc->queues[i].qpage) - xive_pre_save_queue(xive, &xc->queues[i]); + if (xc->queues[j].qpage) + xive_pre_save_queue(xive, &xc->queues[j]); } } diff --git a/arch/powerpc/kvm/book3s_xive_template.c b/arch/powerpc/kvm/book3s_xive_template.c index 023a31133c37..4636ca6e7d38 100644 --- a/arch/powerpc/kvm/book3s_xive_template.c +++ b/arch/powerpc/kvm/book3s_xive_template.c @@ -69,7 +69,7 @@ static void GLUE(X_PFX,source_eoi)(u32 hw_irq, struct xive_irq_data *xd) { /* If the XIVE supports the new "store EOI facility, use it */ if (xd->flags & XIVE_IRQ_FLAG_STORE_EOI) - __x_writeq(0, __x_eoi_page(xd)); + __x_writeq(0, __x_eoi_page(xd) + XIVE_ESB_STORE_EOI); else if (hw_irq && xd->flags & XIVE_IRQ_FLAG_EOI_FW) { opal_int_eoi(hw_irq); } else { @@ -89,7 +89,7 @@ static void GLUE(X_PFX,source_eoi)(u32 hw_irq, struct xive_irq_data *xd) * properly. */ if (xd->flags & XIVE_IRQ_FLAG_LSI) - __x_readq(__x_eoi_page(xd)); + __x_readq(__x_eoi_page(xd) + XIVE_ESB_LOAD_EOI); else { eoi_val = GLUE(X_PFX,esb_load)(xd, XIVE_ESB_SET_PQ_00); diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c index 3eaac3809977..071b87ee682f 100644 --- a/arch/powerpc/kvm/booke.c +++ b/arch/powerpc/kvm/booke.c @@ -687,7 +687,7 @@ int kvmppc_core_prepare_to_enter(struct kvm_vcpu *vcpu) kvmppc_core_check_exceptions(vcpu); - if (vcpu->requests) { + if (kvm_request_pending(vcpu)) { /* Exception delivery raised request; start over */ return 1; } diff --git a/arch/powerpc/kvm/emulate.c b/arch/powerpc/kvm/emulate.c index c873ffe55362..4d8b4d6cebff 100644 --- a/arch/powerpc/kvm/emulate.c +++ b/arch/powerpc/kvm/emulate.c @@ -39,7 +39,7 @@ void kvmppc_emulate_dec(struct kvm_vcpu *vcpu) unsigned long dec_nsec; unsigned long long dec_time; - pr_debug("mtDEC: %x\n", vcpu->arch.dec); + pr_debug("mtDEC: %lx\n", vcpu->arch.dec); hrtimer_try_to_cancel(&vcpu->arch.dec_timer); #ifdef CONFIG_PPC_BOOK3S @@ -109,7 +109,7 @@ static int kvmppc_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs) case SPRN_TBWU: break; case SPRN_DEC: - vcpu->arch.dec = spr_val; + vcpu->arch.dec = (u32) spr_val; kvmppc_emulate_dec(vcpu); break; diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index f7cf2cd564ef..1a75c0b5f4ca 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -55,8 +55,7 @@ EXPORT_SYMBOL_GPL(kvmppc_pr_ops); int kvm_arch_vcpu_runnable(struct kvm_vcpu *v) { - return !!(v->arch.pending_exceptions) || - v->requests; + return !!(v->arch.pending_exceptions) || kvm_request_pending(v); } int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu) @@ -108,7 +107,7 @@ int kvmppc_prepare_to_enter(struct kvm_vcpu *vcpu) */ smp_mb(); - if (vcpu->requests) { + if (kvm_request_pending(vcpu)) { /* Make sure we process requests preemptable */ local_irq_enable(); trace_kvm_check_requests(vcpu); @@ -554,13 +553,28 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE case KVM_CAP_PPC_SMT: r = 0; - if (hv_enabled) { + if (kvm) { + if (kvm->arch.emul_smt_mode > 1) + r = kvm->arch.emul_smt_mode; + else + r = kvm->arch.smt_mode; + } else if (hv_enabled) { if (cpu_has_feature(CPU_FTR_ARCH_300)) r = 1; else r = threads_per_subcore; } break; + case KVM_CAP_PPC_SMT_POSSIBLE: + r = 1; + if (hv_enabled) { + if (!cpu_has_feature(CPU_FTR_ARCH_300)) + r = ((threads_per_subcore << 1) - 1); + else + /* P9 can emulate dbells, so allow any mode */ + r = 8 | 4 | 2 | 1; + } + break; case KVM_CAP_PPC_RMA: r = 0; break; @@ -619,6 +633,11 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) r = !!hv_enabled && !cpu_has_feature(CPU_FTR_ARCH_300); break; #endif +#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE + case KVM_CAP_PPC_FWNMI: + r = hv_enabled; + break; +#endif case KVM_CAP_PPC_HTM: r = cpu_has_feature(CPU_FTR_TM_COMP) && is_kvmppc_hv_enabled(kvm); @@ -1538,6 +1557,15 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu, break; } #endif /* CONFIG_KVM_XICS */ +#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE + case KVM_CAP_PPC_FWNMI: + r = -EINVAL; + if (!is_kvmppc_hv_enabled(vcpu->kvm)) + break; + r = 0; + vcpu->kvm->arch.fwnmi_enabled = true; + break; +#endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */ default: r = -EINVAL; break; @@ -1712,6 +1740,15 @@ static int kvm_vm_ioctl_enable_cap(struct kvm *kvm, r = 0; break; } + case KVM_CAP_PPC_SMT: { + unsigned long mode = cap->args[0]; + unsigned long flags = cap->args[1]; + + r = -EINVAL; + if (kvm->arch.kvm_ops->set_smt_mode) + r = kvm->arch.kvm_ops->set_smt_mode(kvm, mode, flags); + break; + } #endif default: r = -EINVAL; @@ -1749,7 +1786,7 @@ long kvm_arch_vm_ioctl(struct file *filp, r = kvm_vm_ioctl_enable_cap(kvm, &cap); break; } -#ifdef CONFIG_PPC_BOOK3S_64 +#ifdef CONFIG_SPAPR_TCE_IOMMU case KVM_CREATE_SPAPR_TCE_64: { struct kvm_create_spapr_tce_64 create_tce_64; @@ -1780,6 +1817,8 @@ long kvm_arch_vm_ioctl(struct file *filp, r = kvm_vm_ioctl_create_spapr_tce(kvm, &create_tce_64); goto out; } +#endif +#ifdef CONFIG_PPC_BOOK3S_64 case KVM_PPC_GET_SMMU_INFO: { struct kvm_ppc_smmu_info info; struct kvm *kvm = filp->private_data; diff --git a/arch/powerpc/mm/dump_linuxpagetables.c b/arch/powerpc/mm/dump_linuxpagetables.c index d659345a98d6..44fe4833910f 100644 --- a/arch/powerpc/mm/dump_linuxpagetables.c +++ b/arch/powerpc/mm/dump_linuxpagetables.c @@ -16,6 +16,7 @@ */ #include <linux/debugfs.h> #include <linux/fs.h> +#include <linux/hugetlb.h> #include <linux/io.h> #include <linux/mm.h> #include <linux/sched.h> @@ -391,7 +392,7 @@ static void walk_pmd(struct pg_state *st, pud_t *pud, unsigned long start) for (i = 0; i < PTRS_PER_PMD; i++, pmd++) { addr = start + i * PMD_SIZE; - if (!pmd_none(*pmd)) + if (!pmd_none(*pmd) && !pmd_huge(*pmd)) /* pmd exists */ walk_pte(st, pmd, addr); else @@ -407,7 +408,7 @@ static void walk_pud(struct pg_state *st, pgd_t *pgd, unsigned long start) for (i = 0; i < PTRS_PER_PUD; i++, pud++) { addr = start + i * PUD_SIZE; - if (!pud_none(*pud)) + if (!pud_none(*pud) && !pud_huge(*pud)) /* pud exists */ walk_pmd(st, pud, addr); else @@ -427,7 +428,7 @@ static void walk_pagetables(struct pg_state *st) */ for (i = 0; i < PTRS_PER_PGD; i++, pgd++) { addr = KERN_VIRT_START + i * PGDIR_SIZE; - if (!pgd_none(*pgd)) + if (!pgd_none(*pgd) && !pgd_huge(*pgd)) /* pgd exists */ walk_pud(st, pgd, addr); else diff --git a/arch/powerpc/mm/hugetlbpage-radix.c b/arch/powerpc/mm/hugetlbpage-radix.c index 6575b9aabef4..a12e86395025 100644 --- a/arch/powerpc/mm/hugetlbpage-radix.c +++ b/arch/powerpc/mm/hugetlbpage-radix.c @@ -68,7 +68,7 @@ radix__hugetlb_get_unmapped_area(struct file *file, unsigned long addr, addr = ALIGN(addr, huge_page_size(h)); vma = find_vma(mm, addr); if (mm->task_size - len >= addr && - (!vma || addr + len <= vma->vm_start)) + (!vma || addr + len <= vm_start_gap(vma))) return addr; } /* diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c index a4f33de4008e..c41dc44472c5 100644 --- a/arch/powerpc/mm/hugetlbpage.c +++ b/arch/powerpc/mm/hugetlbpage.c @@ -17,6 +17,8 @@ #include <linux/memblock.h> #include <linux/bootmem.h> #include <linux/moduleparam.h> +#include <linux/swap.h> +#include <linux/swapops.h> #include <asm/pgtable.h> #include <asm/pgalloc.h> #include <asm/tlb.h> @@ -55,7 +57,7 @@ static unsigned nr_gpages; #define hugepd_none(hpd) (hpd_val(hpd) == 0) -pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr) +pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr, unsigned long sz) { /* Only called for hugetlbfs pages, hence can ignore THP */ return __find_linux_pte_or_hugepte(mm->pgd, addr, NULL, NULL); @@ -617,62 +619,39 @@ void hugetlb_free_pgd_range(struct mmu_gather *tlb, } while (addr = next, addr != end); } -/* - * We are holding mmap_sem, so a parallel huge page collapse cannot run. - * To prevent hugepage split, disable irq. - */ -struct page * -follow_huge_addr(struct mm_struct *mm, unsigned long address, int write) +struct page *follow_huge_pd(struct vm_area_struct *vma, + unsigned long address, hugepd_t hpd, + int flags, int pdshift) { - bool is_thp; - pte_t *ptep, pte; - unsigned shift; - unsigned long mask, flags; - struct page *page = ERR_PTR(-EINVAL); - - local_irq_save(flags); - ptep = find_linux_pte_or_hugepte(mm->pgd, address, &is_thp, &shift); - if (!ptep) - goto no_page; - pte = READ_ONCE(*ptep); - /* - * Verify it is a huge page else bail. - * Transparent hugepages are handled by generic code. We can skip them - * here. - */ - if (!shift || is_thp) - goto no_page; - - if (!pte_present(pte)) { - page = NULL; - goto no_page; + pte_t *ptep; + spinlock_t *ptl; + struct page *page = NULL; + unsigned long mask; + int shift = hugepd_shift(hpd); + struct mm_struct *mm = vma->vm_mm; + +retry: + ptl = &mm->page_table_lock; + spin_lock(ptl); + + ptep = hugepte_offset(hpd, address, pdshift); + if (pte_present(*ptep)) { + mask = (1UL << shift) - 1; + page = pte_page(*ptep); + page += ((address & mask) >> PAGE_SHIFT); + if (flags & FOLL_GET) + get_page(page); + } else { + if (is_hugetlb_entry_migration(*ptep)) { + spin_unlock(ptl); + __migration_entry_wait(mm, ptep, ptl); + goto retry; + } } - mask = (1UL << shift) - 1; - page = pte_page(pte); - if (page) - page += (address & mask) / PAGE_SIZE; - -no_page: - local_irq_restore(flags); + spin_unlock(ptl); return page; } -struct page * -follow_huge_pmd(struct mm_struct *mm, unsigned long address, - pmd_t *pmd, int write) -{ - BUG(); - return NULL; -} - -struct page * -follow_huge_pud(struct mm_struct *mm, unsigned long address, - pud_t *pud, int write) -{ - BUG(); - return NULL; -} - static unsigned long hugepte_addr_end(unsigned long addr, unsigned long end, unsigned long sz) { @@ -763,8 +742,11 @@ static int __init add_huge_page_size(unsigned long long size) * Hash: 16M and 16G */ if (radix_enabled()) { - if (mmu_psize != MMU_PAGE_2M) - return -EINVAL; + if (mmu_psize != MMU_PAGE_2M) { + if (cpu_has_feature(CPU_FTR_POWER9_DD1) || + (mmu_psize != MMU_PAGE_1G)) + return -EINVAL; + } } else { if (mmu_psize != MMU_PAGE_16M && mmu_psize != MMU_PAGE_16G) return -EINVAL; diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index 9ee536ec0739..de5a90e1ceaa 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -126,18 +126,14 @@ int __weak remove_section_mapping(unsigned long start, unsigned long end) return -ENODEV; } -int arch_add_memory(int nid, u64 start, u64 size, bool for_device) +int arch_add_memory(int nid, u64 start, u64 size, bool want_memblock) { - struct pglist_data *pgdata; - struct zone *zone; unsigned long start_pfn = start >> PAGE_SHIFT; unsigned long nr_pages = size >> PAGE_SHIFT; int rc; resize_hpt_for_hotplug(memblock_phys_mem_size()); - pgdata = NODE_DATA(nid); - start = (unsigned long)__va(start); rc = create_section_mapping(start, start + size); if (rc) { @@ -147,11 +143,7 @@ int arch_add_memory(int nid, u64 start, u64 size, bool for_device) return -EFAULT; } - /* this should work for most non-highmem platforms */ - zone = pgdata->node_zones + - zone_for_memory(nid, start, size, 0, for_device); - - return __add_pages(nid, zone, start_pfn, nr_pages); + return __add_pages(nid, start_pfn, nr_pages, want_memblock); } #ifdef CONFIG_MEMORY_HOTREMOVE diff --git a/arch/powerpc/mm/mmap.c b/arch/powerpc/mm/mmap.c index 9dbd2a733d6b..0ee6be4f1ba4 100644 --- a/arch/powerpc/mm/mmap.c +++ b/arch/powerpc/mm/mmap.c @@ -112,7 +112,7 @@ radix__arch_get_unmapped_area(struct file *filp, unsigned long addr, addr = PAGE_ALIGN(addr); vma = find_vma(mm, addr); if (mm->task_size - len >= addr && addr >= mmap_min_addr && - (!vma || addr + len <= vma->vm_start)) + (!vma || addr + len <= vm_start_gap(vma))) return addr; } @@ -157,7 +157,7 @@ radix__arch_get_unmapped_area_topdown(struct file *filp, addr = PAGE_ALIGN(addr); vma = find_vma(mm, addr); if (mm->task_size - len >= addr && addr >= mmap_min_addr && - (!vma || addr + len <= vma->vm_start)) + (!vma || addr + len <= vm_start_gap(vma))) return addr; } diff --git a/arch/powerpc/mm/mmu_context_book3s64.c b/arch/powerpc/mm/mmu_context_book3s64.c index c6dca2ae78ef..a3edf813d455 100644 --- a/arch/powerpc/mm/mmu_context_book3s64.c +++ b/arch/powerpc/mm/mmu_context_book3s64.c @@ -99,7 +99,7 @@ static int hash__init_new_context(struct mm_struct *mm) * mm->context.addr_limit. Default to max task size so that we copy the * default values to paca which will help us to handle slb miss early. */ - mm->context.addr_limit = TASK_SIZE_128TB; + mm->context.addr_limit = DEFAULT_MAP_WINDOW_USER64; /* * The old code would re-promote on fork, we don't do that when using diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index 371792e4418f..b95c584ce19d 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -1311,8 +1311,10 @@ static int update_lookup_table(void *data) /* * Update the node maps and sysfs entries for each cpu whose home node * has changed. Returns 1 when the topology has changed, and 0 otherwise. + * + * cpus_locked says whether we already hold cpu_hotplug_lock. */ -int arch_update_cpu_topology(void) +int numa_update_cpu_topology(bool cpus_locked) { unsigned int cpu, sibling, changed = 0; struct topology_update_data *updates, *ud; @@ -1400,15 +1402,23 @@ int arch_update_cpu_topology(void) if (!cpumask_weight(&updated_cpus)) goto out; - stop_machine(update_cpu_topology, &updates[0], &updated_cpus); + if (cpus_locked) + stop_machine_cpuslocked(update_cpu_topology, &updates[0], + &updated_cpus); + else + stop_machine(update_cpu_topology, &updates[0], &updated_cpus); /* * Update the numa-cpu lookup table with the new mappings, even for * offline CPUs. It is best to perform this update from the stop- * machine context. */ - stop_machine(update_lookup_table, &updates[0], + if (cpus_locked) + stop_machine_cpuslocked(update_lookup_table, &updates[0], cpumask_of(raw_smp_processor_id())); + else + stop_machine(update_lookup_table, &updates[0], + cpumask_of(raw_smp_processor_id())); for (ud = &updates[0]; ud; ud = ud->next) { unregister_cpu_under_node(ud->cpu, ud->old_nid); @@ -1426,6 +1436,12 @@ out: return changed; } +int arch_update_cpu_topology(void) +{ + lockdep_assert_cpus_held(); + return numa_update_cpu_topology(true); +} + static void topology_work_fn(struct work_struct *work) { rebuild_sched_domains(); diff --git a/arch/powerpc/mm/slice.c b/arch/powerpc/mm/slice.c index 966b9fccfa66..45f6740dd407 100644 --- a/arch/powerpc/mm/slice.c +++ b/arch/powerpc/mm/slice.c @@ -99,7 +99,7 @@ static int slice_area_is_free(struct mm_struct *mm, unsigned long addr, if ((mm->task_size - len) < addr) return 0; vma = find_vma(mm, addr); - return (!vma || (addr + len) <= vma->vm_start); + return (!vma || (addr + len) <= vm_start_gap(vma)); } static int slice_low_has_vma(struct mm_struct *mm, unsigned long slice) diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c index aee2bb817ac6..861c5af1c9c4 100644 --- a/arch/powerpc/net/bpf_jit_comp64.c +++ b/arch/powerpc/net/bpf_jit_comp64.c @@ -938,7 +938,7 @@ common_load: /* * Tail call */ - case BPF_JMP | BPF_CALL | BPF_X: + case BPF_JMP | BPF_TAIL_CALL: ctx->seen |= SEEN_TAILCALL; bpf_jit_emit_tail_call(image, ctx, addrs[i + 1]); break; @@ -1052,6 +1052,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp) fp->bpf_func = (void *)image; fp->jited = 1; + fp->jited_len = alloclen; bpf_flush_icache(bpf_hdr, (u8 *)bpf_hdr + (bpf_hdr->pages * PAGE_SIZE)); diff --git a/arch/powerpc/perf/perf_regs.c b/arch/powerpc/perf/perf_regs.c index cbd82fde5770..09ceea6175ba 100644 --- a/arch/powerpc/perf/perf_regs.c +++ b/arch/powerpc/perf/perf_regs.c @@ -101,5 +101,6 @@ void perf_get_regs_user(struct perf_regs *regs_user, struct pt_regs *regs_user_copy) { regs_user->regs = task_pt_regs(current); - regs_user->abi = perf_reg_abi(current); + regs_user->abi = (regs_user->regs) ? perf_reg_abi(current) : + PERF_SAMPLE_REGS_ABI_NONE; } diff --git a/arch/powerpc/perf/power9-pmu.c b/arch/powerpc/perf/power9-pmu.c index 018f8e90ac35..bb28e1a41257 100644 --- a/arch/powerpc/perf/power9-pmu.c +++ b/arch/powerpc/perf/power9-pmu.c @@ -402,7 +402,7 @@ static struct power_pmu power9_isa207_pmu = { .name = "POWER9", .n_counter = MAX_PMU_COUNTERS, .add_fields = ISA207_ADD_FIELDS, - .test_adder = ISA207_TEST_ADDER, + .test_adder = P9_DD1_TEST_ADDER, .compute_mmcr = isa207_compute_mmcr, .config_bhrb = power9_config_bhrb, .bhrb_filter_map = power9_bhrb_filter_map, @@ -421,7 +421,7 @@ static struct power_pmu power9_pmu = { .name = "POWER9", .n_counter = MAX_PMU_COUNTERS, .add_fields = ISA207_ADD_FIELDS, - .test_adder = P9_DD1_TEST_ADDER, + .test_adder = ISA207_TEST_ADDER, .compute_mmcr = isa207_compute_mmcr, .config_bhrb = power9_config_bhrb, .bhrb_filter_map = power9_bhrb_filter_map, diff --git a/arch/powerpc/platforms/Kconfig b/arch/powerpc/platforms/Kconfig index 33244e3d9375..4fd64d3f5c44 100644 --- a/arch/powerpc/platforms/Kconfig +++ b/arch/powerpc/platforms/Kconfig @@ -59,6 +59,17 @@ config PPC_OF_BOOT_TRAMPOLINE In case of doubt, say Y +config PPC_DT_CPU_FTRS + bool "Device-tree based CPU feature discovery & setup" + depends on PPC_BOOK3S_64 + default y + help + This enables code to use a new device tree binding for describing CPU + compatibility and features. Saying Y here will attempt to use the new + binding if the firmware provides it. Currently only the skiboot + firmware provides this binding. + If you're not sure say Y. + config UDBG_RTAS_CONSOLE bool "RTAS based debug console" depends on PPC_RTAS diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype index 684e886eaae4..2f629e0551e9 100644 --- a/arch/powerpc/platforms/Kconfig.cputype +++ b/arch/powerpc/platforms/Kconfig.cputype @@ -344,12 +344,18 @@ config PPC_STD_MMU_64 config PPC_RADIX_MMU bool "Radix MMU Support" depends on PPC_BOOK3S_64 + select ARCH_HAS_GIGANTIC_PAGE if (MEMORY_ISOLATION && COMPACTION) || CMA default y help Enable support for the Power ISA 3.0 Radix style MMU. Currently this is only implemented by IBM Power9 CPUs, if you don't have one of them you can probably disable this. +config ARCH_ENABLE_HUGEPAGE_MIGRATION + def_bool y + depends on PPC_BOOK3S_64 && HUGETLB_PAGE && MIGRATION + + config PPC_MMU_NOHASH def_bool y depends on !PPC_STD_MMU diff --git a/arch/powerpc/platforms/cell/iommu.c b/arch/powerpc/platforms/cell/iommu.c index 71b995bbcae0..29d4f96ed33e 100644 --- a/arch/powerpc/platforms/cell/iommu.c +++ b/arch/powerpc/platforms/cell/iommu.c @@ -644,32 +644,22 @@ static void dma_fixed_unmap_sg(struct device *dev, struct scatterlist *sg, direction, attrs); } -static int dma_fixed_dma_supported(struct device *dev, u64 mask) -{ - return mask == DMA_BIT_MASK(64); -} - -static int dma_set_mask_and_switch(struct device *dev, u64 dma_mask); +static int dma_suported_and_switch(struct device *dev, u64 dma_mask); static const struct dma_map_ops dma_iommu_fixed_ops = { .alloc = dma_fixed_alloc_coherent, .free = dma_fixed_free_coherent, .map_sg = dma_fixed_map_sg, .unmap_sg = dma_fixed_unmap_sg, - .dma_supported = dma_fixed_dma_supported, - .set_dma_mask = dma_set_mask_and_switch, + .dma_supported = dma_suported_and_switch, .map_page = dma_fixed_map_page, .unmap_page = dma_fixed_unmap_page, + .mapping_error = dma_iommu_mapping_error, }; -static void cell_dma_dev_setup_fixed(struct device *dev); - static void cell_dma_dev_setup(struct device *dev) { - /* Order is important here, these are not mutually exclusive */ - if (get_dma_ops(dev) == &dma_iommu_fixed_ops) - cell_dma_dev_setup_fixed(dev); - else if (get_pci_dma_ops() == &dma_iommu_ops) + if (get_pci_dma_ops() == &dma_iommu_ops) set_iommu_table_base(dev, cell_get_iommu_table(dev)); else if (get_pci_dma_ops() == &dma_direct_ops) set_dma_offset(dev, cell_dma_direct_offset); @@ -956,38 +946,29 @@ out: return dev_addr; } -static int dma_set_mask_and_switch(struct device *dev, u64 dma_mask) +static int dma_suported_and_switch(struct device *dev, u64 dma_mask) { - if (!dev->dma_mask || !dma_supported(dev, dma_mask)) - return -EIO; - if (dma_mask == DMA_BIT_MASK(64) && - cell_iommu_get_fixed_address(dev) != OF_BAD_ADDR) - { + cell_iommu_get_fixed_address(dev) != OF_BAD_ADDR) { + u64 addr = cell_iommu_get_fixed_address(dev) + + dma_iommu_fixed_base; dev_dbg(dev, "iommu: 64-bit OK, using fixed ops\n"); + dev_dbg(dev, "iommu: fixed addr = %llx\n", addr); set_dma_ops(dev, &dma_iommu_fixed_ops); - } else { + set_dma_offset(dev, addr); + return 1; + } + + if (dma_iommu_dma_supported(dev, dma_mask)) { dev_dbg(dev, "iommu: not 64-bit, using default ops\n"); set_dma_ops(dev, get_pci_dma_ops()); + cell_dma_dev_setup(dev); + return 1; } - cell_dma_dev_setup(dev); - - *dev->dma_mask = dma_mask; - return 0; } -static void cell_dma_dev_setup_fixed(struct device *dev) -{ - u64 addr; - - addr = cell_iommu_get_fixed_address(dev) + dma_iommu_fixed_base; - set_dma_offset(dev, addr); - - dev_dbg(dev, "iommu: fixed addr = %llx\n", addr); -} - static void insert_16M_pte(unsigned long addr, unsigned long *ptab, unsigned long base_pte) { @@ -1139,7 +1120,7 @@ static int __init cell_iommu_fixed_mapping_init(void) cell_iommu_setup_window(iommu, np, dbase, dsize, 0); } - dma_iommu_ops.set_dma_mask = dma_set_mask_and_switch; + dma_iommu_ops.dma_supported = dma_suported_and_switch; set_pci_dma_ops(&dma_iommu_ops); return 0; diff --git a/arch/powerpc/platforms/cell/spu_base.c b/arch/powerpc/platforms/cell/spu_base.c index 96c2b8a40630..0c45cdbac4cf 100644 --- a/arch/powerpc/platforms/cell/spu_base.c +++ b/arch/powerpc/platforms/cell/spu_base.c @@ -197,7 +197,9 @@ static int __spu_trap_data_map(struct spu *spu, unsigned long ea, u64 dsisr) (REGION_ID(ea) != USER_REGION_ID)) { spin_unlock(&spu->register_lock); - ret = hash_page(ea, _PAGE_PRESENT | _PAGE_READ, 0x300, dsisr); + ret = hash_page(ea, + _PAGE_PRESENT | _PAGE_READ | _PAGE_PRIVILEGED, + 0x300, dsisr); spin_lock(&spu->register_lock); if (!ret) { diff --git a/arch/powerpc/platforms/cell/spufs/coredump.c b/arch/powerpc/platforms/cell/spufs/coredump.c index e5a891ae80ee..84b7ac926ce6 100644 --- a/arch/powerpc/platforms/cell/spufs/coredump.c +++ b/arch/powerpc/platforms/cell/spufs/coredump.c @@ -175,6 +175,8 @@ static int spufs_arch_write_note(struct spu_context *ctx, int i, skip = roundup(cprm->pos - total + sz, 4) - cprm->pos; if (!dump_skip(cprm, skip)) goto Eio; + + rc = 0; out: free_page((unsigned long)buf); return rc; diff --git a/arch/powerpc/platforms/powernv/npu-dma.c b/arch/powerpc/platforms/powernv/npu-dma.c index 067defeea691..b5d960d6db3d 100644 --- a/arch/powerpc/platforms/powernv/npu-dma.c +++ b/arch/powerpc/platforms/powernv/npu-dma.c @@ -75,7 +75,8 @@ struct pci_dev *pnv_pci_get_npu_dev(struct pci_dev *gpdev, int index) if (WARN_ON(!gpdev)) return NULL; - if (WARN_ON(!gpdev->dev.of_node)) + /* Not all PCI devices have device-tree nodes */ + if (!gpdev->dev.of_node) return NULL; /* Get assoicated PCI device */ @@ -448,7 +449,7 @@ static int mmio_launch_invalidate(struct npu *npu, unsigned long launch, return mmio_atsd_reg; } -static int mmio_invalidate_pid(struct npu *npu, unsigned long pid) +static int mmio_invalidate_pid(struct npu *npu, unsigned long pid, bool flush) { unsigned long launch; @@ -464,12 +465,15 @@ static int mmio_invalidate_pid(struct npu *npu, unsigned long pid) /* PID */ launch |= pid << PPC_BITLSHIFT(38); + /* No flush */ + launch |= !flush << PPC_BITLSHIFT(39); + /* Invalidating the entire process doesn't use a va */ return mmio_launch_invalidate(npu, launch, 0); } static int mmio_invalidate_va(struct npu *npu, unsigned long va, - unsigned long pid) + unsigned long pid, bool flush) { unsigned long launch; @@ -485,26 +489,60 @@ static int mmio_invalidate_va(struct npu *npu, unsigned long va, /* PID */ launch |= pid << PPC_BITLSHIFT(38); + /* No flush */ + launch |= !flush << PPC_BITLSHIFT(39); + return mmio_launch_invalidate(npu, launch, va); } #define mn_to_npu_context(x) container_of(x, struct npu_context, mn) +struct mmio_atsd_reg { + struct npu *npu; + int reg; +}; + +static void mmio_invalidate_wait( + struct mmio_atsd_reg mmio_atsd_reg[NV_MAX_NPUS], bool flush) +{ + struct npu *npu; + int i, reg; + + /* Wait for all invalidations to complete */ + for (i = 0; i <= max_npu2_index; i++) { + if (mmio_atsd_reg[i].reg < 0) + continue; + + /* Wait for completion */ + npu = mmio_atsd_reg[i].npu; + reg = mmio_atsd_reg[i].reg; + while (__raw_readq(npu->mmio_atsd_regs[reg] + XTS_ATSD_STAT)) + cpu_relax(); + + put_mmio_atsd_reg(npu, reg); + + /* + * The GPU requires two flush ATSDs to ensure all entries have + * been flushed. We use PID 0 as it will never be used for a + * process on the GPU. + */ + if (flush) + mmio_invalidate_pid(npu, 0, true); + } +} + /* * Invalidate either a single address or an entire PID depending on * the value of va. */ static void mmio_invalidate(struct npu_context *npu_context, int va, - unsigned long address) + unsigned long address, bool flush) { - int i, j, reg; + int i, j; struct npu *npu; struct pnv_phb *nphb; struct pci_dev *npdev; - struct { - struct npu *npu; - int reg; - } mmio_atsd_reg[NV_MAX_NPUS]; + struct mmio_atsd_reg mmio_atsd_reg[NV_MAX_NPUS]; unsigned long pid = npu_context->mm->context.id; /* @@ -524,10 +562,11 @@ static void mmio_invalidate(struct npu_context *npu_context, int va, if (va) mmio_atsd_reg[i].reg = - mmio_invalidate_va(npu, address, pid); + mmio_invalidate_va(npu, address, pid, + flush); else mmio_atsd_reg[i].reg = - mmio_invalidate_pid(npu, pid); + mmio_invalidate_pid(npu, pid, flush); /* * The NPU hardware forwards the shootdown to all GPUs @@ -543,18 +582,10 @@ static void mmio_invalidate(struct npu_context *npu_context, int va, */ flush_tlb_mm(npu_context->mm); - /* Wait for all invalidations to complete */ - for (i = 0; i <= max_npu2_index; i++) { - if (mmio_atsd_reg[i].reg < 0) - continue; - - /* Wait for completion */ - npu = mmio_atsd_reg[i].npu; - reg = mmio_atsd_reg[i].reg; - while (__raw_readq(npu->mmio_atsd_regs[reg] + XTS_ATSD_STAT)) - cpu_relax(); - put_mmio_atsd_reg(npu, reg); - } + mmio_invalidate_wait(mmio_atsd_reg, flush); + if (flush) + /* Wait for the flush to complete */ + mmio_invalidate_wait(mmio_atsd_reg, false); } static void pnv_npu2_mn_release(struct mmu_notifier *mn, @@ -570,7 +601,7 @@ static void pnv_npu2_mn_release(struct mmu_notifier *mn, * There should be no more translation requests for this PID, but we * need to ensure any entries for it are removed from the TLB. */ - mmio_invalidate(npu_context, 0, 0); + mmio_invalidate(npu_context, 0, 0, true); } static void pnv_npu2_mn_change_pte(struct mmu_notifier *mn, @@ -580,7 +611,7 @@ static void pnv_npu2_mn_change_pte(struct mmu_notifier *mn, { struct npu_context *npu_context = mn_to_npu_context(mn); - mmio_invalidate(npu_context, 1, address); + mmio_invalidate(npu_context, 1, address, true); } static void pnv_npu2_mn_invalidate_page(struct mmu_notifier *mn, @@ -589,7 +620,7 @@ static void pnv_npu2_mn_invalidate_page(struct mmu_notifier *mn, { struct npu_context *npu_context = mn_to_npu_context(mn); - mmio_invalidate(npu_context, 1, address); + mmio_invalidate(npu_context, 1, address, true); } static void pnv_npu2_mn_invalidate_range(struct mmu_notifier *mn, @@ -599,8 +630,11 @@ static void pnv_npu2_mn_invalidate_range(struct mmu_notifier *mn, struct npu_context *npu_context = mn_to_npu_context(mn); unsigned long address; - for (address = start; address <= end; address += PAGE_SIZE) - mmio_invalidate(npu_context, 1, address); + for (address = start; address < end; address += PAGE_SIZE) + mmio_invalidate(npu_context, 1, address, false); + + /* Do the flush only on the final addess == end */ + mmio_invalidate(npu_context, 1, address, true); } static const struct mmu_notifier_ops nv_nmmu_notifier_ops = { @@ -650,8 +684,11 @@ struct npu_context *pnv_npu2_init_context(struct pci_dev *gpdev, /* No nvlink associated with this GPU device */ return ERR_PTR(-ENODEV); - if (!mm) { - /* kernel thread contexts are not supported */ + if (!mm || mm->context.id == 0) { + /* + * Kernel thread contexts are not supported and context id 0 is + * reserved on the GPU. + */ return ERR_PTR(-EINVAL); } @@ -714,7 +751,7 @@ static void pnv_npu2_release_context(struct kref *kref) void pnv_npu2_destroy_context(struct npu_context *npu_context, struct pci_dev *gpdev) { - struct pnv_phb *nphb, *phb; + struct pnv_phb *nphb; struct npu *npu; struct pci_dev *npdev = pnv_pci_get_npu_dev(gpdev, 0); struct device_node *nvlink_dn; @@ -728,13 +765,12 @@ void pnv_npu2_destroy_context(struct npu_context *npu_context, nphb = pci_bus_to_host(npdev->bus)->private_data; npu = &nphb->npu; - phb = pci_bus_to_host(gpdev->bus)->private_data; nvlink_dn = of_parse_phandle(npdev->dev.of_node, "ibm,nvlink", 0); if (WARN_ON(of_property_read_u32(nvlink_dn, "ibm,npu-link-index", &nvlink_index))) return; npu_context->npdev[npu->index][nvlink_index] = NULL; - opal_npu_destroy_context(phb->opal_id, npu_context->mm->context.id, + opal_npu_destroy_context(nphb->opal_id, npu_context->mm->context.id, PCI_DEVID(gpdev->bus->number, gpdev->devfn)); kref_put(&npu_context->kref, pnv_npu2_release_context); } diff --git a/arch/powerpc/platforms/powernv/subcore.c b/arch/powerpc/platforms/powernv/subcore.c index 0babef11136f..309876d699e9 100644 --- a/arch/powerpc/platforms/powernv/subcore.c +++ b/arch/powerpc/platforms/powernv/subcore.c @@ -348,7 +348,7 @@ static int set_subcores_per_core(int new_mode) state->master = 0; } - get_online_cpus(); + cpus_read_lock(); /* This cpu will update the globals before exiting stop machine */ this_cpu_ptr(&split_state)->master = 1; @@ -356,9 +356,10 @@ static int set_subcores_per_core(int new_mode) /* Ensure state is consistent before we call the other cpus */ mb(); - stop_machine(cpu_update_split_mode, &new_mode, cpu_online_mask); + stop_machine_cpuslocked(cpu_update_split_mode, &new_mode, + cpu_online_mask); - put_online_cpus(); + cpus_read_unlock(); return 0; } @@ -407,7 +408,13 @@ static DEVICE_ATTR(subcores_per_core, 0644, static int subcore_init(void) { - if (!cpu_has_feature(CPU_FTR_SUBCORE)) + unsigned pvr_ver; + + pvr_ver = PVR_VER(mfspr(SPRN_PVR)); + + if (pvr_ver != PVR_POWER8 && + pvr_ver != PVR_POWER8E && + pvr_ver != PVR_POWER8NVL) return 0; /* diff --git a/arch/powerpc/platforms/ps3/system-bus.c b/arch/powerpc/platforms/ps3/system-bus.c index 2d2e5f80a3d3..5cc35d6b94b6 100644 --- a/arch/powerpc/platforms/ps3/system-bus.c +++ b/arch/powerpc/platforms/ps3/system-bus.c @@ -471,11 +471,13 @@ static ssize_t modalias_show(struct device *_dev, struct device_attribute *a, return (len >= PAGE_SIZE) ? (PAGE_SIZE - 1) : len; } +static DEVICE_ATTR_RO(modalias); -static struct device_attribute ps3_system_bus_dev_attrs[] = { - __ATTR_RO(modalias), - __ATTR_NULL, +static struct attribute *ps3_system_bus_dev_attrs[] = { + &dev_attr_modalias.attr, + NULL, }; +ATTRIBUTE_GROUPS(ps3_system_bus_dev); struct bus_type ps3_system_bus_type = { .name = "ps3_system_bus", @@ -484,7 +486,7 @@ struct bus_type ps3_system_bus_type = { .probe = ps3_system_bus_probe, .remove = ps3_system_bus_remove, .shutdown = ps3_system_bus_shutdown, - .dev_attrs = ps3_system_bus_dev_attrs, + .dev_groups = ps3_system_bus_dev_groups, }; static int __init ps3_system_bus_init(void) diff --git a/arch/powerpc/platforms/pseries/dlpar.c b/arch/powerpc/platforms/pseries/dlpar.c index bda18d8e1674..39187696ee74 100644 --- a/arch/powerpc/platforms/pseries/dlpar.c +++ b/arch/powerpc/platforms/pseries/dlpar.c @@ -588,7 +588,7 @@ static ssize_t dlpar_show(struct class *class, struct class_attribute *attr, return sprintf(buf, "%s\n", "memory,cpu"); } -static CLASS_ATTR(dlpar, S_IWUSR | S_IRUSR, dlpar_show, dlpar_store); +static CLASS_ATTR_RW(dlpar); static int __init pseries_dlpar_init(void) { diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c index e104c71ea44a..1fb162ba9d1c 100644 --- a/arch/powerpc/platforms/pseries/hotplug-memory.c +++ b/arch/powerpc/platforms/pseries/hotplug-memory.c @@ -124,6 +124,7 @@ static struct property *dlpar_clone_drconf_property(struct device_node *dn) for (i = 0; i < num_lmbs; i++) { lmbs[i].base_addr = be64_to_cpu(lmbs[i].base_addr); lmbs[i].drc_index = be32_to_cpu(lmbs[i].drc_index); + lmbs[i].aa_index = be32_to_cpu(lmbs[i].aa_index); lmbs[i].flags = be32_to_cpu(lmbs[i].flags); } @@ -147,6 +148,7 @@ static void dlpar_update_drconf_property(struct device_node *dn, for (i = 0; i < num_lmbs; i++) { lmbs[i].base_addr = cpu_to_be64(lmbs[i].base_addr); lmbs[i].drc_index = cpu_to_be32(lmbs[i].drc_index); + lmbs[i].aa_index = cpu_to_be32(lmbs[i].aa_index); lmbs[i].flags = cpu_to_be32(lmbs[i].flags); } diff --git a/arch/powerpc/platforms/pseries/ibmebus.c b/arch/powerpc/platforms/pseries/ibmebus.c index b363e439ddb9..52146b1356d2 100644 --- a/arch/powerpc/platforms/pseries/ibmebus.c +++ b/arch/powerpc/platforms/pseries/ibmebus.c @@ -397,6 +397,7 @@ static ssize_t devspec_show(struct device *dev, ofdev = to_platform_device(dev); return sprintf(buf, "%s\n", ofdev->dev.of_node->full_name); } +static DEVICE_ATTR_RO(devspec); static ssize_t name_show(struct device *dev, struct device_attribute *attr, char *buf) @@ -406,19 +407,22 @@ static ssize_t name_show(struct device *dev, ofdev = to_platform_device(dev); return sprintf(buf, "%s\n", ofdev->dev.of_node->name); } +static DEVICE_ATTR_RO(name); static ssize_t modalias_show(struct device *dev, struct device_attribute *attr, char *buf) { return of_device_modalias(dev, buf, PAGE_SIZE); } +static DEVICE_ATTR_RO(modalias); -static struct device_attribute ibmebus_bus_device_attrs[] = { - __ATTR_RO(devspec), - __ATTR_RO(name), - __ATTR_RO(modalias), - __ATTR_NULL +static struct attribute *ibmebus_bus_device_attrs[] = { + &dev_attr_devspec.attr, + &dev_attr_name.attr, + &dev_attr_modalias.attr, + NULL, }; +ATTRIBUTE_GROUPS(ibmebus_bus_device); struct bus_type ibmebus_bus_type = { .name = "ibmebus", @@ -428,7 +432,7 @@ struct bus_type ibmebus_bus_type = { .probe = ibmebus_bus_device_probe, .remove = ibmebus_bus_device_remove, .shutdown = ibmebus_bus_device_shutdown, - .dev_attrs = ibmebus_bus_device_attrs, + .dev_groups = ibmebus_bus_device_groups, }; EXPORT_SYMBOL(ibmebus_bus_type); diff --git a/arch/powerpc/platforms/pseries/mobility.c b/arch/powerpc/platforms/pseries/mobility.c index 5a0c7ba429ce..2da4851eff99 100644 --- a/arch/powerpc/platforms/pseries/mobility.c +++ b/arch/powerpc/platforms/pseries/mobility.c @@ -349,8 +349,9 @@ void post_mobility_fixup(void) return; } -static ssize_t migrate_store(struct class *class, struct class_attribute *attr, - const char *buf, size_t count) +static ssize_t migration_store(struct class *class, + struct class_attribute *attr, const char *buf, + size_t count) { u64 streamid; int rc; @@ -380,7 +381,7 @@ static ssize_t migrate_store(struct class *class, struct class_attribute *attr, */ #define MIGRATION_API_VERSION 1 -static CLASS_ATTR(migration, S_IWUSR, NULL, migrate_store); +static CLASS_ATTR_WO(migration); static CLASS_ATTR_STRING(api_version, S_IRUGO, __stringify(MIGRATION_API_VERSION)); static int __init mobility_sysfs_init(void) diff --git a/arch/powerpc/platforms/pseries/vio.c b/arch/powerpc/platforms/pseries/vio.c index 28b09fd797ec..8a47f168476b 100644 --- a/arch/powerpc/platforms/pseries/vio.c +++ b/arch/powerpc/platforms/pseries/vio.c @@ -519,7 +519,7 @@ static dma_addr_t vio_dma_iommu_map_page(struct device *dev, struct page *page, { struct vio_dev *viodev = to_vio_dev(dev); struct iommu_table *tbl; - dma_addr_t ret = DMA_ERROR_CODE; + dma_addr_t ret = IOMMU_MAPPING_ERROR; tbl = get_iommu_table_base(dev); if (vio_cmo_alloc(viodev, roundup(size, IOMMU_PAGE_SIZE(tbl)))) { @@ -625,6 +625,7 @@ static const struct dma_map_ops vio_dma_mapping_ops = { .unmap_page = vio_dma_iommu_unmap_page, .dma_supported = vio_dma_iommu_dma_supported, .get_required_mask = vio_dma_get_required_mask, + .mapping_error = dma_iommu_mapping_error, }; /** @@ -948,21 +949,21 @@ static void vio_cmo_bus_init(void) /* sysfs device functions and data structures for CMO */ #define viodev_cmo_rd_attr(name) \ -static ssize_t viodev_cmo_##name##_show(struct device *dev, \ +static ssize_t cmo_##name##_show(struct device *dev, \ struct device_attribute *attr, \ char *buf) \ { \ return sprintf(buf, "%lu\n", to_vio_dev(dev)->cmo.name); \ } -static ssize_t viodev_cmo_allocs_failed_show(struct device *dev, +static ssize_t cmo_allocs_failed_show(struct device *dev, struct device_attribute *attr, char *buf) { struct vio_dev *viodev = to_vio_dev(dev); return sprintf(buf, "%d\n", atomic_read(&viodev->cmo.allocs_failed)); } -static ssize_t viodev_cmo_allocs_failed_reset(struct device *dev, +static ssize_t cmo_allocs_failed_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct vio_dev *viodev = to_vio_dev(dev); @@ -970,7 +971,7 @@ static ssize_t viodev_cmo_allocs_failed_reset(struct device *dev, return count; } -static ssize_t viodev_cmo_desired_set(struct device *dev, +static ssize_t cmo_desired_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct vio_dev *viodev = to_vio_dev(dev); @@ -993,27 +994,37 @@ static ssize_t name_show(struct device *, struct device_attribute *, char *); static ssize_t devspec_show(struct device *, struct device_attribute *, char *); static ssize_t modalias_show(struct device *dev, struct device_attribute *attr, char *buf); -static struct device_attribute vio_cmo_dev_attrs[] = { - __ATTR_RO(name), - __ATTR_RO(devspec), - __ATTR_RO(modalias), - __ATTR(cmo_desired, S_IWUSR|S_IRUSR|S_IWGRP|S_IRGRP|S_IROTH, - viodev_cmo_desired_show, viodev_cmo_desired_set), - __ATTR(cmo_entitled, S_IRUGO, viodev_cmo_entitled_show, NULL), - __ATTR(cmo_allocated, S_IRUGO, viodev_cmo_allocated_show, NULL), - __ATTR(cmo_allocs_failed, S_IWUSR|S_IRUSR|S_IWGRP|S_IRGRP|S_IROTH, - viodev_cmo_allocs_failed_show, viodev_cmo_allocs_failed_reset), - __ATTR_NULL + +static struct device_attribute dev_attr_name; +static struct device_attribute dev_attr_devspec; +static struct device_attribute dev_attr_modalias; + +static DEVICE_ATTR_RO(cmo_entitled); +static DEVICE_ATTR_RO(cmo_allocated); +static DEVICE_ATTR_RW(cmo_desired); +static DEVICE_ATTR_RW(cmo_allocs_failed); + +static struct attribute *vio_cmo_dev_attrs[] = { + &dev_attr_name.attr, + &dev_attr_devspec.attr, + &dev_attr_modalias.attr, + &dev_attr_cmo_entitled.attr, + &dev_attr_cmo_allocated.attr, + &dev_attr_cmo_desired.attr, + &dev_attr_cmo_allocs_failed.attr, + NULL, }; +ATTRIBUTE_GROUPS(vio_cmo_dev); /* sysfs bus functions and data structures for CMO */ #define viobus_cmo_rd_attr(name) \ -static ssize_t cmo_##name##_show(struct bus_type *bt, char *buf) \ +static ssize_t cmo_bus_##name##_show(struct bus_type *bt, char *buf) \ { \ return sprintf(buf, "%lu\n", vio_cmo.name); \ } \ -static BUS_ATTR_RO(cmo_##name) +static struct bus_attribute bus_attr_cmo_bus_##name = \ + __ATTR(cmo_##name, S_IRUGO, cmo_bus_##name##_show, NULL) #define viobus_cmo_pool_rd_attr(name, var) \ static ssize_t \ @@ -1051,11 +1062,11 @@ static ssize_t cmo_high_store(struct bus_type *bt, const char *buf, static BUS_ATTR_RW(cmo_high); static struct attribute *vio_bus_attrs[] = { - &bus_attr_cmo_entitled.attr, - &bus_attr_cmo_spare.attr, - &bus_attr_cmo_min.attr, - &bus_attr_cmo_desired.attr, - &bus_attr_cmo_curr.attr, + &bus_attr_cmo_bus_entitled.attr, + &bus_attr_cmo_bus_spare.attr, + &bus_attr_cmo_bus_min.attr, + &bus_attr_cmo_bus_desired.attr, + &bus_attr_cmo_bus_curr.attr, &bus_attr_cmo_high.attr, &bus_attr_cmo_reserve_size.attr, &bus_attr_cmo_excess_size.attr, @@ -1066,7 +1077,7 @@ ATTRIBUTE_GROUPS(vio_bus); static void vio_cmo_sysfs_init(void) { - vio_bus_type.dev_attrs = vio_cmo_dev_attrs; + vio_bus_type.dev_groups = vio_cmo_dev_groups; vio_bus_type.bus_groups = vio_bus_groups; } #else /* CONFIG_PPC_SMLPAR */ @@ -1537,6 +1548,7 @@ static ssize_t name_show(struct device *dev, { return sprintf(buf, "%s\n", to_vio_dev(dev)->name); } +static DEVICE_ATTR_RO(name); static ssize_t devspec_show(struct device *dev, struct device_attribute *attr, char *buf) @@ -1545,6 +1557,7 @@ static ssize_t devspec_show(struct device *dev, return sprintf(buf, "%s\n", of_node_full_name(of_node)); } +static DEVICE_ATTR_RO(devspec); static ssize_t modalias_show(struct device *dev, struct device_attribute *attr, char *buf) @@ -1566,13 +1579,15 @@ static ssize_t modalias_show(struct device *dev, struct device_attribute *attr, return sprintf(buf, "vio:T%sS%s\n", vio_dev->type, cp); } +static DEVICE_ATTR_RO(modalias); -static struct device_attribute vio_dev_attrs[] = { - __ATTR_RO(name), - __ATTR_RO(devspec), - __ATTR_RO(modalias), - __ATTR_NULL +static struct attribute *vio_dev_attrs[] = { + &dev_attr_name.attr, + &dev_attr_devspec.attr, + &dev_attr_modalias.attr, + NULL, }; +ATTRIBUTE_GROUPS(vio_dev); void vio_unregister_device(struct vio_dev *viodev) { @@ -1608,7 +1623,7 @@ static int vio_hotplug(struct device *dev, struct kobj_uevent_env *env) struct bus_type vio_bus_type = { .name = "vio", - .dev_attrs = vio_dev_attrs, + .dev_groups = vio_dev_groups, .uevent = vio_hotplug, .match = vio_bus_match, .probe = vio_bus_probe, diff --git a/arch/powerpc/sysdev/axonram.c b/arch/powerpc/sysdev/axonram.c index a7fe5fee744f..2799706106c6 100644 --- a/arch/powerpc/sysdev/axonram.c +++ b/arch/powerpc/sysdev/axonram.c @@ -45,6 +45,7 @@ #include <linux/of_device.h> #include <linux/of_platform.h> #include <linux/pfn_t.h> +#include <linux/uio.h> #include <asm/page.h> #include <asm/prom.h> @@ -163,8 +164,15 @@ axon_ram_dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, long nr_pa return __axon_ram_direct_access(bank, pgoff, nr_pages, kaddr, pfn); } +static size_t axon_ram_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff, + void *addr, size_t bytes, struct iov_iter *i) +{ + return copy_from_iter(addr, bytes, i); +} + static const struct dax_operations axon_ram_dax_ops = { .direct_access = axon_ram_dax_direct_access, + .copy_from_iter = axon_ram_copy_from_iter, }; /** diff --git a/arch/powerpc/sysdev/simple_gpio.c b/arch/powerpc/sysdev/simple_gpio.c index ef470b470b04..6afddae2fb47 100644 --- a/arch/powerpc/sysdev/simple_gpio.c +++ b/arch/powerpc/sysdev/simple_gpio.c @@ -75,7 +75,8 @@ static int u8_gpio_dir_out(struct gpio_chip *gc, unsigned int gpio, int val) static void u8_gpio_save_regs(struct of_mm_gpio_chip *mm_gc) { - struct u8_gpio_chip *u8_gc = gpiochip_get_data(&mm_gc->gc); + struct u8_gpio_chip *u8_gc = + container_of(mm_gc, struct u8_gpio_chip, mm_gc); u8_gc->data = in_8(mm_gc->regs); } diff --git a/arch/powerpc/sysdev/xive/common.c b/arch/powerpc/sysdev/xive/common.c index 913825086b8d..8f5e3035483b 100644 --- a/arch/powerpc/sysdev/xive/common.c +++ b/arch/powerpc/sysdev/xive/common.c @@ -297,7 +297,7 @@ void xive_do_source_eoi(u32 hw_irq, struct xive_irq_data *xd) { /* If the XIVE supports the new "store EOI facility, use it */ if (xd->flags & XIVE_IRQ_FLAG_STORE_EOI) - out_be64(xd->eoi_mmio, 0); + out_be64(xd->eoi_mmio + XIVE_ESB_STORE_EOI, 0); else if (hw_irq && xd->flags & XIVE_IRQ_FLAG_EOI_FW) { /* * The FW told us to call it. This happens for some |