diff options
Diffstat (limited to 'arch/powerpc')
74 files changed, 1224 insertions, 831 deletions
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 5e7aaa9976e2..494091762bd7 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -166,7 +166,6 @@ config PPC select ARCH_HAS_SCALED_CPUTIME if VIRT_CPU_ACCOUNTING_NATIVE select HAVE_ARCH_HARDENED_USERCOPY select HAVE_KERNEL_GZIP - select HAVE_CC_STACKPROTECTOR select HAVE_CONTEXT_TRACKING if PPC64 config GENERIC_CSUM @@ -487,6 +486,7 @@ config RELOCATABLE bool "Build a relocatable kernel" depends on (PPC64 && !COMPILE_TEST) || (FLATMEM && (44x || FSL_BOOKE)) select NONSTATIC_KERNEL + select MODULE_REL_CRCS if MODVERSIONS help This builds a kernel image that is capable of running at the location the kernel is loaded at. For ppc32, there is no any diff --git a/arch/powerpc/boot/dts/fsl/mpc8569mds.dts b/arch/powerpc/boot/dts/fsl/mpc8569mds.dts index 8e94448f296c..76b2bd6f7742 100644 --- a/arch/powerpc/boot/dts/fsl/mpc8569mds.dts +++ b/arch/powerpc/boot/dts/fsl/mpc8569mds.dts @@ -55,7 +55,7 @@ label = "kernel"; reg = <0x01c00000 0x002e0000>; }; - partiton@1ee0000 { + partition@1ee0000 { label = "dtb"; reg = <0x01ee0000 0x00020000>; }; diff --git a/arch/powerpc/boot/dts/fsl/t1023si-post.dtsi b/arch/powerpc/boot/dts/fsl/t1023si-post.dtsi index da2894c59479..4908af501098 100644 --- a/arch/powerpc/boot/dts/fsl/t1023si-post.dtsi +++ b/arch/powerpc/boot/dts/fsl/t1023si-post.dtsi @@ -422,7 +422,7 @@ 0x00030001 0x0000000d 0x00030002 0x00000019 0x00030003 0x00000024>; - #thermal-sensor-cells = <0>; + #thermal-sensor-cells = <1>; }; thermal-zones { @@ -430,7 +430,7 @@ polling-delay-passive = <1000>; polling-delay = <5000>; - thermal-sensors = <&tmu>; + thermal-sensors = <&tmu 0>; trips { cpu_alert: cpu-alert { diff --git a/arch/powerpc/boot/dts/fsl/t1040si-post.dtsi b/arch/powerpc/boot/dts/fsl/t1040si-post.dtsi index 44e399b17f6f..145c7f43b5b6 100644 --- a/arch/powerpc/boot/dts/fsl/t1040si-post.dtsi +++ b/arch/powerpc/boot/dts/fsl/t1040si-post.dtsi @@ -526,7 +526,7 @@ 0x00030000 0x00000012 0x00030001 0x0000001d>; - #thermal-sensor-cells = <0>; + #thermal-sensor-cells = <1>; }; thermal-zones { @@ -534,7 +534,7 @@ polling-delay-passive = <1000>; polling-delay = <5000>; - thermal-sensors = <&tmu>; + thermal-sensors = <&tmu 2>; trips { cpu_alert: cpu-alert { diff --git a/arch/powerpc/boot/dts/fsl/t2081si-post.dtsi b/arch/powerpc/boot/dts/fsl/t2081si-post.dtsi index c744569a20e1..a97296c64eb2 100644 --- a/arch/powerpc/boot/dts/fsl/t2081si-post.dtsi +++ b/arch/powerpc/boot/dts/fsl/t2081si-post.dtsi @@ -678,5 +678,6 @@ compatible = "fsl,t2080-l2-cache-controller"; reg = <0xc20000 0x40000>; next-level-cache = <&cpc>; + interrupts = <16 2 1 9>; }; }; diff --git a/arch/powerpc/configs/ppc6xx_defconfig b/arch/powerpc/configs/ppc6xx_defconfig index 3ce91a3df27f..1d2d69dd6409 100644 --- a/arch/powerpc/configs/ppc6xx_defconfig +++ b/arch/powerpc/configs/ppc6xx_defconfig @@ -62,7 +62,6 @@ CONFIG_MPC8610_HPCD=y CONFIG_GEF_SBC610=y CONFIG_CPU_FREQ=y CONFIG_CPU_FREQ_STAT=m -CONFIG_CPU_FREQ_STAT_DETAILS=y CONFIG_CPU_FREQ_DEFAULT_GOV_USERSPACE=y CONFIG_CPU_FREQ_GOV_PERFORMANCE=y CONFIG_CPU_FREQ_GOV_POWERSAVE=m diff --git a/arch/powerpc/include/asm/accounting.h b/arch/powerpc/include/asm/accounting.h index c133246df467..3abcf98ed2e0 100644 --- a/arch/powerpc/include/asm/accounting.h +++ b/arch/powerpc/include/asm/accounting.h @@ -12,9 +12,17 @@ /* Stuff for accurate time accounting */ struct cpu_accounting_data { - unsigned long user_time; /* accumulated usermode TB ticks */ - unsigned long system_time; /* accumulated system TB ticks */ - unsigned long user_time_scaled; /* accumulated usermode SPURR ticks */ + /* Accumulated cputime values to flush on ticks*/ + unsigned long utime; + unsigned long stime; + unsigned long utime_scaled; + unsigned long stime_scaled; + unsigned long gtime; + unsigned long hardirq_time; + unsigned long softirq_time; + unsigned long steal_time; + unsigned long idle_time; + /* Internal counters */ unsigned long starttime; /* TB value snapshot */ unsigned long starttime_user; /* TB value on exit to usermode */ unsigned long startspurr; /* SPURR value snapshot */ diff --git a/arch/powerpc/include/asm/book3s/64/mmu.h b/arch/powerpc/include/asm/book3s/64/mmu.h index d73e9dfa5237..1145dc8e726d 100644 --- a/arch/powerpc/include/asm/book3s/64/mmu.h +++ b/arch/powerpc/include/asm/book3s/64/mmu.h @@ -30,7 +30,7 @@ extern struct mmu_psize_def mmu_psize_defs[MMU_PAGE_COUNT]; #ifndef __ASSEMBLY__ /* - * ISA 3.0 partiton and process table entry format + * ISA 3.0 partition and process table entry format */ struct prtb_entry { __be64 prtb0; diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h index fef738229a68..1eeeb72c7015 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable.h @@ -1,6 +1,9 @@ #ifndef _ASM_POWERPC_BOOK3S_64_PGTABLE_H_ #define _ASM_POWERPC_BOOK3S_64_PGTABLE_H_ +#ifndef __ASSEMBLY__ +#include <linux/mmdebug.h> +#endif /* * Common bits between hash and Radix page table */ @@ -434,15 +437,47 @@ static inline pte_t pte_clear_soft_dirty(pte_t pte) #endif /* CONFIG_HAVE_ARCH_SOFT_DIRTY */ #ifdef CONFIG_NUMA_BALANCING -/* - * These work without NUMA balancing but the kernel does not care. See the - * comment in include/asm-generic/pgtable.h . On powerpc, this will only - * work for user pages and always return true for kernel pages. - */ static inline int pte_protnone(pte_t pte) { - return (pte_raw(pte) & cpu_to_be64(_PAGE_PRESENT | _PAGE_PRIVILEGED)) == - cpu_to_be64(_PAGE_PRESENT | _PAGE_PRIVILEGED); + return (pte_raw(pte) & cpu_to_be64(_PAGE_PRESENT | _PAGE_PTE | _PAGE_RWX)) == + cpu_to_be64(_PAGE_PRESENT | _PAGE_PTE); +} + +#define pte_mk_savedwrite pte_mk_savedwrite +static inline pte_t pte_mk_savedwrite(pte_t pte) +{ + /* + * Used by Autonuma subsystem to preserve the write bit + * while marking the pte PROT_NONE. Only allow this + * on PROT_NONE pte + */ + VM_BUG_ON((pte_raw(pte) & cpu_to_be64(_PAGE_PRESENT | _PAGE_RWX | _PAGE_PRIVILEGED)) != + cpu_to_be64(_PAGE_PRESENT | _PAGE_PRIVILEGED)); + return __pte(pte_val(pte) & ~_PAGE_PRIVILEGED); +} + +#define pte_clear_savedwrite pte_clear_savedwrite +static inline pte_t pte_clear_savedwrite(pte_t pte) +{ + /* + * Used by KSM subsystem to make a protnone pte readonly. + */ + VM_BUG_ON(!pte_protnone(pte)); + return __pte(pte_val(pte) | _PAGE_PRIVILEGED); +} + +#define pte_savedwrite pte_savedwrite +static inline bool pte_savedwrite(pte_t pte) +{ + /* + * Saved write ptes are prot none ptes that doesn't have + * privileged bit sit. We mark prot none as one which has + * present and pviliged bit set and RWX cleared. To mark + * protnone which used to have _PAGE_WRITE set we clear + * the privileged bit. + */ + VM_BUG_ON(!pte_protnone(pte)); + return !(pte_raw(pte) & cpu_to_be64(_PAGE_RWX | _PAGE_PRIVILEGED)); } #endif /* CONFIG_NUMA_BALANCING */ @@ -873,6 +908,8 @@ static inline pte_t *pmdp_ptep(pmd_t *pmd) #define pmd_mkclean(pmd) pte_pmd(pte_mkclean(pmd_pte(pmd))) #define pmd_mkyoung(pmd) pte_pmd(pte_mkyoung(pmd_pte(pmd))) #define pmd_mkwrite(pmd) pte_pmd(pte_mkwrite(pmd_pte(pmd))) +#define pmd_mk_savedwrite(pmd) pte_pmd(pte_mk_savedwrite(pmd_pte(pmd))) +#define pmd_clear_savedwrite(pmd) pte_pmd(pte_clear_savedwrite(pmd_pte(pmd))) #ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY #define pmd_soft_dirty(pmd) pte_soft_dirty(pmd_pte(pmd)) @@ -889,6 +926,7 @@ static inline int pmd_protnone(pmd_t pmd) #define __HAVE_ARCH_PMD_WRITE #define pmd_write(pmd) pte_write(pmd_pte(pmd)) +#define pmd_savedwrite(pmd) pte_savedwrite(pmd_pte(pmd)) #ifdef CONFIG_TRANSPARENT_HUGEPAGE extern pmd_t pfn_pmd(unsigned long pfn, pgprot_t pgprot); diff --git a/arch/powerpc/include/asm/cpu_has_feature.h b/arch/powerpc/include/asm/cpu_has_feature.h index b312b152461b..6e834caa3720 100644 --- a/arch/powerpc/include/asm/cpu_has_feature.h +++ b/arch/powerpc/include/asm/cpu_has_feature.h @@ -23,7 +23,9 @@ static __always_inline bool cpu_has_feature(unsigned long feature) { int i; +#ifndef __clang__ /* clang can't cope with this */ BUILD_BUG_ON(!__builtin_constant_p(feature)); +#endif #ifdef CONFIG_JUMP_LABEL_FEATURE_CHECK_DEBUG if (!static_key_initialized) { diff --git a/arch/powerpc/include/asm/cputime.h b/arch/powerpc/include/asm/cputime.h index aa2e6a34b872..99b541865d8d 100644 --- a/arch/powerpc/include/asm/cputime.h +++ b/arch/powerpc/include/asm/cputime.h @@ -16,12 +16,7 @@ #ifndef __POWERPC_CPUTIME_H #define __POWERPC_CPUTIME_H -#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE -#include <asm-generic/cputime.h> -#ifdef __KERNEL__ -static inline void setup_cputime_one_jiffy(void) { } -#endif -#else +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE #include <linux/types.h> #include <linux/time.h> @@ -36,65 +31,6 @@ typedef u64 __nocast cputime64_t; #define cmpxchg_cputime(ptr, old, new) cmpxchg(ptr, old, new) #ifdef __KERNEL__ - -/* - * One jiffy in timebase units computed during initialization - */ -extern cputime_t cputime_one_jiffy; - -/* - * Convert cputime <-> jiffies - */ -extern u64 __cputime_jiffies_factor; - -static inline unsigned long cputime_to_jiffies(const cputime_t ct) -{ - return mulhdu((__force u64) ct, __cputime_jiffies_factor); -} - -static inline cputime_t jiffies_to_cputime(const unsigned long jif) -{ - u64 ct; - unsigned long sec; - - /* have to be a little careful about overflow */ - ct = jif % HZ; - sec = jif / HZ; - if (ct) { - ct *= tb_ticks_per_sec; - do_div(ct, HZ); - } - if (sec) - ct += (cputime_t) sec * tb_ticks_per_sec; - return (__force cputime_t) ct; -} - -static inline void setup_cputime_one_jiffy(void) -{ - cputime_one_jiffy = jiffies_to_cputime(1); -} - -static inline cputime64_t jiffies64_to_cputime64(const u64 jif) -{ - u64 ct; - u64 sec = jif; - - /* have to be a little careful about overflow */ - ct = do_div(sec, HZ); - if (ct) { - ct *= tb_ticks_per_sec; - do_div(ct, HZ); - } - if (sec) - ct += (u64) sec * tb_ticks_per_sec; - return (__force cputime64_t) ct; -} - -static inline u64 cputime64_to_jiffies64(const cputime_t ct) -{ - return mulhdu((__force u64) ct, __cputime_jiffies_factor); -} - /* * Convert cputime <-> microseconds */ @@ -105,117 +41,6 @@ static inline unsigned long cputime_to_usecs(const cputime_t ct) return mulhdu((__force u64) ct, __cputime_usec_factor); } -static inline cputime_t usecs_to_cputime(const unsigned long us) -{ - u64 ct; - unsigned long sec; - - /* have to be a little careful about overflow */ - ct = us % 1000000; - sec = us / 1000000; - if (ct) { - ct *= tb_ticks_per_sec; - do_div(ct, 1000000); - } - if (sec) - ct += (cputime_t) sec * tb_ticks_per_sec; - return (__force cputime_t) ct; -} - -#define usecs_to_cputime64(us) usecs_to_cputime(us) - -/* - * Convert cputime <-> seconds - */ -extern u64 __cputime_sec_factor; - -static inline unsigned long cputime_to_secs(const cputime_t ct) -{ - return mulhdu((__force u64) ct, __cputime_sec_factor); -} - -static inline cputime_t secs_to_cputime(const unsigned long sec) -{ - return (__force cputime_t)((u64) sec * tb_ticks_per_sec); -} - -/* - * Convert cputime <-> timespec - */ -static inline void cputime_to_timespec(const cputime_t ct, struct timespec *p) -{ - u64 x = (__force u64) ct; - unsigned int frac; - - frac = do_div(x, tb_ticks_per_sec); - p->tv_sec = x; - x = (u64) frac * 1000000000; - do_div(x, tb_ticks_per_sec); - p->tv_nsec = x; -} - -static inline cputime_t timespec_to_cputime(const struct timespec *p) -{ - u64 ct; - - ct = (u64) p->tv_nsec * tb_ticks_per_sec; - do_div(ct, 1000000000); - return (__force cputime_t)(ct + (u64) p->tv_sec * tb_ticks_per_sec); -} - -/* - * Convert cputime <-> timeval - */ -static inline void cputime_to_timeval(const cputime_t ct, struct timeval *p) -{ - u64 x = (__force u64) ct; - unsigned int frac; - - frac = do_div(x, tb_ticks_per_sec); - p->tv_sec = x; - x = (u64) frac * 1000000; - do_div(x, tb_ticks_per_sec); - p->tv_usec = x; -} - -static inline cputime_t timeval_to_cputime(const struct timeval *p) -{ - u64 ct; - - ct = (u64) p->tv_usec * tb_ticks_per_sec; - do_div(ct, 1000000); - return (__force cputime_t)(ct + (u64) p->tv_sec * tb_ticks_per_sec); -} - -/* - * Convert cputime <-> clock_t (units of 1/USER_HZ seconds) - */ -extern u64 __cputime_clockt_factor; - -static inline unsigned long cputime_to_clock_t(const cputime_t ct) -{ - return mulhdu((__force u64) ct, __cputime_clockt_factor); -} - -static inline cputime_t clock_t_to_cputime(const unsigned long clk) -{ - u64 ct; - unsigned long sec; - - /* have to be a little careful about overflow */ - ct = clk % USER_HZ; - sec = clk / USER_HZ; - if (ct) { - ct *= tb_ticks_per_sec; - do_div(ct, USER_HZ); - } - if (sec) - ct += (u64) sec * tb_ticks_per_sec; - return (__force cputime_t) ct; -} - -#define cputime64_to_clock_t(ct) cputime_to_clock_t((cputime_t)(ct)) - /* * PPC64 uses PACA which is task independent for storing accounting data while * PPC32 uses struct thread_info, therefore at task switch the accounting data diff --git a/arch/powerpc/include/asm/device.h b/arch/powerpc/include/asm/device.h index 406c2b1ff82d..0245bfcaac32 100644 --- a/arch/powerpc/include/asm/device.h +++ b/arch/powerpc/include/asm/device.h @@ -6,7 +6,6 @@ #ifndef _ASM_POWERPC_DEVICE_H #define _ASM_POWERPC_DEVICE_H -struct dma_map_ops; struct device_node; #ifdef CONFIG_PPC64 struct pci_dn; @@ -20,9 +19,6 @@ struct iommu_table; * drivers/macintosh/macio_asic.c */ struct dev_archdata { - /* DMA operations on that device */ - struct dma_map_ops *dma_ops; - /* * These two used to be a union. However, with the hybrid ops we need * both so here we store both a DMA offset for direct mappings and diff --git a/arch/powerpc/include/asm/dma-mapping.h b/arch/powerpc/include/asm/dma-mapping.h index 84e3f8dd5e4f..181a095468e4 100644 --- a/arch/powerpc/include/asm/dma-mapping.h +++ b/arch/powerpc/include/asm/dma-mapping.h @@ -76,24 +76,16 @@ static inline unsigned long device_to_mask(struct device *dev) #ifdef CONFIG_PPC64 extern struct dma_map_ops dma_iommu_ops; #endif -extern struct dma_map_ops dma_direct_ops; +extern const struct dma_map_ops dma_direct_ops; -static inline struct dma_map_ops *get_dma_ops(struct device *dev) +static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus) { /* We don't handle the NULL dev case for ISA for now. We could * do it via an out of line call but it is not needed for now. The * only ISA DMA device we support is the floppy and we have a hack * in the floppy driver directly to get a device for us. */ - if (unlikely(dev == NULL)) - return NULL; - - return dev->archdata.dma_ops; -} - -static inline void set_dma_ops(struct device *dev, struct dma_map_ops *ops) -{ - dev->archdata.dma_ops = ops; + return NULL; } /* diff --git a/arch/powerpc/include/asm/fsl_hcalls.h b/arch/powerpc/include/asm/fsl_hcalls.h index 3abb58394da4..b889d13547fd 100644 --- a/arch/powerpc/include/asm/fsl_hcalls.h +++ b/arch/powerpc/include/asm/fsl_hcalls.h @@ -109,7 +109,7 @@ static inline unsigned int fh_send_nmi(unsigned int vcpu_mask) #define FH_DTPROP_MAX_PROPLEN 32768 /** - * fh_partiton_get_dtprop - get a property from a guest device tree. + * fh_partition_get_dtprop - get a property from a guest device tree. * @handle: handle of partition whose device tree is to be accessed * @dtpath_addr: physical address of device tree path to access * @propname_addr: physical address of name of property diff --git a/arch/powerpc/include/asm/kprobes.h b/arch/powerpc/include/asm/kprobes.h index d821835ade86..0503c98b2117 100644 --- a/arch/powerpc/include/asm/kprobes.h +++ b/arch/powerpc/include/asm/kprobes.h @@ -1,5 +1,8 @@ #ifndef _ASM_POWERPC_KPROBES_H #define _ASM_POWERPC_KPROBES_H + +#include <asm-generic/kprobes.h> + #ifdef __KERNEL__ /* * Kernel Probes (KProbes) diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h index 0db010cc4e65..d9b48f5bb606 100644 --- a/arch/powerpc/include/asm/kvm_book3s_64.h +++ b/arch/powerpc/include/asm/kvm_book3s_64.h @@ -22,6 +22,10 @@ #include <asm/book3s/64/mmu-hash.h> +/* Power architecture requires HPT is at least 256kiB, at most 64TiB */ +#define PPC_MIN_HPT_ORDER 18 +#define PPC_MAX_HPT_ORDER 46 + #ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE static inline struct kvmppc_book3s_shadow_vcpu *svcpu_get(struct kvm_vcpu *vcpu) { @@ -356,6 +360,18 @@ extern void kvmppc_mmu_debugfs_init(struct kvm *kvm); extern void kvmhv_rm_send_ipi(int cpu); +static inline unsigned long kvmppc_hpt_npte(struct kvm_hpt_info *hpt) +{ + /* HPTEs are 2**4 bytes long */ + return 1UL << (hpt->order - 4); +} + +static inline unsigned long kvmppc_hpt_mask(struct kvm_hpt_info *hpt) +{ + /* 128 (2**7) bytes in each HPTEG */ + return (1UL << (hpt->order - 7)) - 1; +} + #endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */ #endif /* __ASM_KVM_BOOK3S_64_H__ */ diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index b2dbeac3f450..7bba8f415627 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -241,12 +241,24 @@ struct kvm_arch_memory_slot { #endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */ }; +struct kvm_hpt_info { + /* Host virtual (linear mapping) address of guest HPT */ + unsigned long virt; + /* Array of reverse mapping entries for each guest HPTE */ + struct revmap_entry *rev; + /* Guest HPT size is 2**(order) bytes */ + u32 order; + /* 1 if HPT allocated with CMA, 0 otherwise */ + int cma; +}; + +struct kvm_resize_hpt; + struct kvm_arch { unsigned int lpid; #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE unsigned int tlb_sets; - unsigned long hpt_virt; - struct revmap_entry *revmap; + struct kvm_hpt_info hpt; atomic64_t mmio_update; unsigned int host_lpid; unsigned long host_lpcr; @@ -256,20 +268,17 @@ struct kvm_arch { unsigned long lpcr; unsigned long vrma_slb_v; int hpte_setup_done; - u32 hpt_order; atomic_t vcpus_running; u32 online_vcores; - unsigned long hpt_npte; - unsigned long hpt_mask; atomic_t hpte_mod_interest; cpumask_t need_tlb_flush; cpumask_t cpu_in_guest; - int hpt_cma_alloc; u8 radix; pgd_t *pgtable; u64 process_table; struct dentry *debugfs_dir; struct dentry *htab_dentry; + struct kvm_resize_hpt *resize_hpt; /* protected by kvm->lock */ #endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */ #ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE struct mutex hpt_mutex; diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h index 48c760f89590..dd11c4c8c56a 100644 --- a/arch/powerpc/include/asm/kvm_ppc.h +++ b/arch/powerpc/include/asm/kvm_ppc.h @@ -155,9 +155,10 @@ extern void kvmppc_core_destroy_mmu(struct kvm_vcpu *vcpu); extern int kvmppc_kvm_pv(struct kvm_vcpu *vcpu); extern void kvmppc_map_magic(struct kvm_vcpu *vcpu); -extern long kvmppc_alloc_hpt(struct kvm *kvm, u32 *htab_orderp); -extern long kvmppc_alloc_reset_hpt(struct kvm *kvm, u32 *htab_orderp); -extern void kvmppc_free_hpt(struct kvm *kvm); +extern int kvmppc_allocate_hpt(struct kvm_hpt_info *info, u32 order); +extern void kvmppc_set_hpt(struct kvm *kvm, struct kvm_hpt_info *info); +extern long kvmppc_alloc_reset_hpt(struct kvm *kvm, int order); +extern void kvmppc_free_hpt(struct kvm_hpt_info *info); extern long kvmppc_prepare_vrma(struct kvm *kvm, struct kvm_userspace_memory_region *mem); extern void kvmppc_map_vrma(struct kvm_vcpu *vcpu, @@ -186,8 +187,8 @@ extern long kvmppc_h_stuff_tce(struct kvm_vcpu *vcpu, unsigned long tce_value, unsigned long npages); extern long kvmppc_h_get_tce(struct kvm_vcpu *vcpu, unsigned long liobn, unsigned long ioba); -extern struct page *kvm_alloc_hpt(unsigned long nr_pages); -extern void kvm_release_hpt(struct page *page, unsigned long nr_pages); +extern struct page *kvm_alloc_hpt_cma(unsigned long nr_pages); +extern void kvm_free_hpt_cma(struct page *page, unsigned long nr_pages); extern int kvmppc_core_init_vm(struct kvm *kvm); extern void kvmppc_core_destroy_vm(struct kvm *kvm); extern void kvmppc_core_free_memslot(struct kvm *kvm, @@ -214,6 +215,10 @@ extern void kvmppc_bookehv_exit(void); extern int kvmppc_prepare_to_enter(struct kvm_vcpu *vcpu); extern int kvm_vm_ioctl_get_htab_fd(struct kvm *kvm, struct kvm_get_htab_fd *); +extern long kvm_vm_ioctl_resize_hpt_prepare(struct kvm *kvm, + struct kvm_ppc_resize_hpt *rhpt); +extern long kvm_vm_ioctl_resize_hpt_commit(struct kvm *kvm, + struct kvm_ppc_resize_hpt *rhpt); int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu, struct kvm_interrupt *irq); diff --git a/arch/powerpc/include/asm/livepatch.h b/arch/powerpc/include/asm/livepatch.h index a402f7f94896..47a03b9b528b 100644 --- a/arch/powerpc/include/asm/livepatch.h +++ b/arch/powerpc/include/asm/livepatch.h @@ -28,13 +28,6 @@ static inline int klp_check_compiler_support(void) return 0; } -static inline int klp_write_module_reloc(struct module *mod, unsigned long - type, unsigned long loc, unsigned long value) -{ - /* This requires infrastructure changes; we need the loadinfos. */ - return -ENOSYS; -} - static inline void klp_arch_set_pc(struct pt_regs *regs, unsigned long ip) { regs->nip = ip; diff --git a/arch/powerpc/include/asm/mmu.h b/arch/powerpc/include/asm/mmu.h index e5616bf83623..065e762fae85 100644 --- a/arch/powerpc/include/asm/mmu.h +++ b/arch/powerpc/include/asm/mmu.h @@ -161,7 +161,9 @@ static __always_inline bool mmu_has_feature(unsigned long feature) { int i; +#ifndef __clang__ /* clang can't cope with this */ BUILD_BUG_ON(!__builtin_constant_p(feature)); +#endif #ifdef CONFIG_JUMP_LABEL_FEATURE_CHECK_DEBUG if (!static_key_initialized) { diff --git a/arch/powerpc/include/asm/module.h b/arch/powerpc/include/asm/module.h index cc12c61ef315..53885512b8d3 100644 --- a/arch/powerpc/include/asm/module.h +++ b/arch/powerpc/include/asm/module.h @@ -90,9 +90,5 @@ static inline int module_finalize_ftrace(struct module *mod, const Elf_Shdr *sec } #endif -#if defined(CONFIG_MODVERSIONS) && defined(CONFIG_PPC64) -#define ARCH_RELOCATES_KCRCTAB -#define reloc_start PHYSICAL_START -#endif #endif /* __KERNEL__ */ #endif /* _ASM_POWERPC_MODULE_H */ diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h index 6a6792bb39fb..708c3e592eeb 100644 --- a/arch/powerpc/include/asm/paca.h +++ b/arch/powerpc/include/asm/paca.h @@ -187,7 +187,6 @@ struct paca_struct { /* Stuff for accurate time accounting */ struct cpu_accounting_data accounting; - u64 stolen_time; /* TB ticks taken by hypervisor */ u64 dtl_ridx; /* read index in dispatch log */ struct dtl_entry *dtl_curr; /* pointer corresponding to dtl_ridx */ diff --git a/arch/powerpc/include/asm/page.h b/arch/powerpc/include/asm/page.h index 47120bf2670c..2a32483c7b6c 100644 --- a/arch/powerpc/include/asm/page.h +++ b/arch/powerpc/include/asm/page.h @@ -230,7 +230,9 @@ extern long long virt_phys_offset; * and needs to be executable. This means the whole heap ends * up being executable. */ -#define VM_DATA_DEFAULT_FLAGS32 (VM_READ | VM_WRITE | VM_EXEC | \ +#define VM_DATA_DEFAULT_FLAGS32 \ + (((current->personality & READ_IMPLIES_EXEC) ? VM_EXEC : 0) | \ + VM_READ | VM_WRITE | \ VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC) #define VM_DATA_DEFAULT_FLAGS64 (VM_READ | VM_WRITE | \ diff --git a/arch/powerpc/include/asm/pci.h b/arch/powerpc/include/asm/pci.h index e9bd6cf0212f..93eded8d3843 100644 --- a/arch/powerpc/include/asm/pci.h +++ b/arch/powerpc/include/asm/pci.h @@ -53,8 +53,8 @@ static inline int pci_get_legacy_ide_irq(struct pci_dev *dev, int channel) } #ifdef CONFIG_PCI -extern void set_pci_dma_ops(struct dma_map_ops *dma_ops); -extern struct dma_map_ops *get_pci_dma_ops(void); +extern void set_pci_dma_ops(const struct dma_map_ops *dma_ops); +extern const struct dma_map_ops *get_pci_dma_ops(void); #else /* CONFIG_PCI */ #define set_pci_dma_ops(d) #define get_pci_dma_ops() NULL diff --git a/arch/powerpc/include/asm/ps3.h b/arch/powerpc/include/asm/ps3.h index a19f831a4cc9..17ee719e799f 100644 --- a/arch/powerpc/include/asm/ps3.h +++ b/arch/powerpc/include/asm/ps3.h @@ -435,7 +435,7 @@ static inline void *ps3_system_bus_get_drvdata( return dev_get_drvdata(&dev->core); } -/* These two need global scope for get_dma_ops(). */ +/* These two need global scope for get_arch_dma_ops(). */ extern struct bus_type ps3_system_bus_type; diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index 9c4689401298..fc879fd6bdae 100644 --- a/arch/powerpc/include/asm/reg.h +++ b/arch/powerpc/include/asm/reg.h @@ -655,9 +655,10 @@ #define SRR1_ISI_N_OR_G 0x10000000 /* ISI: Access is no-exec or G */ #define SRR1_ISI_PROT 0x08000000 /* ISI: Other protection fault */ #define SRR1_WAKEMASK 0x00380000 /* reason for wakeup */ -#define SRR1_WAKEMASK_P8 0x003c0000 /* reason for wakeup on POWER8 */ +#define SRR1_WAKEMASK_P8 0x003c0000 /* reason for wakeup on POWER8 and 9 */ #define SRR1_WAKESYSERR 0x00300000 /* System error */ #define SRR1_WAKEEE 0x00200000 /* External interrupt */ +#define SRR1_WAKEHVI 0x00240000 /* Hypervisor Virtualization Interrupt (P9) */ #define SRR1_WAKEMT 0x00280000 /* mtctrl */ #define SRR1_WAKEHMI 0x00280000 /* Hypervisor maintenance */ #define SRR1_WAKEDEC 0x00180000 /* Decrementer interrupt */ diff --git a/arch/powerpc/include/asm/stackprotector.h b/arch/powerpc/include/asm/stackprotector.h deleted file mode 100644 index 6720190eabec..000000000000 --- a/arch/powerpc/include/asm/stackprotector.h +++ /dev/null @@ -1,40 +0,0 @@ -/* - * GCC stack protector support. - * - * Stack protector works by putting predefined pattern at the start of - * the stack frame and verifying that it hasn't been overwritten when - * returning from the function. The pattern is called stack canary - * and gcc expects it to be defined by a global variable called - * "__stack_chk_guard" on PPC. This unfortunately means that on SMP - * we cannot have a different canary value per task. - */ - -#ifndef _ASM_STACKPROTECTOR_H -#define _ASM_STACKPROTECTOR_H - -#include <linux/random.h> -#include <linux/version.h> -#include <asm/reg.h> - -extern unsigned long __stack_chk_guard; - -/* - * Initialize the stackprotector canary value. - * - * NOTE: this must only be called from functions that never return, - * and it must always be inlined. - */ -static __always_inline void boot_init_stack_canary(void) -{ - unsigned long canary; - - /* Try to get a semi random initial value. */ - get_random_bytes(&canary, sizeof(canary)); - canary ^= mftb(); - canary ^= LINUX_VERSION_CODE; - - current->stack_canary = canary; - __stack_chk_guard = current->stack_canary; -} - -#endif /* _ASM_STACKPROTECTOR_H */ diff --git a/arch/powerpc/include/asm/swiotlb.h b/arch/powerpc/include/asm/swiotlb.h index de99d6e29430..01d45a5fd00b 100644 --- a/arch/powerpc/include/asm/swiotlb.h +++ b/arch/powerpc/include/asm/swiotlb.h @@ -13,7 +13,7 @@ #include <linux/swiotlb.h> -extern struct dma_map_ops swiotlb_dma_ops; +extern const struct dma_map_ops swiotlb_dma_ops; static inline void dma_mark_clean(void *addr, size_t size) {} diff --git a/arch/powerpc/include/asm/xics.h b/arch/powerpc/include/asm/xics.h index f0b238516e9b..e0b9e576905a 100644 --- a/arch/powerpc/include/asm/xics.h +++ b/arch/powerpc/include/asm/xics.h @@ -44,6 +44,7 @@ static inline int icp_hv_init(void) { return -ENODEV; } #ifdef CONFIG_PPC_POWERNV extern int icp_opal_init(void); +extern void icp_opal_flush_interrupt(void); #else static inline int icp_opal_init(void) { return -ENODEV; } #endif diff --git a/arch/powerpc/include/uapi/asm/kvm.h b/arch/powerpc/include/uapi/asm/kvm.h index cc0908b6c2a0..4edbe4bb0e8b 100644 --- a/arch/powerpc/include/uapi/asm/kvm.h +++ b/arch/powerpc/include/uapi/asm/kvm.h @@ -633,5 +633,7 @@ struct kvm_ppc_rmmu_info { #define KVM_XICS_LEVEL_SENSITIVE (1ULL << 40) #define KVM_XICS_MASKED (1ULL << 41) #define KVM_XICS_PENDING (1ULL << 42) +#define KVM_XICS_PRESENTED (1ULL << 43) +#define KVM_XICS_QUEUED (1ULL << 44) #endif /* __LINUX_KVM_POWERPC_H */ diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index a048b37b9b27..811f441a125f 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -19,10 +19,6 @@ CFLAGS_prom_init.o += $(DISABLE_LATENT_ENTROPY_PLUGIN) CFLAGS_btext.o += $(DISABLE_LATENT_ENTROPY_PLUGIN) CFLAGS_prom.o += $(DISABLE_LATENT_ENTROPY_PLUGIN) -# -fstack-protector triggers protection checks in this code, -# but it is being used too early to link to meaningful stack_chk logic. -CFLAGS_prom_init.o += $(call cc-option, -fno-stack-protector) - ifdef CONFIG_FUNCTION_TRACER # Do not trace early boot code CFLAGS_REMOVE_cputable.o = -mno-sched-epilog $(CC_FLAGS_FTRACE) diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index b6709021fee5..4367e7df51a1 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -94,9 +94,6 @@ int main(void) OFFSET(TI_livepatch_sp, thread_info, livepatch_sp); #endif -#ifdef CONFIG_CC_STACKPROTECTOR - DEFINE(TSK_STACK_CANARY, offsetof(struct task_struct, stack_canary)); -#endif OFFSET(KSP, thread_struct, ksp); OFFSET(PT_REGS, thread_struct, regs); #ifdef CONFIG_BOOKE @@ -242,8 +239,8 @@ int main(void) OFFSET(PACA_DSCR_DEFAULT, paca_struct, dscr_default); OFFSET(ACCOUNT_STARTTIME, paca_struct, accounting.starttime); OFFSET(ACCOUNT_STARTTIME_USER, paca_struct, accounting.starttime_user); - OFFSET(ACCOUNT_USER_TIME, paca_struct, accounting.user_time); - OFFSET(ACCOUNT_SYSTEM_TIME, paca_struct, accounting.system_time); + OFFSET(ACCOUNT_USER_TIME, paca_struct, accounting.utime); + OFFSET(ACCOUNT_SYSTEM_TIME, paca_struct, accounting.stime); OFFSET(PACA_TRAP_SAVE, paca_struct, trap_save); OFFSET(PACA_NAPSTATELOST, paca_struct, nap_state_lost); OFFSET(PACA_SPRG_VDSO, paca_struct, sprg_vdso); @@ -251,8 +248,8 @@ int main(void) #ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE OFFSET(ACCOUNT_STARTTIME, thread_info, accounting.starttime); OFFSET(ACCOUNT_STARTTIME_USER, thread_info, accounting.starttime_user); - OFFSET(ACCOUNT_USER_TIME, thread_info, accounting.user_time); - OFFSET(ACCOUNT_SYSTEM_TIME, thread_info, accounting.system_time); + OFFSET(ACCOUNT_USER_TIME, thread_info, accounting.utime); + OFFSET(ACCOUNT_SYSTEM_TIME, thread_info, accounting.stime); #endif #endif /* CONFIG_PPC64 */ diff --git a/arch/powerpc/kernel/dma-swiotlb.c b/arch/powerpc/kernel/dma-swiotlb.c index c6689f658b50..d0ea7860e02b 100644 --- a/arch/powerpc/kernel/dma-swiotlb.c +++ b/arch/powerpc/kernel/dma-swiotlb.c @@ -46,7 +46,7 @@ static u64 swiotlb_powerpc_get_required(struct device *dev) * map_page, and unmap_page on highmem, use normal dma_ops * for everything else. */ -struct dma_map_ops swiotlb_dma_ops = { +const struct dma_map_ops swiotlb_dma_ops = { .alloc = __dma_direct_alloc_coherent, .free = __dma_direct_free_coherent, .mmap = dma_direct_mmap_coherent, diff --git a/arch/powerpc/kernel/dma.c b/arch/powerpc/kernel/dma.c index 6877e3fa95bb..41c749586bd2 100644 --- a/arch/powerpc/kernel/dma.c +++ b/arch/powerpc/kernel/dma.c @@ -33,7 +33,7 @@ static u64 __maybe_unused get_pfn_limit(struct device *dev) struct dev_archdata __maybe_unused *sd = &dev->archdata; #ifdef CONFIG_SWIOTLB - if (sd->max_direct_dma_addr && sd->dma_ops == &swiotlb_dma_ops) + if (sd->max_direct_dma_addr && dev->dma_ops == &swiotlb_dma_ops) pfn = min_t(u64, pfn, sd->max_direct_dma_addr >> PAGE_SHIFT); #endif @@ -274,7 +274,7 @@ static inline void dma_direct_sync_single(struct device *dev, } #endif -struct dma_map_ops dma_direct_ops = { +const struct dma_map_ops dma_direct_ops = { .alloc = dma_direct_alloc_coherent, .free = dma_direct_free_coherent, .mmap = dma_direct_mmap_coherent, @@ -316,7 +316,7 @@ EXPORT_SYMBOL(dma_set_coherent_mask); int __dma_set_mask(struct device *dev, u64 dma_mask) { - struct dma_map_ops *dma_ops = get_dma_ops(dev); + 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); @@ -344,7 +344,7 @@ EXPORT_SYMBOL(dma_set_mask); u64 __dma_get_required_mask(struct device *dev) { - struct dma_map_ops *dma_ops = get_dma_ops(dev); + const struct dma_map_ops *dma_ops = get_dma_ops(dev); if (unlikely(dma_ops == NULL)) return 0; diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c index d88573bdd090..b94887165a10 100644 --- a/arch/powerpc/kernel/eeh_driver.c +++ b/arch/powerpc/kernel/eeh_driver.c @@ -545,7 +545,7 @@ static void *eeh_pe_detach_dev(void *data, void *userdata) static void *__eeh_clear_pe_frozen_state(void *data, void *flag) { struct eeh_pe *pe = (struct eeh_pe *)data; - bool *clear_sw_state = flag; + bool clear_sw_state = *(bool *)flag; int i, rc = 1; for (i = 0; rc && i < 3; i++) diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S index f3e4fc1c1b4d..a38600949f3a 100644 --- a/arch/powerpc/kernel/entry_32.S +++ b/arch/powerpc/kernel/entry_32.S @@ -681,11 +681,7 @@ BEGIN_FTR_SECTION mtspr SPRN_SPEFSCR,r0 /* restore SPEFSCR reg */ END_FTR_SECTION_IFSET(CPU_FTR_SPE) #endif /* CONFIG_SPE */ -#if defined(CONFIG_CC_STACKPROTECTOR) && !defined(CONFIG_SMP) - lwz r0,TSK_STACK_CANARY(r2) - lis r4,__stack_chk_guard@ha - stw r0,__stack_chk_guard@l(r4) -#endif + lwz r0,_CCR(r1) mtcrf 0xFF,r0 /* r3-r12 are destroyed -- Cort */ diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c index bb1807184bad..0b0f89685b67 100644 --- a/arch/powerpc/kernel/module_64.c +++ b/arch/powerpc/kernel/module_64.c @@ -286,14 +286,6 @@ static void dedotify_versions(struct modversion_info *vers, for (end = (void *)vers + size; vers < end; vers++) if (vers->name[0] == '.') { memmove(vers->name, vers->name+1, strlen(vers->name)); -#ifdef ARCH_RELOCATES_KCRCTAB - /* The TOC symbol has no CRC computed. To avoid CRC - * check failing, we must force it to the expected - * value (see CRC check in module.c). - */ - if (!strcmp(vers->name, "TOC.")) - vers->crc = -(unsigned long)reloc_start; -#endif } } diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c index 05bfdaeaa2f9..ffda24a38dda 100644 --- a/arch/powerpc/kernel/pci-common.c +++ b/arch/powerpc/kernel/pci-common.c @@ -25,6 +25,7 @@ #include <linux/of_address.h> #include <linux/of_pci.h> #include <linux/mm.h> +#include <linux/shmem_fs.h> #include <linux/list.h> #include <linux/syscalls.h> #include <linux/irq.h> @@ -59,14 +60,14 @@ resource_size_t isa_mem_base; EXPORT_SYMBOL(isa_mem_base); -static struct dma_map_ops *pci_dma_ops = &dma_direct_ops; +static const struct dma_map_ops *pci_dma_ops = &dma_direct_ops; -void set_pci_dma_ops(struct dma_map_ops *dma_ops) +void set_pci_dma_ops(const struct dma_map_ops *dma_ops) { pci_dma_ops = dma_ops; } -struct dma_map_ops *get_pci_dma_ops(void) +const struct dma_map_ops *get_pci_dma_ops(void) { return pci_dma_ops; } diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 2dcb65fee638..4379a079b3c2 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -64,12 +64,6 @@ #include <linux/kprobes.h> #include <linux/kdebug.h> -#ifdef CONFIG_CC_STACKPROTECTOR -#include <linux/stackprotector.h> -unsigned long __stack_chk_guard __read_mostly; -EXPORT_SYMBOL(__stack_chk_guard); -#endif - /* Transactional Memory debug */ #ifdef TM_DEBUG_SW #define TM_DEBUG(x...) printk(KERN_INFO x) diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index 1a835e77b54b..a3944540fe0d 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -2850,6 +2850,9 @@ static void __init prom_find_boot_cpu(void) cpu_pkg = call_prom("instance-to-package", 1, 1, prom_cpu); + if (!PHANDLE_VALID(cpu_pkg)) + return; + prom_getprop(cpu_pkg, "reg", &rval, sizeof(rval)); prom.cpu = be32_to_cpu(rval); diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index 893bd7f79be6..573fb3a461b5 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -707,7 +707,7 @@ void start_secondary(void *unused) unsigned int cpu = smp_processor_id(); int i, base; - atomic_inc(&init_mm.mm_count); + mmgrab(&init_mm); current->active_mm = &init_mm; smp_store_cpu_info(cpu); diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index 06bca663b4df..bc84a8d47b9e 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -57,6 +57,7 @@ #include <linux/clk-provider.h> #include <linux/suspend.h> #include <linux/rtc.h> +#include <linux/cputime.h> #include <asm/trace.h> #include <asm/io.h> @@ -72,7 +73,6 @@ #include <asm/smp.h> #include <asm/vdso_datapage.h> #include <asm/firmware.h> -#include <asm/cputime.h> #include <asm/asm-prototypes.h> /* powerpc clocksource/clockevent code */ @@ -152,20 +152,11 @@ EXPORT_SYMBOL_GPL(ppc_tb_freq); #ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE /* - * Factors for converting from cputime_t (timebase ticks) to - * jiffies, microseconds, seconds, and clock_t (1/USER_HZ seconds). - * These are all stored as 0.64 fixed-point binary fractions. + * Factor for converting from cputime_t (timebase ticks) to + * microseconds. This is stored as 0.64 fixed-point binary fraction. */ -u64 __cputime_jiffies_factor; -EXPORT_SYMBOL(__cputime_jiffies_factor); u64 __cputime_usec_factor; EXPORT_SYMBOL(__cputime_usec_factor); -u64 __cputime_sec_factor; -EXPORT_SYMBOL(__cputime_sec_factor); -u64 __cputime_clockt_factor; -EXPORT_SYMBOL(__cputime_clockt_factor); - -cputime_t cputime_one_jiffy; #ifdef CONFIG_PPC_SPLPAR void (*dtl_consumer)(struct dtl_entry *, u64); @@ -181,14 +172,8 @@ static void calc_cputime_factors(void) { struct div_result res; - div128_by_32(HZ, 0, tb_ticks_per_sec, &res); - __cputime_jiffies_factor = res.result_low; div128_by_32(1000000, 0, tb_ticks_per_sec, &res); __cputime_usec_factor = res.result_low; - div128_by_32(1, 0, tb_ticks_per_sec, &res); - __cputime_sec_factor = res.result_low; - div128_by_32(USER_HZ, 0, tb_ticks_per_sec, &res); - __cputime_clockt_factor = res.result_low; } /* @@ -271,25 +256,19 @@ void accumulate_stolen_time(void) sst = scan_dispatch_log(acct->starttime_user); ust = scan_dispatch_log(acct->starttime); - acct->system_time -= sst; - acct->user_time -= ust; - local_paca->stolen_time += ust + sst; + acct->stime -= sst; + acct->utime -= ust; + acct->steal_time += ust + sst; local_paca->soft_enabled = save_soft_enabled; } static inline u64 calculate_stolen_time(u64 stop_tb) { - u64 stolen = 0; + if (get_paca()->dtl_ridx != be64_to_cpu(get_lppaca()->dtl_idx)) + return scan_dispatch_log(stop_tb); - if (get_paca()->dtl_ridx != be64_to_cpu(get_lppaca()->dtl_idx)) { - stolen = scan_dispatch_log(stop_tb); - get_paca()->accounting.system_time -= stolen; - } - - stolen += get_paca()->stolen_time; - get_paca()->stolen_time = 0; - return stolen; + return 0; } #else /* CONFIG_PPC_SPLPAR */ @@ -305,28 +284,27 @@ static inline u64 calculate_stolen_time(u64 stop_tb) * or soft irq state. */ static unsigned long vtime_delta(struct task_struct *tsk, - unsigned long *sys_scaled, - unsigned long *stolen) + unsigned long *stime_scaled, + unsigned long *steal_time) { unsigned long now, nowscaled, deltascaled; - unsigned long udelta, delta, user_scaled; + unsigned long stime; + unsigned long utime, utime_scaled; struct cpu_accounting_data *acct = get_accounting(tsk); WARN_ON_ONCE(!irqs_disabled()); now = mftb(); nowscaled = read_spurr(now); - acct->system_time += now - acct->starttime; + stime = now - acct->starttime; acct->starttime = now; deltascaled = nowscaled - acct->startspurr; acct->startspurr = nowscaled; - *stolen = calculate_stolen_time(now); + *steal_time = calculate_stolen_time(now); - delta = acct->system_time; - acct->system_time = 0; - udelta = acct->user_time - acct->utime_sspurr; - acct->utime_sspurr = acct->user_time; + utime = acct->utime - acct->utime_sspurr; + acct->utime_sspurr = acct->utime; /* * Because we don't read the SPURR on every kernel entry/exit, @@ -338,62 +316,105 @@ static unsigned long vtime_delta(struct task_struct *tsk, * the user ticks get saved up in paca->user_time_scaled to be * used by account_process_tick. */ - *sys_scaled = delta; - user_scaled = udelta; - if (deltascaled != delta + udelta) { - if (udelta) { - *sys_scaled = deltascaled * delta / (delta + udelta); - user_scaled = deltascaled - *sys_scaled; + *stime_scaled = stime; + utime_scaled = utime; + if (deltascaled != stime + utime) { + if (utime) { + *stime_scaled = deltascaled * stime / (stime + utime); + utime_scaled = deltascaled - *stime_scaled; } else { - *sys_scaled = deltascaled; + *stime_scaled = deltascaled; } } - acct->user_time_scaled += user_scaled; + acct->utime_scaled += utime_scaled; - return delta; + return stime; } void vtime_account_system(struct task_struct *tsk) { - unsigned long delta, sys_scaled, stolen; + unsigned long stime, stime_scaled, steal_time; + struct cpu_accounting_data *acct = get_accounting(tsk); + + stime = vtime_delta(tsk, &stime_scaled, &steal_time); - delta = vtime_delta(tsk, &sys_scaled, &stolen); - account_system_time(tsk, 0, delta); - tsk->stimescaled += sys_scaled; - if (stolen) - account_steal_time(stolen); + stime -= min(stime, steal_time); + acct->steal_time += steal_time; + + if ((tsk->flags & PF_VCPU) && !irq_count()) { + acct->gtime += stime; + acct->utime_scaled += stime_scaled; + } else { + if (hardirq_count()) + acct->hardirq_time += stime; + else if (in_serving_softirq()) + acct->softirq_time += stime; + else + acct->stime += stime; + + acct->stime_scaled += stime_scaled; + } } EXPORT_SYMBOL_GPL(vtime_account_system); void vtime_account_idle(struct task_struct *tsk) { - unsigned long delta, sys_scaled, stolen; + unsigned long stime, stime_scaled, steal_time; + struct cpu_accounting_data *acct = get_accounting(tsk); - delta = vtime_delta(tsk, &sys_scaled, &stolen); - account_idle_time(delta + stolen); + stime = vtime_delta(tsk, &stime_scaled, &steal_time); + acct->idle_time += stime + steal_time; } /* - * Transfer the user time accumulated in the paca - * by the exception entry and exit code to the generic - * process user time records. + * Account the whole cputime accumulated in the paca * Must be called with interrupts disabled. * Assumes that vtime_account_system/idle() has been called * recently (i.e. since the last entry from usermode) so that * get_paca()->user_time_scaled is up to date. */ -void vtime_account_user(struct task_struct *tsk) +void vtime_flush(struct task_struct *tsk) { - cputime_t utime, utimescaled; struct cpu_accounting_data *acct = get_accounting(tsk); - utime = acct->user_time; - utimescaled = acct->user_time_scaled; - acct->user_time = 0; - acct->user_time_scaled = 0; + if (acct->utime) + account_user_time(tsk, cputime_to_nsecs(acct->utime)); + + if (acct->utime_scaled) + tsk->utimescaled += cputime_to_nsecs(acct->utime_scaled); + + if (acct->gtime) + account_guest_time(tsk, cputime_to_nsecs(acct->gtime)); + + if (acct->steal_time) + account_steal_time(cputime_to_nsecs(acct->steal_time)); + + if (acct->idle_time) + account_idle_time(cputime_to_nsecs(acct->idle_time)); + + if (acct->stime) + account_system_index_time(tsk, cputime_to_nsecs(acct->stime), + CPUTIME_SYSTEM); + if (acct->stime_scaled) + tsk->stimescaled += cputime_to_nsecs(acct->stime_scaled); + + if (acct->hardirq_time) + account_system_index_time(tsk, cputime_to_nsecs(acct->hardirq_time), + CPUTIME_IRQ); + if (acct->softirq_time) + account_system_index_time(tsk, cputime_to_nsecs(acct->softirq_time), + CPUTIME_SOFTIRQ); + + acct->utime = 0; + acct->utime_scaled = 0; acct->utime_sspurr = 0; - account_user_time(tsk, utime); - tsk->utimescaled += utimescaled; + acct->gtime = 0; + acct->steal_time = 0; + acct->idle_time = 0; + acct->stime = 0; + acct->stime_scaled = 0; + acct->hardirq_time = 0; + acct->softirq_time = 0; } #ifdef CONFIG_PPC32 @@ -407,8 +428,7 @@ void arch_vtime_task_switch(struct task_struct *prev) struct cpu_accounting_data *acct = get_accounting(current); acct->starttime = get_accounting(prev)->starttime; - acct->system_time = 0; - acct->user_time = 0; + acct->startspurr = get_accounting(prev)->startspurr; } #endif /* CONFIG_PPC32 */ @@ -1018,7 +1038,6 @@ void __init time_init(void) tb_ticks_per_sec = ppc_tb_freq; tb_ticks_per_usec = ppc_tb_freq / 1000000; calc_cputime_factors(); - setup_cputime_one_jiffy(); /* * Compute scale factor for sched_clock. diff --git a/arch/powerpc/kvm/book3s_32_mmu.c b/arch/powerpc/kvm/book3s_32_mmu.c index a2eb6d354a57..1992676c7a94 100644 --- a/arch/powerpc/kvm/book3s_32_mmu.c +++ b/arch/powerpc/kvm/book3s_32_mmu.c @@ -224,7 +224,8 @@ static int kvmppc_mmu_book3s_32_xlate_pte(struct kvm_vcpu *vcpu, gva_t eaddr, ptem = kvmppc_mmu_book3s_32_get_ptem(sre, eaddr, primary); if(copy_from_user(pteg, (void __user *)ptegp, sizeof(pteg))) { - printk(KERN_ERR "KVM: Can't copy data from 0x%lx!\n", ptegp); + printk_ratelimited(KERN_ERR + "KVM: Can't copy data from 0x%lx!\n", ptegp); goto no_page_found; } diff --git a/arch/powerpc/kvm/book3s_64_mmu.c b/arch/powerpc/kvm/book3s_64_mmu.c index b9131aa1aedf..70153578131a 100644 --- a/arch/powerpc/kvm/book3s_64_mmu.c +++ b/arch/powerpc/kvm/book3s_64_mmu.c @@ -265,7 +265,8 @@ do_second: goto no_page_found; if(copy_from_user(pteg, (void __user *)ptegp, sizeof(pteg))) { - printk(KERN_ERR "KVM can't copy data from 0x%lx!\n", ptegp); + printk_ratelimited(KERN_ERR + "KVM: Can't copy data from 0x%lx!\n", ptegp); goto no_page_found; } diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c index 9df3d940acec..f3158fb16de3 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_hv.c +++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c @@ -40,84 +40,101 @@ #include "trace_hv.h" -/* Power architecture requires HPT is at least 256kB */ -#define PPC_MIN_HPT_ORDER 18 +//#define DEBUG_RESIZE_HPT 1 + +#ifdef DEBUG_RESIZE_HPT +#define resize_hpt_debug(resize, ...) \ + do { \ + printk(KERN_DEBUG "RESIZE HPT %p: ", resize); \ + printk(__VA_ARGS__); \ + } while (0) +#else +#define resize_hpt_debug(resize, ...) \ + do { } while (0) +#endif static long kvmppc_virtmode_do_h_enter(struct kvm *kvm, unsigned long flags, long pte_index, unsigned long pteh, unsigned long ptel, unsigned long *pte_idx_ret); + +struct kvm_resize_hpt { + /* These fields read-only after init */ + struct kvm *kvm; + struct work_struct work; + u32 order; + + /* These fields protected by kvm->lock */ + int error; + bool prepare_done; + + /* Private to the work thread, until prepare_done is true, + * then protected by kvm->resize_hpt_sem */ + struct kvm_hpt_info hpt; +}; + static void kvmppc_rmap_reset(struct kvm *kvm); -long kvmppc_alloc_hpt(struct kvm *kvm, u32 *htab_orderp) +int kvmppc_allocate_hpt(struct kvm_hpt_info *info, u32 order) { unsigned long hpt = 0; - struct revmap_entry *rev; + int cma = 0; struct page *page = NULL; - long order = KVM_DEFAULT_HPT_ORDER; + struct revmap_entry *rev; + unsigned long npte; - if (htab_orderp) { - order = *htab_orderp; - if (order < PPC_MIN_HPT_ORDER) - order = PPC_MIN_HPT_ORDER; - } + if ((order < PPC_MIN_HPT_ORDER) || (order > PPC_MAX_HPT_ORDER)) + return -EINVAL; - kvm->arch.hpt_cma_alloc = 0; - page = kvm_alloc_hpt(1ul << (order - PAGE_SHIFT)); + page = kvm_alloc_hpt_cma(1ul << (order - PAGE_SHIFT)); if (page) { hpt = (unsigned long)pfn_to_kaddr(page_to_pfn(page)); memset((void *)hpt, 0, (1ul << order)); - kvm->arch.hpt_cma_alloc = 1; + cma = 1; } - /* Lastly try successively smaller sizes from the page allocator */ - /* Only do this if userspace didn't specify a size via ioctl */ - while (!hpt && order > PPC_MIN_HPT_ORDER && !htab_orderp) { - hpt = __get_free_pages(GFP_KERNEL|__GFP_ZERO|__GFP_REPEAT| - __GFP_NOWARN, order - PAGE_SHIFT); - if (!hpt) - --order; - } + if (!hpt) + hpt = __get_free_pages(GFP_KERNEL|__GFP_ZERO|__GFP_REPEAT + |__GFP_NOWARN, order - PAGE_SHIFT); if (!hpt) return -ENOMEM; - kvm->arch.hpt_virt = hpt; - kvm->arch.hpt_order = order; /* HPTEs are 2**4 bytes long */ - kvm->arch.hpt_npte = 1ul << (order - 4); - /* 128 (2**7) bytes in each HPTEG */ - kvm->arch.hpt_mask = (1ul << (order - 7)) - 1; - - atomic64_set(&kvm->arch.mmio_update, 0); + npte = 1ul << (order - 4); /* Allocate reverse map array */ - rev = vmalloc(sizeof(struct revmap_entry) * kvm->arch.hpt_npte); + rev = vmalloc(sizeof(struct revmap_entry) * npte); if (!rev) { - pr_err("kvmppc_alloc_hpt: Couldn't alloc reverse map array\n"); - goto out_freehpt; + pr_err("kvmppc_allocate_hpt: Couldn't alloc reverse map array\n"); + if (cma) + kvm_free_hpt_cma(page, 1 << (order - PAGE_SHIFT)); + else + free_pages(hpt, order - PAGE_SHIFT); + return -ENOMEM; } - kvm->arch.revmap = rev; - kvm->arch.sdr1 = __pa(hpt) | (order - 18); - pr_info("KVM guest htab at %lx (order %ld), LPID %x\n", - hpt, order, kvm->arch.lpid); + info->order = order; + info->virt = hpt; + info->cma = cma; + info->rev = rev; - if (htab_orderp) - *htab_orderp = order; return 0; +} - out_freehpt: - if (kvm->arch.hpt_cma_alloc) - kvm_release_hpt(page, 1 << (order - PAGE_SHIFT)); - else - free_pages(hpt, order - PAGE_SHIFT); - return -ENOMEM; +void kvmppc_set_hpt(struct kvm *kvm, struct kvm_hpt_info *info) +{ + atomic64_set(&kvm->arch.mmio_update, 0); + kvm->arch.hpt = *info; + kvm->arch.sdr1 = __pa(info->virt) | (info->order - 18); + + pr_debug("KVM guest htab at %lx (order %ld), LPID %x\n", + info->virt, (long)info->order, kvm->arch.lpid); } -long kvmppc_alloc_reset_hpt(struct kvm *kvm, u32 *htab_orderp) +long kvmppc_alloc_reset_hpt(struct kvm *kvm, int order) { long err = -EBUSY; - long order; + struct kvm_hpt_info info; if (kvm_is_radix(kvm)) return -EINVAL; @@ -132,36 +149,44 @@ long kvmppc_alloc_reset_hpt(struct kvm *kvm, u32 *htab_orderp) goto out; } } - if (kvm->arch.hpt_virt) { - order = kvm->arch.hpt_order; + if (kvm->arch.hpt.order == order) { + /* We already have a suitable HPT */ + /* Set the entire HPT to 0, i.e. invalid HPTEs */ - memset((void *)kvm->arch.hpt_virt, 0, 1ul << order); + memset((void *)kvm->arch.hpt.virt, 0, 1ul << order); /* * Reset all the reverse-mapping chains for all memslots */ kvmppc_rmap_reset(kvm); /* Ensure that each vcpu will flush its TLB on next entry. */ cpumask_setall(&kvm->arch.need_tlb_flush); - *htab_orderp = order; err = 0; - } else { - err = kvmppc_alloc_hpt(kvm, htab_orderp); - order = *htab_orderp; + goto out; } - out: + + if (kvm->arch.hpt.virt) + kvmppc_free_hpt(&kvm->arch.hpt); + + err = kvmppc_allocate_hpt(&info, order); + if (err < 0) + goto out; + kvmppc_set_hpt(kvm, &info); + +out: mutex_unlock(&kvm->lock); return err; } -void kvmppc_free_hpt(struct kvm *kvm) +void kvmppc_free_hpt(struct kvm_hpt_info *info) { - vfree(kvm->arch.revmap); - if (kvm->arch.hpt_cma_alloc) - kvm_release_hpt(virt_to_page(kvm->arch.hpt_virt), - 1 << (kvm->arch.hpt_order - PAGE_SHIFT)); - else if (kvm->arch.hpt_virt) - free_pages(kvm->arch.hpt_virt, - kvm->arch.hpt_order - PAGE_SHIFT); + vfree(info->rev); + if (info->cma) + kvm_free_hpt_cma(virt_to_page(info->virt), + 1 << (info->order - PAGE_SHIFT)); + else if (info->virt) + free_pages(info->virt, info->order - PAGE_SHIFT); + info->virt = 0; + info->order = 0; } /* Bits in first HPTE dword for pagesize 4k, 64k or 16M */ @@ -196,8 +221,8 @@ void kvmppc_map_vrma(struct kvm_vcpu *vcpu, struct kvm_memory_slot *memslot, if (npages > 1ul << (40 - porder)) npages = 1ul << (40 - porder); /* Can't use more than 1 HPTE per HPTEG */ - if (npages > kvm->arch.hpt_mask + 1) - npages = kvm->arch.hpt_mask + 1; + if (npages > kvmppc_hpt_mask(&kvm->arch.hpt) + 1) + npages = kvmppc_hpt_mask(&kvm->arch.hpt) + 1; hp0 = HPTE_V_1TB_SEG | (VRMA_VSID << (40 - 16)) | HPTE_V_BOLTED | hpte0_pgsize_encoding(psize); @@ -207,7 +232,8 @@ void kvmppc_map_vrma(struct kvm_vcpu *vcpu, struct kvm_memory_slot *memslot, for (i = 0; i < npages; ++i) { addr = i << porder; /* can't use hpt_hash since va > 64 bits */ - hash = (i ^ (VRMA_VSID ^ (VRMA_VSID << 25))) & kvm->arch.hpt_mask; + hash = (i ^ (VRMA_VSID ^ (VRMA_VSID << 25))) + & kvmppc_hpt_mask(&kvm->arch.hpt); /* * We assume that the hash table is empty and no * vcpus are using it at this stage. Since we create @@ -340,11 +366,11 @@ static int kvmppc_mmu_book3s_64_hv_xlate(struct kvm_vcpu *vcpu, gva_t eaddr, preempt_enable(); return -ENOENT; } - hptep = (__be64 *)(kvm->arch.hpt_virt + (index << 4)); + hptep = (__be64 *)(kvm->arch.hpt.virt + (index << 4)); v = orig_v = be64_to_cpu(hptep[0]) & ~HPTE_V_HVLOCK; if (cpu_has_feature(CPU_FTR_ARCH_300)) v = hpte_new_to_old_v(v, be64_to_cpu(hptep[1])); - gr = kvm->arch.revmap[index].guest_rpte; + gr = kvm->arch.hpt.rev[index].guest_rpte; unlock_hpte(hptep, orig_v); preempt_enable(); @@ -485,8 +511,8 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu, } } index = vcpu->arch.pgfault_index; - hptep = (__be64 *)(kvm->arch.hpt_virt + (index << 4)); - rev = &kvm->arch.revmap[index]; + hptep = (__be64 *)(kvm->arch.hpt.virt + (index << 4)); + rev = &kvm->arch.hpt.rev[index]; preempt_disable(); while (!try_lock_hpte(hptep, HPTE_V_HVLOCK)) cpu_relax(); @@ -745,13 +771,53 @@ static int kvm_handle_hva(struct kvm *kvm, unsigned long hva, return kvm_handle_hva_range(kvm, hva, hva + 1, handler); } +/* Must be called with both HPTE and rmap locked */ +static void kvmppc_unmap_hpte(struct kvm *kvm, unsigned long i, + unsigned long *rmapp, unsigned long gfn) +{ + __be64 *hptep = (__be64 *) (kvm->arch.hpt.virt + (i << 4)); + struct revmap_entry *rev = kvm->arch.hpt.rev; + unsigned long j, h; + unsigned long ptel, psize, rcbits; + + j = rev[i].forw; + if (j == i) { + /* chain is now empty */ + *rmapp &= ~(KVMPPC_RMAP_PRESENT | KVMPPC_RMAP_INDEX); + } else { + /* remove i from chain */ + h = rev[i].back; + rev[h].forw = j; + rev[j].back = h; + rev[i].forw = rev[i].back = i; + *rmapp = (*rmapp & ~KVMPPC_RMAP_INDEX) | j; + } + + /* Now check and modify the HPTE */ + ptel = rev[i].guest_rpte; + psize = hpte_page_size(be64_to_cpu(hptep[0]), ptel); + if ((be64_to_cpu(hptep[0]) & HPTE_V_VALID) && + hpte_rpn(ptel, psize) == gfn) { + hptep[0] |= cpu_to_be64(HPTE_V_ABSENT); + kvmppc_invalidate_hpte(kvm, hptep, i); + hptep[1] &= ~cpu_to_be64(HPTE_R_KEY_HI | HPTE_R_KEY_LO); + /* Harvest R and C */ + rcbits = be64_to_cpu(hptep[1]) & (HPTE_R_R | HPTE_R_C); + *rmapp |= rcbits << KVMPPC_RMAP_RC_SHIFT; + if (rcbits & HPTE_R_C) + kvmppc_update_rmap_change(rmapp, psize); + if (rcbits & ~rev[i].guest_rpte) { + rev[i].guest_rpte = ptel | rcbits; + note_hpte_modification(kvm, &rev[i]); + } + } +} + static int kvm_unmap_rmapp(struct kvm *kvm, struct kvm_memory_slot *memslot, unsigned long gfn) { - struct revmap_entry *rev = kvm->arch.revmap; - unsigned long h, i, j; + unsigned long i; __be64 *hptep; - unsigned long ptel, psize, rcbits; unsigned long *rmapp; rmapp = &memslot->arch.rmap[gfn - memslot->base_gfn]; @@ -768,7 +834,7 @@ static int kvm_unmap_rmapp(struct kvm *kvm, struct kvm_memory_slot *memslot, * rmap chain lock. */ i = *rmapp & KVMPPC_RMAP_INDEX; - hptep = (__be64 *) (kvm->arch.hpt_virt + (i << 4)); + hptep = (__be64 *) (kvm->arch.hpt.virt + (i << 4)); if (!try_lock_hpte(hptep, HPTE_V_HVLOCK)) { /* unlock rmap before spinning on the HPTE lock */ unlock_rmap(rmapp); @@ -776,37 +842,8 @@ static int kvm_unmap_rmapp(struct kvm *kvm, struct kvm_memory_slot *memslot, cpu_relax(); continue; } - j = rev[i].forw; - if (j == i) { - /* chain is now empty */ - *rmapp &= ~(KVMPPC_RMAP_PRESENT | KVMPPC_RMAP_INDEX); - } else { - /* remove i from chain */ - h = rev[i].back; - rev[h].forw = j; - rev[j].back = h; - rev[i].forw = rev[i].back = i; - *rmapp = (*rmapp & ~KVMPPC_RMAP_INDEX) | j; - } - /* Now check and modify the HPTE */ - ptel = rev[i].guest_rpte; - psize = hpte_page_size(be64_to_cpu(hptep[0]), ptel); - if ((be64_to_cpu(hptep[0]) & HPTE_V_VALID) && - hpte_rpn(ptel, psize) == gfn) { - hptep[0] |= cpu_to_be64(HPTE_V_ABSENT); - kvmppc_invalidate_hpte(kvm, hptep, i); - hptep[1] &= ~cpu_to_be64(HPTE_R_KEY_HI | HPTE_R_KEY_LO); - /* Harvest R and C */ - rcbits = be64_to_cpu(hptep[1]) & (HPTE_R_R | HPTE_R_C); - *rmapp |= rcbits << KVMPPC_RMAP_RC_SHIFT; - if (rcbits & HPTE_R_C) - kvmppc_update_rmap_change(rmapp, psize); - if (rcbits & ~rev[i].guest_rpte) { - rev[i].guest_rpte = ptel | rcbits; - note_hpte_modification(kvm, &rev[i]); - } - } + kvmppc_unmap_hpte(kvm, i, rmapp, gfn); unlock_rmap(rmapp); __unlock_hpte(hptep, be64_to_cpu(hptep[0])); } @@ -860,7 +897,7 @@ void kvmppc_core_flush_memslot_hv(struct kvm *kvm, static int kvm_age_rmapp(struct kvm *kvm, struct kvm_memory_slot *memslot, unsigned long gfn) { - struct revmap_entry *rev = kvm->arch.revmap; + struct revmap_entry *rev = kvm->arch.hpt.rev; unsigned long head, i, j; __be64 *hptep; int ret = 0; @@ -880,7 +917,7 @@ static int kvm_age_rmapp(struct kvm *kvm, struct kvm_memory_slot *memslot, i = head = *rmapp & KVMPPC_RMAP_INDEX; do { - hptep = (__be64 *) (kvm->arch.hpt_virt + (i << 4)); + hptep = (__be64 *) (kvm->arch.hpt.virt + (i << 4)); j = rev[i].forw; /* If this HPTE isn't referenced, ignore it */ @@ -923,7 +960,7 @@ int kvm_age_hva_hv(struct kvm *kvm, unsigned long start, unsigned long end) static int kvm_test_age_rmapp(struct kvm *kvm, struct kvm_memory_slot *memslot, unsigned long gfn) { - struct revmap_entry *rev = kvm->arch.revmap; + struct revmap_entry *rev = kvm->arch.hpt.rev; unsigned long head, i, j; unsigned long *hp; int ret = 1; @@ -940,7 +977,7 @@ static int kvm_test_age_rmapp(struct kvm *kvm, struct kvm_memory_slot *memslot, if (*rmapp & KVMPPC_RMAP_PRESENT) { i = head = *rmapp & KVMPPC_RMAP_INDEX; do { - hp = (unsigned long *)(kvm->arch.hpt_virt + (i << 4)); + hp = (unsigned long *)(kvm->arch.hpt.virt + (i << 4)); j = rev[i].forw; if (be64_to_cpu(hp[1]) & HPTE_R_R) goto out; @@ -980,7 +1017,7 @@ static int vcpus_running(struct kvm *kvm) */ static int kvm_test_clear_dirty_npages(struct kvm *kvm, unsigned long *rmapp) { - struct revmap_entry *rev = kvm->arch.revmap; + struct revmap_entry *rev = kvm->arch.hpt.rev; unsigned long head, i, j; unsigned long n; unsigned long v, r; @@ -1005,7 +1042,7 @@ static int kvm_test_clear_dirty_npages(struct kvm *kvm, unsigned long *rmapp) i = head = *rmapp & KVMPPC_RMAP_INDEX; do { unsigned long hptep1; - hptep = (__be64 *) (kvm->arch.hpt_virt + (i << 4)); + hptep = (__be64 *) (kvm->arch.hpt.virt + (i << 4)); j = rev[i].forw; /* @@ -1172,6 +1209,363 @@ void kvmppc_unpin_guest_page(struct kvm *kvm, void *va, unsigned long gpa, } /* + * HPT resizing + */ +static int resize_hpt_allocate(struct kvm_resize_hpt *resize) +{ + int rc; + + rc = kvmppc_allocate_hpt(&resize->hpt, resize->order); + if (rc < 0) + return rc; + + resize_hpt_debug(resize, "resize_hpt_allocate(): HPT @ 0x%lx\n", + resize->hpt.virt); + + return 0; +} + +static unsigned long resize_hpt_rehash_hpte(struct kvm_resize_hpt *resize, + unsigned long idx) +{ + struct kvm *kvm = resize->kvm; + struct kvm_hpt_info *old = &kvm->arch.hpt; + struct kvm_hpt_info *new = &resize->hpt; + unsigned long old_hash_mask = (1ULL << (old->order - 7)) - 1; + unsigned long new_hash_mask = (1ULL << (new->order - 7)) - 1; + __be64 *hptep, *new_hptep; + unsigned long vpte, rpte, guest_rpte; + int ret; + struct revmap_entry *rev; + unsigned long apsize, psize, avpn, pteg, hash; + unsigned long new_idx, new_pteg, replace_vpte; + + hptep = (__be64 *)(old->virt + (idx << 4)); + + /* Guest is stopped, so new HPTEs can't be added or faulted + * in, only unmapped or altered by host actions. So, it's + * safe to check this before we take the HPTE lock */ + vpte = be64_to_cpu(hptep[0]); + if (!(vpte & HPTE_V_VALID) && !(vpte & HPTE_V_ABSENT)) + return 0; /* nothing to do */ + + while (!try_lock_hpte(hptep, HPTE_V_HVLOCK)) + cpu_relax(); + + vpte = be64_to_cpu(hptep[0]); + + ret = 0; + if (!(vpte & HPTE_V_VALID) && !(vpte & HPTE_V_ABSENT)) + /* Nothing to do */ + goto out; + + /* Unmap */ + rev = &old->rev[idx]; + guest_rpte = rev->guest_rpte; + + ret = -EIO; + apsize = hpte_page_size(vpte, guest_rpte); + if (!apsize) + goto out; + + if (vpte & HPTE_V_VALID) { + unsigned long gfn = hpte_rpn(guest_rpte, apsize); + int srcu_idx = srcu_read_lock(&kvm->srcu); + struct kvm_memory_slot *memslot = + __gfn_to_memslot(kvm_memslots(kvm), gfn); + + if (memslot) { + unsigned long *rmapp; + rmapp = &memslot->arch.rmap[gfn - memslot->base_gfn]; + + lock_rmap(rmapp); + kvmppc_unmap_hpte(kvm, idx, rmapp, gfn); + unlock_rmap(rmapp); + } + + srcu_read_unlock(&kvm->srcu, srcu_idx); + } + + /* Reload PTE after unmap */ + vpte = be64_to_cpu(hptep[0]); + + BUG_ON(vpte & HPTE_V_VALID); + BUG_ON(!(vpte & HPTE_V_ABSENT)); + + ret = 0; + if (!(vpte & HPTE_V_BOLTED)) + goto out; + + rpte = be64_to_cpu(hptep[1]); + psize = hpte_base_page_size(vpte, rpte); + avpn = HPTE_V_AVPN_VAL(vpte) & ~((psize - 1) >> 23); + pteg = idx / HPTES_PER_GROUP; + if (vpte & HPTE_V_SECONDARY) + pteg = ~pteg; + + if (!(vpte & HPTE_V_1TB_SEG)) { + unsigned long offset, vsid; + + /* We only have 28 - 23 bits of offset in avpn */ + offset = (avpn & 0x1f) << 23; + vsid = avpn >> 5; + /* We can find more bits from the pteg value */ + if (psize < (1ULL << 23)) + offset |= ((vsid ^ pteg) & old_hash_mask) * psize; + + hash = vsid ^ (offset / psize); + } else { + unsigned long offset, vsid; + + /* We only have 40 - 23 bits of seg_off in avpn */ + offset = (avpn & 0x1ffff) << 23; + vsid = avpn >> 17; + if (psize < (1ULL << 23)) + offset |= ((vsid ^ (vsid << 25) ^ pteg) & old_hash_mask) * psize; + + hash = vsid ^ (vsid << 25) ^ (offset / psize); + } + + new_pteg = hash & new_hash_mask; + if (vpte & HPTE_V_SECONDARY) { + BUG_ON(~pteg != (hash & old_hash_mask)); + new_pteg = ~new_pteg; + } else { + BUG_ON(pteg != (hash & old_hash_mask)); + } + + new_idx = new_pteg * HPTES_PER_GROUP + (idx % HPTES_PER_GROUP); + new_hptep = (__be64 *)(new->virt + (new_idx << 4)); + + replace_vpte = be64_to_cpu(new_hptep[0]); + + if (replace_vpte & (HPTE_V_VALID | HPTE_V_ABSENT)) { + BUG_ON(new->order >= old->order); + + if (replace_vpte & HPTE_V_BOLTED) { + if (vpte & HPTE_V_BOLTED) + /* Bolted collision, nothing we can do */ + ret = -ENOSPC; + /* Discard the new HPTE */ + goto out; + } + + /* Discard the previous HPTE */ + } + + new_hptep[1] = cpu_to_be64(rpte); + new->rev[new_idx].guest_rpte = guest_rpte; + /* No need for a barrier, since new HPT isn't active */ + new_hptep[0] = cpu_to_be64(vpte); + unlock_hpte(new_hptep, vpte); + +out: + unlock_hpte(hptep, vpte); + return ret; +} + +static int resize_hpt_rehash(struct kvm_resize_hpt *resize) +{ + struct kvm *kvm = resize->kvm; + unsigned long i; + int rc; + + /* + * resize_hpt_rehash_hpte() doesn't handle the new-format HPTEs + * that POWER9 uses, and could well hit a BUG_ON on POWER9. + */ + if (cpu_has_feature(CPU_FTR_ARCH_300)) + return -EIO; + for (i = 0; i < kvmppc_hpt_npte(&kvm->arch.hpt); i++) { + rc = resize_hpt_rehash_hpte(resize, i); + if (rc != 0) + return rc; + } + + return 0; +} + +static void resize_hpt_pivot(struct kvm_resize_hpt *resize) +{ + struct kvm *kvm = resize->kvm; + struct kvm_hpt_info hpt_tmp; + + /* Exchange the pending tables in the resize structure with + * the active tables */ + + resize_hpt_debug(resize, "resize_hpt_pivot()\n"); + + spin_lock(&kvm->mmu_lock); + asm volatile("ptesync" : : : "memory"); + + hpt_tmp = kvm->arch.hpt; + kvmppc_set_hpt(kvm, &resize->hpt); + resize->hpt = hpt_tmp; + + spin_unlock(&kvm->mmu_lock); + + synchronize_srcu_expedited(&kvm->srcu); + + resize_hpt_debug(resize, "resize_hpt_pivot() done\n"); +} + +static void resize_hpt_release(struct kvm *kvm, struct kvm_resize_hpt *resize) +{ + BUG_ON(kvm->arch.resize_hpt != resize); + + if (!resize) + return; + + if (resize->hpt.virt) + kvmppc_free_hpt(&resize->hpt); + + kvm->arch.resize_hpt = NULL; + kfree(resize); +} + +static void resize_hpt_prepare_work(struct work_struct *work) +{ + struct kvm_resize_hpt *resize = container_of(work, + struct kvm_resize_hpt, + work); + struct kvm *kvm = resize->kvm; + int err; + + resize_hpt_debug(resize, "resize_hpt_prepare_work(): order = %d\n", + resize->order); + + err = resize_hpt_allocate(resize); + + mutex_lock(&kvm->lock); + + resize->error = err; + resize->prepare_done = true; + + mutex_unlock(&kvm->lock); +} + +long kvm_vm_ioctl_resize_hpt_prepare(struct kvm *kvm, + struct kvm_ppc_resize_hpt *rhpt) +{ + unsigned long flags = rhpt->flags; + unsigned long shift = rhpt->shift; + struct kvm_resize_hpt *resize; + int ret; + + if (flags != 0) + return -EINVAL; + + if (shift && ((shift < 18) || (shift > 46))) + return -EINVAL; + + mutex_lock(&kvm->lock); + + resize = kvm->arch.resize_hpt; + + if (resize) { + if (resize->order == shift) { + /* Suitable resize in progress */ + if (resize->prepare_done) { + ret = resize->error; + if (ret != 0) + resize_hpt_release(kvm, resize); + } else { + ret = 100; /* estimated time in ms */ + } + + goto out; + } + + /* not suitable, cancel it */ + resize_hpt_release(kvm, resize); + } + + ret = 0; + if (!shift) + goto out; /* nothing to do */ + + /* start new resize */ + + resize = kzalloc(sizeof(*resize), GFP_KERNEL); + resize->order = shift; + resize->kvm = kvm; + INIT_WORK(&resize->work, resize_hpt_prepare_work); + kvm->arch.resize_hpt = resize; + + schedule_work(&resize->work); + + ret = 100; /* estimated time in ms */ + +out: + mutex_unlock(&kvm->lock); + return ret; +} + +static void resize_hpt_boot_vcpu(void *opaque) +{ + /* Nothing to do, just force a KVM exit */ +} + +long kvm_vm_ioctl_resize_hpt_commit(struct kvm *kvm, + struct kvm_ppc_resize_hpt *rhpt) +{ + unsigned long flags = rhpt->flags; + unsigned long shift = rhpt->shift; + struct kvm_resize_hpt *resize; + long ret; + + if (flags != 0) + return -EINVAL; + + if (shift && ((shift < 18) || (shift > 46))) + return -EINVAL; + + mutex_lock(&kvm->lock); + + resize = kvm->arch.resize_hpt; + + /* This shouldn't be possible */ + ret = -EIO; + if (WARN_ON(!kvm->arch.hpte_setup_done)) + goto out_no_hpt; + + /* Stop VCPUs from running while we mess with the HPT */ + kvm->arch.hpte_setup_done = 0; + smp_mb(); + + /* Boot all CPUs out of the guest so they re-read + * hpte_setup_done */ + on_each_cpu(resize_hpt_boot_vcpu, NULL, 1); + + ret = -ENXIO; + if (!resize || (resize->order != shift)) + goto out; + + ret = -EBUSY; + if (!resize->prepare_done) + goto out; + + ret = resize->error; + if (ret != 0) + goto out; + + ret = resize_hpt_rehash(resize); + if (ret != 0) + goto out; + + resize_hpt_pivot(resize); + +out: + /* Let VCPUs run again */ + kvm->arch.hpte_setup_done = 1; + smp_mb(); +out_no_hpt: + resize_hpt_release(kvm, resize); + mutex_unlock(&kvm->lock); + return ret; +} + +/* * Functions for reading and writing the hash table via reads and * writes on a file descriptor. * @@ -1311,8 +1705,8 @@ static ssize_t kvm_htab_read(struct file *file, char __user *buf, flags = ctx->flags; i = ctx->index; - hptp = (__be64 *)(kvm->arch.hpt_virt + (i * HPTE_SIZE)); - revp = kvm->arch.revmap + i; + hptp = (__be64 *)(kvm->arch.hpt.virt + (i * HPTE_SIZE)); + revp = kvm->arch.hpt.rev + i; lbuf = (unsigned long __user *)buf; nb = 0; @@ -1327,7 +1721,7 @@ static ssize_t kvm_htab_read(struct file *file, char __user *buf, /* Skip uninteresting entries, i.e. clean on not-first pass */ if (!first_pass) { - while (i < kvm->arch.hpt_npte && + while (i < kvmppc_hpt_npte(&kvm->arch.hpt) && !hpte_dirty(revp, hptp)) { ++i; hptp += 2; @@ -1337,7 +1731,7 @@ static ssize_t kvm_htab_read(struct file *file, char __user *buf, hdr.index = i; /* Grab a series of valid entries */ - while (i < kvm->arch.hpt_npte && + while (i < kvmppc_hpt_npte(&kvm->arch.hpt) && hdr.n_valid < 0xffff && nb + HPTE_SIZE < count && record_hpte(flags, hptp, hpte, revp, 1, first_pass)) { @@ -1353,7 +1747,7 @@ static ssize_t kvm_htab_read(struct file *file, char __user *buf, ++revp; } /* Now skip invalid entries while we can */ - while (i < kvm->arch.hpt_npte && + while (i < kvmppc_hpt_npte(&kvm->arch.hpt) && hdr.n_invalid < 0xffff && record_hpte(flags, hptp, hpte, revp, 0, first_pass)) { /* found an invalid entry */ @@ -1374,7 +1768,7 @@ static ssize_t kvm_htab_read(struct file *file, char __user *buf, } /* Check if we've wrapped around the hash table */ - if (i >= kvm->arch.hpt_npte) { + if (i >= kvmppc_hpt_npte(&kvm->arch.hpt)) { i = 0; ctx->first_pass = 0; break; @@ -1433,11 +1827,11 @@ static ssize_t kvm_htab_write(struct file *file, const char __user *buf, err = -EINVAL; i = hdr.index; - if (i >= kvm->arch.hpt_npte || - i + hdr.n_valid + hdr.n_invalid > kvm->arch.hpt_npte) + if (i >= kvmppc_hpt_npte(&kvm->arch.hpt) || + i + hdr.n_valid + hdr.n_invalid > kvmppc_hpt_npte(&kvm->arch.hpt)) break; - hptp = (__be64 *)(kvm->arch.hpt_virt + (i * HPTE_SIZE)); + hptp = (__be64 *)(kvm->arch.hpt.virt + (i * HPTE_SIZE)); lbuf = (unsigned long __user *)buf; for (j = 0; j < hdr.n_valid; ++j) { __be64 hpte_v; @@ -1624,8 +2018,9 @@ static ssize_t debugfs_htab_read(struct file *file, char __user *buf, kvm = p->kvm; i = p->hpt_index; - hptp = (__be64 *)(kvm->arch.hpt_virt + (i * HPTE_SIZE)); - for (; len != 0 && i < kvm->arch.hpt_npte; ++i, hptp += 2) { + hptp = (__be64 *)(kvm->arch.hpt.virt + (i * HPTE_SIZE)); + for (; len != 0 && i < kvmppc_hpt_npte(&kvm->arch.hpt); + ++i, hptp += 2) { if (!(be64_to_cpu(hptp[0]) & (HPTE_V_VALID | HPTE_V_ABSENT))) continue; @@ -1635,7 +2030,7 @@ static ssize_t debugfs_htab_read(struct file *file, char __user *buf, cpu_relax(); v = be64_to_cpu(hptp[0]) & ~HPTE_V_HVLOCK; hr = be64_to_cpu(hptp[1]); - gr = kvm->arch.revmap[i].guest_rpte; + gr = kvm->arch.hpt.rev[i].guest_rpte; unlock_hpte(hptp, v); preempt_enable(); diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c index c379ff5a4438..ab9d14c0e460 100644 --- a/arch/powerpc/kvm/book3s_64_vio.c +++ b/arch/powerpc/kvm/book3s_64_vio.c @@ -102,9 +102,9 @@ static void release_spapr_tce_table(struct rcu_head *head) kfree(stt); } -static int kvm_spapr_tce_fault(struct vm_area_struct *vma, struct vm_fault *vmf) +static int kvm_spapr_tce_fault(struct vm_fault *vmf) { - struct kvmppc_spapr_tce_table *stt = vma->vm_file->private_data; + struct kvmppc_spapr_tce_table *stt = vmf->vma->vm_file->private_data; struct page *page; if (vmf->pgoff >= kvmppc_tce_pages(stt->size)) @@ -171,6 +171,7 @@ long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm, goto fail; } + ret = -ENOMEM; stt = kzalloc(sizeof(*stt) + npages * sizeof(struct page *), GFP_KERNEL); if (!stt) diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index e4a79679342e..1e107ece4e37 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -182,7 +182,8 @@ static void kvmppc_fast_vcpu_kick_hv(struct kvm_vcpu *vcpu) ++vcpu->stat.halt_wakeup; } - if (kvmppc_ipi_thread(vcpu->arch.thread_cpu)) + cpu = READ_ONCE(vcpu->arch.thread_cpu); + if (cpu >= 0 && kvmppc_ipi_thread(cpu)) return; /* CPU points to the first thread of the core */ @@ -773,12 +774,8 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu) } tvcpu->arch.prodded = 1; smp_mb(); - if (vcpu->arch.ceded) { - if (swait_active(&vcpu->wq)) { - swake_up(&vcpu->wq); - vcpu->stat.halt_wakeup++; - } - } + if (tvcpu->arch.ceded) + kvmppc_fast_vcpu_kick_hv(tvcpu); break; case H_CONFER: target = kvmppc_get_gpr(vcpu, 4); @@ -2665,7 +2662,8 @@ 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) + if (vcpu->arch.pending_exceptions || !vcpu->arch.ceded || + vcpu->arch.prodded) return 1; } @@ -2851,7 +2849,7 @@ 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) + if (!v->arch.pending_exceptions && !v->arch.prodded) n_ceded += v->arch.ceded; else v->arch.ceded = 0; @@ -3199,12 +3197,23 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu) goto out; /* another vcpu beat us to it */ /* Allocate hashed page table (if not done already) and reset it */ - if (!kvm->arch.hpt_virt) { - err = kvmppc_alloc_hpt(kvm, NULL); - if (err) { + if (!kvm->arch.hpt.virt) { + int order = KVM_DEFAULT_HPT_ORDER; + struct kvm_hpt_info info; + + err = kvmppc_allocate_hpt(&info, order); + /* If we get here, it means userspace didn't specify a + * size explicitly. So, try successively smaller + * sizes if the default failed. */ + while ((err == -ENOMEM) && --order >= PPC_MIN_HPT_ORDER) + err = kvmppc_allocate_hpt(&info, order); + + if (err < 0) { pr_err("KVM: Couldn't alloc HPT\n"); goto out; } + + kvmppc_set_hpt(kvm, &info); } /* Look up the memslot for guest physical address 0 */ @@ -3413,6 +3422,9 @@ static int kvmppc_core_init_vm_hv(struct kvm *kvm) kvm->arch.lpcr = lpcr; + /* Initialization for future HPT resizes */ + kvm->arch.resize_hpt = NULL; + /* * Work out how many sets the TLB has, for the use of * the TLB invalidation loop in book3s_hv_rmhandlers.S. @@ -3469,7 +3481,7 @@ static void kvmppc_core_destroy_vm_hv(struct kvm *kvm) if (kvm_is_radix(kvm)) kvmppc_free_radix(kvm); else - kvmppc_free_hpt(kvm); + kvmppc_free_hpt(&kvm->arch.hpt); kvmppc_free_pimap(kvm); } @@ -3695,12 +3707,9 @@ static long kvm_arch_vm_ioctl_hv(struct file *filp, r = -EFAULT; if (get_user(htab_order, (u32 __user *)argp)) break; - r = kvmppc_alloc_reset_hpt(kvm, &htab_order); + r = kvmppc_alloc_reset_hpt(kvm, htab_order); if (r) break; - r = -EFAULT; - if (put_user(htab_order, (u32 __user *)argp)) - break; r = 0; break; } @@ -3715,6 +3724,28 @@ static long kvm_arch_vm_ioctl_hv(struct file *filp, break; } + case KVM_PPC_RESIZE_HPT_PREPARE: { + struct kvm_ppc_resize_hpt rhpt; + + r = -EFAULT; + if (copy_from_user(&rhpt, argp, sizeof(rhpt))) + break; + + r = kvm_vm_ioctl_resize_hpt_prepare(kvm, &rhpt); + break; + } + + case KVM_PPC_RESIZE_HPT_COMMIT: { + struct kvm_ppc_resize_hpt rhpt; + + r = -EFAULT; + if (copy_from_user(&rhpt, argp, sizeof(rhpt))) + break; + + r = kvm_vm_ioctl_resize_hpt_commit(kvm, &rhpt); + break; + } + default: r = -ENOTTY; } diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c index 2f69fbc19bb0..4d6c64b3041c 100644 --- a/arch/powerpc/kvm/book3s_hv_builtin.c +++ b/arch/powerpc/kvm/book3s_hv_builtin.c @@ -52,19 +52,20 @@ static int __init early_parse_kvm_cma_resv(char *p) } early_param("kvm_cma_resv_ratio", early_parse_kvm_cma_resv); -struct page *kvm_alloc_hpt(unsigned long nr_pages) +struct page *kvm_alloc_hpt_cma(unsigned long nr_pages) { VM_BUG_ON(order_base_2(nr_pages) < KVM_CMA_CHUNK_ORDER - PAGE_SHIFT); - return cma_alloc(kvm_cma, nr_pages, order_base_2(HPT_ALIGN_PAGES)); + return cma_alloc(kvm_cma, nr_pages, order_base_2(HPT_ALIGN_PAGES), + GFP_KERNEL); } -EXPORT_SYMBOL_GPL(kvm_alloc_hpt); +EXPORT_SYMBOL_GPL(kvm_alloc_hpt_cma); -void kvm_release_hpt(struct page *page, unsigned long nr_pages) +void kvm_free_hpt_cma(struct page *page, unsigned long nr_pages) { cma_release(kvm_cma, page, nr_pages); } -EXPORT_SYMBOL_GPL(kvm_release_hpt); +EXPORT_SYMBOL_GPL(kvm_free_hpt_cma); /** * kvm_cma_reserve() - reserve area for kvm hash pagetable diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c index b095afcd4309..6fca970373ee 100644 --- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c +++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c @@ -86,10 +86,10 @@ void kvmppc_add_revmap_chain(struct kvm *kvm, struct revmap_entry *rev, if (*rmap & KVMPPC_RMAP_PRESENT) { i = *rmap & KVMPPC_RMAP_INDEX; - head = &kvm->arch.revmap[i]; + head = &kvm->arch.hpt.rev[i]; if (realmode) head = real_vmalloc_addr(head); - tail = &kvm->arch.revmap[head->back]; + tail = &kvm->arch.hpt.rev[head->back]; if (realmode) tail = real_vmalloc_addr(tail); rev->forw = i; @@ -154,8 +154,8 @@ static void remove_revmap_chain(struct kvm *kvm, long pte_index, lock_rmap(rmap); head = *rmap & KVMPPC_RMAP_INDEX; - next = real_vmalloc_addr(&kvm->arch.revmap[rev->forw]); - prev = real_vmalloc_addr(&kvm->arch.revmap[rev->back]); + next = real_vmalloc_addr(&kvm->arch.hpt.rev[rev->forw]); + prev = real_vmalloc_addr(&kvm->arch.hpt.rev[rev->back]); next->back = rev->back; prev->forw = rev->forw; if (head == pte_index) { @@ -292,11 +292,11 @@ long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags, /* Find and lock the HPTEG slot to use */ do_insert: - if (pte_index >= kvm->arch.hpt_npte) + if (pte_index >= kvmppc_hpt_npte(&kvm->arch.hpt)) return H_PARAMETER; if (likely((flags & H_EXACT) == 0)) { pte_index &= ~7UL; - hpte = (__be64 *)(kvm->arch.hpt_virt + (pte_index << 4)); + hpte = (__be64 *)(kvm->arch.hpt.virt + (pte_index << 4)); for (i = 0; i < 8; ++i) { if ((be64_to_cpu(*hpte) & HPTE_V_VALID) == 0 && try_lock_hpte(hpte, HPTE_V_HVLOCK | HPTE_V_VALID | @@ -327,7 +327,7 @@ long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags, } pte_index += i; } else { - hpte = (__be64 *)(kvm->arch.hpt_virt + (pte_index << 4)); + hpte = (__be64 *)(kvm->arch.hpt.virt + (pte_index << 4)); if (!try_lock_hpte(hpte, HPTE_V_HVLOCK | HPTE_V_VALID | HPTE_V_ABSENT)) { /* Lock the slot and check again */ @@ -344,7 +344,7 @@ long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags, } /* Save away the guest's idea of the second HPTE dword */ - rev = &kvm->arch.revmap[pte_index]; + rev = &kvm->arch.hpt.rev[pte_index]; if (realmode) rev = real_vmalloc_addr(rev); if (rev) { @@ -469,9 +469,9 @@ long kvmppc_do_h_remove(struct kvm *kvm, unsigned long flags, if (kvm_is_radix(kvm)) return H_FUNCTION; - if (pte_index >= kvm->arch.hpt_npte) + if (pte_index >= kvmppc_hpt_npte(&kvm->arch.hpt)) return H_PARAMETER; - hpte = (__be64 *)(kvm->arch.hpt_virt + (pte_index << 4)); + hpte = (__be64 *)(kvm->arch.hpt.virt + (pte_index << 4)); while (!try_lock_hpte(hpte, HPTE_V_HVLOCK)) cpu_relax(); pte = orig_pte = be64_to_cpu(hpte[0]); @@ -487,7 +487,7 @@ long kvmppc_do_h_remove(struct kvm *kvm, unsigned long flags, return H_NOT_FOUND; } - rev = real_vmalloc_addr(&kvm->arch.revmap[pte_index]); + rev = real_vmalloc_addr(&kvm->arch.hpt.rev[pte_index]); v = pte & ~HPTE_V_HVLOCK; if (v & HPTE_V_VALID) { hpte[0] &= ~cpu_to_be64(HPTE_V_VALID); @@ -557,13 +557,13 @@ long kvmppc_h_bulk_remove(struct kvm_vcpu *vcpu) break; } if (req != 1 || flags == 3 || - pte_index >= kvm->arch.hpt_npte) { + pte_index >= kvmppc_hpt_npte(&kvm->arch.hpt)) { /* parameter error */ args[j] = ((0xa0 | flags) << 56) + pte_index; ret = H_PARAMETER; break; } - hp = (__be64 *) (kvm->arch.hpt_virt + (pte_index << 4)); + hp = (__be64 *) (kvm->arch.hpt.virt + (pte_index << 4)); /* to avoid deadlock, don't spin except for first */ if (!try_lock_hpte(hp, HPTE_V_HVLOCK)) { if (n) @@ -600,7 +600,7 @@ long kvmppc_h_bulk_remove(struct kvm_vcpu *vcpu) } args[j] = ((0x80 | flags) << 56) + pte_index; - rev = real_vmalloc_addr(&kvm->arch.revmap[pte_index]); + rev = real_vmalloc_addr(&kvm->arch.hpt.rev[pte_index]); note_hpte_modification(kvm, rev); if (!(hp0 & HPTE_V_VALID)) { @@ -657,10 +657,10 @@ long kvmppc_h_protect(struct kvm_vcpu *vcpu, unsigned long flags, if (kvm_is_radix(kvm)) return H_FUNCTION; - if (pte_index >= kvm->arch.hpt_npte) + if (pte_index >= kvmppc_hpt_npte(&kvm->arch.hpt)) return H_PARAMETER; - hpte = (__be64 *)(kvm->arch.hpt_virt + (pte_index << 4)); + hpte = (__be64 *)(kvm->arch.hpt.virt + (pte_index << 4)); while (!try_lock_hpte(hpte, HPTE_V_HVLOCK)) cpu_relax(); v = pte_v = be64_to_cpu(hpte[0]); @@ -680,7 +680,7 @@ long kvmppc_h_protect(struct kvm_vcpu *vcpu, unsigned long flags, /* Update guest view of 2nd HPTE dword */ mask = HPTE_R_PP0 | HPTE_R_PP | HPTE_R_N | HPTE_R_KEY_HI | HPTE_R_KEY_LO; - rev = real_vmalloc_addr(&kvm->arch.revmap[pte_index]); + rev = real_vmalloc_addr(&kvm->arch.hpt.rev[pte_index]); if (rev) { r = (rev->guest_rpte & ~mask) | bits; rev->guest_rpte = r; @@ -728,15 +728,15 @@ long kvmppc_h_read(struct kvm_vcpu *vcpu, unsigned long flags, if (kvm_is_radix(kvm)) return H_FUNCTION; - if (pte_index >= kvm->arch.hpt_npte) + if (pte_index >= kvmppc_hpt_npte(&kvm->arch.hpt)) return H_PARAMETER; if (flags & H_READ_4) { pte_index &= ~3; n = 4; } - rev = real_vmalloc_addr(&kvm->arch.revmap[pte_index]); + rev = real_vmalloc_addr(&kvm->arch.hpt.rev[pte_index]); for (i = 0; i < n; ++i, ++pte_index) { - hpte = (__be64 *)(kvm->arch.hpt_virt + (pte_index << 4)); + hpte = (__be64 *)(kvm->arch.hpt.virt + (pte_index << 4)); v = be64_to_cpu(hpte[0]) & ~HPTE_V_HVLOCK; r = be64_to_cpu(hpte[1]); if (cpu_has_feature(CPU_FTR_ARCH_300)) { @@ -769,11 +769,11 @@ long kvmppc_h_clear_ref(struct kvm_vcpu *vcpu, unsigned long flags, if (kvm_is_radix(kvm)) return H_FUNCTION; - if (pte_index >= kvm->arch.hpt_npte) + if (pte_index >= kvmppc_hpt_npte(&kvm->arch.hpt)) return H_PARAMETER; - rev = real_vmalloc_addr(&kvm->arch.revmap[pte_index]); - hpte = (__be64 *)(kvm->arch.hpt_virt + (pte_index << 4)); + rev = real_vmalloc_addr(&kvm->arch.hpt.rev[pte_index]); + hpte = (__be64 *)(kvm->arch.hpt.virt + (pte_index << 4)); while (!try_lock_hpte(hpte, HPTE_V_HVLOCK)) cpu_relax(); v = be64_to_cpu(hpte[0]); @@ -817,11 +817,11 @@ long kvmppc_h_clear_mod(struct kvm_vcpu *vcpu, unsigned long flags, if (kvm_is_radix(kvm)) return H_FUNCTION; - if (pte_index >= kvm->arch.hpt_npte) + if (pte_index >= kvmppc_hpt_npte(&kvm->arch.hpt)) return H_PARAMETER; - rev = real_vmalloc_addr(&kvm->arch.revmap[pte_index]); - hpte = (__be64 *)(kvm->arch.hpt_virt + (pte_index << 4)); + rev = real_vmalloc_addr(&kvm->arch.hpt.rev[pte_index]); + hpte = (__be64 *)(kvm->arch.hpt.virt + (pte_index << 4)); while (!try_lock_hpte(hpte, HPTE_V_HVLOCK)) cpu_relax(); v = be64_to_cpu(hpte[0]); @@ -970,7 +970,7 @@ long kvmppc_hv_find_lock_hpte(struct kvm *kvm, gva_t eaddr, unsigned long slb_v, somask = (1UL << 28) - 1; vsid = (slb_v & ~SLB_VSID_B) >> SLB_VSID_SHIFT; } - hash = (vsid ^ ((eaddr & somask) >> pshift)) & kvm->arch.hpt_mask; + hash = (vsid ^ ((eaddr & somask) >> pshift)) & kvmppc_hpt_mask(&kvm->arch.hpt); avpn = slb_v & ~(somask >> 16); /* also includes B */ avpn |= (eaddr & somask) >> 16; @@ -981,7 +981,7 @@ long kvmppc_hv_find_lock_hpte(struct kvm *kvm, gva_t eaddr, unsigned long slb_v, val |= avpn; for (;;) { - hpte = (__be64 *)(kvm->arch.hpt_virt + (hash << 7)); + hpte = (__be64 *)(kvm->arch.hpt.virt + (hash << 7)); for (i = 0; i < 16; i += 2) { /* Read the PTE racily */ @@ -1017,7 +1017,7 @@ long kvmppc_hv_find_lock_hpte(struct kvm *kvm, gva_t eaddr, unsigned long slb_v, if (val & HPTE_V_SECONDARY) break; val |= HPTE_V_SECONDARY; - hash = hash ^ kvm->arch.hpt_mask; + hash = hash ^ kvmppc_hpt_mask(&kvm->arch.hpt); } return -1; } @@ -1066,14 +1066,14 @@ long kvmppc_hpte_hv_fault(struct kvm_vcpu *vcpu, unsigned long addr, return status; /* there really was no HPTE */ return 0; /* for prot fault, HPTE disappeared */ } - hpte = (__be64 *)(kvm->arch.hpt_virt + (index << 4)); + hpte = (__be64 *)(kvm->arch.hpt.virt + (index << 4)); v = orig_v = be64_to_cpu(hpte[0]) & ~HPTE_V_HVLOCK; r = be64_to_cpu(hpte[1]); if (cpu_has_feature(CPU_FTR_ARCH_300)) { v = hpte_new_to_old_v(v, r); r = hpte_new_to_old_r(r); } - rev = real_vmalloc_addr(&kvm->arch.revmap[index]); + rev = real_vmalloc_addr(&kvm->arch.hpt.rev[index]); gr = rev->guest_rpte; unlock_hpte(hpte, orig_v); diff --git a/arch/powerpc/kvm/book3s_hv_rm_xics.c b/arch/powerpc/kvm/book3s_hv_rm_xics.c index 29f43ed6d5eb..e78542d99cd6 100644 --- a/arch/powerpc/kvm/book3s_hv_rm_xics.c +++ b/arch/powerpc/kvm/book3s_hv_rm_xics.c @@ -35,7 +35,7 @@ int kvm_irq_bypass = 1; EXPORT_SYMBOL(kvm_irq_bypass); static void icp_rm_deliver_irq(struct kvmppc_xics *xics, struct kvmppc_icp *icp, - u32 new_irq); + u32 new_irq, bool check_resend); static int xics_opal_set_server(unsigned int hw_irq, int server_cpu); /* -- ICS routines -- */ @@ -44,20 +44,12 @@ static void ics_rm_check_resend(struct kvmppc_xics *xics, { int i; - arch_spin_lock(&ics->lock); - for (i = 0; i < KVMPPC_XICS_IRQ_PER_ICS; i++) { struct ics_irq_state *state = &ics->irq_state[i]; - - if (!state->resend) - continue; - - arch_spin_unlock(&ics->lock); - icp_rm_deliver_irq(xics, icp, state->number); - arch_spin_lock(&ics->lock); + if (state->resend) + icp_rm_deliver_irq(xics, icp, state->number, true); } - arch_spin_unlock(&ics->lock); } /* -- ICP routines -- */ @@ -288,7 +280,7 @@ static bool icp_rm_try_to_deliver(struct kvmppc_icp *icp, u32 irq, u8 priority, } static void icp_rm_deliver_irq(struct kvmppc_xics *xics, struct kvmppc_icp *icp, - u32 new_irq) + u32 new_irq, bool check_resend) { struct ics_irq_state *state; struct kvmppc_ics *ics; @@ -333,6 +325,10 @@ static void icp_rm_deliver_irq(struct kvmppc_xics *xics, struct kvmppc_icp *icp, } } + if (check_resend) + if (!state->resend) + goto out; + /* Clear the resend bit of that interrupt */ state->resend = 0; @@ -378,7 +374,9 @@ static void icp_rm_deliver_irq(struct kvmppc_xics *xics, struct kvmppc_icp *icp, */ if (reject && reject != XICS_IPI) { arch_spin_unlock(&ics->lock); + icp->n_reject++; new_irq = reject; + check_resend = 0; goto again; } } else { @@ -386,10 +384,16 @@ static void icp_rm_deliver_irq(struct kvmppc_xics *xics, struct kvmppc_icp *icp, * We failed to deliver the interrupt we need to set the * resend map bit and mark the ICS state as needing a resend */ - set_bit(ics->icsid, icp->resend_map); state->resend = 1; /* + * Make sure when checking resend, we don't miss the resend + * if resend_map bit is seen and cleared. + */ + smp_wmb(); + set_bit(ics->icsid, icp->resend_map); + + /* * If the need_resend flag got cleared in the ICP some time * between icp_rm_try_to_deliver() atomic update and now, then * we know it might have missed the resend_map bit. So we @@ -397,7 +401,9 @@ static void icp_rm_deliver_irq(struct kvmppc_xics *xics, struct kvmppc_icp *icp, */ smp_mb(); if (!icp->state.need_resend) { + state->resend = 0; arch_spin_unlock(&ics->lock); + check_resend = 0; goto again; } } @@ -592,7 +598,7 @@ int kvmppc_rm_h_ipi(struct kvm_vcpu *vcpu, unsigned long server, /* Handle reject in real mode */ if (reject && reject != XICS_IPI) { this_icp->n_reject++; - icp_rm_deliver_irq(xics, icp, reject); + icp_rm_deliver_irq(xics, icp, reject, false); } /* Handle resends in real mode */ @@ -660,59 +666,45 @@ int kvmppc_rm_h_cppr(struct kvm_vcpu *vcpu, unsigned long cppr) */ if (reject && reject != XICS_IPI) { icp->n_reject++; - icp_rm_deliver_irq(xics, icp, reject); + icp_rm_deliver_irq(xics, icp, reject, false); } bail: return check_too_hard(xics, icp); } -int kvmppc_rm_h_eoi(struct kvm_vcpu *vcpu, unsigned long xirr) +static int ics_rm_eoi(struct kvm_vcpu *vcpu, u32 irq) { struct kvmppc_xics *xics = vcpu->kvm->arch.xics; struct kvmppc_icp *icp = vcpu->arch.icp; struct kvmppc_ics *ics; struct ics_irq_state *state; - u32 irq = xirr & 0x00ffffff; u16 src; - - if (!xics || !xics->real_mode) - return H_TOO_HARD; + u32 pq_old, pq_new; /* - * ICP State: EOI + * ICS EOI handling: For LSI, if P bit is still set, we need to + * resend it. * - * Note: If EOI is incorrectly used by SW to lower the CPPR - * value (ie more favored), we do not check for rejection of - * a pending interrupt, this is a SW error and PAPR sepcifies - * that we don't have to deal with it. - * - * The sending of an EOI to the ICS is handled after the - * CPPR update - * - * ICP State: Down_CPPR which we handle - * in a separate function as it's shared with H_CPPR. + * For MSI, we move Q bit into P (and clear Q). If it is set, + * resend it. */ - icp_rm_down_cppr(xics, icp, xirr >> 24); - /* IPIs have no EOI */ - if (irq == XICS_IPI) - goto bail; - /* - * EOI handling: If the interrupt is still asserted, we need to - * resend it. We can take a lockless "peek" at the ICS state here. - * - * "Message" interrupts will never have "asserted" set - */ ics = kvmppc_xics_find_ics(xics, irq, &src); if (!ics) goto bail; + state = &ics->irq_state[src]; - /* Still asserted, resend it */ - if (state->asserted) { - icp->n_reject++; - icp_rm_deliver_irq(xics, icp, irq); - } + if (state->lsi) + pq_new = state->pq_state; + else + do { + pq_old = state->pq_state; + pq_new = pq_old >> 1; + } while (cmpxchg(&state->pq_state, pq_old, pq_new) != pq_old); + + if (pq_new & PQ_PRESENTED) + icp_rm_deliver_irq(xics, NULL, irq, false); if (!hlist_empty(&vcpu->kvm->irq_ack_notifier_list)) { icp->rm_action |= XICS_RM_NOTIFY_EOI; @@ -733,10 +725,43 @@ int kvmppc_rm_h_eoi(struct kvm_vcpu *vcpu, unsigned long xirr) state->intr_cpu = -1; } } + bail: return check_too_hard(xics, icp); } +int kvmppc_rm_h_eoi(struct kvm_vcpu *vcpu, unsigned long xirr) +{ + struct kvmppc_xics *xics = vcpu->kvm->arch.xics; + struct kvmppc_icp *icp = vcpu->arch.icp; + u32 irq = xirr & 0x00ffffff; + + if (!xics || !xics->real_mode) + return H_TOO_HARD; + + /* + * ICP State: EOI + * + * Note: If EOI is incorrectly used by SW to lower the CPPR + * value (ie more favored), we do not check for rejection of + * a pending interrupt, this is a SW error and PAPR specifies + * that we don't have to deal with it. + * + * The sending of an EOI to the ICS is handled after the + * CPPR update + * + * ICP State: Down_CPPR which we handle + * in a separate function as it's shared with H_CPPR. + */ + icp_rm_down_cppr(xics, icp, xirr >> 24); + + /* IPIs have no EOI */ + if (irq == XICS_IPI) + return check_too_hard(xics, icp); + + return ics_rm_eoi(vcpu, irq); +} + unsigned long eoi_rc; static void icp_eoi(struct irq_chip *c, u32 hwirq, __be32 xirr, bool *again) @@ -823,14 +848,33 @@ long kvmppc_deliver_irq_passthru(struct kvm_vcpu *vcpu, { struct kvmppc_xics *xics; struct kvmppc_icp *icp; + struct kvmppc_ics *ics; + struct ics_irq_state *state; u32 irq; + u16 src; + u32 pq_old, pq_new; irq = irq_map->v_hwirq; xics = vcpu->kvm->arch.xics; icp = vcpu->arch.icp; kvmppc_rm_handle_irq_desc(irq_map->desc); - icp_rm_deliver_irq(xics, icp, irq); + + ics = kvmppc_xics_find_ics(xics, irq, &src); + if (!ics) + return 2; + + state = &ics->irq_state[src]; + + /* only MSIs register bypass producers, so it must be MSI here */ + do { + pq_old = state->pq_state; + pq_new = ((pq_old << 1) & 3) | PQ_PRESENTED; + } while (cmpxchg(&state->pq_state, pq_old, pq_new) != pq_old); + + /* Test P=1, Q=0, this is the only case where we present */ + if (pq_new == PQ_PRESENTED) + icp_rm_deliver_irq(xics, icp, irq, false); /* EOI the interrupt */ icp_eoi(irq_desc_get_chip(irq_map->desc), irq_map->r_hwirq, xirr, diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c index 1482961ceb4d..d4dfc0ca2a44 100644 --- a/arch/powerpc/kvm/book3s_pr.c +++ b/arch/powerpc/kvm/book3s_pr.c @@ -902,6 +902,69 @@ static void kvmppc_clear_debug(struct kvm_vcpu *vcpu) } } +static int kvmppc_exit_pr_progint(struct kvm_run *run, struct kvm_vcpu *vcpu, + unsigned int exit_nr) +{ + enum emulation_result er; + ulong flags; + u32 last_inst; + int emul, r; + + /* + * shadow_srr1 only contains valid flags if we came here via a program + * exception. The other exceptions (emulation assist, FP unavailable, + * etc.) do not provide flags in SRR1, so use an illegal-instruction + * exception when injecting a program interrupt into the guest. + */ + if (exit_nr == BOOK3S_INTERRUPT_PROGRAM) + flags = vcpu->arch.shadow_srr1 & 0x1f0000ull; + else + flags = SRR1_PROGILL; + + emul = kvmppc_get_last_inst(vcpu, INST_GENERIC, &last_inst); + if (emul != EMULATE_DONE) + return RESUME_GUEST; + + if (kvmppc_get_msr(vcpu) & MSR_PR) { +#ifdef EXIT_DEBUG + pr_info("Userspace triggered 0x700 exception at\n 0x%lx (0x%x)\n", + kvmppc_get_pc(vcpu), last_inst); +#endif + if ((last_inst & 0xff0007ff) != (INS_DCBZ & 0xfffffff7)) { + kvmppc_core_queue_program(vcpu, flags); + return RESUME_GUEST; + } + } + + vcpu->stat.emulated_inst_exits++; + er = kvmppc_emulate_instruction(run, vcpu); + switch (er) { + case EMULATE_DONE: + r = RESUME_GUEST_NV; + break; + case EMULATE_AGAIN: + r = RESUME_GUEST; + break; + case EMULATE_FAIL: + pr_crit("%s: emulation at %lx failed (%08x)\n", + __func__, kvmppc_get_pc(vcpu), last_inst); + kvmppc_core_queue_program(vcpu, flags); + r = RESUME_GUEST; + break; + case EMULATE_DO_MMIO: + run->exit_reason = KVM_EXIT_MMIO; + r = RESUME_HOST_NV; + break; + case EMULATE_EXIT_USER: + r = RESUME_HOST_NV; + break; + default: + BUG(); + } + + return r; +} + int kvmppc_handle_exit_pr(struct kvm_run *run, struct kvm_vcpu *vcpu, unsigned int exit_nr) { @@ -1044,71 +1107,8 @@ int kvmppc_handle_exit_pr(struct kvm_run *run, struct kvm_vcpu *vcpu, break; case BOOK3S_INTERRUPT_PROGRAM: case BOOK3S_INTERRUPT_H_EMUL_ASSIST: - { - enum emulation_result er; - ulong flags; - u32 last_inst; - int emul; - -program_interrupt: - /* - * shadow_srr1 only contains valid flags if we came here via - * a program exception. The other exceptions (emulation assist, - * FP unavailable, etc.) do not provide flags in SRR1, so use - * an illegal-instruction exception when injecting a program - * interrupt into the guest. - */ - if (exit_nr == BOOK3S_INTERRUPT_PROGRAM) - flags = vcpu->arch.shadow_srr1 & 0x1f0000ull; - else - flags = SRR1_PROGILL; - - emul = kvmppc_get_last_inst(vcpu, INST_GENERIC, &last_inst); - if (emul != EMULATE_DONE) { - r = RESUME_GUEST; - break; - } - - if (kvmppc_get_msr(vcpu) & MSR_PR) { -#ifdef EXIT_DEBUG - pr_info("Userspace triggered 0x700 exception at\n 0x%lx (0x%x)\n", - kvmppc_get_pc(vcpu), last_inst); -#endif - if ((last_inst & 0xff0007ff) != - (INS_DCBZ & 0xfffffff7)) { - kvmppc_core_queue_program(vcpu, flags); - r = RESUME_GUEST; - break; - } - } - - vcpu->stat.emulated_inst_exits++; - er = kvmppc_emulate_instruction(run, vcpu); - switch (er) { - case EMULATE_DONE: - r = RESUME_GUEST_NV; - break; - case EMULATE_AGAIN: - r = RESUME_GUEST; - break; - case EMULATE_FAIL: - printk(KERN_CRIT "%s: emulation at %lx failed (%08x)\n", - __func__, kvmppc_get_pc(vcpu), last_inst); - kvmppc_core_queue_program(vcpu, flags); - r = RESUME_GUEST; - break; - case EMULATE_DO_MMIO: - run->exit_reason = KVM_EXIT_MMIO; - r = RESUME_HOST_NV; - break; - case EMULATE_EXIT_USER: - r = RESUME_HOST_NV; - break; - default: - BUG(); - } + r = kvmppc_exit_pr_progint(run, vcpu, exit_nr); break; - } case BOOK3S_INTERRUPT_SYSCALL: { u32 last_sc; @@ -1185,7 +1185,7 @@ program_interrupt: emul = kvmppc_get_last_inst(vcpu, INST_GENERIC, &last_inst); if (emul == EMULATE_DONE) - goto program_interrupt; + r = kvmppc_exit_pr_progint(run, vcpu, exit_nr); else r = RESUME_GUEST; diff --git a/arch/powerpc/kvm/book3s_xics.c b/arch/powerpc/kvm/book3s_xics.c index 20dff102a06f..e48803e2918d 100644 --- a/arch/powerpc/kvm/book3s_xics.c +++ b/arch/powerpc/kvm/book3s_xics.c @@ -63,7 +63,7 @@ /* -- ICS routines -- */ static void icp_deliver_irq(struct kvmppc_xics *xics, struct kvmppc_icp *icp, - u32 new_irq); + u32 new_irq, bool check_resend); /* * Return value ideally indicates how the interrupt was handled, but no @@ -75,6 +75,7 @@ static int ics_deliver_irq(struct kvmppc_xics *xics, u32 irq, u32 level) struct ics_irq_state *state; struct kvmppc_ics *ics; u16 src; + u32 pq_old, pq_new; XICS_DBG("ics deliver %#x (level: %d)\n", irq, level); @@ -87,25 +88,41 @@ static int ics_deliver_irq(struct kvmppc_xics *xics, u32 irq, u32 level) if (!state->exists) return -EINVAL; + if (level == KVM_INTERRUPT_SET_LEVEL || level == KVM_INTERRUPT_SET) + level = 1; + else if (level == KVM_INTERRUPT_UNSET) + level = 0; /* - * We set state->asserted locklessly. This should be fine as - * we are the only setter, thus concurrent access is undefined - * to begin with. + * Take other values the same as 1, consistent with original code. + * maybe WARN here? */ - if ((level == 1 && state->lsi) || level == KVM_INTERRUPT_SET_LEVEL) - state->asserted = 1; - else if (level == 0 || level == KVM_INTERRUPT_UNSET) { - state->asserted = 0; + + if (!state->lsi && level == 0) /* noop for MSI */ return 0; - } + + do { + pq_old = state->pq_state; + if (state->lsi) { + if (level) { + if (pq_old & PQ_PRESENTED) + /* Setting already set LSI ... */ + return 0; + + pq_new = PQ_PRESENTED; + } else + pq_new = 0; + } else + pq_new = ((pq_old << 1) & 3) | PQ_PRESENTED; + } while (cmpxchg(&state->pq_state, pq_old, pq_new) != pq_old); + + /* Test P=1, Q=0, this is the only case where we present */ + if (pq_new == PQ_PRESENTED) + icp_deliver_irq(xics, NULL, irq, false); /* Record which CPU this arrived on for passed-through interrupts */ if (state->host_irq) state->intr_cpu = raw_smp_processor_id(); - /* Attempt delivery */ - icp_deliver_irq(xics, NULL, irq); - return 0; } @@ -114,29 +131,14 @@ static void ics_check_resend(struct kvmppc_xics *xics, struct kvmppc_ics *ics, { int i; - unsigned long flags; - - local_irq_save(flags); - arch_spin_lock(&ics->lock); - for (i = 0; i < KVMPPC_XICS_IRQ_PER_ICS; i++) { struct ics_irq_state *state = &ics->irq_state[i]; - - if (!state->resend) - continue; - - XICS_DBG("resend %#x prio %#x\n", state->number, - state->priority); - - arch_spin_unlock(&ics->lock); - local_irq_restore(flags); - icp_deliver_irq(xics, icp, state->number); - local_irq_save(flags); - arch_spin_lock(&ics->lock); + if (state->resend) { + XICS_DBG("resend %#x prio %#x\n", state->number, + state->priority); + icp_deliver_irq(xics, icp, state->number, true); + } } - - arch_spin_unlock(&ics->lock); - local_irq_restore(flags); } static bool write_xive(struct kvmppc_xics *xics, struct kvmppc_ics *ics, @@ -155,6 +157,7 @@ static bool write_xive(struct kvmppc_xics *xics, struct kvmppc_ics *ics, deliver = false; if ((state->masked_pending || state->resend) && priority != MASKED) { state->masked_pending = 0; + state->resend = 0; deliver = true; } @@ -189,7 +192,7 @@ int kvmppc_xics_set_xive(struct kvm *kvm, u32 irq, u32 server, u32 priority) state->masked_pending, state->resend); if (write_xive(xics, ics, state, server, priority, priority)) - icp_deliver_irq(xics, icp, irq); + icp_deliver_irq(xics, icp, irq, false); return 0; } @@ -242,7 +245,7 @@ int kvmppc_xics_int_on(struct kvm *kvm, u32 irq) if (write_xive(xics, ics, state, state->server, state->saved_priority, state->saved_priority)) - icp_deliver_irq(xics, icp, irq); + icp_deliver_irq(xics, icp, irq, false); return 0; } @@ -376,7 +379,7 @@ static bool icp_try_to_deliver(struct kvmppc_icp *icp, u32 irq, u8 priority, } static void icp_deliver_irq(struct kvmppc_xics *xics, struct kvmppc_icp *icp, - u32 new_irq) + u32 new_irq, bool check_resend) { struct ics_irq_state *state; struct kvmppc_ics *ics; @@ -422,6 +425,10 @@ static void icp_deliver_irq(struct kvmppc_xics *xics, struct kvmppc_icp *icp, } } + if (check_resend) + if (!state->resend) + goto out; + /* Clear the resend bit of that interrupt */ state->resend = 0; @@ -470,6 +477,7 @@ static void icp_deliver_irq(struct kvmppc_xics *xics, struct kvmppc_icp *icp, arch_spin_unlock(&ics->lock); local_irq_restore(flags); new_irq = reject; + check_resend = 0; goto again; } } else { @@ -477,10 +485,16 @@ static void icp_deliver_irq(struct kvmppc_xics *xics, struct kvmppc_icp *icp, * We failed to deliver the interrupt we need to set the * resend map bit and mark the ICS state as needing a resend */ - set_bit(ics->icsid, icp->resend_map); state->resend = 1; /* + * Make sure when checking resend, we don't miss the resend + * if resend_map bit is seen and cleared. + */ + smp_wmb(); + set_bit(ics->icsid, icp->resend_map); + + /* * If the need_resend flag got cleared in the ICP some time * between icp_try_to_deliver() atomic update and now, then * we know it might have missed the resend_map bit. So we @@ -488,8 +502,10 @@ static void icp_deliver_irq(struct kvmppc_xics *xics, struct kvmppc_icp *icp, */ smp_mb(); if (!icp->state.need_resend) { + state->resend = 0; arch_spin_unlock(&ics->lock); local_irq_restore(flags); + check_resend = 0; goto again; } } @@ -681,7 +697,7 @@ static noinline int kvmppc_h_ipi(struct kvm_vcpu *vcpu, unsigned long server, /* Handle reject */ if (reject && reject != XICS_IPI) - icp_deliver_irq(xics, icp, reject); + icp_deliver_irq(xics, icp, reject, false); /* Handle resend */ if (resend) @@ -761,17 +777,54 @@ static noinline void kvmppc_h_cppr(struct kvm_vcpu *vcpu, unsigned long cppr) * attempt (see comments in icp_deliver_irq). */ if (reject && reject != XICS_IPI) - icp_deliver_irq(xics, icp, reject); + icp_deliver_irq(xics, icp, reject, false); } -static noinline int kvmppc_h_eoi(struct kvm_vcpu *vcpu, unsigned long xirr) +static int ics_eoi(struct kvm_vcpu *vcpu, u32 irq) { struct kvmppc_xics *xics = vcpu->kvm->arch.xics; struct kvmppc_icp *icp = vcpu->arch.icp; struct kvmppc_ics *ics; struct ics_irq_state *state; - u32 irq = xirr & 0x00ffffff; u16 src; + u32 pq_old, pq_new; + + /* + * ICS EOI handling: For LSI, if P bit is still set, we need to + * resend it. + * + * For MSI, we move Q bit into P (and clear Q). If it is set, + * resend it. + */ + + ics = kvmppc_xics_find_ics(xics, irq, &src); + if (!ics) { + XICS_DBG("ios_eoi: IRQ 0x%06x not found !\n", irq); + return H_PARAMETER; + } + state = &ics->irq_state[src]; + + if (state->lsi) + pq_new = state->pq_state; + else + do { + pq_old = state->pq_state; + pq_new = pq_old >> 1; + } while (cmpxchg(&state->pq_state, pq_old, pq_new) != pq_old); + + if (pq_new & PQ_PRESENTED) + icp_deliver_irq(xics, icp, irq, false); + + kvm_notify_acked_irq(vcpu->kvm, 0, irq); + + return H_SUCCESS; +} + +static noinline int kvmppc_h_eoi(struct kvm_vcpu *vcpu, unsigned long xirr) +{ + struct kvmppc_xics *xics = vcpu->kvm->arch.xics; + struct kvmppc_icp *icp = vcpu->arch.icp; + u32 irq = xirr & 0x00ffffff; XICS_DBG("h_eoi vcpu %d eoi %#lx\n", vcpu->vcpu_id, xirr); @@ -794,26 +847,8 @@ static noinline int kvmppc_h_eoi(struct kvm_vcpu *vcpu, unsigned long xirr) /* IPIs have no EOI */ if (irq == XICS_IPI) return H_SUCCESS; - /* - * EOI handling: If the interrupt is still asserted, we need to - * resend it. We can take a lockless "peek" at the ICS state here. - * - * "Message" interrupts will never have "asserted" set - */ - ics = kvmppc_xics_find_ics(xics, irq, &src); - if (!ics) { - XICS_DBG("h_eoi: IRQ 0x%06x not found !\n", irq); - return H_PARAMETER; - } - state = &ics->irq_state[src]; - /* Still asserted, resend it */ - if (state->asserted) - icp_deliver_irq(xics, icp, irq); - - kvm_notify_acked_irq(vcpu->kvm, 0, irq); - - return H_SUCCESS; + return ics_eoi(vcpu, irq); } int kvmppc_xics_rm_complete(struct kvm_vcpu *vcpu, u32 hcall) @@ -832,10 +867,6 @@ int kvmppc_xics_rm_complete(struct kvm_vcpu *vcpu, u32 hcall) icp->n_rm_check_resend++; icp_check_resend(xics, icp->rm_resend_icp); } - if (icp->rm_action & XICS_RM_REJECT) { - icp->n_rm_reject++; - icp_deliver_irq(xics, icp, icp->rm_reject); - } if (icp->rm_action & XICS_RM_NOTIFY_EOI) { icp->n_rm_notify_eoi++; kvm_notify_acked_irq(vcpu->kvm, 0, icp->rm_eoied_irq); @@ -920,7 +951,7 @@ static int xics_debug_show(struct seq_file *m, void *private) int icsid, i; unsigned long flags; unsigned long t_rm_kick_vcpu, t_rm_check_resend; - unsigned long t_rm_reject, t_rm_notify_eoi; + unsigned long t_rm_notify_eoi; unsigned long t_reject, t_check_resend; if (!kvm) @@ -929,7 +960,6 @@ static int xics_debug_show(struct seq_file *m, void *private) t_rm_kick_vcpu = 0; t_rm_notify_eoi = 0; t_rm_check_resend = 0; - t_rm_reject = 0; t_check_resend = 0; t_reject = 0; @@ -952,14 +982,13 @@ static int xics_debug_show(struct seq_file *m, void *private) t_rm_kick_vcpu += icp->n_rm_kick_vcpu; t_rm_notify_eoi += icp->n_rm_notify_eoi; t_rm_check_resend += icp->n_rm_check_resend; - t_rm_reject += icp->n_rm_reject; t_check_resend += icp->n_check_resend; t_reject += icp->n_reject; } - seq_printf(m, "ICP Guest->Host totals: kick_vcpu=%lu check_resend=%lu reject=%lu notify_eoi=%lu\n", + seq_printf(m, "ICP Guest->Host totals: kick_vcpu=%lu check_resend=%lu notify_eoi=%lu\n", t_rm_kick_vcpu, t_rm_check_resend, - t_rm_reject, t_rm_notify_eoi); + t_rm_notify_eoi); seq_printf(m, "ICP Real Mode totals: check_resend=%lu resend=%lu\n", t_check_resend, t_reject); for (icsid = 0; icsid <= KVMPPC_XICS_MAX_ICS_ID; icsid++) { @@ -977,9 +1006,9 @@ static int xics_debug_show(struct seq_file *m, void *private) for (i = 0; i < KVMPPC_XICS_IRQ_PER_ICS; i++) { struct ics_irq_state *irq = &ics->irq_state[i]; - seq_printf(m, "irq 0x%06x: server %#x prio %#x save prio %#x asserted %d resend %d masked pending %d\n", + seq_printf(m, "irq 0x%06x: server %#x prio %#x save prio %#x pq_state %d resend %d masked pending %d\n", irq->number, irq->server, irq->priority, - irq->saved_priority, irq->asserted, + irq->saved_priority, irq->pq_state, irq->resend, irq->masked_pending); } @@ -1198,10 +1227,17 @@ static int xics_get_source(struct kvmppc_xics *xics, long irq, u64 addr) val |= prio << KVM_XICS_PRIORITY_SHIFT; if (irqp->lsi) { val |= KVM_XICS_LEVEL_SENSITIVE; - if (irqp->asserted) + if (irqp->pq_state & PQ_PRESENTED) val |= KVM_XICS_PENDING; } else if (irqp->masked_pending || irqp->resend) val |= KVM_XICS_PENDING; + + if (irqp->pq_state & PQ_PRESENTED) + val |= KVM_XICS_PRESENTED; + + if (irqp->pq_state & PQ_QUEUED) + val |= KVM_XICS_QUEUED; + ret = 0; } arch_spin_unlock(&ics->lock); @@ -1253,18 +1289,20 @@ static int xics_set_source(struct kvmppc_xics *xics, long irq, u64 addr) irqp->resend = 0; irqp->masked_pending = 0; irqp->lsi = 0; - irqp->asserted = 0; - if (val & KVM_XICS_LEVEL_SENSITIVE) { + irqp->pq_state = 0; + if (val & KVM_XICS_LEVEL_SENSITIVE) irqp->lsi = 1; - if (val & KVM_XICS_PENDING) - irqp->asserted = 1; - } + /* If PENDING, set P in case P is not saved because of old code */ + if (val & KVM_XICS_PRESENTED || val & KVM_XICS_PENDING) + irqp->pq_state |= PQ_PRESENTED; + if (val & KVM_XICS_QUEUED) + irqp->pq_state |= PQ_QUEUED; irqp->exists = 1; arch_spin_unlock(&ics->lock); local_irq_restore(flags); if (val & KVM_XICS_PENDING) - icp_deliver_irq(xics, NULL, irqp->number); + icp_deliver_irq(xics, NULL, irqp->number, false); return 0; } diff --git a/arch/powerpc/kvm/book3s_xics.h b/arch/powerpc/kvm/book3s_xics.h index 2a50320b55ca..ec5474cf70c6 100644 --- a/arch/powerpc/kvm/book3s_xics.h +++ b/arch/powerpc/kvm/book3s_xics.h @@ -31,16 +31,19 @@ /* Priority value to use for disabling an interrupt */ #define MASKED 0xff +#define PQ_PRESENTED 1 +#define PQ_QUEUED 2 + /* State for one irq source */ struct ics_irq_state { u32 number; u32 server; + u32 pq_state; u8 priority; u8 saved_priority; u8 resend; u8 masked_pending; u8 lsi; /* level-sensitive interrupt */ - u8 asserted; /* Only for LSI */ u8 exists; int intr_cpu; u32 host_irq; @@ -73,7 +76,6 @@ struct kvmppc_icp { */ #define XICS_RM_KICK_VCPU 0x1 #define XICS_RM_CHECK_RESEND 0x2 -#define XICS_RM_REJECT 0x4 #define XICS_RM_NOTIFY_EOI 0x8 u32 rm_action; struct kvm_vcpu *rm_kick_target; @@ -84,7 +86,6 @@ struct kvmppc_icp { /* Counters for each reason we exited real mode */ unsigned long n_rm_kick_vcpu; unsigned long n_rm_check_resend; - unsigned long n_rm_reject; unsigned long n_rm_notify_eoi; /* Counters for handling ICP processing in real mode */ unsigned long n_check_resend; diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 40a5b2d75ed1..2b38d824e9e5 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -511,6 +511,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_ONE_REG: case KVM_CAP_IOEVENTFD: case KVM_CAP_DEVICE_CTRL: + case KVM_CAP_IMMEDIATE_EXIT: r = 1; break; case KVM_CAP_PPC_PAIRED_SINGLES: @@ -612,6 +613,10 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_SPAPR_MULTITCE: r = 1; break; + case KVM_CAP_SPAPR_RESIZE_HPT: + /* Disable this on POWER9 until code handles new HPTE format */ + r = !!hv_enabled && !cpu_has_feature(CPU_FTR_ARCH_300); + break; #endif case KVM_CAP_PPC_HTM: r = cpu_has_feature(CPU_FTR_TM_COMP) && @@ -1114,7 +1119,10 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run) #endif } - r = kvmppc_vcpu_run(run, vcpu); + if (run->immediate_exit) + r = -EINTR; + else + r = kvmppc_vcpu_run(run, vcpu); if (vcpu->sigset_active) sigprocmask(SIG_SETMASK, &sigsaved, NULL); diff --git a/arch/powerpc/lib/code-patching.c b/arch/powerpc/lib/code-patching.c index 0899315e1434..0d3002b7e2b4 100644 --- a/arch/powerpc/lib/code-patching.c +++ b/arch/powerpc/lib/code-patching.c @@ -14,6 +14,7 @@ #include <asm/page.h> #include <asm/code-patching.h> #include <linux/uaccess.h> +#include <linux/kprobes.h> int patch_instruction(unsigned int *addr, unsigned int instr) diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c index c636137666c1..8dc758658972 100644 --- a/arch/powerpc/mm/fault.c +++ b/arch/powerpc/mm/fault.c @@ -253,8 +253,11 @@ int do_page_fault(struct pt_regs *regs, unsigned long address, if (unlikely(debugger_fault_handler(regs))) goto bail; - /* On a kernel SLB miss we can only check for a valid exception entry */ - if (!user_mode(regs) && (address >= TASK_SIZE)) { + /* + * The kernel should never take an execute fault nor should it + * take a page fault to a kernel address. + */ + if (!user_mode(regs) && (is_exec || (address >= TASK_SIZE))) { rc = SIGSEGV; goto bail; } @@ -391,20 +394,6 @@ good_area: if (is_exec) { /* - * An execution fault + no execute ? - * - * On CPUs that don't have CPU_FTR_COHERENT_ICACHE we - * deliberately create NX mappings, and use the fault to do the - * cache flush. This is usually handled in hash_page_do_lazy_icache() - * but we could end up here if that races with a concurrent PTE - * update. In that case we need to fall through here to the VMA - * check below. - */ - if (cpu_has_feature(CPU_FTR_COHERENT_ICACHE) && - (regs->msr & SRR1_ISI_N_OR_G)) - goto bad_area; - - /* * Allow execution from readable areas if the MMU does not * provide separate controls over reading and executing. * diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c index 10c9a545a646..6aa3b76aa0d6 100644 --- a/arch/powerpc/mm/init_64.c +++ b/arch/powerpc/mm/init_64.c @@ -373,7 +373,8 @@ static void early_check_vec5(void) void __init mmu_early_init_devtree(void) { /* Disable radix mode based on kernel command line. */ - if (disable_radix) + /* We don't yet have the machinery to do radix as a guest. */ + if (disable_radix || !(mfmsr() & MSR_HV)) cur_cpu_spec->mmu_features &= ~MMU_FTR_TYPE_RADIX; /* diff --git a/arch/powerpc/mm/pgtable-radix.c b/arch/powerpc/mm/pgtable-radix.c index de81b5e3b2f2..feeda90cd06d 100644 --- a/arch/powerpc/mm/pgtable-radix.c +++ b/arch/powerpc/mm/pgtable-radix.c @@ -66,7 +66,7 @@ int radix__map_kernel_page(unsigned long ea, unsigned long pa, if (!pmdp) return -ENOMEM; if (map_page_size == PMD_SIZE) { - ptep = (pte_t *)pudp; + ptep = pmdp_ptep(pmdp); goto set_the_pte; } ptep = pte_alloc_kernel(pmdp, ea); @@ -91,7 +91,7 @@ int radix__map_kernel_page(unsigned long ea, unsigned long pa, } pmdp = pmd_offset(pudp, ea); if (map_page_size == PMD_SIZE) { - ptep = (pte_t *)pudp; + ptep = pmdp_ptep(pmdp); goto set_the_pte; } if (!pmd_present(*pmdp)) { diff --git a/arch/powerpc/mm/tlb-radix.c b/arch/powerpc/mm/tlb-radix.c index 61b79119065f..952713d6cf04 100644 --- a/arch/powerpc/mm/tlb-radix.c +++ b/arch/powerpc/mm/tlb-radix.c @@ -50,9 +50,7 @@ static inline void _tlbiel_pid(unsigned long pid, unsigned long ric) for (set = 0; set < POWER9_TLB_SETS_RADIX ; set++) { __tlbiel_pid(pid, set, ric); } - if (cpu_has_feature(CPU_FTR_POWER9_DD1)) - asm volatile(PPC_INVALIDATE_ERAT : : :"memory"); - return; + asm volatile(PPC_INVALIDATE_ERAT "; isync" : : :"memory"); } static inline void _tlbie_pid(unsigned long pid, unsigned long ric) @@ -85,8 +83,6 @@ static inline void _tlbiel_va(unsigned long va, unsigned long pid, asm volatile(PPC_TLBIEL(%0, %4, %3, %2, %1) : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory"); asm volatile("ptesync": : :"memory"); - if (cpu_has_feature(CPU_FTR_POWER9_DD1)) - asm volatile(PPC_INVALIDATE_ERAT : : :"memory"); } static inline void _tlbie_va(unsigned long va, unsigned long pid, diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c index d4ed7a0872b1..aee2bb817ac6 100644 --- a/arch/powerpc/net/bpf_jit_comp64.c +++ b/arch/powerpc/net/bpf_jit_comp64.c @@ -961,8 +961,6 @@ common_load: return 0; } -void bpf_jit_compile(struct bpf_prog *fp) { } - struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp) { u32 proglen; @@ -1066,6 +1064,7 @@ out: return fp; } +/* Overriding bpf_jit_free() as we don't set images read-only. */ void bpf_jit_free(struct bpf_prog *fp) { unsigned long addr = (unsigned long)fp->bpf_func & PAGE_MASK; diff --git a/arch/powerpc/platforms/cell/iommu.c b/arch/powerpc/platforms/cell/iommu.c index 7ff51f96a00e..71b995bbcae0 100644 --- a/arch/powerpc/platforms/cell/iommu.c +++ b/arch/powerpc/platforms/cell/iommu.c @@ -651,7 +651,7 @@ static int dma_fixed_dma_supported(struct device *dev, u64 mask) static int dma_set_mask_and_switch(struct device *dev, u64 dma_mask); -static struct dma_map_ops dma_iommu_fixed_ops = { +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, @@ -692,7 +692,7 @@ static int cell_of_bus_notify(struct notifier_block *nb, unsigned long action, return 0; /* We use the PCI DMA ops */ - dev->archdata.dma_ops = get_pci_dma_ops(); + dev->dma_ops = get_pci_dma_ops(); cell_dma_dev_setup(dev); @@ -1172,7 +1172,7 @@ __setup("iommu_fixed=", setup_iommu_fixed); static u64 cell_dma_get_required_mask(struct device *dev) { - struct dma_map_ops *dma_ops; + const struct dma_map_ops *dma_ops; if (!dev->dma_mask) return 0; diff --git a/arch/powerpc/platforms/cell/spufs/file.c b/arch/powerpc/platforms/cell/spufs/file.c index 03f2cdfabf23..ae2f740a82f1 100644 --- a/arch/powerpc/platforms/cell/spufs/file.c +++ b/arch/powerpc/platforms/cell/spufs/file.c @@ -233,8 +233,9 @@ spufs_mem_write(struct file *file, const char __user *buffer, } static int -spufs_mem_mmap_fault(struct vm_area_struct *vma, struct vm_fault *vmf) +spufs_mem_mmap_fault(struct vm_fault *vmf) { + struct vm_area_struct *vma = vmf->vma; struct spu_context *ctx = vma->vm_file->private_data; unsigned long pfn, offset; @@ -311,12 +312,11 @@ static const struct file_operations spufs_mem_fops = { .mmap = spufs_mem_mmap, }; -static int spufs_ps_fault(struct vm_area_struct *vma, - struct vm_fault *vmf, +static int spufs_ps_fault(struct vm_fault *vmf, unsigned long ps_offs, unsigned long ps_size) { - struct spu_context *ctx = vma->vm_file->private_data; + struct spu_context *ctx = vmf->vma->vm_file->private_data; unsigned long area, offset = vmf->pgoff << PAGE_SHIFT; int ret = 0; @@ -354,7 +354,7 @@ static int spufs_ps_fault(struct vm_area_struct *vma, down_read(¤t->mm->mmap_sem); } else { area = ctx->spu->problem_phys + ps_offs; - vm_insert_pfn(vma, vmf->address, (area + offset) >> PAGE_SHIFT); + vm_insert_pfn(vmf->vma, vmf->address, (area + offset) >> PAGE_SHIFT); spu_context_trace(spufs_ps_fault__insert, ctx, ctx->spu); } @@ -367,10 +367,9 @@ refault: } #if SPUFS_MMAP_4K -static int spufs_cntl_mmap_fault(struct vm_area_struct *vma, - struct vm_fault *vmf) +static int spufs_cntl_mmap_fault(struct vm_fault *vmf) { - return spufs_ps_fault(vma, vmf, 0x4000, SPUFS_CNTL_MAP_SIZE); + return spufs_ps_fault(vmf, 0x4000, SPUFS_CNTL_MAP_SIZE); } static const struct vm_operations_struct spufs_cntl_mmap_vmops = { @@ -1042,15 +1041,15 @@ static ssize_t spufs_signal1_write(struct file *file, const char __user *buf, } static int -spufs_signal1_mmap_fault(struct vm_area_struct *vma, struct vm_fault *vmf) +spufs_signal1_mmap_fault(struct vm_fault *vmf) { #if SPUFS_SIGNAL_MAP_SIZE == 0x1000 - return spufs_ps_fault(vma, vmf, 0x14000, SPUFS_SIGNAL_MAP_SIZE); + return spufs_ps_fault(vmf, 0x14000, SPUFS_SIGNAL_MAP_SIZE); #elif SPUFS_SIGNAL_MAP_SIZE == 0x10000 /* For 64k pages, both signal1 and signal2 can be used to mmap the whole * signal 1 and 2 area */ - return spufs_ps_fault(vma, vmf, 0x10000, SPUFS_SIGNAL_MAP_SIZE); + return spufs_ps_fault(vmf, 0x10000, SPUFS_SIGNAL_MAP_SIZE); #else #error unsupported page size #endif @@ -1180,15 +1179,15 @@ static ssize_t spufs_signal2_write(struct file *file, const char __user *buf, #if SPUFS_MMAP_4K static int -spufs_signal2_mmap_fault(struct vm_area_struct *vma, struct vm_fault *vmf) +spufs_signal2_mmap_fault(struct vm_fault *vmf) { #if SPUFS_SIGNAL_MAP_SIZE == 0x1000 - return spufs_ps_fault(vma, vmf, 0x1c000, SPUFS_SIGNAL_MAP_SIZE); + return spufs_ps_fault(vmf, 0x1c000, SPUFS_SIGNAL_MAP_SIZE); #elif SPUFS_SIGNAL_MAP_SIZE == 0x10000 /* For 64k pages, both signal1 and signal2 can be used to mmap the whole * signal 1 and 2 area */ - return spufs_ps_fault(vma, vmf, 0x10000, SPUFS_SIGNAL_MAP_SIZE); + return spufs_ps_fault(vmf, 0x10000, SPUFS_SIGNAL_MAP_SIZE); #else #error unsupported page size #endif @@ -1309,9 +1308,9 @@ DEFINE_SPUFS_ATTRIBUTE(spufs_signal2_type, spufs_signal2_type_get, #if SPUFS_MMAP_4K static int -spufs_mss_mmap_fault(struct vm_area_struct *vma, struct vm_fault *vmf) +spufs_mss_mmap_fault(struct vm_fault *vmf) { - return spufs_ps_fault(vma, vmf, 0x0000, SPUFS_MSS_MAP_SIZE); + return spufs_ps_fault(vmf, 0x0000, SPUFS_MSS_MAP_SIZE); } static const struct vm_operations_struct spufs_mss_mmap_vmops = { @@ -1371,9 +1370,9 @@ static const struct file_operations spufs_mss_fops = { }; static int -spufs_psmap_mmap_fault(struct vm_area_struct *vma, struct vm_fault *vmf) +spufs_psmap_mmap_fault(struct vm_fault *vmf) { - return spufs_ps_fault(vma, vmf, 0x0000, SPUFS_PS_MAP_SIZE); + return spufs_ps_fault(vmf, 0x0000, SPUFS_PS_MAP_SIZE); } static const struct vm_operations_struct spufs_psmap_mmap_vmops = { @@ -1431,9 +1430,9 @@ static const struct file_operations spufs_psmap_fops = { #if SPUFS_MMAP_4K static int -spufs_mfc_mmap_fault(struct vm_area_struct *vma, struct vm_fault *vmf) +spufs_mfc_mmap_fault(struct vm_fault *vmf) { - return spufs_ps_fault(vma, vmf, 0x3000, SPUFS_MFC_MAP_SIZE); + return spufs_ps_fault(vmf, 0x3000, SPUFS_MFC_MAP_SIZE); } static const struct vm_operations_struct spufs_mfc_mmap_vmops = { diff --git a/arch/powerpc/platforms/pasemi/iommu.c b/arch/powerpc/platforms/pasemi/iommu.c index e74adc4e7fd8..7fec04de27fc 100644 --- a/arch/powerpc/platforms/pasemi/iommu.c +++ b/arch/powerpc/platforms/pasemi/iommu.c @@ -186,7 +186,7 @@ static void pci_dma_dev_setup_pasemi(struct pci_dev *dev) */ if (dev->vendor == 0x1959 && dev->device == 0xa007 && !firmware_has_feature(FW_FEATURE_LPAR)) { - dev->dev.archdata.dma_ops = &dma_direct_ops; + dev->dev.dma_ops = &dma_direct_ops; /* * Set the coherent DMA mask to prevent the iommu * being used unnecessarily diff --git a/arch/powerpc/platforms/pasemi/setup.c b/arch/powerpc/platforms/pasemi/setup.c index 3182400cf48f..c4a3e93dc324 100644 --- a/arch/powerpc/platforms/pasemi/setup.c +++ b/arch/powerpc/platforms/pasemi/setup.c @@ -363,7 +363,7 @@ static int pcmcia_notify(struct notifier_block *nb, unsigned long action, return 0; /* We use the direct ops for localbus */ - dev->archdata.dma_ops = &dma_direct_ops; + dev->dma_ops = &dma_direct_ops; return 0; } diff --git a/arch/powerpc/platforms/powernv/npu-dma.c b/arch/powerpc/platforms/powernv/npu-dma.c index 73b155fd4481..1c383f38031d 100644 --- a/arch/powerpc/platforms/powernv/npu-dma.c +++ b/arch/powerpc/platforms/powernv/npu-dma.c @@ -115,7 +115,7 @@ static u64 dma_npu_get_required_mask(struct device *dev) return 0; } -static struct dma_map_ops dma_npu_ops = { +static const struct dma_map_ops dma_npu_ops = { .map_page = dma_npu_map_page, .map_sg = dma_npu_map_sg, .alloc = dma_npu_alloc, diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index 06c91705562e..6901a06da2f9 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -3032,7 +3032,7 @@ static void pnv_ioda_setup_pe_res(struct pnv_ioda_pe *pe, /* * This function is supposed to be called on basis of PE from top * to bottom style. So the the I/O or MMIO segment assigned to - * parent PE could be overrided by its child PEs if necessary. + * parent PE could be overridden by its child PEs if necessary. */ static void pnv_ioda_setup_pe_seg(struct pnv_ioda_pe *pe) { diff --git a/arch/powerpc/platforms/powernv/smp.c b/arch/powerpc/platforms/powernv/smp.c index 1c6405fb769a..e39e6c428af1 100644 --- a/arch/powerpc/platforms/powernv/smp.c +++ b/arch/powerpc/platforms/powernv/smp.c @@ -155,8 +155,10 @@ static void pnv_smp_cpu_kill_self(void) wmask = SRR1_WAKEMASK_P8; idle_states = pnv_get_supported_cpuidle_states(); + /* We don't want to take decrementer interrupts while we are offline, - * so clear LPCR:PECE1. We keep PECE2 enabled. + * so clear LPCR:PECE1. We keep PECE2 (and LPCR_PECE_HVEE on P9) + * enabled as to let IPIs in. */ mtspr(SPRN_LPCR, mfspr(SPRN_LPCR) & ~(u64)LPCR_PECE1); @@ -208,8 +210,12 @@ static void pnv_smp_cpu_kill_self(void) * contains 0. */ if (((srr1 & wmask) == SRR1_WAKEEE) || + ((srr1 & wmask) == SRR1_WAKEHVI) || (local_paca->irq_happened & PACA_IRQ_EE)) { - icp_native_flush_interrupt(); + if (cpu_has_feature(CPU_FTR_ARCH_300)) + icp_opal_flush_interrupt(); + else + icp_native_flush_interrupt(); } else if ((srr1 & wmask) == SRR1_WAKEHDBELL) { unsigned long msg = PPC_DBELL_TYPE(PPC_DBELL_SERVER); asm volatile(PPC_MSGCLR(%0) : : "r" (msg)); @@ -223,6 +229,8 @@ static void pnv_smp_cpu_kill_self(void) if (srr1 && !generic_check_cpu_restart(cpu)) DBG("CPU%d Unexpected exit while offline !\n", cpu); } + + /* Re-enable decrementer interrupts */ mtspr(SPRN_LPCR, mfspr(SPRN_LPCR) | LPCR_PECE1); DBG("CPU%d coming online...\n", cpu); } diff --git a/arch/powerpc/platforms/ps3/system-bus.c b/arch/powerpc/platforms/ps3/system-bus.c index 8af1c15aef85..2d2e5f80a3d3 100644 --- a/arch/powerpc/platforms/ps3/system-bus.c +++ b/arch/powerpc/platforms/ps3/system-bus.c @@ -701,7 +701,7 @@ static u64 ps3_dma_get_required_mask(struct device *_dev) return DMA_BIT_MASK(32); } -static struct dma_map_ops ps3_sb_dma_ops = { +static const struct dma_map_ops ps3_sb_dma_ops = { .alloc = ps3_alloc_coherent, .free = ps3_free_coherent, .map_sg = ps3_sb_map_sg, @@ -712,7 +712,7 @@ static struct dma_map_ops ps3_sb_dma_ops = { .unmap_page = ps3_unmap_page, }; -static struct dma_map_ops ps3_ioc0_dma_ops = { +static const struct dma_map_ops ps3_ioc0_dma_ops = { .alloc = ps3_alloc_coherent, .free = ps3_free_coherent, .map_sg = ps3_ioc0_map_sg, @@ -756,11 +756,11 @@ int ps3_system_bus_device_register(struct ps3_system_bus_device *dev) switch (dev->dev_type) { case PS3_DEVICE_TYPE_IOC0: - dev->core.archdata.dma_ops = &ps3_ioc0_dma_ops; + dev->core.dma_ops = &ps3_ioc0_dma_ops; dev_set_name(&dev->core, "ioc0_%02x", ++dev_ioc0_count); break; case PS3_DEVICE_TYPE_SB: - dev->core.archdata.dma_ops = &ps3_sb_dma_ops; + dev->core.dma_ops = &ps3_sb_dma_ops; dev_set_name(&dev->core, "sb_%02x", ++dev_sb_count); break; diff --git a/arch/powerpc/platforms/pseries/ibmebus.c b/arch/powerpc/platforms/pseries/ibmebus.c index 614c28537141..99a6bf7f3bcf 100644 --- a/arch/powerpc/platforms/pseries/ibmebus.c +++ b/arch/powerpc/platforms/pseries/ibmebus.c @@ -136,7 +136,7 @@ static u64 ibmebus_dma_get_required_mask(struct device *dev) return DMA_BIT_MASK(64); } -static struct dma_map_ops ibmebus_dma_ops = { +static const struct dma_map_ops ibmebus_dma_ops = { .alloc = ibmebus_alloc_coherent, .free = ibmebus_free_coherent, .map_sg = ibmebus_map_sg, @@ -169,7 +169,7 @@ static int ibmebus_create_device(struct device_node *dn) return -ENOMEM; dev->dev.bus = &ibmebus_bus_type; - dev->dev.archdata.dma_ops = &ibmebus_dma_ops; + dev->dev.dma_ops = &ibmebus_dma_ops; ret = of_device_add(dev); if (ret) diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c index 0024e451bb36..4d757eaa46bf 100644 --- a/arch/powerpc/platforms/pseries/iommu.c +++ b/arch/powerpc/platforms/pseries/iommu.c @@ -1020,7 +1020,7 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn) /* check largest block * page size > max memory hotplug addr */ max_addr = memory_hotplug_max(); if (query.largest_available_block < (max_addr >> page_shift)) { - dev_dbg(&dev->dev, "can't map partiton max 0x%llx with %u " + dev_dbg(&dev->dev, "can't map partition max 0x%llx with %u " "%llu-sized pages\n", max_addr, query.largest_available_block, 1ULL << page_shift); goto out_failed; diff --git a/arch/powerpc/platforms/pseries/vio.c b/arch/powerpc/platforms/pseries/vio.c index 2c8fb3ec989e..720493932486 100644 --- a/arch/powerpc/platforms/pseries/vio.c +++ b/arch/powerpc/platforms/pseries/vio.c @@ -615,7 +615,7 @@ static u64 vio_dma_get_required_mask(struct device *dev) return dma_iommu_ops.get_required_mask(dev); } -static struct dma_map_ops vio_dma_mapping_ops = { +static const struct dma_map_ops vio_dma_mapping_ops = { .alloc = vio_dma_iommu_alloc_coherent, .free = vio_dma_iommu_free_coherent, .mmap = dma_direct_mmap_coherent, diff --git a/arch/powerpc/sysdev/xics/icp-opal.c b/arch/powerpc/sysdev/xics/icp-opal.c index 60c57657c772..f9670eabfcfa 100644 --- a/arch/powerpc/sysdev/xics/icp-opal.c +++ b/arch/powerpc/sysdev/xics/icp-opal.c @@ -120,18 +120,49 @@ static void icp_opal_cause_ipi(int cpu, unsigned long data) { int hw_cpu = get_hard_smp_processor_id(cpu); + kvmppc_set_host_ipi(cpu, 1); opal_int_set_mfrr(hw_cpu, IPI_PRIORITY); } static irqreturn_t icp_opal_ipi_action(int irq, void *dev_id) { - int hw_cpu = hard_smp_processor_id(); + int cpu = smp_processor_id(); - opal_int_set_mfrr(hw_cpu, 0xff); + kvmppc_set_host_ipi(cpu, 0); + opal_int_set_mfrr(get_hard_smp_processor_id(cpu), 0xff); return smp_ipi_demux(); } +/* + * Called when an interrupt is received on an off-line CPU to + * clear the interrupt, so that the CPU can go back to nap mode. + */ +void icp_opal_flush_interrupt(void) +{ + unsigned int xirr; + unsigned int vec; + + do { + xirr = icp_opal_get_xirr(); + vec = xirr & 0x00ffffff; + if (vec == XICS_IRQ_SPURIOUS) + break; + if (vec == XICS_IPI) { + /* Clear pending IPI */ + int cpu = smp_processor_id(); + kvmppc_set_host_ipi(cpu, 0); + opal_int_set_mfrr(get_hard_smp_processor_id(cpu), 0xff); + } else { + pr_err("XICS: hw interrupt 0x%x to offline cpu, " + "disabling\n", vec); + xics_mask_unknown_vec(vec); + } + + /* EOI the interrupt */ + } while (opal_int_eoi(xirr) > 0); +} + #endif /* CONFIG_SMP */ static const struct icp_ops icp_opal_ops = { diff --git a/arch/powerpc/xmon/ppc-opc.c b/arch/powerpc/xmon/ppc-opc.c index f2a49d237b59..ac2b55b1332e 100644 --- a/arch/powerpc/xmon/ppc-opc.c +++ b/arch/powerpc/xmon/ppc-opc.c @@ -2429,7 +2429,7 @@ extract_vleil (unsigned long insn, #define CTX(op, xop) (OP (op) | (((unsigned long)(xop)) & 0x7)) #define CTX_MASK CTX(0x3f, 0x7) -/* An User Context form instruction. */ +/* A User Context form instruction. */ #define UCTX(op, xop) (OP (op) | (((unsigned long)(xop)) & 0x1f)) #define UCTX_MASK UCTX(0x3f, 0x1f) diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c index 57503cdbd76f..26fa03fc9f3c 100644 --- a/arch/powerpc/xmon/xmon.c +++ b/arch/powerpc/xmon/xmon.c @@ -920,7 +920,7 @@ cmds(struct pt_regs *excp) memzcan(); break; case 'i': - show_mem(0); + show_mem(0, NULL); break; default: termch = cmd; @@ -2291,14 +2291,14 @@ static void dump_one_paca(int cpu) DUMP(p, subcore_sibling_mask, "x"); #endif - DUMP(p, accounting.user_time, "llx"); - DUMP(p, accounting.system_time, "llx"); - DUMP(p, accounting.user_time_scaled, "llx"); + DUMP(p, accounting.utime, "llx"); + DUMP(p, accounting.stime, "llx"); + DUMP(p, accounting.utime_scaled, "llx"); DUMP(p, accounting.starttime, "llx"); DUMP(p, accounting.starttime_user, "llx"); DUMP(p, accounting.startspurr, "llx"); DUMP(p, accounting.utime_sspurr, "llx"); - DUMP(p, stolen_time, "llx"); + DUMP(p, accounting.steal_time, "llx"); #undef DUMP catch_memory_errors = 0; |
